3766 files changed, 163672 insertions, 67475 deletions

diff --git a/.cocciconfig b/.cocciconfig
new file mode 100644
index 000000000000..43967c6b2015
--- /dev/null
+++ b/.cocciconfig
@@ -0,0 +1,3 @@
+[spatch]
+	options = --timeout 200
+	options = --use-gitgrep
diff --git a/.gitignore b/.gitignore
index 0c320bf02586..c2ed4ecb0acd 100644
--- a/.gitignore
+++ b/.gitignore
@@ -37,6 +37,7 @@ modules.builtin
 Module.symvers
 *.dwo
 *.su
+*.c.[012]*.*
 
 #
 # Top-level generic files
@@ -66,6 +67,7 @@ Module.symvers
 #
 !.gitignore
 !.mailmap
+!.cocciconfig
 
 #
 # Generated include files
diff --git a/.mailmap b/.mailmap
index d2acafb09e60..c0d57049d3f0 100644
--- a/.mailmap
+++ b/.mailmap
@@ -92,6 +92,8 @@ Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com>
 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 Leonid I Ananiev <leonid.i.ananiev@intel.com>
 Linas Vepstas <linas@austin.ibm.com>
+Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
+Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
 Mark Brown <broonie@sirena.org.uk>
 Matthieu CASTET <castet.matthieu@free.fr>
 Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com> <mchehab@infradead.org> <mchehab@redhat.com> <m.chehab@samsung.com> <mchehab@osg.samsung.com> <mchehab@s-opensource.com>
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index 01bab5014a4a..8e6dd4b14314 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -16,7 +16,7 @@ DOCBOOKS := z8530book.xml device-drivers.xml \
 	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
 	    80211.xml debugobjects.xml sh.xml regulator.xml \
 	    alsa-driver-api.xml writing-an-alsa-driver.xml \
-	    tracepoint.xml gpu.xml media_api.xml w1.xml \
+	    tracepoint.xml media_api.xml w1.xml \
 	    writing_musb_glue_layer.xml crypto-API.xml iio.xml
 
 include Documentation/DocBook/media/Makefile
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index 99cdc05bbb7a..9c10030eb2be 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -161,6 +161,10 @@ X!Edrivers/base/interface.c
 !Iinclude/linux/fence.h
 !Edrivers/dma-buf/seqno-fence.c
 !Iinclude/linux/seqno-fence.h
+!Edrivers/dma-buf/fence-array.c
+!Iinclude/linux/fence-array.h
+!Edrivers/dma-buf/reservation.c
+!Iinclude/linux/reservation.h
 !Edrivers/dma-buf/sync_file.c
 !Iinclude/linux/sync_file.h
        </sect2>
diff --git a/Documentation/DocBook/gpu.tmpl b/Documentation/DocBook/gpu.tmpl
deleted file mode 100644
index 7586bf75f62e..000000000000
--- a/Documentation/DocBook/gpu.tmpl
+++ /dev/null
@@ -1,3540 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
-	"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
-
-<book id="gpuDevelopersGuide">
-  <bookinfo>
-    <title>Linux GPU Driver Developer's Guide</title>
-
-    <authorgroup>
-      <author>
-	<firstname>Jesse</firstname>
-	<surname>Barnes</surname>
-	<contrib>Initial version</contrib>
-	<affiliation>
-	  <orgname>Intel Corporation</orgname>
-	  <address>
-	    <email>jesse.barnes@intel.com</email>
-	  </address>
-	</affiliation>
-      </author>
-      <author>
-	<firstname>Laurent</firstname>
-	<surname>Pinchart</surname>
-	<contrib>Driver internals</contrib>
-	<affiliation>
-	  <orgname>Ideas on board SPRL</orgname>
-	  <address>
-	    <email>laurent.pinchart@ideasonboard.com</email>
-	  </address>
-	</affiliation>
-      </author>
-      <author>
-	<firstname>Daniel</firstname>
-	<surname>Vetter</surname>
-	<contrib>Contributions all over the place</contrib>
-	<affiliation>
-	  <orgname>Intel Corporation</orgname>
-	  <address>
-	    <email>daniel.vetter@ffwll.ch</email>
-	  </address>
-	</affiliation>
-      </author>
-      <author>
-	<firstname>Lukas</firstname>
-	<surname>Wunner</surname>
-	<contrib>vga_switcheroo documentation</contrib>
-	<affiliation>
-	  <address>
-	    <email>lukas@wunner.de</email>
-	  </address>
-	</affiliation>
-      </author>
-    </authorgroup>
-
-    <copyright>
-      <year>2008-2009</year>
-      <year>2013-2014</year>
-      <holder>Intel Corporation</holder>
-    </copyright>
-    <copyright>
-      <year>2012</year>
-      <holder>Laurent Pinchart</holder>
-    </copyright>
-    <copyright>
-      <year>2015</year>
-      <holder>Lukas Wunner</holder>
-    </copyright>
-
-    <legalnotice>
-      <para>
-	The contents of this file may be used under the terms of the GNU
-	General Public License version 2 (the "GPL") as distributed in
-	the kernel source COPYING file.
-      </para>
-    </legalnotice>
-
-    <revhistory>
-      <!-- Put document revisions here, newest first. -->
-      <revision>
-	<revnumber>1.0</revnumber>
-	<date>2012-07-13</date>
-	<authorinitials>LP</authorinitials>
-	<revremark>Added extensive documentation about driver internals.
-	</revremark>
-      </revision>
-      <revision>
-	<revnumber>1.1</revnumber>
-	<date>2015-10-11</date>
-	<authorinitials>LW</authorinitials>
-	<revremark>Added vga_switcheroo documentation.
-	</revremark>
-      </revision>
-    </revhistory>
-  </bookinfo>
-
-<toc></toc>
-
-<part id="drmCore">
-  <title>DRM Core</title>
-  <partintro>
-    <para>
-      This first part of the GPU Driver Developer's Guide documents core DRM
-      code, helper libraries for writing drivers and generic userspace
-      interfaces exposed by DRM drivers.
-    </para>
-  </partintro>
-
-  <chapter id="drmIntroduction">
-    <title>Introduction</title>
-    <para>
-      The Linux DRM layer contains code intended to support the needs
-      of complex graphics devices, usually containing programmable
-      pipelines well suited to 3D graphics acceleration.  Graphics
-      drivers in the kernel may make use of DRM functions to make
-      tasks like memory management, interrupt handling and DMA easier,
-      and provide a uniform interface to applications.
-    </para>
-    <para>
-      A note on versions: this guide covers features found in the DRM
-      tree, including the TTM memory manager, output configuration and
-      mode setting, and the new vblank internals, in addition to all
-      the regular features found in current kernels.
-    </para>
-    <para>
-      [Insert diagram of typical DRM stack here]
-    </para>
-  <sect1>
-    <title>Style Guidelines</title>
-    <para>
-      For consistency this documentation uses American English. Abbreviations
-      are written as all-uppercase, for example: DRM, KMS, IOCTL, CRTC, and so
-      on. To aid in reading, documentations make full use of the markup
-      characters kerneldoc provides: @parameter for function parameters, @member
-      for structure members, &amp;structure to reference structures and
-      function() for functions. These all get automatically hyperlinked if
-      kerneldoc for the referenced objects exists. When referencing entries in
-      function vtables please use -&gt;vfunc(). Note that kerneldoc does
-      not support referencing struct members directly, so please add a reference
-      to the vtable struct somewhere in the same paragraph or at least section.
-    </para>
-    <para>
-      Except in special situations (to separate locked from unlocked variants)
-      locking requirements for functions aren't documented in the kerneldoc.
-      Instead locking should be check at runtime using e.g.
-      <code>WARN_ON(!mutex_is_locked(...));</code>. Since it's much easier to
-      ignore documentation than runtime noise this provides more value. And on
-      top of that runtime checks do need to be updated when the locking rules
-      change, increasing the chances that they're correct. Within the
-      documentation the locking rules should be explained in the relevant
-      structures: Either in the comment for the lock explaining what it
-      protects, or data fields need a note about which lock protects them, or
-      both.
-    </para>
-    <para>
-      Functions which have a non-<code>void</code> return value should have a
-      section called "Returns" explaining the expected return values in
-      different cases and their meanings. Currently there's no consensus whether
-      that section name should be all upper-case or not, and whether it should
-      end in a colon or not. Go with the file-local style. Other common section
-      names are "Notes" with information for dangerous or tricky corner cases,
-      and "FIXME" where the interface could be cleaned up.
-    </para>
-  </sect1>
-  </chapter>
-
-  <!-- Internals -->
-
-  <chapter id="drmInternals">
-    <title>DRM Internals</title>
-    <para>
-      This chapter documents DRM internals relevant to driver authors
-      and developers working to add support for the latest features to
-      existing drivers.
-    </para>
-    <para>
-      First, we go over some typical driver initialization
-      requirements, like setting up command buffers, creating an
-      initial output configuration, and initializing core services.
-      Subsequent sections cover core internals in more detail,
-      providing implementation notes and examples.
-    </para>
-    <para>
-      The DRM layer provides several services to graphics drivers,
-      many of them driven by the application interfaces it provides
-      through libdrm, the library that wraps most of the DRM ioctls.
-      These include vblank event handling, memory
-      management, output management, framebuffer management, command
-      submission &amp; fencing, suspend/resume support, and DMA
-      services.
-    </para>
-
-  <!-- Internals: driver init -->
-
-  <sect1>
-    <title>Driver Initialization</title>
-    <para>
-      At the core of every DRM driver is a <structname>drm_driver</structname>
-      structure. Drivers typically statically initialize a drm_driver structure,
-      and then pass it to <function>drm_dev_alloc()</function> to allocate a
-      device instance. After the device instance is fully initialized it can be
-      registered (which makes it accessible from userspace) using
-      <function>drm_dev_register()</function>.
-    </para>
-    <para>
-      The <structname>drm_driver</structname> structure contains static
-      information that describes the driver and features it supports, and
-      pointers to methods that the DRM core will call to implement the DRM API.
-      We will first go through the <structname>drm_driver</structname> static
-      information fields, and will then describe individual operations in
-      details as they get used in later sections.
-    </para>
-    <sect2>
-      <title>Driver Information</title>
-      <sect3>
-        <title>Driver Features</title>
-        <para>
-          Drivers inform the DRM core about their requirements and supported
-          features by setting appropriate flags in the
-          <structfield>driver_features</structfield> field. Since those flags
-          influence the DRM core behaviour since registration time, most of them
-          must be set to registering the <structname>drm_driver</structname>
-          instance.
-        </para>
-        <synopsis>u32 driver_features;</synopsis>
-        <variablelist>
-          <title>Driver Feature Flags</title>
-          <varlistentry>
-            <term>DRIVER_USE_AGP</term>
-            <listitem><para>
-              Driver uses AGP interface, the DRM core will manage AGP resources.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_REQUIRE_AGP</term>
-            <listitem><para>
-              Driver needs AGP interface to function. AGP initialization failure
-              will become a fatal error.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_PCI_DMA</term>
-            <listitem><para>
-              Driver is capable of PCI DMA, mapping of PCI DMA buffers to
-              userspace will be enabled. Deprecated.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_SG</term>
-            <listitem><para>
-              Driver can perform scatter/gather DMA, allocation and mapping of
-              scatter/gather buffers will be enabled. Deprecated.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_HAVE_DMA</term>
-            <listitem><para>
-              Driver supports DMA, the userspace DMA API will be supported.
-              Deprecated.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_HAVE_IRQ</term><term>DRIVER_IRQ_SHARED</term>
-            <listitem><para>
-              DRIVER_HAVE_IRQ indicates whether the driver has an IRQ handler
-              managed by the DRM Core. The core will support simple IRQ handler
-              installation when the flag is set. The installation process is
-              described in <xref linkend="drm-irq-registration"/>.</para>
-              <para>DRIVER_IRQ_SHARED indicates whether the device &amp; handler
-              support shared IRQs (note that this is required of PCI  drivers).
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_GEM</term>
-            <listitem><para>
-              Driver use the GEM memory manager.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_MODESET</term>
-            <listitem><para>
-              Driver supports mode setting interfaces (KMS).
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_PRIME</term>
-            <listitem><para>
-              Driver implements DRM PRIME buffer sharing.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_RENDER</term>
-            <listitem><para>
-              Driver supports dedicated render nodes.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRIVER_ATOMIC</term>
-            <listitem><para>
-              Driver supports atomic properties.  In this case the driver
-              must implement appropriate obj->atomic_get_property() vfuncs
-              for any modeset objects with driver specific properties.
-            </para></listitem>
-          </varlistentry>
-        </variablelist>
-      </sect3>
-      <sect3>
-        <title>Major, Minor and Patchlevel</title>
-        <synopsis>int major;
-int minor;
-int patchlevel;</synopsis>
-        <para>
-          The DRM core identifies driver versions by a major, minor and patch
-          level triplet. The information is printed to the kernel log at
-          initialization time and passed to userspace through the
-          DRM_IOCTL_VERSION ioctl.
-        </para>
-        <para>
-          The major and minor numbers are also used to verify the requested driver
-          API version passed to DRM_IOCTL_SET_VERSION. When the driver API changes
-          between minor versions, applications can call DRM_IOCTL_SET_VERSION to
-          select a specific version of the API. If the requested major isn't equal
-          to the driver major, or the requested minor is larger than the driver
-          minor, the DRM_IOCTL_SET_VERSION call will return an error. Otherwise
-          the driver's set_version() method will be called with the requested
-          version.
-        </para>
-      </sect3>
-      <sect3>
-        <title>Name, Description and Date</title>
-        <synopsis>char *name;
-char *desc;
-char *date;</synopsis>
-        <para>
-          The driver name is printed to the kernel log at initialization time,
-          used for IRQ registration and passed to userspace through
-          DRM_IOCTL_VERSION.
-        </para>
-        <para>
-          The driver description is a purely informative string passed to
-          userspace through the DRM_IOCTL_VERSION ioctl and otherwise unused by
-          the kernel.
-        </para>
-        <para>
-          The driver date, formatted as YYYYMMDD, is meant to identify the date of
-          the latest modification to the driver. However, as most drivers fail to
-          update it, its value is mostly useless. The DRM core prints it to the
-          kernel log at initialization time and passes it to userspace through the
-          DRM_IOCTL_VERSION ioctl.
-        </para>
-      </sect3>
-    </sect2>
-    <sect2>
-      <title>Device Instance and Driver Handling</title>
-!Pdrivers/gpu/drm/drm_drv.c driver instance overview
-!Edrivers/gpu/drm/drm_drv.c
-    </sect2>
-    <sect2>
-      <title>Driver Load</title>
-      <sect3 id="drm-irq-registration">
-        <title>IRQ Registration</title>
-        <para>
-          The DRM core tries to facilitate IRQ handler registration and
-          unregistration by providing <function>drm_irq_install</function> and
-          <function>drm_irq_uninstall</function> functions. Those functions only
-          support a single interrupt per device, devices that use more than one
-          IRQs need to be handled manually.
-        </para>
-        <sect4>
-          <title>Managed IRQ Registration</title>
-          <para>
-            <function>drm_irq_install</function> starts by calling the
-            <methodname>irq_preinstall</methodname> driver operation. The operation
-            is optional and must make sure that the interrupt will not get fired by
-            clearing all pending interrupt flags or disabling the interrupt.
-          </para>
-          <para>
-            The passed-in IRQ will then be requested by a call to
-            <function>request_irq</function>. If the DRIVER_IRQ_SHARED driver
-            feature flag is set, a shared (IRQF_SHARED) IRQ handler will be
-            requested.
-          </para>
-          <para>
-            The IRQ handler function must be provided as the mandatory irq_handler
-            driver operation. It will get passed directly to
-            <function>request_irq</function> and thus has the same prototype as all
-            IRQ handlers. It will get called with a pointer to the DRM device as the
-            second argument.
-          </para>
-          <para>
-            Finally the function calls the optional
-            <methodname>irq_postinstall</methodname> driver operation. The operation
-            usually enables interrupts (excluding the vblank interrupt, which is
-            enabled separately), but drivers may choose to enable/disable interrupts
-            at a different time.
-          </para>
-          <para>
-            <function>drm_irq_uninstall</function> is similarly used to uninstall an
-            IRQ handler. It starts by waking up all processes waiting on a vblank
-            interrupt to make sure they don't hang, and then calls the optional
-            <methodname>irq_uninstall</methodname> driver operation. The operation
-            must disable all hardware interrupts. Finally the function frees the IRQ
-            by calling <function>free_irq</function>.
-          </para>
-        </sect4>
-        <sect4>
-          <title>Manual IRQ Registration</title>
-          <para>
-            Drivers that require multiple interrupt handlers can't use the managed
-            IRQ registration functions. In that case IRQs must be registered and
-            unregistered manually (usually with the <function>request_irq</function>
-            and <function>free_irq</function> functions, or their devm_* equivalent).
-          </para>
-          <para>
-            When manually registering IRQs, drivers must not set the DRIVER_HAVE_IRQ
-            driver feature flag, and must not provide the
-	    <methodname>irq_handler</methodname> driver operation. They must set the
-	    <structname>drm_device</structname> <structfield>irq_enabled</structfield>
-	    field to 1 upon registration of the IRQs, and clear it to 0 after
-	    unregistering the IRQs.
-          </para>
-        </sect4>
-      </sect3>
-      <sect3>
-        <title>Memory Manager Initialization</title>
-        <para>
-          Every DRM driver requires a memory manager which must be initialized at
-          load time. DRM currently contains two memory managers, the Translation
-          Table Manager (TTM) and the Graphics Execution Manager (GEM).
-          This document describes the use of the GEM memory manager only. See
-          <xref linkend="drm-memory-management"/> for details.
-        </para>
-      </sect3>
-      <sect3>
-        <title>Miscellaneous Device Configuration</title>
-        <para>
-          Another task that may be necessary for PCI devices during configuration
-          is mapping the video BIOS. On many devices, the VBIOS describes device
-          configuration, LCD panel timings (if any), and contains flags indicating
-          device state. Mapping the BIOS can be done using the pci_map_rom() call,
-          a convenience function that takes care of mapping the actual ROM,
-          whether it has been shadowed into memory (typically at address 0xc0000)
-          or exists on the PCI device in the ROM BAR. Note that after the ROM has
-          been mapped and any necessary information has been extracted, it should
-          be unmapped; on many devices, the ROM address decoder is shared with
-          other BARs, so leaving it mapped could cause undesired behaviour like
-          hangs or memory corruption.
-  <!--!Fdrivers/pci/rom.c pci_map_rom-->
-        </para>
-      </sect3>
-    </sect2>
-    <sect2>
-      <title>Bus-specific Device Registration and PCI Support</title>
-      <para>
-        A number of functions are provided to help with device registration.
-	The functions deal with PCI and platform devices respectively and are
-	only provided for historical reasons. These are all deprecated and
-	shouldn't be used in new drivers. Besides that there's a few
-	helpers for pci drivers.
-      </para>
-!Edrivers/gpu/drm/drm_pci.c
-!Edrivers/gpu/drm/drm_platform.c
-    </sect2>
-  </sect1>
-
-  <!-- Internals: memory management -->
-
-  <sect1 id="drm-memory-management">
-    <title>Memory management</title>
-    <para>
-      Modern Linux systems require large amount of graphics memory to store
-      frame buffers, textures, vertices and other graphics-related data. Given
-      the very dynamic nature of many of that data, managing graphics memory
-      efficiently is thus crucial for the graphics stack and plays a central
-      role in the DRM infrastructure.
-    </para>
-    <para>
-      The DRM core includes two memory managers, namely Translation Table Maps
-      (TTM) and Graphics Execution Manager (GEM). TTM was the first DRM memory
-      manager to be developed and tried to be a one-size-fits-them all
-      solution. It provides a single userspace API to accommodate the need of
-      all hardware, supporting both Unified Memory Architecture (UMA) devices
-      and devices with dedicated video RAM (i.e. most discrete video cards).
-      This resulted in a large, complex piece of code that turned out to be
-      hard to use for driver development.
-    </para>
-    <para>
-      GEM started as an Intel-sponsored project in reaction to TTM's
-      complexity. Its design philosophy is completely different: instead of
-      providing a solution to every graphics memory-related problems, GEM
-      identified common code between drivers and created a support library to
-      share it. GEM has simpler initialization and execution requirements than
-      TTM, but has no video RAM management capabilities and is thus limited to
-      UMA devices.
-    </para>
-    <sect2>
-      <title>The Translation Table Manager (TTM)</title>
-      <para>
-        TTM design background and information belongs here.
-      </para>
-      <sect3>
-        <title>TTM initialization</title>
-        <warning><para>This section is outdated.</para></warning>
-        <para>
-          Drivers wishing to support TTM must fill out a drm_bo_driver
-          structure. The structure contains several fields with function
-          pointers for initializing the TTM, allocating and freeing memory,
-          waiting for command completion and fence synchronization, and memory
-          migration. See the radeon_ttm.c file for an example of usage.
-        </para>
-        <para>
-          The ttm_global_reference structure is made up of several fields:
-        </para>
-        <programlisting>
-          struct ttm_global_reference {
-                  enum ttm_global_types global_type;
-                  size_t size;
-                  void *object;
-                  int (*init) (struct ttm_global_reference *);
-                  void (*release) (struct ttm_global_reference *);
-          };
-        </programlisting>
-        <para>
-          There should be one global reference structure for your memory
-          manager as a whole, and there will be others for each object
-          created by the memory manager at runtime.  Your global TTM should
-          have a type of TTM_GLOBAL_TTM_MEM.  The size field for the global
-          object should be sizeof(struct ttm_mem_global), and the init and
-          release hooks should point at your driver-specific init and
-          release routines, which probably eventually call
-          ttm_mem_global_init and ttm_mem_global_release, respectively.
-        </para>
-        <para>
-          Once your global TTM accounting structure is set up and initialized
-          by calling ttm_global_item_ref() on it,
-          you need to create a buffer object TTM to
-          provide a pool for buffer object allocation by clients and the
-          kernel itself.  The type of this object should be TTM_GLOBAL_TTM_BO,
-          and its size should be sizeof(struct ttm_bo_global).  Again,
-          driver-specific init and release functions may be provided,
-          likely eventually calling ttm_bo_global_init() and
-          ttm_bo_global_release(), respectively.  Also, like the previous
-          object, ttm_global_item_ref() is used to create an initial reference
-          count for the TTM, which will call your initialization function.
-        </para>
-      </sect3>
-    </sect2>
-    <sect2 id="drm-gem">
-      <title>The Graphics Execution Manager (GEM)</title>
-      <para>
-        The GEM design approach has resulted in a memory manager that doesn't
-        provide full coverage of all (or even all common) use cases in its
-        userspace or kernel API. GEM exposes a set of standard memory-related
-        operations to userspace and a set of helper functions to drivers, and let
-        drivers implement hardware-specific operations with their own private API.
-      </para>
-      <para>
-        The GEM userspace API is described in the
-        <ulink url="http://lwn.net/Articles/283798/"><citetitle>GEM - the Graphics
-        Execution Manager</citetitle></ulink> article on LWN. While slightly
-        outdated, the document provides a good overview of the GEM API principles.
-        Buffer allocation and read and write operations, described as part of the
-        common GEM API, are currently implemented using driver-specific ioctls.
-      </para>
-      <para>
-        GEM is data-agnostic. It manages abstract buffer objects without knowing
-        what individual buffers contain. APIs that require knowledge of buffer
-        contents or purpose, such as buffer allocation or synchronization
-        primitives, are thus outside of the scope of GEM and must be implemented
-        using driver-specific ioctls.
-      </para>
-      <para>
-        On a fundamental level, GEM involves several operations:
-        <itemizedlist>
-          <listitem>Memory allocation and freeing</listitem>
-          <listitem>Command execution</listitem>
-          <listitem>Aperture management at command execution time</listitem>
-        </itemizedlist>
-        Buffer object allocation is relatively straightforward and largely
-        provided by Linux's shmem layer, which provides memory to back each
-        object.
-      </para>
-      <para>
-        Device-specific operations, such as command execution, pinning, buffer
-        read &amp; write, mapping, and domain ownership transfers are left to
-        driver-specific ioctls.
-      </para>
-      <sect3>
-        <title>GEM Initialization</title>
-        <para>
-          Drivers that use GEM must set the DRIVER_GEM bit in the struct
-          <structname>drm_driver</structname>
-          <structfield>driver_features</structfield> field. The DRM core will
-          then automatically initialize the GEM core before calling the
-          <methodname>load</methodname> operation. Behind the scene, this will
-          create a DRM Memory Manager object which provides an address space
-          pool for object allocation.
-        </para>
-        <para>
-          In a KMS configuration, drivers need to allocate and initialize a
-          command ring buffer following core GEM initialization if required by
-          the hardware. UMA devices usually have what is called a "stolen"
-          memory region, which provides space for the initial framebuffer and
-          large, contiguous memory regions required by the device. This space is
-          typically not managed by GEM, and must be initialized separately into
-          its own DRM MM object.
-        </para>
-      </sect3>
-      <sect3>
-        <title>GEM Objects Creation</title>
-        <para>
-          GEM splits creation of GEM objects and allocation of the memory that
-          backs them in two distinct operations.
-        </para>
-        <para>
-          GEM objects are represented by an instance of struct
-          <structname>drm_gem_object</structname>. Drivers usually need to extend
-          GEM objects with private information and thus create a driver-specific
-          GEM object structure type that embeds an instance of struct
-          <structname>drm_gem_object</structname>.
-        </para>
-        <para>
-          To create a GEM object, a driver allocates memory for an instance of its
-          specific GEM object type and initializes the embedded struct
-          <structname>drm_gem_object</structname> with a call to
-          <function>drm_gem_object_init</function>. The function takes a pointer to
-          the DRM device, a pointer to the GEM object and the buffer object size
-          in bytes.
-        </para>
-        <para>
-          GEM uses shmem to allocate anonymous pageable memory.
-          <function>drm_gem_object_init</function> will create an shmfs file of
-          the requested size and store it into the struct
-          <structname>drm_gem_object</structname> <structfield>filp</structfield>
-          field. The memory is used as either main storage for the object when the
-          graphics hardware uses system memory directly or as a backing store
-          otherwise.
-        </para>
-        <para>
-          Drivers are responsible for the actual physical pages allocation by
-          calling <function>shmem_read_mapping_page_gfp</function> for each page.
-          Note that they can decide to allocate pages when initializing the GEM
-          object, or to delay allocation until the memory is needed (for instance
-          when a page fault occurs as a result of a userspace memory access or
-          when the driver needs to start a DMA transfer involving the memory).
-        </para>
-        <para>
-          Anonymous pageable memory allocation is not always desired, for instance
-          when the hardware requires physically contiguous system memory as is
-          often the case in embedded devices. Drivers can create GEM objects with
-          no shmfs backing (called private GEM objects) by initializing them with
-          a call to <function>drm_gem_private_object_init</function> instead of
-          <function>drm_gem_object_init</function>. Storage for private GEM
-          objects must be managed by drivers.
-        </para>
-      </sect3>
-      <sect3>
-        <title>GEM Objects Lifetime</title>
-        <para>
-          All GEM objects are reference-counted by the GEM core. References can be
-          acquired and release by <function>calling drm_gem_object_reference</function>
-          and <function>drm_gem_object_unreference</function> respectively. The
-          caller must hold the <structname>drm_device</structname>
-	  <structfield>struct_mutex</structfield> lock when calling
-	  <function>drm_gem_object_reference</function>. As a convenience, GEM
-	  provides <function>drm_gem_object_unreference_unlocked</function>
-	  functions that can be called without holding the lock.
-        </para>
-        <para>
-          When the last reference to a GEM object is released the GEM core calls
-          the <structname>drm_driver</structname>
-          <methodname>gem_free_object</methodname> operation. That operation is
-          mandatory for GEM-enabled drivers and must free the GEM object and all
-          associated resources.
-        </para>
-        <para>
-          <synopsis>void (*gem_free_object) (struct drm_gem_object *obj);</synopsis>
-          Drivers are responsible for freeing all GEM object resources. This includes
-          the resources created by the GEM core, which need to be released with
-          <function>drm_gem_object_release</function>.
-        </para>
-      </sect3>
-      <sect3>
-        <title>GEM Objects Naming</title>
-        <para>
-          Communication between userspace and the kernel refers to GEM objects
-          using local handles, global names or, more recently, file descriptors.
-          All of those are 32-bit integer values; the usual Linux kernel limits
-          apply to the file descriptors.
-        </para>
-        <para>
-          GEM handles are local to a DRM file. Applications get a handle to a GEM
-          object through a driver-specific ioctl, and can use that handle to refer
-          to the GEM object in other standard or driver-specific ioctls. Closing a
-          DRM file handle frees all its GEM handles and dereferences the
-          associated GEM objects.
-        </para>
-        <para>
-          To create a handle for a GEM object drivers call
-          <function>drm_gem_handle_create</function>. The function takes a pointer
-          to the DRM file and the GEM object and returns a locally unique handle.
-          When the handle is no longer needed drivers delete it with a call to
-          <function>drm_gem_handle_delete</function>. Finally the GEM object
-          associated with a handle can be retrieved by a call to
-          <function>drm_gem_object_lookup</function>.
-        </para>
-        <para>
-          Handles don't take ownership of GEM objects, they only take a reference
-          to the object that will be dropped when the handle is destroyed. To
-          avoid leaking GEM objects, drivers must make sure they drop the
-          reference(s) they own (such as the initial reference taken at object
-          creation time) as appropriate, without any special consideration for the
-          handle. For example, in the particular case of combined GEM object and
-          handle creation in the implementation of the
-          <methodname>dumb_create</methodname> operation, drivers must drop the
-          initial reference to the GEM object before returning the handle.
-        </para>
-        <para>
-          GEM names are similar in purpose to handles but are not local to DRM
-          files. They can be passed between processes to reference a GEM object
-          globally. Names can't be used directly to refer to objects in the DRM
-          API, applications must convert handles to names and names to handles
-          using the DRM_IOCTL_GEM_FLINK and DRM_IOCTL_GEM_OPEN ioctls
-          respectively. The conversion is handled by the DRM core without any
-          driver-specific support.
-        </para>
-        <para>
-          GEM also supports buffer sharing with dma-buf file descriptors through
-          PRIME. GEM-based drivers must use the provided helpers functions to
-          implement the exporting and importing correctly. See <xref linkend="drm-prime-support" />.
-          Since sharing file descriptors is inherently more secure than the
-          easily guessable and global GEM names it is the preferred buffer
-          sharing mechanism. Sharing buffers through GEM names is only supported
-          for legacy userspace. Furthermore PRIME also allows cross-device
-          buffer sharing since it is based on dma-bufs.
-        </para>
-      </sect3>
-      <sect3 id="drm-gem-objects-mapping">
-        <title>GEM Objects Mapping</title>
-        <para>
-          Because mapping operations are fairly heavyweight GEM favours
-          read/write-like access to buffers, implemented through driver-specific
-          ioctls, over mapping buffers to userspace. However, when random access
-          to the buffer is needed (to perform software rendering for instance),
-          direct access to the object can be more efficient.
-        </para>
-        <para>
-          The mmap system call can't be used directly to map GEM objects, as they
-          don't have their own file handle. Two alternative methods currently
-          co-exist to map GEM objects to userspace. The first method uses a
-          driver-specific ioctl to perform the mapping operation, calling
-          <function>do_mmap</function> under the hood. This is often considered
-          dubious, seems to be discouraged for new GEM-enabled drivers, and will
-          thus not be described here.
-        </para>
-        <para>
-          The second method uses the mmap system call on the DRM file handle.
-          <synopsis>void *mmap(void *addr, size_t length, int prot, int flags, int fd,
-             off_t offset);</synopsis>
-          DRM identifies the GEM object to be mapped by a fake offset passed
-          through the mmap offset argument. Prior to being mapped, a GEM object
-          must thus be associated with a fake offset. To do so, drivers must call
-          <function>drm_gem_create_mmap_offset</function> on the object.
-        </para>
-        <para>
-          Once allocated, the fake offset value
-          must be passed to the application in a driver-specific way and can then
-          be used as the mmap offset argument.
-        </para>
-        <para>
-          The GEM core provides a helper method <function>drm_gem_mmap</function>
-          to handle object mapping. The method can be set directly as the mmap
-          file operation handler. It will look up the GEM object based on the
-          offset value and set the VMA operations to the
-          <structname>drm_driver</structname> <structfield>gem_vm_ops</structfield>
-          field. Note that <function>drm_gem_mmap</function> doesn't map memory to
-          userspace, but relies on the driver-provided fault handler to map pages
-          individually.
-        </para>
-        <para>
-          To use <function>drm_gem_mmap</function>, drivers must fill the struct
-          <structname>drm_driver</structname> <structfield>gem_vm_ops</structfield>
-          field with a pointer to VM operations.
-        </para>
-        <para>
-          <synopsis>struct vm_operations_struct *gem_vm_ops
-
-  struct vm_operations_struct {
-          void (*open)(struct vm_area_struct * area);
-          void (*close)(struct vm_area_struct * area);
-          int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
-  };</synopsis>
-        </para>
-        <para>
-          The <methodname>open</methodname> and <methodname>close</methodname>
-          operations must update the GEM object reference count. Drivers can use
-          the <function>drm_gem_vm_open</function> and
-          <function>drm_gem_vm_close</function> helper functions directly as open
-          and close handlers.
-        </para>
-        <para>
-          The fault operation handler is responsible for mapping individual pages
-          to userspace when a page fault occurs. Depending on the memory
-          allocation scheme, drivers can allocate pages at fault time, or can
-          decide to allocate memory for the GEM object at the time the object is
-          created.
-        </para>
-        <para>
-          Drivers that want to map the GEM object upfront instead of handling page
-          faults can implement their own mmap file operation handler.
-        </para>
-      </sect3>
-      <sect3>
-        <title>Memory Coherency</title>
-        <para>
-          When mapped to the device or used in a command buffer, backing pages
-          for an object are flushed to memory and marked write combined so as to
-          be coherent with the GPU. Likewise, if the CPU accesses an object
-          after the GPU has finished rendering to the object, then the object
-          must be made coherent with the CPU's view of memory, usually involving
-          GPU cache flushing of various kinds. This core CPU&lt;-&gt;GPU
-          coherency management is provided by a device-specific ioctl, which
-          evaluates an object's current domain and performs any necessary
-          flushing or synchronization to put the object into the desired
-          coherency domain (note that the object may be busy, i.e. an active
-          render target; in that case, setting the domain blocks the client and
-          waits for rendering to complete before performing any necessary
-          flushing operations).
-        </para>
-      </sect3>
-      <sect3>
-        <title>Command Execution</title>
-        <para>
-          Perhaps the most important GEM function for GPU devices is providing a
-          command execution interface to clients. Client programs construct
-          command buffers containing references to previously allocated memory
-          objects, and then submit them to GEM. At that point, GEM takes care to
-          bind all the objects into the GTT, execute the buffer, and provide
-          necessary synchronization between clients accessing the same buffers.
-          This often involves evicting some objects from the GTT and re-binding
-          others (a fairly expensive operation), and providing relocation
-          support which hides fixed GTT offsets from clients. Clients must take
-          care not to submit command buffers that reference more objects than
-          can fit in the GTT; otherwise, GEM will reject them and no rendering
-          will occur. Similarly, if several objects in the buffer require fence
-          registers to be allocated for correct rendering (e.g. 2D blits on
-          pre-965 chips), care must be taken not to require more fence registers
-          than are available to the client. Such resource management should be
-          abstracted from the client in libdrm.
-        </para>
-      </sect3>
-    </sect2>
-    <sect2>
-      <title>GEM Function Reference</title>
-!Edrivers/gpu/drm/drm_gem.c
-!Iinclude/drm/drm_gem.h
-    </sect2>
-    <sect2>
-      <title>VMA Offset Manager</title>
-!Pdrivers/gpu/drm/drm_vma_manager.c vma offset manager
-!Edrivers/gpu/drm/drm_vma_manager.c
-!Iinclude/drm/drm_vma_manager.h
-    </sect2>
-    <sect2 id="drm-prime-support">
-      <title>PRIME Buffer Sharing</title>
-      <para>
-        PRIME is the cross device buffer sharing framework in drm, originally
-        created for the OPTIMUS range of multi-gpu platforms. To userspace
-        PRIME buffers are dma-buf based file descriptors.
-      </para>
-      <sect3>
-        <title>Overview and Driver Interface</title>
-        <para>
-          Similar to GEM global names, PRIME file descriptors are
-          also used to share buffer objects across processes. They offer
-          additional security: as file descriptors must be explicitly sent over
-          UNIX domain sockets to be shared between applications, they can't be
-          guessed like the globally unique GEM names.
-        </para>
-        <para>
-          Drivers that support the PRIME
-          API must set the DRIVER_PRIME bit in the struct
-          <structname>drm_driver</structname>
-          <structfield>driver_features</structfield> field, and implement the
-          <methodname>prime_handle_to_fd</methodname> and
-          <methodname>prime_fd_to_handle</methodname> operations.
-        </para>
-        <para>
-          <synopsis>int (*prime_handle_to_fd)(struct drm_device *dev,
-                          struct drm_file *file_priv, uint32_t handle,
-                          uint32_t flags, int *prime_fd);
-int (*prime_fd_to_handle)(struct drm_device *dev,
-                          struct drm_file *file_priv, int prime_fd,
-                          uint32_t *handle);</synopsis>
-            Those two operations convert a handle to a PRIME file descriptor and
-            vice versa. Drivers must use the kernel dma-buf buffer sharing framework
-            to manage the PRIME file descriptors. Similar to the mode setting
-            API PRIME is agnostic to the underlying buffer object manager, as
-            long as handles are 32bit unsigned integers.
-          </para>
-          <para>
-            While non-GEM drivers must implement the operations themselves, GEM
-            drivers must use the <function>drm_gem_prime_handle_to_fd</function>
-            and <function>drm_gem_prime_fd_to_handle</function> helper functions.
-            Those helpers rely on the driver
-            <methodname>gem_prime_export</methodname> and
-            <methodname>gem_prime_import</methodname> operations to create a dma-buf
-            instance from a GEM object (dma-buf exporter role) and to create a GEM
-            object from a dma-buf instance (dma-buf importer role).
-          </para>
-          <para>
-            <synopsis>struct dma_buf * (*gem_prime_export)(struct drm_device *dev,
-                             struct drm_gem_object *obj,
-                             int flags);
-struct drm_gem_object * (*gem_prime_import)(struct drm_device *dev,
-                                            struct dma_buf *dma_buf);</synopsis>
-            These two operations are mandatory for GEM drivers that support
-            PRIME.
-          </para>
-        </sect3>
-      <sect3>
-        <title>PRIME Helper Functions</title>
-!Pdrivers/gpu/drm/drm_prime.c PRIME Helpers
-      </sect3>
-    </sect2>
-    <sect2>
-      <title>PRIME Function References</title>
-!Edrivers/gpu/drm/drm_prime.c
-    </sect2>
-    <sect2>
-      <title>DRM MM Range Allocator</title>
-      <sect3>
-        <title>Overview</title>
-!Pdrivers/gpu/drm/drm_mm.c Overview
-      </sect3>
-      <sect3>
-        <title>LRU Scan/Eviction Support</title>
-!Pdrivers/gpu/drm/drm_mm.c lru scan roaster
-      </sect3>
-      </sect2>
-    <sect2>
-      <title>DRM MM Range Allocator Function References</title>
-!Edrivers/gpu/drm/drm_mm.c
-!Iinclude/drm/drm_mm.h
-    </sect2>
-    <sect2>
-      <title>CMA Helper Functions Reference</title>
-!Pdrivers/gpu/drm/drm_gem_cma_helper.c cma helpers
-!Edrivers/gpu/drm/drm_gem_cma_helper.c
-!Iinclude/drm/drm_gem_cma_helper.h
-    </sect2>
-  </sect1>
-
-  <!-- Internals: mode setting -->
-
-  <sect1 id="drm-mode-setting">
-    <title>Mode Setting</title>
-    <para>
-      Drivers must initialize the mode setting core by calling
-      <function>drm_mode_config_init</function> on the DRM device. The function
-      initializes the <structname>drm_device</structname>
-      <structfield>mode_config</structfield> field and never fails. Once done,
-      mode configuration must be setup by initializing the following fields.
-    </para>
-    <itemizedlist>
-      <listitem>
-        <synopsis>int min_width, min_height;
-int max_width, max_height;</synopsis>
-        <para>
-	  Minimum and maximum width and height of the frame buffers in pixel
-	  units.
-	</para>
-      </listitem>
-      <listitem>
-        <synopsis>struct drm_mode_config_funcs *funcs;</synopsis>
-	<para>Mode setting functions.</para>
-      </listitem>
-    </itemizedlist>
-    <sect2>
-      <title>Display Modes Function Reference</title>
-!Iinclude/drm/drm_modes.h
-!Edrivers/gpu/drm/drm_modes.c
-    </sect2>
-    <sect2>
-      <title>Atomic Mode Setting Function Reference</title>
-!Edrivers/gpu/drm/drm_atomic.c
-!Idrivers/gpu/drm/drm_atomic.c
-    </sect2>
-    <sect2>
-      <title>Frame Buffer Abstraction</title>
-      <para>
-        Frame buffers are abstract memory objects that provide a source of
-        pixels to scanout to a CRTC. Applications explicitly request the
-        creation of frame buffers through the DRM_IOCTL_MODE_ADDFB(2) ioctls and
-        receive an opaque handle that can be passed to the KMS CRTC control,
-        plane configuration and page flip functions.
-      </para>
-      <para>
-        Frame buffers rely on the underneath memory manager for low-level memory
-        operations. When creating a frame buffer applications pass a memory
-        handle (or a list of memory handles for multi-planar formats) through
-	the <parameter>drm_mode_fb_cmd2</parameter> argument. For drivers using
-	GEM as their userspace buffer management interface this would be a GEM
-	handle.  Drivers are however free to use their own backing storage object
-	handles, e.g. vmwgfx directly exposes special TTM handles to userspace
-	and so expects TTM handles in the create ioctl and not GEM handles.
-      </para>
-      <para>
-	The lifetime of a drm framebuffer is controlled with a reference count,
-	drivers can grab additional references with
-	<function>drm_framebuffer_reference</function>and drop them
-	again with <function>drm_framebuffer_unreference</function>. For
-	driver-private framebuffers for which the last reference is never
-	dropped (e.g. for the fbdev framebuffer when the struct
-	<structname>drm_framebuffer</structname> is embedded into the fbdev
-	helper struct) drivers can manually clean up a framebuffer at module
-	unload time with
-	<function>drm_framebuffer_unregister_private</function>.
-      </para>
-    </sect2>
-    <sect2>
-      <title>Dumb Buffer Objects</title>
-      <para>
-	The KMS API doesn't standardize backing storage object creation and
-	leaves it to driver-specific ioctls. Furthermore actually creating a
-	buffer object even for GEM-based drivers is done through a
-	driver-specific ioctl - GEM only has a common userspace interface for
-	sharing and destroying objects. While not an issue for full-fledged
-	graphics stacks that include device-specific userspace components (in
-	libdrm for instance), this limit makes DRM-based early boot graphics
-	unnecessarily complex.
-      </para>
-      <para>
-        Dumb objects partly alleviate the problem by providing a standard
-        API to create dumb buffers suitable for scanout, which can then be used
-        to create KMS frame buffers.
-      </para>
-      <para>
-        To support dumb objects drivers must implement the
-        <methodname>dumb_create</methodname>,
-        <methodname>dumb_destroy</methodname> and
-        <methodname>dumb_map_offset</methodname> operations.
-      </para>
-      <itemizedlist>
-        <listitem>
-          <synopsis>int (*dumb_create)(struct drm_file *file_priv, struct drm_device *dev,
-                   struct drm_mode_create_dumb *args);</synopsis>
-          <para>
-            The <methodname>dumb_create</methodname> operation creates a driver
-	    object (GEM or TTM handle) suitable for scanout based on the
-	    width, height and depth from the struct
-	    <structname>drm_mode_create_dumb</structname> argument. It fills the
-	    argument's <structfield>handle</structfield>,
-	    <structfield>pitch</structfield> and <structfield>size</structfield>
-	    fields with a handle for the newly created object and its line
-            pitch and size in bytes.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int (*dumb_destroy)(struct drm_file *file_priv, struct drm_device *dev,
-                    uint32_t handle);</synopsis>
-          <para>
-            The <methodname>dumb_destroy</methodname> operation destroys a dumb
-            object created by <methodname>dumb_create</methodname>.
-          </para>
-        </listitem>
-        <listitem>
-          <synopsis>int (*dumb_map_offset)(struct drm_file *file_priv, struct drm_device *dev,
-                       uint32_t handle, uint64_t *offset);</synopsis>
-          <para>
-            The <methodname>dumb_map_offset</methodname> operation associates an
-            mmap fake offset with the object given by the handle and returns
-            it. Drivers must use the
-            <function>drm_gem_create_mmap_offset</function> function to
-            associate the fake offset as described in
-            <xref linkend="drm-gem-objects-mapping"/>.
-          </para>
-        </listitem>
-      </itemizedlist>
-      <para>
-        Note that dumb objects may not be used for gpu acceleration, as has been
-	attempted on some ARM embedded platforms. Such drivers really must have
-	a hardware-specific ioctl to allocate suitable buffer objects.
-      </para>
-    </sect2>
-    <sect2>
-      <title>Output Polling</title>
-      <synopsis>void (*output_poll_changed)(struct drm_device *dev);</synopsis>
-      <para>
-        This operation notifies the driver that the status of one or more
-        connectors has changed. Drivers that use the fb helper can just call the
-        <function>drm_fb_helper_hotplug_event</function> function to handle this
-        operation.
-      </para>
-    </sect2>
-    <sect2>
-      <title>Locking</title>
-      <para>
-        Beside some lookup structures with their own locking (which is hidden
-	behind the interface functions) most of the modeset state is protected
-	by the <code>dev-&lt;mode_config.lock</code> mutex and additionally
-	per-crtc locks to allow cursor updates, pageflips and similar operations
-	to occur concurrently with background tasks like output detection.
-	Operations which cross domains like a full modeset always grab all
-	locks. Drivers there need to protect resources shared between crtcs with
-	additional locking. They also need to be careful to always grab the
-	relevant crtc locks if a modset functions touches crtc state, e.g. for
-	load detection (which does only grab the <code>mode_config.lock</code>
-	to allow concurrent screen updates on live crtcs).
-      </para>
-    </sect2>
-  </sect1>
-
-  <!-- Internals: kms initialization and cleanup -->
-
-  <sect1 id="drm-kms-init">
-    <title>KMS Initialization and Cleanup</title>
-    <para>
-      A KMS device is abstracted and exposed as a set of planes, CRTCs, encoders
-      and connectors. KMS drivers must thus create and initialize all those
-      objects at load time after initializing mode setting.
-    </para>
-    <sect2>
-      <title>CRTCs (struct <structname>drm_crtc</structname>)</title>
-      <para>
-        A CRTC is an abstraction representing a part of the chip that contains a
-	pointer to a scanout buffer. Therefore, the number of CRTCs available
-	determines how many independent scanout buffers can be active at any
-	given time. The CRTC structure contains several fields to support this:
-	a pointer to some video memory (abstracted as a frame buffer object), a
-	display mode, and an (x, y) offset into the video memory to support
-	panning or configurations where one piece of video memory spans multiple
-	CRTCs.
-      </para>
-      <sect3>
-        <title>CRTC Initialization</title>
-        <para>
-          A KMS device must create and register at least one struct
-          <structname>drm_crtc</structname> instance. The instance is allocated
-          and zeroed by the driver, possibly as part of a larger structure, and
-          registered with a call to <function>drm_crtc_init</function> with a
-          pointer to CRTC functions.
-        </para>
-      </sect3>
-    </sect2>
-    <sect2>
-      <title>Planes (struct <structname>drm_plane</structname>)</title>
-      <para>
-        A plane represents an image source that can be blended with or overlayed
-	on top of a CRTC during the scanout process. Planes are associated with
-	a frame buffer to crop a portion of the image memory (source) and
-	optionally scale it to a destination size. The result is then blended
-	with or overlayed on top of a CRTC.
-      </para>
-      <para>
-      The DRM core recognizes three types of planes:
-      <itemizedlist>
-        <listitem>
-        DRM_PLANE_TYPE_PRIMARY represents a "main" plane for a CRTC.  Primary
-        planes are the planes operated upon by CRTC modesetting and flipping
-	operations described in the page_flip hook in <structname>drm_crtc_funcs</structname>.
-        </listitem>
-        <listitem>
-        DRM_PLANE_TYPE_CURSOR represents a "cursor" plane for a CRTC.  Cursor
-        planes are the planes operated upon by the DRM_IOCTL_MODE_CURSOR and
-        DRM_IOCTL_MODE_CURSOR2 ioctls.
-        </listitem>
-        <listitem>
-        DRM_PLANE_TYPE_OVERLAY represents all non-primary, non-cursor planes.
-        Some drivers refer to these types of planes as "sprites" internally.
-        </listitem>
-      </itemizedlist>
-      For compatibility with legacy userspace, only overlay planes are made
-      available to userspace by default.  Userspace clients may set the
-      DRM_CLIENT_CAP_UNIVERSAL_PLANES client capability bit to indicate that
-      they wish to receive a universal plane list containing all plane types.
-      </para>
-      <sect3>
-        <title>Plane Initialization</title>
-        <para>
-          To create a plane, a KMS drivers allocates and
-          zeroes an instances of struct <structname>drm_plane</structname>
-          (possibly as part of a larger structure) and registers it with a call
-          to <function>drm_universal_plane_init</function>. The function takes a bitmask
-          of the CRTCs that can be associated with the plane, a pointer to the
-          plane functions, a list of format supported formats, and the type of
-          plane (primary, cursor, or overlay) being initialized.
-        </para>
-        <para>
-          Cursor and overlay planes are optional.  All drivers should provide
-          one primary plane per CRTC (although this requirement may change in
-          the future); drivers that do not wish to provide special handling for
-          primary planes may make use of the helper functions described in
-          <xref linkend="drm-kms-planehelpers"/> to create and register a
-          primary plane with standard capabilities.
-        </para>
-      </sect3>
-    </sect2>
-    <sect2>
-      <title>Encoders (struct <structname>drm_encoder</structname>)</title>
-      <para>
-        An encoder takes pixel data from a CRTC and converts it to a format
-	suitable for any attached connectors. On some devices, it may be
-	possible to have a CRTC send data to more than one encoder. In that
-	case, both encoders would receive data from the same scanout buffer,
-	resulting in a "cloned" display configuration across the connectors
-	attached to each encoder.
-      </para>
-      <sect3>
-        <title>Encoder Initialization</title>
-        <para>
-          As for CRTCs, a KMS driver must create, initialize and register at
-          least one struct <structname>drm_encoder</structname> instance. The
-          instance is allocated and zeroed by the driver, possibly as part of a
-          larger structure.
-        </para>
-        <para>
-          Drivers must initialize the struct <structname>drm_encoder</structname>
-          <structfield>possible_crtcs</structfield> and
-          <structfield>possible_clones</structfield> fields before registering the
-          encoder. Both fields are bitmasks of respectively the CRTCs that the
-          encoder can be connected to, and sibling encoders candidate for cloning.
-        </para>
-        <para>
-          After being initialized, the encoder must be registered with a call to
-          <function>drm_encoder_init</function>. The function takes a pointer to
-          the encoder functions and an encoder type. Supported types are
-          <itemizedlist>
-            <listitem>
-              DRM_MODE_ENCODER_DAC for VGA and analog on DVI-I/DVI-A
-              </listitem>
-            <listitem>
-              DRM_MODE_ENCODER_TMDS for DVI, HDMI and (embedded) DisplayPort
-            </listitem>
-            <listitem>
-              DRM_MODE_ENCODER_LVDS for display panels
-            </listitem>
-            <listitem>
-              DRM_MODE_ENCODER_TVDAC for TV output (Composite, S-Video, Component,
-              SCART)
-            </listitem>
-            <listitem>
-              DRM_MODE_ENCODER_VIRTUAL for virtual machine displays
-            </listitem>
-          </itemizedlist>
-        </para>
-        <para>
-          Encoders must be attached to a CRTC to be used. DRM drivers leave
-          encoders unattached at initialization time. Applications (or the fbdev
-          compatibility layer when implemented) are responsible for attaching the
-          encoders they want to use to a CRTC.
-        </para>
-      </sect3>
-    </sect2>
-    <sect2>
-      <title>Connectors (struct <structname>drm_connector</structname>)</title>
-      <para>
-        A connector is the final destination for pixel data on a device, and
-	usually connects directly to an external display device like a monitor
-	or laptop panel. A connector can only be attached to one encoder at a
-	time. The connector is also the structure where information about the
-	attached display is kept, so it contains fields for display data, EDID
-	data, DPMS &amp; connection status, and information about modes
-	supported on the attached displays.
-      </para>
-      <sect3>
-        <title>Connector Initialization</title>
-        <para>
-          Finally a KMS driver must create, initialize, register and attach at
-          least one struct <structname>drm_connector</structname> instance. The
-          instance is created as other KMS objects and initialized by setting the
-          following fields.
-        </para>
-        <variablelist>
-          <varlistentry>
-            <term><structfield>interlace_allowed</structfield></term>
-            <listitem><para>
-              Whether the connector can handle interlaced modes.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term><structfield>doublescan_allowed</structfield></term>
-            <listitem><para>
-              Whether the connector can handle doublescan.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term><structfield>display_info
-            </structfield></term>
-            <listitem><para>
-              Display information is filled from EDID information when a display
-              is detected. For non hot-pluggable displays such as flat panels in
-              embedded systems, the driver should initialize the
-              <structfield>display_info</structfield>.<structfield>width_mm</structfield>
-              and
-              <structfield>display_info</structfield>.<structfield>height_mm</structfield>
-              fields with the physical size of the display.
-            </para></listitem>
-          </varlistentry>
-          <varlistentry>
-            <term id="drm-kms-connector-polled"><structfield>polled</structfield></term>
-            <listitem><para>
-              Connector polling mode, a combination of
-              <variablelist>
-                <varlistentry>
-                  <term>DRM_CONNECTOR_POLL_HPD</term>
-                  <listitem><para>
-                    The connector generates hotplug events and doesn't need to be
-                    periodically polled. The CONNECT and DISCONNECT flags must not
-                    be set together with the HPD flag.
-                  </para></listitem>
-                </varlistentry>
-                <varlistentry>
-                  <term>DRM_CONNECTOR_POLL_CONNECT</term>
-                  <listitem><para>
-                    Periodically poll the connector for connection.
-                  </para></listitem>
-                </varlistentry>
-                <varlistentry>
-                  <term>DRM_CONNECTOR_POLL_DISCONNECT</term>
-                  <listitem><para>
-                    Periodically poll the connector for disconnection.
-                  </para></listitem>
-                </varlistentry>
-              </variablelist>
-              Set to 0 for connectors that don't support connection status
-              discovery.
-            </para></listitem>
-          </varlistentry>
-        </variablelist>
-        <para>
-          The connector is then registered with a call to
-          <function>drm_connector_init</function> with a pointer to the connector
-          functions and a connector type, and exposed through sysfs with a call to
-          <function>drm_connector_register</function>.
-        </para>
-        <para>
-          Supported connector types are
-          <itemizedlist>
-            <listitem>DRM_MODE_CONNECTOR_VGA</listitem>
-            <listitem>DRM_MODE_CONNECTOR_DVII</listitem>
-            <listitem>DRM_MODE_CONNECTOR_DVID</listitem>
-            <listitem>DRM_MODE_CONNECTOR_DVIA</listitem>
-            <listitem>DRM_MODE_CONNECTOR_Composite</listitem>
-            <listitem>DRM_MODE_CONNECTOR_SVIDEO</listitem>
-            <listitem>DRM_MODE_CONNECTOR_LVDS</listitem>
-            <listitem>DRM_MODE_CONNECTOR_Component</listitem>
-            <listitem>DRM_MODE_CONNECTOR_9PinDIN</listitem>
-            <listitem>DRM_MODE_CONNECTOR_DisplayPort</listitem>
-            <listitem>DRM_MODE_CONNECTOR_HDMIA</listitem>
-            <listitem>DRM_MODE_CONNECTOR_HDMIB</listitem>
-            <listitem>DRM_MODE_CONNECTOR_TV</listitem>
-            <listitem>DRM_MODE_CONNECTOR_eDP</listitem>
-            <listitem>DRM_MODE_CONNECTOR_VIRTUAL</listitem>
-          </itemizedlist>
-        </para>
-        <para>
-          Connectors must be attached to an encoder to be used. For devices that
-          map connectors to encoders 1:1, the connector should be attached at
-          initialization time with a call to
-          <function>drm_mode_connector_attach_encoder</function>. The driver must
-          also set the <structname>drm_connector</structname>
-          <structfield>encoder</structfield> field to point to the attached
-          encoder.
-        </para>
-        <para>
-          Finally, drivers must initialize the connectors state change detection
-          with a call to <function>drm_kms_helper_poll_init</function>. If at
-          least one connector is pollable but can't generate hotplug interrupts
-          (indicated by the DRM_CONNECTOR_POLL_CONNECT and
-          DRM_CONNECTOR_POLL_DISCONNECT connector flags), a delayed work will
-          automatically be queued to periodically poll for changes. Connectors
-          that can generate hotplug interrupts must be marked with the
-          DRM_CONNECTOR_POLL_HPD flag instead, and their interrupt handler must
-          call <function>drm_helper_hpd_irq_event</function>. The function will
-          queue a delayed work to check the state of all connectors, but no
-          periodic polling will be done.
-        </para>
-      </sect3>
-      <sect3>
-        <title>Connector Operations</title>
-        <note><para>
-          Unless otherwise state, all operations are mandatory.
-        </para></note>
-        <sect4>
-          <title>DPMS</title>
-          <synopsis>void (*dpms)(struct drm_connector *connector, int mode);</synopsis>
-          <para>
-            The DPMS operation sets the power state of a connector. The mode
-            argument is one of
-            <itemizedlist>
-              <listitem><para>DRM_MODE_DPMS_ON</para></listitem>
-              <listitem><para>DRM_MODE_DPMS_STANDBY</para></listitem>
-              <listitem><para>DRM_MODE_DPMS_SUSPEND</para></listitem>
-              <listitem><para>DRM_MODE_DPMS_OFF</para></listitem>
-            </itemizedlist>
-          </para>
-          <para>
-            In all but DPMS_ON mode the encoder to which the connector is attached
-            should put the display in low-power mode by driving its signals
-            appropriately. If more than one connector is attached to the encoder
-            care should be taken not to change the power state of other displays as
-            a side effect. Low-power mode should be propagated to the encoders and
-            CRTCs when all related connectors are put in low-power mode.
-          </para>
-        </sect4>
-        <sect4>
-          <title>Modes</title>
-          <synopsis>int (*fill_modes)(struct drm_connector *connector, uint32_t max_width,
-                      uint32_t max_height);</synopsis>
-          <para>
-            Fill the mode list with all supported modes for the connector. If the
-            <parameter>max_width</parameter> and <parameter>max_height</parameter>
-            arguments are non-zero, the implementation must ignore all modes wider
-            than <parameter>max_width</parameter> or higher than
-            <parameter>max_height</parameter>.
-          </para>
-          <para>
-            The connector must also fill in this operation its
-            <structfield>display_info</structfield>
-            <structfield>width_mm</structfield> and
-            <structfield>height_mm</structfield> fields with the connected display
-            physical size in millimeters. The fields should be set to 0 if the value
-            isn't known or is not applicable (for instance for projector devices).
-          </para>
-        </sect4>
-        <sect4>
-          <title>Connection Status</title>
-          <para>
-            The connection status is updated through polling or hotplug events when
-            supported (see <xref linkend="drm-kms-connector-polled"/>). The status
-            value is reported to userspace through ioctls and must not be used
-            inside the driver, as it only gets initialized by a call to
-            <function>drm_mode_getconnector</function> from userspace.
-          </para>
-          <synopsis>enum drm_connector_status (*detect)(struct drm_connector *connector,
-                                        bool force);</synopsis>
-          <para>
-            Check to see if anything is attached to the connector. The
-            <parameter>force</parameter> parameter is set to false whilst polling or
-            to true when checking the connector due to user request.
-            <parameter>force</parameter> can be used by the driver to avoid
-            expensive, destructive operations during automated probing.
-          </para>
-          <para>
-            Return connector_status_connected if something is connected to the
-            connector, connector_status_disconnected if nothing is connected and
-            connector_status_unknown if the connection state isn't known.
-          </para>
-          <para>
-            Drivers should only return connector_status_connected if the connection
-            status has really been probed as connected. Connectors that can't detect
-            the connection status, or failed connection status probes, should return
-            connector_status_unknown.
-          </para>
-        </sect4>
-      </sect3>
-    </sect2>
-    <sect2>
-      <title>Cleanup</title>
-      <para>
-        The DRM core manages its objects' lifetime. When an object is not needed
-	anymore the core calls its destroy function, which must clean up and
-	free every resource allocated for the object. Every
-	<function>drm_*_init</function> call must be matched with a
-	corresponding <function>drm_*_cleanup</function> call to cleanup CRTCs
-	(<function>drm_crtc_cleanup</function>), planes
-	(<function>drm_plane_cleanup</function>), encoders
-	(<function>drm_encoder_cleanup</function>) and connectors
-	(<function>drm_connector_cleanup</function>). Furthermore, connectors
-	that have been added to sysfs must be removed by a call to
-	<function>drm_connector_unregister</function> before calling
-	<function>drm_connector_cleanup</function>.
-      </para>
-      <para>
-        Connectors state change detection must be cleanup up with a call to
-	<function>drm_kms_helper_poll_fini</function>.
-      </para>
-    </sect2>
-    <sect2>
-      <title>Output discovery and initialization example</title>
-      <programlisting><![CDATA[
-void intel_crt_init(struct drm_device *dev)
-{
-	struct drm_connector *connector;
-	struct intel_output *intel_output;
-
-	intel_output = kzalloc(sizeof(struct intel_output), GFP_KERNEL);
-	if (!intel_output)
-		return;
-
-	connector = &intel_output->base;
-	drm_connector_init(dev, &intel_output->base,
-			   &intel_crt_connector_funcs, DRM_MODE_CONNECTOR_VGA);
-
-	drm_encoder_init(dev, &intel_output->enc, &intel_crt_enc_funcs,
-			 DRM_MODE_ENCODER_DAC);
-
-	drm_mode_connector_attach_encoder(&intel_output->base,
-					  &intel_output->enc);
-
-	/* Set up the DDC bus. */
-	intel_output->ddc_bus = intel_i2c_create(dev, GPIOA, "CRTDDC_A");
-	if (!intel_output->ddc_bus) {
-		dev_printk(KERN_ERR, &dev->pdev->dev, "DDC bus registration "
-			   "failed.\n");
-		return;
-	}
-
-	intel_output->type = INTEL_OUTPUT_ANALOG;
-	connector->interlace_allowed = 0;
-	connector->doublescan_allowed = 0;
-
-	drm_encoder_helper_add(&intel_output->enc, &intel_crt_helper_funcs);
-	drm_connector_helper_add(connector, &intel_crt_connector_helper_funcs);
-
-	drm_connector_register(connector);
-}]]></programlisting>
-      <para>
-        In the example above (taken from the i915 driver), a CRTC, connector and
-        encoder combination is created. A device-specific i2c bus is also
-        created for fetching EDID data and performing monitor detection. Once
-        the process is complete, the new connector is registered with sysfs to
-        make its properties available to applications.
-      </para>
-    </sect2>
-    <sect2>
-      <title>KMS API Functions</title>
-!Edrivers/gpu/drm/drm_crtc.c
-    </sect2>
-    <sect2>
-      <title>KMS Data Structures</title>
-!Iinclude/drm/drm_crtc.h
-    </sect2>
-    <sect2>
-      <title>KMS Locking</title>
-!Pdrivers/gpu/drm/drm_modeset_lock.c kms locking
-!Iinclude/drm/drm_modeset_lock.h
-!Edrivers/gpu/drm/drm_modeset_lock.c
-    </sect2>
-  </sect1>
-
-  <!-- Internals: kms helper functions -->
-
-  <sect1>
-    <title>Mode Setting Helper Functions</title>
-    <para>
-      The plane, CRTC, encoder and connector functions provided by the drivers
-      implement the DRM API. They're called by the DRM core and ioctl handlers
-      to handle device state changes and configuration request. As implementing
-      those functions often requires logic not specific to drivers, mid-layer
-      helper functions are available to avoid duplicating boilerplate code.
-    </para>
-    <para>
-      The DRM core contains one mid-layer implementation. The mid-layer provides
-      implementations of several plane, CRTC, encoder and connector functions
-      (called from the top of the mid-layer) that pre-process requests and call
-      lower-level functions provided by the driver (at the bottom of the
-      mid-layer). For instance, the
-      <function>drm_crtc_helper_set_config</function> function can be used to
-      fill the struct <structname>drm_crtc_funcs</structname>
-      <structfield>set_config</structfield> field. When called, it will split
-      the <methodname>set_config</methodname> operation in smaller, simpler
-      operations and call the driver to handle them.
-    </para>
-    <para>
-      To use the mid-layer, drivers call <function>drm_crtc_helper_add</function>,
-      <function>drm_encoder_helper_add</function> and
-      <function>drm_connector_helper_add</function> functions to install their
-      mid-layer bottom operations handlers, and fill the
-      <structname>drm_crtc_funcs</structname>,
-      <structname>drm_encoder_funcs</structname> and
-      <structname>drm_connector_funcs</structname> structures with pointers to
-      the mid-layer top API functions. Installing the mid-layer bottom operation
-      handlers is best done right after registering the corresponding KMS object.
-    </para>
-    <para>
-      The mid-layer is not split between CRTC, encoder and connector operations.
-      To use it, a driver must provide bottom functions for all of the three KMS
-      entities.
-    </para>
-    <sect2>
-      <title>Atomic Modeset Helper Functions Reference</title>
-      <sect3>
-	<title>Overview</title>
-!Pdrivers/gpu/drm/drm_atomic_helper.c overview
-      </sect3>
-      <sect3>
-	<title>Implementing Asynchronous Atomic Commit</title>
-!Pdrivers/gpu/drm/drm_atomic_helper.c implementing async commit
-      </sect3>
-      <sect3>
-	<title>Atomic State Reset and Initialization</title>
-!Pdrivers/gpu/drm/drm_atomic_helper.c atomic state reset and initialization
-      </sect3>
-!Iinclude/drm/drm_atomic_helper.h
-!Edrivers/gpu/drm/drm_atomic_helper.c
-    </sect2>
-    <sect2>
-      <title>Modeset Helper Reference for Common Vtables</title>
-!Iinclude/drm/drm_modeset_helper_vtables.h
-!Pinclude/drm/drm_modeset_helper_vtables.h overview
-    </sect2>
-    <sect2>
-      <title>Legacy CRTC/Modeset Helper Functions Reference</title>
-!Edrivers/gpu/drm/drm_crtc_helper.c
-!Pdrivers/gpu/drm/drm_crtc_helper.c overview
-    </sect2>
-    <sect2>
-      <title>Output Probing Helper Functions Reference</title>
-!Pdrivers/gpu/drm/drm_probe_helper.c output probing helper overview
-!Edrivers/gpu/drm/drm_probe_helper.c
-    </sect2>
-    <sect2>
-      <title>fbdev Helper Functions Reference</title>
-!Pdrivers/gpu/drm/drm_fb_helper.c fbdev helpers
-!Edrivers/gpu/drm/drm_fb_helper.c
-!Iinclude/drm/drm_fb_helper.h
-    </sect2>
-    <sect2>
-      <title>Framebuffer CMA Helper Functions Reference</title>
-!Pdrivers/gpu/drm/drm_fb_cma_helper.c framebuffer cma helper functions
-!Edrivers/gpu/drm/drm_fb_cma_helper.c
-    </sect2>
-    <sect2>
-      <title>Display Port Helper Functions Reference</title>
-!Pdrivers/gpu/drm/drm_dp_helper.c dp helpers
-!Iinclude/drm/drm_dp_helper.h
-!Edrivers/gpu/drm/drm_dp_helper.c
-    </sect2>
-    <sect2>
-      <title>Display Port Dual Mode Adaptor Helper Functions Reference</title>
-!Pdrivers/gpu/drm/drm_dp_dual_mode_helper.c dp dual mode helpers
-!Iinclude/drm/drm_dp_dual_mode_helper.h
-!Edrivers/gpu/drm/drm_dp_dual_mode_helper.c
-    </sect2>
-    <sect2>
-      <title>Display Port MST Helper Functions Reference</title>
-!Pdrivers/gpu/drm/drm_dp_mst_topology.c dp mst helper
-!Iinclude/drm/drm_dp_mst_helper.h
-!Edrivers/gpu/drm/drm_dp_mst_topology.c
-    </sect2>
-    <sect2>
-      <title>MIPI DSI Helper Functions Reference</title>
-!Pdrivers/gpu/drm/drm_mipi_dsi.c dsi helpers
-!Iinclude/drm/drm_mipi_dsi.h
-!Edrivers/gpu/drm/drm_mipi_dsi.c
-    </sect2>
-    <sect2>
-      <title>EDID Helper Functions Reference</title>
-!Edrivers/gpu/drm/drm_edid.c
-    </sect2>
-    <sect2>
-      <title>Rectangle Utilities Reference</title>
-!Pinclude/drm/drm_rect.h rect utils
-!Iinclude/drm/drm_rect.h
-!Edrivers/gpu/drm/drm_rect.c
-    </sect2>
-    <sect2>
-      <title>Flip-work Helper Reference</title>
-!Pinclude/drm/drm_flip_work.h flip utils
-!Iinclude/drm/drm_flip_work.h
-!Edrivers/gpu/drm/drm_flip_work.c
-    </sect2>
-    <sect2>
-      <title>HDMI Infoframes Helper Reference</title>
-      <para>
-	Strictly speaking this is not a DRM helper library but generally useable
-	by any driver interfacing with HDMI outputs like v4l or alsa drivers.
-	But it nicely fits into the overall topic of mode setting helper
-	libraries and hence is also included here.
-      </para>
-!Iinclude/linux/hdmi.h
-!Edrivers/video/hdmi.c
-    </sect2>
-    <sect2>
-      <title id="drm-kms-planehelpers">Plane Helper Reference</title>
-!Edrivers/gpu/drm/drm_plane_helper.c
-!Pdrivers/gpu/drm/drm_plane_helper.c overview
-    </sect2>
-    <sect2>
-	  <title>Tile group</title>
-!Pdrivers/gpu/drm/drm_crtc.c Tile group
-    </sect2>
-    <sect2>
-      <title>Bridges</title>
-      <sect3>
-        <title>Overview</title>
-!Pdrivers/gpu/drm/drm_bridge.c overview
-      </sect3>
-      <sect3>
-        <title>Default bridge callback sequence</title>
-!Pdrivers/gpu/drm/drm_bridge.c bridge callbacks
-      </sect3>
-!Edrivers/gpu/drm/drm_bridge.c
-    </sect2>
-    <sect2>
-      <title>Panel Helper Reference</title>
-!Iinclude/drm/drm_panel.h
-!Edrivers/gpu/drm/drm_panel.c
-!Pdrivers/gpu/drm/drm_panel.c drm panel
-    </sect2>
-  </sect1>
-
-  <!-- Internals: kms properties -->
-
-  <sect1 id="drm-kms-properties">
-    <title>KMS Properties</title>
-    <para>
-      Drivers may need to expose additional parameters to applications than
-      those described in the previous sections. KMS supports attaching
-      properties to CRTCs, connectors and planes and offers a userspace API to
-      list, get and set the property values.
-    </para>
-    <para>
-      Properties are identified by a name that uniquely defines the property
-      purpose, and store an associated value. For all property types except blob
-      properties the value is a 64-bit unsigned integer.
-    </para>
-    <para>
-      KMS differentiates between properties and property instances. Drivers
-      first create properties and then create and associate individual instances
-      of those properties to objects. A property can be instantiated multiple
-      times and associated with different objects. Values are stored in property
-      instances, and all other property information are stored in the property
-      and shared between all instances of the property.
-    </para>
-    <para>
-      Every property is created with a type that influences how the KMS core
-      handles the property. Supported property types are
-      <variablelist>
-        <varlistentry>
-          <term>DRM_MODE_PROP_RANGE</term>
-          <listitem><para>Range properties report their minimum and maximum
-            admissible values. The KMS core verifies that values set by
-            application fit in that range.</para></listitem>
-        </varlistentry>
-        <varlistentry>
-          <term>DRM_MODE_PROP_ENUM</term>
-          <listitem><para>Enumerated properties take a numerical value that
-            ranges from 0 to the number of enumerated values defined by the
-            property minus one, and associate a free-formed string name to each
-            value. Applications can retrieve the list of defined value-name pairs
-            and use the numerical value to get and set property instance values.
-            </para></listitem>
-        </varlistentry>
-        <varlistentry>
-          <term>DRM_MODE_PROP_BITMASK</term>
-          <listitem><para>Bitmask properties are enumeration properties that
-            additionally restrict all enumerated values to the 0..63 range.
-            Bitmask property instance values combine one or more of the
-            enumerated bits defined by the property.</para></listitem>
-        </varlistentry>
-        <varlistentry>
-          <term>DRM_MODE_PROP_BLOB</term>
-          <listitem><para>Blob properties store a binary blob without any format
-            restriction. The binary blobs are created as KMS standalone objects,
-            and blob property instance values store the ID of their associated
-            blob object.</para>
-	    <para>Blob properties are only used for the connector EDID property
-	    and cannot be created by drivers.</para></listitem>
-        </varlistentry>
-      </variablelist>
-    </para>
-    <para>
-      To create a property drivers call one of the following functions depending
-      on the property type. All property creation functions take property flags
-      and name, as well as type-specific arguments.
-      <itemizedlist>
-        <listitem>
-          <synopsis>struct drm_property *drm_property_create_range(struct drm_device *dev, int flags,
-                                               const char *name,
-                                               uint64_t min, uint64_t max);</synopsis>
-          <para>Create a range property with the given minimum and maximum
-            values.</para>
-        </listitem>
-        <listitem>
-          <synopsis>struct drm_property *drm_property_create_enum(struct drm_device *dev, int flags,
-                                              const char *name,
-                                              const struct drm_prop_enum_list *props,
-                                              int num_values);</synopsis>
-          <para>Create an enumerated property. The <parameter>props</parameter>
-            argument points to an array of <parameter>num_values</parameter>
-            value-name pairs.</para>
-        </listitem>
-        <listitem>
-          <synopsis>struct drm_property *drm_property_create_bitmask(struct drm_device *dev,
-                                                 int flags, const char *name,
-                                                 const struct drm_prop_enum_list *props,
-                                                 int num_values);</synopsis>
-          <para>Create a bitmask property. The <parameter>props</parameter>
-            argument points to an array of <parameter>num_values</parameter>
-            value-name pairs.</para>
-        </listitem>
-      </itemizedlist>
-    </para>
-    <para>
-      Properties can additionally be created as immutable, in which case they
-      will be read-only for applications but can be modified by the driver. To
-      create an immutable property drivers must set the DRM_MODE_PROP_IMMUTABLE
-      flag at property creation time.
-    </para>
-    <para>
-      When no array of value-name pairs is readily available at property
-      creation time for enumerated or range properties, drivers can create
-      the property using the <function>drm_property_create</function> function
-      and manually add enumeration value-name pairs by calling the
-      <function>drm_property_add_enum</function> function. Care must be taken to
-      properly specify the property type through the <parameter>flags</parameter>
-      argument.
-    </para>
-    <para>
-      After creating properties drivers can attach property instances to CRTC,
-      connector and plane objects by calling the
-      <function>drm_object_attach_property</function>. The function takes a
-      pointer to the target object, a pointer to the previously created property
-      and an initial instance value.
-    </para>
-    <sect2>
-	<title>Existing KMS Properties</title>
-	<para>
-	The following table gives description of drm properties exposed by various
-	modules/drivers.
-	</para>
-	<table border="1" cellpadding="0" cellspacing="0">
-	<tbody>
-	<tr style="font-weight: bold;">
-	<td valign="top" >Owner Module/Drivers</td>
-	<td valign="top" >Group</td>
-	<td valign="top" >Property Name</td>
-	<td valign="top" >Type</td>
-	<td valign="top" >Property Values</td>
-	<td valign="top" >Object attached</td>
-	<td valign="top" >Description/Restrictions</td>
-	</tr>
-	<tr>
-	<td rowspan="42" valign="top" >DRM</td>
-	<td rowspan="2" valign="top" >Generic</td>
-	<td valign="top" >“rotation”</td>
-	<td valign="top" >BITMASK</td>
-	<td valign="top" >{ 0, "rotate-0" },
-	{ 1, "rotate-90" },
-	{ 2, "rotate-180" },
-	{ 3, "rotate-270" },
-	{ 4, "reflect-x" },
-	{ 5, "reflect-y" }</td>
-	<td valign="top" >CRTC, Plane</td>
-	<td valign="top" >rotate-(degrees) rotates the image by the specified amount in degrees
-	in counter clockwise direction. reflect-x and reflect-y reflects the
-	image along the specified axis prior to rotation</td>
-	</tr>
-	<tr>
-	<td valign="top" >“scaling mode”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "None", "Full", "Center", "Full aspect" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >Supported by: amdgpu, gma500, i915, nouveau and radeon.</td>
-	</tr>
-	<tr>
-	<td rowspan="5" valign="top" >Connector</td>
-	<td valign="top" >“EDID”</td>
-	<td valign="top" >BLOB | IMMUTABLE</td>
-	<td valign="top" >0</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >Contains id of edid blob ptr object.</td>
-	</tr>
-	<tr>
-	<td valign="top" >“DPMS”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ “On”, “Standby”, “Suspend”, “Off” }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >Contains DPMS operation mode value.</td>
-	</tr>
-	<tr>
-	<td valign="top" >“PATH”</td>
-	<td valign="top" >BLOB | IMMUTABLE</td>
-	<td valign="top" >0</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >Contains topology path to a connector.</td>
-	</tr>
-	<tr>
-	<td valign="top" >“TILE”</td>
-	<td valign="top" >BLOB | IMMUTABLE</td>
-	<td valign="top" >0</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >Contains tiling information for a connector.</td>
-	</tr>
-	<tr>
-	<td valign="top" >“CRTC_ID”</td>
-	<td valign="top" >OBJECT</td>
-	<td valign="top" >DRM_MODE_OBJECT_CRTC</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >CRTC that connector is attached to (atomic)</td>
-	</tr>
-	<tr>
-	<td rowspan="11" valign="top" >Plane</td>
-	<td valign="top" >“type”</td>
-	<td valign="top" >ENUM | IMMUTABLE</td>
-	<td valign="top" >{ "Overlay", "Primary", "Cursor" }</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >Plane type</td>
-	</tr>
-	<tr>
-	<td valign="top" >“SRC_X”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=UINT_MAX</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >Scanout source x coordinate in 16.16 fixed point (atomic)</td>
-	</tr>
-	<tr>
-	<td valign="top" >“SRC_Y”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=UINT_MAX</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >Scanout source y coordinate in 16.16 fixed point (atomic)</td>
-	</tr>
-	<tr>
-	<td valign="top" >“SRC_W”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=UINT_MAX</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >Scanout source width in 16.16 fixed point (atomic)</td>
-	</tr>
-	<tr>
-	<td valign="top" >“SRC_H”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=UINT_MAX</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >Scanout source height in 16.16 fixed point (atomic)</td>
-	</tr>
-	<tr>
-	<td valign="top" >“CRTC_X”</td>
-	<td valign="top" >SIGNED_RANGE</td>
-	<td valign="top" >Min=INT_MIN, Max=INT_MAX</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >Scanout CRTC (destination) x coordinate (atomic)</td>
-	</tr>
-	<tr>
-	<td valign="top" >“CRTC_Y”</td>
-	<td valign="top" >SIGNED_RANGE</td>
-	<td valign="top" >Min=INT_MIN, Max=INT_MAX</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >Scanout CRTC (destination) y coordinate (atomic)</td>
-	</tr>
-	<tr>
-	<td valign="top" >“CRTC_W”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=UINT_MAX</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >Scanout CRTC (destination) width (atomic)</td>
-	</tr>
-	<tr>
-	<td valign="top" >“CRTC_H”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=UINT_MAX</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >Scanout CRTC (destination) height (atomic)</td>
-	</tr>
-	<tr>
-	<td valign="top" >“FB_ID”</td>
-	<td valign="top" >OBJECT</td>
-	<td valign="top" >DRM_MODE_OBJECT_FB</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >Scanout framebuffer (atomic)</td>
-	</tr>
-	<tr>
-	<td valign="top" >“CRTC_ID”</td>
-	<td valign="top" >OBJECT</td>
-	<td valign="top" >DRM_MODE_OBJECT_CRTC</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >CRTC that plane is attached to (atomic)</td>
-	</tr>
-	<tr>
-	<td rowspan="2" valign="top" >DVI-I</td>
-	<td valign="top" >“subconnector”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ “Unknown”, “DVI-D”, “DVI-A” }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“select subconnector”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ “Automatic”, “DVI-D”, “DVI-A” }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="13" valign="top" >TV</td>
-	<td valign="top" >“subconnector”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "Unknown", "Composite", "SVIDEO", "Component", "SCART" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“select subconnector”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "Automatic", "Composite", "SVIDEO", "Component", "SCART" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“mode”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "NTSC_M", "NTSC_J", "NTSC_443", "PAL_B" } etc.</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“left margin”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“right margin”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“top margin”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“bottom margin”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“brightness”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“contrast”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“flicker reduction”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“overscan”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“saturation”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“hue”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="2" valign="top" >Virtual GPU</td>
-	<td valign="top" >“suggested X”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0xffffffff</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >property to suggest an X offset for a connector</td>
-	</tr>
-	<tr>
-	<td valign="top" >“suggested Y”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0xffffffff</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >property to suggest an Y offset for a connector</td>
-	</tr>
-	<tr>
-	<td rowspan="7" valign="top" >Optional</td>
-	<td valign="top" >"aspect ratio"</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "None", "4:3", "16:9" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TDB</td>
-	</tr>
-	<tr>
-	<td valign="top" >“dirty”</td>
-	<td valign="top" >ENUM | IMMUTABLE</td>
-	<td valign="top" >{ "Off", "On", "Annotate" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“DEGAMMA_LUT”</td>
-	<td valign="top" >BLOB</td>
-	<td valign="top" >0</td>
-	<td valign="top" >CRTC</td>
-	<td valign="top" >DRM property to set the degamma lookup table
-		(LUT) mapping pixel data from the framebuffer before it is
-		given to the transformation matrix. The data is an interpreted
-		as an array of struct drm_color_lut elements. Hardware might
-		choose not to use the full precision of the LUT elements nor
-		use all the elements of the LUT (for example the hardware
-		might choose to interpolate between LUT[0] and LUT[4]). </td>
-	</tr>
-	<tr>
-	<td valign="top" >“DEGAMMA_LUT_SIZE”</td>
-	<td valign="top" >RANGE | IMMUTABLE</td>
-	<td valign="top" >Min=0, Max=UINT_MAX</td>
-	<td valign="top" >CRTC</td>
-	<td valign="top" >DRM property to gives the size of the lookup
-		table to be set on the DEGAMMA_LUT property (the size depends
-		on the underlying hardware).</td>
-	</tr>
-	<tr>
-	<td valign="top" >“CTM”</td>
-	<td valign="top" >BLOB</td>
-	<td valign="top" >0</td>
-	<td valign="top" >CRTC</td>
-	<td valign="top" >DRM property to set the current
-		transformation matrix (CTM) apply to pixel data after the
-		lookup through the degamma LUT and before the lookup through
-		the gamma LUT. The data is an interpreted as a struct
-		drm_color_ctm.</td>
-	</tr>
-	<tr>
-	<td valign="top" >“GAMMA_LUT”</td>
-	<td valign="top" >BLOB</td>
-	<td valign="top" >0</td>
-	<td valign="top" >CRTC</td>
-	<td valign="top" >DRM property to set the gamma lookup table
-		(LUT) mapping pixel data after to the transformation matrix to
-		data sent to the connector. The data is an interpreted as an
-		array of struct drm_color_lut elements. Hardware might choose
-		not to use the full precision of the LUT elements nor use all
-		the elements of the LUT (for example the hardware might choose
-		to interpolate between LUT[0] and LUT[4]).</td>
-	</tr>
-	<tr>
-	<td valign="top" >“GAMMA_LUT_SIZE”</td>
-	<td valign="top" >RANGE | IMMUTABLE</td>
-	<td valign="top" >Min=0, Max=UINT_MAX</td>
-	<td valign="top" >CRTC</td>
-	<td valign="top" >DRM property to gives the size of the lookup
-		table to be set on the GAMMA_LUT property (the size depends on
-		the underlying hardware).</td>
-	</tr>
-	<tr>
-	<td rowspan="20" valign="top" >i915</td>
-	<td rowspan="2" valign="top" >Generic</td>
-	<td valign="top" >"Broadcast RGB"</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "Automatic", "Full", "Limited 16:235" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >When this property is set to Limited 16:235
-		and CTM is set, the hardware will be programmed with the
-		result of the multiplication of CTM by the limited range
-		matrix to ensure the pixels normaly in the range 0..1.0 are
-		remapped to the range 16/255..235/255.</td>
-	</tr>
-	<tr>
-	<td valign="top" >“audio”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "force-dvi", "off", "auto", "on" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="17" valign="top" >SDVO-TV</td>
-	<td valign="top" >“mode”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "NTSC_M", "NTSC_J", "NTSC_443", "PAL_B" } etc.</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"left_margin"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"right_margin"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"top_margin"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"bottom_margin"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“hpos”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“vpos”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“contrast”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“saturation”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“hue”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“sharpness”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“flicker_filter”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“flicker_filter_adaptive”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“flicker_filter_2d”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“tv_chroma_filter”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“tv_luma_filter”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“dot_crawl”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=1</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >SDVO-TV/LVDS</td>
-	<td valign="top" >“brightness”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="2" valign="top" >CDV gma-500</td>
-	<td rowspan="2" valign="top" >Generic</td>
-	<td valign="top" >"Broadcast RGB"</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ “Full”, “Limited 16:235” }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"Broadcast RGB"</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ “off”, “auto”, “on” }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="19" valign="top" >Poulsbo</td>
-	<td rowspan="1" valign="top" >Generic</td>
-	<td valign="top" >“backlight”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=100</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="17" valign="top" >SDVO-TV</td>
-	<td valign="top" >“mode”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "NTSC_M", "NTSC_J", "NTSC_443", "PAL_B" } etc.</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"left_margin"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"right_margin"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"top_margin"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"bottom_margin"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“hpos”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“vpos”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“contrast”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“saturation”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“hue”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“sharpness”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“flicker_filter”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“flicker_filter_adaptive”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“flicker_filter_2d”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“tv_chroma_filter”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“tv_luma_filter”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“dot_crawl”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=1</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >SDVO-TV/LVDS</td>
-	<td valign="top" >“brightness”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max= SDVO dependent</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="11" valign="top" >armada</td>
-	<td rowspan="2" valign="top" >CRTC</td>
-	<td valign="top" >"CSC_YUV"</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "Auto" , "CCIR601", "CCIR709" }</td>
-	<td valign="top" >CRTC</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"CSC_RGB"</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "Auto", "Computer system", "Studio" }</td>
-	<td valign="top" >CRTC</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="9" valign="top" >Overlay</td>
-	<td valign="top" >"colorkey"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0xffffff</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"colorkey_min"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0xffffff</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"colorkey_max"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0xffffff</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"colorkey_val"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0xffffff</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"colorkey_alpha"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0xffffff</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"colorkey_mode"</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "disabled", "Y component", "U component"
-	, "V component", "RGB", “R component", "G component", "B component" }</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"brightness"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=256 + 255</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"contrast"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0x7fff</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"saturation"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0x7fff</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="2" valign="top" >exynos</td>
-	<td valign="top" >CRTC</td>
-	<td valign="top" >“mode”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "normal", "blank" }</td>
-	<td valign="top" >CRTC</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >Overlay</td>
-	<td valign="top" >“zpos”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=MAX_PLANE-1</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="2" valign="top" >i2c/ch7006_drv</td>
-	<td valign="top" >Generic</td>
-	<td valign="top" >“scale”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=2</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="1" valign="top" >TV</td>
-	<td valign="top" >“mode”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "PAL", "PAL-M","PAL-N"}, ”PAL-Nc"
-	, "PAL-60", "NTSC-M", "NTSC-J" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="15" valign="top" >nouveau</td>
-	<td rowspan="6" valign="top" >NV10 Overlay</td>
-	<td valign="top" >"colorkey"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0x01ffffff</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“contrast”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=8192-1</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“brightness”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=1024</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“hue”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=359</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“saturation”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=8192-1</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“iturbt_709”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=1</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="2" valign="top" >Nv04 Overlay</td>
-	<td valign="top" >“colorkey”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0x01ffffff</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“brightness”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=1024</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="7" valign="top" >Display</td>
-	<td valign="top" >“dithering mode”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "auto", "off", "on" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“dithering depth”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "auto", "off", "on", "static 2x2", "dynamic 2x2", "temporal" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“underscan”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "auto", "6 bpc", "8 bpc" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“underscan hborder”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=128</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“underscan vborder”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=128</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“vibrant hue”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=180</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >“color vibrance”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=200</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >omap</td>
-	<td valign="top" >Generic</td>
-	<td valign="top" >“zorder”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=3</td>
-	<td valign="top" >CRTC, Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >qxl</td>
-	<td valign="top" >Generic</td>
-	<td valign="top" >“hotplug_mode_update"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=1</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="9" valign="top" >radeon</td>
-	<td valign="top" >DVI-I</td>
-	<td valign="top" >“coherent”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=1</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >DAC enable load detect</td>
-	<td valign="top" >“load detection”</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=1</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >TV Standard</td>
-	<td valign="top" >"tv standard"</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "ntsc", "pal", "pal-m", "pal-60", "ntsc-j"
-	, "scart-pal", "pal-cn", "secam" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >legacy TMDS PLL detect</td>
-	<td valign="top" >"tmds_pll"</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "driver", "bios" }</td>
-	<td valign="top" >-</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="3" valign="top" >Underscan</td>
-	<td valign="top" >"underscan"</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "off", "on", "auto" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"underscan hborder"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=128</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"underscan vborder"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=128</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >Audio</td>
-	<td valign="top" >“audio”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "off", "on", "auto" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >FMT Dithering</td>
-	<td valign="top" >“dither”</td>
-	<td valign="top" >ENUM</td>
-	<td valign="top" >{ "off", "on" }</td>
-	<td valign="top" >Connector</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td rowspan="3" valign="top" >rcar-du</td>
-	<td rowspan="3" valign="top" >Generic</td>
-	<td valign="top" >"alpha"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=255</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"colorkey"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=0, Max=0x01ffffff</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	<tr>
-	<td valign="top" >"zpos"</td>
-	<td valign="top" >RANGE</td>
-	<td valign="top" >Min=1, Max=7</td>
-	<td valign="top" >Plane</td>
-	<td valign="top" >TBD</td>
-	</tr>
-	</tbody>
-	</table>
-    </sect2>
-  </sect1>
-
-  <!-- Internals: vertical blanking -->
-
-  <sect1 id="drm-vertical-blank">
-    <title>Vertical Blanking</title>
-    <para>
-      Vertical blanking plays a major role in graphics rendering. To achieve
-      tear-free display, users must synchronize page flips and/or rendering to
-      vertical blanking. The DRM API offers ioctls to perform page flips
-      synchronized to vertical blanking and wait for vertical blanking.
-    </para>
-    <para>
-      The DRM core handles most of the vertical blanking management logic, which
-      involves filtering out spurious interrupts, keeping race-free blanking
-      counters, coping with counter wrap-around and resets and keeping use
-      counts. It relies on the driver to generate vertical blanking interrupts
-      and optionally provide a hardware vertical blanking counter. Drivers must
-      implement the following operations.
-    </para>
-    <itemizedlist>
-      <listitem>
-        <synopsis>int (*enable_vblank) (struct drm_device *dev, int crtc);
-void (*disable_vblank) (struct drm_device *dev, int crtc);</synopsis>
-        <para>
-	  Enable or disable vertical blanking interrupts for the given CRTC.
-	</para>
-      </listitem>
-      <listitem>
-        <synopsis>u32 (*get_vblank_counter) (struct drm_device *dev, int crtc);</synopsis>
-        <para>
-	  Retrieve the value of the vertical blanking counter for the given
-	  CRTC. If the hardware maintains a vertical blanking counter its value
-	  should be returned. Otherwise drivers can use the
-	  <function>drm_vblank_count</function> helper function to handle this
-	  operation.
-	</para>
-      </listitem>
-    </itemizedlist>
-    <para>
-      Drivers must initialize the vertical blanking handling core with a call to
-      <function>drm_vblank_init</function> in their
-      <methodname>load</methodname> operation. The function will set the struct
-      <structname>drm_device</structname>
-      <structfield>vblank_disable_allowed</structfield> field to 0. This will
-      keep vertical blanking interrupts enabled permanently until the first mode
-      set operation, where <structfield>vblank_disable_allowed</structfield> is
-      set to 1. The reason behind this is not clear. Drivers can set the field
-      to 1 after <function>calling drm_vblank_init</function> to make vertical
-      blanking interrupts dynamically managed from the beginning.
-    </para>
-    <para>
-      Vertical blanking interrupts can be enabled by the DRM core or by drivers
-      themselves (for instance to handle page flipping operations). The DRM core
-      maintains a vertical blanking use count to ensure that the interrupts are
-      not disabled while a user still needs them. To increment the use count,
-      drivers call <function>drm_vblank_get</function>. Upon return vertical
-      blanking interrupts are guaranteed to be enabled.
-    </para>
-    <para>
-      To decrement the use count drivers call
-      <function>drm_vblank_put</function>. Only when the use count drops to zero
-      will the DRM core disable the vertical blanking interrupts after a delay
-      by scheduling a timer. The delay is accessible through the vblankoffdelay
-      module parameter or the <varname>drm_vblank_offdelay</varname> global
-      variable and expressed in milliseconds. Its default value is 5000 ms.
-      Zero means never disable, and a negative value means disable immediately.
-      Drivers may override the behaviour by setting the
-      <structname>drm_device</structname>
-      <structfield>vblank_disable_immediate</structfield> flag, which when set
-      causes vblank interrupts to be disabled immediately regardless of the
-      drm_vblank_offdelay value. The flag should only be set if there's a
-      properly working hardware vblank counter present.
-    </para>
-    <para>
-      When a vertical blanking interrupt occurs drivers only need to call the
-      <function>drm_handle_vblank</function> function to account for the
-      interrupt.
-    </para>
-    <para>
-      Resources allocated by <function>drm_vblank_init</function> must be freed
-      with a call to <function>drm_vblank_cleanup</function> in the driver
-      <methodname>unload</methodname> operation handler.
-    </para>
-    <sect2>
-      <title>Vertical Blanking and Interrupt Handling Functions Reference</title>
-!Edrivers/gpu/drm/drm_irq.c
-!Finclude/drm/drmP.h drm_crtc_vblank_waitqueue
-    </sect2>
-  </sect1>
-
-  <!-- Internals: open/close, file operations and ioctls -->
-
-  <sect1>
-    <title>Open/Close, File Operations and IOCTLs</title>
-    <sect2>
-      <title>Open and Close</title>
-      <synopsis>int (*firstopen) (struct drm_device *);
-void (*lastclose) (struct drm_device *);
-int (*open) (struct drm_device *, struct drm_file *);
-void (*preclose) (struct drm_device *, struct drm_file *);
-void (*postclose) (struct drm_device *, struct drm_file *);</synopsis>
-      <abstract>Open and close handlers. None of those methods are mandatory.
-      </abstract>
-      <para>
-        The <methodname>firstopen</methodname> method is called by the DRM core
-	for legacy UMS (User Mode Setting) drivers only when an application
-	opens a device that has no other opened file handle. UMS drivers can
-	implement it to acquire device resources. KMS drivers can't use the
-	method and must acquire resources in the <methodname>load</methodname>
-	method instead.
-      </para>
-      <para>
-	Similarly the <methodname>lastclose</methodname> method is called when
-	the last application holding a file handle opened on the device closes
-	it, for both UMS and KMS drivers. Additionally, the method is also
-	called at module unload time or, for hot-pluggable devices, when the
-	device is unplugged. The <methodname>firstopen</methodname> and
-	<methodname>lastclose</methodname> calls can thus be unbalanced.
-      </para>
-      <para>
-        The <methodname>open</methodname> method is called every time the device
-	is opened by an application. Drivers can allocate per-file private data
-	in this method and store them in the struct
-	<structname>drm_file</structname> <structfield>driver_priv</structfield>
-	field. Note that the <methodname>open</methodname> method is called
-	before <methodname>firstopen</methodname>.
-      </para>
-      <para>
-        The close operation is split into <methodname>preclose</methodname> and
-	<methodname>postclose</methodname> methods. Drivers must stop and
-	cleanup all per-file operations in the <methodname>preclose</methodname>
-	method. For instance pending vertical blanking and page flip events must
-	be cancelled. No per-file operation is allowed on the file handle after
-	returning from the <methodname>preclose</methodname> method.
-      </para>
-      <para>
-        Finally the <methodname>postclose</methodname> method is called as the
-	last step of the close operation, right before calling the
-	<methodname>lastclose</methodname> method if no other open file handle
-	exists for the device. Drivers that have allocated per-file private data
-	in the <methodname>open</methodname> method should free it here.
-      </para>
-      <para>
-        The <methodname>lastclose</methodname> method should restore CRTC and
-	plane properties to default value, so that a subsequent open of the
-	device will not inherit state from the previous user. It can also be
-	used to execute delayed power switching state changes, e.g. in
-	conjunction with the vga_switcheroo infrastructure (see
-	<xref linkend="vga_switcheroo"/>). Beyond that KMS drivers should not
-	do any further cleanup. Only legacy UMS drivers might need to clean up
-	device state so that the vga console or an independent fbdev driver
-	could take over.
-      </para>
-    </sect2>
-    <sect2>
-      <title>File Operations</title>
-!Pdrivers/gpu/drm/drm_fops.c file operations
-!Edrivers/gpu/drm/drm_fops.c
-    </sect2>
-    <sect2>
-      <title>IOCTLs</title>
-      <synopsis>struct drm_ioctl_desc *ioctls;
-int num_ioctls;</synopsis>
-      <abstract>Driver-specific ioctls descriptors table.</abstract>
-      <para>
-        Driver-specific ioctls numbers start at DRM_COMMAND_BASE. The ioctls
-	descriptors table is indexed by the ioctl number offset from the base
-	value. Drivers can use the DRM_IOCTL_DEF_DRV() macro to initialize the
-	table entries.
-      </para>
-      <para>
-        <programlisting>DRM_IOCTL_DEF_DRV(ioctl, func, flags)</programlisting>
-	<para>
-	  <parameter>ioctl</parameter> is the ioctl name. Drivers must define
-	  the DRM_##ioctl and DRM_IOCTL_##ioctl macros to the ioctl number
-	  offset from DRM_COMMAND_BASE and the ioctl number respectively. The
-	  first macro is private to the device while the second must be exposed
-	  to userspace in a public header.
-	</para>
-	<para>
-	  <parameter>func</parameter> is a pointer to the ioctl handler function
-	  compatible with the <type>drm_ioctl_t</type> type.
-	  <programlisting>typedef int drm_ioctl_t(struct drm_device *dev, void *data,
-		struct drm_file *file_priv);</programlisting>
-	</para>
-	<para>
-	  <parameter>flags</parameter> is a bitmask combination of the following
-	  values. It restricts how the ioctl is allowed to be called.
-	  <itemizedlist>
-	    <listitem><para>
-	      DRM_AUTH - Only authenticated callers allowed
-	    </para></listitem>
-	    <listitem><para>
-	      DRM_MASTER - The ioctl can only be called on the master file
-	      handle
-	    </para></listitem>
-            <listitem><para>
-	      DRM_ROOT_ONLY - Only callers with the SYSADMIN capability allowed
-	    </para></listitem>
-            <listitem><para>
-	      DRM_CONTROL_ALLOW - The ioctl can only be called on a control
-	      device
-	    </para></listitem>
-            <listitem><para>
-	      DRM_UNLOCKED - The ioctl handler will be called without locking
-	      the DRM global mutex. This is the enforced default for kms drivers
-	      (i.e. using the DRIVER_MODESET flag) and hence shouldn't be used
-	      any more for new drivers.
-	    </para></listitem>
-	  </itemizedlist>
-	</para>
-      </para>
-!Edrivers/gpu/drm/drm_ioctl.c
-    </sect2>
-  </sect1>
-  <sect1>
-    <title>Legacy Support Code</title>
-    <para>
-      The section very briefly covers some of the old legacy support code which
-      is only used by old DRM drivers which have done a so-called shadow-attach
-      to the underlying device instead of registering as a real driver. This
-      also includes some of the old generic buffer management and command
-      submission code. Do not use any of this in new and modern drivers.
-    </para>
-
-    <sect2>
-      <title>Legacy Suspend/Resume</title>
-      <para>
-	The DRM core provides some suspend/resume code, but drivers wanting full
-	suspend/resume support should provide save() and restore() functions.
-	These are called at suspend, hibernate, or resume time, and should perform
-	any state save or restore required by your device across suspend or
-	hibernate states.
-      </para>
-      <synopsis>int (*suspend) (struct drm_device *, pm_message_t state);
-  int (*resume) (struct drm_device *);</synopsis>
-      <para>
-	Those are legacy suspend and resume methods which
-	<emphasis>only</emphasis> work with the legacy shadow-attach driver
-	registration functions. New driver should use the power management
-	interface provided by their bus type (usually through
-	the struct <structname>device_driver</structname> dev_pm_ops) and set
-	these methods to NULL.
-      </para>
-    </sect2>
-
-    <sect2>
-      <title>Legacy DMA Services</title>
-      <para>
-	This should cover how DMA mapping etc. is supported by the core.
-	These functions are deprecated and should not be used.
-      </para>
-    </sect2>
-  </sect1>
-  </chapter>
-
-<!-- TODO
-
-- Add a glossary
-- Document the struct_mutex catch-all lock
-- Document connector properties
-
-- Why is the load method optional?
-- What are drivers supposed to set the initial display state to, and how?
-  Connector's DPMS states are not initialized and are thus equal to
-  DRM_MODE_DPMS_ON. The fbcon compatibility layer calls
-  drm_helper_disable_unused_functions(), which disables unused encoders and
-  CRTCs, but doesn't touch the connectors' DPMS state, and
-  drm_helper_connector_dpms() in reaction to fbdev blanking events. Do drivers
-  that don't implement (or just don't use) fbcon compatibility need to call
-  those functions themselves?
-- KMS drivers must call drm_vblank_pre_modeset() and drm_vblank_post_modeset()
-  around mode setting. Should this be done in the DRM core?
-- vblank_disable_allowed is set to 1 in the first drm_vblank_post_modeset()
-  call and never set back to 0. It seems to be safe to permanently set it to 1
-  in drm_vblank_init() for KMS driver, and it might be safe for UMS drivers as
-  well. This should be investigated.
-- crtc and connector .save and .restore operations are only used internally in
-  drivers, should they be removed from the core?
-- encoder mid-layer .save and .restore operations are only used internally in
-  drivers, should they be removed from the core?
-- encoder mid-layer .detect operation is only used internally in drivers,
-  should it be removed from the core?
--->
-
-  <!-- External interfaces -->
-
-  <chapter id="drmExternals">
-    <title>Userland interfaces</title>
-    <para>
-      The DRM core exports several interfaces to applications,
-      generally intended to be used through corresponding libdrm
-      wrapper functions.  In addition, drivers export device-specific
-      interfaces for use by userspace drivers &amp; device-aware
-      applications through ioctls and sysfs files.
-    </para>
-    <para>
-      External interfaces include: memory mapping, context management,
-      DMA operations, AGP management, vblank control, fence
-      management, memory management, and output management.
-    </para>
-    <para>
-      Cover generic ioctls and sysfs layout here.  We only need high-level
-      info, since man pages should cover the rest.
-    </para>
-
-  <!-- External: render nodes -->
-
-    <sect1>
-      <title>Render nodes</title>
-      <para>
-        DRM core provides multiple character-devices for user-space to use.
-        Depending on which device is opened, user-space can perform a different
-        set of operations (mainly ioctls). The primary node is always created
-        and called card&lt;num&gt;. Additionally, a currently
-        unused control node, called controlD&lt;num&gt; is also
-        created. The primary node provides all legacy operations and
-        historically was the only interface used by userspace. With KMS, the
-        control node was introduced. However, the planned KMS control interface
-        has never been written and so the control node stays unused to date.
-      </para>
-      <para>
-        With the increased use of offscreen renderers and GPGPU applications,
-        clients no longer require running compositors or graphics servers to
-        make use of a GPU. But the DRM API required unprivileged clients to
-        authenticate to a DRM-Master prior to getting GPU access. To avoid this
-        step and to grant clients GPU access without authenticating, render
-        nodes were introduced. Render nodes solely serve render clients, that
-        is, no modesetting or privileged ioctls can be issued on render nodes.
-        Only non-global rendering commands are allowed. If a driver supports
-        render nodes, it must advertise it via the DRIVER_RENDER
-        DRM driver capability. If not supported, the primary node must be used
-        for render clients together with the legacy drmAuth authentication
-        procedure.
-      </para>
-      <para>
-        If a driver advertises render node support, DRM core will create a
-        separate render node called renderD&lt;num&gt;. There will
-        be one render node per device. No ioctls except  PRIME-related ioctls
-        will be allowed on this node. Especially GEM_OPEN will be
-        explicitly prohibited. Render nodes are designed to avoid the
-        buffer-leaks, which occur if clients guess the flink names or mmap
-        offsets on the legacy interface. Additionally to this basic interface,
-        drivers must mark their driver-dependent render-only ioctls as
-        DRM_RENDER_ALLOW so render clients can use them. Driver
-        authors must be careful not to allow any privileged ioctls on render
-        nodes.
-      </para>
-      <para>
-        With render nodes, user-space can now control access to the render node
-        via basic file-system access-modes. A running graphics server which
-        authenticates clients on the privileged primary/legacy node is no longer
-        required. Instead, a client can open the render node and is immediately
-        granted GPU access. Communication between clients (or servers) is done
-        via PRIME. FLINK from render node to legacy node is not supported. New
-        clients must not use the insecure FLINK interface.
-      </para>
-      <para>
-        Besides dropping all modeset/global ioctls, render nodes also drop the
-        DRM-Master concept. There is no reason to associate render clients with
-        a DRM-Master as they are independent of any graphics server. Besides,
-        they must work without any running master, anyway.
-        Drivers must be able to run without a master object if they support
-        render nodes. If, on the other hand, a driver requires shared state
-        between clients which is visible to user-space and accessible beyond
-        open-file boundaries, they cannot support render nodes.
-      </para>
-    </sect1>
-
-  <!-- External: vblank handling -->
-
-    <sect1>
-      <title>VBlank event handling</title>
-      <para>
-        The DRM core exposes two vertical blank related ioctls:
-        <variablelist>
-          <varlistentry>
-            <term>DRM_IOCTL_WAIT_VBLANK</term>
-            <listitem>
-              <para>
-                This takes a struct drm_wait_vblank structure as its argument,
-                and it is used to block or request a signal when a specified
-                vblank event occurs.
-              </para>
-            </listitem>
-          </varlistentry>
-          <varlistentry>
-            <term>DRM_IOCTL_MODESET_CTL</term>
-            <listitem>
-              <para>
-		This was only used for user-mode-settind drivers around
-		modesetting changes to allow the kernel to update the vblank
-		interrupt after mode setting, since on many devices the vertical
-		blank counter is reset to 0 at some point during modeset. Modern
-		drivers should not call this any more since with kernel mode
-		setting it is a no-op.
-              </para>
-            </listitem>
-          </varlistentry>
-        </variablelist>
-      </para>
-    </sect1>
-
-  </chapter>
-</part>
-<part id="drmDrivers">
-  <title>DRM Drivers</title>
-
-  <partintro>
-    <para>
-      This second part of the GPU Driver Developer's Guide documents driver
-      code, implementation details and also all the driver-specific userspace
-      interfaces. Especially since all hardware-acceleration interfaces to
-      userspace are driver specific for efficiency and other reasons these
-      interfaces can be rather substantial. Hence every driver has its own
-      chapter.
-    </para>
-  </partintro>
-
-  <chapter id="drmI915">
-    <title>drm/i915 Intel GFX Driver</title>
-    <para>
-      The drm/i915 driver supports all (with the exception of some very early
-      models) integrated GFX chipsets with both Intel display and rendering
-      blocks. This excludes a set of SoC platforms with an SGX rendering unit,
-      those have basic support through the gma500 drm driver.
-    </para>
-    <sect1>
-      <title>Core Driver Infrastructure</title>
-      <para>
-	This section covers core driver infrastructure used by both the display
-	and the GEM parts of the driver.
-      </para>
-      <sect2>
-        <title>Runtime Power Management</title>
-!Pdrivers/gpu/drm/i915/intel_runtime_pm.c runtime pm
-!Idrivers/gpu/drm/i915/intel_runtime_pm.c
-!Idrivers/gpu/drm/i915/intel_uncore.c
-      </sect2>
-      <sect2>
-        <title>Interrupt Handling</title>
-!Pdrivers/gpu/drm/i915/i915_irq.c interrupt handling
-!Fdrivers/gpu/drm/i915/i915_irq.c intel_irq_init intel_irq_init_hw intel_hpd_init
-!Fdrivers/gpu/drm/i915/i915_irq.c intel_runtime_pm_disable_interrupts
-!Fdrivers/gpu/drm/i915/i915_irq.c intel_runtime_pm_enable_interrupts
-      </sect2>
-      <sect2>
-        <title>Intel GVT-g Guest Support(vGPU)</title>
-!Pdrivers/gpu/drm/i915/i915_vgpu.c Intel GVT-g guest support
-!Idrivers/gpu/drm/i915/i915_vgpu.c
-      </sect2>
-    </sect1>
-    <sect1>
-      <title>Display Hardware Handling</title>
-      <para>
-        This section covers everything related to the display hardware including
-        the mode setting infrastructure, plane, sprite and cursor handling and
-        display, output probing and related topics.
-      </para>
-      <sect2>
-        <title>Mode Setting Infrastructure</title>
-        <para>
-          The i915 driver is thus far the only DRM driver which doesn't use the
-          common DRM helper code to implement mode setting sequences. Thus it
-          has its own tailor-made infrastructure for executing a display
-          configuration change.
-        </para>
-      </sect2>
-      <sect2>
-        <title>Frontbuffer Tracking</title>
-!Pdrivers/gpu/drm/i915/intel_frontbuffer.c frontbuffer tracking
-!Idrivers/gpu/drm/i915/intel_frontbuffer.c
-!Fdrivers/gpu/drm/i915/i915_gem.c i915_gem_track_fb
-      </sect2>
-      <sect2>
-        <title>Display FIFO Underrun Reporting</title>
-!Pdrivers/gpu/drm/i915/intel_fifo_underrun.c fifo underrun handling
-!Idrivers/gpu/drm/i915/intel_fifo_underrun.c
-      </sect2>
-      <sect2>
-        <title>Plane Configuration</title>
-        <para>
-	  This section covers plane configuration and composition with the
-	  primary plane, sprites, cursors and overlays. This includes the
-	  infrastructure to do atomic vsync'ed updates of all this state and
-	  also tightly coupled topics like watermark setup and computation,
-	  framebuffer compression and panel self refresh.
-        </para>
-      </sect2>
-      <sect2>
-        <title>Atomic Plane Helpers</title>
-!Pdrivers/gpu/drm/i915/intel_atomic_plane.c atomic plane helpers
-!Idrivers/gpu/drm/i915/intel_atomic_plane.c
-      </sect2>
-      <sect2>
-        <title>Output Probing</title>
-        <para>
-	  This section covers output probing and related infrastructure like the
-	  hotplug interrupt storm detection and mitigation code. Note that the
-	  i915 driver still uses most of the common DRM helper code for output
-	  probing, so those sections fully apply.
-        </para>
-      </sect2>
-      <sect2>
-        <title>Hotplug</title>
-!Pdrivers/gpu/drm/i915/intel_hotplug.c Hotplug
-!Idrivers/gpu/drm/i915/intel_hotplug.c
-      </sect2>
-      <sect2>
-	<title>High Definition Audio</title>
-!Pdrivers/gpu/drm/i915/intel_audio.c High Definition Audio over HDMI and Display Port
-!Idrivers/gpu/drm/i915/intel_audio.c
-!Iinclude/drm/i915_component.h
-      </sect2>
-      <sect2>
-	<title>Panel Self Refresh PSR (PSR/SRD)</title>
-!Pdrivers/gpu/drm/i915/intel_psr.c Panel Self Refresh (PSR/SRD)
-!Idrivers/gpu/drm/i915/intel_psr.c
-      </sect2>
-      <sect2>
-	<title>Frame Buffer Compression (FBC)</title>
-!Pdrivers/gpu/drm/i915/intel_fbc.c Frame Buffer Compression (FBC)
-!Idrivers/gpu/drm/i915/intel_fbc.c
-      </sect2>
-      <sect2>
-        <title>Display Refresh Rate Switching (DRRS)</title>
-!Pdrivers/gpu/drm/i915/intel_dp.c Display Refresh Rate Switching (DRRS)
-!Fdrivers/gpu/drm/i915/intel_dp.c intel_dp_set_drrs_state
-!Fdrivers/gpu/drm/i915/intel_dp.c intel_edp_drrs_enable
-!Fdrivers/gpu/drm/i915/intel_dp.c intel_edp_drrs_disable
-!Fdrivers/gpu/drm/i915/intel_dp.c intel_edp_drrs_invalidate
-!Fdrivers/gpu/drm/i915/intel_dp.c intel_edp_drrs_flush
-!Fdrivers/gpu/drm/i915/intel_dp.c intel_dp_drrs_init
-
-      </sect2>
-      <sect2>
-        <title>DPIO</title>
-!Pdrivers/gpu/drm/i915/i915_reg.h DPIO
-      </sect2>
-
-      <sect2>
-       <title>CSR firmware support for DMC</title>
-!Pdrivers/gpu/drm/i915/intel_csr.c csr support for dmc
-!Idrivers/gpu/drm/i915/intel_csr.c
-      </sect2>
-      <sect2>
-	<title>Video BIOS Table (VBT)</title>
-!Pdrivers/gpu/drm/i915/intel_bios.c Video BIOS Table (VBT)
-!Idrivers/gpu/drm/i915/intel_bios.c
-!Idrivers/gpu/drm/i915/intel_vbt_defs.h
-      </sect2>
-    </sect1>
-
-    <sect1>
-      <title>Memory Management and Command Submission</title>
-      <para>
-	This sections covers all things related to the GEM implementation in the
-	i915 driver.
-      </para>
-      <sect2>
-        <title>Batchbuffer Parsing</title>
-!Pdrivers/gpu/drm/i915/i915_cmd_parser.c batch buffer command parser
-!Idrivers/gpu/drm/i915/i915_cmd_parser.c
-      </sect2>
-      <sect2>
-        <title>Batchbuffer Pools</title>
-!Pdrivers/gpu/drm/i915/i915_gem_batch_pool.c batch pool
-!Idrivers/gpu/drm/i915/i915_gem_batch_pool.c
-      </sect2>
-      <sect2>
-        <title>Logical Rings, Logical Ring Contexts and Execlists</title>
-!Pdrivers/gpu/drm/i915/intel_lrc.c Logical Rings, Logical Ring Contexts and Execlists
-!Idrivers/gpu/drm/i915/intel_lrc.c
-      </sect2>
-      <sect2>
-        <title>Global GTT views</title>
-!Pdrivers/gpu/drm/i915/i915_gem_gtt.c Global GTT views
-!Idrivers/gpu/drm/i915/i915_gem_gtt.c
-      </sect2>
-      <sect2>
-        <title>GTT Fences and Swizzling</title>
-!Idrivers/gpu/drm/i915/i915_gem_fence.c
-        <sect3>
-          <title>Global GTT Fence Handling</title>
-!Pdrivers/gpu/drm/i915/i915_gem_fence.c fence register handling
-        </sect3>
-        <sect3>
-          <title>Hardware Tiling and Swizzling Details</title>
-!Pdrivers/gpu/drm/i915/i915_gem_fence.c tiling swizzling details
-        </sect3>
-      </sect2>
-      <sect2>
-        <title>Object Tiling IOCTLs</title>
-!Idrivers/gpu/drm/i915/i915_gem_tiling.c
-!Pdrivers/gpu/drm/i915/i915_gem_tiling.c buffer object tiling
-      </sect2>
-      <sect2>
-        <title>Buffer Object Eviction</title>
-	<para>
-	  This section documents the interface functions for evicting buffer
-	  objects to make space available in the virtual gpu address spaces.
-	  Note that this is mostly orthogonal to shrinking buffer objects
-	  caches, which has the goal to make main memory (shared with the gpu
-	  through the unified memory architecture) available.
-	</para>
-!Idrivers/gpu/drm/i915/i915_gem_evict.c
-      </sect2>
-      <sect2>
-        <title>Buffer Object Memory Shrinking</title>
-	<para>
-	  This section documents the interface function for shrinking memory
-	  usage of buffer object caches. Shrinking is used to make main memory
-	  available.  Note that this is mostly orthogonal to evicting buffer
-	  objects, which has the goal to make space in gpu virtual address
-	  spaces.
-	</para>
-!Idrivers/gpu/drm/i915/i915_gem_shrinker.c
-      </sect2>
-    </sect1>
-    <sect1>
-      <title>GuC</title>
-      <sect2>
-        <title>GuC-specific firmware loader</title>
-!Pdrivers/gpu/drm/i915/intel_guc_loader.c GuC-specific firmware loader
-!Idrivers/gpu/drm/i915/intel_guc_loader.c
-      </sect2>
-      <sect2>
-        <title>GuC-based command submission</title>
-!Pdrivers/gpu/drm/i915/i915_guc_submission.c GuC-based command submission
-!Idrivers/gpu/drm/i915/i915_guc_submission.c
-      </sect2>
-      <sect2>
-        <title>GuC Firmware Layout</title>
-!Pdrivers/gpu/drm/i915/intel_guc_fwif.h GuC Firmware Layout
-      </sect2>
-    </sect1>
-
-    <sect1>
-      <title> Tracing </title>
-      <para>
-    This sections covers all things related to the tracepoints implemented in
-    the i915 driver.
-      </para>
-      <sect2>
-        <title> i915_ppgtt_create and i915_ppgtt_release </title>
-!Pdrivers/gpu/drm/i915/i915_trace.h i915_ppgtt_create and i915_ppgtt_release tracepoints
-      </sect2>
-      <sect2>
-        <title> i915_context_create and i915_context_free </title>
-!Pdrivers/gpu/drm/i915/i915_trace.h i915_context_create and i915_context_free tracepoints
-      </sect2>
-      <sect2>
-        <title> switch_mm </title>
-!Pdrivers/gpu/drm/i915/i915_trace.h switch_mm tracepoint
-      </sect2>
-    </sect1>
-
-  </chapter>
-!Cdrivers/gpu/drm/i915/i915_irq.c
-</part>
-
-<part id="vga_switcheroo">
-  <title>vga_switcheroo</title>
-  <partintro>
-!Pdrivers/gpu/vga/vga_switcheroo.c Overview
-  </partintro>
-
-  <chapter id="modes_of_use">
-    <title>Modes of Use</title>
-    <sect1>
-      <title>Manual switching and manual power control</title>
-!Pdrivers/gpu/vga/vga_switcheroo.c Manual switching and manual power control
-    </sect1>
-    <sect1>
-      <title>Driver power control</title>
-!Pdrivers/gpu/vga/vga_switcheroo.c Driver power control
-    </sect1>
-  </chapter>
-
-  <chapter id="api">
-    <title>API</title>
-    <sect1>
-      <title>Public functions</title>
-!Edrivers/gpu/vga/vga_switcheroo.c
-    </sect1>
-    <sect1>
-      <title>Public structures</title>
-!Finclude/linux/vga_switcheroo.h vga_switcheroo_handler
-!Finclude/linux/vga_switcheroo.h vga_switcheroo_client_ops
-    </sect1>
-    <sect1>
-      <title>Public constants</title>
-!Finclude/linux/vga_switcheroo.h vga_switcheroo_handler_flags_t
-!Finclude/linux/vga_switcheroo.h vga_switcheroo_client_id
-!Finclude/linux/vga_switcheroo.h vga_switcheroo_state
-    </sect1>
-    <sect1>
-      <title>Private structures</title>
-!Fdrivers/gpu/vga/vga_switcheroo.c vgasr_priv
-!Fdrivers/gpu/vga/vga_switcheroo.c vga_switcheroo_client
-    </sect1>
-  </chapter>
-
-  <chapter id="handlers">
-    <title>Handlers</title>
-    <sect1>
-      <title>apple-gmux Handler</title>
-!Pdrivers/platform/x86/apple-gmux.c Overview
-!Pdrivers/platform/x86/apple-gmux.c Interrupt
-      <sect2>
-        <title>Graphics mux</title>
-!Pdrivers/platform/x86/apple-gmux.c Graphics mux
-      </sect2>
-      <sect2>
-        <title>Power control</title>
-!Pdrivers/platform/x86/apple-gmux.c Power control
-      </sect2>
-      <sect2>
-        <title>Backlight control</title>
-!Pdrivers/platform/x86/apple-gmux.c Backlight control
-      </sect2>
-      <sect2>
-        <title>Public functions</title>
-!Iinclude/linux/apple-gmux.h
-      </sect2>
-    </sect1>
-  </chapter>
-
-!Cdrivers/gpu/vga/vga_switcheroo.c
-!Cinclude/linux/vga_switcheroo.h
-!Cdrivers/platform/x86/apple-gmux.c
-</part>
-
-</book>
diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt
index 1179850f453c..c55df2911136 100644
--- a/Documentation/PCI/MSI-HOWTO.txt
+++ b/Documentation/PCI/MSI-HOWTO.txt
@@ -78,422 +78,111 @@ CONFIG_PCI_MSI option.
 
 4.2 Using MSI
 
-Most of the hard work is done for the driver in the PCI layer.  It simply
-has to request that the PCI layer set up the MSI capability for this
+Most of the hard work is done for the driver in the PCI layer.  The driver
+simply has to request that the PCI layer set up the MSI capability for this
 device.
 
-4.2.1 pci_enable_msi
+To automatically use MSI or MSI-X interrupt vectors, use the following
+function:
 
-int pci_enable_msi(struct pci_dev *dev)
+  int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs,
+		unsigned int max_vecs, unsigned int flags);
 
-A successful call allocates ONE interrupt to the device, regardless
-of how many MSIs the device supports.  The device is switched from
-pin-based interrupt mode to MSI mode.  The dev->irq number is changed
-to a new number which represents the message signaled interrupt;
-consequently, this function should be called before the driver calls
-request_irq(), because an MSI is delivered via a vector that is
-different from the vector of a pin-based interrupt.
+which allocates up to max_vecs interrupt vectors for a PCI device.  It
+returns the number of vectors allocated or a negative error.  If the device
+has a requirements for a minimum number of vectors the driver can pass a
+min_vecs argument set to this limit, and the PCI core will return -ENOSPC
+if it can't meet the minimum number of vectors.
 
-4.2.2 pci_enable_msi_range
+The flags argument should normally be set to 0, but can be used to pass the
+PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support
+MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in
+case the device does not support legacy interrupt lines.
 
-int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
+By default this function will spread the interrupts around the available
+CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY
+flag.
 
-This function allows a device driver to request any number of MSI
-interrupts within specified range from 'minvec' to 'maxvec'.
+To get the Linux IRQ numbers passed to request_irq() and free_irq() and the
+vectors, use the following function:
 
-If this function returns a positive number it indicates the number of
-MSI interrupts that have been successfully allocated.  In this case
-the device is switched from pin-based interrupt mode to MSI mode and
-updates dev->irq to be the lowest of the new interrupts assigned to it.
-The other interrupts assigned to the device are in the range dev->irq
-to dev->irq + returned value - 1.  Device driver can use the returned
-number of successfully allocated MSI interrupts to further allocate
-and initialize device resources.
+  int pci_irq_vector(struct pci_dev *dev, unsigned int nr);
 
-If this function returns a negative number, it indicates an error and
-the driver should not attempt to request any more MSI interrupts for
-this device.
+Any allocated resources should be freed before removing the device using
+the following function:
 
-This function should be called before the driver calls request_irq(),
-because MSI interrupts are delivered via vectors that are different
-from the vector of a pin-based interrupt.
+  void pci_free_irq_vectors(struct pci_dev *dev);
 
-It is ideal if drivers can cope with a variable number of MSI interrupts;
-there are many reasons why the platform may not be able to provide the
-exact number that a driver asks for.
+If a device supports both MSI-X and MSI capabilities, this API will use the
+MSI-X facilities in preference to the MSI facilities.  MSI-X supports any
+number of interrupts between 1 and 2048.  In contrast, MSI is restricted to
+a maximum of 32 interrupts (and must be a power of two).  In addition, the
+MSI interrupt vectors must be allocated consecutively, so the system might
+not be able to allocate as many vectors for MSI as it could for MSI-X.  On
+some platforms, MSI interrupts must all be targeted at the same set of CPUs
+whereas MSI-X interrupts can all be targeted at different CPUs.
 
-There could be devices that can not operate with just any number of MSI
-interrupts within a range.  See chapter 4.3.1.3 to get the idea how to
-handle such devices for MSI-X - the same logic applies to MSI.
+If a device supports neither MSI-X or MSI it will fall back to a single
+legacy IRQ vector.
 
-4.2.1.1 Maximum possible number of MSI interrupts
+The typical usage of MSI or MSI-X interrupts is to allocate as many vectors
+as possible, likely up to the limit supported by the device.  If nvec is
+larger than the number supported by the device it will automatically be
+capped to the supported limit, so there is no need to query the number of
+vectors supported beforehand:
 
-The typical usage of MSI interrupts is to allocate as many vectors as
-possible, likely up to the limit returned by pci_msi_vec_count() function:
-
-static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec)
-{
-	return pci_enable_msi_range(pdev, 1, nvec);
-}
-
-Note the value of 'minvec' parameter is 1.  As 'minvec' is inclusive,
-the value of 0 would be meaningless and could result in error.
-
-Some devices have a minimal limit on number of MSI interrupts.
-In this case the function could look like this:
-
-static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec)
-{
-	return pci_enable_msi_range(pdev, FOO_DRIVER_MINIMUM_NVEC, nvec);
-}
-
-4.2.1.2 Exact number of MSI interrupts
+	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0);
+	if (nvec < 0)
+		goto out_err;
 
 If a driver is unable or unwilling to deal with a variable number of MSI
-interrupts it could request a particular number of interrupts by passing
-that number to pci_enable_msi_range() function as both 'minvec' and 'maxvec'
-parameters:
-
-static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec)
-{
-	return pci_enable_msi_range(pdev, nvec, nvec);
-}
-
-Note, unlike pci_enable_msi_exact() function, which could be also used to
-enable a particular number of MSI-X interrupts, pci_enable_msi_range()
-returns either a negative errno or 'nvec' (not negative errno or 0 - as
-pci_enable_msi_exact() does).
-
-4.2.1.3 Single MSI mode
-
-The most notorious example of the request type described above is
-enabling the single MSI mode for a device.  It could be done by passing
-two 1s as 'minvec' and 'maxvec':
-
-static int foo_driver_enable_single_msi(struct pci_dev *pdev)
-{
-	return pci_enable_msi_range(pdev, 1, 1);
-}
-
-Note, unlike pci_enable_msi() function, which could be also used to
-enable the single MSI mode, pci_enable_msi_range() returns either a
-negative errno or 1 (not negative errno or 0 - as pci_enable_msi()
-does).
-
-4.2.3 pci_enable_msi_exact
-
-int pci_enable_msi_exact(struct pci_dev *dev, int nvec)
-
-This variation on pci_enable_msi_range() call allows a device driver to
-request exactly 'nvec' MSIs.
-
-If this function returns a negative number, it indicates an error and
-the driver should not attempt to request any more MSI interrupts for
-this device.
-
-By contrast with pci_enable_msi_range() function, pci_enable_msi_exact()
-returns zero in case of success, which indicates MSI interrupts have been
-successfully allocated.
-
-4.2.4 pci_disable_msi
-
-void pci_disable_msi(struct pci_dev *dev)
-
-This function should be used to undo the effect of pci_enable_msi_range().
-Calling it restores dev->irq to the pin-based interrupt number and frees
-the previously allocated MSIs.  The interrupts may subsequently be assigned
-to another device, so drivers should not cache the value of dev->irq.
-
-Before calling this function, a device driver must always call free_irq()
-on any interrupt for which it previously called request_irq().
-Failure to do so results in a BUG_ON(), leaving the device with
-MSI enabled and thus leaking its vector.
-
-4.2.4 pci_msi_vec_count
-
-int pci_msi_vec_count(struct pci_dev *dev)
-
-This function could be used to retrieve the number of MSI vectors the
-device requested (via the Multiple Message Capable register). The MSI
-specification only allows the returned value to be a power of two,
-up to a maximum of 2^5 (32).
-
-If this function returns a negative number, it indicates the device is
-not capable of sending MSIs.
-
-If this function returns a positive number, it indicates the maximum
-number of MSI interrupt vectors that could be allocated.
-
-4.3 Using MSI-X
-
-The MSI-X capability is much more flexible than the MSI capability.
-It supports up to 2048 interrupts, each of which can be controlled
-independently.  To support this flexibility, drivers must use an array of
-`struct msix_entry':
-
-struct msix_entry {
-	u16 	vector; /* kernel uses to write alloc vector */
-	u16	entry; /* driver uses to specify entry */
-};
-
-This allows for the device to use these interrupts in a sparse fashion;
-for example, it could use interrupts 3 and 1027 and yet allocate only a
-two-element array.  The driver is expected to fill in the 'entry' value
-in each element of the array to indicate for which entries the kernel
-should assign interrupts; it is invalid to fill in two entries with the
-same number.
-
-4.3.1 pci_enable_msix_range
-
-int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
-			  int minvec, int maxvec)
-
-Calling this function asks the PCI subsystem to allocate any number of
-MSI-X interrupts within specified range from 'minvec' to 'maxvec'.
-The 'entries' argument is a pointer to an array of msix_entry structs
-which should be at least 'maxvec' entries in size.
-
-On success, the device is switched into MSI-X mode and the function
-returns the number of MSI-X interrupts that have been successfully
-allocated.  In this case the 'vector' member in entries numbered from
-0 to the returned value - 1 is populated with the interrupt number;
-the driver should then call request_irq() for each 'vector' that it
-decides to use.  The device driver is responsible for keeping track of the
-interrupts assigned to the MSI-X vectors so it can free them again later.
-Device driver can use the returned number of successfully allocated MSI-X
-interrupts to further allocate and initialize device resources.
-
-If this function returns a negative number, it indicates an error and
-the driver should not attempt to allocate any more MSI-X interrupts for
-this device.
-
-This function, in contrast with pci_enable_msi_range(), does not adjust
-dev->irq.  The device will not generate interrupts for this interrupt
-number once MSI-X is enabled.
-
-Device drivers should normally call this function once per device
-during the initialization phase.
-
-It is ideal if drivers can cope with a variable number of MSI-X interrupts;
-there are many reasons why the platform may not be able to provide the
-exact number that a driver asks for.
-
-There could be devices that can not operate with just any number of MSI-X
-interrupts within a range.  E.g., an network adapter might need let's say
-four vectors per each queue it provides.  Therefore, a number of MSI-X
-interrupts allocated should be a multiple of four.  In this case interface
-pci_enable_msix_range() can not be used alone to request MSI-X interrupts
-(since it can allocate any number within the range, without any notion of
-the multiple of four) and the device driver should master a custom logic
-to request the required number of MSI-X interrupts.
-
-4.3.1.1 Maximum possible number of MSI-X interrupts
-
-The typical usage of MSI-X interrupts is to allocate as many vectors as
-possible, likely up to the limit returned by pci_msix_vec_count() function:
-
-static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
-{
-	return pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
-				     1, nvec);
-}
-
-Note the value of 'minvec' parameter is 1.  As 'minvec' is inclusive,
-the value of 0 would be meaningless and could result in error.
-
-Some devices have a minimal limit on number of MSI-X interrupts.
-In this case the function could look like this:
-
-static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
-{
-	return pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
-				     FOO_DRIVER_MINIMUM_NVEC, nvec);
-}
-
-4.3.1.2 Exact number of MSI-X interrupts
-
-If a driver is unable or unwilling to deal with a variable number of MSI-X
-interrupts it could request a particular number of interrupts by passing
-that number to pci_enable_msix_range() function as both 'minvec' and 'maxvec'
-parameters:
-
-static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
-{
-	return pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
-				     nvec, nvec);
-}
-
-Note, unlike pci_enable_msix_exact() function, which could be also used to
-enable a particular number of MSI-X interrupts, pci_enable_msix_range()
-returns either a negative errno or 'nvec' (not negative errno or 0 - as
-pci_enable_msix_exact() does).
-
-4.3.1.3 Specific requirements to the number of MSI-X interrupts
-
-As noted above, there could be devices that can not operate with just any
-number of MSI-X interrupts within a range.  E.g., let's assume a device that
-is only capable sending the number of MSI-X interrupts which is a power of
-two.  A routine that enables MSI-X mode for such device might look like this:
-
-/*
- * Assume 'minvec' and 'maxvec' are non-zero
- */
-static int foo_driver_enable_msix(struct foo_adapter *adapter,
-				  int minvec, int maxvec)
-{
-	int rc;
-
-	minvec = roundup_pow_of_two(minvec);
-	maxvec = rounddown_pow_of_two(maxvec);
-
-	if (minvec > maxvec)
-		return -ERANGE;
-
-retry:
-	rc = pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
-				   maxvec, maxvec);
-	/*
-	 * -ENOSPC is the only error code allowed to be analyzed
-	 */
-	if (rc == -ENOSPC) {
-		if (maxvec == 1)
-			return -ENOSPC;
-
-		maxvec /= 2;
-
-		if (minvec > maxvec)
-			return -ENOSPC;
-
-		goto retry;
-	}
-
-	return rc;
-}
-
-Note how pci_enable_msix_range() return value is analyzed for a fallback -
-any error code other than -ENOSPC indicates a fatal error and should not
-be retried.
-
-4.3.2 pci_enable_msix_exact
-
-int pci_enable_msix_exact(struct pci_dev *dev,
-			  struct msix_entry *entries, int nvec)
-
-This variation on pci_enable_msix_range() call allows a device driver to
-request exactly 'nvec' MSI-Xs.
-
-If this function returns a negative number, it indicates an error and
-the driver should not attempt to allocate any more MSI-X interrupts for
-this device.
-
-By contrast with pci_enable_msix_range() function, pci_enable_msix_exact()
-returns zero in case of success, which indicates MSI-X interrupts have been
-successfully allocated.
-
-Another version of a routine that enables MSI-X mode for a device with
-specific requirements described in chapter 4.3.1.3 might look like this:
-
-/*
- * Assume 'minvec' and 'maxvec' are non-zero
- */
-static int foo_driver_enable_msix(struct foo_adapter *adapter,
-				  int minvec, int maxvec)
-{
-	int rc;
-
-	minvec = roundup_pow_of_two(minvec);
-	maxvec = rounddown_pow_of_two(maxvec);
-
-	if (minvec > maxvec)
-		return -ERANGE;
-
-retry:
-	rc = pci_enable_msix_exact(adapter->pdev,
-				   adapter->msix_entries, maxvec);
-
-	/*
-	 * -ENOSPC is the only error code allowed to be analyzed
-	 */
-	if (rc == -ENOSPC) {
-		if (maxvec == 1)
-			return -ENOSPC;
-
-		maxvec /= 2;
-
-		if (minvec > maxvec)
-			return -ENOSPC;
-
-		goto retry;
-	} else if (rc < 0) {
-		return rc;
-	}
-
-	return maxvec;
-}
-
-4.3.3 pci_disable_msix
-
-void pci_disable_msix(struct pci_dev *dev)
-
-This function should be used to undo the effect of pci_enable_msix_range().
-It frees the previously allocated MSI-X interrupts. The interrupts may
-subsequently be assigned to another device, so drivers should not cache
-the value of the 'vector' elements over a call to pci_disable_msix().
-
-Before calling this function, a device driver must always call free_irq()
-on any interrupt for which it previously called request_irq().
-Failure to do so results in a BUG_ON(), leaving the device with
-MSI-X enabled and thus leaking its vector.
-
-4.3.3 The MSI-X Table
-
-The MSI-X capability specifies a BAR and offset within that BAR for the
-MSI-X Table.  This address is mapped by the PCI subsystem, and should not
-be accessed directly by the device driver.  If the driver wishes to
-mask or unmask an interrupt, it should call disable_irq() / enable_irq().
+interrupts it can request a particular number of interrupts by passing that
+number to pci_alloc_irq_vectors() function as both 'min_vecs' and
+'max_vecs' parameters:
 
-4.3.4 pci_msix_vec_count
+	ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0);
+	if (ret < 0)
+		goto out_err;
 
-int pci_msix_vec_count(struct pci_dev *dev)
+The most notorious example of the request type described above is enabling
+the single MSI mode for a device.  It could be done by passing two 1s as
+'min_vecs' and 'max_vecs':
 
-This function could be used to retrieve number of entries in the device
-MSI-X table.
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, 0);
+	if (ret < 0)
+		goto out_err;
 
-If this function returns a negative number, it indicates the device is
-not capable of sending MSI-Xs.
+Some devices might not support using legacy line interrupts, in which case
+the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform
+can't provide MSI or MSI-X interrupts:
 
-If this function returns a positive number, it indicates the maximum
-number of MSI-X interrupt vectors that could be allocated.
+	nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY);
+	if (nvec < 0)
+		goto out_err;
 
-4.4 Handling devices implementing both MSI and MSI-X capabilities
+4.3 Legacy APIs
 
-If a device implements both MSI and MSI-X capabilities, it can
-run in either MSI mode or MSI-X mode, but not both simultaneously.
-This is a requirement of the PCI spec, and it is enforced by the
-PCI layer.  Calling pci_enable_msi_range() when MSI-X is already
-enabled or pci_enable_msix_range() when MSI is already enabled
-results in an error.  If a device driver wishes to switch between MSI
-and MSI-X at runtime, it must first quiesce the device, then switch
-it back to pin-interrupt mode, before calling pci_enable_msi_range()
-or pci_enable_msix_range() and resuming operation.  This is not expected
-to be a common operation but may be useful for debugging or testing
-during development.
+The following old APIs to enable and disable MSI or MSI-X interrupts should
+not be used in new code:
 
-4.5 Considerations when using MSIs
+  pci_enable_msi()		/* deprecated */
+  pci_enable_msi_range()	/* deprecated */
+  pci_enable_msi_exact()	/* deprecated */
+  pci_disable_msi()		/* deprecated */
+  pci_enable_msix_range()	/* deprecated */
+  pci_enable_msix_exact()	/* deprecated */
+  pci_disable_msix()		/* deprecated */
 
-4.5.1 Choosing between MSI-X and MSI
+Additionally there are APIs to provide the number of supported MSI or MSI-X
+vectors: pci_msi_vec_count() and pci_msix_vec_count().  In general these
+should be avoided in favor of letting pci_alloc_irq_vectors() cap the
+number of vectors.  If you have a legitimate special use case for the count
+of vectors we might have to revisit that decision and add a
+pci_nr_irq_vectors() helper that handles MSI and MSI-X transparently.
 
-If your device supports both MSI-X and MSI capabilities, you should use
-the MSI-X facilities in preference to the MSI facilities.  As mentioned
-above, MSI-X supports any number of interrupts between 1 and 2048.
-In contrast, MSI is restricted to a maximum of 32 interrupts (and
-must be a power of two).  In addition, the MSI interrupt vectors must
-be allocated consecutively, so the system might not be able to allocate
-as many vectors for MSI as it could for MSI-X.  On some platforms, MSI
-interrupts must all be targeted at the same set of CPUs whereas MSI-X
-interrupts can all be targeted at different CPUs.
+4.4 Considerations when using MSIs
 
-4.5.2 Spinlocks
+4.4.1 Spinlocks
 
 Most device drivers have a per-device spinlock which is taken in the
 interrupt handler.  With pin-based interrupts or a single MSI, it is not
@@ -505,7 +194,7 @@ acquire the spinlock.  Such deadlocks can be avoided by using
 spin_lock_irqsave() or spin_lock_irq() which disable local interrupts
 and acquire the lock (see Documentation/DocBook/kernel-locking).
 
-4.6 How to tell whether MSI/MSI-X is enabled on a device
+4.5 How to tell whether MSI/MSI-X is enabled on a device
 
 Using 'lspci -v' (as root) may show some devices with "MSI", "Message
 Signalled Interrupts" or "MSI-X" capabilities.  Each of these capabilities
diff --git a/Documentation/arm/Atmel/README b/Documentation/arm/Atmel/README
index 0931cf7e2e56..6ca78f818dbf 100644
--- a/Documentation/arm/Atmel/README
+++ b/Documentation/arm/Atmel/README
@@ -91,9 +91,15 @@ the Atmel website: http://www.atmel.com.
           http://www.atmel.com/Images/Atmel-11238-32-bit-Cortex-A5-Microcontroller-SAMA5D4_Datasheet.pdf
 
       - sama5d2 family
-        - sama5d27
+        - sama5d21
+        - sama5d22
+        - sama5d23
+        - sama5d24
+        - sama5d26
+        - sama5d27 (device superset)
+        - sama5d28 (device superset + environmental monitors)
         + Datasheet
-          Coming soon
+          http://www.atmel.com/Images/Atmel-11267-32-bit-Cortex-A5-Microcontroller-SAMA5D2_Datasheet.pdf
 
 
 Linux kernel information
diff --git a/Documentation/coccinelle.txt b/Documentation/coccinelle.txt
index 7f773d51fdd9..01fb1dae3163 100644
--- a/Documentation/coccinelle.txt
+++ b/Documentation/coccinelle.txt
@@ -38,6 +38,15 @@ as a regular user, and install it with
 
         sudo make install
 
+ Supplemental documentation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For supplemental documentation refer to the wiki:
+
+https://bottest.wiki.kernel.org/coccicheck
+
+The wiki documentation always refers to the linux-next version of the script.
+
  Using Coccinelle on the Linux kernel
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -94,11 +103,26 @@ To enable verbose messages set the V= variable, for example:
 
    make coccicheck MODE=report V=1
 
+ Coccinelle parallelization
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
 By default, coccicheck tries to run as parallel as possible. To change
 the parallelism, set the J= variable. For example, to run across 4 CPUs:
 
    make coccicheck MODE=report J=4
 
+As of Coccinelle 1.0.2 Coccinelle uses Ocaml parmap for parallelization,
+if support for this is detected you will benefit from parmap parallelization.
+
+When parmap is enabled coccicheck will enable dynamic load balancing by using
+'--chunksize 1' argument, this ensures we keep feeding threads with work
+one by one, so that we avoid the situation where most work gets done by only
+a few threads. With dynamic load balancing, if a thread finishes early we keep
+feeding it more work.
+
+When parmap is enabled, if an error occurs in Coccinelle, this error
+value is propagated back, the return value of the 'make coccicheck'
+captures this return value.
 
  Using Coccinelle with a single semantic patch
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -142,15 +166,118 @@ semantic patch as shown in the previous section.
 The "report" mode is the default. You can select another one with the
 MODE variable explained above.
 
+ Debugging Coccinelle SmPL patches
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Using coccicheck is best as it provides in the spatch command line
+include options matching the options used when we compile the kernel.
+You can learn what these options are by using V=1, you could then
+manually run Coccinelle with debug options added.
+
+Alternatively you can debug running Coccinelle against SmPL patches
+by asking for stderr to be redirected to stderr, by default stderr
+is redirected to /dev/null, if you'd like to capture stderr you
+can specify the DEBUG_FILE="file.txt" option to coccicheck. For
+instance:
+
+    rm -f cocci.err
+    make coccicheck COCCI=scripts/coccinelle/free/kfree.cocci MODE=report DEBUG_FILE=cocci.err
+    cat cocci.err
+
+You can use SPFLAGS to add debugging flags, for instance you may want to
+add both --profile --show-trying to SPFLAGS when debugging. For instance
+you may want to use:
+
+    rm -f err.log
+    export COCCI=scripts/coccinelle/misc/irqf_oneshot.cocci
+    make coccicheck DEBUG_FILE="err.log" MODE=report SPFLAGS="--profile --show-trying" M=./drivers/mfd/arizona-irq.c
+
+err.log will now have the profiling information, while stdout will
+provide some progress information as Coccinelle moves forward with
+work.
+
+DEBUG_FILE support is only supported when using coccinelle >= 1.2.
+
+ .cocciconfig support
+~~~~~~~~~~~~~~~~~~~~~~
+
+Coccinelle supports reading .cocciconfig for default Coccinelle options that
+should be used every time spatch is spawned, the order of precedence for
+variables for .cocciconfig is as follows:
+
+  o Your current user's home directory is processed first
+  o Your directory from which spatch is called is processed next
+  o The directory provided with the --dir option is processed last, if used
+
+Since coccicheck runs through make, it naturally runs from the kernel
+proper dir, as such the second rule above would be implied for picking up a
+.cocciconfig when using 'make coccicheck'.
+
+'make coccicheck' also supports using M= targets.If you do not supply
+any M= target, it is assumed you want to target the entire kernel.
+The kernel coccicheck script has:
+
+    if [ "$KBUILD_EXTMOD" = "" ] ; then
+        OPTIONS="--dir $srctree $COCCIINCLUDE"
+    else
+        OPTIONS="--dir $KBUILD_EXTMOD $COCCIINCLUDE"
+    fi
+
+KBUILD_EXTMOD is set when an explicit target with M= is used. For both cases
+the spatch --dir argument is used, as such third rule applies when whether M=
+is used or not, and when M= is used the target directory can have its own
+.cocciconfig file. When M= is not passed as an argument to coccicheck the
+target directory is the same as the directory from where spatch was called.
+
+If not using the kernel's coccicheck target, keep the above precedence
+order logic of .cocciconfig reading. If using the kernel's coccicheck target,
+override any of the kernel's .coccicheck's settings using SPFLAGS.
+
+We help Coccinelle when used against Linux with a set of sensible defaults
+options for Linux with our own Linux .cocciconfig. This hints to coccinelle
+git can be used for 'git grep' queries over coccigrep. A timeout of 200
+seconds should suffice for now.
+
+The options picked up by coccinelle when reading a .cocciconfig do not appear
+as arguments to spatch processes running on your system, to confirm what
+options will be used by Coccinelle run:
+
+      spatch --print-options-only
+
+You can override with your own preferred index option by using SPFLAGS. Take
+note that when there are conflicting options Coccinelle takes precedence for
+the last options passed. Using .cocciconfig is possible to use idutils, however
+given the order of precedence followed by Coccinelle, since the kernel now
+carries its own .cocciconfig, you will need to use SPFLAGS to use idutils if
+desired. See below section "Additional flags" for more details on how to use
+idutils.
+
  Additional flags
 ~~~~~~~~~~~~~~~~~~
 
 Additional flags can be passed to spatch through the SPFLAGS
-variable.
+variable. This works as Coccinelle respects the last flags
+given to it when options are in conflict.
 
     make SPFLAGS=--use-glimpse coccicheck
+
+Coccinelle supports idutils as well but requires coccinelle >= 1.0.6.
+When no ID file is specified coccinelle assumes your ID database file
+is in the file .id-utils.index on the top level of the kernel, coccinelle
+carries a script scripts/idutils_index.sh which creates the database with
+
+    mkid -i C --output .id-utils.index
+
+If you have another database filename you can also just symlink with this
+name.
+
     make SPFLAGS=--use-idutils coccicheck
 
+Alternatively you can specify the database filename explicitly, for
+instance:
+
+    make SPFLAGS="--use-idutils /full-path/to/ID" coccicheck
+
 See spatch --help to learn more about spatch options.
 
 Note that the '--use-glimpse' and '--use-idutils' options
@@ -159,6 +286,25 @@ thus active by default. However, by indexing the code with
 one of these tools, and according to the cocci file used,
 spatch could proceed the entire code base more quickly.
 
+ SmPL patch specific options
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+SmPL patches can have their own requirements for options passed
+to Coccinelle. SmPL patch specific options can be provided by
+providing them at the top of the SmPL patch, for instance:
+
+// Options: --no-includes --include-headers
+
+ SmPL patch Coccinelle requirements
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As Coccinelle features get added some more advanced SmPL patches
+may require newer versions of Coccinelle. If an SmPL patch requires
+at least a version of Coccinelle, this can be specified as follows,
+as an example if requiring at least Coccinelle >= 1.0.5:
+
+// Requires: 1.0.5
+
  Proposing new semantic patches
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/Documentation/devicetree/bindings/arm/arm,scpi.txt b/Documentation/devicetree/bindings/arm/arm,scpi.txt
index 313dabdc14f9..faa4b44572e3 100644
--- a/Documentation/devicetree/bindings/arm/arm,scpi.txt
+++ b/Documentation/devicetree/bindings/arm/arm,scpi.txt
@@ -87,10 +87,33 @@ Required properties:
 			 implementation for the IDs to use. For Juno
 			 R0 and Juno R1 refer to [3].
 
+Power domain bindings for the power domains based on SCPI Message Protocol
+------------------------------------------------------------
+
+This binding uses the generic power domain binding[4].
+
+PM domain providers
+===================
+
+Required properties:
+ - #power-domain-cells : Should be 1. Contains the device or the power
+			 domain ID value used by SCPI commands.
+ - num-domains: Total number of power domains provided by SCPI. This is
+		needed as the SCPI message protocol lacks a mechanism to
+		query this information at runtime.
+
+PM domain consumers
+===================
+
+Required properties:
+ - power-domains : A phandle and PM domain specifier as defined by bindings of
+                   the power controller specified by phandle.
+
 [0] http://infocenter.arm.com/help/topic/com.arm.doc.dui0922b/index.html
 [1] Documentation/devicetree/bindings/clock/clock-bindings.txt
 [2] Documentation/devicetree/bindings/thermal/thermal.txt
 [3] http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.dui0922b/apas03s22.html
+[4] Documentation/devicetree/bindings/power/power_domain.txt
 
 Example:
 
@@ -144,6 +167,12 @@ scpi_protocol: scpi@2e000000 {
 		compatible = "arm,scpi-sensors";
 		#thermal-sensor-cells = <1>;
 	};
+
+	scpi_devpd: scpi-power-domains {
+		compatible = "arm,scpi-power-domains";
+		num-domains = <2>;
+		#power-domain-cells = <1>;
+	};
 };
 
 cpu@0 {
@@ -156,6 +185,7 @@ hdlcd@7ff60000 {
 	...
 	reg = <0 0x7ff60000 0 0x1000>;
 	clocks = <&scpi_clk 4>;
+	power-domains = <&scpi_devpd 1>;
 };
 
 thermal-zones {
@@ -186,3 +216,7 @@ The thermal-sensors property in the soc_thermal node uses the
 temperature sensor provided by SCP firmware to setup a thermal
 zone. The ID "3" is the sensor identifier for the temperature sensor
 as used by the firmware.
+
+The num-domains property in scpi-power-domains domain specifies that
+SCPI provides 2 power domains. The hdlcd node uses the power domain with
+domain ID 1.
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm11351-cpu-method.txt b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm11351-cpu-method.txt
index 8240c023e202..e3f996920403 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm11351-cpu-method.txt
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm11351-cpu-method.txt
@@ -5,7 +5,7 @@ CPUs in the following Broadcom SoCs:
   BCM11130, BCM11140, BCM11351, BCM28145, BCM28155, BCM21664
 
 The enable method is specified by defining the following required
-properties in the "cpus" device tree node:
+properties in the "cpu" device tree node:
   - enable-method = "brcm,bcm11351-cpu-method";
   - secondary-boot-reg = <...>;
 
@@ -19,8 +19,6 @@ Example:
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		enable-method = "brcm,bcm11351-cpu-method";
-		secondary-boot-reg = <0x3500417c>;
 
 		cpu0: cpu@0 {
 			device_type = "cpu";
@@ -32,5 +30,7 @@ Example:
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <1>;
+			enable-method = "brcm,bcm11351-cpu-method";
+			secondary-boot-reg = <0x3500417c>;
 		};
 	};
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm23550-cpu-method.txt b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm23550-cpu-method.txt
new file mode 100644
index 000000000000..a3af54c0e404
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm23550-cpu-method.txt
@@ -0,0 +1,36 @@
+Broadcom Kona Family CPU Enable Method
+--------------------------------------
+This binding defines the enable method used for starting secondary
+CPUs in the following Broadcom SoCs:
+  BCM23550
+
+The enable method is specified by defining the following required
+properties in the "cpu" device tree node:
+  - enable-method = "brcm,bcm23550";
+  - secondary-boot-reg = <...>;
+
+The secondary-boot-reg property is a u32 value that specifies the
+physical address of the register used to request the ROM holding pen
+code release a secondary CPU.  The value written to the register is
+formed by encoding the target CPU id into the low bits of the
+physical start address it should jump to.
+
+Example:
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <1>;
+			enable-method = "brcm,bcm23550";
+			secondary-boot-reg = <0x3500417c>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm23550.txt b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm23550.txt
new file mode 100644
index 000000000000..080baad923d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm23550.txt
@@ -0,0 +1,15 @@
+Broadcom BCM23550 device tree bindings
+--------------------------------------
+
+This document describes the device tree bindings for boards with the BCM23550
+SoC.
+
+Required root node property:
+  - compatible: brcm,bcm23550
+
+Example:
+	/ {
+		model = "BCM23550 SoC";
+		compatible = "brcm,bcm23550";
+		[...]
+	}
diff --git a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm2835.txt b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm2835.txt
index 11d3056dc2bd..6ffe08778465 100644
--- a/Documentation/devicetree/bindings/arm/bcm/brcm,bcm2835.txt
+++ b/Documentation/devicetree/bindings/arm/bcm/brcm,bcm2835.txt
@@ -30,6 +30,10 @@ Raspberry Pi 2 Model B
 Required root node properties:
 compatible = "raspberrypi,2-model-b", "brcm,bcm2836";
 
+Raspberry Pi 3 Model B
+Required root node properties:
+compatible = "raspberrypi,3-model-b", "brcm,bcm2837";
+
 Raspberry Pi Compute Module
 Required root node properties:
 compatible = "raspberrypi,compute-module", "brcm,bcm2835";
diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt
index 93147c0c8a0e..fcbae6a5e6c1 100644
--- a/Documentation/devicetree/bindings/arm/coresight.txt
+++ b/Documentation/devicetree/bindings/arm/coresight.txt
@@ -12,14 +12,33 @@ its hardware characteristcs.
 
 	* compatible: These have to be supplemented with "arm,primecell" as
 	  drivers are using the AMBA bus interface.  Possible values include:
-		- "arm,coresight-etb10", "arm,primecell";
-		- "arm,coresight-tpiu", "arm,primecell";
-		- "arm,coresight-tmc", "arm,primecell";
-		- "arm,coresight-funnel", "arm,primecell";
-		- "arm,coresight-etm3x", "arm,primecell";
-		- "arm,coresight-etm4x", "arm,primecell";
-		- "qcom,coresight-replicator1x", "arm,primecell";
-		- "arm,coresight-stm", "arm,primecell"; [1]
+		- Embedded Trace Buffer (version 1.0):
+			"arm,coresight-etb10", "arm,primecell";
+
+		- Trace Port Interface Unit:
+			"arm,coresight-tpiu", "arm,primecell";
+
+		- Trace Memory Controller, used for Embedded Trace Buffer(ETB),
+		  Embedded Trace FIFO(ETF) and Embedded Trace Router(ETR)
+		  configuration.  The configuration mode (ETB, ETF, ETR) is
+		  discovered at boot time when the device is probed.
+			"arm,coresight-tmc", "arm,primecell";
+
+		- Trace Funnel:
+			"arm,coresight-funnel", "arm,primecell";
+
+		- Embedded Trace Macrocell (version 3.x) and
+					Program Flow Trace Macrocell:
+			"arm,coresight-etm3x", "arm,primecell";
+
+		- Embedded Trace Macrocell (version 4.x):
+			"arm,coresight-etm4x", "arm,primecell";
+
+		- Qualcomm Configurable Replicator (version 1.x):
+			"qcom,coresight-replicator1x", "arm,primecell";
+
+		- System Trace Macrocell:
+			"arm,coresight-stm", "arm,primecell"; [1]
 
 	* reg: physical base address and length of the register
 	  set(s) of the component.
diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt
index 3f0cbbb8395f..e6782d50cbcd 100644
--- a/Documentation/devicetree/bindings/arm/cpus.txt
+++ b/Documentation/devicetree/bindings/arm/cpus.txt
@@ -193,6 +193,8 @@ nodes to be present and contain the properties described below.
 			    "allwinner,sun6i-a31"
 			    "allwinner,sun8i-a23"
 			    "arm,realview-smp"
+			    "brcm,bcm11351-cpu-method"
+			    "brcm,bcm23550"
 			    "brcm,bcm-nsp-smp"
 			    "brcm,brahma-b15"
 			    "marvell,armada-375-smp"
@@ -204,6 +206,7 @@ nodes to be present and contain the properties described below.
 			    "qcom,gcc-msm8660"
 			    "qcom,kpss-acc-v1"
 			    "qcom,kpss-acc-v2"
+			    "renesas,apmu"
 			    "rockchip,rk3036-smp"
 			    "rockchip,rk3066-smp"
 			    "ste,dbx500-smp"
diff --git a/Documentation/devicetree/bindings/arm/hisilicon/hi3519-sysctrl.txt b/Documentation/devicetree/bindings/arm/hisilicon/hi3519-sysctrl.txt
new file mode 100644
index 000000000000..115c5be0bd0b
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/hisilicon/hi3519-sysctrl.txt
@@ -0,0 +1,14 @@
+* Hisilicon Hi3519 System Controller Block
+
+This bindings use the following binding:
+Documentation/devicetree/bindings/mfd/syscon.txt
+
+Required properties:
+- compatible: "hisilicon,hi3519-sysctrl".
+- reg: the register region of this block
+
+Examples:
+sysctrl: system-controller@12010000 {
+	compatible = "hisilicon,hi3519-sysctrl", "syscon";
+	reg = <0x12010000 0x1000>;
+};
diff --git a/Documentation/devicetree/bindings/arm/l2c2x0.txt b/Documentation/devicetree/bindings/arm/l2c2x0.txt
index c453ab5553cd..917199f17965 100644
--- a/Documentation/devicetree/bindings/arm/l2c2x0.txt
+++ b/Documentation/devicetree/bindings/arm/l2c2x0.txt
@@ -86,10 +86,10 @@ Optional properties:
   firmware)
 - arm,dynamic-clock-gating : L2 dynamic clock gating. Value: <0> (forcibly
   disable), <1> (forcibly enable), property absent (OS specific behavior,
-  preferrably retain firmware settings)
+  preferably retain firmware settings)
 - arm,standby-mode: L2 standby mode enable. Value <0> (forcibly disable),
   <1> (forcibly enable), property absent (OS specific behavior,
-  preferrably retain firmware settings)
+  preferably retain firmware settings)
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/arm/mediatek.txt b/Documentation/devicetree/bindings/arm/mediatek.txt
index d9c2a37a4090..c860b245d8c8 100644
--- a/Documentation/devicetree/bindings/arm/mediatek.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek.txt
@@ -10,6 +10,7 @@ compatible: Must contain one of
    "mediatek,mt6580"
    "mediatek,mt6589"
    "mediatek,mt6592"
+   "mediatek,mt6755"
    "mediatek,mt6795"
    "mediatek,mt7623"
    "mediatek,mt8127"
@@ -31,6 +32,9 @@ Supported boards:
 - Evaluation board for MT6592:
     Required root node properties:
       - compatible = "mediatek,mt6592-evb", "mediatek,mt6592";
+- Evaluation phone for MT6755(Helio P10):
+    Required root node properties:
+      - compatible = "mediatek,mt6755-evb", "mediatek,mt6755";
 - Evaluation board for MT6795(Helio X10):
     Required root node properties:
       - compatible = "mediatek,mt6795-evb", "mediatek,mt6795";
diff --git a/Documentation/devicetree/bindings/arm/olimex.txt b/Documentation/devicetree/bindings/arm/olimex.txt
index 007fb5c685a1..d726aeca56be 100644
--- a/Documentation/devicetree/bindings/arm/olimex.txt
+++ b/Documentation/devicetree/bindings/arm/olimex.txt
@@ -1,5 +1,9 @@
-Olimex i.MX Platforms Device Tree Bindings
-------------------------------------------
+Olimex Device Tree Bindings
+---------------------------
+
+SAM9-L9260 Board
+Required root node properties:
+    - compatible = "olimex,sam9-l9260", "atmel,at91sam9260";
 
 i.MX23 Olinuxino Low Cost Board
 Required root node properties:
diff --git a/Documentation/devicetree/bindings/arm/rockchip.txt b/Documentation/devicetree/bindings/arm/rockchip.txt
index 715d960d5eea..666864517069 100644
--- a/Documentation/devicetree/bindings/arm/rockchip.txt
+++ b/Documentation/devicetree/bindings/arm/rockchip.txt
@@ -107,6 +107,9 @@ Rockchip platforms device tree bindings
     Required root node properties:
      - compatible = "rockchip,rk3228-evb", "rockchip,rk3228";
 
+- Rockchip RK3229 Evaluation board:
+     - compatible = "rockchip,rk3229-evb", "rockchip,rk3229";
+
 - Rockchip RK3399 evb:
     Required root node properties:
       - compatible = "rockchip,rk3399-evb", "rockchip,rk3399";
diff --git a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
index f5deace2b380..0ea7f14ef294 100644
--- a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
+++ b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
@@ -47,6 +47,7 @@ Required root node properties:
 	- "hardkernel,odroid-u3"  - for Exynos4412-based Hardkernel Odroid U3.
 	- "hardkernel,odroid-x"   - for Exynos4412-based Hardkernel Odroid X.
 	- "hardkernel,odroid-x2"  - for Exynos4412-based Hardkernel Odroid X2.
+	- "hardkernel,odroid-xu"  - for Exynos5410-based Hardkernel Odroid XU.
 	- "hardkernel,odroid-xu3" - for Exynos5422-based Hardkernel Odroid XU3.
 	- "hardkernel,odroid-xu3-lite" - for Exynos5422-based Hardkernel
 					 Odroid XU3 Lite board.
diff --git a/Documentation/devicetree/bindings/arm/shmobile.txt b/Documentation/devicetree/bindings/arm/shmobile.txt
index 9cf67e48f222..1df32d339da5 100644
--- a/Documentation/devicetree/bindings/arm/shmobile.txt
+++ b/Documentation/devicetree/bindings/arm/shmobile.txt
@@ -29,6 +29,8 @@ SoCs:
     compatible = "renesas,r8a7794"
   - R-Car H3 (R8A77950)
     compatible = "renesas,r8a7795"
+  - R-Car M3-W (R8A77960)
+    compatible = "renesas,r8a7796"
 
 
 Boards:
@@ -39,6 +41,8 @@ Boards:
     compatible = "renesas,ape6evm", "renesas,r8a73a4"
   - Atmark Techno Armadillo-800 EVA
     compatible = "renesas,armadillo800eva"
+  - Blanche (RTP0RC7792SEB00010S)
+    compatible = "renesas,blanche", "renesas,r8a7792"
   - BOCK-W
     compatible = "renesas,bockw", "renesas,r8a7778"
   - Genmai (RTK772100BC00000BR)
@@ -61,5 +65,7 @@ Boards:
     compatible = "renesas,porter", "renesas,r8a7791"
   - Salvator-X (RTP0RC7795SIPB0010S)
     compatible = "renesas,salvator-x", "renesas,r8a7795";
+  - Salvator-X
+    compatible = "renesas,salvator-x", "renesas,r8a7796";
   - SILK (RTP0RC7794LCB00011S)
     compatible = "renesas,silk", "renesas,r8a7794"
diff --git a/Documentation/devicetree/bindings/arm/tegra.txt b/Documentation/devicetree/bindings/arm/tegra.txt
index 73278c6d2dc3..b5a4342c1d46 100644
--- a/Documentation/devicetree/bindings/arm/tegra.txt
+++ b/Documentation/devicetree/bindings/arm/tegra.txt
@@ -32,7 +32,11 @@ board-specific compatible values:
   nvidia,whistler
   toradex,apalis_t30
   toradex,apalis_t30-eval
+  toradex,apalis-tk1
+  toradex,apalis-tk1-eval
   toradex,colibri_t20-512
+  toradex,colibri_t30
+  toradex,colibri_t30-eval-v3
   toradex,iris
 
 Trusted Foundations
diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt
index 87adfb227ca9..fedc213b5f1a 100644
--- a/Documentation/devicetree/bindings/ata/ahci-platform.txt
+++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt
@@ -10,6 +10,7 @@ PHYs.
 Required properties:
 - compatible        : compatible string, one of:
   - "allwinner,sun4i-a10-ahci"
+  - "brcm,iproc-ahci"
   - "hisilicon,hisi-ahci"
   - "cavium,octeon-7130-ahci"
   - "ibm,476gtr-ahci"
diff --git a/Documentation/devicetree/bindings/bus/nvidia,tegra210-aconnect.txt b/Documentation/devicetree/bindings/bus/nvidia,tegra210-aconnect.txt
new file mode 100644
index 000000000000..7ff13be1750b
--- /dev/null
+++ b/Documentation/devicetree/bindings/bus/nvidia,tegra210-aconnect.txt
@@ -0,0 +1,45 @@
+NVIDIA Tegra ACONNECT Bus
+
+The Tegra ACONNECT bus is an AXI switch which is used to connnect various
+components inside the Audio Processing Engine (APE). All CPU accesses to
+the APE subsystem go through the ACONNECT via an APB to AXI wrapper.
+
+Required properties:
+- compatible: Must be "nvidia,tegra210-aconnect".
+- clocks: Must contain the entries for the APE clock (TEGRA210_CLK_APE),
+  and APE interface clock (TEGRA210_CLK_APB2APE).
+- clock-names: Must contain the names "ape" and "apb2ape" for the corresponding
+  'clocks' entries.
+- power-domains: Must contain a phandle that points to the audio powergate
+  (namely 'aud') for Tegra210.
+- #address-cells: The number of cells used to represent physical base addresses
+  in the aconnect address space. Should be 1.
+- #size-cells: The number of cells used to represent the size of an address
+  range in the aconnect address space. Should be 1.
+- ranges: Mapping of the aconnect address space to the CPU address space.
+
+All devices accessed via the ACONNNECT are described by child-nodes.
+
+Example:
+
+	aconnect@702c0000 {
+		compatible = "nvidia,tegra210-aconnect";
+		clocks = <&tegra_car TEGRA210_CLK_APE>,
+			 <&tegra_car TEGRA210_CLK_APB2APE>;
+		clock-names = "ape", "apb2ape";
+		power-domains = <&pd_audio>;
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x702c0000 0x0 0x702c0000 0x00040000>;
+
+		status = "disabled";
+
+		child1 {
+			...
+		};
+
+		child2 {
+			...
+		};
+	};
diff --git a/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt b/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt
new file mode 100644
index 000000000000..ce06435d28ed
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/amlogic,gxbb-clkc.txt
@@ -0,0 +1,36 @@
+* Amlogic GXBB Clock and Reset Unit
+
+The Amlogic GXBB clock controller generates and supplies clock to various
+controllers within the SoC.
+
+Required Properties:
+
+- compatible: should be "amlogic,gxbb-clkc"
+- reg: physical base address of the clock controller and length of memory
+       mapped region.
+
+- #clock-cells: should be 1.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. All available clocks are defined as
+preprocessor macros in the dt-bindings/clock/gxbb-clkc.h header and can be
+used in device tree sources.
+
+Example: Clock controller node:
+
+	clkc: clock-controller@c883c000 {
+		#clock-cells = <1>;
+		compatible = "amlogic,gxbb-clkc";
+		reg = <0x0 0xc883c000 0x0 0x3db>;
+	};
+
+Example: UART controller node that consumes the clock generated by the clock
+  controller:
+
+	uart_AO: serial@c81004c0 {
+		compatible = "amlogic,meson-uart";
+		reg = <0xc81004c0 0x14>;
+		interrupts = <0 90 1>;
+		clocks = <&clkc CLKID_CLK81>;
+		status = "disabled";
+	};
diff --git a/Documentation/devicetree/bindings/clock/clps711x-clock.txt b/Documentation/devicetree/bindings/clock/clps711x-clock.txt
index ce5a7476f05d..f1bd53f79d91 100644
--- a/Documentation/devicetree/bindings/clock/clps711x-clock.txt
+++ b/Documentation/devicetree/bindings/clock/clps711x-clock.txt
@@ -1,7 +1,7 @@
 * Clock bindings for the Cirrus Logic CLPS711X CPUs
 
 Required properties:
-- compatible       : Shall contain "cirrus,clps711x-clk".
+- compatible       : Shall contain "cirrus,ep7209-clk".
 - reg              : Address of the internal register set.
 - startup-frequency: Factory set CPU startup frequency in HZ.
 - #clock-cells     : Should be <1>.
@@ -13,7 +13,7 @@ for the full list of CLPS711X clock IDs.
 Example:
 	clks: clks@80000000 {
 		#clock-cells = <1>;
-		compatible = "cirrus,ep7312-clk", "cirrus,clps711x-clk";
+		compatible = "cirrus,ep7312-clk", "cirrus,ep7209-clk";
 		reg = <0x80000000 0xc000>;
 		startup-frequency = <73728000>;
 	};
diff --git a/Documentation/devicetree/bindings/clock/fixed-factor-clock.txt b/Documentation/devicetree/bindings/clock/fixed-factor-clock.txt
index 1bae8527eb9b..189467a7188a 100644
--- a/Documentation/devicetree/bindings/clock/fixed-factor-clock.txt
+++ b/Documentation/devicetree/bindings/clock/fixed-factor-clock.txt
@@ -14,6 +14,10 @@ Required properties:
 Optional properties:
 - clock-output-names : From common clock binding.
 
+Some clocks that require special treatments are also handled by that
+driver, with the compatibles:
+  - allwinner,sun4i-a10-pll3-2x-clk
+
 Example:
 	clock {
 		compatible = "fixed-factor-clock";
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.txt
index fefb8023020f..394d725ac7e0 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.txt
@@ -13,7 +13,8 @@ They provide the following functionalities:
 
 Required Properties:
   - compatible: Must be one of:
-      - "renesas,r8a7795-cpg-mssr" for the r8a7795 SoC
+      - "renesas,r8a7795-cpg-mssr" for the r8a7795 SoC (R-Car H3)
+      - "renesas,r8a7796-cpg-mssr" for the r8a7796 SoC (R-Car M3-W)
 
   - reg: Base address and length of the memory resource used by the CPG/MSSR
     block
@@ -21,8 +22,8 @@ Required Properties:
   - clocks: References to external parent clocks, one entry for each entry in
     clock-names
   - clock-names: List of external parent clock names. Valid names are:
-      - "extal" (r8a7795)
-      - "extalr" (r8a7795)
+      - "extal" (r8a7795, r8a7796)
+      - "extalr" (r8a7795, r8a7796)
 
   - #clock-cells: Must be 2
       - For CPG core clocks, the two clock specifier cells must be "CPG_CORE"
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
index 16ed18155160..da578ebdda28 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
@@ -17,6 +17,7 @@ Required Properties:
     - "renesas,r8a7779-mstp-clocks" for R8A7779 (R-Car H1) MSTP gate clocks
     - "renesas,r8a7790-mstp-clocks" for R8A7790 (R-Car H2) MSTP gate clocks
     - "renesas,r8a7791-mstp-clocks" for R8A7791 (R-Car M2-W) MSTP gate clocks
+    - "renesas,r8a7792-mstp-clocks" for R8A7792 (R-Car V2H) MSTP gate clocks
     - "renesas,r8a7793-mstp-clocks" for R8A7793 (R-Car M2-N) MSTP gate clocks
     - "renesas,r8a7794-mstp-clocks" for R8A7794 (R-Car E2) MSTP gate clocks
     - "renesas,sh73a0-mstp-clocks" for SH73A0 (SH-MobileAG5) MSTP gate clocks
diff --git a/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
index 2a9a8edc8f35..f8c05bb4116e 100644
--- a/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
@@ -10,6 +10,7 @@ Required Properties:
   - compatible: Must be one of
     - "renesas,r8a7790-cpg-clocks" for the r8a7790 CPG
     - "renesas,r8a7791-cpg-clocks" for the r8a7791 CPG
+    - "renesas,r8a7792-cpg-clocks" for the r8a7792 CPG
     - "renesas,r8a7793-cpg-clocks" for the r8a7793 CPG
     - "renesas,r8a7794-cpg-clocks" for the r8a7794 CPG
     and "renesas,rcar-gen2-cpg-clocks" as a fallback.
diff --git a/Documentation/devicetree/bindings/clock/sunxi-ccu.txt b/Documentation/devicetree/bindings/clock/sunxi-ccu.txt
new file mode 100644
index 000000000000..cb91507ffb1e
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/sunxi-ccu.txt
@@ -0,0 +1,24 @@
+Allwinner Clock Control Unit Binding
+------------------------------------
+
+Required properties :
+- compatible: must contain one of the following compatible:
+		- "allwinner,sun8i-h3-ccu"
+
+- reg: Must contain the registers base address and length
+- clocks: phandle to the oscillators feeding the CCU. Two are needed:
+  - "hosc": the high frequency oscillator (usually at 24MHz)
+  - "losc": the low frequency oscillator (usually at 32kHz)
+- clock-names: Must contain the clock names described just above
+- #clock-cells : must contain 1
+- #reset-cells : must contain 1
+
+Example:
+ccu: clock@01c20000 {
+	compatible = "allwinner,sun8i-h3-ccu";
+	reg = <0x01c20000 0x400>;
+	clocks = <&osc24M>, <&osc32k>;
+	clock-names = "hosc", "losc";
+	#clock-cells = <1>;
+	#reset-cells = <1>;
+};
diff --git a/Documentation/devicetree/bindings/display/arm,malidp.txt b/Documentation/devicetree/bindings/display/arm,malidp.txt
new file mode 100644
index 000000000000..2f7870983ef1
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/arm,malidp.txt
@@ -0,0 +1,65 @@
+ARM Mali-DP
+
+The following bindings apply to a family of Display Processors sold as
+licensable IP by ARM Ltd. The bindings describe the Mali DP500, DP550 and
+DP650 processors that offer multiple composition layers, support for
+rotation and scaling output.
+
+Required properties:
+  - compatible: should be one of
+	"arm,mali-dp500"
+	"arm,mali-dp550"
+	"arm,mali-dp650"
+    depending on the particular implementation present in the hardware
+  - reg: Physical base address and size of the block of registers used by
+    the processor.
+  - interrupts: Interrupt list, as defined in ../interrupt-controller/interrupts.txt,
+    interrupt client nodes.
+  - interrupt-names: name of the engine inside the processor that will
+    use the corresponding interrupt. Should be one of "DE" or "SE".
+  - clocks: A list of phandle + clock-specifier pairs, one for each entry
+    in 'clock-names'
+  - clock-names: A list of clock names. It should contain:
+      - "pclk": for the APB interface clock
+      - "aclk": for the AXI interface clock
+      - "mclk": for the main processor clock
+      - "pxlclk": for the pixel clock feeding the output PLL of the processor.
+  - arm,malidp-output-port-lines: Array of u8 values describing the number
+    of output lines per channel (R, G and B).
+
+Required sub-nodes:
+  - port: The Mali DP connection to an encoder input port. The connection
+    is modelled using the OF graph bindings specified in
+    Documentation/devicetree/bindings/graph.txt
+
+Optional properties:
+  - memory-region: phandle to a node describing memory (see
+    Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt)
+    to be used for the framebuffer; if not present, the framebuffer may
+    be located anywhere in memory.
+
+
+Example:
+
+/ {
+	...
+
+	dp0: malidp@6f200000 {
+		compatible = "arm,mali-dp650";
+		reg = <0 0x6f200000 0 0x20000>;
+		memory-region = <&display_reserved>;
+		interrupts = <0 168 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 168 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "DE", "SE";
+		clocks = <&oscclk2>, <&fpgaosc0>, <&fpgaosc1>, <&fpgaosc1>;
+		clock-names = "pxlclk", "mclk", "aclk", "pclk";
+		arm,malidp-output-port-lines = /bits/ 8 <8 8 8>;
+		port {
+			dp0_output: endpoint {
+				remote-endpoint = <&tda998x_2_input>;
+			};
+		};
+	};
+
+	...
+};
diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt b/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt
index 96c25ee01501..6532a59c9b43 100644
--- a/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt
+++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt
@@ -1,13 +1,19 @@
-Analog Device ADV7511(W)/13 HDMI Encoders
+Analog Device ADV7511(W)/13/33 HDMI Encoders
 -----------------------------------------
 
-The ADV7511, ADV7511W and ADV7513 are HDMI audio and video transmitters
+The ADV7511, ADV7511W, ADV7513 and ADV7533 are HDMI audio and video transmitters
 compatible with HDMI 1.4 and DVI 1.0. They support color space conversion,
-S/PDIF, CEC and HDCP.
+S/PDIF, CEC and HDCP. ADV7533 supports the DSI interface for input pixels, while
+the others support RGB interface.
 
 Required properties:
 
-- compatible: Should be one of "adi,adv7511", "adi,adv7511w" or "adi,adv7513"
+- compatible: Should be one of:
+		"adi,adv7511"
+		"adi,adv7511w"
+		"adi,adv7513"
+		"adi,adv7533"
+
 - reg: I2C slave address
 
 The ADV7511 supports a large number of input data formats that differ by their
@@ -32,6 +38,11 @@ The following input format properties are required except in "rgb 1x" and
 - adi,input-justification: The input bit justification ("left", "evenly",
   "right").
 
+The following properties are required for ADV7533:
+
+- adi,dsi-lanes: Number of DSI data lanes connected to the DSI host. It should
+  be one of 1, 2, 3 or 4.
+
 Optional properties:
 
 - interrupts: Specifier for the ADV7511 interrupt
@@ -42,13 +53,18 @@ Optional properties:
 - adi,embedded-sync: The input uses synchronization signals embedded in the
   data stream (similar to BT.656). Defaults to separate H/V synchronization
   signals.
+- adi,disable-timing-generator: Only for ADV7533. Disables the internal timing
+  generator. The chip will rely on the sync signals in the DSI data lanes,
+  rather than generate its own timings for HDMI output.
 
 Required nodes:
 
 The ADV7511 has two video ports. Their connections are modelled using the OF
 graph bindings specified in Documentation/devicetree/bindings/graph.txt.
 
-- Video port 0 for the RGB or YUV input
+- Video port 0 for the RGB, YUV or DSI input. In the case of ADV7533, the
+  remote endpoint phandle should be a reference to a valid mipi_dsi_host device
+  node.
 - Video port 1 for the HDMI output
 
 
diff --git a/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt b/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt
index 4f2ba8c13d92..4a0f4f7682ad 100644
--- a/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt
+++ b/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt
@@ -5,6 +5,7 @@ Required properties for dp-controller:
 		platform specific such as:
 		 * "samsung,exynos5-dp"
 		 * "rockchip,rk3288-dp"
+		 * "rockchip,rk3399-edp"
 	-reg:
 		physical base address of the controller and length
 		of memory mapped region.
diff --git a/Documentation/devicetree/bindings/display/bridge/sii902x.txt b/Documentation/devicetree/bindings/display/bridge/sii902x.txt
new file mode 100644
index 000000000000..56a3e68ccb80
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/bridge/sii902x.txt
@@ -0,0 +1,35 @@
+sii902x HDMI bridge bindings
+
+Required properties:
+	- compatible: "sil,sii9022"
+	- reg: i2c address of the bridge
+
+Optional properties:
+	- interrupts-extended or interrupt-parent + interrupts: describe
+	  the interrupt line used to inform the host about hotplug events.
+	- reset-gpios: OF device-tree gpio specification for RST_N pin.
+
+Optional subnodes:
+	- video input: this subnode can contain a video input port node
+	  to connect the bridge to a display controller output (See this
+	  documentation [1]).
+
+[1]: Documentation/devicetree/bindings/media/video-interfaces.txt
+
+Example:
+	hdmi-bridge@39 {
+		compatible = "sil,sii9022";
+		reg = <0x39>;
+		reset-gpios = <&pioA 1 0>;
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				bridge_in: endpoint {
+					remote-endpoint = <&dc_out>;
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.txt b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.txt
new file mode 100644
index 000000000000..e3f6aa6a214d
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.txt
@@ -0,0 +1,53 @@
+Toshiba TC358767 eDP bridge bindings
+
+Required properties:
+ - compatible: "toshiba,tc358767"
+ - reg: i2c address of the bridge, 0x68 or 0x0f, depending on bootstrap pins
+ - clock-names: should be "ref"
+ - clocks: OF device-tree clock specification for refclk input. The reference
+   clock rate must be 13 MHz, 19.2 MHz, 26 MHz, or 38.4 MHz.
+
+Optional properties:
+ - shutdown-gpios: OF device-tree gpio specification for SD pin
+                   (active high shutdown input)
+ - reset-gpios: OF device-tree gpio specification for RSTX pin
+                (active low system reset)
+ - ports: the ports node can contain video interface port nodes to connect
+   to a DPI/DSI source and to an eDP/DP sink according to [1][2]:
+    - port@0: DSI input port
+    - port@1: DPI input port
+    - port@2: eDP/DP output port
+
+[1]: Documentation/devicetree/bindings/graph.txt
+[2]: Documentation/devicetree/bindings/media/video-interfaces.txt
+
+Example:
+	edp-bridge@68 {
+		compatible = "toshiba,tc358767";
+		reg = <0x68>;
+		shutdown-gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>;
+		clock-names = "ref";
+		clocks = <&edp_refclk>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@1 {
+				reg = <1>;
+
+				bridge_in: endpoint {
+					remote-endpoint = <&dpi_out>;
+				};
+			};
+
+			port@2 {
+				reg = <2>;
+
+				bridge_out: endpoint {
+					remote-endpoint = <&panel_in>;
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/cirrus,clps711x-fb.txt b/Documentation/devicetree/bindings/display/cirrus,clps711x-fb.txt
index d685be898d0c..e9c65746e2f1 100644
--- a/Documentation/devicetree/bindings/display/cirrus,clps711x-fb.txt
+++ b/Documentation/devicetree/bindings/display/cirrus,clps711x-fb.txt
@@ -1,7 +1,7 @@
 * Currus Logic CLPS711X Framebuffer
 
 Required properties:
-- compatible: Shall contain "cirrus,clps711x-fb".
+- compatible: Shall contain "cirrus,ep7209-fb".
 - reg       : Physical base address and length of the controller's registers +
               location and size of the framebuffer memory.
 - clocks    : phandle + clock specifier pair of the FB reference clock.
@@ -18,7 +18,7 @@ Optional properties:
 
 Example:
 	fb: fb@800002c0 {
-		compatible = "cirrus,ep7312-fb", "cirrus,clps711x-fb";
+		compatible = "cirrus,ep7312-fb", "cirrus,ep7209-fb";
 		reg = <0x800002c0 0xd44>, <0x60000000 0xc000>;
 		clocks = <&clks 2>;
 		lcd-supply = <&reg5v0>;
diff --git a/Documentation/devicetree/bindings/display/connector/hdmi-connector.txt b/Documentation/devicetree/bindings/display/connector/hdmi-connector.txt
index acd5668b1ce1..508aee461e0d 100644
--- a/Documentation/devicetree/bindings/display/connector/hdmi-connector.txt
+++ b/Documentation/devicetree/bindings/display/connector/hdmi-connector.txt
@@ -8,6 +8,7 @@ Required properties:
 Optional properties:
 - label: a symbolic name for the connector
 - hpd-gpios: HPD GPIO number
+- ddc-i2c-bus: phandle link to the I2C controller used for DDC EDID probing
 
 Required nodes:
 - Video port for HDMI input
diff --git a/Documentation/devicetree/bindings/display/fsl,dcu.txt b/Documentation/devicetree/bindings/display/fsl,dcu.txt
index ae55cde1b69e..63ec2a624aa9 100644
--- a/Documentation/devicetree/bindings/display/fsl,dcu.txt
+++ b/Documentation/devicetree/bindings/display/fsl,dcu.txt
@@ -12,7 +12,7 @@ Required properties:
 - clock-names:		Should be "dcu" and "pix"
 			See ../clocks/clock-bindings.txt for details.
 - big-endian		Boolean property, LS1021A DCU registers are big-endian.
-- fsl,panel:		The phandle to panel node.
+- port			Video port for the panel output
 
 Optional properties:
 - fsl,tcon:		The phandle to the timing controller node.
@@ -24,6 +24,11 @@ dcu: dcu@2ce0000 {
 	clocks = <&platform_clk 0>, <&platform_clk 0>;
 	clock-names = "dcu", "pix";
 	big-endian;
-	fsl,panel = <&panel>;
 	fsl,tcon = <&tcon>;
+
+	port {
+		dcu_out: endpoint {
+			remote-endpoint = <&panel_out>;
+	     };
+	};
 };
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,hdmi.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,hdmi.txt
new file mode 100644
index 000000000000..7b124242b0c5
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,hdmi.txt
@@ -0,0 +1,148 @@
+Mediatek HDMI Encoder
+=====================
+
+The Mediatek HDMI encoder can generate HDMI 1.4a or MHL 2.0 signals from
+its parallel input.
+
+Required properties:
+- compatible: Should be "mediatek,<chip>-hdmi".
+- reg: Physical base address and length of the controller's registers
+- interrupts: The interrupt signal from the function block.
+- clocks: device clocks
+  See Documentation/devicetree/bindings/clock/clock-bindings.txt for details.
+- clock-names: must contain "pixel", "pll", "bclk", and "spdif".
+- phys: phandle link to the HDMI PHY node.
+  See Documentation/devicetree/bindings/phy/phy-bindings.txt for details.
+- phy-names: must contain "hdmi"
+- mediatek,syscon-hdmi: phandle link and register offset to the system
+  configuration registers. For mt8173 this must be offset 0x900 into the
+  MMSYS_CONFIG region: <&mmsys 0x900>.
+- ports: A node containing input and output port nodes with endpoint
+  definitions as documented in Documentation/devicetree/bindings/graph.txt.
+- port@0: The input port in the ports node should be connected to a DPI output
+  port.
+- port@1: The output port in the ports node should be connected to the input
+  port of a connector node that contains a ddc-i2c-bus property, or to the
+  input port of an attached bridge chip, such as a SlimPort transmitter.
+
+HDMI CEC
+========
+
+The HDMI CEC controller handles hotplug detection and CEC communication.
+
+Required properties:
+- compatible: Should be "mediatek,<chip>-cec"
+- reg: Physical base address and length of the controller's registers
+- interrupts: The interrupt signal from the function block.
+- clocks: device clock
+
+HDMI DDC
+========
+
+The HDMI DDC i2c controller is used to interface with the HDMI DDC pins.
+The Mediatek's I2C controller is used to interface with I2C devices.
+
+Required properties:
+- compatible: Should be "mediatek,<chip>-hdmi-ddc"
+- reg: Physical base address and length of the controller's registers
+- clocks: device clock
+- clock-names: Should be "ddc-i2c".
+
+HDMI PHY
+========
+
+The HDMI PHY serializes the HDMI encoder's three channel 10-bit parallel
+output and drives the HDMI pads.
+
+Required properties:
+- compatible: "mediatek,<chip>-hdmi-phy"
+- reg: Physical base address and length of the module's registers
+- clocks: PLL reference clock
+- clock-names: must contain "pll_ref"
+- clock-output-names: must be "hdmitx_dig_cts" on mt8173
+- #phy-cells: must be <0>
+- #clock-cells: must be <0>
+
+Optional properties:
+- mediatek,ibias: TX DRV bias current for <1.65Gbps, defaults to 0xa
+- mediatek,ibias_up: TX DRV bias current for >1.65Gbps, defaults to 0x1c
+
+Example:
+
+cec: cec@10013000 {
+	compatible = "mediatek,mt8173-cec";
+	reg = <0 0x10013000 0 0xbc>;
+	interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_LOW>;
+	clocks = <&infracfg CLK_INFRA_CEC>;
+};
+
+hdmi_phy: hdmi-phy@10209100 {
+	compatible = "mediatek,mt8173-hdmi-phy";
+	reg = <0 0x10209100 0 0x24>;
+	clocks = <&apmixedsys CLK_APMIXED_HDMI_REF>;
+	clock-names = "pll_ref";
+	clock-output-names = "hdmitx_dig_cts";
+	mediatek,ibias = <0xa>;
+	mediatek,ibias_up = <0x1c>;
+	#clock-cells = <0>;
+	#phy-cells = <0>;
+};
+
+hdmi_ddc0: i2c@11012000 {
+	compatible = "mediatek,mt8173-hdmi-ddc";
+	reg = <0 0x11012000 0 0x1c>;
+	interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_LOW>;
+	clocks = <&pericfg CLK_PERI_I2C5>;
+	clock-names = "ddc-i2c";
+};
+
+hdmi0: hdmi@14025000 {
+	compatible = "mediatek,mt8173-hdmi";
+	reg = <0 0x14025000 0 0x400>;
+	interrupts = <GIC_SPI 206 IRQ_TYPE_LEVEL_LOW>;
+	clocks = <&mmsys CLK_MM_HDMI_PIXEL>,
+		 <&mmsys CLK_MM_HDMI_PLLCK>,
+		 <&mmsys CLK_MM_HDMI_AUDIO>,
+		 <&mmsys CLK_MM_HDMI_SPDIF>;
+	clock-names = "pixel", "pll", "bclk", "spdif";
+	pinctrl-names = "default";
+	pinctrl-0 = <&hdmi_pin>;
+	phys = <&hdmi_phy>;
+	phy-names = "hdmi";
+	mediatek,syscon-hdmi = <&mmsys 0x900>;
+	assigned-clocks = <&topckgen CLK_TOP_HDMI_SEL>;
+	assigned-clock-parents = <&hdmi_phy>;
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+
+			hdmi0_in: endpoint {
+				remote-endpoint = <&dpi0_out>;
+			};
+		};
+
+		port@1 {
+			reg = <1>;
+
+			hdmi0_out: endpoint {
+				remote-endpoint = <&hdmi_con_in>;
+			};
+		};
+	};
+};
+
+connector {
+	compatible = "hdmi-connector";
+	type = "a";
+	ddc-i2c-bus = <&hdmiddc0>;
+
+	port {
+		hdmi_con_in: endpoint {
+			remote-endpoint = <&hdmi0_out>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt
index f5948c48b9a2..6b1cab17f52d 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi.txt
+++ b/Documentation/devicetree/bindings/display/msm/dsi.txt
@@ -11,8 +11,7 @@ Required properties:
   be 0 or 1, since we have 2 DSI controllers at most for now.
 - interrupts: The interrupt signal from the DSI block.
 - power-domains: Should be <&mmcc MDSS_GDSC>.
-- clocks: device clocks
-  See Documentation/devicetree/bindings/clocks/clock-bindings.txt for details.
+- clocks: Phandles to device clocks.
 - clock-names: the following clocks are required:
   * "mdp_core_clk"
   * "iface_clk"
@@ -23,16 +22,21 @@ Required properties:
   * "core_clk"
   For DSIv2, we need an additional clock:
    * "src_clk"
+- assigned-clocks: Parents of "byte_clk" and "pixel_clk" for the given platform.
+- assigned-clock-parents: The Byte clock and Pixel clock PLL outputs provided
+  by a DSI PHY block. See [1] for details on clock bindings.
 - vdd-supply: phandle to vdd regulator device node
 - vddio-supply: phandle to vdd-io regulator device node
 - vdda-supply: phandle to vdda regulator device node
-- qcom,dsi-phy: phandle to DSI PHY device node
+- phys: phandle to DSI PHY device node
+- phy-names: the name of the corresponding PHY device
 - syscon-sfpb: A phandle to mmss_sfpb syscon node (only for DSIv2)
+- ports: Contains 2 DSI controller ports as child nodes. Each port contains
+  an endpoint subnode as defined in [2] and [3].
 
 Optional properties:
 - panel@0: Node of panel connected to this DSI controller.
-  See files in Documentation/devicetree/bindings/display/panel/ for each supported
-  panel.
+  See files in [4] for each supported panel.
 - qcom,dual-dsi-mode: Boolean value indicating if the DSI controller is
   driving a panel which needs 2 DSI links.
 - qcom,master-dsi: Boolean value indicating if the DSI controller is driving
@@ -44,34 +48,38 @@ Optional properties:
 - pinctrl-names: the pin control state names; should contain "default"
 - pinctrl-0: the default pinctrl state (active)
 - pinctrl-n: the "sleep" pinctrl state
-- port: DSI controller output port, containing one endpoint subnode.
+- ports: contains DSI controller input and output ports as children, each
+  containing one endpoint subnode.
 
   DSI Endpoint properties:
-  - remote-endpoint: set to phandle of the connected panel's endpoint.
-    See Documentation/devicetree/bindings/graph.txt for device graph info.
-  - qcom,data-lane-map: this describes how the logical DSI lanes are mapped
-    to the physical lanes on the given platform. The value contained in
-    index n describes what logical data lane is mapped to the physical data
-    lane n (DATAn, where n lies between 0 and 3).
+  - remote-endpoint: For port@0, set to phandle of the connected panel/bridge's
+    input endpoint. For port@1, set to the MDP interface output. See [2] for
+    device graph info.
+
+  - data-lanes: this describes how the physical DSI data lanes are mapped
+    to the logical lanes on the given platform. The value contained in
+    index n describes what physical lane is mapped to the logical lane n
+    (DATAn, where n lies between 0 and 3). The clock lane position is fixed
+    and can't be changed. Hence, they aren't a part of the DT bindings. See
+    [3] for more info on the data-lanes property.
 
     For example:
 
-    qcom,data-lane-map = <3 0 1 2>;
+    data-lanes = <3 0 1 2>;
 
-    The above mapping describes that the logical data lane DATA3 is mapped to
-    the physical data lane DATA0, logical DATA0 to physical DATA1, logic DATA1
-    to phys DATA2 and logic DATA2 to phys DATA3.
+    The above mapping describes that the logical data lane DATA0 is mapped to
+    the physical data lane DATA3, logical DATA1 to physical DATA0, logic DATA2
+    to phys DATA1 and logic DATA3 to phys DATA2.
 
     There are only a limited number of physical to logical mappings possible:
-
-    "0123": Logic 0->Phys 0; Logic 1->Phys 1; Logic 2->Phys 2; Logic 3->Phys 3;
-    "3012": Logic 3->Phys 0; Logic 0->Phys 1; Logic 1->Phys 2; Logic 2->Phys 3;
-    "2301": Logic 2->Phys 0; Logic 3->Phys 1; Logic 0->Phys 2; Logic 1->Phys 3;
-    "1230": Logic 1->Phys 0; Logic 2->Phys 1; Logic 3->Phys 2; Logic 0->Phys 3;
-    "0321": Logic 0->Phys 0; Logic 3->Phys 1; Logic 2->Phys 2; Logic 1->Phys 3;
-    "1032": Logic 1->Phys 0; Logic 0->Phys 1; Logic 3->Phys 2; Logic 2->Phys 3;
-    "2103": Logic 2->Phys 0; Logic 1->Phys 1; Logic 0->Phys 2; Logic 3->Phys 3;
-    "3210": Logic 3->Phys 0; Logic 2->Phys 1; Logic 1->Phys 2; Logic 0->Phys 3;
+    <0 1 2 3>
+    <1 2 3 0>
+    <2 3 0 1>
+    <3 0 1 2>
+    <0 3 2 1>
+    <1 0 3 2>
+    <2 1 0 3>
+    <3 2 1 0>
 
 DSI PHY:
 Required properties:
@@ -86,11 +94,12 @@ Required properties:
   * "dsi_pll"
   * "dsi_phy"
   * "dsi_phy_regulator"
+- clock-cells: Must be 1. The DSI PHY block acts as a clock provider, creating
+  2 clocks: A byte clock (index 0), and a pixel clock (index 1).
 - qcom,dsi-phy-index: The ID of DSI PHY hardware instance. This should
   be 0 or 1, since we have 2 DSI PHYs at most for now.
 - power-domains: Should be <&mmcc MDSS_GDSC>.
-- clocks: device clocks
-  See Documentation/devicetree/bindings/clocks/clock-bindings.txt for details.
+- clocks: Phandles to device clocks. See [1] for details on clock bindings.
 - clock-names: the following clocks are required:
   * "iface_clk"
 - vddio-supply: phandle to vdd-io regulator device node
@@ -99,11 +108,16 @@ Optional properties:
 - qcom,dsi-phy-regulator-ldo-mode: Boolean value indicating if the LDO mode PHY
   regulator is wanted.
 
+[1] Documentation/devicetree/bindings/clocks/clock-bindings.txt
+[2] Documentation/devicetree/bindings/graph.txt
+[3] Documentation/devicetree/bindings/media/video-interfaces.txt
+[4] Documentation/devicetree/bindings/display/panel/
+
 Example:
-	mdss_dsi0: qcom,mdss_dsi@fd922800 {
+	dsi0: dsi@fd922800 {
 		compatible = "qcom,mdss-dsi-ctrl";
 		qcom,dsi-host-index = <0>;
-		interrupt-parent = <&mdss_mdp>;
+		interrupt-parent = <&mdp>;
 		interrupts = <4 0>;
 		reg-names = "dsi_ctrl";
 		reg = <0xfd922800 0x200>;
@@ -124,19 +138,48 @@ Example:
 			<&mmcc MDSS_AHB_CLK>,
 			<&mmcc MDSS_MDP_CLK>,
 			<&mmcc MDSS_PCLK0_CLK>;
+
+		assigned-clocks =
+				 <&mmcc BYTE0_CLK_SRC>,
+				 <&mmcc PCLK0_CLK_SRC>;
+		assigned-clock-parents =
+				 <&dsi_phy0 0>,
+				 <&dsi_phy0 1>;
+
 		vdda-supply = <&pma8084_l2>;
 		vdd-supply = <&pma8084_l22>;
 		vddio-supply = <&pma8084_l12>;
 
-		qcom,dsi-phy = <&mdss_dsi_phy0>;
+		phys = <&dsi_phy0>;
+		phy-names ="dsi-phy";
 
 		qcom,dual-dsi-mode;
 		qcom,master-dsi;
 		qcom,sync-dual-dsi;
 
 		pinctrl-names = "default", "sleep";
-		pinctrl-0 = <&mdss_dsi_active>;
-		pinctrl-1 = <&mdss_dsi_suspend>;
+		pinctrl-0 = <&dsi_active>;
+		pinctrl-1 = <&dsi_suspend>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				dsi0_in: endpoint {
+					remote-endpoint = <&mdp_intf1_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				dsi0_out: endpoint {
+					remote-endpoint = <&panel_in>;
+					data-lanes = <0 1 2 3>;
+				};
+			};
+		};
 
 		panel: panel@0 {
 			compatible = "sharp,lq101r1sx01";
@@ -152,16 +195,9 @@ Example:
 				};
 			};
 		};
-
-		port {
-			dsi0_out: endpoint {
-				remote-endpoint = <&panel_in>;
-				lanes = <0 1 2 3>;
-			};
-		};
 	};
 
-	mdss_dsi_phy0: qcom,mdss_dsi_phy@fd922a00 {
+	dsi_phy0: dsi-phy@fd922a00 {
 		compatible = "qcom,dsi-phy-28nm-hpm";
 		qcom,dsi-phy-index = <0>;
 		reg-names =
@@ -173,6 +209,7 @@ Example:
 			<0xfd922d80 0x7b>;
 		clock-names = "iface_clk";
 		clocks = <&mmcc MDSS_AHB_CLK>;
+		#clock-cells = <1>;
 		vddio-supply = <&pma8084_l12>;
 
 		qcom,dsi-phy-regulator-ldo-mode;
diff --git a/Documentation/devicetree/bindings/display/msm/mdp.txt b/Documentation/devicetree/bindings/display/msm/mdp.txt
deleted file mode 100644
index a214f6cd0363..000000000000
--- a/Documentation/devicetree/bindings/display/msm/mdp.txt
+++ /dev/null
@@ -1,59 +0,0 @@
-Qualcomm adreno/snapdragon display controller
-
-Required properties:
-- compatible:
-  * "qcom,mdp4" - mdp4
-  * "qcom,mdp5" - mdp5
-- reg: Physical base address and length of the controller's registers.
-- interrupts: The interrupt signal from the display controller.
-- connectors: array of phandles for output device(s)
-- clocks: device clocks
-  See ../clocks/clock-bindings.txt for details.
-- clock-names: the following clocks are required.
-  For MDP4:
-   * "core_clk"
-   * "iface_clk"
-   * "lut_clk"
-   * "src_clk"
-   * "hdmi_clk"
-   * "mdp_clk"
-  For MDP5:
-   * "bus_clk"
-   * "iface_clk"
-   * "core_clk_src"
-   * "core_clk"
-   * "lut_clk" (some MDP5 versions may not need this)
-   * "vsync_clk"
-
-Optional properties:
-- gpus: phandle for gpu device
-- clock-names: the following clocks are optional:
-  * "lut_clk"
-
-Example:
-
-/ {
-	...
-
-	mdp: qcom,mdp@5100000 {
-		compatible = "qcom,mdp4";
-		reg = <0x05100000 0xf0000>;
-		interrupts = <GIC_SPI 75 0>;
-		connectors = <&hdmi>;
-		gpus = <&gpu>;
-		clock-names =
-		    "core_clk",
-		    "iface_clk",
-		    "lut_clk",
-		    "src_clk",
-		    "hdmi_clk",
-		    "mdp_clk";
-		clocks =
-		    <&mmcc MDP_SRC>,
-		    <&mmcc MDP_AHB_CLK>,
-		    <&mmcc MDP_LUT_CLK>,
-		    <&mmcc TV_SRC>,
-		    <&mmcc HDMI_TV_CLK>,
-		    <&mmcc MDP_TV_CLK>;
-	};
-};
diff --git a/Documentation/devicetree/bindings/display/msm/mdp4.txt b/Documentation/devicetree/bindings/display/msm/mdp4.txt
new file mode 100644
index 000000000000..3c341a15ccdc
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/msm/mdp4.txt
@@ -0,0 +1,112 @@
+Qualcomm adreno/snapdragon MDP4 display controller
+
+Description:
+
+This is the bindings documentation for the MDP4 display controller found in
+SoCs like MSM8960, APQ8064 and MSM8660.
+
+Required properties:
+- compatible:
+  * "qcom,mdp4" - mdp4
+- reg: Physical base address and length of the controller's registers.
+- interrupts: The interrupt signal from the display controller.
+- clocks: device clocks
+  See ../clocks/clock-bindings.txt for details.
+- clock-names: the following clocks are required.
+  * "core_clk"
+  * "iface_clk"
+  * "bus_clk"
+  * "lut_clk"
+  * "hdmi_clk"
+  * "tv_clk"
+- ports: contains the list of output ports from MDP. These connect to interfaces
+  that are external to the MDP hardware, such as HDMI, DSI, EDP etc (LVDS is a
+  special case since it is a part of the MDP block itself).
+
+  Each output port contains an endpoint that describes how it is connected to an
+  external interface. These are described by the standard properties documented
+  here:
+	Documentation/devicetree/bindings/graph.txt
+	Documentation/devicetree/bindings/media/video-interfaces.txt
+
+  The output port mappings are:
+	Port 0 -> LCDC/LVDS
+	Port 1 -> DSI1 Cmd/Video
+	Port 2 -> DSI2 Cmd/Video
+	Port 3 -> DTV
+
+Optional properties:
+- clock-names: the following clocks are optional:
+  * "lut_clk"
+
+Example:
+
+/ {
+	...
+
+	hdmi: hdmi@4a00000 {
+		...
+		ports {
+			...
+			port@0 {
+				reg = <0>;
+				hdmi_in: endpoint {
+					remote-endpoint = <&mdp_dtv_out>;
+				};
+			};
+			...
+		};
+		...
+	};
+
+	...
+
+	mdp: mdp@5100000 {
+		compatible = "qcom,mdp4";
+		reg = <0x05100000 0xf0000>;
+		interrupts = <GIC_SPI 75 0>;
+		clock-names =
+		    "core_clk",
+		    "iface_clk",
+		    "lut_clk",
+		    "hdmi_clk",
+		    "tv_clk";
+		clocks =
+		    <&mmcc MDP_CLK>,
+		    <&mmcc MDP_AHB_CLK>,
+		    <&mmcc MDP_AXI_CLK>,
+		    <&mmcc MDP_LUT_CLK>,
+		    <&mmcc HDMI_TV_CLK>,
+		    <&mmcc MDP_TV_CLK>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					mdp_lvds_out: endpoint {
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					mdp_dsi1_out: endpoint {
+					};
+				};
+
+				port@2 {
+					reg = <2>;
+					mdp_dsi2_out: endpoint {
+					};
+				};
+
+				port@3 {
+					reg = <3>;
+					mdp_dtv_out: endpoint {
+						remote-endpoint = <&hdmi_in>;
+					};
+				};
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/display/msm/mdp5.txt b/Documentation/devicetree/bindings/display/msm/mdp5.txt
new file mode 100644
index 000000000000..30c11ea83754
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/msm/mdp5.txt
@@ -0,0 +1,160 @@
+Qualcomm adreno/snapdragon MDP5 display controller
+
+Description:
+
+This is the bindings documentation for the Mobile Display Subsytem(MDSS) that
+encapsulates sub-blocks like MDP5, DSI, HDMI, eDP etc, and the MDP5 display
+controller found in SoCs like MSM8974, APQ8084, MSM8916, MSM8994 and MSM8996.
+
+MDSS:
+Required properties:
+- compatible:
+  * "qcom,mdss" - MDSS
+- reg: Physical base address and length of the controller's registers.
+- reg-names: The names of register regions. The following regions are required:
+  * "mdss_phys"
+  * "vbif_phys"
+- interrupts: The interrupt signal from MDSS.
+- interrupt-controller: identifies the node as an interrupt controller.
+- #interrupt-cells: specifies the number of cells needed to encode an interrupt
+  source, should be 1.
+- power-domains: a power domain consumer specifier according to
+  Documentation/devicetree/bindings/power/power_domain.txt
+- clocks: device clocks. See ../clocks/clock-bindings.txt for details.
+- clock-names: the following clocks are required.
+  * "iface_clk"
+  * "bus_clk"
+  * "vsync_clk"
+- #address-cells: number of address cells for the MDSS children. Should be 1.
+- #size-cells: Should be 1.
+- ranges: parent bus address space is the same as the child bus address space.
+
+Optional properties:
+- clock-names: the following clocks are optional:
+  * "lut_clk"
+
+MDP5:
+Required properties:
+- compatible:
+  * "qcom,mdp5" - MDP5
+- reg: Physical base address and length of the controller's registers.
+- reg-names: The names of register regions. The following regions are required:
+  * "mdp_phys"
+- interrupts: Interrupt line from MDP5 to MDSS interrupt controller.
+- interrupt-parent: phandle to the MDSS block
+  through MDP block
+- clocks: device clocks. See ../clocks/clock-bindings.txt for details.
+- clock-names: the following clocks are required.
+-   * "bus_clk"
+-   * "iface_clk"
+-   * "core_clk"
+-   * "vsync_clk"
+- ports: contains the list of output ports from MDP. These connect to interfaces
+  that are external to the MDP hardware, such as HDMI, DSI, EDP etc (LVDS is a
+  special case since it is a part of the MDP block itself).
+
+  Each output port contains an endpoint that describes how it is connected to an
+  external interface. These are described by the standard properties documented
+  here:
+	Documentation/devicetree/bindings/graph.txt
+	Documentation/devicetree/bindings/media/video-interfaces.txt
+
+  The availability of output ports can vary across SoC revisions:
+
+  For MSM8974 and APQ8084:
+	 Port 0 -> MDP_INTF0 (eDP)
+	 Port 1 -> MDP_INTF1 (DSI1)
+	 Port 2 -> MDP_INTF2 (DSI2)
+	 Port 3 -> MDP_INTF3 (HDMI)
+
+  For MSM8916:
+	 Port 0 -> MDP_INTF1 (DSI1)
+
+  For MSM8994 and MSM8996:
+	 Port 0 -> MDP_INTF1 (DSI1)
+	 Port 1 -> MDP_INTF2 (DSI2)
+	 Port 2 -> MDP_INTF3 (HDMI)
+
+Optional properties:
+- clock-names: the following clocks are optional:
+  * "lut_clk"
+
+Example:
+
+/ {
+	...
+
+	mdss: mdss@1a00000 {
+		compatible = "qcom,mdss";
+		reg = <0x1a00000 0x1000>,
+		      <0x1ac8000 0x3000>;
+		reg-names = "mdss_phys", "vbif_phys";
+
+		power-domains = <&gcc MDSS_GDSC>;
+
+		clocks = <&gcc GCC_MDSS_AHB_CLK>,
+			 <&gcc GCC_MDSS_AXI_CLK>,
+			 <&gcc GCC_MDSS_VSYNC_CLK>;
+		clock-names = "iface_clk",
+			      "bus_clk",
+			      "vsync_clk"
+
+		interrupts = <0 72 0>;
+
+		interrupt-controller;
+		#interrupt-cells = <1>;
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		mdp: mdp@1a01000 {
+			compatible = "qcom,mdp5";
+			reg = <0x1a01000 0x90000>;
+			reg-names = "mdp_phys";
+
+			interrupt-parent = <&mdss>;
+			interrupts = <0 0>;
+
+			clocks = <&gcc GCC_MDSS_AHB_CLK>,
+				 <&gcc GCC_MDSS_AXI_CLK>,
+				 <&gcc GCC_MDSS_MDP_CLK>,
+				 <&gcc GCC_MDSS_VSYNC_CLK>;
+			clock-names = "iface_clk",
+				      "bus_clk",
+				      "core_clk",
+				      "vsync_clk";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					mdp5_intf1_out: endpoint {
+						remote-endpoint = <&dsi0_in>;
+					};
+				};
+			};
+		};
+
+		dsi0: dsi@1a98000 {
+			...
+			ports {
+				...
+				port@0 {
+					reg = <0>;
+					dsi0_in: endpoint {
+						remote-endpoint = <&mdp5_intf1_out>;
+					};
+				};
+				...
+			};
+			...
+		};
+
+		dsi_phy0: dsi-phy@1a98300 {
+			...
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/display/panel/lg,lp079qx1-sp0v.txt b/Documentation/devicetree/bindings/display/panel/lg,lp079qx1-sp0v.txt
new file mode 100644
index 000000000000..b9877acad012
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/lg,lp079qx1-sp0v.txt
@@ -0,0 +1,7 @@
+LG LP079QX1-SP0V 7.9" (1536x2048 pixels) TFT LCD panel
+
+Required properties:
+- compatible: should be "lg,lp079qx1-sp0v"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/lg,lp097qx1-spa1.txt b/Documentation/devicetree/bindings/display/panel/lg,lp097qx1-spa1.txt
new file mode 100644
index 000000000000..42141516f078
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/lg,lp097qx1-spa1.txt
@@ -0,0 +1,7 @@
+LG 9.7" (2048x1536 pixels) TFT LCD panel
+
+Required properties:
+- compatible: should be "lg,lp097qx1-spa1"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/panel-dpi.txt b/Documentation/devicetree/bindings/display/panel/panel-dpi.txt
index 216c894d4f99..b52ac52757df 100644
--- a/Documentation/devicetree/bindings/display/panel/panel-dpi.txt
+++ b/Documentation/devicetree/bindings/display/panel/panel-dpi.txt
@@ -7,6 +7,8 @@ Required properties:
 Optional properties:
 - label: a symbolic name for the panel
 - enable-gpios: panel enable gpio
+- reset-gpios: GPIO to control the RESET pin
+- vcc-supply: phandle of regulator that will be used to enable power to the display
 
 Required nodes:
 - "panel-timing" containing video timings
diff --git a/Documentation/devicetree/bindings/display/panel/samsung,lsn122dl01-c01.txt b/Documentation/devicetree/bindings/display/panel/samsung,lsn122dl01-c01.txt
new file mode 100644
index 000000000000..dba298b43b24
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/samsung,lsn122dl01-c01.txt
@@ -0,0 +1,7 @@
+Samsung 12.2" (2560x1600 pixels) TFT LCD panel
+
+Required properties:
+- compatible: should be "samsung,lsn122dl01-c01"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/sharp,lq101k1ly04.txt b/Documentation/devicetree/bindings/display/panel/sharp,lq101k1ly04.txt
new file mode 100644
index 000000000000..4aff25b8dfe6
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/sharp,lq101k1ly04.txt
@@ -0,0 +1,7 @@
+Sharp Display Corp. LQ101K1LY04 10.07" WXGA TFT LCD panel
+
+Required properties:
+- compatible: should be "sharp,lq101k1ly04"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/sharp,lq123p1jx31.txt b/Documentation/devicetree/bindings/display/panel/sharp,lq123p1jx31.txt
new file mode 100644
index 000000000000..bcb0e8a29f71
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/sharp,lq123p1jx31.txt
@@ -0,0 +1,7 @@
+Sharp 12.3" (2400x1600 pixels) TFT LCD panel
+
+Required properties:
+- compatible: should be "sharp,lq123p1jx31"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/starry,kr122ea0sra.txt b/Documentation/devicetree/bindings/display/panel/starry,kr122ea0sra.txt
new file mode 100644
index 000000000000..1e87fe6078af
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/starry,kr122ea0sra.txt
@@ -0,0 +1,7 @@
+Starry 12.2" (1920x1200 pixels) TFT LCD panel
+
+Required properties:
+- compatible: should be "starry,kr122ea0sra"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/rockchip/analogix_dp-rockchip.txt b/Documentation/devicetree/bindings/display/rockchip/analogix_dp-rockchip.txt
index e832ff98fd61..01cced1c2a18 100644
--- a/Documentation/devicetree/bindings/display/rockchip/analogix_dp-rockchip.txt
+++ b/Documentation/devicetree/bindings/display/rockchip/analogix_dp-rockchip.txt
@@ -2,7 +2,8 @@ Rockchip RK3288 specific extensions to the Analogix Display Port
 ================================
 
 Required properties:
-- compatible: "rockchip,rk3288-edp";
+- compatible: "rockchip,rk3288-dp",
+	      "rockchip,rk3399-edp";
 
 - reg: physical base address of the controller and length
 
@@ -27,6 +28,12 @@ Required properties:
     Port 0: contained 2 endpoints, connecting to the output of vop.
     Port 1: contained 1 endpoint, connecting to the input of panel.
 
+Optional property for different chips:
+- clocks: from common clock binding: handle to grf_vio clock.
+
+- clock-names: from common clock binding:
+	       Required elements: "grf"
+
 For the below properties, please refer to Analogix DP binding document:
  * Documentation/devicetree/bindings/drm/bridge/analogix_dp.txt
 - phys (required)
diff --git a/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt b/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt
index a3bd8c050c4e..0fad7ed2ea19 100644
--- a/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt
+++ b/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt
@@ -208,6 +208,7 @@ of the following host1x client modules:
     See ../clocks/clock-bindings.txt for details.
   - clock-names: Must include the following entries:
     - sor: clock input for the SOR hardware
+    - source: source clock for the SOR clock
     - parent: input for the pixel clock
     - dp: reference clock for the SOR clock
     - safe: safe reference for the SOR clock during power up
@@ -226,9 +227,9 @@ of the following host1x client modules:
   - nvidia,dpaux: phandle to a DispayPort AUX interface
 
 - dpaux: DisplayPort AUX interface
-  - compatible: For Tegra124, must contain "nvidia,tegra124-dpaux".  Otherwise,
-    must contain '"nvidia,<chip>-dpaux", "nvidia,tegra124-dpaux"', where
-    <chip> is tegra132.
+  - compatible : Should contain one of the following:
+    - "nvidia,tegra124-dpaux": for Tegra124 and Tegra132
+    - "nvidia,tegra210-dpaux": for Tegra210
   - reg: Physical base address and length of the controller's registers.
   - interrupts: The interrupt outputs from the controller.
   - clocks: Must contain an entry for each entry in clock-names.
@@ -241,6 +242,12 @@ of the following host1x client modules:
   - reset-names: Must include the following entries:
     - dpaux
   - vdd-supply: phandle of a supply that powers the DisplayPort link
+  - i2c-bus: Subnode where I2C slave devices are listed. This subnode
+    must be always present. If there are no I2C slave devices, an empty
+    node should be added. See ../../i2c/i2c.txt for more information.
+
+  See ../pinctrl/nvidia,tegra124-dpaux-padctl.txt for information
+  regarding the DPAUX pad controller bindings.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt
index 079b42a81d7c..18090e7226b4 100644
--- a/Documentation/devicetree/bindings/dma/ti-edma.txt
+++ b/Documentation/devicetree/bindings/dma/ti-edma.txt
@@ -15,7 +15,7 @@ Required properties:
 - reg:		Memory map of eDMA CC
 - reg-names:	"edma3_cc"
 - interrupts:	Interrupt lines for CCINT, MPERR and CCERRINT.
-- interrupt-names: "edma3_ccint", "emda3_mperr" and "edma3_ccerrint"
+- interrupt-names: "edma3_ccint", "edma3_mperr" and "edma3_ccerrint"
 - ti,tptcs:	List of TPTCs associated with the eDMA in the following form:
 		<&tptc_phandle TC_priority_number>. The highest priority is 0.
 
@@ -48,7 +48,7 @@ edma: edma@49000000 {
 	reg =	<0x49000000 0x10000>;
 	reg-names = "edma3_cc";
 	interrupts = <12 13 14>;
-	interrupt-names = "edma3_ccint", "emda3_mperr", "edma3_ccerrint";
+	interrupt-names = "edma3_ccint", "edma3_mperr", "edma3_ccerrint";
 	dma-requests = <64>;
 	#dma-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/firmware/qcom,scm.txt b/Documentation/devicetree/bindings/firmware/qcom,scm.txt
new file mode 100644
index 000000000000..3b4436e56865
--- /dev/null
+++ b/Documentation/devicetree/bindings/firmware/qcom,scm.txt
@@ -0,0 +1,28 @@
+QCOM Secure Channel Manager (SCM)
+
+Qualcomm processors include an interface to communicate to the secure firmware.
+This interface allows for clients to request different types of actions.  These
+can include CPU power up/down, HDCP requests, loading of firmware, and other
+assorted actions.
+
+Required properties:
+- compatible: must contain one of the following:
+ * "qcom,scm-apq8064" for APQ8064 platforms
+ * "qcom,scm-msm8660" for MSM8660 platforms
+ * "qcom,scm-msm8690" for MSM8690 platforms
+ * "qcom,scm" for later processors (MSM8916, APQ8084, MSM8974, etc)
+- clocks: One to three clocks may be required based on compatible.
+ * Only core clock required for "qcom,scm-apq8064", "qcom,scm-msm8660", and "qcom,scm-msm8960"
+ * Core, iface, and bus clocks required for "qcom,scm"
+- clock-names: Must contain "core" for the core clock, "iface" for the interface
+  clock and "bus" for the bus clock per the requirements of the compatible.
+
+Example for MSM8916:
+
+	firmware {
+		scm {
+			compatible = "qcom,scm";
+			clocks = <&gcc GCC_CRYPTO_CLK> , <&gcc GCC_CRYPTO_AXI_CLK>, <&gcc GCC_CRYPTO_AHB_CLK>;
+			clock-names = "core", "bus", "iface";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
index a92d4f3e7044..5c70ce9c1954 100644
--- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
@@ -146,10 +146,10 @@ samsung,24ad0xd1	S524AD0XF1 (128K/256K-bit Serial EEPROM for Low Power)
 sgx,vz89x		SGX Sensortech VZ89X Sensors
 sii,s35390a		2-wire CMOS real-time clock
 skyworks,sky81452	Skyworks SKY81452: Six-Channel White LED Driver with Touch Panel Bias Supply
-st-micro,24c256		i2c serial eeprom  (24cxx)
-stm,m41t00		Serial Access TIMEKEEPER
-stm,m41t62		Serial real-time clock (RTC) with alarm
-stm,m41t80		M41T80 - SERIAL ACCESS RTC WITH ALARMS
+st,24c256		i2c serial eeprom  (24cxx)
+st,m41t00		Serial real-time clock (RTC)
+st,m41t62		Serial real-time clock (RTC) with alarm
+st,m41t80		M41T80 - SERIAL ACCESS RTC WITH ALARMS
 taos,tsl2550		Ambient Light Sensor with SMBUS/Two Wire Serial Interface
 ti,ads7828		8-Channels, 12-bit ADC
 ti,ads7830		8-Channels, 8-bit ADC
diff --git a/Documentation/devicetree/bindings/iio/adc/at91_adc.txt b/Documentation/devicetree/bindings/iio/adc/at91_adc.txt
index 0f813dec5e08..f65b04fb7962 100644
--- a/Documentation/devicetree/bindings/iio/adc/at91_adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/at91_adc.txt
@@ -59,28 +59,24 @@ adc0: adc@fffb0000 {
 	atmel,adc-res-names = "lowres", "highres";
 	atmel,adc-use-res = "lowres";
 
-	trigger@0 {
-		reg = <0>;
+	trigger0 {
 		trigger-name = "external-rising";
 		trigger-value = <0x1>;
 		trigger-external;
 	};
-	trigger@1 {
-		reg = <1>;
+	trigger1 {
 		trigger-name = "external-falling";
 		trigger-value = <0x2>;
 		trigger-external;
 	};
 
-	trigger@2 {
-		reg = <2>;
+	trigger2 {
 		trigger-name = "external-any";
 		trigger-value = <0x3>;
 		trigger-external;
 	};
 
-	trigger@3 {
-		reg = <3>;
+	trigger3 {
 		trigger-name = "continuous";
 		trigger-value = <0x6>;
 	};
diff --git a/Documentation/devicetree/bindings/input/clps711x-keypad.txt b/Documentation/devicetree/bindings/input/clps711x-keypad.txt
index e68d2bbc6c07..3eed8819d05d 100644
--- a/Documentation/devicetree/bindings/input/clps711x-keypad.txt
+++ b/Documentation/devicetree/bindings/input/clps711x-keypad.txt
@@ -1,7 +1,7 @@
 * Cirrus Logic CLPS711X matrix keypad device tree bindings
 
 Required Properties:
-- compatible:    Shall contain "cirrus,clps711x-keypad".
+- compatible:    Shall contain "cirrus,ep7209-keypad".
 - row-gpios:     List of GPIOs used as row lines.
 - poll-interval: Poll interval time in milliseconds.
 - linux,keymap:  The definition can be found at
@@ -12,7 +12,7 @@ Optional Properties:
 
 Example:
 	keypad {
-		compatible = "cirrus,ep7312-keypad", "cirrus,clps711x-keypad";
+		compatible = "cirrus,ep7312-keypad", "cirrus,ep7209-keypad";
 		autorepeat;
 		poll-interval = <120>;
 		row-gpios = <&porta 0 0>,
diff --git a/Documentation/devicetree/bindings/interrupt-controller/cirrus,clps711x-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/cirrus,clps711x-intc.txt
index 759339c34e4f..969b4582ec60 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/cirrus,clps711x-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/cirrus,clps711x-intc.txt
@@ -2,7 +2,7 @@ Cirrus Logic CLPS711X Interrupt Controller
 
 Required properties:
 
-- compatible: Should be "cirrus,clps711x-intc".
+- compatible: Should be "cirrus,ep7209-intc".
 - reg: Specifies base physical address of the registers set.
 - interrupt-controller: Identifies the node as an interrupt controller.
 - #interrupt-cells: Specifies the number of cells needed to encode an
@@ -34,7 +34,7 @@ ID	Name	Description
 
 Example:
 	intc: interrupt-controller {
-		compatible = "cirrus,clps711x-intc";
+		compatible = "cirrus,ep7312-intc", "cirrus,ep7209-intc";
 		reg = <0x80000000 0x4000>;
 		interrupt-controller;
 		#interrupt-cells = <1>;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt b/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
index 8cf564d083d2..9d1d72c65489 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
@@ -9,6 +9,7 @@ Required properties:
 	"mediatek,mt8135-sysirq"
 	"mediatek,mt8127-sysirq"
 	"mediatek,mt6795-sysirq"
+	"mediatek,mt6755-sysirq"
 	"mediatek,mt6592-sysirq"
 	"mediatek,mt6589-sysirq"
 	"mediatek,mt6582-sysirq"
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
index 947863acc2d4..7b94c88cf2ee 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
@@ -1,6 +1,6 @@
 * ARM SMMUv3 Architecture Implementation
 
-The SMMUv3 architecture is a significant deparature from previous
+The SMMUv3 architecture is a significant departure from previous
 revisions, replacing the MMIO register interface with in-memory command
 and event queues and adding support for the ATS and PRI components of
 the PCIe specification.
diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt b/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt
index cd1b1cd7b5c4..53c20cae309f 100644
--- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt
+++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt
@@ -1,7 +1,9 @@
 * Mediatek IOMMU Architecture Implementation
 
-  Some Mediatek SOCs contain a Multimedia Memory Management Unit (M4U) which
-uses the ARM Short-Descriptor translation table format for address translation.
+  Some Mediatek SOCs contain a Multimedia Memory Management Unit (M4U), and
+this M4U have two generations of HW architecture. Generation one uses flat
+pagetable, and only supports 4K size page mapping. Generation two uses the
+ARM Short-Descriptor translation table format for address translation.
 
   About the M4U Hardware Block Diagram, please check below:
 
@@ -36,7 +38,9 @@ in each larb. Take a example, There are many ports like MC, PP, VLD in the
 video decode local arbiter, all these ports are according to the video HW.
 
 Required properties:
-- compatible : must be "mediatek,mt8173-m4u".
+- compatible : must be one of the following string:
+	"mediatek,mt2701-m4u" for mt2701 which uses generation one m4u HW.
+	"mediatek,mt8173-m4u" for mt8173 which uses generation two m4u HW.
 - reg : m4u register base and size.
 - interrupts : the interrupt of m4u.
 - clocks : must contain one entry for each clock-names.
@@ -46,7 +50,8 @@ Required properties:
 	according to the local arbiter index, like larb0, larb1, larb2...
 - iommu-cells : must be 1. This is the mtk_m4u_id according to the HW.
 	Specifies the mtk_m4u_id as defined in
-	dt-binding/memory/mt8173-larb-port.h.
+	dt-binding/memory/mt2701-larb-port.h for mt2701 and
+	dt-binding/memory/mt8173-larb-port.h for mt8173
 
 Example:
 	iommu: iommu@10205000 {
diff --git a/Documentation/devicetree/bindings/iommu/msm,iommu-v0.txt b/Documentation/devicetree/bindings/iommu/msm,iommu-v0.txt
new file mode 100644
index 000000000000..20236385f26e
--- /dev/null
+++ b/Documentation/devicetree/bindings/iommu/msm,iommu-v0.txt
@@ -0,0 +1,64 @@
+* QCOM IOMMU
+
+The MSM IOMMU is an implementation compatible with the ARM VMSA short
+descriptor page tables. It provides address translation for bus masters outside
+of the CPU, each connected to the IOMMU through a port called micro-TLB.
+
+Required Properties:
+
+  - compatible: Must contain "qcom,apq8064-iommu".
+  - reg: Base address and size of the IOMMU registers.
+  - interrupts: Specifiers for the MMU fault interrupts. For instances that
+    support secure mode two interrupts must be specified, for non-secure and
+    secure mode, in that order. For instances that don't support secure mode a
+    single interrupt must be specified.
+  - #iommu-cells: The number of cells needed to specify the stream id. This
+		  is always 1.
+  - qcom,ncb:	  The total number of context banks in the IOMMU.
+  - clocks	: List of clocks to be used during SMMU register access. See
+		  Documentation/devicetree/bindings/clock/clock-bindings.txt
+		  for information about the format. For each clock specified
+		  here, there must be a corresponding entry in clock-names
+		  (see below).
+
+  - clock-names	: List of clock names corresponding to the clocks specified in
+		  the "clocks" property (above).
+		  Should be "smmu_pclk" for specifying the interface clock
+		  required for iommu's register accesses.
+		  Should be "smmu_clk" for specifying the functional clock
+		  required by iommu for bus accesses.
+
+Each bus master connected to an IOMMU must reference the IOMMU in its device
+node with the following property:
+
+  - iommus: A reference to the IOMMU in multiple cells. The first cell is a
+	    phandle to the IOMMU and the second cell is the stream id.
+	    A single master device can be connected to more than one iommu
+	    and multiple contexts in each of the iommu. So multiple entries
+	    are required to list all the iommus and the stream ids that the
+	    master is connected to.
+
+Example: mdp iommu and its bus master
+
+                mdp_port0: iommu@7500000 {
+			compatible = "qcom,apq8064-iommu";
+			#iommu-cells = <1>;
+			clock-names =
+			    "smmu_pclk",
+			    "smmu_clk";
+			clocks =
+			    <&mmcc SMMU_AHB_CLK>,
+			    <&mmcc MDP_AXI_CLK>;
+			reg = <0x07500000 0x100000>;
+			interrupts =
+			    <GIC_SPI 63 0>,
+			    <GIC_SPI 64 0>;
+			qcom,ncb = <2>;
+		};
+
+		mdp: qcom,mdp@5100000 {
+			compatible = "qcom,mdp";
+			...
+			iommus = <&mdp_port0 0
+				  &mdp_port0 2>;
+		};
diff --git a/Documentation/devicetree/bindings/leds/backlight/lp855x.txt b/Documentation/devicetree/bindings/leds/backlight/lp855x.txt
index 0a3ecbc3a1b9..88f56641fc28 100644
--- a/Documentation/devicetree/bindings/leds/backlight/lp855x.txt
+++ b/Documentation/devicetree/bindings/leds/backlight/lp855x.txt
@@ -13,6 +13,7 @@ Optional properties:
   - rom-addr: Register address of ROM area to be updated (u8)
   - rom-val: Register value to be updated (u8)
   - power-supply: Regulator which controls the 3V rail
+  - enable-supply: Regulator which controls the EN/VDDIO input
 
 Example:
 
@@ -57,6 +58,7 @@ Example:
 	backlight@2c {
 		compatible = "ti,lp8557";
 		reg = <0x2c>;
+		enable-supply = <&backlight_vddio>;
 		power-supply = <&backlight_vdd>;
 
 		dev-ctrl = /bits/ 8 <0x41>;
diff --git a/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt b/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt
new file mode 100644
index 000000000000..411ccf421584
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/brcm,iproc-pdc-mbox.txt
@@ -0,0 +1,23 @@
+The PDC driver manages data transfer to and from various offload engines
+on some Broadcom SoCs. An SoC may have multiple PDC hardware blocks. There is
+one device tree entry per block.
+
+Required properties:
+- compatible : Should be "brcm,iproc-pdc-mbox".
+- reg: Should contain PDC registers location and length.
+- interrupts: Should contain the IRQ line for the PDC.
+- #mbox-cells: 1
+- brcm,rx-status-len: Length of metadata preceding received frames, in bytes.
+
+Optional properties:
+- brcm,use-bcm-hdr:  present if a BCM header precedes each frame.
+
+Example:
+	pdc0: iproc-pdc0@0x612c0000 {
+		compatible = "brcm,iproc-pdc-mbox";
+		reg = <0 0x612c0000 0 0x445>;  /* PDC FS0 regs */
+		interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
+		#mbox-cells = <1>;   /* one cell per mailbox channel */
+		brcm,rx-status-len = <32>;
+		brcm,use-bcm-hdr;
+	};
diff --git a/Documentation/devicetree/bindings/media/nokia,n900-ir b/Documentation/devicetree/bindings/media/nokia,n900-ir
new file mode 100644
index 000000000000..13a18ce37dd1
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/nokia,n900-ir
@@ -0,0 +1,20 @@
+Device-Tree bindings for LIRC TX driver for Nokia N900(RX51)
+
+Required properties:
+	- compatible: should be "nokia,n900-ir".
+	- pwms: specifies PWM used for IR signal transmission.
+
+Example node:
+
+	pwm9: dmtimer-pwm@9 {
+		compatible = "ti,omap-dmtimer-pwm";
+		ti,timers = <&timer9>;
+		ti,clock-source = <0x00>; /* timer_sys_ck */
+		#pwm-cells = <3>;
+	};
+
+	ir: n900-ir {
+		compatible = "nokia,n900-ir";
+
+		pwms = <&pwm9 0 26316 0>; /* 38000 Hz */
+	};
diff --git a/Documentation/devicetree/bindings/memory-controllers/atmel,ebi.txt b/Documentation/devicetree/bindings/memory-controllers/atmel,ebi.txt
new file mode 100644
index 000000000000..9bb5f57e2066
--- /dev/null
+++ b/Documentation/devicetree/bindings/memory-controllers/atmel,ebi.txt
@@ -0,0 +1,136 @@
+* Device tree bindings for Atmel EBI
+
+The External Bus Interface (EBI) controller is a bus where you can connect
+asynchronous (NAND, NOR, SRAM, ....) and synchronous memories (SDR/DDR SDRAMs).
+The EBI provides a glue-less interface to asynchronous memories through the SMC
+(Static Memory Controller).
+
+Required properties:
+
+- compatible:		"atmel,at91sam9260-ebi"
+			"atmel,at91sam9261-ebi"
+			"atmel,at91sam9263-ebi0"
+			"atmel,at91sam9263-ebi1"
+			"atmel,at91sam9rl-ebi"
+			"atmel,at91sam9g45-ebi"
+			"atmel,at91sam9x5-ebi"
+			"atmel,sama5d3-ebi"
+
+- reg:			Contains offset/length value for EBI memory mapping.
+			This property might contain several entries if the EBI
+			memory range is not contiguous
+
+- #address-cells:	Must be 2.
+			The first cell encodes the CS.
+			The second cell encode the offset into the CS memory
+			range.
+
+- #size-cells:		Must be set to 1.
+
+- ranges:		Encodes CS to memory region association.
+
+- clocks:		Clock feeding the EBI controller.
+			See clock-bindings.txt
+
+Children device nodes are representing device connected to the EBI bus.
+
+Required device node properties:
+
+- reg:			Contains the chip-select id, the offset and the length
+			of the memory region requested by the device.
+
+EBI bus configuration will be defined directly in the device subnode.
+
+Optional EBI/SMC properties:
+
+- atmel,smc-bus-width:		width of the asynchronous device's data bus
+				8, 16 or 32.
+				Default to 8 when undefined.
+
+- atmel,smc-byte-access-type	"write" or "select" (see Atmel datasheet).
+				Default to "select" when undefined.
+
+- atmel,smc-read-mode		"nrd" or "ncs".
+				Default to "ncs" when undefined.
+
+- atmel,smc-write-mode		"nwe" or "ncs".
+				Default to "ncs" when undefined.
+
+- atmel,smc-exnw-mode		"disabled", "frozen" or "ready".
+				Default to "disabled" when undefined.
+
+- atmel,smc-page-mode		enable page mode if present. The provided value
+				defines the page size (supported values: 4, 8,
+				16 and 32).
+
+- atmel,smc-tdf-mode:		"normal" or "optimized". When set to
+				"optimized" the data float time is optimized
+				depending on the next device being accessed
+				(next device setup time is subtracted to the
+				current device data float time).
+				Default to "normal" when undefined.
+
+If at least one atmel,smc- property is defined the following SMC timing
+properties become mandatory. In the other hand, if none of the atmel,smc-
+properties are specified, we assume that the EBI bus configuration will be
+handled by the sub-device driver, and none of those properties should be
+defined.
+
+All the timings are expressed in nanoseconds (see Atmel datasheet for a full
+description).
+
+- atmel,smc-ncs-rd-setup-ns
+- atmel,smc-nrd-setup-ns
+- atmel,smc-ncs-wr-setup-ns
+- atmel,smc-nwe-setup-ns
+- atmel,smc-ncs-rd-pulse-ns
+- atmel,smc-nrd-pulse-ns
+- atmel,smc-ncs-wr-pulse-ns
+- atmel,smc-nwe-pulse-ns
+- atmel,smc-nwe-cycle-ns
+- atmel,smc-nrd-cycle-ns
+- atmel,smc-tdf-ns
+
+Example:
+
+	ebi: ebi@10000000 {
+		compatible = "atmel,sama5d3-ebi";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		atmel,smc = <&hsmc>;
+		atmel,matrix = <&matrix>;
+		reg = <0x10000000 0x10000000
+		       0x40000000 0x30000000>;
+		ranges = <0x0 0x0 0x10000000 0x10000000
+			  0x1 0x0 0x40000000 0x10000000
+			  0x2 0x0 0x50000000 0x10000000
+			  0x3 0x0 0x60000000 0x10000000>;
+		clocks = <&mck>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_ebi_addr>;
+
+		nor: flash@0,0 {
+			compatible = "cfi-flash";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x0 0x0 0x1000000>;
+			bank-width = <2>;
+
+			atmel,smc-read-mode = "nrd";
+			atmel,smc-write-mode = "nwe";
+			atmel,smc-bus-width = <16>;
+			atmel,smc-ncs-rd-setup-ns = <0>;
+			atmel,smc-ncs-wr-setup-ns = <0>;
+			atmel,smc-nwe-setup-ns = <8>;
+			atmel,smc-nrd-setup-ns = <16>;
+			atmel,smc-ncs-rd-pulse-ns = <84>;
+			atmel,smc-ncs-wr-pulse-ns = <84>;
+			atmel,smc-nrd-pulse-ns = <76>;
+			atmel,smc-nwe-pulse-ns = <76>;
+			atmel,smc-nrd-cycle-ns = <107>;
+			atmel,smc-nwe-cycle-ns = <84>;
+			atmel,smc-tdf-ns = <16>;
+		};
+	};
+
diff --git a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt
index 06a83ceebba7..aa614b2d7cab 100644
--- a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt
@@ -2,16 +2,31 @@ SMI (Smart Multimedia Interface) Common
 
 The hardware block diagram please check bindings/iommu/mediatek,iommu.txt
 
+Mediatek SMI have two generations of HW architecture, mt8173 uses the second
+generation of SMI HW while mt2701 uses the first generation HW of SMI.
+
+There's slight differences between the two SMI, for generation 2, the
+register which control the iommu port is at each larb's register base. But
+for generation 1, the register is at smi ao base(smi always on register
+base). Besides that, the smi async clock should be prepared and enabled for
+SMI generation 1 to transform the smi clock into emi clock domain, but that is
+not needed for SMI generation 2.
+
 Required properties:
-- compatible : must be "mediatek,mt8173-smi-common"
+- compatible : must be one of :
+	"mediatek,mt2701-smi-common"
+	"mediatek,mt8173-smi-common"
 - reg : the register and size of the SMI block.
 - power-domains : a phandle to the power domain of this local arbiter.
 - clocks : Must contain an entry for each entry in clock-names.
-- clock-names : must contain 2 entries, as follows:
+- clock-names : must contain 3 entries for generation 1 smi HW and 2 entries
+  for generation 2 smi HW as follows:
   - "apb" : Advanced Peripheral Bus clock, It's the clock for setting
 	    the register.
   - "smi" : It's the clock for transfer data and command.
-  They may be the same if both source clocks are the same.
+	    They may be the same if both source clocks are the same.
+  - "async" : asynchronous clock, it help transform the smi clock into the emi
+	      clock domain, this clock is only needed by generation 1 smi HW.
 
 Example:
 	smi_common: smi@14022000 {
diff --git a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt
index 55ff3b7e0bb9..21277a56e94c 100644
--- a/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt
@@ -3,7 +3,9 @@ SMI (Smart Multimedia Interface) Local Arbiter
 The hardware block diagram please check bindings/iommu/mediatek,iommu.txt
 
 Required properties:
-- compatible : must be "mediatek,mt8173-smi-larb"
+- compatible : must be one of :
+		"mediatek,mt8173-smi-larb"
+		"mediatek,mt2701-smi-larb"
 - reg : the register and size of this local arbiter.
 - mediatek,smi : a phandle to the smi_common node.
 - power-domains : a phandle to the power domain of this local arbiter.
diff --git a/Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt b/Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt
index 21055e210234..c1359f4d48d7 100644
--- a/Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt
@@ -46,6 +46,10 @@ Required properties:
 			0 maps to GPMC_WAIT0 pin.
  - gpio-cells:		Must be set to 2
 
+Required properties when using NAND prefetch dma:
+ - dmas			GPMC NAND prefetch dma channel
+ - dma-names		Must be set to "rxtx"
+
 Timing properties for child nodes. All are optional and default to 0.
 
  - gpmc,sync-clk-ps:	Minimum clock period for synchronous mode, in picoseconds
@@ -137,7 +141,8 @@ Example for an AM33xx board:
 		ti,hwmods = "gpmc";
 		reg = <0x50000000 0x2000>;
 		interrupts = <100>;
-
+		dmas = <&edma 52 0>;
+		dma-names = "rxtx";
 		gpmc,num-cs = <8>;
 		gpmc,num-waitpins = <2>;
 		#address-cells = <2>;
diff --git a/Documentation/devicetree/bindings/mfd/da9052-i2c.txt b/Documentation/devicetree/bindings/mfd/da9052-i2c.txt
index 1857f4a6b9a9..9554292dc6cb 100644
--- a/Documentation/devicetree/bindings/mfd/da9052-i2c.txt
+++ b/Documentation/devicetree/bindings/mfd/da9052-i2c.txt
@@ -8,10 +8,13 @@ Sub-nodes:
 - regulators : Contain the regulator nodes. The DA9052/53 regulators are
   bound using their names as listed below:
 
-    buck0     : regulator BUCK0
-    buck1     : regulator BUCK1
-    buck2     : regulator BUCK2
-    buck3     : regulator BUCK3
+    buck1     : regulator BUCK CORE
+    buck2     : regulator BUCK PRO
+    buck3     : regulator BUCK MEM
+    buck4     : regulator BUCK PERI
+    ldo1      : regulator LDO1
+    ldo2      : regulator LDO2
+    ldo3      : regulator LDO3
     ldo4      : regulator LDO4
     ldo5      : regulator LDO5
     ldo6      : regulator LDO6
@@ -19,9 +22,6 @@ Sub-nodes:
     ldo8      : regulator LDO8
     ldo9      : regulator LDO9
     ldo10     : regulator LDO10
-    ldo11     : regulator LDO11
-    ldo12     : regulator LDO12
-    ldo13     : regulator LDO13
 
   The bindings details of individual regulator device can be found in:
   Documentation/devicetree/bindings/regulator/regulator.txt
@@ -36,22 +36,22 @@ i2c@63fc8000 { /* I2C1 */
 		reg = <0x48>;
 
 		regulators {
-			buck0 {
+			buck1 {
 				regulator-min-microvolt = <500000>;
 				regulator-max-microvolt = <2075000>;
 			};
 
-			buck1 {
+			buck2 {
 				regulator-min-microvolt = <500000>;
 				regulator-max-microvolt = <2075000>;
 			};
 
-			buck2 {
+			buck3 {
 				regulator-min-microvolt = <925000>;
 				regulator-max-microvolt = <2500000>;
 			};
 
-			buck3 {
+			buck4 {
 				regulator-min-microvolt = <925000>;
 				regulator-max-microvolt = <2500000>;
 			};
diff --git a/Documentation/devicetree/bindings/mfd/twl6040.txt b/Documentation/devicetree/bindings/mfd/twl6040.txt
index a41157b5d930..e6afdfa3543d 100644
--- a/Documentation/devicetree/bindings/mfd/twl6040.txt
+++ b/Documentation/devicetree/bindings/mfd/twl6040.txt
@@ -19,8 +19,8 @@ Required properties:
 
 Optional properties, nodes:
 - enable-active-high: To power on the twl6040 during boot.
-- clocks: phandle to the clk32k clock provider
-- clock-names: Must be "clk32k"
+- clocks: phandle to the clk32k and/or to mclk clock provider
+- clock-names: Must be "clk32k" for the 32K clock and "mclk" for the MCLK.
 
 Vibra functionality
 Required properties:
diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
index 31b35c3a5e47..3404afa9b938 100644
--- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
@@ -9,8 +9,12 @@ Device Tree Bindings for the Arasan SDHCI Controller
   [4] Documentation/devicetree/bindings/phy/phy-bindings.txt
 
 Required Properties:
-  - compatible: Compatibility string. Must be 'arasan,sdhci-8.9a' or
-                'arasan,sdhci-4.9a' or 'arasan,sdhci-5.1'
+  - compatible: Compatibility string.  One of:
+    - "arasan,sdhci-8.9a": generic Arasan SDHCI 8.9a PHY
+    - "arasan,sdhci-4.9a": generic Arasan SDHCI 4.9a PHY
+    - "arasan,sdhci-5.1": generic Arasan SDHCI 5.1 PHY
+    - "rockchip,rk3399-sdhci-5.1", "arasan,sdhci-5.1": rk3399 eMMC PHY
+      For this device it is strongly suggested to include arasan,soc-ctl-syscon.
   - reg: From mmc bindings: Register location and length.
   - clocks: From clock bindings: Handles to clock inputs.
   - clock-names: From clock bindings: Tuple including "clk_xin" and "clk_ahb"
@@ -22,6 +26,17 @@ Required Properties for "arasan,sdhci-5.1":
   - phys: From PHY bindings: Phandle for the Generic PHY for arasan.
   - phy-names:  MUST be "phy_arasan".
 
+Optional Properties:
+  - arasan,soc-ctl-syscon: A phandle to a syscon device (see ../mfd/syscon.txt)
+    used to access core corecfg registers.  Offsets of registers in this
+    syscon are determined based on the main compatible string for the device.
+  - clock-output-names: If specified, this will be the name of the card clock
+    which will be exposed by this device.  Required if #clock-cells is
+    specified.
+  - #clock-cells: If specified this should be the value <0>.  With this property
+    in place we will export a clock representing the Card Clock.  This clock
+    is expected to be consumed by our PHY.  You must also specify
+
 Example:
 	sdhci@e0100000 {
 		compatible = "arasan,sdhci-8.9a";
@@ -42,3 +57,19 @@ Example:
 		phys = <&emmc_phy>;
 		phy-names = "phy_arasan";
 	} ;
+
+	sdhci: sdhci@fe330000 {
+		compatible = "rockchip,rk3399-sdhci-5.1", "arasan,sdhci-5.1";
+		reg = <0x0 0xfe330000 0x0 0x10000>;
+		interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru SCLK_EMMC>, <&cru ACLK_EMMC>;
+		clock-names = "clk_xin", "clk_ahb";
+		arasan,soc-ctl-syscon = <&grf>;
+		assigned-clocks = <&cru SCLK_EMMC>;
+		assigned-clock-rates = <200000000>;
+		clock-output-names = "emmc_cardclock";
+		phys = <&emmc_phy>;
+		phy-names = "phy_arasan";
+		#clock-cells = <0>;
+		status = "disabled";
+	};
diff --git a/Documentation/devicetree/bindings/mmc/brcm,bcm2835-sdhci.txt b/Documentation/devicetree/bindings/mmc/brcm,bcm2835-sdhci.txt
deleted file mode 100644
index 59476fbdbfa1..000000000000
--- a/Documentation/devicetree/bindings/mmc/brcm,bcm2835-sdhci.txt
+++ /dev/null
@@ -1,18 +0,0 @@
-Broadcom BCM2835 SDHCI controller
-
-This file documents differences between the core properties described
-by mmc.txt and the properties that represent the BCM2835 controller.
-
-Required properties:
-- compatible : Should be "brcm,bcm2835-sdhci".
-- clocks : The clock feeding the SDHCI controller.
-
-Example:
-
-sdhci: sdhci {
-	compatible = "brcm,bcm2835-sdhci";
-	reg = <0x7e300000 0x100>;
-	interrupts = <2 30>;
-	clocks = <&clk_mmc>;
-	bus-width = <4>;
-};
diff --git a/Documentation/devicetree/bindings/mmc/brcm,bcm7425-sdhci.txt b/Documentation/devicetree/bindings/mmc/brcm,bcm7425-sdhci.txt
new file mode 100644
index 000000000000..82847174c37d
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/brcm,bcm7425-sdhci.txt
@@ -0,0 +1,36 @@
+* BROADCOM BRCMSTB/BMIPS SDHCI Controller
+
+This file documents differences between the core properties in mmc.txt
+and the properties used by the sdhci-brcmstb driver.
+
+NOTE: The driver disables all UHS speed modes by default and depends
+on Device Tree properties to enable them for SoC/Board combinations
+that support them.
+
+Required properties:
+- compatible: "brcm,bcm7425-sdhci"
+
+Refer to clocks/clock-bindings.txt for generic clock consumer properties.
+
+Example:
+
+	sdhci@f03e0100 {
+		compatible = "brcm,bcm7425-sdhci";
+		reg = <0xf03e0000 0x100>;
+		interrupts = <0x0 0x26 0x0>;
+		sdhci,auto-cmd12;
+		clocks = <&sw_sdio>;
+		sd-uhs-sdr50;
+		sd-uhs-ddr50;
+	};
+
+	sdhci@f03e0300 {
+		non-removable;
+		bus-width = <0x8>;
+		compatible = "brcm,bcm7425-sdhci";
+		reg = <0xf03e0200 0x100>;
+		interrupts = <0x0 0x27 0x0>;
+		sdhci,auto-cmd12;
+		clocks = <sw_sdio>;
+		mmc-hs200-1_8v;
+	};
diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
index dca56d6248f5..3e29050ec769 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
@@ -28,6 +28,8 @@ Optional properties:
   transparent level shifters on the outputs of the controller. Two cells are
   required, first cell specifies minimum slot voltage (mV), second cell
   specifies maximum slot voltage (mV). Several ranges could be specified.
+- fsl,tuning-start-tap: Specify the start dealy cell point when send first CMD19
+  in tuning procedure.
 - fsl,tuning-step: Specify the increasing delay cell steps in tuning procedure.
   The uSDHC use one delay cell as default increasing step to do tuning process.
   This property allows user to change the tuning step to more than one delay
diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index ed23b9bedfdc..22d1e1f3f38b 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -46,8 +46,12 @@ Optional properties:
 - mmc-hs200-1_2v: eMMC HS200 mode(1.2V I/O) is supported
 - mmc-hs400-1_8v: eMMC HS400 mode(1.8V I/O) is supported
 - mmc-hs400-1_2v: eMMC HS400 mode(1.2V I/O) is supported
+- mmc-hs400-enhanced-strobe: eMMC HS400 enhanced strobe mode is supported
 - dsr: Value the card's (optional) Driver Stage Register (DSR) should be
   programmed with. Valid range: [0 .. 0xffff].
+- no-sdio: controller is limited to send sdio cmd during initialization
+- no-sd: controller is limited to send sd cmd during initialization
+- no-mmc: controller is limited to send mmc cmd during initialization
 
 *NOTE* on CD and WP polarity. To use common for all SD/MMC host controllers line
 polarity properties, we have to fix the meaning of the "normal" and "inverted"
diff --git a/Documentation/devicetree/bindings/mtd/atmel-quadspi.txt b/Documentation/devicetree/bindings/mtd/atmel-quadspi.txt
new file mode 100644
index 000000000000..489807005eda
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/atmel-quadspi.txt
@@ -0,0 +1,32 @@
+* Atmel Quad Serial Peripheral Interface (QSPI)
+
+Required properties:
+- compatible:     Should be "atmel,sama5d2-qspi".
+- reg:            Should contain the locations and lengths of the base registers
+                  and the mapped memory.
+- reg-names:      Should contain the resource reg names:
+                  - qspi_base: configuration register address space
+                  - qspi_mmap: memory mapped address space
+- interrupts:     Should contain the interrupt for the device.
+- clocks:         The phandle of the clock needed by the QSPI controller.
+- #address-cells: Should be <1>.
+- #size-cells:    Should be <0>.
+
+Example:
+
+spi@f0020000 {
+	compatible = "atmel,sama5d2-qspi";
+	reg = <0xf0020000 0x100>, <0xd0000000 0x8000000>;
+	reg-names = "qspi_base", "qspi_mmap";
+	interrupts = <52 IRQ_TYPE_LEVEL_HIGH 7>;
+	clocks = <&spi0_clk>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_spi0_default>;
+	status = "okay";
+
+	m25p80@0 {
+		...
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
index 7066597c9a81..b40f3a492800 100644
--- a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
+++ b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
@@ -27,6 +27,7 @@ Required properties:
                          brcm,brcmnand-v6.2
                          brcm,brcmnand-v7.0
                          brcm,brcmnand-v7.1
+                         brcm,brcmnand-v7.2
                          brcm,brcmnand
 - reg              : the register start and length for NAND register region.
                      (optional) Flash DMA register range (if present)
diff --git a/Documentation/devicetree/bindings/mtd/cadence-quadspi.txt b/Documentation/devicetree/bindings/mtd/cadence-quadspi.txt
new file mode 100644
index 000000000000..f248056da24c
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/cadence-quadspi.txt
@@ -0,0 +1,56 @@
+* Cadence Quad SPI controller
+
+Required properties:
+- compatible : Should be "cdns,qspi-nor".
+- reg : Contains two entries, each of which is a tuple consisting of a
+	physical address and length. The first entry is the address and
+	length of the controller register set. The second entry is the
+	address and length of the QSPI Controller data area.
+- interrupts : Unit interrupt specifier for the controller interrupt.
+- clocks : phandle to the Quad SPI clock.
+- cdns,fifo-depth : Size of the data FIFO in words.
+- cdns,fifo-width : Bus width of the data FIFO in bytes.
+- cdns,trigger-address : 32-bit indirect AHB trigger address.
+
+Optional properties:
+- cdns,is-decoded-cs : Flag to indicate whether decoder is used or not.
+
+Optional subnodes:
+Subnodes of the Cadence Quad SPI controller are spi slave nodes with additional
+custom properties:
+- cdns,read-delay : Delay for read capture logic, in clock cycles
+- cdns,tshsl-ns : Delay in nanoseconds for the length that the master
+                  mode chip select outputs are de-asserted between
+		  transactions.
+- cdns,tsd2d-ns : Delay in nanoseconds between one chip select being
+                  de-activated and the activation of another.
+- cdns,tchsh-ns : Delay in nanoseconds between last bit of current
+                  transaction and deasserting the device chip select
+		  (qspi_n_ss_out).
+- cdns,tslch-ns : Delay in nanoseconds between setting qspi_n_ss_out low
+                  and first bit transfer.
+
+Example:
+
+	qspi: spi@ff705000 {
+		compatible = "cdns,qspi-nor";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0xff705000 0x1000>,
+		      <0xffa00000 0x1000>;
+		interrupts = <0 151 4>;
+		clocks = <&qspi_clk>;
+		cdns,is-decoded-cs;
+		cdns,fifo-depth = <128>;
+		cdns,fifo-width = <4>;
+		cdns,trigger-address = <0x00000000>;
+
+		flash0: n25q00@0 {
+			...
+			cdns,read-delay = <4>;
+			cdns,tshsl-ns = <50>;
+			cdns,tsd2d-ns = <50>;
+			cdns,tchsh-ns = <4>;
+			cdns,tslch-ns = <4>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
index 3ee7e202657c..174f68c26c1b 100644
--- a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
@@ -39,7 +39,7 @@ Optional properties:
 
 		"prefetch-polled"	Prefetch polled mode (default)
 		"polled"		Polled mode, without prefetch
-		"prefetch-dma"		Prefetch enabled sDMA mode
+		"prefetch-dma"		Prefetch enabled DMA mode
 		"prefetch-irq"		Prefetch enabled irq mode
 
  - elm_id:	<deprecated> use "ti,elm-id" instead
diff --git a/Documentation/devicetree/bindings/mtd/hisilicon,fmc-spi-nor.txt b/Documentation/devicetree/bindings/mtd/hisilicon,fmc-spi-nor.txt
new file mode 100644
index 000000000000..74981520d6dd
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/hisilicon,fmc-spi-nor.txt
@@ -0,0 +1,24 @@
+HiSilicon SPI-NOR Flash Controller
+
+Required properties:
+- compatible : Should be "hisilicon,fmc-spi-nor" and one of the following strings:
+		"hisilicon,hi3519-spi-nor"
+- address-cells : Should be 1.
+- size-cells : Should be 0.
+- reg : Offset and length of the register set for the controller device.
+- reg-names : Must include the following two entries: "control", "memory".
+- clocks : handle to spi-nor flash controller clock.
+
+Example:
+spi-nor-controller@10000000 {
+	compatible = "hisilicon,hi3519-spi-nor", "hisilicon,fmc-spi-nor";
+	#address-cells = <1>;
+	#size-cells = <0>;
+	reg = <0x10000000 0x1000>, <0x14000000 0x1000000>;
+	reg-names = "control", "memory";
+	clocks = <&clock HI3519_FMC_CLK>;
+	spi-nor@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/mtk-nand.txt b/Documentation/devicetree/bindings/mtd/mtk-nand.txt
new file mode 100644
index 000000000000..069c192ed5c2
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/mtk-nand.txt
@@ -0,0 +1,160 @@
+MTK SoCs NAND FLASH controller (NFC) DT binding
+
+This file documents the device tree bindings for MTK SoCs NAND controllers.
+The functional split of the controller requires two drivers to operate:
+the nand controller interface driver and the ECC engine driver.
+
+The hardware description for both devices must be captured as device
+tree nodes.
+
+1) NFC NAND Controller Interface (NFI):
+=======================================
+
+The first part of NFC is NAND Controller Interface (NFI) HW.
+Required NFI properties:
+- compatible:			Should be "mediatek,mtxxxx-nfc".
+- reg:				Base physical address and size of NFI.
+- interrupts:			Interrupts of NFI.
+- clocks:			NFI required clocks.
+- clock-names:			NFI clocks internal name.
+- status:			Disabled default. Then set "okay" by platform.
+- ecc-engine:			Required ECC Engine node.
+- #address-cells:		NAND chip index, should be 1.
+- #size-cells:			Should be 0.
+
+Example:
+
+	nandc: nfi@1100d000 {
+		compatible = "mediatek,mt2701-nfc";
+		reg = <0 0x1100d000 0 0x1000>;
+		interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&pericfg CLK_PERI_NFI>,
+			 <&pericfg CLK_PERI_NFI_PAD>;
+		clock-names = "nfi_clk", "pad_clk";
+		status = "disabled";
+		ecc-engine = <&bch>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+        };
+
+Platform related properties, should be set in {platform_name}.dts:
+- children nodes:	NAND chips.
+
+Children nodes properties:
+- reg:			Chip Select Signal, default 0.
+			Set as reg = <0>, <1> when need 2 CS.
+Optional:
+- nand-on-flash-bbt:	Store BBT on NAND Flash.
+- nand-ecc-mode:	the NAND ecc mode (check driver for supported modes)
+- nand-ecc-step-size:	Number of data bytes covered by a single ECC step.
+			valid values: 512 and 1024.
+			1024 is recommended for large page NANDs.
+- nand-ecc-strength:	Number of bits to correct per ECC step.
+			The valid values that the controller supports are: 4, 6,
+			8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36, 40, 44,
+			48, 52, 56, 60.
+			The strength should be calculated as follows:
+			E = (S - F) * 8 / 14
+			S = O / (P / Q)
+				E :	nand-ecc-strength.
+				S :	spare size per sector.
+				F :	FDM size, should be in the range [1,8].
+					It is used to store free oob data.
+				O :	oob size.
+				P :	page size.
+				Q :	nand-ecc-step-size.
+			If the result does not match any one of the listed
+			choices above, please select the smaller valid value from
+			the list.
+			(otherwise the driver will do the adjustment at runtime)
+- pinctrl-names:	Default NAND pin GPIO setting name.
+- pinctrl-0:		GPIO setting node.
+
+Example:
+	&pio {
+		nand_pins_default: nanddefault {
+			pins_dat {
+				pinmux = <MT2701_PIN_111_MSDC0_DAT7__FUNC_NLD7>,
+					 <MT2701_PIN_112_MSDC0_DAT6__FUNC_NLD6>,
+					 <MT2701_PIN_114_MSDC0_DAT4__FUNC_NLD4>,
+					 <MT2701_PIN_118_MSDC0_DAT3__FUNC_NLD3>,
+					 <MT2701_PIN_121_MSDC0_DAT0__FUNC_NLD0>,
+					 <MT2701_PIN_120_MSDC0_DAT1__FUNC_NLD1>,
+					 <MT2701_PIN_113_MSDC0_DAT5__FUNC_NLD5>,
+					 <MT2701_PIN_115_MSDC0_RSTB__FUNC_NLD8>,
+					 <MT2701_PIN_119_MSDC0_DAT2__FUNC_NLD2>;
+				input-enable;
+				drive-strength = <MTK_DRIVE_8mA>;
+				bias-pull-up;
+			};
+
+			pins_we {
+				pinmux = <MT2701_PIN_117_MSDC0_CLK__FUNC_NWEB>;
+				drive-strength = <MTK_DRIVE_8mA>;
+				bias-pull-up = <MTK_PUPD_SET_R1R0_10>;
+			};
+
+			pins_ale {
+				pinmux = <MT2701_PIN_116_MSDC0_CMD__FUNC_NALE>;
+				drive-strength = <MTK_DRIVE_8mA>;
+				bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+			};
+		};
+	};
+
+	&nandc {
+		status = "okay";
+		pinctrl-names = "default";
+		pinctrl-0 = <&nand_pins_default>;
+		nand@0 {
+			reg = <0>;
+			nand-on-flash-bbt;
+			nand-ecc-mode = "hw";
+			nand-ecc-strength = <24>;
+			nand-ecc-step-size = <1024>;
+		};
+	};
+
+NAND chip optional subnodes:
+- Partitions, see Documentation/devicetree/bindings/mtd/partition.txt
+
+Example:
+	nand@0 {
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			preloader@0 {
+				label = "pl";
+				read-only;
+				reg = <0x00000000 0x00400000>;
+			};
+			android@0x00400000 {
+				label = "android";
+				reg = <0x00400000 0x12c00000>;
+			};
+		};
+	};
+
+2) ECC Engine:
+==============
+
+Required BCH properties:
+- compatible:	Should be "mediatek,mtxxxx-ecc".
+- reg:		Base physical address and size of ECC.
+- interrupts:	Interrupts of ECC.
+- clocks:	ECC required clocks.
+- clock-names:	ECC clocks internal name.
+- status:	Disabled default. Then set "okay" by platform.
+
+Example:
+
+	bch: ecc@1100e000 {
+		compatible = "mediatek,mt2701-ecc";
+		reg = <0 0x1100e000 0 0x1000>;
+		interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&pericfg CLK_PERI_NFI_ECC>;
+		clock-names = "nfiecc_clk";
+		status = "disabled";
+	};
diff --git a/Documentation/devicetree/bindings/mtd/sunxi-nand.txt b/Documentation/devicetree/bindings/mtd/sunxi-nand.txt
index 086d6f44c4b9..f322f56aef74 100644
--- a/Documentation/devicetree/bindings/mtd/sunxi-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/sunxi-nand.txt
@@ -11,10 +11,16 @@ Required properties:
     * "ahb" : AHB gating clock
     * "mod" : nand controller clock
 
+Optional properties:
+- dmas : shall reference DMA channel associated to the NAND controller.
+- dma-names : shall be "rxtx".
+
 Optional children nodes:
 Children nodes represent the available nand chips.
 
 Optional properties:
+- reset : phandle + reset specifier pair
+- reset-names : must contain "ahb"
 - allwinner,rb : shall contain the native Ready/Busy ids.
  or
 - rb-gpios : shall contain the gpios used as R/B pins.
diff --git a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt
index 05f705e32a4a..e41b2d59ca7f 100644
--- a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt
+++ b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt
@@ -59,8 +59,8 @@ Example:
 		compatible = "apm,xgene-enet";
 		status = "disabled";
 		reg = <0x0 0x17020000 0x0 0xd100>,
-		      <0x0 0X17030000 0x0 0X400>,
-		      <0x0 0X10000000 0x0 0X200>;
+		      <0x0 0x17030000 0x0 0x400>,
+		      <0x0 0x10000000 0x0 0x200>;
 		reg-names = "enet_csr", "ring_csr", "ring_cmd";
 		interrupts = <0x0 0x3c 0x4>;
 		port-id = <0>;
diff --git a/Documentation/devicetree/bindings/net/cavium-pip.txt b/Documentation/devicetree/bindings/net/cavium-pip.txt
index 7dbd158810d2..e3b8fe71762b 100644
--- a/Documentation/devicetree/bindings/net/cavium-pip.txt
+++ b/Documentation/devicetree/bindings/net/cavium-pip.txt
@@ -37,6 +37,12 @@ Properties for PIP port which is a child the PIP interface:
 
 - phy-handle: Optional, see ethernet.txt file in the same directory.
 
+- rx-delay: Delay value for RGMII receive clock. Optional. Disabled if 0.
+  Value range is 1-31, and mapping to the actual delay varies depending on HW.
+
+- tx-delay: Delay value for RGMII transmit clock. Optional. Disabled if 0.
+  Value range is 1-31, and mapping to the actual delay varies depending on HW.
+
 Example:
 
 	pip@11800a0000000 {
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt
index 9bbbe7f87d67..a4a570fb2494 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.txt
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt
@@ -317,7 +317,7 @@ Each port children node must have the following mandatory properties:
 Note that a port labelled "dsa" will imply checking for the uplink phandle
 described below.
 
-Optionnal property:
+Optional property:
 - link			: Should be a list of phandles to another switch's DSA port.
 			  This property is only used when switches are being
 			  chained/cascaded together. This port is used as outgoing port
diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt
index b037a9d78d93..a1e3693cca16 100644
--- a/Documentation/devicetree/bindings/net/fsl-fec.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fec.txt
@@ -27,6 +27,9 @@ Optional properties:
   number to 1.
 - fsl,magic-packet : If present, indicates that the hardware supports waking
   up via magic packet.
+- fsl,err006687-workaround-present: If present indicates that the system has
+  the hardware workaround for ERR006687 applied and does not need a software
+  workaround.
 
 Optional subnodes:
 - mdio : specifies the mdio bus in the FEC, used as a container for phy nodes
diff --git a/Documentation/devicetree/bindings/pci/aardvark-pci.txt b/Documentation/devicetree/bindings/pci/aardvark-pci.txt
new file mode 100644
index 000000000000..bbcd9f4c501f
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/aardvark-pci.txt
@@ -0,0 +1,56 @@
+Aardvark PCIe controller
+
+This PCIe controller is used on the Marvell Armada 3700 ARM64 SoC.
+
+The Device Tree node describing an Aardvark PCIe controller must
+contain the following properties:
+
+ - compatible: Should be "marvell,armada-3700-pcie"
+ - reg: range of registers for the PCIe controller
+ - interrupts: the interrupt line of the PCIe controller
+ - #address-cells: set to <3>
+ - #size-cells: set to <2>
+ - device_type: set to "pci"
+ - ranges: ranges for the PCI memory and I/O regions
+ - #interrupt-cells: set to <1>
+ - msi-controller: indicates that the PCIe controller can itself
+   handle MSI interrupts
+ - msi-parent: pointer to the MSI controller to be used
+ - interrupt-map-mask and interrupt-map: standard PCI properties to
+   define the mapping of the PCIe interface to interrupt numbers.
+ - bus-range: PCI bus numbers covered
+
+In addition, the Device Tree describing an Aardvark PCIe controller
+must include a sub-node that describes the legacy interrupt controller
+built into the PCIe controller. This sub-node must have the following
+properties:
+
+ - interrupt-controller
+ - #interrupt-cells: set to <1>
+
+Example:
+
+	pcie0: pcie@d0070000 {
+		compatible = "marvell,armada-3700-pcie";
+		device_type = "pci";
+		status = "disabled";
+		reg = <0 0xd0070000 0 0x20000>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+		bus-range = <0x00 0xff>;
+		interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+		#interrupt-cells = <1>;
+		msi-controller;
+		msi-parent = <&pcie0>;
+		ranges = <0x82000000 0 0xe8000000   0 0xe8000000 0 0x1000000 /* Port 0 MEM */
+			  0x81000000 0 0xe9000000   0 0xe9000000 0 0x10000>; /* Port 0 IO*/
+		interrupt-map-mask = <0 0 0 7>;
+		interrupt-map = <0 0 0 1 &pcie_intc 0>,
+				<0 0 0 2 &pcie_intc 1>,
+				<0 0 0 3 &pcie_intc 2>,
+				<0 0 0 4 &pcie_intc 3>;
+		pcie_intc: interrupt-controller {
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/pci/axis,artpec6-pcie.txt b/Documentation/devicetree/bindings/pci/axis,artpec6-pcie.txt
new file mode 100644
index 000000000000..330a45b5f0b5
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/axis,artpec6-pcie.txt
@@ -0,0 +1,46 @@
+* Axis ARTPEC-6 PCIe interface
+
+This PCIe host controller is based on the Synopsys DesignWare PCIe IP
+and thus inherits all the common properties defined in designware-pcie.txt.
+
+Required properties:
+- compatible: "axis,artpec6-pcie", "snps,dw-pcie"
+- reg: base addresses and lengths of the PCIe controller (DBI),
+	the phy controller, and configuration address space.
+- reg-names: Must include the following entries:
+	- "dbi"
+	- "phy"
+	- "config"
+- interrupts: A list of interrupt outputs of the controller. Must contain an
+  entry for each entry in the interrupt-names property.
+- interrupt-names: Must include the following entries:
+	- "msi": The interrupt that is asserted when an MSI is received
+- axis,syscon-pcie: A phandle pointing to the ARTPEC-6 system controller,
+	used to enable and control the Synopsys IP.
+
+Example:
+
+	pcie@f8050000 {
+		compatible = "axis,artpec6-pcie", "snps,dw-pcie";
+		reg = <0xf8050000 0x2000
+		       0xf8040000 0x1000
+		       0xc0000000 0x1000>;
+		reg-names = "dbi", "phy", "config";
+		#address-cells = <3>;
+		#size-cells = <2>;
+		device_type = "pci";
+			  /* downstream I/O */
+		ranges = <0x81000000 0 0x00010000 0xc0010000 0 0x00010000
+			  /* non-prefetchable memory */
+			  0x82000000 0 0xc0020000 0xc0020000 0 0x1ffe0000>;
+		num-lanes = <2>;
+		interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "msi";
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 0x7>;
+		interrupt-map = <0 0 0 1 &intc GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+		                <0 0 0 2 &intc GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+		                <0 0 0 3 &intc GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
+		                <0 0 0 4 &intc GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+		axis,syscon-pcie = <&syscon>;
+	};
diff --git a/Documentation/devicetree/bindings/pci/layerscape-pci.txt b/Documentation/devicetree/bindings/pci/layerscape-pci.txt
index ef683b2fd23a..41e9f55a1467 100644
--- a/Documentation/devicetree/bindings/pci/layerscape-pci.txt
+++ b/Documentation/devicetree/bindings/pci/layerscape-pci.txt
@@ -24,6 +24,9 @@ Required properties:
   The first entry must be a link to the SCFG device node
   The second entry must be '0' or '1' based on physical PCIe controller index.
   This is used to get SCFG PEXN registers
+- dma-coherent: Indicates that the hardware IP block can ensure the coherency
+  of the data transferred from/to the IP block. This can avoid the software
+  cache flush/invalid actions, and improve the performance significantly.
 
 Example:
 
@@ -38,6 +41,7 @@ Example:
 		#address-cells = <3>;
 		#size-cells = <2>;
 		device_type = "pci";
+		dma-coherent;
 		num-lanes = <4>;
 		bus-range = <0x0 0xff>;
 		ranges = <0x81000000 0x0 0x00000000 0x40 0x00010000 0x0 0x00010000   /* downstream I/O */
diff --git a/Documentation/devicetree/bindings/phy/nvidia,tegra124-xusb-padctl.txt b/Documentation/devicetree/bindings/phy/nvidia,tegra124-xusb-padctl.txt
index 0bf1ae243552..3742c152c467 100644
--- a/Documentation/devicetree/bindings/phy/nvidia,tegra124-xusb-padctl.txt
+++ b/Documentation/devicetree/bindings/phy/nvidia,tegra124-xusb-padctl.txt
@@ -124,7 +124,7 @@ For Tegra124 and Tegra132, the list of valid PHY nodes is given below:
   - functions: "usb3-ss", "sata"
 
 For Tegra210, the list of valid PHY nodes is given below:
-- utmi: utmi-0, utmi-1, utmi-2, utmi-3
+- usb2: usb2-0, usb2-1, usb2-2, usb2-3
   - functions: "snps", "xusb", "uart"
 - hsic: hsic-0, hsic-1
   - functions: "snps", "xusb"
diff --git a/Documentation/devicetree/bindings/phy/rockchip-emmc-phy.txt b/Documentation/devicetree/bindings/phy/rockchip-emmc-phy.txt
index 555cb0f40690..e3ea55763b0a 100644
--- a/Documentation/devicetree/bindings/phy/rockchip-emmc-phy.txt
+++ b/Documentation/devicetree/bindings/phy/rockchip-emmc-phy.txt
@@ -7,6 +7,13 @@ Required properties:
  - reg: PHY register address offset and length in "general
    register files"
 
+Optional clocks using the clock bindings (see ../clock/clock-bindings.txt),
+specified by name:
+ - clock-names: Should contain "emmcclk".  Although this is listed as optional
+		(because most boards can get basic functionality without having
+		access to it), it is strongly suggested.
+ - clocks: Should have a phandle to the card clock exported by the SDHCI driver.
+
 Example:
 
 
@@ -20,6 +27,8 @@ grf: syscon@ff770000 {
 	emmcphy: phy@f780 {
 		compatible = "rockchip,rk3399-emmc-phy";
 		reg = <0xf780 0x20>;
+		clocks = <&sdhci>;
+		clock-names = "emmcclk";
 		#phy-cells = <0>;
 	};
 };
diff --git a/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt
index 32f4a2d6d0b3..fe7fe0b03cfb 100644
--- a/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt
@@ -5,6 +5,8 @@ Required properties for the root node:
 		      "amlogic,meson8b-cbus-pinctrl"
 		      "amlogic,meson8-aobus-pinctrl"
 		      "amlogic,meson8b-aobus-pinctrl"
+		      "amlogic,meson-gxbb-periphs-pinctrl"
+		      "amlogic,meson-gxbb-aobus-pinctrl"
  - reg: address and size of registers controlling irq functionality
 
 === GPIO sub-nodes ===
diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-dpaux-padctl.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-dpaux-padctl.txt
new file mode 100644
index 000000000000..f2abdaee9022
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-dpaux-padctl.txt
@@ -0,0 +1,60 @@
+Device tree binding for NVIDIA Tegra DPAUX pad controller
+========================================================
+
+The Tegra Display Port Auxiliary (DPAUX) pad controller manages two pins
+which can be assigned to either the DPAUX channel or to an I2C
+controller.
+
+This document defines the device-specific binding for the DPAUX pad
+controller. Refer to pinctrl-bindings.txt in this directory for generic
+information about pin controller device tree bindings. Please refer to
+the binding document ../display/tegra/nvidia,tegra20-host1x.txt for more
+details on the DPAUX binding.
+
+Pin muxing:
+-----------
+
+Child nodes contain the pinmux configurations following the conventions
+from the pinctrl-bindings.txt document.
+
+Since only three configurations are possible, only three child nodes are
+needed to describe the pin mux'ing options for the DPAUX pads.
+Furthermore, given that the pad functions are only applicable to a
+single set of pads, the child nodes only need to describe the pad group
+the functions are being applied to rather than the individual pads.
+
+Required properties:
+- groups: Must be "dpaux-io"
+- function: Must be either "aux", "i2c" or "off".
+
+Example:
+--------
+
+	dpaux@545c0000 {
+		...
+
+		state_dpaux_aux: pinmux-aux {
+			groups = "dpaux-io";
+			function = "aux";
+		};
+
+		state_dpaux_i2c: pinmux-i2c {
+			groups = "dpaux-io";
+			function = "i2c";
+		};
+
+		state_dpaux_off: pinmux-off {
+			groups = "dpaux-io";
+			function = "off";
+		};
+	};
+
+	...
+
+	i2c@7000d100 {
+		...
+		pinctrl-0 = <&state_dpaux_i2c>;
+		pinctrl-1 = <&state_dpaux_off>;
+		pinctrl-names = "default", "idle";
+		status = "disabled";
+	};
diff --git a/Documentation/devicetree/bindings/power/renesas,apmu.txt b/Documentation/devicetree/bindings/power/renesas,apmu.txt
new file mode 100644
index 000000000000..84404c9edff7
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/renesas,apmu.txt
@@ -0,0 +1,31 @@
+DT bindings for the Renesas Advanced Power Management Unit
+
+Renesas R-Car line of SoCs utilize one or more APMU hardware units
+for CPU core power domain control including SMP boot and CPU Hotplug.
+
+Required properties:
+
+- compatible: Should be "renesas,<soctype>-apmu", "renesas,apmu" as fallback.
+	      Examples with soctypes are:
+		- "renesas,r8a7790-apmu" (R-Car H2)
+		- "renesas,r8a7791-apmu" (R-Car M2-W)
+		- "renesas,r8a7792-apmu" (R-Car V2H)
+		- "renesas,r8a7793-apmu" (R-Car M2-N)
+		- "renesas,r8a7794-apmu" (R-Car E2)
+
+- reg: Base address and length of the I/O registers used by the APMU.
+
+- cpus: This node contains a list of CPU cores, which should match the order
+  of CPU cores used by the WUPCR and PSTR registers in the Advanced Power
+  Management Unit section of the device's datasheet.
+
+
+Example:
+
+This shows the r8a7791 APMU that can control CPU0 and CPU1.
+
+	apmu@e6152000 {
+		compatible = "renesas,r8a7791-apmu", "renesas,apmu";
+		reg = <0 0xe6152000 0 0x188>;
+		cpus = <&cpu0 &cpu1>;
+	};
diff --git a/Documentation/devicetree/bindings/power/renesas,rcar-sysc.txt b/Documentation/devicetree/bindings/power/renesas,rcar-sysc.txt
index b74e4d4785ab..0725fb37a973 100644
--- a/Documentation/devicetree/bindings/power/renesas,rcar-sysc.txt
+++ b/Documentation/devicetree/bindings/power/renesas,rcar-sysc.txt
@@ -14,6 +14,7 @@ Required properties:
       - "renesas,r8a7793-sysc" (R-Car M2-N)
       - "renesas,r8a7794-sysc" (R-Car E2)
       - "renesas,r8a7795-sysc" (R-Car H3)
+      - "renesas,r8a7796-sysc" (R-Car M3-W)
   - reg: Address start and address range for the device.
   - #power-domain-cells: Must be 1.
 
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/network.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/network.txt
deleted file mode 100644
index 29b28b8f9a89..000000000000
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/network.txt
+++ /dev/null
@@ -1,43 +0,0 @@
-* Network
-
-Currently defined compatibles:
-- fsl,cpm1-scc-enet
-- fsl,cpm2-scc-enet
-- fsl,cpm1-fec-enet
-- fsl,cpm2-fcc-enet (third resource is GFEMR)
-- fsl,qe-enet
-
-Example:
-
-	ethernet@11300 {
-		compatible = "fsl,mpc8272-fcc-enet",
-			     "fsl,cpm2-fcc-enet";
-		reg = <11300 20 8400 100 11390 1>;
-		local-mac-address = [ 00 00 00 00 00 00 ];
-		interrupts = <20 8>;
-		interrupt-parent = <&PIC>;
-		phy-handle = <&PHY0>;
-		fsl,cpm-command = <12000300>;
-	};
-
-* MDIO
-
-Currently defined compatibles:
-fsl,pq1-fec-mdio (reg is same as first resource of FEC device)
-fsl,cpm2-mdio-bitbang (reg is port C registers)
-
-Properties for fsl,cpm2-mdio-bitbang:
-fsl,mdio-pin : pin of port C controlling mdio data
-fsl,mdc-pin : pin of port C controlling mdio clock
-
-Example:
-	mdio@10d40 {
-		compatible = "fsl,mpc8272ads-mdio-bitbang",
-			     "fsl,mpc8272-mdio-bitbang",
-			     "fsl,cpm2-mdio-bitbang";
-		reg = <10d40 14>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		fsl,mdio-pin = <12>;
-		fsl,mdc-pin = <13>;
-	};
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/fman.txt b/Documentation/devicetree/bindings/powerpc/fsl/fman.txt
index 55c2c03fc81e..df873d1f3b7c 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/fman.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/fman.txt
@@ -35,7 +35,7 @@ PROPERTIES
 		Definition: Specifies the index of the FMan unit.
 
 		The cell-index value may be used by the SoC, to identify the
-		FMan unit in the SoC memory map. In the table bellow,
+		FMan unit in the SoC memory map. In the table below,
 		there's a description of the cell-index use in each SoC:
 
 		- P1023:
@@ -247,7 +247,7 @@ PROPERTIES
 
 		The cell-index value may be used by the FMan or the SoC, to
 		identify the MAC unit in the FMan (or SoC) memory map.
-		In the tables bellow there's a description of the cell-index
+		In the tables below there's a description of the cell-index
 		use, there are two tables, one describes the use of cell-index
 		by the FMan, the second describes the use by the SoC:
 
diff --git a/Documentation/devicetree/bindings/powerpc/opal/oppanel-opal.txt b/Documentation/devicetree/bindings/powerpc/opal/oppanel-opal.txt
new file mode 100644
index 000000000000..dffb79108b61
--- /dev/null
+++ b/Documentation/devicetree/bindings/powerpc/opal/oppanel-opal.txt
@@ -0,0 +1,14 @@
+IBM OPAL Operator Panel Binding
+-------------------------------
+
+Required properties:
+- compatible : Should be "ibm,opal-oppanel".
+- #lines     : Number of lines on the operator panel e.g. <0x2>.
+- #length    : Number of characters per line of the operator panel e.g. <0x10>.
+
+Example:
+	oppanel {
+		compatible = "ibm,opal-oppanel";
+		#lines = <0x2>;
+		#length = <0x10>;
+	};
diff --git a/Documentation/devicetree/bindings/pwm/cirrus,clps711x-pwm.txt b/Documentation/devicetree/bindings/pwm/cirrus,clps711x-pwm.txt
index a183db48f910..c0b2028238d6 100644
--- a/Documentation/devicetree/bindings/pwm/cirrus,clps711x-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/cirrus,clps711x-pwm.txt
@@ -1,15 +1,14 @@
 * Cirris Logic CLPS711X PWM controller
 
 Required properties:
-- compatible: Shall contain "cirrus,clps711x-pwm".
+- compatible: Shall contain "cirrus,ep7209-pwm".
 - reg: Physical base address and length of the controller's registers.
 - clocks: phandle + clock specifier pair of the PWM reference clock.
 - #pwm-cells: Should be 1. The cell specifies the index of the channel.
 
 Example:
 	pwm: pwm@80000400 {
-		compatible = "cirrus,ep7312-pwm",
-			     "cirrus,clps711x-pwm";
+		compatible = "cirrus,ep7312-pwm", "cirrus,ep7209-pwm";
 		reg = <0x80000400 0x4>;
 		clocks = <&clks 8>;
 		#pwm-cells = <1>;
diff --git a/Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt b/Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt
index 5befb538db95..2e53324fb720 100644
--- a/Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt
+++ b/Documentation/devicetree/bindings/pwm/pwm-omap-dmtimer.txt
@@ -9,6 +9,10 @@ Required properties:
 
 Optional properties:
 - ti,prescaler: Should be a value between 0 and 7, see the timers datasheet
+- ti,clock-source: Set dmtimer parent clock, values between 0 and 2:
+  - 0x00 - high-frequency system clock (timer_sys_ck)
+  - 0x01 - 32-kHz always-on clock (timer_32k_ck)
+  - 0x02 - external clock (timer_ext_ck, OMAP2 only)
 
 Example:
 	pwm9: dmtimer-pwm@9 {
diff --git a/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt b/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt
index fb81179dce37..8007e839a716 100644
--- a/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt
+++ b/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt
@@ -2,28 +2,48 @@ TI SOC ECAP based APWM controller
 
 Required properties:
 - compatible: Must be "ti,<soc>-ecap".
-  for am33xx - compatible = "ti,am33xx-ecap";
-  for da850  - compatible = "ti,da850-ecap", "ti,am33xx-ecap";
+  for am33xx - compatible = "ti,am3352-ecap", "ti,am33xx-ecap";
+  for am4372 - compatible = "ti,am4372-ecap", "ti,am3352-ecap", "ti,am33xx-ecap";
+  for da850  - compatible = "ti,da850-ecap", "ti,am3352-ecap", "ti,am33xx-ecap";
+  for dra746 - compatible = "ti,dra746-ecap", "ti,am3352-ecap";
 - #pwm-cells: should be 3. See pwm.txt in this directory for a description of
   the cells format. The PWM channel index ranges from 0 to 4. The only third
   cell flag supported by this binding is PWM_POLARITY_INVERTED.
 - reg: physical base address and size of the registers map.
 
 Optional properties:
-- ti,hwmods: Name of the hwmod associated to the ECAP:
-  "ecap<x>", <x> being the 0-based instance number from the HW spec
+- clocks: Handle to the ECAP's functional clock.
+- clock-names: Must be set to "fck".
 
 Example:
 
-ecap0: ecap@0 { /* ECAP on am33xx */
-	compatible = "ti,am33xx-ecap";
+ecap0: ecap@48300100 { /* ECAP on am33xx */
+	compatible = "ti,am3352-ecap", "ti,am33xx-ecap";
+	#pwm-cells = <3>;
+	reg = <0x48300100 0x80>;
+	clocks = <&l4ls_gclk>;
+	clock-names = "fck";
+};
+
+ecap0: ecap@48300100 { /* ECAP on am4372 */
+	compatible = "ti,am4372-ecap", "ti,am3352-ecap", "ti,am33xx-ecap";
 	#pwm-cells = <3>;
 	reg = <0x48300100 0x80>;
 	ti,hwmods = "ecap0";
+	clocks = <&l4ls_gclk>;
+	clock-names = "fck";
+};
+
+ecap0: ecap@1f06000 { /* ECAP on da850 */
+	compatible = "ti,da850-ecap", "ti,am3352-ecap", "ti,am33xx-ecap";
+	#pwm-cells = <3>;
+	reg = <0x1f06000 0x80>;
 };
 
-ecap0: ecap@0 { /* ECAP on da850 */
-	compatible = "ti,da850-ecap", "ti,am33xx-ecap";
+ecap0: ecap@4843e100 {
+	compatible = "ti,dra746-ecap", "ti,am3352-ecap";
 	#pwm-cells = <3>;
-	reg = <0x306000 0x80>;
+	reg = <0x4843e100 0x80>;
+	clocks = <&l4_root_clk_div>;
+	clock-names = "fck";
 };
diff --git a/Documentation/devicetree/bindings/pwm/pwm-tiehrpwm.txt b/Documentation/devicetree/bindings/pwm/pwm-tiehrpwm.txt
index 9c100b2c5b23..944fe356bb45 100644
--- a/Documentation/devicetree/bindings/pwm/pwm-tiehrpwm.txt
+++ b/Documentation/devicetree/bindings/pwm/pwm-tiehrpwm.txt
@@ -2,28 +2,48 @@ TI SOC EHRPWM based PWM controller
 
 Required properties:
 - compatible: Must be "ti,<soc>-ehrpwm".
-  for am33xx - compatible = "ti,am33xx-ehrpwm";
-  for da850  - compatible = "ti,da850-ehrpwm", "ti,am33xx-ehrpwm";
+  for am33xx  - compatible = "ti,am3352-ehrpwm", "ti,am33xx-ehrpwm";
+  for am4372  - compatible = "ti,am4372-ehrpwm", "ti-am3352-ehrpwm", "ti,am33xx-ehrpwm";
+  for da850   - compatible = "ti,da850-ehrpwm", "ti-am3352-ehrpwm", "ti,am33xx-ehrpwm";
+  for dra746 - compatible = "ti,dra746-ehrpwm", "ti-am3352-ehrpwm";
 - #pwm-cells: should be 3. See pwm.txt in this directory for a description of
   the cells format. The only third cell flag supported by this binding is
   PWM_POLARITY_INVERTED.
 - reg: physical base address and size of the registers map.
 
 Optional properties:
-- ti,hwmods: Name of the hwmod associated to the EHRPWM:
-  "ehrpwm<x>", <x> being the 0-based instance number from the HW spec
+- clocks: Handle to the PWM's time-base and functional clock.
+- clock-names: Must be set to "tbclk" and "fck".
 
 Example:
 
-ehrpwm0: ehrpwm@0 { /* EHRPWM on am33xx */
-	compatible = "ti,am33xx-ehrpwm";
+ehrpwm0: pwm@48300200 { /* EHRPWM on am33xx */
+	compatible = "ti,am3352-ehrpwm", "ti,am33xx-ehrpwm";
 	#pwm-cells = <3>;
 	reg = <0x48300200 0x100>;
+	clocks = <&ehrpwm0_tbclk>, <&l4ls_gclk>;
+	clock-names = "tbclk", "fck";
+};
+
+ehrpwm0: pwm@48300200 { /* EHRPWM on am4372 */
+	compatible = "ti,am4372-ehrpwm", "ti,am3352-ehrpwm", "ti,am33xx-ehrpwm";
+	#pwm-cells = <3>;
+	reg = <0x48300200 0x80>;
+	clocks = <&ehrpwm0_tbclk>, <&l4ls_gclk>;
+	clock-names = "tbclk", "fck";
 	ti,hwmods = "ehrpwm0";
 };
 
-ehrpwm0: ehrpwm@0 { /* EHRPWM on da850 */
-	compatible = "ti,da850-ehrpwm", "ti,am33xx-ehrpwm";
+ehrpwm0: pwm@1f00000 { /* EHRPWM on da850 */
+	compatible = "ti,da850-ehrpwm", "ti,am3352-ehrpwm", "ti,am33xx-ehrpwm";
+	#pwm-cells = <3>;
+	reg = <0x1f00000 0x2000>;
+};
+
+ehrpwm0: pwm@4843e200 { /* EHRPWM on dra746 */
+	compatible = "ti,dra746-ehrpwm", "ti,am3352-ehrpwm";
 	#pwm-cells = <3>;
-	reg = <0x300000 0x2000>;
+	reg = <0x4843e200 0x80>;
+	clocks = <&ehrpwm0_tbclk>, <&l4_root_clk_div>;
+	clock-names = "tbclk", "fck";
 };
diff --git a/Documentation/devicetree/bindings/pwm/pwm-tipwmss.txt b/Documentation/devicetree/bindings/pwm/pwm-tipwmss.txt
index f7eae77f8354..1a5d7b71db89 100644
--- a/Documentation/devicetree/bindings/pwm/pwm-tipwmss.txt
+++ b/Documentation/devicetree/bindings/pwm/pwm-tipwmss.txt
@@ -1,7 +1,11 @@
 TI SOC based PWM Subsystem
 
 Required properties:
-- compatible: Must be "ti,am33xx-pwmss";
+- compatible: Must be "ti,<soc>-pwmss".
+  for am33xx  - compatible = "ti,am33xx-pwmss";
+  for am4372  - compatible = "ti,am4372-pwmss","ti,am33xx-pwmss";
+  for dra746 - compatible = "ti,dra746-pwmss", "ti,am33xx-pwmss"
+
 - reg: physical base address and size of the registers map.
 - address-cells: Specify the number of u32 entries needed in child nodes.
 		  Should set to 1.
@@ -16,7 +20,7 @@ Required properties:
 Also child nodes should also populated under PWMSS DT node.
 
 Example:
-pwmss0: pwmss@48300000 {
+epwmss0: epwmss@48300000 { /* PWMSS for am33xx */
 	compatible = "ti,am33xx-pwmss";
 	reg = <0x48300000 0x10>;
 	ti,hwmods = "epwmss0";
@@ -29,3 +33,28 @@ pwmss0: pwmss@48300000 {
 
 	/* child nodes go here */
 };
+
+epwmss0: epwmss@48300000 { /* PWMSS for am4372 */
+	compatible = "ti,am4372-pwmss","ti,am33xx-pwmss"
+	reg = <0x48300000 0x10>;
+	ti,hwmods = "epwmss0";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	status = "disabled";
+	ranges = <0x48300100 0x48300100 0x80   /* ECAP */
+		  0x48300180 0x48300180 0x80   /* EQEP */
+		  0x48300200 0x48300200 0x80>; /* EHRPWM */
+
+	/* child nodes go here */
+};
+
+epwmss0: epwmss@4843e000 { /* PWMSS for DRA7xx */
+	compatible = "ti,dra746-pwmss", "ti,am33xx-pwmss";
+	reg = <0x4843e000 0x30>;
+	ti,hwmods = "epwmss0";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	ranges;
+
+	/* child nodes go here */
+};
diff --git a/Documentation/devicetree/bindings/regmap/regmap.txt b/Documentation/devicetree/bindings/regmap/regmap.txt
index 0127be360fe8..873096be0278 100644
--- a/Documentation/devicetree/bindings/regmap/regmap.txt
+++ b/Documentation/devicetree/bindings/regmap/regmap.txt
@@ -14,7 +14,7 @@ architectures that typically run big-endian operating systems
 be marked that way in the devicetree.
 
 On SoCs that can be operated in both big-endian and little-endian
-modes, with a single hardware switch controlling both the endianess
+modes, with a single hardware switch controlling both the endianness
 of the CPU and a byteswap for MMIO registers (e.g. many Broadcom MIPS
 chips), "native-endian" is used to allow using the same device tree
 blob in both cases.
diff --git a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.txt b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.txt
new file mode 100644
index 000000000000..e746b631793a
--- /dev/null
+++ b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.txt
@@ -0,0 +1,18 @@
+Amlogic Meson SoC Reset Controller
+=======================================
+
+Please also refer to reset.txt in this directory for common reset
+controller binding usage.
+
+Required properties:
+- compatible: Should be "amlogic,meson8b-reset" or "amlogic,meson-gxbb-reset"
+- reg: should contain the register address base
+- #reset-cells: 1, see below
+
+example:
+
+reset: reset-controller {
+	compatible = "amlogic,meson-gxbb-reset";
+	reg = <0x0 0x04404 0x0 0x20>;
+	#reset-cells = <1>;
+};
diff --git a/Documentation/devicetree/bindings/reset/hisilicon,hi6220-reset.txt b/Documentation/devicetree/bindings/reset/hisilicon,hi6220-reset.txt
index e0b185a944ba..c25da39df707 100644
--- a/Documentation/devicetree/bindings/reset/hisilicon,hi6220-reset.txt
+++ b/Documentation/devicetree/bindings/reset/hisilicon,hi6220-reset.txt
@@ -8,7 +8,9 @@ The reset controller registers are part of the system-ctl block on
 hi6220 SoC.
 
 Required properties:
-- compatible: may be "hisilicon,hi6220-sysctrl"
+- compatible: should be one of the following:
+  - "hisilicon,hi6220-sysctrl", "syscon" : For peripheral reset controller.
+  - "hisilicon,hi6220-mediactrl", "syscon" : For media reset controller.
 - reg: should be register base and length as documented in the
   datasheet
 - #reset-cells: 1, see below
diff --git a/Documentation/devicetree/bindings/reset/ti-syscon-reset.txt b/Documentation/devicetree/bindings/reset/ti-syscon-reset.txt
new file mode 100644
index 000000000000..164c7f34c451
--- /dev/null
+++ b/Documentation/devicetree/bindings/reset/ti-syscon-reset.txt
@@ -0,0 +1,91 @@
+TI SysCon Reset Controller
+=======================
+
+Almost all SoCs have hardware modules that require reset control in addition
+to clock and power control for their functionality. The reset control is
+typically provided by means of memory-mapped I/O registers. These registers are
+sometimes a part of a larger register space region implementing various
+functionalities. This register range is best represented as a syscon node to
+allow multiple entities to access their relevant registers in the common
+register space.
+
+A SysCon Reset Controller node defines a device that uses a syscon node
+and provides reset management functionality for various hardware modules
+present on the SoC.
+
+SysCon Reset Controller Node
+============================
+Each of the reset provider/controller nodes should be a child of a syscon
+node and have the following properties.
+
+Required properties:
+--------------------
+ - compatible		: Should be,
+			    "ti,k2e-pscrst"
+			    "ti,k2l-pscrst"
+			    "ti,k2hk-pscrst"
+			    "ti,syscon-reset"
+ - #reset-cells		: Should be 1. Please see the reset consumer node below
+			  for usage details
+ - ti,reset-bits	: Contains the reset control register information
+			  Should contain 7 cells for each reset exposed to
+			  consumers, defined as:
+			    Cell #1 : offset of the reset assert control
+			              register from the syscon register base
+			    Cell #2 : bit position of the reset in the reset
+			              assert control register
+			    Cell #3 : offset of the reset deassert control
+			              register from the syscon register base
+			    Cell #4 : bit position of the reset in the reset
+			              deassert control register
+			    Cell #5 : offset of the reset status register
+			              from the syscon register base
+			    Cell #6 : bit position of the reset in the
+			              reset status register
+			    Cell #7 : Flags used to control reset behavior,
+			              availible flags defined in the DT include
+			              file <dt-bindings/reset/ti-syscon.h>
+
+SysCon Reset Consumer Nodes
+===========================
+Each of the reset consumer nodes should have the following properties,
+in addition to their own properties.
+
+Required properties:
+--------------------
+ - resets	: A phandle to the reset controller node and an index number
+		  to a reset specifier as defined above.
+
+Please also refer to Documentation/devicetree/bindings/reset/reset.txt for
+common reset controller usage by consumers.
+
+Example:
+--------
+The following example demonstrates a syscon node, the reset controller node
+using the syscon node, and a consumer (a DSP device) on the TI Keystone 2
+Edison SoC.
+
+/ {
+	soc {
+		psc: power-sleep-controller@02350000 {
+			compatible = "syscon", "simple-mfd";
+			reg = <0x02350000 0x1000>;
+
+			pscrst: psc-reset {
+				compatible = "ti,k2e-pscrst", "ti,syscon-reset";
+				#reset-cells = <1>;
+
+				ti,reset-bits = <
+					0xa3c 8 0xa3c 8 0x83c 8 (ASSERT_SET|DEASSERT_CLEAR|STATUS_SET)   /* 0: pcrst-dsp0 */
+					0xa40 5 0xa44 3 0     0 (ASSERT_SET|DEASSERT_CLEAR|STATUS_NONE)  /* 1: pcrst-example */
+				>;
+			};
+		};
+
+		dsp0: dsp0 {
+			...
+			resets = <&pscrst 0>;
+			...
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/rng/amlogic,meson-rng.txt b/Documentation/devicetree/bindings/rng/amlogic,meson-rng.txt
new file mode 100644
index 000000000000..202f2d09a23f
--- /dev/null
+++ b/Documentation/devicetree/bindings/rng/amlogic,meson-rng.txt
@@ -0,0 +1,14 @@
+Amlogic Meson Random number generator
+=====================================
+
+Required properties:
+
+- compatible : should be "amlogic,meson-rng"
+- reg : Specifies base physical address and size of the registers.
+
+Example:
+
+rng {
+        compatible = "amlogic,meson-rng";
+        reg = <0x0 0xc8834000 0x0 0x4>;
+};
diff --git a/Documentation/devicetree/bindings/rtc/rtc-opal.txt b/Documentation/devicetree/bindings/rtc/rtc-opal.txt
index a1734e5cb75b..2340938cd0f5 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-opal.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-opal.txt
@@ -2,7 +2,7 @@ IBM OPAL real-time clock
 ------------------------
 
 Required properties:
-- comapatible: Should be "ibm,opal-rtc"
+- compatible: Should be "ibm,opal-rtc"
 
 Optional properties:
 - wakeup-source: Decides if the wakeup is supported or not
diff --git a/Documentation/devicetree/bindings/serial/cirrus,clps711x-uart.txt b/Documentation/devicetree/bindings/serial/cirrus,clps711x-uart.txt
index caaeb2583579..07013fa60a48 100644
--- a/Documentation/devicetree/bindings/serial/cirrus,clps711x-uart.txt
+++ b/Documentation/devicetree/bindings/serial/cirrus,clps711x-uart.txt
@@ -1,7 +1,7 @@
 * Cirrus Logic CLPS711X Universal Asynchronous Receiver/Transmitter (UART)
 
 Required properties:
-- compatible: Should be "cirrus,clps711x-uart".
+- compatible: Should be "cirrus,ep7209-uart".
 - reg: Address and length of the register set for the device.
 - interrupts: Should contain UART TX and RX interrupt.
 - clocks: Should contain UART core clock number.
@@ -20,7 +20,7 @@ Example:
 	};
 
 	uart1: uart@80000480 {
-		compatible = "cirrus,clps711x-uart";
+		compatible = "cirrus,ep7312-uart","cirrus,ep7209-uart";
 		reg = <0x80000480 0x80>;
 		interrupts = <12 13>;
 		clocks = <&clks 11>;
diff --git a/Documentation/devicetree/bindings/serial/mtk-uart.txt b/Documentation/devicetree/bindings/serial/mtk-uart.txt
index e99e10ab9ecb..0015c722be7b 100644
--- a/Documentation/devicetree/bindings/serial/mtk-uart.txt
+++ b/Documentation/devicetree/bindings/serial/mtk-uart.txt
@@ -6,6 +6,7 @@ Required properties:
   * "mediatek,mt6580-uart" for MT6580 compatible UARTS
   * "mediatek,mt6582-uart" for MT6582 compatible UARTS
   * "mediatek,mt6589-uart" for MT6589 compatible UARTS
+  * "mediatek,mt6755-uart" for MT6755 compatible UARTS
   * "mediatek,mt6795-uart" for MT6795 compatible UARTS
   * "mediatek,mt7623-uart" for MT7623 compatible UARTS
   * "mediatek,mt8127-uart" for MT8127 compatible UARTS
diff --git a/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.txt b/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.txt
index 182777fac9a2..d5f73b8f614f 100644
--- a/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.txt
+++ b/Documentation/devicetree/bindings/serial/qcom,msm-uartdm.txt
@@ -28,10 +28,10 @@ Optional properties:
 - dma-names: Should contain "tx" for transmit and "rx" for receive channels
 - qcom,tx-crci: Identificator <u32> for Client Rate Control Interface to be
            used with TX DMA channel. Required when using DMA for transmission
-           with UARTDM v1.3 and bellow.
+           with UARTDM v1.3 and below.
 - qcom,rx-crci: Identificator <u32> for Client Rate Control Interface to be
            used with RX DMA channel. Required when using DMA for reception
-           with UARTDM v1.3 and bellow.
+           with UARTDM v1.3 and below.
 
 Note: Aliases may be defined to ensure the correct ordering of the UARTs.
 The alias serialN will result in the UART being assigned port N.  If any
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/cpm.txt
index 160c752484b4..160c752484b4 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/cpm.txt
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/brg.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/cpm/brg.txt
index 4c7d45eaf025..4c7d45eaf025 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/brg.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/cpm/brg.txt
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/i2c.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/cpm/i2c.txt
index 87bc6048667e..87bc6048667e 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/i2c.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/cpm/i2c.txt
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/pic.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/cpm/pic.txt
index 8e3ee1681618..8e3ee1681618 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/pic.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/cpm/pic.txt
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/usb.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/cpm/usb.txt
index 74bfda4bb824..74bfda4bb824 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/usb.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/cpm/usb.txt
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/gpio.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt
index 349f79fd7076..349f79fd7076 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/gpio.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt
diff --git a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/network.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/network.txt
new file mode 100644
index 000000000000..03c741602c6d
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/network.txt
@@ -0,0 +1,124 @@
+* Network
+
+Currently defined compatibles:
+- fsl,cpm1-scc-enet
+- fsl,cpm2-scc-enet
+- fsl,cpm1-fec-enet
+- fsl,cpm2-fcc-enet (third resource is GFEMR)
+- fsl,qe-enet
+
+Example:
+
+	ethernet@11300 {
+		compatible = "fsl,mpc8272-fcc-enet",
+			     "fsl,cpm2-fcc-enet";
+		reg = <11300 20 8400 100 11390 1>;
+		local-mac-address = [ 00 00 00 00 00 00 ];
+		interrupts = <20 8>;
+		interrupt-parent = <&PIC>;
+		phy-handle = <&PHY0>;
+		fsl,cpm-command = <12000300>;
+	};
+
+* MDIO
+
+Currently defined compatibles:
+fsl,pq1-fec-mdio (reg is same as first resource of FEC device)
+fsl,cpm2-mdio-bitbang (reg is port C registers)
+
+Properties for fsl,cpm2-mdio-bitbang:
+fsl,mdio-pin : pin of port C controlling mdio data
+fsl,mdc-pin : pin of port C controlling mdio clock
+
+Example:
+	mdio@10d40 {
+		compatible = "fsl,mpc8272ads-mdio-bitbang",
+			     "fsl,mpc8272-mdio-bitbang",
+			     "fsl,cpm2-mdio-bitbang";
+		reg = <10d40 14>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		fsl,mdio-pin = <12>;
+		fsl,mdc-pin = <13>;
+	};
+
+* HDLC
+
+Currently defined compatibles:
+- fsl,ucc-hdlc
+
+Properties for fsl,ucc-hdlc:
+- rx-clock-name
+- tx-clock-name
+	Usage: required
+	Value type: <string>
+	Definition : Must be "brg1"-"brg16" for internal clock source,
+		     Must be "clk1"-"clk24" for external clock source.
+
+- fsl,tdm-interface
+	Usage: optional
+	Value type: <empty>
+	Definition : Specify that hdlc is based on tdm-interface
+
+The property below is dependent on fsl,tdm-interface:
+- fsl,rx-sync-clock
+	Usage: required
+	Value type: <string>
+	Definition : Must be "none", "rsync_pin", "brg9-11" and "brg13-15".
+
+- fsl,tx-sync-clock
+	Usage: required
+	Value type: <string>
+	Definition : Must be "none", "tsync_pin", "brg9-11" and "brg13-15".
+
+- fsl,tdm-framer-type
+	Usage: required for tdm interface
+	Value type: <string>
+	Definition : "e1" or "t1".Now e1 and t1 are used, other framer types
+		     are not supported.
+
+- fsl,tdm-id
+	Usage: required for tdm interface
+	Value type: <u32>
+	Definition : number of TDM ID
+
+- fsl,tx-timeslot-mask
+- fsl,rx-timeslot-mask
+	Usage: required for tdm interface
+	Value type: <u32>
+	Definition : time slot mask for TDM operation. Indicates which time
+		     slots used for transmitting and receiving.
+
+- fsl,siram-entry-id
+	Usage: required for tdm interface
+	Value type: <u32>
+	Definition : Must be 0,2,4...64. the number of TDM entry.
+
+- fsl,tdm-internal-loopback
+	usage: optional for tdm interface
+	value type: <empty>
+	Definition : Internal loopback connecting on TDM layer.
+
+Example for tdm interface:
+
+	ucc@2000 {
+		compatible = "fsl,ucc-hdlc";
+		rx-clock-name = "clk8";
+		tx-clock-name = "clk9";
+		fsl,rx-sync-clock = "rsync_pin";
+		fsl,tx-sync-clock = "tsync_pin";
+		fsl,tx-timeslot-mask = <0xfffffffe>;
+		fsl,rx-timeslot-mask = <0xfffffffe>;
+		fsl,tdm-framer-type = "e1";
+		fsl,tdm-id = <0>;
+		fsl,siram-entry-id = <0>;
+		fsl,tdm-interface;
+	};
+
+Example for hdlc without tdm interface:
+
+	ucc@2000 {
+		compatible = "fsl,ucc-hdlc";
+		rx-clock-name = "brg1";
+		tx-clock-name = "brg1";
+	};
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe.txt
index 4f8930263dd9..d7afaff5faff 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe.txt
@@ -69,6 +69,58 @@ Example:
 	};
      };
 
+* Interrupt Controller (IC)
+
+Required properties:
+- compatible : should be "fsl,qe-ic".
+- reg : Address range of IC register set.
+- interrupts : interrupts generated by the device.
+- interrupt-controller : this device is a interrupt controller.
+
+Example:
+
+	qeic: interrupt-controller@80 {
+		interrupt-controller;
+		compatible = "fsl,qe-ic";
+		#address-cells = <0>;
+		#interrupt-cells = <1>;
+		reg = <0x80 0x80>;
+		interrupts = <95 2 0 0  94 2 0 0>;
+	};
+
+* Serial Interface Block (SI)
+
+The SI manages the routing of eight TDM lines to the QE block serial drivers
+, the MCC and the UCCs, for receive and transmit.
+
+Required properties:
+- compatible : must be "fsl,<chip>-qe-si". For t1040, must contain
+  "fsl,t1040-qe-si".
+- reg : Address range of SI register set.
+
+Example:
+
+	si1: si@700 {
+		compatible = "fsl,t1040-qe-si";
+		reg = <0x700 0x80>;
+	};
+
+* Serial Interface Block RAM(SIRAM)
+
+store the routing entries of SI
+
+Required properties:
+- compatible : should be "fsl,<chip>-qe-siram". For t1040, must contain
+  "fsl,t1040-qe-siram".
+- reg : Address range of SI RAM.
+
+Example:
+
+	siram1: siram@1000 {
+		compatible = "fsl,t1040-qe-siram";
+		reg = <0x1000 0x800>;
+	};
+
 * QE Firmware Node
 
 This node defines a firmware binary that is embedded in the device tree, for
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/firmware.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/firmware.txt
index 249db3a15d15..249db3a15d15 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/firmware.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/firmware.txt
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/par_io.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/par_io.txt
index 60984260207b..60984260207b 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/par_io.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/par_io.txt
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/pincfg.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/pincfg.txt
index ec6ee2e864a2..ec6ee2e864a2 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/pincfg.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/pincfg.txt
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/ucc.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt
index e47734bee3f0..e47734bee3f0 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/ucc.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/usb.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt
index 9ccd5f30405b..9ccd5f30405b 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/usb.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/serial.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/serial.txt
index 2ea76d9d137c..2ea76d9d137c 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/serial.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/serial.txt
diff --git a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/uqe_serial.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/uqe_serial.txt
new file mode 100644
index 000000000000..8823c86c8085
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/uqe_serial.txt
@@ -0,0 +1,17 @@
+* Serial
+
+Required Properties:
+compatible : must be "fsl,<chip>-ucc-uart". For t1040, must be
+"fsl,t1040-ucc-uart".
+port-number : port number of UCC-UART
+tx/rx-clock-name : should be "brg1"-"brg16" for internal clock source,
+		   should be "clk1"-"clk28" for external clock source.
+
+Example:
+
+	ucc_serial: ucc@2200 {
+		compatible = "fsl,t1040-ucc-uart";
+		port-number = <0>;
+		rx-clock-name = "brg2";
+		tx-clock-name = "brg2";
+	};
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt
index 5cc82b8353d8..af9ca37221ce 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,smp2p.txt
@@ -68,7 +68,7 @@ important.
 	Value type: <u32>
 	Definition: must be 2 - denoting the bit in the entry and IRQ flags
 
-- #qcom,state-cells:
+- #qcom,smem-state-cells:
 	Usage: required for outgoing entries
 	Value type: <u32>
 	Definition: must be 1 - denoting the bit in the entry
@@ -92,7 +92,7 @@ wcnss-smp2p {
 	wcnss_smp2p_out: master-kernel {
 		qcom,entry-name = "master-kernel";
 
-		#qcom,state-cells = <1>;
+		#qcom,smem-state-cells = <1>;
 	};
 
 	wcnss_smp2p_in: slave-kernel {
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,smsm.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,smsm.txt
index a6634c70850d..2993b5a97dd6 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,smsm.txt
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,smsm.txt
@@ -51,7 +51,7 @@ important.
 	Definition: specifies the offset, in words, of the first bit for this
 		    entry
 
-- #qcom,state-cells:
+- #qcom,smem-state-cells:
 	Usage: required for local entry
 	Value type: <u32>
 	Definition: must be 1 - denotes bit number
@@ -91,7 +91,7 @@ smsm {
 	apps_smsm: apps@0 {
 		reg = <0>;
 
-		#qcom,state-cells = <1>;
+		#qcom,smem-state-cells = <1>;
 	};
 
 	wcnss_smsm: wcnss@7 {
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.txt
new file mode 100644
index 000000000000..4ea39e9186a7
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,wcnss.txt
@@ -0,0 +1,116 @@
+Qualcomm WCNSS Binding
+
+This binding describes the Qualcomm WCNSS hardware. It consists of control
+block and a BT, WiFi and FM radio block, all using SMD as command channels.
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be: "qcom,wcnss",
+
+- qcom,smd-channel:
+	Usage: required
+	Value type: <string>
+	Definition: standard SMD property specifying the SMD channel used for
+		    communication with the WiFi firmware.
+		    Should be "WCNSS_CTRL".
+
+- qcom,mmio:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: reference to a node specifying the wcnss "ccu" and "dxe"
+		    register blocks. The node must be compatible with one of
+		    the following:
+		    "qcom,riva",
+		    "qcom,pronto"
+
+= SUBNODES
+The subnodes of the wcnss node are optional and describe the individual blocks in
+the WCNSS.
+
+== Bluetooth
+The following properties are defined to the bluetooth node:
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be:
+		    "qcom,wcnss-bt"
+
+== WiFi
+The following properties are defined to the WiFi node:
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+		    "qcom,wcnss-wlan",
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: should specify the "rx" and "tx" interrupts
+
+- interrupt-names:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must contain "rx" and "tx"
+
+- qcom,smem-state:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: should reference the tx-enable and tx-rings-empty SMEM states
+
+- qcom,smem-state-names:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must contain "tx-enable" and "tx-rings-empty"
+
+= EXAMPLE
+The following example represents a SMD node, with one edge representing the
+"pronto" subsystem, with the wcnss device and its wcn3680 BT and WiFi blocks
+described; as found on the 8974 platform.
+
+smd {
+	compatible = "qcom,smd";
+
+	pronto-edge {
+		interrupts = <0 142 1>;
+
+		qcom,ipc = <&apcs 8 17>;
+		qcom,smd-edge = <6>;
+
+		wcnss {
+			compatible = "qcom,wcnss";
+			qcom,smd-channels = "WCNSS_CTRL";
+
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			qcom,mmio = <&pronto>;
+
+			bt {
+				compatible = "qcom,wcnss-bt";
+			};
+
+			wlan {
+				compatible = "qcom,wcnss-wlan";
+
+				interrupts = <0 145 0>, <0 146 0>;
+				interrupt-names = "tx", "rx";
+
+				qcom,smem-state = <&apps_smsm 10>, <&apps_smsm 9>;
+				qcom,smem-state-names = "tx-enable", "tx-rings-empty";
+			};
+		};
+	};
+};
+
+soc {
+	pronto: pronto {
+		compatible = "qcom,pronto";
+
+		reg = <0xfb204000 0x2000>, <0xfb202000 0x1000>, <0xfb21b000 0x3000>;
+		reg-names = "ccu", "dxe", "pmu";
+	};
+};
diff --git a/Documentation/devicetree/bindings/sound/adi,adau17x1.txt b/Documentation/devicetree/bindings/sound/adi,adau17x1.txt
index 8dbce0e18dda..1447dec28125 100644
--- a/Documentation/devicetree/bindings/sound/adi,adau17x1.txt
+++ b/Documentation/devicetree/bindings/sound/adi,adau17x1.txt
@@ -13,6 +13,11 @@ Required properties:
  - reg:			The i2c address. Value depends on the state of ADDR0
 			and ADDR1, as wired in hardware.
 
+Optional properties:
+ - clock-names:		If provided must be "mclk".
+ - clocks:		phandle + clock-specifiers for the clock that provides
+			the audio master clock for the device.
+
 Examples:
 #include <dt-bindings/sound/adau17x1.h>
 
@@ -20,5 +25,8 @@ Examples:
 		adau1361@38 {
 			compatible = "adi,adau1761";
 			reg = <0x38>;
+
+			clock-names = "mclk";
+			clocks = <&audio_clock>;
 		};
 	};
diff --git a/Documentation/devicetree/bindings/sound/adi,adau7002.txt b/Documentation/devicetree/bindings/sound/adi,adau7002.txt
new file mode 100644
index 000000000000..f144ee1abf85
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/adi,adau7002.txt
@@ -0,0 +1,19 @@
+Analog Devices ADAU7002 Stereo PDM-to-I2S/TDM Converter
+
+Required properties:
+
+ - compatible: Must be "adi,adau7002"
+
+Optional properties:
+
+ - IOVDD-supply: Phandle and specifier for the power supply providing the IOVDD
+	supply as covered in Documentation/devicetree/bindings/regulator/regulator.txt
+
+	If this property is not present it is assumed that the supply pin is
+	hardwired to always on.
+
+Example:
+	adau7002: pdm-to-i2s {
+		compatible = "adi,adau7002";
+		IOVDD-supply = <&supply>;
+	};
diff --git a/Documentation/devicetree/bindings/sound/brcm,cygnus-audio.txt b/Documentation/devicetree/bindings/sound/brcm,cygnus-audio.txt
new file mode 100644
index 000000000000..b139e66d2a11
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/brcm,cygnus-audio.txt
@@ -0,0 +1,67 @@
+BROADCOM Cygnus Audio I2S/TDM/SPDIF controller
+
+Required properties:
+	- compatible : "brcm,cygnus-audio"
+	- #address-cells: 32bit valued, 1 cell.
+	- #size-cells:  32bit valued, 0 cell.
+	- reg : Should contain audio registers location and length
+	- reg-names: names of the registers listed in "reg" property
+		Valid names are "aud" and "i2s_in". "aud" contains a
+		set of DMA, I2S_OUT and SPDIF registers. "i2s_in" contains
+		a set of I2S_IN registers.
+	- clocks: PLL and leaf clocks used by audio ports
+	- assigned-clocks: PLL and leaf clocks
+	- assigned-clock-parents: parent clocks of the assigned clocks
+		(usually the PLL)
+	- assigned-clock-rates: List of clock frequencies of the
+		assigned clocks
+	- clock-names: names of 3 leaf clocks used by audio ports
+		Valid names are "ch0_audio", "ch1_audio", "ch2_audio"
+	- interrupts: audio DMA interrupt number
+
+SSP Subnode properties:
+- reg: The index of ssp port interface to use
+	Valid value are 0, 1, 2, or 3 (for spdif)
+
+Example:
+	cygnus_audio: audio@180ae000 {
+		compatible = "brcm,cygnus-audio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x180ae000 0xafd>, <0x180aec00 0x1f8>;
+		reg-names = "aud", "i2s_in";
+		clocks = <&audiopll BCM_CYGNUS_AUDIOPLL_CH0>,
+				<&audiopll BCM_CYGNUS_AUDIOPLL_CH1>,
+				<&audiopll BCM_CYGNUS_AUDIOPLL_CH2>;
+		assigned-clocks = <&audiopll BCM_CYGNUS_AUDIOPLL>,
+							<&audiopll BCM_CYGNUS_AUDIOPLL_CH0>,
+							<&audiopll BCM_CYGNUS_AUDIOPLL_CH1>,
+							<&audiopll BCM_CYGNUS_AUDIOPLL_CH2>;
+		assigned-clock-parents = <&audiopll BCM_CYGNUS_AUDIOPLL>;
+		assigned-clock-rates = <1769470191>,
+								<0>,
+								<0>,
+								<0>;
+		clock-names = "ch0_audio", "ch1_audio", "ch2_audio";
+		interrupts = <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
+
+		ssp0: ssp_port@0 {
+			reg = <0>;
+			status = "okay";
+		};
+
+		ssp1: ssp_port@1 {
+			reg = <1>;
+			status = "disabled";
+		};
+
+		ssp2: ssp_port@2 {
+			reg = <2>;
+			status = "disabled";
+		};
+
+		spdif: spdif_port@3 {
+			reg = <3>;
+			status = "disabled";
+		};
+	};
diff --git a/Documentation/devicetree/bindings/sound/bt-sco.txt b/Documentation/devicetree/bindings/sound/bt-sco.txt
index 29b8e5d40203..641edf75e184 100644
--- a/Documentation/devicetree/bindings/sound/bt-sco.txt
+++ b/Documentation/devicetree/bindings/sound/bt-sco.txt
@@ -4,7 +4,7 @@ This device support generic Bluetooth SCO link.
 
 Required properties:
 
-  - compatible : "delta,dfbmcs320"
+  - compatible : "delta,dfbmcs320" or "linux,bt-sco"
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/sound/cs35l33.txt b/Documentation/devicetree/bindings/sound/cs35l33.txt
new file mode 100644
index 000000000000..acfb47525b49
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/cs35l33.txt
@@ -0,0 +1,126 @@
+CS35L33 Speaker Amplifier
+
+Required properties:
+
+  - compatible : "cirrus,cs35l33"
+
+  - reg : the I2C address of the device for I2C
+
+  - VA-supply, VP-supply : power supplies for the device,
+    as covered in
+    Documentation/devicetree/bindings/regulator/regulator.txt.
+
+Optional properties:
+
+  - reset-gpios : gpio used to reset the amplifier
+
+  - interrupt-parent : Specifies the phandle of the interrupt controller to
+    which the IRQs from CS35L33 are delivered to.
+ -  interrupts : IRQ line info CS35L33.
+    (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
+    for further information relating to interrupt properties)
+
+  - cirrus,boost-ctl : Booster voltage use to supply the amp. If the value is
+    0, then VBST = VP. If greater than 0, the boost voltage will be 3300mV with
+    a value of 1 and will increase at a step size of 100mV until a maximum of
+    8000mV.
+
+  - cirrus,ramp-rate : On power up, it affects the time from when the power
+    up sequence begins to the time the audio reaches a full-scale output.
+    On power down, it affects the time from when the power-down sequence
+    begins to when the amplifier disables the PWM outputs. If this property
+    is not set then soft ramping will be disabled and ramp time would be
+    20ms. If this property is set to 0,1,2,3 then ramp times would be 40ms,
+    60ms,100ms,175ms respectively for 48KHz sample rate.
+
+  - cirrus,boost-ipk : The maximum current allowed for the boost converter.
+    The range starts at 1850000uA and goes to a maximum of 3600000uA
+    with a step size of 15625uA. The default is 2500000uA.
+
+  - cirrus,imon-adc-scale : Configures the scaling of data bits from the IMON
+    ADC data word. This property can be set as a value of 0 for bits 15 down
+    to 0, 6 for 21 down to 6, 7, for 22 down to 7, 8 for 23 down to 8.
+
+
+Optional H/G Algorithm sub-node:
+
+The cs35l33 node can have a single "cirrus,hg-algo" sub-node that will enable
+the internal H/G Algorithm.
+
+  - cirrus,hg-algo : Sub-node for internal Class H/G algorithm that
+    controls the amplifier supplies.
+
+Optional properties for the "cirrus,hg-algo" sub-node:
+
+  - cirrus,mem-depth : Memory depth for the Class H/G algorithm measured in
+    LRCLK cycles. If this property is set to 0, 1, 2, or 3 then the memory
+    depths will be 1, 4, 8, 16 LRCLK cycles.  The default is 16 LRCLK cycles.
+
+    cirrus,release-rate : The number of consecutive LRCLK periods before
+    allowing release condition tracking updates. The number of LRCLK periods
+    start at 3 to a maximum of 255.
+
+  - cirrus,ldo-thld : Configures the signal threshold at which the PWM output
+    stage enters LDO operation. Starts as a default value of 50mV for a value
+    of 1 and increases with a step size of 50mV to a maximum of 750mV (value of
+    0xF).
+
+  - cirrus,ldo-path-disable : This is a boolean property. If present, the H/G
+    algorithm uses the max detection path.  If not present, the LDO
+    detection path is used.
+
+  - cirrus,ldo-entry-delay : The LDO entry delay in milliseconds before the H/G
+    algorithm switches to the LDO voltage.  This property can be set to values
+    from 0 to 7 for delays of 5ms, 10ms, 50ms, 100ms, 200ms, 500ms, 1000ms.
+    The default is 100ms.
+
+  - cirrus,vp-hg-auto : This is a boolean property.  When set, class H/G VPhg
+    automatic updating is enabled.
+
+  - cirrus,vp-hg :  Class H/G algorithm VPhg.  Controls the H/G algorithm's
+    reference to the VP voltage for when to start generating a boosted VBST.
+    The reference voltage starts at 3000mV with a value of 0x3 and is increased
+    by 100mV per step to a maximum of 5500mV.
+
+  - cirrus,vp-hg-rate : The rate (number of LRCLK periods) at which the VPhg is
+    allowed to increase to a higher voltage when using VPhg automatic
+    tracking. This property can be set to values from 0 to 3 with rates of 128
+    periods, 2048 periods, 32768 periods, and 524288 periods.
+    The default is 32768 periods.
+
+  - cirrus,vp-hg-va : VA calculation reference for automatic VPhg tracking
+    using VPMON. This property can be set to values from 0 to 6 starting at
+    1800mV with a step size of 50mV up to a maximum value of 1750mV.
+    Default is 1800mV.
+
+Example:
+
+cs35l33: cs35l33@40 {
+	compatible = "cirrus,cs35l33";
+	reg = <0x40>;
+
+	VA-supply = <&ldo5_reg>;
+	VP-supply = <&ldo5_reg>;
+
+	interrupt-parent = <&gpio8>;
+	interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
+
+	reset-gpios = <&cs47l91 34 0>;
+
+	cirrus,ramp-rate = <0x0>;
+	cirrus,boost-ctl = <0x30>;  /* VBST = 8000mV */
+	cirrus,boost-ipk = <0xE0>; /* 3600mA */
+	cirrus,imon-adc-scale = <0> /* Bits 15 down to 0 */
+
+	cirrus,hg-algo {
+		cirrus,mem-depth = <0x3>;
+		cirrus,release-rate = <0x3>;
+		cirrus,ldo-thld = <0x1>;
+		cirrus,ldo-path-disable = <0x0>;
+		cirrus,ldo-entry-delay=<0x4>;
+		cirrus,vp-hg-auto;
+		cirrus,vp-hg=<0xF>;
+		cirrus,vp-hg-rate=<0x2>;
+		cirrus,vp-hg-va=<0x0>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/sound/cs53l30.txt b/Documentation/devicetree/bindings/sound/cs53l30.txt
new file mode 100644
index 000000000000..4dbfb8274cd9
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/cs53l30.txt
@@ -0,0 +1,44 @@
+CS53L30 audio CODEC
+
+Required properties:
+
+  - compatible : "cirrus,cs53l30"
+
+  - reg : the I2C address of the device
+
+  - VA-supply, VP-supply : power supplies for the device,
+    as covered in Documentation/devicetree/bindings/regulator/regulator.txt.
+
+Optional properties:
+
+  - reset-gpios : a GPIO spec for the reset pin.
+
+  - mute-gpios : a GPIO spec for the MUTE pin. The active state can be either
+		 GPIO_ACTIVE_HIGH or GPIO_ACTIVE_LOW, which would be handled
+		 by the driver automatically.
+
+  - cirrus,micbias-lvl : Set the output voltage level on the MICBIAS Pin.
+			 0 = Hi-Z
+			 1 = 1.80 V
+			 2 = 2.75 V
+
+  - cirrus,use-sdout2 : This is a boolean property. If present, it indicates
+			the hardware design connects both SDOUT1 and SDOUT2
+			pins to output data. Otherwise, it indicates that
+			only SDOUT1 is connected for data output.
+			* CS53l30 supports 4-channel data output in the same
+			* frame using two different ways:
+			* 1) Normal I2S mode on two data pins -- each SDOUT
+			*    carries 2-channel data in the same time.
+			* 2) TDM mode on one signle data pin -- SDOUT1 carries
+			*    4-channel data per frame.
+
+Example:
+
+codec: cs53l30@48 {
+	compatible = "cirrus,cs53l30";
+	reg = <0x48>;
+	reset-gpios = <&gpio 54 0>;
+	VA-supply = <&cs53l30_va>;
+	VP-supply = <&cs53l30_vp>;
+};
diff --git a/Documentation/devicetree/bindings/sound/designware-i2s.txt b/Documentation/devicetree/bindings/sound/designware-i2s.txt
index 7bb54247f8e8..6a536d570e29 100644
--- a/Documentation/devicetree/bindings/sound/designware-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/designware-i2s.txt
@@ -12,6 +12,10 @@ Required properties:
    one for receive.
  - dma-names : "tx" for the transmit channel, "rx" for the receive channel.
 
+Optional properties:
+ - interrupts: The interrupt line number for the I2S controller. Add this
+   parameter if the I2S controller that you are using does not support DMA.
+
 For more details on the 'dma', 'dma-names', 'clock' and 'clock-names'
 properties please check:
 	* resource-names.txt
diff --git a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
index ceaef5126989..f749e2744824 100644
--- a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
+++ b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
@@ -58,7 +58,7 @@ Required properties:
 			   * DMIC (stands for Digital Microphone Jack)
 
 			  Note: The "Mic Jack" and "AMIC" are redundant while
-			        coexsiting in order to support the old bindings
+			        coexisting in order to support the old bindings
 				of wm8962 and sgtl5000.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/sound/max98504.txt b/Documentation/devicetree/bindings/sound/max98504.txt
new file mode 100644
index 000000000000..583ed5fdfb28
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/max98504.txt
@@ -0,0 +1,44 @@
+Maxim MAX98504 class D mono speaker amplifier
+
+This device supports I2C control interface and an IRQ output signal. It features
+a PCM and PDM digital audio interface (DAI) and a differential analog input.
+
+Required properties:
+
+ - compatible : "maxim,max98504"
+ - reg : should contain the I2C slave device address
+ - DVDD-supply, DIOVDD-supply, PVDD-supply: power supplies for the device,
+   as covered in ../regulator/regulator.txt
+ - interrupts : should specify the interrupt line the device is connected to,
+   as described in ../interrupt-controller/interrupts.txt
+
+Optional properties:
+
+ - maxim,brownout-threshold - the PVDD brownout threshold, the value must be
+   from 0, 1...21 range, corresponding to 2.6V, 2.65V...3.65V voltage range
+ - maxim,brownout-attenuation - the brownout attenuation to the speaker gain
+   applied during the "attack hold" and "timed hold" phase, the value must be
+   from 0...6 (dB) range
+ - maxim,brownout-attack-hold-ms - the brownout attack hold phase time in ms,
+   0...255 (VBATBROWN_ATTK_HOLD, register 0x0018)
+ - maxim,brownout-timed-hold-ms - the brownout timed hold phase time in ms,
+   0...255 (VBATBROWN_TIME_HOLD, register 0x0019)
+ - maxim,brownout-release-rate-ms - the brownout release phase step time in ms,
+   0...255 (VBATBROWN_RELEASE, register 0x001A)
+
+The default value when the above properties are not specified is 0,
+the maxim,brownout-threshold property must be specified to actually enable
+the PVDD brownout protection.
+
+Example:
+
+ max98504@31 {
+	compatible = "maxim,max98504";
+	reg = <0x31>;
+	interrupt-parent = <&gpio_bank_0>;
+	interrupts = <2 0>;
+
+	DVDD-supply = <&regulator>;
+	DIOVDD-supply = <&regulator>;
+	PVDD-supply = <&regulator>;
+};
diff --git a/Documentation/devicetree/bindings/sound/max9860.txt b/Documentation/devicetree/bindings/sound/max9860.txt
new file mode 100644
index 000000000000..e0d4e95e31b3
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/max9860.txt
@@ -0,0 +1,28 @@
+MAX9860 Mono Audio Voice Codec
+
+Required properties:
+
+  - compatible : "maxim,max9860"
+
+  - reg : the I2C address of the device
+
+  - AVDD-supply, DVDD-supply and DVDDIO-supply : power supplies for
+    the device, as covered in bindings/regulator/regulator.txt
+
+  - clock-names : Required element: "mclk".
+
+  - clocks : A clock specifier for the clock connected as MCLK.
+
+Examples:
+
+	max9860: max9860@10 {
+		compatible = "maxim,max9860";
+		reg = <0x10>;
+
+		AVDD-supply = <&reg_1v8>;
+		DVDD-supply = <&reg_1v8>;
+		DVDDIO-supply = <&reg_3v0>;
+
+		clock-names = "mclk";
+		clocks = <&pck2>;
+	};
diff --git a/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt b/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt
new file mode 100644
index 000000000000..3e623a724e55
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/mt2701-afe-pcm.txt
@@ -0,0 +1,150 @@
+Mediatek AFE PCM controller for mt2701
+
+Required properties:
+- compatible = "mediatek,mt2701-audio";
+- reg: register location and size
+- interrupts: Should contain AFE interrupt
+- clock-names: should have these clock names:
+		"infra_sys_audio_clk",
+		"top_audio_mux1_sel",
+		"top_audio_mux2_sel",
+		"top_audio_mux1_div",
+		"top_audio_mux2_div",
+		"top_audio_48k_timing",
+		"top_audio_44k_timing",
+		"top_audpll_mux_sel",
+		"top_apll_sel",
+		"top_aud1_pll_98M",
+		"top_aud2_pll_90M",
+		"top_hadds2_pll_98M",
+		"top_hadds2_pll_294M",
+		"top_audpll",
+		"top_audpll_d4",
+		"top_audpll_d8",
+		"top_audpll_d16",
+		"top_audpll_d24",
+		"top_audintbus_sel",
+		"clk_26m",
+		"top_syspll1_d4",
+		"top_aud_k1_src_sel",
+		"top_aud_k2_src_sel",
+		"top_aud_k3_src_sel",
+		"top_aud_k4_src_sel",
+		"top_aud_k5_src_sel",
+		"top_aud_k6_src_sel",
+		"top_aud_k1_src_div",
+		"top_aud_k2_src_div",
+		"top_aud_k3_src_div",
+		"top_aud_k4_src_div",
+		"top_aud_k5_src_div",
+		"top_aud_k6_src_div",
+		"top_aud_i2s1_mclk",
+		"top_aud_i2s2_mclk",
+		"top_aud_i2s3_mclk",
+		"top_aud_i2s4_mclk",
+		"top_aud_i2s5_mclk",
+		"top_aud_i2s6_mclk",
+		"top_asm_m_sel",
+		"top_asm_h_sel",
+		"top_univpll2_d4",
+		"top_univpll2_d2",
+		"top_syspll_d5";
+
+Example:
+
+	afe: mt2701-afe-pcm@11220000 {
+		compatible = "mediatek,mt2701-audio";
+		reg = <0 0x11220000 0 0x2000>,
+		      <0 0x112A0000 0 0x20000>;
+		interrupts = <GIC_SPI 104 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_SPI 132 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&infracfg CLK_INFRA_AUDIO>,
+			 <&topckgen CLK_TOP_AUD_MUX1_SEL>,
+			 <&topckgen CLK_TOP_AUD_MUX2_SEL>,
+			 <&topckgen CLK_TOP_AUD_MUX1_DIV>,
+			 <&topckgen CLK_TOP_AUD_MUX2_DIV>,
+			 <&topckgen CLK_TOP_AUD_48K_TIMING>,
+			 <&topckgen CLK_TOP_AUD_44K_TIMING>,
+			 <&topckgen CLK_TOP_AUDPLL_MUX_SEL>,
+			 <&topckgen CLK_TOP_APLL_SEL>,
+			 <&topckgen CLK_TOP_AUD1PLL_98M>,
+			 <&topckgen CLK_TOP_AUD2PLL_90M>,
+			 <&topckgen CLK_TOP_HADDS2PLL_98M>,
+			 <&topckgen CLK_TOP_HADDS2PLL_294M>,
+			 <&topckgen CLK_TOP_AUDPLL>,
+			 <&topckgen CLK_TOP_AUDPLL_D4>,
+			 <&topckgen CLK_TOP_AUDPLL_D8>,
+			 <&topckgen CLK_TOP_AUDPLL_D16>,
+			 <&topckgen CLK_TOP_AUDPLL_D24>,
+			 <&topckgen CLK_TOP_AUDINTBUS_SEL>,
+			 <&clk26m>,
+			 <&topckgen CLK_TOP_SYSPLL1_D4>,
+			 <&topckgen CLK_TOP_AUD_K1_SRC_SEL>,
+			 <&topckgen CLK_TOP_AUD_K2_SRC_SEL>,
+			 <&topckgen CLK_TOP_AUD_K3_SRC_SEL>,
+			 <&topckgen CLK_TOP_AUD_K4_SRC_SEL>,
+			 <&topckgen CLK_TOP_AUD_K5_SRC_SEL>,
+			 <&topckgen CLK_TOP_AUD_K6_SRC_SEL>,
+			 <&topckgen CLK_TOP_AUD_K1_SRC_DIV>,
+			 <&topckgen CLK_TOP_AUD_K2_SRC_DIV>,
+			 <&topckgen CLK_TOP_AUD_K3_SRC_DIV>,
+			 <&topckgen CLK_TOP_AUD_K4_SRC_DIV>,
+			 <&topckgen CLK_TOP_AUD_K5_SRC_DIV>,
+			 <&topckgen CLK_TOP_AUD_K6_SRC_DIV>,
+			 <&topckgen CLK_TOP_AUD_I2S1_MCLK>,
+			 <&topckgen CLK_TOP_AUD_I2S2_MCLK>,
+			 <&topckgen CLK_TOP_AUD_I2S3_MCLK>,
+			 <&topckgen CLK_TOP_AUD_I2S4_MCLK>,
+			 <&topckgen CLK_TOP_AUD_I2S5_MCLK>,
+			 <&topckgen CLK_TOP_AUD_I2S6_MCLK>,
+			 <&topckgen CLK_TOP_ASM_M_SEL>,
+			 <&topckgen CLK_TOP_ASM_H_SEL>,
+			 <&topckgen CLK_TOP_UNIVPLL2_D4>,
+			 <&topckgen CLK_TOP_UNIVPLL2_D2>,
+			 <&topckgen CLK_TOP_SYSPLL_D5>;
+
+		clock-names = "infra_sys_audio_clk",
+			      "top_audio_mux1_sel",
+			      "top_audio_mux2_sel",
+			      "top_audio_mux1_div",
+			      "top_audio_mux2_div",
+			      "top_audio_48k_timing",
+			      "top_audio_44k_timing",
+			      "top_audpll_mux_sel",
+			      "top_apll_sel",
+			      "top_aud1_pll_98M",
+			      "top_aud2_pll_90M",
+			      "top_hadds2_pll_98M",
+			      "top_hadds2_pll_294M",
+			      "top_audpll",
+			      "top_audpll_d4",
+			      "top_audpll_d8",
+			      "top_audpll_d16",
+			      "top_audpll_d24",
+			      "top_audintbus_sel",
+			      "clk_26m",
+			      "top_syspll1_d4",
+			      "top_aud_k1_src_sel",
+			      "top_aud_k2_src_sel",
+			      "top_aud_k3_src_sel",
+			      "top_aud_k4_src_sel",
+			      "top_aud_k5_src_sel",
+			      "top_aud_k6_src_sel",
+			      "top_aud_k1_src_div",
+			      "top_aud_k2_src_div",
+			      "top_aud_k3_src_div",
+			      "top_aud_k4_src_div",
+			      "top_aud_k5_src_div",
+			      "top_aud_k6_src_div",
+			      "top_aud_i2s1_mclk",
+			      "top_aud_i2s2_mclk",
+			      "top_aud_i2s3_mclk",
+			      "top_aud_i2s4_mclk",
+			      "top_aud_i2s5_mclk",
+			      "top_aud_i2s6_mclk",
+			      "top_asm_m_sel",
+			      "top_asm_h_sel",
+			      "top_univpll2_d4",
+			      "top_univpll2_d2",
+			      "top_syspll_d5";
+	};
diff --git a/Documentation/devicetree/bindings/sound/mt2701-cs42448.txt b/Documentation/devicetree/bindings/sound/mt2701-cs42448.txt
new file mode 100644
index 000000000000..05574446ceb6
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/mt2701-cs42448.txt
@@ -0,0 +1,43 @@
+MT2701 with CS42448 CODEC
+
+Required properties:
+- compatible: "mediatek,mt2701-cs42448-machine"
+- mediatek,platform: the phandle of MT2701 ASoC platform
+- audio-routing: a list of the connections between audio
+- mediatek,audio-codec: the phandles of cs42448 codec
+- mediatek,audio-codec-bt-mrg the phandles of bt-sco dummy codec
+- pinctrl-names: Should contain only one value - "default"
+- pinctrl-0: Should specify pin control groups used for this controller.
+- i2s1-in-sel-gpio1, i2s1-in-sel-gpio2: Should specify two gpio pins to
+					control I2S1-in mux.
+
+Example:
+
+	sound:sound {
+		compatible = "mediatek,mt2701-cs42448-machine";
+		mediatek,platform = <&afe>;
+		/* CS42448 Machine name */
+		audio-routing =
+			"Line Out Jack", "AOUT1L",
+			"Line Out Jack", "AOUT1R",
+			"Line Out Jack", "AOUT2L",
+			"Line Out Jack", "AOUT2R",
+			"Line Out Jack", "AOUT3L",
+			"Line Out Jack", "AOUT3R",
+			"Line Out Jack", "AOUT4L",
+			"Line Out Jack", "AOUT4R",
+			"AIN1L", "AMIC",
+			"AIN1R", "AMIC",
+			"AIN2L", "Tuner In",
+			"AIN2R", "Tuner In",
+			"AIN3L", "Satellite Tuner In",
+			"AIN3R", "Satellite Tuner In",
+			"AIN3L", "AUX In",
+			"AIN3R", "AUX In";
+		mediatek,audio-codec = <&cs42448>;
+		mediatek,audio-codec-bt-mrg = <&bt_sco_codec>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&aud_pins_default>;
+		i2s1-in-sel-gpio1 = <&pio 53 0>;
+		i2s1-in-sel-gpio2 = <&pio 54 0>;
+	};
diff --git a/Documentation/devicetree/bindings/sound/mt8173-rt5650.txt b/Documentation/devicetree/bindings/sound/mt8173-rt5650.txt
index 5bfa6b60530b..29dce2ac8773 100644
--- a/Documentation/devicetree/bindings/sound/mt8173-rt5650.txt
+++ b/Documentation/devicetree/bindings/sound/mt8173-rt5650.txt
@@ -1,8 +1,9 @@
-MT8173 with RT5650 CODECS
+MT8173 with RT5650 CODECS and HDMI via I2S
 
 Required properties:
 - compatible : "mediatek,mt8173-rt5650"
 - mediatek,audio-codec: the phandles of rt5650 codecs
+                        and of the hdmi encoder node
 - mediatek,platform: the phandle of MT8173 ASoC platform
 
 Optional subnodes:
@@ -12,12 +13,17 @@ Required codec-capture subnode properties:
   <&rt5650 0> : Default setting. Connect rt5650 I2S1 for capture. (dai_name = rt5645-aif1)
   <&rt5650 1> : Connect rt5650 I2S2 for capture. (dai_name = rt5645-aif2)
 
+- mediatek,mclk: the MCLK source
+  0 : external oscillator, MCLK = 12.288M
+  1 : internal source from mt8173, MCLK = sampling rate*256
+
 Example:
 
 	sound {
 		compatible = "mediatek,mt8173-rt5650";
-		mediatek,audio-codec = <&rt5650>;
+		mediatek,audio-codec = <&rt5650 &hdmi0>;
 		mediatek,platform = <&afe>;
+		mediatek,mclk = <0>;
 		codec-capture {
 			sound-dai = <&rt5650 1>;
 		};
diff --git a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
index 0741dff048dd..6f6c2f8e908d 100644
--- a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
+++ b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
@@ -8,6 +8,8 @@ Required properties:
 - interrupts: Interrupt number for McPDM
 - interrupt-parent: The parent interrupt controller
 - ti,hwmods: Name of the hwmod associated to the McPDM
+- clocks:  phandle for the pdmclk provider, likely <&twl6040>
+- clock-names: Must be "pdmclk"
 
 Example:
 
@@ -19,3 +21,11 @@ mcpdm: mcpdm@40132000 {
 	interrupt-parent = <&gic>;
 	ti,hwmods = "mcpdm";
 };
+
+In board DTS file the pdmclk needs to be added:
+
+&mcpdm {
+	clocks = <&twl6040>;
+	clock-names = "pdmclk";
+	status = "okay";
+};
diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
index c7b29df4a963..15a7316e4c91 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
+++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
@@ -373,6 +373,8 @@ Optional properties:
 - #clock-cells			: it must be 0 if your system has audio_clkout
 				  it must be 1 if your system has audio_clkout0/1/2/3
 - clock-frequency		: for all audio_clkout0/1/2/3
+- clkout-lr-asynchronous	: boolean property. it indicates that audio_clkoutn
+				  is asynchronizes with lr-clock.
 
 SSI subnode properties:
 - interrupts			: Should contain SSI interrupt for PIO transfer
diff --git a/Documentation/devicetree/bindings/sound/rockchip-i2s.txt b/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
index 6e86d8aa29b4..4ea29aa9af59 100644
--- a/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
@@ -23,6 +23,11 @@ Required properties:
 - rockchip,playback-channels: max playback channels, if not set, 8 channels default.
 - rockchip,capture-channels: max capture channels, if not set, 2 channels default.
 
+Required properties for controller which support multi channels
+playback/capture:
+
+- rockchip,grf: the phandle of the syscon node for GRF register.
+
 Example for rk3288 I2S controller:
 
 i2s@ff890000 {
diff --git a/Documentation/devicetree/bindings/sound/rt5514.txt b/Documentation/devicetree/bindings/sound/rt5514.txt
index e24436fc5ea9..9cabfc18cb57 100644
--- a/Documentation/devicetree/bindings/sound/rt5514.txt
+++ b/Documentation/devicetree/bindings/sound/rt5514.txt
@@ -8,6 +8,11 @@ Required properties:
 
 - reg : The I2C address of the device.
 
+Optional properties:
+
+- clocks: The phandle of the master clock to the CODEC
+- clock-names: Should be "mclk"
+
 Pins on the device (for linking into audio routes) for RT5514:
 
   * DMIC1L
diff --git a/Documentation/devicetree/bindings/sound/samsung,odroidx2-max98090.txt b/Documentation/devicetree/bindings/sound/samsung,odroidx2-max98090.txt
deleted file mode 100644
index 9148f72319e1..000000000000
--- a/Documentation/devicetree/bindings/sound/samsung,odroidx2-max98090.txt
+++ /dev/null
@@ -1,35 +0,0 @@
-Samsung Exynos Odroid X2/U3 audio complex with MAX98090 codec
-
-Required properties:
- - compatible : "samsung,odroidx2-audio" - for Odroid X2 board,
-		"samsung,odroidu3-audio" - for Odroid U3 board
- - samsung,model : the user-visible name of this sound complex
- - samsung,i2s-controller : the phandle of the I2S controller
- - samsung,audio-codec : the phandle of the MAX98090 audio codec
- - samsung,audio-routing : a list of the connections between audio
-   components;  each entry is a pair of strings, the first being the
-   connection's sink, the second being the connection's source;
-   valid names for sources and sinks are the MAX98090's pins (as
-   documented in its binding), and the jacks on the board
-   For Odroid X2:
-     * Headphone Jack
-     * Mic Jack
-     * DMIC
-
-   For Odroid U3:
-     * Headphone Jack
-     * Speakers
-
-Example:
-
-sound {
-	compatible = "samsung,odroidu3-audio";
-	samsung,i2s-controller = <&i2s0>;
-	samsung,audio-codec = <&max98090>;
-	samsung,model = "Odroid-X2";
-	samsung,audio-routing =
-		"Headphone Jack", "HPL",
-		"Headphone Jack", "HPR",
-		"IN1", "Mic Jack",
-		"Mic Jack", "MICBIAS";
-};
diff --git a/Documentation/devicetree/bindings/sound/sgtl5000.txt b/Documentation/devicetree/bindings/sound/sgtl5000.txt
index 0e5e4eb3ef1b..5666da7b8605 100644
--- a/Documentation/devicetree/bindings/sound/sgtl5000.txt
+++ b/Documentation/devicetree/bindings/sound/sgtl5000.txt
@@ -7,6 +7,14 @@ Required properties:
 
 - clocks : the clock provider of SYS_MCLK
 
+- VDDA-supply : the regulator provider of VDDA
+
+- VDDIO-supply: the regulator provider of VDDIO
+
+Optional properties:
+
+- VDDD-supply : the regulator provider of VDDD
+
 - micbias-resistor-k-ohms : the bias resistor to be used in kOmhs
 	The resistor can take values of 2k, 4k or 8k.
 	If set to 0 it will be off.
@@ -15,17 +23,9 @@ Required properties:
 
 - micbias-voltage-m-volts : the bias voltage to be used in mVolts
 	The voltage can take values from 1.25V to 3V by 250mV steps
-	If this node is not mentionned or the value is unknown, then
+	If this node is not mentioned or the value is unknown, then
 	the value is set to 1.25V.
 
-- VDDA-supply : the regulator provider of VDDA
-
-- VDDIO-supply: the regulator provider of VDDIO
-
-Optional properties:
-
-- VDDD-supply : the regulator provider of VDDD
-
 Example:
 
 codec: sgtl5000@0a {
diff --git a/Documentation/devicetree/bindings/sound/simple-card.txt b/Documentation/devicetree/bindings/sound/simple-card.txt
index cf3979eb3578..59d862801e59 100644
--- a/Documentation/devicetree/bindings/sound/simple-card.txt
+++ b/Documentation/devicetree/bindings/sound/simple-card.txt
@@ -30,7 +30,7 @@ Optional subnodes:
 					  sub-nodes. This container may be
 					  omitted when the card has only one
 					  DAI link. See the examples and the
-					  section bellow.
+					  section below.
 
 Dai-link subnode properties and subnodes:
 
diff --git a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
index 4d9a83d9a017..16bcdfb6760e 100644
--- a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
+++ b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
@@ -33,11 +33,11 @@ Required properties:
 	"tx" for "st,sti-uni-player" compatibility
 	"rx" for "st,sti-uni-reader" compatibility
 
-  - version: IP version integrated in SOC.
+  - st,version: IP version integrated in SOC.
 
   - dai-name: DAI name that describes the IP.
 
-  - IP mode: IP working mode depending on associated codec.
+  - st,mode: IP working mode depending on associated codec.
 	"HDMI" connected to HDMI codec and support IEC HDMI formats (player only).
 	"SPDIF" connected to SPDIF codec and support SPDIF formats (player only).
 	"PCM" PCM standard mode for I2S or TDM bus.
@@ -47,7 +47,7 @@ Required properties ("st,sti-uni-player" compatibility only):
   - clocks: CPU_DAI IP clock source, listed in the same order than the
 	    CPU_DAI properties.
 
-  - uniperiph-id: internal SOC IP instance ID.
+  - st,uniperiph-id: internal SOC IP instance ID.
 
 Optional properties:
   - pinctrl-0: defined for CPU_DAI@1 and CPU_DAI@4 to describe I2S PIOs for
@@ -84,9 +84,9 @@ Example:
 		dmas = <&fdma0 4 0 1>;
 		dai-name = "Uni Player #2 (DAC)";
 		dma-names = "tx";
-		uniperiph-id = <2>;
-		version = <5>;
-		mode = "PCM";
+		st,uniperiph-id = <2>;
+		st,version = <5>;
+		st,mode = "PCM";
 	};
 
 	sti_uni_player3: sti-uni-player@3 {
@@ -100,9 +100,9 @@ Example:
 		dmas = <&fdma0 7 0 1>;
 		dma-names = "tx";
 		dai-name = "Uni Player #3 (SPDIF)";
-		uniperiph-id = <3>;
-		version = <5>;
-		mode = "SPDIF";
+		st,uniperiph-id = <3>;
+		st,version = <5>;
+		st,mode = "SPDIF";
 	};
 
 	sti_uni_reader1: sti-uni-reader@1 {
@@ -115,7 +115,7 @@ Example:
 		dmas = <&fdma0 6 0 1>;
 		dma-names = "rx";
 		dai-name = "Uni Reader #1 (HDMI RX)";
-		version = <3>;
+		st,version = <3>;
 		st,mode = "PCM";
 	};
 
diff --git a/Documentation/devicetree/bindings/sound/sun4i-i2s.txt b/Documentation/devicetree/bindings/sound/sun4i-i2s.txt
new file mode 100644
index 000000000000..7b526ec64991
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/sun4i-i2s.txt
@@ -0,0 +1,34 @@
+* Allwinner A10 I2S controller
+
+The I2S bus (Inter-IC sound bus) is a serial link for digital
+audio data transfer between devices in the system.
+
+Required properties:
+
+- compatible: should be one of the followings
+   - "allwinner,sun4i-a10-i2s"
+- reg: physical base address of the controller and length of memory mapped
+  region.
+- interrupts: should contain the I2S interrupt.
+- dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
+	Documentation/devicetree/bindings/dma/dma.txt
+- dma-names: should include "tx" and "rx".
+- clocks: a list of phandle + clock-specifer pairs, one for each entry in clock-names.
+- clock-names: should contain followings:
+   - "apb" : clock for the I2S bus interface
+   - "mod" : module clock for the I2S controller
+- #sound-dai-cells : Must be equal to 0
+
+Example:
+
+i2s0: i2s@01c22400 {
+	#sound-dai-cells = <0>;
+	compatible = "allwinner,sun4i-a10-i2s";
+	reg = <0x01c22400 0x400>;
+	interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&apb0_gates 3>, <&i2s0_clk>;
+	clock-names = "apb", "mod";
+	dmas = <&dma SUN4I_DMA_NORMAL 3>,
+	       <&dma SUN4I_DMA_NORMAL 3>;
+	dma-names = "rx", "tx";
+};
diff --git a/Documentation/devicetree/bindings/timer/allwinner,sun5i-a13-hstimer.txt b/Documentation/devicetree/bindings/timer/allwinner,sun5i-a13-hstimer.txt
index 27cfc7d7ccd7..8d6e4fd2468e 100644
--- a/Documentation/devicetree/bindings/timer/allwinner,sun5i-a13-hstimer.txt
+++ b/Documentation/devicetree/bindings/timer/allwinner,sun5i-a13-hstimer.txt
@@ -9,7 +9,7 @@ Required properties:
 		one)
 - clocks: phandle to the source clock (usually the AHB clock)
 
-Optionnal properties:
+Optional properties:
 - resets: phandle to a reset controller asserting the timer
 
 Example:
diff --git a/Documentation/devicetree/bindings/timer/cirrus,clps711x-timer.txt b/Documentation/devicetree/bindings/timer/cirrus,clps711x-timer.txt
index cd55b52548e4..d4c62e7b1714 100644
--- a/Documentation/devicetree/bindings/timer/cirrus,clps711x-timer.txt
+++ b/Documentation/devicetree/bindings/timer/cirrus,clps711x-timer.txt
@@ -1,7 +1,7 @@
 * Cirrus Logic CLPS711X Timer Counter
 
 Required properties:
-- compatible: Shall contain "cirrus,clps711x-timer".
+- compatible: Shall contain "cirrus,ep7209-timer".
 - reg       : Address and length of the register set.
 - interrupts: The interrupt number of the timer.
 - clocks    : phandle of timer reference clock.
@@ -15,14 +15,14 @@ Example:
 	};
 
 	timer1: timer@80000300 {
-		compatible = "cirrus,ep7312-timer", "cirrus,clps711x-timer";
+		compatible = "cirrus,ep7312-timer", "cirrus,ep7209-timer";
 		reg = <0x80000300 0x4>;
 		interrupts = <8>;
 		clocks = <&clks 5>;
 	};
 
 	timer2: timer@80000340 {
-		compatible = "cirrus,ep7312-timer", "cirrus,clps711x-timer";
+		compatible = "cirrus,ep7312-timer", "cirrus,ep7209-timer";
 		reg = <0x80000340 0x4>;
 		interrupts = <9>;
 		clocks = <&clks 6>;
diff --git a/Documentation/devicetree/bindings/usb/atmel-usb.txt b/Documentation/devicetree/bindings/usb/atmel-usb.txt
index 5883b73ea1b5..f4262ed60582 100644
--- a/Documentation/devicetree/bindings/usb/atmel-usb.txt
+++ b/Documentation/devicetree/bindings/usb/atmel-usb.txt
@@ -113,13 +113,13 @@ usb2: gadget@fff78000 {
 	clock-names = "hclk", "pclk";
 	atmel,vbus-gpio = <&pioB 19 0>;
 
-	ep0 {
+	ep@0 {
 		reg = <0>;
 		atmel,fifo-size = <64>;
 		atmel,nb-banks = <1>;
 	};
 
-	ep1 {
+	ep@1 {
 		reg = <1>;
 		atmel,fifo-size = <1024>;
 		atmel,nb-banks = <2>;
@@ -127,7 +127,7 @@ usb2: gadget@fff78000 {
 		atmel,can-isoc;
 	};
 
-	ep2 {
+	ep@2 {
 		reg = <2>;
 		atmel,fifo-size = <1024>;
 		atmel,nb-banks = <2>;
@@ -135,21 +135,21 @@ usb2: gadget@fff78000 {
 		atmel,can-isoc;
 	};
 
-	ep3 {
+	ep@3 {
 		reg = <3>;
 		atmel,fifo-size = <1024>;
 		atmel,nb-banks = <3>;
 		atmel,can-dma;
 	};
 
-	ep4 {
+	ep@4 {
 		reg = <4>;
 		atmel,fifo-size = <1024>;
 		atmel,nb-banks = <3>;
 		atmel,can-dma;
 	};
 
-	ep5 {
+	ep@5 {
 		reg = <5>;
 		atmel,fifo-size = <1024>;
 		atmel,nb-banks = <3>;
@@ -157,7 +157,7 @@ usb2: gadget@fff78000 {
 		atmel,can-isoc;
 	};
 
-	ep6 {
+	ep@6 {
 		reg = <6>;
 		atmel,fifo-size = <1024>;
 		atmel,nb-banks = <3>;
diff --git a/Documentation/devicetree/bindings/usb/nvidia,tegra124-xusb.txt b/Documentation/devicetree/bindings/usb/nvidia,tegra124-xusb.txt
index d28295a3e55f..3eee9e505400 100644
--- a/Documentation/devicetree/bindings/usb/nvidia,tegra124-xusb.txt
+++ b/Documentation/devicetree/bindings/usb/nvidia,tegra124-xusb.txt
@@ -104,10 +104,10 @@ Example:
 
 		nvidia,xusb-padctl = <&padctl>;
 
-		phys = <&{/padctl@0,7009f000/pads/usb2/usb2-1}>, /* mini-PCIe USB */
-		       <&{/padctl@0,7009f000/pads/usb2/usb2-2}>, /* USB A */
-		       <&{/padctl@0,7009f000/pads/pcie/pcie-0}>; /* USB A */
-		phy-names = "utmi-1", "utmi-2", "usb3-0";
+		phys = <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-1}>, /* mini-PCIe USB */
+		       <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-2}>, /* USB A */
+		       <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-0}>; /* USB A */
+		phy-names = "usb2-1", "usb2-2", "usb3-0";
 
 		avddio-pex-supply = <&vdd_1v05_run>;
 		dvddio-pex-supply = <&vdd_1v05_run>;
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index b9361816fc32..68391a462c0a 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -249,6 +249,7 @@ sony	Sony Corporation
 spansion	Spansion Inc.
 sprd	Spreadtrum Communications Inc.
 st	STMicroelectronics
+starry	Starry Electronic Technology (ShenZhen) Co., LTD
 startek	Startek
 ste	ST-Ericsson
 stericsson	ST-Ericsson
diff --git a/Documentation/devicetree/bindings/watchdog/aspeed-wdt.txt b/Documentation/devicetree/bindings/watchdog/aspeed-wdt.txt
new file mode 100644
index 000000000000..c5e74d7b4406
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/aspeed-wdt.txt
@@ -0,0 +1,16 @@
+Aspeed Watchdog Timer
+
+Required properties:
+ - compatible: must be one of:
+	- "aspeed,ast2400-wdt"
+	- "aspeed,ast2500-wdt"
+
+ - reg: physical base address of the controller and length of memory mapped
+   region
+
+Example:
+
+	wdt1: watchdog@1e785000 {
+		compatible = "aspeed,ast2400-wdt";
+		reg = <0x1e785000 0x1c>;
+	};
diff --git a/Documentation/devicetree/bindings/watchdog/meson-gxbb-wdt.txt b/Documentation/devicetree/bindings/watchdog/meson-gxbb-wdt.txt
new file mode 100644
index 000000000000..c7fe36fa739c
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/meson-gxbb-wdt.txt
@@ -0,0 +1,16 @@
+Meson GXBB SoCs Watchdog timer
+
+Required properties:
+
+- compatible : should be "amlogic,meson-gxbb-wdt"
+- reg : Specifies base physical address and size of the registers.
+- clocks : Should be a phandle to the Watchdog clock source, for GXBB the xtal
+	   is the default clock source.
+
+Example:
+
+wdt: watchdog@98d0 {
+	compatible = "amlogic,meson-gxbb-wdt";
+	reg = <0 0x98d0 0x0 0x10>;
+	clocks = <&xtal>;
+};
diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.txt b/Documentation/devicetree/bindings/watchdog/qcom-wdt.txt
index 4726924d034e..41aeaa2ff0f8 100644
--- a/Documentation/devicetree/bindings/watchdog/qcom-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/qcom-wdt.txt
@@ -7,6 +7,10 @@ Required properties :
 			"qcom,kpss-wdt-msm8960"
 			"qcom,kpss-wdt-apq8064"
 			"qcom,kpss-wdt-ipq8064"
+			"qcom,kpss-wdt-ipq4019"
+			"qcom,kpss-timer"
+			"qcom,scss-timer"
+			"qcom,kpss-wdt"
 
 - reg : shall contain base register location and length
 - clocks : shall contain the input clock
diff --git a/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt b/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt
index b9512f1eb80a..da24e3133417 100644
--- a/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt
@@ -1,7 +1,11 @@
 Renesas Watchdog Timer (WDT) Controller
 
 Required properties:
-- compatible : Should be "renesas,r8a7795-wdt", or "renesas,rcar-gen3-wdt"
+- compatible : Should be "renesas,<soctype>-wdt", and
+	       "renesas,rcar-gen3-wdt" as fallback.
+	       Examples with soctypes are:
+	         - "renesas,r8a7795-wdt" (R-Car H3)
+	         - "renesas,r8a7796-wdt" (R-Car M3-W)
 
   When compatible with the generic version, nodes must list the SoC-specific
   version corresponding to the platform first, followed by the generic
diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index 8ea834f6b289..5385cba941d2 100644
--- a/Documentation/dontdiff
+++ b/Documentation/dontdiff
@@ -3,6 +3,7 @@
 *.bc
 *.bin
 *.bz2
+*.c.[012]*.*
 *.cis
 *.cpio
 *.csp
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index c63eea0c1c8c..b0d775d28e97 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -352,8 +352,15 @@ REGULATOR
   devm_regulator_put()
   devm_regulator_register()
 
+RESET
+  devm_reset_control_get()
+  devm_reset_controller_register()
+
 SLAVE DMA ENGINE
   devm_acpi_dma_controller_register()
 
 SPI
   devm_spi_register_master()
+
+WATCHDOG
+  devm_watchdog_register_device()
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
index 5b21ef76f751..c0727dc36271 100644
--- a/Documentation/filesystems/nilfs2.txt
+++ b/Documentation/filesystems/nilfs2.txt
@@ -267,7 +267,8 @@ among NILFS2 files can be depicted as follows:
                                   `-- file (ino=yy)
                                     ( regular file, directory, or symlink )
 
-For detail on the format of each file, please see include/linux/nilfs2_fs.h.
+For detail on the format of each file, please see nilfs2_ondisk.h
+located at include/uapi/linux directory.
 
 There are no patents or other intellectual property that we protect
 with regard to the design of NILFS2.  It is allowed to replicate the
diff --git a/Documentation/filesystems/orangefs.txt b/Documentation/filesystems/orangefs.txt
index e1a0056a365f..1dfdec790946 100644
--- a/Documentation/filesystems/orangefs.txt
+++ b/Documentation/filesystems/orangefs.txt
@@ -281,7 +281,7 @@ on the wait queue and one attempt is made to recycle them. Obviously,
 if the client-core stays dead too long, the arbitrary userspace processes
 trying to use Orangefs will be negatively affected. Waiting ops
 that can't be serviced will be removed from the request list and
-have their states set to "given up". In-progress ops that can't 
+have their states set to "given up". In-progress ops that can't
 be serviced will be removed from the in_progress hash table and
 have their states set to "given up".
 
@@ -338,7 +338,7 @@ particular response.
   PVFS2_VFS_OP_STATFS
     fill a pvfs2_statfs_response_t with useless info <g>. It is hard for
     us to know, in a timely fashion, these statistics about our
-    distributed network filesystem. 
+    distributed network filesystem.
 
   PVFS2_VFS_OP_FS_MOUNT
     fill a pvfs2_fs_mount_response_t which is just like a PVFS_object_kref
@@ -386,7 +386,7 @@ responses:
 
   io_array[1].iov_base = address of global variable "pdev_magic" (int32_t)
   io_array[1].iov_len = sizeof(int32_t)
-  
+
   io_array[2].iov_base = address of parameter "tag" (PVFS_id_gen_t)
   io_array[2].iov_len = sizeof(int64_t)
 
@@ -402,5 +402,47 @@ Readdir responses initialize the fifth element io_array like this:
   io_array[4].iov_len = contents of member trailer_size (PVFS_size)
                         from out_downcall member of global variable
                         vfs_request
-  
+
+Orangefs exploits the dcache in order to avoid sending redundant
+requests to userspace. We keep object inode attributes up-to-date with
+orangefs_inode_getattr. Orangefs_inode_getattr uses two arguments to
+help it decide whether or not to update an inode: "new" and "bypass".
+Orangefs keeps private data in an object's inode that includes a short
+timeout value, getattr_time, which allows any iteration of
+orangefs_inode_getattr to know how long it has been since the inode was
+updated. When the object is not new (new == 0) and the bypass flag is not
+set (bypass == 0) orangefs_inode_getattr returns without updating the inode
+if getattr_time has not timed out. Getattr_time is updated each time the
+inode is updated.
+
+Creation of a new object (file, dir, sym-link) includes the evaluation of
+its pathname, resulting in a negative directory entry for the object.
+A new inode is allocated and associated with the dentry, turning it from
+a negative dentry into a "productive full member of society". Orangefs
+obtains the new inode from Linux with new_inode() and associates
+the inode with the dentry by sending the pair back to Linux with
+d_instantiate().
+
+The evaluation of a pathname for an object resolves to its corresponding
+dentry. If there is no corresponding dentry, one is created for it in
+the dcache. Whenever a dentry is modified or verified Orangefs stores a
+short timeout value in the dentry's d_time, and the dentry will be trusted
+for that amount of time. Orangefs is a network filesystem, and objects
+can potentially change out-of-band with any particular Orangefs kernel module
+instance, so trusting a dentry is risky. The alternative to trusting
+dentries is to always obtain the needed information from userspace - at
+least a trip to the client-core, maybe to the servers. Obtaining information
+from a dentry is cheap, obtaining it from userspace is relatively expensive,
+hence the motivation to use the dentry when possible.
+
+The timeout values d_time and getattr_time are jiffy based, and the
+code is designed to avoid the jiffy-wrap problem:
+
+"In general, if the clock may have wrapped around more than once, there
+is no way to tell how much time has elapsed. However, if the times t1
+and t2 are known to be fairly close, we can reliably compute the
+difference in a way that takes into account the possibility that the
+clock may have wrapped between times."
+
+                      from course notes by instructor Andy Wang
 
diff --git a/Documentation/gcc-plugins.txt b/Documentation/gcc-plugins.txt
new file mode 100644
index 000000000000..891c69464434
--- /dev/null
+++ b/Documentation/gcc-plugins.txt
@@ -0,0 +1,87 @@
+GCC plugin infrastructure
+=========================
+
+
+1. Introduction
+===============
+
+GCC plugins are loadable modules that provide extra features to the
+compiler [1]. They are useful for runtime instrumentation and static analysis.
+We can analyse, change and add further code during compilation via
+callbacks [2], GIMPLE [3], IPA [4] and RTL passes [5].
+
+The GCC plugin infrastructure of the kernel supports all gcc versions from
+4.5 to 6.0, building out-of-tree modules, cross-compilation and building in a
+separate directory.
+Plugin source files have to be compilable by both a C and a C++ compiler as well
+because gcc versions 4.5 and 4.6 are compiled by a C compiler,
+gcc-4.7 can be compiled by a C or a C++ compiler,
+and versions 4.8+ can only be compiled by a C++ compiler.
+
+Currently the GCC plugin infrastructure supports only the x86, arm and arm64
+architectures.
+
+This infrastructure was ported from grsecurity [6] and PaX [7].
+
+--
+[1] https://gcc.gnu.org/onlinedocs/gccint/Plugins.html
+[2] https://gcc.gnu.org/onlinedocs/gccint/Plugin-API.html#Plugin-API
+[3] https://gcc.gnu.org/onlinedocs/gccint/GIMPLE.html
+[4] https://gcc.gnu.org/onlinedocs/gccint/IPA.html
+[5] https://gcc.gnu.org/onlinedocs/gccint/RTL.html
+[6] https://grsecurity.net/
+[7] https://pax.grsecurity.net/
+
+
+2. Files
+========
+
+$(src)/scripts/gcc-plugins
+	This is the directory of the GCC plugins.
+
+$(src)/scripts/gcc-plugins/gcc-common.h
+	This is a compatibility header for GCC plugins.
+	It should be always included instead of individual gcc headers.
+
+$(src)/scripts/gcc-plugin.sh
+	This script checks the availability of the included headers in
+	gcc-common.h and chooses the proper host compiler to build the plugins
+	(gcc-4.7 can be built by either gcc or g++).
+
+$(src)/scripts/gcc-plugins/gcc-generate-gimple-pass.h
+$(src)/scripts/gcc-plugins/gcc-generate-ipa-pass.h
+$(src)/scripts/gcc-plugins/gcc-generate-simple_ipa-pass.h
+$(src)/scripts/gcc-plugins/gcc-generate-rtl-pass.h
+	These headers automatically generate the registration structures for
+	GIMPLE, SIMPLE_IPA, IPA and RTL passes. They support all gcc versions
+	from 4.5 to 6.0.
+	They should be preferred to creating the structures by hand.
+
+
+3. Usage
+========
+
+You must install the gcc plugin headers for your gcc version,
+e.g., on Ubuntu for gcc-4.9:
+
+	apt-get install gcc-4.9-plugin-dev
+
+Enable a GCC plugin based feature in the kernel config:
+
+	CONFIG_GCC_PLUGIN_CYC_COMPLEXITY = y
+
+To compile only the plugin(s):
+
+	make gcc-plugins
+
+or just run the kernel make and compile the whole kernel with
+the cyclomatic complexity GCC plugin.
+
+
+4. How to add a new GCC plugin
+==============================
+
+The GCC plugins are in $(src)/scripts/gcc-plugins/. You can use a file or a directory
+here. It must be added to $(src)/scripts/gcc-plugins/Makefile,
+$(src)/scripts/Makefile.gcc-plugins and $(src)/arch/Kconfig.
+See the cyc_complexity_plugin.c (CONFIG_GCC_PLUGIN_CYC_COMPLEXITY) GCC plugin.
diff --git a/Documentation/gpu/drm-internals.rst b/Documentation/gpu/drm-internals.rst
new file mode 100644
index 000000000000..3bb26135971f
--- /dev/null
+++ b/Documentation/gpu/drm-internals.rst
@@ -0,0 +1,381 @@
+=============
+DRM Internals
+=============
+
+This chapter documents DRM internals relevant to driver authors and
+developers working to add support for the latest features to existing
+drivers.
+
+First, we go over some typical driver initialization requirements, like
+setting up command buffers, creating an initial output configuration,
+and initializing core services. Subsequent sections cover core internals
+in more detail, providing implementation notes and examples.
+
+The DRM layer provides several services to graphics drivers, many of
+them driven by the application interfaces it provides through libdrm,
+the library that wraps most of the DRM ioctls. These include vblank
+event handling, memory management, output management, framebuffer
+management, command submission & fencing, suspend/resume support, and
+DMA services.
+
+Driver Initialization
+=====================
+
+At the core of every DRM driver is a :c:type:`struct drm_driver
+<drm_driver>` structure. Drivers typically statically initialize
+a drm_driver structure, and then pass it to
+:c:func:`drm_dev_alloc()` to allocate a device instance. After the
+device instance is fully initialized it can be registered (which makes
+it accessible from userspace) using :c:func:`drm_dev_register()`.
+
+The :c:type:`struct drm_driver <drm_driver>` structure
+contains static information that describes the driver and features it
+supports, and pointers to methods that the DRM core will call to
+implement the DRM API. We will first go through the :c:type:`struct
+drm_driver <drm_driver>` static information fields, and will
+then describe individual operations in details as they get used in later
+sections.
+
+Driver Information
+------------------
+
+Driver Features
+~~~~~~~~~~~~~~~
+
+Drivers inform the DRM core about their requirements and supported
+features by setting appropriate flags in the driver_features field.
+Since those flags influence the DRM core behaviour since registration
+time, most of them must be set to registering the :c:type:`struct
+drm_driver <drm_driver>` instance.
+
+u32 driver_features;
+
+DRIVER_USE_AGP
+    Driver uses AGP interface, the DRM core will manage AGP resources.
+
+DRIVER_REQUIRE_AGP
+    Driver needs AGP interface to function. AGP initialization failure
+    will become a fatal error.
+
+DRIVER_PCI_DMA
+    Driver is capable of PCI DMA, mapping of PCI DMA buffers to
+    userspace will be enabled. Deprecated.
+
+DRIVER_SG
+    Driver can perform scatter/gather DMA, allocation and mapping of
+    scatter/gather buffers will be enabled. Deprecated.
+
+DRIVER_HAVE_DMA
+    Driver supports DMA, the userspace DMA API will be supported.
+    Deprecated.
+
+DRIVER_HAVE_IRQ; DRIVER_IRQ_SHARED
+    DRIVER_HAVE_IRQ indicates whether the driver has an IRQ handler
+    managed by the DRM Core. The core will support simple IRQ handler
+    installation when the flag is set. The installation process is
+    described in ?.
+
+    DRIVER_IRQ_SHARED indicates whether the device & handler support
+    shared IRQs (note that this is required of PCI drivers).
+
+DRIVER_GEM
+    Driver use the GEM memory manager.
+
+DRIVER_MODESET
+    Driver supports mode setting interfaces (KMS).
+
+DRIVER_PRIME
+    Driver implements DRM PRIME buffer sharing.
+
+DRIVER_RENDER
+    Driver supports dedicated render nodes.
+
+DRIVER_ATOMIC
+    Driver supports atomic properties. In this case the driver must
+    implement appropriate obj->atomic_get_property() vfuncs for any
+    modeset objects with driver specific properties.
+
+Major, Minor and Patchlevel
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+int major; int minor; int patchlevel;
+The DRM core identifies driver versions by a major, minor and patch
+level triplet. The information is printed to the kernel log at
+initialization time and passed to userspace through the
+DRM_IOCTL_VERSION ioctl.
+
+The major and minor numbers are also used to verify the requested driver
+API version passed to DRM_IOCTL_SET_VERSION. When the driver API
+changes between minor versions, applications can call
+DRM_IOCTL_SET_VERSION to select a specific version of the API. If the
+requested major isn't equal to the driver major, or the requested minor
+is larger than the driver minor, the DRM_IOCTL_SET_VERSION call will
+return an error. Otherwise the driver's set_version() method will be
+called with the requested version.
+
+Name, Description and Date
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+char \*name; char \*desc; char \*date;
+The driver name is printed to the kernel log at initialization time,
+used for IRQ registration and passed to userspace through
+DRM_IOCTL_VERSION.
+
+The driver description is a purely informative string passed to
+userspace through the DRM_IOCTL_VERSION ioctl and otherwise unused by
+the kernel.
+
+The driver date, formatted as YYYYMMDD, is meant to identify the date of
+the latest modification to the driver. However, as most drivers fail to
+update it, its value is mostly useless. The DRM core prints it to the
+kernel log at initialization time and passes it to userspace through the
+DRM_IOCTL_VERSION ioctl.
+
+Device Instance and Driver Handling
+-----------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_drv.c
+   :doc: driver instance overview
+
+.. kernel-doc:: drivers/gpu/drm/drm_drv.c
+   :export:
+
+Driver Load
+-----------
+
+IRQ Registration
+~~~~~~~~~~~~~~~~
+
+The DRM core tries to facilitate IRQ handler registration and
+unregistration by providing :c:func:`drm_irq_install()` and
+:c:func:`drm_irq_uninstall()` functions. Those functions only
+support a single interrupt per device, devices that use more than one
+IRQs need to be handled manually.
+
+Managed IRQ Registration
+''''''''''''''''''''''''
+
+:c:func:`drm_irq_install()` starts by calling the irq_preinstall
+driver operation. The operation is optional and must make sure that the
+interrupt will not get fired by clearing all pending interrupt flags or
+disabling the interrupt.
+
+The passed-in IRQ will then be requested by a call to
+:c:func:`request_irq()`. If the DRIVER_IRQ_SHARED driver feature
+flag is set, a shared (IRQF_SHARED) IRQ handler will be requested.
+
+The IRQ handler function must be provided as the mandatory irq_handler
+driver operation. It will get passed directly to
+:c:func:`request_irq()` and thus has the same prototype as all IRQ
+handlers. It will get called with a pointer to the DRM device as the
+second argument.
+
+Finally the function calls the optional irq_postinstall driver
+operation. The operation usually enables interrupts (excluding the
+vblank interrupt, which is enabled separately), but drivers may choose
+to enable/disable interrupts at a different time.
+
+:c:func:`drm_irq_uninstall()` is similarly used to uninstall an
+IRQ handler. It starts by waking up all processes waiting on a vblank
+interrupt to make sure they don't hang, and then calls the optional
+irq_uninstall driver operation. The operation must disable all hardware
+interrupts. Finally the function frees the IRQ by calling
+:c:func:`free_irq()`.
+
+Manual IRQ Registration
+'''''''''''''''''''''''
+
+Drivers that require multiple interrupt handlers can't use the managed
+IRQ registration functions. In that case IRQs must be registered and
+unregistered manually (usually with the :c:func:`request_irq()` and
+:c:func:`free_irq()` functions, or their :c:func:`devm_request_irq()` and
+:c:func:`devm_free_irq()` equivalents).
+
+When manually registering IRQs, drivers must not set the
+DRIVER_HAVE_IRQ driver feature flag, and must not provide the
+irq_handler driver operation. They must set the :c:type:`struct
+drm_device <drm_device>` irq_enabled field to 1 upon
+registration of the IRQs, and clear it to 0 after unregistering the
+IRQs.
+
+Memory Manager Initialization
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Every DRM driver requires a memory manager which must be initialized at
+load time. DRM currently contains two memory managers, the Translation
+Table Manager (TTM) and the Graphics Execution Manager (GEM). This
+document describes the use of the GEM memory manager only. See ? for
+details.
+
+Miscellaneous Device Configuration
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Another task that may be necessary for PCI devices during configuration
+is mapping the video BIOS. On many devices, the VBIOS describes device
+configuration, LCD panel timings (if any), and contains flags indicating
+device state. Mapping the BIOS can be done using the pci_map_rom()
+call, a convenience function that takes care of mapping the actual ROM,
+whether it has been shadowed into memory (typically at address 0xc0000)
+or exists on the PCI device in the ROM BAR. Note that after the ROM has
+been mapped and any necessary information has been extracted, it should
+be unmapped; on many devices, the ROM address decoder is shared with
+other BARs, so leaving it mapped could cause undesired behaviour like
+hangs or memory corruption.
+
+Bus-specific Device Registration and PCI Support
+------------------------------------------------
+
+A number of functions are provided to help with device registration. The
+functions deal with PCI and platform devices respectively and are only
+provided for historical reasons. These are all deprecated and shouldn't
+be used in new drivers. Besides that there's a few helpers for pci
+drivers.
+
+.. kernel-doc:: drivers/gpu/drm/drm_pci.c
+   :export:
+
+.. kernel-doc:: drivers/gpu/drm/drm_platform.c
+   :export:
+
+Open/Close, File Operations and IOCTLs
+======================================
+
+Open and Close
+--------------
+
+Open and close handlers. None of those methods are mandatory::
+
+    int (*firstopen) (struct drm_device *);
+    void (*lastclose) (struct drm_device *);
+    int (*open) (struct drm_device *, struct drm_file *);
+    void (*preclose) (struct drm_device *, struct drm_file *);
+    void (*postclose) (struct drm_device *, struct drm_file *);
+
+The firstopen method is called by the DRM core for legacy UMS (User Mode
+Setting) drivers only when an application opens a device that has no
+other opened file handle. UMS drivers can implement it to acquire device
+resources. KMS drivers can't use the method and must acquire resources
+in the load method instead.
+
+Similarly the lastclose method is called when the last application
+holding a file handle opened on the device closes it, for both UMS and
+KMS drivers. Additionally, the method is also called at module unload
+time or, for hot-pluggable devices, when the device is unplugged. The
+firstopen and lastclose calls can thus be unbalanced.
+
+The open method is called every time the device is opened by an
+application. Drivers can allocate per-file private data in this method
+and store them in the struct :c:type:`struct drm_file
+<drm_file>` driver_priv field. Note that the open method is
+called before firstopen.
+
+The close operation is split into preclose and postclose methods.
+Drivers must stop and cleanup all per-file operations in the preclose
+method. For instance pending vertical blanking and page flip events must
+be cancelled. No per-file operation is allowed on the file handle after
+returning from the preclose method.
+
+Finally the postclose method is called as the last step of the close
+operation, right before calling the lastclose method if no other open
+file handle exists for the device. Drivers that have allocated per-file
+private data in the open method should free it here.
+
+The lastclose method should restore CRTC and plane properties to default
+value, so that a subsequent open of the device will not inherit state
+from the previous user. It can also be used to execute delayed power
+switching state changes, e.g. in conjunction with the :ref:`vga_switcheroo`
+infrastructure. Beyond that KMS drivers should not do any
+further cleanup. Only legacy UMS drivers might need to clean up device
+state so that the vga console or an independent fbdev driver could take
+over.
+
+File Operations
+---------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_fops.c
+   :doc: file operations
+
+.. kernel-doc:: drivers/gpu/drm/drm_fops.c
+   :export:
+
+IOCTLs
+------
+
+struct drm_ioctl_desc \*ioctls; int num_ioctls;
+    Driver-specific ioctls descriptors table.
+
+Driver-specific ioctls numbers start at DRM_COMMAND_BASE. The ioctls
+descriptors table is indexed by the ioctl number offset from the base
+value. Drivers can use the DRM_IOCTL_DEF_DRV() macro to initialize
+the table entries.
+
+::
+
+    DRM_IOCTL_DEF_DRV(ioctl, func, flags)
+
+``ioctl`` is the ioctl name. Drivers must define the DRM_##ioctl and
+DRM_IOCTL_##ioctl macros to the ioctl number offset from
+DRM_COMMAND_BASE and the ioctl number respectively. The first macro is
+private to the device while the second must be exposed to userspace in a
+public header.
+
+``func`` is a pointer to the ioctl handler function compatible with the
+``drm_ioctl_t`` type.
+
+::
+
+    typedef int drm_ioctl_t(struct drm_device *dev, void *data,
+            struct drm_file *file_priv);
+
+``flags`` is a bitmask combination of the following values. It restricts
+how the ioctl is allowed to be called.
+
+-  DRM_AUTH - Only authenticated callers allowed
+
+-  DRM_MASTER - The ioctl can only be called on the master file handle
+
+-  DRM_ROOT_ONLY - Only callers with the SYSADMIN capability allowed
+
+-  DRM_CONTROL_ALLOW - The ioctl can only be called on a control
+   device
+
+-  DRM_UNLOCKED - The ioctl handler will be called without locking the
+   DRM global mutex. This is the enforced default for kms drivers (i.e.
+   using the DRIVER_MODESET flag) and hence shouldn't be used any more
+   for new drivers.
+
+.. kernel-doc:: drivers/gpu/drm/drm_ioctl.c
+   :export:
+
+Legacy Support Code
+===================
+
+The section very briefly covers some of the old legacy support code
+which is only used by old DRM drivers which have done a so-called
+shadow-attach to the underlying device instead of registering as a real
+driver. This also includes some of the old generic buffer management and
+command submission code. Do not use any of this in new and modern
+drivers.
+
+Legacy Suspend/Resume
+---------------------
+
+The DRM core provides some suspend/resume code, but drivers wanting full
+suspend/resume support should provide save() and restore() functions.
+These are called at suspend, hibernate, or resume time, and should
+perform any state save or restore required by your device across suspend
+or hibernate states.
+
+int (\*suspend) (struct drm_device \*, pm_message_t state); int
+(\*resume) (struct drm_device \*);
+Those are legacy suspend and resume methods which *only* work with the
+legacy shadow-attach driver registration functions. New driver should
+use the power management interface provided by their bus type (usually
+through the :c:type:`struct device_driver <device_driver>`
+dev_pm_ops) and set these methods to NULL.
+
+Legacy DMA Services
+-------------------
+
+This should cover how DMA mapping etc. is supported by the core. These
+functions are deprecated and should not be used.
diff --git a/Documentation/gpu/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst
new file mode 100644
index 000000000000..0b302fedf1af
--- /dev/null
+++ b/Documentation/gpu/drm-kms-helpers.rst
@@ -0,0 +1,260 @@
+=============================
+Mode Setting Helper Functions
+=============================
+
+The plane, CRTC, encoder and connector functions provided by the drivers
+implement the DRM API. They're called by the DRM core and ioctl handlers
+to handle device state changes and configuration request. As
+implementing those functions often requires logic not specific to
+drivers, mid-layer helper functions are available to avoid duplicating
+boilerplate code.
+
+The DRM core contains one mid-layer implementation. The mid-layer
+provides implementations of several plane, CRTC, encoder and connector
+functions (called from the top of the mid-layer) that pre-process
+requests and call lower-level functions provided by the driver (at the
+bottom of the mid-layer). For instance, the
+:c:func:`drm_crtc_helper_set_config()` function can be used to
+fill the :c:type:`struct drm_crtc_funcs <drm_crtc_funcs>`
+set_config field. When called, it will split the set_config operation
+in smaller, simpler operations and call the driver to handle them.
+
+To use the mid-layer, drivers call
+:c:func:`drm_crtc_helper_add()`,
+:c:func:`drm_encoder_helper_add()` and
+:c:func:`drm_connector_helper_add()` functions to install their
+mid-layer bottom operations handlers, and fill the :c:type:`struct
+drm_crtc_funcs <drm_crtc_funcs>`, :c:type:`struct
+drm_encoder_funcs <drm_encoder_funcs>` and :c:type:`struct
+drm_connector_funcs <drm_connector_funcs>` structures with
+pointers to the mid-layer top API functions. Installing the mid-layer
+bottom operation handlers is best done right after registering the
+corresponding KMS object.
+
+The mid-layer is not split between CRTC, encoder and connector
+operations. To use it, a driver must provide bottom functions for all of
+the three KMS entities.
+
+Atomic Modeset Helper Functions Reference
+=========================================
+
+Overview
+--------
+
+.. kernel-doc:: drivers/gpu/drm/drm_atomic_helper.c
+   :doc: overview
+
+Implementing Asynchronous Atomic Commit
+---------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_atomic_helper.c
+   :doc: implementing nonblocking commit
+
+Atomic State Reset and Initialization
+-------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_atomic_helper.c
+   :doc: atomic state reset and initialization
+
+.. kernel-doc:: include/drm/drm_atomic_helper.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_atomic_helper.c
+   :export:
+
+Modeset Helper Reference for Common Vtables
+===========================================
+
+.. kernel-doc:: include/drm/drm_modeset_helper_vtables.h
+   :internal:
+
+.. kernel-doc:: include/drm/drm_modeset_helper_vtables.h
+   :doc: overview
+
+Legacy CRTC/Modeset Helper Functions Reference
+==============================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_crtc_helper.c
+   :export:
+
+.. kernel-doc:: drivers/gpu/drm/drm_crtc_helper.c
+   :doc: overview
+
+Output Probing Helper Functions Reference
+=========================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_probe_helper.c
+   :doc: output probing helper overview
+
+.. kernel-doc:: drivers/gpu/drm/drm_probe_helper.c
+   :export:
+
+fbdev Helper Functions Reference
+================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_fb_helper.c
+   :doc: fbdev helpers
+
+.. kernel-doc:: drivers/gpu/drm/drm_fb_helper.c
+   :export:
+
+.. kernel-doc:: include/drm/drm_fb_helper.h
+   :internal:
+
+Framebuffer CMA Helper Functions Reference
+==========================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_fb_cma_helper.c
+   :doc: framebuffer cma helper functions
+
+.. kernel-doc:: drivers/gpu/drm/drm_fb_cma_helper.c
+   :export:
+
+Display Port Helper Functions Reference
+=======================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_dp_helper.c
+   :doc: dp helpers
+
+.. kernel-doc:: include/drm/drm_dp_helper.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_dp_helper.c
+   :export:
+
+Display Port Dual Mode Adaptor Helper Functions Reference
+=========================================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_dp_dual_mode_helper.c
+   :doc: dp dual mode helpers
+
+.. kernel-doc:: include/drm/drm_dp_dual_mode_helper.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_dp_dual_mode_helper.c
+   :export:
+
+Display Port MST Helper Functions Reference
+===========================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_dp_mst_topology.c
+   :doc: dp mst helper
+
+.. kernel-doc:: include/drm/drm_dp_mst_helper.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_dp_mst_topology.c
+   :export:
+
+MIPI DSI Helper Functions Reference
+===================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_mipi_dsi.c
+   :doc: dsi helpers
+
+.. kernel-doc:: include/drm/drm_mipi_dsi.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_mipi_dsi.c
+   :export:
+
+EDID Helper Functions Reference
+===============================
+
+.. kernel-doc:: drivers/gpu/drm/drm_edid.c
+   :export:
+
+Rectangle Utilities Reference
+=============================
+
+.. kernel-doc:: include/drm/drm_rect.h
+   :doc: rect utils
+
+.. kernel-doc:: include/drm/drm_rect.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_rect.c
+   :export:
+
+Flip-work Helper Reference
+==========================
+
+.. kernel-doc:: include/drm/drm_flip_work.h
+   :doc: flip utils
+
+.. kernel-doc:: include/drm/drm_flip_work.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_flip_work.c
+   :export:
+
+HDMI Infoframes Helper Reference
+================================
+
+Strictly speaking this is not a DRM helper library but generally useable
+by any driver interfacing with HDMI outputs like v4l or alsa drivers.
+But it nicely fits into the overall topic of mode setting helper
+libraries and hence is also included here.
+
+.. kernel-doc:: include/linux/hdmi.h
+   :internal:
+
+.. kernel-doc:: drivers/video/hdmi.c
+   :export:
+
+Plane Helper Reference
+======================
+
+.. kernel-doc:: drivers/gpu/drm/drm_plane_helper.c
+   :export:
+
+.. kernel-doc:: drivers/gpu/drm/drm_plane_helper.c
+   :doc: overview
+
+Tile group
+----------
+
+.. kernel-doc:: drivers/gpu/drm/drm_crtc.c
+   :doc: Tile group
+
+Bridges
+=======
+
+Overview
+--------
+
+.. kernel-doc:: drivers/gpu/drm/drm_bridge.c
+   :doc: overview
+
+Default bridge callback sequence
+--------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_bridge.c
+   :doc: bridge callbacks
+
+.. kernel-doc:: drivers/gpu/drm/drm_bridge.c
+   :export:
+
+Panel Helper Reference
+======================
+
+.. kernel-doc:: include/drm/drm_panel.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_panel.c
+   :export:
+
+.. kernel-doc:: drivers/gpu/drm/drm_panel.c
+   :doc: drm panel
+
+Simple KMS Helper Reference
+===========================
+
+.. kernel-doc:: include/drm/drm_simple_kms_helper.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_simple_kms_helper.c
+   :export:
+
+.. kernel-doc:: drivers/gpu/drm/drm_simple_kms_helper.c
+   :doc: overview
diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
new file mode 100644
index 000000000000..8dfa4b214b96
--- /dev/null
+++ b/Documentation/gpu/drm-kms.rst
@@ -0,0 +1,653 @@
+=========================
+Kernel Mode Setting (KMS)
+=========================
+
+Mode Setting
+============
+
+Drivers must initialize the mode setting core by calling
+:c:func:`drm_mode_config_init()` on the DRM device. The function
+initializes the :c:type:`struct drm_device <drm_device>`
+mode_config field and never fails. Once done, mode configuration must
+be setup by initializing the following fields.
+
+-  int min_width, min_height; int max_width, max_height;
+   Minimum and maximum width and height of the frame buffers in pixel
+   units.
+
+-  struct drm_mode_config_funcs \*funcs;
+   Mode setting functions.
+
+Display Modes Function Reference
+--------------------------------
+
+.. kernel-doc:: include/drm/drm_modes.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_modes.c
+   :export:
+
+Atomic Mode Setting Function Reference
+--------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_atomic.c
+   :export:
+
+.. kernel-doc:: drivers/gpu/drm/drm_atomic.c
+   :internal:
+
+Frame Buffer Abstraction
+------------------------
+
+Frame buffers are abstract memory objects that provide a source of
+pixels to scanout to a CRTC. Applications explicitly request the
+creation of frame buffers through the DRM_IOCTL_MODE_ADDFB(2) ioctls
+and receive an opaque handle that can be passed to the KMS CRTC control,
+plane configuration and page flip functions.
+
+Frame buffers rely on the underneath memory manager for low-level memory
+operations. When creating a frame buffer applications pass a memory
+handle (or a list of memory handles for multi-planar formats) through
+the ``drm_mode_fb_cmd2`` argument. For drivers using GEM as their
+userspace buffer management interface this would be a GEM handle.
+Drivers are however free to use their own backing storage object
+handles, e.g. vmwgfx directly exposes special TTM handles to userspace
+and so expects TTM handles in the create ioctl and not GEM handles.
+
+The lifetime of a drm framebuffer is controlled with a reference count,
+drivers can grab additional references with
+:c:func:`drm_framebuffer_reference()`and drop them again with
+:c:func:`drm_framebuffer_unreference()`. For driver-private
+framebuffers for which the last reference is never dropped (e.g. for the
+fbdev framebuffer when the struct :c:type:`struct drm_framebuffer
+<drm_framebuffer>` is embedded into the fbdev helper struct)
+drivers can manually clean up a framebuffer at module unload time with
+:c:func:`drm_framebuffer_unregister_private()`.
+
+DRM Format Handling
+-------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_fourcc.c
+   :export:
+
+Dumb Buffer Objects
+-------------------
+
+The KMS API doesn't standardize backing storage object creation and
+leaves it to driver-specific ioctls. Furthermore actually creating a
+buffer object even for GEM-based drivers is done through a
+driver-specific ioctl - GEM only has a common userspace interface for
+sharing and destroying objects. While not an issue for full-fledged
+graphics stacks that include device-specific userspace components (in
+libdrm for instance), this limit makes DRM-based early boot graphics
+unnecessarily complex.
+
+Dumb objects partly alleviate the problem by providing a standard API to
+create dumb buffers suitable for scanout, which can then be used to
+create KMS frame buffers.
+
+To support dumb objects drivers must implement the dumb_create,
+dumb_destroy and dumb_map_offset operations.
+
+-  int (\*dumb_create)(struct drm_file \*file_priv, struct
+   drm_device \*dev, struct drm_mode_create_dumb \*args);
+   The dumb_create operation creates a driver object (GEM or TTM
+   handle) suitable for scanout based on the width, height and depth
+   from the struct :c:type:`struct drm_mode_create_dumb
+   <drm_mode_create_dumb>` argument. It fills the argument's
+   handle, pitch and size fields with a handle for the newly created
+   object and its line pitch and size in bytes.
+
+-  int (\*dumb_destroy)(struct drm_file \*file_priv, struct
+   drm_device \*dev, uint32_t handle);
+   The dumb_destroy operation destroys a dumb object created by
+   dumb_create.
+
+-  int (\*dumb_map_offset)(struct drm_file \*file_priv, struct
+   drm_device \*dev, uint32_t handle, uint64_t \*offset);
+   The dumb_map_offset operation associates an mmap fake offset with
+   the object given by the handle and returns it. Drivers must use the
+   :c:func:`drm_gem_create_mmap_offset()` function to associate
+   the fake offset as described in ?.
+
+Note that dumb objects may not be used for gpu acceleration, as has been
+attempted on some ARM embedded platforms. Such drivers really must have
+a hardware-specific ioctl to allocate suitable buffer objects.
+
+Output Polling
+--------------
+
+void (\*output_poll_changed)(struct drm_device \*dev);
+This operation notifies the driver that the status of one or more
+connectors has changed. Drivers that use the fb helper can just call the
+:c:func:`drm_fb_helper_hotplug_event()` function to handle this
+operation.
+
+KMS Initialization and Cleanup
+==============================
+
+A KMS device is abstracted and exposed as a set of planes, CRTCs,
+encoders and connectors. KMS drivers must thus create and initialize all
+those objects at load time after initializing mode setting.
+
+CRTCs (:c:type:`struct drm_crtc <drm_crtc>`)
+--------------------------------------------
+
+A CRTC is an abstraction representing a part of the chip that contains a
+pointer to a scanout buffer. Therefore, the number of CRTCs available
+determines how many independent scanout buffers can be active at any
+given time. The CRTC structure contains several fields to support this:
+a pointer to some video memory (abstracted as a frame buffer object), a
+display mode, and an (x, y) offset into the video memory to support
+panning or configurations where one piece of video memory spans multiple
+CRTCs.
+
+CRTC Initialization
+~~~~~~~~~~~~~~~~~~~
+
+A KMS device must create and register at least one struct
+:c:type:`struct drm_crtc <drm_crtc>` instance. The instance is
+allocated and zeroed by the driver, possibly as part of a larger
+structure, and registered with a call to :c:func:`drm_crtc_init()`
+with a pointer to CRTC functions.
+
+Planes (:c:type:`struct drm_plane <drm_plane>`)
+-----------------------------------------------
+
+A plane represents an image source that can be blended with or overlayed
+on top of a CRTC during the scanout process. Planes are associated with
+a frame buffer to crop a portion of the image memory (source) and
+optionally scale it to a destination size. The result is then blended
+with or overlayed on top of a CRTC.
+
+The DRM core recognizes three types of planes:
+
+-  DRM_PLANE_TYPE_PRIMARY represents a "main" plane for a CRTC.
+   Primary planes are the planes operated upon by CRTC modesetting and
+   flipping operations described in the page_flip hook in
+   :c:type:`struct drm_crtc_funcs <drm_crtc_funcs>`.
+-  DRM_PLANE_TYPE_CURSOR represents a "cursor" plane for a CRTC.
+   Cursor planes are the planes operated upon by the
+   DRM_IOCTL_MODE_CURSOR and DRM_IOCTL_MODE_CURSOR2 ioctls.
+-  DRM_PLANE_TYPE_OVERLAY represents all non-primary, non-cursor
+   planes. Some drivers refer to these types of planes as "sprites"
+   internally.
+
+For compatibility with legacy userspace, only overlay planes are made
+available to userspace by default. Userspace clients may set the
+DRM_CLIENT_CAP_UNIVERSAL_PLANES client capability bit to indicate
+that they wish to receive a universal plane list containing all plane
+types.
+
+Plane Initialization
+~~~~~~~~~~~~~~~~~~~~
+
+To create a plane, a KMS drivers allocates and zeroes an instances of
+:c:type:`struct drm_plane <drm_plane>` (possibly as part of a
+larger structure) and registers it with a call to
+:c:func:`drm_universal_plane_init()`. The function takes a
+bitmask of the CRTCs that can be associated with the plane, a pointer to
+the plane functions, a list of format supported formats, and the type of
+plane (primary, cursor, or overlay) being initialized.
+
+Cursor and overlay planes are optional. All drivers should provide one
+primary plane per CRTC (although this requirement may change in the
+future); drivers that do not wish to provide special handling for
+primary planes may make use of the helper functions described in ? to
+create and register a primary plane with standard capabilities.
+
+Encoders (:c:type:`struct drm_encoder <drm_encoder>`)
+-----------------------------------------------------
+
+An encoder takes pixel data from a CRTC and converts it to a format
+suitable for any attached connectors. On some devices, it may be
+possible to have a CRTC send data to more than one encoder. In that
+case, both encoders would receive data from the same scanout buffer,
+resulting in a "cloned" display configuration across the connectors
+attached to each encoder.
+
+Encoder Initialization
+~~~~~~~~~~~~~~~~~~~~~~
+
+As for CRTCs, a KMS driver must create, initialize and register at least
+one :c:type:`struct drm_encoder <drm_encoder>` instance. The
+instance is allocated and zeroed by the driver, possibly as part of a
+larger structure.
+
+Drivers must initialize the :c:type:`struct drm_encoder
+<drm_encoder>` possible_crtcs and possible_clones fields before
+registering the encoder. Both fields are bitmasks of respectively the
+CRTCs that the encoder can be connected to, and sibling encoders
+candidate for cloning.
+
+After being initialized, the encoder must be registered with a call to
+:c:func:`drm_encoder_init()`. The function takes a pointer to the
+encoder functions and an encoder type. Supported types are
+
+-  DRM_MODE_ENCODER_DAC for VGA and analog on DVI-I/DVI-A
+-  DRM_MODE_ENCODER_TMDS for DVI, HDMI and (embedded) DisplayPort
+-  DRM_MODE_ENCODER_LVDS for display panels
+-  DRM_MODE_ENCODER_TVDAC for TV output (Composite, S-Video,
+   Component, SCART)
+-  DRM_MODE_ENCODER_VIRTUAL for virtual machine displays
+
+Encoders must be attached to a CRTC to be used. DRM drivers leave
+encoders unattached at initialization time. Applications (or the fbdev
+compatibility layer when implemented) are responsible for attaching the
+encoders they want to use to a CRTC.
+
+Connectors (:c:type:`struct drm_connector <drm_connector>`)
+-----------------------------------------------------------
+
+A connector is the final destination for pixel data on a device, and
+usually connects directly to an external display device like a monitor
+or laptop panel. A connector can only be attached to one encoder at a
+time. The connector is also the structure where information about the
+attached display is kept, so it contains fields for display data, EDID
+data, DPMS & connection status, and information about modes supported on
+the attached displays.
+
+Connector Initialization
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Finally a KMS driver must create, initialize, register and attach at
+least one :c:type:`struct drm_connector <drm_connector>`
+instance. The instance is created as other KMS objects and initialized
+by setting the following fields.
+
+interlace_allowed
+    Whether the connector can handle interlaced modes.
+
+doublescan_allowed
+    Whether the connector can handle doublescan.
+
+display_info
+    Display information is filled from EDID information when a display
+    is detected. For non hot-pluggable displays such as flat panels in
+    embedded systems, the driver should initialize the
+    display_info.width_mm and display_info.height_mm fields with the
+    physical size of the display.
+
+polled
+    Connector polling mode, a combination of
+
+    DRM_CONNECTOR_POLL_HPD
+        The connector generates hotplug events and doesn't need to be
+        periodically polled. The CONNECT and DISCONNECT flags must not
+        be set together with the HPD flag.
+
+    DRM_CONNECTOR_POLL_CONNECT
+        Periodically poll the connector for connection.
+
+    DRM_CONNECTOR_POLL_DISCONNECT
+        Periodically poll the connector for disconnection.
+
+    Set to 0 for connectors that don't support connection status
+    discovery.
+
+The connector is then registered with a call to
+:c:func:`drm_connector_init()` with a pointer to the connector
+functions and a connector type, and exposed through sysfs with a call to
+:c:func:`drm_connector_register()`.
+
+Supported connector types are
+
+-  DRM_MODE_CONNECTOR_VGA
+-  DRM_MODE_CONNECTOR_DVII
+-  DRM_MODE_CONNECTOR_DVID
+-  DRM_MODE_CONNECTOR_DVIA
+-  DRM_MODE_CONNECTOR_Composite
+-  DRM_MODE_CONNECTOR_SVIDEO
+-  DRM_MODE_CONNECTOR_LVDS
+-  DRM_MODE_CONNECTOR_Component
+-  DRM_MODE_CONNECTOR_9PinDIN
+-  DRM_MODE_CONNECTOR_DisplayPort
+-  DRM_MODE_CONNECTOR_HDMIA
+-  DRM_MODE_CONNECTOR_HDMIB
+-  DRM_MODE_CONNECTOR_TV
+-  DRM_MODE_CONNECTOR_eDP
+-  DRM_MODE_CONNECTOR_VIRTUAL
+
+Connectors must be attached to an encoder to be used. For devices that
+map connectors to encoders 1:1, the connector should be attached at
+initialization time with a call to
+:c:func:`drm_mode_connector_attach_encoder()`. The driver must
+also set the :c:type:`struct drm_connector <drm_connector>`
+encoder field to point to the attached encoder.
+
+Finally, drivers must initialize the connectors state change detection
+with a call to :c:func:`drm_kms_helper_poll_init()`. If at least
+one connector is pollable but can't generate hotplug interrupts
+(indicated by the DRM_CONNECTOR_POLL_CONNECT and
+DRM_CONNECTOR_POLL_DISCONNECT connector flags), a delayed work will
+automatically be queued to periodically poll for changes. Connectors
+that can generate hotplug interrupts must be marked with the
+DRM_CONNECTOR_POLL_HPD flag instead, and their interrupt handler must
+call :c:func:`drm_helper_hpd_irq_event()`. The function will
+queue a delayed work to check the state of all connectors, but no
+periodic polling will be done.
+
+Connector Operations
+~~~~~~~~~~~~~~~~~~~~
+
+    **Note**
+
+    Unless otherwise state, all operations are mandatory.
+
+DPMS
+''''
+
+void (\*dpms)(struct drm_connector \*connector, int mode);
+The DPMS operation sets the power state of a connector. The mode
+argument is one of
+
+-  DRM_MODE_DPMS_ON
+
+-  DRM_MODE_DPMS_STANDBY
+
+-  DRM_MODE_DPMS_SUSPEND
+
+-  DRM_MODE_DPMS_OFF
+
+In all but DPMS_ON mode the encoder to which the connector is attached
+should put the display in low-power mode by driving its signals
+appropriately. If more than one connector is attached to the encoder
+care should be taken not to change the power state of other displays as
+a side effect. Low-power mode should be propagated to the encoders and
+CRTCs when all related connectors are put in low-power mode.
+
+Modes
+'''''
+
+int (\*fill_modes)(struct drm_connector \*connector, uint32_t
+max_width, uint32_t max_height);
+Fill the mode list with all supported modes for the connector. If the
+``max_width`` and ``max_height`` arguments are non-zero, the
+implementation must ignore all modes wider than ``max_width`` or higher
+than ``max_height``.
+
+The connector must also fill in this operation its display_info
+width_mm and height_mm fields with the connected display physical size
+in millimeters. The fields should be set to 0 if the value isn't known
+or is not applicable (for instance for projector devices).
+
+Connection Status
+'''''''''''''''''
+
+The connection status is updated through polling or hotplug events when
+supported (see ?). The status value is reported to userspace through
+ioctls and must not be used inside the driver, as it only gets
+initialized by a call to :c:func:`drm_mode_getconnector()` from
+userspace.
+
+enum drm_connector_status (\*detect)(struct drm_connector
+\*connector, bool force);
+Check to see if anything is attached to the connector. The ``force``
+parameter is set to false whilst polling or to true when checking the
+connector due to user request. ``force`` can be used by the driver to
+avoid expensive, destructive operations during automated probing.
+
+Return connector_status_connected if something is connected to the
+connector, connector_status_disconnected if nothing is connected and
+connector_status_unknown if the connection state isn't known.
+
+Drivers should only return connector_status_connected if the
+connection status has really been probed as connected. Connectors that
+can't detect the connection status, or failed connection status probes,
+should return connector_status_unknown.
+
+Cleanup
+-------
+
+The DRM core manages its objects' lifetime. When an object is not needed
+anymore the core calls its destroy function, which must clean up and
+free every resource allocated for the object. Every
+:c:func:`drm_\*_init()` call must be matched with a corresponding
+:c:func:`drm_\*_cleanup()` call to cleanup CRTCs
+(:c:func:`drm_crtc_cleanup()`), planes
+(:c:func:`drm_plane_cleanup()`), encoders
+(:c:func:`drm_encoder_cleanup()`) and connectors
+(:c:func:`drm_connector_cleanup()`). Furthermore, connectors that
+have been added to sysfs must be removed by a call to
+:c:func:`drm_connector_unregister()` before calling
+:c:func:`drm_connector_cleanup()`.
+
+Connectors state change detection must be cleanup up with a call to
+:c:func:`drm_kms_helper_poll_fini()`.
+
+Output discovery and initialization example
+-------------------------------------------
+
+::
+
+    void intel_crt_init(struct drm_device *dev)
+    {
+        struct drm_connector *connector;
+        struct intel_output *intel_output;
+
+        intel_output = kzalloc(sizeof(struct intel_output), GFP_KERNEL);
+        if (!intel_output)
+            return;
+
+        connector = &intel_output->base;
+        drm_connector_init(dev, &intel_output->base,
+                   &intel_crt_connector_funcs, DRM_MODE_CONNECTOR_VGA);
+
+        drm_encoder_init(dev, &intel_output->enc, &intel_crt_enc_funcs,
+                 DRM_MODE_ENCODER_DAC);
+
+        drm_mode_connector_attach_encoder(&intel_output->base,
+                          &intel_output->enc);
+
+        /* Set up the DDC bus. */
+        intel_output->ddc_bus = intel_i2c_create(dev, GPIOA, "CRTDDC_A");
+        if (!intel_output->ddc_bus) {
+            dev_printk(KERN_ERR, &dev->pdev->dev, "DDC bus registration "
+                   "failed.\n");
+            return;
+        }
+
+        intel_output->type = INTEL_OUTPUT_ANALOG;
+        connector->interlace_allowed = 0;
+        connector->doublescan_allowed = 0;
+
+        drm_encoder_helper_add(&intel_output->enc, &intel_crt_helper_funcs);
+        drm_connector_helper_add(connector, &intel_crt_connector_helper_funcs);
+
+        drm_connector_register(connector);
+    }
+
+In the example above (taken from the i915 driver), a CRTC, connector and
+encoder combination is created. A device-specific i2c bus is also
+created for fetching EDID data and performing monitor detection. Once
+the process is complete, the new connector is registered with sysfs to
+make its properties available to applications.
+
+KMS API Functions
+-----------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_crtc.c
+   :export:
+
+KMS Data Structures
+-------------------
+
+.. kernel-doc:: include/drm/drm_crtc.h
+   :internal:
+
+KMS Locking
+-----------
+
+.. kernel-doc:: drivers/gpu/drm/drm_modeset_lock.c
+   :doc: kms locking
+
+.. kernel-doc:: include/drm/drm_modeset_lock.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_modeset_lock.c
+   :export:
+
+KMS Properties
+==============
+
+Drivers may need to expose additional parameters to applications than
+those described in the previous sections. KMS supports attaching
+properties to CRTCs, connectors and planes and offers a userspace API to
+list, get and set the property values.
+
+Properties are identified by a name that uniquely defines the property
+purpose, and store an associated value. For all property types except
+blob properties the value is a 64-bit unsigned integer.
+
+KMS differentiates between properties and property instances. Drivers
+first create properties and then create and associate individual
+instances of those properties to objects. A property can be instantiated
+multiple times and associated with different objects. Values are stored
+in property instances, and all other property information are stored in
+the property and shared between all instances of the property.
+
+Every property is created with a type that influences how the KMS core
+handles the property. Supported property types are
+
+DRM_MODE_PROP_RANGE
+    Range properties report their minimum and maximum admissible values.
+    The KMS core verifies that values set by application fit in that
+    range.
+
+DRM_MODE_PROP_ENUM
+    Enumerated properties take a numerical value that ranges from 0 to
+    the number of enumerated values defined by the property minus one,
+    and associate a free-formed string name to each value. Applications
+    can retrieve the list of defined value-name pairs and use the
+    numerical value to get and set property instance values.
+
+DRM_MODE_PROP_BITMASK
+    Bitmask properties are enumeration properties that additionally
+    restrict all enumerated values to the 0..63 range. Bitmask property
+    instance values combine one or more of the enumerated bits defined
+    by the property.
+
+DRM_MODE_PROP_BLOB
+    Blob properties store a binary blob without any format restriction.
+    The binary blobs are created as KMS standalone objects, and blob
+    property instance values store the ID of their associated blob
+    object.
+
+    Blob properties are only used for the connector EDID property and
+    cannot be created by drivers.
+
+To create a property drivers call one of the following functions
+depending on the property type. All property creation functions take
+property flags and name, as well as type-specific arguments.
+
+-  struct drm_property \*drm_property_create_range(struct
+   drm_device \*dev, int flags, const char \*name, uint64_t min,
+   uint64_t max);
+   Create a range property with the given minimum and maximum values.
+
+-  struct drm_property \*drm_property_create_enum(struct drm_device
+   \*dev, int flags, const char \*name, const struct
+   drm_prop_enum_list \*props, int num_values);
+   Create an enumerated property. The ``props`` argument points to an
+   array of ``num_values`` value-name pairs.
+
+-  struct drm_property \*drm_property_create_bitmask(struct
+   drm_device \*dev, int flags, const char \*name, const struct
+   drm_prop_enum_list \*props, int num_values);
+   Create a bitmask property. The ``props`` argument points to an array
+   of ``num_values`` value-name pairs.
+
+Properties can additionally be created as immutable, in which case they
+will be read-only for applications but can be modified by the driver. To
+create an immutable property drivers must set the
+DRM_MODE_PROP_IMMUTABLE flag at property creation time.
+
+When no array of value-name pairs is readily available at property
+creation time for enumerated or range properties, drivers can create the
+property using the :c:func:`drm_property_create()` function and
+manually add enumeration value-name pairs by calling the
+:c:func:`drm_property_add_enum()` function. Care must be taken to
+properly specify the property type through the ``flags`` argument.
+
+After creating properties drivers can attach property instances to CRTC,
+connector and plane objects by calling the
+:c:func:`drm_object_attach_property()`. The function takes a
+pointer to the target object, a pointer to the previously created
+property and an initial instance value.
+
+Existing KMS Properties
+-----------------------
+
+The following table gives description of drm properties exposed by
+various modules/drivers.
+
+.. csv-table::
+   :header-rows: 1
+   :file: kms-properties.csv
+
+Vertical Blanking
+=================
+
+Vertical blanking plays a major role in graphics rendering. To achieve
+tear-free display, users must synchronize page flips and/or rendering to
+vertical blanking. The DRM API offers ioctls to perform page flips
+synchronized to vertical blanking and wait for vertical blanking.
+
+The DRM core handles most of the vertical blanking management logic,
+which involves filtering out spurious interrupts, keeping race-free
+blanking counters, coping with counter wrap-around and resets and
+keeping use counts. It relies on the driver to generate vertical
+blanking interrupts and optionally provide a hardware vertical blanking
+counter. Drivers must implement the following operations.
+
+-  int (\*enable_vblank) (struct drm_device \*dev, int crtc); void
+   (\*disable_vblank) (struct drm_device \*dev, int crtc);
+   Enable or disable vertical blanking interrupts for the given CRTC.
+
+-  u32 (\*get_vblank_counter) (struct drm_device \*dev, int crtc);
+   Retrieve the value of the vertical blanking counter for the given
+   CRTC. If the hardware maintains a vertical blanking counter its value
+   should be returned. Otherwise drivers can use the
+   :c:func:`drm_vblank_count()` helper function to handle this
+   operation.
+
+Drivers must initialize the vertical blanking handling core with a call
+to :c:func:`drm_vblank_init()` in their load operation.
+
+Vertical blanking interrupts can be enabled by the DRM core or by
+drivers themselves (for instance to handle page flipping operations).
+The DRM core maintains a vertical blanking use count to ensure that the
+interrupts are not disabled while a user still needs them. To increment
+the use count, drivers call :c:func:`drm_vblank_get()`. Upon
+return vertical blanking interrupts are guaranteed to be enabled.
+
+To decrement the use count drivers call
+:c:func:`drm_vblank_put()`. Only when the use count drops to zero
+will the DRM core disable the vertical blanking interrupts after a delay
+by scheduling a timer. The delay is accessible through the
+vblankoffdelay module parameter or the ``drm_vblank_offdelay`` global
+variable and expressed in milliseconds. Its default value is 5000 ms.
+Zero means never disable, and a negative value means disable
+immediately. Drivers may override the behaviour by setting the
+:c:type:`struct drm_device <drm_device>`
+vblank_disable_immediate flag, which when set causes vblank interrupts
+to be disabled immediately regardless of the drm_vblank_offdelay
+value. The flag should only be set if there's a properly working
+hardware vblank counter present.
+
+When a vertical blanking interrupt occurs drivers only need to call the
+:c:func:`drm_handle_vblank()` function to account for the
+interrupt.
+
+Resources allocated by :c:func:`drm_vblank_init()` must be freed
+with a call to :c:func:`drm_vblank_cleanup()` in the driver unload
+operation handler.
+
+Vertical Blanking and Interrupt Handling Functions Reference
+------------------------------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_irq.c
+   :export:
+
+.. kernel-doc:: include/drm/drm_irq.h
+   :internal:
diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst
new file mode 100644
index 000000000000..59f9822fecd0
--- /dev/null
+++ b/Documentation/gpu/drm-mm.rst
@@ -0,0 +1,454 @@
+=====================
+DRM Memory Management
+=====================
+
+Modern Linux systems require large amount of graphics memory to store
+frame buffers, textures, vertices and other graphics-related data. Given
+the very dynamic nature of many of that data, managing graphics memory
+efficiently is thus crucial for the graphics stack and plays a central
+role in the DRM infrastructure.
+
+The DRM core includes two memory managers, namely Translation Table Maps
+(TTM) and Graphics Execution Manager (GEM). TTM was the first DRM memory
+manager to be developed and tried to be a one-size-fits-them all
+solution. It provides a single userspace API to accommodate the need of
+all hardware, supporting both Unified Memory Architecture (UMA) devices
+and devices with dedicated video RAM (i.e. most discrete video cards).
+This resulted in a large, complex piece of code that turned out to be
+hard to use for driver development.
+
+GEM started as an Intel-sponsored project in reaction to TTM's
+complexity. Its design philosophy is completely different: instead of
+providing a solution to every graphics memory-related problems, GEM
+identified common code between drivers and created a support library to
+share it. GEM has simpler initialization and execution requirements than
+TTM, but has no video RAM management capabilities and is thus limited to
+UMA devices.
+
+The Translation Table Manager (TTM)
+-----------------------------------
+
+TTM design background and information belongs here.
+
+TTM initialization
+~~~~~~~~~~~~~~~~~~
+
+    **Warning**
+
+    This section is outdated.
+
+Drivers wishing to support TTM must fill out a drm_bo_driver
+structure. The structure contains several fields with function pointers
+for initializing the TTM, allocating and freeing memory, waiting for
+command completion and fence synchronization, and memory migration. See
+the radeon_ttm.c file for an example of usage.
+
+The ttm_global_reference structure is made up of several fields:
+
+::
+
+              struct ttm_global_reference {
+                      enum ttm_global_types global_type;
+                      size_t size;
+                      void *object;
+                      int (*init) (struct ttm_global_reference *);
+                      void (*release) (struct ttm_global_reference *);
+              };
+
+
+There should be one global reference structure for your memory manager
+as a whole, and there will be others for each object created by the
+memory manager at runtime. Your global TTM should have a type of
+TTM_GLOBAL_TTM_MEM. The size field for the global object should be
+sizeof(struct ttm_mem_global), and the init and release hooks should
+point at your driver-specific init and release routines, which probably
+eventually call ttm_mem_global_init and ttm_mem_global_release,
+respectively.
+
+Once your global TTM accounting structure is set up and initialized by
+calling ttm_global_item_ref() on it, you need to create a buffer
+object TTM to provide a pool for buffer object allocation by clients and
+the kernel itself. The type of this object should be
+TTM_GLOBAL_TTM_BO, and its size should be sizeof(struct
+ttm_bo_global). Again, driver-specific init and release functions may
+be provided, likely eventually calling ttm_bo_global_init() and
+ttm_bo_global_release(), respectively. Also, like the previous
+object, ttm_global_item_ref() is used to create an initial reference
+count for the TTM, which will call your initialization function.
+
+The Graphics Execution Manager (GEM)
+------------------------------------
+
+The GEM design approach has resulted in a memory manager that doesn't
+provide full coverage of all (or even all common) use cases in its
+userspace or kernel API. GEM exposes a set of standard memory-related
+operations to userspace and a set of helper functions to drivers, and
+let drivers implement hardware-specific operations with their own
+private API.
+
+The GEM userspace API is described in the `GEM - the Graphics Execution
+Manager <http://lwn.net/Articles/283798/>`__ article on LWN. While
+slightly outdated, the document provides a good overview of the GEM API
+principles. Buffer allocation and read and write operations, described
+as part of the common GEM API, are currently implemented using
+driver-specific ioctls.
+
+GEM is data-agnostic. It manages abstract buffer objects without knowing
+what individual buffers contain. APIs that require knowledge of buffer
+contents or purpose, such as buffer allocation or synchronization
+primitives, are thus outside of the scope of GEM and must be implemented
+using driver-specific ioctls.
+
+On a fundamental level, GEM involves several operations:
+
+-  Memory allocation and freeing
+-  Command execution
+-  Aperture management at command execution time
+
+Buffer object allocation is relatively straightforward and largely
+provided by Linux's shmem layer, which provides memory to back each
+object.
+
+Device-specific operations, such as command execution, pinning, buffer
+read & write, mapping, and domain ownership transfers are left to
+driver-specific ioctls.
+
+GEM Initialization
+~~~~~~~~~~~~~~~~~~
+
+Drivers that use GEM must set the DRIVER_GEM bit in the struct
+:c:type:`struct drm_driver <drm_driver>` driver_features
+field. The DRM core will then automatically initialize the GEM core
+before calling the load operation. Behind the scene, this will create a
+DRM Memory Manager object which provides an address space pool for
+object allocation.
+
+In a KMS configuration, drivers need to allocate and initialize a
+command ring buffer following core GEM initialization if required by the
+hardware. UMA devices usually have what is called a "stolen" memory
+region, which provides space for the initial framebuffer and large,
+contiguous memory regions required by the device. This space is
+typically not managed by GEM, and must be initialized separately into
+its own DRM MM object.
+
+GEM Objects Creation
+~~~~~~~~~~~~~~~~~~~~
+
+GEM splits creation of GEM objects and allocation of the memory that
+backs them in two distinct operations.
+
+GEM objects are represented by an instance of struct :c:type:`struct
+drm_gem_object <drm_gem_object>`. Drivers usually need to
+extend GEM objects with private information and thus create a
+driver-specific GEM object structure type that embeds an instance of
+struct :c:type:`struct drm_gem_object <drm_gem_object>`.
+
+To create a GEM object, a driver allocates memory for an instance of its
+specific GEM object type and initializes the embedded struct
+:c:type:`struct drm_gem_object <drm_gem_object>` with a call
+to :c:func:`drm_gem_object_init()`. The function takes a pointer
+to the DRM device, a pointer to the GEM object and the buffer object
+size in bytes.
+
+GEM uses shmem to allocate anonymous pageable memory.
+:c:func:`drm_gem_object_init()` will create an shmfs file of the
+requested size and store it into the struct :c:type:`struct
+drm_gem_object <drm_gem_object>` filp field. The memory is
+used as either main storage for the object when the graphics hardware
+uses system memory directly or as a backing store otherwise.
+
+Drivers are responsible for the actual physical pages allocation by
+calling :c:func:`shmem_read_mapping_page_gfp()` for each page.
+Note that they can decide to allocate pages when initializing the GEM
+object, or to delay allocation until the memory is needed (for instance
+when a page fault occurs as a result of a userspace memory access or
+when the driver needs to start a DMA transfer involving the memory).
+
+Anonymous pageable memory allocation is not always desired, for instance
+when the hardware requires physically contiguous system memory as is
+often the case in embedded devices. Drivers can create GEM objects with
+no shmfs backing (called private GEM objects) by initializing them with
+a call to :c:func:`drm_gem_private_object_init()` instead of
+:c:func:`drm_gem_object_init()`. Storage for private GEM objects
+must be managed by drivers.
+
+GEM Objects Lifetime
+~~~~~~~~~~~~~~~~~~~~
+
+All GEM objects are reference-counted by the GEM core. References can be
+acquired and release by :c:func:`calling
+drm_gem_object_reference()` and
+:c:func:`drm_gem_object_unreference()` respectively. The caller
+must hold the :c:type:`struct drm_device <drm_device>`
+struct_mutex lock when calling
+:c:func:`drm_gem_object_reference()`. As a convenience, GEM
+provides :c:func:`drm_gem_object_unreference_unlocked()`
+functions that can be called without holding the lock.
+
+When the last reference to a GEM object is released the GEM core calls
+the :c:type:`struct drm_driver <drm_driver>` gem_free_object
+operation. That operation is mandatory for GEM-enabled drivers and must
+free the GEM object and all associated resources.
+
+void (\*gem_free_object) (struct drm_gem_object \*obj); Drivers are
+responsible for freeing all GEM object resources. This includes the
+resources created by the GEM core, which need to be released with
+:c:func:`drm_gem_object_release()`.
+
+GEM Objects Naming
+~~~~~~~~~~~~~~~~~~
+
+Communication between userspace and the kernel refers to GEM objects
+using local handles, global names or, more recently, file descriptors.
+All of those are 32-bit integer values; the usual Linux kernel limits
+apply to the file descriptors.
+
+GEM handles are local to a DRM file. Applications get a handle to a GEM
+object through a driver-specific ioctl, and can use that handle to refer
+to the GEM object in other standard or driver-specific ioctls. Closing a
+DRM file handle frees all its GEM handles and dereferences the
+associated GEM objects.
+
+To create a handle for a GEM object drivers call
+:c:func:`drm_gem_handle_create()`. The function takes a pointer
+to the DRM file and the GEM object and returns a locally unique handle.
+When the handle is no longer needed drivers delete it with a call to
+:c:func:`drm_gem_handle_delete()`. Finally the GEM object
+associated with a handle can be retrieved by a call to
+:c:func:`drm_gem_object_lookup()`.
+
+Handles don't take ownership of GEM objects, they only take a reference
+to the object that will be dropped when the handle is destroyed. To
+avoid leaking GEM objects, drivers must make sure they drop the
+reference(s) they own (such as the initial reference taken at object
+creation time) as appropriate, without any special consideration for the
+handle. For example, in the particular case of combined GEM object and
+handle creation in the implementation of the dumb_create operation,
+drivers must drop the initial reference to the GEM object before
+returning the handle.
+
+GEM names are similar in purpose to handles but are not local to DRM
+files. They can be passed between processes to reference a GEM object
+globally. Names can't be used directly to refer to objects in the DRM
+API, applications must convert handles to names and names to handles
+using the DRM_IOCTL_GEM_FLINK and DRM_IOCTL_GEM_OPEN ioctls
+respectively. The conversion is handled by the DRM core without any
+driver-specific support.
+
+GEM also supports buffer sharing with dma-buf file descriptors through
+PRIME. GEM-based drivers must use the provided helpers functions to
+implement the exporting and importing correctly. See ?. Since sharing
+file descriptors is inherently more secure than the easily guessable and
+global GEM names it is the preferred buffer sharing mechanism. Sharing
+buffers through GEM names is only supported for legacy userspace.
+Furthermore PRIME also allows cross-device buffer sharing since it is
+based on dma-bufs.
+
+GEM Objects Mapping
+~~~~~~~~~~~~~~~~~~~
+
+Because mapping operations are fairly heavyweight GEM favours
+read/write-like access to buffers, implemented through driver-specific
+ioctls, over mapping buffers to userspace. However, when random access
+to the buffer is needed (to perform software rendering for instance),
+direct access to the object can be more efficient.
+
+The mmap system call can't be used directly to map GEM objects, as they
+don't have their own file handle. Two alternative methods currently
+co-exist to map GEM objects to userspace. The first method uses a
+driver-specific ioctl to perform the mapping operation, calling
+:c:func:`do_mmap()` under the hood. This is often considered
+dubious, seems to be discouraged for new GEM-enabled drivers, and will
+thus not be described here.
+
+The second method uses the mmap system call on the DRM file handle. void
+\*mmap(void \*addr, size_t length, int prot, int flags, int fd, off_t
+offset); DRM identifies the GEM object to be mapped by a fake offset
+passed through the mmap offset argument. Prior to being mapped, a GEM
+object must thus be associated with a fake offset. To do so, drivers
+must call :c:func:`drm_gem_create_mmap_offset()` on the object.
+
+Once allocated, the fake offset value must be passed to the application
+in a driver-specific way and can then be used as the mmap offset
+argument.
+
+The GEM core provides a helper method :c:func:`drm_gem_mmap()` to
+handle object mapping. The method can be set directly as the mmap file
+operation handler. It will look up the GEM object based on the offset
+value and set the VMA operations to the :c:type:`struct drm_driver
+<drm_driver>` gem_vm_ops field. Note that
+:c:func:`drm_gem_mmap()` doesn't map memory to userspace, but
+relies on the driver-provided fault handler to map pages individually.
+
+To use :c:func:`drm_gem_mmap()`, drivers must fill the struct
+:c:type:`struct drm_driver <drm_driver>` gem_vm_ops field
+with a pointer to VM operations.
+
+struct vm_operations_struct \*gem_vm_ops struct
+vm_operations_struct { void (\*open)(struct vm_area_struct \* area);
+void (\*close)(struct vm_area_struct \* area); int (\*fault)(struct
+vm_area_struct \*vma, struct vm_fault \*vmf); };
+
+The open and close operations must update the GEM object reference
+count. Drivers can use the :c:func:`drm_gem_vm_open()` and
+:c:func:`drm_gem_vm_close()` helper functions directly as open
+and close handlers.
+
+The fault operation handler is responsible for mapping individual pages
+to userspace when a page fault occurs. Depending on the memory
+allocation scheme, drivers can allocate pages at fault time, or can
+decide to allocate memory for the GEM object at the time the object is
+created.
+
+Drivers that want to map the GEM object upfront instead of handling page
+faults can implement their own mmap file operation handler.
+
+Memory Coherency
+~~~~~~~~~~~~~~~~
+
+When mapped to the device or used in a command buffer, backing pages for
+an object are flushed to memory and marked write combined so as to be
+coherent with the GPU. Likewise, if the CPU accesses an object after the
+GPU has finished rendering to the object, then the object must be made
+coherent with the CPU's view of memory, usually involving GPU cache
+flushing of various kinds. This core CPU<->GPU coherency management is
+provided by a device-specific ioctl, which evaluates an object's current
+domain and performs any necessary flushing or synchronization to put the
+object into the desired coherency domain (note that the object may be
+busy, i.e. an active render target; in that case, setting the domain
+blocks the client and waits for rendering to complete before performing
+any necessary flushing operations).
+
+Command Execution
+~~~~~~~~~~~~~~~~~
+
+Perhaps the most important GEM function for GPU devices is providing a
+command execution interface to clients. Client programs construct
+command buffers containing references to previously allocated memory
+objects, and then submit them to GEM. At that point, GEM takes care to
+bind all the objects into the GTT, execute the buffer, and provide
+necessary synchronization between clients accessing the same buffers.
+This often involves evicting some objects from the GTT and re-binding
+others (a fairly expensive operation), and providing relocation support
+which hides fixed GTT offsets from clients. Clients must take care not
+to submit command buffers that reference more objects than can fit in
+the GTT; otherwise, GEM will reject them and no rendering will occur.
+Similarly, if several objects in the buffer require fence registers to
+be allocated for correct rendering (e.g. 2D blits on pre-965 chips),
+care must be taken not to require more fence registers than are
+available to the client. Such resource management should be abstracted
+from the client in libdrm.
+
+GEM Function Reference
+----------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_gem.c
+   :export:
+
+.. kernel-doc:: include/drm/drm_gem.h
+   :internal:
+
+VMA Offset Manager
+------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_vma_manager.c
+   :doc: vma offset manager
+
+.. kernel-doc:: drivers/gpu/drm/drm_vma_manager.c
+   :export:
+
+.. kernel-doc:: include/drm/drm_vma_manager.h
+   :internal:
+
+PRIME Buffer Sharing
+--------------------
+
+PRIME is the cross device buffer sharing framework in drm, originally
+created for the OPTIMUS range of multi-gpu platforms. To userspace PRIME
+buffers are dma-buf based file descriptors.
+
+Overview and Driver Interface
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Similar to GEM global names, PRIME file descriptors are also used to
+share buffer objects across processes. They offer additional security:
+as file descriptors must be explicitly sent over UNIX domain sockets to
+be shared between applications, they can't be guessed like the globally
+unique GEM names.
+
+Drivers that support the PRIME API must set the DRIVER_PRIME bit in the
+struct :c:type:`struct drm_driver <drm_driver>`
+driver_features field, and implement the prime_handle_to_fd and
+prime_fd_to_handle operations.
+
+int (\*prime_handle_to_fd)(struct drm_device \*dev, struct drm_file
+\*file_priv, uint32_t handle, uint32_t flags, int \*prime_fd); int
+(\*prime_fd_to_handle)(struct drm_device \*dev, struct drm_file
+\*file_priv, int prime_fd, uint32_t \*handle); Those two operations
+convert a handle to a PRIME file descriptor and vice versa. Drivers must
+use the kernel dma-buf buffer sharing framework to manage the PRIME file
+descriptors. Similar to the mode setting API PRIME is agnostic to the
+underlying buffer object manager, as long as handles are 32bit unsigned
+integers.
+
+While non-GEM drivers must implement the operations themselves, GEM
+drivers must use the :c:func:`drm_gem_prime_handle_to_fd()` and
+:c:func:`drm_gem_prime_fd_to_handle()` helper functions. Those
+helpers rely on the driver gem_prime_export and gem_prime_import
+operations to create a dma-buf instance from a GEM object (dma-buf
+exporter role) and to create a GEM object from a dma-buf instance
+(dma-buf importer role).
+
+struct dma_buf \* (\*gem_prime_export)(struct drm_device \*dev,
+struct drm_gem_object \*obj, int flags); struct drm_gem_object \*
+(\*gem_prime_import)(struct drm_device \*dev, struct dma_buf
+\*dma_buf); These two operations are mandatory for GEM drivers that
+support PRIME.
+
+PRIME Helper Functions
+~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/drm_prime.c
+   :doc: PRIME Helpers
+
+PRIME Function References
+-------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_prime.c
+   :export:
+
+DRM MM Range Allocator
+----------------------
+
+Overview
+~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/drm_mm.c
+   :doc: Overview
+
+LRU Scan/Eviction Support
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/drm_mm.c
+   :doc: lru scan roaster
+
+DRM MM Range Allocator Function References
+------------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_mm.c
+   :export:
+
+.. kernel-doc:: include/drm/drm_mm.h
+   :internal:
+
+CMA Helper Functions Reference
+------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_gem_cma_helper.c
+   :doc: cma helpers
+
+.. kernel-doc:: drivers/gpu/drm/drm_gem_cma_helper.c
+   :export:
+
+.. kernel-doc:: include/drm/drm_gem_cma_helper.h
+   :internal:
diff --git a/Documentation/gpu/drm-uapi.rst b/Documentation/gpu/drm-uapi.rst
new file mode 100644
index 000000000000..536bf3eaadd4
--- /dev/null
+++ b/Documentation/gpu/drm-uapi.rst
@@ -0,0 +1,111 @@
+===================
+Userland interfaces
+===================
+
+The DRM core exports several interfaces to applications, generally
+intended to be used through corresponding libdrm wrapper functions. In
+addition, drivers export device-specific interfaces for use by userspace
+drivers & device-aware applications through ioctls and sysfs files.
+
+External interfaces include: memory mapping, context management, DMA
+operations, AGP management, vblank control, fence management, memory
+management, and output management.
+
+Cover generic ioctls and sysfs layout here. We only need high-level
+info, since man pages should cover the rest.
+
+libdrm Device Lookup
+====================
+
+.. kernel-doc:: drivers/gpu/drm/drm_ioctl.c
+   :doc: getunique and setversion story
+
+
+Primary Nodes, DRM Master and Authentication
+============================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_auth.c
+   :doc: master and authentication
+
+.. kernel-doc:: drivers/gpu/drm/drm_auth.c
+   :export:
+
+.. kernel-doc:: include/drm/drm_auth.h
+   :internal:
+
+Render nodes
+============
+
+DRM core provides multiple character-devices for user-space to use.
+Depending on which device is opened, user-space can perform a different
+set of operations (mainly ioctls). The primary node is always created
+and called card<num>. Additionally, a currently unused control node,
+called controlD<num> is also created. The primary node provides all
+legacy operations and historically was the only interface used by
+userspace. With KMS, the control node was introduced. However, the
+planned KMS control interface has never been written and so the control
+node stays unused to date.
+
+With the increased use of offscreen renderers and GPGPU applications,
+clients no longer require running compositors or graphics servers to
+make use of a GPU. But the DRM API required unprivileged clients to
+authenticate to a DRM-Master prior to getting GPU access. To avoid this
+step and to grant clients GPU access without authenticating, render
+nodes were introduced. Render nodes solely serve render clients, that
+is, no modesetting or privileged ioctls can be issued on render nodes.
+Only non-global rendering commands are allowed. If a driver supports
+render nodes, it must advertise it via the DRIVER_RENDER DRM driver
+capability. If not supported, the primary node must be used for render
+clients together with the legacy drmAuth authentication procedure.
+
+If a driver advertises render node support, DRM core will create a
+separate render node called renderD<num>. There will be one render node
+per device. No ioctls except PRIME-related ioctls will be allowed on
+this node. Especially GEM_OPEN will be explicitly prohibited. Render
+nodes are designed to avoid the buffer-leaks, which occur if clients
+guess the flink names or mmap offsets on the legacy interface.
+Additionally to this basic interface, drivers must mark their
+driver-dependent render-only ioctls as DRM_RENDER_ALLOW so render
+clients can use them. Driver authors must be careful not to allow any
+privileged ioctls on render nodes.
+
+With render nodes, user-space can now control access to the render node
+via basic file-system access-modes. A running graphics server which
+authenticates clients on the privileged primary/legacy node is no longer
+required. Instead, a client can open the render node and is immediately
+granted GPU access. Communication between clients (or servers) is done
+via PRIME. FLINK from render node to legacy node is not supported. New
+clients must not use the insecure FLINK interface.
+
+Besides dropping all modeset/global ioctls, render nodes also drop the
+DRM-Master concept. There is no reason to associate render clients with
+a DRM-Master as they are independent of any graphics server. Besides,
+they must work without any running master, anyway. Drivers must be able
+to run without a master object if they support render nodes. If, on the
+other hand, a driver requires shared state between clients which is
+visible to user-space and accessible beyond open-file boundaries, they
+cannot support render nodes.
+
+VBlank event handling
+=====================
+
+The DRM core exposes two vertical blank related ioctls:
+
+DRM_IOCTL_WAIT_VBLANK
+    This takes a struct drm_wait_vblank structure as its argument, and
+    it is used to block or request a signal when a specified vblank
+    event occurs.
+
+DRM_IOCTL_MODESET_CTL
+    This was only used for user-mode-settind drivers around modesetting
+    changes to allow the kernel to update the vblank interrupt after
+    mode setting, since on many devices the vertical blank counter is
+    reset to 0 at some point during modeset. Modern drivers should not
+    call this any more since with kernel mode setting it is a no-op.
+
+This second part of the GPU Driver Developer's Guide documents driver
+code, implementation details and also all the driver-specific userspace
+interfaces. Especially since all hardware-acceleration interfaces to
+userspace are driver specific for efficiency and other reasons these
+interfaces can be rather substantial. Hence every driver has its own
+chapter.
diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
new file mode 100644
index 000000000000..2fe5952e90f1
--- /dev/null
+++ b/Documentation/gpu/i915.rst
@@ -0,0 +1,347 @@
+===========================
+ drm/i915 Intel GFX Driver
+===========================
+
+The drm/i915 driver supports all (with the exception of some very early
+models) integrated GFX chipsets with both Intel display and rendering
+blocks. This excludes a set of SoC platforms with an SGX rendering unit,
+those have basic support through the gma500 drm driver.
+
+Core Driver Infrastructure
+==========================
+
+This section covers core driver infrastructure used by both the display
+and the GEM parts of the driver.
+
+Runtime Power Management
+------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_runtime_pm.c
+   :doc: runtime pm
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_runtime_pm.c
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_uncore.c
+   :internal:
+
+Interrupt Handling
+------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_irq.c
+   :doc: interrupt handling
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_irq.c
+   :functions: intel_irq_init intel_irq_init_hw intel_hpd_init
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_irq.c
+   :functions: intel_runtime_pm_disable_interrupts
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_irq.c
+   :functions: intel_runtime_pm_enable_interrupts
+
+Intel GVT-g Guest Support(vGPU)
+-------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_vgpu.c
+   :doc: Intel GVT-g guest support
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_vgpu.c
+   :internal:
+
+Display Hardware Handling
+=========================
+
+This section covers everything related to the display hardware including
+the mode setting infrastructure, plane, sprite and cursor handling and
+display, output probing and related topics.
+
+Mode Setting Infrastructure
+---------------------------
+
+The i915 driver is thus far the only DRM driver which doesn't use the
+common DRM helper code to implement mode setting sequences. Thus it has
+its own tailor-made infrastructure for executing a display configuration
+change.
+
+Frontbuffer Tracking
+--------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_frontbuffer.c
+   :doc: frontbuffer tracking
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_frontbuffer.c
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem.c
+   :functions: i915_gem_track_fb
+
+Display FIFO Underrun Reporting
+-------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_fifo_underrun.c
+   :doc: fifo underrun handling
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_fifo_underrun.c
+   :internal:
+
+Plane Configuration
+-------------------
+
+This section covers plane configuration and composition with the primary
+plane, sprites, cursors and overlays. This includes the infrastructure
+to do atomic vsync'ed updates of all this state and also tightly coupled
+topics like watermark setup and computation, framebuffer compression and
+panel self refresh.
+
+Atomic Plane Helpers
+--------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_atomic_plane.c
+   :doc: atomic plane helpers
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_atomic_plane.c
+   :internal:
+
+Output Probing
+--------------
+
+This section covers output probing and related infrastructure like the
+hotplug interrupt storm detection and mitigation code. Note that the
+i915 driver still uses most of the common DRM helper code for output
+probing, so those sections fully apply.
+
+Hotplug
+-------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_hotplug.c
+   :doc: Hotplug
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_hotplug.c
+   :internal:
+
+High Definition Audio
+---------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_audio.c
+   :doc: High Definition Audio over HDMI and Display Port
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_audio.c
+   :internal:
+
+.. kernel-doc:: include/drm/i915_component.h
+   :internal:
+
+Panel Self Refresh PSR (PSR/SRD)
+--------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_psr.c
+   :doc: Panel Self Refresh (PSR/SRD)
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_psr.c
+   :internal:
+
+Frame Buffer Compression (FBC)
+------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_fbc.c
+   :doc: Frame Buffer Compression (FBC)
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_fbc.c
+   :internal:
+
+Display Refresh Rate Switching (DRRS)
+-------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_dp.c
+   :doc: Display Refresh Rate Switching (DRRS)
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_dp.c
+   :functions: intel_dp_set_drrs_state
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_dp.c
+   :functions: intel_edp_drrs_enable
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_dp.c
+   :functions: intel_edp_drrs_disable
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_dp.c
+   :functions: intel_edp_drrs_invalidate
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_dp.c
+   :functions: intel_edp_drrs_flush
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_dp.c
+   :functions: intel_dp_drrs_init
+
+DPIO
+----
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_reg.h
+   :doc: DPIO
+
+CSR firmware support for DMC
+----------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_csr.c
+   :doc: csr support for dmc
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_csr.c
+   :internal:
+
+Video BIOS Table (VBT)
+----------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_bios.c
+   :doc: Video BIOS Table (VBT)
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_bios.c
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_vbt_defs.h
+   :internal:
+
+Memory Management and Command Submission
+========================================
+
+This sections covers all things related to the GEM implementation in the
+i915 driver.
+
+Batchbuffer Parsing
+-------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_cmd_parser.c
+   :doc: batch buffer command parser
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_cmd_parser.c
+   :internal:
+
+Batchbuffer Pools
+-----------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_batch_pool.c
+   :doc: batch pool
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_batch_pool.c
+   :internal:
+
+Logical Rings, Logical Ring Contexts and Execlists
+--------------------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_lrc.c
+   :doc: Logical Rings, Logical Ring Contexts and Execlists
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_lrc.c
+   :internal:
+
+Global GTT views
+----------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_gtt.c
+   :doc: Global GTT views
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_gtt.c
+   :internal:
+
+GTT Fences and Swizzling
+------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_fence.c
+   :internal:
+
+Global GTT Fence Handling
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_fence.c
+   :doc: fence register handling
+
+Hardware Tiling and Swizzling Details
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_fence.c
+   :doc: tiling swizzling details
+
+Object Tiling IOCTLs
+--------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_tiling.c
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_tiling.c
+   :doc: buffer object tiling
+
+Buffer Object Eviction
+----------------------
+
+This section documents the interface functions for evicting buffer
+objects to make space available in the virtual gpu address spaces. Note
+that this is mostly orthogonal to shrinking buffer objects caches, which
+has the goal to make main memory (shared with the gpu through the
+unified memory architecture) available.
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_evict.c
+   :internal:
+
+Buffer Object Memory Shrinking
+------------------------------
+
+This section documents the interface function for shrinking memory usage
+of buffer object caches. Shrinking is used to make main memory
+available. Note that this is mostly orthogonal to evicting buffer
+objects, which has the goal to make space in gpu virtual address spaces.
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_shrinker.c
+   :internal:
+
+GuC
+===
+
+GuC-specific firmware loader
+----------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_loader.c
+   :doc: GuC-specific firmware loader
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_loader.c
+   :internal:
+
+GuC-based command submission
+----------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_guc_submission.c
+   :doc: GuC-based command submission
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_guc_submission.c
+   :internal:
+
+GuC Firmware Layout
+-------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_fwif.h
+   :doc: GuC Firmware Layout
+
+Tracing
+=======
+
+This sections covers all things related to the tracepoints implemented
+in the i915 driver.
+
+i915_ppgtt_create and i915_ppgtt_release
+----------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_trace.h
+   :doc: i915_ppgtt_create and i915_ppgtt_release tracepoints
+
+i915_context_create and i915_context_free
+-----------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_trace.h
+   :doc: i915_context_create and i915_context_free tracepoints
+
+switch_mm
+---------
+
+.. kernel-doc:: drivers/gpu/drm/i915/i915_trace.h
+   :doc: switch_mm tracepoint
+
+.. WARNING: DOCPROC directive not supported: !Cdrivers/gpu/drm/i915/i915_irq.c
diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst
new file mode 100644
index 000000000000..fcac0fa72056
--- /dev/null
+++ b/Documentation/gpu/index.rst
@@ -0,0 +1,14 @@
+==================================
+Linux GPU Driver Developer's Guide
+==================================
+
+.. toctree::
+
+   introduction
+   drm-internals
+   drm-mm
+   drm-kms
+   drm-kms-helpers
+   drm-uapi
+   i915
+   vga-switcheroo
diff --git a/Documentation/gpu/introduction.rst b/Documentation/gpu/introduction.rst
new file mode 100644
index 000000000000..1903595b5310
--- /dev/null
+++ b/Documentation/gpu/introduction.rst
@@ -0,0 +1,51 @@
+============
+Introduction
+============
+
+The Linux DRM layer contains code intended to support the needs of
+complex graphics devices, usually containing programmable pipelines well
+suited to 3D graphics acceleration. Graphics drivers in the kernel may
+make use of DRM functions to make tasks like memory management,
+interrupt handling and DMA easier, and provide a uniform interface to
+applications.
+
+A note on versions: this guide covers features found in the DRM tree,
+including the TTM memory manager, output configuration and mode setting,
+and the new vblank internals, in addition to all the regular features
+found in current kernels.
+
+[Insert diagram of typical DRM stack here]
+
+Style Guidelines
+================
+
+For consistency this documentation uses American English. Abbreviations
+are written as all-uppercase, for example: DRM, KMS, IOCTL, CRTC, and so
+on. To aid in reading, documentations make full use of the markup
+characters kerneldoc provides: @parameter for function parameters,
+@member for structure members, &structure to reference structures and
+function() for functions. These all get automatically hyperlinked if
+kerneldoc for the referenced objects exists. When referencing entries in
+function vtables please use ->vfunc(). Note that kerneldoc does not
+support referencing struct members directly, so please add a reference
+to the vtable struct somewhere in the same paragraph or at least
+section.
+
+Except in special situations (to separate locked from unlocked variants)
+locking requirements for functions aren't documented in the kerneldoc.
+Instead locking should be check at runtime using e.g.
+``WARN_ON(!mutex_is_locked(...));``. Since it's much easier to ignore
+documentation than runtime noise this provides more value. And on top of
+that runtime checks do need to be updated when the locking rules change,
+increasing the chances that they're correct. Within the documentation
+the locking rules should be explained in the relevant structures: Either
+in the comment for the lock explaining what it protects, or data fields
+need a note about which lock protects them, or both.
+
+Functions which have a non-\ ``void`` return value should have a section
+called "Returns" explaining the expected return values in different
+cases and their meanings. Currently there's no consensus whether that
+section name should be all upper-case or not, and whether it should end
+in a colon or not. Go with the file-local style. Other common section
+names are "Notes" with information for dangerous or tricky corner cases,
+and "FIXME" where the interface could be cleaned up.
diff --git a/Documentation/gpu/kms-properties.csv b/Documentation/gpu/kms-properties.csv
new file mode 100644
index 000000000000..b6fcaf639c04
--- /dev/null
+++ b/Documentation/gpu/kms-properties.csv
@@ -0,0 +1,128 @@
+Owner Module/Drivers,Group,Property Name,Type,Property Values,Object attached,Description/Restrictions
+DRM,Generic,“rotation”,BITMASK,"{ 0, ""rotate-0"" }, { 1, ""rotate-90"" }, { 2, ""rotate-180"" }, { 3, ""rotate-270"" }, { 4, ""reflect-x"" }, { 5, ""reflect-y"" }","CRTC, Plane",rotate-(degrees) rotates the image by the specified amount in degrees in counter clockwise direction. reflect-x and reflect-y reflects the image along the specified axis prior to rotation
+,,“scaling mode”,ENUM,"{ ""None"", ""Full"", ""Center"", ""Full aspect"" }",Connector,"Supported by: amdgpu, gma500, i915, nouveau and radeon."
+,Connector,“EDID”,BLOB | IMMUTABLE,0,Connector,Contains id of edid blob ptr object.
+,,“DPMS”,ENUM,"{ “On”, “Standby”, “Suspend”, “Off” }",Connector,Contains DPMS operation mode value.
+,,“PATH”,BLOB | IMMUTABLE,0,Connector,Contains topology path to a connector.
+,,“TILE”,BLOB | IMMUTABLE,0,Connector,Contains tiling information for a connector.
+,,“CRTC_ID”,OBJECT,DRM_MODE_OBJECT_CRTC,Connector,CRTC that connector is attached to (atomic)
+,Plane,“type”,ENUM | IMMUTABLE,"{ ""Overlay"", ""Primary"", ""Cursor"" }",Plane,Plane type
+,,“SRC_X”,RANGE,"Min=0, Max=UINT_MAX",Plane,Scanout source x coordinate in 16.16 fixed point (atomic)
+,,“SRC_Y”,RANGE,"Min=0, Max=UINT_MAX",Plane,Scanout source y coordinate in 16.16 fixed point (atomic)
+,,“SRC_W”,RANGE,"Min=0, Max=UINT_MAX",Plane,Scanout source width in 16.16 fixed point (atomic)
+,,“SRC_H”,RANGE,"Min=0, Max=UINT_MAX",Plane,Scanout source height in 16.16 fixed point (atomic)
+,,“CRTC_X”,SIGNED_RANGE,"Min=INT_MIN, Max=INT_MAX",Plane,Scanout CRTC (destination) x coordinate (atomic)
+,,“CRTC_Y”,SIGNED_RANGE,"Min=INT_MIN, Max=INT_MAX",Plane,Scanout CRTC (destination) y coordinate (atomic)
+,,“CRTC_W”,RANGE,"Min=0, Max=UINT_MAX",Plane,Scanout CRTC (destination) width (atomic)
+,,“CRTC_H”,RANGE,"Min=0, Max=UINT_MAX",Plane,Scanout CRTC (destination) height (atomic)
+,,“FB_ID”,OBJECT,DRM_MODE_OBJECT_FB,Plane,Scanout framebuffer (atomic)
+,,“CRTC_ID”,OBJECT,DRM_MODE_OBJECT_CRTC,Plane,CRTC that plane is attached to (atomic)
+,DVI-I,“subconnector”,ENUM,"{ “Unknown”, “DVI-D”, “DVI-A” }",Connector,TBD
+,,“select subconnector”,ENUM,"{ “Automatic”, “DVI-D”, “DVI-A” }",Connector,TBD
+,TV,“subconnector”,ENUM,"{ ""Unknown"", ""Composite"", ""SVIDEO"", ""Component"", ""SCART"" }",Connector,TBD
+,,“select subconnector”,ENUM,"{ ""Automatic"", ""Composite"", ""SVIDEO"", ""Component"", ""SCART"" }",Connector,TBD
+,,“mode”,ENUM,"{ ""NTSC_M"", ""NTSC_J"", ""NTSC_443"", ""PAL_B"" } etc.",Connector,TBD
+,,“left margin”,RANGE,"Min=0, Max=100",Connector,TBD
+,,“right margin”,RANGE,"Min=0, Max=100",Connector,TBD
+,,“top margin”,RANGE,"Min=0, Max=100",Connector,TBD
+,,“bottom margin”,RANGE,"Min=0, Max=100",Connector,TBD
+,,“brightness”,RANGE,"Min=0, Max=100",Connector,TBD
+,,“contrast”,RANGE,"Min=0, Max=100",Connector,TBD
+,,“flicker reduction”,RANGE,"Min=0, Max=100",Connector,TBD
+,,“overscan”,RANGE,"Min=0, Max=100",Connector,TBD
+,,“saturation”,RANGE,"Min=0, Max=100",Connector,TBD
+,,“hue”,RANGE,"Min=0, Max=100",Connector,TBD
+,Virtual GPU,“suggested X”,RANGE,"Min=0, Max=0xffffffff",Connector,property to suggest an X offset for a connector
+,,“suggested Y”,RANGE,"Min=0, Max=0xffffffff",Connector,property to suggest an Y offset for a connector
+,Optional,"""aspect ratio""",ENUM,"{ ""None"", ""4:3"", ""16:9"" }",Connector,TDB
+,,“dirty”,ENUM | IMMUTABLE,"{ ""Off"", ""On"", ""Annotate"" }",Connector,TBD
+,,“DEGAMMA_LUT”,BLOB,0,CRTC,DRM property to set the degamma lookup table (LUT) mapping pixel data from the framebuffer before it is given to the transformation matrix. The data is an interpreted as an array of struct drm_color_lut elements. Hardware might choose not to use the full precision of the LUT elements nor use all the elements of the LUT (for example the hardware might choose to interpolate between LUT[0] and LUT[4]).
+,,“DEGAMMA_LUT_SIZE”,RANGE | IMMUTABLE,"Min=0, Max=UINT_MAX",CRTC,DRM property to gives the size of the lookup table to be set on the DEGAMMA_LUT property (the size depends on the underlying hardware).
+,,“CTM”,BLOB,0,CRTC,DRM property to set the current transformation matrix (CTM) apply to pixel data after the lookup through the degamma LUT and before the lookup through the gamma LUT. The data is an interpreted as a struct drm_color_ctm.
+,,“GAMMA_LUT”,BLOB,0,CRTC,DRM property to set the gamma lookup table (LUT) mapping pixel data after to the transformation matrix to data sent to the connector. The data is an interpreted as an array of struct drm_color_lut elements. Hardware might choose not to use the full precision of the LUT elements nor use all the elements of the LUT (for example the hardware might choose to interpolate between LUT[0] and LUT[4]).
+,,“GAMMA_LUT_SIZE”,RANGE | IMMUTABLE,"Min=0, Max=UINT_MAX",CRTC,DRM property to gives the size of the lookup table to be set on the GAMMA_LUT property (the size depends on the underlying hardware).
+i915,Generic,"""Broadcast RGB""",ENUM,"{ ""Automatic"", ""Full"", ""Limited 16:235"" }",Connector,"When this property is set to Limited 16:235 and CTM is set, the hardware will be programmed with the result of the multiplication of CTM by the limited range matrix to ensure the pixels normaly in the range 0..1.0 are remapped to the range 16/255..235/255."
+,,“audio”,ENUM,"{ ""force-dvi"", ""off"", ""auto"", ""on"" }",Connector,TBD
+,SDVO-TV,“mode”,ENUM,"{ ""NTSC_M"", ""NTSC_J"", ""NTSC_443"", ""PAL_B"" } etc.",Connector,TBD
+,,"""left_margin""",RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,"""right_margin""",RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,"""top_margin""",RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,"""bottom_margin""",RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“hpos”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“vpos”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“contrast”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“saturation”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“hue”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“sharpness”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“flicker_filter”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“flicker_filter_adaptive”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“flicker_filter_2d”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“tv_chroma_filter”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“tv_luma_filter”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“dot_crawl”,RANGE,"Min=0, Max=1",Connector,TBD
+,SDVO-TV/LVDS,“brightness”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+CDV gma-500,Generic,"""Broadcast RGB""",ENUM,"{ “Full”, “Limited 16:235” }",Connector,TBD
+,,"""Broadcast RGB""",ENUM,"{ “off”, “auto”, “on” }",Connector,TBD
+Poulsbo,Generic,“backlight”,RANGE,"Min=0, Max=100",Connector,TBD
+,SDVO-TV,“mode”,ENUM,"{ ""NTSC_M"", ""NTSC_J"", ""NTSC_443"", ""PAL_B"" } etc.",Connector,TBD
+,,"""left_margin""",RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,"""right_margin""",RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,"""top_margin""",RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,"""bottom_margin""",RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“hpos”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“vpos”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“contrast”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“saturation”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“hue”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“sharpness”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“flicker_filter”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“flicker_filter_adaptive”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“flicker_filter_2d”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“tv_chroma_filter”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“tv_luma_filter”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+,,“dot_crawl”,RANGE,"Min=0, Max=1",Connector,TBD
+,SDVO-TV/LVDS,“brightness”,RANGE,"Min=0, Max= SDVO dependent",Connector,TBD
+armada,CRTC,"""CSC_YUV""",ENUM,"{ ""Auto"" , ""CCIR601"", ""CCIR709"" }",CRTC,TBD
+,,"""CSC_RGB""",ENUM,"{ ""Auto"", ""Computer system"", ""Studio"" }",CRTC,TBD
+,Overlay,"""colorkey""",RANGE,"Min=0, Max=0xffffff",Plane,TBD
+,,"""colorkey_min""",RANGE,"Min=0, Max=0xffffff",Plane,TBD
+,,"""colorkey_max""",RANGE,"Min=0, Max=0xffffff",Plane,TBD
+,,"""colorkey_val""",RANGE,"Min=0, Max=0xffffff",Plane,TBD
+,,"""colorkey_alpha""",RANGE,"Min=0, Max=0xffffff",Plane,TBD
+,,"""colorkey_mode""",ENUM,"{ ""disabled"", ""Y component"", ""U component"" , ""V component"", ""RGB"", “R component"", ""G component"", ""B component"" }",Plane,TBD
+,,"""brightness""",RANGE,"Min=0, Max=256 + 255",Plane,TBD
+,,"""contrast""",RANGE,"Min=0, Max=0x7fff",Plane,TBD
+,,"""saturation""",RANGE,"Min=0, Max=0x7fff",Plane,TBD
+exynos,CRTC,“mode”,ENUM,"{ ""normal"", ""blank"" }",CRTC,TBD
+,Overlay,“zpos”,RANGE,"Min=0, Max=MAX_PLANE-1",Plane,TBD
+i2c/ch7006_drv,Generic,“scale”,RANGE,"Min=0, Max=2",Connector,TBD
+,TV,“mode”,ENUM,"{ ""PAL"", ""PAL-M"",""PAL-N""}, ”PAL-Nc"" , ""PAL-60"", ""NTSC-M"", ""NTSC-J"" }",Connector,TBD
+nouveau,NV10 Overlay,"""colorkey""",RANGE,"Min=0, Max=0x01ffffff",Plane,TBD
+,,“contrast”,RANGE,"Min=0, Max=8192-1",Plane,TBD
+,,“brightness”,RANGE,"Min=0, Max=1024",Plane,TBD
+,,“hue”,RANGE,"Min=0, Max=359",Plane,TBD
+,,“saturation”,RANGE,"Min=0, Max=8192-1",Plane,TBD
+,,“iturbt_709”,RANGE,"Min=0, Max=1",Plane,TBD
+,Nv04 Overlay,“colorkey”,RANGE,"Min=0, Max=0x01ffffff",Plane,TBD
+,,“brightness”,RANGE,"Min=0, Max=1024",Plane,TBD
+,Display,“dithering mode”,ENUM,"{ ""auto"", ""off"", ""on"" }",Connector,TBD
+,,“dithering depth”,ENUM,"{ ""auto"", ""off"", ""on"", ""static 2x2"", ""dynamic 2x2"", ""temporal"" }",Connector,TBD
+,,“underscan”,ENUM,"{ ""auto"", ""6 bpc"", ""8 bpc"" }",Connector,TBD
+,,“underscan hborder”,RANGE,"Min=0, Max=128",Connector,TBD
+,,“underscan vborder”,RANGE,"Min=0, Max=128",Connector,TBD
+,,“vibrant hue”,RANGE,"Min=0, Max=180",Connector,TBD
+,,“color vibrance”,RANGE,"Min=0, Max=200",Connector,TBD
+omap,Generic,“zorder”,RANGE,"Min=0, Max=3","CRTC, Plane",TBD
+qxl,Generic,"“hotplug_mode_update""",RANGE,"Min=0, Max=1",Connector,TBD
+radeon,DVI-I,“coherent”,RANGE,"Min=0, Max=1",Connector,TBD
+,DAC enable load detect,“load detection”,RANGE,"Min=0, Max=1",Connector,TBD
+,TV Standard,"""tv standard""",ENUM,"{ ""ntsc"", ""pal"", ""pal-m"", ""pal-60"", ""ntsc-j"" , ""scart-pal"", ""pal-cn"", ""secam"" }",Connector,TBD
+,legacy TMDS PLL detect,"""tmds_pll""",ENUM,"{ ""driver"", ""bios"" }",-,TBD
+,Underscan,"""underscan""",ENUM,"{ ""off"", ""on"", ""auto"" }",Connector,TBD
+,,"""underscan hborder""",RANGE,"Min=0, Max=128",Connector,TBD
+,,"""underscan vborder""",RANGE,"Min=0, Max=128",Connector,TBD
+,Audio,“audio”,ENUM,"{ ""off"", ""on"", ""auto"" }",Connector,TBD
+,FMT Dithering,“dither”,ENUM,"{ ""off"", ""on"" }",Connector,TBD
+rcar-du,Generic,"""alpha""",RANGE,"Min=0, Max=255",Plane,TBD
+,,"""colorkey""",RANGE,"Min=0, Max=0x01ffffff",Plane,TBD
+,,"""zpos""",RANGE,"Min=1, Max=7",Plane,TBD
diff --git a/Documentation/gpu/vga-switcheroo.rst b/Documentation/gpu/vga-switcheroo.rst
new file mode 100644
index 000000000000..cbbdb994f1dd
--- /dev/null
+++ b/Documentation/gpu/vga-switcheroo.rst
@@ -0,0 +1,98 @@
+.. _vga_switcheroo:
+
+==============
+VGA Switcheroo
+==============
+
+.. kernel-doc:: drivers/gpu/vga/vga_switcheroo.c
+   :doc: Overview
+
+Modes of Use
+============
+
+Manual switching and manual power control
+-----------------------------------------
+
+.. kernel-doc:: drivers/gpu/vga/vga_switcheroo.c
+   :doc: Manual switching and manual power control
+
+Driver power control
+--------------------
+
+.. kernel-doc:: drivers/gpu/vga/vga_switcheroo.c
+   :doc: Driver power control
+
+API
+===
+
+Public functions
+----------------
+
+.. kernel-doc:: drivers/gpu/vga/vga_switcheroo.c
+   :export:
+
+Public structures
+-----------------
+
+.. kernel-doc:: include/linux/vga_switcheroo.h
+   :functions: vga_switcheroo_handler
+
+.. kernel-doc:: include/linux/vga_switcheroo.h
+   :functions: vga_switcheroo_client_ops
+
+Public constants
+----------------
+
+.. kernel-doc:: include/linux/vga_switcheroo.h
+   :functions: vga_switcheroo_handler_flags_t
+
+.. kernel-doc:: include/linux/vga_switcheroo.h
+   :functions: vga_switcheroo_client_id
+
+.. kernel-doc:: include/linux/vga_switcheroo.h
+   :functions: vga_switcheroo_state
+
+Private structures
+------------------
+
+.. kernel-doc:: drivers/gpu/vga/vga_switcheroo.c
+   :functions: vgasr_priv
+
+.. kernel-doc:: drivers/gpu/vga/vga_switcheroo.c
+   :functions: vga_switcheroo_client
+
+Handlers
+========
+
+apple-gmux Handler
+------------------
+
+.. kernel-doc:: drivers/platform/x86/apple-gmux.c
+   :doc: Overview
+
+.. kernel-doc:: drivers/platform/x86/apple-gmux.c
+   :doc: Interrupt
+
+Graphics mux
+~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/platform/x86/apple-gmux.c
+   :doc: Graphics mux
+
+Power control
+~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/platform/x86/apple-gmux.c
+   :doc: Power control
+
+Backlight control
+~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/platform/x86/apple-gmux.c
+   :doc: Backlight control
+
+Public functions
+~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: include/linux/apple-gmux.h
+   :internal:
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 43c722f15292..e0fc72963e87 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -18,6 +18,7 @@ Contents:
    media/media_kapi
    media/dvb-drivers/index
    media/v4l-drivers/index
+   gpu/index
 
 Indices and tables
 ==================
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 56af5e43e9c0..81c7f2bb7daf 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -248,7 +248,7 @@ Code  Seq#(hex)	Include File		Comments
 'm'	00	drivers/scsi/megaraid/megaraid_ioctl.h	conflict!
 'm'	00-1F	net/irda/irmod.h	conflict!
 'n'	00-7F	linux/ncp_fs.h and fs/ncpfs/ioctl.c
-'n'	80-8F	linux/nilfs2_fs.h	NILFS2
+'n'	80-8F	uapi/linux/nilfs2_api.h	NILFS2
 'n'	E0-FF	linux/matroxfb.h	matroxfb
 'o'	00-1F	fs/ocfs2/ocfs2_fs.h	OCFS2
 'o'     00-03   mtd/ubi-user.h		conflict! (OCFS2 and UBI overlaps)
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 769db8399ac8..00e4c2f615a8 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -931,9 +931,18 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	dhash_entries=	[KNL]
 			Set number of hash buckets for dentry cache.
 
+	disable_1tb_segments [PPC]
+			Disables the use of 1TB hash page table segments. This
+			causes the kernel to fall back to 256MB segments which
+			can be useful when debugging issues that require an SLB
+			miss to occur.
+
 	disable=	[IPV6]
 			See Documentation/networking/ipv6.txt.
 
+	disable_radix	[PPC]
+			Disable RADIX MMU mode on POWER9
+
 	disable_cpu_apicid= [X86,APIC,SMP]
 			Format: <int>
 			The number of initial APIC ID for the
@@ -3012,6 +3021,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 		resource_alignment=
 				Format:
 				[<order of align>@][<domain>:]<bus>:<slot>.<func>[; ...]
+				[<order of align>@]pci:<vendor>:<device>\
+						[:<subvendor>:<subdevice>][; ...]
 				Specifies alignment and device to reassign
 				aligned memory resources.
 				If <order of align> is not specified,
@@ -3030,6 +3041,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 		hpmemsize=nn[KMG]	The fixed amount of bus space which is
 				reserved for hotplug bridge's memory window.
 				Default size is 2 megabytes.
+		hpbussize=nn	The minimum amount of additional bus numbers
+				reserved for buses below a hotplug bridge.
+				Default is 1.
 		realloc=	Enable/disable reallocating PCI bridge resources
 				if allocations done by BIOS are too small to
 				accommodate resources required by all child
@@ -3061,6 +3075,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 		compat	Treat PCIe ports as PCI-to-PCI bridges, disable the PCIe
 			ports driver.
 
+	pcie_port_pm=	[PCIE] PCIe port power management handling:
+		off	Disable power management of all PCIe ports
+		force	Forcibly enable power management of all PCIe ports
+
 	pcie_pme=	[PCIE,PM] Native PCIe PME signaling options:
 		nomsi	Do not use MSI for native PCIe PME signaling (this makes
 			all PCIe root ports use INTx for all services).
@@ -3164,6 +3182,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Format: <bool>  (1/Y/y=enable, 0/N/n=disable)
 			default: disabled
 
+	printk.devkmsg={on,off,ratelimit}
+			Control writing to /dev/kmsg.
+			on - unlimited logging to /dev/kmsg from userspace
+			off - logging to /dev/kmsg disabled
+			ratelimit - ratelimit the logging
+			Default: ratelimit
+
 	printk.time=	Show timing data prefixed to each printk message line
 			Format: <bool>  (1/Y/y=enable, 0/N/n=disable)
 
diff --git a/Documentation/mmc/mmc-dev-attrs.txt b/Documentation/mmc/mmc-dev-attrs.txt
index caa555706f89..404a0e9e92b0 100644
--- a/Documentation/mmc/mmc-dev-attrs.txt
+++ b/Documentation/mmc/mmc-dev-attrs.txt
@@ -28,6 +28,8 @@ All attributes are read-only.
 	preferred_erase_size	Preferred erase size
 	raw_rpmb_size_mult	RPMB partition size
 	rel_sectors		Reliable write sector count
+	ocr 			Operation Conditions Register
+	dsr			Driver Stage Register
 
 Note on Erase Size and Preferred Erase Size:
 
diff --git a/Documentation/rapidio/mport_cdev.txt b/Documentation/rapidio/mport_cdev.txt
index 20c120d4b3b8..6e491a662461 100644
--- a/Documentation/rapidio/mport_cdev.txt
+++ b/Documentation/rapidio/mport_cdev.txt
@@ -82,8 +82,7 @@ III. Module parameters
 
 - 'dbg_level' - This parameter allows to control amount of debug information
         generated by this device driver. This parameter is formed by set of
-        This parameter can be changed bit masks that correspond to the specific
-        functional block.
+        bit masks that correspond to the specific functional blocks.
         For mask definitions see 'drivers/rapidio/devices/rio_mport_cdev.c'
         This parameter can be changed dynamically.
         Use CONFIG_RAPIDIO_DEBUG=y to enable debug output at the top level.
diff --git a/Documentation/rapidio/rio_cm.txt b/Documentation/rapidio/rio_cm.txt
new file mode 100644
index 000000000000..27aa401f1126
--- /dev/null
+++ b/Documentation/rapidio/rio_cm.txt
@@ -0,0 +1,119 @@
+RapidIO subsystem Channelized Messaging character device driver (rio_cm.c)
+==========================================================================
+
+Version History:
+----------------
+  1.0.0 - Initial driver release.
+
+==========================================================================
+
+I. Overview
+
+This device driver is the result of collaboration within the RapidIO.org
+Software Task Group (STG) between Texas Instruments, Prodrive Technologies,
+Nokia Networks, BAE and IDT.  Additional input was received from other members
+of RapidIO.org.
+
+The objective was to create a character mode driver interface which exposes
+messaging capabilities of RapidIO endpoint devices (mports) directly
+to applications, in a manner that allows the numerous and varied RapidIO
+implementations to interoperate.
+
+This driver (RIO_CM) provides to user-space applications shared access to
+RapidIO mailbox messaging resources.
+
+RapidIO specification (Part 2) defines that endpoint devices may have up to four
+messaging mailboxes in case of multi-packet message (up to 4KB) and
+up to 64 mailboxes if single-packet messages (up to 256 B) are used. In addition
+to protocol definition limitations, a particular hardware implementation can
+have reduced number of messaging mailboxes.  RapidIO aware applications must
+therefore share the messaging resources of a RapidIO endpoint.
+
+Main purpose of this device driver is to provide RapidIO mailbox messaging
+capability to large number of user-space processes by introducing socket-like
+operations using a single messaging mailbox.  This allows applications to
+use the limited RapidIO messaging hardware resources efficiently.
+
+Most of device driver's operations are supported through 'ioctl' system calls.
+
+When loaded this device driver creates a single file system node named rio_cm
+in /dev directory common for all registered RapidIO mport devices.
+
+Following ioctl commands are available to user-space applications:
+
+- RIO_CM_MPORT_GET_LIST : Returns to caller list of local mport devices that
+    support messaging operations (number of entries up to RIO_MAX_MPORTS).
+    Each list entry is combination of mport's index in the system and RapidIO
+    destination ID assigned to the port.
+- RIO_CM_EP_GET_LIST_SIZE : Returns number of messaging capable remote endpoints
+    in a RapidIO network associated with the specified mport device.
+- RIO_CM_EP_GET_LIST : Returns list of RapidIO destination IDs for messaging
+    capable remote endpoints (peers) available in a RapidIO network associated
+    with the specified mport device.
+- RIO_CM_CHAN_CREATE : Creates RapidIO message exchange channel data structure
+    with channel ID assigned automatically or as requested by a caller.
+- RIO_CM_CHAN_BIND : Binds the specified channel data structure to the specified
+    mport device.
+- RIO_CM_CHAN_LISTEN : Enables listening for connection requests on the specified
+    channel.
+- RIO_CM_CHAN_ACCEPT : Accepts a connection request from peer on the specified
+    channel. If wait timeout for this request is specified by a caller it is
+    a blocking call. If timeout set to 0 this is non-blocking call - ioctl
+    handler checks for a pending connection request and if one is not available
+    exits with -EGAIN error status immediately.
+- RIO_CM_CHAN_CONNECT : Sends a connection request to a remote peer/channel.
+- RIO_CM_CHAN_SEND : Sends a data message through the specified channel.
+    The handler for this request assumes that message buffer specified by
+    a caller includes the reserved space for a packet header required by
+    this driver.
+- RIO_CM_CHAN_RECEIVE : Receives a data message through a connected channel.
+    If the channel does not have an incoming message ready to return this ioctl
+    handler will wait for new message until timeout specified by a caller
+    expires. If timeout value is set to 0, ioctl handler uses a default value
+    defined by MAX_SCHEDULE_TIMEOUT.
+- RIO_CM_CHAN_CLOSE : Closes a specified channel and frees associated buffers.
+    If the specified channel is in the CONNECTED state, sends close notification
+    to the remote peer.
+
+The ioctl command codes and corresponding data structures intended for use by
+user-space applications are defined in 'include/uapi/linux/rio_cm_cdev.h'.
+
+II. Hardware Compatibility
+
+This device driver uses standard interfaces defined by kernel RapidIO subsystem
+and therefore it can be used with any mport device driver registered by RapidIO
+subsystem with limitations set by available mport HW implementation of messaging
+mailboxes.
+
+III. Module parameters
+
+- 'dbg_level' - This parameter allows to control amount of debug information
+        generated by this device driver. This parameter is formed by set of
+        bit masks that correspond to the specific functional block.
+        For mask definitions see 'drivers/rapidio/devices/rio_cm.c'
+        This parameter can be changed dynamically.
+        Use CONFIG_RAPIDIO_DEBUG=y to enable debug output at the top level.
+
+- 'cmbox' - Number of RapidIO mailbox to use (default value is 1).
+        This parameter allows to set messaging mailbox number that will be used
+        within entire RapidIO network. It can be used when default mailbox is
+        used by other device drivers or is not supported by some nodes in the
+        RapidIO network.
+
+- 'chstart' - Start channel number for dynamic assignment. Default value - 256.
+        Allows to exclude channel numbers below this parameter from dynamic
+        allocation to avoid conflicts with software components that use
+        reserved predefined channel numbers.
+
+IV. Known problems
+
+  None.
+
+V. User-space Applications and API Library
+
+Messaging API library and applications that use this device driver are available
+from RapidIO.org.
+
+VI. TODO List
+
+- Add support for system notification messages (reserved channel 0).
diff --git a/Documentation/rapidio/tsi721.txt b/Documentation/rapidio/tsi721.txt
index 7c1c7bf48ec0..cd2a2935d51d 100644
--- a/Documentation/rapidio/tsi721.txt
+++ b/Documentation/rapidio/tsi721.txt
@@ -25,6 +25,32 @@ fully compatible with RIONET driver (Ethernet over RapidIO messaging services).
         This parameter can be changed dynamically.
         Use CONFIG_RAPIDIO_DEBUG=y to enable debug output at the top level.
 
+- 'dma_desc_per_channel' - This parameter defines number of hardware buffer
+        descriptors allocated for each registered Tsi721 DMA channel.
+        Its default value is 128.
+
+- 'dma_txqueue_sz' - DMA transactions queue size. Defines number of pending
+        transaction requests that can be accepted by each DMA channel.
+        Default value is 16.
+
+- 'dma_sel' - DMA channel selection mask. Bitmask that defines which hardware
+        DMA channels (0 ... 6) will be registered with DmaEngine core.
+        If bit is set to 1, the corresponding DMA channel will be registered.
+        DMA channels not selected by this mask will not be used by this device
+        driver. Default value is 0x7f (use all channels).
+
+- 'pcie_mrrs' - override value for PCIe Maximum Read Request Size (MRRS).
+        This parameter gives an ability to override MRRS value set during PCIe
+        configuration process. Tsi721 supports read request sizes up to 4096B.
+        Value for this parameter must be set as defined by PCIe specification:
+        0 = 128B, 1 = 256B, 2 = 512B, 3 = 1024B, 4 = 2048B and 5 = 4096B.
+        Default value is '-1' (= keep platform setting).
+
+- 'mbox_sel' - RIO messaging MBOX selection mask. This is a bitmask that defines
+        messaging MBOXes are managed by this device driver. Mask bits 0 - 3
+        correspond to MBOX0 - MBOX3. MBOX is under driver's control if the
+        corresponding bit is set to '1'. Default value is 0x0f (= all).
+
 II. Known problems
 
   None.
diff --git a/Documentation/sound/alsa/soc/machine.txt b/Documentation/sound/alsa/soc/machine.txt
index 74056dba52be..6bf2d2063b52 100644
--- a/Documentation/sound/alsa/soc/machine.txt
+++ b/Documentation/sound/alsa/soc/machine.txt
@@ -3,7 +3,7 @@ ASoC Machine Driver
 
 The ASoC machine (or board) driver is the code that glues together all the
 component drivers (e.g. codecs, platforms and DAIs). It also describes the
-relationships between each componnent which include audio paths, GPIOs,
+relationships between each component which include audio paths, GPIOs,
 interrupts, clocking, jacks and voltage regulators.
 
 The machine driver can contain codec and platform specific code. It registers
diff --git a/Documentation/sound/alsa/timestamping.txt b/Documentation/sound/alsa/timestamping.txt
index 1b6473f393a8..9d579aefbffd 100644
--- a/Documentation/sound/alsa/timestamping.txt
+++ b/Documentation/sound/alsa/timestamping.txt
@@ -14,7 +14,7 @@ provides a refined estimate with a delay.
 event or application query.
 The difference (tstamp - trigger_tstamp) defines the elapsed time.
 
-The ALSA API provides reports two basic pieces of information, avail
+The ALSA API provides two basic pieces of information, avail
 and delay, which combined with the trigger and current system
 timestamps allow for applications to keep track of the 'fullness' of
 the ring buffer and the amount of queued samples.
@@ -53,21 +53,21 @@ case):
 The analog time is taken at the last stage of the playback, as close
 as possible to the actual transducer
 
-The link time is taken at the output of the SOC/chipset as the samples
+The link time is taken at the output of the SoC/chipset as the samples
 are pushed on a link. The link time can be directly measured if
 supported in hardware by sample counters or wallclocks (e.g. with
 HDAudio 24MHz or PTP clock for networked solutions) or indirectly
 estimated (e.g. with the frame counter in USB).
 
 The DMA time is measured using counters - typically the least reliable
-of all measurements due to the bursty natured of DMA transfers.
+of all measurements due to the bursty nature of DMA transfers.
 
 The app time corresponds to the time tracked by an application after
 writing in the ring buffer.
 
-The application can query what the hardware supports, define which
+The application can query the hardware capabilities, define which
 audio time it wants reported by selecting the relevant settings in
-audio_tstamp_config fields, get an estimate of the timestamp
+audio_tstamp_config fields, thus get an estimate of the timestamp
 accuracy. It can also request the delay-to-analog be included in the
 measurement. Direct access to the link time is very interesting on
 platforms that provide an embedded DSP; measuring directly the link
@@ -169,7 +169,7 @@ playback: systime: 938107562 nsec, audio time 938112708 nsec, 	systime delta -51
 Example 1 shows that the timestamp at the DMA level is close to 1ms
 ahead of the actual playback time (as a side time this sort of
 measurement can help define rewind safeguards). Compensating for the
-DMA-link delay in example 2 helps remove the hardware buffering abut
+DMA-link delay in example 2 helps remove the hardware buffering but
 the information is still very jittery, with up to one sample of
 error. In example 3 where the timestamps are measured with the link
 wallclock, the timestamps show a monotonic behavior and a lower
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 33204604de6c..ffab8b5caa60 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -764,6 +764,20 @@ send before ratelimiting kicks in.
 
 ==============================================================
 
+printk_devkmsg:
+
+Control the logging to /dev/kmsg from userspace:
+
+ratelimit: default, ratelimited
+on: unlimited logging to /dev/kmsg from userspace
+off: logging to /dev/kmsg disabled
+
+The kernel command line parameter printk.devkmsg= overrides this and is
+a one-time setting until next reboot: once set, it cannot be changed by
+this sysctl interface anymore.
+
+==============================================================
+
 randomize_va_space:
 
 This option can be used to select the type of process address
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a4482cce4bae..5237e1b2fd66 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1482,6 +1482,11 @@ struct kvm_irq_routing_msi {
 	__u32 pad;
 };
 
+On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
+feature of KVM_CAP_X2APIC_API capability is enabled.  If it is enabled,
+address_hi bits 31-8 provide bits 31-8 of the destination id.  Bits 7-0 of
+address_hi must be zero.
+
 struct kvm_irq_routing_s390_adapter {
 	__u64 ind_addr;
 	__u64 summary_addr;
@@ -1583,6 +1588,17 @@ struct kvm_lapic_state {
 Reads the Local APIC registers and copies them into the input argument.  The
 data format and layout are the same as documented in the architecture manual.
 
+If KVM_X2APIC_API_USE_32BIT_IDS feature of KVM_CAP_X2APIC_API is
+enabled, then the format of APIC_ID register depends on the APIC mode
+(reported by MSR_IA32_APICBASE) of its VCPU.  x2APIC stores APIC ID in
+the APIC_ID register (bytes 32-35).  xAPIC only allows an 8-bit APIC ID
+which is stored in bits 31-24 of the APIC register, or equivalently in
+byte 35 of struct kvm_lapic_state's regs field.  KVM_GET_LAPIC must then
+be called after MSR_IA32_APICBASE has been set with KVM_SET_MSR.
+
+If KVM_X2APIC_API_USE_32BIT_IDS feature is disabled, struct kvm_lapic_state
+always uses xAPIC format.
+
 
 4.58 KVM_SET_LAPIC
 
@@ -1600,6 +1616,10 @@ struct kvm_lapic_state {
 Copies the input argument into the Local APIC registers.  The data format
 and layout are the same as documented in the architecture manual.
 
+The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's
+regs field) depends on the state of the KVM_CAP_X2APIC_API capability.
+See the note in KVM_GET_LAPIC.
+
 
 4.59 KVM_IOEVENTFD
 
@@ -2032,6 +2052,12 @@ registers, find a list below:
   MIPS  | KVM_REG_MIPS_CP0_CONFIG5      | 32
   MIPS  | KVM_REG_MIPS_CP0_CONFIG7      | 32
   MIPS  | KVM_REG_MIPS_CP0_ERROREPC     | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH1    | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH2    | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH3    | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH4    | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH5    | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH6    | 64
   MIPS  | KVM_REG_MIPS_COUNT_CTL        | 64
   MIPS  | KVM_REG_MIPS_COUNT_RESUME     | 64
   MIPS  | KVM_REG_MIPS_COUNT_HZ         | 64
@@ -2156,7 +2182,7 @@ after pausing the vcpu, but before it is resumed.
 4.71 KVM_SIGNAL_MSI
 
 Capability: KVM_CAP_SIGNAL_MSI
-Architectures: x86
+Architectures: x86 arm64
 Type: vm ioctl
 Parameters: struct kvm_msi (in)
 Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
@@ -2169,10 +2195,22 @@ struct kvm_msi {
 	__u32 address_hi;
 	__u32 data;
 	__u32 flags;
-	__u8  pad[16];
+	__u32 devid;
+	__u8  pad[12];
 };
 
-No flags are defined so far. The corresponding field must be 0.
+flags: KVM_MSI_VALID_DEVID: devid contains a valid value
+devid: If KVM_MSI_VALID_DEVID is set, contains a unique device identifier
+       for the device that wrote the MSI message.
+       For PCI, this is usually a BFD identifier in the lower 16 bits.
+
+The per-VM KVM_CAP_MSI_DEVID capability advertises the need to provide
+the device ID. If this capability is not set, userland cannot rely on
+the kernel to allow the KVM_MSI_VALID_DEVID flag being set.
+
+On x86, address_hi is ignored unless the KVM_CAP_X2APIC_API capability is
+enabled.  If it is enabled, address_hi bits 31-8 provide bits 31-8 of the
+destination id.  Bits 7-0 of address_hi must be zero.
 
 
 4.71 KVM_CREATE_PIT2
@@ -2520,6 +2558,7 @@ Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
   ENXIO:  The group or attribute is unknown/unsupported for this device
+          or hardware support is missing.
   EPERM:  The attribute cannot (currently) be accessed this way
           (e.g. read-only attribute, or attribute that only makes
           sense when the device is in a different state)
@@ -2547,6 +2586,7 @@ Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
   ENXIO:  The group or attribute is unknown/unsupported for this device
+          or hardware support is missing.
 
 Tests whether a device supports a particular attribute.  A successful
 return indicates the attribute is implemented.  It does not necessarily
@@ -3803,6 +3843,42 @@ Allows use of runtime-instrumentation introduced with zEC12 processor.
 Will return -EINVAL if the machine does not support runtime-instrumentation.
 Will return -EBUSY if a VCPU has already been created.
 
+7.7 KVM_CAP_X2APIC_API
+
+Architectures: x86
+Parameters: args[0] - features that should be enabled
+Returns: 0 on success, -EINVAL when args[0] contains invalid features
+
+Valid feature flags in args[0] are
+
+#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
+
+Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of
+KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC,
+allowing the use of 32-bit APIC IDs.  See KVM_CAP_X2APIC_API in their
+respective sections.
+
+KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK must be enabled for x2APIC to work
+in logical mode or with more than 255 VCPUs.  Otherwise, KVM treats 0xff
+as a broadcast even in x2APIC mode in order to support physical x2APIC
+without interrupt remapping.  This is undesirable in logical mode,
+where 0xff represents CPUs 0-7 in cluster 0.
+
+7.8 KVM_CAP_S390_USER_INSTR0
+
+Architectures: s390
+Parameters: none
+
+With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
+be intercepted and forwarded to user space. User space can use this
+mechanism e.g. to realize 2-byte software breakpoints. The kernel will
+not inject an operating exception for these instructions, user space has
+to take care of that.
+
+This capability can be enabled dynamically even if VCPUs were already
+created and are running.
+
 8. Other capabilities.
 ----------------------
 
diff --git a/Documentation/virtual/kvm/devices/arm-vgic.txt b/Documentation/virtual/kvm/devices/arm-vgic.txt
index 59541d49e15c..89182f80cc7f 100644
--- a/Documentation/virtual/kvm/devices/arm-vgic.txt
+++ b/Documentation/virtual/kvm/devices/arm-vgic.txt
@@ -4,16 +4,22 @@ ARM Virtual Generic Interrupt Controller (VGIC)
 Device types supported:
   KVM_DEV_TYPE_ARM_VGIC_V2     ARM Generic Interrupt Controller v2.0
   KVM_DEV_TYPE_ARM_VGIC_V3     ARM Generic Interrupt Controller v3.0
+  KVM_DEV_TYPE_ARM_VGIC_ITS    ARM Interrupt Translation Service Controller
 
-Only one VGIC instance may be instantiated through either this API or the
-legacy KVM_CREATE_IRQCHIP api.  The created VGIC will act as the VM interrupt
-controller, requiring emulated user-space devices to inject interrupts to the
-VGIC instead of directly to CPUs.
+Only one VGIC instance of the V2/V3 types above may be instantiated through
+either this API or the legacy KVM_CREATE_IRQCHIP api.  The created VGIC will
+act as the VM interrupt controller, requiring emulated user-space devices to
+inject interrupts to the VGIC instead of directly to CPUs.
 
 Creating a guest GICv3 device requires a host GICv3 as well.
 GICv3 implementations with hardware compatibility support allow a guest GICv2
 as well.
 
+Creating a virtual ITS controller requires a host GICv3 (but does not depend
+on having physical ITS controllers).
+There can be multiple ITS controllers per guest, each of them has to have
+a separate, non-overlapping MMIO region.
+
 Groups:
   KVM_DEV_ARM_VGIC_GRP_ADDR
   Attributes:
@@ -39,6 +45,13 @@ Groups:
       Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
       This address needs to be 64K aligned.
 
+    KVM_VGIC_V3_ADDR_TYPE_ITS (rw, 64-bit)
+      Base address in the guest physical address space of the GICv3 ITS
+      control register frame. The ITS allows MSI(-X) interrupts to be
+      injected into guests. This extension is optional. If the kernel
+      does not support the ITS, the call returns -ENODEV.
+      Only valid for KVM_DEV_TYPE_ARM_VGIC_ITS.
+      This address needs to be 64K aligned and the region covers 128K.
 
   KVM_DEV_ARM_VGIC_GRP_DIST_REGS
   Attributes:
@@ -109,8 +122,8 @@ Groups:
   KVM_DEV_ARM_VGIC_GRP_CTRL
   Attributes:
     KVM_DEV_ARM_VGIC_CTRL_INIT
-      request the initialization of the VGIC, no additional parameter in
-      kvm_device_attr.addr.
+      request the initialization of the VGIC or ITS, no additional parameter
+      in kvm_device_attr.addr.
   Errors:
     -ENXIO: VGIC not properly configured as required prior to calling
      this attribute
diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virtual/kvm/devices/vm.txt
index a9ea8774a45f..b6cda49f2ba4 100644
--- a/Documentation/virtual/kvm/devices/vm.txt
+++ b/Documentation/virtual/kvm/devices/vm.txt
@@ -20,7 +20,8 @@ Enables Collaborative Memory Management Assist (CMMA) for the virtual machine.
 
 1.2. ATTRIBUTE: KVM_S390_VM_MEM_CLR_CMMA
 Parameters: none
-Returns: 0
+Returns: -EINVAL if CMMA was not enabled
+         0 otherwise
 
 Clear the CMMA status for all guest pages, so any pages the guest marked
 as unused are again used any may not be reclaimed by the host.
@@ -85,6 +86,90 @@ Returns:    -EBUSY in case 1 or more vcpus are already activated (only in write
 	    -ENOMEM if not enough memory is available to process the ioctl
 	    0 in case of success
 
+2.3. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_FEAT (r/o)
+
+Allows user space to retrieve available cpu features. A feature is available if
+provided by the hardware and supported by kvm. In theory, cpu features could
+even be completely emulated by kvm.
+
+struct kvm_s390_vm_cpu_feat {
+        __u64 feat[16]; # Bitmap (1 = feature available), MSB 0 bit numbering
+};
+
+Parameters: address of a buffer to load the feature list from.
+Returns:    -EFAULT if the given address is not accessible from kernel space.
+	    0 in case of success.
+
+2.4. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_FEAT (r/w)
+
+Allows user space to retrieve or change enabled cpu features for all VCPUs of a
+VM. Features that are not available cannot be enabled.
+
+See 2.3. for a description of the parameter struct.
+
+Parameters: address of a buffer to store/load the feature list from.
+Returns:    -EFAULT if the given address is not accessible from kernel space.
+	    -EINVAL if a cpu feature that is not available is to be enabled.
+	    -EBUSY if at least one VCPU has already been defined.
+	    0 in case of success.
+
+2.5. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_SUBFUNC (r/o)
+
+Allows user space to retrieve available cpu subfunctions without any filtering
+done by a set IBC. These subfunctions are indicated to the guest VCPU via
+query or "test bit" subfunctions and used e.g. by cpacf functions, plo and ptff.
+
+A subfunction block is only valid if KVM_S390_VM_CPU_MACHINE contains the
+STFL(E) bit introducing the affected instruction. If the affected instruction
+indicates subfunctions via a "query subfunction", the response block is
+contained in the returned struct. If the affected instruction
+indicates subfunctions via a "test bit" mechanism, the subfunction codes are
+contained in the returned struct in MSB 0 bit numbering.
+
+struct kvm_s390_vm_cpu_subfunc {
+       u8 plo[32];           # always valid (ESA/390 feature)
+       u8 ptff[16];          # valid with TOD-clock steering
+       u8 kmac[16];          # valid with Message-Security-Assist
+       u8 kmc[16];           # valid with Message-Security-Assist
+       u8 km[16];            # valid with Message-Security-Assist
+       u8 kimd[16];          # valid with Message-Security-Assist
+       u8 klmd[16];          # valid with Message-Security-Assist
+       u8 pckmo[16];         # valid with Message-Security-Assist-Extension 3
+       u8 kmctr[16];         # valid with Message-Security-Assist-Extension 4
+       u8 kmf[16];           # valid with Message-Security-Assist-Extension 4
+       u8 kmo[16];           # valid with Message-Security-Assist-Extension 4
+       u8 pcc[16];           # valid with Message-Security-Assist-Extension 4
+       u8 ppno[16];          # valid with Message-Security-Assist-Extension 5
+       u8 reserved[1824];    # reserved for future instructions
+};
+
+Parameters: address of a buffer to load the subfunction blocks from.
+Returns:    -EFAULT if the given address is not accessible from kernel space.
+	    0 in case of success.
+
+2.6. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_SUBFUNC (r/w)
+
+Allows user space to retrieve or change cpu subfunctions to be indicated for
+all VCPUs of a VM. This attribute will only be available if kernel and
+hardware support are in place.
+
+The kernel uses the configured subfunction blocks for indication to
+the guest. A subfunction block will only be used if the associated STFL(E) bit
+has not been disabled by user space (so the instruction to be queried is
+actually available for the guest).
+
+As long as no data has been written, a read will fail. The IBC will be used
+to determine available subfunctions in this case, this will guarantee backward
+compatibility.
+
+See 2.5. for a description of the parameter struct.
+
+Parameters: address of a buffer to store/load the subfunction blocks from.
+Returns:    -EFAULT if the given address is not accessible from kernel space.
+	    -EINVAL when reading, if there was no write yet.
+	    -EBUSY if at least one VCPU has already been defined.
+	    0 in case of success.
+
 3. GROUP: KVM_S390_VM_TOD
 Architectures: s390
 
diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index 19f94a6b9bb0..f2491a8c68b4 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -89,7 +89,7 @@ In mmu_spte_clear_track_bits():
    old_spte = *spte;
 
    /* 'if' condition is satisfied. */
-   if (old_spte.Accssed == 1 &&
+   if (old_spte.Accessed == 1 &&
         old_spte.W == 0)
       spte = 0ull;
                                          on fast page fault path:
@@ -102,7 +102,7 @@ In mmu_spte_clear_track_bits():
       old_spte = xchg(spte, 0ull)
 
 
-   if (old_spte.Accssed == 1)
+   if (old_spte.Accessed == 1)
       kvm_set_pfn_accessed(spte.pfn);
    if (old_spte.Dirty == 1)
       kvm_set_pfn_dirty(spte.pfn);
diff --git a/Documentation/watchdog/hpwdt.txt b/Documentation/watchdog/hpwdt.txt
index a40398cce9d1..7a9f635d0258 100644
--- a/Documentation/watchdog/hpwdt.txt
+++ b/Documentation/watchdog/hpwdt.txt
@@ -1,9 +1,9 @@
-Last reviewed: 04/04/2016
+Last reviewed: 05/20/2016
 
                      HPE iLO NMI Watchdog Driver
               NMI sourcing for iLO based ProLiant Servers
                      Documentation and Driver by
-              Thomas Mingarelli <thomas.mingarelli@hpe.com>
+                         Thomas Mingarelli
 
  The HPE iLO NMI Watchdog driver is a kernel module that provides basic
  watchdog functionality and the added benefit of NMI sourcing. Both the
@@ -95,4 +95,3 @@ Last reviewed: 04/04/2016
 
 
  -- Tom Mingarelli
-    (thomas.mingarelli@hpe.com)
diff --git a/Documentation/watchdog/src/watchdog-test.c b/Documentation/watchdog/src/watchdog-test.c
index fcdde8fc98be..6983d05097e2 100644
--- a/Documentation/watchdog/src/watchdog-test.c
+++ b/Documentation/watchdog/src/watchdog-test.c
@@ -2,6 +2,7 @@
  * Watchdog Driver Test Program
  */
 
+#include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -13,6 +14,7 @@
 #include <linux/watchdog.h>
 
 int fd;
+const char v = 'V';
 
 /*
  * This function simply sends an IOCTL to the driver, which in turn ticks
@@ -23,6 +25,7 @@ static void keep_alive(void)
 {
     int dummy;
 
+    printf(".");
     ioctl(fd, WDIOC_KEEPALIVE, &dummy);
 }
 
@@ -33,8 +36,13 @@ static void keep_alive(void)
 
 static void term(int sig)
 {
+    int ret = write(fd, &v, 1);
+
     close(fd);
-    fprintf(stderr, "Stopping watchdog ticks...\n");
+    if (ret < 0)
+	printf("\nStopping watchdog ticks failed (%d)...\n", errno);
+    else
+	printf("\nStopping watchdog ticks...\n");
     exit(0);
 }
 
@@ -42,12 +50,14 @@ int main(int argc, char *argv[])
 {
     int flags;
     unsigned int ping_rate = 1;
+    int ret;
+
+    setbuf(stdout, NULL);
 
     fd = open("/dev/watchdog", O_WRONLY);
 
     if (fd == -1) {
-	fprintf(stderr, "Watchdog device not enabled.\n");
-	fflush(stderr);
+	printf("Watchdog device not enabled.\n");
 	exit(-1);
     }
 
@@ -55,36 +65,30 @@ int main(int argc, char *argv[])
 	if (!strncasecmp(argv[1], "-d", 2)) {
 	    flags = WDIOS_DISABLECARD;
 	    ioctl(fd, WDIOC_SETOPTIONS, &flags);
-	    fprintf(stderr, "Watchdog card disabled.\n");
-	    fflush(stderr);
+	    printf("Watchdog card disabled.\n");
 	    goto end;
 	} else if (!strncasecmp(argv[1], "-e", 2)) {
 	    flags = WDIOS_ENABLECARD;
 	    ioctl(fd, WDIOC_SETOPTIONS, &flags);
-	    fprintf(stderr, "Watchdog card enabled.\n");
-	    fflush(stderr);
+	    printf("Watchdog card enabled.\n");
 	    goto end;
 	} else if (!strncasecmp(argv[1], "-t", 2) && argv[2]) {
 	    flags = atoi(argv[2]);
 	    ioctl(fd, WDIOC_SETTIMEOUT, &flags);
-	    fprintf(stderr, "Watchdog timeout set to %u seconds.\n", flags);
-	    fflush(stderr);
+	    printf("Watchdog timeout set to %u seconds.\n", flags);
 	    goto end;
 	} else if (!strncasecmp(argv[1], "-p", 2) && argv[2]) {
 	    ping_rate = strtoul(argv[2], NULL, 0);
-	    fprintf(stderr, "Watchdog ping rate set to %u seconds.\n", ping_rate);
-	    fflush(stderr);
+	    printf("Watchdog ping rate set to %u seconds.\n", ping_rate);
 	} else {
-	    fprintf(stderr, "-d to disable, -e to enable, -t <n> to set " \
+	    printf("-d to disable, -e to enable, -t <n> to set " \
 		"the timeout,\n-p <n> to set the ping rate, and \n");
-	    fprintf(stderr, "run by itself to tick the card.\n");
-	    fflush(stderr);
+	    printf("run by itself to tick the card.\n");
 	    goto end;
 	}
     }
 
-    fprintf(stderr, "Watchdog Ticking Away!\n");
-    fflush(stderr);
+    printf("Watchdog Ticking Away!\n");
 
     signal(SIGINT, term);
 
@@ -93,6 +97,9 @@ int main(int argc, char *argv[])
 	sleep(ping_rate);
     }
 end:
+    ret = write(fd, &v, 1);
+    if (ret < 0)
+	printf("Stopping watchdog ticks failed (%d)...\n", errno);
     close(fd);
     return 0;
 }
diff --git a/Documentation/watchdog/watchdog-kernel-api.txt b/Documentation/watchdog/watchdog-kernel-api.txt
index 917eeeabfa5e..7f31125c123e 100644
--- a/Documentation/watchdog/watchdog-kernel-api.txt
+++ b/Documentation/watchdog/watchdog-kernel-api.txt
@@ -82,8 +82,9 @@ It contains following fields:
 * max_timeout: the watchdog timer's maximum timeout value (in seconds),
   as seen from userspace. If set, the maximum configurable value for
   'timeout'. Not used if max_hw_heartbeat_ms is non-zero.
-* min_hw_heartbeat_ms: Minimum time between heartbeats sent to the chip,
-  in milli-seconds.
+* min_hw_heartbeat_ms: Hardware limit for minimum time between heartbeats,
+  in milli-seconds. This value is normally 0; it should only be provided
+  if the hardware can not tolerate lower intervals between heartbeats.
 * max_hw_heartbeat_ms: Maximum hardware heartbeat, in milli-seconds.
   If set, the infrastructure will send heartbeats to the watchdog driver
   if 'timeout' is larger than max_hw_heartbeat_ms, unless WDOG_ACTIVE
@@ -166,6 +167,10 @@ they are supported. These optional routines/operations are:
   info structure).
 * status: this routine checks the status of the watchdog timer device. The
   status of the device is reported with watchdog WDIOF_* status flags/bits.
+  WDIOF_MAGICCLOSE and WDIOF_KEEPALIVEPING are reported by the watchdog core;
+  it is not necessary to report those bits from the driver. Also, if no status
+  function is provided by the driver, the watchdog core reports the status bits
+  provided in the bootstatus variable of struct watchdog_device.
 * set_timeout: this routine checks and changes the timeout of the watchdog
   timer device. It returns 0 on success, -EINVAL for "parameter out of range"
   and -EIO for "could not write value to the watchdog". On success this
diff --git a/Documentation/x86/early-microcode.txt b/Documentation/x86/early-microcode.txt
index c956d99cf1de..07749e7f3d50 100644
--- a/Documentation/x86/early-microcode.txt
+++ b/Documentation/x86/early-microcode.txt
@@ -45,7 +45,10 @@ Builtin microcode
 =================
 
 We can also load builtin microcode supplied through the regular firmware
-builtin method CONFIG_FIRMWARE_IN_KERNEL. Here's an example:
+builtin method CONFIG_FIRMWARE_IN_KERNEL. Only 64-bit is currently
+supported.
+
+Here's an example:
 
 CONFIG_FIRMWARE_IN_KERNEL=y
 CONFIG_EXTRA_FIRMWARE="intel-ucode/06-3a-09 amd-ucode/microcode_amd_fam15h.bin"
diff --git a/MAINTAINERS b/MAINTAINERS
index 256f56bbb2ad..429fc61bee81 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -612,6 +612,13 @@ L:	linux-gpio@vger.kernel.org
 S:	Maintained
 F:	drivers/gpio/gpio-altera.c
 
+ALTERA SYSTEM RESOURCE DRIVER FOR ARRIA10 DEVKIT
+M:	Thor Thayer <tthayer@opensource.altera.com>
+S:	Maintained
+F:	drivers/gpio/gpio-altera-a10sr.c
+F:	drivers/mfd/altera-a10sr.c
+F:	include/linux/mfd/altera-a10sr.h
+
 ALTERA TRIPLE SPEED ETHERNET DRIVER
 M:	Vince Bridgers <vbridger@opensource.altera.com>
 L:	netdev@vger.kernel.org
@@ -771,6 +778,11 @@ W:	http://ez.analog.com/community/linux-device-drivers
 S:	Supported
 F:	drivers/dma/dma-axi-dmac.c
 
+ANDROID CONFIG FRAGMENTS
+M:	Rob Herring <robh@kernel.org>
+S:	Supported
+F:	kernel/configs/android*
+
 ANDROID DRIVERS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 M:	Arve Hjønnevåg <arve@android.com>
@@ -872,9 +884,17 @@ F:	Documentation/devicetree/bindings/display/snps,arcpgu.txt
 ARM HDLCD DRM DRIVER
 M:	Liviu Dudau <liviu.dudau@arm.com>
 S:	Supported
-F:	drivers/gpu/drm/arm/
+F:	drivers/gpu/drm/arm/hdlcd_*
 F:	Documentation/devicetree/bindings/display/arm,hdlcd.txt
 
+ARM MALI-DP DRM DRIVER
+M:	Liviu Dudau <liviu.dudau@arm.com>
+M:	Brian Starkey <brian.starkey@arm.com>
+M:	Mali DP Maintainers <malidp@foss.arm.com>
+S:	Supported
+F:	drivers/gpu/drm/arm/
+F:	Documentation/devicetree/bindings/display/arm,malidp.txt
+
 ARM MFM AND FLOPPY DRIVERS
 M:	Ian Molton <spyro@f2s.com>
 S:	Maintained
@@ -1529,6 +1549,7 @@ M:	David Brown <david.brown@linaro.org>
 L:	linux-arm-msm@vger.kernel.org
 L:	linux-soc@vger.kernel.org
 S:	Maintained
+F:	Documentation/devicetree/bindings/soc/qcom/
 F:	arch/arm/boot/dts/qcom-*.dts
 F:	arch/arm/boot/dts/qcom-*.dtsi
 F:	arch/arm/mach-qcom/
@@ -1606,12 +1627,13 @@ F:	arch/arm/mach-s3c24*/
 F:	arch/arm/mach-s3c64xx/
 F:	arch/arm/mach-s5p*/
 F:	arch/arm/mach-exynos*/
-F:	drivers/*/*s3c2410*
-F:	drivers/*/*/*s3c2410*
+F:	drivers/*/*s3c24*
+F:	drivers/*/*/*s3c24*
+F:	drivers/*/*s3c64xx*
+F:	drivers/*/*s5pv210*
 F:	drivers/memory/samsung/*
 F:	drivers/soc/samsung/*
 F:	drivers/spi/spi-s3c*
-F:	sound/soc/samsung/*
 F:	Documentation/arm/Samsung/
 F:	Documentation/devicetree/bindings/arm/samsung/
 F:	Documentation/devicetree/bindings/sram/samsung-sram.txt
@@ -1746,8 +1768,7 @@ ARM/TANGO ARCHITECTURE
 M:	Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
 L:	linux-arm-kernel@lists.infradead.org
 S:	Maintained
-F:	arch/arm/mach-tango/
-F:	arch/arm/boot/dts/tango*
+N:	tango
 
 ARM/TECHNOLOGIC SYSTEMS TS7250 MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
@@ -1834,7 +1855,6 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 T:	git git://git.linaro.org/people/ulfh/clk.git
 S:	Maintained
 F:	drivers/clk/ux500/
-F:	include/linux/platform_data/clk-ux500.h
 
 ARM/VERSATILE EXPRESS PLATFORM
 M:	Liviu Dudau <liviu.dudau@arm.com>
@@ -2331,7 +2351,10 @@ S:	Supported
 F:	drivers/media/platform/sti/bdisp
 
 BEFS FILE SYSTEM
-S:	Orphan
+M:	Luis de Bethencourt <luisbg@osg.samsung.com>
+M:	Salah Triki <salah.triki@gmail.com>
+S:	Maintained
+T:	git git://github.com/luisbg/linux-befs.git
 F:	Documentation/filesystems/befs.txt
 F:	fs/befs/
 
@@ -2501,17 +2524,14 @@ BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE
 M:	Florian Fainelli <f.fainelli@gmail.com>
 M:	Ray Jui <rjui@broadcom.com>
 M:	Scott Branden <sbranden@broadcom.com>
-L:	bcm-kernel-feedback-list@broadcom.com
+M:	bcm-kernel-feedback-list@broadcom.com
 T:	git git://github.com/broadcom/mach-bcm
 S:	Maintained
+N:	bcm281*
+N:	bcm113*
+N:	bcm216*
+N:	kona
 F:	arch/arm/mach-bcm/
-F:	arch/arm/boot/dts/bcm113*
-F:	arch/arm/boot/dts/bcm216*
-F:	arch/arm/boot/dts/bcm281*
-F:	arch/arm64/boot/dts/broadcom/
-F:	arch/arm/configs/bcm_defconfig
-F:	drivers/mmc/host/sdhci-bcm-kona.c
-F:	drivers/clocksource/bcm_kona_timer.c
 
 BROADCOM BCM2835 ARM ARCHITECTURE
 M:	Stephen Warren <swarren@wwwdotorg.org>
@@ -2534,20 +2554,21 @@ F:	arch/mips/include/asm/mach-bcm47xx/*
 
 BROADCOM BCM5301X ARM ARCHITECTURE
 M:	Hauke Mehrtens <hauke@hauke-m.de>
+M:	Rafał Miłecki <zajec5@gmail.com>
+M:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-arm-kernel@lists.infradead.org
 S:	Maintained
 F:	arch/arm/mach-bcm/bcm_5301x.c
-F:	arch/arm/boot/dts/bcm5301x.dtsi
+F:	arch/arm/boot/dts/bcm5301x*.dtsi
 F:	arch/arm/boot/dts/bcm470*
 
 BROADCOM BCM63XX ARM ARCHITECTURE
 M:	Florian Fainelli <f.fainelli@gmail.com>
+M:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-L:	bcm-kernel-feedback-list@broadcom.com
 T:	git git://github.com/broadcom/stblinux.git
 S:	Maintained
-F:	arch/arm/mach-bcm/bcm63xx.c
-F:	arch/arm/include/debug/bcm63xx.S
+N:	bcm63xx
 
 BROADCOM BCM63XX/BCM33XX UDC DRIVER
 M:	Kevin Cernekee <cernekee@gmail.com>
@@ -2559,8 +2580,8 @@ BROADCOM BCM7XXX ARM ARCHITECTURE
 M:	Brian Norris <computersforpeace@gmail.com>
 M:	Gregory Fong <gregory.0xf0@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
+M:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-L:	bcm-kernel-feedback-list@broadcom.com
 T:	git git://github.com/broadcom/stblinux.git
 S:	Maintained
 F:	arch/arm/mach-bcm/*brcmstb*
@@ -2617,13 +2638,13 @@ BROADCOM IPROC ARM ARCHITECTURE
 M:	Ray Jui <rjui@broadcom.com>
 M:	Scott Branden <sbranden@broadcom.com>
 M:	Jon Mason <jonmason@broadcom.com>
+M:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-L:	bcm-kernel-feedback-list@broadcom.com
 T:	git git://github.com/broadcom/cygnus-linux.git
 S:	Maintained
 N:	iproc
 N:	cygnus
-N:	nsp
+N:	bcm[-_]nsp
 N:	bcm9113*
 N:	bcm9583*
 N:	bcm9585*
@@ -2634,6 +2655,9 @@ N:	bcm583*
 N:	bcm585*
 N:	bcm586*
 N:	bcm88312
+F:	arch/arm64/boot/dts/broadcom/ns2*
+F:	drivers/clk/bcm/clk-ns*
+F:	drivers/pinctrl/bcm/pinctrl-ns*
 
 BROADCOM BRCMSTB GPIO DRIVER
 M:	Gregory Fong <gregory.0xf0@gmail.com>
@@ -2678,8 +2702,8 @@ F:	drivers/net/ethernet/broadcom/bcmsysport.*
 
 BROADCOM VULCAN ARM64 SOC
 M:	Jayachandran C. <jchandra@broadcom.com>
+M:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-L:	bcm-kernel-feedback-list@broadcom.com
 S:	Maintained
 F:	arch/arm64/boot/dts/broadcom/vulcan*
 
@@ -3712,6 +3736,8 @@ M:	Support Opensource <support.opensource@diasemi.com>
 W:	http://www.dialog-semiconductor.com/products
 S:	Supported
 F:	Documentation/hwmon/da90??
+F:	Documentation/devicetree/bindings/mfd/da90*.txt
+F:	Documentation/devicetree/bindings/regulator/da92*.txt
 F:	Documentation/devicetree/bindings/sound/da[79]*.txt
 F:	drivers/gpio/gpio-da90??.c
 F:	drivers/hwmon/da90??-hwmon.c
@@ -3732,8 +3758,10 @@ F:	drivers/watchdog/da90??_wdt.c
 F:	include/linux/mfd/da903x.h
 F:	include/linux/mfd/da9052/
 F:	include/linux/mfd/da9055/
+F:	include/linux/mfd/da9062/
 F:	include/linux/mfd/da9063/
 F:	include/linux/mfd/da9150/
+F:	include/linux/regulator/da9211.h
 F:	include/sound/da[79]*.h
 F:	sound/soc/codecs/da[79]*.[ch]
 
@@ -3809,6 +3837,17 @@ F:	include/linux/*fence.h
 F:	Documentation/dma-buf-sharing.txt
 T:	git git://git.linaro.org/people/sumitsemwal/linux-dma-buf.git
 
+SYNC FILE FRAMEWORK
+M:	Sumit Semwal <sumit.semwal@linaro.org>
+R:	Gustavo Padovan <gustavo@padovan.org>
+S:	Maintained
+L:	linux-media@vger.kernel.org
+L:	dri-devel@lists.freedesktop.org
+F:	drivers/dma-buf/sync_file.c
+F:	include/linux/sync_file.h
+F:	Documentation/sync_file.txt
+T:	git git://git.linaro.org/people/sumitsemwal/linux-dma-buf.git
+
 DMA GENERIC OFFLOAD ENGINE SUBSYSTEM
 M:	Vinod Koul <vinod.koul@intel.com>
 L:	dmaengine@vger.kernel.org
@@ -3898,7 +3937,10 @@ T:	git git://people.freedesktop.org/~airlied/linux
 S:	Maintained
 F:	drivers/gpu/drm/
 F:	drivers/gpu/vga/
-F:	Documentation/DocBook/gpu.*
+F:	Documentation/devicetree/bindings/display/
+F:	Documentation/devicetree/bindings/gpu/
+F:	Documentation/devicetree/bindings/video/
+F:	Documentation/gpu/
 F:	include/drm/
 F:	include/uapi/drm/
 
@@ -3950,6 +3992,7 @@ S:	Supported
 F:	drivers/gpu/drm/i915/
 F:	include/drm/i915*
 F:	include/uapi/drm/i915_drm.h
+F:	Documentation/gpu/i915.rst
 
 DRM DRIVERS FOR ATMEL HLCDC
 M:	Boris Brezillon <boris.brezillon@free-electrons.com>
@@ -4145,6 +4188,21 @@ F:	drivers/gpu/drm/vc4/
 F:	include/uapi/drm/vc4_drm.h
 F:	Documentation/devicetree/bindings/display/brcm,bcm-vc4.txt
 
+DRM DRIVERS FOR TI OMAP
+M:	Tomi Valkeinen <tomi.valkeinen@ti.com>
+L:	dri-devel@lists.freedesktop.org
+S:	Maintained
+F:	drivers/gpu/drm/omapdrm/
+F:	Documentation/devicetree/bindings/display/ti/
+
+DRM DRIVERS FOR TI LCDC
+M:	Jyri Sarha <jsarha@ti.com>
+R:	Tomi Valkeinen <tomi.valkeinen@ti.com>
+L:	dri-devel@lists.freedesktop.org
+S:	Maintained
+F:	drivers/gpu/drm/tilcdc/
+F:	Documentation/devicetree/bindings/display/tilcdc/
+
 DSBR100 USB FM RADIO DRIVER
 M:	Alexey Klimov <klimov.linux@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -5044,6 +5102,15 @@ L:	linux-scsi@vger.kernel.org
 S:	Odd Fixes (e.g., new signatures)
 F:	drivers/scsi/fdomain.*
 
+GCC PLUGINS
+M:	Kees Cook <keescook@chromium.org>
+R:	Emese Revfy <re.emese@gmail.com>
+L:	kernel-hardening@lists.openwall.com
+S:	Maintained
+F:	scripts/gcc-plugins/
+F:	scripts/gcc-plugin.sh
+F:	Documentation/gcc-plugins.txt
+
 GCOV BASED KERNEL PROFILING
 M:	Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
 S:	Maintained
@@ -5354,6 +5421,12 @@ T:	git git://linuxtv.org/anttip/media_tree.git
 S:	Maintained
 F:	drivers/media/dvb-frontends/hd29l2*
 
+HEWLETT PACKARD ENTERPRISE ILO NMI WATCHDOG DRIVER
+M:	Brian Boylston <brian.boylston@hpe.com>
+S:	Supported
+F:	Documentation/watchdog/hpwdt.txt
+F:	drivers/watchdog/hpwdt.c
+
 HEWLETT-PACKARD SMART ARRAY RAID DRIVER (hpsa)
 M:	Don Brace <don.brace@microsemi.com>
 L:	iss_storagedev@hp.com
@@ -6218,6 +6291,7 @@ M:	Joerg Roedel <joro@8bytes.org>
 L:	iommu@lists.linux-foundation.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/iommu/
 F:	drivers/iommu/
 
 IP MASQUERADING
@@ -6948,6 +7022,7 @@ F:	drivers/crypto/nx/
 F:	drivers/crypto/vmx/
 F:	drivers/net/ethernet/ibm/ibmveth.*
 F:	drivers/net/ethernet/ibm/ibmvnic.*
+F:	drivers/pci/hotplug/pnv_php.c
 F:	drivers/pci/hotplug/rpa*
 F:	drivers/scsi/ibmvscsi/
 N:	opal
@@ -7354,6 +7429,13 @@ F:	Documentation/devicetree/bindings/i2c/max6697.txt
 F:	drivers/hwmon/max6697.c
 F:	include/linux/platform_data/max6697.h
 
+MAX9860 MONO AUDIO VOICE CODEC DRIVER
+M:	Peter Rosin <peda@axentia.se>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/devicetree/bindings/sound/max9860.txt
+F:	sound/soc/codecs/max9860.*
+
 MAXIM MUIC CHARGER DRIVERS FOR EXYNOS BASED BOARDS
 M:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
 L:	linux-pm@vger.kernel.org
@@ -7850,6 +7932,7 @@ M:	Ulf Hansson <ulf.hansson@linaro.org>
 L:	linux-mmc@vger.kernel.org
 T:	git git://git.linaro.org/people/ulf.hansson/mmc.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/mmc/
 F:	drivers/mmc/
 F:	include/linux/mmc/
 F:	include/uapi/linux/mmc/
@@ -8189,8 +8272,9 @@ T:	git git://github.com/konis/nilfs2.git
 S:	Supported
 F:	Documentation/filesystems/nilfs2.txt
 F:	fs/nilfs2/
-F:	include/linux/nilfs2_fs.h
 F:	include/trace/events/nilfs2.h
+F:	include/uapi/linux/nilfs2_api.h
+F:	include/uapi/linux/nilfs2_ondisk.h
 
 NINJA SCSI-3 / NINJA SCSI-32Bi (16bit/CardBus) PCMCIA SCSI HOST ADAPTER DRIVER
 M:	YOKOTA Hiroshi <yokota@netlab.is.tsukuba.ac.jp>
@@ -8808,6 +8892,7 @@ L:	linux-pci@vger.kernel.org
 Q:	http://patchwork.ozlabs.org/project/linux-pci/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git
 S:	Supported
+F:	Documentation/devicetree/bindings/pci/
 F:	Documentation/PCI/
 F:	drivers/pci/
 F:	include/linux/pci*
@@ -8871,6 +8956,13 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/pci/host/*mvebu*
 
+PCI DRIVER FOR AARDVARK (Marvell Armada 3700)
+M:	Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+L:	linux-pci@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	drivers/pci/host/pci-aardvark.c
+
 PCI DRIVER FOR NVIDIA TEGRA
 M:	Thierry Reding <thierry.reding@gmail.com>
 L:	linux-tegra@vger.kernel.org
@@ -8953,6 +9045,15 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/pci/xgene-pci-msi.txt
 F:	drivers/pci/host/pci-xgene-msi.c
 
+PCIE DRIVER FOR AXIS ARTPEC
+M:	Niklas Cassel <niklas.cassel@axis.com>
+M:	Jesper Nilsson <jesper.nilsson@axis.com>
+L:	linux-arm-kernel@axis.com
+L:	linux-pci@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/pci/axis,artpec*
+F:	drivers/pci/host/*artpec*
+
 PCIE DRIVER FOR HISILICON
 M:	Zhou Wang <wangzhou1@hisilicon.com>
 M:	Gabriele Paoloni <gabriele.paoloni@huawei.com>
@@ -9214,6 +9315,12 @@ F:	drivers/firmware/psci.c
 F:	include/linux/psci.h
 F:	include/uapi/linux/psci.h
 
+POWERNV OPERATOR PANEL LCD DISPLAY DRIVER
+M:	Suraj Jitindar Singh <sjitindarsingh@gmail.com>
+L:	linuxppc-dev@lists.ozlabs.org
+S:	Maintained
+F:	drivers/char/powernv-op-panel.c
+
 PNP SUPPORT
 M:	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
 S:	Maintained
@@ -10020,7 +10127,9 @@ S:	Maintained
 F:	drivers/platform/x86/samsung-laptop.c
 
 SAMSUNG AUDIO (ASoC) DRIVERS
+M:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
 M:	Sangbeom Kim <sbkim73@samsung.com>
+M:	Sylwester Nawrocki <s.nawrocki@samsung.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
 F:	sound/soc/samsung/
@@ -10334,6 +10443,13 @@ F:	tools/testing/selftests/seccomp/*
 K:	\bsecure_computing
 K:	\bTIF_SECCOMP\b
 
+SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) Broadcom BRCMSTB DRIVER
+M:	Al Cooper <alcooperx@gmail.com>
+L:	linux-mmc@vger.kernel.org
+L:	bcm-kernel-feedback-list@broadcom.com
+S:	Maintained
+F:	drivers/mmc/host/sdhci-brcmstb*
+
 SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) SAMSUNG DRIVER
 M:	Ben Dooks <ben-linux@fluff.org>
 M:	Jaehoon Chung <jh80.chung@samsung.com>
@@ -10849,6 +10965,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 W:	http://alsa-project.org/main/index.php/ASoC
 S:	Supported
+F:	Documentation/devicetree/bindings/sound/
 F:	Documentation/sound/alsa/soc/
 F:	sound/soc/
 F:	include/sound/soc*
diff --git a/Makefile b/Makefile
index 393b6159ae92..d6d401bf9d95 100644
--- a/Makefile
+++ b/Makefile
@@ -371,26 +371,27 @@ CFLAGS_KERNEL	=
 AFLAGS_KERNEL	=
 LDFLAGS_vmlinux =
 CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage -fno-tree-loop-im
-CFLAGS_KCOV	= -fsanitize-coverage=trace-pc
+CFLAGS_KCOV	:= $(call cc-option,-fsanitize-coverage=trace-pc,)
 
 
 # Use USERINCLUDE when you must reference the UAPI directories only.
 USERINCLUDE    := \
 		-I$(srctree)/arch/$(hdr-arch)/include/uapi \
-		-Iarch/$(hdr-arch)/include/generated/uapi \
+		-I$(objtree)/arch/$(hdr-arch)/include/generated/uapi \
 		-I$(srctree)/include/uapi \
-		-Iinclude/generated/uapi \
+		-I$(objtree)/include/generated/uapi \
                 -include $(srctree)/include/linux/kconfig.h
 
 # Use LINUXINCLUDE when you must reference the include/ directory.
 # Needed to be compatible with the O= option
 LINUXINCLUDE    := \
 		-I$(srctree)/arch/$(hdr-arch)/include \
-		-Iarch/$(hdr-arch)/include/generated/uapi \
-		-Iarch/$(hdr-arch)/include/generated \
+		-I$(objtree)/arch/$(hdr-arch)/include/generated/uapi \
+		-I$(objtree)/arch/$(hdr-arch)/include/generated \
 		$(if $(KBUILD_SRC), -I$(srctree)/include) \
-		-Iinclude \
-		$(USERINCLUDE)
+		-I$(objtree)/include
+
+LINUXINCLUDE	+= $(filter-out $(LINUXINCLUDE),$(USERINCLUDE))
 
 KBUILD_CPPFLAGS := -D__KERNEL__
 
@@ -554,7 +555,7 @@ ifeq ($(KBUILD_EXTMOD),)
 # in parallel
 PHONY += scripts
 scripts: scripts_basic include/config/auto.conf include/config/tristate.conf \
-	 asm-generic
+	 asm-generic gcc-plugins
 	$(Q)$(MAKE) $(build)=$(@)
 
 # Objects we will link into vmlinux / subdirs we need to visit
@@ -635,6 +636,15 @@ endif
 # Tell gcc to never replace conditional load with a non-conditional one
 KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)
 
+PHONY += gcc-plugins
+gcc-plugins: scripts_basic
+ifdef CONFIG_GCC_PLUGINS
+	$(Q)$(MAKE) $(build)=scripts/gcc-plugins
+endif
+	@:
+
+include scripts/Makefile.gcc-plugins
+
 ifdef CONFIG_READABLE_ASM
 # Disable optimizations that make assembler listings hard to read.
 # reorder blocks reorders the control in the function
@@ -666,21 +676,11 @@ endif
 endif
 # Find arch-specific stack protector compiler sanity-checking script.
 ifdef CONFIG_CC_STACKPROTECTOR
-  stackp-path := $(srctree)/scripts/gcc-$(ARCH)_$(BITS)-has-stack-protector.sh
-  ifneq ($(wildcard $(stackp-path)),)
-    stackp-check := $(stackp-path)
-  endif
+  stackp-path := $(srctree)/scripts/gcc-$(SRCARCH)_$(BITS)-has-stack-protector.sh
+  stackp-check := $(wildcard $(stackp-path))
 endif
 KBUILD_CFLAGS += $(stackp-flag)
 
-ifdef CONFIG_KCOV
-  ifeq ($(call cc-option, $(CFLAGS_KCOV)),)
-    $(warning Cannot use CONFIG_KCOV: \
-             -fsanitize-coverage=trace-pc is not supported by compiler)
-    CFLAGS_KCOV =
-  endif
-endif
-
 ifeq ($(cc-name),clang)
 KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
 KBUILD_CPPFLAGS += $(call cc-option,-Wno-unknown-warning-option,)
@@ -1019,7 +1019,7 @@ prepare1: prepare2 $(version_h) include/generated/utsrelease.h \
 
 archprepare: archheaders archscripts prepare1 scripts_basic
 
-prepare0: archprepare
+prepare0: archprepare gcc-plugins
 	$(Q)$(MAKE) $(build)=.
 
 # All the preparing..
@@ -1531,6 +1531,7 @@ clean: $(clean-dirs)
 		-o -name '.*.d' -o -name '.*.tmp' -o -name '*.mod.c' \
 		-o -name '*.symtypes' -o -name 'modules.order' \
 		-o -name modules.builtin -o -name '.tmp_*.o.*' \
+		-o -name '*.c.[012]*.*' \
 		-o -name '*.gcno' \) -type f -print | xargs rm -f
 
 # Generate tags for editors
@@ -1641,7 +1642,7 @@ endif
 	$(Q)$(MAKE) KBUILD_MODULES=$(if $(CONFIG_MODULES),1) \
 	$(build)=$(build-dir)
 # Make sure the latest headers are built for Documentation
-Documentation/: headers_install
+Documentation/ samples/: headers_install
 %/: prepare scripts FORCE
 	$(cmd_crmodverdir)
 	$(Q)$(MAKE) KBUILD_MODULES=$(if $(CONFIG_MODULES),1) \
diff --git a/arch/Kconfig b/arch/Kconfig
index 15996290fed4..bd8056b5b246 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -357,6 +357,43 @@ config SECCOMP_FILTER
 
 	  See Documentation/prctl/seccomp_filter.txt for details.
 
+config HAVE_GCC_PLUGINS
+	bool
+	help
+	  An arch should select this symbol if it supports building with
+	  GCC plugins.
+
+menuconfig GCC_PLUGINS
+	bool "GCC plugins"
+	depends on HAVE_GCC_PLUGINS
+	depends on !COMPILE_TEST
+	help
+	  GCC plugins are loadable modules that provide extra features to the
+	  compiler. They are useful for runtime instrumentation and static analysis.
+
+	  See Documentation/gcc-plugins.txt for details.
+
+config GCC_PLUGIN_CYC_COMPLEXITY
+	bool "Compute the cyclomatic complexity of a function"
+	depends on GCC_PLUGINS
+	help
+	  The complexity M of a function's control flow graph is defined as:
+	   M = E - N + 2P
+	  where
+
+	  E = the number of edges
+	  N = the number of nodes
+	  P = the number of connected components (exit nodes).
+
+config GCC_PLUGIN_SANCOV
+	bool
+	depends on GCC_PLUGINS
+	help
+	  This plugin inserts a __sanitizer_cov_trace_pc() call at the start of
+	  basic blocks. It supports all gcc versions with plugin support (from
+	  gcc-4.5 on). It is based on the commit "Add fuzzing coverage support"
+	  by Dmitry Vyukov <dvyukov@google.com>.
+
 config HAVE_CC_STACKPROTECTOR
 	bool
 	help
diff --git a/arch/alpha/boot/Makefile b/arch/alpha/boot/Makefile
index 8399bd0e68e8..0cbe4c59d3ce 100644
--- a/arch/alpha/boot/Makefile
+++ b/arch/alpha/boot/Makefile
@@ -15,7 +15,7 @@ targets		:= vmlinux.gz vmlinux \
 OBJSTRIP	:= $(obj)/tools/objstrip
 
 HOSTCFLAGS	:= -Wall -I$(objtree)/usr/include
-BOOTCFLAGS	+= -I$(obj) -I$(srctree)/$(obj)
+BOOTCFLAGS	+= -I$(objtree)/$(obj) -I$(srctree)/$(obj)
 
 # SRM bootable image.  Copy to offset 512 of a partition.
 $(obj)/bootimage: $(addprefix $(obj)/tools/,mkbb lxboot bootlx) $(obj)/vmlinux.nh
diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index 32e920a83ae5..e9e90bfa2b50 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -86,33 +86,6 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #define TS_UAC_NOPRINT		0x0001	/* ! Preserve the following three */
 #define TS_UAC_NOFIX		0x0002	/* ! flags as they match          */
 #define TS_UAC_SIGBUS		0x0004	/* ! userspace part of 'osf_sysinfo' */
-#define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal() */
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	WARN_ON(!test_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags));
-}
-static inline void clear_restore_sigmask(void)
-{
-	current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-}
-static inline bool test_restore_sigmask(void)
-{
-	return current_thread_info()->status & TS_RESTORE_SIGMASK;
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	if (!(ti->status & TS_RESTORE_SIGMASK))
-		return false;
-	ti->status &= ~TS_RESTORE_SIGMASK;
-	return true;
-}
-#endif
 
 #define SET_UNALIGN_CTL(task,value)	({				\
 	__u32 status = task_thread_info(task)->status & ~UAC_BITMASK;	\
diff --git a/arch/alpha/kernel/machvec_impl.h b/arch/alpha/kernel/machvec_impl.h
index f54bdf658cd0..d3398f6ab74c 100644
--- a/arch/alpha/kernel/machvec_impl.h
+++ b/arch/alpha/kernel/machvec_impl.h
@@ -137,7 +137,7 @@
 #define __initmv __initdata
 #define ALIAS_MV(x)
 #else
-#define __initmv __initdata_refok
+#define __initmv __refdata
 
 /* GCC actually has a syntax for defining aliases, but is under some
    delusion that you shouldn't be able to declare it extern somewhere
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index 763d66c883da..e659a340ca8a 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -19,7 +19,7 @@
 		/* this is for console on PGU */
 		/* bootargs = "console=tty0 consoleblank=0"; */
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24";
 	};
 
 	aliases {
@@ -57,9 +57,17 @@
 			no-loopback-test = <1>;
 		};
 
-		pgu0: pgu@f9000000 {
-			compatible = "snps,arcpgufb";
+		pguclk: pguclk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <25175000>;
+		};
+
+		pgu@f9000000 {
+			compatible = "snps,arcpgu";
 			reg = <0xf9000000 0x400>;
+			clocks = <&pguclk>;
+			clock-names = "pxlclk";
 		};
 
 		ps2: ps2@f9001000 {
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
index 4eb97c584b18..16ce5d65cfde 100644
--- a/arch/arc/boot/dts/nsimosci_hs.dts
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -19,7 +19,7 @@
 		/* this is for console on PGU */
 		/* bootargs = "console=tty0 consoleblank=0"; */
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24";
 	};
 
 	aliases {
@@ -57,9 +57,17 @@
 			no-loopback-test = <1>;
 		};
 
-		pgu0: pgu@f9000000 {
-			compatible = "snps,arcpgufb";
+		pguclk: pguclk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <25175000>;
+		};
+
+		pgu@f9000000 {
+			compatible = "snps,arcpgu";
 			reg = <0xf9000000 0x400>;
+			clocks = <&pguclk>;
+			clock-names = "pxlclk";
 		};
 
 		ps2: ps2@f9001000 {
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
index 853f897eb2a3..ce8dfbc30c4d 100644
--- a/arch/arc/boot/dts/nsimosci_hs_idu.dts
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -17,7 +17,7 @@
 
 	chosen {
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24";
 	};
 
 	aliases {
@@ -76,9 +76,17 @@
 			no-loopback-test = <1>;
 		};
 
-		pgu0: pgu@f9000000 {
-			compatible = "snps,arcpgufb";
+		pguclk: pguclk {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <25175000>;
+		};
+
+		pgu@f9000000 {
+			compatible = "snps,arcpgu";
 			reg = <0xf9000000 0x400>;
+			clocks = <&pguclk>;
+			clock-names = "pxlclk";
 		};
 
 		ps2: ps2@f9001000 {
diff --git a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
index 45cd665fca23..99498a4b4216 100644
--- a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
@@ -23,6 +23,11 @@
 				#clock-cells = <0>;
 			};
 
+			pguclk: pguclk {
+				#clock-cells = <0>;
+				compatible = "fixed-clock";
+				clock-frequency = <25175000>;
+			};
 		};
 
 		ethernet@0x18000 {
@@ -75,11 +80,11 @@
 		};
 
 /* PGU output directly sent to virtual LCD screen; hdmi controller not modelled */
-		pgu@0x17000 {
-			compatible = "snps,arcpgufb";
+		pgu@17000 {
+			compatible = "snps,arcpgu";
 			reg = <0x17000 0x400>;
-			clock-frequency = <51000000>; /* PGU'clock is initated in init function */
-			/* interrupts = <5>;   PGU interrupts not used, this vector is used for ps2 below */
+			clocks = <&pguclk>;
+			clock-names = "pxlclk";
 		};
 
 /* VDK has additional ps2 keyboard/mouse interface integrated in LCD screen model */
diff --git a/arch/arc/boot/dts/vdk_hs38_smp.dts b/arch/arc/boot/dts/vdk_hs38_smp.dts
index 031a5bc79b3e..2ba60c399d99 100644
--- a/arch/arc/boot/dts/vdk_hs38_smp.dts
+++ b/arch/arc/boot/dts/vdk_hs38_smp.dts
@@ -16,6 +16,6 @@
 	compatible = "snps,axs103";
 
 	chosen {
-		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0";
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=640x480-24";
 	};
 };
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 42bafa552498..98cf20933bbb 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -58,7 +58,8 @@ CONFIG_SERIAL_8250_RUNTIME_UARTS=1
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-CONFIG_FB=y
+CONFIG_DRM=y
+CONFIG_DRM_ARCPGU=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_HID is not set
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index 4bb60c1cd4a2..ddf8b96d494e 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -57,7 +57,8 @@ CONFIG_SERIAL_8250_RUNTIME_UARTS=1
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-CONFIG_FB=y
+CONFIG_DRM=y
+CONFIG_DRM_ARCPGU=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_HID is not set
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index 7e88f4c720f8..ceb90745326e 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -70,7 +70,8 @@ CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-CONFIG_FB=y
+CONFIG_DRM=y
+CONFIG_DRM_ARCPGU=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_HID is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index 52ec315dc5c9..969b206d6c67 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -63,12 +63,9 @@ CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-CONFIG_FB=y
-CONFIG_ARCPGU_RGB888=y
-CONFIG_ARCPGU_DISPTYPE=0
-# CONFIG_VGA_CONSOLE is not set
+CONFIG_DRM=y
+CONFIG_DRM_ARCPGU=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 5f8c0b47045a..a946400a86d0 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -15,7 +15,6 @@
 #include <linux/cpu.h>
 #include <linux/of_fdt.h>
 #include <linux/of.h>
-#include <linux/of_platform.h>
 #include <linux/cache.h>
 #include <asm/sections.h>
 #include <asm/arcregs.h>
@@ -436,12 +435,6 @@ void __init setup_arch(char **cmdline_p)
 
 static int __init customize_machine(void)
 {
-	/*
-	 * Traverses flattened DeviceTree - registering platform devices
-	 * (if any) complete with their resources
-	 */
-	of_platform_default_populate(NULL, NULL, NULL);
-
 	if (machine_desc->init_machine)
 		machine_desc->init_machine();
 
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index 8be930394750..399e2f223d25 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -220,7 +220,7 @@ void __init mem_init(void)
 /*
  * free_initmem: Free all the __init memory.
  */
-void __init_refok free_initmem(void)
+void __ref free_initmem(void)
 {
 	free_initmem_default(-1);
 }
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 4c445fb9c189..2d601d769a1c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -54,6 +54,7 @@ config ARM
 	select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL)
 	select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL)
 	select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
+	select HAVE_GCC_PLUGINS
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
 	select HAVE_IDE if PCI || ISA || PCMCIA
@@ -327,7 +328,6 @@ choice
 config ARCH_MULTIPLATFORM
 	bool "Allow multiple platforms to be selected"
 	depends on MMU
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_HAS_SG_CHAIN
 	select ARM_PATCH_PHYS_VIRT
 	select AUTO_ZRELADDR
@@ -342,7 +342,6 @@ config ARCH_MULTIPLATFORM
 config ARM_SINGLE_ARMV7M
 	bool "ARMv7-M based platforms (Cortex-M0/M3/M4)"
 	depends on !MMU
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_NVIC
 	select AUTO_ZRELADDR
 	select CLKSRC_OF
@@ -353,26 +352,12 @@ config ARM_SINGLE_ARMV7M
 	select SPARSE_IRQ
 	select USE_OF
 
-
-config ARCH_CLPS711X
-	bool "Cirrus Logic CLPS711x/EP721x/EP731x-based"
-	select ARCH_REQUIRE_GPIOLIB
-	select AUTO_ZRELADDR
-	select COMMON_CLK
-	select CPU_ARM720T
-	select GENERIC_CLOCKEVENTS
-	select CLPS711X_TIMER
-	select MFD_SYSCON
-	select SOC_BUS
-	help
-	  Support for Cirrus Logic 711x/721x/731x based boards.
-
 config ARCH_GEMINI
 	bool "Cortina Systems Gemini"
-	select ARCH_REQUIRE_GPIOLIB
 	select CLKSRC_MMIO
 	select CPU_FA526
 	select GENERIC_CLOCKEVENTS
+	select GPIOLIB
 	help
 	  Support for the Cortina Systems Gemini family SoCs
 
@@ -393,7 +378,6 @@ config ARCH_EBSA110
 config ARCH_EP93XX
 	bool "EP93xx-based"
 	select ARCH_HAS_HOLES_MEMORYMODEL
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_PATCH_PHYS_VIRT
 	select ARM_VIC
@@ -402,6 +386,7 @@ config ARCH_EP93XX
 	select CLKSRC_MMIO
 	select CPU_ARM920T
 	select GENERIC_CLOCKEVENTS
+	select GPIOLIB
 	help
 	  This enables support for the Cirrus EP93xx series of CPUs.
 
@@ -442,9 +427,9 @@ config ARCH_IOP13XX
 config ARCH_IOP32X
 	bool "IOP32x-based"
 	depends on MMU
-	select ARCH_REQUIRE_GPIOLIB
 	select CPU_XSCALE
 	select GPIO_IOP
+	select GPIOLIB
 	select NEED_RET_TO_USER
 	select PCI
 	select PLAT_IOP
@@ -455,9 +440,9 @@ config ARCH_IOP32X
 config ARCH_IOP33X
 	bool "IOP33x-based"
 	depends on MMU
-	select ARCH_REQUIRE_GPIOLIB
 	select CPU_XSCALE
 	select GPIO_IOP
+	select GPIOLIB
 	select NEED_RET_TO_USER
 	select PCI
 	select PLAT_IOP
@@ -468,12 +453,12 @@ config ARCH_IXP4XX
 	bool "IXP4xx-based"
 	depends on MMU
 	select ARCH_HAS_DMA_SET_COHERENT_MASK
-	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select CLKSRC_MMIO
 	select CPU_XSCALE
 	select DMABOUNCE if PCI
 	select GENERIC_CLOCKEVENTS
+	select GPIOLIB
 	select MIGHT_HAVE_PCI
 	select NEED_MACH_IO_H
 	select USB_EHCI_BIG_ENDIAN_DESC
@@ -483,9 +468,9 @@ config ARCH_IXP4XX
 
 config ARCH_DOVE
 	bool "Marvell Dove"
-	select ARCH_REQUIRE_GPIOLIB
 	select CPU_PJ4
 	select GENERIC_CLOCKEVENTS
+	select GPIOLIB
 	select MIGHT_HAVE_PCI
 	select MULTI_IRQ_HANDLER
 	select MVEBU_MBUS
@@ -499,10 +484,10 @@ config ARCH_DOVE
 
 config ARCH_KS8695
 	bool "Micrel/Kendin KS8695"
-	select ARCH_REQUIRE_GPIOLIB
 	select CLKSRC_MMIO
 	select CPU_ARM922T
 	select GENERIC_CLOCKEVENTS
+	select GPIOLIB
 	select NEED_MACH_MEMORY_H
 	help
 	  Support for Micrel/Kendin KS8695 "Centaur" (ARM922T) based
@@ -510,11 +495,11 @@ config ARCH_KS8695
 
 config ARCH_W90X900
 	bool "Nuvoton W90X900 CPU"
-	select ARCH_REQUIRE_GPIOLIB
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
+	select GPIOLIB
 	help
 	  Support for Nuvoton (Winbond logic dept.) ARM9 processor,
 	  At present, the w90x900 has been renamed nuc900, regarding
@@ -526,13 +511,13 @@ config ARCH_W90X900
 
 config ARCH_LPC32XX
 	bool "NXP LPC32XX"
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select CLKDEV_LOOKUP
 	select CLKSRC_LPC32XX
 	select COMMON_CLK
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
+	select GPIOLIB
 	select MULTI_IRQ_HANDLER
 	select SPARSE_IRQ
 	select USE_OF
@@ -543,7 +528,6 @@ config ARCH_PXA
 	bool "PXA2xx/PXA3xx-based"
 	depends on MMU
 	select ARCH_MTD_XIP
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_CPU_SUSPEND if PM
 	select AUTO_ZRELADDR
 	select COMMON_CLK
@@ -554,6 +538,7 @@ config ARCH_PXA
 	select CPU_XSCALE if !CPU_XSC3
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
+	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
@@ -584,7 +569,6 @@ config ARCH_RPC
 config ARCH_SA1100
 	bool "SA1100-based"
 	select ARCH_MTD_XIP
-	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SPARSEMEM_ENABLE
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
@@ -593,6 +577,7 @@ config ARCH_SA1100
 	select CPU_FREQ
 	select CPU_SA1100
 	select GENERIC_CLOCKEVENTS
+	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
 	select ISA
@@ -604,12 +589,12 @@ config ARCH_SA1100
 
 config ARCH_S3C24XX
 	bool "Samsung S3C24XX SoCs"
-	select ARCH_REQUIRE_GPIOLIB
 	select ATAGS
 	select CLKDEV_LOOKUP
 	select CLKSRC_SAMSUNG_PWM
 	select GENERIC_CLOCKEVENTS
 	select GPIO_SAMSUNG
+	select GPIOLIB
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_S3C_RTC if RTC_CLASS
@@ -625,12 +610,12 @@ config ARCH_S3C24XX
 config ARCH_DAVINCI
 	bool "TI DaVinci"
 	select ARCH_HAS_HOLES_MEMORYMODEL
-	select ARCH_REQUIRE_GPIOLIB
 	select CLKDEV_LOOKUP
 	select CPU_ARM926T
 	select GENERIC_ALLOCATOR
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
+	select GPIOLIB
 	select HAVE_IDE
 	select USE_OF
 	select ZONE_DMA
@@ -642,11 +627,11 @@ config ARCH_OMAP1
 	depends on MMU
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_OMAP
-	select ARCH_REQUIRE_GPIOLIB
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
+	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
@@ -715,7 +700,7 @@ config ARCH_VIRT
 	depends on ARCH_MULTI_V7
 	select ARM_AMBA
 	select ARM_GIC
-	select ARM_GIC_V2M if PCI_MSI
+	select ARM_GIC_V2M if PCI
 	select ARM_GIC_V3
 	select ARM_PSCI
 	select HAVE_ARM_ARCH_TIMER
@@ -868,7 +853,7 @@ source "arch/arm/mach-zynq/Kconfig"
 config ARCH_EFM32
 	bool "Energy Micro efm32"
 	depends on ARM_SINGLE_ARMV7M
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	help
 	  Support for Energy Micro's (now Silicon Labs) efm32 Giant Gecko
 	  processors.
@@ -901,7 +886,7 @@ config MACH_STM32F429
 	default y
 
 config ARCH_MPS2
-	bool "ARM MPS2 paltform"
+	bool "ARM MPS2 platform"
 	depends on ARM_SINGLE_ARMV7M
 	select ARM_AMBA
 	select CLKSRC_MPS2
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 19a3dcf5eb2e..a9693b6987a6 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -109,23 +109,41 @@ choice
 		    0x80020000      | 0xf0020000     | UART8
 		    0x80024000      | 0xf0024000     | UART9
 
-	config DEBUG_AT91_UART
-		bool "Kernel low-level debugging on Atmel SoCs"
-		depends on ARCH_AT91
+	config DEBUG_AT91_RM9200_DBGU
+		bool "Kernel low-level debugging on AT91RM9200, AT91SAM9 DBGU"
+		select DEBUG_AT91_UART
+		depends on SOC_AT91RM9200 || SOC_AT91SAM9
 		help
-		  Say Y here if you want the debug print routines to direct
-		  their output to the serial port on atmel devices.
+		  Say Y here if you want kernel low-level debugging support
+		  on the DBGU port of:
+		    at91rm9200, at91sam9260, at91sam9g20, at91sam9261,
+		    at91sam9g10, at91sam9n12, at91sam9rl64, at91sam9x5
 
-		  SOC                  DEBUG_UART_PHYS   DEBUG_UART_VIRT  PORT
-		  rm9200, 9260/9g20,   0xfffff200        0xfefff200       DBGU
-		  9261/9g10, 9rl
-		  9263, 9g45, sama5d3  0xffffee00        0xfeffee00       DBGU
-		  sama5d4              0xfc00c000        0xfb00c000       USART3
-		  sama5d4              0xfc069000        0xfb069000       DBGU
-		  sama5d2              0xf8020000        0xf7020000       UART1
+	config DEBUG_AT91_SAM9263_DBGU
+		bool "Kernel low-level debugging on AT91SAM{9263,9G45,A5D3} DBGU"
+		select DEBUG_AT91_UART
+		depends on SOC_AT91SAM9 || SOC_SAMA5D3
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on the DBGU port of:
+		    at91sam9263, at91sam9g45, at91sam9m10,
+		    sama5d3
 
-		  Please adjust DEBUG_UART_PHYS configuration options based on
-		  your needs.
+	config DEBUG_AT91_SAMA5D2_UART1
+		bool "Kernel low-level debugging on SAMA5D2 UART1"
+		select DEBUG_AT91_UART
+		depends on SOC_SAMA5D2
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on the UART1 port of sama5d2.
+
+	config DEBUG_AT91_SAMA5D4_USART3
+		bool "Kernel low-level debugging on SAMA5D4 USART3"
+		select DEBUG_AT91_UART
+		depends on SOC_SAMA5D4
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on the USART3 port of sama5d4.
 
 	config DEBUG_BCM2835
 		bool "Kernel low-level debugging on BCM2835 PL011 UART"
@@ -138,8 +156,8 @@ choice
 		select DEBUG_UART_PL01X
 
 	config DEBUG_BCM_5301X
-		bool "Kernel low-level debugging on BCM5301X UART1"
-		depends on ARCH_BCM_5301X
+		bool "Kernel low-level debugging on BCM5301X/NSP UART1"
+		depends on ARCH_BCM_5301X || ARCH_BCM_NSP
 		select DEBUG_UART_8250
 
 	config DEBUG_BCM_KONA_UART
@@ -1296,6 +1314,10 @@ choice
 
 endchoice
 
+config DEBUG_AT91_UART
+	bool
+	depends on ARCH_AT91
+
 config DEBUG_EXYNOS_UART
 	bool
 
@@ -1502,8 +1524,10 @@ config DEBUG_UART_PHYS
 	default 0xf1012000 if DEBUG_MVEBU_UART0_ALTERNATE
 	default 0xf1012100 if DEBUG_MVEBU_UART1_ALTERNATE
 	default 0xf7fc9000 if DEBUG_BERLIN_UART
+	default 0xf8020000 if DEBUG_AT91_SAMA5D2_UART1
 	default 0xf8b00000 if DEBUG_HIX5HD2_UART
 	default 0xf991e000 if DEBUG_QCOM_UARTDM
+	default 0xfc00c000 if DEBUG_AT91_SAMA5D4_USART3
 	default 0xfcb00000 if DEBUG_HI3620_UART
 	default 0xfd883000 if DEBUG_ALPINE_UART0
 	default 0xfe800000 if ARCH_IOP32X
@@ -1518,6 +1542,8 @@ config DEBUG_UART_PHYS
 	default 0xfffb0800 if DEBUG_OMAP1UART2 || DEBUG_OMAP7XXUART2
 	default 0xfffb9800 if DEBUG_OMAP1UART3 || DEBUG_OMAP7XXUART3
 	default 0xfffe8600 if DEBUG_BCM63XX_UART
+	default 0xffffee00 if DEBUG_AT91_SAM9263_DBGU
+	default 0xfffff200 if DEBUG_AT91_RM9200_DBGU
 	default 0xfffff700 if ARCH_IOP33X
 	depends on ARCH_EP93XX || \
 	        DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
@@ -1566,13 +1592,17 @@ config DEBUG_UART_VIRT
 				DEBUG_S3C2410_UART1)
 	default 0xf7008000 if DEBUG_S3C24XX_UART && (DEBUG_S3C_UART2 || \
 				DEBUG_S3C2410_UART2)
+	default 0xf7020000 if DEBUG_AT91_SAMA5D2_UART1
 	default 0xf7fc9000 if DEBUG_BERLIN_UART
 	default 0xf8007000 if DEBUG_HIP04_UART
 	default 0xf8009000 if DEBUG_VEXPRESS_UART0_CA9
 	default 0xf8090000 if DEBUG_VEXPRESS_UART0_RS1
+	default 0xf8ffee00 if DEBUG_AT91_SAM9263_DBGU
+	default 0xf8fff200 if DEBUG_AT91_RM9200_DBGU
 	default 0xfa71e000 if DEBUG_QCOM_UARTDM
 	default 0xfb002000 if DEBUG_CNS3XXX
 	default 0xfb009000 if DEBUG_REALVIEW_STD_PORT
+	default 0xfb00c000 if DEBUG_AT91_SAMA5D4_USART3
 	default 0xfb10c000 if DEBUG_REALVIEW_PB1176_PORT
 	default 0xfc40ab00 if DEBUG_BRCMSTB_UART
 	default 0xfc705000 if DEBUG_ZTE_ZX
@@ -1627,7 +1657,8 @@ config DEBUG_UART_VIRT
 		DEBUG_QCOM_UARTDM || DEBUG_S3C24XX_UART || \
 		DEBUG_S3C64XX_UART || \
 		DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \
-		DEBUG_SIRFSOC_UART || DEBUG_DIGICOLOR_UA0
+		DEBUG_SIRFSOC_UART || DEBUG_DIGICOLOR_UA0 || \
+		DEBUG_AT91_UART
 
 config DEBUG_UART_8250_SHIFT
 	int "Register offset shift for the 8250 debug UART"
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 229afaf2058b..56ea5c60b318 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -140,7 +140,6 @@ head-y		:= arch/arm/kernel/head$(MMUEXT).o
 # Text offset. This list is sorted numerically by address in order to
 # provide a means to avoid/resolve conflicts in multi-arch kernels.
 textofs-y	:= 0x00008000
-textofs-$(CONFIG_ARCH_CLPS711X) := 0x00028000
 # We don't want the htc bootloader to corrupt kernel during resume
 textofs-$(CONFIG_PM_H1940)      := 0x00108000
 # SA1111 DMA bug: we don't want the kernel to live in precious DMA-able memory
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 414b42710a36..faacd52370d2 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -7,9 +7,10 @@ dtb-$(CONFIG_MACH_ARTPEC6) += \
 dtb-$(CONFIG_MACH_ASM9260) += \
 	alphascale-asm9260-devkit.dtb
 # Keep at91 dtb files sorted alphabetically for each SoC
-dtb-$(CONFIG_SOC_SAM_V4_V5) += \
+dtb-$(CONFIG_SOC_AT91RM9200) += \
 	at91rm9200ek.dtb \
-	mpa1600.dtb \
+	mpa1600.dtb
+dtb-$(CONFIG_SOC_AT91SAM9) += \
 	animeo_ip.dtb \
 	at91-qil_a9260.dtb \
 	aks-cdu.dtb \
@@ -17,8 +18,10 @@ dtb-$(CONFIG_SOC_SAM_V4_V5) += \
 	evk-pro3.dtb \
 	tny_a9260.dtb \
 	usb_a9260.dtb \
+	at91sam9260ek.dtb \
 	at91sam9261ek.dtb \
 	at91sam9263ek.dtb \
+	at91-sam9_l9260.dtb \
 	tny_a9263.dtb \
 	usb_a9263.dtb \
 	at91-foxg20.dtb \
@@ -85,6 +88,7 @@ dtb-$(CONFIG_ARCH_BCM_5301X) += \
 	bcm47094-dlink-dir-885l.dtb \
 	bcm94708.dtb \
 	bcm94709.dtb \
+	bcm953012er.dtb \
 	bcm953012k.dtb
 dtb-$(CONFIG_ARCH_BCM_63XX) += \
 	bcm963138dvt.dtb
@@ -95,8 +99,11 @@ dtb-$(CONFIG_ARCH_BCM_CYGNUS) += \
 	bcm958305k.dtb
 dtb-$(CONFIG_ARCH_BCM_MOBILE) += \
 	bcm28155-ap.dtb \
-	bcm21664-garnet.dtb
+	bcm21664-garnet.dtb \
+	bcm23550-sparrow.dtb
 dtb-$(CONFIG_ARCH_BCM_NSP) += \
+	bcm958525xmc.dtb \
+	bcm958625hr.dtb \
 	bcm958625k.dtb
 dtb-$(CONFIG_ARCH_BERLIN) += \
 	berlin2-sony-nsz-gs7.dtb \
@@ -104,6 +111,8 @@ dtb-$(CONFIG_ARCH_BERLIN) += \
 	berlin2q-marvell-dmp.dtb
 dtb-$(CONFIG_ARCH_BRCMSTB) += \
 	bcm7445-bcm97445svmb.dtb
+dtb-$(CONFIG_ARCH_CLPS711X) += \
+	ep7211-edb7211.dtb
 dtb-$(CONFIG_ARCH_DAVINCI) += \
 	da850-enbw-cmc.dtb \
 	da850-evm.dtb
@@ -134,6 +143,7 @@ dtb-$(CONFIG_ARCH_EXYNOS5) += \
 	exynos5250-snow-rev5.dtb \
 	exynos5250-spring.dtb \
 	exynos5260-xyref5260.dtb \
+	exynos5410-odroidxu.dtb \
 	exynos5410-smdk5410.dtb \
 	exynos5420-arndale-octa.dtb \
 	exynos5420-peach-pit.dtb \
@@ -146,8 +156,6 @@ dtb-$(CONFIG_ARCH_EXYNOS5) += \
 	exynos5800-peach-pi.dtb
 dtb-$(CONFIG_ARCH_HI3xxx) += \
 	hi3620-hi4511.dtb
-dtb-$(CONFIG_ARCH_HIX5HD2) += \
-	hisi-x5hd2-dkb.dtb
 dtb-$(CONFIG_ARCH_HIGHBANK) += \
 	highbank.dtb \
 	ecx-2000.dtb
@@ -155,6 +163,10 @@ dtb-$(CONFIG_ARCH_HIP01) += \
 	hip01-ca9x2.dtb
 dtb-$(CONFIG_ARCH_HIP04) += \
 	hip04-d01.dtb
+dtb-$(CONFIG_ARCH_HISI) += \
+	hi3519-demb.dtb
+dtb-$(CONFIG_ARCH_HIX5HD2) += \
+	hisi-x5hd2-dkb.dtb
 dtb-$(CONFIG_ARCH_INTEGRATOR) += \
 	integratorap.dtb \
 	integratorcp.dtb
@@ -356,6 +368,7 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6q-gw54xx.dtb \
 	imx6q-gw551x.dtb \
 	imx6q-gw552x.dtb \
+	imx6q-h100.dtb \
 	imx6q-hummingboard.dtb \
 	imx6q-icore-rqs.dtb \
 	imx6q-marsboard.dtb \
@@ -377,6 +390,7 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6q-tx6q-1110.dtb \
 	imx6q-tx6q-11x0-mb7.dtb \
 	imx6q-udoo.dtb \
+	imx6q-utilite-pro.dtb \
 	imx6q-wandboard.dtb \
 	imx6q-wandboard-revb1.dtb \
 	imx6qp-nitrogen6_max.dtb \
@@ -399,9 +413,11 @@ dtb-$(CONFIG_SOC_IMX6UL) += \
 	imx6ul-tx6ul-mainboard.dtb
 dtb-$(CONFIG_SOC_IMX7D) += \
 	imx7d-cl-som-imx7.dtb \
+	imx7d-colibri-eval-v3.dtb \
 	imx7d-nitrogen7.dtb \
 	imx7d-sbc-imx7.dtb \
-	imx7d-sdb.dtb
+	imx7d-sdb.dtb \
+	imx7s-colibri-eval-v3.dtb
 dtb-$(CONFIG_SOC_LS1021A) += \
 	ls1021a-qds.dtb \
 	ls1021a-twr.dtb
@@ -416,7 +432,9 @@ dtb-$(CONFIG_SOC_VF610) += \
 dtb-$(CONFIG_ARCH_MXS) += \
 	imx23-evk.dtb \
 	imx23-olinuxino.dtb \
+	imx23-sansa.dtb \
 	imx23-stmp378x_devb.dtb \
+	imx23-xfi3.dtb \
 	imx28-apf28.dtb \
 	imx28-apf28dev.dtb \
 	imx28-apx4devkit.dtb \
@@ -572,7 +590,8 @@ dtb-$(CONFIG_ARCH_PRIMA2) += \
 dtb-$(CONFIG_ARCH_OXNAS) += \
 	wd-mbwe.dtb
 dtb-$(CONFIG_ARCH_QCOM) += \
-	qcom-apq8064-arrow-db600c.dtb \
+	qcom-apq8060-dragonboard.dtb \
+	qcom-apq8064-arrow-sd-600eval.dtb \
 	qcom-apq8064-cm-qs600.dtb \
 	qcom-apq8064-ifc6410.dtb \
 	qcom-apq8064-sony-xperia-yuga.dtb \
@@ -602,6 +621,7 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += \
 	rk3066a-rayeager.dtb \
 	rk3188-radxarock.dtb \
 	rk3228-evb.dtb \
+	rk3229-evb.dtb \
 	rk3288-evb-act8846.dtb \
 	rk3288-evb-rk808.dtb \
 	rk3288-firefly-beta.dtb \
@@ -638,6 +658,7 @@ dtb-$(CONFIG_ARCH_SHMOBILE_MULTI) += \
 	r8a7790-lager.dtb \
 	r8a7791-koelsch.dtb \
 	r8a7791-porter.dtb \
+	r8a7792-blanche.dtb \
 	r8a7793-gose.dtb \
 	r8a7794-alt.dtb \
 	r8a7794-silk.dtb \
@@ -728,6 +749,7 @@ dtb-$(CONFIG_MACH_SUN6I) += \
 	sun6i-a31s-yones-toptech-bs1078-v2.dtb
 dtb-$(CONFIG_MACH_SUN7I) += \
 	sun7i-a20-bananapi.dtb \
+	sun7i-a20-bananapi-m1-plus.dtb \
 	sun7i-a20-bananapro.dtb \
 	sun7i-a20-cubieboard2.dtb \
 	sun7i-a20-cubietruck.dtb \
@@ -752,8 +774,10 @@ dtb-$(CONFIG_MACH_SUN7I) += \
 dtb-$(CONFIG_MACH_SUN8I) += \
 	sun8i-a23-evb.dtb \
 	sun8i-a23-gt90h-v4.dtb \
+	sun8i-a23-inet86dz.dtb \
 	sun8i-a23-ippo-q8h-v5.dtb \
 	sun8i-a23-ippo-q8h-v1.2.dtb \
+	sun8i-a23-polaroid-mid2407pxe03.dtb \
 	sun8i-a23-polaroid-mid2809pxe04.dtb \
 	sun8i-a23-q8-tablet.dtb \
 	sun8i-a33-et-q8-v1.6.dtb \
@@ -763,10 +787,12 @@ dtb-$(CONFIG_MACH_SUN8I) += \
 	sun8i-a33-sinlinx-sina33.dtb \
 	sun8i-a83t-allwinner-h8homlet-v2.dtb \
 	sun8i-a83t-cubietruck-plus.dtb \
+	sun8i-h3-bananapi-m2-plus.dtb \
 	sun8i-h3-orangepi-2.dtb \
 	sun8i-h3-orangepi-one.dtb \
 	sun8i-h3-orangepi-pc.dtb \
-	sun8i-h3-orangepi-plus.dtb
+	sun8i-h3-orangepi-plus.dtb \
+	sun8i-r16-parrot.dtb
 dtb-$(CONFIG_MACH_SUN9I) += \
 	sun9i-a80-optimus.dtb \
 	sun9i-a80-cubieboard4.dtb
@@ -794,6 +820,7 @@ dtb-$(CONFIG_ARCH_TEGRA_114_SOC) += \
 	tegra114-roth.dtb \
 	tegra114-tn7.dtb
 dtb-$(CONFIG_ARCH_TEGRA_124_SOC) += \
+	tegra124-apalis-eval.dtb \
 	tegra124-jetson-tk1.dtb \
 	tegra124-nyan-big.dtb \
 	tegra124-nyan-blaze.dtb \
diff --git a/arch/arm/boot/dts/aks-cdu.dts b/arch/arm/boot/dts/aks-cdu.dts
index d9c50fbb49d2..5b1bf92d927c 100644
--- a/arch/arm/boot/dts/aks-cdu.dts
+++ b/arch/arm/boot/dts/aks-cdu.dts
@@ -57,7 +57,7 @@
 			};
 		};
 
-		usb0: ohci@00500000 {
+		usb0: ohci@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index 0cc150b87b86..e247c15e5176 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -18,6 +18,10 @@
 		reg = <0x80000000 0x10000000>; /* 256 MB */
 	};
 
+	chosen {
+		stdout-path = &uart0;
+	};
+
 	leds {
 		pinctrl-names = "default";
 		pinctrl-0 = <&user_leds_s0>;
@@ -318,7 +322,7 @@
 			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
-			regulator-max-microvolt = <1325000>;
+			regulator-max-microvolt = <1351500>;
 			regulator-boot-on;
 			regulator-always-on;
 		};
@@ -359,12 +363,8 @@
 	phy-mode = "mii";
 };
 
-&cpsw_emac1 {
-	phy_id = <&davinci_mdio>, <1>;
-	phy-mode = "mii";
-};
-
 &mac {
+	slaves = <1>;
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&cpsw_default>;
 	pinctrl-1 = <&cpsw_sleep>;
diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts
index 55c0e954b146..ca721670bd91 100644
--- a/arch/arm/boot/dts/am335x-boneblack.dts
+++ b/arch/arm/boot/dts/am335x-boneblack.dts
@@ -33,6 +33,17 @@
 	status = "okay";
 };
 
+&cpu0_opp_table {
+	/*
+	 * All PG 2.0 silicon may not support 1GHz but some of the early
+	 * BeagleBone Blacks have PG 2.0 silicon which is guaranteed
+	 * to support 1GHz OPP so enable it for PG 2.0 on this board.
+	 */
+	oppnitro@1000000000 {
+		opp-supported-hw = <0x06 0x0100>;
+	};
+};
+
 &am33xx_pinmux {
 	nxp_hdmi_bonelt_pins: nxp_hdmi_bonelt_pins {
 		pinctrl-single,pins = <
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index 516673bb023d..5d28712ad253 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -640,7 +640,7 @@
 			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <912500>;
-			regulator-max-microvolt = <1312500>;
+			regulator-max-microvolt = <1351500>;
 			regulator-boot-on;
 			regulator-always-on;
 		};
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 282fe1b37095..09308d66645b 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -560,7 +560,7 @@
 			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <912500>;
-			regulator-max-microvolt = <1312500>;
+			regulator-max-microvolt = <1351500>;
 			regulator-boot-on;
 			regulator-always-on;
 		};
diff --git a/arch/arm/boot/dts/am335x-icev2.dts b/arch/arm/boot/dts/am335x-icev2.dts
index e271013e78a6..7d8b8fefdf08 100644
--- a/arch/arm/boot/dts/am335x-icev2.dts
+++ b/arch/arm/boot/dts/am335x-icev2.dts
@@ -206,6 +206,13 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 	};
+
+	pca9536: gpio@41 {
+		compatible = "ti,pca9536";
+		reg = <0x41>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
 };
 
 #include "tps65910.dtsi"
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 7fa295155543..98748c61ed99 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -45,19 +45,9 @@
 			device_type = "cpu";
 			reg = <0>;
 
-			/*
-			 * To consider voltage drop between PMIC and SoC,
-			 * tolerance value is reduced to 2% from 4% and
-			 * voltage value is increased as a precaution.
-			 */
-			operating-points = <
-				/* kHz    uV */
-				720000  1285000
-				600000  1225000
-				500000  1125000
-				275000  1125000
-			>;
-			voltage-tolerance = <2>; /* 2 percentage */
+			operating-points-v2 = <&cpu0_opp_table>;
+			ti,syscon-efuse = <&scm_conf 0x7fc 0x1fff 0>;
+			ti,syscon-rev = <&scm_conf 0x600>;
 
 			clocks = <&dpll_mpu_ck>;
 			clock-names = "cpu";
@@ -66,6 +56,78 @@
 		};
 	};
 
+	cpu0_opp_table: opp_table0 {
+		compatible = "operating-points-v2";
+
+		/*
+		 * The three following nodes are marked with opp-suspend
+		 * because the can not be enabled simultaneously on a
+		 * single SoC.
+		 */
+		opp50@300000000 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-microvolt = <950000 931000 969000>;
+			opp-supported-hw = <0x06 0x0010>;
+			opp-suspend;
+		};
+
+		opp100@275000000 {
+			opp-hz = /bits/ 64 <275000000>;
+			opp-microvolt = <1100000 1078000 1122000>;
+			opp-supported-hw = <0x01 0x00FF>;
+			opp-suspend;
+		};
+
+		opp100@300000000 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-microvolt = <1100000 1078000 1122000>;
+			opp-supported-hw = <0x06 0x0020>;
+			opp-suspend;
+		};
+
+		opp100@500000000 {
+			opp-hz = /bits/ 64 <500000000>;
+			opp-microvolt = <1100000 1078000 1122000>;
+			opp-supported-hw = <0x01 0xFFFF>;
+		};
+
+		opp100@600000000 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-microvolt = <1100000 1078000 1122000>;
+			opp-supported-hw = <0x06 0x0040>;
+		};
+
+		opp120@600000000 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-microvolt = <1200000 1176000 1224000>;
+			opp-supported-hw = <0x01 0xFFFF>;
+		};
+
+		opp120@720000000 {
+			opp-hz = /bits/ 64 <720000000>;
+			opp-microvolt = <1200000 1176000 1224000>;
+			opp-supported-hw = <0x06 0x0080>;
+		};
+
+		oppturbo@720000000 {
+			opp-hz = /bits/ 64 <720000000>;
+			opp-microvolt = <1260000 1234800 1285200>;
+			opp-supported-hw = <0x01 0xFFFF>;
+		};
+
+		oppturbo@800000000 {
+			opp-hz = /bits/ 64 <800000000>;
+			opp-microvolt = <1260000 1234800 1285200>;
+			opp-supported-hw = <0x06 0x0100>;
+		};
+
+		oppnitro@1000000000 {
+			opp-hz = /bits/ 64 <1000000000>;
+			opp-microvolt = <1325000 1298500 1351500>;
+			opp-supported-hw = <0x04 0x0200>;
+		};
+	};
+
 	pmu {
 		compatible = "arm,cortex-a8-pmu";
 		interrupts = <3>;
@@ -187,7 +249,7 @@
 			reg =	<0x49000000 0x10000>;
 			reg-names = "edma3_cc";
 			interrupts = <12 13 14>;
-			interrupt-names = "edma3_ccint", "emda3_mperr",
+			interrupt-names = "edma3_ccint", "edma3_mperr",
 					  "edma3_ccerrint";
 			dma-requests = <64>;
 			#dma-cells = <2>;
@@ -679,20 +741,24 @@
 				  0x48300200 0x48300200 0x80>; /* EHRPWM */
 
 			ecap0: ecap@48300100 {
-				compatible = "ti,am33xx-ecap";
+				compatible = "ti,am3352-ecap",
+					     "ti,am33xx-ecap";
 				#pwm-cells = <3>;
 				reg = <0x48300100 0x80>;
+				clocks = <&l4ls_gclk>;
+				clock-names = "fck";
 				interrupts = <31>;
 				interrupt-names = "ecap0";
-				ti,hwmods = "ecap0";
 				status = "disabled";
 			};
 
 			ehrpwm0: pwm@48300200 {
-				compatible = "ti,am33xx-ehrpwm";
+				compatible = "ti,am3352-ehrpwm",
+					     "ti,am33xx-ehrpwm";
 				#pwm-cells = <3>;
 				reg = <0x48300200 0x80>;
-				ti,hwmods = "ehrpwm0";
+				clocks = <&ehrpwm0_tbclk>, <&l4ls_gclk>;
+				clock-names = "tbclk", "fck";
 				status = "disabled";
 			};
 		};
@@ -709,20 +775,24 @@
 				  0x48302200 0x48302200 0x80>; /* EHRPWM */
 
 			ecap1: ecap@48302100 {
-				compatible = "ti,am33xx-ecap";
+				compatible = "ti,am3352-ecap",
+					     "ti,am33xx-ecap";
 				#pwm-cells = <3>;
 				reg = <0x48302100 0x80>;
+				clocks = <&l4ls_gclk>;
+				clock-names = "fck";
 				interrupts = <47>;
 				interrupt-names = "ecap1";
-				ti,hwmods = "ecap1";
 				status = "disabled";
 			};
 
 			ehrpwm1: pwm@48302200 {
-				compatible = "ti,am33xx-ehrpwm";
+				compatible = "ti,am3352-ehrpwm",
+					     "ti,am33xx-ehrpwm";
 				#pwm-cells = <3>;
 				reg = <0x48302200 0x80>;
-				ti,hwmods = "ehrpwm1";
+				clocks = <&ehrpwm1_tbclk>, <&l4ls_gclk>;
+				clock-names = "tbclk", "fck";
 				status = "disabled";
 			};
 		};
@@ -739,20 +809,24 @@
 				  0x48304200 0x48304200 0x80>; /* EHRPWM */
 
 			ecap2: ecap@48304100 {
-				compatible = "ti,am33xx-ecap";
+				compatible = "ti,am3352-ecap",
+					     "ti,am33xx-ecap";
 				#pwm-cells = <3>;
 				reg = <0x48304100 0x80>;
+				clocks = <&l4ls_gclk>;
+				clock-names = "fck";
 				interrupts = <61>;
 				interrupt-names = "ecap2";
-				ti,hwmods = "ecap2";
 				status = "disabled";
 			};
 
 			ehrpwm2: pwm@48304200 {
-				compatible = "ti,am33xx-ehrpwm";
+				compatible = "ti,am3352-ehrpwm",
+					     "ti,am33xx-ehrpwm";
 				#pwm-cells = <3>;
 				reg = <0x48304200 0x80>;
-				ti,hwmods = "ehrpwm2";
+				clocks = <&ehrpwm2_tbclk>, <&l4ls_gclk>;
+				clock-names = "tbclk", "fck";
 				status = "disabled";
 			};
 		};
diff --git a/arch/arm/boot/dts/am3517-craneboard.dts b/arch/arm/boot/dts/am3517-craneboard.dts
index cb7de1d4e05f..f9d8f3948c4a 100644
--- a/arch/arm/boot/dts/am3517-craneboard.dts
+++ b/arch/arm/boot/dts/am3517-craneboard.dts
@@ -20,7 +20,7 @@
 		reg = <0x80000000 0x10000000>;	/* 256 MB */
 	};
 
-	vbat: fixedregulator@0 {
+	vbat: fixedregulator {
 		compatible = "regulator-fixed";
 		regulator-name = "vbat";
 		regulator-min-microvolt = <5000000>;
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index cd81ecf12731..0fadae5396e1 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -44,10 +44,49 @@
 			clocks = <&dpll_mpu_ck>;
 			clock-names = "cpu";
 
+			operating-points-v2 = <&cpu0_opp_table>;
+			ti,syscon-efuse = <&scm_conf 0x610 0x3f 0>;
+			ti,syscon-rev = <&scm_conf 0x600>;
+
 			clock-latency = <300000>; /* From omap-cpufreq driver */
 		};
 	};
 
+	cpu0_opp_table: opp_table0 {
+		compatible = "operating-points-v2";
+
+		opp50@300000000 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-microvolt = <950000 931000 969000>;
+			opp-supported-hw = <0xFF 0x01>;
+			opp-suspend;
+		};
+
+		opp100@600000000 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-microvolt = <1100000 1078000 1122000>;
+			opp-supported-hw = <0xFF 0x04>;
+		};
+
+		opp120@720000000 {
+			opp-hz = /bits/ 64 <720000000>;
+			opp-microvolt = <1200000 1176000 1224000>;
+			opp-supported-hw = <0xFF 0x08>;
+		};
+
+		oppturbo@800000000 {
+			opp-hz = /bits/ 64 <800000000>;
+			opp-microvolt = <1260000 1234800 1285200>;
+			opp-supported-hw = <0xFF 0x10>;
+		};
+
+		oppnitro@1000000000 {
+			opp-hz = /bits/ 64 <1000000000>;
+			opp-microvolt = <1325000 1298500 1351500>;
+			opp-supported-hw = <0xFF 0x20>;
+		};
+	};
+
 	gic: interrupt-controller@48241000 {
 		compatible = "arm,cortex-a9-gic";
 		interrupt-controller;
@@ -199,7 +238,7 @@
 			interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "edma3_ccint", "emda3_mperr",
+			interrupt-names = "edma3_ccint", "edma3_mperr",
 					  "edma3_ccerrint";
 			dma-requests = <64>;
 			#dma-cells = <2>;
@@ -671,18 +710,24 @@
 			status = "disabled";
 
 			ecap0: ecap@48300100 {
-				compatible = "ti,am4372-ecap","ti,am33xx-ecap";
+				compatible = "ti,am4372-ecap",
+					     "ti,am3352-ecap",
+					     "ti,am33xx-ecap";
 				#pwm-cells = <3>;
 				reg = <0x48300100 0x80>;
-				ti,hwmods = "ecap0";
+				clocks = <&l4ls_gclk>;
+				clock-names = "fck";
 				status = "disabled";
 			};
 
 			ehrpwm0: pwm@48300200 {
-				compatible = "ti,am4372-ehrpwm","ti,am33xx-ehrpwm";
+				compatible = "ti,am4372-ehrpwm",
+					     "ti,am3352-ehrpwm",
+					     "ti,am33xx-ehrpwm";
 				#pwm-cells = <3>;
 				reg = <0x48300200 0x80>;
-				ti,hwmods = "ehrpwm0";
+				clocks = <&ehrpwm0_tbclk>, <&l4ls_gclk>;
+				clock-names = "tbclk", "fck";
 				status = "disabled";
 			};
 		};
@@ -697,18 +742,24 @@
 			status = "disabled";
 
 			ecap1: ecap@48302100 {
-				compatible = "ti,am4372-ecap","ti,am33xx-ecap";
+				compatible = "ti,am4372-ecap",
+					     "ti,am3352-ecap",
+					     "ti,am33xx-ecap";
 				#pwm-cells = <3>;
 				reg = <0x48302100 0x80>;
-				ti,hwmods = "ecap1";
+				clocks = <&l4ls_gclk>;
+				clock-names = "fck";
 				status = "disabled";
 			};
 
 			ehrpwm1: pwm@48302200 {
-				compatible = "ti,am4372-ehrpwm","ti,am33xx-ehrpwm";
+				compatible = "ti,am4372-ehrpwm",
+					     "ti,am3352-ehrpwm",
+					     "ti,am33xx-ehrpwm";
 				#pwm-cells = <3>;
 				reg = <0x48302200 0x80>;
-				ti,hwmods = "ehrpwm1";
+				clocks = <&ehrpwm1_tbclk>, <&l4ls_gclk>;
+				clock-names = "tbclk", "fck";
 				status = "disabled";
 			};
 		};
@@ -723,18 +774,24 @@
 			status = "disabled";
 
 			ecap2: ecap@48304100 {
-				compatible = "ti,am4372-ecap","ti,am33xx-ecap";
+				compatible = "ti,am4372-ecap",
+					     "ti,am3352-ecap",
+					     "ti,am33xx-ecap";
 				#pwm-cells = <3>;
 				reg = <0x48304100 0x80>;
-				ti,hwmods = "ecap2";
+				clocks = <&l4ls_gclk>;
+				clock-names = "fck";
 				status = "disabled";
 			};
 
 			ehrpwm2: pwm@48304200 {
-				compatible = "ti,am4372-ehrpwm","ti,am33xx-ehrpwm";
+				compatible = "ti,am4372-ehrpwm",
+					     "ti,am3352-ehrpwm",
+					     "ti,am33xx-ehrpwm";
 				#pwm-cells = <3>;
 				reg = <0x48304200 0x80>;
-				ti,hwmods = "ehrpwm2";
+				clocks = <&ehrpwm2_tbclk>, <&l4ls_gclk>;
+				clock-names = "tbclk", "fck";
 				status = "disabled";
 			};
 		};
@@ -749,10 +806,13 @@
 			status = "disabled";
 
 			ehrpwm3: pwm@48306200 {
-				compatible = "ti,am4372-ehrpwm","ti,am33xx-ehrpwm";
+				compatible = "ti,am4372-ehrpwm",
+					     "ti,am3352-ehrpwm",
+					     "ti,am33xx-ehrpwm";
 				#pwm-cells = <3>;
 				reg = <0x48306200 0x80>;
-				ti,hwmods = "ehrpwm3";
+				clocks = <&ehrpwm3_tbclk>, <&l4ls_gclk>;
+				clock-names = "tbclk", "fck";
 				status = "disabled";
 			};
 		};
@@ -767,10 +827,13 @@
 			status = "disabled";
 
 			ehrpwm4: pwm@48308200 {
-				compatible = "ti,am4372-ehrpwm","ti,am33xx-ehrpwm";
+				compatible = "ti,am4372-ehrpwm",
+					     "ti,am3352-ehrpwm",
+					     "ti,am33xx-ehrpwm";
 				#pwm-cells = <3>;
 				reg = <0x48308200 0x80>;
-				ti,hwmods = "ehrpwm4";
+				clocks = <&ehrpwm4_tbclk>, <&l4ls_gclk>;
+				clock-names = "tbclk", "fck";
 				status = "disabled";
 			};
 		};
@@ -785,10 +848,13 @@
 			status = "disabled";
 
 			ehrpwm5: pwm@4830a200 {
-				compatible = "ti,am4372-ehrpwm","ti,am33xx-ehrpwm";
+				compatible = "ti,am4372-ehrpwm",
+					     "ti,am3352-ehrpwm",
+					     "ti,am33xx-ehrpwm";
 				#pwm-cells = <3>;
 				reg = <0x4830a200 0x80>;
-				ti,hwmods = "ehrpwm5";
+				clocks = <&ehrpwm5_tbclk>, <&l4ls_gclk>;
+				clock-names = "tbclk", "fck";
 				status = "disabled";
 			};
 		};
@@ -842,6 +908,13 @@
 			dma-names = "tx", "rx";
 		};
 
+		rng: rng@48310000 {
+			compatible = "ti,omap4-rng";
+			ti,hwmods = "rng";
+			reg = <0x48310000 0x2000>;
+			interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
 		mcasp0: mcasp@48038000 {
 			compatible = "ti,am33xx-mcasp-audio";
 			ti,hwmods = "mcasp0";
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index 5bcd3aa025bc..14677d599595 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -897,7 +897,7 @@
 	pinctrl-0 = <&dss_pins>;
 
 	port {
-		dpi_out: endpoint@0 {
+		dpi_out: endpoint {
 			remote-endpoint = <&lcd_in>;
 			data-lines = <24>;
 		};
@@ -975,3 +975,7 @@
 	clock-names = "ext-clk", "int-clk";
 	status = "okay";
 };
+
+&cpu {
+	cpu0-supply = <&dcdc2>;
+};
diff --git a/arch/arm/boot/dts/am437x-idk-evm.dts b/arch/arm/boot/dts/am437x-idk-evm.dts
index 76dcfc6d5f0d..12a69518383e 100644
--- a/arch/arm/boot/dts/am437x-idk-evm.dts
+++ b/arch/arm/boot/dts/am437x-idk-evm.dts
@@ -382,6 +382,7 @@
 };
 
 &mac {
+	slaves = <1>;
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&cpsw_default>;
 	pinctrl-1 = <&cpsw_sleep>;
diff --git a/arch/arm/boot/dts/am437x-sbc-t43.dts b/arch/arm/boot/dts/am437x-sbc-t43.dts
index 5f750c0ed6c9..d23260d3a581 100644
--- a/arch/arm/boot/dts/am437x-sbc-t43.dts
+++ b/arch/arm/boot/dts/am437x-sbc-t43.dts
@@ -145,7 +145,7 @@
 	pinctrl-0 = <&dss_pinctrl_default>;
 
 	port {
-		dpi_lcd_out: endpoint@0 {
+		dpi_lcd_out: endpoint {
 			remote-endpoint = <&lcd_in>;
 			data-lines = <24>;
 		};
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index 3549b8c9ac49..ad32e55532f8 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -754,7 +754,7 @@
 	pinctrl-0 = <&dss_pins>;
 
 	port {
-		dpi_out: endpoint@0 {
+		dpi_out: endpoint {
 			remote-endpoint = <&lcd_in>;
 			data-lines = <24>;
 		};
diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi
index 7630ba1d89e4..d1d73b725f47 100644
--- a/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -104,6 +104,14 @@
 		clock-div = <1>;
 	};
 
+	rng_fck: rng_fck {
+		#clock-cells = <0>;
+		compatible = "fixed-factor-clock";
+		clocks = <&sys_clkin_ck>;
+		clock-mult = <1>;
+		clock-div = <1>;
+	};
+
 	ehrpwm0_tbclk: ehrpwm0_tbclk@664 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
diff --git a/arch/arm/boot/dts/am57xx-sbc-am57x.dts b/arch/arm/boot/dts/am57xx-sbc-am57x.dts
index 988e99632d49..31f9be632406 100644
--- a/arch/arm/boot/dts/am57xx-sbc-am57x.dts
+++ b/arch/arm/boot/dts/am57xx-sbc-am57x.dts
@@ -128,7 +128,7 @@
 	vdda_video-supply = <&ldoln_reg>;
 
 	port {
-		dpi_lcd_out: endpoint@0 {
+		dpi_lcd_out: endpoint {
 			remote-endpoint = <&lcd_in>;
 			data-lines = <24>;
 		};
diff --git a/arch/arm/boot/dts/animeo_ip.dts b/arch/arm/boot/dts/animeo_ip.dts
index 0962f2fa3f6e..9cc372b9fb9b 100644
--- a/arch/arm/boot/dts/animeo_ip.dts
+++ b/arch/arm/boot/dts/animeo_ip.dts
@@ -32,15 +32,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -114,7 +105,7 @@
 			};
 		};
 
-		usb0: ohci@00500000 {
+		usb0: ohci@500000 {
 			num-ports = <2>;
 			atmel,vbus-gpio = <&pioB 15 GPIO_ACTIVE_LOW>;
 			status = "okay";
diff --git a/arch/arm/boot/dts/armada-388-clearfog.dts b/arch/arm/boot/dts/armada-388-clearfog.dts
index c60206efb583..2e0556af6e5e 100644
--- a/arch/arm/boot/dts/armada-388-clearfog.dts
+++ b/arch/arm/boot/dts/armada-388-clearfog.dts
@@ -239,22 +239,6 @@
 				status = "okay";
 			};
 
-			mdio@72004 {
-				pinctrl-0 = <&mdio_pins>;
-				pinctrl-names = "default";
-
-				phy_dedicated: ethernet-phy@0 {
-					/*
-					 * Annoyingly, the marvell phy driver
-					 * configures the LED register, rather
-					 * than preserving reset-loaded setting.
-					 * We undo that rubbish here.
-					 */
-					marvell,reg-init = <3 16 0 0x101e>;
-					reg = <0>;
-				};
-			};
-
 			pinctrl@18000 {
 				clearfog_dsa0_clk_pins: clearfog-dsa0-clk-pins {
 					marvell,pins = "mpp46";
diff --git a/arch/arm/boot/dts/at91-ariag25.dts b/arch/arm/boot/dts/at91-ariag25.dts
index e9ced30159a7..4da011a7a698 100644
--- a/arch/arm/boot/dts/at91-ariag25.dts
+++ b/arch/arm/boot/dts/at91-ariag25.dts
@@ -34,15 +34,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -178,7 +169,7 @@
 
 	};
 
-	onewire@0 {
+	onewire {
 		compatible = "w1-gpio";
 		gpios = <&pioA 21 GPIO_ACTIVE_LOW>;
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/at91-cosino.dtsi b/arch/arm/boot/dts/at91-cosino.dtsi
index b6ea3f4a7206..02d8ef43de3a 100644
--- a/arch/arm/boot/dts/at91-cosino.dtsi
+++ b/arch/arm/boot/dts/at91-cosino.dtsi
@@ -26,15 +26,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/at91-foxg20.dts b/arch/arm/boot/dts/at91-foxg20.dts
index 6bf873e7d96c..50d5e719b451 100644
--- a/arch/arm/boot/dts/at91-foxg20.dts
+++ b/arch/arm/boot/dts/at91-foxg20.dts
@@ -23,15 +23,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -128,13 +119,13 @@
 			};
 		};
 
-		usb0: ohci@00500000 {
+		usb0: ohci@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_i2c0>;
 		i2c-gpio,delay-us = <5>;	/* ~85 kHz */
diff --git a/arch/arm/boot/dts/at91-kizbox.dts b/arch/arm/boot/dts/at91-kizbox.dts
index 229e989eb60d..b4f147c193fd 100644
--- a/arch/arm/boot/dts/at91-kizbox.dts
+++ b/arch/arm/boot/dts/at91-kizbox.dts
@@ -54,7 +54,7 @@
 			};
 		};
 
-		usb0: ohci@00500000 {
+		usb0: ohci@500000 {
 			num-ports = <1>;
 			status = "okay";
 		};
@@ -96,7 +96,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 
 		rtc: pcf8563@51 {
diff --git a/arch/arm/boot/dts/at91-qil_a9260.dts b/arch/arm/boot/dts/at91-qil_a9260.dts
index 4f2eebf4a560..8f019184fccf 100644
--- a/arch/arm/boot/dts/at91-qil_a9260.dts
+++ b/arch/arm/boot/dts/at91-qil_a9260.dts
@@ -20,15 +20,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -111,7 +102,7 @@
 			};
 		};
 
-		usb0: ohci@00500000 {
+		usb0: ohci@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
@@ -187,7 +178,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 	};
 };
diff --git a/arch/arm/boot/dts/at91-sam9_l9260.dts b/arch/arm/boot/dts/at91-sam9_l9260.dts
new file mode 100644
index 000000000000..171243ca4f2f
--- /dev/null
+++ b/arch/arm/boot/dts/at91-sam9_l9260.dts
@@ -0,0 +1,121 @@
+/*
+ * at91-sam9_l9260.dts - Device Tree file for Olimex SAM9-L9260 board
+ *
+ *  Copyright (C) 2016 Raashid Muhammed <raashidmuhammed@zilogic.com>
+ *
+ * Licensed under GPLv2 or later.
+ */
+/dts-v1/;
+#include "at91sam9260.dtsi"
+
+/ {
+	model = "Olimex sam9-l9260";
+	compatible = "olimex,sam9-l9260", "atmel,at91sam9260", "atmel,at91sam9";
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory {
+		reg = <0x20000000 0x4000000>;
+	};
+
+	clocks {
+		slow_xtal {
+			clock-frequency = <32768>;
+		};
+
+		main_xtal {
+			clock-frequency = <18432000>;
+		};
+	};
+
+	ahb {
+		apb {
+			mmc0: mmc@fffa8000 {
+				pinctrl-0 = <
+					&pinctrl_board_mmc0
+					&pinctrl_mmc0_clk
+					&pinctrl_mmc0_slot1_cmd_dat0
+					&pinctrl_mmc0_slot1_dat1_3>;
+				status = "okay";
+
+				slot@1 {
+					reg = <1>;
+					bus-width = <4>;
+					cd-gpios = <&pioC 8 GPIO_ACTIVE_HIGH>;
+					wp-gpios = <&pioC 4 GPIO_ACTIVE_HIGH>;
+				};
+			};
+
+			macb0: ethernet@fffc4000 {
+				pinctrl-0 = <&pinctrl_macb_rmii &pinctrl_macb_rmii_mii_alt>;
+				phy-mode = "mii";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "okay";
+
+				ethernet-phy@1 {
+					reg = <0x1>;
+				};
+			};
+
+			spi0: spi@fffc8000 {
+				cs-gpios = <&pioC 11 0>, <0>, <0>, <0>;
+				status = "okay";
+
+				flash@0 {
+					compatible = "atmel,at45", "atmel,dataflash";
+					spi-max-frequency = <15000000>;
+					reg = <0>;
+				};
+			};
+
+			dbgu: serial@fffff200 {
+				status = "okay";
+			};
+
+			pinctrl@fffff400 {
+				mmc0 {
+					pinctrl_board_mmc0: mmc0-board {
+						atmel,pins =
+							<AT91_PIOC 8 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH	/* CD pin */
+							 AT91_PIOC 4 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP>;	/* WP pin */
+					};
+				};
+			};
+		};
+
+		nand0: nand@40000000 {
+			nand-bus-width = <8>;
+			nand-ecc-mode = "soft";
+			nand-on-flash-bbt = <1>;
+			status = "okay";
+		};
+
+		usb0: ohci@500000 {
+			status = "okay";
+		};
+
+	};
+
+	i2c-gpio-0 {
+		status = "okay";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		pwr_led {
+			label = "sam9-l9260:yellow:pwr";
+			gpios = <&pioA 9 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "cpu0";
+		};
+
+		status_led {
+			label = "sam9-l9260:green:status";
+			gpios = <&pioA 6 GPIO_ACTIVE_LOW>;
+			linux,default-trigger = "timer";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
index eb4f1ac96271..0b9a59d5fdac 100644
--- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -158,56 +158,64 @@
 				i2c-sda-hold-time-ns = <350>;
 				status = "okay";
 
-				pmic: act8865@5b {
-					compatible = "active-semi,act8865";
+				pmic@5b {
+					compatible = "active-semi,act8945a";
 					reg = <0x5b>;
 					active-semi,vsel-high;
+					active-semi,chglev-gpios = <&pioA 12 GPIO_ACTIVE_HIGH>;
+					active-semi,lbo-gpios = <&pioA 72 GPIO_ACTIVE_LOW>;
+					active-semi,irq_gpios = <&pioA 45 GPIO_ACTIVE_LOW>;
+					active-semi,input-voltage-threshold-microvolt = <6600>;
+					active-semi,precondition-timeout = <40>;
+					active-semi,total-timeout = <3>;
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_charger_chglev &pinctrl_charger_lbo &pinctrl_charger_irq>;
 					status = "okay";
 
 					regulators {
-						vdd_1v35_reg: DCDC_REG1 {
+						vdd_1v35_reg: REG_DCDC1 {
 							regulator-name = "VDD_1V35";
 							regulator-min-microvolt = <1350000>;
 							regulator-max-microvolt = <1350000>;
 							regulator-always-on;
 						};
 
-						vdd_1v2_reg: DCDC_REG2 {
+						vdd_1v2_reg: REG_DCDC2 {
 							regulator-name = "VDD_1V2";
 							regulator-min-microvolt = <1100000>;
 							regulator-max-microvolt = <1300000>;
 							regulator-always-on;
 						};
 
-						vdd_3v3_reg: DCDC_REG3 {
+						vdd_3v3_reg: REG_DCDC3 {
 							regulator-name = "VDD_3V3";
 							regulator-min-microvolt = <3300000>;
 							regulator-max-microvolt = <3300000>;
 							regulator-always-on;
 						};
 
-						vdd_fuse_reg: LDO_REG1 {
+						vdd_fuse_reg: REG_LDO1 {
 							regulator-name = "VDD_FUSE";
 							regulator-min-microvolt = <2500000>;
 							regulator-max-microvolt = <2500000>;
 							regulator-always-on;
 						};
 
-						vdd_3v3_lp_reg: LDO_REG2 {
+						vdd_3v3_lp_reg: REG_LDO2 {
 							regulator-name = "VDD_3V3_LP";
 							regulator-min-microvolt = <3300000>;
 							regulator-max-microvolt = <3300000>;
 							regulator-always-on;
 						};
 
-						vdd_led_reg: LDO_REG3 {
+						vdd_led_reg: REG_LDO3 {
 							regulator-name = "VDD_LED";
 							regulator-min-microvolt = <3300000>;
 							regulator-max-microvolt = <3300000>;
 							regulator-always-on;
 						};
 
-						vdd_sdhc_1v8_reg: LDO_REG4 {
+						vdd_sdhc_1v8_reg: REG_LDO4 {
 							regulator-name = "VDD_SDHC_1V8";
 							regulator-min-microvolt = <1800000>;
 							regulator-max-microvolt = <1800000>;
@@ -309,6 +317,21 @@
 					bias-disable;
 				};
 
+				pinctrl_charger_chglev: charger_chglev {
+					pinmux = <PIN_PA12__GPIO>;
+					bias-disable;
+				};
+
+				pinctrl_charger_irq: charger_irq {
+					pinmux = <PIN_PB13__GPIO>;
+					bias-disable;
+				};
+
+				pinctrl_charger_lbo: charger_lbo {
+					pinmux = <PIN_PC8__GPIO>;
+					bias-pull-up;
+				};
+
 				pinctrl_flx0_default: flx0_default {
 					pinmux = <PIN_PB28__FLEXCOM0_IO0>,
 						 <PIN_PB29__FLEXCOM0_IO1>;
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
index f3e2b96c06a3..c51fc652f6c7 100644
--- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -297,7 +297,7 @@
 		};
 	};
 
-	vcc_mmc0_reg: fixedregulator@0 {
+	vcc_mmc0_reg: fixedregulator_mmc0 {
 		compatible = "regulator-fixed";
 		gpio = <&pioE 2 GPIO_ACTIVE_LOW>;
 		regulator-name = "mmc0-card-supply";
diff --git a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi
index e7b2109fc85a..a92c6e0ca854 100644
--- a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi
+++ b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi
@@ -20,8 +20,11 @@
 	};
 
 	clocks {
-		main_clock: main_clock {
-			compatible = "atmel,osc", "fixed-clock";
+		slow_xtal {
+			clock-frequency = <32768>;
+		};
+
+		main_xtal {
 			clock-frequency = <12000000>;
 		};
 
@@ -106,7 +109,7 @@
 		};
 	};
 
-	vcc_3v3_reg: fixedregulator@0 {
+	vcc_3v3_reg: fixedregulator_3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC 3V3";
 		regulator-min-microvolt = <3300000>;
@@ -115,7 +118,7 @@
 		regulator-always-on;
 	};
 
-	vcc_mmc0_reg: fixedregulator@1 {
+	vcc_mmc0_reg: fixedregulator_mmc0 {
 		compatible = "regulator-fixed";
 		gpio = <&pioE 15 GPIO_ACTIVE_HIGH>;
 		regulator-name = "RST_n MCI0";
diff --git a/arch/arm/boot/dts/at91-sama5d4_ma5d4evk.dts b/arch/arm/boot/dts/at91-sama5d4_ma5d4evk.dts
index abaaba58fbec..eac4ea2744cc 100644
--- a/arch/arm/boot/dts/at91-sama5d4_ma5d4evk.dts
+++ b/arch/arm/boot/dts/at91-sama5d4_ma5d4evk.dts
@@ -159,7 +159,7 @@
 		};
 	};
 
-	vcc_mmc1_reg: fixedregulator@2 {
+	vcc_mmc1_reg: fixedregulator_mmc1 {
 		compatible = "regulator-fixed";
 		gpio = <&pioE 17 GPIO_ACTIVE_LOW>;
 		regulator-name = "VDD MCI1";
diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
index da84e65b56ef..ed7fce297738 100644
--- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
@@ -252,7 +252,7 @@
 		};
 	};
 
-	vcc_3v3_reg: fixedregulator@0 {
+	vcc_3v3_reg: fixedregulator_3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC 3V3";
 		regulator-min-microvolt = <3300000>;
@@ -261,7 +261,7 @@
 		regulator-always-on;
 	};
 
-	vcc_mmc1_reg: fixedregulator@1 {
+	vcc_mmc1_reg: fixedregulator_mmc1 {
 		compatible = "regulator-fixed";
 		gpio = <&pioE 4 GPIO_ACTIVE_LOW>;
 		regulator-name = "VDD MCI1";
diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts
index 4e98cda97403..f8b96cef5e1a 100644
--- a/arch/arm/boot/dts/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d4ek.dts
@@ -69,26 +69,6 @@
 
 	ahb {
 		apb {
-			lcd_bus@f0000000 {
-				status = "okay";
-
-				lcd@f0000000 {
-					status = "okay";
-				};
-
-				lcdovl1@f0000140 {
-					status = "okay";
-				};
-
-				lcdovl2@f0000240 {
-					status = "okay";
-				};
-
-				lcdheo1@f0000340 {
-					status = "okay";
-				};
-			};
-
 			adc0: adc@fc034000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <
diff --git a/arch/arm/boot/dts/at91-vinco.dts b/arch/arm/boot/dts/at91-vinco.dts
index 6a366ee952a8..e0c0b2897a49 100644
--- a/arch/arm/boot/dts/at91-vinco.dts
+++ b/arch/arm/boot/dts/at91-vinco.dts
@@ -245,7 +245,7 @@
 
 	};
 
-	vcc_3v3_reg: fixedregulator@0 {
+	vcc_3v3_reg: fixedregulator_3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC 3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm/boot/dts/at91rm9200.dtsi b/arch/arm/boot/dts/at91rm9200.dtsi
index f6cb7a80a2f5..4e913c2ccb79 100644
--- a/arch/arm/boot/dts/at91rm9200.dtsi
+++ b/arch/arm/boot/dts/at91rm9200.dtsi
@@ -948,7 +948,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		compatible = "i2c-gpio";
 		gpios = <&pioA 25 GPIO_ACTIVE_HIGH /* sda */
 			 &pioA 26 GPIO_ACTIVE_HIGH /* scl */
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index d4884dd1c243..a3e363d79122 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -938,25 +938,21 @@
 				atmel,adc-res-names = "lowres", "highres";
 				atmel,adc-use-res = "highres";
 
-				trigger@0 {
-					reg = <0>;
+				trigger0 {
 					trigger-name = "timer-counter-0";
 					trigger-value = <0x1>;
 				};
-				trigger@1 {
-					reg = <1>;
+				trigger1 {
 					trigger-name = "timer-counter-1";
 					trigger-value = <0x3>;
 				};
 
-				trigger@2 {
-					reg = <2>;
+				trigger2 {
 					trigger-name = "timer-counter-2";
 					trigger-value = <0x5>;
 				};
 
-				trigger@3 {
-					reg = <3>;
+				trigger3 {
 					trigger-name = "external";
 					trigger-value = <0xd>;
 					trigger-external;
@@ -1007,7 +1003,7 @@
 			status = "disabled";
 		};
 
-		usb0: ohci@00500000 {
+		usb0: ohci@500000 {
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00500000 0x100000>;
 			interrupts = <20 IRQ_TYPE_LEVEL_HIGH 2>;
@@ -1017,7 +1013,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		compatible = "i2c-gpio";
 		gpios = <&pioA 23 GPIO_ACTIVE_HIGH /* sda */
 			 &pioA 24 GPIO_ACTIVE_HIGH /* scl */
diff --git a/arch/arm/boot/dts/at91sam9260ek.dts b/arch/arm/boot/dts/at91sam9260ek.dts
new file mode 100644
index 000000000000..2c87f58448e7
--- /dev/null
+++ b/arch/arm/boot/dts/at91sam9260ek.dts
@@ -0,0 +1,211 @@
+/*
+ * Device Tree file for Atmel at91sam9260 Evaluation Kit
+ *
+ *  Copyright (C) 2016 Atmel,
+ *		  2016 Nicolas Ferre <nicolas.ferre@atmel.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+/dts-v1/;
+#include "at91sam9260.dtsi"
+
+/ {
+	model = "Atmel at91sam9260ek";
+	compatible = "atmel,at91sam9260ek", "atmel,at91sam9260", "atmel,at91sam9";
+
+	chosen {
+		stdout-path = &dbgu;
+	};
+
+	memory {
+		reg = <0x20000000 0x4000000>;
+	};
+
+	clocks {
+		slow_xtal {
+			clock-frequency = <32768>;
+		};
+
+		main_xtal {
+			clock-frequency = <18432000>;
+		};
+	};
+
+	ahb {
+		apb {
+			usb1: gadget@fffa4000 {
+				atmel,vbus-gpio = <&pioC 5 GPIO_ACTIVE_HIGH>;
+				status = "okay";
+			};
+
+			mmc0: mmc@fffa8000 {
+				pinctrl-0 = <
+					&pinctrl_board_mmc0_slot1
+					&pinctrl_mmc0_clk
+					&pinctrl_mmc0_slot1_cmd_dat0
+					&pinctrl_mmc0_slot1_dat1_3>;
+				status = "okay";
+				slot@1 {
+					reg = <1>;
+					bus-width = <4>;
+					cd-gpios = <&pioC 9 GPIO_ACTIVE_HIGH>;
+				};
+			};
+
+			usart0: serial@fffb0000 {
+				pinctrl-0 =
+					<&pinctrl_usart0
+					 &pinctrl_usart0_rts
+					 &pinctrl_usart0_cts
+					 &pinctrl_usart0_dtr_dsr
+					 &pinctrl_usart0_dcd
+					 &pinctrl_usart0_ri>;
+				status = "okay";
+			};
+
+			usart1: serial@fffb4000 {
+				status = "okay";
+			};
+
+			ssc0: ssc@fffbc000 {
+				status = "okay";
+				pinctrl-0 = <&pinctrl_ssc0_tx>;
+			};
+
+			macb0: ethernet@fffc4000 {
+				phy-mode = "rmii";
+				status = "okay";
+			};
+
+			spi0: spi@fffc8000 {
+				cs-gpios = <0>, <&pioC 11 0>, <0>, <0>;
+				mtd_dataflash@0 {
+					compatible = "atmel,at45", "atmel,dataflash";
+					spi-max-frequency = <50000000>;
+					reg = <1>;
+				};
+			};
+
+			dbgu: serial@fffff200 {
+				status = "okay";
+			};
+
+			pinctrl@fffff400 {
+				board {
+					pinctrl_board_mmc0_slot1: mmc0_slot1-board {
+						atmel,pins =
+							<AT91_PIOC 9 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
+				};
+			};
+
+			shdwc@fffffd10 {
+				atmel,wakeup-counter = <10>;
+				atmel,wakeup-rtt-timer;
+			};
+
+			rtc@fffffd20 {
+				atmel,rtt-rtc-time-reg = <&gpbr 0x0>;
+				status = "okay";
+			};
+
+			watchdog@fffffd40 {
+				status = "okay";
+			};
+
+			gpbr: syscon@fffffd50 {
+				status = "okay";
+			};
+		};
+
+		usb0: ohci@500000 {
+			num-ports = <2>;
+			status = "okay";
+		};
+
+		nand0: nand@40000000 {
+			nand-bus-width = <8>;
+			nand-ecc-mode = "soft";
+			nand-on-flash-bbt;
+			status = "okay";
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+
+		btn3 {
+			label = "Button 3";
+			gpios = <&pioA 30 GPIO_ACTIVE_LOW>;
+			linux,code = <0x103>;
+			gpio-key,wakeup;
+		};
+
+		btn4 {
+			label = "Button 4";
+			gpios = <&pioA 31 GPIO_ACTIVE_LOW>;
+			linux,code = <0x104>;
+			gpio-key,wakeup;
+		};
+	};
+
+	i2c-gpio-0 {
+		status = "okay";
+
+		24c512@50 {
+			compatible = "24c512";
+			reg = <0x50>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		ds1 {
+			label = "ds1";
+			gpios = <&pioA 9 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+
+		ds5 {
+			label = "ds5";
+			gpios = <&pioA 6 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/at91sam9261.dtsi b/arch/arm/boot/dts/at91sam9261.dtsi
index 5e09de4eb9cd..32752d7883f1 100644
--- a/arch/arm/boot/dts/at91sam9261.dtsi
+++ b/arch/arm/boot/dts/at91sam9261.dtsi
@@ -860,7 +860,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		compatible = "i2c-gpio";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_i2c_bitbang>;
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index 93446420af25..aeb1a36373f4 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -1019,7 +1019,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		compatible = "i2c-gpio";
 		gpios = <&pioB 4 GPIO_ACTIVE_HIGH /* sda */
 			 &pioB 5 GPIO_ACTIVE_HIGH /* scl */
diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts
index 59df9d73d276..127cc42e9e29 100644
--- a/arch/arm/boot/dts/at91sam9263ek.dts
+++ b/arch/arm/boot/dts/at91sam9263ek.dts
@@ -215,7 +215,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 
 		24c512@50 {
diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
index e9cc99b6353a..27847a47c108 100644
--- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
+++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
@@ -170,13 +170,13 @@
 			};
 		};
 
-		usb0: ohci@00500000 {
+		usb0: ohci@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 
 		24c512@50 {
diff --git a/arch/arm/boot/dts/at91sam9g25ek.dts b/arch/arm/boot/dts/at91sam9g25ek.dts
index 707fd4ea58f5..91a71774472e 100644
--- a/arch/arm/boot/dts/at91sam9g25ek.dts
+++ b/arch/arm/boot/dts/at91sam9g25ek.dts
@@ -26,7 +26,24 @@
 
 			i2c0: i2c@f8010000 {
 				ov2640: camera@0x30 {
+					compatible = "ovti,ov2640";
+					reg = <0x30>;
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_pck0_as_isi_mck &pinctrl_sensor_power &pinctrl_sensor_reset>;
+					resetb-gpios = <&pioA 7 GPIO_ACTIVE_LOW>;
+					pwdn-gpios = <&pioA 13 GPIO_ACTIVE_HIGH>;
+					clocks = <&pck0>;
+					clock-names = "xvclk";
+					assigned-clocks = <&pck0>;
+					assigned-clock-rates = <25000000>;
 					status = "okay";
+
+					port {
+						ov2640_0: endpoint {
+							remote-endpoint = <&isi_0>;
+							bus-width = <8>;
+						};
+					};
 				};
 			};
 
@@ -37,6 +54,15 @@
 
 			isi: isi@f8048000 {
 				status = "okay";
+				port {
+					isi_0: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&ov2640_0>;
+						bus-width = <8>;
+						vsync-active = <1>;
+						hsync-active = <1>;
+					};
+				};
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index 8837b7e4292c..b3501ae2a3bd 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -1044,28 +1044,24 @@
 				atmel,adc-res-names = "lowres", "highres";
 				atmel,adc-use-res = "highres";
 
-				trigger@0 {
-					reg = <0>;
+				trigger0 {
 					trigger-name = "external-rising";
 					trigger-value = <0x1>;
 					trigger-external;
 				};
-				trigger@1 {
-					reg = <1>;
+				trigger1 {
 					trigger-name = "external-falling";
 					trigger-value = <0x2>;
 					trigger-external;
 				};
 
-				trigger@2 {
-					reg = <2>;
+				trigger2 {
 					trigger-name = "external-any";
 					trigger-value = <0x3>;
 					trigger-external;
 				};
 
-				trigger@3 {
-					reg = <3>;
+				trigger3 {
 					trigger-name = "continuous";
 					trigger-value = <0x6>;
 				};
@@ -1169,13 +1165,13 @@
 				clock-names = "pclk", "hclk";
 				status = "disabled";
 
-				ep0 {
+				ep@0 {
 					reg = <0>;
 					atmel,fifo-size = <64>;
 					atmel,nb-banks = <1>;
 				};
 
-				ep1 {
+				ep@1 {
 					reg = <1>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <2>;
@@ -1183,7 +1179,7 @@
 					atmel,can-isoc;
 				};
 
-				ep2 {
+				ep@2 {
 					reg = <2>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <2>;
@@ -1191,21 +1187,21 @@
 					atmel,can-isoc;
 				};
 
-				ep3 {
+				ep@3 {
 					reg = <3>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
 					atmel,can-dma;
 				};
 
-				ep4 {
+				ep@4 {
 					reg = <4>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
 					atmel,can-dma;
 				};
 
-				ep5 {
+				ep@5 {
 					reg = <5>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
@@ -1213,7 +1209,7 @@
 					atmel,can-isoc;
 				};
 
-				ep6 {
+				ep@6 {
 					reg = <6>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
@@ -1320,7 +1316,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		compatible = "i2c-gpio";
 		gpios = <&pioA 20 GPIO_ACTIVE_HIGH /* sda */
 			 &pioA 21 GPIO_ACTIVE_HIGH /* scl */
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index 95569a87b6c9..3b3eb3edcb47 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -1030,7 +1030,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		compatible = "i2c-gpio";
 		gpios = <&pioA 30 GPIO_ACTIVE_HIGH /* sda */
 			 &pioA 31 GPIO_ACTIVE_HIGH /* scl */
diff --git a/arch/arm/boot/dts/at91sam9rl.dtsi b/arch/arm/boot/dts/at91sam9rl.dtsi
index 6d829db4e887..70adf940d98c 100644
--- a/arch/arm/boot/dts/at91sam9rl.dtsi
+++ b/arch/arm/boot/dts/at91sam9rl.dtsi
@@ -265,25 +265,21 @@
 				atmel,adc-res-names = "lowres", "highres";
 				atmel,adc-use-res = "highres";
 
-				trigger@0 {
-					reg = <0>;
+				trigger0 {
 					trigger-name = "timer-counter-0";
 					trigger-value = <0x1>;
 				};
-				trigger@1 {
-					reg = <1>;
+				trigger1 {
 					trigger-name = "timer-counter-1";
 					trigger-value = <0x3>;
 				};
 
-				trigger@2 {
-					reg = <2>;
+				trigger2 {
 					trigger-name = "timer-counter-2";
 					trigger-value = <0x5>;
 				};
 
-				trigger@3 {
-					reg = <3>;
+				trigger3 {
 					trigger-name = "external";
 					trigger-value = <0x13>;
 					trigger-external;
@@ -301,13 +297,13 @@
 				clock-names = "pclk", "hclk";
 				status = "disabled";
 
-				ep0 {
+				ep@0 {
 					reg = <0>;
 					atmel,fifo-size = <64>;
 					atmel,nb-banks = <1>;
 				};
 
-				ep1 {
+				ep@1 {
 					reg = <1>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <2>;
@@ -315,7 +311,7 @@
 					atmel,can-isoc;
 				};
 
-				ep2 {
+				ep@2 {
 					reg = <2>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <2>;
@@ -323,21 +319,21 @@
 					atmel,can-isoc;
 				};
 
-				ep3 {
+				ep@3 {
 					reg = <3>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
 					atmel,can-dma;
 				};
 
-				ep4 {
+				ep@4 {
 					reg = <4>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
 					atmel,can-dma;
 				};
 
-				ep5 {
+				ep@5 {
 					reg = <5>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
@@ -345,7 +341,7 @@
 					atmel,can-isoc;
 				};
 
-				ep6 {
+				ep@6 {
 					reg = <6>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
@@ -1093,7 +1089,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		compatible = "i2c-gpio";
 		gpios = <&pioA 23 GPIO_ACTIVE_HIGH>, /* sda */
 			<&pioA 24 GPIO_ACTIVE_HIGH>; /* scl */
@@ -1107,7 +1103,7 @@
 		status = "disabled";
 	};
 
-	i2c@1 {
+	i2c-gpio-1 {
 		compatible = "i2c-gpio";
 		gpios = <&pioD 10 GPIO_ACTIVE_HIGH>, /* sda */
 			<&pioD 11 GPIO_ACTIVE_HIGH>; /* scl */
diff --git a/arch/arm/boot/dts/at91sam9rlek.dts b/arch/arm/boot/dts/at91sam9rlek.dts
index f10566f759cd..2e567d90fba8 100644
--- a/arch/arm/boot/dts/at91sam9rlek.dts
+++ b/arch/arm/boot/dts/at91sam9rlek.dts
@@ -227,11 +227,11 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 	};
 
-	i2c@1 {
+	i2c-gpio-1 {
 		status = "okay";
 	};
 };
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index cd0cd5fd09a3..ed4e4bd8a8f1 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -1048,29 +1048,25 @@
 				atmel,adc-res-names = "lowres", "highres";
 				atmel,adc-use-res = "highres";
 
-				trigger@0 {
-					reg = <0>;
+				trigger0 {
 					trigger-name = "external-rising";
 					trigger-value = <0x1>;
 					trigger-external;
 				};
 
-				trigger@1 {
-					reg = <1>;
+				trigger1 {
 					trigger-name = "external-falling";
 					trigger-value = <0x2>;
 					trigger-external;
 				};
 
-				trigger@2 {
-					reg = <2>;
+				trigger2 {
 					trigger-name = "external-any";
 					trigger-value = <0x3>;
 					trigger-external;
 				};
 
-				trigger@3 {
-					reg = <3>;
+				trigger3 {
 					trigger-name = "continuous";
 					trigger-value = <0x6>;
 				};
@@ -1119,13 +1115,13 @@
 				clock-names = "hclk", "pclk";
 				status = "disabled";
 
-				ep0 {
+				ep@0 {
 					reg = <0>;
 					atmel,fifo-size = <64>;
 					atmel,nb-banks = <1>;
 				};
 
-				ep1 {
+				ep@1 {
 					reg = <1>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <2>;
@@ -1133,7 +1129,7 @@
 					atmel,can-isoc;
 				};
 
-				ep2 {
+				ep@2 {
 					reg = <2>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <2>;
@@ -1141,21 +1137,21 @@
 					atmel,can-isoc;
 				};
 
-				ep3 {
+				ep@3 {
 					reg = <3>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
 					atmel,can-dma;
 				};
 
-				ep4 {
+				ep@4 {
 					reg = <4>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
 					atmel,can-dma;
 				};
 
-				ep5 {
+				ep@5 {
 					reg = <5>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
@@ -1163,7 +1159,7 @@
 					atmel,can-isoc;
 				};
 
-				ep6 {
+				ep@6 {
 					reg = <6>;
 					atmel,fifo-size = <1024>;
 					atmel,nb-banks = <3>;
@@ -1242,7 +1238,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		compatible = "i2c-gpio";
 		gpios = <&pioA 30 GPIO_ACTIVE_HIGH /* sda */
 			 &pioA 31 GPIO_ACTIVE_HIGH /* scl */
@@ -1257,7 +1253,7 @@
 		status = "disabled";
 	};
 
-	i2c@1 {
+	i2c-gpio-1 {
 		compatible = "i2c-gpio";
 		gpios = <&pioC 0 GPIO_ACTIVE_HIGH /* sda */
 			 &pioC 1 GPIO_ACTIVE_HIGH /* scl */
@@ -1272,7 +1268,7 @@
 		status = "disabled";
 	};
 
-	i2c@2 {
+	i2c-gpio-2 {
 		compatible = "i2c-gpio";
 		gpios = <&pioB 4 GPIO_ACTIVE_HIGH /* sda */
 			 &pioB 5 GPIO_ACTIVE_HIGH /* scl */
diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi
index 52425a4ca97e..696b8ba064a6 100644
--- a/arch/arm/boot/dts/at91sam9x5ek.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi
@@ -60,18 +60,6 @@
 				status = "okay";
 			};
 
-			isi: isi@f8048000 {
-				status = "disabled";
-				port {
-					isi_0: endpoint@0 {
-						remote-endpoint = <&ov2640_0>;
-						bus-width = <8>;
-						vsync-active = <1>;
-						hsync-active = <1>;
-					};
-				};
-			};
-
 			i2c0: i2c@f8010000 {
 				status = "okay";
 
@@ -79,27 +67,6 @@
 					compatible = "wm8731";
 					reg = <0x1a>;
 				};
-
-				ov2640: camera@0x30 {
-					compatible = "ovti,ov2640";
-					reg = <0x30>;
-					pinctrl-names = "default";
-					pinctrl-0 = <&pinctrl_pck0_as_isi_mck &pinctrl_sensor_power &pinctrl_sensor_reset>;
-					resetb-gpios = <&pioA 7 GPIO_ACTIVE_LOW>;
-					pwdn-gpios = <&pioA 13 GPIO_ACTIVE_HIGH>;
-					clocks = <&pck0>;
-					clock-names = "xvclk";
-					assigned-clocks = <&pck0>;
-					assigned-clock-rates = <25000000>;
-					status = "disabled";
-
-					port {
-						ov2640_0: endpoint {
-							remote-endpoint = <&isi_0>;
-							bus-width = <8>;
-						};
-					};
-				};
 			};
 
 			adc0: adc@f804c000 {
diff --git a/arch/arm/boot/dts/axp209.dtsi b/arch/arm/boot/dts/axp209.dtsi
index 051ab3ba9a65..afbe89c01df5 100644
--- a/arch/arm/boot/dts/axp209.dtsi
+++ b/arch/arm/boot/dts/axp209.dtsi
@@ -87,6 +87,7 @@
 
 		reg_ldo5: ldo5 {
 			regulator-name = "ldo5";
+			status = "disabled";
 		};
 	};
 
diff --git a/arch/arm/boot/dts/axp22x.dtsi b/arch/arm/boot/dts/axp22x.dtsi
index 76302f58c478..458b6681e3ec 100644
--- a/arch/arm/boot/dts/axp22x.dtsi
+++ b/arch/arm/boot/dts/axp22x.dtsi
@@ -126,10 +126,12 @@
 
 		reg_ldo_io0: ldo_io0 {
 			regulator-name = "ldo_io0";
+			status = "disabled";
 		};
 
 		reg_ldo_io1: ldo_io1 {
 			regulator-name = "ldo_io1";
+			status = "disabled";
 		};
 
 		reg_rtc_ldo: rtc_ldo {
@@ -139,5 +141,15 @@
 			regulator-max-microvolt = <3000000>;
 			regulator-name = "rtc_ldo";
 		};
+
+		reg_drivevbus: drivevbus {
+			regulator-name = "drivevbus";
+			status = "disabled";
+		};
+	};
+
+	usb_power_supply: usb_power_supply {
+		compatible = "x-powers,axp221-usb-power-supply";
+		status = "disabled";
 	};
 };
diff --git a/arch/arm/boot/dts/axp809.dtsi b/arch/arm/boot/dts/axp809.dtsi
new file mode 100644
index 000000000000..ab8e5f2d9246
--- /dev/null
+++ b/arch/arm/boot/dts/axp809.dtsi
@@ -0,0 +1,53 @@
+/*
+ * Copyright 2015 Chen-Yu Tsai
+ *
+ * Chen-Yu Tsai <wens@csie.org>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * AXP809 Integrated Power Management Chip
+ */
+
+&axp809 {
+	compatible = "x-powers,axp809";
+	interrupt-controller;
+	#interrupt-cells = <1>;
+};
diff --git a/arch/arm/boot/dts/bcm-cygnus.dtsi b/arch/arm/boot/dts/bcm-cygnus.dtsi
index b42fe5596b94..fabc9f36c408 100644
--- a/arch/arm/boot/dts/bcm-cygnus.dtsi
+++ b/arch/arm/boot/dts/bcm-cygnus.dtsi
@@ -366,5 +366,16 @@
 			interrupts = <GIC_SPI 164 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
 		};
+
+		adc: adc@180a6000 {
+			compatible = "brcm,iproc-static-adc";
+			#io-channel-cells = <1>;
+			io-channel-ranges;
+			adc-syscon = <&ts_adc_syscon>;
+			clocks = <&asiu_clks BCM_CYGNUS_ASIU_ADC_CLK>;
+			clock-names = "tsc_clk";
+			interrupts = <GIC_SPI 164 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index 6a40ed7d0502..c3bf7d23f136 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -57,7 +57,7 @@
 			compatible = "arm,cortex-a9";
 			next-level-cache = <&L2>;
 			enable-method = "brcm,bcm-nsp-smp";
-			secondary-boot-reg = <0xffff042c>;
+			secondary-boot-reg = <0xffff0fec>;
 			reg = <0x1>;
 		};
 	};
@@ -192,6 +192,23 @@
 			status = "disabled";
 		};
 
+		dma@20000 {
+			compatible = "arm,pl330", "arm,primecell";
+			reg = <0x20000 0x1000>;
+			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&iprocslow>;
+			clock-names = "apb_pclk";
+			#dma-cells = <1>;
+		};
+
 		nand: nand@26000 {
 			compatible = "brcm,nand-iproc", "brcm,brcmnand-v6.1";
 			reg = <0x026000 0x600>,
@@ -337,6 +354,18 @@
 		ranges = <0x82000000 0 0x08000000 0x08000000 0 0x8000000>;
 
 		status = "disabled";
+
+		msi-parent = <&msi0>;
+		msi0: msi@18012000 {
+			compatible = "brcm,iproc-msi";
+			msi-controller;
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_SPI 127 IRQ_TYPE_NONE>,
+				     <GIC_SPI 128 IRQ_TYPE_NONE>,
+				     <GIC_SPI 129 IRQ_TYPE_NONE>,
+				     <GIC_SPI 130 IRQ_TYPE_NONE>;
+			brcm,pcie-msi-inten;
+		};
 	};
 
 	pcie1: pcie@18013000 {
@@ -361,6 +390,18 @@
 		ranges = <0x82000000 0 0x40000000 0x40000000 0 0x8000000>;
 
 		status = "disabled";
+
+		msi-parent = <&msi1>;
+		msi1: msi@18013000 {
+			compatible = "brcm,iproc-msi";
+			msi-controller;
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_SPI 133 IRQ_TYPE_NONE>,
+				     <GIC_SPI 134 IRQ_TYPE_NONE>,
+				     <GIC_SPI 135 IRQ_TYPE_NONE>,
+				     <GIC_SPI 136 IRQ_TYPE_NONE>;
+			brcm,pcie-msi-inten;
+		};
 	};
 
 	pcie2: pcie@18014000 {
@@ -385,5 +426,17 @@
 		ranges = <0x82000000 0 0x48000000 0x48000000 0 0x8000000>;
 
 		status = "disabled";
+
+		msi-parent = <&msi2>;
+		msi2: msi@18014000 {
+			compatible = "brcm,iproc-msi";
+			msi-controller;
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_SPI 139 IRQ_TYPE_NONE>,
+				     <GIC_SPI 140 IRQ_TYPE_NONE>,
+				     <GIC_SPI 141 IRQ_TYPE_NONE>,
+				     <GIC_SPI 142 IRQ_TYPE_NONE>;
+			brcm,pcie-msi-inten;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi
index 3dc7a8cc5812..18045c38bcf1 100644
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@@ -30,7 +30,6 @@
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		enable-method = "brcm,bcm11351-cpu-method";
 
 		cpu0: cpu@0 {
 			device_type = "cpu";
@@ -41,6 +40,7 @@
 		cpu1: cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
+			enable-method = "brcm,bcm11351-cpu-method";
 			secondary-boot-reg = <0x3500417c>;
 			reg = <1>;
 		};
diff --git a/arch/arm/boot/dts/bcm21664.dtsi b/arch/arm/boot/dts/bcm21664.dtsi
index 3f525be28fd0..6dde95f21cef 100644
--- a/arch/arm/boot/dts/bcm21664.dtsi
+++ b/arch/arm/boot/dts/bcm21664.dtsi
@@ -30,7 +30,6 @@
        cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		enable-method = "brcm,bcm11351-cpu-method";
 
 		cpu0: cpu@0 {
 			device_type = "cpu";
@@ -41,6 +40,7 @@
 		cpu1: cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
+			enable-method = "brcm,bcm11351-cpu-method";
 			secondary-boot-reg = <0x35004178>;
 			reg = <1>;
 		};
diff --git a/arch/arm/boot/dts/bcm23550-sparrow.dts b/arch/arm/boot/dts/bcm23550-sparrow.dts
new file mode 100644
index 000000000000..4d525ccb48c8
--- /dev/null
+++ b/arch/arm/boot/dts/bcm23550-sparrow.dts
@@ -0,0 +1,80 @@
+/*
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Broadcom.  All rights reserved.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Broadcom Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+
+#include "bcm23550.dtsi"
+
+/ {
+	model = "BCM23550 Sparrow board";
+	compatible = "brcm,bcm23550-sparrow", "brcm,bcm23550";
+
+	chosen {
+		stdout-path = "/slaves@3e000000/serial@0:115200n8";
+		bootargs = "console=ttyS0,115200n8";
+	};
+
+	memory {
+		reg = <0x80000000 0x20000000>; /* 512 MB */
+	};
+};
+
+&uartb {
+	status = "okay";
+};
+
+&usbotg {
+	status = "okay";
+};
+
+&usbphy {
+	status = "okay";
+};
+
+&sdio1 {
+	max-frequency = <48000000>;
+	status = "okay";
+};
+
+&sdio2 {
+	non-removable;
+	max-frequency = <48000000>;
+	status = "okay";
+};
+
+&sdio4 {
+	max-frequency = <48000000>;
+	cd-gpios = <&gpio 91 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm23550.dtsi b/arch/arm/boot/dts/bcm23550.dtsi
new file mode 100644
index 000000000000..a7a643f38385
--- /dev/null
+++ b/arch/arm/boot/dts/bcm23550.dtsi
@@ -0,0 +1,415 @@
+/*
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Broadcom.  All rights reserved.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Broadcom Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/* BCM23550 and BCM21664 have almost identical clocks */
+#include "dt-bindings/clock/bcm21664.h"
+
+#include "skeleton.dtsi"
+
+/ {
+	model = "BCM23550 SoC";
+	compatible = "brcm,bcm23550";
+	interrupt-parent = <&gic>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0>;
+			clock-frequency = <1000000000>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			enable-method = "brcm,bcm23550";
+			secondary-boot-reg = <0x35004178>;
+			reg = <1>;
+			clock-frequency = <1000000000>;
+		};
+
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			enable-method = "brcm,bcm23550";
+			secondary-boot-reg = <0x35004178>;
+			reg = <2>;
+			clock-frequency = <1000000000>;
+		};
+
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			enable-method = "brcm,bcm23550";
+			secondary-boot-reg = <0x35004178>;
+			reg = <3>;
+			clock-frequency = <1000000000>;
+		};
+	};
+
+	/* Hub bus */
+	hub@34000000 {
+		compatible = "simple-bus";
+		ranges = <0 0x34000000 0x102f83ac>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		smc@4e000 {
+			compatible = "brcm,bcm23550-smc", "brcm,kona-smc";
+			reg = <0x0004e000 0x400>; /* 1 KiB in SRAM */
+		};
+
+		resetmgr: reset-controller@1001f00 {
+			compatible = "brcm,bcm21664-resetmgr";
+			reg = <0x01001f00 0x24>;
+		};
+
+		gpio: gpio@1003000 {
+			compatible = "brcm,bcm23550-gpio", "brcm,kona-gpio";
+			reg = <0x01003000 0x524>;
+			interrupts =
+			       <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH
+				GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH
+				GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH
+				GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
+			#gpio-cells = <2>;
+			#interrupt-cells = <2>;
+			gpio-controller;
+			interrupt-controller;
+		};
+
+		timer@1006000 {
+			compatible = "brcm,kona-timer";
+			reg = <0x01006000 0x1c>;
+			interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&aon_ccu BCM21664_AON_CCU_HUB_TIMER>;
+		};
+	};
+
+	/* Slaves bus */
+	slaves@3e000000 {
+		compatible = "simple-bus";
+		ranges = <0 0x3e000000 0x0001c070>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		uartb: serial@0 {
+			compatible = "snps,dw-apb-uart";
+			status = "disabled";
+			reg = <0x00000000 0x118>;
+			clocks = <&slave_ccu BCM21664_SLAVE_CCU_UARTB>;
+			interrupts = <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		uartb2: serial@1000 {
+			compatible = "snps,dw-apb-uart";
+			status = "disabled";
+			reg = <0x00001000 0x118>;
+			clocks = <&slave_ccu BCM21664_SLAVE_CCU_UARTB2>;
+			interrupts = <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		uartb3: serial@2000 {
+			compatible = "snps,dw-apb-uart";
+			status = "disabled";
+			reg = <0x00002000 0x118>;
+			clocks = <&slave_ccu BCM21664_SLAVE_CCU_UARTB3>;
+			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+		};
+
+		bsc1: i2c@16000 {
+			compatible = "brcm,kona-i2c";
+			reg = <0x00016000 0x70>;
+			interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&slave_ccu BCM21664_SLAVE_CCU_BSC1>;
+			status = "disabled";
+		};
+
+		bsc2: i2c@17000 {
+			compatible = "brcm,kona-i2c";
+			reg = <0x00017000 0x70>;
+			interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&slave_ccu BCM21664_SLAVE_CCU_BSC2>;
+			status = "disabled";
+		};
+
+		bsc3: i2c@18000 {
+			compatible = "brcm,kona-i2c";
+			reg = <0x00018000 0x70>;
+			interrupts = <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&slave_ccu BCM21664_SLAVE_CCU_BSC3>;
+			status = "disabled";
+		};
+
+		bsc4: i2c@1c000 {
+			compatible = "brcm,kona-i2c";
+			reg = <0x0001c000 0x70>;
+			interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&slave_ccu BCM21664_SLAVE_CCU_BSC4>;
+			status = "disabled";
+		};
+	};
+
+	/* Apps bus */
+	apps@3e300000 {
+		compatible = "simple-bus";
+		ranges = <0 0x3e300000 0x01b77000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		usbotg: usb@e20000 {
+			compatible = "snps,dwc2";
+			reg = <0x00e20000 0x10000>;
+			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&usb_otg_ahb_clk>;
+			clock-names = "otg";
+			phys = <&usbphy>;
+			phy-names = "usb2-phy";
+			status = "disabled";
+		};
+
+		usbphy: usb-phy@e30000 {
+			compatible = "brcm,kona-usb2-phy";
+			reg = <0x00e30000 0x28>;
+			#phy-cells = <0>;
+			status = "disabled";
+		};
+
+		sdio1: sdio@e80000 {
+			compatible = "brcm,kona-sdhci";
+			reg = <0x00e80000 0x801c>;
+			interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&master_ccu BCM21664_MASTER_CCU_SDIO1>;
+			status = "disabled";
+		};
+
+		sdio2: sdio@e90000 {
+			compatible = "brcm,kona-sdhci";
+			reg = <0x00e90000 0x801c>;
+			interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&master_ccu BCM21664_MASTER_CCU_SDIO2>;
+			status = "disabled";
+		};
+
+		sdio3: sdio@ea0000 {
+			compatible = "brcm,kona-sdhci";
+			reg = <0x00ea0000 0x801c>;
+			interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&master_ccu BCM21664_MASTER_CCU_SDIO3>;
+			status = "disabled";
+		};
+
+		sdio4: sdio@eb0000 {
+			compatible = "brcm,kona-sdhci";
+			reg = <0x00eb0000 0x801c>;
+			interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&master_ccu BCM21664_MASTER_CCU_SDIO4>;
+			status = "disabled";
+		};
+
+		cdc: cdc@1b0e000 {
+			compatible = "brcm,bcm23550-cdc";
+			reg = <0x01b0e000 0x78>;
+		};
+
+		gic: interrupt-controller@1b21000 {
+			compatible = "arm,cortex-a9-gic";
+			#interrupt-cells = <3>;
+			#address-cells = <0>;
+			interrupt-controller;
+			reg = <0x01b21000 0x1000>,
+			      <0x01b22000 0x1000>;
+		};
+	};
+
+	clocks {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		/*
+		 * Fixed clocks are defined before CCUs whose
+		 * clocks may depend on them.
+		 */
+
+		ref_32k_clk: ref_32k {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <32768>;
+		};
+
+		bbl_32k_clk: bbl_32k {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <32768>;
+		};
+
+		ref_13m_clk: ref_13m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <13000000>;
+		};
+
+		var_13m_clk: var_13m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <13000000>;
+		};
+
+		dft_19_5m_clk: dft_19_5m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <19500000>;
+		};
+
+		ref_crystal_clk: ref_crystal {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <26000000>;
+		};
+
+		ref_52m_clk: ref_52m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <52000000>;
+		};
+
+		var_52m_clk: var_52m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <52000000>;
+		};
+
+		usb_otg_ahb_clk: usb_otg_ahb {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <52000000>;
+		};
+
+		ref_96m_clk: ref_96m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <96000000>;
+		};
+
+		var_96m_clk: var_96m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <96000000>;
+		};
+
+		ref_104m_clk: ref_104m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <104000000>;
+		};
+
+		var_104m_clk: var_104m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <104000000>;
+		};
+
+		ref_156m_clk: ref_156m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <156000000>;
+		};
+
+		var_156m_clk: var_156m {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <156000000>;
+		};
+
+		root_ccu: root_ccu {
+			compatible = BCM21664_DT_ROOT_CCU_COMPAT;
+			reg = <0x35001000 0x0f00>;
+			#clock-cells = <1>;
+			clock-output-names = "frac_1m";
+		};
+
+		aon_ccu: aon_ccu {
+			compatible = BCM21664_DT_AON_CCU_COMPAT;
+			reg = <0x35002000 0x0f00>;
+			#clock-cells = <1>;
+			clock-output-names = "hub_timer";
+		};
+
+		slave_ccu: slave_ccu {
+			compatible = BCM21664_DT_SLAVE_CCU_COMPAT;
+			reg = <0x3e011000 0x0f00>;
+			#clock-cells = <1>;
+			clock-output-names = "uartb",
+					     "uartb2",
+					     "uartb3",
+					     "bsc1",
+					     "bsc2",
+					     "bsc3",
+					     "bsc4";
+		};
+
+		master_ccu: master_ccu {
+			compatible = BCM21664_DT_MASTER_CCU_COMPAT;
+			reg = <0x3f001000 0x0f00>;
+			#clock-cells = <1>;
+			clock-output-names = "sdio1",
+					     "sdio2",
+					     "sdio3",
+					     "sdio4",
+					     "sdio1_sleep",
+					     "sdio2_sleep",
+					     "sdio3_sleep",
+					     "sdio4_sleep";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/bcm2835-rpi-b-plus.dts b/arch/arm/boot/dts/bcm2835-rpi-b-plus.dts
index 57d313b6afaf..d5fdb8e761a3 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-b-plus.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-b-plus.dts
@@ -1,6 +1,7 @@
 /dts-v1/;
 #include "bcm2835.dtsi"
 #include "bcm2835-rpi.dtsi"
+#include "bcm283x-rpi-smsc9514.dtsi"
 
 / {
 	compatible = "raspberrypi,model-b-plus", "brcm,bcm2835";
diff --git a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts
index cf2774ec0834..bfc4bd9b7733 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts
@@ -1,6 +1,7 @@
 /dts-v1/;
 #include "bcm2835.dtsi"
 #include "bcm2835-rpi.dtsi"
+#include "bcm283x-rpi-smsc9512.dtsi"
 
 / {
 	compatible = "raspberrypi,model-b-rev2", "brcm,bcm2835";
diff --git a/arch/arm/boot/dts/bcm2835-rpi-b.dts b/arch/arm/boot/dts/bcm2835-rpi-b.dts
index 8b15f9c35643..0371bb7374b8 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-b.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-b.dts
@@ -1,6 +1,7 @@
 /dts-v1/;
 #include "bcm2835.dtsi"
 #include "bcm2835-rpi.dtsi"
+#include "bcm283x-rpi-smsc9512.dtsi"
 
 / {
 	compatible = "raspberrypi,model-b", "brcm,bcm2835";
diff --git a/arch/arm/boot/dts/bcm2836-rpi-2-b.dts b/arch/arm/boot/dts/bcm2836-rpi-2-b.dts
index c4743f42237b..29e1cfe8eb14 100644
--- a/arch/arm/boot/dts/bcm2836-rpi-2-b.dts
+++ b/arch/arm/boot/dts/bcm2836-rpi-2-b.dts
@@ -1,6 +1,7 @@
 /dts-v1/;
 #include "bcm2836.dtsi"
 #include "bcm2835-rpi.dtsi"
+#include "bcm283x-rpi-smsc9514.dtsi"
 
 / {
 	compatible = "raspberrypi,2-model-b", "brcm,bcm2836";
diff --git a/arch/arm/boot/dts/bcm283x-rpi-smsc9512.dtsi b/arch/arm/boot/dts/bcm283x-rpi-smsc9512.dtsi
new file mode 100644
index 000000000000..12c981e51134
--- /dev/null
+++ b/arch/arm/boot/dts/bcm283x-rpi-smsc9512.dtsi
@@ -0,0 +1,19 @@
+/ {
+	aliases {
+		ethernet = &ethernet;
+	};
+};
+
+&usb {
+	usb1@1 {
+		compatible = "usb424,9512";
+		reg = <1>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethernet: usbether@1 {
+			compatible = "usb424,ec00";
+			reg = <1>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/bcm283x-rpi-smsc9514.dtsi b/arch/arm/boot/dts/bcm283x-rpi-smsc9514.dtsi
new file mode 100644
index 000000000000..3f0a56ebcf1f
--- /dev/null
+++ b/arch/arm/boot/dts/bcm283x-rpi-smsc9514.dtsi
@@ -0,0 +1,19 @@
+/ {
+	aliases {
+		ethernet = &ethernet;
+	};
+};
+
+&usb {
+	usb1@1 {
+		compatible = "usb424,9514";
+		reg = <1>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethernet: usbether@1 {
+			compatible = "usb424,ec00";
+			reg = <1>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 10b27b912bac..b98252232d20 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -287,6 +287,8 @@
 			compatible = "brcm,bcm2835-usb";
 			reg = <0x7e980000 0x10000>;
 			interrupts = <1 9>;
+			#address-cells = <1>;
+			#size-cells = <0>;
 		};
 
 		v3d: v3d@7ec00000 {
diff --git a/arch/arm/boot/dts/bcm4708-buffalo-wzr-1750dhp.dts b/arch/arm/boot/dts/bcm4708-buffalo-wzr-1750dhp.dts
index 5087aa81efb1..9cb186ea2e97 100644
--- a/arch/arm/boot/dts/bcm4708-buffalo-wzr-1750dhp.dts
+++ b/arch/arm/boot/dts/bcm4708-buffalo-wzr-1750dhp.dts
@@ -147,3 +147,7 @@
 &usb3 {
 	vcc-gpio = <&chipcommon 10 GPIO_ACTIVE_LOW>;
 };
+
+&spi_nor {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm4708-netgear-r6250.dts b/arch/arm/boot/dts/bcm4708-netgear-r6250.dts
index 1049ab108b32..8ce39d58eeb8 100644
--- a/arch/arm/boot/dts/bcm4708-netgear-r6250.dts
+++ b/arch/arm/boot/dts/bcm4708-netgear-r6250.dts
@@ -90,3 +90,7 @@
 &usb3 {
 	vcc-gpio = <&chipcommon 0 GPIO_ACTIVE_HIGH>;
 };
+
+&spi_nor {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm4708-netgear-r6300-v2.dts b/arch/arm/boot/dts/bcm4708-netgear-r6300-v2.dts
index 3a94606d042b..6229ef283c41 100644
--- a/arch/arm/boot/dts/bcm4708-netgear-r6300-v2.dts
+++ b/arch/arm/boot/dts/bcm4708-netgear-r6300-v2.dts
@@ -82,3 +82,7 @@
 		};
 	};
 };
+
+&spi_nor {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm4708-smartrg-sr400ac.dts b/arch/arm/boot/dts/bcm4708-smartrg-sr400ac.dts
index 8b0c440b2e71..70f4bb9d864a 100644
--- a/arch/arm/boot/dts/bcm4708-smartrg-sr400ac.dts
+++ b/arch/arm/boot/dts/bcm4708-smartrg-sr400ac.dts
@@ -126,3 +126,43 @@
 &spi_nor {
 	status = "okay";
 };
+
+&srab {
+	status = "okay";
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			label = "lan4";
+		};
+
+		port@1 {
+			reg = <1>;
+			label = "lan3";
+		};
+
+		port@2 {
+			reg = <2>;
+			label = "lan2";
+		};
+
+		port@3 {
+			reg = <3>;
+			label = "lan1";
+		};
+
+		port@4 {
+			reg = <4>;
+			label = "wan";
+		};
+
+		port@5 {
+			reg = <5>;
+			label = "cpu";
+			ethernet = <&gmac0>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/bcm4709-buffalo-wxr-1900dhp.dts b/arch/arm/boot/dts/bcm4709-buffalo-wxr-1900dhp.dts
index 791d7225c733..0653e7ef248c 100644
--- a/arch/arm/boot/dts/bcm4709-buffalo-wxr-1900dhp.dts
+++ b/arch/arm/boot/dts/bcm4709-buffalo-wxr-1900dhp.dts
@@ -131,3 +131,7 @@
 &usb2 {
 	vcc-gpio = <&chipcommon 13 GPIO_ACTIVE_HIGH>;
 };
+
+&spi_nor {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm47094-dlink-dir-885l.dts b/arch/arm/boot/dts/bcm47094-dlink-dir-885l.dts
index ace38efd2db3..c8c0b3616935 100644
--- a/arch/arm/boot/dts/bcm47094-dlink-dir-885l.dts
+++ b/arch/arm/boot/dts/bcm47094-dlink-dir-885l.dts
@@ -10,7 +10,7 @@
 /dts-v1/;
 
 #include "bcm4708.dtsi"
-#include "bcm5301x-nand-cs0-bch8.dtsi"
+#include "bcm5301x-nand-cs0-bch1.dtsi"
 
 / {
 	compatible = "dlink,dir-885l", "brcm,bcm47094", "brcm,bcm4708";
@@ -113,3 +113,7 @@
 &usb3 {
 	vcc-gpio = <&chipcommon 18 GPIO_ACTIVE_HIGH>;
 };
+
+&spi_nor {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/bcm5301x-nand-cs0-bch1.dtsi b/arch/arm/boot/dts/bcm5301x-nand-cs0-bch1.dtsi
new file mode 100644
index 000000000000..24b099c00f13
--- /dev/null
+++ b/arch/arm/boot/dts/bcm5301x-nand-cs0-bch1.dtsi
@@ -0,0 +1,15 @@
+/*
+ * Broadcom Northstar NAND.
+ *
+ * Copyright (C) 2016 Rafał Miłecki <rafal.milecki@gmail.com>
+ *
+ * Licensed under the ISC license.
+ */
+
+#include "bcm5301x-nand-cs0.dtsi"
+
+&nandcs {
+	nand-ecc-algo = "bch";
+	nand-ecc-strength = <1>;
+	nand-ecc-step-size = <512>;
+};
diff --git a/arch/arm/boot/dts/bcm5301x-nand-cs0-bch8.dtsi b/arch/arm/boot/dts/bcm5301x-nand-cs0-bch8.dtsi
index d10781e36f54..9a9630ded306 100644
--- a/arch/arm/boot/dts/bcm5301x-nand-cs0-bch8.dtsi
+++ b/arch/arm/boot/dts/bcm5301x-nand-cs0-bch8.dtsi
@@ -9,16 +9,10 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
-/ {
-	nand@18028000 {
-		nandcs@0 {
-			compatible = "brcm,nandcs";
-			reg = <0>;
-			#address-cells = <1>;
-			#size-cells = <1>;
+#include "bcm5301x-nand-cs0.dtsi"
 
-			nand-ecc-strength = <8>;
-			nand-ecc-step-size = <512>;
-		};
-	};
+&nandcs {
+	nand-ecc-algo = "bch";
+	nand-ecc-strength = <8>;
+	nand-ecc-step-size = <512>;
 };
diff --git a/arch/arm/boot/dts/bcm5301x-nand-cs0.dtsi b/arch/arm/boot/dts/bcm5301x-nand-cs0.dtsi
new file mode 100644
index 000000000000..168495106b82
--- /dev/null
+++ b/arch/arm/boot/dts/bcm5301x-nand-cs0.dtsi
@@ -0,0 +1,18 @@
+/*
+ * Broadcom Northstar NAND.
+ *
+ * Copyright (C) 2015 Hauke Mehrtens <hauke@hauke-m.de>
+ *
+ * Licensed under the GNU/GPL. See COPYING for details.
+ */
+
+/ {
+	nand@18028000 {
+		nandcs: nandcs@0 {
+			compatible = "brcm,nandcs";
+			reg = <0>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 7d4d29bf0ed3..8af47913b3b4 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -153,6 +153,21 @@
 			/* ChipCommon */
 			<0x00000000 0 &gic GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
 
+			/* Switch Register Access Block */
+			<0x00007000 0 &gic GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 1 &gic GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 2 &gic GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 3 &gic GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 4 &gic GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 5 &gic GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 6 &gic GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 7 &gic GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 8 &gic GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 9 &gic GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 10 &gic GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 11 &gic GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>,
+			<0x00007000 12 &gic GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>,
+
 			/* PCIe Controller 0 */
 			<0x00012000 0 &gic GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>,
 			<0x00012000 1 &gic GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>,
@@ -239,6 +254,22 @@
 				status = "disabled";
 			};
 		};
+
+		gmac0: ethernet@24000 {
+			reg = <0x24000 0x800>;
+		};
+
+		gmac1: ethernet@25000 {
+			reg = <0x25000 0x800>;
+		};
+
+		gmac2: ethernet@26000 {
+			reg = <0x26000 0x800>;
+		};
+
+		gmac3: ethernet@27000 {
+			reg = <0x27000 0x800>;
+		};
 	};
 
 	lcpll0: lcpll0@1800c100 {
@@ -260,6 +291,22 @@
 				     "sata2";
 	};
 
+	srab: srab@18007000 {
+		compatible = "brcm,bcm5301x-srab";
+		reg = <0x18007000 0x1000>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		status = "disabled";
+
+		/* ports are defined in board DTS */
+	};
+
+	rng: rng@18004000 {
+		compatible = "brcm,bcm5301x-rng";
+		reg = <0x18004000 0x14>;
+	};
+
 	nand: nand@18028000 {
 		compatible = "brcm,nand-iproc", "brcm,brcmnand-v6.1", "brcm,brcmnand";
 		reg = <0x18028000 0x600>, <0x1811a408 0x600>, <0x18028f00 0x20>;
diff --git a/arch/arm/boot/dts/bcm953012er.dts b/arch/arm/boot/dts/bcm953012er.dts
new file mode 100644
index 000000000000..0a9abecf9423
--- /dev/null
+++ b/arch/arm/boot/dts/bcm953012er.dts
@@ -0,0 +1,104 @@
+/*
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Broadcom. All rights reserved.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Broadcom Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+#include "bcm4708.dtsi"
+#include "bcm5301x-nand-cs0-bch8.dtsi"
+
+/ {
+	model = "NorthStar Enterprise Router (BCM953012ER)";
+	compatible = "brcm,bcm953012er", "brcm,brcm53012", "brcm,bcm4708";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory {
+		reg = <0x00000000 0x8000000>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		wps {
+			label = "WPS";
+			linux,code = <KEY_WPS_BUTTON>;
+			gpios = <&chipcommon 6 GPIO_ACTIVE_LOW>;
+		};
+
+		restart {
+			label = "Reset";
+			linux,code = <KEY_RESTART>;
+			gpios = <&chipcommon 15 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&spi_nor {
+	status = "okay";
+};
+
+&srab {
+	status = "okay";
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			label = "port0";
+		};
+
+		port@1 {
+			reg = <1>;
+			label = "port1";
+		};
+
+		port@5 {
+			reg = <5>;
+			label = "cpu";
+			ethernet = <&gmac0>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/bcm958525xmc.dts b/arch/arm/boot/dts/bcm958525xmc.dts
new file mode 100644
index 000000000000..d257e83dedfc
--- /dev/null
+++ b/arch/arm/boot/dts/bcm958525xmc.dts
@@ -0,0 +1,109 @@
+/*
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Broadcom.  All rights reserved.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Broadcom Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+#include "bcm-nsp.dtsi"
+
+/ {
+	model = "NorthStar Plus XMC (BCM958525xmc)";
+	compatible = "brcm,bcm58525", "brcm,nsp";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+};
+
+&nand {
+	nandcs@0 {
+		compatible = "brcm,nandcs";
+		reg = <0>;
+		nand-on-flash-bbt;
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		nand-ecc-strength = <24>;
+		nand-ecc-step-size = <1024>;
+
+		brcm,nand-oob-sector-size = <27>;
+
+		partition@0 {
+			label = "nboot";
+			reg = <0x00000000 0x00200000>;
+			read-only;
+		};
+		partition@200000 {
+			label = "nenv";
+			reg = <0x00200000 0x00400000>;
+		};
+		partition@600000 {
+			label = "nsystem";
+			reg = <0x00600000 0x00a00000>;
+		};
+		partition@1000000 {
+			label = "nrootfs";
+			reg = <0x01000000 0x03000000>;
+		};
+		partition@4000000 {
+			label = "ncustfs";
+			reg = <0x04000000 0x3c000000>;
+		};
+	};
+};
+
+/* XHCI, SATA, MMC, and Ethernet support needed to be complete */
+
+&uart0 {
+	status = "okay";
+};
+
+&pcie0 {
+	status = "okay";
+};
+
+&pcie1 {
+	status = "okay";
+};
+
+&pinctrl {
+	pinctrl-names = "default";
+	pinctrl-0 = <&nand_sel>;
+	nand_sel: nand_sel {
+		function = "nand";
+		groups = "nand_grp";
+	};
+};
diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts
new file mode 100644
index 000000000000..03b8bbeb694f
--- /dev/null
+++ b/arch/arm/boot/dts/bcm958625hr.dts
@@ -0,0 +1,111 @@
+/*
+ *  BSD LICENSE
+ *
+ *  Copyright (c) 2016 Broadcom.  All rights reserved.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Broadcom Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+#include "bcm-nsp.dtsi"
+
+/ {
+	model = "NorthStar Plus SVK (BCM958625HR)";
+	compatible = "brcm,bcm58625", "brcm,nsp";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory {
+		reg = <0x60000000 0x20000000>;
+	};
+};
+
+&nand {
+	nandcs@0 {
+		compatible = "brcm,nandcs";
+		reg = <0>;
+		nand-on-flash-bbt;
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		nand-ecc-strength = <24>;
+		nand-ecc-step-size = <1024>;
+
+		brcm,nand-oob-sector-size = <27>;
+
+		partition@0 {
+			label = "nboot";
+			reg = <0x00000000 0x00200000>;
+			read-only;
+		};
+		partition@200000 {
+			label = "nenv";
+			reg = <0x00200000 0x00400000>;
+		};
+		partition@600000 {
+			label = "nsystem";
+			reg = <0x00600000 0x00a00000>;
+		};
+		partition@1000000 {
+			label = "nrootfs";
+			reg = <0x01000000 0x03000000>;
+		};
+		partition@4000000 {
+			label = "ncustfs";
+			reg = <0x04000000 0x3c000000>;
+		};
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&pcie0 {
+	status = "okay";
+};
+
+&pcie1 {
+	status = "okay";
+};
+
+&pinctrl {
+	pinctrl-names = "default";
+	pinctrl-0 = <&nand_sel>;
+	nand_sel: nand_sel {
+		function = "nand";
+		groups = "nand_grp";
+	};
+};
diff --git a/arch/arm/boot/dts/compulab-sb-som.dtsi b/arch/arm/boot/dts/compulab-sb-som.dtsi
index 93d7e235bc80..4af1adfee788 100644
--- a/arch/arm/boot/dts/compulab-sb-som.dtsi
+++ b/arch/arm/boot/dts/compulab-sb-som.dtsi
@@ -40,7 +40,7 @@
 		};
 	};
 
-	hdmi_conn: connector@0 {
+	hdmi_conn: connector {
 		compatible = "hdmi-connector";
 		label = "hdmi";
 
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index f23cae0c2179..68e412c9863c 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -448,7 +448,7 @@
 			reg =	<0x49000000 0x10000>;
 			reg-names = "edma3_cc";
 			interrupts = <12 13 14>;
-			interrupt-names = "edma3_ccint", "emda3_mperr",
+			interrupt-names = "edma3_ccint", "edma3_mperr",
 					  "edma3_ccerrint";
 			dma-requests = <64>;
 			#dma-cells = <2>;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index de559f6e4fee..d9bfb94a2992 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -73,6 +73,49 @@
 		interrupt-parent = <&gic>;
 	};
 
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+
+			operating-points-v2 = <&cpu0_opp_table>;
+			ti,syscon-efuse = <&scm_wkup 0x20c 0xf80000 19>;
+			ti,syscon-rev = <&scm_wkup 0x204>;
+
+			clocks = <&dpll_mpu_ck>;
+			clock-names = "cpu";
+
+			clock-latency = <300000>; /* From omap-cpufreq driver */
+
+			/* cooling options */
+			cooling-min-level = <0>;
+			cooling-max-level = <2>;
+			#cooling-cells = <2>; /* min followed by max */
+		};
+	};
+
+	cpu0_opp_table: opp_table0 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		opp_nom@1000000000 {
+			opp-hz = /bits/ 64 <1000000000>;
+			opp-microvolt = <1060000 850000 1150000>;
+			opp-supported-hw = <0xFF 0x01>;
+			opp-suspend;
+		};
+
+		opp_od@1176000000 {
+			opp-hz = /bits/ 64 <1176000000>;
+			opp-microvolt = <1160000 885000 1160000>;
+			opp-supported-hw = <0xFF 0x02>;
+		};
+	};
+
 	/*
 	 * The soc node represents the soc top level view. It is used for IPs
 	 * that are not memory mapped in the MPU view or for the MPU itself.
@@ -233,6 +276,11 @@
 				prm_clockdomains: clockdomains {
 				};
 			};
+
+			scm_wkup: scm_conf@c000 {
+				compatible = "syscon";
+				reg = <0xc000 0x1000>;
+			};
 		};
 
 		axi@0 {
@@ -276,7 +324,7 @@
 			ranges = <0x51800000 0x51800000 0x3000
 				  0x0	     0x30000000 0x10000000>;
 			status = "disabled";
-			pcie@51000000 {
+			pcie@51800000 {
 				compatible = "ti,dra7-pcie";
 				reg = <0x51800000 0x2000>, <0x51802000 0x14c>, <0x1000 0x2000>;
 				reg-names = "rc_dbics", "ti_conf", "config";
@@ -304,6 +352,53 @@
 			};
 		};
 
+		ocmcram1: ocmcram@40300000 {
+			compatible = "mmio-sram";
+			reg = <0x40300000 0x80000>;
+			ranges = <0x0 0x40300000 0x80000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			/*
+			 * This is a placeholder for an optional reserved
+			 * region for use by secure software. The size
+			 * of this region is not known until runtime so it
+			 * is set as zero to either be updated to reserve
+			 * space or left unchanged to leave all SRAM for use.
+			 * On HS parts that that require the reserved region
+			 * either the bootloader can update the size to
+			 * the required amount or the node can be overridden
+			 * from the board dts file for the secure platform.
+			 */
+			sram-hs@0 {
+				compatible = "ti,secure-ram";
+				reg = <0x0 0x0>;
+			};
+		};
+
+		/*
+		 * NOTE: ocmcram2 and ocmcram3 are not available on all
+		 * DRA7xx and AM57xx variants. Confirm availability in
+		 * the data manual for the exact part number in use
+		 * before enabling these nodes in the board dts file.
+		 */
+		ocmcram2: ocmcram@40400000 {
+			status = "disabled";
+			compatible = "mmio-sram";
+			reg = <0x40400000 0x100000>;
+			ranges = <0x0 0x40400000 0x100000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+		};
+
+		ocmcram3: ocmcram@40500000 {
+			status = "disabled";
+			compatible = "mmio-sram";
+			reg = <0x40500000 0x100000>;
+			ranges = <0x0 0x40500000 0x100000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+		};
+
 		bandgap: bandgap@4a0021e0 {
 			reg = <0x4a0021e0 0xc
 				0x4a00232c 0xc
@@ -341,7 +436,7 @@
 			interrupts = <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 360 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 359 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "edma3_ccint", "emda3_mperr",
+			interrupt-names = "edma3_ccint", "edma3_mperr",
 					  "edma3_ccerrint";
 			dma-requests = <64>;
 			#dma-cells = <2>;
@@ -1744,6 +1839,149 @@
 				clock-names = "fck", "sys_clk";
 			};
 		};
+
+		epwmss0: epwmss@4843e000 {
+			compatible = "ti,dra746-pwmss", "ti,am33xx-pwmss";
+			reg = <0x4843e000 0x30>;
+			ti,hwmods = "epwmss0";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			status = "disabled";
+			ranges;
+
+			ehrpwm0: pwm@4843e200 {
+				compatible = "ti,dra746-ehrpwm",
+					     "ti,am3352-ehrpwm";
+				#pwm-cells = <3>;
+				reg = <0x4843e200 0x80>;
+				clocks = <&ehrpwm0_tbclk>, <&l4_root_clk_div>;
+				clock-names = "tbclk", "fck";
+				status = "disabled";
+			};
+
+			ecap0: ecap@4843e100 {
+				compatible = "ti,dra746-ecap",
+					     "ti,am3352-ecap";
+				#pwm-cells = <3>;
+				reg = <0x4843e100 0x80>;
+				clocks = <&l4_root_clk_div>;
+				clock-names = "fck";
+				status = "disabled";
+			};
+		};
+
+		epwmss1: epwmss@48440000 {
+			compatible = "ti,dra746-pwmss", "ti,am33xx-pwmss";
+			reg = <0x48440000 0x30>;
+			ti,hwmods = "epwmss1";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			status = "disabled";
+			ranges;
+
+			ehrpwm1: pwm@48440200 {
+				compatible = "ti,dra746-ehrpwm",
+					     "ti,am3352-ehrpwm";
+				#pwm-cells = <3>;
+				reg = <0x48440200 0x80>;
+				clocks = <&ehrpwm1_tbclk>, <&l4_root_clk_div>;
+				clock-names = "tbclk", "fck";
+				status = "disabled";
+			};
+
+			ecap1: ecap@48440100 {
+				compatible = "ti,dra746-ecap",
+					     "ti,am3352-ecap";
+				#pwm-cells = <3>;
+				reg = <0x48440100 0x80>;
+				clocks = <&l4_root_clk_div>;
+				clock-names = "fck";
+				status = "disabled";
+			};
+		};
+
+		epwmss2: epwmss@48442000 {
+			compatible = "ti,dra746-pwmss", "ti,am33xx-pwmss";
+			reg = <0x48442000 0x30>;
+			ti,hwmods = "epwmss2";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			status = "disabled";
+			ranges;
+
+			ehrpwm2: pwm@48442200 {
+				compatible = "ti,dra746-ehrpwm",
+					     "ti,am3352-ehrpwm";
+				#pwm-cells = <3>;
+				reg = <0x48442200 0x80>;
+				clocks = <&ehrpwm2_tbclk>, <&l4_root_clk_div>;
+				clock-names = "tbclk", "fck";
+				status = "disabled";
+			};
+
+			ecap2: ecap@48442100 {
+				compatible = "ti,dra746-ecap",
+					     "ti,am3352-ecap";
+				#pwm-cells = <3>;
+				reg = <0x48442100 0x80>;
+				clocks = <&l4_root_clk_div>;
+				clock-names = "fck";
+				status = "disabled";
+			};
+		};
+
+		aes1: aes@4b500000 {
+			compatible = "ti,omap4-aes";
+			ti,hwmods = "aes1";
+			reg = <0x4b500000 0xa0>;
+			interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
+			dmas = <&edma_xbar 111 0>, <&edma_xbar 110 0>;
+			dma-names = "tx", "rx";
+			clocks = <&l3_iclk_div>;
+			clock-names = "fck";
+		};
+
+		aes2: aes@4b700000 {
+			compatible = "ti,omap4-aes";
+			ti,hwmods = "aes2";
+			reg = <0x4b700000 0xa0>;
+			interrupts = <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>;
+			dmas = <&edma_xbar 114 0>, <&edma_xbar 113 0>;
+			dma-names = "tx", "rx";
+			clocks = <&l3_iclk_div>;
+			clock-names = "fck";
+		};
+
+		des: des@480a5000 {
+			compatible = "ti,omap4-des";
+			ti,hwmods = "des";
+			reg = <0x480a5000 0xa0>;
+			interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
+			dmas = <&sdma_xbar 117>, <&sdma_xbar 116>;
+			dma-names = "tx", "rx";
+			clocks = <&l3_iclk_div>;
+			clock-names = "fck";
+		};
+
+		sham: sham@53100000 {
+			compatible = "ti,omap5-sham";
+			ti,hwmods = "sham";
+			reg = <0x4b101000 0x300>;
+			interrupts = <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>;
+			dmas = <&edma_xbar 119 0>;
+			dma-names = "rx";
+			clocks = <&l3_iclk_div>;
+			clock-names = "fck";
+		};
+
+		rng: rng@48090000 {
+			compatible = "ti,omap4-rng";
+			ti,hwmods = "rng";
+			reg = <0x48090000 0x2000>;
+			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&l3_iclk_div>;
+			clock-names = "fck";
+		};
 	};
 
 	thermal_zones: thermal-zones {
diff --git a/arch/arm/boot/dts/dra72-evm-common.dtsi b/arch/arm/boot/dts/dra72-evm-common.dtsi
index 093538ea5b5f..9d3cf50ca37e 100644
--- a/arch/arm/boot/dts/dra72-evm-common.dtsi
+++ b/arch/arm/boot/dts/dra72-evm-common.dtsi
@@ -18,7 +18,7 @@
 		display0 = &hdmi0;
 	};
 
-	evm_3v3: fixedregulator-evm_3v3 {
+	evm_3v3_sw: fixedregulator-evm_3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "evm_3v3";
 		regulator-min-microvolt = <3300000>;
@@ -29,7 +29,7 @@
 		/* TPS77018DBVT */
 		compatible = "regulator-fixed";
 		regulator-name = "aic_dvdd";
-		vin-supply = <&evm_3v3>;
+		vin-supply = <&evm_3v3_sw>;
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
@@ -414,9 +414,9 @@
 		status = "okay";
 
 		/* Regulators */
-		AVDD-supply = <&evm_3v3>;
-		IOVDD-supply = <&evm_3v3>;
-		DRVDD-supply = <&evm_3v3>;
+		AVDD-supply = <&evm_3v3_sw>;
+		IOVDD-supply = <&evm_3v3_sw>;
+		DRVDD-supply = <&evm_3v3_sw>;
 		DVDD-supply = <&aic_dvdd>;
 	};
 };
@@ -597,7 +597,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc2_pins_default>;
 
-	vmmc-supply = <&evm_3v3>;
+	vmmc-supply = <&evm_3v3_sw>;
 	bus-width = <8>;
 	ti,non-removable;
 	max-frequency = <192000000>;
diff --git a/arch/arm/boot/dts/dra72x.dtsi b/arch/arm/boot/dts/dra72x.dtsi
index 70a217050a4c..67107605fb4c 100644
--- a/arch/arm/boot/dts/dra72x.dtsi
+++ b/arch/arm/boot/dts/dra72x.dtsi
@@ -12,22 +12,6 @@
 / {
 	compatible = "ti,dra722", "ti,dra72", "ti,dra7";
 
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu0: cpu@0 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a15";
-			reg = <0>;
-
-			/* cooling options */
-			cooling-min-level = <0>;
-			cooling-max-level = <2>;
-			#cooling-cells = <2>; /* min followed by max */
-		};
-	};
-
 	pmu {
 		compatible = "arm,cortex-a15-pmu";
 		interrupt-parent = <&wakeupgen>;
diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi
index 5e06020f450b..8987b3e180a1 100644
--- a/arch/arm/boot/dts/dra74x.dtsi
+++ b/arch/arm/boot/dts/dra74x.dtsi
@@ -13,34 +13,11 @@
 	compatible = "ti,dra742", "ti,dra74", "ti,dra7";
 
 	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu0: cpu@0 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a15";
-			reg = <0>;
-
-			operating-points = <
-				/* kHz    uV */
-				1000000	1060000
-				1176000	1160000
-				>;
-
-			clocks = <&dpll_mpu_ck>;
-			clock-names = "cpu";
-
-			clock-latency = <300000>; /* From omap-cpufreq driver */
-
-			/* cooling options */
-			cooling-min-level = <0>;
-			cooling-max-level = <2>;
-			#cooling-cells = <2>; /* min followed by max */
-		};
 		cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <1>;
+			operating-points-v2 = <&cpu0_opp_table>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/emev2-kzm9d.dts b/arch/arm/boot/dts/emev2-kzm9d.dts
index a35b851e1cd7..60d0a732833a 100644
--- a/arch/arm/boot/dts/emev2-kzm9d.dts
+++ b/arch/arm/boot/dts/emev2-kzm9d.dts
@@ -18,14 +18,18 @@
 	model = "EMEV2 KZM9D Board";
 	compatible = "renesas,kzm9d", "renesas,emev2";
 
-	memory {
+	memory@40000000 {
 		device_type = "memory";
 		reg = <0x40000000 0x8000000>;
 	};
 
+	aliases {
+		serial1 = &uart1;
+	};
+
 	chosen {
-		bootargs = "console=ttyS1,115200n81 ignore_loglevel root=/dev/nfs ip=dhcp";
-		stdout-path = &uart1;
+		bootargs = "ignore_loglevel root=/dev/nfs ip=dhcp";
+		stdout-path = "serial1:115200n8";
 	};
 
 	gpio_keys {
@@ -33,28 +37,28 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		button@1 {
+		one {
 			debounce_interval = <50>;
 			wakeup-source;
 			label = "DSW2-1";
 			linux,code = <KEY_1>;
 			gpios = <&gpio0 14 GPIO_ACTIVE_HIGH>;
 		};
-		button@2 {
+		two {
 			debounce_interval = <50>;
 			wakeup-source;
 			label = "DSW2-2";
 			linux,code = <KEY_2>;
 			gpios = <&gpio0 15 GPIO_ACTIVE_HIGH>;
 		};
-		button@3 {
+		three {
 			debounce_interval = <50>;
 			wakeup-source;
 			label = "DSW2-3";
 			linux,code = <KEY_3>;
 			gpios = <&gpio0 16 GPIO_ACTIVE_HIGH>;
 		};
-		button@4 {
+		four {
 			debounce_interval = <50>;
 			wakeup-source;
 			label = "DSW2-4";
@@ -63,7 +67,7 @@
 		};
 	};
 
-	reg_1p8v: regulator@0 {
+	reg_1p8v: regulator-1p8v {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-1.8V";
 		regulator-min-microvolt = <1800000>;
@@ -72,7 +76,7 @@
 		regulator-boot-on;
 	};
 
-	reg_3p3v: regulator@1 {
+	reg_3p3v: regulator-3p3v {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-3.3V";
 		regulator-min-microvolt = <3300000>;
@@ -104,7 +108,7 @@
 };
 
 &pfc {
-	uart1_pins: serial@e1030000 {
+	uart1_pins: uart1 {
 		groups = "uart1_ctrl", "uart1_data";
 		function = "uart1";
 	};
diff --git a/arch/arm/boot/dts/emev2.dtsi b/arch/arm/boot/dts/emev2.dtsi
index bcce6f50c93d..cd119400f440 100644
--- a/arch/arm/boot/dts/emev2.dtsi
+++ b/arch/arm/boot/dts/emev2.dtsi
@@ -69,25 +69,25 @@
 			clock-frequency = <32768>;
 			#clock-cells = <0>;
 		};
-		iic0_sclkdiv: iic0_sclkdiv {
+		iic0_sclkdiv: iic0_sclkdiv@624,0 {
 			compatible = "renesas,emev2-smu-clkdiv";
 			reg = <0x624 0>;
 			clocks = <&pll3_fo>;
 			#clock-cells = <0>;
 		};
-		iic0_sclk: iic0_sclk {
+		iic0_sclk: iic0_sclk@48c,1 {
 			compatible = "renesas,emev2-smu-gclk";
 			reg = <0x48c 1>;
 			clocks = <&iic0_sclkdiv>;
 			#clock-cells = <0>;
 		};
-		iic1_sclkdiv: iic1_sclkdiv {
+		iic1_sclkdiv: iic1_sclkdiv@624,16 {
 			compatible = "renesas,emev2-smu-clkdiv";
 			reg = <0x624 16>;
 			clocks = <&pll3_fo>;
 			#clock-cells = <0>;
 		};
-		iic1_sclk: iic1_sclk {
+		iic1_sclk: iic1_sclk@490,1 {
 			compatible = "renesas,emev2-smu-gclk";
 			reg = <0x490 1>;
 			clocks = <&iic1_sclkdiv>;
@@ -100,55 +100,55 @@
 			clock-mult = <7000>;
 			#clock-cells = <0>;
 		};
-		usia_u0_sclkdiv: usia_u0_sclkdiv {
+		usia_u0_sclkdiv: usia_u0_sclkdiv@610,0 {
 			compatible = "renesas,emev2-smu-clkdiv";
 			reg = <0x610 0>;
 			clocks = <&pll3_fo>;
 			#clock-cells = <0>;
 		};
-		usib_u1_sclkdiv: usib_u1_sclkdiv {
+		usib_u1_sclkdiv: usib_u1_sclkdiv@65c,0 {
 			compatible = "renesas,emev2-smu-clkdiv";
 			reg = <0x65c 0>;
 			clocks = <&pll3_fo>;
 			#clock-cells = <0>;
 		};
-		usib_u2_sclkdiv: usib_u2_sclkdiv {
+		usib_u2_sclkdiv: usib_u2_sclkdiv@65c,16 {
 			compatible = "renesas,emev2-smu-clkdiv";
 			reg = <0x65c 16>;
 			clocks = <&pll3_fo>;
 			#clock-cells = <0>;
 		};
-		usib_u3_sclkdiv: usib_u3_sclkdiv {
+		usib_u3_sclkdiv: usib_u3_sclkdiv@660,0 {
 			compatible = "renesas,emev2-smu-clkdiv";
 			reg = <0x660 0>;
 			clocks = <&pll3_fo>;
 			#clock-cells = <0>;
 		};
-		usia_u0_sclk: usia_u0_sclk {
+		usia_u0_sclk: usia_u0_sclk@4a0,1 {
 			compatible = "renesas,emev2-smu-gclk";
 			reg = <0x4a0 1>;
 			clocks = <&usia_u0_sclkdiv>;
 			#clock-cells = <0>;
 		};
-		usib_u1_sclk: usib_u1_sclk {
+		usib_u1_sclk: usib_u1_sclk@4b8,1 {
 			compatible = "renesas,emev2-smu-gclk";
 			reg = <0x4b8 1>;
 			clocks = <&usib_u1_sclkdiv>;
 			#clock-cells = <0>;
 		};
-		usib_u2_sclk: usib_u2_sclk {
+		usib_u2_sclk: usib_u2_sclk@4bc,1 {
 			compatible = "renesas,emev2-smu-gclk";
 			reg = <0x4bc 1>;
 			clocks = <&usib_u2_sclkdiv>;
 			#clock-cells = <0>;
 		};
-		usib_u3_sclk: usib_u3_sclk {
+		usib_u3_sclk: usib_u3_sclk@4c0,1 {
 			compatible = "renesas,emev2-smu-gclk";
 			reg = <0x4c0 1>;
 			clocks = <&usib_u3_sclkdiv>;
 			#clock-cells = <0>;
 		};
-		sti_sclk: sti_sclk {
+		sti_sclk: sti_sclk@528,1 {
 			compatible = "renesas,emev2-smu-gclk";
 			reg = <0x528 1>;
 			clocks = <&c32ki>;
diff --git a/arch/arm/boot/dts/ep7209.dtsi b/arch/arm/boot/dts/ep7209.dtsi
new file mode 100644
index 000000000000..aaf1261d2ee4
--- /dev/null
+++ b/arch/arm/boot/dts/ep7209.dtsi
@@ -0,0 +1,191 @@
+/*
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ */
+
+/dts-v1/;
+
+#include "skeleton.dtsi"
+
+#include <dt-bindings/clock/clps711x-clock.h>
+
+/ {
+	model = "Cirrus Logic EP7209";
+	compatible = "cirrus,ep7209";
+
+	aliases {
+		gpio0 = &porta;
+		gpio1 = &portb;
+		gpio3 = &portd;
+		gpio4 = &porte;
+		serial0 = &uart1;
+		serial1 = &uart2;
+		spi0 = &spi;
+		timer0 = &timer1;
+		timer1 = &timer2;
+	};
+
+	cpus {
+		#address-cells = <0>;
+		#size-cells = <0>;
+
+		cpu {
+			device_type = "cpu";
+			compatible = "arm,arm720t";
+		};
+	};
+
+	soc {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		interrupt-parent = <&intc>;
+		ranges;
+
+		clks: clks@80000000 {
+			#clock-cells = <1>;
+			compatible = "cirrus,ep7209-clk";
+			reg = <0x80000000 0xc000>;
+			startup-frequency = <73728000>;
+		};
+
+		intc: intc@80000000 {
+			compatible = "cirrus,ep7209-intc";
+			reg = <0x80000000 0x4000>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		porta: gpio@80000000 {
+			compatible = "cirrus,ep7209-gpio";
+			reg = <0x80000000 0x1 0x80000040 0x1>;
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
+
+		portb: gpio@80000001 {
+			compatible = "cirrus,ep7209-gpio";
+			reg = <0x80000001 0x1 0x80000041 0x1>;
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
+
+		portd: gpio@80000003 {
+			compatible = "cirrus,ep7209-gpio";
+			reg = <0x80000003 0x1 0x80000043 0x1>;
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
+
+		porte: gpio@80000083 {
+			compatible = "cirrus,ep7209-gpio";
+			reg = <0x80000083 0x1 0x800000c3 0x1>;
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
+
+		syscon1: syscon@80000100 {
+			compatible = "cirrus,ep7209-syscon1", "syscon";
+			reg = <0x80000100 0x80>;
+		};
+
+		bus: bus@80000180 {
+			#address-cells = <2>;
+			#size-cells = <1>;
+			compatible = "cirrus,ep7209-bus", "simple-bus";
+			clocks = <&clks CLPS711X_CLK_BUS>;
+			reg = <0x80000180 0x80>;
+			ranges = <
+				0 0 0x00000000 0x10000000
+				1 0 0x10000000 0x10000000
+				2 0 0x20000000 0x10000000
+				3 0 0x30000000 0x10000000
+				4 0 0x40000000 0x10000000
+				5 0 0x50000000 0x10000000
+				6 0 0x60000000 0x0000c000
+				7 0 0x70000000 0x00000080
+			>;
+		};
+
+		fb: fb@800002c0 {
+			compatible = "cirrus,ep7209-fb";
+			reg = <0x800002c0 0xd44>, <0x60000000 0xc000>;
+			clocks = <&clks CLPS711X_CLK_BUS>;
+			status = "disabled";
+		};
+
+		timer1: timer@80000300 {
+			compatible = "cirrus,ep7209-timer";
+			reg = <0x80000300 0x4>;
+			clocks = <&clks CLPS711X_CLK_TIMER1>;
+			interrupts = <8>;
+		};
+
+		timer2: timer@80000340 {
+			compatible = "cirrus,ep7209-timer";
+			reg = <0x80000340 0x4>;
+			clocks = <&clks CLPS711X_CLK_TIMER2>;
+			interrupts = <9>;
+		};
+
+		pwm: pwm@80000400 {
+			compatible = "cirrus,ep7209-pwm";
+			reg = <0x80000400 0x4>;
+			clocks = <&clks CLPS711X_CLK_PWM>;
+			#pwm-cells = <1>;
+		};
+
+		uart1: uart@80000480 {
+			compatible = "cirrus,ep7209-uart";
+			reg = <0x80000480 0x80>;
+			interrupts = <12 13>;
+			clocks = <&clks CLPS711X_CLK_UART>;
+			syscon = <&syscon1>;
+		};
+
+		spi: spi@80000500 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "cirrus,ep7209-spi";
+			reg = <0x80000500 0x4>;
+			interrupts = <15>;
+			clocks = <&clks CLPS711X_CLK_SPI>;
+			status = "disabled";
+		};
+
+		syscon2: syscon@80001100 {
+			compatible = "cirrus,ep7209-syscon2", "syscon";
+			reg = <0x80001100 0x80>;
+		};
+
+		uart2: uart@80001480 {
+			compatible = "cirrus,ep7209-uart";
+			reg = <0x80001480 0x80>;
+			interrupts = <28 29>;
+			clocks = <&clks CLPS711X_CLK_UART>;
+			syscon = <&syscon2>;
+		};
+
+		dai: dai@80002000 {
+			#sound-dai-cells = <0>;
+			compatible = "cirrus,ep7209-dai";
+			reg = <0x80002000 0x604>;
+			clocks = <&clks CLPS711X_CLK_PLL>;
+			clock-names = "pll";
+			interrupts = <32>;
+			status = "disabled";
+		};
+
+		syscon3: syscon@80002200 {
+			compatible = "cirrus,ep7209-syscon3", "syscon";
+			reg = <0x80002200 0x40>;
+		};
+	};
+
+	mctrl: mctrl {
+		compatible = "cirrus,ep7209-mctrl-gpio";
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+};
diff --git a/arch/arm/boot/dts/ep7211-edb7211.dts b/arch/arm/boot/dts/ep7211-edb7211.dts
new file mode 100644
index 000000000000..9a134ed271eb
--- /dev/null
+++ b/arch/arm/boot/dts/ep7211-edb7211.dts
@@ -0,0 +1,100 @@
+/*
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ */
+
+#include "ep7211.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	model = "Cirrus Logic EP7211 Development Board";
+	compatible = "cirrus,edb7211", "cirrus,ep7211", "cirrus,ep7209";
+
+	memory {
+		reg = <0xc0000000 0x02000000>;
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm 0>;
+		brightness-levels = <
+			0x0 0x1 0x2 0x3 0x4 0x5 0x6 0x7
+			0x8 0x9 0xa 0xb 0xc 0xd 0xe 0xf
+		>;
+		default-brightness-level = <0x0>;
+		power-supply = <&blen>;
+	};
+
+	display: display {
+		model = "320x240x4";
+		native-mode = <&timing0>;
+		bits-per-pixel = <4>;
+		ac-prescale = <17>;
+
+		display-timings {
+			timing0: 320x240 {
+				hactive = <320>;
+				hback-porch = <0>;
+				hfront-porch = <0>;
+				hsync-len = <0>;
+				vactive = <240>;
+				vback-porch = <0>;
+				vfront-porch = <0>;
+				vsync-len = <0>;
+				clock-frequency = <6500000>;
+			};
+		};
+	};
+
+	i2c: i2c {
+		compatible = "i2c-gpio";
+		gpios = <&portd 4 GPIO_ACTIVE_HIGH>,
+			<&portd 5 GPIO_ACTIVE_HIGH>;
+		i2c-gpio,delay-us = <2>;
+		i2c-gpio,scl-output-only;
+		#address-cells = <1>;
+		#size-cells = <0>;
+	};
+
+	lcddc: lcddc {
+		compatible = "regulator-fixed";
+		regulator-name = "BACKLIGHT ENABLE";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&portd 1 GPIO_ACTIVE_HIGH>;
+	};
+
+	blen: blen {
+		compatible = "regulator-fixed";
+		regulator-name = "BACKLIGHT ENABLE";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&portd 3 GPIO_ACTIVE_HIGH>;
+	};
+};
+
+&bus {
+	flash: nor@00000000 {
+		compatible = "cfi-flash";
+		reg = <0 0x00000000 0x02000000>;
+		bank-width = <2>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+	};
+};
+
+&fb {
+	display = <&display>;
+	lcd-supply = <&lcddc>;
+	status = "okay";
+};
+
+&portd {
+	lcden {
+		gpio-hog;
+		gpios = <2 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "LCD ENABLE";
+	};
+};
diff --git a/arch/arm/boot/dts/ep7211.dtsi b/arch/arm/boot/dts/ep7211.dtsi
new file mode 100644
index 000000000000..e438f6db0673
--- /dev/null
+++ b/arch/arm/boot/dts/ep7211.dtsi
@@ -0,0 +1,12 @@
+/*
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ */
+
+#include "ep7209.dtsi"
+
+/ {
+	model = "Cirrus Logic EP7211";
+	compatible = "cirrus,ep7211", "cirrus,ep7209";
+};
diff --git a/arch/arm/boot/dts/ethernut5.dts b/arch/arm/boot/dts/ethernut5.dts
index 243044343ee8..4687229a3ab9 100644
--- a/arch/arm/boot/dts/ethernut5.dts
+++ b/arch/arm/boot/dts/ethernut5.dts
@@ -77,13 +77,13 @@
 			};
 		};
 
-		usb0: ohci@00500000 {
+		usb0: ohci@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 
 		pcf8563@50 {
diff --git a/arch/arm/boot/dts/evk-pro3.dts b/arch/arm/boot/dts/evk-pro3.dts
index f72969efe6d7..20a4481b6e12 100644
--- a/arch/arm/boot/dts/evk-pro3.dts
+++ b/arch/arm/boot/dts/evk-pro3.dts
@@ -46,13 +46,13 @@
 			};
 		};
 
-		usb0: ohci@00500000 {
+		usb0: ohci@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 	};
 
diff --git a/arch/arm/boot/dts/exynos-mfc-reserved-memory.dtsi b/arch/arm/boot/dts/exynos-mfc-reserved-memory.dtsi
new file mode 100644
index 000000000000..f78c14c82e17
--- /dev/null
+++ b/arch/arm/boot/dts/exynos-mfc-reserved-memory.dtsi
@@ -0,0 +1,35 @@
+/*
+ * Samsung's Exynos SoC MFC (Video Codec) reserved memory common definition.
+ *
+ * Copyright (c) 2016 Samsung Electronics Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		mfc_left: region_mfc_left {
+			compatible = "shared-dma-pool";
+			no-map;
+			size = <0x1000000>;
+			alignment = <0x100000>;
+		};
+
+		mfc_right: region_mfc_right {
+			compatible = "shared-dma-pool";
+			no-map;
+			size = <0x800000>;
+			alignment = <0x100000>;
+		};
+	};
+};
+
+&mfc {
+	memory-region = <&mfc_left>, <&mfc_right>;
+};
diff --git a/arch/arm/boot/dts/exynos3250-rinato.dts b/arch/arm/boot/dts/exynos3250-rinato.dts
index e422819591dc..a92181368e5b 100644
--- a/arch/arm/boot/dts/exynos3250-rinato.dts
+++ b/arch/arm/boot/dts/exynos3250-rinato.dts
@@ -632,10 +632,6 @@
 	status = "okay";
 };
 
-&mfc {
-	status = "okay";
-};
-
 &jpeg {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index 62f3dcd9e046..70e3aceab3a9 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -431,7 +431,6 @@
 			clocks = <&cmu CLK_MFC>, <&cmu CLK_SCLK_MFC>;
 			power-domains = <&pd_mfc>;
 			iommus = <&sysmmu_mfc>;
-			status = "disabled";
 		};
 
 		sysmmu_mfc: sysmmu@13620000 {
diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi
index ca8f3e3cf2f3..32f22e12c70b 100644
--- a/arch/arm/boot/dts/exynos4.dtsi
+++ b/arch/arm/boot/dts/exynos4.dtsi
@@ -428,7 +428,6 @@
 		clock-names = "mfc", "sclk_mfc";
 		iommus = <&sysmmu_mfc_l>, <&sysmmu_mfc_r>;
 		iommu-names = "left", "right";
-		status = "disabled";
 	};
 
 	serial_0: serial@13800000 {
diff --git a/arch/arm/boot/dts/exynos4210-origen.dts b/arch/arm/boot/dts/exynos4210-origen.dts
index ad7394c1d67a..be2751eebaf8 100644
--- a/arch/arm/boot/dts/exynos4210-origen.dts
+++ b/arch/arm/boot/dts/exynos4210-origen.dts
@@ -18,6 +18,7 @@
 #include "exynos4210.dtsi"
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "Insignal Origen evaluation board based on Exynos4210";
@@ -287,12 +288,6 @@
 	};
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-	status = "okay";
-};
-
 &sdhci_0 {
 	bus-width = <4>;
 	pinctrl-0 = <&sd0_clk &sd0_cmd &sd0_bus4 &sd0_cd>;
diff --git a/arch/arm/boot/dts/exynos4210-smdkv310.dts b/arch/arm/boot/dts/exynos4210-smdkv310.dts
index 94ca7d36ab37..847fae3dd1f1 100644
--- a/arch/arm/boot/dts/exynos4210-smdkv310.dts
+++ b/arch/arm/boot/dts/exynos4210-smdkv310.dts
@@ -17,6 +17,7 @@
 /dts-v1/;
 #include "exynos4210.dtsi"
 #include <dt-bindings/gpio/gpio.h>
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "Samsung smdkv310 evaluation board based on Exynos4210";
@@ -132,12 +133,6 @@
 	};
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-	status = "okay";
-};
-
 &pinctrl_1 {
 	keypad_rows: keypad-rows {
 		samsung,pins = "gpx2-0", "gpx2-1";
diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
index ec7619a384a2..58ad48e7b8f7 100644
--- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
+++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
@@ -13,6 +13,7 @@
 #include "exynos4412.dtsi"
 #include "exynos4412-ppmu-common.dtsi"
 #include <dt-bindings/gpio/gpio.h>
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	chosen {
@@ -297,7 +298,6 @@
 				regulator-name = "VDDQ_MMC2_2.8V";
 				regulator-min-microvolt = <2800000>;
 				regulator-max-microvolt = <2800000>;
-				regulator-always-on;
 				regulator-boot-on;
 			};
 
@@ -390,10 +390,18 @@
 			};
 
 			ldo21_reg: LDO21 {
-				regulator-name = "LDO21_3.3V";
-				regulator-min-microvolt = <3300000>;
-				regulator-max-microvolt = <3300000>;
-				regulator-always-on;
+				regulator-name = "TFLASH_2.8V";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-boot-on;
+			};
+
+			ldo22_reg: LDO22 {
+				/*
+				 * Only U3 uses it, so let it define the
+				 * constraints
+				 */
+				regulator-name = "LDO22";
 				regulator-boot-on;
 			};
 
@@ -460,9 +468,11 @@
 			};
 
 			buck8_reg: BUCK8 {
+				/*
+				 * Constraints set by specific board: X,
+				 * X2 and U3.
+				 */
 				regulator-name = "BUCK8_2.8V";
-				regulator-min-microvolt = <2800000>;
-				regulator-max-microvolt = <2800000>;
 			};
 		};
 	};
@@ -506,7 +516,7 @@
 &mshc_0 {
 	pinctrl-0 = <&sd4_clk &sd4_cmd &sd4_bus4 &sd4_bus8>;
 	pinctrl-names = "default";
-	vmmc-supply = <&ldo20_reg &buck8_reg>;
+	vmmc-supply = <&ldo20_reg>;
 	mmc-pwrseq = <&emmc_pwrseq>;
 	status = "okay";
 
@@ -530,7 +540,8 @@
 	bus-width = <4>;
 	pinctrl-0 = <&sd2_clk &sd2_cmd &sd2_cd &sd2_bus4>;
 	pinctrl-names = "default";
-	vmmc-supply = <&ldo4_reg &ldo21_reg>;
+	vmmc-supply = <&ldo21_reg>;
+	vqmmc-supply = <&ldo4_reg>;
 	cd-gpios = <&gpk2 2 GPIO_ACTIVE_HIGH>;
 	cd-inverted;
 	status = "okay";
diff --git a/arch/arm/boot/dts/exynos4412-odroidu3.dts b/arch/arm/boot/dts/exynos4412-odroidu3.dts
index dd89f7b37c9f..d73aa6c58fe3 100644
--- a/arch/arm/boot/dts/exynos4412-odroidu3.dts
+++ b/arch/arm/boot/dts/exynos4412-odroidu3.dts
@@ -69,6 +69,24 @@
 	};
 };
 
+/* Supply for LAN9730/SMSC95xx */
+&buck8_reg {
+	regulator-name = "BUCK8_P3V3";
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+};
+
+/* VDDQ for MSHC (eMMC card) */
+&ldo22_reg {
+	regulator-name = "LDO22_VDDQ_MMC4_2.8V";
+	regulator-min-microvolt = <2800000>;
+	regulator-max-microvolt = <2800000>;
+};
+
+&mshc_0 {
+	vqmmc-supply = <&ldo22_reg>;
+};
+
 &pwm {
 	pinctrl-0 = <&pwm0_out>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/exynos4412-odroidx.dts b/arch/arm/boot/dts/exynos4412-odroidx.dts
index bf7b21b817e4..2af235151301 100644
--- a/arch/arm/boot/dts/exynos4412-odroidx.dts
+++ b/arch/arm/boot/dts/exynos4412-odroidx.dts
@@ -63,12 +63,23 @@
 	};
 };
 
+/* VDDQ for MSHC (eMMC card) */
+&buck8_reg {
+	regulator-name = "BUCK8_VDDQ_MMC4_2.8V";
+	regulator-min-microvolt = <2800000>;
+	regulator-max-microvolt = <2800000>;
+};
+
 &ehci {
 	port@1 {
 		status = "okay";
 	};
 };
 
+&mshc_0 {
+	vqmmc-supply = <&buck8_reg>;
+};
+
 &pinctrl_1 {
 	gpio_home_key: home_key {
 		samsung,pins = "gpx2-2";
diff --git a/arch/arm/boot/dts/exynos4412-odroidx2.dts b/arch/arm/boot/dts/exynos4412-odroidx2.dts
index 6e33678562ae..3e3584270e00 100644
--- a/arch/arm/boot/dts/exynos4412-odroidx2.dts
+++ b/arch/arm/boot/dts/exynos4412-odroidx2.dts
@@ -22,6 +22,17 @@
 	};
 };
 
+/* VDDQ for MSHC (eMMC card) */
+&buck8_reg {
+	regulator-name = "BUCK8_VDDQ_MMC4_2.8V";
+	regulator-min-microvolt = <2800000>;
+	regulator-max-microvolt = <2800000>;
+};
+
+&mshc_0 {
+	vqmmc-supply = <&buck8_reg>;
+};
+
 &sound {
 	simple-audio-card,name = "Odroid-X2";
 	simple-audio-card,widgets =
diff --git a/arch/arm/boot/dts/exynos4412-origen.dts b/arch/arm/boot/dts/exynos4412-origen.dts
index 8bca699b7f20..26a36fed9652 100644
--- a/arch/arm/boot/dts/exynos4412-origen.dts
+++ b/arch/arm/boot/dts/exynos4412-origen.dts
@@ -16,6 +16,7 @@
 #include "exynos4412.dtsi"
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "Insignal Origen evaluation board based on Exynos4412";
@@ -83,6 +84,22 @@
 	cpu0-supply = <&buck2_reg>;
 };
 
+&exynos_usbphy {
+	status = "okay";
+};
+
+&ehci {
+	samsung,vbus-gpio = <&gpx3 5 1>;
+	status = "okay";
+
+	port@1{
+		status = "okay";
+	};
+	port@2 {
+		status = "okay";
+	};
+};
+
 &fimd {
 	pinctrl-0 = <&lcd_clk &lcd_data24 &pwm1_out>;
 	pinctrl-names = "default";
@@ -465,12 +482,6 @@
 	};
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-	status = "okay";
-};
-
 &mshc_0 {
 	pinctrl-0 = <&sd4_clk &sd4_cmd &sd4_bus4 &sd4_bus8>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/exynos4412-smdk4412.dts b/arch/arm/boot/dts/exynos4412-smdk4412.dts
index a51069f3c03b..231ffbdbf9d0 100644
--- a/arch/arm/boot/dts/exynos4412-smdk4412.dts
+++ b/arch/arm/boot/dts/exynos4412-smdk4412.dts
@@ -14,6 +14,7 @@
 
 /dts-v1/;
 #include "exynos4412.dtsi"
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "Samsung SMDK evaluation board based on Exynos4412";
@@ -111,12 +112,6 @@
 	};
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-	status = "okay";
-};
-
 &pinctrl_1 {
 	keypad_rows: keypad-rows {
 		samsung,pins = "gpx2-0", "gpx2-1", "gpx2-2";
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index 9336fd4824d9..129e973a06a6 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -253,7 +253,7 @@
 	};
 
 	thermistor-ap {
-		compatible = "ntc,ncp15wb473";
+		compatible = "murata,ncp15wb473";
 		pullup-uv = <1800000>;	 /* VCC_1.8V_AP */
 		pullup-ohm = <100000>;	 /* 100K */
 		pulldown-ohm = <100000>; /* 100K */
@@ -261,7 +261,7 @@
 	};
 
 	thermistor-battery {
-		compatible = "ntc,ncp15wb473";
+		compatible = "murata,ncp15wb473";
 		pullup-uv = <1800000>;	 /* VCC_1.8V_AP */
 		pullup-ohm = <100000>;	 /* 100K */
 		pulldown-ohm = <100000>; /* 100K */
diff --git a/arch/arm/boot/dts/exynos5.dtsi b/arch/arm/boot/dts/exynos5.dtsi
index d5c0f18a4223..cab91782e20c 100644
--- a/arch/arm/boot/dts/exynos5.dtsi
+++ b/arch/arm/boot/dts/exynos5.dtsi
@@ -20,97 +20,160 @@
 	interrupt-parent = <&gic>;
 
 	aliases {
+		i2c0 = &i2c_0;
+		i2c1 = &i2c_1;
+		i2c2 = &i2c_2;
+		i2c3 = &i2c_3;
 		serial0 = &serial_0;
 		serial1 = &serial_1;
 		serial2 = &serial_2;
 		serial3 = &serial_3;
 	};
 
-	chipid@10000000 {
-		compatible = "samsung,exynos4210-chipid";
-		reg = <0x10000000 0x100>;
-	};
+	soc: soc {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
 
-	memory-controller@12250000 {
-		compatible = "samsung,exynos4210-srom";
-		reg = <0x12250000 0x14>;
-	};
+		chipid@10000000 {
+			compatible = "samsung,exynos4210-chipid";
+			reg = <0x10000000 0x100>;
+		};
 
-	combiner: interrupt-controller@10440000 {
-		compatible = "samsung,exynos4210-combiner";
-		#interrupt-cells = <2>;
-		interrupt-controller;
-		samsung,combiner-nr = <32>;
-		reg = <0x10440000 0x1000>;
-		interrupts =	<0 0 0>, <0 1 0>, <0 2 0>, <0 3 0>,
-				<0 4 0>, <0 5 0>, <0 6 0>, <0 7 0>,
-				<0 8 0>, <0 9 0>, <0 10 0>, <0 11 0>,
-				<0 12 0>, <0 13 0>, <0 14 0>, <0 15 0>,
-				<0 16 0>, <0 17 0>, <0 18 0>, <0 19 0>,
-				<0 20 0>, <0 21 0>, <0 22 0>, <0 23 0>,
-				<0 24 0>, <0 25 0>, <0 26 0>, <0 27 0>,
-				<0 28 0>, <0 29 0>, <0 30 0>, <0 31 0>;
-	};
+		sromc: memory-controller@12250000 {
+			compatible = "samsung,exynos4210-srom";
+			reg = <0x12250000 0x14>;
+		};
 
-	gic: interrupt-controller@10481000 {
-		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
-		#interrupt-cells = <3>;
-		interrupt-controller;
-		reg =	<0x10481000 0x1000>,
-			<0x10482000 0x1000>,
-			<0x10484000 0x2000>,
-			<0x10486000 0x2000>;
-		interrupts = <1 9 0xf04>;
-	};
+		combiner: interrupt-controller@10440000 {
+			compatible = "samsung,exynos4210-combiner";
+			#interrupt-cells = <2>;
+			interrupt-controller;
+			samsung,combiner-nr = <32>;
+			reg = <0x10440000 0x1000>;
+			interrupts =	<0 0 0>, <0 1 0>, <0 2 0>, <0 3 0>,
+					<0 4 0>, <0 5 0>, <0 6 0>, <0 7 0>,
+					<0 8 0>, <0 9 0>, <0 10 0>, <0 11 0>,
+					<0 12 0>, <0 13 0>, <0 14 0>, <0 15 0>,
+					<0 16 0>, <0 17 0>, <0 18 0>, <0 19 0>,
+					<0 20 0>, <0 21 0>, <0 22 0>, <0 23 0>,
+					<0 24 0>, <0 25 0>, <0 26 0>, <0 27 0>,
+					<0 28 0>, <0 29 0>, <0 30 0>, <0 31 0>;
+		};
 
-	serial_0: serial@12C00000 {
-		compatible = "samsung,exynos4210-uart";
-		reg = <0x12C00000 0x100>;
-		interrupts = <0 51 0>;
-	};
+		gic: interrupt-controller@10481000 {
+			compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+			#interrupt-cells = <3>;
+			interrupt-controller;
+			reg =	<0x10481000 0x1000>,
+				<0x10482000 0x1000>,
+				<0x10484000 0x2000>,
+				<0x10486000 0x2000>;
+			interrupts = <1 9 0xf04>;
+		};
 
-	serial_1: serial@12C10000 {
-		compatible = "samsung,exynos4210-uart";
-		reg = <0x12C10000 0x100>;
-		interrupts = <0 52 0>;
-	};
+		sysreg_system_controller: syscon@10050000 {
+			compatible = "samsung,exynos5-sysreg", "syscon";
+			reg = <0x10050000 0x5000>;
+		};
 
-	serial_2: serial@12C20000 {
-		compatible = "samsung,exynos4210-uart";
-		reg = <0x12C20000 0x100>;
-		interrupts = <0 53 0>;
-	};
+		serial_0: serial@12C00000 {
+			compatible = "samsung,exynos4210-uart";
+			reg = <0x12C00000 0x100>;
+			interrupts = <0 51 0>;
+		};
 
-	serial_3: serial@12C30000 {
-		compatible = "samsung,exynos4210-uart";
-		reg = <0x12C30000 0x100>;
-		interrupts = <0 54 0>;
-	};
+		serial_1: serial@12C10000 {
+			compatible = "samsung,exynos4210-uart";
+			reg = <0x12C10000 0x100>;
+			interrupts = <0 52 0>;
+		};
 
-	rtc: rtc@101E0000 {
-		compatible = "samsung,s3c6410-rtc";
-		reg = <0x101E0000 0x100>;
-		interrupts = <0 43 0>, <0 44 0>;
-		status = "disabled";
-	};
+		serial_2: serial@12C20000 {
+			compatible = "samsung,exynos4210-uart";
+			reg = <0x12C20000 0x100>;
+			interrupts = <0 53 0>;
+		};
 
-	fimd: fimd@14400000 {
-		compatible = "samsung,exynos5250-fimd";
-		interrupt-parent = <&combiner>;
-		reg = <0x14400000 0x40000>;
-		interrupt-names = "fifo", "vsync", "lcd_sys";
-		interrupts = <18 4>, <18 5>, <18 6>;
-		samsung,sysreg = <&sysreg_system_controller>;
-		status = "disabled";
-	};
+		serial_3: serial@12C30000 {
+			compatible = "samsung,exynos4210-uart";
+			reg = <0x12C30000 0x100>;
+			interrupts = <0 54 0>;
+		};
 
-	dp: dp-controller@145B0000 {
-		compatible = "samsung,exynos5-dp";
-		reg = <0x145B0000 0x1000>;
-		interrupts = <10 3>;
-		interrupt-parent = <&combiner>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		status = "disabled";
+		i2c_0: i2c@12C60000 {
+			compatible = "samsung,s3c2440-i2c";
+			reg = <0x12C60000 0x100>;
+			interrupts = <0 56 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			samsung,sysreg-phandle = <&sysreg_system_controller>;
+			status = "disabled";
+		};
+
+		i2c_1: i2c@12C70000 {
+			compatible = "samsung,s3c2440-i2c";
+			reg = <0x12C70000 0x100>;
+			interrupts = <0 57 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			samsung,sysreg-phandle = <&sysreg_system_controller>;
+			status = "disabled";
+		};
+
+		i2c_2: i2c@12C80000 {
+			compatible = "samsung,s3c2440-i2c";
+			reg = <0x12C80000 0x100>;
+			interrupts = <0 58 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			samsung,sysreg-phandle = <&sysreg_system_controller>;
+			status = "disabled";
+		};
+
+		i2c_3: i2c@12C90000 {
+			compatible = "samsung,s3c2440-i2c";
+			reg = <0x12C90000 0x100>;
+			interrupts = <0 59 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			samsung,sysreg-phandle = <&sysreg_system_controller>;
+			status = "disabled";
+		};
+
+		pwm: pwm@12DD0000 {
+			compatible = "samsung,exynos4210-pwm";
+			reg = <0x12DD0000 0x100>;
+			samsung,pwm-outputs = <0>, <1>, <2>, <3>;
+			#pwm-cells = <3>;
+		};
+
+		rtc: rtc@101E0000 {
+			compatible = "samsung,s3c6410-rtc";
+			reg = <0x101E0000 0x100>;
+			interrupts = <0 43 0>, <0 44 0>;
+			status = "disabled";
+		};
+
+		fimd: fimd@14400000 {
+			compatible = "samsung,exynos5250-fimd";
+			interrupt-parent = <&combiner>;
+			reg = <0x14400000 0x40000>;
+			interrupt-names = "fifo", "vsync", "lcd_sys";
+			interrupts = <18 4>, <18 5>, <18 6>;
+			samsung,sysreg = <&sysreg_system_controller>;
+			status = "disabled";
+		};
+
+		dp: dp-controller@145B0000 {
+			compatible = "samsung,exynos5-dp";
+			reg = <0x145B0000 0x1000>;
+			interrupts = <10 3>;
+			interrupt-parent = <&combiner>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/exynos5250-arndale.dts b/arch/arm/boot/dts/exynos5250-arndale.dts
index 85dad29c08dc..ea70603f660d 100644
--- a/arch/arm/boot/dts/exynos5250-arndale.dts
+++ b/arch/arm/boot/dts/exynos5250-arndale.dts
@@ -14,6 +14,7 @@
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/input/input.h>
 #include "exynos5250.dtsi"
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "Insignal Arndale evaluation board based on EXYNOS5250";
@@ -515,11 +516,6 @@
 	status = "okay";
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-};
-
 &mmc_0 {
 	status = "okay";
 	num-slots = <1>;
diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts
index b7992b13c9de..381af134c4c8 100644
--- a/arch/arm/boot/dts/exynos5250-smdk5250.dts
+++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts
@@ -13,6 +13,7 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include "exynos5250.dtsi"
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "SAMSUNG SMDK5250 board based on EXYNOS5250";
@@ -343,11 +344,6 @@
 	status = "okay";
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-};
-
 &mmc_0 {
 	status = "okay";
 	num-slots = <1>;
diff --git a/arch/arm/boot/dts/exynos5250-snow-common.dtsi b/arch/arm/boot/dts/exynos5250-snow-common.dtsi
index fa14f77df563..fadbea744e1a 100644
--- a/arch/arm/boot/dts/exynos5250-snow-common.dtsi
+++ b/arch/arm/boot/dts/exynos5250-snow-common.dtsi
@@ -61,7 +61,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		i2c-parent = <&{/i2c@12CA0000}>;
+		i2c-parent = <&i2c_4>;
 
 		our-claim-gpio = <&gpf0 3 GPIO_ACTIVE_LOW>;
 		their-claim-gpios = <&gpe0 4 GPIO_ACTIVE_LOW>;
diff --git a/arch/arm/boot/dts/exynos5250-spring.dts b/arch/arm/boot/dts/exynos5250-spring.dts
index ac291f540812..44f4292bfef6 100644
--- a/arch/arm/boot/dts/exynos5250-spring.dts
+++ b/arch/arm/boot/dts/exynos5250-spring.dts
@@ -14,6 +14,7 @@
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/input/input.h>
 #include "exynos5250.dtsi"
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "Google Spring";
@@ -424,11 +425,6 @@
 	status = "okay";
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-};
-
 &mmc_0 {
 	status = "okay";
 	num-slots = <1>;
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index c7158b2fb213..f7357d99b47c 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -37,10 +37,6 @@
 		mshc1 = &mmc_1;
 		mshc2 = &mmc_2;
 		mshc3 = &mmc_3;
-		i2c0 = &i2c_0;
-		i2c1 = &i2c_1;
-		i2c2 = &i2c_2;
-		i2c3 = &i2c_3;
 		i2c4 = &i2c_4;
 		i2c5 = &i2c_5;
 		i2c6 = &i2c_6;
@@ -96,962 +92,896 @@
 		};
 	};
 
-	sysram@02020000 {
-		compatible = "mmio-sram";
-		reg = <0x02020000 0x30000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0 0x02020000 0x30000>;
+	soc: soc {
+		sysram@02020000 {
+			compatible = "mmio-sram";
+			reg = <0x02020000 0x30000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x02020000 0x30000>;
 
-		smp-sysram@0 {
-			compatible = "samsung,exynos4210-sysram";
-			reg = <0x0 0x1000>;
-		};
+			smp-sysram@0 {
+				compatible = "samsung,exynos4210-sysram";
+				reg = <0x0 0x1000>;
+			};
 
-		smp-sysram@2f000 {
-			compatible = "samsung,exynos4210-sysram-ns";
-			reg = <0x2f000 0x1000>;
+			smp-sysram@2f000 {
+				compatible = "samsung,exynos4210-sysram-ns";
+				reg = <0x2f000 0x1000>;
+			};
 		};
-	};
 
-	pd_gsc: gsc-power-domain@10044000 {
-		compatible = "samsung,exynos4210-pd";
-		reg = <0x10044000 0x20>;
-		#power-domain-cells = <0>;
-	};
+		pd_gsc: gsc-power-domain@10044000 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x10044000 0x20>;
+			#power-domain-cells = <0>;
+		};
 
-	pd_mfc: mfc-power-domain@10044040 {
-		compatible = "samsung,exynos4210-pd";
-		reg = <0x10044040 0x20>;
-		#power-domain-cells = <0>;
-	};
+		pd_mfc: mfc-power-domain@10044040 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x10044040 0x20>;
+			#power-domain-cells = <0>;
+		};
 
-	pd_disp1: disp1-power-domain@100440A0 {
-		compatible = "samsung,exynos4210-pd";
-		reg = <0x100440A0 0x20>;
-		#power-domain-cells = <0>;
-		clocks = <&clock CLK_FIN_PLL>,
-			 <&clock CLK_MOUT_ACLK200_DISP1_SUB>,
-			 <&clock CLK_MOUT_ACLK300_DISP1_SUB>;
-		clock-names = "oscclk", "clk0", "clk1";
-	};
+		pd_disp1: disp1-power-domain@100440A0 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x100440A0 0x20>;
+			#power-domain-cells = <0>;
+			clocks = <&clock CLK_FIN_PLL>,
+				 <&clock CLK_MOUT_ACLK200_DISP1_SUB>,
+				 <&clock CLK_MOUT_ACLK300_DISP1_SUB>;
+			clock-names = "oscclk", "clk0", "clk1";
+		};
 
-	clock: clock-controller@10010000 {
-		compatible = "samsung,exynos5250-clock";
-		reg = <0x10010000 0x30000>;
-		#clock-cells = <1>;
-	};
+		clock: clock-controller@10010000 {
+			compatible = "samsung,exynos5250-clock";
+			reg = <0x10010000 0x30000>;
+			#clock-cells = <1>;
+		};
 
-	clock_audss: audss-clock-controller@3810000 {
-		compatible = "samsung,exynos5250-audss-clock";
-		reg = <0x03810000 0x0C>;
-		#clock-cells = <1>;
-		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_FOUT_EPLL>,
-			 <&clock CLK_SCLK_AUDIO0>, <&clock CLK_DIV_PCM0>;
-		clock-names = "pll_ref", "pll_in", "sclk_audio", "sclk_pcm_in";
-	};
+		clock_audss: audss-clock-controller@3810000 {
+			compatible = "samsung,exynos5250-audss-clock";
+			reg = <0x03810000 0x0C>;
+			#clock-cells = <1>;
+			clocks = <&clock CLK_FIN_PLL>, <&clock CLK_FOUT_EPLL>,
+				 <&clock CLK_SCLK_AUDIO0>, <&clock CLK_DIV_PCM0>;
+			clock-names = "pll_ref", "pll_in", "sclk_audio", "sclk_pcm_in";
+		};
 
-	timer {
-		compatible = "arm,armv7-timer";
-		interrupts = <1 13 0xf08>,
-			     <1 14 0xf08>,
-			     <1 11 0xf08>,
-			     <1 10 0xf08>;
-		/* Unfortunately we need this since some versions of U-Boot
-		 * on Exynos don't set the CNTFRQ register, so we need the
-		 * value from DT.
-		 */
-		clock-frequency = <24000000>;
-	};
+		timer {
+			compatible = "arm,armv7-timer";
+			interrupts = <1 13 0xf08>,
+				     <1 14 0xf08>,
+				     <1 11 0xf08>,
+				     <1 10 0xf08>;
+			/*
+			 * Unfortunately we need this since some versions
+			 * of U-Boot on Exynos don't set the CNTFRQ register,
+			 * so we need the value from DT.
+			 */
+			clock-frequency = <24000000>;
+		};
 
-	mct@101C0000 {
-		compatible = "samsung,exynos4210-mct";
-		reg = <0x101C0000 0x800>;
-		interrupt-controller;
-		#interrupt-cells = <2>;
-		interrupt-parent = <&mct_map>;
-		interrupts = <0 0>, <1 0>, <2 0>, <3 0>,
-			     <4 0>, <5 0>;
-		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MCT>;
-		clock-names = "fin_pll", "mct";
-
-		mct_map: mct-map {
+		mct@101C0000 {
+			compatible = "samsung,exynos4210-mct";
+			reg = <0x101C0000 0x800>;
+			interrupt-controller;
 			#interrupt-cells = <2>;
-			#address-cells = <0>;
-			#size-cells = <0>;
-			interrupt-map = <0x0 0 &combiner 23 3>,
-					<0x1 0 &combiner 23 4>,
-					<0x2 0 &combiner 25 2>,
-					<0x3 0 &combiner 25 3>,
-					<0x4 0 &gic 0 120 0>,
-					<0x5 0 &gic 0 121 0>;
+			interrupt-parent = <&mct_map>;
+			interrupts = <0 0>, <1 0>, <2 0>, <3 0>,
+				     <4 0>, <5 0>;
+			clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MCT>;
+			clock-names = "fin_pll", "mct";
+
+			mct_map: mct-map {
+				#interrupt-cells = <2>;
+				#address-cells = <0>;
+				#size-cells = <0>;
+				interrupt-map = <0x0 0 &combiner 23 3>,
+						<0x1 0 &combiner 23 4>,
+						<0x2 0 &combiner 25 2>,
+						<0x3 0 &combiner 25 3>,
+						<0x4 0 &gic 0 120 0>,
+						<0x5 0 &gic 0 121 0>;
+			};
 		};
-	};
-
-	pmu {
-		compatible = "arm,cortex-a15-pmu";
-		interrupt-parent = <&combiner>;
-		interrupts = <1 2>, <22 4>;
-	};
-
-	pinctrl_0: pinctrl@11400000 {
-		compatible = "samsung,exynos5250-pinctrl";
-		reg = <0x11400000 0x1000>;
-		interrupts = <0 46 0>;
 
-		wakup_eint: wakeup-interrupt-controller {
-			compatible = "samsung,exynos4210-wakeup-eint";
-			interrupt-parent = <&gic>;
-			interrupts = <0 32 0>;
+		pmu {
+			compatible = "arm,cortex-a15-pmu";
+			interrupt-parent = <&combiner>;
+			interrupts = <1 2>, <22 4>;
 		};
-	};
-
-	pinctrl_1: pinctrl@13400000 {
-		compatible = "samsung,exynos5250-pinctrl";
-		reg = <0x13400000 0x1000>;
-		interrupts = <0 45 0>;
-	};
 
-	pinctrl_2: pinctrl@10d10000 {
-		compatible = "samsung,exynos5250-pinctrl";
-		reg = <0x10d10000 0x1000>;
-		interrupts = <0 50 0>;
-	};
-
-	pinctrl_3: pinctrl@03860000 {
-		compatible = "samsung,exynos5250-pinctrl";
-		reg = <0x03860000 0x1000>;
-		interrupts = <0 47 0>;
-	};
-
-	pmu_system_controller: system-controller@10040000 {
-		compatible = "samsung,exynos5250-pmu", "syscon";
-		reg = <0x10040000 0x5000>;
-		clock-names = "clkout16";
-		clocks = <&clock CLK_FIN_PLL>;
-		#clock-cells = <1>;
-		interrupt-controller;
-		#interrupt-cells = <3>;
-		interrupt-parent = <&gic>;
-	};
+		pinctrl_0: pinctrl@11400000 {
+			compatible = "samsung,exynos5250-pinctrl";
+			reg = <0x11400000 0x1000>;
+			interrupts = <0 46 0>;
 
-	sysreg_system_controller: syscon@10050000 {
-		compatible = "samsung,exynos5-sysreg", "syscon";
-		reg = <0x10050000 0x5000>;
-	};
+			wakup_eint: wakeup-interrupt-controller {
+				compatible = "samsung,exynos4210-wakeup-eint";
+				interrupt-parent = <&gic>;
+				interrupts = <0 32 0>;
+			};
+		};
 
-	watchdog@101D0000 {
-		compatible = "samsung,exynos5250-wdt";
-		reg = <0x101D0000 0x100>;
-		interrupts = <0 42 0>;
-		clocks = <&clock CLK_WDT>;
-		clock-names = "watchdog";
-		samsung,syscon-phandle = <&pmu_system_controller>;
-	};
+		pinctrl_1: pinctrl@13400000 {
+			compatible = "samsung,exynos5250-pinctrl";
+			reg = <0x13400000 0x1000>;
+			interrupts = <0 45 0>;
+		};
 
-	g2d@10850000 {
-		compatible = "samsung,exynos5250-g2d";
-		reg = <0x10850000 0x1000>;
-		interrupts = <0 91 0>;
-		clocks = <&clock CLK_G2D>;
-		clock-names = "fimg2d";
-		iommus = <&sysmmu_g2d>;
-	};
+		pinctrl_2: pinctrl@10d10000 {
+			compatible = "samsung,exynos5250-pinctrl";
+			reg = <0x10d10000 0x1000>;
+			interrupts = <0 50 0>;
+		};
 
-	mfc: codec@11000000 {
-		compatible = "samsung,mfc-v6";
-		reg = <0x11000000 0x10000>;
-		interrupts = <0 96 0>;
-		power-domains = <&pd_mfc>;
-		clocks = <&clock CLK_MFC>;
-		clock-names = "mfc";
-		iommus = <&sysmmu_mfc_l>, <&sysmmu_mfc_r>;
-		iommu-names = "left", "right";
-	};
+		pinctrl_3: pinctrl@03860000 {
+			compatible = "samsung,exynos5250-pinctrl";
+			reg = <0x03860000 0x1000>;
+			interrupts = <0 47 0>;
+		};
 
-	rotator: rotator@11C00000 {
-		compatible = "samsung,exynos5250-rotator";
-		reg = <0x11C00000 0x64>;
-		interrupts = <0 84 0>;
-		clocks = <&clock CLK_ROTATOR>;
-		clock-names = "rotator";
-		iommus = <&sysmmu_rotator>;
-	};
+		pmu_system_controller: system-controller@10040000 {
+			compatible = "samsung,exynos5250-pmu", "syscon";
+			reg = <0x10040000 0x5000>;
+			clock-names = "clkout16";
+			clocks = <&clock CLK_FIN_PLL>;
+			#clock-cells = <1>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+			interrupt-parent = <&gic>;
+		};
 
-	tmu: tmu@10060000 {
-		compatible = "samsung,exynos5250-tmu";
-		reg = <0x10060000 0x100>;
-		interrupts = <0 65 0>;
-		clocks = <&clock CLK_TMU>;
-		clock-names = "tmu_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
-	};
+		watchdog@101D0000 {
+			compatible = "samsung,exynos5250-wdt";
+			reg = <0x101D0000 0x100>;
+			interrupts = <0 42 0>;
+			clocks = <&clock CLK_WDT>;
+			clock-names = "watchdog";
+			samsung,syscon-phandle = <&pmu_system_controller>;
+		};
 
-	thermal-zones {
-		cpu_thermal: cpu-thermal {
-			polling-delay-passive = <0>;
-			polling-delay = <0>;
-			thermal-sensors = <&tmu 0>;
+		g2d@10850000 {
+			compatible = "samsung,exynos5250-g2d";
+			reg = <0x10850000 0x1000>;
+			interrupts = <0 91 0>;
+			clocks = <&clock CLK_G2D>;
+			clock-names = "fimg2d";
+			iommus = <&sysmmu_g2d>;
+		};
 
-			cooling-maps {
-				map0 {
-				     /* Corresponds to 800MHz at freq_table */
-				     cooling-device = <&cpu0 9 9>;
-				};
-				map1 {
-				     /* Corresponds to 200MHz at freq_table */
-				     cooling-device = <&cpu0 15 15>;
-			       };
-		       };
+		mfc: codec@11000000 {
+			compatible = "samsung,mfc-v6";
+			reg = <0x11000000 0x10000>;
+			interrupts = <0 96 0>;
+			power-domains = <&pd_mfc>;
+			clocks = <&clock CLK_MFC>;
+			clock-names = "mfc";
+			iommus = <&sysmmu_mfc_l>, <&sysmmu_mfc_r>;
+			iommu-names = "left", "right";
 		};
-	};
 
-	sata: sata@122F0000 {
-		compatible = "snps,dwc-ahci";
-		samsung,sata-freq = <66>;
-		reg = <0x122F0000 0x1ff>;
-		interrupts = <0 115 0>;
-		clocks = <&clock CLK_SATA>, <&clock CLK_SCLK_SATA>;
-		clock-names = "sata", "sclk_sata";
-		phys = <&sata_phy>;
-		phy-names = "sata-phy";
-		status = "disabled";
-	};
+		rotator: rotator@11C00000 {
+			compatible = "samsung,exynos5250-rotator";
+			reg = <0x11C00000 0x64>;
+			interrupts = <0 84 0>;
+			clocks = <&clock CLK_ROTATOR>;
+			clock-names = "rotator";
+			iommus = <&sysmmu_rotator>;
+		};
 
-	sata_phy: sata-phy@12170000 {
-		compatible = "samsung,exynos5250-sata-phy";
-		reg = <0x12170000 0x1ff>;
-		clocks = <&clock CLK_SATA_PHYCTRL>;
-		clock-names = "sata_phyctrl";
-		#phy-cells = <0>;
-		samsung,syscon-phandle = <&pmu_system_controller>;
-		status = "disabled";
-	};
+		tmu: tmu@10060000 {
+			compatible = "samsung,exynos5250-tmu";
+			reg = <0x10060000 0x100>;
+			interrupts = <0 65 0>;
+			clocks = <&clock CLK_TMU>;
+			clock-names = "tmu_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
+		};
 
-	i2c_0: i2c@12C60000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12C60000 0x100>;
-		interrupts = <0 56 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C0>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c0_bus>;
-		samsung,sysreg-phandle = <&sysreg_system_controller>;
-		status = "disabled";
-	};
+		sata: sata@122F0000 {
+			compatible = "snps,dwc-ahci";
+			samsung,sata-freq = <66>;
+			reg = <0x122F0000 0x1ff>;
+			interrupts = <0 115 0>;
+			clocks = <&clock CLK_SATA>, <&clock CLK_SCLK_SATA>;
+			clock-names = "sata", "sclk_sata";
+			phys = <&sata_phy>;
+			phy-names = "sata-phy";
+			status = "disabled";
+		};
 
-	i2c_1: i2c@12C70000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12C70000 0x100>;
-		interrupts = <0 57 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C1>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c1_bus>;
-		samsung,sysreg-phandle = <&sysreg_system_controller>;
-		status = "disabled";
-	};
+		sata_phy: sata-phy@12170000 {
+			compatible = "samsung,exynos5250-sata-phy";
+			reg = <0x12170000 0x1ff>;
+			clocks = <&clock CLK_SATA_PHYCTRL>;
+			clock-names = "sata_phyctrl";
+			#phy-cells = <0>;
+			samsung,syscon-phandle = <&pmu_system_controller>;
+			status = "disabled";
+		};
 
-	i2c_2: i2c@12C80000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12C80000 0x100>;
-		interrupts = <0 58 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C2>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c2_bus>;
-		samsung,sysreg-phandle = <&sysreg_system_controller>;
-		status = "disabled";
-	};
+		/* i2c_0-3 are defined in exynos5.dtsi */
+		i2c_4: i2c@12CA0000 {
+			compatible = "samsung,s3c2440-i2c";
+			reg = <0x12CA0000 0x100>;
+			interrupts = <0 60 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&clock CLK_I2C4>;
+			clock-names = "i2c";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c4_bus>;
+			status = "disabled";
+		};
 
-	i2c_3: i2c@12C90000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12C90000 0x100>;
-		interrupts = <0 59 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C3>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c3_bus>;
-		samsung,sysreg-phandle = <&sysreg_system_controller>;
-		status = "disabled";
-	};
+		i2c_5: i2c@12CB0000 {
+			compatible = "samsung,s3c2440-i2c";
+			reg = <0x12CB0000 0x100>;
+			interrupts = <0 61 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&clock CLK_I2C5>;
+			clock-names = "i2c";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c5_bus>;
+			status = "disabled";
+		};
 
-	i2c_4: i2c@12CA0000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12CA0000 0x100>;
-		interrupts = <0 60 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C4>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c4_bus>;
-		status = "disabled";
-	};
+		i2c_6: i2c@12CC0000 {
+			compatible = "samsung,s3c2440-i2c";
+			reg = <0x12CC0000 0x100>;
+			interrupts = <0 62 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&clock CLK_I2C6>;
+			clock-names = "i2c";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c6_bus>;
+			status = "disabled";
+		};
 
-	i2c_5: i2c@12CB0000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12CB0000 0x100>;
-		interrupts = <0 61 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C5>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c5_bus>;
-		status = "disabled";
-	};
+		i2c_7: i2c@12CD0000 {
+			compatible = "samsung,s3c2440-i2c";
+			reg = <0x12CD0000 0x100>;
+			interrupts = <0 63 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&clock CLK_I2C7>;
+			clock-names = "i2c";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c7_bus>;
+			status = "disabled";
+		};
 
-	i2c_6: i2c@12CC0000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12CC0000 0x100>;
-		interrupts = <0 62 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C6>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c6_bus>;
-		status = "disabled";
-	};
+		i2c_8: i2c@12CE0000 {
+			compatible = "samsung,s3c2440-hdmiphy-i2c";
+			reg = <0x12CE0000 0x1000>;
+			interrupts = <0 64 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&clock CLK_I2C_HDMI>;
+			clock-names = "i2c";
+			status = "disabled";
+		};
 
-	i2c_7: i2c@12CD0000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12CD0000 0x100>;
-		interrupts = <0 63 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C7>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c7_bus>;
-		status = "disabled";
-	};
+		i2c_9: i2c@121D0000 {
+			compatible = "samsung,exynos5-sata-phy-i2c";
+			reg = <0x121D0000 0x100>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&clock CLK_SATA_PHYI2C>;
+			clock-names = "i2c";
+			status = "disabled";
+		};
 
-	i2c_8: i2c@12CE0000 {
-		compatible = "samsung,s3c2440-hdmiphy-i2c";
-		reg = <0x12CE0000 0x1000>;
-		interrupts = <0 64 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C_HDMI>;
-		clock-names = "i2c";
-		status = "disabled";
-	};
+		spi_0: spi@12d20000 {
+			compatible = "samsung,exynos4210-spi";
+			status = "disabled";
+			reg = <0x12d20000 0x100>;
+			interrupts = <0 66 0>;
+			dmas = <&pdma0 5
+				&pdma0 4>;
+			dma-names = "tx", "rx";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&clock CLK_SPI0>, <&clock CLK_SCLK_SPI0>;
+			clock-names = "spi", "spi_busclk0";
+			pinctrl-names = "default";
+			pinctrl-0 = <&spi0_bus>;
+		};
 
-	i2c_9: i2c@121D0000 {
-                compatible = "samsung,exynos5-sata-phy-i2c";
-                reg = <0x121D0000 0x100>;
-                #address-cells = <1>;
-                #size-cells = <0>;
-		clocks = <&clock CLK_SATA_PHYI2C>;
-		clock-names = "i2c";
-		status = "disabled";
-	};
+		spi_1: spi@12d30000 {
+			compatible = "samsung,exynos4210-spi";
+			status = "disabled";
+			reg = <0x12d30000 0x100>;
+			interrupts = <0 67 0>;
+			dmas = <&pdma1 5
+				&pdma1 4>;
+			dma-names = "tx", "rx";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&clock CLK_SPI1>, <&clock CLK_SCLK_SPI1>;
+			clock-names = "spi", "spi_busclk0";
+			pinctrl-names = "default";
+			pinctrl-0 = <&spi1_bus>;
+		};
 
-	spi_0: spi@12d20000 {
-		compatible = "samsung,exynos4210-spi";
-		status = "disabled";
-		reg = <0x12d20000 0x100>;
-		interrupts = <0 66 0>;
-		dmas = <&pdma0 5
-			&pdma0 4>;
-		dma-names = "tx", "rx";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_SPI0>, <&clock CLK_SCLK_SPI0>;
-		clock-names = "spi", "spi_busclk0";
-		pinctrl-names = "default";
-		pinctrl-0 = <&spi0_bus>;
-	};
+		spi_2: spi@12d40000 {
+			compatible = "samsung,exynos4210-spi";
+			status = "disabled";
+			reg = <0x12d40000 0x100>;
+			interrupts = <0 68 0>;
+			dmas = <&pdma0 7
+				&pdma0 6>;
+			dma-names = "tx", "rx";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&clock CLK_SPI2>, <&clock CLK_SCLK_SPI2>;
+			clock-names = "spi", "spi_busclk0";
+			pinctrl-names = "default";
+			pinctrl-0 = <&spi2_bus>;
+		};
 
-	spi_1: spi@12d30000 {
-		compatible = "samsung,exynos4210-spi";
-		status = "disabled";
-		reg = <0x12d30000 0x100>;
-		interrupts = <0 67 0>;
-		dmas = <&pdma1 5
-			&pdma1 4>;
-		dma-names = "tx", "rx";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_SPI1>, <&clock CLK_SCLK_SPI1>;
-		clock-names = "spi", "spi_busclk0";
-		pinctrl-names = "default";
-		pinctrl-0 = <&spi1_bus>;
-	};
+		mmc_0: mmc@12200000 {
+			compatible = "samsung,exynos5250-dw-mshc";
+			interrupts = <0 75 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x12200000 0x1000>;
+			clocks = <&clock CLK_SDMMC0>, <&clock CLK_SCLK_MMC0>;
+			clock-names = "biu", "ciu";
+			fifo-depth = <0x80>;
+			status = "disabled";
+		};
 
-	spi_2: spi@12d40000 {
-		compatible = "samsung,exynos4210-spi";
-		status = "disabled";
-		reg = <0x12d40000 0x100>;
-		interrupts = <0 68 0>;
-		dmas = <&pdma0 7
-			&pdma0 6>;
-		dma-names = "tx", "rx";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_SPI2>, <&clock CLK_SCLK_SPI2>;
-		clock-names = "spi", "spi_busclk0";
-		pinctrl-names = "default";
-		pinctrl-0 = <&spi2_bus>;
-	};
+		mmc_1: mmc@12210000 {
+			compatible = "samsung,exynos5250-dw-mshc";
+			interrupts = <0 76 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x12210000 0x1000>;
+			clocks = <&clock CLK_SDMMC1>, <&clock CLK_SCLK_MMC1>;
+			clock-names = "biu", "ciu";
+			fifo-depth = <0x80>;
+			status = "disabled";
+		};
 
-	mmc_0: mmc@12200000 {
-		compatible = "samsung,exynos5250-dw-mshc";
-		interrupts = <0 75 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		reg = <0x12200000 0x1000>;
-		clocks = <&clock CLK_SDMMC0>, <&clock CLK_SCLK_MMC0>;
-		clock-names = "biu", "ciu";
-		fifo-depth = <0x80>;
-		status = "disabled";
-	};
+		mmc_2: mmc@12220000 {
+			compatible = "samsung,exynos5250-dw-mshc";
+			interrupts = <0 77 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x12220000 0x1000>;
+			clocks = <&clock CLK_SDMMC2>, <&clock CLK_SCLK_MMC2>;
+			clock-names = "biu", "ciu";
+			fifo-depth = <0x80>;
+			status = "disabled";
+		};
 
-	mmc_1: mmc@12210000 {
-		compatible = "samsung,exynos5250-dw-mshc";
-		interrupts = <0 76 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		reg = <0x12210000 0x1000>;
-		clocks = <&clock CLK_SDMMC1>, <&clock CLK_SCLK_MMC1>;
-		clock-names = "biu", "ciu";
-		fifo-depth = <0x80>;
-		status = "disabled";
-	};
+		mmc_3: mmc@12230000 {
+			compatible = "samsung,exynos5250-dw-mshc";
+			reg = <0x12230000 0x1000>;
+			interrupts = <0 78 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			clocks = <&clock CLK_SDMMC3>, <&clock CLK_SCLK_MMC3>;
+			clock-names = "biu", "ciu";
+			fifo-depth = <0x80>;
+			status = "disabled";
+		};
 
-	mmc_2: mmc@12220000 {
-		compatible = "samsung,exynos5250-dw-mshc";
-		interrupts = <0 77 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		reg = <0x12220000 0x1000>;
-		clocks = <&clock CLK_SDMMC2>, <&clock CLK_SCLK_MMC2>;
-		clock-names = "biu", "ciu";
-		fifo-depth = <0x80>;
-		status = "disabled";
-	};
+		i2s0: i2s@03830000 {
+			compatible = "samsung,s5pv210-i2s";
+			status = "disabled";
+			reg = <0x03830000 0x100>;
+			dmas = <&pdma0 10
+				&pdma0 9
+				&pdma0 8>;
+			dma-names = "tx", "rx", "tx-sec";
+			clocks = <&clock_audss EXYNOS_I2S_BUS>,
+				<&clock_audss EXYNOS_I2S_BUS>,
+				<&clock_audss EXYNOS_SCLK_I2S>;
+			clock-names = "iis", "i2s_opclk0", "i2s_opclk1";
+			samsung,idma-addr = <0x03000000>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2s0_bus>;
+		};
 
-	mmc_3: mmc@12230000 {
-		compatible = "samsung,exynos5250-dw-mshc";
-		reg = <0x12230000 0x1000>;
-		interrupts = <0 78 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_SDMMC3>, <&clock CLK_SCLK_MMC3>;
-		clock-names = "biu", "ciu";
-		fifo-depth = <0x80>;
-		status = "disabled";
-	};
+		i2s1: i2s@12D60000 {
+			compatible = "samsung,s3c6410-i2s";
+			status = "disabled";
+			reg = <0x12D60000 0x100>;
+			dmas = <&pdma1 12
+				&pdma1 11>;
+			dma-names = "tx", "rx";
+			clocks = <&clock CLK_I2S1>, <&clock CLK_DIV_I2S1>;
+			clock-names = "iis", "i2s_opclk0";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2s1_bus>;
+		};
 
-	i2s0: i2s@03830000 {
-		compatible = "samsung,s5pv210-i2s";
-		status = "disabled";
-		reg = <0x03830000 0x100>;
-		dmas = <&pdma0 10
-			&pdma0 9
-			&pdma0 8>;
-		dma-names = "tx", "rx", "tx-sec";
-		clocks = <&clock_audss EXYNOS_I2S_BUS>,
-			<&clock_audss EXYNOS_I2S_BUS>,
-			<&clock_audss EXYNOS_SCLK_I2S>;
-		clock-names = "iis", "i2s_opclk0", "i2s_opclk1";
-		samsung,idma-addr = <0x03000000>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2s0_bus>;
-	};
+		i2s2: i2s@12D70000 {
+			compatible = "samsung,s3c6410-i2s";
+			status = "disabled";
+			reg = <0x12D70000 0x100>;
+			dmas = <&pdma0 12
+				&pdma0 11>;
+			dma-names = "tx", "rx";
+			clocks = <&clock CLK_I2S2>, <&clock CLK_DIV_I2S2>;
+			clock-names = "iis", "i2s_opclk0";
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2s2_bus>;
+		};
 
-	i2s1: i2s@12D60000 {
-		compatible = "samsung,s3c6410-i2s";
-		status = "disabled";
-		reg = <0x12D60000 0x100>;
-		dmas = <&pdma1 12
-			&pdma1 11>;
-		dma-names = "tx", "rx";
-		clocks = <&clock CLK_I2S1>, <&clock CLK_DIV_I2S1>;
-		clock-names = "iis", "i2s_opclk0";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2s1_bus>;
-	};
+		usb_dwc3 {
+			compatible = "samsung,exynos5250-dwusb3";
+			clocks = <&clock CLK_USB3>;
+			clock-names = "usbdrd30";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			usbdrd_dwc3: dwc3@12000000 {
+				compatible = "synopsys,dwc3";
+				reg = <0x12000000 0x10000>;
+				interrupts = <0 72 0>;
+				phys = <&usbdrd_phy 0>, <&usbdrd_phy 1>;
+				phy-names = "usb2-phy", "usb3-phy";
+			};
+		};
 
-	i2s2: i2s@12D70000 {
-		compatible = "samsung,s3c6410-i2s";
-		status = "disabled";
-		reg = <0x12D70000 0x100>;
-		dmas = <&pdma0 12
-			&pdma0 11>;
-		dma-names = "tx", "rx";
-		clocks = <&clock CLK_I2S2>, <&clock CLK_DIV_I2S2>;
-		clock-names = "iis", "i2s_opclk0";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2s2_bus>;
-	};
+		usbdrd_phy: phy@12100000 {
+			compatible = "samsung,exynos5250-usbdrd-phy";
+			reg = <0x12100000 0x100>;
+			clocks = <&clock CLK_USB3>, <&clock CLK_FIN_PLL>;
+			clock-names = "phy", "ref";
+			samsung,pmu-syscon = <&pmu_system_controller>;
+			#phy-cells = <1>;
+		};
 
-	usb_dwc3 {
-		compatible = "samsung,exynos5250-dwusb3";
-		clocks = <&clock CLK_USB3>;
-		clock-names = "usbdrd30";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
+		ehci: usb@12110000 {
+			compatible = "samsung,exynos4210-ehci";
+			reg = <0x12110000 0x100>;
+			interrupts = <0 71 0>;
 
-		usbdrd_dwc3: dwc3@12000000 {
-			compatible = "synopsys,dwc3";
-			reg = <0x12000000 0x10000>;
-			interrupts = <0 72 0>;
-			phys = <&usbdrd_phy 0>, <&usbdrd_phy 1>;
-			phy-names = "usb2-phy", "usb3-phy";
+			clocks = <&clock CLK_USB2>;
+			clock-names = "usbhost";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			port@0 {
+				reg = <0>;
+				phys = <&usb2_phy_gen 1>;
+			};
 		};
-	};
-
-	usbdrd_phy: phy@12100000 {
-		compatible = "samsung,exynos5250-usbdrd-phy";
-		reg = <0x12100000 0x100>;
-		clocks = <&clock CLK_USB3>, <&clock CLK_FIN_PLL>;
-		clock-names = "phy", "ref";
-		samsung,pmu-syscon = <&pmu_system_controller>;
-		#phy-cells = <1>;
-	};
 
-	ehci: usb@12110000 {
-		compatible = "samsung,exynos4210-ehci";
-		reg = <0x12110000 0x100>;
-		interrupts = <0 71 0>;
+		ohci: usb@12120000 {
+			compatible = "samsung,exynos4210-ohci";
+			reg = <0x12120000 0x100>;
+			interrupts = <0 71 0>;
 
-		clocks = <&clock CLK_USB2>;
-		clock-names = "usbhost";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		port@0 {
-			reg = <0>;
-			phys = <&usb2_phy_gen 1>;
+			clocks = <&clock CLK_USB2>;
+			clock-names = "usbhost";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			port@0 {
+				reg = <0>;
+				phys = <&usb2_phy_gen 1>;
+			};
 		};
-	};
 
-	ohci: usb@12120000 {
-		compatible = "samsung,exynos4210-ohci";
-		reg = <0x12120000 0x100>;
-		interrupts = <0 71 0>;
-
-		clocks = <&clock CLK_USB2>;
-		clock-names = "usbhost";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		port@0 {
-			reg = <0>;
-			phys = <&usb2_phy_gen 1>;
+		usb2_phy_gen: phy@12130000 {
+			compatible = "samsung,exynos5250-usb2-phy";
+			reg = <0x12130000 0x100>;
+			clocks = <&clock CLK_USB2>, <&clock CLK_FIN_PLL>;
+			clock-names = "phy", "ref";
+			#phy-cells = <1>;
+			samsung,sysreg-phandle = <&sysreg_system_controller>;
+			samsung,pmureg-phandle = <&pmu_system_controller>;
 		};
-	};
 
-	usb2_phy_gen: phy@12130000 {
-		compatible = "samsung,exynos5250-usb2-phy";
-		reg = <0x12130000 0x100>;
-		clocks = <&clock CLK_USB2>, <&clock CLK_FIN_PLL>;
-		clock-names = "phy", "ref";
-		#phy-cells = <1>;
-		samsung,sysreg-phandle = <&sysreg_system_controller>;
-		samsung,pmureg-phandle = <&pmu_system_controller>;
-	};
+		amba {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "simple-bus";
+			interrupt-parent = <&gic>;
+			ranges;
+
+			pdma0: pdma@121A0000 {
+				compatible = "arm,pl330", "arm,primecell";
+				reg = <0x121A0000 0x1000>;
+				interrupts = <0 34 0>;
+				clocks = <&clock CLK_PDMA0>;
+				clock-names = "apb_pclk";
+				#dma-cells = <1>;
+				#dma-channels = <8>;
+				#dma-requests = <32>;
+			};
+
+			pdma1: pdma@121B0000 {
+				compatible = "arm,pl330", "arm,primecell";
+				reg = <0x121B0000 0x1000>;
+				interrupts = <0 35 0>;
+				clocks = <&clock CLK_PDMA1>;
+				clock-names = "apb_pclk";
+				#dma-cells = <1>;
+				#dma-channels = <8>;
+				#dma-requests = <32>;
+			};
+
+			mdma0: mdma@10800000 {
+				compatible = "arm,pl330", "arm,primecell";
+				reg = <0x10800000 0x1000>;
+				interrupts = <0 33 0>;
+				clocks = <&clock CLK_MDMA0>;
+				clock-names = "apb_pclk";
+				#dma-cells = <1>;
+				#dma-channels = <8>;
+				#dma-requests = <1>;
+			};
+
+			mdma1: mdma@11C10000 {
+				compatible = "arm,pl330", "arm,primecell";
+				reg = <0x11C10000 0x1000>;
+				interrupts = <0 124 0>;
+				clocks = <&clock CLK_MDMA1>;
+				clock-names = "apb_pclk";
+				#dma-cells = <1>;
+				#dma-channels = <8>;
+				#dma-requests = <1>;
+			};
+		};
 
-	pwm: pwm@12dd0000 {
-		compatible = "samsung,exynos4210-pwm";
-		reg = <0x12dd0000 0x100>;
-		samsung,pwm-outputs = <0>, <1>, <2>, <3>;
-		#pwm-cells = <3>;
-		clocks = <&clock CLK_PWM>;
-		clock-names = "timers";
-	};
+		gsc_0:  gsc@13e00000 {
+			compatible = "samsung,exynos5-gsc";
+			reg = <0x13e00000 0x1000>;
+			interrupts = <0 85 0>;
+			power-domains = <&pd_gsc>;
+			clocks = <&clock CLK_GSCL0>;
+			clock-names = "gscl";
+			iommu = <&sysmmu_gsc0>;
+		};
 
-	amba {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		compatible = "simple-bus";
-		interrupt-parent = <&gic>;
-		ranges;
-
-		pdma0: pdma@121A0000 {
-			compatible = "arm,pl330", "arm,primecell";
-			reg = <0x121A0000 0x1000>;
-			interrupts = <0 34 0>;
-			clocks = <&clock CLK_PDMA0>;
-			clock-names = "apb_pclk";
-			#dma-cells = <1>;
-			#dma-channels = <8>;
-			#dma-requests = <32>;
-		};
-
-		pdma1: pdma@121B0000 {
-			compatible = "arm,pl330", "arm,primecell";
-			reg = <0x121B0000 0x1000>;
-			interrupts = <0 35 0>;
-			clocks = <&clock CLK_PDMA1>;
-			clock-names = "apb_pclk";
-			#dma-cells = <1>;
-			#dma-channels = <8>;
-			#dma-requests = <32>;
-		};
-
-		mdma0: mdma@10800000 {
-			compatible = "arm,pl330", "arm,primecell";
-			reg = <0x10800000 0x1000>;
-			interrupts = <0 33 0>;
-			clocks = <&clock CLK_MDMA0>;
-			clock-names = "apb_pclk";
-			#dma-cells = <1>;
-			#dma-channels = <8>;
-			#dma-requests = <1>;
-		};
-
-		mdma1: mdma@11C10000 {
-			compatible = "arm,pl330", "arm,primecell";
-			reg = <0x11C10000 0x1000>;
-			interrupts = <0 124 0>;
-			clocks = <&clock CLK_MDMA1>;
-			clock-names = "apb_pclk";
-			#dma-cells = <1>;
-			#dma-channels = <8>;
-			#dma-requests = <1>;
+		gsc_1:  gsc@13e10000 {
+			compatible = "samsung,exynos5-gsc";
+			reg = <0x13e10000 0x1000>;
+			interrupts = <0 86 0>;
+			power-domains = <&pd_gsc>;
+			clocks = <&clock CLK_GSCL1>;
+			clock-names = "gscl";
+			iommu = <&sysmmu_gsc1>;
 		};
-	};
 
-	gsc_0:  gsc@13e00000 {
-		compatible = "samsung,exynos5-gsc";
-		reg = <0x13e00000 0x1000>;
-		interrupts = <0 85 0>;
-		power-domains = <&pd_gsc>;
-		clocks = <&clock CLK_GSCL0>;
-		clock-names = "gscl";
-		iommu = <&sysmmu_gsc0>;
-	};
+		gsc_2:  gsc@13e20000 {
+			compatible = "samsung,exynos5-gsc";
+			reg = <0x13e20000 0x1000>;
+			interrupts = <0 87 0>;
+			power-domains = <&pd_gsc>;
+			clocks = <&clock CLK_GSCL2>;
+			clock-names = "gscl";
+			iommu = <&sysmmu_gsc2>;
+		};
 
-	gsc_1:  gsc@13e10000 {
-		compatible = "samsung,exynos5-gsc";
-		reg = <0x13e10000 0x1000>;
-		interrupts = <0 86 0>;
-		power-domains = <&pd_gsc>;
-		clocks = <&clock CLK_GSCL1>;
-		clock-names = "gscl";
-		iommu = <&sysmmu_gsc1>;
-	};
+		gsc_3:  gsc@13e30000 {
+			compatible = "samsung,exynos5-gsc";
+			reg = <0x13e30000 0x1000>;
+			interrupts = <0 88 0>;
+			power-domains = <&pd_gsc>;
+			clocks = <&clock CLK_GSCL3>;
+			clock-names = "gscl";
+			iommu = <&sysmmu_gsc3>;
+		};
 
-	gsc_2:  gsc@13e20000 {
-		compatible = "samsung,exynos5-gsc";
-		reg = <0x13e20000 0x1000>;
-		interrupts = <0 87 0>;
-		power-domains = <&pd_gsc>;
-		clocks = <&clock CLK_GSCL2>;
-		clock-names = "gscl";
-		iommu = <&sysmmu_gsc2>;
-	};
+		hdmi: hdmi@14530000 {
+			compatible = "samsung,exynos4212-hdmi";
+			reg = <0x14530000 0x70000>;
+			power-domains = <&pd_disp1>;
+			interrupts = <0 95 0>;
+			clocks = <&clock CLK_HDMI>, <&clock CLK_SCLK_HDMI>,
+				 <&clock CLK_SCLK_PIXEL>, <&clock CLK_SCLK_HDMIPHY>,
+				 <&clock CLK_MOUT_HDMI>;
+			clock-names = "hdmi", "sclk_hdmi", "sclk_pixel",
+					"sclk_hdmiphy", "mout_hdmi";
+			samsung,syscon-phandle = <&pmu_system_controller>;
+		};
 
-	gsc_3:  gsc@13e30000 {
-		compatible = "samsung,exynos5-gsc";
-		reg = <0x13e30000 0x1000>;
-		interrupts = <0 88 0>;
-		power-domains = <&pd_gsc>;
-		clocks = <&clock CLK_GSCL3>;
-		clock-names = "gscl";
-		iommu = <&sysmmu_gsc3>;
-	};
+		mixer@14450000 {
+			compatible = "samsung,exynos5250-mixer";
+			reg = <0x14450000 0x10000>;
+			power-domains = <&pd_disp1>;
+			interrupts = <0 94 0>;
+			clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>,
+				 <&clock CLK_SCLK_HDMI>;
+			clock-names = "mixer", "hdmi", "sclk_hdmi";
+			iommus = <&sysmmu_tv>;
+		};
 
-	hdmi: hdmi@14530000 {
-		compatible = "samsung,exynos4212-hdmi";
-		reg = <0x14530000 0x70000>;
-		power-domains = <&pd_disp1>;
-		interrupts = <0 95 0>;
-		clocks = <&clock CLK_HDMI>, <&clock CLK_SCLK_HDMI>,
-			 <&clock CLK_SCLK_PIXEL>, <&clock CLK_SCLK_HDMIPHY>,
-			 <&clock CLK_MOUT_HDMI>;
-		clock-names = "hdmi", "sclk_hdmi", "sclk_pixel",
-				"sclk_hdmiphy", "mout_hdmi";
-		samsung,syscon-phandle = <&pmu_system_controller>;
-	};
+		dp_phy: video-phy {
+			compatible = "samsung,exynos5250-dp-video-phy";
+			samsung,pmu-syscon = <&pmu_system_controller>;
+			#phy-cells = <0>;
+		};
 
-	mixer@14450000 {
-		compatible = "samsung,exynos5250-mixer";
-		reg = <0x14450000 0x10000>;
-		power-domains = <&pd_disp1>;
-		interrupts = <0 94 0>;
-		clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>,
-			 <&clock CLK_SCLK_HDMI>;
-		clock-names = "mixer", "hdmi", "sclk_hdmi";
-		iommus = <&sysmmu_tv>;
-	};
+		adc: adc@12D10000 {
+			compatible = "samsung,exynos-adc-v1";
+			reg = <0x12D10000 0x100>;
+			interrupts = <0 106 0>;
+			clocks = <&clock CLK_ADC>;
+			clock-names = "adc";
+			#io-channel-cells = <1>;
+			io-channel-ranges;
+			samsung,syscon-phandle = <&pmu_system_controller>;
+			status = "disabled";
+		};
 
-	dp_phy: video-phy {
-		compatible = "samsung,exynos5250-dp-video-phy";
-		samsung,pmu-syscon = <&pmu_system_controller>;
-		#phy-cells = <0>;
-	};
+		sss@10830000 {
+			compatible = "samsung,exynos4210-secss";
+			reg = <0x10830000 0x300>;
+			interrupts = <0 112 0>;
+			clocks = <&clock CLK_SSS>;
+			clock-names = "secss";
+		};
 
-	adc: adc@12D10000 {
-		compatible = "samsung,exynos-adc-v1";
-		reg = <0x12D10000 0x100>;
-		interrupts = <0 106 0>;
-		clocks = <&clock CLK_ADC>;
-		clock-names = "adc";
-		#io-channel-cells = <1>;
-		io-channel-ranges;
-		samsung,syscon-phandle = <&pmu_system_controller>;
-		status = "disabled";
-	};
+		sysmmu_g2d: sysmmu@10A60000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x10A60000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <24 5>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_2D>, <&clock CLK_G2D>;
+			#iommu-cells = <0>;
+		};
 
-	sss@10830000 {
-		compatible = "samsung,exynos4210-secss";
-		reg = <0x10830000 0x300>;
-		interrupts = <0 112 0>;
-		clocks = <&clock CLK_SSS>;
-		clock-names = "secss";
-	};
+		sysmmu_mfc_r: sysmmu@11200000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x11200000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <6 2>;
+			power-domains = <&pd_mfc>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MFCR>, <&clock CLK_MFC>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_g2d: sysmmu@10A60000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x10A60000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <24 5>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_2D>, <&clock CLK_G2D>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_mfc_l: sysmmu@11210000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x11210000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <8 5>;
+			power-domains = <&pd_mfc>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MFCL>, <&clock CLK_MFC>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_mfc_r: sysmmu@11200000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x11200000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <6 2>;
-		power-domains = <&pd_mfc>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MFCR>, <&clock CLK_MFC>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_rotator: sysmmu@11D40000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x11D40000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <4 0>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_ROTATOR>, <&clock CLK_ROTATOR>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_mfc_l: sysmmu@11210000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x11210000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <8 5>;
-		power-domains = <&pd_mfc>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MFCL>, <&clock CLK_MFC>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_jpeg: sysmmu@11F20000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x11F20000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <4 2>;
+			power-domains = <&pd_gsc>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_JPEG>, <&clock CLK_JPEG>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_rotator: sysmmu@11D40000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x11D40000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <4 0>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_ROTATOR>, <&clock CLK_ROTATOR>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_isp: sysmmu@13260000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13260000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <10 6>;
+			clock-names = "sysmmu";
+			clocks = <&clock CLK_SMMU_FIMC_ISP>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_jpeg: sysmmu@11F20000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x11F20000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <4 2>;
-		power-domains = <&pd_gsc>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_JPEG>, <&clock CLK_JPEG>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_drc: sysmmu@13270000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13270000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <11 6>;
+			clock-names = "sysmmu";
+			clocks = <&clock CLK_SMMU_FIMC_DRC>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_isp: sysmmu@13260000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13260000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <10 6>;
-		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FIMC_ISP>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_fd: sysmmu@132A0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x132A0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <5 0>;
+			clock-names = "sysmmu";
+			clocks = <&clock CLK_SMMU_FIMC_FD>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_drc: sysmmu@13270000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13270000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <11 6>;
-		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FIMC_DRC>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_scc: sysmmu@13280000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13280000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <5 2>;
+			clock-names = "sysmmu";
+			clocks = <&clock CLK_SMMU_FIMC_SCC>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_fd: sysmmu@132A0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x132A0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <5 0>;
-		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FIMC_FD>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_scp: sysmmu@13290000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13290000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <3 6>;
+			clock-names = "sysmmu";
+			clocks = <&clock CLK_SMMU_FIMC_SCP>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_scc: sysmmu@13280000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13280000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <5 2>;
-		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FIMC_SCC>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_mcuctl: sysmmu@132B0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x132B0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <5 4>;
+			clock-names = "sysmmu";
+			clocks = <&clock CLK_SMMU_FIMC_MCU>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_scp: sysmmu@13290000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13290000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <3 6>;
-		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FIMC_SCP>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_odc: sysmmu@132C0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x132C0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <11 0>;
+			clock-names = "sysmmu";
+			clocks = <&clock CLK_SMMU_FIMC_ODC>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_mcuctl: sysmmu@132B0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x132B0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <5 4>;
-		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FIMC_MCU>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_dis0: sysmmu@132D0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x132D0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <10 4>;
+			clock-names = "sysmmu";
+			clocks = <&clock CLK_SMMU_FIMC_DIS0>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_odc: sysmmu@132C0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x132C0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <11 0>;
-		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FIMC_ODC>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_dis1: sysmmu@132E0000{
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x132E0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <9 4>;
+			clock-names = "sysmmu";
+			clocks = <&clock CLK_SMMU_FIMC_DIS1>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_dis0: sysmmu@132D0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x132D0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <10 4>;
-		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FIMC_DIS0>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_3dnr: sysmmu@132F0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x132F0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <5 6>;
+			clock-names = "sysmmu";
+			clocks = <&clock CLK_SMMU_FIMC_3DNR>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_dis1: sysmmu@132E0000{
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x132E0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <9 4>;
-		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FIMC_DIS1>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_lite0: sysmmu@13C40000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13C40000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <3 4>;
+			power-domains = <&pd_gsc>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_FIMC_LITE0>, <&clock CLK_CAMIF_TOP>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_3dnr: sysmmu@132F0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x132F0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <5 6>;
-		clock-names = "sysmmu";
-		clocks = <&clock CLK_SMMU_FIMC_3DNR>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimc_lite1: sysmmu@13C50000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13C50000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <24 1>;
+			power-domains = <&pd_gsc>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_FIMC_LITE1>, <&clock CLK_CAMIF_TOP>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_lite0: sysmmu@13C40000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13C40000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <3 4>;
-		power-domains = <&pd_gsc>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_FIMC_LITE0>, <&clock CLK_CAMIF_TOP>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_gsc0: sysmmu@13E80000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13E80000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <2 0>;
+			power-domains = <&pd_gsc>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_GSCL0>, <&clock CLK_GSCL0>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_fimc_lite1: sysmmu@13C50000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13C50000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <24 1>;
-		power-domains = <&pd_gsc>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_FIMC_LITE1>, <&clock CLK_CAMIF_TOP>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_gsc1: sysmmu@13E90000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13E90000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <2 2>;
+			power-domains = <&pd_gsc>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_GSCL1>, <&clock CLK_GSCL1>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_gsc0: sysmmu@13E80000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13E80000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <2 0>;
-		power-domains = <&pd_gsc>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_GSCL0>, <&clock CLK_GSCL0>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_gsc2: sysmmu@13EA0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13EA0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <2 4>;
+			power-domains = <&pd_gsc>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_GSCL2>, <&clock CLK_GSCL2>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_gsc1: sysmmu@13E90000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13E90000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <2 2>;
-		power-domains = <&pd_gsc>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_GSCL1>, <&clock CLK_GSCL1>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_gsc3: sysmmu@13EB0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13EB0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <2 6>;
+			power-domains = <&pd_gsc>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_GSCL3>, <&clock CLK_GSCL3>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_gsc2: sysmmu@13EA0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13EA0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <2 4>;
-		power-domains = <&pd_gsc>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_GSCL2>, <&clock CLK_GSCL2>;
-		#iommu-cells = <0>;
-	};
+		sysmmu_fimd1: sysmmu@14640000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x14640000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <3 2>;
+			power-domains = <&pd_disp1>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_FIMD1>, <&clock CLK_FIMD1>;
+			#iommu-cells = <0>;
+		};
 
-	sysmmu_gsc3: sysmmu@13EB0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13EB0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <2 6>;
-		power-domains = <&pd_gsc>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_GSCL3>, <&clock CLK_GSCL3>;
-		#iommu-cells = <0>;
+		sysmmu_tv: sysmmu@14650000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x14650000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <7 4>;
+			power-domains = <&pd_disp1>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_TV>, <&clock CLK_MIXER>;
+			#iommu-cells = <0>;
+		};
 	};
 
-	sysmmu_fimd1: sysmmu@14640000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x14640000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <3 2>;
-		power-domains = <&pd_disp1>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_FIMD1>, <&clock CLK_FIMD1>;
-		#iommu-cells = <0>;
-	};
+	thermal-zones {
+		cpu_thermal: cpu-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&tmu 0>;
 
-	sysmmu_tv: sysmmu@14650000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x14650000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <7 4>;
-		power-domains = <&pd_disp1>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_TV>, <&clock CLK_MIXER>;
-		#iommu-cells = <0>;
+			cooling-maps {
+				map0 {
+				     /* Corresponds to 800MHz at freq_table */
+				     cooling-device = <&cpu0 9 9>;
+				};
+				map1 {
+				     /* Corresponds to 200MHz at freq_table */
+				     cooling-device = <&cpu0 15 15>;
+			       };
+		       };
+		};
 	};
 };
 
@@ -1070,6 +1000,39 @@
 	iommus = <&sysmmu_fimd1>;
 };
 
+&i2c_0 {
+	clocks = <&clock CLK_I2C0>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_bus>;
+};
+
+&i2c_1 {
+	clocks = <&clock CLK_I2C1>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_bus>;
+};
+
+&i2c_2 {
+	clocks = <&clock CLK_I2C2>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c2_bus>;
+};
+
+&i2c_3 {
+	clocks = <&clock CLK_I2C3>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c3_bus>;
+};
+
+&pwm {
+	clocks = <&clock CLK_PWM>;
+	clock-names = "timers";
+};
+
 &rtc {
 	clocks = <&clock CLK_RTC>;
 	clock-names = "rtc";
diff --git a/arch/arm/boot/dts/exynos5410-odroidxu.dts b/arch/arm/boot/dts/exynos5410-odroidxu.dts
new file mode 100644
index 000000000000..d9499310a301
--- /dev/null
+++ b/arch/arm/boot/dts/exynos5410-odroidxu.dts
@@ -0,0 +1,580 @@
+/*
+ * Hardkernel Odroid XU board device tree source
+ *
+ * Copyright (c) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ * Copyright (c) 2016 Krzysztof Kozlowski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/dts-v1/;
+#include "exynos5410.dtsi"
+#include <dt-bindings/clock/maxim,max77802.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include "exynos54xx-odroidxu-leds.dtsi"
+
+/ {
+	model = "Hardkernel Odroid XU";
+	compatible = "hardkernel,odroid-xu", "samsung,exynos5410", "samsung,exynos5";
+
+	memory {
+		reg = <0x40000000 0x7ea00000>;
+	};
+
+	chosen {
+		linux,stdout-path = &serial_2;
+	};
+
+	emmc_pwrseq: pwrseq {
+		pinctrl-0 = <&emmc_nrst_pin>;
+		pinctrl-names = "default";
+		compatible = "mmc-pwrseq-emmc";
+		reset-gpios = <&gpd1 0 GPIO_ACTIVE_LOW>;
+	};
+
+	fan0: pwm-fan {
+		compatible = "pwm-fan";
+		pwms = <&pwm 0 20972 0>;
+		cooling-min-state = <0>;
+		cooling-max-state = <3>;
+		#cooling-cells = <2>;
+		cooling-levels = <0 130 170 230>;
+	};
+
+	fin_pll: xxti {
+		compatible = "fixed-clock";
+		clock-frequency = <24000000>;
+		clock-output-names = "fin_pll";
+		#clock-cells = <0>;
+	};
+
+	firmware@02073000 {
+		compatible = "samsung,secure-firmware";
+		reg = <0x02073000 0x1000>;
+	};
+};
+
+&cpu0_thermal {
+	thermal-sensors = <&tmu_cpu0 0>;
+	polling-delay-passive = <0>;
+	polling-delay = <0>;
+
+	trips {
+		cpu_alert0: cpu-alert-0 {
+			temperature = <50000>; /* millicelsius */
+			hysteresis = <5000>; /* millicelsius */
+			type = "active";
+		};
+		cpu_alert1: cpu-alert-1 {
+			temperature = <60000>; /* millicelsius */
+			hysteresis = <5000>; /* millicelsius */
+			type = "active";
+		};
+		cpu_alert2: cpu-alert-2 {
+			temperature = <70000>; /* millicelsius */
+			hysteresis = <5000>; /* millicelsius */
+			type = "active";
+		};
+		cpu_crit0: cpu-crit-0 {
+			temperature = <120000>; /* millicelsius */
+			hysteresis = <0>; /* millicelsius */
+			type = "critical";
+		};
+	};
+
+	cooling-maps {
+		map0 {
+			trip = <&cpu_alert0>;
+			cooling-device = <&fan0 0 1>;
+		};
+		map1 {
+			trip = <&cpu_alert1>;
+			cooling-device = <&fan0 1 2>;
+		};
+		map2 {
+			trip = <&cpu_alert2>;
+			cooling-device = <&fan0 2 3>;
+		};
+	};
+};
+
+&hsi2c_4 {
+	samsung,i2c-sda-delay = <100>;
+	samsung,i2c-max-bus-freq = <400000>;
+	status = "okay";
+
+	usb3503: usb-hub@08 {
+		compatible = "smsc,usb3503";
+		reg = <0x08>;
+
+		intn-gpios = <&gpx0 7 GPIO_ACTIVE_HIGH>;
+		connect-gpios = <&gpx0 6 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpx1 4 GPIO_ACTIVE_HIGH>;
+		initial-mode = <1>;
+
+		clock-names = "refclk";
+		clocks = <&pmu_system_controller 0>;
+		refclk-frequency = <24000000>;
+	};
+
+	max77802: pmic@09 {
+		compatible = "maxim,max77802";
+		reg = <0x9>;
+		interrupt-parent = <&gpx0>;
+		interrupts = <4 IRQ_TYPE_NONE>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&max77802_irq>, <&pmic_dvs_1>, <&pmic_dvs_2>,
+			    <&pmic_dvs_3>;
+		#clock-cells = <1>;
+
+		inl1-supply = <&buck5_reg>;
+		inl2-supply = <&buck7_reg>;
+		inl3-supply = <&buck9_reg>;
+		inl4-supply = <&buck9_reg>;
+		inl5-supply = <&buck9_reg>;
+		inl6-supply = <&buck10_reg>;
+		inl7-supply = <&buck9_reg>;
+		/* inl9 supply is BOOST, not configured here */
+		inl10-supply = <&buck7_reg>;
+
+		regulators {
+			buck1_reg: BUCK1 {
+				regulator-name = "vdd_mif";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1300000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck2_reg: BUCK2 {
+				regulator-name = "vdd_arm";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1500000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck3_reg: BUCK3 {
+				regulator-name = "vdd_int";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1400000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck4_reg: BUCK4 {
+				regulator-name = "vdd_g3d";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1400000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck5_reg: BUCK5 {
+				regulator-name = "vdd_mem";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1500000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck6_reg: BUCK6 {
+				regulator-name = "vdd_kfc";
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1500000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck7_reg: BUCK7 {
+				regulator-name = "buck7";
+				regulator-min-microvolt = <1300000>;
+				regulator-max-microvolt = <1300000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck8_reg: BUCK8 {
+				/* vdd_mmc0 */
+				regulator-name = "vddf_2v85";
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <2850000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck9_reg: BUCK9 {
+				regulator-name = "buck9";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			buck10_reg: BUCK10 {
+				regulator-name = "buck10";
+				regulator-min-microvolt = <2950000>;
+				regulator-max-microvolt = <2950000>;
+				regulator-always-on;
+				regulator-boot-on;
+			};
+
+			ldo1_reg: LDO1 {
+				regulator-name = "vdd_alive";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-always-on;
+			};
+
+			ldo2_reg: LDO2 {
+				regulator-name = "vddq_m1_m2";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-always-on;
+			};
+
+			ldo3_reg: LDO3 {
+				regulator-name = "vddq_gpio";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			ldo4_reg: LDO4 {
+				regulator-name = "vddq_mmc2";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3000000>;
+				/* Having it off prevents reboot */
+				regulator-always-on;
+			};
+
+			ldo5_reg: LDO5 {
+				regulator-name = "vdd18_hsic";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			ldo6_reg: LDO6 {
+				regulator-name = "vdd18_bpll";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			ldo7_reg: LDO7 {
+				regulator-name = "vddq_lcd";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+			};
+
+			ldo8_reg: LDO8 {
+				regulator-name = "vdd10_hdmi";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-always-on;
+			};
+
+			ldo9_reg: LDO9 {
+				regulator-name = "ldo9";
+			};
+
+			ldo10_reg: LDO10 {
+				regulator-name = "vdd18_mipi";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			ldo11_reg: LDO11 {
+				regulator-name = "vddq_mmc01";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				/*
+				 * Having it off prevents accessing MMC after
+				 * reboot with error:
+				 * MMC Device 1: Clock OFF has been failed.
+				 */
+				regulator-always-on;
+			};
+
+			ldo12_reg: LDO12 {
+				regulator-name = "vdd33_usb3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			ldo13_reg: LDO13 {
+				regulator-name = "vddq_abbg0";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			ldo14_reg: LDO14 {
+				regulator-name = "vddq_abbg1";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+
+			ldo15_reg: LDO15 {
+				regulator-name = "vdd10_usb3";
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-always-on;
+			};
+
+			ldo16_reg: LDO16 {
+				regulator-name = "ldo16";
+			};
+
+			ldo17_reg: LDO17 {
+				regulator-name = "cam_sensor_core";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+			};
+
+			ldo18_reg: LDO18 {
+				regulator-name = "ldo18";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+			};
+
+			ldo19_reg: LDO19 {
+				regulator-name = "ldo19";
+			};
+
+			ldo20_reg: LDO20 {
+				regulator-name = "vdd_mmc0";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+			};
+
+			ldo21_reg: LDO21 {
+				/* vdd_mmc2 */
+				regulator-name = "vddf_2v8";
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <2850000>;
+			};
+
+			ldo22_reg: LDO22 {
+				regulator-name = "ldo22";
+			};
+
+			ldo23_reg: LDO23 {
+				regulator-name = "dp_p3v3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			ldo24_reg: LDO24 {
+				regulator-name = "cam_af";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+			};
+
+			ldo25_reg: LDO25 {
+				regulator-name = "eth_p3v3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			ldo26_reg: LDO26 {
+				regulator-name = "usb30_extclk";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			ldo27_reg: LDO27 {
+				regulator-name = "ldo27";
+			};
+
+			ldo28_reg: LDO28 {
+				regulator-name = "ldo28";
+			};
+
+			ldo29_reg: LDO29 {
+				regulator-name = "ldo29";
+			};
+
+			ldo30_reg: LDO30 {
+				regulator-name = "vddq_e1_e2";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-always-on;
+			};
+
+			ldo31_reg: LDO31 {
+				regulator-name = "ldo31";
+			};
+
+			/* On revisions with ti,ina231 this is sensor VS */
+			ldo32_reg: LDO32 {
+				regulator-name = "vs_power_meter";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			ldo33_reg: LDO33 {
+				regulator-name = "ldo33";
+			};
+
+			ldo34_reg: LDO34 {
+				regulator-name = "ldo34";
+			};
+
+			ldo35_reg: LDO35 {
+				regulator-name = "ldo35";
+			};
+		};
+	};
+};
+
+&mmc_0 {
+	status = "okay";
+	mmc-pwrseq = <&emmc_pwrseq>;
+	cd-gpios = <&gpc0 2 GPIO_ACTIVE_LOW>;
+	card-detect-delay = <200>;
+	samsung,dw-mshc-ciu-div = <3>;
+	samsung,dw-mshc-sdr-timing = <0 4>;
+	samsung,dw-mshc-ddr-timing = <0 2>;
+	samsung,dw-mshc-hs400-timing = <0 2>;
+	samsung,read-strobe-delay = <90>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sd0_clk &sd0_cmd &sd0_bus1 &sd0_bus4 &sd0_bus8 &sd0_cd>;
+	bus-width = <8>;
+	cap-mmc-highspeed;
+	mmc-hs200-1_8v;
+	mmc-hs400-1_8v;
+	vmmc-supply = <&ldo20_reg>;
+	vqmmc-supply = <&ldo11_reg>;
+};
+
+&mmc_2 {
+	status = "okay";
+	card-detect-delay = <200>;
+	samsung,dw-mshc-ciu-div = <3>;
+	samsung,dw-mshc-sdr-timing = <0 4>;
+	samsung,dw-mshc-ddr-timing = <0 2>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sd2_clk &sd2_cmd &sd2_cd &sd2_bus1 &sd2_bus4>;
+	bus-width = <4>;
+	cap-sd-highspeed;
+	vmmc-supply = <&ldo21_reg>;
+	vqmmc-supply = <&ldo4_reg>;
+};
+
+&pinctrl_0 {
+	emmc_nrst_pin: emmc-nrst {
+		samsung,pins = "gpd1-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pmic_dvs_3: pmic-dvs-3 {
+		samsung,pins = "gpx0-0";
+		samsung,pin-function = <1>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pmic_dvs_2: pmic-dvs-2 {
+		samsung,pins = "gpx0-1";
+		samsung,pin-function = <1>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pmic_dvs_1: pmic-dvs-1 {
+		samsung,pins = "gpx0-2";
+		samsung,pin-function = <1>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+		samsung,pin-val = <1>;
+	};
+
+	max77802_irq: max77802-irq {
+		samsung,pins = "gpx0-4";
+		samsung,pin-function = <0xf>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+};
+
+&pwm {
+	/*
+	 * PWM 0 -- fan
+	 * PWM 1 -- Green LED
+	 * PWM 2 -- Blue LED
+	 * PWM 3 -- on MIPI connector for backlight
+	 */
+	pinctrl-0 = <&pwm0_out &pwm1_out &pwm2_out &pwm3_out>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&rtc {
+	status = "okay";
+	clocks = <&clock CLK_RTC>, <&max77802 MAX77802_CLK_32K_AP>;
+	clock-names = "rtc", "rtc_src";
+};
+
+&serial_0 {
+	status = "okay";
+};
+
+&serial_1 {
+	status = "okay";
+};
+
+&serial_2 {
+	status = "okay";
+};
+
+&serial_3 {
+	status = "okay";
+};
+
+&tmu_cpu0 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_cpu1 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_cpu2 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_cpu3 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&usbdrd_dwc3_0 {
+	dr_mode = "host";
+};
+
+&usbdrd_dwc3_1 {
+	dr_mode = "peripheral";
+};
+
+&usbdrd3_0 {
+	vdd33-supply = <&ldo12_reg>;
+	vdd10-supply = <&ldo15_reg>;
+};
+
+&usbdrd3_1 {
+	vdd33-supply = <&ldo12_reg>;
+	vdd10-supply = <&ldo15_reg>;
+};
diff --git a/arch/arm/boot/dts/exynos5410-pinctrl.dtsi b/arch/arm/boot/dts/exynos5410-pinctrl.dtsi
index f9aa6bb55464..b58a0f29f42c 100644
--- a/arch/arm/boot/dts/exynos5410-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5410-pinctrl.dtsi
@@ -277,6 +277,216 @@
 		interrupt-controller;
 		#interrupt-cells = <2>;
 	};
+
+	uart0_data: uart0-data {
+		samsung,pins = "gpa0-0", "gpa0-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart0_fctl: uart0-fctl {
+		samsung,pins = "gpa0-2", "gpa0-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart1_data: uart1-data {
+		samsung,pins = "gpa0-4", "gpa0-5";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart1_fctl: uart1-fctl {
+		samsung,pins = "gpa0-6", "gpa0-7";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c2_bus: i2c2-bus {
+		samsung,pins = "gpa0-6", "gpa0-7";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart2_data: uart2-data {
+		samsung,pins = "gpa1-0", "gpa1-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart2_fctl: uart2-fctl {
+		samsung,pins = "gpa1-2", "gpa1-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c3_bus: i2c3-bus {
+		samsung,pins = "gpa1-2", "gpa1-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	uart3_data: uart3-data {
+		samsung,pins = "gpa1-4", "gpa1-5";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c4_hs_bus: i2c4-hs-bus {
+		samsung,pins = "gpa2-0", "gpa2-1";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c5_hs_bus: i2c5-hs-bus {
+		samsung,pins = "gpa2-2", "gpa2-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c6_hs_bus: i2c6-hs-bus {
+		samsung,pins = "gpb1-3", "gpb1-4";
+		samsung,pin-function = <4>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm0_out: pwm0-out {
+		samsung,pins = "gpb2-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm1_out: pwm1-out {
+		samsung,pins = "gpb2-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm2_out: pwm2-out {
+		samsung,pins = "gpb2-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	pwm3_out: pwm3-out {
+		samsung,pins = "gpb2-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c7_hs_bus: i2c7-hs-bus {
+		samsung,pins = "gpb2-2", "gpb2-3";
+		samsung,pin-function = <3>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c0_bus: i2c0-bus {
+		samsung,pins = "gpb3-0", "gpb3-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	i2c1_bus: i2c1-bus {
+		samsung,pins = "gpb3-2", "gpb3-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <0>;
+	};
+
+	sd0_clk: sd0-clk {
+		samsung,pins = "gpc0-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_cmd: sd0-cmd {
+		samsung,pins = "gpc0-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_cd: sd0-cd {
+		samsung,pins = "gpc0-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_bus1: sd0-bus-width1 {
+		samsung,pins = "gpc0-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_bus4: sd0-bus-width4 {
+		samsung,pins = "gpc0-4", "gpc0-5", "gpc0-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_clk: sd2-clk {
+		samsung,pins = "gpc2-0";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_cmd: sd2-cmd {
+		samsung,pins = "gpc2-1";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <0>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_cd: sd2-cd {
+		samsung,pins = "gpc2-2";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_bus1: sd2-bus-width1 {
+		samsung,pins = "gpc2-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd2_bus4: sd2-bus-width4 {
+		samsung,pins = "gpc2-4", "gpc2-5", "gpc2-6";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
+
+	sd0_bus8: sd0-bus-width8 {
+		samsung,pins = "gpc3-0", "gpc3-1", "gpc3-2", "gpc3-3";
+		samsung,pin-function = <2>;
+		samsung,pin-pud = <3>;
+		samsung,pin-drv = <3>;
+	};
 };
 
 &pinctrl_1 {
diff --git a/arch/arm/boot/dts/exynos5410-smdk5410.dts b/arch/arm/boot/dts/exynos5410-smdk5410.dts
index 0f6429e1b75c..777fcf2edd79 100644
--- a/arch/arm/boot/dts/exynos5410-smdk5410.dts
+++ b/arch/arm/boot/dts/exynos5410-smdk5410.dts
@@ -102,14 +102,14 @@
 	};
 };
 
-&uart0 {
+&serial_0 {
 	status = "okay";
 };
 
-&uart1 {
+&serial_1 {
 	status = "okay";
 };
 
-&uart2 {
+&serial_2 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/exynos5410.dtsi b/arch/arm/boot/dts/exynos5410.dtsi
index 7a56aec2c5ba..137f48464f8b 100644
--- a/arch/arm/boot/dts/exynos5410.dtsi
+++ b/arch/arm/boot/dts/exynos5410.dtsi
@@ -13,9 +13,10 @@
  * published by the Free Software Foundation.
  */
 
-#include "skeleton.dtsi"
+#include "exynos54xx.dtsi"
 #include "exynos-syscon-restart.dtsi"
 #include <dt-bindings/clock/exynos5410.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
 
 / {
 	compatible = "samsung,exynos5410", "samsung,exynos5";
@@ -26,37 +27,34 @@
 		pinctrl1 = &pinctrl_1;
 		pinctrl2 = &pinctrl_2;
 		pinctrl3 = &pinctrl_3;
-		serial0 = &uart0;
-		serial1 = &uart1;
-		serial2 = &uart2;
 	};
 
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		CPU0: cpu@0 {
+		cpu0: cpu@0 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <0x0>;
 			clock-frequency = <1600000000>;
 		};
 
-		CPU1: cpu@1 {
+		cpu1: cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <0x1>;
 			clock-frequency = <1600000000>;
 		};
 
-		CPU2: cpu@2 {
+		cpu2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <0x2>;
 			clock-frequency = <1600000000>;
 		};
 
-		CPU3: cpu@3 {
+		cpu3: cpu@3 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <0x3>;
@@ -70,105 +68,54 @@
 		#size-cells = <1>;
 		ranges;
 
-		combiner: interrupt-controller@10440000 {
-			compatible = "samsung,exynos4210-combiner";
-			#interrupt-cells = <2>;
-			interrupt-controller;
-			samsung,combiner-nr = <32>;
-			reg = <0x10440000 0x1000>;
-			interrupts =	<0 0 0>, <0 1 0>, <0 2 0>, <0 3 0>,
-					<0 4 0>, <0 5 0>, <0 6 0>, <0 7 0>,
-					<0 8 0>, <0 9 0>, <0 10 0>, <0 11 0>,
-					<0 12 0>, <0 13 0>, <0 14 0>, <0 15 0>,
-					<0 16 0>, <0 17 0>, <0 18 0>, <0 19 0>,
-					<0 20 0>, <0 21 0>, <0 22 0>, <0 23 0>,
-					<0 24 0>, <0 25 0>, <0 26 0>, <0 27 0>,
-					<0 28 0>, <0 29 0>, <0 30 0>, <0 31 0>;
-		};
-
-		gic: interrupt-controller@10481000 {
-			compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
-			#interrupt-cells = <3>;
-			interrupt-controller;
-			reg =	<0x10481000 0x1000>,
-				<0x10482000 0x1000>,
-				<0x10484000 0x2000>,
-				<0x10486000 0x2000>;
-			interrupts = <1 9 0xf04>;
-		};
-
-		chipid@10000000 {
-			compatible = "samsung,exynos4210-chipid";
-			reg = <0x10000000 0x100>;
-		};
-
-		sromc: memory-controller@12250000 {
-			compatible = "samsung,exynos4210-srom";
-			reg = <0x12250000 0x14>;
-			#address-cells = <2>;
-			#size-cells = <1>;
-			ranges = <0 0 0x04000000 0x20000
-				  1 0 0x05000000 0x20000
-				  2 0 0x06000000 0x20000
-				  3 0 0x07000000 0x20000>;
-		};
-
 		pmu_system_controller: system-controller@10040000 {
 			compatible = "samsung,exynos5410-pmu", "syscon";
 			reg = <0x10040000 0x5000>;
+			clock-names = "clkout16";
+			clocks = <&fin_pll>;
+			#clock-cells = <1>;
 		};
 
-		mct: mct@101C0000 {
-			compatible = "samsung,exynos4210-mct";
-			reg = <0x101C0000 0xB00>;
-			interrupt-parent = <&interrupt_map>;
-			interrupts = <0>, <1>, <2>, <3>,
-				<4>, <5>, <6>, <7>,
-				<8>, <9>, <10>, <11>;
-			clocks = <&fin_pll>, <&clock CLK_MCT>;
-			clock-names = "fin_pll", "mct";
-
-			interrupt_map: interrupt-map {
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = <0 &combiner 23 3>,
-						<1 &combiner 23 4>,
-						<2 &combiner 25 2>,
-						<3 &combiner 25 3>,
-						<4 &gic 0 120 0>,
-						<5 &gic 0 121 0>,
-						<6 &gic 0 122 0>,
-						<7 &gic 0 123 0>,
-						<8 &gic 0 128 0>,
-						<9 &gic 0 129 0>,
-						<10 &gic 0 130 0>,
-						<11 &gic 0 131 0>;
-			};
+		clock: clock-controller@10010000 {
+			compatible = "samsung,exynos5410-clock";
+			reg = <0x10010000 0x30000>;
+			#clock-cells = <1>;
 		};
 
-		sysram@02020000 {
-			compatible = "mmio-sram";
-			reg = <0x02020000 0x54000>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0 0x02020000 0x54000>;
+		tmu_cpu0: tmu@10060000 {
+			compatible = "samsung,exynos5420-tmu";
+			reg = <0x10060000 0x100>;
+			interrupts = <GIC_SPI 65 0>;
+			clocks = <&clock CLK_TMU>;
+			clock-names = "tmu_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
+		};
 
-			smp-sysram@0 {
-				compatible = "samsung,exynos4210-sysram";
-				reg = <0x0 0x1000>;
-			};
+		tmu_cpu1: tmu@10064000 {
+			compatible = "samsung,exynos5420-tmu";
+			reg = <0x10064000 0x100>;
+			interrupts = <GIC_SPI 183 0>;
+			clocks = <&clock CLK_TMU>;
+			clock-names = "tmu_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
+		};
 
-			smp-sysram@53000 {
-				compatible = "samsung,exynos4210-sysram-ns";
-				reg = <0x53000 0x1000>;
-			};
+		tmu_cpu2: tmu@10068000 {
+			compatible = "samsung,exynos5420-tmu";
+			reg = <0x10068000 0x100>;
+			interrupts = <GIC_SPI 184 0>;
+			clocks = <&clock CLK_TMU>;
+			clock-names = "tmu_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
 		};
 
-		clock: clock-controller@10010000 {
-			compatible = "samsung,exynos5410-clock";
-			reg = <0x10010000 0x30000>;
-			#clock-cells = <1>;
+		tmu_cpu3: tmu@1006c000 {
+			compatible = "samsung,exynos5420-tmu";
+			reg = <0x1006c000 0x100>;
+			interrupts = <GIC_SPI 185 0>;
+			clocks = <&clock CLK_TMU>;
+			clock-names = "tmu_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
 		};
 
 		mmc_0: mmc@12200000 {
@@ -236,34 +183,182 @@
 			reg = <0x03860000 0x1000>;
 			interrupts = <0 47 0>;
 		};
+	};
 
-		uart0: serial@12C00000 {
-			compatible = "samsung,exynos4210-uart";
-			reg = <0x12C00000 0x100>;
-			interrupts = <0 51 0>;
-			clocks = <&clock CLK_UART0>, <&clock CLK_SCLK_UART0>;
-			clock-names = "uart", "clk_uart_baud0";
-			status = "disabled";
+	thermal-zones {
+		cpu0_thermal: cpu0-thermal {
+			thermal-sensors = <&tmu_cpu0>;
+			#include "exynos5420-trip-points.dtsi"
 		};
-
-		uart1: serial@12C10000 {
-			compatible = "samsung,exynos4210-uart";
-			reg = <0x12C10000 0x100>;
-			interrupts = <0 52 0>;
-			clocks = <&clock CLK_UART1>, <&clock CLK_SCLK_UART1>;
-			clock-names = "uart", "clk_uart_baud0";
-			status = "disabled";
+		cpu1_thermal: cpu1-thermal {
+		       thermal-sensors = <&tmu_cpu1>;
+		       #include "exynos5420-trip-points.dtsi"
 		};
-
-		uart2: serial@12C20000 {
-			compatible = "samsung,exynos4210-uart";
-			reg = <0x12C20000 0x100>;
-			interrupts = <0 53 0>;
-			clocks = <&clock CLK_UART2>, <&clock CLK_SCLK_UART2>;
-			clock-names = "uart", "clk_uart_baud0";
-			status = "disabled";
+		cpu2_thermal: cpu2-thermal {
+		       thermal-sensors = <&tmu_cpu2>;
+		       #include "exynos5420-trip-points.dtsi"
+		};
+		cpu3_thermal: cpu3-thermal {
+		       thermal-sensors = <&tmu_cpu3>;
+		       #include "exynos5420-trip-points.dtsi"
 		};
 	};
 };
 
+&i2c_0 {
+	clocks = <&clock CLK_I2C0>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_bus>;
+};
+
+&i2c_1 {
+	clocks = <&clock CLK_I2C1>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_bus>;
+};
+
+&i2c_2 {
+	clocks = <&clock CLK_I2C2>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c2_bus>;
+};
+
+&i2c_3 {
+	clocks = <&clock CLK_I2C3>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c3_bus>;
+};
+
+&hsi2c_4 {
+	clocks = <&clock CLK_USI0>;
+	clock-names = "hsi2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c4_hs_bus>;
+};
+
+&hsi2c_5 {
+	clocks = <&clock CLK_USI1>;
+	clock-names = "hsi2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c5_hs_bus>;
+};
+
+&hsi2c_6 {
+	clocks = <&clock CLK_USI2>;
+	clock-names = "hsi2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c6_hs_bus>;
+};
+
+&hsi2c_7 {
+	clocks = <&clock CLK_USI3>;
+	clock-names = "hsi2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c7_hs_bus>;
+};
+
+&mct {
+	clocks = <&fin_pll>, <&clock CLK_MCT>;
+	clock-names = "fin_pll", "mct";
+};
+
+&pwm {
+	clocks = <&clock CLK_PWM>;
+	clock-names = "timers";
+};
+
+&rtc {
+	clocks = <&clock CLK_RTC>;
+	clock-names = "rtc";
+	interrupt-parent = <&pmu_system_controller>;
+	status = "disabled";
+};
+
+&serial_0 {
+	clocks = <&clock CLK_UART0>, <&clock CLK_SCLK_UART0>;
+	clock-names = "uart", "clk_uart_baud0";
+};
+
+&serial_1 {
+	clocks = <&clock CLK_UART1>, <&clock CLK_SCLK_UART1>;
+	clock-names = "uart", "clk_uart_baud0";
+};
+
+&serial_2 {
+	clocks = <&clock CLK_UART2>, <&clock CLK_SCLK_UART2>;
+	clock-names = "uart", "clk_uart_baud0";
+};
+
+&serial_3 {
+	clocks = <&clock CLK_UART3>, <&clock CLK_SCLK_UART3>;
+	clock-names = "uart", "clk_uart_baud0";
+};
+
+&sss {
+	clocks = <&clock CLK_SSS>;
+	clock-names = "secss";
+};
+
+&sromc {
+	#address-cells = <2>;
+	#size-cells = <1>;
+	ranges = <0 0 0x04000000 0x20000
+		  1 0 0x05000000 0x20000
+		  2 0 0x06000000 0x20000
+		  3 0 0x07000000 0x20000>;
+};
+
+&usbdrd3_0 {
+	clocks = <&clock CLK_USBD300>;
+	clock-names = "usbdrd30";
+};
+
+&usbdrd_phy0 {
+	clocks = <&clock CLK_USBD300>, <&clock CLK_SCLK_USBPHY300>;
+	clock-names = "phy", "ref";
+	samsung,pmu-syscon = <&pmu_system_controller>;
+};
+
+&usbdrd3_1 {
+	clocks = <&clock CLK_USBD301>;
+	clock-names = "usbdrd30";
+};
+
+&usbdrd_dwc3_1 {
+	interrupts = <GIC_SPI 200 0>;
+};
+
+&usbdrd_phy1 {
+	clocks = <&clock CLK_USBD301>, <&clock CLK_SCLK_USBPHY301>;
+	clock-names = "phy", "ref";
+	samsung,pmu-syscon = <&pmu_system_controller>;
+};
+
+&usbhost1 {
+	clocks = <&clock CLK_USBH20>;
+	clock-names = "usbhost";
+};
+
+&usbhost2 {
+	clocks = <&clock CLK_USBH20>;
+	clock-names = "usbhost";
+};
+
+&usb2_phy {
+	clocks = <&clock CLK_USBH20>, <&clock CLK_SCLK_USBPHY300>;
+	clock-names = "phy", "ref";
+	samsung,sysreg-phandle = <&sysreg_system_controller>;
+	samsung,pmureg-phandle = <&pmu_system_controller>;
+};
+
+&watchdog {
+	clocks = <&clock CLK_WDT>;
+	clock-names = "watchdog";
+	samsung,syscon-phandle = <&pmu_system_controller>;
+};
+
 #include "exynos5410-pinctrl.dtsi"
diff --git a/arch/arm/boot/dts/exynos5420-arndale-octa.dts b/arch/arm/boot/dts/exynos5420-arndale-octa.dts
index 60bc861d0f9d..39a3b81478fd 100644
--- a/arch/arm/boot/dts/exynos5420-arndale-octa.dts
+++ b/arch/arm/boot/dts/exynos5420-arndale-octa.dts
@@ -16,6 +16,7 @@
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/clock/samsung,s2mps11.h>
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "Insignal Arndale Octa evaluation board based on EXYNOS5420";
@@ -346,11 +347,6 @@
 	};
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-};
-
 &mmc_0 {
 	status = "okay";
 	broken-cd;
diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts
index 1de972d46a87..fe4e0915c0c6 100644
--- a/arch/arm/boot/dts/exynos5420-peach-pit.dts
+++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts
@@ -16,6 +16,7 @@
 #include <dt-bindings/regulator/maxim,max77802.h>
 #include "exynos5420.dtsi"
 #include "exynos5420-cpus.dtsi"
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "Google Peach Pit Rev 6+";
@@ -278,7 +279,6 @@
 				regulator-name = "vdd_1v2";
 				regulator-min-microvolt = <1200000>;
 				regulator-max-microvolt = <1200000>;
-				regulator-always-on;
 				regulator-boot-on;
 				regulator-state-mem {
 					regulator-off-in-suspend;
@@ -301,7 +301,6 @@
 				regulator-name = "vdd_1v35";
 				regulator-min-microvolt = <1350000>;
 				regulator-max-microvolt = <1350000>;
-				regulator-always-on;
 				regulator-boot-on;
 				regulator-state-mem {
 					regulator-on-in-suspend;
@@ -323,7 +322,6 @@
 				regulator-name = "vdd_2v";
 				regulator-min-microvolt = <2000000>;
 				regulator-max-microvolt = <2000000>;
-				regulator-always-on;
 				regulator-boot-on;
 				regulator-state-mem {
 					regulator-on-in-suspend;
@@ -334,7 +332,6 @@
 				regulator-name = "vdd_1v8";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
-				regulator-always-on;
 				regulator-boot-on;
 				regulator-state-mem {
 					regulator-on-in-suspend;
@@ -419,7 +416,6 @@
 				regulator-name = "vdd_ldo9";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
-				regulator-always-on;
 				regulator-state-mem {
 					regulator-on-in-suspend;
 					regulator-mode = <MAX77802_OPMODE_LP>;
@@ -430,7 +426,6 @@
 				regulator-name = "vdd_ldo10";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
-				regulator-always-on;
 				regulator-state-mem {
 					regulator-off-in-suspend;
 				};
@@ -701,11 +696,6 @@
 	status = "okay";
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-};
-
 &mmc_0 {
 	status = "okay";
 	num-slots = <1>;
@@ -1053,6 +1043,26 @@
 	status = "okay";
 };
 
+&tmu_cpu0 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_cpu1 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_cpu2 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_cpu3 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_gpu {
+	vtmu-supply = <&ldo10_reg>;
+};
+
 &usbdrd_dwc3_0 {
 	dr_mode = "host";
 };
diff --git a/arch/arm/boot/dts/exynos5420-pinctrl.dtsi b/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
index 130563b2ca95..14beb7e07323 100644
--- a/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5420-pinctrl.dtsi
@@ -193,17 +193,17 @@
 		samsung,pin-drv = <3>;
 	};
 
-	sd1_clk: sd1-clk {
-		samsung,pins = "gpc1-0";
+	sd0_rclk: sd0-rclk {
+		samsung,pins = "gpc0-7";
 		samsung,pin-function = <2>;
-		samsung,pin-pud = <0>;
+		samsung,pin-pud = <1>;
 		samsung,pin-drv = <3>;
 	};
 
-	sd0_rclk: sd0-rclk {
-		samsung,pins = "gpc0-7";
+	sd1_clk: sd1-clk {
+		samsung,pins = "gpc1-0";
 		samsung,pin-function = <2>;
-		samsung,pin-pud = <1>;
+		samsung,pin-pud = <0>;
 		samsung,pin-drv = <3>;
 	};
 
diff --git a/arch/arm/boot/dts/exynos5420-smdk5420.dts b/arch/arm/boot/dts/exynos5420-smdk5420.dts
index 2e748d19322f..ed8f3426911b 100644
--- a/arch/arm/boot/dts/exynos5420-smdk5420.dts
+++ b/arch/arm/boot/dts/exynos5420-smdk5420.dts
@@ -13,6 +13,7 @@
 #include "exynos5420.dtsi"
 #include "exynos5420-cpus.dtsi"
 #include <dt-bindings/gpio/gpio.h>
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "Samsung SMDK5420 board based on EXYNOS5420";
@@ -354,11 +355,6 @@
 	};
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-};
-
 &mmc_0 {
 	status = "okay";
 	broken-cd;
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index c6e05eb88937..00c4cfa54839 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -13,10 +13,10 @@
  * published by the Free Software Foundation.
  */
 
+#include "exynos54xx.dtsi"
 #include <dt-bindings/clock/exynos5420.h>
-#include "exynos5.dtsi"
-
 #include <dt-bindings/clock/exynos-audss-clk.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
 
 / {
 	compatible = "samsung,exynos5420", "samsung,exynos5";
@@ -30,14 +30,6 @@
 		pinctrl2 = &pinctrl_2;
 		pinctrl3 = &pinctrl_3;
 		pinctrl4 = &pinctrl_4;
-		i2c0 = &i2c_0;
-		i2c1 = &i2c_1;
-		i2c2 = &i2c_2;
-		i2c3 = &i2c_3;
-		i2c4 = &hsi2c_4;
-		i2c5 = &hsi2c_5;
-		i2c6 = &hsi2c_6;
-		i2c7 = &hsi2c_7;
 		i2c8 = &hsi2c_8;
 		i2c9 = &hsi2c_9;
 		i2c10 = &hsi2c_10;
@@ -46,118 +38,6 @@
 		spi0 = &spi_0;
 		spi1 = &spi_1;
 		spi2 = &spi_2;
-		usbdrdphy0 = &usbdrd_phy0;
-		usbdrdphy1 = &usbdrd_phy1;
-	};
-
-	cluster_a15_opp_table: opp_table0 {
-		compatible = "operating-points-v2";
-		opp-shared;
-		opp@1800000000 {
-			opp-hz = /bits/ 64 <1800000000>;
-			opp-microvolt = <1250000>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1700000000 {
-			opp-hz = /bits/ 64 <1700000000>;
-			opp-microvolt = <1212500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1600000000 {
-			opp-hz = /bits/ 64 <1600000000>;
-			opp-microvolt = <1175000>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1500000000 {
-			opp-hz = /bits/ 64 <1500000000>;
-			opp-microvolt = <1137500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1400000000 {
-			opp-hz = /bits/ 64 <1400000000>;
-			opp-microvolt = <1112500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1300000000 {
-			opp-hz = /bits/ 64 <1300000000>;
-			opp-microvolt = <1062500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1200000000 {
-			opp-hz = /bits/ 64 <1200000000>;
-			opp-microvolt = <1037500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1100000000 {
-			opp-hz = /bits/ 64 <1100000000>;
-			opp-microvolt = <1012500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1000000000 {
-			opp-hz = /bits/ 64 <1000000000>;
-			opp-microvolt = < 987500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@900000000 {
-			opp-hz = /bits/ 64 <900000000>;
-			opp-microvolt = < 962500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@800000000 {
-			opp-hz = /bits/ 64 <800000000>;
-			opp-microvolt = < 937500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@700000000 {
-			opp-hz = /bits/ 64 <700000000>;
-			opp-microvolt = < 912500>;
-			clock-latency-ns = <140000>;
-		};
-	};
-
-	cluster_a7_opp_table: opp_table1 {
-		compatible = "operating-points-v2";
-		opp-shared;
-		opp@1300000000 {
-			opp-hz = /bits/ 64 <1300000000>;
-			opp-microvolt = <1275000>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1200000000 {
-			opp-hz = /bits/ 64 <1200000000>;
-			opp-microvolt = <1212500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1100000000 {
-			opp-hz = /bits/ 64 <1100000000>;
-			opp-microvolt = <1162500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@1000000000 {
-			opp-hz = /bits/ 64 <1000000000>;
-			opp-microvolt = <1112500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@900000000 {
-			opp-hz = /bits/ 64 <900000000>;
-			opp-microvolt = <1062500>;
-			clock-latency-ns = <140000>;
-		};
-		opp@800000000 {
-			opp-hz = /bits/ 64 <800000000>;
-			opp-microvolt = <1025000>;
-			clock-latency-ns = <140000>;
-		};
-		opp@700000000 {
-			opp-hz = /bits/ 64 <700000000>;
-			opp-microvolt = <975000>;
-			clock-latency-ns = <140000>;
-		};
-		opp@600000000 {
-			opp-hz = /bits/ 64 <600000000>;
-			opp-microvolt = <937500>;
-			clock-latency-ns = <140000>;
-		};
 	};
 
 	/*
@@ -165,1434 +45,1270 @@
 	 * by exynos5420-cpus.dtsi or exynos5422-cpus.dtsi.
 	 */
 
-	cci: cci@10d20000 {
-		compatible = "arm,cci-400";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		reg = <0x10d20000 0x1000>;
-		ranges = <0x0 0x10d20000 0x6000>;
-
-		cci_control0: slave-if@4000 {
-			compatible = "arm,cci-400-ctrl-if";
-			interface-type = "ace";
-			reg = <0x4000 0x1000>;
-		};
-		cci_control1: slave-if@5000 {
-			compatible = "arm,cci-400-ctrl-if";
-			interface-type = "ace";
-			reg = <0x5000 0x1000>;
+	soc: soc {
+		cluster_a15_opp_table: opp_table0 {
+			compatible = "operating-points-v2";
+			opp-shared;
+			opp@1800000000 {
+				opp-hz = /bits/ 64 <1800000000>;
+				opp-microvolt = <1250000>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1700000000 {
+				opp-hz = /bits/ 64 <1700000000>;
+				opp-microvolt = <1212500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1600000000 {
+				opp-hz = /bits/ 64 <1600000000>;
+				opp-microvolt = <1175000>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1500000000 {
+				opp-hz = /bits/ 64 <1500000000>;
+				opp-microvolt = <1137500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1400000000 {
+				opp-hz = /bits/ 64 <1400000000>;
+				opp-microvolt = <1112500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1300000000 {
+				opp-hz = /bits/ 64 <1300000000>;
+				opp-microvolt = <1062500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1200000000 {
+				opp-hz = /bits/ 64 <1200000000>;
+				opp-microvolt = <1037500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1100000000 {
+				opp-hz = /bits/ 64 <1100000000>;
+				opp-microvolt = <1012500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1000000000 {
+				opp-hz = /bits/ 64 <1000000000>;
+				opp-microvolt = < 987500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@900000000 {
+				opp-hz = /bits/ 64 <900000000>;
+				opp-microvolt = < 962500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@800000000 {
+				opp-hz = /bits/ 64 <800000000>;
+				opp-microvolt = < 937500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@700000000 {
+				opp-hz = /bits/ 64 <700000000>;
+				opp-microvolt = < 912500>;
+				clock-latency-ns = <140000>;
+			};
+		};
+
+		cluster_a7_opp_table: opp_table1 {
+			compatible = "operating-points-v2";
+			opp-shared;
+			opp@1300000000 {
+				opp-hz = /bits/ 64 <1300000000>;
+				opp-microvolt = <1275000>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1200000000 {
+				opp-hz = /bits/ 64 <1200000000>;
+				opp-microvolt = <1212500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1100000000 {
+				opp-hz = /bits/ 64 <1100000000>;
+				opp-microvolt = <1162500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@1000000000 {
+				opp-hz = /bits/ 64 <1000000000>;
+				opp-microvolt = <1112500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@900000000 {
+				opp-hz = /bits/ 64 <900000000>;
+				opp-microvolt = <1062500>;
+				clock-latency-ns = <140000>;
+			};
+			opp@800000000 {
+				opp-hz = /bits/ 64 <800000000>;
+				opp-microvolt = <1025000>;
+				clock-latency-ns = <140000>;
+			};
+			opp@700000000 {
+				opp-hz = /bits/ 64 <700000000>;
+				opp-microvolt = <975000>;
+				clock-latency-ns = <140000>;
+			};
+			opp@600000000 {
+				opp-hz = /bits/ 64 <600000000>;
+				opp-microvolt = <937500>;
+				clock-latency-ns = <140000>;
+			};
+		};
+
+		cci: cci@10d20000 {
+			compatible = "arm,cci-400";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x10d20000 0x1000>;
+			ranges = <0x0 0x10d20000 0x6000>;
+
+			cci_control0: slave-if@4000 {
+				compatible = "arm,cci-400-ctrl-if";
+				interface-type = "ace";
+				reg = <0x4000 0x1000>;
+			};
+			cci_control1: slave-if@5000 {
+				compatible = "arm,cci-400-ctrl-if";
+				interface-type = "ace";
+				reg = <0x5000 0x1000>;
+			};
+		};
+
+		clock: clock-controller@10010000 {
+			compatible = "samsung,exynos5420-clock";
+			reg = <0x10010000 0x30000>;
+			#clock-cells = <1>;
+		};
+
+		clock_audss: audss-clock-controller@3810000 {
+			compatible = "samsung,exynos5420-audss-clock";
+			reg = <0x03810000 0x0C>;
+			#clock-cells = <1>;
+			clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MAU_EPLL>,
+				 <&clock CLK_SCLK_MAUDIO0>, <&clock CLK_SCLK_MAUPCM0>;
+			clock-names = "pll_ref", "pll_in", "sclk_audio", "sclk_pcm_in";
+		};
+
+		mfc: codec@11000000 {
+			compatible = "samsung,mfc-v7";
+			reg = <0x11000000 0x10000>;
+			interrupts = <0 96 0>;
+			clocks = <&clock CLK_MFC>;
+			clock-names = "mfc";
+			power-domains = <&mfc_pd>;
+			iommus = <&sysmmu_mfc_l>, <&sysmmu_mfc_r>;
+			iommu-names = "left", "right";
+		};
+
+		mmc_0: mmc@12200000 {
+			compatible = "samsung,exynos5420-dw-mshc-smu";
+			interrupts = <0 75 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x12200000 0x2000>;
+			clocks = <&clock CLK_MMC0>, <&clock CLK_SCLK_MMC0>;
+			clock-names = "biu", "ciu";
+			fifo-depth = <0x40>;
+			status = "disabled";
 		};
-	};
-
-	sysram@02020000 {
-		compatible = "mmio-sram";
-		reg = <0x02020000 0x54000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0 0x02020000 0x54000>;
 
-		smp-sysram@0 {
-			compatible = "samsung,exynos4210-sysram";
-			reg = <0x0 0x1000>;
+		mmc_1: mmc@12210000 {
+			compatible = "samsung,exynos5420-dw-mshc-smu";
+			interrupts = <0 76 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x12210000 0x2000>;
+			clocks = <&clock CLK_MMC1>, <&clock CLK_SCLK_MMC1>;
+			clock-names = "biu", "ciu";
+			fifo-depth = <0x40>;
+			status = "disabled";
 		};
 
-		smp-sysram@53000 {
-			compatible = "samsung,exynos4210-sysram-ns";
-			reg = <0x53000 0x1000>;
+		mmc_2: mmc@12220000 {
+			compatible = "samsung,exynos5420-dw-mshc";
+			interrupts = <0 77 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x12220000 0x1000>;
+			clocks = <&clock CLK_MMC2>, <&clock CLK_SCLK_MMC2>;
+			clock-names = "biu", "ciu";
+			fifo-depth = <0x40>;
+			status = "disabled";
 		};
-	};
-
-	clock: clock-controller@10010000 {
-		compatible = "samsung,exynos5420-clock";
-		reg = <0x10010000 0x30000>;
-		#clock-cells = <1>;
-	};
 
-	clock_audss: audss-clock-controller@3810000 {
-		compatible = "samsung,exynos5420-audss-clock";
-		reg = <0x03810000 0x0C>;
-		#clock-cells = <1>;
-		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MAU_EPLL>,
-			 <&clock CLK_SCLK_MAUDIO0>, <&clock CLK_SCLK_MAUPCM0>;
-		clock-names = "pll_ref", "pll_in", "sclk_audio", "sclk_pcm_in";
-	};
-
-	mfc: codec@11000000 {
-		compatible = "samsung,mfc-v7";
-		reg = <0x11000000 0x10000>;
-		interrupts = <0 96 0>;
-		clocks = <&clock CLK_MFC>;
-		clock-names = "mfc";
-		power-domains = <&mfc_pd>;
-		iommus = <&sysmmu_mfc_l>, <&sysmmu_mfc_r>;
-		iommu-names = "left", "right";
-	};
+		nocp_mem0_0: nocp@10CA1000 {
+			compatible = "samsung,exynos5420-nocp";
+			reg = <0x10CA1000 0x200>;
+			status = "disabled";
+		};
 
-	mmc_0: mmc@12200000 {
-		compatible = "samsung,exynos5420-dw-mshc-smu";
-		interrupts = <0 75 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		reg = <0x12200000 0x2000>;
-		clocks = <&clock CLK_MMC0>, <&clock CLK_SCLK_MMC0>;
-		clock-names = "biu", "ciu";
-		fifo-depth = <0x40>;
-		status = "disabled";
-	};
+		nocp_mem0_1: nocp@10CA1400 {
+			compatible = "samsung,exynos5420-nocp";
+			reg = <0x10CA1400 0x200>;
+			status = "disabled";
+		};
 
-	mmc_1: mmc@12210000 {
-		compatible = "samsung,exynos5420-dw-mshc-smu";
-		interrupts = <0 76 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		reg = <0x12210000 0x2000>;
-		clocks = <&clock CLK_MMC1>, <&clock CLK_SCLK_MMC1>;
-		clock-names = "biu", "ciu";
-		fifo-depth = <0x40>;
-		status = "disabled";
-	};
+		nocp_mem1_0: nocp@10CA1800 {
+			compatible = "samsung,exynos5420-nocp";
+			reg = <0x10CA1800 0x200>;
+			status = "disabled";
+		};
 
-	mmc_2: mmc@12220000 {
-		compatible = "samsung,exynos5420-dw-mshc";
-		interrupts = <0 77 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		reg = <0x12220000 0x1000>;
-		clocks = <&clock CLK_MMC2>, <&clock CLK_SCLK_MMC2>;
-		clock-names = "biu", "ciu";
-		fifo-depth = <0x40>;
-		status = "disabled";
-	};
+		nocp_mem1_1: nocp@10CA1C00 {
+			compatible = "samsung,exynos5420-nocp";
+			reg = <0x10CA1C00 0x200>;
+			status = "disabled";
+		};
 
-	mct: mct@101C0000 {
-		compatible = "samsung,exynos4210-mct";
-		reg = <0x101C0000 0x800>;
-		interrupt-controller;
-		#interrupt-cells = <1>;
-		interrupt-parent = <&mct_map>;
-		interrupts = <0>, <1>, <2>, <3>, <4>, <5>, <6>, <7>,
-				<8>, <9>, <10>, <11>;
-		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MCT>;
-		clock-names = "fin_pll", "mct";
-
-		mct_map: mct-map {
-			#interrupt-cells = <1>;
-			#address-cells = <0>;
-			#size-cells = <0>;
-			interrupt-map = <0 &combiner 23 3>,
-					<1 &combiner 23 4>,
-					<2 &combiner 25 2>,
-					<3 &combiner 25 3>,
-					<4 &gic 0 120 0>,
-					<5 &gic 0 121 0>,
-					<6 &gic 0 122 0>,
-					<7 &gic 0 123 0>,
-					<8 &gic 0 128 0>,
-					<9 &gic 0 129 0>,
-					<10 &gic 0 130 0>,
-					<11 &gic 0 131 0>;
+		nocp_g3d_0: nocp@11A51000 {
+			compatible = "samsung,exynos5420-nocp";
+			reg = <0x11A51000 0x200>;
+			status = "disabled";
 		};
-	};
 
-	nocp_mem0_0: nocp@10CA1000 {
-		compatible = "samsung,exynos5420-nocp";
-		reg = <0x10CA1000 0x200>;
-		status = "disabled";
-	};
+		nocp_g3d_1: nocp@11A51400 {
+			compatible = "samsung,exynos5420-nocp";
+			reg = <0x11A51400 0x200>;
+			status = "disabled";
+		};
 
-	nocp_mem0_1: nocp@10CA1400 {
-		compatible = "samsung,exynos5420-nocp";
-		reg = <0x10CA1400 0x200>;
-		status = "disabled";
-	};
+		gsc_pd: power-domain@10044000 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x10044000 0x20>;
+			#power-domain-cells = <0>;
+			clocks = <&clock CLK_FIN_PLL>,
+				 <&clock CLK_MOUT_USER_ACLK300_GSCL>,
+				 <&clock CLK_GSCL0>, <&clock CLK_GSCL1>;
+			clock-names = "oscclk", "clk0", "asb0", "asb1";
+		};
 
-	nocp_mem1_0: nocp@10CA1800 {
-		compatible = "samsung,exynos5420-nocp";
-		reg = <0x10CA1800 0x200>;
-		status = "disabled";
-	};
+		isp_pd: power-domain@10044020 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x10044020 0x20>;
+			#power-domain-cells = <0>;
+		};
 
-	nocp_mem1_1: nocp@10CA1C00 {
-		compatible = "samsung,exynos5420-nocp";
-		reg = <0x10CA1C00 0x200>;
-		status = "disabled";
-	};
+		mfc_pd: power-domain@10044060 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x10044060 0x20>;
+			clocks = <&clock CLK_FIN_PLL>,
+				 <&clock CLK_MOUT_USER_ACLK333>,
+				 <&clock CLK_ACLK333>;
+			clock-names = "oscclk", "clk0","asb0";
+			#power-domain-cells = <0>;
+		};
 
-	nocp_g3d_0: nocp@11A51000 {
-		compatible = "samsung,exynos5420-nocp";
-		reg = <0x11A51000 0x200>;
-		status = "disabled";
-	};
+		msc_pd: power-domain@10044120 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x10044120 0x20>;
+			#power-domain-cells = <0>;
+		};
 
-	nocp_g3d_1: nocp@11A51400 {
-		compatible = "samsung,exynos5420-nocp";
-		reg = <0x11A51400 0x200>;
-		status = "disabled";
-	};
+		disp_pd: power-domain@100440C0 {
+			compatible = "samsung,exynos4210-pd";
+			reg = <0x100440C0 0x20>;
+			#power-domain-cells = <0>;
+			clocks = <&clock CLK_FIN_PLL>,
+				 <&clock CLK_MOUT_USER_ACLK200_DISP1>,
+				 <&clock CLK_MOUT_USER_ACLK300_DISP1>,
+				 <&clock CLK_MOUT_USER_ACLK400_DISP1>,
+				 <&clock CLK_FIMD1>, <&clock CLK_MIXER>;
+			clock-names = "oscclk", "clk0", "clk1", "clk2", "asb0", "asb1";
+		};
 
-	gsc_pd: power-domain@10044000 {
-		compatible = "samsung,exynos4210-pd";
-		reg = <0x10044000 0x20>;
-		#power-domain-cells = <0>;
-		clocks = <&clock CLK_FIN_PLL>,
-			 <&clock CLK_MOUT_USER_ACLK300_GSCL>,
-			 <&clock CLK_GSCL0>, <&clock CLK_GSCL1>;
-		clock-names = "oscclk", "clk0", "asb0", "asb1";
-	};
+		pinctrl_0: pinctrl@13400000 {
+			compatible = "samsung,exynos5420-pinctrl";
+			reg = <0x13400000 0x1000>;
+			interrupts = <0 45 0>;
 
-	isp_pd: power-domain@10044020 {
-		compatible = "samsung,exynos4210-pd";
-		reg = <0x10044020 0x20>;
-		#power-domain-cells = <0>;
-	};
+			wakeup-interrupt-controller {
+				compatible = "samsung,exynos4210-wakeup-eint";
+				interrupt-parent = <&gic>;
+				interrupts = <0 32 0>;
+			};
+		};
 
-	mfc_pd: power-domain@10044060 {
-		compatible = "samsung,exynos4210-pd";
-		reg = <0x10044060 0x20>;
-		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MOUT_USER_ACLK333>;
-		clock-names = "oscclk", "clk0";
-		#power-domain-cells = <0>;
-	};
+		pinctrl_1: pinctrl@13410000 {
+			compatible = "samsung,exynos5420-pinctrl";
+			reg = <0x13410000 0x1000>;
+			interrupts = <0 78 0>;
+		};
 
-	msc_pd: power-domain@10044120 {
-		compatible = "samsung,exynos4210-pd";
-		reg = <0x10044120 0x20>;
-		#power-domain-cells = <0>;
-	};
+		pinctrl_2: pinctrl@14000000 {
+			compatible = "samsung,exynos5420-pinctrl";
+			reg = <0x14000000 0x1000>;
+			interrupts = <0 46 0>;
+		};
 
-	disp_pd: power-domain@100440C0 {
-		compatible = "samsung,exynos4210-pd";
-		reg = <0x100440C0 0x20>;
-		#power-domain-cells = <0>;
-		clocks = <&clock CLK_FIN_PLL>,
-			 <&clock CLK_MOUT_USER_ACLK200_DISP1>,
-			 <&clock CLK_MOUT_USER_ACLK300_DISP1>,
-			 <&clock CLK_MOUT_USER_ACLK400_DISP1>,
-			 <&clock CLK_FIMD1>, <&clock CLK_MIXER>;
-		clock-names = "oscclk", "clk0", "clk1", "clk2", "asb0", "asb1";
-	};
+		pinctrl_3: pinctrl@14010000 {
+			compatible = "samsung,exynos5420-pinctrl";
+			reg = <0x14010000 0x1000>;
+			interrupts = <0 50 0>;
+		};
 
-	pinctrl_0: pinctrl@13400000 {
-		compatible = "samsung,exynos5420-pinctrl";
-		reg = <0x13400000 0x1000>;
-		interrupts = <0 45 0>;
+		pinctrl_4: pinctrl@03860000 {
+			compatible = "samsung,exynos5420-pinctrl";
+			reg = <0x03860000 0x1000>;
+			interrupts = <0 47 0>;
+		};
 
-		wakeup-interrupt-controller {
-			compatible = "samsung,exynos4210-wakeup-eint";
+		amba {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "simple-bus";
 			interrupt-parent = <&gic>;
-			interrupts = <0 32 0>;
+			ranges;
+
+			adma: adma@03880000 {
+				compatible = "arm,pl330", "arm,primecell";
+				reg = <0x03880000 0x1000>;
+				interrupts = <0 110 0>;
+				clocks = <&clock_audss EXYNOS_ADMA>;
+				clock-names = "apb_pclk";
+				#dma-cells = <1>;
+				#dma-channels = <6>;
+				#dma-requests = <16>;
+			};
+
+			pdma0: pdma@121A0000 {
+				compatible = "arm,pl330", "arm,primecell";
+				reg = <0x121A0000 0x1000>;
+				interrupts = <0 34 0>;
+				clocks = <&clock CLK_PDMA0>;
+				clock-names = "apb_pclk";
+				#dma-cells = <1>;
+				#dma-channels = <8>;
+				#dma-requests = <32>;
+			};
+
+			pdma1: pdma@121B0000 {
+				compatible = "arm,pl330", "arm,primecell";
+				reg = <0x121B0000 0x1000>;
+				interrupts = <0 35 0>;
+				clocks = <&clock CLK_PDMA1>;
+				clock-names = "apb_pclk";
+				#dma-cells = <1>;
+				#dma-channels = <8>;
+				#dma-requests = <32>;
+			};
+
+			mdma0: mdma@10800000 {
+				compatible = "arm,pl330", "arm,primecell";
+				reg = <0x10800000 0x1000>;
+				interrupts = <0 33 0>;
+				clocks = <&clock CLK_MDMA0>;
+				clock-names = "apb_pclk";
+				#dma-cells = <1>;
+				#dma-channels = <8>;
+				#dma-requests = <1>;
+			};
+
+			mdma1: mdma@11C10000 {
+				compatible = "arm,pl330", "arm,primecell";
+				reg = <0x11C10000 0x1000>;
+				interrupts = <0 124 0>;
+				clocks = <&clock CLK_MDMA1>;
+				clock-names = "apb_pclk";
+				#dma-cells = <1>;
+				#dma-channels = <8>;
+				#dma-requests = <1>;
+				/*
+				 * MDMA1 can support both secure and non-secure
+				 * AXI transactions. When this is enabled in
+				 * the kernel for boards that run in secure
+				 * mode, we are getting imprecise external
+				 * aborts causing the kernel to oops.
+				 */
+				status = "disabled";
+			};
+		};
+
+		i2s0: i2s@03830000 {
+			compatible = "samsung,exynos5420-i2s";
+			reg = <0x03830000 0x100>;
+			dmas = <&adma 0
+				&adma 2
+				&adma 1>;
+			dma-names = "tx", "rx", "tx-sec";
+			clocks = <&clock_audss EXYNOS_I2S_BUS>,
+				<&clock_audss EXYNOS_I2S_BUS>,
+				<&clock_audss EXYNOS_SCLK_I2S>;
+			clock-names = "iis", "i2s_opclk0", "i2s_opclk1";
+			#clock-cells = <1>;
+			clock-output-names = "i2s_cdclk0";
+			#sound-dai-cells = <1>;
+			samsung,idma-addr = <0x03000000>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2s0_bus>;
+			status = "disabled";
 		};
-	};
-
-	pinctrl_1: pinctrl@13410000 {
-		compatible = "samsung,exynos5420-pinctrl";
-		reg = <0x13410000 0x1000>;
-		interrupts = <0 78 0>;
-	};
 
-	pinctrl_2: pinctrl@14000000 {
-		compatible = "samsung,exynos5420-pinctrl";
-		reg = <0x14000000 0x1000>;
-		interrupts = <0 46 0>;
-	};
-
-	pinctrl_3: pinctrl@14010000 {
-		compatible = "samsung,exynos5420-pinctrl";
-		reg = <0x14010000 0x1000>;
-		interrupts = <0 50 0>;
-	};
-
-	pinctrl_4: pinctrl@03860000 {
-		compatible = "samsung,exynos5420-pinctrl";
-		reg = <0x03860000 0x1000>;
-		interrupts = <0 47 0>;
-	};
-
-	amba {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		compatible = "simple-bus";
-		interrupt-parent = <&gic>;
-		ranges;
-
-		adma: adma@03880000 {
-			compatible = "arm,pl330", "arm,primecell";
-			reg = <0x03880000 0x1000>;
-			interrupts = <0 110 0>;
-			clocks = <&clock_audss EXYNOS_ADMA>;
-			clock-names = "apb_pclk";
-			#dma-cells = <1>;
-			#dma-channels = <6>;
-			#dma-requests = <16>;
-		};
-
-		pdma0: pdma@121A0000 {
-			compatible = "arm,pl330", "arm,primecell";
-			reg = <0x121A0000 0x1000>;
-			interrupts = <0 34 0>;
-			clocks = <&clock CLK_PDMA0>;
-			clock-names = "apb_pclk";
-			#dma-cells = <1>;
-			#dma-channels = <8>;
-			#dma-requests = <32>;
-		};
-
-		pdma1: pdma@121B0000 {
-			compatible = "arm,pl330", "arm,primecell";
-			reg = <0x121B0000 0x1000>;
-			interrupts = <0 35 0>;
-			clocks = <&clock CLK_PDMA1>;
-			clock-names = "apb_pclk";
-			#dma-cells = <1>;
-			#dma-channels = <8>;
-			#dma-requests = <32>;
-		};
-
-		mdma0: mdma@10800000 {
-			compatible = "arm,pl330", "arm,primecell";
-			reg = <0x10800000 0x1000>;
-			interrupts = <0 33 0>;
-			clocks = <&clock CLK_MDMA0>;
-			clock-names = "apb_pclk";
-			#dma-cells = <1>;
-			#dma-channels = <8>;
-			#dma-requests = <1>;
-		};
-
-		mdma1: mdma@11C10000 {
-			compatible = "arm,pl330", "arm,primecell";
-			reg = <0x11C10000 0x1000>;
-			interrupts = <0 124 0>;
-			clocks = <&clock CLK_MDMA1>;
-			clock-names = "apb_pclk";
-			#dma-cells = <1>;
-			#dma-channels = <8>;
-			#dma-requests = <1>;
-			/*
-			 * MDMA1 can support both secure and non-secure
-			 * AXI transactions. When this is enabled in the kernel
-			 * for boards that run in secure mode, we are getting
-			 * imprecise external aborts causing the kernel to oops.
-			 */
+		i2s1: i2s@12D60000 {
+			compatible = "samsung,exynos5420-i2s";
+			reg = <0x12D60000 0x100>;
+			dmas = <&pdma1 12
+				&pdma1 11>;
+			dma-names = "tx", "rx";
+			clocks = <&clock CLK_I2S1>, <&clock CLK_SCLK_I2S1>;
+			clock-names = "iis", "i2s_opclk0";
+			#clock-cells = <1>;
+			clock-output-names = "i2s_cdclk1";
+			#sound-dai-cells = <1>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2s1_bus>;
 			status = "disabled";
 		};
-	};
-
-	i2s0: i2s@03830000 {
-		compatible = "samsung,exynos5420-i2s";
-		reg = <0x03830000 0x100>;
-		dmas = <&adma 0
-			&adma 2
-			&adma 1>;
-		dma-names = "tx", "rx", "tx-sec";
-		clocks = <&clock_audss EXYNOS_I2S_BUS>,
-			<&clock_audss EXYNOS_I2S_BUS>,
-			<&clock_audss EXYNOS_SCLK_I2S>;
-		clock-names = "iis", "i2s_opclk0", "i2s_opclk1";
-		#clock-cells = <1>;
-		clock-output-names = "i2s_cdclk0";
-		#sound-dai-cells = <1>;
-		samsung,idma-addr = <0x03000000>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2s0_bus>;
-		status = "disabled";
-	};
-
-	i2s1: i2s@12D60000 {
-		compatible = "samsung,exynos5420-i2s";
-		reg = <0x12D60000 0x100>;
-		dmas = <&pdma1 12
-			&pdma1 11>;
-		dma-names = "tx", "rx";
-		clocks = <&clock CLK_I2S1>, <&clock CLK_SCLK_I2S1>;
-		clock-names = "iis", "i2s_opclk0";
-		#clock-cells = <1>;
-		clock-output-names = "i2s_cdclk1";
-		#sound-dai-cells = <1>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2s1_bus>;
-		status = "disabled";
-	};
-
-	i2s2: i2s@12D70000 {
-		compatible = "samsung,exynos5420-i2s";
-		reg = <0x12D70000 0x100>;
-		dmas = <&pdma0 12
-			&pdma0 11>;
-		dma-names = "tx", "rx";
-		clocks = <&clock CLK_I2S2>, <&clock CLK_SCLK_I2S2>;
-		clock-names = "iis", "i2s_opclk0";
-		#clock-cells = <1>;
-		clock-output-names = "i2s_cdclk2";
-		#sound-dai-cells = <1>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2s2_bus>;
-		status = "disabled";
-	};
-
-	spi_0: spi@12d20000 {
-		compatible = "samsung,exynos4210-spi";
-		reg = <0x12d20000 0x100>;
-		interrupts = <0 68 0>;
-		dmas = <&pdma0 5
-			&pdma0 4>;
-		dma-names = "tx", "rx";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&spi0_bus>;
-		clocks = <&clock CLK_SPI0>, <&clock CLK_SCLK_SPI0>;
-		clock-names = "spi", "spi_busclk0";
-		status = "disabled";
-	};
-
-	spi_1: spi@12d30000 {
-		compatible = "samsung,exynos4210-spi";
-		reg = <0x12d30000 0x100>;
-		interrupts = <0 69 0>;
-		dmas = <&pdma1 5
-			&pdma1 4>;
-		dma-names = "tx", "rx";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&spi1_bus>;
-		clocks = <&clock CLK_SPI1>, <&clock CLK_SCLK_SPI1>;
-		clock-names = "spi", "spi_busclk0";
-		status = "disabled";
-	};
-
-	spi_2: spi@12d40000 {
-		compatible = "samsung,exynos4210-spi";
-		reg = <0x12d40000 0x100>;
-		interrupts = <0 70 0>;
-		dmas = <&pdma0 7
-			&pdma0 6>;
-		dma-names = "tx", "rx";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&spi2_bus>;
-		clocks = <&clock CLK_SPI2>, <&clock CLK_SCLK_SPI2>;
-		clock-names = "spi", "spi_busclk0";
-		status = "disabled";
-	};
-
-	pwm: pwm@12dd0000 {
-		compatible = "samsung,exynos4210-pwm";
-		reg = <0x12dd0000 0x100>;
-		samsung,pwm-outputs = <0>, <1>, <2>, <3>;
-		#pwm-cells = <3>;
-		clocks = <&clock CLK_PWM>;
-		clock-names = "timers";
-	};
-
-	dp_phy: dp-video-phy {
-		compatible = "samsung,exynos5420-dp-video-phy";
-		samsung,pmu-syscon = <&pmu_system_controller>;
-		#phy-cells = <0>;
-	};
-
-	mipi_phy: mipi-video-phy {
-		compatible = "samsung,s5pv210-mipi-video-phy";
-		syscon = <&pmu_system_controller>;
-		#phy-cells = <1>;
-	};
-
-	dsi@14500000 {
-		compatible = "samsung,exynos5410-mipi-dsi";
-		reg = <0x14500000 0x10000>;
-		interrupts = <0 82 0>;
-		phys = <&mipi_phy 1>;
-		phy-names = "dsim";
-		clocks = <&clock CLK_DSIM1>, <&clock CLK_SCLK_MIPI1>;
-		clock-names = "bus_clk", "pll_clk";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		status = "disabled";
-	};
-
-	adc: adc@12D10000 {
-		compatible = "samsung,exynos-adc-v2";
-		reg = <0x12D10000 0x100>;
-		interrupts = <0 106 0>;
-		clocks = <&clock CLK_TSADC>;
-		clock-names = "adc";
-		#io-channel-cells = <1>;
-		io-channel-ranges;
-		samsung,syscon-phandle = <&pmu_system_controller>;
-		status = "disabled";
-	};
-
-	i2c_0: i2c@12C60000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12C60000 0x100>;
-		interrupts = <0 56 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C0>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c0_bus>;
-		samsung,sysreg-phandle = <&sysreg_system_controller>;
-		status = "disabled";
-	};
-
-	i2c_1: i2c@12C70000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12C70000 0x100>;
-		interrupts = <0 57 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C1>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c1_bus>;
-		samsung,sysreg-phandle = <&sysreg_system_controller>;
-		status = "disabled";
-	};
-
-	i2c_2: i2c@12C80000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12C80000 0x100>;
-		interrupts = <0 58 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C2>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c2_bus>;
-		samsung,sysreg-phandle = <&sysreg_system_controller>;
-		status = "disabled";
-	};
-
-	i2c_3: i2c@12C90000 {
-		compatible = "samsung,s3c2440-i2c";
-		reg = <0x12C90000 0x100>;
-		interrupts = <0 59 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&clock CLK_I2C3>;
-		clock-names = "i2c";
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c3_bus>;
-		samsung,sysreg-phandle = <&sysreg_system_controller>;
-		status = "disabled";
-	};
 
-	hsi2c_4: i2c@12CA0000 {
-		compatible = "samsung,exynos5-hsi2c";
-		reg = <0x12CA0000 0x1000>;
-		interrupts = <0 60 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c4_hs_bus>;
-		clocks = <&clock CLK_USI0>;
-		clock-names = "hsi2c";
-		status = "disabled";
-	};
-
-	hsi2c_5: i2c@12CB0000 {
-		compatible = "samsung,exynos5-hsi2c";
-		reg = <0x12CB0000 0x1000>;
-		interrupts = <0 61 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c5_hs_bus>;
-		clocks = <&clock CLK_USI1>;
-		clock-names = "hsi2c";
-		status = "disabled";
-	};
-
-	hsi2c_6: i2c@12CC0000 {
-		compatible = "samsung,exynos5-hsi2c";
-		reg = <0x12CC0000 0x1000>;
-		interrupts = <0 62 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c6_hs_bus>;
-		clocks = <&clock CLK_USI2>;
-		clock-names = "hsi2c";
-		status = "disabled";
-	};
-
-	hsi2c_7: i2c@12CD0000 {
-		compatible = "samsung,exynos5-hsi2c";
-		reg = <0x12CD0000 0x1000>;
-		interrupts = <0 63 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c7_hs_bus>;
-		clocks = <&clock CLK_USI3>;
-		clock-names = "hsi2c";
-		status = "disabled";
-	};
-
-	hsi2c_8: i2c@12E00000 {
-		compatible = "samsung,exynos5-hsi2c";
-		reg = <0x12E00000 0x1000>;
-		interrupts = <0 87 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c8_hs_bus>;
-		clocks = <&clock CLK_USI4>;
-		clock-names = "hsi2c";
-		status = "disabled";
-	};
-
-	hsi2c_9: i2c@12E10000 {
-		compatible = "samsung,exynos5-hsi2c";
-		reg = <0x12E10000 0x1000>;
-		interrupts = <0 88 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c9_hs_bus>;
-		clocks = <&clock CLK_USI5>;
-		clock-names = "hsi2c";
-		status = "disabled";
-	};
-
-	hsi2c_10: i2c@12E20000 {
-		compatible = "samsung,exynos5-hsi2c";
-		reg = <0x12E20000 0x1000>;
-		interrupts = <0 203 0>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c10_hs_bus>;
-		clocks = <&clock CLK_USI6>;
-		clock-names = "hsi2c";
-		status = "disabled";
-	};
-
-	hdmi: hdmi@14530000 {
-		compatible = "samsung,exynos5420-hdmi";
-		reg = <0x14530000 0x70000>;
-		interrupts = <0 95 0>;
-		clocks = <&clock CLK_HDMI>, <&clock CLK_SCLK_HDMI>,
-			 <&clock CLK_DOUT_PIXEL>, <&clock CLK_SCLK_HDMIPHY>,
-			 <&clock CLK_MOUT_HDMI>;
-		clock-names = "hdmi", "sclk_hdmi", "sclk_pixel",
-			"sclk_hdmiphy", "mout_hdmi";
-		phy = <&hdmiphy>;
-		samsung,syscon-phandle = <&pmu_system_controller>;
-		status = "disabled";
-		power-domains = <&disp_pd>;
-	};
-
-	hdmiphy: hdmiphy@145D0000 {
-		reg = <0x145D0000 0x20>;
-	};
-
-	mixer: mixer@14450000 {
-		compatible = "samsung,exynos5420-mixer";
-		reg = <0x14450000 0x10000>;
-		interrupts = <0 94 0>;
-		clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>,
-			 <&clock CLK_SCLK_HDMI>;
-		clock-names = "mixer", "hdmi", "sclk_hdmi";
-		power-domains = <&disp_pd>;
-		iommus = <&sysmmu_tv>;
-	};
-
-	rotator: rotator@11C00000 {
-		compatible = "samsung,exynos5250-rotator";
-		reg = <0x11C00000 0x64>;
-		interrupts = <0 84 0>;
-		clocks = <&clock CLK_ROTATOR>;
-		clock-names = "rotator";
-		iommus = <&sysmmu_rotator>;
-	};
-
-	gsc_0: video-scaler@13e00000 {
-		compatible = "samsung,exynos5-gsc";
-		reg = <0x13e00000 0x1000>;
-		interrupts = <0 85 0>;
-		clocks = <&clock CLK_GSCL0>;
-		clock-names = "gscl";
-		power-domains = <&gsc_pd>;
-		iommus = <&sysmmu_gscl0>;
-	};
-
-	gsc_1: video-scaler@13e10000 {
-		compatible = "samsung,exynos5-gsc";
-		reg = <0x13e10000 0x1000>;
-		interrupts = <0 86 0>;
-		clocks = <&clock CLK_GSCL1>;
-		clock-names = "gscl";
-		power-domains = <&gsc_pd>;
-		iommus = <&sysmmu_gscl1>;
-	};
-
-	jpeg_0: jpeg@11F50000 {
-		compatible = "samsung,exynos5420-jpeg";
-		reg = <0x11F50000 0x1000>;
-		interrupts = <0 89 0>;
-		clock-names = "jpeg";
-		clocks = <&clock CLK_JPEG>;
-		iommus = <&sysmmu_jpeg0>;
-	};
-
-	jpeg_1: jpeg@11F60000 {
-		compatible = "samsung,exynos5420-jpeg";
-		reg = <0x11F60000 0x1000>;
-		interrupts = <0 168 0>;
-		clock-names = "jpeg";
-		clocks = <&clock CLK_JPEG2>;
-		iommus = <&sysmmu_jpeg1>;
-	};
-
-	pmu_system_controller: system-controller@10040000 {
-		compatible = "samsung,exynos5420-pmu", "syscon";
-		reg = <0x10040000 0x5000>;
-		clock-names = "clkout16";
-		clocks = <&clock CLK_FIN_PLL>;
-		#clock-cells = <1>;
-		interrupt-controller;
-		#interrupt-cells = <3>;
-		interrupt-parent = <&gic>;
-	};
-
-	sysreg_system_controller: syscon@10050000 {
-		compatible = "samsung,exynos5-sysreg", "syscon";
-		reg = <0x10050000 0x5000>;
-	};
-
-	tmu_cpu0: tmu@10060000 {
-		compatible = "samsung,exynos5420-tmu";
-		reg = <0x10060000 0x100>;
-		interrupts = <0 65 0>;
-		clocks = <&clock CLK_TMU>;
-		clock-names = "tmu_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
-	};
-
-	tmu_cpu1: tmu@10064000 {
-		compatible = "samsung,exynos5420-tmu";
-		reg = <0x10064000 0x100>;
-		interrupts = <0 183 0>;
-		clocks = <&clock CLK_TMU>;
-		clock-names = "tmu_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
-	};
-
-	tmu_cpu2: tmu@10068000 {
-		compatible = "samsung,exynos5420-tmu-ext-triminfo";
-		reg = <0x10068000 0x100>, <0x1006c000 0x4>;
-		interrupts = <0 184 0>;
-		clocks = <&clock CLK_TMU>, <&clock CLK_TMU>;
-		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
-	};
-
-	tmu_cpu3: tmu@1006c000 {
-		compatible = "samsung,exynos5420-tmu-ext-triminfo";
-		reg = <0x1006c000 0x100>, <0x100a0000 0x4>;
-		interrupts = <0 185 0>;
-		clocks = <&clock CLK_TMU>, <&clock CLK_TMU_GPU>;
-		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
-	};
-
-	tmu_gpu: tmu@100a0000 {
-		compatible = "samsung,exynos5420-tmu-ext-triminfo";
-		reg = <0x100a0000 0x100>, <0x10068000 0x4>;
-		interrupts = <0 215 0>;
-		clocks = <&clock CLK_TMU_GPU>, <&clock CLK_TMU>;
-		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
-		#include "exynos4412-tmu-sensor-conf.dtsi"
-	};
-
-	thermal-zones {
-		cpu0_thermal: cpu0-thermal {
-			thermal-sensors = <&tmu_cpu0>;
-			#include "exynos5420-trip-points.dtsi"
-		};
-		cpu1_thermal: cpu1-thermal {
-		       thermal-sensors = <&tmu_cpu1>;
-		       #include "exynos5420-trip-points.dtsi"
-		};
-		cpu2_thermal: cpu2-thermal {
-		       thermal-sensors = <&tmu_cpu2>;
-		       #include "exynos5420-trip-points.dtsi"
-		};
-		cpu3_thermal: cpu3-thermal {
-		       thermal-sensors = <&tmu_cpu3>;
-		       #include "exynos5420-trip-points.dtsi"
-		};
-		gpu_thermal: gpu-thermal {
-		       thermal-sensors = <&tmu_gpu>;
-		       #include "exynos5420-trip-points.dtsi"
+		i2s2: i2s@12D70000 {
+			compatible = "samsung,exynos5420-i2s";
+			reg = <0x12D70000 0x100>;
+			dmas = <&pdma0 12
+				&pdma0 11>;
+			dma-names = "tx", "rx";
+			clocks = <&clock CLK_I2S2>, <&clock CLK_SCLK_I2S2>;
+			clock-names = "iis", "i2s_opclk0";
+			#clock-cells = <1>;
+			clock-output-names = "i2s_cdclk2";
+			#sound-dai-cells = <1>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2s2_bus>;
+			status = "disabled";
 		};
-	};
 
-        watchdog: watchdog@101D0000 {
-		compatible = "samsung,exynos5420-wdt";
-		reg = <0x101D0000 0x100>;
-		interrupts = <0 42 0>;
-		clocks = <&clock CLK_WDT>;
-		clock-names = "watchdog";
-		samsung,syscon-phandle = <&pmu_system_controller>;
-        };
-
-	sss: sss@10830000 {
-		compatible = "samsung,exynos4210-secss";
-		reg = <0x10830000 0x300>;
-		interrupts = <0 112 0>;
-		clocks = <&clock CLK_SSS>;
-		clock-names = "secss";
-	};
-
-	usbdrd3_0: usb3-0 {
-		compatible = "samsung,exynos5250-dwusb3";
-		clocks = <&clock CLK_USBD300>;
-		clock-names = "usbdrd30";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		usbdrd_dwc3_0: dwc3@12000000 {
-			compatible = "snps,dwc3";
-			reg = <0x12000000 0x10000>;
-			interrupts = <0 72 0>;
-			phys = <&usbdrd_phy0 0>, <&usbdrd_phy0 1>;
-			phy-names = "usb2-phy", "usb3-phy";
+		spi_0: spi@12d20000 {
+			compatible = "samsung,exynos4210-spi";
+			reg = <0x12d20000 0x100>;
+			interrupts = <0 68 0>;
+			dmas = <&pdma0 5
+				&pdma0 4>;
+			dma-names = "tx", "rx";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&spi0_bus>;
+			clocks = <&clock CLK_SPI0>, <&clock CLK_SCLK_SPI0>;
+			clock-names = "spi", "spi_busclk0";
+			status = "disabled";
 		};
-	};
-
-	usbdrd_phy0: phy@12100000 {
-		compatible = "samsung,exynos5420-usbdrd-phy";
-		reg = <0x12100000 0x100>;
-		clocks = <&clock CLK_USBD300>, <&clock CLK_SCLK_USBPHY300>;
-		clock-names = "phy", "ref";
-		samsung,pmu-syscon = <&pmu_system_controller>;
-		#phy-cells = <1>;
-	};
 
-	usbdrd3_1: usb3-1 {
-		compatible = "samsung,exynos5250-dwusb3";
-		clocks = <&clock CLK_USBD301>;
-		clock-names = "usbdrd30";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		usbdrd_dwc3_1: dwc3@12400000 {
-			compatible = "snps,dwc3";
-			reg = <0x12400000 0x10000>;
-			interrupts = <0 73 0>;
-			phys = <&usbdrd_phy1 0>, <&usbdrd_phy1 1>;
-			phy-names = "usb2-phy", "usb3-phy";
+		spi_1: spi@12d30000 {
+			compatible = "samsung,exynos4210-spi";
+			reg = <0x12d30000 0x100>;
+			interrupts = <0 69 0>;
+			dmas = <&pdma1 5
+				&pdma1 4>;
+			dma-names = "tx", "rx";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&spi1_bus>;
+			clocks = <&clock CLK_SPI1>, <&clock CLK_SCLK_SPI1>;
+			clock-names = "spi", "spi_busclk0";
+			status = "disabled";
 		};
-	};
-
-	usbdrd_phy1: phy@12500000 {
-		compatible = "samsung,exynos5420-usbdrd-phy";
-		reg = <0x12500000 0x100>;
-		clocks = <&clock CLK_USBD301>, <&clock CLK_SCLK_USBPHY301>;
-		clock-names = "phy", "ref";
-		samsung,pmu-syscon = <&pmu_system_controller>;
-		#phy-cells = <1>;
-	};
-
-	usbhost2: usb@12110000 {
-		compatible = "samsung,exynos4210-ehci";
-		reg = <0x12110000 0x100>;
-		interrupts = <0 71 0>;
 
-		clocks = <&clock CLK_USBH20>;
-		clock-names = "usbhost";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		port@0 {
-			reg = <0>;
-			phys = <&usb2_phy 1>;
+		spi_2: spi@12d40000 {
+			compatible = "samsung,exynos4210-spi";
+			reg = <0x12d40000 0x100>;
+			interrupts = <0 70 0>;
+			dmas = <&pdma0 7
+				&pdma0 6>;
+			dma-names = "tx", "rx";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&spi2_bus>;
+			clocks = <&clock CLK_SPI2>, <&clock CLK_SCLK_SPI2>;
+			clock-names = "spi", "spi_busclk0";
+			status = "disabled";
 		};
-	};
 
-	usbhost1: usb@12120000 {
-		compatible = "samsung,exynos4210-ohci";
-		reg = <0x12120000 0x100>;
-		interrupts = <0 71 0>;
-
-		clocks = <&clock CLK_USBH20>;
-		clock-names = "usbhost";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		port@0 {
-			reg = <0>;
-			phys = <&usb2_phy 1>;
+		dp_phy: dp-video-phy {
+			compatible = "samsung,exynos5420-dp-video-phy";
+			samsung,pmu-syscon = <&pmu_system_controller>;
+			#phy-cells = <0>;
 		};
-	};
-
-	usb2_phy: phy@12130000 {
-		compatible = "samsung,exynos5250-usb2-phy";
-		reg = <0x12130000 0x100>;
-		clocks = <&clock CLK_USBH20>, <&clock CLK_SCLK_USBPHY300>;
-		clock-names = "phy", "ref";
-		#phy-cells = <1>;
-		samsung,sysreg-phandle = <&sysreg_system_controller>;
-		samsung,pmureg-phandle = <&pmu_system_controller>;
-	};
-
-	sysmmu_g2dr: sysmmu@0x10A60000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x10A60000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <24 5>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_G2D>, <&clock CLK_G2D>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_g2dw: sysmmu@0x10A70000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x10A70000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <22 2>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_G2D>, <&clock CLK_G2D>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_tv: sysmmu@0x14650000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x14650000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <7 4>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MIXER>, <&clock CLK_MIXER>;
-		power-domains = <&disp_pd>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_gscl0: sysmmu@0x13E80000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13E80000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <2 0>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_GSCL0>, <&clock CLK_GSCL0>;
-		power-domains = <&gsc_pd>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_gscl1: sysmmu@0x13E90000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x13E90000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <2 2>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_GSCL1>, <&clock CLK_GSCL1>;
-		power-domains = <&gsc_pd>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_scaler0r: sysmmu@0x12880000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x12880000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <22 4>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MSCL0>, <&clock CLK_MSCL0>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_scaler1r: sysmmu@0x12890000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x12890000 0x1000>;
-		interrupts = <0 186 0>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MSCL1>, <&clock CLK_MSCL1>;
-		#iommu-cells = <0>;
-	};
 
-	sysmmu_scaler2r: sysmmu@0x128A0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x128A0000 0x1000>;
-		interrupts = <0 188 0>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MSCL2>, <&clock CLK_MSCL2>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_scaler0w: sysmmu@0x128C0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x128C0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <27 2>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MSCL0>, <&clock CLK_MSCL0>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_scaler1w: sysmmu@0x128D0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x128D0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <22 6>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MSCL1>, <&clock CLK_MSCL1>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_scaler2w: sysmmu@0x128E0000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x128E0000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <19 6>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MSCL2>, <&clock CLK_MSCL2>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_rotator: sysmmu@0x11D40000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x11D40000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <4 0>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_ROTATOR>, <&clock CLK_ROTATOR>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_jpeg0: sysmmu@0x11F10000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x11F10000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <4 2>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_JPEG>, <&clock CLK_JPEG>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_jpeg1: sysmmu@0x11F20000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x11F20000 0x1000>;
-		interrupts = <0 169 0>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_JPEG2>, <&clock CLK_JPEG2>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_mfc_l: sysmmu@0x11200000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x11200000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <6 2>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MFCL>, <&clock CLK_MFC>;
-		power-domains = <&mfc_pd>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_mfc_r: sysmmu@0x11210000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x11210000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <8 5>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_MFCR>, <&clock CLK_MFC>;
-		power-domains = <&mfc_pd>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_fimd1_0: sysmmu@0x14640000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x14640000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <3 2>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_FIMD1M0>, <&clock CLK_FIMD1>;
-		power-domains = <&disp_pd>;
-		#iommu-cells = <0>;
-	};
-
-	sysmmu_fimd1_1: sysmmu@0x14680000 {
-		compatible = "samsung,exynos-sysmmu";
-		reg = <0x14680000 0x1000>;
-		interrupt-parent = <&combiner>;
-		interrupts = <3 0>;
-		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_FIMD1M1>, <&clock CLK_FIMD1>;
-		power-domains = <&disp_pd>;
-		#iommu-cells = <0>;
-	};
-
-	bus_wcore: bus_wcore {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK400_WCORE>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_wcore_opp_table>;
-		status = "disabled";
-	};
-
-	bus_noc: bus_noc {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK100_NOC>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_noc_opp_table>;
-		status = "disabled";
-	};
-
-	bus_fsys_apb: bus_fsys_apb {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_PCLK200_FSYS>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_fsys_apb_opp_table>;
-		status = "disabled";
-	};
-
-	bus_fsys: bus_fsys {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK200_FSYS>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_fsys_apb_opp_table>;
-		status = "disabled";
-	};
-
-	bus_fsys2: bus_fsys2 {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK200_FSYS2>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_fsys2_opp_table>;
-		status = "disabled";
-	};
-
-	bus_mfc: bus_mfc {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK333>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_mfc_opp_table>;
-		status = "disabled";
-	};
-
-	bus_gen: bus_gen {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK266>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_gen_opp_table>;
-		status = "disabled";
-	};
-
-	bus_peri: bus_peri {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK66>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_peri_opp_table>;
-		status = "disabled";
-	};
-
-	bus_g2d: bus_g2d {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK333_G2D>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_g2d_opp_table>;
-		status = "disabled";
-	};
-
-	bus_g2d_acp: bus_g2d_acp {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK266_G2D>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_g2d_acp_opp_table>;
-		status = "disabled";
-	};
-
-	bus_jpeg: bus_jpeg {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK300_JPEG>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_jpeg_opp_table>;
-		status = "disabled";
-	};
-
-	bus_jpeg_apb: bus_jpeg_apb {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK166>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_jpeg_apb_opp_table>;
-		status = "disabled";
-	};
-
-	bus_disp1_fimd: bus_disp1_fimd {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK300_DISP1>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_disp1_fimd_opp_table>;
-		status = "disabled";
-	};
-
-	bus_disp1: bus_disp1 {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK400_DISP1>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_disp1_opp_table>;
-		status = "disabled";
-	};
-
-	bus_gscl_scaler: bus_gscl_scaler {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK300_GSCL>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_gscl_opp_table>;
-		status = "disabled";
-	};
-
-	bus_mscl: bus_mscl {
-		compatible = "samsung,exynos-bus";
-		clocks = <&clock CLK_DOUT_ACLK400_MSCL>;
-		clock-names = "bus";
-		operating-points-v2 = <&bus_mscl_opp_table>;
-		status = "disabled";
-	};
-
-	bus_wcore_opp_table: opp_table2 {
-		compatible = "operating-points-v2";
-
-		opp00 {
-			opp-hz = /bits/ 64 <84000000>;
-			opp-microvolt = <925000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <111000000>;
-			opp-microvolt = <950000>;
-		};
-		opp02 {
-			opp-hz = /bits/ 64 <222000000>;
-			opp-microvolt = <950000>;
+		mipi_phy: mipi-video-phy {
+			compatible = "samsung,s5pv210-mipi-video-phy";
+			syscon = <&pmu_system_controller>;
+			#phy-cells = <1>;
 		};
-		opp03 {
-			opp-hz = /bits/ 64 <333000000>;
-			opp-microvolt = <950000>;
-		};
-		opp04 {
-			opp-hz = /bits/ 64 <400000000>;
-			opp-microvolt = <987500>;
-		};
-	};
 
-	bus_noc_opp_table: opp_table3 {
-		compatible = "operating-points-v2";
-
-		opp00 {
-			opp-hz = /bits/ 64 <67000000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <75000000>;
-		};
-		opp02 {
-			opp-hz = /bits/ 64 <86000000>;
-		};
-		opp03 {
-			opp-hz = /bits/ 64 <100000000>;
+		dsi@14500000 {
+			compatible = "samsung,exynos5410-mipi-dsi";
+			reg = <0x14500000 0x10000>;
+			interrupts = <0 82 0>;
+			phys = <&mipi_phy 1>;
+			phy-names = "dsim";
+			clocks = <&clock CLK_DSIM1>, <&clock CLK_SCLK_MIPI1>;
+			clock-names = "bus_clk", "pll_clk";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
 		};
-	};
-
-	bus_fsys_apb_opp_table: opp_table4 {
-		compatible = "operating-points-v2";
-		opp-shared;
 
-		opp00 {
-			opp-hz = /bits/ 64 <100000000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <200000000>;
+		adc: adc@12D10000 {
+			compatible = "samsung,exynos-adc-v2";
+			reg = <0x12D10000 0x100>;
+			interrupts = <0 106 0>;
+			clocks = <&clock CLK_TSADC>;
+			clock-names = "adc";
+			#io-channel-cells = <1>;
+			io-channel-ranges;
+			samsung,syscon-phandle = <&pmu_system_controller>;
+			status = "disabled";
 		};
-	};
-
-	bus_fsys2_opp_table: opp_table5 {
-		compatible = "operating-points-v2";
 
-		opp00 {
-			opp-hz = /bits/ 64 <75000000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <100000000>;
-		};
-		opp02 {
-			opp-hz = /bits/ 64 <150000000>;
+		hsi2c_8: i2c@12E00000 {
+			compatible = "samsung,exynos5250-hsi2c";
+			reg = <0x12E00000 0x1000>;
+			interrupts = <0 87 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c8_hs_bus>;
+			clocks = <&clock CLK_USI4>;
+			clock-names = "hsi2c";
+			status = "disabled";
 		};
-	};
 
-	bus_mfc_opp_table: opp_table6 {
-		compatible = "operating-points-v2";
-
-		opp00 {
-			opp-hz = /bits/ 64 <96000000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <111000000>;
-		};
-		opp02 {
-			opp-hz = /bits/ 64 <167000000>;
-		};
-		opp03 {
-			opp-hz = /bits/ 64 <222000000>;
-		};
-		opp04 {
-			opp-hz = /bits/ 64 <333000000>;
+		hsi2c_9: i2c@12E10000 {
+			compatible = "samsung,exynos5250-hsi2c";
+			reg = <0x12E10000 0x1000>;
+			interrupts = <0 88 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c9_hs_bus>;
+			clocks = <&clock CLK_USI5>;
+			clock-names = "hsi2c";
+			status = "disabled";
 		};
-	};
 
-	bus_gen_opp_table: opp_table7 {
-		compatible = "operating-points-v2";
-
-		opp00 {
-			opp-hz = /bits/ 64 <89000000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <133000000>;
-		};
-		opp02 {
-			opp-hz = /bits/ 64 <178000000>;
-		};
-		opp03 {
-			opp-hz = /bits/ 64 <267000000>;
+		hsi2c_10: i2c@12E20000 {
+			compatible = "samsung,exynos5250-hsi2c";
+			reg = <0x12E20000 0x1000>;
+			interrupts = <0 203 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&i2c10_hs_bus>;
+			clocks = <&clock CLK_USI6>;
+			clock-names = "hsi2c";
+			status = "disabled";
 		};
-	};
-
-	bus_peri_opp_table: opp_table8 {
-		compatible = "operating-points-v2";
 
-		opp00 {
-			opp-hz = /bits/ 64 <67000000>;
+		hdmi: hdmi@14530000 {
+			compatible = "samsung,exynos5420-hdmi";
+			reg = <0x14530000 0x70000>;
+			interrupts = <0 95 0>;
+			clocks = <&clock CLK_HDMI>, <&clock CLK_SCLK_HDMI>,
+				 <&clock CLK_DOUT_PIXEL>, <&clock CLK_SCLK_HDMIPHY>,
+				 <&clock CLK_MOUT_HDMI>;
+			clock-names = "hdmi", "sclk_hdmi", "sclk_pixel",
+				"sclk_hdmiphy", "mout_hdmi";
+			phy = <&hdmiphy>;
+			samsung,syscon-phandle = <&pmu_system_controller>;
+			status = "disabled";
+			power-domains = <&disp_pd>;
+		};
+
+		hdmiphy: hdmiphy@145D0000 {
+			reg = <0x145D0000 0x20>;
+		};
+
+		mixer: mixer@14450000 {
+			compatible = "samsung,exynos5420-mixer";
+			reg = <0x14450000 0x10000>;
+			interrupts = <0 94 0>;
+			clocks = <&clock CLK_MIXER>, <&clock CLK_HDMI>,
+				 <&clock CLK_SCLK_HDMI>;
+			clock-names = "mixer", "hdmi", "sclk_hdmi";
+			power-domains = <&disp_pd>;
+			iommus = <&sysmmu_tv>;
+		};
+
+		rotator: rotator@11C00000 {
+			compatible = "samsung,exynos5250-rotator";
+			reg = <0x11C00000 0x64>;
+			interrupts = <0 84 0>;
+			clocks = <&clock CLK_ROTATOR>;
+			clock-names = "rotator";
+			iommus = <&sysmmu_rotator>;
+		};
+
+		gsc_0: video-scaler@13e00000 {
+			compatible = "samsung,exynos5-gsc";
+			reg = <0x13e00000 0x1000>;
+			interrupts = <0 85 0>;
+			clocks = <&clock CLK_GSCL0>;
+			clock-names = "gscl";
+			power-domains = <&gsc_pd>;
+			iommus = <&sysmmu_gscl0>;
+		};
+
+		gsc_1: video-scaler@13e10000 {
+			compatible = "samsung,exynos5-gsc";
+			reg = <0x13e10000 0x1000>;
+			interrupts = <0 86 0>;
+			clocks = <&clock CLK_GSCL1>;
+			clock-names = "gscl";
+			power-domains = <&gsc_pd>;
+			iommus = <&sysmmu_gscl1>;
+		};
+
+		jpeg_0: jpeg@11F50000 {
+			compatible = "samsung,exynos5420-jpeg";
+			reg = <0x11F50000 0x1000>;
+			interrupts = <0 89 0>;
+			clock-names = "jpeg";
+			clocks = <&clock CLK_JPEG>;
+			iommus = <&sysmmu_jpeg0>;
+		};
+
+		jpeg_1: jpeg@11F60000 {
+			compatible = "samsung,exynos5420-jpeg";
+			reg = <0x11F60000 0x1000>;
+			interrupts = <0 168 0>;
+			clock-names = "jpeg";
+			clocks = <&clock CLK_JPEG2>;
+			iommus = <&sysmmu_jpeg1>;
+		};
+
+		pmu_system_controller: system-controller@10040000 {
+			compatible = "samsung,exynos5420-pmu", "syscon";
+			reg = <0x10040000 0x5000>;
+			clock-names = "clkout16";
+			clocks = <&clock CLK_FIN_PLL>;
+			#clock-cells = <1>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+			interrupt-parent = <&gic>;
 		};
-	};
-
-	bus_g2d_opp_table: opp_table9 {
-		compatible = "operating-points-v2";
 
-		opp00 {
-			opp-hz = /bits/ 64 <84000000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <167000000>;
-		};
-		opp02 {
-			opp-hz = /bits/ 64 <222000000>;
-		};
-		opp03 {
-			opp-hz = /bits/ 64 <300000000>;
-		};
-		opp04 {
-			opp-hz = /bits/ 64 <333000000>;
+		tmu_cpu0: tmu@10060000 {
+			compatible = "samsung,exynos5420-tmu";
+			reg = <0x10060000 0x100>;
+			interrupts = <0 65 0>;
+			clocks = <&clock CLK_TMU>;
+			clock-names = "tmu_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
+		};
+
+		tmu_cpu1: tmu@10064000 {
+			compatible = "samsung,exynos5420-tmu";
+			reg = <0x10064000 0x100>;
+			interrupts = <0 183 0>;
+			clocks = <&clock CLK_TMU>;
+			clock-names = "tmu_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
+		};
+
+		tmu_cpu2: tmu@10068000 {
+			compatible = "samsung,exynos5420-tmu-ext-triminfo";
+			reg = <0x10068000 0x100>, <0x1006c000 0x4>;
+			interrupts = <0 184 0>;
+			clocks = <&clock CLK_TMU>, <&clock CLK_TMU>;
+			clock-names = "tmu_apbif", "tmu_triminfo_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
+		};
+
+		tmu_cpu3: tmu@1006c000 {
+			compatible = "samsung,exynos5420-tmu-ext-triminfo";
+			reg = <0x1006c000 0x100>, <0x100a0000 0x4>;
+			interrupts = <0 185 0>;
+			clocks = <&clock CLK_TMU>, <&clock CLK_TMU_GPU>;
+			clock-names = "tmu_apbif", "tmu_triminfo_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
+		};
+
+		tmu_gpu: tmu@100a0000 {
+			compatible = "samsung,exynos5420-tmu-ext-triminfo";
+			reg = <0x100a0000 0x100>, <0x10068000 0x4>;
+			interrupts = <0 215 0>;
+			clocks = <&clock CLK_TMU_GPU>, <&clock CLK_TMU>;
+			clock-names = "tmu_apbif", "tmu_triminfo_apbif";
+			#include "exynos4412-tmu-sensor-conf.dtsi"
+		};
+
+		sysmmu_g2dr: sysmmu@0x10A60000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x10A60000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <24 5>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_G2D>, <&clock CLK_G2D>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_g2dw: sysmmu@0x10A70000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x10A70000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <22 2>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_G2D>, <&clock CLK_G2D>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_tv: sysmmu@0x14650000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x14650000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <7 4>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MIXER>, <&clock CLK_MIXER>;
+			power-domains = <&disp_pd>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_gscl0: sysmmu@0x13E80000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13E80000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <2 0>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_GSCL0>, <&clock CLK_GSCL0>;
+			power-domains = <&gsc_pd>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_gscl1: sysmmu@0x13E90000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x13E90000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <2 2>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_GSCL1>, <&clock CLK_GSCL1>;
+			power-domains = <&gsc_pd>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_scaler0r: sysmmu@0x12880000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x12880000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <22 4>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MSCL0>, <&clock CLK_MSCL0>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_scaler1r: sysmmu@0x12890000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x12890000 0x1000>;
+			interrupts = <0 186 0>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MSCL1>, <&clock CLK_MSCL1>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_scaler2r: sysmmu@0x128A0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x128A0000 0x1000>;
+			interrupts = <0 188 0>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MSCL2>, <&clock CLK_MSCL2>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_scaler0w: sysmmu@0x128C0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x128C0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <27 2>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MSCL0>, <&clock CLK_MSCL0>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_scaler1w: sysmmu@0x128D0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x128D0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <22 6>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MSCL1>, <&clock CLK_MSCL1>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_scaler2w: sysmmu@0x128E0000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x128E0000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <19 6>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MSCL2>, <&clock CLK_MSCL2>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_rotator: sysmmu@0x11D40000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x11D40000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <4 0>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_ROTATOR>, <&clock CLK_ROTATOR>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_jpeg0: sysmmu@0x11F10000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x11F10000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <4 2>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_JPEG>, <&clock CLK_JPEG>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_jpeg1: sysmmu@0x11F20000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x11F20000 0x1000>;
+			interrupts = <0 169 0>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_JPEG2>, <&clock CLK_JPEG2>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_mfc_l: sysmmu@0x11200000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x11200000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <6 2>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MFCL>, <&clock CLK_MFC>;
+			power-domains = <&mfc_pd>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_mfc_r: sysmmu@0x11210000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x11210000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <8 5>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_MFCR>, <&clock CLK_MFC>;
+			power-domains = <&mfc_pd>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_fimd1_0: sysmmu@0x14640000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x14640000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <3 2>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_FIMD1M0>, <&clock CLK_FIMD1>;
+			power-domains = <&disp_pd>;
+			#iommu-cells = <0>;
+		};
+
+		sysmmu_fimd1_1: sysmmu@0x14680000 {
+			compatible = "samsung,exynos-sysmmu";
+			reg = <0x14680000 0x1000>;
+			interrupt-parent = <&combiner>;
+			interrupts = <3 0>;
+			clock-names = "sysmmu", "master";
+			clocks = <&clock CLK_SMMU_FIMD1M1>, <&clock CLK_FIMD1>;
+			power-domains = <&disp_pd>;
+			#iommu-cells = <0>;
+		};
+
+		bus_wcore: bus_wcore {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK400_WCORE>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_wcore_opp_table>;
+			status = "disabled";
 		};
-	};
-
-	bus_g2d_acp_opp_table: opp_table10 {
-		compatible = "operating-points-v2";
 
-		opp00 {
-			opp-hz = /bits/ 64 <67000000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <133000000>;
-		};
-		opp02 {
-			opp-hz = /bits/ 64 <178000000>;
-		};
-		opp03 {
-			opp-hz = /bits/ 64 <267000000>;
+		bus_noc: bus_noc {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK100_NOC>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_noc_opp_table>;
+			status = "disabled";
 		};
-	};
-
-	bus_jpeg_opp_table: opp_table11 {
-		compatible = "operating-points-v2";
 
-		opp00 {
-			opp-hz = /bits/ 64 <75000000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <150000000>;
-		};
-		opp02 {
-			opp-hz = /bits/ 64 <200000000>;
-		};
-		opp03 {
-			opp-hz = /bits/ 64 <300000000>;
+		bus_fsys_apb: bus_fsys_apb {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_PCLK200_FSYS>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_fsys_apb_opp_table>;
+			status = "disabled";
 		};
-	};
-
-	bus_jpeg_apb_opp_table: opp_table12 {
-		compatible = "operating-points-v2";
 
-		opp00 {
-			opp-hz = /bits/ 64 <84000000>;
-		};
-		opp01 {
-			opp-hz = /bits/ 64 <111000000>;
+		bus_fsys: bus_fsys {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK200_FSYS>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_fsys_apb_opp_table>;
+			status = "disabled";
 		};
-		opp02 {
-			opp-hz = /bits/ 64 <134000000>;
+
+		bus_fsys2: bus_fsys2 {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK200_FSYS2>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_fsys2_opp_table>;
+			status = "disabled";
 		};
-		opp03 {
-			opp-hz = /bits/ 64 <167000000>;
+
+		bus_mfc: bus_mfc {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK333>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_mfc_opp_table>;
+			status = "disabled";
 		};
-	};
 
-	bus_disp1_fimd_opp_table: opp_table13 {
-		compatible = "operating-points-v2";
+		bus_gen: bus_gen {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK266>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_gen_opp_table>;
+			status = "disabled";
+		};
 
-		opp00 {
-			opp-hz = /bits/ 64 <120000000>;
+		bus_peri: bus_peri {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK66>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_peri_opp_table>;
+			status = "disabled";
 		};
-		opp01 {
-			opp-hz = /bits/ 64 <200000000>;
+
+		bus_g2d: bus_g2d {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK333_G2D>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_g2d_opp_table>;
+			status = "disabled";
 		};
-	};
 
-	bus_disp1_opp_table: opp_table14 {
-		compatible = "operating-points-v2";
+		bus_g2d_acp: bus_g2d_acp {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK266_G2D>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_g2d_acp_opp_table>;
+			status = "disabled";
+		};
 
-		opp00 {
-			opp-hz = /bits/ 64 <120000000>;
+		bus_jpeg: bus_jpeg {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK300_JPEG>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_jpeg_opp_table>;
+			status = "disabled";
 		};
-		opp01 {
-			opp-hz = /bits/ 64 <200000000>;
+
+		bus_jpeg_apb: bus_jpeg_apb {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK166>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_jpeg_apb_opp_table>;
+			status = "disabled";
 		};
-		opp02 {
-			opp-hz = /bits/ 64 <300000000>;
+
+		bus_disp1_fimd: bus_disp1_fimd {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK300_DISP1>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_disp1_fimd_opp_table>;
+			status = "disabled";
 		};
-	};
 
-	bus_gscl_opp_table: opp_table15 {
-		compatible = "operating-points-v2";
+		bus_disp1: bus_disp1 {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK400_DISP1>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_disp1_opp_table>;
+			status = "disabled";
+		};
 
-		opp00 {
-			opp-hz = /bits/ 64 <150000000>;
+		bus_gscl_scaler: bus_gscl_scaler {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK300_GSCL>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_gscl_opp_table>;
+			status = "disabled";
 		};
-		opp01 {
-			opp-hz = /bits/ 64 <200000000>;
+
+		bus_mscl: bus_mscl {
+			compatible = "samsung,exynos-bus";
+			clocks = <&clock CLK_DOUT_ACLK400_MSCL>;
+			clock-names = "bus";
+			operating-points-v2 = <&bus_mscl_opp_table>;
+			status = "disabled";
 		};
-		opp02 {
-			opp-hz = /bits/ 64 <300000000>;
+
+		bus_wcore_opp_table: opp_table2 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <84000000>;
+				opp-microvolt = <925000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <111000000>;
+				opp-microvolt = <950000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <222000000>;
+				opp-microvolt = <950000>;
+			};
+			opp03 {
+				opp-hz = /bits/ 64 <333000000>;
+				opp-microvolt = <950000>;
+			};
+			opp04 {
+				opp-hz = /bits/ 64 <400000000>;
+				opp-microvolt = <987500>;
+			};
+		};
+
+		bus_noc_opp_table: opp_table3 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <67000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <75000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <86000000>;
+			};
+			opp03 {
+				opp-hz = /bits/ 64 <100000000>;
+			};
+		};
+
+		bus_fsys_apb_opp_table: opp_table4 {
+			compatible = "operating-points-v2";
+			opp-shared;
+
+			opp00 {
+				opp-hz = /bits/ 64 <100000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <200000000>;
+			};
+		};
+
+		bus_fsys2_opp_table: opp_table5 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <75000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <100000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <150000000>;
+			};
+		};
+
+		bus_mfc_opp_table: opp_table6 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <96000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <111000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <167000000>;
+			};
+			opp03 {
+				opp-hz = /bits/ 64 <222000000>;
+			};
+			opp04 {
+				opp-hz = /bits/ 64 <333000000>;
+			};
+		};
+
+		bus_gen_opp_table: opp_table7 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <89000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <133000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <178000000>;
+			};
+			opp03 {
+				opp-hz = /bits/ 64 <267000000>;
+			};
+		};
+
+		bus_peri_opp_table: opp_table8 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <67000000>;
+			};
+		};
+
+		bus_g2d_opp_table: opp_table9 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <84000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <167000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <222000000>;
+			};
+			opp03 {
+				opp-hz = /bits/ 64 <300000000>;
+			};
+			opp04 {
+				opp-hz = /bits/ 64 <333000000>;
+			};
+		};
+
+		bus_g2d_acp_opp_table: opp_table10 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <67000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <133000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <178000000>;
+			};
+			opp03 {
+				opp-hz = /bits/ 64 <267000000>;
+			};
+		};
+
+		bus_jpeg_opp_table: opp_table11 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <75000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <150000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <200000000>;
+			};
+			opp03 {
+				opp-hz = /bits/ 64 <300000000>;
+			};
+		};
+
+		bus_jpeg_apb_opp_table: opp_table12 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <84000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <111000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <134000000>;
+			};
+			opp03 {
+				opp-hz = /bits/ 64 <167000000>;
+			};
+		};
+
+		bus_disp1_fimd_opp_table: opp_table13 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <120000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <200000000>;
+			};
+		};
+
+		bus_disp1_opp_table: opp_table14 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <120000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <200000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <300000000>;
+			};
+		};
+
+		bus_gscl_opp_table: opp_table15 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <150000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <200000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <300000000>;
+			};
+		};
+
+		bus_mscl_opp_table: opp_table16 {
+			compatible = "operating-points-v2";
+
+			opp00 {
+				opp-hz = /bits/ 64 <84000000>;
+			};
+			opp01 {
+				opp-hz = /bits/ 64 <167000000>;
+			};
+			opp02 {
+				opp-hz = /bits/ 64 <222000000>;
+			};
+			opp03 {
+				opp-hz = /bits/ 64 <333000000>;
+			};
+			opp04 {
+				opp-hz = /bits/ 64 <400000000>;
+			};
 		};
 	};
 
-	bus_mscl_opp_table: opp_table16 {
-		compatible = "operating-points-v2";
-
-		opp00 {
-			opp-hz = /bits/ 64 <84000000>;
+	thermal-zones {
+		cpu0_thermal: cpu0-thermal {
+			thermal-sensors = <&tmu_cpu0>;
+			#include "exynos5420-trip-points.dtsi"
 		};
-		opp01 {
-			opp-hz = /bits/ 64 <167000000>;
+		cpu1_thermal: cpu1-thermal {
+		       thermal-sensors = <&tmu_cpu1>;
+		       #include "exynos5420-trip-points.dtsi"
 		};
-		opp02 {
-			opp-hz = /bits/ 64 <222000000>;
+		cpu2_thermal: cpu2-thermal {
+		       thermal-sensors = <&tmu_cpu2>;
+		       #include "exynos5420-trip-points.dtsi"
 		};
-		opp03 {
-			opp-hz = /bits/ 64 <333000000>;
+		cpu3_thermal: cpu3-thermal {
+		       thermal-sensors = <&tmu_cpu3>;
+		       #include "exynos5420-trip-points.dtsi"
 		};
-		opp04 {
-			opp-hz = /bits/ 64 <400000000>;
+		gpu_thermal: gpu-thermal {
+		       thermal-sensors = <&tmu_gpu>;
+		       #include "exynos5420-trip-points.dtsi"
 		};
 	};
 };
@@ -1614,6 +1330,72 @@
 	iommu-names = "m0", "m1";
 };
 
+&i2c_0 {
+	clocks = <&clock CLK_I2C0>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_bus>;
+};
+
+&i2c_1 {
+	clocks = <&clock CLK_I2C1>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_bus>;
+};
+
+&i2c_2 {
+	clocks = <&clock CLK_I2C2>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c2_bus>;
+};
+
+&i2c_3 {
+	clocks = <&clock CLK_I2C3>;
+	clock-names = "i2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c3_bus>;
+};
+
+&hsi2c_4 {
+	clocks = <&clock CLK_USI0>;
+	clock-names = "hsi2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c4_hs_bus>;
+};
+
+&hsi2c_5 {
+	clocks = <&clock CLK_USI1>;
+	clock-names = "hsi2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c5_hs_bus>;
+};
+
+&hsi2c_6 {
+	clocks = <&clock CLK_USI2>;
+	clock-names = "hsi2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c6_hs_bus>;
+};
+
+&hsi2c_7 {
+	clocks = <&clock CLK_USI3>;
+	clock-names = "hsi2c";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c7_hs_bus>;
+};
+
+&mct {
+	clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MCT>;
+	clock-names = "fin_pll", "mct";
+};
+
+&pwm {
+	clocks = <&clock CLK_PWM>;
+	clock-names = "timers";
+};
+
 &rtc {
 	clocks = <&clock CLK_RTC>;
 	clock-names = "rtc";
@@ -1641,4 +1423,58 @@
 	clock-names = "uart", "clk_uart_baud0";
 };
 
+&sss {
+	clocks = <&clock CLK_SSS>;
+	clock-names = "secss";
+};
+
+&usbdrd3_0 {
+	clocks = <&clock CLK_USBD300>;
+	clock-names = "usbdrd30";
+};
+
+&usbdrd_phy0 {
+	clocks = <&clock CLK_USBD300>, <&clock CLK_SCLK_USBPHY300>;
+	clock-names = "phy", "ref";
+	samsung,pmu-syscon = <&pmu_system_controller>;
+};
+
+&usbdrd3_1 {
+	clocks = <&clock CLK_USBD301>;
+	clock-names = "usbdrd30";
+};
+
+&usbdrd_dwc3_1 {
+	interrupts = <GIC_SPI 73 0>;
+};
+
+&usbdrd_phy1 {
+	clocks = <&clock CLK_USBD301>, <&clock CLK_SCLK_USBPHY301>;
+	clock-names = "phy", "ref";
+	samsung,pmu-syscon = <&pmu_system_controller>;
+};
+
+&usbhost1 {
+	clocks = <&clock CLK_USBH20>;
+	clock-names = "usbhost";
+};
+
+&usbhost2 {
+	clocks = <&clock CLK_USBH20>;
+	clock-names = "usbhost";
+};
+
+&usb2_phy {
+	clocks = <&clock CLK_USBH20>, <&clock CLK_SCLK_USBPHY300>;
+	clock-names = "phy", "ref";
+	samsung,sysreg-phandle = <&sysreg_system_controller>;
+	samsung,pmureg-phandle = <&pmu_system_controller>;
+};
+
+&watchdog {
+	clocks = <&clock CLK_WDT>;
+	clock-names = "watchdog";
+	samsung,syscon-phandle = <&pmu_system_controller>;
+};
+
 #include "exynos5420-pinctrl.dtsi"
diff --git a/arch/arm/boot/dts/exynos5422-cpu-thermal.dtsi b/arch/arm/boot/dts/exynos5422-cpu-thermal.dtsi
deleted file mode 100644
index 3e4c4ad96d63..000000000000
--- a/arch/arm/boot/dts/exynos5422-cpu-thermal.dtsi
+++ /dev/null
@@ -1,103 +0,0 @@
-/*
- * Device tree sources for Exynos5422 thermal zone
- *
- * Copyright (c) 2015 Lukasz Majewski <l.majewski@samsung.com>
- *			Anand Moon <linux.amoon@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#include <dt-bindings/thermal/thermal.h>
-
-/ {
-	thermal-zones {
-		cpu0_thermal: cpu0-thermal {
-			thermal-sensors = <&tmu_cpu0 0>;
-			polling-delay-passive = <250>;
-			polling-delay = <0>;
-			trips {
-				cpu_alert0: cpu-alert-0 {
-					temperature = <50000>; /* millicelsius */
-					hysteresis = <5000>; /* millicelsius */
-					type = "active";
-				};
-				cpu_alert1: cpu-alert-1 {
-					temperature = <60000>; /* millicelsius */
-					hysteresis = <5000>; /* millicelsius */
-					type = "active";
-				};
-				cpu_alert2: cpu-alert-2 {
-					temperature = <70000>; /* millicelsius */
-					hysteresis = <5000>; /* millicelsius */
-					type = "active";
-				};
-				cpu_crit0: cpu-crit-0 {
-					temperature = <120000>; /* millicelsius */
-					hysteresis = <0>; /* millicelsius */
-					type = "critical";
-				};
-				/*
-				 * Exyunos542x support only 4 trip-points
-				 * so for these polling mode is required.
-				 * Start polling at temperature level of last
-				 * interrupt-driven trip: cpu_alert2
-				 */
-				cpu_alert3: cpu-alert-3 {
-					temperature = <70000>; /* millicelsius */
-					hysteresis = <10000>; /* millicelsius */
-					type = "passive";
-				};
-				cpu_alert4: cpu-alert-4 {
-					temperature = <85000>; /* millicelsius */
-					hysteresis = <10000>; /* millicelsius */
-					type = "passive";
-				};
-
-			};
-			cooling-maps {
-				map0 {
-				     trip = <&cpu_alert0>;
-				     cooling-device = <&fan0 0 1>;
-				};
-				map1 {
-				     trip = <&cpu_alert1>;
-				     cooling-device = <&fan0 1 2>;
-				};
-				map2 {
-				     trip = <&cpu_alert2>;
-				     cooling-device = <&fan0 2 3>;
-				};
-				/*
-				 * When reaching cpu_alert3, reduce CPU
-				 * by 2 steps. On Exynos5422/5800 that would
-				 * be: 1500 MHz and 1100 MHz.
-				 */
-				map3 {
-				     trip = <&cpu_alert3>;
-				     cooling-device = <&cpu0 0 2>;
-				};
-				map4 {
-				     trip = <&cpu_alert3>;
-				     cooling-device = <&cpu4 0 2>;
-				};
-
-				/*
-				 * When reaching cpu_alert4, reduce CPU
-				 * further, down to 600 MHz (11 steps for big,
-				 * 7 steps for LITTLE).
-				 */
-				map5 {
-				     trip = <&cpu_alert4>;
-				     cooling-device = <&cpu0 3 7>;
-				};
-				map6 {
-				     trip = <&cpu_alert4>;
-				     cooling-device = <&cpu4 3 11>;
-				};
-			};
-		};
-	};
-};
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
index 2a4e10bc8801..d56253049ccb 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi
@@ -1,9 +1,11 @@
 /*
  * Hardkernel Odroid XU3 board device tree source
  *
- * Copyright (c) 2014 Collabora Ltd.
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
+ * Copyright (c) 2014 Collabora Ltd.
+ * Copyright (c) 2015 Lukasz Majewski <l.majewski@samsung.com>
+ *                    Anand Moon <linux.amoon@gmail.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -16,7 +18,7 @@
 #include <dt-bindings/sound/samsung-i2s.h>
 #include "exynos5800.dtsi"
 #include "exynos5422-cpus.dtsi"
-#include "exynos5422-cpu-thermal.dtsi"
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	memory {
@@ -54,6 +56,94 @@
 		#cooling-cells = <2>;
 		cooling-levels = <0 130 170 230>;
 	};
+
+	thermal-zones {
+		cpu0_thermal: cpu0-thermal {
+			thermal-sensors = <&tmu_cpu0 0>;
+			polling-delay-passive = <250>;
+			polling-delay = <0>;
+			trips {
+				cpu_alert0: cpu-alert-0 {
+					temperature = <50000>; /* millicelsius */
+					hysteresis = <5000>; /* millicelsius */
+					type = "active";
+				};
+				cpu_alert1: cpu-alert-1 {
+					temperature = <60000>; /* millicelsius */
+					hysteresis = <5000>; /* millicelsius */
+					type = "active";
+				};
+				cpu_alert2: cpu-alert-2 {
+					temperature = <70000>; /* millicelsius */
+					hysteresis = <5000>; /* millicelsius */
+					type = "active";
+				};
+				cpu_crit0: cpu-crit-0 {
+					temperature = <120000>; /* millicelsius */
+					hysteresis = <0>; /* millicelsius */
+					type = "critical";
+				};
+				/*
+				 * Exynos542x supports only 4 trip-points
+				 * so for these polling mode is required.
+				 * Start polling at temperature level of last
+				 * interrupt-driven trip: cpu_alert2
+				 */
+				cpu_alert3: cpu-alert-3 {
+					temperature = <70000>; /* millicelsius */
+					hysteresis = <10000>; /* millicelsius */
+					type = "passive";
+				};
+				cpu_alert4: cpu-alert-4 {
+					temperature = <85000>; /* millicelsius */
+					hysteresis = <10000>; /* millicelsius */
+					type = "passive";
+				};
+
+			};
+			cooling-maps {
+				map0 {
+					trip = <&cpu_alert0>;
+					cooling-device = <&fan0 0 1>;
+				};
+				map1 {
+					trip = <&cpu_alert1>;
+					cooling-device = <&fan0 1 2>;
+				};
+				map2 {
+					trip = <&cpu_alert2>;
+					cooling-device = <&fan0 2 3>;
+				};
+				/*
+				 * When reaching cpu_alert3, reduce CPU
+				 * by 2 steps. On Exynos5422/5800 that would
+				 * be: 1600 MHz and 1100 MHz.
+				 */
+				map3 {
+					trip = <&cpu_alert3>;
+					cooling-device = <&cpu0 0 2>;
+				};
+				map4 {
+					trip = <&cpu_alert3>;
+					cooling-device = <&cpu4 0 2>;
+				};
+
+				/*
+				 * When reaching cpu_alert4, reduce CPU
+				 * further, down to 600 MHz (11 steps for big,
+				 * 7 steps for LITTLE).
+				 */
+				map5 {
+					trip = <&cpu_alert4>;
+					cooling-device = <&cpu0 3 7>;
+				};
+				map6 {
+					trip = <&cpu_alert4>;
+					cooling-device = <&cpu4 3 11>;
+				};
+			};
+		};
+	};
 };
 
 &bus_wcore {
@@ -405,11 +495,6 @@
 	};
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-};
-
 &mmc_0 {
 	status = "okay";
 	mmc-pwrseq = <&emmc_pwrseq>;
@@ -487,27 +572,22 @@
 
 &tmu_cpu0 {
 	vtmu-supply = <&ldo7_reg>;
-	status = "okay";
 };
 
 &tmu_cpu1 {
 	vtmu-supply = <&ldo7_reg>;
-	status = "okay";
 };
 
 &tmu_cpu2 {
 	vtmu-supply = <&ldo7_reg>;
-	status = "okay";
 };
 
 &tmu_cpu3 {
 	vtmu-supply = <&ldo7_reg>;
-	status = "okay";
 };
 
 &tmu_gpu {
 	vtmu-supply = <&ldo7_reg>;
-	status = "okay";
 };
 
 &rtc {
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-lite.dts b/arch/arm/boot/dts/exynos5422-odroidxu3-lite.dts
index 2ae1cf41dcb6..03fa88c45426 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3-lite.dts
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3-lite.dts
@@ -14,44 +14,11 @@
 /dts-v1/;
 #include "exynos5422-odroidxu3-common.dtsi"
 #include "exynos5422-odroidxu3-audio.dtsi"
+#include "exynos54xx-odroidxu-leds.dtsi"
 
 / {
 	model = "Hardkernel Odroid XU3 Lite";
 	compatible = "hardkernel,odroid-xu3-lite", "samsung,exynos5800", "samsung,exynos5";
-
-	pwmleds {
-		compatible = "pwm-leds";
-
-		greenled {
-			label = "green:mmc0";
-			pwms = <&pwm 1 2000000 0>;
-			pwm-names = "pwm1";
-			/*
-			 * Green LED is much brighter than the others
-			 * so limit its max brightness
-			 */
-			max_brightness = <127>;
-			linux,default-trigger = "mmc0";
-		};
-
-		blueled {
-			label = "blue:heartbeat";
-			pwms = <&pwm 2 2000000 0>;
-			pwm-names = "pwm2";
-			max_brightness = <255>;
-			linux,default-trigger = "heartbeat";
-		};
-	};
-
-	gpioleds {
-		compatible = "gpio-leds";
-		redled {
-			label = "red:microSD";
-			gpios = <&gpx2 3 GPIO_ACTIVE_HIGH>;
-			default-state = "off";
-			linux,default-trigger = "mmc1";
-		};
-	};
 };
 
 &pwm {
diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3.dts b/arch/arm/boot/dts/exynos5422-odroidxu3.dts
index 432406db85de..9ed6564acfb0 100644
--- a/arch/arm/boot/dts/exynos5422-odroidxu3.dts
+++ b/arch/arm/boot/dts/exynos5422-odroidxu3.dts
@@ -13,44 +13,11 @@
 /dts-v1/;
 #include "exynos5422-odroidxu3-common.dtsi"
 #include "exynos5422-odroidxu3-audio.dtsi"
+#include "exynos54xx-odroidxu-leds.dtsi"
 
 / {
 	model = "Hardkernel Odroid XU3";
 	compatible = "hardkernel,odroid-xu3", "samsung,exynos5800", "samsung,exynos5";
-
-	pwmleds {
-		compatible = "pwm-leds";
-
-		greenled {
-			label = "green:mmc0";
-			pwms = <&pwm 1 2000000 0>;
-			pwm-names = "pwm1";
-			/*
-			 * Green LED is much brighter than the others
-			 * so limit its max brightness
-			 */
-			max_brightness = <127>;
-			linux,default-trigger = "mmc0";
-		};
-
-		blueled {
-			label = "blue:heartbeat";
-			pwms = <&pwm 2 2000000 0>;
-			pwm-names = "pwm2";
-			max_brightness = <255>;
-			linux,default-trigger = "heartbeat";
-		};
-	};
-
-	gpioleds {
-		compatible = "gpio-leds";
-		redled {
-			label = "red:microSD";
-			gpios = <&gpx2 3 GPIO_ACTIVE_HIGH>;
-			default-state = "off";
-			linux,default-trigger = "mmc1";
-		};
-	};
 };
 
 &i2c_0 {
diff --git a/arch/arm/boot/dts/exynos54xx-odroidxu-leds.dtsi b/arch/arm/boot/dts/exynos54xx-odroidxu-leds.dtsi
new file mode 100644
index 000000000000..0ed30206625c
--- /dev/null
+++ b/arch/arm/boot/dts/exynos54xx-odroidxu-leds.dtsi
@@ -0,0 +1,50 @@
+/*
+ * Hardkernel Odroid XU/XU3 LED device tree source
+ *
+ * Copyright (c) 2015,2016 Krzysztof Kozlowski
+ * Copyright (c) 2014 Collabora Ltd.
+ * Copyright (c) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	pwmleds {
+		compatible = "pwm-leds";
+
+		greenled {
+			label = "green:mmc0";
+			pwms = <&pwm 1 2000000 0>;
+			pwm-names = "pwm1";
+			/*
+			 * Green LED is much brighter than the others
+			 * so limit its max brightness
+			 */
+			max_brightness = <127>;
+			linux,default-trigger = "mmc0";
+		};
+
+		blueled {
+			label = "blue:heartbeat";
+			pwms = <&pwm 2 2000000 0>;
+			pwm-names = "pwm2";
+			max_brightness = <255>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+
+	gpioleds {
+		compatible = "gpio-leds";
+		redled {
+			label = "red:microSD";
+			gpios = <&gpx2 3 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			linux,default-trigger = "mmc1";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/exynos54xx.dtsi b/arch/arm/boot/dts/exynos54xx.dtsi
new file mode 100644
index 000000000000..06a604911e87
--- /dev/null
+++ b/arch/arm/boot/dts/exynos54xx.dtsi
@@ -0,0 +1,199 @@
+/*
+ * Samsung's Exynos54xx SoC series common device tree source
+ *
+ * Copyright (c) 2012-2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ * Copyright (c) 2016 Krzysztof Kozlowski
+ *
+ * Device nodes common for Samsung Exynos5410/5420/5422/5800. Specific
+ * Exynos 54xx SoCs should include this file and customize it further
+ * (e.g. with clocks).
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "skeleton.dtsi"
+#include "exynos5.dtsi"
+
+/ {
+	compatible = "samsung,exynos5";
+
+	aliases {
+		i2c4 = &hsi2c_4;
+		i2c5 = &hsi2c_5;
+		i2c6 = &hsi2c_6;
+		i2c7 = &hsi2c_7;
+		usbdrdphy0 = &usbdrd_phy0;
+		usbdrdphy1 = &usbdrd_phy1;
+	};
+
+	soc: soc {
+		sysram@02020000 {
+			compatible = "mmio-sram";
+			reg = <0x02020000 0x54000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0x02020000 0x54000>;
+
+			smp-sysram@0 {
+				compatible = "samsung,exynos4210-sysram";
+				reg = <0x0 0x1000>;
+			};
+
+			smp-sysram@53000 {
+				compatible = "samsung,exynos4210-sysram-ns";
+				reg = <0x53000 0x1000>;
+			};
+		};
+
+		mct: mct@101c0000 {
+			compatible = "samsung,exynos4210-mct";
+			reg = <0x101c0000 0xb00>;
+			interrupt-parent = <&mct_map>;
+			interrupts = <0>, <1>, <2>, <3>, <4>, <5>, <6>, <7>,
+					<8>, <9>, <10>, <11>;
+
+			mct_map: mct-map {
+				#interrupt-cells = <1>;
+				#address-cells = <0>;
+				#size-cells = <0>;
+				interrupt-map = <0 &combiner 23 3>,
+						<1 &combiner 23 4>,
+						<2 &combiner 25 2>,
+						<3 &combiner 25 3>,
+						<4 &gic 0 120 0>,
+						<5 &gic 0 121 0>,
+						<6 &gic 0 122 0>,
+						<7 &gic 0 123 0>,
+						<8 &gic 0 128 0>,
+						<9 &gic 0 129 0>,
+						<10 &gic 0 130 0>,
+						<11 &gic 0 131 0>;
+			};
+		};
+
+		watchdog: watchdog@101d0000 {
+			compatible = "samsung,exynos5420-wdt";
+			reg = <0x101d0000 0x100>;
+			interrupts = <0 42 0>;
+		};
+
+		sss: sss@10830000 {
+			compatible = "samsung,exynos4210-secss";
+			reg = <0x10830000 0x300>;
+			interrupts = <0 112 0>;
+		};
+
+		/* i2c_0-3 are defined in exynos5.dtsi */
+		hsi2c_4: i2c@12ca0000 {
+			compatible = "samsung,exynos5250-hsi2c";
+			reg = <0x12ca0000 0x1000>;
+			interrupts = <0 60 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		hsi2c_5: i2c@12cb0000 {
+			compatible = "samsung,exynos5250-hsi2c";
+			reg = <0x12cb0000 0x1000>;
+			interrupts = <0 61 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		hsi2c_6: i2c@12cc0000 {
+			compatible = "samsung,exynos5250-hsi2c";
+			reg = <0x12cc0000 0x1000>;
+			interrupts = <0 62 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		hsi2c_7: i2c@12cd0000 {
+			compatible = "samsung,exynos5250-hsi2c";
+			reg = <0x12cd0000 0x1000>;
+			interrupts = <0 63 0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		usbdrd3_0: usb3-0 {
+			compatible = "samsung,exynos5250-dwusb3";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			usbdrd_dwc3_0: dwc3@12000000 {
+				compatible = "snps,dwc3";
+				reg = <0x12000000 0x10000>;
+				interrupts = <0 72 0>;
+				phys = <&usbdrd_phy0 0>, <&usbdrd_phy0 1>;
+				phy-names = "usb2-phy", "usb3-phy";
+			};
+		};
+
+		usbdrd_phy0: phy@12100000 {
+			compatible = "samsung,exynos5420-usbdrd-phy";
+			reg = <0x12100000 0x100>;
+			#phy-cells = <1>;
+		};
+
+		usbdrd3_1: usb3-1 {
+			compatible = "samsung,exynos5250-dwusb3";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			usbdrd_dwc3_1: dwc3@12400000 {
+				compatible = "snps,dwc3";
+				reg = <0x12400000 0x10000>;
+				phys = <&usbdrd_phy1 0>, <&usbdrd_phy1 1>;
+				phy-names = "usb2-phy", "usb3-phy";
+			};
+		};
+
+		usbdrd_phy1: phy@12500000 {
+			compatible = "samsung,exynos5420-usbdrd-phy";
+			reg = <0x12500000 0x100>;
+			#phy-cells = <1>;
+		};
+
+		usbhost2: usb@12110000 {
+			compatible = "samsung,exynos4210-ehci";
+			reg = <0x12110000 0x100>;
+			interrupts = <0 71 0>;
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+			port@0 {
+				reg = <0>;
+				phys = <&usb2_phy 1>;
+			};
+		};
+
+		usbhost1: usb@12120000 {
+			compatible = "samsung,exynos4210-ohci";
+			reg = <0x12120000 0x100>;
+			interrupts = <0 71 0>;
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+			port@0 {
+				reg = <0>;
+				phys = <&usb2_phy 1>;
+			};
+		};
+
+		usb2_phy: phy@12130000 {
+			compatible = "samsung,exynos5250-usb2-phy";
+			reg = <0x12130000 0x100>;
+			#phy-cells = <1>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/exynos5800-peach-pi.dts b/arch/arm/boot/dts/exynos5800-peach-pi.dts
index 62ceb89e073f..5ec71e2400fd 100644
--- a/arch/arm/boot/dts/exynos5800-peach-pi.dts
+++ b/arch/arm/boot/dts/exynos5800-peach-pi.dts
@@ -16,6 +16,7 @@
 #include <dt-bindings/regulator/maxim,max77802.h>
 #include "exynos5800.dtsi"
 #include "exynos5420-cpus.dtsi"
+#include "exynos-mfc-reserved-memory.dtsi"
 
 / {
 	model = "Google Peach Pi Rev 10+";
@@ -278,7 +279,6 @@
 				regulator-name = "vdd_1v2";
 				regulator-min-microvolt = <1200000>;
 				regulator-max-microvolt = <1200000>;
-				regulator-always-on;
 				regulator-boot-on;
 				regulator-state-mem {
 					regulator-off-in-suspend;
@@ -301,7 +301,6 @@
 				regulator-name = "vdd_1v35";
 				regulator-min-microvolt = <1350000>;
 				regulator-max-microvolt = <1350000>;
-				regulator-always-on;
 				regulator-boot-on;
 				regulator-state-mem {
 					regulator-on-in-suspend;
@@ -323,7 +322,6 @@
 				regulator-name = "vdd_2v";
 				regulator-min-microvolt = <2000000>;
 				regulator-max-microvolt = <2000000>;
-				regulator-always-on;
 				regulator-boot-on;
 				regulator-state-mem {
 					regulator-on-in-suspend;
@@ -334,7 +332,6 @@
 				regulator-name = "vdd_1v8";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
-				regulator-always-on;
 				regulator-boot-on;
 				regulator-state-mem {
 					regulator-on-in-suspend;
@@ -419,7 +416,6 @@
 				regulator-name = "vdd_ldo9";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
-				regulator-always-on;
 				regulator-state-mem {
 					regulator-on-in-suspend;
 					regulator-mode = <MAX77802_OPMODE_LP>;
@@ -430,7 +426,6 @@
 				regulator-name = "vdd_ldo10";
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
-				regulator-always-on;
 				regulator-state-mem {
 					regulator-off-in-suspend;
 				};
@@ -669,11 +664,6 @@
 	status = "okay";
 };
 
-&mfc {
-	samsung,mfc-r = <0x43000000 0x800000>;
-	samsung,mfc-l = <0x51000000 0x800000>;
-};
-
 &mmc_0 {
 	status = "okay";
 	num-slots = <1>;
@@ -1022,6 +1012,26 @@
 	status = "okay";
 };
 
+&tmu_cpu0 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_cpu1 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_cpu2 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_cpu3 {
+	vtmu-supply = <&ldo10_reg>;
+};
+
+&tmu_gpu {
+	vtmu-supply = <&ldo10_reg>;
+};
+
 &usbdrd_dwc3_0 {
 	dr_mode = "host";
 };
diff --git a/arch/arm/boot/dts/ge863-pro3.dtsi b/arch/arm/boot/dts/ge863-pro3.dtsi
index 0d0e62489d93..4aee5cc75fa4 100644
--- a/arch/arm/boot/dts/ge863-pro3.dtsi
+++ b/arch/arm/boot/dts/ge863-pro3.dtsi
@@ -11,15 +11,6 @@
 
 / {
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <6000000>;
-		};
-
 		main_xtal {
 			clock-frequency = <6000000>;
 		};
diff --git a/arch/arm/boot/dts/hi3519-demb.dts b/arch/arm/boot/dts/hi3519-demb.dts
new file mode 100644
index 000000000000..6991ab694c9c
--- /dev/null
+++ b/arch/arm/boot/dts/hi3519-demb.dts
@@ -0,0 +1,42 @@
+/*
+ * Copyright (c) 2015 HiSilicon Technologies Co., Ltd.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+/dts-v1/;
+#include "hi3519.dtsi"
+
+/ {
+	model = "HiSilicon HI3519 DEMO Board";
+	compatible = "hisilicon,hi3519";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x40000000>;
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&dual_timer0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/hi3519.dtsi b/arch/arm/boot/dts/hi3519.dtsi
new file mode 100644
index 000000000000..5729ecfcdc8b
--- /dev/null
+++ b/arch/arm/boot/dts/hi3519.dtsi
@@ -0,0 +1,187 @@
+/*
+ * Copyright (c) 2015 HiSilicon Technologies Co., Ltd.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#include <dt-bindings/clock/hi3519-clock.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	chosen { };
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0>;
+		};
+	};
+
+	gic: interrupt-controller@10300000 {
+		compatible = "arm,cortex-a7-gic";
+		#interrupt-cells = <3>;
+		interrupt-controller;
+		reg = <0x10301000 0x1000>, <0x10302000 0x1000>;
+	};
+
+	clk_3m: clk_3m {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <3000000>;
+	};
+
+	crg: clock-reset-controller@12010000 {
+		compatible = "hisilicon,hi3519-crg";
+		#clock-cells = <1>;
+		#reset-cells = <2>;
+		reg = <0x12010000 0x10000>;
+	};
+
+	soc {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		interrupt-parent = <&gic>;
+		ranges;
+
+		uart0: serial@12100000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x12100000 0x1000>;
+			interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&crg HI3519_UART0_CLK>;
+			clock-names = "apb_pclk";
+			status = "disable";
+		};
+
+		uart1: serial@12101000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x12101000 0x1000>;
+			interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&crg HI3519_UART1_CLK>;
+			clock-names = "apb_pclk";
+			status = "disable";
+		};
+
+		uart2: serial@12102000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x12102000 0x1000>;
+			interrupts = <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&crg HI3519_UART2_CLK>;
+			clock-names = "apb_pclk";
+			status = "disable";
+		};
+
+		uart3: serial@12103000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x12103000 0x1000>;
+			interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&crg HI3519_UART3_CLK>;
+			clock-names = "apb_pclk";
+			status = "disable";
+		};
+
+		uart4: serial@12104000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x12104000 0x1000>;
+			interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&crg HI3519_UART4_CLK>;
+			clock-names = "apb_pclk";
+			status = "disable";
+		};
+
+		dual_timer0: timer@12000000 {
+			compatible = "arm,sp804", "arm,primecell";
+			interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
+			reg = <0x12000000 0x1000>;
+			clocks = <&clk_3m>;
+			clock-names = "apb_pclk";
+			status = "disable";
+		};
+
+		dual_timer1: timer@12001000 {
+			compatible = "arm,sp804", "arm,primecell";
+			interrupts = <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>;
+			reg = <0x12001000 0x1000>;
+			clocks = <&clk_3m>;
+			clock-names = "apb_pclk";
+			status = "disable";
+		};
+
+		dual_timer2: timer@12002000 {
+			compatible = "arm,sp804", "arm,primecell";
+			interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
+			reg = <0x12002000 0x1000>;
+			clocks = <&clk_3m>;
+			clock-names = "apb_pclk";
+			status = "disable";
+		};
+
+		spi_bus0: spi@12120000 {
+			compatible = "arm,pl022", "arm,primecell";
+			reg = <0x12120000 0x1000>;
+			interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&crg HI3519_SPI0_CLK>;
+			clock-names = "apb_pclk";
+			num-cs = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disable";
+		};
+
+		spi_bus1: spi@12121000 {
+			compatible = "arm,pl022", "arm,primecell";
+			reg = <0x12121000 0x1000>;
+			interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&crg HI3519_SPI1_CLK>;
+			clock-names = "apb_pclk";
+			num-cs = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disable";
+		};
+
+		spi_bus2: spi@12122000 {
+			compatible = "arm,pl022", "arm,primecell";
+			reg = <0x12122000 0x1000>;
+			interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&crg HI3519_SPI2_CLK>;
+			clock-names = "apb_pclk";
+			num-cs = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disable";
+		};
+
+		sysctrl: system-controller@12020000 {
+			compatible = "hisilicon,hi3519-sysctrl", "syscon";
+			reg = <0x12020000 0x1000>;
+		};
+
+		reboot {
+			compatible = "syscon-reboot";
+			regmap = <&sysctrl>;
+			offset = <0x4>;
+			mask = <0xdeadbeef>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx1-ads.dts b/arch/arm/boot/dts/imx1-ads.dts
index af4eee5794aa..f50498659cc3 100644
--- a/arch/arm/boot/dts/imx1-ads.dts
+++ b/arch/arm/boot/dts/imx1-ads.dts
@@ -66,14 +66,14 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx1-apf9328.dts b/arch/arm/boot/dts/imx1-apf9328.dts
index 07d92fb40e6f..e8b4b52c2418 100644
--- a/arch/arm/boot/dts/imx1-apf9328.dts
+++ b/arch/arm/boot/dts/imx1-apf9328.dts
@@ -34,14 +34,14 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx23-sansa.dts b/arch/arm/boot/dts/imx23-sansa.dts
new file mode 100644
index 000000000000..4ec32f4c7885
--- /dev/null
+++ b/arch/arm/boot/dts/imx23-sansa.dts
@@ -0,0 +1,207 @@
+/*
+ * Copyright (C) 2013-2016 Marek Vasut <marek.vasut@gmail.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of
+ *     the License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+/dts-v1/;
+#include "imx23.dtsi"
+
+/ {
+	model = "SanDisk Sansa Fuze+";
+	compatible = "sandisk,sansa_fuze_plus", "fsl,imx23";
+
+	memory {
+		reg = <0x40000000 0x04000000>;
+	};
+
+	apb@80000000 {
+		apbh@80000000 {
+			ssp0: ssp@80010000 {
+				compatible = "fsl,imx23-mmc";
+				pinctrl-names = "default";
+				pinctrl-0 = <&mmc0_4bit_pins_a &mmc0_pins_fixup>;
+				bus-width = <4>;
+				vmmc-supply = <&reg_vddio_sd0>;
+				cd-inverted;
+				status = "okay";
+			};
+
+			ssp1: ssp@80034000 {
+				compatible = "fsl,imx23-mmc";
+				pinctrl-names = "default";
+				pinctrl-0 = <&mmc1_8bit_pins_a>;
+				bus-width = <8>;
+				vmmc-supply = <&reg_vddio_sd1>;
+				non-removable;
+				status = "okay";
+			};
+
+			pinctrl@80018000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&hog_pins_a>;
+
+				hog_pins_a: hog@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						MX23_PAD_GPMI_D08__GPIO_0_8
+						MX23_PAD_PWM3__GPIO_1_29
+						MX23_PAD_AUART1_RTS__GPIO_0_27
+						MX23_PAD_AUART1_CTS__GPIO_0_26
+						MX23_PAD_I2C_SCL__I2C_SCL
+						MX23_PAD_I2C_SDA__I2C_SDA
+						MX23_PAD_LCD_DOTCK__GPIO_1_22
+						MX23_PAD_LCD_HSYNC__GPIO_1_24
+						MX23_PAD_PWM3__GPIO_1_29
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <0>;
+				};
+			};
+		};
+
+		apbx@80040000 {
+			pwm: pwm@80064000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pwm2_pins_a>;
+				status = "okay";
+			};
+
+			duart: serial@80070000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&duart_pins_a>;
+				status = "okay";
+			};
+
+			usbphy0: usbphy@8007c000 {
+				status = "okay";
+			};
+
+			lradc@80050000 {
+				status = "okay";
+			};
+		};
+	};
+
+	ahb@80080000 {
+		usb0: usb@80080000 {
+			dr_mode = "peripheral";
+			status = "okay";
+		};
+	};
+
+	reg_vddio_sd0: regulator-vddio-sd0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vddio-sd0";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio0 8 0>;
+	};
+
+	reg_vddio_sd1: regulator-vddio-sd1 {
+		compatible = "regulator-fixed";
+		regulator-name = "vddio-sd1";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio1 29 0>;
+	};
+
+	reg_vdd_touchpad: regulator-vdd-touchpad0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd-touchpad0";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio0 26 0>;
+		regulator-always-on;
+		enable-active-low;
+	};
+
+	reg_vdd_tuner: regulator-vdd-tuner0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd-tuner0";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio0 29 0>;
+		regulator-always-on;
+		enable-active-low;
+	};
+
+	backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm 2 5000000>;
+		brightness-levels = <0 4 8 16 32 64 128 255>;
+		default-brightness-level = <6>;
+	};
+
+	i2c-0 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "i2c-gpio";
+		gpios = <
+			&gpio1 24 0		/* SDA */
+			&gpio1 22 0		/* SCL */
+		>;
+		i2c-gpio,delay-us = <2>;	/* ~100 kHz */
+	};
+
+	i2c-1 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "i2c-gpio";
+		gpios = <
+			&gpio0 31 0		/* SDA */
+			&gpio0 30 0		/* SCL */
+		>;
+		i2c-gpio,delay-us = <2>;	/* ~100 kHz */
+
+		touch: touch@20 {
+			compatible = "synaptics,synaptics_i2c";
+			reg = <0x20>;
+		};
+
+		eeprom: eeprom@50 {
+			compatible = "atmel,24c64";
+			reg = <0x50>;
+			pagesize = <32>;
+		};
+	};
+
+};
diff --git a/arch/arm/boot/dts/imx23-xfi3.dts b/arch/arm/boot/dts/imx23-xfi3.dts
new file mode 100644
index 000000000000..025cf949662d
--- /dev/null
+++ b/arch/arm/boot/dts/imx23-xfi3.dts
@@ -0,0 +1,179 @@
+/*
+ * Copyright (C) 2013-2016 Marek Vasut <marek.vasut@gmail.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of
+ *     the License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+/dts-v1/;
+#include "imx23.dtsi"
+
+/ {
+	model = "Creative ZEN X-Fi3";
+	compatible = "creative,x-fi3", "fsl,imx23";
+
+	memory {
+		reg = <0x40000000 0x04000000>;
+	};
+
+	apb@80000000 {
+		apbh@80000000 {
+			ssp0: ssp@80010000 {
+				compatible = "fsl,imx23-mmc";
+				pinctrl-names = "default";
+				pinctrl-0 = <&mmc0_4bit_pins_a &mmc0_pins_fixup>;
+				bus-width = <4>;
+				vmmc-supply = <&reg_vddio_sd0>;
+				cd-inverted;
+				status = "okay";
+			};
+
+			ssp1: ssp@80034000 {
+				compatible = "fsl,imx23-mmc";
+				pinctrl-names = "default";
+				pinctrl-0 = <&mmc1_4bit_pins_a>;
+				bus-width = <4>;
+				non-removable;
+				status = "okay";
+			};
+
+			pinctrl@80018000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&hog_pins_a>;
+
+				hog_pins_a: hog@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						MX23_PAD_GPMI_D07__GPIO_0_7
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <0>;
+				};
+
+				key_pins_a: keys@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						MX23_PAD_ROTARYA__GPIO_2_7
+						MX23_PAD_ROTARYB__GPIO_2_8
+					>;
+					fsl,drive-strength = <0>;
+					fsl,voltage = <1>;
+					fsl,pull-up = <1>;
+				};
+			};
+		};
+
+		apbx@80040000 {
+			i2c: i2c@80058000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&i2c_pins_a>;
+				status = "okay";
+			};
+
+			pwm: pwm@80064000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&pwm2_pins_a>;
+				status = "okay";
+			};
+
+			duart: serial@80070000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&duart_pins_a>;
+				status = "okay";
+			};
+
+			auart1: serial@8006e000 {
+				pinctrl-names = "default";
+				pinctrl-0 = <&auart1_2pins_a>;
+				status = "okay";
+			};
+
+			usbphy0: usbphy@8007c000 {
+				status = "okay";
+			};
+
+			lradc@80050000 {
+				status = "okay";
+			};
+		};
+	};
+
+	ahb@80080000 {
+		usb0: usb@80080000 {
+			dr_mode = "peripheral";
+			status = "okay";
+		};
+	};
+
+	reg_vddio_sd0: regulator-vddio-sd0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vddio-sd0";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio0 7 0>;
+	};
+
+	backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm 2 5000000>;
+		brightness-levels = <0 4 8 16 32 64 128 255>;
+		default-brightness-level = <6>;
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&key_pins_a>;
+
+		voldown {
+			label = "volume-down";
+			linux,code = <114>;
+			gpios = <&gpio2 7 0>;
+			debounce-interval = <20>;
+		};
+
+		volup {
+			label = "volume-up";
+			linux,code = <115>;
+			gpios = <&gpio2 8 0>;
+			debounce-interval = <20>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi
index 302d1168f424..440ee9a4a158 100644
--- a/arch/arm/boot/dts/imx23.dtsi
+++ b/arch/arm/boot/dts/imx23.dtsi
@@ -111,6 +111,7 @@
 
 				gpio0: gpio@0 {
 					compatible = "fsl,imx23-gpio", "fsl,mxs-gpio";
+					reg = <0>;
 					interrupts = <16>;
 					gpio-controller;
 					#gpio-cells = <2>;
@@ -120,6 +121,7 @@
 
 				gpio1: gpio@1 {
 					compatible = "fsl,imx23-gpio", "fsl,mxs-gpio";
+					reg = <1>;
 					interrupts = <17>;
 					gpio-controller;
 					#gpio-cells = <2>;
@@ -129,6 +131,7 @@
 
 				gpio2: gpio@2 {
 					compatible = "fsl,imx23-gpio", "fsl,mxs-gpio";
+					reg = <2>;
 					interrupts = <18>;
 					gpio-controller;
 					#gpio-cells = <2>;
@@ -171,6 +174,17 @@
 					fsl,pull-up = <MXS_PULL_DISABLE>;
 				};
 
+				auart1_2pins_a: auart1-2pins@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						MX23_PAD_GPMI_D14__AUART2_RX
+						MX23_PAD_GPMI_D15__AUART2_TX
+					>;
+					fsl,drive-strength = <MXS_DRIVE_4mA>;
+					fsl,voltage = <MXS_VOLTAGE_HIGH>;
+					fsl,pull-up = <MXS_PULL_DISABLE>;
+				};
+
 				gpmi_pins_a: gpmi-nand@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
@@ -249,6 +263,40 @@
 					fsl,pull-up = <MXS_PULL_DISABLE>;
 				};
 
+				mmc1_4bit_pins_a: mmc1-4bit@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						MX23_PAD_GPMI_D00__SSP2_DATA0
+						MX23_PAD_GPMI_D01__SSP2_DATA1
+						MX23_PAD_GPMI_D02__SSP2_DATA2
+						MX23_PAD_GPMI_D03__SSP2_DATA3
+						MX23_PAD_GPMI_RDY1__SSP2_CMD
+						MX23_PAD_GPMI_WRN__SSP2_SCK
+					>;
+					fsl,drive-strength = <MXS_DRIVE_8mA>;
+					fsl,voltage = <MXS_VOLTAGE_HIGH>;
+					fsl,pull-up = <MXS_PULL_ENABLE>;
+				};
+
+				mmc1_8bit_pins_a: mmc1-8bit@0 {
+					reg = <0>;
+					fsl,pinmux-ids = <
+						MX23_PAD_GPMI_D00__SSP2_DATA0
+						MX23_PAD_GPMI_D01__SSP2_DATA1
+						MX23_PAD_GPMI_D02__SSP2_DATA2
+						MX23_PAD_GPMI_D03__SSP2_DATA3
+						MX23_PAD_GPMI_D04__SSP2_DATA4
+						MX23_PAD_GPMI_D05__SSP2_DATA5
+						MX23_PAD_GPMI_D06__SSP2_DATA6
+						MX23_PAD_GPMI_D07__SSP2_DATA7
+						MX23_PAD_GPMI_RDY1__SSP2_CMD
+						MX23_PAD_GPMI_WRN__SSP2_SCK
+					>;
+					fsl,drive-strength = <MXS_DRIVE_8mA>;
+					fsl,voltage = <MXS_VOLTAGE_HIGH>;
+					fsl,pull-up = <MXS_PULL_ENABLE>;
+				};
+
 				pwm2_pins_a: pwm2@0 {
 					reg = <0>;
 					fsl,pinmux-ids = <
diff --git a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard.dts b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard.dts
index cda6907a27b9..9300711f1ea3 100644
--- a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard.dts
+++ b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard.dts
@@ -161,14 +161,14 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx25-pdk.dts b/arch/arm/boot/dts/imx25-pdk.dts
index 9351296356dc..70292101ba03 100644
--- a/arch/arm/boot/dts/imx25-pdk.dts
+++ b/arch/arm/boot/dts/imx25-pdk.dts
@@ -298,7 +298,7 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx25-pinfunc.h b/arch/arm/boot/dts/imx25-pinfunc.h
index f96fa2df8f11..f840f03ad171 100644
--- a/arch/arm/boot/dts/imx25-pinfunc.h
+++ b/arch/arm/boot/dts/imx25-pinfunc.h
@@ -26,77 +26,77 @@
 #define MX25_PAD_A13__GPIO_4_1			0x00c 0x22C 0x000 0x05 0x000
 #define MX25_PAD_A13__LCDC_CLS			0x00c 0x22C 0x000 0x07 0x000
 
-#define MX25_PAD_A14__A14			0x010 0x230 0x000 0x10 0x000
-#define MX25_PAD_A14__GPIO_2_0			0x010 0x230 0x000 0x15 0x000
-#define MX25_PAD_A14__SIM1_CLK1			0x010 0x230 0x000 0x16 0x000
-#define MX25_PAD_A14__LCDC_SPL			0x010 0x230 0x000 0x17 0x000
-
-#define MX25_PAD_A15__A15			0x014 0x234 0x000 0x10 0x000
-#define MX25_PAD_A15__GPIO_2_1			0x014 0x234 0x000 0x15 0x000
-#define MX25_PAD_A15__SIM1_RST1			0x014 0x234 0x000 0x16 0x000
-#define MX25_PAD_A15__LCDC_PS			0x014 0x234 0x000 0x17 0x000
-
-#define MX25_PAD_A16__A16			0x018 0x000 0x000 0x10 0x000
-#define MX25_PAD_A16__GPIO_2_2			0x018 0x000 0x000 0x15 0x000
-#define MX25_PAD_A16__SIM1_VEN1			0x018 0x000 0x000 0x16 0x000
-#define MX25_PAD_A16__LCDC_REV			0x018 0x000 0x000 0x17 0x000
-
-#define MX25_PAD_A17__A17			0x01c 0x238 0x000 0x10 0x000
-#define MX25_PAD_A17__GPIO_2_3			0x01c 0x238 0x000 0x15 0x000
-#define MX25_PAD_A17__SIM1_TX			0x01c 0x238 0x554 0x16 0x000
-#define MX25_PAD_A17__FEC_TX_ERR		0x01c 0x238 0x000 0x17 0x000
-
-#define MX25_PAD_A18__A18			0x020 0x23c 0x000 0x10 0x000
-#define MX25_PAD_A18__GPIO_2_4			0x020 0x23c 0x000 0x15 0x000
-#define MX25_PAD_A18__SIM1_PD1			0x020 0x23c 0x550 0x16 0x000
-#define MX25_PAD_A18__FEC_COL			0x020 0x23c 0x504 0x17 0x000
-
-#define MX25_PAD_A19__A19			0x024 0x240 0x000 0x10 0x000
-#define MX25_PAD_A19__GPIO_2_5			0x024 0x240 0x000 0x15 0x000
-#define MX25_PAD_A19__SIM1_RX1			0x024 0x240 0x54c 0x16 0x000
-#define MX25_PAD_A19__FEC_RX_ERR		0x024 0x240 0x518 0x17 0x000
-
-#define MX25_PAD_A20__A20			0x028 0x244 0x000 0x10 0x000
-#define MX25_PAD_A20__GPIO_2_6			0x028 0x244 0x000 0x15 0x000
-#define MX25_PAD_A20__SIM2_CLK1			0x028 0x244 0x000 0x16 0x000
-#define MX25_PAD_A20__FEC_RDATA2		0x028 0x244 0x50c 0x17 0x000
-
-#define MX25_PAD_A21__A21			0x02c 0x248 0x000 0x10 0x000
-#define MX25_PAD_A21__GPIO_2_7			0x02c 0x248 0x000 0x15 0x000
-#define MX25_PAD_A21__SIM2_RST1			0x02c 0x248 0x000 0x16 0x000
-#define MX25_PAD_A21__FEC_RDATA3		0x02c 0x248 0x510 0x17 0x000
-
-#define MX25_PAD_A22__A22			0x030 0x000 0x000 0x10 0x000
-#define MX25_PAD_A22__GPIO_2_8			0x030 0x000 0x000 0x15 0x000
-#define MX25_PAD_A22__FEC_TDATA2		0x030 0x000 0x000 0x17 0x000
-#define MX25_PAD_A22__SIM2_VEN1			0x030 0x000 0x000 0x16 0x000
-#define MX25_PAD_A22__FEC_TDATA2		0x030 0x000 0x000 0x17 0x000
-
-#define MX25_PAD_A23__A23			0x034 0x24c 0x000 0x10 0x000
-#define MX25_PAD_A23__GPIO_2_9			0x034 0x24c 0x000 0x15 0x000
-#define MX25_PAD_A23__SIM2_TX1			0x034 0x24c 0x560 0x16 0x000
-#define MX25_PAD_A23__FEC_TDATA3		0x034 0x24c 0x000 0x17 0x000
-
-#define MX25_PAD_A24__A24			0x038 0x250 0x000 0x10 0x000
-#define MX25_PAD_A24__GPIO_2_10			0x038 0x250 0x000 0x15 0x000
-#define MX25_PAD_A24__SIM2_PD1			0x038 0x250 0x55c 0x16 0x000
-#define MX25_PAD_A24__FEC_RX_CLK		0x038 0x250 0x514 0x17 0x000
-
-#define MX25_PAD_A25__A25			0x03c 0x254 0x000 0x10 0x000
-#define MX25_PAD_A25__GPIO_2_11			0x03c 0x254 0x000 0x15 0x000
-#define MX25_PAD_A25__FEC_CRS			0x03c 0x254 0x508 0x17 0x000
-
-#define MX25_PAD_EB0__EB0			0x040 0x258 0x000 0x10 0x000
-#define MX25_PAD_EB0__AUD4_TXD			0x040 0x258 0x464 0x14 0x000
-#define MX25_PAD_EB0__GPIO_2_12			0x040 0x258 0x000 0x15 0x000
-
-#define MX25_PAD_EB1__EB1			0x044 0x25c 0x000 0x10 0x000
-#define MX25_PAD_EB1__AUD4_RXD			0x044 0x25c 0x460 0x14 0x000
-#define MX25_PAD_EB1__GPIO_2_13			0x044 0x25c 0x000 0x15 0x000
-
-#define MX25_PAD_OE__OE				0x048 0x260 0x000 0x10 0x000
-#define MX25_PAD_OE__AUD4_TXC			0x048 0x260 0x000 0x14 0x000
-#define MX25_PAD_OE__GPIO_2_14			0x048 0x260 0x000 0x15 0x000
+#define MX25_PAD_A14__A14			0x010 0x230 0x000 0x00 0x000
+#define MX25_PAD_A14__GPIO_2_0			0x010 0x230 0x000 0x05 0x000
+#define MX25_PAD_A14__SIM1_CLK1			0x010 0x230 0x000 0x06 0x000
+#define MX25_PAD_A14__LCDC_SPL			0x010 0x230 0x000 0x07 0x000
+
+#define MX25_PAD_A15__A15			0x014 0x234 0x000 0x00 0x000
+#define MX25_PAD_A15__GPIO_2_1			0x014 0x234 0x000 0x05 0x000
+#define MX25_PAD_A15__SIM1_RST1			0x014 0x234 0x000 0x06 0x000
+#define MX25_PAD_A15__LCDC_PS			0x014 0x234 0x000 0x07 0x000
+
+#define MX25_PAD_A16__A16			0x018 0x000 0x000 0x00 0x000
+#define MX25_PAD_A16__GPIO_2_2			0x018 0x000 0x000 0x05 0x000
+#define MX25_PAD_A16__SIM1_VEN1			0x018 0x000 0x000 0x06 0x000
+#define MX25_PAD_A16__LCDC_REV			0x018 0x000 0x000 0x07 0x000
+
+#define MX25_PAD_A17__A17			0x01c 0x238 0x000 0x00 0x000
+#define MX25_PAD_A17__GPIO_2_3			0x01c 0x238 0x000 0x05 0x000
+#define MX25_PAD_A17__SIM1_TX			0x01c 0x238 0x554 0x06 0x000
+#define MX25_PAD_A17__FEC_TX_ERR		0x01c 0x238 0x000 0x07 0x000
+
+#define MX25_PAD_A18__A18			0x020 0x23c 0x000 0x00 0x000
+#define MX25_PAD_A18__GPIO_2_4			0x020 0x23c 0x000 0x05 0x000
+#define MX25_PAD_A18__SIM1_PD1			0x020 0x23c 0x550 0x06 0x000
+#define MX25_PAD_A18__FEC_COL			0x020 0x23c 0x504 0x07 0x000
+
+#define MX25_PAD_A19__A19			0x024 0x240 0x000 0x00 0x000
+#define MX25_PAD_A19__GPIO_2_5			0x024 0x240 0x000 0x05 0x000
+#define MX25_PAD_A19__SIM1_RX1			0x024 0x240 0x54c 0x06 0x000
+#define MX25_PAD_A19__FEC_RX_ERR		0x024 0x240 0x518 0x07 0x000
+
+#define MX25_PAD_A20__A20			0x028 0x244 0x000 0x00 0x000
+#define MX25_PAD_A20__GPIO_2_6			0x028 0x244 0x000 0x05 0x000
+#define MX25_PAD_A20__SIM2_CLK1			0x028 0x244 0x000 0x06 0x000
+#define MX25_PAD_A20__FEC_RDATA2		0x028 0x244 0x50c 0x07 0x000
+
+#define MX25_PAD_A21__A21			0x02c 0x248 0x000 0x00 0x000
+#define MX25_PAD_A21__GPIO_2_7			0x02c 0x248 0x000 0x05 0x000
+#define MX25_PAD_A21__SIM2_RST1			0x02c 0x248 0x000 0x06 0x000
+#define MX25_PAD_A21__FEC_RDATA3		0x02c 0x248 0x510 0x07 0x000
+
+#define MX25_PAD_A22__A22			0x030 0x000 0x000 0x00 0x000
+#define MX25_PAD_A22__GPIO_2_8			0x030 0x000 0x000 0x05 0x000
+#define MX25_PAD_A22__FEC_TDATA2		0x030 0x000 0x000 0x07 0x000
+#define MX25_PAD_A22__SIM2_VEN1			0x030 0x000 0x000 0x06 0x000
+#define MX25_PAD_A22__FEC_TDATA2		0x030 0x000 0x000 0x07 0x000
+
+#define MX25_PAD_A23__A23			0x034 0x24c 0x000 0x00 0x000
+#define MX25_PAD_A23__GPIO_2_9			0x034 0x24c 0x000 0x05 0x000
+#define MX25_PAD_A23__SIM2_TX1			0x034 0x24c 0x560 0x06 0x000
+#define MX25_PAD_A23__FEC_TDATA3		0x034 0x24c 0x000 0x07 0x000
+
+#define MX25_PAD_A24__A24			0x038 0x250 0x000 0x00 0x000
+#define MX25_PAD_A24__GPIO_2_10			0x038 0x250 0x000 0x05 0x000
+#define MX25_PAD_A24__SIM2_PD1			0x038 0x250 0x55c 0x06 0x000
+#define MX25_PAD_A24__FEC_RX_CLK		0x038 0x250 0x514 0x07 0x000
+
+#define MX25_PAD_A25__A25			0x03c 0x254 0x000 0x00 0x000
+#define MX25_PAD_A25__GPIO_2_11			0x03c 0x254 0x000 0x05 0x000
+#define MX25_PAD_A25__FEC_CRS			0x03c 0x254 0x508 0x07 0x000
+
+#define MX25_PAD_EB0__EB0			0x040 0x258 0x000 0x00 0x000
+#define MX25_PAD_EB0__AUD4_TXD			0x040 0x258 0x464 0x04 0x000
+#define MX25_PAD_EB0__GPIO_2_12			0x040 0x258 0x000 0x05 0x000
+
+#define MX25_PAD_EB1__EB1			0x044 0x25c 0x000 0x00 0x000
+#define MX25_PAD_EB1__AUD4_RXD			0x044 0x25c 0x460 0x04 0x000
+#define MX25_PAD_EB1__GPIO_2_13			0x044 0x25c 0x000 0x05 0x000
+
+#define MX25_PAD_OE__OE				0x048 0x260 0x000 0x00 0x000
+#define MX25_PAD_OE__AUD4_TXC			0x048 0x260 0x000 0x04 0x000
+#define MX25_PAD_OE__GPIO_2_14			0x048 0x260 0x000 0x05 0x000
 
 #define MX25_PAD_CS0__CS0			0x04c 0x000 0x000 0x00 0x000
 #define MX25_PAD_CS0__GPIO_4_2			0x04c 0x000 0x000 0x05 0x000
@@ -105,51 +105,51 @@
 #define MX25_PAD_CS1__NF_CE3			0x050 0x000 0x000 0x01 0x000
 #define MX25_PAD_CS1__GPIO_4_3			0x050 0x000 0x000 0x05 0x000
 
-#define MX25_PAD_CS4__CS4			0x054 0x264 0x000 0x10 0x000
+#define MX25_PAD_CS4__CS4			0x054 0x264 0x000 0x00 0x000
 #define MX25_PAD_CS4__NF_CE1			0x054 0x264 0x000 0x01 0x000
-#define MX25_PAD_CS4__UART5_CTS			0x054 0x264 0x000 0x13 0x000
-#define MX25_PAD_CS4__GPIO_3_20			0x054 0x264 0x000 0x15 0x000
+#define MX25_PAD_CS4__UART5_CTS			0x054 0x264 0x000 0x03 0x000
+#define MX25_PAD_CS4__GPIO_3_20			0x054 0x264 0x000 0x05 0x000
 
 #define MX25_PAD_CS5__CS5			0x058 0x268 0x000 0x00 0x000
 #define MX25_PAD_CS5__NF_CE2			0x058 0x268 0x000 0x01 0x000
 #define MX25_PAD_CS5__UART5_RTS			0x058 0x268 0x574 0x03 0x000
 #define MX25_PAD_CS5__GPIO_3_21			0x058 0x268 0x000 0x05 0x000
 
-#define MX25_PAD_NF_CE0__NF_CE0			0x05c 0x26c 0x000 0x10 0x000
-#define MX25_PAD_NF_CE0__GPIO_3_22		0x05c 0x26c 0x000 0x15 0x000
+#define MX25_PAD_NF_CE0__NF_CE0			0x05c 0x26c 0x000 0x00 0x000
+#define MX25_PAD_NF_CE0__GPIO_3_22		0x05c 0x26c 0x000 0x05 0x000
 
-#define MX25_PAD_ECB__ECB			0x060 0x270 0x000 0x10 0x000
-#define MX25_PAD_ECB__UART5_TXD			0x060 0x270 0x000 0x13 0x000
-#define MX25_PAD_ECB__GPIO_3_23			0x060 0x270 0x000 0x15 0x000
+#define MX25_PAD_ECB__ECB			0x060 0x270 0x000 0x00 0x000
+#define MX25_PAD_ECB__UART5_TXD			0x060 0x270 0x000 0x03 0x000
+#define MX25_PAD_ECB__GPIO_3_23			0x060 0x270 0x000 0x05 0x000
 
-#define MX25_PAD_LBA__LBA			0x064 0x274 0x000 0x10 0x000
-#define MX25_PAD_LBA__UART5_RXD			0x064 0x274 0x578 0x13 0x000
-#define MX25_PAD_LBA__GPIO_3_24			0x064 0x274 0x000 0x15 0x000
+#define MX25_PAD_LBA__LBA			0x064 0x274 0x000 0x00 0x000
+#define MX25_PAD_LBA__UART5_RXD			0x064 0x274 0x578 0x03 0x000
+#define MX25_PAD_LBA__GPIO_3_24			0x064 0x274 0x000 0x05 0x000
 
 #define MX25_PAD_BCLK__BCLK			0x068 0x000 0x000 0x00 0x000
 #define MX25_PAD_BCLK__GPIO_4_4			0x068 0x000 0x000 0x05 0x000
 
-#define MX25_PAD_RW__RW				0x06c 0x278 0x000 0x10 0x000
-#define MX25_PAD_RW__AUD4_TXFS			0x06c 0x278 0x474 0x14 0x000
-#define MX25_PAD_RW__GPIO_3_25			0x06c 0x278 0x000 0x15 0x000
+#define MX25_PAD_RW__RW				0x06c 0x278 0x000 0x00 0x000
+#define MX25_PAD_RW__AUD4_TXFS			0x06c 0x278 0x474 0x04 0x000
+#define MX25_PAD_RW__GPIO_3_25			0x06c 0x278 0x000 0x05 0x000
 
-#define MX25_PAD_NFWE_B__NFWE_B			0x070 0x000 0x000 0x10 0x000
-#define MX25_PAD_NFWE_B__GPIO_3_26		0x070 0x000 0x000 0x15 0x000
+#define MX25_PAD_NFWE_B__NFWE_B			0x070 0x000 0x000 0x00 0x000
+#define MX25_PAD_NFWE_B__GPIO_3_26		0x070 0x000 0x000 0x05 0x000
 
-#define MX25_PAD_NFRE_B__NFRE_B			0x074 0x000 0x000 0x10 0x000
-#define MX25_PAD_NFRE_B__GPIO_3_27		0x074 0x000 0x000 0x15 0x000
+#define MX25_PAD_NFRE_B__NFRE_B			0x074 0x000 0x000 0x00 0x000
+#define MX25_PAD_NFRE_B__GPIO_3_27		0x074 0x000 0x000 0x05 0x000
 
-#define MX25_PAD_NFALE__NFALE			0x078 0x000 0x000 0x10 0x000
-#define MX25_PAD_NFALE__GPIO_3_28		0x078 0x000 0x000 0x15 0x000
+#define MX25_PAD_NFALE__NFALE			0x078 0x000 0x000 0x00 0x000
+#define MX25_PAD_NFALE__GPIO_3_28		0x078 0x000 0x000 0x05 0x000
 
-#define MX25_PAD_NFCLE__NFCLE			0x07c 0x000 0x000 0x10 0x000
-#define MX25_PAD_NFCLE__GPIO_3_29		0x07c 0x000 0x000 0x15 0x000
+#define MX25_PAD_NFCLE__NFCLE			0x07c 0x000 0x000 0x00 0x000
+#define MX25_PAD_NFCLE__GPIO_3_29		0x07c 0x000 0x000 0x05 0x000
 
-#define MX25_PAD_NFWP_B__NFWP_B			0x080 0x000 0x000 0x10 0x000
-#define MX25_PAD_NFWP_B__GPIO_3_30		0x080 0x000 0x000 0x15 0x000
+#define MX25_PAD_NFWP_B__NFWP_B			0x080 0x000 0x000 0x00 0x000
+#define MX25_PAD_NFWP_B__GPIO_3_30		0x080 0x000 0x000 0x05 0x000
 
-#define MX25_PAD_NFRB__NFRB			0x084 0x27c 0x000 0x10 0x000
-#define MX25_PAD_NFRB__GPIO_3_31		0x084 0x27c 0x000 0x15 0x000
+#define MX25_PAD_NFRB__NFRB			0x084 0x27c 0x000 0x00 0x000
+#define MX25_PAD_NFRB__GPIO_3_31		0x084 0x27c 0x000 0x05 0x000
 
 #define MX25_PAD_D15__D15			0x088 0x280 0x000 0x00 0x000
 #define MX25_PAD_D15__LD16			0x088 0x280 0x000 0x01 0x000
@@ -210,101 +210,101 @@
 #define MX25_PAD_D0__D0				0x0c4 0x2bc 0x000 0x00 0x000
 #define MX25_PAD_D0__GPIO_4_20			0x0c4 0x2bc 0x000 0x05 0x000
 
-#define MX25_PAD_LD0__LD0			0x0c8 0x2c0 0x000 0x10 0x000
-#define MX25_PAD_LD0__CSI_D0			0x0c8 0x2c0 0x488 0x12 0x000
-#define MX25_PAD_LD0__GPIO_2_15			0x0c8 0x2c0 0x000 0x15 0x000
+#define MX25_PAD_LD0__LD0			0x0c8 0x2c0 0x000 0x00 0x000
+#define MX25_PAD_LD0__CSI_D0			0x0c8 0x2c0 0x488 0x02 0x000
+#define MX25_PAD_LD0__GPIO_2_15			0x0c8 0x2c0 0x000 0x05 0x000
 
-#define MX25_PAD_LD1__LD1			0x0cc 0x2c4 0x000 0x10 0x000
-#define MX25_PAD_LD1__CSI_D1			0x0cc 0x2c4 0x48c 0x12 0x000
-#define MX25_PAD_LD1__GPIO_2_16			0x0cc 0x2c4 0x000 0x15 0x000
+#define MX25_PAD_LD1__LD1			0x0cc 0x2c4 0x000 0x00 0x000
+#define MX25_PAD_LD1__CSI_D1			0x0cc 0x2c4 0x48c 0x02 0x000
+#define MX25_PAD_LD1__GPIO_2_16			0x0cc 0x2c4 0x000 0x05 0x000
 
-#define MX25_PAD_LD2__LD2			0x0d0 0x2c8 0x000 0x10 0x000
-#define MX25_PAD_LD2__GPIO_2_17			0x0d0 0x2c8 0x000 0x15 0x000
+#define MX25_PAD_LD2__LD2			0x0d0 0x2c8 0x000 0x00 0x000
+#define MX25_PAD_LD2__GPIO_2_17			0x0d0 0x2c8 0x000 0x05 0x000
 
-#define MX25_PAD_LD3__LD3			0x0d4 0x2cc 0x000 0x10 0x000
-#define MX25_PAD_LD3__GPIO_2_18			0x0d4 0x2cc 0x000 0x15 0x000
+#define MX25_PAD_LD3__LD3			0x0d4 0x2cc 0x000 0x00 0x000
+#define MX25_PAD_LD3__GPIO_2_18			0x0d4 0x2cc 0x000 0x05 0x000
 
-#define MX25_PAD_LD4__LD4			0x0d8 0x2d0 0x000 0x10 0x000
-#define MX25_PAD_LD4__GPIO_2_19			0x0d8 0x2d0 0x000 0x15 0x000
+#define MX25_PAD_LD4__LD4			0x0d8 0x2d0 0x000 0x00 0x000
+#define MX25_PAD_LD4__GPIO_2_19			0x0d8 0x2d0 0x000 0x05 0x000
 
-#define MX25_PAD_LD5__LD5			0x0dc 0x2d4 0x000 0x10 0x000
-#define MX25_PAD_LD5__GPIO_1_19			0x0dc 0x2d4 0x000 0x15 0x000
+#define MX25_PAD_LD5__LD5			0x0dc 0x2d4 0x000 0x00 0x000
+#define MX25_PAD_LD5__GPIO_1_19			0x0dc 0x2d4 0x000 0x05 0x000
 
-#define MX25_PAD_LD6__LD6			0x0e0 0x2d8 0x000 0x10 0x000
-#define MX25_PAD_LD6__GPIO_1_20			0x0e0 0x2d8 0x000 0x15 0x000
+#define MX25_PAD_LD6__LD6			0x0e0 0x2d8 0x000 0x00 0x000
+#define MX25_PAD_LD6__GPIO_1_20			0x0e0 0x2d8 0x000 0x05 0x000
 
-#define MX25_PAD_LD7__LD7			0x0e4 0x2dc 0x000 0x10 0x000
-#define MX25_PAD_LD7__GPIO_1_21			0x0e4 0x2dc 0x000 0x15 0x000
+#define MX25_PAD_LD7__LD7			0x0e4 0x2dc 0x000 0x00 0x000
+#define MX25_PAD_LD7__GPIO_1_21			0x0e4 0x2dc 0x000 0x05 0x000
 
-#define MX25_PAD_LD8__LD8			0x0e8 0x2e0 0x000 0x10 0x000
-#define MX25_PAD_LD8__UART4_RXD			0x0e8 0x2e0 0x570 0x12 0x000
-#define MX25_PAD_LD8__FEC_TX_ERR		0x0e8 0x2e0 0x000 0x15 0x000
+#define MX25_PAD_LD8__LD8			0x0e8 0x2e0 0x000 0x00 0x000
+#define MX25_PAD_LD8__UART4_RXD			0x0e8 0x2e0 0x570 0x02 0x000
+#define MX25_PAD_LD8__FEC_TX_ERR		0x0e8 0x2e0 0x000 0x05 0x000
 #define MX25_PAD_LD8__SDHC2_CMD			0x0e8 0x2e0 0x4e0 0x06 0x000
 
-#define MX25_PAD_LD9__LD9			0x0ec 0x2e4 0x000 0x10 0x000
-#define MX25_PAD_LD9__UART4_TXD			0x0ec 0x2e4 0x000 0x12 0x000
-#define MX25_PAD_LD9__FEC_COL			0x0ec 0x2e4 0x504 0x15 0x001
+#define MX25_PAD_LD9__LD9			0x0ec 0x2e4 0x000 0x00 0x000
+#define MX25_PAD_LD9__UART4_TXD			0x0ec 0x2e4 0x000 0x02 0x000
+#define MX25_PAD_LD9__FEC_COL			0x0ec 0x2e4 0x504 0x05 0x001
 #define MX25_PAD_LD9__SDHC2_CLK			0x0ec 0x2e4 0x4dc 0x06 0x000
 
 #define MX25_PAD_LD10__LD10			0x0f0 0x2e8 0x000 0x00 0x000
 #define MX25_PAD_LD10__UART4_RTS		0x0f0 0x2e8 0x56c 0x02 0x000
 #define MX25_PAD_LD10__FEC_RX_ERR		0x0f0 0x2e8 0x518 0x05 0x001
 
-#define MX25_PAD_LD11__LD11			0x0f4 0x2ec 0x000 0x10 0x000
-#define MX25_PAD_LD11__UART4_CTS		0x0f4 0x2ec 0x000 0x12 0x000
-#define MX25_PAD_LD11__FEC_RDATA2		0x0f4 0x2ec 0x50c 0x15 0x001
+#define MX25_PAD_LD11__LD11			0x0f4 0x2ec 0x000 0x00 0x000
+#define MX25_PAD_LD11__UART4_CTS		0x0f4 0x2ec 0x000 0x02 0x000
+#define MX25_PAD_LD11__FEC_RDATA2		0x0f4 0x2ec 0x50c 0x05 0x001
 #define MX25_PAD_LD11__SDHC2_DAT1		0x0f4 0x2ec 0x4e8 0x06 0x000
 
-#define MX25_PAD_LD12__LD12			0x0f8 0x2f0 0x000 0x10 0x000
+#define MX25_PAD_LD12__LD12			0x0f8 0x2f0 0x000 0x00 0x000
 #define MX25_PAD_LD12__CSPI2_MOSI		0x0f8 0x2f0 0x4a0 0x02 0x000
-#define MX25_PAD_LD12__FEC_RDATA3		0x0f8 0x2f0 0x510 0x15 0x001
+#define MX25_PAD_LD12__FEC_RDATA3		0x0f8 0x2f0 0x510 0x05 0x001
 
-#define MX25_PAD_LD13__LD13			0x0fc 0x2f4 0x000 0x10 0x000
+#define MX25_PAD_LD13__LD13			0x0fc 0x2f4 0x000 0x00 0x000
 #define MX25_PAD_LD13__CSPI2_MISO		0x0fc 0x2f4 0x49c 0x02 0x000
-#define MX25_PAD_LD13__FEC_TDATA2		0x0fc 0x2f4 0x000 0x15 0x000
+#define MX25_PAD_LD13__FEC_TDATA2		0x0fc 0x2f4 0x000 0x05 0x000
 
-#define MX25_PAD_LD14__LD14			0x100 0x2f8 0x000 0x10 0x000
+#define MX25_PAD_LD14__LD14			0x100 0x2f8 0x000 0x00 0x000
 #define MX25_PAD_LD14__CSPI2_SCLK		0x100 0x2f8 0x494 0x02 0x000
-#define MX25_PAD_LD14__FEC_TDATA3		0x100 0x2f8 0x000 0x15 0x000
+#define MX25_PAD_LD14__FEC_TDATA3		0x100 0x2f8 0x000 0x05 0x000
 
-#define MX25_PAD_LD15__LD15			0x104 0x2fc 0x000 0x10 0x000
+#define MX25_PAD_LD15__LD15			0x104 0x2fc 0x000 0x00 0x000
 #define MX25_PAD_LD15__CSPI2_RDY		0x104 0x2fc 0x498 0x02 0x000
-#define MX25_PAD_LD15__FEC_RX_CLK		0x104 0x2fc 0x514 0x15 0x001
+#define MX25_PAD_LD15__FEC_RX_CLK		0x104 0x2fc 0x514 0x05 0x001
 
-#define MX25_PAD_HSYNC__HSYNC			0x108 0x300 0x000 0x10 0x000
-#define MX25_PAD_HSYNC__GPIO_1_22		0x108 0x300 0x000 0x15 0x000
+#define MX25_PAD_HSYNC__HSYNC			0x108 0x300 0x000 0x00 0x000
+#define MX25_PAD_HSYNC__GPIO_1_22		0x108 0x300 0x000 0x05 0x000
 
-#define MX25_PAD_VSYNC__VSYNC			0x10c 0x304 0x000 0x10 0x000
-#define MX25_PAD_VSYNC__GPIO_1_23		0x10c 0x304 0x000 0x15 0x000
+#define MX25_PAD_VSYNC__VSYNC			0x10c 0x304 0x000 0x00 0x000
+#define MX25_PAD_VSYNC__GPIO_1_23		0x10c 0x304 0x000 0x05 0x000
 
-#define MX25_PAD_LSCLK__LSCLK			0x110 0x308 0x000 0x10 0x000
-#define MX25_PAD_LSCLK__GPIO_1_24		0x110 0x308 0x000 0x15 0x000
+#define MX25_PAD_LSCLK__LSCLK			0x110 0x308 0x000 0x00 0x000
+#define MX25_PAD_LSCLK__GPIO_1_24		0x110 0x308 0x000 0x05 0x000
 
-#define MX25_PAD_OE_ACD__OE_ACD			0x114 0x30c 0x000 0x10 0x000
+#define MX25_PAD_OE_ACD__OE_ACD			0x114 0x30c 0x000 0x00 0x000
 #define MX25_PAD_OE_ACD__CSPI2_SS0		0x114 0x30c 0x4a4 0x02 0x000
-#define MX25_PAD_OE_ACD__GPIO_1_25		0x114 0x30c 0x000 0x15 0x000
+#define MX25_PAD_OE_ACD__GPIO_1_25		0x114 0x30c 0x000 0x05 0x000
 
-#define MX25_PAD_CONTRAST__CONTRAST		0x118 0x310 0x000 0x10 0x000
-#define MX25_PAD_CONTRAST__CC4			0x118 0x310 0x000 0x11 0x000
-#define MX25_PAD_CONTRAST__PWM4_PWMO		0x118 0x310 0x000 0x14 0x000
-#define MX25_PAD_CONTRAST__FEC_CRS		0x118 0x310 0x508 0x15 0x001
-#define MX25_PAD_CONTRAST__USBH2_PWR		0x118 0x310 0x000 0x16 0x000
+#define MX25_PAD_CONTRAST__CONTRAST		0x118 0x310 0x000 0x00 0x000
+#define MX25_PAD_CONTRAST__CC4			0x118 0x310 0x000 0x01 0x000
+#define MX25_PAD_CONTRAST__PWM4_PWMO		0x118 0x310 0x000 0x04 0x000
+#define MX25_PAD_CONTRAST__FEC_CRS		0x118 0x310 0x508 0x05 0x001
+#define MX25_PAD_CONTRAST__USBH2_PWR		0x118 0x310 0x000 0x06 0x000
 
-#define MX25_PAD_PWM__PWM			0x11c 0x314 0x000 0x10 0x000
-#define MX25_PAD_PWM__GPIO_1_26			0x11c 0x314 0x000 0x15 0x000
-#define MX25_PAD_PWM__USBH2_OC			0x11c 0x314 0x580 0x16 0x001
+#define MX25_PAD_PWM__PWM			0x11c 0x314 0x000 0x00 0x000
+#define MX25_PAD_PWM__GPIO_1_26			0x11c 0x314 0x000 0x05 0x000
+#define MX25_PAD_PWM__USBH2_OC			0x11c 0x314 0x580 0x06 0x001
 
-#define MX25_PAD_CSI_D2__CSI_D2			0x120 0x318 0x000 0x10 0x000
-#define MX25_PAD_CSI_D2__UART5_RXD		0x120 0x318 0x578 0x11 0x001
+#define MX25_PAD_CSI_D2__CSI_D2			0x120 0x318 0x000 0x00 0x000
+#define MX25_PAD_CSI_D2__UART5_RXD		0x120 0x318 0x578 0x01 0x001
 #define MX25_PAD_CSI_D2__SIM1_CLK0		0x120 0x318 0x000 0x04 0x000
-#define MX25_PAD_CSI_D2__GPIO_1_27		0x120 0x318 0x000 0x15 0x000
-#define MX25_PAD_CSI_D2__CSPI3_MOSI		0x120 0x318 0x000 0x17 0x000
+#define MX25_PAD_CSI_D2__GPIO_1_27		0x120 0x318 0x000 0x05 0x000
+#define MX25_PAD_CSI_D2__CSPI3_MOSI		0x120 0x318 0x000 0x07 0x000
 
-#define MX25_PAD_CSI_D3__CSI_D3			0x124 0x31c 0x000 0x10 0x000
-#define MX25_PAD_CSI_D3__UART5_TXD		0x124 0x31c 0x000 0x11 0x000
+#define MX25_PAD_CSI_D3__CSI_D3			0x124 0x31c 0x000 0x00 0x000
+#define MX25_PAD_CSI_D3__UART5_TXD		0x124 0x31c 0x000 0x01 0x000
 #define MX25_PAD_CSI_D3__SIM1_RST0		0x124 0x31c 0x000 0x04 0x000
-#define MX25_PAD_CSI_D3__GPIO_1_28		0x124 0x31c 0x000 0x15 0x000
-#define MX25_PAD_CSI_D3__CSPI3_MISO		0x124 0x31c 0x4b4 0x17 0x001
+#define MX25_PAD_CSI_D3__GPIO_1_28		0x124 0x31c 0x000 0x05 0x000
+#define MX25_PAD_CSI_D3__CSPI3_MISO		0x124 0x31c 0x4b4 0x07 0x001
 
 #define MX25_PAD_CSI_D4__CSI_D4			0x128 0x320 0x000 0x00 0x000
 #define MX25_PAD_CSI_D4__UART5_RTS		0x128 0x320 0x574 0x01 0x001
@@ -312,80 +312,80 @@
 #define MX25_PAD_CSI_D4__GPIO_1_29		0x128 0x320 0x000 0x05 0x000
 #define MX25_PAD_CSI_D4__CSPI3_SCLK		0x128 0x320 0x000 0x07 0x000
 
-#define MX25_PAD_CSI_D5__CSI_D5			0x12c 0x324 0x000 0x10 0x000
-#define MX25_PAD_CSI_D5__UART5_CTS		0x12c 0x324 0x000 0x11 0x000
+#define MX25_PAD_CSI_D5__CSI_D5			0x12c 0x324 0x000 0x00 0x000
+#define MX25_PAD_CSI_D5__UART5_CTS		0x12c 0x324 0x000 0x01 0x000
 #define MX25_PAD_CSI_D5__SIM1_TX0		0x12c 0x324 0x000 0x04 0x000
-#define MX25_PAD_CSI_D5__GPIO_1_30		0x12c 0x324 0x000 0x15 0x000
-#define MX25_PAD_CSI_D5__CSPI3_RDY		0x12c 0x324 0x000 0x17 0x000
+#define MX25_PAD_CSI_D5__GPIO_1_30		0x12c 0x324 0x000 0x05 0x000
+#define MX25_PAD_CSI_D5__CSPI3_RDY		0x12c 0x324 0x000 0x07 0x000
 
-#define MX25_PAD_CSI_D6__CSI_D6			0x130 0x328 0x000 0x10 0x000
-#define MX25_PAD_CSI_D6__SDHC2_CMD		0x130 0x328 0x4e0 0x12 0x001
+#define MX25_PAD_CSI_D6__CSI_D6			0x130 0x328 0x000 0x00 0x000
+#define MX25_PAD_CSI_D6__SDHC2_CMD		0x130 0x328 0x4e0 0x02 0x001
 #define MX25_PAD_CSI_D6__SIM1_PD0		0x130 0x328 0x000 0x04 0x000
-#define MX25_PAD_CSI_D6__GPIO_1_31		0x130 0x328 0x000 0x15 0x000
+#define MX25_PAD_CSI_D6__GPIO_1_31		0x130 0x328 0x000 0x05 0x000
 
-#define MX25_PAD_CSI_D7__CSI_D7			0x134 0x32c 0x000 0x10 0x000
-#define MX25_PAD_CSI_D7__SDHC2_DAT_CLK		0x134 0x32C 0x4dc 0x12 0x001
-#define MX25_PAD_CSI_D7__GPIO_1_6		0x134 0x32c 0x000 0x15 0x000
+#define MX25_PAD_CSI_D7__CSI_D7			0x134 0x32c 0x000 0x00 0x000
+#define MX25_PAD_CSI_D7__SDHC2_DAT_CLK		0x134 0x32C 0x4dc 0x02 0x001
+#define MX25_PAD_CSI_D7__GPIO_1_6		0x134 0x32c 0x000 0x05 0x000
 
-#define MX25_PAD_CSI_D8__CSI_D8			0x138 0x330 0x000 0x10 0x000
-#define MX25_PAD_CSI_D8__AUD6_RXC		0x138 0x330 0x000 0x12 0x000
-#define MX25_PAD_CSI_D8__GPIO_1_7		0x138 0x330 0x000 0x15 0x000
-#define MX25_PAD_CSI_D8__CSPI3_SS2		0x138 0x330 0x4c4 0x17 0x000
+#define MX25_PAD_CSI_D8__CSI_D8			0x138 0x330 0x000 0x00 0x000
+#define MX25_PAD_CSI_D8__AUD6_RXC		0x138 0x330 0x000 0x02 0x000
+#define MX25_PAD_CSI_D8__GPIO_1_7		0x138 0x330 0x000 0x05 0x000
+#define MX25_PAD_CSI_D8__CSPI3_SS2		0x138 0x330 0x4c4 0x07 0x000
 
-#define MX25_PAD_CSI_D9__CSI_D9			0x13c 0x334 0x000 0x10 0x000
-#define MX25_PAD_CSI_D9__AUD6_RXFS		0x13c 0x334 0x000 0x12 0x000
-#define MX25_PAD_CSI_D9__GPIO_4_21		0x13c 0x334 0x000 0x15 0x000
-#define MX25_PAD_CSI_D9__CSPI3_SS3		0x13c 0x334 0x4c8 0x17 0x000
+#define MX25_PAD_CSI_D9__CSI_D9			0x13c 0x334 0x000 0x00 0x000
+#define MX25_PAD_CSI_D9__AUD6_RXFS		0x13c 0x334 0x000 0x02 0x000
+#define MX25_PAD_CSI_D9__GPIO_4_21		0x13c 0x334 0x000 0x05 0x000
+#define MX25_PAD_CSI_D9__CSPI3_SS3		0x13c 0x334 0x4c8 0x07 0x000
 
-#define MX25_PAD_CSI_MCLK__CSI_MCLK		0x140 0x338 0x000 0x10 0x000
-#define MX25_PAD_CSI_MCLK__AUD6_TXD		0x140 0x338 0x000 0x11 0x000
-#define MX25_PAD_CSI_MCLK__SDHC2_DAT0		0x140 0x338 0x4e4 0x12 0x001
-#define MX25_PAD_CSI_MCLK__GPIO_1_8		0x140 0x338 0x000 0x15 0x000
+#define MX25_PAD_CSI_MCLK__CSI_MCLK		0x140 0x338 0x000 0x00 0x000
+#define MX25_PAD_CSI_MCLK__AUD6_TXD		0x140 0x338 0x000 0x01 0x000
+#define MX25_PAD_CSI_MCLK__SDHC2_DAT0		0x140 0x338 0x4e4 0x02 0x001
+#define MX25_PAD_CSI_MCLK__GPIO_1_8		0x140 0x338 0x000 0x05 0x000
 
-#define MX25_PAD_CSI_VSYNC__CSI_VSYNC		0x144 0x33c 0x000 0x10 0x000
-#define MX25_PAD_CSI_VSYNC__AUD6_RXD		0x144 0x33c 0x000 0x11 0x000
-#define MX25_PAD_CSI_VSYNC__SDHC2_DAT1		0x144 0x33c 0x4e8 0x12 0x001
-#define MX25_PAD_CSI_VSYNC__GPIO_1_9		0x144 0x33c 0x000 0x15 0x000
+#define MX25_PAD_CSI_VSYNC__CSI_VSYNC		0x144 0x33c 0x000 0x00 0x000
+#define MX25_PAD_CSI_VSYNC__AUD6_RXD		0x144 0x33c 0x000 0x01 0x000
+#define MX25_PAD_CSI_VSYNC__SDHC2_DAT1		0x144 0x33c 0x4e8 0x02 0x001
+#define MX25_PAD_CSI_VSYNC__GPIO_1_9		0x144 0x33c 0x000 0x05 0x000
 
-#define MX25_PAD_CSI_HSYNC__CSI_HSYNC		0x148 0x340 0x000 0x10 0x000
-#define MX25_PAD_CSI_HSYNC__AUD6_TXC		0x148 0x340 0x000 0x11 0x000
-#define MX25_PAD_CSI_HSYNC__SDHC2_DAT2		0x148 0x340 0x4ec 0x12 0x001
-#define MX25_PAD_CSI_HSYNC__GPIO_1_10		0x148 0x340 0x000 0x15 0x000
+#define MX25_PAD_CSI_HSYNC__CSI_HSYNC		0x148 0x340 0x000 0x00 0x000
+#define MX25_PAD_CSI_HSYNC__AUD6_TXC		0x148 0x340 0x000 0x01 0x000
+#define MX25_PAD_CSI_HSYNC__SDHC2_DAT2		0x148 0x340 0x4ec 0x02 0x001
+#define MX25_PAD_CSI_HSYNC__GPIO_1_10		0x148 0x340 0x000 0x05 0x000
 
-#define MX25_PAD_CSI_PIXCLK__CSI_PIXCLK		0x14c 0x344 0x000 0x10 0x000
-#define MX25_PAD_CSI_PIXCLK__AUD6_TXFS		0x14c 0x344 0x000 0x11 0x000
-#define MX25_PAD_CSI_PIXCLK__SDHC2_DAT3		0x14c 0x344 0x4f0 0x12 0x001
-#define MX25_PAD_CSI_PIXCLK__GPIO_1_11		0x14c 0x344 0x000 0x15 0x000
+#define MX25_PAD_CSI_PIXCLK__CSI_PIXCLK		0x14c 0x344 0x000 0x00 0x000
+#define MX25_PAD_CSI_PIXCLK__AUD6_TXFS		0x14c 0x344 0x000 0x01 0x000
+#define MX25_PAD_CSI_PIXCLK__SDHC2_DAT3		0x14c 0x344 0x4f0 0x02 0x001
+#define MX25_PAD_CSI_PIXCLK__GPIO_1_11		0x14c 0x344 0x000 0x05 0x000
 
-#define MX25_PAD_I2C1_CLK__I2C1_CLK		0x150 0x348 0x000 0x10 0x000
-#define MX25_PAD_I2C1_CLK__GPIO_1_12		0x150 0x348 0x000 0x15 0x000
+#define MX25_PAD_I2C1_CLK__I2C1_CLK		0x150 0x348 0x000 0x00 0x000
+#define MX25_PAD_I2C1_CLK__GPIO_1_12		0x150 0x348 0x000 0x05 0x000
 
-#define MX25_PAD_I2C1_DAT__I2C1_DAT		0x154 0x34c 0x000 0x10 0x000
-#define MX25_PAD_I2C1_DAT__GPIO_1_13		0x154 0x34c 0x000 0x15 0x000
+#define MX25_PAD_I2C1_DAT__I2C1_DAT		0x154 0x34c 0x000 0x00 0x000
+#define MX25_PAD_I2C1_DAT__GPIO_1_13		0x154 0x34c 0x000 0x05 0x000
 
-#define MX25_PAD_CSPI1_MOSI__CSPI1_MOSI		0x158 0x350 0x000 0x10 0x000
-#define MX25_PAD_CSPI1_MOSI__UART3_RXD		0x158 0x350 0x568 0x12 0x000
-#define MX25_PAD_CSPI1_MOSI__GPIO_1_14		0x158 0x350 0x000 0x15 0x000
+#define MX25_PAD_CSPI1_MOSI__CSPI1_MOSI		0x158 0x350 0x000 0x00 0x000
+#define MX25_PAD_CSPI1_MOSI__UART3_RXD		0x158 0x350 0x568 0x02 0x000
+#define MX25_PAD_CSPI1_MOSI__GPIO_1_14		0x158 0x350 0x000 0x05 0x000
 
-#define MX25_PAD_CSPI1_MISO__CSPI1_MISO		0x15c 0x354 0x000 0x10 0x000
-#define MX25_PAD_CSPI1_MISO__UART3_TXD		0x15c 0x354 0x000 0x12 0x000
-#define MX25_PAD_CSPI1_MISO__GPIO_1_15		0x15c 0x354 0x000 0x15 0x000
+#define MX25_PAD_CSPI1_MISO__CSPI1_MISO		0x15c 0x354 0x000 0x00 0x000
+#define MX25_PAD_CSPI1_MISO__UART3_TXD		0x15c 0x354 0x000 0x02 0x000
+#define MX25_PAD_CSPI1_MISO__GPIO_1_15		0x15c 0x354 0x000 0x05 0x000
 
-#define MX25_PAD_CSPI1_SS0__CSPI1_SS0		0x160 0x358 0x000 0x10 0x000
-#define MX25_PAD_CSPI1_SS0__PWM2_PWMO		0x160 0x358 0x000 0x12 0x000
-#define MX25_PAD_CSPI1_SS0__GPIO_1_16		0x160 0x358 0x000 0x15 0x000
+#define MX25_PAD_CSPI1_SS0__CSPI1_SS0		0x160 0x358 0x000 0x00 0x000
+#define MX25_PAD_CSPI1_SS0__PWM2_PWMO		0x160 0x358 0x000 0x02 0x000
+#define MX25_PAD_CSPI1_SS0__GPIO_1_16		0x160 0x358 0x000 0x05 0x000
 
 #define MX25_PAD_CSPI1_SS1__CSPI1_SS1		0x164 0x35c 0x000 0x00 0x000
 #define MX25_PAD_CSPI1_SS1__I2C3_DAT		0x164 0x35C 0x528 0x01 0x001
 #define MX25_PAD_CSPI1_SS1__UART3_RTS		0x164 0x35c 0x000 0x02 0x000
 #define MX25_PAD_CSPI1_SS1__GPIO_1_17		0x164 0x35c 0x000 0x05 0x000
 
-#define MX25_PAD_CSPI1_SCLK__CSPI1_SCLK		0x168 0x360 0x000 0x10 0x000
-#define MX25_PAD_CSPI1_SCLK__UART3_CTS		0x168 0x360 0x000 0x12 0x000
-#define MX25_PAD_CSPI1_SCLK__GPIO_1_18		0x168 0x360 0x000 0x15 0x000
+#define MX25_PAD_CSPI1_SCLK__CSPI1_SCLK		0x168 0x360 0x000 0x00 0x000
+#define MX25_PAD_CSPI1_SCLK__UART3_CTS		0x168 0x360 0x000 0x02 0x000
+#define MX25_PAD_CSPI1_SCLK__GPIO_1_18		0x168 0x360 0x000 0x05 0x000
 
-#define MX25_PAD_CSPI1_RDY__CSPI1_RDY		0x16c 0x364 0x000 0x10 0x000
-#define MX25_PAD_CSPI1_RDY__GPIO_2_22		0x16c 0x364 0x000 0x15 0x000
+#define MX25_PAD_CSPI1_RDY__CSPI1_RDY		0x16c 0x364 0x000 0x00 0x000
+#define MX25_PAD_CSPI1_RDY__GPIO_2_22		0x16c 0x364 0x000 0x05 0x000
 
 #define MX25_PAD_UART1_RXD__UART1_RXD		0x170 0x368 0x000 0x00 0x000
 #define MX25_PAD_UART1_RXD__UART2_DTR		0x170 0x368 0x000 0x03 0x000
@@ -406,46 +406,55 @@
 #define MX25_PAD_UART1_CTS__UART2_RI		0x17c 0x374 0x000 0x03 0x001
 #define MX25_PAD_UART1_CTS__GPIO_4_25		0x17c 0x374 0x000 0x05 0x000
 
-#define MX25_PAD_UART2_RXD__UART2_RXD		0x180 0x378 0x000 0x10 0x000
-#define MX25_PAD_UART2_RXD__GPIO_4_26		0x180 0x378 0x000 0x15 0x000
+#define MX25_PAD_UART2_RXD__UART2_RXD		0x180 0x378 0x000 0x00 0x000
+#define MX25_PAD_UART2_RXD__GPIO_4_26		0x180 0x378 0x000 0x05 0x000
 
-#define MX25_PAD_UART2_TXD__UART2_TXD		0x184 0x37c 0x000 0x10 0x000
-#define MX25_PAD_UART2_TXD__GPIO_4_27		0x184 0x37c 0x000 0x15 0x000
+#define MX25_PAD_UART2_TXD__UART2_TXD		0x184 0x37c 0x000 0x00 0x000
+#define MX25_PAD_UART2_TXD__GPIO_4_27		0x184 0x37c 0x000 0x05 0x000
 
 #define MX25_PAD_UART2_RTS__UART2_RTS		0x188 0x380 0x000 0x00 0x000
 #define MX25_PAD_UART2_RTS__FEC_COL		0x188 0x380 0x504 0x02 0x002
 #define MX25_PAD_UART2_RTS__CC1			0x188 0x380 0x000 0x03 0x000
 #define MX25_PAD_UART2_RTS__GPIO_4_28		0x188 0x380 0x000 0x05 0x000
 
-#define MX25_PAD_UART2_CTS__UART2_CTS		0x18c 0x384 0x000 0x10 0x000
-#define MX25_PAD_UART2_CTS__FEC_RX_ERR		0x18c 0x384 0x518 0x12 0x002
-#define MX25_PAD_UART2_CTS__GPIO_4_29		0x18c 0x384 0x000 0x15 0x000
+#define MX25_PAD_UART2_CTS__UART2_CTS		0x18c 0x384 0x000 0x00 0x000
+#define MX25_PAD_UART2_CTS__FEC_RX_ERR		0x18c 0x384 0x518 0x02 0x002
+#define MX25_PAD_UART2_CTS__GPIO_4_29		0x18c 0x384 0x000 0x05 0x000
 
+/*
+ * Removing the SION bit from MX25_PAD_SD1_CMD__SD1_CMD breaks detecting an SD
+ * card. According to the i.MX25 reference manual (e.g. Figure 23-2 in IMX25RM
+ * Rev. 2 from 01/2011) this pin is bidirectional. So it seems to be a silicon
+ * bug that configuring the SD1_CMD function doesn't enable the input path for
+ * this pin.
+ * This might have side effects for other hardware units that are connected to
+ * that pin and use the respective function as input.
+ */
 #define MX25_PAD_SD1_CMD__SD1_CMD		0x190 0x388 0x000 0x10 0x000
-#define MX25_PAD_SD1_CMD__CSPI2_MOSI		0x190 0x388 0x4a0 0x11 0x001
-#define MX25_PAD_SD1_CMD__FEC_RDATA2		0x190 0x388 0x50c 0x12 0x002
-#define MX25_PAD_SD1_CMD__GPIO_2_23		0x190 0x388 0x000 0x15 0x000
+#define MX25_PAD_SD1_CMD__CSPI2_MOSI		0x190 0x388 0x4a0 0x01 0x001
+#define MX25_PAD_SD1_CMD__FEC_RDATA2		0x190 0x388 0x50c 0x02 0x002
+#define MX25_PAD_SD1_CMD__GPIO_2_23		0x190 0x388 0x000 0x05 0x000
 
-#define MX25_PAD_SD1_CLK__SD1_CLK		0x194 0x38c 0x000 0x10 0x000
-#define MX25_PAD_SD1_CLK__CSPI2_MISO		0x194 0x38c 0x49c 0x11 0x001
-#define MX25_PAD_SD1_CLK__FEC_RDATA3		0x194 0x38c 0x510 0x12 0x002
-#define MX25_PAD_SD1_CLK__GPIO_2_24		0x194 0x38c 0x000 0x15 0x000
+#define MX25_PAD_SD1_CLK__SD1_CLK		0x194 0x38c 0x000 0x00 0x000
+#define MX25_PAD_SD1_CLK__CSPI2_MISO		0x194 0x38c 0x49c 0x01 0x001
+#define MX25_PAD_SD1_CLK__FEC_RDATA3		0x194 0x38c 0x510 0x02 0x002
+#define MX25_PAD_SD1_CLK__GPIO_2_24		0x194 0x38c 0x000 0x05 0x000
 
-#define MX25_PAD_SD1_DATA0__SD1_DATA0		0x198 0x390 0x000 0x10 0x000
-#define MX25_PAD_SD1_DATA0__CSPI2_SCLK		0x198 0x390 0x494 0x11 0x001
-#define MX25_PAD_SD1_DATA0__GPIO_2_25		0x198 0x390 0x000 0x15 0x000
+#define MX25_PAD_SD1_DATA0__SD1_DATA0		0x198 0x390 0x000 0x00 0x000
+#define MX25_PAD_SD1_DATA0__CSPI2_SCLK		0x198 0x390 0x494 0x01 0x001
+#define MX25_PAD_SD1_DATA0__GPIO_2_25		0x198 0x390 0x000 0x05 0x000
 
-#define MX25_PAD_SD1_DATA1__SD1_DATA1		0x19c 0x394 0x000 0x10 0x000
-#define MX25_PAD_SD1_DATA1__AUD7_RXD		0x19c 0x394 0x478 0x13 0x000
-#define MX25_PAD_SD1_DATA1__GPIO_2_26		0x19c 0x394 0x000 0x15 0x000
+#define MX25_PAD_SD1_DATA1__SD1_DATA1		0x19c 0x394 0x000 0x00 0x000
+#define MX25_PAD_SD1_DATA1__AUD7_RXD		0x19c 0x394 0x478 0x03 0x000
+#define MX25_PAD_SD1_DATA1__GPIO_2_26		0x19c 0x394 0x000 0x05 0x000
 
-#define MX25_PAD_SD1_DATA2__SD1_DATA2		0x1a0 0x398 0x000 0x10 0x000
-#define MX25_PAD_SD1_DATA2__FEC_RX_CLK		0x1a0 0x398 0x514 0x12 0x002
-#define MX25_PAD_SD1_DATA2__GPIO_2_27		0x1a0 0x398 0x000 0x15 0x000
+#define MX25_PAD_SD1_DATA2__SD1_DATA2		0x1a0 0x398 0x000 0x00 0x000
+#define MX25_PAD_SD1_DATA2__FEC_RX_CLK		0x1a0 0x398 0x514 0x02 0x002
+#define MX25_PAD_SD1_DATA2__GPIO_2_27		0x1a0 0x398 0x000 0x05 0x000
 
-#define MX25_PAD_SD1_DATA3__SD1_DATA3		0x1a4 0x39c 0x000 0x10 0x000
-#define MX25_PAD_SD1_DATA3__FEC_CRS		0x1a4 0x39c 0x508 0x12 0x002
-#define MX25_PAD_SD1_DATA3__GPIO_2_28		0x1a4 0x39c 0x000 0x15 0x000
+#define MX25_PAD_SD1_DATA3__SD1_DATA3		0x1a4 0x39c 0x000 0x00 0x000
+#define MX25_PAD_SD1_DATA3__FEC_CRS		0x1a4 0x39c 0x508 0x02 0x002
+#define MX25_PAD_SD1_DATA3__GPIO_2_28		0x1a4 0x39c 0x000 0x05 0x000
 
 #define MX25_PAD_KPP_ROW0__KPP_ROW0		0x1a8 0x3a0 0x000 0x00 0x000
 #define MX25_PAD_KPP_ROW0__UART3_RXD		0x1a8 0x3a0 0x568 0x01 0x001
@@ -469,123 +478,123 @@
 #define MX25_PAD_KPP_ROW3__UART1_RI		0x1b4 0x3ac 0x000 0x04 0x000
 #define MX25_PAD_KPP_ROW3__GPIO_3_0		0x1b4 0x3ac 0x000 0x05 0x000
 
-#define MX25_PAD_KPP_COL0__KPP_COL0		0x1b8 0x3b0 0x000 0x10 0x000
-#define MX25_PAD_KPP_COL0__UART4_RXD		0x1b8 0x3b0 0x570 0x11 0x001
-#define MX25_PAD_KPP_COL0__AUD5_TXD		0x1b8 0x3b0 0x000 0x12 0x000
-#define MX25_PAD_KPP_COL0__GPIO_3_1		0x1b8 0x3b0 0x000 0x15 0x000
+#define MX25_PAD_KPP_COL0__KPP_COL0		0x1b8 0x3b0 0x000 0x00 0x000
+#define MX25_PAD_KPP_COL0__UART4_RXD		0x1b8 0x3b0 0x570 0x01 0x001
+#define MX25_PAD_KPP_COL0__AUD5_TXD		0x1b8 0x3b0 0x000 0x02 0x000
+#define MX25_PAD_KPP_COL0__GPIO_3_1		0x1b8 0x3b0 0x000 0x05 0x000
 
-#define MX25_PAD_KPP_COL1__KPP_COL1		0x1bc 0x3b4 0x000 0x10 0x000
-#define MX25_PAD_KPP_COL1__UART4_TXD		0x1bc 0x3b4 0x000 0x11 0x000
-#define MX25_PAD_KPP_COL1__AUD5_RXD		0x1bc 0x3b4 0x000 0x12 0x000
-#define MX25_PAD_KPP_COL1__GPIO_3_2		0x1bc 0x3b4 0x000 0x15 0x000
+#define MX25_PAD_KPP_COL1__KPP_COL1		0x1bc 0x3b4 0x000 0x00 0x000
+#define MX25_PAD_KPP_COL1__UART4_TXD		0x1bc 0x3b4 0x000 0x01 0x000
+#define MX25_PAD_KPP_COL1__AUD5_RXD		0x1bc 0x3b4 0x000 0x02 0x000
+#define MX25_PAD_KPP_COL1__GPIO_3_2		0x1bc 0x3b4 0x000 0x05 0x000
 
 #define MX25_PAD_KPP_COL2__KPP_COL2		0x1c0 0x3b8 0x000 0x00 0x000
 #define MX25_PAD_KPP_COL2__UART4_RTS		0x1c0 0x3b8 0x56c 0x01 0x001
 #define MX25_PAD_KPP_COL2__AUD5_TXC		0x1c0 0x3b8 0x000 0x02 0x000
 #define MX25_PAD_KPP_COL2__GPIO_3_3		0x1c0 0x3b8 0x000 0x05 0x000
 
-#define MX25_PAD_KPP_COL3__KPP_COL3		0x1c4 0x3bc 0x000 0x10 0x000
-#define MX25_PAD_KPP_COL3__UART4_CTS		0x1c4 0x3bc 0x000 0x11 0x000
-#define MX25_PAD_KPP_COL3__AUD5_TXFS		0x1c4 0x3bc 0x000 0x12 0x000
-#define MX25_PAD_KPP_COL3__GPIO_3_4		0x1c4 0x3bc 0x000 0x15 0x000
+#define MX25_PAD_KPP_COL3__KPP_COL3		0x1c4 0x3bc 0x000 0x00 0x000
+#define MX25_PAD_KPP_COL3__UART4_CTS		0x1c4 0x3bc 0x000 0x01 0x000
+#define MX25_PAD_KPP_COL3__AUD5_TXFS		0x1c4 0x3bc 0x000 0x02 0x000
+#define MX25_PAD_KPP_COL3__GPIO_3_4		0x1c4 0x3bc 0x000 0x05 0x000
 
-#define MX25_PAD_FEC_MDC__FEC_MDC		0x1c8 0x3c0 0x000 0x10 0x000
-#define MX25_PAD_FEC_MDC__AUD4_TXD		0x1c8 0x3c0 0x464 0x12 0x001
-#define MX25_PAD_FEC_MDC__GPIO_3_5		0x1c8 0x3c0 0x000 0x15 0x000
+#define MX25_PAD_FEC_MDC__FEC_MDC		0x1c8 0x3c0 0x000 0x00 0x000
+#define MX25_PAD_FEC_MDC__AUD4_TXD		0x1c8 0x3c0 0x464 0x02 0x001
+#define MX25_PAD_FEC_MDC__GPIO_3_5		0x1c8 0x3c0 0x000 0x05 0x000
 
-#define MX25_PAD_FEC_MDIO__FEC_MDIO		0x1cc 0x3c4 0x000 0x10 0x000
-#define MX25_PAD_FEC_MDIO__AUD4_RXD		0x1cc 0x3c4 0x460 0x12 0x001
-#define MX25_PAD_FEC_MDIO__GPIO_3_6		0x1cc 0x3c4 0x000 0x15 0x000
+#define MX25_PAD_FEC_MDIO__FEC_MDIO		0x1cc 0x3c4 0x000 0x00 0x000
+#define MX25_PAD_FEC_MDIO__AUD4_RXD		0x1cc 0x3c4 0x460 0x02 0x001
+#define MX25_PAD_FEC_MDIO__GPIO_3_6		0x1cc 0x3c4 0x000 0x05 0x000
 
-#define MX25_PAD_FEC_TDATA0__FEC_TDATA0		0x1d0 0x3c8 0x000 0x10 0x000
-#define MX25_PAD_FEC_TDATA0__GPIO_3_7		0x1d0 0x3c8 0x000 0x15 0x000
+#define MX25_PAD_FEC_TDATA0__FEC_TDATA0		0x1d0 0x3c8 0x000 0x00 0x000
+#define MX25_PAD_FEC_TDATA0__GPIO_3_7		0x1d0 0x3c8 0x000 0x05 0x000
 
-#define MX25_PAD_FEC_TDATA1__FEC_TDATA1		0x1d4 0x3cc 0x000 0x10 0x000
-#define MX25_PAD_FEC_TDATA1__AUD4_TXFS		0x1d4 0x3cc 0x474 0x12 0x001
-#define MX25_PAD_FEC_TDATA1__GPIO_3_8		0x1d4 0x3cc 0x000 0x15 0x000
+#define MX25_PAD_FEC_TDATA1__FEC_TDATA1		0x1d4 0x3cc 0x000 0x00 0x000
+#define MX25_PAD_FEC_TDATA1__AUD4_TXFS		0x1d4 0x3cc 0x474 0x02 0x001
+#define MX25_PAD_FEC_TDATA1__GPIO_3_8		0x1d4 0x3cc 0x000 0x05 0x000
 
-#define MX25_PAD_FEC_TX_EN__FEC_TX_EN		0x1d8 0x3d0 0x000 0x10 0x000
-#define MX25_PAD_FEC_TX_EN__GPIO_3_9		0x1d8 0x3d0 0x000 0x15 0x000
+#define MX25_PAD_FEC_TX_EN__FEC_TX_EN		0x1d8 0x3d0 0x000 0x00 0x000
+#define MX25_PAD_FEC_TX_EN__GPIO_3_9		0x1d8 0x3d0 0x000 0x05 0x000
 
-#define MX25_PAD_FEC_RDATA0__FEC_RDATA0		0x1dc 0x3d4 0x000 0x10 0x000
-#define MX25_PAD_FEC_RDATA0__GPIO_3_10		0x1dc 0x3d4 0x000 0x15 0x000
+#define MX25_PAD_FEC_RDATA0__FEC_RDATA0		0x1dc 0x3d4 0x000 0x00 0x000
+#define MX25_PAD_FEC_RDATA0__GPIO_3_10		0x1dc 0x3d4 0x000 0x05 0x000
 
-#define MX25_PAD_FEC_RDATA1__FEC_RDATA1		0x1e0 0x3d8 0x000 0x10 0x000
+#define MX25_PAD_FEC_RDATA1__FEC_RDATA1		0x1e0 0x3d8 0x000 0x00 0x000
 /*
  * According to the i.MX25 Reference manual (IMX25RM, Rev. 2,
  * 01/2011) this is CAN1_TX but that's wrong.
  */
-#define MX25_PAD_FEC_RDATA1__CAN2_TX		0x1e0 0x3d8 0x000 0x14 0x000
-#define MX25_PAD_FEC_RDATA1__GPIO_3_11		0x1e0 0x3d8 0x000 0x15 0x000
+#define MX25_PAD_FEC_RDATA1__CAN2_TX		0x1e0 0x3d8 0x000 0x04 0x000
+#define MX25_PAD_FEC_RDATA1__GPIO_3_11		0x1e0 0x3d8 0x000 0x05 0x000
 
-#define MX25_PAD_FEC_RX_DV__FEC_RX_DV		0x1e4 0x3dc 0x000 0x10 0x000
+#define MX25_PAD_FEC_RX_DV__FEC_RX_DV		0x1e4 0x3dc 0x000 0x00 0x000
 /*
  * According to the i.MX25 Reference manual (IMX25RM, Rev. 2,
  * 01/2011) this is CAN1_RX but that's wrong.
  */
-#define MX25_PAD_FEC_RX_DV__CAN2_RX		0x1e4 0x3dc 0x484 0x14 0x000
-#define MX25_PAD_FEC_RX_DV__GPIO_3_12		0x1e4 0x3dc 0x000 0x15 0x000
+#define MX25_PAD_FEC_RX_DV__CAN2_RX		0x1e4 0x3dc 0x484 0x04 0x000
+#define MX25_PAD_FEC_RX_DV__GPIO_3_12		0x1e4 0x3dc 0x000 0x05 0x000
 
-#define MX25_PAD_FEC_TX_CLK__FEC_TX_CLK		0x1e8 0x3e0 0x000 0x10 0x000
-#define MX25_PAD_FEC_TX_CLK__GPIO_3_13		0x1e8 0x3e0 0x000 0x15 0x000
+#define MX25_PAD_FEC_TX_CLK__FEC_TX_CLK		0x1e8 0x3e0 0x000 0x00 0x000
+#define MX25_PAD_FEC_TX_CLK__GPIO_3_13		0x1e8 0x3e0 0x000 0x05 0x000
 
-#define MX25_PAD_RTCK__RTCK			0x1ec 0x3e4 0x000 0x10 0x000
-#define MX25_PAD_RTCK__OWIRE			0x1ec 0x3e4 0x000 0x11 0x000
-#define MX25_PAD_RTCK__GPIO_3_14		0x1ec 0x3e4 0x000 0x15 0x000
+#define MX25_PAD_RTCK__RTCK			0x1ec 0x3e4 0x000 0x00 0x000
+#define MX25_PAD_RTCK__OWIRE			0x1ec 0x3e4 0x000 0x01 0x000
+#define MX25_PAD_RTCK__GPIO_3_14		0x1ec 0x3e4 0x000 0x05 0x000
 
-#define MX25_PAD_DE_B__DE_B			0x1f0 0x3ec 0x000 0x10 0x000
-#define MX25_PAD_DE_B__GPIO_2_20		0x1f0 0x3ec 0x000 0x15 0x000
+#define MX25_PAD_DE_B__DE_B			0x1f0 0x3ec 0x000 0x00 0x000
+#define MX25_PAD_DE_B__GPIO_2_20		0x1f0 0x3ec 0x000 0x05 0x000
 
-#define MX25_PAD_GPIO_A__GPIO_A			0x1f4 0x3f0 0x000 0x10 0x000
-#define MX25_PAD_GPIO_A__CAN1_TX		0x1f4 0x3f0 0x000 0x16 0x000
-#define MX25_PAD_GPIO_A__USBOTG_PWR		0x1f4 0x3f0 0x000 0x12 0x000
+#define MX25_PAD_GPIO_A__GPIO_A			0x1f4 0x3f0 0x000 0x00 0x000
+#define MX25_PAD_GPIO_A__CAN1_TX		0x1f4 0x3f0 0x000 0x06 0x000
+#define MX25_PAD_GPIO_A__USBOTG_PWR		0x1f4 0x3f0 0x000 0x02 0x000
 
-#define MX25_PAD_GPIO_B__GPIO_B			0x1f8 0x3f4 0x000 0x10 0x000
-#define MX25_PAD_GPIO_B__USBOTG_OC		0x1f8 0x3f4 0x57c 0x12 0x001
-#define MX25_PAD_GPIO_B__CAN1_RX		0x1f8 0x3f4 0x480 0x16 0x001
+#define MX25_PAD_GPIO_B__GPIO_B			0x1f8 0x3f4 0x000 0x00 0x000
+#define MX25_PAD_GPIO_B__USBOTG_OC		0x1f8 0x3f4 0x57c 0x02 0x001
+#define MX25_PAD_GPIO_B__CAN1_RX		0x1f8 0x3f4 0x480 0x06 0x001
 
-#define MX25_PAD_GPIO_C__GPIO_C			0x1fc 0x3f8 0x000 0x10 0x000
-#define MX25_PAD_GPIO_C__PWM4_PWMO		0x1fc 0x3f8 0x000 0x11 0x000
-#define MX25_PAD_GPIO_C__I2C2_SCL		0x1fc 0x3f8 0x51c 0x12 0x001
-#define MX25_PAD_GPIO_C__KPP_COL4		0x1fc 0x3f8 0x52c 0x13 0x001
-#define MX25_PAD_GPIO_C__CAN2_TX		0x1fc 0x3f8 0x000 0x16 0x000
+#define MX25_PAD_GPIO_C__GPIO_C			0x1fc 0x3f8 0x000 0x00 0x000
+#define MX25_PAD_GPIO_C__PWM4_PWMO		0x1fc 0x3f8 0x000 0x01 0x000
+#define MX25_PAD_GPIO_C__I2C2_SCL		0x1fc 0x3f8 0x51c 0x02 0x001
+#define MX25_PAD_GPIO_C__KPP_COL4		0x1fc 0x3f8 0x52c 0x03 0x001
+#define MX25_PAD_GPIO_C__CAN2_TX		0x1fc 0x3f8 0x000 0x06 0x000
 
-#define MX25_PAD_GPIO_D__GPIO_D			0x200 0x3fc 0x000 0x10 0x000
-#define MX25_PAD_GPIO_D__I2C2_SDA		0x200 0x3fc 0x520 0x12 0x001
-#define MX25_PAD_GPIO_D__CAN2_RX		0x200 0x3fc 0x484 0x16 0x001
+#define MX25_PAD_GPIO_D__GPIO_D			0x200 0x3fc 0x000 0x00 0x000
+#define MX25_PAD_GPIO_D__I2C2_SDA		0x200 0x3fc 0x520 0x02 0x001
+#define MX25_PAD_GPIO_D__CAN2_RX		0x200 0x3fc 0x484 0x06 0x001
 
-#define MX25_PAD_GPIO_E__GPIO_E			0x204 0x400 0x000 0x10 0x000
-#define MX25_PAD_GPIO_E__I2C3_CLK		0x204 0x400 0x524 0x11 0x002
-#define MX25_PAD_GPIO_E__LD16			0x204 0x400 0x000 0x12 0x000
-#define MX25_PAD_GPIO_E__AUD7_TXD		0x204 0x400 0x000 0x14 0x000
-#define MX25_PAD_GPIO_E__UART4_RXD		0x204 0x400 0x570 0x16 0x002
+#define MX25_PAD_GPIO_E__GPIO_E			0x204 0x400 0x000 0x00 0x000
+#define MX25_PAD_GPIO_E__I2C3_CLK		0x204 0x400 0x524 0x01 0x002
+#define MX25_PAD_GPIO_E__LD16			0x204 0x400 0x000 0x02 0x000
+#define MX25_PAD_GPIO_E__AUD7_TXD		0x204 0x400 0x000 0x04 0x000
+#define MX25_PAD_GPIO_E__UART4_RXD		0x204 0x400 0x570 0x06 0x002
 
-#define MX25_PAD_GPIO_F__GPIO_F			0x208 0x404 0x000 0x10 0x000
-#define MX25_PAD_GPIO_F__LD17			0x208 0x404 0x000 0x12 0x000
-#define MX25_PAD_GPIO_F__AUD7_TXC		0x208 0x404 0x000 0x14 0x000
-#define MX25_PAD_GPIO_F__UART4_TXD		0x208 0x404 0x000 0x16 0x000
+#define MX25_PAD_GPIO_F__GPIO_F			0x208 0x404 0x000 0x00 0x000
+#define MX25_PAD_GPIO_F__LD17			0x208 0x404 0x000 0x02 0x000
+#define MX25_PAD_GPIO_F__AUD7_TXC		0x208 0x404 0x000 0x04 0x000
+#define MX25_PAD_GPIO_F__UART4_TXD		0x208 0x404 0x000 0x06 0x000
 
-#define MX25_PAD_EXT_ARMCLK__EXT_ARMCLK		0x20c 0x000 0x000 0x10 0x000
-#define MX25_PAD_EXT_ARMCLK__GPIO_3_15		0x20c 0x000 0x000 0x15 0x000
+#define MX25_PAD_EXT_ARMCLK__EXT_ARMCLK		0x20c 0x000 0x000 0x00 0x000
+#define MX25_PAD_EXT_ARMCLK__GPIO_3_15		0x20c 0x000 0x000 0x05 0x000
 
-#define MX25_PAD_UPLL_BYPCLK__UPLL_BYPCLK	0x210 0x000 0x000 0x10 0x000
-#define MX25_PAD_UPLL_BYPCLK__GPIO_3_16		0x210 0x000 0x000 0x15 0x000
+#define MX25_PAD_UPLL_BYPCLK__UPLL_BYPCLK	0x210 0x000 0x000 0x00 0x000
+#define MX25_PAD_UPLL_BYPCLK__GPIO_3_16		0x210 0x000 0x000 0x05 0x000
 
 #define MX25_PAD_VSTBY_REQ__VSTBY_REQ		0x214 0x408 0x000 0x00 0x000
 #define MX25_PAD_VSTBY_REQ__AUD7_TXFS		0x214 0x408 0x000 0x04 0x000
 #define MX25_PAD_VSTBY_REQ__GPIO_3_17		0x214 0x408 0x000 0x05 0x000
 #define MX25_PAD_VSTBY_REQ__UART4_RTS		0x214 0x408 0x56c 0x06 0x002
 
-#define MX25_PAD_VSTBY_ACK__VSTBY_ACK		0x218 0x40c 0x000 0x10 0x000
-#define MX25_PAD_VSTBY_ACK__GPIO_3_18		0x218 0x40c 0x000 0x15 0x000
+#define MX25_PAD_VSTBY_ACK__VSTBY_ACK		0x218 0x40c 0x000 0x00 0x000
+#define MX25_PAD_VSTBY_ACK__GPIO_3_18		0x218 0x40c 0x000 0x05 0x000
 
-#define MX25_PAD_POWER_FAIL__POWER_FAIL		0x21c 0x410 0x000 0x10 0x000
-#define MX25_PAD_POWER_FAIL__AUD7_RXD		0x21c 0x410 0x478 0x14 0x001
-#define MX25_PAD_POWER_FAIL__GPIO_3_19		0x21c 0x410 0x000 0x15 0x000
-#define MX25_PAD_POWER_FAIL__UART4_CTS		0x21c 0x410 0x000 0x16 0x000
+#define MX25_PAD_POWER_FAIL__POWER_FAIL		0x21c 0x410 0x000 0x00 0x000
+#define MX25_PAD_POWER_FAIL__AUD7_RXD		0x21c 0x410 0x478 0x04 0x001
+#define MX25_PAD_POWER_FAIL__GPIO_3_19		0x21c 0x410 0x000 0x05 0x000
+#define MX25_PAD_POWER_FAIL__UART4_CTS		0x21c 0x410 0x000 0x06 0x000
 
-#define MX25_PAD_CLKO__CLKO			0x220 0x414 0x000 0x10 0x000
-#define MX25_PAD_CLKO__GPIO_2_21		0x220 0x414 0x000 0x15 0x000
+#define MX25_PAD_CLKO__CLKO			0x220 0x414 0x000 0x00 0x000
+#define MX25_PAD_CLKO__GPIO_2_21		0x220 0x414 0x000 0x05 0x000
 
 #define MX25_PAD_BOOT_MODE0__BOOT_MODE0		0x224 0x000 0x000 0x00 0x000
 #define MX25_PAD_BOOT_MODE0__GPIO_4_30		0x224 0x000 0x000 0x05 0x000
diff --git a/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi b/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi
index e2242638ea0b..2cf896c505f9 100644
--- a/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi
+++ b/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi
@@ -77,7 +77,7 @@
 &uart4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart4>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts b/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts
index 2ab65fc4c1e1..27846ff9bb0d 100644
--- a/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts
+++ b/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts
@@ -140,21 +140,21 @@
 };
 
 &uart1 {
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
 	status = "okay";
 };
 
 &uart2 {
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
 	status = "okay";
 };
 
 &uart3 {
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx27-pdk.dts b/arch/arm/boot/dts/imx27-pdk.dts
index 49450dbbcab8..d0ef496a1af8 100644
--- a/arch/arm/boot/dts/imx27-pdk.dts
+++ b/arch/arm/boot/dts/imx27-pdk.dts
@@ -106,7 +106,7 @@
 };
 
 &uart1 {
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
index 7c869fe3c30b..bfd4946cf9fe 100644
--- a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
+++ b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
@@ -147,21 +147,21 @@
 };
 
 &uart1 {
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
 	status = "okay";
 };
 
 &uart2 {
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
 	status = "okay";
 };
 
 &uart3 {
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts
index 538568b0de26..cf09e72aeb06 100644
--- a/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts
+++ b/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts
@@ -283,14 +283,14 @@
 };
 
 &uart1 {
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
 	status = "okay";
 };
 
 &uart2 {
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx28-apf28dev.dts b/arch/arm/boot/dts/imx28-apf28dev.dts
index 1eaa131e2d18..c4fadbc1b400 100644
--- a/arch/arm/boot/dts/imx28-apf28dev.dts
+++ b/arch/arm/boot/dts/imx28-apf28dev.dts
@@ -140,7 +140,7 @@
 			auart0: serial@8006a000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&auart0_pins_a>;
-				fsl,uart-has-rtscts;
+				uart-has-rtscts;
 				status = "okay";
 			};
 
diff --git a/arch/arm/boot/dts/imx28-cfa10049.dts b/arch/arm/boot/dts/imx28-cfa10049.dts
index ef944b6d4f01..a9c347e48bcf 100644
--- a/arch/arm/boot/dts/imx28-cfa10049.dts
+++ b/arch/arm/boot/dts/imx28-cfa10049.dts
@@ -426,7 +426,7 @@
 
 	};
 
-	onewire@0 {
+	onewire {
 		compatible = "w1-gpio";
 		pinctrl-names = "default";
 		pinctrl-0 = <&w1_gpio_pins>;
diff --git a/arch/arm/boot/dts/imx28-eukrea-mbmx28lc.dtsi b/arch/arm/boot/dts/imx28-eukrea-mbmx28lc.dtsi
index 88594747f454..581e85f4fd4c 100644
--- a/arch/arm/boot/dts/imx28-eukrea-mbmx28lc.dtsi
+++ b/arch/arm/boot/dts/imx28-eukrea-mbmx28lc.dtsi
@@ -84,6 +84,7 @@
 
 		reg_3p3v: regulator@0 {
 			compatible = "regulator-fixed";
+			reg = <0>;
 			regulator-name = "3P3V";
 			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
@@ -92,6 +93,7 @@
 
 		reg_lcd_3v3: regulator@1 {
 			compatible = "regulator-fixed";
+			reg = <1>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&reg_lcd_3v3_pins_mbmx28lc>;
 			regulator-name = "lcd-3v3";
@@ -103,6 +105,7 @@
 
 		reg_usb0_vbus: regulator@2 {
 			compatible = "regulator-fixed";
+			reg = <2>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&reg_usb0_vbus_pins_mbmx28lc>;
 			regulator-name = "usb0_vbus";
@@ -114,6 +117,7 @@
 
 		reg_usb1_vbus: regulator@3 {
 			compatible = "regulator-fixed";
+			reg = <3>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&reg_usb1_vbus_pins_mbmx28lc>;
 			regulator-name = "usb1_vbus";
diff --git a/arch/arm/boot/dts/imx28-evk.dts b/arch/arm/boot/dts/imx28-evk.dts
index e3ef94ac159f..a5ba669b4eaa 100644
--- a/arch/arm/boot/dts/imx28-evk.dts
+++ b/arch/arm/boot/dts/imx28-evk.dts
@@ -224,7 +224,7 @@
 			auart0: serial@8006a000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&auart0_pins_a>;
-				fsl,uart-has-rtscts;
+				uart-has-rtscts;
 				status = "okay";
 			};
 
diff --git a/arch/arm/boot/dts/imx28-m28.dtsi b/arch/arm/boot/dts/imx28-m28.dtsi
index 6cebaa6b8833..214bb1506b53 100644
--- a/arch/arm/boot/dts/imx28-m28.dtsi
+++ b/arch/arm/boot/dts/imx28-m28.dtsi
@@ -37,7 +37,7 @@
 				status = "okay";
 
 				rtc: rtc@68 {
-					compatible = "stm,m41t62";
+					compatible = "st,m41t62";
 					reg = <0x68>;
 				};
 			};
diff --git a/arch/arm/boot/dts/imx28-tx28.dts b/arch/arm/boot/dts/imx28-tx28.dts
index fd20e99c777e..0ebbc83852d0 100644
--- a/arch/arm/boot/dts/imx28-tx28.dts
+++ b/arch/arm/boot/dts/imx28-tx28.dts
@@ -173,7 +173,7 @@
 		default-brightness-level = <50>;
 	};
 
-	matrix_keypad: matrix-keypad@0 {
+	matrix_keypad: matrix-keypad {
 		compatible = "gpio-matrix-keypad";
 		col-gpios = <
 			&gpio5 0 GPIO_ACTIVE_HIGH
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 74aa151cdb45..0ad893bf5f43 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -165,6 +165,7 @@
 
 				gpio0: gpio@0 {
 					compatible = "fsl,imx28-gpio", "fsl,mxs-gpio";
+					reg = <0>;
 					interrupts = <127>;
 					gpio-controller;
 					#gpio-cells = <2>;
@@ -174,6 +175,7 @@
 
 				gpio1: gpio@1 {
 					compatible = "fsl,imx28-gpio", "fsl,mxs-gpio";
+					reg = <1>;
 					interrupts = <126>;
 					gpio-controller;
 					#gpio-cells = <2>;
@@ -183,6 +185,7 @@
 
 				gpio2: gpio@2 {
 					compatible = "fsl,imx28-gpio", "fsl,mxs-gpio";
+					reg = <2>;
 					interrupts = <125>;
 					gpio-controller;
 					#gpio-cells = <2>;
@@ -192,6 +195,7 @@
 
 				gpio3: gpio@3 {
 					compatible = "fsl,imx28-gpio", "fsl,mxs-gpio";
+					reg = <3>;
 					interrupts = <124>;
 					gpio-controller;
 					#gpio-cells = <2>;
@@ -201,6 +205,7 @@
 
 				gpio4: gpio@4 {
 					compatible = "fsl,imx28-gpio", "fsl,mxs-gpio";
+					reg = <4>;
 					interrupts = <123>;
 					gpio-controller;
 					#gpio-cells = <2>;
diff --git a/arch/arm/boot/dts/imx31-bug.dts b/arch/arm/boot/dts/imx31-bug.dts
index 2424abfc9c7b..ae6cebbed84b 100644
--- a/arch/arm/boot/dts/imx31-bug.dts
+++ b/arch/arm/boot/dts/imx31-bug.dts
@@ -22,6 +22,6 @@
 };
 
 &uart5 {
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx35-eukrea-mbimxsd35-baseboard.dts b/arch/arm/boot/dts/imx35-eukrea-mbimxsd35-baseboard.dts
index 4727bbb804e1..e9357131b026 100644
--- a/arch/arm/boot/dts/imx35-eukrea-mbimxsd35-baseboard.dts
+++ b/arch/arm/boot/dts/imx35-eukrea-mbimxsd35-baseboard.dts
@@ -139,14 +139,14 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx35-pdk.dts b/arch/arm/boot/dts/imx35-pdk.dts
index 8d715523708f..9bb628f22502 100644
--- a/arch/arm/boot/dts/imx35-pdk.dts
+++ b/arch/arm/boot/dts/imx35-pdk.dts
@@ -63,6 +63,6 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx51-babbage.dts b/arch/arm/boot/dts/imx51-babbage.dts
index 018d24eb9965..f097b4f29ab4 100644
--- a/arch/arm/boot/dts/imx51-babbage.dts
+++ b/arch/arm/boot/dts/imx51-babbage.dts
@@ -388,7 +388,7 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
@@ -401,7 +401,7 @@
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts b/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts
index d270df3e5891..728212861ece 100644
--- a/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts
+++ b/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts
@@ -261,14 +261,14 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3 &pinctrl_uart3_rtscts>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx51-ts4800.dts b/arch/arm/boot/dts/imx51-ts4800.dts
index 0ff76a1bc0f1..ca1cc5eca80f 100644
--- a/arch/arm/boot/dts/imx51-ts4800.dts
+++ b/arch/arm/boot/dts/imx51-ts4800.dts
@@ -102,7 +102,7 @@
 	status = "okay";
 
 	rtc: m41t00@68 {
-		compatible = "stm,m41t00";
+		compatible = "st,m41t00";
 		reg = <0x68>;
 	};
 };
@@ -165,6 +165,27 @@
 			reg = <0x12000 0x1000>;
 			syscon = <&syscon 0x10 6>;
 		};
+
+		fpga_irqc: fpga-irqc@15000 {
+			compatible = "technologic,ts4800-irqc";
+			reg = <0x15000 0x1000>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_interrupt_fpga>;
+			interrupt-parent = <&gpio2>;
+			interrupts= <9 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		can@1a000 {
+			compatible = "technologic,sja1000";
+			reg = <0x1a000 0x100>;
+			interrupt-parent = <&fpga_irqc>;
+			interrupts = <1>;
+			reg-io-width = <2>;
+			nxp,tx-output-config = <0x06>;
+			nxp,external-clock-frequency = <24000000>;
+		};
 	};
 };
 
@@ -228,6 +249,12 @@
 		>;
 	};
 
+	pinctrl_interrupt_fpga: fpgaicgrp {
+		fsl,pins = <
+			MX51_PAD_EIM_D27__GPIO2_9		0xe5
+		>;
+	};
+
 	pinctrl_lcd: lcdgrp {
 		fsl,pins = <
 			MX51_PAD_DISP1_DAT0__DISP1_DAT0		0x5
diff --git a/arch/arm/boot/dts/imx53-m53.dtsi b/arch/arm/boot/dts/imx53-m53.dtsi
index 87a7fc709c2d..d259f57bfd98 100644
--- a/arch/arm/boot/dts/imx53-m53.dtsi
+++ b/arch/arm/boot/dts/imx53-m53.dtsi
@@ -84,7 +84,7 @@
 	};
 
 	rtc: rtc@68 {
-		compatible = "stm,m41t62";
+		compatible = "st,m41t62";
 		reg = <0x68>;
 	};
 };
diff --git a/arch/arm/boot/dts/imx53-smd.dts b/arch/arm/boot/dts/imx53-smd.dts
index 542ab9e697fb..9f5190040555 100644
--- a/arch/arm/boot/dts/imx53-smd.dts
+++ b/arch/arm/boot/dts/imx53-smd.dts
@@ -56,7 +56,7 @@
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-tqma53.dtsi b/arch/arm/boot/dts/imx53-tqma53.dtsi
index e03373a58760..91a6a9ff50d7 100644
--- a/arch/arm/boot/dts/imx53-tqma53.dtsi
+++ b/arch/arm/boot/dts/imx53-tqma53.dtsi
@@ -218,7 +218,7 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "disabled";
 };
 
diff --git a/arch/arm/boot/dts/imx53-tx53.dtsi b/arch/arm/boot/dts/imx53-tx53.dtsi
index bd3dfefa5778..57e75f1639e0 100644
--- a/arch/arm/boot/dts/imx53-tx53.dtsi
+++ b/arch/arm/boot/dts/imx53-tx53.dtsi
@@ -513,21 +513,21 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6dl-riotboard.dts b/arch/arm/boot/dts/imx6dl-riotboard.dts
index bfbed52ce1bd..2becd7cd6544 100644
--- a/arch/arm/boot/dts/imx6dl-riotboard.dts
+++ b/arch/arm/boot/dts/imx6dl-riotboard.dts
@@ -97,6 +97,7 @@
 	phy-reset-gpios = <&gpio3 31 0>;
 	interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_HIGH>,
 			      <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+	fsl,err006687-workaround-present;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6q-apalis-ixora.dts b/arch/arm/boot/dts/imx6q-apalis-ixora.dts
index 8e67ca27ad79..207b85b91ada 100644
--- a/arch/arm/boot/dts/imx6q-apalis-ixora.dts
+++ b/arch/arm/boot/dts/imx6q-apalis-ixora.dts
@@ -93,7 +93,7 @@
 			reg = <0>;
 
 			lcd_display_in: endpoint {
-				remote-endpoint = <&ipu1_di0_disp1>;
+				remote-endpoint = <&ipu1_di1_disp1>;
 			};
 		};
 
@@ -210,7 +210,7 @@
 	};
 };
 
-&ipu1_di0_disp1 {
+&ipu1_di1_disp1 {
 	remote-endpoint = <&lcd_display_in>;
 };
 
diff --git a/arch/arm/boot/dts/imx6q-arm2.dts b/arch/arm/boot/dts/imx6q-arm2.dts
index d6515f7a56c4..d8acf15611e4 100644
--- a/arch/arm/boot/dts/imx6q-arm2.dts
+++ b/arch/arm/boot/dts/imx6q-arm2.dts
@@ -185,6 +185,7 @@
 	phy-mode = "rgmii";
 	interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_HIGH>,
 			      <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+	fsl,err006687-workaround-present;
 	status = "okay";
 };
 
@@ -218,7 +219,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
 	fsl,dte-mode;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6q-ba16.dtsi b/arch/arm/boot/dts/imx6q-ba16.dtsi
index f7e17e2004ac..f2adc60723da 100644
--- a/arch/arm/boot/dts/imx6q-ba16.dtsi
+++ b/arch/arm/boot/dts/imx6q-ba16.dtsi
@@ -351,7 +351,7 @@
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
index bb66dfd5294c..cf3fd31e3406 100644
--- a/arch/arm/boot/dts/imx6q-bx50v3.dtsi
+++ b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
@@ -52,6 +52,12 @@
 		};
 	};
 
+	gpio-poweroff {
+		compatible = "gpio-poweroff";
+		gpios = <&gpio4 11 GPIO_ACTIVE_LOW>;
+		status = "okay";
+	};
+
 	reg_wl18xx_vmmc: regulator-wl18xx {
 		compatible = "regulator-fixed";
 		regulator-name = "vwl1807";
diff --git a/arch/arm/boot/dts/imx6q-cm-fx6.dts b/arch/arm/boot/dts/imx6q-cm-fx6.dts
index 99b46f8030ad..b5de7e620905 100644
--- a/arch/arm/boot/dts/imx6q-cm-fx6.dts
+++ b/arch/arm/boot/dts/imx6q-cm-fx6.dts
@@ -3,15 +3,46 @@
  *
  * Author: Valentin Raevsky <valentin@compulab.co.il>
  *
- * The code contained herein is licensed under the GNU General Public
- * License. You may obtain a copy of the GNU General Public License
- * Version 2 or later at the following locations:
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
  *
- * http://www.opensource.org/licenses/gpl-license.html
- * http://www.gnu.org/copyleft/gpl.html
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
  */
 
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 #include "imx6q.dtsi"
 
 / {
@@ -31,6 +62,71 @@
 			linux,default-trigger = "heartbeat";
 		};
 	};
+
+	reg_pcie_power_on_gpio: regulator-pcie-power-on-gpio {
+		compatible = "regulator-fixed";
+		regulator-name = "regulator-pcie-power-on-gpio";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio2 24 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_usb_h1_vbus: usb_h1_vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_h1_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio7 8 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_usb_otg_vbus: usb_otg_vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "usb_otg_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio3 22 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+};
+
+&cpu0 {
+	/*
+	 * Although the imx6q fuse indicates that 1.2GHz operation is possible,
+	 * the module behaves unstable at this frequency. Hence, remove the
+	 * 1.2GHz operation point here.
+	 */
+	operating-points = <
+		/* kHz	uV */
+		996000	1250000
+		852000	1250000
+		792000	1175000
+		396000	975000
+	>;
+	fsl,soc-operating-points = <
+		/* ARM kHz	SOC-PU uV */
+		996000		1250000
+		852000		1250000
+		792000		1175000
+		396000		1175000
+	>;
+};
+
+&ecspi1 {
+	fsl,spi-num-chipselects = <2>;
+	cs-gpios = <&gpio2 30 GPIO_ACTIVE_HIGH>, <&gpio3 19 GPIO_ACTIVE_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi1>;
+	status = "okay";
+
+	m25p80@0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "st,m25p", "jedec,spi-nor";
+		spi-max-frequency = <20000000>;
+		reg = <0>;
+	};
 };
 
 &fec {
@@ -46,58 +142,122 @@
 	status = "okay";
 };
 
+&i2c3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c3>;
+	status = "okay";
+	clock-frequency = <100000>;
+
+	eeprom@50 {
+		compatible = "at24,24c02";
+		reg = <0x50>;
+		pagesize = <16>;
+	};
+};
+
 &iomuxc {
-	imx6q-cm-fx6 {
-		pinctrl_enet: enetgrp {
-			fsl,pins = <
-				MX6QDL_PAD_RGMII_RXC__RGMII_RXC		0x1b0b0
-				MX6QDL_PAD_RGMII_RD0__RGMII_RD0		0x1b0b0
-				MX6QDL_PAD_RGMII_RD1__RGMII_RD1		0x1b0b0
-				MX6QDL_PAD_RGMII_RD2__RGMII_RD2		0x1b0b0
-				MX6QDL_PAD_RGMII_RD3__RGMII_RD3		0x1b0b0
-				MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL	0x1b0b0
-				MX6QDL_PAD_RGMII_TXC__RGMII_TXC		0x1b0b0
-				MX6QDL_PAD_RGMII_TD0__RGMII_TD0		0x1b0b0
-				MX6QDL_PAD_RGMII_TD1__RGMII_TD1		0x1b0b0
-				MX6QDL_PAD_RGMII_TD2__RGMII_TD2		0x1b0b0
-				MX6QDL_PAD_RGMII_TD3__RGMII_TD3		0x1b0b0
-				MX6QDL_PAD_RGMII_TX_CTL__RGMII_TX_CTL	0x1b0b0
-				MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK	0x1b0b0
-				MX6QDL_PAD_ENET_MDIO__ENET_MDIO		0x1b0b0
-				MX6QDL_PAD_ENET_MDC__ENET_MDC		0x1b0b0
-				MX6QDL_PAD_GPIO_16__ENET_REF_CLK	0x4001b0a8
-			>;
-		};
+	pinctrl_ecspi1: ecspi1grp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_D16__ECSPI1_SCLK	0x100b1
+			MX6QDL_PAD_EIM_D17__ECSPI1_MISO	0x100b1
+			MX6QDL_PAD_EIM_D18__ECSPI1_MOSI	0x100b1
+			MX6QDL_PAD_EIM_EB2__GPIO2_IO30	0x100b1
+			MX6QDL_PAD_EIM_D19__GPIO3_IO19	0x100b1
+		>;
+	};
 
-		pinctrl_gpmi_nand: gpminandgrp {
-			fsl,pins = <
-				MX6QDL_PAD_NANDF_CLE__NAND_CLE		0xb0b1
-				MX6QDL_PAD_NANDF_ALE__NAND_ALE		0xb0b1
-				MX6QDL_PAD_NANDF_WP_B__NAND_WP_B	0xb0b1
-				MX6QDL_PAD_NANDF_RB0__NAND_READY_B	0xb000
-				MX6QDL_PAD_NANDF_CS0__NAND_CE0_B	0xb0b1
-				MX6QDL_PAD_NANDF_CS1__NAND_CE1_B	0xb0b1
-				MX6QDL_PAD_SD4_CMD__NAND_RE_B		0xb0b1
-				MX6QDL_PAD_SD4_CLK__NAND_WE_B		0xb0b1
-				MX6QDL_PAD_NANDF_D0__NAND_DATA00	0xb0b1
-				MX6QDL_PAD_NANDF_D1__NAND_DATA01	0xb0b1
-				MX6QDL_PAD_NANDF_D2__NAND_DATA02	0xb0b1
-				MX6QDL_PAD_NANDF_D3__NAND_DATA03	0xb0b1
-				MX6QDL_PAD_NANDF_D4__NAND_DATA04	0xb0b1
-				MX6QDL_PAD_NANDF_D5__NAND_DATA05	0xb0b1
-				MX6QDL_PAD_NANDF_D6__NAND_DATA06	0xb0b1
-				MX6QDL_PAD_NANDF_D7__NAND_DATA07	0xb0b1
-				MX6QDL_PAD_SD4_DAT0__NAND_DQS		0x00b1
-			>;
-		};
+	pinctrl_enet: enetgrp {
+		fsl,pins = <
+			MX6QDL_PAD_RGMII_RXC__RGMII_RXC		0x1b0b0
+			MX6QDL_PAD_RGMII_RD0__RGMII_RD0		0x1b0b0
+			MX6QDL_PAD_RGMII_RD1__RGMII_RD1		0x1b0b0
+			MX6QDL_PAD_RGMII_RD2__RGMII_RD2		0x1b0b0
+			MX6QDL_PAD_RGMII_RD3__RGMII_RD3		0x1b0b0
+			MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL	0x1b0b0
+			MX6QDL_PAD_RGMII_TXC__RGMII_TXC		0x1b0b0
+			MX6QDL_PAD_RGMII_TD0__RGMII_TD0		0x1b0b0
+			MX6QDL_PAD_RGMII_TD1__RGMII_TD1		0x1b0b0
+			MX6QDL_PAD_RGMII_TD2__RGMII_TD2		0x1b0b0
+			MX6QDL_PAD_RGMII_TD3__RGMII_TD3		0x1b0b0
+			MX6QDL_PAD_RGMII_TX_CTL__RGMII_TX_CTL	0x1b0b0
+			MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK	0x1b0b0
+			MX6QDL_PAD_ENET_MDIO__ENET_MDIO		0x1b0b0
+			MX6QDL_PAD_ENET_MDC__ENET_MDC		0x1b0b0
+			MX6QDL_PAD_GPIO_16__ENET_REF_CLK	0x4001b0a8
+		>;
+	};
 
-		pinctrl_uart4: uart4grp {
-			fsl,pins = <
-				MX6QDL_PAD_KEY_COL0__UART4_TX_DATA	0x1b0b1
-				MX6QDL_PAD_KEY_ROW0__UART4_RX_DATA	0x1b0b1
-			>;
-		};
+	pinctrl_gpmi_nand: gpminandgrp {
+		fsl,pins = <
+			MX6QDL_PAD_NANDF_CLE__NAND_CLE		0xb0b1
+			MX6QDL_PAD_NANDF_ALE__NAND_ALE		0xb0b1
+			MX6QDL_PAD_NANDF_WP_B__NAND_WP_B	0xb0b1
+			MX6QDL_PAD_NANDF_RB0__NAND_READY_B	0xb000
+			MX6QDL_PAD_NANDF_CS0__NAND_CE0_B	0xb0b1
+			MX6QDL_PAD_NANDF_CS1__NAND_CE1_B	0xb0b1
+			MX6QDL_PAD_SD4_CMD__NAND_RE_B		0xb0b1
+			MX6QDL_PAD_SD4_CLK__NAND_WE_B		0xb0b1
+			MX6QDL_PAD_NANDF_D0__NAND_DATA00	0xb0b1
+			MX6QDL_PAD_NANDF_D1__NAND_DATA01	0xb0b1
+			MX6QDL_PAD_NANDF_D2__NAND_DATA02	0xb0b1
+			MX6QDL_PAD_NANDF_D3__NAND_DATA03	0xb0b1
+			MX6QDL_PAD_NANDF_D4__NAND_DATA04	0xb0b1
+			MX6QDL_PAD_NANDF_D5__NAND_DATA05	0xb0b1
+			MX6QDL_PAD_NANDF_D6__NAND_DATA06	0xb0b1
+			MX6QDL_PAD_NANDF_D7__NAND_DATA07	0xb0b1
+			MX6QDL_PAD_SD4_DAT0__NAND_DQS		0x00b1
+		>;
+	};
+
+	pinctrl_i2c3: i2c3grp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_3__I2C3_SCL	0x4001b8b1
+			MX6QDL_PAD_GPIO_6__I2C3_SDA	0x4001b8b1
+		>;
+	};
+
+	pinctrl_pcie: pciegrp {
+		fsl,pins = <
+			MX6QDL_PAD_ENET_RXD1__GPIO1_IO26	0x1b0b1
+			MX6QDL_PAD_EIM_CS1__GPIO2_IO24	0x1b0b1
+		>;
+	};
+
+	pinctrl_uart4: uart4grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL0__UART4_TX_DATA	0x1b0b1
+			MX6QDL_PAD_KEY_ROW0__UART4_RX_DATA	0x1b0b1
+		>;
 	};
+
+	pinctrl_usbh1: usbh1grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD3_RST__GPIO7_IO08	0x1b0b1
+		>;
+	};
+
+	pinctrl_usbotg: usbotggrp {
+		fsl,pins = <
+			MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID	0x17059
+			MX6QDL_PAD_EIM_D22__GPIO3_IO22	0x130b0
+		>;
+	};
+};
+
+&pcie {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pcie>;
+	reset-gpio = <&gpio1 26 GPIO_ACTIVE_LOW>;
+	vdd-supply = <&reg_pcie_power_on_gpio>;
+	status = "okay";
+};
+
+&sata {
+	status = "okay";
+};
+
+&snvs_poweroff {
+	status = "okay";
 };
 
 &uart4 {
@@ -105,3 +265,18 @@
 	pinctrl-0 = <&pinctrl_uart4>;
 	status = "okay";
 };
+
+&usbh1 {
+	vbus-supply = <&reg_usb_h1_vbus>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usbh1>;
+	status = "okay";
+};
+
+&usbotg {
+	vbus-supply = <&reg_usb_otg_vbus>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usbotg>;
+	dr_mode = "otg";
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6q-dmo-edmqmx6.dts b/arch/arm/boot/dts/imx6q-dmo-edmqmx6.dts
index 364578d707a5..905907325f3b 100644
--- a/arch/arm/boot/dts/imx6q-dmo-edmqmx6.dts
+++ b/arch/arm/boot/dts/imx6q-dmo-edmqmx6.dts
@@ -282,7 +282,7 @@
 	};
 
 	rtc: m41t62@68 {
-		compatible = "stm,m41t62";
+		compatible = "st,m41t62";
 		reg = <0x68>;
 	};
 };
diff --git a/arch/arm/boot/dts/imx6q-h100.dts b/arch/arm/boot/dts/imx6q-h100.dts
new file mode 100644
index 000000000000..65e66f994f88
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-h100.dts
@@ -0,0 +1,395 @@
+/*
+ * Copyright (C) 2015 Lucas Stach <kernel@pengutronix.de>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+
+#include "imx6q.dtsi"
+#include "imx6qdl-microsom.dtsi"
+#include "imx6qdl-microsom-ar8035.dtsi"
+
+/ {
+	model = "Auvidea H100";
+	compatible = "auvidea,h100", "fsl,imx6q";
+
+	aliases {
+		rtc0 = &rtc;
+		rtc1 = &snvs_rtc;
+	};
+
+	chosen {
+		stdout-path = &uart2;
+	};
+
+	hdmi_osc: hdmi-osc {
+		compatible = "fixed-clock";
+		clock-output-names = "hdmi-osc";
+		clock-frequency = <27000000>;
+		#clock-cells = <0>;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_h100_leds>;
+
+		led0: power {
+			label = "power";
+			gpios = <&gpio3 0 GPIO_ACTIVE_LOW>;
+			default-state = "on";
+		};
+
+		led1: stream {
+			label = "stream";
+			gpios = <&gpio2 29 GPIO_ACTIVE_LOW>;
+			default-state = "off";
+		};
+
+		led2: rec {
+			label = "rec";
+			gpios = <&gpio2 28 GPIO_ACTIVE_LOW>;
+			default-state = "off";
+		};
+	};
+
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "3P3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	reg_hdmi: regulator-hdmi {
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_h100_reg_hdmi>;
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 20 GPIO_ACTIVE_HIGH>;
+		regulator-name = "V_HDMI";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+	};
+
+	reg_nvcc_sd2: regulator-nvcc-sd2 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_h100_reg_nvcc_sd2>;
+		compatible = "regulator-gpio";
+		regulator-name = "NVCC_SD2";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-type = "voltage";
+		regulator-boot-on;
+		regulator-always-on;
+		gpios = <&gpio4 9 GPIO_ACTIVE_HIGH>;
+		states = <1800000 0x1
+			  3300000 0x0>;
+	};
+
+	reg_usbh1_vbus: regulator-usb-h1-vbus {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio1 0 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_h100_usbh1_vbus>;
+		regulator-name = "USB_H1_VBUS";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	reg_usbotg_vbus: regulator-usb-otg-vbus {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 22 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_h100_usbotg_vbus>;
+		regulator-name = "USB_OTG_VBUS";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	sound-sgtl5000 {
+		compatible = "fsl,imx-audio-sgtl5000";
+		model = "H100 on-board codec";
+		audio-codec = <&sgtl5000>;
+		audio-routing =
+			"MIC_IN", "Mic Jack",
+			"Mic Jack", "Mic Bias",
+			"Headphone Jack", "HP_OUT";
+		mux-ext-port = <5>;
+		mux-int-port = <1>;
+		ssi-controller = <&ssi1>;
+	};
+};
+
+&audmux {
+	status = "okay";
+};
+
+&hdmi {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_h100_hdmi>;
+	ddc-i2c-bus = <&i2c2>;
+	status = "okay";
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_h100_i2c1>;
+	status = "okay";
+
+	eeprom: 24c02@51 {
+		compatible = "microchip,24c02", "at24";
+		reg = <0x51>;
+	};
+
+	rtc: pcf8523@68 {
+		compatible = "nxp,pcf8523";
+		reg = <0x68>;
+	};
+
+	sgtl5000: sgtl5000@0a {
+		compatible = "fsl,sgtl5000";
+		reg = <0x0a>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_h100_sgtl5000>;
+		clocks = <&clks IMX6QDL_CLK_CKO>;
+		VDDA-supply = <&reg_3p3v>;
+		VDDIO-supply = <&reg_3p3v>;
+	};
+
+	tc358743: tc358743@0f {
+		compatible = "toshiba,tc358743";
+		reg = <0x0f>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_h100_tc358743>;
+		clocks = <&hdmi_osc>;
+		clock-names = "refclk";
+		reset-gpios = <&gpio6 15 GPIO_ACTIVE_LOW>;
+		/* IRQ has a wrong pull resistor which renders it useless  */
+
+		port@0 {
+			tc358743_out: endpoint {
+				remote-endpoint = <&mipi_csi2_in>;
+				data-lanes = <1 2 3 4>;
+				clock-lanes = <0>;
+				clock-noncontinuous;
+				link-frequencies = /bits/ 64 <297000000>;
+			};
+		};
+	};
+};
+
+&i2c2 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_h100_i2c2>;
+	status = "okay";
+};
+
+&iomuxc {
+	h100 {
+		pinctrl_h100_hdmi: h100-hdmi {
+			fsl,pins = <
+				MX6QDL_PAD_KEY_ROW2__HDMI_TX_CEC_LINE	0x1f8b0
+			>;
+		};
+
+		pinctrl_h100_i2c1: h100-i2c1 {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_D21__I2C1_SCL		0x4001b8b1
+				MX6QDL_PAD_EIM_D28__I2C1_SDA		0x4001b8b1
+			>;
+		};
+
+		pinctrl_h100_i2c2: h100-i2c2 {
+			fsl,pins = <
+				MX6QDL_PAD_KEY_COL3__I2C2_SCL		0x4001b8b1
+				MX6QDL_PAD_KEY_ROW3__I2C2_SDA		0x4001b8b1
+			>;
+		};
+
+		pinctrl_h100_leds: pinctrl-h100-leds {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_DA0__GPIO3_IO00		0x1b0b0
+				MX6QDL_PAD_EIM_EB1__GPIO2_IO29		0x1b0b0
+				MX6QDL_PAD_EIM_EB0__GPIO2_IO28		0x1b0b0
+			>;
+		};
+
+		pinctrl_h100_reg_hdmi: h100-reg-hdmi {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_A18__GPIO2_IO20		0x1b0b0
+			>;
+		};
+
+		pinctrl_h100_reg_nvcc_sd2: h100-reg-nvcc-sd2 {
+			fsl,pins = <
+				MX6QDL_PAD_KEY_ROW1__GPIO4_IO09		0x1b0b0
+			>;
+		};
+
+		pinctrl_h100_sgtl5000: h100-sgtl5000 {
+			fsl,pins = <
+				MX6QDL_PAD_DISP0_DAT19__AUD5_RXD	0x130b0
+				MX6QDL_PAD_KEY_COL0__AUD5_TXC		0x130b0
+				MX6QDL_PAD_KEY_ROW0__AUD5_TXD		0x110b0
+				MX6QDL_PAD_KEY_COL1__AUD5_TXFS		0x130b0
+				MX6QDL_PAD_GPIO_5__CCM_CLKO1		0x130b0
+			>;
+		};
+
+		pinctrl_h100_tc358743: h100-tc358743 {
+			fsl,pins = <
+				MX6QDL_PAD_NANDF_CS2__GPIO6_IO15	0x1b0b0
+			>;
+		};
+
+		pinctrl_h100_uart2: h100-uart2 {
+			fsl,pins = <
+				MX6QDL_PAD_SD4_DAT4__UART2_RX_DATA	0x1b0b1
+				MX6QDL_PAD_SD4_DAT7__UART2_TX_DATA	0x1b0b1
+			>;
+		};
+
+		pinctrl_h100_usbh1_vbus: hummingboard-usbh1-vbus {
+			fsl,pins = <
+				MX6QDL_PAD_GPIO_0__GPIO1_IO00		0x1b0b0
+			>;
+		};
+
+		pinctrl_h100_usbotg_id: hummingboard-usbotg-id {
+			fsl,pins = <
+				MX6QDL_PAD_GPIO_1__USB_OTG_ID		0x13059
+			>;
+		};
+
+		pinctrl_h100_usbotg_vbus: hummingboard-usbotg-vbus {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_D22__GPIO3_IO22		0x1b0b0
+			>;
+		};
+
+		pinctrl_h100_usdhc2: h100-usdhc2 {
+			fsl,pins = <
+				MX6QDL_PAD_GPIO_4__GPIO1_IO04		0x1f071
+				MX6QDL_PAD_SD2_CMD__SD2_CMD		0x17059
+				MX6QDL_PAD_SD2_CLK__SD2_CLK		0x10059
+				MX6QDL_PAD_SD2_DAT0__SD2_DATA0		0x17059
+				MX6QDL_PAD_SD2_DAT1__SD2_DATA1		0x17059
+				MX6QDL_PAD_SD2_DAT2__SD2_DATA2		0x17059
+				MX6QDL_PAD_SD2_DAT3__SD2_DATA3		0x13059
+			>;
+		};
+
+		pinctrl_h100_usdhc2_100mhz: h100-usdhc2-100mhz {
+			fsl,pins = <
+				MX6QDL_PAD_GPIO_4__GPIO1_IO04		0x1f071
+				MX6QDL_PAD_SD2_CMD__SD2_CMD		0x170b9
+				MX6QDL_PAD_SD2_CLK__SD2_CLK		0x100b9
+				MX6QDL_PAD_SD2_DAT0__SD2_DATA0		0x170b9
+				MX6QDL_PAD_SD2_DAT1__SD2_DATA1		0x170b9
+				MX6QDL_PAD_SD2_DAT2__SD2_DATA2		0x170b9
+				MX6QDL_PAD_SD2_DAT3__SD2_DATA3		0x170b9
+			>;
+		};
+
+		pinctrl_h100_usdhc2_200mhz: h100-usdhc2-200mhz {
+			fsl,pins = <
+				MX6QDL_PAD_GPIO_4__GPIO1_IO04		0x1f071
+				MX6QDL_PAD_SD2_CMD__SD2_CMD		0x170f9
+				MX6QDL_PAD_SD2_CLK__SD2_CLK		0x100f9
+				MX6QDL_PAD_SD2_DAT0__SD2_DATA0		0x170f9
+				MX6QDL_PAD_SD2_DAT1__SD2_DATA1		0x170f9
+				MX6QDL_PAD_SD2_DAT2__SD2_DATA2		0x170f9
+				MX6QDL_PAD_SD2_DAT3__SD2_DATA3		0x170f9
+			>;
+		};
+	};
+};
+
+&mipi_csi {
+	status = "okay";
+
+	port@0 {
+		mipi_csi2_in: endpoint {
+			remote-endpoint = <&tc358743_out>;
+			data-lanes = <1 2 3 4>;
+			clock-lanes = <0>;
+			clock-noncontinuous;
+			link-frequencies = /bits/ 64 <297000000>;
+		};
+	};
+};
+
+&ssi1 {
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_h100_uart2>;
+	status = "okay";
+};
+
+&usbh1 {
+	disable-over-current;
+	vbus-supply = <&reg_usbh1_vbus>;
+	status = "okay";
+};
+
+&usbotg {
+	disable-over-current;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_h100_usbotg_id>;
+	vbus-supply = <&reg_usbotg_vbus>;
+	status = "okay";
+};
+
+&usdhc2 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_h100_usdhc2>;
+	pinctrl-1 = <&pinctrl_h100_usdhc2_100mhz>;
+	pinctrl-2 = <&pinctrl_h100_usdhc2_200mhz>;
+	vmmc-supply = <&reg_3p3v>;
+	vqmmc-supply = <&reg_nvcc_sd2>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6q-tbs2910.dts b/arch/arm/boot/dts/imx6q-tbs2910.dts
index 1926b1348a62..d7c8ccb2da95 100644
--- a/arch/arm/boot/dts/imx6q-tbs2910.dts
+++ b/arch/arm/boot/dts/imx6q-tbs2910.dts
@@ -191,7 +191,7 @@
 &pcie {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_pcie>;
-	reset-gpio = <&gpio7 12 GPIO_ACTIVE_HIGH>;
+	reset-gpio = <&gpio7 12 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6q-utilite-pro.dts b/arch/arm/boot/dts/imx6q-utilite-pro.dts
new file mode 100644
index 000000000000..61990630a748
--- /dev/null
+++ b/arch/arm/boot/dts/imx6q-utilite-pro.dts
@@ -0,0 +1,197 @@
+/*
+ * Copyright 2013 CompuLab Ltd.
+ * Copyright 2016 Christopher Spinrath
+ *
+ * Based on the devicetree distributed with the vendor kernel for the
+ * Utilite Pro:
+ *	Copyright 2013 CompuLab Ltd.
+ *	Author: Valentin Raevsky <valentin@compulab.co.il>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <dt-bindings/input/input.h>
+#include "imx6q-cm-fx6.dts"
+
+/ {
+	model = "CompuLab Utilite Pro";
+	compatible = "compulab,utilite-pro", "compulab,cm-fx6", "fsl,imx6q";
+
+	aliases {
+		ethernet1 = &eth1;
+		rtc0 = &em3027;
+		rtc1 = &snvs_rtc;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_keys>;
+
+		power {
+			label = "Power Button";
+			gpios = <&gpio1 29 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_POWER>;
+			gpio-key,wakeup;
+		};
+	};
+};
+
+&hdmi {
+	ddc-i2c-bus = <&i2c2>;
+	status = "okay";
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c1>;
+	status = "okay";
+
+	eeprom@50 {
+		compatible = "at24,24c02";
+		reg = <0x50>;
+		pagesize = <16>;
+	};
+
+	em3027: rtc@56 {
+		compatible = "emmicro,em3027";
+		reg = <0x56>;
+	};
+};
+
+&i2c2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c2>;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_gpio_keys: gpio_keysgrp {
+		fsl,pins = <
+			MX6QDL_PAD_ENET_TXD1__GPIO1_IO29 0x1b0b0
+		>;
+	};
+
+	pinctrl_i2c1: i2c1grp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_D21__I2C1_SCL 0x4001b8b1
+			MX6QDL_PAD_EIM_D28__I2C1_SDA 0x4001b8b1
+		>;
+	};
+
+	pinctrl_i2c2: i2c2grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL3__I2C2_SCL 0x4001b8b1
+			MX6QDL_PAD_KEY_ROW3__I2C2_SDA 0x4001b8b1
+		>;
+	};
+
+	pinctrl_uart2: uart2grp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_7__UART2_TX_DATA 0x1b0b1
+			MX6QDL_PAD_GPIO_8__UART2_RX_DATA 0x1b0b1
+			MX6QDL_PAD_SD4_DAT5__UART2_RTS_B 0x1b0b1
+			MX6QDL_PAD_SD4_DAT6__UART2_CTS_B 0x1b0b1
+		>;
+	};
+
+	pinctrl_usdhc3: usdhc3grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD3_CMD__SD3_CMD	0x17059
+			MX6QDL_PAD_SD3_CLK__SD3_CLK	0x10059
+			MX6QDL_PAD_SD3_DAT0__SD3_DATA0	0x17059
+			MX6QDL_PAD_SD3_DAT1__SD3_DATA1	0x17059
+			MX6QDL_PAD_SD3_DAT2__SD3_DATA2	0x17059
+			MX6QDL_PAD_SD3_DAT3__SD3_DATA3	0x17059
+		>;
+	};
+
+	pinctrl_usdhc3_100mhz: usdhc3grp-100mhz {
+		fsl,pins = <
+			MX6QDL_PAD_SD3_CMD__SD3_CMD	0x170B9
+			MX6QDL_PAD_SD3_CLK__SD3_CLK	0x100B9
+			MX6QDL_PAD_SD3_DAT0__SD3_DATA0	0x170B9
+			MX6QDL_PAD_SD3_DAT1__SD3_DATA1	0x170B9
+			MX6QDL_PAD_SD3_DAT2__SD3_DATA2	0x170B9
+			MX6QDL_PAD_SD3_DAT3__SD3_DATA3	0x170B9
+		>;
+	};
+
+	pinctrl_usdhc3_200mhz: usdhc3grp-200mhz {
+		fsl,pins = <
+			MX6QDL_PAD_SD3_CMD__SD3_CMD	0x170F9
+			MX6QDL_PAD_SD3_CLK__SD3_CLK	0x100F9
+			MX6QDL_PAD_SD3_DAT0__SD3_DATA0	0x170F9
+			MX6QDL_PAD_SD3_DAT1__SD3_DATA1	0x170F9
+			MX6QDL_PAD_SD3_DAT2__SD3_DATA2	0x170F9
+			MX6QDL_PAD_SD3_DAT3__SD3_DATA3	0x170F9
+		>;
+	};
+};
+
+&pcie {
+	pcie@0,0 {
+		reg = <0x000000 0 0 0 0>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+
+		/* non-removable i211 ethernet card */
+		eth1: intel,i211@pcie0,0 {
+			reg = <0x010000 0 0 0 0>;
+		};
+	};
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2>;
+	uart-has-rtscts;
+	status = "okay";
+};
+
+&usdhc3 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc3>;
+	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
+	no-1-8-v;
+	broken-cd;
+	keep-power-in-suspend;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/imx6qdl-apalis.dtsi
index 922b1dd06fda..315e033ff1d8 100644
--- a/arch/arm/boot/dts/imx6qdl-apalis.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-apalis.dtsi
@@ -423,7 +423,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1_dte &pinctrl_uart1_ctrl>;
 	fsl,dte-mode;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "disabled";
 };
 
@@ -431,7 +431,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2_dte>;
 	fsl,dte-mode;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "disabled";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-apf6dev.dtsi b/arch/arm/boot/dts/imx6qdl-apf6dev.dtsi
index 865c9a264a43..edbce222c782 100644
--- a/arch/arm/boot/dts/imx6qdl-apf6dev.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-apf6dev.dtsi
@@ -254,7 +254,7 @@
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3 &pinctrl_gsm>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
index ecbc6eba6a2c..54f4f0193f2b 100644
--- a/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
@@ -143,14 +143,14 @@
 &uart4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart4>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart5 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart5>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
index 7d81100e7d47..7fff02c406f2 100644
--- a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
@@ -351,7 +351,7 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
@@ -364,7 +364,7 @@
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-microsom.dtsi b/arch/arm/boot/dts/imx6qdl-microsom.dtsi
index 86460e46d055..3d62401dbd7f 100644
--- a/arch/arm/boot/dts/imx6qdl-microsom.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-microsom.dtsi
@@ -143,7 +143,7 @@
 &uart4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_microsom_brcm_bt &pinctrl_microsom_uart4>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi b/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi
index e456b5cc1b03..cfd50ea1ed48 100644
--- a/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nit6xlite.dtsi
@@ -250,6 +250,7 @@
 	txd3-skew-ps = <0>;
 	interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_HIGH>,
 			      <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+	fsl,err006687-workaround-present;
 	status = "okay";
 };
 
@@ -591,7 +592,7 @@
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
index 657da6b6ccd2..9677bf323823 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
@@ -385,6 +385,7 @@
 	txd3-skew-ps = <0>;
 	interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_HIGH>,
 			      <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+	fsl,err006687-workaround-present;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
index 73915db704a0..97d9c333902b 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
@@ -287,6 +287,7 @@
 	txd3-skew-ps = <0>;
 	interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_HIGH>,
 			      <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+	fsl,err006687-workaround-present;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
index d354d406954d..6aa193fb283f 100644
--- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
@@ -155,6 +155,7 @@
 	phy-mode = "rgmii";
 	interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_HIGH>,
 			      <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+	fsl,err006687-workaround-present;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi b/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
index c47fe6c79b36..f65fdfc2536d 100644
--- a/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
@@ -273,6 +273,7 @@
 	txd3-skew-ps = <0>;
 	interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_HIGH>,
 			      <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+	fsl,err006687-workaround-present;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
index 5248e7bd2b06..d77ea9423bbc 100644
--- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
@@ -501,6 +501,12 @@
 				MX6QDL_PAD_SD4_DAT7__SD4_DATA7		0x17059
 			>;
 		};
+
+		pinctrl_wdog: wdoggrp {
+			fsl,pins = <
+				MX6QDL_PAD_GPIO_1__WDOG2_B		0x1b0b0
+			>;
+		};
 	};
 
 	gpio_leds {
@@ -533,7 +539,7 @@
 &pcie {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_pcie>;
-	reset-gpio = <&gpio7 12 0>;
+	reset-gpio = <&gpio7 12 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
@@ -596,3 +602,14 @@
 	no-1-8-v;
 	status = "okay";
 };
+
+&wdog1 {
+	status = "disabled";
+};
+
+&wdog2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_wdog>;
+	fsl,ext-reset-output;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx6qdl-tx6.dtsi b/arch/arm/boot/dts/imx6qdl-tx6.dtsi
index 39b85aef93e1..ac9529f85593 100644
--- a/arch/arm/boot/dts/imx6qdl-tx6.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-tx6.dtsi
@@ -689,21 +689,21 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1 &pinctrl_uart1_rtscts>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2 &pinctrl_uart2_rtscts>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3 &pinctrl_uart3_rtscts>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
index 8e7c40e114dd..3ffe00c557f1 100644
--- a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
@@ -211,6 +211,7 @@
 	phy-reset-gpios = <&gpio3 29 0>;
 	interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_HIGH>,
 			      <&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+	fsl,err006687-workaround-present;
 	status = "okay";
 };
 
@@ -233,7 +234,7 @@
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index ed613ebe0812..b620ac884cfd 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -185,6 +185,7 @@
 			cache-level = <2>;
 			arm,tag-latency = <4 2 3>;
 			arm,data-latency = <4 2 3>;
+			arm,shared-override;
 		};
 
 		pcie: pcie@0x01000000 {
@@ -1100,6 +1101,7 @@
 			ocotp: ocotp@021bc000 {
 				compatible = "fsl,imx6q-ocotp", "syscon";
 				reg = <0x021bc000 0x4000>;
+				clocks = <&clks IMX6QDL_CLK_IIM>;
 			};
 
 			tzasc@021d0000 { /* TZASC1 */
@@ -1255,7 +1257,7 @@
 				#size-cells = <0>;
 				reg = <3>;
 
-				ipu1_di0_disp1: disp1-endpoint {
+				ipu1_di1_disp1: disp1-endpoint {
 				};
 
 				ipu1_di1_hdmi: hdmi-endpoint {
diff --git a/arch/arm/boot/dts/imx6sl-warp.dts b/arch/arm/boot/dts/imx6sl-warp.dts
index 058bcdceb81a..72c7745f51d3 100644
--- a/arch/arm/boot/dts/imx6sl-warp.dts
+++ b/arch/arm/boot/dts/imx6sl-warp.dts
@@ -84,7 +84,7 @@
 &uart5 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart5>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi
index d12b250342a6..542515089b1e 100644
--- a/arch/arm/boot/dts/imx6sl.dtsi
+++ b/arch/arm/boot/dts/imx6sl.dtsi
@@ -461,7 +461,7 @@
 					     <0 54 IRQ_TYPE_LEVEL_HIGH>,
 					     <0 127 IRQ_TYPE_LEVEL_HIGH>;
 
-				regulator-1p1@110 {
+				regulator-1p1 {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd1p1";
 					regulator-min-microvolt = <800000>;
@@ -475,7 +475,7 @@
 					anatop-max-voltage = <1375000>;
 				};
 
-				regulator-3p0@120 {
+				regulator-3p0 {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd3p0";
 					regulator-min-microvolt = <2800000>;
@@ -489,7 +489,7 @@
 					anatop-max-voltage = <3400000>;
 				};
 
-				regulator-2p5@130 {
+				regulator-2p5 {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd2p5";
 					regulator-min-microvolt = <2100000>;
@@ -503,7 +503,7 @@
 					anatop-max-voltage = <2850000>;
 				};
 
-				reg_arm: regulator-vddcore@140 {
+				reg_arm: regulator-vddcore {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddarm";
 					regulator-min-microvolt = <725000>;
@@ -520,7 +520,7 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_pu: regulator-vddpu@140 {
+				reg_pu: regulator-vddpu {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddpu";
 					regulator-min-microvolt = <725000>;
@@ -537,7 +537,7 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_soc: regulator-vddsoc@140 {
+				reg_soc: regulator-vddsoc {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddsoc";
 					regulator-min-microvolt = <725000>;
@@ -853,6 +853,7 @@
 			ocotp: ocotp@021bc000 {
 				compatible = "fsl,imx6sl-ocotp", "syscon";
 				reg = <0x021bc000 0x4000>;
+				clocks = <&clks IMX6SL_CLK_OCOTP>;
 			};
 
 			audmux: audmux@021d8000 {
diff --git a/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts b/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts
index ba62348d8284..9b817f3501a6 100644
--- a/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts
+++ b/arch/arm/boot/dts/imx6sx-nitrogen6sx.dts
@@ -326,7 +326,7 @@
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi
index e5eafe4d9a70..9d70cfd40aff 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dtsi
+++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi
@@ -273,7 +273,7 @@
 &uart5 { /* for bluetooth */
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart5>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
@@ -322,6 +322,12 @@
 	status = "okay";
 };
 
+&wdog1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_wdog>;
+	fsl,ext-reset-output;
+};
+
 &iomuxc {
 	imx6x-sdb {
 		pinctrl_audmux: audmuxgrp {
@@ -588,5 +594,11 @@
 				MX6SX_PAD_SD4_DATA6__GPIO6_IO_20	0x17059 /* WP */
 			>;
 		};
+
+		pinctrl_wdog: wdoggrp {
+			fsl,pins = <
+				MX6SX_PAD_GPIO1_IO13__WDOG1_WDOG_ANY 0x30b0
+			>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi
index 6a993bfda248..2863c52be6f5 100644
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -547,7 +547,7 @@
 					     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
 
-				regulator-1p1@110 {
+				regulator-1p1 {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd1p1";
 					regulator-min-microvolt = <800000>;
@@ -561,7 +561,7 @@
 					anatop-max-voltage = <1375000>;
 				};
 
-				regulator-3p0@120 {
+				regulator-3p0 {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd3p0";
 					regulator-min-microvolt = <2800000>;
@@ -575,7 +575,7 @@
 					anatop-max-voltage = <3400000>;
 				};
 
-				regulator-2p5@130 {
+				regulator-2p5 {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd2p5";
 					regulator-min-microvolt = <2100000>;
@@ -589,7 +589,7 @@
 					anatop-max-voltage = <2875000>;
 				};
 
-				reg_arm: regulator-vddcore@140 {
+				reg_arm: regulator-vddcore {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddarm";
 					regulator-min-microvolt = <725000>;
@@ -606,7 +606,7 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_pcie: regulator-vddpcie@140 {
+				reg_pcie: regulator-vddpcie {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddpcie";
 					regulator-min-microvolt = <725000>;
@@ -622,7 +622,7 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_soc: regulator-vddsoc@140 {
+				reg_soc: regulator-vddsoc {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddsoc";
 					regulator-min-microvolt = <725000>;
diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dts b/arch/arm/boot/dts/imx6ul-14x14-evk.dts
index 668a72997590..e281d5087d4a 100644
--- a/arch/arm/boot/dts/imx6ul-14x14-evk.dts
+++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dts
@@ -22,6 +22,14 @@
 		reg = <0x80000000 0x20000000>;
 	};
 
+	backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm1 0 5000000>;
+		brightness-levels = <0 4 8 16 32 64 128 255>;
+		default-brightness-level = <6>;
+		status = "okay";
+	};
+
 	regulators {
 		compatible = "simple-bus";
 		#address-cells = <1>;
@@ -125,6 +133,46 @@
 	};
 };
 
+
+&lcdif {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_lcdif_dat
+		     &pinctrl_lcdif_ctrl>;
+	display = <&display0>;
+	status = "okay";
+
+	display0: display {
+		bits-per-pixel = <16>;
+		bus-width = <24>;
+
+		display-timings {
+			native-mode = <&timing0>;
+
+			timing0: timing0 {
+				clock-frequency = <9200000>;
+				hactive = <480>;
+				vactive = <272>;
+				hfront-porch = <8>;
+				hback-porch = <4>;
+				hsync-len = <41>;
+				vback-porch = <2>;
+				vfront-porch = <4>;
+				vsync-len = <10>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				de-active = <1>;
+				pixelclk-active = <0>;
+			};
+		};
+	};
+};
+
+&pwm1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm1>;
+	status = "okay";
+};
+
 &qspi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_qspi>;
@@ -146,6 +194,7 @@
 			  <&clks IMX6UL_CLK_SAI2>;
 	assigned-clock-parents = <&clks IMX6UL_CLK_PLL4_AUDIO_DIV>;
 	assigned-clock-rates = <0>, <12288000>;
+	fsl,sai-mclk-direction-output;
 	status = "okay";
 };
 
@@ -171,7 +220,7 @@
 &uart2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
@@ -207,6 +256,12 @@
 	status = "okay";
 };
 
+&wdog1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_wdog>;
+	fsl,ext-reset-output;
+};
+
 &iomuxc {
 	pinctrl-names = "default";
 
@@ -435,4 +490,10 @@
 			MX6UL_PAD_NAND_DATA03__USDHC2_DATA3 0x17059
 		>;
 	};
+
+	pinctrl_wdog: wdoggrp {
+		fsl,pins = <
+			MX6UL_PAD_LCD_RESET__WDOG1_WDOG_ANY    0x30b0
+		>;
+	};
 };
diff --git a/arch/arm/boot/dts/imx6ul-pico-hobbit.dts b/arch/arm/boot/dts/imx6ul-pico-hobbit.dts
index 8ce1fec36e86..86f68faded0e 100644
--- a/arch/arm/boot/dts/imx6ul-pico-hobbit.dts
+++ b/arch/arm/boot/dts/imx6ul-pico-hobbit.dts
@@ -151,8 +151,8 @@
 	phy-mode = "rmii";
 	phy-handle = <&ethphy1>;
 	status = "okay";
-	phy-reset-gpios = <&gpio2 15 GPIO_ACTIVE_LOW>;
-	phy-reset-duration = <11>;
+	phy-reset-gpios = <&gpio1 28 GPIO_ACTIVE_LOW>;
+	phy-reset-duration = <1>;
 
 	mdio {
 		#address-cells = <1>;
@@ -286,7 +286,7 @@
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6ul-tx6ul-mainboard.dts b/arch/arm/boot/dts/imx6ul-tx6ul-mainboard.dts
index d25899b71575..7c5dd1b316ca 100644
--- a/arch/arm/boot/dts/imx6ul-tx6ul-mainboard.dts
+++ b/arch/arm/boot/dts/imx6ul-tx6ul-mainboard.dts
@@ -146,12 +146,12 @@
 
 &uart1 {
 	pinctrl-0 = <&pinctrl_uart1>;
-	/delete-property/ fsl,uart-has-rtscts;
+	/delete-property/ uart-has-rtscts;
 };
 
 &uart2 {
 	pinctrl-0 = <&pinctrl_uart2>;
-	/delete-property/ fsl,uart-has-rtscts;
+	/delete-property/ uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6ul-tx6ul.dtsi b/arch/arm/boot/dts/imx6ul-tx6ul.dtsi
index 437e9aad5920..530e9ca13a74 100644
--- a/arch/arm/boot/dts/imx6ul-tx6ul.dtsi
+++ b/arch/arm/boot/dts/imx6ul-tx6ul.dtsi
@@ -563,21 +563,21 @@
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1 &pinctrl_uart1_rtscts>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2 &pinctrl_uart2_rtscts>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart5 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart5 &pinctrl_uart5_rtscts>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi
index 4356b655ef02..33b95d78831a 100644
--- a/arch/arm/boot/dts/imx6ul.dtsi
+++ b/arch/arm/boot/dts/imx6ul.dtsi
@@ -36,6 +36,9 @@
 		serial5 = &uart6;
 		serial6 = &uart7;
 		serial7 = &uart8;
+		sai1 = &sai1;
+		sai2 = &sai2;
+		sai3 = &sai3;
 		spi0 = &ecspi1;
 		spi1 = &ecspi2;
 		spi2 = &ecspi3;
@@ -512,7 +515,7 @@
 					     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
 
-				reg_3p0: regulator-3p0@120 {
+				reg_3p0: regulator-3p0 {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vdd3p0";
 					regulator-min-microvolt = <2625000>;
@@ -526,7 +529,7 @@
 					anatop-enable-bit = <0>;
 				};
 
-				reg_arm: regulator-vddcore@140 {
+				reg_arm: regulator-vddcore {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "cpu";
 					regulator-min-microvolt = <725000>;
@@ -543,7 +546,7 @@
 					anatop-max-voltage = <1450000>;
 				};
 
-				reg_soc: regulator-vddsoc@140 {
+				reg_soc: regulator-vddsoc {
 					compatible = "fsl,anatop-regulator";
 					regulator-name = "vddsoc";
 					regulator-min-microvolt = <725000>;
diff --git a/arch/arm/boot/dts/imx7-colibri-eval-v3.dtsi b/arch/arm/boot/dts/imx7-colibri-eval-v3.dtsi
new file mode 100644
index 000000000000..1545661df583
--- /dev/null
+++ b/arch/arm/boot/dts/imx7-colibri-eval-v3.dtsi
@@ -0,0 +1,148 @@
+/*
+ * Copyright 2016 Toradex AG
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/ {
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+};
+
+&bl {
+	brightness-levels = <0 4 8 16 32 64 128 255>;
+	default-brightness-level = <6>;
+	status = "okay";
+};
+
+&adc1 {
+	status = "okay";
+};
+
+&adc2 {
+	status = "okay";
+};
+
+&fec1 {
+	status = "okay";
+};
+
+&i2c4 {
+	status = "okay";
+
+	/* M41T0M6 real time clock on carrier board */
+	rtc: m41t0m6@68 {
+		compatible = "st,m41t00";
+		reg = <0x68>;
+	};
+};
+
+&lcdif {
+	display = <&display0>;
+	status = "okay";
+
+	display0: lcd-display {
+		bits-per-pixel = <16>;
+		bus-width = <18>;
+
+		display-timings {
+			native-mode = <&timing_vga>;
+
+			/* Standard VGA timing */
+			timing_vga: 640x480 {
+				clock-frequency = <25175000>;
+				hactive = <640>;
+				vactive = <480>;
+				hback-porch = <40>;
+				hfront-porch = <24>;
+				vback-porch = <32>;
+				vfront-porch = <11>;
+				hsync-len = <96>;
+				vsync-len = <2>;
+				de-active = <1>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				pixelclk-active = <0>;
+			};
+		};
+	};
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&pwm2 {
+	status = "okay";
+};
+
+&pwm3 {
+	status = "okay";
+};
+
+&pwm4 {
+	status = "okay";
+};
+
+&uart1 {
+	status = "okay";
+};
+
+&uart2 {
+	status = "okay";
+};
+
+&uart3 {
+	status = "okay";
+};
+
+&usbotg1 {
+	status = "okay";
+};
+
+&usdhc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc1 &pinctrl_cd_usdhc1>;
+	no-1-8-v;
+	cd-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
+	keep-power-in-suspend;
+	wakeup-source;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx7-colibri.dtsi b/arch/arm/boot/dts/imx7-colibri.dtsi
new file mode 100644
index 000000000000..0a9d3a822fc0
--- /dev/null
+++ b/arch/arm/boot/dts/imx7-colibri.dtsi
@@ -0,0 +1,571 @@
+/*
+ * Copyright 2016 Toradex AG
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/ {
+	bl: backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm1 0 5000000>;
+	};
+
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "3P3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+
+	reg_vref_1v8: regulator-vref-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "vref-1v8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+};
+
+&adc1 {
+	vref-supply = <&reg_vref_1v8>;
+};
+
+&adc2 {
+	vref-supply = <&reg_vref_1v8>;
+};
+
+&cpu0 {
+	arm-supply = <&reg_DCDC2>;
+};
+
+&fec1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_enet1>;
+	clocks = <&clks IMX7D_ENET_AXI_ROOT_CLK>,
+		<&clks IMX7D_ENET_AXI_ROOT_CLK>,
+		<&clks IMX7D_ENET1_TIME_ROOT_CLK>,
+		<&clks IMX7D_PLL_ENET_MAIN_50M_CLK>;
+	clock-names = "ipg", "ahb", "ptp", "enet_clk_ref";
+	assigned-clocks = <&clks IMX7D_ENET1_TIME_ROOT_SRC>,
+			  <&clks IMX7D_ENET1_TIME_ROOT_CLK>;
+	assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>;
+	assigned-clock-rates = <0>, <100000000>;
+	phy-mode = "rmii";
+	phy-supply = <&reg_LDO1>;
+	fsl,magic-packet;
+};
+
+&i2c1 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c1 &pinctrl_i2c1_int>;
+	status = "okay";
+
+	ad7879@2c {
+		compatible = "adi,ad7879-1";
+		reg = <0x2c>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <13 IRQ_TYPE_EDGE_FALLING>;
+		touchscreen-max-pressure = <4096>;
+		adi,resistance-plate-x = <120>;
+		adi,first-conversion-delay = /bits/ 8 <3>;
+		adi,acquisition-time = /bits/ 8 <1>;
+		adi,median-filter-size = /bits/ 8 <2>;
+		adi,averaging = /bits/ 8 <1>;
+		adi,conversion-interval = /bits/ 8 <255>;
+	};
+
+	pmic@33 {
+		compatible = "ricoh,rn5t567";
+		reg = <0x33>;
+
+		regulators {
+			reg_DCDC1: DCDC1 {  /* V1.0_SOC */
+				regulator-min-microvolt =  <975000>;
+				regulator-max-microvolt = <1125000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_DCDC2: DCDC2 { /* V1.1_ARM */
+				regulator-min-microvolt =  <975000>;
+				regulator-max-microvolt = <1125000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_DCDC3: DCDC3 { /* V1.8 */
+				regulator-min-microvolt = <1775000>;
+				regulator-max-microvolt = <1825000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_DCDC4: DCDC4 { /* V1.35_DRAM */
+				regulator-min-microvolt = <1325000>;
+				regulator-max-microvolt = <1375000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_LDO1: LDO1 { /* PWR_EN_+V3.3_ETH */
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			reg_LDO2: LDO2 { /* +V1.8_SD */
+				regulator-min-microvolt = <1775000>;
+				regulator-max-microvolt = <3325000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_LDO3: LDO3 { /* PWR_EN_+V3.3_LPSR */
+				regulator-min-microvolt = <3275000>;
+				regulator-max-microvolt = <3325000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_LDO4: LDO4 { /* V1.8_LPSR */
+				regulator-min-microvolt = <1775000>;
+				regulator-max-microvolt = <1825000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			reg_LDO5: LDO5 { /* PWR_EN_+V3.3 */
+				regulator-min-microvolt = <1775000>;
+				regulator-max-microvolt = <1825000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
+};
+
+&i2c4 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c4>;
+};
+
+&lcdif {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_lcdif_dat
+		     &pinctrl_lcdif_ctrl>;
+};
+
+&pwm1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm1>;
+};
+
+&pwm2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm2>;
+};
+
+&pwm3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm3>;
+};
+
+&pwm4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm4>;
+};
+
+&reg_1p0d {
+	vin-supply = <&reg_DCDC3>;
+};
+
+&snvs_pwrkey {
+	status = "disabled";
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1 &pinctrl_uart1_ctrl1 &pinctrl_uart1_ctrl2>;
+	assigned-clocks = <&clks IMX7D_UART1_ROOT_SRC>;
+	assigned-clock-parents = <&clks IMX7D_OSC_24M_CLK>;
+	uart-has-rtscts;
+	fsl,dte-mode;
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2>;
+	assigned-clocks = <&clks IMX7D_UART2_ROOT_SRC>;
+	assigned-clock-parents = <&clks IMX7D_OSC_24M_CLK>;
+	uart-has-rtscts;
+	fsl,dte-mode;
+};
+
+&uart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart3>;
+	assigned-clocks = <&clks IMX7D_UART3_ROOT_SRC>;
+	assigned-clock-parents = <&clks IMX7D_OSC_24M_CLK>;
+	fsl,dte-mode;
+};
+
+&usbotg1 {
+	dr_mode = "host";
+};
+
+&iomuxc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_gpio1 &pinctrl_gpio2 &pinctrl_gpio3 &pinctrl_gpio4>;
+
+	pinctrl_gpio1: gpio1-grp {
+		fsl,pins = <
+			MX7D_PAD_ENET1_RGMII_RD3__GPIO7_IO3	0x14 /* SODIMM 55 */
+			MX7D_PAD_ENET1_RGMII_RD2__GPIO7_IO2	0x14 /* SODIMM 63 */
+			MX7D_PAD_SD1_RESET_B__GPIO5_IO2		0X14 /* SODIMM 73 */
+			MX7D_PAD_SAI1_RX_SYNC__GPIO6_IO16	0X14 /* SODIMM 77 */
+			MX7D_PAD_EPDC_DATA09__GPIO2_IO9		0x14 /* SODIMM 89 */
+			MX7D_PAD_EPDC_DATA08__GPIO2_IO8		0x14 /* SODIMM 91 */
+			MX7D_PAD_LCD_RESET__GPIO3_IO4		0x14 /* SODIMM 93 */
+			MX7D_PAD_EPDC_DATA13__GPIO2_IO13	0x14 /* SODIMM 95 */
+			MX7D_PAD_ENET1_RGMII_TXC__GPIO7_IO11	0x14 /* SODIMM 99 */
+			MX7D_PAD_EPDC_DATA10__GPIO2_IO10	0x14 /* SODIMM 105 */
+			MX7D_PAD_EPDC_DATA15__GPIO2_IO15	0x14 /* SODIMM 107 */
+			MX7D_PAD_EPDC_DATA00__GPIO2_IO0		0x14 /* SODIMM 111 */
+			MX7D_PAD_EPDC_DATA01__GPIO2_IO1		0x14 /* SODIMM 113 */
+			MX7D_PAD_EPDC_DATA02__GPIO2_IO2		0x14 /* SODIMM 115 */
+			MX7D_PAD_EPDC_DATA03__GPIO2_IO3		0x14 /* SODIMM 117 */
+			MX7D_PAD_EPDC_DATA04__GPIO2_IO4		0x14 /* SODIMM 119 */
+			MX7D_PAD_EPDC_DATA05__GPIO2_IO5		0x14 /* SODIMM 121 */
+			MX7D_PAD_EPDC_DATA06__GPIO2_IO6		0x14 /* SODIMM 123 */
+			MX7D_PAD_EPDC_DATA07__GPIO2_IO7		0x14 /* SODIMM 125 */
+			MX7D_PAD_EPDC_SDCE2__GPIO2_IO22		0x14 /* SODIMM 127 */
+			MX7D_PAD_UART3_RTS_B__GPIO4_IO6		0x14 /* SODIMM 131 */
+			MX7D_PAD_EPDC_GDRL__GPIO2_IO26		0x14 /* SODIMM 133 */
+			MX7D_PAD_SAI1_RX_BCLK__GPIO6_IO17	0x14 /* SODIMM 24 */
+			MX7D_PAD_SD2_DATA2__GPIO5_IO16		0x14 /* SODIMM 100 */
+			MX7D_PAD_SD2_DATA3__GPIO5_IO17		0x14 /* SODIMM 102 */
+			MX7D_PAD_EPDC_GDSP__GPIO2_IO27		0x14 /* SODIMM 104 */
+			MX7D_PAD_EPDC_BDR0__GPIO2_IO28		0x14 /* SODIMM 106 */
+			MX7D_PAD_EPDC_BDR1__GPIO2_IO29		0x14 /* SODIMM 110 */
+			MX7D_PAD_EPDC_PWR_COM__GPIO2_IO30	0x14 /* SODIMM 112 */
+			MX7D_PAD_EPDC_SDCLK__GPIO2_IO16		0x14 /* SODIMM 114 */
+			MX7D_PAD_EPDC_SDLE__GPIO2_IO17		0x14 /* SODIMM 116 */
+			MX7D_PAD_EPDC_SDOE__GPIO2_IO18		0x14 /* SODIMM 118 */
+			MX7D_PAD_EPDC_SDSHR__GPIO2_IO19		0x14 /* SODIMM 120 */
+			MX7D_PAD_EPDC_SDCE0__GPIO2_IO20		0x14 /* SODIMM 122 */
+			MX7D_PAD_EPDC_SDCE1__GPIO2_IO21		0x14 /* SODIMM 124 */
+			MX7D_PAD_EPDC_DATA14__GPIO2_IO14	0x14 /* SODIMM 126 */
+			MX7D_PAD_EPDC_PWR_STAT__GPIO2_IO31	0x14 /* SODIMM 128 */
+			MX7D_PAD_EPDC_SDCE3__GPIO2_IO23		0x14 /* SODIMM 130 */
+			MX7D_PAD_EPDC_GDCLK__GPIO2_IO24		0x14 /* SODIMM 132 */
+			MX7D_PAD_EPDC_GDOE__GPIO2_IO25		0x14 /* SODIMM 134 */
+			MX7D_PAD_EPDC_DATA12__GPIO2_IO12	0x14 /* SODIMM 150 */
+			MX7D_PAD_EPDC_DATA11__GPIO2_IO11	0x14 /* SODIMM 152 */
+			MX7D_PAD_SD2_CLK__GPIO5_IO12		0x14 /* SODIMM 184 */
+			MX7D_PAD_SD2_CMD__GPIO5_IO13		0x14 /* SODIMM 186 */
+		>;
+	};
+
+	pinctrl_gpio2: gpio2-grp { /* On X22 Camera interface */
+		fsl,pins = <
+			MX7D_PAD_ECSPI2_SS0__GPIO4_IO23		0x14 /* SODIMM 65 */
+			MX7D_PAD_SD1_CD_B__GPIO5_IO0		0x14 /* SODIMM 69 */
+			MX7D_PAD_SD1_WP__GPIO5_IO1		0x14 /* SODIMM 71 */
+			MX7D_PAD_I2C4_SDA__GPIO4_IO15		0x14 /* SODIMM 75 */
+			MX7D_PAD_ECSPI1_MISO__GPIO4_IO18	0x14 /* SODIMM 79 */
+			MX7D_PAD_I2C3_SCL__GPIO4_IO12		0x14 /* SODIMM 81 */
+			MX7D_PAD_ECSPI2_MISO__GPIO4_IO22	0x14 /* SODIMM 85 */
+			MX7D_PAD_ECSPI1_SS0__GPIO4_IO19		0x14 /* SODIMM 97 */
+			MX7D_PAD_ECSPI1_SCLK__GPIO4_IO16	0x14 /* SODIMM 101 */
+			MX7D_PAD_ECSPI1_MOSI__GPIO4_IO17	0x14 /* SODIMM 103 */
+			MX7D_PAD_I2C3_SDA__GPIO4_IO13		0x14 /* SODIMM 94 */
+			MX7D_PAD_I2C4_SCL__GPIO4_IO14		0x14 /* SODIMM 96 */
+			MX7D_PAD_SD2_RESET_B__GPIO5_IO11	0x14 /* SODIMM 98 */
+		>;
+	};
+
+	pinctrl_gpio3: gpio3-grp { /* LCD 18-23 */
+		fsl,pins = <
+			MX7D_PAD_LCD_DATA18__GPIO3_IO23		0x14 /* SODIMM 136 */
+			MX7D_PAD_LCD_DATA19__GPIO3_IO24		0x14 /* SODIMM 138 */
+			MX7D_PAD_LCD_DATA20__GPIO3_IO25		0x14 /* SODIMM 140 */
+			MX7D_PAD_LCD_DATA21__GPIO3_IO26		0x14 /* SODIMM 142 */
+			MX7D_PAD_LCD_DATA22__GPIO3_IO27		0x14 /* SODIMM 146 */
+			MX7D_PAD_LCD_DATA23__GPIO3_IO28		0x14 /* SODIMM 148 */
+		>;
+	};
+
+	pinctrl_gpio4: gpio4-grp { /* Alternatively CAN2 */
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO15__GPIO1_IO15		0x14 /* SODIMM 178 */
+			MX7D_PAD_GPIO1_IO14__GPIO1_IO14		0x14 /* SODIMM 188 */
+		>;
+	};
+
+	pinctrl_i2c1_int: i2c1-int-grp { /* PMIC / TOUCH */
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO13__GPIO1_IO13	0x79
+		>;
+	};
+
+	pinctrl_enet1: enet1grp {
+		fsl,pins = <
+			MX7D_PAD_ENET1_CRS__GPIO7_IO14			0x14
+			MX7D_PAD_ENET1_RGMII_RX_CTL__ENET1_RGMII_RX_CTL	0x73
+			MX7D_PAD_ENET1_RGMII_RD0__ENET1_RGMII_RD0	0x73
+			MX7D_PAD_ENET1_RGMII_RD1__ENET1_RGMII_RD1	0x73
+			MX7D_PAD_ENET1_RGMII_RXC__ENET1_RX_ER		0x73
+
+			MX7D_PAD_ENET1_RGMII_TX_CTL__ENET1_RGMII_TX_CTL	0x73
+			MX7D_PAD_ENET1_RGMII_TD0__ENET1_RGMII_TD0	0x73
+			MX7D_PAD_ENET1_RGMII_TD1__ENET1_RGMII_TD1	0x73
+			MX7D_PAD_GPIO1_IO12__CCM_ENET_REF_CLK1		0x73
+			MX7D_PAD_SD2_CD_B__ENET1_MDIO			0x3
+			MX7D_PAD_SD2_WP__ENET1_MDC			0x3
+		>;
+	};
+
+	pinctrl_ecspi3_cs: ecspi3-cs-grp {
+		fsl,pins = <
+			MX7D_PAD_I2C2_SDA__GPIO4_IO11		0x14
+		>;
+	};
+
+	pinctrl_ecspi3: ecspi3-grp {
+		fsl,pins = <
+			MX7D_PAD_I2C1_SCL__ECSPI3_MISO		0x2
+			MX7D_PAD_I2C1_SDA__ECSPI3_MOSI		0x2
+			MX7D_PAD_I2C2_SCL__ECSPI3_SCLK		0x2
+		>;
+	};
+
+	pinctrl_flexcan2: flexcan2-grp {
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO14__FLEXCAN2_RX	0x59
+			MX7D_PAD_GPIO1_IO15__FLEXCAN2_TX	0x59
+		>;
+	};
+
+	pinctrl_gpmi_nand: gpmi-nand-grp {
+		fsl,pins = <
+			MX7D_PAD_SD3_CLK__NAND_CLE		0x71
+			MX7D_PAD_SD3_CMD__NAND_ALE		0x71
+			MX7D_PAD_SAI1_TX_BCLK__NAND_CE0_B	0x71
+			MX7D_PAD_SAI1_RX_DATA__NAND_CE1_B	0x71
+			MX7D_PAD_SAI1_TX_DATA__NAND_READY_B	0x74
+			MX7D_PAD_SD3_STROBE__NAND_RE_B		0x71
+			MX7D_PAD_SD3_RESET_B__NAND_WE_B		0x71
+			MX7D_PAD_SD3_DATA0__NAND_DATA00		0x71
+			MX7D_PAD_SD3_DATA1__NAND_DATA01		0x71
+			MX7D_PAD_SD3_DATA2__NAND_DATA02		0x71
+			MX7D_PAD_SD3_DATA3__NAND_DATA03		0x71
+			MX7D_PAD_SD3_DATA4__NAND_DATA04		0x71
+			MX7D_PAD_SD3_DATA5__NAND_DATA05		0x71
+			MX7D_PAD_SD3_DATA6__NAND_DATA06		0x71
+			MX7D_PAD_SD3_DATA7__NAND_DATA07		0x71
+		>;
+	};
+
+	pinctrl_i2c4: i2c4-grp {
+		fsl,pins = <
+			MX7D_PAD_ENET1_RGMII_TD3__I2C4_SDA	0x4000007f
+			MX7D_PAD_ENET1_RGMII_TD2__I2C4_SCL	0x4000007f
+		>;
+	};
+
+	pinctrl_lcdif_dat: lcdif-dat-grp {
+		fsl,pins = <
+			MX7D_PAD_LCD_DATA00__LCD_DATA0		0x79
+			MX7D_PAD_LCD_DATA01__LCD_DATA1		0x79
+			MX7D_PAD_LCD_DATA02__LCD_DATA2		0x79
+			MX7D_PAD_LCD_DATA03__LCD_DATA3		0x79
+			MX7D_PAD_LCD_DATA04__LCD_DATA4		0x79
+			MX7D_PAD_LCD_DATA05__LCD_DATA5		0x79
+			MX7D_PAD_LCD_DATA06__LCD_DATA6		0x79
+			MX7D_PAD_LCD_DATA07__LCD_DATA7		0x79
+			MX7D_PAD_LCD_DATA08__LCD_DATA8		0x79
+			MX7D_PAD_LCD_DATA09__LCD_DATA9		0x79
+			MX7D_PAD_LCD_DATA10__LCD_DATA10		0x79
+			MX7D_PAD_LCD_DATA11__LCD_DATA11		0x79
+			MX7D_PAD_LCD_DATA12__LCD_DATA12		0x79
+			MX7D_PAD_LCD_DATA13__LCD_DATA13		0x79
+			MX7D_PAD_LCD_DATA14__LCD_DATA14		0x79
+			MX7D_PAD_LCD_DATA15__LCD_DATA15		0x79
+			MX7D_PAD_LCD_DATA16__LCD_DATA16		0x79
+			MX7D_PAD_LCD_DATA17__LCD_DATA17		0x79
+		>;
+	};
+
+	pinctrl_lcdif_dat_24: lcdif-dat-24-grp {
+		fsl,pins = <
+			MX7D_PAD_LCD_DATA18__LCD_DATA18		0x79
+			MX7D_PAD_LCD_DATA19__LCD_DATA19		0x79
+			MX7D_PAD_LCD_DATA20__LCD_DATA20		0x79
+			MX7D_PAD_LCD_DATA21__LCD_DATA21		0x79
+			MX7D_PAD_LCD_DATA22__LCD_DATA22		0x79
+			MX7D_PAD_LCD_DATA23__LCD_DATA23		0x79
+		>;
+	};
+
+	pinctrl_lcdif_ctrl: lcdif-ctrl-grp {
+		fsl,pins = <
+			MX7D_PAD_LCD_CLK__LCD_CLK		0x79
+			MX7D_PAD_LCD_ENABLE__LCD_ENABLE		0x79
+			MX7D_PAD_LCD_VSYNC__LCD_VSYNC		0x79
+			MX7D_PAD_LCD_HSYNC__LCD_HSYNC		0x79
+		>;
+	};
+
+	pinctrl_pwm1: pwm1-grp {
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO08__PWM1_OUT		0x79
+		>;
+	};
+
+	pinctrl_pwm2: pwm2-grp {
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO09__PWM2_OUT		0x79
+		>;
+	};
+
+	pinctrl_pwm3: pwm3-grp {
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO10__PWM3_OUT		0x79
+		>;
+	};
+
+	pinctrl_pwm4: pwm4-grp {
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO11__PWM4_OUT		0x79
+		>;
+	};
+
+	pinctrl_uart1: uart1-grp {
+		fsl,pins = <
+			MX7D_PAD_UART1_TX_DATA__UART1_DTE_RX	0x79
+			MX7D_PAD_UART1_RX_DATA__UART1_DTE_TX	0x79
+			MX7D_PAD_SAI2_TX_BCLK__UART1_DTE_CTS	0x79
+			MX7D_PAD_SAI2_TX_SYNC__UART1_DTE_RTS	0x79
+		>;
+	};
+
+	pinctrl_uart1_ctrl1: uart1-ctrl1-grp {
+		fsl,pins = <
+			MX7D_PAD_SD2_DATA1__GPIO5_IO15		0x14 /* DCD */
+			MX7D_PAD_SD2_DATA0__GPIO5_IO14		0x14 /* DTR */
+		>;
+	};
+
+	pinctrl_uart2: uart2-grp {
+		fsl,pins = <
+			MX7D_PAD_UART2_TX_DATA__UART2_DTE_RX 0x79
+			MX7D_PAD_UART2_RX_DATA__UART2_DTE_TX 0x79
+			MX7D_PAD_SAI2_RX_DATA__UART2_DTE_RTS 0x79
+			MX7D_PAD_SAI2_TX_DATA__UART2_DTE_CTS 0x79
+		>;
+	};
+	pinctrl_uart3: uart3-grp {
+		fsl,pins = <
+			MX7D_PAD_UART3_TX_DATA__UART3_DTE_RX 0x79
+			MX7D_PAD_UART3_RX_DATA__UART3_DTE_TX 0x79
+		>;
+	};
+
+	pinctrl_usbotg2_reg: gpio-usbotg2-vbus {
+		fsl,pins = <
+			MX7D_PAD_UART3_CTS_B__GPIO4_IO7	0x14 /* SODIMM 129 USBH PEN */
+		>;
+	};
+
+	pinctrl_usdhc1: usdhc1-grp {
+		fsl,pins = <
+			MX7D_PAD_SD1_CMD__SD1_CMD	0x59
+			MX7D_PAD_SD1_CLK__SD1_CLK	0x19
+			MX7D_PAD_SD1_DATA0__SD1_DATA0	0x59
+			MX7D_PAD_SD1_DATA1__SD1_DATA1	0x59
+			MX7D_PAD_SD1_DATA2__SD1_DATA2	0x59
+			MX7D_PAD_SD1_DATA3__SD1_DATA3	0x59
+		>;
+	};
+
+	pinctrl_sai1: sai1-grp {
+		fsl,pins = <
+			MX7D_PAD_SAI1_MCLK__SAI1_MCLK           0x1f
+			MX7D_PAD_ENET1_RX_CLK__SAI1_TX_BCLK     0x1f
+			MX7D_PAD_SAI1_TX_SYNC__SAI1_TX_SYNC	0x1f
+			MX7D_PAD_ENET1_COL__SAI1_TX_DATA0	0x30
+			MX7D_PAD_ENET1_TX_CLK__SAI1_RX_DATA0	0x1f
+		>;
+	};
+};
+
+&iomuxc_lpsr {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_gpio_lpsr>;
+
+	pinctrl_gpio_lpsr: gpio1-grp {
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO01__GPIO1_IO1	0x59
+			MX7D_PAD_GPIO1_IO02__GPIO1_IO2	0x59
+			MX7D_PAD_GPIO1_IO03__GPIO1_IO3	0x59
+		>;
+	};
+
+	pinctrl_i2c1: i2c1-grp {
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO05__I2C1_SDA	0x4000007f
+			MX7D_PAD_GPIO1_IO04__I2C1_SCL	0x4000007f
+		>;
+	};
+
+	pinctrl_cd_usdhc1: usdhc1-cd-grp {
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO00__GPIO1_IO0	0x59 /* CD */
+		>;
+	};
+
+	pinctrl_uart1_ctrl2: uart1-ctrl2-grp {
+		fsl,pins = <
+			MX7D_PAD_GPIO1_IO07__GPIO1_IO7	0x14 /* DSR */
+			MX7D_PAD_GPIO1_IO06__GPIO1_IO6	0x14 /* RI */
+		>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx7d-cl-som-imx7.dts b/arch/arm/boot/dts/imx7d-cl-som-imx7.dts
index 48634519d13a..58b09bf1ba2d 100644
--- a/arch/arm/boot/dts/imx7d-cl-som-imx7.dts
+++ b/arch/arm/boot/dts/imx7d-cl-som-imx7.dts
@@ -12,7 +12,6 @@
 
 /dts-v1/;
 
-#include <dt-bindings/input/input.h>
 #include "imx7d.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/imx7d-colibri-eval-v3.dts b/arch/arm/boot/dts/imx7d-colibri-eval-v3.dts
new file mode 100644
index 000000000000..bd01d2cc642d
--- /dev/null
+++ b/arch/arm/boot/dts/imx7d-colibri-eval-v3.dts
@@ -0,0 +1,66 @@
+/*
+ * Copyright 2016 Toradex AG
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "imx7d-colibri.dtsi"
+#include "imx7-colibri-eval-v3.dtsi"
+
+/ {
+	model = "Toradex Colibri iMX7D on Colibri Evaluation Board V3";
+	compatible = "toradex,colibri-imx7d-eval-v3", "toradex,colibri-imx7d",
+		     "fsl,imx7d";
+
+	reg_usb_otg2_vbus: regulator-usb-otg2-vbus {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usbotg2_reg>;
+		regulator-name = "VCC_USB[1-4]";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio4 7 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&usbotg2 {
+	vbus-supply = <&reg_usb_otg2_vbus>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/imx7d-colibri.dtsi b/arch/arm/boot/dts/imx7d-colibri.dtsi
new file mode 100644
index 000000000000..3c2cb502b388
--- /dev/null
+++ b/arch/arm/boot/dts/imx7d-colibri.dtsi
@@ -0,0 +1,54 @@
+/*
+ * Copyright 2016 Toradex AG
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include "imx7d.dtsi"
+#include "imx7-colibri.dtsi"
+
+/ {
+	memory {
+		reg = <0x80000000 0x20000000>;
+	};
+};
+
+&usbotg2 {
+	dr_mode = "host";
+};
diff --git a/arch/arm/boot/dts/imx7d-nitrogen7.dts b/arch/arm/boot/dts/imx7d-nitrogen7.dts
index 1ce97800f0c5..ce08f180f213 100644
--- a/arch/arm/boot/dts/imx7d-nitrogen7.dts
+++ b/arch/arm/boot/dts/imx7d-nitrogen7.dts
@@ -42,7 +42,6 @@
 
 /dts-v1/;
 
-#include <dt-bindings/input/input.h>
 #include "imx7d.dtsi"
 
 / {
@@ -392,7 +391,7 @@
 	pinctrl-0 = <&pinctrl_uart6>;
 	assigned-clocks = <&clks IMX7D_UART6_ROOT_SRC>;
 	assigned-clock-parents = <&clks IMX7D_PLL_SYS_MAIN_240M_CLK>;
-	fsl,uart-has-rtscts;
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx7d-pinfunc.h b/arch/arm/boot/dts/imx7d-pinfunc.h
index eeda78347619..3f9f0d9c8094 100644
--- a/arch/arm/boot/dts/imx7d-pinfunc.h
+++ b/arch/arm/boot/dts/imx7d-pinfunc.h
@@ -594,7 +594,7 @@
 #define MX7D_PAD_UART2_RX_DATA__GPIO4_IO2                         0x0130 0x03A0 0x0000 0x5 0x0
 #define MX7D_PAD_UART2_RX_DATA__ENET2_MDIO                        0x0130 0x03A0 0x0000 0x6 0x0
 #define MX7D_PAD_UART2_TX_DATA__UART2_DCE_TX                      0x0134 0x03A4 0x0000 0x0 0x0
-#define MX7D_PAD_UART2_TX_DATA__UART2_DTE_RX                      0x0134 0x03A4 0x0000 0x0 0x0
+#define MX7D_PAD_UART2_TX_DATA__UART2_DTE_RX                      0x0134 0x03A4 0x06FC 0x0 0x3
 #define MX7D_PAD_UART2_TX_DATA__I2C2_SDA                          0x0134 0x03A4 0x05E0 0x1 0x0
 #define MX7D_PAD_UART2_TX_DATA__SAI3_RX_DATA0                     0x0134 0x03A4 0x06C8 0x2 0x0
 #define MX7D_PAD_UART2_TX_DATA__ECSPI1_RDY                        0x0134 0x03A4 0x0000 0x3 0x0
diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts
index b267f79e3059..95ee268ed510 100644
--- a/arch/arm/boot/dts/imx7d-sdb.dts
+++ b/arch/arm/boot/dts/imx7d-sdb.dts
@@ -42,7 +42,6 @@
 
 /dts-v1/;
 
-#include <dt-bindings/input/input.h>
 #include "imx7d.dtsi"
 
 / {
@@ -111,6 +110,32 @@
 	arm-supply = <&sw1a_reg>;
 };
 
+&ecspi3 {
+	fsl,spi-num-chipselects = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi3>;
+	cs-gpios = <&gpio5 9 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+
+	tsc2046@0 {
+		compatible = "ti,tsc2046";
+		reg = <0>;
+		spi-max-frequency = <1000000>;
+		pinctrl-names ="default";
+		pinctrl-0 = <&pinctrl_tsc2046_pendown>;
+		interrupt-parent = <&gpio2>;
+		interrupts = <29 0>;
+		pendown-gpio = <&gpio2 29 GPIO_ACTIVE_HIGH>;
+		ti,x-min = /bits/ 16 <0>;
+		ti,x-max = /bits/ 16 <0>;
+		ti,y-min = /bits/ 16 <0>;
+		ti,y-max = /bits/ 16 <0>;
+		ti,pressure-max = /bits/ 16 <0>;
+		ti,x-plat-ohms = /bits/ 16 <400>;
+		wakeup-source;
+	};
+};
+
 &fec1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet1>;
@@ -272,6 +297,44 @@
 	};
 };
 
+&lcdif {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_lcdif>;
+	display = <&display0>;
+	status = "okay";
+
+	display0: display {
+		bits-per-pixel = <16>;
+		bus-width = <24>;
+
+		display-timings {
+			native-mode = <&timing0>;
+
+			timing0: timing0 {
+				clock-frequency = <9200000>;
+				hactive = <480>;
+				vactive = <272>;
+				hfront-porch = <8>;
+				hback-porch = <4>;
+				hsync-len = <41>;
+				vback-porch = <2>;
+				vfront-porch = <4>;
+				vsync-len = <10>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+				de-active = <1>;
+				pixelclk-active = <0>;
+			};
+		};
+	};
+};
+
+&pwm1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm1>;
+	status = "okay";
+};
+
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart1>;
@@ -314,11 +377,26 @@
 	status = "okay";
 };
 
+&wdog1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_wdog>;
+	fsl,ext-reset-output;
+};
+
 &iomuxc {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_hog>;
 
 	imx7d-sdb {
+		pinctrl_ecspi3: ecspi3grp {
+			fsl,pins = <
+				MX7D_PAD_SAI2_TX_SYNC__ECSPI3_MISO	0x2
+				MX7D_PAD_SAI2_TX_BCLK__ECSPI3_MOSI	0x2
+				MX7D_PAD_SAI2_RX_DATA__ECSPI3_SCLK	0x2
+				MX7D_PAD_SD2_CD_B__GPIO5_IO9		0x59
+			>;
+		};
+
 		pinctrl_enet1: enet1grp {
 			fsl,pins = <
 				MX7D_PAD_GPIO1_IO10__ENET1_MDIO			0x3
@@ -390,6 +468,52 @@
 			>;
 		};
 
+		pinctrl_lcdif: lcdifgrp {
+			fsl,pins = <
+				MX7D_PAD_LCD_DATA00__LCD_DATA0		0x79
+				MX7D_PAD_LCD_DATA01__LCD_DATA1		0x79
+				MX7D_PAD_LCD_DATA02__LCD_DATA2		0x79
+				MX7D_PAD_LCD_DATA03__LCD_DATA3		0x79
+				MX7D_PAD_LCD_DATA04__LCD_DATA4		0x79
+				MX7D_PAD_LCD_DATA05__LCD_DATA5		0x79
+				MX7D_PAD_LCD_DATA06__LCD_DATA6		0x79
+				MX7D_PAD_LCD_DATA07__LCD_DATA7		0x79
+				MX7D_PAD_LCD_DATA08__LCD_DATA8		0x79
+				MX7D_PAD_LCD_DATA09__LCD_DATA9		0x79
+				MX7D_PAD_LCD_DATA10__LCD_DATA10		0x79
+				MX7D_PAD_LCD_DATA11__LCD_DATA11		0x79
+				MX7D_PAD_LCD_DATA12__LCD_DATA12		0x79
+				MX7D_PAD_LCD_DATA13__LCD_DATA13		0x79
+				MX7D_PAD_LCD_DATA14__LCD_DATA14		0x79
+				MX7D_PAD_LCD_DATA15__LCD_DATA15		0x79
+				MX7D_PAD_LCD_DATA16__LCD_DATA16		0x79
+				MX7D_PAD_LCD_DATA17__LCD_DATA17		0x79
+				MX7D_PAD_LCD_DATA18__LCD_DATA18		0x79
+				MX7D_PAD_LCD_DATA19__LCD_DATA19		0x79
+				MX7D_PAD_LCD_DATA20__LCD_DATA20		0x79
+				MX7D_PAD_LCD_DATA21__LCD_DATA21		0x79
+				MX7D_PAD_LCD_DATA22__LCD_DATA22		0x79
+				MX7D_PAD_LCD_DATA23__LCD_DATA23		0x79
+				MX7D_PAD_LCD_CLK__LCD_CLK		0x79
+				MX7D_PAD_LCD_ENABLE__LCD_ENABLE		0x79
+				MX7D_PAD_LCD_VSYNC__LCD_VSYNC		0x79
+				MX7D_PAD_LCD_HSYNC__LCD_HSYNC		0x79
+				MX7D_PAD_LCD_RESET__LCD_RESET		0x79
+			>;
+		};
+
+		pinctrl_pwm1: pwm1grp {
+			fsl,pins = <
+				MX7D_PAD_GPIO1_IO01__PWM1_OUT		0x110b0
+			>;
+		};
+
+		pinctrl_tsc2046_pendown: tsc2046_pendown {
+			fsl,pins = <
+				MX7D_PAD_EPDC_BDR1__GPIO2_IO29		0x59
+			>;
+		};
+
 		pinctrl_uart1: uart1grp {
 			fsl,pins = <
 				MX7D_PAD_UART1_TX_DATA__UART1_DCE_TX	0x79
@@ -512,5 +636,10 @@
 			>;
 		};
 
+		pinctrl_wdog: wdoggrp {
+			fsl,pins = <
+				MX7D_PAD_GPIO1_IO00__WDOD1_WDOG_B	0x74
+			>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi
index 6b3faa298417..51c13cbdffb7 100644
--- a/arch/arm/boot/dts/imx7d.dtsi
+++ b/arch/arm/boot/dts/imx7d.dtsi
@@ -1,5 +1,6 @@
 /*
  * Copyright 2015 Freescale Semiconductor, Inc.
+ * Copyright 2016 Toradex AG
  *
  * This file is dual-licensed: you can use it either under the terms
  * of the GPL or the X11 license, at your option. Note that this dual
@@ -40,54 +41,10 @@
  *     OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#include <dt-bindings/clock/imx7d-clock.h>
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/interrupt-controller/arm-gic.h>
-#include "imx7d-pinfunc.h"
-#include "skeleton.dtsi"
+#include "imx7s.dtsi"
 
 / {
-	aliases {
-		gpio0 = &gpio1;
-		gpio1 = &gpio2;
-		gpio2 = &gpio3;
-		gpio3 = &gpio4;
-		gpio4 = &gpio5;
-		gpio5 = &gpio6;
-		gpio6 = &gpio7;
-		i2c0 = &i2c1;
-		i2c1 = &i2c2;
-		i2c2 = &i2c3;
-		i2c3 = &i2c4;
-		mmc0 = &usdhc1;
-		mmc1 = &usdhc2;
-		mmc2 = &usdhc3;
-		serial0 = &uart1;
-		serial1 = &uart2;
-		serial2 = &uart3;
-		serial3 = &uart4;
-		serial4 = &uart5;
-		serial5 = &uart6;
-		serial6 = &uart7;
-	};
-
 	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu0: cpu@0 {
-			compatible = "arm,cortex-a7";
-			device_type = "cpu";
-			reg = <0>;
-			operating-points = <
-				/* KHz	uV */
-				996000	1075000
-				792000	975000
-			>;
-			clock-latency = <61036>; /* two CLK32 periods */
-			clocks = <&clks IMX7D_CLK_ARM>;
-		};
-
 		cpu1: cpu@1 {
 			compatible = "arm,cortex-a7";
 			device_type = "cpu";
@@ -95,221 +52,6 @@
 		};
 	};
 
-	intc: interrupt-controller@31001000 {
-		compatible = "arm,cortex-a7-gic";
-		#interrupt-cells = <3>;
-		interrupt-controller;
-		reg = <0x31001000 0x1000>,
-		      <0x31002000 0x1000>,
-		      <0x31004000 0x2000>,
-		      <0x31006000 0x2000>;
-	};
-
-	ckil: clock-cki {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <32768>;
-		clock-output-names = "ckil";
-	};
-
-	osc: clock-osc {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <24000000>;
-		clock-output-names = "osc";
-	};
-
-	timer {
-		compatible = "arm,armv7-timer";
-		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
-		interrupt-parent = <&intc>;
-	};
-
-	etr@30086000 {
-		compatible = "arm,coresight-tmc", "arm,primecell";
-		reg = <0x30086000 0x1000>;
-		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
-		clock-names = "apb_pclk";
-
-		port {
-			etr_in_port: endpoint {
-				slave-mode;
-				remote-endpoint = <&replicator_out_port1>;
-			};
-		};
-	};
-
-	tpiu@30087000 {
-		compatible = "arm,coresight-tpiu", "arm,primecell";
-		reg = <0x30087000 0x1000>;
-		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
-		clock-names = "apb_pclk";
-
-		port {
-			tpiu_in_port: endpoint {
-				slave-mode;
-				remote-endpoint = <&replicator_out_port1>;
-			};
-		};
-	};
-
-	replicator {
-		/*
-		 * non-configurable replicators don't show up on the
-		 * AMBA bus.  As such no need to add "arm,primecell"
-		 */
-		compatible = "arm,coresight-replicator";
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			/* replicator output ports */
-			port@0 {
-				reg = <0>;
-				replicator_out_port0: endpoint {
-					remote-endpoint = <&tpiu_in_port>;
-				};
-			};
-
-			port@1 {
-				reg = <1>;
-				replicator_out_port1: endpoint {
-					remote-endpoint = <&etr_in_port>;
-				};
-			};
-
-			/* replicator input port */
-			port@2 {
-				reg = <0>;
-				replicator_in_port0: endpoint {
-					slave-mode;
-					remote-endpoint = <&etf_out_port>;
-				};
-			};
-		};
-	};
-
-	etf@30084000 {
-		compatible = "arm,coresight-tmc", "arm,primecell";
-		reg = <0x30084000 0x1000>;
-		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
-		clock-names = "apb_pclk";
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			port@0 {
-				reg = <0>;
-				etf_in_port: endpoint {
-					slave-mode;
-					remote-endpoint = <&hugo_funnel_out_port0>;
-				};
-			};
-
-			port@1 {
-				reg = <0>;
-				etf_out_port: endpoint {
-					remote-endpoint = <&replicator_in_port0>;
-				};
-			};
-		};
-	};
-
-	funnel@30083000 {
-		compatible = "arm,coresight-funnel", "arm,primecell";
-		reg = <0x30083000 0x1000>;
-		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
-		clock-names = "apb_pclk";
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			/* funnel input ports */
-			port@0 {
-				reg = <0>;
-				hugo_funnel_in_port0: endpoint {
-					slave-mode;
-					remote-endpoint = <&ca_funnel_out_port0>;
-				};
-			};
-
-			port@1 {
-				reg = <1>;
-				hugo_funnel_in_port1: endpoint {
-					slave-mode; /* M4 input */
-				};
-			};
-
-			port@2 {
-				reg = <0>;
-				hugo_funnel_out_port0: endpoint {
-					remote-endpoint = <&etf_in_port>;
-				};
-			};
-
-			/* the other input ports are not connect to anything */
-		};
-	};
-
-	funnel@30041000 {
-		compatible = "arm,coresight-funnel", "arm,primecell";
-		reg = <0x30041000 0x1000>;
-		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
-		clock-names = "apb_pclk";
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			/* funnel input ports */
-			port@0 {
-				reg = <0>;
-				ca_funnel_in_port0: endpoint {
-					slave-mode;
-					remote-endpoint = <&etm0_out_port>;
-				};
-			};
-
-			port@1 {
-				reg = <1>;
-				ca_funnel_in_port1: endpoint {
-					slave-mode;
-					remote-endpoint = <&etm1_out_port>;
-				};
-			};
-
-			/* funnel output port */
-			port@2 {
-				reg = <0>;
-				ca_funnel_out_port0: endpoint {
-					remote-endpoint = <&hugo_funnel_in_port0>;
-				};
-			};
-
-			/* the other input ports are not connect to anything */
-		};
-	};
-
-	etm@3007c000 {
-		compatible = "arm,coresight-etm3x", "arm,primecell";
-		reg = <0x3007c000 0x1000>;
-		cpu = <&cpu0>;
-		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
-		clock-names = "apb_pclk";
-
-		port {
-			etm0_out_port: endpoint {
-				remote-endpoint = <&ca_funnel_in_port0>;
-			};
-		};
-	};
-
 	etm@3007d000 {
 		compatible = "arm,coresight-etm3x", "arm,primecell";
 		reg = <0x3007d000 0x1000>;
@@ -330,626 +72,57 @@
 			};
 		};
 	};
+};
 
-	soc {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		compatible = "simple-bus";
-		interrupt-parent = <&intc>;
-		ranges;
-
-		aips1: aips-bus@30000000 {
-			compatible = "fsl,aips-bus", "simple-bus";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			reg = <0x30000000 0x400000>;
-			ranges;
-
-			gpio1: gpio@30200000 {
-				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
-				reg = <0x30200000 0x10000>;
-				interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>, /* GPIO1_INT15_0 */
-					     <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; /* GPIO1_INT31_16 */
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-			};
-
-			gpio2: gpio@30210000 {
-				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
-				reg = <0x30210000 0x10000>;
-				interrupts = <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>;
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-			};
-
-			gpio3: gpio@30220000 {
-				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
-				reg = <0x30220000 0x10000>;
-				interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-			};
-
-			gpio4: gpio@30230000 {
-				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
-				reg = <0x30230000 0x10000>;
-				interrupts = <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-			};
-
-			gpio5: gpio@30240000 {
-				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
-				reg = <0x30240000 0x10000>;
-				interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-			};
-
-			gpio6: gpio@30250000 {
-				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
-				reg = <0x30250000 0x10000>;
-				interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-			};
-
-			gpio7: gpio@30260000 {
-				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
-				reg = <0x30260000 0x10000>;
-				interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
-				gpio-controller;
-				#gpio-cells = <2>;
-				interrupt-controller;
-				#interrupt-cells = <2>;
-			};
-
-			wdog1: wdog@30280000 {
-				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
-				reg = <0x30280000 0x10000>;
-				interrupts = <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_WDOG1_ROOT_CLK>;
-			};
-
-			wdog2: wdog@30290000 {
-				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
-				reg = <0x30290000 0x10000>;
-				interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_WDOG2_ROOT_CLK>;
-				status = "disabled";
-			};
-
-			wdog3: wdog@302a0000 {
-				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
-				reg = <0x302a0000 0x10000>;
-				interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_WDOG3_ROOT_CLK>;
-				status = "disabled";
-			};
-
-			wdog4: wdog@302b0000 {
-				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
-				reg = <0x302b0000 0x10000>;
-				interrupts = <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_WDOG4_ROOT_CLK>;
-				status = "disabled";
-			};
-
-			iomuxc_lpsr: iomuxc-lpsr@302c0000 {
-				compatible = "fsl,imx7d-iomuxc-lpsr";
-				reg = <0x302c0000 0x10000>;
-				fsl,input-sel = <&iomuxc>;
-			};
-
-			gpt1: gpt@302d0000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
-				reg = <0x302d0000 0x10000>;
-				interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
-					 <&clks IMX7D_GPT1_ROOT_CLK>;
-				clock-names = "ipg", "per";
-			};
-
-			gpt2: gpt@302e0000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
-				reg = <0x302e0000 0x10000>;
-				interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
-					 <&clks IMX7D_GPT2_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			gpt3: gpt@302f0000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
-				reg = <0x302f0000 0x10000>;
-				interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
-					 <&clks IMX7D_GPT3_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			gpt4: gpt@30300000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
-				reg = <0x30300000 0x10000>;
-				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
-					 <&clks IMX7D_GPT4_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			iomuxc: iomuxc@30330000 {
-				compatible = "fsl,imx7d-iomuxc";
-				reg = <0x30330000 0x10000>;
-			};
-
-			gpr: iomuxc-gpr@30340000 {
-				compatible = "fsl,imx7d-iomuxc-gpr", "syscon";
-				reg = <0x30340000 0x10000>;
-			};
-
-			ocotp: ocotp-ctrl@30350000 {
-				compatible = "syscon";
-				reg = <0x30350000 0x10000>;
-				clocks = <&clks IMX7D_CLK_DUMMY>;
-				status = "disabled";
-			};
-
-			anatop: anatop@30360000 {
-				compatible = "fsl,imx7d-anatop", "fsl,imx6q-anatop",
-					"syscon", "simple-bus";
-				reg = <0x30360000 0x10000>;
-				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
-					<GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
-
-				reg_1p0d: regulator-vdd1p0d@210 {
-					compatible = "fsl,anatop-regulator";
-					regulator-name = "vdd1p0d";
-					regulator-min-microvolt = <800000>;
-					regulator-max-microvolt = <1200000>;
-					anatop-reg-offset = <0x210>;
-					anatop-vol-bit-shift = <8>;
-					anatop-vol-bit-width = <5>;
-					anatop-min-bit-val = <8>;
-					anatop-min-voltage = <800000>;
-					anatop-max-voltage = <1200000>;
-					anatop-enable-bit = <31>;
-				};
-			};
-
-			snvs: snvs@30370000 {
-				compatible = "fsl,sec-v4.0-mon", "syscon", "simple-mfd";
-				reg = <0x30370000 0x10000>;
-
-				snvs_rtc: snvs-rtc-lp {
-					compatible = "fsl,sec-v4.0-mon-rtc-lp";
-					regmap = <&snvs>;
-					offset = <0x34>;
-					interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
-						     <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
-				};
-
-				snvs_poweroff: snvs-poweroff {
-					compatible = "syscon-poweroff";
-					regmap = <&snvs>;
-					offset = <0x38>;
-					mask = <0x60>;
-				};
-
-				snvs_pwrkey: snvs-powerkey {
-					compatible = "fsl,sec-v4.0-pwrkey";
-					regmap = <&snvs>;
-					interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
-					linux,keycode = <KEY_POWER>;
-					wakeup-source;
-				};
-			};
-
-			clks: ccm@30380000 {
-				compatible = "fsl,imx7d-ccm";
-				reg = <0x30380000 0x10000>;
-				interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
-				#clock-cells = <1>;
-				clocks = <&ckil>, <&osc>;
-				clock-names = "ckil", "osc";
-			};
-
-			src: src@30390000 {
-				compatible = "fsl,imx7d-src", "fsl,imx51-src", "syscon";
-				reg = <0x30390000 0x10000>;
-				interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
-				#reset-cells = <1>;
-			};
-		};
-
-		aips2: aips-bus@30400000 {
-			compatible = "fsl,aips-bus", "simple-bus";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			reg = <0x30400000 0x400000>;
-			ranges;
-
-			adc1: adc@30610000 {
-				compatible = "fsl,imx7d-adc";
-				reg = <0x30610000 0x10000>;
-				interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_ADC_ROOT_CLK>;
-				clock-names = "adc";
-				status = "disabled";
-			};
-
-			adc2: adc@30620000 {
-				compatible = "fsl,imx7d-adc";
-				reg = <0x30620000 0x10000>;
-				interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_ADC_ROOT_CLK>;
-				clock-names = "adc";
-				status = "disabled";
-			};
-
-			pwm1: pwm@30660000 {
-				compatible = "fsl,imx7d-pwm", "fsl,imx27-pwm";
-				reg = <0x30660000 0x10000>;
-				interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_PWM1_ROOT_CLK>,
-					 <&clks IMX7D_PWM1_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				#pwm-cells = <2>;
-				status = "disabled";
-			};
-
-			pwm2: pwm@30670000 {
-				compatible = "fsl,imx7d-pwm", "fsl,imx27-pwm";
-				reg = <0x30670000 0x10000>;
-				interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_PWM2_ROOT_CLK>,
-					 <&clks IMX7D_PWM2_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				#pwm-cells = <2>;
-				status = "disabled";
-			};
-
-			pwm3: pwm@30680000 {
-				compatible = "fsl,imx7d-pwm", "fsl,imx27-pwm";
-				reg = <0x30680000 0x10000>;
-				interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_PWM3_ROOT_CLK>,
-					 <&clks IMX7D_PWM3_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				#pwm-cells = <2>;
-				status = "disabled";
-			};
-
-			pwm4: pwm@30690000 {
-				compatible = "fsl,imx7d-pwm", "fsl,imx27-pwm";
-				reg = <0x30690000 0x10000>;
-				interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_PWM4_ROOT_CLK>,
-					 <&clks IMX7D_PWM4_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				#pwm-cells = <2>;
-				status = "disabled";
-			};
-
-			lcdif: lcdif@30730000 {
-				compatible = "fsl,imx7d-lcdif", "fsl,imx28-lcdif";
-				reg = <0x30730000 0x10000>;
-				interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>,
-					<&clks IMX7D_CLK_DUMMY>,
-					<&clks IMX7D_CLK_DUMMY>;
-				clock-names = "pix", "axi", "disp_axi";
-				status = "disabled";
-			};
-		};
-
-		aips3: aips-bus@30800000 {
-			compatible = "fsl,aips-bus", "simple-bus";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			reg = <0x30800000 0x400000>;
-			ranges;
-
-			uart1: serial@30860000 {
-				compatible = "fsl,imx7d-uart",
-					     "fsl,imx6q-uart";
-				reg = <0x30860000 0x10000>;
-				interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_UART1_ROOT_CLK>,
-					<&clks IMX7D_UART1_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			uart2: serial@30890000 {
-				compatible = "fsl,imx7d-uart",
-					     "fsl,imx6q-uart";
-				reg = <0x30890000 0x10000>;
-				interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_UART2_ROOT_CLK>,
-					<&clks IMX7D_UART2_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			uart3: serial@30880000 {
-				compatible = "fsl,imx7d-uart",
-					     "fsl,imx6q-uart";
-				reg = <0x30880000 0x10000>;
-				interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_UART3_ROOT_CLK>,
-					<&clks IMX7D_UART3_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			flexcan1: can@30a00000 {
-				compatible = "fsl,imx7d-flexcan", "fsl,imx6q-flexcan";
-				reg = <0x30a00000 0x10000>;
-				interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
-					<&clks IMX7D_CAN1_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			flexcan2: can@30a10000 {
-				compatible = "fsl,imx7d-flexcan", "fsl,imx6q-flexcan";
-				reg = <0x30a10000 0x10000>;
-				interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
-					<&clks IMX7D_CAN2_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			i2c1: i2c@30a20000 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,imx7d-i2c", "fsl,imx21-i2c";
-				reg = <0x30a20000 0x10000>;
-				interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_I2C1_ROOT_CLK>;
-				status = "disabled";
-			};
-
-			i2c2: i2c@30a30000 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,imx7d-i2c", "fsl,imx21-i2c";
-				reg = <0x30a30000 0x10000>;
-				interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_I2C2_ROOT_CLK>;
-				status = "disabled";
-			};
-
-			i2c3: i2c@30a40000 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,imx7d-i2c", "fsl,imx21-i2c";
-				reg = <0x30a40000 0x10000>;
-				interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_I2C3_ROOT_CLK>;
-				status = "disabled";
-			};
-
-			i2c4: i2c@30a50000 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,imx7d-i2c", "fsl,imx21-i2c";
-				reg = <0x30a50000 0x10000>;
-				interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_I2C4_ROOT_CLK>;
-				status = "disabled";
-			};
-
-			uart4: serial@30a60000 {
-				compatible = "fsl,imx7d-uart",
-					     "fsl,imx6q-uart";
-				reg = <0x30a60000 0x10000>;
-				interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_UART4_ROOT_CLK>,
-					<&clks IMX7D_UART4_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			uart5: serial@30a70000 {
-				compatible = "fsl,imx7d-uart",
-					     "fsl,imx6q-uart";
-				reg = <0x30a70000 0x10000>;
-				interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_UART5_ROOT_CLK>,
-					<&clks IMX7D_UART5_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			uart6: serial@30a80000 {
-				compatible = "fsl,imx7d-uart",
-					     "fsl,imx6q-uart";
-				reg = <0x30a80000 0x10000>;
-				interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_UART6_ROOT_CLK>,
-					<&clks IMX7D_UART6_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			uart7: serial@30a90000 {
-				compatible = "fsl,imx7d-uart",
-					     "fsl,imx6q-uart";
-				reg = <0x30a90000 0x10000>;
-				interrupts = <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_UART7_ROOT_CLK>,
-					<&clks IMX7D_UART7_ROOT_CLK>;
-				clock-names = "ipg", "per";
-				status = "disabled";
-			};
-
-			usbotg1: usb@30b10000 {
-				compatible = "fsl,imx7d-usb", "fsl,imx27-usb";
-				reg = <0x30b10000 0x200>;
-				interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_USB_CTRL_CLK>;
-				fsl,usbphy = <&usbphynop1>;
-				fsl,usbmisc = <&usbmisc1 0>;
-				phy-clkgate-delay-us = <400>;
-				status = "disabled";
-			};
-
-			usbotg2: usb@30b20000 {
-				compatible = "fsl,imx7d-usb", "fsl,imx27-usb";
-				reg = <0x30b20000 0x200>;
-				interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_USB_CTRL_CLK>;
-				fsl,usbphy = <&usbphynop2>;
-				fsl,usbmisc = <&usbmisc2 0>;
-				phy-clkgate-delay-us = <400>;
-				status = "disabled";
-			};
-
-			usbh: usb@30b30000 {
-				compatible = "fsl,imx7d-usb", "fsl,imx27-usb";
-				reg = <0x30b30000 0x200>;
-				interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_USB_CTRL_CLK>;
-				fsl,usbphy = <&usbphynop3>;
-				fsl,usbmisc = <&usbmisc3 0>;
-				phy_type = "hsic";
-				dr_mode = "host";
-				phy-clkgate-delay-us = <400>;
-				status = "disabled";
-			};
-
-			usbmisc1: usbmisc@30b10200 {
-				#index-cells = <1>;
-				compatible = "fsl,imx7d-usbmisc", "fsl,imx6q-usbmisc";
-				reg = <0x30b10200 0x200>;
-			};
-
-			usbmisc2: usbmisc@30b20200 {
-				#index-cells = <1>;
-				compatible = "fsl,imx7d-usbmisc", "fsl,imx6q-usbmisc";
-				reg = <0x30b20200 0x200>;
-			};
-
-			usbmisc3: usbmisc@30b30200 {
-				#index-cells = <1>;
-				compatible = "fsl,imx7d-usbmisc", "fsl,imx6q-usbmisc";
-				reg = <0x30b30200 0x200>;
-			};
-
-			usbphynop1: usbphynop1 {
-				compatible = "usb-nop-xceiv";
-				clocks = <&clks IMX7D_USB_PHY1_CLK>;
-				clock-names = "main_clk";
-			};
-
-			usbphynop2: usbphynop2 {
-				compatible = "usb-nop-xceiv";
-				clocks = <&clks IMX7D_USB_PHY2_CLK>;
-				clock-names = "main_clk";
-			};
-
-			usbphynop3: usbphynop3 {
-				compatible = "usb-nop-xceiv";
-				clocks = <&clks IMX7D_USB_HSIC_ROOT_CLK>;
-				clock-names = "main_clk";
-			};
-
-			usdhc1: usdhc@30b40000 {
-				compatible = "fsl,imx7d-usdhc", "fsl,imx6sl-usdhc";
-				reg = <0x30b40000 0x10000>;
-				interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
-					<&clks IMX7D_CLK_DUMMY>,
-					<&clks IMX7D_USDHC1_ROOT_CLK>;
-				clock-names = "ipg", "ahb", "per";
-				bus-width = <4>;
-				status = "disabled";
-			};
+&aips3 {
+	usbotg2: usb@30b20000 {
+		compatible = "fsl,imx7d-usb", "fsl,imx27-usb";
+		reg = <0x30b20000 0x200>;
+		interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&clks IMX7D_USB_CTRL_CLK>;
+		fsl,usbphy = <&usbphynop2>;
+		fsl,usbmisc = <&usbmisc2 0>;
+		phy-clkgate-delay-us = <400>;
+		status = "disabled";
+	};
 
-			usdhc2: usdhc@30b50000 {
-				compatible = "fsl,imx7d-usdhc", "fsl,imx6sl-usdhc";
-				reg = <0x30b50000 0x10000>;
-				interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
-					<&clks IMX7D_CLK_DUMMY>,
-					<&clks IMX7D_USDHC2_ROOT_CLK>;
-				clock-names = "ipg", "ahb", "per";
-				bus-width = <4>;
-				status = "disabled";
-			};
+	usbmisc2: usbmisc@30b20200 {
+		#index-cells = <1>;
+		compatible = "fsl,imx7d-usbmisc", "fsl,imx6q-usbmisc";
+		reg = <0x30b20200 0x200>;
+	};
 
-			usdhc3: usdhc@30b60000 {
-				compatible = "fsl,imx7d-usdhc", "fsl,imx6sl-usdhc";
-				reg = <0x30b60000 0x10000>;
-				interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
-					<&clks IMX7D_CLK_DUMMY>,
-					<&clks IMX7D_USDHC3_ROOT_CLK>;
-				clock-names = "ipg", "ahb", "per";
-				bus-width = <4>;
-				status = "disabled";
-			};
+	usbphynop2: usbphynop2 {
+		compatible = "usb-nop-xceiv";
+		clocks = <&clks IMX7D_USB_PHY2_CLK>;
+		clock-names = "main_clk";
+	};
 
-			fec1: ethernet@30be0000 {
-				compatible = "fsl,imx7d-fec", "fsl,imx6sx-fec";
-				reg = <0x30be0000 0x10000>;
-				interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
-					<GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>,
-					<GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_ENET_AXI_ROOT_CLK>,
-					<&clks IMX7D_ENET_AXI_ROOT_CLK>,
-					<&clks IMX7D_ENET1_TIME_ROOT_CLK>,
-					<&clks IMX7D_PLL_ENET_MAIN_125M_CLK>,
-					<&clks IMX7D_ENET_PHY_REF_ROOT_CLK>;
-				clock-names = "ipg", "ahb", "ptp",
-					"enet_clk_ref", "enet_out";
-				fsl,num-tx-queues=<3>;
-				fsl,num-rx-queues=<3>;
-				status = "disabled";
-			};
+	fec2: ethernet@30bf0000 {
+		compatible = "fsl,imx7d-fec", "fsl,imx6sx-fec";
+		reg = <0x30bf0000 0x10000>;
+		interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&clks IMX7D_ENET_AXI_ROOT_CLK>,
+			<&clks IMX7D_ENET_AXI_ROOT_CLK>,
+			<&clks IMX7D_ENET2_TIME_ROOT_CLK>,
+			<&clks IMX7D_PLL_ENET_MAIN_125M_CLK>,
+			<&clks IMX7D_ENET_PHY_REF_ROOT_CLK>;
+		clock-names = "ipg", "ahb", "ptp",
+			"enet_clk_ref", "enet_out";
+		fsl,num-tx-queues=<3>;
+		fsl,num-rx-queues=<3>;
+		status = "disabled";
+	};
+};
 
-			fec2: ethernet@30bf0000 {
-				compatible = "fsl,imx7d-fec", "fsl,imx6sx-fec";
-				reg = <0x30bf0000 0x10000>;
-				interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
-					<GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
-					<GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_ENET_AXI_ROOT_CLK>,
-					<&clks IMX7D_ENET_AXI_ROOT_CLK>,
-					<&clks IMX7D_ENET2_TIME_ROOT_CLK>,
-					<&clks IMX7D_PLL_ENET_MAIN_125M_CLK>,
-					<&clks IMX7D_ENET_PHY_REF_ROOT_CLK>;
-				clock-names = "ipg", "ahb", "ptp",
-					"enet_clk_ref", "enet_out";
-				fsl,num-tx-queues=<3>;
-				fsl,num-rx-queues=<3>;
-				status = "disabled";
-			};
+&ca_funnel_ports {
+	port@1 {
+		reg = <1>;
+		ca_funnel_in_port1: endpoint {
+			slave-mode;
+			remote-endpoint = <&etm1_out_port>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx7s-colibri-eval-v3.dts b/arch/arm/boot/dts/imx7s-colibri-eval-v3.dts
new file mode 100644
index 000000000000..bd2a49c1ade6
--- /dev/null
+++ b/arch/arm/boot/dts/imx7s-colibri-eval-v3.dts
@@ -0,0 +1,51 @@
+/*
+ * Copyright 2016 Toradex AG
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "imx7s-colibri.dtsi"
+#include "imx7-colibri-eval-v3.dtsi"
+
+/ {
+	model = "Toradex Colibri iMX7S on Colibri Evaluation Board V3";
+	compatible = "toradex,colibri-imx7s-eval-v3", "toradex,colibri-imx7s",
+		     "fsl,imx7s";
+};
diff --git a/arch/arm/boot/dts/imx7s-colibri.dtsi b/arch/arm/boot/dts/imx7s-colibri.dtsi
new file mode 100644
index 000000000000..b81013455b21
--- /dev/null
+++ b/arch/arm/boot/dts/imx7s-colibri.dtsi
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2016 Toradex AG
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include "imx7s.dtsi"
+#include "imx7-colibri.dtsi"
+
+/ {
+	memory {
+		reg = <0x80000000 0x10000000>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi
new file mode 100644
index 000000000000..1e90bdbe3a6e
--- /dev/null
+++ b/arch/arm/boot/dts/imx7s.dtsi
@@ -0,0 +1,933 @@
+/*
+ * Copyright 2015 Freescale Semiconductor, Inc.
+ * Copyright 2016 Toradex AG
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <dt-bindings/clock/imx7d-clock.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include "imx7d-pinfunc.h"
+#include "skeleton.dtsi"
+
+/ {
+	aliases {
+		gpio0 = &gpio1;
+		gpio1 = &gpio2;
+		gpio2 = &gpio3;
+		gpio3 = &gpio4;
+		gpio4 = &gpio5;
+		gpio5 = &gpio6;
+		gpio6 = &gpio7;
+		i2c0 = &i2c1;
+		i2c1 = &i2c2;
+		i2c2 = &i2c3;
+		i2c3 = &i2c4;
+		mmc0 = &usdhc1;
+		mmc1 = &usdhc2;
+		mmc2 = &usdhc3;
+		serial0 = &uart1;
+		serial1 = &uart2;
+		serial2 = &uart3;
+		serial3 = &uart4;
+		serial4 = &uart5;
+		serial5 = &uart6;
+		serial6 = &uart7;
+		spi0 = &ecspi1;
+		spi1 = &ecspi2;
+		spi2 = &ecspi3;
+		spi3 = &ecspi4;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "arm,cortex-a7";
+			device_type = "cpu";
+			reg = <0>;
+			operating-points = <
+				/* KHz	uV */
+				996000	1075000
+				792000	975000
+			>;
+			clock-latency = <61036>; /* two CLK32 periods */
+			clocks = <&clks IMX7D_CLK_ARM>;
+		};
+	};
+
+	intc: interrupt-controller@31001000 {
+		compatible = "arm,cortex-a7-gic";
+		#interrupt-cells = <3>;
+		interrupt-controller;
+		reg = <0x31001000 0x1000>,
+		      <0x31002000 0x1000>,
+		      <0x31004000 0x2000>,
+		      <0x31006000 0x2000>;
+	};
+
+	ckil: clock-cki {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+		clock-output-names = "ckil";
+	};
+
+	osc: clock-osc {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+		clock-output-names = "osc";
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
+		interrupt-parent = <&intc>;
+	};
+
+	etr@30086000 {
+		compatible = "arm,coresight-tmc", "arm,primecell";
+		reg = <0x30086000 0x1000>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		port {
+			etr_in_port: endpoint {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port1>;
+			};
+		};
+	};
+
+	tpiu@30087000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0x30087000 0x1000>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		port {
+			tpiu_in_port: endpoint {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port1>;
+			};
+		};
+	};
+
+	replicator {
+		/*
+		 * non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell"
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator_out_port0: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator_out_port1: endpoint {
+					remote-endpoint = <&etr_in_port>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&etf_out_port>;
+				};
+			};
+		};
+	};
+
+	etf@30084000 {
+		compatible = "arm,coresight-tmc", "arm,primecell";
+		reg = <0x30084000 0x1000>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				etf_in_port: endpoint {
+					slave-mode;
+					remote-endpoint = <&hugo_funnel_out_port0>;
+				};
+			};
+
+			port@1 {
+				reg = <0>;
+				etf_out_port: endpoint {
+					remote-endpoint = <&replicator_in_port0>;
+				};
+			};
+		};
+	};
+
+	funnel@30083000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0x30083000 0x1000>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel input ports */
+			port@0 {
+				reg = <0>;
+				hugo_funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ca_funnel_out_port0>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				hugo_funnel_in_port1: endpoint {
+					slave-mode; /* M4 input */
+				};
+			};
+
+			port@2 {
+				reg = <0>;
+				hugo_funnel_out_port0: endpoint {
+					remote-endpoint = <&etf_in_port>;
+				};
+			};
+
+			/* the other input ports are not connect to anything */
+		};
+	};
+
+	funnel@30041000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0x30041000 0x1000>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		ca_funnel_ports: ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel input ports */
+			port@0 {
+				reg = <0>;
+				ca_funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm0_out_port>;
+				};
+			};
+
+			/* funnel output port */
+			port@2 {
+				reg = <0>;
+				ca_funnel_out_port0: endpoint {
+					remote-endpoint = <&hugo_funnel_in_port0>;
+				};
+			};
+
+			/* the other input ports are not connect to anything */
+		};
+	};
+
+	etm@3007c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0x3007c000 0x1000>;
+		cpu = <&cpu0>;
+		clocks = <&clks IMX7D_MAIN_AXI_ROOT_CLK>;
+		clock-names = "apb_pclk";
+
+		port {
+			etm0_out_port: endpoint {
+				remote-endpoint = <&ca_funnel_in_port0>;
+			};
+		};
+	};
+
+	soc {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		interrupt-parent = <&intc>;
+		ranges;
+
+		aips1: aips-bus@30000000 {
+			compatible = "fsl,aips-bus", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x30000000 0x400000>;
+			ranges;
+
+			gpio1: gpio@30200000 {
+				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
+				reg = <0x30200000 0x10000>;
+				interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>, /* GPIO1_INT15_0 */
+					     <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; /* GPIO1_INT31_16 */
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio2: gpio@30210000 {
+				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
+				reg = <0x30210000 0x10000>;
+				interrupts = <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio3: gpio@30220000 {
+				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
+				reg = <0x30220000 0x10000>;
+				interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio4: gpio@30230000 {
+				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
+				reg = <0x30230000 0x10000>;
+				interrupts = <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio5: gpio@30240000 {
+				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
+				reg = <0x30240000 0x10000>;
+				interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio6: gpio@30250000 {
+				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
+				reg = <0x30250000 0x10000>;
+				interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			gpio7: gpio@30260000 {
+				compatible = "fsl,imx7d-gpio", "fsl,imx35-gpio";
+				reg = <0x30260000 0x10000>;
+				interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
+				gpio-controller;
+				#gpio-cells = <2>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+			};
+
+			wdog1: wdog@30280000 {
+				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
+				reg = <0x30280000 0x10000>;
+				interrupts = <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_WDOG1_ROOT_CLK>;
+			};
+
+			wdog2: wdog@30290000 {
+				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
+				reg = <0x30290000 0x10000>;
+				interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_WDOG2_ROOT_CLK>;
+				status = "disabled";
+			};
+
+			wdog3: wdog@302a0000 {
+				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
+				reg = <0x302a0000 0x10000>;
+				interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_WDOG3_ROOT_CLK>;
+				status = "disabled";
+			};
+
+			wdog4: wdog@302b0000 {
+				compatible = "fsl,imx7d-wdt", "fsl,imx21-wdt";
+				reg = <0x302b0000 0x10000>;
+				interrupts = <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_WDOG4_ROOT_CLK>;
+				status = "disabled";
+			};
+
+			iomuxc_lpsr: iomuxc-lpsr@302c0000 {
+				compatible = "fsl,imx7d-iomuxc-lpsr";
+				reg = <0x302c0000 0x10000>;
+				fsl,input-sel = <&iomuxc>;
+			};
+
+			gpt1: gpt@302d0000 {
+				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				reg = <0x302d0000 0x10000>;
+				interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_CLK_DUMMY>,
+					 <&clks IMX7D_GPT1_ROOT_CLK>;
+				clock-names = "ipg", "per";
+			};
+
+			gpt2: gpt@302e0000 {
+				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				reg = <0x302e0000 0x10000>;
+				interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_CLK_DUMMY>,
+					 <&clks IMX7D_GPT2_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			gpt3: gpt@302f0000 {
+				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				reg = <0x302f0000 0x10000>;
+				interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_CLK_DUMMY>,
+					 <&clks IMX7D_GPT3_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			gpt4: gpt@30300000 {
+				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				reg = <0x30300000 0x10000>;
+				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_CLK_DUMMY>,
+					 <&clks IMX7D_GPT4_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			iomuxc: iomuxc@30330000 {
+				compatible = "fsl,imx7d-iomuxc";
+				reg = <0x30330000 0x10000>;
+			};
+
+			gpr: iomuxc-gpr@30340000 {
+				compatible = "fsl,imx7d-iomuxc-gpr", "syscon";
+				reg = <0x30340000 0x10000>;
+			};
+
+			ocotp: ocotp-ctrl@30350000 {
+				compatible = "syscon";
+				reg = <0x30350000 0x10000>;
+				clocks = <&clks IMX7D_CLK_DUMMY>;
+				status = "disabled";
+			};
+
+			anatop: anatop@30360000 {
+				compatible = "fsl,imx7d-anatop", "fsl,imx6q-anatop",
+					"syscon", "simple-bus";
+				reg = <0x30360000 0x10000>;
+				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
+
+				reg_1p0d: regulator-vdd1p0d {
+					compatible = "fsl,anatop-regulator";
+					regulator-name = "vdd1p0d";
+					regulator-min-microvolt = <800000>;
+					regulator-max-microvolt = <1200000>;
+					anatop-reg-offset = <0x210>;
+					anatop-vol-bit-shift = <8>;
+					anatop-vol-bit-width = <5>;
+					anatop-min-bit-val = <8>;
+					anatop-min-voltage = <800000>;
+					anatop-max-voltage = <1200000>;
+					anatop-enable-bit = <31>;
+				};
+			};
+
+			snvs: snvs@30370000 {
+				compatible = "fsl,sec-v4.0-mon", "syscon", "simple-mfd";
+				reg = <0x30370000 0x10000>;
+
+				snvs_rtc: snvs-rtc-lp {
+					compatible = "fsl,sec-v4.0-mon-rtc-lp";
+					regmap = <&snvs>;
+					offset = <0x34>;
+					interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
+						     <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
+				};
+
+				snvs_poweroff: snvs-poweroff {
+					compatible = "syscon-poweroff";
+					regmap = <&snvs>;
+					offset = <0x38>;
+					mask = <0x60>;
+				};
+
+				snvs_pwrkey: snvs-powerkey {
+					compatible = "fsl,sec-v4.0-pwrkey";
+					regmap = <&snvs>;
+					interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
+					linux,keycode = <KEY_POWER>;
+					wakeup-source;
+				};
+			};
+
+			clks: ccm@30380000 {
+				compatible = "fsl,imx7d-ccm";
+				reg = <0x30380000 0x10000>;
+				interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+				#clock-cells = <1>;
+				clocks = <&ckil>, <&osc>;
+				clock-names = "ckil", "osc";
+			};
+
+			src: src@30390000 {
+				compatible = "fsl,imx7d-src", "fsl,imx51-src", "syscon";
+				reg = <0x30390000 0x10000>;
+				interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
+				#reset-cells = <1>;
+			};
+		};
+
+		aips2: aips-bus@30400000 {
+			compatible = "fsl,aips-bus", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x30400000 0x400000>;
+			ranges;
+
+			adc1: adc@30610000 {
+				compatible = "fsl,imx7d-adc";
+				reg = <0x30610000 0x10000>;
+				interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_ADC_ROOT_CLK>;
+				clock-names = "adc";
+				status = "disabled";
+			};
+
+			adc2: adc@30620000 {
+				compatible = "fsl,imx7d-adc";
+				reg = <0x30620000 0x10000>;
+				interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_ADC_ROOT_CLK>;
+				clock-names = "adc";
+				status = "disabled";
+			};
+
+			ecspi4: ecspi@30630000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx7d-ecspi", "fsl,imx51-ecspi";
+				reg = <0x30630000 0x10000>;
+				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_ECSPI4_ROOT_CLK>,
+					<&clks IMX7D_ECSPI4_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			pwm1: pwm@30660000 {
+				compatible = "fsl,imx7d-pwm", "fsl,imx27-pwm";
+				reg = <0x30660000 0x10000>;
+				interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_PWM1_ROOT_CLK>,
+					 <&clks IMX7D_PWM1_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				#pwm-cells = <2>;
+				status = "disabled";
+			};
+
+			pwm2: pwm@30670000 {
+				compatible = "fsl,imx7d-pwm", "fsl,imx27-pwm";
+				reg = <0x30670000 0x10000>;
+				interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_PWM2_ROOT_CLK>,
+					 <&clks IMX7D_PWM2_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				#pwm-cells = <2>;
+				status = "disabled";
+			};
+
+			pwm3: pwm@30680000 {
+				compatible = "fsl,imx7d-pwm", "fsl,imx27-pwm";
+				reg = <0x30680000 0x10000>;
+				interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_PWM3_ROOT_CLK>,
+					 <&clks IMX7D_PWM3_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				#pwm-cells = <2>;
+				status = "disabled";
+			};
+
+			pwm4: pwm@30690000 {
+				compatible = "fsl,imx7d-pwm", "fsl,imx27-pwm";
+				reg = <0x30690000 0x10000>;
+				interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_PWM4_ROOT_CLK>,
+					 <&clks IMX7D_PWM4_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				#pwm-cells = <2>;
+				status = "disabled";
+			};
+
+			lcdif: lcdif@30730000 {
+				compatible = "fsl,imx7d-lcdif", "fsl,imx28-lcdif";
+				reg = <0x30730000 0x10000>;
+				interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>,
+					<&clks IMX7D_CLK_DUMMY>,
+					<&clks IMX7D_CLK_DUMMY>;
+				clock-names = "pix", "axi", "disp_axi";
+				status = "disabled";
+			};
+		};
+
+		aips3: aips-bus@30800000 {
+			compatible = "fsl,aips-bus", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x30800000 0x400000>;
+			ranges;
+
+			ecspi1: ecspi@30820000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx7d-ecspi", "fsl,imx51-ecspi";
+				reg = <0x30820000 0x10000>;
+				interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_ECSPI1_ROOT_CLK>,
+					<&clks IMX7D_ECSPI1_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			ecspi2: ecspi@30830000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx7d-ecspi", "fsl,imx51-ecspi";
+				reg = <0x30830000 0x10000>;
+				interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_ECSPI2_ROOT_CLK>,
+					<&clks IMX7D_ECSPI2_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			ecspi3: ecspi@30840000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx7d-ecspi", "fsl,imx51-ecspi";
+				reg = <0x30840000 0x10000>;
+				interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_ECSPI3_ROOT_CLK>,
+					<&clks IMX7D_ECSPI3_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			uart1: serial@30860000 {
+				compatible = "fsl,imx7d-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x30860000 0x10000>;
+				interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_UART1_ROOT_CLK>,
+					<&clks IMX7D_UART1_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			uart2: serial@30890000 {
+				compatible = "fsl,imx7d-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x30890000 0x10000>;
+				interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_UART2_ROOT_CLK>,
+					<&clks IMX7D_UART2_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			uart3: serial@30880000 {
+				compatible = "fsl,imx7d-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x30880000 0x10000>;
+				interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_UART3_ROOT_CLK>,
+					<&clks IMX7D_UART3_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			flexcan1: can@30a00000 {
+				compatible = "fsl,imx7d-flexcan", "fsl,imx6q-flexcan";
+				reg = <0x30a00000 0x10000>;
+				interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_CLK_DUMMY>,
+					<&clks IMX7D_CAN1_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			flexcan2: can@30a10000 {
+				compatible = "fsl,imx7d-flexcan", "fsl,imx6q-flexcan";
+				reg = <0x30a10000 0x10000>;
+				interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_CLK_DUMMY>,
+					<&clks IMX7D_CAN2_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			i2c1: i2c@30a20000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx7d-i2c", "fsl,imx21-i2c";
+				reg = <0x30a20000 0x10000>;
+				interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_I2C1_ROOT_CLK>;
+				status = "disabled";
+			};
+
+			i2c2: i2c@30a30000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx7d-i2c", "fsl,imx21-i2c";
+				reg = <0x30a30000 0x10000>;
+				interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_I2C2_ROOT_CLK>;
+				status = "disabled";
+			};
+
+			i2c3: i2c@30a40000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx7d-i2c", "fsl,imx21-i2c";
+				reg = <0x30a40000 0x10000>;
+				interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_I2C3_ROOT_CLK>;
+				status = "disabled";
+			};
+
+			i2c4: i2c@30a50000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,imx7d-i2c", "fsl,imx21-i2c";
+				reg = <0x30a50000 0x10000>;
+				interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_I2C4_ROOT_CLK>;
+				status = "disabled";
+			};
+
+			uart4: serial@30a60000 {
+				compatible = "fsl,imx7d-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x30a60000 0x10000>;
+				interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_UART4_ROOT_CLK>,
+					<&clks IMX7D_UART4_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			uart5: serial@30a70000 {
+				compatible = "fsl,imx7d-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x30a70000 0x10000>;
+				interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_UART5_ROOT_CLK>,
+					<&clks IMX7D_UART5_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			uart6: serial@30a80000 {
+				compatible = "fsl,imx7d-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x30a80000 0x10000>;
+				interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_UART6_ROOT_CLK>,
+					<&clks IMX7D_UART6_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			uart7: serial@30a90000 {
+				compatible = "fsl,imx7d-uart",
+					     "fsl,imx6q-uart";
+				reg = <0x30a90000 0x10000>;
+				interrupts = <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_UART7_ROOT_CLK>,
+					<&clks IMX7D_UART7_ROOT_CLK>;
+				clock-names = "ipg", "per";
+				status = "disabled";
+			};
+
+			usbotg1: usb@30b10000 {
+				compatible = "fsl,imx7d-usb", "fsl,imx27-usb";
+				reg = <0x30b10000 0x200>;
+				interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_USB_CTRL_CLK>;
+				fsl,usbphy = <&usbphynop1>;
+				fsl,usbmisc = <&usbmisc1 0>;
+				phy-clkgate-delay-us = <400>;
+				status = "disabled";
+			};
+
+			usbh: usb@30b30000 {
+				compatible = "fsl,imx7d-usb", "fsl,imx27-usb";
+				reg = <0x30b30000 0x200>;
+				interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_USB_CTRL_CLK>;
+				fsl,usbphy = <&usbphynop3>;
+				fsl,usbmisc = <&usbmisc3 0>;
+				phy_type = "hsic";
+				dr_mode = "host";
+				phy-clkgate-delay-us = <400>;
+				status = "disabled";
+			};
+
+			usbmisc1: usbmisc@30b10200 {
+				#index-cells = <1>;
+				compatible = "fsl,imx7d-usbmisc", "fsl,imx6q-usbmisc";
+				reg = <0x30b10200 0x200>;
+			};
+
+			usbmisc3: usbmisc@30b30200 {
+				#index-cells = <1>;
+				compatible = "fsl,imx7d-usbmisc", "fsl,imx6q-usbmisc";
+				reg = <0x30b30200 0x200>;
+			};
+
+			usbphynop1: usbphynop1 {
+				compatible = "usb-nop-xceiv";
+				clocks = <&clks IMX7D_USB_PHY1_CLK>;
+				clock-names = "main_clk";
+			};
+
+			usbphynop3: usbphynop3 {
+				compatible = "usb-nop-xceiv";
+				clocks = <&clks IMX7D_USB_HSIC_ROOT_CLK>;
+				clock-names = "main_clk";
+			};
+
+			usdhc1: usdhc@30b40000 {
+				compatible = "fsl,imx7d-usdhc", "fsl,imx6sl-usdhc";
+				reg = <0x30b40000 0x10000>;
+				interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_CLK_DUMMY>,
+					<&clks IMX7D_CLK_DUMMY>,
+					<&clks IMX7D_USDHC1_ROOT_CLK>;
+				clock-names = "ipg", "ahb", "per";
+				bus-width = <4>;
+				status = "disabled";
+			};
+
+			usdhc2: usdhc@30b50000 {
+				compatible = "fsl,imx7d-usdhc", "fsl,imx6sl-usdhc";
+				reg = <0x30b50000 0x10000>;
+				interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_CLK_DUMMY>,
+					<&clks IMX7D_CLK_DUMMY>,
+					<&clks IMX7D_USDHC2_ROOT_CLK>;
+				clock-names = "ipg", "ahb", "per";
+				bus-width = <4>;
+				status = "disabled";
+			};
+
+			usdhc3: usdhc@30b60000 {
+				compatible = "fsl,imx7d-usdhc", "fsl,imx6sl-usdhc";
+				reg = <0x30b60000 0x10000>;
+				interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_CLK_DUMMY>,
+					<&clks IMX7D_CLK_DUMMY>,
+					<&clks IMX7D_USDHC3_ROOT_CLK>;
+				clock-names = "ipg", "ahb", "per";
+				bus-width = <4>;
+				status = "disabled";
+			};
+
+			fec1: ethernet@30be0000 {
+				compatible = "fsl,imx7d-fec", "fsl,imx6sx-fec";
+				reg = <0x30be0000 0x10000>;
+				interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>,
+					<GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&clks IMX7D_ENET_AXI_ROOT_CLK>,
+					<&clks IMX7D_ENET_AXI_ROOT_CLK>,
+					<&clks IMX7D_ENET1_TIME_ROOT_CLK>,
+					<&clks IMX7D_PLL_ENET_MAIN_125M_CLK>,
+					<&clks IMX7D_ENET_PHY_REF_ROOT_CLK>;
+				clock-names = "ipg", "ahb", "ptp",
+					"enet_clk_ref", "enet_out";
+				fsl,num-tx-queues=<3>;
+				fsl,num-rx-queues=<3>;
+				status = "disabled";
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/keystone-k2e.dtsi b/arch/arm/boot/dts/keystone-k2e.dtsi
index 96b349fb0430..9a51b8c88581 100644
--- a/arch/arm/boot/dts/keystone-k2e.dtsi
+++ b/arch/arm/boot/dts/keystone-k2e.dtsi
@@ -96,13 +96,16 @@
 			#address-cells = <3>;
 			#size-cells = <2>;
 			reg =  <0x21021000 0x2000>, <0x21020000 0x1000>, <0x02620128 4>;
-			ranges = <0x81000000 0 0 0x23260000 0x4000 0x4000
-				0x82000000 0 0x60000000 0x60000000 0 0x10000000>;
+			ranges = <0x82000000 0 0x60000000 0x60000000
+				  0 0x10000000>;
 
 			status = "disabled";
 			device_type = "pci";
 			num-lanes = <2>;
+			bus-range = <0x00 0xff>;
 
+			/* error interrupt */
+			interrupts = <GIC_SPI 385 IRQ_TYPE_EDGE_RISING>;
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 7>;
 			interrupt-map = <0 0 0 1 &pcie_intc1 0>, /* INT A */
diff --git a/arch/arm/boot/dts/keystone-k2g-evm.dts b/arch/arm/boot/dts/keystone-k2g-evm.dts
index 5bfd9e7845f2..692fcbb1434a 100644
--- a/arch/arm/boot/dts/keystone-k2g-evm.dts
+++ b/arch/arm/boot/dts/keystone-k2g-evm.dts
@@ -27,6 +27,17 @@
 
 };
 
+&k2g_pinctrl {
+	uart0_pins: pinmux_uart0_pins {
+		pinctrl-single,pins = <
+			K2G_CORE_IOPAD(0x11cc) (BUFFER_CLASS_B | PULL_DISABLE | MUX_MODE0)	/* uart0_rxd.uart0_rxd */
+			K2G_CORE_IOPAD(0x11d0) (BUFFER_CLASS_B | PIN_PULLDOWN | MUX_MODE0)	/* uart0_txd.uart0_txd */
+		>;
+	};
+};
+
 &uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pins>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/keystone-k2g.dtsi b/arch/arm/boot/dts/keystone-k2g.dtsi
index 7ff2796ae925..3372615b885c 100644
--- a/arch/arm/boot/dts/keystone-k2g.dtsi
+++ b/arch/arm/boot/dts/keystone-k2g.dtsi
@@ -14,6 +14,7 @@
  */
 
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/pinctrl/keystone.h>
 #include "skeleton.dtsi"
 
 / {
@@ -75,6 +76,13 @@
 		ranges = <0x0 0x0 0x0 0xc0000000>;
 		dma-ranges = <0x80000000 0x8 0x00000000 0x80000000>;
 
+		k2g_pinctrl: pinmux@02621000 {
+			compatible = "pinctrl-single";
+			reg = <0x02621000 0x410>;
+			pinctrl-single,register-width = <32>;
+			pinctrl-single,function-mask = <0x001b0007>;
+		};
+
 		uart0: serial@02530c00 {
 			compatible = "ns16550a";
 			current-speed = <115200>;
diff --git a/arch/arm/boot/dts/keystone-k2l.dtsi b/arch/arm/boot/dts/keystone-k2l.dtsi
index ff22ffc3dee7..2ee3d0ac2816 100644
--- a/arch/arm/boot/dts/keystone-k2l.dtsi
+++ b/arch/arm/boot/dts/keystone-k2l.dtsi
@@ -54,6 +54,155 @@
 			interrupts = <GIC_SPI 435 IRQ_TYPE_EDGE_RISING>;
 		};
 
+		k2l_pmx: pinmux@02620690 {
+			compatible = "pinctrl-single";
+			reg = <0x02620690 0xc>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-single,bit-per-mux;
+			pinctrl-single,register-width = <32>;
+			pinctrl-single,function-mask = <0x1>;
+			status = "disabled";
+
+			uart3_emifa_pins: pinmux_uart3_emifa_pins {
+				pinctrl-single,bits = <
+					/* UART3_EMIFA_SEL */
+					0x0 0x0  0xc0
+				>;
+			};
+
+			uart2_emifa_pins: pinmux_uart2_emifa_pins {
+			pinctrl-single,bits = <
+					/* UART2_EMIFA_SEL */
+					0x0 0x0  0x30
+				>;
+			};
+
+			uart01_spi2_pins: pinmux_uart01_spi2_pins {
+				pinctrl-single,bits = <
+					/* UART01_SPI2_SEL */
+					0x0 0x0 0x4
+				>;
+			};
+
+			dfesync_rp1_pins: pinmux_dfesync_rp1_pins{
+				pinctrl-single,bits = <
+					/* DFESYNC_RP1_SEL */
+					0x0 0x0 0x2
+				>;
+			};
+
+			avsif_pins: pinmux_avsif_pins {
+				pinctrl-single,bits = <
+					/* AVSIF_SEL */
+					0x0 0x0 0x1
+				>;
+			};
+
+			gpio_emu_pins: pinmux_gpio_emu_pins {
+				pinctrl-single,bits = <
+				/*
+				 * GPIO_EMU_SEL[31]: 0-GPIO31, 1-EMU33
+				 * GPIO_EMU_SEL[30]: 0-GPIO30, 1-EMU32
+				 * GPIO_EMU_SEL[29]: 0-GPIO29, 1-EMU31
+				 * GPIO_EMU_SEL[28]: 0-GPIO28, 1-EMU30
+				 * GPIO_EMU_SEL[27]: 0-GPIO27, 1-EMU29
+				 * GPIO_EMU_SEL[26]: 0-GPIO26, 1-EMU28
+				 * GPIO_EMU_SEL[25]: 0-GPIO25, 1-EMU27
+				 * GPIO_EMU_SEL[24]: 0-GPIO24, 1-EMU26
+				 * GPIO_EMU_SEL[23]: 0-GPIO23, 1-EMU25
+				 * GPIO_EMU_SEL[22]: 0-GPIO22, 1-EMU24
+				 * GPIO_EMU_SEL[21]: 0-GPIO21, 1-EMU23
+				 * GPIO_EMU_SEL[20]: 0-GPIO20, 1-EMU22
+				 * GPIO_EMU_SEL[19]: 0-GPIO19, 1-EMU21
+				 * GPIO_EMU_SEL[18]: 0-GPIO18, 1-EMU20
+				 * GPIO_EMU_SEL[17]: 0-GPIO17, 1-EMU19
+				 */
+					0x4 0x0000 0xFFFE0000
+				>;
+			};
+
+			gpio_timio_pins: pinmux_gpio_timio_pins {
+				pinctrl-single,bits = <
+				/*
+				 * GPIO_TIMIO_SEL[15]: 0-GPIO15, 1-TIMO7
+				 * GPIO_TIMIO_SEL[14]: 0-GPIO14, 1-TIMO6
+				 * GPIO_TIMIO_SEL[13]: 0-GPIO13, 1-TIMO5
+				 * GPIO_TIMIO_SEL[12]: 0-GPIO12, 1-TIMO4
+				 * GPIO_TIMIO_SEL[11]: 0-GPIO11, 1-TIMO3
+				 * GPIO_TIMIO_SEL[10]: 0-GPIO10, 1-TIMO2
+				 * GPIO_TIMIO_SEL[9]: 0-GPIO9, 1-TIMI7
+				 * GPIO_TIMIO_SEL[8]: 0-GPIO8, 1-TIMI6
+				 * GPIO_TIMIO_SEL[7]: 0-GPIO7, 1-TIMI5
+				 * GPIO_TIMIO_SEL[6]: 0-GPIO6, 1-TIMI4
+				 * GPIO_TIMIO_SEL[5]: 0-GPIO5, 1-TIMI3
+				 * GPIO_TIMIO_SEL[4]: 0-GPIO4, 1-TIMI2
+				 */
+					0x4 0x0 0xFFF0
+				>;
+			};
+
+			gpio_spi2cs_pins: pinmux_gpio_spi2cs_pins {
+				pinctrl-single,bits = <
+				/*
+				 * GPIO_SPI2CS_SEL[3]: 0-GPIO3, 1-SPI2CS4
+				 * GPIO_SPI2CS_SEL[2]: 0-GPIO2, 1-SPI2CS3
+				 * GPIO_SPI2CS_SEL[1]: 0-GPIO1, 1-SPI2CS2
+				 * GPIO_SPI2CS_SEL[0]: 0-GPIO0, 1-SPI2CS1
+				 */
+					0x4 0x0 0xF
+				>;
+			};
+
+			gpio_dfeio_pins: pinmux_gpio_dfeio_pins {
+				pinctrl-single,bits = <
+				/*
+				 * GPIO_DFEIO_SEL[31]: 0-DFEIO17, 1-GPIO63
+				 * GPIO_DFEIO_SEL[30]: 0-DFEIO16, 1-GPIO62
+				 * GPIO_DFEIO_SEL[29]: 0-DFEIO15, 1-GPIO61
+				 * GPIO_DFEIO_SEL[28]: 0-DFEIO14, 1-GPIO60
+				 * GPIO_DFEIO_SEL[27]: 0-DFEIO13, 1-GPIO59
+				 * GPIO_DFEIO_SEL[26]: 0-DFEIO12, 1-GPIO58
+				 * GPIO_DFEIO_SEL[25]: 0-DFEIO11, 1-GPIO57
+				 * GPIO_DFEIO_SEL[24]: 0-DFEIO10, 1-GPIO56
+				 * GPIO_DFEIO_SEL[23]: 0-DFEIO9, 1-GPIO55
+				 * GPIO_DFEIO_SEL[22]: 0-DFEIO8, 1-GPIO54
+				 * GPIO_DFEIO_SEL[21]: 0-DFEIO7, 1-GPIO53
+				 * GPIO_DFEIO_SEL[20]: 0-DFEIO6, 1-GPIO52
+				 * GPIO_DFEIO_SEL[19]: 0-DFEIO5, 1-GPIO51
+				 * GPIO_DFEIO_SEL[18]: 0-DFEIO4, 1-GPIO50
+				 * GPIO_DFEIO_SEL[17]: 0-DFEIO3, 1-GPIO49
+				 * GPIO_DFEIO_SEL[16]: 0-DFEIO2, 1-GPIO48
+				 */
+					0x8 0x0 0xFFFF0000
+				>;
+			};
+
+			gpio_emifa_pins: pinmux_gpio_emifa_pins {
+				pinctrl-single,bits = <
+				/*
+				 * GPIO_EMIFA_SEL[15]: 0-EMIFA17, 1-GPIO47
+				 * GPIO_EMIFA_SEL[14]: 0-EMIFA16, 1-GPIO46
+				 * GPIO_EMIFA_SEL[13]: 0-EMIFA15, 1-GPIO45
+				 * GPIO_EMIFA_SEL[12]: 0-EMIFA14, 1-GPIO44
+				 * GPIO_EMIFA_SEL[11]: 0-EMIFA13, 1-GPIO43
+				 * GPIO_EMIFA_SEL[10]: 0-EMIFA10, 1-GPIO42
+				 * GPIO_EMIFA_SEL[9]: 0-EMIFA9, 1-GPIO41
+				 * GPIO_EMIFA_SEL[8]: 0-EMIFA8, 1-GPIO40
+				 * GPIO_EMIFA_SEL[7]: 0-EMIFA7, 1-GPIO39
+				 * GPIO_EMIFA_SEL[6]: 0-EMIFA6, 1-GPIO38
+				 * GPIO_EMIFA_SEL[5]: 0-EMIFA5, 1-GPIO37
+				 * GPIO_EMIFA_SEL[4]: 0-EMIFA4, 1-GPIO36
+				 * GPIO_EMIFA_SEL[3]: 0-EMIFA3, 1-GPIO35
+				 * GPIO_EMIFA_SEL[2]: 0-EMIFA2, 1-GPIO34
+				 * GPIO_EMIFA_SEL[1]: 0-EMIFA1, 1-GPIO33
+				 * GPIO_EMIFA_SEL[0]: 0-EMIFA0, 1-GPIO32
+				 */
+					0x8 0x0 0xFFFF
+				>;
+			};
+		};
+
 		dspgpio0: keystone_dsp_gpio@02620240 {
 			compatible = "ti,keystone-dsp-gpio";
 			gpio-controller;
diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi
index e34b2265458a..00cb314d5e4d 100644
--- a/arch/arm/boot/dts/keystone.dtsi
+++ b/arch/arm/boot/dts/keystone.dtsi
@@ -70,6 +70,14 @@
 		cpu_on		= <0x84000003>;
 	};
 
+	psci {
+		compatible	= "arm,psci";
+		method		= "smc";
+		cpu_suspend	= <0x84000001>;
+		cpu_off		= <0x84000002>;
+		cpu_on		= <0x84000003>;
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -294,13 +302,16 @@
 			#address-cells = <3>;
 			#size-cells = <2>;
 			reg =  <0x21801000 0x2000>, <0x21800000 0x1000>, <0x02620128 4>;
-			ranges = <0x81000000 0 0 0x23250000 0 0x4000
-				0x82000000 0 0x50000000 0x50000000 0 0x10000000>;
+			ranges = <0x82000000 0 0x50000000 0x50000000
+				  0 0x10000000>;
 
 			status = "disabled";
 			device_type = "pci";
 			num-lanes = <2>;
+			bus-range = <0x00 0xff>;
 
+			/* error interrupt */
+			interrupts = <GIC_SPI 38 IRQ_TYPE_EDGE_RISING>;
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 7>;
 			interrupt-map = <0 0 0 1 &pcie_intc0 0>, /* INT A */
diff --git a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
index 015f795a8d19..08cce17a25a0 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
+++ b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
@@ -72,7 +72,7 @@
 		};
 	};
 
-	pwm10: dmtimer-pwm@10 {
+	pwm10: dmtimer-pwm {
 		compatible = "ti,omap-dmtimer-pwm";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pwm_pins>;
@@ -147,7 +147,7 @@
 		gpio = <&gpio5 27 GPIO_ACTIVE_HIGH>;	/* gpio155, lcd INI */
 	};
 
-	lcd0: display@0 {
+	lcd0: display {
 		compatible = "panel-dpi";
 		label = "15";
 		status = "okay";
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi
index 5ae8e9297e9a..368e21934285 100644
--- a/arch/arm/boot/dts/ls1021a.dtsi
+++ b/arch/arm/boot/dts/ls1021a.dtsi
@@ -626,6 +626,7 @@
 			interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>;
 			dr_mode = "host";
 			snps,quirk-frame-length-adjustment = <0x20>;
+			snps,dis_rxdet_inp3_quirk;
 		};
 
 		pcie@3400000 {
diff --git a/arch/arm/boot/dts/meson8b.dtsi b/arch/arm/boot/dts/meson8b.dtsi
index 2bfe401a4da9..fc4080de4b7b 100644
--- a/arch/arm/boot/dts/meson8b.dtsi
+++ b/arch/arm/boot/dts/meson8b.dtsi
@@ -46,6 +46,7 @@
 
 #include <dt-bindings/clock/meson8b-clkc.h>
 #include <dt-bindings/gpio/meson8b-gpio.h>
+#include <dt-bindings/reset/amlogic,meson8b-reset.h>
 #include "skeleton.dtsi"
 
 / {
@@ -105,6 +106,12 @@
 			#interrupt-cells = <3>;
 		};
 
+		reset: reset-controller@c1104404 {
+			compatible = "amlogic,meson8b-reset";
+			reg = <0xc1104404 0x20>;
+			#reset-cells = <1>;
+		};
+
 		wdt: watchdog@c1109900 {
 			compatible = "amlogic,meson8b-wdt";
 			reg = <0xc1109900 0x8>;
diff --git a/arch/arm/boot/dts/mpa1600.dts b/arch/arm/boot/dts/mpa1600.dts
index f0f5e1098928..116ce78bea4f 100644
--- a/arch/arm/boot/dts/mpa1600.dts
+++ b/arch/arm/boot/dts/mpa1600.dts
@@ -17,15 +17,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -61,7 +52,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 	};
 
diff --git a/arch/arm/boot/dts/omap24xx-clocks.dtsi b/arch/arm/boot/dts/omap24xx-clocks.dtsi
index ca73722b5ea4..769a346de613 100644
--- a/arch/arm/boot/dts/omap24xx-clocks.dtsi
+++ b/arch/arm/boot/dts/omap24xx-clocks.dtsi
@@ -164,7 +164,7 @@
 		clock-div = <1>;
 	};
 
-	func_96m_ck: func_96m_ck {
+	func_96m_ck: func_96m_ck@540 {
 		#clock-cells = <0>;
 	};
 
diff --git a/arch/arm/boot/dts/omap3-beagle-xm.dts b/arch/arm/boot/dts/omap3-beagle-xm.dts
index 01e1e2d5c735..8ffde06281ad 100644
--- a/arch/arm/boot/dts/omap3-beagle-xm.dts
+++ b/arch/arm/boot/dts/omap3-beagle-xm.dts
@@ -91,7 +91,7 @@
 		vcc-supply = <&hsusb2_power>;
 	};
 
-	tfp410: encoder@0 {
+	tfp410: encoder0 {
 		compatible = "ti,tfp410";
 		powerdown-gpios = <&twl_gpio 2 GPIO_ACTIVE_LOW>;
 
@@ -104,7 +104,7 @@
 			port@0 {
 				reg = <0>;
 
-				tfp410_in: endpoint@0 {
+				tfp410_in: endpoint {
 					remote-endpoint = <&dpi_out>;
 				};
 			};
@@ -112,14 +112,14 @@
 			port@1 {
 				reg = <1>;
 
-				tfp410_out: endpoint@0 {
+				tfp410_out: endpoint {
 					remote-endpoint = <&dvi_connector_in>;
 				};
 			};
 		};
 	};
 
-	dvi0: connector@0 {
+	dvi0: connector0 {
 		compatible = "dvi-connector";
 		label = "dvi";
 
@@ -134,7 +134,7 @@
 		};
 	};
 
-	tv0: connector@1 {
+	tv0: connector1 {
 		compatible = "svideo-connector";
 		label = "tv";
 
diff --git a/arch/arm/boot/dts/omap3-beagle.dts b/arch/arm/boot/dts/omap3-beagle.dts
index a4deff0e2d52..a19d907d4850 100644
--- a/arch/arm/boot/dts/omap3-beagle.dts
+++ b/arch/arm/boot/dts/omap3-beagle.dts
@@ -85,7 +85,7 @@
 
 	};
 
-	tfp410: encoder@0 {
+	tfp410: encoder0 {
 		compatible = "ti,tfp410";
 		powerdown-gpios = <&gpio6 10 GPIO_ACTIVE_LOW>;	/* gpio_170 */
 
@@ -99,7 +99,7 @@
 			port@0 {
 				reg = <0>;
 
-				tfp410_in: endpoint@0 {
+				tfp410_in: endpoint {
 					remote-endpoint = <&dpi_out>;
 				};
 			};
@@ -107,14 +107,14 @@
 			port@1 {
 				reg = <1>;
 
-				tfp410_out: endpoint@0 {
+				tfp410_out: endpoint {
 					remote-endpoint = <&dvi_connector_in>;
 				};
 			};
 		};
 	};
 
-	dvi0: connector@0 {
+	dvi0: connector0 {
 		compatible = "dvi-connector";
 		label = "dvi";
 
@@ -129,7 +129,7 @@
 		};
 	};
 
-	tv0: connector@1 {
+	tv0: connector1 {
 		compatible = "svideo-connector";
 		label = "tv";
 
diff --git a/arch/arm/boot/dts/omap3-cm-t3x.dtsi b/arch/arm/boot/dts/omap3-cm-t3x.dtsi
index a8127bc31fd9..6a0df13fa0f3 100644
--- a/arch/arm/boot/dts/omap3-cm-t3x.dtsi
+++ b/arch/arm/boot/dts/omap3-cm-t3x.dtsi
@@ -57,7 +57,7 @@
 		regulator-max-microvolt = <3300000>;
 	};
 
-	tv0: connector@1 {
+	tv0: connector {
 		compatible = "svideo-connector";
 		label = "tv";
 
diff --git a/arch/arm/boot/dts/omap3-devkit8000-common.dtsi b/arch/arm/boot/dts/omap3-devkit8000-common.dtsi
index b1b8ebf90c1c..586010179752 100644
--- a/arch/arm/boot/dts/omap3-devkit8000-common.dtsi
+++ b/arch/arm/boot/dts/omap3-devkit8000-common.dtsi
@@ -68,7 +68,7 @@
 		};
 	};
 
-	tfp410: encoder@0 {
+	tfp410: encoder0 {
 		compatible = "ti,tfp410";
 		powerdown-gpios = <&twl_gpio 7 GPIO_ACTIVE_LOW>;
 
@@ -79,7 +79,7 @@
 			port@0 {
 				reg = <0>;
 
-				tfp410_in: endpoint@0 {
+				tfp410_in: endpoint {
 					remote-endpoint = <&dpi_dvi_out>;
 				};
 			};
@@ -87,14 +87,14 @@
 			port@1 {
 				reg = <1>;
 
-				tfp410_out: endpoint@0 {
+				tfp410_out: endpoint {
 					remote-endpoint = <&dvi_connector_in>;
 				};
 			};
 		};
 	};
 
-	dvi0: connector@0 {
+	dvi0: connector0 {
 		compatible = "dvi-connector";
 		label = "dvi";
 
@@ -109,7 +109,7 @@
 		};
 	};
 
-	tv0: connector@1 {
+	tv0: connector1 {
 		compatible = "svideo-connector";
 		label = "tv";
 
@@ -352,7 +352,7 @@
 	vdda_dac-supply = <&vdac>;
 
 	port {
-		dpi_dvi_out: endpoint@0 {
+		dpi_dvi_out: endpoint {
 			remote-endpoint = <&tfp410_in>;
 			data-lines = <24>;
 		};
diff --git a/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi b/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi
index 738910db5c0c..2d64bcffaaa8 100644
--- a/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi
+++ b/arch/arm/boot/dts/omap3-devkit8000-lcd-common.dtsi
@@ -14,7 +14,7 @@
 		display2 = &tv0;
 	};
 
-	lcd0: display@0 {
+	lcd0: display {
 		compatible = "panel-dpi";
 		label = "lcd";
 
@@ -30,7 +30,7 @@
 
 &dss {
 	port {
-		dpi_lcd_out: endpoint@1 {
+		dpi_lcd_out: endpoint {
 			remote-endpoint = <&lcd_in>;
 			data-lines = <24>;
 		};
diff --git a/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts b/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts
index d5705356d52c..d8b16398bfb3 100644
--- a/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts
+++ b/arch/arm/boot/dts/omap3-devkit8000-lcd43.dts
@@ -16,7 +16,7 @@
 	model = "TimLL OMAP3 Devkit8000 with 4.3'' LCD panel";
 	compatible = "timll,omap3-devkit8000", "ti,omap3";
 
-	lcd0: display@0 {
+	lcd0: display {
 		panel-timing {
 			clock-frequency = <10164705>;
 			hactive = <480>;
diff --git a/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts b/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts
index 4afad4b233ec..edb37ba80498 100644
--- a/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts
+++ b/arch/arm/boot/dts/omap3-devkit8000-lcd70.dts
@@ -16,7 +16,7 @@
 	model = "TimLL OMAP3 Devkit8000 with 7.0'' LCD panel";
 	compatible = "timll,omap3-devkit8000", "ti,omap3";
 
-	lcd0: display@0 {
+	lcd0: display {
 		panel-timing {
 			clock-frequency = <40000000>;
 			hactive = <800>;
diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi
index ab9fb8f49ff3..c09a0574af90 100644
--- a/arch/arm/boot/dts/omap3-gta04.dtsi
+++ b/arch/arm/boot/dts/omap3-gta04.dtsi
@@ -100,12 +100,28 @@
 		};
 	};
 
+	backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm11 0 2000000 0>;
+		pwm-names = "backlight";
+		brightness-levels = <0 11 20 30 40 50 60 70 80 90 100>;
+		default-brightness-level = <9>;	/* => 90 */
+		pinctrl-names = "default";
+		pinctrl-0 = <&backlight_pins>;
+	};
+
+	pwm11: dmtimer-pwm {
+		compatible = "ti,omap-dmtimer-pwm";
+		ti,timers = <&timer11>;
+		#pwm-cells = <3>;
+	};
+
 	hsusb2_phy: hsusb2_phy {
 		compatible = "usb-nop-xceiv";
 		reset-gpios = <&gpio6 14 GPIO_ACTIVE_LOW>;
 	};
 
-	tv0: connector@1 {
+	tv0: connector {
 		compatible = "svideo-connector";
 		label = "tv";
 
@@ -126,19 +142,24 @@
 
 			port@0 {
 				reg = <0>;
-				opa_in: endpoint@0 {
+				opa_in: endpoint {
 					remote-endpoint = <&venc_out>;
 				};
 			};
 
 			port@1 {
 				reg = <1>;
-				opa_out: endpoint@0 {
+				opa_out: endpoint {
 					remote-endpoint = <&tv_connector_in>;
 				};
 			};
 		};
 	};
+
+	wifi_pwrseq: wifi_pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		reset-gpios = <&tca6507 0 GPIO_ACTIVE_LOW>;	/* W2CBW003 reset through tca6507 */
+	};
 };
 
 &omap3_pmx_core {
@@ -190,6 +211,12 @@
 		>;
 	};
 
+	backlight_pins: backlight_pins_pimnux {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20ba, MUX_MODE3)		/* gpt11/gpio57 */
+		>;
+	};
+
 	dss_dpi_pins: pinmux_dss_dpi_pins {
                pinctrl-single,pins = <
 			OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0)   /* dss_pclk.dss_pclk */
@@ -228,6 +255,24 @@
 			OMAP3_CORE1_IOPAD(0x21c6, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda.hdq */
 		>;
 	};
+
+	bma180_pins: pinmux_bma180_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x213a, PIN_INPUT_PULLUP | MUX_MODE4) /* gpio115 */
+		>;
+	};
+
+	itg3200_pins: pinmux_itg3200_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20b8, PIN_INPUT_PULLUP | MUX_MODE4) /* gpio56 */
+		>;
+	};
+
+	hmc5843_pins: pinmux_hmc5843_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2134, PIN_INPUT_PULLUP | MUX_MODE4) /* gpio112 */
+		>;
+	};
 };
 
 &omap3_pmx_core2 {
@@ -298,6 +343,8 @@
 	bma180@41 {
 		compatible = "bosch,bma180";
 		reg = <0x41>;
+		pinctrl-names = "default";
+		pintcrl-0 = <&bma180_pins>;
 		interrupt-parent = <&gpio4>;
 		interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; /* GPIO_115 */
 	};
@@ -306,12 +353,14 @@
 	itg3200@68 {
 		compatible = "invensense,itg3200";
 		reg = <0x68>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&itg3200_pins>;
 		interrupt-parent = <&gpio2>;
-		interrupts = <24 0>; /* GPIO_56 */
+		interrupts = <24 IRQ_TYPE_EDGE_FALLING>; /* GPIO_56 */
 	};
 
-	/* leds */
-	tca6507@45 {
+	/* leds + gpios */
+	tca6507: tca6507@45 {
 		compatible = "ti,tca6507";
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -351,6 +400,10 @@
 	hmc5843@1e {
 		compatible = "honeywell,hmc5883l";
 		reg = <0x1e>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&hmc5843_pins>;
+		interrupt-parent = <&gpio4>;
+		interrupts = <16 IRQ_TYPE_EDGE_FALLING>;	/* gpio112 */
 	};
 
 	/* touchscreen */
@@ -362,6 +415,12 @@
 		gpios = <&gpio6 0 GPIO_ACTIVE_LOW>;
 		ti,x-plate-ohms = <600>;
 	};
+
+	/* RFID EEPROM */
+	m24lr64@50 {
+		compatible = "at,24c64";
+		reg = <0x50>;
+	};
 };
 
 &i2c3 {
@@ -398,6 +457,7 @@
 	bus-width = <4>;
 	ti,non-removable;
 	cap-power-off-card;
+	mmc-pwrseq = <&wifi_pwrseq>;
 };
 
 &mmc3 {
diff --git a/arch/arm/boot/dts/omap3-ha-lcd.dts b/arch/arm/boot/dts/omap3-ha-lcd.dts
index 11aa28d73f3a..60af7c2358a3 100644
--- a/arch/arm/boot/dts/omap3-ha-lcd.dts
+++ b/arch/arm/boot/dts/omap3-ha-lcd.dts
@@ -121,7 +121,7 @@
 		display0 = &lcd0;
 	};
 
-	lcd0: display@0 {
+	lcd0: display {
 		compatible = "panel-dpi";
 		label = "lcd";
 
diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
index b6971060648a..667f96245729 100644
--- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi
+++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
@@ -60,7 +60,7 @@
 		vcc-supply = <&hsusb1_power>;
 	};
 
-	tfp410: encoder@0 {
+	tfp410: encoder {
 		compatible = "ti,tfp410";
 		powerdown-gpios = <&gpio6 10 GPIO_ACTIVE_LOW>; /* gpio_170 */
 
@@ -71,7 +71,7 @@
 			port@0 {
 				reg = <0>;
 
-				tfp410_in: endpoint@0 {
+				tfp410_in: endpoint {
 					remote-endpoint = <&dpi_out>;
 				};
 			};
@@ -79,14 +79,14 @@
 			port@1 {
 				reg = <1>;
 
-				tfp410_out: endpoint@0 {
+				tfp410_out: endpoint {
 					remote-endpoint = <&dvi_connector_in>;
 				};
 			};
 		};
 	};
 
-	dvi0: connector@0 {
+	dvi0: connector {
 		compatible = "dvi-connector";
 		label = "dvi";
 
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 2b74a81d1de2..2a6078a8422c 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -143,6 +143,18 @@
 		io-channels = <&twl_madc 0>, <&twl_madc 4>, <&twl_madc 12>;
 		io-channel-names = "temp", "bsi", "vbat";
 	};
+
+	pwm9: dmtimer-pwm {
+		compatible = "ti,omap-dmtimer-pwm";
+		#pwm-cells = <3>;
+		ti,timers = <&timer9>;
+		ti,clock-source = <0x00>; /* timer_sys_ck */
+	};
+
+	ir: n900-ir {
+		compatible = "nokia,n900-ir";
+		pwms = <&pwm9 0 26316 0>; /* 38000 Hz */
+	};
 };
 
 &omap3_pmx_core {
diff --git a/arch/arm/boot/dts/omap3-overo-common-dvi.dtsi b/arch/arm/boot/dts/omap3-overo-common-dvi.dtsi
index 802f704f67e5..ae5564abbe2f 100644
--- a/arch/arm/boot/dts/omap3-overo-common-dvi.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-common-dvi.dtsi
@@ -69,7 +69,7 @@
 		display0 = &dvi0;
 	};
 
-	tfp410: encoder@0 {
+	tfp410: encoder {
 		compatible = "ti,tfp410";
 
 		ports {
@@ -79,7 +79,7 @@
 			port@0 {
 				reg = <0>;
 
-				tfp410_in: endpoint@0 {
+				tfp410_in: endpoint {
 					remote-endpoint = <&dpi_out>;
 				};
 			};
@@ -87,14 +87,14 @@
 			port@1 {
 				reg = <1>;
 
-				tfp410_out: endpoint@0 {
+				tfp410_out: endpoint {
 					remote-endpoint = <&dvi_connector_in>;
 				};
 			};
 		};
 	};
 
-	dvi0: connector@0 {
+	dvi0: connector {
 		compatible = "dvi-connector";
 		label = "dvi";
 
diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
index 6314da2580f5..ca86da68220c 100644
--- a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
@@ -119,7 +119,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&mcspi1_pins>;
 
-	lcd0: display@0 {
+	lcd0: display {
 		compatible = "lgphilips,lb035q02";
 		label = "lcd35";
 
diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
index 7e3fe85a8ad9..b0753ef8abd4 100644
--- a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
@@ -96,7 +96,7 @@
 		display0 = &lcd0;
 	};
 
-	lcd0: display@0 {
+	lcd0: display {
 		compatible = "samsung,lte430wq-f0c", "panel-dpi";
 		label = "lcd43";
 
diff --git a/arch/arm/boot/dts/omap3-pandora-common.dtsi b/arch/arm/boot/dts/omap3-pandora-common.dtsi
index bcf39d606b65..dbc4dc721cc2 100644
--- a/arch/arm/boot/dts/omap3-pandora-common.dtsi
+++ b/arch/arm/boot/dts/omap3-pandora-common.dtsi
@@ -27,7 +27,7 @@
 		display0 = &lcd;
 	};
 
-	tv: connector@1 {
+	tv: connector {
 		compatible = "connector-analog-tv";
 		label = "tv";
 
diff --git a/arch/arm/boot/dts/omap3-sb-t35.dtsi b/arch/arm/boot/dts/omap3-sb-t35.dtsi
index 827f614261f6..73643fabde5d 100644
--- a/arch/arm/boot/dts/omap3-sb-t35.dtsi
+++ b/arch/arm/boot/dts/omap3-sb-t35.dtsi
@@ -3,7 +3,7 @@
  */
 
 / {
-	tfp410: encoder@0 {
+	tfp410: encoder {
 		compatible = "ti,tfp410";
 
 		powerdown-gpios = <&gpio2 22 GPIO_ACTIVE_LOW>;  /* gpio_54 */
@@ -18,7 +18,7 @@
 			port@0 {
 				reg = <0>;
 
-				tfp410_in: endpoint@0 {
+				tfp410_in: endpoint {
 					remote-endpoint = <&dpi_out>;
 				};
 			};
@@ -26,14 +26,14 @@
 			port@1 {
 				reg = <1>;
 
-				tfp410_out: endpoint@0 {
+				tfp410_out: endpoint {
 					remote-endpoint = <&dvi_connector_in>;
 				};
 			};
 		};
 	};
 
-	dvi0: connector@0 {
+	dvi0: connector {
 		compatible = "dvi-connector";
 		label = "dvi";
 
diff --git a/arch/arm/boot/dts/omap3-thunder.dts b/arch/arm/boot/dts/omap3-thunder.dts
index d659515ab9b8..9736ba79bb5b 100644
--- a/arch/arm/boot/dts/omap3-thunder.dts
+++ b/arch/arm/boot/dts/omap3-thunder.dts
@@ -85,7 +85,7 @@
 		display0 = &lcd0;
 	};
 
-	lcd0: display@0 {
+	lcd0: display {
 		compatible = "samsung,lte430wq-f0c", "panel-dpi";
 		label = "lcd";
 
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 9fbda38528dc..4c3c471d2a83 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -493,6 +493,8 @@
 			dmas = <&sdma 31>,
 			       <&sdma 32>;
 			dma-names = "tx", "rx";
+			clocks = <&mcbsp1_fck>;
+			clock-names = "fck";
 			status = "disabled";
 		};
 
@@ -511,6 +513,8 @@
 			dmas = <&sdma 33>,
 			       <&sdma 34>;
 			dma-names = "tx", "rx";
+			clocks = <&mcbsp2_fck>, <&mcbsp2_ick>;
+			clock-names = "fck", "ick";
 			status = "disabled";
 		};
 
@@ -529,6 +533,8 @@
 			dmas = <&sdma 17>,
 			       <&sdma 18>;
 			dma-names = "tx", "rx";
+			clocks = <&mcbsp3_fck>, <&mcbsp3_ick>;
+			clock-names = "fck", "ick";
 			status = "disabled";
 		};
 
@@ -545,6 +551,8 @@
 			dmas = <&sdma 19>,
 			       <&sdma 20>;
 			dma-names = "tx", "rx";
+			clocks = <&mcbsp4_fck>;
+			clock-names = "fck";
 			status = "disabled";
 		};
 
@@ -561,6 +569,8 @@
 			dmas = <&sdma 21>,
 			       <&sdma 22>;
 			dma-names = "tx", "rx";
+			clocks = <&mcbsp5_fck>;
+			clock-names = "fck";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts
index 06c54822ddc2..6b39808b8313 100644
--- a/arch/arm/boot/dts/omap4-duovero-parlor.dts
+++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts
@@ -40,7 +40,7 @@
 		};
 	};
 
-	hdmi0: connector@0 {
+	hdmi0: connector {
 		compatible = "hdmi-connector";
 		label = "hdmi";
 
diff --git a/arch/arm/boot/dts/omap4-duovero.dtsi b/arch/arm/boot/dts/omap4-duovero.dtsi
index f2a94fa62552..a90b582e4c3f 100644
--- a/arch/arm/boot/dts/omap4-duovero.dtsi
+++ b/arch/arm/boot/dts/omap4-duovero.dtsi
@@ -177,6 +177,7 @@
 
 	twl6040: twl@4b {
 		compatible = "ti,twl6040";
+		#clock-cells = <0>;
 		reg = <0x4b>;
 		interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;		/* IRQ_SYS_2N cascaded to gic */
 		ti,audpwron-gpio = <&gpio6 0 GPIO_ACTIVE_HIGH>;		/* gpio_160 */
@@ -207,6 +208,10 @@
 &mcpdm {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mcpdm_pins>;
+
+	clocks = <&twl6040>;
+	clock-names = "pdmclk";
+
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi
index df2e356ec089..f8f13952cfeb 100644
--- a/arch/arm/boot/dts/omap4-panda-common.dtsi
+++ b/arch/arm/boot/dts/omap4-panda-common.dtsi
@@ -103,7 +103,7 @@
 		enable-active-high;
 	};
 
-	tfp410: encoder@0 {
+	tfp410: encoder0 {
 		compatible = "ti,tfp410";
 		powerdown-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;	/* gpio_0 */
 
@@ -114,7 +114,7 @@
 			port@0 {
 				reg = <0>;
 
-				tfp410_in: endpoint@0 {
+				tfp410_in: endpoint {
 					remote-endpoint = <&dpi_out>;
 				};
 			};
@@ -122,14 +122,14 @@
 			port@1 {
 				reg = <1>;
 
-				tfp410_out: endpoint@0 {
+				tfp410_out: endpoint {
 					remote-endpoint = <&dvi_connector_in>;
 				};
 			};
 		};
 	};
 
-	dvi0: connector@0 {
+	dvi0: connector0 {
 		compatible = "dvi-connector";
 		label = "dvi";
 
@@ -144,7 +144,7 @@
 		};
 	};
 
-	tpd12s015: encoder@1 {
+	tpd12s015: encoder1 {
 		compatible = "ti,tpd12s015";
 
 		gpios = <&gpio2 28 GPIO_ACTIVE_HIGH>,	/* 60, CT CP HPD */
@@ -158,7 +158,7 @@
 			port@0 {
 				reg = <0>;
 
-				tpd12s015_in: endpoint@0 {
+				tpd12s015_in: endpoint {
 					remote-endpoint = <&hdmi_out>;
 				};
 			};
@@ -166,14 +166,14 @@
 			port@1 {
 				reg = <1>;
 
-				tpd12s015_out: endpoint@0 {
+				tpd12s015_out: endpoint {
 					remote-endpoint = <&hdmi_connector_in>;
 				};
 			};
 		};
 	};
 
-	hdmi0: connector@1 {
+	hdmi0: connector1 {
 		compatible = "hdmi-connector";
 		label = "hdmi";
 
@@ -376,6 +376,7 @@
 
 	twl6040: twl@4b {
 		compatible = "ti,twl6040";
+		#clock-cells = <0>;
 		reg = <0x4b>;
 
 		pinctrl-names = "default";
@@ -479,6 +480,10 @@
 &mcpdm {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mcpdm_pins>;
+
+	clocks = <&twl6040>;
+	clock-names = "pdmclk";
+
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/omap4-sdp.dts b/arch/arm/boot/dts/omap4-sdp.dts
index aae513265dc2..10d73a784050 100644
--- a/arch/arm/boot/dts/omap4-sdp.dts
+++ b/arch/arm/boot/dts/omap4-sdp.dts
@@ -160,7 +160,7 @@
 		enable-active-high;
 	};
 
-	tpd12s015: encoder@0 {
+	tpd12s015: encoder {
 		compatible = "ti,tpd12s015";
 
 		gpios = <&gpio2 28 GPIO_ACTIVE_HIGH>,	/* 60, CT CP HPD */
@@ -174,7 +174,7 @@
 			port@0 {
 				reg = <0>;
 
-				tpd12s015_in: endpoint@0 {
+				tpd12s015_in: endpoint {
 					remote-endpoint = <&hdmi_out>;
 				};
 			};
@@ -182,14 +182,14 @@
 			port@1 {
 				reg = <1>;
 
-				tpd12s015_out: endpoint@0 {
+				tpd12s015_out: endpoint {
 					remote-endpoint = <&hdmi_connector_in>;
 				};
 			};
 		};
 	};
 
-	hdmi0: connector@0 {
+	hdmi0: connector {
 		compatible = "hdmi-connector";
 		label = "hdmi";
 
@@ -367,6 +367,7 @@
 
 	twl6040: twl@4b {
 		compatible = "ti,twl6040";
+		#clock-cells = <0>;
 		reg = <0x4b>;
 
 		pinctrl-names = "default";
@@ -620,6 +621,10 @@
 &mcpdm {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mcpdm_pins>;
+
+	clocks = <&twl6040>;
+	clock-names = "pdmclk";
+
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/omap4-var-om44customboard.dtsi b/arch/arm/boot/dts/omap4-var-om44customboard.dtsi
index 6e278d7716a5..74940b6d7719 100644
--- a/arch/arm/boot/dts/omap4-var-om44customboard.dtsi
+++ b/arch/arm/boot/dts/omap4-var-om44customboard.dtsi
@@ -45,7 +45,7 @@
 		};
 	};
 
-	hdmi0: connector@0 {
+	hdmi0: connector {
 		compatible = "hdmi-connector";
 		pinctrl-names = "default";
 		pinctrl-0 = <&hdmi_hpd_pins>;
diff --git a/arch/arm/boot/dts/omap4-var-som-om44.dtsi b/arch/arm/boot/dts/omap4-var-som-om44.dtsi
index a17997f4e9aa..873cfc87260c 100644
--- a/arch/arm/boot/dts/omap4-var-som-om44.dtsi
+++ b/arch/arm/boot/dts/omap4-var-som-om44.dtsi
@@ -189,6 +189,7 @@
 
 	twl6040: twl@4b {
 		compatible = "ti,twl6040";
+		#clock-cells = <0>;
 		reg = <0x4b>;
 
 		pinctrl-names = "default";
@@ -252,6 +253,10 @@
 &mcpdm {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mcpdm_pins>;
+
+	clocks = <&twl6040>;
+	clock-names = "pdmclk";
+
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index 5d5b620b7d9b..5196113202a2 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -87,7 +87,7 @@
 		};
 	};
 
-	tpd12s015: encoder@0 {
+	tpd12s015: encoder {
 		compatible = "ti,tpd12s015";
 
 		pinctrl-names = "default";
@@ -102,7 +102,7 @@
 			port@0 {
 				reg = <0>;
 
-				tpd12s015_in: endpoint@0 {
+				tpd12s015_in: endpoint {
 					remote-endpoint = <&hdmi_out>;
 				};
 			};
@@ -110,14 +110,14 @@
 			port@1 {
 				reg = <1>;
 
-				tpd12s015_out: endpoint@0 {
+				tpd12s015_out: endpoint {
 					remote-endpoint = <&hdmi_connector_in>;
 				};
 			};
 		};
 	};
 
-	hdmi0: connector@0 {
+	hdmi0: connector {
 		compatible = "hdmi-connector";
 		label = "hdmi";
 
@@ -637,6 +637,7 @@
 
 	twl6040: twl@4b {
 		compatible = "ti,twl6040";
+		#clock-cells = <0>;
 		reg = <0x4b>;
 
 		pinctrl-names = "default";
@@ -658,6 +659,10 @@
 &mcpdm {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mcpdm_pins>;
+
+	clocks = <&twl6040>;
+	clock-names = "pdmclk";
+
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts
index 93fdfa96776e..a9765605d53b 100644
--- a/arch/arm/boot/dts/omap5-cm-t54.dts
+++ b/arch/arm/boot/dts/omap5-cm-t54.dts
@@ -112,7 +112,7 @@
                 };
         };
 
-	hdmi0: connector@0 {
+	hdmi0: connector0 {
 		compatible = "hdmi-connector";
 		label = "hdmi";
 
@@ -130,7 +130,7 @@
 		};
 	};
 
-	tfp410: encoder@0 {
+	tfp410: encoder0 {
 		compatible = "ti,tfp410";
 
 		ports {
@@ -140,7 +140,7 @@
 			port@0 {
 				reg = <0>;
 
-				tfp410_in: endpoint@0 {
+				tfp410_in: endpoint {
 					remote-endpoint = <&dpi_dvi_out>;
 				};
 			};
@@ -148,14 +148,14 @@
 			port@1 {
 				reg = <1>;
 
-				tfp410_out: endpoint@0 {
+				tfp410_out: endpoint {
 					remote-endpoint = <&dvi_connector_in>;
 				};
 			};
 		};
 	};
 
-	dvi0: connector@1 {
+	dvi0: connector1 {
 		compatible = "dvi-connector";
 		label = "dvi";
 
@@ -646,12 +646,17 @@
 	pinctrl-0 = <&dss_dpi_pins>;
 
 	port {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
 		dpi_dvi_out: endpoint@0 {
+			reg = <0>;
 			remote-endpoint = <&tfp410_in>;
 			data-lines = <24>;
 		};
 
 		dpi_lcd_out: endpoint@1 {
+			reg = <1>;
 			remote-endpoint = <&lcd_in>;
 			data-lines = <24>;
 		};
diff --git a/arch/arm/boot/dts/pm9g45.dts b/arch/arm/boot/dts/pm9g45.dts
index 66afcff67fde..0abd7bf17568 100644
--- a/arch/arm/boot/dts/pm9g45.dts
+++ b/arch/arm/boot/dts/pm9g45.dts
@@ -21,15 +21,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 		      clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/pxa27x.dtsi b/arch/arm/boot/dts/pxa27x.dtsi
index 210192c38df3..9e73dc6b3ed3 100644
--- a/arch/arm/boot/dts/pxa27x.dtsi
+++ b/arch/arm/boot/dts/pxa27x.dtsi
@@ -22,8 +22,15 @@
 			marvell,intc-nr-irqs = <34>;
 		};
 
+		pinctrl: pinctrl@40e00000 {
+			reg = <0x40e00054 0x20 0x40e0000c 0xc 0x40e0010c 4
+			       0x40f00020 0x10>;
+			compatible = "marvell,pxa27x-pinctrl";
+		};
+
 		gpio: gpio@40e00000 {
 			compatible = "intel,pxa27x-gpio";
+			gpio-ranges = <&pinctrl 0 0 128>;
 			clocks = <&clks CLK_NONE>;
 		};
 
diff --git a/arch/arm/boot/dts/pxa2xx.dtsi b/arch/arm/boot/dts/pxa2xx.dtsi
index 5e5af078b9b5..3ff077ca4400 100644
--- a/arch/arm/boot/dts/pxa2xx.dtsi
+++ b/arch/arm/boot/dts/pxa2xx.dtsi
@@ -140,5 +140,13 @@
 			reg = <0x40900000 0x3c>;
 			interrupts = <30 31>;
 		};
+
+		lcd-controller@40500000 {
+			compatible = "marvell,pxa2xx-lcdc";
+			reg = <0x44000000 0x10000>;
+			interrupts = <17>;
+			clocks = <&clks CLK_LCD>;
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/pxa3xx.dtsi b/arch/arm/boot/dts/pxa3xx.dtsi
index fec47bcd8292..9d6f3aacedb7 100644
--- a/arch/arm/boot/dts/pxa3xx.dtsi
+++ b/arch/arm/boot/dts/pxa3xx.dtsi
@@ -1,6 +1,96 @@
 /* The pxa3xx skeleton simply augments the 2xx version */
 #include "pxa2xx.dtsi"
 
+#define MFP_PIN_PXA300(gpio)				\
+	((gpio <= 2) ? (0x00b4 + 4 * gpio) :		\
+	 (gpio <= 26) ? (0x027c + 4 * (gpio - 3)) :	\
+	 (gpio <= 98) ? (0x0400 + 4 * (gpio - 27)) :	\
+	 (gpio <= 127) ? (0x0600 + 4 * (gpio - 99)) :	\
+	 0)
+
+#define MFP_PIN_PXA310(gpio)				\
+	((gpio <= 2) ? (0x00b4 + 4 * gpio) :		\
+	 (gpio <= 26) ? (0x027c + 4 * (gpio - 3)) :	\
+	 (gpio <= 29) ? (0x0400 + 4 * (gpio - 27)) :	\
+	 (gpio <= 98) ? (0x0418 + 4 * (gpio - 30)) :	\
+	 (gpio <= 127) ? (0x0600 + 4 * (gpio - 99)) :	\
+	 (gpio <= 262) ? 0 :				\
+	 (gpio <= 268) ? (0x052c + 4 * (gpio - 263)) :	\
+	 0)
+
+#define MFP_PIN_PXA320(gpio)				\
+	((gpio <= 4) ? (0x0124 + 4 * gpio) :		\
+	 (gpio <= 9) ? (0x028c + 4 * (gpio - 5)) :	\
+	 (gpio <= 10) ? (0x0458 + 4 * (gpio - 10)) :	\
+	 (gpio <= 26) ? (0x02a0 + 4 * (gpio - 11)) :	\
+	 (gpio <= 48) ? (0x0400 + 4 * (gpio - 27)) :	\
+	 (gpio <= 62) ? (0x045c + 4 * (gpio - 49)) :	\
+	 (gpio <= 73) ? (0x04b4 + 4 * (gpio - 63)) :	\
+	 (gpio <= 98) ? (0x04f0 + 4 * (gpio - 74)) :	\
+	 (gpio <= 127) ? (0x0600 + 4 * (gpio - 99)) :	\
+	 0)
+
+/*
+ * MFP Alternate functions for pins having a gpio.
+ * Example of use: pinctrl-single,pins = < MFP_PIN_PXA310(21) MFP_AF1 >
+ */
+#define MFP_AF0		(0 << 0)
+#define MFP_AF1		(1 << 0)
+#define MFP_AF2		(2 << 0)
+#define MFP_AF3		(3 << 0)
+#define MFP_AF4		(4 << 0)
+#define MFP_AF5		(5 << 0)
+#define MFP_AF6		(6 << 0)
+
+/*
+ * MFP drive strength functions for pins.
+ * Example of use: pinctrl-single,drive-strength = MFP_DS03X;
+ */
+#define MFP_DSMSK	(0x7 << 10)
+#define MFP_DS01X	< (0x0 << 10) MFP_DSMSK >
+#define MFP_DS02X	< (0x1 << 10) MFP_DSMSK >
+#define MFP_DS03X	< (0x2 << 10) MFP_DSMSK >
+#define MFP_DS04X	< (0x3 << 10) MFP_DSMSK >
+#define MFP_DS06X	< (0x4 << 10) MFP_DSMSK >
+#define MFP_DS08X	< (0x5 << 10) MFP_DSMSK >
+#define MFP_DS10X	< (0x6 << 10) MFP_DSMSK >
+#define MFP_DS13X	< (0x7 << 10) MFP_DSMSK >
+
+/*
+ * MFP low power mode for pins.
+ * Example of use:
+ *   pinctrl-single,low-power-mode = MFP_LPM(MFP_LPM_PULL_LOW|MFP_LPM_EDGE_FALL);
+ *
+ * Table that determines the low power modes outputs, with actual settings
+ * used in parentheses for don't-care values. Except for the float output,
+ * the configured driven and pulled levels match, so if there is a need for
+ * non-LPM pulled output, the same configuration could probably be used.
+ *
+ * Output value  sleep_oe_n  sleep_data  pullup_en  pulldown_en  pull_sel
+ *                 (bit 7)    (bit 8)    (bit 14)     (bit 13)   (bit 15)
+ *
+ * Input            0          X(0)        X(0)        X(0)       0
+ * Drive 0          0          0           0           X(1)       0
+ * Drive 1          0          1           X(1)        0	  0
+ * Pull hi (1)      1          X(1)        1           0	  0
+ * Pull lo (0)      1          X(0)        0           1	  0
+ * Z (float)        1          X(0)        0           0	  0
+ */
+#define MFP_LPM(x)		< (x) MFP_LPM_MSK >
+
+#define MFP_LPM_MSK		0xe1f0
+#define MFP_LPM_INPUT		0x0000
+#define MFP_LPM_DRIVE_LOW	0x2000
+#define MFP_LPM_DRIVE_HIGH	0x4100
+#define MFP_LPM_PULL_LOW	0x2080
+#define MFP_LPM_PULL_HIGH	0x4180
+#define MFP_LPM_FLOAT		0x0080
+
+#define MFP_LPM_EDGE_NONE	0x0000
+#define MFP_LPM_EDGE_RISE	0x0010
+#define MFP_LPM_EDGE_FALL	0x0020
+#define MFP_LPM_EDGE_BOTH	0x0030
+
 / {
 	model = "Marvell PXA3xx familiy SoC";
 	compatible = "marvell,pxa3xx";
@@ -43,6 +133,15 @@
 			marvell,intc-nr-irqs = <56>;
 		};
 
+		pinctrl: pinctrl@40e10000 {
+			compatible = "pinconf-single";
+			reg = <0x40e10000 0xffff>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-single,register-width = <32>;
+			pinctrl-single,function-mask = <0x7>;
+		};
+
 		gpio: gpio@40e00000 {
 			compatible = "intel,pxa3xx-gpio";
 			reg = <0x40e00000 0x10000>;
@@ -92,7 +191,39 @@
 			compatible = "marvell,pxa-ohci";
 			reg = <0x4c000000 0x10000>;
 			interrupts = <3>;
-			clocks = <&clks CLK_USBHOST>;
+			clocks = <&clks CLK_USBH>;
+			status = "disabled";
+		};
+
+		pwm0: pwm@40b00000 {
+			compatible = "marvell,pxa270-pwm";
+			reg = <0x40b00000 0x10>;
+			#pwm-cells = <1>;
+			clocks = <&clks CLK_PWM0>;
+			status = "disabled";
+		};
+
+		pwm1: pwm@40b00010 {
+			compatible = "marvell,pxa270-pwm";
+			reg = <0x40b00010 0x10>;
+			#pwm-cells = <1>;
+			clocks = <&clks CLK_PWM1>;
+			status = "disabled";
+		};
+
+		pwm2: pwm@40c00000 {
+			compatible = "marvell,pxa270-pwm";
+			reg = <0x40c00000 0x10>;
+			#pwm-cells = <1>;
+			clocks = <&clks CLK_PWM0>;
+			status = "disabled";
+		};
+
+		pwm3: pwm@40c00010 {
+			compatible = "marvell,pxa270-pwm";
+			reg = <0x40c00010 0x10>;
+			#pwm-cells = <1>;
+			clocks = <&clks CLK_PWM1>;
 			status = "disabled";
 		};
 	};
diff --git a/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts b/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts
new file mode 100644
index 000000000000..0abc93e5bb00
--- /dev/null
+++ b/arch/arm/boot/dts/qcom-apq8060-dragonboard.dts
@@ -0,0 +1,626 @@
+/*
+ * Copyright 2016 Linaro Ltd
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
+#include "qcom-msm8660.dtsi"
+
+/ {
+	model = "Qualcomm APQ8060 Dragonboard";
+	compatible = "qcom,apq8060-dragonboard", "qcom,msm8660";
+
+	aliases {
+		serial0 = &gsbi12_serial;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	regulators {
+		compatible = "simple-bus";
+
+		/* Main power of the board: 3.7V */
+		vph: regulator-fixed {
+			compatible = "regulator-fixed";
+			regulator-min-microvolt = <3700000>;
+			regulator-max-microvolt = <3700000>;
+			regulator-name = "VPH";
+			regulator-type = "voltage";
+			regulator-always-on;
+			regulator-boot-on;
+		};
+
+		/* This is a levelshifter for SDCC5 */
+		dragon_vio_txb: txb0104rgyr {
+			compatible = "regulator-fixed";
+			regulator-name = "Dragon SDCC levelshifter";
+			vin-supply = <&pm8058_l14>;
+			regulator-always-on;
+		};
+	};
+
+	soc {
+		pinctrl@800000 {
+			/* eMMMC pins, all 8 data lines connected */
+			dragon_sdcc1_pins: sdcc1 {
+				mux {
+					pins = "gpio159", "gpio160", "gpio161",
+					     "gpio162", "gpio163", "gpio164",
+					     "gpio165", "gpio166", "gpio167",
+					     "gpio168";
+					     function = "sdc1";
+				};
+				clk {
+					pins = "gpio167"; /* SDC5 CLK */
+					drive-strength = <16>;
+					bias-disable;
+				};
+				cmd {
+					pins = "gpio168"; /* SDC5 CMD */
+					drive-strength = <10>;
+					bias-pull-up;
+				};
+				data {
+					/* SDC5 D0 to D7 */
+					pins = "gpio159", "gpio160", "gpio161", "gpio162",
+					     "gpio163", "gpio164", "gpio165", "gpio166";
+					drive-strength = <10>;
+					bias-pull-up;
+				};
+			};
+
+			/*
+			 * The SDCC3 pins are hardcoded (non-muxable) but need some pin
+			 * configuration.
+			 */
+			dragon_sdcc3_pins: sdcc3 {
+				clk {
+					pins = "sdc3_clk";
+					drive-strength = <8>;
+					bias-disable;
+				};
+				cmd {
+					pins = "sdc3_cmd";
+					drive-strength = <8>;
+					bias-pull-up;
+				};
+				data {
+					pins = "sdc3_data";
+					drive-strength = <8>;
+					bias-pull-up;
+				};
+			};
+
+			/* Second SD card slot pins */
+			dragon_sdcc5_pins: sdcc5 {
+				mux {
+					pins = "gpio95", "gpio96", "gpio97",
+					    "gpio98", "gpio99", "gpio100";
+					function = "sdc5";
+				};
+				clk {
+					pins = "gpio97"; /* SDC5 CLK */
+					drive-strength = <16>;
+					bias-disable;
+				};
+				cmd {
+					pins = "gpio95"; /* SDC5 CMD */
+					drive-strength = <10>;
+					bias-pull-up;
+				};
+				data {
+					/* SDC5 D0 to D3 */
+					pins = "gpio96", "gpio98", "gpio99", "gpio100";
+					drive-strength = <10>;
+					bias-pull-up;
+				};
+			};
+
+			dragon_gsbi12_i2c_pins: gsbi12_i2c {
+				mux {
+					pins = "gpio115", "gpio116";
+					function = "gsbi12";
+				};
+				pinconf {
+					pins = "gpio115", "gpio116";
+					drive-strength = <16>;
+					/* These have external pull-up 4.7kOhm to 1.8V */
+					bias-disable;
+				};
+			};
+
+			/* Primary serial port uart 0 pins */
+			dragon_gsbi12_serial_pins: gsbi12_serial {
+				mux {
+					pins = "gpio117", "gpio118";
+					function = "gsbi12";
+				};
+				tx {
+					pins = "gpio117";
+					drive-strength = <8>;
+					bias-disable;
+				};
+				rx {
+					pins = "gpio118";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+			};
+		};
+
+		qcom,ssbi@500000 {
+			pmic@0 {
+				keypad@148 {
+					linux,keymap = <
+					MATRIX_KEY(0, 0, KEY_MENU)
+					MATRIX_KEY(0, 2, KEY_1)
+					MATRIX_KEY(0, 3, KEY_4)
+					MATRIX_KEY(0, 4, KEY_7)
+					MATRIX_KEY(1, 0, KEY_UP)
+					MATRIX_KEY(1, 1, KEY_LEFT)
+					MATRIX_KEY(1, 2, KEY_DOWN)
+					MATRIX_KEY(1, 3, KEY_5)
+					MATRIX_KEY(1, 3, KEY_8)
+					MATRIX_KEY(2, 0, KEY_HOME)
+					MATRIX_KEY(2, 1, KEY_REPLY)
+					MATRIX_KEY(2, 2, KEY_2)
+					MATRIX_KEY(2, 3, KEY_6)
+					MATRIX_KEY(3, 0, KEY_VOLUMEUP)
+					MATRIX_KEY(3, 1, KEY_RIGHT)
+					MATRIX_KEY(3, 2, KEY_3)
+					MATRIX_KEY(3, 3, KEY_9)
+					MATRIX_KEY(3, 4, KEY_SWITCHVIDEOMODE)
+					MATRIX_KEY(4, 0, KEY_VOLUMEDOWN)
+					MATRIX_KEY(4, 1, KEY_BACK)
+					MATRIX_KEY(4, 2, KEY_CAMERA)
+					MATRIX_KEY(4, 3, KEY_KBDILLUMTOGGLE)
+					>;
+					keypad,num-rows = <6>;
+					keypad,num-columns = <5>;
+				};
+
+				gpio@150 {
+					dragon_bmp085_gpios: bmp085-gpios {
+						pinconf {
+							pins = "gpio16";
+							function = "normal";
+							input-enable;
+							bias-disable;
+							power-source = <PM8058_GPIO_S3>;
+						};
+					};
+					dragon_sdcc3_gpios: sdcc3-gpios {
+						pinconf {
+							pins = "gpio22";
+							function = "normal";
+							input-enable;
+							bias-disable;
+							power-source = <PM8058_GPIO_S3>;
+						};
+					};
+					dragon_sdcc5_gpios: sdcc5-gpios {
+						pinconf {
+							pins = "gpio26";
+							function = "normal";
+							input-enable;
+							bias-pull-up;
+							qcom,pull-up-strength = <PMIC_GPIO_PULL_UP_30>;
+							power-source = <PM8058_GPIO_S3>;
+						};
+					};
+					dragon_ak8975_gpios: ak8975-gpios {
+						pinconf {
+							pins = "gpio33";
+							function = "normal";
+							input-enable;
+							bias-disable;
+							power-source = <PM8058_GPIO_S3>;
+						};
+					};
+				};
+			};
+		};
+
+		gsbi@19c00000 {
+			status = "ok";
+			qcom,mode = <GSBI_PROT_I2C_UART>;
+
+			serial@19c40000 {
+				status = "ok";
+				pinctrl-names = "default";
+				pinctrl-0 = <&dragon_gsbi12_serial_pins>;
+			};
+
+			i2c@19c80000 {
+				status = "ok";
+				pinctrl-names = "default";
+				pinctrl-0 = <&dragon_gsbi12_i2c_pins>;
+
+				ak8975@0c {
+					compatible = "asahi-kasei,ak8975";
+					reg = <0x0c>;
+					/* GPIO33 has interrupt 224 on the PM8058 */
+					interrupt-parent = <&pm8058_gpio>;
+					interrupts = <224 IRQ_TYPE_EDGE_RISING>;
+					pinctrl-names = "default";
+					pinctrl-0 = <&dragon_ak8975_gpios>;
+					vid-supply = <&pm8058_lvs0>; // 1.8V
+					vdd-supply = <&pm8058_l14>; // 2.85V
+				};
+				bmp085@77 {
+					compatible = "bosch,bmp085";
+					reg = <0x77>;
+					/* GPIO16 has interrupt 207 on the PM8058 */
+					interrupt-parent = <&pm8058_gpio>;
+					interrupts = <207 IRQ_TYPE_EDGE_RISING>;
+					reset-gpios = <&tlmm 86 GPIO_ACTIVE_LOW>;
+					pinctrl-names = "default";
+					pinctrl-0 = <&dragon_bmp085_gpios>;
+					vddd-supply = <&pm8058_lvs0>; // 1.8V
+					vdda-supply = <&pm8058_l14>; // 2.85V
+				};
+			};
+		};
+
+		rpm@104000 {
+			/*
+			 * Set up of the PMIC RPM regulators for this board
+			 * PM8901 supplies "preliminary regulators" whatever
+			 * that means
+			 */
+			pm8901-regulators {
+				vdd_l0-supply = <&pm8901_s4>;
+				vdd_l1-supply = <&vph>;
+				vdd_l2-supply = <&vph>;
+				vdd_l3-supply = <&vph>;
+				vdd_l4-supply = <&vph>;
+				vdd_l5-supply = <&vph>;
+				vdd_l6-supply = <&vph>;
+				/* vdd_s0-supply, vdd_s1-supply: SAW regulators */
+				vdd_s2-supply = <&vph>;
+				vdd_s3-supply = <&vph>;
+				vdd_s4-supply = <&vph>;
+				lvs0_in-supply = <&pm8058_s3>;
+				lvs1_in-supply = <&pm8901_s4>;
+				lvs2_in-supply = <&pm8058_l0>;
+				lvs3_in-supply = <&pm8058_s2>;
+				mvs_in-supply = <&pm8058_s3>;
+
+				l0 {
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					bias-pull-down;
+				};
+				l1 {
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
+					bias-pull-down;
+				};
+				l2 {
+					regulator-min-microvolt = <2850000>;
+					regulator-max-microvolt = <3300000>;
+					bias-pull-down;
+				};
+				l3 {
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
+					bias-pull-down;
+				};
+				l4 {
+					regulator-min-microvolt = <2600000>;
+					regulator-max-microvolt = <2600000>;
+					bias-pull-down;
+				};
+				l5 {
+					regulator-min-microvolt = <2850000>;
+					regulator-max-microvolt = <2850000>;
+					bias-pull-down;
+				};
+				l6 {
+					regulator-min-microvolt = <2200000>;
+					regulator-max-microvolt = <2200000>;
+					bias-pull-down;
+				};
+
+				/* s0 and s1 are SAW regulators controlled over SPM */
+				s2 {
+					regulator-min-microvolt = <1300000>;
+					regulator-max-microvolt = <1300000>;
+					qcom,switch-mode-frequency = <1600000>;
+					bias-pull-down;
+				};
+				s3 {
+					regulator-min-microvolt = <1100000>;
+					regulator-max-microvolt = <1100000>;
+					qcom,switch-mode-frequency = <1600000>;
+					bias-pull-down;
+				};
+				s4 {
+					regulator-min-microvolt = <1225000>;
+					regulator-max-microvolt = <1225000>;
+					qcom,switch-mode-frequency = <1600000>;
+					bias-pull-down;
+				};
+
+				/* LVS0 thru 3 and mvs0 are just switches */
+				lvs0 {
+					regulator-always-on;
+				};
+				lvs1 { };
+				lvs2 { };
+				lvs3 { };
+				mvs0 {};
+
+			};
+
+			pm8058-regulators {
+				vdd_l0_l1_lvs-supply = <&pm8058_s3>;
+				vdd_l2_l11_l12-supply = <&vph>;
+				vdd_l3_l4_l5-supply = <&vph>;
+				vdd_l6_l7-supply = <&vph>;
+				vdd_l8-supply = <&vph>;
+				vdd_l9-supply = <&vph>;
+				vdd_l10-supply = <&vph>;
+				vdd_l13_l16-supply = <&pm8058_s4>;
+				vdd_l14_l15-supply = <&vph>;
+				vdd_l17_l18-supply = <&vph>;
+				vdd_l19_l20-supply = <&vph>;
+				vdd_l21-supply = <&pm8058_s3>;
+				vdd_l22-supply = <&pm8058_s3>;
+				vdd_l23_l24_l25-supply = <&pm8058_s3>;
+				vdd_s0-supply = <&vph>;
+				vdd_s1-supply = <&vph>;
+				vdd_s2-supply = <&vph>;
+				vdd_s3-supply = <&vph>;
+				vdd_s4-supply = <&vph>;
+				vdd_ncp-supply = <&vph>;
+
+				l0 {
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					bias-pull-down;
+				};
+				l1 {
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					bias-pull-down;
+				};
+				l2 {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <2600000>;
+					bias-pull-down;
+				};
+				l3 {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					bias-pull-down;
+				};
+				l4 {
+					regulator-min-microvolt = <2850000>;
+					regulator-max-microvolt = <2850000>;
+					bias-pull-down;
+				};
+				l5 {
+					regulator-min-microvolt = <2850000>;
+					regulator-max-microvolt = <2850000>;
+					bias-pull-down;
+				};
+				l6 {
+					regulator-min-microvolt = <3000000>;
+					regulator-max-microvolt = <3600000>;
+					bias-pull-down;
+				};
+				l7 {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					bias-pull-down;
+				};
+				l8 {
+					regulator-min-microvolt = <2900000>;
+					regulator-max-microvolt = <3050000>;
+					bias-pull-down;
+				};
+				l9 {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					bias-pull-down;
+				};
+				l10 {
+					regulator-min-microvolt = <2600000>;
+					regulator-max-microvolt = <2600000>;
+					bias-pull-down;
+				};
+				l11 {
+					regulator-min-microvolt = <1500000>;
+					regulator-max-microvolt = <1500000>;
+					bias-pull-down;
+				};
+				l12 {
+					regulator-min-microvolt = <2900000>;
+					regulator-max-microvolt = <2900000>;
+					bias-pull-down;
+				};
+				l13 {
+					regulator-min-microvolt = <2050000>;
+					regulator-max-microvolt = <2050000>;
+					bias-pull-down;
+				};
+				l14 {
+					regulator-min-microvolt = <2850000>;
+					regulator-max-microvolt = <2850000>;
+				};
+				l15 {
+					regulator-min-microvolt = <2850000>;
+					regulator-max-microvolt = <2850000>;
+					bias-pull-down;
+				};
+				l16 {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					bias-pull-down;
+					regulator-always-on;
+				};
+				l17 {
+					// 1.5V according to schematic
+					regulator-min-microvolt = <2600000>;
+					regulator-max-microvolt = <2600000>;
+					bias-pull-down;
+				};
+				l18 {
+					regulator-min-microvolt = <2200000>;
+					regulator-max-microvolt = <2200000>;
+					bias-pull-down;
+				};
+				l19 {
+					regulator-min-microvolt = <2500000>;
+					regulator-max-microvolt = <2500000>;
+					bias-pull-down;
+				};
+				l20 {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					bias-pull-down;
+				};
+				l21 {
+					// 1.1 V according to schematic
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					bias-pull-down;
+					regulator-always-on;
+				};
+				l22 {
+					// 1.2 V according to schematic
+					regulator-min-microvolt = <1150000>;
+					regulator-max-microvolt = <1150000>;
+					bias-pull-down;
+				};
+				l23 {
+					// Unused
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					bias-pull-down;
+				};
+				l24 {
+					// Unused
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					bias-pull-down;
+				};
+				l25 {
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					bias-pull-down;
+				};
+
+				s0 {
+					// regulator-min-microvolt = <500000>;
+					// regulator-max-microvolt = <1325000>;
+					regulator-min-microvolt = <1100000>;
+					regulator-max-microvolt = <1100000>;
+					qcom,switch-mode-frequency = <1600000>;
+					bias-pull-down;
+				};
+				s1 {
+					// regulator-min-microvolt = <500000>;
+					// regulator-max-microvolt = <1250000>;
+					regulator-min-microvolt = <1100000>;
+					regulator-max-microvolt = <1100000>;
+					qcom,switch-mode-frequency = <1600000>;
+					bias-pull-down;
+				};
+				s2 {
+					// 1.3 V according to schematic
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1400000>;
+					qcom,switch-mode-frequency = <1600000>;
+					bias-pull-down;
+				};
+				s3 {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					qcom,switch-mode-frequency = <1600000>;
+					regulator-always-on;
+					bias-pull-down;
+				};
+				s4 {
+					regulator-min-microvolt = <2200000>;
+					regulator-max-microvolt = <2200000>;
+					qcom,switch-mode-frequency = <1600000>;
+					regulator-always-on;
+					bias-pull-down;
+				};
+
+				/* LVS0 and LVS1 are just switches */
+				lvs0 {
+					bias-pull-down;
+				};
+				lvs1 {
+					bias-pull-down;
+				};
+
+				ncp {
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					qcom,switch-mode-frequency = <1600000>;
+				};
+			};
+		};
+		amba {
+			/* Internal 3.69 GiB eMMC */
+			sdcc@12400000 {
+				status = "okay";
+				pinctrl-names = "default";
+				pinctrl-0 = <&dragon_sdcc1_pins>;
+				vmmc-supply = <&pm8901_l5>;
+				vqmmc-supply = <&pm8901_lvs0>;
+			};
+
+			/* External micro SD card, directly connected, pulled up to 2.85 V */
+			sdcc@12180000 {
+				status = "okay";
+				/* Enable SSBI GPIO 22 as input, use for card detect */
+				pinctrl-names = "default";
+				pinctrl-0 = <&dragon_sdcc3_pins>, <&dragon_sdcc3_gpios>;
+				cd-gpios = <&pm8058_gpio 22 GPIO_ACTIVE_LOW>;
+				wp-gpios = <&tlmm 110 GPIO_ACTIVE_HIGH>;
+				vmmc-supply = <&pm8058_l14>;
+			};
+
+			/*
+			 * Second external micro SD card, using two TXB104RGYR levelshifters
+			 * to lift from 1.8 V to 2.85 V
+			 */
+			sdcc@12200000 {
+				status = "okay";
+				/* Enable SSBI GPIO 26 as input, use for card detect */
+				pinctrl-names = "default";
+				pinctrl-0 = <&dragon_sdcc5_pins>, <&dragon_sdcc5_gpios>;
+				cd-gpios = <&pm8058_gpio 26 GPIO_ACTIVE_LOW>;
+				wp-gpios = <&tlmm 106 GPIO_ACTIVE_HIGH>;
+				vmmc-supply = <&pm8058_l14>;
+				vqmmc-supply = <&dragon_vio_txb>;
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/qcom-apq8064-arrow-db600c-pins.dtsi b/arch/arm/boot/dts/qcom-apq8064-arrow-sd-600eval-pins.dtsi
index a3efb9704fcd..a3efb9704fcd 100644
--- a/arch/arm/boot/dts/qcom-apq8064-arrow-db600c-pins.dtsi
+++ b/arch/arm/boot/dts/qcom-apq8064-arrow-sd-600eval-pins.dtsi
diff --git a/arch/arm/boot/dts/qcom-apq8064-arrow-db600c.dts b/arch/arm/boot/dts/qcom-apq8064-arrow-sd-600eval.dts
index e01b27ea7fba..39ae2bc8cb08 100644
--- a/arch/arm/boot/dts/qcom-apq8064-arrow-db600c.dts
+++ b/arch/arm/boot/dts/qcom-apq8064-arrow-sd-600eval.dts
@@ -1,10 +1,11 @@
 #include "qcom-apq8064-v2.0.dtsi"
-#include "qcom-apq8064-arrow-db600c-pins.dtsi"
+#include "qcom-apq8064-arrow-sd-600eval-pins.dtsi"
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/mfd/qcom-rpm.h>
 
 / {
-	model = "Arrow Electronics, APQ8064 DB600c";
-	compatible = "arrow,db600c", "qcom,apq8064";
+	model = "Arrow Electronics, APQ8064 SD_600eval";
+	compatible = "arrow,sd_600eval", "qcom,apq8064";
 
 	aliases {
 		serial0 = &gsbi7_serial;
@@ -82,7 +83,8 @@
 				s4 {
 					regulator-min-microvolt	= <1800000>;
 					regulator-max-microvolt	= <1800000>;
-					qcom,switch-mode-frequency = <3200000>;
+					qcom,switch-mode-frequency = <1600000>;
+					qcom,force-mode = <QCOM_RPM_FORCE_MODE_AUTO>;
 					bias-pull-down;
 					regulator-always-on;
 				};
diff --git a/arch/arm/boot/dts/qcom-apq8064-asus-nexus7-flo.dts b/arch/arm/boot/dts/qcom-apq8064-asus-nexus7-flo.dts
index 32fedfa149d0..7b05f072bfc2 100644
--- a/arch/arm/boot/dts/qcom-apq8064-asus-nexus7-flo.dts
+++ b/arch/arm/boot/dts/qcom-apq8064-asus-nexus7-flo.dts
@@ -29,12 +29,6 @@
 
 	gpio-keys {
 		compatible = "gpio-keys";
-		power {
-			label = "Power";
-			gpios = <&tlmm_pinmux 26 GPIO_ACTIVE_LOW>;
-			linux,code = <KEY_POWER>;
-			gpio-key,wakeup;
-		};
 		volume_up {
 			label = "Volume Up";
 			gpios = <&pm8921_gpio 4 GPIO_ACTIVE_HIGH>;
diff --git a/arch/arm/boot/dts/qcom-apq8064-pins.dtsi b/arch/arm/boot/dts/qcom-apq8064-pins.dtsi
index 4102a98f475b..6b801e7e57a2 100644
--- a/arch/arm/boot/dts/qcom-apq8064-pins.dtsi
+++ b/arch/arm/boot/dts/qcom-apq8064-pins.dtsi
@@ -7,6 +7,46 @@
 		};
 	};
 
+	sdcc1_pins: sdcc1-pin-active {
+		clk {
+			pins = "sdc1_clk";
+			drive-strengh = <16>;
+			bias-disable;
+		};
+
+		cmd {
+			pins = "sdc1_cmd";
+			drive-strengh = <10>;
+			bias-pull-up;
+		};
+
+		data {
+			pins = "sdc1_data";
+			drive-strengh = <10>;
+			bias-pull-up;
+		};
+	};
+
+	sdcc3_pins: sdcc3-pin-active {
+		clk {
+			pins = "sdc3_clk";
+			drive-strengh = <8>;
+			bias-disable;
+		};
+
+		cmd {
+			pins = "sdc3_cmd";
+			drive-strengh = <8>;
+			bias-pull-up;
+		};
+
+		data {
+			pins = "sdc3_data";
+			drive-strengh = <8>;
+			bias-pull-up;
+		};
+	};
+
 	ps_hold: ps_hold {
 		mux {
 			pins = "gpio78";
diff --git a/arch/arm/boot/dts/qcom-apq8064-sony-xperia-yuga.dts b/arch/arm/boot/dts/qcom-apq8064-sony-xperia-yuga.dts
index 06b3c76c3e41..ebd675ca94b4 100644
--- a/arch/arm/boot/dts/qcom-apq8064-sony-xperia-yuga.dts
+++ b/arch/arm/boot/dts/qcom-apq8064-sony-xperia-yuga.dts
@@ -70,45 +70,6 @@
 				};
 			};
 
-			sdcc1_pin_a: sdcc1-pin-active {
-				clk {
-					pins = "sdc1_clk";
-					drive-strengh = <16>;
-					bias-disable;
-				};
-
-				cmd {
-					pins = "sdc1_cmd";
-					drive-strengh = <10>;
-					bias-pull-up;
-				};
-
-				data {
-					pins = "sdc1_data";
-					drive-strengh = <10>;
-					bias-pull-up;
-				};
-			};
-
-			sdcc3_pin_a: sdcc3-pin-active {
-				clk {
-					pins = "sdc3_clk";
-					drive-strengh = <8>;
-					bias-disable;
-				};
-
-				cmd {
-					pins = "sdc3_cmd";
-					drive-strengh = <8>;
-					bias-pull-up;
-				};
-
-				data {
-					pins = "sdc3_data";
-					drive-strengh = <8>;
-					bias-pull-up;
-				};
-			};
 
 			sdcc3_cd_pin_a: sdcc3-cd-pin-active {
 				pins = "gpio26";
@@ -417,9 +378,6 @@
 
 				vmmc-supply = <&pm8921_l5>;
 				vqmmc-supply = <&pm8921_s4>;
-
-				pinctrl-names = "default";
-				pinctrl-0 = <&sdcc1_pin_a>;
 			};
 
 			sdcc3: sdcc@12180000 {
@@ -429,7 +387,7 @@
 				cd-gpios = <&tlmm_pinmux 26 GPIO_ACTIVE_LOW>;
 
 				pinctrl-names = "default";
-				pinctrl-0 = <&sdcc3_pin_a>, <&sdcc3_cd_pin_a>;
+				pinctrl-0 = <&sdcc3_pins>, <&sdcc3_cd_pin_a>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi
index df96ccdc9bb4..74a9b6c394f5 100644
--- a/arch/arm/boot/dts/qcom-apq8064.dtsi
+++ b/arch/arm/boot/dts/qcom-apq8064.dtsi
@@ -177,7 +177,7 @@
 
 		apps_smsm: apps@0 {
 			reg = <0>;
-			#qcom,state-cells = <1>;
+			#qcom,smem-state-cells = <1>;
 		};
 
 		modem_smsm: modem@1 {
@@ -213,6 +213,12 @@
 		};
 	};
 
+	firmware {
+		scm {
+			compatible = "qcom,scm-apq8064";
+		};
+	};
+
 	soc: soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -247,7 +253,8 @@
 		};
 
 		timer@200a000 {
-			compatible = "qcom,kpss-timer", "qcom,msm-timer";
+			compatible = "qcom,kpss-timer",
+				     "qcom,kpss-wdt-apq8064", "qcom,msm-timer";
 			interrupts = <1 1 0x301>,
 				     <1 2 0x301>,
 				     <1 3 0x301>;
@@ -853,6 +860,8 @@
 			sdcc1: sdcc@12400000 {
 				status		= "disabled";
 				compatible	= "arm,pl18x", "arm,primecell";
+				pinctrl-names	= "default";
+				pinctrl-0	= <&sdcc1_pins>;
 				arm,primecell-periphid = <0x00051180>;
 				reg		= <0x12400000 0x2000>;
 				interrupts	= <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/qcom-apq8074-dragonboard.dts b/arch/arm/boot/dts/qcom-apq8074-dragonboard.dts
index c0e205315042..ad51df27dfb7 100644
--- a/arch/arm/boot/dts/qcom-apq8074-dragonboard.dts
+++ b/arch/arm/boot/dts/qcom-apq8074-dragonboard.dts
@@ -25,11 +25,23 @@
 			bus-width = <8>;
 			non-removable;
 			status = "ok";
+
+			vmmc-supply = <&pm8941_l20>;
+			vqmmc-supply = <&pm8941_s3>;
+
+			pinctrl-names = "default";
+			pinctrl-0 = <&sdhc1_pin_a>;
 		};
 
 		sdhci@f98a4900 {
 			cd-gpios = <&msmgpio 62 0x1>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&sdhc2_pin_a>, <&sdhc2_cd_pin_a>;
 			bus-width = <4>;
+			status = "ok";
+
+			vmmc-supply = <&pm8941_l21>;
+			vqmmc-supply = <&pm8941_l13>;
 		};
 
 
@@ -59,6 +71,42 @@
 					function = "blsp_spi8";
 				};
 			};
+
+			sdhc1_pin_a: sdhc1-pin-active {
+				clk {
+					pins = "sdc1_clk";
+					drive-strength = <16>;
+					bias-disable;
+				};
+
+				cmd-data {
+					pins = "sdc1_cmd", "sdc1_data";
+					drive-strength = <10>;
+					bias-pull-up;
+				};
+			};
+
+			sdhc2_cd_pin_a: sdhc2-cd-pin-active {
+				pins = "gpio62";
+				function = "gpio";
+
+				drive-strength = <2>;
+				bias-disable;
+			};
+
+			sdhc2_pin_a: sdhc2-pin-active {
+				clk {
+					pins = "sdc2_clk";
+					drive-strength = <10>;
+					bias-disable;
+				};
+
+				cmd-data {
+					pins = "sdc2_cmd", "sdc2_data";
+					drive-strength = <6>;
+					bias-pull-up;
+				};
+			};
 		};
 
 		i2c@f9967000 {
@@ -75,4 +123,203 @@
 			};
 		};
 	};
+
+	smd {
+		rpm {
+			rpm_requests {
+				pm8841-regulators {
+					s1 {
+						regulator-min-microvolt = <675000>;
+						regulator-max-microvolt = <1050000>;
+					};
+
+					s2 {
+						regulator-min-microvolt = <500000>;
+						regulator-max-microvolt = <1050000>;
+					};
+
+					s3 {
+						regulator-min-microvolt = <500000>;
+						regulator-max-microvolt = <1050000>;
+					};
+
+					s4 {
+						regulator-min-microvolt = <500000>;
+						regulator-max-microvolt = <1050000>;
+					};
+				};
+
+				pm8941-regulators {
+					vdd_l1_l3-supply = <&pm8941_s1>;
+					vdd_l2_lvs1_2_3-supply = <&pm8941_s3>;
+					vdd_l4_l11-supply = <&pm8941_s1>;
+					vdd_l5_l7-supply = <&pm8941_s2>;
+					vdd_l6_l12_l14_l15-supply = <&pm8941_s2>;
+					vin_5vs-supply = <&pm8941_5v>;
+
+					s1 {
+						regulator-min-microvolt = <1300000>;
+						regulator-max-microvolt = <1300000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					s2 {
+						regulator-min-microvolt = <2150000>;
+						regulator-max-microvolt = <2150000>;
+						regulator-boot-on;
+					};
+
+					s3 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					l1 {
+						regulator-min-microvolt = <1225000>;
+						regulator-max-microvolt = <1225000>;
+
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					l2 {
+						regulator-min-microvolt = <1200000>;
+						regulator-max-microvolt = <1200000>;
+					};
+
+					l3 {
+						regulator-min-microvolt = <1225000>;
+						regulator-max-microvolt = <1225000>;
+					};
+
+					l4 {
+						regulator-min-microvolt = <1225000>;
+						regulator-max-microvolt = <1225000>;
+					};
+
+					l5 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+					};
+
+					l6 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+
+						regulator-boot-on;
+					};
+
+					l7 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+
+						regulator-boot-on;
+					};
+
+					l8 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+					};
+
+					l9 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <2950000>;
+					};
+
+					l10 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+						regulator-always-on;
+					};
+
+					l11 {
+						regulator-min-microvolt = <1300000>;
+						regulator-max-microvolt = <1300000>;
+					};
+
+					l12 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+
+						regulator-always-on;
+						regulator-boot-on;
+					};
+
+					l13 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <2950000>;
+
+						regulator-boot-on;
+					};
+
+					l14 {
+						regulator-min-microvolt = <1800000>;
+						regulator-max-microvolt = <1800000>;
+					};
+
+					l15 {
+						regulator-min-microvolt = <2050000>;
+						regulator-max-microvolt = <2050000>;
+					};
+
+					l16 {
+						regulator-min-microvolt = <2700000>;
+						regulator-max-microvolt = <2700000>;
+					};
+
+					l17 {
+						regulator-min-microvolt = <2700000>;
+						regulator-max-microvolt = <2700000>;
+					};
+
+					l18 {
+						regulator-min-microvolt = <2850000>;
+						regulator-max-microvolt = <2850000>;
+					};
+
+					l19 {
+						regulator-min-microvolt = <3300000>;
+						regulator-max-microvolt = <3300000>;
+						regulator-always-on;
+					};
+
+					l20 {
+						regulator-min-microvolt = <2950000>;
+						regulator-max-microvolt = <2950000>;
+
+						regulator-allow-set-load;
+						regulator-boot-on;
+						regulator-system-load = <200000>;
+					};
+
+					l21 {
+						regulator-min-microvolt = <2950000>;
+						regulator-max-microvolt = <2950000>;
+
+						regulator-boot-on;
+					};
+
+					l22 {
+						regulator-min-microvolt = <3000000>;
+						regulator-max-microvolt = <3000000>;
+					};
+
+					l23 {
+						regulator-min-microvolt = <3000000>;
+						regulator-max-microvolt = <3000000>;
+					};
+
+					l24 {
+						regulator-min-microvolt = <3075000>;
+						regulator-max-microvolt = <3075000>;
+
+						regulator-boot-on;
+					};
+				};
+			};
+		};
+	};
 };
diff --git a/arch/arm/boot/dts/qcom-apq8084.dtsi b/arch/arm/boot/dts/qcom-apq8084.dtsi
index a33a09f6821e..7c2df062a025 100644
--- a/arch/arm/boot/dts/qcom-apq8084.dtsi
+++ b/arch/arm/boot/dts/qcom-apq8084.dtsi
@@ -86,6 +86,14 @@
 		};
 	};
 
+	firmware {
+		scm {
+			compatible = "qcom,scm";
+			clocks = <&gcc GCC_CE1_CLK> , <&gcc GCC_CE1_AXI_CLK>, <&gcc GCC_CE1_AHB_CLK>;
+			clock-names = "core", "bus", "iface";
+		};
+	};
+
 	cpu-pmu {
 		compatible = "qcom,krait-pmu";
 		interrupts = <1 7 0xf04>;
diff --git a/arch/arm/boot/dts/qcom-ipq4019.dtsi b/arch/arm/boot/dts/qcom-ipq4019.dtsi
index 5c08d19066c2..b7a24af8f47b 100644
--- a/arch/arm/boot/dts/qcom-ipq4019.dtsi
+++ b/arch/arm/boot/dts/qcom-ipq4019.dtsi
@@ -84,6 +84,12 @@
 		};
 	};
 
+	pmu {
+		compatible = "arm,cortex-a7-pmu";
+		interrupts = <GIC_PPI 7 (GIC_CPU_MASK_SIMPLE(4) |
+					 IRQ_TYPE_LEVEL_HIGH)>;
+	};
+
 	clocks {
 		sleep_clk: sleep_clk {
 			compatible = "fixed-clock";
@@ -252,7 +258,7 @@
 		};
 
 		watchdog@b017000 {
-			compatible = "qcom,kpss-standalone";
+			compatible = "qcom,kpss-wdt", "qcom,kpss-wdt-ipq4019";
 			reg = <0xb017000 0x40>;
 			clocks = <&sleep_clk>;
 			timeout-sec = <10>;
diff --git a/arch/arm/boot/dts/qcom-ipq8064.dtsi b/arch/arm/boot/dts/qcom-ipq8064.dtsi
index 2601a907947b..2e375576ffd0 100644
--- a/arch/arm/boot/dts/qcom-ipq8064.dtsi
+++ b/arch/arm/boot/dts/qcom-ipq8064.dtsi
@@ -122,7 +122,8 @@
 		};
 
 		timer@200a000 {
-			compatible = "qcom,kpss-timer", "qcom,msm-timer";
+			compatible = "qcom,kpss-timer",
+				     "qcom,kpss-wdt-ipq8064", "qcom,msm-timer";
 			interrupts = <1 1 0x301>,
 				     <1 2 0x301>,
 				     <1 3 0x301>,
diff --git a/arch/arm/boot/dts/qcom-msm8660-surf.dts b/arch/arm/boot/dts/qcom-msm8660-surf.dts
index b17f379e8c2a..23de764558ab 100644
--- a/arch/arm/boot/dts/qcom-msm8660-surf.dts
+++ b/arch/arm/boot/dts/qcom-msm8660-surf.dts
@@ -23,15 +23,26 @@
 			};
 		};
 
+		/* Temporary fixed regulator */
+		vsdcc_fixed: vsdcc-regulator {
+			compatible = "regulator-fixed";
+			regulator-name = "SDCC Power";
+			regulator-min-microvolt = <2700000>;
+			regulator-max-microvolt = <2700000>;
+			regulator-always-on;
+		};
+
 		amba {
 			/* eMMC */
 			sdcc1: sdcc@12400000 {
 				status = "okay";
+				vmmc-supply = <&vsdcc_fixed>;
 			};
 
 			/* External micro SD card */
 			sdcc3: sdcc@12180000 {
 				status = "okay";
+				vmmc-supply = <&vsdcc_fixed>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/qcom-msm8660.dtsi b/arch/arm/boot/dts/qcom-msm8660.dtsi
index cd214030b84a..acbe71febe13 100644
--- a/arch/arm/boot/dts/qcom-msm8660.dtsi
+++ b/arch/arm/boot/dts/qcom-msm8660.dtsi
@@ -122,11 +122,22 @@
 				compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 				reg = <0x19c40000 0x1000>,
 				      <0x19c00000 0x1000>;
-				interrupts = <0 195 0x0>;
+				interrupts = <0 195 IRQ_TYPE_NONE>;
 				clocks = <&gcc GSBI12_UART_CLK>, <&gcc GSBI12_H_CLK>;
 				clock-names = "core", "iface";
 				status = "disabled";
 			};
+
+			gsbi12_i2c: i2c@19c80000 {
+				compatible = "qcom,i2c-qup-v1.1.1";
+				reg = <0x19c80000 0x1000>;
+				interrupts = <0 196 IRQ_TYPE_NONE>;
+				clocks = <&gcc GSBI12_QUP_CLK>, <&gcc GSBI12_H_CLK>;
+				clock-names = "core", "iface";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
 		};
 
 		qcom,ssbi@500000 {
@@ -143,6 +154,44 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 
+				pm8058_gpio: gpio@150 {
+					compatible = "qcom,pm8058-gpio",
+						     "qcom,ssbi-gpio";
+					reg = <0x150>;
+					interrupt-parent = <&pmicintc>;
+					interrupts = <192 1>, <193 1>, <194 1>,
+						     <195 1>, <196 1>, <197 1>,
+						     <198 1>, <199 1>, <200 1>,
+						     <201 1>, <202 1>, <203 1>,
+						     <204 1>, <205 1>, <206 1>,
+						     <207 1>, <208 1>, <209 1>,
+						     <210 1>, <211 1>, <212 1>,
+						     <213 1>, <214 1>, <215 1>,
+						     <216 1>, <217 1>, <218 1>,
+						     <219 1>, <220 1>, <221 1>,
+						     <222 1>, <223 1>, <224 1>,
+						     <225 1>, <226 1>, <227 1>,
+						     <228 1>, <229 1>, <230 1>,
+						     <231 1>, <232 1>, <233 1>,
+						     <234 1>, <235 1>;
+					gpio-controller;
+					#gpio-cells = <2>;
+
+				};
+
+				pm8058_mpps: mpps@50 {
+					compatible = "qcom,pm8058-mpp",
+						     "qcom,ssbi-mpp";
+					reg = <0x50>;
+					gpio-controller;
+					#gpio-cells = <2>;
+					interrupt-parent = <&pmicintc>;
+					interrupts =
+					<128 1>, <129 1>, <130 1>, <131 1>,
+					<132 1>, <133 1>, <134 1>, <135 1>,
+					<136 1>, <137 1>, <138 1>, <139 1>;
+				};
+
 				pwrkey@1c {
 					compatible = "qcom,pm8058-pwrkey";
 					reg = <0x1c>;
@@ -162,11 +211,11 @@
 					row-hold = <91500>;
 				};
 
-				rtc@11d {
+				rtc@1e8 {
 					compatible = "qcom,pm8058-rtc";
+					reg = <0x1e8>;
 					interrupt-parent = <&pmicintc>;
 					interrupts = <39 1>;
-					reg = <0x11d>;
 					allow-set-time;
 				};
 
@@ -177,13 +226,93 @@
 			};
 		};
 
-		/* Temporary fixed regulator */
-		vsdcc_fixed: vsdcc-regulator {
-			compatible = "regulator-fixed";
-			regulator-name = "SDCC Power";
-			regulator-min-microvolt = <2700000>;
-			regulator-max-microvolt = <2700000>;
-			regulator-always-on;
+		l2cc: clock-controller@2082000 {
+			compatible	= "syscon";
+			reg		= <0x02082000 0x1000>;
+		};
+
+		rpm: rpm@104000 {
+			compatible	= "qcom,rpm-msm8660";
+			reg		= <0x00104000 0x1000>;
+			qcom,ipc	= <&l2cc 0x8 2>;
+
+			interrupts	= <GIC_SPI 19 IRQ_TYPE_EDGE_RISING>,
+					  <GIC_SPI 21 IRQ_TYPE_EDGE_RISING>,
+					  <GIC_SPI 22 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names	= "ack", "err", "wakeup";
+			clocks = <&gcc RPM_MSG_RAM_H_CLK>;
+			clock-names = "ram";
+
+			rpmcc: clock-controller {
+				compatible	= "qcom,rpmcc-apq8660", "qcom,rpmcc";
+				#clock-cells = <1>;
+			};
+
+			pm8901-regulators {
+				compatible = "qcom,rpm-pm8901-regulators";
+
+				pm8901_l0: l0 {};
+				pm8901_l1: l1 {};
+				pm8901_l2: l2 {};
+				pm8901_l3: l3 {};
+				pm8901_l4: l4 {};
+				pm8901_l5: l5 {};
+				pm8901_l6: l6 {};
+
+				/* S0 and S1 Handled as SAW regulators by SPM */
+				pm8901_s2: s2 {};
+				pm8901_s3: s3 {};
+				pm8901_s4: s4 {};
+
+				pm8901_lvs0: lvs0 {};
+				pm8901_lvs1: lvs1 {};
+				pm8901_lvs2: lvs2 {};
+				pm8901_lvs3: lvs3 {};
+
+				pm8901_mvs: mvs {};
+			};
+
+			pm8058-regulators {
+				compatible = "qcom,rpm-pm8058-regulators";
+
+				pm8058_l0: l0 {};
+				pm8058_l1: l1 {};
+				pm8058_l2: l2 {};
+				pm8058_l3: l3 {};
+				pm8058_l4: l4 {};
+				pm8058_l5: l5 {};
+				pm8058_l6: l6 {};
+				pm8058_l7: l7 {};
+				pm8058_l8: l8 {};
+				pm8058_l9: l9 {};
+				pm8058_l10: l10 {};
+				pm8058_l11: l11 {};
+				pm8058_l12: l12 {};
+				pm8058_l13: l13 {};
+				pm8058_l14: l14 {};
+				pm8058_l15: l15 {};
+				pm8058_l16: l16 {};
+				pm8058_l17: l17 {};
+				pm8058_l18: l18 {};
+				pm8058_l19: l19 {};
+				pm8058_l20: l20 {};
+				pm8058_l21: l21 {};
+				pm8058_l22: l22 {};
+				pm8058_l23: l23 {};
+				pm8058_l24: l24 {};
+				pm8058_l25: l25 {};
+
+				pm8058_s0: s0 {};
+				pm8058_s1: s1 {};
+				pm8058_s2: s2 {};
+				pm8058_s3: s3 {};
+				pm8058_s4: s4 {};
+
+				pm8058_lvs0: lvs0 {};
+				pm8058_lvs1: lvs1 {};
+
+				pm8058_ncp: ncp {};
+			};
 		};
 
 		amba {
@@ -205,7 +334,6 @@
 				non-removable;
 				cap-sd-highspeed;
 				cap-mmc-highspeed;
-				vmmc-supply = <&vsdcc_fixed>;
 			};
 
 			sdcc3: sdcc@12180000 {
@@ -222,7 +350,21 @@
 				cap-mmc-highspeed;
 				max-frequency	= <48000000>;
 				no-1-8-v;
-				vmmc-supply = <&vsdcc_fixed>;
+			};
+
+			sdcc5: sdcc@12200000 {
+				compatible	= "arm,pl18x", "arm,primecell";
+				arm,primecell-periphid = <0x00051180>;
+				status		= "disabled";
+				reg		= <0x12200000 0x8000>;
+				interrupts	= <GIC_SPI 188 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names	= "cmd_irq";
+				clocks		= <&gcc SDC5_CLK>, <&gcc SDC5_H_CLK>;
+				clock-names	= "mclk", "apb_pclk";
+				bus-width	= <4>;
+				cap-sd-highspeed;
+				cap-mmc-highspeed;
+				max-frequency	= <48000000>;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/qcom-msm8960.dtsi b/arch/arm/boot/dts/qcom-msm8960.dtsi
index da05e28a81a7..288f56e0ccf5 100644
--- a/arch/arm/boot/dts/qcom-msm8960.dtsi
+++ b/arch/arm/boot/dts/qcom-msm8960.dtsi
@@ -87,7 +87,8 @@
 		};
 
 		timer@200a000 {
-			compatible = "qcom,kpss-timer", "qcom,msm-timer";
+			compatible = "qcom,kpss-timer",
+				     "qcom,kpss-wdt-msm8960", "qcom,msm-timer";
 			interrupts = <1 1 0x301>,
 				     <1 2 0x301>,
 				     <1 3 0x301>;
diff --git a/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts b/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts
index a0398b69f4f2..3fb4dada6b0d 100644
--- a/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts
+++ b/arch/arm/boot/dts/qcom-msm8974-sony-xperia-honami.dts
@@ -367,6 +367,10 @@
 		};
 
 	};
+
+	dma-controller@f9944000 {
+		qcom,controlled-remotely;
+	};
 };
 
 &spmi_bus {
diff --git a/arch/arm/boot/dts/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom-msm8974.dtsi
index 6f164266a010..561d4d136762 100644
--- a/arch/arm/boot/dts/qcom-msm8974.dtsi
+++ b/arch/arm/boot/dts/qcom-msm8974.dtsi
@@ -1,6 +1,6 @@
 /dts-v1/;
 
-#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/clock/qcom,gcc-msm8974.h>
 #include "skeleton.dtsi"
 
@@ -182,7 +182,7 @@
 
 		modem_smp2p_out: master-kernel {
 			qcom,entry-name = "master-kernel";
-			#qcom,state-cells = <1>;
+			#qcom,smem-state-cells = <1>;
 		};
 
 		modem_smp2p_in: slave-kernel {
@@ -208,7 +208,7 @@
 		wcnss_smp2p_out: master-kernel {
 			qcom,entry-name = "master-kernel";
 
-			#qcom,state-cells = <1>;
+			#qcom,smem-state-cells = <1>;
 		};
 
 		wcnss_smp2p_in: slave-kernel {
@@ -232,7 +232,7 @@
 		apps_smsm: apps@0 {
 			reg = <0>;
 
-			#qcom,state-cells = <1>;
+			#qcom,smem-state-cells = <1>;
 		};
 
 		modem_smsm: modem@1 {
@@ -260,6 +260,14 @@
 		};
 	};
 
+	firmware {
+		scm {
+			compatible = "qcom,scm";
+			clocks = <&gcc GCC_CE1_CLK>, <&gcc GCC_CE1_AXI_CLK>, <&gcc GCC_CE1_AHB_CLK>;
+			clock-names = "core", "bus", "iface";
+		};
+	};
+
 	soc: soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -501,6 +509,8 @@
 			clock-names = "core", "iface";
 			#address-cells = <1>;
 			#size-cells = <0>;
+			dmas = <&blsp2_dma 20>, <&blsp2_dma 21>;
+			dma-names = "tx", "rx";
 		};
 
 		spmi_bus: spmi@fc4cf000 {
@@ -518,6 +528,16 @@
 			interrupt-controller;
 			#interrupt-cells = <4>;
 		};
+
+		blsp2_dma: dma-controller@f9944000 {
+			compatible = "qcom,bam-v1.4.0";
+			reg = <0xf9944000 0x19000>;
+			interrupts = <GIC_SPI 239 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP2_AHB_CLK>;
+			clock-names = "bam_clk";
+			#dma-cells = <1>;
+			qcom,ee = <0>;
+		};
 	};
 
 	smd {
diff --git a/arch/arm/boot/dts/qcom-pma8084.dtsi b/arch/arm/boot/dts/qcom-pma8084.dtsi
index 4e9bd3f88473..82d258094156 100644
--- a/arch/arm/boot/dts/qcom-pma8084.dtsi
+++ b/arch/arm/boot/dts/qcom-pma8084.dtsi
@@ -12,15 +12,23 @@
 
 		rtc@6000 {
 			compatible = "qcom,pm8941-rtc";
-			reg = <0x6000 0x100>,
-			      <0x6100 0x100>;
+			reg = <0x6000>,
+			      <0x6100>;
 			reg-names = "rtc", "alarm";
 			interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>;
 		};
 
+		pwrkey@800 {
+			compatible = "qcom,pm8941-pwrkey";
+			reg = <0x800>;
+			interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>;
+			debounce = <15625>;
+			bias-pull-up;
+		};
+
 		pma8084_gpios: gpios@c000 {
 			compatible = "qcom,pma8084-gpio", "qcom,spmi-gpio";
-			reg = <0xc000 0x1600>;
+			reg = <0xc000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupts = <0 0xc0 0 IRQ_TYPE_NONE>,
@@ -49,7 +57,7 @@
 
 		pma8084_mpps: mpps@a000 {
 			compatible = "qcom,pma8084-mpp", "qcom,spmi-mpp";
-			reg = <0xa000 0x800>;
+			reg = <0xa000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupts = <0 0xa0 0 IRQ_TYPE_NONE>,
@@ -64,7 +72,7 @@
 
 		pma8084_temp: temp-alarm@2400 {
 			compatible = "qcom,spmi-temp-alarm";
-			reg = <0x2400 0x100>;
+			reg = <0x2400>;
 			interrupts = <0 0x24 0 IRQ_TYPE_EDGE_RISING>;
 			#thermal-sensor-cells = <0>;
 			io-channels = <&pma8084_vadc VADC_DIE_TEMP>;
@@ -73,7 +81,7 @@
 
 		pma8084_vadc: vadc@3100 {
 			compatible = "qcom,spmi-vadc";
-			reg = <0x3100 0x100>;
+			reg = <0x3100>;
 			interrupts = <0x0 0x31 0x0 IRQ_TYPE_EDGE_RISING>;
 			#address-cells = <1>;
 			#size-cells = <0>;
diff --git a/arch/arm/boot/dts/r7s72100-genmai.dts b/arch/arm/boot/dts/r7s72100-genmai.dts
index a9da7a89fc4b..118a8e2b86bd 100644
--- a/arch/arm/boot/dts/r7s72100-genmai.dts
+++ b/arch/arm/boot/dts/r7s72100-genmai.dts
@@ -17,15 +17,15 @@
 	compatible = "renesas,genmai", "renesas,r7s72100";
 
 	aliases {
-		serial2 = &scif2;
+		serial0 = &scif2;
 	};
 
 	chosen {
 		bootargs = "ignore_loglevel rw root=/dev/nfs ip=dhcp";
-		stdout-path = &scif2;
+		stdout-path = "serial0:115200n8";
 	};
 
-	memory {
+	memory@8000000 {
 		device_type = "memory";
 		reg = <0x08000000 0x08000000>;
 	};
diff --git a/arch/arm/boot/dts/r8a73a4-ape6evm.dts b/arch/arm/boot/dts/r8a73a4-ape6evm.dts
index 93ace33e3e36..ec7c86e06538 100644
--- a/arch/arm/boot/dts/r8a73a4-ape6evm.dts
+++ b/arch/arm/boot/dts/r8a73a4-ape6evm.dts
@@ -36,7 +36,7 @@
 		reg = <2 0x00000000 0 0x40000000>;
 	};
 
-	vcc_mmc0: regulator@0 {
+	vcc_mmc0: regulator-mmc0 {
 		compatible = "regulator-fixed";
 		regulator-name = "MMC0 Vcc";
 		regulator-min-microvolt = <2800000>;
@@ -44,7 +44,7 @@
 		regulator-always-on;
 	};
 
-	vcc_sdhi0: regulator@1 {
+	vcc_sdhi0: regulator-sdhi0 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI0 Vcc";
@@ -56,7 +56,7 @@
 	};
 
 	/* Common 1.8V and 3.3V rails, used by several devices on APE6EVM */
-	ape6evm_fixed_1v8: regulator@2 {
+	ape6evm_fixed_1v8: regulator-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "1V8";
 		regulator-min-microvolt = <1800000>;
@@ -64,7 +64,7 @@
 		regulator-always-on;
 	};
 
-	ape6evm_fixed_3v3: regulator@3 {
+	ape6evm_fixed_3v3: regulator-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "3V3";
 		regulator-min-microvolt = <3300000>;
@@ -188,12 +188,12 @@
 };
 
 &pfc {
-	scifa0_pins: serial0 {
+	scifa0_pins: scifa0 {
 		groups = "scifa0_data";
 		function = "scifa0";
 	};
 
-	mmc0_pins: mmc {
+	mmc0_pins: mmc0 {
 		groups = "mmc0_data8", "mmc0_ctrl";
 		function = "mmc0";
 	};
diff --git a/arch/arm/boot/dts/r8a73a4.dtsi b/arch/arm/boot/dts/r8a73a4.dtsi
index 6954912a3753..ca8672778fe0 100644
--- a/arch/arm/boot/dts/r8a73a4.dtsi
+++ b/arch/arm/boot/dts/r8a73a4.dtsi
@@ -31,6 +31,24 @@
 			power-domains = <&pd_a2sl>;
 			next-level-cache = <&L2_CA15>;
 		};
+
+		L2_CA15: cache-controller@0 {
+			compatible = "cache";
+			reg = <0>;
+			clocks = <&cpg_clocks R8A73A4_CLK_Z>;
+			power-domains = <&pd_a3sm>;
+			cache-unified;
+			cache-level = <2>;
+		};
+
+		L2_CA7: cache-controller@100 {
+			compatible = "cache";
+			reg = <0x100>;
+			clocks = <&cpg_clocks R8A73A4_CLK_Z2>;
+			power-domains = <&pd_a3km>;
+			cache-unified;
+			cache-level = <2>;
+		};
 	};
 
 	ptm {
@@ -46,22 +64,6 @@
 			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
 	};
 
-	L2_CA15: cache-controller@0 {
-		compatible = "cache";
-		clocks = <&cpg_clocks R8A73A4_CLK_Z>;
-		power-domains = <&pd_a3sm>;
-		cache-unified;
-		cache-level = <2>;
-	};
-
-	L2_CA7: cache-controller@1 {
-		compatible = "cache";
-		clocks = <&cpg_clocks R8A73A4_CLK_Z2>;
-		power-domains = <&pd_a3km>;
-		cache-unified;
-		cache-level = <2>;
-	};
-
 	dbsc1: memory-controller@e6790000 {
 		compatible = "renesas,dbsc-r8a73a4";
 		reg = <0 0xe6790000 0 0x10000>;
diff --git a/arch/arm/boot/dts/r8a7740-armadillo800eva.dts b/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
index 2c82dab2b6f4..7885075428bb 100644
--- a/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
+++ b/arch/arm/boot/dts/r8a7740-armadillo800eva.dts
@@ -20,20 +20,20 @@
 	compatible = "renesas,armadillo800eva", "renesas,r8a7740";
 
 	aliases {
-		serial1 = &scifa1;
+		serial0 = &scifa1;
 	};
 
 	chosen {
-		bootargs = "console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp rw";
-		stdout-path = &scifa1;
+		bootargs = "earlyprintk ignore_loglevel root=/dev/nfs ip=dhcp rw";
+		stdout-path = "serial0:115200n8";
 	};
 
-	memory {
+	memory@40000000 {
 		device_type = "memory";
 		reg = <0x40000000 0x20000000>;
 	};
 
-	reg_3p3v: regulator@0 {
+	reg_3p3v: regulator-3p3v {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-3.3V";
 		regulator-min-microvolt = <3300000>;
@@ -42,7 +42,7 @@
 		regulator-boot-on;
 	};
 
-	vcc_sdhi0: regulator@1 {
+	vcc_sdhi0: regulator-vcc-sdhi0 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI0 Vcc";
@@ -53,7 +53,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi0: regulator@2 {
+	vccq_sdhi0: regulator-vccq-sdhi0 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI0 VccQ";
@@ -69,7 +69,7 @@
 		enable-active-high;
 	};
 
-	reg_5p0v: regulator@3 {
+	reg_5p0v: regulator-5p0v {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-5.0V";
 		regulator-min-microvolt = <5000000>;
@@ -127,7 +127,7 @@
 		};
 	};
 
-	i2c2: i2c@2 {
+	i2c2: i2c-2 {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		compatible = "i2c-gpio";
@@ -232,7 +232,7 @@
 		function = "gether";
 	};
 
-	scifa1_pins: serial1 {
+	scifa1_pins: scifa1 {
 		groups = "scifa1_data";
 		function = "scifa1";
 	};
diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi
index 39b2f88ad151..159e04eb1b9e 100644
--- a/arch/arm/boot/dts/r8a7740.dtsi
+++ b/arch/arm/boot/dts/r8a7740.dtsi
@@ -39,7 +39,7 @@
 		      <0xc2000000 0x1000>;
 	};
 
-	L2: cache-controller {
+	L2: cache-controller@f0100000 {
 		compatible = "arm,pl310-cache";
 		reg = <0xf0100000 0x1000>;
 		interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/r8a7778-bockw.dts b/arch/arm/boot/dts/r8a7778-bockw.dts
index e0dab1464648..211d239d9041 100644
--- a/arch/arm/boot/dts/r8a7778-bockw.dts
+++ b/arch/arm/boot/dts/r8a7778-bockw.dts
@@ -32,12 +32,12 @@
 		stdout-path = "serial0:115200n8";
 	};
 
-	memory {
+	memory@60000000 {
 		device_type = "memory";
 		reg = <0x60000000 0x10000000>;
 	};
 
-	fixedregulator3v3: fixedregulator@0 {
+	fixedregulator3v3: regulator-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-3.3V";
 		regulator-min-microvolt = <3300000>;
@@ -129,7 +129,7 @@
 	pinctrl-0 = <&scif_clk_pins>;
 	pinctrl-names = "default";
 
-	scif0_pins: serial0 {
+	scif0_pins: scif0 {
 		groups = "scif0_data_a", "scif0_ctrl";
 		function = "scif0";
 	};
@@ -223,6 +223,7 @@
 	pinctrl-0 = <&scif0_pins>;
 	pinctrl-names = "default";
 
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/r8a7778.dtsi b/arch/arm/boot/dts/r8a7778.dtsi
index fe787b4751d2..e571d66ea0fe 100644
--- a/arch/arm/boot/dts/r8a7778.dtsi
+++ b/arch/arm/boot/dts/r8a7778.dtsi
@@ -276,23 +276,23 @@
 		status = "disabled";
 
 		rcar_sound,src {
-			src3: src@3 { };
-			src4: src@4 { };
-			src5: src@5 { };
-			src6: src@6 { };
-			src7: src@7 { };
-			src8: src@8 { };
-			src9: src@9 { };
+			src3: src-3 { };
+			src4: src-4 { };
+			src5: src-5 { };
+			src6: src-6 { };
+			src7: src-7 { };
+			src8: src-8 { };
+			src9: src-9 { };
 		};
 
 		rcar_sound,ssi {
-			ssi3: ssi@3 { interrupts = <GIC_SPI 0x85 IRQ_TYPE_LEVEL_HIGH>; };
-			ssi4: ssi@4 { interrupts = <GIC_SPI 0x85 IRQ_TYPE_LEVEL_HIGH>; };
-			ssi5: ssi@5 { interrupts = <GIC_SPI 0x86 IRQ_TYPE_LEVEL_HIGH>; };
-			ssi6: ssi@6 { interrupts = <GIC_SPI 0x86 IRQ_TYPE_LEVEL_HIGH>; };
-			ssi7: ssi@7 { interrupts = <GIC_SPI 0x86 IRQ_TYPE_LEVEL_HIGH>; };
-			ssi8: ssi@8 { interrupts = <GIC_SPI 0x86 IRQ_TYPE_LEVEL_HIGH>; };
-			ssi9: ssi@9 { interrupts = <GIC_SPI 0x86 IRQ_TYPE_LEVEL_HIGH>; };
+			ssi3: ssi-3 { interrupts = <GIC_SPI 0x85 IRQ_TYPE_LEVEL_HIGH>; };
+			ssi4: ssi-4 { interrupts = <GIC_SPI 0x85 IRQ_TYPE_LEVEL_HIGH>; };
+			ssi5: ssi-5 { interrupts = <GIC_SPI 0x86 IRQ_TYPE_LEVEL_HIGH>; };
+			ssi6: ssi-6 { interrupts = <GIC_SPI 0x86 IRQ_TYPE_LEVEL_HIGH>; };
+			ssi7: ssi-7 { interrupts = <GIC_SPI 0x86 IRQ_TYPE_LEVEL_HIGH>; };
+			ssi8: ssi-8 { interrupts = <GIC_SPI 0x86 IRQ_TYPE_LEVEL_HIGH>; };
+			ssi9: ssi-9 { interrupts = <GIC_SPI 0x86 IRQ_TYPE_LEVEL_HIGH>; };
 		};
 	};
 
diff --git a/arch/arm/boot/dts/r8a7779-marzen.dts b/arch/arm/boot/dts/r8a7779-marzen.dts
index b795da6f5503..541678df90a9 100644
--- a/arch/arm/boot/dts/r8a7779-marzen.dts
+++ b/arch/arm/boot/dts/r8a7779-marzen.dts
@@ -25,15 +25,15 @@
 
 	chosen {
 		bootargs = "ignore_loglevel root=/dev/nfs ip=on";
-		stdout-path = &scif2;
+		stdout-path = "serial0:115200n8";
 	};
 
-	memory {
+	memory@60000000 {
 		device_type = "memory";
 		reg = <0x60000000 0x40000000>;
 	};
 
-	fixedregulator3v3: fixedregulator@0 {
+	fixedregulator3v3: regulator-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-3.3V";
 		regulator-min-microvolt = <3300000>;
@@ -195,12 +195,12 @@
 		};
 	};
 
-	scif2_pins: serial2 {
+	scif2_pins: scif2 {
 		groups = "scif2_data_c";
 		function = "scif2";
 	};
 
-	scif4_pins: serial4 {
+	scif4_pins: scif4 {
 		groups = "scif4_data";
 		function = "scif4";
 	};
diff --git a/arch/arm/boot/dts/r8a7790-lager.dts b/arch/arm/boot/dts/r8a7790-lager.dts
index 749ba02b6a53..52b56fcaddf2 100644
--- a/arch/arm/boot/dts/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/r8a7790-lager.dts
@@ -76,28 +76,28 @@
 	keyboard {
 		compatible = "gpio-keys";
 
-		button@1 {
+		one {
 			linux,code = <KEY_1>;
 			label = "SW2-1";
 			wakeup-source;
 			debounce-interval = <20>;
 			gpios = <&gpio1 14 GPIO_ACTIVE_LOW>;
 		};
-		button@2 {
+		two {
 			linux,code = <KEY_2>;
 			label = "SW2-2";
 			wakeup-source;
 			debounce-interval = <20>;
 			gpios = <&gpio1 24 GPIO_ACTIVE_LOW>;
 		};
-		button@3 {
+		three {
 			linux,code = <KEY_3>;
 			label = "SW2-3";
 			wakeup-source;
 			debounce-interval = <20>;
 			gpios = <&gpio1 26 GPIO_ACTIVE_LOW>;
 		};
-		button@4 {
+		four {
 			linux,code = <KEY_4>;
 			label = "SW2-4";
 			wakeup-source;
@@ -119,7 +119,7 @@
 		};
 	};
 
-	fixedregulator3v3: fixedregulator@0 {
+	fixedregulator3v3: regulator-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-3.3V";
 		regulator-min-microvolt = <3300000>;
@@ -128,7 +128,7 @@
 		regulator-always-on;
 	};
 
-	vcc_sdhi0: regulator@1 {
+	vcc_sdhi0: regulator-vcc-sdhi0 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI0 Vcc";
@@ -139,7 +139,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi0: regulator@2 {
+	vccq_sdhi0: regulator-vccq-sdhi0 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI0 VccQ";
@@ -152,7 +152,7 @@
 			  1800000 0>;
 	};
 
-	vcc_sdhi2: regulator@3 {
+	vcc_sdhi2: regulator-vcc-sdhi2 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI2 Vcc";
@@ -163,7 +163,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi2: regulator@4 {
+	vccq_sdhi2: regulator-vccq-sdhi2 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI2 VccQ";
@@ -263,7 +263,7 @@
 	 * instantiate the slave device at runtime according to the documentation.
 	 * You can then communicate with the slave via IIC3.
 	 */
-	i2cexio: i2c@8 {
+	i2cexio: i2c-8 {
 		compatible = "i2c-demux-pinctrl";
 		i2c-parent = <&iic0>, <&i2c0>;
 		i2c-bus-name = "i2c-exio";
@@ -317,7 +317,7 @@
 		function = "du";
 	};
 
-	scif0_pins: serial0 {
+	scif0_pins: scif0 {
 		groups = "scif0_data";
 		function = "scif0";
 	};
@@ -337,7 +337,7 @@
 		function = "intc";
 	};
 
-	scifa1_pins: serial1 {
+	scifa1_pins: scifa1 {
 		groups = "scifa1_data";
 		function = "scifa1";
 	};
@@ -371,12 +371,12 @@
 		function = "mmc1";
 	};
 
-	qspi_pins: spi0 {
+	qspi_pins: qspi {
 		groups = "qspi_ctrl", "qspi_data4";
 		function = "qspi";
 	};
 
-	msiof1_pins: spi2 {
+	msiof1_pins: msiof1 {
 		groups = "msiof1_clk", "msiof1_sync", "msiof1_rx",
 				 "msiof1_tx";
 		function = "msiof1";
@@ -427,7 +427,7 @@
 		function = "usb2";
 	};
 
-	vin1_pins: vin {
+	vin1_pins: vin1 {
 		groups = "vin1_data8", "vin1_clk";
 		function = "vin1";
 	};
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 83cf23cd26bb..d18558f21102 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -44,6 +44,7 @@
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
+		enable-method = "renesas,apmu";
 
 		cpu0: cpu@0 {
 			device_type = "cpu";
@@ -92,7 +93,7 @@
 			next-level-cache = <&L2_CA15>;
 		};
 
-		cpu4: cpu@4 {
+		cpu4: cpu@100 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x100>;
@@ -101,7 +102,7 @@
 			next-level-cache = <&L2_CA7>;
 		};
 
-		cpu5: cpu@5 {
+		cpu5: cpu@101 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x101>;
@@ -110,7 +111,7 @@
 			next-level-cache = <&L2_CA7>;
 		};
 
-		cpu6: cpu@6 {
+		cpu6: cpu@102 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x102>;
@@ -119,7 +120,7 @@
 			next-level-cache = <&L2_CA7>;
 		};
 
-		cpu7: cpu@7 {
+		cpu7: cpu@103 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x103>;
@@ -127,6 +128,22 @@
 			power-domains = <&sysc R8A7790_PD_CA7_CPU3>;
 			next-level-cache = <&L2_CA7>;
 		};
+
+		L2_CA15: cache-controller@0 {
+			compatible = "cache";
+			reg = <0>;
+			power-domains = <&sysc R8A7790_PD_CA15_SCU>;
+			cache-unified;
+			cache-level = <2>;
+		};
+
+		L2_CA7: cache-controller@100 {
+			compatible = "cache";
+			reg = <0x100>;
+			power-domains = <&sysc R8A7790_PD_CA7_SCU>;
+			cache-unified;
+			cache-level = <2>;
+		};
 	};
 
 	thermal-zones {
@@ -148,18 +165,16 @@
 		};
 	};
 
-	L2_CA15: cache-controller@0 {
-		compatible = "cache";
-		power-domains = <&sysc R8A7790_PD_CA15_SCU>;
-		cache-unified;
-		cache-level = <2>;
+	apmu@e6151000 {
+		compatible = "renesas,r8a7790-apmu", "renesas,apmu";
+		reg = <0 0xe6151000 0 0x188>;
+		cpus = <&cpu4 &cpu5 &cpu6 &cpu7>;
 	};
 
-	L2_CA7: cache-controller@1 {
-		compatible = "cache";
-		power-domains = <&sysc R8A7790_PD_CA7_SCU>;
-		cache-unified;
-		cache-level = <2>;
+	apmu@e6152000 {
+		compatible = "renesas,r8a7790-apmu", "renesas,apmu";
+		reg = <0 0xe6152000 0 0x188>;
+		cpus = <&cpu0 &cpu1 &cpu2 &cpu3>;
 	};
 
 	gic: interrupt-controller@f1001000 {
@@ -517,8 +532,9 @@
 		reg = <0 0xe6500000 0 0x425>;
 		interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_IIC0>;
-		dmas = <&dmac0 0x61>, <&dmac0 0x62>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x61>, <&dmac0 0x62>,
+		       <&dmac1 0x61>, <&dmac1 0x62>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -530,8 +546,9 @@
 		reg = <0 0xe6510000 0 0x425>;
 		interrupts = <GIC_SPI 175 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_IIC1>;
-		dmas = <&dmac0 0x65>, <&dmac0 0x66>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x65>, <&dmac0 0x66>,
+		       <&dmac1 0x65>, <&dmac1 0x66>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -543,8 +560,9 @@
 		reg = <0 0xe6520000 0 0x425>;
 		interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_IIC2>;
-		dmas = <&dmac0 0x69>, <&dmac0 0x6a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x69>, <&dmac0 0x6a>,
+		       <&dmac1 0x69>, <&dmac1 0x6a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -556,8 +574,9 @@
 		reg = <0 0xe60b0000 0 0x425>;
 		interrupts = <GIC_SPI 173 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7790_CLK_IICDVFS>;
-		dmas = <&dmac0 0x77>, <&dmac0 0x78>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x77>, <&dmac0 0x78>,
+		       <&dmac1 0x77>, <&dmac1 0x78>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -567,8 +586,9 @@
 		reg = <0 0xee200000 0 0x80>;
 		interrupts = <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_MMCIF0>;
-		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>,
+		       <&dmac1 0xd1>, <&dmac1 0xd2>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		reg-io-width = <4>;
 		status = "disabled";
@@ -580,8 +600,9 @@
 		reg = <0 0xee220000 0 0x80>;
 		interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_MMCIF1>;
-		dmas = <&dmac0 0xe1>, <&dmac0 0xe2>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xe1>, <&dmac0 0xe2>,
+		       <&dmac1 0xe1>, <&dmac1 0xe2>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		reg-io-width = <4>;
 		status = "disabled";
@@ -598,8 +619,9 @@
 		reg = <0 0xee100000 0 0x328>;
 		interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_SDHI0>;
-		dmas = <&dmac1 0xcd>, <&dmac1 0xce>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xcd>, <&dmac0 0xce>,
+		       <&dmac1 0xcd>, <&dmac1 0xce>;
+		dma-names = "tx", "rx", "tx", "rx";
 		max-frequency = <195000000>;
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
@@ -610,8 +632,9 @@
 		reg = <0 0xee120000 0 0x328>;
 		interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_SDHI1>;
-		dmas = <&dmac1 0xc9>, <&dmac1 0xca>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xc9>, <&dmac0 0xca>,
+		       <&dmac1 0xc9>, <&dmac1 0xca>;
+		dma-names = "tx", "rx", "tx", "rx";
 		max-frequency = <195000000>;
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
@@ -622,8 +645,9 @@
 		reg = <0 0xee140000 0 0x100>;
 		interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_SDHI2>;
-		dmas = <&dmac1 0xc1>, <&dmac1 0xc2>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xc1>, <&dmac0 0xc2>,
+		       <&dmac1 0xc1>, <&dmac1 0xc2>;
+		dma-names = "tx", "rx", "tx", "rx";
 		max-frequency = <97500000>;
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
@@ -634,8 +658,9 @@
 		reg = <0 0xee160000 0 0x100>;
 		interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7790_CLK_SDHI3>;
-		dmas = <&dmac1 0xd3>, <&dmac1 0xd4>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xd3>, <&dmac0 0xd4>,
+		       <&dmac1 0xd3>, <&dmac1 0xd4>;
+		dma-names = "tx", "rx", "tx", "rx";
 		max-frequency = <97500000>;
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
@@ -648,8 +673,9 @@
 		interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7790_CLK_SCIFA0>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x21>, <&dmac0 0x22>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x21>, <&dmac0 0x22>,
+		       <&dmac1 0x21>, <&dmac1 0x22>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -661,8 +687,9 @@
 		interrupts = <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7790_CLK_SCIFA1>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x25>, <&dmac0 0x26>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x25>, <&dmac0 0x26>,
+		       <&dmac1 0x25>, <&dmac1 0x26>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -674,8 +701,9 @@
 		interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7790_CLK_SCIFA2>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x27>, <&dmac0 0x28>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x27>, <&dmac0 0x28>,
+		       <&dmac1 0x27>, <&dmac1 0x28>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -687,8 +715,9 @@
 		interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7790_CLK_SCIFB0>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>,
+		       <&dmac1 0x3d>, <&dmac1 0x3e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -700,8 +729,9 @@
 		interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7790_CLK_SCIFB1>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x19>, <&dmac0 0x1a>,
+		       <&dmac1 0x19>, <&dmac1 0x1a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -713,8 +743,9 @@
 		interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7790_CLK_SCIFB2>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>,
+		       <&dmac1 0x1d>, <&dmac1 0x1e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -727,8 +758,9 @@
 		clocks = <&mstp7_clks R8A7790_CLK_SCIF0>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x29>, <&dmac0 0x2a>,
+		       <&dmac1 0x29>, <&dmac1 0x2a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -741,8 +773,9 @@
 		clocks = <&mstp7_clks R8A7790_CLK_SCIF1>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>,
+		       <&dmac1 0x2d>, <&dmac1 0x2e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -755,8 +788,9 @@
 		clocks = <&mstp3_clks R8A7790_CLK_SCIF2>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2b>, <&dmac0 0x2c>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2b>, <&dmac0 0x2c>,
+		       <&dmac1 0x2b>, <&dmac1 0x2c>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -769,8 +803,9 @@
 		clocks = <&mstp7_clks R8A7790_CLK_HSCIF0>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x39>, <&dmac0 0x3a>,
+		       <&dmac1 0x39>, <&dmac1 0x3a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -783,8 +818,9 @@
 		clocks = <&mstp7_clks R8A7790_CLK_HSCIF1>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>,
+		       <&dmac1 0x4d>, <&dmac1 0x4e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -1469,8 +1505,9 @@
 		reg = <0 0xe6b10000 0 0x2c>;
 		interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7790_CLK_QSPI_MOD>;
-		dmas = <&dmac0 0x17>, <&dmac0 0x18>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x17>, <&dmac0 0x18>,
+		       <&dmac1 0x17>, <&dmac1 0x18>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		num-cs = <1>;
 		#address-cells = <1>;
@@ -1483,8 +1520,9 @@
 		reg = <0 0xe6e20000 0 0x0064>;
 		interrupts = <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7790_CLK_MSIOF0>;
-		dmas = <&dmac0 0x51>, <&dmac0 0x52>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x51>, <&dmac0 0x52>,
+		       <&dmac1 0x51>, <&dmac1 0x52>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1496,8 +1534,9 @@
 		reg = <0 0xe6e10000 0 0x0064>;
 		interrupts = <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7790_CLK_MSIOF1>;
-		dmas = <&dmac0 0x55>, <&dmac0 0x56>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x55>, <&dmac0 0x56>,
+		       <&dmac1 0x55>, <&dmac1 0x56>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1509,8 +1548,9 @@
 		reg = <0 0xe6e00000 0 0x0064>;
 		interrupts = <GIC_SPI 158 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7790_CLK_MSIOF2>;
-		dmas = <&dmac0 0x41>, <&dmac0 0x42>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x41>, <&dmac0 0x42>,
+		       <&dmac1 0x41>, <&dmac1 0x42>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1522,8 +1562,9 @@
 		reg = <0 0xe6c90000 0 0x0064>;
 		interrupts = <GIC_SPI 159 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7790_CLK_MSIOF3>;
-		dmas = <&dmac0 0x45>, <&dmac0 0x46>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x45>, <&dmac0 0x46>,
+		       <&dmac1 0x45>, <&dmac1 0x46>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1702,79 +1743,79 @@
 		status = "disabled";
 
 		rcar_sound,dvc {
-			dvc0: dvc@0 {
+			dvc0: dvc-0 {
 				dmas = <&audma0 0xbc>;
 				dma-names = "tx";
 			};
-			dvc1: dvc@1 {
+			dvc1: dvc-1 {
 				dmas = <&audma0 0xbe>;
 				dma-names = "tx";
 			};
 		};
 
 		rcar_sound,mix {
-			mix0: mix@0 { };
-			mix1: mix@1 { };
+			mix0: mix-0 { };
+			mix1: mix-1 { };
 		};
 
 		rcar_sound,ctu {
-			ctu00: ctu@0 { };
-			ctu01: ctu@1 { };
-			ctu02: ctu@2 { };
-			ctu03: ctu@3 { };
-			ctu10: ctu@4 { };
-			ctu11: ctu@5 { };
-			ctu12: ctu@6 { };
-			ctu13: ctu@7 { };
+			ctu00: ctu-0 { };
+			ctu01: ctu-1 { };
+			ctu02: ctu-2 { };
+			ctu03: ctu-3 { };
+			ctu10: ctu-4 { };
+			ctu11: ctu-5 { };
+			ctu12: ctu-6 { };
+			ctu13: ctu-7 { };
 		};
 
 		rcar_sound,src {
-			src0: src@0 {
+			src0: src-0 {
 				interrupts = <GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x85>, <&audma1 0x9a>;
 				dma-names = "rx", "tx";
 			};
-			src1: src@1 {
+			src1: src-1 {
 				interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x87>, <&audma1 0x9c>;
 				dma-names = "rx", "tx";
 			};
-			src2: src@2 {
+			src2: src-2 {
 				interrupts = <GIC_SPI 354 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x89>, <&audma1 0x9e>;
 				dma-names = "rx", "tx";
 			};
-			src3: src@3 {
+			src3: src-3 {
 				interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x8b>, <&audma1 0xa0>;
 				dma-names = "rx", "tx";
 			};
-			src4: src@4 {
+			src4: src-4 {
 				interrupts = <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x8d>, <&audma1 0xb0>;
 				dma-names = "rx", "tx";
 			};
-			src5: src@5 {
+			src5: src-5 {
 				interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x8f>, <&audma1 0xb2>;
 				dma-names = "rx", "tx";
 			};
-			src6: src@6 {
+			src6: src-6 {
 				interrupts = <GIC_SPI 358 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x91>, <&audma1 0xb4>;
 				dma-names = "rx", "tx";
 			};
-			src7: src@7 {
+			src7: src-7 {
 				interrupts = <GIC_SPI 359 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x93>, <&audma1 0xb6>;
 				dma-names = "rx", "tx";
 			};
-			src8: src@8 {
+			src8: src-8 {
 				interrupts = <GIC_SPI 360 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x95>, <&audma1 0xb8>;
 				dma-names = "rx", "tx";
 			};
-			src9: src@9 {
+			src9: src-9 {
 				interrupts = <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x97>, <&audma1 0xba>;
 				dma-names = "rx", "tx";
@@ -1782,52 +1823,52 @@
 		};
 
 		rcar_sound,ssi {
-			ssi0: ssi@0 {
+			ssi0: ssi-0 {
 				interrupts = <GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x01>, <&audma1 0x02>, <&audma0 0x15>, <&audma1 0x16>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi1: ssi@1 {
+			ssi1: ssi-1 {
 				 interrupts = <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x03>, <&audma1 0x04>, <&audma0 0x49>, <&audma1 0x4a>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi2: ssi@2 {
+			ssi2: ssi-2 {
 				interrupts = <GIC_SPI 372 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x05>, <&audma1 0x06>, <&audma0 0x63>, <&audma1 0x64>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi3: ssi@3 {
+			ssi3: ssi-3 {
 				interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x07>, <&audma1 0x08>, <&audma0 0x6f>, <&audma1 0x70>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi4: ssi@4 {
+			ssi4: ssi-4 {
 				interrupts = <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x09>, <&audma1 0x0a>, <&audma0 0x71>, <&audma1 0x72>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi5: ssi@5 {
+			ssi5: ssi-5 {
 				interrupts = <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x0b>, <&audma1 0x0c>, <&audma0 0x73>, <&audma1 0x74>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi6: ssi@6 {
+			ssi6: ssi-6 {
 				interrupts = <GIC_SPI 376 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x0d>, <&audma1 0x0e>, <&audma0 0x75>, <&audma1 0x76>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi7: ssi@7 {
+			ssi7: ssi-7 {
 				interrupts = <GIC_SPI 377 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x0f>, <&audma1 0x10>, <&audma0 0x79>, <&audma1 0x7a>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi8: ssi@8 {
+			ssi8: ssi-8 {
 				interrupts = <GIC_SPI 378 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x11>, <&audma1 0x12>, <&audma0 0x7b>, <&audma1 0x7c>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi9: ssi@9 {
+			ssi9: ssi-9 {
 				interrupts = <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x13>, <&audma1 0x14>, <&audma0 0x7d>, <&audma1 0x7e>;
 				dma-names = "rx", "tx", "rxu", "txu";
diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts
index da59c2844b8a..f8a7d090fd01 100644
--- a/arch/arm/boot/dts/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/r8a7791-koelsch.dts
@@ -170,7 +170,7 @@
 		};
 	};
 
-	vcc_sdhi0: regulator@0 {
+	vcc_sdhi0: regulator-vcc-sdhi0 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI0 Vcc";
@@ -181,7 +181,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi0: regulator@1 {
+	vccq_sdhi0: regulator-vccq-sdhi0 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI0 VccQ";
@@ -194,7 +194,7 @@
 			  1800000 0>;
 	};
 
-	vcc_sdhi1: regulator@2 {
+	vcc_sdhi1: regulator-vcc-sdhi1 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI1 Vcc";
@@ -205,7 +205,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi1: regulator@3 {
+	vccq_sdhi1: regulator-vccq-sdhi1 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI1 VccQ";
@@ -218,7 +218,7 @@
 			  1800000 0>;
 	};
 
-	vcc_sdhi2: regulator@4 {
+	vcc_sdhi2: regulator-vcc-sdhi2 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI2 Vcc";
@@ -229,7 +229,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi2: regulator@5 {
+	vccq_sdhi2: regulator-vccq-sdhi2 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI2 VccQ";
@@ -332,12 +332,12 @@
 		function = "du";
 	};
 
-	scif0_pins: serial0 {
+	scif0_pins: scif0 {
 		groups = "scif0_data_d";
 		function = "scif0";
 	};
 
-	scif1_pins: serial1 {
+	scif1_pins: scif1 {
 		groups = "scif1_data_d";
 		function = "scif1";
 	};
@@ -372,12 +372,12 @@
 		function = "sdhi2";
 	};
 
-	qspi_pins: spi0 {
+	qspi_pins: qspi {
 		groups = "qspi_ctrl", "qspi_data4";
 		function = "qspi";
 	};
 
-	msiof0_pins: spi1 {
+	msiof0_pins: msiof0 {
 		groups = "msiof0_clk", "msiof0_sync", "msiof0_rx",
 				 "msiof0_tx";
 		function = "msiof0";
diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts
index 6a1bb1a8209b..6761d11d3f9e 100644
--- a/arch/arm/boot/dts/r8a7791-porter.dts
+++ b/arch/arm/boot/dts/r8a7791-porter.dts
@@ -46,7 +46,7 @@
 		reg = <2 0x00000000 0 0x40000000>;
 	};
 
-	vcc_sdhi0: regulator@0 {
+	vcc_sdhi0: regulator-vcc-sdhi0 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI0 Vcc";
@@ -55,7 +55,7 @@
 		regulator-always-on;
 	};
 
-	vccq_sdhi0: regulator@1 {
+	vccq_sdhi0: regulator-vccq-sdhi0 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI0 VccQ";
@@ -68,7 +68,7 @@
 			  1800000 0>;
 	};
 
-	vcc_sdhi2: regulator@2 {
+	vcc_sdhi2: regulator-vcc-sdhi2 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI2 Vcc";
@@ -77,7 +77,7 @@
 		regulator-always-on;
 	};
 
-	vccq_sdhi2: regulator@3 {
+	vccq_sdhi2: regulator-vccq-sdhi2 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI2 VccQ";
@@ -142,7 +142,7 @@
 };
 
 &pfc {
-	scif0_pins: serial0 {
+	scif0_pins: scif0 {
 		groups = "scif0_data_d";
 		function = "scif0";
 	};
@@ -167,7 +167,7 @@
 		function = "sdhi2";
 	};
 
-	qspi_pins: spi0 {
+	qspi_pins: qspi {
 		groups = "qspi_ctrl", "qspi_data4";
 		function = "qspi";
 	};
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index db67e342c585..8f0086bbd96b 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -43,6 +43,7 @@
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
+		enable-method = "renesas,apmu";
 
 		cpu0: cpu@0 {
 			device_type = "cpu";
@@ -72,6 +73,14 @@
 			power-domains = <&sysc R8A7791_PD_CA15_CPU1>;
 			next-level-cache = <&L2_CA15>;
 		};
+
+		L2_CA15: cache-controller@0 {
+			compatible = "cache";
+			reg = <0>;
+			power-domains = <&sysc R8A7791_PD_CA15_SCU>;
+			cache-unified;
+			cache-level = <2>;
+		};
 	};
 
 	thermal-zones {
@@ -93,11 +102,10 @@
 		};
 	};
 
-	L2_CA15: cache-controller@0 {
-		compatible = "cache";
-		power-domains = <&sysc R8A7791_PD_CA15_SCU>;
-		cache-unified;
-		cache-level = <2>;
+	apmu@e6152000 {
+		compatible = "renesas,r8a7791-apmu", "renesas,apmu";
+		reg = <0 0xe6152000 0 0x188>;
+		cpus = <&cpu0 &cpu1>;
 	};
 
 	gic: interrupt-controller@f1001000 {
@@ -514,8 +522,9 @@
 		reg = <0 0xe60b0000 0 0x425>;
 		interrupts = <GIC_SPI 173 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7791_CLK_IICDVFS>;
-		dmas = <&dmac0 0x77>, <&dmac0 0x78>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x77>, <&dmac0 0x78>,
+		       <&dmac1 0x77>, <&dmac1 0x78>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -527,8 +536,9 @@
 		reg = <0 0xe6500000 0 0x425>;
 		interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7791_CLK_IIC0>;
-		dmas = <&dmac0 0x61>, <&dmac0 0x62>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x61>, <&dmac0 0x62>,
+		       <&dmac1 0x61>, <&dmac1 0x62>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -540,8 +550,9 @@
 		reg = <0 0xe6510000 0 0x425>;
 		interrupts = <GIC_SPI 175 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7791_CLK_IIC1>;
-		dmas = <&dmac0 0x65>, <&dmac0 0x66>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x65>, <&dmac0 0x66>,
+		       <&dmac1 0x65>, <&dmac1 0x66>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -556,8 +567,9 @@
 		reg = <0 0xee200000 0 0x80>;
 		interrupts = <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7791_CLK_MMCIF0>;
-		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>,
+		       <&dmac1 0xd1>, <&dmac1 0xd2>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		reg-io-width = <4>;
 		status = "disabled";
@@ -569,8 +581,9 @@
 		reg = <0 0xee100000 0 0x328>;
 		interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7791_CLK_SDHI0>;
-		dmas = <&dmac1 0xcd>, <&dmac1 0xce>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xcd>, <&dmac0 0xce>,
+		       <&dmac1 0xcd>, <&dmac1 0xce>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -580,8 +593,9 @@
 		reg = <0 0xee140000 0 0x100>;
 		interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7791_CLK_SDHI1>;
-		dmas = <&dmac1 0xc1>, <&dmac1 0xc2>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xc1>, <&dmac0 0xc2>,
+		       <&dmac1 0xc1>, <&dmac1 0xc2>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -591,8 +605,9 @@
 		reg = <0 0xee160000 0 0x100>;
 		interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7791_CLK_SDHI2>;
-		dmas = <&dmac1 0xd3>, <&dmac1 0xd4>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xd3>, <&dmac0 0xd4>,
+		       <&dmac1 0xd3>, <&dmac1 0xd4>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -604,8 +619,9 @@
 		interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7791_CLK_SCIFA0>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x21>, <&dmac0 0x22>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x21>, <&dmac0 0x22>,
+		       <&dmac1 0x21>, <&dmac1 0x22>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -617,8 +633,9 @@
 		interrupts = <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7791_CLK_SCIFA1>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x25>, <&dmac0 0x26>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x25>, <&dmac0 0x26>,
+		       <&dmac1 0x25>, <&dmac1 0x26>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -630,8 +647,9 @@
 		interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7791_CLK_SCIFA2>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x27>, <&dmac0 0x28>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x27>, <&dmac0 0x28>,
+		       <&dmac1 0x27>, <&dmac1 0x28>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -643,8 +661,9 @@
 		interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp11_clks R8A7791_CLK_SCIFA3>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x1b>, <&dmac0 0x1c>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x1b>, <&dmac0 0x1c>,
+		       <&dmac1 0x1b>, <&dmac1 0x1c>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -656,8 +675,9 @@
 		interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp11_clks R8A7791_CLK_SCIFA4>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x1f>, <&dmac0 0x20>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x1f>, <&dmac0 0x20>,
+		       <&dmac1 0x1f>, <&dmac1 0x20>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -669,8 +689,9 @@
 		interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp11_clks R8A7791_CLK_SCIFA5>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x23>, <&dmac0 0x24>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x23>, <&dmac0 0x24>,
+		       <&dmac1 0x23>, <&dmac1 0x24>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -682,8 +703,9 @@
 		interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7791_CLK_SCIFB0>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>,
+		       <&dmac1 0x3d>, <&dmac1 0x3e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -695,8 +717,9 @@
 		interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7791_CLK_SCIFB1>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x19>, <&dmac0 0x1a>,
+		       <&dmac1 0x19>, <&dmac1 0x1a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -708,8 +731,9 @@
 		interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7791_CLK_SCIFB2>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>,
+		       <&dmac1 0x1d>, <&dmac1 0x1e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -722,8 +746,9 @@
 		clocks = <&mstp7_clks R8A7791_CLK_SCIF0>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x29>, <&dmac0 0x2a>,
+		       <&dmac1 0x29>, <&dmac1 0x2a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -736,8 +761,9 @@
 		clocks = <&mstp7_clks R8A7791_CLK_SCIF1>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>,
+		       <&dmac1 0x2d>, <&dmac1 0x2e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -750,8 +776,9 @@
 		clocks = <&mstp7_clks R8A7791_CLK_SCIF2>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2b>, <&dmac0 0x2c>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2b>, <&dmac0 0x2c>,
+		       <&dmac1 0x2b>, <&dmac1 0x2c>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -764,8 +791,9 @@
 		clocks = <&mstp7_clks R8A7791_CLK_SCIF3>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2f>, <&dmac0 0x30>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2f>, <&dmac0 0x30>,
+		       <&dmac1 0x2f>, <&dmac1 0x30>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -778,8 +806,9 @@
 		clocks = <&mstp7_clks R8A7791_CLK_SCIF4>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0xfb>, <&dmac0 0xfc>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xfb>, <&dmac0 0xfc>,
+		       <&dmac1 0xfb>, <&dmac1 0xfc>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -792,8 +821,9 @@
 		clocks = <&mstp7_clks R8A7791_CLK_SCIF5>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0xfd>, <&dmac0 0xfe>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xfd>, <&dmac0 0xfe>,
+		       <&dmac1 0xfd>, <&dmac1 0xfe>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -806,8 +836,9 @@
 		clocks = <&mstp7_clks R8A7791_CLK_HSCIF0>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x39>, <&dmac0 0x3a>,
+		       <&dmac1 0x39>, <&dmac1 0x3a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -820,8 +851,9 @@
 		clocks = <&mstp7_clks R8A7791_CLK_HSCIF1>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>,
+		       <&dmac1 0x4d>, <&dmac1 0x4e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -834,8 +866,9 @@
 		clocks = <&mstp7_clks R8A7791_CLK_HSCIF2>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x3b>, <&dmac0 0x3c>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x3b>, <&dmac0 0x3c>,
+		       <&dmac1 0x3b>, <&dmac1 0x3c>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -1478,8 +1511,9 @@
 		reg = <0 0xe6b10000 0 0x2c>;
 		interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7791_CLK_QSPI_MOD>;
-		dmas = <&dmac0 0x17>, <&dmac0 0x18>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x17>, <&dmac0 0x18>,
+		       <&dmac1 0x17>, <&dmac1 0x18>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		num-cs = <1>;
 		#address-cells = <1>;
@@ -1492,8 +1526,9 @@
 		reg = <0 0xe6e20000 0 0x0064>;
 		interrupts = <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp0_clks R8A7791_CLK_MSIOF0>;
-		dmas = <&dmac0 0x51>, <&dmac0 0x52>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x51>, <&dmac0 0x52>,
+		       <&dmac1 0x51>, <&dmac1 0x52>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1505,8 +1540,9 @@
 		reg = <0 0xe6e10000 0 0x0064>;
 		interrupts = <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7791_CLK_MSIOF1>;
-		dmas = <&dmac0 0x55>, <&dmac0 0x56>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x55>, <&dmac0 0x56>,
+		       <&dmac1 0x55>, <&dmac1 0x56>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1518,8 +1554,9 @@
 		reg = <0 0xe6e00000 0 0x0064>;
 		interrupts = <GIC_SPI 158 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7791_CLK_MSIOF2>;
-		dmas = <&dmac0 0x41>, <&dmac0 0x42>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x41>, <&dmac0 0x42>,
+		       <&dmac1 0x41>, <&dmac1 0x42>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -1737,79 +1774,79 @@
 		status = "disabled";
 
 		rcar_sound,dvc {
-			dvc0: dvc@0 {
+			dvc0: dvc-0 {
 				dmas = <&audma0 0xbc>;
 				dma-names = "tx";
 			};
-			dvc1: dvc@1 {
+			dvc1: dvc-1 {
 				dmas = <&audma0 0xbe>;
 				dma-names = "tx";
 			};
 		};
 
 		rcar_sound,mix {
-			mix0: mix@0 { };
-			mix1: mix@1 { };
+			mix0: mix-0 { };
+			mix1: mix-1 { };
 		};
 
 		rcar_sound,ctu {
-			ctu00: ctu@0 { };
-			ctu01: ctu@1 { };
-			ctu02: ctu@2 { };
-			ctu03: ctu@3 { };
-			ctu10: ctu@4 { };
-			ctu11: ctu@5 { };
-			ctu12: ctu@6 { };
-			ctu13: ctu@7 { };
+			ctu00: ctu-0 { };
+			ctu01: ctu-1 { };
+			ctu02: ctu-2 { };
+			ctu03: ctu-3 { };
+			ctu10: ctu-4 { };
+			ctu11: ctu-5 { };
+			ctu12: ctu-6 { };
+			ctu13: ctu-7 { };
 		};
 
 		rcar_sound,src {
-			src0: src@0 {
+			src0: src-0 {
 				interrupts = <GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x85>, <&audma1 0x9a>;
 				dma-names = "rx", "tx";
 			};
-			src1: src@1 {
+			src1: src-1 {
 				interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x87>, <&audma1 0x9c>;
 				dma-names = "rx", "tx";
 			};
-			src2: src@2 {
+			src2: src-2 {
 				interrupts = <GIC_SPI 354 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x89>, <&audma1 0x9e>;
 				dma-names = "rx", "tx";
 			};
-			src3: src@3 {
+			src3: src-3 {
 				interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x8b>, <&audma1 0xa0>;
 				dma-names = "rx", "tx";
 			};
-			src4: src@4 {
+			src4: src-4 {
 				interrupts = <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x8d>, <&audma1 0xb0>;
 				dma-names = "rx", "tx";
 			};
-			src5: src@5 {
+			src5: src-5 {
 				interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x8f>, <&audma1 0xb2>;
 				dma-names = "rx", "tx";
 			};
-			src6: src@6 {
+			src6: src-6 {
 				interrupts = <GIC_SPI 358 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x91>, <&audma1 0xb4>;
 				dma-names = "rx", "tx";
 			};
-			src7: src@7 {
+			src7: src-7 {
 				interrupts = <GIC_SPI 359 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x93>, <&audma1 0xb6>;
 				dma-names = "rx", "tx";
 			};
-			src8: src@8 {
+			src8: src-8 {
 				interrupts = <GIC_SPI 360 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x95>, <&audma1 0xb8>;
 				dma-names = "rx", "tx";
 			};
-			src9: src@9 {
+			src9: src-9 {
 				interrupts = <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x97>, <&audma1 0xba>;
 				dma-names = "rx", "tx";
@@ -1817,52 +1854,52 @@
 		};
 
 		rcar_sound,ssi {
-			ssi0: ssi@0 {
+			ssi0: ssi-0 {
 				interrupts = <GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x01>, <&audma1 0x02>, <&audma0 0x15>, <&audma1 0x16>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi1: ssi@1 {
+			ssi1: ssi-1 {
 				 interrupts = <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x03>, <&audma1 0x04>, <&audma0 0x49>, <&audma1 0x4a>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi2: ssi@2 {
+			ssi2: ssi-2 {
 				interrupts = <GIC_SPI 372 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x05>, <&audma1 0x06>, <&audma0 0x63>, <&audma1 0x64>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi3: ssi@3 {
+			ssi3: ssi-3 {
 				interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x07>, <&audma1 0x08>, <&audma0 0x6f>, <&audma1 0x70>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi4: ssi@4 {
+			ssi4: ssi-4 {
 				interrupts = <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x09>, <&audma1 0x0a>, <&audma0 0x71>, <&audma1 0x72>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi5: ssi@5 {
+			ssi5: ssi-5 {
 				interrupts = <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x0b>, <&audma1 0x0c>, <&audma0 0x73>, <&audma1 0x74>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi6: ssi@6 {
+			ssi6: ssi-6 {
 				interrupts = <GIC_SPI 376 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x0d>, <&audma1 0x0e>, <&audma0 0x75>, <&audma1 0x76>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi7: ssi@7 {
+			ssi7: ssi-7 {
 				interrupts = <GIC_SPI 377 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x0f>, <&audma1 0x10>, <&audma0 0x79>, <&audma1 0x7a>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi8: ssi@8 {
+			ssi8: ssi-8 {
 				interrupts = <GIC_SPI 378 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x11>, <&audma1 0x12>, <&audma0 0x7b>, <&audma1 0x7c>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi9: ssi@9 {
+			ssi9: ssi-9 {
 				interrupts = <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x13>, <&audma1 0x14>, <&audma0 0x7d>, <&audma1 0x7e>;
 				dma-names = "rx", "tx", "rxu", "txu";
diff --git a/arch/arm/boot/dts/r8a7792-blanche.dts b/arch/arm/boot/dts/r8a7792-blanche.dts
new file mode 100644
index 000000000000..e7b40f0e7da6
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7792-blanche.dts
@@ -0,0 +1,66 @@
+/*
+ * Device Tree Source for the Blanche board
+ *
+ * Copyright (C) 2014 Renesas Electronics Corporation
+ * Copyright (C) 2016 Cogent  Embedded, Inc.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/dts-v1/;
+#include "r8a7792.dtsi"
+
+/ {
+	model = "Blanche";
+	compatible = "renesas,blanche", "renesas,r8a7792";
+
+	aliases {
+		serial0 = &scif0;
+		serial1 = &scif3;
+	};
+
+	chosen {
+		bootargs = "ignore_loglevel rw root=/dev/nfs ip=dhcp";
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0 0x40000000 0 0x40000000>;
+	};
+
+	d3_3v: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "D3.3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
+	ethernet@18000000 {
+		compatible = "smsc,lan89218", "smsc,lan9115";
+		reg = <0 0x18000000 0 0x100>;
+		phy-mode = "mii";
+		interrupt-parent = <&irqc>;
+		interrupts = <0 IRQ_TYPE_EDGE_FALLING>;
+		smsc,irq-push-pull;
+		reg-io-width = <4>;
+		vddvario-supply = <&d3_3v>;
+		vdd33a-supply = <&d3_3v>;
+	};
+};
+
+&extal_clk {
+	clock-frequency = <20000000>;
+};
+
+&scif0 {
+	status = "okay";
+};
+
+&scif3 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/r8a7792.dtsi b/arch/arm/boot/dts/r8a7792.dtsi
new file mode 100644
index 000000000000..3fd61d7ab906
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7792.dtsi
@@ -0,0 +1,385 @@
+/*
+ * Device Tree Source for the r8a7792 SoC
+ *
+ * Copyright (C) 2016 Cogent Embedded Inc.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <dt-bindings/clock/r8a7792-clock.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/power/r8a7792-sysc.h>
+
+/ {
+	compatible = "renesas,r8a7792";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		enable-method = "renesas,apmu";
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			clock-frequency = <1000000000>;
+			clocks = <&cpg_clocks R8A7792_CLK_Z>;
+			power-domains = <&sysc R8A7792_PD_CA15_CPU0>;
+			next-level-cache = <&L2_CA15>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+			clock-frequency = <1000000000>;
+			power-domains = <&sysc R8A7792_PD_CA15_CPU1>;
+			next-level-cache = <&L2_CA15>;
+		};
+
+		L2_CA15: cache-controller@0 {
+			compatible = "cache";
+			reg = <0>;
+			cache-unified;
+			cache-level = <2>;
+			power-domains = <&sysc R8A7792_PD_CA15_SCU>;
+		};
+	};
+
+	soc {
+		compatible = "simple-bus";
+		interrupt-parent = <&gic>;
+
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		apmu@e6152000 {
+			compatible = "renesas,r8a7792-apmu", "renesas,apmu";
+			reg = <0 0xe6152000 0 0x188>;
+			cpus = <&cpu0 &cpu1>;
+		};
+
+		gic: interrupt-controller@f1001000 {
+			compatible = "arm,gic-400";
+			#interrupt-cells = <3>;
+			interrupt-controller;
+			reg = <0 0xf1001000 0 0x1000>,
+			      <0 0xf1002000 0 0x1000>,
+			      <0 0xf1004000 0 0x2000>,
+			      <0 0xf1006000 0 0x2000>;
+			interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(2) |
+				      IRQ_TYPE_LEVEL_HIGH)>;
+		};
+
+		irqc: interrupt-controller@e61c0000 {
+			compatible = "renesas,irqc-r8a7792", "renesas,irqc";
+			#interrupt-cells = <2>;
+			interrupt-controller;
+			reg = <0 0xe61c0000 0 0x200>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&mstp4_clks R8A7792_CLK_IRQC>;
+			power-domains = <&sysc R8A7792_PD_ALWAYS_ON>;
+		};
+
+		timer {
+			compatible = "arm,armv7-timer";
+			interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) |
+				      IRQ_TYPE_LEVEL_LOW)>,
+				     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) |
+				      IRQ_TYPE_LEVEL_LOW)>,
+				     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) |
+				      IRQ_TYPE_LEVEL_LOW)>,
+				     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) |
+				      IRQ_TYPE_LEVEL_LOW)>;
+		};
+
+		sysc: system-controller@e6180000 {
+			compatible = "renesas,r8a7792-sysc";
+			reg = <0 0xe6180000 0 0x0200>;
+			#power-domain-cells = <1>;
+		};
+
+		dmac0: dma-controller@e6700000 {
+			compatible = "renesas,dmac-r8a7792",
+				     "renesas,rcar-dmac";
+			reg = <0 0xe6700000 0 0x20000>;
+			interrupts = <GIC_SPI 197 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 200 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 201 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 202 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 203 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 204 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 205 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 206 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 207 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 209 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 210 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 211 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 212 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 213 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 214 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14";
+			clocks = <&mstp2_clks R8A7792_CLK_SYS_DMAC0>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A7792_PD_ALWAYS_ON>;
+			#dma-cells = <1>;
+			dma-channels = <15>;
+		};
+
+		dmac1: dma-controller@e6720000 {
+			compatible = "renesas,dmac-r8a7792",
+				     "renesas,rcar-dmac";
+			reg = <0 0xe6720000 0 0x20000>;
+			interrupts = <GIC_SPI 220 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 216 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 217 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 218 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 219 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 310 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 311 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 312 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 315 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 316 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 317 IRQ_TYPE_LEVEL_HIGH
+				      GIC_SPI 318 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14";
+			clocks = <&mstp2_clks R8A7792_CLK_SYS_DMAC1>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A7792_PD_ALWAYS_ON>;
+			#dma-cells = <1>;
+			dma-channels = <15>;
+		};
+
+		scif0: serial@e6e60000 {
+			compatible = "renesas,scif-r8a7792",
+				     "renesas,rcar-gen2-scif", "renesas,scif";
+			reg = <0 0xe6e60000 0 64>;
+			interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&mstp7_clks R8A7792_CLK_SCIF0>, <&zs_clk>,
+				 <&scif_clk>;
+			clock-names = "fck", "brg_int", "scif_clk";
+			dmas = <&dmac0 0x29>, <&dmac0 0x2a>,
+			       <&dmac1 0x29>, <&dmac1 0x2a>;
+			dma-names = "tx", "rx", "tx", "rx";
+			power-domains = <&sysc R8A7792_PD_ALWAYS_ON>;
+			status = "disabled";
+		};
+
+		scif1: serial@e6e68000 {
+			compatible = "renesas,scif-r8a7792",
+				     "renesas,rcar-gen2-scif", "renesas,scif";
+			reg = <0 0xe6e68000 0 64>;
+			interrupts = <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&mstp7_clks R8A7792_CLK_SCIF1>, <&zs_clk>,
+				 <&scif_clk>;
+			clock-names = "fck", "brg_int", "scif_clk";
+			dmas = <&dmac0 0x2d>, <&dmac0 0x2e>,
+			       <&dmac1 0x2d>, <&dmac1 0x2e>;
+			dma-names = "tx", "rx", "tx", "rx";
+			power-domains = <&sysc R8A7792_PD_ALWAYS_ON>;
+			status = "disabled";
+		};
+
+		scif2: serial@e6e58000 {
+			compatible = "renesas,scif-r8a7792",
+				     "renesas,rcar-gen2-scif", "renesas,scif";
+			reg = <0 0xe6e58000 0 64>;
+			interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&mstp7_clks R8A7792_CLK_SCIF2>, <&zs_clk>,
+				 <&scif_clk>;
+			clock-names = "fck", "brg_int", "scif_clk";
+			dmas = <&dmac0 0x2b>, <&dmac0 0x2c>,
+			       <&dmac1 0x2b>, <&dmac1 0x2c>;
+			dma-names = "tx", "rx", "tx", "rx";
+			power-domains = <&sysc R8A7792_PD_ALWAYS_ON>;
+			status = "disabled";
+		};
+
+		scif3: serial@e6ea8000 {
+			compatible = "renesas,scif-r8a7792",
+				     "renesas,rcar-gen2-scif", "renesas,scif";
+			reg = <0 0xe6ea8000 0 64>;
+			interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&mstp7_clks R8A7792_CLK_SCIF3>, <&zs_clk>,
+				 <&scif_clk>;
+			clock-names = "fck", "brg_int", "scif_clk";
+			dmas = <&dmac0 0x2f>, <&dmac0 0x30>,
+			       <&dmac1 0x2f>, <&dmac1 0x30>;
+			dma-names = "tx", "rx", "tx", "rx";
+			power-domains = <&sysc R8A7792_PD_ALWAYS_ON>;
+			status = "disabled";
+		};
+
+		hscif0: serial@e62c0000 {
+			compatible = "renesas,hscif-r8a7792",
+				     "renesas,rcar-gen2-hscif", "renesas,hscif";
+			reg = <0 0xe62c0000 0 96>;
+			interrupts = <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&mstp7_clks R8A7792_CLK_HSCIF0>, <&zs_clk>,
+				 <&scif_clk>;
+			clock-names = "fck", "brg_int", "scif_clk";
+			dmas = <&dmac0 0x39>, <&dmac0 0x3a>,
+			       <&dmac1 0x39>, <&dmac1 0x3a>;
+			dma-names = "tx", "rx", "tx", "rx";
+			power-domains = <&sysc R8A7792_PD_ALWAYS_ON>;
+			status = "disabled";
+		};
+
+		hscif1: serial@e62c8000 {
+			compatible = "renesas,hscif-r8a7792",
+				     "renesas,rcar-gen2-hscif", "renesas,hscif";
+			reg = <0 0xe62c8000 0 96>;
+			interrupts = <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&mstp7_clks R8A7792_CLK_HSCIF1>, <&zs_clk>,
+				 <&scif_clk>;
+			clock-names = "fck", "brg_int", "scif_clk";
+			dmas = <&dmac0 0x4d>, <&dmac0 0x4e>,
+			       <&dmac1 0x4d>, <&dmac1 0x4e>;
+			dma-names = "tx", "rx", "tx", "rx";
+			power-domains = <&sysc R8A7792_PD_ALWAYS_ON>;
+			status = "disabled";
+		};
+
+		jpu: jpeg-codec@fe980000 {
+			compatible = "renesas,jpu-r8a7792",
+				     "renesas,rcar-gen2-jpu";
+			reg = <0 0xfe980000 0 0x10300>;
+			interrupts = <GIC_SPI 272 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&mstp1_clks R8A7792_CLK_JPU>;
+			power-domains = <&sysc R8A7792_PD_ALWAYS_ON>;
+		};
+
+		/* Special CPG clocks */
+		cpg_clocks: cpg_clocks@e6150000 {
+			compatible = "renesas,r8a7792-cpg-clocks",
+				     "renesas,rcar-gen2-cpg-clocks";
+			reg = <0 0xe6150000 0 0x1000>;
+			clocks = <&extal_clk>;
+			#clock-cells = <1>;
+			clock-output-names = "main", "pll0", "pll1", "pll3",
+					     "lb", "qspi", "z";
+			#power-domain-cells = <0>;
+		};
+
+		/* Fixed factor clocks */
+		pll1_div2_clk: pll1_div2 {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7792_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <2>;
+			clock-mult = <1>;
+		};
+		zs_clk: zs {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7792_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <6>;
+			clock-mult = <1>;
+		};
+		p_clk: p {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7792_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <24>;
+			clock-mult = <1>;
+		};
+		cp_clk: cp {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7792_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <48>;
+			clock-mult = <1>;
+		};
+		m2_clk: m2 {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7792_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <8>;
+			clock-mult = <1>;
+		};
+
+		/* Gate clocks */
+		mstp1_clks: mstp1_clks@e6150134 {
+			compatible = "renesas,r8a7792-mstp-clocks",
+				     "renesas,cpg-mstp-clocks";
+			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
+			clocks = <&m2_clk>;
+			#clock-cells = <1>;
+			clock-indices = <R8A7792_CLK_JPU>;
+			clock-output-names = "jpu";
+		};
+		mstp2_clks: mstp2_clks@e6150138 {
+			compatible = "renesas,r8a7792-mstp-clocks",
+				     "renesas,cpg-mstp-clocks";
+			reg = <0 0xe6150138 0 4>, <0 0xe6150040 0 4>;
+			clocks = <&zs_clk>, <&zs_clk>;
+			#clock-cells = <1>;
+			clock-indices = <
+				R8A7792_CLK_SYS_DMAC1 R8A7792_CLK_SYS_DMAC0
+			>;
+			clock-output-names = "sys-dmac1", "sys-dmac0";
+		};
+		mstp4_clks: mstp4_clks@e6150140 {
+			compatible = "renesas,r8a7792-mstp-clocks",
+				     "renesas,cpg-mstp-clocks";
+			reg = <0 0xe6150140 0 4>, <0 0xe615004c 0 4>;
+			clocks = <&cp_clk>;
+			#clock-cells = <1>;
+			clock-indices = <R8A7792_CLK_IRQC>;
+			clock-output-names = "irqc";
+		};
+		mstp7_clks: mstp7_clks@e615014c {
+			compatible = "renesas,r8a7792-mstp-clocks",
+				     "renesas,cpg-mstp-clocks";
+			reg = <0 0xe615014c 0 4>, <0 0xe61501c4 0 4>;
+			clocks = <&zs_clk>, <&zs_clk>, <&p_clk>, <&p_clk>,
+				 <&p_clk>, <&p_clk>;
+			#clock-cells = <1>;
+			clock-indices = <
+				R8A7792_CLK_HSCIF1 R8A7792_CLK_HSCIF0
+				R8A7792_CLK_SCIF3 R8A7792_CLK_SCIF2
+				R8A7792_CLK_SCIF1 R8A7792_CLK_SCIF0
+			>;
+			clock-output-names = "hscif1", "hscif0", "scif3",
+					     "scif2", "scif1", "scif0";
+		};
+	};
+
+	/* External root clock */
+	extal_clk: extal {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
+	};
+
+	/* External SCIF clock */
+	scif_clk: scif {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board. */
+		clock-frequency = <0>;
+	};
+};
diff --git a/arch/arm/boot/dts/r8a7793-gose.dts b/arch/arm/boot/dts/r8a7793-gose.dts
index 0ebc3ee34923..90af18600124 100644
--- a/arch/arm/boot/dts/r8a7793-gose.dts
+++ b/arch/arm/boot/dts/r8a7793-gose.dts
@@ -158,7 +158,7 @@
 		};
 	};
 
-	vcc_sdhi0: regulator@0 {
+	vcc_sdhi0: regulator-vcc-sdhi0 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI0 Vcc";
@@ -169,7 +169,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi0: regulator@1 {
+	vccq_sdhi0: regulator-vccq-sdhi0 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI0 VccQ";
@@ -182,7 +182,7 @@
 			  1800000 0>;
 	};
 
-	vcc_sdhi1: regulator@2 {
+	vcc_sdhi1: regulator-vcc-sdhi1 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI1 Vcc";
@@ -193,7 +193,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi1: regulator@3 {
+	vccq_sdhi1: regulator-vccq-sdhi1 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI1 VccQ";
@@ -206,7 +206,7 @@
 			  1800000 0>;
 	};
 
-	vcc_sdhi2: regulator@4 {
+	vcc_sdhi2: regulator-vcc-sdhi2 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI2 Vcc";
@@ -217,7 +217,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi2: regulator@5 {
+	vccq_sdhi2: regulator-vccq-sdhi2 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI2 VccQ";
@@ -320,12 +320,12 @@
 		function = "du";
 	};
 
-	scif0_pins: serial0 {
+	scif0_pins: scif0 {
 		groups = "scif0_data_d";
 		function = "scif0";
 	};
 
-	scif1_pins: serial1 {
+	scif1_pins: scif1 {
 		groups = "scif1_data_d";
 		function = "scif1";
 	};
@@ -360,7 +360,7 @@
 		renesas,function = "sdhi2";
 	};
 
-	qspi_pins: spi0 {
+	qspi_pins: qspi {
 		groups = "qspi_ctrl", "qspi_data4";
 		function = "qspi";
 	};
diff --git a/arch/arm/boot/dts/r8a7793.dtsi b/arch/arm/boot/dts/r8a7793.dtsi
index 1dd6d202cd4c..8d02aacf2892 100644
--- a/arch/arm/boot/dts/r8a7793.dtsi
+++ b/arch/arm/boot/dts/r8a7793.dtsi
@@ -35,6 +35,7 @@
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
+		enable-method = "renesas,apmu";
 
 		cpu0: cpu@0 {
 			device_type = "cpu";
@@ -55,6 +56,28 @@
 					   < 375000 1000000>;
 			next-level-cache = <&L2_CA15>;
 		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+			clock-frequency = <1500000000>;
+			power-domains = <&sysc R8A7793_PD_CA15_CPU1>;
+		};
+
+		L2_CA15: cache-controller@0 {
+			compatible = "cache";
+			reg = <0>;
+			power-domains = <&sysc R8A7793_PD_CA15_SCU>;
+			cache-unified;
+			cache-level = <2>;
+		};
+	};
+
+	apmu@e6152000 {
+		compatible = "renesas,r8a7793-apmu", "renesas,apmu";
+		reg = <0 0xe6152000 0 0x188>;
+		cpus = <&cpu0 &cpu1>;
 	};
 
 	thermal-zones {
@@ -76,13 +99,6 @@
 		};
 	};
 
-	L2_CA15: cache-controller@0 {
-		compatible = "cache";
-		power-domains = <&sysc R8A7793_PD_CA15_SCU>;
-		cache-unified;
-		cache-level = <2>;
-	};
-
 	gic: interrupt-controller@f1001000 {
 		compatible = "arm,gic-400";
 		#interrupt-cells = <3>;
@@ -473,8 +489,9 @@
 		reg = <0 0xe60b0000 0 0x425>;
 		interrupts = <GIC_SPI 173 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7793_CLK_IICDVFS>;
-		dmas = <&dmac0 0x77>, <&dmac0 0x78>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x77>, <&dmac0 0x78>,
+		       <&dmac1 0x77>, <&dmac1 0x78>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -486,8 +503,9 @@
 		reg = <0 0xe6500000 0 0x425>;
 		interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7793_CLK_IIC0>;
-		dmas = <&dmac0 0x61>, <&dmac0 0x62>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x61>, <&dmac0 0x62>,
+		       <&dmac1 0x61>, <&dmac1 0x62>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -499,8 +517,9 @@
 		reg = <0 0xe6510000 0 0x425>;
 		interrupts = <GIC_SPI 175 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7793_CLK_IIC1>;
-		dmas = <&dmac0 0x65>, <&dmac0 0x66>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x65>, <&dmac0 0x66>,
+		       <&dmac1 0x65>, <&dmac1 0x66>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -515,8 +534,9 @@
 		reg = <0 0xee100000 0 0x328>;
 		interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7793_CLK_SDHI0>;
-		dmas = <&dmac0 0xcd>, <&dmac0 0xce>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xcd>, <&dmac0 0xce>,
+		       <&dmac1 0xcd>, <&dmac1 0xce>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -526,8 +546,9 @@
 		reg = <0 0xee140000 0 0x100>;
 		interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7793_CLK_SDHI1>;
-		dmas = <&dmac0 0xc1>, <&dmac0 0xc2>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xc1>, <&dmac0 0xc2>,
+		       <&dmac1 0xc1>, <&dmac1 0xc2>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -537,10 +558,25 @@
 		reg = <0 0xee160000 0 0x100>;
 		interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7793_CLK_SDHI2>;
-		dmas = <&dmac0 0xd3>, <&dmac0 0xd4>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xd3>, <&dmac0 0xd4>,
+		       <&dmac1 0xd3>, <&dmac1 0xd4>;
+		dma-names = "tx", "rx", "tx", "rx";
+		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
+		status = "disabled";
+	};
+
+	mmcif0: mmc@ee200000 {
+		compatible = "renesas,mmcif-r8a7793", "renesas,sh-mmcif";
+		reg = <0 0xee200000 0 0x80>;
+		interrupts = <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp3_clks R8A7793_CLK_MMCIF0>;
+		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>,
+		       <&dmac1 0xd1>, <&dmac1 0xd2>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
+		reg-io-width = <4>;
 		status = "disabled";
+		max-frequency = <97500000>;
 	};
 
 	scifa0: serial@e6c40000 {
@@ -550,8 +586,9 @@
 		interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7793_CLK_SCIFA0>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x21>, <&dmac0 0x22>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x21>, <&dmac0 0x22>,
+		       <&dmac1 0x21>, <&dmac1 0x22>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -563,8 +600,9 @@
 		interrupts = <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7793_CLK_SCIFA1>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x25>, <&dmac0 0x26>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x25>, <&dmac0 0x26>,
+		       <&dmac1 0x25>, <&dmac1 0x26>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -576,8 +614,9 @@
 		interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7793_CLK_SCIFA2>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x27>, <&dmac0 0x28>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x27>, <&dmac0 0x28>,
+		       <&dmac1 0x27>, <&dmac1 0x28>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -589,8 +628,9 @@
 		interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp11_clks R8A7793_CLK_SCIFA3>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x1b>, <&dmac0 0x1c>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x1b>, <&dmac0 0x1c>,
+		       <&dmac1 0x1b>, <&dmac1 0x1c>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -602,8 +642,9 @@
 		interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp11_clks R8A7793_CLK_SCIFA4>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x1f>, <&dmac0 0x20>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x1f>, <&dmac0 0x20>,
+		       <&dmac1 0x1f>, <&dmac1 0x20>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -615,8 +656,9 @@
 		interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp11_clks R8A7793_CLK_SCIFA5>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x23>, <&dmac0 0x24>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x23>, <&dmac0 0x24>,
+		       <&dmac1 0x23>, <&dmac1 0x24>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -628,8 +670,9 @@
 		interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7793_CLK_SCIFB0>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>,
+		       <&dmac1 0x3d>, <&dmac1 0x3e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -641,8 +684,9 @@
 		interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7793_CLK_SCIFB1>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x19>, <&dmac0 0x1a>,
+		       <&dmac1 0x19>, <&dmac1 0x1a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -654,8 +698,9 @@
 		interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7793_CLK_SCIFB2>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>,
+		       <&dmac1 0x1d>, <&dmac1 0x1e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -668,8 +713,9 @@
 		clocks = <&mstp7_clks R8A7793_CLK_SCIF0>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x29>, <&dmac0 0x2a>,
+		       <&dmac1 0x29>, <&dmac1 0x2a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -682,8 +728,9 @@
 		clocks = <&mstp7_clks R8A7793_CLK_SCIF1>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>,
+		       <&dmac1 0x2d>, <&dmac1 0x2e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -696,8 +743,9 @@
 		clocks = <&mstp7_clks R8A7793_CLK_SCIF2>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2b>, <&dmac0 0x2c>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2b>, <&dmac0 0x2c>,
+		       <&dmac1 0x2b>, <&dmac1 0x2c>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -710,8 +758,9 @@
 		clocks = <&mstp7_clks R8A7793_CLK_SCIF3>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2f>, <&dmac0 0x30>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2f>, <&dmac0 0x30>,
+		       <&dmac1 0x2f>, <&dmac1 0x30>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -724,8 +773,9 @@
 		clocks = <&mstp7_clks R8A7793_CLK_SCIF4>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0xfb>, <&dmac0 0xfc>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xfb>, <&dmac0 0xfc>,
+		       <&dmac1 0xfb>, <&dmac1 0xfc>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -738,8 +788,9 @@
 		clocks = <&mstp7_clks R8A7793_CLK_SCIF5>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0xfd>, <&dmac0 0xfe>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xfd>, <&dmac0 0xfe>,
+		       <&dmac1 0xfd>, <&dmac1 0xfe>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -752,8 +803,9 @@
 		clocks = <&mstp7_clks R8A7793_CLK_HSCIF0>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x39>, <&dmac0 0x3a>,
+		       <&dmac1 0x39>, <&dmac1 0x3a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -766,8 +818,9 @@
 		clocks = <&mstp7_clks R8A7793_CLK_HSCIF1>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>,
+		       <&dmac1 0x4d>, <&dmac1 0x4e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -780,8 +833,9 @@
 		clocks = <&mstp7_clks R8A7793_CLK_HSCIF2>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x3b>, <&dmac0 0x3c>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x3b>, <&dmac0 0x3c>,
+		       <&dmac1 0x3b>, <&dmac1 0x3c>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -803,8 +857,9 @@
 		reg = <0 0xe6b10000 0 0x2c>;
 		interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7793_CLK_QSPI_MOD>;
-		dmas = <&dmac0 0x17>, <&dmac0 0x18>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x17>, <&dmac0 0x18>,
+		       <&dmac1 0x17>, <&dmac1 0x18>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
 		num-cs = <1>;
 		#address-cells = <1>;
@@ -1330,63 +1385,63 @@
 		status = "disabled";
 
 		rcar_sound,dvc {
-			dvc0: dvc@0 {
+			dvc0: dvc-0 {
 				dmas = <&audma0 0xbc>;
 				dma-names = "tx";
 			};
-			dvc1: dvc@1 {
+			dvc1: dvc-1 {
 				dmas = <&audma0 0xbe>;
 				dma-names = "tx";
 			};
 		};
 
 		rcar_sound,src {
-			src0: src@0 {
+			src0: src-0 {
 				interrupts = <GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x85>, <&audma1 0x9a>;
 				dma-names = "rx", "tx";
 			};
-			src1: src@1 {
+			src1: src-1 {
 				interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x87>, <&audma1 0x9c>;
 				dma-names = "rx", "tx";
 			};
-			src2: src@2 {
+			src2: src-2 {
 				interrupts = <GIC_SPI 354 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x89>, <&audma1 0x9e>;
 				dma-names = "rx", "tx";
 			};
-			src3: src@3 {
+			src3: src-3 {
 				interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x8b>, <&audma1 0xa0>;
 				dma-names = "rx", "tx";
 			};
-			src4: src@4 {
+			src4: src-4 {
 				interrupts = <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x8d>, <&audma1 0xb0>;
 				dma-names = "rx", "tx";
 			};
-			src5: src@5 {
+			src5: src-5 {
 				interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x8f>, <&audma1 0xb2>;
 				dma-names = "rx", "tx";
 			};
-			src6: src@6 {
+			src6: src-6 {
 				interrupts = <GIC_SPI 358 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x91>, <&audma1 0xb4>;
 				dma-names = "rx", "tx";
 			};
-			src7: src@7 {
+			src7: src-7 {
 				interrupts = <GIC_SPI 359 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x93>, <&audma1 0xb6>;
 				dma-names = "rx", "tx";
 			};
-			src8: src@8 {
+			src8: src-8 {
 				interrupts = <GIC_SPI 360 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x95>, <&audma1 0xb8>;
 				dma-names = "rx", "tx";
 			};
-			src9: src@9 {
+			src9: src-9 {
 				interrupts = <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x97>, <&audma1 0xba>;
 				dma-names = "rx", "tx";
@@ -1394,52 +1449,52 @@
 		};
 
 		rcar_sound,ssi {
-			ssi0: ssi@0 {
+			ssi0: ssi-0 {
 				interrupts = <GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x01>, <&audma1 0x02>, <&audma0 0x15>, <&audma1 0x16>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi1: ssi@1 {
+			ssi1: ssi-1 {
 				 interrupts = <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x03>, <&audma1 0x04>, <&audma0 0x49>, <&audma1 0x4a>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi2: ssi@2 {
+			ssi2: ssi-2 {
 				interrupts = <GIC_SPI 372 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x05>, <&audma1 0x06>, <&audma0 0x63>, <&audma1 0x64>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi3: ssi@3 {
+			ssi3: ssi-3 {
 				interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x07>, <&audma1 0x08>, <&audma0 0x6f>, <&audma1 0x70>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi4: ssi@4 {
+			ssi4: ssi-4 {
 				interrupts = <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x09>, <&audma1 0x0a>, <&audma0 0x71>, <&audma1 0x72>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi5: ssi@5 {
+			ssi5: ssi-5 {
 				interrupts = <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x0b>, <&audma1 0x0c>, <&audma0 0x73>, <&audma1 0x74>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi6: ssi@6 {
+			ssi6: ssi-6 {
 				interrupts = <GIC_SPI 376 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x0d>, <&audma1 0x0e>, <&audma0 0x75>, <&audma1 0x76>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi7: ssi@7 {
+			ssi7: ssi-7 {
 				interrupts = <GIC_SPI 377 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x0f>, <&audma1 0x10>, <&audma0 0x79>, <&audma1 0x7a>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi8: ssi@8 {
+			ssi8: ssi-8 {
 				interrupts = <GIC_SPI 378 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x11>, <&audma1 0x12>, <&audma0 0x7b>, <&audma1 0x7c>;
 				dma-names = "rx", "tx", "rxu", "txu";
 			};
-			ssi9: ssi@9 {
+			ssi9: ssi-9 {
 				interrupts = <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH>;
 				dmas = <&audma0 0x13>, <&audma1 0x14>, <&audma0 0x7d>, <&audma1 0x7e>;
 				dma-names = "rx", "tx", "rxu", "txu";
diff --git a/arch/arm/boot/dts/r8a7794-alt.dts b/arch/arm/boot/dts/r8a7794-alt.dts
index 383ad791f1db..1ad37d431a2a 100644
--- a/arch/arm/boot/dts/r8a7794-alt.dts
+++ b/arch/arm/boot/dts/r8a7794-alt.dts
@@ -111,7 +111,7 @@
 		function = "du";
 	};
 
-	scif2_pins: serial2 {
+	scif2_pins: scif2 {
 		groups = "scif2_data";
 		function = "scif2";
 	};
@@ -147,7 +147,7 @@
 };
 
 &pfc {
-	qspi_pins: spi0 {
+	qspi_pins: qspi {
 		groups = "qspi_ctrl", "qspi_data4";
 		function = "qspi";
 	};
diff --git a/arch/arm/boot/dts/r8a7794-silk.dts b/arch/arm/boot/dts/r8a7794-silk.dts
index 56d98d5b2185..cf24f45fff22 100644
--- a/arch/arm/boot/dts/r8a7794-silk.dts
+++ b/arch/arm/boot/dts/r8a7794-silk.dts
@@ -32,7 +32,7 @@
 		reg = <0 0x40000000 0 0x40000000>;
 	};
 
-	d3_3v: regulator@0 {
+	d3_3v: regulator-d3-3v {
 		compatible = "regulator-fixed";
 		regulator-name = "D3.3V";
 		regulator-min-microvolt = <3300000>;
@@ -41,7 +41,7 @@
 		regulator-always-on;
 	};
 
-	vcc_sdhi1: regulator@3 {
+	vcc_sdhi1: regulator-vcc-sdhi1 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI1 Vcc";
@@ -52,7 +52,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi1: regulator@4 {
+	vccq_sdhi1: regulator-vccq-sdhi1 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI1 VccQ";
@@ -129,7 +129,7 @@
 	pinctrl-0 = <&scif_clk_pins>;
 	pinctrl-names = "default";
 
-	scif2_pins: serial2 {
+	scif2_pins: scif2 {
 		groups = "scif2_data";
 		function = "scif2";
 	};
@@ -164,7 +164,7 @@
 		function = "sdhi1";
 	};
 
-	qspi_pins: spi0 {
+	qspi_pins: qspi {
 		groups = "qspi_ctrl", "qspi_data4";
 		function = "qspi";
 	};
@@ -183,6 +183,16 @@
 		groups = "usb1";
 		function = "usb1";
 	};
+
+	du0_pins: du0 {
+		groups = "du0_rgb888", "du0_sync", "du0_disp", "du0_clk0_out";
+		function = "du0";
+	};
+
+	du1_pins: du1 {
+		groups = "du1_rgb666", "du1_sync", "du1_disp", "du1_clk0_out";
+		function = "du1";
+	};
 };
 
 &scif2 {
@@ -360,6 +370,8 @@
 };
 
 &du {
+	pinctrl-0 = <&du0_pins &du1_pins>;
+	pinctrl-names = "default";
 	status = "okay";
 
 	clocks = <&mstp7_clks R8A7794_CLK_DU0>,
diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index f334a3a715f2..685f986cf962 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -55,13 +55,14 @@
 			power-domains = <&sysc R8A7794_PD_CA7_CPU1>;
 			next-level-cache = <&L2_CA7>;
 		};
-	};
 
-	L2_CA7: cache-controller@1 {
-		compatible = "cache";
-		power-domains = <&sysc R8A7794_PD_CA7_SCU>;
-		cache-unified;
-		cache-level = <2>;
+		L2_CA7: cache-controller@0 {
+			compatible = "cache";
+			reg = <0>;
+			power-domains = <&sysc R8A7794_PD_CA7_SCU>;
+			cache-unified;
+			cache-level = <2>;
+		};
 	};
 
 	gic: interrupt-controller@f1001000 {
@@ -302,8 +303,9 @@
 		interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7794_CLK_SCIFA0>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x21>, <&dmac0 0x22>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x21>, <&dmac0 0x22>,
+		       <&dmac1 0x21>, <&dmac1 0x22>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -315,8 +317,9 @@
 		interrupts = <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7794_CLK_SCIFA1>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x25>, <&dmac0 0x26>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x25>, <&dmac0 0x26>,
+		       <&dmac1 0x25>, <&dmac1 0x26>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -328,8 +331,9 @@
 		interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7794_CLK_SCIFA2>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x27>, <&dmac0 0x28>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x27>, <&dmac0 0x28>,
+		       <&dmac1 0x27>, <&dmac1 0x28>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -341,8 +345,9 @@
 		interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp11_clks R8A7794_CLK_SCIFA3>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x1b>, <&dmac0 0x1c>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x1b>, <&dmac0 0x1c>,
+		       <&dmac1 0x1b>, <&dmac1 0x1c>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -354,8 +359,9 @@
 		interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp11_clks R8A7794_CLK_SCIFA4>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x1f>, <&dmac0 0x20>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x1f>, <&dmac0 0x20>,
+		       <&dmac1 0x1f>, <&dmac1 0x20>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -367,8 +373,9 @@
 		interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp11_clks R8A7794_CLK_SCIFA5>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x23>, <&dmac0 0x24>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x23>, <&dmac0 0x24>,
+		       <&dmac1 0x23>, <&dmac1 0x24>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -380,8 +387,9 @@
 		interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7794_CLK_SCIFB0>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x3d>, <&dmac0 0x3e>,
+		       <&dmac1 0x3d>, <&dmac1 0x3e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -393,8 +401,9 @@
 		interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7794_CLK_SCIFB1>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x19>, <&dmac0 0x1a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x19>, <&dmac0 0x1a>,
+		       <&dmac1 0x19>, <&dmac1 0x1a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -406,8 +415,9 @@
 		interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp2_clks R8A7794_CLK_SCIFB2>;
 		clock-names = "fck";
-		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x1d>, <&dmac0 0x1e>,
+		       <&dmac1 0x1d>, <&dmac1 0x1e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -420,8 +430,9 @@
 		clocks = <&mstp7_clks R8A7794_CLK_SCIF0>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x29>, <&dmac0 0x2a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x29>, <&dmac0 0x2a>,
+		       <&dmac1 0x29>, <&dmac1 0x2a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -434,8 +445,9 @@
 		clocks = <&mstp7_clks R8A7794_CLK_SCIF1>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2d>, <&dmac0 0x2e>,
+		       <&dmac1 0x2d>, <&dmac1 0x2e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -448,8 +460,9 @@
 		clocks = <&mstp7_clks R8A7794_CLK_SCIF2>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2b>, <&dmac0 0x2c>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2b>, <&dmac0 0x2c>,
+		       <&dmac1 0x2b>, <&dmac1 0x2c>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -462,8 +475,9 @@
 		clocks = <&mstp7_clks R8A7794_CLK_SCIF3>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x2f>, <&dmac0 0x30>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x2f>, <&dmac0 0x30>,
+		       <&dmac1 0x2f>, <&dmac1 0x30>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -476,8 +490,9 @@
 		clocks = <&mstp7_clks R8A7794_CLK_SCIF4>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0xfb>, <&dmac0 0xfc>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xfb>, <&dmac0 0xfc>,
+		       <&dmac1 0xfb>, <&dmac1 0xfc>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -490,8 +505,9 @@
 		clocks = <&mstp7_clks R8A7794_CLK_SCIF5>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0xfd>, <&dmac0 0xfe>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xfd>, <&dmac0 0xfe>,
+		       <&dmac1 0xfd>, <&dmac1 0xfe>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -504,8 +520,9 @@
 		clocks = <&mstp7_clks R8A7794_CLK_HSCIF0>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x39>, <&dmac0 0x3a>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x39>, <&dmac0 0x3a>,
+		       <&dmac1 0x39>, <&dmac1 0x3a>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -518,8 +535,9 @@
 		clocks = <&mstp7_clks R8A7794_CLK_HSCIF1>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x4d>, <&dmac0 0x4e>,
+		       <&dmac1 0x4d>, <&dmac1 0x4e>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -532,8 +550,9 @@
 		clocks = <&mstp7_clks R8A7794_CLK_HSCIF2>, <&zs_clk>,
 			 <&scif_clk>;
 		clock-names = "fck", "brg_int", "scif_clk";
-		dmas = <&dmac0 0x3b>, <&dmac0 0x3c>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x3b>, <&dmac0 0x3c>,
+		       <&dmac1 0x3b>, <&dmac1 0x3c>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -640,8 +659,9 @@
 		reg = <0 0xe6500000 0 0x425>;
 		interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7794_CLK_IIC0>;
-		dmas = <&dmac0 0x61>, <&dmac0 0x62>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x61>, <&dmac0 0x62>,
+		       <&dmac1 0x61>, <&dmac1 0x62>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -653,8 +673,9 @@
 		reg = <0 0xe6510000 0 0x425>;
 		interrupts = <GIC_SPI 175 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7794_CLK_IIC1>;
-		dmas = <&dmac0 0x65>, <&dmac0 0x66>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x65>, <&dmac0 0x66>,
+		       <&dmac1 0x65>, <&dmac1 0x66>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -666,8 +687,9 @@
 		reg = <0 0xee200000 0 0x80>;
 		interrupts = <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7794_CLK_MMCIF0>;
-		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>,
+		       <&dmac1 0xd1>, <&dmac1 0xd2>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		reg-io-width = <4>;
 		status = "disabled";
@@ -678,6 +700,9 @@
 		reg = <0 0xee100000 0 0x200>;
 		interrupts = <GIC_SPI 165 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7794_CLK_SDHI0>;
+		dmas = <&dmac0 0xcd>, <&dmac0 0xce>,
+		       <&dmac1 0xcd>, <&dmac1 0xce>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -687,6 +712,9 @@
 		reg = <0 0xee140000 0 0x100>;
 		interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7794_CLK_SDHI1>;
+		dmas = <&dmac0 0xc1>, <&dmac0 0xc2>,
+		       <&dmac1 0xc1>, <&dmac1 0xc2>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -696,6 +724,9 @@
 		reg = <0 0xee160000 0 0x100>;
 		interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A7794_CLK_SDHI2>;
+		dmas = <&dmac0 0xd3>, <&dmac0 0xd4>,
+		       <&dmac1 0xd3>, <&dmac1 0xd4>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		status = "disabled";
 	};
@@ -705,8 +736,9 @@
 		reg = <0 0xe6b10000 0 0x2c>;
 		interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp9_clks R8A7794_CLK_QSPI_MOD>;
-		dmas = <&dmac0 0x17>, <&dmac0 0x18>;
-		dma-names = "tx", "rx";
+		dmas = <&dmac0 0x17>, <&dmac0 0x18>,
+		       <&dmac1 0x17>, <&dmac1 0x18>;
+		dma-names = "tx", "rx", "tx", "rx";
 		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		num-cs = <1>;
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/rk3228-evb.dts b/arch/arm/boot/dts/rk3228-evb.dts
index 5956e8246abe..904668e2e666 100644
--- a/arch/arm/boot/dts/rk3228-evb.dts
+++ b/arch/arm/boot/dts/rk3228-evb.dts
@@ -40,7 +40,7 @@
 
 /dts-v1/;
 
-#include "rk3228.dtsi"
+#include "rk322x.dtsi"
 
 / {
 	model = "Rockchip RK3228 Evaluation board";
diff --git a/arch/arm/boot/dts/rk3229-evb.dts b/arch/arm/boot/dts/rk3229-evb.dts
new file mode 100644
index 000000000000..b6a12035a6bb
--- /dev/null
+++ b/arch/arm/boot/dts/rk3229-evb.dts
@@ -0,0 +1,90 @@
+/*
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *  Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+
+#include "rk322x.dtsi"
+
+/ {
+	model = "Rockchip RK3229 Evaluation board";
+	compatible = "rockchip,rk3229-evb", "rockchip,rk3229";
+
+	memory {
+		device_type = "memory";
+		reg = <0x60000000 0x40000000>;
+	};
+
+	ext_gmac: ext_gmac {
+		compatible = "fixed-clock";
+		clock-frequency = <125000000>;
+		clock-output-names = "ext_gmac";
+		#clock-cells = <0>;
+	};
+
+	vcc_phy: vcc-phy-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		regulator-name = "vcc_phy";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+};
+
+&gmac {
+	assigned-clocks = <&cru SCLK_MAC_EXTCLK>, <&cru SCLK_MAC>;
+	assigned-clock-parents = <&ext_gmac>, <&cru SCLK_MAC_EXTCLK>;
+	clock_in_out = "input";
+	phy-supply = <&vcc_phy>;
+	phy-mode = "rgmii";
+	pinctrl-names = "default";
+	pinctrl-0 = <&rgmii_pins>;
+	snps,reset-gpio = <&gpio2 24 GPIO_ACTIVE_LOW>;
+	snps,reset-active-low;
+	snps,reset-delays-us = <0 10000 1000000>;
+	tx_delay = <0x30>;
+	rx_delay = <0x10>;
+	status = "okay";
+};
+
+&uart2 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/rk3228.dtsi b/arch/arm/boot/dts/rk322x.dtsi
index e23a22e29155..9e6bf0e311bb 100644
--- a/arch/arm/boot/dts/rk3228.dtsi
+++ b/arch/arm/boot/dts/rk322x.dtsi
@@ -47,8 +47,6 @@
 #include "skeleton.dtsi"
 
 / {
-	compatible = "rockchip,rk3228";
-
 	interrupt-parent = <&gic>;
 
 	aliases {
@@ -140,6 +138,47 @@
 		#clock-cells = <0>;
 	};
 
+	i2s1: i2s1@100b0000 {
+		compatible = "rockchip,rk3228-i2s", "rockchip,rk3066-i2s";
+		reg = <0x100b0000 0x4000>;
+		interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clock-names = "i2s_clk", "i2s_hclk";
+		clocks = <&cru SCLK_I2S1>, <&cru HCLK_I2S1_8CH>;
+		dmas = <&pdma 14>, <&pdma 15>;
+		dma-names = "tx", "rx";
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2s1_bus>;
+		status = "disabled";
+	};
+
+	i2s0: i2s0@100c0000 {
+		compatible = "rockchip,rk3228-i2s", "rockchip,rk3066-i2s";
+		reg = <0x100c0000 0x4000>;
+		interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clock-names = "i2s_clk", "i2s_hclk";
+		clocks = <&cru SCLK_I2S0>, <&cru HCLK_I2S0_8CH>;
+		dmas = <&pdma 11>, <&pdma 12>;
+		dma-names = "tx", "rx";
+		status = "disabled";
+	};
+
+	i2s2: i2s2@100e0000 {
+		compatible = "rockchip,rk3228-i2s", "rockchip,rk3066-i2s";
+		reg = <0x100e0000 0x4000>;
+		interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clock-names = "i2s_clk", "i2s_hclk";
+		clocks = <&cru SCLK_I2S2>, <&cru HCLK_I2S2_2CH>;
+		dmas = <&pdma 0>, <&pdma 1>;
+		dma-names = "tx", "rx";
+		status = "disabled";
+	};
+
 	grf: syscon@11000000 {
 		compatible = "syscon";
 		reg = <0x11000000 0x1000>;
@@ -376,6 +415,25 @@
 		status = "disabled";
 	};
 
+	gmac: ethernet@30200000 {
+		compatible = "rockchip,rk3228-gmac";
+		reg = <0x30200000 0x10000>;
+		interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "macirq";
+		clocks = <&cru SCLK_MAC>, <&cru SCLK_MAC_RX>,
+			<&cru SCLK_MAC_TX>, <&cru SCLK_MAC_REF>,
+			<&cru SCLK_MAC_REFOUT>, <&cru ACLK_GMAC>,
+			<&cru PCLK_GMAC>;
+		clock-names = "stmmaceth", "mac_clk_rx",
+			"mac_clk_tx", "clk_mac_ref",
+			"clk_mac_refout", "aclk_mac",
+			"pclk_mac";
+		resets = <&cru SRST_GMAC>;
+		reset-names = "stmmaceth";
+		rockchip,grf = <&grf>;
+		status = "disabled";
+	};
+
 	gic: interrupt-controller@32010000 {
 		compatible = "arm,gic-400";
 		interrupt-controller;
@@ -460,6 +518,10 @@
 			bias-disable;
 		};
 
+		pcfg_pull_none_drv_12ma: pcfg-pull-none-drv-12ma {
+			drive-strength = <12>;
+		};
+
 		emmc {
 			emmc_clk: emmc-clk {
 				rockchip,pins = <2 7 RK_FUNC_2 &pcfg_pull_none>;
@@ -481,6 +543,44 @@
 			};
 		};
 
+		gmac {
+			rgmii_pins: rgmii-pins {
+				rockchip,pins = <2 14 RK_FUNC_1 &pcfg_pull_none>,
+						<2 12 RK_FUNC_1 &pcfg_pull_none>,
+						<2 25 RK_FUNC_1 &pcfg_pull_none>,
+						<2 19 RK_FUNC_1 &pcfg_pull_none_drv_12ma>,
+						<2 18 RK_FUNC_1 &pcfg_pull_none_drv_12ma>,
+						<2 22 RK_FUNC_1 &pcfg_pull_none_drv_12ma>,
+						<2 23 RK_FUNC_1 &pcfg_pull_none_drv_12ma>,
+						<2 9 RK_FUNC_1 &pcfg_pull_none_drv_12ma>,
+						<2 13 RK_FUNC_1 &pcfg_pull_none_drv_12ma>,
+						<2 17 RK_FUNC_1 &pcfg_pull_none>,
+						<2 16 RK_FUNC_1 &pcfg_pull_none>,
+						<2 21 RK_FUNC_2 &pcfg_pull_none>,
+						<2 20 RK_FUNC_2 &pcfg_pull_none>,
+						<2 11 RK_FUNC_1 &pcfg_pull_none>,
+						<2 8 RK_FUNC_1 &pcfg_pull_none>;
+			};
+
+			rmii_pins: rmii-pins {
+				rockchip,pins = <2 14 RK_FUNC_1 &pcfg_pull_none>,
+						<2 12 RK_FUNC_1 &pcfg_pull_none>,
+						<2 25 RK_FUNC_1 &pcfg_pull_none>,
+						<2 19 RK_FUNC_1 &pcfg_pull_none_drv_12ma>,
+						<2 18 RK_FUNC_1 &pcfg_pull_none_drv_12ma>,
+						<2 13 RK_FUNC_1 &pcfg_pull_none_drv_12ma>,
+						<2 17 RK_FUNC_1 &pcfg_pull_none>,
+						<2 16 RK_FUNC_1 &pcfg_pull_none>,
+						<2 8 RK_FUNC_1 &pcfg_pull_none>,
+						<2 15 RK_FUNC_1 &pcfg_pull_none>;
+			};
+
+			phy_pins: phy-pins {
+				rockchip,pins = <2 14 RK_FUNC_2 &pcfg_pull_none>,
+						<2 8 RK_FUNC_2 &pcfg_pull_none>;
+			};
+		};
+
 		i2c0 {
 			i2c0_xfer: i2c0-xfer {
 				rockchip,pins = <0 0 RK_FUNC_1 &pcfg_pull_none>,
@@ -509,6 +609,20 @@
 			};
 		};
 
+		i2s1 {
+			i2s1_bus: i2s1-bus {
+				rockchip,pins = <0 8 RK_FUNC_1 &pcfg_pull_none>,
+						<0 9 RK_FUNC_1 &pcfg_pull_none>,
+						<0 11 RK_FUNC_1 &pcfg_pull_none>,
+						<0 12 RK_FUNC_1 &pcfg_pull_none>,
+						<0 13 RK_FUNC_1 &pcfg_pull_none>,
+						<0 14 RK_FUNC_1 &pcfg_pull_none>,
+						<1 2 RK_FUNC_1 &pcfg_pull_none>,
+						<1 4 RK_FUNC_1 &pcfg_pull_none>,
+						<1 5 RK_FUNC_1 &pcfg_pull_none>;
+			};
+		};
+
 		pwm0 {
 			pwm0_pin: pwm0-pin {
 				rockchip,pins = <3 21 RK_FUNC_1 &pcfg_pull_none>;
diff --git a/arch/arm/boot/dts/rk3288-firefly.dtsi b/arch/arm/boot/dts/rk3288-firefly.dtsi
index d6cf9ada13c9..114c90fb65e2 100644
--- a/arch/arm/boot/dts/rk3288-firefly.dtsi
+++ b/arch/arm/boot/dts/rk3288-firefly.dtsi
@@ -64,22 +64,6 @@
 		clock-output-names = "ext_gmac";
 	};
 
-	io_domains: io-domains {
-		compatible = "rockchip,rk3288-io-voltage-domain";
-		rockchip,grf = <&grf>;
-
-		audio-supply = <&vcca_33>;
-		bb-supply = <&vcc_io>;
-		dvp-supply = <&dovdd_1v8>;
-		flash0-supply = <&vcc_flash>;
-		flash1-supply = <&vcc_lan>;
-		gpio30-supply = <&vcc_io>;
-		gpio1830-supply = <&vcc_io>;
-		lcdc-supply = <&vcc_io>;
-		sdcard-supply = <&vccio_sd>;
-		wifi-supply = <&vccio_wl>;
-	};
-
 	ir: ir-receiver {
 		compatible = "gpio-ir-receiver";
 		pinctrl-names = "default";
@@ -397,6 +381,21 @@
 	status = "okay";
 };
 
+&io_domains {
+	status = "okay";
+
+	audio-supply = <&vcca_33>;
+	bb-supply = <&vcc_io>;
+	dvp-supply = <&dovdd_1v8>;
+	flash0-supply = <&vcc_flash>;
+	flash1-supply = <&vcc_lan>;
+	gpio30-supply = <&vcc_io>;
+	gpio1830-supply = <&vcc_io>;
+	lcdc-supply = <&vcc_io>;
+	sdcard-supply = <&vccio_sd>;
+	wifi-supply = <&vccio_wl>;
+};
+
 &pinctrl {
 	pcfg_output_high: pcfg-output-high {
 		output-high;
diff --git a/arch/arm/boot/dts/rk3288-miqi.dts b/arch/arm/boot/dts/rk3288-miqi.dts
index 8643103d8cd8..24488421f0f0 100644
--- a/arch/arm/boot/dts/rk3288-miqi.dts
+++ b/arch/arm/boot/dts/rk3288-miqi.dts
@@ -64,19 +64,6 @@
 		clock-output-names = "ext_gmac";
 	};
 
-	io_domains: io-domains {
-		compatible = "rockchip,rk3288-io-voltage-domain";
-
-		audio-supply = <&vcca_33>;
-		flash0-supply = <&vcc_flash>;
-		flash1-supply = <&vcc_lan>;
-		gpio30-supply = <&vcc_io>;
-		gpio1830-supply = <&vcc_io>;
-		lcdc-supply = <&vcc_io>;
-		sdcard-supply = <&vccio_sd>;
-		wifi-supply = <&vcc_18>;
-	};
-
 	leds {
 		compatible = "gpio-leds";
 
@@ -321,6 +308,19 @@
 	status = "okay";
 };
 
+&io_domains {
+	status = "okay";
+
+	audio-supply = <&vcca_33>;
+	flash0-supply = <&vcc_flash>;
+	flash1-supply = <&vcc_lan>;
+	gpio30-supply = <&vcc_io>;
+	gpio1830-supply = <&vcc_io>;
+	lcdc-supply = <&vcc_io>;
+	sdcard-supply = <&vccio_sd>;
+	wifi-supply = <&vcc_18>;
+};
+
 &pinctrl {
 	pcfg_output_high: pcfg-output-high {
 		output-high;
diff --git a/arch/arm/boot/dts/rk3288-popmetal.dts b/arch/arm/boot/dts/rk3288-popmetal.dts
index 720717bb3614..dda8d259bb6d 100644
--- a/arch/arm/boot/dts/rk3288-popmetal.dts
+++ b/arch/arm/boot/dts/rk3288-popmetal.dts
@@ -77,22 +77,6 @@
 		};
 	};
 
-	io_domains: io-domains {
-		compatible = "rockchip,rk3288-io-voltage-domain";
-		rockchip,grf = <&grf>;
-
-		audio-supply = <&vcca_33>;
-		bb-supply = <&vcc_io>;
-		dvp-supply = <&vcc18_dvp>;
-		flash0-supply = <&vcc_flash>;
-		flash1-supply = <&vcc_lan>;
-		gpio30-supply = <&vcc_io>;
-		gpio1830-supply = <&vcc_io>;
-		lcdc-supply = <&vcc_io>;
-		sdcard-supply = <&vccio_sd>;
-		wifi-supply = <&vccio_wl>;
-	};
-
 	ir: ir-receiver {
 		compatible = "gpio-ir-receiver";
 		gpios = <&gpio0 6 GPIO_ACTIVE_LOW>;
@@ -437,6 +421,21 @@
 	status = "okay";
 };
 
+&io_domains {
+	status = "okay";
+
+	audio-supply = <&vcca_33>;
+	bb-supply = <&vcc_io>;
+	dvp-supply = <&vcc18_dvp>;
+	flash0-supply = <&vcc_flash>;
+	flash1-supply = <&vcc_lan>;
+	gpio30-supply = <&vcc_io>;
+	gpio1830-supply = <&vcc_io>;
+	lcdc-supply = <&vcc_io>;
+	sdcard-supply = <&vccio_sd>;
+	wifi-supply = <&vccio_wl>;
+};
+
 &pinctrl {
 	ak8963 {
 		comp_int: comp-int {
diff --git a/arch/arm/boot/dts/rk3288-rock2-som.dtsi b/arch/arm/boot/dts/rk3288-rock2-som.dtsi
index e1ee9f949035..bb1f01e037ba 100644
--- a/arch/arm/boot/dts/rk3288-rock2-som.dtsi
+++ b/arch/arm/boot/dts/rk3288-rock2-som.dtsi
@@ -61,22 +61,6 @@
 		clock-output-names = "ext_gmac";
 	};
 
-	io_domains: io-domains {
-		compatible = "rockchip,rk3288-io-voltage-domain";
-		rockchip,grf = <&grf>;
-
-		audio-supply = <&vcc_io>;
-		bb-supply = <&vcc_io>;
-		dvp-supply = <&vcc_18>;
-		flash0-supply = <&vcc_flash>;
-		flash1-supply = <&vccio_pmu>;
-		gpio30-supply = <&vccio_pmu>;
-		gpio1830 = <&vcc_io>;
-		lcdc-supply = <&vcc_io>;
-		sdcard-supply = <&vccio_sd>;
-		wifi-supply = <&vcc_18>;
-	};
-
 	vcc_flash: flash-regulator {
 		compatible = "regulator-fixed";
 		regulator-name = "vcc_sys";
@@ -259,6 +243,21 @@
 	};
 };
 
+&io_domains {
+	status = "okay";
+
+	audio-supply = <&vcc_io>;
+	bb-supply = <&vcc_io>;
+	dvp-supply = <&vcc_18>;
+	flash0-supply = <&vcc_flash>;
+	flash1-supply = <&vccio_pmu>;
+	gpio30-supply = <&vccio_pmu>;
+	gpio1830 = <&vcc_io>;
+	lcdc-supply = <&vcc_io>;
+	sdcard-supply = <&vccio_sd>;
+	wifi-supply = <&vcc_18>;
+};
+
 &pinctrl {
 	pcfg_output_high: pcfg-output-high {
 		output-high;
diff --git a/arch/arm/boot/dts/rk3288-veyron-analog-audio.dtsi b/arch/arm/boot/dts/rk3288-veyron-analog-audio.dtsi
new file mode 100644
index 000000000000..6d105914a4f3
--- /dev/null
+++ b/arch/arm/boot/dts/rk3288-veyron-analog-audio.dtsi
@@ -0,0 +1,101 @@
+/*
+ * Google Veyron (and derivatives) fragment for the  max98090 audio
+ * codec and analog headphone jack.
+ *
+ * Copyright 2016 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+	sound {
+		compatible = "rockchip,rockchip-audio-max98090";
+		pinctrl-names = "default";
+		pinctrl-0 = <&mic_det>, <&hp_det>;
+		rockchip,model = "VEYRON-I2S";
+		rockchip,i2s-controller = <&i2s>;
+		rockchip,audio-codec = <&max98090>;
+		rockchip,hp-det-gpios = <&gpio6 5 GPIO_ACTIVE_HIGH>;
+		rockchip,mic-det-gpios = <&gpio6 11 GPIO_ACTIVE_LOW>;
+		rockchip,headset-codec = <&headsetcodec>;
+	};
+};
+
+&i2c2 {
+	max98090: max98090@10 {
+		compatible = "maxim,max98090";
+		reg = <0x10>;
+		interrupt-parent = <&gpio6>;
+		interrupts = <7 IRQ_TYPE_EDGE_FALLING>;
+		clock-names = "mclk";
+		clocks = <&cru SCLK_I2S0_OUT>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&int_codec>;
+	};
+};
+
+&i2c4 {
+	headsetcodec: ts3a227e@3b {
+		compatible = "ti,ts3a227e";
+		reg = <0x3b>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ts3a227e_int_l>;
+		ti,micbias = <7>;		/* MICBIAS = 2.8V */
+	};
+};
+
+&i2s {
+	status = "okay";
+};
+
+&io_domains {
+	audio-supply = <&vcc18_codec>;
+};
+
+&rk808 {
+	vcc10-supply = <&vcc33_sys>;
+
+	regulators {
+		vcc18_codec: LDO_REG6 {
+			regulator-name = "vcc18_codec";
+			regulator-always-on;
+			regulator-boot-on;
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-state-mem {
+				regulator-off-in-suspend;
+			};
+		};
+	};
+};
+
+&pinctrl {
+	codec {
+		hp_det: hp-det {
+			rockchip,pins = <6 5 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		/*
+		 * HACK: We're going to _pull down_ this _active low_ interrupt
+		 * so that it never fires.  We don't need this interrupt because
+		 * we've got a ts3a227e chip but the driver requires it.
+		 */
+		int_codec: int-codec {
+			rockchip,pins = <6 7 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+
+		mic_det: mic-det {
+			rockchip,pins = <6 11 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	headset {
+		ts3a227e_int_l: ts3a227e-int-l {
+			rockchip,pins = <0 3 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/rk3288-veyron-chromebook.dtsi b/arch/arm/boot/dts/rk3288-veyron-chromebook.dtsi
index 2958c36d12a0..ce1f87980bcb 100644
--- a/arch/arm/boot/dts/rk3288-veyron-chromebook.dtsi
+++ b/arch/arm/boot/dts/rk3288-veyron-chromebook.dtsi
@@ -46,6 +46,7 @@
 #include <dt-bindings/clock/rockchip,rk808.h>
 #include <dt-bindings/input/input.h>
 #include "rk3288-veyron.dtsi"
+#include "rk3288-veyron-analog-audio.dtsi"
 #include "rk3288-veyron-sdmmc.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/rk3288-veyron.dtsi b/arch/arm/boot/dts/rk3288-veyron.dtsi
index b2557bf5a58f..3dd2cca48c11 100644
--- a/arch/arm/boot/dts/rk3288-veyron.dtsi
+++ b/arch/arm/boot/dts/rk3288-veyron.dtsi
@@ -83,19 +83,6 @@
 		reset-gpios = <&gpio2 9 GPIO_ACTIVE_HIGH>;
 	};
 
-	io_domains: io-domains {
-		compatible = "rockchip,rk3288-io-voltage-domain";
-		rockchip,grf = <&grf>;
-
-		bb-supply = <&vcc33_io>;
-		dvp-supply = <&vcc_18>;
-		flash0-supply = <&vcc18_flashio>;
-		gpio1830-supply = <&vcc33_io>;
-		gpio30-supply = <&vcc33_io>;
-		lcdc-supply = <&vcc33_lcd>;
-		wifi-supply = <&vcc18_wl>;
-	};
-
 	sdio_pwrseq: sdio-pwrseq {
 		compatible = "mmc-pwrseq-simple";
 		clocks = <&rk808 RK808_CLKOUT1>;
@@ -355,6 +342,18 @@
 	i2c-scl-rising-time-ns = <1000>;
 };
 
+&io_domains {
+	status = "okay";
+
+	bb-supply = <&vcc33_io>;
+	dvp-supply = <&vcc_18>;
+	flash0-supply = <&vcc18_flashio>;
+	gpio1830-supply = <&vcc33_io>;
+	gpio30-supply = <&vcc33_io>;
+	lcdc-supply = <&vcc33_lcd>;
+	wifi-supply = <&vcc18_wl>;
+};
+
 &pwm1 {
 	status = "okay";
 };
@@ -383,6 +382,12 @@
 	status = "okay";
 
 	rx-sample-delay-ns = <12>;
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		spi-max-frequency = <50000000>;
+		reg = <0>;
+	};
 };
 
 &tsadc {
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 3ebee530f2b0..cd33f0170890 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -827,6 +827,11 @@
 			#phy-cells = <0>;
 			status = "disabled";
 		};
+
+		io_domains: io-domains {
+			compatible = "rockchip,rk3288-io-voltage-domain";
+			status = "disabled";
+		};
 	};
 
 	wdt: watchdog@ff800000 {
diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi
index 5dd2734e67ba..353d0e5ec83b 100644
--- a/arch/arm/boot/dts/sama5d2.dtsi
+++ b/arch/arm/boot/dts/sama5d2.dtsi
@@ -72,6 +72,11 @@
 		};
 	};
 
+	pmu {
+		compatible = "arm,cortex-a5-pmu";
+		interrupts = <2 IRQ_TYPE_LEVEL_HIGH 0>;
+	};
+
 	memory {
 		reg = <0x20000000 0x20000000>;
 	};
@@ -112,13 +117,13 @@
 			clock-names = "pclk", "hclk";
 			status = "disabled";
 
-			ep0 {
+			ep@0 {
 				reg = <0>;
 				atmel,fifo-size = <64>;
 				atmel,nb-banks = <1>;
 			};
 
-			ep1 {
+			ep@1 {
 				reg = <1>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <3>;
@@ -126,7 +131,7 @@
 				atmel,can-isoc;
 			};
 
-			ep2 {
+			ep@2 {
 				reg = <2>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <3>;
@@ -134,7 +139,7 @@
 				atmel,can-isoc;
 			};
 
-			ep3 {
+			ep@3 {
 				reg = <3>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -142,7 +147,7 @@
 				atmel,can-isoc;
 			};
 
-			ep4 {
+			ep@4 {
 				reg = <4>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -150,7 +155,7 @@
 				atmel,can-isoc;
 			};
 
-			ep5 {
+			ep@5 {
 				reg = <5>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -158,7 +163,7 @@
 				atmel,can-isoc;
 			};
 
-			ep6 {
+			ep@6 {
 				reg = <6>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -166,7 +171,7 @@
 				atmel,can-isoc;
 			};
 
-			ep7 {
+			ep@7 {
 				reg = <7>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -174,56 +179,56 @@
 				atmel,can-isoc;
 			};
 
-			ep8 {
+			ep@8 {
 				reg = <8>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep9 {
+			ep@9 {
 				reg = <9>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep10 {
+			ep@10 {
 				reg = <10>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep11 {
+			ep@11 {
 				reg = <11>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep12 {
+			ep@12 {
 				reg = <12>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep13 {
+			ep@13 {
 				reg = <13>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep14 {
+			ep@14 {
 				reg = <14>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep15 {
+			ep@15 {
 				reg = <15>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 36301bd9a14a..4c84d333fc7e 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -326,26 +326,22 @@
 				atmel,adc-res-names = "lowres", "highres";
 				status = "disabled";
 
-				trigger@0 {
-					reg = <0>;
+				trigger0 {
 					trigger-name = "external-rising";
 					trigger-value = <0x1>;
 					trigger-external;
 				};
-				trigger@1 {
-					reg = <1>;
+				trigger1 {
 					trigger-name = "external-falling";
 					trigger-value = <0x2>;
 					trigger-external;
 				};
-				trigger@2 {
-					reg = <2>;
+				trigger2 {
 					trigger-name = "external-any";
 					trigger-value = <0x3>;
 					trigger-external;
 				};
-				trigger@3 {
-					reg = <3>;
+				trigger3 {
 					trigger-name = "continuous";
 					trigger-value = <0x6>;
 				};
@@ -1341,13 +1337,13 @@
 			clock-names = "pclk", "hclk";
 			status = "disabled";
 
-			ep0 {
+			ep@0 {
 				reg = <0>;
 				atmel,fifo-size = <64>;
 				atmel,nb-banks = <1>;
 			};
 
-			ep1 {
+			ep@1 {
 				reg = <1>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <3>;
@@ -1355,7 +1351,7 @@
 				atmel,can-isoc;
 			};
 
-			ep2 {
+			ep@2 {
 				reg = <2>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <3>;
@@ -1363,84 +1359,84 @@
 				atmel,can-isoc;
 			};
 
-			ep3 {
+			ep@3 {
 				reg = <3>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-dma;
 			};
 
-			ep4 {
+			ep@4 {
 				reg = <4>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-dma;
 			};
 
-			ep5 {
+			ep@5 {
 				reg = <5>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-dma;
 			};
 
-			ep6 {
+			ep@6 {
 				reg = <6>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-dma;
 			};
 
-			ep7 {
+			ep@7 {
 				reg = <7>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-dma;
 			};
 
-			ep8 {
+			ep@8 {
 				reg = <8>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 			};
 
-			ep9 {
+			ep@9 {
 				reg = <9>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 			};
 
-			ep10 {
+			ep@10 {
 				reg = <10>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 			};
 
-			ep11 {
+			ep@11 {
 				reg = <11>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 			};
 
-			ep12 {
+			ep@12 {
 				reg = <12>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 			};
 
-			ep13 {
+			ep@13 {
 				reg = <13>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 			};
 
-			ep14 {
+			ep@14 {
 				reg = <14>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 			};
 
-			ep15 {
+			ep@15 {
 				reg = <15>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
diff --git a/arch/arm/boot/dts/sama5d31ek.dts b/arch/arm/boot/dts/sama5d31ek.dts
index 04eec0dfcf7d..25e4c0b2d786 100644
--- a/arch/arm/boot/dts/sama5d31ek.dts
+++ b/arch/arm/boot/dts/sama5d31ek.dts
@@ -9,6 +9,7 @@
 /dts-v1/;
 #include "sama5d31.dtsi"
 #include "sama5d3xmb.dtsi"
+#include "sama5d3xmb_emac.dtsi"
 #include "sama5d3xdm.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/sama5d33ek.dts b/arch/arm/boot/dts/sama5d33ek.dts
index cbd6a3ff1545..c517b87a1de2 100644
--- a/arch/arm/boot/dts/sama5d33ek.dts
+++ b/arch/arm/boot/dts/sama5d33ek.dts
@@ -9,6 +9,7 @@
 /dts-v1/;
 #include "sama5d33.dtsi"
 #include "sama5d3xmb.dtsi"
+#include "sama5d3xmb_gmac.dtsi"
 #include "sama5d3xdm.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/sama5d34ek.dts b/arch/arm/boot/dts/sama5d34ek.dts
index 878aa164275a..c8b8449fdc3e 100644
--- a/arch/arm/boot/dts/sama5d34ek.dts
+++ b/arch/arm/boot/dts/sama5d34ek.dts
@@ -9,6 +9,7 @@
 /dts-v1/;
 #include "sama5d34.dtsi"
 #include "sama5d3xmb.dtsi"
+#include "sama5d3xmb_gmac.dtsi"
 #include "sama5d3xdm.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/sama5d35ek.dts b/arch/arm/boot/dts/sama5d35ek.dts
index e812f5c1bf70..6e261fcf576c 100644
--- a/arch/arm/boot/dts/sama5d35ek.dts
+++ b/arch/arm/boot/dts/sama5d35ek.dts
@@ -9,6 +9,8 @@
 /dts-v1/;
 #include "sama5d35.dtsi"
 #include "sama5d3xmb.dtsi"
+#include "sama5d3xmb_emac.dtsi"
+#include "sama5d3xmb_gmac.dtsi"
 
 / {
 	model = "Atmel SAMA5D35-EK";
diff --git a/arch/arm/boot/dts/sama5d36ek.dts b/arch/arm/boot/dts/sama5d36ek.dts
index 59576c6f9826..cd458b85a205 100644
--- a/arch/arm/boot/dts/sama5d36ek.dts
+++ b/arch/arm/boot/dts/sama5d36ek.dts
@@ -10,6 +10,8 @@
 #include "sama5d36.dtsi"
 #include "sama5d3xmb.dtsi"
 #include "sama5d3xdm.dtsi"
+#include "sama5d3xmb_emac.dtsi"
+#include "sama5d3xmb_gmac.dtsi"
 
 / {
 	model = "Atmel SAMA5D36-EK";
diff --git a/arch/arm/boot/dts/sama5d3xcm.dtsi b/arch/arm/boot/dts/sama5d3xcm.dtsi
index 2cf9c3611db6..b5e111b29da1 100644
--- a/arch/arm/boot/dts/sama5d3xcm.dtsi
+++ b/arch/arm/boot/dts/sama5d3xcm.dtsi
@@ -34,40 +34,6 @@
 			spi0: spi@f0004000 {
 				cs-gpios = <&pioD 13 0>, <0>, <0>, <0>;
 			};
-
-			macb0: ethernet@f0028000 {
-				phy-mode = "rgmii";
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				ethernet-phy@1 {
-					reg = <0x1>;
-					interrupt-parent = <&pioB>;
-					interrupts = <25 IRQ_TYPE_EDGE_FALLING>;
-					txen-skew-ps = <800>;
-					txc-skew-ps = <3000>;
-					rxdv-skew-ps = <400>;
-					rxc-skew-ps = <3000>;
-					rxd0-skew-ps = <400>;
-					rxd1-skew-ps = <400>;
-					rxd2-skew-ps = <400>;
-					rxd3-skew-ps = <400>;
-				};
-
-				ethernet-phy@7 {
-					reg = <0x7>;
-					interrupt-parent = <&pioB>;
-					interrupts = <25 IRQ_TYPE_EDGE_FALLING>;
-					txen-skew-ps = <800>;
-					txc-skew-ps = <3000>;
-					rxdv-skew-ps = <400>;
-					rxc-skew-ps = <3000>;
-					rxd0-skew-ps = <400>;
-					rxd1-skew-ps = <400>;
-					rxd2-skew-ps = <400>;
-					rxd3-skew-ps = <400>;
-				};
-			};
 		};
 
 		nand0: nand@60000000 {
diff --git a/arch/arm/boot/dts/sama5d3xmb.dtsi b/arch/arm/boot/dts/sama5d3xmb.dtsi
index 89010422812d..6d252ad050f6 100644
--- a/arch/arm/boot/dts/sama5d3xmb.dtsi
+++ b/arch/arm/boot/dts/sama5d3xmb.dtsi
@@ -117,18 +117,6 @@
 				status = "okay";
 			};
 
-			macb1: ethernet@f802c000 {
-				phy-mode = "rmii";
-
-				#address-cells = <1>;
-				#size-cells = <0>;
-				phy0: ethernet-phy@1 {
-					interrupt-parent = <&pioE>;
-					interrupts = <30 IRQ_TYPE_EDGE_FALLING>;
-					reg = <1>;
-				};
-			};
-
 			pinctrl@fffff200 {
 				board {
 					pinctrl_mmc0_cd: mmc0_cd {
diff --git a/arch/arm/boot/dts/sama5d3xmb_emac.dtsi b/arch/arm/boot/dts/sama5d3xmb_emac.dtsi
new file mode 100644
index 000000000000..2fd14f371a04
--- /dev/null
+++ b/arch/arm/boot/dts/sama5d3xmb_emac.dtsi
@@ -0,0 +1,26 @@
+/*
+ * sama5d3xmb_emac.dts - Device Tree Include file for SAMA5D3x mother board
+ * Ethernet
+ *
+ *  Copyright (C) 2016 Atmel,
+ *
+ * Licensed under GPLv2 or later.
+ */
+
+/ {
+	ahb {
+		apb {
+			macb1: ethernet@f802c000 {
+				phy-mode = "rmii";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+				phy0: ethernet-phy@1 {
+					interrupt-parent = <&pioE>;
+					interrupts = <30 IRQ_TYPE_EDGE_FALLING>;
+					reg = <1>;
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/sama5d3xmb_gmac.dtsi b/arch/arm/boot/dts/sama5d3xmb_gmac.dtsi
new file mode 100644
index 000000000000..65aea7a75b1d
--- /dev/null
+++ b/arch/arm/boot/dts/sama5d3xmb_gmac.dtsi
@@ -0,0 +1,48 @@
+/*
+ * sama5d3xmb_gmac.dtsi - Device Tree Include file for SAMA5D3x motherboard
+ * Gigabit Ethernet
+ *
+ *  Copyright (C) 2016 Atmel,
+ *
+ * Licensed under GPLv2 or later.
+ */
+
+/ {
+	ahb {
+		apb {
+			macb0: ethernet@f0028000 {
+				phy-mode = "rgmii";
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				ethernet-phy@1 {
+					reg = <0x1>;
+					interrupt-parent = <&pioB>;
+					interrupts = <25 IRQ_TYPE_EDGE_FALLING>;
+					txen-skew-ps = <800>;
+					txc-skew-ps = <3000>;
+					rxdv-skew-ps = <400>;
+					rxc-skew-ps = <3000>;
+					rxd0-skew-ps = <400>;
+					rxd1-skew-ps = <400>;
+					rxd2-skew-ps = <400>;
+					rxd3-skew-ps = <400>;
+				};
+
+				ethernet-phy@7 {
+					reg = <0x7>;
+					interrupt-parent = <&pioB>;
+					interrupts = <25 IRQ_TYPE_EDGE_FALLING>;
+					txen-skew-ps = <800>;
+					txc-skew-ps = <3000>;
+					rxdv-skew-ps = <400>;
+					rxc-skew-ps = <3000>;
+					rxd0-skew-ps = <400>;
+					rxd1-skew-ps = <400>;
+					rxd2-skew-ps = <400>;
+					rxd3-skew-ps = <400>;
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index 4e2cc30d6615..65e725fb5679 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -135,13 +135,13 @@
 			clock-names = "pclk", "hclk";
 			status = "disabled";
 
-			ep0 {
+			ep@0 {
 				reg = <0>;
 				atmel,fifo-size = <64>;
 				atmel,nb-banks = <1>;
 			};
 
-			ep1 {
+			ep@1 {
 				reg = <1>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <3>;
@@ -149,7 +149,7 @@
 				atmel,can-isoc;
 			};
 
-			ep2 {
+			ep@2 {
 				reg = <2>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <3>;
@@ -157,7 +157,7 @@
 				atmel,can-isoc;
 			};
 
-			ep3 {
+			ep@3 {
 				reg = <3>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -165,7 +165,7 @@
 				atmel,can-isoc;
 			};
 
-			ep4 {
+			ep@4 {
 				reg = <4>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -173,7 +173,7 @@
 				atmel,can-isoc;
 			};
 
-			ep5 {
+			ep@5 {
 				reg = <5>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -181,7 +181,7 @@
 				atmel,can-isoc;
 			};
 
-			ep6 {
+			ep@6 {
 				reg = <6>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -189,7 +189,7 @@
 				atmel,can-isoc;
 			};
 
-			ep7 {
+			ep@7 {
 				reg = <7>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -197,56 +197,56 @@
 				atmel,can-isoc;
 			};
 
-			ep8 {
+			ep@8 {
 				reg = <8>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep9 {
+			ep@9 {
 				reg = <9>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep10 {
+			ep@10 {
 				reg = <10>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep11 {
+			ep@11 {
 				reg = <11>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep12 {
+			ep@12 {
 				reg = <12>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep13 {
+			ep@13 {
 				reg = <13>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep14 {
+			ep@14 {
 				reg = <14>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
 				atmel,can-isoc;
 			};
 
-			ep15 {
+			ep@15 {
 				reg = <15>;
 				atmel,fifo-size = <1024>;
 				atmel,nb-banks = <2>;
@@ -1226,22 +1226,22 @@
 				atmel,adc-ts-pressure-threshold = <10000>;
 				status = "disabled";
 
-				trigger@0 {
+				trigger0 {
 					trigger-name = "external-rising";
 					trigger-value = <0x1>;
 					trigger-external;
 				};
-				trigger@1 {
+				trigger1 {
 					trigger-name = "external-falling";
 					trigger-value = <0x2>;
 					trigger-external;
 				};
-				trigger@2 {
+				trigger2 {
 					trigger-name = "external-any";
 					trigger-value = <0x3>;
 					trigger-external;
 				};
-				trigger@3 {
+				trigger3 {
 					trigger-name = "continuous";
 					trigger-value = <0x6>;
 				};
diff --git a/arch/arm/boot/dts/sh73a0-kzm9g.dts b/arch/arm/boot/dts/sh73a0-kzm9g.dts
index c2d8a080e392..3d65f1f6d78b 100644
--- a/arch/arm/boot/dts/sh73a0-kzm9g.dts
+++ b/arch/arm/boot/dts/sh73a0-kzm9g.dts
@@ -22,7 +22,7 @@
 	compatible = "renesas,kzm9g", "renesas,sh73a0";
 
 	aliases {
-		serial4 = &scifa4;
+		serial0 = &scifa4;
 	};
 
 	cpus {
@@ -39,16 +39,16 @@
 	};
 
 	chosen {
-		bootargs = "console=tty0 console=ttySC4,115200 root=/dev/nfs ip=dhcp ignore_loglevel rw";
-		stdout-path = &scifa4;
+		bootargs = "root=/dev/nfs ip=dhcp ignore_loglevel rw";
+		stdout-path = "serial0:115200n8";
 	};
 
-	memory {
+	memory@40000000 {
 		device_type = "memory";
 		reg = <0x40000000 0x20000000>;
 	};
 
-	reg_1p8v: regulator@0 {
+	reg_1p8v: regulator-1p8v {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-1.8V";
 		regulator-min-microvolt = <1800000>;
@@ -57,7 +57,7 @@
 		regulator-boot-on;
 	};
 
-	reg_3p3v: regulator@1 {
+	reg_3p3v: regulator-3p3v {
 		compatible = "regulator-fixed";
 		regulator-name = "fixed-3.3V";
 		regulator-min-microvolt = <3300000>;
@@ -66,7 +66,7 @@
 		regulator-boot-on;
 	};
 
-	vmmc_sdhi0: regulator@2 {
+	vmmc_sdhi0: regulator-vmmc-sdhi0 {
 		compatible = "regulator-fixed";
 		regulator-name = "SDHI0 Vcc";
 		regulator-min-microvolt = <3300000>;
@@ -75,7 +75,7 @@
 		enable-active-high;
 	};
 
-	vmmc_sdhi2: regulator@3 {
+	vmmc_sdhi2: regulator-vmmc-sdhi2 {
 		compatible = "regulator-fixed";
 		regulator-name = "SDHI2 Vcc";
 		regulator-min-microvolt = <3300000>;
@@ -352,7 +352,7 @@
 		};
 	};
 
-	scifa4_pins: serial4 {
+	scifa4_pins: scifa4 {
 		groups = "scifa4_data", "scifa4_ctrl";
 		function = "scifa4";
 	};
@@ -378,6 +378,7 @@
 	pinctrl-0 = <&scifa4_pins>;
 	pinctrl-names = "default";
 
+	uart-has-rtscts;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/sh73a0.dtsi b/arch/arm/boot/dts/sh73a0.dtsi
index c4f434cdec60..032fe2f14b16 100644
--- a/arch/arm/boot/dts/sh73a0.dtsi
+++ b/arch/arm/boot/dts/sh73a0.dtsi
@@ -55,7 +55,7 @@
 		      <0xf0000100 0x100>;
 	};
 
-	L2: cache-controller {
+	L2: cache-controller@f0100000 {
 		compatible = "arm,pl310-cache";
 		reg = <0xf0100000 0x1000>;
 		interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index 5820b70c95b3..94000cbe576b 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -22,11 +22,6 @@
 	#address-cells = <1>;
 	#size-cells = <1>;
 
-	aliases {
-		serial0 = &uart0;
-		serial1 = &uart1;
-	};
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -572,12 +567,6 @@
 			reg = <0xffcfb100 0x80>;
 		};
 
-		sdramedac {
-			compatible = "altr,sdram-edac-a10";
-			altr,sdr-syscon = <&sdr>;
-			interrupts = <0 2 4>, <0 0 4>;
-		};
-
 		L2: l2-cache@fffff000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffff000 0x1000>;
@@ -610,16 +599,29 @@
 			#size-cells = <1>;
 			interrupts = <0 2 IRQ_TYPE_LEVEL_HIGH>,
 				     <0 0 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
 			ranges;
 
+			sdramedac {
+				compatible = "altr,sdram-edac-a10";
+				altr,sdr-syscon = <&sdr>;
+				interrupts = <17 IRQ_TYPE_LEVEL_HIGH>,
+					     <49 IRQ_TYPE_LEVEL_HIGH>;
+			};
+
 			l2-ecc@ffd06010 {
 				compatible = "altr,socfpga-a10-l2-ecc";
 				reg = <0xffd06010 0x4>;
+				interrupts = <0 IRQ_TYPE_LEVEL_HIGH>,
+					     <32 IRQ_TYPE_LEVEL_HIGH>;
 			};
 
 			ocram-ecc@ff8c3000 {
 				compatible = "altr,socfpga-a10-ocram-ecc";
 				reg = <0xff8c3000 0x400>;
+				interrupts = <1 IRQ_TYPE_LEVEL_HIGH>,
+					     <33 IRQ_TYPE_LEVEL_HIGH>;
 			};
 
 			emac0-rx-ecc@ff8c0800 {
diff --git a/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi b/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi
index 567df98f1bb5..8e3a4adc389f 100644
--- a/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10_socdk.dtsi
@@ -20,9 +20,14 @@
 	model = "Altera SOCFPGA Arria 10";
 	compatible = "altr,socfpga-arria10", "altr,socfpga";
 
+	aliases {
+		ethernet0 = &gmac0;
+		serial0 = &uart1;
+	};
+
 	chosen {
 		bootargs = "earlyprintk";
-		stdout-path = "serial1:115200n8";
+		stdout-path = "serial0:115200n8";
 	};
 
 	memory {
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts b/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts
index e1a61f20873f..d79853775061 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts
@@ -52,7 +52,7 @@
 	status = "okay";
 
 	rtc: rtc@68 {
-		compatible = "stm,m41t82";
+		compatible = "st,m41t82";
 		reg = <0x68>;
 	};
 };
diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi
index 6ae56838bd3a..d309314f3a36 100644
--- a/arch/arm/boot/dts/ste-dbx5x0.dtsi
+++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi
@@ -604,6 +604,7 @@
 				#interrupt-cells = <2>;
 
 				ab8500_gpio: ab8500-gpio {
+					compatible = "stericsson,ab8500-gpio";
 					gpio-controller;
 					#gpio-cells = <2>;
 				};
diff --git a/arch/arm/boot/dts/ste-href-tvk1281618.dtsi b/arch/arm/boot/dts/ste-href-tvk1281618.dtsi
index fc5e8ce700c3..3c9f2f068c2f 100644
--- a/arch/arm/boot/dts/ste-href-tvk1281618.dtsi
+++ b/arch/arm/boot/dts/ste-href-tvk1281618.dtsi
@@ -99,46 +99,69 @@
 				vddio-supply = <&db8500_vsmps2_reg>;
 				pinctrl-names = "default";
 				pinctrl-0 = <&accel_tvk_mode>;
-				interrupt-parent = <&gpio2>;
-				interrupts = <18 IRQ_TYPE_EDGE_FALLING>,
-					     <19 IRQ_TYPE_EDGE_FALLING>;
-			};
-			lsm303dlh@1e {
 				/*
-				 * This magnetometer is packaged with
-				 * the accelerometer, and has a DRDY line,
-				 * however it is not connected on this
-				 * board so it can not generate interrupts.
+				 * These interrupts cannot be used: the other component
+				 * ST-Micro L3D4200D gyro that is connected to the same lines
+				 * cannot set its DRDY line to open drain, so it cannot be
+				 * shared with other peripherals. The should be defined for
+				 * the falling edge if they could be wired together.
+				 *
+				 * interrupts-extended =
+				 * <&gpio1 0 IRQ_TYPE_EDGE_FALLING>,
+				 * <&gpio2 19 IRQ_TYPE_EDGE_FALLING>;
 				 */
+			};
+			lsm303dlh@1e {
+				/* Magnetometer */
 				compatible = "st,lsm303dlh-magn";
 				reg = <0x1e>;
 				vdd-supply = <&ab8500_ldo_aux1_reg>;
 				vddio-supply = <&db8500_vsmps2_reg>;
+				/*
+				 * These interrupts cannot be used: the other component
+				 * ST-Micro L3D4200D gyro that is connected to the same lines
+				 * cannot set its DRDY line to open drain, so it cannot be
+				 * shared with other peripherals. The should be defined for
+				 * the falling edge if they could be wired together.
+				 *
+				 * interrupts-extended =
+				 * <&gpio1 0 IRQ_TYPE_EDGE_FALLING>,
+				 * <&gpio2 19 IRQ_TYPE_EDGE_FALLING>;
+				 */
 			};
 			lis331dl@1c {
 				/* Accelerometer */
 				compatible = "st,lis331dl-accel";
 				st,drdy-int-pin = <1>;
-				drive-open-drain;
 				reg = <0x1c>;
 				vdd-supply = <&ab8500_ldo_aux1_reg>;
 				vddio-supply = <&db8500_vsmps2_reg>;
 				pinctrl-names = "default";
 				pinctrl-0 = <&accel_tvk_mode>;
 				interrupt-parent = <&gpio2>;
-				interrupts = <18 IRQ_TYPE_EDGE_FALLING>,
-					     <19 IRQ_TYPE_EDGE_FALLING>;
+				/* INT2 would need to be open drain */
+				interrupts = <18 IRQ_TYPE_EDGE_RISING>,
+					     <19 IRQ_TYPE_EDGE_RISING>;
 			};
 			ak8974@0f {
 				/* Magnetometer */
 				compatible = "asahi-kasei,ak8974";
 				reg = <0x0f>;
-				vdd-supply = <&ab8500_ldo_aux1_reg>;
-				vddio-supply = <&db8500_vsmps2_reg>;
+				avdd-supply = <&ab8500_ldo_aux1_reg>;
+				dvdd-supply = <&db8500_vsmps2_reg>;
 				pinctrl-names = "default";
 				pinctrl-0 = <&gyro_magn_tvk_mode>;
-				interrupt-parent = <&gpio1>;
-				interrupts = <0 IRQ_TYPE_EDGE_RISING>;
+				/*
+				 * These interrupts cannot be used: the other component
+				 * ST-Micro L3D4200D gyro that is connected to the same lines
+				 * cannot set its DRDY line to open drain, so it cannot be
+				 * shared with other peripherals. The should be defined for
+				 * the falling edge if they could be wired together.
+				 *
+				 * interrupts-extended =
+				 * <&gpio1 0 IRQ_TYPE_EDGE_FALLING>,
+				 * <&gpio0 31 IRQ_TYPE_EDGE_FALLING>;
+				 */
 			};
 			l3g4200d@68 {
 				/* Gyroscope */
@@ -149,8 +172,9 @@
 				vddio-supply = <&db8500_vsmps2_reg>;
 				pinctrl-names = "default";
 				pinctrl-0 = <&gyro_magn_tvk_mode>;
-				interrupt-parent = <&gpio1>;
-				interrupts = <0 IRQ_TYPE_EDGE_RISING>;
+				interrupts-extended =
+				<&gpio1 0 IRQ_TYPE_EDGE_RISING>,
+				<&gpio0 31 IRQ_TYPE_EDGE_RISING>;
 			};
 			lsp001wm@5c {
 				/* Barometer/pressure sensor */
@@ -218,7 +242,7 @@
 					/* Accelerometer interrupt lines 1 & 2 */
 					tvk_cfg {
 						pins = "GPIO82_C1", "GPIO83_D3";
-						ste,config = <&gpio_in_pu>;
+						ste,config = <&gpio_in_pd>;
 					};
 				};
 			};
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index 6d8ce154347e..48dc38482633 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -223,7 +223,6 @@
 		prcmu@80157000 {
 			ab8500 {
 				ab8500-gpio {
-					compatible = "stericsson,ab8500-gpio";
 				};
 
 				ab8500-regulators {
diff --git a/arch/arm/boot/dts/ste-hrefv60plus.dtsi b/arch/arm/boot/dts/ste-hrefv60plus.dtsi
index 45d7af326718..7187676836be 100644
--- a/arch/arm/boot/dts/ste-hrefv60plus.dtsi
+++ b/arch/arm/boot/dts/ste-hrefv60plus.dtsi
@@ -18,6 +18,126 @@
 	compatible = "st-ericsson,hrefv60+", "st-ericsson,u8500";
 
 	soc {
+		/* Name the GPIO muxed rails on the HREF boards */
+		gpio@8012e000 {
+			/* GPIOs 0 - 31 */
+			gpio-line-names =
+				     /* GPIO0,1 used for UART0 BT RX/TX */
+				     "", "",
+				     "UART_WAKE",
+				     "BT_WAKE",
+				     "",
+				     "SDMMC_1V8_3V_SEL",
+				     "FLASH_LED_SYNC (FLASH_CTRL_0)",
+				     "XENON_READY (FLASH_CTRL_1)",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "",
+				     "",
+				     "FLASH_LED_EN (FLASH_CTRL_3)",
+				     "", "",
+				     "", "", "", "", "",
+				     /* Used by UART2 (console) */
+				     "", "",
+				     "MAGNETOMETER_INT";
+		};
+
+		gpio@8012e080 {
+			/* GPIOs 32 - 63 */
+			gpio-line-names =
+				     "MAGNETOMETER_DRDY",
+				     "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "";
+		};
+
+		gpio@8000e000 {
+			/* GPIOs 64 - 95 */
+			gpio-line-names = "XENON_EN2 (FLASH_CTRL_4)",
+				     "DISP1_RST",
+				     "DISP2_RST",
+				     "TOUCH_INT2",
+				     "LCD_VSI0_A",
+				     "LCD_VSI1_A",
+				     /* GPIO 70-77 used for ETM */
+				     "", "", "", "", "", "", "", "",
+				     /* GPIO 78-81 used for YCBCR */
+				     "", "", "", "",
+				     "ACCELEROMETER_INT1_RDY",
+				     "ACCELEROMETER_INT2",
+				     "TOUCH_INT",
+				     "WLAN_ENA",
+				     "", "", "", "", "",
+				     "FORCE_SENSING_INT",
+				     "FORCE_SENSING_RESET",
+				     "", "",
+				     "SDMMC_CD";
+		};
+
+		gpio@8000e080 {
+			/* GPIOs 96 - 127 */
+			gpio-line-names = "",
+				     "FORCE_SENSING_WU",
+				     "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "";
+		};
+
+		gpio@8000e100 {
+			/* GPIOs 128 - 159 */
+			gpio-line-names = "", "", "", "", "", "", "", "",
+				     "", "", "",
+				     "DIPRO_INT", /* GPIO139 */
+				     "XSHUTDOWN_SECONDARY_SENSOR",
+				     "XSHUTDOWN_PRIMARY_SENSOR",
+				     "NFC_RST (NFC_CTRL_",
+				     "TOUCH_RST",
+				     "NFC_IRQ (NFC_CTRL_1)",
+				     "HAL_SW",
+				     "TOUCH_RST2",
+				     "", "",
+				     "VAUDIO_HF_EN", /* GPIO149 */
+				     "", "", "", "", "", "", "", "", "", "";
+		};
+
+		gpio@8000e180 {
+			/* GPIOs 160 - 191 */
+			gpio-line-names = "", "", "", "", "", "", "", "",
+				     "",
+				     "SDMMC_EN",
+				     "XENON_CHARGE (FLASH_CONTROL_5)",
+				     "GBF_ENA_RESET",
+				     "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "";
+		};
+
+		gpio@8011e000 {
+			/* GPIOs 192 - 223 */
+			gpio-line-names = "HDTV_INTN",
+				     "", "", "",
+				     "HDTV_RSTN",
+				     "", "", "",
+				     "", /* GPIO200 */
+				     "", "", "", "", "", "", "",
+				     /* GPIO208-216 used for WGBF_MC1 */
+				     "", "", "", "", "", "", "", "", "",
+				     "SW_FRONT_PROXIMITY", /* GPIO217 */
+				     "KPD_CTRL_INT", /* Keypad controller */
+				     "", "", "", "", "";
+		};
+
+		gpio@8011e080 {
+			/* GPIOs 224 - 255 */
+			gpio-line-names = "", "",
+				     "HSIT_ACWAKE0",
+				     "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "";
+		};
+
 		// External Micro SD slot
 		sdi0_per1@80126000 {
 			cd-gpios  = <&gpio2 31 GPIO_ACTIVE_HIGH>; // 95
diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index 36e84efc401c..b3df1c60d465 100644
--- a/arch/arm/boot/dts/ste-snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -95,6 +95,70 @@
 	};
 
 	soc {
+		/* Name the GPIO muxed rails on the Snowball board */
+		gpio@8012e000 {
+			/* GPIOs 0 - 31 */
+			gpio-line-names = "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "",
+				     "AP_GPIO31";
+		};
+
+		gpio@8012e080 {
+			/* GPIOs 32 - 63 */
+			gpio-line-names = "USR PB", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "";
+		};
+
+		gpio@8000e000 {
+			/* GPIOs 64 - 95 */
+			gpio-line-names = "", "", "", "", "AP_GPIO68", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "";
+		};
+
+		gpio@8000e100 {
+			/* GPIOs 128 - 159 */
+			gpio-line-names = "", "", "", "", "", "", "", "",
+				     "", "", "", "", "IRQ_LAN", "RSTn_LAN",
+				     "USR_LED", "", "", "", "", "", "",
+				     "", "", "AP_GPIO151", "AP_GPIO152",
+				     "", "", "", "", "", "", "";
+		};
+
+		gpio@8000e180 {
+			/* GPIOs 160 - 191 */
+			gpio-line-names = "", "AP_GPIO161", "AP_GPIO162",
+				     "ACCELEROMETER_INT1_RDY",
+				     "ACCELEROMETER_INT2", "MAG_DRDY",
+				     "GYRO_DRDY", "RSTn_MLC", "RSTn_SLC",
+				     "GYRO_INT", "UART_WAKE", "GBF_RESET",
+				     "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "";
+		};
+
+		gpio@8011e000 {
+			/* GPIOs 192 - 223 */
+			gpio-line-names = "HDTV_INTn", "", "", "", "HDTV_RST",
+				     "", "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "", "",
+				     "WLAN_RESETN", "WLAN_IRQ", "MMC_EN",
+				     "MMC_CD", "", "", "", "", "";
+		};
+
+		gpio@8011e080 {
+			/* GPIOs 224 - 255 */
+			gpio-line-names = "", "", "", "", "SD_SEL", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "",
+				     "", "", "", "", "", "", "", "";
+		};
+
 		usb_per5@a03e0000 {
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&musb_default_mode>;
@@ -352,7 +416,25 @@
 
 			ab8500 {
 				ab8500-gpio {
-					compatible = "stericsson,ab8500-gpio";
+					/*
+					 * AB8500 GPIOs are numbered starting from 1, so the first
+					 * index 0 is what in the datasheet is called "GPIO1", and
+					 * the second is "GPIO2" and so forth. Confusingly, the
+					 * Snowball schematic then names the "GPIO2" line "PM_GPIO1".
+					 * while later naming "GPIO4" as "PM_GPIO4".
+					 */
+					gpio-line-names = "", /* AB8500 GPIO1 */
+						     "PM_GPIO1", /* AB8500 GPIO2 */
+						     "WLAN_CLK_REQ", /* AB8500 GPIO3 */
+						     "PM_GPIO4", /* AB8500 GPIO4 */
+						     "", "", "", "", "", "", "", "", "", "", "",
+						     "EN_3V6", /* AB8500 GPIO16 */
+						     "", "", "", "" ,"", "", "", "", "",
+						     "EN_3V3", /* AB8500 GPIO26 */
+						     "", "", "", "", "", "", "", "", "", "", "", "", "",
+						     "PM_GPIO40", /* AB8500 GPIO40 */
+						     "PM_GPIO41", /* AB8500 GPIO41 */
+						     "PM_GPIO42"; /* AB8500 GPIO42 */
 				};
 
 				ext_regulators: ab8500-ext-regulators {
diff --git a/arch/arm/boot/dts/stih410-clock.dtsi b/arch/arm/boot/dts/stih410-clock.dtsi
index d1f2acafc9b6..fd5049682181 100644
--- a/arch/arm/boot/dts/stih410-clock.dtsi
+++ b/arch/arm/boot/dts/stih410-clock.dtsi
@@ -103,6 +103,7 @@
 				clocks = <&clk_sysin>;
 
 				clock-output-names = "clk-s-a0-pll-ofd-0";
+				clock-critical = <0>; /* clk-s-a0-pll-ofd-0 */
 			};
 
 			clk_s_a0_flexgen: clk-s-a0-flexgen {
@@ -115,6 +116,7 @@
 
 				clock-output-names = "clk-ic-lmi0",
 						     "clk-ic-lmi1";
+				clock-critical = <CLK_IC_LMI0>;
 			};
 		};
 
@@ -129,6 +131,7 @@
 					     "clk-s-c0-fs0-ch1",
 					     "clk-s-c0-fs0-ch2",
 					     "clk-s-c0-fs0-ch3";
+			clock-critical = <0>; /* clk-s-c0-fs0-ch0 */
 		};
 
 		clk_s_c0: clockgen-c@09103000 {
@@ -142,6 +145,7 @@
 				clocks = <&clk_sysin>;
 
 				clock-output-names = "clk-s-c0-pll0-odf-0";
+				clock-critical = <0>; /* clk-s-c0-pll0-odf-0 */
 			};
 
 			clk_s_c0_pll1: clk-s-c0-pll1 {
@@ -204,6 +208,11 @@
 						     "clk-clust-hades",
 						     "clk-hwpe-hades",
 						     "clk-fc-hades";
+				clock-critical = <CLK_ICN_CPU>,
+						 <CLK_TX_ICN_DMU>,
+						 <CLK_EXT2F_A9>,
+						 <CLK_ICN_LMI>,
+						 <CLK_ICN_SBC>;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/sun4i-a10-a1000.dts b/arch/arm/boot/dts/sun4i-a10-a1000.dts
index c92a1ae33a1e..39e368ec3428 100644
--- a/arch/arm/boot/dts/sun4i-a10-a1000.dts
+++ b/arch/arm/boot/dts/sun4i-a10-a1000.dts
@@ -72,8 +72,9 @@
 		};
 
 		blue {
-			label = "a1000:blue:usr";
+			label = "a1000:blue:pwr";
 			gpios = <&pio 7 20 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
 		};
 	};
 
@@ -84,6 +85,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 15 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/sun4i-a10-hackberry.dts b/arch/arm/boot/dts/sun4i-a10-hackberry.dts
index 2b17c5199151..6de83a6187d0 100644
--- a/arch/arm/boot/dts/sun4i-a10-hackberry.dts
+++ b/arch/arm/boot/dts/sun4i-a10-hackberry.dts
@@ -66,6 +66,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
index 7afc7a64eef1..e28f080b1fd5 100644
--- a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
+++ b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
@@ -80,6 +80,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>;   /* PH19 */
 	};
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index ca58eb279d55..7e7dfc2b43db 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -65,9 +65,9 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0-hdmi";
-			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
-				 <&ahb_gates 43>, <&ahb_gates 44>,
-				 <&dram_gates 26>;
+			clocks = <&ahb_gates 36>, <&ahb_gates 43>,
+				 <&ahb_gates 44>, <&de_be0_clk>,
+				 <&tcon0_ch1_clk>, <&dram_gates 26>;
 			status = "disabled";
 		};
 
@@ -75,9 +75,9 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_fe0-de_be0-lcd0-hdmi";
-			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
-				 <&ahb_gates 43>, <&ahb_gates 44>,
-				 <&ahb_gates 46>,
+			clocks = <&ahb_gates 36>, <&ahb_gates 43>,
+				 <&ahb_gates 44>, <&ahb_gates 46>,
+				 <&de_be0_clk>, <&de_fe0_clk>, <&tcon0_ch1_clk>,
 				 <&dram_gates 25>, <&dram_gates 26>;
 			status = "disabled";
 		};
@@ -86,8 +86,8 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_fe0-de_be0-lcd0";
-			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
-				 <&ahb_gates 44>, <&ahb_gates 46>,
+			clocks = <&ahb_gates 36>, <&ahb_gates 44>, <&ahb_gates 46>,
+				 <&de_be0_clk>, <&de_fe0_clk>, <&tcon0_ch0_clk>,
 				 <&dram_gates 25>, <&dram_gates 26>;
 			status = "disabled";
 		};
@@ -96,10 +96,11 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_fe0-de_be0-lcd0-tve0";
-			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>,
-				 <&ahb_gates 36>, <&ahb_gates 44>,
-				 <&ahb_gates 46>,
-				 <&dram_gates 5>, <&dram_gates 25>, <&dram_gates 26>;
+			clocks = <&ahb_gates 34>, <&ahb_gates 36>,
+				 <&ahb_gates 44>, <&ahb_gates 46>,
+				 <&de_be0_clk>, <&de_fe0_clk>,
+				 <&tcon0_ch1_clk>, <&dram_gates 5>,
+				 <&dram_gates 25>, <&dram_gates 26>;
 			status = "disabled";
 		};
 	};
@@ -577,6 +578,81 @@
 					     "dram_de_mp", "dram_ace";
 		};
 
+		de_be0_clk: clk@01c20104 {
+			#clock-cells = <0>;
+			#reset-cells = <0>;
+			compatible = "allwinner,sun4i-a10-display-clk";
+			reg = <0x01c20104 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll5 1>;
+			clock-output-names = "de-be0";
+		};
+
+		de_be1_clk: clk@01c20108 {
+			#clock-cells = <0>;
+			#reset-cells = <0>;
+			compatible = "allwinner,sun4i-a10-display-clk";
+			reg = <0x01c20108 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll5 1>;
+			clock-output-names = "de-be1";
+		};
+
+		de_fe0_clk: clk@01c2010c {
+			#clock-cells = <0>;
+			#reset-cells = <0>;
+			compatible = "allwinner,sun4i-a10-display-clk";
+			reg = <0x01c2010c 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll5 1>;
+			clock-output-names = "de-fe0";
+		};
+
+		de_fe1_clk: clk@01c20110 {
+			#clock-cells = <0>;
+			#reset-cells = <0>;
+			compatible = "allwinner,sun4i-a10-display-clk";
+			reg = <0x01c20110 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll5 1>;
+			clock-output-names = "de-fe1";
+		};
+
+
+		tcon0_ch0_clk: clk@01c20118 {
+			#clock-cells = <0>;
+			#reset-cells = <1>;
+			compatible = "allwinner,sun4i-a10-tcon-ch0-clk";
+			reg = <0x01c20118 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll3x2>, <&pll7x2>;
+			clock-output-names = "tcon0-ch0-sclk";
+
+		};
+
+		tcon1_ch0_clk: clk@01c2011c {
+			#clock-cells = <0>;
+			#reset-cells = <1>;
+			compatible = "allwinner,sun4i-a10-tcon-ch1-clk";
+			reg = <0x01c2011c 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll3x2>, <&pll7x2>;
+			clock-output-names = "tcon1-ch0-sclk";
+
+		};
+
+		tcon0_ch1_clk: clk@01c2012c {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-a10-tcon-ch0-clk";
+			reg = <0x01c2012c 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll3x2>, <&pll7x2>;
+			clock-output-names = "tcon0-ch1-sclk";
+
+		};
+
+		tcon1_ch1_clk: clk@01c20130 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-a10-tcon-ch1-clk";
+			reg = <0x01c20130 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll3x2>, <&pll7x2>;
+			clock-output-names = "tcon1-ch1-sclk";
+
+		};
+
 		ve_clk: clk@01c2013c {
 			#clock-cells = <0>;
 			#reset-cells = <0>;
@@ -645,6 +721,19 @@
 			#dma-cells = <2>;
 		};
 
+		nfc: nand@01c03000 {
+			compatible = "allwinner,sun4i-a10-nand";
+			reg = <0x01c03000 0x1000>;
+			interrupts = <37>;
+			clocks = <&ahb_gates 13>, <&nand_clk>;
+			clock-names = "ahb", "mod";
+			dmas = <&dma SUN4I_DMA_DEDICATED 3>;
+			dma-names = "rxtx";
+			status = "disabled";
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
 		spi0: spi@01c05000 {
 			compatible = "allwinner,sun4i-a10-spi";
 			reg = <0x01c05000 0x1000>;
@@ -884,69 +973,62 @@
 			#interrupt-cells = <3>;
 			#gpio-cells = <3>;
 
-			pwm0_pins_a: pwm0@0 {
-				allwinner,pins = "PB2";
-				allwinner,function = "pwm";
-				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
-			};
-
-			pwm1_pins_a: pwm1@0 {
-				allwinner,pins = "PI3";
-				allwinner,function = "pwm";
+			emac_pins_a: emac0@0 {
+				allwinner,pins = "PA0", "PA1", "PA2",
+						"PA3", "PA4", "PA5", "PA6",
+						"PA7", "PA8", "PA9", "PA10",
+						"PA11", "PA12", "PA13", "PA14",
+						"PA15", "PA16";
+				allwinner,function = "emac";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart0_pins_a: uart0@0 {
-				allwinner,pins = "PB22", "PB23";
-				allwinner,function = "uart0";
+			i2c0_pins_a: i2c0@0 {
+				allwinner,pins = "PB0", "PB1";
+				allwinner,function = "i2c0";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart0_pins_b: uart0@1 {
-				allwinner,pins = "PF2", "PF4";
-				allwinner,function = "uart0";
+			i2c1_pins_a: i2c1@0 {
+				allwinner,pins = "PB18", "PB19";
+				allwinner,function = "i2c1";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart1_pins_a: uart1@0 {
-				allwinner,pins = "PA10", "PA11";
-				allwinner,function = "uart1";
+			i2c2_pins_a: i2c2@0 {
+				allwinner,pins = "PB20", "PB21";
+				allwinner,function = "i2c2";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			i2c0_pins_a: i2c0@0 {
-				allwinner,pins = "PB0", "PB1";
-				allwinner,function = "i2c0";
+			ir0_rx_pins_a: ir0@0 {
+				allwinner,pins = "PB4";
+				allwinner,function = "ir0";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			i2c1_pins_a: i2c1@0 {
-				allwinner,pins = "PB18", "PB19";
-				allwinner,function = "i2c1";
+			ir0_tx_pins_a: ir0@1 {
+				allwinner,pins = "PB3";
+				allwinner,function = "ir0";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			i2c2_pins_a: i2c2@0 {
-				allwinner,pins = "PB20", "PB21";
-				allwinner,function = "i2c2";
+			ir1_rx_pins_a: ir1@0 {
+				allwinner,pins = "PB23";
+				allwinner,function = "ir1";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			emac_pins_a: emac0@0 {
-				allwinner,pins = "PA0", "PA1", "PA2",
-						"PA3", "PA4", "PA5", "PA6",
-						"PA7", "PA8", "PA9", "PA10",
-						"PA11", "PA12", "PA13", "PA14",
-						"PA15", "PA16";
-				allwinner,function = "emac";
+			ir1_tx_pins_a: ir1@1 {
+				allwinner,pins = "PB22";
+				allwinner,function = "ir1";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
@@ -966,34 +1048,41 @@
 				allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
 			};
 
-			ir0_rx_pins_a: ir0@0 {
-				allwinner,pins = "PB4";
-				allwinner,function = "ir0";
+			ps20_pins_a: ps20@0 {
+				allwinner,pins = "PI20", "PI21";
+				allwinner,function = "ps2";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ir0_tx_pins_a: ir0@1 {
-				allwinner,pins = "PB3";
-				allwinner,function = "ir0";
+			ps21_pins_a: ps21@0 {
+				allwinner,pins = "PH12", "PH13";
+				allwinner,function = "ps2";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ir1_rx_pins_a: ir1@0 {
-				allwinner,pins = "PB23";
-				allwinner,function = "ir1";
+			pwm0_pins_a: pwm0@0 {
+				allwinner,pins = "PB2";
+				allwinner,function = "pwm";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ir1_tx_pins_a: ir1@1 {
-				allwinner,pins = "PB22";
-				allwinner,function = "ir1";
+			pwm1_pins_a: pwm1@0 {
+				allwinner,pins = "PI3";
+				allwinner,function = "pwm";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
+			spdif_tx_pins_a: spdif@0 {
+				allwinner,pins = "PB13";
+				allwinner,function = "spdif";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+			};
+
 			spi0_pins_a: spi0@0 {
 				allwinner,pins = "PI11", "PI12", "PI13";
 				allwinner,function = "spi0";
@@ -1050,25 +1139,25 @@
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ps20_pins_a: ps20@0 {
-				allwinner,pins = "PI20", "PI21";
-				allwinner,function = "ps2";
+			uart0_pins_a: uart0@0 {
+				allwinner,pins = "PB22", "PB23";
+				allwinner,function = "uart0";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ps21_pins_a: ps21@0 {
-				allwinner,pins = "PH12", "PH13";
-				allwinner,function = "ps2";
+			uart0_pins_b: uart0@1 {
+				allwinner,pins = "PF2", "PF4";
+				allwinner,function = "uart0";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			spdif_tx_pins_a: spdif@0 {
-				allwinner,pins = "PB13";
-				allwinner,function = "spdif";
+			uart1_pins_a: uart1@0 {
+				allwinner,pins = "PA10", "PA11";
+				allwinner,function = "uart1";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/sun5i-a10s-auxtek-t004.dts b/arch/arm/boot/dts/sun5i-a10s-auxtek-t004.dts
index a790ec8adb75..2150e15e115a 100644
--- a/arch/arm/boot/dts/sun5i-a10s-auxtek-t004.dts
+++ b/arch/arm/boot/dts/sun5i-a10s-auxtek-t004.dts
@@ -124,7 +124,18 @@
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PG12";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
 	mmc0_cd_pin_t004: mmc0_cd_pin@0 {
 		allwinner,pins = "PG1";
 		allwinner,function = "gpio_in";
@@ -158,11 +169,19 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
 &usb1_vbus_pin_a {
 	allwinner,pins = "PG13";
 };
 
 &usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>;
+	usb0_id_det-gpio = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun5i-a10s-mk802.dts b/arch/arm/boot/dts/sun5i-a10s-mk802.dts
index 46ff9407826d..c84ac005342e 100644
--- a/arch/arm/boot/dts/sun5i-a10s-mk802.dts
+++ b/arch/arm/boot/dts/sun5i-a10s-mk802.dts
@@ -73,6 +73,20 @@
 	status = "okay";
 };
 
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins_a>;
+	status = "okay";
+
+	axp152: pmic@30 {
+		compatible = "x-powers,axp152";
+		reg = <0x30>;
+		interrupts = <0>;
+		interrupt-controller;
+		#interrupt-cells = <1>;
+	};
+};
+
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_mk802>;
@@ -83,10 +97,23 @@
 	status = "okay";
 };
 
+&mmc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins_a>;
+	vmmc-supply = <&reg_vcc3v3>;
+	bus-width = <4>;
+	non-removable;
+	status = "okay";
+};
+
 &ohci0 {
 	status = "okay";
 };
 
+&otg_sram {
+	status = "okay";
+};
+
 &pio {
 	led_pins_mk802: led_pins@0 {
 		allwinner,pins = "PB2";
@@ -122,6 +149,11 @@
 	status = "okay";
 };
 
+&usb_otg {
+	dr_mode = "peripheral";
+	status = "okay";
+};
+
 &usbphy {
 	usb1_vbus-supply = <&reg_usb1_vbus>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
index 86d046a502e6..aef91476f9ae 100644
--- a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
+++ b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
@@ -248,6 +248,13 @@
 	status = "okay";
 };
 
+&spi2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2_pins_a>,
+		    <&spi2_cs0_pins_a>;
+	status = "okay";
+};
+
 &uart0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart0_pins_a>;
diff --git a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
index 9fea918f949e..b5de75f4c710 100644
--- a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
+++ b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
@@ -79,6 +79,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 0 2 GPIO_ACTIVE_HIGH>;
 	};
@@ -195,7 +196,14 @@
 	regulator-always-on;
 	regulator-min-microvolt = <3300000>;
 	regulator-max-microvolt = <3300000>;
-	regulator-name = "vcc-wifi";
+	regulator-name = "vcc-wifi1";
+};
+
+&reg_ldo4 {
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi2";
 };
 
 &reg_usb1_vbus {
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index 367f33012493..c41a2ba34dde 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -242,6 +242,20 @@
 		allwinner,drive = <SUN4I_PINCTRL_30_MA>;
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
+
+	spi2_pins_a: spi2@0 {
+		allwinner,pins = "PB12", "PB13", "PB14";
+		allwinner,function = "spi2";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
+	spi2_cs0_pins_a: spi2_cs0@0 {
+		allwinner,pins = "PB11";
+		allwinner,function = "spi2";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
 };
 
 &sram_a {
diff --git a/arch/arm/boot/dts/sun5i-a13-difrnce-dit4350.dts b/arch/arm/boot/dts/sun5i-a13-difrnce-dit4350.dts
index 6546fa02901d..894c4c4f9a1f 100644
--- a/arch/arm/boot/dts/sun5i-a13-difrnce-dit4350.dts
+++ b/arch/arm/boot/dts/sun5i-a13-difrnce-dit4350.dts
@@ -42,185 +42,9 @@
 
 /dts-v1/;
 #include "sun5i-a13.dtsi"
-#include "sunxi-common-regulators.dtsi"
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/input/input.h>
-#include <dt-bindings/interrupt-controller/irq.h>
-#include <dt-bindings/pinctrl/sun4i-a10.h>
-#include <dt-bindings/pwm/pwm.h>
+#include "sun5i-reference-design-tablet.dtsi"
 
 / {
 	model = "Difrnce DIT4350";
 	compatible = "difrnce,dit4350", "allwinner,sun5i-a13";
-
-	aliases {
-		serial0 = &uart1;
-	};
-
-	backlight: backlight {
-		compatible = "pwm-backlight";
-		pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>;
-		brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>;
-		default-brightness-level = <8>;
-		/* TODO: backlight uses axp gpio1 as enable pin */
-	};
-
-	chosen {
-		stdout-path = "serial0:115200n8";
-	};
-};
-
-&cpu0 {
-	cpu-supply = <&reg_dcdc2>;
-};
-
-&ehci0 {
-	status = "okay";
-};
-
-&i2c0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c0_pins_a>;
-	status = "okay";
-
-	axp209: pmic@34 {
-		reg = <0x34>;
-		interrupts = <0>;
-	};
-};
-
-#include "axp209.dtsi"
-
-&i2c1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c1_pins_a>;
-	status = "okay";
-
-	pcf8563: rtc@51 {
-		compatible = "nxp,pcf8563";
-		reg = <0x51>;
-	};
-};
-
-&lradc {
-	vref-supply = <&reg_ldo2>;
-	status = "okay";
-
-	button@200 {
-		label = "Volume Up";
-		linux,code = <KEY_VOLUMEUP>;
-		channel = <0>;
-		voltage = <200000>;
-	};
-
-	button@400 {
-		label = "Volume Down";
-		linux,code = <KEY_VOLUMEDOWN>;
-		channel = <0>;
-		voltage = <400000>;
-	};
-};
-
-&mmc0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_d709>;
-	vmmc-supply = <&reg_vcc3v3>;
-	bus-width = <4>;
-	cd-gpios = <&pio 6 0 GPIO_ACTIVE_HIGH>; /* PG0 */
-	cd-inverted;
-	status = "okay";
-};
-
-&otg_sram {
-	status = "okay";
-};
-
-&pio {
-	mmc0_cd_pin_d709: mmc0_cd_pin@0 {
-		allwinner,pins = "PG0";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
-	};
-
-	usb0_vbus_detect_pin: usb0_vbus_detect_pin@0 {
-		allwinner,pins = "PG1";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_PULL_DOWN>;
-	};
-
-	usb0_id_detect_pin: usb0_id_detect_pin@0 {
-		allwinner,pins = "PG2";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
-	};
-};
-
-&pwm {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pwm0_pins>;
-	status = "okay";
-};
-
-&reg_dcdc2 {
-	regulator-always-on;
-	regulator-min-microvolt = <1000000>;
-	regulator-max-microvolt = <1400000>;
-	regulator-name = "vdd-cpu";
-};
-
-&reg_dcdc3 {
-	regulator-always-on;
-	regulator-min-microvolt = <1250000>;
-	regulator-max-microvolt = <1250000>;
-	regulator-name = "vdd-int-pll";
-};
-
-&reg_ldo1 {
-	regulator-name = "vdd-rtc";
-};
-
-&reg_ldo2 {
-	regulator-always-on;
-	regulator-min-microvolt = <3000000>;
-	regulator-max-microvolt = <3000000>;
-	regulator-name = "avcc";
-};
-
-&reg_ldo3 {
-	regulator-min-microvolt = <3300000>;
-	regulator-max-microvolt = <3300000>;
-	regulator-name = "vcc-wifi";
-};
-
-&reg_usb0_vbus {
-	gpio = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */
-	status = "okay";
-};
-
-&uart1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&uart1_pins_b>;
-	status = "okay";
-};
-
-&usb_otg {
-	dr_mode = "otg";
-	status = "okay";
-};
-
-&usb0_vbus_pin_a {
-	allwinner,pins = "PG12";
-};
-
-&usbphy {
-	pinctrl-names = "default";
-	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
-	usb0_id_det-gpio = <&pio 6 2 GPIO_ACTIVE_HIGH>; /* PG2 */
-	usb0_vbus_det-gpio = <&pio 6 1 GPIO_ACTIVE_HIGH>; /* PG1 */
-	usb0_vbus-supply = <&reg_usb0_vbus>;
-	usb1_vbus-supply = <&reg_ldo3>;
-	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun5i-a13-q8-tablet.dts b/arch/arm/boot/dts/sun5i-a13-q8-tablet.dts
index 72e93acb5a9e..a89f29fa3e40 100644
--- a/arch/arm/boot/dts/sun5i-a13-q8-tablet.dts
+++ b/arch/arm/boot/dts/sun5i-a13-q8-tablet.dts
@@ -42,19 +42,45 @@
 
 /dts-v1/;
 #include "sun5i-a13.dtsi"
-#include "sun5i-q8-common.dtsi"
+#include "sun5i-reference-design-tablet.dtsi"
 
 / {
 	model = "Q8 A13 Tablet";
 	compatible = "allwinner,q8-a13", "allwinner,sun5i-a13";
+
+	panel: panel {
+		compatible = "urt,umsh-8596md-t", "simple-panel";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			/* TODO: lcd panel uses axp gpio0 as enable pin */
+			backlight = <&backlight>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			panel_input: endpoint@0 {
+				reg = <0>;
+				remote-endpoint = <&tcon0_out_lcd>;
+			};
+		};
+	};
+};
+
+&be0 {
+	status = "okay";
 };
 
-&reg_ldo3 {
-	regulator-min-microvolt = <3300000>;
-	regulator-max-microvolt = <3300000>;
-	regulator-name = "vcc-wifi";
+&tcon0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&lcd_rgb666_pins>;
+	status = "okay";
 };
 
-&usbphy {
-	usb1_vbus-supply = <&reg_ldo3>;
+&tcon0_out {
+	tcon0_out_lcd: endpoint@0 {
+		reg = <0>;
+		remote-endpoint = <&panel_input>;
+	};
 };
diff --git a/arch/arm/boot/dts/sun5i-a13-utoo-p66.dts b/arch/arm/boot/dts/sun5i-a13-utoo-p66.dts
index fa9ddfdcfe96..a8b0bcc04514 100644
--- a/arch/arm/boot/dts/sun5i-a13-utoo-p66.dts
+++ b/arch/arm/boot/dts/sun5i-a13-utoo-p66.dts
@@ -42,24 +42,20 @@
 
 /dts-v1/;
 #include "sun5i-a13.dtsi"
-#include "sunxi-common-regulators.dtsi"
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/input/input.h>
+#include "sun5i-reference-design-tablet.dtsi"
 #include <dt-bindings/interrupt-controller/irq.h>
-#include <dt-bindings/pinctrl/sun4i-a10.h>
-#include <dt-bindings/pwm/pwm.h>
 
 / {
 	model = "Utoo P66";
 	compatible = "utoo,p66", "allwinner,sun5i-a13";
 
-	backlight: backlight {
-		compatible = "pwm-backlight";
-		pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>;
-		/* Note levels of 10 / 20% result in backlight off */
-		brightness-levels = <0 30 40 50 60 70 80 90 100>;
-		default-brightness-level = <6>;
-		/* TODO: backlight uses axp gpio1 as enable pin */
+	/* The P66 uses the uart pins as gpios */
+	aliases {
+		/delete-property/serial0;
+	};
+
+	chosen {
+		/delete-property/stdout-path;
 	};
 
 	i2c_lcd: i2c@0 {
@@ -73,39 +69,21 @@
 	};
 };
 
-&codec {
-	pinctrl-names = "default";
-	pinctrl-0 = <&codec_pa_pin>;
-	allwinner,pa-gpios = <&pio 6 3 GPIO_ACTIVE_HIGH>; /* PG3 */
-	status = "okay";
-};
-
-&cpu0 {
-	cpu-supply = <&reg_dcdc2>;
+&backlight {
+	/* Note levels of 10 / 20% result in backlight off */
+	brightness-levels = <0 30 40 50 60 70 80 90 100>;
+	default-brightness-level = <6>;
 };
 
-&ehci0 {
-	status = "okay";
+&codec {
+	allwinner,pa-gpios = <&pio 6 3 GPIO_ACTIVE_HIGH>; /* PG3 */
 };
 
-&i2c0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c0_pins_a>;
-	status = "okay";
-
-	axp209: pmic@34 {
-		reg = <0x34>;
-		interrupts = <0>;
-	};
+&codec_pa_pin {
+	allwinner,pins = "PG3";
 };
 
-#include "axp209.dtsi"
-
 &i2c1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c1_pins_a>;
-	status = "okay";
-
 	icn8318: touchscreen@40 {
 		compatible = "chipone,icn8318";
 		reg = <0x40>;
@@ -119,40 +97,6 @@
 		touchscreen-inverted-x;
 		touchscreen-swapped-x-y;
 	};
-
-	pcf8563: rtc@51 {
-		compatible = "nxp,pcf8563";
-		reg = <0x51>;
-	};
-};
-
-&lradc {
-	vref-supply = <&reg_ldo2>;
-	status = "okay";
-
-	button@200 {
-		label = "Volume Up";
-		linux,code = <KEY_VOLUMEUP>;
-		channel = <0>;
-		voltage = <200000>;
-	};
-
-	button@400 {
-		label = "Volume Down";
-		linux,code = <KEY_VOLUMEDOWN>;
-		channel = <0>;
-		voltage = <400000>;
-	};
-};
-
-&mmc0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_p66>;
-	vmmc-supply = <&reg_vcc3v3>;
-	bus-width = <4>;
-	cd-gpios = <&pio 6 0 GPIO_ACTIVE_HIGH>; /* PG0 */
-	cd-inverted;
-	status = "okay";
 };
 
 &mmc2 {
@@ -170,39 +114,7 @@
 	};
 };
 
-&otg_sram {
-	status = "okay";
-};
-
 &pio {
-	codec_pa_pin: codec_pa_pin@0 {
-		allwinner,pins = "PG3";
-		allwinner,function = "gpio_out";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
-	};
-
-	mmc0_cd_pin_p66: mmc0_cd_pin@0 {
-		allwinner,pins = "PG0";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
-	};
-
-	usb0_vbus_detect_pin: usb0_vbus_detect_pin@0 {
-		allwinner,pins = "PG1";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_PULL_DOWN>;
-	};
-
-	usb0_id_detect_pin: usb0_id_detect_pin@0 {
-		allwinner,pins = "PG2";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
-	};
-
 	i2c_lcd_pins: i2c_lcd_pin@0 {
 		allwinner,pins = "PG10", "PG12";
 		allwinner,function = "gpio_out";
@@ -217,67 +129,17 @@
 		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 	};
 
-	usb0_vbus_pin_a: usb0_vbus_pin@0 {
-		allwinner,pins = "PB4";
-		allwinner,function = "gpio_out";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
-	};
-};
-
-&pwm {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pwm0_pins>;
-	status = "okay";
-};
-
-&reg_dcdc2 {
-	regulator-always-on;
-	regulator-min-microvolt = <1000000>;
-	regulator-max-microvolt = <1500000>;
-	regulator-name = "vdd-cpu";
-};
-
-&reg_dcdc3 {
-	regulator-always-on;
-	regulator-min-microvolt = <1000000>;
-	regulator-max-microvolt = <1400000>;
-	regulator-name = "vdd-int-pll";
-};
-
-&reg_ldo1 {
-	regulator-name = "vdd-rtc";
-};
-
-&reg_ldo2 {
-	regulator-always-on;
-	regulator-min-microvolt = <3000000>;
-	regulator-max-microvolt = <3000000>;
-	regulator-name = "avcc";
-};
-
-&reg_ldo3 {
-	regulator-min-microvolt = <3300000>;
-	regulator-max-microvolt = <3300000>;
-	regulator-name = "vcc-wifi";
 };
 
 &reg_usb0_vbus {
 	gpio = <&pio 1 4 GPIO_ACTIVE_HIGH>; /* PB4 */
-	status = "okay";
 };
 
-&usb_otg {
-	dr_mode = "otg";
-	status = "okay";
+&uart1 {
+	/* The P66 uses the uart pins as gpios */
+	status = "disabled";
 };
 
-&usbphy {
-	pinctrl-names = "default";
-	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
-	usb0_id_det-gpio = <&pio 6 2 GPIO_ACTIVE_HIGH>; /* PG2 */
-	usb0_vbus_det-gpio = <&pio 6 1 GPIO_ACTIVE_HIGH>; /* PG1 */
-	usb0_vbus-supply = <&reg_usb0_vbus>;
-	usb1_vbus-supply = <&reg_ldo3>;
-	status = "okay";
+&usb0_vbus_pin_a {
+	allwinner,pins = "PB4";
 };
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index 263d46dbc7e6..e012890e0cf2 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -207,7 +207,50 @@
 		};
 	};
 
+	display-engine {
+		compatible = "allwinner,sun5i-a13-display-engine";
+		allwinner,pipelines = <&fe0>;
+	};
+
 	soc@01c00000 {
+		tcon0: lcd-controller@01c0c000 {
+			compatible = "allwinner,sun5i-a13-tcon";
+			reg = <0x01c0c000 0x1000>;
+			interrupts = <44>;
+			resets = <&tcon_ch0_clk 1>;
+			reset-names = "lcd";
+			clocks = <&ahb_gates 36>,
+				 <&tcon_ch0_clk>,
+				 <&tcon_ch1_clk>;
+			clock-names = "ahb",
+				      "tcon-ch0",
+				      "tcon-ch1";
+			clock-output-names = "tcon-pixel-clock";
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				tcon0_in: port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+
+					tcon0_in_be0: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&be0_out_tcon0>;
+					};
+				};
+
+				tcon0_out: port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+				};
+			};
+		};
+
 		pwm: pwm@01c20e00 {
 			compatible = "allwinner,sun5i-a13-pwm";
 			reg = <0x01c20e00 0xc>;
@@ -215,6 +258,75 @@
 			#pwm-cells = <3>;
 			status = "disabled";
 		};
+
+		fe0: display-frontend@01e00000 {
+			compatible = "allwinner,sun5i-a13-display-frontend";
+			reg = <0x01e00000 0x20000>;
+			interrupts = <47>;
+			clocks = <&ahb_gates 46>, <&de_fe_clk>,
+				 <&dram_gates 25>;
+			clock-names = "ahb", "mod",
+				      "ram";
+			resets = <&de_fe_clk>;
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				fe0_out: port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+
+					fe0_out_be0: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&be0_in_fe0>;
+					};
+				};
+			};
+		};
+
+		be0: display-backend@01e60000 {
+			compatible = "allwinner,sun5i-a13-display-backend";
+			reg = <0x01e60000 0x10000>;
+			clocks = <&ahb_gates 44>, <&de_be_clk>,
+				 <&dram_gates 26>;
+			clock-names = "ahb", "mod",
+				      "ram";
+			resets = <&de_be_clk>;
+			status = "disabled";
+
+			assigned-clocks = <&de_be_clk>;
+			assigned-clock-rates = <300000000>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				be0_in: port@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+
+					be0_in_fe0: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&fe0_out_be0>;
+					};
+				};
+
+				be0_out: port@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <1>;
+
+					be0_out_tcon0: endpoint@0 {
+						reg = <0>;
+						remote-endpoint = <&tcon0_in_be0>;
+					};
+				};
+			};
+		};
 	};
 };
 
@@ -237,6 +349,16 @@
 &pio {
 	compatible = "allwinner,sun5i-a13-pinctrl";
 
+	lcd_rgb666_pins: lcd_rgb666@0 {
+		allwinner,pins = "PD2", "PD3", "PD4", "PD5", "PD6", "PD7",
+				 "PD10", "PD11", "PD12", "PD13", "PD14", "PD15",
+				 "PD18", "PD19", "PD20", "PD21", "PD22", "PD23",
+				 "PD24", "PD25", "PD26", "PD27";
+		allwinner,function = "lcd0";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
 	uart1_pins_a: uart1@0 {
 		allwinner,pins = "PE10", "PE11";
 		allwinner,function = "uart1";
diff --git a/arch/arm/boot/dts/sun5i-r8.dtsi b/arch/arm/boot/dts/sun5i-r8.dtsi
index c04cf690b858..8b058f53b7dc 100644
--- a/arch/arm/boot/dts/sun5i-r8.dtsi
+++ b/arch/arm/boot/dts/sun5i-r8.dtsi
@@ -76,122 +76,12 @@
 				};
 			};
 		};
-
-		tcon0: lcd-controller@01c0c000 {
-			compatible = "allwinner,sun5i-a13-tcon";
-			reg = <0x01c0c000 0x1000>;
-			interrupts = <44>;
-			resets = <&tcon_ch0_clk 1>;
-			reset-names = "lcd";
-			clocks = <&ahb_gates 36>,
-				 <&tcon_ch0_clk>,
-				 <&tcon_ch1_clk>;
-			clock-names = "ahb",
-				      "tcon-ch0",
-				      "tcon-ch1";
-			clock-output-names = "tcon-pixel-clock";
-			status = "disabled";
-
-			ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				tcon0_in: port@0 {
-					#address-cells = <1>;
-					#size-cells = <0>;
-					reg = <0>;
-
-					tcon0_in_be0: endpoint@0 {
-						reg = <0>;
-						remote-endpoint = <&be0_out_tcon0>;
-					};
-				};
-
-				tcon0_out: port@1 {
-					#address-cells = <1>;
-					#size-cells = <0>;
-					reg = <1>;
-
-					tcon0_out_tve0: endpoint@1 {
-						reg = <1>;
-						remote-endpoint = <&tve0_in_tcon0>;
-					};
-				};
-			};
-		};
-
-		fe0: display-frontend@01e00000 {
-			compatible = "allwinner,sun5i-a13-display-frontend";
-			reg = <0x01e00000 0x20000>;
-			interrupts = <47>;
-			clocks = <&ahb_gates 46>, <&de_fe_clk>,
-				 <&dram_gates 25>;
-			clock-names = "ahb", "mod",
-				      "ram";
-			resets = <&de_fe_clk>;
-			status = "disabled";
-
-			ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				fe0_out: port@1 {
-					#address-cells = <1>;
-					#size-cells = <0>;
-					reg = <1>;
-
-					fe0_out_be0: endpoint@0 {
-						reg = <0>;
-						remote-endpoint = <&be0_in_fe0>;
-					};
-				};
-			};
-		};
-
-		be0: display-backend@01e60000 {
-			compatible = "allwinner,sun5i-a13-display-backend";
-			reg = <0x01e60000 0x10000>;
-			clocks = <&ahb_gates 44>, <&de_be_clk>,
-				 <&dram_gates 26>;
-			clock-names = "ahb", "mod",
-				      "ram";
-			resets = <&de_be_clk>;
-			status = "disabled";
-
-			assigned-clocks = <&de_be_clk>;
-			assigned-clock-rates = <300000000>;
-
-			ports {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				be0_in: port@0 {
-					#address-cells = <1>;
-					#size-cells = <0>;
-					reg = <0>;
-
-					be0_in_fe0: endpoint@0 {
-						reg = <0>;
-						remote-endpoint = <&fe0_out_be0>;
-					};
-				};
-
-				be0_out: port@1 {
-					#address-cells = <1>;
-					#size-cells = <0>;
-					reg = <1>;
-
-					be0_out_tcon0: endpoint@0 {
-						reg = <0>;
-						remote-endpoint = <&tcon0_in_be0>;
-					};
-				};
-			};
-		};
 	};
+};
 
-	display-engine {
-		compatible = "allwinner,sun5i-a13-display-engine";
-		allwinner,pipelines = <&fe0>;
+&tcon0_out {
+	tcon0_out_tve0: endpoint@1 {
+		reg = <1>;
+		remote-endpoint = <&tve0_in_tcon0>;
 	};
 };
diff --git a/arch/arm/boot/dts/sun5i-q8-common.dtsi b/arch/arm/boot/dts/sun5i-reference-design-tablet.dtsi
index a78e189f6653..20cc940f5f91 100644
--- a/arch/arm/boot/dts/sun5i-q8-common.dtsi
+++ b/arch/arm/boot/dts/sun5i-reference-design-tablet.dtsi
@@ -39,7 +39,7 @@
  *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  *     OTHER DEALINGS IN THE SOFTWARE.
  */
-#include "sunxi-q8-common.dtsi"
+#include "sunxi-reference-design-tablet.dtsi"
 
 #include <dt-bindings/pwm/pwm.h>
 
@@ -61,6 +61,13 @@
 	};
 };
 
+&codec {
+	pinctrl-names = "default";
+	pinctrl-0 = <&codec_pa_pin>;
+	allwinner,pa-gpios = <&pio 6 10 GPIO_ACTIVE_HIGH>; /* PG10 */
+	status = "okay";
+};
+
 &cpu0 {
 	cpu-supply = <&reg_dcdc2>;
 };
@@ -85,9 +92,13 @@
 
 #include "axp209.dtsi"
 
+&lradc {
+	vref-supply = <&reg_ldo2>;
+};
+
 &mmc0 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_q8>;
+	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
 	vmmc-supply = <&reg_vcc3v0>;
 	bus-width = <4>;
 	cd-gpios = <&pio 6 0 GPIO_ACTIVE_HIGH>; /* PG0 */
@@ -100,7 +111,14 @@
 };
 
 &pio {
-	mmc0_cd_pin_q8: mmc0_cd_pin@0 {
+	codec_pa_pin: codec_pa_pin@0 {
+		allwinner,pins = "PG10";
+		allwinner,function = "gpio_out";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
+	mmc0_cd_pin: mmc0_cd_pin@0 {
 		allwinner,pins = "PG0";
 		allwinner,function = "gpio_in";
 		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
@@ -154,6 +172,12 @@
 	regulator-name = "avcc";
 };
 
+&reg_ldo3 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi";
+};
+
 &reg_usb0_vbus {
 	gpio = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */
 	status = "okay";
@@ -170,11 +194,17 @@
 	status = "okay";
 };
 
+&usb_power_supply {
+	status = "okay";
+};
+
 &usbphy {
 	pinctrl-names = "default";
 	pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
 	usb0_id_det-gpio = <&pio 6 2 GPIO_ACTIVE_HIGH>; /* PG2 */
 	usb0_vbus_det-gpio = <&pio 6 1 GPIO_ACTIVE_HIGH>; /* PG1 */
+	usb0_vbus_power-supply = <&usb_power_supply>;
 	usb0_vbus-supply = <&reg_usb0_vbus>;
+	usb1_vbus-supply = <&reg_ldo3>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi
index 0840612b5ed6..e374f4fc8073 100644
--- a/arch/arm/boot/dts/sun5i.dtsi
+++ b/arch/arm/boot/dts/sun5i.dtsi
@@ -130,7 +130,7 @@
 		};
 
 		pll3x2: pll3x2_clk {
-			compatible = "fixed-factor-clock";
+			compatible = "allwinner,sun4i-a10-pll3-2x-clk", "fixed-factor-clock";
 			#clock-cells = <0>;
 			clock-div = <1>;
 			clock-mult = <2>;
diff --git a/arch/arm/boot/dts/sun6i-a31-m9.dts b/arch/arm/boot/dts/sun6i-a31-m9.dts
index 6e0e5687a09c..29016a13a2c1 100644
--- a/arch/arm/boot/dts/sun6i-a31-m9.dts
+++ b/arch/arm/boot/dts/sun6i-a31-m9.dts
@@ -65,12 +65,17 @@
 		pinctrl-0 = <&led_pins_m9>;
 
 		blue {
-			label = "m9:blue:usr";
+			label = "m9:blue:pwr";
 			gpios = <&pio 7 13 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
 		};
 	};
 };
 
+&cpu0 {
+	cpu-supply = <&reg_dcdc3>;
+};
+
 &ehci0 {
 	status = "okay";
 };
@@ -84,6 +89,7 @@
 	pinctrl-0 = <&gmac_pins_mii_a>;
 	phy = <&phy1>;
 	phy-mode = "mii";
+	phy-supply = <&reg_dldo1>;
 	status = "okay";
 
 	phy1: ethernet-phy@1 {
@@ -100,13 +106,26 @@
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_m9>;
-	vmmc-supply = <&reg_vcc3v3>;
+	vmmc-supply = <&reg_dcdc1>;
 	bus-width = <4>;
 	cd-gpios = <&pio 7 22 GPIO_ACTIVE_HIGH>; /* PH22 */
 	cd-inverted;
 	status = "okay";
 };
 
+&p2wi {
+	status = "okay";
+
+	axp22x: pmic@68 {
+		compatible = "x-powers,axp221";
+		reg = <0x68>;
+		interrupt-parent = <&nmi_intc>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
+
+#include "axp22x.dtsi"
+
 &pio {
 	led_pins_m9: led_pins@0 {
 		allwinner,pins = "PH13";
@@ -130,6 +149,78 @@
 	};
 };
 
+&reg_aldo1 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi";
+};
+
+&reg_aldo3 {
+	regulator-always-on;
+	regulator-min-microvolt = <2700000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "avcc";
+};
+
+&reg_dc5ldo {
+	regulator-always-on;
+	regulator-min-microvolt = <700000>;
+	regulator-max-microvolt = <1320000>;
+	regulator-name = "vdd-cpus"; /* This is an educated guess */
+};
+
+&reg_dcdc1 {
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-3v3";
+};
+
+&reg_dcdc2 {
+	regulator-min-microvolt = <700000>;
+	regulator-max-microvolt = <1320000>;
+	regulator-name = "vdd-gpu";
+};
+
+&reg_dcdc3 {
+	regulator-always-on;
+	regulator-min-microvolt = <700000>;
+	regulator-max-microvolt = <1320000>;
+	regulator-name = "vdd-cpu";
+};
+
+&reg_dcdc4 {
+	regulator-always-on;
+	regulator-min-microvolt = <700000>;
+	regulator-max-microvolt = <1320000>;
+	regulator-name = "vdd-sys-dll";
+};
+
+&reg_dcdc5 {
+	regulator-always-on;
+	regulator-min-microvolt = <1500000>;
+	regulator-max-microvolt = <1500000>;
+	regulator-name = "vcc-dram";
+};
+
+&reg_dldo1 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-ethernet-phy";
+};
+
+/*
+ * Both reg_usb1_vbus and reg_dldo4 need to be on for the hub attached
+ * to usb1 to work, and we can list only one usb1_vbus-supply, so dldo4 is
+ * marked as regulator-always-on.
+ */
+&reg_dldo4 {
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-usb-hub";
+};
+
 &reg_usb1_vbus {
 	pinctrl-names = "default";
 	pinctrl-0 = <&usb1_vbus_pin_m9>;
@@ -145,5 +236,6 @@
 
 &usbphy {
 	usb1_vbus-supply = <&reg_usb1_vbus>;
+	usb2_vbus-supply = <&reg_aldo1>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun6i-a31-mele-a1000g-quad.dts b/arch/arm/boot/dts/sun6i-a31-mele-a1000g-quad.dts
index 4dd70cce2127..5faeae429e2a 100644
--- a/arch/arm/boot/dts/sun6i-a31-mele-a1000g-quad.dts
+++ b/arch/arm/boot/dts/sun6i-a31-mele-a1000g-quad.dts
@@ -65,12 +65,17 @@
 		pinctrl-0 = <&led_pins_m9>;
 
 		blue {
-			label = "m9:blue:usr";
+			label = "a1000g:blue:pwr";
 			gpios = <&pio 7 13 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
 		};
 	};
 };
 
+&cpu0 {
+	cpu-supply = <&reg_dcdc3>;
+};
+
 &ehci0 {
 	status = "okay";
 };
@@ -84,6 +89,7 @@
 	pinctrl-0 = <&gmac_pins_mii_a>;
 	phy = <&phy1>;
 	phy-mode = "mii";
+	phy-supply = <&reg_dldo1>;
 	status = "okay";
 
 	phy1: ethernet-phy@1 {
@@ -100,13 +106,26 @@
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_m9>;
-	vmmc-supply = <&reg_vcc3v3>;
+	vmmc-supply = <&reg_dcdc1>;
 	bus-width = <4>;
 	cd-gpios = <&pio 7 22 GPIO_ACTIVE_HIGH>; /* PH22 */
 	cd-inverted;
 	status = "okay";
 };
 
+&p2wi {
+	status = "okay";
+
+	axp22x: pmic@68 {
+		compatible = "x-powers,axp221";
+		reg = <0x68>;
+		interrupt-parent = <&nmi_intc>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
+
+#include "axp22x.dtsi"
+
 &pio {
 	led_pins_m9: led_pins@0 {
 		allwinner,pins = "PH13";
@@ -130,6 +149,78 @@
 	};
 };
 
+&reg_aldo1 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi";
+};
+
+&reg_aldo3 {
+	regulator-always-on;
+	regulator-min-microvolt = <2700000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "avcc";
+};
+
+&reg_dc5ldo {
+	regulator-always-on;
+	regulator-min-microvolt = <700000>;
+	regulator-max-microvolt = <1320000>;
+	regulator-name = "vdd-cpus"; /* This is an educated guess */
+};
+
+&reg_dcdc1 {
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-3v3";
+};
+
+&reg_dcdc2 {
+	regulator-min-microvolt = <700000>;
+	regulator-max-microvolt = <1320000>;
+	regulator-name = "vdd-gpu";
+};
+
+&reg_dcdc3 {
+	regulator-always-on;
+	regulator-min-microvolt = <700000>;
+	regulator-max-microvolt = <1320000>;
+	regulator-name = "vdd-cpu";
+};
+
+&reg_dcdc4 {
+	regulator-always-on;
+	regulator-min-microvolt = <700000>;
+	regulator-max-microvolt = <1320000>;
+	regulator-name = "vdd-sys-dll";
+};
+
+&reg_dcdc5 {
+	regulator-always-on;
+	regulator-min-microvolt = <1500000>;
+	regulator-max-microvolt = <1500000>;
+	regulator-name = "vcc-dram";
+};
+
+&reg_dldo1 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-ethernet-phy";
+};
+
+/*
+ * Both reg_usb1_vbus and reg_dldo4 need to be on for the hub attached
+ * to usb1 to work, and we can list only one usb1_vbus-supply, so dldo4 is
+ * marked as regulator-always-on.
+ */
+&reg_dldo4 {
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-usb-hub";
+};
+
 &reg_usb1_vbus {
 	pinctrl-names = "default";
 	pinctrl-0 = <&usb1_vbus_pin_m9>;
@@ -150,5 +241,6 @@
 
 &usbphy {
 	usb1_vbus-supply = <&reg_usb1_vbus>;
+	usb2_vbus-supply = <&reg_aldo1>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts
new file mode 100644
index 000000000000..ba5bca0fe997
--- /dev/null
+++ b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts
@@ -0,0 +1,229 @@
+/*
+ * Copyright 2016 Luo Yi <luoyi.ly@gmail.com>
+ *
+ * Thanks to the original work by Hans de Goede <hdegoede@redhat.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "sun7i-a20.dtsi"
+#include "sunxi-common-regulators.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	model = "Banana Pi BPI-M1-Plus";
+	compatible = "sinovoip,bpi-m1-plus", "allwinner,sun7i-a20";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_pins_bpi_m1p>;
+
+		green {
+			label = "bananapi-m1-plus:green:usr";
+			gpios = <&pio 7 24 GPIO_ACTIVE_HIGH>;
+		};
+
+		pwr {
+			label = "bananapi-m1-plus:pwr:usr";
+			gpios = <&pio 7 25 GPIO_ACTIVE_HIGH>;
+			default-state = "on";
+		};
+	};
+
+	mmc3_pwrseq: mmc3_pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		pinctrl-names = "default";
+		pinctrl-0 = <&mmc3_pwrseq_pin_bpi_m1p>;
+		reset-gpios = <&pio 7 22 GPIO_ACTIVE_LOW>; /* PH22 WL-PMU-EN */
+	};
+
+	reg_gmac_3v3: gmac-3v3 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&gmac_power_pin_bpi_m1p>;
+		regulator-name = "gmac-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <100000>;
+		enable-active-high;
+		gpio = <&pio 7 23 GPIO_ACTIVE_HIGH>;
+	};
+};
+
+&ahci {
+	status = "okay";
+};
+
+&codec {
+	status = "okay";
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&ehci1 {
+	status = "okay";
+};
+
+&gmac {
+	pinctrl-names = "default";
+	pinctrl-0 = <&gmac_pins_rgmii_a>;
+	phy = <&phy1>;
+	phy-mode = "rgmii";
+	phy-supply = <&reg_gmac_3v3>;
+	status = "okay";
+
+	phy1: ethernet-phy@1 {
+		reg = <1>;
+	};
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins_a>;
+	status = "okay";
+
+	axp209: pmic@34 {
+		compatible = "x-powers,axp209";
+		reg = <0x34>;
+		interrupt-parent = <&nmi_intc>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+
+		interrupt-controller;
+		#interrupt-cells = <1>;
+	};
+};
+
+&ir0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&ir0_rx_pins_a>;
+	status = "okay";
+};
+
+&mmc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_bpi_m1p>;
+	vmmc-supply = <&reg_vcc3v3>;
+	bus-width = <4>;
+	cd-gpios = <&pio 7 10 GPIO_ACTIVE_HIGH>; /* PH10 */
+	cd-inverted;
+	status = "okay";
+};
+
+&mmc3 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc3_pins_a>;
+	vmmc-supply = <&reg_vcc3v3>;
+	mmc-pwrseq = <&mmc3_pwrseq>;
+	bus-width = <4>;
+	non-removable;
+	enable-sdio-wakeup;
+	status = "okay";
+
+	brcmf: bcrmf@1 {
+		reg = <1>;
+		compatible = "brcm,bcm4329-fmac";
+		interrupt-parent = <&pio>;
+		interrupts = <7 15 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-names = "host-wake";
+	};
+};
+
+&mmc3_pins_a {
+	/* AP6210 requires pull-up */
+	allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+};
+
+&ohci0 {
+	status = "okay";
+};
+
+&ohci1 {
+	status = "okay";
+};
+
+&pio {
+	gmac_power_pin_bpi_m1p: gmac_power_pin@0 {
+		allwinner,pins = "PH23";
+		allwinner,function = "gpio_out";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
+	led_pins_bpi_m1p: led_pins@0 {
+		allwinner,pins = "PH24", "PH25";
+		allwinner,function = "gpio_out";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
+	mmc0_cd_pin_bpi_m1p: mmc0_cd_pin@0 {
+		allwinner,pins = "PH10";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
+	mmc3_pwrseq_pin_bpi_m1p: mmc3_pwrseq_pin@0 {
+		allwinner,pins = "PH22";
+		allwinner,function = "gpio_out";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pins_a>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts b/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts
index 5ee43d8bf174..73c05dab0a69 100644
--- a/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts
+++ b/arch/arm/boot/dts/sun7i-a20-lamobo-r1.dts
@@ -95,6 +95,10 @@
 	status = "okay";
 };
 
+&codec {
+	status = "okay";
+};
+
 &cpu0 {
 	cpu-supply = <&reg_dcdc2>;
 };
@@ -110,13 +114,67 @@
 &gmac {
 	pinctrl-names = "default";
 	pinctrl-0 = <&gmac_pins_rgmii_a>;
-	phy = <&phy1>;
 	phy-mode = "rgmii";
 	phy-supply = <&reg_gmac_3v3>;
 	status = "okay";
 
-	phy1: ethernet-phy@1 {
-		reg = <1>;
+	fixed-link {
+		speed = <1000>;
+		full-duplex;
+	};
+
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		switch: ethernet-switch@1e {
+			compatible = "brcm,bcm53125";
+			reg = <30>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port0: port@0 {
+					reg = <0>;
+					label = "lan2";
+				};
+
+				port1: port@1 {
+					reg = <1>;
+					label = "lan3";
+				};
+
+				port2: port@2 {
+					reg = <2>;
+					label = "lan4";
+				};
+
+				port3: port@3 {
+					reg = <3>;
+					label = "wan";
+				};
+
+				port4: port@4 {
+					reg = <4>;
+					label = "lan1";
+				};
+
+				port8: port@8 {
+					reg = <8>;
+					label = "cpu";
+					ethernet = <&gmac>;
+					phy-mode = "rgmii";
+					fixed-link {
+						speed = <1000>;
+						full-duplex;
+					};
+				};
+			};
+		};
 	};
 };
 
@@ -158,10 +216,6 @@
 	status = "okay";
 };
 
-&ohci1 {
-	status = "okay";
-};
-
 &otg_sram {
 	status = "okay";
 };
@@ -199,7 +253,7 @@
 #include "axp209.dtsi"
 
 &reg_ahci_5v {
-	gpio = <&pio 1 3 0>; /* PB3 */
+	gpio = <&pio 1 3 GPIO_ACTIVE_HIGH>; /* PB3 */
 	status = "okay";
 };
 
@@ -232,11 +286,8 @@
 	status = "okay";
 };
 
-&reg_usb1_vbus {
-	status = "okay";
-};
-
 &reg_usb2_vbus {
+	gpio = <&pio 7 12 GPIO_ACTIVE_HIGH>; /* PH12 */
 	status = "okay";
 };
 
@@ -275,13 +326,16 @@
 	status = "okay";
 };
 
+&usb2_vbus_pin_a {
+	allwinner,pins = "PH12";
+};
+
 &usbphy {
 	pinctrl-names = "default";
 	pinctrl-0 = <&usb0_id_detect_pin>;
 	usb0_id_det-gpio = <&pio 7 4 GPIO_ACTIVE_HIGH>; /* PH4 */
 	usb0_vbus_power-supply = <&usb_power_supply>;
 	usb0_vbus-supply = <&reg_usb0_vbus>;
-	usb1_vbus-supply = <&reg_usb1_vbus>;
 	usb2_vbus-supply = <&reg_usb2_vbus>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 2c34bbbb9570..bd0c47660243 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -67,9 +67,9 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0-hdmi";
-			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
-				 <&ahb_gates 43>, <&ahb_gates 44>,
-				 <&dram_gates 26>;
+			clocks = <&ahb_gates 36>, <&ahb_gates 43>,
+				 <&ahb_gates 44>, <&de_be0_clk>,
+				 <&tcon0_ch1_clk>, <&dram_gates 26>;
 			status = "disabled";
 		};
 
@@ -77,8 +77,9 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0";
-			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
-				 <&ahb_gates 44>, <&dram_gates 26>;
+			clocks = <&ahb_gates 36>, <&ahb_gates 44>,
+				 <&de_be0_clk>, <&tcon0_ch0_clk>,
+				 <&dram_gates 26>;
 			status = "disabled";
 		};
 
@@ -86,8 +87,9 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0-tve0";
-			clocks = <&pll3>, <&pll5 1>,
-				 <&ahb_gates 34>, <&ahb_gates 36>, <&ahb_gates 44>,
+			clocks = <&ahb_gates 34>, <&ahb_gates 36>,
+				 <&ahb_gates 44>,
+				 <&de_be0_clk>, <&tcon0_ch1_clk>,
 				 <&dram_gates 5>, <&dram_gates 26>;
 			status = "disabled";
 		};
@@ -369,9 +371,9 @@
 					<5>, <6>, <7>,
 					<8>, <10>;
 			clock-output-names = "apb0_codec", "apb0_spdif",
-				"apb0_ac97", "apb0_iis0", "apb0_iis1",
+				"apb0_ac97", "apb0_i2s0", "apb0_i2s1",
 				"apb0_pio", "apb0_ir0", "apb0_ir1",
-				"apb0_iis2", "apb0_keypad";
+				"apb0_i2s2", "apb0_keypad";
 		};
 
 		apb1: clk@01c20058 {
@@ -521,6 +523,28 @@
 			clock-output-names = "ir1";
 		};
 
+		i2s0_clk: clk@01c200b8 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-a10-mod1-clk";
+			reg = <0x01c200b8 0x4>;
+			clocks = <&pll2 SUN4I_A10_PLL2_8X>,
+				 <&pll2 SUN4I_A10_PLL2_4X>,
+				 <&pll2 SUN4I_A10_PLL2_2X>,
+				 <&pll2 SUN4I_A10_PLL2_1X>;
+			clock-output-names = "i2s0";
+		};
+
+		ac97_clk: clk@01c200bc {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-a10-mod1-clk";
+			reg = <0x01c200bc 0x4>;
+			clocks = <&pll2 SUN4I_A10_PLL2_8X>,
+				 <&pll2 SUN4I_A10_PLL2_4X>,
+				 <&pll2 SUN4I_A10_PLL2_2X>,
+				 <&pll2 SUN4I_A10_PLL2_1X>;
+			clock-output-names = "ac97";
+		};
+
 		spdif_clk: clk@01c200c0 {
 			#clock-cells = <0>;
 			compatible = "allwinner,sun4i-a10-mod1-clk";
@@ -558,6 +582,28 @@
 			clock-output-names = "spi3";
 		};
 
+		i2s1_clk: clk@01c200d8 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-a10-mod1-clk";
+			reg = <0x01c200d8 0x4>;
+			clocks = <&pll2 SUN4I_A10_PLL2_8X>,
+				 <&pll2 SUN4I_A10_PLL2_4X>,
+				 <&pll2 SUN4I_A10_PLL2_2X>,
+				 <&pll2 SUN4I_A10_PLL2_1X>;
+			clock-output-names = "i2s1";
+		};
+
+		i2s2_clk: clk@01c200dc {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-a10-mod1-clk";
+			reg = <0x01c200dc 0x4>;
+			clocks = <&pll2 SUN4I_A10_PLL2_8X>,
+				 <&pll2 SUN4I_A10_PLL2_4X>,
+				 <&pll2 SUN4I_A10_PLL2_2X>,
+				 <&pll2 SUN4I_A10_PLL2_1X>;
+			clock-output-names = "i2s2";
+		};
+
 		dram_gates: clk@01c20100 {
 			#clock-cells = <1>;
 			compatible = "allwinner,sun4i-a10-dram-gates-clk";
@@ -583,6 +629,80 @@
 					     "dram_de_mp", "dram_ace";
 		};
 
+		de_be0_clk: clk@01c20104 {
+			#clock-cells = <0>;
+			#reset-cells = <0>;
+			compatible = "allwinner,sun4i-a10-display-clk";
+			reg = <0x01c20104 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll5 1>;
+			clock-output-names = "de-be0";
+		};
+
+		de_be1_clk: clk@01c20108 {
+			#clock-cells = <0>;
+			#reset-cells = <0>;
+			compatible = "allwinner,sun4i-a10-display-clk";
+			reg = <0x01c20108 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll5 1>;
+			clock-output-names = "de-be1";
+		};
+
+		de_fe0_clk: clk@01c2010c {
+			#clock-cells = <0>;
+			#reset-cells = <0>;
+			compatible = "allwinner,sun4i-a10-display-clk";
+			reg = <0x01c2010c 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll5 1>;
+			clock-output-names = "de-fe0";
+		};
+
+		de_fe1_clk: clk@01c20110 {
+			#clock-cells = <0>;
+			#reset-cells = <0>;
+			compatible = "allwinner,sun4i-a10-display-clk";
+			reg = <0x01c20110 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll5 1>;
+			clock-output-names = "de-fe1";
+		};
+
+		tcon0_ch0_clk: clk@01c20118 {
+			#clock-cells = <0>;
+			#reset-cells = <1>;
+			compatible = "allwinner,sun4i-a10-tcon-ch0-clk";
+			reg = <0x01c20118 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll3x2>, <&pll7x2>;
+			clock-output-names = "tcon0-ch0-sclk";
+
+		};
+
+		tcon1_ch0_clk: clk@01c2011c {
+			#clock-cells = <0>;
+			#reset-cells = <1>;
+			compatible = "allwinner,sun4i-a10-tcon-ch1-clk";
+			reg = <0x01c2011c 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll3x2>, <&pll7x2>;
+			clock-output-names = "tcon1-ch0-sclk";
+
+		};
+
+		tcon0_ch1_clk: clk@01c2012c {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-a10-tcon-ch0-clk";
+			reg = <0x01c2012c 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll3x2>, <&pll7x2>;
+			clock-output-names = "tcon0-ch1-sclk";
+
+		};
+
+		tcon1_ch1_clk: clk@01c20130 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun4i-a10-tcon-ch1-clk";
+			reg = <0x01c20130 0x4>;
+			clocks = <&pll3>, <&pll7>, <&pll3x2>, <&pll7x2>;
+			clock-output-names = "tcon1-ch1-sclk";
+
+		};
+
 		ve_clk: clk@01c2013c {
 			#clock-cells = <0>;
 			#reset-cells = <0>;
@@ -726,6 +846,19 @@
 			#dma-cells = <2>;
 		};
 
+		nfc: nand@01c03000 {
+			compatible = "allwinner,sun4i-a10-nand";
+			reg = <0x01c03000 0x1000>;
+			interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ahb_gates 13>, <&nand_clk>;
+			clock-names = "ahb", "mod";
+			dmas = <&dma SUN4I_DMA_DEDICATED 3>;
+			dma-names = "rxtx";
+			status = "disabled";
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
 		spi0: spi@01c05000 {
 			compatible = "allwinner,sun4i-a10-spi";
 			reg = <0x01c05000 0x1000>;
@@ -958,160 +1091,177 @@
 			#interrupt-cells = <3>;
 			#gpio-cells = <3>;
 
-			pwm0_pins_a: pwm0@0 {
-				allwinner,pins = "PB2";
-				allwinner,function = "pwm";
+			clk_out_a_pins_a: clk_out_a@0 {
+				allwinner,pins = "PI12";
+				allwinner,function = "clk_out_a";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			pwm1_pins_a: pwm1@0 {
-				allwinner,pins = "PI3";
-				allwinner,function = "pwm";
+			clk_out_b_pins_a: clk_out_b@0 {
+				allwinner,pins = "PI13";
+				allwinner,function = "clk_out_b";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart0_pins_a: uart0@0 {
-				allwinner,pins = "PB22", "PB23";
-				allwinner,function = "uart0";
+			emac_pins_a: emac0@0 {
+				allwinner,pins = "PA0", "PA1", "PA2",
+						"PA3", "PA4", "PA5", "PA6",
+						"PA7", "PA8", "PA9", "PA10",
+						"PA11", "PA12", "PA13", "PA14",
+						"PA15", "PA16";
+				allwinner,function = "emac";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart2_pins_a: uart2@0 {
-				allwinner,pins = "PI16", "PI17", "PI18", "PI19";
-				allwinner,function = "uart2";
+			gmac_pins_mii_a: gmac_mii@0 {
+				allwinner,pins = "PA0", "PA1", "PA2",
+						"PA3", "PA4", "PA5", "PA6",
+						"PA7", "PA8", "PA9", "PA10",
+						"PA11", "PA12", "PA13", "PA14",
+						"PA15", "PA16";
+				allwinner,function = "gmac";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart3_pins_a: uart3@0 {
-				allwinner,pins = "PG6", "PG7", "PG8", "PG9";
-				allwinner,function = "uart3";
-				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+			gmac_pins_rgmii_a: gmac_rgmii@0 {
+				allwinner,pins = "PA0", "PA1", "PA2",
+						"PA3", "PA4", "PA5", "PA6",
+						"PA7", "PA8", "PA10",
+						"PA11", "PA12", "PA13",
+						"PA15", "PA16";
+				allwinner,function = "gmac";
+				/*
+				 * data lines in RGMII mode use DDR mode
+				 * and need a higher signal drive strength
+				 */
+				allwinner,drive = <SUN4I_PINCTRL_40_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart3_pins_b: uart3@1 {
-				allwinner,pins = "PH0", "PH1";
-				allwinner,function = "uart3";
+			i2c0_pins_a: i2c0@0 {
+				allwinner,pins = "PB0", "PB1";
+				allwinner,function = "i2c0";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart4_pins_a: uart4@0 {
-				allwinner,pins = "PG10", "PG11";
-				allwinner,function = "uart4";
+			i2c1_pins_a: i2c1@0 {
+				allwinner,pins = "PB18", "PB19";
+				allwinner,function = "i2c1";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart4_pins_b: uart4@1 {
-				allwinner,pins = "PH4", "PH5";
-				allwinner,function = "uart4";
+			i2c2_pins_a: i2c2@0 {
+				allwinner,pins = "PB20", "PB21";
+				allwinner,function = "i2c2";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart5_pins_a: uart5@0 {
-				allwinner,pins = "PI10", "PI11";
-				allwinner,function = "uart5";
+			i2c3_pins_a: i2c3@0 {
+				allwinner,pins = "PI0", "PI1";
+				allwinner,function = "i2c3";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart6_pins_a: uart6@0 {
-				allwinner,pins = "PI12", "PI13";
-				allwinner,function = "uart6";
-				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			ir0_rx_pins_a: ir0@0 {
+				    allwinner,pins = "PB4";
+				    allwinner,function = "ir0";
+				    allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				    allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			uart7_pins_a: uart7@0 {
-				allwinner,pins = "PI20", "PI21";
-				allwinner,function = "uart7";
-				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			ir0_tx_pins_a: ir0@1 {
+				    allwinner,pins = "PB3";
+				    allwinner,function = "ir0";
+				    allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				    allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			i2c0_pins_a: i2c0@0 {
-				allwinner,pins = "PB0", "PB1";
-				allwinner,function = "i2c0";
-				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			ir1_rx_pins_a: ir1@0 {
+				    allwinner,pins = "PB23";
+				    allwinner,function = "ir1";
+				    allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				    allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			i2c1_pins_a: i2c1@0 {
-				allwinner,pins = "PB18", "PB19";
-				allwinner,function = "i2c1";
-				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			ir1_tx_pins_a: ir1@1 {
+				    allwinner,pins = "PB22";
+				    allwinner,function = "ir1";
+				    allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				    allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			i2c2_pins_a: i2c2@0 {
-				allwinner,pins = "PB20", "PB21";
-				allwinner,function = "i2c2";
-				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+			mmc0_pins_a: mmc0@0 {
+				allwinner,pins = "PF0", "PF1", "PF2",
+						 "PF3", "PF4", "PF5";
+				allwinner,function = "mmc0";
+				allwinner,drive = <SUN4I_PINCTRL_30_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			i2c3_pins_a: i2c3@0 {
-				allwinner,pins = "PI0", "PI1";
-				allwinner,function = "i2c3";
+			mmc0_cd_pin_reference_design: mmc0_cd_pin@0 {
+				allwinner,pins = "PH1";
+				allwinner,function = "gpio_in";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+			};
+
+			mmc2_pins_a: mmc2@0 {
+				allwinner,pins = "PC6", "PC7", "PC8",
+						 "PC9", "PC10", "PC11";
+				allwinner,function = "mmc2";
+				allwinner,drive = <SUN4I_PINCTRL_30_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+			};
+
+			mmc3_pins_a: mmc3@0 {
+				allwinner,pins = "PI4", "PI5", "PI6",
+						 "PI7", "PI8", "PI9";
+				allwinner,function = "mmc3";
+				allwinner,drive = <SUN4I_PINCTRL_30_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			emac_pins_a: emac0@0 {
-				allwinner,pins = "PA0", "PA1", "PA2",
-						"PA3", "PA4", "PA5", "PA6",
-						"PA7", "PA8", "PA9", "PA10",
-						"PA11", "PA12", "PA13", "PA14",
-						"PA15", "PA16";
-				allwinner,function = "emac";
+			ps20_pins_a: ps20@0 {
+				allwinner,pins = "PI20", "PI21";
+				allwinner,function = "ps2";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			clk_out_a_pins_a: clk_out_a@0 {
-				allwinner,pins = "PI12";
-				allwinner,function = "clk_out_a";
+			ps21_pins_a: ps21@0 {
+				allwinner,pins = "PH12", "PH13";
+				allwinner,function = "ps2";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			clk_out_b_pins_a: clk_out_b@0 {
-				allwinner,pins = "PI13";
-				allwinner,function = "clk_out_b";
+			pwm0_pins_a: pwm0@0 {
+				allwinner,pins = "PB2";
+				allwinner,function = "pwm";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			gmac_pins_mii_a: gmac_mii@0 {
-				allwinner,pins = "PA0", "PA1", "PA2",
-						"PA3", "PA4", "PA5", "PA6",
-						"PA7", "PA8", "PA9", "PA10",
-						"PA11", "PA12", "PA13", "PA14",
-						"PA15", "PA16";
-				allwinner,function = "gmac";
+			pwm1_pins_a: pwm1@0 {
+				allwinner,pins = "PI3";
+				allwinner,function = "pwm";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			gmac_pins_rgmii_a: gmac_rgmii@0 {
-				allwinner,pins = "PA0", "PA1", "PA2",
-						"PA3", "PA4", "PA5", "PA6",
-						"PA7", "PA8", "PA10",
-						"PA11", "PA12", "PA13",
-						"PA15", "PA16";
-				allwinner,function = "gmac";
-				/*
-				 * data lines in RGMII mode use DDR mode
-				 * and need a higher signal drive strength
-				 */
-				allwinner,drive = <SUN4I_PINCTRL_40_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			spdif_tx_pins_a: spdif@0 {
+				allwinner,pins = "PB13";
+				allwinner,function = "spdif";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
 			};
 
 			spi0_pins_a: spi0@0 {
@@ -1177,84 +1327,67 @@
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			mmc0_pins_a: mmc0@0 {
-				allwinner,pins = "PF0", "PF1", "PF2",
-						 "PF3", "PF4", "PF5";
-				allwinner,function = "mmc0";
-				allwinner,drive = <SUN4I_PINCTRL_30_MA>;
+			uart0_pins_a: uart0@0 {
+				allwinner,pins = "PB22", "PB23";
+				allwinner,function = "uart0";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			mmc0_cd_pin_reference_design: mmc0_cd_pin@0 {
-				allwinner,pins = "PH1";
-				allwinner,function = "gpio_in";
+			uart2_pins_a: uart2@0 {
+				allwinner,pins = "PI16", "PI17", "PI18", "PI19";
+				allwinner,function = "uart2";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
-			};
-
-			mmc2_pins_a: mmc2@0 {
-				allwinner,pins = "PC6", "PC7", "PC8",
-						 "PC9", "PC10", "PC11";
-				allwinner,function = "mmc2";
-				allwinner,drive = <SUN4I_PINCTRL_30_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
-			};
-
-			mmc3_pins_a: mmc3@0 {
-				allwinner,pins = "PI4", "PI5", "PI6",
-						 "PI7", "PI8", "PI9";
-				allwinner,function = "mmc3";
-				allwinner,drive = <SUN4I_PINCTRL_30_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ir0_rx_pins_a: ir0@0 {
-				    allwinner,pins = "PB4";
-				    allwinner,function = "ir0";
-				    allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				    allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			uart3_pins_a: uart3@0 {
+				allwinner,pins = "PG6", "PG7", "PG8", "PG9";
+				allwinner,function = "uart3";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ir0_tx_pins_a: ir0@1 {
-				    allwinner,pins = "PB3";
-				    allwinner,function = "ir0";
-				    allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				    allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			uart3_pins_b: uart3@1 {
+				allwinner,pins = "PH0", "PH1";
+				allwinner,function = "uart3";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ir1_rx_pins_a: ir1@0 {
-				    allwinner,pins = "PB23";
-				    allwinner,function = "ir1";
-				    allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				    allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			uart4_pins_a: uart4@0 {
+				allwinner,pins = "PG10", "PG11";
+				allwinner,function = "uart4";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ir1_tx_pins_a: ir1@1 {
-				    allwinner,pins = "PB22";
-				    allwinner,function = "ir1";
-				    allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				    allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			uart4_pins_b: uart4@1 {
+				allwinner,pins = "PH4", "PH5";
+				allwinner,function = "uart4";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ps20_pins_a: ps20@0 {
-				allwinner,pins = "PI20", "PI21";
-				allwinner,function = "ps2";
+			uart5_pins_a: uart5@0 {
+				allwinner,pins = "PI10", "PI11";
+				allwinner,function = "uart5";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			ps21_pins_a: ps21@0 {
-				allwinner,pins = "PH12", "PH13";
-				allwinner,function = "ps2";
+			uart6_pins_a: uart6@0 {
+				allwinner,pins = "PI12", "PI13";
+				allwinner,function = "uart6";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
-			spdif_tx_pins_a: spdif@0 {
-				allwinner,pins = "PB13";
-				allwinner,function = "spdif";
+			uart7_pins_a: uart7@0 {
+				allwinner,pins = "PI20", "PI21";
+				allwinner,function = "uart7";
 				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 		};
 
@@ -1320,6 +1453,32 @@
 			status = "disabled";
 		};
 
+		i2s1: i2s@01c22000 {
+			#sound-dai-cells = <0>;
+			compatible = "allwinner,sun4i-a10-i2s";
+			reg = <0x01c22000 0x400>;
+			interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&apb0_gates 4>, <&i2s1_clk>;
+			clock-names = "apb", "mod";
+			dmas = <&dma SUN4I_DMA_NORMAL 4>,
+			       <&dma SUN4I_DMA_NORMAL 4>;
+			dma-names = "rx", "tx";
+			status = "disabled";
+		};
+
+		i2s0: i2s@01c22400 {
+			#sound-dai-cells = <0>;
+			compatible = "allwinner,sun4i-a10-i2s";
+			reg = <0x01c22400 0x400>;
+			interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&apb0_gates 3>, <&i2s0_clk>;
+			clock-names = "apb", "mod";
+			dmas = <&dma SUN4I_DMA_NORMAL 3>,
+			       <&dma SUN4I_DMA_NORMAL 3>;
+			dma-names = "rx", "tx";
+			status = "disabled";
+		};
+
 		lradc: lradc@01c22800 {
 			compatible = "allwinner,sun4i-a10-lradc-keys";
 			reg = <0x01c22800 0x100>;
@@ -1345,6 +1504,19 @@
 			reg = <0x01c23800 0x200>;
 		};
 
+		i2s2: i2s@01c24400 {
+			#sound-dai-cells = <0>;
+			compatible = "allwinner,sun4i-a10-i2s";
+			reg = <0x01c24400 0x400>;
+			interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&apb0_gates 8>, <&i2s2_clk>;
+			clock-names = "apb", "mod";
+			dmas = <&dma SUN4I_DMA_NORMAL 6>,
+			       <&dma SUN4I_DMA_NORMAL 6>;
+			dma-names = "rx", "tx";
+			status = "disabled";
+		};
+
 		rtp: rtp@01c25000 {
 			compatible = "allwinner,sun5i-a13-ts";
 			reg = <0x01c25000 0x100>;
diff --git a/arch/arm/boot/dts/sun8i-a23-inet86dz.dts b/arch/arm/boot/dts/sun8i-a23-inet86dz.dts
new file mode 100644
index 000000000000..0f9f71b14047
--- /dev/null
+++ b/arch/arm/boot/dts/sun8i-a23-inet86dz.dts
@@ -0,0 +1,58 @@
+/*
+ * Copyright 2016 Hans de Goede <hdegoede@redhat.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "sun8i-a23.dtsi"
+#include "sun8i-reference-design-tablet.dtsi"
+
+/ {
+	model = "INet-86DZ Rev 01";
+	compatible = "primux,inet86dz", "allwinner,sun8i-a23";
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&usbphy {
+	usb1_vbus-supply = <&reg_dldo1>;
+};
diff --git a/arch/arm/boot/dts/sun8i-a23-polaroid-mid2407pxe03.dts b/arch/arm/boot/dts/sun8i-a23-polaroid-mid2407pxe03.dts
new file mode 100644
index 000000000000..e3004428e7a7
--- /dev/null
+++ b/arch/arm/boot/dts/sun8i-a23-polaroid-mid2407pxe03.dts
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2016 Hans de Goede <hdegoede@redhat.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "sun8i-a23.dtsi"
+#include "sun8i-reference-design-tablet.dtsi"
+
+/ {
+	model = "Polaroid MID2407PXE03 tablet";
+	compatible = "polaroid,mid2407pxe03", "allwinner,sun8i-a23";
+};
diff --git a/arch/arm/boot/dts/sun8i-a23-polaroid-mid2809pxe04.dts b/arch/arm/boot/dts/sun8i-a23-polaroid-mid2809pxe04.dts
index cb5daafcb7c2..6d06e24d446b 100644
--- a/arch/arm/boot/dts/sun8i-a23-polaroid-mid2809pxe04.dts
+++ b/arch/arm/boot/dts/sun8i-a23-polaroid-mid2809pxe04.dts
@@ -42,202 +42,9 @@
 
 /dts-v1/;
 #include "sun8i-a23.dtsi"
-#include "sunxi-common-regulators.dtsi"
-
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/input/input.h>
-#include <dt-bindings/pinctrl/sun4i-a10.h>
-#include <dt-bindings/pwm/pwm.h>
+#include "sun8i-reference-design-tablet.dtsi"
 
 / {
 	model = "Polaroid MID2809PXE04 tablet";
 	compatible = "polaroid,mid2809pxe04", "allwinner,sun8i-a23";
-
-	aliases {
-		serial0 = &r_uart;
-	};
-
-	backlight: backlight {
-		compatible = "pwm-backlight";
-		pinctrl-names = "default";
-		pinctrl-0 = <&bl_en_pin_mid2809>;
-		pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>;
-		brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>;
-		default-brightness-level = <8>;
-		enable-gpios = <&pio 7 6 GPIO_ACTIVE_HIGH>; /* PH6 */
-	};
-
-	chosen {
-		stdout-path = "serial0:115200n8";
-	};
-};
-
-&ehci0 {
-	status = "okay";
-};
-
-&i2c0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c0_pins_a>;
-	status = "okay";
-};
-
-&i2c1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c1_pins_a>;
-	status = "okay";
-};
-
-&lradc {
-	vref-supply = <&reg_vcc3v0>;
-	status = "okay";
-
-	button@200 {
-		label = "Volume Up";
-		linux,code = <KEY_VOLUMEUP>;
-		channel = <0>;
-		voltage = <200000>;
-	};
-
-	button@400 {
-		label = "Volume Down";
-		linux,code = <KEY_VOLUMEDOWN>;
-		channel = <0>;
-		voltage = <400000>;
-	};
-};
-
-&mmc0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_mid2809>;
-	vmmc-supply = <&reg_dcdc1>;
-	bus-width = <4>;
-	cd-gpios = <&pio 1 4 GPIO_ACTIVE_HIGH>; /* PB4 */
-	cd-inverted;
-	status = "okay";
-};
-
-&pio {
-	bl_en_pin_mid2809: bl_en_pin@0 {
-		allwinner,pins = "PH6";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
-	};
-
-	mmc0_cd_pin_mid2809: mmc0_cd_pin@0 {
-		allwinner,pins = "PB4";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
-	};
-};
-
-&pwm {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pwm0_pins>;
-	status = "okay";
-};
-
-&r_rsb {
-	status = "okay";
-
-	axp22x: pmic@3a3 {
-		compatible = "x-powers,axp223";
-		reg = <0x3a3>;
-		interrupt-parent = <&nmi_intc>;
-		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
-		eldoin-supply = <&reg_dcdc1>;
-	};
-};
-
-&r_uart {
-	pinctrl-names = "default";
-	pinctrl-0 = <&r_uart_pins_a>;
-	status = "okay";
-};
-
-#include "axp22x.dtsi"
-
-&reg_aldo1 {
-	regulator-always-on;
-	regulator-min-microvolt = <3000000>;
-	regulator-max-microvolt = <3000000>;
-	regulator-name = "vcc-io";
-};
-
-&reg_aldo2 {
-	regulator-always-on;
-	regulator-min-microvolt = <2350000>;
-	regulator-max-microvolt = <2650000>;
-	regulator-name = "vdd-dll";
-};
-
-&reg_aldo3 {
-	regulator-always-on;
-	regulator-min-microvolt = <2700000>;
-	regulator-max-microvolt = <3300000>;
-	regulator-name = "vcc-pll-avcc";
-};
-
-&reg_dc1sw {
-	regulator-name = "vcc-lcd";
-};
-
-&reg_dc5ldo {
-	regulator-always-on;
-	regulator-min-microvolt = <900000>;
-	regulator-max-microvolt = <1400000>;
-	regulator-name = "vdd-cpus";
-};
-
-&reg_dcdc1 {
-	regulator-always-on;
-	regulator-min-microvolt = <3000000>;
-	regulator-max-microvolt = <3000000>;
-	regulator-name = "vcc-3v0";
-};
-
-&reg_dcdc2 {
-	regulator-always-on;
-	regulator-min-microvolt = <900000>;
-	regulator-max-microvolt = <1400000>;
-	regulator-name = "vdd-sys";
-};
-
-&reg_dcdc3 {
-	regulator-always-on;
-	regulator-min-microvolt = <900000>;
-	regulator-max-microvolt = <1400000>;
-	regulator-name = "vdd-cpu";
-};
-
-&reg_dcdc5 {
-	regulator-always-on;
-	regulator-min-microvolt = <1500000>;
-	regulator-max-microvolt = <1500000>;
-	regulator-name = "vcc-dram";
-};
-
-&reg_rtc_ldo {
-	regulator-name = "vcc-rtc";
-};
-
-&simplefb_lcd {
-	vcc-lcd-supply = <&reg_dc1sw>;
-};
-
-/*
- * FIXME for now we only support host mode and rely on u-boot to have
- * turned on Vbus which is controlled by the axp223 pmic on the board.
- *
- * Once we have axp223 support we should switch to fully supporting otg.
- */
-&usb_otg {
-	dr_mode = "host";
-	status = "okay";
-};
-
-&usbphy {
-	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun8i-a23-q8-tablet.dts b/arch/arm/boot/dts/sun8i-a23-q8-tablet.dts
index 6062ea7a9903..956320a6cc78 100644
--- a/arch/arm/boot/dts/sun8i-a23-q8-tablet.dts
+++ b/arch/arm/boot/dts/sun8i-a23-q8-tablet.dts
@@ -48,18 +48,3 @@
 	model = "Q8 A23 Tablet";
 	compatible = "allwinner,q8-a23", "allwinner,sun8i-a23";
 };
-
-/*
- * FIXME for now we only support host mode and rely on u-boot to have
- * turned on Vbus which is controlled by the axp223 pmic on the board.
- *
- * Once we have axp223 support we should switch to fully supporting otg.
- */
-&usb_otg {
-	dr_mode = "host";
-	status = "okay";
-};
-
-&usbphy {
-	status = "okay";
-};
diff --git a/arch/arm/boot/dts/sun8i-a33-ga10h-v1.1.dts b/arch/arm/boot/dts/sun8i-a33-ga10h-v1.1.dts
index 1aefc6793e25..65660324005c 100644
--- a/arch/arm/boot/dts/sun8i-a33-ga10h-v1.1.dts
+++ b/arch/arm/boot/dts/sun8i-a33-ga10h-v1.1.dts
@@ -42,59 +42,18 @@
 
 /dts-v1/;
 #include "sun8i-a33.dtsi"
-#include "sunxi-common-regulators.dtsi"
-
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/input/input.h>
-#include <dt-bindings/pinctrl/sun4i-a10.h>
+#include "sun8i-reference-design-tablet.dtsi"
 
 / {
 	model = "Allwinner GA10H Quad Core Tablet (v1.1)";
 	compatible = "allwinner,ga10h-v1.1", "allwinner,sun8i-a33";
-
-	aliases {
-		serial0 = &r_uart;
-	};
-
-	chosen {
-		stdout-path = "serial0:115200n8";
-	};
 };
 
 &ehci0 {
 	status = "okay";
 };
 
-&i2c0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c0_pins_a>;
-	status = "okay";
-};
-
-&i2c1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c1_pins_a>;
-	status = "okay";
-};
-
 &lradc {
-	vref-supply = <&reg_vcc3v0>;
-	status = "okay";
-
-	button@200 {
-		label = "Volume Up";
-		linux,code = <KEY_VOLUMEUP>;
-		channel = <0>;
-		voltage = <200000>;
-	};
-
-	button@400 {
-		label = "Volume Down";
-		linux,code = <KEY_VOLUMEDOWN>;
-		channel = <0>;
-		voltage = <400000>;
-	};
-
 	button@600 {
 		label = "Back";
 		linux,code = <KEY_BACK>;
@@ -103,40 +62,6 @@
 	};
 };
 
-&mmc0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_q8h>;
-	vmmc-supply = <&reg_vcc3v0>;
-	bus-width = <4>;
-	cd-gpios = <&pio 1 4 GPIO_ACTIVE_HIGH>; /* PB4 */
-	cd-inverted;
-	status = "okay";
-};
-
 &ohci0 {
 	status = "okay";
 };
-
-&pio {
-	mmc0_cd_pin_q8h: mmc0_cd_pin@0 {
-		allwinner,pins = "PB4";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
-	};
-};
-
-&r_uart {
-	pinctrl-names = "default";
-	pinctrl-0 = <&r_uart_pins_a>;
-	status = "okay";
-};
-
-&usb_otg {
-	dr_mode = "host";
-	status = "okay";
-};
-
-&usbphy {
-	status = "okay";
-};
diff --git a/arch/arm/boot/dts/sun8i-a33-q8-tablet.dts b/arch/arm/boot/dts/sun8i-a33-q8-tablet.dts
index 44b32296a025..b0bc2360f8c4 100644
--- a/arch/arm/boot/dts/sun8i-a33-q8-tablet.dts
+++ b/arch/arm/boot/dts/sun8i-a33-q8-tablet.dts
@@ -48,18 +48,3 @@
 	model = "Q8 A33 Tablet";
 	compatible = "allwinner,q8-a33", "allwinner,sun8i-a33";
 };
-
-/*
- * FIXME for now we only support host mode and rely on u-boot to have
- * turned on Vbus which is controlled by the axp223 pmic on the board.
- *
- * Once we have axp223 support we should switch to fully supporting otg.
- */
-&usb_otg {
-	dr_mode = "host";
-	status = "okay";
-};
-
-&usbphy {
-	status = "okay";
-};
diff --git a/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts b/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts
new file mode 100644
index 000000000000..f3b1d5f6dbd2
--- /dev/null
+++ b/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts
@@ -0,0 +1,195 @@
+/*
+ * Copyright (C) 2016 Chen-Yu Tsai <wens@csie.org>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "sun8i-h3.dtsi"
+#include "sunxi-common-regulators.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/pinctrl/sun4i-a10.h>
+
+/ {
+	model = "Banana Pi BPI-M2-Plus";
+	compatible = "sinovoip,bpi-m2-plus", "allwinner,sun8i-h3";
+
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pwr_led_bpi_m2p>;
+
+		pwr_led {
+			label = "bananapi-m2-plus:red:pwr";
+			gpios = <&r_pio 0 10 GPIO_ACTIVE_HIGH>; /* PL10 */
+			default-state = "on";
+		};
+	};
+
+	gpio_keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&sw_r_bpi_m2p>;
+
+		sw4 {
+			label = "power";
+			linux,code = <BTN_0>;
+			gpios = <&r_pio 0 3 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	wifi_pwrseq: wifi_pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		pinctrl-names = "default";
+		pinctrl-0 = <&wifi_en_bpi_m2p>;
+		reset-gpios = <&r_pio 0 7 GPIO_ACTIVE_LOW>; /* PL7 */
+	};
+};
+
+&ehci1 {
+	status = "okay";
+};
+
+&ehci2 {
+	status = "okay";
+};
+
+&ir {
+	pinctrl-names = "default";
+	pinctrl-0 = <&ir_pins_a>;
+	status = "okay";
+};
+
+&mmc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
+	vmmc-supply = <&reg_vcc3v3>;
+	bus-width = <4>;
+	cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>; /* PF6 */
+	cd-inverted;
+	status = "okay";
+};
+
+&mmc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins_a>;
+	vmmc-supply = <&reg_vcc3v3>;
+	vqmmc-supply = <&reg_vcc3v3>;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	bus-width = <4>;
+	non-removable;
+	status = "okay";
+
+	brcmf: bcrmf@1 {
+		reg = <1>;
+		compatible = "brcm,bcm4329-fmac";
+		interrupt-parent = <&pio>;
+		interrupts = <6 10 IRQ_TYPE_LEVEL_LOW>; /* PG10 / EINT10 */
+		interrupt-names = "host-wake";
+	};
+};
+
+&mmc2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc2_8bit_pins>;
+	vmmc-supply = <&reg_vcc3v3>;
+	vqmmc-supply = <&reg_vcc3v3>;
+	bus-width = <8>;
+	non-removable;
+	status = "okay";
+};
+
+&ohci1 {
+	status = "okay";
+};
+
+&ohci2 {
+	status = "okay";
+};
+
+&r_pio {
+	pwr_led_bpi_m2p: led_pins@0 {
+		allwinner,pins = "PL10";
+		allwinner,function = "gpio_out";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
+	sw_r_bpi_m2p: key_pins@0 {
+		allwinner,pins = "PL3";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
+	wifi_en_bpi_m2p: wifi_en_pin {
+		allwinner,pins = "PL7";
+		allwinner,function = "gpio_out";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pins_a>;
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart1_pins_a>;
+	status = "okay";
+};
+
+&usbphy {
+	/* USB VBUS is on as long as VCC-IO is on */
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/sun8i-h3.dtsi b/arch/arm/boot/dts/sun8i-h3.dtsi
index 4a4926b0b0ed..fdf9fdbda267 100644
--- a/arch/arm/boot/dts/sun8i-h3.dtsi
+++ b/arch/arm/boot/dts/sun8i-h3.dtsi
@@ -42,8 +42,10 @@
 
 #include "skeleton.dtsi"
 
+#include <dt-bindings/clock/sun8i-h3-ccu.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/pinctrl/sun4i-a10.h>
+#include <dt-bindings/reset/sun8i-h3-ccu.h>
 
 / {
 	interrupt-parent = <&gic>;
@@ -104,191 +106,6 @@
 			clock-output-names = "osc32k";
 		};
 
-		pll1: clk@01c20000 {
-			#clock-cells = <0>;
-			compatible = "allwinner,sun8i-a23-pll1-clk";
-			reg = <0x01c20000 0x4>;
-			clocks = <&osc24M>;
-			clock-output-names = "pll1";
-		};
-
-		/* dummy clock until actually implemented */
-		pll5: pll5_clk {
-			#clock-cells = <0>;
-			compatible = "fixed-clock";
-			clock-frequency = <0>;
-			clock-output-names = "pll5";
-		};
-
-		pll6: clk@01c20028 {
-			#clock-cells = <1>;
-			compatible = "allwinner,sun6i-a31-pll6-clk";
-			reg = <0x01c20028 0x4>;
-			clocks = <&osc24M>;
-			clock-output-names = "pll6", "pll6x2";
-		};
-
-		pll6d2: pll6d2_clk {
-			#clock-cells = <0>;
-			compatible = "fixed-factor-clock";
-			clock-div = <2>;
-			clock-mult = <1>;
-			clocks = <&pll6 0>;
-			clock-output-names = "pll6d2";
-		};
-
-		/* dummy clock until pll6 can be reused */
-		pll8: pll8_clk {
-			#clock-cells = <0>;
-			compatible = "fixed-clock";
-			clock-frequency = <1>;
-			clock-output-names = "pll8";
-		};
-
-		cpu: cpu_clk@01c20050 {
-			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-cpu-clk";
-			reg = <0x01c20050 0x4>;
-			clocks = <&osc32k>, <&osc24M>, <&pll1>, <&pll1>;
-			clock-output-names = "cpu";
-		};
-
-		axi: axi_clk@01c20050 {
-			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-axi-clk";
-			reg = <0x01c20050 0x4>;
-			clocks = <&cpu>;
-			clock-output-names = "axi";
-		};
-
-		ahb1: ahb1_clk@01c20054 {
-			#clock-cells = <0>;
-			compatible = "allwinner,sun6i-a31-ahb1-clk";
-			reg = <0x01c20054 0x4>;
-			clocks = <&osc32k>, <&osc24M>, <&axi>, <&pll6 0>;
-			clock-output-names = "ahb1";
-		};
-
-		ahb2: ahb2_clk@01c2005c {
-			#clock-cells = <0>;
-			compatible = "allwinner,sun8i-h3-ahb2-clk";
-			reg = <0x01c2005c 0x4>;
-			clocks = <&ahb1>, <&pll6d2>;
-			clock-output-names = "ahb2";
-		};
-
-		apb1: apb1_clk@01c20054 {
-			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-apb0-clk";
-			reg = <0x01c20054 0x4>;
-			clocks = <&ahb1>;
-			clock-output-names = "apb1";
-		};
-
-		apb2: apb2_clk@01c20058 {
-			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-apb1-clk";
-			reg = <0x01c20058 0x4>;
-			clocks = <&osc32k>, <&osc24M>, <&pll6 0>, <&pll6 0>;
-			clock-output-names = "apb2";
-		};
-
-		bus_gates: clk@01c20060 {
-			#clock-cells = <1>;
-			compatible = "allwinner,sun8i-h3-bus-gates-clk";
-			reg = <0x01c20060 0x14>;
-			clocks = <&ahb1>, <&ahb2>, <&apb1>, <&apb2>;
-			clock-names = "ahb1", "ahb2", "apb1", "apb2";
-			clock-indices = <5>, <6>, <8>,
-					<9>, <10>, <13>,
-					<14>, <17>, <18>,
-					<19>, <20>,
-					<21>, <23>,
-					<24>, <25>,
-					<26>, <27>,
-					<28>, <29>,
-					<30>, <31>, <32>,
-					<35>, <36>, <37>,
-					<40>, <41>, <43>,
-					<44>, <52>, <53>,
-					<54>, <64>,
-					<65>, <69>, <72>,
-					<76>, <77>, <78>,
-					<96>, <97>, <98>,
-					<112>, <113>,
-					<114>, <115>,
-					<116>, <128>, <135>;
-			clock-output-names = "bus_ce", "bus_dma", "bus_mmc0",
-					     "bus_mmc1", "bus_mmc2", "bus_nand",
-					     "bus_sdram", "bus_gmac", "bus_ts",
-					     "bus_hstimer", "bus_spi0",
-					     "bus_spi1", "bus_otg",
-					     "bus_otg_ehci0", "bus_ehci1",
-					     "bus_ehci2", "bus_ehci3",
-					     "bus_otg_ohci0", "bus_ohci1",
-					     "bus_ohci2", "bus_ohci3", "bus_ve",
-					     "bus_lcd0", "bus_lcd1", "bus_deint",
-					     "bus_csi", "bus_tve", "bus_hdmi",
-					     "bus_de", "bus_gpu", "bus_msgbox",
-					     "bus_spinlock", "bus_codec",
-					     "bus_spdif", "bus_pio", "bus_ths",
-					     "bus_i2s0", "bus_i2s1", "bus_i2s2",
-					     "bus_i2c0", "bus_i2c1", "bus_i2c2",
-					     "bus_uart0", "bus_uart1",
-					     "bus_uart2", "bus_uart3",
-					     "bus_scr", "bus_ephy", "bus_dbg";
-		};
-
-		mmc0_clk: clk@01c20088 {
-			#clock-cells = <1>;
-			compatible = "allwinner,sun4i-a10-mmc-clk";
-			reg = <0x01c20088 0x4>;
-			clocks = <&osc24M>, <&pll6 0>, <&pll8>;
-			clock-output-names = "mmc0",
-					     "mmc0_output",
-					     "mmc0_sample";
-		};
-
-		mmc1_clk: clk@01c2008c {
-			#clock-cells = <1>;
-			compatible = "allwinner,sun4i-a10-mmc-clk";
-			reg = <0x01c2008c 0x4>;
-			clocks = <&osc24M>, <&pll6 0>, <&pll8>;
-			clock-output-names = "mmc1",
-					     "mmc1_output",
-					     "mmc1_sample";
-		};
-
-		mmc2_clk: clk@01c20090 {
-			#clock-cells = <1>;
-			compatible = "allwinner,sun4i-a10-mmc-clk";
-			reg = <0x01c20090 0x4>;
-			clocks = <&osc24M>, <&pll6 0>, <&pll8>;
-			clock-output-names = "mmc2",
-					     "mmc2_output",
-					     "mmc2_sample";
-		};
-
-		usb_clk: clk@01c200cc {
-			#clock-cells = <1>;
-			#reset-cells = <1>;
-			compatible = "allwinner,sun8i-h3-usb-clk";
-			reg = <0x01c200cc 0x4>;
-			clocks = <&osc24M>;
-			clock-output-names = "usb_phy0", "usb_phy1",
-					     "usb_phy2", "usb_phy3",
-					     "usb_ohci0", "usb_ohci1",
-					     "usb_ohci2", "usb_ohci3";
-		};
-
-		mbus_clk: clk@01c2015c {
-			#clock-cells = <0>;
-			compatible = "allwinner,sun8i-a23-mbus-clk";
-			reg = <0x01c2015c 0x4>;
-			clocks = <&osc24M>, <&pll6 1>, <&pll5>;
-			clock-output-names = "mbus";
-		};
-
 		apb0: apb0_clk {
 			compatible = "fixed-factor-clock";
 			#clock-cells = <0>;
@@ -327,23 +144,23 @@
 			compatible = "allwinner,sun8i-h3-dma";
 			reg = <0x01c02000 0x1000>;
 			interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bus_gates 6>;
-			resets = <&ahb_rst 6>;
+			clocks = <&ccu CLK_BUS_DMA>;
+			resets = <&ccu RST_BUS_DMA>;
 			#dma-cells = <1>;
 		};
 
 		mmc0: mmc@01c0f000 {
 			compatible = "allwinner,sun5i-a13-mmc";
 			reg = <0x01c0f000 0x1000>;
-			clocks = <&bus_gates 8>,
-				 <&mmc0_clk 0>,
-				 <&mmc0_clk 1>,
-				 <&mmc0_clk 2>;
+			clocks = <&ccu CLK_BUS_MMC0>,
+				 <&ccu CLK_MMC0>,
+				 <&ccu CLK_MMC0_OUTPUT>,
+				 <&ccu CLK_MMC0_SAMPLE>;
 			clock-names = "ahb",
 				      "mmc",
 				      "output",
 				      "sample";
-			resets = <&ahb_rst 8>;
+			resets = <&ccu RST_BUS_MMC0>;
 			reset-names = "ahb";
 			interrupts = <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
@@ -354,15 +171,15 @@
 		mmc1: mmc@01c10000 {
 			compatible = "allwinner,sun5i-a13-mmc";
 			reg = <0x01c10000 0x1000>;
-			clocks = <&bus_gates 9>,
-				 <&mmc1_clk 0>,
-				 <&mmc1_clk 1>,
-				 <&mmc1_clk 2>;
+			clocks = <&ccu CLK_BUS_MMC1>,
+				 <&ccu CLK_MMC1>,
+				 <&ccu CLK_MMC1_OUTPUT>,
+				 <&ccu CLK_MMC1_SAMPLE>;
 			clock-names = "ahb",
 				      "mmc",
 				      "output",
 				      "sample";
-			resets = <&ahb_rst 9>;
+			resets = <&ccu RST_BUS_MMC1>;
 			reset-names = "ahb";
 			interrupts = <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
@@ -373,15 +190,15 @@
 		mmc2: mmc@01c11000 {
 			compatible = "allwinner,sun5i-a13-mmc";
 			reg = <0x01c11000 0x1000>;
-			clocks = <&bus_gates 10>,
-				 <&mmc2_clk 0>,
-				 <&mmc2_clk 1>,
-				 <&mmc2_clk 2>;
+			clocks = <&ccu CLK_BUS_MMC2>,
+				 <&ccu CLK_MMC2>,
+				 <&ccu CLK_MMC2_OUTPUT>,
+				 <&ccu CLK_MMC2_SAMPLE>;
 			clock-names = "ahb",
 				      "mmc",
 				      "output",
 				      "sample";
-			resets = <&ahb_rst 10>;
+			resets = <&ccu RST_BUS_MMC2>;
 			reset-names = "ahb";
 			interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
@@ -401,18 +218,18 @@
 				    "pmu1",
 				    "pmu2",
 				    "pmu3";
-			clocks = <&usb_clk 8>,
-				 <&usb_clk 9>,
-				 <&usb_clk 10>,
-				 <&usb_clk 11>;
+			clocks = <&ccu CLK_USB_PHY0>,
+				 <&ccu CLK_USB_PHY1>,
+				 <&ccu CLK_USB_PHY2>,
+				 <&ccu CLK_USB_PHY3>;
 			clock-names = "usb0_phy",
 				      "usb1_phy",
 				      "usb2_phy",
 				      "usb3_phy";
-			resets = <&usb_clk 0>,
-				 <&usb_clk 1>,
-				 <&usb_clk 2>,
-				 <&usb_clk 3>;
+			resets = <&ccu RST_USB_PHY0>,
+				 <&ccu RST_USB_PHY1>,
+				 <&ccu RST_USB_PHY2>,
+				 <&ccu RST_USB_PHY3>;
 			reset-names = "usb0_reset",
 				      "usb1_reset",
 				      "usb2_reset",
@@ -425,8 +242,8 @@
 			compatible = "allwinner,sun8i-h3-ehci", "generic-ehci";
 			reg = <0x01c1b000 0x100>;
 			interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bus_gates 25>, <&bus_gates 29>;
-			resets = <&ahb_rst 25>, <&ahb_rst 29>;
+			clocks = <&ccu CLK_BUS_EHCI1>, <&ccu CLK_BUS_OHCI1>;
+			resets = <&ccu RST_BUS_EHCI1>, <&ccu RST_BUS_OHCI1>;
 			phys = <&usbphy 1>;
 			phy-names = "usb";
 			status = "disabled";
@@ -436,9 +253,9 @@
 			compatible = "allwinner,sun8i-h3-ohci", "generic-ohci";
 			reg = <0x01c1b400 0x100>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bus_gates 29>, <&bus_gates 25>,
-				 <&usb_clk 17>;
-			resets = <&ahb_rst 29>, <&ahb_rst 25>;
+			clocks = <&ccu CLK_BUS_EHCI1>, <&ccu CLK_BUS_OHCI1>,
+				 <&ccu CLK_USB_OHCI1>;
+			resets = <&ccu RST_BUS_EHCI1>, <&ccu RST_BUS_OHCI1>;
 			phys = <&usbphy 1>;
 			phy-names = "usb";
 			status = "disabled";
@@ -448,8 +265,8 @@
 			compatible = "allwinner,sun8i-h3-ehci", "generic-ehci";
 			reg = <0x01c1c000 0x100>;
 			interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bus_gates 26>, <&bus_gates 30>;
-			resets = <&ahb_rst 26>, <&ahb_rst 30>;
+			clocks = <&ccu CLK_BUS_EHCI2>, <&ccu CLK_BUS_OHCI2>;
+			resets = <&ccu RST_BUS_EHCI2>, <&ccu RST_BUS_OHCI2>;
 			phys = <&usbphy 2>;
 			phy-names = "usb";
 			status = "disabled";
@@ -459,9 +276,9 @@
 			compatible = "allwinner,sun8i-h3-ohci", "generic-ohci";
 			reg = <0x01c1c400 0x100>;
 			interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bus_gates 30>, <&bus_gates 26>,
-				 <&usb_clk 18>;
-			resets = <&ahb_rst 30>, <&ahb_rst 26>;
+			clocks = <&ccu CLK_BUS_EHCI2>, <&ccu CLK_BUS_OHCI2>,
+				 <&ccu CLK_USB_OHCI2>;
+			resets = <&ccu RST_BUS_EHCI2>, <&ccu RST_BUS_OHCI2>;
 			phys = <&usbphy 2>;
 			phy-names = "usb";
 			status = "disabled";
@@ -471,8 +288,8 @@
 			compatible = "allwinner,sun8i-h3-ehci", "generic-ehci";
 			reg = <0x01c1d000 0x100>;
 			interrupts = <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bus_gates 27>, <&bus_gates 31>;
-			resets = <&ahb_rst 27>, <&ahb_rst 31>;
+			clocks = <&ccu CLK_BUS_EHCI3>, <&ccu CLK_BUS_OHCI3>;
+			resets = <&ccu RST_BUS_EHCI3>, <&ccu RST_BUS_OHCI3>;
 			phys = <&usbphy 3>;
 			phy-names = "usb";
 			status = "disabled";
@@ -482,32 +299,34 @@
 			compatible = "allwinner,sun8i-h3-ohci", "generic-ohci";
 			reg = <0x01c1d400 0x100>;
 			interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bus_gates 31>, <&bus_gates 27>,
-				 <&usb_clk 19>;
-			resets = <&ahb_rst 31>, <&ahb_rst 27>;
+			clocks = <&ccu CLK_BUS_EHCI3>, <&ccu CLK_BUS_OHCI3>,
+				 <&ccu CLK_USB_OHCI3>;
+			resets = <&ccu RST_BUS_EHCI3>, <&ccu RST_BUS_OHCI3>;
 			phys = <&usbphy 3>;
 			phy-names = "usb";
 			status = "disabled";
 		};
 
+		ccu: clock@01c20000 {
+			compatible = "allwinner,sun8i-h3-ccu";
+			reg = <0x01c20000 0x400>;
+			clocks = <&osc24M>, <&osc32k>;
+			clock-names = "hosc", "losc";
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
 		pio: pinctrl@01c20800 {
 			compatible = "allwinner,sun8i-h3-pinctrl";
 			reg = <0x01c20800 0x400>;
 			interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&bus_gates 69>;
+			clocks = <&ccu CLK_BUS_PIO>;
 			gpio-controller;
 			#gpio-cells = <3>;
 			interrupt-controller;
 			#interrupt-cells = <3>;
 
-			uart0_pins_a: uart0@0 {
-				allwinner,pins = "PA4", "PA5";
-				allwinner,function = "uart0";
-				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
-			};
-
 			mmc0_pins_a: mmc0@0 {
 				allwinner,pins = "PF0", "PF1", "PF2", "PF3",
 						 "PF4", "PF5";
@@ -540,24 +359,20 @@
 				allwinner,drive = <SUN4I_PINCTRL_30_MA>;
 				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
-		};
 
-		ahb_rst: reset@01c202c0 {
-			#reset-cells = <1>;
-			compatible = "allwinner,sun6i-a31-ahb1-reset";
-			reg = <0x01c202c0 0xc>;
-		};
-
-		apb1_rst: reset@01c202d0 {
-			#reset-cells = <1>;
-			compatible = "allwinner,sun6i-a31-clock-reset";
-			reg = <0x01c202d0 0x4>;
-		};
+			uart0_pins_a: uart0@0 {
+				allwinner,pins = "PA4", "PA5";
+				allwinner,function = "uart0";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			};
 
-		apb2_rst: reset@01c202d8 {
-			#reset-cells = <1>;
-			compatible = "allwinner,sun6i-a31-clock-reset";
-			reg = <0x01c202d8 0x4>;
+			uart1_pins_a: uart1@0 {
+				allwinner,pins = "PG6", "PG7", "PG8", "PG9";
+				allwinner,function = "uart1";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+			};
 		};
 
 		timer@01c20c00 {
@@ -580,8 +395,8 @@
 			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
 			reg-shift = <2>;
 			reg-io-width = <4>;
-			clocks = <&bus_gates 112>;
-			resets = <&apb2_rst 16>;
+			clocks = <&ccu CLK_BUS_UART0>;
+			resets = <&ccu RST_BUS_UART0>;
 			dmas = <&dma 6>, <&dma 6>;
 			dma-names = "rx", "tx";
 			status = "disabled";
@@ -593,8 +408,8 @@
 			interrupts = <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>;
 			reg-shift = <2>;
 			reg-io-width = <4>;
-			clocks = <&bus_gates 113>;
-			resets = <&apb2_rst 17>;
+			clocks = <&ccu CLK_BUS_UART1>;
+			resets = <&ccu RST_BUS_UART1>;
 			dmas = <&dma 7>, <&dma 7>;
 			dma-names = "rx", "tx";
 			status = "disabled";
@@ -606,8 +421,8 @@
 			interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 			reg-shift = <2>;
 			reg-io-width = <4>;
-			clocks = <&bus_gates 114>;
-			resets = <&apb2_rst 18>;
+			clocks = <&ccu CLK_BUS_UART2>;
+			resets = <&ccu RST_BUS_UART2>;
 			dmas = <&dma 8>, <&dma 8>;
 			dma-names = "rx", "tx";
 			status = "disabled";
@@ -619,8 +434,8 @@
 			interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>;
 			reg-shift = <2>;
 			reg-io-width = <4>;
-			clocks = <&bus_gates 115>;
-			resets = <&apb2_rst 19>;
+			clocks = <&ccu CLK_BUS_UART3>;
+			resets = <&ccu RST_BUS_UART3>;
 			dmas = <&dma 9>, <&dma 9>;
 			dma-names = "rx", "tx";
 			status = "disabled";
diff --git a/arch/arm/boot/dts/sun8i-q8-common.dtsi b/arch/arm/boot/dts/sun8i-q8-common.dtsi
index 346a49d805a7..60fa9585022b 100644
--- a/arch/arm/boot/dts/sun8i-q8-common.dtsi
+++ b/arch/arm/boot/dts/sun8i-q8-common.dtsi
@@ -39,140 +39,13 @@
  *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  *     OTHER DEALINGS IN THE SOFTWARE.
  */
-#include "sunxi-q8-common.dtsi"
+#include "sunxi-reference-design-tablet.dtsi"
+#include "sun8i-reference-design-tablet.dtsi"
 
-#include <dt-bindings/pwm/pwm.h>
-
-/ {
-	aliases {
-		serial0 = &r_uart;
-	};
-
-	backlight: backlight {
-		compatible = "pwm-backlight";
-		pinctrl-names = "default";
-		pinctrl-0 = <&bl_en_pin_q8>;
-		pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>;
-		brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>;
-		default-brightness-level = <8>;
-		enable-gpios = <&pio 7 6 GPIO_ACTIVE_HIGH>; /* PH6 */
-	};
-
-	chosen {
-		stdout-path = "serial0:115200n8";
-	};
-};
-
-&mmc0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_q8>;
-	vmmc-supply = <&reg_dcdc1>;
-	bus-width = <4>;
-	cd-gpios = <&pio 1 4 GPIO_ACTIVE_HIGH>; /* PB4 */
-	cd-inverted;
-	status = "okay";
-};
-
-&pio {
-	bl_en_pin_q8: bl_en_pin@0 {
-		allwinner,pins = "PH6";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
-	};
-
-	mmc0_cd_pin_q8: mmc0_cd_pin@0 {
-		allwinner,pins = "PB4";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
-	};
-};
-
-&r_rsb {
-	status = "okay";
-
-	axp22x: pmic@3a3 {
-		compatible = "x-powers,axp223";
-		reg = <0x3a3>;
-		interrupt-parent = <&nmi_intc>;
-		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
-		eldoin-supply = <&reg_dcdc1>;
-	};
-};
-
-#include "axp22x.dtsi"
-
-&reg_aldo1 {
-	regulator-always-on;
-	regulator-min-microvolt = <3000000>;
-	regulator-max-microvolt = <3000000>;
-	regulator-name = "vcc-io";
-};
-
-&reg_aldo2 {
-	regulator-always-on;
-	regulator-min-microvolt = <2350000>;
-	regulator-max-microvolt = <2650000>;
-	regulator-name = "vdd-dll";
-};
-
-&reg_aldo3 {
-	regulator-always-on;
-	regulator-min-microvolt = <2700000>;
-	regulator-max-microvolt = <3300000>;
-	regulator-name = "vcc-pll-avcc";
-};
-
-&reg_dc1sw {
-	regulator-name = "vcc-lcd";
-};
-
-&reg_dc5ldo {
-	regulator-always-on;
-	regulator-min-microvolt = <900000>;
-	regulator-max-microvolt = <1400000>;
-	regulator-name = "vdd-cpus";
-};
-
-&reg_dcdc1 {
-	regulator-always-on;
-	regulator-min-microvolt = <3000000>;
-	regulator-max-microvolt = <3000000>;
-	regulator-name = "vcc-3v0";
-};
-
-&reg_dcdc2 {
-	regulator-always-on;
-	regulator-min-microvolt = <900000>;
-	regulator-max-microvolt = <1400000>;
-	regulator-name = "vdd-sys";
-};
-
-&reg_dcdc3 {
-	regulator-always-on;
-	regulator-min-microvolt = <900000>;
-	regulator-max-microvolt = <1400000>;
-	regulator-name = "vdd-cpu";
-};
-
-&reg_dcdc5 {
-	regulator-always-on;
-	regulator-min-microvolt = <1500000>;
-	regulator-max-microvolt = <1500000>;
-	regulator-name = "vcc-dram";
-};
-
-&reg_rtc_ldo {
-	regulator-name = "vcc-rtc";
-};
-
-&r_uart {
-	pinctrl-names = "default";
-	pinctrl-0 = <&r_uart_pins_a>;
-	status = "okay";
+&ehci0 {
+	status  = "okay";
 };
 
-&simplefb_lcd {
-	vcc-lcd-supply = <&reg_dc1sw>;
+&usbphy {
+	usb1_vbus-supply = <&reg_dldo1>;
 };
diff --git a/arch/arm/boot/dts/sun8i-r16-parrot.dts b/arch/arm/boot/dts/sun8i-r16-parrot.dts
new file mode 100644
index 000000000000..47553e522982
--- /dev/null
+++ b/arch/arm/boot/dts/sun8i-r16-parrot.dts
@@ -0,0 +1,351 @@
+/*
+ * Copyright 2016 Quentin Schulz
+ *
+ * Quentin Schulz <quentin.schulz@free-electrons.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+#include "sun8i-a33.dtsi"
+#include "sunxi-common-regulators.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+
+/ {
+	model = "Allwinner R16 EVB (Parrot)";
+	compatible = "allwinner,parrot", "allwinner,sun8i-a33";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&led_pins_parrot>;
+
+		led1 {
+			label = "parrot:led1:usr";
+			gpio = <&pio 4 17 GPIO_ACTIVE_HIGH>; /* PE17 */
+		};
+
+		led2 {
+			label = "parrot:led2:usr";
+			gpio = <&pio 4 16 GPIO_ACTIVE_HIGH>; /* PE16 */
+		};
+	};
+
+	wifi_pwrseq: wifi_pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		reset-gpios = <&r_pio 0 6 GPIO_ACTIVE_LOW>; /* PL06 */
+	};
+
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins_a>;
+	status = "okay";
+
+	/*
+	 * FIXME: An as-yet-unknown accelerometer is connected to this
+	 * i2c bus.
+	 */
+};
+
+&lradc {
+	vref-supply = <&reg_aldo3>;
+	status = "okay";
+
+	button@0 {
+		label = "V+";
+		linux,code = <KEY_VOLUMEUP>;
+		channel = <0>;
+		voltage = <190000>;
+	};
+
+	button@1 {
+		label = "V-";
+		linux,code = <KEY_VOLUMEDOWN>;
+		channel = <0>;
+		voltage = <390000>;
+	};
+
+};
+
+&mmc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin_parrot>;
+	vmmc-supply = <&reg_dcdc1>;
+	cd-gpios = <&pio 3 14 GPIO_ACTIVE_LOW>; /* PD14 */
+	bus-width = <4>;
+	status = "okay";
+};
+
+&mmc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins_a>, <&wifi_reset_pin_parrot>;
+	vmmc-supply = <&reg_aldo1>;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	bus-width = <4>;
+	non-removable;
+	status = "okay";
+};
+
+&mmc2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc2_8bit_pins>;
+	vmmc-supply = <&reg_dcdc1>;
+	bus-width = <8>;
+	non-removable;
+	cap-mmc-hw-reset;
+	status = "okay";
+};
+
+&mmc2_8bit_pins {
+	allwinner,drive = <SUN4I_PINCTRL_40_MA>;
+	allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+};
+
+&ohci0 {
+	status = "okay";
+};
+
+&pio {
+	mmc0_cd_pin_parrot: mmc0_cd_pin@0 {
+		allwinner,pins = "PD14";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
+	led_pins_parrot: led_pins@0 {
+		allwinner,pins = "PE16", "PE17";
+		allwinner,function = "gpio_out";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
+	usb0_id_det: usb0_id_detect_pin@0 {
+		allwinner,pins = "PD10";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
+	usb1_vbus_pin_parrot: usb1_vbus_pin@0 {
+		allwinner,pins = "PD12";
+		allwinner,function = "gpio_out";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+};
+
+&r_pio {
+	wifi_reset_pin_parrot: wifi_reset_pin@0 {
+		allwinner,pins = "PL6";
+		allwinner,function = "gpio_out";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+};
+
+&r_rsb {
+	status = "okay";
+
+	axp22x: pmic@3a3 {
+		compatible = "x-powers,axp223";
+		reg = <0x3a3>;
+		interrupt-parent = <&nmi_intc>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+		drivevbus-supply = <&reg_vcc5v0>;
+		x-powers,drive-vbus-en;
+	};
+};
+
+#include "axp22x.dtsi"
+
+&reg_aldo1 {
+	regulator-always-on;
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "vcc-io";
+};
+
+&reg_aldo2 {
+	regulator-always-on;
+	regulator-min-microvolt = <2350000>;
+	regulator-max-microvolt = <2650000>;
+	regulator-name = "vdd-dll";
+};
+
+&reg_aldo3 {
+	regulator-always-on;
+	regulator-min-microvolt = <2700000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-pll-avcc";
+};
+
+&reg_dc5ldo {
+	regulator-always-on;
+	regulator-min-microvolt = <900000>;
+	regulator-max-microvolt = <1400000>;
+	regulator-name = "vdd-cpus";
+};
+
+&reg_dcdc1 {
+	regulator-always-on;
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "vcc-3v0";
+};
+
+&reg_dcdc2 {
+	regulator-always-on;
+	regulator-min-microvolt = <900000>;
+	regulator-max-microvolt = <1400000>;
+	regulator-name = "vdd-sys";
+};
+
+&reg_dcdc3 {
+	regulator-always-on;
+	regulator-min-microvolt = <900000>;
+	regulator-max-microvolt = <1400000>;
+	regulator-name = "vdd-cpu";
+};
+
+&reg_dcdc5 {
+	regulator-always-on;
+	regulator-min-microvolt = <1500000>;
+	regulator-max-microvolt = <1500000>;
+	regulator-name = "vcc-dram";
+};
+
+&reg_dldo1 {
+	/*
+	 * TODO: WiFi chip needs dldo1 AND dldo2 to be on to be powered.
+	 * Remove next line once it is possible to sync two regulators.
+	 */
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi0";
+};
+
+&reg_dldo2 {
+	/*
+	 * TODO: WiFi chip needs dldo1 AND dldo2 to be on to be powered.
+	 * Remove next line once it is possible to sync two regulators.
+	 */
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi1";
+};
+
+&reg_dldo3 {
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "vcc-3v0-csi";
+};
+
+&reg_drivevbus {
+	regulator-name = "usb0-vbus";
+	status = "okay";
+};
+
+&reg_eldo1 {
+	regulator-min-microvolt = <1200000>;
+	regulator-max-microvolt = <1200000>;
+	regulator-name = "vcc-1v2-hsic";
+};
+
+&reg_eldo2 {
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "vcc-dsp";
+};
+
+&reg_eldo3 {
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "eldo3";
+};
+
+&reg_usb1_vbus {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb1_vbus_pin_parrot>;
+	gpio = <&pio 3 12 GPIO_ACTIVE_HIGH>; /* PD12 */
+	status = "okay";
+};
+
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pins_b>;
+	status = "okay";
+};
+
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
+&usb_power_supply {
+	status = "okay";
+};
+
+&usbphy {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_det>;
+	usb0_vbus-supply = <&reg_drivevbus>;
+	usb0_id_det-gpios = <&pio 3 10 GPIO_ACTIVE_HIGH>; /* PD10 */
+	usb0_vbus_power-supply = <&usb_power_supply>;
+	usb1_vbus-supply = <&reg_usb1_vbus>;
+};
diff --git a/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi b/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi
new file mode 100644
index 000000000000..9d9036140511
--- /dev/null
+++ b/arch/arm/boot/dts/sun8i-reference-design-tablet.dtsi
@@ -0,0 +1,216 @@
+/*
+ * Copyright 2015 Hans de Goede <hdegoede@redhat.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "sunxi-reference-design-tablet.dtsi"
+
+#include <dt-bindings/pwm/pwm.h>
+
+/ {
+	aliases {
+		serial0 = &r_uart;
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		pinctrl-names = "default";
+		pinctrl-0 = <&bl_en_pin>;
+		pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>;
+		brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>;
+		default-brightness-level = <8>;
+		enable-gpios = <&pio 7 6 GPIO_ACTIVE_HIGH>; /* PH6 */
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+};
+
+&mmc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
+	vmmc-supply = <&reg_dcdc1>;
+	bus-width = <4>;
+	cd-gpios = <&pio 1 4 GPIO_ACTIVE_HIGH>; /* PB4 */
+	cd-inverted;
+	status = "okay";
+};
+
+&pio {
+	bl_en_pin: bl_en_pin@0 {
+		allwinner,pins = "PH6";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
+	mmc0_cd_pin: mmc0_cd_pin@0 {
+		allwinner,pins = "PB4";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+
+	usb0_id_detect_pin: usb0_id_detect_pin@0 {
+		allwinner,pins = "PH8";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+};
+
+&r_rsb {
+	status = "okay";
+
+	axp22x: pmic@3a3 {
+		compatible = "x-powers,axp223";
+		reg = <0x3a3>;
+		interrupt-parent = <&nmi_intc>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+		eldoin-supply = <&reg_dcdc1>;
+		drivevbus-supply = <&reg_vcc5v0>;
+		x-powers,drive-vbus-en;
+	};
+};
+
+#include "axp22x.dtsi"
+
+&reg_aldo1 {
+	regulator-always-on;
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "vcc-io";
+};
+
+&reg_aldo2 {
+	regulator-always-on;
+	regulator-min-microvolt = <2350000>;
+	regulator-max-microvolt = <2650000>;
+	regulator-name = "vdd-dll";
+};
+
+&reg_aldo3 {
+	regulator-always-on;
+	regulator-min-microvolt = <2700000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-pll-avcc";
+};
+
+&reg_dc1sw {
+	regulator-name = "vcc-lcd";
+};
+
+&reg_dc5ldo {
+	regulator-always-on;
+	regulator-min-microvolt = <900000>;
+	regulator-max-microvolt = <1400000>;
+	regulator-name = "vdd-cpus";
+};
+
+&reg_dcdc1 {
+	regulator-always-on;
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "vcc-3v0";
+};
+
+&reg_dcdc2 {
+	regulator-always-on;
+	regulator-min-microvolt = <900000>;
+	regulator-max-microvolt = <1400000>;
+	regulator-name = "vdd-sys";
+};
+
+&reg_dcdc3 {
+	regulator-always-on;
+	regulator-min-microvolt = <900000>;
+	regulator-max-microvolt = <1400000>;
+	regulator-name = "vdd-cpu";
+};
+
+&reg_dcdc5 {
+	regulator-always-on;
+	regulator-min-microvolt = <1500000>;
+	regulator-max-microvolt = <1500000>;
+	regulator-name = "vcc-dram";
+};
+
+&reg_dldo1 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi";
+};
+
+&reg_drivevbus {
+	regulator-name = "usb0-vbus";
+	status = "okay";
+};
+
+&reg_rtc_ldo {
+	regulator-name = "vcc-rtc";
+};
+
+&r_uart {
+	pinctrl-names = "default";
+	pinctrl-0 = <&r_uart_pins_a>;
+	status = "okay";
+};
+
+&simplefb_lcd {
+	vcc-lcd-supply = <&reg_dc1sw>;
+};
+
+&usb_otg {
+	dr_mode = "otg";
+	status = "okay";
+};
+
+&usb_power_supply {
+	status = "okay";
+};
+
+&usbphy {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_id_detect_pin>;
+	usb0_id_det-gpio = <&pio 7 8 GPIO_ACTIVE_HIGH>; /* PH8 */
+	usb0_vbus_power-supply = <&usb_power_supply>;
+	usb0_vbus-supply = <&reg_drivevbus>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts
index eb2ccd0a3bd5..1526b41c70f1 100644
--- a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts
+++ b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts
@@ -45,7 +45,6 @@
 
 /dts-v1/;
 #include "sun9i-a80.dtsi"
-#include "sunxi-common-regulators.dtsi"
 
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/pinctrl/sun4i-a10.h>
@@ -79,26 +78,10 @@
 	};
 };
 
-&pio {
-	led_pins_cubieboard4: led-pins@0 {
-		allwinner,pins = "PH6", "PH17";
-		allwinner,function = "gpio_out";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
-	};
-
-	mmc0_cd_pin_cubieboard4: mmc0_cd_pin@0 {
-		allwinner,pins = "PH18";
-		allwinner,function = "gpio_in";
-		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
-		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
-	};
-};
-
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins>, <&mmc0_cd_pin_cubieboard4>;
-	vmmc-supply = <&reg_vcc3v0>;
+	vmmc-supply = <&reg_dcdc1>;
 	bus-width = <4>;
 	cd-gpios = <&pio 7 18 GPIO_ACTIVE_HIGH>; /* PH18 */
 	cd-inverted;
@@ -108,7 +91,7 @@
 &mmc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc2_8bit_pins>;
-	vmmc-supply = <&reg_vcc3v0>;
+	vmmc-supply = <&reg_dcdc1>;
 	bus-width = <8>;
 	non-removable;
 	cap-mmc-hw-reset;
@@ -120,14 +103,157 @@
 	allwinner,drive = <SUN4I_PINCTRL_40_MA>;
 };
 
+&pio {
+	led_pins_cubieboard4: led-pins@0 {
+		allwinner,pins = "PH6", "PH17";
+		allwinner,function = "gpio_out";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
+	};
+
+	mmc0_cd_pin_cubieboard4: mmc0_cd_pin@0 {
+		allwinner,pins = "PH18";
+		allwinner,function = "gpio_in";
+		allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+		allwinner,pull = <SUN4I_PINCTRL_PULL_UP>;
+	};
+};
+
 &r_ir {
 	status = "okay";
 };
 
 &r_rsb {
 	status = "okay";
+
+	axp809: pmic@3a3 {
+		reg = <0x3a3>;
+		interrupt-parent = <&nmi_intc>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+
+		regulators {
+			reg_aldo1: aldo1 {
+				/*
+				 * TODO: This should be handled by the
+				 * USB PHY driver.
+				 */
+				regulator-always-on;
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-name = "vcc33-usbh";
+			};
+
+			reg_aldo2: aldo2 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc-pb-io-cam";
+			};
+
+			aldo3 {
+				/* unused */
+			};
+
+			reg_dc5ldo: dc5ldo {
+				regulator-always-on;
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-cpus-09-usbh";
+			};
+
+			reg_dcdc1: dcdc1 {
+				regulator-always-on;
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-name = "vcc-3v";
+			};
+
+			reg_dcdc2: dcdc2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-gpu";
+			};
+
+			reg_dcdc3: dcdc3 {
+				regulator-always-on;
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-cpua";
+			};
+
+			reg_dcdc4: dcdc4 {
+				regulator-always-on;
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-sys-usb0-hdmi";
+			};
+
+			reg_dcdc5: dcdc5 {
+				regulator-always-on;
+				regulator-min-microvolt = <1425000>;
+				regulator-max-microvolt = <1575000>;
+				regulator-name = "vcc-dram";
+			};
+
+			reg_dldo1: dldo1 {
+				/*
+				 * The WiFi chip supports a wide range
+				 * (3.0 ~ 4.8V) of voltages, and so does
+				 * this regulator (3.0 ~ 4.2V), but
+				 * Allwinner SDK always sets it to 3.3V.
+				 */
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc-wifi";
+			};
+
+			reg_dldo2: dldo2 {
+				regulator-always-on;
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-name = "vcc-pl";
+			};
+
+			reg_eldo1: eldo1 {
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-name = "vcc-dvdd-cam";
+			};
+
+			reg_eldo2: eldo2 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc-pe";
+			};
+
+			reg_eldo3: eldo3 {
+				regulator-always-on;
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-name = "vcc-pm-codec-io1";
+			};
+
+			reg_ldo_io0: ldo_io0 {
+				regulator-always-on;
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-name = "vcc-pg";
+			};
+
+			reg_ldo_io1: ldo_io1 {
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <2500000>;
+				regulator-name = "vcc-pa-gmac-2v5";
+			};
+
+			reg_rtc_ldo: rtc_ldo {
+				regulator-name = "vcc-rtc-vdd1v8-io";
+			};
+		};
+	};
 };
 
+#include "axp809.dtsi"
+
 &uart0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart0_pins_a>;
diff --git a/arch/arm/boot/dts/sun9i-a80-optimus.dts b/arch/arm/boot/dts/sun9i-a80-optimus.dts
index d7a20d92b114..7fd22e888602 100644
--- a/arch/arm/boot/dts/sun9i-a80-optimus.dts
+++ b/arch/arm/boot/dts/sun9i-a80-optimus.dts
@@ -44,7 +44,6 @@
 
 /dts-v1/;
 #include "sun9i-a80.dtsi"
-#include "sunxi-common-regulators.dtsi"
 
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/pinctrl/sun4i-a10.h>
@@ -85,6 +84,17 @@
 		};
 	};
 
+	reg_usb1_vbus: usb1-vbus {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb1_vbus_pin_optimus>;
+		regulator-name = "usb1-vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		enable-active-high;
+		gpio = <&pio 7 4 GPIO_ACTIVE_HIGH>; /* PH4 */
+	};
+
 	reg_usb3_vbus: usb3-vbus {
 		compatible = "regulator-fixed";
 		pinctrl-names = "default";
@@ -109,6 +119,31 @@
 	status = "okay";
 };
 
+&mmc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc0_pins>, <&mmc0_cd_pin_optimus>;
+	vmmc-supply = <&reg_dcdc1>;
+	bus-width = <4>;
+	cd-gpios = <&pio 7 18 GPIO_ACTIVE_HIGH>; /* PH8 */
+	cd-inverted;
+	status = "okay";
+};
+
+&mmc2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc2_8bit_pins>;
+	vmmc-supply = <&reg_dcdc1>;
+	bus-width = <8>;
+	non-removable;
+	cap-mmc-hw-reset;
+	status = "okay";
+};
+
+&mmc2_8bit_pins {
+	/* Increase drive strength for DDR modes */
+	allwinner,drive = <SUN4I_PINCTRL_40_MA>;
+};
+
 &ohci0 {
 	status = "okay";
 };
@@ -147,37 +182,6 @@
 	};
 };
 
-&mmc0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&mmc0_pins>, <&mmc0_cd_pin_optimus>;
-	vmmc-supply = <&reg_vcc3v0>;
-	bus-width = <4>;
-	cd-gpios = <&pio 7 18 GPIO_ACTIVE_HIGH>; /* PH8 */
-	cd-inverted;
-	status = "okay";
-};
-
-&mmc2 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&mmc2_8bit_pins>;
-	vmmc-supply = <&reg_vcc3v0>;
-	bus-width = <8>;
-	non-removable;
-	cap-mmc-hw-reset;
-	status = "okay";
-};
-
-&mmc2_8bit_pins {
-	/* Increase drive strength for DDR modes */
-	allwinner,drive = <SUN4I_PINCTRL_40_MA>;
-};
-
-&reg_usb1_vbus {
-	pinctrl-0 = <&usb1_vbus_pin_optimus>;
-	gpio = <&pio 7 4 GPIO_ACTIVE_HIGH>; /* PH4 */
-	status = "okay";
-};
-
 &r_ir {
 	status = "okay";
 };
@@ -193,8 +197,135 @@
 
 &r_rsb {
 	status = "okay";
+
+	axp809: pmic@3a3 {
+		reg = <0x3a3>;
+		interrupt-parent = <&nmi_intc>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+
+		regulators {
+			reg_aldo1: aldo1 {
+				/*
+				 * TODO: This should be handled by the
+				 * USB PHY driver.
+				 */
+				regulator-always-on;
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-name = "vcc33-usbh";
+			};
+
+			reg_aldo2: aldo2 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc-pb-io-cam";
+			};
+
+			aldo3 {
+				/* unused */
+			};
+
+			reg_dc5ldo: dc5ldo {
+				regulator-always-on;
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-cpus-09-usbh";
+			};
+
+			reg_dcdc1: dcdc1 {
+				regulator-always-on;
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-name = "vcc-3v";
+			};
+
+			reg_dcdc2: dcdc2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-gpu";
+			};
+
+			reg_dcdc3: dcdc3 {
+				regulator-always-on;
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-cpua";
+			};
+
+			reg_dcdc4: dcdc4 {
+				regulator-always-on;
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-sys-usb0-hdmi";
+			};
+
+			reg_dcdc5: dcdc5 {
+				regulator-always-on;
+				regulator-min-microvolt = <1425000>;
+				regulator-max-microvolt = <1575000>;
+				regulator-name = "vcc-dram";
+			};
+
+			reg_dldo1: dldo1 {
+				/*
+				 * The WiFi chip supports a wide range
+				 * (3.0 ~ 4.8V) of voltages, and so does
+				 * this regulator (3.0 ~ 4.2V), but
+				 * Allwinner SDK always sets it to 3.3V.
+				 */
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc-wifi";
+			};
+
+			reg_dldo2: dldo2 {
+				regulator-always-on;
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-name = "vcc-pl";
+			};
+
+			reg_eldo1: eldo1 {
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-name = "vcc-dvdd-cam";
+			};
+
+			reg_eldo2: eldo2 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc-pe";
+			};
+
+			reg_eldo3: eldo3 {
+				regulator-always-on;
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-name = "vcc-pm-codec-io1";
+			};
+
+			reg_ldo_io0: ldo_io0 {
+				regulator-always-on;
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-name = "vcc-pg";
+			};
+
+			reg_ldo_io1: ldo_io1 {
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <2500000>;
+				regulator-name = "vcc-pa-gmac-2v5";
+			};
+
+			reg_rtc_ldo: rtc_ldo {
+				regulator-name = "vcc-rtc-vdd1v8-io";
+			};
+		};
+	};
 };
 
+#include "axp809.dtsi"
+
 &uart0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart0_pins_a>;
diff --git a/arch/arm/boot/dts/sunxi-q8-common.dtsi b/arch/arm/boot/dts/sunxi-reference-design-tablet.dtsi
index b8241462fcea..b8241462fcea 100644
--- a/arch/arm/boot/dts/sunxi-q8-common.dtsi
+++ b/arch/arm/boot/dts/sunxi-reference-design-tablet.dtsi
diff --git a/arch/arm/boot/dts/tegra114-dalmore.dts b/arch/arm/boot/dts/tegra114-dalmore.dts
index c970bf65c74c..1dfc492cc004 100644
--- a/arch/arm/boot/dts/tegra114-dalmore.dts
+++ b/arch/arm/boot/dts/tegra114-dalmore.dts
@@ -1149,7 +1149,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra114-roth.dts b/arch/arm/boot/dts/tegra114-roth.dts
index 9d868af97b8e..70cf40996c3f 100644
--- a/arch/arm/boot/dts/tegra114-roth.dts
+++ b/arch/arm/boot/dts/tegra114-roth.dts
@@ -1020,9 +1020,9 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		clk32k_in: clock {
+		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra114-tn7.dts b/arch/arm/boot/dts/tegra114-tn7.dts
index 89047edb5c5f..17dd14545862 100644
--- a/arch/arm/boot/dts/tegra114-tn7.dts
+++ b/arch/arm/boot/dts/tegra114-tn7.dts
@@ -277,7 +277,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		clk32k_in: clock {
+		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
 			reg = <0>;
 			#clock-cells = <0>;
diff --git a/arch/arm/boot/dts/tegra124-apalis-emc.dtsi b/arch/arm/boot/dts/tegra124-apalis-emc.dtsi
new file mode 100644
index 000000000000..ca2c3a557895
--- /dev/null
+++ b/arch/arm/boot/dts/tegra124-apalis-emc.dtsi
@@ -0,0 +1,1502 @@
+/*
+ * Copyright 2016 Toradex AG
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/ {
+	clock@60006000 {
+		emc-timings-1 {
+			nvidia,ram-code = <1>;
+
+			timing-12750000 {
+				clock-frequency = <12750000>;
+				nvidia,parent-clock-frequency = <408000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_P>;
+				clock-names = "emc-parent";
+			};
+			timing-20400000 {
+				clock-frequency = <20400000>;
+				nvidia,parent-clock-frequency = <408000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_P>;
+				clock-names = "emc-parent";
+			};
+			timing-40800000 {
+				clock-frequency = <40800000>;
+				nvidia,parent-clock-frequency = <408000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_P>;
+				clock-names = "emc-parent";
+			};
+			timing-68000000 {
+				clock-frequency = <68000000>;
+				nvidia,parent-clock-frequency = <408000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_P>;
+				clock-names = "emc-parent";
+			};
+			timing-102000000 {
+				clock-frequency = <102000000>;
+				nvidia,parent-clock-frequency = <408000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_P>;
+				clock-names = "emc-parent";
+			};
+			timing-204000000 {
+				clock-frequency = <204000000>;
+				nvidia,parent-clock-frequency = <408000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_P>;
+				clock-names = "emc-parent";
+			};
+			timing-300000000 {
+				clock-frequency = <300000000>;
+				nvidia,parent-clock-frequency = <600000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_C>;
+				clock-names = "emc-parent";
+			};
+			timing-396000000 {
+				clock-frequency = <396000000>;
+				nvidia,parent-clock-frequency = <792000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_M>;
+				clock-names = "emc-parent";
+			};
+			timing-528000000 {
+				clock-frequency = <528000000>;
+				nvidia,parent-clock-frequency = <528000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_M_UD>;
+				clock-names = "emc-parent";
+			};
+			timing-600000000 {
+				clock-frequency = <600000000>;
+				nvidia,parent-clock-frequency = <600000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_C_UD>;
+				clock-names = "emc-parent";
+			};
+			timing-792000000 {
+				clock-frequency = <792000000>;
+				nvidia,parent-clock-frequency = <792000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_M_UD>;
+				clock-names = "emc-parent";
+			};
+			timing-924000000 {
+				clock-frequency = <924000000>;
+				nvidia,parent-clock-frequency = <924000000>;
+				clocks = <&tegra_car TEGRA124_CLK_PLL_M_UD>;
+				clock-names = "emc-parent";
+			};
+		};
+	};
+
+	emc@7001b000 {
+		emc-timings-1 {
+			nvidia,ram-code = <1>;
+
+			timing-12750000 {
+				clock-frequency = <12750000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000008>;
+				nvidia,emc-cfg = <0x73240000>;
+				nvidia,emc-cfg-2 = <0x000008c5>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100003>;
+				nvidia,emc-mode-2 = <0x80200008>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80001221>;
+				nvidia,emc-mrs-wait-cnt = <0x000e000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040128>;
+				nvidia,emc-xm2dqspadctrl2 = <0x0130b118>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00000000>;
+
+				nvidia,emc-configuration = <
+					0x00000000 0x00000003
+					0x00000000 0x00000000
+					0x00000000 0x00000004
+					0x0000000a 0x00000005
+					0x0000000b 0x00000000
+					0x00000000 0x00000003
+					0x00000003 0x00000000
+					0x00000006 0x00000006
+					0x00000006 0x00000002
+					0x00000000 0x00000005
+					0x00000005 0x00010000
+					0x00000003 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000004
+					0x0000000c 0x0000000d
+					0x0000000f 0x00000060
+					0x00000000 0x00000018
+					0x00000002 0x00000002
+					0x00000001 0x00000000
+					0x00000007 0x0000000f
+					0x00000005 0x00000005
+					0x00000004 0x00000005
+					0x00000004 0x00000000
+					0x00000000 0x00000005
+					0x00000005 0x00000064
+					0x00000000 0x00000000
+					0x00000000 0x106aa298
+					0x002c00a0 0x00008000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x000fc000 0x000fc000
+					0x000fc000 0x000fc000
+					0x0000fc00 0x0000fc00
+					0x0000fc00 0x0000fc00
+					0x10000280 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc081
+					0x00000e0e 0x81f1f108
+					0x07070004 0x0000003f
+					0x016eeeee 0x51451400
+					0x00514514 0x00514514
+					0x51451400 0x0000003f
+					0x00000007 0x00000000
+					0x00000042 0x000e000e
+					0x00000000 0x00000003
+					0x0000f2f3 0x800001c5
+					0x0000000a
+				>;
+			};
+
+			timing-20400000 {
+				clock-frequency = <20400000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000008>;
+				nvidia,emc-cfg = <0x73240000>;
+				nvidia,emc-cfg-2 = <0x000008c5>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100003>;
+				nvidia,emc-mode-2 = <0x80200008>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80001221>;
+				nvidia,emc-mrs-wait-cnt = <0x000e000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040128>;
+				nvidia,emc-xm2dqspadctrl2 = <0x0130b118>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00000000>;
+
+				nvidia,emc-configuration = <
+					0x00000000 0x00000005
+					0x00000000 0x00000000
+					0x00000000 0x00000004
+					0x0000000a 0x00000005
+					0x0000000b 0x00000000
+					0x00000000 0x00000003
+					0x00000003 0x00000000
+					0x00000006 0x00000006
+					0x00000006 0x00000002
+					0x00000000 0x00000005
+					0x00000005 0x00010000
+					0x00000003 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000004
+					0x0000000c 0x0000000d
+					0x0000000f 0x0000009a
+					0x00000000 0x00000026
+					0x00000002 0x00000002
+					0x00000001 0x00000000
+					0x00000007 0x0000000f
+					0x00000006 0x00000006
+					0x00000004 0x00000005
+					0x00000004 0x00000000
+					0x00000000 0x00000005
+					0x00000005 0x000000a0
+					0x00000000 0x00000000
+					0x00000000 0x106aa298
+					0x002c00a0 0x00008000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x000fc000 0x000fc000
+					0x000fc000 0x000fc000
+					0x0000fc00 0x0000fc00
+					0x0000fc00 0x0000fc00
+					0x10000280 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc081
+					0x00000e0e 0x81f1f108
+					0x07070004 0x0000003f
+					0x016eeeee 0x51451400
+					0x00514514 0x00514514
+					0x51451400 0x0000003f
+					0x0000000b 0x00000000
+					0x00000042 0x000e000e
+					0x00000000 0x00000003
+					0x0000f2f3 0x8000023a
+					0x0000000a
+				>;
+			};
+
+			timing-40800000 {
+				clock-frequency = <40800000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000008>;
+				nvidia,emc-cfg = <0x73240000>;
+				nvidia,emc-cfg-2 = <0x000008c5>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100003>;
+				nvidia,emc-mode-2 = <0x80200008>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80001221>;
+				nvidia,emc-mrs-wait-cnt = <0x000e000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040128>;
+				nvidia,emc-xm2dqspadctrl2 = <0x0130b118>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00000000>;
+
+				nvidia,emc-configuration = <
+					0x00000001 0x0000000a
+					0x00000000 0x00000001
+					0x00000000 0x00000004
+					0x0000000a 0x00000005
+					0x0000000b 0x00000000
+					0x00000000 0x00000003
+					0x00000003 0x00000000
+					0x00000006 0x00000006
+					0x00000006 0x00000002
+					0x00000000 0x00000005
+					0x00000005 0x00010000
+					0x00000003 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000004
+					0x0000000c 0x0000000d
+					0x0000000f 0x00000134
+					0x00000000 0x0000004d
+					0x00000002 0x00000002
+					0x00000001 0x00000000
+					0x00000008 0x0000000f
+					0x0000000c 0x0000000c
+					0x00000004 0x00000005
+					0x00000004 0x00000000
+					0x00000000 0x00000005
+					0x00000005 0x0000013f
+					0x00000000 0x00000000
+					0x00000000 0x106aa298
+					0x002c00a0 0x00008000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x000fc000 0x000fc000
+					0x000fc000 0x000fc000
+					0x0000fc00 0x0000fc00
+					0x0000fc00 0x0000fc00
+					0x10000280 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc081
+					0x00000e0e 0x81f1f108
+					0x07070004 0x0000003f
+					0x016eeeee 0x51451400
+					0x00514514 0x00514514
+					0x51451400 0x0000003f
+					0x00000015 0x00000000
+					0x00000042 0x000e000e
+					0x00000000 0x00000003
+					0x0000f2f3 0x80000370
+					0x0000000a
+				>;
+			};
+
+			timing-68000000 {
+				clock-frequency = <68000000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000008>;
+				nvidia,emc-cfg = <0x73240000>;
+				nvidia,emc-cfg-2 = <0x000008c5>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100003>;
+				nvidia,emc-mode-2 = <0x80200008>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80001221>;
+				nvidia,emc-mrs-wait-cnt = <0x000e000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040128>;
+				nvidia,emc-xm2dqspadctrl2 = <0x0130b118>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00000000>;
+
+				nvidia,emc-configuration = <
+					0x00000003 0x00000011
+					0x00000000 0x00000002
+					0x00000000 0x00000004
+					0x0000000a 0x00000005
+					0x0000000b 0x00000000
+					0x00000000 0x00000003
+					0x00000003 0x00000000
+					0x00000006 0x00000006
+					0x00000006 0x00000002
+					0x00000000 0x00000005
+					0x00000005 0x00010000
+					0x00000003 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000004
+					0x0000000c 0x0000000d
+					0x0000000f 0x00000202
+					0x00000000 0x00000080
+					0x00000002 0x00000002
+					0x00000001 0x00000000
+					0x0000000f 0x0000000f
+					0x00000013 0x00000013
+					0x00000004 0x00000005
+					0x00000004 0x00000001
+					0x00000000 0x00000005
+					0x00000005 0x00000213
+					0x00000000 0x00000000
+					0x00000000 0x106aa298
+					0x002c00a0 0x00008000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x000fc000 0x000fc000
+					0x000fc000 0x000fc000
+					0x0000fc00 0x0000fc00
+					0x0000fc00 0x0000fc00
+					0x10000280 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc081
+					0x00000e0e 0x81f1f108
+					0x07070004 0x0000003f
+					0x016eeeee 0x51451400
+					0x00514514 0x00514514
+					0x51451400 0x0000003f
+					0x00000022 0x00000000
+					0x00000042 0x000e000e
+					0x00000000 0x00000003
+					0x0000f2f3 0x8000050e
+					0x0000000a
+				>;
+			};
+
+			timing-102000000 {
+				clock-frequency = <102000000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000008>;
+				nvidia,emc-cfg = <0x73240000>;
+				nvidia,emc-cfg-2 = <0x000008c5>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100003>;
+				nvidia,emc-mode-2 = <0x80200008>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80001221>;
+				nvidia,emc-mrs-wait-cnt = <0x000e000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040128>;
+				nvidia,emc-xm2dqspadctrl2 = <0x0130b118>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00000000>;
+
+				nvidia,emc-configuration = <
+					0x00000004 0x0000001a
+					0x00000000 0x00000003
+					0x00000001 0x00000004
+					0x0000000a 0x00000005
+					0x0000000b 0x00000001
+					0x00000001 0x00000003
+					0x00000003 0x00000000
+					0x00000006 0x00000006
+					0x00000006 0x00000002
+					0x00000000 0x00000005
+					0x00000005 0x00010000
+					0x00000003 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000004
+					0x0000000c 0x0000000d
+					0x0000000f 0x00000304
+					0x00000000 0x000000c1
+					0x00000002 0x00000002
+					0x00000001 0x00000000
+					0x00000018 0x0000000f
+					0x0000001c 0x0000001c
+					0x00000004 0x00000005
+					0x00000004 0x00000002
+					0x00000000 0x00000005
+					0x00000005 0x0000031c
+					0x00000000 0x00000000
+					0x00000000 0x106aa298
+					0x002c00a0 0x00008000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x000fc000 0x000fc000
+					0x000fc000 0x000fc000
+					0x0000fc00 0x0000fc00
+					0x0000fc00 0x0000fc00
+					0x10000280 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc081
+					0x00000e0e 0x81f1f108
+					0x07070004 0x0000003f
+					0x016eeeee 0x51451400
+					0x00514514 0x00514514
+					0x51451400 0x0000003f
+					0x00000033 0x00000000
+					0x00000042 0x000e000e
+					0x00000000 0x00000003
+					0x0000f2f3 0x80000713
+					0x0000000a
+				>;
+			};
+
+			timing-204000000 {
+				clock-frequency = <204000000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000008>;
+				nvidia,emc-cfg = <0x73240000>;
+				nvidia,emc-cfg-2 = <0x000008cd>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100003>;
+				nvidia,emc-mode-2 = <0x80200008>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80001221>;
+				nvidia,emc-mrs-wait-cnt = <0x000e000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040128>;
+				nvidia,emc-xm2dqspadctrl2 = <0x0130b118>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00020000>;
+
+				nvidia,emc-configuration = <
+					0x00000009 0x00000035
+					0x00000000 0x00000006
+					0x00000002 0x00000005
+					0x0000000a 0x00000005
+					0x0000000b 0x00000002
+					0x00000002 0x00000003
+					0x00000003 0x00000000
+					0x00000005 0x00000005
+					0x00000006 0x00000002
+					0x00000000 0x00000004
+					0x00000006 0x00010000
+					0x00000003 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000003
+					0x0000000d 0x0000000f
+					0x00000011 0x00000607
+					0x00000000 0x00000181
+					0x00000002 0x00000002
+					0x00000001 0x00000000
+					0x00000032 0x0000000f
+					0x00000038 0x00000038
+					0x00000004 0x00000005
+					0x00000004 0x00000006
+					0x00000000 0x00000005
+					0x00000005 0x00000638
+					0x00000000 0x00000000
+					0x00000000 0x106aa298
+					0x002c00a0 0x00008000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00080000 0x00080000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00008000 0x00000000
+					0x00000000 0x00008000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00090000 0x00090000
+					0x00090000 0x00090000
+					0x00009000 0x00009000
+					0x00009000 0x00009000
+					0x10000280 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc081
+					0x00000707 0x81f1f108
+					0x07070004 0x0000003f
+					0x016eeeee 0x51451400
+					0x00514514 0x00514514
+					0x51451400 0x0000003f
+					0x00000066 0x00000000
+					0x00000100 0x000e000e
+					0x00000000 0x00000003
+					0x0000d2b3 0x80000d22
+					0x0000000a
+				>;
+			};
+
+			timing-300000000 {
+				clock-frequency = <300000000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000000>;
+				nvidia,emc-cfg = <0x73340000>;
+				nvidia,emc-cfg-2 = <0x000008d5>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100002>;
+				nvidia,emc-mode-2 = <0x80200000>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80000321>;
+				nvidia,emc-mrs-wait-cnt = <0x0173000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040128>;
+				nvidia,emc-xm2dqspadctrl2 = <0x01231339>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00020000>;
+
+				nvidia,emc-configuration = <
+					0x0000000d 0x0000004d
+					0x00000000 0x00000009
+					0x00000003 0x00000004
+					0x00000008 0x00000002
+					0x00000009 0x00000003
+					0x00000003 0x00000002
+					0x00000002 0x00000000
+					0x00000003 0x00000003
+					0x00000005 0x00000002
+					0x00000000 0x00000002
+					0x00000007 0x00020000
+					0x00000003 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000001
+					0x0000000e 0x00000010
+					0x00000012 0x000008e4
+					0x00000000 0x00000239
+					0x00000001 0x00000008
+					0x00000001 0x00000000
+					0x0000004b 0x0000000e
+					0x00000052 0x00000200
+					0x00000004 0x00000005
+					0x00000004 0x00000008
+					0x00000000 0x00000005
+					0x00000005 0x00000924
+					0x00000000 0x00000000
+					0x00000000 0x104ab098
+					0x002c00a0 0x00008000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00098000 0x00098000
+					0x00000000 0x00098000
+					0x00098000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00050000 0x00050000
+					0x00050000 0x00050000
+					0x00005000 0x00005000
+					0x00005000 0x00005000
+					0x10000280 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc081
+					0x00000505 0x81f1f108
+					0x07070004 0x00000000
+					0x016eeeee 0x51451420
+					0x00514514 0x00514514
+					0x51451400 0x0000003f
+					0x00000096 0x00000000
+					0x00000100 0x0173000e
+					0x00000000 0x00000003
+					0x000052a3 0x800012d7
+					0x00000009
+				>;
+			};
+
+			timing-396000000 {
+				clock-frequency = <396000000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000000>;
+				nvidia,emc-cfg = <0x73340000>;
+				nvidia,emc-cfg-2 = <0x00000895>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100002>;
+				nvidia,emc-mode-2 = <0x80200000>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80000521>;
+				nvidia,emc-mrs-wait-cnt = <0x015b000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040008>;
+				nvidia,emc-xm2dqspadctrl2 = <0x01231339>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00020000>;
+
+				nvidia,emc-configuration = <
+					0x00000011 0x00000066
+					0x00000000 0x0000000c
+					0x00000004 0x00000004
+					0x00000008 0x00000002
+					0x0000000a 0x00000004
+					0x00000004 0x00000002
+					0x00000002 0x00000000
+					0x00000003 0x00000003
+					0x00000005 0x00000002
+					0x00000000 0x00000001
+					0x00000008 0x00020000
+					0x00000003 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x0000000f 0x00000010
+					0x00000012 0x00000bd1
+					0x00000000 0x000002f4
+					0x00000001 0x00000008
+					0x00000001 0x00000000
+					0x00000063 0x0000000f
+					0x0000006c 0x00000200
+					0x00000004 0x00000005
+					0x00000004 0x0000000b
+					0x00000000 0x00000005
+					0x00000005 0x00000c11
+					0x00000000 0x00000000
+					0x00000000 0x104ab098
+					0x002c00a0 0x00008000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00030000 0x00030000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00070000 0x00070000
+					0x00000000 0x00070000
+					0x00070000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00038000 0x00038000
+					0x00038000 0x00038000
+					0x00003800 0x00003800
+					0x00003800 0x00003800
+					0x10000280 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc081
+					0x00000505 0x81f1f108
+					0x07070004 0x00000000
+					0x016eeeee 0x51451420
+					0x00514514 0x00514514
+					0x51451400 0x0000003f
+					0x000000c6 0x00000000
+					0x00000100 0x015b000e
+					0x00000000 0x00000003
+					0x000052a3 0x8000188b
+					0x00000009
+				>;
+			};
+
+			timing-528000000 {
+				clock-frequency = <528000000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000000>;
+				nvidia,emc-cfg = <0x73300000>;
+				nvidia,emc-cfg-2 = <0x0000089d>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100002>;
+				nvidia,emc-mode-2 = <0x80200008>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80000941>;
+				nvidia,emc-mrs-wait-cnt = <0x0139000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040008>;
+				nvidia,emc-xm2dqspadctrl2 = <0x0123133d>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00020000>;
+
+				nvidia,emc-configuration = <
+					0x00000018 0x00000088
+					0x00000000 0x00000010
+					0x00000006 0x00000006
+					0x00000009 0x00000002
+					0x0000000d 0x00000006
+					0x00000006 0x00000002
+					0x00000002 0x00000000
+					0x00000003 0x00000003
+					0x00000006 0x00000002
+					0x00000000 0x00000001
+					0x00000009 0x00030000
+					0x00000003 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000010 0x00000012
+					0x00000014 0x00000fd6
+					0x00000000 0x000003f5
+					0x00000002 0x0000000b
+					0x00000001 0x00000000
+					0x00000085 0x00000012
+					0x00000090 0x00000200
+					0x00000004 0x00000005
+					0x00000004 0x00000010
+					0x00000000 0x00000006
+					0x00000006 0x00001017
+					0x00000000 0x00000000
+					0x00000000 0x104ab098
+					0xe01200b1 0x00008000
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00054000 0x00054000
+					0x00000000 0x00054000
+					0x00054000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x0000000c 0x0000000c
+					0x0000000c 0x0000000c
+					0x0000000c 0x0000000c
+					0x0000000c 0x0000000c
+					0x100002a0 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc085
+					0x00000505 0x81f1f108
+					0x07070004 0x00000000
+					0x016eeeee 0x51451420
+					0x00514514 0x00514514
+					0x51451400 0x0606003f
+					0x00000000 0x00000000
+					0x00000100 0x0139000e
+					0x00000000 0x00000003
+					0x000042a0 0x80002062
+					0x0000000a
+				>;
+			};
+
+			timing-600000000 {
+				clock-frequency = <600000000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000000>;
+				nvidia,emc-cfg = <0x73300000>;
+				nvidia,emc-cfg-2 = <0x0000089d>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100002>;
+				nvidia,emc-mode-2 = <0x80200010>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80000b61>;
+				nvidia,emc-mrs-wait-cnt = <0x0127000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040008>;
+				nvidia,emc-xm2dqspadctrl2 = <0x0121113d>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00020000>;
+
+				nvidia,emc-configuration = <
+					0x0000001b 0x0000009b
+					0x00000000 0x00000013
+					0x00000007 0x00000007
+					0x0000000b 0x00000003
+					0x00000010 0x00000007
+					0x00000007 0x00000002
+					0x00000002 0x00000000
+					0x00000005 0x00000005
+					0x0000000a 0x00000002
+					0x00000000 0x00000003
+					0x0000000b 0x00070000
+					0x00000003 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000002
+					0x00000012 0x00000016
+					0x00000018 0x00001208
+					0x00000000 0x00000482
+					0x00000002 0x0000000d
+					0x00000001 0x00000000
+					0x00000097 0x00000015
+					0x000000a3 0x00000200
+					0x00000004 0x00000005
+					0x00000004 0x00000013
+					0x00000000 0x00000006
+					0x00000006 0x00001248
+					0x00000000 0x00000000
+					0x00000000 0x104ab098
+					0xe00e00b1 0x00008000
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00048000 0x00048000
+					0x00000000 0x00048000
+					0x00048000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x0000000d 0x0000000d
+					0x0000000d 0x0000000d
+					0x0000000d 0x0000000d
+					0x0000000d 0x0000000d
+					0x100002a0 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc085
+					0x00000505 0x81f1f108
+					0x07070004 0x00000000
+					0x016eeeee 0x51451420
+					0x00514514 0x00514514
+					0x51451400 0x0606003f
+					0x00000000 0x00000000
+					0x00000100 0x0127000e
+					0x00000000 0x00000003
+					0x000040a0 0x800024aa
+					0x0000000e
+				>;
+			};
+
+			timing-792000000 {
+				clock-frequency = <792000000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430000>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000000>;
+				nvidia,emc-cfg = <0x73300000>;
+				nvidia,emc-cfg-2 = <0x0000089d>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100002>;
+				nvidia,emc-mode-2 = <0x80200018>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80000d71>;
+				nvidia,emc-mrs-wait-cnt = <0x00f7000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040000>;
+				nvidia,emc-xm2dqspadctrl2 = <0x0120113d>;
+				nvidia,emc-zcal-cnt-long = <0x00000042>;
+				nvidia,emc-zcal-interval = <0x00020000>;
+
+				nvidia,emc-configuration = <
+					0x00000024 0x000000cd
+					0x00000000 0x00000019
+					0x0000000a 0x00000008
+					0x0000000d 0x00000004
+					0x00000013 0x0000000a
+					0x0000000a 0x00000004
+					0x00000002 0x00000000
+					0x00000006 0x00000006
+					0x0000000b 0x00000002
+					0x00000000 0x00000002
+					0x0000000d 0x00080000
+					0x00000004 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000001
+					0x00000014 0x00000018
+					0x0000001a 0x000017e2
+					0x00000000 0x000005f8
+					0x00000003 0x00000011
+					0x00000001 0x00000000
+					0x000000c7 0x00000018
+					0x000000d7 0x00000200
+					0x00000005 0x00000006
+					0x00000005 0x00000019
+					0x00000000 0x00000008
+					0x00000008 0x00001822
+					0x00000000 0x00000000
+					0x00000000 0x104ab098
+					0xe00700b1 0x00008000
+					0x007fc008 0x007fc008
+					0x007fc008 0x007fc008
+					0x007fc008 0x007fc008
+					0x007fc008 0x007fc008
+					0x007fc008 0x007fc008
+					0x007fc008 0x007fc008
+					0x007fc008 0x007fc008
+					0x007fc008 0x007fc008
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00034000 0x00034000
+					0x00000000 0x00034000
+					0x00034000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000005 0x00000005
+					0x00000005 0x00000005
+					0x00000005 0x00000005
+					0x00000005 0x00000005
+					0x00000005 0x00000005
+					0x00000005 0x00000005
+					0x00000005 0x00000005
+					0x00000005 0x00000005
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x0000000a 0x0000000a
+					0x100002a0 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc085
+					0x00000000 0x81f1f108
+					0x07070004 0x00000000
+					0x016eeeee 0x61861820
+					0x00514514 0x00514514
+					0x61861800 0x0606003f
+					0x00000000 0x00000000
+					0x00000100 0x00f7000e
+					0x00000000 0x00000004
+					0x00004080 0x80003012
+					0x0000000f
+				>;
+			};
+
+			timing-924000000 {
+				clock-frequency = <924000000>;
+
+				nvidia,emc-auto-cal-config = <0xa1430303>;
+				nvidia,emc-auto-cal-config2 = <0x00000000>;
+				nvidia,emc-auto-cal-config3 = <0x00000000>;
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-bgbias-ctl0 = <0x00000000>;
+				nvidia,emc-cfg = <0x73300000>;
+				nvidia,emc-cfg-2 = <0x0000089d>;
+				nvidia,emc-ctt-term-ctrl = <0x00000802>;
+				nvidia,emc-mode-1 = <0x80100002>;
+				nvidia,emc-mode-2 = <0x80200020>;
+				nvidia,emc-mode-4 = <0x00000000>;
+				nvidia,emc-mode-reset = <0x80000f15>;
+				nvidia,emc-mrs-wait-cnt = <0x00cd000e>;
+				nvidia,emc-sel-dpd-ctrl = <0x00040000>;
+				nvidia,emc-xm2dqspadctrl2 = <0x0120113d>;
+				nvidia,emc-zcal-cnt-long = <0x0000004c>;
+				nvidia,emc-zcal-interval = <0x00020000>;
+
+				nvidia,emc-configuration = <
+					0x0000002b 0x000000f0
+					0x00000000 0x0000001e
+					0x0000000b 0x00000009
+					0x0000000f 0x00000005
+					0x00000016 0x0000000b
+					0x0000000b 0x00000004
+					0x00000002 0x00000000
+					0x00000007 0x00000007
+					0x0000000d 0x00000002
+					0x00000000 0x00000002
+					0x0000000f 0x000a0000
+					0x00000004 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000001
+					0x00000016 0x0000001a
+					0x0000001c 0x00001be7
+					0x00000000 0x000006f9
+					0x00000004 0x00000015
+					0x00000001 0x00000000
+					0x000000e7 0x0000001b
+					0x000000fb 0x00000200
+					0x00000006 0x00000007
+					0x00000006 0x0000001e
+					0x00000000 0x0000000a
+					0x0000000a 0x00001c28
+					0x00000000 0x00000000
+					0x00000000 0x104ab898
+					0xe00400b1 0x00008000
+					0x007f800a 0x007f800a
+					0x007f800a 0x007f800a
+					0x007f800a 0x007f800a
+					0x007f800a 0x007f800a
+					0x007f800a 0x007f800a
+					0x007f800a 0x007f800a
+					0x007f800a 0x007f800a
+					0x007f800a 0x007f800a
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x0002c000 0x0002c000
+					0x00000000 0x0002c000
+					0x0002c000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000000 0x00000000
+					0x00000004 0x00000004
+					0x00000004 0x00000004
+					0x00000004 0x00000004
+					0x00000004 0x00000004
+					0x00000004 0x00000004
+					0x00000004 0x00000004
+					0x00000004 0x00000004
+					0x00000004 0x00000004
+					0x00000008 0x00000008
+					0x00000008 0x00000008
+					0x00000008 0x00000008
+					0x00000008 0x00000008
+					0x100002a0 0x00000000
+					0x00111111 0x00000000
+					0x00000000 0x77ffc085
+					0x00000000 0x81f1f108
+					0x07070004 0x00000000
+					0x016eeeee 0x5d75d720
+					0x00514514 0x00514514
+					0x5d75d700 0x0606003f
+					0x00000000 0x00000000
+					0x00000128 0x00cd000e
+					0x00000000 0x00000004
+					0x00004080 0x800037ea
+					0x00000011
+				>;
+			};
+
+		};
+	};
+
+	memory-controller@70019000 {
+		emc-timings-1 {
+			nvidia,ram-code = <1>;
+
+			timing-12750000 {
+				clock-frequency = <12750000>;
+
+				nvidia,emem-configuration = <
+					0x40040001 0x8000000a
+					0x00000001 0x00000001
+					0x00000002 0x00000000
+					0x00000002 0x00000001
+					0x00000003 0x00000008
+					0x00000003 0x00000002
+					0x00000003 0x00000006
+					0x06030203 0x000a0502
+					0x77e30303 0x70000f03
+					0x001f0000
+				>;
+			};
+
+			timing-20400000 {
+				clock-frequency = <20400000>;
+
+				nvidia,emem-configuration = <
+					0x40020001 0x80000012
+					0x00000001 0x00000001
+					0x00000002 0x00000000
+					0x00000002 0x00000001
+					0x00000003 0x00000008
+					0x00000003 0x00000002
+					0x00000003 0x00000006
+					0x06030203 0x000a0502
+					0x76230303 0x70000f03
+					0x001f0000
+				>;
+			};
+
+			timing-40800000 {
+				clock-frequency = <40800000>;
+
+				nvidia,emem-configuration = <
+					0xa0000001 0x80000017
+					0x00000001 0x00000001
+					0x00000002 0x00000000
+					0x00000002 0x00000001
+					0x00000003 0x00000008
+					0x00000003 0x00000002
+					0x00000003 0x00000006
+					0x06030203 0x000a0502
+					0x74a30303 0x70000f03
+					0x001f0000
+				>;
+			};
+
+			timing-68000000 {
+				clock-frequency = <68000000>;
+
+				nvidia,emem-configuration = <
+					0x00000001 0x8000001e
+					0x00000001 0x00000001
+					0x00000002 0x00000000
+					0x00000002 0x00000001
+					0x00000003 0x00000008
+					0x00000003 0x00000002
+					0x00000003 0x00000006
+					0x06030203 0x000a0502
+					0x74230403 0x70000f03
+					0x001f0000
+				>;
+			};
+
+			timing-102000000 {
+				clock-frequency = <102000000>;
+
+				nvidia,emem-configuration = <
+					0x08000001 0x80000026
+					0x00000001 0x00000001
+					0x00000003 0x00000000
+					0x00000002 0x00000001
+					0x00000003 0x00000008
+					0x00000003 0x00000002
+					0x00000003 0x00000006
+					0x06030203 0x000a0503
+					0x73c30504 0x70000f03
+					0x001f0000
+				>;
+			};
+
+			timing-204000000 {
+				clock-frequency = <204000000>;
+
+				nvidia,emem-configuration = <
+					0x01000003 0x80000040
+					0x00000001 0x00000001
+					0x00000004 0x00000002
+					0x00000003 0x00000001
+					0x00000003 0x00000008
+					0x00000003 0x00000002
+					0x00000004 0x00000006
+					0x06040203 0x000a0504
+					0x73840a05 0x70000f03
+					0x001f0000
+				>;
+			};
+
+			timing-300000000 {
+				clock-frequency = <300000000>;
+
+				nvidia,emem-configuration = <
+					0x08000004 0x80000040
+					0x00000001 0x00000002
+					0x00000007 0x00000004
+					0x00000004 0x00000001
+					0x00000002 0x00000007
+					0x00000002 0x00000002
+					0x00000004 0x00000006
+					0x06040202 0x000b0607
+					0x77450e08 0x70000f03
+					0x001f0000
+				>;
+			};
+
+			timing-396000000 {
+				clock-frequency = <396000000>;
+
+				nvidia,emem-configuration = <
+					0x0f000005 0x80000040
+					0x00000001 0x00000002
+					0x00000009 0x00000005
+					0x00000006 0x00000001
+					0x00000002 0x00000008
+					0x00000002 0x00000002
+					0x00000004 0x00000006
+					0x06040202 0x000d0709
+					0x7586120a 0x70000f03
+					0x001f0000
+				>;
+			};
+
+			timing-528000000 {
+				clock-frequency = <528000000>;
+
+				nvidia,emem-configuration = <
+					0x0f000007 0x80000040
+					0x00000002 0x00000003
+					0x0000000c 0x00000007
+					0x00000008 0x00000001
+					0x00000002 0x00000009
+					0x00000002 0x00000002
+					0x00000005 0x00000006
+					0x06050202 0x0010090c
+					0x7428180d 0x70000f03
+					0x001f0000
+				>;
+			};
+
+			timing-600000000 {
+				clock-frequency = <600000000>;
+
+				nvidia,emem-configuration = <
+					0x00000009 0x80000040
+					0x00000003 0x00000004
+					0x0000000e 0x00000009
+					0x0000000a 0x00000001
+					0x00000003 0x0000000b
+					0x00000002 0x00000002
+					0x00000005 0x00000007
+					0x07050202 0x00130b0e
+					0x73a91b0f 0x70000f03
+					0x001f0000
+				>;
+			};
+
+			timing-792000000 {
+				clock-frequency = <792000000>;
+
+				nvidia,emem-configuration = <
+					0x0e00000b 0x80000040
+					0x00000004 0x00000005
+					0x00000013 0x0000000c
+					0x0000000d 0x00000002
+					0x00000003 0x0000000c
+					0x00000002 0x00000002
+					0x00000006 0x00000008
+					0x08060202 0x00170e13
+					0x736c2414 0x70000f02
+					0x001f0000
+				>;
+			};
+
+			timing-924000000 {
+				clock-frequency = <924000000>;
+
+				nvidia,emem-configuration = <
+					0x0e00000d 0x80000040
+					0x00000005 0x00000006
+					0x00000016 0x0000000e
+					0x0000000f 0x00000002
+					0x00000004 0x0000000e
+					0x00000002 0x00000002
+					0x00000006 0x00000009
+					0x09060202 0x001a1016
+					0x734e2a17 0x70000f02
+					0x001f0000
+				>;
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/tegra124-apalis-eval.dts b/arch/arm/boot/dts/tegra124-apalis-eval.dts
new file mode 100644
index 000000000000..653044a44f0d
--- /dev/null
+++ b/arch/arm/boot/dts/tegra124-apalis-eval.dts
@@ -0,0 +1,284 @@
+/*
+ * Copyright 2016 Toradex AG
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/input/input.h>
+#include "tegra124-apalis.dtsi"
+
+/ {
+	model = "Toradex Apalis TK1 on Apalis Evaluation Board";
+	compatible = "toradex,apalis-tk1-eval", "toradex,apalis-tk1",
+		     "nvidia,tegra124";
+
+	aliases {
+		rtc0 = "/i2c@7000c000/rtc@68";
+		rtc1 = "/i2c@7000d000/pmic@40";
+		rtc2 = "/rtc@7000e000";
+		serial0 = &uarta;
+		serial1 = &uartb;
+		serial2 = &uartc;
+		serial3 = &uartd;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	pcie-controller@01003000 {
+		pci@1,0 {
+			status = "okay";
+		};
+	};
+
+	host1x@50000000 {
+		hdmi@54280000 {
+			status = "okay";
+		};
+	};
+
+	/* Apalis UART1 */
+	serial@70006000 {
+		status = "okay";
+	};
+
+	/* Apalis UART2 */
+	serial@70006040 {
+		status = "okay";
+	};
+
+	/* Apalis UART3 */
+	serial@70006200 {
+		status = "okay";
+	};
+
+	/* Apalis UART4 */
+	serial@70006300 {
+		status = "okay";
+	};
+
+	pwm@7000a000 {
+		status = "okay";
+	};
+
+	/*
+	 * GEN1_I2C: I2C1_SDA/SCL on MXM3 pin 209/211 (e.g. RTC on carrier
+	 * board)
+	 */
+	i2c@7000c000 {
+		status = "okay";
+		clock-frequency = <100000>;
+
+		pcie-switch@58 {
+			compatible = "plx,pex8605";
+			reg = <0x58>;
+		};
+
+		/* M41T0M6 real time clock on carrier board */
+		rtc@68 {
+			compatible = "st,m41t00";
+			reg = <0x68>;
+		};
+	};
+
+	/*
+	 * GEN2_I2C: I2C2_SDA/SCL (DDC) on MXM3 pin 205/207 (e.g. display EDID)
+	 */
+	hdmi_ddc: i2c@7000c400 {
+		status = "okay";
+		clock-frequency = <100000>;
+	};
+
+	/*
+	 * CAM_I2C: I2C3_SDA/SCL (CAM) on MXM3 pin 201/203 (e.g. camera sensor
+	 * on carrier board)
+	 */
+	i2c@7000c500 {
+		status = "okay";
+		clock-frequency = <100000>;
+	};
+
+	/* I2C4 (DDC): unused */
+
+	/* SPI1: Apalis SPI1 */
+	spi@7000d400 {
+		status = "okay";
+		spi-max-frequency = <50000000>;
+
+		spidev0: spidev@0 {
+			compatible = "spidev";
+			reg = <0>;
+			spi-max-frequency = <50000000>;
+		};
+	};
+
+	/* SPI4: Apalis SPI2 */
+	spi@7000da00 {
+		status = "okay";
+		spi-max-frequency = <50000000>;
+
+		spidev1: spidev@0 {
+			compatible = "spidev";
+			reg = <0>;
+			spi-max-frequency = <50000000>;
+		};
+	};
+
+	/* Apalis Serial ATA */
+	sata@70020000 {
+		status = "okay";
+	};
+
+	hda@70030000 {
+		status = "okay";
+	};
+
+	usb@70090000 {
+		status = "okay";
+	};
+
+	/* Apalis MMC1 */
+	sdhci@700b0000 {
+		status = "okay";
+		/* MMC1_CD# */
+		cd-gpios = <&gpio TEGRA_GPIO(V, 3) GPIO_ACTIVE_LOW>;
+		bus-width = <4>;
+		vqmmc-supply = <&vddio_sdmmc1>;
+	};
+
+	/* Apalis SD1 */
+	sdhci@700b0400 {
+		status = "okay";
+		/*
+		 * Don't use SD1_CD# aka SDMMC3_CLK_LB_OUT for now as it
+		 * features some magic properties even though the external
+		 * loopback is disabled and the internal loopback used as per
+		 * SDMMC_VENDOR_MISC_CNTRL_0 register's SDMMC_SPARE1 bits being
+		 * set to 0xfffd according to the TRM!
+		 * cd-gpios = <&gpio TEGRA_GPIO(EE, 4) GPIO_ACTIVE_LOW>;
+		 */
+		bus-width = <4>;
+		vqmmc-supply = <&vddio_sdmmc3>;
+	};
+
+	/* EHCI instance 0: USB1_DP/N -> USBO1_DP/N */
+	usb@7d000000 {
+		status = "okay";
+		dr_mode = "otg";
+	};
+
+	usb-phy@7d000000 {
+		status = "okay";
+		vbus-supply = <&reg_usbo1_vbus>;
+	};
+
+	/* EHCI instance 1: USB2_DP/N -> USBH2_DP/N */
+	usb@7d004000 {
+		status = "okay";
+	};
+
+	usb-phy@7d004000 {
+		status = "okay";
+		vbus-supply = <&reg_usbh_vbus>;
+	};
+
+	/* EHCI instance 2: USB3_DP/N -> USBH4_DP/N */
+	usb@7d008000 {
+		status = "okay";
+	};
+
+	usb-phy@7d008000 {
+		status = "okay";
+		vbus-supply = <&reg_usbh_vbus>;
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+
+		/* BKL1_PWM */
+		pwms = <&pwm 3 5000000>;
+		brightness-levels = <255 231 223 207 191 159 127 0>;
+		default-brightness-level = <6>;
+		/* BKL1_ON */
+		enable-gpios = <&gpio TEGRA_GPIO(BB, 5) GPIO_ACTIVE_HIGH>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		wakeup {
+			label = "WAKE1_MICO";
+			gpios = <&gpio TEGRA_GPIO(DD, 3) GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_WAKEUP>;
+			debounce-interval = <10>;
+			wakeup-source;
+		};
+	};
+
+	reg_5v0: regulator-5v0 {
+		compatible = "regulator-fixed";
+		regulator-name = "5V_SW";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	/* USBO1_EN */
+	reg_usbo1_vbus: regulator-usbo1-vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_USBO1";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio TEGRA_GPIO(N, 4) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_5v0>;
+	};
+
+	/* USBH_EN */
+	reg_usbh_vbus: regulator-usbh-vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_USBH(2A|2C|2D|3|4)";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		gpio = <&gpio TEGRA_GPIO(N, 5) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_5v0>;
+	};
+};
diff --git a/arch/arm/boot/dts/tegra124-apalis.dtsi b/arch/arm/boot/dts/tegra124-apalis.dtsi
new file mode 100644
index 000000000000..e7a73db17613
--- /dev/null
+++ b/arch/arm/boot/dts/tegra124-apalis.dtsi
@@ -0,0 +1,2100 @@
+/*
+ * Copyright 2016 Toradex AG
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License
+ *     version 2 as published by the Free Software Foundation.
+ *
+ *     This file is distributed in the hope that it will be useful
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED , WITHOUT WARRANTY OF ANY KIND
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include "tegra124.dtsi"
+#include "tegra124-apalis-emc.dtsi"
+
+/*
+ * Toradex Apalis TK1 Module Device Tree
+ * Compatible for Revisions 2GB: V1.0A
+ */
+/ {
+	model = "Toradex Apalis TK1";
+	compatible = "toradex,apalis-tk1", "nvidia,tegra124";
+
+	memory {
+		reg = <0x0 0x80000000 0x0 0x80000000>;
+	};
+
+	pcie-controller@01003000 {
+		status = "okay";
+
+		avddio-pex-supply = <&vdd_1v05>;
+		avdd-pex-pll-supply = <&vdd_1v05>;
+		avdd-pll-erefe-supply = <&avdd_1v05>;
+		dvddio-pex-supply = <&vdd_1v05>;
+		hvdd-pex-pll-e-supply = <&reg_3v3>;
+		hvdd-pex-supply = <&reg_3v3>;
+		vddio-pex-ctl-supply = <&reg_3v3>;
+
+		/* Apalis PCIe (additional lane Apalis type specific) */
+		pci@1,0 {
+			/* PCIE1_RX/TX and TS_DIFF1/2 */
+			phys = <&{/padctl@7009f000/pads/pcie/lanes/pcie-4}>,
+			       <&{/padctl@7009f000/pads/pcie/lanes/pcie-3}>;
+			phy-names = "pcie-0", "pcie-1";
+		};
+
+		/* I210 Gigabit Ethernet Controller (On-module) */
+		pci@2,0 {
+			phys = <&{/padctl@7009f000/pads/pcie/lanes/pcie-2}>;
+			phy-names = "pcie-0";
+			status = "okay";
+		};
+	};
+
+	host1x@50000000 {
+		hdmi@54280000 {
+			pll-supply = <&reg_1v05_avdd_hdmi_pll>;
+			vdd-supply = <&reg_3v3_avdd_hdmi>;
+
+			nvidia,ddc-i2c-bus = <&hdmi_ddc>;
+			nvidia,hpd-gpio =
+				<&gpio TEGRA_GPIO(N, 7) GPIO_ACTIVE_HIGH>;
+		};
+	};
+
+	gpu@0,57000000 {
+		/*
+		 * Node left disabled on purpose - the bootloader will enable
+		 * it after having set the VPR up
+		 */
+		vdd-supply = <&vdd_gpu>;
+	};
+
+	pinmux: pinmux@70000868 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&state_default>;
+
+		state_default: pinmux {
+			/* Analogue Audio (On-module) */
+			dap3_fs_pp0 {
+				nvidia,pins = "dap3_fs_pp0";
+				nvidia,function = "i2s2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap3_din_pp1 {
+				nvidia,pins = "dap3_din_pp1";
+				nvidia,function = "i2s2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			dap3_dout_pp2 {
+				nvidia,pins = "dap3_dout_pp2";
+				nvidia,function = "i2s2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap3_sclk_pp3 {
+				nvidia,pins = "dap3_sclk_pp3";
+				nvidia,function = "i2s2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap_mclk1_pw4 {
+				nvidia,pins = "dap_mclk1_pw4";
+				nvidia,function = "extperiph1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis BKL1_ON */
+			pbb5 {
+				nvidia,pins = "pbb5";
+				nvidia,function = "vgp5";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis BKL1_PWM */
+			pu6 {
+				nvidia,pins = "pu6";
+				nvidia,function = "pwm3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis CAM1_MCLK */
+			cam_mclk_pcc0 {
+				nvidia,pins = "cam_mclk_pcc0";
+				nvidia,function = "vi_alt3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis Digital Audio */
+			dap2_fs_pa2 {
+				nvidia,pins = "dap2_fs_pa2";
+				nvidia,function = "hda";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			dap2_sclk_pa3 {
+				nvidia,pins = "dap2_sclk_pa3";
+				nvidia,function = "hda";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			dap2_din_pa4 {
+				nvidia,pins = "dap2_din_pa4";
+				nvidia,function = "hda";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			dap2_dout_pa5 {
+				nvidia,pins = "dap2_dout_pa5";
+				nvidia,function = "hda";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pbb3 { /* DAP1_RESET */
+				nvidia,pins = "pbb3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			clk3_out_pee0 {
+				nvidia,pins = "clk3_out_pee0";
+				nvidia,function = "extperiph3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis GPIO */
+			ddc_scl_pv4 {
+				nvidia,pins = "ddc_scl_pv4";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			ddc_sda_pv5 {
+				nvidia,pins = "ddc_sda_pv5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			pex_l0_rst_n_pdd1 {
+				nvidia,pins = "pex_l0_rst_n_pdd1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			pex_l0_clkreq_n_pdd2 {
+				nvidia,pins = "pex_l0_clkreq_n_pdd2";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			pex_l1_rst_n_pdd5 {
+				nvidia,pins = "pex_l1_rst_n_pdd5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			pex_l1_clkreq_n_pdd6 {
+				nvidia,pins = "pex_l1_clkreq_n_pdd6";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			dp_hpd_pff0 {
+				nvidia,pins = "dp_hpd_pff0";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			pff2 {
+				nvidia,pins = "pff2";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			owr { /* PEX_L1_CLKREQ_N multiplexed GPIO6 */
+				nvidia,pins = "owr";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+				nvidia,rcv-sel = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis HDMI1_CEC */
+			hdmi_cec_pee3 {
+				nvidia,pins = "hdmi_cec_pee3";
+				nvidia,function = "cec";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis HDMI1_HPD */
+			hdmi_int_pn7 {
+				nvidia,pins = "hdmi_int_pn7";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,rcv-sel = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis I2C1 */
+			gen1_i2c_scl_pc4 {
+				nvidia,pins = "gen1_i2c_scl_pc4";
+				nvidia,function = "i2c1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+			};
+			gen1_i2c_sda_pc5 {
+				nvidia,pins = "gen1_i2c_sda_pc5";
+				nvidia,function = "i2c1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Apalis I2C2 (DDC) */
+			gen2_i2c_scl_pt5 {
+				nvidia,pins = "gen2_i2c_scl_pt5";
+				nvidia,function = "i2c2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+			};
+			gen2_i2c_sda_pt6 {
+				nvidia,pins = "gen2_i2c_sda_pt6";
+				nvidia,function = "i2c2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Apalis I2C3 (CAM) */
+			cam_i2c_scl_pbb1 {
+				nvidia,pins = "cam_i2c_scl_pbb1";
+				nvidia,function = "i2c3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+			};
+			cam_i2c_sda_pbb2 {
+				nvidia,pins = "cam_i2c_sda_pbb2";
+				nvidia,function = "i2c3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Apalis MMC1 */
+			sdmmc1_cd_n_pv3 { /* CD# GPIO */
+				nvidia,pins = "sdmmc1_wp_n_pv3";
+				nvidia,function = "sdmmc1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			clk2_out_pw5 { /* D5 GPIO */
+				nvidia,pins = "clk2_out_pw5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc1_dat3_py4 {
+				nvidia,pins = "sdmmc1_dat3_py4";
+				nvidia,function = "sdmmc1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc1_dat2_py5 {
+				nvidia,pins = "sdmmc1_dat2_py5";
+				nvidia,function = "sdmmc1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc1_dat1_py6 {
+				nvidia,pins = "sdmmc1_dat1_py6";
+				nvidia,function = "sdmmc1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc1_dat0_py7 {
+				nvidia,pins = "sdmmc1_dat0_py7";
+				nvidia,function = "sdmmc1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc1_clk_pz0 {
+				nvidia,pins = "sdmmc1_clk_pz0";
+				nvidia,function = "sdmmc1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc1_cmd_pz1 {
+				nvidia,pins = "sdmmc1_cmd_pz1";
+				nvidia,function = "sdmmc1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			clk2_req_pcc5 { /* D4 GPIO */
+				nvidia,pins = "clk2_req_pcc5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			/*
+			 * Don't use MMC1_D6 aka SDMMC3_CLK_LB_IN for now as it
+			 * features some magic properties even though the
+			 * external loopback is disabled and the internal
+			 * loopback used as per SDMMC_VENDOR_MISC_CNTRL_0
+			 * register's SDMMC_SPARE1 bits being set to 0xfffd
+			 * according to the TRM!
+			 */
+			sdmmc3_clk_lb_in_pee5 { /* D6 GPIO */
+				nvidia,pins = "sdmmc3_clk_lb_in_pee5";
+				nvidia,function = "sdmmc3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			usb_vbus_en2_pff1 { /* D7 GPIO */
+				nvidia,pins = "usb_vbus_en2_pff1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Apalis PWM */
+			ph0 {
+				nvidia,pins = "ph0";
+				nvidia,function = "pwm0";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ph1 {
+				nvidia,pins = "ph1";
+				nvidia,function = "pwm1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ph2 {
+				nvidia,pins = "ph2";
+				nvidia,function = "pwm2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			/* PWM3 active on pu6 being Apalis BKL1_PWM */
+			ph3 {
+				nvidia,pins = "ph3";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis SATA1_ACT# */
+			dap1_dout_pn2 {
+				nvidia,pins = "dap1_dout_pn2";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis SD1 */
+			sdmmc3_clk_pa6 {
+				nvidia,pins = "sdmmc3_clk_pa6";
+				nvidia,function = "sdmmc3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc3_cmd_pa7 {
+				nvidia,pins = "sdmmc3_cmd_pa7";
+				nvidia,function = "sdmmc3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc3_dat3_pb4 {
+				nvidia,pins = "sdmmc3_dat3_pb4";
+				nvidia,function = "sdmmc3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc3_dat2_pb5 {
+				nvidia,pins = "sdmmc3_dat2_pb5";
+				nvidia,function = "sdmmc3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc3_dat1_pb6 {
+				nvidia,pins = "sdmmc3_dat1_pb6";
+				nvidia,function = "sdmmc3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc3_dat0_pb7 {
+				nvidia,pins = "sdmmc3_dat0_pb7";
+				nvidia,function = "sdmmc3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			/*
+			 * Don't use SD1_CD# aka SDMMC3_CLK_LB_OUT for now as it
+			 * features some magic properties even though the
+			 * external loopback is disabled and the internal
+			 * loopback used as per SDMMC_VENDOR_MISC_CNTRL_0
+			 * register's SDMMC_SPARE1 bits being set to 0xfffd
+			 * according to the TRM!
+			 */
+			sdmmc3_clk_lb_out_pee4 { /* CD# GPIO */
+				nvidia,pins = "sdmmc3_clk_lb_out_pee4";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis SPDIF */
+			spdif_out_pk5 {
+				nvidia,pins = "spdif_out_pk5";
+				nvidia,function = "spdif";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			spdif_in_pk6 {
+				nvidia,pins = "spdif_in_pk6";
+				nvidia,function = "spdif";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Apalis SPI1 */
+			ulpi_clk_py0 {
+				nvidia,pins = "ulpi_clk_py0";
+				nvidia,function = "spi1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ulpi_dir_py1 {
+				nvidia,pins = "ulpi_dir_py1";
+				nvidia,function = "spi1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			ulpi_nxt_py2 {
+				nvidia,pins = "ulpi_nxt_py2";
+				nvidia,function = "spi1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ulpi_stp_py3 {
+				nvidia,pins = "ulpi_stp_py3";
+				nvidia,function = "spi1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis SPI2 */
+			pg5 {
+				nvidia,pins = "pg5";
+				nvidia,function = "spi4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pg6 {
+				nvidia,pins = "pg6";
+				nvidia,function = "spi4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pg7 {
+				nvidia,pins = "pg7";
+				nvidia,function = "spi4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			pi3 {
+				nvidia,pins = "pi3";
+				nvidia,function = "spi4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis UART1 */
+			pb1 { /* DCD GPIO */
+				nvidia,pins = "pb1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			pk7 { /* RI GPIO */
+				nvidia,pins = "pk7";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			uart1_txd_pu0 {
+				nvidia,pins = "pu0";
+				nvidia,function = "uarta";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			uart1_rxd_pu1 {
+				nvidia,pins = "pu1";
+				nvidia,function = "uarta";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			uart1_cts_n_pu2 {
+				nvidia,pins = "pu2";
+				nvidia,function = "uarta";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			uart1_rts_n_pu3 {
+				nvidia,pins = "pu3";
+				nvidia,function = "uarta";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			uart3_cts_n_pa1 { /* DSR GPIO */
+				nvidia,pins = "uart3_cts_n_pa1";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			uart3_rts_n_pc0 { /* DTR GPIO */
+				nvidia,pins = "uart3_rts_n_pc0";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis UART2 */
+			uart2_txd_pc2 {
+				nvidia,pins = "uart2_txd_pc2";
+				nvidia,function = "irda";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			uart2_rxd_pc3 {
+				nvidia,pins = "uart2_rxd_pc3";
+				nvidia,function = "irda";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			uart2_cts_n_pj5 {
+				nvidia,pins = "uart2_cts_n_pj5";
+				nvidia,function = "uartb";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			uart2_rts_n_pj6 {
+				nvidia,pins = "uart2_rts_n_pj6";
+				nvidia,function = "uartb";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis UART3 */
+			uart3_txd_pw6 {
+				nvidia,pins = "uart3_txd_pw6";
+				nvidia,function = "uartc";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			uart3_rxd_pw7 {
+				nvidia,pins = "uart3_rxd_pw7";
+				nvidia,function = "uartc";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Apalis UART4 */
+			uart4_rxd_pb0 {
+				nvidia,pins = "pb0";
+				nvidia,function = "uartd";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			uart4_txd_pj7 {
+				nvidia,pins = "pj7";
+				nvidia,function = "uartd";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis USBH_EN */
+			usb_vbus_en1_pn5 {
+				nvidia,pins = "usb_vbus_en1_pn5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+				nvidia,open-drain = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis USBH_OC# */
+			pbb0 {
+				nvidia,pins = "pbb0";
+				nvidia,function = "vgp6";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Apalis USBO1_EN */
+			usb_vbus_en0_pn4 {
+				nvidia,pins = "usb_vbus_en0_pn4";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+				nvidia,open-drain = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Apalis USBO1_OC# */
+			pbb4 {
+				nvidia,pins = "pbb4";
+				nvidia,function = "vgp4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Apalis WAKE1_MICO */
+			pex_wake_n_pdd3 {
+				nvidia,pins = "pex_wake_n_pdd3";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* CORE_PWR_REQ */
+			core_pwr_req {
+				nvidia,pins = "core_pwr_req";
+				nvidia,function = "pwron";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* CPU_PWR_REQ */
+			cpu_pwr_req {
+				nvidia,pins = "cpu_pwr_req";
+				nvidia,function = "cpu";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* DVFS */
+			dvfs_pwm_px0 {
+				nvidia,pins = "dvfs_pwm_px0";
+				nvidia,function = "cldvfs";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dvfs_clk_px2 {
+				nvidia,pins = "dvfs_clk_px2";
+				nvidia,function = "cldvfs";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* eMMC */
+			sdmmc4_dat0_paa0 {
+				nvidia,pins = "sdmmc4_dat0_paa0";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4_dat1_paa1 {
+				nvidia,pins = "sdmmc4_dat1_paa1";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4_dat2_paa2 {
+				nvidia,pins = "sdmmc4_dat2_paa2";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4_dat3_paa3 {
+				nvidia,pins = "sdmmc4_dat3_paa3";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4_dat4_paa4 {
+				nvidia,pins = "sdmmc4_dat4_paa4";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4_dat5_paa5 {
+				nvidia,pins = "sdmmc4_dat5_paa5";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4_dat6_paa6 {
+				nvidia,pins = "sdmmc4_dat6_paa6";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4_dat7_paa7 {
+				nvidia,pins = "sdmmc4_dat7_paa7";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4_clk_pcc4 {
+				nvidia,pins = "sdmmc4_clk_pcc4";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4_cmd_pt7 {
+				nvidia,pins = "sdmmc4_cmd_pt7";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* JTAG_RTCK */
+			jtag_rtck {
+				nvidia,pins = "jtag_rtck";
+				nvidia,function = "rtck";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* LAN_DEV_OFF# */
+			ulpi_data5_po6 {
+				nvidia,pins = "ulpi_data5_po6";
+				nvidia,function = "ulpi";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* LAN_RESET# */
+			kb_row10_ps2 {
+				nvidia,pins = "kb_row10_ps2";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* LAN_WAKE# */
+			ulpi_data4_po5 {
+				nvidia,pins = "ulpi_data4_po5";
+				nvidia,function = "ulpi";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* MCU_INT1# */
+			pk2 {
+				nvidia,pins = "pk2";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* MCU_INT2# */
+			pj2 {
+				nvidia,pins = "pj2";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* MCU_INT3# */
+			pi5 {
+				nvidia,pins = "pi5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* MCU_INT4# */
+			pj0 {
+				nvidia,pins = "pj0";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* MCU_RESET */
+			pbb6 {
+				nvidia,pins = "pbb6";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* MCU SPI */
+			gpio_x4_aud_px4 {
+				nvidia,pins = "gpio_x4_aud_px4";
+				nvidia,function = "spi2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			gpio_x5_aud_px5 {
+				nvidia,pins = "gpio_x5_aud_px5";
+				nvidia,function = "spi2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			gpio_x6_aud_px6 { /* MCU_CS */
+				nvidia,pins = "gpio_x6_aud_px6";
+				nvidia,function = "spi2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			gpio_x7_aud_px7 {
+				nvidia,pins = "gpio_x7_aud_px7";
+				nvidia,function = "spi2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			gpio_w2_aud_pw2 { /* MCU_CSEZP */
+				nvidia,pins = "gpio_w2_aud_pw2";
+				nvidia,function = "spi2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* PMIC_CLK_32K */
+			clk_32k_in {
+				nvidia,pins = "clk_32k_in";
+				nvidia,function = "clk";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* PMIC_CPU_OC_INT */
+			clk_32k_out_pa0 {
+				nvidia,pins = "clk_32k_out_pa0";
+				nvidia,function = "soc";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* PWR_I2C */
+			pwr_i2c_scl_pz6 {
+				nvidia,pins = "pwr_i2c_scl_pz6";
+				nvidia,function = "i2cpwr";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+			};
+			pwr_i2c_sda_pz7 {
+				nvidia,pins = "pwr_i2c_sda_pz7";
+				nvidia,function = "i2cpwr";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* PWR_INT_N */
+			pwr_int_n {
+				nvidia,pins = "pwr_int_n";
+				nvidia,function = "pmi";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* RESET_MOCI_CTRL */
+			pu4 {
+				nvidia,pins = "pu4";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* RESET_OUT_N */
+			reset_out_n {
+				nvidia,pins = "reset_out_n";
+				nvidia,function = "reset_out_n";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* SHIFT_CTRL_DIR_IN */
+			kb_row0_pr0 {
+				nvidia,pins = "kb_row0_pr0";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row1_pr1 {
+				nvidia,pins = "kb_row1_pr1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Configure level-shifter as output for HDA */
+			kb_row11_ps3 {
+				nvidia,pins = "kb_row11_ps3";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* SHIFT_CTRL_DIR_OUT */
+			kb_col5_pq5 {
+				nvidia,pins = "kb_col5_pq5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_col6_pq6 {
+				nvidia,pins = "kb_col6_pq6";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_col7_pq7 {
+				nvidia,pins = "kb_col7_pq7";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* SHIFT_CTRL_OE */
+			kb_col0_pq0 {
+				nvidia,pins = "kb_col0_pq0";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_col1_pq1 {
+				nvidia,pins = "kb_col1_pq1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_col2_pq2 {
+				nvidia,pins = "kb_col2_pq2";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_col4_pq4 {
+				nvidia,pins = "kb_col4_pq4";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row2_pr2 {
+				nvidia,pins = "kb_row2_pr2";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* GPIO_PI6 aka TEMP_ALERT_L */
+			pi6 {
+				nvidia,pins = "pi6";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* TOUCH_INT */
+			gpio_w3_aud_pw3 {
+				nvidia,pins = "gpio_w3_aud_pw3";
+				nvidia,function = "spi6";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			pc7 { /* NC */
+				nvidia,pins = "pc7";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pg0 { /* NC */
+				nvidia,pins = "pg0";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pg1 { /* NC */
+				nvidia,pins = "pg1";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pg2 { /* NC */
+				nvidia,pins = "pg2";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pg3 { /* NC */
+				nvidia,pins = "pg3";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pg4 { /* NC */
+				nvidia,pins = "pg4";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ph4 { /* NC */
+				nvidia,pins = "ph4";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ph5 { /* NC */
+				nvidia,pins = "ph5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ph6 { /* NC */
+				nvidia,pins = "ph6";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ph7 { /* NC */
+				nvidia,pins = "ph7";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pi0 { /* NC */
+				nvidia,pins = "pi0";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pi1 { /* NC */
+				nvidia,pins = "pi1";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pi2 { /* NC */
+				nvidia,pins = "pi2";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pi4 { /* NC */
+				nvidia,pins = "pi4";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pi7 { /* NC */
+				nvidia,pins = "pi7";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pk0 { /* NC */
+				nvidia,pins = "pk0";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pk1 { /* NC */
+				nvidia,pins = "pk1";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pk3 { /* NC */
+				nvidia,pins = "pk3";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pk4 { /* NC */
+				nvidia,pins = "pk4";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap1_fs_pn0 { /* NC */
+				nvidia,pins = "dap1_fs_pn0";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap1_din_pn1 { /* NC */
+				nvidia,pins = "dap1_din_pn1";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap1_sclk_pn3 { /* NC */
+				nvidia,pins = "dap1_sclk_pn3";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ulpi_data7_po0 { /* NC */
+				nvidia,pins = "ulpi_data7_po0";
+				nvidia,function = "ulpi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ulpi_data0_po1 { /* NC */
+				nvidia,pins = "ulpi_data0_po1";
+				nvidia,function = "ulpi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ulpi_data1_po2 { /* NC */
+				nvidia,pins = "ulpi_data1_po2";
+				nvidia,function = "ulpi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ulpi_data2_po3 { /* NC */
+				nvidia,pins = "ulpi_data2_po3";
+				nvidia,function = "ulpi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ulpi_data3_po4 { /* NC */
+				nvidia,pins = "ulpi_data3_po4";
+				nvidia,function = "ulpi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ulpi_data6_po7 { /* NC */
+				nvidia,pins = "ulpi_data6_po7";
+				nvidia,function = "ulpi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap4_fs_pp4 { /* NC */
+				nvidia,pins = "dap4_fs_pp4";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap4_din_pp5 { /* NC */
+				nvidia,pins = "dap4_din_pp5";
+				nvidia,function = "rsvd3";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap4_dout_pp6 { /* NC */
+				nvidia,pins = "dap4_dout_pp6";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap4_sclk_pp7 { /* NC */
+				nvidia,pins = "dap4_sclk_pp7";
+				nvidia,function = "rsvd3";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_col3_pq3 { /* NC */
+				nvidia,pins = "kb_col3_pq3";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row3_pr3 { /* NC */
+				nvidia,pins = "kb_row3_pr3";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row4_pr4 { /* NC */
+				nvidia,pins = "kb_row4_pr4";
+				nvidia,function = "rsvd3";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row5_pr5 { /* NC */
+				nvidia,pins = "kb_row5_pr5";
+				nvidia,function = "rsvd3";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row6_pr6 { /* NC */
+				nvidia,pins = "kb_row6_pr6";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row7_pr7 { /* NC */
+				nvidia,pins = "kb_row7_pr7";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row8_ps0 { /* NC */
+				nvidia,pins = "kb_row8_ps0";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row9_ps1 { /* NC */
+				nvidia,pins = "kb_row9_ps1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row12_ps4 { /* NC */
+				nvidia,pins = "kb_row12_ps4";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row13_ps5 { /* NC */
+				nvidia,pins = "kb_row13_ps5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row14_ps6 { /* NC */
+				nvidia,pins = "kb_row14_ps6";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row15_ps7 { /* NC */
+				nvidia,pins = "kb_row15_ps7";
+				nvidia,function = "rsvd3";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row16_pt0 { /* NC */
+				nvidia,pins = "kb_row16_pt0";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			kb_row17_pt1 { /* NC */
+				nvidia,pins = "kb_row17_pt1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pu5 { /* NC */
+				nvidia,pins = "pu5";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pv0 { /* NC */
+				nvidia,pins = "pv0";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pv1 { /* NC */
+				nvidia,pins = "pv1";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			sdmmc3_cd_n_pv2 { /* NC */
+				nvidia,pins = "sdmmc3_cd_n_pv2";
+				nvidia,function = "rsvd3";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			gpio_x1_aud_px1 { /* NC */
+				nvidia,pins = "gpio_x1_aud_px1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			gpio_x3_aud_px3 { /* NC */
+				nvidia,pins = "gpio_x3_aud_px3";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pbb7 { /* NC */
+				nvidia,pins = "pbb7";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pcc1 { /* NC */
+				nvidia,pins = "pcc1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pcc2 { /* NC */
+				nvidia,pins = "pcc2";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			clk3_req_pee1 { /* NC */
+				nvidia,pins = "clk3_req_pee1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap_mclk1_req_pee2 { /* NC */
+				nvidia,pins = "dap_mclk1_req_pee2";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+		};
+	};
+
+	serial@70006040 {
+		compatible = "nvidia,tegra124-hsuart";
+	};
+
+	serial@70006200 {
+		compatible = "nvidia,tegra124-hsuart";
+	};
+
+	serial@70006300 {
+		compatible = "nvidia,tegra124-hsuart";
+	};
+
+	hdmi_ddc: i2c@7000c400 {
+		clock-frequency = <100000>;
+	};
+
+	/* PWR_I2C: power I2C to audio codec, PMIC and temperature sensor */
+	i2c@7000d000 {
+		status = "okay";
+		clock-frequency = <400000>;
+
+		/* SGTL5000 audio codec */
+		sgtl5000: codec@0a {
+			compatible = "fsl,sgtl5000";
+			reg = <0x0a>;
+			VDDA-supply = <&reg_3v3>;
+			VDDIO-supply = <&vddio_1v8>;
+			clocks = <&tegra_car TEGRA124_CLK_EXTERN1>;
+		};
+
+		pmic: pmic@40 {
+			compatible = "ams,as3722";
+			reg = <0x40>;
+			interrupts = <0 86 IRQ_TYPE_LEVEL_HIGH>;
+
+			ams,system-power-controller;
+
+			#interrupt-cells = <2>;
+			interrupt-controller;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+
+			pinctrl-names = "default";
+			pinctrl-0 = <&as3722_default>;
+
+			as3722_default: pinmux {
+				gpio2_7 {
+					pins = "gpio2", /* PWR_EN_+V3.3 */
+					       "gpio7"; /* +V1.6_LPO */
+					function = "gpio";
+					bias-pull-up;
+				};
+
+				gpio1_3_4_5_6 {
+					pins = "gpio1", "gpio3", "gpio4",
+					       "gpio5", "gpio6";
+					bias-high-impedance;
+				};
+			};
+
+			regulators {
+				vsup-sd2-supply = <&reg_3v3>;
+				vsup-sd3-supply = <&reg_3v3>;
+				vsup-sd4-supply = <&reg_3v3>;
+				vsup-sd5-supply = <&reg_3v3>;
+				vin-ldo0-supply = <&vddio_ddr_1v35>;
+				vin-ldo1-6-supply = <&reg_3v3>;
+				vin-ldo2-5-7-supply = <&vddio_1v8>;
+				vin-ldo3-4-supply = <&reg_3v3>;
+				vin-ldo9-10-supply = <&reg_3v3>;
+				vin-ldo11-supply = <&reg_3v3>;
+
+				vdd_cpu: sd0 {
+					regulator-name = "+VDD_CPU_AP";
+					regulator-min-microvolt = <700000>;
+					regulator-max-microvolt = <1400000>;
+					regulator-min-microamp = <3500000>;
+					regulator-max-microamp = <3500000>;
+					regulator-always-on;
+					regulator-boot-on;
+					ams,ext-control = <2>;
+				};
+
+				sd1 {
+					regulator-name = "+VDD_CORE";
+					regulator-min-microvolt = <700000>;
+					regulator-max-microvolt = <1350000>;
+					regulator-min-microamp = <2500000>;
+					regulator-max-microamp = <4000000>;
+					regulator-always-on;
+					regulator-boot-on;
+					ams,ext-control = <1>;
+				};
+
+				vddio_ddr_1v35: sd2 {
+					regulator-name =
+						"+V1.35_VDDIO_DDR(sd2)";
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
+					regulator-always-on;
+					regulator-boot-on;
+				};
+
+				sd3 {
+					regulator-name =
+						"+V1.35_VDDIO_DDR(sd3)";
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
+					regulator-always-on;
+					regulator-boot-on;
+				};
+
+				vdd_1v05: sd4 {
+					regulator-name = "+V1.05";
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1050000>;
+				};
+
+				vddio_1v8: sd5 {
+					regulator-name = "+V1.8";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-boot-on;
+					regulator-always-on;
+				};
+
+				vdd_gpu: sd6 {
+					regulator-name = "+VDD_GPU_AP";
+					regulator-min-microvolt = <650000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-min-microamp = <3500000>;
+					regulator-max-microamp = <3500000>;
+					regulator-boot-on;
+					regulator-always-on;
+				};
+
+				avdd_1v05: ldo0 {
+					regulator-name = "+V1.05_AVDD";
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1050000>;
+					regulator-boot-on;
+					regulator-always-on;
+					ams,ext-control = <1>;
+				};
+
+				vddio_sdmmc1: ldo1 {
+					regulator-name = "VDDIO_SDMMC1";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <3300000>;
+				};
+
+				ldo2 {
+					regulator-name = "+V1.2";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-boot-on;
+					regulator-always-on;
+				};
+
+				ldo3 {
+					regulator-name = "+V1.05_RTC";
+					regulator-min-microvolt = <1000000>;
+					regulator-max-microvolt = <1000000>;
+					regulator-boot-on;
+					regulator-always-on;
+					ams,enable-tracking;
+				};
+
+				/* 1.8V for LVDS, 3.3V for eDP */
+				ldo4 {
+					regulator-name = "AVDD_LVDS0_PLL";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+				};
+
+				/* LDO5 not used */
+
+				vddio_sdmmc3: ldo6 {
+					regulator-name = "VDDIO_SDMMC3";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <3300000>;
+				};
+
+				/* LDO7 not used */
+
+				ldo9 {
+					regulator-name = "+V3.3_ETH(ldo9)";
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
+					regulator-always-on;
+				};
+
+				ldo10 {
+					regulator-name = "+V3.3_ETH(ldo10)";
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
+					regulator-always-on;
+				};
+
+				ldo11 {
+					regulator-name = "+V1.8_VPP_FUSE";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+				};
+			};
+		};
+
+		/*
+		 * TMP451 temperature sensor
+		 * Note: THERM_N directly connected to AS3722 PMIC THERM
+		 */
+		temperature-sensor@4c {
+			compatible = "ti,tmp451";
+			reg = <0x4c>;
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(I, 6) IRQ_TYPE_LEVEL_LOW>;
+
+			#thermal-sensor-cells = <1>;
+		};
+	};
+
+	/* SPI2: MCU SPI */
+	spi@7000d600 {
+		status = "okay";
+		spi-max-frequency = <25000000>;
+	};
+
+	pmc@7000e400 {
+		nvidia,invert-interrupt;
+		nvidia,suspend-mode = <1>;
+		nvidia,cpu-pwr-good-time = <500>;
+		nvidia,cpu-pwr-off-time = <300>;
+		nvidia,core-pwr-good-time = <641 3845>;
+		nvidia,core-pwr-off-time = <61036>;
+		nvidia,core-power-req-active-high;
+		nvidia,sys-clock-req-active-high;
+
+		/* Set power_off bit in ResetControl register of AS3722 PMIC */
+		i2c-thermtrip {
+			nvidia,i2c-controller-id = <4>;
+			nvidia,bus-addr = <0x40>;
+			nvidia,reg-addr = <0x36>;
+			nvidia,reg-data = <0x2>;
+		};
+	};
+
+	sata@70020000 {
+		phys = <&{/padctl@7009f000/pads/sata/lanes/sata-0}>;
+		phy-names = "sata-0";
+
+		avdd-supply = <&vdd_1v05>;
+		hvdd-supply = <&reg_3v3>;
+		vddio-supply = <&vdd_1v05>;
+	};
+
+	usb@70090000 {
+		/* USBO1, USBO1 (SS), USBH2, USBH4 and USBH4 (SS) */
+		phys = <&{/padctl@7009f000/pads/usb2/lanes/usb2-0}>,
+		       <&{/padctl@7009f000/pads/pcie/lanes/pcie-1}>,
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-1}>,
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-2}>,
+		       <&{/padctl@7009f000/pads/pcie/lanes/pcie-0}>;
+		phy-names = "usb2-0", "usb3-1", "usb2-1", "usb2-2", "usb3-0";
+
+		avddio-pex-supply = <&vdd_1v05>;
+		avdd-pll-erefe-supply = <&avdd_1v05>;
+		avdd-pll-utmip-supply = <&vddio_1v8>;
+		avdd-usb-ss-pll-supply = <&vdd_1v05>;
+		avdd-usb-supply = <&reg_3v3>;
+		dvddio-pex-supply = <&vdd_1v05>;
+		hvdd-usb-ss-pll-e-supply = <&reg_3v3>;
+		hvdd-usb-ss-supply = <&reg_3v3>;
+	};
+
+	padctl@7009f000 {
+		pads {
+			usb2 {
+				status = "okay";
+
+				lanes {
+					usb2-0 {
+						nvidia,function = "xusb";
+						status = "okay";
+					};
+
+					usb2-1 {
+						nvidia,function = "xusb";
+						status = "okay";
+					};
+
+					usb2-2 {
+						nvidia,function = "xusb";
+						status = "okay";
+					};
+				};
+			};
+
+			pcie {
+				status = "okay";
+
+				lanes {
+					pcie-0 {
+						nvidia,function = "usb3-ss";
+						status = "okay";
+					};
+
+					pcie-1 {
+						nvidia,function = "usb3-ss";
+						status = "okay";
+					};
+
+					pcie-2 {
+						nvidia,function = "pcie";
+						status = "okay";
+					};
+
+					pcie-3 {
+						nvidia,function = "pcie";
+						status = "okay";
+					};
+
+					pcie-4 {
+						nvidia,function = "pcie";
+						status = "okay";
+					};
+				};
+			};
+
+			sata {
+				status = "okay";
+
+				lanes {
+					sata-0 {
+						nvidia,function = "sata";
+						status = "okay";
+					};
+				};
+			};
+		};
+
+		ports {
+			/* USBO1 */
+			usb2-0 {
+				status = "okay";
+				mode = "otg";
+
+				vbus-supply = <&reg_usbo1_vbus>;
+			};
+
+			/* USBH2 */
+			usb2-1 {
+				status = "okay";
+				mode = "host";
+
+				vbus-supply = <&reg_usbh_vbus>;
+			};
+
+			/* USBH4 */
+			usb2-2 {
+				status = "okay";
+				mode = "host";
+
+				vbus-supply = <&reg_usbh_vbus>;
+			};
+
+			usb3-0 {
+				nvidia,usb2-companion = <2>;
+				status = "okay";
+			};
+
+			usb3-1 {
+				nvidia,usb2-companion = <0>;
+				status = "okay";
+			};
+		};
+	};
+
+	/* eMMC */
+	sdhci@700b0600 {
+		status = "okay";
+		bus-width = <8>;
+		non-removable;
+	};
+
+	/* CPU DFLL clock */
+	clock@70110000 {
+		status = "okay";
+		vdd-cpu-supply = <&vdd_cpu>;
+		nvidia,i2c-fs-rate = <400000>;
+	};
+
+	ahub@70300000 {
+		i2s@70301200 {
+			status = "okay";
+		};
+	};
+
+	clocks {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		clk32k_in: clock@0 {
+			compatible = "fixed-clock";
+			reg = <0>;
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+		};
+	};
+
+	cpus {
+		cpu@0 {
+			vdd-cpu-supply = <&vdd_cpu>;
+		};
+	};
+
+	reg_1v05_avdd_hdmi_pll: regulator-1v05-avdd-hdmi-pll {
+		compatible = "regulator-fixed";
+		regulator-name = "+V1.05_AVDD_HDMI_PLL";
+		regulator-min-microvolt = <1050000>;
+		regulator-max-microvolt = <1050000>;
+		gpio = <&gpio TEGRA_GPIO(H, 7) GPIO_ACTIVE_LOW>;
+		vin-supply = <&vdd_1v05>;
+	};
+
+	reg_3v3_mxm: regulator-3v3-mxm {
+		compatible = "regulator-fixed";
+		regulator-name = "+V3.3_MXM";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reg_3v3: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "+V3.3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+		/* PWR_EN_+V3.3 */
+		gpio = <&pmic 2 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&reg_3v3_mxm>;
+	};
+
+	reg_3v3_avdd_hdmi: regulator-3v3-avdd-hdmi {
+		compatible = "regulator-fixed";
+		regulator-name = "+V3.3_AVDD_HDMI";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vdd_1v05>;
+	};
+
+	sound {
+		compatible = "toradex,tegra-audio-sgtl5000-apalis_tk1",
+			     "nvidia,tegra-audio-sgtl5000";
+		nvidia,model = "Toradex Apalis TK1";
+		nvidia,audio-routing =
+			"Headphone Jack", "HP_OUT",
+			"LINE_IN", "Line In Jack",
+			"MIC_IN", "Mic Jack";
+		nvidia,i2s-controller = <&tegra_i2s2>;
+		nvidia,audio-codec = <&sgtl5000>;
+		clocks = <&tegra_car TEGRA124_CLK_PLL_A>,
+			 <&tegra_car TEGRA124_CLK_PLL_A_OUT0>,
+			 <&tegra_car TEGRA124_CLK_EXTERN1>;
+		clock-names = "pll_a", "pll_a_out0", "mclk";
+	};
+
+	thermal-zones {
+		cpu {
+			trips {
+				trip@0 {
+					temperature = <101000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				/*
+				 * There are currently no cooling maps because
+				 * there are no cooling devices
+				 */
+			};
+		};
+
+		mem {
+			trips {
+				trip@0 {
+					temperature = <101000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				/*
+				 * There are currently no cooling maps because
+				 * there are no cooling devices
+				 */
+			};
+		};
+
+		gpu {
+			trips {
+				trip@0 {
+					temperature = <101000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				/*
+				 * There are currently no cooling maps because
+				 * there are no cooling devices
+				 */
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/tegra124-jetson-tk1-emc.dtsi b/arch/arm/boot/dts/tegra124-jetson-tk1-emc.dtsi
index 2c5cede686dc..accb7055165a 100644
--- a/arch/arm/boot/dts/tegra124-jetson-tk1-emc.dtsi
+++ b/arch/arm/boot/dts/tegra124-jetson-tk1-emc.dtsi
@@ -1,5 +1,5 @@
 / {
-	clock@0,60006000 {
+	clock@60006000 {
 		emc-timings-3 {
 			nvidia,ram-code = <3>;
 
@@ -78,7 +78,7 @@
 		};
 	};
 
-	emc@0,7001b000 {
+	emc@7001b000 {
 		emc-timings-3 {
 			nvidia,ram-code = <3>;
 
@@ -2101,7 +2101,7 @@
 		};
 	};
 
-	memory-controller@0,70019000 {
+	memory-controller@70019000 {
 		emc-timings-3 {
 			nvidia,ram-code = <3>;
 
diff --git a/arch/arm/boot/dts/tegra124-jetson-tk1.dts b/arch/arm/boot/dts/tegra124-jetson-tk1.dts
index 941f36263c8f..e52b82449a79 100644
--- a/arch/arm/boot/dts/tegra124-jetson-tk1.dts
+++ b/arch/arm/boot/dts/tegra124-jetson-tk1.dts
@@ -10,8 +10,8 @@
 	compatible = "nvidia,jetson-tk1", "nvidia,tegra124";
 
 	aliases {
-		rtc0 = "/i2c@0,7000d000/pmic@40";
-		rtc1 = "/rtc@0,7000e000";
+		rtc0 = "/i2c@7000d000/pmic@40";
+		rtc1 = "/rtc@7000e000";
 
 		/* This order keeps the mapping DB9 connector <-> ttyS0 */
 		serial0 = &uartd;
@@ -27,7 +27,7 @@
 		reg = <0x0 0x80000000 0x0 0x80000000>;
 	};
 
-	pcie-controller@0,01003000 {
+	pcie-controller@01003000 {
 		status = "okay";
 
 		avddio-pex-supply = <&vdd_1v05_run>;
@@ -40,21 +40,21 @@
 
 		/* Mini PCIe */
 		pci@1,0 {
-			phys = <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-4}>;
+			phys = <&{/padctl@7009f000/pads/pcie/lanes/pcie-4}>;
 			phy-names = "pcie-0";
 			status = "okay";
 		};
 
 		/* Gigabit Ethernet */
 		pci@2,0 {
-			phys = <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-2}>;
+			phys = <&{/padctl@7009f000/pads/pcie/lanes/pcie-2}>;
 			phy-names = "pcie-0";
 			status = "okay";
 		};
 	};
 
-	host1x@0,50000000 {
-		hdmi@0,54280000 {
+	host1x@50000000 {
+		hdmi@54280000 {
 			status = "okay";
 
 			hdmi-supply = <&vdd_5v0_hdmi>;
@@ -75,7 +75,7 @@
 		vdd-supply = <&vdd_gpu>;
 	};
 
-	pinmux: pinmux@0,70000868 {
+	pinmux: pinmux@70000868 {
 		pinctrl-names = "boot";
 		pinctrl-0 = <&state_boot>;
 
@@ -1356,14 +1356,6 @@
 				nvidia,tristate = <TEGRA_PIN_DISABLE>;
 				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
 			};
-			owr {
-				nvidia,pins = "owr";
-				nvidia,function = "rsvd2";
-				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
-				nvidia,tristate = <TEGRA_PIN_ENABLE>;
-				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
-				nvidia,rcv-sel = <TEGRA_PIN_DISABLE>;
-			};
 			clk_32k_in {
 				nvidia,pins = "clk_32k_in";
 				nvidia,function = "clk";
@@ -1378,6 +1370,10 @@
 				nvidia,tristate = <TEGRA_PIN_DISABLE>;
 				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
 			};
+			dsi_b {
+				nvidia,pins = "mipi_pad_ctrl_dsi_b";
+				nvidia,function = "dsi_b";
+			};
 		};
 	};
 
@@ -1404,12 +1400,12 @@
 	};
 
 	/* DB9 serial port */
-	serial@0,70006300 {
+	serial@70006300 {
 		status = "okay";
 	};
 
 	/* Expansion GEN1_I2C_*, mini-PCIe I2C, on-board components */
-	i2c@0,7000c000 {
+	i2c@7000c000 {
 		status = "okay";
 		clock-frequency = <100000>;
 
@@ -1437,25 +1433,25 @@
 	};
 
 	/* Expansion GEN2_I2C_* */
-	i2c@0,7000c400 {
+	i2c@7000c400 {
 		status = "okay";
 		clock-frequency = <100000>;
 	};
 
 	/* Expansion CAM_I2C_* */
-	i2c@0,7000c500 {
+	i2c@7000c500 {
 		status = "okay";
 		clock-frequency = <100000>;
 	};
 
 	/* HDMI DDC */
-	hdmi_ddc: i2c@0,7000c700 {
+	hdmi_ddc: i2c@7000c700 {
 		status = "okay";
 		clock-frequency = <100000>;
 	};
 
 	/* Expansion PWR_I2C_*, on-board components */
-	i2c@0,7000d000 {
+	i2c@7000d000 {
 		status = "okay";
 		clock-frequency = <400000>;
 
@@ -1646,12 +1642,12 @@
 	};
 
 	/* Expansion TS_SPI_* */
-	spi@0,7000d400 {
+	spi@7000d400 {
 		status = "okay";
 	};
 
 	/* Internal SPI */
-	spi@0,7000da00 {
+	spi@7000da00 {
 		status = "okay";
 		spi-max-frequency = <25000000>;
 		spi-flash@0 {
@@ -1661,7 +1657,7 @@
 		};
 	};
 
-	pmc@0,7000e400 {
+	pmc@7000e400 {
 		nvidia,invert-interrupt;
 		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <500>;
@@ -1680,10 +1676,10 @@
 	};
 
 	/* Serial ATA */
-	sata@0,70020000 {
+	sata@70020000 {
 		status = "okay";
 
-		phys = <&{/padctl@0,7009f000/pads/sata/lanes/sata-0}>;
+		phys = <&{/padctl@7009f000/pads/sata/lanes/sata-0}>;
 		phy-names = "sata-0";
 
 		hvdd-supply = <&vdd_3v3_lp0>;
@@ -1694,15 +1690,15 @@
 		target-12v-supply = <&vdd_12v0_sata>;
 	};
 
-	hda@0,70030000 {
+	hda@70030000 {
 		status = "okay";
 	};
 
-	usb@0,70090000 {
-		phys = <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-0}>, /* Micro A/B */
-		       <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-1}>, /* Mini PCIe */
-		       <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-2}>, /* USB3 */
-		       <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-0}>; /* USB3 */
+	usb@70090000 {
+		phys = <&{/padctl@7009f000/pads/usb2/lanes/usb2-0}>, /* Micro A/B */
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-1}>, /* Mini PCIe */
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-2}>, /* USB3 */
+		       <&{/padctl@7009f000/pads/pcie/lanes/pcie-0}>; /* USB3 */
 		phy-names = "usb2-0", "usb2-1", "usb2-2", "usb3-0";
 
 		avddio-pex-supply = <&vdd_1v05_run>;
@@ -1717,7 +1713,7 @@
 		status = "okay";
 	};
 
-	padctl@0,7009f000 {
+	padctl@7009f000 {
 		status = "okay";
 
 		pads {
@@ -1804,7 +1800,7 @@
 	};
 
 	/* SD card */
-	sdhci@0,700b0400 {
+	sdhci@700b0400 {
 		status = "okay";
 		cd-gpios = <&gpio TEGRA_GPIO(V, 2) GPIO_ACTIVE_LOW>;
 		power-gpios = <&gpio TEGRA_GPIO(R, 0) GPIO_ACTIVE_HIGH>;
@@ -1814,40 +1810,40 @@
 	};
 
 	/* eMMC */
-	sdhci@0,700b0600 {
+	sdhci@700b0600 {
 		status = "okay";
 		bus-width = <8>;
 		non-removable;
 	};
 
 	/* CPU DFLL clock */
-	clock@0,70110000 {
+	clock@70110000 {
 		status = "okay";
 		vdd-cpu-supply = <&vdd_cpu>;
 		nvidia,i2c-fs-rate = <400000>;
 	};
 
-	ahub@0,70300000 {
-		i2s@0,70301100 {
+	ahub@70300000 {
+		i2s@70301100 {
 			status = "okay";
 		};
 	};
 
 	/* mini-PCIe USB */
-	usb@0,7d004000 {
+	usb@7d004000 {
 		status = "okay";
 	};
 
-	usb-phy@0,7d004000 {
+	usb-phy@7d004000 {
 		status = "okay";
 	};
 
 	/* USB A connector */
-	usb@0,7d008000 {
+	usb@7d008000 {
 		status = "okay";
 	};
 
-	usb-phy@0,7d008000 {
+	usb-phy@7d008000 {
 		status = "okay";
 		vbus-supply = <&vdd_usb3_vbus>;
 	};
@@ -2049,7 +2045,7 @@
 	thermal-zones {
 		cpu {
 			trips {
-				trip@0 {
+				trip {
 					temperature = <101000>;
 					hysteresis = <0>;
 					type = "critical";
@@ -2063,7 +2059,7 @@
 
 		mem {
 			trips {
-				trip@0 {
+				trip {
 					temperature = <101000>;
 					hysteresis = <0>;
 					type = "critical";
@@ -2077,7 +2073,7 @@
 
 		gpu {
 			trips {
-				trip@0 {
+				trip {
 					temperature = <101000>;
 					hysteresis = <0>;
 					type = "critical";
diff --git a/arch/arm/boot/dts/tegra124-nyan-big-emc.dtsi b/arch/arm/boot/dts/tegra124-nyan-big-emc.dtsi
index 1a5748d05dda..4458e86b2769 100644
--- a/arch/arm/boot/dts/tegra124-nyan-big-emc.dtsi
+++ b/arch/arm/boot/dts/tegra124-nyan-big-emc.dtsi
@@ -1,5 +1,5 @@
 / {
-	clock@0,60006000 {
+	clock@60006000 {
 		emc-timings-1 {
 			nvidia,ram-code = <1>;
 
@@ -67,7 +67,7 @@
 		};
 	};
 
-	emc@0,7001b000 {
+	emc@7001b000 {
 		emc-timings-1 {
 			nvidia,ram-code = <1>;
 
@@ -1754,7 +1754,7 @@
 		};
 	};
 
-	memory-controller@0,70019000 {
+	memory-controller@70019000 {
 		emc-timings-1 {
 			nvidia,ram-code = <1>;
 
diff --git a/arch/arm/boot/dts/tegra124-nyan-big.dts b/arch/arm/boot/dts/tegra124-nyan-big.dts
index 2d21253ea4e3..67d7cfb32541 100644
--- a/arch/arm/boot/dts/tegra124-nyan-big.dts
+++ b/arch/arm/boot/dts/tegra124-nyan-big.dts
@@ -15,7 +15,7 @@
 		ddc-i2c-bus = <&dpaux>;
 	};
 
-	sdhci@0,700b0400 { /* SD Card on this bus */
+	sdhci@700b0400 { /* SD Card on this bus */
 		wp-gpios = <&gpio TEGRA_GPIO(Q, 4) GPIO_ACTIVE_LOW>;
 	};
 
@@ -26,7 +26,7 @@
 		nvidia,model = "GoogleNyanBig";
 	};
 
-	pinmux@0,70000868 {
+	pinmux@70000868 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinmux_default>;
 
diff --git a/arch/arm/boot/dts/tegra124-nyan-blaze-emc.dtsi b/arch/arm/boot/dts/tegra124-nyan-blaze-emc.dtsi
index 9ecd108f56cf..4e7b59e25728 100644
--- a/arch/arm/boot/dts/tegra124-nyan-blaze-emc.dtsi
+++ b/arch/arm/boot/dts/tegra124-nyan-blaze-emc.dtsi
@@ -1,5 +1,5 @@
 / {
-	clock@0,60006000 {
+	clock@60006000 {
 		emc-timings-1 {
 			nvidia,ram-code = <1>;
 
@@ -67,7 +67,7 @@
 		};
 	};
 
-	emc@0,7001b000 {
+	emc@7001b000 {
 		emc-timings-1 {
 			nvidia,ram-code = <1>;
 
@@ -1754,7 +1754,7 @@
 		};
 	};
 
-	memory-controller@0,70019000 {
+	memory-controller@70019000 {
 		emc-timings-1 {
 			nvidia,ram-code = <1>;
 
diff --git a/arch/arm/boot/dts/tegra124-nyan-blaze.dts b/arch/arm/boot/dts/tegra124-nyan-blaze.dts
index 0d30c514ffad..c9582361c26e 100644
--- a/arch/arm/boot/dts/tegra124-nyan-blaze.dts
+++ b/arch/arm/boot/dts/tegra124-nyan-blaze.dts
@@ -22,7 +22,7 @@
 		nvidia,model = "GoogleNyanBlaze";
 	};
 
-	pinmux@0,70000868 {
+	pinmux@70000868 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinmux_default>;
 
diff --git a/arch/arm/boot/dts/tegra124-nyan.dtsi b/arch/arm/boot/dts/tegra124-nyan.dtsi
index 0710a600cc69..271505e0715f 100644
--- a/arch/arm/boot/dts/tegra124-nyan.dtsi
+++ b/arch/arm/boot/dts/tegra124-nyan.dtsi
@@ -3,8 +3,8 @@
 
 / {
 	aliases {
-		rtc0 = "/i2c@0,7000d000/pmic@40";
-		rtc1 = "/rtc@0,7000e000";
+		rtc0 = "/i2c@7000d000/pmic@40";
+		rtc1 = "/rtc@7000e000";
 		serial0 = &uarta;
 	};
 
@@ -16,8 +16,8 @@
 		reg = <0x0 0x80000000 0x0 0x80000000>;
 	};
 
-	host1x@0,50000000 {
-		hdmi@0,54280000 {
+	host1x@50000000 {
+		hdmi@54280000 {
 			status = "okay";
 
 			vdd-supply = <&vdd_3v3_hdmi>;
@@ -29,29 +29,29 @@
 				<&gpio TEGRA_GPIO(N, 7) GPIO_ACTIVE_HIGH>;
 		};
 
-		sor@0,54540000 {
+		sor@54540000 {
 			status = "okay";
 
 			nvidia,dpaux = <&dpaux>;
 			nvidia,panel = <&panel>;
 		};
 
-		dpaux@0,545c0000 {
+		dpaux@545c0000 {
 			vdd-supply = <&vdd_3v3_panel>;
 			status = "okay";
 		};
 	};
 
-	serial@0,70006000 {
+	serial@70006000 {
 		/* Debug connector on the bottom of the board near SD card. */
 		status = "okay";
 	};
 
-	pwm@0,7000a000 {
+	pwm@7000a000 {
 		status = "okay";
 	};
 
-	i2c@0,7000c000 {
+	i2c@7000c000 {
 		status = "okay";
 		clock-frequency = <100000>;
 
@@ -72,7 +72,7 @@
 		};
 	};
 
-	i2c@0,7000c400 {
+	i2c@7000c400 {
 		status = "okay";
 		clock-frequency = <100000>;
 
@@ -85,7 +85,7 @@
 		};
 	};
 
-	i2c@0,7000c500 {
+	i2c@7000c500 {
 		status = "okay";
 		clock-frequency = <400000>;
 
@@ -95,12 +95,12 @@
 		};
 	};
 
-	hdmi_ddc: i2c@0,7000c700 {
+	hdmi_ddc: i2c@7000c700 {
 		status = "okay";
 		clock-frequency = <100000>;
 	};
 
-	i2c@0,7000d000 {
+	i2c@7000d000 {
 		status = "okay";
 		clock-frequency = <400000>;
 
@@ -301,7 +301,7 @@
 		};
 	};
 
-	spi@0,7000d400 {
+	spi@7000d400 {
 		status = "okay";
 
 		cros_ec: cros-ec@0 {
@@ -342,7 +342,7 @@
 		};
 	};
 
-	spi@0,7000da00 {
+	spi@7000da00 {
 		status = "okay";
 		spi-max-frequency = <25000000>;
 
@@ -353,7 +353,7 @@
 		};
 	};
 
-	pmc@0,7000e400 {
+	pmc@7000e400 {
 		nvidia,invert-interrupt;
 		nvidia,suspend-mode = <0>;
 		nvidia,cpu-pwr-good-time = <500>;
@@ -364,16 +364,16 @@
 		nvidia,sys-clock-req-active-high;
 	};
 
-	hda@0,70030000 {
+	hda@70030000 {
 		status = "okay";
 	};
 
-	usb@0,70090000 {
-		phys = <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-0}>, /* 1st USB A */
-		       <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-1}>, /* Internal USB */
-		       <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-2}>, /* 2nd USB A */
-		       <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-0}>, /* 1st USB A */
-		       <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-1}>; /* 2nd USB A */
+	usb@70090000 {
+		phys = <&{/padctl@7009f000/pads/usb2/lanes/usb2-0}>, /* 1st USB A */
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-1}>, /* Internal USB */
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-2}>, /* 2nd USB A */
+		       <&{/padctl@7009f000/pads/pcie/lanes/pcie-0}>, /* 1st USB A */
+		       <&{/padctl@7009f000/pads/pcie/lanes/pcie-1}>; /* 2nd USB A */
 		phy-names = "usb2-0", "usb2-1", "usb2-2", "usb3-0", "usb3-1";
 
 		avddio-pex-supply = <&vdd_1v05_run>;
@@ -388,7 +388,7 @@
 		status = "okay";
 	};
 
-	padctl@0,7009f000 {
+	padctl@7009f000 {
 		status = "okay";
 
 		pads {
@@ -467,7 +467,7 @@
 		reset-gpios = <&gpio TEGRA_GPIO(X, 7) GPIO_ACTIVE_LOW>;
 	};
 
-	sdhci@0,700b0000 { /* WiFi/BT on this bus */
+	sdhci@700b0000 { /* WiFi/BT on this bus */
 		status = "okay";
 		bus-width = <4>;
 		no-1-8-v;
@@ -478,7 +478,7 @@
 		keep-power-in-suspend;
 	};
 
-	sdhci@0,700b0400 { /* SD Card on this bus */
+	sdhci@700b0400 { /* SD Card on this bus */
 		status = "okay";
 		cd-gpios = <&gpio TEGRA_GPIO(V, 2) GPIO_ACTIVE_LOW>;
 		power-gpios = <&gpio TEGRA_GPIO(R, 0) GPIO_ACTIVE_HIGH>;
@@ -487,7 +487,7 @@
 		vqmmc-supply = <&vddio_sdmmc3>;
 	};
 
-	sdhci@0,700b0600 { /* eMMC on this bus */
+	sdhci@700b0600 { /* eMMC on this bus */
 		status = "okay";
 		bus-width = <8>;
 		no-1-8-v;
@@ -495,14 +495,14 @@
 	};
 
 	/* CPU DFLL clock */
-	clock@0,70110000 {
+	clock@70110000 {
 		status = "disabled";
 		vdd-cpu-supply = <&vdd_cpu>;
 		nvidia,i2c-fs-rate = <400000>;
 	};
 
-	ahub@0,70300000 {
-		i2s@0,70301100 {
+	ahub@70300000 {
+		i2s@70301100 {
 			status = "okay";
 		};
 	};
diff --git a/arch/arm/boot/dts/tegra124-venice2.dts b/arch/arm/boot/dts/tegra124-venice2.dts
index 973446d07182..6e59cec0962b 100644
--- a/arch/arm/boot/dts/tegra124-venice2.dts
+++ b/arch/arm/boot/dts/tegra124-venice2.dts
@@ -8,8 +8,8 @@
 	compatible = "nvidia,venice2", "nvidia,tegra124";
 
 	aliases {
-		rtc0 = "/i2c@0,7000d000/pmic@40";
-		rtc1 = "/rtc@0,7000e000";
+		rtc0 = "/i2c@7000d000/pmic@40";
+		rtc1 = "/rtc@7000e000";
 		serial0 = &uarta;
 	};
 
@@ -21,8 +21,8 @@
 		reg = <0x0 0x80000000 0x0 0x80000000>;
 	};
 
-	host1x@0,50000000 {
-		hdmi@0,54280000 {
+	host1x@50000000 {
+		hdmi@54280000 {
 			status = "okay";
 
 			vdd-supply = <&vdd_3v3_hdmi>;
@@ -34,14 +34,14 @@
 				<&gpio TEGRA_GPIO(N, 7) GPIO_ACTIVE_HIGH>;
 		};
 
-		sor@0,54540000 {
+		sor@54540000 {
 			status = "okay";
 
 			nvidia,dpaux = <&dpaux>;
 			nvidia,panel = <&panel>;
 		};
 
-		dpaux@0,545c0000 {
+		dpaux@545c0000 {
 			vdd-supply = <&vdd_3v3_panel>;
 			status = "okay";
 		};
@@ -55,7 +55,7 @@
 		vdd-supply = <&vdd_gpu>;
 	};
 
-	pinmux: pinmux@0,70000868 {
+	pinmux: pinmux@70000868 {
 		pinctrl-names = "boot";
 		pinctrl-0 = <&pinmux_boot>;
 
@@ -596,15 +596,15 @@
 		};
 	};
 
-	serial@0,70006000 {
+	serial@70006000 {
 		status = "okay";
 	};
 
-	pwm@0,7000a000 {
+	pwm@7000a000 {
 		status = "okay";
 	};
 
-	i2c@0,7000c000 {
+	i2c@7000c000 {
 		status = "okay";
 		clock-frequency = <100000>;
 
@@ -616,7 +616,7 @@
 		};
 	};
 
-	i2c@0,7000c400 {
+	i2c@7000c400 {
 		status = "okay";
 		clock-frequency = <100000>;
 
@@ -629,17 +629,17 @@
 		};
 	};
 
-	i2c@0,7000c500 {
+	i2c@7000c500 {
 		status = "okay";
 		clock-frequency = <100000>;
 	};
 
-	hdmi_ddc: i2c@0,7000c700 {
+	hdmi_ddc: i2c@7000c700 {
 		status = "okay";
 		clock-frequency = <100000>;
 	};
 
-	i2c@0,7000d000 {
+	i2c@7000d000 {
 		status = "okay";
 		clock-frequency = <400000>;
 
@@ -834,7 +834,7 @@
 		};
 	};
 
-	spi@0,7000d400 {
+	spi@7000d400 {
 		status = "okay";
 
 		cros_ec: cros-ec@0 {
@@ -874,7 +874,7 @@
 		};
 	};
 
-	spi@0,7000da00 {
+	spi@7000da00 {
 		status = "okay";
 		spi-max-frequency = <25000000>;
 		spi-flash@0 {
@@ -884,7 +884,7 @@
 		};
 	};
 
-	pmc@0,7000e400 {
+	pmc@7000e400 {
 		nvidia,invert-interrupt;
 		nvidia,suspend-mode = <1>;
 		nvidia,cpu-pwr-good-time = <500>;
@@ -895,16 +895,16 @@
 		nvidia,sys-clock-req-active-high;
 	};
 
-	hda@0,70030000 {
+	hda@70030000 {
 		status = "okay";
 	};
 
-	usb@0,70090000 {
-		phys = <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-0}>, /* 1st USB A */
-		       <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-1}>, /* Internal USB */
-		       <&{/padctl@0,7009f000/pads/usb2/lanes/usb2-2}>, /* 2nd USB A */
-		       <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-0}>, /* 1st USB A */
-		       <&{/padctl@0,7009f000/pads/pcie/lanes/pcie-1}>; /* 2nd USB A */
+	usb@70090000 {
+		phys = <&{/padctl@7009f000/pads/usb2/lanes/usb2-0}>, /* 1st USB A */
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-1}>, /* Internal USB */
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-2}>, /* 2nd USB A */
+		       <&{/padctl@7009f000/pads/pcie/lanes/pcie-0}>, /* 1st USB A */
+		       <&{/padctl@7009f000/pads/pcie/lanes/pcie-1}>; /* 2nd USB A */
 		phy-names = "usb2-0", "usb2-1", "usb2-2", "usb3-0", "usb3-1";
 
 		avddio-pex-supply = <&vdd_1v05_run>;
@@ -919,7 +919,7 @@
 		status = "okay";
 	};
 
-	padctl@0,7009f000 {
+	padctl@7009f000 {
 		pads {
 			usb2 {
 				status = "okay";
@@ -998,7 +998,7 @@
 		};
 	};
 
-	sdhci@0,700b0400 {
+	sdhci@700b0400 {
 		cd-gpios = <&gpio TEGRA_GPIO(V, 2) GPIO_ACTIVE_HIGH>;
 		power-gpios = <&gpio TEGRA_GPIO(R, 0) GPIO_ACTIVE_HIGH>;
 		wp-gpios = <&gpio TEGRA_GPIO(Q, 4) GPIO_ACTIVE_LOW>;
@@ -1007,41 +1007,41 @@
 		vqmmc-supply = <&vddio_sdmmc3>;
 	};
 
-	sdhci@0,700b0600 {
+	sdhci@700b0600 {
 		status = "okay";
 		bus-width = <8>;
 		non-removable;
 	};
 
-	ahub@0,70300000 {
-		i2s@0,70301100 {
+	ahub@70300000 {
+		i2s@70301100 {
 			status = "okay";
 		};
 	};
 
-	usb@0,7d000000 {
+	usb@7d000000 {
 		status = "okay";
 	};
 
-	usb-phy@0,7d000000 {
+	usb-phy@7d000000 {
 		status = "okay";
 		vbus-supply = <&vdd_usb1_vbus>;
 	};
 
-	usb@0,7d004000 {
+	usb@7d004000 {
 		status = "okay";
 	};
 
-	usb-phy@0,7d004000 {
+	usb-phy@7d004000 {
 		status = "okay";
 		vbus-supply = <&vdd_run_cam>;
 	};
 
-	usb@0,7d008000 {
+	usb@7d008000 {
 		status = "okay";
 	};
 
-	usb-phy@0,7d008000 {
+	usb-phy@7d008000 {
 		status = "okay";
 		vbus-supply = <&vdd_usb3_vbus>;
 	};
diff --git a/arch/arm/boot/dts/tegra124.dtsi b/arch/arm/boot/dts/tegra124.dtsi
index ea4811870de2..ea340f9de448 100644
--- a/arch/arm/boot/dts/tegra124.dtsi
+++ b/arch/arm/boot/dts/tegra124.dtsi
@@ -14,7 +14,7 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
-	pcie-controller@0,01003000 {
+	pcie-controller@01003000 {
 		compatible = "nvidia,tegra124-pcie";
 		device_type = "pci";
 		reg = <0x0 0x01003000 0x0 0x00000800   /* PADS registers */
@@ -77,7 +77,7 @@
 		};
 	};
 
-	host1x@0,50000000 {
+	host1x@50000000 {
 		compatible = "nvidia,tegra124-host1x", "simple-bus";
 		reg = <0x0 0x50000000 0x0 0x00034000>;
 		interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>, /* syncpt */
@@ -91,7 +91,7 @@
 
 		ranges = <0 0x54000000 0 0x54000000 0 0x01000000>;
 
-		dc@0,54200000 {
+		dc@54200000 {
 			compatible = "nvidia,tegra124-dc";
 			reg = <0x0 0x54200000 0x0 0x00040000>;
 			interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
@@ -106,7 +106,7 @@
 			nvidia,head = <0>;
 		};
 
-		dc@0,54240000 {
+		dc@54240000 {
 			compatible = "nvidia,tegra124-dc";
 			reg = <0x0 0x54240000 0x0 0x00040000>;
 			interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
@@ -121,7 +121,7 @@
 			nvidia,head = <1>;
 		};
 
-		hdmi@0,54280000 {
+		hdmi@54280000 {
 			compatible = "nvidia,tegra124-hdmi";
 			reg = <0x0 0x54280000 0x0 0x00040000>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
@@ -133,7 +133,7 @@
 			status = "disabled";
 		};
 
-		sor@0,54540000 {
+		sor@54540000 {
 			compatible = "nvidia,tegra124-sor";
 			reg = <0x0 0x54540000 0x0 0x00040000>;
 			interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>;
@@ -147,7 +147,7 @@
 			status = "disabled";
 		};
 
-		dpaux: dpaux@0,545c0000 {
+		dpaux: dpaux@545c0000 {
 			compatible = "nvidia,tegra124-dpaux";
 			reg = <0x0 0x545c0000 0x0 0x00040000>;
 			interrupts = <GIC_SPI 159 IRQ_TYPE_LEVEL_HIGH>;
@@ -160,7 +160,7 @@
 		};
 	};
 
-	gic: interrupt-controller@0,50041000 {
+	gic: interrupt-controller@50041000 {
 		compatible = "arm,cortex-a15-gic";
 		#interrupt-cells = <3>;
 		interrupt-controller;
@@ -173,6 +173,11 @@
 		interrupt-parent = <&gic>;
 	};
 
+	/*
+	 * Please keep the following 0, notation in place as a former mainline
+	 * U-Boot version was looking for that particular notation in order to
+	 * perform required fix-ups on that GPU node.
+	 */
 	gpu@0,57000000 {
 		compatible = "nvidia,gk20a";
 		reg = <0x0 0x57000000 0x0 0x01000000>,
@@ -203,7 +208,7 @@
 		interrupt-parent = <&gic>;
 	};
 
-	timer@0,60005000 {
+	timer@60005000 {
 		compatible = "nvidia,tegra124-timer", "nvidia,tegra30-timer", "nvidia,tegra20-timer";
 		reg = <0x0 0x60005000 0x0 0x400>;
 		interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>,
@@ -215,7 +220,7 @@
 		clocks = <&tegra_car TEGRA124_CLK_TIMER>;
 	};
 
-	tegra_car: clock@0,60006000 {
+	tegra_car: clock@60006000 {
 		compatible = "nvidia,tegra124-car";
 		reg = <0x0 0x60006000 0x0 0x1000>;
 		#clock-cells = <1>;
@@ -223,12 +228,12 @@
 		nvidia,external-memory-controller = <&emc>;
 	};
 
-	flow-controller@0,60007000 {
+	flow-controller@60007000 {
 		compatible = "nvidia,tegra124-flowctrl";
 		reg = <0x0 0x60007000 0x0 0x1000>;
 	};
 
-	actmon@0,6000c800 {
+	actmon@6000c800 {
 		compatible = "nvidia,tegra124-actmon";
 		reg = <0x0 0x6000c800 0x0 0x400>;
 		interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
@@ -239,7 +244,7 @@
 		reset-names = "actmon";
 	};
 
-	gpio: gpio@0,6000d000 {
+	gpio: gpio@6000d000 {
 		compatible = "nvidia,tegra124-gpio", "nvidia,tegra30-gpio";
 		reg = <0x0 0x6000d000 0x0 0x1000>;
 		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
@@ -259,7 +264,7 @@
 		*/
 	};
 
-	apbdma: dma@0,60020000 {
+	apbdma: dma@60020000 {
 		compatible = "nvidia,tegra124-apbdma", "nvidia,tegra148-apbdma";
 		reg = <0x0 0x60020000 0x0 0x1400>;
 		interrupts = <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>,
@@ -300,13 +305,13 @@
 		#dma-cells = <1>;
 	};
 
-	apbmisc@0,70000800 {
+	apbmisc@70000800 {
 		compatible = "nvidia,tegra124-apbmisc", "nvidia,tegra20-apbmisc";
 		reg = <0x0 0x70000800 0x0 0x64>,   /* Chip revision */
 		      <0x0 0x7000e864 0x0 0x04>;   /* Strapping options */
 	};
 
-	pinmux: pinmux@0,70000868 {
+	pinmux: pinmux@70000868 {
 		compatible = "nvidia,tegra124-pinmux";
 		reg = <0x0 0x70000868 0x0 0x164>, /* Pad control registers */
 		      <0x0 0x70003000 0x0 0x434>, /* Mux registers */
@@ -321,7 +326,7 @@
 	 * the APB DMA based serial driver, the compatible is
 	 * "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart".
 	 */
-	uarta: serial@0,70006000 {
+	uarta: serial@70006000 {
 		compatible = "nvidia,tegra124-uart", "nvidia,tegra20-uart";
 		reg = <0x0 0x70006000 0x0 0x40>;
 		reg-shift = <2>;
@@ -334,7 +339,7 @@
 		status = "disabled";
 	};
 
-	uartb: serial@0,70006040 {
+	uartb: serial@70006040 {
 		compatible = "nvidia,tegra124-uart", "nvidia,tegra20-uart";
 		reg = <0x0 0x70006040 0x0 0x40>;
 		reg-shift = <2>;
@@ -347,7 +352,7 @@
 		status = "disabled";
 	};
 
-	uartc: serial@0,70006200 {
+	uartc: serial@70006200 {
 		compatible = "nvidia,tegra124-uart", "nvidia,tegra20-uart";
 		reg = <0x0 0x70006200 0x0 0x40>;
 		reg-shift = <2>;
@@ -360,7 +365,7 @@
 		status = "disabled";
 	};
 
-	uartd: serial@0,70006300 {
+	uartd: serial@70006300 {
 		compatible = "nvidia,tegra124-uart", "nvidia,tegra20-uart";
 		reg = <0x0 0x70006300 0x0 0x40>;
 		reg-shift = <2>;
@@ -373,7 +378,7 @@
 		status = "disabled";
 	};
 
-	pwm: pwm@0,7000a000 {
+	pwm: pwm@7000a000 {
 		compatible = "nvidia,tegra124-pwm", "nvidia,tegra20-pwm";
 		reg = <0x0 0x7000a000 0x0 0x100>;
 		#pwm-cells = <2>;
@@ -383,7 +388,7 @@
 		status = "disabled";
 	};
 
-	i2c@0,7000c000 {
+	i2c@7000c000 {
 		compatible = "nvidia,tegra124-i2c", "nvidia,tegra114-i2c";
 		reg = <0x0 0x7000c000 0x0 0x100>;
 		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
@@ -398,7 +403,7 @@
 		status = "disabled";
 	};
 
-	i2c@0,7000c400 {
+	i2c@7000c400 {
 		compatible = "nvidia,tegra124-i2c", "nvidia,tegra114-i2c";
 		reg = <0x0 0x7000c400 0x0 0x100>;
 		interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
@@ -413,7 +418,7 @@
 		status = "disabled";
 	};
 
-	i2c@0,7000c500 {
+	i2c@7000c500 {
 		compatible = "nvidia,tegra124-i2c", "nvidia,tegra114-i2c";
 		reg = <0x0 0x7000c500 0x0 0x100>;
 		interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
@@ -428,7 +433,7 @@
 		status = "disabled";
 	};
 
-	i2c@0,7000c700 {
+	i2c@7000c700 {
 		compatible = "nvidia,tegra124-i2c", "nvidia,tegra114-i2c";
 		reg = <0x0 0x7000c700 0x0 0x100>;
 		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
@@ -443,7 +448,7 @@
 		status = "disabled";
 	};
 
-	i2c@0,7000d000 {
+	i2c@7000d000 {
 		compatible = "nvidia,tegra124-i2c", "nvidia,tegra114-i2c";
 		reg = <0x0 0x7000d000 0x0 0x100>;
 		interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
@@ -458,7 +463,7 @@
 		status = "disabled";
 	};
 
-	i2c@0,7000d100 {
+	i2c@7000d100 {
 		compatible = "nvidia,tegra124-i2c", "nvidia,tegra114-i2c";
 		reg = <0x0 0x7000d100 0x0 0x100>;
 		interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
@@ -473,7 +478,7 @@
 		status = "disabled";
 	};
 
-	spi@0,7000d400 {
+	spi@7000d400 {
 		compatible = "nvidia,tegra124-spi", "nvidia,tegra114-spi";
 		reg = <0x0 0x7000d400 0x0 0x200>;
 		interrupts = <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>;
@@ -488,7 +493,7 @@
 		status = "disabled";
 	};
 
-	spi@0,7000d600 {
+	spi@7000d600 {
 		compatible = "nvidia,tegra124-spi", "nvidia,tegra114-spi";
 		reg = <0x0 0x7000d600 0x0 0x200>;
 		interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
@@ -503,7 +508,7 @@
 		status = "disabled";
 	};
 
-	spi@0,7000d800 {
+	spi@7000d800 {
 		compatible = "nvidia,tegra124-spi", "nvidia,tegra114-spi";
 		reg = <0x0 0x7000d800 0x0 0x200>;
 		interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
@@ -518,7 +523,7 @@
 		status = "disabled";
 	};
 
-	spi@0,7000da00 {
+	spi@7000da00 {
 		compatible = "nvidia,tegra124-spi", "nvidia,tegra114-spi";
 		reg = <0x0 0x7000da00 0x0 0x200>;
 		interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>;
@@ -533,7 +538,7 @@
 		status = "disabled";
 	};
 
-	spi@0,7000dc00 {
+	spi@7000dc00 {
 		compatible = "nvidia,tegra124-spi", "nvidia,tegra114-spi";
 		reg = <0x0 0x7000dc00 0x0 0x200>;
 		interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
@@ -548,7 +553,7 @@
 		status = "disabled";
 	};
 
-	spi@0,7000de00 {
+	spi@7000de00 {
 		compatible = "nvidia,tegra124-spi", "nvidia,tegra114-spi";
 		reg = <0x0 0x7000de00 0x0 0x200>;
 		interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
@@ -563,21 +568,21 @@
 		status = "disabled";
 	};
 
-	rtc@0,7000e000 {
+	rtc@7000e000 {
 		compatible = "nvidia,tegra124-rtc", "nvidia,tegra20-rtc";
 		reg = <0x0 0x7000e000 0x0 0x100>;
 		interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&tegra_car TEGRA124_CLK_RTC>;
 	};
 
-	pmc@0,7000e400 {
+	pmc@7000e400 {
 		compatible = "nvidia,tegra124-pmc";
 		reg = <0x0 0x7000e400 0x0 0x400>;
 		clocks = <&tegra_car TEGRA124_CLK_PCLK>, <&clk32k_in>;
 		clock-names = "pclk", "clk32k_in";
 	};
 
-	fuse@0,7000f800 {
+	fuse@7000f800 {
 		compatible = "nvidia,tegra124-efuse";
 		reg = <0x0 0x7000f800 0x0 0x400>;
 		clocks = <&tegra_car TEGRA124_CLK_FUSE>;
@@ -586,7 +591,7 @@
 		reset-names = "fuse";
 	};
 
-	mc: memory-controller@0,70019000 {
+	mc: memory-controller@70019000 {
 		compatible = "nvidia,tegra124-mc";
 		reg = <0x0 0x70019000 0x0 0x1000>;
 		clocks = <&tegra_car TEGRA124_CLK_MC>;
@@ -597,14 +602,14 @@
 		#iommu-cells = <1>;
 	};
 
-	emc: emc@0,7001b000 {
+	emc: emc@7001b000 {
 		compatible = "nvidia,tegra124-emc";
 		reg = <0x0 0x7001b000 0x0 0x1000>;
 
 		nvidia,memory-controller = <&mc>;
 	};
 
-	sata@0,70020000 {
+	sata@70020000 {
 		compatible = "nvidia,tegra124-ahci";
 		reg = <0x0 0x70027000 0x0 0x2000>, /* AHCI */
 		      <0x0 0x70020000 0x0 0x7000>; /* SATA */
@@ -621,7 +626,7 @@
 		status = "disabled";
 	};
 
-	hda@0,70030000 {
+	hda@70030000 {
 		compatible = "nvidia,tegra124-hda", "nvidia,tegra30-hda";
 		reg = <0x0 0x70030000 0x0 0x10000>;
 		interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
@@ -636,7 +641,7 @@
 		status = "disabled";
 	};
 
-	usb@0,70090000 {
+	usb@70090000 {
 		compatible = "nvidia,tegra124-xusb";
 		reg = <0x0 0x70090000 0x0 0x8000>,
 		      <0x0 0x70098000 0x0 0x1000>,
@@ -671,7 +676,7 @@
 		status = "disabled";
 	};
 
-	padctl: padctl@0,7009f000 {
+	padctl: padctl@7009f000 {
 		compatible = "nvidia,tegra124-xusb-padctl";
 		reg = <0x0 0x7009f000 0x0 0x1000>;
 		resets = <&tegra_car 142>;
@@ -804,7 +809,7 @@
 		};
 	};
 
-	sdhci@0,700b0000 {
+	sdhci@700b0000 {
 		compatible = "nvidia,tegra124-sdhci";
 		reg = <0x0 0x700b0000 0x0 0x200>;
 		interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
@@ -814,7 +819,7 @@
 		status = "disabled";
 	};
 
-	sdhci@0,700b0200 {
+	sdhci@700b0200 {
 		compatible = "nvidia,tegra124-sdhci";
 		reg = <0x0 0x700b0200 0x0 0x200>;
 		interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
@@ -824,7 +829,7 @@
 		status = "disabled";
 	};
 
-	sdhci@0,700b0400 {
+	sdhci@700b0400 {
 		compatible = "nvidia,tegra124-sdhci";
 		reg = <0x0 0x700b0400 0x0 0x200>;
 		interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
@@ -834,7 +839,7 @@
 		status = "disabled";
 	};
 
-	sdhci@0,700b0600 {
+	sdhci@700b0600 {
 		compatible = "nvidia,tegra124-sdhci";
 		reg = <0x0 0x700b0600 0x0 0x200>;
 		interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
@@ -844,7 +849,7 @@
 		status = "disabled";
 	};
 
-	soctherm: thermal-sensor@0,700e2000 {
+	soctherm: thermal-sensor@700e2000 {
 		compatible = "nvidia,tegra124-soctherm";
 		reg = <0x0 0x700e2000 0x0 0x1000>;
 		interrupts = <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
@@ -856,7 +861,7 @@
 		#thermal-sensor-cells = <1>;
 	};
 
-	dfll: clock@0,70110000 {
+	dfll: clock@70110000 {
 		compatible = "nvidia,tegra124-dfll";
 		reg = <0 0x70110000 0 0x100>, /* DFLL control */
 		      <0 0x70110000 0 0x100>, /* I2C output control */
@@ -880,7 +885,7 @@
 		status = "disabled";
 	};
 
-	ahub@0,70300000 {
+	ahub@70300000 {
 		compatible = "nvidia,tegra124-ahub";
 		reg = <0x0 0x70300000 0x0 0x200>,
 		      <0x0 0x70300800 0x0 0x800>,
@@ -932,7 +937,7 @@
 		#address-cells = <2>;
 		#size-cells = <2>;
 
-		tegra_i2s0: i2s@0,70301000 {
+		tegra_i2s0: i2s@70301000 {
 			compatible = "nvidia,tegra124-i2s";
 			reg = <0x0 0x70301000 0x0 0x100>;
 			nvidia,ahub-cif-ids = <4 4>;
@@ -942,7 +947,7 @@
 			status = "disabled";
 		};
 
-		tegra_i2s1: i2s@0,70301100 {
+		tegra_i2s1: i2s@70301100 {
 			compatible = "nvidia,tegra124-i2s";
 			reg = <0x0 0x70301100 0x0 0x100>;
 			nvidia,ahub-cif-ids = <5 5>;
@@ -952,7 +957,7 @@
 			status = "disabled";
 		};
 
-		tegra_i2s2: i2s@0,70301200 {
+		tegra_i2s2: i2s@70301200 {
 			compatible = "nvidia,tegra124-i2s";
 			reg = <0x0 0x70301200 0x0 0x100>;
 			nvidia,ahub-cif-ids = <6 6>;
@@ -962,7 +967,7 @@
 			status = "disabled";
 		};
 
-		tegra_i2s3: i2s@0,70301300 {
+		tegra_i2s3: i2s@70301300 {
 			compatible = "nvidia,tegra124-i2s";
 			reg = <0x0 0x70301300 0x0 0x100>;
 			nvidia,ahub-cif-ids = <7 7>;
@@ -972,7 +977,7 @@
 			status = "disabled";
 		};
 
-		tegra_i2s4: i2s@0,70301400 {
+		tegra_i2s4: i2s@70301400 {
 			compatible = "nvidia,tegra124-i2s";
 			reg = <0x0 0x70301400 0x0 0x100>;
 			nvidia,ahub-cif-ids = <8 8>;
@@ -983,7 +988,7 @@
 		};
 	};
 
-	usb@0,7d000000 {
+	usb@7d000000 {
 		compatible = "nvidia,tegra124-ehci", "nvidia,tegra30-ehci", "usb-ehci";
 		reg = <0x0 0x7d000000 0x0 0x4000>;
 		interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
@@ -995,7 +1000,7 @@
 		status = "disabled";
 	};
 
-	phy1: usb-phy@0,7d000000 {
+	phy1: usb-phy@7d000000 {
 		compatible = "nvidia,tegra124-usb-phy", "nvidia,tegra30-usb-phy";
 		reg = <0x0 0x7d000000 0x0 0x4000>,
 		      <0x0 0x7d000000 0x0 0x4000>;
@@ -1020,7 +1025,7 @@
 		status = "disabled";
 	};
 
-	usb@0,7d004000 {
+	usb@7d004000 {
 		compatible = "nvidia,tegra124-ehci", "nvidia,tegra30-ehci", "usb-ehci";
 		reg = <0x0 0x7d004000 0x0 0x4000>;
 		interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
@@ -1032,7 +1037,7 @@
 		status = "disabled";
 	};
 
-	phy2: usb-phy@0,7d004000 {
+	phy2: usb-phy@7d004000 {
 		compatible = "nvidia,tegra124-usb-phy", "nvidia,tegra30-usb-phy";
 		reg = <0x0 0x7d004000 0x0 0x4000>,
 		      <0x0 0x7d000000 0x0 0x4000>;
@@ -1056,7 +1061,7 @@
 		status = "disabled";
 	};
 
-	usb@0,7d008000 {
+	usb@7d008000 {
 		compatible = "nvidia,tegra124-ehci", "nvidia,tegra30-ehci", "usb-ehci";
 		reg = <0x0 0x7d008000 0x0 0x4000>;
 		interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
@@ -1068,7 +1073,7 @@
 		status = "disabled";
 	};
 
-	phy3: usb-phy@0,7d008000 {
+	phy3: usb-phy@7d008000 {
 		compatible = "nvidia,tegra124-usb-phy", "nvidia,tegra30-usb-phy";
 		reg = <0x0 0x7d008000 0x0 0x4000>,
 		      <0x0 0x7d000000 0x0 0x4000>;
diff --git a/arch/arm/boot/dts/tegra20-colibri-512.dtsi b/arch/arm/boot/dts/tegra20-colibri-512.dtsi
index 8e0066ad9628..1242b841f147 100644
--- a/arch/arm/boot/dts/tegra20-colibri-512.dtsi
+++ b/arch/arm/boot/dts/tegra20-colibri-512.dtsi
@@ -478,7 +478,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra20-harmony.dts b/arch/arm/boot/dts/tegra20-harmony.dts
index d2e960cbc001..d4fb4d39ede7 100644
--- a/arch/arm/boot/dts/tegra20-harmony.dts
+++ b/arch/arm/boot/dts/tegra20-harmony.dts
@@ -646,7 +646,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra20-paz00.dts b/arch/arm/boot/dts/tegra20-paz00.dts
index 33ed2b23026b..4e361a8c167e 100644
--- a/arch/arm/boot/dts/tegra20-paz00.dts
+++ b/arch/arm/boot/dts/tegra20-paz00.dts
@@ -512,7 +512,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra20-seaboard.dts b/arch/arm/boot/dts/tegra20-seaboard.dts
index 94b60a710dd8..2017acacc00c 100644
--- a/arch/arm/boot/dts/tegra20-seaboard.dts
+++ b/arch/arm/boot/dts/tegra20-seaboard.dts
@@ -798,7 +798,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra20-tamonten.dtsi b/arch/arm/boot/dts/tegra20-tamonten.dtsi
index 025e9e8037da..27d2bbbf1eae 100644
--- a/arch/arm/boot/dts/tegra20-tamonten.dtsi
+++ b/arch/arm/boot/dts/tegra20-tamonten.dtsi
@@ -508,7 +508,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra20-trimslice.dts b/arch/arm/boot/dts/tegra20-trimslice.dts
index 4a035f74043a..381747f114a9 100644
--- a/arch/arm/boot/dts/tegra20-trimslice.dts
+++ b/arch/arm/boot/dts/tegra20-trimslice.dts
@@ -383,7 +383,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra20-ventana.dts b/arch/arm/boot/dts/tegra20-ventana.dts
index a28c060a839b..8f0aaabf7e28 100644
--- a/arch/arm/boot/dts/tegra20-ventana.dts
+++ b/arch/arm/boot/dts/tegra20-ventana.dts
@@ -592,7 +592,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra20-whistler.dts b/arch/arm/boot/dts/tegra20-whistler.dts
index 073806d07b2b..1e06f854c8b4 100644
--- a/arch/arm/boot/dts/tegra20-whistler.dts
+++ b/arch/arm/boot/dts/tegra20-whistler.dts
@@ -569,7 +569,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra30-apalis.dtsi b/arch/arm/boot/dts/tegra30-apalis.dtsi
index bf361277fe10..192b95177aac 100644
--- a/arch/arm/boot/dts/tegra30-apalis.dtsi
+++ b/arch/arm/boot/dts/tegra30-apalis.dtsi
@@ -567,7 +567,7 @@
 			blocks = <0x5>;
 			irq-trigger = <0x1>;
 
-			stmpe_touchscreen {
+			stmpe_touchscreen@0 {
 				compatible = "st,stmpe-ts";
 				reg = <0>;
 				/* 3.25 MHz ADC clock speed */
@@ -674,13 +674,14 @@
 
 		clk32k_in: clk@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
+
 		clk16m: clk@1 {
 			compatible = "fixed-clock";
-			reg=<1>;
+			reg = <1>;
 			#clock-cells = <0>;
 			clock-frequency = <16000000>;
 			clock-output-names = "clk16m";
diff --git a/arch/arm/boot/dts/tegra30-beaver.dts b/arch/arm/boot/dts/tegra30-beaver.dts
index b6da15d823a6..0350002849d5 100644
--- a/arch/arm/boot/dts/tegra30-beaver.dts
+++ b/arch/arm/boot/dts/tegra30-beaver.dts
@@ -1952,7 +1952,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra30-cardhu.dtsi b/arch/arm/boot/dts/tegra30-cardhu.dtsi
index 4721c1c9c780..f11012bb58cc 100644
--- a/arch/arm/boot/dts/tegra30-cardhu.dtsi
+++ b/arch/arm/boot/dts/tegra30-cardhu.dtsi
@@ -423,7 +423,7 @@
 
 		clk32k_in: clock@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tegra30-colibri-eval-v3.dts b/arch/arm/boot/dts/tegra30-colibri-eval-v3.dts
index 76875c3160fe..a8c0318743b6 100644
--- a/arch/arm/boot/dts/tegra30-colibri-eval-v3.dts
+++ b/arch/arm/boot/dts/tegra30-colibri-eval-v3.dts
@@ -131,7 +131,7 @@
 	clocks {
 		clk16m: clk@1 {
 			compatible = "fixed-clock";
-			reg=<1>;
+			reg = <1>;
 			#clock-cells = <0>;
 			clock-frequency = <16000000>;
 			clock-output-names = "clk16m";
diff --git a/arch/arm/boot/dts/tegra30-colibri.dtsi b/arch/arm/boot/dts/tegra30-colibri.dtsi
index 2d8c58fd9357..a265534cd314 100644
--- a/arch/arm/boot/dts/tegra30-colibri.dtsi
+++ b/arch/arm/boot/dts/tegra30-colibri.dtsi
@@ -420,7 +420,7 @@
 
 		clk32k_in: clk@0 {
 			compatible = "fixed-clock";
-			reg=<0>;
+			reg = <0>;
 			#clock-cells = <0>;
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tny_a9260_common.dtsi b/arch/arm/boot/dts/tny_a9260_common.dtsi
index ce7138c3af1b..f9dc463b9e48 100644
--- a/arch/arm/boot/dts/tny_a9260_common.dtsi
+++ b/arch/arm/boot/dts/tny_a9260_common.dtsi
@@ -16,15 +16,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/tny_a9263.dts b/arch/arm/boot/dts/tny_a9263.dts
index 3043296345b7..9161cd9889b4 100644
--- a/arch/arm/boot/dts/tny_a9263.dts
+++ b/arch/arm/boot/dts/tny_a9263.dts
@@ -21,15 +21,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -99,7 +90,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 	};
 };
diff --git a/arch/arm/boot/dts/uniphier-common32.dtsi b/arch/arm/boot/dts/uniphier-common32.dtsi
index 61a095598206..03f60ec340b5 100644
--- a/arch/arm/boot/dts/uniphier-common32.dtsi
+++ b/arch/arm/boot/dts/uniphier-common32.dtsi
@@ -105,6 +105,8 @@
 			reg = <0x58c00000 0x400>;
 			#address-cells = <2>;
 			#size-cells = <1>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_system_bus>;
 		};
 
 		smpctrl@59800000 {
@@ -134,9 +136,13 @@
 			interrupt-controller;
 		};
 
-		pinctrl: pinctrl@5f801000 {
-			/* specify compatible in each SoC DTSI */
-			reg = <0x5f801000 0xe00>;
+		soc-glue@5f800000 {
+			compatible = "simple-mfd", "syscon";
+			reg = <0x5f800000 0x2000>;
+
+			pinctrl: pinctrl {
+				 /* specify compatible in each SoC DTSI */
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/uniphier-ph1-ld4.dtsi b/arch/arm/boot/dts/uniphier-ph1-ld4.dtsi
index dadd86070c98..debad7ffef05 100644
--- a/arch/arm/boot/dts/uniphier-ph1-ld4.dtsi
+++ b/arch/arm/boot/dts/uniphier-ph1-ld4.dtsi
@@ -182,5 +182,5 @@
 };
 
 &pinctrl {
-	compatible = "socionext,ph1-ld4-pinctrl", "syscon";
+	compatible = "socionext,uniphier-ld4-pinctrl";
 };
diff --git a/arch/arm/boot/dts/uniphier-ph1-ld6b.dtsi b/arch/arm/boot/dts/uniphier-ph1-ld6b.dtsi
index 532115234025..19c107c66bae 100644
--- a/arch/arm/boot/dts/uniphier-ph1-ld6b.dtsi
+++ b/arch/arm/boot/dts/uniphier-ph1-ld6b.dtsi
@@ -63,5 +63,5 @@
  * which makes the pinctrl driver unshareable.
  */
 &pinctrl {
-	compatible = "socionext,ph1-ld6b-pinctrl", "syscon";
+	compatible = "socionext,uniphier-ld6b-pinctrl";
 };
diff --git a/arch/arm/boot/dts/uniphier-ph1-pro4.dtsi b/arch/arm/boot/dts/uniphier-ph1-pro4.dtsi
index 20f3f2ae7fa4..7b9da0852005 100644
--- a/arch/arm/boot/dts/uniphier-ph1-pro4.dtsi
+++ b/arch/arm/boot/dts/uniphier-ph1-pro4.dtsi
@@ -200,5 +200,5 @@
 };
 
 &pinctrl {
-	compatible = "socionext,ph1-pro4-pinctrl", "syscon";
+	compatible = "socionext,uniphier-pro4-pinctrl";
 };
diff --git a/arch/arm/boot/dts/uniphier-ph1-pro5.dtsi b/arch/arm/boot/dts/uniphier-ph1-pro5.dtsi
index 24f6f664b269..7e4aa2fde719 100644
--- a/arch/arm/boot/dts/uniphier-ph1-pro5.dtsi
+++ b/arch/arm/boot/dts/uniphier-ph1-pro5.dtsi
@@ -194,5 +194,5 @@
 };
 
 &pinctrl {
-	compatible = "socionext,ph1-pro5-pinctrl", "syscon";
+	compatible = "socionext,uniphier-pro5-pinctrl";
 };
diff --git a/arch/arm/boot/dts/uniphier-ph1-sld8.dtsi b/arch/arm/boot/dts/uniphier-ph1-sld8.dtsi
index 6bfd29a05575..467f9d8e9873 100644
--- a/arch/arm/boot/dts/uniphier-ph1-sld8.dtsi
+++ b/arch/arm/boot/dts/uniphier-ph1-sld8.dtsi
@@ -181,5 +181,5 @@
 };
 
 &pinctrl {
-	compatible = "socionext,ph1-sld8-pinctrl", "syscon";
+	compatible = "socionext,uniphier-sld8-pinctrl";
 };
diff --git a/arch/arm/boot/dts/uniphier-pinctrl.dtsi b/arch/arm/boot/dts/uniphier-pinctrl.dtsi
index f2f3fbe2d517..10a711041b4a 100644
--- a/arch/arm/boot/dts/uniphier-pinctrl.dtsi
+++ b/arch/arm/boot/dts/uniphier-pinctrl.dtsi
@@ -78,6 +78,11 @@
 		function = "nand";
 	};
 
+	pinctrl_system_bus: system_bus_grp {
+		groups = "system_bus", "system_bus_cs1";
+		function = "system_bus";
+	};
+
 	pinctrl_uart0: uart0_grp {
 		groups = "uart0";
 		function = "uart0";
diff --git a/arch/arm/boot/dts/uniphier-proxstream2-gentil.dts b/arch/arm/boot/dts/uniphier-proxstream2-gentil.dts
index bf2619e4d489..98d895b7af1d 100644
--- a/arch/arm/boot/dts/uniphier-proxstream2-gentil.dts
+++ b/arch/arm/boot/dts/uniphier-proxstream2-gentil.dts
@@ -55,13 +55,13 @@
 	};
 
 	chosen {
-		stdout-path = "serial2:115200n8";
+		stdout-path = "serial0:115200n8";
 	};
 
 	aliases {
-		serial0 = &serial0;
-		serial1 = &serial1;
-		serial2 = &serial2;
+		serial0 = &serial2;
+		serial1 = &serial0;
+		serial2 = &serial1;
 		i2c0 = &i2c0;
 		i2c2 = &i2c2;
 		i2c4 = &i2c4;
diff --git a/arch/arm/boot/dts/uniphier-proxstream2-vodka.dts b/arch/arm/boot/dts/uniphier-proxstream2-vodka.dts
index 498acac3d95d..1fb8bd7bb686 100644
--- a/arch/arm/boot/dts/uniphier-proxstream2-vodka.dts
+++ b/arch/arm/boot/dts/uniphier-proxstream2-vodka.dts
@@ -55,13 +55,13 @@
 	};
 
 	chosen {
-		stdout-path = "serial2:115200n8";
+		stdout-path = "serial0:115200n8";
 	};
 
 	aliases {
-		serial0 = &serial0;
-		serial1 = &serial1;
-		serial2 = &serial2;
+		serial0 = &serial2;
+		serial1 = &serial0;
+		serial2 = &serial1;
 		i2c0 = &i2c0;
 		i2c4 = &i2c4;
 		i2c5 = &i2c5;
diff --git a/arch/arm/boot/dts/uniphier-proxstream2.dtsi b/arch/arm/boot/dts/uniphier-proxstream2.dtsi
index 4ac484c6ce4e..d00d6f5c2668 100644
--- a/arch/arm/boot/dts/uniphier-proxstream2.dtsi
+++ b/arch/arm/boot/dts/uniphier-proxstream2.dtsi
@@ -205,5 +205,5 @@
 };
 
 &pinctrl {
-	compatible = "socionext,proxstream2-pinctrl", "syscon";
+	compatible = "socionext,uniphier-pxs2-pinctrl";
 };
diff --git a/arch/arm/boot/dts/usb_a9260_common.dtsi b/arch/arm/boot/dts/usb_a9260_common.dtsi
index 9beea8976584..7514b347cdd2 100644
--- a/arch/arm/boot/dts/usb_a9260_common.dtsi
+++ b/arch/arm/boot/dts/usb_a9260_common.dtsi
@@ -8,15 +8,6 @@
 
 / {
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -90,7 +81,7 @@
 			};
 		};
 
-		usb0: ohci@00500000 {
+		usb0: ohci@500000 {
 			num-ports = <2>;
 			status = "okay";
 		};
@@ -119,7 +110,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 	};
 };
diff --git a/arch/arm/boot/dts/usb_a9263.dts b/arch/arm/boot/dts/usb_a9263.dts
index 8cc6edb29694..bfc48a272417 100644
--- a/arch/arm/boot/dts/usb_a9263.dts
+++ b/arch/arm/boot/dts/usb_a9263.dts
@@ -21,15 +21,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -147,7 +138,7 @@
 		};
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		status = "okay";
 	};
 };
diff --git a/arch/arm/boot/dts/usb_a9g20_common.dtsi b/arch/arm/boot/dts/usb_a9g20_common.dtsi
index 0b3b36182fe5..088c2c3685ab 100644
--- a/arch/arm/boot/dts/usb_a9g20_common.dtsi
+++ b/arch/arm/boot/dts/usb_a9g20_common.dtsi
@@ -11,14 +11,15 @@
 
 / {
 	chosen {
-		bootargs = "mem=64M console=ttyS0,115200 root=/dev/mtdblock5 rw rootfstype=ubifs";
+		bootargs = "mem=64M root=/dev/mtdblock5 rw rootfstype=ubifs";
+		stdout-path = "serial0:115200n8";
 	};
 
 	memory {
 		reg = <0x20000000 0x4000000>;
 	};
 
-	i2c@0 {
+	i2c-gpio-0 {
 		rv3029c2@56 {
 			compatible = "rv3029c2";
 			reg = <0x56>;
diff --git a/arch/arm/configs/bcm_defconfig b/arch/arm/configs/bcm_defconfig
deleted file mode 100644
index 909049a280ec..000000000000
--- a/arch/arm/configs/bcm_defconfig
+++ /dev/null
@@ -1,141 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-# CONFIG_SWAP is not set
-CONFIG_SYSVIPC=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=19
-CONFIG_CGROUPS=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CGROUP_CPUACCT=y
-CONFIG_CGROUP_SCHED=y
-CONFIG_BLK_CGROUP=y
-CONFIG_NAMESPACES=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_SYSCTL_SYSCALL=y
-CONFIG_EMBEDDED=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_ARCH_BCM=y
-CONFIG_ARCH_BCM_21664=y
-CONFIG_ARCH_BCM_281XX=y
-CONFIG_ARM_THUMBEE=y
-CONFIG_SMP=y
-CONFIG_PREEMPT=y
-CONFIG_AEABI=y
-# CONFIG_COMPACTION is not set
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_CMDLINE="console=ttyS0,115200n8 mem=128M"
-CONFIG_CPU_IDLE=y
-CONFIG_VFP=y
-CONFIG_NEON=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_PM=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_PACKET_DIAG=y
-CONFIG_UNIX=y
-CONFIG_UNIX_DIAG=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_SYN_COOKIES=y
-CONFIG_TCP_MD5SIG=y
-CONFIG_IPV6=y
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_PROC_DEVICETREE=y
-# CONFIG_BLK_DEV is not set
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_MULTI_LUN=y
-CONFIG_SCSI_SCAN_ASYNC=y
-CONFIG_INPUT_FF_MEMLESS=y
-CONFIG_INPUT_JOYDEV=y
-CONFIG_INPUT_EVDEV=y
-# CONFIG_KEYBOARD_ATKBD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_INPUT_MISC=y
-CONFIG_INPUT_UINPUT=y
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_8250_RSA=y
-CONFIG_SERIAL_8250_DW=y
-CONFIG_HW_RANDOM=y
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-# CONFIG_HWMON is not set
-CONFIG_MFD_BCM590XX=y
-CONFIG_REGULATOR=y
-CONFIG_REGULATOR_FIXED_VOLTAGE=y
-CONFIG_REGULATOR_USERSPACE_CONSUMER=y
-CONFIG_REGULATOR_BCM590XX=y
-
-CONFIG_VIDEO_OUTPUT_CONTROL=y
-CONFIG_FB=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_BACKLIGHT_CLASS_DEVICE=y
-CONFIG_BACKLIGHT_PWM=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_MMC=y
-CONFIG_MMC_BLOCK_MINORS=32
-CONFIG_MMC_TEST=y
-CONFIG_MMC_SDHCI=y
-CONFIG_MMC_SDHCI_PLTFM=y
-CONFIG_MMC_SDHCI_BCM_KONA=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
-CONFIG_PWM=y
-CONFIG_PWM_BCM_KONA=y
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_EXT4_FS_SECURITY=y
-CONFIG_AUTOFS4_FS=y
-CONFIG_FUSE_FS=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_CONFIGFS_FS=y
-# CONFIG_MISC_FILESYSTEMS is not set
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=110
-CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y
-# CONFIG_FTRACE is not set
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
-CONFIG_CRC_ITU_T=y
-CONFIG_CRC7=y
-CONFIG_XZ_DEC=y
-CONFIG_AVERAGE=y
-CONFIG_PINCTRL_BCM281XX=y
-CONFIG_WATCHDOG=y
-CONFIG_BCM_KONA_WDT=y
-CONFIG_BCM_KONA_WDT_DEBUG=y
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 47195e8690b4..01986deef7c5 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -1,5 +1,4 @@
 CONFIG_SYSVIPC=y
-CONFIG_FHANDLE=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_CGROUPS=y
@@ -13,8 +12,6 @@ CONFIG_ARCH_EXYNOS3=y
 CONFIG_EXYNOS5420_MCPM=y
 CONFIG_SMP=y
 CONFIG_BIG_LITTLE=y
-CONFIG_BL_SWITCHER=y
-CONFIG_BL_SWITCHER_DUMMY_IF=y
 CONFIG_NR_CPUS=8
 CONFIG_PREEMPT=y
 CONFIG_AEABI=y
@@ -84,9 +81,9 @@ CONFIG_INPUT_MAX77693_HAPTIC=y
 CONFIG_INPUT_MAX8997_HAPTIC=y
 CONFIG_KEYBOARD_SAMSUNG=y
 CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_SAMSUNG=y
 CONFIG_SERIAL_SAMSUNG_CONSOLE=y
-CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_HW_RANDOM=y
 CONFIG_TCG_TPM=y
 CONFIG_TCG_TIS_I2C_INFINEON=y
@@ -112,10 +109,8 @@ CONFIG_SENSORS_LM90=y
 CONFIG_SENSORS_NTC_THERMISTOR=y
 CONFIG_SENSORS_PWM_FAN=y
 CONFIG_SENSORS_INA2XX=y
-CONFIG_THERMAL=y
 CONFIG_CPU_THERMAL=y
 CONFIG_THERMAL_EMULATION=y
-CONFIG_EXYNOS_THERMAL=y
 CONFIG_WATCHDOG=y
 CONFIG_S3C2410_WATCHDOG=y
 CONFIG_MFD_CROS_EC=y
@@ -144,20 +139,32 @@ CONFIG_REGULATOR_TPS65090=y
 CONFIG_REGULATOR_WM8994=y
 CONFIG_MEDIA_SUPPORT=m
 CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_MEDIA_CONTROLLER=y
+CONFIG_VIDEO_V4L2_SUBDEV_API=y
 CONFIG_MEDIA_USB_SUPPORT=y
 CONFIG_USB_VIDEO_CLASS=m
+CONFIG_V4L_PLATFORM_DRIVERS=y
+CONFIG_VIDEO_SAMSUNG_EXYNOS4_IS=m
+CONFIG_VIDEO_S5P_FIMC=m
+CONFIG_VIDEO_S5P_MIPI_CSIS=m
+CONFIG_VIDEO_EXYNOS_FIMC_LITE=m
+CONFIG_VIDEO_EXYNOS4_FIMC_IS=m
+CONFIG_V4L_MEM2MEM_DRIVERS=y
+CONFIG_VIDEO_SAMSUNG_S5P_JPEG=m
+CONFIG_VIDEO_SAMSUNG_S5P_MFC=m
+CONFIG_V4L_TEST_DRIVERS=y
 CONFIG_DRM=y
-CONFIG_DRM_NXP_PTN3460=y
-CONFIG_DRM_PARADE_PS8622=y
 CONFIG_DRM_EXYNOS=y
 CONFIG_DRM_EXYNOS_FIMD=y
-CONFIG_DRM_EXYNOS_DSI=y
 CONFIG_DRM_EXYNOS_MIXER=y
 CONFIG_DRM_EXYNOS_DPI=y
+CONFIG_DRM_EXYNOS_DSI=y
 CONFIG_DRM_EXYNOS_HDMI=y
 CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_DRM_PANEL_SAMSUNG_LD9040=y
 CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0=y
+CONFIG_DRM_NXP_PTN3460=y
+CONFIG_DRM_PARADE_PS8622=y
 CONFIG_EXYNOS_VIDEO=y
 CONFIG_EXYNOS_MIPI_DSI=y
 CONFIG_LCD_CLASS_DEVICE=y
@@ -171,7 +178,6 @@ CONFIG_SND_SOC_SAMSUNG=y
 CONFIG_SND_SOC_SAMSUNG_SMDK_WM8994=y
 CONFIG_SND_SOC_SMDK_WM8994_PCM=y
 CONFIG_SND_SOC_SNOW=y
-CONFIG_SND_SOC_ODROIDX2=y
 CONFIG_SND_SIMPLE_CARD=y
 CONFIG_USB=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
@@ -209,7 +215,6 @@ CONFIG_RTC_DRV_S5M=y
 CONFIG_RTC_DRV_S3C=y
 CONFIG_DMADEVICES=y
 CONFIG_PL330_DMA=y
-CONFIG_CHROME_PLATFORMS=y
 CONFIG_CROS_EC_CHARDEV=y
 CONFIG_COMMON_CLK_MAX77686=y
 CONFIG_COMMON_CLK_MAX77802=y
@@ -227,7 +232,6 @@ CONFIG_PWM_SAMSUNG=y
 CONFIG_PHY_EXYNOS5250_SATA=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
-CONFIG_EXT4_FS=y
 CONFIG_AUTOFS4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
@@ -260,3 +264,4 @@ CONFIG_CRYPTO_AES_ARM_BS=m
 CONFIG_CRC_CCITT=y
 CONFIG_FONTS=y
 CONFIG_FONT_7x14=y
+CONFIG_VIDEO_VIVID=m
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 21339ce29654..3219480b9dbf 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -146,7 +146,7 @@ CONFIG_MICREL_PHY=y
 CONFIG_USB_PEGASUS=m
 CONFIG_USB_RTL8150=m
 CONFIG_USB_RTL8152=m
-CONFIG_USB_USBNET=m
+CONFIG_USB_USBNET=y
 CONFIG_USB_NET_CDC_EEM=m
 CONFIG_BRCMFMAC=m
 CONFIG_WL12XX=m
@@ -161,6 +161,7 @@ CONFIG_KEYBOARD_IMX=y
 CONFIG_MOUSE_PS2=m
 CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_ADS7846=y
 CONFIG_TOUCHSCREEN_EGALAX=y
 CONFIG_TOUCHSCREEN_IMX6UL_TSC=y
 CONFIG_TOUCHSCREEN_EDT_FT5X06=y
@@ -296,6 +297,7 @@ CONFIG_USB_ZERO=m
 CONFIG_USB_ETH=m
 CONFIG_USB_G_NCM=m
 CONFIG_USB_GADGETFS=m
+CONFIG_USB_FUNCTIONFS=m
 CONFIG_USB_MASS_STORAGE=m
 CONFIG_USB_G_SERIAL=m
 CONFIG_MMC=y
diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig
index faba04d93ad5..71b42e66488a 100644
--- a/arch/arm/configs/keystone_defconfig
+++ b/arch/arm/configs/keystone_defconfig
@@ -144,6 +144,7 @@ CONFIG_I2C_DAVINCI=y
 CONFIG_SPI=y
 CONFIG_SPI_DAVINCI=y
 CONFIG_SPI_SPIDEV=y
+CONFIG_PINCTRL_SINGLE=y
 CONFIG_GPIOLIB=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_DAVINCI=y
diff --git a/arch/arm/configs/lpc18xx_defconfig b/arch/arm/configs/lpc18xx_defconfig
index 2ae00b09cfc2..2de1bf0e497e 100644
--- a/arch/arm/configs/lpc18xx_defconfig
+++ b/arch/arm/configs/lpc18xx_defconfig
@@ -149,6 +149,8 @@ CONFIG_PWM=y
 CONFIG_PWM_LPC18XX_SCT=y
 CONFIG_IIO=y
 CONFIG_MMA7455_I2C=y
+CONFIG_LPC18XX_ADC=y
+CONFIG_LPC18XX_DAC=y
 CONFIG_IIO_SYSFS_TRIGGER=y
 CONFIG_PHY_LPC18XX_USB_OTG=y
 CONFIG_NVMEM=y
diff --git a/arch/arm/configs/multi_v4t_defconfig b/arch/arm/configs/multi_v4t_defconfig
new file mode 100644
index 000000000000..433eebb4103f
--- /dev/null
+++ b/arch/arm/configs/multi_v4t_defconfig
@@ -0,0 +1,106 @@
+CONFIG_KERNEL_LZMA=y
+CONFIG_SYSVIPC=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EMBEDDED=y
+CONFIG_SLOB=y
+CONFIG_JUMP_LABEL=y
+# CONFIG_LBDAF is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARCH_MULTI_V4T=y
+# CONFIG_ARCH_MULTI_V7 is not set
+CONFIG_ARCH_AT91=y
+CONFIG_SOC_AT91RM9200=y
+CONFIG_ARCH_CLPS711X=y
+CONFIG_ARCH_INTEGRATOR=y
+CONFIG_ARCH_INTEGRATOR_AP=y
+CONFIG_INTEGRATOR_IMPD1=y
+CONFIG_INTEGRATOR_CM720T=y
+CONFIG_INTEGRATOR_CM920T=y
+CONFIG_INTEGRATOR_CM922T_XA10=y
+CONFIG_ARCH_MXC=y
+CONFIG_MACH_SCB9328=y
+CONFIG_MACH_APF9328=y
+CONFIG_MACH_IMX1_DT=y
+CONFIG_ARCH_NSPIRE=y
+CONFIG_AEABI=y
+# CONFIG_ATAGS is not set
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_CPU_IDLE=y
+CONFIG_ARM_CPUIDLE=y
+CONFIG_ARM_CLPS711X_CPUIDLE=y
+# CONFIG_COREDUMP is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_JEDECPROBE=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_CFI_STAA=y
+CONFIG_MTD_PLATRAM=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_GPIO=y
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+CONFIG_SERIAL_CLPS711X=y
+CONFIG_SERIAL_CLPS711X_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_AT91=y
+CONFIG_I2C_GPIO=y
+CONFIG_I2C_IMX=y
+CONFIG_SPI=y
+CONFIG_SPI_ATMEL=y
+CONFIG_SPI_CLPS711X=y
+CONFIG_SPI_GPIO=y
+CONFIG_SPI_IMX=y
+CONFIG_PINCTRL_AT91PIO4=y
+CONFIG_GPIO_74XX_MMIO=y
+CONFIG_GPIO_CLPS711X=y
+CONFIG_GPIO_GENERIC_PLATFORM=y
+CONFIG_GPIO_SYSCON=y
+CONFIG_W1=y
+CONFIG_W1_MASTER_MXC=y
+CONFIG_W1_MASTER_GPIO=y
+CONFIG_POWER_RESET_AT91_POWEROFF=y
+CONFIG_POWER_RESET_AT91_RESET=y
+CONFIG_POWER_RESET_AT91_SAMA5D2_SHDWC=y
+CONFIG_POWER_RESET_GPIO=y
+CONFIG_POWER_RESET_GPIO_RESTART=y
+CONFIG_POWER_RESET_SYSCON=y
+CONFIG_POWER_RESET_SYSCON_POWEROFF=y
+# CONFIG_HWMON is not set
+CONFIG_WATCHDOG=y
+CONFIG_GPIO_WATCHDOG=y
+CONFIG_AT91RM9200_WATCHDOG=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_REGULATOR_GPIO=y
+CONFIG_FB=y
+CONFIG_FB_CLPS711X=y
+CONFIG_FB_IMX=y
+CONFIG_LCD_PLATFORM=y
+CONFIG_BACKLIGHT_PWM=y
+# CONFIG_USB_SUPPORT is not set
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_PWM=y
+CONFIG_PWM_ATMEL=y
+CONFIG_PWM_CLPS711X=y
+CONFIG_PWM_IMX=y
+CONFIG_EXT2_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_CRAMFS=y
+CONFIG_MINIX_FS=y
+# CONFIG_FTRACE is not set
+CONFIG_DEBUG_USER=y
+CONFIG_CRC_CCITT=y
diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig
index 4f82656f7ea2..2658b80fa263 100644
--- a/arch/arm/configs/multi_v5_defconfig
+++ b/arch/arm/configs/multi_v5_defconfig
@@ -13,6 +13,8 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_ARCH_MULTI_V7 is not set
 CONFIG_ARCH_MVEBU=y
 CONFIG_MACH_KIRKWOOD=y
+CONFIG_ARCH_AT91=y
+CONFIG_SOC_AT91SAM9=y
 CONFIG_ARCH_ASPEED=y
 CONFIG_MACH_ASPEED_G4=y
 CONFIG_ARCH_MXC=y
@@ -89,8 +91,12 @@ CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_STAA=y
 CONFIG_MTD_PHYSMAP=y
 CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_ATMEL=y
 CONFIG_MTD_NAND_ORION=y
+CONFIG_MTD_UBI=y
 CONFIG_BLK_DEV_LOOP=y
+CONFIG_ATMEL_TCLIB=y
+CONFIG_ATMEL_SSC=m
 CONFIG_EEPROM_AT24=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
@@ -102,15 +108,22 @@ CONFIG_SATA_MV=y
 CONFIG_NETDEVICES=y
 CONFIG_NET_DSA_MV88E6060=y
 CONFIG_NET_DSA_MV88E6XXX=y
+CONFIG_MACB=y
+CONFIG_DM9000=y
 CONFIG_MV643XX_ETH=y
 CONFIG_R8169=y
 CONFIG_MARVELL_PHY=y
+CONFIG_DAVICOM_PHY=y
+CONFIG_MICREL_PHY=y
 CONFIG_LIBERTAS=y
 CONFIG_LIBERTAS_SDIO=y
 CONFIG_MWL8K=m
 CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_QT1070=m
 CONFIG_KEYBOARD_GPIO=y
 # CONFIG_INPUT_MOUSE is not set
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_ADS7846=m
 CONFIG_LEGACY_PTY_COUNT=16
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
@@ -120,16 +133,21 @@ CONFIG_SERIAL_8250_RUNTIME_UARTS=6
 CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SERIAL_ATMEL=y
+CONFIG_SERIAL_ATMEL_CONSOLE=y
+CONFIG_SERIAL_ATMEL_TTYAT=y
 CONFIG_SERIAL_IMX=y
 CONFIG_SERIAL_IMX_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
+CONFIG_HW_RANDOM=y
 CONFIG_I2C=y
 # CONFIG_I2C_COMPAT is not set
 CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_AT91=y
 CONFIG_I2C_IMX=y
 CONFIG_I2C_MV64XXX=y
 CONFIG_I2C_NOMADIK=y
 CONFIG_SPI=y
+CONFIG_SPI_ATMEL=y
 CONFIG_SPI_IMX=y
 CONFIG_SPI_ORION=y
 CONFIG_GPIO_SYSFS=y
@@ -143,18 +161,36 @@ CONFIG_SENSORS_LM75=y
 CONFIG_SENSORS_LM85=y
 CONFIG_THERMAL=y
 CONFIG_KIRKWOOD_THERMAL=y
+CONFIG_AT91SAM9X_WATCHDOG=y
 CONFIG_ORION_WATCHDOG=y
 CONFIG_IMX2_WDT=y
+CONFIG_MFD_ATMEL_HLCDC=y
 # CONFIG_ABX500_CORE is not set
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_MEDIA_CAMERA_SUPPORT=y
+CONFIG_V4L_PLATFORM_DRIVERS=y
+CONFIG_SOC_CAMERA=y
+CONFIG_VIDEO_ATMEL_ISI=m
+CONFIG_SOC_CAMERA_OV2640=m
+CONFIG_DRM=y
+CONFIG_DRM_ATMEL_HLCDC=m
+CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_FB=y
 CONFIG_FB_IMX=y
+CONFIG_FB_ATMEL=y
+CONFIG_BACKLIGHT_ATMEL_LCDC=y
 CONFIG_SOUND=y
 CONFIG_SND=y
 CONFIG_SND_SOC=y
+CONFIG_SND_ATMEL_SOC=y
+CONFIG_SND_AT91_SOC_SAM9G20_WM8731=m
+CONFIG_SND_ATMEL_SOC_WM8904=m
+CONFIG_SND_AT91_SOC_SAM9X5_WM8731=m
 CONFIG_SND_KIRKWOOD_SOC=y
 CONFIG_SND_SOC_ALC5623=y
+CONFIG_SND_SOC_WM8731=y
 CONFIG_SND_SIMPLE_CARD=y
 CONFIG_HID_DRAGONRISE=y
 CONFIG_HID_GYRATION=y
@@ -173,6 +209,7 @@ CONFIG_HID_ZEROPLUS=y
 CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_PRINTER=m
 CONFIG_USB_STORAGE=y
 CONFIG_USB_STORAGE_DATAFAB=y
@@ -182,8 +219,12 @@ CONFIG_USB_STORAGE_SDDR55=y
 CONFIG_USB_STORAGE_JUMPSHOT=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_AT91=m
+CONFIG_USB_ATMEL_USBA=m
 CONFIG_MMC=y
 CONFIG_SDIO_UART=y
+CONFIG_MMC_ATMELMCI=y
 CONFIG_MMC_MVSDIO=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
@@ -196,11 +237,21 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_RS5C372=y
 CONFIG_RTC_DRV_PCF8563=y
 CONFIG_RTC_DRV_S35390A=y
+CONFIG_RTC_DRV_RV3029C2=m
+CONFIG_RTC_DRV_AT91RM9200=m
+CONFIG_RTC_DRV_AT91SAM9=m
 CONFIG_RTC_DRV_MV=y
 CONFIG_DMADEVICES=y
+CONFIG_AT_HDMAC=y
 CONFIG_MV_XOR=y
 CONFIG_STAGING=y
 CONFIG_FB_XGI=y
+CONFIG_IIO=m
+CONFIG_AT91_ADC=m
+CONFIG_PWM=y
+CONFIG_PWM_ATMEL=m
+CONFIG_PWM_ATMEL_HLCDC_PWM=m
+CONFIG_PWM_ATMEL_TCB=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 CONFIG_ISO9660_FS=m
@@ -210,6 +261,7 @@ CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
+CONFIG_UBIFS_FS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 8a5fff1b7f6f..2c8665cd9dc5 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -36,6 +36,7 @@ CONFIG_ARCH_BCM_21664=y
 CONFIG_ARCH_BCM_281XX=y
 CONFIG_ARCH_BCM_5301X=y
 CONFIG_ARCH_BCM2835=y
+CONFIG_ARCH_BCM_63XX=y
 CONFIG_ARCH_BRCMSTB=y
 CONFIG_ARCH_BERLIN=y
 CONFIG_MACH_BERLIN_BG2=y
@@ -90,6 +91,7 @@ CONFIG_ARCH_R8A7778=y
 CONFIG_ARCH_R8A7779=y
 CONFIG_ARCH_R8A7790=y
 CONFIG_ARCH_R8A7791=y
+CONFIG_ARCH_R8A7792=y
 CONFIG_ARCH_R8A7793=y
 CONFIG_ARCH_R8A7794=y
 CONFIG_ARCH_SH73A0=y
@@ -157,6 +159,8 @@ CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
 CONFIG_IPV6_TUNNEL=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NET_DSA=m
+CONFIG_NET_SWITCHDEV=y
 CONFIG_CAN=y
 CONFIG_CAN_RAW=y
 CONFIG_CAN_BCM=y
@@ -165,6 +169,7 @@ CONFIG_CAN_AT91=m
 CONFIG_CAN_RCAR=m
 CONFIG_CAN_XILINXCAN=y
 CONFIG_CAN_MCP251X=y
+CONFIG_NET_DSA_BCM_SF2=m
 CONFIG_CAN_SUN4I=y
 CONFIG_BT=m
 CONFIG_BT_MRVL=m
@@ -213,6 +218,7 @@ CONFIG_SCSI_MULTI_LUN=y
 CONFIG_ATA=y
 CONFIG_SATA_AHCI=y
 CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_AHCI_BRCM=y
 CONFIG_AHCI_ST=y
 CONFIG_AHCI_SUNXI=y
 CONFIG_AHCI_TEGRA=y
@@ -224,6 +230,8 @@ CONFIG_VIRTIO_NET=y
 CONFIG_HIX5HD2_GMAC=y
 CONFIG_SUN4I_EMAC=y
 CONFIG_MACB=y
+CONFIG_BCMGENET=m
+CONFIG_SYSTEMPORT=m
 CONFIG_NET_CALXEDA_XGMAC=y
 CONFIG_GIANFAR=y
 CONFIG_IGB=y
@@ -270,6 +278,7 @@ CONFIG_MOUSE_CYAPA=m
 CONFIG_MOUSE_ELAN_I2C=y
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_TOUCHSCREEN_ATMEL_MXT=y
+CONFIG_TOUCHSCREEN_MMS114=m
 CONFIG_TOUCHSCREEN_ST1232=m
 CONFIG_TOUCHSCREEN_STMPE=y
 CONFIG_TOUCHSCREEN_SUN4I=y
@@ -292,6 +301,8 @@ CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_SERIAL_ATMEL=y
 CONFIG_SERIAL_ATMEL_CONSOLE=y
 CONFIG_SERIAL_ATMEL_TTYAT=y
+CONFIG_SERIAL_BCM63XX=y
+CONFIG_SERIAL_BCM63XX_CONSOLE=y
 CONFIG_SERIAL_MESON=y
 CONFIG_SERIAL_MESON_CONSOLE=y
 CONFIG_SERIAL_SAMSUNG=y
@@ -358,6 +369,7 @@ CONFIG_SPI_BCM2835=y
 CONFIG_SPI_BCM2835AUX=y
 CONFIG_SPI_CADENCE=y
 CONFIG_SPI_DAVINCI=y
+CONFIG_SPI_GPIO=m
 CONFIG_SPI_FSL_DSPI=m
 CONFIG_SPI_OMAP24XX=y
 CONFIG_SPI_ORION=y
@@ -404,12 +416,14 @@ CONFIG_GPIO_PALMAS=y
 CONFIG_GPIO_SYSCON=y
 CONFIG_GPIO_TPS6586X=y
 CONFIG_GPIO_TPS65910=y
+CONFIG_BATTERY_ACT8945A=y
 CONFIG_BATTERY_SBS=y
 CONFIG_BATTERY_MAX17040=m
 CONFIG_BATTERY_MAX17042=m
 CONFIG_CHARGER_MAX14577=m
 CONFIG_CHARGER_MAX77693=m
 CONFIG_CHARGER_MAX8997=m
+CONFIG_CHARGER_MAX8998=m
 CONFIG_CHARGER_TPS65090=y
 CONFIG_AXP20X_POWER=m
 CONFIG_POWER_RESET_AS3722=y
@@ -449,6 +463,9 @@ CONFIG_MESON_WATCHDOG=y
 CONFIG_DW_WATCHDOG=y
 CONFIG_DIGICOLOR_WATCHDOG=y
 CONFIG_BCM2835_WDT=y
+CONFIG_BCM7038_WDT=m
+CONFIG_BCM_KONA_WDT=y
+CONFIG_MFD_ACT8945A=y
 CONFIG_MFD_AS3711=y
 CONFIG_MFD_AS3722=y
 CONFIG_MFD_ATMEL_FLEXCOM=y
@@ -463,9 +480,10 @@ CONFIG_MFD_CROS_EC_SPI=m
 CONFIG_MFD_DA9063=m
 CONFIG_MFD_MAX14577=y
 CONFIG_MFD_MAX77686=y
-CONFIG_MFD_MAX77693=y
+CONFIG_MFD_MAX77693=m
 CONFIG_MFD_MAX8907=y
 CONFIG_MFD_MAX8997=y
+CONFIG_MFD_MAX8998=y
 CONFIG_MFD_RK808=y
 CONFIG_MFD_PM8921_CORE=y
 CONFIG_MFD_QCOM_RPM=y
@@ -478,6 +496,7 @@ CONFIG_MFD_TPS65217=y
 CONFIG_MFD_TPS65218=y
 CONFIG_MFD_TPS6586X=y
 CONFIG_MFD_TPS65910=y
+CONFIG_REGULATOR_ACT8945A=y
 CONFIG_REGULATOR_AB8500=y
 CONFIG_REGULATOR_ACT8865=y
 CONFIG_REGULATOR_AS3711=y
@@ -495,6 +514,7 @@ CONFIG_REGULATOR_MAX14577=m
 CONFIG_REGULATOR_MAX8907=y
 CONFIG_REGULATOR_MAX8973=y
 CONFIG_REGULATOR_MAX8997=m
+CONFIG_REGULATOR_MAX8998=m
 CONFIG_REGULATOR_MAX77686=y
 CONFIG_REGULATOR_MAX77693=m
 CONFIG_REGULATOR_MAX77802=m
@@ -515,6 +535,7 @@ CONFIG_REGULATOR_TPS6586X=y
 CONFIG_REGULATOR_TPS65910=y
 CONFIG_REGULATOR_TWL4030=y
 CONFIG_REGULATOR_VEXPRESS=y
+CONFIG_REGULATOR_WM8994=m
 CONFIG_MEDIA_SUPPORT=m
 CONFIG_MEDIA_CAMERA_SUPPORT=y
 CONFIG_MEDIA_CONTROLLER=y
@@ -527,9 +548,18 @@ CONFIG_SOC_CAMERA=m
 CONFIG_SOC_CAMERA_PLATFORM=m
 CONFIG_VIDEO_RCAR_VIN=m
 CONFIG_VIDEO_ATMEL_ISI=m
+CONFIG_VIDEO_SAMSUNG_EXYNOS4_IS=m
+CONFIG_VIDEO_S5P_FIMC=m
+CONFIG_VIDEO_S5P_MIPI_CSIS=m
+CONFIG_VIDEO_EXYNOS_FIMC_LITE=m
+CONFIG_VIDEO_EXYNOS4_FIMC_IS=m
 CONFIG_V4L_MEM2MEM_DRIVERS=y
+CONFIG_VIDEO_SAMSUNG_S5P_JPEG=m
+CONFIG_VIDEO_SAMSUNG_S5P_MFC=m
+CONFIG_VIDEO_STI_BDISP=m
 CONFIG_VIDEO_RENESAS_JPU=m
 CONFIG_VIDEO_RENESAS_VSP1=m
+CONFIG_V4L_TEST_DRIVERS=y
 # CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set
 CONFIG_VIDEO_ADV7180=m
 CONFIG_VIDEO_ML86V7667=m
@@ -541,8 +571,10 @@ CONFIG_DRM_NXP_PTN3460=m
 CONFIG_DRM_PARADE_PS8622=m
 CONFIG_DRM_NOUVEAU=m
 CONFIG_DRM_EXYNOS=m
-CONFIG_DRM_EXYNOS_DSI=y
 CONFIG_DRM_EXYNOS_FIMD=y
+CONFIG_DRM_EXYNOS_MIXER=y
+CONFIG_DRM_EXYNOS_DPI=y
+CONFIG_DRM_EXYNOS_DSI=y
 CONFIG_DRM_EXYNOS_HDMI=y
 CONFIG_DRM_ROCKCHIP=m
 CONFIG_ROCKCHIP_ANALOGIX_DP=m
@@ -553,9 +585,12 @@ CONFIG_DRM_ATMEL_HLCDC=m
 CONFIG_DRM_RCAR_DU=m
 CONFIG_DRM_RCAR_HDMI=y
 CONFIG_DRM_RCAR_LVDS=y
+CONFIG_DRM_SUN4I=m
 CONFIG_DRM_TEGRA=y
+CONFIG_DRM_PANEL_SAMSUNG_LD9040=m
 CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0=m
 CONFIG_DRM_PANEL_SIMPLE=y
+CONFIG_DRM_STI=m
 CONFIG_DRM_VC4=y
 CONFIG_FB_ARMCLCD=y
 CONFIG_FB_WM8505=y
@@ -588,13 +623,14 @@ CONFIG_SND_SOC_ROCKCHIP=m
 CONFIG_SND_SOC_ROCKCHIP_SPDIF=m
 CONFIG_SND_SOC_ROCKCHIP_MAX98090=m
 CONFIG_SND_SOC_ROCKCHIP_RT5645=m
+CONFIG_SND_SOC_SAMSUNG=m
+CONFIG_SND_SOC_SAMSUNG_SMDK_WM8994=m
+CONFIG_SND_SOC_SMDK_WM8994_PCM=m
+CONFIG_SND_SOC_SNOW=m
 CONFIG_SND_SOC_SH4_FSI=m
 CONFIG_SND_SOC_RCAR=m
 CONFIG_SND_SOC_RSRC_CARD=m
 CONFIG_SND_SUN4I_CODEC=m
-CONFIG_SND_SOC_SAMSUNG=m
-CONFIG_SND_SOC_SNOW=m
-CONFIG_SND_SOC_ODROIDX2=m
 CONFIG_SND_SOC_TEGRA=m
 CONFIG_SND_SOC_TEGRA_RT5640=m
 CONFIG_SND_SOC_TEGRA_WM8753=m
@@ -700,6 +736,7 @@ CONFIG_RTC_DRV_AS3722=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_HYM8563=m
 CONFIG_RTC_DRV_MAX8907=y
+CONFIG_RTC_DRV_MAX8998=m
 CONFIG_RTC_DRV_MAX8997=m
 CONFIG_RTC_DRV_MAX77686=y
 CONFIG_RTC_DRV_RK808=m
@@ -791,6 +828,7 @@ CONFIG_BERLIN2_ADC=m
 CONFIG_EXYNOS_ADC=m
 CONFIG_VF610_ADC=m
 CONFIG_XILINX_XADC=y
+CONFIG_CM36651=m
 CONFIG_AK8975=y
 CONFIG_RASPBERRYPI_POWER=y
 CONFIG_PWM=y
@@ -807,6 +845,7 @@ CONFIG_PWM_VT8500=y
 CONFIG_PHY_HIX5HD2_SATA=y
 CONFIG_PWM_STI=y
 CONFIG_PWM_BCM2835=y
+CONFIG_PWM_BRCMSTB=m
 CONFIG_OMAP_USB2=y
 CONFIG_TI_PIPE3=y
 CONFIG_PHY_BERLIN_USB=y
@@ -823,6 +862,7 @@ CONFIG_PHY_SUN4I_USB=y
 CONFIG_PHY_SUN9I_USB=y
 CONFIG_PHY_SAMSUNG_USB2=m
 CONFIG_PHY_TEGRA_XUSB=y
+CONFIG_PHY_BRCM_SATA=y
 CONFIG_NVMEM=y
 CONFIG_NVMEM_SUNXI_SID=y
 CONFIG_BCM2835_MBOX=y
@@ -855,6 +895,7 @@ CONFIG_KEYSTONE_IRQ=y
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_ST=y
 CONFIG_CRYPTO_DEV_MARVELL_CESA=m
+CONFIG_CRYPTO_DEV_S5P=m
 CONFIG_CRYPTO_DEV_SUN4I_SS=m
 CONFIG_CRYPTO_DEV_ROCKCHIP=m
 CONFIG_ARM_CRYPTO=y
@@ -871,6 +912,7 @@ CONFIG_CRYPTO_GHASH_ARM_CE=m
 CONFIG_CRYPTO_DEV_ATMEL_AES=m
 CONFIG_CRYPTO_DEV_ATMEL_TDES=m
 CONFIG_CRYPTO_DEV_ATMEL_SHA=m
+CONFIG_VIDEO_VIVID=m
 CONFIG_VIRTIO=y
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_PCI_LEGACY=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index ac717cccd2b5..487c6c3b13fd 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -355,11 +355,13 @@ CONFIG_USB_OHCI_HCD=m
 CONFIG_USB_WDM=m
 CONFIG_USB_STORAGE=m
 CONFIG_USB_MUSB_HDRC=m
+CONFIG_USB_MUSB_TUSB6010=m
 CONFIG_USB_MUSB_OMAP2PLUS=m
 CONFIG_USB_MUSB_AM35X=m
 CONFIG_USB_MUSB_DSPS=m
 CONFIG_USB_INVENTRA_DMA=y
 CONFIG_USB_TI_CPPI41_DMA=y
+CONFIG_USB_TUSB_OMAP_DMA=y
 CONFIG_USB_DWC3=m
 CONFIG_USB_SERIAL=m
 CONFIG_USB_SERIAL_GENERIC=y
@@ -367,7 +369,8 @@ CONFIG_USB_SERIAL_SIMPLE=m
 CONFIG_USB_SERIAL_FTDI_SIO=m
 CONFIG_USB_SERIAL_PL2303=m
 CONFIG_USB_TEST=m
-CONFIG_AM335X_PHY_USB=y
+CONFIG_NOP_USB_XCEIV=m
+CONFIG_AM335X_PHY_USB=m
 CONFIG_TWL6030_USB=m
 CONFIG_USB_GADGET=m
 CONFIG_USB_GADGET_DEBUG=y
diff --git a/arch/arm/configs/qcom_defconfig b/arch/arm/configs/qcom_defconfig
index 7bff7bf24a85..c2dff4fd5fc4 100644
--- a/arch/arm/configs/qcom_defconfig
+++ b/arch/arm/configs/qcom_defconfig
@@ -23,6 +23,7 @@ CONFIG_ARCH_QCOM=y
 CONFIG_ARCH_MSM8X60=y
 CONFIG_ARCH_MSM8960=y
 CONFIG_ARCH_MSM8974=y
+CONFIG_ARCH_MDM9615=y
 CONFIG_SMP=y
 CONFIG_HAVE_ARM_ARCH_TIMER=y
 CONFIG_PREEMPT=y
@@ -94,6 +95,7 @@ CONFIG_SERIO_LIBPS2=y
 CONFIG_SERIAL_MSM=y
 CONFIG_SERIAL_MSM_CONSOLE=y
 CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_MSM=y
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_QUP=y
@@ -103,7 +105,9 @@ CONFIG_SPMI=y
 CONFIG_PINCTRL_APQ8064=y
 CONFIG_PINCTRL_APQ8084=y
 CONFIG_PINCTRL_IPQ8064=y
+CONFIG_PINCTRL_MSM8660=y
 CONFIG_PINCTRL_MSM8960=y
+CONFIG_PINCTRL_MDM9615=y
 CONFIG_PINCTRL_MSM8X74=y
 CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
 CONFIG_PINCTRL_QCOM_SSBI_PMIC=y
@@ -114,6 +118,7 @@ CONFIG_CHARGER_QCOM_SMBB=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_MSM=y
 CONFIG_THERMAL=y
+CONFIG_MFD_PM8XXX=y
 CONFIG_MFD_PM8921_CORE=y
 CONFIG_MFD_QCOM_RPM=y
 CONFIG_MFD_SPMI_PMIC=y
@@ -143,6 +148,7 @@ CONFIG_USB_GADGET_VBUS_DRAW=500
 CONFIG_MMC=y
 CONFIG_MMC_BLOCK_MINORS=32
 CONFIG_MMC_ARMMMCI=y
+CONFIG_MMC_QCOM_DML=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_MSM=y
@@ -156,6 +162,8 @@ CONFIG_APQ_MMCC_8084=y
 CONFIG_IPQ_LCC_806X=y
 CONFIG_MSM_GCC_8660=y
 CONFIG_MSM_LCC_8960=y
+CONFIG_MSM_GCC_9615=y
+CONFIG_MSM_LCC_9615=y
 CONFIG_MSM_MMCC_8960=y
 CONFIG_MSM_MMCC_8974=y
 CONFIG_HWSPINLOCK_QCOM=y
diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig
index 9cb1a85bb166..aca8625b6fc9 100644
--- a/arch/arm/configs/sama5_defconfig
+++ b/arch/arm/configs/sama5_defconfig
@@ -129,16 +129,19 @@ CONFIG_SPI_ATMEL=y
 CONFIG_SPI_GPIO=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_POWER_SUPPLY=y
+CONFIG_BATTERY_ACT8945A=y
 CONFIG_POWER_RESET=y
 # CONFIG_HWMON is not set
 CONFIG_WATCHDOG=y
 CONFIG_AT91SAM9X_WATCHDOG=y
 CONFIG_SAMA5D4_WATCHDOG=y
+CONFIG_MFD_ACT8945A=y
 CONFIG_MFD_ATMEL_FLEXCOM=y
 CONFIG_MFD_ATMEL_HLCDC=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_ACT8865=y
+CONFIG_REGULATOR_ACT8945A=y
 CONFIG_MEDIA_SUPPORT=y
 CONFIG_MEDIA_CAMERA_SUPPORT=y
 CONFIG_V4L_PLATFORM_DRIVERS=y
diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig
index f2d635566a13..baa07a46a88b 100644
--- a/arch/arm/configs/shmobile_defconfig
+++ b/arch/arm/configs/shmobile_defconfig
@@ -17,6 +17,7 @@ CONFIG_ARCH_R8A7778=y
 CONFIG_ARCH_R8A7779=y
 CONFIG_ARCH_R8A7790=y
 CONFIG_ARCH_R8A7791=y
+CONFIG_ARCH_R8A7792=y
 CONFIG_ARCH_R8A7793=y
 CONFIG_ARCH_R8A7794=y
 CONFIG_ARCH_SH73A0=y
diff --git a/arch/arm/configs/socfpga_defconfig b/arch/arm/configs/socfpga_defconfig
index 753f1a5defc7..9f84be5b3ac5 100644
--- a/arch/arm/configs/socfpga_defconfig
+++ b/arch/arm/configs/socfpga_defconfig
@@ -1,5 +1,4 @@
 CONFIG_SYSVIPC=y
-CONFIG_FHANDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
@@ -19,6 +18,10 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_SOCFPGA=y
 CONFIG_ARM_THUMBEE=y
+CONFIG_PCI=y
+CONFIG_PCI_MSI=y
+CONFIG_PCIE_ALTERA=y
+CONFIG_PCIE_ALTERA_MSI=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=2
 CONFIG_AEABI=y
@@ -50,15 +53,21 @@ CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=2
 CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_BLK_DEV_NVME=m
 CONFIG_SRAM=y
 CONFIG_SCSI=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
+CONFIG_E1000E=m
+CONFIG_IGB=m
+CONFIG_IXGBE=m
 CONFIG_STMMAC_ETH=y
 CONFIG_MICREL_PHY=y
 CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_STMPE=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIO_AMBAKMI=y
 CONFIG_LEGACY_PTY_COUNT=16
@@ -78,14 +87,19 @@ CONFIG_SENSORS_LTC2978=y
 CONFIG_SENSORS_LTC2978_REGULATOR=y
 CONFIG_WATCHDOG=y
 CONFIG_DW_WATCHDOG=y
+CONFIG_MFD_STMPE=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_USB=y
+CONFIG_USB_STORAGE=y
 CONFIG_USB_DWC2=y
 CONFIG_NOP_USB_XCEIV=y
 CONFIG_USB_GADGET=y
 CONFIG_MMC=y
 CONFIG_MMC_DW=y
+CONFIG_DMADEVICES=y
+CONFIG_PL330_DMA=y
+CONFIG_DMATEST=m
 CONFIG_FPGA=y
 CONFIG_FPGA_MGR_SOCFPGA=y
 CONFIG_EXT2_FS=y
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 81a1b92fd4e6..714da336ec86 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -97,6 +97,8 @@ CONFIG_MEDIA_SUPPORT=y
 CONFIG_MEDIA_RC_SUPPORT=y
 CONFIG_RC_DEVICES=y
 CONFIG_IR_SUNXI=y
+CONFIG_DRM=y
+CONFIG_DRM_SUN4I=y
 CONFIG_FB=y
 CONFIG_FB_SIMPLE=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
diff --git a/arch/arm/include/asm/kexec.h b/arch/arm/include/asm/kexec.h
index c2b9b4bdec00..1869af6bac5c 100644
--- a/arch/arm/include/asm/kexec.h
+++ b/arch/arm/include/asm/kexec.h
@@ -53,6 +53,30 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 /* Function pointer to optional machine-specific reinitialization */
 extern void (*kexec_reinit)(void);
 
+static inline unsigned long phys_to_boot_phys(phys_addr_t phys)
+{
+	return phys_to_idmap(phys);
+}
+#define phys_to_boot_phys phys_to_boot_phys
+
+static inline phys_addr_t boot_phys_to_phys(unsigned long entry)
+{
+	return idmap_to_phys(entry);
+}
+#define boot_phys_to_phys boot_phys_to_phys
+
+static inline unsigned long page_to_boot_pfn(struct page *page)
+{
+	return page_to_pfn(page) + (arch_phys_to_idmap_offset >> PAGE_SHIFT);
+}
+#define page_to_boot_pfn page_to_boot_pfn
+
+static inline struct page *boot_pfn_to_page(unsigned long boot_pfn)
+{
+	return pfn_to_page(boot_pfn - (arch_phys_to_idmap_offset >> PAGE_SHIFT));
+}
+#define boot_pfn_to_page boot_pfn_to_page
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* CONFIG_KEXEC */
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 3d5a5cd071bd..58faff5f1eb2 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -66,6 +66,8 @@ extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern void __init_stage2_translation(void);
+
+extern void __kvm_hyp_reset(unsigned long);
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 96387d477e91..de338d93d11b 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -241,8 +241,7 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		int exception_index);
 
-static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
-				       phys_addr_t pgd_ptr,
+static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,
 				       unsigned long vector_ptr)
 {
@@ -251,18 +250,13 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 	 * code. The init code doesn't need to preserve these
 	 * registers as r0-r3 are already callee saved according to
 	 * the AAPCS.
-	 * Note that we slightly misuse the prototype by casing the
+	 * Note that we slightly misuse the prototype by casting the
 	 * stack pointer to a void *.
-	 *
-	 * We don't have enough registers to perform the full init in
-	 * one go.  Install the boot PGD first, and then install the
-	 * runtime PGD, stack pointer and vectors. The PGDs are always
-	 * passed as the third argument, in order to be passed into
-	 * r2-r3 to the init code (yes, this is compliant with the
-	 * PCS!).
-	 */
 
-	kvm_call_hyp(NULL, 0, boot_pgd_ptr);
+	 * The PGDs are always passed as the third argument, in order
+	 * to be passed into r2-r3 to the init code (yes, this is
+	 * compliant with the PCS!).
+	 */
 
 	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
 }
@@ -272,16 +266,13 @@ static inline void __cpu_init_stage2(void)
 	kvm_call_hyp(__init_stage2_translation);
 }
 
-static inline void __cpu_reset_hyp_mode(phys_addr_t boot_pgd_ptr,
+static inline void __cpu_reset_hyp_mode(unsigned long vector_ptr,
 					phys_addr_t phys_idmap_start)
 {
-	/*
-	 * TODO
-	 * kvm_call_reset(boot_pgd_ptr, phys_idmap_start);
-	 */
+	kvm_call_hyp((void *)virt_to_idmap(__kvm_hyp_reset), vector_ptr);
 }
 
-static inline int kvm_arch_dev_ioctl_check_extension(long ext)
+static inline int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	return 0;
 }
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
index f0e860761380..6eaff28f2ff3 100644
--- a/arch/arm/include/asm/kvm_hyp.h
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -25,9 +25,6 @@
 
 #define __hyp_text __section(.hyp.text) notrace
 
-#define kern_hyp_va(v) (v)
-#define hyp_kern_va(v) (v)
-
 #define __ACCESS_CP15(CRn, Op1, CRm, Op2)	\
 	"mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32
 #define __ACCESS_CP15_64(Op1, CRm)		\
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index f9a65061130b..3bb803d6814b 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -26,16 +26,7 @@
  * We directly use the kernel VA for the HYP, as we can directly share
  * the mapping (HTTBR "covers" TTBR1).
  */
-#define HYP_PAGE_OFFSET_MASK	UL(~0)
-#define HYP_PAGE_OFFSET		PAGE_OFFSET
-#define KERN_TO_HYP(kva)	(kva)
-
-/*
- * Our virtual mapping for the boot-time MMU-enable code. Must be
- * shared across all the page-tables. Conveniently, we use the vectors
- * page, where no kernel data will ever be shared with HYP.
- */
-#define TRAMPOLINE_VA		UL(CONFIG_VECTORS_BASE)
+#define kern_hyp_va(kva)	(kva)
 
 /*
  * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
@@ -49,9 +40,8 @@
 #include <asm/pgalloc.h>
 #include <asm/stage2_pgtable.h>
 
-int create_hyp_mappings(void *from, void *to);
+int create_hyp_mappings(void *from, void *to, pgprot_t prot);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
-void free_boot_hyp_pgd(void);
 void free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
@@ -65,7 +55,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
-phys_addr_t kvm_mmu_get_boot_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
 phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h
index 0070e8520cd4..2d88af5be45f 100644
--- a/arch/arm/include/asm/mach/pci.h
+++ b/arch/arm/include/asm/mach/pci.h
@@ -22,6 +22,7 @@ struct hw_pci {
 	struct msi_controller *msi_ctrl;
 	struct pci_ops	*ops;
 	int		nr_controllers;
+	unsigned int	io_optional:1;
 	void		**private_data;
 	int		(*setup)(int nr, struct pci_sys_data *);
 	struct pci_bus *(*scan)(int nr, struct pci_sys_data *);
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index d62204060cbe..a8d656d9aec7 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -97,7 +97,9 @@ extern pgprot_t		pgprot_s2_device;
 #define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY)
 #define PAGE_KERNEL		_MOD_PROT(pgprot_kernel, L_PTE_XN)
 #define PAGE_KERNEL_EXEC	pgprot_kernel
-#define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP)
+#define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_XN)
+#define PAGE_HYP_EXEC		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY)
+#define PAGE_HYP_RO		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY | L_PTE_XN)
 #define PAGE_HYP_DEVICE		_MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
 #define PAGE_S2			_MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
 #define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY)
diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h
index d4ceaf5f299b..a2e75b84e2ae 100644
--- a/arch/arm/include/asm/virt.h
+++ b/arch/arm/include/asm/virt.h
@@ -80,6 +80,10 @@ static inline bool is_kernel_in_hyp_mode(void)
 	return false;
 }
 
+/* The section containing the hypervisor idmap text */
+extern char __hyp_idmap_text_start[];
+extern char __hyp_idmap_text_end[];
+
 /* The section containing the hypervisor text */
 extern char __hyp_text_start[];
 extern char __hyp_text_end[];
diff --git a/arch/arm/include/debug/at91.S b/arch/arm/include/debug/at91.S
index d4ae3b8e2426..0098401e5aeb 100644
--- a/arch/arm/include/debug/at91.S
+++ b/arch/arm/include/debug/at91.S
@@ -9,14 +9,6 @@
  *
 */
 
-#ifdef CONFIG_MMU
-#define AT91_IO_P2V(x) ((x) - 0x01000000)
-#else
-#define AT91_IO_P2V(x) (x)
-#endif
-
-#define AT91_DEBUG_UART_VIRT AT91_IO_P2V(CONFIG_DEBUG_UART_PHYS)
-
 #define AT91_DBGU_SR		(0x14)	/* Status Register */
 #define AT91_DBGU_THR		(0x1c)	/* Transmitter Holding Register */
 #define AT91_DBGU_TXRDY		(1 << 1)	/* Transmitter Ready */
@@ -24,7 +16,7 @@
 
 	.macro	addruart, rp, rv, tmp
 	ldr	\rp, =CONFIG_DEBUG_UART_PHYS		@ System peripherals (phys address)
-	ldr	\rv, =AT91_DEBUG_UART_VIRT		@ System peripherals (virt address)
+	ldr	\rv, =CONFIG_DEBUG_UART_VIRT		@ System peripherals (virt address)
 	.endm
 
 	.macro	senduart,rd,rx
diff --git a/arch/arm/include/debug/clps711x.S b/arch/arm/include/debug/clps711x.S
index abe225436686..c17ac5c9e5f3 100644
--- a/arch/arm/include/debug/clps711x.S
+++ b/arch/arm/include/debug/clps711x.S
@@ -9,10 +9,10 @@
 
 #ifndef CONFIG_DEBUG_CLPS711X_UART2
 #define CLPS711X_UART_PADDR	(0x80000000 + 0x0000)
-#define CLPS711X_UART_VADDR	(0xfeff0000 + 0x0000)
+#define CLPS711X_UART_VADDR	(0xfeff4000 + 0x0000)
 #else
 #define CLPS711X_UART_PADDR	(0x80000000 + 0x1000)
-#define CLPS711X_UART_VADDR	(0xfeff0000 + 0x1000)
+#define CLPS711X_UART_VADDR	(0xfeff4000 + 0x1000)
 #endif
 
 #define SYSFLG		(0x0140)
diff --git a/arch/arm/include/debug/exynos.S b/arch/arm/include/debug/exynos.S
index b17fdb7fbd34..60bf3c23200d 100644
--- a/arch/arm/include/debug/exynos.S
+++ b/arch/arm/include/debug/exynos.S
@@ -24,7 +24,11 @@
 		mrc	p15, 0, \tmp, c0, c0, 0
 		and	\tmp, \tmp, #0xf0
 		teq	\tmp, #0xf0		@@ A15
-		ldreq	\rp, =EXYNOS5_PA_UART
+		beq	100f
+		mrc	p15, 0, \tmp, c0, c0, 5
+		and	\tmp, \tmp, #0xf00
+		teq	\tmp, #0x100		@@ A15 + A7 but boot to A7
+100:		ldreq	\rp, =EXYNOS5_PA_UART
 		movne	\rp, #EXYNOS4_PA_UART	@@ EXYNOS4
 		ldr	\rv, =S3C_VA_UART
 #if CONFIG_DEBUG_S3C_UART != 0
diff --git a/arch/arm/include/debug/samsung.S b/arch/arm/include/debug/samsung.S
index 8d8d922e5e44..f4eeed2a1981 100644
--- a/arch/arm/include/debug/samsung.S
+++ b/arch/arm/include/debug/samsung.S
@@ -15,11 +15,13 @@
 
 	.macro fifo_level_s5pv210 rd, rx
 		ldr	\rd, [\rx, # S3C2410_UFSTAT]
+ARM_BE8(rev \rd, \rd)
 		and	\rd, \rd, #S5PV210_UFSTAT_TXMASK
 	.endm
 
 	.macro  fifo_full_s5pv210 rd, rx
 		ldr	\rd, [\rx, # S3C2410_UFSTAT]
+ARM_BE8(rev \rd, \rd)
 		tst	\rd, #S5PV210_UFSTAT_TXFULL
 	.endm
 
@@ -28,6 +30,7 @@
 
 	.macro fifo_level_s3c2440 rd, rx
 		ldr	\rd, [\rx, # S3C2410_UFSTAT]
+ARM_BE8(rev \rd, \rd)
 		and	\rd, \rd, #S3C2440_UFSTAT_TXMASK
 	.endm
 
@@ -37,6 +40,7 @@
 
 	.macro  fifo_full_s3c2440 rd, rx
 		ldr	\rd, [\rx, # S3C2410_UFSTAT]
+ARM_BE8(rev \rd, \rd)
 		tst	\rd, #S3C2440_UFSTAT_TXFULL
 	.endm
 
@@ -50,6 +54,7 @@
 
 	.macro	busyuart, rd, rx
 		ldr	\rd, [\rx, # S3C2410_UFCON]
+ARM_BE8(rev \rd, \rd)
 		tst	\rd, #S3C2410_UFCON_FIFOMODE	@ fifo enabled?
 		beq	1001f				@
 		@ FIFO enabled...
@@ -61,6 +66,7 @@
 1001:
 		@ busy waiting for non fifo
 		ldr	\rd, [\rx, # S3C2410_UTRSTAT]
+ARM_BE8(rev \rd, \rd)
 		tst	\rd, #S3C2410_UTRSTAT_TXFE
 		beq	1001b
 
@@ -69,6 +75,7 @@
 
 	.macro	waituart,rd,rx
 		ldr	\rd, [\rx, # S3C2410_UFCON]
+ARM_BE8(rev \rd, \rd)
 		tst	\rd, #S3C2410_UFCON_FIFOMODE	@ fifo enabled?
 		beq	1001f				@
 		@ FIFO enabled...
@@ -80,6 +87,7 @@
 1001:
 		@ idle waiting for non fifo
 		ldr	\rd, [\rx, # S3C2410_UTRSTAT]
+ARM_BE8(rev \rd, \rd)
 		tst	\rd, #S3C2410_UTRSTAT_TXFE
 		beq	1001b
 
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 05e61a2eeabe..2f0e07735d1d 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -410,7 +410,8 @@ static int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return irq;
 }
 
-static int pcibios_init_resources(int busnr, struct pci_sys_data *sys)
+static int pcibios_init_resource(int busnr, struct pci_sys_data *sys,
+				 int io_optional)
 {
 	int ret;
 	struct resource_entry *window;
@@ -420,6 +421,14 @@ static int pcibios_init_resources(int busnr, struct pci_sys_data *sys)
 			 &iomem_resource, sys->mem_offset);
 	}
 
+	/*
+	 * If a platform says I/O port support is optional, we don't add
+	 * the default I/O space.  The platform is responsible for adding
+	 * any I/O space it needs.
+	 */
+	if (io_optional)
+		return 0;
+
 	resource_list_for_each_entry(window, &sys->resources)
 		if (resource_type(window->res) == IORESOURCE_IO)
 			return 0;
@@ -466,7 +475,7 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw,
 		if (ret > 0) {
 			struct pci_host_bridge *host_bridge;
 
-			ret = pcibios_init_resources(nr, sys);
+			ret = pcibios_init_resource(nr, sys, hw->io_optional);
 			if (ret)  {
 				kfree(sys);
 				break;
@@ -515,25 +524,23 @@ void pci_common_init_dev(struct device *parent, struct hw_pci *hw)
 	list_for_each_entry(sys, &head, node) {
 		struct pci_bus *bus = sys->bus;
 
-		if (!pci_has_flag(PCI_PROBE_ONLY)) {
+		/*
+		 * We insert PCI resources into the iomem_resource and
+		 * ioport_resource trees in either pci_bus_claim_resources()
+		 * or pci_bus_assign_resources().
+		 */
+		if (pci_has_flag(PCI_PROBE_ONLY)) {
+			pci_bus_claim_resources(bus);
+		} else {
 			struct pci_bus *child;
 
-			/*
-			 * Size the bridge windows.
-			 */
 			pci_bus_size_bridges(bus);
-
-			/*
-			 * Assign resources.
-			 */
 			pci_bus_assign_resources(bus);
 
 			list_for_each_entry(child, &bus->children, node)
 				pcie_bus_configure_settings(child);
 		}
-		/*
-		 * Tell drivers about devices found.
-		 */
+
 		pci_bus_add_devices(bus);
 	}
 }
@@ -590,18 +597,6 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 	return start;
 }
 
-/**
- * pcibios_enable_device - Enable I/O and memory.
- * @dev: PCI device to be enabled
- */
-int pcibios_enable_device(struct pci_dev *dev, int mask)
-{
-	if (pci_has_flag(PCI_PROBE_ONLY))
-		return 0;
-
-	return pci_enable_resources(dev, mask);
-}
-
 int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 59fd0e24c56b..b18c1ea56bed 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -57,7 +57,7 @@ int machine_kexec_prepare(struct kimage *image)
 	for (i = 0; i < image->nr_segments; i++) {
 		current_segment = &image->segment[i];
 
-		if (!memblock_is_region_memory(current_segment->mem,
+		if (!memblock_is_region_memory(idmap_to_phys(current_segment->mem),
 					       current_segment->memsz))
 			return -EINVAL;
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 85a0bcb1f7ca..df7f2a75e769 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -19,7 +19,6 @@
 #include <linux/bootmem.h>
 #include <linux/seq_file.h>
 #include <linux/screen_info.h>
-#include <linux/of_iommu.h>
 #include <linux/of_platform.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
@@ -849,10 +848,29 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 	kernel_data.end     = virt_to_phys(_end - 1);
 
 	for_each_memblock(memory, region) {
+		phys_addr_t start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
+		phys_addr_t end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
+		unsigned long boot_alias_start;
+
+		/*
+		 * Some systems have a special memory alias which is only
+		 * used for booting.  We need to advertise this region to
+		 * kexec-tools so they know where bootable RAM is located.
+		 */
+		boot_alias_start = phys_to_idmap(start);
+		if (arm_has_idmap_alias() && boot_alias_start != IDMAP_INVALID_ADDR) {
+			res = memblock_virt_alloc(sizeof(*res), 0);
+			res->name = "System RAM (boot alias)";
+			res->start = boot_alias_start;
+			res->end = phys_to_idmap(end);
+			res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+			request_resource(&iomem_resource, res);
+		}
+
 		res = memblock_virt_alloc(sizeof(*res), 0);
 		res->name  = "System RAM";
-		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
-		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
+		res->start = start;
+		res->end = end;
 		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 		request_resource(&iomem_resource, res);
@@ -903,14 +921,9 @@ static int __init customize_machine(void)
 	 * machine from the device tree, if no callback is provided,
 	 * otherwise we would always need an init_machine callback.
 	 */
-	of_iommu_init();
 	if (machine_desc->init_machine)
 		machine_desc->init_machine();
-#ifdef CONFIG_OF
-	else
-		of_platform_populate(NULL, of_default_bus_match_table,
-					NULL, NULL);
-#endif
+
 	return 0;
 }
 arch_initcall(customize_machine);
@@ -1006,9 +1019,25 @@ static void __init reserve_crashkernel(void)
 		(unsigned long)(crash_base >> 20),
 		(unsigned long)(total_mem >> 20));
 
+	/* The crashk resource must always be located in normal mem */
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
 	insert_resource(&iomem_resource, &crashk_res);
+
+	if (arm_has_idmap_alias()) {
+		/*
+		 * If we have a special RAM alias for use at boot, we
+		 * need to advertise to kexec tools where the alias is.
+		 */
+		static struct resource crashk_boot_res = {
+			.name = "Crash kernel (boot alias)",
+			.flags = IORESOURCE_BUSY | IORESOURCE_MEM,
+		};
+
+		crashk_boot_res.start = phys_to_idmap(crash_base);
+		crashk_boot_res.end = crashk_boot_res.start + crash_size - 1;
+		insert_resource(&iomem_resource, &crashk_boot_res);
+	}
 }
 #else
 static inline void reserve_crashkernel(void) {}
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 02abfff68ee5..95a000515e43 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -46,13 +46,6 @@ config KVM_ARM_HOST
 	---help---
 	  Provides host support for ARM processors.
 
-config KVM_NEW_VGIC
-	bool "New VGIC implementation"
-	depends on KVM
-	default y
-	---help---
-	  uses the new VGIC implementation
-
 source drivers/vhost/Kconfig
 
 endif # VIRTUALIZATION
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index a596b58f6d37..5e28df80dca7 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -22,7 +22,6 @@ obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
 
-ifeq ($(CONFIG_KVM_NEW_VGIC),y)
 obj-y += $(KVM)/arm/vgic/vgic.o
 obj-y += $(KVM)/arm/vgic/vgic-init.o
 obj-y += $(KVM)/arm/vgic/vgic-irqfd.o
@@ -30,9 +29,4 @@ obj-y += $(KVM)/arm/vgic/vgic-v2.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
 obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o
-else
-obj-y += $(KVM)/arm/vgic.o
-obj-y += $(KVM)/arm/vgic-v2.o
-obj-y += $(KVM)/arm/vgic-v2-emul.o
-endif
 obj-y += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index f1bde7c4e736..d94bb9093ead 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -20,6 +20,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/list.h>
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
@@ -122,7 +123,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out_fail_alloc;
 
-	ret = create_hyp_mappings(kvm, kvm + 1);
+	ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
 	if (ret)
 		goto out_free_stage2_pgd;
 
@@ -201,7 +202,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_MAX_VCPUS;
 		break;
 	default:
-		r = kvm_arch_dev_ioctl_check_extension(ext);
+		r = kvm_arch_dev_ioctl_check_extension(kvm, ext);
 		break;
 	}
 	return r;
@@ -239,7 +240,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;
 
-	err = create_hyp_mappings(vcpu, vcpu + 1);
+	err = create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP);
 	if (err)
 		goto vcpu_uninit;
 
@@ -377,7 +378,7 @@ void force_vm_exit(const cpumask_t *mask)
 
 /**
  * need_new_vmid_gen - check that the VMID is still valid
- * @kvm: The VM's VMID to checkt
+ * @kvm: The VM's VMID to check
  *
  * return true if there is a new generation of VMIDs being used
  *
@@ -616,7 +617,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * Enter the guest
 		 */
 		trace_kvm_entry(*vcpu_pc(vcpu));
-		__kvm_guest_enter();
+		guest_enter_irqoff();
 		vcpu->mode = IN_GUEST_MODE;
 
 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
@@ -642,14 +643,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		local_irq_enable();
 
 		/*
-		 * We do local_irq_enable() before calling kvm_guest_exit() so
+		 * We do local_irq_enable() before calling guest_exit() so
 		 * that if a timer interrupt hits while running the guest we
 		 * account that tick as being spent in the guest.  We enable
-		 * preemption after calling kvm_guest_exit() so that if we get
+		 * preemption after calling guest_exit() so that if we get
 		 * preempted we make sure ticks after that is not counted as
 		 * guest time.
 		 */
-		kvm_guest_exit();
+		guest_exit();
 		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
 
 		/*
@@ -1039,7 +1040,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 static void cpu_init_hyp_mode(void *dummy)
 {
-	phys_addr_t boot_pgd_ptr;
 	phys_addr_t pgd_ptr;
 	unsigned long hyp_stack_ptr;
 	unsigned long stack_page;
@@ -1048,13 +1048,12 @@ static void cpu_init_hyp_mode(void *dummy)
 	/* Switch from the HYP stub to our own HYP init vector */
 	__hyp_set_vectors(kvm_get_idmap_vector());
 
-	boot_pgd_ptr = kvm_mmu_get_boot_httbr();
 	pgd_ptr = kvm_mmu_get_httbr();
 	stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
 	hyp_stack_ptr = stack_page + PAGE_SIZE;
 	vector_ptr = (unsigned long)kvm_ksym_ref(__kvm_hyp_vector);
 
-	__cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
+	__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
 	__cpu_init_stage2();
 
 	kvm_arm_init_debug();
@@ -1076,15 +1075,9 @@ static void cpu_hyp_reinit(void)
 
 static void cpu_hyp_reset(void)
 {
-	phys_addr_t boot_pgd_ptr;
-	phys_addr_t phys_idmap_start;
-
-	if (!is_kernel_in_hyp_mode()) {
-		boot_pgd_ptr = kvm_mmu_get_boot_httbr();
-		phys_idmap_start = kvm_get_idmap_start();
-
-		__cpu_reset_hyp_mode(boot_pgd_ptr, phys_idmap_start);
-	}
+	if (!is_kernel_in_hyp_mode())
+		__cpu_reset_hyp_mode(hyp_default_vectors,
+				     kvm_get_idmap_start());
 }
 
 static void _kvm_arch_hardware_enable(void *discard)
@@ -1294,14 +1287,14 @@ static int init_hyp_mode(void)
 	 * Map the Hyp-code called directly from the host
 	 */
 	err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start),
-				  kvm_ksym_ref(__hyp_text_end));
+				  kvm_ksym_ref(__hyp_text_end), PAGE_HYP_EXEC);
 	if (err) {
 		kvm_err("Cannot map world-switch code\n");
 		goto out_err;
 	}
 
 	err = create_hyp_mappings(kvm_ksym_ref(__start_rodata),
-				  kvm_ksym_ref(__end_rodata));
+				  kvm_ksym_ref(__end_rodata), PAGE_HYP_RO);
 	if (err) {
 		kvm_err("Cannot map rodata section\n");
 		goto out_err;
@@ -1312,7 +1305,8 @@ static int init_hyp_mode(void)
 	 */
 	for_each_possible_cpu(cpu) {
 		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
-		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE);
+		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE,
+					  PAGE_HYP);
 
 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
@@ -1324,7 +1318,7 @@ static int init_hyp_mode(void)
 		kvm_cpu_context_t *cpu_ctxt;
 
 		cpu_ctxt = per_cpu_ptr(kvm_host_cpu_state, cpu);
-		err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1);
+		err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1, PAGE_HYP);
 
 		if (err) {
 			kvm_err("Cannot map host CPU state: %d\n", err);
@@ -1332,10 +1326,6 @@ static int init_hyp_mode(void)
 		}
 	}
 
-#ifndef CONFIG_HOTPLUG_CPU
-	free_boot_hyp_pgd();
-#endif
-
 	/* set size of VMID supported by CPU */
 	kvm_vmid_bits = kvm_get_vmid_bits();
 	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c
index a494def3f195..af93e3ffc9f3 100644
--- a/arch/arm/kvm/emulate.c
+++ b/arch/arm/kvm/emulate.c
@@ -210,7 +210,7 @@ bool kvm_condition_valid(struct kvm_vcpu *vcpu)
  * @vcpu:	The VCPU pointer
  *
  * When exceptions occur while instructions are executed in Thumb IF-THEN
- * blocks, the ITSTATE field of the CPSR is not advanved (updated), so we have
+ * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have
  * to do this little bit of work manually. The fields map like this:
  *
  * IT[7:0] -> CPSR[26:25],CPSR[15:10]
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 9093ed0f8b2a..9aca92074f85 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -182,7 +182,7 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 /**
  * kvm_arm_copy_reg_indices - get indices of all registers.
  *
- * We do core registers right here, then we apppend coproc regs.
+ * We do core registers right here, then we append coproc regs.
  */
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 1f9ae17476f9..bf89c919efc1 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -32,23 +32,13 @@
  *       r2,r3 = Hypervisor pgd pointer
  *
  * The init scenario is:
- * - We jump in HYP with four parameters: boot HYP pgd, runtime HYP pgd,
- *   runtime stack, runtime vectors
- * - Enable the MMU with the boot pgd
- * - Jump to a target into the trampoline page (remember, this is the same
- *   physical page!)
- * - Now switch to the runtime pgd (same VA, and still the same physical
- *   page!)
+ * - We jump in HYP with 3 parameters: runtime HYP pgd, runtime stack,
+ *   runtime vectors
  * - Invalidate TLBs
  * - Set stack and vectors
+ * - Setup the page tables
+ * - Enable the MMU
  * - Profit! (or eret, if you only care about the code).
- *
- * As we only have four registers available to pass parameters (and we
- * need six), we split the init in two phases:
- * - Phase 1: r0 = 0, r1 = 0, r2,r3 contain the boot PGD.
- *   Provides the basic HYP init, and enable the MMU.
- * - Phase 2: r0 = ToS, r1 = vectors, r2,r3 contain the runtime PGD.
- *   Switches to the runtime PGD, set stack and vectors.
  */
 
 	.text
@@ -68,8 +58,11 @@ __kvm_hyp_init:
 	W(b)	.
 
 __do_hyp_init:
-	cmp	r0, #0			@ We have a SP?
-	bne	phase2			@ Yes, second stage init
+	@ Set stack pointer
+	mov	sp, r0
+
+	@ Set HVBAR to point to the HYP vectors
+	mcr	p15, 4, r1, c12, c0, 0	@ HVBAR
 
 	@ Set the HTTBR to point to the hypervisor PGD pointer passed
 	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
@@ -114,34 +107,25 @@ __do_hyp_init:
  THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
-	isb
 	mcr	p15, 4, r0, c1, c0, 0	@ HSCR
+	isb
 
-	@ End of init phase-1
 	eret
 
-phase2:
-	@ Set stack pointer
-	mov	sp, r0
-
-	@ Set HVBAR to point to the HYP vectors
-	mcr	p15, 4, r1, c12, c0, 0	@ HVBAR
-
-	@ Jump to the trampoline page
-	ldr	r0, =TRAMPOLINE_VA
-	adr	r1, target
-	bfi	r0, r1, #0, #PAGE_SHIFT
-	ret	r0
+	@ r0 : stub vectors address
+ENTRY(__kvm_hyp_reset)
+	/* We're now in idmap, disable MMU */
+	mrc	p15, 4, r1, c1, c0, 0	@ HSCTLR
+	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_C | HSCTLR_I)
+	bic	r1, r1, r2
+	mcr	p15, 4, r1, c1, c0, 0	@ HSCTLR
 
-target:	@ We're now in the trampoline code, switch page tables
-	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
+	/* Install stub vectors */
+	mcr	p15, 4, r0, c12, c0, 0	@ HVBAR
 	isb
 
-	@ Invalidate the old TLBs
-	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
-	dsb	ish
-
 	eret
+ENDPROC(__kvm_hyp_reset)
 
 	.ltorg
 
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 45c43aecb8f2..bda27b6b1aa2 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -32,8 +32,6 @@
 
 #include "trace.h"
 
-extern char  __hyp_idmap_text_start[], __hyp_idmap_text_end[];
-
 static pgd_t *boot_hyp_pgd;
 static pgd_t *hyp_pgd;
 static pgd_t *merged_hyp_pgd;
@@ -484,28 +482,6 @@ static void unmap_hyp_range(pgd_t *pgdp, phys_addr_t start, u64 size)
 }
 
 /**
- * free_boot_hyp_pgd - free HYP boot page tables
- *
- * Free the HYP boot page tables. The bounce page is also freed.
- */
-void free_boot_hyp_pgd(void)
-{
-	mutex_lock(&kvm_hyp_pgd_mutex);
-
-	if (boot_hyp_pgd) {
-		unmap_hyp_range(boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
-		unmap_hyp_range(boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
-		boot_hyp_pgd = NULL;
-	}
-
-	if (hyp_pgd)
-		unmap_hyp_range(hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-
-	mutex_unlock(&kvm_hyp_pgd_mutex);
-}
-
-/**
  * free_hyp_pgds - free Hyp-mode page tables
  *
  * Assumes hyp_pgd is a page table used strictly in Hyp-mode and
@@ -519,15 +495,20 @@ void free_hyp_pgds(void)
 {
 	unsigned long addr;
 
-	free_boot_hyp_pgd();
-
 	mutex_lock(&kvm_hyp_pgd_mutex);
 
+	if (boot_hyp_pgd) {
+		unmap_hyp_range(boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
+		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
+		boot_hyp_pgd = NULL;
+	}
+
 	if (hyp_pgd) {
+		unmap_hyp_range(hyp_pgd, hyp_idmap_start, PAGE_SIZE);
 		for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE)
-			unmap_hyp_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE);
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
-			unmap_hyp_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE);
 
 		free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
 		hyp_pgd = NULL;
@@ -679,17 +660,18 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
  * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
  * @from:	The virtual kernel start address of the range
  * @to:		The virtual kernel end address of the range (exclusive)
+ * @prot:	The protection to be applied to this range
  *
  * The same virtual address as the kernel virtual address is also used
  * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying
  * physical pages.
  */
-int create_hyp_mappings(void *from, void *to)
+int create_hyp_mappings(void *from, void *to, pgprot_t prot)
 {
 	phys_addr_t phys_addr;
 	unsigned long virt_addr;
-	unsigned long start = KERN_TO_HYP((unsigned long)from);
-	unsigned long end = KERN_TO_HYP((unsigned long)to);
+	unsigned long start = kern_hyp_va((unsigned long)from);
+	unsigned long end = kern_hyp_va((unsigned long)to);
 
 	if (is_kernel_in_hyp_mode())
 		return 0;
@@ -704,7 +686,7 @@ int create_hyp_mappings(void *from, void *to)
 		err = __create_hyp_mappings(hyp_pgd, virt_addr,
 					    virt_addr + PAGE_SIZE,
 					    __phys_to_pfn(phys_addr),
-					    PAGE_HYP);
+					    prot);
 		if (err)
 			return err;
 	}
@@ -723,8 +705,8 @@ int create_hyp_mappings(void *from, void *to)
  */
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
 {
-	unsigned long start = KERN_TO_HYP((unsigned long)from);
-	unsigned long end = KERN_TO_HYP((unsigned long)to);
+	unsigned long start = kern_hyp_va((unsigned long)from);
+	unsigned long end = kern_hyp_va((unsigned long)to);
 
 	if (is_kernel_in_hyp_mode())
 		return 0;
@@ -1687,14 +1669,6 @@ phys_addr_t kvm_mmu_get_httbr(void)
 		return virt_to_phys(hyp_pgd);
 }
 
-phys_addr_t kvm_mmu_get_boot_httbr(void)
-{
-	if (__kvm_cpu_uses_extended_idmap())
-		return virt_to_phys(merged_hyp_pgd);
-	else
-		return virt_to_phys(boot_hyp_pgd);
-}
-
 phys_addr_t kvm_get_idmap_vector(void)
 {
 	return hyp_idmap_vector;
@@ -1705,6 +1679,22 @@ phys_addr_t kvm_get_idmap_start(void)
 	return hyp_idmap_start;
 }
 
+static int kvm_map_idmap_text(pgd_t *pgd)
+{
+	int err;
+
+	/* Create the idmap in the boot page tables */
+	err = 	__create_hyp_mappings(pgd,
+				      hyp_idmap_start, hyp_idmap_end,
+				      __phys_to_pfn(hyp_idmap_start),
+				      PAGE_HYP_EXEC);
+	if (err)
+		kvm_err("Failed to idmap %lx-%lx\n",
+			hyp_idmap_start, hyp_idmap_end);
+
+	return err;
+}
+
 int kvm_mmu_init(void)
 {
 	int err;
@@ -1719,28 +1709,41 @@ int kvm_mmu_init(void)
 	 */
 	BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);
 
-	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
-	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
+	kvm_info("IDMAP page: %lx\n", hyp_idmap_start);
+	kvm_info("HYP VA range: %lx:%lx\n",
+		 kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
 
-	if (!hyp_pgd || !boot_hyp_pgd) {
-		kvm_err("Hyp mode PGD not allocated\n");
-		err = -ENOMEM;
+	if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
+	    hyp_idmap_start <  kern_hyp_va(~0UL)) {
+		/*
+		 * The idmap page is intersecting with the VA space,
+		 * it is not safe to continue further.
+		 */
+		kvm_err("IDMAP intersecting with HYP VA, unable to continue\n");
+		err = -EINVAL;
 		goto out;
 	}
 
-	/* Create the idmap in the boot page tables */
-	err = 	__create_hyp_mappings(boot_hyp_pgd,
-				      hyp_idmap_start, hyp_idmap_end,
-				      __phys_to_pfn(hyp_idmap_start),
-				      PAGE_HYP);
-
-	if (err) {
-		kvm_err("Failed to idmap %lx-%lx\n",
-			hyp_idmap_start, hyp_idmap_end);
+	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
+	if (!hyp_pgd) {
+		kvm_err("Hyp mode PGD not allocated\n");
+		err = -ENOMEM;
 		goto out;
 	}
 
 	if (__kvm_cpu_uses_extended_idmap()) {
+		boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+							 hyp_pgd_order);
+		if (!boot_hyp_pgd) {
+			kvm_err("Hyp boot PGD not allocated\n");
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = kvm_map_idmap_text(boot_hyp_pgd);
+		if (err)
+			goto out;
+
 		merged_hyp_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 		if (!merged_hyp_pgd) {
 			kvm_err("Failed to allocate extra HYP pgd\n");
@@ -1748,29 +1751,10 @@ int kvm_mmu_init(void)
 		}
 		__kvm_extend_hypmap(boot_hyp_pgd, hyp_pgd, merged_hyp_pgd,
 				    hyp_idmap_start);
-		return 0;
-	}
-
-	/* Map the very same page at the trampoline VA */
-	err = 	__create_hyp_mappings(boot_hyp_pgd,
-				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,
-				      __phys_to_pfn(hyp_idmap_start),
-				      PAGE_HYP);
-	if (err) {
-		kvm_err("Failed to map trampoline @%lx into boot HYP pgd\n",
-			TRAMPOLINE_VA);
-		goto out;
-	}
-
-	/* Map the same page again into the runtime page tables */
-	err = 	__create_hyp_mappings(hyp_pgd,
-				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,
-				      __phys_to_pfn(hyp_idmap_start),
-				      PAGE_HYP);
-	if (err) {
-		kvm_err("Failed to map trampoline @%lx into runtime HYP pgd\n",
-			TRAMPOLINE_VA);
-		goto out;
+	} else {
+		err = kvm_map_idmap_text(hyp_pgd);
+		if (err)
+			goto out;
 	}
 
 	return 0;
diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c
index 0048b5a62a50..4b5e802e57d1 100644
--- a/arch/arm/kvm/reset.c
+++ b/arch/arm/kvm/reset.c
@@ -52,7 +52,7 @@ static const struct kvm_irq_level cortexa_vtimer_irq = {
  * @vcpu: The VCPU pointer
  *
  * This function finds the right table above and sets the registers on the
- * virtual CPU struct to their architectually defined reset values.
+ * virtual CPU struct to their architecturally defined reset values.
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/arm/mach-artpec/board-artpec6.c b/arch/arm/mach-artpec/board-artpec6.c
index 71513df3374e..a0b1979c2c2c 100644
--- a/arch/arm/mach-artpec/board-artpec6.c
+++ b/arch/arm/mach-artpec/board-artpec6.c
@@ -13,7 +13,6 @@
 #include <linux/irqchip.h>
 #include <linux/irqchip/arm-gic.h>
 #include <linux/mfd/syscon.h>
-#include <linux/of_platform.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/clk-provider.h>
@@ -44,8 +43,6 @@ static void __init artpec6_init_machine(void)
 		regmap_write(regmap, ARTPEC6_DMACFG_REGNUM,
 			     ARTPEC6_DMACFG_UARTS_BURST);
 	};
-
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static void artpec6_l2c310_write_sec(unsigned long val, unsigned reg)
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 08047afdf38e..5204395efda8 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -1,8 +1,8 @@
 menuconfig ARCH_AT91
 	bool "Atmel SoCs"
 	depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 || ARCH_MULTI_V7
-	select ARCH_REQUIRE_GPIOLIB
 	select COMMON_CLK_AT91
+	select GPIOLIB
 	select PINCTRL
 	select SOC_BUS
 
diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c
index 63b4fa25b48a..d068ec3cd1f6 100644
--- a/arch/arm/mach-at91/at91rm9200.c
+++ b/arch/arm/mach-at91/at91rm9200.c
@@ -30,7 +30,7 @@ static void __init at91rm9200_dt_device_init(void)
 	if (soc != NULL)
 		soc_dev = soc_device_to_device(soc);
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
+	of_platform_default_populate(NULL, NULL, soc_dev);
 
 	at91rm9200_pm_init();
 }
diff --git a/arch/arm/mach-at91/at91sam9.c b/arch/arm/mach-at91/at91sam9.c
index cada2a6412b3..ba28e9cc584d 100644
--- a/arch/arm/mach-at91/at91sam9.c
+++ b/arch/arm/mach-at91/at91sam9.c
@@ -61,7 +61,7 @@ static void __init at91sam9_common_init(void)
 	if (soc != NULL)
 		soc_dev = soc_device_to_device(soc);
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
+	of_platform_default_populate(NULL, NULL, soc_dev);
 }
 
 static void __init at91sam9_dt_device_init(void)
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index f06270198bf1..b4332b727e9c 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -22,6 +22,7 @@
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/atmel.h>
 #include <linux/io.h>
 #include <linux/clk/at91_pmc.h>
 
@@ -355,7 +356,7 @@ static __init void at91_dt_ramc(void)
 	at91_pm_set_standby(standby);
 }
 
-void at91rm9200_idle(void)
+static void at91rm9200_idle(void)
 {
 	/*
 	 * Disable the processor clock.  The processor will be automatically
@@ -364,7 +365,7 @@ void at91rm9200_idle(void)
 	writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR);
 }
 
-void at91sam9_idle(void)
+static void at91sam9_idle(void)
 {
 	writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR);
 	cpu_do_idle();
diff --git a/arch/arm/mach-at91/sama5.c b/arch/arm/mach-at91/sama5.c
index 922b85f07cd2..b272c45b400f 100644
--- a/arch/arm/mach-at91/sama5.c
+++ b/arch/arm/mach-at91/sama5.c
@@ -68,7 +68,7 @@ static void __init sama5_dt_device_init(void)
 	if (soc != NULL)
 		soc_dev = soc_device_to_device(soc);
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
+	of_platform_default_populate(NULL, NULL, soc_dev);
 	sama5_pm_init();
 }
 
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index 4f1709b31822..34f0fca0b847 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -17,7 +17,7 @@ config ARCH_BCM_IPROC
 	select ARM_GLOBAL_TIMER
 	select COMMON_CLK_IPROC
 	select CLKSRC_MMIO
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select ARM_AMBA
 	select PINCTRL
 	help
@@ -80,7 +80,7 @@ comment "KONA architected SoCs"
 
 config ARCH_BCM_MOBILE
 	bool
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
 	select ARM_GIC
@@ -112,9 +112,17 @@ config ARCH_BCM_21664
 	  Enable support for the BCM21664 family, which includes
 	  BCM21663 and BCM21664 variants.
 
+config ARCH_BCM_23550
+	bool "Broadcom BCM23550 SoC"
+	depends on ARCH_MULTI_V7
+	select ARCH_BCM_MOBILE
+	select HAVE_SMP
+	help
+	  Enable support for the BCM23550.
+
 config ARCH_BCM_MOBILE_L2_CACHE
 	bool "Broadcom mobile SoC level 2 cache support"
-	depends on ARCH_BCM_MOBILE
+	depends on ARCH_BCM_281XX || ARCH_BCM_21664
 	default y
 	select CACHE_L2X0
 	select ARCH_BCM_MOBILE_SMC
@@ -129,7 +137,7 @@ config ARCH_BCM_MOBILE_SMP
 	select HAVE_ARM_SCU
 	select ARM_ERRATA_764369
 	help
-	  SMP support for the BCM281XX and BCM21664 SoC families.
+	  SMP support for the BCM281XX, BCM21664 and BCM23550 SoC families.
 	  Provided as an option so SMP support for SoCs of this type
 	  can be disabled for an SMP-enabled kernel.
 
@@ -138,7 +146,7 @@ comment "Other Architectures"
 config ARCH_BCM2835
 	bool "Broadcom BCM2835 family"
 	depends on ARCH_MULTI_V6 || ARCH_MULTI_V7
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select ARM_AMBA
 	select ARM_ERRATA_411920 if ARCH_MULTI_V6
 	select ARM_TIMER_SP804
@@ -178,7 +186,6 @@ config ARCH_BRCMSTB
 	select BRCMSTB_L2_IRQ
 	select BCM7120_L2_IRQ
 	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select SOC_BRCMSTB
 	select SOC_BUS
 	help
diff --git a/arch/arm/mach-bcm/Makefile b/arch/arm/mach-bcm/Makefile
index 7d665151c772..980f5850097c 100644
--- a/arch/arm/mach-bcm/Makefile
+++ b/arch/arm/mach-bcm/Makefile
@@ -26,7 +26,10 @@ obj-$(CONFIG_ARCH_BCM_281XX)	+= board_bcm281xx.o
 # BCM21664
 obj-$(CONFIG_ARCH_BCM_21664)	+= board_bcm21664.o
 
-# BCM281XX and BCM21664 SMP support
+# BCM23550
+obj-$(CONFIG_ARCH_BCM_23550)	+= board_bcm23550.o
+
+# BCM281XX, BCM21664 and BCM23550 SMP support
 obj-$(CONFIG_ARCH_BCM_MOBILE_SMP) += platsmp.o
 
 # BCM281XX and BCM21664 L2 cache control
diff --git a/arch/arm/mach-bcm/board_bcm21664.c b/arch/arm/mach-bcm/board_bcm21664.c
index 82ad5687771f..c5bf01641172 100644
--- a/arch/arm/mach-bcm/board_bcm21664.c
+++ b/arch/arm/mach-bcm/board_bcm21664.c
@@ -11,56 +11,12 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
-#include <linux/io.h>
-
 #include <asm/mach/arch.h>
 
 #include "kona_l2_cache.h"
 
-#define RSTMGR_DT_STRING		"brcm,bcm21664-resetmgr"
-
-#define RSTMGR_REG_WR_ACCESS_OFFSET	0
-#define RSTMGR_REG_CHIP_SOFT_RST_OFFSET	4
-
-#define RSTMGR_WR_PASSWORD		0xa5a5
-#define RSTMGR_WR_PASSWORD_SHIFT	8
-#define RSTMGR_WR_ACCESS_ENABLE		1
-
-static void bcm21664_restart(enum reboot_mode mode, const char *cmd)
-{
-	void __iomem *base;
-	struct device_node *resetmgr;
-
-	resetmgr = of_find_compatible_node(NULL, NULL, RSTMGR_DT_STRING);
-	if (!resetmgr) {
-		pr_emerg("Couldn't find " RSTMGR_DT_STRING "\n");
-		return;
-	}
-	base = of_iomap(resetmgr, 0);
-	if (!base) {
-		pr_emerg("Couldn't map " RSTMGR_DT_STRING "\n");
-		return;
-	}
-
-	/*
-	 * A soft reset is triggered by writing a 0 to bit 0 of the soft reset
-	 * register. To write to that register we must first write the password
-	 * and the enable bit in the write access enable register.
-	 */
-	writel((RSTMGR_WR_PASSWORD << RSTMGR_WR_PASSWORD_SHIFT) |
-		RSTMGR_WR_ACCESS_ENABLE,
-		base + RSTMGR_REG_WR_ACCESS_OFFSET);
-	writel(0, base + RSTMGR_REG_CHIP_SOFT_RST_OFFSET);
-
-	/* Wait for reset */
-	while (1);
-}
-
 static void __init bcm21664_init(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	kona_l2_cache_init();
 }
 
@@ -71,6 +27,5 @@ static const char * const bcm21664_dt_compat[] = {
 
 DT_MACHINE_START(BCM21664_DT, "BCM21664 Broadcom Application Processor")
 	.init_machine = bcm21664_init,
-	.restart = bcm21664_restart,
 	.dt_compat = bcm21664_dt_compat,
 MACHINE_END
diff --git a/arch/arm/mach-bcm/board_bcm23550.c b/arch/arm/mach-bcm/board_bcm23550.c
new file mode 100644
index 000000000000..0ac01debd077
--- /dev/null
+++ b/arch/arm/mach-bcm/board_bcm23550.c
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2016 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of_platform.h>
+
+#include <asm/mach/arch.h>
+
+static const char * const bcm23550_dt_compat[] = {
+	"brcm,bcm23550",
+	NULL,
+};
+
+DT_MACHINE_START(BCM23550_DT, "BCM23550 Broadcom Application Processor")
+	.dt_compat = bcm23550_dt_compat,
+MACHINE_END
diff --git a/arch/arm/mach-bcm/board_bcm281xx.c b/arch/arm/mach-bcm/board_bcm281xx.c
index 2e367bd7c600..b81bb386951d 100644
--- a/arch/arm/mach-bcm/board_bcm281xx.c
+++ b/arch/arm/mach-bcm/board_bcm281xx.c
@@ -13,7 +13,6 @@
 
 #include <linux/clocksource.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 
 #include <asm/mach/arch.h>
 
@@ -58,7 +57,6 @@ static void bcm281xx_restart(enum reboot_mode mode, const char *cmd)
 
 static void __init bcm281xx_init(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	kona_l2_cache_init();
 }
 
diff --git a/arch/arm/mach-bcm/board_bcm2835.c b/arch/arm/mach-bcm/board_bcm2835.c
index 834d67684e20..0c1edfc98696 100644
--- a/arch/arm/mach-bcm/board_bcm2835.c
+++ b/arch/arm/mach-bcm/board_bcm2835.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 #include <linux/irqchip.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 #include <linux/clk/bcm2835.h>
 
 #include <asm/mach/arch.h>
@@ -23,16 +22,7 @@
 
 static void __init bcm2835_init(void)
 {
-	int ret;
-
 	bcm2835_init_clocks();
-
-	ret = of_platform_populate(NULL, of_default_bus_match_table, NULL,
-				   NULL);
-	if (ret) {
-		pr_err("of_platform_populate failed: %d\n", ret);
-		BUG();
-	}
 }
 
 static const char * const bcm2835_compat[] = {
diff --git a/arch/arm/mach-bcm/kona_l2_cache.c b/arch/arm/mach-bcm/kona_l2_cache.c
index b31970377c20..59ad86304092 100644
--- a/arch/arm/mach-bcm/kona_l2_cache.c
+++ b/arch/arm/mach-bcm/kona_l2_cache.c
@@ -17,6 +17,7 @@
 #include <asm/hardware/cache-l2x0.h>
 
 #include "bcm_kona_smc.h"
+#include "kona_l2_cache.h"
 
 void __init kona_l2_cache_init(void)
 {
diff --git a/arch/arm/mach-bcm/platsmp.c b/arch/arm/mach-bcm/platsmp.c
index cfae9c71fb74..3ac3a9bc663c 100644
--- a/arch/arm/mach-bcm/platsmp.c
+++ b/arch/arm/mach-bcm/platsmp.c
@@ -19,6 +19,7 @@
 #include <linux/io.h>
 #include <linux/jiffies.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 
@@ -37,9 +38,6 @@
 #define OF_SECONDARY_BOOT	"secondary-boot-reg"
 #define MPIDR_CPUID_BITMASK	0x3
 
-/* I/O address of register used to coordinate secondary core startup */
-static u32	secondary_boot_addr;
-
 /*
  * Enable the Cortex A9 Snoop Control Unit
  *
@@ -81,20 +79,40 @@ static int __init scu_a9_enable(void)
 	return 0;
 }
 
-static int nsp_write_lut(void)
+static u32 secondary_boot_addr_for(unsigned int cpu)
+{
+	u32 secondary_boot_addr = 0;
+	struct device_node *cpu_node = of_get_cpu_node(cpu, NULL);
+
+        if (!cpu_node) {
+		pr_err("Failed to find device tree node for CPU%u\n", cpu);
+		return 0;
+	}
+
+	if (of_property_read_u32(cpu_node,
+				 OF_SECONDARY_BOOT,
+				 &secondary_boot_addr))
+		pr_err("required secondary boot register not specified for CPU%u\n",
+			cpu);
+
+	of_node_put(cpu_node);
+
+	return secondary_boot_addr;
+}
+
+static int nsp_write_lut(unsigned int cpu)
 {
 	void __iomem *sku_rom_lut;
 	phys_addr_t secondary_startup_phy;
+	const u32 secondary_boot_addr = secondary_boot_addr_for(cpu);
 
-	if (!secondary_boot_addr) {
-		pr_warn("required secondary boot register not specified\n");
+	if (!secondary_boot_addr)
 		return -EINVAL;
-	}
 
 	sku_rom_lut = ioremap_nocache((phys_addr_t)secondary_boot_addr,
-						sizeof(secondary_boot_addr));
+				      sizeof(phys_addr_t));
 	if (!sku_rom_lut) {
-		pr_warn("unable to ioremap SKU-ROM LUT register\n");
+		pr_warn("unable to ioremap SKU-ROM LUT register for cpu %u\n", cpu);
 		return -ENOMEM;
 	}
 
@@ -113,70 +131,12 @@ static int nsp_write_lut(void)
 
 static void __init bcm_smp_prepare_cpus(unsigned int max_cpus)
 {
-	static cpumask_t only_cpu_0 = { CPU_BITS_CPU0 };
-	struct device_node *cpus_node = NULL;
-	struct device_node *cpu_node = NULL;
-	int ret;
-
-	/*
-	 * This function is only called via smp_ops->smp_prepare_cpu().
-	 * That only happens if a "/cpus" device tree node exists
-	 * and has an "enable-method" property that selects the SMP
-	 * operations defined herein.
-	 */
-	cpus_node = of_find_node_by_path("/cpus");
-	if (!cpus_node)
-		return;
-
-	for_each_child_of_node(cpus_node, cpu_node) {
-		u32 cpuid;
-
-		if (of_node_cmp(cpu_node->type, "cpu"))
-			continue;
-
-		if (of_property_read_u32(cpu_node, "reg", &cpuid)) {
-			pr_debug("%s: missing reg property\n",
-				     cpu_node->full_name);
-			ret = -ENOENT;
-			goto out;
-		}
-
-		/*
-		 * "secondary-boot-reg" property should be defined only
-		 * for secondary cpu
-		 */
-		if ((cpuid & MPIDR_CPUID_BITMASK) == 1) {
-			/*
-			 * Our secondary enable method requires a
-			 * "secondary-boot-reg" property to specify a register
-			 * address used to request the ROM code boot a secondary
-			 * core. If we have any trouble getting this we fall
-			 * back to uniprocessor mode.
-			 */
-			if (of_property_read_u32(cpu_node,
-						OF_SECONDARY_BOOT,
-						&secondary_boot_addr)) {
-				pr_warn("%s: no" OF_SECONDARY_BOOT "property\n",
-					cpu_node->name);
-				ret = -ENOENT;
-				goto out;
-			}
-		}
-	}
-
-	/*
-	 * Enable the SCU on Cortex A9 based SoCs. If -ENOENT is
-	 * returned, the SoC reported a uniprocessor configuration.
-	 * We bail on any other error.
-	 */
-	ret = scu_a9_enable();
-out:
-	of_node_put(cpu_node);
-	of_node_put(cpus_node);
+	const cpumask_t only_cpu_0 = { CPU_BITS_CPU0 };
 
-	if (ret) {
+	/* Enable the SCU on Cortex A9 based SoCs */
+	if (scu_a9_enable()) {
 		/* Update the CPU present map to reflect uniprocessor mode */
-		pr_warn("disabling SMP\n");
+		pr_warn("failed to enable A9 SCU - disabling SMP\n");
 		init_cpu_present(&only_cpu_0);
 	}
 }
@@ -207,6 +167,7 @@ static int kona_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	u32 cpu_id;
 	u32 boot_val;
 	bool timeout = false;
+	const u32 secondary_boot_addr = secondary_boot_addr_for(cpu);
 
 	cpu_id = cpu_logical_map(cpu);
 	if (cpu_id & ~BOOT_ADDR_CPUID_MASK) {
@@ -214,13 +175,11 @@ static int kona_boot_secondary(unsigned int cpu, struct task_struct *idle)
 		return -EINVAL;
 	}
 
-	if (!secondary_boot_addr) {
-		pr_err("required secondary boot register not specified\n");
+	if (!secondary_boot_addr)
 		return -EINVAL;
-	}
 
-	boot_reg = ioremap_nocache(
-			(phys_addr_t)secondary_boot_addr, sizeof(u32));
+	boot_reg = ioremap_nocache((phys_addr_t)secondary_boot_addr,
+				   sizeof(phys_addr_t));
 	if (!boot_reg) {
 		pr_err("unable to map boot register for cpu %u\n", cpu_id);
 		return -ENOMEM;
@@ -255,6 +214,57 @@ static int kona_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	return -ENXIO;
 }
 
+/* Cluster Dormant Control command to bring CPU into a running state */
+#define CDC_CMD			6
+#define CDC_CMD_OFFSET		0
+#define CDC_CMD_REG(cpu)	(CDC_CMD_OFFSET + 4*(cpu))
+
+/*
+ * BCM23550 has a Cluster Dormant Control block that keeps the core in
+ * idle state. A command needs to be sent to the block to bring the CPU
+ * into running state.
+ */
+static int bcm23550_boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	void __iomem *cdc_base;
+	struct device_node *dn;
+	char *name;
+	int ret;
+
+	/* Make sure a CDC node exists before booting the
+	 * secondary core.
+	 */
+	name = "brcm,bcm23550-cdc";
+	dn = of_find_compatible_node(NULL, NULL, name);
+	if (!dn) {
+		pr_err("unable to find cdc node\n");
+		return -ENODEV;
+	}
+
+	cdc_base = of_iomap(dn, 0);
+	of_node_put(dn);
+
+	if (!cdc_base) {
+		pr_err("unable to remap cdc base register\n");
+		return -ENOMEM;
+	}
+
+	/* Boot the secondary core */
+	ret = kona_boot_secondary(cpu, idle);
+	if (ret)
+		goto out;
+
+	/* Bring this CPU to RUN state so that nIRQ nFIQ
+	 * signals are unblocked.
+	 */
+	writel_relaxed(CDC_CMD, cdc_base + CDC_CMD_REG(cpu));
+
+out:
+	iounmap(cdc_base);
+
+	return ret;
+}
+
 static int nsp_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	int ret;
@@ -263,7 +273,7 @@ static int nsp_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * After wake up, secondary core branches to the startup
 	 * address programmed at SKU ROM LUT location.
 	 */
-	ret = nsp_write_lut();
+	ret = nsp_write_lut(cpu);
 	if (ret) {
 		pr_err("unable to write startup addr to SKU ROM LUT\n");
 		goto out;
@@ -276,12 +286,18 @@ out:
 	return ret;
 }
 
-static const struct smp_operations bcm_smp_ops __initconst = {
+static const struct smp_operations kona_smp_ops __initconst = {
 	.smp_prepare_cpus	= bcm_smp_prepare_cpus,
 	.smp_boot_secondary	= kona_boot_secondary,
 };
 CPU_METHOD_OF_DECLARE(bcm_smp_bcm281xx, "brcm,bcm11351-cpu-method",
-			&bcm_smp_ops);
+			&kona_smp_ops);
+
+static const struct smp_operations bcm23550_smp_ops __initconst = {
+	.smp_boot_secondary	= bcm23550_boot_secondary,
+};
+CPU_METHOD_OF_DECLARE(bcm_smp_bcm23550, "brcm,bcm23550",
+			&bcm23550_smp_ops);
 
 static const struct smp_operations nsp_smp_ops __initconst = {
 	.smp_prepare_cpus	= bcm_smp_prepare_cpus,
diff --git a/arch/arm/mach-berlin/Kconfig b/arch/arm/mach-berlin/Kconfig
index ffbfa0bd091b..63ab1d368625 100644
--- a/arch/arm/mach-berlin/Kconfig
+++ b/arch/arm/mach-berlin/Kconfig
@@ -2,11 +2,11 @@ menuconfig ARCH_BERLIN
 	bool "Marvell Berlin SoCs"
 	depends on ARCH_MULTI_V7
 	select ARCH_HAS_RESET_CONTROLLER
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_GIC
 	select DW_APB_ICTL
 	select DW_APB_TIMER_OF
 	select GENERIC_IRQ_CHIP
+	select GPIOLIB
 	select MFD_SYSCON
 	select PINCTRL
 
diff --git a/arch/arm/mach-clps711x/Kconfig b/arch/arm/mach-clps711x/Kconfig
index f711498c180c..dc7c6edeab39 100644
--- a/arch/arm/mach-clps711x/Kconfig
+++ b/arch/arm/mach-clps711x/Kconfig
@@ -1,38 +1,15 @@
-if ARCH_CLPS711X
-
-menu "CLPS711X/EP721X/EP731X Implementations"
-
-config ARCH_AUTCPU12
-	bool "AUTCPU12"
-	help
-	  Say Y if you intend to run the kernel on the autronix autcpu12
-	  board. This board is based on a Cirrus Logic CS89712.
-
-config ARCH_CDB89712
-	bool "CDB89712"
-	help
-	  This is an evaluation board from Cirrus for the CS89712 processor.
-	  The board includes 2 serial ports, Ethernet, IRDA, and expansion
-	  headers.  It comes with 16 MB SDRAM and 8 MB flash ROM.
-
-config ARCH_CLEP7312
-	bool "CLEP7312"
-	help
-	  Boards based on the Cirrus Logic 7212/7312 chips.
-
-config ARCH_EDB7211
-	bool "EDB7211"
-	select ARCH_HAS_HOLES_MEMORYMODEL
-	help
-	  Say Y here if you intend to run this kernel on a Cirrus Logic EDB-7211
-	  evaluation board.
-
-config ARCH_P720T
-	bool "P720T"
-	help
-	  Say Y here if you intend to run this kernel on the ARM Prospector
-	  720T.
-
-endmenu
-
-endif
+menuconfig ARCH_CLPS711X
+	bool "Cirrus Logic EP721x/EP731x-based"
+	depends on ARCH_MULTI_V4T
+	select ARCH_REQUIRE_GPIOLIB
+	select AUTO_ZRELADDR
+	select CLKSRC_OF
+	select CLPS711X_TIMER
+	select COMMON_CLK
+	select CPU_ARM720T
+	select GENERIC_CLOCKEVENTS
+	select MFD_SYSCON
+	select OF_IRQ
+	select USE_OF
+	help
+	  Select this if you use ARMv4T Cirrus Logic chips.
diff --git a/arch/arm/mach-clps711x/Makefile b/arch/arm/mach-clps711x/Makefile
index f04151efd96a..bd0b7b5d6e9d 100644
--- a/arch/arm/mach-clps711x/Makefile
+++ b/arch/arm/mach-clps711x/Makefile
@@ -1,13 +1 @@
-#
-# Makefile for the linux kernel.
-#
-
-# Object file lists.
-
-obj-y				:= common.o devices.o
-
-obj-$(CONFIG_ARCH_AUTCPU12)	+= board-autcpu12.o
-obj-$(CONFIG_ARCH_CDB89712)	+= board-cdb89712.o
-obj-$(CONFIG_ARCH_CLEP7312)	+= board-clep7312.o
-obj-$(CONFIG_ARCH_EDB7211)	+= board-edb7211.o
-obj-$(CONFIG_ARCH_P720T)	+= board-p720t.o
+obj-y += board-dt.o
diff --git a/arch/arm/mach-clps711x/Makefile.boot b/arch/arm/mach-clps711x/Makefile.boot
index eba77d35a615..e69de29bb2d1 100644
--- a/arch/arm/mach-clps711x/Makefile.boot
+++ b/arch/arm/mach-clps711x/Makefile.boot
@@ -1,5 +0,0 @@
-# The standard locations for stuff on CLPS711x type processors
-params_phys-y				:= 0xc0000100
-# Should probably have some agreement on these...
-initrd_phys-$(CONFIG_ARCH_P720T)	:= 0xc0400000
-initrd_phys-$(CONFIG_ARCH_CDB89712)	:= 0x00700000
diff --git a/arch/arm/mach-clps711x/board-dt.c b/arch/arm/mach-clps711x/board-dt.c
new file mode 100644
index 000000000000..ee1f83b1a332
--- /dev/null
+++ b/arch/arm/mach-clps711x/board-dt.c
@@ -0,0 +1,82 @@
+/*
+ *  Author: Alexander Shiyan <shc_work@mail.ru>, 2016
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/io.h>
+#include <linux/of_fdt.h>
+#include <linux/platform_device.h>
+#include <linux/random.h>
+#include <linux/sizes.h>
+
+#include <linux/mfd/syscon/clps711x.h>
+
+#include <asm/system_info.h>
+#include <asm/system_misc.h>
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+
+#define CLPS711X_VIRT_BASE	IOMEM(0xfeff4000)
+#define CLPS711X_PHYS_BASE	(0x80000000)
+# define SYSFLG1		(0x0140)
+# define HALT			(0x0800)
+# define UNIQID			(0x2440)
+# define RANDID0		(0x2700)
+# define RANDID1		(0x2704)
+# define RANDID2		(0x2708)
+# define RANDID3		(0x270c)
+
+static struct map_desc clps711x_io_desc __initdata = {
+	.virtual	= (unsigned long)CLPS711X_VIRT_BASE,
+	.pfn		= __phys_to_pfn(CLPS711X_PHYS_BASE),
+	.length		= 48 * SZ_1K,
+	.type		= MT_DEVICE,
+};
+
+static void __init clps711x_map_io(void)
+{
+	iotable_init(&clps711x_io_desc, 1);
+}
+
+static const struct resource clps711x_cpuidle_res =
+	DEFINE_RES_MEM(CLPS711X_PHYS_BASE + HALT, SZ_128);
+
+static void __init clps711x_init(void)
+{
+	u32 id[5];
+
+	id[0] = readl(CLPS711X_VIRT_BASE + UNIQID);
+	id[1] = readl(CLPS711X_VIRT_BASE + RANDID0);
+	id[2] = readl(CLPS711X_VIRT_BASE + RANDID1);
+	id[3] = readl(CLPS711X_VIRT_BASE + RANDID2);
+	id[4] = readl(CLPS711X_VIRT_BASE + RANDID3);
+	system_rev = SYSFLG1_VERID(readl(CLPS711X_VIRT_BASE + SYSFLG1));
+
+	add_device_randomness(id, sizeof(id));
+
+	system_serial_low = id[0];
+
+	platform_device_register_simple("clps711x-cpuidle", PLATFORM_DEVID_NONE,
+					&clps711x_cpuidle_res, 1);
+}
+
+static void clps711x_restart(enum reboot_mode mode, const char *cmd)
+{
+	soft_restart(0);
+}
+
+static const char *clps711x_compat[] __initconst = {
+	"cirrus,ep7209",
+	NULL
+};
+
+DT_MACHINE_START(CLPS711X_DT, "Cirrus Logic CLPS711X (Device Tree Support)")
+	.dt_compat	= clps711x_compat,
+	.map_io		= clps711x_map_io,
+	.init_late	= clps711x_init,
+	.restart	= clps711x_restart,
+MACHINE_END
diff --git a/arch/arm/mach-clps711x/common.c b/arch/arm/mach-clps711x/common.c
index 671acc5a3282..6466da8f3c11 100644
--- a/arch/arm/mach-clps711x/common.c
+++ b/arch/arm/mach-clps711x/common.c
@@ -37,8 +37,8 @@ static struct map_desc clps711x_io_desc[] __initdata = {
 	{
 		.virtual	= (unsigned long)CLPS711X_VIRT_BASE,
 		.pfn		= __phys_to_pfn(CLPS711X_PHYS_BASE),
-		.length		= SZ_64K,
-		.type		= MT_DEVICE
+		.length		= 48 * SZ_1K,
+		.type		= MT_DEVICE,
 	}
 };
 
diff --git a/arch/arm/mach-clps711x/include/mach/clps711x.h b/arch/arm/mach-clps711x/include/mach/clps711x.h
deleted file mode 100644
index eb052a11aa9d..000000000000
--- a/arch/arm/mach-clps711x/include/mach/clps711x.h
+++ /dev/null
@@ -1,204 +0,0 @@
-/*
- *  This file contains the hardware definitions of the Cirrus Logic
- *  ARM7 CLPS711X internal registers.
- *
- *  Copyright (C) 2000 Deep Blue Solutions Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#ifndef __MACH_CLPS711X_H
-#define __MACH_CLPS711X_H
-
-#include <linux/mfd/syscon/clps711x.h>
-
-#define CLPS711X_PHYS_BASE	(0x80000000)
-
-#define PADR		(0x0000)
-#define PBDR		(0x0001)
-#define PCDR		(0x0002)
-#define PDDR		(0x0003)
-#define PADDR		(0x0040)
-#define PBDDR		(0x0041)
-#define PCDDR		(0x0042)
-#define PDDDR		(0x0043)
-#define PEDR		(0x0083)
-#define PEDDR		(0x00c3)
-#define SYSCON1		(0x0100)
-#define SYSFLG1		(0x0140)
-#define MEMCFG1		(0x0180)
-#define MEMCFG2		(0x01c0)
-#define DRFPR		(0x0200)
-#define LCDCON		(0x02c0)
-#define TC1D		(0x0300)
-#define TC2D		(0x0340)
-#define RTCDR		(0x0380)
-#define RTCMR		(0x03c0)
-#define PMPCON		(0x0400)
-#define CODR		(0x0440)
-#define UARTDR1		(0x0480)
-#define UBRLCR1		(0x04c0)
-#define SYNCIO		(0x0500)
-#define PALLSW		(0x0540)
-#define PALMSW		(0x0580)
-#define STFCLR		(0x05c0)
-#define HALT		(0x0800)
-#define STDBY		(0x0840)
-
-#define FBADDR		(0x1000)
-#define SYSCON2		(0x1100)
-#define SYSFLG2		(0x1140)
-#define UARTDR2		(0x1480)
-#define UBRLCR2		(0x14c0)
-#define SS2DR		(0x1500)
-#define SS2POP		(0x16c0)
-
-#define DAIR		(0x2000)
-#define DAIDR0		(0x2040)
-#define DAIDR1		(0x2080)
-#define DAIDR2		(0x20c0)
-#define DAISR		(0x2100)
-#define SYSCON3		(0x2200)
-#define LEDFLSH		(0x22c0)
-#define SDCONF		(0x2300)
-#define SDRFPR		(0x2340)
-#define UNIQID		(0x2440)
-#define DAI64FS		(0x2600)
-#define PLLW		(0x2610)
-#define PLLR		(0xa5a8)
-#define RANDID0		(0x2700)
-#define RANDID1		(0x2704)
-#define RANDID2		(0x2708)
-#define RANDID3		(0x270c)
-
-#define LCDCON_GSEN		(1 << 30)
-#define LCDCON_GSMD		(1 << 31)
-
-/* common bits: UARTDR1 / UARTDR2 */
-#define UARTDR_FRMERR		(1 << 8)
-#define UARTDR_PARERR		(1 << 9)
-#define UARTDR_OVERR		(1 << 10)
-
-/* common bits: UBRLCR1 / UBRLCR2 */
-#define UBRLCR_BAUD_MASK	((1 << 12) - 1)
-#define UBRLCR_BREAK		(1 << 12)
-#define UBRLCR_PRTEN		(1 << 13)
-#define UBRLCR_EVENPRT		(1 << 14)
-#define UBRLCR_XSTOP		(1 << 15)
-#define UBRLCR_FIFOEN		(1 << 16)
-#define UBRLCR_WRDLEN5		(0 << 17)
-#define UBRLCR_WRDLEN6		(1 << 17)
-#define UBRLCR_WRDLEN7		(2 << 17)
-#define UBRLCR_WRDLEN8		(3 << 17)
-#define UBRLCR_WRDLEN_MASK	(3 << 17)
-
-#define SYNCIO_FRMLEN(x)	(((x) & 0x1f) << 8)
-#define SYNCIO_SMCKEN		(1 << 13)
-#define SYNCIO_TXFRMEN		(1 << 14)
-
-#define DAIR_RESERVED		(0x0404)
-#define DAIR_DAIEN		(1 << 16)
-#define DAIR_ECS		(1 << 17)
-#define DAIR_LCTM		(1 << 19)
-#define DAIR_LCRM		(1 << 20)
-#define DAIR_RCTM		(1 << 21)
-#define DAIR_RCRM		(1 << 22)
-#define DAIR_LBM		(1 << 23)
-
-#define DAIDR2_FIFOEN		(1 << 15)
-#define DAIDR2_FIFOLEFT		(0x0d << 16)
-#define DAIDR2_FIFORIGHT	(0x11 << 16)
-
-#define DAISR_RCTS		(1 << 0)
-#define DAISR_RCRS		(1 << 1)
-#define DAISR_LCTS		(1 << 2)
-#define DAISR_LCRS		(1 << 3)
-#define DAISR_RCTU		(1 << 4)
-#define DAISR_RCRO		(1 << 5)
-#define DAISR_LCTU		(1 << 6)
-#define DAISR_LCRO		(1 << 7)
-#define DAISR_RCNF		(1 << 8)
-#define DAISR_RCNE		(1 << 9)
-#define DAISR_LCNF		(1 << 10)
-#define DAISR_LCNE		(1 << 11)
-#define DAISR_FIFO		(1 << 12)
-
-#define DAI64FS_I2SF64		(1 << 0)
-#define DAI64FS_AUDIOCLKEN	(1 << 1)
-#define DAI64FS_AUDIOCLKSRC	(1 << 2)
-#define DAI64FS_MCLK256EN	(1 << 3)
-#define DAI64FS_LOOPBACK	(1 << 5)
-
-#define SDCONF_ACTIVE		(1 << 10)
-#define SDCONF_CLKCTL		(1 << 9)
-#define SDCONF_WIDTH_4		(0 << 7)
-#define SDCONF_WIDTH_8		(1 << 7)
-#define SDCONF_WIDTH_16		(2 << 7)
-#define SDCONF_WIDTH_32		(3 << 7)
-#define SDCONF_SIZE_16		(0 << 5)
-#define SDCONF_SIZE_64		(1 << 5)
-#define SDCONF_SIZE_128		(2 << 5)
-#define SDCONF_SIZE_256		(3 << 5)
-#define SDCONF_CASLAT_2		(2)
-#define SDCONF_CASLAT_3		(3)
-
-#define MEMCFG_BUS_WIDTH_32	(1)
-#define MEMCFG_BUS_WIDTH_16	(0)
-#define MEMCFG_BUS_WIDTH_8	(3)
-
-#define MEMCFG_SQAEN		(1 << 6)
-#define MEMCFG_CLKENB		(1 << 7)
-
-#define MEMCFG_WAITSTATE_8_3	(0 << 2)
-#define MEMCFG_WAITSTATE_7_3	(1 << 2)
-#define MEMCFG_WAITSTATE_6_3	(2 << 2)
-#define MEMCFG_WAITSTATE_5_3	(3 << 2)
-#define MEMCFG_WAITSTATE_4_2	(4 << 2)
-#define MEMCFG_WAITSTATE_3_2	(5 << 2)
-#define MEMCFG_WAITSTATE_2_2	(6 << 2)
-#define MEMCFG_WAITSTATE_1_2	(7 << 2)
-#define MEMCFG_WAITSTATE_8_1	(8 << 2)
-#define MEMCFG_WAITSTATE_7_1	(9 << 2)
-#define MEMCFG_WAITSTATE_6_1	(10 << 2)
-#define MEMCFG_WAITSTATE_5_1	(11 << 2)
-#define MEMCFG_WAITSTATE_4_0	(12 << 2)
-#define MEMCFG_WAITSTATE_3_0	(13 << 2)
-#define MEMCFG_WAITSTATE_2_0	(14 << 2)
-#define MEMCFG_WAITSTATE_1_0	(15 << 2)
-
-/* INTSR1 Interrupts */
-#define IRQ_CSINT		(4)
-#define IRQ_EINT1		(5)
-#define IRQ_EINT2		(6)
-#define IRQ_EINT3		(7)
-#define IRQ_TC1OI		(8)
-#define IRQ_TC2OI		(9)
-#define IRQ_RTCMI		(10)
-#define IRQ_TINT		(11)
-#define IRQ_UTXINT1		(12)
-#define IRQ_URXINT1		(13)
-#define IRQ_UMSINT		(14)
-#define IRQ_SSEOTI		(15)
-
-/* INTSR2 Interrupts */
-#define IRQ_KBDINT		(16 + 0)
-#define IRQ_SS2RX		(16 + 1)
-#define IRQ_SS2TX		(16 + 2)
-#define IRQ_UTXINT2		(16 + 12)
-#define IRQ_URXINT2		(16 + 13)
-
-/* INTSR3 Interrupts */
-#define IRQ_DAIINT		(32 + 0)
-
-#endif /* __MACH_CLPS711X_H */
diff --git a/arch/arm/mach-clps711x/include/mach/hardware.h b/arch/arm/mach-clps711x/include/mach/hardware.h
deleted file mode 100644
index 833129c9f798..000000000000
--- a/arch/arm/mach-clps711x/include/mach/hardware.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- *  arch/arm/mach-clps711x/include/mach/hardware.h
- *
- *  This file contains the hardware definitions of the Prospector P720T.
- *
- *  Copyright (C) 2000 Deep Blue Solutions Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#ifndef __MACH_HARDWARE_H
-#define __MACH_HARDWARE_H
-
-#include <mach/clps711x.h>
-
-#define CLPS711X_VIRT_BASE	IOMEM(0xfeff0000)
-
-#ifndef __ASSEMBLY__
-#define clps_readb(off)		readb(CLPS711X_VIRT_BASE + (off))
-#define clps_readw(off)		readw(CLPS711X_VIRT_BASE + (off))
-#define clps_readl(off)		readl(CLPS711X_VIRT_BASE + (off))
-#define clps_writeb(val,off)	writeb(val, CLPS711X_VIRT_BASE + (off))
-#define clps_writew(val,off)	writew(val, CLPS711X_VIRT_BASE + (off))
-#define clps_writel(val,off)	writel(val, CLPS711X_VIRT_BASE + (off))
-#endif
-
-#define CS0_PHYS_BASE		(0x00000000)
-#define CS1_PHYS_BASE		(0x10000000)
-#define CS2_PHYS_BASE		(0x20000000)
-#define CS3_PHYS_BASE		(0x30000000)
-#define CS4_PHYS_BASE		(0x40000000)
-#define CS5_PHYS_BASE		(0x50000000)
-#define CS6_PHYS_BASE		(0x60000000)
-#define CS7_PHYS_BASE		(0x70000000)
-
-#define CLPS711X_SRAM_BASE	CS6_PHYS_BASE
-#define CLPS711X_SRAM_SIZE	(48 * 1024)
-
-#define CLPS711X_SDRAM0_BASE	(0xc0000000)
-#define CLPS711X_SDRAM1_BASE	(0xd0000000)
-
-#endif
diff --git a/arch/arm/mach-clps711x/include/mach/uncompress.h b/arch/arm/mach-clps711x/include/mach/uncompress.h
deleted file mode 100644
index 5f02d06dc655..000000000000
--- a/arch/arm/mach-clps711x/include/mach/uncompress.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- *  arch/arm/mach-clps711x/include/mach/uncompress.h
- *
- *  Copyright (C) 2000 Deep Blue Solutions Ltd
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#include <mach/clps711x.h>
-
-#ifdef CONFIG_DEBUG_CLPS711X_UART2
-#define SYSFLGx	SYSFLG2
-#define UARTDRx	UARTDR2
-#else
-#define SYSFLGx	SYSFLG1
-#define UARTDRx	UARTDR1
-#endif
-
-#define phys_reg(x)	(*(volatile u32 *)(CLPS711X_PHYS_BASE + (x)))
-
-/*
- * The following code assumes the serial port has already been
- * initialized by the bootloader.  If you didn't setup a port in
- * your bootloader then nothing will appear (which might be desired).
- *
- * This does not append a newline
- */
-static inline void putc(int c)
-{
-	while (phys_reg(SYSFLGx) & SYSFLG_UTXFF)
-		barrier();
-	phys_reg(UARTDRx) = c;
-}
-
-static inline void flush(void)
-{
-	while (phys_reg(SYSFLGx) & SYSFLG_UBUSY)
-		barrier();
-}
-
-/*
- * nothing to do
- */
-#define arch_decomp_setup()
diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c
index 9b1dc223d8d3..03da3813f1ab 100644
--- a/arch/arm/mach-cns3xxx/core.c
+++ b/arch/arm/mach-cns3xxx/core.c
@@ -395,8 +395,7 @@ static void __init cns3xxx_init(void)
 
 	pm_power_off = cns3xxx_power_off;
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-                        cns3xxx_auxdata, NULL);
+	of_platform_default_populate(NULL, cns3xxx_auxdata, NULL);
 }
 
 static const char *const cns3xxx_dt_compat[] __initconst = {
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index 1844076f6403..18296a99c4d2 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -115,8 +115,6 @@ static struct davinci_i2c_platform_data i2c_pdata = {
 	.scl_pin        = 14,
 };
 
-static struct snd_platform_data dm355_evm_snd_data;
-
 static int dm355evm_mmc_gpios = -EINVAL;
 
 static void dm355evm_mmcsd_gpios(unsigned gpio)
@@ -411,7 +409,7 @@ static __init void dm355_evm_init(void)
 			ARRAY_SIZE(dm355_evm_spi_info));
 
 	/* DM335 EVM uses ASP1; line-out is a stereo mini-jack */
-	dm355_init_asp1(ASP1_TX_EVT_EN | ASP1_RX_EVT_EN, &dm355_evm_snd_data);
+	dm355_init_asp1(ASP1_TX_EVT_EN | ASP1_RX_EVT_EN);
 }
 
 MACHINE_START(DAVINCI_DM355_EVM, "DaVinci DM355 EVM")
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index f073518f621a..0464999b7137 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -176,10 +176,6 @@ static struct at24_platform_data eeprom_info = {
 	.context	= (void *)0x7f00,
 };
 
-static struct snd_platform_data dm365_evm_snd_data __maybe_unused = {
-	.asp_chan_q = EVENTQ_3,
-};
-
 static struct i2c_board_info i2c_info[] = {
 	{
 		I2C_BOARD_INFO("24c256", 0x50),
@@ -763,9 +759,9 @@ static __init void dm365_evm_init(void)
 	evm_init_cpld();
 
 #ifdef CONFIG_SND_DM365_AIC3X_CODEC
-	dm365_init_asp(&dm365_evm_snd_data);
+	dm365_init_asp();
 #elif defined(CONFIG_SND_DM365_VOICE_CODEC)
-	dm365_init_vc(&dm365_evm_snd_data);
+	dm365_init_vc();
 #endif
 	dm365_init_rtc();
 	dm365_init_ks(&dm365evm_ks_data);
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index ab47b8eb1b15..521e40977265 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -264,8 +264,6 @@ static struct platform_device rtc_dev = {
 	.id             = -1,
 };
 
-static struct snd_platform_data dm644x_evm_snd_data;
-
 /*----------------------------------------------------------------------*/
 #ifdef CONFIG_I2C
 /*
@@ -799,7 +797,7 @@ static __init void davinci_evm_init(void)
 	dm644x_init_video(&dm644xevm_capture_cfg, &dm644xevm_display_cfg);
 
 	davinci_serial_init(dm644x_serial_device);
-	dm644x_init_asp(&dm644x_evm_snd_data);
+	dm644x_init_asp();
 
 	/* irlml6401 switches over 1A, in under 8 msec */
 	davinci_setup_usb(1000, 8);
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index 8fcdcf87c47c..ad10017203c1 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -127,8 +127,6 @@ static struct platform_device davinci_fb_device = {
 	.num_resources = 0,
 };
 
-static struct snd_platform_data dm644x_ntosd2_snd_data;
-
 static struct gpio_led ntosd2_leds[] = {
 	{ .name = "led1_green", .gpio = GPIO(10), },
 	{ .name = "led1_red",   .gpio = GPIO(11), },
@@ -200,7 +198,7 @@ static __init void davinci_ntosd2_init(void)
 				ARRAY_SIZE(davinci_ntosd2_devices));
 
 	davinci_serial_init(dm644x_serial_device);
-	dm644x_init_asp(&dm644x_ntosd2_snd_data);
+	dm644x_init_asp();
 
 	soc_info->emac_pdata->phy_id = NEUROS_OSD2_PHY_ID;
 
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 239886299968..0d046accb35b 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -326,6 +326,20 @@ static struct clk mcasp_clk = {
 	.gpsc		= 1,
 };
 
+static struct clk mcbsp0_clk = {
+	.name		= "mcbsp0",
+	.parent		= &async3_clk,
+	.lpsc		= DA850_LPSC1_McBSP0,
+	.gpsc		= 1,
+};
+
+static struct clk mcbsp1_clk = {
+	.name		= "mcbsp1",
+	.parent		= &async3_clk,
+	.lpsc		= DA850_LPSC1_McBSP1,
+	.gpsc		= 1,
+};
+
 static struct clk lcdc_clk = {
 	.name		= "lcdc",
 	.parent		= &pll0_sysclk2,
@@ -482,6 +496,8 @@ static struct clk_lookup da850_clks[] = {
 	CLK("davinci_emac.1",	NULL,		&emac_clk),
 	CLK("davinci_mdio.0",	"fck",		&emac_clk),
 	CLK("davinci-mcasp.0",	NULL,		&mcasp_clk),
+	CLK("davinci-mcbsp.0",	NULL,		&mcbsp0_clk),
+	CLK("davinci-mcbsp.1",	NULL,		&mcbsp1_clk),
 	CLK("da8xx_lcdc.0",	"fck",		&lcdc_clk),
 	CLK("da830-mmc.0",	NULL,		&mmcsd0_clk),
 	CLK("da830-mmc.1",	NULL,		&mmcsd1_clk),
diff --git a/arch/arm/mach-davinci/davinci.h b/arch/arm/mach-davinci/davinci.h
index 4ffc37accce0..c62b90c6118a 100644
--- a/arch/arm/mach-davinci/davinci.h
+++ b/arch/arm/mach-davinci/davinci.h
@@ -85,14 +85,14 @@ int davinci_init_wdt(void);
 void dm355_init(void);
 void dm355_init_spi0(unsigned chipselect_mask,
 		const struct spi_board_info *info, unsigned len);
-void dm355_init_asp1(u32 evt_enable, struct snd_platform_data *pdata);
+void dm355_init_asp1(u32 evt_enable);
 int dm355_init_video(struct vpfe_config *, struct vpbe_config *);
 int dm355_gpio_register(void);
 
 /* DM365 function declarations */
 void dm365_init(void);
-void dm365_init_asp(struct snd_platform_data *pdata);
-void dm365_init_vc(struct snd_platform_data *pdata);
+void dm365_init_asp(void);
+void dm365_init_vc(void);
 void dm365_init_ks(struct davinci_ks_platform_data *pdata);
 void dm365_init_rtc(void);
 void dm365_init_spi0(unsigned chipselect_mask,
@@ -102,7 +102,7 @@ int dm365_gpio_register(void);
 
 /* DM644x function declarations */
 void dm644x_init(void);
-void dm644x_init_asp(struct snd_platform_data *pdata);
+void dm644x_init_asp(void);
 int dm644x_init_video(struct vpfe_config *, struct vpbe_config *);
 int dm644x_gpio_register(void);
 
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 5a19cca7ed6a..d33322ddedab 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -1035,7 +1035,7 @@ static struct davinci_soc_info davinci_soc_info_dm355 = {
 	.sram_len		= SZ_32K,
 };
 
-void __init dm355_init_asp1(u32 evt_enable, struct snd_platform_data *pdata)
+void __init dm355_init_asp1(u32 evt_enable)
 {
 	/* we don't use ASP1 IRQs, or we'd need to mux them ... */
 	if (evt_enable & ASP1_TX_EVT_EN)
@@ -1044,7 +1044,6 @@ void __init dm355_init_asp1(u32 evt_enable, struct snd_platform_data *pdata)
 	if (evt_enable & ASP1_RX_EVT_EN)
 		davinci_cfg_reg(DM355_EVT9_ASP1_RX);
 
-	dm355_asp1_device.dev.platform_data = pdata;
 	platform_device_register(&dm355_asp1_device);
 }
 
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 8aa004b02fe9..ef3add999263 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -1138,7 +1138,7 @@ static struct davinci_soc_info davinci_soc_info_dm365 = {
 	.sram_len		= SZ_32K,
 };
 
-void __init dm365_init_asp(struct snd_platform_data *pdata)
+void __init dm365_init_asp(void)
 {
 	davinci_cfg_reg(DM365_MCBSP0_BDX);
 	davinci_cfg_reg(DM365_MCBSP0_X);
@@ -1148,15 +1148,13 @@ void __init dm365_init_asp(struct snd_platform_data *pdata)
 	davinci_cfg_reg(DM365_MCBSP0_BFSR);
 	davinci_cfg_reg(DM365_EVT2_ASP_TX);
 	davinci_cfg_reg(DM365_EVT3_ASP_RX);
-	dm365_asp_device.dev.platform_data = pdata;
 	platform_device_register(&dm365_asp_device);
 }
 
-void __init dm365_init_vc(struct snd_platform_data *pdata)
+void __init dm365_init_vc(void)
 {
 	davinci_cfg_reg(DM365_EVT2_VC_TX);
 	davinci_cfg_reg(DM365_EVT3_VC_RX);
-	dm365_vc_device.dev.platform_data = pdata;
 	platform_device_register(&dm365_vc_device);
 }
 
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index 0afa279ec460..b437c3730f65 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -921,10 +921,9 @@ static struct davinci_soc_info davinci_soc_info_dm644x = {
 	.sram_len		= SZ_16K,
 };
 
-void __init dm644x_init_asp(struct snd_platform_data *pdata)
+void __init dm644x_init_asp(void)
 {
 	davinci_cfg_reg(DM644X_MCBSP);
-	dm644x_asp_device.dev.platform_data = pdata;
 	platform_device_register(&dm644x_asp_device);
 }
 
diff --git a/arch/arm/mach-davinci/psc.h b/arch/arm/mach-davinci/psc.h
index 99d47cfa301f..8af9f09fc10c 100644
--- a/arch/arm/mach-davinci/psc.h
+++ b/arch/arm/mach-davinci/psc.h
@@ -171,6 +171,8 @@
 #define DA8XX_LPSC1_I2C			11
 #define DA8XX_LPSC1_UART1		12
 #define DA8XX_LPSC1_UART2		13
+#define DA850_LPSC1_McBSP0		14
+#define DA850_LPSC1_McBSP1		15
 #define DA8XX_LPSC1_LCDC		16
 #define DA8XX_LPSC1_PWM			17
 #define DA850_LPSC1_MMC_SD1		18
diff --git a/arch/arm/mach-digicolor/Kconfig b/arch/arm/mach-digicolor/Kconfig
index fc65b0f1db48..9d05c6c4181d 100644
--- a/arch/arm/mach-digicolor/Kconfig
+++ b/arch/arm/mach-digicolor/Kconfig
@@ -1,10 +1,10 @@
 config ARCH_DIGICOLOR
 	bool "Conexant Digicolor SoC Support"
 	depends on ARCH_MULTI_V7
-	select ARCH_REQUIRE_GPIOLIB
 	select CLKSRC_MMIO
 	select DIGICOLOR_TIMER
 	select GENERIC_IRQ_CHIP
+	select GPIOLIB
 	select MFD_SYSCON
 	select PINCTRL
 	select PINCTRL_DIGICOLOR
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 20dcf6e904b2..8f820de890b4 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -12,13 +12,14 @@ menuconfig ARCH_EXYNOS
 	depends on ARCH_MULTI_V7
 	select ARCH_HAS_BANDGAP
 	select ARCH_HAS_HOLES_MEMORYMODEL
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_GIC
 	select COMMON_CLK_SAMSUNG
 	select EXYNOS_THERMAL
 	select EXYNOS_PMU
 	select EXYNOS_SROM
+	select EXYNOS_PM_DOMAINS if PM_GENERIC_DOMAINS
+	select GPIOLIB
 	select HAVE_ARM_SCU if SMP
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
diff --git a/arch/arm/mach-exynos/Makefile b/arch/arm/mach-exynos/Makefile
index 34d29df3e006..9ea6c54645ad 100644
--- a/arch/arm/mach-exynos/Makefile
+++ b/arch/arm/mach-exynos/Makefile
@@ -13,7 +13,6 @@ obj-$(CONFIG_ARCH_EXYNOS)	+= exynos.o exynos-smc.o firmware.o
 
 obj-$(CONFIG_EXYNOS_CPU_SUSPEND) += pm.o sleep.o
 obj-$(CONFIG_PM_SLEEP)		+= suspend.o
-obj-$(CONFIG_PM_GENERIC_DOMAINS) += pm_domains.o
 
 obj-$(CONFIG_SMP)		+= platsmp.o headsmp.o
 
@@ -23,5 +22,3 @@ AFLAGS_sleep.o			:=-Wa,-march=armv7-a$(plus_sec)
 
 obj-$(CONFIG_EXYNOS5420_MCPM)	+= mcpm-exynos.o
 CFLAGS_mcpm-exynos.o		+= -march=armv7-a
-
-obj-$(CONFIG_S5P_DEV_MFC)	+= s5p-dev-mfc.o
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index 5365bf1f586a..9424a8a9f308 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -166,7 +166,6 @@ extern struct cpuidle_exynos_data cpuidle_coupled_exynos_data;
 
 extern void exynos_set_delayed_reset_assertion(bool enable);
 
-extern void s5p_init_cpu(void __iomem *cpuid_addr);
 extern unsigned int samsung_rev(void);
 extern void exynos_core_restart(u32 core_id);
 extern int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr);
@@ -174,12 +173,12 @@ extern int exynos_get_boot_addr(u32 core_id, unsigned long *boot_addr);
 
 static inline void pmu_raw_writel(u32 val, u32 offset)
 {
-	__raw_writel(val, pmu_base_addr + offset);
+	writel_relaxed(val, pmu_base_addr + offset);
 }
 
 static inline u32 pmu_raw_readl(u32 offset)
 {
-	return __raw_readl(pmu_base_addr + offset);
+	return readl_relaxed(pmu_base_addr + offset);
 }
 
 #endif /* __ARCH_ARM_MACH_EXYNOS_COMMON_H */
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index 52ccf247e079..acabf0bffc5d 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -14,7 +14,6 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/irqchip.h>
 #include <linux/soc/samsung/exynos-regs-pmu.h>
@@ -25,9 +24,9 @@
 #include <asm/mach/map.h>
 
 #include <mach/map.h>
+#include <plat/cpu.h>
 
 #include "common.h"
-#include "mfc.h"
 
 static struct map_desc exynos4_iodesc[] __initdata = {
 	{
@@ -217,8 +216,6 @@ static void __init exynos_dt_machine_init(void)
 	    of_machine_is_compatible("samsung,exynos3250") ||
 	    of_machine_is_compatible("samsung,exynos5250"))
 		platform_device_register(&exynos_cpuidle);
-
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static char const *const exynos_dt_compat[] __initconst = {
@@ -237,23 +234,6 @@ static char const *const exynos_dt_compat[] __initconst = {
 	NULL
 };
 
-static void __init exynos_reserve(void)
-{
-#ifdef CONFIG_S5P_DEV_MFC
-	int i;
-	char *mfc_mem[] = {
-		"samsung,mfc-v5",
-		"samsung,mfc-v6",
-		"samsung,mfc-v7",
-		"samsung,mfc-v8",
-	};
-
-	for (i = 0; i < ARRAY_SIZE(mfc_mem); i++)
-		if (of_scan_flat_dt(s5p_fdt_alloc_mfc_mem, mfc_mem[i]))
-			break;
-#endif
-}
-
 static void __init exynos_dt_fixup(void)
 {
 	/*
@@ -275,6 +255,5 @@ DT_MACHINE_START(EXYNOS_DT, "SAMSUNG EXYNOS (Flattened Device Tree)")
 	.init_machine	= exynos_dt_machine_init,
 	.init_late	= exynos_init_late,
 	.dt_compat	= exynos_dt_compat,
-	.reserve	= exynos_reserve,
 	.dt_fixup	= exynos_dt_fixup,
 MACHINE_END
diff --git a/arch/arm/mach-exynos/firmware.c b/arch/arm/mach-exynos/firmware.c
index 1bfd1b0bd9dc..fd6da5419b51 100644
--- a/arch/arm/mach-exynos/firmware.c
+++ b/arch/arm/mach-exynos/firmware.c
@@ -41,9 +41,9 @@ static int exynos_do_idle(unsigned long mode)
 	case FW_DO_IDLE_AFTR:
 		if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9)
 			exynos_save_cp15();
-		__raw_writel(virt_to_phys(exynos_cpu_resume_ns),
-			     sysram_ns_base_addr + 0x24);
-		__raw_writel(EXYNOS_AFTR_MAGIC, sysram_ns_base_addr + 0x20);
+		writel_relaxed(virt_to_phys(exynos_cpu_resume_ns),
+			       sysram_ns_base_addr + 0x24);
+		writel_relaxed(EXYNOS_AFTR_MAGIC, sysram_ns_base_addr + 0x20);
 		if (soc_is_exynos3250()) {
 			flush_cache_all();
 			exynos_smc(SMC_CMD_SAVE, OP_TYPE_CORE,
@@ -97,7 +97,7 @@ static int exynos_set_cpu_boot_addr(int cpu, unsigned long boot_addr)
 	if (soc_is_exynos4412())
 		boot_reg += 4 * cpu;
 
-	__raw_writel(boot_addr, boot_reg);
+	writel_relaxed(boot_addr, boot_reg);
 	return 0;
 }
 
@@ -113,7 +113,7 @@ static int exynos_get_cpu_boot_addr(int cpu, unsigned long *boot_addr)
 	if (soc_is_exynos4412())
 		boot_reg += 4 * cpu;
 
-	*boot_addr = __raw_readl(boot_reg);
+	*boot_addr = readl_relaxed(boot_reg);
 	return 0;
 }
 
@@ -234,20 +234,20 @@ void exynos_set_boot_flag(unsigned int cpu, unsigned int mode)
 {
 	unsigned int tmp;
 
-	tmp = __raw_readl(REG_CPU_STATE_ADDR + cpu * 4);
+	tmp = readl_relaxed(REG_CPU_STATE_ADDR + cpu * 4);
 
 	if (mode & BOOT_MODE_MASK)
 		tmp &= ~BOOT_MODE_MASK;
 
 	tmp |= mode;
-	__raw_writel(tmp, REG_CPU_STATE_ADDR + cpu * 4);
+	writel_relaxed(tmp, REG_CPU_STATE_ADDR + cpu * 4);
 }
 
 void exynos_clear_boot_flag(unsigned int cpu, unsigned int mode)
 {
 	unsigned int tmp;
 
-	tmp = __raw_readl(REG_CPU_STATE_ADDR + cpu * 4);
+	tmp = readl_relaxed(REG_CPU_STATE_ADDR + cpu * 4);
 	tmp &= ~mode;
-	__raw_writel(tmp, REG_CPU_STATE_ADDR + cpu * 4);
+	writel_relaxed(tmp, REG_CPU_STATE_ADDR + cpu * 4);
 }
diff --git a/arch/arm/mach-exynos/headsmp.S b/arch/arm/mach-exynos/headsmp.S
index b54f9701e421..d3d24ab351ae 100644
--- a/arch/arm/mach-exynos/headsmp.S
+++ b/arch/arm/mach-exynos/headsmp.S
@@ -12,12 +12,15 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
+#include <asm/assembler.h>
+
 /*
  * exynos4 specific entry point for secondary CPUs.  This provides
  * a "holding pen" into which all secondary cores are held until we're
  * ready for them to initialise.
  */
 ENTRY(exynos4_secondary_startup)
+ARM_BE8(setend	be)
 	mrc	p15, 0, r0, c0, c0, 5
 	and	r0, r0, #15
 	adr	r4, 1f
diff --git a/arch/arm/mach-exynos/mfc.h b/arch/arm/mach-exynos/mfc.h
deleted file mode 100644
index dec93cd5b3c6..000000000000
--- a/arch/arm/mach-exynos/mfc.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * Copyright (C) 2013 Samsung Electronics Co.Ltd
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef __MACH_EXYNOS_MFC_H
-#define __MACH_EXYNOS_MFC_H __FILE__
-
-int __init s5p_fdt_alloc_mfc_mem(unsigned long node, const char *uname,
-				int depth, void *data);
-
-#endif /* __MACH_EXYNOS_MFC_H */
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 85c3be63d644..98ffe1e62ad5 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -264,7 +264,7 @@ int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr)
 			ret = PTR_ERR(boot_reg);
 			goto fail;
 		}
-		__raw_writel(boot_addr, boot_reg);
+		writel_relaxed(boot_addr, boot_reg);
 		ret = 0;
 	}
 fail:
@@ -289,7 +289,7 @@ int exynos_get_boot_addr(u32 core_id, unsigned long *boot_addr)
 			ret = PTR_ERR(boot_reg);
 			goto fail;
 		}
-		*boot_addr = __raw_readl(boot_reg);
+		*boot_addr = readl_relaxed(boot_reg);
 		ret = 0;
 	}
 fail:
diff --git a/arch/arm/mach-exynos/pm.c b/arch/arm/mach-exynos/pm.c
index c43b776a51a3..487295f4a56b 100644
--- a/arch/arm/mach-exynos/pm.c
+++ b/arch/arm/mach-exynos/pm.c
@@ -132,9 +132,9 @@ static void exynos_set_wakeupmask(long mask)
 
 static void exynos_cpu_set_boot_vector(long flags)
 {
-	__raw_writel(virt_to_phys(exynos_cpu_resume),
-		     exynos_boot_vector_addr());
-	__raw_writel(flags, exynos_boot_vector_flag());
+	writel_relaxed(virt_to_phys(exynos_cpu_resume),
+		       exynos_boot_vector_addr());
+	writel_relaxed(flags, exynos_boot_vector_flag());
 }
 
 static int exynos_aftr_finisher(unsigned long flags)
diff --git a/arch/arm/mach-exynos/s5p-dev-mfc.c b/arch/arm/mach-exynos/s5p-dev-mfc.c
deleted file mode 100644
index 8ef1f3ee4e98..000000000000
--- a/arch/arm/mach-exynos/s5p-dev-mfc.c
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * Copyright (C) 2010-2011 Samsung Electronics Co.Ltd
- *
- * Base S5P MFC resource and device definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/dma-mapping.h>
-#include <linux/memblock.h>
-#include <linux/ioport.h>
-#include <linux/of_fdt.h>
-#include <linux/of.h>
-
-static struct platform_device s5p_device_mfc_l;
-static struct platform_device s5p_device_mfc_r;
-
-struct s5p_mfc_dt_meminfo {
-	unsigned long	loff;
-	unsigned long	lsize;
-	unsigned long	roff;
-	unsigned long	rsize;
-	char		*compatible;
-};
-
-struct s5p_mfc_reserved_mem {
-	phys_addr_t	base;
-	unsigned long	size;
-	struct device	*dev;
-};
-
-static struct s5p_mfc_reserved_mem s5p_mfc_mem[2] __initdata;
-
-
-static void __init s5p_mfc_reserve_mem(phys_addr_t rbase, unsigned int rsize,
-				phys_addr_t lbase, unsigned int lsize)
-{
-	int i;
-
-	s5p_mfc_mem[0].dev = &s5p_device_mfc_r.dev;
-	s5p_mfc_mem[0].base = rbase;
-	s5p_mfc_mem[0].size = rsize;
-
-	s5p_mfc_mem[1].dev = &s5p_device_mfc_l.dev;
-	s5p_mfc_mem[1].base = lbase;
-	s5p_mfc_mem[1].size = lsize;
-
-	for (i = 0; i < ARRAY_SIZE(s5p_mfc_mem); i++) {
-		struct s5p_mfc_reserved_mem *area = &s5p_mfc_mem[i];
-		if (memblock_remove(area->base, area->size)) {
-			printk(KERN_ERR "Failed to reserve memory for MFC device (%ld bytes at 0x%08lx)\n",
-			       area->size, (unsigned long) area->base);
-			area->base = 0;
-		}
-	}
-}
-
-int __init s5p_fdt_alloc_mfc_mem(unsigned long node, const char *uname,
-				int depth, void *data)
-{
-	const __be32 *prop;
-	int len;
-	struct s5p_mfc_dt_meminfo mfc_mem;
-
-	if (!data)
-		return 0;
-
-	if (!of_flat_dt_is_compatible(node, data))
-		return 0;
-
-	prop = of_get_flat_dt_prop(node, "samsung,mfc-l", &len);
-	if (!prop || (len != 2 * sizeof(unsigned long)))
-		return 0;
-
-	mfc_mem.loff = be32_to_cpu(prop[0]);
-	mfc_mem.lsize = be32_to_cpu(prop[1]);
-
-	prop = of_get_flat_dt_prop(node, "samsung,mfc-r", &len);
-	if (!prop || (len != 2 * sizeof(unsigned long)))
-		return 0;
-
-	mfc_mem.roff = be32_to_cpu(prop[0]);
-	mfc_mem.rsize = be32_to_cpu(prop[1]);
-
-	s5p_mfc_reserve_mem(mfc_mem.roff, mfc_mem.rsize,
-			mfc_mem.loff, mfc_mem.lsize);
-
-	return 1;
-}
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index f21690937b7d..3750575c73c5 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -301,7 +301,7 @@ static int exynos5420_cpu_suspend(unsigned long arg)
 	unsigned int cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 	unsigned int cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 
-	__raw_writel(0x0, sysram_base_addr + EXYNOS5420_CPU_STATE);
+	writel_relaxed(0x0, sysram_base_addr + EXYNOS5420_CPU_STATE);
 
 	if (IS_ENABLED(CONFIG_EXYNOS5420_MCPM)) {
 		mcpm_set_entry_vector(cpu, cluster, exynos_cpu_resume);
@@ -373,8 +373,8 @@ static void exynos5420_pm_prepare(void)
 	 * needs to restore it back in case, the primary cpu fails to
 	 * suspend for any reason.
 	 */
-	exynos5420_cpu_state = __raw_readl(sysram_base_addr +
-						EXYNOS5420_CPU_STATE);
+	exynos5420_cpu_state = readl_relaxed(sysram_base_addr +
+					     EXYNOS5420_CPU_STATE);
 
 	exynos_pm_enter_sleep_mode();
 
@@ -504,11 +504,11 @@ static void exynos5420_pm_resume(void)
 	/* Restore the CPU0 low power state register */
 	tmp = pmu_raw_readl(EXYNOS5_ARM_CORE0_SYS_PWR_REG);
 	pmu_raw_writel(tmp | S5P_CORE_LOCAL_PWR_EN,
-		EXYNOS5_ARM_CORE0_SYS_PWR_REG);
+		       EXYNOS5_ARM_CORE0_SYS_PWR_REG);
 
 	/* Restore the sysram cpu state register */
-	__raw_writel(exynos5420_cpu_state,
-		sysram_base_addr + EXYNOS5420_CPU_STATE);
+	writel_relaxed(exynos5420_cpu_state,
+		       sysram_base_addr + EXYNOS5420_CPU_STATE);
 
 	pmu_raw_writel(EXYNOS5420_USE_STANDBY_WFI_ALL,
 			S5P_CENTRAL_SEQ_OPTION);
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index 6050a14faee6..07f60986dc2c 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -23,7 +23,6 @@
 #include <linux/pl320-ipc.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
 #include <linux/of_address.h>
 #include <linux/reboot.h>
 #include <linux/amba/bus.h>
@@ -163,8 +162,6 @@ static void __init highbank_init(void)
 
 	pl320_ipc_register_notifier(&hb_keys_nb);
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-
 	if (psci_ops.cpu_suspend)
 		platform_device_register(&highbank_cpuidle_device);
 }
diff --git a/arch/arm/mach-hisi/hisilicon.c b/arch/arm/mach-hisi/hisilicon.c
index 8cc62150116a..c08c44ec5175 100644
--- a/arch/arm/mach-hisi/hisilicon.c
+++ b/arch/arm/mach-hisi/hisilicon.c
@@ -53,31 +53,3 @@ DT_MACHINE_START(HI3620, "Hisilicon Hi3620 (Flattened Device Tree)")
 	.map_io		= hi3620_map_io,
 	.dt_compat	= hi3xxx_compat,
 MACHINE_END
-
-static const char *const hix5hd2_compat[] __initconst = {
-	"hisilicon,hix5hd2",
-	NULL,
-};
-
-DT_MACHINE_START(HIX5HD2_DT, "Hisilicon HIX5HD2 (Flattened Device Tree)")
-	.dt_compat	= hix5hd2_compat,
-MACHINE_END
-
-static const char *const hip04_compat[] __initconst = {
-	"hisilicon,hip04-d01",
-	NULL,
-};
-
-DT_MACHINE_START(HIP04, "Hisilicon HiP04 (Flattened Device Tree)")
-	.dt_compat	= hip04_compat,
-MACHINE_END
-
-static const char *const hip01_compat[] __initconst = {
-	"hisilicon,hip01",
-	"hisilicon,hip01-ca9x2",
-	NULL,
-};
-
-DT_MACHINE_START(HIP01, "Hisilicon HIP01 (Flattened Device Tree)")
-	.dt_compat      = hip01_compat,
-MACHINE_END
diff --git a/arch/arm/mach-hisi/platsmp.c b/arch/arm/mach-hisi/platsmp.c
index 47ed32cf57cc..e1d67648d5d0 100644
--- a/arch/arm/mach-hisi/platsmp.c
+++ b/arch/arm/mach-hisi/platsmp.c
@@ -103,7 +103,7 @@ static void __init hisi_common_smp_prepare_cpus(unsigned int max_cpus)
 	hisi_enable_scu_a9();
 }
 
-void hix5hd2_set_scu_boot_addr(phys_addr_t start_addr, phys_addr_t jump_addr)
+static void hix5hd2_set_scu_boot_addr(phys_addr_t start_addr, phys_addr_t jump_addr)
 {
 	void __iomem *virt;
 
@@ -139,7 +139,7 @@ static const struct smp_operations hix5hd2_smp_ops __initconst = {
 #define HIP01_BOOT_ADDRESS     0x80000000
 #define REG_SC_CTRL            0x000
 
-void hip01_set_boot_addr(phys_addr_t start_addr, phys_addr_t jump_addr)
+static void hip01_set_boot_addr(phys_addr_t start_addr, phys_addr_t jump_addr)
 {
 	void __iomem *virt;
 
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index dd905b9602a0..ee9a318cab31 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -1,10 +1,10 @@
 menuconfig ARCH_MXC
 	bool "Freescale i.MX family"
 	depends on ARCH_MULTI_V4_V5 || ARCH_MULTI_V6_V7 || ARM_SINGLE_ARMV7M
-	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select CLKSRC_IMX_GPT
 	select GENERIC_IRQ_CHIP
+	select GPIOLIB
 	select PINCTRL
 	select PM_OPP if PM
 	select SOC_BUS
@@ -44,9 +44,6 @@ config MXC_USE_EPIT
 	  uses the same clocks as the GPT. Anyway, on some systems the GPT
 	  may be in use for other purposes.
 
-config ARCH_HAS_RNGA
-	bool
-
 config HAVE_IMX_ANATOP
 	bool
 
@@ -90,7 +87,6 @@ config SOC_IMX27
 config SOC_IMX31
 	bool
 	select CPU_V6
-	select IMX_HAVE_PLATFORM_MXC_RNGA
 	select MXC_AVIC
 	select SMP_ON_UP if SMP
 
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index 9fbe624a5ef9..9f5fffd62702 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -8,8 +8,8 @@ obj-$(CONFIG_SOC_IMX25) += cpu-imx25.o mach-imx25.o pm-imx25.o
 obj-$(CONFIG_SOC_IMX27) += cpu-imx27.o pm-imx27.o
 obj-$(CONFIG_SOC_IMX27) += mm-imx27.o ehci-imx27.o
 
-obj-$(CONFIG_SOC_IMX31) += mm-imx3.o cpu-imx31.o iomux-imx31.o ehci-imx31.o pm-imx3.o
-obj-$(CONFIG_SOC_IMX35) += mm-imx3.o cpu-imx35.o ehci-imx35.o pm-imx3.o
+obj-$(CONFIG_SOC_IMX31) += mm-imx3.o cpu-imx31.o iomux-imx31.o ehci-imx31.o
+obj-$(CONFIG_SOC_IMX35) += mm-imx3.o cpu-imx35.o ehci-imx35.o
 
 imx5-pm-$(CONFIG_PM) += pm-imx5.o
 obj-$(CONFIG_SOC_IMX5) += cpu-imx5.o $(imx5-pm-y)
diff --git a/arch/arm/mach-imx/avic.c b/arch/arm/mach-imx/avic.c
index 7fa176e792bd..1afccae0420c 100644
--- a/arch/arm/mach-imx/avic.c
+++ b/arch/arm/mach-imx/avic.c
@@ -55,23 +55,20 @@ static void __iomem *avic_base;
 static struct irq_domain *domain;
 
 #ifdef CONFIG_FIQ
-static int avic_set_irq_fiq(unsigned int irq, unsigned int type)
+static int avic_set_irq_fiq(unsigned int hwirq, unsigned int type)
 {
-	struct irq_data *d = irq_get_irq_data(irq);
 	unsigned int irqt;
 
-	irq = d->hwirq;
-
-	if (irq >= AVIC_NUM_IRQS)
+	if (hwirq >= AVIC_NUM_IRQS)
 		return -EINVAL;
 
-	if (irq < AVIC_NUM_IRQS / 2) {
-		irqt = imx_readl(avic_base + AVIC_INTTYPEL) & ~(1 << irq);
-		imx_writel(irqt | (!!type << irq), avic_base + AVIC_INTTYPEL);
+	if (hwirq < AVIC_NUM_IRQS / 2) {
+		irqt = imx_readl(avic_base + AVIC_INTTYPEL) & ~(1 << hwirq);
+		imx_writel(irqt | (!!type << hwirq), avic_base + AVIC_INTTYPEL);
 	} else {
-		irq -= AVIC_NUM_IRQS / 2;
-		irqt = imx_readl(avic_base + AVIC_INTTYPEH) & ~(1 << irq);
-		imx_writel(irqt | (!!type << irq), avic_base + AVIC_INTTYPEH);
+		hwirq -= AVIC_NUM_IRQS / 2;
+		irqt = imx_readl(avic_base + AVIC_INTTYPEH) & ~(1 << hwirq);
+		imx_writel(irqt | (!!type << hwirq), avic_base + AVIC_INTTYPEH);
 	}
 
 	return 0;
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 58a38464480d..a8f469333027 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -32,7 +32,6 @@ void imx27_init_early(void);
 void imx31_init_early(void);
 void imx35_init_early(void);
 void mxc_init_irq(void __iomem *);
-void tzic_init_irq(void);
 void mx1_init_irq(void);
 void mx21_init_irq(void);
 void mx27_init_irq(void);
@@ -55,6 +54,7 @@ struct platform_device *mxc_register_gpio(char *name, int id,
 void mxc_set_cpu_type(unsigned int type);
 void mxc_restart(enum reboot_mode, const char *);
 void mxc_arch_reset_init(void __iomem *);
+void imx1_reset_init(void __iomem *);
 void imx_set_aips(void __iomem *);
 void imx_aips_allow_unprivileged_access(const char *compat);
 int mxc_device_init(void);
@@ -67,6 +67,7 @@ void imx_gpc_set_arm_power_in_lpm(bool power_off);
 void imx_gpc_set_arm_power_up_timing(u32 sw2iso, u32 sw);
 void imx_gpc_set_arm_power_down_timing(u32 sw2iso, u32 sw);
 void imx25_pm_init(void);
+void imx27_pm_init(void);
 
 enum mxc_cpu_pwr_mode {
 	WAIT_CLOCKED,		/* wfi only */
diff --git a/arch/arm/mach-imx/cpu-imx5.c b/arch/arm/mach-imx/cpu-imx5.c
index 3403bac94a31..4f2d1c772f85 100644
--- a/arch/arm/mach-imx/cpu-imx5.c
+++ b/arch/arm/mach-imx/cpu-imx5.c
@@ -60,13 +60,9 @@ static int get_mx51_srev(void)
 /*
  * Returns:
  *	the silicon revision of the cpu
- *	-EINVAL - not a mx51
  */
 int mx51_revision(void)
 {
-	if (!cpu_is_mx51())
-		return -EINVAL;
-
 	if (mx5_cpu_rev == -1)
 		mx5_cpu_rev = get_mx51_srev();
 
@@ -112,13 +108,9 @@ static int get_mx53_srev(void)
 /*
  * Returns:
  *	the silicon revision of the cpu
- *	-EINVAL - not a mx53
  */
 int mx53_revision(void)
 {
-	if (!cpu_is_mx53())
-		return -EINVAL;
-
 	if (mx5_cpu_rev == -1)
 		mx5_cpu_rev = get_mx53_srev();
 
diff --git a/arch/arm/mach-imx/cpu.c b/arch/arm/mach-imx/cpu.c
index 6a96b7cf468f..b3347d32349f 100644
--- a/arch/arm/mach-imx/cpu.c
+++ b/arch/arm/mach-imx/cpu.c
@@ -10,8 +10,6 @@
 #include "common.h"
 
 unsigned int __mxc_cpu_type;
-EXPORT_SYMBOL(__mxc_cpu_type);
-
 static unsigned int imx_soc_revision;
 
 void mxc_set_cpu_type(unsigned int type)
diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c
index 353bb8774112..db0f48c4b17e 100644
--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -10,6 +10,8 @@
 #include <linux/module.h>
 #include <asm/cpuidle.h>
 
+#include <soc/imx/cpuidle.h>
+
 #include "common.h"
 #include "cpuidle.h"
 #include "hardware.h"
@@ -62,6 +64,24 @@ static struct cpuidle_driver imx6q_cpuidle_driver = {
 	.safe_state_index = 0,
 };
 
+/*
+ * i.MX6 Q/DL has an erratum (ERR006687) that prevents the FEC from waking the
+ * CPUs when they are in wait(unclocked) state. As the hardware workaround isn't
+ * applicable to all boards, disable the deeper idle state when the workaround
+ * isn't present and the FEC is in use.
+ */
+void imx6q_cpuidle_fec_irqs_used(void)
+{
+	imx6q_cpuidle_driver.states[1].disabled = true;
+}
+EXPORT_SYMBOL_GPL(imx6q_cpuidle_fec_irqs_used);
+
+void imx6q_cpuidle_fec_irqs_unused(void)
+{
+	imx6q_cpuidle_driver.states[1].disabled = false;
+}
+EXPORT_SYMBOL_GPL(imx6q_cpuidle_fec_irqs_unused);
+
 int __init imx6q_cpuidle_init(void)
 {
 	/* Set INT_MEM_CLK_LPM bit to get a reliable WAIT mode support */
diff --git a/arch/arm/mach-imx/devices/Kconfig b/arch/arm/mach-imx/devices/Kconfig
index 3a552989248e..6ffe57267233 100644
--- a/arch/arm/mach-imx/devices/Kconfig
+++ b/arch/arm/mach-imx/devices/Kconfig
@@ -57,10 +57,6 @@ config IMX_HAVE_PLATFORM_MXC_MMC
 config IMX_HAVE_PLATFORM_MXC_NAND
 	bool
 
-config IMX_HAVE_PLATFORM_MXC_RNGA
-	bool
-	select ARCH_HAS_RNGA
-
 config IMX_HAVE_PLATFORM_MXC_RTC
 	bool
 
diff --git a/arch/arm/mach-imx/devices/devices.c b/arch/arm/mach-imx/devices/devices.c
index 8eab5440da28..300451727362 100644
--- a/arch/arm/mach-imx/devices/devices.c
+++ b/arch/arm/mach-imx/devices/devices.c
@@ -22,6 +22,9 @@
 #include <linux/err.h>
 #include <linux/platform_device.h>
 
+#include "../common.h"
+#include "devices-common.h"
+
 struct device mxc_aips_bus = {
 	.init_name	= "mxc_aips",
 };
diff --git a/arch/arm/mach-imx/devices/platform-gpio-mxc.c b/arch/arm/mach-imx/devices/platform-gpio-mxc.c
index 26483fa94b75..cd1fe69d8807 100644
--- a/arch/arm/mach-imx/devices/platform-gpio-mxc.c
+++ b/arch/arm/mach-imx/devices/platform-gpio-mxc.c
@@ -7,6 +7,7 @@
  * Free Software Foundation.
  */
 #include "devices-common.h"
+#include "../common.h"
 
 struct platform_device *__init mxc_register_gpio(char *name, int id,
 	resource_size_t iobase, resource_size_t iosize, int irq, int irq_high)
diff --git a/arch/arm/mach-imx/devices/platform-mxc_rnga.c b/arch/arm/mach-imx/devices/platform-mxc_rnga.c
deleted file mode 100644
index 851fbc8af7a9..000000000000
--- a/arch/arm/mach-imx/devices/platform-mxc_rnga.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * Copyright (C) 2010 Pengutronix
- * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
- *
- * This program is free software; you can redistribute it and/or modify it under
- * the terms of the GNU General Public License version 2 as published by the
- * Free Software Foundation.
- */
-#include "../hardware.h"
-#include "devices-common.h"
-
-struct imx_mxc_rnga_data {
-	resource_size_t iobase;
-};
-
-#define imx_mxc_rnga_data_entry_single(soc)				\
-	{								\
-		.iobase = soc ## _RNGA_BASE_ADDR,			\
-	}
-
-#ifdef CONFIG_SOC_IMX31
-static const struct imx_mxc_rnga_data imx31_mxc_rnga_data __initconst =
-	imx_mxc_rnga_data_entry_single(MX31);
-#endif /* ifdef CONFIG_SOC_IMX31 */
-
-static struct platform_device *__init imx_add_mxc_rnga(
-		const struct imx_mxc_rnga_data *data)
-{
-	struct resource res[] = {
-		{
-			.start = data->iobase,
-			.end = data->iobase + SZ_16K - 1,
-			.flags = IORESOURCE_MEM,
-		},
-	};
-	return imx_add_platform_device("mxc_rnga", -1,
-			res, ARRAY_SIZE(res), NULL, 0);
-}
-
-static int __init imxXX_add_mxc_rnga(void)
-{
-	struct platform_device *ret;
-
-#if defined(CONFIG_SOC_IMX31)
-	if (cpu_is_mx31())
-		ret = imx_add_mxc_rnga(&imx31_mxc_rnga_data);
-	else
-#endif /* if defined(CONFIG_SOC_IMX31) */
-		ret = ERR_PTR(-ENODEV);
-
-	return PTR_ERR_OR_ZERO(ret);
-}
-arch_initcall(imxXX_add_mxc_rnga);
diff --git a/arch/arm/mach-imx/eukrea-baseboards.h b/arch/arm/mach-imx/eukrea-baseboards.h
deleted file mode 100644
index bb2c90d65914..000000000000
--- a/arch/arm/mach-imx/eukrea-baseboards.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * Copyright (C) 2010 Eric Benard - eric@eukrea.com
- *
- * Based on board-pcm038.h which is :
- * Copyright (C) 2008 Juergen Beisert (kernel@pengutronix.de)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef __MACH_EUKREA_BASEBOARDS_H__
-#define __MACH_EUKREA_BASEBOARDS_H__
-
-#ifndef __ASSEMBLY__
-/*
- * This CPU module needs a baseboard to work. After basic initializing
- * its own devices, it calls baseboard's init function.
- * TODO: Add your own baseboard init function and call it from
- * inside eukrea_cpuimx25_init() or eukrea_cpuimx35_init()
- *
- * This example here is for the development board. Refer
- * mach-mx25/eukrea_mbimxsd-baseboard.c for cpuimx25
- * mach-mx3/eukrea_mbimxsd-baseboard.c for cpuimx35
- */
-
-extern void eukrea_mbimxsd25_baseboard_init(void);
-extern void eukrea_mbimxsd35_baseboard_init(void);
-
-#endif
-
-#endif /* __MACH_EUKREA_BASEBOARDS_H__ */
diff --git a/arch/arm/mach-imx/imx27-dt.c b/arch/arm/mach-imx/imx27-dt.c
index 530a728c2acc..a754b8a48f38 100644
--- a/arch/arm/mach-imx/imx27-dt.c
+++ b/arch/arm/mach-imx/imx27-dt.c
@@ -27,5 +27,6 @@ DT_MACHINE_START(IMX27_DT, "Freescale i.MX27 (Device Tree Support)")
 	.map_io		= mx27_map_io,
 	.init_early	= imx27_init_early,
 	.init_irq	= mx27_init_irq,
+	.init_late	= imx27_pm_init,
 	.dt_compat	= imx27_dt_board_compat,
 MACHINE_END
diff --git a/arch/arm/mach-imx/imx31-dt.c b/arch/arm/mach-imx/imx31-dt.c
index 32100222a017..62e6b4fb5370 100644
--- a/arch/arm/mach-imx/imx31-dt.c
+++ b/arch/arm/mach-imx/imx31-dt.c
@@ -28,10 +28,22 @@ static void __init imx31_dt_timer_init(void)
 	mx31_clocks_init_dt();
 }
 
+/* FIXME: replace with DT binding */
+static const struct resource imx31_rnga_res[] __initconst = {
+	DEFINE_RES_MEM(MX31_RNGA_BASE_ADDR, SZ_16K),
+};
+
+static void __init imx31_dt_mach_init(void)
+{
+	platform_device_register_simple("mxc_rnga", -1, imx31_rnga_res,
+					ARRAY_SIZE(imx31_rnga_res));
+}
+
 DT_MACHINE_START(IMX31_DT, "Freescale i.MX31 (Device Tree Support)")
 	.map_io		= mx31_map_io,
 	.init_early	= imx31_init_early,
 	.init_irq	= mx31_init_irq,
 	.init_time	= imx31_dt_timer_init,
+	.init_machine	= imx31_dt_mach_init,
 	.dt_compat	= imx31_dt_board_compat,
 MACHINE_END
diff --git a/arch/arm/mach-imx/imx35-dt.c b/arch/arm/mach-imx/imx35-dt.c
index e9396037235d..99bb63dedb87 100644
--- a/arch/arm/mach-imx/imx35-dt.c
+++ b/arch/arm/mach-imx/imx35-dt.c
@@ -20,20 +20,16 @@
 #include "common.h"
 #include "mx35.h"
 
-static void __init imx35_irq_init(void)
-{
-	imx_init_l2cache();
-	mx35_init_irq();
-}
-
 static const char * const imx35_dt_board_compat[] __initconst = {
 	"fsl,imx35",
 	NULL
 };
 
 DT_MACHINE_START(IMX35_DT, "Freescale i.MX35 (Device Tree Support)")
+	.l2c_aux_val 	= 0,
+	.l2c_aux_mask	= ~0,
 	.map_io		= mx35_map_io,
 	.init_early	= imx35_init_early,
-	.init_irq	= imx35_irq_init,
+	.init_irq	= mx35_init_irq,
 	.dt_compat	= imx35_dt_board_compat,
 MACHINE_END
diff --git a/arch/arm/mach-imx/irq-common.c b/arch/arm/mach-imx/irq-common.c
index 0a920d184867..210d36eba8f2 100644
--- a/arch/arm/mach-imx/irq-common.c
+++ b/arch/arm/mach-imx/irq-common.c
@@ -33,8 +33,10 @@ int mxc_set_irq_fiq(unsigned int irq, unsigned int type)
 	gc = irq_get_chip_data(irq);
 	if (gc && gc->private) {
 		exirq = gc->private;
-		if (exirq->set_irq_fiq)
-			ret = exirq->set_irq_fiq(irq, type);
+		if (exirq->set_irq_fiq) {
+			struct irq_data *d = irq_get_irq_data(irq);
+			ret = exirq->set_irq_fiq(irqd_to_hwirq(d), type);
+		}
 	}
 
 	return ret;
diff --git a/arch/arm/mach-imx/mach-imx50.c b/arch/arm/mach-imx/mach-imx50.c
index ecf58b9e974b..4cab5f61260f 100644
--- a/arch/arm/mach-imx/mach-imx50.c
+++ b/arch/arm/mach-imx/mach-imx50.c
@@ -22,6 +22,5 @@ static const char * const imx50_dt_board_compat[] __initconst = {
 };
 
 DT_MACHINE_START(IMX50_DT, "Freescale i.MX50 (Device Tree Support)")
-	.init_irq	= tzic_init_irq,
 	.dt_compat	= imx50_dt_board_compat,
 MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx51.c b/arch/arm/mach-imx/mach-imx51.c
index 10a82a4f1e58..3835b6a3423c 100644
--- a/arch/arm/mach-imx/mach-imx51.c
+++ b/arch/arm/mach-imx/mach-imx51.c
@@ -53,7 +53,7 @@ static void __init imx51_dt_init(void)
 	imx51_ipu_mipi_setup();
 	imx_src_init();
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+	imx_aips_allow_unprivileged_access("fsl,imx51-aipstz");
 }
 
 static void __init imx51_init_late(void)
@@ -69,7 +69,6 @@ static const char * const imx51_dt_board_compat[] __initconst = {
 
 DT_MACHINE_START(IMX51_DT, "Freescale i.MX51 (Device Tree Support)")
 	.init_early	= imx51_init_early,
-	.init_irq	= tzic_init_irq,
 	.init_machine	= imx51_dt_init,
 	.init_late	= imx51_init_late,
 	.dt_compat	= imx51_dt_board_compat,
diff --git a/arch/arm/mach-imx/mach-imx53.c b/arch/arm/mach-imx/mach-imx53.c
index 18b5c5c136db..07c2e8dca494 100644
--- a/arch/arm/mach-imx/mach-imx53.c
+++ b/arch/arm/mach-imx/mach-imx53.c
@@ -32,8 +32,6 @@ static void __init imx53_dt_init(void)
 {
 	imx_src_init();
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-
 	imx_aips_allow_unprivileged_access("fsl,imx53-aipstz");
 }
 
@@ -49,7 +47,6 @@ static const char * const imx53_dt_board_compat[] __initconst = {
 
 DT_MACHINE_START(IMX53_DT, "Freescale i.MX53 (Device Tree Support)")
 	.init_early	= imx53_init_early,
-	.init_irq	= tzic_init_irq,
 	.init_machine	= imx53_dt_init,
 	.init_late	= imx53_init_late,
 	.dt_compat	= imx53_dt_board_compat,
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index cb27d566d5ab..97fd25105e2c 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -220,7 +220,7 @@ static void __init imx6q_1588_init(void)
 				IMX6Q_GPR1_ENET_CLK_SEL_MASK,
 				clksel);
 	else
-		pr_err("failed to find fsl,imx6q-iomux-gpr regmap\n");
+		pr_err("failed to find fsl,imx6q-iomuxc-gpr regmap\n");
 
 	clk_put(enet_ref);
 put_ptp_clk:
@@ -278,7 +278,7 @@ static void __init imx6q_init_machine(void)
 
 	imx6q_enet_phy_init();
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, parent);
+	of_platform_default_populate(NULL, NULL, parent);
 
 	imx_anatop_init();
 	cpu_is_imx6q() ?  imx6q_pm_init() : imx6dl_pm_init();
@@ -407,6 +407,8 @@ static const char * const imx6q_dt_compat[] __initconst = {
 };
 
 DT_MACHINE_START(IMX6Q, "Freescale i.MX6 Quad/DualLite (Device Tree)")
+	.l2c_aux_val 	= 0,
+	.l2c_aux_mask	= ~0,
 	.smp		= smp_ops(imx_smp_ops),
 	.map_io		= imx6q_map_io,
 	.init_irq	= imx6q_init_irq,
diff --git a/arch/arm/mach-imx/mach-imx6sl.c b/arch/arm/mach-imx/mach-imx6sl.c
index 300326373166..04084900d810 100644
--- a/arch/arm/mach-imx/mach-imx6sl.c
+++ b/arch/arm/mach-imx/mach-imx6sl.c
@@ -52,7 +52,7 @@ static void __init imx6sl_init_machine(void)
 	if (parent == NULL)
 		pr_warn("failed to initialize soc device\n");
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, parent);
+	of_platform_default_populate(NULL, NULL, parent);
 
 	imx6sl_fec_init();
 	imx_anatop_init();
@@ -75,6 +75,8 @@ static const char * const imx6sl_dt_compat[] __initconst = {
 };
 
 DT_MACHINE_START(IMX6SL, "Freescale i.MX6 SoloLite (Device Tree)")
+	.l2c_aux_val 	= 0,
+	.l2c_aux_mask	= ~0,
 	.init_irq	= imx6sl_init_irq,
 	.init_machine	= imx6sl_init_machine,
 	.init_late      = imx6sl_init_late,
diff --git a/arch/arm/mach-imx/mach-imx6sx.c b/arch/arm/mach-imx/mach-imx6sx.c
index 6a0b0614de29..7f52d9b1e8a4 100644
--- a/arch/arm/mach-imx/mach-imx6sx.c
+++ b/arch/arm/mach-imx/mach-imx6sx.c
@@ -72,7 +72,7 @@ static void __init imx6sx_init_machine(void)
 	if (parent == NULL)
 		pr_warn("failed to initialize soc device\n");
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, parent);
+	of_platform_default_populate(NULL, NULL, parent);
 
 	imx6sx_enet_init();
 	imx_anatop_init();
@@ -103,6 +103,8 @@ static const char * const imx6sx_dt_compat[] __initconst = {
 };
 
 DT_MACHINE_START(IMX6SX, "Freescale i.MX6 SoloX (Device Tree)")
+	.l2c_aux_val 	= 0,
+	.l2c_aux_mask	= ~0,
 	.init_irq	= imx6sx_init_irq,
 	.init_machine	= imx6sx_init_machine,
 	.dt_compat	= imx6sx_dt_compat,
diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c
index b56de4b8cdf2..5d9bfab279dd 100644
--- a/arch/arm/mach-imx/mach-imx6ul.c
+++ b/arch/arm/mach-imx/mach-imx6ul.c
@@ -64,7 +64,6 @@ static void __init imx6ul_init_machine(void)
 	if (parent == NULL)
 		pr_warn("failed to initialize soc device\n");
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	imx6ul_enet_init();
 	imx_anatop_init();
 	imx6ul_pm_init();
diff --git a/arch/arm/mach-imx/mach-imx7d.c b/arch/arm/mach-imx/mach-imx7d.c
index b450f525a670..26ca744d3e2b 100644
--- a/arch/arm/mach-imx/mach-imx7d.c
+++ b/arch/arm/mach-imx/mach-imx7d.c
@@ -93,7 +93,6 @@ static void __init imx7d_init_machine(void)
 	if (parent == NULL)
 		pr_warn("failed to initialize soc device\n");
 
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	imx_anatop_init();
 	imx7d_enet_init();
 }
@@ -107,6 +106,7 @@ static void __init imx7d_init_irq(void)
 
 static const char *const imx7d_dt_compat[] __initconst = {
 	"fsl,imx7d",
+	"fsl,imx7s",
 	NULL,
 };
 
diff --git a/arch/arm/mach-imx/mm-imx1.c b/arch/arm/mach-imx/mm-imx1.c
index e065fedb3ad4..9a42f19be81e 100644
--- a/arch/arm/mach-imx/mm-imx1.c
+++ b/arch/arm/mach-imx/mm-imx1.c
@@ -50,7 +50,7 @@ void __init mx1_init_irq(void)
 
 void __init imx1_soc_init(void)
 {
-	mxc_arch_reset_init(MX1_IO_ADDRESS(MX1_WDT_BASE_ADDR));
+	imx1_reset_init(MX1_IO_ADDRESS(MX1_WDT_BASE_ADDR));
 	mxc_device_init();
 
 	mxc_register_gpio("imx1-gpio", 0, MX1_GPIO1_BASE_ADDR, SZ_256,
diff --git a/arch/arm/mach-imx/mm-imx27.c b/arch/arm/mach-imx/mm-imx27.c
index 7d82a5a5b16b..862b9b7762c7 100644
--- a/arch/arm/mach-imx/mm-imx27.c
+++ b/arch/arm/mach-imx/mm-imx27.c
@@ -98,4 +98,6 @@ void __init imx27_soc_init(void)
 	/* imx27 has the imx21 type audmux */
 	platform_device_register_simple("imx21-audmux", 0, imx27_audmux_res,
 					ARRAY_SIZE(imx27_audmux_res));
+
+	imx27_pm_init();
 }
diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c
index 0884ca90d15a..7638a35b3b36 100644
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/err.h>
+#include <linux/io.h>
 #include <linux/pinctrl/machine.h>
 
 #include <asm/pgtable.h>
@@ -38,8 +39,6 @@ static void imx3_idle(void)
 {
 	unsigned long reg = 0;
 
-	mx3_cpu_lp_set(MX3_WAIT);
-
 	__asm__ __volatile__(
 		/* disable I and D cache */
 		"mrc p15, 0, %0, c1, c0, 0\n"
@@ -135,11 +134,20 @@ void __init mx31_map_io(void)
 	iotable_init(mx31_io_desc, ARRAY_SIZE(mx31_io_desc));
 }
 
+static void imx31_idle(void)
+{
+	int reg = imx_readl(mx3_ccm_base + MXC_CCM_CCMR);
+	reg &= ~MXC_CCM_CCMR_LPM_MASK;
+	imx_writel(reg, mx3_ccm_base + MXC_CCM_CCMR);
+
+	imx3_idle();
+}
+
 void __init imx31_init_early(void)
 {
 	mxc_set_cpu_type(MXC_CPU_MX31);
 	arch_ioremap_caller = imx3_ioremap_caller;
-	arm_pm_idle = imx3_idle;
+	arm_pm_idle = imx31_idle;
 	mx3_ccm_base = MX31_IO_ADDRESS(MX31_CCM_BASE_ADDR);
 }
 
@@ -167,6 +175,10 @@ static const struct resource imx31_audmux_res[] __initconst = {
 	DEFINE_RES_MEM(MX31_AUDMUX_BASE_ADDR, SZ_16K),
 };
 
+static const struct resource imx31_rnga_res[] __initconst = {
+	DEFINE_RES_MEM(MX31_RNGA_BASE_ADDR, SZ_16K),
+};
+
 void __init imx31_soc_init(void)
 {
 	int to_version = mx31_revision() >> 4;
@@ -195,6 +207,8 @@ void __init imx31_soc_init(void)
 
 	platform_device_register_simple("imx31-audmux", 0, imx31_audmux_res,
 					ARRAY_SIZE(imx31_audmux_res));
+	platform_device_register_simple("mxc_rnga", -1, imx31_rnga_res,
+					ARRAY_SIZE(imx31_rnga_res));
 }
 #endif /* ifdef CONFIG_SOC_IMX31 */
 
@@ -212,11 +226,21 @@ void __init mx35_map_io(void)
 	iotable_init(mx35_io_desc, ARRAY_SIZE(mx35_io_desc));
 }
 
+static void imx35_idle(void)
+{
+	int reg = imx_readl(mx3_ccm_base + MXC_CCM_CCMR);
+	reg &= ~MXC_CCM_CCMR_LPM_MASK;
+	reg |= MXC_CCM_CCMR_LPM_WAIT_MX35;
+	imx_writel(reg, mx3_ccm_base + MXC_CCM_CCMR);
+
+	imx3_idle();
+}
+
 void __init imx35_init_early(void)
 {
 	mxc_set_cpu_type(MXC_CPU_MX35);
 	mxc_iomux_v3_init(MX35_IO_ADDRESS(MX35_IOMUXC_BASE_ADDR));
-	arm_pm_idle = imx3_idle;
+	arm_pm_idle = imx35_idle;
 	arch_ioremap_caller = imx3_ioremap_caller;
 	mx3_ccm_base = MX35_IO_ADDRESS(MX35_CCM_BASE_ADDR);
 }
diff --git a/arch/arm/mach-imx/mxc.h b/arch/arm/mach-imx/mxc.h
index d32704256781..34f2ff62583c 100644
--- a/arch/arm/mach-imx/mxc.h
+++ b/arch/arm/mach-imx/mxc.h
@@ -45,105 +45,7 @@
 
 #ifndef __ASSEMBLY__
 extern unsigned int __mxc_cpu_type;
-#endif
-
-#ifdef CONFIG_SOC_IMX1
-# ifdef mxc_cpu_type
-#  undef mxc_cpu_type
-#  define mxc_cpu_type __mxc_cpu_type
-# else
-#  define mxc_cpu_type MXC_CPU_MX1
-# endif
-# define cpu_is_mx1()		(mxc_cpu_type == MXC_CPU_MX1)
-#else
-# define cpu_is_mx1()		(0)
-#endif
-
-#ifdef CONFIG_SOC_IMX21
-# ifdef mxc_cpu_type
-#  undef mxc_cpu_type
-#  define mxc_cpu_type __mxc_cpu_type
-# else
-#  define mxc_cpu_type MXC_CPU_MX21
-# endif
-# define cpu_is_mx21()		(mxc_cpu_type == MXC_CPU_MX21)
-#else
-# define cpu_is_mx21()		(0)
-#endif
 
-#ifdef CONFIG_SOC_IMX25
-# ifdef mxc_cpu_type
-#  undef mxc_cpu_type
-#  define mxc_cpu_type __mxc_cpu_type
-# else
-#  define mxc_cpu_type MXC_CPU_MX25
-# endif
-# define cpu_is_mx25()		(mxc_cpu_type == MXC_CPU_MX25)
-#else
-# define cpu_is_mx25()		(0)
-#endif
-
-#ifdef CONFIG_SOC_IMX27
-# ifdef mxc_cpu_type
-#  undef mxc_cpu_type
-#  define mxc_cpu_type __mxc_cpu_type
-# else
-#  define mxc_cpu_type MXC_CPU_MX27
-# endif
-# define cpu_is_mx27()		(mxc_cpu_type == MXC_CPU_MX27)
-#else
-# define cpu_is_mx27()		(0)
-#endif
-
-#ifdef CONFIG_SOC_IMX31
-# ifdef mxc_cpu_type
-#  undef mxc_cpu_type
-#  define mxc_cpu_type __mxc_cpu_type
-# else
-#  define mxc_cpu_type MXC_CPU_MX31
-# endif
-# define cpu_is_mx31()		(mxc_cpu_type == MXC_CPU_MX31)
-#else
-# define cpu_is_mx31()		(0)
-#endif
-
-#ifdef CONFIG_SOC_IMX35
-# ifdef mxc_cpu_type
-#  undef mxc_cpu_type
-#  define mxc_cpu_type __mxc_cpu_type
-# else
-#  define mxc_cpu_type MXC_CPU_MX35
-# endif
-# define cpu_is_mx35()		(mxc_cpu_type == MXC_CPU_MX35)
-#else
-# define cpu_is_mx35()		(0)
-#endif
-
-#ifdef CONFIG_SOC_IMX51
-# ifdef mxc_cpu_type
-#  undef mxc_cpu_type
-#  define mxc_cpu_type __mxc_cpu_type
-# else
-#  define mxc_cpu_type MXC_CPU_MX51
-# endif
-# define cpu_is_mx51()		(mxc_cpu_type == MXC_CPU_MX51)
-#else
-# define cpu_is_mx51()		(0)
-#endif
-
-#ifdef CONFIG_SOC_IMX53
-# ifdef mxc_cpu_type
-#  undef mxc_cpu_type
-#  define mxc_cpu_type __mxc_cpu_type
-# else
-#  define mxc_cpu_type MXC_CPU_MX53
-# endif
-# define cpu_is_mx53()		(mxc_cpu_type == MXC_CPU_MX53)
-#else
-# define cpu_is_mx53()		(0)
-#endif
-
-#ifndef __ASSEMBLY__
 #ifdef CONFIG_SOC_IMX6SL
 static inline bool cpu_is_imx6sl(void)
 {
@@ -190,9 +92,6 @@ int tzic_enable_wake(void);
 extern struct cpu_op *(*get_cpu_op)(int *op);
 #endif
 
-#define cpu_is_mx3()	(cpu_is_mx31() || cpu_is_mx35())
-#define cpu_is_mx2()	(cpu_is_mx21() || cpu_is_mx27())
-
 #define imx_readl	readl_relaxed
 #define imx_readw	readw_relaxed
 #define imx_writel	writel_relaxed
diff --git a/arch/arm/mach-imx/pm-imx27.c b/arch/arm/mach-imx/pm-imx27.c
index 43096c8990d4..d943535566c8 100644
--- a/arch/arm/mach-imx/pm-imx27.c
+++ b/arch/arm/mach-imx/pm-imx27.c
@@ -37,13 +37,7 @@ static const struct platform_suspend_ops mx27_suspend_ops = {
 	.valid = suspend_valid_only_mem,
 };
 
-static int __init mx27_pm_init(void)
+void __init imx27_pm_init(void)
 {
-	if (!cpu_is_mx27())
-		return 0;
-
 	suspend_set_ops(&mx27_suspend_ops);
-	return 0;
 }
-
-device_initcall(mx27_pm_init);
diff --git a/arch/arm/mach-imx/pm-imx3.c b/arch/arm/mach-imx/pm-imx3.c
deleted file mode 100644
index 94c0898751d8..000000000000
--- a/arch/arm/mach-imx/pm-imx3.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- *  Copyright (C) 2012 Freescale Semiconductor, Inc. All Rights Reserved.
- *
- * The code contained herein is licensed under the GNU General Public
- * License. You may obtain a copy of the GNU General Public License
- * Version 2 or later at the following locations:
- *
- * http://www.opensource.org/licenses/gpl-license.html
- * http://www.gnu.org/copyleft/gpl.html
- */
-#include <linux/io.h>
-
-#include "common.h"
-#include "crmregs-imx3.h"
-#include "devices/devices-common.h"
-#include "hardware.h"
-
-/*
- * Set cpu low power mode before WFI instruction. This function is called
- * mx3 because it can be used for mx31 and mx35.
- * Currently only WAIT_MODE is supported.
- */
-void mx3_cpu_lp_set(enum mx3_cpu_pwr_mode mode)
-{
-	int reg = imx_readl(mx3_ccm_base + MXC_CCM_CCMR);
-	reg &= ~MXC_CCM_CCMR_LPM_MASK;
-
-	switch (mode) {
-	case MX3_WAIT:
-		if (cpu_is_mx35())
-			reg |= MXC_CCM_CCMR_LPM_WAIT_MX35;
-		imx_writel(reg, mx3_ccm_base + MXC_CCM_CCMR);
-		break;
-	default:
-		pr_err("Unknown cpu power mode: %d\n", mode);
-		return;
-	}
-}
diff --git a/arch/arm/mach-imx/system.c b/arch/arm/mach-imx/system.c
index 105d1ce4ed9d..c06af650e6b1 100644
--- a/arch/arm/mach-imx/system.c
+++ b/arch/arm/mach-imx/system.c
@@ -34,25 +34,19 @@
 
 static void __iomem *wdog_base;
 static struct clk *wdog_clk;
+static int wcr_enable = (1 << 2);
 
 /*
  * Reset the system. It is called by machine_restart().
  */
 void mxc_restart(enum reboot_mode mode, const char *cmd)
 {
-	unsigned int wcr_enable;
-
 	if (!wdog_base)
 		goto reset_fallback;
 
 	if (!IS_ERR(wdog_clk))
 		clk_enable(wdog_clk);
 
-	if (cpu_is_mx1())
-		wcr_enable = (1 << 0);
-	else
-		wcr_enable = (1 << 2);
-
 	/* Assert SRS signal */
 	imx_writew(wcr_enable, wdog_base);
 	/*
@@ -89,6 +83,14 @@ void __init mxc_arch_reset_init(void __iomem *base)
 		clk_prepare(wdog_clk);
 }
 
+#ifdef CONFIG_SOC_IMX1
+void __init imx1_reset_init(void __iomem *base)
+{
+	wcr_enable = (1 << 0);
+	mxc_arch_reset_init(base);
+}
+#endif
+
 #ifdef CONFIG_CACHE_L2X0
 void __init imx_init_l2cache(void)
 {
@@ -98,38 +100,28 @@ void __init imx_init_l2cache(void)
 
 	np = of_find_compatible_node(NULL, NULL, "arm,pl310-cache");
 	if (!np)
-		goto out;
+		return;
 
 	l2x0_base = of_iomap(np, 0);
-	if (!l2x0_base) {
-		of_node_put(np);
-		goto out;
-	}
+	if (!l2x0_base)
+		goto put_node;
 
-	if (readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)
-		goto skip_if_enabled;
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
+		/* Configure the L2 PREFETCH and POWER registers */
+		val = readl_relaxed(l2x0_base + L310_PREFETCH_CTRL);
+		val |= L310_PREFETCH_CTRL_DBL_LINEFILL |
+			L310_PREFETCH_CTRL_INSTR_PREFETCH |
+			L310_PREFETCH_CTRL_DATA_PREFETCH;
 
-	/* Configure the L2 PREFETCH and POWER registers */
-	val = readl_relaxed(l2x0_base + L310_PREFETCH_CTRL);
-	val |= 0x70800000;
-	/*
-	 * The L2 cache controller(PL310) version on the i.MX6D/Q is r3p1-50rel0
-	 * The L2 cache controller(PL310) version on the i.MX6DL/SOLO/SL is r3p2
-	 * But according to ARM PL310 errata: 752271
-	 * ID: 752271: Double linefill feature can cause data corruption
-	 * Fault Status: Present in: r3p0, r3p1, r3p1-50rel0. Fixed in r3p2
-	 * Workaround: The only workaround to this erratum is to disable the
-	 * double linefill feature. This is the default behavior.
-	 */
-	if (cpu_is_imx6q())
-		val &= ~(1 << 30 | 1 << 23);
-	writel_relaxed(val, l2x0_base + L310_PREFETCH_CTRL);
+		/* Set perfetch offset to improve performance */
+		val &= ~L310_PREFETCH_CTRL_OFFSET_MASK;
+		val |= 15;
+
+		writel_relaxed(val, l2x0_base + L310_PREFETCH_CTRL);
+	}
 
-skip_if_enabled:
 	iounmap(l2x0_base);
+put_node:
 	of_node_put(np);
-
-out:
-	l2x0_of_init(0, ~0);
 }
 #endif
diff --git a/arch/arm/mach-imx/tzic.c b/arch/arm/mach-imx/tzic.c
index ae23d50f7861..4ca37c3f1da4 100644
--- a/arch/arm/mach-imx/tzic.c
+++ b/arch/arm/mach-imx/tzic.c
@@ -9,12 +9,11 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/module.h>
-#include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/errno.h>
 #include <linux/io.h>
+#include <linux/irqchip.h>
 #include <linux/irqdomain.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -56,14 +55,14 @@ static struct irq_domain *domain;
 #define TZIC_NUM_IRQS 128
 
 #ifdef CONFIG_FIQ
-static int tzic_set_irq_fiq(unsigned int irq, unsigned int type)
+static int tzic_set_irq_fiq(unsigned int hwirq, unsigned int type)
 {
 	unsigned int index, mask, value;
 
-	index = irq >> 5;
+	index = hwirq >> 5;
 	if (unlikely(index >= 4))
 		return -EINVAL;
-	mask = 1U << (irq & 0x1F);
+	mask = 1U << (hwirq & 0x1F);
 
 	value = imx_readl(tzic_base + TZIC_INTSEC0(index)) | mask;
 	if (type)
@@ -153,13 +152,11 @@ static void __exception_irq_entry tzic_handle_irq(struct pt_regs *regs)
  * interrupts. It registers the interrupt enable and disable functions
  * to the kernel for each interrupt source.
  */
-void __init tzic_init_irq(void)
+static int __init tzic_init_dt(struct device_node *np, struct device_node *p)
 {
-	struct device_node *np;
 	int irq_base;
 	int i;
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,tzic");
 	tzic_base = of_iomap(np, 0);
 	WARN_ON(!tzic_base);
 
@@ -199,7 +196,10 @@ void __init tzic_init_irq(void)
 #endif
 
 	pr_info("TrustZone Interrupt Controller (TZIC) initialized\n");
+
+	return 0;
 }
+IRQCHIP_DECLARE(tzic, "fsl,tzic", tzic_init_dt);
 
 /**
  * tzic_enable_wake() - enable wakeup interrupt
diff --git a/arch/arm/mach-integrator/Kconfig b/arch/arm/mach-integrator/Kconfig
index 291262e5aeaf..599f973e10d8 100644
--- a/arch/arm/mach-integrator/Kconfig
+++ b/arch/arm/mach-integrator/Kconfig
@@ -32,9 +32,9 @@ config ARCH_INTEGRATOR_AP
 config INTEGRATOR_IMPD1
 	bool "Include support for Integrator/IM-PD1"
 	depends on ARCH_INTEGRATOR_AP
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_VIC
-	select GPIO_PL061 if GPIOLIB
+	select GPIO_PL061
+	select GPIOLIB
 	help
 	  The IM-PD1 is an add-on logic module for the Integrator which
 	  allows ARM(R) Ltd PrimeCells to be developed and evaluated.
diff --git a/arch/arm/mach-integrator/impd1.c b/arch/arm/mach-integrator/impd1.c
index 38b0da300dd5..ed9a01484030 100644
--- a/arch/arm/mach-integrator/impd1.c
+++ b/arch/arm/mach-integrator/impd1.c
@@ -320,11 +320,11 @@ static struct impd1_device impd1_devs[] = {
 #define IMPD1_VALID_IRQS 0x00000bffU
 
 /*
- * As this module is bool, it is OK to have this as __init_refok() - no
+ * As this module is bool, it is OK to have this as __ref() - no
  * probe calls will be done after the initial system bootup, as devices
  * are discovered as part of the machine startup.
  */
-static int __init_refok impd1_probe(struct lm_device *dev)
+static int __ref impd1_probe(struct lm_device *dev)
 {
 	struct impd1_module *impd1;
 	int irq_base;
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 2b118f20c62c..c7bb83205f5b 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -240,8 +240,7 @@ static void __init ap_init_of(void)
 	if (!ebi_base)
 		return;
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			ap_auxdata_lookup, NULL);
+	of_platform_default_populate(NULL, ap_auxdata_lookup, NULL);
 
 	sc_dec = readl(ap_syscon_base + INTEGRATOR_SC_DEC_OFFSET);
 	for (i = 0; i < 4; i++) {
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index 6f6b051e81e0..825298349bf5 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -231,8 +231,7 @@ static void __init intcp_init_of(void)
 	if (!intcp_con_base)
 		return;
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     intcp_auxdata_lookup, NULL);
+	of_platform_default_populate(NULL, intcp_auxdata_lookup, NULL);
 }
 
 static const char * intcp_dt_board_compat[] = {
diff --git a/arch/arm/mach-keystone/Kconfig b/arch/arm/mach-keystone/Kconfig
index bac577badc7e..8ff61be1a29f 100644
--- a/arch/arm/mach-keystone/Kconfig
+++ b/arch/arm/mach-keystone/Kconfig
@@ -1,7 +1,6 @@
 config ARCH_KEYSTONE
 	bool "Texas Instruments Keystone Devices"
 	depends on ARCH_MULTI_V7
-	depends on ARM_PATCH_PHYS_VIRT
 	select ARM_GIC
 	select HAVE_ARM_ARCH_TIMER
 	select KEYSTONE_TIMER
@@ -11,6 +10,7 @@ config ARCH_KEYSTONE
 	select ZONE_DMA if ARM_LPAE
 	select MIGHT_HAVE_PCI
 	select PCI_DOMAINS if PCI
+	select PINCTRL
 	help
 	  Support for boards based on the Texas Instruments Keystone family of
 	  SoCs.
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index a33a296b00dc..84613abf35a3 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -60,7 +60,6 @@ static void __init keystone_init(void)
 		bus_register_notifier(&platform_bus_type, &platform_nb);
 	}
 	keystone_pm_runtime_init();
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static long long __init keystone_pv_fixup(void)
diff --git a/arch/arm/mach-keystone/pm_domain.c b/arch/arm/mach-keystone/pm_domain.c
index e283939a216f..8cbb35765a19 100644
--- a/arch/arm/mach-keystone/pm_domain.c
+++ b/arch/arm/mach-keystone/pm_domain.c
@@ -18,6 +18,8 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 
+#include "keystone.h"
+
 static struct dev_pm_domain keystone_pm_domain = {
 	.ops = {
 		USE_PM_CLK_RUNTIME_OPS
diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c
index 81265e80302d..0e4cbbe980eb 100644
--- a/arch/arm/mach-lpc32xx/phy3250.c
+++ b/arch/arm/mach-lpc32xx/phy3250.c
@@ -191,8 +191,7 @@ static void __init lpc3250_machine_init(void)
 		LPC32XX_CLKPWR_TESTCLK_TESTCLK2_EN,
 		LPC32XX_CLKPWR_TEST_CLK_SEL);
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     lpc32xx_auxdata_lookup, NULL);
+	of_platform_default_populate(NULL, lpc32xx_auxdata_lookup, NULL);
 }
 
 static const char *const lpc32xx_dt_compat[] __initconst = {
diff --git a/arch/arm/mach-meson/Kconfig b/arch/arm/mach-meson/Kconfig
index 31bdd91098b6..b6e3acc63e14 100644
--- a/arch/arm/mach-meson/Kconfig
+++ b/arch/arm/mach-meson/Kconfig
@@ -1,12 +1,14 @@
 menuconfig ARCH_MESON
 	bool "Amlogic Meson SoCs"
 	depends on ARCH_MULTI_V7
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select GENERIC_IRQ_CHIP
 	select ARM_GIC
 	select CACHE_L2X0
 	select PINCTRL
 	select PINCTRL_MESON
+	select COMMON_CLK
+	select COMMON_CLK_AMLOGIC
 
 if ARCH_MESON
 
@@ -24,5 +26,6 @@ config MACH_MESON8B
 	bool "Amlogic Meson8b SoCs support"
 	default ARCH_MESON
 	select MESON6_TIMER
+	select COMMON_CLK_MESON8B
 
 endif
diff --git a/arch/arm/mach-mmp/Kconfig b/arch/arm/mach-mmp/Kconfig
index 01c57d369462..94500bed56ab 100644
--- a/arch/arm/mach-mmp/Kconfig
+++ b/arch/arm/mach-mmp/Kconfig
@@ -1,8 +1,8 @@
 menuconfig ARCH_MMP
 	bool "Marvell PXA168/910/MMP2"
 	depends on ARCH_MULTI_V5 || ARCH_MULTI_V7
-	select ARCH_REQUIRE_GPIOLIB
 	select GPIO_PXA
+	select GPIOLIB
 	select PINCTRL
 	select PLAT_PXA
 	help
diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig
index ddc79cea32d3..f69e28b85e88 100644
--- a/arch/arm/mach-moxart/Kconfig
+++ b/arch/arm/mach-moxart/Kconfig
@@ -5,7 +5,7 @@ menuconfig ARCH_MOXART
 	select ARM_DMA_MEM_BUFFERABLE
 	select MOXART_TIMER
 	select GENERIC_IRQ_CHIP
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select PHYLIB if NETDEVICES
 	help
 	  Say Y here if you want to run your kernel on hardware with a
diff --git a/arch/arm/mach-mv78xx0/Kconfig b/arch/arm/mach-mv78xx0/Kconfig
index c32f85559c65..81c0f08a2684 100644
--- a/arch/arm/mach-mv78xx0/Kconfig
+++ b/arch/arm/mach-mv78xx0/Kconfig
@@ -1,8 +1,8 @@
 menuconfig ARCH_MV78XX0
 	bool "Marvell MV78xx0"
 	depends on ARCH_MULTI_V5
-	select ARCH_REQUIRE_GPIOLIB
 	select CPU_FEROCEON
+	select GPIOLIB
 	select MVEBU_MBUS
 	select PCI
 	select PLAT_ORION_LEGACY
diff --git a/arch/arm/mach-mv78xx0/common.c b/arch/arm/mach-mv78xx0/common.c
index 45a05207b418..6af5430d0d97 100644
--- a/arch/arm/mach-mv78xx0/common.c
+++ b/arch/arm/mach-mv78xx0/common.c
@@ -343,7 +343,7 @@ void __init mv78xx0_init_early(void)
 				DDR_WINDOW_CPU1_BASE, DDR_WINDOW_CPU_SZ);
 }
 
-void __init_refok mv78xx0_timer_init(void)
+void __ref mv78xx0_timer_init(void)
 {
 	orion_time_init(BRIDGE_VIRT_BASE, BRIDGE_INT_TIMER1_CLR,
 			IRQ_MV78XX0_TIMER_1, get_tclk());
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 348044ea650c..f9b6bd306cfe 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -8,7 +8,7 @@ menuconfig ARCH_MVEBU
 	select SOC_BUS
 	select MVEBU_MBUS
 	select ZONE_DMA if ARM_LPAE
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select PCI_QUIRKS if PCI
 	select OF_ADDRESS_PCI
 
@@ -119,8 +119,8 @@ config MACH_DOVE
 config MACH_KIRKWOOD
 	bool "Marvell Kirkwood boards"
 	depends on ARCH_MULTI_V5
-	select ARCH_REQUIRE_GPIOLIB
 	select CPU_FEROCEON
+	select GPIOLIB
 	select KIRKWOOD_CLK
 	select MACH_MVEBU_ANY
 	select ORION_IRQCHIP
diff --git a/arch/arm/mach-mvebu/board-v7.c b/arch/arm/mach-mvebu/board-v7.c
index 1648edd515a2..ccca95173e17 100644
--- a/arch/arm/mach-mvebu/board-v7.c
+++ b/arch/arm/mach-mvebu/board-v7.c
@@ -16,7 +16,6 @@
 #include <linux/init.h>
 #include <linux/of_address.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 #include <linux/io.h>
 #include <linux/clocksource.h>
 #include <linux/dma-mapping.h>
@@ -144,8 +143,6 @@ static void __init mvebu_dt_init(void)
 {
 	if (of_machine_is_compatible("marvell,armadaxp"))
 		i2c_quirk();
-
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static const char * const armada_370_xp_dt_compat[] __initconst = {
diff --git a/arch/arm/mach-mvebu/coherency.h b/arch/arm/mach-mvebu/coherency.h
index 54cb7607b526..6067f14263f7 100644
--- a/arch/arm/mach-mvebu/coherency.h
+++ b/arch/arm/mach-mvebu/coherency.h
@@ -14,6 +14,7 @@
 #ifndef __MACH_370_XP_COHERENCY_H
 #define __MACH_370_XP_COHERENCY_H
 
+extern void __iomem *coherency_base;	/* for coherency_ll.S */
 extern unsigned long coherency_phys_base;
 int set_cpu_coherent(void);
 
diff --git a/arch/arm/mach-mvebu/cpu-reset.c b/arch/arm/mach-mvebu/cpu-reset.c
index 4a2cadd6b48e..f33a31c6aff8 100644
--- a/arch/arm/mach-mvebu/cpu-reset.c
+++ b/arch/arm/mach-mvebu/cpu-reset.c
@@ -16,6 +16,8 @@
 #include <linux/io.h>
 #include <linux/resource.h>
 
+#include "common.h"
+
 static void __iomem *cpu_reset_base;
 static size_t cpu_reset_size;
 
diff --git a/arch/arm/mach-mvebu/dove.c b/arch/arm/mach-mvebu/dove.c
index 1aebb82e3d7b..d076c5771adc 100644
--- a/arch/arm/mach-mvebu/dove.c
+++ b/arch/arm/mach-mvebu/dove.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/mbus.h>
 #include <linux/of.h>
-#include <linux/of_platform.h>
 #include <linux/soc/dove/pmu.h>
 #include <asm/hardware/cache-tauros2.h>
 #include <asm/mach/arch.h>
@@ -26,7 +25,6 @@ static void __init dove_init(void)
 #endif
 	BUG_ON(mvebu_mbus_dt_init(false));
 	dove_init_pmu();
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static const char * const dove_dt_compat[] __initconst = {
diff --git a/arch/arm/mach-mvebu/kirkwood-pm.c b/arch/arm/mach-mvebu/kirkwood-pm.c
index cbb816f2120c..1e1f879f16ce 100644
--- a/arch/arm/mach-mvebu/kirkwood-pm.c
+++ b/arch/arm/mach-mvebu/kirkwood-pm.c
@@ -18,6 +18,7 @@
 #include <linux/suspend.h>
 #include <linux/io.h>
 #include "kirkwood.h"
+#include "kirkwood-pm.h"
 
 static void __iomem *ddr_operation_base;
 static void __iomem *memory_pm_ctrl;
@@ -66,11 +67,10 @@ static const struct platform_suspend_ops kirkwood_suspend_ops = {
 	.valid = kirkwood_pm_valid_standby,
 };
 
-int __init kirkwood_pm_init(void)
+void __init kirkwood_pm_init(void)
 {
 	ddr_operation_base = ioremap(DDR_OPERATION_BASE, 4);
 	memory_pm_ctrl = ioremap(MEMORY_PM_CTRL_PHYS, 4);
 
 	suspend_set_ops(&kirkwood_suspend_ops);
-	return 0;
 }
diff --git a/arch/arm/mach-mvebu/kirkwood.c b/arch/arm/mach-mvebu/kirkwood.c
index f9d8e1ea7183..7d9f2fd9e450 100644
--- a/arch/arm/mach-mvebu/kirkwood.c
+++ b/arch/arm/mach-mvebu/kirkwood.c
@@ -150,7 +150,7 @@ eth_fixup_skip:
  * causes mbus errors (which can occur for example for PCI aborts) to
  * throw CPU aborts, which we're not set up to deal with.
  */
-void kirkwood_disable_mbus_error_propagation(void)
+static void kirkwood_disable_mbus_error_propagation(void)
 {
 	void __iomem *cpu_config;
 
@@ -179,7 +179,7 @@ static void __init kirkwood_dt_init(void)
 	kirkwood_pm_init();
 	kirkwood_dt_eth_fixup();
 
-	of_platform_populate(NULL, of_default_bus_match_table, auxdata, NULL);
+	of_platform_default_populate(NULL, auxdata, NULL);
 }
 
 static const char * const kirkwood_dt_board_compat[] __initconst = {
diff --git a/arch/arm/mach-mvebu/pm.c b/arch/arm/mach-mvebu/pm.c
index 8d32bf762b86..2990c5269b18 100644
--- a/arch/arm/mach-mvebu/pm.c
+++ b/arch/arm/mach-mvebu/pm.c
@@ -23,6 +23,7 @@
 #include <asm/suspend.h>
 
 #include "coherency.h"
+#include "common.h"
 #include "pmsu.h"
 
 #define SDRAM_CONFIG_OFFS                  0x0
diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c
index b44442338e4e..f39bd51bce18 100644
--- a/arch/arm/mach-mvebu/pmsu.c
+++ b/arch/arm/mach-mvebu/pmsu.c
@@ -25,6 +25,7 @@
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/mbus.h>
+#include <linux/mvebu-pmsu.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
@@ -38,7 +39,7 @@
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 #include "common.h"
-
+#include "pmsu.h"
 
 #define PMSU_BASE_OFFSET    0x100
 #define PMSU_REG_SIZE	    0x1000
diff --git a/arch/arm/mach-mvebu/system-controller.c b/arch/arm/mach-mvebu/system-controller.c
index c6c132acd7a6..76cbc82a7407 100644
--- a/arch/arm/mach-mvebu/system-controller.c
+++ b/arch/arm/mach-mvebu/system-controller.c
@@ -127,7 +127,7 @@ int mvebu_system_controller_get_soc_id(u32 *dev, u32 *rev)
 }
 
 #if defined(CONFIG_SMP) && defined(CONFIG_MACH_MVEBU_V7)
-void mvebu_armada375_smp_wa_init(void)
+static void mvebu_armada375_smp_wa_init(void)
 {
 	u32 dev, rev;
 	phys_addr_t resume_addr_reg;
diff --git a/arch/arm/mach-mxs/Kconfig b/arch/arm/mach-mxs/Kconfig
index 68a3a9ec605d..cb429bc6dc0d 100644
--- a/arch/arm/mach-mxs/Kconfig
+++ b/arch/arm/mach-mxs/Kconfig
@@ -15,7 +15,7 @@ config SOC_IMX28
 config ARCH_MXS
 	bool "Freescale MXS (i.MX23, i.MX28) support"
 	depends on ARCH_MULTI_V5
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select MXS_TIMER
 	select PINCTRL
 	select SOC_BUS
diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c
index f1ea4700efcf..0b7fe74ff46d 100644
--- a/arch/arm/mach-mxs/mach-mxs.c
+++ b/arch/arm/mach-mxs/mach-mxs.c
@@ -498,8 +498,7 @@ static void __init mxs_machine_init(void)
 	else if (of_machine_is_compatible("msr,m28cu3"))
 		m28cu3_init();
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     NULL, parent);
+	of_platform_default_populate(NULL, NULL, parent);
 
 	mxs_restart_init();
 
diff --git a/arch/arm/mach-nomadik/Kconfig b/arch/arm/mach-nomadik/Kconfig
index 3c61096c8627..b7e9801fdaa4 100644
--- a/arch/arm/mach-nomadik/Kconfig
+++ b/arch/arm/mach-nomadik/Kconfig
@@ -1,12 +1,12 @@
 menuconfig ARCH_NOMADIK
 	bool "ST-Ericsson Nomadik"
 	depends on ARCH_MULTI_V5
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_VIC
 	select CLKSRC_NOMADIK_MTU
 	select CLKSRC_NOMADIK_MTU_SCHED_CLOCK
 	select CPU_ARM926T
+	select GPIOLIB
 	select MIGHT_HAVE_CACHE_L2X0
 	select PINCTRL
 	select PINCTRL_NOMADIK
diff --git a/arch/arm/mach-nspire/nspire.c b/arch/arm/mach-nspire/nspire.c
index 34c2a1b32e7d..f0808fcc5acc 100644
--- a/arch/arm/mach-nspire/nspire.c
+++ b/arch/arm/mach-nspire/nspire.c
@@ -57,8 +57,7 @@ static struct of_dev_auxdata nspire_auxdata[] __initdata = {
 
 static void __init nspire_init(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table,
-			nspire_auxdata, NULL);
+	of_platform_default_populate(NULL, nspire_auxdata, NULL);
 }
 
 static void nspire_restart(enum reboot_mode mode, const char *cmd)
diff --git a/arch/arm/mach-omap1/ams-delta-fiq.c b/arch/arm/mach-omap1/ams-delta-fiq.c
index ec760ae2f917..793a24a53c52 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq.c
+++ b/arch/arm/mach-omap1/ams-delta-fiq.c
@@ -137,7 +137,7 @@ void __init ams_delta_init_fiq(void)
 		fiq_buffer[i] = 0;
 
 	/*
-	 * FIQ mode r9 always points to the fiq_buffer, becauses the FIQ isr
+	 * FIQ mode r9 always points to the fiq_buffer, because the FIQ isr
 	 * will run in an unpredictable context. The fiq_buffer is the FIQ isr's
 	 * only means of communication with the IRQ level and other kernel
 	 * context code.
diff --git a/arch/arm/mach-omap1/include/mach/mtd-xip.h b/arch/arm/mach-omap1/include/mach/mtd-xip.h
index f82a8dcaad94..d09b2bc4920f 100644
--- a/arch/arm/mach-omap1/include/mach/mtd-xip.h
+++ b/arch/arm/mach-omap1/include/mach/mtd-xip.h
@@ -39,7 +39,7 @@ static inline unsigned long xip_omap_mpu_timer_read(int nr)
 #define xip_currtime()		(~xip_omap_mpu_timer_read(0))
 
 /*
- * It's permitted to do approxmation for xip_elapsed_since macro
+ * It's permitted to do approximation for xip_elapsed_since macro
  * (see linux/mtd/xip.h)
  */
 
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 1a648e9dfaa0..5a0b380a8166 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -92,9 +92,9 @@ config ARCH_OMAP2PLUS
 	select ARCH_HAS_BANDGAP
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_OMAP
-	select ARCH_REQUIRE_GPIOLIB
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
+	select GPIOLIB
 	select MACH_OMAP_GENERIC
 	select MEMORY
 	select MFD_SYSCON
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 04e276ce8413..a7f2d051f524 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -8,7 +8,7 @@ ccflags-y := -I$(srctree)/$(src)/include \
 # Common support
 obj-y := id.o io.o control.o mux.o devices.o fb.o serial.o timer.o pm.o \
 	 common.o gpio.o dma.o wd_timer.o display.o i2c.o hdq1w.o omap_hwmod.o \
-	 omap_device.o sram.o drm.o
+	 omap_device.o omap-headsmp.o sram.o drm.o
 
 hwmod-common				= omap_hwmod.o omap_hwmod_reset.o \
 					  omap_hwmod_common_data.o
@@ -32,7 +32,7 @@ obj-$(CONFIG_SOC_HAS_OMAP2_SDRC)	+= sdrc.o
 
 # SMP support ONLY available for OMAP4
 
-smp-$(CONFIG_SMP)			+= omap-smp.o omap-headsmp.o
+smp-$(CONFIG_SMP)			+= omap-smp.o
 smp-$(CONFIG_HOTPLUG_CPU)		+= omap-hotplug.o
 omap-4-5-common				=  omap4-common.o omap-wakeupgen.o
 obj-$(CONFIG_ARCH_OMAP4)		+= $(omap-4-5-common) $(smp-y) sleep44xx.o
@@ -78,13 +78,16 @@ obj-$(CONFIG_ARCH_OMAP4)		+= opp4xxx_data.o
 endif
 
 # Power Management
+omap-4-5-pm-common			= omap-mpuss-lowpower.o
+obj-$(CONFIG_ARCH_OMAP4)		+= $(omap-4-5-pm-common)
+obj-$(CONFIG_ARCH_OMAP5)		+= $(omap-4-5-pm-common)
 obj-$(CONFIG_OMAP_PM_NOOP)		+= omap-pm-noop.o
 
 ifeq ($(CONFIG_PM),y)
 obj-$(CONFIG_ARCH_OMAP2)		+= pm24xx.o
 obj-$(CONFIG_ARCH_OMAP2)		+= sleep24xx.o
 obj-$(CONFIG_ARCH_OMAP3)		+= pm34xx.o sleep34xx.o
-omap-4-5-pm-common			=  pm44xx.o omap-mpuss-lowpower.o
+omap-4-5-pm-common			+= pm44xx.o
 obj-$(CONFIG_ARCH_OMAP4)		+= $(omap-4-5-pm-common)
 obj-$(CONFIG_SOC_OMAP5)			+= $(omap-4-5-pm-common)
 obj-$(CONFIG_SOC_DRA7XX)		+= $(omap-4-5-pm-common)
diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c
index d9c3ffc39329..390795b334c3 100644
--- a/arch/arm/mach-omap2/board-ldp.c
+++ b/arch/arm/mach-omap2/board-ldp.c
@@ -39,7 +39,7 @@
 #include "gpmc.h"
 #include "gpmc-smsc911x.h"
 
-#include <video/omapdss.h>
+#include <linux/platform_data/omapdss.h>
 #include <video/omap-panel-data.h>
 
 #include "board-flash.h"
@@ -47,6 +47,7 @@
 #include "hsmmc.h"
 #include "control.h"
 #include "common-board-devices.h"
+#include "display.h"
 
 #define LDP_SMSC911X_CS		1
 #define LDP_SMSC911X_GPIO	152
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 9a7073949d1d..a5ab712c1a59 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -1242,11 +1242,6 @@ static struct pwm_omap_dmtimer_pdata __maybe_unused pwm_dmtimer_pdata = {
 #if defined(CONFIG_IR_RX51) || defined(CONFIG_IR_RX51_MODULE)
 static struct lirc_rx51_platform_data rx51_lirc_data = {
 	.set_max_mpu_wakeup_lat = omap_pm_set_max_mpu_wakeup_lat,
-	.pwm_timer = 9, /* Use GPT 9 for CIR */
-#if IS_ENABLED(CONFIG_OMAP_DM_TIMER)
-	.dmtimer = &pwm_dmtimer_pdata,
-#endif
-
 };
 
 static struct platform_device rx51_lirc_device = {
diff --git a/arch/arm/mach-omap2/board-rx51-video.c b/arch/arm/mach-omap2/board-rx51-video.c
index 9cfebc5c7455..180c6aa633bd 100644
--- a/arch/arm/mach-omap2/board-rx51-video.c
+++ b/arch/arm/mach-omap2/board-rx51-video.c
@@ -15,13 +15,14 @@
 #include <linux/spi/spi.h>
 #include <linux/mm.h>
 #include <asm/mach-types.h>
-#include <video/omapdss.h>
+#include <linux/platform_data/omapdss.h>
 #include <video/omap-panel-data.h>
 
 #include <linux/platform_data/spi-omap2-mcspi.h>
 
 #include "soc.h"
 #include "board-rx51.h"
+#include "display.h"
 
 #include "mux.h"
 
@@ -32,7 +33,6 @@
 static struct connector_atv_platform_data rx51_tv_pdata = {
 	.name = "tv",
 	.source = "venc.0",
-	.connector_type = OMAP_DSS_VENC_TYPE_COMPOSITE,
 	.invert_polarity = false,
 };
 
diff --git a/arch/arm/mach-omap2/clockdomain.c b/arch/arm/mach-omap2/clockdomain.c
index 2da3b5ec010c..b79b1ca9aee9 100644
--- a/arch/arm/mach-omap2/clockdomain.c
+++ b/arch/arm/mach-omap2/clockdomain.c
@@ -465,10 +465,7 @@ int clkdm_complete_init(void)
 		return -EACCES;
 
 	list_for_each_entry(clkdm, &clkdm_list, node) {
-		if (clkdm->flags & CLKDM_CAN_FORCE_WAKEUP)
-			clkdm_wakeup(clkdm);
-		else if (clkdm->flags & CLKDM_CAN_DISABLE_AUTO)
-			clkdm_deny_idle(clkdm);
+		clkdm_deny_idle(clkdm);
 
 		_resolve_clkdm_deps(clkdm, clkdm->wkdep_srcs);
 		clkdm_clear_all_wkdeps(clkdm);
@@ -925,11 +922,20 @@ void clkdm_allow_idle_nolock(struct clockdomain *clkdm)
 	if (!clkdm)
 		return;
 
-	if (!(clkdm->flags & CLKDM_CAN_ENABLE_AUTO)) {
-		pr_debug("clock: %s: automatic idle transitions cannot be enabled\n",
-			 clkdm->name);
+	if (!WARN_ON(!clkdm->forcewake_count))
+		clkdm->forcewake_count--;
+
+	if (clkdm->forcewake_count)
+		return;
+
+	if (!clkdm->usecount && (clkdm->flags & CLKDM_CAN_FORCE_SLEEP))
+		clkdm_sleep_nolock(clkdm);
+
+	if (!(clkdm->flags & CLKDM_CAN_ENABLE_AUTO))
+		return;
+
+	if (clkdm->flags & CLKDM_MISSING_IDLE_REPORTING)
 		return;
-	}
 
 	if (!arch_clkdm || !arch_clkdm->clkdm_allow_idle)
 		return;
@@ -974,11 +980,17 @@ void clkdm_deny_idle_nolock(struct clockdomain *clkdm)
 	if (!clkdm)
 		return;
 
-	if (!(clkdm->flags & CLKDM_CAN_DISABLE_AUTO)) {
-		pr_debug("clockdomain: %s: automatic idle transitions cannot be disabled\n",
-			 clkdm->name);
+	if (clkdm->forcewake_count++)
+		return;
+
+	if (clkdm->flags & CLKDM_CAN_FORCE_WAKEUP)
+		clkdm_wakeup_nolock(clkdm);
+
+	if (!(clkdm->flags & CLKDM_CAN_DISABLE_AUTO))
+		return;
+
+	if (clkdm->flags & CLKDM_MISSING_IDLE_REPORTING)
 		return;
-	}
 
 	if (!arch_clkdm || !arch_clkdm->clkdm_deny_idle)
 		return;
diff --git a/arch/arm/mach-omap2/clockdomain.h b/arch/arm/mach-omap2/clockdomain.h
index 2c398ce1a0f2..24667a5a9dc0 100644
--- a/arch/arm/mach-omap2/clockdomain.h
+++ b/arch/arm/mach-omap2/clockdomain.h
@@ -114,6 +114,7 @@ struct omap_hwmod;
  * @wkdep_srcs: Clockdomains that can be told to wake this powerdomain up
  * @sleepdep_srcs: Clockdomains that can be told to keep this clkdm from inact
  * @usecount: Usecount tracking
+ * @forcewake_count: Usecount for forcing the domain active
  * @node: list_head to link all clockdomains together
  *
  * @prcm_partition should be a macro from mach-omap2/prcm44xx.h (OMAP4 only)
@@ -138,6 +139,7 @@ struct clockdomain {
 	struct clkdm_dep *wkdep_srcs;
 	struct clkdm_dep *sleepdep_srcs;
 	int usecount;
+	int forcewake_count;
 	struct list_head node;
 };
 
diff --git a/arch/arm/mach-omap2/cm33xx.c b/arch/arm/mach-omap2/cm33xx.c
index 7b181f929525..c073fb57dd13 100644
--- a/arch/arm/mach-omap2/cm33xx.c
+++ b/arch/arm/mach-omap2/cm33xx.c
@@ -220,6 +220,9 @@ static int am33xx_cm_wait_module_ready(u8 part, s16 inst, u16 clkctrl_offs,
 {
 	int i = 0;
 
+	if (!clkctrl_offs)
+		return 0;
+
 	omap_test_timeout(_is_module_ready(inst, clkctrl_offs),
 			  MAX_MODULE_READY_TIME, i);
 
diff --git a/arch/arm/mach-omap2/cm3xxx.c b/arch/arm/mach-omap2/cm3xxx.c
index 187fa4386718..d91ae8206d1e 100644
--- a/arch/arm/mach-omap2/cm3xxx.c
+++ b/arch/arm/mach-omap2/cm3xxx.c
@@ -649,7 +649,7 @@ void omap3_cm_save_scratchpad_contents(u32 *ptr)
 	/*
 	 * As per erratum i671, ROM code does not respect the PER DPLL
 	 * programming scheme if CM_AUTOIDLE_PLL..AUTO_PERIPH_DPLL == 1.
-	 * Then,  in anycase, clear these bits to avoid extra latencies.
+	 * Then,  in any case, clear these bits to avoid extra latencies.
 	 */
 	*ptr++ = omap2_cm_read_mod_reg(PLL_MOD, CM_AUTOIDLE) &
 		~OMAP3430_AUTO_PERIPH_DPLL_MASK;
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index f7666b9f3b21..deed42e1dd9c 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -257,18 +257,22 @@ extern void gic_dist_enable(void);
 extern bool gic_dist_disabled(void);
 extern void gic_timer_retrigger(void);
 extern void omap_smc1(u32 fn, u32 arg);
+extern void omap4_sar_ram_init(void);
 extern void __iomem *omap4_get_sar_ram_base(void);
+extern void omap4_mpuss_early_init(void);
 extern void omap_do_wfi(void);
 
-#ifdef CONFIG_SMP
-/* Needed for secondary core boot */
 extern void omap4_secondary_startup(void);
 extern void omap4460_secondary_startup(void);
+
+#ifdef CONFIG_SMP
+/* Needed for secondary core boot */
 extern u32 omap_modify_auxcoreboot0(u32 set_mask, u32 clear_mask);
 extern void omap_auxcoreboot_addr(u32 cpu_addr);
 extern u32 omap_read_auxcoreboot0(void);
 
 extern void omap4_cpu_die(unsigned int cpu);
+extern int omap4_cpu_kill(unsigned int cpu);
 
 extern const struct smp_operations omap4_smp_ops;
 
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 4b8e9f4d59ea..fa138d4032b6 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -140,7 +140,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 		    mpuss_can_lose_context)
 			gic_dist_disable();
 
-		clkdm_wakeup(cpu_clkdm[1]);
+		clkdm_deny_idle(cpu_clkdm[1]);
 		omap_set_pwrdm_state(cpu_pd[1], PWRDM_POWER_ON);
 		clkdm_allow_idle(cpu_clkdm[1]);
 
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 6ab13d18c636..70b3eaf085e4 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -29,7 +29,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 
-#include <video/omapdss.h>
+#include <linux/platform_data/omapdss.h>
 #include "omap_hwmod.h"
 #include "omap_device.h"
 #include "omap-pm.h"
diff --git a/arch/arm/mach-omap2/display.h b/arch/arm/mach-omap2/display.h
index 7375854b16c7..78f253005279 100644
--- a/arch/arm/mach-omap2/display.h
+++ b/arch/arm/mach-omap2/display.h
@@ -33,4 +33,9 @@ int omap_init_vout(void);
 
 struct device_node * __init omapdss_find_dss_of_node(void);
 
+struct omap_dss_board_info;
+
+/* Init with the board info */
+int omap_display_init(struct omap_dss_board_info *board_data);
+
 #endif
diff --git a/arch/arm/mach-omap2/dss-common.c b/arch/arm/mach-omap2/dss-common.c
index ea2be0f5953b..1d583bc0b1a9 100644
--- a/arch/arm/mach-omap2/dss-common.c
+++ b/arch/arm/mach-omap2/dss-common.c
@@ -27,7 +27,7 @@
 #include <linux/gpio.h>
 #include <linux/platform_device.h>
 
-#include <video/omapdss.h>
+#include <linux/platform_data/omapdss.h>
 #include <video/omap-panel-data.h>
 
 #include "soc.h"
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 49de4dd227be..0e9acdd95d70 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -690,6 +690,8 @@ void __init omap4430_init_early(void)
 	omap4xxx_check_revision();
 	omap4xxx_check_features();
 	omap2_prcm_base_init();
+	omap4_sar_ram_init();
+	omap4_mpuss_early_init();
 	omap4_pm_init_early();
 	omap44xx_voltagedomains_init();
 	omap44xx_powerdomains_init();
@@ -718,6 +720,7 @@ void __init omap5_init_early(void)
 	omap4_pm_init_early();
 	omap2_prcm_base_init();
 	omap5xxx_check_revision();
+	omap4_sar_ram_init();
 	omap54xx_voltagedomains_init();
 	omap54xx_powerdomains_init();
 	omap54xx_clockdomains_init();
diff --git a/arch/arm/mach-omap2/mcbsp.c b/arch/arm/mach-omap2/mcbsp.c
index b4ac3af1160c..fc04be74e064 100644
--- a/arch/arm/mach-omap2/mcbsp.c
+++ b/arch/arm/mach-omap2/mcbsp.c
@@ -34,18 +34,24 @@
 #include "cm3xxx.h"
 #include "cm-regbits-34xx.h"
 
-static struct clk *mcbsp_iclks[5];
-
-static int omap3_enable_st_clock(unsigned int id, bool enable)
+static int omap3_mcbsp_force_ick_on(struct clk *clk, bool force_on)
 {
-	/*
-	 * Sidetone uses McBSP ICLK - which must not idle when sidetones
-	 * are enabled or sidetones start sounding ugly.
-	 */
-	if (enable)
-		return omap2_clk_deny_idle(mcbsp_iclks[id]);
+	if (!clk)
+		return 0;
+
+	if (force_on)
+		return omap2_clk_deny_idle(clk);
 	else
-		return omap2_clk_allow_idle(mcbsp_iclks[id]);
+		return omap2_clk_allow_idle(clk);
+}
+
+void __init omap3_mcbsp_init_pdata_callback(
+					struct omap_mcbsp_platform_data *pdata)
+{
+	if (!pdata)
+		return;
+
+	pdata->force_ick_on = omap3_mcbsp_force_ick_on;
 }
 
 static int __init omap_init_mcbsp(struct omap_hwmod *oh, void *unused)
@@ -55,7 +61,6 @@ static int __init omap_init_mcbsp(struct omap_hwmod *oh, void *unused)
 	struct omap_hwmod *oh_device[2];
 	struct omap_mcbsp_platform_data *pdata = NULL;
 	struct platform_device *pdev;
-	char clk_name[11];
 
 	sscanf(oh->name, "mcbsp%d", &id);
 
@@ -96,9 +101,7 @@ static int __init omap_init_mcbsp(struct omap_hwmod *oh, void *unused)
 	if (oh->dev_attr) {
 		oh_device[1] = omap_hwmod_lookup((
 		(struct omap_mcbsp_dev_attr *)(oh->dev_attr))->sidetone);
-		pdata->enable_st_clock = omap3_enable_st_clock;
-		sprintf(clk_name, "mcbsp%d_ick", id);
-		mcbsp_iclks[id] = clk_get(NULL, clk_name);
+		pdata->force_ick_on = omap3_mcbsp_force_ick_on;
 		count++;
 	}
 	pdev = omap_device_build_ss(name, id, oh_device, count, pdata,
diff --git a/arch/arm/mach-omap2/mux34xx.c b/arch/arm/mach-omap2/mux34xx.c
index be271f1d585b..393e687f99e2 100644
--- a/arch/arm/mach-omap2/mux34xx.c
+++ b/arch/arm/mach-omap2/mux34xx.c
@@ -1266,7 +1266,7 @@ static struct omap_ball __initdata omap3_cus_ball[] = {
 #endif
 
 /*
- * Signals different on CBB package comapared to superset
+ * Signals different on CBB package compared to superset
  */
 #if defined(CONFIG_OMAP_MUX) && defined(CONFIG_OMAP_PACKAGE_CBB)
 static struct omap_mux __initdata omap3_cbb_subset[] = {
@@ -1597,7 +1597,7 @@ static struct omap_ball __initdata omap3_cbb_ball[] = {
 #endif
 
 /*
- * Signals different on 36XX CBP package comapared to 34XX CBC package
+ * Signals different on 36XX CBP package compared to 34XX CBC package
  */
 #if defined(CONFIG_OMAP_MUX) && defined(CONFIG_OMAP_PACKAGE_CBP)
 static struct omap_mux __initdata omap36xx_cbp_subset[] = {
diff --git a/arch/arm/mach-omap2/omap-headsmp.S b/arch/arm/mach-omap2/omap-headsmp.S
index 6d1dffca6c7b..fe36ce2734d4 100644
--- a/arch/arm/mach-omap2/omap-headsmp.S
+++ b/arch/arm/mach-omap2/omap-headsmp.S
@@ -24,6 +24,16 @@
 #define AUX_CORE_BOOT0_PA			0x48281800
 #define API_HYP_ENTRY				0x102
 
+ENTRY(omap_secondary_startup)
+#ifdef CONFIG_SMP
+	b	secondary_startup
+#else
+/* Should never get here */
+again:	wfi
+	b	again
+#endif
+#ENDPROC(omap_secondary_startup)
+
 /*
  * OMAP5 specific entry point for secondary CPU to jump from ROM
  * code.  This routine also provides a holding flag into which
@@ -39,7 +49,7 @@ wait:	ldr	r2, =AUX_CORE_BOOT0_PA	@ read from AuxCoreBoot0
 	and	r4, r4, #0x0f
 	cmp	r0, r4
 	bne	wait
-	b	secondary_startup
+	b	omap_secondary_startup
 ENDPROC(omap5_secondary_startup)
 /*
  * Same as omap5_secondary_startup except we call into the ROM to
@@ -59,7 +69,7 @@ wait_2:	ldr	r2, =AUX_CORE_BOOT0_PA	@ read from AuxCoreBoot0
 	adr	r0, hyp_boot
 	smc	#0
 hyp_boot:
-	b	secondary_startup
+	b	omap_secondary_startup
 ENDPROC(omap5_secondary_hyp_startup)
 /*
  * OMAP4 specific entry point for secondary CPU to jump from ROM
@@ -82,7 +92,7 @@ hold:	ldr	r12,=0x103
 	 * we've been released from the wait loop,secondary_stack
 	 * should now contain the SVC stack for this core
 	 */
-	b	secondary_startup
+	b	omap_secondary_startup
 ENDPROC(omap4_secondary_startup)
 
 ENTRY(omap4460_secondary_startup)
@@ -119,5 +129,5 @@ hold_2:	ldr	r12,=0x103
 	 * we've been released from the wait loop,secondary_stack
 	 * should now contain the SVC stack for this core
 	 */
-	b	secondary_startup
+	b	omap_secondary_startup
 ENDPROC(omap4460_secondary_startup)
diff --git a/arch/arm/mach-omap2/omap-hotplug.c b/arch/arm/mach-omap2/omap-hotplug.c
index 593fec753b28..d3fb5661bb5d 100644
--- a/arch/arm/mach-omap2/omap-hotplug.c
+++ b/arch/arm/mach-omap2/omap-hotplug.c
@@ -64,3 +64,9 @@ void omap4_cpu_die(unsigned int cpu)
 		pr_debug("CPU%u: spurious wakeup call\n", cpu);
 	}
 }
+
+/* Needed by kexec and platform_can_cpu_hotplug() */
+int omap4_cpu_kill(unsigned int cpu)
+{
+	return 1;
+}
diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
index 65024af169d3..ad982465efd0 100644
--- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c
+++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -62,7 +62,9 @@
 #include "prm44xx.h"
 #include "prm-regbits-44xx.h"
 
-#ifdef CONFIG_SMP
+static void __iomem *sar_base;
+
+#if defined(CONFIG_PM) && defined(CONFIG_SMP)
 
 struct omap4_cpu_pm_info {
 	struct powerdomain *pwrdm;
@@ -90,7 +92,6 @@ struct cpu_pm_ops {
 
 static DEFINE_PER_CPU(struct omap4_cpu_pm_info, omap4_pm_info);
 static struct powerdomain *mpuss_pd;
-static void __iomem *sar_base;
 static u32 cpu_context_offset;
 
 static int default_finish_suspend(unsigned long cpu_state)
@@ -366,9 +367,6 @@ int __init omap4_mpuss_init(void)
 		return -ENODEV;
 	}
 
-	if (cpu_is_omap44xx())
-		sar_base = omap4_get_sar_ram_base();
-
 	/* Initilaise per CPU PM information */
 	pm_info = &per_cpu(omap4_pm_info, 0x0);
 	if (sar_base) {
@@ -444,3 +442,26 @@ int __init omap4_mpuss_init(void)
 }
 
 #endif
+
+/*
+ * For kexec, we must set CPU1_WAKEUP_NS_PA_ADDR to point to
+ * current kernel's secondary_startup() early before
+ * clockdomains_init(). Otherwise clockdomain_init() can
+ * wake CPU1 and cause a hang.
+ */
+void __init omap4_mpuss_early_init(void)
+{
+	unsigned long startup_pa;
+
+	if (!cpu_is_omap44xx())
+		return;
+
+	sar_base = omap4_get_sar_ram_base();
+
+	if (cpu_is_omap443x())
+		startup_pa = virt_to_phys(omap4_secondary_startup);
+	else
+		startup_pa = virt_to_phys(omap4460_secondary_startup);
+
+	writel_relaxed(startup_pa, sar_base + CPU1_WAKEUP_NS_PA_ADDR_OFFSET);
+}
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 8cd1de914ee4..b4de3da6dffa 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -40,14 +40,35 @@
 
 #define OMAP5_CORE_COUNT	0x2
 
-/* SCU base address */
-static void __iomem *scu_base;
+struct omap_smp_config {
+	unsigned long cpu1_rstctrl_pa;
+	void __iomem *cpu1_rstctrl_va;
+	void __iomem *scu_base;
+	void *startup_addr;
+};
+
+static struct omap_smp_config cfg;
+
+static const struct omap_smp_config omap443x_cfg __initconst = {
+	.cpu1_rstctrl_pa = 0x4824380c,
+	.startup_addr = omap4_secondary_startup,
+};
+
+static const struct omap_smp_config omap446x_cfg __initconst = {
+	.cpu1_rstctrl_pa = 0x4824380c,
+	.startup_addr = omap4460_secondary_startup,
+};
+
+static const struct omap_smp_config omap5_cfg __initconst = {
+	.cpu1_rstctrl_pa = 0x48243810,
+	.startup_addr = omap5_secondary_startup,
+};
 
 static DEFINE_SPINLOCK(boot_lock);
 
 void __iomem *omap4_get_scu_base(void)
 {
-	return scu_base;
+	return cfg.scu_base;
 }
 
 #ifdef CONFIG_OMAP5_ERRATA_801819
@@ -93,7 +114,7 @@ static void omap4_secondary_init(unsigned int cpu)
 	 * OMAP443X GP devices- SMP bit isn't accessible.
 	 * OMAP446X GP devices - SMP bit access is enabled on both CPUs.
 	 */
-	if (cpu_is_omap443x() && (omap_type() != OMAP2_DEVICE_TYPE_GP))
+	if (soc_is_omap443x() && (omap_type() != OMAP2_DEVICE_TYPE_GP))
 		omap_secure_dispatcher(OMAP4_PPA_CPU_ACTRL_SMP_INDEX,
 							4, 0, 0, 0, 0, 0);
 
@@ -179,7 +200,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
 		 * Ensure that CPU power state is set to ON to avoid CPU
 		 * powerdomain transition on wfi
 		 */
-		clkdm_wakeup_nolock(cpu1_clkdm);
+		clkdm_deny_idle_nolock(cpu1_clkdm);
 		pwrdm_set_next_pwrst(cpu1_pwrdm, PWRDM_POWER_ON);
 		clkdm_allow_idle_nolock(cpu1_clkdm);
 
@@ -222,9 +243,9 @@ static void __init omap4_smp_init_cpus(void)
 		 * Currently we can't call ioremap here because
 		 * SoC detection won't work until after init_early.
 		 */
-		scu_base =  OMAP2_L4_IO_ADDRESS(scu_a9_get_base());
-		BUG_ON(!scu_base);
-		ncores = scu_get_core_count(scu_base);
+		cfg.scu_base =  OMAP2_L4_IO_ADDRESS(scu_a9_get_base());
+		BUG_ON(!cfg.scu_base);
+		ncores = scu_get_core_count(cfg.scu_base);
 	} else if (cpu_id == CPU_CORTEX_A15) {
 		ncores = OMAP5_CORE_COUNT;
 	}
@@ -242,20 +263,51 @@ static void __init omap4_smp_init_cpus(void)
 
 static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 {
-	void *startup_addr = omap4_secondary_startup;
 	void __iomem *base = omap_get_wakeupgen_base();
+	const struct omap_smp_config *c = NULL;
+
+	if (soc_is_omap443x())
+		c = &omap443x_cfg;
+	else if (soc_is_omap446x())
+		c = &omap446x_cfg;
+	else if (soc_is_dra74x() || soc_is_omap54xx())
+		c = &omap5_cfg;
+
+	if (!c) {
+		pr_err("%s Unknown SMP SoC?\n", __func__);
+		return;
+	}
+
+	/* Must preserve cfg.scu_base set earlier */
+	cfg.cpu1_rstctrl_pa = c->cpu1_rstctrl_pa;
+	cfg.startup_addr = c->startup_addr;
+
+	if (soc_is_dra74x() || soc_is_omap54xx()) {
+		if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE)
+			cfg.startup_addr = omap5_secondary_hyp_startup;
+		omap5_erratum_workaround_801819();
+	}
+
+	cfg.cpu1_rstctrl_va = ioremap(cfg.cpu1_rstctrl_pa, 4);
+	if (!cfg.cpu1_rstctrl_va)
+		return;
 
 	/*
 	 * Initialise the SCU and wake up the secondary core using
 	 * wakeup_secondary().
 	 */
-	if (scu_base)
-		scu_enable(scu_base);
+	if (cfg.scu_base)
+		scu_enable(cfg.scu_base);
 
-	if (cpu_is_omap446x())
-		startup_addr = omap4460_secondary_startup;
-	if (soc_is_dra74x() || soc_is_omap54xx())
-		omap5_erratum_workaround_801819();
+	/*
+	 * Reset CPU1 before configuring, otherwise kexec will
+	 * end up trying to use old kernel startup address.
+	 */
+	if (cfg.cpu1_rstctrl_va) {
+		writel_relaxed(1, cfg.cpu1_rstctrl_va);
+		readl_relaxed(cfg.cpu1_rstctrl_va);
+		writel_relaxed(0, cfg.cpu1_rstctrl_va);
+	}
 
 	/*
 	 * Write the address of secondary startup routine into the
@@ -264,19 +316,10 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 	 * A barrier is added to ensure that write buffer is drained
 	 */
 	if (omap_secure_apis_support())
-		omap_auxcoreboot_addr(virt_to_phys(startup_addr));
+		omap_auxcoreboot_addr(virt_to_phys(cfg.startup_addr));
 	else
-		/*
-		 * If the boot CPU is in HYP mode then start secondary
-		 * CPU in HYP mode as well.
-		 */
-		if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE)
-			writel_relaxed(virt_to_phys(omap5_secondary_hyp_startup),
-				       base + OMAP_AUX_CORE_BOOT_1);
-		else
-			writel_relaxed(virt_to_phys(omap5_secondary_startup),
-				       base + OMAP_AUX_CORE_BOOT_1);
-
+		writel_relaxed(virt_to_phys(cfg.startup_addr),
+			       base + OMAP_AUX_CORE_BOOT_1);
 }
 
 const struct smp_operations omap4_smp_ops __initconst = {
@@ -286,5 +329,6 @@ const struct smp_operations omap4_smp_ops __initconst = {
 	.smp_boot_secondary	= omap4_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= omap4_cpu_die,
+	.cpu_kill		= omap4_cpu_kill,
 #endif
 };
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index 949696b6f17b..cf65ab8bb004 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -61,7 +61,7 @@ static phys_addr_t dram_sync_paddr;
 static u32 dram_sync_size;
 
 /*
- * The OMAP4 bus structure contains asynchrnous bridges which can buffer
+ * The OMAP4 bus structure contains asynchronous bridges which can buffer
  * data writes from the MPU. These asynchronous bridges can be found on
  * paths between the MPU to EMIF, and the MPU to L3 interconnects.
  *
@@ -266,10 +266,11 @@ void __iomem *omap4_get_sar_ram_base(void)
 }
 
 /*
- * SAR RAM used to save and restore the HW
- * context in low power modes
+ * SAR RAM used to save and restore the HW context in low power modes.
+ * Note that we need to initialize this very early for kexec. See
+ * omap4_mpuss_early_init().
  */
-static int __init omap4_sar_ram_init(void)
+void __init omap4_sar_ram_init(void)
 {
 	unsigned long sar_base;
 
@@ -282,16 +283,13 @@ static int __init omap4_sar_ram_init(void)
 	else if (soc_is_omap54xx())
 		sar_base = OMAP54XX_SAR_RAM_BASE;
 	else
-		return -ENOMEM;
+		return;
 
 	/* Static mapping, never released */
 	sar_ram_base = ioremap(sar_base, SZ_16K);
 	if (WARN_ON(!sar_ram_base))
-		return -ENOMEM;
-
-	return 0;
+		return;
 }
-omap_early_initcall(omap4_sar_ram_init);
 
 static const struct of_device_id intc_match[] = {
 	{ .compatible = "ti,omap4-wugen-mpu", },
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 208f11563036..e920dd83e443 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -63,7 +63,22 @@ static void _add_clkdev(struct omap_device *od, const char *clk_alias,
 		return;
 	}
 
-	rc = clk_add_alias(clk_alias, dev_name(&od->pdev->dev), clk_name, NULL);
+	r = clk_get_sys(NULL, clk_name);
+
+	if (IS_ERR(r) && of_have_populated_dt()) {
+		struct of_phandle_args clkspec;
+
+		clkspec.np = of_find_node_by_name(NULL, clk_name);
+
+		r = of_clk_get_from_provider(&clkspec);
+
+		rc = clk_register_clkdev(r, clk_alias,
+					 dev_name(&od->pdev->dev));
+	} else {
+		rc = clk_add_alias(clk_alias, dev_name(&od->pdev->dev),
+				   clk_name, NULL);
+	}
+
 	if (rc) {
 		if (rc == -ENODEV || rc == -ENOMEM)
 			dev_err(&od->pdev->dev,
@@ -268,7 +283,7 @@ static int _omap_device_idle_hwmods(struct omap_device *od)
  * function returns a value different than the value the caller got
  * the last time it called this function.
  *
- * If any hwmods exist for the omap_device assoiated with @pdev,
+ * If any hwmods exist for the omap_device associated with @pdev,
  * return the context loss counter for that hwmod, otherwise return
  * zero.
  */
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 83cb527755a9..5b709383381c 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -178,6 +178,11 @@
  */
 #define OMAP4_RST_CTRL_ST_OFFSET	4
 
+/*
+ * Maximum length for module clock handle names
+ */
+#define MOD_CLK_MAX_NAME_LEN		32
+
 /**
  * struct omap_hwmod_soc_ops - fn ptrs for some SoC-specific operations
  * @enable_module: function to enable a module (via MODULEMODE)
@@ -200,6 +205,7 @@ struct omap_hwmod_soc_ops {
 	int (*init_clkdm)(struct omap_hwmod *oh);
 	void (*update_context_lost)(struct omap_hwmod *oh);
 	int (*get_context_lost)(struct omap_hwmod *oh);
+	int (*disable_direct_prcm)(struct omap_hwmod *oh);
 };
 
 /* soc_ops: adapts the omap_hwmod code to the currently-booted SoC */
@@ -776,17 +782,35 @@ static int _del_initiator_dep(struct omap_hwmod *oh, struct omap_hwmod *init_oh)
  * @oh: struct omap_hwmod *
  *
  * Called from _init_clocks().  Populates the @oh _clk (main
- * functional clock pointer) if a main_clk is present.  Returns 0 on
- * success or -EINVAL on error.
+ * functional clock pointer) if a clock matching the hwmod name is found,
+ * or a main_clk is present.  Returns 0 on success or -EINVAL on error.
  */
 static int _init_main_clk(struct omap_hwmod *oh)
 {
 	int ret = 0;
+	char name[MOD_CLK_MAX_NAME_LEN];
+	struct clk *clk;
 
-	if (!oh->main_clk)
-		return 0;
+	/* +7 magic comes from '_mod_ck' suffix */
+	if (strlen(oh->name) + 7 > MOD_CLK_MAX_NAME_LEN)
+		pr_warn("%s: warning: cropping name for %s\n", __func__,
+			oh->name);
+
+	strncpy(name, oh->name, MOD_CLK_MAX_NAME_LEN - 7);
+	strcat(name, "_mod_ck");
+
+	clk = clk_get(NULL, name);
+	if (!IS_ERR(clk)) {
+		oh->_clk = clk;
+		soc_ops.disable_direct_prcm(oh);
+		oh->main_clk = kstrdup(name, GFP_KERNEL);
+	} else {
+		if (!oh->main_clk)
+			return 0;
+
+		oh->_clk = clk_get(NULL, oh->main_clk);
+	}
 
-	oh->_clk = clk_get(NULL, oh->main_clk);
 	if (IS_ERR(oh->_clk)) {
 		pr_warn("omap_hwmod: %s: cannot clk_get main_clk %s\n",
 			oh->name, oh->main_clk);
@@ -1678,7 +1702,6 @@ static int _deassert_hardreset(struct omap_hwmod *oh, const char *name)
 {
 	struct omap_hwmod_rst_info ohri;
 	int ret = -EINVAL;
-	int hwsup = 0;
 
 	if (!oh)
 		return -EINVAL;
@@ -1696,7 +1719,7 @@ static int _deassert_hardreset(struct omap_hwmod *oh, const char *name)
 		 * might not be completed. The clockdomain can be set
 		 * in HW_AUTO only when the module become ready.
 		 */
-		hwsup = clkdm_in_hwsup(oh->clkdm);
+		clkdm_deny_idle(oh->clkdm);
 		ret = clkdm_hwmod_enable(oh->clkdm, oh);
 		if (ret) {
 			WARN(1, "omap_hwmod: %s: could not enable clockdomain %s: %d\n",
@@ -1723,8 +1746,7 @@ static int _deassert_hardreset(struct omap_hwmod *oh, const char *name)
 		 * Set the clockdomain to HW_AUTO, assuming that the
 		 * previous state was HW_AUTO.
 		 */
-		if (hwsup)
-			clkdm_allow_idle(oh->clkdm);
+		clkdm_allow_idle(oh->clkdm);
 
 		clkdm_hwmod_disable(oh->clkdm, oh);
 	}
@@ -2078,7 +2100,6 @@ static int _enable_preprogram(struct omap_hwmod *oh)
 static int _enable(struct omap_hwmod *oh)
 {
 	int r;
-	int hwsup = 0;
 
 	pr_debug("omap_hwmod: %s: enabling\n", oh->name);
 
@@ -2138,8 +2159,7 @@ static int _enable(struct omap_hwmod *oh)
 		 * completely the module. The clockdomain can be set
 		 * in HW_AUTO only when the module become ready.
 		 */
-		hwsup = clkdm_in_hwsup(oh->clkdm) &&
-			!clkdm_missing_idle_reporting(oh->clkdm);
+		clkdm_deny_idle(oh->clkdm);
 		r = clkdm_hwmod_enable(oh->clkdm, oh);
 		if (r) {
 			WARN(1, "omap_hwmod: %s: could not enable clockdomain %s: %d\n",
@@ -2159,14 +2179,10 @@ static int _enable(struct omap_hwmod *oh)
 
 	r = (soc_ops.wait_target_ready) ? soc_ops.wait_target_ready(oh) :
 		-EINVAL;
-	if (!r) {
-		/*
-		 * Set the clockdomain to HW_AUTO only if the target is ready,
-		 * assuming that the previous state was HW_AUTO
-		 */
-		if (oh->clkdm && hwsup)
-			clkdm_allow_idle(oh->clkdm);
+	if (oh->clkdm)
+		clkdm_allow_idle(oh->clkdm);
 
+	if (!r) {
 		oh->_state = _HWMOD_STATE_ENABLED;
 
 		/* Access the sysconfig only if the target is ready */
@@ -2220,6 +2236,9 @@ static int _idle(struct omap_hwmod *oh)
 		_idle_sysc(oh);
 	_del_initiator_dep(oh, mpu_oh);
 
+	if (oh->clkdm)
+		clkdm_deny_idle(oh->clkdm);
+
 	if (oh->flags & HWMOD_BLOCK_WFI)
 		cpu_idle_poll_ctrl(false);
 	if (soc_ops.disable_module)
@@ -2232,8 +2251,10 @@ static int _idle(struct omap_hwmod *oh)
 	 * transition to complete properly.
 	 */
 	_disable_clocks(oh);
-	if (oh->clkdm)
+	if (oh->clkdm) {
+		clkdm_allow_idle(oh->clkdm);
 		clkdm_hwmod_disable(oh->clkdm, oh);
+	}
 
 	/* Mux pins for device idle if populated */
 	if (oh->mux && oh->mux->pads_dynamic) {
@@ -3091,6 +3112,25 @@ static int _omap4_is_hardreset_asserted(struct omap_hwmod *oh,
 }
 
 /**
+ * _omap4_disable_direct_prcm - disable direct PRCM control for hwmod
+ * @oh: struct omap_hwmod * to disable control for
+ *
+ * Disables direct PRCM clkctrl done by hwmod core. Instead, the hwmod
+ * will be using its main_clk to enable/disable the module. Returns
+ * 0 if successful.
+ */
+static int _omap4_disable_direct_prcm(struct omap_hwmod *oh)
+{
+	if (!oh)
+		return -EINVAL;
+
+	oh->prcm.omap4.clkctrl_offs = 0;
+	oh->prcm.omap4.modulemode = 0;
+
+	return 0;
+}
+
+/**
  * _am33xx_deassert_hardreset - call AM33XX PRM hardreset fn with hwmod args
  * @oh: struct omap_hwmod * to deassert hardreset
  * @ohri: hardreset line data
@@ -3913,6 +3953,7 @@ void __init omap_hwmod_init(void)
 		soc_ops.init_clkdm = _init_clkdm;
 		soc_ops.update_context_lost = _omap4_update_context_lost;
 		soc_ops.get_context_lost = _omap4_get_context_lost;
+		soc_ops.disable_direct_prcm = _omap4_disable_direct_prcm;
 	} else if (cpu_is_ti814x() || cpu_is_ti816x() || soc_is_am33xx() ||
 		   soc_is_am43xx()) {
 		soc_ops.enable_module = _omap4_enable_module;
@@ -3922,6 +3963,7 @@ void __init omap_hwmod_init(void)
 		soc_ops.deassert_hardreset = _am33xx_deassert_hardreset;
 		soc_ops.is_hardreset_asserted = _omap4_is_hardreset_asserted;
 		soc_ops.init_clkdm = _init_clkdm;
+		soc_ops.disable_direct_prcm = _omap4_disable_direct_prcm;
 	} else {
 		WARN(1, "omap_hwmod: unknown SoC type\n");
 	}
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_common_data.h b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_common_data.h
index 7f737965f543..d3e61d1a02d7 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_common_data.h
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_common_data.h
@@ -36,17 +36,8 @@ extern struct omap_hwmod_ocp_if am33xx_l4_per__gpio3;
 extern struct omap_hwmod_ocp_if am33xx_cpgmac0__mdio;
 extern struct omap_hwmod_ocp_if am33xx_l4_ls__elm;
 extern struct omap_hwmod_ocp_if am33xx_l4_ls__epwmss0;
-extern struct omap_hwmod_ocp_if am33xx_epwmss0__ecap0;
-extern struct omap_hwmod_ocp_if am33xx_epwmss0__eqep0;
-extern struct omap_hwmod_ocp_if am33xx_epwmss0__ehrpwm0;
 extern struct omap_hwmod_ocp_if am33xx_l4_ls__epwmss1;
-extern struct omap_hwmod_ocp_if am33xx_epwmss1__ecap1;
-extern struct omap_hwmod_ocp_if am33xx_epwmss1__eqep1;
-extern struct omap_hwmod_ocp_if am33xx_epwmss1__ehrpwm1;
 extern struct omap_hwmod_ocp_if am33xx_l4_ls__epwmss2;
-extern struct omap_hwmod_ocp_if am33xx_epwmss2__ecap2;
-extern struct omap_hwmod_ocp_if am33xx_epwmss2__eqep2;
-extern struct omap_hwmod_ocp_if am33xx_epwmss2__ehrpwm2;
 extern struct omap_hwmod_ocp_if am33xx_l3_s__gpmc;
 extern struct omap_hwmod_ocp_if am33xx_l4_per__i2c2;
 extern struct omap_hwmod_ocp_if am33xx_l4_per__i2c3;
@@ -98,17 +89,8 @@ extern struct omap_hwmod am33xx_dcan0_hwmod;
 extern struct omap_hwmod am33xx_dcan1_hwmod;
 extern struct omap_hwmod am33xx_elm_hwmod;
 extern struct omap_hwmod am33xx_epwmss0_hwmod;
-extern struct omap_hwmod am33xx_ecap0_hwmod;
-extern struct omap_hwmod am33xx_eqep0_hwmod;
-extern struct omap_hwmod am33xx_ehrpwm0_hwmod;
 extern struct omap_hwmod am33xx_epwmss1_hwmod;
-extern struct omap_hwmod am33xx_ecap1_hwmod;
-extern struct omap_hwmod am33xx_eqep1_hwmod;
-extern struct omap_hwmod am33xx_ehrpwm1_hwmod;
 extern struct omap_hwmod am33xx_epwmss2_hwmod;
-extern struct omap_hwmod am33xx_ecap2_hwmod;
-extern struct omap_hwmod am33xx_eqep2_hwmod;
-extern struct omap_hwmod am33xx_ehrpwm2_hwmod;
 extern struct omap_hwmod am33xx_gpio1_hwmod;
 extern struct omap_hwmod am33xx_gpio2_hwmod;
 extern struct omap_hwmod am33xx_gpio3_hwmod;
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_interconnect_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_interconnect_data.c
index 1c210cb2b8c1..10dff2f0086a 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_interconnect_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_interconnect_data.c
@@ -176,28 +176,6 @@ struct omap_hwmod_ocp_if am33xx_l4_ls__epwmss0 = {
 	.user		= OCP_USER_MPU,
 };
 
-struct omap_hwmod_ocp_if am33xx_epwmss0__ecap0 = {
-	.master		= &am33xx_epwmss0_hwmod,
-	.slave		= &am33xx_ecap0_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
-struct omap_hwmod_ocp_if am33xx_epwmss0__eqep0 = {
-	.master		= &am33xx_epwmss0_hwmod,
-	.slave		= &am33xx_eqep0_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
-struct omap_hwmod_ocp_if am33xx_epwmss0__ehrpwm0 = {
-	.master		= &am33xx_epwmss0_hwmod,
-	.slave		= &am33xx_ehrpwm0_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
-
 static struct omap_hwmod_addr_space am33xx_epwmss1_addr_space[] = {
 	{
 		.pa_start	= 0x48302000,
@@ -215,27 +193,6 @@ struct omap_hwmod_ocp_if am33xx_l4_ls__epwmss1 = {
 	.user		= OCP_USER_MPU,
 };
 
-struct omap_hwmod_ocp_if am33xx_epwmss1__ecap1 = {
-	.master		= &am33xx_epwmss1_hwmod,
-	.slave		= &am33xx_ecap1_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
-struct omap_hwmod_ocp_if am33xx_epwmss1__eqep1 = {
-	.master		= &am33xx_epwmss1_hwmod,
-	.slave		= &am33xx_eqep1_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
-struct omap_hwmod_ocp_if am33xx_epwmss1__ehrpwm1 = {
-	.master		= &am33xx_epwmss1_hwmod,
-	.slave		= &am33xx_ehrpwm1_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
 static struct omap_hwmod_addr_space am33xx_epwmss2_addr_space[] = {
 	{
 		.pa_start	= 0x48304000,
@@ -253,27 +210,6 @@ struct omap_hwmod_ocp_if am33xx_l4_ls__epwmss2 = {
 	.user		= OCP_USER_MPU,
 };
 
-struct omap_hwmod_ocp_if am33xx_epwmss2__ecap2 = {
-	.master		= &am33xx_epwmss2_hwmod,
-	.slave		= &am33xx_ecap2_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
-struct omap_hwmod_ocp_if am33xx_epwmss2__eqep2 = {
-	.master		= &am33xx_epwmss2_hwmod,
-	.slave		= &am33xx_eqep2_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
-struct omap_hwmod_ocp_if am33xx_epwmss2__ehrpwm2 = {
-	.master		= &am33xx_epwmss2_hwmod,
-	.slave		= &am33xx_ehrpwm2_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
 /* l3s cfg -> gpmc */
 struct omap_hwmod_ocp_if am33xx_l3_s__gpmc = {
 	.master		= &am33xx_l3_s_hwmod,
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
index aed33621deeb..55c5878577f4 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
@@ -449,18 +449,6 @@ struct omap_hwmod_class am33xx_epwmss_hwmod_class = {
 	.sysc		= &am33xx_epwmss_sysc,
 };
 
-static struct omap_hwmod_class am33xx_ecap_hwmod_class = {
-	.name		= "ecap",
-};
-
-static struct omap_hwmod_class am33xx_eqep_hwmod_class = {
-	.name		= "eqep",
-};
-
-struct omap_hwmod_class am33xx_ehrpwm_hwmod_class = {
-	.name		= "ehrpwm",
-};
-
 /* epwmss0 */
 struct omap_hwmod am33xx_epwmss0_hwmod = {
 	.name		= "epwmss0",
@@ -474,30 +462,6 @@ struct omap_hwmod am33xx_epwmss0_hwmod = {
 	},
 };
 
-/* ecap0 */
-struct omap_hwmod am33xx_ecap0_hwmod = {
-	.name		= "ecap0",
-	.class		= &am33xx_ecap_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
-/* eqep0 */
-struct omap_hwmod am33xx_eqep0_hwmod = {
-	.name		= "eqep0",
-	.class		= &am33xx_eqep_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
-/* ehrpwm0 */
-struct omap_hwmod am33xx_ehrpwm0_hwmod = {
-	.name		= "ehrpwm0",
-	.class		= &am33xx_ehrpwm_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
 /* epwmss1 */
 struct omap_hwmod am33xx_epwmss1_hwmod = {
 	.name		= "epwmss1",
@@ -511,30 +475,6 @@ struct omap_hwmod am33xx_epwmss1_hwmod = {
 	},
 };
 
-/* ecap1 */
-struct omap_hwmod am33xx_ecap1_hwmod = {
-	.name		= "ecap1",
-	.class		= &am33xx_ecap_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
-/* eqep1 */
-struct omap_hwmod am33xx_eqep1_hwmod = {
-	.name		= "eqep1",
-	.class		= &am33xx_eqep_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
-/* ehrpwm1 */
-struct omap_hwmod am33xx_ehrpwm1_hwmod = {
-	.name		= "ehrpwm1",
-	.class		= &am33xx_ehrpwm_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
 /* epwmss2 */
 struct omap_hwmod am33xx_epwmss2_hwmod = {
 	.name		= "epwmss2",
@@ -548,30 +488,6 @@ struct omap_hwmod am33xx_epwmss2_hwmod = {
 	},
 };
 
-/* ecap2 */
-struct omap_hwmod am33xx_ecap2_hwmod = {
-	.name		= "ecap2",
-	.class		= &am33xx_ecap_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
-/* eqep2 */
-struct omap_hwmod am33xx_eqep2_hwmod = {
-	.name		= "eqep2",
-	.class		= &am33xx_eqep_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
-/* ehrpwm2 */
-struct omap_hwmod am33xx_ehrpwm2_hwmod = {
-	.name		= "ehrpwm2",
-	.class		= &am33xx_ehrpwm_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
 /*
  * 'gpio' class: for gpio 0,1,2,3
  */
@@ -1476,6 +1392,7 @@ static void omap_hwmod_am43xx_rst(void)
 {
 	RSTCTRL(am33xx_pruss_hwmod, AM43XX_RM_PER_RSTCTRL_OFFSET);
 	RSTCTRL(am33xx_gfx_hwmod, AM43XX_RM_GFX_RSTCTRL_OFFSET);
+	RSTST(am33xx_pruss_hwmod, AM43XX_RM_PER_RSTST_OFFSET);
 	RSTST(am33xx_gfx_hwmod, AM43XX_RM_GFX_RSTST_OFFSET);
 }
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
index cc0791d9125b..e1c2025d6d3e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
@@ -593,17 +593,8 @@ static struct omap_hwmod_ocp_if *am33xx_hwmod_ocp_ifs[] __initdata = {
 	&am33xx_l4_ls__spinlock,
 	&am33xx_l4_ls__elm,
 	&am33xx_l4_ls__epwmss0,
-	&am33xx_epwmss0__ecap0,
-	&am33xx_epwmss0__eqep0,
-	&am33xx_epwmss0__ehrpwm0,
 	&am33xx_l4_ls__epwmss1,
-	&am33xx_epwmss1__ecap1,
-	&am33xx_epwmss1__eqep1,
-	&am33xx_epwmss1__ehrpwm1,
 	&am33xx_l4_ls__epwmss2,
-	&am33xx_epwmss2__ecap2,
-	&am33xx_epwmss2__eqep2,
-	&am33xx_epwmss2__ehrpwm2,
 	&am33xx_l3_s__gpmc,
 	&am33xx_l3_main__lcdc,
 	&am33xx_l4_ls__mcspi0,
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 9869a75c5d96..d72ee6185d5e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -1322,16 +1322,8 @@ static struct omap_hwmod omap3xxx_mcbsp2_sidetone_hwmod = {
 	.name		= "mcbsp2_sidetone",
 	.class		= &omap3xxx_mcbsp_sidetone_hwmod_class,
 	.mpu_irqs	= omap3xxx_mcbsp2_sidetone_irqs,
-	.main_clk	= "mcbsp2_fck",
-	.prcm		= {
-		.omap2 = {
-			.prcm_reg_id = 1,
-			 .module_bit = OMAP3430_EN_MCBSP2_SHIFT,
-			.module_offs = OMAP3430_PER_MOD,
-			.idlest_reg_id = 1,
-			.idlest_idle_bit = OMAP3430_ST_MCBSP2_SHIFT,
-		},
-	},
+	.main_clk	= "mcbsp2_ick",
+	.flags		= HWMOD_NO_IDLEST,
 };
 
 /* mcbsp3_sidetone */
@@ -1344,16 +1336,8 @@ static struct omap_hwmod omap3xxx_mcbsp3_sidetone_hwmod = {
 	.name		= "mcbsp3_sidetone",
 	.class		= &omap3xxx_mcbsp_sidetone_hwmod_class,
 	.mpu_irqs	= omap3xxx_mcbsp3_sidetone_irqs,
-	.main_clk	= "mcbsp3_fck",
-	.prcm		= {
-		.omap2 = {
-			.prcm_reg_id = 1,
-			.module_bit = OMAP3430_EN_MCBSP3_SHIFT,
-			.module_offs = OMAP3430_PER_MOD,
-			.idlest_reg_id = 1,
-			.idlest_idle_bit = OMAP3430_ST_MCBSP3_SHIFT,
-		},
-	},
+	.main_clk	= "mcbsp3_ick",
+	.flags		= HWMOD_NO_IDLEST,
 };
 
 /* SR common */
diff --git a/arch/arm/mach-omap2/omap_hwmod_43xx_data.c b/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
index 97fd399202dc..61f2f301d739 100644
--- a/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
@@ -202,13 +202,6 @@ static struct omap_hwmod am43xx_epwmss3_hwmod = {
 	},
 };
 
-static struct omap_hwmod am43xx_ehrpwm3_hwmod = {
-	.name		= "ehrpwm3",
-	.class		= &am33xx_ehrpwm_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
 static struct omap_hwmod am43xx_epwmss4_hwmod = {
 	.name		= "epwmss4",
 	.class		= &am33xx_epwmss_hwmod_class,
@@ -222,13 +215,6 @@ static struct omap_hwmod am43xx_epwmss4_hwmod = {
 	},
 };
 
-static struct omap_hwmod am43xx_ehrpwm4_hwmod = {
-	.name		= "ehrpwm4",
-	.class		= &am33xx_ehrpwm_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
 static struct omap_hwmod am43xx_epwmss5_hwmod = {
 	.name		= "epwmss5",
 	.class		= &am33xx_epwmss_hwmod_class,
@@ -242,13 +228,6 @@ static struct omap_hwmod am43xx_epwmss5_hwmod = {
 	},
 };
 
-static struct omap_hwmod am43xx_ehrpwm5_hwmod = {
-	.name		= "ehrpwm5",
-	.class		= &am33xx_ehrpwm_hwmod_class,
-	.clkdm_name	= "l4ls_clkdm",
-	.main_clk	= "l4ls_gclk",
-};
-
 static struct omap_hwmod am43xx_spi2_hwmod = {
 	.name		= "spi2",
 	.class		= &am33xx_spi_hwmod_class,
@@ -744,13 +723,6 @@ static struct omap_hwmod_ocp_if am43xx_l4_ls__epwmss3 = {
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_ocp_if am43xx_epwmss3__ehrpwm3 = {
-	.master		= &am43xx_epwmss3_hwmod,
-	.slave		= &am43xx_ehrpwm3_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
 static struct omap_hwmod_ocp_if am43xx_l4_ls__epwmss4 = {
 	.master		= &am33xx_l4_ls_hwmod,
 	.slave		= &am43xx_epwmss4_hwmod,
@@ -758,13 +730,6 @@ static struct omap_hwmod_ocp_if am43xx_l4_ls__epwmss4 = {
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_ocp_if am43xx_epwmss4__ehrpwm4 = {
-	.master		= &am43xx_epwmss4_hwmod,
-	.slave		= &am43xx_ehrpwm4_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
 static struct omap_hwmod_ocp_if am43xx_l4_ls__epwmss5 = {
 	.master		= &am33xx_l4_ls_hwmod,
 	.slave		= &am43xx_epwmss5_hwmod,
@@ -772,13 +737,6 @@ static struct omap_hwmod_ocp_if am43xx_l4_ls__epwmss5 = {
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_ocp_if am43xx_epwmss5__ehrpwm5 = {
-	.master		= &am43xx_epwmss5_hwmod,
-	.slave		= &am43xx_ehrpwm5_hwmod,
-	.clk		= "l4ls_gclk",
-	.user		= OCP_USER_MPU,
-};
-
 static struct omap_hwmod_ocp_if am43xx_l4_ls__mcspi2 = {
 	.master		= &am33xx_l4_ls_hwmod,
 	.slave		= &am43xx_spi2_hwmod,
@@ -919,11 +877,8 @@ static struct omap_hwmod_ocp_if *am43xx_hwmod_ocp_ifs[] __initdata = {
 	&am43xx_l4_ls__timer10,
 	&am43xx_l4_ls__timer11,
 	&am43xx_l4_ls__epwmss3,
-	&am43xx_epwmss3__ehrpwm3,
 	&am43xx_l4_ls__epwmss4,
-	&am43xx_epwmss4__ehrpwm4,
 	&am43xx_l4_ls__epwmss5,
-	&am43xx_epwmss5__ehrpwm5,
 	&am43xx_l4_ls__mcspi2,
 	&am43xx_l4_ls__mcspi3,
 	&am43xx_l4_ls__mcspi4,
@@ -982,17 +937,8 @@ static struct omap_hwmod_ocp_if *am43xx_hwmod_ocp_ifs[] __initdata = {
 	&am33xx_l4_ls__spinlock,
 	&am33xx_l4_ls__elm,
 	&am33xx_l4_ls__epwmss0,
-	&am33xx_epwmss0__ecap0,
-	&am33xx_epwmss0__eqep0,
-	&am33xx_epwmss0__ehrpwm0,
 	&am33xx_l4_ls__epwmss1,
-	&am33xx_epwmss1__ecap1,
-	&am33xx_epwmss1__eqep1,
-	&am33xx_epwmss1__ehrpwm1,
 	&am33xx_l4_ls__epwmss2,
-	&am33xx_epwmss2__ecap2,
-	&am33xx_epwmss2__eqep2,
-	&am33xx_epwmss2__ehrpwm2,
 	&am33xx_l3_s__gpmc,
 	&am33xx_l4_ls__mcspi0,
 	&am33xx_l4_ls__mcspi1,
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index d0e7e5259ec3..1ab7096af8e2 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -2905,58 +2905,27 @@ static struct omap_hwmod_ocp_if dra7xx_l3_main_1__tptc1 = {
 	.user		= OCP_USER_MPU,
 };
 
-static struct omap_hwmod_addr_space dra7xx_dss_addrs[] = {
-	{
-		.name		= "family",
-		.pa_start	= 0x58000000,
-		.pa_end		= 0x5800007f,
-		.flags		= ADDR_TYPE_RT
-	},
-};
-
 /* l3_main_1 -> dss */
 static struct omap_hwmod_ocp_if dra7xx_l3_main_1__dss = {
 	.master		= &dra7xx_l3_main_1_hwmod,
 	.slave		= &dra7xx_dss_hwmod,
 	.clk		= "l3_iclk_div",
-	.addr		= dra7xx_dss_addrs,
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
-static struct omap_hwmod_addr_space dra7xx_dss_dispc_addrs[] = {
-	{
-		.name		= "dispc",
-		.pa_start	= 0x58001000,
-		.pa_end		= 0x58001fff,
-		.flags		= ADDR_TYPE_RT
-	},
-};
-
 /* l3_main_1 -> dispc */
 static struct omap_hwmod_ocp_if dra7xx_l3_main_1__dispc = {
 	.master		= &dra7xx_l3_main_1_hwmod,
 	.slave		= &dra7xx_dss_dispc_hwmod,
 	.clk		= "l3_iclk_div",
-	.addr		= dra7xx_dss_dispc_addrs,
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
-static struct omap_hwmod_addr_space dra7xx_dss_hdmi_addrs[] = {
-	{
-		.name		= "hdmi_wp",
-		.pa_start	= 0x58040000,
-		.pa_end		= 0x580400ff,
-		.flags		= ADDR_TYPE_RT
-	},
-	{ }
-};
-
 /* l3_main_1 -> dispc */
 static struct omap_hwmod_ocp_if dra7xx_l3_main_1__hdmi = {
 	.master		= &dra7xx_l3_main_1_hwmod,
 	.slave		= &dra7xx_dss_hdmi_hwmod,
 	.clk		= "l3_iclk_div",
-	.addr		= dra7xx_dss_hdmi_addrs,
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
@@ -3410,21 +3379,11 @@ static struct omap_hwmod_ocp_if dra7xx_l4_cfg__pciess2 = {
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
-static struct omap_hwmod_addr_space dra7xx_qspi_addrs[] = {
-	{
-		.pa_start	= 0x4b300000,
-		.pa_end		= 0x4b30007f,
-		.flags		= ADDR_TYPE_RT
-	},
-	{ }
-};
-
 /* l3_main_1 -> qspi */
 static struct omap_hwmod_ocp_if dra7xx_l3_main_1__qspi = {
 	.master		= &dra7xx_l3_main_1_hwmod,
 	.slave		= &dra7xx_qspi_hwmod,
 	.clk		= "l3_iclk_div",
-	.addr		= dra7xx_qspi_addrs,
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
index df8327713d06..b82b77cff24c 100644
--- a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
@@ -243,7 +243,7 @@ static struct omap_hwmod_class ti81xx_rtc_hwmod_class = {
 	.sysc		= &ti81xx_rtc_sysc,
 };
 
-struct omap_hwmod ti81xx_rtc_hwmod = {
+static struct omap_hwmod ti81xx_rtc_hwmod = {
 	.name		= "rtc",
 	.class		= &ti81xx_rtc_hwmod_class,
 	.clkdm_name	= "alwon_l3s_clkdm",
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 6571ad959908..05e20aaf68dd 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -26,6 +26,7 @@
 #include <linux/platform_data/wkup_m3.h>
 #include <linux/platform_data/pwm_omap_dmtimer.h>
 #include <linux/platform_data/media/ir-rx51.h>
+#include <linux/platform_data/asoc-ti-mcbsp.h>
 #include <plat/dmtimer.h>
 
 #include "common.h"
@@ -273,8 +274,6 @@ static struct platform_device omap3_rom_rng_device = {
 	},
 };
 
-static struct platform_device rx51_lirc_device;
-
 static void __init nokia_n900_legacy_init(void)
 {
 	hsmmc2_internal_input_clk();
@@ -293,10 +292,7 @@ static void __init nokia_n900_legacy_init(void)
 
 		pr_info("RX-51: Registering OMAP3 HWRNG device\n");
 		platform_device_register(&omap3_rom_rng_device);
-
 	}
-
-	platform_device_register(&rx51_lirc_device);
 }
 
 static void __init omap3_tao3530_legacy_init(void)
@@ -491,10 +487,6 @@ static struct pwm_omap_dmtimer_pdata pwm_dmtimer_pdata = {
 
 static struct lirc_rx51_platform_data __maybe_unused rx51_lirc_data = {
 	.set_max_mpu_wakeup_lat = omap_pm_set_max_mpu_wakeup_lat,
-	.pwm_timer = 9, /* Use GPT 9 for CIR */
-#if IS_ENABLED(CONFIG_OMAP_DM_TIMER)
-	.dmtimer = &pwm_dmtimer_pdata,
-#endif
 };
 
 static struct platform_device __maybe_unused rx51_lirc_device = {
@@ -505,6 +497,16 @@ static struct platform_device __maybe_unused rx51_lirc_device = {
 	},
 };
 
+#if IS_ENABLED(CONFIG_SND_OMAP_SOC_MCBSP)
+static struct omap_mcbsp_platform_data mcbsp_pdata;
+static void __init omap3_mcbsp_init(void)
+{
+	omap3_mcbsp_init_pdata_callback(&mcbsp_pdata);
+}
+#else
+static void __init omap3_mcbsp_init(void) {}
+#endif
+
 /*
  * Few boards still need auxdata populated before we populate
  * the dev entries in of_platform_populate().
@@ -532,10 +534,16 @@ static struct of_dev_auxdata omap_auxdata_lookup[] __initdata = {
 		       &omap3_iommu_pdata),
 	OF_DEV_AUXDATA("ti,omap3-hsmmc", 0x4809c000, "4809c000.mmc", &mmc_pdata[0]),
 	OF_DEV_AUXDATA("ti,omap3-hsmmc", 0x480b4000, "480b4000.mmc", &mmc_pdata[1]),
+	OF_DEV_AUXDATA("nokia,n900-ir", 0, "n900-ir", &rx51_lirc_data),
 	/* Only on am3517 */
 	OF_DEV_AUXDATA("ti,davinci_mdio", 0x5c030000, "davinci_mdio.0", NULL),
 	OF_DEV_AUXDATA("ti,am3517-emac", 0x5c000000, "davinci_emac.0",
 		       &am35xx_emac_pdata),
+	/* McBSP modules with sidetone core */
+#if IS_ENABLED(CONFIG_SND_OMAP_SOC_MCBSP)
+	OF_DEV_AUXDATA("ti,omap3-mcbsp", 0x49022000, "49022000.mcbsp", &mcbsp_pdata),
+	OF_DEV_AUXDATA("ti,omap3-mcbsp", 0x49024000, "49024000.mcbsp", &mcbsp_pdata),
+#endif
 #endif
 #ifdef CONFIG_SOC_AM33XX
 	OF_DEV_AUXDATA("ti,am3352-wkup-m3", 0x44d00000, "44d00000.wkup_m3",
@@ -608,6 +616,8 @@ void __init pdata_quirks_init(const struct of_device_id *omap_dt_match_table)
 	    of_machine_is_compatible("ti,omap3"))
 		omap_sdrc_init(NULL, NULL);
 
+	if (of_machine_is_compatible("ti,omap3"))
+		omap3_mcbsp_init();
 	pdata_quirks_check(auxdata_quirks);
 	of_platform_populate(NULL, omap_dt_match_table,
 			     omap_auxdata_lookup, NULL);
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 2f7b11da7d5d..678d2a31dcb8 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -110,13 +110,7 @@ static void __init omap2_init_processor_devices(void)
 
 int __init omap_pm_clkdms_setup(struct clockdomain *clkdm, void *unused)
 {
-	/* XXX The usecount test is racy */
-	if ((clkdm->flags & CLKDM_CAN_ENABLE_AUTO) &&
-	    !(clkdm->flags & CLKDM_MISSING_IDLE_REPORTING))
-		clkdm_allow_idle(clkdm);
-	else if (clkdm->flags & CLKDM_CAN_FORCE_SLEEP &&
-		 clkdm->usecount == 0)
-		clkdm_sleep(clkdm);
+	clkdm_allow_idle(clkdm);
 	return 0;
 }
 
diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index daf2753de7aa..76eb6ec5f157 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -223,7 +223,6 @@ static int _pwrdm_post_transition_cb(struct powerdomain *pwrdm, void *unused)
  * @pwrdm: struct powerdomain * to operate on
  * @curr_pwrst: current power state of @pwrdm
  * @pwrst: power state to switch to
- * @hwsup: ptr to a bool to return whether the clkdm is hardware-supervised
  *
  * Determine whether the powerdomain needs to be turned on before
  * attempting to switch power states.  Called by
@@ -234,8 +233,7 @@ static int _pwrdm_post_transition_cb(struct powerdomain *pwrdm, void *unused)
  * "Types of sleep_switch" comment above).
  */
 static u8 _pwrdm_save_clkdm_state_and_activate(struct powerdomain *pwrdm,
-					       u8 curr_pwrst, u8 pwrst,
-					       bool *hwsup)
+					       u8 curr_pwrst, u8 pwrst)
 {
 	u8 sleep_switch;
 
@@ -245,8 +243,7 @@ static u8 _pwrdm_save_clkdm_state_and_activate(struct powerdomain *pwrdm,
 		    arch_pwrdm->pwrdm_set_lowpwrstchange) {
 			sleep_switch = LOWPOWERSTATE_SWITCH;
 		} else {
-			*hwsup = clkdm_in_hwsup(pwrdm->pwrdm_clkdms[0]);
-			clkdm_wakeup_nolock(pwrdm->pwrdm_clkdms[0]);
+			clkdm_deny_idle_nolock(pwrdm->pwrdm_clkdms[0]);
 			sleep_switch = FORCEWAKEUP_SWITCH;
 		}
 	} else {
@@ -260,7 +257,6 @@ static u8 _pwrdm_save_clkdm_state_and_activate(struct powerdomain *pwrdm,
  * _pwrdm_restore_clkdm_state - restore the clkdm hwsup state after pwrst change
  * @pwrdm: struct powerdomain * to operate on
  * @sleep_switch: return value from _pwrdm_save_clkdm_state_and_activate()
- * @hwsup: should @pwrdm's first clockdomain be set to hardware-supervised mode?
  *
  * Restore the clockdomain state perturbed by
  * _pwrdm_save_clkdm_state_and_activate(), and call the power state
@@ -271,14 +267,11 @@ static u8 _pwrdm_save_clkdm_state_and_activate(struct powerdomain *pwrdm,
  * software-supervised sleep.  No return value.
  */
 static void _pwrdm_restore_clkdm_state(struct powerdomain *pwrdm,
-				       u8 sleep_switch, bool hwsup)
+				       u8 sleep_switch)
 {
 	switch (sleep_switch) {
 	case FORCEWAKEUP_SWITCH:
-		if (hwsup)
-			clkdm_allow_idle_nolock(pwrdm->pwrdm_clkdms[0]);
-		else
-			clkdm_sleep_nolock(pwrdm->pwrdm_clkdms[0]);
+		clkdm_allow_idle_nolock(pwrdm->pwrdm_clkdms[0]);
 		break;
 	case LOWPOWERSTATE_SWITCH:
 		if (pwrdm->flags & PWRDM_HAS_LOWPOWERSTATECHANGE &&
@@ -1093,7 +1086,6 @@ int omap_set_pwrdm_state(struct powerdomain *pwrdm, u8 pwrst)
 	u8 next_pwrst, sleep_switch;
 	int curr_pwrst;
 	int ret = 0;
-	bool hwsup = false;
 
 	if (!pwrdm || IS_ERR(pwrdm))
 		return -EINVAL;
@@ -1117,14 +1109,14 @@ int omap_set_pwrdm_state(struct powerdomain *pwrdm, u8 pwrst)
 		goto osps_out;
 
 	sleep_switch = _pwrdm_save_clkdm_state_and_activate(pwrdm, curr_pwrst,
-							    pwrst, &hwsup);
+							    pwrst);
 
 	ret = pwrdm_set_next_pwrst(pwrdm, pwrst);
 	if (ret)
 		pr_err("%s: unable to set power state of powerdomain: %s\n",
 		       __func__, pwrdm->name);
 
-	_pwrdm_restore_clkdm_state(pwrdm, sleep_switch, hwsup);
+	_pwrdm_restore_clkdm_state(pwrdm, sleep_switch);
 
 osps_out:
 	pwrdm_unlock(pwrdm);
diff --git a/arch/arm/mach-omap2/prcm43xx.h b/arch/arm/mach-omap2/prcm43xx.h
index 7c34c44eb0ae..babb5db5a3a4 100644
--- a/arch/arm/mach-omap2/prcm43xx.h
+++ b/arch/arm/mach-omap2/prcm43xx.h
@@ -39,6 +39,7 @@
 
 /* RM RSTST offsets */
 #define AM43XX_RM_GFX_RSTST_OFFSET			0x0014
+#define AM43XX_RM_PER_RSTST_OFFSET			0x0014
 #define AM43XX_RM_WKUP_RSTST_OFFSET			0x0014
 
 /* CM instances */
diff --git a/arch/arm/mach-omap2/prm33xx.h b/arch/arm/mach-omap2/prm33xx.h
index 2bc4ec52ba78..66302c6aba61 100644
--- a/arch/arm/mach-omap2/prm33xx.h
+++ b/arch/arm/mach-omap2/prm33xx.h
@@ -52,8 +52,6 @@
 /* PRM.PER_PRM register offsets */
 #define AM33XX_RM_PER_RSTCTRL_OFFSET		0x0000
 #define AM33XX_RM_PER_RSTCTRL			AM33XX_PRM_REGADDR(AM33XX_PRM_PER_MOD, 0x0000)
-#define AM33XX_RM_PER_RSTST_OFFSET		0x0004
-#define AM33XX_RM_PER_RSTST			AM33XX_PRM_REGADDR(AM33XX_PRM_PER_MOD, 0x0004)
 #define AM33XX_PM_PER_PWRSTST_OFFSET		0x0008
 #define AM33XX_PM_PER_PWRSTST			AM33XX_PRM_REGADDR(AM33XX_PRM_PER_MOD, 0x0008)
 #define AM33XX_PM_PER_PWRSTCTRL_OFFSET		0x000c
diff --git a/arch/arm/mach-omap2/sdrc.h b/arch/arm/mach-omap2/sdrc.h
index 645a2a46b213..f11500612983 100644
--- a/arch/arm/mach-omap2/sdrc.h
+++ b/arch/arm/mach-omap2/sdrc.h
@@ -175,8 +175,8 @@ u32 omap2xxx_sdrc_reprogram(u32 level, u32 force);
  * don't adjust it down as your clock period increases the refresh interval
  * will not be met. Setting all parameters for complete worst case may work,
  * but may cut memory performance by 2x. Due to errata the DLLs need to be
- * unlocked and their value needs run time calibration.	A dynamic call is
- * need for that as no single right value exists acorss production samples.
+ * unlocked and their value needs run time calibration. A dynamic call is
+ * need for that as no single right value exists across production samples.
  *
  * Only the FULL speed values are given. Current code is such that rate
  * changes must be made at DPLLoutx2. The actual value adjustment for low
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index cb9497a20fb3..5e2e2218a402 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -289,6 +289,8 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer,
 	if (!timer->io_base)
 		return -ENXIO;
 
+	omap_hwmod_setup_one(oh_name);
+
 	/* After the dmtimer is using hwmod these clocks won't be needed */
 	timer->fclk = clk_get(NULL, omap_hwmod_get_main_clk(oh));
 	if (IS_ERR(timer->fclk))
@@ -303,7 +305,6 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer,
 
 	clk_put(src);
 
-	omap_hwmod_setup_one(oh_name);
 	omap_hwmod_enable(oh);
 	__omap_dm_timer_init_regs(timer);
 
diff --git a/arch/arm/mach-orion5x/Kconfig b/arch/arm/mach-orion5x/Kconfig
index a2af15822fcb..89bb0fc796bd 100644
--- a/arch/arm/mach-orion5x/Kconfig
+++ b/arch/arm/mach-orion5x/Kconfig
@@ -1,9 +1,9 @@
 menuconfig ARCH_ORION5X
 	bool "Marvell Orion"
 	depends on MMU && ARCH_MULTI_V5
-	select ARCH_REQUIRE_GPIOLIB
 	select CPU_FEROCEON
 	select GENERIC_CLOCKEVENTS
+	select GPIOLIB
 	select MVEBU_MBUS
 	select PCI
 	select PLAT_ORION_LEGACY
diff --git a/arch/arm/mach-orion5x/board-dt.c b/arch/arm/mach-orion5x/board-dt.c
index 6f4c2c4ae2a5..3d36f1d95196 100644
--- a/arch/arm/mach-orion5x/board-dt.c
+++ b/arch/arm/mach-orion5x/board-dt.c
@@ -63,8 +63,7 @@ static void __init orion5x_dt_init(void)
 	if (of_machine_is_compatible("maxtor,shared-storage-2"))
 		mss2_init();
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     orion5x_auxdata_lookup, NULL);
+	of_platform_default_populate(NULL, orion5x_auxdata_lookup, NULL);
 }
 
 static const char *orion5x_dt_compat[] = {
diff --git a/arch/arm/mach-orion5x/irq.c b/arch/arm/mach-orion5x/irq.c
index de980ef9cda1..ac4af2283bef 100644
--- a/arch/arm/mach-orion5x/irq.c
+++ b/arch/arm/mach-orion5x/irq.c
@@ -26,7 +26,7 @@ static int __initdata gpio0_irqs[4] = {
 	IRQ_ORION5X_GPIO_24_31,
 };
 
-asmlinkage void
+static asmlinkage void
 __exception_irq_entry orion5x_legacy_handle_irq(struct pt_regs *regs)
 {
 	u32 stat;
diff --git a/arch/arm/mach-oxnas/Kconfig b/arch/arm/mach-oxnas/Kconfig
index 4fff3c7666df..567496bd250a 100644
--- a/arch/arm/mach-oxnas/Kconfig
+++ b/arch/arm/mach-oxnas/Kconfig
@@ -1,7 +1,7 @@
 menuconfig ARCH_OXNAS
 	bool "Oxford Semiconductor OXNAS Family SoCs"
-	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_HAS_RESET_CONTROLLER
+	select GPIOLIB
 	select PINCTRL
 	depends on ARCH_MULTI_V5
 	help
@@ -11,10 +11,10 @@ if ARCH_OXNAS
 
 config MACH_OX810SE
 	bool "Support OX810SE Based Products"
-	select ARM_TIMER_SP804
 	select COMMON_CLK_OXNAS
 	select CPU_ARM926T
 	select MFD_SYSCON
+	select OXNAS_RPS_TIMER
 	select PINCTRL_OXNAS
 	select RESET_OXNAS
 	select VERSATILE_FPGA_IRQ
diff --git a/arch/arm/mach-picoxcell/Kconfig b/arch/arm/mach-picoxcell/Kconfig
index aef92ba0eacd..1c8f701526c9 100644
--- a/arch/arm/mach-picoxcell/Kconfig
+++ b/arch/arm/mach-picoxcell/Kconfig
@@ -1,8 +1,8 @@
 config ARCH_PICOXCELL
 	bool "Picochip PicoXcell"
 	depends on ARCH_MULTI_V6
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_VIC
 	select DW_APB_TIMER_OF
+	select GPIOLIB
 	select HAVE_TCM
 	select NO_IOPORT_MAP
diff --git a/arch/arm/mach-picoxcell/common.c b/arch/arm/mach-picoxcell/common.c
index ec79fea82704..4e3d6d5c82cd 100644
--- a/arch/arm/mach-picoxcell/common.c
+++ b/arch/arm/mach-picoxcell/common.c
@@ -10,7 +10,6 @@
 #include <linux/delay.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 #include <linux/reboot.h>
 
 #include <asm/mach/arch.h>
@@ -54,7 +53,6 @@ static void __init picoxcell_map_io(void)
 
 static void __init picoxcell_init_machine(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	picoxcell_setup_restart();
 }
 
diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig
index 9e938f2961cf..85e874a97337 100644
--- a/arch/arm/mach-prima2/Kconfig
+++ b/arch/arm/mach-prima2/Kconfig
@@ -3,8 +3,8 @@ menuconfig ARCH_SIRF
 	depends on ARCH_MULTI_V7
 	select ARCH_HAS_RESET_CONTROLLER
 	select RESET_CONTROLLER
-	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_IRQ_CHIP
+	select GPIOLIB
 	select NO_IOPORT_MAP
 	select REGMAP
 	select PINCTRL
diff --git a/arch/arm/mach-qcom/Kconfig b/arch/arm/mach-qcom/Kconfig
index 73494500b51c..46ed10a807f0 100644
--- a/arch/arm/mach-qcom/Kconfig
+++ b/arch/arm/mach-qcom/Kconfig
@@ -23,4 +23,8 @@ config ARCH_MSM8974
 	bool "Enable support for MSM8974"
 	select HAVE_ARM_ARCH_TIMER
 
+config ARCH_MDM9615
+	bool "Enable support for MDM9615"
+	select CLKSRC_QCOM
+
 endif
diff --git a/arch/arm/mach-qcom/board.c b/arch/arm/mach-qcom/board.c
index 6d8bbf7d39d8..d8060dfd1a21 100644
--- a/arch/arm/mach-qcom/board.c
+++ b/arch/arm/mach-qcom/board.c
@@ -22,6 +22,7 @@ static const char * const qcom_dt_match[] __initconst = {
 	"qcom,ipq8064",
 	"qcom,msm8660-surf",
 	"qcom,msm8960-cdp",
+	"qcom,mdm9615",
 	NULL
 };
 
diff --git a/arch/arm/mach-rockchip/Kconfig b/arch/arm/mach-rockchip/Kconfig
index cef42fd886d1..9ad84cd01ba0 100644
--- a/arch/arm/mach-rockchip/Kconfig
+++ b/arch/arm/mach-rockchip/Kconfig
@@ -4,10 +4,10 @@ config ARCH_ROCKCHIP
 	select PINCTRL
 	select PINCTRL_ROCKCHIP
 	select ARCH_HAS_RESET_CONTROLLER
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_GIC
 	select CACHE_L2X0
+	select GPIOLIB
 	select HAVE_ARM_ARCH_TIMER
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
diff --git a/arch/arm/mach-rockchip/rockchip.c b/arch/arm/mach-rockchip/rockchip.c
index beb71da5d9c8..a7ab9ec141f8 100644
--- a/arch/arm/mach-rockchip/rockchip.c
+++ b/arch/arm/mach-rockchip/rockchip.c
@@ -73,7 +73,6 @@ static void __init rockchip_timer_init(void)
 static void __init rockchip_dt_init(void)
 {
 	rockchip_suspend_init();
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static const char * const rockchip_board_dt_compat[] = {
diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig
index b91aee406c74..4b1690acb6a5 100644
--- a/arch/arm/mach-s3c24xx/Kconfig
+++ b/arch/arm/mach-s3c24xx/Kconfig
@@ -11,7 +11,7 @@ if ARCH_S3C24XX
 
 config PLAT_S3C24XX
 	def_bool y
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select NO_IOPORT_MAP
 	select S3C_DEV_NAND
 	select IRQ_DOMAIN
diff --git a/arch/arm/mach-s3c24xx/include/mach/regs-gpio.h b/arch/arm/mach-s3c24xx/include/mach/regs-gpio.h
index c6583cfa5835..0d622f3b57a5 100644
--- a/arch/arm/mach-s3c24xx/include/mach/regs-gpio.h
+++ b/arch/arm/mach-s3c24xx/include/mach/regs-gpio.h
@@ -520,7 +520,7 @@
 #define S3C24XX_EXTINT1	   S3C24XX_GPIOREG2(0x8C)
 #define S3C24XX_EXTINT2	   S3C24XX_GPIOREG2(0x90)
 
-/* interrupt filtering conrrol for EINT16..EINT23 */
+/* interrupt filtering control for EINT16..EINT23 */
 #define S3C2410_EINFLT0	   S3C2410_GPIOREG(0x94)
 #define S3C2410_EINFLT1	   S3C2410_GPIOREG(0x98)
 #define S3C2410_EINFLT2	   S3C2410_GPIOREG(0x9C)
diff --git a/arch/arm/mach-s3c24xx/iotiming-s3c2410.c b/arch/arm/mach-s3c24xx/iotiming-s3c2410.c
index 4cd13ab6496b..65e5f9cb650f 100644
--- a/arch/arm/mach-s3c24xx/iotiming-s3c2410.c
+++ b/arch/arm/mach-s3c24xx/iotiming-s3c2410.c
@@ -423,7 +423,7 @@ void s3c2410_iotiming_set(struct s3c_cpufreq_config *cfg,
  * @timings: The IO timing information to fill out.
  *
  * Calculate the @timings timing information from the current frequency
- * information in @cfg, and the new frequency configur
+ * information in @cfg, and the new frequency configuration
  * through all the IO banks, reading the state and then updating @iot
  * as necessary.
  *
diff --git a/arch/arm/mach-s3c24xx/mach-n30.c b/arch/arm/mach-s3c24xx/mach-n30.c
index 171c1f11fd22..070a0d0714a5 100644
--- a/arch/arm/mach-s3c24xx/mach-n30.c
+++ b/arch/arm/mach-s3c24xx/mach-n30.c
@@ -522,7 +522,7 @@ static void __init n30_hwinit(void)
 	 *
 	 * The pull ups for H6/H7 are enabled on N30 but not on the
 	 * N35/PiN.  I suppose is useful for a budget model of the N30
-	 * with no bluetooh.  It doesn't hurt to have the pull ups
+	 * with no bluetooth.  It doesn't hurt to have the pull ups
 	 * enabled on the N35, so leave them enabled for all models.
 	 */
 	__raw_writel(0x0028aaaa, S3C2410_GPHCON);
diff --git a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
index ce2db235dbaf..262ab0744748 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
@@ -143,7 +143,7 @@ static int osiris_dvs_remove(struct platform_device *pdev)
 	return 0;
 }
 
-/* the CONFIG_PM block is so small, it isn't worth actaully compiling it
+/* the CONFIG_PM block is so small, it isn't worth actually compiling it
  * out if the configuration isn't set. */
 
 static int osiris_dvs_suspend(struct device *dev)
diff --git a/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c b/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c
index 5f028ff84cfe..c83c076578dd 100644
--- a/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c
+++ b/arch/arm/mach-s3c24xx/mach-s3c2416-dt.c
@@ -17,7 +17,6 @@
 
 #include <linux/clocksource.h>
 #include <linux/irqchip.h>
-#include <linux/of_platform.h>
 #include <linux/serial_s3c.h>
 
 #include <asm/mach/arch.h>
@@ -35,7 +34,6 @@ static void __init s3c2416_dt_map_io(void)
 
 static void __init s3c2416_dt_machine_init(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	s3c_pm_init();
 }
 
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2410.c b/arch/arm/mach-s3c24xx/pll-s3c2410.c
index 5e37d368594b..7ee4924a543d 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2410.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2410.c
@@ -32,11 +32,12 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
+/* This array should be sorted in ascending order of the frequencies */
 static struct cpufreq_frequency_table pll_vals_12MHz[] = {
     { .frequency = 34000000,  .driver_data = PLLVAL(82, 2, 3),   },
     { .frequency = 45000000,  .driver_data = PLLVAL(82, 1, 3),   },
-    { .frequency = 51000000,  .driver_data = PLLVAL(161, 3, 3),  },
     { .frequency = 48000000,  .driver_data = PLLVAL(120, 2, 3),  },
+    { .frequency = 51000000,  .driver_data = PLLVAL(161, 3, 3),  },
     { .frequency = 56000000,  .driver_data = PLLVAL(142, 2, 3),  },
     { .frequency = 68000000,  .driver_data = PLLVAL(82, 2, 2),   },
     { .frequency = 79000000,  .driver_data = PLLVAL(71, 1, 2),   },
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
index b355fca6cc2e..a3fbfed75e28 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
@@ -20,6 +20,7 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
+/* This array should be sorted in ascending order of the frequencies */
 static struct cpufreq_frequency_table s3c2440_plls_12[] = {
 	{ .frequency = 75000000,	.driver_data = PLLVAL(0x75, 3, 3),  }, 	/* FVco 600.000000 */
 	{ .frequency = 80000000,	.driver_data = PLLVAL(0x98, 4, 3),  }, 	/* FVco 640.000000 */
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
index be9a248b5ce9..bcff89fd9871 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
@@ -20,6 +20,7 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
+/* This array should be sorted in ascending order of the frequencies */
 static struct cpufreq_frequency_table s3c2440_plls_169344[] = {
 	{ .frequency = 78019200,	.driver_data = PLLVAL(121, 5, 3), 	}, 	/* FVco 624.153600 */
 	{ .frequency = 84067200,	.driver_data = PLLVAL(131, 5, 3), 	}, 	/* FVco 672.537600 */
diff --git a/arch/arm/mach-s3c64xx/Kconfig b/arch/arm/mach-s3c64xx/Kconfig
index e5c1888fc67b..459214fa20b4 100644
--- a/arch/arm/mach-s3c64xx/Kconfig
+++ b/arch/arm/mach-s3c64xx/Kconfig
@@ -5,12 +5,12 @@
 menuconfig ARCH_S3C64XX
 	bool "Samsung S3C64XX"
 	depends on ARCH_MULTI_V6
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_VIC
 	select CLKSRC_SAMSUNG_PWM
 	select COMMON_CLK_SAMSUNG
 	select GPIO_SAMSUNG if ATAGS
+	select GPIOLIB
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_TCM
diff --git a/arch/arm/mach-s3c64xx/common.h b/arch/arm/mach-s3c64xx/common.h
index 9eb864412911..4f204668f00e 100644
--- a/arch/arm/mach-s3c64xx/common.h
+++ b/arch/arm/mach-s3c64xx/common.h
@@ -24,6 +24,7 @@ void s3c64xx_init_io(struct map_desc *mach_desc, int size);
 
 void s3c64xx_restart(enum reboot_mode mode, const char *cmd);
 
+struct device_node;
 void s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f,
 	unsigned long xusbxti_f, bool is_s3c6400, void __iomem *reg_base);
 void s3c64xx_set_xtal_freq(unsigned long freq);
diff --git a/arch/arm/mach-s3c64xx/include/mach/map.h b/arch/arm/mach-s3c64xx/include/mach/map.h
index f55ccb1ce893..d51873e8f63f 100644
--- a/arch/arm/mach-s3c64xx/include/mach/map.h
+++ b/arch/arm/mach-s3c64xx/include/mach/map.h
@@ -99,7 +99,7 @@
 
 #define S3C64XX_PA_USB_HSPHY	(0x7C100000)
 
-/* compatibiltiy defines. */
+/* compatibility defines. */
 #define S3C_PA_TIMER		S3C64XX_PA_TIMER
 #define S3C_PA_HSMMC0		S3C64XX_PA_HSMMC0
 #define S3C_PA_HSMMC1		S3C64XX_PA_HSMMC1
diff --git a/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c b/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
index bbf74edd3dd9..5bf9afae752d 100644
--- a/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
+++ b/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
@@ -8,8 +8,6 @@
  * published by the Free Software Foundation.
 */
 
-#include <linux/of_platform.h>
-
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/system_misc.h>
@@ -48,7 +46,6 @@ static void __init s3c64xx_dt_map_io(void)
 static void __init s3c64xx_dt_init_machine(void)
 {
 	samsung_wdt_reset_of_init();
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static void s3c64xx_dt_restart(enum reboot_mode mode, const char *cmd)
diff --git a/arch/arm/mach-s3c64xx/mach-smartq.c b/arch/arm/mach-s3c64xx/mach-smartq.c
index 936a63fc68d5..e0e1a729ef98 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq.c
@@ -43,6 +43,7 @@
 #include <plat/samsung-time.h>
 
 #include "common.h"
+#include "mach-smartq.h"
 #include "regs-modem.h"
 
 #define UCON S3C2410_UCON_DEFAULT
diff --git a/arch/arm/mach-s5pv210/Kconfig b/arch/arm/mach-s5pv210/Kconfig
index 13bc9820ff22..4cec11cf5e6f 100644
--- a/arch/arm/mach-s5pv210/Kconfig
+++ b/arch/arm/mach-s5pv210/Kconfig
@@ -11,10 +11,10 @@ config ARCH_S5PV210
 	bool "Samsung S5PV210/S5PC110"
 	depends on ARCH_MULTI_V7
 	select ARCH_HAS_HOLES_MEMORYMODEL
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_VIC
 	select CLKSRC_SAMSUNG_PWM
 	select COMMON_CLK_SAMSUNG
+	select GPIOLIB
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_S3C_RTC if RTC_CLASS
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index fe4ccb52f921..4a48c9f5f725 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -41,7 +41,7 @@ menuconfig ARCH_RENESAS
 	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
 	select NO_IOPORT_MAP
 	select PINCTRL
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select ZONE_DMA if ARM_LPAE
 
 if ARCH_RENESAS
@@ -86,6 +86,10 @@ config ARCH_R8A7791
 	select ARCH_RCAR_GEN2
 	select I2C
 
+config ARCH_R8A7792
+	bool "R-Car V2H (R8A77920)"
+	select ARCH_RCAR_GEN2
+
 config ARCH_R8A7793
 	bool "R-Car M2-N (R8A7793)"
 	select ARCH_RCAR_GEN2
diff --git a/arch/arm/mach-shmobile/Makefile b/arch/arm/mach-shmobile/Makefile
index fc95f7bd2dd9..3fc48b02eb4f 100644
--- a/arch/arm/mach-shmobile/Makefile
+++ b/arch/arm/mach-shmobile/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_ARCH_R8A7778)	+= setup-r8a7778.o
 obj-$(CONFIG_ARCH_R8A7779)	+= setup-r8a7779.o pm-r8a7779.o
 obj-$(CONFIG_ARCH_R8A7790)	+= setup-r8a7790.o
 obj-$(CONFIG_ARCH_R8A7791)	+= setup-r8a7791.o
+obj-$(CONFIG_ARCH_R8A7792)	+= setup-r8a7792.o
 obj-$(CONFIG_ARCH_R8A7793)	+= setup-r8a7793.o
 obj-$(CONFIG_ARCH_R8A7794)	+= setup-r8a7794.o
 obj-$(CONFIG_ARCH_EMEV2)	+= setup-emev2.o
diff --git a/arch/arm/mach-shmobile/common.h b/arch/arm/mach-shmobile/common.h
index 3b562d87826d..1a8f7b3ab449 100644
--- a/arch/arm/mach-shmobile/common.h
+++ b/arch/arm/mach-shmobile/common.h
@@ -10,6 +10,7 @@ extern void shmobile_smp_sleep(void);
 extern void shmobile_smp_hook(unsigned int cpu, unsigned long fn,
 			      unsigned long arg);
 extern bool shmobile_smp_cpu_can_disable(unsigned int cpu);
+extern bool shmobile_smp_init_fallback_ops(void);
 extern void shmobile_boot_scu(void);
 extern void shmobile_smp_scu_prepare_cpus(phys_addr_t scu_base_phys,
 					  unsigned int max_cpus);
diff --git a/arch/arm/mach-shmobile/platsmp-apmu.c b/arch/arm/mach-shmobile/platsmp-apmu.c
index aba75c89f9c1..0c6bb458b7a4 100644
--- a/arch/arm/mach-shmobile/platsmp-apmu.c
+++ b/arch/arm/mach-shmobile/platsmp-apmu.c
@@ -24,6 +24,7 @@
 #include <asm/suspend.h>
 #include "common.h"
 #include "platsmp-apmu.h"
+#include "rcar-gen2.h"
 
 static struct {
 	void __iomem *iomem;
@@ -74,6 +75,7 @@ static int __maybe_unused apmu_wrap(int cpu, int (*fn)(void __iomem *p, int cpu)
 	return p ? fn(p, apmu_cpus[cpu].bit) : -EINVAL;
 }
 
+#ifdef CONFIG_SMP
 static void apmu_init_cpu(struct resource *res, int cpu, int bit)
 {
 	if ((cpu >= ARRAY_SIZE(apmu_cpus)) || apmu_cpus[cpu].iomem)
@@ -117,18 +119,69 @@ static void apmu_parse_cfg(void (*fn)(struct resource *res, int cpu, int bit),
 	}
 }
 
-void __init shmobile_smp_apmu_prepare_cpus(unsigned int max_cpus,
-					   struct rcar_apmu_config *apmu_config,
-					   int num)
+static const struct of_device_id apmu_ids[] = {
+	{ .compatible = "renesas,apmu" },
+	{ /*sentinel*/ }
+};
+
+static void apmu_parse_dt(void (*fn)(struct resource *res, int cpu, int bit))
+{
+	struct device_node *np_apmu, *np_cpu;
+	struct resource res;
+	int bit, index;
+	u32 id;
+
+	for_each_matching_node(np_apmu, apmu_ids) {
+		/* only enable the cluster that includes the boot CPU */
+		bool is_allowed = false;
+
+		for (bit = 0; bit < CONFIG_NR_CPUS; bit++) {
+			np_cpu = of_parse_phandle(np_apmu, "cpus", bit);
+			if (np_cpu) {
+				if (!of_property_read_u32(np_cpu, "reg", &id)) {
+					if (id == cpu_logical_map(0)) {
+						is_allowed = true;
+						of_node_put(np_cpu);
+						break;
+					}
+
+				}
+				of_node_put(np_cpu);
+			}
+		}
+		if (!is_allowed)
+			continue;
+
+		for (bit = 0; bit < CONFIG_NR_CPUS; bit++) {
+			np_cpu = of_parse_phandle(np_apmu, "cpus", bit);
+			if (np_cpu) {
+				if (!of_property_read_u32(np_cpu, "reg", &id)) {
+					index = get_logical_index(id);
+					if ((index >= 0) &&
+					    !of_address_to_resource(np_apmu,
+								    0, &res))
+						fn(&res, index, bit);
+				}
+				of_node_put(np_cpu);
+			}
+		}
+	}
+}
+
+static void __init shmobile_smp_apmu_setup_boot(void)
 {
 	/* install boot code shared by all CPUs */
 	shmobile_boot_fn = virt_to_phys(shmobile_smp_boot);
+}
 
-	/* perform per-cpu setup */
+void __init shmobile_smp_apmu_prepare_cpus(unsigned int max_cpus,
+					   struct rcar_apmu_config *apmu_config,
+					   int num)
+{
+	shmobile_smp_apmu_setup_boot();
 	apmu_parse_cfg(apmu_init_cpu, apmu_config, num);
 }
 
-#ifdef CONFIG_SMP
 int shmobile_smp_apmu_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	/* For this particular CPU register boot vector */
@@ -136,7 +189,38 @@ int shmobile_smp_apmu_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 	return apmu_wrap(cpu, apmu_power_on);
 }
+
+static void __init shmobile_smp_apmu_prepare_cpus_dt(unsigned int max_cpus)
+{
+	shmobile_smp_apmu_setup_boot();
+	apmu_parse_dt(apmu_init_cpu);
+	rcar_gen2_pm_init();
+}
+
+static int shmobile_smp_apmu_boot_secondary_md21(unsigned int cpu,
+						 struct task_struct *idle)
+{
+	/* Error out when hardware debug mode is enabled */
+	if (rcar_gen2_read_mode_pins() & BIT(21)) {
+		pr_warn("Unable to boot CPU%u when MD21 is set\n", cpu);
+		return -ENOTSUPP;
+	}
+
+	return shmobile_smp_apmu_boot_secondary(cpu, idle);
+}
+
+static struct smp_operations apmu_smp_ops __initdata = {
+	.smp_prepare_cpus	= shmobile_smp_apmu_prepare_cpus_dt,
+	.smp_boot_secondary	= shmobile_smp_apmu_boot_secondary_md21,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_can_disable	= shmobile_smp_cpu_can_disable,
+	.cpu_die		= shmobile_smp_apmu_cpu_die,
+	.cpu_kill		= shmobile_smp_apmu_cpu_kill,
 #endif
+};
+
+CPU_METHOD_OF_DECLARE(shmobile_smp_apmu, "renesas,apmu", &apmu_smp_ops);
+#endif /* CONFIG_SMP */
 
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_SUSPEND)
 /* nicked from arch/arm/mach-exynos/hotplug.c */
diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c
index b23378f3d7e1..f3dba6f356e2 100644
--- a/arch/arm/mach-shmobile/platsmp.c
+++ b/arch/arm/mach-shmobile/platsmp.c
@@ -36,3 +36,9 @@ bool shmobile_smp_cpu_can_disable(unsigned int cpu)
 	return true; /* Hotplug of any CPU is supported */
 }
 #endif
+
+bool __init shmobile_smp_init_fallback_ops(void)
+{
+	/* fallback on PSCI/smp_ops if no other DT based method is detected */
+	return platform_can_secondary_boot() ? true : false;
+}
diff --git a/arch/arm/mach-shmobile/pm-r8a7779.c b/arch/arm/mach-shmobile/pm-r8a7779.c
index 4174cbcbc467..5c9a93f5e650 100644
--- a/arch/arm/mach-shmobile/pm-r8a7779.c
+++ b/arch/arm/mach-shmobile/pm-r8a7779.c
@@ -23,11 +23,7 @@
 
 static void __init r8a7779_sysc_init(void)
 {
-	void __iomem *base = rcar_sysc_init(0xffd85000);
-
-	/* enable all interrupt sources, but do not use interrupt handler */
-	iowrite32(0x0131000e, base + SYSCIER);
-	iowrite32(0, base + SYSCIMR);
+	rcar_sysc_init(0xffd85000, 0x0131000e);
 }
 
 #else /* CONFIG_PM || CONFIG_SMP */
diff --git a/arch/arm/mach-shmobile/pm-rcar-gen2.c b/arch/arm/mach-shmobile/pm-rcar-gen2.c
index 691ac166a277..dd9ac366868f 100644
--- a/arch/arm/mach-shmobile/pm-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/pm-rcar-gen2.c
@@ -26,8 +26,7 @@
 #define CA7RESCNT	0x0044
 
 /* On-chip RAM */
-#define MERAM		0xe8080000
-#define RAM		0xe6300000
+#define ICRAM1		0xe63c0000	/* Inter Connect RAM1 (4 KiB) */
 
 /* SYSC */
 #define SYSCIER 0x0c
@@ -37,11 +36,7 @@
 
 static void __init rcar_gen2_sysc_init(u32 syscier)
 {
-	void __iomem *base = rcar_sysc_init(0xe6180000);
-
-	/* enable all interrupt sources, but do not use interrupt handler */
-	iowrite32(syscier, base + SYSCIER);
-	iowrite32(0, base + SYSCIMR);
+	rcar_sysc_init(0xe6180000, syscier);
 }
 
 #else /* CONFIG_SMP */
@@ -58,7 +53,7 @@ void __init rcar_gen2_pm_init(void)
 	struct device_node *np, *cpus;
 	bool has_a7 = false;
 	bool has_a15 = false;
-	phys_addr_t boot_vector_addr = 0;
+	phys_addr_t boot_vector_addr = ICRAM1;
 	u32 syscier = 0;
 
 	if (once++)
@@ -75,14 +70,10 @@ void __init rcar_gen2_pm_init(void)
 			has_a7 = true;
 	}
 
-	if (of_machine_is_compatible("renesas,r8a7790")) {
-		boot_vector_addr = MERAM;
+	if (of_machine_is_compatible("renesas,r8a7790"))
 		syscier = 0x013111ef;
-
-	} else if (of_machine_is_compatible("renesas,r8a7791")) {
-		boot_vector_addr = RAM;
+	else if (of_machine_is_compatible("renesas,r8a7791"))
 		syscier = 0x00111003;
-	}
 
 	/* RAM for jump stub, because BAR requires 256KB aligned address */
 	p = ioremap_nocache(boot_vector_addr, shmobile_boot_size);
diff --git a/arch/arm/mach-shmobile/pm-rmobile.c b/arch/arm/mach-shmobile/pm-rmobile.c
index c0b05e9e6442..45a195501b78 100644
--- a/arch/arm/mach-shmobile/pm-rmobile.c
+++ b/arch/arm/mach-shmobile/pm-rmobile.c
@@ -131,13 +131,13 @@ static void rmobile_init_pm_domain(struct rmobile_pm_domain *rmobile_pd)
 	struct dev_power_governor *gov = rmobile_pd->gov;
 
 	genpd->flags = GENPD_FLAG_PM_CLK;
-	pm_genpd_init(genpd, gov ? : &simple_qos_governor, false);
 	genpd->dev_ops.active_wakeup	= rmobile_pd_active_wakeup;
 	genpd->power_off		= rmobile_pd_power_down;
 	genpd->power_on			= rmobile_pd_power_up;
 	genpd->attach_dev		= cpg_mstp_attach_dev;
 	genpd->detach_dev		= cpg_mstp_detach_dev;
 	__rmobile_pd_power_up(rmobile_pd, false);
+	pm_genpd_init(genpd, gov ? : &simple_qos_governor, false);
 }
 
 static int rmobile_pd_suspend_busy(void)
diff --git a/arch/arm/mach-shmobile/setup-r8a7740.c b/arch/arm/mach-shmobile/setup-r8a7740.c
index db6dbfbaf9f1..3849eef0d3a7 100644
--- a/arch/arm/mach-shmobile/setup-r8a7740.c
+++ b/arch/arm/mach-shmobile/setup-r8a7740.c
@@ -18,7 +18,6 @@
 #include <linux/io.h>
 #include <linux/irqchip.h>
 #include <linux/irqchip/arm-gic.h>
-#include <linux/of_platform.h>
 
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
@@ -77,8 +76,6 @@ static void __init r8a7740_init_irq_of(void)
 static void __init r8a7740_generic_init(void)
 {
 	r8a7740_meram_workaround();
-
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static const char *const r8a7740_boards_compat_dt[] __initconst = {
diff --git a/arch/arm/mach-shmobile/setup-r8a7790.c b/arch/arm/mach-shmobile/setup-r8a7790.c
index 3a18af4922b4..3506327e0bed 100644
--- a/arch/arm/mach-shmobile/setup-r8a7790.c
+++ b/arch/arm/mach-shmobile/setup-r8a7790.c
@@ -28,6 +28,7 @@ static const char * const r8a7790_boards_compat_dt[] __initconst = {
 };
 
 DT_MACHINE_START(R8A7790_DT, "Generic R8A7790 (Flattened Device Tree)")
+	.smp_init	= shmobile_smp_init_fallback_ops,
 	.smp		= smp_ops(r8a7790_smp_ops),
 	.init_early	= shmobile_init_delay,
 	.init_time	= rcar_gen2_timer_init,
diff --git a/arch/arm/mach-shmobile/setup-r8a7791.c b/arch/arm/mach-shmobile/setup-r8a7791.c
index 3b8dbaf07777..110e8b588e56 100644
--- a/arch/arm/mach-shmobile/setup-r8a7791.c
+++ b/arch/arm/mach-shmobile/setup-r8a7791.c
@@ -29,6 +29,7 @@ static const char *const r8a7791_boards_compat_dt[] __initconst = {
 };
 
 DT_MACHINE_START(R8A7791_DT, "Generic R8A7791 (Flattened Device Tree)")
+	.smp_init	= shmobile_smp_init_fallback_ops,
 	.smp		= smp_ops(r8a7791_smp_ops),
 	.init_early	= shmobile_init_delay,
 	.init_time	= rcar_gen2_timer_init,
diff --git a/arch/arm/mach-shmobile/setup-r8a7792.c b/arch/arm/mach-shmobile/setup-r8a7792.c
new file mode 100644
index 000000000000..a0910395da09
--- /dev/null
+++ b/arch/arm/mach-shmobile/setup-r8a7792.c
@@ -0,0 +1,35 @@
+/*
+ * r8a7792 processor support
+ *
+ * Copyright (C) 2014 Renesas Electronics Corporation
+ * Copyright (C) 2016 Cogent  Embedded, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of_platform.h>
+
+#include <asm/mach/arch.h>
+
+#include "common.h"
+#include "rcar-gen2.h"
+
+static const char * const r8a7792_boards_compat_dt[] __initconst = {
+	"renesas,r8a7792",
+	NULL,
+};
+
+DT_MACHINE_START(R8A7792_DT, "Generic R8A7792 (Flattened Device Tree)")
+	.init_early	= shmobile_init_delay,
+	.init_late	= shmobile_init_late,
+	.init_time	= rcar_gen2_timer_init,
+	.reserve	= rcar_gen2_reserve,
+	.dt_compat	= r8a7792_boards_compat_dt,
+MACHINE_END
diff --git a/arch/arm/mach-shmobile/setup-rcar-gen2.c b/arch/arm/mach-shmobile/setup-rcar-gen2.c
index 1c6fd11c2f82..afb9fdcd3d90 100644
--- a/arch/arm/mach-shmobile/setup-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/setup-rcar-gen2.c
@@ -46,6 +46,26 @@ u32 rcar_gen2_read_mode_pins(void)
 	return mode;
 }
 
+static unsigned int __init get_extal_freq(void)
+{
+	struct device_node *cpg, *extal;
+	u32 freq = 20000000;
+
+	cpg = of_find_compatible_node(NULL, NULL,
+				      "renesas,rcar-gen2-cpg-clocks");
+	if (!cpg)
+		return freq;
+
+	extal = of_parse_phandle(cpg, "clocks", 0);
+	of_node_put(cpg);
+	if (!extal)
+		return freq;
+
+	of_property_read_u32(extal, "clock-frequency", &freq);
+	of_node_put(extal);
+	return freq;
+}
+
 #define CNTCR 0
 #define CNTFID0 0x20
 
@@ -54,10 +74,10 @@ void __init rcar_gen2_timer_init(void)
 	u32 mode = rcar_gen2_read_mode_pins();
 #ifdef CONFIG_ARM_ARCH_TIMER
 	void __iomem *base;
-	int extal_mhz = 0;
 	u32 freq;
 
-	if (of_machine_is_compatible("renesas,r8a7794")) {
+	if (of_machine_is_compatible("renesas,r8a7792") ||
+	    of_machine_is_compatible("renesas,r8a7794")) {
 		freq = 260000000 / 8;	/* ZS / 8 */
 		/* CNTVOFF has to be initialized either from non-secure
 		 * Hypervisor mode or secure Monitor mode with SCR.NS==1.
@@ -82,26 +102,9 @@ void __init rcar_gen2_timer_init(void)
 		 * with the counter disabled. Moreover, it may also report
 		 * a potentially incorrect fixed 13 MHz frequency. To be
 		 * correct these registers need to be updated to use the
-		 * frequency EXTAL / 2 which can be determined by the MD pins.
+		 * frequency EXTAL / 2.
 		 */
-
-		switch (mode & (MD(14) | MD(13))) {
-		case 0:
-			extal_mhz = 15;
-			break;
-		case MD(13):
-			extal_mhz = 20;
-			break;
-		case MD(14):
-			extal_mhz = 26;
-			break;
-		case MD(13) | MD(14):
-			extal_mhz = 30;
-			break;
-		}
-
-		/* The arch timer frequency equals EXTAL / 2 */
-		freq = extal_mhz * (1000000 / 2);
+		freq = get_extal_freq() / 2;
 	}
 
 	/* Remap "armgcnt address map" space */
diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c
index 99a2004cac76..a25ff188e403 100644
--- a/arch/arm/mach-shmobile/setup-sh73a0.c
+++ b/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -18,7 +18,6 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/of_platform.h>
 #include <linux/delay.h>
 #include <linux/input.h>
 #include <linux/io.h>
@@ -55,7 +54,6 @@ static void __init sh73a0_generic_init(void)
 	/* Shared attribute override enable, 64K*8way */
 	l2x0_init(IOMEM(0xf0100000), 0x00400000, 0xc20f0fff);
 #endif
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static const char *const sh73a0_boards_compat_dt[] __initconst = {
diff --git a/arch/arm/mach-spear/Kconfig b/arch/arm/mach-spear/Kconfig
index ea9ea95630bd..b7260c2b510c 100644
--- a/arch/arm/mach-spear/Kconfig
+++ b/arch/arm/mach-spear/Kconfig
@@ -5,9 +5,9 @@
 menuconfig PLAT_SPEAR
 	bool "ST SPEAr Family"
 	depends on ARCH_MULTI_V7 || ARCH_MULTI_V5
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select CLKSRC_MMIO
+	select GPIOLIB
 
 if PLAT_SPEAR
 
diff --git a/arch/arm/mach-spear/spear1310.c b/arch/arm/mach-spear/spear1310.c
index cd5d375d91f0..a7d4f136836f 100644
--- a/arch/arm/mach-spear/spear1310.c
+++ b/arch/arm/mach-spear/spear1310.c
@@ -14,7 +14,6 @@
 #define pr_fmt(fmt) "SPEAr1310: " fmt
 
 #include <linux/amba/pl022.h>
-#include <linux/of_platform.h>
 #include <linux/pata_arasan_cf_data.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -27,7 +26,6 @@
 
 static void __init spear1310_dt_init(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	platform_device_register_simple("spear-cpufreq", -1, NULL, 0);
 }
 
diff --git a/arch/arm/mach-spear/spear1340.c b/arch/arm/mach-spear/spear1340.c
index 94594d5a446c..a212af90c0bc 100644
--- a/arch/arm/mach-spear/spear1340.c
+++ b/arch/arm/mach-spear/spear1340.c
@@ -19,7 +19,6 @@
 
 static void __init spear1340_dt_init(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	platform_device_register_simple("spear-cpufreq", -1, NULL, 0);
 }
 
diff --git a/arch/arm/mach-spear/spear300.c b/arch/arm/mach-spear/spear300.c
index 5b32edda2276..325b89579be1 100644
--- a/arch/arm/mach-spear/spear300.c
+++ b/arch/arm/mach-spear/spear300.c
@@ -194,8 +194,7 @@ static void __init spear300_dt_init(void)
 	pl080_plat_data.slave_channels = spear300_dma_info;
 	pl080_plat_data.num_slave_channels = ARRAY_SIZE(spear300_dma_info);
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			spear300_auxdata_lookup, NULL);
+	of_platform_default_populate(NULL, spear300_auxdata_lookup, NULL);
 }
 
 static const char * const spear300_dt_board_compat[] = {
diff --git a/arch/arm/mach-spear/spear310.c b/arch/arm/mach-spear/spear310.c
index 86a44ac7ff67..59e173dc85cf 100644
--- a/arch/arm/mach-spear/spear310.c
+++ b/arch/arm/mach-spear/spear310.c
@@ -236,8 +236,7 @@ static void __init spear310_dt_init(void)
 	pl080_plat_data.slave_channels = spear310_dma_info;
 	pl080_plat_data.num_slave_channels = ARRAY_SIZE(spear310_dma_info);
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			spear310_auxdata_lookup, NULL);
+	of_platform_default_populate(NULL, spear310_auxdata_lookup, NULL);
 }
 
 static const char * const spear310_dt_board_compat[] = {
diff --git a/arch/arm/mach-spear/spear320.c b/arch/arm/mach-spear/spear320.c
index d45d751926c5..0958f68a21e2 100644
--- a/arch/arm/mach-spear/spear320.c
+++ b/arch/arm/mach-spear/spear320.c
@@ -240,8 +240,7 @@ static void __init spear320_dt_init(void)
 	pl080_plat_data.slave_channels = spear320_dma_info;
 	pl080_plat_data.num_slave_channels = ARRAY_SIZE(spear320_dma_info);
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			spear320_auxdata_lookup, NULL);
+	of_platform_default_populate(NULL, spear320_auxdata_lookup, NULL);
 }
 
 static const char * const spear320_dt_board_compat[] = {
diff --git a/arch/arm/mach-spear/spear6xx.c b/arch/arm/mach-spear/spear6xx.c
index da26fa5b68d7..ccf3573b831c 100644
--- a/arch/arm/mach-spear/spear6xx.c
+++ b/arch/arm/mach-spear/spear6xx.c
@@ -411,8 +411,7 @@ struct of_dev_auxdata spear6xx_auxdata_lookup[] __initdata = {
 
 static void __init spear600_dt_init(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table,
-			spear6xx_auxdata_lookup, NULL);
+	of_platform_default_populate(NULL, spear6xx_auxdata_lookup, NULL);
 }
 
 static const char *spear600_dt_board_compat[] = {
diff --git a/arch/arm/mach-sti/Kconfig b/arch/arm/mach-sti/Kconfig
index 6f1af29f935d..119e1108b1f8 100644
--- a/arch/arm/mach-sti/Kconfig
+++ b/arch/arm/mach-sti/Kconfig
@@ -10,7 +10,7 @@ menuconfig ARCH_STI
 	select MFD_SYSCON
 	select ARCH_HAS_RESET_CONTROLLER
 	select HAVE_ARM_SCU if SMP
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_764369 if SMP
 	select ARM_ERRATA_775420
diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c
index ae10fb280a78..e04cd1b201bb 100644
--- a/arch/arm/mach-sti/board-dt.c
+++ b/arch/arm/mach-sti/board-dt.c
@@ -23,7 +23,15 @@ static const char *const stih41x_dt_match[] __initconst = {
 	NULL
 };
 
-DT_MACHINE_START(STM, "STiH415/416 SoC with Flattened Device Tree")
+static void sti_l2_write_sec(unsigned long val, unsigned reg)
+{
+	/*
+	 * We can't write to secure registers as we are in non-secure
+	 * mode, until we have some SMI service available.
+	 */
+}
+
+DT_MACHINE_START(STM, "STi SoC with Flattened Device Tree")
 	.dt_compat	= stih41x_dt_match,
 	.l2c_aux_val	= L2C_AUX_CTRL_SHARED_OVERRIDE |
 			  L310_AUX_CTRL_DATA_PREFETCH |
@@ -31,4 +39,5 @@ DT_MACHINE_START(STM, "STiH415/416 SoC with Flattened Device Tree")
 			  L2C_AUX_CTRL_WAY_SIZE(4),
 	.l2c_aux_mask	= 0xc0000fff,
 	.smp		= smp_ops(sti_smp_ops),
+	.l2c_write_sec	= sti_l2_write_sec,
 MACHINE_END
diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index c124d658b350..096ed216c6d5 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/arch/arm/mach-sunxi/Kconfig
@@ -1,10 +1,10 @@
 menuconfig ARCH_SUNXI
 	bool "Allwinner SoCs"
 	depends on ARCH_MULTI_V7
-	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_HAS_RESET_CONTROLLER
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
+	select GPIOLIB
 	select PINCTRL
 	select SUN4I_TIMER
 	select RESET_CONTROLLER
diff --git a/arch/arm/mach-tango/Makefile b/arch/arm/mach-tango/Makefile
index f33935e42e77..204fcd9fe180 100644
--- a/arch/arm/mach-tango/Makefile
+++ b/arch/arm/mach-tango/Makefile
@@ -3,3 +3,4 @@ AFLAGS_smc.o := -Wa,-march=armv7-a$(plus_sec)
 
 obj-y += setup.o smc.o
 obj-$(CONFIG_SMP) += platsmp.o
+obj-$(CONFIG_SUSPEND) += pm.o
diff --git a/arch/arm/mach-tango/platsmp.c b/arch/arm/mach-tango/platsmp.c
index a21f55e000d2..98c62a4a8623 100644
--- a/arch/arm/mach-tango/platsmp.c
+++ b/arch/arm/mach-tango/platsmp.c
@@ -1,3 +1,4 @@
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/smp.h>
 #include "smc.h"
@@ -9,8 +10,42 @@ static int tango_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	return 0;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * cpu_kill() and cpu_die() run concurrently on different cores.
+ * Firmware will only "kill" a core once it has properly "died".
+ * Try a few times to kill a core before giving up, and sleep
+ * between tries to give that core enough time to die.
+ */
+static int tango_cpu_kill(unsigned int cpu)
+{
+	int i, err;
+
+	for (i = 0; i < 10; ++i) {
+		msleep(10);
+		err = tango_aux_core_kill(cpu);
+		if (!err)
+			return true;
+	}
+
+	return false;
+}
+
+static void tango_cpu_die(unsigned int cpu)
+{
+	while (tango_aux_core_die(cpu) < 0)
+		cpu_relax();
+
+	panic("cpu %d failed to die\n", cpu);
+}
+#endif
+
 static const struct smp_operations tango_smp_ops __initconst = {
 	.smp_boot_secondary	= tango_boot_secondary,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_kill		= tango_cpu_kill,
+	.cpu_die		= tango_cpu_die,
+#endif
 };
 
 CPU_METHOD_OF_DECLARE(tango4_smp, "sigma,tango4-smp", &tango_smp_ops);
diff --git a/arch/arm/mach-tango/pm.c b/arch/arm/mach-tango/pm.c
new file mode 100644
index 000000000000..b05c6d6f99d0
--- /dev/null
+++ b/arch/arm/mach-tango/pm.c
@@ -0,0 +1,32 @@
+#include <linux/init.h>
+#include <linux/suspend.h>
+#include <asm/suspend.h>
+#include "smc.h"
+
+static int tango_pm_powerdown(unsigned long arg)
+{
+	tango_suspend(virt_to_phys(cpu_resume));
+
+	return -EIO; /* tango_suspend has failed */
+}
+
+static int tango_pm_enter(suspend_state_t state)
+{
+	if (state == PM_SUSPEND_MEM)
+		return cpu_suspend(0, tango_pm_powerdown);
+
+	return -EINVAL;
+}
+
+static const struct platform_suspend_ops tango_pm_ops = {
+	.enter = tango_pm_enter,
+	.valid = suspend_valid_only_mem,
+};
+
+static int __init tango_pm_init(void)
+{
+	suspend_set_ops(&tango_pm_ops);
+	return 0;
+}
+
+late_initcall(tango_pm_init);
diff --git a/arch/arm/mach-tango/smc.h b/arch/arm/mach-tango/smc.h
index 7a4af35cc390..57919539da1b 100644
--- a/arch/arm/mach-tango/smc.h
+++ b/arch/arm/mach-tango/smc.h
@@ -2,4 +2,7 @@ extern int tango_smc(unsigned int val, unsigned int service);
 
 #define tango_set_l2_control(val)	tango_smc(val, 0x102)
 #define tango_start_aux_core(val)	tango_smc(val, 0x104)
-#define tango_set_aux_boot_addr(val)	tango_smc((unsigned int)val, 0x105)
+#define tango_set_aux_boot_addr(val)	tango_smc(val, 0x105)
+#define tango_suspend(val)		tango_smc(val, 0x120)
+#define tango_aux_core_die(val)		tango_smc(val, 0x121)
+#define tango_aux_core_kill(val)	tango_smc(val, 0x122)
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index 0fa8b84ed657..329f01c5b6f8 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -1,11 +1,11 @@
 menuconfig ARCH_TEGRA
 	bool "NVIDIA Tegra"
 	depends on ARCH_MULTI_V7
-	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SUPPORTS_TRUSTED_FOUNDATIONS
 	select ARM_AMBA
 	select ARM_GIC
 	select CLKSRC_MMIO
+	select GPIOLIB
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
 	select PINCTRL
diff --git a/arch/arm/mach-tegra/common.h b/arch/arm/mach-tegra/common.h
index 1f6fb808e236..4cc00e993b00 100644
--- a/arch/arm/mach-tegra/common.h
+++ b/arch/arm/mach-tegra/common.h
@@ -1,4 +1,26 @@
+/*
+ * Copyright (c) 2011, ARM Ltd.
+ * Copyright (c) 2013, NVIDIA Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __MACH_TEGRA_COMMON_H
+#define __MACH_TEGRA_COMMON_H
+
 extern const struct smp_operations tegra_smp_ops;
 
 extern int tegra_cpu_kill(unsigned int cpu);
 extern void tegra_cpu_die(unsigned int cpu);
+
+#endif
diff --git a/arch/arm/mach-tegra/cpuidle-tegra114.c b/arch/arm/mach-tegra/cpuidle-tegra114.c
index 9157546fe68c..d3aa9be16621 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra114.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra114.c
@@ -26,6 +26,7 @@
 #include <asm/suspend.h>
 #include <asm/psci.h>
 
+#include "cpuidle.h"
 #include "pm.h"
 #include "sleep.h"
 
diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c
index 7469347b1749..afcee04f2616 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra20.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra20.c
@@ -30,6 +30,7 @@
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
 
+#include "cpuidle.h"
 #include "flowctrl.h"
 #include "iomap.h"
 #include "irq.h"
diff --git a/arch/arm/mach-tegra/cpuidle-tegra30.c b/arch/arm/mach-tegra/cpuidle-tegra30.c
index 4dbe1dae937c..c1417361e10e 100644
--- a/arch/arm/mach-tegra/cpuidle-tegra30.c
+++ b/arch/arm/mach-tegra/cpuidle-tegra30.c
@@ -30,6 +30,7 @@
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
 
+#include "cpuidle.h"
 #include "pm.h"
 #include "sleep.h"
 
diff --git a/arch/arm/mach-tegra/cpuidle.h b/arch/arm/mach-tegra/cpuidle.h
index c017dab60ffa..dd1624d4b294 100644
--- a/arch/arm/mach-tegra/cpuidle.h
+++ b/arch/arm/mach-tegra/cpuidle.h
@@ -23,8 +23,10 @@ void tegra20_cpuidle_pcie_irqs_in_use(void);
 int tegra30_cpuidle_init(void);
 int tegra114_cpuidle_init(void);
 void tegra_cpuidle_init(void);
+void tegra_cpuidle_pcie_irqs_in_use(void);
 #else
 static inline void tegra_cpuidle_init(void) {}
+static inline void tegra_cpuidle_pcie_irqs_in_use(void) {}
 #endif
 
 #endif
diff --git a/arch/arm/mach-tegra/hotplug.c b/arch/arm/mach-tegra/hotplug.c
index 1b129899a277..8ec707826072 100644
--- a/arch/arm/mach-tegra/hotplug.c
+++ b/arch/arm/mach-tegra/hotplug.c
@@ -17,6 +17,7 @@
 
 #include <asm/smp_plat.h>
 
+#include "common.h"
 #include "sleep.h"
 
 static void (*tegra_hotplug_shutdown)(void);
diff --git a/arch/arm/mach-tegra/irq.c b/arch/arm/mach-tegra/irq.c
index 3b9098d27ea5..a69b22d37eed 100644
--- a/arch/arm/mach-tegra/irq.c
+++ b/arch/arm/mach-tegra/irq.c
@@ -29,6 +29,7 @@
 
 #include "board.h"
 #include "iomap.h"
+#include "irq.h"
 
 #define SGI_MASK 0xFFFF
 
diff --git a/arch/arm/mach-tegra/pm.h b/arch/arm/mach-tegra/pm.h
index 83bc87583446..717b48f22912 100644
--- a/arch/arm/mach-tegra/pm.h
+++ b/arch/arm/mach-tegra/pm.h
@@ -36,7 +36,7 @@ void tegra30_sleep_core_init(void);
 
 void tegra_clear_cpu_in_lp2(void);
 bool tegra_set_cpu_in_lp2(void);
-
+int tegra_cpu_do_idle(void);
 void tegra_idle_lp2_last(void);
 extern void (*tegra_tear_down_cpu)(void);
 
diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c
index 2378fa560a21..e01cbca196b5 100644
--- a/arch/arm/mach-tegra/tegra.c
+++ b/arch/arm/mach-tegra/tegra.c
@@ -115,35 +115,17 @@ static void __init tegra_dt_init(void)
 	 * devices
 	 */
 out:
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, parent);
+	of_platform_default_populate(NULL, NULL, parent);
 }
 
-static void __init paz00_init(void)
-{
-	if (IS_ENABLED(CONFIG_ARCH_TEGRA_2x_SOC))
-		tegra_paz00_wifikill_init();
-}
-
-static struct {
-	char *machine;
-	void (*init)(void);
-} board_init_funcs[] = {
-	{ "compal,paz00", paz00_init },
-};
-
 static void __init tegra_dt_init_late(void)
 {
-	int i;
-
 	tegra_init_suspend();
 	tegra_cpuidle_init();
 
-	for (i = 0; i < ARRAY_SIZE(board_init_funcs); i++) {
-		if (of_machine_is_compatible(board_init_funcs[i].machine)) {
-			board_init_funcs[i].init();
-			break;
-		}
-	}
+	if (IS_ENABLED(CONFIG_ARCH_TEGRA_2x_SOC) &&
+	    of_machine_is_compatible("compal,paz00"))
+		tegra_paz00_wifikill_init();
 }
 
 static const char * const tegra_dt_board_compat[] = {
diff --git a/arch/arm/mach-u300/Kconfig b/arch/arm/mach-u300/Kconfig
index 4fdc3425ffbd..22dcbf5b76b2 100644
--- a/arch/arm/mach-u300/Kconfig
+++ b/arch/arm/mach-u300/Kconfig
@@ -1,11 +1,11 @@
 menuconfig ARCH_U300
 	bool "ST-Ericsson U300 Series"
 	depends on ARCH_MULTI_V5 && MMU
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_VIC
 	select U300_TIMER
 	select CPU_ARM926T
+	select GPIOLIB
 	select HAVE_TCM
 	select PINCTRL
 	select PINCTRL_COH901
diff --git a/arch/arm/mach-u300/core.c b/arch/arm/mach-u300/core.c
index 546338bbacf8..a4910ea6811a 100644
--- a/arch/arm/mach-u300/core.c
+++ b/arch/arm/mach-u300/core.c
@@ -391,8 +391,7 @@ static void __init u300_init_machine_dt(void)
 	pinctrl_register_mappings(u300_pinmux_map,
 				  ARRAY_SIZE(u300_pinmux_map));
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			u300_auxdata_lookup, NULL);
+	of_platform_default_populate(NULL, u300_auxdata_lookup, NULL);
 
 	/* Enable SEMI self refresh */
 	val = readw(syscon_base + U300_SYSCON_SMCR) |
diff --git a/arch/arm/mach-uniphier/Makefile b/arch/arm/mach-uniphier/Makefile
index 1233f9b610bc..396afe109e67 100644
--- a/arch/arm/mach-uniphier/Makefile
+++ b/arch/arm/mach-uniphier/Makefile
@@ -1,2 +1 @@
-obj-y			:= uniphier.o
 obj-$(CONFIG_SMP)	+= platsmp.o headsmp.o
diff --git a/arch/arm/mach-uniphier/platsmp.c b/arch/arm/mach-uniphier/platsmp.c
index e802ca836ec7..9978c41128f6 100644
--- a/arch/arm/mach-uniphier/platsmp.c
+++ b/arch/arm/mach-uniphier/platsmp.c
@@ -101,21 +101,13 @@ static int __init uniphier_smp_prepare_trampoline(unsigned int max_cpus)
 	np = of_find_compatible_node(NULL, NULL, "socionext,uniphier-smpctrl");
 	ret = of_address_to_resource(np, 0, &res);
 	of_node_put(np);
-	if (!ret) {
-		rom_rsv2_phys = res.start + UNIPHIER_SMPCTRL_ROM_RSV2;
-	} else {
-		/* try old binding too */
-		np = of_find_compatible_node(NULL, NULL,
-					     "socionext,uniphier-system-bus-controller");
-		ret = of_address_to_resource(np, 1, &res);
-		of_node_put(np);
-		if (ret) {
-			pr_err("failed to get resource of SMP control\n");
-			return ret;
-		}
-		rom_rsv2_phys = res.start + 0x1000 + UNIPHIER_SMPCTRL_ROM_RSV2;
+	if (ret) {
+		pr_err("failed to get resource of SMP control\n");
+		return ret;
 	}
 
+	rom_rsv2_phys = res.start + UNIPHIER_SMPCTRL_ROM_RSV2;
+
 	ret = uniphier_smp_copy_trampoline(rom_rsv2_phys);
 	if (ret)
 		return ret;
diff --git a/arch/arm/mach-uniphier/uniphier.c b/arch/arm/mach-uniphier/uniphier.c
deleted file mode 100644
index 9be10efacb7d..000000000000
--- a/arch/arm/mach-uniphier/uniphier.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <asm/mach/arch.h>
-
-static const char * const uniphier_dt_compat[] __initconst = {
-	"socionext,ph1-sld3",
-	"socionext,ph1-ld4",
-	"socionext,ph1-pro4",
-	"socionext,ph1-sld8",
-	"socionext,ph1-pro5",
-	"socionext,proxstream2",
-	"socionext,ph1-ld6b",
-	NULL,
-};
-
-DT_MACHINE_START(UNIPHIER, "Socionext UniPhier")
-	.dt_compat	= uniphier_dt_compat,
-MACHINE_END
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index 3185081bdb2c..4740ac393297 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -3,13 +3,13 @@ menuconfig ARCH_U8500
 	depends on ARCH_MULTI_V7 && MMU
 	select AB8500_CORE
 	select ABX500_CORE
-	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_764369 if SMP
 	select ARM_GIC
 	select CACHE_L2X0
 	select CLKSRC_NOMADIK_MTU
+	select GPIOLIB
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
 	select PINCTRL
diff --git a/arch/arm/mach-ux500/Makefile b/arch/arm/mach-ux500/Makefile
index edfff1ae1f8d..56d0eb6e254e 100644
--- a/arch/arm/mach-ux500/Makefile
+++ b/arch/arm/mach-ux500/Makefile
@@ -2,11 +2,9 @@
 # Makefile for the linux kernel, U8500 machine.
 #
 
-obj-y				:= cpu.o id.o pm.o
-obj-$(CONFIG_CACHE_L2X0)	+= cache-l2x0.o
+obj-y				:= pm.o
 obj-$(CONFIG_UX500_SOC_DB8500)	+= cpu-db8500.o
-obj-$(CONFIG_MACH_MOP500)	+= board-mop500-regulators.o \
-				board-mop500-audio.o
+obj-$(CONFIG_MACH_MOP500)	+= board-mop500-audio.o
 obj-$(CONFIG_SMP)		+= platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)	+= hotplug.o
 obj-$(CONFIG_PM_GENERIC_DOMAINS) += pm_domains.o
diff --git a/arch/arm/mach-ux500/board-mop500-regulators.c b/arch/arm/mach-ux500/board-mop500-regulators.c
deleted file mode 100644
index 32d744e91ec2..000000000000
--- a/arch/arm/mach-ux500/board-mop500-regulators.c
+++ /dev/null
@@ -1,1065 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2010
- *
- * License Terms: GNU General Public License v2
- *
- * Authors: Sundar Iyer <sundar.iyer@stericsson.com>
- *          Bengt Jonsson <bengt.g.jonsson@stericsson.com>
- *          Daniel Willerud <daniel.willerud@stericsson.com>
- *
- * MOP500 board specific initialization for regulators
- */
-#include <linux/kernel.h>
-#include <linux/regulator/machine.h>
-#include <linux/regulator/ab8500.h>
-#include "board-mop500-regulators.h"
-#include "id.h"
-
-static struct regulator_consumer_supply gpio_en_3v3_consumers[] = {
-       REGULATOR_SUPPLY("vdd33a", "smsc911x.0"),
-};
-
-struct regulator_init_data gpio_en_3v3_regulator = {
-       .constraints = {
-               .name = "EN-3V3",
-               .min_uV = 3300000,
-               .max_uV = 3300000,
-               .valid_ops_mask = REGULATOR_CHANGE_STATUS,
-       },
-       .num_consumer_supplies = ARRAY_SIZE(gpio_en_3v3_consumers),
-       .consumer_supplies = gpio_en_3v3_consumers,
-};
-
-/*
- * TPS61052 regulator
- */
-static struct regulator_consumer_supply tps61052_vaudio_consumers[] = {
-	/*
-	 * Boost converter supply to raise voltage on audio speaker, this
-	 * is actually connected to three pins, VInVhfL (left amplifier)
-	 * VInVhfR (right amplifier) and VIntDClassInt - all three must
-	 * be connected to the same voltage.
-	 */
-	REGULATOR_SUPPLY("vintdclassint", "ab8500-codec.0"),
-};
-
-struct regulator_init_data tps61052_regulator = {
-	.constraints = {
-		.name = "vaudio-hf",
-		.min_uV = 4500000,
-		.max_uV = 4500000,
-		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies = ARRAY_SIZE(tps61052_vaudio_consumers),
-	.consumer_supplies = tps61052_vaudio_consumers,
-};
-
-static struct regulator_consumer_supply ab8500_vaux1_consumers[] = {
-	/* Main display, u8500 R3 uib */
-	REGULATOR_SUPPLY("vddi", "mcde_disp_sony_acx424akp.0"),
-	/* Main display, u8500 uib and ST uib */
-	REGULATOR_SUPPLY("vdd1", "samsung_s6d16d0.0"),
-	/* Secondary display, ST uib */
-	REGULATOR_SUPPLY("vdd1", "samsung_s6d16d0.1"),
-	/* SFH7741 proximity sensor */
-	REGULATOR_SUPPLY("vcc", "gpio-keys.0"),
-	/* BH1780GLS ambient light sensor */
-	REGULATOR_SUPPLY("vcc", "2-0029"),
-	/* lsm303dlh accelerometer */
-	REGULATOR_SUPPLY("vdd", "2-0018"),
-	/* lsm303dlhc accelerometer */
-	REGULATOR_SUPPLY("vdd", "2-0019"),
-	/* lsm303dlh magnetometer */
-	REGULATOR_SUPPLY("vdd", "2-001e"),
-	/* Rohm BU21013 Touchscreen devices */
-	REGULATOR_SUPPLY("avdd", "3-005c"),
-	REGULATOR_SUPPLY("avdd", "3-005d"),
-	/* Synaptics RMI4 Touchscreen device */
-	REGULATOR_SUPPLY("vdd", "3-004b"),
-	/* L3G4200D Gyroscope device */
-	REGULATOR_SUPPLY("vdd", "2-0068"),
-	/* Ambient light sensor device */
-	REGULATOR_SUPPLY("vdd", "3-0029"),
-	/* Pressure sensor device */
-	REGULATOR_SUPPLY("vdd", "2-005c"),
-	/* Cypress TrueTouch Touchscreen device */
-	REGULATOR_SUPPLY("vcpin", "spi8.0"),
-	/* Camera device */
-	REGULATOR_SUPPLY("vaux12v5", "mmio_camera"),
-};
-
-static struct regulator_consumer_supply ab8500_vaux2_consumers[] = {
-	/* On-board eMMC power */
-	REGULATOR_SUPPLY("vmmc", "sdi4"),
-	/* AB8500 audio codec */
-	REGULATOR_SUPPLY("vcc-N2158", "ab8500-codec.0"),
-	/* AB8500 accessory detect 1 */
-	REGULATOR_SUPPLY("vcc-N2158", "ab8500-acc-det.0"),
-	/* AB8500 Tv-out device */
-	REGULATOR_SUPPLY("vcc-N2158", "mcde_tv_ab8500.4"),
-	/* AV8100 HDMI device */
-	REGULATOR_SUPPLY("vcc-N2158", "av8100_hdmi.3"),
-};
-
-static struct regulator_consumer_supply ab8500_vaux3_consumers[] = {
-	REGULATOR_SUPPLY("v-SD-STM", "stm"),
-	/* External MMC slot power */
-	REGULATOR_SUPPLY("vmmc", "sdi0"),
-};
-
-static struct regulator_consumer_supply ab8505_vaux4_consumers[] = {
-};
-
-static struct regulator_consumer_supply ab8505_vaux5_consumers[] = {
-};
-
-static struct regulator_consumer_supply ab8505_vaux6_consumers[] = {
-};
-
-static struct regulator_consumer_supply ab8505_vaux8_consumers[] = {
-	/* AB8500 audio codec device */
-	REGULATOR_SUPPLY("v-aux8", NULL),
-};
-
-static struct regulator_consumer_supply ab8505_vadc_consumers[] = {
-	/* Internal general-purpose ADC */
-	REGULATOR_SUPPLY("vddadc", "ab8500-gpadc.0"),
-	/* ADC for charger */
-	REGULATOR_SUPPLY("vddadc", "ab8500-charger.0"),
-};
-
-static struct regulator_consumer_supply ab8500_vtvout_consumers[] = {
-	/* TV-out DENC supply */
-	REGULATOR_SUPPLY("vtvout", "ab8500-denc.0"),
-	/* Internal general-purpose ADC */
-	REGULATOR_SUPPLY("vddadc", "ab8500-gpadc.0"),
-	/* ADC for charger */
-	REGULATOR_SUPPLY("vddadc", "ab8500-charger.0"),
-	/* AB8500 Tv-out device */
-	REGULATOR_SUPPLY("vtvout", "mcde_tv_ab8500.4"),
-};
-
-static struct regulator_consumer_supply ab8500_vaud_consumers[] = {
-	/* AB8500 audio-codec main supply */
-	REGULATOR_SUPPLY("vaud", "ab8500-codec.0"),
-};
-
-static struct regulator_consumer_supply ab8500_vamic1_consumers[] = {
-	/* AB8500 audio-codec Mic1 supply */
-	REGULATOR_SUPPLY("vamic1", "ab8500-codec.0"),
-};
-
-static struct regulator_consumer_supply ab8500_vamic2_consumers[] = {
-	/* AB8500 audio-codec Mic2 supply */
-	REGULATOR_SUPPLY("vamic2", "ab8500-codec.0"),
-};
-
-static struct regulator_consumer_supply ab8500_vdmic_consumers[] = {
-	/* AB8500 audio-codec DMic supply */
-	REGULATOR_SUPPLY("vdmic", "ab8500-codec.0"),
-};
-
-static struct regulator_consumer_supply ab8500_vintcore_consumers[] = {
-	/* SoC core supply, no device */
-	REGULATOR_SUPPLY("v-intcore", NULL),
-	/* USB Transceiver */
-	REGULATOR_SUPPLY("vddulpivio18", "ab8500-usb.0"),
-	/* Handled by abx500 clk driver */
-	REGULATOR_SUPPLY("v-intcore", "abx500-clk.0"),
-};
-
-static struct regulator_consumer_supply ab8505_usb_consumers[] = {
-	/* HS USB OTG physical interface */
-	REGULATOR_SUPPLY("v-ape", NULL),
-};
-
-static struct regulator_consumer_supply ab8500_vana_consumers[] = {
-	/* DB8500 DSI */
-	REGULATOR_SUPPLY("vdddsi1v2", "mcde"),
-	REGULATOR_SUPPLY("vdddsi1v2", "b2r2_core"),
-	REGULATOR_SUPPLY("vdddsi1v2", "b2r2_1_core"),
-	REGULATOR_SUPPLY("vdddsi1v2", "dsilink.0"),
-	REGULATOR_SUPPLY("vdddsi1v2", "dsilink.1"),
-	REGULATOR_SUPPLY("vdddsi1v2", "dsilink.2"),
-	/* DB8500 CSI */
-	REGULATOR_SUPPLY("vddcsi1v2", "mmio_camera"),
-};
-
-/* ab8500 regulator register initialization */
-static struct ab8500_regulator_reg_init ab8500_reg_init[] = {
-	/*
-	 * VanaRequestCtrl          = HP/LP depending on VxRequest
-	 * VextSupply1RequestCtrl   = HP/LP depending on VxRequest
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL2,       0xf0, 0x00),
-	/*
-	 * VextSupply2RequestCtrl   = HP/LP depending on VxRequest
-	 * VextSupply3RequestCtrl   = HP/LP depending on VxRequest
-	 * Vaux1RequestCtrl         = HP/LP depending on VxRequest
-	 * Vaux2RequestCtrl         = HP/LP depending on VxRequest
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL3,       0xff, 0x00),
-	/*
-	 * Vaux3RequestCtrl         = HP/LP depending on VxRequest
-	 * SwHPReq                  = Control through SWValid disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL4,       0x07, 0x00),
-	/*
-	 * VanaSysClkReq1HPValid    = disabled
-	 * Vaux1SysClkReq1HPValid   = disabled
-	 * Vaux2SysClkReq1HPValid   = disabled
-	 * Vaux3SysClkReq1HPValid   = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID1, 0xe8, 0x00),
-	/*
-	 * VextSupply1SysClkReq1HPValid = disabled
-	 * VextSupply2SysClkReq1HPValid = disabled
-	 * VextSupply3SysClkReq1HPValid = SysClkReq1 controlled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID2, 0x70, 0x40),
-	/*
-	 * VanaHwHPReq1Valid        = disabled
-	 * Vaux1HwHPreq1Valid       = disabled
-	 * Vaux2HwHPReq1Valid       = disabled
-	 * Vaux3HwHPReqValid        = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID1,     0xe8, 0x00),
-	/*
-	 * VextSupply1HwHPReq1Valid = disabled
-	 * VextSupply2HwHPReq1Valid = disabled
-	 * VextSupply3HwHPReq1Valid = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID2,     0x07, 0x00),
-	/*
-	 * VanaHwHPReq2Valid        = disabled
-	 * Vaux1HwHPReq2Valid       = disabled
-	 * Vaux2HwHPReq2Valid       = disabled
-	 * Vaux3HwHPReq2Valid       = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID1,     0xe8, 0x00),
-	/*
-	 * VextSupply1HwHPReq2Valid = disabled
-	 * VextSupply2HwHPReq2Valid = disabled
-	 * VextSupply3HwHPReq2Valid = HWReq2 controlled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID2,     0x07, 0x04),
-	/*
-	 * VanaSwHPReqValid         = disabled
-	 * Vaux1SwHPReqValid        = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID1,      0xa0, 0x00),
-	/*
-	 * Vaux2SwHPReqValid        = disabled
-	 * Vaux3SwHPReqValid        = disabled
-	 * VextSupply1SwHPReqValid  = disabled
-	 * VextSupply2SwHPReqValid  = disabled
-	 * VextSupply3SwHPReqValid  = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID2,      0x1f, 0x00),
-	/*
-	 * SysClkReq2Valid1         = SysClkReq2 controlled
-	 * SysClkReq3Valid1         = disabled
-	 * SysClkReq4Valid1         = SysClkReq4 controlled
-	 * SysClkReq5Valid1         = disabled
-	 * SysClkReq6Valid1         = SysClkReq6 controlled
-	 * SysClkReq7Valid1         = disabled
-	 * SysClkReq8Valid1         = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID1,    0xfe, 0x2a),
-	/*
-	 * SysClkReq2Valid2         = disabled
-	 * SysClkReq3Valid2         = disabled
-	 * SysClkReq4Valid2         = disabled
-	 * SysClkReq5Valid2         = disabled
-	 * SysClkReq6Valid2         = SysClkReq6 controlled
-	 * SysClkReq7Valid2         = disabled
-	 * SysClkReq8Valid2         = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID2,    0xfe, 0x20),
-	/*
-	 * VTVoutEna                = disabled
-	 * Vintcore12Ena            = disabled
-	 * Vintcore12Sel            = 1.25 V
-	 * Vintcore12LP             = inactive (HP)
-	 * VTVoutLP                 = inactive (HP)
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUMISC1,              0xfe, 0x10),
-	/*
-	 * VaudioEna                = disabled
-	 * VdmicEna                 = disabled
-	 * Vamic1Ena                = disabled
-	 * Vamic2Ena                = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_VAUDIOSUPPLY,           0x1e, 0x00),
-	/*
-	 * Vamic1_dzout             = high-Z when Vamic1 is disabled
-	 * Vamic2_dzout             = high-Z when Vamic2 is disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUCTRL1VAMIC,         0x03, 0x00),
-	/*
-	 * VPll                     = Hw controlled (NOTE! PRCMU bits)
-	 * VanaRegu                 = force off
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_VPLLVANAREGU,           0x0f, 0x02),
-	/*
-	 * VrefDDREna               = disabled
-	 * VrefDDRSleepMode         = inactive (no pulldown)
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_VREFDDR,                0x03, 0x00),
-	/*
-	 * VextSupply1Regu          = force LP
-	 * VextSupply2Regu          = force OFF
-	 * VextSupply3Regu          = force HP (-> STBB2=LP and TPS=LP)
-	 * ExtSupply2Bypass         = ExtSupply12LPn ball is 0 when Ena is 0
-	 * ExtSupply3Bypass         = ExtSupply3LPn ball is 0 when Ena is 0
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_EXTSUPPLYREGU,          0xff, 0x13),
-	/*
-	 * Vaux1Regu                = force HP
-	 * Vaux2Regu                = force off
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_VAUX12REGU,             0x0f, 0x01),
-	/*
-	 * Vaux3Regu                = force off
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3REGU,          0x03, 0x00),
-	/*
-	 * Vaux1Sel                 = 2.8 V
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_VAUX1SEL,               0x0f, 0x0C),
-	/*
-	 * Vaux2Sel                 = 2.9 V
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_VAUX2SEL,               0x0f, 0x0d),
-	/*
-	 * Vaux3Sel                 = 2.91 V
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3SEL,           0x07, 0x07),
-	/*
-	 * VextSupply12LP           = disabled (no LP)
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUCTRL2SPARE,         0x01, 0x00),
-	/*
-	 * Vaux1Disch               = short discharge time
-	 * Vaux2Disch               = short discharge time
-	 * Vaux3Disch               = short discharge time
-	 * Vintcore12Disch          = short discharge time
-	 * VTVoutDisch              = short discharge time
-	 * VaudioDisch              = short discharge time
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH,          0xfc, 0x00),
-	/*
-	 * VanaDisch                = short discharge time
-	 * VdmicPullDownEna         = pulldown disabled when Vdmic is disabled
-	 * VdmicDisch               = short discharge time
-	 */
-	INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH2,         0x16, 0x00),
-};
-
-/* AB8500 regulators */
-static struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = {
-	/* supplies to the display/camera */
-	[AB8500_LDO_AUX1] = {
-		.supply_regulator = "ab8500-ext-supply3",
-		.constraints = {
-			.name = "V-DISPLAY",
-			.min_uV = 2800000,
-			.max_uV = 3300000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS,
-			.boot_on = 1, /* display is on at boot */
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaux1_consumers),
-		.consumer_supplies = ab8500_vaux1_consumers,
-	},
-	/* supplies to the on-board eMMC */
-	[AB8500_LDO_AUX2] = {
-		.supply_regulator = "ab8500-ext-supply3",
-		.constraints = {
-			.name = "V-eMMC1",
-			.min_uV = 1100000,
-			.max_uV = 3300000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaux2_consumers),
-		.consumer_supplies = ab8500_vaux2_consumers,
-	},
-	/* supply for VAUX3, supplies to SDcard slots */
-	[AB8500_LDO_AUX3] = {
-		.supply_regulator = "ab8500-ext-supply3",
-		.constraints = {
-			.name = "V-MMC-SD",
-			.min_uV = 1100000,
-			.max_uV = 3300000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaux3_consumers),
-		.consumer_supplies = ab8500_vaux3_consumers,
-	},
-	/* supply for tvout, gpadc, TVOUT LDO */
-	[AB8500_LDO_TVOUT] = {
-		.constraints = {
-			.name = "V-TVOUT",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vtvout_consumers),
-		.consumer_supplies = ab8500_vtvout_consumers,
-	},
-	/* supply for ab8500-vaudio, VAUDIO LDO */
-	[AB8500_LDO_AUDIO] = {
-		.constraints = {
-			.name = "V-AUD",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaud_consumers),
-		.consumer_supplies = ab8500_vaud_consumers,
-	},
-	/* supply for v-anamic1 VAMic1-LDO */
-	[AB8500_LDO_ANAMIC1] = {
-		.constraints = {
-			.name = "V-AMIC1",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vamic1_consumers),
-		.consumer_supplies = ab8500_vamic1_consumers,
-	},
-	/* supply for v-amic2, VAMIC2 LDO, reuse constants for AMIC1 */
-	[AB8500_LDO_ANAMIC2] = {
-		.constraints = {
-			.name = "V-AMIC2",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vamic2_consumers),
-		.consumer_supplies = ab8500_vamic2_consumers,
-	},
-	/* supply for v-dmic, VDMIC LDO */
-	[AB8500_LDO_DMIC] = {
-		.constraints = {
-			.name = "V-DMIC",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vdmic_consumers),
-		.consumer_supplies = ab8500_vdmic_consumers,
-	},
-	/* supply for v-intcore12, VINTCORE12 LDO */
-	[AB8500_LDO_INTCORE] = {
-		.constraints = {
-			.name = "V-INTCORE",
-			.min_uV = 1250000,
-			.max_uV = 1350000,
-			.input_uV = 1800000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE |
-					  REGULATOR_CHANGE_DRMS,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vintcore_consumers),
-		.consumer_supplies = ab8500_vintcore_consumers,
-	},
-	/* supply for U8500 CSI-DSI, VANA LDO */
-	[AB8500_LDO_ANA] = {
-		.constraints = {
-			.name = "V-CSI-DSI",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vana_consumers),
-		.consumer_supplies = ab8500_vana_consumers,
-	},
-};
-
-/* supply for VextSupply3 */
-static struct regulator_consumer_supply ab8500_ext_supply3_consumers[] = {
-	/* SIM supply for 3 V SIM cards */
-	REGULATOR_SUPPLY("vinvsim", "sim-detect.0"),
-};
-
-/* extended configuration for VextSupply2, only used for HREFP_V20 boards */
-static struct ab8500_ext_regulator_cfg ab8500_ext_supply2 = {
-	.hwreq = true,
-};
-
-/*
- * AB8500 external regulators
- */
-static struct regulator_init_data ab8500_ext_regulators[] = {
-	/* fixed Vbat supplies VSMPS1_EXT_1V8 */
-	[AB8500_EXT_SUPPLY1] = {
-		.constraints = {
-			.name = "ab8500-ext-supply1",
-			.min_uV = 1800000,
-			.max_uV = 1800000,
-			.initial_mode = REGULATOR_MODE_IDLE,
-			.boot_on = 1,
-			.always_on = 1,
-		},
-	},
-	/* fixed Vbat supplies VSMPS2_EXT_1V36 and VSMPS5_EXT_1V15 */
-	[AB8500_EXT_SUPPLY2] = {
-		.constraints = {
-			.name = "ab8500-ext-supply2",
-			.min_uV = 1360000,
-			.max_uV = 1360000,
-		},
-	},
-	/* fixed Vbat supplies VSMPS3_EXT_3V4 and VSMPS4_EXT_3V4 */
-	[AB8500_EXT_SUPPLY3] = {
-		.constraints = {
-			.name = "ab8500-ext-supply3",
-			.min_uV = 3400000,
-			.max_uV = 3400000,
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-			.boot_on = 1,
-		},
-		.num_consumer_supplies =
-			ARRAY_SIZE(ab8500_ext_supply3_consumers),
-		.consumer_supplies = ab8500_ext_supply3_consumers,
-	},
-};
-
-/* ab8505 regulator register initialization */
-static struct ab8500_regulator_reg_init ab8505_reg_init[] = {
-	/*
-	 * VarmRequestCtrl
-	 * VsmpsCRequestCtrl
-	 * VsmpsARequestCtrl
-	 * VsmpsBRequestCtrl
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL1,       0x00, 0x00),
-	/*
-	 * VsafeRequestCtrl
-	 * VpllRequestCtrl
-	 * VanaRequestCtrl          = HP/LP depending on VxRequest
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL2,       0x30, 0x00),
-	/*
-	 * Vaux1RequestCtrl         = HP/LP depending on VxRequest
-	 * Vaux2RequestCtrl         = HP/LP depending on VxRequest
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL3,       0xf0, 0x00),
-	/*
-	 * Vaux3RequestCtrl         = HP/LP depending on VxRequest
-	 * SwHPReq                  = Control through SWValid disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUREQUESTCTRL4,       0x07, 0x00),
-	/*
-	 * VsmpsASysClkReq1HPValid
-	 * VsmpsBSysClkReq1HPValid
-	 * VsafeSysClkReq1HPValid
-	 * VanaSysClkReq1HPValid    = disabled
-	 * VpllSysClkReq1HPValid
-	 * Vaux1SysClkReq1HPValid   = disabled
-	 * Vaux2SysClkReq1HPValid   = disabled
-	 * Vaux3SysClkReq1HPValid   = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQ1HPVALID1, 0xe8, 0x00),
-	/*
-	 * VsmpsCSysClkReq1HPValid
-	 * VarmSysClkReq1HPValid
-	 * VbbSysClkReq1HPValid
-	 * VsmpsMSysClkReq1HPValid
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQ1HPVALID2, 0x00, 0x00),
-	/*
-	 * VsmpsAHwHPReq1Valid
-	 * VsmpsBHwHPReq1Valid
-	 * VsafeHwHPReq1Valid
-	 * VanaHwHPReq1Valid        = disabled
-	 * VpllHwHPReq1Valid
-	 * Vaux1HwHPreq1Valid       = disabled
-	 * Vaux2HwHPReq1Valid       = disabled
-	 * Vaux3HwHPReqValid        = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ1VALID1,     0xe8, 0x00),
-	/*
-	 * VsmpsMHwHPReq1Valid
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ1VALID2,     0x00, 0x00),
-	/*
-	 * VsmpsAHwHPReq2Valid
-	 * VsmpsBHwHPReq2Valid
-	 * VsafeHwHPReq2Valid
-	 * VanaHwHPReq2Valid        = disabled
-	 * VpllHwHPReq2Valid
-	 * Vaux1HwHPReq2Valid       = disabled
-	 * Vaux2HwHPReq2Valid       = disabled
-	 * Vaux3HwHPReq2Valid       = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ2VALID1,     0xe8, 0x00),
-	/*
-	 * VsmpsMHwHPReq2Valid
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUHWHPREQ2VALID2,     0x00, 0x00),
-	/**
-	 * VsmpsCSwHPReqValid
-	 * VarmSwHPReqValid
-	 * VsmpsASwHPReqValid
-	 * VsmpsBSwHPReqValid
-	 * VsafeSwHPReqValid
-	 * VanaSwHPReqValid
-	 * VanaSwHPReqValid         = disabled
-	 * VpllSwHPReqValid
-	 * Vaux1SwHPReqValid        = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUSWHPREQVALID1,      0xa0, 0x00),
-	/*
-	 * Vaux2SwHPReqValid        = disabled
-	 * Vaux3SwHPReqValid        = disabled
-	 * VsmpsMSwHPReqValid
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUSWHPREQVALID2,      0x03, 0x00),
-	/*
-	 * SysClkReq2Valid1         = SysClkReq2 controlled
-	 * SysClkReq3Valid1         = disabled
-	 * SysClkReq4Valid1         = SysClkReq4 controlled
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQVALID1,    0x0e, 0x0a),
-	/*
-	 * SysClkReq2Valid2         = disabled
-	 * SysClkReq3Valid2         = disabled
-	 * SysClkReq4Valid2         = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUSYSCLKREQVALID2,    0x0e, 0x00),
-	/*
-	 * Vaux4SwHPReqValid
-	 * Vaux4HwHPReq2Valid
-	 * Vaux4HwHPReq1Valid
-	 * Vaux4SysClkReq1HPValid
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUVAUX4REQVALID,    0x00, 0x00),
-	/*
-	 * VadcEna                  = disabled
-	 * VintCore12Ena            = disabled
-	 * VintCore12Sel            = 1.25 V
-	 * VintCore12LP             = inactive (HP)
-	 * VadcLP                   = inactive (HP)
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUMISC1,              0xfe, 0x10),
-	/*
-	 * VaudioEna                = disabled
-	 * Vaux8Ena                 = disabled
-	 * Vamic1Ena                = disabled
-	 * Vamic2Ena                = disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VAUDIOSUPPLY,           0x1e, 0x00),
-	/*
-	 * Vamic1_dzout             = high-Z when Vamic1 is disabled
-	 * Vamic2_dzout             = high-Z when Vamic2 is disabled
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUCTRL1VAMIC,         0x03, 0x00),
-	/*
-	 * VsmpsARegu
-	 * VsmpsASelCtrl
-	 * VsmpsAAutoMode
-	 * VsmpsAPWMMode
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSMPSAREGU,    0x00, 0x00),
-	/*
-	 * VsmpsBRegu
-	 * VsmpsBSelCtrl
-	 * VsmpsBAutoMode
-	 * VsmpsBPWMMode
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSMPSBREGU,    0x00, 0x00),
-	/*
-	 * VsafeRegu
-	 * VsafeSelCtrl
-	 * VsafeAutoMode
-	 * VsafePWMMode
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSAFEREGU,    0x00, 0x00),
-	/*
-	 * VPll                     = Hw controlled (NOTE! PRCMU bits)
-	 * VanaRegu                 = force off
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VPLLVANAREGU,           0x0f, 0x02),
-	/*
-	 * VextSupply1Regu          = force OFF (OTP_ExtSupply12LPnPolarity 1)
-	 * VextSupply2Regu          = force OFF (OTP_ExtSupply12LPnPolarity 1)
-	 * VextSupply3Regu          = force OFF (OTP_ExtSupply3LPnPolarity 0)
-	 * ExtSupply2Bypass         = ExtSupply12LPn ball is 0 when Ena is 0
-	 * ExtSupply3Bypass         = ExtSupply3LPn ball is 0 when Ena is 0
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_EXTSUPPLYREGU,          0xff, 0x30),
-	/*
-	 * Vaux1Regu                = force HP
-	 * Vaux2Regu                = force off
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VAUX12REGU,             0x0f, 0x01),
-	/*
-	 * Vaux3Regu                = force off
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VRF1VAUX3REGU,          0x03, 0x00),
-	/*
-	 * VsmpsASel1
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSMPSASEL1,    0x00, 0x00),
-	/*
-	 * VsmpsASel2
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSMPSASEL2,    0x00, 0x00),
-	/*
-	 * VsmpsASel3
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSMPSASEL3,    0x00, 0x00),
-	/*
-	 * VsmpsBSel1
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSMPSBSEL1,    0x00, 0x00),
-	/*
-	 * VsmpsBSel2
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSMPSBSEL2,    0x00, 0x00),
-	/*
-	 * VsmpsBSel3
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSMPSBSEL3,    0x00, 0x00),
-	/*
-	 * VsafeSel1
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSAFESEL1,    0x00, 0x00),
-	/*
-	 * VsafeSel2
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSAFESEL2,    0x00, 0x00),
-	/*
-	 * VsafeSel3
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VSAFESEL3,    0x00, 0x00),
-	/*
-	 * Vaux1Sel                 = 2.8 V
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VAUX1SEL,               0x0f, 0x0C),
-	/*
-	 * Vaux2Sel                 = 2.9 V
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VAUX2SEL,               0x0f, 0x0d),
-	/*
-	 * Vaux3Sel                 = 2.91 V
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VRF1VAUX3SEL,           0x07, 0x07),
-	/*
-	 * Vaux4RequestCtrl
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VAUX4REQCTRL,    0x00, 0x00),
-	/*
-	 * Vaux4Regu
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VAUX4REGU,    0x00, 0x00),
-	/*
-	 * Vaux4Sel
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_VAUX4SEL,    0x00, 0x00),
-	/*
-	 * Vaux1Disch               = short discharge time
-	 * Vaux2Disch               = short discharge time
-	 * Vaux3Disch               = short discharge time
-	 * Vintcore12Disch          = short discharge time
-	 * VTVoutDisch              = short discharge time
-	 * VaudioDisch              = short discharge time
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUCTRLDISCH,          0xfc, 0x00),
-	/*
-	 * VanaDisch                = short discharge time
-	 * Vaux8PullDownEna         = pulldown disabled when Vaux8 is disabled
-	 * Vaux8Disch               = short discharge time
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUCTRLDISCH2,         0x16, 0x00),
-	/*
-	 * Vaux4Disch               = short discharge time
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_REGUCTRLDISCH3,         0x01, 0x00),
-	/*
-	 * Vaux5Sel
-	 * Vaux5LP
-	 * Vaux5Ena
-	 * Vaux5Disch
-	 * Vaux5DisSfst
-	 * Vaux5DisPulld
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_CTRLVAUX5,              0x00, 0x00),
-	/*
-	 * Vaux6Sel
-	 * Vaux6LP
-	 * Vaux6Ena
-	 * Vaux6DisPulld
-	 */
-	INIT_REGULATOR_REGISTER(AB8505_CTRLVAUX6,              0x00, 0x00),
-};
-
-static struct regulator_init_data ab8505_regulators[AB8505_NUM_REGULATORS] = {
-	/* supplies to the display/camera */
-	[AB8505_LDO_AUX1] = {
-		.constraints = {
-			.name = "V-DISPLAY",
-			.min_uV = 2800000,
-			.max_uV = 3300000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS,
-			.boot_on = 1, /* display is on at boot */
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaux1_consumers),
-		.consumer_supplies = ab8500_vaux1_consumers,
-	},
-	/* supplies to the on-board eMMC */
-	[AB8505_LDO_AUX2] = {
-		.constraints = {
-			.name = "V-eMMC1",
-			.min_uV = 1100000,
-			.max_uV = 3300000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaux2_consumers),
-		.consumer_supplies = ab8500_vaux2_consumers,
-	},
-	/* supply for VAUX3, supplies to SDcard slots */
-	[AB8505_LDO_AUX3] = {
-		.constraints = {
-			.name = "V-MMC-SD",
-			.min_uV = 1100000,
-			.max_uV = 3300000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaux3_consumers),
-		.consumer_supplies = ab8500_vaux3_consumers,
-	},
-	/* supply for VAUX4, supplies to NFC and standalone secure element */
-	[AB8505_LDO_AUX4] = {
-		.constraints = {
-			.name = "V-NFC-SE",
-			.min_uV = 1100000,
-			.max_uV = 3300000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8505_vaux4_consumers),
-		.consumer_supplies = ab8505_vaux4_consumers,
-	},
-	/* supply for VAUX5, supplies to TBD */
-	[AB8505_LDO_AUX5] = {
-		.constraints = {
-			.name = "V-AUX5",
-			.min_uV = 1050000,
-			.max_uV = 2790000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8505_vaux5_consumers),
-		.consumer_supplies = ab8505_vaux5_consumers,
-	},
-	/* supply for VAUX6, supplies to TBD */
-	[AB8505_LDO_AUX6] = {
-		.constraints = {
-			.name = "V-AUX6",
-			.min_uV = 1050000,
-			.max_uV = 2790000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8505_vaux6_consumers),
-		.consumer_supplies = ab8505_vaux6_consumers,
-	},
-	/* supply for gpadc, ADC LDO */
-	[AB8505_LDO_ADC] = {
-		.constraints = {
-			.name = "V-ADC",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8505_vadc_consumers),
-		.consumer_supplies = ab8505_vadc_consumers,
-	},
-	/* supply for ab8500-vaudio, VAUDIO LDO */
-	[AB8505_LDO_AUDIO] = {
-		.constraints = {
-			.name = "V-AUD",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaud_consumers),
-		.consumer_supplies = ab8500_vaud_consumers,
-	},
-	/* supply for v-anamic1 VAMic1-LDO */
-	[AB8505_LDO_ANAMIC1] = {
-		.constraints = {
-			.name = "V-AMIC1",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vamic1_consumers),
-		.consumer_supplies = ab8500_vamic1_consumers,
-	},
-	/* supply for v-amic2, VAMIC2 LDO, reuse constants for AMIC1 */
-	[AB8505_LDO_ANAMIC2] = {
-		.constraints = {
-			.name = "V-AMIC2",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vamic2_consumers),
-		.consumer_supplies = ab8500_vamic2_consumers,
-	},
-	/* supply for v-aux8, VAUX8 LDO */
-	[AB8505_LDO_AUX8] = {
-		.constraints = {
-			.name = "V-AUX8",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8505_vaux8_consumers),
-		.consumer_supplies = ab8505_vaux8_consumers,
-	},
-	/* supply for v-intcore12, VINTCORE12 LDO */
-	[AB8505_LDO_INTCORE] = {
-		.constraints = {
-			.name = "V-INTCORE",
-			.min_uV = 1250000,
-			.max_uV = 1350000,
-			.input_uV = 1800000,
-			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
-					  REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE |
-					  REGULATOR_CHANGE_DRMS,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vintcore_consumers),
-		.consumer_supplies = ab8500_vintcore_consumers,
-	},
-	/* supply for LDO USB */
-	[AB8505_LDO_USB] = {
-		.constraints = {
-			.name = "V-USB",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS |
-					  REGULATOR_CHANGE_MODE,
-			.valid_modes_mask = REGULATOR_MODE_NORMAL |
-					    REGULATOR_MODE_IDLE,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8505_usb_consumers),
-		.consumer_supplies = ab8505_usb_consumers,
-	},
-	/* supply for U8500 CSI-DSI, VANA LDO */
-	[AB8505_LDO_ANA] = {
-		.constraints = {
-			.name = "V-CSI-DSI",
-			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-		},
-		.num_consumer_supplies = ARRAY_SIZE(ab8500_vana_consumers),
-		.consumer_supplies = ab8500_vana_consumers,
-	},
-};
-
-struct ab8500_regulator_platform_data ab8500_regulator_plat_data = {
-	.reg_init               = ab8500_reg_init,
-	.num_reg_init           = ARRAY_SIZE(ab8500_reg_init),
-	.regulator              = ab8500_regulators,
-	.num_regulator          = ARRAY_SIZE(ab8500_regulators),
-	.ext_regulator          = ab8500_ext_regulators,
-	.num_ext_regulator      = ARRAY_SIZE(ab8500_ext_regulators),
-};
-
-struct ab8500_regulator_platform_data ab8505_regulator_plat_data = {
-	.reg_init               = ab8505_reg_init,
-	.num_reg_init           = ARRAY_SIZE(ab8505_reg_init),
-	.regulator              = ab8505_regulators,
-	.num_regulator          = ARRAY_SIZE(ab8505_regulators),
-};
-
-static void ab8500_modify_reg_init(int id, u8 mask, u8 value)
-{
-	int i;
-
-	if (cpu_is_u8520()) {
-		for (i = ARRAY_SIZE(ab8505_reg_init) - 1; i >= 0; i--) {
-			if (ab8505_reg_init[i].id == id) {
-				u8 initval = ab8505_reg_init[i].value;
-				initval = (initval & ~mask) | (value & mask);
-				ab8505_reg_init[i].value = initval;
-
-				BUG_ON(mask & ~ab8505_reg_init[i].mask);
-				return;
-			}
-		}
-	} else {
-		for (i = ARRAY_SIZE(ab8500_reg_init) - 1; i >= 0; i--) {
-			if (ab8500_reg_init[i].id == id) {
-				u8 initval = ab8500_reg_init[i].value;
-				initval = (initval & ~mask) | (value & mask);
-				ab8500_reg_init[i].value = initval;
-
-				BUG_ON(mask & ~ab8500_reg_init[i].mask);
-				return;
-			}
-		}
-	}
-
-	BUG_ON(1);
-}
-
-void mop500_regulator_init(void)
-{
-	struct regulator_init_data *regulator;
-
-	/*
-	 * Temporarily turn on Vaux2 on 8520 machine
-	 */
-	if (cpu_is_u8520()) {
-		/* Vaux2 initialized to be on */
-		ab8500_modify_reg_init(AB8505_VAUX12REGU, 0x0f, 0x05);
-	}
-
-	/*
-	 * Handle AB8500_EXT_SUPPLY2 on HREFP_V20_V50 boards (do it for
-	 * all HREFP_V20 boards)
-	 */
-	if (cpu_is_u8500v20()) {
-		/* VextSupply2RequestCtrl =  HP/OFF depending on VxRequest */
-		ab8500_modify_reg_init(AB8500_REGUREQUESTCTRL3, 0x01, 0x01);
-
-		/* VextSupply2SysClkReq1HPValid = SysClkReq1 controlled */
-		ab8500_modify_reg_init(AB8500_REGUSYSCLKREQ1HPVALID2,
-			0x20, 0x20);
-
-		/* VextSupply2 = force HP at initialization */
-		ab8500_modify_reg_init(AB8500_EXTSUPPLYREGU, 0x0c, 0x04);
-
-		/* enable VextSupply2 during platform active */
-		regulator = &ab8500_ext_regulators[AB8500_EXT_SUPPLY2];
-		regulator->constraints.always_on = 1;
-
-		/* disable VextSupply2 in suspend */
-		regulator = &ab8500_ext_regulators[AB8500_EXT_SUPPLY2];
-		regulator->constraints.state_mem.disabled = 1;
-		regulator->constraints.state_standby.disabled = 1;
-
-		/* enable VextSupply2 HW control (used in suspend) */
-		regulator->driver_data = (void *)&ab8500_ext_supply2;
-	}
-}
diff --git a/arch/arm/mach-ux500/board-mop500-regulators.h b/arch/arm/mach-ux500/board-mop500-regulators.h
deleted file mode 100644
index 9bece38fe933..000000000000
--- a/arch/arm/mach-ux500/board-mop500-regulators.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2010
- *
- * License Terms: GNU General Public License v2
- *
- * Author: Bengt Jonsson <bengt.g.jonsson@stericsson.com> for ST-Ericsson
- *
- * MOP500 board specific initialization for regulators
- */
-
-#ifndef __BOARD_MOP500_REGULATORS_H
-#define __BOARD_MOP500_REGULATORS_H
-
-#include <linux/regulator/machine.h>
-#include <linux/regulator/ab8500.h>
-
-extern struct ab8500_regulator_platform_data ab8500_regulator_plat_data;
-extern struct ab8500_regulator_platform_data ab8505_regulator_plat_data;
-extern struct regulator_init_data tps61052_regulator;
-extern struct regulator_init_data gpio_en_3v3_regulator;
-
-void mop500_regulator_init(void);
-
-#endif
diff --git a/arch/arm/mach-ux500/cache-l2x0.c b/arch/arm/mach-ux500/cache-l2x0.c
deleted file mode 100644
index 780bd13cd7e3..000000000000
--- a/arch/arm/mach-ux500/cache-l2x0.c
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2011
- *
- * License terms: GNU General Public License (GPL) version 2
- */
-
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-
-#include <asm/outercache.h>
-#include <asm/hardware/cache-l2x0.h>
-
-#include "db8500-regs.h"
-#include "id.h"
-
-static int __init ux500_l2x0_unlock(void)
-{
-	int i;
-	struct device_node *np;
-	void __iomem *l2x0_base;
-
-	np = of_find_compatible_node(NULL, NULL, "arm,pl310-cache");
-	l2x0_base = of_iomap(np, 0);
-	of_node_put(np);
-	if (!l2x0_base)
-		return -ENODEV;
-
-	/*
-	 * Unlock Data and Instruction Lock if locked. Ux500 U-Boot versions
-	 * apparently locks both caches before jumping to the kernel. The
-	 * l2x0 core will not touch the unlock registers if the l2x0 is
-	 * already enabled, so we do it right here instead. The PL310 has
-	 * 8 sets of registers, one per possible CPU.
-	 */
-	for (i = 0; i < 8; i++) {
-		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE +
-			       i * L2X0_LOCKDOWN_STRIDE);
-		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE +
-			       i * L2X0_LOCKDOWN_STRIDE);
-	}
-	iounmap(l2x0_base);
-	return 0;
-}
-
-static void ux500_l2c310_write_sec(unsigned long val, unsigned reg)
-{
-	/*
-	 * We can't write to secure registers as we are in non-secure
-	 * mode, until we have some SMI service available.
-	 */
-}
-
-static int __init ux500_l2x0_init(void)
-{
-	/* Multiplatform guard */
-	if (!((cpu_is_u8500_family() || cpu_is_ux540_family())))
-		return -ENODEV;
-
-	/* Unlock before init */
-	ux500_l2x0_unlock();
-	outer_cache.write_sec = ux500_l2c310_write_sec;
-	l2x0_of_init(0, ~0);
-
-	return 0;
-}
-early_initcall(ux500_l2x0_init);
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index a557955472ea..46b1da1bf5d2 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -12,41 +12,107 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/amba/bus.h>
+#include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/mfd/dbx500-prcmu.h>
+#include <linux/platform_data/arm-ux500-pm.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
-#include <linux/mfd/abx500/ab8500.h>
-#include <linux/mfd/dbx500-prcmu.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/regulator/machine.h>
-#include <linux/random.h>
 
+#include <asm/outercache.h>
+#include <asm/hardware/cache-l2x0.h>
 #include <asm/mach/map.h>
+#include <asm/mach/arch.h>
 
 #include "setup.h"
 
-#include "board-mop500-regulators.h"
 #include "board-mop500.h"
 #include "db8500-regs.h"
-#include "id.h"
 
-static struct ab8500_platform_data ab8500_platdata = {
-	.regulator	= &ab8500_regulator_plat_data,
-};
+static int __init ux500_l2x0_unlock(void)
+{
+	int i;
+	struct device_node *np;
+	void __iomem *l2x0_base;
 
-static struct prcmu_pdata db8500_prcmu_pdata = {
-	.ab_platdata	= &ab8500_platdata,
-	.version_offset	= DB8500_PRCMU_FW_VERSION_OFFSET,
-	.legacy_offset	= DB8500_PRCMU_LEGACY_OFFSET,
-};
+	np = of_find_compatible_node(NULL, NULL, "arm,pl310-cache");
+	l2x0_base = of_iomap(np, 0);
+	of_node_put(np);
+	if (!l2x0_base)
+		return -ENODEV;
+
+	/*
+	 * Unlock Data and Instruction Lock if locked. Ux500 U-Boot versions
+	 * apparently locks both caches before jumping to the kernel. The
+	 * l2x0 core will not touch the unlock registers if the l2x0 is
+	 * already enabled, so we do it right here instead. The PL310 has
+	 * 8 sets of registers, one per possible CPU.
+	 */
+	for (i = 0; i < 8; i++) {
+		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE +
+			       i * L2X0_LOCKDOWN_STRIDE);
+		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE +
+			       i * L2X0_LOCKDOWN_STRIDE);
+	}
+	iounmap(l2x0_base);
+	return 0;
+}
+
+static void ux500_l2c310_write_sec(unsigned long val, unsigned reg)
+{
+	/*
+	 * We can't write to secure registers as we are in non-secure
+	 * mode, until we have some SMI service available.
+	 */
+}
 
-static void __init u8500_map_io(void)
+/*
+ * FIXME: Should we set up the GPIO domain here?
+ *
+ * The problem is that we cannot put the interrupt resources into the platform
+ * device until the irqdomain has been added. Right now, we set the GIC interrupt
+ * domain from init_irq(), then load the gpio driver from
+ * core_initcall(nmk_gpio_init) and add the platform devices from
+ * arch_initcall(customize_machine).
+ *
+ * This feels fragile because it depends on the gpio device getting probed
+ * _before_ any device uses the gpio interrupts.
+*/
+static void __init ux500_init_irq(void)
+{
+	struct device_node *np;
+	struct resource r;
+
+	irqchip_init();
+	np = of_find_compatible_node(NULL, NULL, "stericsson,db8500-prcmu");
+	of_address_to_resource(np, 0, &r);
+	of_node_put(np);
+	if (!r.start) {
+		pr_err("could not find PRCMU base resource\n");
+		return;
+	}
+	prcmu_early_init(r.start, r.end-r.start);
+	ux500_pm_init(r.start, r.end-r.start);
+
+	/* Unlock before init */
+	ux500_l2x0_unlock();
+	outer_cache.write_sec = ux500_l2c310_write_sec;
+}
+
+static void ux500_restart(enum reboot_mode mode, const char *cmd)
 {
-	debug_ll_io_init();
-	ux500_setup_id();
+	local_irq_disable();
+	local_fiq_disable();
+
+	prcmu_system_reset(0);
 }
 
 /*
@@ -73,31 +139,6 @@ static struct arm_pmu_platdata db8500_pmu_platdata = {
 	.handle_irq		= db8500_pmu_handler,
 };
 
-static const char *db8500_read_soc_id(void)
-{
-	void __iomem *uid;
-	const char *retstr;
-
-	uid = ioremap(U8500_BB_UID_BASE, 0x20);
-	if (!uid)
-		return NULL;
-	/* Throw these device-specific numbers into the entropy pool */
-	add_device_randomness(uid, 0x14);
-	retstr = kasprintf(GFP_KERNEL, "%08x%08x%08x%08x%08x",
-			 readl((u32 *)uid+0),
-			 readl((u32 *)uid+1), readl((u32 *)uid+2),
-			 readl((u32 *)uid+3), readl((u32 *)uid+4));
-	iounmap(uid);
-	return retstr;
-}
-
-static struct device * __init db8500_soc_device_init(void)
-{
-	const char *soc_id = db8500_read_soc_id();
-
-	return ux500_soc_device_init(soc_id);
-}
-
 static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = {
 	/* Requires call-back bindings. */
 	OF_DEV_AUXDATA("arm,cortex-a9-pmu", 0, "arm-pmu", &db8500_pmu_platdata),
@@ -111,8 +152,7 @@ static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("stericsson,ux500-msp-i2s", 0x80125000,
 		       "ux500-msp-i2s.3", &msp3_platform_data),
 	/* Requires non-DT:able platform data. */
-	OF_DEV_AUXDATA("stericsson,db8500-prcmu", 0x80157000, "db8500-prcmu",
-			&db8500_prcmu_pdata),
+	OF_DEV_AUXDATA("stericsson,db8500-prcmu", 0x80157000, "db8500-prcmu", NULL),
 	OF_DEV_AUXDATA("stericsson,ux500-cryp", 0xa03cb000, "cryp1", NULL),
 	OF_DEV_AUXDATA("stericsson,ux500-hash", 0xa03c2000, "hash1", NULL),
 	OF_DEV_AUXDATA("stericsson,snd-soc-mop500", 0, "snd-soc-mop500.0",
@@ -121,8 +161,7 @@ static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = {
 };
 
 static struct of_dev_auxdata u8540_auxdata_lookup[] __initdata = {
-	OF_DEV_AUXDATA("stericsson,db8500-prcmu", 0x80157000, "db8500-prcmu",
-			&db8500_prcmu_pdata),
+	OF_DEV_AUXDATA("stericsson,db8500-prcmu", 0x80157000, "db8500-prcmu", NULL),
 	{},
 };
 
@@ -136,15 +175,13 @@ static const struct of_device_id u8500_local_bus_nodes[] = {
 
 static void __init u8500_init_machine(void)
 {
-	struct device *parent = db8500_soc_device_init();
-
 	/* automatically probe child nodes of dbx5x0 devices */
 	if (of_machine_is_compatible("st-ericsson,u8540"))
 		of_platform_populate(NULL, u8500_local_bus_nodes,
-				     u8540_auxdata_lookup, parent);
+				     u8540_auxdata_lookup, NULL);
 	else
 		of_platform_populate(NULL, u8500_local_bus_nodes,
-				     u8500_auxdata_lookup, parent);
+				     u8500_auxdata_lookup, NULL);
 }
 
 static const char * stericsson_dt_platform_compat[] = {
@@ -156,10 +193,10 @@ static const char * stericsson_dt_platform_compat[] = {
 };
 
 DT_MACHINE_START(U8500_DT, "ST-Ericsson Ux5x0 platform (Device Tree Support)")
-	.map_io		= u8500_map_io,
+	.l2c_aux_val    = 0,
+	.l2c_aux_mask	= ~0,
 	.init_irq	= ux500_init_irq,
 	.init_machine	= u8500_init_machine,
-	.init_late	= NULL,
 	.dt_compat      = stericsson_dt_platform_compat,
 	.restart        = ux500_restart,
 MACHINE_END
diff --git a/arch/arm/mach-ux500/cpu.c b/arch/arm/mach-ux500/cpu.c
deleted file mode 100644
index 82156cbc22ce..000000000000
--- a/arch/arm/mach-ux500/cpu.c
+++ /dev/null
@@ -1,148 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2010
- *
- * Author: Rabin Vincent <rabin.vincent@stericsson.com> for ST-Ericsson
- * Author: Lee Jones <lee.jones@linaro.org> for ST-Ericsson
- * License terms: GNU General Public License (GPL) version 2
- */
-
-#include <linux/platform_device.h>
-#include <linux/io.h>
-#include <linux/mfd/dbx500-prcmu.h>
-#include <linux/sys_soc.h>
-#include <linux/err.h>
-#include <linux/slab.h>
-#include <linux/stat.h>
-#include <linux/of.h>
-#include <linux/of_irq.h>
-#include <linux/of_address.h>
-#include <linux/irq.h>
-#include <linux/irqchip.h>
-#include <linux/irqchip/arm-gic.h>
-#include <linux/platform_data/clk-ux500.h>
-#include <linux/platform_data/arm-ux500-pm.h>
-
-#include <asm/mach/map.h>
-
-#include "setup.h"
-
-#include "board-mop500.h"
-#include "db8500-regs.h"
-#include "id.h"
-
-void ux500_restart(enum reboot_mode mode, const char *cmd)
-{
-	local_irq_disable();
-	local_fiq_disable();
-
-	prcmu_system_reset(0);
-}
-
-/*
- * FIXME: Should we set up the GPIO domain here?
- *
- * The problem is that we cannot put the interrupt resources into the platform
- * device until the irqdomain has been added. Right now, we set the GIC interrupt
- * domain from init_irq(), then load the gpio driver from
- * core_initcall(nmk_gpio_init) and add the platform devices from
- * arch_initcall(customize_machine).
- *
- * This feels fragile because it depends on the gpio device getting probed
- * _before_ any device uses the gpio interrupts.
-*/
-void __init ux500_init_irq(void)
-{
-	struct device_node *np;
-	struct resource r;
-
-	irqchip_init();
-	np = of_find_compatible_node(NULL, NULL, "stericsson,db8500-prcmu");
-	of_address_to_resource(np, 0, &r);
-	of_node_put(np);
-	if (!r.start) {
-		pr_err("could not find PRCMU base resource\n");
-		return;
-	}
-	prcmu_early_init(r.start, r.end-r.start);
-	ux500_pm_init(r.start, r.end-r.start);
-
-	/*
-	 * Init clocks here so that they are available for system timer
-	 * initialization.
-	 */
-	if (cpu_is_u8500_family())
-		u8500_clk_init();
-	else if (cpu_is_u9540())
-		u9540_clk_init();
-	else if (cpu_is_u8540())
-		u8540_clk_init();
-}
-
-static const char * __init ux500_get_machine(void)
-{
-	return kasprintf(GFP_KERNEL, "DB%4x", dbx500_partnumber());
-}
-
-static const char * __init ux500_get_family(void)
-{
-	return kasprintf(GFP_KERNEL, "ux500");
-}
-
-static const char * __init ux500_get_revision(void)
-{
-	unsigned int rev = dbx500_revision();
-
-	if (rev == 0x01)
-		return kasprintf(GFP_KERNEL, "%s", "ED");
-	else if (rev >= 0xA0)
-		return kasprintf(GFP_KERNEL, "%d.%d",
-				 (rev >> 4) - 0xA + 1, rev & 0xf);
-
-	return kasprintf(GFP_KERNEL, "%s", "Unknown");
-}
-
-static ssize_t ux500_get_process(struct device *dev,
-					struct device_attribute *attr,
-					char *buf)
-{
-	if (dbx500_id.process == 0x00)
-		return sprintf(buf, "Standard\n");
-
-	return sprintf(buf, "%02xnm\n", dbx500_id.process);
-}
-
-static void __init soc_info_populate(struct soc_device_attribute *soc_dev_attr,
-				     const char *soc_id)
-{
-	soc_dev_attr->soc_id   = soc_id;
-	soc_dev_attr->machine  = ux500_get_machine();
-	soc_dev_attr->family   = ux500_get_family();
-	soc_dev_attr->revision = ux500_get_revision();
-}
-
-static const struct device_attribute ux500_soc_attr =
-	__ATTR(process,  S_IRUGO, ux500_get_process,  NULL);
-
-struct device * __init ux500_soc_device_init(const char *soc_id)
-{
-	struct device *parent;
-	struct soc_device *soc_dev;
-	struct soc_device_attribute *soc_dev_attr;
-
-	soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL);
-	if (!soc_dev_attr)
-		return ERR_PTR(-ENOMEM);
-
-	soc_info_populate(soc_dev_attr, soc_id);
-
-	soc_dev = soc_device_register(soc_dev_attr);
-	if (IS_ERR(soc_dev)) {
-	        kfree(soc_dev_attr);
-		return NULL;
-	}
-
-	parent = soc_device_to_device(soc_dev);
-	device_create_file(parent, &ux500_soc_attr);
-
-	return parent;
-}
diff --git a/arch/arm/mach-ux500/id.c b/arch/arm/mach-ux500/id.c
deleted file mode 100644
index 1e81e990044b..000000000000
--- a/arch/arm/mach-ux500/id.c
+++ /dev/null
@@ -1,116 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2010
- *
- * Author: Rabin Vincent <rabin.vincent@stericsson.com> for ST-Ericsson
- * License terms: GNU General Public License (GPL) version 2
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/io.h>
-
-#include <asm/cputype.h>
-#include <asm/tlbflush.h>
-#include <asm/cacheflush.h>
-#include <asm/mach/map.h>
-
-#include "setup.h"
-
-#include "db8500-regs.h"
-#include "id.h"
-
-struct dbx500_asic_id dbx500_id;
-
-static unsigned int __init ux500_read_asicid(phys_addr_t addr)
-{
-	phys_addr_t base = addr & ~0xfff;
-	struct map_desc desc = {
-		.virtual	= (unsigned long)UX500_VIRT_ROM,
-		.pfn		= __phys_to_pfn(base),
-		.length		= SZ_16K,
-		.type		= MT_DEVICE,
-	};
-
-	iotable_init(&desc, 1);
-
-	/* As in devicemaps_init() */
-	local_flush_tlb_all();
-	flush_cache_all();
-
-	return readl(UX500_VIRT_ROM + (addr & 0xfff));
-}
-
-static void ux500_print_soc_info(unsigned int asicid)
-{
-	unsigned int rev = dbx500_revision();
-
-	pr_info("DB%4x ", dbx500_partnumber());
-
-	if (rev == 0x01)
-		pr_cont("Early Drop");
-	else if (rev >= 0xA0)
-		pr_cont("v%d.%d" , (rev >> 4) - 0xA + 1, rev & 0xf);
-	else
-		pr_cont("Unknown");
-
-	pr_cont(" [%#010x]\n", asicid);
-}
-
-static unsigned int partnumber(unsigned int asicid)
-{
-	return (asicid >> 8) & 0xffff;
-}
-
-/*
- * SOC		MIDR		ASICID ADDRESS		ASICID VALUE
- * DB8500ed	0x410fc090	0x9001FFF4		0x00850001
- * DB8500v1	0x411fc091	0x9001FFF4		0x008500A0
- * DB8500v1.1	0x411fc091	0x9001FFF4		0x008500A1
- * DB8500v2	0x412fc091	0x9001DBF4		0x008500B0
- * DB8520v2.2	0x412fc091	0x9001DBF4		0x008500B2
- * DB5500v1	0x412fc091	0x9001FFF4		0x005500A0
- * DB9540	0x413fc090	0xFFFFDBF4		0x009540xx
- */
-
-void __init ux500_setup_id(void)
-{
-	unsigned int cpuid = read_cpuid_id();
-	unsigned int asicid = 0;
-	phys_addr_t addr = 0;
-
-	switch (cpuid) {
-	case 0x410fc090: /* DB8500ed */
-	case 0x411fc091: /* DB8500v1 */
-		addr = 0x9001FFF4;
-		break;
-
-	case 0x412fc091: /* DB8520 / DB8500v2 / DB5500v1 */
-		asicid = ux500_read_asicid(0x9001DBF4);
-		if (partnumber(asicid) == 0x8500 ||
-		    partnumber(asicid) == 0x8520)
-			/* DB8500v2 */
-			break;
-
-		/* DB5500v1 */
-		addr = 0x9001FFF4;
-		break;
-
-	case 0x413fc090: /* DB9540 */
-		addr = 0xFFFFDBF4;
-		break;
-	}
-
-	if (addr)
-		asicid = ux500_read_asicid(addr);
-
-	if (!asicid) {
-		pr_err("Unable to identify SoC\n");
-		ux500_unknown_soc();
-	}
-
-	dbx500_id.process = asicid >> 24;
-	dbx500_id.partnumber = partnumber(asicid);
-	dbx500_id.revision = asicid & 0xff;
-
-	ux500_print_soc_info(asicid);
-}
diff --git a/arch/arm/mach-ux500/id.h b/arch/arm/mach-ux500/id.h
deleted file mode 100644
index bcc58a8cccbc..000000000000
--- a/arch/arm/mach-ux500/id.h
+++ /dev/null
@@ -1,144 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2010
- *
- * Author: Rabin Vincent <rabin.vincent@stericsson.com> for ST-Ericsson
- * License terms: GNU General Public License (GPL) version 2
- */
-
-#ifndef __MACH_UX500_ID
-#define __MACH_UX500_ID
-
-/**
- * struct dbx500_asic_id - fields of the ASIC ID
- * @process: the manufacturing process, 0x40 is 40 nm 0x00 is "standard"
- * @partnumber: hithereto 0x8500 for DB8500
- * @revision: version code in the series
- */
-struct dbx500_asic_id {
-	u16	partnumber;
-	u8	revision;
-	u8	process;
-};
-
-extern struct dbx500_asic_id dbx500_id;
-
-static inline unsigned int __attribute_const__ dbx500_partnumber(void)
-{
-	return dbx500_id.partnumber;
-}
-
-static inline unsigned int __attribute_const__ dbx500_revision(void)
-{
-	return dbx500_id.revision;
-}
-
-/*
- * SOCs
- */
-
-static inline bool __attribute_const__ cpu_is_u8500(void)
-{
-	return dbx500_partnumber() == 0x8500;
-}
-
-static inline bool __attribute_const__ cpu_is_u8520(void)
-{
-	return dbx500_partnumber() == 0x8520;
-}
-
-static inline bool cpu_is_u8500_family(void)
-{
-	return cpu_is_u8500() || cpu_is_u8520();
-}
-
-static inline bool __attribute_const__ cpu_is_u9540(void)
-{
-	return dbx500_partnumber() == 0x9540;
-}
-
-static inline bool __attribute_const__ cpu_is_u8540(void)
-{
-	return dbx500_partnumber() == 0x8540;
-}
-
-static inline bool __attribute_const__ cpu_is_u8580(void)
-{
-	return dbx500_partnumber() == 0x8580;
-}
-
-static inline bool cpu_is_ux540_family(void)
-{
-	return cpu_is_u9540() || cpu_is_u8540() || cpu_is_u8580();
-}
-
-/*
- * 8500 revisions
- */
-
-static inline bool __attribute_const__ cpu_is_u8500ed(void)
-{
-	return cpu_is_u8500() && dbx500_revision() == 0x00;
-}
-
-static inline bool __attribute_const__ cpu_is_u8500v1(void)
-{
-	return cpu_is_u8500() && (dbx500_revision() & 0xf0) == 0xA0;
-}
-
-static inline bool __attribute_const__ cpu_is_u8500v10(void)
-{
-	return cpu_is_u8500() && dbx500_revision() == 0xA0;
-}
-
-static inline bool __attribute_const__ cpu_is_u8500v11(void)
-{
-	return cpu_is_u8500() && dbx500_revision() == 0xA1;
-}
-
-static inline bool __attribute_const__ cpu_is_u8500v2(void)
-{
-	return cpu_is_u8500() && ((dbx500_revision() & 0xf0) == 0xB0);
-}
-
-static inline bool cpu_is_u8500v20(void)
-{
-	return cpu_is_u8500() && (dbx500_revision() == 0xB0);
-}
-
-static inline bool cpu_is_u8500v21(void)
-{
-	return cpu_is_u8500() && (dbx500_revision() == 0xB1);
-}
-
-static inline bool cpu_is_u8500v22(void)
-{
-	return cpu_is_u8500() && (dbx500_revision() == 0xB2);
-}
-
-static inline bool cpu_is_u8500v20_or_later(void)
-{
-	return (cpu_is_u8500() && !cpu_is_u8500v10() && !cpu_is_u8500v11());
-}
-
-/*
- * 8540 revisions
- */
-
-static inline bool __attribute_const__ cpu_is_u8540v10(void)
-{
-	return cpu_is_u8540() && dbx500_revision() == 0xA0;
-}
-
-static inline bool __attribute_const__ cpu_is_u8580v10(void)
-{
-	return cpu_is_u8580() && dbx500_revision() == 0xA0;
-}
-
-static inline bool ux500_is_svp(void)
-{
-	return false;
-}
-
-#define ux500_unknown_soc()	BUG()
-
-#endif
diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index 88b8ab4f300c..8f2f615ff958 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -26,7 +26,6 @@
 #include "setup.h"
 
 #include "db8500-regs.h"
-#include "id.h"
 
 /* Magic triggers in backup RAM */
 #define UX500_CPU1_JUMPADDR_OFFSET 0x1FF4
diff --git a/arch/arm/mach-ux500/setup.h b/arch/arm/mach-ux500/setup.h
index c704254ab67c..988e7c77068d 100644
--- a/arch/arm/mach-ux500/setup.h
+++ b/arch/arm/mach-ux500/setup.h
@@ -11,18 +11,6 @@
 #ifndef __ASM_ARCH_SETUP_H
 #define __ASM_ARCH_SETUP_H
 
-#include <asm/mach/arch.h>
-#include <linux/init.h>
-#include <linux/mfd/abx500/ab8500.h>
-
-void ux500_restart(enum reboot_mode mode, const char *cmd);
-
-void __init ux500_setup_id(void);
-
-extern void __init ux500_init_irq(void);
-
-extern struct device *ux500_soc_device_init(const char *soc_id);
-
 extern void ux500_cpu_die(unsigned int cpu);
 
 #endif /*  __ASM_ARCH_SETUP_H */
diff --git a/arch/arm/mach-versatile/versatile_dt.c b/arch/arm/mach-versatile/versatile_dt.c
index d643b9210dbd..3c8d39c12909 100644
--- a/arch/arm/mach-versatile/versatile_dt.c
+++ b/arch/arm/mach-versatile/versatile_dt.c
@@ -344,8 +344,7 @@ static void __init versatile_dt_init(void)
 
 	versatile_dt_pci_init();
 
-	of_platform_populate(NULL, of_default_bus_match_table,
-			     versatile_auxdata_lookup, NULL);
+	of_platform_default_populate(NULL, versatile_auxdata_lookup, NULL);
 }
 
 static const char *const versatile_dt_match[] __initconst = {
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 398a297b7e09..7c728ebc0b33 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -1,13 +1,13 @@
 menuconfig ARCH_VEXPRESS
 	bool "ARM Ltd. Versatile Express family"
 	depends on ARCH_MULTI_V7
-	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARM_AMBA
 	select ARM_GIC
 	select ARM_GLOBAL_TIMER
 	select ARM_TIMER_SP804
 	select COMMON_CLK_VERSATILE
+	select GPIOLIB
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
 	select HAVE_PATA_PLATFORM
diff --git a/arch/arm/mach-vexpress/hotplug.c b/arch/arm/mach-vexpress/hotplug.c
index f2fafc10a91d..d8f1a05f5e87 100644
--- a/arch/arm/mach-vexpress/hotplug.c
+++ b/arch/arm/mach-vexpress/hotplug.c
@@ -15,6 +15,8 @@
 #include <asm/smp_plat.h>
 #include <asm/cp15.h>
 
+#include "core.h"
+
 static inline void cpu_enter_lowpower(void)
 {
 	unsigned int v;
diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c
index 8409cab3f760..fe488523694c 100644
--- a/arch/arm/mach-vexpress/spc.c
+++ b/arch/arm/mach-vexpress/spc.c
@@ -31,6 +31,8 @@
 
 #include <asm/cacheflush.h>
 
+#include "spc.h"
+
 #define SPCLOG "vexpress-spc: "
 
 #define PERF_LVL_A15		0x00
@@ -319,17 +321,15 @@ static int ve_spc_waitforcompletion(int req_type)
 
 static int ve_spc_set_performance(int cluster, u32 freq)
 {
-	u32 perf_cfg_reg, perf_stat_reg;
+	u32 perf_cfg_reg;
 	int ret, perf, req_type;
 
 	if (cluster_is_a15(cluster)) {
 		req_type = CA15_DVFS;
 		perf_cfg_reg = PERF_LVL_A15;
-		perf_stat_reg = PERF_REQ_A15;
 	} else {
 		req_type = CA7_DVFS;
 		perf_cfg_reg = PERF_LVL_A7;
-		perf_stat_reg = PERF_REQ_A7;
 	}
 
 	perf = ve_spc_find_performance_index(cluster, freq);
diff --git a/arch/arm/mach-vt8500/Kconfig b/arch/arm/mach-vt8500/Kconfig
index aaaa24fe4d71..c4f1dba7bd8a 100644
--- a/arch/arm/mach-vt8500/Kconfig
+++ b/arch/arm/mach-vt8500/Kconfig
@@ -1,6 +1,6 @@
 config ARCH_VT8500
 	bool
-	select ARCH_REQUIRE_GPIOLIB
+	select GPIOLIB
 	select CLKDEV_LOOKUP
 	select VT8500_TIMER
 	select PINCTRL
diff --git a/arch/arm/mach-vt8500/vt8500.c b/arch/arm/mach-vt8500/vt8500.c
index 3bc0dc9a4d69..773c04fdb746 100644
--- a/arch/arm/mach-vt8500/vt8500.c
+++ b/arch/arm/mach-vt8500/vt8500.c
@@ -30,7 +30,6 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
 
 #define LEGACY_GPIO_BASE	0xD8110000
 #define LEGACY_PMC_BASE		0xD8130000
@@ -158,8 +157,6 @@ static void __init vt8500_init(void)
 		pm_power_off = &vt8500_power_off;
 	else
 		pr_err("%s: PMC Hibernation register could not be remapped, not enabling power off!\n", __func__);
-
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
 static const char * const vt8500_dt_compat[] = {
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index da876d28ccbc..d12002cd63bc 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -141,7 +141,7 @@ out:
 	 * Finished with the static registrations now; fill in the missing
 	 * devices
 	 */
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, parent);
+	of_platform_default_populate(NULL, NULL, parent);
 
 	platform_device_register(&zynq_cpuidle_device);
 }
diff --git a/arch/arm/plat-iop/setup.c b/arch/arm/plat-iop/setup.c
index 5b217f460f18..8151bde990e6 100644
--- a/arch/arm/plat-iop/setup.c
+++ b/arch/arm/plat-iop/setup.c
@@ -20,12 +20,12 @@
  * the IOP3xx OCCDR must be mapped uncached and unbuffered.
  */
 static struct map_desc iop3xx_std_desc[] __initdata = {
-	 {	/* mem mapped registers */
+	{	/* mem mapped registers */
 		.virtual	= IOP3XX_PERIPHERAL_VIRT_BASE,
 		.pfn		= __phys_to_pfn(IOP3XX_PERIPHERAL_PHYS_BASE),
 		.length		= IOP3XX_PERIPHERAL_SIZE,
 		.type		= MT_UNCACHED,
-	 },
+	},
 };
 
 void __init iop3xx_map_io(void)
diff --git a/arch/arm/plat-samsung/cpu.c b/arch/arm/plat-samsung/cpu.c
index 71333bb61013..a107b3a0b095 100644
--- a/arch/arm/plat-samsung/cpu.c
+++ b/arch/arm/plat-samsung/cpu.c
@@ -29,14 +29,14 @@ EXPORT_SYMBOL(samsung_rev);
 
 void __init s3c64xx_init_cpu(void)
 {
-	samsung_cpu_id = __raw_readl(S3C_VA_SYS + 0x118);
+	samsung_cpu_id = readl_relaxed(S3C_VA_SYS + 0x118);
 	if (!samsung_cpu_id) {
 		/*
 		 * S3C6400 has the ID register in a different place,
 		 * and needs a write before it can be read.
 		 */
-		__raw_writel(0x0, S3C_VA_SYS + 0xA1C);
-		samsung_cpu_id = __raw_readl(S3C_VA_SYS + 0xA1C);
+		writel_relaxed(0x0, S3C_VA_SYS + 0xA1C);
+		samsung_cpu_id = readl_relaxed(S3C_VA_SYS + 0xA1C);
 	}
 
 	samsung_cpu_rev = 0;
@@ -44,9 +44,9 @@ void __init s3c64xx_init_cpu(void)
 	pr_info("Samsung CPU ID: 0x%08lx\n", samsung_cpu_id);
 }
 
-void __init s5p_init_cpu(void __iomem *cpuid_addr)
+void __init s5p_init_cpu(const void __iomem *cpuid_addr)
 {
-	samsung_cpu_id = __raw_readl(cpuid_addr);
+	samsung_cpu_id = readl_relaxed(cpuid_addr);
 	samsung_cpu_rev = samsung_cpu_id & 0xFF;
 
 	pr_info("Samsung CPU ID: 0x%08lx\n", samsung_cpu_id);
diff --git a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
index 317c52303288..37cf20e04aff 100644
--- a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
+++ b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
@@ -39,7 +39,7 @@ struct s3c2410_iobank_timing {
 	unsigned int	tacs;
 	unsigned int	tcos;
 	unsigned int	tacc;
-	unsigned int	tcoh;		/* nCS hold afrer nOE/nWE */
+	unsigned int	tcoh;		/* nCS hold after nOE/nWE */
 	unsigned int	tcah;		/* Address hold after nCS */
 	unsigned char	nwait_en;	/* nWait enabled for bank. */
 };
diff --git a/arch/arm/plat-samsung/include/plat/cpu.h b/arch/arm/plat-samsung/include/plat/cpu.h
index 61d14f3a0426..b7b702a72cac 100644
--- a/arch/arm/plat-samsung/include/plat/cpu.h
+++ b/arch/arm/plat-samsung/include/plat/cpu.h
@@ -113,6 +113,7 @@ extern void s3c_init_cpu(unsigned long idcode,
 extern void s3c24xx_init_io(struct map_desc *mach_desc, int size);
 
 extern void s3c64xx_init_cpu(void);
+extern void s5p_init_cpu(const void __iomem *cpuid_addr);
 
 extern unsigned int samsung_rev(void);
 
diff --git a/arch/arm/plat-samsung/include/plat/fb-s3c2410.h b/arch/arm/plat-samsung/include/plat/fb-s3c2410.h
index 4e5d9588b5ba..1f2972a74e9f 100644
--- a/arch/arm/plat-samsung/include/plat/fb-s3c2410.h
+++ b/arch/arm/plat-samsung/include/plat/fb-s3c2410.h
@@ -48,7 +48,7 @@ struct s3c2410fb_display {
 
 struct s3c2410fb_mach_info {
 
-	struct s3c2410fb_display *displays;	/* attached diplays info */
+	struct s3c2410fb_display *displays;	/* attached displays info */
 	unsigned num_displays;			/* number of defined displays */
 	unsigned default_display;
 
diff --git a/arch/arm/plat-samsung/include/plat/gpio-cfg.h b/arch/arm/plat-samsung/include/plat/gpio-cfg.h
index b5294eff18b5..21391faab068 100644
--- a/arch/arm/plat-samsung/include/plat/gpio-cfg.h
+++ b/arch/arm/plat-samsung/include/plat/gpio-cfg.h
@@ -35,7 +35,7 @@ struct samsung_gpio_chip;
  * struct samsung_gpio_cfg GPIO configuration
  * @cfg_eint: Configuration setting when used for external interrupt source
  * @get_pull: Read the current pull configuration for the GPIO
- * @set_pull: Set the current pull configuraiton for the GPIO
+ * @set_pull: Set the current pull configuration for the GPIO
  * @set_config: Set the current configuration for the GPIO
  * @get_config: Read the current configuration for the GPIO
  *
diff --git a/arch/arm/plat-samsung/pm-check.c b/arch/arm/plat-samsung/pm-check.c
index 70f2f699bed3..d63516374f7c 100644
--- a/arch/arm/plat-samsung/pm-check.c
+++ b/arch/arm/plat-samsung/pm-check.c
@@ -5,7 +5,7 @@
  *	http://armlinux.simtec.co.uk
  *	Ben Dooks <ben@simtec.co.uk>
  *
- * S3C Power Mangament - suspend/resume memory corruptiuon check.
+ * S3C Power Mangament - suspend/resume memory corruption check.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/arch/arm/plat-samsung/pm-common.c b/arch/arm/plat-samsung/pm-common.c
index 515cd53372bd..6534c3ff9fe2 100644
--- a/arch/arm/plat-samsung/pm-common.c
+++ b/arch/arm/plat-samsung/pm-common.c
@@ -31,7 +31,7 @@
 void s3c_pm_do_save(struct sleep_save *ptr, int count)
 {
 	for (; count > 0; count--, ptr++) {
-		ptr->val = __raw_readl(ptr->reg);
+		ptr->val = readl_relaxed(ptr->reg);
 		S3C_PMDBG("saved %p value %08lx\n", ptr->reg, ptr->val);
 	}
 }
@@ -51,9 +51,9 @@ void s3c_pm_do_restore(const struct sleep_save *ptr, int count)
 {
 	for (; count > 0; count--, ptr++) {
 		pr_debug("restore %p (restore %08lx, was %08x)\n",
-				ptr->reg, ptr->val, __raw_readl(ptr->reg));
+				ptr->reg, ptr->val, readl_relaxed(ptr->reg));
 
-		__raw_writel(ptr->val, ptr->reg);
+		writel_relaxed(ptr->val, ptr->reg);
 	}
 }
 
@@ -71,5 +71,5 @@ void s3c_pm_do_restore(const struct sleep_save *ptr, int count)
 void s3c_pm_do_restore_core(const struct sleep_save *ptr, int count)
 {
 	for (; count > 0; count--, ptr++)
-		__raw_writel(ptr->val, ptr->reg);
+		writel_relaxed(ptr->val, ptr->reg);
 }
diff --git a/arch/arm/plat-samsung/watchdog-reset.c b/arch/arm/plat-samsung/watchdog-reset.c
index 2ecb50bea044..307d8ad96a78 100644
--- a/arch/arm/plat-samsung/watchdog-reset.c
+++ b/arch/arm/plat-samsung/watchdog-reset.c
@@ -3,7 +3,7 @@
  * Copyright (c) 2008 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
- * Coyright (c) 2013 Tomasz Figa <tomasz.figa@gmail.com>
+ * Copyright (c) 2013 Tomasz Figa <tomasz.figa@gmail.com>
  *
  * Watchdog reset support for Samsung SoCs.
  *
diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c
index 53feb90c840c..c2366510187a 100644
--- a/arch/arm/plat-versatile/platsmp.c
+++ b/arch/arm/plat-versatile/platsmp.c
@@ -18,6 +18,8 @@
 #include <asm/cacheflush.h>
 #include <asm/smp_plat.h>
 
+#include <plat/platsmp.h>
+
 /*
  * Write pen_release in a way that is guaranteed to be visible to all
  * observers, irrespective of whether they're taking part in coherency
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9f8b99e20557..69c8787bec7d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -3,6 +3,7 @@ config ARM64
 	select ACPI_CCA_REQUIRED if ACPI
 	select ACPI_GENERIC_GSI if ACPI
 	select ACPI_REDUCED_HARDWARE_ONLY if ACPI
+	select ACPI_MCFG if ACPI
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
@@ -22,9 +23,9 @@ config ARM64
 	select ARM_ARCH_TIMER
 	select ARM_GIC
 	select AUDIT_ARCH_COMPAT_GENERIC
-	select ARM_GIC_V2M if PCI_MSI
+	select ARM_GIC_V2M if PCI
 	select ARM_GIC_V3
-	select ARM_GIC_V3_ITS if PCI_MSI
+	select ARM_GIC_V3_ITS if PCI
 	select ARM_PSCI_FW
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
@@ -78,6 +79,7 @@ config ARM64
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_GCC_PLUGINS
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_IRQ_TIME_ACCOUNTING
@@ -101,6 +103,7 @@ config ARM64
 	select OF_EARLY_FLATTREE
 	select OF_NUMA if NUMA && OF
 	select OF_RESERVED_MEM
+	select PCI_ECAM if ACPI
 	select PERF_USE_VMALLOC
 	select POWER_RESET
 	select POWER_SUPPLY
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 7ef1d05859ae..bb2616b16157 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -13,6 +13,19 @@ config ARCH_ALPINE
 	  This enables support for the Annapurna Labs Alpine
 	  Soc family.
 
+config ARCH_BCM2835
+	bool "Broadcom BCM2835 family"
+	select ARCH_REQUIRE_GPIOLIB
+	select CLKSRC_OF
+	select PINCTRL
+	select PINCTRL_BCM2835
+	select ARM_AMBA
+	select ARM_TIMER_SP804
+	select HAVE_ARM_ARCH_TIMER
+	help
+	  This enables support for the Broadcom BCM2837 SoC.
+	  This SoC is used in the Raspberry Pi 3 device.
+
 config ARCH_BCM_IPROC
 	bool "Broadcom iProc SoC Family"
 	select COMMON_CLK_IPROC
@@ -36,6 +49,7 @@ config ARCH_EXYNOS
 	select HAVE_S3C_RTC if RTC_CLASS
 	select PINCTRL
 	select PINCTRL_EXYNOS
+	select SOC_SAMSUNG
 	help
 	  This enables support for ARMv8 based Samsung Exynos SoC family.
 
@@ -66,6 +80,10 @@ config ARCH_MEDIATEK
 
 config ARCH_MESON
 	bool "Amlogic Platforms"
+	select PINCTRL
+	select PINCTRL_MESON
+	select COMMON_CLK_AMLOGIC
+	select COMMON_CLK_GXBB
 	help
 	  This enables support for the Amlogic S905 SoCs.
 
@@ -73,6 +91,7 @@ config ARCH_MVEBU
 	bool "Marvell EBU SoC Family"
 	select ARMADA_AP806_SYSCON
 	select ARMADA_CP110_SYSCON
+	select ARMADA_37XX_CLK
 	select MVEBU_ODMI
 	help
 	  This enables support for Marvell EBU familly, including:
@@ -121,6 +140,12 @@ config ARCH_R8A7795
 	help
 	  This enables support for the Renesas R-Car H3 SoC.
 
+config ARCH_R8A7796
+	bool "Renesas R-Car M3-W SoC Platform"
+	depends on ARCH_RENESAS
+	help
+	  This enables support for the Renesas R-Car M3-W SoC.
+
 config ARCH_STRATIX10
 	bool "Altera's Stratix 10 SoCFPGA Family"
 	help
@@ -160,6 +185,8 @@ config ARCH_VEXPRESS
 	bool "ARMv8 software model (Versatile Express)"
 	select ARCH_REQUIRE_GPIOLIB
 	select COMMON_CLK_VERSATILE
+	select PM
+	select PM_GENERIC_DOMAINS
 	select POWER_RESET_VEXPRESS
 	select VEXPRESS_CONFIG
 	help
@@ -168,6 +195,7 @@ config ARCH_VEXPRESS
 
 config ARCH_VULCAN
 	bool "Broadcom Vulcan SOC Family"
+	select GPIOLIB
 	help
 	  This enables support for Broadcom Vulcan SoC Family
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
index 7f2c6747a71e..90a84c514d3d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
@@ -45,6 +45,7 @@
 /dts-v1/;
 
 #include "meson-gxbb.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 
 / {
 	compatible = "hardkernel,odroid-c2", "amlogic,meson-gxbb";
@@ -62,8 +63,27 @@
 		device_type = "memory";
 		reg = <0x0 0x0 0x0 0x80000000>;
 	};
+
+	leds {
+		compatible = "gpio-leds";
+		blue {
+			label = "c2:blue:alive";
+			gpios = <&gpio_ao GPIOAO_13 GPIO_ACTIVE_LOW>;
+			linux,default-trigger = "heartbeat";
+			default-state = "off";
+		};
+	};
 };
 
 &uart_AO {
 	status = "okay";
+	pinctrl-0 = <&uart_ao_a_pins>;
+	pinctrl-names = "default";
+};
+
+&ethmac {
+	status = "okay";
+	pinctrl-0 = <&eth_pins>;
+	pinctrl-names = "default";
 };
+
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
index bf7ff1d41851..f4f30f674b4c 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
@@ -62,4 +62,13 @@
 /* This UART is brought out to the DB9 connector */
 &uart_AO {
 	status = "okay";
+	pinctrl-0 = <&uart_ao_a_pins>;
+	pinctrl-names = "default";
 };
+
+&ethmac {
+	status = "okay";
+	pinctrl-0 = <&eth_pins>;
+	pinctrl-names = "default";
+};
+
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
index 012cdccc8a35..54bb7c739089 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
@@ -56,4 +56,7 @@
 
 &uart_AO {
 	status = "okay";
+	pinctrl-0 = <&uart_ao_a_pins>;
+	pinctrl-names = "default";
+
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 832815d80462..e502c24b0ac7 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -43,6 +43,8 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/gpio/meson-gxbb-gpio.h>
+#include <dt-bindings/reset/amlogic,meson-gxbb-reset.h>
 
 / {
 	compatible = "amlogic,meson-gxbb";
@@ -129,13 +131,35 @@
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xc1100000 0x0 0x100000>;
 
+			reset: reset-controller@4404 {
+				compatible = "amlogic,meson-gxbb-reset";
+				reg = <0x0 0x04404 0x0 0x20>;
+				#reset-cells = <1>;
+			};
+
 			uart_A: serial@84c0 {
 				compatible = "amlogic,meson-uart";
-				reg = <0x0 0x084c0 0x0 0x14>;
+				reg = <0x0 0x84c0 0x0 0x14>;
 				interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>;
 				clocks = <&xtal>;
 				status = "disabled";
 			};
+
+			uart_B: serial@84dc {
+				compatible = "amlogic,meson-uart";
+				reg = <0x0 0x84dc 0x0 0x14>;
+				interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&xtal>;
+				status = "disabled";
+			};
+
+			uart_C: serial@8700 {
+				compatible = "amlogic,meson-uart";
+				reg = <0x0 0x8700 0x0 0x14>;
+				interrupts = <GIC_SPI 93 IRQ_TYPE_EDGE_RISING>;
+				clocks = <&xtal>;
+				status = "disabled";
+			};
 		};
 
 		gic: interrupt-controller@c4301000 {
@@ -158,6 +182,29 @@
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xc8100000 0x0 0x100000>;
 
+			pinctrl_aobus: pinctrl@14 {
+				compatible = "amlogic,meson-gxbb-aobus-pinctrl";
+				#address-cells = <2>;
+				#size-cells = <2>;
+				ranges;
+
+				gpio_ao: bank@14 {
+					reg = <0x0 0x00014 0x0 0x8>,
+					      <0x0 0x0002c 0x0 0x4>,
+					      <0x0 0x00024 0x0 0x8>;
+					reg-names = "mux", "pull", "gpio";
+					gpio-controller;
+					#gpio-cells = <2>;
+				};
+
+				uart_ao_a_pins: uart_ao_a {
+					mux {
+						groups = "uart_tx_ao_a", "uart_rx_ao_a";
+						function = "uart_ao";
+					};
+				};
+			};
+
 			uart_AO: serial@4c0 {
 				compatible = "amlogic,meson-uart";
 				reg = <0x0 0x004c0 0x0 0x14>;
@@ -167,6 +214,115 @@
 			};
 		};
 
+		periphs: periphs@c8834000 {
+			compatible = "simple-bus";
+			reg = <0x0 0xc8834000 0x0 0x2000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges = <0x0 0x0 0x0 0xc8834000 0x0 0x2000>;
+
+			rng {
+				compatible = "amlogic,meson-rng";
+				reg = <0x0 0x0 0x0 0x4>;
+			};
+
+			pinctrl_periphs: pinctrl@4b0 {
+				compatible = "amlogic,meson-gxbb-periphs-pinctrl";
+				#address-cells = <2>;
+				#size-cells = <2>;
+				ranges;
+
+				gpio: bank@4b0 {
+					reg = <0x0 0x004b0 0x0 0x28>,
+					      <0x0 0x004e8 0x0 0x14>,
+					      <0x0 0x00120 0x0 0x14>,
+					      <0x0 0x00430 0x0 0x40>;
+					reg-names = "mux", "pull", "pull-enable", "gpio";
+					gpio-controller;
+					#gpio-cells = <2>;
+				};
+
+				emmc_pins: emmc {
+					mux {
+						groups = "emmc_nand_d07",
+						       "emmc_cmd",
+						       "emmc_clk";
+						function = "emmc";
+					};
+				};
+
+				sdcard_pins: sdcard {
+					mux {
+						groups = "sdcard_d0",
+						       "sdcard_d1",
+						       "sdcard_d2",
+						       "sdcard_d3",
+						       "sdcard_cmd",
+						       "sdcard_clk";
+						function = "sdcard";
+					};
+				};
+
+				uart_a_pins: uart_a {
+					mux {
+						groups = "uart_tx_a",
+						       "uart_rx_a";
+						function = "uart_a";
+					};
+				};
+
+				uart_b_pins: uart_b {
+					mux {
+						groups = "uart_tx_b",
+						       "uart_rx_b";
+						function = "uart_b";
+					};
+				};
+
+				uart_c_pins: uart_c {
+					mux {
+						groups = "uart_tx_c",
+						       "uart_rx_c";
+						function = "uart_c";
+					};
+				};
+
+				eth_pins: eth_c {
+					mux {
+						groups = "eth_mdio",
+						       "eth_mdc",
+						       "eth_clk_rx_clk",
+						       "eth_rx_dv",
+						       "eth_rxd0",
+						       "eth_rxd1",
+						       "eth_rxd2",
+						       "eth_rxd3",
+						       "eth_rgmii_tx_clk",
+						       "eth_tx_en",
+						       "eth_txd0",
+						       "eth_txd1",
+						       "eth_txd2",
+						       "eth_txd3";
+						function = "eth";
+					};
+				};
+			};
+		};
+
+		hiubus: hiubus@c883c000 {
+			compatible = "simple-bus";
+			reg = <0x0 0xc883c000 0x0 0x2000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges = <0x0 0x0 0x0 0xc883c000 0x0 0x2000>;
+
+			clkc: clock-controller@0 {
+				compatible = "amlogic,gxbb-clkc";
+				#clock-cells = <1>;
+				reg = <0x0 0x0 0x0 0x3db>;
+			};
+		};
+
 		apb: apb@d0000000 {
 			compatible = "simple-bus";
 			reg = <0x0 0xd0000000 0x0 0x200000>;
@@ -174,5 +330,17 @@
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xd0000000 0x0 0x200000>;
 		};
+
+		ethmac: ethernet@c9410000 {
+			compatible = "amlogic,meson6-dwmac", "snps,dwmac";
+			reg = <0x0 0xc9410000 0x0 0x10000
+			       0x0 0xc8834540 0x0 0x4>;
+			interrupts = <0 8 1>;
+			interrupt-names = "macirq";
+			clocks = <&xtal>;
+			clock-names = "stmmaceth";
+			phy-mode = "rgmii";
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi b/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi
index 2e1e5daa1dc7..1425ed41620c 100644
--- a/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi
@@ -106,88 +106,88 @@
 		interrupts = <1 9 0xf04>;	/* GIC Maintenence IRQ */
 		ranges = <0 0 0 0x79000000 0x0 0x800000>; /* MSI Range */
 		reg = <0x0 0x78090000 0x0 0x10000>,	/* GIC Dist */
-		      <0x0 0x780A0000 0x0 0x20000>,	/* GIC CPU */
-		      <0x0 0x780C0000 0x0 0x10000>,	/* GIC VCPU Control */
-		      <0x0 0x780E0000 0x0 0x20000>;	/* GIC VCPU */
-		v2m0: v2m@0x00000 {
+		      <0x0 0x780a0000 0x0 0x20000>,	/* GIC CPU */
+		      <0x0 0x780c0000 0x0 0x10000>,	/* GIC VCPU Control */
+		      <0x0 0x780e0000 0x0 0x20000>;	/* GIC VCPU */
+		v2m0: v2m@00000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x0 0x0 0x1000>;
 		};
-		v2m1: v2m@0x10000 {
+		v2m1: v2m@10000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x10000 0x0 0x1000>;
 		};
-		v2m2: v2m@0x20000 {
+		v2m2: v2m@20000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x20000 0x0 0x1000>;
 		};
-		v2m3: v2m@0x30000 {
+		v2m3: v2m@30000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x30000 0x0 0x1000>;
 		};
-		v2m4: v2m@0x40000 {
+		v2m4: v2m@40000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x40000 0x0 0x1000>;
 		};
-		v2m5: v2m@0x50000 {
+		v2m5: v2m@50000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x50000 0x0 0x1000>;
 		};
-		v2m6: v2m@0x60000 {
+		v2m6: v2m@60000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x60000 0x0 0x1000>;
 		};
-		v2m7: v2m@0x70000 {
+		v2m7: v2m@70000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x70000 0x0 0x1000>;
 		};
-		v2m8: v2m@0x80000 {
+		v2m8: v2m@80000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x80000 0x0 0x1000>;
 		};
-		v2m9: v2m@0x90000 {
+		v2m9: v2m@90000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
 			reg = <0x0 0x90000 0x0 0x1000>;
 		};
-		v2m10: v2m@0xA0000 {
+		v2m10: v2m@a0000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
-			reg = <0x0 0xA0000 0x0 0x1000>;
+			reg = <0x0 0xa0000 0x0 0x1000>;
 		};
-		v2m11: v2m@0xB0000 {
+		v2m11: v2m@b0000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
-			reg = <0x0 0xB0000 0x0 0x1000>;
+			reg = <0x0 0xb0000 0x0 0x1000>;
 		};
-		v2m12: v2m@0xC0000 {
+		v2m12: v2m@c0000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
-			reg = <0x0 0xC0000 0x0 0x1000>;
+			reg = <0x0 0xc0000 0x0 0x1000>;
 		};
-		v2m13: v2m@0xD0000 {
+		v2m13: v2m@d0000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
-			reg = <0x0 0xD0000 0x0 0x1000>;
+			reg = <0x0 0xd0000 0x0 0x1000>;
 		};
-		v2m14: v2m@0xE0000 {
+		v2m14: v2m@e0000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
-			reg = <0x0 0xE0000 0x0 0x1000>;
+			reg = <0x0 0xe0000 0x0 0x1000>;
 		};
-		v2m15: v2m@0xF0000 {
+		v2m15: v2m@f0000 {
 			compatible = "arm,gic-v2m-frame";
 			msi-controller;
-			reg = <0x0 0xF0000 0x0 0x1000>;
+			reg = <0x0 0xf0000 0x0 0x1000>;
 		};
 	};
 
@@ -198,10 +198,10 @@
 
 	timer {
 		compatible = "arm,armv8-timer";
-		interrupts = <1 0 0xff04>,	/* Secure Phys IRQ */
-			     <1 13 0xff04>,	/* Non-secure Phys IRQ */
-			     <1 14 0xff04>,	/* Virt IRQ */
-			     <1 15 0xff04>;	/* Hyp IRQ */
+		interrupts = <1 0 0xff08>,	/* Secure Phys IRQ */
+			     <1 13 0xff08>,	/* Non-secure Phys IRQ */
+			     <1 14 0xff08>,	/* Virt IRQ */
+			     <1 15 0xff08>;	/* Hyp IRQ */
 		clock-frequency = <50000000>;
 	};
 
@@ -637,8 +637,8 @@
 			compatible = "apm,xgene2-sgenet";
 			status = "disabled";
 			reg = <0x0 0x1f610000 0x0 0xd100>,
-			      <0x0 0x1f600000 0x0 0Xd100>,
-			      <0x0 0x20000000 0x0 0X20000>;
+			      <0x0 0x1f600000 0x0 0xd100>,
+			      <0x0 0x20000000 0x0 0x20000>;
 			interrupts = <0 96 4>,
 				     <0 97 4>;
 			dma-coherent;
@@ -652,8 +652,8 @@
 			compatible = "apm,xgene2-xgenet";
 			status = "disabled";
 			reg = <0x0 0x1f620000 0x0 0x10000>,
-			      <0x0 0x1f600000 0x0 0Xd100>,
-			      <0x0 0x20000000 0x0 0X220000>;
+			      <0x0 0x1f600000 0x0 0xd100>,
+			      <0x0 0x20000000 0x0 0x220000>;
 			interrupts = <0 108 4>,
 				     <0 109 4>,
 				     <0 110 4>,
@@ -693,7 +693,7 @@
 			#size-cells = <0>;
 			compatible = "snps,designware-i2c";
 			reg = <0x0 0x10640000 0x0 0x1000>;
-			interrupts = <0 0x3A 0x4>;
+			interrupts = <0 0x3a 0x4>;
 			clocks = <&i2c4clk 0>;
 			bus_num = <4>;
 		};
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index 6bf7cbe2e72d..f1c2c713f9b0 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -199,16 +199,6 @@
 				clock-output-names = "sdioclk";
 			};
 
-			qmlclk: qmlclk {
-				compatible = "apm,xgene-device-clock";
-				#clock-cells = <1>;
-				clocks = <&socplldiv2 0>;
-				clock-names = "qmlclk";
-				reg = <0x0 0x1703C000 0x0 0x1000>;
-				reg-names = "csr-reg";
-				clock-output-names = "qmlclk";
-			};
-
 			ethclk: ethclk {
 				compatible = "apm,xgene-device-clock";
 				#clock-cells = <1>;
@@ -226,7 +216,7 @@
 				compatible = "apm,xgene-device-clock";
 				#clock-cells = <1>;
 				clocks = <&ethclk 0>;
-				reg = <0x0 0x1702C000 0x0 0x1000>;
+				reg = <0x0 0x1702c000 0x0 0x1000>;
 				reg-names = "csr-reg";
 				clock-output-names = "menetclk";
 			};
@@ -924,8 +914,8 @@
 			compatible = "apm,xgene-enet";
 			status = "disabled";
 			reg = <0x0 0x17020000 0x0 0xd100>,
-			      <0x0 0X17030000 0x0 0Xc300>,
-			      <0x0 0X10000000 0x0 0X200>;
+			      <0x0 0x17030000 0x0 0xc300>,
+			      <0x0 0x10000000 0x0 0x200>;
 			reg-names = "enet_csr", "ring_csr", "ring_cmd";
 			interrupts = <0x0 0x3c 0x4>;
 			dma-coherent;
@@ -950,11 +940,11 @@
 			compatible = "apm,xgene1-sgenet";
 			status = "disabled";
 			reg = <0x0 0x1f210000 0x0 0xd100>,
-			      <0x0 0x1f200000 0x0 0Xc300>,
-			      <0x0 0x1B000000 0x0 0X200>;
+			      <0x0 0x1f200000 0x0 0xc300>,
+			      <0x0 0x1b000000 0x0 0x200>;
 			reg-names = "enet_csr", "ring_csr", "ring_cmd";
-			interrupts = <0x0 0xA0 0x4>,
-				     <0x0 0xA1 0x4>;
+			interrupts = <0x0 0xa0 0x4>,
+				     <0x0 0xa1 0x4>;
 			dma-coherent;
 			clocks = <&sge0clk 0>;
 			local-mac-address = [00 00 00 00 00 00];
@@ -966,11 +956,11 @@
 			compatible = "apm,xgene1-sgenet";
 			status = "disabled";
 			reg = <0x0 0x1f210030 0x0 0xd100>,
-			      <0x0 0x1f200000 0x0 0Xc300>,
-			      <0x0 0x1B000000 0x0 0X8000>;
+			      <0x0 0x1f200000 0x0 0xc300>,
+			      <0x0 0x1b000000 0x0 0x8000>;
 			reg-names = "enet_csr", "ring_csr", "ring_cmd";
-			interrupts = <0x0 0xAC 0x4>,
-				     <0x0 0xAD 0x4>;
+			interrupts = <0x0 0xac 0x4>,
+				     <0x0 0xad 0x4>;
 			port-id = <1>;
 			dma-coherent;
 			local-mac-address = [00 00 00 00 00 00];
@@ -982,8 +972,8 @@
 			compatible = "apm,xgene1-xgenet";
 			status = "disabled";
 			reg = <0x0 0x1f610000 0x0 0xd100>,
-			      <0x0 0x1f600000 0x0 0Xc300>,
-			      <0x0 0x18000000 0x0 0X200>;
+			      <0x0 0x1f600000 0x0 0xc300>,
+			      <0x0 0x18000000 0x0 0x200>;
 			reg-names = "enet_csr", "ring_csr", "ring_cmd";
 			interrupts = <0x0 0x60 0x4>,
 				     <0x0 0x61 0x4>,
@@ -1005,11 +995,11 @@
 			compatible = "apm,xgene1-xgenet";
 			status = "disabled";
 			reg = <0x0 0x1f620000 0x0 0xd100>,
-			      <0x0 0x1f600000 0x0 0Xc300>,
-			      <0x0 0x18000000 0x0 0X8000>;
+			      <0x0 0x1f600000 0x0 0xc300>,
+			      <0x0 0x18000000 0x0 0x8000>;
 			reg-names = "enet_csr", "ring_csr", "ring_cmd";
-			interrupts = <0x0 0x6C 0x4>,
-				     <0x0 0x6D 0x4>;
+			interrupts = <0x0 0x6c 0x4>,
+				     <0x0 0x6d 0x4>;
 			port-id = <1>;
 			dma-coherent;
 			clocks = <&xge1clk 0>;
diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi
index dee2386d3b9b..334271a25f70 100644
--- a/arch/arm64/boot/dts/arm/juno-base.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-base.dtsi
@@ -56,6 +56,315 @@
 			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(6) | IRQ_TYPE_LEVEL_LOW)>;
 	};
 
+	/*
+	 * Juno TRMs specify the size for these coresight components as 64K.
+	 * The actual size is just 4K though 64K is reserved. Access to the
+	 * unmapped reserved region results in a DECERR response.
+	 */
+	etf@20010000 {
+		compatible = "arm,coresight-tmc", "arm,primecell";
+		reg = <0 0x20010000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* input port */
+			port@0 {
+				reg = <0>;
+				etf_in_port: endpoint {
+					slave-mode;
+					remote-endpoint = <&main_funnel_out_port>;
+				};
+			};
+
+			/* output port */
+			port@1 {
+				reg = <0>;
+				etf_out_port: endpoint {
+					remote-endpoint = <&replicator_in_port0>;
+				};
+			};
+		};
+	};
+
+	tpiu@20030000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0 0x20030000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		port {
+			tpiu_in_port: endpoint {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port0>;
+			};
+		};
+	};
+
+	main-funnel@20040000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0x20040000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				main_funnel_out_port: endpoint {
+					remote-endpoint = <&etf_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <0>;
+				main_funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&cluster0_funnel_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				main_funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&cluster1_funnel_out_port>;
+				};
+			};
+
+		};
+	};
+
+	etr@20070000 {
+		compatible = "arm,coresight-tmc", "arm,primecell";
+		reg = <0 0x20070000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		port {
+			etr_in_port: endpoint {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port1>;
+			};
+		};
+	};
+
+	etm0: etm@22040000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x22040000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		port {
+			cluster0_etm0_out_port: endpoint {
+				remote-endpoint = <&cluster0_funnel_in_port0>;
+			};
+		};
+	};
+
+	cluster0-funnel@220c0000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0x220c0000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				cluster0_funnel_out_port: endpoint {
+					remote-endpoint = <&main_funnel_in_port0>;
+				};
+			};
+
+			port@1 {
+				reg = <0>;
+				cluster0_funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&cluster0_etm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				cluster0_funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&cluster0_etm1_out_port>;
+				};
+			};
+		};
+	};
+
+	etm1: etm@22140000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x22140000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		port {
+			cluster0_etm1_out_port: endpoint {
+				remote-endpoint = <&cluster0_funnel_in_port1>;
+			};
+		};
+	};
+
+	etm2: etm@23040000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x23040000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		port {
+			cluster1_etm0_out_port: endpoint {
+				remote-endpoint = <&cluster1_funnel_in_port0>;
+			};
+		};
+	};
+
+	cluster1-funnel@230c0000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0x230c0000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				cluster1_funnel_out_port: endpoint {
+					remote-endpoint = <&main_funnel_in_port1>;
+				};
+			};
+
+			port@1 {
+				reg = <0>;
+				cluster1_funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&cluster1_etm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				cluster1_funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&cluster1_etm1_out_port>;
+				};
+			};
+			port@3 {
+				reg = <2>;
+				cluster1_funnel_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&cluster1_etm2_out_port>;
+				};
+			};
+			port@4 {
+				reg = <3>;
+				cluster1_funnel_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&cluster1_etm3_out_port>;
+				};
+			};
+		};
+	};
+
+	etm3: etm@23140000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x23140000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		port {
+			cluster1_etm1_out_port: endpoint {
+				remote-endpoint = <&cluster1_funnel_in_port1>;
+			};
+		};
+	};
+
+	etm4: etm@23240000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x23240000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		port {
+			cluster1_etm2_out_port: endpoint {
+				remote-endpoint = <&cluster1_funnel_in_port2>;
+			};
+		};
+	};
+
+	etm5: etm@23340000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x23340000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		power-domains = <&scpi_devpd 0>;
+		port {
+			cluster1_etm3_out_port: endpoint {
+				remote-endpoint = <&cluster1_funnel_in_port3>;
+			};
+		};
+	};
+
+	coresight-replicator {
+		/*
+		 * Non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator_out_port0: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator_out_port1: endpoint {
+					remote-endpoint = <&etr_in_port>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&etf_out_port>;
+				};
+			};
+		};
+	};
+
 	sram: sram@2e000000 {
 		compatible = "arm,juno-sram-ns", "mmio-sram";
 		reg = <0x0 0x2e000000 0x0 0x8000>;
@@ -119,12 +428,60 @@
 			};
 		};
 
+		scpi_devpd: scpi-power-domains {
+			compatible = "arm,scpi-power-domains";
+			num-domains = <2>;
+			#power-domain-cells = <1>;
+		};
+
 		scpi_sensors0: sensors {
 			compatible = "arm,scpi-sensors";
 			#thermal-sensor-cells = <1>;
 		};
 	};
 
+	thermal-zones {
+		pmic {
+			polling-delay = <1000>;
+			polling-delay-passive = <100>;
+			thermal-sensors = <&scpi_sensors0 0>;
+		};
+
+		soc {
+			polling-delay = <1000>;
+			polling-delay-passive = <100>;
+			thermal-sensors = <&scpi_sensors0 3>;
+		};
+
+		big_cluster_thermal_zone: big_cluster {
+			polling-delay = <1000>;
+			polling-delay-passive = <100>;
+			thermal-sensors = <&scpi_sensors0 21>;
+			status = "disabled";
+		};
+
+		little_cluster_thermal_zone: little_cluster {
+			polling-delay = <1000>;
+			polling-delay-passive = <100>;
+			thermal-sensors = <&scpi_sensors0 22>;
+			status = "disabled";
+		};
+
+		gpu0_thermal_zone: gpu0 {
+			polling-delay = <1000>;
+			polling-delay-passive = <100>;
+			thermal-sensors = <&scpi_sensors0 23>;
+			status = "disabled";
+		};
+
+		gpu1_thermal_zone: gpu1 {
+			polling-delay = <1000>;
+			polling-delay-passive = <100>;
+			thermal-sensors = <&scpi_sensors0 24>;
+			status = "disabled";
+		};
+	};
+
 	/include/ "juno-clocks.dtsi"
 
 	dma@7ff00000 {
diff --git a/arch/arm64/boot/dts/arm/juno-r1.dts b/arch/arm64/boot/dts/arm/juno-r1.dts
index d95d9e7e2dc0..123a58b29cbd 100644
--- a/arch/arm64/boot/dts/arm/juno-r1.dts
+++ b/arch/arm64/boot/dts/arm/juno-r1.dts
@@ -181,3 +181,43 @@
 &pcie_ctlr {
 	status = "okay";
 };
+
+&etm0 {
+	cpu = <&A57_0>;
+};
+
+&etm1 {
+	cpu = <&A57_1>;
+};
+
+&etm2 {
+	cpu = <&A53_0>;
+};
+
+&etm3 {
+	cpu = <&A53_1>;
+};
+
+&etm4 {
+	cpu = <&A53_2>;
+};
+
+&etm5 {
+	cpu = <&A53_3>;
+};
+
+&big_cluster_thermal_zone {
+	status = "okay";
+};
+
+&little_cluster_thermal_zone {
+	status = "okay";
+};
+
+&gpu0_thermal_zone {
+	status = "okay";
+};
+
+&gpu1_thermal_zone {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/arm/juno-r2.dts b/arch/arm64/boot/dts/arm/juno-r2.dts
index 88ecd6182b67..007be826efce 100644
--- a/arch/arm64/boot/dts/arm/juno-r2.dts
+++ b/arch/arm64/boot/dts/arm/juno-r2.dts
@@ -181,3 +181,43 @@
 &pcie_ctlr {
 	status = "okay";
 };
+
+&etm0 {
+	cpu = <&A72_0>;
+};
+
+&etm1 {
+	cpu = <&A72_1>;
+};
+
+&etm2 {
+	cpu = <&A53_0>;
+};
+
+&etm3 {
+	cpu = <&A53_1>;
+};
+
+&etm4 {
+	cpu = <&A53_2>;
+};
+
+&etm5 {
+	cpu = <&A53_3>;
+};
+
+&big_cluster_thermal_zone {
+	status = "okay";
+};
+
+&little_cluster_thermal_zone {
+	status = "okay";
+};
+
+&gpu0_thermal_zone {
+	status = "okay";
+};
+
+&gpu1_thermal_zone {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts
index dcfcf15a17f5..a7270eff6939 100644
--- a/arch/arm64/boot/dts/arm/juno.dts
+++ b/arch/arm64/boot/dts/arm/juno.dts
@@ -173,3 +173,27 @@
 
 	#include "juno-base.dtsi"
 };
+
+&etm0 {
+	cpu = <&A57_0>;
+};
+
+&etm1 {
+	cpu = <&A57_1>;
+};
+
+&etm2 {
+	cpu = <&A53_0>;
+};
+
+&etm3 {
+	cpu = <&A53_1>;
+};
+
+&etm4 {
+	cpu = <&A53_2>;
+};
+
+&etm5 {
+	cpu = <&A53_3>;
+};
diff --git a/arch/arm64/boot/dts/broadcom/Makefile b/arch/arm64/boot/dts/broadcom/Makefile
index bec1f8b36f60..05faf2a8a35c 100644
--- a/arch/arm64/boot/dts/broadcom/Makefile
+++ b/arch/arm64/boot/dts/broadcom/Makefile
@@ -1,3 +1,4 @@
+dtb-$(CONFIG_ARCH_BCM2835) += bcm2837-rpi-3-b.dtb
 dtb-$(CONFIG_ARCH_BCM_IPROC) += ns2-svk.dtb
 dtb-$(CONFIG_ARCH_VULCAN) += vulcan-eval.dtb
 
diff --git a/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts b/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts
new file mode 100644
index 000000000000..6f47dd2bb1db
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/bcm2837-rpi-3-b.dts
@@ -0,0 +1,30 @@
+/dts-v1/;
+#include "bcm2837.dtsi"
+#include "../../../../arm/boot/dts/bcm2835-rpi.dtsi"
+#include "../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi"
+
+/ {
+	compatible = "raspberrypi,3-model-b", "brcm,bcm2837";
+	model = "Raspberry Pi 3 Model B";
+
+	memory {
+		reg = <0 0x40000000>;
+	};
+
+	leds {
+		act {
+			gpios = <&gpio 47 0>;
+		};
+
+		pwr {
+			label = "PWR";
+			gpios = <&gpio 35 0>;
+			default-state = "keep";
+			linux,default-trigger = "default-on";
+		};
+	};
+};
+
+&uart1 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/broadcom/bcm2837.dtsi b/arch/arm64/boot/dts/broadcom/bcm2837.dtsi
new file mode 100644
index 000000000000..f2a31d06845d
--- /dev/null
+++ b/arch/arm64/boot/dts/broadcom/bcm2837.dtsi
@@ -0,0 +1,76 @@
+#include "../../../../arm/boot/dts/bcm283x.dtsi"
+
+/ {
+	compatible = "brcm,bcm2836";
+
+	soc {
+		ranges = <0x7e000000 0x3f000000 0x1000000>,
+			 <0x40000000 0x40000000 0x00001000>;
+		dma-ranges = <0xc0000000 0x00000000 0x3f000000>;
+
+		local_intc: local_intc {
+			compatible = "brcm,bcm2836-l1-intc";
+			reg = <0x40000000 0x100>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&local_intc>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupt-parent = <&local_intc>;
+		interrupts = <0>, // PHYS_SECURE_PPI
+			     <1>, // PHYS_NONSECURE_PPI
+			     <3>, // VIRT_PPI
+			     <2>; // HYP_PPI
+		always-on;
+	};
+
+	cpus: cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			reg = <0>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x0 0x000000d8>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			reg = <1>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x0 0x000000e0>;
+		};
+
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			reg = <2>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x0 0x000000e8>;
+		};
+
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			reg = <3>;
+			enable-method = "spin-table";
+			cpu-release-addr = <0x0 0x000000f0>;
+		};
+	};
+};
+
+/* Make the BCM2835-style global interrupt controller be a child of the
+ * CPU-local interrupt controller.
+ */
+&intc {
+	compatible = "brcm,bcm2836-armctrl-ic";
+	reg = <0x7e00b200 0x200>;
+	interrupt-parent = <&local_intc>;
+	interrupts = <8>;
+};
diff --git a/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
index ea5603fd106a..2d7872a36b91 100644
--- a/arch/arm64/boot/dts/broadcom/ns2-svk.dts
+++ b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
@@ -40,10 +40,14 @@
 
 	aliases {
 		serial0 = &uart3;
+		serial1 = &uart0;
+		serial2 = &uart1;
+		serial3 = &uart2;
 	};
 
 	chosen {
 		stdout-path = "serial0:115200n8";
+		bootargs = "earlycon=uart8250,mmio32,0x66130000";
 	};
 
 	memory {
@@ -76,6 +80,18 @@
 	status = "ok";
 };
 
+&uart0 {
+	status = "ok";
+};
+
+&uart1 {
+	status = "ok";
+};
+
+&uart2 {
+	status = "ok";
+};
+
 &uart3 {
 	status = "ok";
 };
@@ -125,6 +141,18 @@
 	};
 };
 
+&sata_phy0 {
+	status = "ok";
+};
+
+&sata_phy1 {
+	status = "ok";
+};
+
+&sata {
+	status = "ok";
+};
+
 &sdio0 {
 	status = "ok";
 };
@@ -148,3 +176,12 @@
 		};
 	};
 };
+
+&pinctrl {
+	pinctrl-names = "default";
+	pinctrl-0 = <&nand_sel>;
+	nand_sel: nand_sel {
+		function = "nand";
+		groups = "nand_grp";
+	};
+};
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index 46b78fa89f4c..f53b0955bfd3 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -251,6 +251,22 @@
 			mmu-masters;
 		};
 
+		pinctrl: pinctrl@6501d130 {
+			compatible = "brcm,ns2-pinmux";
+			reg = <0x6501d130 0x08>,
+			      <0x660a0028 0x04>,
+			      <0x660009b0 0x40>;
+		};
+
+		gpio_aon: gpio@65024800 {
+			compatible = "brcm,iproc-gpio";
+			reg = <0x65024800 0x50>,
+			      <0x65024008 0x18>;
+			ngpios = <6>;
+			#gpio-cells = <2>;
+			gpio-controller;
+		};
+
 		gic: interrupt-controller@65210000 {
 			compatible = "arm,gic-400";
 			#interrupt-cells = <3>;
@@ -263,6 +279,26 @@
 				      IRQ_TYPE_LEVEL_HIGH)>;
 		};
 
+		cci@65590000 {
+			compatible = "arm,cci-400";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			reg = <0x65590000 0x1000>;
+			ranges = <0 0x65590000 0x10000>;
+
+			pmu@9000 {
+				compatible = "arm,cci-400-pmu,r1",
+					     "arm,cci-400-pmu";
+				reg = <0x9000 0x4000>;
+				interrupts = <GIC_SPI 344 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 345 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 346 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 348 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 349 IRQ_TYPE_LEVEL_HIGH>;
+			};
+		};
+
 		mdio_mux_iproc: mdio-mux@6602023c {
 			compatible = "brcm,mdio-mux-iproc";
 			reg = <0x6602023c 0x14>;
@@ -360,6 +396,16 @@
 			clock-names = "wdogclk", "apb_pclk";
 		};
 
+		gpio_g: gpio@660a0000 {
+			compatible = "brcm,iproc-gpio";
+			reg = <0x660a0000 0x50>;
+			ngpios = <32>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			interrupt-controller;
+			interrupts = <GIC_SPI 400 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
 		i2c1: i2c@660b0000 {
 			compatible = "brcm,iproc-i2c";
 			reg = <0x660b0000 0x100>;
@@ -370,6 +416,36 @@
 			status = "disabled";
 		};
 
+		uart0: serial@66100000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x66100000 0x100>;
+			interrupts = <GIC_SPI 390 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&iprocslow>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			status = "disabled";
+		};
+
+		uart1: serial@66110000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x66110000 0x100>;
+			interrupts = <GIC_SPI 391 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&iprocslow>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			status = "disabled";
+		};
+
+		uart2: serial@66120000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x66120000 0x100>;
+			interrupts = <GIC_SPI 392 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&iprocslow>;
+			reg-shift = <2>;
+			reg-io-width = <4>;
+			status = "disabled";
+		};
+
 		uart3: serial@66130000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x66130000 0x100>;
@@ -407,6 +483,49 @@
 			reg = <0x66220000 0x28>;
 		};
 
+		sata_phy: sata_phy@663f0100 {
+			compatible = "brcm,iproc-ns2-sata-phy";
+			reg = <0x663f0100 0x1f00>,
+			      <0x663f004c 0x10>;
+			reg-names = "phy", "phy-ctrl";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			sata_phy0: sata-phy@0 {
+				reg = <0>;
+				#phy-cells = <0>;
+				status = "disabled";
+			};
+
+			sata_phy1: sata-phy@1 {
+				reg = <1>;
+				#phy-cells = <0>;
+				status = "disabled";
+			};
+		};
+
+		sata: ahci@663f2000 {
+			compatible = "brcm,iproc-ahci", "generic-ahci";
+			reg = <0x663f2000 0x1000>;
+			reg-names = "ahci";
+			interrupts = <GIC_SPI 438 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+
+			sata0: sata-port@0 {
+				reg = <0>;
+				phys = <&sata_phy0>;
+				phy-names = "sata-phy";
+			};
+
+			sata1: sata-port@1 {
+				reg = <1>;
+				phys = <&sata_phy1>;
+				phy-names = "sata-phy";
+			};
+		};
+
 		sdio0: sdhci@66420000 {
 			compatible = "brcm,sdhci-iproc-cygnus";
 			reg = <0x66420000 0x100>;
diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
index d8767b00862e..299f3ce969ab 100644
--- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
+++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts
@@ -249,7 +249,7 @@
 
 			buck2_reg: BUCK2 {
 				regulator-name = "vdd_atlas";
-				regulator-min-microvolt = <1200000>;
+				regulator-min-microvolt = <500000>;
 				regulator-max-microvolt = <1200000>;
 				regulator-always-on;
 				regulator-boot-on;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index 6bd46c133010..e669fbd7f9c3 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -51,7 +51,7 @@
 	#size-cells = <2>;
 
 	cpus {
-		#address-cells = <2>;
+		#address-cells = <1>;
 		#size-cells = <0>;
 
 		/*
@@ -63,29 +63,37 @@
 		cpu0: cpu@0 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a53";
-			reg = <0x0 0x0>;
+			reg = <0x0>;
 			clocks = <&clockgen 1 0>;
+			next-level-cache = <&l2>;
 		};
 
 		cpu1: cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a53";
-			reg = <0x0 0x1>;
+			reg = <0x1>;
 			clocks = <&clockgen 1 0>;
+			next-level-cache = <&l2>;
 		};
 
 		cpu2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a53";
-			reg = <0x0 0x2>;
+			reg = <0x2>;
 			clocks = <&clockgen 1 0>;
+			next-level-cache = <&l2>;
 		};
 
 		cpu3: cpu@3 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a53";
-			reg = <0x0 0x3>;
+			reg = <0x3>;
 			clocks = <&clockgen 1 0>;
+			next-level-cache = <&l2>;
+		};
+
+		l2: l2-cache {
+			compatible = "cache";
 		};
 	};
 
@@ -465,6 +473,7 @@
 			interrupts = <0 60 0x4>;
 			dr_mode = "host";
 			snps,quirk-frame-length-adjustment = <0x20>;
+			snps,dis_rxdet_inp3_quirk;
 		};
 
 		usb1: usb3@3000000 {
@@ -473,6 +482,7 @@
 			interrupts = <0 61 0x4>;
 			dr_mode = "host";
 			snps,quirk-frame-length-adjustment = <0x20>;
+			snps,dis_rxdet_inp3_quirk;
 		};
 
 		usb2: usb3@3100000 {
@@ -481,6 +491,7 @@
 			interrupts = <0 63 0x4>;
 			dr_mode = "host";
 			snps,quirk-frame-length-adjustment = <0x20>;
+			snps,dis_rxdet_inp3_quirk;
 		};
 
 		sata: sata@3200000 {
@@ -522,6 +533,7 @@
 			#address-cells = <3>;
 			#size-cells = <2>;
 			device_type = "pci";
+			dma-coherent;
 			num-lanes = <4>;
 			bus-range = <0x0 0xff>;
 			ranges = <0x81000000 0x0 0x00000000 0x40 0x00010000 0x0 0x00010000   /* downstream I/O */
@@ -546,6 +558,7 @@
 			#address-cells = <3>;
 			#size-cells = <2>;
 			device_type = "pci";
+			dma-coherent;
 			num-lanes = <2>;
 			bus-range = <0x0 0xff>;
 			ranges = <0x81000000 0x0 0x00000000 0x48 0x00010000 0x0 0x00010000   /* downstream I/O */
@@ -570,6 +583,7 @@
 			#address-cells = <3>;
 			#size-cells = <2>;
 			device_type = "pci";
+			dma-coherent;
 			num-lanes = <2>;
 			bus-range = <0x0 0xff>;
 			ranges = <0x81000000 0x0 0x00000000 0x50 0x00010000 0x0 0x00010000   /* downstream I/O */
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
index 3187c822afa3..21023a388c29 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
@@ -51,7 +51,7 @@
 	#size-cells = <2>;
 
 	cpus {
-		#address-cells = <2>;
+		#address-cells = <1>;
 		#size-cells = <0>;
 
 		/*
@@ -65,57 +65,81 @@
 		cpu@0 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a57";
-			reg = <0x0 0x0>;
+			reg = <0x0>;
 			clocks = <&clockgen 1 0>;
+			next-level-cache = <&cluster0_l2>;
 		};
 
 		cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a57";
-			reg = <0x0 0x1>;
+			reg = <0x1>;
 			clocks = <&clockgen 1 0>;
+			next-level-cache = <&cluster0_l2>;
 		};
 
 		cpu@100 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a57";
-			reg = <0x0 0x100>;
+			reg = <0x100>;
 			clocks = <&clockgen 1 1>;
+			next-level-cache = <&cluster1_l2>;
 		};
 
 		cpu@101 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a57";
-			reg = <0x0 0x101>;
+			reg = <0x101>;
 			clocks = <&clockgen 1 1>;
+			next-level-cache = <&cluster1_l2>;
 		};
 
 		cpu@200 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a57";
-			reg = <0x0 0x200>;
+			reg = <0x200>;
 			clocks = <&clockgen 1 2>;
+			next-level-cache = <&cluster2_l2>;
 		};
 
 		cpu@201 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a57";
-			reg = <0x0 0x201>;
+			reg = <0x201>;
 			clocks = <&clockgen 1 2>;
+			next-level-cache = <&cluster2_l2>;
 		};
 
 		cpu@300 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a57";
-			reg = <0x0 0x300>;
+			reg = <0x300>;
 			clocks = <&clockgen 1 3>;
+			next-level-cache = <&cluster3_l2>;
 		};
 
 		cpu@301 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a57";
-			reg = <0x0 0x301>;
+			reg = <0x301>;
 			clocks = <&clockgen 1 3>;
+			next-level-cache = <&cluster3_l2>;
+		};
+
+		cluster0_l2: l2-cache0 {
+			compatible = "cache";
+		};
+
+		cluster1_l2: l2-cache1 {
+			compatible = "cache";
+		};
+
+		cluster2_l2: l2-cache2 {
+			compatible = "cache";
+		};
+
+		cluster3_l2: l2-cache3 {
+			compatible = "cache";
 		};
 	};
 
@@ -672,6 +696,7 @@
 			interrupts = <0 80 0x4>; /* Level high type */
 			dr_mode = "host";
 			snps,quirk-frame-length-adjustment = <0x20>;
+			snps,dis_rxdet_inp3_quirk;
 		};
 
 		usb1: usb3@3110000 {
@@ -681,6 +706,7 @@
 			interrupts = <0 81 0x4>; /* Level high type */
 			dr_mode = "host";
 			snps,quirk-frame-length-adjustment = <0x20>;
+			snps,dis_rxdet_inp3_quirk;
 		};
 
 		ccn@4000000 {
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index e92a30c87a82..593c7e43de79 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -66,6 +66,149 @@
 			status = "ok";
 		};
 
+		/*
+		 * Legend: proper name = the GPIO line is used as GPIO
+		 *         NC = not connected (not routed from the SoC)
+		 *         "[PER]" = pin is muxed for peripheral (not GPIO)
+		 *         "" = no idea, schematic doesn't say, could be
+		 *              unrouted (not connected to any external pin)
+		 *         LSEC = Low Speed External Connector
+		 *         HSEC = High Speed External Connector
+		 *
+		 * Pin assignments taken from LeMaker and CircuitCo Schematics
+		 * Rev A1.
+		 *
+		 * For the lines routed to the external connectors the
+		 * lines are named after the 96Boards CE Specification 1.0,
+		 * Appendix "Expansion Connector Signal Description".
+		 *
+		 * When the 96Board naming of a line and the schematic name of
+		 * the same line are in conflict, the 96Board specification
+		 * takes precedence, which means that the external UART on the
+		 * LSEC is named UART0 while the schematic and SoC names this
+		 * UART2. This is only for the informational lines i.e. "[FOO]",
+		 * the GPIO named lines "GPIO-A" thru "GPIO-L" are the only
+		 * ones actually used for GPIO.
+		 */
+		gpio0: gpio@f8011000 {
+			gpio-line-names = "PWR_HOLD", "DSI_SEL",
+			"USB_HUB_RESET_N", "USB_SEL", "HDMI_PD", "WL_REG_ON",
+			"PWRON_DET", "5V_HUB_EN";
+		};
+
+		gpio1: gpio@f8012000 {
+			gpio-line-names = "SD_DET", "HDMI_INT", "PMU_IRQ_N",
+			"WL_HOST_WAKE", "NC", "NC", "NC", "BT_REG_ON";
+		};
+
+		gpio2: gpio@f8013000 {
+			gpio-line-names =
+				"GPIO-A", /* LSEC Pin 23: GPIO2_0 */
+				"GPIO-B", /* LSEC Pin 24: GPIO2_1 */
+				"GPIO-C", /* LSEC Pin 25: GPIO2_2 */
+				"GPIO-D", /* LSEC Pin 26: GPIO2_3 */
+				"GPIO-E", /* LSEC Pin 27: GPIO2_4 */
+				"USB_ID_DET", "USB_VBUS_DET",
+				"GPIO-H"; /* LSEC Pin 30: GPIO2_7 */
+		};
+
+		gpio3: gpio@f8014000 {
+			gpio-line-names = "GPIO3_0", "NC", "NC", "", "NC", "",
+			"WLAN_ACTIVE", "NC", "NC";
+		};
+
+		gpio4: gpio@f7020000 {
+			gpio-line-names = "USER_LED1", "USER_LED2", "USER_LED3",
+			"USER_LED4", "SD_SEL", "NC", "NC", "BT_ACTIVE";
+		};
+
+		gpio5: gpio@f7021000 {
+			gpio-line-names = "NC", "NC",
+			"[UART1_RxD]", /* LSEC Pin 11: UART3_RX */
+			"[UART1_TxD]", /* LSEC Pin 13: UART3_TX */
+			"[AUX_SSI1]", "NC",
+			"[PCM_CLK]", /* LSEC Pin 18: MODEM_PCM_XCLK */
+			"[PCM_FS]"; /* LSEC Pin 16: MODEM_PCM_XFS */
+		};
+
+		gpio6: gpio@f7022000 {
+			gpio-line-names =
+			"[SPI0_DIN]", /* Pin 10: SPI0_DI */
+			"[SPI0_DOUT]", /* Pin 14: SPI0_DO */
+			"[SPI0_CS]", /* Pin 12: SPI0_CS_N */
+			"[SPI0_SCLK]", /* Pin 8: SPI0_SCLK */
+			"NC", "NC", "NC",
+			"GPIO-G"; /* Pin 29: GPIO6_7_DSI_TE0 */
+		};
+
+		gpio7: gpio@f7023000 {
+			gpio-line-names = "NC", "NC", "NC", "NC",
+			"[PCM_DI]", /* Pin 22: MODEM_PCM_DI */
+			"[PCM_DO]", /* Pin 20: MODEM_PCM_DO */
+			"NC", "NC";
+		};
+
+		gpio8: gpio@f7024000 {
+			gpio-line-names = "NC", "[CEC_CLK_19_2MHZ]", "NC",
+			"", "", "", "", "", "";
+		};
+
+		gpio9: gpio@f7025000 {
+			gpio-line-names = "",
+			"GPIO-J", /* LSEC Pin 32: ISP_PWDN0_GPIO9_1 */
+			"GPIO-L", /* LSEC Pin 34: ISP_PWDN1_GPIO9_2 */
+			"NC", "NC", "NC", "NC", "[ISP_CCLK0]";
+		};
+
+		gpio10: gpio@f7026000 {
+			gpio-line-names = "BOOT_SEL",
+			"[ISP_CCLK1]",
+			"GPIO-I", /* LSEC Pin 31: ISP_RSTB0_GPIO10_2 */
+			"GPIO-K", /* LSEC Pin 33: ISP_RSTB1_GPIO10_3 */
+			"NC", "NC",
+			"[I2C2_SDA]", /* HSEC Pin 34: ISP0_SDA */
+			"[I2C2_SCL]"; /* HSEC Pin 32: ISP0_SCL */
+		};
+
+		gpio11: gpio@f7027000 {
+			gpio-line-names =
+			"[I2C3_SDA]", /* HSEC Pin 38: ISP1_SDA */
+			"[I2C3_SCL]", /* HSEC Pin 36: ISP1_SCL */
+			"", "NC", "NC", "NC", "", "";
+		};
+
+		gpio12: gpio@f7028000 {
+			gpio-line-names = "[BT_PCM_XFS]", "[BT_PCM_DI]",
+			"[BT_PCM_DO]",
+			"NC", "NC", "NC", "NC",
+			"GPIO-F"; /* LSEC Pin 28: BL_PWM_GPIO12_7 */
+		};
+
+		gpio13: gpio@f7029000 {
+			gpio-line-names = "[UART0_RX]", "[UART0_TX]",
+			"[BT_UART1_CTS]", "[BT_UART1_RTS]",
+			"[BT_UART1_RX]", "[BT_UART1_TX]",
+			"[UART0_CTS]", /* LSEC Pin 3: UART2_CTS_N */
+			"[UART0_RTS]"; /* LSEC Pin 9: UART2_RTS_N */
+		};
+
+		gpio14: gpio@f702a000 {
+			gpio-line-names =
+			"[UART0_RxD]", /* LSEC Pin 7: UART2_RX */
+			"[UART0_TxD]", /* LSEC Pin 5: UART2_TX */
+			"[I2C0_SCL]", /* LSEC Pin 15: I2C0_SCL */
+			"[I2C0_SDA]", /* LSEC Pin 17: I2C0_SDA */
+			"[I2C1_SCL]", /* LSEC Pin 19: I2C1_SCL */
+			"[I2C1_SDA]", /* LSEC Pin 21: I2C1_SDA */
+			"[I2C2_SCL]", "[I2C2_SDA]";
+		};
+
+		gpio15: gpio@f702b000 {
+			gpio-line-names = "", "", "", "", "", "", "NC", "";
+		};
+
+		/* GPIO blocks 16 thru 19 do not appear to be routed to pins */
+
 		dwmmc_2: dwmmc2@f723f000 {
 			ti,non-removable;
 			non-removable;
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220.dtsi b/arch/arm64/boot/dts/hisilicon/hi6220.dtsi
index 189d21541f9c..4f270410a5cb 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hi6220.dtsi
@@ -5,6 +5,7 @@
  */
 
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/reset/hisi,hi6220-resets.h>
 #include <dt-bindings/clock/hi6220-clock.h>
 #include <dt-bindings/pinctrl/hisi.h>
 #include <dt-bindings/thermal/thermal.h>
@@ -252,6 +253,7 @@
 			compatible = "hisilicon,hi6220-mediactrl", "syscon";
 			reg = <0x0 0xf4410000 0x0 0x1000>;
 			#clock-cells = <1>;
+			#reset-cells = <1>;
 		};
 
 		pm_ctrl: pm_ctrl@f7032000 {
@@ -336,6 +338,22 @@
 			clock-names = "timer1", "timer2", "apb_pclk";
 		};
 
+		rtc0: rtc@f8003000 {
+			compatible = "arm,pl031", "arm,primecell";
+			reg = <0x0 0xf8003000 0x0 0x1000>;
+			interrupts = <0 12 4>;
+			clocks = <&ao_ctrl HI6220_RTC0_PCLK>;
+			clock-names = "apb_pclk";
+		};
+
+		rtc1: rtc@f8004000 {
+			compatible = "arm,pl031", "arm,primecell";
+			reg = <0x0 0xf8004000 0x0 0x1000>;
+			interrupts = <0 8 4>;
+			clocks = <&ao_ctrl HI6220_RTC1_PCLK>;
+			clock-names = "apb_pclk";
+		};
+
 		pmx0: pinmux@f7010000 {
 			compatible = "pinctrl-single";
 			reg = <0x0 0xf7010000  0x0 0x27c>;
diff --git a/arch/arm64/boot/dts/lg/Makefile b/arch/arm64/boot/dts/lg/Makefile
index b0cc64964171..5c7b54c12adc 100644
--- a/arch/arm64/boot/dts/lg/Makefile
+++ b/arch/arm64/boot/dts/lg/Makefile
@@ -1,4 +1,5 @@
 dtb-$(CONFIG_ARCH_LG1K) += lg1312-ref.dtb
+dtb-$(CONFIG_ARCH_LG1K) += lg1313-ref.dtb
 
 always		:= $(dtb-y)
 subdir-y	:= $(dts-dirs)
diff --git a/arch/arm64/boot/dts/lg/lg1313-ref.dts b/arch/arm64/boot/dts/lg/lg1313-ref.dts
new file mode 100644
index 000000000000..df0ece43cfbf
--- /dev/null
+++ b/arch/arm64/boot/dts/lg/lg1313-ref.dts
@@ -0,0 +1,36 @@
+/*
+ * dts file for lg1313 Reference Board.
+ *
+ * Copyright (C) 2016, LG Electronics
+ */
+
+/dts-v1/;
+
+#include "lg1313.dtsi"
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <1>;
+
+	model = "LG Electronics, DTV SoC LG1313 Reference Board";
+	compatible = "lge,lg1313-ref", "lge,lg1313";
+
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x0 0x00000000 0x20000000>;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/lg/lg1313.dtsi b/arch/arm64/boot/dts/lg/lg1313.dtsi
new file mode 100644
index 000000000000..e703e1149c75
--- /dev/null
+++ b/arch/arm64/boot/dts/lg/lg1313.dtsi
@@ -0,0 +1,351 @@
+/*
+ * dts file for lg1313 SoC
+ *
+ * Copyright (C) 2016, LG Electronics
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	compatible = "lge,lg1313";
+	interrupt-parent = <&gic>;
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x0>;
+			next-level-cache = <&L2_0>;
+		};
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+			next-level-cache = <&L2_0>;
+		};
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x2>;
+			enable-method = "psci";
+			next-level-cache = <&L2_0>;
+		};
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x3>;
+			enable-method = "psci";
+			next-level-cache = <&L2_0>;
+		};
+		L2_0: l2-cache0 {
+			compatible = "cache";
+		};
+	};
+
+	psci {
+		compatible  = "arm,psci-0.2", "arm,psci";
+		method = "smc";
+		cpu_suspend = <0x84000001>;
+		cpu_off = <0x84000002>;
+		cpu_on = <0x84000003>;
+	};
+
+	gic: interrupt-controller@c0001000 {
+		#interrupt-cells = <3>;
+		compatible = "arm,gic-400";
+		interrupt-controller;
+		reg = <0x0 0xc0001000 0x1000>,
+		      <0x0 0xc0002000 0x2000>,
+		      <0x0 0xc0004000 0x2000>,
+		      <0x0 0xc0006000 0x2000>;
+	};
+
+	pmu {
+		compatible = "arm,cortex-a53-pmu";
+		interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-affinity = <&cpu0>,
+				     <&cpu1>,
+				     <&cpu2>,
+				     <&cpu3>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_RAW(0x0f) |
+			      IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_RAW(0x0f) |
+			      IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_RAW(0x0f) |
+			      IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_RAW(0x0f) |
+			      IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	clk_bus: clk_bus {
+		#clock-cells = <0>;
+
+		compatible = "fixed-clock";
+		clock-frequency = <198000000>;
+		clock-output-names = "BUSCLK";
+	};
+
+	soc {
+		#address-cells = <2>;
+		#size-cells = <1>;
+
+		compatible = "simple-bus";
+		interrupt-parent = <&gic>;
+		ranges;
+
+		eth0: ethernet@c3700000 {
+			compatible = "cdns,gem";
+			reg = <0x0 0xc3700000 0x1000>;
+			interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_bus>, <&clk_bus>;
+			clock-names = "hclk", "pclk";
+			phy-mode = "rmii";
+			/* Filled in by boot */
+			mac-address = [ 00 00 00 00 00 00 ];
+		};
+	};
+
+	amba {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		#interrupts-cells = <3>;
+
+		compatible = "simple-bus";
+		interrupt-parent = <&gic>;
+		ranges;
+
+		timers: timer@fd100000 {
+			compatible = "arm,sp804";
+			reg = <0x0 0xfd100000 0x1000>;
+			interrupts = <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+		};
+		wdog: watchdog@fd200000 {
+			compatible = "arm,sp805", "arm,primecell";
+			reg = <0x0 0xfd200000 0x1000>;
+			interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+		};
+		uart0: serial@fe000000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x0 0xfe000000 0x1000>;
+			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		uart1: serial@fe100000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x0 0xfe100000 0x1000>;
+			interrupts = <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		uart2: serial@fe200000 {
+			compatible = "arm,pl011", "arm,primecell";
+			reg = <0x0 0xfe200000 0x1000>;
+			interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		spi0: ssp@fe800000 {
+			compatible = "arm,pl022", "arm,primecell";
+			reg = <0x0 0xfe800000 0x1000>;
+			interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+		};
+		spi1: ssp@fe900000 {
+			compatible = "arm,pl022", "arm,primecell";
+			reg = <0x0 0xfe900000 0x1000>;
+			interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+		};
+		dmac0: dma@c1128000 {
+			compatible = "arm,pl330", "arm,primecell";
+			reg = <0x0 0xc1128000 0x1000>;
+			interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+		};
+		gpio0: gpio@fd400000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd400000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio1: gpio@fd410000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd410000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio2: gpio@fd420000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd420000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio3: gpio@fd430000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd430000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+		};
+		gpio4: gpio@fd440000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd440000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio5: gpio@fd450000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd450000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio6: gpio@fd460000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd460000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio7: gpio@fd470000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd470000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio8: gpio@fd480000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd480000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio9: gpio@fd490000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd490000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio10: gpio@fd4a0000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd4a0000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio11: gpio@fd4b0000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd4b0000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+		};
+		gpio12: gpio@fd4c0000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd4c0000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio13: gpio@fd4d0000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd4d0000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio14: gpio@fd4e0000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd4e0000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio15: gpio@fd4f0000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd4f0000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio16: gpio@fd500000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd500000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+			status="disabled";
+		};
+		gpio17: gpio@fd510000 {
+			#gpio-cells = <2>;
+			compatible = "arm,pl061", "arm,primecell";
+			gpio-controller;
+			reg = <0x0 0xfd510000 0x1000>;
+			clocks = <&clk_bus>;
+			clock-names = "apb_pclk";
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-db.dts b/arch/arm64/boot/dts/marvell/armada-3720-db.dts
index 86110a6ae330..1372e9a6aaa4 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-db.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-db.dts
@@ -76,3 +76,8 @@
 &usb3 {
 	status = "okay";
 };
+
+/* CON17 (PCIe) / CON12 (mini-PCIe) */
+&pcie0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
index 9e2efb882983..c4762538ec01 100644
--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
@@ -105,6 +105,41 @@
 				status = "disabled";
 			};
 
+			nb_perih_clk: nb-periph-clk@13000{
+				compatible = "marvell,armada-3700-periph-clock-nb";
+				reg = <0x13000 0x100>;
+				clocks = <&tbg 0>, <&tbg 1>, <&tbg 2>,
+				<&tbg 3>, <&xtalclk>;
+				#clock-cells = <1>;
+			};
+
+			sb_perih_clk: sb-periph-clk@18000{
+				compatible = "marvell,armada-3700-periph-clock-sb";
+				reg = <0x18000 0x100>;
+				clocks = <&tbg 0>, <&tbg 1>, <&tbg 2>,
+				<&tbg 3>, <&xtalclk>;
+				#clock-cells = <1>;
+			};
+
+			tbg: tbg@13200 {
+				compatible = "marvell,armada-3700-tbg-clock";
+				reg = <0x13200 0x100>;
+				clocks = <&xtalclk>;
+				#clock-cells = <1>;
+			};
+
+			gpio1: gpio@13800 {
+				compatible = "marvell,mvebu-gpio-3700",
+				"syscon", "simple-mfd";
+				reg = <0x13800 0x500>;
+
+				xtalclk: xtal-clk {
+					compatible = "marvell,armada-3700-xtal-clock";
+					clock-output-names = "xtal";
+					#clock-cells = <0>;
+				};
+			};
+
 			usb3: usb@58000 {
 				compatible = "marvell,armada3700-xhci",
 				"generic-xhci";
@@ -141,5 +176,30 @@
 				      <0x1d40000 0x40000>; /* GICR */
 			};
 		};
+
+		pcie0: pcie@d0070000 {
+			compatible = "marvell,armada-3700-pcie";
+			device_type = "pci";
+			status = "disabled";
+			reg = <0 0xd0070000 0 0x20000>;
+			#address-cells = <3>;
+			#size-cells = <2>;
+			bus-range = <0x00 0xff>;
+			interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+			#interrupt-cells = <1>;
+			msi-parent = <&pcie0>;
+			msi-controller;
+			ranges = <0x82000000 0 0xe8000000   0 0xe8000000 0 0x1000000 /* Port 0 MEM */
+				  0x81000000 0 0xe9000000   0 0xe9000000 0 0x10000>; /* Port 0 IO*/
+			interrupt-map-mask = <0 0 0 7>;
+			interrupt-map = <0 0 0 1 &pcie_intc 0>,
+					<0 0 0 2 &pcie_intc 1>,
+					<0 0 0 3 &pcie_intc 2>,
+					<0 0 0 4 &pcie_intc 3>;
+			pcie_intc: interrupt-controller {
+				interrupt-controller;
+				#interrupt-cells = <1>;
+			};
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index 20d256b32670..eab1a42fb934 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -141,7 +141,7 @@
 			};
 
 			xor@400000 {
-				compatible = "marvell,mv-xor-v2";
+				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
 				reg = <0x400000 0x1000>,
 				      <0x410000 0x1000>;
 				msi-parent = <&gic_v2m0>;
@@ -149,7 +149,7 @@
 			};
 
 			xor@420000 {
-				compatible = "marvell,mv-xor-v2";
+				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
 				reg = <0x420000 0x1000>,
 				      <0x430000 0x1000>;
 				msi-parent = <&gic_v2m0>;
@@ -157,7 +157,7 @@
 			};
 
 			xor@440000 {
-				compatible = "marvell,mv-xor-v2";
+				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
 				reg = <0x440000 0x1000>,
 				      <0x450000 0x1000>;
 				msi-parent = <&gic_v2m0>;
@@ -165,7 +165,7 @@
 			};
 
 			xor@460000 {
-				compatible = "marvell,mv-xor-v2";
+				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
 				reg = <0x460000 0x1000>,
 				      <0x470000 0x1000>;
 				msi-parent = <&gic_v2m0>;
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index 367138bae3e0..da31bbbbb59e 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -107,6 +107,24 @@
 				status = "disabled";
 			};
 
+			cpm_xor0: xor@6a0000 {
+				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
+				reg = <0x6a0000 0x1000>,
+				      <0x6b0000 0x1000>;
+				dma-coherent;
+				msi-parent = <&gic_v2m0>;
+				clocks = <&cpm_syscon0 1 8>;
+			};
+
+			cpm_xor1: xor@6c0000 {
+				compatible = "marvell,armada-7k-xor", "marvell,xor-v2";
+				reg = <0x6c0000 0x1000>,
+				      <0x6d0000 0x1000>;
+				dma-coherent;
+				msi-parent = <&gic_v2m0>;
+				clocks = <&cpm_syscon0 1 7>;
+			};
+
 			cpm_spi0: spi@700600 {
 				compatible = "marvell,armada-380-spi";
 				reg = <0x700600 0x50>;
diff --git a/arch/arm64/boot/dts/mediatek/Makefile b/arch/arm64/boot/dts/mediatek/Makefile
index e0a4bff2fc17..9fbfd3238469 100644
--- a/arch/arm64/boot/dts/mediatek/Makefile
+++ b/arch/arm64/boot/dts/mediatek/Makefile
@@ -1,3 +1,4 @@
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt6755-evb.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt6795-evb.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8173-evb.dtb
 
diff --git a/arch/arm64/boot/dts/mediatek/mt6755-evb.dts b/arch/arm64/boot/dts/mediatek/mt6755-evb.dts
new file mode 100644
index 000000000000..c568d49235af
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt6755-evb.dts
@@ -0,0 +1,38 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Mars.C <mars.cheng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/dts-v1/;
+#include "mt6755.dtsi"
+
+/ {
+	model = "MediaTek MT6755 EVB";
+	compatible = "mediatek,mt6755-evb", "mediatek,mt6755";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0 0x40000000 0 0x1e800000>;
+	};
+
+	chosen {
+		stdout-path = "serial0:921600n8";
+	};
+};
+
+&uart0 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt6755.dtsi b/arch/arm64/boot/dts/mediatek/mt6755.dtsi
new file mode 100644
index 000000000000..01ba77669717
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt6755.dtsi
@@ -0,0 +1,145 @@
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Mars.C <mars.cheng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	compatible = "mediatek,mt6755";
+	interrupt-parent = <&sysirq>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x000>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x001>;
+		};
+
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x002>;
+		};
+
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x003>;
+		};
+
+		cpu4: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x100>;
+		};
+
+		cpu5: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x101>;
+		};
+
+		cpu6: cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x102>;
+		};
+
+		cpu7: cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			enable-method = "psci";
+			reg = <0x103>;
+		};
+	};
+
+	uart_clk: dummy26m {
+		compatible = "fixed-clock";
+		clock-frequency = <26000000>;
+		#clock-cells = <0>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_PPI 13
+			     (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14
+			     (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11
+			     (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10
+			     (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	sysirq: intpol-controller@10200620 {
+		compatible = "mediatek,mt6755-sysirq",
+			     "mediatek,mt6577-sysirq";
+		interrupt-controller;
+		#interrupt-cells = <3>;
+		interrupt-parent = <&gic>;
+		reg = <0 0x10200620 0 0x20>;
+	};
+
+	gic: interrupt-controller@10231000 {
+		compatible = "arm,gic-400";
+		#interrupt-cells = <3>;
+		interrupt-parent = <&gic>;
+		interrupt-controller;
+		reg = <0 0x10231000 0 0x1000>,
+		      <0 0x10232000 0 0x2000>,
+		      <0 0x10234000 0 0x2000>,
+		      <0 0x10236000 0 0x2000>;
+	};
+
+	uart0: serial@11002000 {
+		compatible = "mediatek,mt6755-uart",
+			     "mediatek,mt6577-uart";
+		reg = <0 0x11002000 0 0x400>;
+		interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&uart_clk>;
+		status = "disabled";
+	};
+
+	uart1: serial@11003000 {
+		compatible = "mediatek,mt6755-uart",
+			     "mediatek,mt6577-uart";
+		reg = <0 0x11003000 0 0x400>;
+		interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&uart_clk>;
+		status = "disabled";
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 77b8c4e388ca..10f638f4e7d8 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -26,6 +26,23 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
+	aliases {
+		ovl0 = &ovl0;
+		ovl1 = &ovl1;
+		rdma0 = &rdma0;
+		rdma1 = &rdma1;
+		rdma2 = &rdma2;
+		wdma0 = &wdma0;
+		wdma1 = &wdma1;
+		color0 = &color0;
+		color1 = &color1;
+		split0 = &split0;
+		split1 = &split1;
+		dpi0 = &dpi0;
+		dsi0 = &dsi0;
+		dsi1 = &dsi1;
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -366,6 +383,26 @@
 			#clock-cells = <1>;
 		};
 
+		mipi_tx0: mipi-dphy@10215000 {
+			compatible = "mediatek,mt8173-mipi-tx";
+			reg = <0 0x10215000 0 0x1000>;
+			clocks = <&clk26m>;
+			clock-output-names = "mipi_tx0_pll";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
+			status = "disabled";
+		};
+
+		mipi_tx1: mipi-dphy@10216000 {
+			compatible = "mediatek,mt8173-mipi-tx";
+			reg = <0 0x10216000 0 0x1000>;
+			clocks = <&clk26m>;
+			clock-output-names = "mipi_tx1_pll";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
+			status = "disabled";
+		};
+
 		gic: interrupt-controller@10220000 {
 			compatible = "arm,gic-400";
 			#interrupt-cells = <3>;
@@ -675,9 +712,181 @@
 		mmsys: clock-controller@14000000 {
 			compatible = "mediatek,mt8173-mmsys", "syscon";
 			reg = <0 0x14000000 0 0x1000>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
 			#clock-cells = <1>;
 		};
 
+		ovl0: ovl@1400c000 {
+			compatible = "mediatek,mt8173-disp-ovl";
+			reg = <0 0x1400c000 0 0x1000>;
+			interrupts = <GIC_SPI 180 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_OVL0>;
+			iommus = <&iommu M4U_PORT_DISP_OVL0>;
+			mediatek,larb = <&larb0>;
+		};
+
+		ovl1: ovl@1400d000 {
+			compatible = "mediatek,mt8173-disp-ovl";
+			reg = <0 0x1400d000 0 0x1000>;
+			interrupts = <GIC_SPI 181 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_OVL1>;
+			iommus = <&iommu M4U_PORT_DISP_OVL1>;
+			mediatek,larb = <&larb4>;
+		};
+
+		rdma0: rdma@1400e000 {
+			compatible = "mediatek,mt8173-disp-rdma";
+			reg = <0 0x1400e000 0 0x1000>;
+			interrupts = <GIC_SPI 182 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_RDMA0>;
+			iommus = <&iommu M4U_PORT_DISP_RDMA0>;
+			mediatek,larb = <&larb0>;
+		};
+
+		rdma1: rdma@1400f000 {
+			compatible = "mediatek,mt8173-disp-rdma";
+			reg = <0 0x1400f000 0 0x1000>;
+			interrupts = <GIC_SPI 183 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_RDMA1>;
+			iommus = <&iommu M4U_PORT_DISP_RDMA1>;
+			mediatek,larb = <&larb4>;
+		};
+
+		rdma2: rdma@14010000 {
+			compatible = "mediatek,mt8173-disp-rdma";
+			reg = <0 0x14010000 0 0x1000>;
+			interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_RDMA2>;
+			iommus = <&iommu M4U_PORT_DISP_RDMA2>;
+			mediatek,larb = <&larb4>;
+		};
+
+		wdma0: wdma@14011000 {
+			compatible = "mediatek,mt8173-disp-wdma";
+			reg = <0 0x14011000 0 0x1000>;
+			interrupts = <GIC_SPI 185 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_WDMA0>;
+			iommus = <&iommu M4U_PORT_DISP_WDMA0>;
+			mediatek,larb = <&larb0>;
+		};
+
+		wdma1: wdma@14012000 {
+			compatible = "mediatek,mt8173-disp-wdma";
+			reg = <0 0x14012000 0 0x1000>;
+			interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_WDMA1>;
+			iommus = <&iommu M4U_PORT_DISP_WDMA1>;
+			mediatek,larb = <&larb4>;
+		};
+
+		color0: color@14013000 {
+			compatible = "mediatek,mt8173-disp-color";
+			reg = <0 0x14013000 0 0x1000>;
+			interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_COLOR0>;
+		};
+
+		color1: color@14014000 {
+			compatible = "mediatek,mt8173-disp-color";
+			reg = <0 0x14014000 0 0x1000>;
+			interrupts = <GIC_SPI 188 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_COLOR1>;
+		};
+
+		aal@14015000 {
+			compatible = "mediatek,mt8173-disp-aal";
+			reg = <0 0x14015000 0 0x1000>;
+			interrupts = <GIC_SPI 189 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_AAL>;
+		};
+
+		gamma@14016000 {
+			compatible = "mediatek,mt8173-disp-gamma";
+			reg = <0 0x14016000 0 0x1000>;
+			interrupts = <GIC_SPI 190 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_GAMMA>;
+		};
+
+		merge@14017000 {
+			compatible = "mediatek,mt8173-disp-merge";
+			reg = <0 0x14017000 0 0x1000>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_MERGE>;
+		};
+
+		split0: split@14018000 {
+			compatible = "mediatek,mt8173-disp-split";
+			reg = <0 0x14018000 0 0x1000>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_SPLIT0>;
+		};
+
+		split1: split@14019000 {
+			compatible = "mediatek,mt8173-disp-split";
+			reg = <0 0x14019000 0 0x1000>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_SPLIT1>;
+		};
+
+		ufoe@1401a000 {
+			compatible = "mediatek,mt8173-disp-ufoe";
+			reg = <0 0x1401a000 0 0x1000>;
+			interrupts = <GIC_SPI 191 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DISP_UFOE>;
+		};
+
+		dsi0: dsi@1401b000 {
+			compatible = "mediatek,mt8173-dsi";
+			reg = <0 0x1401b000 0 0x1000>;
+			interrupts = <GIC_SPI 192 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DSI0_ENGINE>,
+				 <&mmsys CLK_MM_DSI0_DIGITAL>,
+				 <&mipi_tx0>;
+			clock-names = "engine", "digital", "hs";
+			phys = <&mipi_tx0>;
+			phy-names = "dphy";
+			status = "disabled";
+		};
+
+		dsi1: dsi@1401c000 {
+			compatible = "mediatek,mt8173-dsi";
+			reg = <0 0x1401c000 0 0x1000>;
+			interrupts = <GIC_SPI 193 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DSI1_ENGINE>,
+				 <&mmsys CLK_MM_DSI1_DIGITAL>,
+				 <&mipi_tx1>;
+			clock-names = "engine", "digital", "hs";
+			phy = <&mipi_tx1>;
+			phy-names = "dphy";
+			status = "disabled";
+		};
+
+		dpi0: dpi@1401d000 {
+			compatible = "mediatek,mt8173-dpi";
+			reg = <0 0x1401d000 0 0x1000>;
+			interrupts = <GIC_SPI 194 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_DPI_PIXEL>,
+				 <&mmsys CLK_MM_DPI_ENGINE>,
+				 <&apmixedsys CLK_APMIXED_TVDPLL>;
+			clock-names = "pixel", "engine", "pll";
+			status = "disabled";
+		};
+
 		pwm0: pwm@1401e000 {
 			compatible = "mediatek,mt8173-disp-pwm",
 				     "mediatek,mt6595-disp-pwm";
@@ -700,6 +909,14 @@
 			status = "disabled";
 		};
 
+		mutex: mutex@14020000 {
+			compatible = "mediatek,mt8173-disp-mutex";
+			reg = <0 0x14020000 0 0x1000>;
+			interrupts = <GIC_SPI 169 IRQ_TYPE_LEVEL_LOW>;
+			power-domains = <&scpsys MT8173_POWER_DOMAIN_MM>;
+			clocks = <&mmsys CLK_MM_MUTEX_32K>;
+		};
+
 		larb0: larb@14021000 {
 			compatible = "mediatek,mt8173-smi-larb";
 			reg = <0 0x14021000 0 0x1000>;
@@ -719,6 +936,12 @@
 			clock-names = "apb", "smi";
 		};
 
+		od@14023000 {
+			compatible = "mediatek,mt8173-disp-od";
+			reg = <0 0x14023000 0 0x1000>;
+			clocks = <&mmsys CLK_MM_DISP_OD>;
+		};
+
 		larb4: larb@14027000 {
 			compatible = "mediatek,mt8173-smi-larb";
 			reg = <0 0x14027000 0 0x1000>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi
index 316c92c03821..5fda583351d7 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi
@@ -1,3 +1,5 @@
+#include <dt-bindings/mfd/max77620.h>
+
 #include "tegra210.dtsi"
 
 / {
@@ -5,10 +7,15 @@
 	compatible = "nvidia,p2180", "nvidia,tegra210";
 
 	aliases {
+		rtc0 = "/i2c@7000d000/pmic@3c";
 		rtc1 = "/rtc@7000e000";
 		serial0 = &uarta;
 	};
 
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
 	memory {
 		device_type = "memory";
 		reg = <0x0 0x80000000 0x1 0x0>;
@@ -19,6 +26,248 @@
 		status = "okay";
 	};
 
+	i2c@7000d000 {
+		status = "okay";
+		clock-frequency = <400000>;
+
+		pmic: pmic@3c {
+			compatible = "maxim,max77620";
+			reg = <0x3c>;
+			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+
+			#interrupt-cells = <2>;
+			interrupt-controller;
+
+			#gpio-cells = <2>;
+			gpio-controller;
+
+			pinctrl-names = "default";
+			pinctrl-0 = <&max77620_default>;
+
+			max77620_default: pinmux {
+				gpio0 {
+					pins = "gpio0";
+					function = "gpio";
+				};
+
+				gpio1 {
+					pins = "gpio1";
+					function = "fps-out";
+					drive-push-pull = <1>;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+					maxim,active-fps-power-up-slot = <7>;
+					maxim,active-fps-power-down-slot = <0>;
+				};
+
+				gpio2_3 {
+					pins = "gpio2", "gpio3";
+					function = "fps-out";
+					drive-open-drain = <1>;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+				};
+
+				gpio4 {
+					pins = "gpio4";
+					function = "32k-out1";
+				};
+
+				gpio5_6_7 {
+					pins = "gpio5", "gpio6", "gpio7";
+					function = "gpio";
+					drive-push-pull = <1>;
+				};
+			};
+
+			fps {
+				fps0 {
+					maxim,fps-event-source = <MAX77620_FPS_EVENT_SRC_EN0>;
+					maxim,suspend-fps-time-period-us = <1280>;
+				};
+
+				fps1 {
+					maxim,fps-event-source = <MAX77620_FPS_EVENT_SRC_EN1>;
+					maxim,suspend-fps-time-period-us = <1280>;
+				};
+
+				fps2 {
+					maxim,fps-event-source = <MAX77620_FPS_EVENT_SRC_EN0>;
+				};
+			};
+
+			regulators {
+				in-ldo0-1-supply = <&vdd_pre>;
+				in-ldo7-8-supply = <&vdd_pre>;
+				in-sd3-supply = <&vdd_5v0_sys>;
+
+				vdd_soc: sd0 {
+					regulator-name = "VDD_SOC";
+					regulator-min-microvolt = <600000>;
+					regulator-max-microvolt = <1400000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					regulator-enable-ramp-delay = <146>;
+					regulator-ramp-delay = <27500>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
+				};
+
+				vdd_ddr: sd1 {
+					regulator-name = "VDD_DDR_1V1_PMIC";
+					regulator-always-on;
+					regulator-boot-on;
+
+					regulator-enable-ramp-delay = <130>;
+					regulator-ramp-delay = <27500>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+				};
+
+				vdd_pre: sd2 {
+					regulator-name = "VDD_PRE_REG_1V35";
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
+
+					regulator-enable-ramp-delay = <176>;
+					regulator-ramp-delay = <27500>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
+				};
+
+				vdd_1v8: sd3 {
+					regulator-name = "VDD_1V8";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					regulator-enable-ramp-delay = <242>;
+					regulator-ramp-delay = <27500>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+				};
+
+				vdd_sys_1v2: ldo0 {
+					regulator-name = "AVDD_SYS_1V2";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					regulator-enable-ramp-delay = <26>;
+					regulator-ramp-delay = <100000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				vdd_pex_1v05: ldo1 {
+					regulator-name = "VDD_PEX_1V05";
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1050000>;
+
+					regulator-enable-ramp-delay = <22>;
+					regulator-ramp-delay = <100000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
+				};
+
+				vddio_sdmmc: ldo2 {
+					regulator-name = "VDDIO_SDMMC";
+					/*
+					 * Technically this supply should have
+					 * a supported range from 1.8 - 3.3 V.
+					 * However, that would cause the SDHCI
+					 * driver to request 2.7 V upon access
+					 * and that in turn will cause traffic
+					 * to be broken. Leave it at 3.3 V for
+					 * now.
+					 */
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					regulator-enable-ramp-delay = <62>;
+					regulator-ramp-delay = <100000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				vdd_cam_hv: ldo3 {
+					regulator-name = "VDD_CAM_HV";
+					regulator-min-microvolt = <2800000>;
+					regulator-max-microvolt = <2800000>;
+
+					regulator-enable-ramp-delay = <50>;
+					regulator-ramp-delay = <100000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				vdd_rtc: ldo4 {
+					regulator-name = "VDD_RTC";
+					regulator-min-microvolt = <850000>;
+					regulator-max-microvolt = <850000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					regulator-enable-ramp-delay = <22>;
+					regulator-ramp-delay = <100000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+				};
+
+				vdd_ts_hv: ldo5 {
+					regulator-name = "VDD_TS_HV";
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
+
+					regulator-enable-ramp-delay = <62>;
+					regulator-ramp-delay = <100000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				vdd_ts: ldo6 {
+					regulator-name = "VDD_TS_1V8";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+
+					regulator-enable-ramp-delay = <36>;
+					regulator-ramp-delay = <100000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+					maxim,active-fps-power-up-slot = <7>;
+					maxim,active-fps-power-down-slot = <0>;
+				};
+
+				avdd_1v05_pll: ldo7 {
+					regulator-name = "AVDD_1V05_PLL";
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1050000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					regulator-enable-ramp-delay = <24>;
+					regulator-ramp-delay = <100000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
+				};
+
+				avdd_1v05: ldo8 {
+					regulator-name = "AVDD_SATA_HDMI_DP_1V05";
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1050000>;
+
+					regulator-enable-ramp-delay = <22>;
+					regulator-ramp-delay = <100000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
+				};
+			};
+		};
+	};
+
 	pmc@7000e400 {
 		nvidia,invert-interrupt;
 	};
diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2371-2180.dts b/arch/arm64/boot/dts/nvidia/tegra210-p2371-2180.dts
index 683b339a980c..983775e637a4 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210-p2371-2180.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra210-p2371-2180.dts
@@ -6,4 +6,49 @@
 / {
 	model = "NVIDIA Jetson TX1 Developer Kit";
 	compatible = "nvidia,p2371-2180", "nvidia,tegra210";
+
+	host1x@50000000 {
+		dsi@54300000 {
+			status = "okay";
+
+			avdd-dsi-csi-supply = <&vdd_dsi_csi>;
+
+			panel@0 {
+				compatible = "auo,b080uan01";
+				reg = <0>;
+
+				enable-gpios = <&gpio TEGRA_GPIO(V, 2)
+						GPIO_ACTIVE_HIGH>;
+				power-supply = <&vdd_5v0_io>;
+				backlight = <&backlight>;
+			};
+		};
+	};
+
+	i2c@7000c400 {
+		backlight: backlight@2c {
+			compatible = "ti,lp8557";
+			reg = <0x2c>;
+
+			dev-ctrl = /bits/ 8 <0x80>;
+			init-brt = /bits/ 8 <0xff>;
+
+			pwm-period = <29334>;
+
+			pwms = <&pwm 0 29334>;
+			pwm-names = "lp8557";
+
+			/* 3 LED string */
+			rom_14h {
+				rom-addr = /bits/ 8 <0x14>;
+				rom-val = /bits/ 8 <0x87>;
+			};
+
+			/* boost frequency 1 MHz */
+			rom_13h {
+				rom-addr = /bits/ 8 <0x13>;
+				rom-val = /bits/ 8 <0x01>;
+			};
+		};
+	};
 };
diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi
index a2480c0c7e72..e5fc67bf46c2 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi
@@ -4,6 +4,24 @@
 	model = "NVIDIA Tegra210 P2597 I/O board";
 	compatible = "nvidia,p2597", "nvidia,tegra210";
 
+	host1x@50000000 {
+		dpaux@54040000 {
+			status = "okay";
+		};
+
+		sor@54580000 {
+			status = "okay";
+
+			avdd-io-supply = <&avdd_1v05>;
+			vdd-pll-supply = <&vdd_1v8>;
+			hdmi-supply = <&vdd_hdmi>;
+
+			nvidia,ddc-i2c-bus = <&hdmi_ddc>;
+			nvidia,hpd-gpio = <&gpio TEGRA_GPIO(CC, 1)
+					   GPIO_ACTIVE_LOW>;
+		};
+	};
+
 	pinmux: pinmux@700008d4 {
 		pinctrl-names = "boot";
 		pinctrl-0 = <&state_boot>;
@@ -1261,6 +1279,169 @@
 		};
 	};
 
+	pwm@7000a000 {
+		status = "okay";
+	};
+
+	i2c@7000c400 {
+		status = "okay";
+		clock-frequency = <100000>;
+
+		exp1: gpio@74 {
+			compatible = "ti,tca9539";
+			reg = <0x74>;
+
+			#gpio-cells = <2>;
+			gpio-controller;
+		};
+	};
+
+	/* HDMI DDC */
+	hdmi_ddc: i2c@7000c700 {
+		status = "okay";
+		clock-frequency = <100000>;
+	};
+
+	usb@70090000 {
+		phys = <&{/padctl@7009f000/pads/usb2/lanes/usb2-0}>,
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-1}>,
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-2}>,
+		       <&{/padctl@7009f000/pads/usb2/lanes/usb2-3}>,
+		       <&{/padctl@7009f000/pads/pcie/lanes/pcie-6}>,
+		       <&{/padctl@7009f000/pads/pcie/lanes/pcie-5}>;
+		phy-names = "usb2-0", "usb2-1", "usb2-2", "usb2-3", "usb3-0",
+			    "usb3-1";
+
+		dvddio-pex-supply = <&vdd_pex_1v05>;
+		hvddio-pex-supply = <&vdd_1v8>;
+		avdd-usb-supply = <&vdd_3v3_sys>;
+		/* XXX what are these? */
+		avdd-pll-utmip-supply = <&vdd_1v8>;
+		avdd-pll-uerefe-supply = <&vdd_pex_1v05>;
+		dvdd-usb-ss-pll-supply = <&vdd_pex_1v05>;
+		hvdd-usb-ss-pll-e-supply = <&vdd_1v8>;
+
+		status = "okay";
+	};
+
+	padctl@7009f000 {
+		status = "okay";
+
+		pads {
+			usb2 {
+				status = "okay";
+
+				lanes {
+					usb2-0 {
+						nvidia,function = "xusb";
+						status = "okay";
+					};
+
+					usb2-1 {
+						nvidia,function = "xusb";
+						status = "okay";
+					};
+
+					usb2-2 {
+						nvidia,function = "xusb";
+						status = "okay";
+					};
+
+					usb2-3 {
+						nvidia,function = "xusb";
+						status = "okay";
+					};
+				};
+			};
+
+			pcie {
+				status = "okay";
+
+				lanes {
+					pcie-0 {
+						nvidia,function = "pcie-x1";
+						status = "okay";
+					};
+
+					pcie-1 {
+						nvidia,function = "pcie-x4";
+						status = "okay";
+					};
+
+					pcie-2 {
+						nvidia,function = "pcie-x4";
+						status = "okay";
+					};
+
+					pcie-3 {
+						nvidia,function = "pcie-x4";
+						status = "okay";
+					};
+
+					pcie-4 {
+						nvidia,function = "pcie-x4";
+						status = "okay";
+					};
+
+					pcie-5 {
+						nvidia,function = "usb3-ss";
+						status = "okay";
+					};
+
+					pcie-6 {
+						nvidia,function = "usb3-ss";
+						status = "okay";
+					};
+				};
+			};
+
+			sata {
+				status = "okay";
+
+				lanes {
+					sata-0 {
+						nvidia,function = "sata";
+						status = "okay";
+					};
+				};
+			};
+		};
+
+		ports {
+			usb2-0 {
+				status = "okay";
+				mode = "otg";
+			};
+
+			usb2-1 {
+				status = "okay";
+				vbus-supply = <&vdd_5v0_rtl>;
+				mode = "host";
+			};
+
+			usb2-2 {
+				status = "okay";
+				vbus-supply = <&vdd_usb_vbus>;
+				mode = "host";
+			};
+
+			usb2-3 {
+				status = "okay";
+				mode = "host";
+			};
+
+			usb3-0 {
+				nvidia,usb2-companion = <1>;
+				status = "okay";
+			};
+
+			usb3-1 {
+				nvidia,usb2-companion = <2>;
+				status = "okay";
+			};
+		};
+	};
+
 	/* MMC/SD */
 	sdhci@700b0000 {
 		status = "okay";
@@ -1268,6 +1449,144 @@
 		no-1-8-v;
 
 		cd-gpios = <&gpio TEGRA_GPIO(Z, 1) GPIO_ACTIVE_LOW>;
+
+		vqmmc-supply = <&vddio_sdmmc>;
+		vmmc-supply = <&vdd_3v3_sd>;
+	};
+
+	regulators {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		vdd_sys_mux: regulator@0 {
+			compatible = "regulator-fixed";
+			reg = <0>;
+			regulator-name = "VDD_SYS_MUX";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			regulator-always-on;
+			regulator-boot-on;
+		};
+
+		vdd_5v0_sys: regulator@1 {
+			compatible = "regulator-fixed";
+			reg = <1>;
+			regulator-name = "VDD_5V0_SYS";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&pmic 1 GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+			vin-supply = <&vdd_sys_mux>;
+		};
+
+		vdd_3v3_sys: regulator@2 {
+			compatible = "regulator-fixed";
+			reg = <2>;
+			regulator-name = "VDD_3V3_SYS";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+			regulator-boot-on;
+			gpio = <&pmic 3 GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+			vin-supply = <&vdd_sys_mux>;
+
+			regulator-enable-ramp-delay = <160>;
+			regulator-disable-ramp-delay = <10000>;
+		};
+
+		vdd_5v0_io: regulator@3 {
+			compatible = "regulator-fixed";
+			reg = <3>;
+			regulator-name = "VDD_5V0_IO_SYS";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			regulator-always-on;
+			regulator-boot-on;
+		};
+
+		vdd_3v3_sd: regulator@4 {
+			compatible = "regulator-fixed";
+			reg = <4>;
+			regulator-name = "VDD_3V3_SD";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			gpio = <&gpio TEGRA_GPIO(Z, 4) GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+			vin-supply = <&vdd_3v3_sys>;
+
+			regulator-enable-ramp-delay = <472>;
+			regulator-disable-ramp-delay = <4880>;
+		};
+
+		vdd_dsi_csi: regulator@5 {
+			compatible = "regulator-fixed";
+			reg = <5>;
+			regulator-name = "AVDD_DSI_CSI_1V2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			vin-supply = <&vdd_sys_1v2>;
+		};
+
+		vdd_3v3_dis: regulator@6 {
+			compatible = "regulator-fixed";
+			reg = <6>;
+			regulator-name = "VDD_DIS_3V3_LCD";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+			gpio = <&exp1 3 GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+			vin-supply = <&vdd_3v3_sys>;
+		};
+
+		vdd_1v8_dis: regulator@7 {
+			compatible = "regulator-fixed";
+			reg = <7>;
+			regulator-name = "VDD_LCD_1V8_DIS";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-always-on;
+			gpio = <&exp1 14 GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+			vin-supply = <&vdd_1v8>;
+		};
+
+		vdd_5v0_rtl: regulator@8 {
+			compatible = "regulator-fixed";
+			reg = <8>;
+			regulator-name = "RTL_5V";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			gpio = <&gpio TEGRA_GPIO(H, 1) GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+			vin-supply = <&vdd_5v0_sys>;
+		};
+
+		vdd_usb_vbus: regulator@9 {
+			compatible = "regulator-fixed";
+			reg = <9>;
+			regulator-name = "USB_VBUS_EN1";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			gpio = <&gpio TEGRA_GPIO(CC, 5) GPIO_ACTIVE_HIGH>;
+			enable-active-high;
+			vin-supply = <&vdd_5v0_sys>;
+		};
+
+		vdd_hdmi: regulator@10 {
+			compatible = "regulator-fixed";
+			reg = <10>;
+			regulator-name = "VDD_HDMI_5V0";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			gpio = <&exp1 12 GPIO_ACTIVE_LOW>;
+			enable-active-high;
+			vin-supply = <&vdd_5v0_sys>;
+		};
 	};
 
 	gpio-keys {
diff --git a/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts b/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts
index 4d89f4e02d98..431266a48e9c 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts
@@ -1,6 +1,7 @@
 /dts-v1/;
 
 #include <dt-bindings/input/input.h>
+#include <dt-bindings/mfd/max77620.h>
 #include <dt-bindings/pinctrl/pinctrl-tegra.h>
 
 #include "tegra210.dtsi"
@@ -1327,6 +1328,234 @@
 		};
 	};
 
+	i2c@7000d000 {
+		status = "okay";
+		clock-frequency = <1000000>;
+
+		max77620: max77620@3c {
+			compatible = "maxim,max77620";
+			reg = <0x3c>;
+			interrupts = <0 86 IRQ_TYPE_NONE>;
+
+			#interrupt-cells = <2>;
+			interrupt-controller;
+
+			gpio-controller;
+			#gpio-cells = <2>;
+
+			pinctrl-names = "default";
+			pinctrl-0 = <&max77620_default>;
+
+			max77620_default: pinmux@0 {
+				pin_gpio {
+					pins = "gpio0", "gpio1", "gpio2", "gpio7";
+					function = "gpio";
+				};
+
+				/*
+				 * GPIO3 is used to en_pp3300, and it is part of power
+				 * sequence, So it must be sequenced up (automatically
+				 * set by OTP) and down properly.
+				 */
+				pin_gpio3 {
+					pins = "gpio3";
+					function = "fps-out";
+					drive-open-drain = <1>;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+					maxim,active-fps-power-up-slot = <4>;
+					maxim,active-fps-power-down-slot = <2>;
+				};
+
+				pin_gpio5_6 {
+					pins = "gpio5", "gpio6";
+					function = "gpio";
+					drive-push-pull = <1>;
+				};
+
+				pin_32k {
+					pins = "gpio4";
+					function = "32k-out1";
+				};
+			};
+
+			fps {
+				fps0 {
+					maxim,shutdown-fps-time-period-us = <5120>;
+					maxim,fps-event-source = <MAX77620_FPS_EVENT_SRC_EN0>;
+				};
+
+				fps1 {
+					maxim,shutdown-fps-time-period-us = <5120>;
+					maxim,fps-event-source = <MAX77620_FPS_EVENT_SRC_EN1>;
+					maxim,device-state-on-disabled-event = <MAX77620_FPS_INACTIVE_STATE_SLEEP>;
+				};
+
+				fps2 {
+					maxim,fps-event-source = <MAX77620_FPS_EVENT_SRC_EN0>;
+				};
+			};
+
+			regulators {
+				in-ldo0-1-supply = <&pp1350>;
+				in-ldo2-supply = <&pp3300>;
+				in-ldo3-5-supply = <&pp3300>;
+				in-ldo7-8-supply = <&pp1350>;
+
+				ppvar_soc: sd0 {
+					regulator-name = "PPVAR_SOC";
+					regulator-min-microvolt = <825000>;
+					regulator-max-microvolt = <1125000>;
+					regulator-always-on;
+					regulator-boot-on;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
+					maxim,active-fps-power-up-slot = <1>;
+					maxim,active-fps-power-down-slot = <7>;
+				};
+
+				pp1100_sd1: sd1 {
+					regulator-name = "PP1100";
+					regulator-min-microvolt = <1125000>;
+					regulator-max-microvolt = <1125000>;
+					regulator-always-on;
+					regulator-boot-on;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+					maxim,active-fps-power-up-slot = <5>;
+					maxim,active-fps-power-down-slot = <1>;
+				};
+
+				pp1350: sd2 {
+					regulator-name = "PP1350";
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
+					regulator-always-on;
+					regulator-boot-on;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+					maxim,active-fps-power-up-slot = <2>;
+					maxim,active-fps-power-down-slot = <5>;
+				};
+
+				pp1800: sd3 {
+					regulator-name = "PP1800";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
+					regulator-boot-on;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+					maxim,active-fps-power-up-slot = <3>;
+					maxim,active-fps-power-down-slot = <3>;
+				};
+
+				pp1200_avdd: ldo0 {
+					regulator-name = "PP1200_AVDD";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-enable-ramp-delay = <26>;
+					regulator-ramp-delay = <100000>;
+					regulator-boot-on;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+					maxim,active-fps-power-up-slot = <0>;
+					maxim,active-fps-power-down-slot = <7>;
+				};
+
+				pp1200_rcam: ldo1 {
+					regulator-name = "PP1200_RCAM";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-enable-ramp-delay = <22>;
+					regulator-ramp-delay = <100000>;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+					maxim,active-fps-power-up-slot = <0>;
+					maxim,active-fps-power-down-slot = <7>;
+				};
+
+				pp_ldo2: ldo2 {
+					regulator-name = "PP_LDO2";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-enable-ramp-delay = <62>;
+					regulator-ramp-delay = <11000>;
+					regulator-always-on;
+					regulator-boot-on;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+					maxim,active-fps-power-up-slot = <0>;
+					maxim,active-fps-power-down-slot = <7>;
+				};
+
+				pp2800l_rcam: ldo3 {
+					regulator-name = "PP2800L_RCAM";
+					regulator-min-microvolt = <2800000>;
+					regulator-max-microvolt = <2800000>;
+					regulator-enable-ramp-delay = <50>;
+					regulator-ramp-delay = <100000>;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+					maxim,active-fps-power-up-slot = <0>;
+					maxim,active-fps-power-down-slot = <7>;
+				};
+
+				pp100_soc_rtc: ldo4 {
+					regulator-name = "PP1100_SOC_RTC";
+					regulator-min-microvolt = <850000>;
+					regulator-max-microvolt = <850000>;
+					regulator-enable-ramp-delay = <22>;
+					regulator-ramp-delay = <100000>;
+					regulator-always-on; /* Check this */
+					regulator-boot-on;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+					maxim,active-fps-power-up-slot = <1>;
+					maxim,active-fps-power-down-slot = <7>;
+				};
+
+				pp2800l_fcam: ldo5 {
+					regulator-name = "PP2800L_FCAM";
+					regulator-min-microvolt = <2800000>;
+					regulator-max-microvolt = <2800000>;
+					regulator-enable-ramp-delay = <62>;
+					regulator-ramp-delay = <100000>;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+					maxim,active-fps-power-up-slot = <0>;
+					maxim,active-fps-power-down-slot = <7>;
+				};
+
+				ldo6 {
+					/* Unused. */
+					regulator-name = "PP_LDO6";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-enable-ramp-delay = <36>;
+					regulator-ramp-delay = <100000>;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+					maxim,active-fps-power-up-slot = <0>;
+					maxim,active-fps-power-down-slot = <7>;
+				};
+
+				pp1050_avdd: ldo7 {
+					regulator-name = "PP1050_AVDD";
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1050000>;
+					regulator-enable-ramp-delay = <24>;
+					regulator-ramp-delay = <100000>;
+					regulator-always-on;
+					regulator-boot-on;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
+					maxim,active-fps-power-up-slot = <3>;
+					maxim,active-fps-power-down-slot = <4>;
+				};
+
+				avddio_1v05: ldo8 {
+					regulator-name = "AVDDIO_1V05";
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1050000>;
+					regulator-enable-ramp-delay = <22>;
+					regulator-ramp-delay = <100000>;
+					regulator-boot-on;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+					maxim,active-fps-power-up-slot = <0>;
+					maxim,active-fps-power-down-slot = <7>;
+				};
+			};
+		};
+	};
+
 	pmc@7000e400 {
 		nvidia,invert-interrupt;
 		nvidia,suspend-mode = <0>;
@@ -1421,4 +1650,89 @@
 		compatible = "arm,psci-1.0";
 		method = "smc";
 	};
+
+	regulators {
+		compatible = "simple-bus";
+		device_type = "fixed-regulators";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ppvar_sys: regulator@0 {
+			compatible = "regulator-fixed";
+			reg = <0>;
+			regulator-name = "PPVAR_SYS";
+			regulator-min-microvolt = <4400000>;
+			regulator-max-microvolt = <4400000>;
+			regulator-always-on;
+		};
+
+		pplcd_vdd: regulator@1 {
+			compatible = "regulator-fixed";
+			reg = <1>;
+			regulator-name = "PPLCD_VDD";
+			regulator-min-microvolt = <4400000>;
+			regulator-max-microvolt = <4400000>;
+			gpio = <&gpio TEGRA_GPIO(V, 4) 0>;
+			enable-active-high;
+			regulator-boot-on;
+		};
+
+		pp3000_always: regulator@2 {
+			compatible = "regulator-fixed";
+			reg = <2>;
+			regulator-name = "PP3000_ALWAYS";
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-always-on;
+		};
+
+		pp3300: regulator@3 {
+			compatible = "regulator-fixed";
+			reg = <3>;
+			regulator-name = "PP3300";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-boot-on;
+			regulator-always-on;
+			enable-active-high;
+		};
+
+		pp5000: regulator@4 {
+			compatible = "regulator-fixed";
+			reg = <4>;
+			regulator-name = "PP5000";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			regulator-always-on;
+		};
+
+		pp1800_lcdio: regulator@5 {
+			compatible = "regulator-fixed";
+			reg = <5>;
+			regulator-name = "PP1800_LCDIO";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			gpio = <&gpio TEGRA_GPIO(V, 3) 0>;
+			enable-active-high;
+			regulator-boot-on;
+		};
+
+		pp1800_cam: regulator@6 {
+			compatible = "regulator-fixed";
+			reg= <6>;
+			regulator-name = "PP1800_CAM";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			gpio = <&gpio TEGRA_GPIO(K, 3) 0>;
+			enable-active-high;
+		};
+
+		usbc_vbus: regulator@7 {
+			compatible = "regulator-fixed";
+			reg = <7>;
+			regulator-name = "USBC_VBUS";
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+		};
+	};
 };
diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
index 76fe31faa1a5..c4cfdcf60d26 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
@@ -35,6 +35,26 @@
 			resets = <&tegra_car 207>;
 			reset-names = "dpaux";
 			status = "disabled";
+
+			state_dpaux1_aux: pinmux-aux {
+				groups = "dpaux-io";
+				function = "aux";
+			};
+
+			state_dpaux1_i2c: pinmux-i2c {
+				groups = "dpaux-io";
+				function = "i2c";
+			};
+
+			state_dpaux1_off: pinmux-off {
+				groups = "dpaux-io";
+				function = "off";
+			};
+
+			i2c-bus {
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
 		};
 
 		vi@54080000 {
@@ -154,6 +174,10 @@
 			clock-names = "sor", "parent", "dp", "safe";
 			resets = <&tegra_car 182>;
 			reset-names = "sor";
+			pinctrl-0 = <&state_dpaux_aux>;
+			pinctrl-1 = <&state_dpaux_i2c>;
+			pinctrl-2 = <&state_dpaux_off>;
+			pinctrl-names = "aux", "i2c", "off";
 			status = "disabled";
 		};
 
@@ -162,12 +186,17 @@
 			reg = <0x0 0x54580000 0x0 0x00040000>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&tegra_car TEGRA210_CLK_SOR1>,
+				 <&tegra_car TEGRA210_CLK_SOR1_SRC>,
 				 <&tegra_car TEGRA210_CLK_PLL_D2_OUT0>,
 				 <&tegra_car TEGRA210_CLK_PLL_DP>,
 				 <&tegra_car TEGRA210_CLK_SOR_SAFE>;
-			clock-names = "sor", "parent", "dp", "safe";
+			clock-names = "sor", "source", "parent", "dp", "safe";
 			resets = <&tegra_car 183>;
 			reset-names = "sor";
+			pinctrl-0 = <&state_dpaux1_aux>;
+			pinctrl-1 = <&state_dpaux1_i2c>;
+			pinctrl-2 = <&state_dpaux1_off>;
+			pinctrl-names = "aux", "i2c", "off";
 			status = "disabled";
 		};
 
@@ -181,6 +210,26 @@
 			resets = <&tegra_car 181>;
 			reset-names = "dpaux";
 			status = "disabled";
+
+			state_dpaux_aux: pinmux-aux {
+				groups = "dpaux-io";
+				function = "aux";
+			};
+
+			state_dpaux_i2c: pinmux-i2c {
+				groups = "dpaux-io";
+				function = "i2c";
+			};
+
+			state_dpaux_off: pinmux-off {
+				groups = "dpaux-io";
+				function = "off";
+			};
+
+			i2c-bus {
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
 		};
 
 		isp@54600000 {
@@ -478,6 +527,9 @@
 		reset-names = "i2c";
 		dmas = <&apbdma 26>, <&apbdma 26>;
 		dma-names = "rx", "tx";
+		pinctrl-0 = <&state_dpaux1_i2c>;
+		pinctrl-1 = <&state_dpaux1_off>;
+		pinctrl-names = "default", "idle";
 		status = "disabled";
 	};
 
@@ -508,6 +560,9 @@
 		reset-names = "i2c";
 		dmas = <&apbdma 30>, <&apbdma 30>;
 		dma-names = "rx", "tx";
+		pinctrl-0 = <&state_dpaux_i2c>;
+		pinctrl-1 = <&state_dpaux_off>;
+		pinctrl-names = "default", "idle";
 		status = "disabled";
 	};
 
@@ -584,6 +639,39 @@
 		reg = <0x0 0x7000e400 0x0 0x400>;
 		clocks = <&tegra_car TEGRA210_CLK_PCLK>, <&clk32k_in>;
 		clock-names = "pclk", "clk32k_in";
+
+		powergates {
+			pd_audio: aud {
+				clocks = <&tegra_car TEGRA210_CLK_APE>,
+					 <&tegra_car TEGRA210_CLK_APB2APE>;
+				resets = <&tegra_car 198>;
+				#power-domain-cells = <0>;
+			};
+
+			pd_xusbss: xusba {
+				clocks = <&tegra_car TEGRA210_CLK_XUSB_SS>;
+				clock-names = "xusb-ss";
+				resets = <&tegra_car TEGRA210_CLK_XUSB_SS>;
+				reset-names = "xusb-ss";
+				#power-domain-cells = <0>;
+			};
+
+			pd_xusbdev: xusbb {
+				clocks = <&tegra_car TEGRA210_CLK_XUSB_DEV>;
+				clock-names = "xusb-dev";
+				resets = <&tegra_car 95>;
+				reset-names = "xusb-dev";
+				#power-domain-cells = <0>;
+			};
+
+			pd_xusbhost: xusbc {
+				clocks = <&tegra_car TEGRA210_CLK_XUSB_HOST>;
+				clock-names = "xusb-host";
+				resets = <&tegra_car TEGRA210_CLK_XUSB_HOST>;
+				reset-names = "xusb-host";
+				#power-domain-cells = <0>;
+			};
+		};
 	};
 
 	fuse@7000f800 {
@@ -621,6 +709,196 @@
 		status = "disabled";
 	};
 
+	usb@70090000 {
+		compatible = "nvidia,tegra210-xusb";
+		reg = <0x0 0x70090000 0x0 0x8000>,
+		      <0x0 0x70098000 0x0 0x1000>,
+		      <0x0 0x70099000 0x0 0x1000>;
+		reg-names = "hcd", "fpci", "ipfs";
+
+		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
+
+		clocks = <&tegra_car TEGRA210_CLK_XUSB_HOST>,
+			 <&tegra_car TEGRA210_CLK_XUSB_HOST_SRC>,
+			 <&tegra_car TEGRA210_CLK_XUSB_FALCON_SRC>,
+			 <&tegra_car TEGRA210_CLK_XUSB_SS>,
+			 <&tegra_car TEGRA210_CLK_XUSB_SS_DIV2>,
+			 <&tegra_car TEGRA210_CLK_XUSB_SS_SRC>,
+			 <&tegra_car TEGRA210_CLK_XUSB_HS_SRC>,
+			 <&tegra_car TEGRA210_CLK_XUSB_FS_SRC>,
+			 <&tegra_car TEGRA210_CLK_PLL_U_480M>,
+			 <&tegra_car TEGRA210_CLK_CLK_M>,
+			 <&tegra_car TEGRA210_CLK_PLL_E>;
+		clock-names = "xusb_host", "xusb_host_src",
+			      "xusb_falcon_src", "xusb_ss",
+			      "xusb_ss_div2", "xusb_ss_src",
+			      "xusb_hs_src", "xusb_fs_src",
+			      "pll_u_480m", "clk_m", "pll_e";
+		resets = <&tegra_car 89>, <&tegra_car 156>,
+			 <&tegra_car 143>;
+		reset-names = "xusb_host", "xusb_ss", "xusb_src";
+
+		nvidia,xusb-padctl = <&padctl>;
+
+		status = "disabled";
+	};
+
+	padctl: padctl@7009f000 {
+		compatible = "nvidia,tegra210-xusb-padctl";
+		reg = <0x0 0x7009f000 0x0 0x1000>;
+		resets = <&tegra_car 142>;
+		reset-names = "padctl";
+
+		status = "disabled";
+
+		pads {
+			usb2 {
+				clocks = <&tegra_car TEGRA210_CLK_USB2_TRK>;
+				clock-names = "trk";
+				status = "disabled";
+
+				lanes {
+					usb2-0 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+
+					usb2-1 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+
+					usb2-2 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+
+					usb2-3 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+				};
+			};
+
+			hsic {
+				clocks = <&tegra_car TEGRA210_CLK_HSIC_TRK>;
+				clock-names = "trk";
+				status = "disabled";
+
+				lanes {
+					hsic-0 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+
+					hsic-1 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+				};
+			};
+
+			pcie {
+				clocks = <&tegra_car TEGRA210_CLK_PLL_E>;
+				clock-names = "pll";
+				resets = <&tegra_car 205>;
+				reset-names = "phy";
+				status = "disabled";
+
+				lanes {
+					pcie-0 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+
+					pcie-1 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+
+					pcie-2 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+
+					pcie-3 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+
+					pcie-4 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+
+					pcie-5 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+
+					pcie-6 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+				};
+			};
+
+			sata {
+				clocks = <&tegra_car TEGRA210_CLK_PLL_E>;
+				clock-names = "pll";
+				resets = <&tegra_car 204>;
+				reset-names = "phy";
+				status = "disabled";
+
+				lanes {
+					sata-0 {
+						status = "disabled";
+						#phy-cells = <0>;
+					};
+				};
+			};
+		};
+
+		ports {
+			usb2-0 {
+				status = "disabled";
+			};
+
+			usb2-1 {
+				status = "disabled";
+			};
+
+			usb2-2 {
+				status = "disabled";
+			};
+
+			usb2-3 {
+				status = "disabled";
+			};
+
+			hsic-0 {
+				status = "disabled";
+			};
+
+			usb3-0 {
+				status = "disabled";
+			};
+
+			usb3-1 {
+				status = "disabled";
+			};
+
+			usb3-2 {
+				status = "disabled";
+			};
+
+			usb3-3 {
+				status = "disabled";
+			};
+		};
+	};
+
 	sdhci@700b0000 {
 		compatible = "nvidia,tegra210-sdhci", "nvidia,tegra124-sdhci";
 		reg = <0x0 0x700b0000 0x0 0x200>;
@@ -673,6 +951,18 @@
 		#nvidia,mipi-calibrate-cells = <1>;
 	};
 
+	aconnect@702c0000 {
+		compatible = "nvidia,tegra210-aconnect";
+		clocks = <&tegra_car TEGRA210_CLK_APE>,
+			 <&tegra_car TEGRA210_CLK_APB2APE>;
+		clock-names = "ape", "apb2ape";
+		power-domains = <&pd_audio>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x702c0000 0x0 0x702c0000 0x00040000>;
+		status = "disabled";
+	};
+
 	spi@70410000 {
 		compatible = "nvidia,tegra210-qspi";
 		reg = <0x0 0x70410000 0x0 0x1000>;
diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi b/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
index 205ef89b8ca0..18639bc0a506 100644
--- a/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
@@ -33,6 +33,10 @@
 	};
 
 	soc {
+		dma@7884000 {
+			status = "okay";
+		};
+
 		serial@78af000 {
 			label = "LS-UART0";
 			status = "okay";
@@ -140,6 +144,18 @@
 			status = "okay";
 		};
 
+		sdhci@07864000 {
+			vmmc-supply = <&pm8916_l11>;
+			vqmmc-supply = <&pm8916_l12>;
+
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&sdc2_clk_on &sdc2_cmd_on &sdc2_data_on &sdc2_cd_on>;
+			pinctrl-1 = <&sdc2_clk_off &sdc2_cmd_off &sdc2_data_off &sdc2_cd_off>;
+
+			cd-gpios = <&msmgpio 38 0x1>;
+			status = "okay";
+		};
+
 		usb@78d9000 {
 			extcon = <&usb_id>, <&usb_id>;
 			status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi
index 96812007850e..11bdc24cfc74 100644
--- a/arch/arm64/boot/dts/qcom/msm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi
@@ -42,13 +42,48 @@
 		#size-cells = <2>;
 		ranges;
 
-		reserve_aligned@86000000 {
-			reg = <0x0 0x86000000 0x0 0x0300000>;
+		tz-apps@86000000 {
+			reg = <0x0 0x86000000 0x0 0x300000>;
 			no-map;
 		};
 
 		smem_mem: smem_region@86300000 {
-			reg = <0x0 0x86300000 0x0 0x0100000>;
+			reg = <0x0 0x86300000 0x0 0x100000>;
+			no-map;
+		};
+
+		hypervisor@86400000 {
+			reg = <0x0 0x86400000 0x0 0x100000>;
+			no-map;
+		};
+
+		tz@86500000 {
+			reg = <0x0 0x86500000 0x0 0x180000>;
+			no-map;
+		};
+
+		reserved@8668000 {
+			reg = <0x0 0x86680000 0x0 0x80000>;
+			no-map;
+		};
+
+		rmtfs@86700000 {
+			reg = <0x0 0x86700000 0x0 0xe0000>;
+			no-map;
+		};
+
+		rfsa@867e00000 {
+			reg = <0x0 0x867e0000 0x0 0x20000>;
+			no-map;
+		};
+
+		mpss@86800000 {
+			reg = <0x0 0x86800000 0x0 0x2b00000>;
+			no-map;
+		};
+
+		wcnss@89300000 {
+			reg = <0x0 0x89300000 0x0 0x600000>;
 			no-map;
 		};
 	};
@@ -62,6 +97,8 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x0>;
 			next-level-cache = <&L2_0>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SPC>;
 		};
 
 		CPU1: cpu@1 {
@@ -69,6 +106,8 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x1>;
 			next-level-cache = <&L2_0>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SPC>;
 		};
 
 		CPU2: cpu@2 {
@@ -76,6 +115,8 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x2>;
 			next-level-cache = <&L2_0>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SPC>;
 		};
 
 		CPU3: cpu@3 {
@@ -83,12 +124,35 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0x3>;
 			next-level-cache = <&L2_0>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SPC>;
 		};
 
 		L2_0: l2-cache {
 		      compatible = "cache";
 		      cache-level = <2>;
 		};
+
+		idle-states {
+			CPU_SPC: spc {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x40000002>;
+				entry-latency-us = <130>;
+				exit-latency-us = <150>;
+				min-residency-us = <2000>;
+				local-timer-stop;
+			};
+		};
+	};
+
+	psci {
+		compatible = "arm,psci-1.0";
+		method = "smc";
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_PPI 7 GIC_CPU_MASK_SIMPLE(4)>;
 	};
 
 	timer {
@@ -122,6 +186,14 @@
 		hwlocks = <&tcsr_mutex 3>;
 	};
 
+	firmware {
+		scm {
+			compatible = "qcom,scm";
+			clocks = <&gcc GCC_CRYPTO_CLK>, <&gcc GCC_CRYPTO_AXI_CLK>, <&gcc GCC_CRYPTO_AHB_CLK>;
+			clock-names = "core", "bus", "iface";
+		};
+	};
+
 	soc: soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/qcom/msm8996-pins.dtsi b/arch/arm64/boot/dts/qcom/msm8996-pins.dtsi
new file mode 100644
index 000000000000..659940434842
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/msm8996-pins.dtsi
@@ -0,0 +1,303 @@
+/*
+ * Copyright (c) 2013-2016, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+&msmgpio {
+
+	blsp1_spi0_default: blsp1_spi0_default {
+		pinmux {
+			function = "blsp_spi1";
+			pins = "gpio0", "gpio1", "gpio3";
+		};
+		pinmux_cs {
+			function = "gpio";
+			pins = "gpio2";
+		};
+		pinconf {
+			pins = "gpio0", "gpio1", "gpio3";
+			drive-strength = <12>;
+			bias-disable;
+		};
+		pinconf_cs {
+			pins = "gpio2";
+			drive-strength = <16>;
+			bias-disable;
+			output-high;
+		};
+	};
+
+	blsp1_spi0_sleep: blsp1_spi0_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio0", "gpio1", "gpio2", "gpio3";
+		};
+		pinconf {
+			pins = "gpio0", "gpio1", "gpio2", "gpio3";
+			drive-strength = <2>;
+			bias-pull-down;
+		};
+	};
+
+	blsp1_i2c2_default: blsp1_i2c2_default {
+		pinmux {
+			function = "blsp_i2c3";
+			pins = "gpio47", "gpio48";
+		};
+		pinconf {
+			pins = "gpio47", "gpio48";
+			drive-strength = <16>;
+			bias-disable = <0>;
+		};
+	};
+
+	blsp1_i2c2_sleep: blsp1_i2c2_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio47", "gpio48";
+		};
+		pinconf {
+			pins = "gpio47", "gpio48";
+			drive-strength = <2>;
+			bias-disable = <0>;
+		};
+	};
+
+	blsp2_i2c0_default: blsp2_i2c0 {
+		pinmux {
+			function = "blsp_i2c7";
+			pins = "gpio55", "gpio56";
+		};
+		pinconf {
+			pins = "gpio55", "gpio56";
+			drive-strength = <16>;
+			bias-disable;
+		};
+	};
+
+	blsp2_i2c0_sleep: blsp2_i2c0_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio55", "gpio56";
+		};
+		pinconf {
+			pins = "gpio55", "gpio56";
+			drive-strength = <2>;
+			bias-disable;
+		};
+	};
+
+	blsp2_uart1_2pins_default: blsp2_uart1_2pins {
+		pinmux {
+			function = "blsp_uart8";
+			pins = "gpio4", "gpio5";
+		};
+		pinconf {
+			pins = "gpio4", "gpio5";
+			drive-strength = <16>;
+			bias-disable;
+		};
+	};
+
+	blsp2_uart1_2pins_sleep: blsp2_uart1_2pins_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio4", "gpio5";
+		};
+		pinconf {
+			pins = "gpio4", "gpio5";
+			drive-strength = <2>;
+			bias-disable;
+		};
+	};
+
+	blsp2_uart1_4pins_default: blsp2_uart1_4pins {
+		pinmux {
+			function = "blsp_uart8";
+			pins = "gpio4", "gpio5", "gpio6", "gpio7";
+		};
+
+		pinconf {
+			pins = "gpio4", "gpio5", "gpio6", "gpio7";
+			drive-strength = <16>;
+			bias-disable;
+		};
+	};
+
+	blsp2_uart1_4pins_sleep: blsp2_uart1_4pins_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio4", "gpio5", "gpio6", "gpio7";
+		};
+
+		pinconf {
+			pins = "gpio4", "gpiio5", "gpio6", "gpio7";
+			drive-strength = <2>;
+			bias-disable;
+		};
+	};
+
+	blsp2_i2c1_default: blsp2_i2c1 {
+		pinmux {
+			function = "blsp_i2c8";
+			pins = "gpio6", "gpio7";
+		};
+		pinconf {
+			pins = "gpio6", "gpio7";
+			drive-strength = <16>;
+			bias-disable;
+		};
+	};
+
+	blsp2_i2c1_sleep: blsp2_i2c1_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio6", "gpio7";
+		};
+		pinconf {
+			pins = "gpio6", "gpio7";
+			drive-strength = <2>;
+			bias-disable;
+		};
+	};
+
+	blsp2_uart2_2pins_default: blsp2_uart2_2pins {
+		pinmux {
+			function = "blsp_uart9";
+			pins = "gpio49", "gpio50";
+		};
+		pinconf {
+			pins = "gpio49", "gpio50";
+			drive-strength = <16>;
+			bias-disable;
+		};
+	};
+
+	blsp2_uart2_2pins_sleep: blsp2_uart2_2pins_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio49", "gpio50";
+		};
+		pinconf {
+			pins = "gpio49", "gpio50";
+			drive-strength = <2>;
+			bias-disable;
+		};
+	};
+
+	blsp2_uart2_4pins_default: blsp2_uart2_4pins {
+		pinmux {
+			function = "blsp_uart9";
+			pins = "gpio49", "gpio50", "gpio51", "gpio52";
+		};
+
+		pinconf {
+			pins = "gpio49", "gpio50", "gpio51", "gpio52";
+			drive-strength = <16>;
+			bias-disable;
+		};
+	};
+
+	blsp2_uart2_4pins_sleep: blsp2_uart2_4pins_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio49", "gpio50", "gpio51", "gpio52";
+		};
+
+		pinconf {
+			pins = "gpio49", "gpio50", "gpio51", "gpio52";
+			drive-strength = <2>;
+			bias-disable;
+		};
+	};
+
+	blsp2_spi5_default: blsp2_spi5_default {
+		pinmux {
+			function = "blsp_spi12";
+			pins = "gpio85", "gpio86", "gpio88";
+		};
+		pinmux_cs {
+			function = "gpio";
+			pins = "gpio87";
+		};
+		pinconf {
+			pins = "gpio85", "gpio86", "gpio88";
+			drive-strength = <12>;
+			bias-disable;
+		};
+		pinconf_cs {
+			pins = "gpio87";
+			drive-strength = <16>;
+			bias-disable;
+			output-high;
+		};
+	};
+
+	blsp2_spi5_sleep: blsp2_spi5_sleep {
+		pinmux {
+			function = "gpio";
+			pins = "gpio85", "gpio86", "gpio87", "gpio88";
+		};
+		pinconf {
+			pins = "gpio85", "gpio86", "gpio87", "gpio88";
+			drive-strength = <2>;
+			bias-pull-down;
+		};
+	};
+
+	sdc2_clk_on: sdc2_clk_on {
+		config {
+			pins = "sdc2_clk";
+			bias-disable;		/* NO pull */
+			drive-strength = <16>;	/* 16 MA */
+		};
+	};
+
+	sdc2_clk_off: sdc2_clk_off {
+		config {
+			pins = "sdc2_clk";
+			bias-disable;		/* NO pull */
+			drive-strength = <2>;	/* 2 MA */
+		};
+	};
+
+	sdc2_cmd_on: sdc2_cmd_on {
+		config {
+			pins = "sdc2_cmd";
+			bias-pull-up;		/* pull up */
+			drive-strength = <10>;	/* 10 MA */
+		};
+	};
+
+	sdc2_cmd_off: sdc2_cmd_off {
+		config {
+			pins = "sdc2_cmd";
+			bias-pull-up;		/* pull up */
+			drive-strength = <2>;	/* 2 MA */
+		};
+	};
+
+	sdc2_data_on: sdc2_data_on {
+		config {
+			pins = "sdc2_data";
+			bias-pull-up;		/* pull up */
+			drive-strength = <10>;	/* 10 MA */
+		};
+	};
+
+	sdc2_data_off: sdc2_data_off {
+		config {
+			pins = "sdc2_data";
+			bias-pull-up;		/* pull up */
+			drive-strength = <2>;	/* 2 MA */
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 0506fb808c56..55ec3e8326b7 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -151,6 +151,36 @@
 			reg = <0x300000 0x90000>;
 		};
 
+		blsp1_spi0: spi@07575000 {
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x07575000 0x600>;
+			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&blsp1_spi0_default>;
+			pinctrl-1 = <&blsp1_spi0_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		blsp2_i2c0: i2c@075b5000 {
+			compatible = "qcom,i2c-qup-v2.2.1";
+			reg = <0x075b5000 0x1000>;
+			interrupts = <GIC_SPI 101 0>;
+			clocks = <&gcc GCC_BLSP2_AHB_CLK>,
+				<&gcc GCC_BLSP2_QUP1_I2C_APPS_CLK>;
+			clock-names = "iface", "core";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&blsp2_i2c0_default>;
+			pinctrl-1 = <&blsp2_i2c0_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
 		blsp2_uart1: serial@75b0000 {
 			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
 			reg = <0x75b0000 0x1000>;
@@ -161,7 +191,77 @@
 			status = "disabled";
 		};
 
-		pinctrl@1010000 {
+		blsp2_i2c1: i2c@075b6000 {
+			compatible = "qcom,i2c-qup-v2.2.1";
+			reg = <0x075b6000 0x1000>;
+			interrupts = <GIC_SPI 102 0>;
+			clocks = <&gcc GCC_BLSP2_AHB_CLK>,
+				<&gcc GCC_BLSP2_QUP2_I2C_APPS_CLK>;
+			clock-names = "iface", "core";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&blsp2_i2c1_default>;
+			pinctrl-1 = <&blsp2_i2c1_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		blsp2_uart2: serial@75b1000 {
+			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
+			reg = <0x075b1000 0x1000>;
+			interrupts = <GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP2_UART3_APPS_CLK>,
+				 <&gcc GCC_BLSP2_AHB_CLK>;
+			clock-names = "core", "iface";
+			status = "disabled";
+		};
+
+		blsp1_i2c2: i2c@07577000 {
+			compatible = "qcom,i2c-qup-v2.2.1";
+			reg = <0x07577000 0x1000>;
+			interrupts = <GIC_SPI 97 0>;
+			clocks = <&gcc GCC_BLSP1_AHB_CLK>,
+				<&gcc GCC_BLSP1_QUP3_I2C_APPS_CLK>;
+			clock-names = "iface", "core";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&blsp1_i2c2_default>;
+			pinctrl-1 = <&blsp1_i2c2_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		blsp2_spi5: spi@075ba000{
+			compatible = "qcom,spi-qup-v2.2.1";
+			reg = <0x075ba000 0x600>;
+			interrupts = <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP2_QUP5_SPI_APPS_CLK>,
+				 <&gcc GCC_BLSP2_AHB_CLK>;
+			clock-names = "core", "iface";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&blsp2_spi5_default>;
+			pinctrl-1 = <&blsp2_spi5_sleep>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		sdhc2: sdhci@74a4900 {
+			 status = "disabled";
+			 compatible = "qcom,sdhci-msm-v4";
+			 reg = <0x74a4900 0x314>, <0x74a4000 0x800>;
+			 reg-names = "hc_mem", "core_mem";
+
+			 interrupts = <0 125 0>, <0 221 0>;
+			 interrupt-names = "hc_irq", "pwr_irq";
+
+			 clock-names = "iface", "core";
+			 clocks = <&gcc GCC_SDCC2_AHB_CLK>,
+			 <&gcc GCC_SDCC2_APPS_CLK>;
+			 bus-width = <4>;
+		 };
+
+		msmgpio: pinctrl@1010000 {
 			compatible = "qcom,msm8996-pinctrl";
 			reg = <0x01010000 0x300000>;
 			interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
@@ -267,3 +367,4 @@
 		};
 	};
 };
+#include "msm8996-pins.dtsi"
diff --git a/arch/arm64/boot/dts/renesas/Makefile b/arch/arm64/boot/dts/renesas/Makefile
index 9ce1890a650e..17139f7003a6 100644
--- a/arch/arm64/boot/dts/renesas/Makefile
+++ b/arch/arm64/boot/dts/renesas/Makefile
@@ -1,4 +1,5 @@
 dtb-$(CONFIG_ARCH_R8A7795) += r8a7795-salvator-x.dtb
+dtb-$(CONFIG_ARCH_R8A7796) += r8a7796-salvator-x.dtb
 
 always		:= $(dtb-y)
 clean-files	:= *.dtb
diff --git a/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts b/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
index 9f561c943f6f..98f02631a0f0 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
+++ b/arch/arm64/boot/dts/renesas/r8a7795-salvator-x.dts
@@ -62,7 +62,7 @@
 		clock-frequency = <24576000>;
 	};
 
-	vcc_sdhi0: regulator@1 {
+	vcc_sdhi0: regulator-vcc-sdhi0 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI0 Vcc";
@@ -73,7 +73,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi0: regulator@2 {
+	vccq_sdhi0: regulator-vccq-sdhi0 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI0 VccQ";
@@ -86,7 +86,7 @@
 			  1800000 0>;
 	};
 
-	vcc_sdhi3: regulator@3 {
+	vcc_sdhi3: regulator-vcc-sdhi3 {
 		compatible = "regulator-fixed";
 
 		regulator-name = "SDHI3 Vcc";
@@ -97,7 +97,7 @@
 		enable-active-high;
 	};
 
-	vccq_sdhi3: regulator@4 {
+	vccq_sdhi3: regulator-vccq-sdhi3 {
 		compatible = "regulator-gpio";
 
 		regulator-name = "SDHI3 VccQ";
@@ -208,6 +208,7 @@
 	pinctrl-0 = <&scif1_pins>;
 	pinctrl-names = "default";
 
+	uart-has-rtscts;
 	status = "okay";
 };
 
@@ -329,6 +330,11 @@
 	shared-pin;
 };
 
+&wdt0 {
+	timeout-sec = <60>;
+	status = "okay";
+};
+
 &audio_clk_a {
 	clock-frequency = <22579200>;
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi
index 3285a9286786..b902356873c2 100644
--- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi
@@ -53,6 +53,7 @@
 			next-level-cache = <&L2_CA57>;
 			enable-method = "psci";
 		};
+
 		a57_2: cpu@2 {
 			compatible = "arm,cortex-a57","arm,armv8";
 			reg = <0x2>;
@@ -61,6 +62,7 @@
 			next-level-cache = <&L2_CA57>;
 			enable-method = "psci";
 		};
+
 		a57_3: cpu@3 {
 			compatible = "arm,cortex-a57","arm,armv8";
 			reg = <0x3>;
@@ -69,20 +71,22 @@
 			next-level-cache = <&L2_CA57>;
 			enable-method = "psci";
 		};
-	};
 
-	L2_CA57: cache-controller@0 {
-		compatible = "cache";
-		power-domains = <&sysc R8A7795_PD_CA57_SCU>;
-		cache-unified;
-		cache-level = <2>;
-	};
+		L2_CA57: cache-controller@0 {
+			compatible = "cache";
+			reg = <0>;
+			power-domains = <&sysc R8A7795_PD_CA57_SCU>;
+			cache-unified;
+			cache-level = <2>;
+		};
 
-	L2_CA53: cache-controller@1 {
-		compatible = "cache";
-		power-domains = <&sysc R8A7795_PD_CA53_SCU>;
-		cache-unified;
-		cache-level = <2>;
+		L2_CA53: cache-controller@100 {
+			compatible = "cache";
+			reg = <0x100>;
+			power-domains = <&sysc R8A7795_PD_CA53_SCU>;
+			cache-unified;
+			cache-level = <2>;
+		};
 	};
 
 	extal_clk: extal {
@@ -151,19 +155,27 @@
 		#size-cells = <2>;
 		ranges;
 
-		gic: interrupt-controller@0xf1010000 {
+		gic: interrupt-controller@f1010000 {
 			compatible = "arm,gic-400";
 			#interrupt-cells = <3>;
 			#address-cells = <0>;
 			interrupt-controller;
 			reg = <0x0 0xf1010000 0 0x1000>,
-			      <0x0 0xf1020000 0 0x2000>,
+			      <0x0 0xf1020000 0 0x20000>,
 			      <0x0 0xf1040000 0 0x20000>,
-			      <0x0 0xf1060000 0 0x2000>;
+			      <0x0 0xf1060000 0 0x20000>;
 			interrupts = <GIC_PPI 9
 					(GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
 		};
 
+		wdt0: watchdog@e6020000 {
+			compatible = "renesas,r8a7795-wdt", "renesas,rcar-gen3-wdt";
+			reg = <0 0xe6020000 0 0x0c>;
+			clocks = <&cpg CPG_MOD 402>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			status = "disabled";
+		};
+
 		gpio0: gpio@e6050000 {
 			compatible = "renesas,gpio-r8a7795",
 				     "renesas,gpio-rcar";
@@ -571,6 +583,30 @@
 			status = "disabled";
 		};
 
+		canfd: can@e66c0000 {
+			compatible = "renesas,r8a7795-canfd",
+				     "renesas,rcar-gen3-canfd";
+			reg = <0 0xe66c0000 0 0x8000>;
+			interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+				   <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 914>,
+			       <&cpg CPG_CORE R8A7795_CLK_CANFD>,
+			       <&can_clk>;
+			clock-names = "fck", "canfd", "can_clk";
+			assigned-clocks = <&cpg CPG_CORE R8A7795_CLK_CANFD>;
+			assigned-clock-rates = <40000000>;
+			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			status = "disabled";
+
+			channel0 {
+				status = "disabled";
+			};
+
+			channel1 {
+				status = "disabled";
+			};
+		};
+
 		hscif0: serial@e6540000 {
 			compatible = "renesas,hscif-r8a7795",
 				     "renesas,rcar-gen3-hscif",
@@ -749,6 +785,8 @@
 			interrupts = <GIC_SPI 287 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 931>;
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			dmas = <&dmac1 0x91>, <&dmac1 0x90>;
+			dma-names = "tx", "rx";
 			i2c-scl-internal-delay-ns = <110>;
 			status = "disabled";
 		};
@@ -761,6 +799,8 @@
 			interrupts = <GIC_SPI 288 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 930>;
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			dmas = <&dmac1 0x93>, <&dmac1 0x92>;
+			dma-names = "tx", "rx";
 			i2c-scl-internal-delay-ns = <6>;
 			status = "disabled";
 		};
@@ -773,6 +813,8 @@
 			interrupts = <GIC_SPI 286 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 929>;
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			dmas = <&dmac1 0x95>, <&dmac1 0x94>;
+			dma-names = "tx", "rx";
 			i2c-scl-internal-delay-ns = <6>;
 			status = "disabled";
 		};
@@ -785,6 +827,8 @@
 			interrupts = <GIC_SPI 290 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 928>;
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			dmas = <&dmac0 0x97>, <&dmac0 0x96>;
+			dma-names = "tx", "rx";
 			i2c-scl-internal-delay-ns = <110>;
 			status = "disabled";
 		};
@@ -797,6 +841,8 @@
 			interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 927>;
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			dmas = <&dmac0 0x99>, <&dmac0 0x98>;
+			dma-names = "tx", "rx";
 			i2c-scl-internal-delay-ns = <110>;
 			status = "disabled";
 		};
@@ -809,6 +855,8 @@
 			interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 919>;
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			dmas = <&dmac0 0x9b>, <&dmac0 0x9a>;
+			dma-names = "tx", "rx";
 			i2c-scl-internal-delay-ns = <110>;
 			status = "disabled";
 		};
@@ -821,6 +869,8 @@
 			interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 918>;
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+			dmas = <&dmac0 0x9d>, <&dmac0 0x9c>;
+			dma-names = "tx", "rx";
 			i2c-scl-internal-delay-ns = <6>;
 			status = "disabled";
 		};
@@ -874,63 +924,63 @@
 			status = "disabled";
 
 			rcar_sound,dvc {
-				dvc0: dvc@0 {
+				dvc0: dvc-0 {
 					dmas = <&audma0 0xbc>;
 					dma-names = "tx";
 				};
-				dvc1: dvc@1 {
+				dvc1: dvc-1 {
 					dmas = <&audma0 0xbe>;
 					dma-names = "tx";
 				};
 			};
 
 			rcar_sound,src {
-				src0: src@0 {
+				src0: src-0 {
 					interrupts = <GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x85>, <&audma1 0x9a>;
 					dma-names = "rx", "tx";
 				};
-				src1: src@1 {
+				src1: src-1 {
 					interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x87>, <&audma1 0x9c>;
 					dma-names = "rx", "tx";
 				};
-				src2: src@2 {
+				src2: src-2 {
 					interrupts = <GIC_SPI 354 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x89>, <&audma1 0x9e>;
 					dma-names = "rx", "tx";
 				};
-				src3: src@3 {
+				src3: src-3 {
 					interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x8b>, <&audma1 0xa0>;
 					dma-names = "rx", "tx";
 				};
-				src4: src@4 {
+				src4: src-4 {
 					interrupts = <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x8d>, <&audma1 0xb0>;
 					dma-names = "rx", "tx";
 				};
-				src5: src@5 {
+				src5: src-5 {
 					interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x8f>, <&audma1 0xb2>;
 					dma-names = "rx", "tx";
 				};
-				src6: src@6 {
+				src6: src-6 {
 					interrupts = <GIC_SPI 358 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x91>, <&audma1 0xb4>;
 					dma-names = "rx", "tx";
 				};
-				src7: src@7 {
+				src7: src-7 {
 					interrupts = <GIC_SPI 359 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x93>, <&audma1 0xb6>;
 					dma-names = "rx", "tx";
 				};
-				src8: src@8 {
+				src8: src-8 {
 					interrupts = <GIC_SPI 360 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x95>, <&audma1 0xb8>;
 					dma-names = "rx", "tx";
 				};
-				src9: src@9 {
+				src9: src-9 {
 					interrupts = <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x97>, <&audma1 0xba>;
 					dma-names = "rx", "tx";
@@ -938,52 +988,52 @@
 			};
 
 			rcar_sound,ssi {
-				ssi0: ssi@0 {
+				ssi0: ssi-0 {
 					interrupts = <GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x01>, <&audma1 0x02>, <&audma0 0x15>, <&audma1 0x16>;
 					dma-names = "rx", "tx", "rxu", "txu";
 				};
-				ssi1: ssi@1 {
+				ssi1: ssi-1 {
 					 interrupts = <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x03>, <&audma1 0x04>, <&audma0 0x49>, <&audma1 0x4a>;
 					dma-names = "rx", "tx", "rxu", "txu";
 				};
-				ssi2: ssi@2 {
+				ssi2: ssi-2 {
 					interrupts = <GIC_SPI 372 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x05>, <&audma1 0x06>, <&audma0 0x63>, <&audma1 0x64>;
 					dma-names = "rx", "tx", "rxu", "txu";
 				};
-				ssi3: ssi@3 {
+				ssi3: ssi-3 {
 					interrupts = <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x07>, <&audma1 0x08>, <&audma0 0x6f>, <&audma1 0x70>;
 					dma-names = "rx", "tx", "rxu", "txu";
 				};
-				ssi4: ssi@4 {
+				ssi4: ssi-4 {
 					interrupts = <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x09>, <&audma1 0x0a>, <&audma0 0x71>, <&audma1 0x72>;
 					dma-names = "rx", "tx", "rxu", "txu";
 				};
-				ssi5: ssi@5 {
+				ssi5: ssi-5 {
 					interrupts = <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x0b>, <&audma1 0x0c>, <&audma0 0x73>, <&audma1 0x74>;
 					dma-names = "rx", "tx", "rxu", "txu";
 				};
-				ssi6: ssi@6 {
+				ssi6: ssi-6 {
 					interrupts = <GIC_SPI 376 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x0d>, <&audma1 0x0e>, <&audma0 0x75>, <&audma1 0x76>;
 					dma-names = "rx", "tx", "rxu", "txu";
 				};
-				ssi7: ssi@7 {
+				ssi7: ssi-7 {
 					interrupts = <GIC_SPI 377 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x0f>, <&audma1 0x10>, <&audma0 0x79>, <&audma1 0x7a>;
 					dma-names = "rx", "tx", "rxu", "txu";
 				};
-				ssi8: ssi@8 {
+				ssi8: ssi-8 {
 					interrupts = <GIC_SPI 378 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x11>, <&audma1 0x12>, <&audma0 0x7b>, <&audma1 0x7c>;
 					dma-names = "rx", "tx", "rxu", "txu";
 				};
-				ssi9: ssi@9 {
+				ssi9: ssi-9 {
 					interrupts = <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH>;
 					dmas = <&audma0 0x13>, <&audma1 0x14>, <&audma0 0x7d>, <&audma1 0x7e>;
 					dma-names = "rx", "tx", "rxu", "txu";
diff --git a/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts b/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts
new file mode 100644
index 000000000000..e72be3856d79
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r8a7796-salvator-x.dts
@@ -0,0 +1,50 @@
+/*
+ * Device Tree Source for the Salvator-X board
+ *
+ * Copyright (C) 2016 Renesas Electronics Corp.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/dts-v1/;
+#include "r8a7796.dtsi"
+
+/ {
+	model = "Renesas Salvator-X board based on r8a7796";
+	compatible = "renesas,salvator-x", "renesas,r8a7796";
+
+	aliases {
+		serial0 = &scif2;
+	};
+
+	chosen {
+		bootargs = "ignore_loglevel";
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@48000000 {
+		device_type = "memory";
+		/* first 128MB is reserved for secure area. */
+		reg = <0x0 0x48000000 0x0 0x78000000>;
+	};
+};
+
+&extal_clk {
+	clock-frequency = <16666666>;
+};
+
+&scif2 {
+	status = "okay";
+};
+
+&scif_clk {
+	clock-frequency = <14745600>;
+	status = "okay";
+};
+
+&wdt0 {
+	timeout-sec = <60>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/renesas/r8a7796.dtsi b/arch/arm64/boot/dts/renesas/r8a7796.dtsi
new file mode 100644
index 000000000000..1edf82440d78
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r8a7796.dtsi
@@ -0,0 +1,138 @@
+/*
+ * Device Tree Source for the r8a7796 SoC
+ *
+ * Copyright (C) 2016 Renesas Electronics Corp.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <dt-bindings/clock/r8a7796-cpg-mssr.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/power/r8a7796-sysc.h>
+
+/ {
+	compatible = "renesas,r8a7796";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		/* 1 core only at this point */
+		a57_0: cpu@0 {
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0>;
+			device_type = "cpu";
+			power-domains = <&sysc R8A7796_PD_CA57_CPU0>;
+			next-level-cache = <&L2_CA57>;
+			enable-method = "psci";
+		};
+
+		L2_CA57: cache-controller@0 {
+			compatible = "cache";
+			reg = <0>;
+			power-domains = <&sysc R8A7796_PD_CA57_SCU>;
+			cache-unified;
+			cache-level = <2>;
+		};
+	};
+
+	extal_clk: extal {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board */
+		clock-frequency = <0>;
+	};
+
+	extalr_clk: extalr {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board */
+		clock-frequency = <0>;
+	};
+
+	/* External SCIF clock - to be overridden by boards that provide it */
+	scif_clk: scif {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	soc {
+		compatible = "simple-bus";
+		interrupt-parent = <&gic>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		gic: interrupt-controller@f1010000 {
+			compatible = "arm,gic-400";
+			#interrupt-cells = <3>;
+			#address-cells = <0>;
+			interrupt-controller;
+			reg = <0x0 0xf1010000 0 0x1000>,
+			      <0x0 0xf1020000 0 0x20000>,
+			      <0x0 0xf1040000 0 0x20000>,
+			      <0x0 0xf1060000 0 0x20000>;
+			interrupts = <GIC_PPI 9
+					(GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_HIGH)>;
+		};
+
+		timer {
+			compatible = "arm,armv8-timer";
+			interrupts = <GIC_PPI 13
+					(GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>,
+				     <GIC_PPI 14
+					(GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>,
+				     <GIC_PPI 11
+					(GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>,
+				     <GIC_PPI 10
+					(GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>;
+		};
+
+		wdt0: watchdog@e6020000 {
+			compatible = "renesas,r8a7796-wdt",
+				     "renesas,rcar-gen3-wdt";
+			reg = <0 0xe6020000 0 0x0c>;
+			clocks = <&cpg CPG_MOD 402>;
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			status = "disabled";
+		};
+
+		cpg: clock-controller@e6150000 {
+			compatible = "renesas,r8a7796-cpg-mssr";
+			reg = <0 0xe6150000 0 0x1000>;
+			clocks = <&extal_clk>, <&extalr_clk>;
+			clock-names = "extal", "extalr";
+			#clock-cells = <2>;
+			#power-domain-cells = <0>;
+		};
+
+		sysc: system-controller@e6180000 {
+			compatible = "renesas,r8a7796-sysc";
+			reg = <0 0xe6180000 0 0x0400>;
+			#power-domain-cells = <1>;
+		};
+
+		scif2: serial@e6e88000 {
+			compatible = "renesas,scif-r8a7796",
+				     "renesas,rcar-gen3-scif", "renesas,scif";
+			reg = <0 0xe6e88000 0 64>;
+			interrupts = <GIC_SPI 164 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 310>,
+				 <&cpg CPG_CORE R8A7796_CLK_S3D1>,
+				 <&scif_clk>;
+			clock-names = "fck", "brg_int", "scif_clk";
+			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+			status = "disabled";
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-r88.dts b/arch/arm64/boot/dts/rockchip/rk3368-r88.dts
index b56b7205e39b..82a32e5591e2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-r88.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3368-r88.dts
@@ -236,6 +236,15 @@
 	};
 };
 
+&io_domains {
+	status = "ok";
+
+	audio-supply = <&vcc_io>;
+	gpio30-supply = <&vcc_io>;
+	gpio1830-supply = <&vcc_io>;
+	wifi-supply = <&vccio_wl>;
+};
+
 &sdio0 {
 	assigned-clocks = <&cru SCLK_SDIO0>;
 	assigned-clock-parents = <&cru PLL_CPLL>;
@@ -329,6 +338,13 @@
 	};
 };
 
+&pmu_io_domains {
+	status = "okay";
+
+	pmu-supply = <&vcc_io>;
+	vop-supply = <&vcc_io>;
+};
+
 &saradc {
 	vref-supply = <&vcc_18>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index 8b4a7c9154e9..d02a900378e1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -632,8 +632,13 @@
 	};
 
 	pmugrf: syscon@ff738000 {
-		compatible = "rockchip,rk3368-pmugrf", "syscon";
+		compatible = "rockchip,rk3368-pmugrf", "syscon", "simple-mfd";
 		reg = <0x0 0xff738000 0x0 0x1000>;
+
+		pmu_io_domains: io-domains {
+			compatible = "rockchip,rk3368-pmu-io-voltage-domain";
+			status = "disabled";
+		};
 	};
 
 	cru: clock-controller@ff760000 {
@@ -645,8 +650,13 @@
 	};
 
 	grf: syscon@ff770000 {
-		compatible = "rockchip,rk3368-grf", "syscon";
+		compatible = "rockchip,rk3368-grf", "syscon", "simple-mfd";
 		reg = <0x0 0xff770000 0x0 0x1000>;
+
+		io_domains: io-domains {
+			compatible = "rockchip,rk3368-io-voltage-domain";
+			status = "disabled";
+		};
 	};
 
 	wdt: watchdog@ff800000 {
@@ -670,7 +680,7 @@
 		#address-cells = <0>;
 
 		reg = <0x0 0xffb71000 0x0 0x1000>,
-		      <0x0 0xffb72000 0x0 0x1000>,
+		      <0x0 0xffb72000 0x0 0x2000>,
 		      <0x0 0xffb74000 0x0 0x2000>,
 		      <0x0 0xffb76000 0x0 0x2000>;
 		interrupts = <GIC_PPI 9
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-evb.dts b/arch/arm64/boot/dts/rockchip/rk3399-evb.dts
index 1a3eb1482050..d33aa06d46f5 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-evb.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-evb.dts
@@ -77,6 +77,10 @@
 	};
 };
 
+&emmc_phy {
+	status = "okay";
+};
+
 &pwm0 {
 	status = "okay";
 };
@@ -89,6 +93,14 @@
 	status = "okay";
 };
 
+&sdhci {
+	bus-width = <8>;
+	mmc-hs400-1_8v;
+	mmc-hs400-enhanced-strobe;
+	non-removable;
+	status = "okay";
+};
+
 &uart2 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 188bbeab92b9..a6dd623a8845 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -45,6 +45,7 @@
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/thermal/thermal.h>
 
 / {
 	compatible = "rockchip,rk3399";
@@ -54,6 +55,15 @@
 	#size-cells = <2>;
 
 	aliases {
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+		i2c4 = &i2c4;
+		i2c5 = &i2c5;
+		i2c6 = &i2c6;
+		i2c7 = &i2c7;
+		i2c8 = &i2c8;
 		serial0 = &uart0;
 		serial1 = &uart1;
 		serial2 = &uart2;
@@ -215,6 +225,22 @@
 		status = "disabled";
 	};
 
+	sdhci: sdhci@fe330000 {
+		compatible = "rockchip,rk3399-sdhci-5.1", "arasan,sdhci-5.1";
+		reg = <0x0 0xfe330000 0x0 0x10000>;
+		interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+		arasan,soc-ctl-syscon = <&grf>;
+		assigned-clocks = <&cru SCLK_EMMC>;
+		assigned-clock-rates = <200000000>;
+		clocks = <&cru SCLK_EMMC>, <&cru ACLK_EMMC>;
+		clock-names = "clk_xin", "clk_ahb";
+		clock-output-names = "emmc_cardclock";
+		#clock-cells = <0>;
+		phys = <&emmc_phy>;
+		phy-names = "phy_arasan";
+		status = "disabled";
+	};
+
 	usb_host0_ehci: usb@fe380000 {
 		compatible = "generic-ehci";
 		reg = <0x0 0xfe380000 0x0 0x20000>;
@@ -272,6 +298,96 @@
 		};
 	};
 
+	i2c1: i2c@ff110000 {
+		compatible = "rockchip,rk3399-i2c";
+		reg = <0x0 0xff110000 0x0 0x1000>;
+		assigned-clocks = <&cru SCLK_I2C1>;
+		assigned-clock-rates = <200000000>;
+		clocks = <&cru SCLK_I2C1>, <&cru PCLK_I2C1>;
+		clock-names = "i2c", "pclk";
+		interrupts = <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c1_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c2: i2c@ff120000 {
+		compatible = "rockchip,rk3399-i2c";
+		reg = <0x0 0xff120000 0x0 0x1000>;
+		assigned-clocks = <&cru SCLK_I2C2>;
+		assigned-clock-rates = <200000000>;
+		clocks = <&cru SCLK_I2C2>, <&cru PCLK_I2C2>;
+		clock-names = "i2c", "pclk";
+		interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c2_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c3: i2c@ff130000 {
+		compatible = "rockchip,rk3399-i2c";
+		reg = <0x0 0xff130000 0x0 0x1000>;
+		assigned-clocks = <&cru SCLK_I2C3>;
+		assigned-clock-rates = <200000000>;
+		clocks = <&cru SCLK_I2C3>, <&cru PCLK_I2C3>;
+		clock-names = "i2c", "pclk";
+		interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c3_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c5: i2c@ff140000 {
+		compatible = "rockchip,rk3399-i2c";
+		reg = <0x0 0xff140000 0x0 0x1000>;
+		assigned-clocks = <&cru SCLK_I2C5>;
+		assigned-clock-rates = <200000000>;
+		clocks = <&cru SCLK_I2C5>, <&cru PCLK_I2C5>;
+		clock-names = "i2c", "pclk";
+		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c5_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c6: i2c@ff150000 {
+		compatible = "rockchip,rk3399-i2c";
+		reg = <0x0 0xff150000 0x0 0x1000>;
+		assigned-clocks = <&cru SCLK_I2C6>;
+		assigned-clock-rates = <200000000>;
+		clocks = <&cru SCLK_I2C6>, <&cru PCLK_I2C6>;
+		clock-names = "i2c", "pclk";
+		interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c6_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c7: i2c@ff160000 {
+		compatible = "rockchip,rk3399-i2c";
+		reg = <0x0 0xff160000 0x0 0x1000>;
+		assigned-clocks = <&cru SCLK_I2C7>;
+		assigned-clock-rates = <200000000>;
+		clocks = <&cru SCLK_I2C7>, <&cru PCLK_I2C7>;
+		clock-names = "i2c", "pclk";
+		interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c7_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
 	uart0: serial@ff180000 {
 		compatible = "rockchip,rk3399-uart", "snps,dw-apb-uart";
 		reg = <0x0 0xff180000 0x0 0x100>;
@@ -389,9 +505,105 @@
 		status = "disabled";
 	};
 
+	thermal-zones {
+		cpu_thermal: cpu {
+			polling-delay-passive = <100>;
+			polling-delay = <1000>;
+
+			thermal-sensors = <&tsadc 0>;
+
+			trips {
+				cpu_alert0: cpu_alert0 {
+					temperature = <70000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+				cpu_alert1: cpu_alert1 {
+					temperature = <75000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+				cpu_crit: cpu_crit {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu_alert0>;
+					cooling-device =
+						<&cpu_b0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+				map1 {
+					trip = <&cpu_alert1>;
+					cooling-device =
+						<&cpu_l0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+						<&cpu_b0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		gpu_thermal: gpu {
+			polling-delay-passive = <100>;
+			polling-delay = <1000>;
+
+			thermal-sensors = <&tsadc 1>;
+
+			trips {
+				gpu_alert0: gpu_alert0 {
+					temperature = <75000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+				gpu_crit: gpu_crit {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&gpu_alert0>;
+					cooling-device =
+						<&cpu_b0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+	};
+
+	tsadc: tsadc@ff260000 {
+		compatible = "rockchip,rk3399-tsadc";
+		reg = <0x0 0xff260000 0x0 0x100>;
+		interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
+		assigned-clocks = <&cru SCLK_TSADC>;
+		assigned-clock-rates = <750000>;
+		clocks = <&cru SCLK_TSADC>, <&cru PCLK_TSADC>;
+		clock-names = "tsadc", "apb_pclk";
+		resets = <&cru SRST_TSADC>;
+		reset-names = "tsadc-apb";
+		rockchip,grf = <&grf>;
+		rockchip,hw-tshut-temp = <95000>;
+		pinctrl-names = "init", "default", "sleep";
+		pinctrl-0 = <&otp_gpio>;
+		pinctrl-1 = <&otp_out>;
+		pinctrl-2 = <&otp_gpio>;
+		#thermal-sensor-cells = <1>;
+		status = "disabled";
+	};
+
 	pmugrf: syscon@ff320000 {
-		compatible = "rockchip,rk3399-pmugrf", "syscon";
+		compatible = "rockchip,rk3399-pmugrf", "syscon", "simple-mfd";
 		reg = <0x0 0xff320000 0x0 0x1000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		pmu_io_domains: io-domains {
+			compatible = "rockchip,rk3399-pmu-io-voltage-domain";
+			status = "disabled";
+		};
 	};
 
 	spi3: spi@ff350000 {
@@ -420,6 +632,51 @@
 		status = "disabled";
 	};
 
+	i2c0: i2c@ff3c0000 {
+		compatible = "rockchip,rk3399-i2c";
+		reg = <0x0 0xff3c0000 0x0 0x1000>;
+		assigned-clocks = <&pmucru SCLK_I2C0_PMU>;
+		assigned-clock-rates = <200000000>;
+		clocks = <&pmucru SCLK_I2C0_PMU>, <&pmucru PCLK_I2C0_PMU>;
+		clock-names = "i2c", "pclk";
+		interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c0_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c4: i2c@ff3d0000 {
+		compatible = "rockchip,rk3399-i2c";
+		reg = <0x0 0xff3d0000 0x0 0x1000>;
+		assigned-clocks = <&pmucru SCLK_I2C4_PMU>;
+		assigned-clock-rates = <200000000>;
+		clocks = <&pmucru SCLK_I2C4_PMU>, <&pmucru PCLK_I2C4_PMU>;
+		clock-names = "i2c", "pclk";
+		interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c4_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
+	i2c8: i2c@ff3e0000 {
+		compatible = "rockchip,rk3399-i2c";
+		reg = <0x0 0xff3e0000 0x0 0x1000>;
+		assigned-clocks = <&pmucru SCLK_I2C8_PMU>;
+		assigned-clock-rates = <200000000>;
+		clocks = <&pmucru SCLK_I2C8_PMU>, <&pmucru PCLK_I2C8_PMU>;
+		clock-names = "i2c", "pclk";
+		interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&i2c8_xfer>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+	};
+
 	pwm0: pwm@ff420000 {
 		compatible = "rockchip,rk3399-pwm", "rockchip,rk3288-pwm";
 		reg = <0x0 0xff420000 0x0 0x10>;
@@ -478,11 +735,43 @@
 		reg = <0x0 0xff760000 0x0 0x1000>;
 		#clock-cells = <1>;
 		#reset-cells = <1>;
+		assigned-clocks =
+			<&cru PLL_GPLL>, <&cru PLL_CPLL>,
+			<&cru PLL_NPLL>,
+			<&cru ACLK_PERIHP>, <&cru HCLK_PERIHP>,
+			<&cru PCLK_PERIHP>,
+			<&cru ACLK_PERILP0>, <&cru HCLK_PERILP0>,
+			<&cru PCLK_PERILP0>,
+			<&cru HCLK_PERILP1>, <&cru PCLK_PERILP1>;
+		assigned-clock-rates =
+			 <594000000>,  <800000000>,
+			<1000000000>,
+			 <150000000>,   <75000000>,
+			  <37500000>,
+			 <100000000>,  <100000000>,
+			  <50000000>,
+			 <100000000>,   <50000000>;
 	};
 
 	grf: syscon@ff770000 {
-		compatible = "rockchip,rk3399-grf", "syscon";
+		compatible = "rockchip,rk3399-grf", "syscon", "simple-mfd";
 		reg = <0x0 0xff770000 0x0 0x10000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		io_domains: io-domains {
+			compatible = "rockchip,rk3399-io-voltage-domain";
+			status = "disabled";
+		};
+
+		emmc_phy: phy@f780 {
+			compatible = "rockchip,rk3399-emmc-phy";
+			reg = <0xf780 0x24>;
+			clocks = <&sdhci>;
+			clock-names = "emmcclk";
+			#phy-cells = <0>;
+			status = "disabled";
+		};
 	};
 
 	watchdog@ff840000 {
@@ -764,6 +1053,16 @@
 			};
 		};
 
+		sleep {
+			ap_pwroff: ap-pwroff {
+				rockchip,pins = <1 5 RK_FUNC_1 &pcfg_pull_none>;
+			};
+
+			ddrio_pwroff: ddrio-pwroff {
+				rockchip,pins = <0 1 RK_FUNC_1 &pcfg_pull_none>;
+			};
+		};
+
 		spdif {
 			spdif_bus: spdif-bus {
 				rockchip,pins =
@@ -889,6 +1188,16 @@
 			};
 		};
 
+		tsadc {
+			otp_gpio: otp-gpio {
+				rockchip,pins = <1 6 RK_FUNC_GPIO &pcfg_pull_none>;
+			};
+
+			otp_out: otp-out {
+				rockchip,pins = <1 6 RK_FUNC_1 &pcfg_pull_none>;
+			};
+		};
+
 		uart0 {
 			uart0_xfer: uart0-xfer {
 				rockchip,pins =
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi
index 95328808e3c1..c223915f0907 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi
@@ -42,6 +42,8 @@
  *     OTHER DEALINGS IN THE SOFTWARE.
  */
 
+/memreserve/ 0x80000000 0x00000008;	/* cpu-release-addr */
+
 / {
 	compatible = "socionext,ph1-ld20";
 	#address-cells = <2>;
@@ -77,7 +79,7 @@
 			compatible = "arm,cortex-a72", "arm,armv8";
 			reg = <0 0x000>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0 0x80000100>;
+			cpu-release-addr = <0 0x80000000>;
 		};
 
 		cpu1: cpu@1 {
@@ -85,7 +87,7 @@
 			compatible = "arm,cortex-a72", "arm,armv8";
 			reg = <0 0x001>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0 0x80000100>;
+			cpu-release-addr = <0 0x80000000>;
 		};
 
 		cpu2: cpu@100 {
@@ -93,7 +95,7 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0 0x100>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0 0x80000100>;
+			cpu-release-addr = <0 0x80000000>;
 		};
 
 		cpu3: cpu@101 {
@@ -101,7 +103,7 @@
 			compatible = "arm,cortex-a53", "arm,armv8";
 			reg = <0 0x101>;
 			enable-method = "spin-table";
-			cpu-release-addr = <0 0x80000100>;
+			cpu-release-addr = <0 0x80000000>;
 		};
 	};
 
@@ -264,9 +266,13 @@
 			reg = <0x59801000 0x400>;
 		};
 
-		pinctrl: pinctrl@5f801000 {
-			compatible = "socionext,ph1-ld20-pinctrl", "syscon";
-			reg = <0x5f801000 0xe00>;
+		soc-glue@5f800000 {
+			compatible = "simple-mfd", "syscon";
+			reg = <0x5f800000 0x2000>;
+
+			pinctrl: pinctrl {
+				 compatible = "socionext,uniphier-ld20-pinctrl";
+			};
 		};
 
 		gic: interrupt-controller@5fe00000 {
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 4ed4756dfa97..0555b7caaf2c 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -45,6 +45,7 @@ CONFIG_ARCH_ROCKCHIP=y
 CONFIG_ARCH_SEATTLE=y
 CONFIG_ARCH_RENESAS=y
 CONFIG_ARCH_R8A7795=y
+CONFIG_ARCH_R8A7796=y
 CONFIG_ARCH_STRATIX10=y
 CONFIG_ARCH_TEGRA=y
 CONFIG_ARCH_SPRD=y
@@ -63,6 +64,7 @@ CONFIG_PCI_XGENE=y
 CONFIG_PCI_LAYERSCAPE=y
 CONFIG_PCI_HISI=y
 CONFIG_PCIE_QCOM=y
+CONFIG_PCIE_ARMADA_8K=y
 CONFIG_ARM64_VA_BITS_48=y
 CONFIG_SCHED_MC=y
 CONFIG_PREEMPT=y
@@ -102,6 +104,7 @@ CONFIG_MTD_M25P80=y
 CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_VIRTIO_BLK=y
+CONFIG_SRAM=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
 # CONFIG_SCSI_LOWLEVEL is not set
@@ -121,6 +124,7 @@ CONFIG_TUN=y
 CONFIG_VIRTIO_NET=y
 CONFIG_AMD_XGBE=y
 CONFIG_NET_XGENE=y
+CONFIG_MACB=y
 CONFIG_E1000E=y
 CONFIG_IGB=y
 CONFIG_IGBVF=y
@@ -128,6 +132,8 @@ CONFIG_SKY2=y
 CONFIG_RAVB=y
 CONFIG_SMC91X=y
 CONFIG_SMSC911X=y
+CONFIG_STMMAC_ETH=m
+CONFIG_REALTEK_PHY=m
 CONFIG_MICREL_PHY=y
 CONFIG_USB_PEGASUS=m
 CONFIG_USB_RTL8150=m
@@ -143,6 +149,8 @@ CONFIG_WL18XX=m
 CONFIG_WLCORE_SDIO=m
 CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_GPIO=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_PM8941_PWRKEY=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIO_AMBAKMI=y
 CONFIG_LEGACY_PTY_COUNT=16
@@ -179,41 +187,62 @@ CONFIG_I2C_QUP=y
 CONFIG_I2C_TEGRA=y
 CONFIG_I2C_UNIPHIER_F=y
 CONFIG_I2C_RCAR=y
+CONFIG_I2C_CROS_EC_TUNNEL=y
 CONFIG_SPI=y
 CONFIG_SPI_ORION=y
 CONFIG_SPI_PL022=y
 CONFIG_SPI_QUP=y
 CONFIG_SPI_SPIDEV=m
+CONFIG_SPI_S3C64XX=y
 CONFIG_SPMI=y
 CONFIG_PINCTRL_SINGLE=y
+CONFIG_PINCTRL_MAX77620=y
 CONFIG_PINCTRL_MSM8916=y
+CONFIG_PINCTRL_MSM8996=y
 CONFIG_PINCTRL_QCOM_SPMI_PMIC=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_DWAPB=y
 CONFIG_GPIO_PL061=y
 CONFIG_GPIO_RCAR=y
 CONFIG_GPIO_XGENE=y
+CONFIG_GPIO_PCA953X=y
+CONFIG_GPIO_PCA953X_IRQ=y
+CONFIG_GPIO_MAX77620=y
 CONFIG_POWER_RESET_MSM=y
+CONFIG_BATTERY_BQ27XXX=y
 CONFIG_POWER_RESET_XGENE=y
 CONFIG_POWER_RESET_SYSCON=y
 CONFIG_SENSORS_LM90=m
 CONFIG_SENSORS_INA2XX=m
+CONFIG_SENSORS_ARM_SCPI=y
 CONFIG_THERMAL=y
 CONFIG_THERMAL_EMULATION=y
 CONFIG_EXYNOS_THERMAL=y
 CONFIG_WATCHDOG=y
 CONFIG_RENESAS_WDT=y
+CONFIG_S3C2410_WATCHDOG=y
+CONFIG_MFD_MAX77620=y
 CONFIG_MFD_SPMI_PMIC=y
 CONFIG_MFD_SEC_CORE=y
 CONFIG_MFD_HI655X_PMIC=y
 CONFIG_REGULATOR=y
+CONFIG_MFD_CROS_EC=y
+CONFIG_MFD_CROS_EC_I2C=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_HI655X=y
+CONFIG_REGULATOR_MAX77620=y
+CONFIG_REGULATOR_PWM=y
 CONFIG_REGULATOR_QCOM_SMD_RPM=y
 CONFIG_REGULATOR_QCOM_SPMI=y
 CONFIG_REGULATOR_S2MPS11=y
+CONFIG_DRM=m
+CONFIG_DRM_NOUVEAU=m
+CONFIG_DRM_TEGRA=m
+CONFIG_DRM_PANEL_SIMPLE=m
 CONFIG_FB=y
 CONFIG_FB_ARMCLCD=y
+CONFIG_BACKLIGHT_GENERIC=m
+CONFIG_BACKLIGHT_LP855X=m
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
@@ -222,18 +251,23 @@ CONFIG_SOUND=y
 CONFIG_SND=y
 CONFIG_SND_SOC=y
 CONFIG_SND_SOC_RCAR=y
+CONFIG_SND_SOC_SAMSUNG=y
 CONFIG_SND_SOC_AK4613=y
 CONFIG_USB=y
 CONFIG_USB_OTG=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_XHCI_RCAR=y
+CONFIG_USB_EHCI_EXYNOS=y
+CONFIG_USB_XHCI_TEGRA=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_MSM=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_EXYNOS=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_OHCI_HCD_PLATFORM=y
 CONFIG_USB_STORAGE=y
 CONFIG_USB_DWC2=y
+CONFIG_USB_DWC3=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_UDC=y
 CONFIG_USB_CHIPIDEA_HOST=y
@@ -263,12 +297,15 @@ CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_CPU=y
 CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_MAX77686=y
 CONFIG_RTC_DRV_S5M=y
 CONFIG_RTC_DRV_DS3232=y
 CONFIG_RTC_DRV_EFI=y
 CONFIG_RTC_DRV_PL031=y
 CONFIG_RTC_DRV_SUN6I=y
+CONFIG_RTC_DRV_TEGRA=y
 CONFIG_RTC_DRV_XGENE=y
+CONFIG_RTC_DRV_S3C=y
 CONFIG_DMADEVICES=y
 CONFIG_PL330_DMA=y
 CONFIG_TEGRA20_APB_DMA=y
@@ -283,9 +320,11 @@ CONFIG_XEN_GNTDEV=y
 CONFIG_XEN_GRANT_DEV_ALLOC=y
 CONFIG_COMMON_CLK_SCPI=y
 CONFIG_COMMON_CLK_CS2000_CP=y
+CONFIG_COMMON_CLK_S2MPS11=y
 CONFIG_CLK_QORIQ=y
 CONFIG_COMMON_CLK_QCOM=y
 CONFIG_MSM_GCC_8916=y
+CONFIG_MSM_MMCC_8996=y
 CONFIG_HWSPINLOCK_QCOM=y
 CONFIG_MAILBOX=y
 CONFIG_ARM_MHU=y
@@ -297,12 +336,18 @@ CONFIG_QCOM_SMD_RPM=y
 CONFIG_ARCH_TEGRA_132_SOC=y
 CONFIG_ARCH_TEGRA_210_SOC=y
 CONFIG_EXTCON_USB_GPIO=y
+CONFIG_PWM=y
+CONFIG_PWM_TEGRA=m
 CONFIG_COMMON_RESET_HI6220=y
 CONFIG_PHY_RCAR_GEN3_USB2=y
 CONFIG_PHY_HI6220_USB=y
 CONFIG_PHY_XGENE=y
+CONFIG_PHY_TEGRA_XUSB=y
 CONFIG_ARM_SCPI_PROTOCOL=y
 CONFIG_ACPI=y
+CONFIG_IIO=y
+CONFIG_EXYNOS_ADC=y
+CONFIG_PWM_SAMSUNG=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 CONFIG_FANOTIFY=y
@@ -319,6 +364,8 @@ CONFIG_EFIVAR_FS=y
 CONFIG_SQUASHFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
 CONFIG_ROOT_NFS=y
 CONFIG_9P_FS=y
 CONFIG_NLS_CODEPAGE_437=y
@@ -344,5 +391,5 @@ CONFIG_CRYPTO_SHA2_ARM64_CE=y
 CONFIG_CRYPTO_GHASH_ARM64_CE=y
 CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
 CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
-CONFIG_CRYPTO_AES_ARM64_NEON_BLK=y
+# CONFIG_CRYPTO_AES_ARM64_NEON_BLK is not set
 CONFIG_CRYPTO_CRC32_ARM64=y
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 49dd1bd3ea50..7099f26e3702 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -36,8 +36,9 @@
 #define ARM64_HAS_VIRT_HOST_EXTN		11
 #define ARM64_WORKAROUND_CAVIUM_27456		12
 #define ARM64_HAS_32BIT_EL0			13
+#define ARM64_HYP_OFFSET_LOW			14
 
-#define ARM64_NCAPS				14
+#define ARM64_NCAPS				15
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 7dbea6c070ec..ccea82c2b089 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -66,12 +66,16 @@ static inline bool is_device_dma_coherent(struct device *dev)
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	return (dma_addr_t)paddr;
+	dma_addr_t dev_addr = (dma_addr_t)paddr;
+
+	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 }
 
 static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
-	return (phys_addr_t)dev_addr;
+	phys_addr_t paddr = (phys_addr_t)dev_addr;
+
+	return paddr + ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 }
 
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
@@ -86,5 +90,14 @@ static inline void dma_mark_clean(void *addr, size_t size)
 {
 }
 
+/* Override for dma_max_pfn() */
+static inline unsigned long dma_max_pfn(struct device *dev)
+{
+	dma_addr_t dma_max = (dma_addr_t)*dev->dma_mask;
+
+	return (ulong)dma_to_phys(dev, dma_max) >> PAGE_SHIFT;
+}
+#define dma_max_pfn(dev) dma_max_pfn(dev)
+
 #endif	/* __KERNEL__ */
 #endif	/* __ASM_DMA_MAPPING_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 2cdb6b551ac6..4b5c977af465 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -178,7 +178,7 @@
 /* Hyp System Trap Register */
 #define HSTR_EL2_T(x)	(1 << x)
 
-/* Hyp Coproccessor Trap Register Shifts */
+/* Hyp Coprocessor Trap Register Shifts */
 #define CPTR_EL2_TFP_SHIFT 10
 
 /* Hyp Coprocessor Trap Register */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 49095fc4b482..3eda975837d0 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -47,8 +47,7 @@
 
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
-int kvm_arch_dev_ioctl_check_extension(long ext);
-unsigned long kvm_hyp_reset_entry(void);
+int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext);
 void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
 
 struct kvm_arch {
@@ -348,8 +347,7 @@ int kvm_perf_teardown(void);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
 
-static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
-				       phys_addr_t pgd_ptr,
+static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,
 				       unsigned long vector_ptr)
 {
@@ -357,19 +355,14 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 	 * Call initialization code, and switch to the full blown
 	 * HYP code.
 	 */
-	__kvm_call_hyp((void *)boot_pgd_ptr, pgd_ptr,
-		       hyp_stack_ptr, vector_ptr);
+	__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr);
 }
 
-static inline void __cpu_reset_hyp_mode(phys_addr_t boot_pgd_ptr,
+void __kvm_hyp_teardown(void);
+static inline void __cpu_reset_hyp_mode(unsigned long vector_ptr,
 					phys_addr_t phys_idmap_start)
 {
-	/*
-	 * Call reset code, and switch back to stub hyp vectors.
-	 * Uses __kvm_call_hyp() to avoid kaslr's kvm_ksym_ref() translation.
-	 */
-	__kvm_call_hyp((void *)kvm_hyp_reset_entry(),
-		       boot_pgd_ptr, phys_idmap_start);
+	kvm_call_hyp(__kvm_hyp_teardown, phys_idmap_start);
 }
 
 static inline void kvm_arch_hardware_unsetup(void) {}
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 44eaff70da6a..cff510574fae 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -25,29 +25,6 @@
 
 #define __hyp_text __section(.hyp.text) notrace
 
-static inline unsigned long __kern_hyp_va(unsigned long v)
-{
-	asm volatile(ALTERNATIVE("and %0, %0, %1",
-				 "nop",
-				 ARM64_HAS_VIRT_HOST_EXTN)
-		     : "+r" (v) : "i" (HYP_PAGE_OFFSET_MASK));
-	return v;
-}
-
-#define kern_hyp_va(v) (typeof(v))(__kern_hyp_va((unsigned long)(v)))
-
-static inline unsigned long __hyp_kern_va(unsigned long v)
-{
-	u64 offset = PAGE_OFFSET - HYP_PAGE_OFFSET;
-	asm volatile(ALTERNATIVE("add %0, %0, %1",
-				 "nop",
-				 ARM64_HAS_VIRT_HOST_EXTN)
-		     : "+r" (v) : "r" (offset));
-	return v;
-}
-
-#define hyp_kern_va(v) (typeof(v))(__hyp_kern_va((unsigned long)(v)))
-
 #define read_sysreg_elx(r,nvh,vh)					\
 	({								\
 		u64 reg;						\
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index f05ac27d033e..b6bb83400cd8 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -29,21 +29,48 @@
  *
  * Instead, give the HYP mode its own VA region at a fixed offset from
  * the kernel by just masking the top bits (which are all ones for a
- * kernel address).
+ * kernel address). We need to find out how many bits to mask.
  *
- * ARMv8.1 (using VHE) does have a TTBR1_EL2, and doesn't use these
- * macros (the entire kernel runs at EL2).
+ * We want to build a set of page tables that cover both parts of the
+ * idmap (the trampoline page used to initialize EL2), and our normal
+ * runtime VA space, at the same time.
+ *
+ * Given that the kernel uses VA_BITS for its entire address space,
+ * and that half of that space (VA_BITS - 1) is used for the linear
+ * mapping, we can also limit the EL2 space to (VA_BITS - 1).
+ *
+ * The main question is "Within the VA_BITS space, does EL2 use the
+ * top or the bottom half of that space to shadow the kernel's linear
+ * mapping?". As we need to idmap the trampoline page, this is
+ * determined by the range in which this page lives.
+ *
+ * If the page is in the bottom half, we have to use the top half. If
+ * the page is in the top half, we have to use the bottom half:
+ *
+ * T = __virt_to_phys(__hyp_idmap_text_start)
+ * if (T & BIT(VA_BITS - 1))
+ *	HYP_VA_MIN = 0  //idmap in upper half
+ * else
+ *	HYP_VA_MIN = 1 << (VA_BITS - 1)
+ * HYP_VA_MAX = HYP_VA_MIN + (1 << (VA_BITS - 1)) - 1
+ *
+ * This of course assumes that the trampoline page exists within the
+ * VA_BITS range. If it doesn't, then it means we're in the odd case
+ * where the kernel idmap (as well as HYP) uses more levels than the
+ * kernel runtime page tables (as seen when the kernel is configured
+ * for 4k pages, 39bits VA, and yet memory lives just above that
+ * limit, forcing the idmap to use 4 levels of page tables while the
+ * kernel itself only uses 3). In this particular case, it doesn't
+ * matter which side of VA_BITS we use, as we're guaranteed not to
+ * conflict with anything.
+ *
+ * When using VHE, there are no separate hyp mappings and all KVM
+ * functionality is already mapped as part of the main kernel
+ * mappings, and none of this applies in that case.
  */
-#define HYP_PAGE_OFFSET_SHIFT	VA_BITS
-#define HYP_PAGE_OFFSET_MASK	((UL(1) << HYP_PAGE_OFFSET_SHIFT) - 1)
-#define HYP_PAGE_OFFSET		(PAGE_OFFSET & HYP_PAGE_OFFSET_MASK)
 
-/*
- * Our virtual mapping for the idmap-ed MMU-enable code. Must be
- * shared across all the page-tables. Conveniently, we use the last
- * possible page, where no kernel mapping will ever exist.
- */
-#define TRAMPOLINE_VA		(HYP_PAGE_OFFSET_MASK & PAGE_MASK)
+#define HYP_PAGE_OFFSET_HIGH_MASK	((UL(1) << VA_BITS) - 1)
+#define HYP_PAGE_OFFSET_LOW_MASK	((UL(1) << (VA_BITS - 1)) - 1)
 
 #ifdef __ASSEMBLY__
 
@@ -53,13 +80,33 @@
 /*
  * Convert a kernel VA into a HYP VA.
  * reg: VA to be converted.
+ *
+ * This generates the following sequences:
+ * - High mask:
+ *		and x0, x0, #HYP_PAGE_OFFSET_HIGH_MASK
+ *		nop
+ * - Low mask:
+ *		and x0, x0, #HYP_PAGE_OFFSET_HIGH_MASK
+ *		and x0, x0, #HYP_PAGE_OFFSET_LOW_MASK
+ * - VHE:
+ *		nop
+ *		nop
+ *
+ * The "low mask" version works because the mask is a strict subset of
+ * the "high mask", hence performing the first mask for nothing.
+ * Should be completely invisible on any viable CPU.
  */
 .macro kern_hyp_va	reg
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN	
-	and	\reg, \reg, #HYP_PAGE_OFFSET_MASK
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
+	and     \reg, \reg, #HYP_PAGE_OFFSET_HIGH_MASK
 alternative_else
 	nop
 alternative_endif
+alternative_if_not ARM64_HYP_OFFSET_LOW
+	nop
+alternative_else
+	and     \reg, \reg, #HYP_PAGE_OFFSET_LOW_MASK
+alternative_endif
 .endm
 
 #else
@@ -70,7 +117,22 @@ alternative_endif
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 
-#define KERN_TO_HYP(kva)	((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET)
+static inline unsigned long __kern_hyp_va(unsigned long v)
+{
+	asm volatile(ALTERNATIVE("and %0, %0, %1",
+				 "nop",
+				 ARM64_HAS_VIRT_HOST_EXTN)
+		     : "+r" (v)
+		     : "i" (HYP_PAGE_OFFSET_HIGH_MASK));
+	asm volatile(ALTERNATIVE("nop",
+				 "and %0, %0, %1",
+				 ARM64_HYP_OFFSET_LOW)
+		     : "+r" (v)
+		     : "i" (HYP_PAGE_OFFSET_LOW_MASK));
+	return v;
+}
+
+#define kern_hyp_va(v) 	(typeof(v))(__kern_hyp_va((unsigned long)(v)))
 
 /*
  * We currently only support a 40bit IPA.
@@ -81,9 +143,8 @@ alternative_endif
 
 #include <asm/stage2_pgtable.h>
 
-int create_hyp_mappings(void *from, void *to);
+int create_hyp_mappings(void *from, void *to, pgprot_t prot);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
-void free_boot_hyp_pgd(void);
 void free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
@@ -97,7 +158,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
-phys_addr_t kvm_mmu_get_boot_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
 phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 2813748e2f24..c3ae239db3ee 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -164,6 +164,7 @@
 #define PTE_CONT		(_AT(pteval_t, 1) << 52)	/* Contiguous range */
 #define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */
 #define PTE_UXN			(_AT(pteval_t, 1) << 54)	/* User XN */
+#define PTE_HYP_XN		(_AT(pteval_t, 1) << 54)	/* HYP XN */
 
 /*
  * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 29fcb33ab401..39f5252673f7 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -55,7 +55,9 @@
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
-#define PAGE_HYP		__pgprot(_PAGE_DEFAULT | PTE_HYP)
+#define PAGE_HYP		__pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
+#define PAGE_HYP_EXEC		__pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
+#define PAGE_HYP_RO		__pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
 
 #define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index bbc6a8cf83f1..1788545f25bc 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -87,6 +87,10 @@ extern void verify_cpu_run_el(void);
 static inline void verify_cpu_run_el(void) {}
 #endif
 
+/* The section containing the hypervisor idmap text */
+extern char __hyp_idmap_text_start[];
+extern char __hyp_idmap_text_end[];
+
 /* The section containing the hypervisor text */
 extern char __hyp_text_start[];
 extern char __hyp_text_end[];
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index f209ea151dca..3051f86a9b5f 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -87,9 +87,11 @@ struct kvm_regs {
 /* Supported VGICv3 address types  */
 #define KVM_VGIC_V3_ADDR_TYPE_DIST	2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
+#define KVM_VGIC_ITS_ADDR_TYPE		4
 
 #define KVM_VGIC_V3_DIST_SIZE		SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE		(2 * SZ_64K)
 
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 916d27ad79c1..62272eac1352 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -726,6 +726,19 @@ static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused
 	return is_kernel_in_hyp_mode();
 }
 
+static bool hyp_offset_low(const struct arm64_cpu_capabilities *entry,
+			   int __unused)
+{
+	phys_addr_t idmap_addr = virt_to_phys(__hyp_idmap_text_start);
+
+	/*
+	 * Activate the lower HYP offset only if:
+	 * - the idmap doesn't clash with it,
+	 * - the kernel is not running at EL2.
+	 */
+	return idmap_addr > GENMASK(VA_BITS - 2, 0) && !is_kernel_in_hyp_mode();
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
@@ -803,6 +816,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64PFR0_EL0_SHIFT,
 		.min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
 	},
+	{
+		.desc = "Reduced HYP mapping offset",
+		.capability = ARM64_HYP_OFFSET_LOW,
+		.def_scope = SCOPE_SYSTEM,
+		.matches = hyp_offset_low,
+	},
 	{},
 };
 
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index 3c4e308b40a0..acf38722457b 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -17,6 +17,9 @@
 #include <linux/mm.h>
 #include <linux/of_pci.h>
 #include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/pci-ecam.h>
 #include <linux/slab.h>
 
 /*
@@ -36,25 +39,17 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 	return res->start;
 }
 
-/**
- * pcibios_enable_device - Enable I/O and memory.
- * @dev: PCI device to be enabled
- * @mask: bitmask of BARs to enable
- */
-int pcibios_enable_device(struct pci_dev *dev, int mask)
-{
-	if (pci_has_flag(PCI_PROBE_ONLY))
-		return 0;
-
-	return pci_enable_resources(dev, mask);
-}
-
 /*
- * Try to assign the IRQ number from DT when adding a new device
+ * Try to assign the IRQ number when probing a new device
  */
-int pcibios_add_device(struct pci_dev *dev)
+int pcibios_alloc_irq(struct pci_dev *dev)
 {
-	dev->irq = of_irq_parse_and_map_pci(dev, 0, 0);
+	if (acpi_disabled)
+		dev->irq = of_irq_parse_and_map_pci(dev, 0, 0);
+#ifdef CONFIG_ACPI
+	else
+		return acpi_pci_irq_enable(dev);
+#endif
 
 	return 0;
 }
@@ -65,13 +60,21 @@ int pcibios_add_device(struct pci_dev *dev)
 int raw_pci_read(unsigned int domain, unsigned int bus,
 		  unsigned int devfn, int reg, int len, u32 *val)
 {
-	return -ENXIO;
+	struct pci_bus *b = pci_find_bus(domain, bus);
+
+	if (!b)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	return b->ops->read(b, devfn, reg, len, val);
 }
 
 int raw_pci_write(unsigned int domain, unsigned int bus,
 		unsigned int devfn, int reg, int len, u32 val)
 {
-	return -ENXIO;
+	struct pci_bus *b = pci_find_bus(domain, bus);
+
+	if (!b)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	return b->ops->write(b, devfn, reg, len, val);
 }
 
 #ifdef CONFIG_NUMA
@@ -85,10 +88,124 @@ EXPORT_SYMBOL(pcibus_to_node);
 #endif
 
 #ifdef CONFIG_ACPI
-/* Root bridge scanning */
+
+struct acpi_pci_generic_root_info {
+	struct acpi_pci_root_info	common;
+	struct pci_config_window	*cfg;	/* config space mapping */
+};
+
+int acpi_pci_bus_find_domain_nr(struct pci_bus *bus)
+{
+	struct pci_config_window *cfg = bus->sysdata;
+	struct acpi_device *adev = to_acpi_device(cfg->parent);
+	struct acpi_pci_root *root = acpi_driver_data(adev);
+
+	return root->segment;
+}
+
+int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
+{
+	if (!acpi_disabled) {
+		struct pci_config_window *cfg = bridge->bus->sysdata;
+		struct acpi_device *adev = to_acpi_device(cfg->parent);
+		ACPI_COMPANION_SET(&bridge->dev, adev);
+	}
+
+	return 0;
+}
+
+/*
+ * Lookup the bus range for the domain in MCFG, and set up config space
+ * mapping.
+ */
+static struct pci_config_window *
+pci_acpi_setup_ecam_mapping(struct acpi_pci_root *root)
+{
+	struct resource *bus_res = &root->secondary;
+	u16 seg = root->segment;
+	struct pci_config_window *cfg;
+	struct resource cfgres;
+	unsigned int bsz;
+
+	/* Use address from _CBA if present, otherwise lookup MCFG */
+	if (!root->mcfg_addr)
+		root->mcfg_addr = pci_mcfg_lookup(seg, bus_res);
+
+	if (!root->mcfg_addr) {
+		dev_err(&root->device->dev, "%04x:%pR ECAM region not found\n",
+			seg, bus_res);
+		return NULL;
+	}
+
+	bsz = 1 << pci_generic_ecam_ops.bus_shift;
+	cfgres.start = root->mcfg_addr + bus_res->start * bsz;
+	cfgres.end = cfgres.start + resource_size(bus_res) * bsz - 1;
+	cfgres.flags = IORESOURCE_MEM;
+	cfg = pci_ecam_create(&root->device->dev, &cfgres, bus_res,
+			      &pci_generic_ecam_ops);
+	if (IS_ERR(cfg)) {
+		dev_err(&root->device->dev, "%04x:%pR error %ld mapping ECAM\n",
+			seg, bus_res, PTR_ERR(cfg));
+		return NULL;
+	}
+
+	return cfg;
+}
+
+/* release_info: free resources allocated by init_info */
+static void pci_acpi_generic_release_info(struct acpi_pci_root_info *ci)
+{
+	struct acpi_pci_generic_root_info *ri;
+
+	ri = container_of(ci, struct acpi_pci_generic_root_info, common);
+	pci_ecam_free(ri->cfg);
+	kfree(ri);
+}
+
+static struct acpi_pci_root_ops acpi_pci_root_ops = {
+	.release_info = pci_acpi_generic_release_info,
+};
+
+/* Interface called from ACPI code to setup PCI host controller */
 struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 {
-	/* TODO: Should be revisited when implementing PCI on ACPI */
-	return NULL;
+	int node = acpi_get_node(root->device->handle);
+	struct acpi_pci_generic_root_info *ri;
+	struct pci_bus *bus, *child;
+
+	ri = kzalloc_node(sizeof(*ri), GFP_KERNEL, node);
+	if (!ri)
+		return NULL;
+
+	ri->cfg = pci_acpi_setup_ecam_mapping(root);
+	if (!ri->cfg) {
+		kfree(ri);
+		return NULL;
+	}
+
+	acpi_pci_root_ops.pci_ops = &ri->cfg->ops->pci_ops;
+	bus = acpi_pci_root_create(root, &acpi_pci_root_ops, &ri->common,
+				   ri->cfg);
+	if (!bus)
+		return NULL;
+
+	pci_bus_size_bridges(bus);
+	pci_bus_assign_resources(bus);
+
+	list_for_each_entry(child, &bus->children, node)
+		pcie_bus_configure_settings(child);
+
+	return bus;
 }
+
+void pcibios_add_bus(struct pci_bus *bus)
+{
+	acpi_pci_add_bus(bus);
+}
+
+void pcibios_remove_bus(struct pci_bus *bus)
+{
+	acpi_pci_remove_bus(bus);
+}
+
 #endif
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 2981f1bdd073..536dce22fe76 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -39,9 +39,7 @@
 #include <linux/fs.h>
 #include <linux/proc_fs.h>
 #include <linux/memblock.h>
-#include <linux/of_iommu.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 #include <linux/efi.h>
 #include <linux/psci.h>
 
@@ -303,19 +301,6 @@ void __init setup_arch(char **cmdline_p)
 	}
 }
 
-static int __init arm64_device_init(void)
-{
-	if (of_have_populated_dt()) {
-		of_iommu_init();
-		of_platform_populate(NULL, of_default_bus_match_table,
-				     NULL, NULL);
-	} else if (acpi_disabled) {
-		pr_crit("Device tree not populated\n");
-	}
-	return 0;
-}
-arch_initcall_sync(arm64_device_init);
-
 static int __init topology_init(void)
 {
 	int i;
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index c4f26ef91e77..9d2eff0b3ad3 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -36,6 +36,7 @@ config KVM
 	select HAVE_KVM_IRQFD
 	select KVM_ARM_VGIC_V3
 	select KVM_ARM_PMU if HW_PERF_EVENTS
+	select HAVE_KVM_MSI
 	---help---
 	  Support hosting virtualized guest machines.
 	  We don't support KVM with 16K page tables yet, due to the multiple
@@ -54,13 +55,6 @@ config KVM_ARM_PMU
 	  Adds support for a virtual Performance Monitoring Unit (PMU) in
 	  virtual machines.
 
-config KVM_NEW_VGIC
-	bool "New VGIC implementation"
-	depends on KVM
-	default y
-        ---help---
-          uses the new VGIC implementation
-
 source drivers/vhost/Kconfig
 
 endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index a7a958ca29d5..a5b96642a9cb 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -20,7 +20,6 @@ kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o
 kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
 kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o
 
-ifeq ($(CONFIG_KVM_NEW_VGIC),y)
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-init.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-irqfd.o
@@ -30,12 +29,6 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v2.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v3.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-kvm-device.o
-else
-kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o
-kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o
-kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o
-kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o
-kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o
-endif
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-its.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
 kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 32fad75bb9ff..3f9e15722473 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -211,7 +211,7 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 /**
  * kvm_arm_copy_reg_indices - get indices of all registers.
  *
- * We do core registers right here, then we apppend system regs.
+ * We do core registers right here, then we append system regs.
  */
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index a873a6d8be90..6b29d3d9e1f2 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -53,10 +53,9 @@ __invalid:
 	b	.
 
 	/*
-	 * x0: HYP boot pgd
-	 * x1: HYP pgd
-	 * x2: HYP stack
-	 * x3: HYP vectors
+	 * x0: HYP pgd
+	 * x1: HYP stack
+	 * x2: HYP vectors
 	 */
 __do_hyp_init:
 
@@ -110,71 +109,27 @@ __do_hyp_init:
 	msr	sctlr_el2, x4
 	isb
 
-	/* Skip the trampoline dance if we merged the boot and runtime PGDs */
-	cmp	x0, x1
-	b.eq	merged
-
-	/* MMU is now enabled. Get ready for the trampoline dance */
-	ldr	x4, =TRAMPOLINE_VA
-	adr	x5, target
-	bfi	x4, x5, #0, #PAGE_SHIFT
-	br	x4
-
-target: /* We're now in the trampoline code, switch page tables */
-	msr	ttbr0_el2, x1
-	isb
-
-	/* Invalidate the old TLBs */
-	tlbi	alle2
-	dsb	sy
-
-merged:
 	/* Set the stack and new vectors */
+	kern_hyp_va	x1
+	mov	sp, x1
 	kern_hyp_va	x2
-	mov	sp, x2
-	kern_hyp_va	x3
-	msr	vbar_el2, x3
+	msr	vbar_el2, x2
 
 	/* Hello, World! */
 	eret
 ENDPROC(__kvm_hyp_init)
 
 	/*
-	 * Reset kvm back to the hyp stub. This is the trampoline dance in
-	 * reverse. If kvm used an extended idmap, __extended_idmap_trampoline
-	 * calls this code directly in the idmap. In this case switching to the
-	 * boot tables is a no-op.
-	 *
-	 * x0: HYP boot pgd
-	 * x1: HYP phys_idmap_start
+	 * Reset kvm back to the hyp stub.
 	 */
 ENTRY(__kvm_hyp_reset)
-	/* We're in trampoline code in VA, switch back to boot page tables */
-	msr	ttbr0_el2, x0
-	isb
-
-	/* Ensure the PA branch doesn't find a stale tlb entry or stale code. */
-	ic	iallu
-	tlbi	alle2
-	dsb	sy
-	isb
-
-	/* Branch into PA space */
-	adr	x0, 1f
-	bfi	x1, x0, #0, #PAGE_SHIFT
-	br	x1
-
 	/* We're now in idmap, disable MMU */
-1:	mrs	x0, sctlr_el2
+	mrs	x0, sctlr_el2
 	ldr	x1, =SCTLR_ELx_FLAGS
 	bic	x0, x0, x1		// Clear SCTL_M and etc
 	msr	sctlr_el2, x0
 	isb
 
-	/* Invalidate the old TLBs */
-	tlbi	alle2
-	dsb	sy
-
 	/* Install stub vectors */
 	adr_l	x0, __hyp_stub_vectors
 	msr	vbar_el2, x0
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index 70254a65bd5b..ce9e5e5f28cf 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -164,22 +164,3 @@ alternative_endif
 
 	eret
 ENDPROC(__fpsimd_guest_restore)
-
-/*
- * When using the extended idmap, we don't have a trampoline page we can use
- * while we switch pages tables during __kvm_hyp_reset. Accessing the idmap
- * directly would be ideal, but if we're using the extended idmap then the
- * idmap is located above HYP_PAGE_OFFSET, and the address will be masked by
- * kvm_call_hyp using kern_hyp_va.
- *
- * x0: HYP boot pgd
- * x1: HYP phys_idmap_start
- */
-ENTRY(__extended_idmap_trampoline)
-	mov	x4, x1
-	adr_l	x3, __kvm_hyp_reset
-
-	/* insert __kvm_hyp_reset()s offset into phys_idmap_start */
-	bfi	x4, x3, #0, #PAGE_SHIFT
-	br	x4
-ENDPROC(__extended_idmap_trampoline)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 2d87f36d5cb4..f6d9694ae3b1 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -62,6 +62,21 @@ ENTRY(__vhe_hyp_call)
 	isb
 	ret
 ENDPROC(__vhe_hyp_call)
+
+/*
+ * Compute the idmap address of __kvm_hyp_reset based on the idmap
+ * start passed as a parameter, and jump there.
+ *
+ * x0: HYP phys_idmap_start
+ */
+ENTRY(__kvm_hyp_teardown)
+	mov	x4, x0
+	adr_l	x3, __kvm_hyp_reset
+
+	/* insert __kvm_hyp_reset()s offset into phys_idmap_start */
+	bfi	x4, x3, #0, #PAGE_SHIFT
+	br	x4
+ENDPROC(__kvm_hyp_teardown)
 	
 el1_sync:				// Guest trapped into EL2
 	save_x0_to_x3
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 4373997d1a70..ae7855f16ec2 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -299,9 +299,16 @@ static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%
 
 static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par)
 {
-	unsigned long str_va = (unsigned long)__hyp_panic_string;
+	unsigned long str_va;
 
-	__hyp_do_panic(hyp_kern_va(str_va),
+	/*
+	 * Force the panic string to be loaded from the literal pool,
+	 * making sure it is a kernel address and not a PC-relative
+	 * reference.
+	 */
+	asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va));
+
+	__hyp_do_panic(str_va,
 		       spsr,  elr,
 		       read_sysreg(esr_el2),   read_sysreg_el2(far),
 		       read_sysreg(hpfar_el2), par,
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index b1ad730e1567..5bc460884639 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -65,7 +65,7 @@ static bool cpu_has_32bit_el1(void)
  * We currently assume that the number of HW registers is uniform
  * across all CPUs (see cpuinfo_sanity_check).
  */
-int kvm_arch_dev_ioctl_check_extension(long ext)
+int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r;
 
@@ -86,6 +86,12 @@ int kvm_arch_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_VCPU_ATTRIBUTES:
 		r = 1;
 		break;
+	case KVM_CAP_MSI_DEVID:
+		if (!kvm)
+			r = -EINVAL;
+		else
+			r = kvm->arch.vgic.msis_require_devid;
+		break;
 	default:
 		r = 0;
 	}
@@ -98,7 +104,7 @@ int kvm_arch_dev_ioctl_check_extension(long ext)
  * @vcpu: The VCPU pointer
  *
  * This function finds the right table above and sets the registers on
- * the virtual CPU struct to their architectually defined reset
+ * the virtual CPU struct to their architecturally defined reset
  * values.
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
@@ -132,31 +138,3 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	/* Reset timer */
 	return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq);
 }
-
-extern char __hyp_idmap_text_start[];
-
-unsigned long kvm_hyp_reset_entry(void)
-{
-	if (!__kvm_cpu_uses_extended_idmap()) {
-		unsigned long offset;
-
-		/*
-		 * Find the address of __kvm_hyp_reset() in the trampoline page.
-		 * This is present in the running page tables, and the boot page
-		 * tables, so we call the code here to start the trampoline
-		 * dance in reverse.
-		 */
-		offset = (unsigned long)__kvm_hyp_reset
-			 - ((unsigned long)__hyp_idmap_text_start & PAGE_MASK);
-
-		return TRAMPOLINE_VA + offset;
-	} else {
-		/*
-		 * KVM is running with merged page tables, which don't have the
-		 * trampoline page mapped. We know the idmap is still mapped,
-		 * but can't be called into directly. Use
-		 * __extended_idmap_trampoline to do the call.
-		 */
-		return (unsigned long)kvm_ksym_ref(__extended_idmap_trampoline);
-	}
-}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index a57d650f552c..b0b225ceca18 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1546,7 +1546,7 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
 				struct sys_reg_params *params)
 {
 	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
-	int cp;
+	int cp = -1;
 
 	switch(hsr_ec) {
 	case ESR_ELx_EC_CP15_32:
@@ -1558,7 +1558,7 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
 		cp = 14;
 		break;
 	default:
-		WARN_ON((cp = -1));
+		WARN_ON(1);
 	}
 
 	kvm_err("Unsupported guest CP%d access at: %08lx\n",
diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c
index 166842de3dc7..b59cd7c3261a 100644
--- a/arch/blackfin/mm/init.c
+++ b/arch/blackfin/mm/init.c
@@ -112,7 +112,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
-void __init_refok free_initmem(void)
+void __ref free_initmem(void)
 {
 #if defined CONFIG_RAMKERNEL && !defined CONFIG_MPU
 	free_initmem_default(-1);
diff --git a/arch/c6x/platforms/Makefile b/arch/c6x/platforms/Makefile
index 9a95b9bca8d0..5f7d93468b6e 100644
--- a/arch/c6x/platforms/Makefile
+++ b/arch/c6x/platforms/Makefile
@@ -4,7 +4,7 @@
 # Copyright 2010, 2011 Texas Instruments Incorporated
 #
 
-obj-y = platform.o cache.o megamod-pic.o pll.o plldata.o timer64.o
+obj-y = cache.o megamod-pic.o pll.o plldata.o timer64.o
 obj-y += dscr.o
 
 # SoC objects
diff --git a/arch/c6x/platforms/platform.c b/arch/c6x/platforms/platform.c
deleted file mode 100644
index 26c1a355d600..000000000000
--- a/arch/c6x/platforms/platform.c
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * Copyright 2011 Texas Instruments Incorporated
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#include <linux/init.h>
-#include <linux/of_platform.h>
-
-static int __init c6x_device_probe(void)
-{
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-	return 0;
-}
-core_initcall(c6x_device_probe);
diff --git a/arch/cris/arch-v10/drivers/axisflashmap.c b/arch/cris/arch-v10/drivers/axisflashmap.c
index 60d57c590032..bdc25aa43468 100644
--- a/arch/cris/arch-v10/drivers/axisflashmap.c
+++ b/arch/cris/arch-v10/drivers/axisflashmap.c
@@ -397,7 +397,7 @@ static int __init init_axis_flash(void)
 	if (!romfs_in_flash) {
 		/* Create an RAM device for the root partition (romfs). */
 
-#if !defined(CONFIG_MTD_MTDRAM) || (CONFIG_MTDRAM_TOTAL_SIZE != 0) || (CONFIG_MTDRAM_ABS_POS != 0)
+#if !defined(CONFIG_MTD_MTDRAM) || (CONFIG_MTDRAM_TOTAL_SIZE != 0)
 		/* No use trying to boot this kernel from RAM. Panic! */
 		printk(KERN_EMERG "axisflashmap: Cannot create an MTD RAM "
 		       "device due to kernel (mis)configuration!\n");
diff --git a/arch/cris/arch-v32/drivers/axisflashmap.c b/arch/cris/arch-v32/drivers/axisflashmap.c
index bd10d3ba0949..87656c41fec7 100644
--- a/arch/cris/arch-v32/drivers/axisflashmap.c
+++ b/arch/cris/arch-v32/drivers/axisflashmap.c
@@ -320,7 +320,7 @@ static int __init init_axis_flash(void)
 	 * but its size must be configured as 0 so as not to conflict
 	 * with our usage.
 	 */
-#if !defined(CONFIG_MTD_MTDRAM) || (CONFIG_MTDRAM_TOTAL_SIZE != 0) || (CONFIG_MTDRAM_ABS_POS != 0)
+#if !defined(CONFIG_MTD_MTDRAM) || (CONFIG_MTDRAM_TOTAL_SIZE != 0)
 	if (!romfs_in_flash && !nand_boot) {
 		printk(KERN_EMERG "axisflashmap: Cannot create an MTD RAM "
 		       "device; configure CONFIG_MTD_MTDRAM with size = 0!\n");
diff --git a/arch/cris/kernel/setup.c b/arch/cris/kernel/setup.c
index bb12aa93201d..4b4853d914e2 100644
--- a/arch/cris/kernel/setup.c
+++ b/arch/cris/kernel/setup.c
@@ -21,7 +21,6 @@
 #include <linux/cpu.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 #include <asm/setup.h>
 #include <arch/system.h>
 
@@ -212,10 +211,3 @@ static int __init topology_init(void)
 }
 
 subsys_initcall(topology_init);
-
-static int __init cris_of_init(void)
-{
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-	return 0;
-}
-core_initcall(cris_of_init);
diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c
index 88977e42af0a..192584d5ac2f 100644
--- a/arch/hexagon/mm/init.c
+++ b/arch/hexagon/mm/init.c
@@ -93,7 +93,7 @@ void __init mem_init(void)
  * Todo:  free pages between __init_begin and __init_end; possibly
  * some devtree related stuff as well.
  */
-void __init_refok free_initmem(void)
+void __ref free_initmem(void)
 {
 }
 
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index d1212b84fb83..29bd59790d6c 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -121,32 +121,4 @@ struct thread_info {
 /* like TIF_ALLWORK_BITS but sans TIF_SYSCALL_TRACE or TIF_SYSCALL_AUDIT */
 #define TIF_WORK_MASK		(TIF_ALLWORK_MASK&~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT))
 
-#define TS_RESTORE_SIGMASK	2	/* restore signal mask in do_signal() */
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	WARN_ON(!test_bit(TIF_SIGPENDING, &ti->flags));
-}
-static inline void clear_restore_sigmask(void)
-{
-	current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-}
-static inline bool test_restore_sigmask(void)
-{
-	return current_thread_info()->status & TS_RESTORE_SIGMASK;
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	if (!(ti->status & TS_RESTORE_SIGMASK))
-		return false;
-	ti->status &= ~TS_RESTORE_SIGMASK;
-	return true;
-}
-#endif	/* !__ASSEMBLY__ */
-
 #endif /* _ASM_IA64_THREAD_INFO_H */
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index 3b7a60e40e8a..121295637d0d 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -236,7 +236,7 @@ STUB_GET_NEXT_HIGH_MONO_COUNT(virt, id)
 STUB_RESET_SYSTEM(virt, id)
 
 void
-efi_gettimeofday (struct timespec *ts)
+efi_gettimeofday (struct timespec64 *ts)
 {
 	efi_time_t tm;
 
@@ -245,7 +245,7 @@ efi_gettimeofday (struct timespec *ts)
 		return;
 	}
 
-	ts->tv_sec = mktime(tm.year, tm.month, tm.day,
+	ts->tv_sec = mktime64(tm.year, tm.month, tm.day,
 			    tm.hour, tm.minute, tm.second);
 	ts->tv_nsec = tm.nanosecond;
 }
diff --git a/arch/ia64/kernel/machine_kexec.c b/arch/ia64/kernel/machine_kexec.c
index b72cd7a07222..599507bcec91 100644
--- a/arch/ia64/kernel/machine_kexec.c
+++ b/arch/ia64/kernel/machine_kexec.c
@@ -163,7 +163,7 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 }
 
-unsigned long paddr_vmcoreinfo_note(void)
+phys_addr_t paddr_vmcoreinfo_note(void)
 {
 	return ia64_tpa((unsigned long)(char *)&vmcoreinfo_note);
 }
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 07a4e32ae96a..eb9220cde76c 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1831,7 +1831,7 @@ format_mca_init_stack(void *mca_data, unsigned long offset,
 }
 
 /* Caller prevents this from being called after init */
-static void * __init_refok mca_bootmem(void)
+static void * __ref mca_bootmem(void)
 {
 	return __alloc_bootmem(sizeof(struct ia64_mca_cpu),
 	                    KERNEL_STACK_SIZE, 0);
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index 1eeffb7fbb16..5313007d5423 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -141,7 +141,7 @@ enum salinfo_state {
 
 struct salinfo_data {
 	cpumask_t		cpu_event;	/* which cpus have outstanding events */
-	struct semaphore	mutex;
+	wait_queue_head_t	read_wait;
 	u8			*log_buffer;
 	u64			log_size;
 	u8			*oemdata;	/* decoded oem data */
@@ -182,21 +182,6 @@ struct salinfo_platform_oemdata_parms {
 	int ret;
 };
 
-/* Kick the mutex that tells user space that there is work to do.  Instead of
- * trying to track the state of the mutex across multiple cpus, in user
- * context, interrupt context, non-maskable interrupt context and hotplug cpu,
- * it is far easier just to grab the mutex if it is free then release it.
- *
- * This routine must be called with data_saved_lock held, to make the down/up
- * operation atomic.
- */
-static void
-salinfo_work_to_do(struct salinfo_data *data)
-{
-	(void)(down_trylock(&data->mutex) ?: 0);
-	up(&data->mutex);
-}
-
 static void
 salinfo_platform_oemdata_cpu(void *context)
 {
@@ -258,7 +243,7 @@ salinfo_log_wakeup(int type, u8 *buffer, u64 size, int irqsafe)
 	}
 	cpumask_set_cpu(smp_processor_id(), &data->cpu_event);
 	if (irqsafe) {
-		salinfo_work_to_do(data);
+		wake_up_interruptible(&data->read_wait);
 		spin_unlock_irqrestore(&data_saved_lock, flags);
 	}
 }
@@ -271,14 +256,10 @@ extern void ia64_mlogbuf_dump(void);
 static void
 salinfo_timeout_check(struct salinfo_data *data)
 {
-	unsigned long flags;
 	if (!data->open)
 		return;
-	if (!cpumask_empty(&data->cpu_event)) {
-		spin_lock_irqsave(&data_saved_lock, flags);
-		salinfo_work_to_do(data);
-		spin_unlock_irqrestore(&data_saved_lock, flags);
-	}
+	if (!cpumask_empty(&data->cpu_event))
+		wake_up_interruptible(&data->read_wait);
 }
 
 static void
@@ -308,10 +289,11 @@ salinfo_event_read(struct file *file, char __user *buffer, size_t count, loff_t
 	int i, n, cpu = -1;
 
 retry:
-	if (cpumask_empty(&data->cpu_event) && down_trylock(&data->mutex)) {
+	if (cpumask_empty(&data->cpu_event)) {
 		if (file->f_flags & O_NONBLOCK)
 			return -EAGAIN;
-		if (down_interruptible(&data->mutex))
+		if (wait_event_interruptible(data->read_wait,
+					     !cpumask_empty(&data->cpu_event)))
 			return -EINTR;
 	}
 
@@ -510,7 +492,7 @@ salinfo_log_clear(struct salinfo_data *data, int cpu)
 	if (data->state == STATE_LOG_RECORD) {
 		spin_lock_irqsave(&data_saved_lock, flags);
 		cpumask_set_cpu(cpu, &data->cpu_event);
-		salinfo_work_to_do(data);
+		wake_up_interruptible(&data->read_wait);
 		spin_unlock_irqrestore(&data_saved_lock, flags);
 	}
 	return 0;
@@ -582,7 +564,7 @@ salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu
 		     i < ARRAY_SIZE(salinfo_data);
 		     ++i, ++data) {
 			cpumask_set_cpu(cpu, &data->cpu_event);
-			salinfo_work_to_do(data);
+			wake_up_interruptible(&data->read_wait);
 		}
 		spin_unlock_irqrestore(&data_saved_lock, flags);
 		break;
@@ -640,7 +622,7 @@ salinfo_init(void)
 	for (i = 0; i < ARRAY_SIZE(salinfo_log_name); i++) {
 		data = salinfo_data + i;
 		data->type = i;
-		sema_init(&data->mutex, 1);
+		init_waitqueue_head(&data->read_wait);
 		dir = proc_mkdir(salinfo_log_name[i], salinfo_dir);
 		if (!dir)
 			continue;
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index c8dbe2acd735..6f892b94e906 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -355,7 +355,7 @@ static struct irqaction timer_irqaction = {
 	.name =		"timer"
 };
 
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
 {
 	efi_gettimeofday(ts);
 }
diff --git a/arch/metag/kernel/setup.c b/arch/metag/kernel/setup.c
index 31cf53d0eba2..1166f1fbfd63 100644
--- a/arch/metag/kernel/setup.c
+++ b/arch/metag/kernel/setup.c
@@ -20,7 +20,6 @@
 #include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 #include <linux/pfn.h>
 #include <linux/root_dev.h>
 #include <linux/sched.h>
@@ -414,9 +413,7 @@ static int __init customize_machine(void)
 	/* customizes platform devices, or adds new ones */
 	if (machine_desc->init_machine)
 		machine_desc->init_machine();
-	else
-		of_platform_populate(NULL, of_default_bus_match_table, NULL,
-				     NULL);
+
 	return 0;
 }
 arch_initcall(customize_machine);
diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h
index fc3ecb55f1b2..2a120bb70e54 100644
--- a/arch/microblaze/include/asm/pci.h
+++ b/arch/microblaze/include/asm/pci.h
@@ -82,9 +82,6 @@ extern pgprot_t	pci_phys_mem_access_prot(struct file *file,
 					 pgprot_t prot);
 
 #define HAVE_ARCH_PCI_RESOURCE_TO_USER
-extern void pci_resource_to_user(const struct pci_dev *dev, int bar,
-				 const struct resource *rsrc,
-				 resource_size_t *start, resource_size_t *end);
 
 extern void pcibios_setup_bus_devices(struct pci_bus *bus);
 extern void pcibios_setup_bus_self(struct pci_bus *bus);
diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h
index 383f387b4eee..e7e8954e9815 100644
--- a/arch/microblaze/include/asm/thread_info.h
+++ b/arch/microblaze/include/asm/thread_info.h
@@ -148,33 +148,6 @@ static inline struct thread_info *current_thread_info(void)
  */
 /* FPU was used by this task this quantum (SMP) */
 #define TS_USEDFPU		0x0001
-#define TS_RESTORE_SIGMASK	0x0002
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK 1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	WARN_ON(!test_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags));
-}
-static inline void clear_restore_sigmask(void)
-{
-	current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-}
-static inline bool test_restore_sigmask(void)
-{
-	return current_thread_info()->status & TS_RESTORE_SIGMASK;
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	if (!(ti->status & TS_RESTORE_SIGMASK))
-		return false;
-	ti->status &= ~TS_RESTORE_SIGMASK;
-	return true;
-}
-#endif
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_MICROBLAZE_THREAD_INFO_H */
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 77bc7c7e6522..434639f9a3a6 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -414,7 +414,7 @@ void __init *early_get_page(void)
 
 #endif /* CONFIG_MMU */
 
-void * __init_refok alloc_maybe_bootmem(size_t size, gfp_t mask)
+void * __ref alloc_maybe_bootmem(size_t size, gfp_t mask)
 {
 	if (mem_init_done)
 		return kmalloc(size, mask);
@@ -422,7 +422,7 @@ void * __init_refok alloc_maybe_bootmem(size_t size, gfp_t mask)
 		return alloc_bootmem(size);
 }
 
-void * __init_refok zalloc_maybe_bootmem(size_t size, gfp_t mask)
+void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask)
 {
 	void *p;
 
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index eb99fcc76088..cc732fe357ad 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -234,7 +234,7 @@ unsigned long iopa(unsigned long addr)
 	return pa;
 }
 
-__init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+__ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 		unsigned long address)
 {
 	pte_t *pte;
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 14cba600da7a..81556b843a8e 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -219,33 +219,6 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 }
 
 /*
- * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
- * device mapping.
- */
-static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
-				      pgprot_t protection,
-				      enum pci_mmap_state mmap_state,
-				      int write_combine)
-{
-	pgprot_t prot = protection;
-
-	/* Write combine is always 0 on non-memory space mappings. On
-	 * memory space, if the user didn't pass 1, we check for a
-	 * "prefetchable" resource. This is a bit hackish, but we use
-	 * this to workaround the inability of /sysfs to provide a write
-	 * combine bit
-	 */
-	if (mmap_state != pci_mmap_mem)
-		write_combine = 0;
-	else if (write_combine == 0) {
-		if (rp->flags & IORESOURCE_PREFETCH)
-			write_combine = 1;
-	}
-
-	return pgprot_noncached(prot);
-}
-
-/*
  * This one is used by /dev/mem and fbdev who have no clue about the
  * PCI device, it tries to find the PCI device first and calls the
  * above routine
@@ -317,9 +290,7 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		return -EINVAL;
 
 	vma->vm_pgoff = offset >> PAGE_SHIFT;
-	vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
-						  vma->vm_page_prot,
-						  mmap_state, write_combine);
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
 	ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
 			       vma->vm_end - vma->vm_start, vma->vm_page_prot);
@@ -473,39 +444,25 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 			  const struct resource *rsrc,
 			  resource_size_t *start, resource_size_t *end)
 {
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	resource_size_t offset = 0;
+	struct pci_bus_region region;
 
-	if (hose == NULL)
+	if (rsrc->flags & IORESOURCE_IO) {
+		pcibios_resource_to_bus(dev->bus, &region,
+					(struct resource *) rsrc);
+		*start = region.start;
+		*end = region.end;
 		return;
+	}
 
-	if (rsrc->flags & IORESOURCE_IO)
-		offset = (unsigned long)hose->io_base_virt - _IO_BASE;
-
-	/* We pass a fully fixed up address to userland for MMIO instead of
-	 * a BAR value because X is lame and expects to be able to use that
-	 * to pass to /dev/mem !
+	/* We pass a CPU physical address to userland for MMIO instead of a
+	 * BAR value because X is lame and expects to be able to use that
+	 * to pass to /dev/mem!
 	 *
-	 * That means that we'll have potentially 64 bits values where some
-	 * userland apps only expect 32 (like X itself since it thinks only
-	 * Sparc has 64 bits MMIO) but if we don't do that, we break it on
-	 * 32 bits CHRPs :-(
-	 *
-	 * Hopefully, the sysfs insterface is immune to that gunk. Once X
-	 * has been fixed (and the fix spread enough), we can re-enable the
-	 * 2 lines below and pass down a BAR value to userland. In that case
-	 * we'll also have to re-enable the matching code in
-	 * __pci_mmap_make_offset().
-	 *
-	 * BenH.
+	 * That means we may have 64-bit values where some apps only expect
+	 * 32 (like X itself since it thinks only Sparc has 64-bit MMIO).
 	 */
-#if 0
-	else if (rsrc->flags & IORESOURCE_MEM)
-		offset = hose->pci_mem_offset;
-#endif
-
-	*start = rsrc->start - offset;
-	*end = rsrc->end - offset;
+	*start = rsrc->start;
+	*end = rsrc->end;
 }
 
 /**
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index ac91939b9b75..29867139851e 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1488,6 +1488,7 @@ config CPU_MIPS64_R2
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
 	select CPU_SUPPORTS_MSA
+	select HAVE_KVM
 	help
 	  Choose this option to build a kernel for release 2 or later of the
 	  MIPS64 architecture.  Many modern embedded systems with a 64-bit
@@ -1505,6 +1506,7 @@ config CPU_MIPS64_R6
 	select CPU_SUPPORTS_MSA
 	select GENERIC_CSUM
 	select MIPS_O32_FP64_SUPPORT if MIPS32_O32
+	select HAVE_KVM
 	help
 	  Choose this option to build a kernel for release 6 or later of the
 	  MIPS64 architecture.  New MIPS processors, starting with the Warrior
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 7adab180e0ca..3a0019deb7f7 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -18,7 +18,6 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
-#include <linux/of_platform.h>
 #include <linux/of_fdt.h>
 
 #include <asm/bootinfo.h>
@@ -285,7 +284,6 @@ void __init plat_time_init(void)
 
 static int __init ath79_setup(void)
 {
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	if  (mips_machtype == ATH79_MACH_GENERIC_OF)
 		return 0;
 
diff --git a/arch/mips/include/asm/addrspace.h b/arch/mips/include/asm/addrspace.h
index 3b0e51d5a613..c5b04e752e97 100644
--- a/arch/mips/include/asm/addrspace.h
+++ b/arch/mips/include/asm/addrspace.h
@@ -45,7 +45,7 @@
 /*
  * Returns the kernel segment base of a given address
  */
-#define KSEGX(a)		((_ACAST32_ (a)) & 0xe0000000)
+#define KSEGX(a)		((_ACAST32_(a)) & _ACAST32_(0xe0000000))
 
 /*
  * Returns the physical address of a CKSEGx / XKPHYS address
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 36a391d289aa..b54bcadd8aec 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -19,6 +19,9 @@
 #include <linux/threads.h>
 #include <linux/spinlock.h>
 
+#include <asm/inst.h>
+#include <asm/mipsregs.h>
+
 /* MIPS KVM register ids */
 #define MIPS_CP0_32(_R, _S)					\
 	(KVM_REG_MIPS_CP0 | KVM_REG_SIZE_U32 | (8 * (_R) + (_S)))
@@ -53,6 +56,12 @@
 #define KVM_REG_MIPS_CP0_CONFIG7	MIPS_CP0_32(16, 7)
 #define KVM_REG_MIPS_CP0_XCONTEXT	MIPS_CP0_64(20, 0)
 #define KVM_REG_MIPS_CP0_ERROREPC	MIPS_CP0_64(30, 0)
+#define KVM_REG_MIPS_CP0_KSCRATCH1	MIPS_CP0_64(31, 2)
+#define KVM_REG_MIPS_CP0_KSCRATCH2	MIPS_CP0_64(31, 3)
+#define KVM_REG_MIPS_CP0_KSCRATCH3	MIPS_CP0_64(31, 4)
+#define KVM_REG_MIPS_CP0_KSCRATCH4	MIPS_CP0_64(31, 5)
+#define KVM_REG_MIPS_CP0_KSCRATCH5	MIPS_CP0_64(31, 6)
+#define KVM_REG_MIPS_CP0_KSCRATCH6	MIPS_CP0_64(31, 7)
 
 
 #define KVM_MAX_VCPUS		1
@@ -65,8 +74,14 @@
 
 
 
-/* Special address that contains the comm page, used for reducing # of traps */
-#define KVM_GUEST_COMMPAGE_ADDR		0x0
+/*
+ * Special address that contains the comm page, used for reducing # of traps
+ * This needs to be within 32Kb of 0x0 (so the zero register can be used), but
+ * preferably not at 0x0 so that most kernel NULL pointer dereferences can be
+ * caught.
+ */
+#define KVM_GUEST_COMMPAGE_ADDR		((PAGE_SIZE > 0x8000) ?	0 : \
+					 (0x8000 - PAGE_SIZE))
 
 #define KVM_GUEST_KERNEL_MODE(vcpu)	((kvm_read_c0_guest_status(vcpu->arch.cop0) & (ST0_EXL | ST0_ERL)) || \
 					((kvm_read_c0_guest_status(vcpu->arch.cop0) & KSU_USER) == 0))
@@ -93,9 +108,6 @@
 #define KVM_INVALID_ADDR		0xdeadbeef
 
 extern atomic_t kvm_mips_instance;
-extern kvm_pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn);
-extern void (*kvm_mips_release_pfn_clean)(kvm_pfn_t pfn);
-extern bool (*kvm_mips_is_error_pfn)(kvm_pfn_t pfn);
 
 struct kvm_vm_stat {
 	u32 remote_tlb_flush;
@@ -126,28 +138,6 @@ struct kvm_vcpu_stat {
 	u32 halt_wakeup;
 };
 
-enum kvm_mips_exit_types {
-	WAIT_EXITS,
-	CACHE_EXITS,
-	SIGNAL_EXITS,
-	INT_EXITS,
-	COP_UNUSABLE_EXITS,
-	TLBMOD_EXITS,
-	TLBMISS_LD_EXITS,
-	TLBMISS_ST_EXITS,
-	ADDRERR_ST_EXITS,
-	ADDRERR_LD_EXITS,
-	SYSCALL_EXITS,
-	RESVD_INST_EXITS,
-	BREAK_INST_EXITS,
-	TRAP_INST_EXITS,
-	MSA_FPE_EXITS,
-	FPE_EXITS,
-	MSA_DISABLED_EXITS,
-	FLUSH_DCACHE_EXITS,
-	MAX_KVM_MIPS_EXIT_TYPES
-};
-
 struct kvm_arch_memory_slot {
 };
 
@@ -215,73 +205,6 @@ struct mips_coproc {
 #define MIPS_CP0_CONFIG4_SEL	4
 #define MIPS_CP0_CONFIG5_SEL	5
 
-/* Config0 register bits */
-#define CP0C0_M			31
-#define CP0C0_K23		28
-#define CP0C0_KU		25
-#define CP0C0_MDU		20
-#define CP0C0_MM		17
-#define CP0C0_BM		16
-#define CP0C0_BE		15
-#define CP0C0_AT		13
-#define CP0C0_AR		10
-#define CP0C0_MT		7
-#define CP0C0_VI		3
-#define CP0C0_K0		0
-
-/* Config1 register bits */
-#define CP0C1_M			31
-#define CP0C1_MMU		25
-#define CP0C1_IS		22
-#define CP0C1_IL		19
-#define CP0C1_IA		16
-#define CP0C1_DS		13
-#define CP0C1_DL		10
-#define CP0C1_DA		7
-#define CP0C1_C2		6
-#define CP0C1_MD		5
-#define CP0C1_PC		4
-#define CP0C1_WR		3
-#define CP0C1_CA		2
-#define CP0C1_EP		1
-#define CP0C1_FP		0
-
-/* Config2 Register bits */
-#define CP0C2_M			31
-#define CP0C2_TU		28
-#define CP0C2_TS		24
-#define CP0C2_TL		20
-#define CP0C2_TA		16
-#define CP0C2_SU		12
-#define CP0C2_SS		8
-#define CP0C2_SL		4
-#define CP0C2_SA		0
-
-/* Config3 Register bits */
-#define CP0C3_M			31
-#define CP0C3_ISA_ON_EXC	16
-#define CP0C3_ULRI		13
-#define CP0C3_DSPP		10
-#define CP0C3_LPA		7
-#define CP0C3_VEIC		6
-#define CP0C3_VInt		5
-#define CP0C3_SP		4
-#define CP0C3_MT		2
-#define CP0C3_SM		1
-#define CP0C3_TL		0
-
-/* MMU types, the first four entries have the same layout as the
-   CP0C0_MT field.  */
-enum mips_mmu_types {
-	MMU_TYPE_NONE,
-	MMU_TYPE_R4000,
-	MMU_TYPE_RESERVED,
-	MMU_TYPE_FMT,
-	MMU_TYPE_R3000,
-	MMU_TYPE_R6000,
-	MMU_TYPE_R8000
-};
-
 /* Resume Flags */
 #define RESUME_FLAG_DR		(1<<0)	/* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST	(1<<1)	/* Resume host? */
@@ -298,11 +221,6 @@ enum emulation_result {
 	EMULATE_PRIV_FAIL,
 };
 
-#define MIPS3_PG_G	0x00000001 /* Global; ignore ASID if in lo0 & lo1 */
-#define MIPS3_PG_V	0x00000002 /* Valid */
-#define MIPS3_PG_NV	0x00000000
-#define MIPS3_PG_D	0x00000004 /* Dirty */
-
 #define mips3_paddr_to_tlbpfn(x) \
 	(((unsigned long)(x) >> MIPS3_PG_SHIFT) & MIPS3_PG_FRAME)
 #define mips3_tlbpfn_to_paddr(x) \
@@ -313,13 +231,11 @@ enum emulation_result {
 
 #define VPN2_MASK		0xffffe000
 #define KVM_ENTRYHI_ASID	MIPS_ENTRYHI_ASID
-#define TLB_IS_GLOBAL(x)	(((x).tlb_lo0 & MIPS3_PG_G) &&		\
-				 ((x).tlb_lo1 & MIPS3_PG_G))
+#define TLB_IS_GLOBAL(x)	((x).tlb_lo[0] & (x).tlb_lo[1] & ENTRYLO_G)
 #define TLB_VPN2(x)		((x).tlb_hi & VPN2_MASK)
 #define TLB_ASID(x)		((x).tlb_hi & KVM_ENTRYHI_ASID)
-#define TLB_IS_VALID(x, va)	(((va) & (1 << PAGE_SHIFT))		\
-				 ? ((x).tlb_lo1 & MIPS3_PG_V)		\
-				 : ((x).tlb_lo0 & MIPS3_PG_V))
+#define TLB_LO_IDX(x, va)	(((va) >> PAGE_SHIFT) & 1)
+#define TLB_IS_VALID(x, va)	((x).tlb_lo[TLB_LO_IDX(x, va)] & ENTRYLO_V)
 #define TLB_HI_VPN2_HIT(x, y)	((TLB_VPN2(x) & ~(x).tlb_mask) ==	\
 				 ((y) & VPN2_MASK & ~(x).tlb_mask))
 #define TLB_HI_ASID_HIT(x, y)	(TLB_IS_GLOBAL(x) ||			\
@@ -328,26 +244,23 @@ enum emulation_result {
 struct kvm_mips_tlb {
 	long tlb_mask;
 	long tlb_hi;
-	long tlb_lo0;
-	long tlb_lo1;
+	long tlb_lo[2];
 };
 
-#define KVM_MIPS_FPU_FPU	0x1
-#define KVM_MIPS_FPU_MSA	0x2
+#define KVM_MIPS_AUX_FPU	0x1
+#define KVM_MIPS_AUX_MSA	0x2
 
 #define KVM_MIPS_GUEST_TLB_SIZE	64
 struct kvm_vcpu_arch {
-	void *host_ebase, *guest_ebase;
+	void *guest_ebase;
 	int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
 	unsigned long host_stack;
 	unsigned long host_gp;
 
 	/* Host CP0 registers used when handling exits from guest */
 	unsigned long host_cp0_badvaddr;
-	unsigned long host_cp0_cause;
 	unsigned long host_cp0_epc;
-	unsigned long host_cp0_entryhi;
-	uint32_t guest_inst;
+	u32 host_cp0_cause;
 
 	/* GPRS */
 	unsigned long gprs[32];
@@ -357,8 +270,8 @@ struct kvm_vcpu_arch {
 
 	/* FPU State */
 	struct mips_fpu_struct fpu;
-	/* Which FPU state is loaded (KVM_MIPS_FPU_*) */
-	unsigned int fpu_inuse;
+	/* Which auxiliary state is loaded (KVM_MIPS_AUX_*) */
+	unsigned int aux_inuse;
 
 	/* COP0 State */
 	struct mips_coproc *cop0;
@@ -370,11 +283,11 @@ struct kvm_vcpu_arch {
 
 	struct hrtimer comparecount_timer;
 	/* Count timer control KVM register */
-	uint32_t count_ctl;
+	u32 count_ctl;
 	/* Count bias from the raw time */
-	uint32_t count_bias;
+	u32 count_bias;
 	/* Frequency of timer in Hz */
-	uint32_t count_hz;
+	u32 count_hz;
 	/* Dynamic nanosecond bias (multiple of count_period) to avoid overflow */
 	s64 count_dyn_bias;
 	/* Resume time */
@@ -388,7 +301,7 @@ struct kvm_vcpu_arch {
 	/* Bitmask of pending exceptions to be cleared */
 	unsigned long pending_exceptions_clr;
 
-	unsigned long pending_load_cause;
+	u32 pending_load_cause;
 
 	/* Save/Restore the entryhi register when are are preempted/scheduled back in */
 	unsigned long preempt_entryhi;
@@ -397,8 +310,8 @@ struct kvm_vcpu_arch {
 	struct kvm_mips_tlb guest_tlb[KVM_MIPS_GUEST_TLB_SIZE];
 
 	/* Cached guest kernel/user ASIDs */
-	uint32_t guest_user_asid[NR_CPUS];
-	uint32_t guest_kernel_asid[NR_CPUS];
+	u32 guest_user_asid[NR_CPUS];
+	u32 guest_kernel_asid[NR_CPUS];
 	struct mm_struct guest_kernel_mm, guest_user_mm;
 
 	int last_sched_cpu;
@@ -408,6 +321,7 @@ struct kvm_vcpu_arch {
 
 	u8 fpu_enabled;
 	u8 msa_enabled;
+	u8 kscratch_enabled;
 };
 
 
@@ -461,6 +375,18 @@ struct kvm_vcpu_arch {
 #define kvm_write_c0_guest_config7(cop0, val)	(cop0->reg[MIPS_CP0_CONFIG][7] = (val))
 #define kvm_read_c0_guest_errorepc(cop0)	(cop0->reg[MIPS_CP0_ERROR_PC][0])
 #define kvm_write_c0_guest_errorepc(cop0, val)	(cop0->reg[MIPS_CP0_ERROR_PC][0] = (val))
+#define kvm_read_c0_guest_kscratch1(cop0)	(cop0->reg[MIPS_CP0_DESAVE][2])
+#define kvm_read_c0_guest_kscratch2(cop0)	(cop0->reg[MIPS_CP0_DESAVE][3])
+#define kvm_read_c0_guest_kscratch3(cop0)	(cop0->reg[MIPS_CP0_DESAVE][4])
+#define kvm_read_c0_guest_kscratch4(cop0)	(cop0->reg[MIPS_CP0_DESAVE][5])
+#define kvm_read_c0_guest_kscratch5(cop0)	(cop0->reg[MIPS_CP0_DESAVE][6])
+#define kvm_read_c0_guest_kscratch6(cop0)	(cop0->reg[MIPS_CP0_DESAVE][7])
+#define kvm_write_c0_guest_kscratch1(cop0, val)	(cop0->reg[MIPS_CP0_DESAVE][2] = (val))
+#define kvm_write_c0_guest_kscratch2(cop0, val)	(cop0->reg[MIPS_CP0_DESAVE][3] = (val))
+#define kvm_write_c0_guest_kscratch3(cop0, val)	(cop0->reg[MIPS_CP0_DESAVE][4] = (val))
+#define kvm_write_c0_guest_kscratch4(cop0, val)	(cop0->reg[MIPS_CP0_DESAVE][5] = (val))
+#define kvm_write_c0_guest_kscratch5(cop0, val)	(cop0->reg[MIPS_CP0_DESAVE][6] = (val))
+#define kvm_write_c0_guest_kscratch6(cop0, val)	(cop0->reg[MIPS_CP0_DESAVE][7] = (val))
 
 /*
  * Some of the guest registers may be modified asynchronously (e.g. from a
@@ -474,7 +400,7 @@ static inline void _kvm_atomic_set_c0_guest_reg(unsigned long *reg,
 	unsigned long temp;
 	do {
 		__asm__ __volatile__(
-		"	.set	mips3				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 		"	" __LL "%0, %1				\n"
 		"	or	%0, %2				\n"
 		"	" __SC	"%0, %1				\n"
@@ -490,7 +416,7 @@ static inline void _kvm_atomic_clear_c0_guest_reg(unsigned long *reg,
 	unsigned long temp;
 	do {
 		__asm__ __volatile__(
-		"	.set	mips3				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 		"	" __LL "%0, %1				\n"
 		"	and	%0, %2				\n"
 		"	" __SC	"%0, %1				\n"
@@ -507,7 +433,7 @@ static inline void _kvm_atomic_change_c0_guest_reg(unsigned long *reg,
 	unsigned long temp;
 	do {
 		__asm__ __volatile__(
-		"	.set	mips3				\n"
+		"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
 		"	" __LL "%0, %1				\n"
 		"	and	%0, %2				\n"
 		"	or	%0, %3				\n"
@@ -542,7 +468,7 @@ static inline void _kvm_atomic_change_c0_guest_reg(unsigned long *reg,
 
 static inline bool kvm_mips_guest_can_have_fpu(struct kvm_vcpu_arch *vcpu)
 {
-	return (!__builtin_constant_p(cpu_has_fpu) || cpu_has_fpu) &&
+	return (!__builtin_constant_p(raw_cpu_has_fpu) || raw_cpu_has_fpu) &&
 		vcpu->fpu_enabled;
 }
 
@@ -589,9 +515,11 @@ struct kvm_mips_callbacks {
 	void (*dequeue_io_int)(struct kvm_vcpu *vcpu,
 			       struct kvm_mips_interrupt *irq);
 	int (*irq_deliver)(struct kvm_vcpu *vcpu, unsigned int priority,
-			   uint32_t cause);
+			   u32 cause);
 	int (*irq_clear)(struct kvm_vcpu *vcpu, unsigned int priority,
-			 uint32_t cause);
+			 u32 cause);
+	unsigned long (*num_regs)(struct kvm_vcpu *vcpu);
+	int (*copy_reg_indices)(struct kvm_vcpu *vcpu, u64 __user *indices);
 	int (*get_one_reg)(struct kvm_vcpu *vcpu,
 			   const struct kvm_one_reg *reg, s64 *v);
 	int (*set_one_reg)(struct kvm_vcpu *vcpu,
@@ -605,8 +533,13 @@ int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks);
 /* Debug: dump vcpu state */
 int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu);
 
-/* Trampoline ASM routine to start running in "Guest" context */
-extern int __kvm_mips_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu);
+extern int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu);
+
+/* Building of entry/exception code */
+int kvm_mips_entry_setup(void);
+void *kvm_mips_build_vcpu_run(void *addr);
+void *kvm_mips_build_exception(void *addr, void *handler);
+void *kvm_mips_build_exit(void *addr);
 
 /* FPU/MSA context management */
 void __kvm_save_fpu(struct kvm_vcpu_arch *vcpu);
@@ -622,11 +555,11 @@ void kvm_drop_fpu(struct kvm_vcpu *vcpu);
 void kvm_lose_fpu(struct kvm_vcpu *vcpu);
 
 /* TLB handling */
-uint32_t kvm_get_kernel_asid(struct kvm_vcpu *vcpu);
+u32 kvm_get_kernel_asid(struct kvm_vcpu *vcpu);
 
-uint32_t kvm_get_user_asid(struct kvm_vcpu *vcpu);
+u32 kvm_get_user_asid(struct kvm_vcpu *vcpu);
 
-uint32_t kvm_get_commpage_asid (struct kvm_vcpu *vcpu);
+u32 kvm_get_commpage_asid (struct kvm_vcpu *vcpu);
 
 extern int kvm_mips_handle_kseg0_tlb_fault(unsigned long badbaddr,
 					   struct kvm_vcpu *vcpu);
@@ -635,22 +568,24 @@ extern int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr,
 					      struct kvm_vcpu *vcpu);
 
 extern int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
-						struct kvm_mips_tlb *tlb,
-						unsigned long *hpa0,
-						unsigned long *hpa1);
+						struct kvm_mips_tlb *tlb);
 
-extern enum emulation_result kvm_mips_handle_tlbmiss(unsigned long cause,
-						     uint32_t *opc,
+extern enum emulation_result kvm_mips_handle_tlbmiss(u32 cause,
+						     u32 *opc,
 						     struct kvm_run *run,
 						     struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_handle_tlbmod(unsigned long cause,
-						    uint32_t *opc,
+extern enum emulation_result kvm_mips_handle_tlbmod(u32 cause,
+						    u32 *opc,
 						    struct kvm_run *run,
 						    struct kvm_vcpu *vcpu);
 
 extern void kvm_mips_dump_host_tlbs(void);
 extern void kvm_mips_dump_guest_tlbs(struct kvm_vcpu *vcpu);
+extern int kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi,
+				   unsigned long entrylo0,
+				   unsigned long entrylo1,
+				   int flush_dcache_mask);
 extern void kvm_mips_flush_host_tlb(int skip_kseg0);
 extern int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long entryhi);
 
@@ -667,90 +602,90 @@ extern void kvm_mips_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 extern void kvm_mips_vcpu_put(struct kvm_vcpu *vcpu);
 
 /* Emulation */
-uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu);
-enum emulation_result update_pc(struct kvm_vcpu *vcpu, uint32_t cause);
+u32 kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu);
+enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause);
 
-extern enum emulation_result kvm_mips_emulate_inst(unsigned long cause,
-						   uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_inst(u32 cause,
+						   u32 *opc,
 						   struct kvm_run *run,
 						   struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_syscall(unsigned long cause,
-						      uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_syscall(u32 cause,
+						      u32 *opc,
 						      struct kvm_run *run,
 						      struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_tlbmiss_ld(unsigned long cause,
-							 uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_tlbmiss_ld(u32 cause,
+							 u32 *opc,
 							 struct kvm_run *run,
 							 struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_tlbinv_ld(unsigned long cause,
-							uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_tlbinv_ld(u32 cause,
+							u32 *opc,
 							struct kvm_run *run,
 							struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_tlbmiss_st(unsigned long cause,
-							 uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_tlbmiss_st(u32 cause,
+							 u32 *opc,
 							 struct kvm_run *run,
 							 struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_tlbinv_st(unsigned long cause,
-							uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_tlbinv_st(u32 cause,
+							u32 *opc,
 							struct kvm_run *run,
 							struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_tlbmod(unsigned long cause,
-						     uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_tlbmod(u32 cause,
+						     u32 *opc,
 						     struct kvm_run *run,
 						     struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_fpu_exc(unsigned long cause,
-						      uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_fpu_exc(u32 cause,
+						      u32 *opc,
 						      struct kvm_run *run,
 						      struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_handle_ri(unsigned long cause,
-						uint32_t *opc,
+extern enum emulation_result kvm_mips_handle_ri(u32 cause,
+						u32 *opc,
 						struct kvm_run *run,
 						struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_ri_exc(unsigned long cause,
-						     uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_ri_exc(u32 cause,
+						     u32 *opc,
 						     struct kvm_run *run,
 						     struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_bp_exc(unsigned long cause,
-						     uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_bp_exc(u32 cause,
+						     u32 *opc,
 						     struct kvm_run *run,
 						     struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_trap_exc(unsigned long cause,
-						       uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_trap_exc(u32 cause,
+						       u32 *opc,
 						       struct kvm_run *run,
 						       struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_msafpe_exc(unsigned long cause,
-							 uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_msafpe_exc(u32 cause,
+							 u32 *opc,
 							 struct kvm_run *run,
 							 struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_fpe_exc(unsigned long cause,
-						      uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_fpe_exc(u32 cause,
+						      u32 *opc,
 						      struct kvm_run *run,
 						      struct kvm_vcpu *vcpu);
 
-extern enum emulation_result kvm_mips_emulate_msadis_exc(unsigned long cause,
-							 uint32_t *opc,
+extern enum emulation_result kvm_mips_emulate_msadis_exc(u32 cause,
+							 u32 *opc,
 							 struct kvm_run *run,
 							 struct kvm_vcpu *vcpu);
 
 extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 							 struct kvm_run *run);
 
-uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu);
-void kvm_mips_write_count(struct kvm_vcpu *vcpu, uint32_t count);
-void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack);
+u32 kvm_mips_read_count(struct kvm_vcpu *vcpu);
+void kvm_mips_write_count(struct kvm_vcpu *vcpu, u32 count);
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, u32 compare, bool ack);
 void kvm_mips_init_count(struct kvm_vcpu *vcpu);
 int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl);
 int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume);
@@ -759,27 +694,27 @@ void kvm_mips_count_enable_cause(struct kvm_vcpu *vcpu);
 void kvm_mips_count_disable_cause(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_mips_count_timeout(struct kvm_vcpu *vcpu);
 
-enum emulation_result kvm_mips_check_privilege(unsigned long cause,
-					       uint32_t *opc,
+enum emulation_result kvm_mips_check_privilege(u32 cause,
+					       u32 *opc,
 					       struct kvm_run *run,
 					       struct kvm_vcpu *vcpu);
 
-enum emulation_result kvm_mips_emulate_cache(uint32_t inst,
-					     uint32_t *opc,
-					     uint32_t cause,
+enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst,
+					     u32 *opc,
+					     u32 cause,
 					     struct kvm_run *run,
 					     struct kvm_vcpu *vcpu);
-enum emulation_result kvm_mips_emulate_CP0(uint32_t inst,
-					   uint32_t *opc,
-					   uint32_t cause,
+enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst,
+					   u32 *opc,
+					   u32 cause,
 					   struct kvm_run *run,
 					   struct kvm_vcpu *vcpu);
-enum emulation_result kvm_mips_emulate_store(uint32_t inst,
-					     uint32_t cause,
+enum emulation_result kvm_mips_emulate_store(union mips_instruction inst,
+					     u32 cause,
 					     struct kvm_run *run,
 					     struct kvm_vcpu *vcpu);
-enum emulation_result kvm_mips_emulate_load(uint32_t inst,
-					    uint32_t cause,
+enum emulation_result kvm_mips_emulate_load(union mips_instruction inst,
+					    u32 cause,
 					    struct kvm_run *run,
 					    struct kvm_vcpu *vcpu);
 
@@ -789,13 +724,13 @@ unsigned int kvm_mips_config4_wrmask(struct kvm_vcpu *vcpu);
 unsigned int kvm_mips_config5_wrmask(struct kvm_vcpu *vcpu);
 
 /* Dynamic binary translation */
-extern int kvm_mips_trans_cache_index(uint32_t inst, uint32_t *opc,
-				      struct kvm_vcpu *vcpu);
-extern int kvm_mips_trans_cache_va(uint32_t inst, uint32_t *opc,
+extern int kvm_mips_trans_cache_index(union mips_instruction inst,
+				      u32 *opc, struct kvm_vcpu *vcpu);
+extern int kvm_mips_trans_cache_va(union mips_instruction inst, u32 *opc,
 				   struct kvm_vcpu *vcpu);
-extern int kvm_mips_trans_mfc0(uint32_t inst, uint32_t *opc,
+extern int kvm_mips_trans_mfc0(union mips_instruction inst, u32 *opc,
 			       struct kvm_vcpu *vcpu);
-extern int kvm_mips_trans_mtc0(uint32_t inst, uint32_t *opc,
+extern int kvm_mips_trans_mtc0(union mips_instruction inst, u32 *opc,
 			       struct kvm_vcpu *vcpu);
 
 /* Misc */
diff --git a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
index d68e685cde60..bd8b9bbe1771 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
@@ -55,7 +55,7 @@
 #define cpu_has_mipsmt		0
 #define cpu_has_vint		0
 #define cpu_has_veic		0
-#define cpu_hwrena_impl_bits	0xc0000000
+#define cpu_hwrena_impl_bits	(MIPS_HWRENA_IMPL1 | MIPS_HWRENA_IMPL2)
 #define cpu_has_wsbh            1
 
 #define cpu_has_rixi		(cpu_data[0].cputype != CPU_CAVIUM_OCTEON)
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index e1ca65c62f6a..def9d8d13f6e 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -53,7 +53,7 @@
 #define CP0_SEGCTL2 $5, 4
 #define CP0_WIRED $6
 #define CP0_INFO $7
-#define CP0_HWRENA $7, 0
+#define CP0_HWRENA $7
 #define CP0_BADVADDR $8
 #define CP0_BADINSTR $8, 1
 #define CP0_COUNT $9
@@ -533,6 +533,7 @@
 #define TX49_CONF_CWFON		(_ULCAST_(1) << 27)
 
 /* Bits specific to the MIPS32/64 PRA.	*/
+#define MIPS_CONF_VI		(_ULCAST_(1) <<  3)
 #define MIPS_CONF_MT		(_ULCAST_(7) <<	 7)
 #define MIPS_CONF_MT_TLB	(_ULCAST_(1) <<  7)
 #define MIPS_CONF_MT_FTLB	(_ULCAST_(4) <<  7)
@@ -853,6 +854,24 @@
 #define MIPS_CDMMBASE_ADDR_SHIFT 11
 #define MIPS_CDMMBASE_ADDR_START 15
 
+/* RDHWR register numbers */
+#define MIPS_HWR_CPUNUM		0	/* CPU number */
+#define MIPS_HWR_SYNCISTEP	1	/* SYNCI step size */
+#define MIPS_HWR_CC		2	/* Cycle counter */
+#define MIPS_HWR_CCRES		3	/* Cycle counter resolution */
+#define MIPS_HWR_ULR		29	/* UserLocal */
+#define MIPS_HWR_IMPL1		30	/* Implementation dependent */
+#define MIPS_HWR_IMPL2		31	/* Implementation dependent */
+
+/* Bits in HWREna register */
+#define MIPS_HWRENA_CPUNUM	(_ULCAST_(1) << MIPS_HWR_CPUNUM)
+#define MIPS_HWRENA_SYNCISTEP	(_ULCAST_(1) << MIPS_HWR_SYNCISTEP)
+#define MIPS_HWRENA_CC		(_ULCAST_(1) << MIPS_HWR_CC)
+#define MIPS_HWRENA_CCRES	(_ULCAST_(1) << MIPS_HWR_CCRES)
+#define MIPS_HWRENA_ULR		(_ULCAST_(1) << MIPS_HWR_ULR)
+#define MIPS_HWRENA_IMPL1	(_ULCAST_(1) << MIPS_HWR_IMPL1)
+#define MIPS_HWRENA_IMPL2	(_ULCAST_(1) << MIPS_HWR_IMPL2)
+
 /*
  * Bitfields in the TX39 family CP0 Configuration Register 3
  */
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 86b239d9d75d..9b63cd41213d 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -80,16 +80,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 
 #define HAVE_ARCH_PCI_RESOURCE_TO_USER
 
-static inline void pci_resource_to_user(const struct pci_dev *dev, int bar,
-		const struct resource *rsrc, resource_size_t *start,
-		resource_size_t *end)
-{
-	phys_addr_t size = resource_size(rsrc);
-
-	*start = fixup_bigphys_addr(rsrc->start, size);
-	*end = rsrc->start + size;
-}
-
 /*
  * Dynamic DMA mapping stuff.
  * MIPS has everything mapped statically.
diff --git a/arch/mips/include/asm/setup.h b/arch/mips/include/asm/setup.h
index d7bfdeba9e84..4f5279a8308d 100644
--- a/arch/mips/include/asm/setup.h
+++ b/arch/mips/include/asm/setup.h
@@ -21,6 +21,7 @@ extern void *set_vi_handler(int n, vi_handler_t addr);
 
 extern void *set_except_vector(int n, void *addr);
 extern unsigned long ebase;
+extern unsigned int hwrena;
 extern void per_cpu_trap_init(bool);
 extern void cpu_cache_init(void);
 
diff --git a/arch/mips/include/asm/uasm.h b/arch/mips/include/asm/uasm.h
index b6ecfeee4dbe..f7929f65f7ca 100644
--- a/arch/mips/include/asm/uasm.h
+++ b/arch/mips/include/asm/uasm.h
@@ -104,8 +104,13 @@ Ip_u1s2(_bltz);
 Ip_u1s2(_bltzl);
 Ip_u1u2s3(_bne);
 Ip_u2s3u1(_cache);
+Ip_u1u2(_cfc1);
+Ip_u2u1(_cfcmsa);
+Ip_u1u2(_ctc1);
+Ip_u2u1(_ctcmsa);
 Ip_u2u1s3(_daddiu);
 Ip_u3u1u2(_daddu);
+Ip_u1(_di);
 Ip_u2u1msbu3(_dins);
 Ip_u2u1msbu3(_dinsm);
 Ip_u1u2(_divu);
@@ -141,6 +146,8 @@ Ip_u1(_mfhi);
 Ip_u1(_mflo);
 Ip_u1u2u3(_mtc0);
 Ip_u1u2u3(_mthc0);
+Ip_u1(_mthi);
+Ip_u1(_mtlo);
 Ip_u3u1u2(_mul);
 Ip_u3u1u2(_or);
 Ip_u2u1u3(_ori);
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index 8051f9aa1379..77429d1622b3 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -21,20 +21,20 @@
 enum major_op {
 	spec_op, bcond_op, j_op, jal_op,
 	beq_op, bne_op, blez_op, bgtz_op,
-	addi_op, cbcond0_op = addi_op, addiu_op, slti_op, sltiu_op,
+	addi_op, pop10_op = addi_op, addiu_op, slti_op, sltiu_op,
 	andi_op, ori_op, xori_op, lui_op,
 	cop0_op, cop1_op, cop2_op, cop1x_op,
 	beql_op, bnel_op, blezl_op, bgtzl_op,
-	daddi_op, cbcond1_op = daddi_op, daddiu_op, ldl_op, ldr_op,
+	daddi_op, pop30_op = daddi_op, daddiu_op, ldl_op, ldr_op,
 	spec2_op, jalx_op, mdmx_op, msa_op = mdmx_op, spec3_op,
 	lb_op, lh_op, lwl_op, lw_op,
 	lbu_op, lhu_op, lwr_op, lwu_op,
 	sb_op, sh_op, swl_op, sw_op,
 	sdl_op, sdr_op, swr_op, cache_op,
 	ll_op, lwc1_op, lwc2_op, bc6_op = lwc2_op, pref_op,
-	lld_op, ldc1_op, ldc2_op, beqzcjic_op = ldc2_op, ld_op,
+	lld_op, ldc1_op, ldc2_op, pop66_op = ldc2_op, ld_op,
 	sc_op, swc1_op, swc2_op, balc6_op = swc2_op, major_3b_op,
-	scd_op, sdc1_op, sdc2_op, bnezcjialc_op = sdc2_op, sd_op
+	scd_op, sdc1_op, sdc2_op, pop76_op = sdc2_op, sd_op
 };
 
 /*
@@ -93,6 +93,50 @@ enum spec3_op {
 };
 
 /*
+ * Bits 10-6 minor opcode for r6 spec mult/div encodings
+ */
+enum mult_op {
+	mult_mult_op = 0x0,
+	mult_mul_op = 0x2,
+	mult_muh_op = 0x3,
+};
+enum multu_op {
+	multu_multu_op = 0x0,
+	multu_mulu_op = 0x2,
+	multu_muhu_op = 0x3,
+};
+enum div_op {
+	div_div_op = 0x0,
+	div_div6_op = 0x2,
+	div_mod_op = 0x3,
+};
+enum divu_op {
+	divu_divu_op = 0x0,
+	divu_divu6_op = 0x2,
+	divu_modu_op = 0x3,
+};
+enum dmult_op {
+	dmult_dmult_op = 0x0,
+	dmult_dmul_op = 0x2,
+	dmult_dmuh_op = 0x3,
+};
+enum dmultu_op {
+	dmultu_dmultu_op = 0x0,
+	dmultu_dmulu_op = 0x2,
+	dmultu_dmuhu_op = 0x3,
+};
+enum ddiv_op {
+	ddiv_ddiv_op = 0x0,
+	ddiv_ddiv6_op = 0x2,
+	ddiv_dmod_op = 0x3,
+};
+enum ddivu_op {
+	ddivu_ddivu_op = 0x0,
+	ddivu_ddivu6_op = 0x2,
+	ddivu_dmodu_op = 0x3,
+};
+
+/*
  * rt field of bcond opcodes.
  */
 enum rt_op {
@@ -103,7 +147,7 @@ enum rt_op {
 	bltzal_op, bgezal_op, bltzall_op, bgezall_op,
 	rt_op_0x14, rt_op_0x15, rt_op_0x16, rt_op_0x17,
 	rt_op_0x18, rt_op_0x19, rt_op_0x1a, rt_op_0x1b,
-	bposge32_op, rt_op_0x1d, rt_op_0x1e, rt_op_0x1f
+	bposge32_op, rt_op_0x1d, rt_op_0x1e, synci_op
 };
 
 /*
@@ -238,6 +282,21 @@ enum bshfl_func {
 };
 
 /*
+ * MSA minor opcodes.
+ */
+enum msa_func {
+	msa_elm_op = 0x19,
+};
+
+/*
+ * MSA ELM opcodes.
+ */
+enum msa_elm {
+	msa_ctc_op = 0x3e,
+	msa_cfc_op = 0x7e,
+};
+
+/*
  * func field for MSA MI10 format.
  */
 enum msa_mi10_func {
@@ -264,7 +323,7 @@ enum mm_major_op {
 	mm_pool32b_op, mm_pool16b_op, mm_lhu16_op, mm_andi16_op,
 	mm_addiu32_op, mm_lhu32_op, mm_sh32_op, mm_lh32_op,
 	mm_pool32i_op, mm_pool16c_op, mm_lwsp16_op, mm_pool16d_op,
-	mm_ori32_op, mm_pool32f_op, mm_reserved1_op, mm_reserved2_op,
+	mm_ori32_op, mm_pool32f_op, mm_pool32s_op, mm_reserved2_op,
 	mm_pool32c_op, mm_lwgp16_op, mm_lw16_op, mm_pool16e_op,
 	mm_xori32_op, mm_jals32_op, mm_addiupc_op, mm_reserved3_op,
 	mm_reserved4_op, mm_pool16f_op, mm_sb16_op, mm_beqz16_op,
@@ -360,7 +419,10 @@ enum mm_32axf_minor_op {
 	mm_mflo32_op = 0x075,
 	mm_jalrhb_op = 0x07c,
 	mm_tlbwi_op = 0x08d,
+	mm_mthi32_op = 0x0b5,
 	mm_tlbwr_op = 0x0cd,
+	mm_mtlo32_op = 0x0f5,
+	mm_di_op = 0x11d,
 	mm_jalrs_op = 0x13c,
 	mm_jalrshb_op = 0x17c,
 	mm_sync_op = 0x1ad,
@@ -479,6 +541,13 @@ enum mm_32f_73_minor_op {
 };
 
 /*
+ * (microMIPS) POOL32S minor opcodes.
+ */
+enum mm_32s_minor_op {
+	mm_32s_elm_op = 0x16,
+};
+
+/*
  * (microMIPS) POOL16C minor opcodes.
  */
 enum mm_16c_minor_op {
@@ -586,6 +655,36 @@ struct r_format {			/* Register format */
 	;))))))
 };
 
+struct c0r_format {			/* C0 register format */
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rs : 5,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int rd : 5,
+	__BITFIELD_FIELD(unsigned int z: 8,
+	__BITFIELD_FIELD(unsigned int sel : 3,
+	;))))))
+};
+
+struct mfmc0_format {			/* MFMC0 register format */
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rs : 5,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int rd : 5,
+	__BITFIELD_FIELD(unsigned int re : 5,
+	__BITFIELD_FIELD(unsigned int sc : 1,
+	__BITFIELD_FIELD(unsigned int : 2,
+	__BITFIELD_FIELD(unsigned int sel : 3,
+	;))))))))
+};
+
+struct co_format {			/* C0 CO format */
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int co : 1,
+	__BITFIELD_FIELD(unsigned int code : 19,
+	__BITFIELD_FIELD(unsigned int func : 6,
+	;))))
+};
+
 struct p_format {		/* Performance counter format (R10000) */
 	__BITFIELD_FIELD(unsigned int opcode : 6,
 	__BITFIELD_FIELD(unsigned int rs : 5,
@@ -937,6 +1036,9 @@ union mips_instruction {
 	struct u_format u_format;
 	struct c_format c_format;
 	struct r_format r_format;
+	struct c0r_format c0r_format;
+	struct mfmc0_format mfmc0_format;
+	struct co_format co_format;
 	struct p_format p_format;
 	struct f_format f_format;
 	struct ma_format ma_format;
diff --git a/arch/mips/jz4740/setup.c b/arch/mips/jz4740/setup.c
index 510fc0d962f2..0914ef775b5f 100644
--- a/arch/mips/jz4740/setup.c
+++ b/arch/mips/jz4740/setup.c
@@ -20,7 +20,6 @@
 #include <linux/kernel.h>
 #include <linux/libfdt.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 
 #include <asm/bootinfo.h>
 #include <asm/prom.h>
@@ -74,13 +73,6 @@ void __init device_tree_init(void)
 	unflatten_and_copy_device_tree();
 }
 
-static int __init populate_machine(void)
-{
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-	return 0;
-}
-arch_initcall(populate_machine);
-
 const char *get_system_type(void)
 {
 	if (config_enabled(CONFIG_MACH_JZ4780))
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index 1ea973b2abb1..fae2f9447792 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -339,71 +339,9 @@ void output_pm_defines(void)
 }
 #endif
 
-void output_cpuinfo_defines(void)
-{
-	COMMENT(" MIPS cpuinfo offsets. ");
-	DEFINE(CPUINFO_SIZE, sizeof(struct cpuinfo_mips));
-#ifdef CONFIG_MIPS_ASID_BITS_VARIABLE
-	OFFSET(CPUINFO_ASID_MASK, cpuinfo_mips, asid_mask);
-#endif
-}
-
 void output_kvm_defines(void)
 {
 	COMMENT(" KVM/MIPS Specfic offsets. ");
-	DEFINE(VCPU_ARCH_SIZE, sizeof(struct kvm_vcpu_arch));
-	OFFSET(VCPU_RUN, kvm_vcpu, run);
-	OFFSET(VCPU_HOST_ARCH, kvm_vcpu, arch);
-
-	OFFSET(VCPU_HOST_EBASE, kvm_vcpu_arch, host_ebase);
-	OFFSET(VCPU_GUEST_EBASE, kvm_vcpu_arch, guest_ebase);
-
-	OFFSET(VCPU_HOST_STACK, kvm_vcpu_arch, host_stack);
-	OFFSET(VCPU_HOST_GP, kvm_vcpu_arch, host_gp);
-
-	OFFSET(VCPU_HOST_CP0_BADVADDR, kvm_vcpu_arch, host_cp0_badvaddr);
-	OFFSET(VCPU_HOST_CP0_CAUSE, kvm_vcpu_arch, host_cp0_cause);
-	OFFSET(VCPU_HOST_EPC, kvm_vcpu_arch, host_cp0_epc);
-	OFFSET(VCPU_HOST_ENTRYHI, kvm_vcpu_arch, host_cp0_entryhi);
-
-	OFFSET(VCPU_GUEST_INST, kvm_vcpu_arch, guest_inst);
-
-	OFFSET(VCPU_R0, kvm_vcpu_arch, gprs[0]);
-	OFFSET(VCPU_R1, kvm_vcpu_arch, gprs[1]);
-	OFFSET(VCPU_R2, kvm_vcpu_arch, gprs[2]);
-	OFFSET(VCPU_R3, kvm_vcpu_arch, gprs[3]);
-	OFFSET(VCPU_R4, kvm_vcpu_arch, gprs[4]);
-	OFFSET(VCPU_R5, kvm_vcpu_arch, gprs[5]);
-	OFFSET(VCPU_R6, kvm_vcpu_arch, gprs[6]);
-	OFFSET(VCPU_R7, kvm_vcpu_arch, gprs[7]);
-	OFFSET(VCPU_R8, kvm_vcpu_arch, gprs[8]);
-	OFFSET(VCPU_R9, kvm_vcpu_arch, gprs[9]);
-	OFFSET(VCPU_R10, kvm_vcpu_arch, gprs[10]);
-	OFFSET(VCPU_R11, kvm_vcpu_arch, gprs[11]);
-	OFFSET(VCPU_R12, kvm_vcpu_arch, gprs[12]);
-	OFFSET(VCPU_R13, kvm_vcpu_arch, gprs[13]);
-	OFFSET(VCPU_R14, kvm_vcpu_arch, gprs[14]);
-	OFFSET(VCPU_R15, kvm_vcpu_arch, gprs[15]);
-	OFFSET(VCPU_R16, kvm_vcpu_arch, gprs[16]);
-	OFFSET(VCPU_R17, kvm_vcpu_arch, gprs[17]);
-	OFFSET(VCPU_R18, kvm_vcpu_arch, gprs[18]);
-	OFFSET(VCPU_R19, kvm_vcpu_arch, gprs[19]);
-	OFFSET(VCPU_R20, kvm_vcpu_arch, gprs[20]);
-	OFFSET(VCPU_R21, kvm_vcpu_arch, gprs[21]);
-	OFFSET(VCPU_R22, kvm_vcpu_arch, gprs[22]);
-	OFFSET(VCPU_R23, kvm_vcpu_arch, gprs[23]);
-	OFFSET(VCPU_R24, kvm_vcpu_arch, gprs[24]);
-	OFFSET(VCPU_R25, kvm_vcpu_arch, gprs[25]);
-	OFFSET(VCPU_R26, kvm_vcpu_arch, gprs[26]);
-	OFFSET(VCPU_R27, kvm_vcpu_arch, gprs[27]);
-	OFFSET(VCPU_R28, kvm_vcpu_arch, gprs[28]);
-	OFFSET(VCPU_R29, kvm_vcpu_arch, gprs[29]);
-	OFFSET(VCPU_R30, kvm_vcpu_arch, gprs[30]);
-	OFFSET(VCPU_R31, kvm_vcpu_arch, gprs[31]);
-	OFFSET(VCPU_LO, kvm_vcpu_arch, lo);
-	OFFSET(VCPU_HI, kvm_vcpu_arch, hi);
-	OFFSET(VCPU_PC, kvm_vcpu_arch, pc);
-	BLANK();
 
 	OFFSET(VCPU_FPR0, kvm_vcpu_arch, fpu.fpr[0]);
 	OFFSET(VCPU_FPR1, kvm_vcpu_arch, fpu.fpr[1]);
@@ -441,14 +379,6 @@ void output_kvm_defines(void)
 	OFFSET(VCPU_FCR31, kvm_vcpu_arch, fpu.fcr31);
 	OFFSET(VCPU_MSA_CSR, kvm_vcpu_arch, fpu.msacsr);
 	BLANK();
-
-	OFFSET(VCPU_COP0, kvm_vcpu_arch, cop0);
-	OFFSET(VCPU_GUEST_KERNEL_ASID, kvm_vcpu_arch, guest_kernel_asid);
-	OFFSET(VCPU_GUEST_USER_ASID, kvm_vcpu_arch, guest_user_asid);
-
-	OFFSET(COP0_TLB_HI, mips_coproc, reg[MIPS_CP0_TLB_HI][0]);
-	OFFSET(COP0_STATUS, mips_coproc, reg[MIPS_CP0_STATUS][0]);
-	BLANK();
 }
 
 #ifdef CONFIG_MIPS_CPS
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 6dc3f1fdaccc..46c227fc98f5 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -790,7 +790,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		epc += 4 + (insn.i_format.simmediate << 2);
 		regs->cp0_epc = epc;
 		break;
-	case beqzcjic_op:
+	case pop66_op:
 		if (!cpu_has_mips_r6) {
 			ret = -SIGILL;
 			break;
@@ -798,7 +798,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		/* Compact branch: BEQZC || JIC */
 		regs->cp0_epc += 8;
 		break;
-	case bnezcjialc_op:
+	case pop76_op:
 		if (!cpu_has_mips_r6) {
 			ret = -SIGILL;
 			break;
@@ -809,8 +809,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 		regs->cp0_epc += 8;
 		break;
 #endif
-	case cbcond0_op:
-	case cbcond1_op:
+	case pop10_op:
+	case pop30_op:
 		/* Only valid for MIPS R6 */
 		if (!cpu_has_mips_r6) {
 			ret = -SIGILL;
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 4a1712b5abdf..6fb4704bd156 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -619,17 +619,17 @@ static int simulate_rdhwr(struct pt_regs *regs, int rd, int rt)
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,
 			1, regs, 0);
 	switch (rd) {
-	case 0:		/* CPU number */
+	case MIPS_HWR_CPUNUM:		/* CPU number */
 		regs->regs[rt] = smp_processor_id();
 		return 0;
-	case 1:		/* SYNCI length */
+	case MIPS_HWR_SYNCISTEP:	/* SYNCI length */
 		regs->regs[rt] = min(current_cpu_data.dcache.linesz,
 				     current_cpu_data.icache.linesz);
 		return 0;
-	case 2:		/* Read count register */
+	case MIPS_HWR_CC:		/* Read count register */
 		regs->regs[rt] = read_c0_count();
 		return 0;
-	case 3:		/* Count register resolution */
+	case MIPS_HWR_CCRES:		/* Count register resolution */
 		switch (current_cpu_type()) {
 		case CPU_20KC:
 		case CPU_25KF:
@@ -639,7 +639,7 @@ static int simulate_rdhwr(struct pt_regs *regs, int rd, int rt)
 			regs->regs[rt] = 2;
 		}
 		return 0;
-	case 29:
+	case MIPS_HWR_ULR:		/* Read UserLocal register */
 		regs->regs[rt] = ti->tp_value;
 		return 0;
 	default:
@@ -1859,6 +1859,7 @@ void __noreturn nmi_exception_handler(struct pt_regs *regs)
 #define VECTORSPACING 0x100	/* for EI/VI mode */
 
 unsigned long ebase;
+EXPORT_SYMBOL_GPL(ebase);
 unsigned long exception_handlers[32];
 unsigned long vi_handlers[64];
 
@@ -2063,16 +2064,22 @@ static void configure_status(void)
 			 status_set);
 }
 
+unsigned int hwrena;
+EXPORT_SYMBOL_GPL(hwrena);
+
 /* configure HWRENA register */
 static void configure_hwrena(void)
 {
-	unsigned int hwrena = cpu_hwrena_impl_bits;
+	hwrena = cpu_hwrena_impl_bits;
 
 	if (cpu_has_mips_r2_r6)
-		hwrena |= 0x0000000f;
+		hwrena |= MIPS_HWRENA_CPUNUM |
+			  MIPS_HWRENA_SYNCISTEP |
+			  MIPS_HWRENA_CC |
+			  MIPS_HWRENA_CCRES;
 
 	if (!noulri && cpu_has_userlocal)
-		hwrena |= (1 << 29);
+		hwrena |= MIPS_HWRENA_ULR;
 
 	if (hwrena)
 		write_c0_hwrena(hwrena);
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index 2ae12825529f..7c56d6b124d1 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -17,6 +17,7 @@ if VIRTUALIZATION
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
+	select EXPORT_UASM
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select KVM_MMIO
diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile
index 637ebbebd549..847429de780d 100644
--- a/arch/mips/kvm/Makefile
+++ b/arch/mips/kvm/Makefile
@@ -7,9 +7,10 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/mips/kvm
 
 common-objs-$(CONFIG_CPU_HAS_MSA) += msa.o
 
-kvm-objs := $(common-objs-y) mips.o emulate.o locore.o \
+kvm-objs := $(common-objs-y) mips.o emulate.o entry.o \
 	    interrupt.o stats.o commpage.o \
 	    dyntrans.o trap_emul.o fpu.o
+kvm-objs += mmu.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
 obj-y			+= callback.o tlb.o
diff --git a/arch/mips/kvm/commpage.c b/arch/mips/kvm/commpage.c
index 2d6e976d1add..a36b77e1705c 100644
--- a/arch/mips/kvm/commpage.c
+++ b/arch/mips/kvm/commpage.c
@@ -4,7 +4,7 @@
  * for more details.
  *
  * commpage, currently used for Virtual COP0 registers.
- * Mapped into the guest kernel @ 0x0.
+ * Mapped into the guest kernel @ KVM_GUEST_COMMPAGE_ADDR.
  *
  * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
  * Authors: Sanjay Lal <sanjayl@kymasys.com>
diff --git a/arch/mips/kvm/dyntrans.c b/arch/mips/kvm/dyntrans.c
index f1527a465c1b..d280894915ed 100644
--- a/arch/mips/kvm/dyntrans.c
+++ b/arch/mips/kvm/dyntrans.c
@@ -11,6 +11,7 @@
 
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/highmem.h>
 #include <linux/kvm_host.h>
 #include <linux/module.h>
 #include <linux/vmalloc.h>
@@ -20,125 +21,114 @@
 
 #include "commpage.h"
 
-#define SYNCI_TEMPLATE  0x041f0000
-#define SYNCI_BASE(x)   (((x) >> 21) & 0x1f)
-#define SYNCI_OFFSET    ((x) & 0xffff)
+/**
+ * kvm_mips_trans_replace() - Replace trapping instruction in guest memory.
+ * @vcpu:	Virtual CPU.
+ * @opc:	PC of instruction to replace.
+ * @replace:	Instruction to write
+ */
+static int kvm_mips_trans_replace(struct kvm_vcpu *vcpu, u32 *opc,
+				  union mips_instruction replace)
+{
+	unsigned long paddr, flags;
+	void *vaddr;
+
+	if (KVM_GUEST_KSEGX((unsigned long)opc) == KVM_GUEST_KSEG0) {
+		paddr = kvm_mips_translate_guest_kseg0_to_hpa(vcpu,
+							    (unsigned long)opc);
+		vaddr = kmap_atomic(pfn_to_page(PHYS_PFN(paddr)));
+		vaddr += paddr & ~PAGE_MASK;
+		memcpy(vaddr, (void *)&replace, sizeof(u32));
+		local_flush_icache_range((unsigned long)vaddr,
+					 (unsigned long)vaddr + 32);
+		kunmap_atomic(vaddr);
+	} else if (KVM_GUEST_KSEGX((unsigned long) opc) == KVM_GUEST_KSEG23) {
+		local_irq_save(flags);
+		memcpy((void *)opc, (void *)&replace, sizeof(u32));
+		local_flush_icache_range((unsigned long)opc,
+					 (unsigned long)opc + 32);
+		local_irq_restore(flags);
+	} else {
+		kvm_err("%s: Invalid address: %p\n", __func__, opc);
+		return -EFAULT;
+	}
 
-#define LW_TEMPLATE     0x8c000000
-#define CLEAR_TEMPLATE  0x00000020
-#define SW_TEMPLATE     0xac000000
+	return 0;
+}
 
-int kvm_mips_trans_cache_index(uint32_t inst, uint32_t *opc,
+int kvm_mips_trans_cache_index(union mips_instruction inst, u32 *opc,
 			       struct kvm_vcpu *vcpu)
 {
-	int result = 0;
-	unsigned long kseg0_opc;
-	uint32_t synci_inst = 0x0;
+	union mips_instruction nop_inst = { 0 };
 
 	/* Replace the CACHE instruction, with a NOP */
-	kseg0_opc =
-	    CKSEG0ADDR(kvm_mips_translate_guest_kseg0_to_hpa
-		       (vcpu, (unsigned long) opc));
-	memcpy((void *)kseg0_opc, (void *)&synci_inst, sizeof(uint32_t));
-	local_flush_icache_range(kseg0_opc, kseg0_opc + 32);
-
-	return result;
+	return kvm_mips_trans_replace(vcpu, opc, nop_inst);
 }
 
 /*
  * Address based CACHE instructions are transformed into synci(s). A little
  * heavy for just D-cache invalidates, but avoids an expensive trap
  */
-int kvm_mips_trans_cache_va(uint32_t inst, uint32_t *opc,
+int kvm_mips_trans_cache_va(union mips_instruction inst, u32 *opc,
 			    struct kvm_vcpu *vcpu)
 {
-	int result = 0;
-	unsigned long kseg0_opc;
-	uint32_t synci_inst = SYNCI_TEMPLATE, base, offset;
-
-	base = (inst >> 21) & 0x1f;
-	offset = inst & 0xffff;
-	synci_inst |= (base << 21);
-	synci_inst |= offset;
-
-	kseg0_opc =
-	    CKSEG0ADDR(kvm_mips_translate_guest_kseg0_to_hpa
-		       (vcpu, (unsigned long) opc));
-	memcpy((void *)kseg0_opc, (void *)&synci_inst, sizeof(uint32_t));
-	local_flush_icache_range(kseg0_opc, kseg0_opc + 32);
-
-	return result;
+	union mips_instruction synci_inst = { 0 };
+
+	synci_inst.i_format.opcode = bcond_op;
+	synci_inst.i_format.rs = inst.i_format.rs;
+	synci_inst.i_format.rt = synci_op;
+	if (cpu_has_mips_r6)
+		synci_inst.i_format.simmediate = inst.spec3_format.simmediate;
+	else
+		synci_inst.i_format.simmediate = inst.i_format.simmediate;
+
+	return kvm_mips_trans_replace(vcpu, opc, synci_inst);
 }
 
-int kvm_mips_trans_mfc0(uint32_t inst, uint32_t *opc, struct kvm_vcpu *vcpu)
+int kvm_mips_trans_mfc0(union mips_instruction inst, u32 *opc,
+			struct kvm_vcpu *vcpu)
 {
-	int32_t rt, rd, sel;
-	uint32_t mfc0_inst;
-	unsigned long kseg0_opc, flags;
-
-	rt = (inst >> 16) & 0x1f;
-	rd = (inst >> 11) & 0x1f;
-	sel = inst & 0x7;
+	union mips_instruction mfc0_inst = { 0 };
+	u32 rd, sel;
 
-	if ((rd == MIPS_CP0_ERRCTL) && (sel == 0)) {
-		mfc0_inst = CLEAR_TEMPLATE;
-		mfc0_inst |= ((rt & 0x1f) << 16);
-	} else {
-		mfc0_inst = LW_TEMPLATE;
-		mfc0_inst |= ((rt & 0x1f) << 16);
-		mfc0_inst |= offsetof(struct kvm_mips_commpage,
-				      cop0.reg[rd][sel]);
-	}
+	rd = inst.c0r_format.rd;
+	sel = inst.c0r_format.sel;
 
-	if (KVM_GUEST_KSEGX(opc) == KVM_GUEST_KSEG0) {
-		kseg0_opc =
-		    CKSEG0ADDR(kvm_mips_translate_guest_kseg0_to_hpa
-			       (vcpu, (unsigned long) opc));
-		memcpy((void *)kseg0_opc, (void *)&mfc0_inst, sizeof(uint32_t));
-		local_flush_icache_range(kseg0_opc, kseg0_opc + 32);
-	} else if (KVM_GUEST_KSEGX((unsigned long) opc) == KVM_GUEST_KSEG23) {
-		local_irq_save(flags);
-		memcpy((void *)opc, (void *)&mfc0_inst, sizeof(uint32_t));
-		local_flush_icache_range((unsigned long)opc,
-					 (unsigned long)opc + 32);
-		local_irq_restore(flags);
+	if (rd == MIPS_CP0_ERRCTL && sel == 0) {
+		mfc0_inst.r_format.opcode = spec_op;
+		mfc0_inst.r_format.rd = inst.c0r_format.rt;
+		mfc0_inst.r_format.func = add_op;
 	} else {
-		kvm_err("%s: Invalid address: %p\n", __func__, opc);
-		return -EFAULT;
+		mfc0_inst.i_format.opcode = lw_op;
+		mfc0_inst.i_format.rt = inst.c0r_format.rt;
+		mfc0_inst.i_format.simmediate = KVM_GUEST_COMMPAGE_ADDR |
+			offsetof(struct kvm_mips_commpage, cop0.reg[rd][sel]);
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		if (sizeof(vcpu->arch.cop0->reg[0][0]) == 8)
+			mfc0_inst.i_format.simmediate |= 4;
+#endif
 	}
 
-	return 0;
+	return kvm_mips_trans_replace(vcpu, opc, mfc0_inst);
 }
 
-int kvm_mips_trans_mtc0(uint32_t inst, uint32_t *opc, struct kvm_vcpu *vcpu)
+int kvm_mips_trans_mtc0(union mips_instruction inst, u32 *opc,
+			struct kvm_vcpu *vcpu)
 {
-	int32_t rt, rd, sel;
-	uint32_t mtc0_inst = SW_TEMPLATE;
-	unsigned long kseg0_opc, flags;
-
-	rt = (inst >> 16) & 0x1f;
-	rd = (inst >> 11) & 0x1f;
-	sel = inst & 0x7;
-
-	mtc0_inst |= ((rt & 0x1f) << 16);
-	mtc0_inst |= offsetof(struct kvm_mips_commpage, cop0.reg[rd][sel]);
-
-	if (KVM_GUEST_KSEGX(opc) == KVM_GUEST_KSEG0) {
-		kseg0_opc =
-		    CKSEG0ADDR(kvm_mips_translate_guest_kseg0_to_hpa
-			       (vcpu, (unsigned long) opc));
-		memcpy((void *)kseg0_opc, (void *)&mtc0_inst, sizeof(uint32_t));
-		local_flush_icache_range(kseg0_opc, kseg0_opc + 32);
-	} else if (KVM_GUEST_KSEGX((unsigned long) opc) == KVM_GUEST_KSEG23) {
-		local_irq_save(flags);
-		memcpy((void *)opc, (void *)&mtc0_inst, sizeof(uint32_t));
-		local_flush_icache_range((unsigned long)opc,
-					 (unsigned long)opc + 32);
-		local_irq_restore(flags);
-	} else {
-		kvm_err("%s: Invalid address: %p\n", __func__, opc);
-		return -EFAULT;
-	}
-
-	return 0;
+	union mips_instruction mtc0_inst = { 0 };
+	u32 rd, sel;
+
+	rd = inst.c0r_format.rd;
+	sel = inst.c0r_format.sel;
+
+	mtc0_inst.i_format.opcode = sw_op;
+	mtc0_inst.i_format.rt = inst.c0r_format.rt;
+	mtc0_inst.i_format.simmediate = KVM_GUEST_COMMPAGE_ADDR |
+		offsetof(struct kvm_mips_commpage, cop0.reg[rd][sel]);
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	if (sizeof(vcpu->arch.cop0->reg[0][0]) == 8)
+		mtc0_inst.i_format.simmediate |= 4;
+#endif
+
+	return kvm_mips_trans_replace(vcpu, opc, mtc0_inst);
 }
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 645c8a1982a7..6eb52b9c9818 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -52,7 +52,7 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu,
 		goto unaligned;
 
 	/* Read the instruction */
-	insn.word = kvm_get_inst((uint32_t *) epc, vcpu);
+	insn.word = kvm_get_inst((u32 *) epc, vcpu);
 
 	if (insn.word == KVM_INVALID_INST)
 		return KVM_INVALID_INST;
@@ -161,9 +161,12 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu,
 		nextpc = epc;
 		break;
 
-	case blez_op:		/* not really i_format */
-	case blezl_op:
-		/* rt field assumed to be zero */
+	case blez_op:	/* POP06 */
+#ifndef CONFIG_CPU_MIPSR6
+	case blezl_op:	/* removed in R6 */
+#endif
+		if (insn.i_format.rt != 0)
+			goto compact_branch;
 		if ((long)arch->gprs[insn.i_format.rs] <= 0)
 			epc = epc + 4 + (insn.i_format.simmediate << 2);
 		else
@@ -171,9 +174,12 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu,
 		nextpc = epc;
 		break;
 
-	case bgtz_op:
-	case bgtzl_op:
-		/* rt field assumed to be zero */
+	case bgtz_op:	/* POP07 */
+#ifndef CONFIG_CPU_MIPSR6
+	case bgtzl_op:	/* removed in R6 */
+#endif
+		if (insn.i_format.rt != 0)
+			goto compact_branch;
 		if ((long)arch->gprs[insn.i_format.rs] > 0)
 			epc = epc + 4 + (insn.i_format.simmediate << 2);
 		else
@@ -185,6 +191,40 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu,
 	case cop1_op:
 		kvm_err("%s: unsupported cop1_op\n", __func__);
 		break;
+
+#ifdef CONFIG_CPU_MIPSR6
+	/* R6 added the following compact branches with forbidden slots */
+	case blezl_op:	/* POP26 */
+	case bgtzl_op:	/* POP27 */
+		/* only rt == 0 isn't compact branch */
+		if (insn.i_format.rt != 0)
+			goto compact_branch;
+		break;
+	case pop10_op:
+	case pop30_op:
+		/* only rs == rt == 0 is reserved, rest are compact branches */
+		if (insn.i_format.rs != 0 || insn.i_format.rt != 0)
+			goto compact_branch;
+		break;
+	case pop66_op:
+	case pop76_op:
+		/* only rs == 0 isn't compact branch */
+		if (insn.i_format.rs != 0)
+			goto compact_branch;
+		break;
+compact_branch:
+		/*
+		 * If we've hit an exception on the forbidden slot, then
+		 * the branch must not have been taken.
+		 */
+		epc += 8;
+		nextpc = epc;
+		break;
+#else
+compact_branch:
+		/* Compact branches not supported before R6 */
+		break;
+#endif
 	}
 
 	return nextpc;
@@ -198,7 +238,7 @@ sigill:
 	return nextpc;
 }
 
-enum emulation_result update_pc(struct kvm_vcpu *vcpu, uint32_t cause)
+enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause)
 {
 	unsigned long branch_pc;
 	enum emulation_result er = EMULATE_DONE;
@@ -243,7 +283,7 @@ static inline int kvm_mips_count_disabled(struct kvm_vcpu *vcpu)
  *
  * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
  */
-static uint32_t kvm_mips_ktime_to_count(struct kvm_vcpu *vcpu, ktime_t now)
+static u32 kvm_mips_ktime_to_count(struct kvm_vcpu *vcpu, ktime_t now)
 {
 	s64 now_ns, periods;
 	u64 delta;
@@ -300,11 +340,11 @@ static inline ktime_t kvm_mips_count_time(struct kvm_vcpu *vcpu)
  *
  * Returns:	The current value of the guest CP0_Count register.
  */
-static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
+static u32 kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	ktime_t expires, threshold;
-	uint32_t count, compare;
+	u32 count, compare;
 	int running;
 
 	/* Calculate the biased and scaled guest CP0_Count */
@@ -315,7 +355,7 @@ static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
 	 * Find whether CP0_Count has reached the closest timer interrupt. If
 	 * not, we shouldn't inject it.
 	 */
-	if ((int32_t)(count - compare) < 0)
+	if ((s32)(count - compare) < 0)
 		return count;
 
 	/*
@@ -360,7 +400,7 @@ static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
  *
  * Returns:	The current guest CP0_Count value.
  */
-uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu)
+u32 kvm_mips_read_count(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 
@@ -387,8 +427,7 @@ uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu)
  *
  * Returns:	The ktime at the point of freeze.
  */
-static ktime_t kvm_mips_freeze_hrtimer(struct kvm_vcpu *vcpu,
-				       uint32_t *count)
+static ktime_t kvm_mips_freeze_hrtimer(struct kvm_vcpu *vcpu, u32 *count)
 {
 	ktime_t now;
 
@@ -419,16 +458,16 @@ static ktime_t kvm_mips_freeze_hrtimer(struct kvm_vcpu *vcpu,
  * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
  */
 static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu,
-				    ktime_t now, uint32_t count)
+				    ktime_t now, u32 count)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	uint32_t compare;
+	u32 compare;
 	u64 delta;
 	ktime_t expire;
 
 	/* Calculate timeout (wrap 0 to 2^32) */
 	compare = kvm_read_c0_guest_compare(cop0);
-	delta = (u64)(uint32_t)(compare - count - 1) + 1;
+	delta = (u64)(u32)(compare - count - 1) + 1;
 	delta = div_u64(delta * NSEC_PER_SEC, vcpu->arch.count_hz);
 	expire = ktime_add_ns(now, delta);
 
@@ -444,7 +483,7 @@ static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu,
  *
  * Sets the CP0_Count value and updates the timer accordingly.
  */
-void kvm_mips_write_count(struct kvm_vcpu *vcpu, uint32_t count)
+void kvm_mips_write_count(struct kvm_vcpu *vcpu, u32 count)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	ktime_t now;
@@ -538,13 +577,13 @@ int kvm_mips_set_count_hz(struct kvm_vcpu *vcpu, s64 count_hz)
  * If @ack, atomically acknowledge any pending timer interrupt, otherwise ensure
  * any pending timer interrupt is preserved.
  */
-void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack)
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, u32 compare, bool ack)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	int dc;
 	u32 old_compare = kvm_read_c0_guest_compare(cop0);
 	ktime_t now;
-	uint32_t count;
+	u32 count;
 
 	/* if unchanged, must just be an ack */
 	if (old_compare == compare) {
@@ -585,7 +624,7 @@ void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack)
 static ktime_t kvm_mips_count_disable(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	uint32_t count;
+	u32 count;
 	ktime_t now;
 
 	/* Stop hrtimer */
@@ -632,7 +671,7 @@ void kvm_mips_count_disable_cause(struct kvm_vcpu *vcpu)
 void kvm_mips_count_enable_cause(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	uint32_t count;
+	u32 count;
 
 	kvm_clear_c0_guest_cause(cop0, CAUSEF_DC);
 
@@ -661,7 +700,7 @@ int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl)
 	s64 changed = count_ctl ^ vcpu->arch.count_ctl;
 	s64 delta;
 	ktime_t expire, now;
-	uint32_t count, compare;
+	u32 count, compare;
 
 	/* Only allow defined bits to be changed */
 	if (changed & ~(s64)(KVM_REG_MIPS_COUNT_CTL_DC))
@@ -687,7 +726,7 @@ int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl)
 			 */
 			count = kvm_read_c0_guest_count(cop0);
 			compare = kvm_read_c0_guest_compare(cop0);
-			delta = (u64)(uint32_t)(compare - count - 1) + 1;
+			delta = (u64)(u32)(compare - count - 1) + 1;
 			delta = div_u64(delta * NSEC_PER_SEC,
 					vcpu->arch.count_hz);
 			expire = ktime_add_ns(vcpu->arch.count_resume, delta);
@@ -776,7 +815,7 @@ enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu)
 		  vcpu->arch.pending_exceptions);
 
 	++vcpu->stat.wait_exits;
-	trace_kvm_exit(vcpu, WAIT_EXITS);
+	trace_kvm_exit(vcpu, KVM_TRACE_EXIT_WAIT);
 	if (!vcpu->arch.pending_exceptions) {
 		vcpu->arch.wait = 1;
 		kvm_vcpu_block(vcpu);
@@ -801,9 +840,9 @@ enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu)
 enum emulation_result kvm_mips_emul_tlbr(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	uint32_t pc = vcpu->arch.pc;
+	unsigned long pc = vcpu->arch.pc;
 
-	kvm_err("[%#x] COP0_TLBR [%ld]\n", pc, kvm_read_c0_guest_index(cop0));
+	kvm_err("[%#lx] COP0_TLBR [%ld]\n", pc, kvm_read_c0_guest_index(cop0));
 	return EMULATE_FAIL;
 }
 
@@ -813,11 +852,11 @@ enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	int index = kvm_read_c0_guest_index(cop0);
 	struct kvm_mips_tlb *tlb = NULL;
-	uint32_t pc = vcpu->arch.pc;
+	unsigned long pc = vcpu->arch.pc;
 
 	if (index < 0 || index >= KVM_MIPS_GUEST_TLB_SIZE) {
 		kvm_debug("%s: illegal index: %d\n", __func__, index);
-		kvm_debug("[%#x] COP0_TLBWI [%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx, mask: %#lx)\n",
+		kvm_debug("[%#lx] COP0_TLBWI [%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx, mask: %#lx)\n",
 			  pc, index, kvm_read_c0_guest_entryhi(cop0),
 			  kvm_read_c0_guest_entrylo0(cop0),
 			  kvm_read_c0_guest_entrylo1(cop0),
@@ -834,10 +873,10 @@ enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
 
 	tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
 	tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
-	tlb->tlb_lo0 = kvm_read_c0_guest_entrylo0(cop0);
-	tlb->tlb_lo1 = kvm_read_c0_guest_entrylo1(cop0);
+	tlb->tlb_lo[0] = kvm_read_c0_guest_entrylo0(cop0);
+	tlb->tlb_lo[1] = kvm_read_c0_guest_entrylo1(cop0);
 
-	kvm_debug("[%#x] COP0_TLBWI [%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx, mask: %#lx)\n",
+	kvm_debug("[%#lx] COP0_TLBWI [%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx, mask: %#lx)\n",
 		  pc, index, kvm_read_c0_guest_entryhi(cop0),
 		  kvm_read_c0_guest_entrylo0(cop0),
 		  kvm_read_c0_guest_entrylo1(cop0),
@@ -851,7 +890,7 @@ enum emulation_result kvm_mips_emul_tlbwr(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_mips_tlb *tlb = NULL;
-	uint32_t pc = vcpu->arch.pc;
+	unsigned long pc = vcpu->arch.pc;
 	int index;
 
 	get_random_bytes(&index, sizeof(index));
@@ -867,10 +906,10 @@ enum emulation_result kvm_mips_emul_tlbwr(struct kvm_vcpu *vcpu)
 
 	tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
 	tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
-	tlb->tlb_lo0 = kvm_read_c0_guest_entrylo0(cop0);
-	tlb->tlb_lo1 = kvm_read_c0_guest_entrylo1(cop0);
+	tlb->tlb_lo[0] = kvm_read_c0_guest_entrylo0(cop0);
+	tlb->tlb_lo[1] = kvm_read_c0_guest_entrylo1(cop0);
 
-	kvm_debug("[%#x] COP0_TLBWR[%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx)\n",
+	kvm_debug("[%#lx] COP0_TLBWR[%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx)\n",
 		  pc, index, kvm_read_c0_guest_entryhi(cop0),
 		  kvm_read_c0_guest_entrylo0(cop0),
 		  kvm_read_c0_guest_entrylo1(cop0));
@@ -882,14 +921,14 @@ enum emulation_result kvm_mips_emul_tlbp(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	long entryhi = kvm_read_c0_guest_entryhi(cop0);
-	uint32_t pc = vcpu->arch.pc;
+	unsigned long pc = vcpu->arch.pc;
 	int index = -1;
 
 	index = kvm_mips_guest_tlb_lookup(vcpu, entryhi);
 
 	kvm_write_c0_guest_index(cop0, index);
 
-	kvm_debug("[%#x] COP0_TLBP (entryhi: %#lx), index: %d\n", pc, entryhi,
+	kvm_debug("[%#lx] COP0_TLBP (entryhi: %#lx), index: %d\n", pc, entryhi,
 		  index);
 
 	return EMULATE_DONE;
@@ -922,8 +961,8 @@ unsigned int kvm_mips_config1_wrmask(struct kvm_vcpu *vcpu)
  */
 unsigned int kvm_mips_config3_wrmask(struct kvm_vcpu *vcpu)
 {
-	/* Config4 is optional */
-	unsigned int mask = MIPS_CONF_M;
+	/* Config4 and ULRI are optional */
+	unsigned int mask = MIPS_CONF_M | MIPS_CONF3_ULRI;
 
 	/* Permit MSA to be present if MSA is supported */
 	if (kvm_mips_guest_can_have_msa(&vcpu->arch))
@@ -942,7 +981,12 @@ unsigned int kvm_mips_config3_wrmask(struct kvm_vcpu *vcpu)
 unsigned int kvm_mips_config4_wrmask(struct kvm_vcpu *vcpu)
 {
 	/* Config5 is optional */
-	return MIPS_CONF_M;
+	unsigned int mask = MIPS_CONF_M;
+
+	/* KScrExist */
+	mask |= (unsigned int)vcpu->arch.kscratch_enabled << 16;
+
+	return mask;
 }
 
 /**
@@ -973,14 +1017,14 @@ unsigned int kvm_mips_config5_wrmask(struct kvm_vcpu *vcpu)
 	return mask;
 }
 
-enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
-					   uint32_t cause, struct kvm_run *run,
+enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst,
+					   u32 *opc, u32 cause,
+					   struct kvm_run *run,
 					   struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	enum emulation_result er = EMULATE_DONE;
-	int32_t rt, rd, copz, sel, co_bit, op;
-	uint32_t pc = vcpu->arch.pc;
+	u32 rt, rd, sel;
 	unsigned long curr_pc;
 
 	/*
@@ -992,16 +1036,8 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 	if (er == EMULATE_FAIL)
 		return er;
 
-	copz = (inst >> 21) & 0x1f;
-	rt = (inst >> 16) & 0x1f;
-	rd = (inst >> 11) & 0x1f;
-	sel = inst & 0x7;
-	co_bit = (inst >> 25) & 1;
-
-	if (co_bit) {
-		op = (inst) & 0xff;
-
-		switch (op) {
+	if (inst.co_format.co) {
+		switch (inst.co_format.func) {
 		case tlbr_op:	/*  Read indexed TLB entry  */
 			er = kvm_mips_emul_tlbr(vcpu);
 			break;
@@ -1020,47 +1056,58 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 		case eret_op:
 			er = kvm_mips_emul_eret(vcpu);
 			goto dont_update_pc;
-			break;
 		case wait_op:
 			er = kvm_mips_emul_wait(vcpu);
 			break;
 		}
 	} else {
-		switch (copz) {
+		rt = inst.c0r_format.rt;
+		rd = inst.c0r_format.rd;
+		sel = inst.c0r_format.sel;
+
+		switch (inst.c0r_format.rs) {
 		case mfc_op:
 #ifdef CONFIG_KVM_MIPS_DEBUG_COP0_COUNTERS
 			cop0->stat[rd][sel]++;
 #endif
 			/* Get reg */
 			if ((rd == MIPS_CP0_COUNT) && (sel == 0)) {
-				vcpu->arch.gprs[rt] = kvm_mips_read_count(vcpu);
+				vcpu->arch.gprs[rt] =
+				    (s32)kvm_mips_read_count(vcpu);
 			} else if ((rd == MIPS_CP0_ERRCTL) && (sel == 0)) {
 				vcpu->arch.gprs[rt] = 0x0;
 #ifdef CONFIG_KVM_MIPS_DYN_TRANS
 				kvm_mips_trans_mfc0(inst, opc, vcpu);
 #endif
 			} else {
-				vcpu->arch.gprs[rt] = cop0->reg[rd][sel];
+				vcpu->arch.gprs[rt] = (s32)cop0->reg[rd][sel];
 
 #ifdef CONFIG_KVM_MIPS_DYN_TRANS
 				kvm_mips_trans_mfc0(inst, opc, vcpu);
 #endif
 			}
 
-			kvm_debug
-			    ("[%#x] MFCz[%d][%d], vcpu->arch.gprs[%d]: %#lx\n",
-			     pc, rd, sel, rt, vcpu->arch.gprs[rt]);
-
+			trace_kvm_hwr(vcpu, KVM_TRACE_MFC0,
+				      KVM_TRACE_COP0(rd, sel),
+				      vcpu->arch.gprs[rt]);
 			break;
 
 		case dmfc_op:
 			vcpu->arch.gprs[rt] = cop0->reg[rd][sel];
+
+			trace_kvm_hwr(vcpu, KVM_TRACE_DMFC0,
+				      KVM_TRACE_COP0(rd, sel),
+				      vcpu->arch.gprs[rt]);
 			break;
 
 		case mtc_op:
 #ifdef CONFIG_KVM_MIPS_DEBUG_COP0_COUNTERS
 			cop0->stat[rd][sel]++;
 #endif
+			trace_kvm_hwr(vcpu, KVM_TRACE_MTC0,
+				      KVM_TRACE_COP0(rd, sel),
+				      vcpu->arch.gprs[rt]);
+
 			if ((rd == MIPS_CP0_TLB_INDEX)
 			    && (vcpu->arch.gprs[rt] >=
 				KVM_MIPS_GUEST_TLB_SIZE)) {
@@ -1078,16 +1125,15 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 				kvm_err("MTCz, cop0->reg[EBASE]: %#lx\n",
 					kvm_read_c0_guest_ebase(cop0));
 			} else if (rd == MIPS_CP0_TLB_HI && sel == 0) {
-				uint32_t nasid =
+				u32 nasid =
 					vcpu->arch.gprs[rt] & KVM_ENTRYHI_ASID;
 				if ((KSEGX(vcpu->arch.gprs[rt]) != CKSEG0) &&
 				    ((kvm_read_c0_guest_entryhi(cop0) &
 				      KVM_ENTRYHI_ASID) != nasid)) {
-					kvm_debug("MTCz, change ASID from %#lx to %#lx\n",
+					trace_kvm_asid_change(vcpu,
 						kvm_read_c0_guest_entryhi(cop0)
-						& KVM_ENTRYHI_ASID,
-						vcpu->arch.gprs[rt]
-						& KVM_ENTRYHI_ASID);
+							& KVM_ENTRYHI_ASID,
+						nasid);
 
 					/* Blow away the shadow host TLBs */
 					kvm_mips_flush_host_tlb(1);
@@ -1100,10 +1146,6 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 				kvm_mips_write_count(vcpu, vcpu->arch.gprs[rt]);
 				goto done;
 			} else if ((rd == MIPS_CP0_COMPARE) && (sel == 0)) {
-				kvm_debug("[%#x] MTCz, COMPARE %#lx <- %#lx\n",
-					  pc, kvm_read_c0_guest_compare(cop0),
-					  vcpu->arch.gprs[rt]);
-
 				/* If we are writing to COMPARE */
 				/* Clear pending timer interrupt, if any */
 				kvm_mips_write_compare(vcpu,
@@ -1155,7 +1197,7 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 				 * it first.
 				 */
 				if (change & ST0_CU1 && !(val & ST0_FR) &&
-				    vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA)
+				    vcpu->arch.aux_inuse & KVM_MIPS_AUX_MSA)
 					kvm_lose_fpu(vcpu);
 
 				/*
@@ -1166,7 +1208,7 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 				 * the near future.
 				 */
 				if (change & ST0_CU1 &&
-				    vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU)
+				    vcpu->arch.aux_inuse & KVM_MIPS_AUX_FPU)
 					change_c0_status(ST0_CU1, val);
 
 				preempt_enable();
@@ -1201,7 +1243,7 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 				 * context is already loaded.
 				 */
 				if (change & MIPS_CONF5_FRE &&
-				    vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU)
+				    vcpu->arch.aux_inuse & KVM_MIPS_AUX_FPU)
 					change_c0_config5(MIPS_CONF5_FRE, val);
 
 				/*
@@ -1211,7 +1253,7 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 				 * quickly enabled again in the near future.
 				 */
 				if (change & MIPS_CONF5_MSAEN &&
-				    vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA)
+				    vcpu->arch.aux_inuse & KVM_MIPS_AUX_MSA)
 					change_c0_config5(MIPS_CONF5_MSAEN,
 							  val);
 
@@ -1219,7 +1261,7 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 
 				kvm_write_c0_guest_config5(cop0, val);
 			} else if ((rd == MIPS_CP0_CAUSE) && (sel == 0)) {
-				uint32_t old_cause, new_cause;
+				u32 old_cause, new_cause;
 
 				old_cause = kvm_read_c0_guest_cause(cop0);
 				new_cause = vcpu->arch.gprs[rt];
@@ -1233,20 +1275,30 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 					else
 						kvm_mips_count_enable_cause(vcpu);
 				}
+			} else if ((rd == MIPS_CP0_HWRENA) && (sel == 0)) {
+				u32 mask = MIPS_HWRENA_CPUNUM |
+					   MIPS_HWRENA_SYNCISTEP |
+					   MIPS_HWRENA_CC |
+					   MIPS_HWRENA_CCRES;
+
+				if (kvm_read_c0_guest_config3(cop0) &
+				    MIPS_CONF3_ULRI)
+					mask |= MIPS_HWRENA_ULR;
+				cop0->reg[rd][sel] = vcpu->arch.gprs[rt] & mask;
 			} else {
 				cop0->reg[rd][sel] = vcpu->arch.gprs[rt];
 #ifdef CONFIG_KVM_MIPS_DYN_TRANS
 				kvm_mips_trans_mtc0(inst, opc, vcpu);
 #endif
 			}
-
-			kvm_debug("[%#x] MTCz, cop0->reg[%d][%d]: %#lx\n", pc,
-				  rd, sel, cop0->reg[rd][sel]);
 			break;
 
 		case dmtc_op:
 			kvm_err("!!!!!!![%#lx]dmtc_op: rt: %d, rd: %d, sel: %d!!!!!!\n",
 				vcpu->arch.pc, rt, rd, sel);
+			trace_kvm_hwr(vcpu, KVM_TRACE_DMTC0,
+				      KVM_TRACE_COP0(rd, sel),
+				      vcpu->arch.gprs[rt]);
 			er = EMULATE_FAIL;
 			break;
 
@@ -1258,7 +1310,7 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 				vcpu->arch.gprs[rt] =
 				    kvm_read_c0_guest_status(cop0);
 			/* EI */
-			if (inst & 0x20) {
+			if (inst.mfmc0_format.sc) {
 				kvm_debug("[%#lx] mfmc0_op: EI\n",
 					  vcpu->arch.pc);
 				kvm_set_c0_guest_status(cop0, ST0_IE);
@@ -1272,9 +1324,8 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 
 		case wrpgpr_op:
 			{
-				uint32_t css =
-				    cop0->reg[MIPS_CP0_STATUS][2] & 0xf;
-				uint32_t pss =
+				u32 css = cop0->reg[MIPS_CP0_STATUS][2] & 0xf;
+				u32 pss =
 				    (cop0->reg[MIPS_CP0_STATUS][2] >> 6) & 0xf;
 				/*
 				 * We don't support any shadow register sets, so
@@ -1291,7 +1342,7 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
 			break;
 		default:
 			kvm_err("[%#lx]MachEmulateCP0: unsupported COP0, copz: 0x%x\n",
-				vcpu->arch.pc, copz);
+				vcpu->arch.pc, inst.c0r_format.rs);
 			er = EMULATE_FAIL;
 			break;
 		}
@@ -1312,13 +1363,14 @@ dont_update_pc:
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_store(uint32_t inst, uint32_t cause,
+enum emulation_result kvm_mips_emulate_store(union mips_instruction inst,
+					     u32 cause,
 					     struct kvm_run *run,
 					     struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DO_MMIO;
-	int32_t op, base, rt, offset;
-	uint32_t bytes;
+	u32 rt;
+	u32 bytes;
 	void *data = run->mmio.data;
 	unsigned long curr_pc;
 
@@ -1331,12 +1383,9 @@ enum emulation_result kvm_mips_emulate_store(uint32_t inst, uint32_t cause,
 	if (er == EMULATE_FAIL)
 		return er;
 
-	rt = (inst >> 16) & 0x1f;
-	base = (inst >> 21) & 0x1f;
-	offset = inst & 0xffff;
-	op = (inst >> 26) & 0x3f;
+	rt = inst.i_format.rt;
 
-	switch (op) {
+	switch (inst.i_format.opcode) {
 	case sb_op:
 		bytes = 1;
 		if (bytes > sizeof(run->mmio.data)) {
@@ -1357,7 +1406,7 @@ enum emulation_result kvm_mips_emulate_store(uint32_t inst, uint32_t cause,
 		*(u8 *) data = vcpu->arch.gprs[rt];
 		kvm_debug("OP_SB: eaddr: %#lx, gpr: %#lx, data: %#x\n",
 			  vcpu->arch.host_cp0_badvaddr, vcpu->arch.gprs[rt],
-			  *(uint8_t *) data);
+			  *(u8 *) data);
 
 		break;
 
@@ -1379,11 +1428,11 @@ enum emulation_result kvm_mips_emulate_store(uint32_t inst, uint32_t cause,
 		run->mmio.is_write = 1;
 		vcpu->mmio_needed = 1;
 		vcpu->mmio_is_write = 1;
-		*(uint32_t *) data = vcpu->arch.gprs[rt];
+		*(u32 *) data = vcpu->arch.gprs[rt];
 
 		kvm_debug("[%#lx] OP_SW: eaddr: %#lx, gpr: %#lx, data: %#x\n",
 			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
-			  vcpu->arch.gprs[rt], *(uint32_t *) data);
+			  vcpu->arch.gprs[rt], *(u32 *) data);
 		break;
 
 	case sh_op:
@@ -1404,15 +1453,16 @@ enum emulation_result kvm_mips_emulate_store(uint32_t inst, uint32_t cause,
 		run->mmio.is_write = 1;
 		vcpu->mmio_needed = 1;
 		vcpu->mmio_is_write = 1;
-		*(uint16_t *) data = vcpu->arch.gprs[rt];
+		*(u16 *) data = vcpu->arch.gprs[rt];
 
 		kvm_debug("[%#lx] OP_SH: eaddr: %#lx, gpr: %#lx, data: %#x\n",
 			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
-			  vcpu->arch.gprs[rt], *(uint32_t *) data);
+			  vcpu->arch.gprs[rt], *(u32 *) data);
 		break;
 
 	default:
-		kvm_err("Store not yet supported");
+		kvm_err("Store not yet supported (inst=0x%08x)\n",
+			inst.word);
 		er = EMULATE_FAIL;
 		break;
 	}
@@ -1424,18 +1474,16 @@ enum emulation_result kvm_mips_emulate_store(uint32_t inst, uint32_t cause,
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
-					    struct kvm_run *run,
+enum emulation_result kvm_mips_emulate_load(union mips_instruction inst,
+					    u32 cause, struct kvm_run *run,
 					    struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DO_MMIO;
-	int32_t op, base, rt, offset;
-	uint32_t bytes;
+	u32 op, rt;
+	u32 bytes;
 
-	rt = (inst >> 16) & 0x1f;
-	base = (inst >> 21) & 0x1f;
-	offset = inst & 0xffff;
-	op = (inst >> 26) & 0x3f;
+	rt = inst.i_format.rt;
+	op = inst.i_format.opcode;
 
 	vcpu->arch.pending_load_cause = cause;
 	vcpu->arch.io_gpr = rt;
@@ -1521,7 +1569,8 @@ enum emulation_result kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
 		break;
 
 	default:
-		kvm_err("Load not yet supported");
+		kvm_err("Load not yet supported (inst=0x%08x)\n",
+			inst.word);
 		er = EMULATE_FAIL;
 		break;
 	}
@@ -1529,40 +1578,15 @@ enum emulation_result kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
 	return er;
 }
 
-int kvm_mips_sync_icache(unsigned long va, struct kvm_vcpu *vcpu)
-{
-	unsigned long offset = (va & ~PAGE_MASK);
-	struct kvm *kvm = vcpu->kvm;
-	unsigned long pa;
-	gfn_t gfn;
-	kvm_pfn_t pfn;
-
-	gfn = va >> PAGE_SHIFT;
-
-	if (gfn >= kvm->arch.guest_pmap_npages) {
-		kvm_err("%s: Invalid gfn: %#llx\n", __func__, gfn);
-		kvm_mips_dump_host_tlbs();
-		kvm_arch_vcpu_dump_regs(vcpu);
-		return -1;
-	}
-	pfn = kvm->arch.guest_pmap[gfn];
-	pa = (pfn << PAGE_SHIFT) | offset;
-
-	kvm_debug("%s: va: %#lx, unmapped: %#x\n", __func__, va,
-		  CKSEG0ADDR(pa));
-
-	local_flush_icache_range(CKSEG0ADDR(pa), 32);
-	return 0;
-}
-
-enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
-					     uint32_t cause,
+enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst,
+					     u32 *opc, u32 cause,
 					     struct kvm_run *run,
 					     struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	enum emulation_result er = EMULATE_DONE;
-	int32_t offset, cache, op_inst, op, base;
+	u32 cache, op_inst, op, base;
+	s16 offset;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
 	unsigned long va;
 	unsigned long curr_pc;
@@ -1576,9 +1600,12 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 	if (er == EMULATE_FAIL)
 		return er;
 
-	base = (inst >> 21) & 0x1f;
-	op_inst = (inst >> 16) & 0x1f;
-	offset = (int16_t)inst;
+	base = inst.i_format.rs;
+	op_inst = inst.i_format.rt;
+	if (cpu_has_mips_r6)
+		offset = inst.spec3_format.simmediate;
+	else
+		offset = inst.i_format.simmediate;
 	cache = op_inst & CacheOp_Cache;
 	op = op_inst & CacheOp_Op;
 
@@ -1634,7 +1661,6 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 						   (cop0) & KVM_ENTRYHI_ASID));
 
 		if (index < 0) {
-			vcpu->arch.host_cp0_entryhi = (va & VPN2_MASK);
 			vcpu->arch.host_cp0_badvaddr = va;
 			vcpu->arch.pc = curr_pc;
 			er = kvm_mips_emulate_tlbmiss_ld(cause, NULL, run,
@@ -1659,9 +1685,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 				 * We fault an entry from the guest tlb to the
 				 * shadow host TLB
 				 */
-				kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
-								     NULL,
-								     NULL);
+				kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb);
 			}
 		}
 	} else {
@@ -1714,20 +1738,20 @@ dont_update_pc:
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_inst(unsigned long cause, uint32_t *opc,
+enum emulation_result kvm_mips_emulate_inst(u32 cause, u32 *opc,
 					    struct kvm_run *run,
 					    struct kvm_vcpu *vcpu)
 {
+	union mips_instruction inst;
 	enum emulation_result er = EMULATE_DONE;
-	uint32_t inst;
 
 	/* Fetch the instruction. */
 	if (cause & CAUSEF_BD)
 		opc += 1;
 
-	inst = kvm_get_inst(opc, vcpu);
+	inst.word = kvm_get_inst(opc, vcpu);
 
-	switch (((union mips_instruction)inst).r_format.opcode) {
+	switch (inst.r_format.opcode) {
 	case cop0_op:
 		er = kvm_mips_emulate_CP0(inst, opc, cause, run, vcpu);
 		break;
@@ -1744,15 +1768,31 @@ enum emulation_result kvm_mips_emulate_inst(unsigned long cause, uint32_t *opc,
 		er = kvm_mips_emulate_load(inst, cause, run, vcpu);
 		break;
 
+#ifndef CONFIG_CPU_MIPSR6
 	case cache_op:
 		++vcpu->stat.cache_exits;
-		trace_kvm_exit(vcpu, CACHE_EXITS);
+		trace_kvm_exit(vcpu, KVM_TRACE_EXIT_CACHE);
 		er = kvm_mips_emulate_cache(inst, opc, cause, run, vcpu);
 		break;
+#else
+	case spec3_op:
+		switch (inst.spec3_format.func) {
+		case cache6_op:
+			++vcpu->stat.cache_exits;
+			trace_kvm_exit(vcpu, KVM_TRACE_EXIT_CACHE);
+			er = kvm_mips_emulate_cache(inst, opc, cause, run,
+						    vcpu);
+			break;
+		default:
+			goto unknown;
+		};
+		break;
+unknown:
+#endif
 
 	default:
 		kvm_err("Instruction emulation not supported (%p/%#x)\n", opc,
-			inst);
+			inst.word);
 		kvm_arch_vcpu_dump_regs(vcpu);
 		er = EMULATE_FAIL;
 		break;
@@ -1761,8 +1801,8 @@ enum emulation_result kvm_mips_emulate_inst(unsigned long cause, uint32_t *opc,
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_syscall(unsigned long cause,
-					       uint32_t *opc,
+enum emulation_result kvm_mips_emulate_syscall(u32 cause,
+					       u32 *opc,
 					       struct kvm_run *run,
 					       struct kvm_vcpu *vcpu)
 {
@@ -1796,8 +1836,8 @@ enum emulation_result kvm_mips_emulate_syscall(unsigned long cause,
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_tlbmiss_ld(unsigned long cause,
-						  uint32_t *opc,
+enum emulation_result kvm_mips_emulate_tlbmiss_ld(u32 cause,
+						  u32 *opc,
 						  struct kvm_run *run,
 						  struct kvm_vcpu *vcpu)
 {
@@ -1842,8 +1882,8 @@ enum emulation_result kvm_mips_emulate_tlbmiss_ld(unsigned long cause,
 	return EMULATE_DONE;
 }
 
-enum emulation_result kvm_mips_emulate_tlbinv_ld(unsigned long cause,
-						 uint32_t *opc,
+enum emulation_result kvm_mips_emulate_tlbinv_ld(u32 cause,
+						 u32 *opc,
 						 struct kvm_run *run,
 						 struct kvm_vcpu *vcpu)
 {
@@ -1888,8 +1928,8 @@ enum emulation_result kvm_mips_emulate_tlbinv_ld(unsigned long cause,
 	return EMULATE_DONE;
 }
 
-enum emulation_result kvm_mips_emulate_tlbmiss_st(unsigned long cause,
-						  uint32_t *opc,
+enum emulation_result kvm_mips_emulate_tlbmiss_st(u32 cause,
+						  u32 *opc,
 						  struct kvm_run *run,
 						  struct kvm_vcpu *vcpu)
 {
@@ -1932,8 +1972,8 @@ enum emulation_result kvm_mips_emulate_tlbmiss_st(unsigned long cause,
 	return EMULATE_DONE;
 }
 
-enum emulation_result kvm_mips_emulate_tlbinv_st(unsigned long cause,
-						 uint32_t *opc,
+enum emulation_result kvm_mips_emulate_tlbinv_st(u32 cause,
+						 u32 *opc,
 						 struct kvm_run *run,
 						 struct kvm_vcpu *vcpu)
 {
@@ -1977,7 +2017,7 @@ enum emulation_result kvm_mips_emulate_tlbinv_st(unsigned long cause,
 }
 
 /* TLBMOD: store into address matching TLB with Dirty bit off */
-enum emulation_result kvm_mips_handle_tlbmod(unsigned long cause, uint32_t *opc,
+enum emulation_result kvm_mips_handle_tlbmod(u32 cause, u32 *opc,
 					     struct kvm_run *run,
 					     struct kvm_vcpu *vcpu)
 {
@@ -2005,8 +2045,8 @@ enum emulation_result kvm_mips_handle_tlbmod(unsigned long cause, uint32_t *opc,
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_tlbmod(unsigned long cause,
-					      uint32_t *opc,
+enum emulation_result kvm_mips_emulate_tlbmod(u32 cause,
+					      u32 *opc,
 					      struct kvm_run *run,
 					      struct kvm_vcpu *vcpu)
 {
@@ -2048,8 +2088,8 @@ enum emulation_result kvm_mips_emulate_tlbmod(unsigned long cause,
 	return EMULATE_DONE;
 }
 
-enum emulation_result kvm_mips_emulate_fpu_exc(unsigned long cause,
-					       uint32_t *opc,
+enum emulation_result kvm_mips_emulate_fpu_exc(u32 cause,
+					       u32 *opc,
 					       struct kvm_run *run,
 					       struct kvm_vcpu *vcpu)
 {
@@ -2077,8 +2117,8 @@ enum emulation_result kvm_mips_emulate_fpu_exc(unsigned long cause,
 	return EMULATE_DONE;
 }
 
-enum emulation_result kvm_mips_emulate_ri_exc(unsigned long cause,
-					      uint32_t *opc,
+enum emulation_result kvm_mips_emulate_ri_exc(u32 cause,
+					      u32 *opc,
 					      struct kvm_run *run,
 					      struct kvm_vcpu *vcpu)
 {
@@ -2112,8 +2152,8 @@ enum emulation_result kvm_mips_emulate_ri_exc(unsigned long cause,
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_bp_exc(unsigned long cause,
-					      uint32_t *opc,
+enum emulation_result kvm_mips_emulate_bp_exc(u32 cause,
+					      u32 *opc,
 					      struct kvm_run *run,
 					      struct kvm_vcpu *vcpu)
 {
@@ -2147,8 +2187,8 @@ enum emulation_result kvm_mips_emulate_bp_exc(unsigned long cause,
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_trap_exc(unsigned long cause,
-						uint32_t *opc,
+enum emulation_result kvm_mips_emulate_trap_exc(u32 cause,
+						u32 *opc,
 						struct kvm_run *run,
 						struct kvm_vcpu *vcpu)
 {
@@ -2182,8 +2222,8 @@ enum emulation_result kvm_mips_emulate_trap_exc(unsigned long cause,
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_msafpe_exc(unsigned long cause,
-						  uint32_t *opc,
+enum emulation_result kvm_mips_emulate_msafpe_exc(u32 cause,
+						  u32 *opc,
 						  struct kvm_run *run,
 						  struct kvm_vcpu *vcpu)
 {
@@ -2217,8 +2257,8 @@ enum emulation_result kvm_mips_emulate_msafpe_exc(unsigned long cause,
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_fpe_exc(unsigned long cause,
-					       uint32_t *opc,
+enum emulation_result kvm_mips_emulate_fpe_exc(u32 cause,
+					       u32 *opc,
 					       struct kvm_run *run,
 					       struct kvm_vcpu *vcpu)
 {
@@ -2252,8 +2292,8 @@ enum emulation_result kvm_mips_emulate_fpe_exc(unsigned long cause,
 	return er;
 }
 
-enum emulation_result kvm_mips_emulate_msadis_exc(unsigned long cause,
-						  uint32_t *opc,
+enum emulation_result kvm_mips_emulate_msadis_exc(u32 cause,
+						  u32 *opc,
 						  struct kvm_run *run,
 						  struct kvm_vcpu *vcpu)
 {
@@ -2287,22 +2327,7 @@ enum emulation_result kvm_mips_emulate_msadis_exc(unsigned long cause,
 	return er;
 }
 
-/* ll/sc, rdhwr, sync emulation */
-
-#define OPCODE 0xfc000000
-#define BASE   0x03e00000
-#define RT     0x001f0000
-#define OFFSET 0x0000ffff
-#define LL     0xc0000000
-#define SC     0xe0000000
-#define SPEC0  0x00000000
-#define SPEC3  0x7c000000
-#define RD     0x0000f800
-#define FUNC   0x0000003f
-#define SYNC   0x0000000f
-#define RDHWR  0x0000003b
-
-enum emulation_result kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
+enum emulation_result kvm_mips_handle_ri(u32 cause, u32 *opc,
 					 struct kvm_run *run,
 					 struct kvm_vcpu *vcpu)
 {
@@ -2310,7 +2335,7 @@ enum emulation_result kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
 	enum emulation_result er = EMULATE_DONE;
 	unsigned long curr_pc;
-	uint32_t inst;
+	union mips_instruction inst;
 
 	/*
 	 * Update PC and hold onto current PC in case there is
@@ -2325,17 +2350,22 @@ enum emulation_result kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 	if (cause & CAUSEF_BD)
 		opc += 1;
 
-	inst = kvm_get_inst(opc, vcpu);
+	inst.word = kvm_get_inst(opc, vcpu);
 
-	if (inst == KVM_INVALID_INST) {
+	if (inst.word == KVM_INVALID_INST) {
 		kvm_err("%s: Cannot get inst @ %p\n", __func__, opc);
 		return EMULATE_FAIL;
 	}
 
-	if ((inst & OPCODE) == SPEC3 && (inst & FUNC) == RDHWR) {
+	if (inst.r_format.opcode == spec3_op &&
+	    inst.r_format.func == rdhwr_op &&
+	    inst.r_format.rs == 0 &&
+	    (inst.r_format.re >> 3) == 0) {
 		int usermode = !KVM_GUEST_KERNEL_MODE(vcpu);
-		int rd = (inst & RD) >> 11;
-		int rt = (inst & RT) >> 16;
+		int rd = inst.r_format.rd;
+		int rt = inst.r_format.rt;
+		int sel = inst.r_format.re & 0x7;
+
 		/* If usermode, check RDHWR rd is allowed by guest HWREna */
 		if (usermode && !(kvm_read_c0_guest_hwrena(cop0) & BIT(rd))) {
 			kvm_debug("RDHWR %#x disallowed by HWREna @ %p\n",
@@ -2343,17 +2373,17 @@ enum emulation_result kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 			goto emulate_ri;
 		}
 		switch (rd) {
-		case 0:	/* CPU number */
-			arch->gprs[rt] = 0;
+		case MIPS_HWR_CPUNUM:		/* CPU number */
+			arch->gprs[rt] = vcpu->vcpu_id;
 			break;
-		case 1:	/* SYNCI length */
+		case MIPS_HWR_SYNCISTEP:	/* SYNCI length */
 			arch->gprs[rt] = min(current_cpu_data.dcache.linesz,
 					     current_cpu_data.icache.linesz);
 			break;
-		case 2:	/* Read count register */
-			arch->gprs[rt] = kvm_mips_read_count(vcpu);
+		case MIPS_HWR_CC:		/* Read count register */
+			arch->gprs[rt] = (s32)kvm_mips_read_count(vcpu);
 			break;
-		case 3:	/* Count register resolution */
+		case MIPS_HWR_CCRES:		/* Count register resolution */
 			switch (current_cpu_data.cputype) {
 			case CPU_20KC:
 			case CPU_25KF:
@@ -2363,7 +2393,7 @@ enum emulation_result kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 				arch->gprs[rt] = 2;
 			}
 			break;
-		case 29:
+		case MIPS_HWR_ULR:		/* Read UserLocal register */
 			arch->gprs[rt] = kvm_read_c0_guest_userlocal(cop0);
 			break;
 
@@ -2371,8 +2401,12 @@ enum emulation_result kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 			kvm_debug("RDHWR %#x not supported @ %p\n", rd, opc);
 			goto emulate_ri;
 		}
+
+		trace_kvm_hwr(vcpu, KVM_TRACE_RDHWR, KVM_TRACE_HWR(rd, sel),
+			      vcpu->arch.gprs[rt]);
 	} else {
-		kvm_debug("Emulate RI not supported @ %p: %#x\n", opc, inst);
+		kvm_debug("Emulate RI not supported @ %p: %#x\n",
+			  opc, inst.word);
 		goto emulate_ri;
 	}
 
@@ -2405,19 +2439,19 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 
 	switch (run->mmio.len) {
 	case 4:
-		*gpr = *(int32_t *) run->mmio.data;
+		*gpr = *(s32 *) run->mmio.data;
 		break;
 
 	case 2:
 		if (vcpu->mmio_needed == 2)
-			*gpr = *(int16_t *) run->mmio.data;
+			*gpr = *(s16 *) run->mmio.data;
 		else
-			*gpr = *(uint16_t *)run->mmio.data;
+			*gpr = *(u16 *)run->mmio.data;
 
 		break;
 	case 1:
 		if (vcpu->mmio_needed == 2)
-			*gpr = *(int8_t *) run->mmio.data;
+			*gpr = *(s8 *) run->mmio.data;
 		else
 			*gpr = *(u8 *) run->mmio.data;
 		break;
@@ -2432,12 +2466,12 @@ done:
 	return er;
 }
 
-static enum emulation_result kvm_mips_emulate_exc(unsigned long cause,
-						  uint32_t *opc,
+static enum emulation_result kvm_mips_emulate_exc(u32 cause,
+						  u32 *opc,
 						  struct kvm_run *run,
 						  struct kvm_vcpu *vcpu)
 {
-	uint32_t exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
+	u32 exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
 	enum emulation_result er = EMULATE_DONE;
@@ -2470,13 +2504,13 @@ static enum emulation_result kvm_mips_emulate_exc(unsigned long cause,
 	return er;
 }
 
-enum emulation_result kvm_mips_check_privilege(unsigned long cause,
-					       uint32_t *opc,
+enum emulation_result kvm_mips_check_privilege(u32 cause,
+					       u32 *opc,
 					       struct kvm_run *run,
 					       struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DONE;
-	uint32_t exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
+	u32 exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
 	unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr;
 
 	int usermode = !KVM_GUEST_KERNEL_MODE(vcpu);
@@ -2566,18 +2600,18 @@ enum emulation_result kvm_mips_check_privilege(unsigned long cause,
  * (2) TLB entry is present in the Guest TLB but not in the shadow, in this
  *     case we inject the TLB from the Guest TLB into the shadow host TLB
  */
-enum emulation_result kvm_mips_handle_tlbmiss(unsigned long cause,
-					      uint32_t *opc,
+enum emulation_result kvm_mips_handle_tlbmiss(u32 cause,
+					      u32 *opc,
 					      struct kvm_run *run,
 					      struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DONE;
-	uint32_t exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
+	u32 exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
 	unsigned long va = vcpu->arch.host_cp0_badvaddr;
 	int index;
 
-	kvm_debug("kvm_mips_handle_tlbmiss: badvaddr: %#lx, entryhi: %#lx\n",
-		  vcpu->arch.host_cp0_badvaddr, vcpu->arch.host_cp0_entryhi);
+	kvm_debug("kvm_mips_handle_tlbmiss: badvaddr: %#lx\n",
+		  vcpu->arch.host_cp0_badvaddr);
 
 	/*
 	 * KVM would not have got the exception if this entry was valid in the
@@ -2620,13 +2654,12 @@ enum emulation_result kvm_mips_handle_tlbmiss(unsigned long cause,
 			}
 		} else {
 			kvm_debug("Injecting hi: %#lx, lo0: %#lx, lo1: %#lx into shadow host TLB\n",
-				  tlb->tlb_hi, tlb->tlb_lo0, tlb->tlb_lo1);
+				  tlb->tlb_hi, tlb->tlb_lo[0], tlb->tlb_lo[1]);
 			/*
 			 * OK we have a Guest TLB entry, now inject it into the
 			 * shadow host TLB
 			 */
-			kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, NULL,
-							     NULL);
+			kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb);
 		}
 	}
 
diff --git a/arch/mips/kvm/entry.c b/arch/mips/kvm/entry.c
new file mode 100644
index 000000000000..6a02b3a3fa65
--- /dev/null
+++ b/arch/mips/kvm/entry.c
@@ -0,0 +1,701 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Generation of main entry point for the guest, exception handling.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ *
+ * Copyright (C) 2016 Imagination Technologies Ltd.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/msa.h>
+#include <asm/setup.h>
+#include <asm/uasm.h>
+
+/* Register names */
+#define ZERO		0
+#define AT		1
+#define V0		2
+#define V1		3
+#define A0		4
+#define A1		5
+
+#if _MIPS_SIM == _MIPS_SIM_ABI32
+#define T0		8
+#define T1		9
+#define T2		10
+#define T3		11
+#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
+
+#if _MIPS_SIM == _MIPS_SIM_ABI64 || _MIPS_SIM == _MIPS_SIM_NABI32
+#define T0		12
+#define T1		13
+#define T2		14
+#define T3		15
+#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 || _MIPS_SIM == _MIPS_SIM_NABI32 */
+
+#define S0		16
+#define S1		17
+#define T9		25
+#define K0		26
+#define K1		27
+#define GP		28
+#define SP		29
+#define RA		31
+
+/* Some CP0 registers */
+#define C0_HWRENA	7, 0
+#define C0_BADVADDR	8, 0
+#define C0_ENTRYHI	10, 0
+#define C0_STATUS	12, 0
+#define C0_CAUSE	13, 0
+#define C0_EPC		14, 0
+#define C0_EBASE	15, 1
+#define C0_CONFIG5	16, 5
+#define C0_DDATA_LO	28, 3
+#define C0_ERROREPC	30, 0
+
+#define CALLFRAME_SIZ   32
+
+#ifdef CONFIG_64BIT
+#define ST0_KX_IF_64	ST0_KX
+#else
+#define ST0_KX_IF_64	0
+#endif
+
+static unsigned int scratch_vcpu[2] = { C0_DDATA_LO };
+static unsigned int scratch_tmp[2] = { C0_ERROREPC };
+
+enum label_id {
+	label_fpu_1 = 1,
+	label_msa_1,
+	label_return_to_host,
+	label_kernel_asid,
+	label_exit_common,
+};
+
+UASM_L_LA(_fpu_1)
+UASM_L_LA(_msa_1)
+UASM_L_LA(_return_to_host)
+UASM_L_LA(_kernel_asid)
+UASM_L_LA(_exit_common)
+
+static void *kvm_mips_build_enter_guest(void *addr);
+static void *kvm_mips_build_ret_from_exit(void *addr);
+static void *kvm_mips_build_ret_to_guest(void *addr);
+static void *kvm_mips_build_ret_to_host(void *addr);
+
+/**
+ * kvm_mips_entry_setup() - Perform global setup for entry code.
+ *
+ * Perform global setup for entry code, such as choosing a scratch register.
+ *
+ * Returns:	0 on success.
+ *		-errno on failure.
+ */
+int kvm_mips_entry_setup(void)
+{
+	/*
+	 * We prefer to use KScratchN registers if they are available over the
+	 * defaults above, which may not work on all cores.
+	 */
+	unsigned int kscratch_mask = cpu_data[0].kscratch_mask & 0xfc;
+
+	/* Pick a scratch register for storing VCPU */
+	if (kscratch_mask) {
+		scratch_vcpu[0] = 31;
+		scratch_vcpu[1] = ffs(kscratch_mask) - 1;
+		kscratch_mask &= ~BIT(scratch_vcpu[1]);
+	}
+
+	/* Pick a scratch register to use as a temp for saving state */
+	if (kscratch_mask) {
+		scratch_tmp[0] = 31;
+		scratch_tmp[1] = ffs(kscratch_mask) - 1;
+		kscratch_mask &= ~BIT(scratch_tmp[1]);
+	}
+
+	return 0;
+}
+
+static void kvm_mips_build_save_scratch(u32 **p, unsigned int tmp,
+					unsigned int frame)
+{
+	/* Save the VCPU scratch register value in cp0_epc of the stack frame */
+	UASM_i_MFC0(p, tmp, scratch_vcpu[0], scratch_vcpu[1]);
+	UASM_i_SW(p, tmp, offsetof(struct pt_regs, cp0_epc), frame);
+
+	/* Save the temp scratch register value in cp0_cause of stack frame */
+	if (scratch_tmp[0] == 31) {
+		UASM_i_MFC0(p, tmp, scratch_tmp[0], scratch_tmp[1]);
+		UASM_i_SW(p, tmp, offsetof(struct pt_regs, cp0_cause), frame);
+	}
+}
+
+static void kvm_mips_build_restore_scratch(u32 **p, unsigned int tmp,
+					   unsigned int frame)
+{
+	/*
+	 * Restore host scratch register values saved by
+	 * kvm_mips_build_save_scratch().
+	 */
+	UASM_i_LW(p, tmp, offsetof(struct pt_regs, cp0_epc), frame);
+	UASM_i_MTC0(p, tmp, scratch_vcpu[0], scratch_vcpu[1]);
+
+	if (scratch_tmp[0] == 31) {
+		UASM_i_LW(p, tmp, offsetof(struct pt_regs, cp0_cause), frame);
+		UASM_i_MTC0(p, tmp, scratch_tmp[0], scratch_tmp[1]);
+	}
+}
+
+/**
+ * build_set_exc_base() - Assemble code to write exception base address.
+ * @p:		Code buffer pointer.
+ * @reg:	Source register (generated code may set WG bit in @reg).
+ *
+ * Assemble code to modify the exception base address in the EBase register,
+ * using the appropriately sized access and setting the WG bit if necessary.
+ */
+static inline void build_set_exc_base(u32 **p, unsigned int reg)
+{
+	if (cpu_has_ebase_wg) {
+		/* Set WG so that all the bits get written */
+		uasm_i_ori(p, reg, reg, MIPS_EBASE_WG);
+		UASM_i_MTC0(p, reg, C0_EBASE);
+	} else {
+		uasm_i_mtc0(p, reg, C0_EBASE);
+	}
+}
+
+/**
+ * kvm_mips_build_vcpu_run() - Assemble function to start running a guest VCPU.
+ * @addr:	Address to start writing code.
+ *
+ * Assemble the start of the vcpu_run function to run a guest VCPU. The function
+ * conforms to the following prototype:
+ *
+ * int vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu);
+ *
+ * The exit from the guest and return to the caller is handled by the code
+ * generated by kvm_mips_build_ret_to_host().
+ *
+ * Returns:	Next address after end of written function.
+ */
+void *kvm_mips_build_vcpu_run(void *addr)
+{
+	u32 *p = addr;
+	unsigned int i;
+
+	/*
+	 * A0: run
+	 * A1: vcpu
+	 */
+
+	/* k0/k1 not being used in host kernel context */
+	UASM_i_ADDIU(&p, K1, SP, -(int)sizeof(struct pt_regs));
+	for (i = 16; i < 32; ++i) {
+		if (i == 24)
+			i = 28;
+		UASM_i_SW(&p, i, offsetof(struct pt_regs, regs[i]), K1);
+	}
+
+	/* Save host status */
+	uasm_i_mfc0(&p, V0, C0_STATUS);
+	UASM_i_SW(&p, V0, offsetof(struct pt_regs, cp0_status), K1);
+
+	/* Save scratch registers, will be used to store pointer to vcpu etc */
+	kvm_mips_build_save_scratch(&p, V1, K1);
+
+	/* VCPU scratch register has pointer to vcpu */
+	UASM_i_MTC0(&p, A1, scratch_vcpu[0], scratch_vcpu[1]);
+
+	/* Offset into vcpu->arch */
+	UASM_i_ADDIU(&p, K1, A1, offsetof(struct kvm_vcpu, arch));
+
+	/*
+	 * Save the host stack to VCPU, used for exception processing
+	 * when we exit from the Guest
+	 */
+	UASM_i_SW(&p, SP, offsetof(struct kvm_vcpu_arch, host_stack), K1);
+
+	/* Save the kernel gp as well */
+	UASM_i_SW(&p, GP, offsetof(struct kvm_vcpu_arch, host_gp), K1);
+
+	/*
+	 * Setup status register for running the guest in UM, interrupts
+	 * are disabled
+	 */
+	UASM_i_LA(&p, K0, ST0_EXL | KSU_USER | ST0_BEV | ST0_KX_IF_64);
+	uasm_i_mtc0(&p, K0, C0_STATUS);
+	uasm_i_ehb(&p);
+
+	/* load up the new EBASE */
+	UASM_i_LW(&p, K0, offsetof(struct kvm_vcpu_arch, guest_ebase), K1);
+	build_set_exc_base(&p, K0);
+
+	/*
+	 * Now that the new EBASE has been loaded, unset BEV, set
+	 * interrupt mask as it was but make sure that timer interrupts
+	 * are enabled
+	 */
+	uasm_i_addiu(&p, K0, ZERO, ST0_EXL | KSU_USER | ST0_IE | ST0_KX_IF_64);
+	uasm_i_andi(&p, V0, V0, ST0_IM);
+	uasm_i_or(&p, K0, K0, V0);
+	uasm_i_mtc0(&p, K0, C0_STATUS);
+	uasm_i_ehb(&p);
+
+	p = kvm_mips_build_enter_guest(p);
+
+	return p;
+}
+
+/**
+ * kvm_mips_build_enter_guest() - Assemble code to resume guest execution.
+ * @addr:	Address to start writing code.
+ *
+ * Assemble the code to resume guest execution. This code is common between the
+ * initial entry into the guest from the host, and returning from the exit
+ * handler back to the guest.
+ *
+ * Returns:	Next address after end of written function.
+ */
+static void *kvm_mips_build_enter_guest(void *addr)
+{
+	u32 *p = addr;
+	unsigned int i;
+	struct uasm_label labels[2];
+	struct uasm_reloc relocs[2];
+	struct uasm_label *l = labels;
+	struct uasm_reloc *r = relocs;
+
+	memset(labels, 0, sizeof(labels));
+	memset(relocs, 0, sizeof(relocs));
+
+	/* Set Guest EPC */
+	UASM_i_LW(&p, T0, offsetof(struct kvm_vcpu_arch, pc), K1);
+	UASM_i_MTC0(&p, T0, C0_EPC);
+
+	/* Set the ASID for the Guest Kernel */
+	UASM_i_LW(&p, T0, offsetof(struct kvm_vcpu_arch, cop0), K1);
+	UASM_i_LW(&p, T0, offsetof(struct mips_coproc, reg[MIPS_CP0_STATUS][0]),
+		  T0);
+	uasm_i_andi(&p, T0, T0, KSU_USER | ST0_ERL | ST0_EXL);
+	uasm_i_xori(&p, T0, T0, KSU_USER);
+	uasm_il_bnez(&p, &r, T0, label_kernel_asid);
+	 UASM_i_ADDIU(&p, T1, K1,
+		      offsetof(struct kvm_vcpu_arch, guest_kernel_asid));
+	/* else user */
+	UASM_i_ADDIU(&p, T1, K1,
+		     offsetof(struct kvm_vcpu_arch, guest_user_asid));
+	uasm_l_kernel_asid(&l, p);
+
+	/* t1: contains the base of the ASID array, need to get the cpu id  */
+	/* smp_processor_id */
+	uasm_i_lw(&p, T2, offsetof(struct thread_info, cpu), GP);
+	/* x4 */
+	uasm_i_sll(&p, T2, T2, 2);
+	UASM_i_ADDU(&p, T3, T1, T2);
+	uasm_i_lw(&p, K0, 0, T3);
+#ifdef CONFIG_MIPS_ASID_BITS_VARIABLE
+	/* x sizeof(struct cpuinfo_mips)/4 */
+	uasm_i_addiu(&p, T3, ZERO, sizeof(struct cpuinfo_mips)/4);
+	uasm_i_mul(&p, T2, T2, T3);
+
+	UASM_i_LA_mostly(&p, AT, (long)&cpu_data[0].asid_mask);
+	UASM_i_ADDU(&p, AT, AT, T2);
+	UASM_i_LW(&p, T2, uasm_rel_lo((long)&cpu_data[0].asid_mask), AT);
+	uasm_i_and(&p, K0, K0, T2);
+#else
+	uasm_i_andi(&p, K0, K0, MIPS_ENTRYHI_ASID);
+#endif
+	uasm_i_mtc0(&p, K0, C0_ENTRYHI);
+	uasm_i_ehb(&p);
+
+	/* Disable RDHWR access */
+	uasm_i_mtc0(&p, ZERO, C0_HWRENA);
+
+	/* load the guest context from VCPU and return */
+	for (i = 1; i < 32; ++i) {
+		/* Guest k0/k1 loaded later */
+		if (i == K0 || i == K1)
+			continue;
+		UASM_i_LW(&p, i, offsetof(struct kvm_vcpu_arch, gprs[i]), K1);
+	}
+
+#ifndef CONFIG_CPU_MIPSR6
+	/* Restore hi/lo */
+	UASM_i_LW(&p, K0, offsetof(struct kvm_vcpu_arch, hi), K1);
+	uasm_i_mthi(&p, K0);
+
+	UASM_i_LW(&p, K0, offsetof(struct kvm_vcpu_arch, lo), K1);
+	uasm_i_mtlo(&p, K0);
+#endif
+
+	/* Restore the guest's k0/k1 registers */
+	UASM_i_LW(&p, K0, offsetof(struct kvm_vcpu_arch, gprs[K0]), K1);
+	UASM_i_LW(&p, K1, offsetof(struct kvm_vcpu_arch, gprs[K1]), K1);
+
+	/* Jump to guest */
+	uasm_i_eret(&p);
+
+	uasm_resolve_relocs(relocs, labels);
+
+	return p;
+}
+
+/**
+ * kvm_mips_build_exception() - Assemble first level guest exception handler.
+ * @addr:	Address to start writing code.
+ * @handler:	Address of common handler (within range of @addr).
+ *
+ * Assemble exception vector code for guest execution. The generated vector will
+ * branch to the common exception handler generated by kvm_mips_build_exit().
+ *
+ * Returns:	Next address after end of written function.
+ */
+void *kvm_mips_build_exception(void *addr, void *handler)
+{
+	u32 *p = addr;
+	struct uasm_label labels[2];
+	struct uasm_reloc relocs[2];
+	struct uasm_label *l = labels;
+	struct uasm_reloc *r = relocs;
+
+	memset(labels, 0, sizeof(labels));
+	memset(relocs, 0, sizeof(relocs));
+
+	/* Save guest k1 into scratch register */
+	UASM_i_MTC0(&p, K1, scratch_tmp[0], scratch_tmp[1]);
+
+	/* Get the VCPU pointer from the VCPU scratch register */
+	UASM_i_MFC0(&p, K1, scratch_vcpu[0], scratch_vcpu[1]);
+	UASM_i_ADDIU(&p, K1, K1, offsetof(struct kvm_vcpu, arch));
+
+	/* Save guest k0 into VCPU structure */
+	UASM_i_SW(&p, K0, offsetof(struct kvm_vcpu_arch, gprs[K0]), K1);
+
+	/* Branch to the common handler */
+	uasm_il_b(&p, &r, label_exit_common);
+	 uasm_i_nop(&p);
+
+	uasm_l_exit_common(&l, handler);
+	uasm_resolve_relocs(relocs, labels);
+
+	return p;
+}
+
+/**
+ * kvm_mips_build_exit() - Assemble common guest exit handler.
+ * @addr:	Address to start writing code.
+ *
+ * Assemble the generic guest exit handling code. This is called by the
+ * exception vectors (generated by kvm_mips_build_exception()), and calls
+ * kvm_mips_handle_exit(), then either resumes the guest or returns to the host
+ * depending on the return value.
+ *
+ * Returns:	Next address after end of written function.
+ */
+void *kvm_mips_build_exit(void *addr)
+{
+	u32 *p = addr;
+	unsigned int i;
+	struct uasm_label labels[3];
+	struct uasm_reloc relocs[3];
+	struct uasm_label *l = labels;
+	struct uasm_reloc *r = relocs;
+
+	memset(labels, 0, sizeof(labels));
+	memset(relocs, 0, sizeof(relocs));
+
+	/*
+	 * Generic Guest exception handler. We end up here when the guest
+	 * does something that causes a trap to kernel mode.
+	 *
+	 * Both k0/k1 registers will have already been saved (k0 into the vcpu
+	 * structure, and k1 into the scratch_tmp register).
+	 *
+	 * The k1 register will already contain the kvm_vcpu_arch pointer.
+	 */
+
+	/* Start saving Guest context to VCPU */
+	for (i = 0; i < 32; ++i) {
+		/* Guest k0/k1 saved later */
+		if (i == K0 || i == K1)
+			continue;
+		UASM_i_SW(&p, i, offsetof(struct kvm_vcpu_arch, gprs[i]), K1);
+	}
+
+#ifndef CONFIG_CPU_MIPSR6
+	/* We need to save hi/lo and restore them on the way out */
+	uasm_i_mfhi(&p, T0);
+	UASM_i_SW(&p, T0, offsetof(struct kvm_vcpu_arch, hi), K1);
+
+	uasm_i_mflo(&p, T0);
+	UASM_i_SW(&p, T0, offsetof(struct kvm_vcpu_arch, lo), K1);
+#endif
+
+	/* Finally save guest k1 to VCPU */
+	uasm_i_ehb(&p);
+	UASM_i_MFC0(&p, T0, scratch_tmp[0], scratch_tmp[1]);
+	UASM_i_SW(&p, T0, offsetof(struct kvm_vcpu_arch, gprs[K1]), K1);
+
+	/* Now that context has been saved, we can use other registers */
+
+	/* Restore vcpu */
+	UASM_i_MFC0(&p, A1, scratch_vcpu[0], scratch_vcpu[1]);
+	uasm_i_move(&p, S1, A1);
+
+	/* Restore run (vcpu->run) */
+	UASM_i_LW(&p, A0, offsetof(struct kvm_vcpu, run), A1);
+	/* Save pointer to run in s0, will be saved by the compiler */
+	uasm_i_move(&p, S0, A0);
+
+	/*
+	 * Save Host level EPC, BadVaddr and Cause to VCPU, useful to process
+	 * the exception
+	 */
+	UASM_i_MFC0(&p, K0, C0_EPC);
+	UASM_i_SW(&p, K0, offsetof(struct kvm_vcpu_arch, pc), K1);
+
+	UASM_i_MFC0(&p, K0, C0_BADVADDR);
+	UASM_i_SW(&p, K0, offsetof(struct kvm_vcpu_arch, host_cp0_badvaddr),
+		  K1);
+
+	uasm_i_mfc0(&p, K0, C0_CAUSE);
+	uasm_i_sw(&p, K0, offsetof(struct kvm_vcpu_arch, host_cp0_cause), K1);
+
+	/* Now restore the host state just enough to run the handlers */
+
+	/* Switch EBASE to the one used by Linux */
+	/* load up the host EBASE */
+	uasm_i_mfc0(&p, V0, C0_STATUS);
+
+	uasm_i_lui(&p, AT, ST0_BEV >> 16);
+	uasm_i_or(&p, K0, V0, AT);
+
+	uasm_i_mtc0(&p, K0, C0_STATUS);
+	uasm_i_ehb(&p);
+
+	UASM_i_LA_mostly(&p, K0, (long)&ebase);
+	UASM_i_LW(&p, K0, uasm_rel_lo((long)&ebase), K0);
+	build_set_exc_base(&p, K0);
+
+	if (raw_cpu_has_fpu) {
+		/*
+		 * If FPU is enabled, save FCR31 and clear it so that later
+		 * ctc1's don't trigger FPE for pending exceptions.
+		 */
+		uasm_i_lui(&p, AT, ST0_CU1 >> 16);
+		uasm_i_and(&p, V1, V0, AT);
+		uasm_il_beqz(&p, &r, V1, label_fpu_1);
+		 uasm_i_nop(&p);
+		uasm_i_cfc1(&p, T0, 31);
+		uasm_i_sw(&p, T0, offsetof(struct kvm_vcpu_arch, fpu.fcr31),
+			  K1);
+		uasm_i_ctc1(&p, ZERO, 31);
+		uasm_l_fpu_1(&l, p);
+	}
+
+	if (cpu_has_msa) {
+		/*
+		 * If MSA is enabled, save MSACSR and clear it so that later
+		 * instructions don't trigger MSAFPE for pending exceptions.
+		 */
+		uasm_i_mfc0(&p, T0, C0_CONFIG5);
+		uasm_i_ext(&p, T0, T0, 27, 1); /* MIPS_CONF5_MSAEN */
+		uasm_il_beqz(&p, &r, T0, label_msa_1);
+		 uasm_i_nop(&p);
+		uasm_i_cfcmsa(&p, T0, MSA_CSR);
+		uasm_i_sw(&p, T0, offsetof(struct kvm_vcpu_arch, fpu.msacsr),
+			  K1);
+		uasm_i_ctcmsa(&p, MSA_CSR, ZERO);
+		uasm_l_msa_1(&l, p);
+	}
+
+	/* Now that the new EBASE has been loaded, unset BEV and KSU_USER */
+	uasm_i_addiu(&p, AT, ZERO, ~(ST0_EXL | KSU_USER | ST0_IE));
+	uasm_i_and(&p, V0, V0, AT);
+	uasm_i_lui(&p, AT, ST0_CU0 >> 16);
+	uasm_i_or(&p, V0, V0, AT);
+	uasm_i_mtc0(&p, V0, C0_STATUS);
+	uasm_i_ehb(&p);
+
+	/* Load up host GP */
+	UASM_i_LW(&p, GP, offsetof(struct kvm_vcpu_arch, host_gp), K1);
+
+	/* Need a stack before we can jump to "C" */
+	UASM_i_LW(&p, SP, offsetof(struct kvm_vcpu_arch, host_stack), K1);
+
+	/* Saved host state */
+	UASM_i_ADDIU(&p, SP, SP, -(int)sizeof(struct pt_regs));
+
+	/*
+	 * XXXKYMA do we need to load the host ASID, maybe not because the
+	 * kernel entries are marked GLOBAL, need to verify
+	 */
+
+	/* Restore host scratch registers, as we'll have clobbered them */
+	kvm_mips_build_restore_scratch(&p, K0, SP);
+
+	/* Restore RDHWR access */
+	UASM_i_LA_mostly(&p, K0, (long)&hwrena);
+	uasm_i_lw(&p, K0, uasm_rel_lo((long)&hwrena), K0);
+	uasm_i_mtc0(&p, K0, C0_HWRENA);
+
+	/* Jump to handler */
+	/*
+	 * XXXKYMA: not sure if this is safe, how large is the stack??
+	 * Now jump to the kvm_mips_handle_exit() to see if we can deal
+	 * with this in the kernel
+	 */
+	UASM_i_LA(&p, T9, (unsigned long)kvm_mips_handle_exit);
+	uasm_i_jalr(&p, RA, T9);
+	 UASM_i_ADDIU(&p, SP, SP, -CALLFRAME_SIZ);
+
+	uasm_resolve_relocs(relocs, labels);
+
+	p = kvm_mips_build_ret_from_exit(p);
+
+	return p;
+}
+
+/**
+ * kvm_mips_build_ret_from_exit() - Assemble guest exit return handler.
+ * @addr:	Address to start writing code.
+ *
+ * Assemble the code to handle the return from kvm_mips_handle_exit(), either
+ * resuming the guest or returning to the host depending on the return value.
+ *
+ * Returns:	Next address after end of written function.
+ */
+static void *kvm_mips_build_ret_from_exit(void *addr)
+{
+	u32 *p = addr;
+	struct uasm_label labels[2];
+	struct uasm_reloc relocs[2];
+	struct uasm_label *l = labels;
+	struct uasm_reloc *r = relocs;
+
+	memset(labels, 0, sizeof(labels));
+	memset(relocs, 0, sizeof(relocs));
+
+	/* Return from handler Make sure interrupts are disabled */
+	uasm_i_di(&p, ZERO);
+	uasm_i_ehb(&p);
+
+	/*
+	 * XXXKYMA: k0/k1 could have been blown away if we processed
+	 * an exception while we were handling the exception from the
+	 * guest, reload k1
+	 */
+
+	uasm_i_move(&p, K1, S1);
+	UASM_i_ADDIU(&p, K1, K1, offsetof(struct kvm_vcpu, arch));
+
+	/*
+	 * Check return value, should tell us if we are returning to the
+	 * host (handle I/O etc)or resuming the guest
+	 */
+	uasm_i_andi(&p, T0, V0, RESUME_HOST);
+	uasm_il_bnez(&p, &r, T0, label_return_to_host);
+	 uasm_i_nop(&p);
+
+	p = kvm_mips_build_ret_to_guest(p);
+
+	uasm_l_return_to_host(&l, p);
+	p = kvm_mips_build_ret_to_host(p);
+
+	uasm_resolve_relocs(relocs, labels);
+
+	return p;
+}
+
+/**
+ * kvm_mips_build_ret_to_guest() - Assemble code to return to the guest.
+ * @addr:	Address to start writing code.
+ *
+ * Assemble the code to handle return from the guest exit handler
+ * (kvm_mips_handle_exit()) back to the guest.
+ *
+ * Returns:	Next address after end of written function.
+ */
+static void *kvm_mips_build_ret_to_guest(void *addr)
+{
+	u32 *p = addr;
+
+	/* Put the saved pointer to vcpu (s1) back into the scratch register */
+	UASM_i_MTC0(&p, S1, scratch_vcpu[0], scratch_vcpu[1]);
+
+	/* Load up the Guest EBASE to minimize the window where BEV is set */
+	UASM_i_LW(&p, T0, offsetof(struct kvm_vcpu_arch, guest_ebase), K1);
+
+	/* Switch EBASE back to the one used by KVM */
+	uasm_i_mfc0(&p, V1, C0_STATUS);
+	uasm_i_lui(&p, AT, ST0_BEV >> 16);
+	uasm_i_or(&p, K0, V1, AT);
+	uasm_i_mtc0(&p, K0, C0_STATUS);
+	uasm_i_ehb(&p);
+	build_set_exc_base(&p, T0);
+
+	/* Setup status register for running guest in UM */
+	uasm_i_ori(&p, V1, V1, ST0_EXL | KSU_USER | ST0_IE);
+	UASM_i_LA(&p, AT, ~(ST0_CU0 | ST0_MX));
+	uasm_i_and(&p, V1, V1, AT);
+	uasm_i_mtc0(&p, V1, C0_STATUS);
+	uasm_i_ehb(&p);
+
+	p = kvm_mips_build_enter_guest(p);
+
+	return p;
+}
+
+/**
+ * kvm_mips_build_ret_to_host() - Assemble code to return to the host.
+ * @addr:	Address to start writing code.
+ *
+ * Assemble the code to handle return from the guest exit handler
+ * (kvm_mips_handle_exit()) back to the host, i.e. to the caller of the vcpu_run
+ * function generated by kvm_mips_build_vcpu_run().
+ *
+ * Returns:	Next address after end of written function.
+ */
+static void *kvm_mips_build_ret_to_host(void *addr)
+{
+	u32 *p = addr;
+	unsigned int i;
+
+	/* EBASE is already pointing to Linux */
+	UASM_i_LW(&p, K1, offsetof(struct kvm_vcpu_arch, host_stack), K1);
+	UASM_i_ADDIU(&p, K1, K1, -(int)sizeof(struct pt_regs));
+
+	/*
+	 * r2/v0 is the return code, shift it down by 2 (arithmetic)
+	 * to recover the err code
+	 */
+	uasm_i_sra(&p, K0, V0, 2);
+	uasm_i_move(&p, V0, K0);
+
+	/* Load context saved on the host stack */
+	for (i = 16; i < 31; ++i) {
+		if (i == 24)
+			i = 28;
+		UASM_i_LW(&p, i, offsetof(struct pt_regs, regs[i]), K1);
+	}
+
+	/* Restore RDHWR access */
+	UASM_i_LA_mostly(&p, K0, (long)&hwrena);
+	uasm_i_lw(&p, K0, uasm_rel_lo((long)&hwrena), K0);
+	uasm_i_mtc0(&p, K0, C0_HWRENA);
+
+	/* Restore RA, which is the address we will return to */
+	UASM_i_LW(&p, RA, offsetof(struct pt_regs, regs[RA]), K1);
+	uasm_i_jr(&p, RA);
+	 uasm_i_nop(&p);
+
+	return p;
+}
+
diff --git a/arch/mips/kvm/fpu.S b/arch/mips/kvm/fpu.S
index 531fbf5131c0..16f17c6390dd 100644
--- a/arch/mips/kvm/fpu.S
+++ b/arch/mips/kvm/fpu.S
@@ -14,13 +14,16 @@
 #include <asm/mipsregs.h>
 #include <asm/regdef.h>
 
+/* preprocessor replaces the fp in ".set fp=64" with $30 otherwise */
+#undef fp
+
 	.set	noreorder
 	.set	noat
 
 LEAF(__kvm_save_fpu)
 	.set	push
-	.set	mips64r2
 	SET_HARDFLOAT
+	.set	fp=64
 	mfc0	t0, CP0_STATUS
 	sll     t0, t0, 5			# is Status.FR set?
 	bgez    t0, 1f				# no: skip odd doubles
@@ -63,8 +66,8 @@ LEAF(__kvm_save_fpu)
 
 LEAF(__kvm_restore_fpu)
 	.set	push
-	.set	mips64r2
 	SET_HARDFLOAT
+	.set	fp=64
 	mfc0	t0, CP0_STATUS
 	sll     t0, t0, 5			# is Status.FR set?
 	bgez    t0, 1f				# no: skip odd doubles
diff --git a/arch/mips/kvm/interrupt.c b/arch/mips/kvm/interrupt.c
index 95f790663b0c..ad28dac6b7e9 100644
--- a/arch/mips/kvm/interrupt.c
+++ b/arch/mips/kvm/interrupt.c
@@ -22,12 +22,12 @@
 
 #include "interrupt.h"
 
-void kvm_mips_queue_irq(struct kvm_vcpu *vcpu, uint32_t priority)
+void kvm_mips_queue_irq(struct kvm_vcpu *vcpu, unsigned int priority)
 {
 	set_bit(priority, &vcpu->arch.pending_exceptions);
 }
 
-void kvm_mips_dequeue_irq(struct kvm_vcpu *vcpu, uint32_t priority)
+void kvm_mips_dequeue_irq(struct kvm_vcpu *vcpu, unsigned int priority)
 {
 	clear_bit(priority, &vcpu->arch.pending_exceptions);
 }
@@ -114,10 +114,10 @@ void kvm_mips_dequeue_io_int_cb(struct kvm_vcpu *vcpu,
 
 /* Deliver the interrupt of the corresponding priority, if possible. */
 int kvm_mips_irq_deliver_cb(struct kvm_vcpu *vcpu, unsigned int priority,
-			    uint32_t cause)
+			    u32 cause)
 {
 	int allowed = 0;
-	uint32_t exccode;
+	u32 exccode;
 
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
@@ -196,12 +196,12 @@ int kvm_mips_irq_deliver_cb(struct kvm_vcpu *vcpu, unsigned int priority,
 }
 
 int kvm_mips_irq_clear_cb(struct kvm_vcpu *vcpu, unsigned int priority,
-			  uint32_t cause)
+			  u32 cause)
 {
 	return 1;
 }
 
-void kvm_mips_deliver_interrupts(struct kvm_vcpu *vcpu, uint32_t cause)
+void kvm_mips_deliver_interrupts(struct kvm_vcpu *vcpu, u32 cause)
 {
 	unsigned long *pending = &vcpu->arch.pending_exceptions;
 	unsigned long *pending_clr = &vcpu->arch.pending_exceptions_clr;
diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h
index 2143884709e4..fb118a2c8379 100644
--- a/arch/mips/kvm/interrupt.h
+++ b/arch/mips/kvm/interrupt.h
@@ -28,17 +28,13 @@
 #define MIPS_EXC_MAX                12
 /* XXXSL More to follow */
 
-extern char __kvm_mips_vcpu_run_end[];
-extern char mips32_exception[], mips32_exceptionEnd[];
-extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
-
 #define C_TI        (_ULCAST_(1) << 30)
 
 #define KVM_MIPS_IRQ_DELIVER_ALL_AT_ONCE (0)
 #define KVM_MIPS_IRQ_CLEAR_ALL_AT_ONCE   (0)
 
-void kvm_mips_queue_irq(struct kvm_vcpu *vcpu, uint32_t priority);
-void kvm_mips_dequeue_irq(struct kvm_vcpu *vcpu, uint32_t priority);
+void kvm_mips_queue_irq(struct kvm_vcpu *vcpu, unsigned int priority);
+void kvm_mips_dequeue_irq(struct kvm_vcpu *vcpu, unsigned int priority);
 int kvm_mips_pending_timer(struct kvm_vcpu *vcpu);
 
 void kvm_mips_queue_timer_int_cb(struct kvm_vcpu *vcpu);
@@ -48,7 +44,7 @@ void kvm_mips_queue_io_int_cb(struct kvm_vcpu *vcpu,
 void kvm_mips_dequeue_io_int_cb(struct kvm_vcpu *vcpu,
 				struct kvm_mips_interrupt *irq);
 int kvm_mips_irq_deliver_cb(struct kvm_vcpu *vcpu, unsigned int priority,
-			    uint32_t cause);
+			    u32 cause);
 int kvm_mips_irq_clear_cb(struct kvm_vcpu *vcpu, unsigned int priority,
-			  uint32_t cause);
-void kvm_mips_deliver_interrupts(struct kvm_vcpu *vcpu, uint32_t cause);
+			  u32 cause);
+void kvm_mips_deliver_interrupts(struct kvm_vcpu *vcpu, u32 cause);
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
deleted file mode 100644
index 828fcfc1cd7f..000000000000
--- a/arch/mips/kvm/locore.S
+++ /dev/null
@@ -1,605 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Main entry point for the guest, exception handling.
- *
- * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
- * Authors: Sanjay Lal <sanjayl@kymasys.com>
- */
-
-#include <asm/asm.h>
-#include <asm/asmmacro.h>
-#include <asm/regdef.h>
-#include <asm/mipsregs.h>
-#include <asm/stackframe.h>
-#include <asm/asm-offsets.h>
-
-#define _C_LABEL(x)     x
-#define MIPSX(name)     mips32_ ## name
-#define CALLFRAME_SIZ   32
-
-/*
- * VECTOR
- *  exception vector entrypoint
- */
-#define VECTOR(x, regmask)      \
-    .ent    _C_LABEL(x),0;      \
-    EXPORT(x);
-
-#define VECTOR_END(x)      \
-    EXPORT(x);
-
-/* Overload, Danger Will Robinson!! */
-#define PT_HOST_USERLOCAL   PT_EPC
-
-#define CP0_DDATA_LO        $28,3
-
-/* Resume Flags */
-#define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
-
-#define RESUME_GUEST            0
-#define RESUME_HOST             RESUME_FLAG_HOST
-
-/*
- * __kvm_mips_vcpu_run: entry point to the guest
- * a0: run
- * a1: vcpu
- */
-	.set	noreorder
-
-FEXPORT(__kvm_mips_vcpu_run)
-	/* k0/k1 not being used in host kernel context */
-	INT_ADDIU k1, sp, -PT_SIZE
-	LONG_S	$16, PT_R16(k1)
-	LONG_S	$17, PT_R17(k1)
-	LONG_S	$18, PT_R18(k1)
-	LONG_S	$19, PT_R19(k1)
-	LONG_S	$20, PT_R20(k1)
-	LONG_S	$21, PT_R21(k1)
-	LONG_S	$22, PT_R22(k1)
-	LONG_S	$23, PT_R23(k1)
-
-	LONG_S	$28, PT_R28(k1)
-	LONG_S	$29, PT_R29(k1)
-	LONG_S	$30, PT_R30(k1)
-	LONG_S	$31, PT_R31(k1)
-
-	/* Save hi/lo */
-	mflo	v0
-	LONG_S	v0, PT_LO(k1)
-	mfhi	v1
-	LONG_S	v1, PT_HI(k1)
-
-	/* Save host status */
-	mfc0	v0, CP0_STATUS
-	LONG_S	v0, PT_STATUS(k1)
-
-	/* Save DDATA_LO, will be used to store pointer to vcpu */
-	mfc0	v1, CP0_DDATA_LO
-	LONG_S	v1, PT_HOST_USERLOCAL(k1)
-
-	/* DDATA_LO has pointer to vcpu */
-	mtc0	a1, CP0_DDATA_LO
-
-	/* Offset into vcpu->arch */
-	INT_ADDIU k1, a1, VCPU_HOST_ARCH
-
-	/*
-	 * Save the host stack to VCPU, used for exception processing
-	 * when we exit from the Guest
-	 */
-	LONG_S	sp, VCPU_HOST_STACK(k1)
-
-	/* Save the kernel gp as well */
-	LONG_S	gp, VCPU_HOST_GP(k1)
-
-	/*
-	 * Setup status register for running the guest in UM, interrupts
-	 * are disabled
-	 */
-	li	k0, (ST0_EXL | KSU_USER | ST0_BEV)
-	mtc0	k0, CP0_STATUS
-	ehb
-
-	/* load up the new EBASE */
-	LONG_L	k0, VCPU_GUEST_EBASE(k1)
-	mtc0	k0, CP0_EBASE
-
-	/*
-	 * Now that the new EBASE has been loaded, unset BEV, set
-	 * interrupt mask as it was but make sure that timer interrupts
-	 * are enabled
-	 */
-	li	k0, (ST0_EXL | KSU_USER | ST0_IE)
-	andi	v0, v0, ST0_IM
-	or	k0, k0, v0
-	mtc0	k0, CP0_STATUS
-	ehb
-
-	/* Set Guest EPC */
-	LONG_L	t0, VCPU_PC(k1)
-	mtc0	t0, CP0_EPC
-
-FEXPORT(__kvm_mips_load_asid)
-	/* Set the ASID for the Guest Kernel */
-	PTR_L	t0, VCPU_COP0(k1)
-	LONG_L	t0, COP0_STATUS(t0)
-	andi	t0, KSU_USER | ST0_ERL | ST0_EXL
-	xori	t0, KSU_USER
-	bnez	t0, 1f		/* If kernel */
-	 INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
-	INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
-1:
-	/* t1: contains the base of the ASID array, need to get the cpu id */
-	LONG_L	t2, TI_CPU($28)             /* smp_processor_id */
-	INT_SLL	t2, t2, 2                   /* x4 */
-	REG_ADDU t3, t1, t2
-	LONG_L	k0, (t3)
-#ifdef CONFIG_MIPS_ASID_BITS_VARIABLE
-	li	t3, CPUINFO_SIZE/4
-	mul	t2, t2, t3		/* x sizeof(struct cpuinfo_mips)/4 */
-	LONG_L	t2, (cpu_data + CPUINFO_ASID_MASK)(t2)
-	and	k0, k0, t2
-#else
-	andi	k0, k0, MIPS_ENTRYHI_ASID
-#endif
-	mtc0	k0, CP0_ENTRYHI
-	ehb
-
-	/* Disable RDHWR access */
-	mtc0	zero, CP0_HWRENA
-
-	.set	noat
-	/* Now load up the Guest Context from VCPU */
-	LONG_L	$1, VCPU_R1(k1)
-	LONG_L	$2, VCPU_R2(k1)
-	LONG_L	$3, VCPU_R3(k1)
-
-	LONG_L	$4, VCPU_R4(k1)
-	LONG_L	$5, VCPU_R5(k1)
-	LONG_L	$6, VCPU_R6(k1)
-	LONG_L	$7, VCPU_R7(k1)
-
-	LONG_L	$8, VCPU_R8(k1)
-	LONG_L	$9, VCPU_R9(k1)
-	LONG_L	$10, VCPU_R10(k1)
-	LONG_L	$11, VCPU_R11(k1)
-	LONG_L	$12, VCPU_R12(k1)
-	LONG_L	$13, VCPU_R13(k1)
-	LONG_L	$14, VCPU_R14(k1)
-	LONG_L	$15, VCPU_R15(k1)
-	LONG_L	$16, VCPU_R16(k1)
-	LONG_L	$17, VCPU_R17(k1)
-	LONG_L	$18, VCPU_R18(k1)
-	LONG_L	$19, VCPU_R19(k1)
-	LONG_L	$20, VCPU_R20(k1)
-	LONG_L	$21, VCPU_R21(k1)
-	LONG_L	$22, VCPU_R22(k1)
-	LONG_L	$23, VCPU_R23(k1)
-	LONG_L	$24, VCPU_R24(k1)
-	LONG_L	$25, VCPU_R25(k1)
-
-	/* k0/k1 loaded up later */
-
-	LONG_L	$28, VCPU_R28(k1)
-	LONG_L	$29, VCPU_R29(k1)
-	LONG_L	$30, VCPU_R30(k1)
-	LONG_L	$31, VCPU_R31(k1)
-
-	/* Restore hi/lo */
-	LONG_L	k0, VCPU_LO(k1)
-	mtlo	k0
-
-	LONG_L	k0, VCPU_HI(k1)
-	mthi	k0
-
-FEXPORT(__kvm_mips_load_k0k1)
-	/* Restore the guest's k0/k1 registers */
-	LONG_L	k0, VCPU_R26(k1)
-	LONG_L	k1, VCPU_R27(k1)
-
-	/* Jump to guest */
-	eret
-EXPORT(__kvm_mips_vcpu_run_end)
-
-VECTOR(MIPSX(exception), unknown)
-/* Find out what mode we came from and jump to the proper handler. */
-	mtc0	k0, CP0_ERROREPC	#01: Save guest k0
-	ehb				#02:
-
-	mfc0	k0, CP0_EBASE		#02: Get EBASE
-	INT_SRL	k0, k0, 10		#03: Get rid of CPUNum
-	INT_SLL	k0, k0, 10		#04
-	LONG_S	k1, 0x3000(k0)		#05: Save k1 @ offset 0x3000
-	INT_ADDIU k0, k0, 0x2000	#06: Exception handler is
-					#    installed @ offset 0x2000
-	j	k0			#07: jump to the function
-	 nop				#08: branch delay slot
-VECTOR_END(MIPSX(exceptionEnd))
-.end MIPSX(exception)
-
-/*
- * Generic Guest exception handler. We end up here when the guest
- * does something that causes a trap to kernel mode.
- */
-NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra)
-	/* Get the VCPU pointer from DDTATA_LO */
-	mfc0	k1, CP0_DDATA_LO
-	INT_ADDIU k1, k1, VCPU_HOST_ARCH
-
-	/* Start saving Guest context to VCPU */
-	LONG_S	$0, VCPU_R0(k1)
-	LONG_S	$1, VCPU_R1(k1)
-	LONG_S	$2, VCPU_R2(k1)
-	LONG_S	$3, VCPU_R3(k1)
-	LONG_S	$4, VCPU_R4(k1)
-	LONG_S	$5, VCPU_R5(k1)
-	LONG_S	$6, VCPU_R6(k1)
-	LONG_S	$7, VCPU_R7(k1)
-	LONG_S	$8, VCPU_R8(k1)
-	LONG_S	$9, VCPU_R9(k1)
-	LONG_S	$10, VCPU_R10(k1)
-	LONG_S	$11, VCPU_R11(k1)
-	LONG_S	$12, VCPU_R12(k1)
-	LONG_S	$13, VCPU_R13(k1)
-	LONG_S	$14, VCPU_R14(k1)
-	LONG_S	$15, VCPU_R15(k1)
-	LONG_S	$16, VCPU_R16(k1)
-	LONG_S	$17, VCPU_R17(k1)
-	LONG_S	$18, VCPU_R18(k1)
-	LONG_S	$19, VCPU_R19(k1)
-	LONG_S	$20, VCPU_R20(k1)
-	LONG_S	$21, VCPU_R21(k1)
-	LONG_S	$22, VCPU_R22(k1)
-	LONG_S	$23, VCPU_R23(k1)
-	LONG_S	$24, VCPU_R24(k1)
-	LONG_S	$25, VCPU_R25(k1)
-
-	/* Guest k0/k1 saved later */
-
-	LONG_S	$28, VCPU_R28(k1)
-	LONG_S	$29, VCPU_R29(k1)
-	LONG_S	$30, VCPU_R30(k1)
-	LONG_S	$31, VCPU_R31(k1)
-
-	.set at
-
-	/* We need to save hi/lo and restore them on the way out */
-	mfhi	t0
-	LONG_S	t0, VCPU_HI(k1)
-
-	mflo	t0
-	LONG_S	t0, VCPU_LO(k1)
-
-	/* Finally save guest k0/k1 to VCPU */
-	mfc0	t0, CP0_ERROREPC
-	LONG_S	t0, VCPU_R26(k1)
-
-	/* Get GUEST k1 and save it in VCPU */
-	PTR_LI	t1, ~0x2ff
-	mfc0	t0, CP0_EBASE
-	and	t0, t0, t1
-	LONG_L	t0, 0x3000(t0)
-	LONG_S	t0, VCPU_R27(k1)
-
-	/* Now that context has been saved, we can use other registers */
-
-	/* Restore vcpu */
-	mfc0	a1, CP0_DDATA_LO
-	move	s1, a1
-
-	/* Restore run (vcpu->run) */
-	LONG_L	a0, VCPU_RUN(a1)
-	/* Save pointer to run in s0, will be saved by the compiler */
-	move	s0, a0
-
-	/*
-	 * Save Host level EPC, BadVaddr and Cause to VCPU, useful to
-	 * process the exception
-	 */
-	mfc0	k0,CP0_EPC
-	LONG_S	k0, VCPU_PC(k1)
-
-	mfc0	k0, CP0_BADVADDR
-	LONG_S	k0, VCPU_HOST_CP0_BADVADDR(k1)
-
-	mfc0	k0, CP0_CAUSE
-	LONG_S	k0, VCPU_HOST_CP0_CAUSE(k1)
-
-	mfc0	k0, CP0_ENTRYHI
-	LONG_S	k0, VCPU_HOST_ENTRYHI(k1)
-
-	/* Now restore the host state just enough to run the handlers */
-
-	/* Switch EBASE to the one used by Linux */
-	/* load up the host EBASE */
-	mfc0	v0, CP0_STATUS
-
-	or	k0, v0, ST0_BEV
-
-	mtc0	k0, CP0_STATUS
-	ehb
-
-	LONG_L	k0, VCPU_HOST_EBASE(k1)
-	mtc0	k0,CP0_EBASE
-
-	/*
-	 * If FPU is enabled, save FCR31 and clear it so that later ctc1's don't
-	 * trigger FPE for pending exceptions.
-	 */
-	and	v1, v0, ST0_CU1
-	beqz	v1, 1f
-	 nop
-	.set	push
-	SET_HARDFLOAT
-	cfc1	t0, fcr31
-	sw	t0, VCPU_FCR31(k1)
-	ctc1	zero,fcr31
-	.set	pop
-1:
-
-#ifdef CONFIG_CPU_HAS_MSA
-	/*
-	 * If MSA is enabled, save MSACSR and clear it so that later
-	 * instructions don't trigger MSAFPE for pending exceptions.
-	 */
-	mfc0	t0, CP0_CONFIG3
-	ext	t0, t0, 28, 1 /* MIPS_CONF3_MSAP */
-	beqz	t0, 1f
-	 nop
-	mfc0	t0, CP0_CONFIG5
-	ext	t0, t0, 27, 1 /* MIPS_CONF5_MSAEN */
-	beqz	t0, 1f
-	 nop
-	_cfcmsa	t0, MSA_CSR
-	sw	t0, VCPU_MSA_CSR(k1)
-	_ctcmsa	MSA_CSR, zero
-1:
-#endif
-
-	/* Now that the new EBASE has been loaded, unset BEV and KSU_USER */
-	and	v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE)
-	or	v0, v0, ST0_CU0
-	mtc0	v0, CP0_STATUS
-	ehb
-
-	/* Load up host GP */
-	LONG_L	gp, VCPU_HOST_GP(k1)
-
-	/* Need a stack before we can jump to "C" */
-	LONG_L	sp, VCPU_HOST_STACK(k1)
-
-	/* Saved host state */
-	INT_ADDIU sp, sp, -PT_SIZE
-
-	/*
-	 * XXXKYMA do we need to load the host ASID, maybe not because the
-	 * kernel entries are marked GLOBAL, need to verify
-	 */
-
-	/* Restore host DDATA_LO */
-	LONG_L	k0, PT_HOST_USERLOCAL(sp)
-	mtc0	k0, CP0_DDATA_LO
-
-	/* Restore RDHWR access */
-	PTR_LI	k0, 0x2000000F
-	mtc0	k0, CP0_HWRENA
-
-	/* Jump to handler */
-FEXPORT(__kvm_mips_jump_to_handler)
-	/*
-	 * XXXKYMA: not sure if this is safe, how large is the stack??
-	 * Now jump to the kvm_mips_handle_exit() to see if we can deal
-	 * with this in the kernel
-	 */
-	PTR_LA	t9, kvm_mips_handle_exit
-	jalr.hb	t9
-	 INT_ADDIU sp, sp, -CALLFRAME_SIZ           /* BD Slot */
-
-	/* Return from handler Make sure interrupts are disabled */
-	di
-	ehb
-
-	/*
-	 * XXXKYMA: k0/k1 could have been blown away if we processed
-	 * an exception while we were handling the exception from the
-	 * guest, reload k1
-	 */
-
-	move	k1, s1
-	INT_ADDIU k1, k1, VCPU_HOST_ARCH
-
-	/*
-	 * Check return value, should tell us if we are returning to the
-	 * host (handle I/O etc)or resuming the guest
-	 */
-	andi	t0, v0, RESUME_HOST
-	bnez	t0, __kvm_mips_return_to_host
-	 nop
-
-__kvm_mips_return_to_guest:
-	/* Put the saved pointer to vcpu (s1) back into the DDATA_LO Register */
-	mtc0	s1, CP0_DDATA_LO
-
-	/* Load up the Guest EBASE to minimize the window where BEV is set */
-	LONG_L	t0, VCPU_GUEST_EBASE(k1)
-
-	/* Switch EBASE back to the one used by KVM */
-	mfc0	v1, CP0_STATUS
-	or	k0, v1, ST0_BEV
-	mtc0	k0, CP0_STATUS
-	ehb
-	mtc0	t0, CP0_EBASE
-
-	/* Setup status register for running guest in UM */
-	or	v1, v1, (ST0_EXL | KSU_USER | ST0_IE)
-	and	v1, v1, ~(ST0_CU0 | ST0_MX)
-	mtc0	v1, CP0_STATUS
-	ehb
-
-	/* Set Guest EPC */
-	LONG_L	t0, VCPU_PC(k1)
-	mtc0	t0, CP0_EPC
-
-	/* Set the ASID for the Guest Kernel */
-	PTR_L	t0, VCPU_COP0(k1)
-	LONG_L	t0, COP0_STATUS(t0)
-	andi	t0, KSU_USER | ST0_ERL | ST0_EXL
-	xori	t0, KSU_USER
-	bnez	t0, 1f		/* If kernel */
-	 INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
-	INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
-1:
-	/* t1: contains the base of the ASID array, need to get the cpu id  */
-	LONG_L	t2, TI_CPU($28)		/* smp_processor_id */
-	INT_SLL	t2, t2, 2		/* x4 */
-	REG_ADDU t3, t1, t2
-	LONG_L	k0, (t3)
-#ifdef CONFIG_MIPS_ASID_BITS_VARIABLE
-	li	t3, CPUINFO_SIZE/4
-	mul	t2, t2, t3		/* x sizeof(struct cpuinfo_mips)/4 */
-	LONG_L	t2, (cpu_data + CPUINFO_ASID_MASK)(t2)
-	and	k0, k0, t2
-#else
-	andi	k0, k0, MIPS_ENTRYHI_ASID
-#endif
-	mtc0	k0, CP0_ENTRYHI
-	ehb
-
-	/* Disable RDHWR access */
-	mtc0	zero, CP0_HWRENA
-
-	.set	noat
-	/* load the guest context from VCPU and return */
-	LONG_L	$0, VCPU_R0(k1)
-	LONG_L	$1, VCPU_R1(k1)
-	LONG_L	$2, VCPU_R2(k1)
-	LONG_L	$3, VCPU_R3(k1)
-	LONG_L	$4, VCPU_R4(k1)
-	LONG_L	$5, VCPU_R5(k1)
-	LONG_L	$6, VCPU_R6(k1)
-	LONG_L	$7, VCPU_R7(k1)
-	LONG_L	$8, VCPU_R8(k1)
-	LONG_L	$9, VCPU_R9(k1)
-	LONG_L	$10, VCPU_R10(k1)
-	LONG_L	$11, VCPU_R11(k1)
-	LONG_L	$12, VCPU_R12(k1)
-	LONG_L	$13, VCPU_R13(k1)
-	LONG_L	$14, VCPU_R14(k1)
-	LONG_L	$15, VCPU_R15(k1)
-	LONG_L	$16, VCPU_R16(k1)
-	LONG_L	$17, VCPU_R17(k1)
-	LONG_L	$18, VCPU_R18(k1)
-	LONG_L	$19, VCPU_R19(k1)
-	LONG_L	$20, VCPU_R20(k1)
-	LONG_L	$21, VCPU_R21(k1)
-	LONG_L	$22, VCPU_R22(k1)
-	LONG_L	$23, VCPU_R23(k1)
-	LONG_L	$24, VCPU_R24(k1)
-	LONG_L	$25, VCPU_R25(k1)
-
-	/* $/k1 loaded later */
-	LONG_L	$28, VCPU_R28(k1)
-	LONG_L	$29, VCPU_R29(k1)
-	LONG_L	$30, VCPU_R30(k1)
-	LONG_L	$31, VCPU_R31(k1)
-
-FEXPORT(__kvm_mips_skip_guest_restore)
-	LONG_L	k0, VCPU_HI(k1)
-	mthi	k0
-
-	LONG_L	k0, VCPU_LO(k1)
-	mtlo	k0
-
-	LONG_L	k0, VCPU_R26(k1)
-	LONG_L	k1, VCPU_R27(k1)
-
-	eret
-	.set	at
-
-__kvm_mips_return_to_host:
-	/* EBASE is already pointing to Linux */
-	LONG_L	k1, VCPU_HOST_STACK(k1)
-	INT_ADDIU k1,k1, -PT_SIZE
-
-	/* Restore host DDATA_LO */
-	LONG_L	k0, PT_HOST_USERLOCAL(k1)
-	mtc0	k0, CP0_DDATA_LO
-
-	/*
-	 * r2/v0 is the return code, shift it down by 2 (arithmetic)
-	 * to recover the err code
-	 */
-	INT_SRA	k0, v0, 2
-	move	$2, k0
-
-	/* Load context saved on the host stack */
-	LONG_L	$16, PT_R16(k1)
-	LONG_L	$17, PT_R17(k1)
-	LONG_L	$18, PT_R18(k1)
-	LONG_L	$19, PT_R19(k1)
-	LONG_L	$20, PT_R20(k1)
-	LONG_L	$21, PT_R21(k1)
-	LONG_L	$22, PT_R22(k1)
-	LONG_L	$23, PT_R23(k1)
-
-	LONG_L	$28, PT_R28(k1)
-	LONG_L	$29, PT_R29(k1)
-	LONG_L	$30, PT_R30(k1)
-
-	LONG_L	k0, PT_HI(k1)
-	mthi	k0
-
-	LONG_L	k0, PT_LO(k1)
-	mtlo	k0
-
-	/* Restore RDHWR access */
-	PTR_LI	k0, 0x2000000F
-	mtc0	k0, CP0_HWRENA
-
-	/* Restore RA, which is the address we will return to */
-	LONG_L	ra, PT_R31(k1)
-	j	ra
-	 nop
-
-VECTOR_END(MIPSX(GuestExceptionEnd))
-.end MIPSX(GuestException)
-
-MIPSX(exceptions):
-	####
-	##### The exception handlers.
-	#####
-	.word _C_LABEL(MIPSX(GuestException))	#  0
-	.word _C_LABEL(MIPSX(GuestException))	#  1
-	.word _C_LABEL(MIPSX(GuestException))	#  2
-	.word _C_LABEL(MIPSX(GuestException))	#  3
-	.word _C_LABEL(MIPSX(GuestException))	#  4
-	.word _C_LABEL(MIPSX(GuestException))	#  5
-	.word _C_LABEL(MIPSX(GuestException))	#  6
-	.word _C_LABEL(MIPSX(GuestException))	#  7
-	.word _C_LABEL(MIPSX(GuestException))	#  8
-	.word _C_LABEL(MIPSX(GuestException))	#  9
-	.word _C_LABEL(MIPSX(GuestException))	# 10
-	.word _C_LABEL(MIPSX(GuestException))	# 11
-	.word _C_LABEL(MIPSX(GuestException))	# 12
-	.word _C_LABEL(MIPSX(GuestException))	# 13
-	.word _C_LABEL(MIPSX(GuestException))	# 14
-	.word _C_LABEL(MIPSX(GuestException))	# 15
-	.word _C_LABEL(MIPSX(GuestException))	# 16
-	.word _C_LABEL(MIPSX(GuestException))	# 17
-	.word _C_LABEL(MIPSX(GuestException))	# 18
-	.word _C_LABEL(MIPSX(GuestException))	# 19
-	.word _C_LABEL(MIPSX(GuestException))	# 20
-	.word _C_LABEL(MIPSX(GuestException))	# 21
-	.word _C_LABEL(MIPSX(GuestException))	# 22
-	.word _C_LABEL(MIPSX(GuestException))	# 23
-	.word _C_LABEL(MIPSX(GuestException))	# 24
-	.word _C_LABEL(MIPSX(GuestException))	# 25
-	.word _C_LABEL(MIPSX(GuestException))	# 26
-	.word _C_LABEL(MIPSX(GuestException))	# 27
-	.word _C_LABEL(MIPSX(GuestException))	# 28
-	.word _C_LABEL(MIPSX(GuestException))	# 29
-	.word _C_LABEL(MIPSX(GuestException))	# 30
-	.word _C_LABEL(MIPSX(GuestException))	# 31
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 44da5259f390..a6ea084b4d9d 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -9,6 +9,7 @@
  * Authors: Sanjay Lal <sanjayl@kymasys.com>
  */
 
+#include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kdebug.h>
@@ -147,7 +148,7 @@ void kvm_mips_free_vcpus(struct kvm *kvm)
 	/* Put the pages we reserved for the guest pmap */
 	for (i = 0; i < kvm->arch.guest_pmap_npages; i++) {
 		if (kvm->arch.guest_pmap[i] != KVM_INVALID_PAGE)
-			kvm_mips_release_pfn_clean(kvm->arch.guest_pmap[i]);
+			kvm_release_pfn_clean(kvm->arch.guest_pmap[i]);
 	}
 	kfree(kvm->arch.guest_pmap);
 
@@ -244,10 +245,27 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	}
 }
 
+static inline void dump_handler(const char *symbol, void *start, void *end)
+{
+	u32 *p;
+
+	pr_debug("LEAF(%s)\n", symbol);
+
+	pr_debug("\t.set push\n");
+	pr_debug("\t.set noreorder\n");
+
+	for (p = start; p < (u32 *)end; ++p)
+		pr_debug("\t.word\t0x%08x\t\t# %p\n", *p, p);
+
+	pr_debug("\t.set\tpop\n");
+
+	pr_debug("\tEND(%s)\n", symbol);
+}
+
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 {
-	int err, size, offset;
-	void *gebase;
+	int err, size;
+	void *gebase, *p, *handler;
 	int i;
 
 	struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
@@ -273,9 +291,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	else
 		size = 0x4000;
 
-	/* Save Linux EBASE */
-	vcpu->arch.host_ebase = (void *)read_c0_ebase();
-
 	gebase = kzalloc(ALIGN(size, PAGE_SIZE), GFP_KERNEL);
 
 	if (!gebase) {
@@ -285,44 +300,53 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	kvm_debug("Allocated %d bytes for KVM Exception Handlers @ %p\n",
 		  ALIGN(size, PAGE_SIZE), gebase);
 
+	/*
+	 * Check new ebase actually fits in CP0_EBase. The lack of a write gate
+	 * limits us to the low 512MB of physical address space. If the memory
+	 * we allocate is out of range, just give up now.
+	 */
+	if (!cpu_has_ebase_wg && virt_to_phys(gebase) >= 0x20000000) {
+		kvm_err("CP0_EBase.WG required for guest exception base %pK\n",
+			gebase);
+		err = -ENOMEM;
+		goto out_free_gebase;
+	}
+
 	/* Save new ebase */
 	vcpu->arch.guest_ebase = gebase;
 
-	/* Copy L1 Guest Exception handler to correct offset */
+	/* Build guest exception vectors dynamically in unmapped memory */
+	handler = gebase + 0x2000;
 
 	/* TLB Refill, EXL = 0 */
-	memcpy(gebase, mips32_exception,
-	       mips32_exceptionEnd - mips32_exception);
+	kvm_mips_build_exception(gebase, handler);
 
 	/* General Exception Entry point */
-	memcpy(gebase + 0x180, mips32_exception,
-	       mips32_exceptionEnd - mips32_exception);
+	kvm_mips_build_exception(gebase + 0x180, handler);
 
 	/* For vectored interrupts poke the exception code @ all offsets 0-7 */
 	for (i = 0; i < 8; i++) {
 		kvm_debug("L1 Vectored handler @ %p\n",
 			  gebase + 0x200 + (i * VECTORSPACING));
-		memcpy(gebase + 0x200 + (i * VECTORSPACING), mips32_exception,
-		       mips32_exceptionEnd - mips32_exception);
+		kvm_mips_build_exception(gebase + 0x200 + i * VECTORSPACING,
+					 handler);
 	}
 
-	/* General handler, relocate to unmapped space for sanity's sake */
-	offset = 0x2000;
-	kvm_debug("Installing KVM Exception handlers @ %p, %#x bytes\n",
-		  gebase + offset,
-		  mips32_GuestExceptionEnd - mips32_GuestException);
+	/* General exit handler */
+	p = handler;
+	p = kvm_mips_build_exit(p);
 
-	memcpy(gebase + offset, mips32_GuestException,
-	       mips32_GuestExceptionEnd - mips32_GuestException);
+	/* Guest entry routine */
+	vcpu->arch.vcpu_run = p;
+	p = kvm_mips_build_vcpu_run(p);
 
-#ifdef MODULE
-	offset += mips32_GuestExceptionEnd - mips32_GuestException;
-	memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run,
-	       __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run);
-	vcpu->arch.vcpu_run = gebase + offset;
-#else
-	vcpu->arch.vcpu_run = __kvm_mips_vcpu_run;
-#endif
+	/* Dump the generated code */
+	pr_debug("#include <asm/asm.h>\n");
+	pr_debug("#include <asm/regdef.h>\n");
+	pr_debug("\n");
+	dump_handler("kvm_vcpu_run", vcpu->arch.vcpu_run, p);
+	dump_handler("kvm_gen_exc", gebase + 0x180, gebase + 0x200);
+	dump_handler("kvm_exit", gebase + 0x2000, vcpu->arch.vcpu_run);
 
 	/* Invalidate the icache for these ranges */
 	local_flush_icache_range((unsigned long)gebase,
@@ -408,17 +432,19 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	kvm_mips_deliver_interrupts(vcpu,
 				    kvm_read_c0_guest_cause(vcpu->arch.cop0));
 
-	__kvm_guest_enter();
+	guest_enter_irqoff();
 
 	/* Disable hardware page table walking while in guest */
 	htw_stop();
 
+	trace_kvm_enter(vcpu);
 	r = vcpu->arch.vcpu_run(run, vcpu);
+	trace_kvm_out(vcpu);
 
 	/* Re-enable HTW before enabling interrupts */
 	htw_start();
 
-	__kvm_guest_exit();
+	guest_exit_irqoff();
 	local_irq_enable();
 
 	if (vcpu->sigset_active)
@@ -507,8 +533,10 @@ static u64 kvm_mips_get_one_regs[] = {
 	KVM_REG_MIPS_R30,
 	KVM_REG_MIPS_R31,
 
+#ifndef CONFIG_CPU_MIPSR6
 	KVM_REG_MIPS_HI,
 	KVM_REG_MIPS_LO,
+#endif
 	KVM_REG_MIPS_PC,
 
 	KVM_REG_MIPS_CP0_INDEX,
@@ -539,6 +567,104 @@ static u64 kvm_mips_get_one_regs[] = {
 	KVM_REG_MIPS_COUNT_HZ,
 };
 
+static u64 kvm_mips_get_one_regs_fpu[] = {
+	KVM_REG_MIPS_FCR_IR,
+	KVM_REG_MIPS_FCR_CSR,
+};
+
+static u64 kvm_mips_get_one_regs_msa[] = {
+	KVM_REG_MIPS_MSA_IR,
+	KVM_REG_MIPS_MSA_CSR,
+};
+
+static u64 kvm_mips_get_one_regs_kscratch[] = {
+	KVM_REG_MIPS_CP0_KSCRATCH1,
+	KVM_REG_MIPS_CP0_KSCRATCH2,
+	KVM_REG_MIPS_CP0_KSCRATCH3,
+	KVM_REG_MIPS_CP0_KSCRATCH4,
+	KVM_REG_MIPS_CP0_KSCRATCH5,
+	KVM_REG_MIPS_CP0_KSCRATCH6,
+};
+
+static unsigned long kvm_mips_num_regs(struct kvm_vcpu *vcpu)
+{
+	unsigned long ret;
+
+	ret = ARRAY_SIZE(kvm_mips_get_one_regs);
+	if (kvm_mips_guest_can_have_fpu(&vcpu->arch)) {
+		ret += ARRAY_SIZE(kvm_mips_get_one_regs_fpu) + 48;
+		/* odd doubles */
+		if (boot_cpu_data.fpu_id & MIPS_FPIR_F64)
+			ret += 16;
+	}
+	if (kvm_mips_guest_can_have_msa(&vcpu->arch))
+		ret += ARRAY_SIZE(kvm_mips_get_one_regs_msa) + 32;
+	ret += __arch_hweight8(vcpu->arch.kscratch_enabled);
+	ret += kvm_mips_callbacks->num_regs(vcpu);
+
+	return ret;
+}
+
+static int kvm_mips_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices)
+{
+	u64 index;
+	unsigned int i;
+
+	if (copy_to_user(indices, kvm_mips_get_one_regs,
+			 sizeof(kvm_mips_get_one_regs)))
+		return -EFAULT;
+	indices += ARRAY_SIZE(kvm_mips_get_one_regs);
+
+	if (kvm_mips_guest_can_have_fpu(&vcpu->arch)) {
+		if (copy_to_user(indices, kvm_mips_get_one_regs_fpu,
+				 sizeof(kvm_mips_get_one_regs_fpu)))
+			return -EFAULT;
+		indices += ARRAY_SIZE(kvm_mips_get_one_regs_fpu);
+
+		for (i = 0; i < 32; ++i) {
+			index = KVM_REG_MIPS_FPR_32(i);
+			if (copy_to_user(indices, &index, sizeof(index)))
+				return -EFAULT;
+			++indices;
+
+			/* skip odd doubles if no F64 */
+			if (i & 1 && !(boot_cpu_data.fpu_id & MIPS_FPIR_F64))
+				continue;
+
+			index = KVM_REG_MIPS_FPR_64(i);
+			if (copy_to_user(indices, &index, sizeof(index)))
+				return -EFAULT;
+			++indices;
+		}
+	}
+
+	if (kvm_mips_guest_can_have_msa(&vcpu->arch)) {
+		if (copy_to_user(indices, kvm_mips_get_one_regs_msa,
+				 sizeof(kvm_mips_get_one_regs_msa)))
+			return -EFAULT;
+		indices += ARRAY_SIZE(kvm_mips_get_one_regs_msa);
+
+		for (i = 0; i < 32; ++i) {
+			index = KVM_REG_MIPS_VEC_128(i);
+			if (copy_to_user(indices, &index, sizeof(index)))
+				return -EFAULT;
+			++indices;
+		}
+	}
+
+	for (i = 0; i < 6; ++i) {
+		if (!(vcpu->arch.kscratch_enabled & BIT(i + 2)))
+			continue;
+
+		if (copy_to_user(indices, &kvm_mips_get_one_regs_kscratch[i],
+				 sizeof(kvm_mips_get_one_regs_kscratch[i])))
+			return -EFAULT;
+		++indices;
+	}
+
+	return kvm_mips_callbacks->copy_reg_indices(vcpu, indices);
+}
+
 static int kvm_mips_get_reg(struct kvm_vcpu *vcpu,
 			    const struct kvm_one_reg *reg)
 {
@@ -554,12 +680,14 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu,
 	case KVM_REG_MIPS_R0 ... KVM_REG_MIPS_R31:
 		v = (long)vcpu->arch.gprs[reg->id - KVM_REG_MIPS_R0];
 		break;
+#ifndef CONFIG_CPU_MIPSR6
 	case KVM_REG_MIPS_HI:
 		v = (long)vcpu->arch.hi;
 		break;
 	case KVM_REG_MIPS_LO:
 		v = (long)vcpu->arch.lo;
 		break;
+#endif
 	case KVM_REG_MIPS_PC:
 		v = (long)vcpu->arch.pc;
 		break;
@@ -688,17 +816,37 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu,
 	case KVM_REG_MIPS_CP0_ERROREPC:
 		v = (long)kvm_read_c0_guest_errorepc(cop0);
 		break;
+	case KVM_REG_MIPS_CP0_KSCRATCH1 ... KVM_REG_MIPS_CP0_KSCRATCH6:
+		idx = reg->id - KVM_REG_MIPS_CP0_KSCRATCH1 + 2;
+		if (!(vcpu->arch.kscratch_enabled & BIT(idx)))
+			return -EINVAL;
+		switch (idx) {
+		case 2:
+			v = (long)kvm_read_c0_guest_kscratch1(cop0);
+			break;
+		case 3:
+			v = (long)kvm_read_c0_guest_kscratch2(cop0);
+			break;
+		case 4:
+			v = (long)kvm_read_c0_guest_kscratch3(cop0);
+			break;
+		case 5:
+			v = (long)kvm_read_c0_guest_kscratch4(cop0);
+			break;
+		case 6:
+			v = (long)kvm_read_c0_guest_kscratch5(cop0);
+			break;
+		case 7:
+			v = (long)kvm_read_c0_guest_kscratch6(cop0);
+			break;
+		}
+		break;
 	/* registers to be handled specially */
-	case KVM_REG_MIPS_CP0_COUNT:
-	case KVM_REG_MIPS_COUNT_CTL:
-	case KVM_REG_MIPS_COUNT_RESUME:
-	case KVM_REG_MIPS_COUNT_HZ:
+	default:
 		ret = kvm_mips_callbacks->get_one_reg(vcpu, reg, &v);
 		if (ret)
 			return ret;
 		break;
-	default:
-		return -EINVAL;
 	}
 	if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U64) {
 		u64 __user *uaddr64 = (u64 __user *)(long)reg->addr;
@@ -755,12 +903,14 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu,
 	case KVM_REG_MIPS_R1 ... KVM_REG_MIPS_R31:
 		vcpu->arch.gprs[reg->id - KVM_REG_MIPS_R0] = v;
 		break;
+#ifndef CONFIG_CPU_MIPSR6
 	case KVM_REG_MIPS_HI:
 		vcpu->arch.hi = v;
 		break;
 	case KVM_REG_MIPS_LO:
 		vcpu->arch.lo = v;
 		break;
+#endif
 	case KVM_REG_MIPS_PC:
 		vcpu->arch.pc = v;
 		break;
@@ -859,22 +1009,34 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu,
 	case KVM_REG_MIPS_CP0_ERROREPC:
 		kvm_write_c0_guest_errorepc(cop0, v);
 		break;
+	case KVM_REG_MIPS_CP0_KSCRATCH1 ... KVM_REG_MIPS_CP0_KSCRATCH6:
+		idx = reg->id - KVM_REG_MIPS_CP0_KSCRATCH1 + 2;
+		if (!(vcpu->arch.kscratch_enabled & BIT(idx)))
+			return -EINVAL;
+		switch (idx) {
+		case 2:
+			kvm_write_c0_guest_kscratch1(cop0, v);
+			break;
+		case 3:
+			kvm_write_c0_guest_kscratch2(cop0, v);
+			break;
+		case 4:
+			kvm_write_c0_guest_kscratch3(cop0, v);
+			break;
+		case 5:
+			kvm_write_c0_guest_kscratch4(cop0, v);
+			break;
+		case 6:
+			kvm_write_c0_guest_kscratch5(cop0, v);
+			break;
+		case 7:
+			kvm_write_c0_guest_kscratch6(cop0, v);
+			break;
+		}
+		break;
 	/* registers to be handled specially */
-	case KVM_REG_MIPS_CP0_COUNT:
-	case KVM_REG_MIPS_CP0_COMPARE:
-	case KVM_REG_MIPS_CP0_CAUSE:
-	case KVM_REG_MIPS_CP0_CONFIG:
-	case KVM_REG_MIPS_CP0_CONFIG1:
-	case KVM_REG_MIPS_CP0_CONFIG2:
-	case KVM_REG_MIPS_CP0_CONFIG3:
-	case KVM_REG_MIPS_CP0_CONFIG4:
-	case KVM_REG_MIPS_CP0_CONFIG5:
-	case KVM_REG_MIPS_COUNT_CTL:
-	case KVM_REG_MIPS_COUNT_RESUME:
-	case KVM_REG_MIPS_COUNT_HZ:
-		return kvm_mips_callbacks->set_one_reg(vcpu, reg, v);
 	default:
-		return -EINVAL;
+		return kvm_mips_callbacks->set_one_reg(vcpu, reg, v);
 	}
 	return 0;
 }
@@ -927,23 +1089,18 @@ long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl,
 	}
 	case KVM_GET_REG_LIST: {
 		struct kvm_reg_list __user *user_list = argp;
-		u64 __user *reg_dest;
 		struct kvm_reg_list reg_list;
 		unsigned n;
 
 		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
 			return -EFAULT;
 		n = reg_list.n;
-		reg_list.n = ARRAY_SIZE(kvm_mips_get_one_regs);
+		reg_list.n = kvm_mips_num_regs(vcpu);
 		if (copy_to_user(user_list, &reg_list, sizeof(reg_list)))
 			return -EFAULT;
 		if (n < reg_list.n)
 			return -E2BIG;
-		reg_dest = user_list->reg;
-		if (copy_to_user(reg_dest, kvm_mips_get_one_regs,
-				 sizeof(kvm_mips_get_one_regs)))
-			return -EFAULT;
-		return 0;
+		return kvm_mips_copy_reg_indices(vcpu, user_list->reg);
 	}
 	case KVM_NMI:
 		/* Treat the NMI as a CPU reset */
@@ -1222,7 +1379,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 
 static void kvm_mips_set_c0_status(void)
 {
-	uint32_t status = read_c0_status();
+	u32 status = read_c0_status();
 
 	if (cpu_has_dsp)
 		status |= (ST0_MX);
@@ -1236,9 +1393,9 @@ static void kvm_mips_set_c0_status(void)
  */
 int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
-	uint32_t cause = vcpu->arch.host_cp0_cause;
-	uint32_t exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
+	u32 cause = vcpu->arch.host_cp0_cause;
+	u32 exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
+	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
 	unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
@@ -1260,6 +1417,7 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	kvm_debug("kvm_mips_handle_exit: cause: %#x, PC: %p, kvm_run: %p, kvm_vcpu: %p\n",
 			cause, opc, run, vcpu);
+	trace_kvm_exit(vcpu, exccode);
 
 	/*
 	 * Do a privilege check, if in UM most of these exit conditions end up
@@ -1279,7 +1437,6 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		kvm_debug("[%d]EXCCODE_INT @ %p\n", vcpu->vcpu_id, opc);
 
 		++vcpu->stat.int_exits;
-		trace_kvm_exit(vcpu, INT_EXITS);
 
 		if (need_resched())
 			cond_resched();
@@ -1291,7 +1448,6 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		kvm_debug("EXCCODE_CPU: @ PC: %p\n", opc);
 
 		++vcpu->stat.cop_unusable_exits;
-		trace_kvm_exit(vcpu, COP_UNUSABLE_EXITS);
 		ret = kvm_mips_callbacks->handle_cop_unusable(vcpu);
 		/* XXXKYMA: Might need to return to user space */
 		if (run->exit_reason == KVM_EXIT_IRQ_WINDOW_OPEN)
@@ -1300,7 +1456,6 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	case EXCCODE_MOD:
 		++vcpu->stat.tlbmod_exits;
-		trace_kvm_exit(vcpu, TLBMOD_EXITS);
 		ret = kvm_mips_callbacks->handle_tlb_mod(vcpu);
 		break;
 
@@ -1310,7 +1465,6 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			  badvaddr);
 
 		++vcpu->stat.tlbmiss_st_exits;
-		trace_kvm_exit(vcpu, TLBMISS_ST_EXITS);
 		ret = kvm_mips_callbacks->handle_tlb_st_miss(vcpu);
 		break;
 
@@ -1319,61 +1473,51 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			  cause, opc, badvaddr);
 
 		++vcpu->stat.tlbmiss_ld_exits;
-		trace_kvm_exit(vcpu, TLBMISS_LD_EXITS);
 		ret = kvm_mips_callbacks->handle_tlb_ld_miss(vcpu);
 		break;
 
 	case EXCCODE_ADES:
 		++vcpu->stat.addrerr_st_exits;
-		trace_kvm_exit(vcpu, ADDRERR_ST_EXITS);
 		ret = kvm_mips_callbacks->handle_addr_err_st(vcpu);
 		break;
 
 	case EXCCODE_ADEL:
 		++vcpu->stat.addrerr_ld_exits;
-		trace_kvm_exit(vcpu, ADDRERR_LD_EXITS);
 		ret = kvm_mips_callbacks->handle_addr_err_ld(vcpu);
 		break;
 
 	case EXCCODE_SYS:
 		++vcpu->stat.syscall_exits;
-		trace_kvm_exit(vcpu, SYSCALL_EXITS);
 		ret = kvm_mips_callbacks->handle_syscall(vcpu);
 		break;
 
 	case EXCCODE_RI:
 		++vcpu->stat.resvd_inst_exits;
-		trace_kvm_exit(vcpu, RESVD_INST_EXITS);
 		ret = kvm_mips_callbacks->handle_res_inst(vcpu);
 		break;
 
 	case EXCCODE_BP:
 		++vcpu->stat.break_inst_exits;
-		trace_kvm_exit(vcpu, BREAK_INST_EXITS);
 		ret = kvm_mips_callbacks->handle_break(vcpu);
 		break;
 
 	case EXCCODE_TR:
 		++vcpu->stat.trap_inst_exits;
-		trace_kvm_exit(vcpu, TRAP_INST_EXITS);
 		ret = kvm_mips_callbacks->handle_trap(vcpu);
 		break;
 
 	case EXCCODE_MSAFPE:
 		++vcpu->stat.msa_fpe_exits;
-		trace_kvm_exit(vcpu, MSA_FPE_EXITS);
 		ret = kvm_mips_callbacks->handle_msa_fpe(vcpu);
 		break;
 
 	case EXCCODE_FPE:
 		++vcpu->stat.fpe_exits;
-		trace_kvm_exit(vcpu, FPE_EXITS);
 		ret = kvm_mips_callbacks->handle_fpe(vcpu);
 		break;
 
 	case EXCCODE_MSADIS:
 		++vcpu->stat.msa_disabled_exits;
-		trace_kvm_exit(vcpu, MSA_DISABLED_EXITS);
 		ret = kvm_mips_callbacks->handle_msa_disabled(vcpu);
 		break;
 
@@ -1400,11 +1544,13 @@ skip_emul:
 			run->exit_reason = KVM_EXIT_INTR;
 			ret = (-EINTR << 2) | RESUME_HOST;
 			++vcpu->stat.signal_exits;
-			trace_kvm_exit(vcpu, SIGNAL_EXITS);
+			trace_kvm_exit(vcpu, KVM_TRACE_EXIT_SIGNAL);
 		}
 	}
 
 	if (ret == RESUME_GUEST) {
+		trace_kvm_reenter(vcpu);
+
 		/*
 		 * If FPU / MSA are enabled (i.e. the guest's FPU / MSA context
 		 * is live), restore FCR31 / MSACSR.
@@ -1450,7 +1596,7 @@ void kvm_own_fpu(struct kvm_vcpu *vcpu)
 	 * not to clobber the status register directly via the commpage.
 	 */
 	if (cpu_has_msa && sr & ST0_CU1 && !(sr & ST0_FR) &&
-	    vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA)
+	    vcpu->arch.aux_inuse & KVM_MIPS_AUX_MSA)
 		kvm_lose_fpu(vcpu);
 
 	/*
@@ -1465,9 +1611,12 @@ void kvm_own_fpu(struct kvm_vcpu *vcpu)
 	enable_fpu_hazard();
 
 	/* If guest FPU state not active, restore it now */
-	if (!(vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU)) {
+	if (!(vcpu->arch.aux_inuse & KVM_MIPS_AUX_FPU)) {
 		__kvm_restore_fpu(&vcpu->arch);
-		vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_FPU;
+		vcpu->arch.aux_inuse |= KVM_MIPS_AUX_FPU;
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE, KVM_TRACE_AUX_FPU);
+	} else {
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_ENABLE, KVM_TRACE_AUX_FPU);
 	}
 
 	preempt_enable();
@@ -1494,8 +1643,8 @@ void kvm_own_msa(struct kvm_vcpu *vcpu)
 		 * interacts with MSA state, so play it safe and save it first.
 		 */
 		if (!(sr & ST0_FR) &&
-		    (vcpu->arch.fpu_inuse & (KVM_MIPS_FPU_FPU |
-				KVM_MIPS_FPU_MSA)) == KVM_MIPS_FPU_FPU)
+		    (vcpu->arch.aux_inuse & (KVM_MIPS_AUX_FPU |
+				KVM_MIPS_AUX_MSA)) == KVM_MIPS_AUX_FPU)
 			kvm_lose_fpu(vcpu);
 
 		change_c0_status(ST0_CU1 | ST0_FR, sr);
@@ -1509,22 +1658,26 @@ void kvm_own_msa(struct kvm_vcpu *vcpu)
 	set_c0_config5(MIPS_CONF5_MSAEN);
 	enable_fpu_hazard();
 
-	switch (vcpu->arch.fpu_inuse & (KVM_MIPS_FPU_FPU | KVM_MIPS_FPU_MSA)) {
-	case KVM_MIPS_FPU_FPU:
+	switch (vcpu->arch.aux_inuse & (KVM_MIPS_AUX_FPU | KVM_MIPS_AUX_MSA)) {
+	case KVM_MIPS_AUX_FPU:
 		/*
 		 * Guest FPU state already loaded, only restore upper MSA state
 		 */
 		__kvm_restore_msa_upper(&vcpu->arch);
-		vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_MSA;
+		vcpu->arch.aux_inuse |= KVM_MIPS_AUX_MSA;
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE, KVM_TRACE_AUX_MSA);
 		break;
 	case 0:
 		/* Neither FPU or MSA already active, restore full MSA state */
 		__kvm_restore_msa(&vcpu->arch);
-		vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_MSA;
+		vcpu->arch.aux_inuse |= KVM_MIPS_AUX_MSA;
 		if (kvm_mips_guest_has_fpu(&vcpu->arch))
-			vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_FPU;
+			vcpu->arch.aux_inuse |= KVM_MIPS_AUX_FPU;
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE,
+			      KVM_TRACE_AUX_FPU_MSA);
 		break;
 	default:
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_ENABLE, KVM_TRACE_AUX_MSA);
 		break;
 	}
 
@@ -1536,13 +1689,15 @@ void kvm_own_msa(struct kvm_vcpu *vcpu)
 void kvm_drop_fpu(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
-	if (cpu_has_msa && vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) {
+	if (cpu_has_msa && vcpu->arch.aux_inuse & KVM_MIPS_AUX_MSA) {
 		disable_msa();
-		vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_MSA;
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_DISCARD, KVM_TRACE_AUX_MSA);
+		vcpu->arch.aux_inuse &= ~KVM_MIPS_AUX_MSA;
 	}
-	if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) {
+	if (vcpu->arch.aux_inuse & KVM_MIPS_AUX_FPU) {
 		clear_c0_status(ST0_CU1 | ST0_FR);
-		vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_FPU;
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_DISCARD, KVM_TRACE_AUX_FPU);
+		vcpu->arch.aux_inuse &= ~KVM_MIPS_AUX_FPU;
 	}
 	preempt_enable();
 }
@@ -1558,25 +1713,27 @@ void kvm_lose_fpu(struct kvm_vcpu *vcpu)
 	 */
 
 	preempt_disable();
-	if (cpu_has_msa && vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) {
+	if (cpu_has_msa && vcpu->arch.aux_inuse & KVM_MIPS_AUX_MSA) {
 		set_c0_config5(MIPS_CONF5_MSAEN);
 		enable_fpu_hazard();
 
 		__kvm_save_msa(&vcpu->arch);
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_FPU_MSA);
 
 		/* Disable MSA & FPU */
 		disable_msa();
-		if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) {
+		if (vcpu->arch.aux_inuse & KVM_MIPS_AUX_FPU) {
 			clear_c0_status(ST0_CU1 | ST0_FR);
 			disable_fpu_hazard();
 		}
-		vcpu->arch.fpu_inuse &= ~(KVM_MIPS_FPU_FPU | KVM_MIPS_FPU_MSA);
-	} else if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) {
+		vcpu->arch.aux_inuse &= ~(KVM_MIPS_AUX_FPU | KVM_MIPS_AUX_MSA);
+	} else if (vcpu->arch.aux_inuse & KVM_MIPS_AUX_FPU) {
 		set_c0_status(ST0_CU1);
 		enable_fpu_hazard();
 
 		__kvm_save_fpu(&vcpu->arch);
-		vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_FPU;
+		vcpu->arch.aux_inuse &= ~KVM_MIPS_AUX_FPU;
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_FPU);
 
 		/* Disable FPU */
 		clear_c0_status(ST0_CU1 | ST0_FR);
@@ -1638,6 +1795,10 @@ static int __init kvm_mips_init(void)
 {
 	int ret;
 
+	ret = kvm_mips_entry_setup();
+	if (ret)
+		return ret;
+
 	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 
 	if (ret)
@@ -1645,18 +1806,6 @@ static int __init kvm_mips_init(void)
 
 	register_die_notifier(&kvm_mips_csr_die_notifier);
 
-	/*
-	 * On MIPS, kernel modules are executed from "mapped space", which
-	 * requires TLBs. The TLB handling code is statically linked with
-	 * the rest of the kernel (tlb.c) to avoid the possibility of
-	 * double faulting. The issue is that the TLB code references
-	 * routines that are part of the the KVM module, which are only
-	 * available once the module is loaded.
-	 */
-	kvm_mips_gfn_to_pfn = gfn_to_pfn;
-	kvm_mips_release_pfn_clean = kvm_release_pfn_clean;
-	kvm_mips_is_error_pfn = is_error_pfn;
-
 	return 0;
 }
 
@@ -1664,10 +1813,6 @@ static void __exit kvm_mips_exit(void)
 {
 	kvm_exit();
 
-	kvm_mips_gfn_to_pfn = NULL;
-	kvm_mips_release_pfn_clean = NULL;
-	kvm_mips_is_error_pfn = NULL;
-
 	unregister_die_notifier(&kvm_mips_csr_die_notifier);
 }
 
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
new file mode 100644
index 000000000000..57319ee57c4f
--- /dev/null
+++ b/arch/mips/kvm/mmu.c
@@ -0,0 +1,375 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * KVM/MIPS MMU handling in the KVM module.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
+
+#include <linux/highmem.h>
+#include <linux/kvm_host.h>
+#include <asm/mmu_context.h>
+
+static u32 kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu)
+{
+	int cpu = smp_processor_id();
+
+	return vcpu->arch.guest_kernel_asid[cpu] &
+			cpu_asid_mask(&cpu_data[cpu]);
+}
+
+static u32 kvm_mips_get_user_asid(struct kvm_vcpu *vcpu)
+{
+	int cpu = smp_processor_id();
+
+	return vcpu->arch.guest_user_asid[cpu] &
+			cpu_asid_mask(&cpu_data[cpu]);
+}
+
+static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn)
+{
+	int srcu_idx, err = 0;
+	kvm_pfn_t pfn;
+
+	if (kvm->arch.guest_pmap[gfn] != KVM_INVALID_PAGE)
+		return 0;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	pfn = gfn_to_pfn(kvm, gfn);
+
+	if (is_error_pfn(pfn)) {
+		kvm_err("Couldn't get pfn for gfn %#llx!\n", gfn);
+		err = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.guest_pmap[gfn] = pfn;
+out:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return err;
+}
+
+/* Translate guest KSEG0 addresses to Host PA */
+unsigned long kvm_mips_translate_guest_kseg0_to_hpa(struct kvm_vcpu *vcpu,
+						    unsigned long gva)
+{
+	gfn_t gfn;
+	unsigned long offset = gva & ~PAGE_MASK;
+	struct kvm *kvm = vcpu->kvm;
+
+	if (KVM_GUEST_KSEGX(gva) != KVM_GUEST_KSEG0) {
+		kvm_err("%s/%p: Invalid gva: %#lx\n", __func__,
+			__builtin_return_address(0), gva);
+		return KVM_INVALID_PAGE;
+	}
+
+	gfn = (KVM_GUEST_CPHYSADDR(gva) >> PAGE_SHIFT);
+
+	if (gfn >= kvm->arch.guest_pmap_npages) {
+		kvm_err("%s: Invalid gfn: %#llx, GVA: %#lx\n", __func__, gfn,
+			gva);
+		return KVM_INVALID_PAGE;
+	}
+
+	if (kvm_mips_map_page(vcpu->kvm, gfn) < 0)
+		return KVM_INVALID_ADDR;
+
+	return (kvm->arch.guest_pmap[gfn] << PAGE_SHIFT) + offset;
+}
+
+/* XXXKYMA: Must be called with interrupts disabled */
+int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr,
+				    struct kvm_vcpu *vcpu)
+{
+	gfn_t gfn;
+	kvm_pfn_t pfn0, pfn1;
+	unsigned long vaddr = 0;
+	unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
+	struct kvm *kvm = vcpu->kvm;
+	const int flush_dcache_mask = 0;
+	int ret;
+
+	if (KVM_GUEST_KSEGX(badvaddr) != KVM_GUEST_KSEG0) {
+		kvm_err("%s: Invalid BadVaddr: %#lx\n", __func__, badvaddr);
+		kvm_mips_dump_host_tlbs();
+		return -1;
+	}
+
+	gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT);
+	if (gfn >= kvm->arch.guest_pmap_npages) {
+		kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__,
+			gfn, badvaddr);
+		kvm_mips_dump_host_tlbs();
+		return -1;
+	}
+	vaddr = badvaddr & (PAGE_MASK << 1);
+
+	if (kvm_mips_map_page(vcpu->kvm, gfn) < 0)
+		return -1;
+
+	if (kvm_mips_map_page(vcpu->kvm, gfn ^ 0x1) < 0)
+		return -1;
+
+	pfn0 = kvm->arch.guest_pmap[gfn & ~0x1];
+	pfn1 = kvm->arch.guest_pmap[gfn | 0x1];
+
+	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) |
+		((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
+		ENTRYLO_D | ENTRYLO_V;
+	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) |
+		((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
+		ENTRYLO_D | ENTRYLO_V;
+
+	preempt_disable();
+	entryhi = (vaddr | kvm_mips_get_kernel_asid(vcpu));
+	ret = kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
+				      flush_dcache_mask);
+	preempt_enable();
+
+	return ret;
+}
+
+int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
+					 struct kvm_mips_tlb *tlb)
+{
+	unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
+	struct kvm *kvm = vcpu->kvm;
+	kvm_pfn_t pfn0, pfn1;
+	int ret;
+
+	if ((tlb->tlb_hi & VPN2_MASK) == 0) {
+		pfn0 = 0;
+		pfn1 = 0;
+	} else {
+		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[0])
+					   >> PAGE_SHIFT) < 0)
+			return -1;
+
+		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[1])
+					   >> PAGE_SHIFT) < 0)
+			return -1;
+
+		pfn0 = kvm->arch.guest_pmap[
+			mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) >> PAGE_SHIFT];
+		pfn1 = kvm->arch.guest_pmap[
+			mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) >> PAGE_SHIFT];
+	}
+
+	/* Get attributes from the Guest TLB */
+	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) |
+		((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
+		(tlb->tlb_lo[0] & ENTRYLO_D) |
+		(tlb->tlb_lo[0] & ENTRYLO_V);
+	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) |
+		((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
+		(tlb->tlb_lo[1] & ENTRYLO_D) |
+		(tlb->tlb_lo[1] & ENTRYLO_V);
+
+	kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
+		  tlb->tlb_lo[0], tlb->tlb_lo[1]);
+
+	preempt_disable();
+	entryhi = (tlb->tlb_hi & VPN2_MASK) | (KVM_GUEST_KERNEL_MODE(vcpu) ?
+					       kvm_mips_get_kernel_asid(vcpu) :
+					       kvm_mips_get_user_asid(vcpu));
+	ret = kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
+				      tlb->tlb_mask);
+	preempt_enable();
+
+	return ret;
+}
+
+void kvm_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu,
+			     struct kvm_vcpu *vcpu)
+{
+	unsigned long asid = asid_cache(cpu);
+
+	asid += cpu_asid_inc();
+	if (!(asid & cpu_asid_mask(&cpu_data[cpu]))) {
+		if (cpu_has_vtag_icache)
+			flush_icache_all();
+
+		kvm_local_flush_tlb_all();      /* start new asid cycle */
+
+		if (!asid)      /* fix version if needed */
+			asid = asid_first_version(cpu);
+	}
+
+	cpu_context(cpu, mm) = asid_cache(cpu) = asid;
+}
+
+/**
+ * kvm_mips_migrate_count() - Migrate timer.
+ * @vcpu:	Virtual CPU.
+ *
+ * Migrate CP0_Count hrtimer to the current CPU by cancelling and restarting it
+ * if it was running prior to being cancelled.
+ *
+ * Must be called when the VCPU is migrated to a different CPU to ensure that
+ * timer expiry during guest execution interrupts the guest and causes the
+ * interrupt to be delivered in a timely manner.
+ */
+static void kvm_mips_migrate_count(struct kvm_vcpu *vcpu)
+{
+	if (hrtimer_cancel(&vcpu->arch.comparecount_timer))
+		hrtimer_restart(&vcpu->arch.comparecount_timer);
+}
+
+/* Restore ASID once we are scheduled back after preemption */
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	unsigned long asid_mask = cpu_asid_mask(&cpu_data[cpu]);
+	unsigned long flags;
+	int newasid = 0;
+
+	kvm_debug("%s: vcpu %p, cpu: %d\n", __func__, vcpu, cpu);
+
+	/* Allocate new kernel and user ASIDs if needed */
+
+	local_irq_save(flags);
+
+	if ((vcpu->arch.guest_kernel_asid[cpu] ^ asid_cache(cpu)) &
+						asid_version_mask(cpu)) {
+		kvm_get_new_mmu_context(&vcpu->arch.guest_kernel_mm, cpu, vcpu);
+		vcpu->arch.guest_kernel_asid[cpu] =
+		    vcpu->arch.guest_kernel_mm.context.asid[cpu];
+		kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu, vcpu);
+		vcpu->arch.guest_user_asid[cpu] =
+		    vcpu->arch.guest_user_mm.context.asid[cpu];
+		newasid++;
+
+		kvm_debug("[%d]: cpu_context: %#lx\n", cpu,
+			  cpu_context(cpu, current->mm));
+		kvm_debug("[%d]: Allocated new ASID for Guest Kernel: %#x\n",
+			  cpu, vcpu->arch.guest_kernel_asid[cpu]);
+		kvm_debug("[%d]: Allocated new ASID for Guest User: %#x\n", cpu,
+			  vcpu->arch.guest_user_asid[cpu]);
+	}
+
+	if (vcpu->arch.last_sched_cpu != cpu) {
+		kvm_debug("[%d->%d]KVM VCPU[%d] switch\n",
+			  vcpu->arch.last_sched_cpu, cpu, vcpu->vcpu_id);
+		/*
+		 * Migrate the timer interrupt to the current CPU so that it
+		 * always interrupts the guest and synchronously triggers a
+		 * guest timer interrupt.
+		 */
+		kvm_mips_migrate_count(vcpu);
+	}
+
+	if (!newasid) {
+		/*
+		 * If we preempted while the guest was executing, then reload
+		 * the pre-empted ASID
+		 */
+		if (current->flags & PF_VCPU) {
+			write_c0_entryhi(vcpu->arch.
+					 preempt_entryhi & asid_mask);
+			ehb();
+		}
+	} else {
+		/* New ASIDs were allocated for the VM */
+
+		/*
+		 * Were we in guest context? If so then the pre-empted ASID is
+		 * no longer valid, we need to set it to what it should be based
+		 * on the mode of the Guest (Kernel/User)
+		 */
+		if (current->flags & PF_VCPU) {
+			if (KVM_GUEST_KERNEL_MODE(vcpu))
+				write_c0_entryhi(vcpu->arch.
+						 guest_kernel_asid[cpu] &
+						 asid_mask);
+			else
+				write_c0_entryhi(vcpu->arch.
+						 guest_user_asid[cpu] &
+						 asid_mask);
+			ehb();
+		}
+	}
+
+	/* restore guest state to registers */
+	kvm_mips_callbacks->vcpu_set_regs(vcpu);
+
+	local_irq_restore(flags);
+
+}
+
+/* ASID can change if another task is scheduled during preemption */
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	unsigned long flags;
+	int cpu;
+
+	local_irq_save(flags);
+
+	cpu = smp_processor_id();
+
+	vcpu->arch.preempt_entryhi = read_c0_entryhi();
+	vcpu->arch.last_sched_cpu = cpu;
+
+	/* save guest state in registers */
+	kvm_mips_callbacks->vcpu_get_regs(vcpu);
+
+	if (((cpu_context(cpu, current->mm) ^ asid_cache(cpu)) &
+	     asid_version_mask(cpu))) {
+		kvm_debug("%s: Dropping MMU Context:  %#lx\n", __func__,
+			  cpu_context(cpu, current->mm));
+		drop_mmu_context(current->mm, cpu);
+	}
+	write_c0_entryhi(cpu_asid(cpu, current->mm));
+	ehb();
+
+	local_irq_restore(flags);
+}
+
+u32 kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	unsigned long paddr, flags, vpn2, asid;
+	unsigned long va = (unsigned long)opc;
+	void *vaddr;
+	u32 inst;
+	int index;
+
+	if (KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0 ||
+	    KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) {
+		local_irq_save(flags);
+		index = kvm_mips_host_tlb_lookup(vcpu, va);
+		if (index >= 0) {
+			inst = *(opc);
+		} else {
+			vpn2 = va & VPN2_MASK;
+			asid = kvm_read_c0_guest_entryhi(cop0) &
+						KVM_ENTRYHI_ASID;
+			index = kvm_mips_guest_tlb_lookup(vcpu, vpn2 | asid);
+			if (index < 0) {
+				kvm_err("%s: get_user_failed for %p, vcpu: %p, ASID: %#lx\n",
+					__func__, opc, vcpu, read_c0_entryhi());
+				kvm_mips_dump_host_tlbs();
+				kvm_mips_dump_guest_tlbs(vcpu);
+				local_irq_restore(flags);
+				return KVM_INVALID_INST;
+			}
+			kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
+							     &vcpu->arch.
+							     guest_tlb[index]);
+			inst = *(opc);
+		}
+		local_irq_restore(flags);
+	} else if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) {
+		paddr = kvm_mips_translate_guest_kseg0_to_hpa(vcpu, va);
+		vaddr = kmap_atomic(pfn_to_page(PHYS_PFN(paddr)));
+		vaddr += paddr & ~PAGE_MASK;
+		inst = *(u32 *)vaddr;
+		kunmap_atomic(vaddr);
+	} else {
+		kvm_err("%s: illegal address: %p\n", __func__, opc);
+		return KVM_INVALID_INST;
+	}
+
+	return inst;
+}
diff --git a/arch/mips/kvm/stats.c b/arch/mips/kvm/stats.c
index 888bb67070ac..53f851a61554 100644
--- a/arch/mips/kvm/stats.c
+++ b/arch/mips/kvm/stats.c
@@ -11,27 +11,6 @@
 
 #include <linux/kvm_host.h>
 
-char *kvm_mips_exit_types_str[MAX_KVM_MIPS_EXIT_TYPES] = {
-	"WAIT",
-	"CACHE",
-	"Signal",
-	"Interrupt",
-	"COP0/1 Unusable",
-	"TLB Mod",
-	"TLB Miss (LD)",
-	"TLB Miss (ST)",
-	"Address Err (ST)",
-	"Address Error (LD)",
-	"System Call",
-	"Reserved Inst",
-	"Break Inst",
-	"Trap Inst",
-	"MSA FPE",
-	"FPE",
-	"MSA Disabled",
-	"D-Cache Flushes",
-};
-
 char *kvm_cop0_str[N_MIPS_COPROC_REGS] = {
 	"Index",
 	"Random",
diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c
index ed021ae7867a..254377d8e0b9 100644
--- a/arch/mips/kvm/tlb.c
+++ b/arch/mips/kvm/tlb.c
@@ -14,7 +14,7 @@
 #include <linux/smp.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kvm_host.h>
 #include <linux/srcu.h>
 
@@ -24,6 +24,7 @@
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 #include <asm/tlb.h>
+#include <asm/tlbdebug.h>
 
 #undef CONFIG_MIPS_MT
 #include <asm/r4kcache.h>
@@ -32,22 +33,10 @@
 #define KVM_GUEST_PC_TLB    0
 #define KVM_GUEST_SP_TLB    1
 
-#define PRIx64 "llx"
-
 atomic_t kvm_mips_instance;
 EXPORT_SYMBOL_GPL(kvm_mips_instance);
 
-/* These function pointers are initialized once the KVM module is loaded */
-kvm_pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn);
-EXPORT_SYMBOL_GPL(kvm_mips_gfn_to_pfn);
-
-void (*kvm_mips_release_pfn_clean)(kvm_pfn_t pfn);
-EXPORT_SYMBOL_GPL(kvm_mips_release_pfn_clean);
-
-bool (*kvm_mips_is_error_pfn)(kvm_pfn_t pfn);
-EXPORT_SYMBOL_GPL(kvm_mips_is_error_pfn);
-
-uint32_t kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu)
+static u32 kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu)
 {
 	int cpu = smp_processor_id();
 
@@ -55,7 +44,7 @@ uint32_t kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu)
 			cpu_asid_mask(&cpu_data[cpu]);
 }
 
-uint32_t kvm_mips_get_user_asid(struct kvm_vcpu *vcpu)
+static u32 kvm_mips_get_user_asid(struct kvm_vcpu *vcpu)
 {
 	int cpu = smp_processor_id();
 
@@ -63,7 +52,7 @@ uint32_t kvm_mips_get_user_asid(struct kvm_vcpu *vcpu)
 			cpu_asid_mask(&cpu_data[cpu]);
 }
 
-inline uint32_t kvm_mips_get_commpage_asid(struct kvm_vcpu *vcpu)
+inline u32 kvm_mips_get_commpage_asid(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->arch.commpage_tlb;
 }
@@ -72,50 +61,15 @@ inline uint32_t kvm_mips_get_commpage_asid(struct kvm_vcpu *vcpu)
 
 void kvm_mips_dump_host_tlbs(void)
 {
-	unsigned long old_entryhi;
-	unsigned long old_pagemask;
-	struct kvm_mips_tlb tlb;
 	unsigned long flags;
-	int i;
 
 	local_irq_save(flags);
 
-	old_entryhi = read_c0_entryhi();
-	old_pagemask = read_c0_pagemask();
-
 	kvm_info("HOST TLBs:\n");
-	kvm_info("ASID: %#lx\n", read_c0_entryhi() &
-		 cpu_asid_mask(&current_cpu_data));
-
-	for (i = 0; i < current_cpu_data.tlbsize; i++) {
-		write_c0_index(i);
-		mtc0_tlbw_hazard();
-
-		tlb_read();
-		tlbw_use_hazard();
+	dump_tlb_regs();
+	pr_info("\n");
+	dump_tlb_all();
 
-		tlb.tlb_hi = read_c0_entryhi();
-		tlb.tlb_lo0 = read_c0_entrylo0();
-		tlb.tlb_lo1 = read_c0_entrylo1();
-		tlb.tlb_mask = read_c0_pagemask();
-
-		kvm_info("TLB%c%3d Hi 0x%08lx ",
-			 (tlb.tlb_lo0 | tlb.tlb_lo1) & MIPS3_PG_V ? ' ' : '*',
-			 i, tlb.tlb_hi);
-		kvm_info("Lo0=0x%09" PRIx64 " %c%c attr %lx ",
-			 (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo0),
-			 (tlb.tlb_lo0 & MIPS3_PG_D) ? 'D' : ' ',
-			 (tlb.tlb_lo0 & MIPS3_PG_G) ? 'G' : ' ',
-			 (tlb.tlb_lo0 >> 3) & 7);
-		kvm_info("Lo1=0x%09" PRIx64 " %c%c attr %lx sz=%lx\n",
-			 (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo1),
-			 (tlb.tlb_lo1 & MIPS3_PG_D) ? 'D' : ' ',
-			 (tlb.tlb_lo1 & MIPS3_PG_G) ? 'G' : ' ',
-			 (tlb.tlb_lo1 >> 3) & 7, tlb.tlb_mask);
-	}
-	write_c0_entryhi(old_entryhi);
-	write_c0_pagemask(old_pagemask);
-	mtc0_tlbw_hazard();
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(kvm_mips_dump_host_tlbs);
@@ -132,74 +86,24 @@ void kvm_mips_dump_guest_tlbs(struct kvm_vcpu *vcpu)
 	for (i = 0; i < KVM_MIPS_GUEST_TLB_SIZE; i++) {
 		tlb = vcpu->arch.guest_tlb[i];
 		kvm_info("TLB%c%3d Hi 0x%08lx ",
-			 (tlb.tlb_lo0 | tlb.tlb_lo1) & MIPS3_PG_V ? ' ' : '*',
+			 (tlb.tlb_lo[0] | tlb.tlb_lo[1]) & ENTRYLO_V
+							? ' ' : '*',
 			 i, tlb.tlb_hi);
-		kvm_info("Lo0=0x%09" PRIx64 " %c%c attr %lx ",
-			 (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo0),
-			 (tlb.tlb_lo0 & MIPS3_PG_D) ? 'D' : ' ',
-			 (tlb.tlb_lo0 & MIPS3_PG_G) ? 'G' : ' ',
-			 (tlb.tlb_lo0 >> 3) & 7);
-		kvm_info("Lo1=0x%09" PRIx64 " %c%c attr %lx sz=%lx\n",
-			 (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo1),
-			 (tlb.tlb_lo1 & MIPS3_PG_D) ? 'D' : ' ',
-			 (tlb.tlb_lo1 & MIPS3_PG_G) ? 'G' : ' ',
-			 (tlb.tlb_lo1 >> 3) & 7, tlb.tlb_mask);
+		kvm_info("Lo0=0x%09llx %c%c attr %lx ",
+			 (u64) mips3_tlbpfn_to_paddr(tlb.tlb_lo[0]),
+			 (tlb.tlb_lo[0] & ENTRYLO_D) ? 'D' : ' ',
+			 (tlb.tlb_lo[0] & ENTRYLO_G) ? 'G' : ' ',
+			 (tlb.tlb_lo[0] & ENTRYLO_C) >> ENTRYLO_C_SHIFT);
+		kvm_info("Lo1=0x%09llx %c%c attr %lx sz=%lx\n",
+			 (u64) mips3_tlbpfn_to_paddr(tlb.tlb_lo[1]),
+			 (tlb.tlb_lo[1] & ENTRYLO_D) ? 'D' : ' ',
+			 (tlb.tlb_lo[1] & ENTRYLO_G) ? 'G' : ' ',
+			 (tlb.tlb_lo[1] & ENTRYLO_C) >> ENTRYLO_C_SHIFT,
+			 tlb.tlb_mask);
 	}
 }
 EXPORT_SYMBOL_GPL(kvm_mips_dump_guest_tlbs);
 
-static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn)
-{
-	int srcu_idx, err = 0;
-	kvm_pfn_t pfn;
-
-	if (kvm->arch.guest_pmap[gfn] != KVM_INVALID_PAGE)
-		return 0;
-
-	srcu_idx = srcu_read_lock(&kvm->srcu);
-	pfn = kvm_mips_gfn_to_pfn(kvm, gfn);
-
-	if (kvm_mips_is_error_pfn(pfn)) {
-		kvm_err("Couldn't get pfn for gfn %#" PRIx64 "!\n", gfn);
-		err = -EFAULT;
-		goto out;
-	}
-
-	kvm->arch.guest_pmap[gfn] = pfn;
-out:
-	srcu_read_unlock(&kvm->srcu, srcu_idx);
-	return err;
-}
-
-/* Translate guest KSEG0 addresses to Host PA */
-unsigned long kvm_mips_translate_guest_kseg0_to_hpa(struct kvm_vcpu *vcpu,
-						    unsigned long gva)
-{
-	gfn_t gfn;
-	uint32_t offset = gva & ~PAGE_MASK;
-	struct kvm *kvm = vcpu->kvm;
-
-	if (KVM_GUEST_KSEGX(gva) != KVM_GUEST_KSEG0) {
-		kvm_err("%s/%p: Invalid gva: %#lx\n", __func__,
-			__builtin_return_address(0), gva);
-		return KVM_INVALID_PAGE;
-	}
-
-	gfn = (KVM_GUEST_CPHYSADDR(gva) >> PAGE_SHIFT);
-
-	if (gfn >= kvm->arch.guest_pmap_npages) {
-		kvm_err("%s: Invalid gfn: %#llx, GVA: %#lx\n", __func__, gfn,
-			gva);
-		return KVM_INVALID_PAGE;
-	}
-
-	if (kvm_mips_map_page(vcpu->kvm, gfn) < 0)
-		return KVM_INVALID_ADDR;
-
-	return (kvm->arch.guest_pmap[gfn] << PAGE_SHIFT) + offset;
-}
-EXPORT_SYMBOL_GPL(kvm_mips_translate_guest_kseg0_to_hpa);
-
 /* XXXKYMA: Must be called with interrupts disabled */
 /* set flush_dcache_mask == 0 if no dcache flush required */
 int kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi,
@@ -243,12 +147,12 @@ int kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi,
 
 	/* Flush D-cache */
 	if (flush_dcache_mask) {
-		if (entrylo0 & MIPS3_PG_V) {
+		if (entrylo0 & ENTRYLO_V) {
 			++vcpu->stat.flush_dcache_exits;
 			flush_data_cache_page((entryhi & VPN2_MASK) &
 					      ~flush_dcache_mask);
 		}
-		if (entrylo1 & MIPS3_PG_V) {
+		if (entrylo1 & ENTRYLO_V) {
 			++vcpu->stat.flush_dcache_exits;
 			flush_data_cache_page(((entryhi & VPN2_MASK) &
 					       ~flush_dcache_mask) |
@@ -259,96 +163,35 @@ int kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi,
 	/* Restore old ASID */
 	write_c0_entryhi(old_entryhi);
 	mtc0_tlbw_hazard();
-	tlbw_use_hazard();
 	local_irq_restore(flags);
 	return 0;
 }
-
-/* XXXKYMA: Must be called with interrupts disabled */
-int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr,
-				    struct kvm_vcpu *vcpu)
-{
-	gfn_t gfn;
-	kvm_pfn_t pfn0, pfn1;
-	unsigned long vaddr = 0;
-	unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
-	int even;
-	struct kvm *kvm = vcpu->kvm;
-	const int flush_dcache_mask = 0;
-	int ret;
-
-	if (KVM_GUEST_KSEGX(badvaddr) != KVM_GUEST_KSEG0) {
-		kvm_err("%s: Invalid BadVaddr: %#lx\n", __func__, badvaddr);
-		kvm_mips_dump_host_tlbs();
-		return -1;
-	}
-
-	gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT);
-	if (gfn >= kvm->arch.guest_pmap_npages) {
-		kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__,
-			gfn, badvaddr);
-		kvm_mips_dump_host_tlbs();
-		return -1;
-	}
-	even = !(gfn & 0x1);
-	vaddr = badvaddr & (PAGE_MASK << 1);
-
-	if (kvm_mips_map_page(vcpu->kvm, gfn) < 0)
-		return -1;
-
-	if (kvm_mips_map_page(vcpu->kvm, gfn ^ 0x1) < 0)
-		return -1;
-
-	if (even) {
-		pfn0 = kvm->arch.guest_pmap[gfn];
-		pfn1 = kvm->arch.guest_pmap[gfn ^ 0x1];
-	} else {
-		pfn0 = kvm->arch.guest_pmap[gfn ^ 0x1];
-		pfn1 = kvm->arch.guest_pmap[gfn];
-	}
-
-	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
-		   (1 << 2) | (0x1 << 1);
-	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
-		   (1 << 2) | (0x1 << 1);
-
-	preempt_disable();
-	entryhi = (vaddr | kvm_mips_get_kernel_asid(vcpu));
-	ret = kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
-				      flush_dcache_mask);
-	preempt_enable();
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(kvm_mips_handle_kseg0_tlb_fault);
+EXPORT_SYMBOL_GPL(kvm_mips_host_tlb_write);
 
 int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr,
 	struct kvm_vcpu *vcpu)
 {
-	kvm_pfn_t pfn0, pfn1;
+	kvm_pfn_t pfn;
 	unsigned long flags, old_entryhi = 0, vaddr = 0;
-	unsigned long entrylo0 = 0, entrylo1 = 0;
+	unsigned long entrylo[2] = { 0, 0 };
+	unsigned int pair_idx;
 
-	pfn0 = CPHYSADDR(vcpu->arch.kseg0_commpage) >> PAGE_SHIFT;
-	pfn1 = 0;
-	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
-		   (1 << 2) | (0x1 << 1);
-	entrylo1 = 0;
+	pfn = PFN_DOWN(virt_to_phys(vcpu->arch.kseg0_commpage));
+	pair_idx = (badvaddr >> PAGE_SHIFT) & 1;
+	entrylo[pair_idx] = mips3_paddr_to_tlbpfn(pfn << PAGE_SHIFT) |
+		((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
+		ENTRYLO_D | ENTRYLO_V;
 
 	local_irq_save(flags);
 
 	old_entryhi = read_c0_entryhi();
 	vaddr = badvaddr & (PAGE_MASK << 1);
 	write_c0_entryhi(vaddr | kvm_mips_get_kernel_asid(vcpu));
-	mtc0_tlbw_hazard();
-	write_c0_entrylo0(entrylo0);
-	mtc0_tlbw_hazard();
-	write_c0_entrylo1(entrylo1);
-	mtc0_tlbw_hazard();
+	write_c0_entrylo0(entrylo[0]);
+	write_c0_entrylo1(entrylo[1]);
 	write_c0_index(kvm_mips_get_commpage_asid(vcpu));
 	mtc0_tlbw_hazard();
 	tlb_write_indexed();
-	mtc0_tlbw_hazard();
 	tlbw_use_hazard();
 
 	kvm_debug("@ %#lx idx: %2d [entryhi(R): %#lx] entrylo0 (R): 0x%08lx, entrylo1(R): 0x%08lx\n",
@@ -358,68 +201,12 @@ int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr,
 	/* Restore old ASID */
 	write_c0_entryhi(old_entryhi);
 	mtc0_tlbw_hazard();
-	tlbw_use_hazard();
 	local_irq_restore(flags);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_mips_handle_commpage_tlb_fault);
 
-int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
-					 struct kvm_mips_tlb *tlb,
-					 unsigned long *hpa0,
-					 unsigned long *hpa1)
-{
-	unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
-	struct kvm *kvm = vcpu->kvm;
-	kvm_pfn_t pfn0, pfn1;
-	int ret;
-
-	if ((tlb->tlb_hi & VPN2_MASK) == 0) {
-		pfn0 = 0;
-		pfn1 = 0;
-	} else {
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
-					   >> PAGE_SHIFT) < 0)
-			return -1;
-
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
-					   >> PAGE_SHIFT) < 0)
-			return -1;
-
-		pfn0 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
-					    >> PAGE_SHIFT];
-		pfn1 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
-					    >> PAGE_SHIFT];
-	}
-
-	if (hpa0)
-		*hpa0 = pfn0 << PAGE_SHIFT;
-
-	if (hpa1)
-		*hpa1 = pfn1 << PAGE_SHIFT;
-
-	/* Get attributes from the Guest TLB */
-	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
-		   (tlb->tlb_lo0 & MIPS3_PG_D) | (tlb->tlb_lo0 & MIPS3_PG_V);
-	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
-		   (tlb->tlb_lo1 & MIPS3_PG_D) | (tlb->tlb_lo1 & MIPS3_PG_V);
-
-	kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
-		  tlb->tlb_lo0, tlb->tlb_lo1);
-
-	preempt_disable();
-	entryhi = (tlb->tlb_hi & VPN2_MASK) | (KVM_GUEST_KERNEL_MODE(vcpu) ?
-					       kvm_mips_get_kernel_asid(vcpu) :
-					       kvm_mips_get_user_asid(vcpu));
-	ret = kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
-				      tlb->tlb_mask);
-	preempt_enable();
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(kvm_mips_handle_mapped_seg_tlb_fault);
-
 int kvm_mips_guest_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long entryhi)
 {
 	int i;
@@ -435,7 +222,7 @@ int kvm_mips_guest_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long entryhi)
 	}
 
 	kvm_debug("%s: entryhi: %#lx, index: %d lo0: %#lx, lo1: %#lx\n",
-		  __func__, entryhi, index, tlb[i].tlb_lo0, tlb[i].tlb_lo1);
+		  __func__, entryhi, index, tlb[i].tlb_lo[0], tlb[i].tlb_lo[1]);
 
 	return index;
 }
@@ -467,7 +254,6 @@ int kvm_mips_host_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long vaddr)
 	/* Restore old ASID */
 	write_c0_entryhi(old_entryhi);
 	mtc0_tlbw_hazard();
-	tlbw_use_hazard();
 
 	local_irq_restore(flags);
 
@@ -498,21 +284,16 @@ int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long va)
 
 	if (idx > 0) {
 		write_c0_entryhi(UNIQUE_ENTRYHI(idx));
-		mtc0_tlbw_hazard();
-
 		write_c0_entrylo0(0);
-		mtc0_tlbw_hazard();
-
 		write_c0_entrylo1(0);
 		mtc0_tlbw_hazard();
 
 		tlb_write_indexed();
-		mtc0_tlbw_hazard();
+		tlbw_use_hazard();
 	}
 
 	write_c0_entryhi(old_entryhi);
 	mtc0_tlbw_hazard();
-	tlbw_use_hazard();
 
 	local_irq_restore(flags);
 
@@ -540,61 +321,39 @@ void kvm_mips_flush_host_tlb(int skip_kseg0)
 	/* Blast 'em all away. */
 	for (entry = 0; entry < maxentry; entry++) {
 		write_c0_index(entry);
-		mtc0_tlbw_hazard();
 
 		if (skip_kseg0) {
+			mtc0_tlbr_hazard();
 			tlb_read();
-			tlbw_use_hazard();
+			tlb_read_hazard();
 
 			entryhi = read_c0_entryhi();
 
 			/* Don't blow away guest kernel entries */
 			if (KVM_GUEST_KSEGX(entryhi) == KVM_GUEST_KSEG0)
 				continue;
+
+			write_c0_pagemask(old_pagemask);
 		}
 
 		/* Make sure all entries differ. */
 		write_c0_entryhi(UNIQUE_ENTRYHI(entry));
-		mtc0_tlbw_hazard();
 		write_c0_entrylo0(0);
-		mtc0_tlbw_hazard();
 		write_c0_entrylo1(0);
 		mtc0_tlbw_hazard();
 
 		tlb_write_indexed();
-		mtc0_tlbw_hazard();
+		tlbw_use_hazard();
 	}
 
-	tlbw_use_hazard();
-
 	write_c0_entryhi(old_entryhi);
 	write_c0_pagemask(old_pagemask);
 	mtc0_tlbw_hazard();
-	tlbw_use_hazard();
 
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(kvm_mips_flush_host_tlb);
 
-void kvm_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu,
-			     struct kvm_vcpu *vcpu)
-{
-	unsigned long asid = asid_cache(cpu);
-
-	asid += cpu_asid_inc();
-	if (!(asid & cpu_asid_mask(&cpu_data[cpu]))) {
-		if (cpu_has_vtag_icache)
-			flush_icache_all();
-
-		kvm_local_flush_tlb_all();      /* start new asid cycle */
-
-		if (!asid)      /* fix version if needed */
-			asid = asid_first_version(cpu);
-	}
-
-	cpu_context(cpu, mm) = asid_cache(cpu) = asid;
-}
-
 void kvm_local_flush_tlb_all(void)
 {
 	unsigned long flags;
@@ -614,185 +373,12 @@ void kvm_local_flush_tlb_all(void)
 		write_c0_index(entry);
 		mtc0_tlbw_hazard();
 		tlb_write_indexed();
+		tlbw_use_hazard();
 		entry++;
 	}
-	tlbw_use_hazard();
 	write_c0_entryhi(old_ctx);
 	mtc0_tlbw_hazard();
 
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(kvm_local_flush_tlb_all);
-
-/**
- * kvm_mips_migrate_count() - Migrate timer.
- * @vcpu:	Virtual CPU.
- *
- * Migrate CP0_Count hrtimer to the current CPU by cancelling and restarting it
- * if it was running prior to being cancelled.
- *
- * Must be called when the VCPU is migrated to a different CPU to ensure that
- * timer expiry during guest execution interrupts the guest and causes the
- * interrupt to be delivered in a timely manner.
- */
-static void kvm_mips_migrate_count(struct kvm_vcpu *vcpu)
-{
-	if (hrtimer_cancel(&vcpu->arch.comparecount_timer))
-		hrtimer_restart(&vcpu->arch.comparecount_timer);
-}
-
-/* Restore ASID once we are scheduled back after preemption */
-void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
-{
-	unsigned long asid_mask = cpu_asid_mask(&cpu_data[cpu]);
-	unsigned long flags;
-	int newasid = 0;
-
-	kvm_debug("%s: vcpu %p, cpu: %d\n", __func__, vcpu, cpu);
-
-	/* Allocate new kernel and user ASIDs if needed */
-
-	local_irq_save(flags);
-
-	if ((vcpu->arch.guest_kernel_asid[cpu] ^ asid_cache(cpu)) &
-						asid_version_mask(cpu)) {
-		kvm_get_new_mmu_context(&vcpu->arch.guest_kernel_mm, cpu, vcpu);
-		vcpu->arch.guest_kernel_asid[cpu] =
-		    vcpu->arch.guest_kernel_mm.context.asid[cpu];
-		kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu, vcpu);
-		vcpu->arch.guest_user_asid[cpu] =
-		    vcpu->arch.guest_user_mm.context.asid[cpu];
-		newasid++;
-
-		kvm_debug("[%d]: cpu_context: %#lx\n", cpu,
-			  cpu_context(cpu, current->mm));
-		kvm_debug("[%d]: Allocated new ASID for Guest Kernel: %#x\n",
-			  cpu, vcpu->arch.guest_kernel_asid[cpu]);
-		kvm_debug("[%d]: Allocated new ASID for Guest User: %#x\n", cpu,
-			  vcpu->arch.guest_user_asid[cpu]);
-	}
-
-	if (vcpu->arch.last_sched_cpu != cpu) {
-		kvm_debug("[%d->%d]KVM VCPU[%d] switch\n",
-			  vcpu->arch.last_sched_cpu, cpu, vcpu->vcpu_id);
-		/*
-		 * Migrate the timer interrupt to the current CPU so that it
-		 * always interrupts the guest and synchronously triggers a
-		 * guest timer interrupt.
-		 */
-		kvm_mips_migrate_count(vcpu);
-	}
-
-	if (!newasid) {
-		/*
-		 * If we preempted while the guest was executing, then reload
-		 * the pre-empted ASID
-		 */
-		if (current->flags & PF_VCPU) {
-			write_c0_entryhi(vcpu->arch.
-					 preempt_entryhi & asid_mask);
-			ehb();
-		}
-	} else {
-		/* New ASIDs were allocated for the VM */
-
-		/*
-		 * Were we in guest context? If so then the pre-empted ASID is
-		 * no longer valid, we need to set it to what it should be based
-		 * on the mode of the Guest (Kernel/User)
-		 */
-		if (current->flags & PF_VCPU) {
-			if (KVM_GUEST_KERNEL_MODE(vcpu))
-				write_c0_entryhi(vcpu->arch.
-						 guest_kernel_asid[cpu] &
-						 asid_mask);
-			else
-				write_c0_entryhi(vcpu->arch.
-						 guest_user_asid[cpu] &
-						 asid_mask);
-			ehb();
-		}
-	}
-
-	/* restore guest state to registers */
-	kvm_mips_callbacks->vcpu_set_regs(vcpu);
-
-	local_irq_restore(flags);
-
-}
-EXPORT_SYMBOL_GPL(kvm_arch_vcpu_load);
-
-/* ASID can change if another task is scheduled during preemption */
-void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
-{
-	unsigned long flags;
-	uint32_t cpu;
-
-	local_irq_save(flags);
-
-	cpu = smp_processor_id();
-
-	vcpu->arch.preempt_entryhi = read_c0_entryhi();
-	vcpu->arch.last_sched_cpu = cpu;
-
-	/* save guest state in registers */
-	kvm_mips_callbacks->vcpu_get_regs(vcpu);
-
-	if (((cpu_context(cpu, current->mm) ^ asid_cache(cpu)) &
-	     asid_version_mask(cpu))) {
-		kvm_debug("%s: Dropping MMU Context:  %#lx\n", __func__,
-			  cpu_context(cpu, current->mm));
-		drop_mmu_context(current->mm, cpu);
-	}
-	write_c0_entryhi(cpu_asid(cpu, current->mm));
-	ehb();
-
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(kvm_arch_vcpu_put);
-
-uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu)
-{
-	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	unsigned long paddr, flags, vpn2, asid;
-	uint32_t inst;
-	int index;
-
-	if (KVM_GUEST_KSEGX((unsigned long) opc) < KVM_GUEST_KSEG0 ||
-	    KVM_GUEST_KSEGX((unsigned long) opc) == KVM_GUEST_KSEG23) {
-		local_irq_save(flags);
-		index = kvm_mips_host_tlb_lookup(vcpu, (unsigned long) opc);
-		if (index >= 0) {
-			inst = *(opc);
-		} else {
-			vpn2 = (unsigned long) opc & VPN2_MASK;
-			asid = kvm_read_c0_guest_entryhi(cop0) &
-						KVM_ENTRYHI_ASID;
-			index = kvm_mips_guest_tlb_lookup(vcpu, vpn2 | asid);
-			if (index < 0) {
-				kvm_err("%s: get_user_failed for %p, vcpu: %p, ASID: %#lx\n",
-					__func__, opc, vcpu, read_c0_entryhi());
-				kvm_mips_dump_host_tlbs();
-				local_irq_restore(flags);
-				return KVM_INVALID_INST;
-			}
-			kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
-							     &vcpu->arch.
-							     guest_tlb[index],
-							     NULL, NULL);
-			inst = *(opc);
-		}
-		local_irq_restore(flags);
-	} else if (KVM_GUEST_KSEGX(opc) == KVM_GUEST_KSEG0) {
-		paddr =
-		    kvm_mips_translate_guest_kseg0_to_hpa(vcpu,
-							  (unsigned long) opc);
-		inst = *(uint32_t *) CKSEG0ADDR(paddr);
-	} else {
-		kvm_err("%s: illegal address: %p\n", __func__, opc);
-		return KVM_INVALID_INST;
-	}
-
-	return inst;
-}
-EXPORT_SYMBOL_GPL(kvm_get_inst);
diff --git a/arch/mips/kvm/trace.h b/arch/mips/kvm/trace.h
index bd6437f67dc0..c858cf168078 100644
--- a/arch/mips/kvm/trace.h
+++ b/arch/mips/kvm/trace.h
@@ -17,8 +17,75 @@
 #define TRACE_INCLUDE_PATH .
 #define TRACE_INCLUDE_FILE trace
 
-/* Tracepoints for VM eists */
-extern char *kvm_mips_exit_types_str[MAX_KVM_MIPS_EXIT_TYPES];
+/*
+ * Tracepoints for VM enters
+ */
+DECLARE_EVENT_CLASS(kvm_transition,
+	TP_PROTO(struct kvm_vcpu *vcpu),
+	TP_ARGS(vcpu),
+	TP_STRUCT__entry(
+		__field(unsigned long, pc)
+	),
+
+	TP_fast_assign(
+		__entry->pc = vcpu->arch.pc;
+	),
+
+	TP_printk("PC: 0x%08lx",
+		  __entry->pc)
+);
+
+DEFINE_EVENT(kvm_transition, kvm_enter,
+	     TP_PROTO(struct kvm_vcpu *vcpu),
+	     TP_ARGS(vcpu));
+
+DEFINE_EVENT(kvm_transition, kvm_reenter,
+	     TP_PROTO(struct kvm_vcpu *vcpu),
+	     TP_ARGS(vcpu));
+
+DEFINE_EVENT(kvm_transition, kvm_out,
+	     TP_PROTO(struct kvm_vcpu *vcpu),
+	     TP_ARGS(vcpu));
+
+/* The first 32 exit reasons correspond to Cause.ExcCode */
+#define KVM_TRACE_EXIT_INT		 0
+#define KVM_TRACE_EXIT_TLBMOD		 1
+#define KVM_TRACE_EXIT_TLBMISS_LD	 2
+#define KVM_TRACE_EXIT_TLBMISS_ST	 3
+#define KVM_TRACE_EXIT_ADDRERR_LD	 4
+#define KVM_TRACE_EXIT_ADDRERR_ST	 5
+#define KVM_TRACE_EXIT_SYSCALL		 8
+#define KVM_TRACE_EXIT_BREAK_INST	 9
+#define KVM_TRACE_EXIT_RESVD_INST	10
+#define KVM_TRACE_EXIT_COP_UNUSABLE	11
+#define KVM_TRACE_EXIT_TRAP_INST	13
+#define KVM_TRACE_EXIT_MSA_FPE		14
+#define KVM_TRACE_EXIT_FPE		15
+#define KVM_TRACE_EXIT_MSA_DISABLED	21
+/* Further exit reasons */
+#define KVM_TRACE_EXIT_WAIT		32
+#define KVM_TRACE_EXIT_CACHE		33
+#define KVM_TRACE_EXIT_SIGNAL		34
+
+/* Tracepoints for VM exits */
+#define kvm_trace_symbol_exit_types				\
+	{ KVM_TRACE_EXIT_INT,		"Interrupt" },		\
+	{ KVM_TRACE_EXIT_TLBMOD,	"TLB Mod" },		\
+	{ KVM_TRACE_EXIT_TLBMISS_LD,	"TLB Miss (LD)" },	\
+	{ KVM_TRACE_EXIT_TLBMISS_ST,	"TLB Miss (ST)" },	\
+	{ KVM_TRACE_EXIT_ADDRERR_LD,	"Address Error (LD)" },	\
+	{ KVM_TRACE_EXIT_ADDRERR_ST,	"Address Err (ST)" },	\
+	{ KVM_TRACE_EXIT_SYSCALL,	"System Call" },	\
+	{ KVM_TRACE_EXIT_BREAK_INST,	"Break Inst" },		\
+	{ KVM_TRACE_EXIT_RESVD_INST,	"Reserved Inst" },	\
+	{ KVM_TRACE_EXIT_COP_UNUSABLE,	"COP0/1 Unusable" },	\
+	{ KVM_TRACE_EXIT_TRAP_INST,	"Trap Inst" },		\
+	{ KVM_TRACE_EXIT_MSA_FPE,	"MSA FPE" },		\
+	{ KVM_TRACE_EXIT_FPE,		"FPE" },		\
+	{ KVM_TRACE_EXIT_MSA_DISABLED,	"MSA Disabled" },	\
+	{ KVM_TRACE_EXIT_WAIT,		"WAIT" },		\
+	{ KVM_TRACE_EXIT_CACHE,		"CACHE" },		\
+	{ KVM_TRACE_EXIT_SIGNAL,	"Signal" }
 
 TRACE_EVENT(kvm_exit,
 	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason),
@@ -34,10 +101,173 @@ TRACE_EVENT(kvm_exit,
 	    ),
 
 	    TP_printk("[%s]PC: 0x%08lx",
-		      kvm_mips_exit_types_str[__entry->reason],
+		      __print_symbolic(__entry->reason,
+				       kvm_trace_symbol_exit_types),
 		      __entry->pc)
 );
 
+#define KVM_TRACE_MFC0		0
+#define KVM_TRACE_MTC0		1
+#define KVM_TRACE_DMFC0		2
+#define KVM_TRACE_DMTC0		3
+#define KVM_TRACE_RDHWR		4
+
+#define KVM_TRACE_HWR_COP0	0
+#define KVM_TRACE_HWR_HWR	1
+
+#define KVM_TRACE_COP0(REG, SEL)	((KVM_TRACE_HWR_COP0 << 8) |	\
+					 ((REG) << 3) | (SEL))
+#define KVM_TRACE_HWR(REG, SEL)		((KVM_TRACE_HWR_HWR  << 8) |	\
+					 ((REG) << 3) | (SEL))
+
+#define kvm_trace_symbol_hwr_ops				\
+	{ KVM_TRACE_MFC0,		"MFC0" },		\
+	{ KVM_TRACE_MTC0,		"MTC0" },		\
+	{ KVM_TRACE_DMFC0,		"DMFC0" },		\
+	{ KVM_TRACE_DMTC0,		"DMTC0" },		\
+	{ KVM_TRACE_RDHWR,		"RDHWR" }
+
+#define kvm_trace_symbol_hwr_cop				\
+	{ KVM_TRACE_HWR_COP0,		"COP0" },		\
+	{ KVM_TRACE_HWR_HWR,		"HWR" }
+
+#define kvm_trace_symbol_hwr_regs				\
+	{ KVM_TRACE_COP0( 0, 0),	"Index" },		\
+	{ KVM_TRACE_COP0( 2, 0),	"EntryLo0" },		\
+	{ KVM_TRACE_COP0( 3, 0),	"EntryLo1" },		\
+	{ KVM_TRACE_COP0( 4, 0),	"Context" },		\
+	{ KVM_TRACE_COP0( 4, 2),	"UserLocal" },		\
+	{ KVM_TRACE_COP0( 5, 0),	"PageMask" },		\
+	{ KVM_TRACE_COP0( 6, 0),	"Wired" },		\
+	{ KVM_TRACE_COP0( 7, 0),	"HWREna" },		\
+	{ KVM_TRACE_COP0( 8, 0),	"BadVAddr" },		\
+	{ KVM_TRACE_COP0( 9, 0),	"Count" },		\
+	{ KVM_TRACE_COP0(10, 0),	"EntryHi" },		\
+	{ KVM_TRACE_COP0(11, 0),	"Compare" },		\
+	{ KVM_TRACE_COP0(12, 0),	"Status" },		\
+	{ KVM_TRACE_COP0(12, 1),	"IntCtl" },		\
+	{ KVM_TRACE_COP0(12, 2),	"SRSCtl" },		\
+	{ KVM_TRACE_COP0(13, 0),	"Cause" },		\
+	{ KVM_TRACE_COP0(14, 0),	"EPC" },		\
+	{ KVM_TRACE_COP0(15, 0),	"PRId" },		\
+	{ KVM_TRACE_COP0(15, 1),	"EBase" },		\
+	{ KVM_TRACE_COP0(16, 0),	"Config" },		\
+	{ KVM_TRACE_COP0(16, 1),	"Config1" },		\
+	{ KVM_TRACE_COP0(16, 2),	"Config2" },		\
+	{ KVM_TRACE_COP0(16, 3),	"Config3" },		\
+	{ KVM_TRACE_COP0(16, 4),	"Config4" },		\
+	{ KVM_TRACE_COP0(16, 5),	"Config5" },		\
+	{ KVM_TRACE_COP0(16, 7),	"Config7" },		\
+	{ KVM_TRACE_COP0(26, 0),	"ECC" },		\
+	{ KVM_TRACE_COP0(30, 0),	"ErrorEPC" },		\
+	{ KVM_TRACE_COP0(31, 2),	"KScratch1" },		\
+	{ KVM_TRACE_COP0(31, 3),	"KScratch2" },		\
+	{ KVM_TRACE_COP0(31, 4),	"KScratch3" },		\
+	{ KVM_TRACE_COP0(31, 5),	"KScratch4" },		\
+	{ KVM_TRACE_COP0(31, 6),	"KScratch5" },		\
+	{ KVM_TRACE_COP0(31, 7),	"KScratch6" },		\
+	{ KVM_TRACE_HWR( 0, 0),		"CPUNum" },		\
+	{ KVM_TRACE_HWR( 1, 0),		"SYNCI_Step" },		\
+	{ KVM_TRACE_HWR( 2, 0),		"CC" },			\
+	{ KVM_TRACE_HWR( 3, 0),		"CCRes" },		\
+	{ KVM_TRACE_HWR(29, 0),		"ULR" }
+
+TRACE_EVENT(kvm_hwr,
+	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int op, unsigned int reg,
+		     unsigned long val),
+	    TP_ARGS(vcpu, op, reg, val),
+	    TP_STRUCT__entry(
+			__field(unsigned long, val)
+			__field(u16, reg)
+			__field(u8, op)
+	    ),
+
+	    TP_fast_assign(
+			__entry->val = val;
+			__entry->reg = reg;
+			__entry->op = op;
+	    ),
+
+	    TP_printk("%s %s (%s:%u:%u) 0x%08lx",
+		      __print_symbolic(__entry->op,
+				       kvm_trace_symbol_hwr_ops),
+		      __print_symbolic(__entry->reg,
+				       kvm_trace_symbol_hwr_regs),
+		      __print_symbolic(__entry->reg >> 8,
+				       kvm_trace_symbol_hwr_cop),
+		      (__entry->reg >> 3) & 0x1f,
+		      __entry->reg & 0x7,
+		      __entry->val)
+);
+
+#define KVM_TRACE_AUX_RESTORE		0
+#define KVM_TRACE_AUX_SAVE		1
+#define KVM_TRACE_AUX_ENABLE		2
+#define KVM_TRACE_AUX_DISABLE		3
+#define KVM_TRACE_AUX_DISCARD		4
+
+#define KVM_TRACE_AUX_FPU		1
+#define KVM_TRACE_AUX_MSA		2
+#define KVM_TRACE_AUX_FPU_MSA		3
+
+#define kvm_trace_symbol_aux_op		\
+	{ KVM_TRACE_AUX_RESTORE, "restore" },	\
+	{ KVM_TRACE_AUX_SAVE,    "save" },	\
+	{ KVM_TRACE_AUX_ENABLE,  "enable" },	\
+	{ KVM_TRACE_AUX_DISABLE, "disable" },	\
+	{ KVM_TRACE_AUX_DISCARD, "discard" }
+
+#define kvm_trace_symbol_aux_state		\
+	{ KVM_TRACE_AUX_FPU,     "FPU" },	\
+	{ KVM_TRACE_AUX_MSA,     "MSA" },	\
+	{ KVM_TRACE_AUX_FPU_MSA, "FPU & MSA" }
+
+TRACE_EVENT(kvm_aux,
+	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int op,
+		     unsigned int state),
+	    TP_ARGS(vcpu, op, state),
+	    TP_STRUCT__entry(
+			__field(unsigned long, pc)
+			__field(u8, op)
+			__field(u8, state)
+	    ),
+
+	    TP_fast_assign(
+			__entry->pc = vcpu->arch.pc;
+			__entry->op = op;
+			__entry->state = state;
+	    ),
+
+	    TP_printk("%s %s PC: 0x%08lx",
+		      __print_symbolic(__entry->op,
+				       kvm_trace_symbol_aux_op),
+		      __print_symbolic(__entry->state,
+				       kvm_trace_symbol_aux_state),
+		      __entry->pc)
+);
+
+TRACE_EVENT(kvm_asid_change,
+	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int old_asid,
+		     unsigned int new_asid),
+	    TP_ARGS(vcpu, old_asid, new_asid),
+	    TP_STRUCT__entry(
+			__field(unsigned long, pc)
+			__field(u8, old_asid)
+			__field(u8, new_asid)
+	    ),
+
+	    TP_fast_assign(
+			__entry->pc = vcpu->arch.pc;
+			__entry->old_asid = old_asid;
+			__entry->new_asid = new_asid;
+	    ),
+
+	    TP_printk("PC: 0x%08lx old: 0x%02x new: 0x%02x",
+		      __entry->pc,
+		      __entry->old_asid,
+		      __entry->new_asid)
+);
+
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c
index 6ba0fafcecbc..091553942bcb 100644
--- a/arch/mips/kvm/trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@@ -21,7 +21,7 @@
 static gpa_t kvm_trap_emul_gva_to_gpa_cb(gva_t gva)
 {
 	gpa_t gpa;
-	uint32_t kseg = KSEGX(gva);
+	gva_t kseg = KSEGX(gva);
 
 	if ((kseg == CKSEG0) || (kseg == CKSEG1))
 		gpa = CPHYSADDR(gva);
@@ -40,8 +40,8 @@ static int kvm_trap_emul_handle_cop_unusable(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -87,15 +87,15 @@ static int kvm_trap_emul_handle_cop_unusable(struct kvm_vcpu *vcpu)
 static int kvm_trap_emul_handle_tlb_mod(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
+	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
 	unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
 	if (KVM_GUEST_KSEGX(badvaddr) < KVM_GUEST_KSEG0
 	    || KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG23) {
-		kvm_debug("USER/KSEG23 ADDR TLB MOD fault: cause %#lx, PC: %p, BadVaddr: %#lx\n",
+		kvm_debug("USER/KSEG23 ADDR TLB MOD fault: cause %#x, PC: %p, BadVaddr: %#lx\n",
 			  cause, opc, badvaddr);
 		er = kvm_mips_handle_tlbmod(cause, opc, run, vcpu);
 
@@ -111,14 +111,14 @@ static int kvm_trap_emul_handle_tlb_mod(struct kvm_vcpu *vcpu)
 		 * when we are not using HIGHMEM. Need to address this in a
 		 * HIGHMEM kernel
 		 */
-		kvm_err("TLB MOD fault not handled, cause %#lx, PC: %p, BadVaddr: %#lx\n",
+		kvm_err("TLB MOD fault not handled, cause %#x, PC: %p, BadVaddr: %#lx\n",
 			cause, opc, badvaddr);
 		kvm_mips_dump_host_tlbs();
 		kvm_arch_vcpu_dump_regs(vcpu);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		ret = RESUME_HOST;
 	} else {
-		kvm_err("Illegal TLB Mod fault address , cause %#lx, PC: %p, BadVaddr: %#lx\n",
+		kvm_err("Illegal TLB Mod fault address , cause %#x, PC: %p, BadVaddr: %#lx\n",
 			cause, opc, badvaddr);
 		kvm_mips_dump_host_tlbs();
 		kvm_arch_vcpu_dump_regs(vcpu);
@@ -128,59 +128,12 @@ static int kvm_trap_emul_handle_tlb_mod(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static int kvm_trap_emul_handle_tlb_st_miss(struct kvm_vcpu *vcpu)
-{
-	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
-	unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
-	enum emulation_result er = EMULATE_DONE;
-	int ret = RESUME_GUEST;
-
-	if (((badvaddr & PAGE_MASK) == KVM_GUEST_COMMPAGE_ADDR)
-	    && KVM_GUEST_KERNEL_MODE(vcpu)) {
-		if (kvm_mips_handle_commpage_tlb_fault(badvaddr, vcpu) < 0) {
-			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-			ret = RESUME_HOST;
-		}
-	} else if (KVM_GUEST_KSEGX(badvaddr) < KVM_GUEST_KSEG0
-		   || KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG23) {
-		kvm_debug("USER ADDR TLB LD fault: cause %#lx, PC: %p, BadVaddr: %#lx\n",
-			  cause, opc, badvaddr);
-		er = kvm_mips_handle_tlbmiss(cause, opc, run, vcpu);
-		if (er == EMULATE_DONE)
-			ret = RESUME_GUEST;
-		else {
-			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-			ret = RESUME_HOST;
-		}
-	} else if (KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG0) {
-		/*
-		 * All KSEG0 faults are handled by KVM, as the guest kernel does
-		 * not expect to ever get them
-		 */
-		if (kvm_mips_handle_kseg0_tlb_fault
-		    (vcpu->arch.host_cp0_badvaddr, vcpu) < 0) {
-			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-			ret = RESUME_HOST;
-		}
-	} else {
-		kvm_err("Illegal TLB LD fault address , cause %#lx, PC: %p, BadVaddr: %#lx\n",
-			cause, opc, badvaddr);
-		kvm_mips_dump_host_tlbs();
-		kvm_arch_vcpu_dump_regs(vcpu);
-		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		ret = RESUME_HOST;
-	}
-	return ret;
-}
-
-static int kvm_trap_emul_handle_tlb_ld_miss(struct kvm_vcpu *vcpu)
+static int kvm_trap_emul_handle_tlb_miss(struct kvm_vcpu *vcpu, bool store)
 {
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
+	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
 	unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -192,8 +145,8 @@ static int kvm_trap_emul_handle_tlb_ld_miss(struct kvm_vcpu *vcpu)
 		}
 	} else if (KVM_GUEST_KSEGX(badvaddr) < KVM_GUEST_KSEG0
 		   || KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG23) {
-		kvm_debug("USER ADDR TLB ST fault: PC: %#lx, BadVaddr: %#lx\n",
-			  vcpu->arch.pc, badvaddr);
+		kvm_debug("USER ADDR TLB %s fault: cause %#x, PC: %p, BadVaddr: %#lx\n",
+			  store ? "ST" : "LD", cause, opc, badvaddr);
 
 		/*
 		 * User Address (UA) fault, this could happen if
@@ -213,14 +166,18 @@ static int kvm_trap_emul_handle_tlb_ld_miss(struct kvm_vcpu *vcpu)
 			ret = RESUME_HOST;
 		}
 	} else if (KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG0) {
+		/*
+		 * All KSEG0 faults are handled by KVM, as the guest kernel does
+		 * not expect to ever get them
+		 */
 		if (kvm_mips_handle_kseg0_tlb_fault
 		    (vcpu->arch.host_cp0_badvaddr, vcpu) < 0) {
 			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 			ret = RESUME_HOST;
 		}
 	} else {
-		kvm_err("Illegal TLB ST fault address , cause %#lx, PC: %p, BadVaddr: %#lx\n",
-			cause, opc, badvaddr);
+		kvm_err("Illegal TLB %s fault address , cause %#x, PC: %p, BadVaddr: %#lx\n",
+			store ? "ST" : "LD", cause, opc, badvaddr);
 		kvm_mips_dump_host_tlbs();
 		kvm_arch_vcpu_dump_regs(vcpu);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
@@ -229,12 +186,22 @@ static int kvm_trap_emul_handle_tlb_ld_miss(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+static int kvm_trap_emul_handle_tlb_st_miss(struct kvm_vcpu *vcpu)
+{
+	return kvm_trap_emul_handle_tlb_miss(vcpu, true);
+}
+
+static int kvm_trap_emul_handle_tlb_ld_miss(struct kvm_vcpu *vcpu)
+{
+	return kvm_trap_emul_handle_tlb_miss(vcpu, false);
+}
+
 static int kvm_trap_emul_handle_addr_err_st(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
+	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
 	unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -251,7 +218,7 @@ static int kvm_trap_emul_handle_addr_err_st(struct kvm_vcpu *vcpu)
 			ret = RESUME_HOST;
 		}
 	} else {
-		kvm_err("Address Error (STORE): cause %#lx, PC: %p, BadVaddr: %#lx\n",
+		kvm_err("Address Error (STORE): cause %#x, PC: %p, BadVaddr: %#lx\n",
 			cause, opc, badvaddr);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		ret = RESUME_HOST;
@@ -262,9 +229,9 @@ static int kvm_trap_emul_handle_addr_err_st(struct kvm_vcpu *vcpu)
 static int kvm_trap_emul_handle_addr_err_ld(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
+	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
 	unsigned long badvaddr = vcpu->arch.host_cp0_badvaddr;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -280,7 +247,7 @@ static int kvm_trap_emul_handle_addr_err_ld(struct kvm_vcpu *vcpu)
 			ret = RESUME_HOST;
 		}
 	} else {
-		kvm_err("Address Error (LOAD): cause %#lx, PC: %p, BadVaddr: %#lx\n",
+		kvm_err("Address Error (LOAD): cause %#x, PC: %p, BadVaddr: %#lx\n",
 			cause, opc, badvaddr);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		ret = RESUME_HOST;
@@ -292,8 +259,8 @@ static int kvm_trap_emul_handle_addr_err_ld(struct kvm_vcpu *vcpu)
 static int kvm_trap_emul_handle_syscall(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -310,8 +277,8 @@ static int kvm_trap_emul_handle_syscall(struct kvm_vcpu *vcpu)
 static int kvm_trap_emul_handle_res_inst(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -328,8 +295,8 @@ static int kvm_trap_emul_handle_res_inst(struct kvm_vcpu *vcpu)
 static int kvm_trap_emul_handle_break(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -346,8 +313,8 @@ static int kvm_trap_emul_handle_break(struct kvm_vcpu *vcpu)
 static int kvm_trap_emul_handle_trap(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 __user *opc = (u32 __user *)vcpu->arch.pc;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -364,8 +331,8 @@ static int kvm_trap_emul_handle_trap(struct kvm_vcpu *vcpu)
 static int kvm_trap_emul_handle_msa_fpe(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 __user *opc = (u32 __user *)vcpu->arch.pc;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -382,8 +349,8 @@ static int kvm_trap_emul_handle_msa_fpe(struct kvm_vcpu *vcpu)
 static int kvm_trap_emul_handle_fpe(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 __user *opc = (u32 __user *)vcpu->arch.pc;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -407,8 +374,8 @@ static int kvm_trap_emul_handle_msa_disabled(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_run *run = vcpu->run;
-	uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc;
-	unsigned long cause = vcpu->arch.host_cp0_cause;
+	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
+	u32 cause = vcpu->arch.host_cp0_cause;
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
@@ -451,24 +418,41 @@ static int kvm_trap_emul_vm_init(struct kvm *kvm)
 
 static int kvm_trap_emul_vcpu_init(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.kscratch_enabled = 0xfc;
+
 	return 0;
 }
 
 static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	uint32_t config1;
+	u32 config, config1;
 	int vcpu_id = vcpu->vcpu_id;
 
 	/*
 	 * Arch specific stuff, set up config registers properly so that the
-	 * guest will come up as expected, for now we simulate a MIPS 24kc
+	 * guest will come up as expected
 	 */
+#ifndef CONFIG_CPU_MIPSR6
+	/* r2-r5, simulate a MIPS 24kc */
 	kvm_write_c0_guest_prid(cop0, 0x00019300);
-	/* Have config1, Cacheable, noncoherent, write-back, write allocate */
-	kvm_write_c0_guest_config(cop0, MIPS_CONF_M | (0x3 << CP0C0_K0) |
-				  (0x1 << CP0C0_AR) |
-				  (MMU_TYPE_R4000 << CP0C0_MT));
+#else
+	/* r6+, simulate a generic QEMU machine */
+	kvm_write_c0_guest_prid(cop0, 0x00010000);
+#endif
+	/*
+	 * Have config1, Cacheable, noncoherent, write-back, write allocate.
+	 * Endianness, arch revision & virtually tagged icache should match
+	 * host.
+	 */
+	config = read_c0_config() & MIPS_CONF_AR;
+	config |= MIPS_CONF_M | CONF_CM_CACHABLE_NONCOHERENT | MIPS_CONF_MT_TLB;
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	config |= CONF_BE;
+#endif
+	if (cpu_has_vtag_icache)
+		config |= MIPS_CONF_VI;
+	kvm_write_c0_guest_config(cop0, config);
 
 	/* Read the cache characteristics from the host Config1 Register */
 	config1 = (read_c0_config1() & ~0x7f);
@@ -478,9 +462,8 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu)
 	config1 |= ((KVM_MIPS_GUEST_TLB_SIZE - 1) << 25);
 
 	/* We unset some bits that we aren't emulating */
-	config1 &=
-	    ~((1 << CP0C1_C2) | (1 << CP0C1_MD) | (1 << CP0C1_PC) |
-	      (1 << CP0C1_WR) | (1 << CP0C1_CA));
+	config1 &= ~(MIPS_CONF1_C2 | MIPS_CONF1_MD | MIPS_CONF1_PC |
+		     MIPS_CONF1_WR | MIPS_CONF1_CA);
 	kvm_write_c0_guest_config1(cop0, config1);
 
 	/* Have config3, no tertiary/secondary caches implemented */
@@ -511,6 +494,17 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static unsigned long kvm_trap_emul_num_regs(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+static int kvm_trap_emul_copy_reg_indices(struct kvm_vcpu *vcpu,
+					  u64 __user *indices)
+{
+	return 0;
+}
+
 static int kvm_trap_emul_get_one_reg(struct kvm_vcpu *vcpu,
 				     const struct kvm_one_reg *reg,
 				     s64 *v)
@@ -660,6 +654,8 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = {
 	.dequeue_io_int = kvm_mips_dequeue_io_int_cb,
 	.irq_deliver = kvm_mips_irq_deliver_cb,
 	.irq_clear = kvm_mips_irq_clear_cb,
+	.num_regs = kvm_trap_emul_num_regs,
+	.copy_reg_indices = kvm_trap_emul_copy_reg_indices,
 	.get_one_reg = kvm_trap_emul_get_one_reg,
 	.set_one_reg = kvm_trap_emul_set_one_reg,
 	.vcpu_get_regs = kvm_trap_emul_vcpu_get_regs,
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index d96e912b9d44..6dc07fba187f 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -627,8 +627,8 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 				dec_insn.pc_inc +
 				dec_insn.next_pc_inc;
 		return 1;
-	case cbcond0_op:
-	case cbcond1_op:
+	case pop10_op:
+	case pop30_op:
 		if (!cpu_has_mips_r6)
 			break;
 		if (insn.i_format.rt && !insn.i_format.rs)
@@ -683,14 +683,14 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 			dec_insn.next_pc_inc;
 
 		return 1;
-	case beqzcjic_op:
+	case pop66_op:
 		if (!cpu_has_mips_r6)
 			break;
 		*contpc = regs->cp0_epc + dec_insn.pc_inc +
 			dec_insn.next_pc_inc;
 
 		return 1;
-	case bnezcjialc_op:
+	case pop76_op:
 		if (!cpu_has_mips_r6)
 			break;
 		if (!insn.i_format.rs)
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index ef7f925dd1b0..7a9c345e87e5 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1206,7 +1206,7 @@ static void probe_pcache(void)
 			      c->icache.linesz;
 		c->icache.waybit = __ffs(icache_size/c->icache.ways);
 
-		if (config & 0x8)		/* VI bit */
+		if (config & MIPS_CONF_VI)
 			c->icache.flags |= MIPS_CACHE_VTAG;
 
 		/*
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 9b58eb5fd0d5..a5509e7dcad2 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -504,7 +504,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 
 void (*free_init_pages_eva)(void *begin, void *end) = NULL;
 
-void __init_refok free_initmem(void)
+void __ref free_initmem(void)
 {
 	prom_free_prom_memory();
 	/*
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index d78178daea4b..277cf52d80e1 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -53,8 +53,13 @@ static struct insn insn_table_MM[] = {
 	{ insn_bltzl, 0, 0 },
 	{ insn_bne, M(mm_bne32_op, 0, 0, 0, 0, 0), RT | RS | BIMM },
 	{ insn_cache, M(mm_pool32b_op, 0, 0, mm_cache_func, 0, 0), RT | RS | SIMM },
+	{ insn_cfc1, M(mm_pool32f_op, 0, 0, 0, mm_cfc1_op, mm_32f_73_op), RT | RS },
+	{ insn_cfcmsa, M(mm_pool32s_op, 0, msa_cfc_op, 0, 0, mm_32s_elm_op), RD | RE },
+	{ insn_ctc1, M(mm_pool32f_op, 0, 0, 0, mm_ctc1_op, mm_32f_73_op), RT | RS },
+	{ insn_ctcmsa, M(mm_pool32s_op, 0, msa_ctc_op, 0, 0, mm_32s_elm_op), RD | RE },
 	{ insn_daddu, 0, 0 },
 	{ insn_daddiu, 0, 0 },
+	{ insn_di, M(mm_pool32a_op, 0, 0, 0, mm_di_op, mm_pool32axf_op), RS },
 	{ insn_divu, M(mm_pool32a_op, 0, 0, 0, mm_divu_op, mm_pool32axf_op), RT | RS },
 	{ insn_dmfc0, 0, 0 },
 	{ insn_dmtc0, 0, 0 },
@@ -84,6 +89,8 @@ static struct insn insn_table_MM[] = {
 	{ insn_mfhi, M(mm_pool32a_op, 0, 0, 0, mm_mfhi32_op, mm_pool32axf_op), RS },
 	{ insn_mflo, M(mm_pool32a_op, 0, 0, 0, mm_mflo32_op, mm_pool32axf_op), RS },
 	{ insn_mtc0, M(mm_pool32a_op, 0, 0, 0, mm_mtc0_op, mm_pool32axf_op), RT | RS | RD },
+	{ insn_mthi, M(mm_pool32a_op, 0, 0, 0, mm_mthi32_op, mm_pool32axf_op), RS },
+	{ insn_mtlo, M(mm_pool32a_op, 0, 0, 0, mm_mtlo32_op, mm_pool32axf_op), RS },
 	{ insn_mul, M(mm_pool32a_op, 0, 0, 0, 0, mm_mul_op), RT | RS | RD },
 	{ insn_or, M(mm_pool32a_op, 0, 0, 0, 0, mm_or32_op), RT | RS | RD },
 	{ insn_ori, M(mm_ori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM },
@@ -166,13 +173,15 @@ static void build_insn(u32 **buf, enum opcode opc, ...)
 	op = ip->match;
 	va_start(ap, opc);
 	if (ip->fields & RS) {
-		if (opc == insn_mfc0 || opc == insn_mtc0)
+		if (opc == insn_mfc0 || opc == insn_mtc0 ||
+		    opc == insn_cfc1 || opc == insn_ctc1)
 			op |= build_rt(va_arg(ap, u32));
 		else
 			op |= build_rs(va_arg(ap, u32));
 	}
 	if (ip->fields & RT) {
-		if (opc == insn_mfc0 || opc == insn_mtc0)
+		if (opc == insn_mfc0 || opc == insn_mtc0 ||
+		    opc == insn_cfc1 || opc == insn_ctc1)
 			op |= build_rs(va_arg(ap, u32));
 		else
 			op |= build_rt(va_arg(ap, u32));
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 9c2220a45189..cec524167822 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -67,9 +67,14 @@ static struct insn insn_table[] = {
 #else
 	{ insn_cache,  M6(cache_op, 0, 0, 0, cache6_op),  RS | RT | SIMM9 },
 #endif
+	{ insn_cfc1, M(cop1_op, cfc_op, 0, 0, 0, 0), RT | RD },
+	{ insn_cfcmsa, M(msa_op, 0, msa_cfc_op, 0, 0, msa_elm_op), RD | RE },
+	{ insn_ctc1, M(cop1_op, ctc_op, 0, 0, 0, 0), RT | RD },
+	{ insn_ctcmsa, M(msa_op, 0, msa_ctc_op, 0, 0, msa_elm_op), RD | RE },
 	{ insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
 	{ insn_dinsm, M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE },
+	{ insn_di, M(cop0_op, mfmc0_op, 0, 12, 0, 0), RT },
 	{ insn_dins, M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE },
 	{ insn_divu, M(spec_op, 0, 0, 0, 0, divu_op), RS | RT },
 	{ insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET},
@@ -114,7 +119,13 @@ static struct insn insn_table[] = {
 	{ insn_mflo,  M(spec_op, 0, 0, 0, 0, mflo_op), RD },
 	{ insn_mtc0,  M(cop0_op, mtc_op, 0, 0, 0, 0),  RT | RD | SET},
 	{ insn_mthc0,  M(cop0_op, mthc0_op, 0, 0, 0, 0),  RT | RD | SET},
+	{ insn_mthi,  M(spec_op, 0, 0, 0, 0, mthi_op), RS },
+	{ insn_mtlo,  M(spec_op, 0, 0, 0, 0, mtlo_op), RS },
+#ifndef CONFIG_CPU_MIPSR6
 	{ insn_mul, M(spec2_op, 0, 0, 0, 0, mul_op), RS | RT | RD},
+#else
+	{ insn_mul, M(spec_op, 0, 0, 0, mult_mul_op, mult_op), RS | RT | RD},
+#endif
 	{ insn_ori,  M(ori_op, 0, 0, 0, 0, 0),	RS | RT | UIMM },
 	{ insn_or,  M(spec_op, 0, 0, 0, 0, or_op),  RS | RT | RD },
 #ifndef CONFIG_CPU_MIPSR6
diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c
index ad718debc35a..3e0282d301d6 100644
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@@ -49,18 +49,19 @@ enum opcode {
 	insn_invalid,
 	insn_addiu, insn_addu, insn_and, insn_andi, insn_bbit0, insn_bbit1,
 	insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl,
-	insn_bne, insn_cache, insn_daddiu, insn_daddu, insn_dins, insn_dinsm,
-	insn_divu, insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll,
+	insn_bne, insn_cache, insn_cfc1, insn_cfcmsa, insn_ctc1, insn_ctcmsa,
+	insn_daddiu, insn_daddu, insn_di, insn_dins, insn_dinsm, insn_divu,
+	insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll,
 	insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32, insn_dsubu, insn_eret,
 	insn_ext, insn_ins, insn_j, insn_jal, insn_jalr, insn_jr, insn_lb,
 	insn_ld, insn_ldx, insn_lh, insn_ll, insn_lld, insn_lui, insn_lw,
 	insn_lwx, insn_mfc0, insn_mfhc0, insn_mfhi, insn_mflo, insn_mtc0,
-	insn_mthc0, insn_mul, insn_or, insn_ori, insn_pref, insn_rfe,
-	insn_rotr, insn_sc, insn_scd, insn_sd, insn_sll, insn_sllv, insn_slt,
-	insn_sltiu, insn_sltu, insn_sra, insn_srl, insn_srlv, insn_subu,
-	insn_sw, insn_sync, insn_syscall, insn_tlbp, insn_tlbr, insn_tlbwi,
-	insn_tlbwr, insn_wait, insn_wsbh, insn_xor, insn_xori, insn_yield,
-	insn_lddir, insn_ldpte,
+	insn_mthc0, insn_mthi, insn_mtlo, insn_mul, insn_or, insn_ori,
+	insn_pref, insn_rfe, insn_rotr, insn_sc, insn_scd, insn_sd, insn_sll,
+	insn_sllv, insn_slt, insn_sltiu, insn_sltu, insn_sra, insn_srl,
+	insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall, insn_tlbp,
+	insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh, insn_xor,
+	insn_xori, insn_yield, insn_lddir, insn_ldpte,
 };
 
 struct insn {
@@ -268,10 +269,15 @@ I_u1s2(_bltz)
 I_u1s2(_bltzl)
 I_u1u2s3(_bne)
 I_u2s3u1(_cache)
+I_u1u2(_cfc1)
+I_u2u1(_cfcmsa)
+I_u1u2(_ctc1)
+I_u2u1(_ctcmsa)
 I_u1u2u3(_dmfc0)
 I_u1u2u3(_dmtc0)
 I_u2u1s3(_daddiu)
 I_u3u1u2(_daddu)
+I_u1(_di);
 I_u1u2(_divu)
 I_u2u1u3(_dsll)
 I_u2u1u3(_dsll32)
@@ -301,6 +307,8 @@ I_u1(_mfhi)
 I_u1(_mflo)
 I_u1u2u3(_mtc0)
 I_u1u2u3(_mthc0)
+I_u1(_mthi)
+I_u1(_mtlo)
 I_u3u1u2(_mul)
 I_u2u1u3(_ori)
 I_u3u1u2(_or)
diff --git a/arch/mips/mti-sead3/sead3-setup.c b/arch/mips/mti-sead3/sead3-setup.c
index 9f2f9b2b23ce..edfcaf06680d 100644
--- a/arch/mips/mti-sead3/sead3-setup.c
+++ b/arch/mips/mti-sead3/sead3-setup.c
@@ -8,7 +8,6 @@
  */
 #include <linux/init.h>
 #include <linux/libfdt.h>
-#include <linux/of_platform.h>
 #include <linux/of_fdt.h>
 
 #include <asm/prom.h>
@@ -107,10 +106,3 @@ void __init device_tree_init(void)
 
 	unflatten_and_copy_device_tree();
 }
-
-static int __init customize_machine(void)
-{
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-	return 0;
-}
-arch_initcall(customize_machine);
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index f1b11f0dea2d..b4c02f29663e 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -112,7 +112,14 @@ static void pcibios_scanbus(struct pci_controller *hose)
 		need_domain_info = 1;
 	}
 
-	if (!pci_has_flag(PCI_PROBE_ONLY)) {
+	/*
+	 * We insert PCI resources into the iomem_resource and
+	 * ioport_resource trees in either pci_bus_claim_resources()
+	 * or pci_bus_assign_resources().
+	 */
+	if (pci_has_flag(PCI_PROBE_ONLY)) {
+		pci_bus_claim_resources(bus);
+	} else {
 		pci_bus_size_bridges(bus);
 		pci_bus_assign_resources(bus);
 	}
@@ -319,6 +326,16 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 EXPORT_SYMBOL(PCIBIOS_MIN_IO);
 EXPORT_SYMBOL(PCIBIOS_MIN_MEM);
 
+void pci_resource_to_user(const struct pci_dev *dev, int bar,
+			  const struct resource *rsrc, resource_size_t *start,
+			  resource_size_t *end)
+{
+	phys_addr_t size = resource_size(rsrc);
+
+	*start = fixup_bigphys_addr(rsrc->start, size);
+	*end = rsrc->start + size;
+}
+
 int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
diff --git a/arch/mips/pic32/pic32mzda/init.c b/arch/mips/pic32/pic32mzda/init.c
index 775ff90a9962..77ecf32ef3dc 100644
--- a/arch/mips/pic32/pic32mzda/init.c
+++ b/arch/mips/pic32/pic32mzda/init.c
@@ -147,8 +147,7 @@ static int __init plat_of_setup(void)
 		panic("Device tree not present");
 
 	pic32_of_prepare_platform_data(pic32_auxdata_lookup);
-	if (of_platform_populate(NULL, of_default_bus_match_table,
-				 pic32_auxdata_lookup, NULL))
+	if (of_platform_default_populate(NULL, pic32_auxdata_lookup, NULL))
 		panic("Failed to populate DT");
 
 	return 0;
diff --git a/arch/mips/pistachio/init.c b/arch/mips/pistachio/init.c
index ab79828230ab..c50a670e60d2 100644
--- a/arch/mips/pistachio/init.c
+++ b/arch/mips/pistachio/init.c
@@ -14,7 +14,6 @@
 #include <linux/kernel.h>
 #include <linux/of_address.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 
 #include <asm/cacheflush.h>
 #include <asm/dma-coherence.h>
@@ -159,15 +158,3 @@ void __init device_tree_init(void)
 
 	unflatten_and_copy_device_tree();
 }
-
-static int __init plat_of_setup(void)
-{
-	if (!of_have_populated_dt())
-		panic("Device tree not present");
-
-	if (of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL))
-		panic("Failed to populate DT");
-
-	return 0;
-}
-arch_initcall(plat_of_setup);
diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c
index a77698ff2b6f..1f6bc9a3036c 100644
--- a/arch/mips/txx9/generic/pci.c
+++ b/arch/mips/txx9/generic/pci.c
@@ -268,7 +268,7 @@ static int txx9_i8259_irq_setup(int irq)
 	return err;
 }
 
-static void __init_refok quirk_slc90e66_bridge(struct pci_dev *dev)
+static void __ref quirk_slc90e66_bridge(struct pci_dev *dev)
 {
 	int irq;	/* PCI/ISA Bridge interrupt */
 	u8 reg_64;
diff --git a/arch/mips/xilfpga/init.c b/arch/mips/xilfpga/init.c
index ce2aee2169ac..602e384a26a2 100644
--- a/arch/mips/xilfpga/init.c
+++ b/arch/mips/xilfpga/init.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 
 #include <asm/prom.h>
 
@@ -43,15 +42,3 @@ void __init device_tree_init(void)
 
 	unflatten_and_copy_device_tree();
 }
-
-static int __init plat_of_setup(void)
-{
-	if (!of_have_populated_dt())
-		panic("Device tree not present");
-
-	if (of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL))
-		panic("Failed to populate DT");
-
-	return 0;
-}
-arch_initcall(plat_of_setup);
diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c
index e75c75d249d6..c92fe4234009 100644
--- a/arch/nios2/mm/init.c
+++ b/arch/nios2/mm/init.c
@@ -89,7 +89,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
-void __init_refok free_initmem(void)
+void __ref free_initmem(void)
 {
 	free_initmem_default(-1);
 }
diff --git a/arch/nios2/platform/platform.c b/arch/nios2/platform/platform.c
index d478773f758a..2a35154ca153 100644
--- a/arch/nios2/platform/platform.c
+++ b/arch/nios2/platform/platform.c
@@ -9,7 +9,6 @@
  */
 
 #include <linux/init.h>
-#include <linux/of_platform.h>
 #include <linux/of_address.h>
 #include <linux/of_fdt.h>
 #include <linux/err.h>
@@ -39,8 +38,7 @@ static int __init nios2_soc_device_init(void)
 		}
 	}
 
-	return of_platform_populate(NULL, of_default_bus_match_table,
-		NULL, NULL);
+	return 0;
 }
 
 device_initcall(nios2_soc_device_init);
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index 5b2a95116e8f..fa60b81aee3e 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -38,7 +38,7 @@ static unsigned int fixmaps_used __initdata;
  * have to convert them into an offset in a page-aligned mapping, but the
  * caller shouldn't need to know that small detail.
  */
-void __iomem *__init_refok
+void __iomem *__ref
 __ioremap(phys_addr_t addr, unsigned long size, pgprot_t prot)
 {
 	phys_addr_t p;
@@ -116,7 +116,7 @@ void iounmap(void *addr)
  * the memblock infrastructure.
  */
 
-pte_t __init_refok *pte_alloc_one_kernel(struct mm_struct *mm,
+pte_t __ref *pte_alloc_one_kernel(struct mm_struct *mm,
 					 unsigned long address)
 {
 	pte_t *pte;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d111044f41a2..ec4047e170a0 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -127,7 +127,8 @@ config PPC
 	select IRQ_FORCED_THREADING
 	select HAVE_RCU_TABLE_FREE if SMP
 	select HAVE_SYSCALL_TRACEPOINTS
-	select HAVE_CBPF_JIT if CPU_BIG_ENDIAN
+	select HAVE_CBPF_JIT if !PPC64
+	select HAVE_EBPF_JIT if PPC64
 	select HAVE_ARCH_JUMP_LABEL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_HAS_GCOV_PROFILE_ALL
@@ -163,6 +164,8 @@ config PPC
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select GENERIC_CPU_AUTOPROBE
+	select HAVE_VIRT_CPU_ACCOUNTING
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
@@ -456,6 +459,29 @@ config KEXEC
 	  interface is strongly in flux, so no good recommendation can be
 	  made.
 
+config RELOCATABLE
+	bool "Build a relocatable kernel"
+	depends on (PPC64 && !COMPILE_TEST) || (FLATMEM && (44x || FSL_BOOKE))
+	select NONSTATIC_KERNEL
+	help
+	  This builds a kernel image that is capable of running at the
+	  location the kernel is loaded at. For ppc32, there is no any
+	  alignment restrictions, and this feature is a superset of
+	  DYNAMIC_MEMSTART and hence overrides it. For ppc64, we should use
+	  16k-aligned base address. The kernel is linked as a
+	  position-independent executable (PIE) and contains dynamic relocations
+	  which are processed early in the bootup process.
+
+	  One use is for the kexec on panic case where the recovery kernel
+	  must live at a different physical address than the primary
+	  kernel.
+
+	  Note: If CONFIG_RELOCATABLE=y, then the kernel runs from the address
+	  it has been loaded at and the compile time physical addresses
+	  CONFIG_PHYSICAL_START is ignored.  However CONFIG_PHYSICAL_START
+	  setting can still be useful to bootwrappers that need to know the
+	  load address of the kernel (eg. u-boot/mkimage).
+
 config CRASH_DUMP
 	bool "Build a kdump crash kernel"
 	depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP)
@@ -948,29 +974,6 @@ config DYNAMIC_MEMSTART
 
 	  This option is overridden by CONFIG_RELOCATABLE
 
-config RELOCATABLE
-	bool "Build a relocatable kernel"
-	depends on ADVANCED_OPTIONS && FLATMEM && (44x || FSL_BOOKE)
-	select NONSTATIC_KERNEL
-	help
-	  This builds a kernel image that is capable of running at the
-	  location the kernel is loaded at, without any alignment restrictions.
-	  This feature is a superset of DYNAMIC_MEMSTART and hence overrides it.
-
-	  One use is for the kexec on panic case where the recovery kernel
-	  must live at a different physical address than the primary
-	  kernel.
-
-	  Note: If CONFIG_RELOCATABLE=y, then the kernel runs from the address
-	  it has been loaded at and the compile time physical addresses
-	  CONFIG_PHYSICAL_START is ignored.  However CONFIG_PHYSICAL_START
-	  setting can still be useful to bootwrappers that need to know the
-	  load address of the kernel (eg. u-boot/mkimage).
-
-config RELOCATABLE_PPC32
-	def_bool y
-	depends on PPC32 && RELOCATABLE
-
 config PAGE_OFFSET_BOOL
 	bool "Set custom page offset address"
 	depends on ADVANCED_OPTIONS
@@ -1053,24 +1056,14 @@ config CONSISTENT_SIZE
 config PIN_TLB
 	bool "Pinned Kernel TLBs (860 ONLY)"
 	depends on ADVANCED_OPTIONS && 8xx
+
+config PIN_TLB_IMMR
+	bool "Pinned TLB for IMMR"
+	depends on PIN_TLB
+	default y
 endmenu
 
 if PPC64
-config RELOCATABLE
-	bool "Build a relocatable kernel"
-	depends on !COMPILE_TEST
-	select NONSTATIC_KERNEL
-	help
-	  This builds a kernel image that is capable of running anywhere
-	  in the RMA (real memory area) at any 16k-aligned base address.
-	  The kernel is linked as a position-independent executable (PIE)
-	  and contains dynamic relocations which are processed early
-	  in the bootup process.
-
-	  One use is for the kexec on panic case where the recovery kernel
-	  must live at a different physical address than the primary
-	  kernel.
-
 # This value must have zeroes in the bottom 60 bits otherwise lots will break
 config PAGE_OFFSET
 	hex
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index d3fcf7e64e3a..171047822b56 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -149,14 +149,14 @@ config PPC_EARLY_DEBUG_BOOTX
 
 config PPC_EARLY_DEBUG_LPAR
 	bool "LPAR HV Console"
-	depends on PPC_PSERIES
+	depends on PPC_PSERIES && HVC_CONSOLE
 	help
 	  Select this to enable early debugging for a machine with a HVC
 	  console on vterm 0.
 
 config PPC_EARLY_DEBUG_LPAR_HVSI
 	bool "LPAR HVSI Console"
-	depends on PPC_PSERIES
+	depends on PPC_PSERIES && HVC_CONSOLE
 	help
 	  Select this to enable early debugging for a machine with a HVSI
 	  console on a specified vterm.
@@ -212,7 +212,6 @@ config PPC_EARLY_DEBUG_40x
 config PPC_EARLY_DEBUG_CPM
 	bool "Early serial debugging for Freescale CPM-based serial ports"
 	depends on SERIAL_CPM
-	select PIN_TLB if PPC_8xx
 	help
 	  Select this to enable early debugging for Freescale chips
 	  using a CPM-based serial port.  This assumes that the bootwrapper
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 709a22a3e824..ca254546cd05 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -181,6 +181,11 @@ KBUILD_CFLAGS	+= -pipe -Iarch/$(ARCH) $(CFLAGS-y)
 CPP		= $(CC) -E $(KBUILD_CFLAGS)
 
 CHECKFLAGS	+= -m$(CONFIG_WORD_SIZE) -D__powerpc__ -D__powerpc$(CONFIG_WORD_SIZE)__
+ifdef CONFIG_CPU_BIG_ENDIAN
+CHECKFLAGS	+= -D__BIG_ENDIAN__
+else
+CHECKFLAGS	+= -D__LITTLE_ENDIAN__
+endif
 
 KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
 
@@ -221,7 +226,7 @@ KBUILD_CFLAGS		+= -mno-sched-epilog
 endif
 
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
-cpu-as-$(CONFIG_ALTIVEC)	+= -Wa,-maltivec
+cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
 
 KBUILD_AFLAGS += $(cpu-as-y)
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 8fe78a3efc92..1a2a6e8dc40d 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -43,7 +43,7 @@ ifeq ($(call cc-option-yn, -fstack-protector),y)
 BOOTCFLAGS	+= -fno-stack-protector
 endif
 
-BOOTCFLAGS	+= -I$(obj) -I$(srctree)/$(obj)
+BOOTCFLAGS	+= -I$(objtree)/$(obj) -I$(srctree)/$(obj)
 
 DTC_FLAGS	?= -p 1024
 
@@ -70,7 +70,7 @@ $(addprefix $(obj)/,$(zlib) cuboot-c2k.o gunzip_util.o main.o): \
 libfdt       := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c
 libfdtheader := fdt.h libfdt.h libfdt_internal.h
 
-$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o): \
+$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o): \
 	$(addprefix $(obj)/,$(libfdtheader))
 
 src-wlib-y := string.S crt0.S crtsavres.S stdio.c main.c \
@@ -78,7 +78,7 @@ src-wlib-y := string.S crt0.S crtsavres.S stdio.c main.c \
 		ns16550.c serial.c simple_alloc.c div64.S util.S \
 		gunzip_util.c elf_util.c $(zlib) devtree.c stdlib.c \
 		oflib.c ofconsole.c cuboot.c mpsc.c cpm-serial.c \
-		uartlite.c mpc52xx-psc.c
+		uartlite.c mpc52xx-psc.c opal.c opal-calls.S
 src-wlib-$(CONFIG_40x) += 4xx.c planetcore.c
 src-wlib-$(CONFIG_44x) += 4xx.c ebony.c bamboo.c
 src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c fsl-soc.c
@@ -113,6 +113,7 @@ src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c
 src-plat-$(CONFIG_PPC_PSERIES) += pseries-head.S
 src-plat-$(CONFIG_PPC_POWERNV) += pseries-head.S
 src-plat-$(CONFIG_PPC_IBM_CELL_BLADE) += pseries-head.S
+src-plat-$(CONFIG_MVME7100) += motload-head.S mvme7100.c
 
 src-wlib := $(sort $(src-wlib-y))
 src-plat := $(sort $(src-plat-y))
@@ -296,6 +297,9 @@ image-$(CONFIG_TQM8560)			+= cuImage.tqm8560
 image-$(CONFIG_SBC8548)			+= cuImage.sbc8548
 image-$(CONFIG_KSI8560)			+= cuImage.ksi8560
 
+# Board ports in arch/powerpc/platform/86xx/Kconfig
+image-$(CONFIG_MVME7100)                += dtbImage.mvme7100
+
 # Board ports in arch/powerpc/platform/embedded6xx/Kconfig
 image-$(CONFIG_STORCENTER)		+= cuImage.storcenter
 image-$(CONFIG_MPC7448HPC2)		+= cuImage.mpc7448hpc2
diff --git a/arch/powerpc/boot/dts/ac14xx.dts b/arch/powerpc/boot/dts/ac14xx.dts
index a1b883730b31..27fcabc2f857 100644
--- a/arch/powerpc/boot/dts/ac14xx.dts
+++ b/arch/powerpc/boot/dts/ac14xx.dts
@@ -231,7 +231,7 @@
 			};
 
 			rtc@68 {
-				compatible = "stm,m41t00";
+				compatible = "st,m41t00";
 				reg = <0x68>;
 			};
 		};
diff --git a/arch/powerpc/boot/dts/akebono.dts b/arch/powerpc/boot/dts/akebono.dts
index f92ecfed3d2f..e61d5dc598c1 100644
--- a/arch/powerpc/boot/dts/akebono.dts
+++ b/arch/powerpc/boot/dts/akebono.dts
@@ -224,7 +224,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				rtc@68 {
-					compatible = "stm,m41t80", "m41st85";
+					compatible = "st,m41t80", "m41st85";
 					reg = <0x68>;
 				};
 			};
diff --git a/arch/powerpc/boot/dts/bluestone.dts b/arch/powerpc/boot/dts/bluestone.dts
index 7daaca324c01..b0b26d8d68a2 100644
--- a/arch/powerpc/boot/dts/bluestone.dts
+++ b/arch/powerpc/boot/dts/bluestone.dts
@@ -279,7 +279,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				rtc@68 {
-					compatible = "stm,m41t80";
+					compatible = "st,m41t80";
 					reg = <0x68>;
 					interrupt-parent = <&UIC0>;
 					interrupts = <0x9 0x8>;
diff --git a/arch/powerpc/boot/dts/canyonlands.dts b/arch/powerpc/boot/dts/canyonlands.dts
index 549c24c4c388..0d6ac92d0f5e 100644
--- a/arch/powerpc/boot/dts/canyonlands.dts
+++ b/arch/powerpc/boot/dts/canyonlands.dts
@@ -319,7 +319,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
                                 rtc@68 {
-                                        compatible = "stm,m41t80";
+                                        compatible = "st,m41t80";
                                         reg = <0x68>;
 					interrupt-parent = <&UIC2>;
 					interrupts = <0x19 0x8>;
diff --git a/arch/powerpc/boot/dts/currituck.dts b/arch/powerpc/boot/dts/currituck.dts
index d2c8a872308e..4191e1850ea1 100644
--- a/arch/powerpc/boot/dts/currituck.dts
+++ b/arch/powerpc/boot/dts/currituck.dts
@@ -116,7 +116,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
                                 rtc@68 {
-                                        compatible = "stm,m41t80", "m41st85";
+                                        compatible = "st,m41t80", "m41st85";
                                         reg = <0x68>;
                                 };
 			};
diff --git a/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi
index bc3bf9333dde..88d8423f8ac5 100644
--- a/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi
@@ -51,6 +51,7 @@
 		serial2 = &serial2;
 		serial3 = &serial3;
 		pci0 = &pci0;
+		usb0 = &usb0;
 		dma0 = &dma0;
 		dma1 = &dma1;
 		sdhc = &sdhc;
diff --git a/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi
index 8797ce146512..f3f968c51f4b 100644
--- a/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi
@@ -51,6 +51,7 @@
 		serial2 = &serial2;
 		serial3 = &serial3;
 		pci0 = &pci0;
+		usb0 = &usb0;
 		dma0 = &dma0;
 		dma1 = &dma1;
 		sdhc = &sdhc;
diff --git a/arch/powerpc/boot/dts/fsl/kmcoge4.dts b/arch/powerpc/boot/dts/fsl/kmcoge4.dts
index 2d4b64fcee88..ae70a24094b0 100644
--- a/arch/powerpc/boot/dts/fsl/kmcoge4.dts
+++ b/arch/powerpc/boot/dts/fsl/kmcoge4.dts
@@ -106,6 +106,43 @@
 		sata@221000 {
 			status = "disabled";
 		};
+
+		fman0: fman@400000 {
+			enet0: ethernet@e0000 {
+				phy-connection-type = "sgmii";
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+				};
+			};
+			mdio0: mdio@e1120 {
+				front_phy: ethernet-phy@11 {
+					reg = <0x11>;
+				};
+			};
+
+			enet1: ethernet@e2000 {
+				phy-connection-type = "sgmii";
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+				};
+			};
+			enet2: ethernet@e4000 {
+				status = "disabled";
+			};
+
+			enet3: ethernet@e6000 {
+				status = "disabled";
+			};
+			enet4: ethernet@e8000 {
+				phy-handle = <&front_phy>;
+				phy-connection-type = "rgmii";
+			};
+			enet5: ethernet@f0000 {
+				status = "disabled";
+			};
+		};
 	};
 
 	rio: rapidio@ffe0c0000 {
diff --git a/arch/powerpc/boot/dts/fsl/mpc8569mds.dts b/arch/powerpc/boot/dts/fsl/mpc8569mds.dts
index a95ff7d2392c..8e94448f296c 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8569mds.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8569mds.dts
@@ -232,7 +232,7 @@
 			mode = "cpu-qe";
 
 			serial-flash@0 {
-				compatible = "stm,m25p40";
+				compatible = "st,m25p40";
 				reg = <0>;
 				spi-max-frequency = <25000000>;
 			};
diff --git a/arch/powerpc/boot/dts/fsl/mvme7100.dts b/arch/powerpc/boot/dts/fsl/mvme7100.dts
new file mode 100644
index 000000000000..e2d306ad37a6
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/mvme7100.dts
@@ -0,0 +1,153 @@
+/*
+ * Device tree source for the Emerson/Artesyn MVME7100
+ *
+ * Copyright 2016 Elettra-Sincrotrone Trieste S.C.p.A.
+ *
+ * Author: Alessio Igor Bogani <alessio.bogani@elettra.eu>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ */
+
+/include/ "mpc8641si-pre.dtsi"
+
+/ {
+	model = "MVME7100";
+	compatible = "artesyn,MVME7100";
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x80000000>;
+	};
+
+	soc: soc@f1000000 {
+		ranges = <0x00000000 0xf1000000 0x00100000>;
+
+		i2c@3000 {
+			hwmon@4c {
+				compatible = "dallas,max6649";
+				reg = <0x4c>;
+			};
+
+			rtc@68 {
+				status = "disabled";
+			};
+		};
+
+
+		enet0: ethernet@24000 {
+			phy-handle = <&phy0>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		mdio@24520 {
+			phy0: ethernet-phy@1 {
+				reg = <1>;
+			};
+			phy1: ethernet-phy@2 {
+				reg = <2>;
+			};
+			phy2: ethernet-phy@3 {
+				reg = <3>;
+			};
+			phy3: ethernet-phy@4 {
+				reg = <4>;
+			};
+		};
+
+		enet1: ethernet@25000 {
+			phy-handle = <&phy1>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		mdio@25520 {
+			status = "disabled";
+		};
+
+		enet2: ethernet@26000 {
+			phy-handle = <&phy2>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		mdio@26520 {
+			status = "disabled";
+		};
+
+		enet3: ethernet@27000 {
+			phy-handle = <&phy3>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		mdio@27520 {
+			status = "disabled";
+		};
+
+		serial1: serial@4600 {
+			status = "disabled";
+		};
+	};
+
+	lbc: localbus@f1005000 {
+		reg = <0xf1005000 0x1000>;
+
+		ranges = <0 0 0xf8000000 0x08000000	// NOR Flash (128MB)
+			  2 0 0xf2030000 0x00010000	// NAND Flash (8GB)
+			  3 0 0xf2400000 0x00080000	// MRAM (512KB)
+			  4 0 0xf2000000 0x00010000	// BCSR
+			  5 0 0xf2010000 0x00010000>;	// QUART
+
+		bcsr@4,0 {
+			compatible = "artesyn,mvme7100-bcsr";
+			reg = <4 0 0x10000>;
+		};
+
+		serial@5,1000 {
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <5 0x1000 0x100>;
+			clock-frequency = <1843200>;
+			interrupts = <11 1 0 0>;
+		};
+
+		serial@5,2000 {
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <5 0x2000 0x100>;
+			clock-frequency = <1843200>;
+			interrupts = <11 1 0 0>;
+		};
+
+		serial@5,3000 {
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <5 0x3000 0x100>;
+			clock-frequency = <1843200>;
+			interrupts = <11 1 0 0>;
+		};
+
+		serial@5,4000 {
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <5 0x4000 0x100>;
+			clock-frequency = <1843200>;
+			interrupts = <11 1 0 0>;
+		};
+	};
+
+	pci0: pcie@f1008000 {
+		status = "disabled";
+	};
+
+	pci1: pcie@f1009000 {
+		status = "disabled";
+	};
+
+	chosen {
+		linux,stdout-path = &serial0;
+	};
+};
+
+/include/ "mpc8641si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1022rdk.dts b/arch/powerpc/boot/dts/fsl/p1022rdk.dts
index d505d7c51903..29e8af1e3711 100644
--- a/arch/powerpc/boot/dts/fsl/p1022rdk.dts
+++ b/arch/powerpc/boot/dts/fsl/p1022rdk.dts
@@ -57,7 +57,7 @@
 				clock-frequency = <12288000>;
 			};
 			rtc@68 {
-				compatible = "stm,m41t62";
+				compatible = "st,m41t62";
 				reg = <0x68>;
 			};
 			adt7461@4c{
diff --git a/arch/powerpc/boot/dts/fsl/qonverge-usb2-dr-0.dtsi b/arch/powerpc/boot/dts/fsl/qonverge-usb2-dr-0.dtsi
index 29dad723091e..fcc7e5b7fd47 100644
--- a/arch/powerpc/boot/dts/fsl/qonverge-usb2-dr-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qonverge-usb2-dr-0.dtsi
@@ -32,7 +32,7 @@
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-usb@210000 {
+usb0: usb@210000 {
 	compatible = "fsl-usb2-dr";
 	reg = <0x210000 0x1000>;
 	#address-cells = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
index 507649ece0a1..44e399b17f6f 100644
--- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -607,7 +607,7 @@
 /include/ "qoriq-gpio-3.dtsi"
 /include/ "qoriq-usb2-mph-0.dtsi"
 		usb0: usb@210000 {
-			compatible = "fsl-usb2-mph-v2.4", "fsl-usb2-mph";
+			compatible = "fsl-usb2-mph-v2.5", "fsl-usb2-mph";
 			fsl,iommu-parent = <&pamu0>;
 			fsl,liodn-reg = <&guts 0x520>; /* USB1LIODNR */
 			phy_type = "utmi";
@@ -615,7 +615,7 @@
 		};
 /include/ "qoriq-usb2-dr-0.dtsi"
 		usb1: usb@211000 {
-			compatible = "fsl-usb2-dr-v2.4", "fsl-usb2-dr";
+			compatible = "fsl-usb2-dr-v2.5", "fsl-usb2-dr";
 			fsl,iommu-parent = <&pamu0>;
 			fsl,liodn-reg = <&guts 0x524>; /* USB2LIODNR */
 			dr_mode = "host";
@@ -673,3 +673,48 @@
 		};
 	};
 };
+
+&qe {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	device_type = "qe";
+	compatible = "fsl,qe";
+	fsl,qe-num-riscs = <1>;
+	fsl,qe-num-snums = <28>;
+
+	qeic: interrupt-controller@80 {
+		interrupt-controller;
+		compatible = "fsl,qe-ic";
+		#address-cells = <0>;
+		#interrupt-cells = <1>;
+		reg = <0x80 0x80>;
+		interrupts = <95 2 0 0  94 2 0 0>; //high:79 low:78
+	};
+
+	ucc@2000 {
+		cell-index = <1>;
+		reg = <0x2000 0x200>;
+		interrupts = <32>;
+		interrupt-parent = <&qeic>;
+	};
+
+	ucc@2200 {
+		cell-index = <3>;
+		reg = <0x2200 0x200>;
+		interrupts = <34>;
+		interrupt-parent = <&qeic>;
+	};
+
+	muram@10000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "fsl,qe-muram", "fsl,cpm-muram";
+		ranges = <0x0 0x10000 0x6000>;
+
+		data-only@0 {
+			compatible = "fsl,qe-muram-data",
+			"fsl,cpm-muram-data";
+			reg = <0x0 0x6000>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/t104xd4rdb.dtsi b/arch/powerpc/boot/dts/fsl/t104xd4rdb.dtsi
index 8c7ea6c05de9..863f9431285f 100644
--- a/arch/powerpc/boot/dts/fsl/t104xd4rdb.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t104xd4rdb.dtsi
@@ -212,4 +212,42 @@
 				  0 0x00010000>;
 		};
 	};
+
+	qe: qe@ffe140000 {
+		ranges = <0x0 0xf 0xfe140000 0x40000>;
+		reg = <0xf 0xfe140000 0 0x480>;
+		brg-frequency = <0>;
+		bus-frequency = <0>;
+
+		si1: si@700 {
+			compatible = "fsl,t1040-qe-si";
+			reg = <0x700 0x80>;
+		};
+
+		siram1: siram@1000 {
+			compatible = "fsl,t1040-qe-siram";
+			reg = <0x1000 0x800>;
+		};
+
+		ucc_hdlc: ucc@2000 {
+			compatible = "fsl,ucc-hdlc";
+			rx-clock-name = "clk8";
+			tx-clock-name = "clk9";
+			fsl,rx-sync-clock = "rsync_pin";
+			fsl,tx-sync-clock = "tsync_pin";
+			fsl,tx-timeslot-mask = <0xfffffffe>;
+			fsl,rx-timeslot-mask = <0xfffffffe>;
+			fsl,tdm-framer-type = "e1";
+			fsl,tdm-id = <0>;
+			fsl,siram-entry-id = <0>;
+			fsl,tdm-interface;
+		};
+
+		ucc_serial: ucc@2200 {
+			compatible = "fsl,t1040-ucc-uart";
+			port-number = <0>;
+			rx-clock-name = "brg2";
+			tx-clock-name = "brg2";
+		};
+	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/t104xqds.dtsi b/arch/powerpc/boot/dts/fsl/t104xqds.dtsi
index 977af355b388..2fd4cbe7098f 100644
--- a/arch/powerpc/boot/dts/fsl/t104xqds.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t104xqds.dtsi
@@ -366,4 +366,42 @@
 				  0 0x00010000>;
 		};
 	};
+
+	qe: qe@ffe140000 {
+		ranges = <0x0 0xf 0xfe140000 0x40000>;
+		reg = <0xf 0xfe140000 0 0x480>;
+		brg-frequency = <0>;
+		bus-frequency = <0>;
+
+		si1: si@700 {
+			compatible = "fsl,t1040-qe-si";
+			reg = <0x700 0x80>;
+		};
+
+		siram1: siram@1000 {
+			compatible = "fsl,t1040-qe-siram";
+			reg = <0x1000 0x800>;
+		};
+
+		ucc_hdlc: ucc@2000 {
+			compatible = "fsl,ucc-hdlc";
+			rx-clock-name = "clk8";
+			tx-clock-name = "clk9";
+			fsl,rx-sync-clock = "rsync_pin";
+			fsl,tx-sync-clock = "tsync_pin";
+			fsl,tx-timeslot-mask = <0xfffffffe>;
+			fsl,rx-timeslot-mask = <0xfffffffe>;
+			fsl,tdm-framer-type = "e1";
+			fsl,tdm-id = <0>;
+			fsl,siram-entry-id = <0>;
+			fsl,tdm-interface;
+		};
+
+		ucc_serial: ucc@2200 {
+			compatible = "fsl,t1040-ucc-uart";
+			port-number = <0>;
+			rx-clock-name = "brg2";
+			tx-clock-name = "brg2";
+		};
+	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi b/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
index 7c4afdb44b46..5fdddbd2a62b 100644
--- a/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
@@ -222,4 +222,42 @@
 				  0 0x00010000>;
 		};
 	};
+
+	qe: qe@ffe140000 {
+		ranges = <0x0 0xf 0xfe140000 0x40000>;
+		reg = <0xf 0xfe140000 0 0x480>;
+		brg-frequency = <0>;
+		bus-frequency = <0>;
+
+		si1: si@700 {
+			compatible = "fsl,t1040-qe-si";
+			reg = <0x700 0x80>;
+		};
+
+		siram1: siram@1000 {
+			compatible = "fsl,t1040-qe-siram";
+			reg = <0x1000 0x800>;
+		};
+
+		ucc_hdlc: ucc@2000 {
+			compatible = "fsl,ucc-hdlc";
+			rx-clock-name = "clk8";
+			tx-clock-name = "clk9";
+			fsl,rx-sync-clock = "rsync_pin";
+			fsl,tx-sync-clock = "tsync_pin";
+			fsl,tx-timeslot-mask = <0xfffffffe>;
+			fsl,rx-timeslot-mask = <0xfffffffe>;
+			fsl,tdm-framer-type = "e1";
+			fsl,tdm-id = <0>;
+			fsl,siram-entry-id = <0>;
+			fsl,tdm-interface;
+		};
+
+		ucc_serial: ucc@2200 {
+			compatible = "fsl,t1040-ucc-uart";
+			port-number = <0>;
+			rx-clock-name = "brg2";
+			tx-clock-name = "brg2";
+		};
+	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi
index 1184a746fcb1..038cf8fadee4 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi
@@ -56,6 +56,8 @@
 		pci1 = &pci1;
 		pci2 = &pci2;
 		pci3 = &pci3;
+		usb0 = &usb0;
+		usb1 = &usb1;
 		dma0 = &dma0;
 		dma1 = &dma1;
 		dma2 = &dma2;
diff --git a/arch/powerpc/boot/dts/glacier.dts b/arch/powerpc/boot/dts/glacier.dts
index 2000060386d7..a7a802f4ffdd 100644
--- a/arch/powerpc/boot/dts/glacier.dts
+++ b/arch/powerpc/boot/dts/glacier.dts
@@ -287,7 +287,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				rtc@68 {
-					compatible = "stm,m41t80";
+					compatible = "st,m41t80";
 					reg = <0x68>;
 					interrupt-parent = <&UIC2>;
 					interrupts = <0x19 0x8>;
diff --git a/arch/powerpc/boot/dts/icon.dts b/arch/powerpc/boot/dts/icon.dts
index abcd0caeccae..9c94fd737f7c 100644
--- a/arch/powerpc/boot/dts/icon.dts
+++ b/arch/powerpc/boot/dts/icon.dts
@@ -256,7 +256,7 @@
 				#size-cells = <0>;
 
                                 rtc@68 {
-                                        compatible = "stm,m41t00";
+                                        compatible = "st,m41t00";
                                         reg = <0x68>;
                                 };
 			};
diff --git a/arch/powerpc/boot/dts/mpc5121ads.dts b/arch/powerpc/boot/dts/mpc5121ads.dts
index c228a0a232a6..75888ce2c792 100644
--- a/arch/powerpc/boot/dts/mpc5121ads.dts
+++ b/arch/powerpc/boot/dts/mpc5121ads.dts
@@ -99,7 +99,7 @@
 			};
 
 			rtc@68 {
-				compatible = "stm,m41t62";
+				compatible = "st,m41t62";
 				reg = <0x68>;
 			};
 		};
diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts
index cf8542401a3c..90aed3ac2f69 100644
--- a/arch/powerpc/boot/dts/mpc8349emitx.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitx.dts
@@ -92,7 +92,7 @@
 			dfsrr;
 
 			eeprom: at24@50 {
-				compatible = "st-micro,24c256";
+				compatible = "st,24c256";
 				reg = <0x50>;
 			};
 
diff --git a/arch/powerpc/boot/dts/mpc836x_rdk.dts b/arch/powerpc/boot/dts/mpc836x_rdk.dts
index daeacbdcf8b4..47c5fc64e433 100644
--- a/arch/powerpc/boot/dts/mpc836x_rdk.dts
+++ b/arch/powerpc/boot/dts/mpc836x_rdk.dts
@@ -416,7 +416,7 @@
 			gpios = <&qe_pio_e 18 0>;
 
 			flash {
-				compatible = "stm,nand512-a";
+				compatible = "st,nand512-a";
 			};
 		};
 
diff --git a/arch/powerpc/boot/dts/pdm360ng.dts b/arch/powerpc/boot/dts/pdm360ng.dts
index 871c16d1ad5e..0cec7244abe7 100644
--- a/arch/powerpc/boot/dts/pdm360ng.dts
+++ b/arch/powerpc/boot/dts/pdm360ng.dts
@@ -103,7 +103,7 @@
 			};
 
 			rtc@68 {
-				compatible = "stm,m41t00";
+				compatible = "st,m41t00";
 				reg = <0x68>;
 			};
 		};
diff --git a/arch/powerpc/boot/dts/sam440ep.dts b/arch/powerpc/boot/dts/sam440ep.dts
index f0663be10421..088361cf4636 100644
--- a/arch/powerpc/boot/dts/sam440ep.dts
+++ b/arch/powerpc/boot/dts/sam440ep.dts
@@ -196,7 +196,7 @@
 				interrupt-parent = <&UIC0>;
 				interrupts = <2 4>;
 				rtc@68 {
-					compatible = "stm,m41t80";
+					compatible = "st,m41t80";
 					reg = <0x68>;
 				};
 			};
diff --git a/arch/powerpc/boot/dts/xcalibur1501.dts b/arch/powerpc/boot/dts/xcalibur1501.dts
index c409cbafb126..1f2952dce77d 100644
--- a/arch/powerpc/boot/dts/xcalibur1501.dts
+++ b/arch/powerpc/boot/dts/xcalibur1501.dts
@@ -238,7 +238,7 @@
 			};
 
 			rtc@68 {
-				compatible = "stm,m41t00",
+				compatible = "st,m41t00",
 				             "dallas,ds1338";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/dts/xpedite5200.dts b/arch/powerpc/boot/dts/xpedite5200.dts
index 8fd7b7031357..5b10e56a1d8e 100644
--- a/arch/powerpc/boot/dts/xpedite5200.dts
+++ b/arch/powerpc/boot/dts/xpedite5200.dts
@@ -130,7 +130,7 @@
 			};
 
 			rtc@68 {
-				compatible = "stm,m41t00",
+				compatible = "st,m41t00",
 					     "dallas,ds1338";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/dts/xpedite5200_xmon.dts b/arch/powerpc/boot/dts/xpedite5200_xmon.dts
index 0baa8283d08c..646acfbef0dd 100644
--- a/arch/powerpc/boot/dts/xpedite5200_xmon.dts
+++ b/arch/powerpc/boot/dts/xpedite5200_xmon.dts
@@ -134,7 +134,7 @@
 			};
 
 			rtc@68 {
-				compatible = "stm,m41t00",
+				compatible = "st,m41t00",
 					     "dallas,ds1338";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/dts/xpedite5301.dts b/arch/powerpc/boot/dts/xpedite5301.dts
index 04cb410da48b..7bcc94ffe53d 100644
--- a/arch/powerpc/boot/dts/xpedite5301.dts
+++ b/arch/powerpc/boot/dts/xpedite5301.dts
@@ -231,7 +231,7 @@
 			};
 
 			rtc@68 {
-				compatible = "stm,m41t00",
+				compatible = "st,m41t00",
 				             "dallas,ds1338";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/dts/xpedite5330.dts b/arch/powerpc/boot/dts/xpedite5330.dts
index 73f8620f1ce7..86df8bc6ebbd 100644
--- a/arch/powerpc/boot/dts/xpedite5330.dts
+++ b/arch/powerpc/boot/dts/xpedite5330.dts
@@ -267,7 +267,7 @@
 			};
 
 			rtc@68 {
-				compatible = "stm,m41t00",
+				compatible = "st,m41t00",
 				             "dallas,ds1338";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/dts/xpedite5370.dts b/arch/powerpc/boot/dts/xpedite5370.dts
index cd0ea2b99362..b8ade094f932 100644
--- a/arch/powerpc/boot/dts/xpedite5370.dts
+++ b/arch/powerpc/boot/dts/xpedite5370.dts
@@ -229,7 +229,7 @@
 			};
 
 			rtc@68 {
-				compatible = "stm,m41t00",
+				compatible = "st,m41t00",
 				             "dallas,ds1338";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/motload-head.S b/arch/powerpc/boot/motload-head.S
new file mode 100644
index 000000000000..41cabb4b63fa
--- /dev/null
+++ b/arch/powerpc/boot/motload-head.S
@@ -0,0 +1,11 @@
+#include "ppc_asm.h"
+
+	.text
+	.globl _zimage_start
+_zimage_start:
+	mfmsr   r10
+	rlwinm  r10,r10,0,~(1<<15)        /* Clear MSR_EE */
+	sync
+	mtmsr   r10
+	isync
+	b	_zimage_start_lib
diff --git a/arch/powerpc/boot/mvme7100.c b/arch/powerpc/boot/mvme7100.c
new file mode 100644
index 000000000000..8b0a932311af
--- /dev/null
+++ b/arch/powerpc/boot/mvme7100.c
@@ -0,0 +1,59 @@
+/*
+ * Motload compatibility for the Emerson/Artesyn MVME7100
+ *
+ * Copyright 2016 Elettra-Sincrotrone Trieste S.C.p.A.
+ *
+ * Author: Alessio Igor Bogani <alessio.bogani@elettra.eu>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ */
+
+#include "ops.h"
+#include "stdio.h"
+#include "cuboot.h"
+
+#define TARGET_86xx
+#define TARGET_HAS_ETH1
+#define TARGET_HAS_ETH2
+#define TARGET_HAS_ETH3
+#include "ppcboot.h"
+
+static bd_t bd;
+
+BSS_STACK(16384);
+
+static void mvme7100_fixups(void)
+{
+	void *devp;
+	unsigned long busfreq = bd.bi_busfreq * 1000000;
+
+	dt_fixup_cpu_clocks(bd.bi_intfreq * 1000000, busfreq / 4, busfreq);
+
+	devp = finddevice("/soc@f1000000");
+	if (devp)
+		setprop(devp, "bus-frequency", &busfreq, sizeof(busfreq));
+
+	devp = finddevice("/soc/serial@4500");
+	if (devp)
+		setprop(devp, "clock-frequency", &busfreq, sizeof(busfreq));
+
+	dt_fixup_memory(bd.bi_memstart, bd.bi_memsize);
+
+	dt_fixup_mac_address_by_alias("ethernet0", bd.bi_enetaddr);
+	dt_fixup_mac_address_by_alias("ethernet1", bd.bi_enet1addr);
+	dt_fixup_mac_address_by_alias("ethernet2", bd.bi_enet2addr);
+	dt_fixup_mac_address_by_alias("ethernet3", bd.bi_enet3addr);
+}
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+		   unsigned long r6, unsigned long r7)
+{
+	CUBOOT_INIT();
+	fdt_init(_dtb_start);
+	serial_console_init();
+	platform_ops.fixups = mvme7100_fixups;
+}
diff --git a/arch/powerpc/boot/opal-calls.S b/arch/powerpc/boot/opal-calls.S
new file mode 100644
index 000000000000..ff2f1b97bc53
--- /dev/null
+++ b/arch/powerpc/boot/opal-calls.S
@@ -0,0 +1,58 @@
+/*
+ * Copyright (c) 2016 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include "ppc_asm.h"
+#include "../include/asm/opal-api.h"
+
+	.text
+
+#define OPAL_CALL(name, token)				\
+	.globl name;					\
+name:							\
+	li	r0, token;				\
+	b	opal_call;
+
+opal_call:
+	mflr	r11
+	std	r11,16(r1)
+	mfcr	r12
+	stw	r12,8(r1)
+	mr	r13,r2
+
+	/* Set opal return address */
+	ld	r11,opal_return@got(r2)
+	mtlr	r11
+	mfmsr	r12
+
+	/* switch to BE when we enter OPAL */
+	li	r11,MSR_LE
+	andc	r12,r12,r11
+	mtspr	SPRN_HSRR1,r12
+
+	/* load the opal call entry point and base */
+	ld	r11,opal@got(r2)
+	ld	r12,8(r11)
+	ld	r2,0(r11)
+	mtspr	SPRN_HSRR0,r12
+	hrfid
+
+opal_return:
+	FIXUP_ENDIAN
+	mr	r2,r13;
+	lwz	r11,8(r1);
+	ld	r12,16(r1)
+	mtcr	r11;
+	mtlr	r12
+	blr
+
+OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
+OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
+OPAL_CALL(opal_console_write_buffer_space,	OPAL_CONSOLE_WRITE_BUFFER_SPACE);
+OPAL_CALL(opal_poll_events,			OPAL_POLL_EVENTS);
+OPAL_CALL(opal_console_flush,			OPAL_CONSOLE_FLUSH);
diff --git a/arch/powerpc/boot/opal.c b/arch/powerpc/boot/opal.c
new file mode 100644
index 000000000000..1f37e1c1d6d8
--- /dev/null
+++ b/arch/powerpc/boot/opal.c
@@ -0,0 +1,98 @@
+/*
+ * Copyright (c) 2016 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include "ops.h"
+#include "stdio.h"
+#include "io.h"
+#include <libfdt.h>
+#include "../include/asm/opal-api.h"
+
+#ifdef __powerpc64__
+
+/* Global OPAL struct used by opal-call.S */
+struct opal {
+	u64 base;
+	u64 entry;
+} opal;
+
+static u32 opal_con_id;
+
+int64_t opal_console_write(int64_t term_number, u64 *length, const u8 *buffer);
+int64_t opal_console_read(int64_t term_number, uint64_t *length, u8 *buffer);
+int64_t opal_console_write_buffer_space(uint64_t term_number, uint64_t *length);
+int64_t opal_console_flush(uint64_t term_number);
+int64_t opal_poll_events(uint64_t *outstanding_event_mask);
+
+static int opal_con_open(void)
+{
+	return 0;
+}
+
+static void opal_con_putc(unsigned char c)
+{
+	int64_t rc;
+	uint64_t olen, len;
+
+	do {
+		rc = opal_console_write_buffer_space(opal_con_id, &olen);
+		len = be64_to_cpu(olen);
+		if (rc)
+			return;
+		opal_poll_events(NULL);
+	} while (len < 1);
+
+
+	olen = cpu_to_be64(1);
+	opal_console_write(opal_con_id, &olen, &c);
+}
+
+static void opal_con_close(void)
+{
+	opal_console_flush(opal_con_id);
+}
+
+static void opal_init(void)
+{
+	void *opal_node;
+
+	opal_node = finddevice("/ibm,opal");
+	if (!opal_node)
+		return;
+	if (getprop(opal_node, "opal-base-address", &opal.base, sizeof(u64)) < 0)
+		return;
+	opal.base = be64_to_cpu(opal.base);
+	if (getprop(opal_node, "opal-entry-address", &opal.entry, sizeof(u64)) < 0)
+		return;
+	opal.entry = be64_to_cpu(opal.entry);
+}
+
+int opal_console_init(void *devp, struct serial_console_data *scdp)
+{
+	opal_init();
+
+	if (devp) {
+		int n = getprop(devp, "reg", &opal_con_id, sizeof(u32));
+		if (n != sizeof(u32))
+			return -1;
+		opal_con_id = be32_to_cpu(opal_con_id);
+	} else
+		opal_con_id = 0;
+
+	scdp->open = opal_con_open;
+	scdp->putc = opal_con_putc;
+	scdp->close = opal_con_close;
+
+	return 0;
+}
+#else
+int opal_console_init(void *devp, struct serial_console_data *scdp)
+{
+	return -1;
+}
+#endif /* __powerpc64__ */
diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h
index 5e75e1c5518e..e19b64ef977a 100644
--- a/arch/powerpc/boot/ops.h
+++ b/arch/powerpc/boot/ops.h
@@ -89,6 +89,7 @@ int mpsc_console_init(void *devp, struct serial_console_data *scdp);
 int cpm_console_init(void *devp, struct serial_console_data *scdp);
 int mpc5200_psc_console_init(void *devp, struct serial_console_data *scdp);
 int uartlite_console_init(void *devp, struct serial_console_data *scdp);
+int opal_console_init(void *devp, struct serial_console_data *scdp);
 void *simple_alloc_init(char *base, unsigned long heap_size,
 			unsigned long granularity, unsigned long max_allocs);
 extern void flush_cache(void *, unsigned long);
diff --git a/arch/powerpc/boot/ppc_asm.h b/arch/powerpc/boot/ppc_asm.h
index 35ea60c1f070..b03373d8b386 100644
--- a/arch/powerpc/boot/ppc_asm.h
+++ b/arch/powerpc/boot/ppc_asm.h
@@ -61,6 +61,10 @@
 
 #define SPRN_TBRL	268
 #define SPRN_TBRU	269
+#define SPRN_HSRR0	0x13A	/* Hypervisor Save/Restore 0 */
+#define SPRN_HSRR1	0x13B	/* Hypervisor Save/Restore 1 */
+
+#define MSR_LE		0x0000000000000001
 
 #define FIXUP_ENDIAN						   \
 	tdi   0, 0, 0x48; /* Reverse endian of b . + 8		*/ \
diff --git a/arch/powerpc/boot/ppcboot.h b/arch/powerpc/boot/ppcboot.h
index 6ae6f9063952..453df429d5d0 100644
--- a/arch/powerpc/boot/ppcboot.h
+++ b/arch/powerpc/boot/ppcboot.h
@@ -43,7 +43,7 @@ typedef struct bd_info {
 	unsigned long	bi_sramstart;	/* start of SRAM memory */
 	unsigned long	bi_sramsize;	/* size	 of SRAM memory */
 #if defined(TARGET_8xx) || defined(TARGET_CPM2) || defined(TARGET_85xx) ||\
-	defined(TARGET_83xx)
+	defined(TARGET_83xx) || defined(TARGET_86xx)
 	unsigned long	bi_immr_base;	/* base of IMMR register */
 #endif
 #if defined(TARGET_PPC_MPC52xx)
diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c
index 167ee9433de6..e04c1e4063ae 100644
--- a/arch/powerpc/boot/serial.c
+++ b/arch/powerpc/boot/serial.c
@@ -132,6 +132,8 @@ int serial_console_init(void)
 	else if (dt_is_compatible(devp, "xlnx,opb-uartlite-1.00.b") ||
 		 dt_is_compatible(devp, "xlnx,xps-uartlite-1.00.a"))
 		rc = uartlite_console_init(devp, &serial_cd);
+	else if (dt_is_compatible(devp, "ibm,opal-console-raw"))
+		rc = opal_console_init(devp, &serial_cd);
 
 	/* Add other serial console driver calls here */
 
diff --git a/arch/powerpc/boot/types.h b/arch/powerpc/boot/types.h
index 31393d17a9c1..85565a89bcc2 100644
--- a/arch/powerpc/boot/types.h
+++ b/arch/powerpc/boot/types.h
@@ -12,6 +12,16 @@ typedef short			s16;
 typedef int			s32;
 typedef long long		s64;
 
+/* required for opal-api.h */
+typedef u8  uint8_t;
+typedef u16 uint16_t;
+typedef u32 uint32_t;
+typedef u64 uint64_t;
+typedef s8  int8_t;
+typedef s16 int16_t;
+typedef s32 int32_t;
+typedef s64 int64_t;
+
 #define min(x,y) ({ \
 	typeof(x) _x = (x);	\
 	typeof(y) _y = (y);	\
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 6a19fcef5596..6681ec3625c9 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -302,6 +302,11 @@ mvme5100)
     platformo="$object/fixed-head.o $object/mvme5100.o"
     binary=y
     ;;
+mvme7100)
+    platformo="$object/motload-head.o $object/mvme7100.o"
+    link_address='0x4000000'
+    binary=y
+    ;;
 esac
 
 vmz="$tmpdir/`basename \"$kernel\"`.$ext"
diff --git a/arch/powerpc/configs/40x/acadia_defconfig b/arch/powerpc/configs/40x/acadia_defconfig
index 9110a5cb1bb7..3438ed99c088 100644
--- a/arch/powerpc/configs/40x/acadia_defconfig
+++ b/arch/powerpc/configs/40x/acadia_defconfig
@@ -21,7 +21,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/40x/ep405_defconfig b/arch/powerpc/configs/40x/ep405_defconfig
index 790366652ba3..36c44c0b560c 100644
--- a/arch/powerpc/configs/40x/ep405_defconfig
+++ b/arch/powerpc/configs/40x/ep405_defconfig
@@ -20,7 +20,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/40x/kilauea_defconfig b/arch/powerpc/configs/40x/kilauea_defconfig
index 01bd71bac027..ad2156c6e2fc 100644
--- a/arch/powerpc/configs/40x/kilauea_defconfig
+++ b/arch/powerpc/configs/40x/kilauea_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/40x/klondike_defconfig b/arch/powerpc/configs/40x/klondike_defconfig
index e2036b7c7edb..28adb782ec51 100644
--- a/arch/powerpc/configs/40x/klondike_defconfig
+++ b/arch/powerpc/configs/40x/klondike_defconfig
@@ -32,8 +32,6 @@ CONFIG_SCSI_SAS_ATTRS=y
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
@@ -44,7 +42,6 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
-CONFIG_AVERAGE=y
 CONFIG_MAGIC_SYSRQ=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_BUGVERBOSE is not set
diff --git a/arch/powerpc/configs/40x/makalu_defconfig b/arch/powerpc/configs/40x/makalu_defconfig
index efd51701fb4d..a00f434c4d47 100644
--- a/arch/powerpc/configs/40x/makalu_defconfig
+++ b/arch/powerpc/configs/40x/makalu_defconfig
@@ -20,7 +20,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/40x/obs600_defconfig b/arch/powerpc/configs/40x/obs600_defconfig
index 5ded3dcdf60a..e500e6a12b3e 100644
--- a/arch/powerpc/configs/40x/obs600_defconfig
+++ b/arch/powerpc/configs/40x/obs600_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/40x/virtex_defconfig b/arch/powerpc/configs/40x/virtex_defconfig
index bcb0c4d854db..65dc084a154c 100644
--- a/arch/powerpc/configs/40x/virtex_defconfig
+++ b/arch/powerpc/configs/40x/virtex_defconfig
@@ -27,7 +27,6 @@ CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_LRO is not set
 CONFIG_NETFILTER=y
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_FILTER=m
diff --git a/arch/powerpc/configs/40x/walnut_defconfig b/arch/powerpc/configs/40x/walnut_defconfig
index 37c838f26e53..567f99bd64a3 100644
--- a/arch/powerpc/configs/40x/walnut_defconfig
+++ b/arch/powerpc/configs/40x/walnut_defconfig
@@ -18,7 +18,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig
index ea4ef02a0578..143b2fbddb46 100644
--- a/arch/powerpc/configs/44x/akebono_defconfig
+++ b/arch/powerpc/configs/44x/akebono_defconfig
@@ -32,7 +32,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
@@ -110,10 +109,9 @@ CONFIG_MMC=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_M41T80=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
 CONFIG_VFAT_FS=y
diff --git a/arch/powerpc/configs/44x/arches_defconfig b/arch/powerpc/configs/44x/arches_defconfig
index 95494209c124..6bba1a55b827 100644
--- a/arch/powerpc/configs/44x/arches_defconfig
+++ b/arch/powerpc/configs/44x/arches_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/bamboo_defconfig b/arch/powerpc/configs/44x/bamboo_defconfig
index a046f08413fd..477d99fefd9a 100644
--- a/arch/powerpc/configs/44x/bamboo_defconfig
+++ b/arch/powerpc/configs/44x/bamboo_defconfig
@@ -21,7 +21,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/bluestone_defconfig b/arch/powerpc/configs/44x/bluestone_defconfig
index a326b773ac05..6b77aea79b6c 100644
--- a/arch/powerpc/configs/44x/bluestone_defconfig
+++ b/arch/powerpc/configs/44x/bluestone_defconfig
@@ -49,7 +49,7 @@ CONFIG_SENSORS_AD7414=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_M41T80=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
diff --git a/arch/powerpc/configs/44x/canyonlands_defconfig b/arch/powerpc/configs/44x/canyonlands_defconfig
index d939e71fff7d..c8e6f048a122 100644
--- a/arch/powerpc/configs/44x/canyonlands_defconfig
+++ b/arch/powerpc/configs/44x/canyonlands_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/currituck_defconfig b/arch/powerpc/configs/44x/currituck_defconfig
index 5aa312a158dd..3799a26de6f4 100644
--- a/arch/powerpc/configs/44x/currituck_defconfig
+++ b/arch/powerpc/configs/44x/currituck_defconfig
@@ -30,7 +30,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
@@ -71,10 +70,9 @@ CONFIG_USB_OHCI_HCD=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_M41T80=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
diff --git a/arch/powerpc/configs/44x/ebony_defconfig b/arch/powerpc/configs/44x/ebony_defconfig
index 5909e016c37d..c265f54ab9e5 100644
--- a/arch/powerpc/configs/44x/ebony_defconfig
+++ b/arch/powerpc/configs/44x/ebony_defconfig
@@ -19,7 +19,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/eiger_defconfig b/arch/powerpc/configs/44x/eiger_defconfig
index 57499d25c877..bb6bd6d90821 100644
--- a/arch/powerpc/configs/44x/eiger_defconfig
+++ b/arch/powerpc/configs/44x/eiger_defconfig
@@ -24,7 +24,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
@@ -43,7 +42,6 @@ CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_SG=y
 CONFIG_FUSION=y
 CONFIG_FUSION_SAS=y
-CONFIG_I2O=y
 CONFIG_NETDEVICES=y
 CONFIG_IBM_EMAC=y
 CONFIG_IBM_EMAC_RXB=256
diff --git a/arch/powerpc/configs/44x/icon_defconfig b/arch/powerpc/configs/44x/icon_defconfig
index 5d52185d8f5a..060f2edddb71 100644
--- a/arch/powerpc/configs/44x/icon_defconfig
+++ b/arch/powerpc/configs/44x/icon_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
@@ -76,8 +75,7 @@ CONFIG_LOGO=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/powerpc/configs/44x/iss476-smp_defconfig b/arch/powerpc/configs/44x/iss476-smp_defconfig
index 0ad3e449526e..115a6b2be18b 100644
--- a/arch/powerpc/configs/44x/iss476-smp_defconfig
+++ b/arch/powerpc/configs/44x/iss476-smp_defconfig
@@ -32,7 +32,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
@@ -56,10 +55,9 @@ CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_THERMAL=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
diff --git a/arch/powerpc/configs/44x/katmai_defconfig b/arch/powerpc/configs/44x/katmai_defconfig
index a042335971da..b999048c4ae6 100644
--- a/arch/powerpc/configs/44x/katmai_defconfig
+++ b/arch/powerpc/configs/44x/katmai_defconfig
@@ -21,7 +21,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/rainier_defconfig b/arch/powerpc/configs/44x/rainier_defconfig
index 91c2aff9bd55..b8c9ee45d0a2 100644
--- a/arch/powerpc/configs/44x/rainier_defconfig
+++ b/arch/powerpc/configs/44x/rainier_defconfig
@@ -22,7 +22,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/redwood_defconfig b/arch/powerpc/configs/44x/redwood_defconfig
index 7fddf3fe275c..a4bb048448da 100644
--- a/arch/powerpc/configs/44x/redwood_defconfig
+++ b/arch/powerpc/configs/44x/redwood_defconfig
@@ -24,7 +24,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
@@ -41,7 +40,6 @@ CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_SG=y
 CONFIG_FUSION=y
 CONFIG_FUSION_SAS=y
-CONFIG_I2O=y
 CONFIG_NETDEVICES=y
 CONFIG_IBM_EMAC=y
 CONFIG_IBM_EMAC_RXB=256
diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig
index 6928012f3813..63302fbd184d 100644
--- a/arch/powerpc/configs/44x/sam440ep_defconfig
+++ b/arch/powerpc/configs/44x/sam440ep_defconfig
@@ -26,7 +26,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
@@ -85,9 +84,8 @@ CONFIG_RTC_DRV_M41T80_WDT=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_REISERFS_FS=y
 CONFIG_AUTOFS4_FS=y
 CONFIG_ISO9660_FS=y
diff --git a/arch/powerpc/configs/44x/sequoia_defconfig b/arch/powerpc/configs/44x/sequoia_defconfig
index c294369cc39f..b3792fd8111d 100644
--- a/arch/powerpc/configs/44x/sequoia_defconfig
+++ b/arch/powerpc/configs/44x/sequoia_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/taishan_defconfig b/arch/powerpc/configs/44x/taishan_defconfig
index e779228d6cd6..ff6f86241418 100644
--- a/arch/powerpc/configs/44x/taishan_defconfig
+++ b/arch/powerpc/configs/44x/taishan_defconfig
@@ -21,7 +21,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/virtex5_defconfig b/arch/powerpc/configs/44x/virtex5_defconfig
index 53d0300b3390..ce052064bcbb 100644
--- a/arch/powerpc/configs/44x/virtex5_defconfig
+++ b/arch/powerpc/configs/44x/virtex5_defconfig
@@ -26,7 +26,6 @@ CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_LRO is not set
 CONFIG_NETFILTER=y
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_FILTER=m
diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig
index ee434375fc24..ab932488e68b 100644
--- a/arch/powerpc/configs/44x/warp_defconfig
+++ b/arch/powerpc/configs/44x/warp_defconfig
@@ -23,7 +23,6 @@ CONFIG_UNIX=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
 CONFIG_VLAN_8021Q=y
@@ -73,9 +72,7 @@ CONFIG_LEDS_GPIO=y
 CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/powerpc/configs/52xx/cm5200_defconfig b/arch/powerpc/configs/52xx/cm5200_defconfig
index 19fad0e0016e..c1faac800806 100644
--- a/arch/powerpc/configs/52xx/cm5200_defconfig
+++ b/arch/powerpc/configs/52xx/cm5200_defconfig
@@ -22,7 +22,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -61,8 +60,7 @@ CONFIG_USB_STORAGE=y
 CONFIG_DMADEVICES=y
 CONFIG_PPC_BESTCOMM=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/powerpc/configs/52xx/lite5200b_defconfig b/arch/powerpc/configs/52xx/lite5200b_defconfig
index 5f40ba92a39a..9493b02ac660 100644
--- a/arch/powerpc/configs/52xx/lite5200b_defconfig
+++ b/arch/powerpc/configs/52xx/lite5200b_defconfig
@@ -24,7 +24,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -53,8 +52,7 @@ CONFIG_I2C_MPC=y
 CONFIG_DMADEVICES=y
 CONFIG_PPC_BESTCOMM=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/52xx/motionpro_defconfig b/arch/powerpc/configs/52xx/motionpro_defconfig
index 909e185a88d1..fe8126bc1655 100644
--- a/arch/powerpc/configs/52xx/motionpro_defconfig
+++ b/arch/powerpc/configs/52xx/motionpro_defconfig
@@ -22,7 +22,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -73,8 +72,7 @@ CONFIG_RTC_DRV_DS1307=y
 CONFIG_DMADEVICES=y
 CONFIG_PPC_BESTCOMM=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/powerpc/configs/52xx/pcm030_defconfig b/arch/powerpc/configs/52xx/pcm030_defconfig
index 649a01a0044d..1554de6968ca 100644
--- a/arch/powerpc/configs/52xx/pcm030_defconfig
+++ b/arch/powerpc/configs/52xx/pcm030_defconfig
@@ -34,7 +34,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
@@ -74,8 +73,7 @@ CONFIG_RTC_DRV_PCF8563=m
 CONFIG_DMADEVICES=y
 CONFIG_PPC_BESTCOMM=y
 CONFIG_EXT2_FS=m
-CONFIG_EXT3_FS=m
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=m
 # CONFIG_DNOTIFY is not set
 CONFIG_VFAT_FS=m
 CONFIG_FAT_DEFAULT_CODEPAGE=850
diff --git a/arch/powerpc/configs/52xx/tqm5200_defconfig b/arch/powerpc/configs/52xx/tqm5200_defconfig
index efab8388ea92..b8b316b884aa 100644
--- a/arch/powerpc/configs/52xx/tqm5200_defconfig
+++ b/arch/powerpc/configs/52xx/tqm5200_defconfig
@@ -26,7 +26,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -75,8 +74,7 @@ CONFIG_RTC_DRV_DS1374=y
 CONFIG_DMADEVICES=y
 CONFIG_PPC_BESTCOMM=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/powerpc/configs/83xx/asp8347_defconfig b/arch/powerpc/configs/83xx/asp8347_defconfig
index bcdfb07921fc..b60cac088a7b 100644
--- a/arch/powerpc/configs/83xx/asp8347_defconfig
+++ b/arch/powerpc/configs/83xx/asp8347_defconfig
@@ -26,7 +26,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -63,8 +62,7 @@ CONFIG_USB_EHCI_FSL=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1374=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/83xx/kmeter1_defconfig b/arch/powerpc/configs/83xx/kmeter1_defconfig
index 11a959283149..9547dcdd6489 100644
--- a/arch/powerpc/configs/83xx/kmeter1_defconfig
+++ b/arch/powerpc/configs/83xx/kmeter1_defconfig
@@ -28,7 +28,6 @@ CONFIG_IP_PNP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_TIPC=y
 CONFIG_BRIDGE=m
diff --git a/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig b/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig
index b47a41f77836..80aa844c1428 100644
--- a/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -79,8 +78,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_INTF_DEV_UIE_EMUL=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig b/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig
index e28c83f320c1..d89d13bc6901 100644
--- a/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -77,8 +76,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_INTF_DEV_UIE_EMUL=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/83xx/mpc832x_mds_defconfig b/arch/powerpc/configs/83xx/mpc832x_mds_defconfig
index e84d35b848c0..e789518a2881 100644
--- a/arch/powerpc/configs/83xx/mpc832x_mds_defconfig
+++ b/arch/powerpc/configs/83xx/mpc832x_mds_defconfig
@@ -26,7 +26,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -52,8 +51,7 @@ CONFIG_WATCHDOG=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1374=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
index ae145f410590..917a49ca2bd1 100644
--- a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
@@ -26,7 +26,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -64,8 +63,7 @@ CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_MMC_SPI=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
index 87fc15bce407..00f636e95cc8 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
@@ -24,7 +24,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -75,8 +74,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_INTF_DEV_UIE_EMUL=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
index 9a2ff25a2e98..a539d44d1dba 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
@@ -24,7 +24,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -66,8 +65,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_INTF_DEV_UIE_EMUL=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/powerpc/configs/83xx/mpc834x_mds_defconfig b/arch/powerpc/configs/83xx/mpc834x_mds_defconfig
index e44edc575549..9f0ddc830c82 100644
--- a/arch/powerpc/configs/83xx/mpc834x_mds_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_mds_defconfig
@@ -25,7 +25,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -51,8 +50,7 @@ CONFIG_WATCHDOG=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1374=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/83xx/mpc836x_mds_defconfig b/arch/powerpc/configs/83xx/mpc836x_mds_defconfig
index 94a7d85f1603..ceed4c1f0ab5 100644
--- a/arch/powerpc/configs/83xx/mpc836x_mds_defconfig
+++ b/arch/powerpc/configs/83xx/mpc836x_mds_defconfig
@@ -25,7 +25,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -57,8 +56,7 @@ CONFIG_WATCHDOG=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1374=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig b/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig
index 761ed8ea0729..a6819bf3ef5e 100644
--- a/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig
+++ b/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig
@@ -24,7 +24,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
@@ -65,8 +64,7 @@ CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/83xx/mpc837x_mds_defconfig b/arch/powerpc/configs/83xx/mpc837x_mds_defconfig
index bcf1b48cc9e6..4bd1992e4d98 100644
--- a/arch/powerpc/configs/83xx/mpc837x_mds_defconfig
+++ b/arch/powerpc/configs/83xx/mpc837x_mds_defconfig
@@ -22,7 +22,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -50,8 +49,7 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MPC=y
 CONFIG_WATCHDOG=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
index f0f0ebf75125..2d4bb63882b8 100644
--- a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
@@ -24,7 +24,6 @@ CONFIG_SYN_COOKIES=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -77,8 +76,7 @@ CONFIG_USB_MON=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_FSL=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/83xx/sbc834x_defconfig b/arch/powerpc/configs/83xx/sbc834x_defconfig
index d2e4d82de14d..b3380dbd1925 100644
--- a/arch/powerpc/configs/83xx/sbc834x_defconfig
+++ b/arch/powerpc/configs/83xx/sbc834x_defconfig
@@ -22,7 +22,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -65,9 +64,7 @@ CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_FSL=y
 CONFIG_USB_STORAGE=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
index b0939dd9ad6f..c79283be5680 100644
--- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig
+++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -165,10 +165,8 @@ CONFIG_FSL_DMA=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_FUSE_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
diff --git a/arch/powerpc/configs/85xx/kmp204x_defconfig b/arch/powerpc/configs/85xx/kmp204x_defconfig
index e94d3eb4a8c1..aaaaa609cd24 100644
--- a/arch/powerpc/configs/85xx/kmp204x_defconfig
+++ b/arch/powerpc/configs/85xx/kmp204x_defconfig
@@ -64,7 +64,6 @@ CONFIG_IP_PIMSM_V2=y
 CONFIG_INET_AH=y
 CONFIG_INET_ESP=y
 CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
 CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_TIPC=y
@@ -189,7 +188,7 @@ CONFIG_RTC_DRV_DS3232=y
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_UIO=y
 CONFIG_STAGING=y
-CONFIG_CLK_PPC_CORENET=y
+CONFIG_CLK_QORIQ=y
 CONFIG_EXT2_FS=y
 CONFIG_NTFS_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/powerpc/configs/85xx/ksi8560_defconfig b/arch/powerpc/configs/85xx/ksi8560_defconfig
index 6f753a71fe5d..bd814dfb0bbd 100644
--- a/arch/powerpc/configs/85xx/ksi8560_defconfig
+++ b/arch/powerpc/configs/85xx/ksi8560_defconfig
@@ -21,7 +21,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -49,8 +48,7 @@ CONFIG_SERIAL_CPM=y
 CONFIG_SERIAL_CPM_CONSOLE=y
 CONFIG_GEN_RTC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/85xx/mpc8540_ads_defconfig b/arch/powerpc/configs/85xx/mpc8540_ads_defconfig
index e38c373f2edf..32af10def641 100644
--- a/arch/powerpc/configs/85xx/mpc8540_ads_defconfig
+++ b/arch/powerpc/configs/85xx/mpc8540_ads_defconfig
@@ -22,7 +22,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -41,8 +40,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_GEN_RTC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/85xx/mpc8560_ads_defconfig b/arch/powerpc/configs/85xx/mpc8560_ads_defconfig
index 48fc8e3a7be0..a52b2170ee33 100644
--- a/arch/powerpc/configs/85xx/mpc8560_ads_defconfig
+++ b/arch/powerpc/configs/85xx/mpc8560_ads_defconfig
@@ -21,7 +21,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -44,8 +43,7 @@ CONFIG_SERIAL_CPM=y
 CONFIG_SERIAL_CPM_CONSOLE=y
 CONFIG_GEN_RTC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig
index ecb0c3bf8796..002bb48abaa3 100644
--- a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig
+++ b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -46,8 +45,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_GEN_RTC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/85xx/sbc8548_defconfig b/arch/powerpc/configs/85xx/sbc8548_defconfig
index 72b7ccfbe2c2..97ae02377cf3 100644
--- a/arch/powerpc/configs/85xx/sbc8548_defconfig
+++ b/arch/powerpc/configs/85xx/sbc8548_defconfig
@@ -20,7 +20,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
diff --git a/arch/powerpc/configs/85xx/socrates_defconfig b/arch/powerpc/configs/85xx/socrates_defconfig
index 0ad7bd5ee6b6..13579cb30539 100644
--- a/arch/powerpc/configs/85xx/socrates_defconfig
+++ b/arch/powerpc/configs/85xx/socrates_defconfig
@@ -22,7 +22,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_CAN=y
 CONFIG_MTD=y
@@ -79,8 +78,7 @@ CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
 CONFIG_USB_STORAGE=y
 CONFIG_RTC_CLASS=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/85xx/stx_gp3_defconfig b/arch/powerpc/configs/85xx/stx_gp3_defconfig
index b45190556c0c..384926f3ce1d 100644
--- a/arch/powerpc/configs/85xx/stx_gp3_defconfig
+++ b/arch/powerpc/configs/85xx/stx_gp3_defconfig
@@ -17,7 +17,6 @@ CONFIG_UNIX=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
 CONFIG_IP_NF_IPTABLES=m
@@ -53,8 +52,7 @@ CONFIG_AGP=m
 CONFIG_DRM=m
 CONFIG_SOUND=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_AUTOFS4_FS=y
 CONFIG_ISO9660_FS=m
 CONFIG_UDF_FS=m
diff --git a/arch/powerpc/configs/85xx/tqm8540_defconfig b/arch/powerpc/configs/85xx/tqm8540_defconfig
index 4daaf2943b44..908f3885f4a5 100644
--- a/arch/powerpc/configs/85xx/tqm8540_defconfig
+++ b/arch/powerpc/configs/85xx/tqm8540_defconfig
@@ -20,7 +20,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -50,8 +49,7 @@ CONFIG_I2C_MPC=y
 CONFIG_HWMON_DEBUG_CHIP=y
 CONFIG_SENSORS_LM75=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/85xx/tqm8541_defconfig b/arch/powerpc/configs/85xx/tqm8541_defconfig
index bb402b3cf786..f47e57610b7c 100644
--- a/arch/powerpc/configs/85xx/tqm8541_defconfig
+++ b/arch/powerpc/configs/85xx/tqm8541_defconfig
@@ -20,7 +20,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -52,8 +51,7 @@ CONFIG_I2C_MPC=y
 CONFIG_HWMON_DEBUG_CHIP=y
 CONFIG_SENSORS_LM75=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/85xx/tqm8548_defconfig b/arch/powerpc/configs/85xx/tqm8548_defconfig
index 685d0fb132d6..42f5d0a7698e 100644
--- a/arch/powerpc/configs/85xx/tqm8548_defconfig
+++ b/arch/powerpc/configs/85xx/tqm8548_defconfig
@@ -28,7 +28,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
diff --git a/arch/powerpc/configs/85xx/tqm8555_defconfig b/arch/powerpc/configs/85xx/tqm8555_defconfig
index 02a931d4e954..71552b7929cd 100644
--- a/arch/powerpc/configs/85xx/tqm8555_defconfig
+++ b/arch/powerpc/configs/85xx/tqm8555_defconfig
@@ -20,7 +20,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -52,8 +51,7 @@ CONFIG_I2C_MPC=y
 CONFIG_HWMON_DEBUG_CHIP=y
 CONFIG_SENSORS_LM75=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/85xx/tqm8560_defconfig b/arch/powerpc/configs/85xx/tqm8560_defconfig
index 633d5b759a36..25aac973d6d7 100644
--- a/arch/powerpc/configs/85xx/tqm8560_defconfig
+++ b/arch/powerpc/configs/85xx/tqm8560_defconfig
@@ -20,7 +20,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -52,8 +51,7 @@ CONFIG_I2C_MPC=y
 CONFIG_HWMON_DEBUG_CHIP=y
 CONFIG_SENSORS_LM75=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index 858b539d004b..dbd961de251e 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -54,7 +54,6 @@ CONFIG_IP_PIMSM_V2=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 CONFIG_IPV6=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
@@ -124,8 +123,7 @@ CONFIG_RTC_DRV_CMOS=y
 CONFIG_DMADEVICES=y
 CONFIG_FSL_DMA=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_ZISOFS=y
diff --git a/arch/powerpc/configs/86xx-hw.config b/arch/powerpc/configs/86xx-hw.config
index f91f8895fc93..d3dd6b8865c0 100644
--- a/arch/powerpc/configs/86xx-hw.config
+++ b/arch/powerpc/configs/86xx-hw.config
@@ -74,9 +74,9 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_NR_UARTS=2
+CONFIG_SERIAL_8250_NR_UARTS=5
 CONFIG_SERIAL_8250_RSA=y
-CONFIG_SERIAL_8250_RUNTIME_UARTS=2
+CONFIG_SERIAL_8250_RUNTIME_UARTS=5
 CONFIG_SERIAL_8250_SHARE_IRQ=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIO_LIBPS2=y
diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig
index d89ff40d39b7..6a3f825452e9 100644
--- a/arch/powerpc/configs/adder875_defconfig
+++ b/arch/powerpc/configs/adder875_defconfig
@@ -24,7 +24,6 @@ CONFIG_SYN_COOKIES=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig
index 84f1b4140579..8b83ce8a01e7 100644
--- a/arch/powerpc/configs/amigaone_defconfig
+++ b/arch/powerpc/configs/amigaone_defconfig
@@ -29,7 +29,6 @@ CONFIG_SYN_COOKIES=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
 # CONFIG_NETFILTER_ADVANCED is not set
@@ -106,7 +105,6 @@ CONFIG_USB_STORAGE=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
 CONFIG_EXT4_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_MSDOS_FS=m
diff --git a/arch/powerpc/configs/c2k_defconfig b/arch/powerpc/configs/c2k_defconfig
index 340685caa7b8..7c9d95370150 100644
--- a/arch/powerpc/configs/c2k_defconfig
+++ b/arch/powerpc/configs/c2k_defconfig
@@ -306,15 +306,13 @@ CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_MAD=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_INFINIBAND_MTHCA=m
-CONFIG_INFINIBAND_AMSO1100=m
 CONFIG_INFINIBAND_IPOIB=m
 CONFIG_INFINIBAND_IPOIB_CM=y
 CONFIG_INFINIBAND_SRP=m
 CONFIG_DMADEVICES=y
-CONFIG_EXT3_FS=m
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=m
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_QUOTA=y
 CONFIG_QFMT_V2=y
 CONFIG_AUTOFS4_FS=m
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index db328e618bb9..7b6f30dece34 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -184,7 +184,7 @@ CONFIG_EDAC_MM_EDAC=y
 CONFIG_EDAC_CELL=y
 CONFIG_UIO=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_AUTOFS4_FS=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig
index 253a9f200097..ac9a50da2dc6 100644
--- a/arch/powerpc/configs/chrp32_defconfig
+++ b/arch/powerpc/configs/chrp32_defconfig
@@ -110,7 +110,6 @@ CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_UHCI_HCD=y
 CONFIG_USB_STORAGE=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
 CONFIG_EXT4_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_MSDOS_FS=m
diff --git a/arch/powerpc/configs/ep8248e_defconfig b/arch/powerpc/configs/ep8248e_defconfig
index 7c137041f1d6..3403b85f9d81 100644
--- a/arch/powerpc/configs/ep8248e_defconfig
+++ b/arch/powerpc/configs/ep8248e_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 CONFIG_NETFILTER=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -50,9 +49,7 @@ CONFIG_SERIAL_CPM_CONSOLE=y
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
 CONFIG_AUTOFS4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig
index ee96be889dac..95411aeeeb8d 100644
--- a/arch/powerpc/configs/ep88xc_defconfig
+++ b/arch/powerpc/configs/ep88xc_defconfig
@@ -26,7 +26,6 @@ CONFIG_SYN_COOKIES=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config
index 41e4d359524d..1a61e81ab0cd 100644
--- a/arch/powerpc/configs/fsl-emb-nonhw.config
+++ b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -33,8 +33,7 @@ CONFIG_DUMMY=y
 CONFIG_EFS_FS=m
 CONFIG_EXPERT=y
 CONFIG_EXT2_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_FB=y
 CONFIG_FHANDLE=y
 CONFIG_FIXED_PHY=y
@@ -55,7 +54,6 @@ CONFIG_IKCONFIG=y
 CONFIG_INET_AH=y
 CONFIG_INET_ESP=y
 CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 CONFIG_INET=y
 CONFIG_IP_ADVANCED_ROUTER=y
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index 1d9ad8500909..3b2511c090d8 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -216,14 +216,13 @@ CONFIG_USB_SERIAL_CYBERJACK=m
 CONFIG_USB_SERIAL_XIRCOM=m
 CONFIG_USB_SERIAL_OMNINET=m
 CONFIG_USB_APPLEDISPLAY=m
+CONFIG_FS_DAX=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=y
 CONFIG_REISERFS_FS_XATTR=y
diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig
index 6c6c60f1aba4..c0eec4a5df4e 100644
--- a/arch/powerpc/configs/gamecube_defconfig
+++ b/arch/powerpc/configs/gamecube_defconfig
@@ -32,7 +32,6 @@ CONFIG_IP_PNP_RARP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
@@ -76,9 +75,7 @@ CONFIG_SND_SEQUENCER_OSS=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_MSDOS_FS=y
diff --git a/arch/powerpc/configs/holly_defconfig b/arch/powerpc/configs/holly_defconfig
index 5e0f2551e5c7..e56e80090529 100644
--- a/arch/powerpc/configs/holly_defconfig
+++ b/arch/powerpc/configs/holly_defconfig
@@ -25,7 +25,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -52,7 +51,7 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_GEN_RTC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/linkstation_defconfig b/arch/powerpc/configs/linkstation_defconfig
index 62ae92956d05..b413c19d7031 100644
--- a/arch/powerpc/configs/linkstation_defconfig
+++ b/arch/powerpc/configs/linkstation_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -109,8 +108,7 @@ CONFIG_USB_SERIAL_FTDI_SIO=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_RS5C372=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_XFS_FS=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig
index ac9666f8abf1..27abfab31219 100644
--- a/arch/powerpc/configs/maple_defconfig
+++ b/arch/powerpc/configs/maple_defconfig
@@ -35,7 +35,6 @@ CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_RAM=y
@@ -102,9 +101,7 @@ CONFIG_USB_SERIAL_KEYSPAN_USA49W=y
 CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y
 CONFIG_USB_SERIAL_TI=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_FS_DAX=y
 CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
diff --git a/arch/powerpc/configs/mgcoge_defconfig b/arch/powerpc/configs/mgcoge_defconfig
index 666922c5b572..197acaa026eb 100644
--- a/arch/powerpc/configs/mgcoge_defconfig
+++ b/arch/powerpc/configs/mgcoge_defconfig
@@ -27,7 +27,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
 CONFIG_TIPC=y
diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig
index d16d6c5cb282..0b4854cf26cb 100644
--- a/arch/powerpc/configs/mpc512x_defconfig
+++ b/arch/powerpc/configs/mpc512x_defconfig
@@ -27,7 +27,6 @@ CONFIG_IP_PNP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 CONFIG_CAN=y
@@ -53,7 +52,7 @@ CONFIG_MTD_UBI=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=1
 CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_BLK_DEV_XIP=y
+CONFIG_BLK_DEV_RAM_DAX=y
 CONFIG_EEPROM_AT24=y
 CONFIG_EEPROM_AT25=y
 CONFIG_SCSI=y
@@ -113,10 +112,9 @@ CONFIG_RTC_DRV_MPC5121=y
 CONFIG_DMADEVICES=y
 CONFIG_MPC512X_DMA=y
 CONFIG_MPC512x_LPBFIFO=y
+CONFIG_FS_DAX=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/powerpc/configs/mpc5200_defconfig b/arch/powerpc/configs/mpc5200_defconfig
index 9fd041bfd778..88336d0df0d6 100644
--- a/arch/powerpc/configs/mpc5200_defconfig
+++ b/arch/powerpc/configs/mpc5200_defconfig
@@ -26,7 +26,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
@@ -114,8 +113,7 @@ CONFIG_RTC_DRV_PCF8563=m
 CONFIG_DMADEVICES=y
 CONFIG_PPC_BESTCOMM=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
diff --git a/arch/powerpc/configs/mpc7448_hpc2_defconfig b/arch/powerpc/configs/mpc7448_hpc2_defconfig
index e2647d5bb605..d933326b4cf9 100644
--- a/arch/powerpc/configs/mpc7448_hpc2_defconfig
+++ b/arch/powerpc/configs/mpc7448_hpc2_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -49,8 +48,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_GEN_RTC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/mpc8272_ads_defconfig b/arch/powerpc/configs/mpc8272_ads_defconfig
index 825b052176af..4cb0f617c0d6 100644
--- a/arch/powerpc/configs/mpc8272_ads_defconfig
+++ b/arch/powerpc/configs/mpc8272_ads_defconfig
@@ -22,7 +22,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 CONFIG_NETFILTER=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -56,8 +55,7 @@ CONFIG_SERIAL_CPM_CONSOLE=y
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_AUTOFS4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig
index 671e220a9a98..6574477fd726 100644
--- a/arch/powerpc/configs/mpc83xx_defconfig
+++ b/arch/powerpc/configs/mpc83xx_defconfig
@@ -37,7 +37,6 @@ CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 CONFIG_INET_ESP=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
@@ -101,8 +100,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_DS1374=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/mpc866_ads_defconfig b/arch/powerpc/configs/mpc866_ads_defconfig
index 321412c5dae4..998454471a48 100644
--- a/arch/powerpc/configs/mpc866_ads_defconfig
+++ b/arch/powerpc/configs/mpc866_ads_defconfig
@@ -24,7 +24,6 @@ CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_NETDEVICES=y
@@ -37,8 +36,7 @@ CONFIG_SERIAL_CPM_CONSOLE=y
 CONFIG_GEN_RTC=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
diff --git a/arch/powerpc/configs/mpc86xx_basic_defconfig b/arch/powerpc/configs/mpc86xx_basic_defconfig
index 33af5c5de105..3283f0586e11 100644
--- a/arch/powerpc/configs/mpc86xx_basic_defconfig
+++ b/arch/powerpc/configs/mpc86xx_basic_defconfig
@@ -8,3 +8,4 @@ CONFIG_GEF_SBC610=y
 CONFIG_MPC8610_HPCD=y
 CONFIG_MPC8641_HPCN=y
 CONFIG_SBC8641D=y
+CONFIG_MVME7100=y
diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig
index 2a10f98d4ee5..91f53f1bec5d 100644
--- a/arch/powerpc/configs/mpc885_ads_defconfig
+++ b/arch/powerpc/configs/mpc885_ads_defconfig
@@ -25,7 +25,6 @@ CONFIG_SYN_COOKIES=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
diff --git a/arch/powerpc/configs/mvme5100_defconfig b/arch/powerpc/configs/mvme5100_defconfig
index 525a2cb500a7..139add95a16a 100644
--- a/arch/powerpc/configs/mvme5100_defconfig
+++ b/arch/powerpc/configs/mvme5100_defconfig
@@ -32,7 +32,6 @@ CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -92,8 +91,7 @@ CONFIG_I2C_MPC=y
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=m
-CONFIG_EXT3_FS=m
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=m
 CONFIG_XFS_FS=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 8f94782eb907..76f4edd441d3 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -152,8 +152,7 @@ CONFIG_RTC_DRV_DS1307=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_AUTOFS4_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_UDF_FS=y
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index 3f6c9a6c815c..e5a674d4a716 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -40,7 +40,6 @@ CONFIG_INET_AH=y
 CONFIG_INET_ESP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -281,10 +280,8 @@ CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y
 CONFIG_USB_APPLEDISPLAY=m
 CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_AUTOFS4_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_ISO9660_FS=y
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index 045031048f8d..dce352e9153b 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -80,6 +80,7 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=y
+CONFIG_MTD_BLOCK=y
 CONFIG_MTD_POWERNV_FLASH=y
 CONFIG_PARPORT=m
 CONFIG_PARPORT_PC=m
@@ -181,6 +182,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_JSM=m
 CONFIG_VIRTIO_CONSOLE=m
+CONFIG_POWERNV_OP_PANEL=m
 CONFIG_IPMI_HANDLER=y
 CONFIG_IPMI_DEVICE_INTERFACE=y
 CONFIG_IPMI_POWERNV=y
@@ -233,9 +235,9 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_REISERFS_FS=y
 CONFIG_REISERFS_FS_XATTR=y
 CONFIG_REISERFS_FS_POSIX_ACL=y
diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig
index a43bf6ea10fb..370c0bbcff71 100644
--- a/arch/powerpc/configs/ppc40x_defconfig
+++ b/arch/powerpc/configs/ppc40x_defconfig
@@ -25,7 +25,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
@@ -67,8 +66,7 @@ CONFIG_THERMAL=y
 CONFIG_FB=m
 CONFIG_FB_XILINX=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=m
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig
index bbc7f76d52c8..2766e8f590bc 100644
--- a/arch/powerpc/configs/ppc44x_defconfig
+++ b/arch/powerpc/configs/ppc44x_defconfig
@@ -35,7 +35,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 CONFIG_BRIDGE=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
@@ -89,8 +88,7 @@ CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
 # CONFIG_USB_OHCI_HCD_PCI is not set
 CONFIG_USB_STORAGE=m
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=m
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index b041fb607376..0a8d250cb97e 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -247,7 +247,6 @@ CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_MAD=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_INFINIBAND_MTHCA=m
-CONFIG_INFINIBAND_EHCA=m
 CONFIG_INFINIBAND_CXGB3=m
 CONFIG_INFINIBAND_CXGB4=m
 CONFIG_MLX4_INFINIBAND=m
@@ -262,14 +261,11 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
+CONFIG_FS_DAX=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index ddf9773458cf..fd2edd650c20 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -178,15 +178,11 @@ CONFIG_EDAC=y
 CONFIG_EDAC_MM_EDAC=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
+CONFIG_FS_DAX=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 1dde0be2be30..8fbf49801233 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -512,7 +512,6 @@ CONFIG_E1000E=m
 CONFIG_IGB=m
 CONFIG_IXGB=m
 CONFIG_IXGBE=m
-CONFIG_IP1000=m
 CONFIG_MV643XX_ETH=m
 CONFIG_SKGE=m
 CONFIG_SKY2=m
@@ -1029,14 +1028,14 @@ CONFIG_UIO_CIF=m
 CONFIG_UIO_PDRV_GENIRQ=m
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
+CONFIG_FS_DAX=y
 CONFIG_EXT2_FS=m
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=m
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
+CONFIG_EXT4_FS=m
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_JBD2_DEBUG=y
 CONFIG_REISERFS_FS=m
diff --git a/arch/powerpc/configs/pq2fads_defconfig b/arch/powerpc/configs/pq2fads_defconfig
index 3e336ee8bb4a..50b2bad51d0a 100644
--- a/arch/powerpc/configs/pq2fads_defconfig
+++ b/arch/powerpc/configs/pq2fads_defconfig
@@ -23,7 +23,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
 CONFIG_NETFILTER=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
@@ -40,7 +39,6 @@ CONFIG_MTD_CFI_I4=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_PHYSMAP_OF=y
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_IDE=y
 CONFIG_NETDEVICES=y
 CONFIG_TUN=y
 CONFIG_FS_ENET=y
@@ -59,8 +57,7 @@ CONFIG_SERIAL_CPM_CONSOLE=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_ETH=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_AUTOFS4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index c40046074f8b..ee0ec5a682fc 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -51,7 +51,6 @@ CONFIG_IP_PNP_DHCP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_INET_DIAG is not set
 CONFIG_BT=m
 CONFIG_BT_RFCOMM=m
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 36871a4bfa54..654aeffc57ef 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -53,6 +53,7 @@ CONFIG_KEXEC=y
 CONFIG_IRQ_ALL_CPUS=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
+CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_PPC_64K_PAGES=y
@@ -223,7 +224,6 @@ CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_MAD=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_INFINIBAND_MTHCA=m
-CONFIG_INFINIBAND_EHCA=m
 CONFIG_INFINIBAND_CXGB3=m
 CONFIG_INFINIBAND_CXGB4=m
 CONFIG_MLX4_INFINIBAND=m
@@ -233,14 +233,11 @@ CONFIG_INFINIBAND_SRP=m
 CONFIG_INFINIBAND_ISER=m
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
+CONFIG_FS_DAX=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig
index b5db7dffe86d..e9122b15e5fd 100644
--- a/arch/powerpc/configs/storcenter_defconfig
+++ b/arch/powerpc/configs/storcenter_defconfig
@@ -25,7 +25,6 @@ CONFIG_IP_PNP_DHCP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
@@ -72,8 +71,7 @@ CONFIG_USB_STORAGE=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT4_FS=y
 CONFIG_XFS_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig
index 4c973c5321c6..78fddf24b5d3 100644
--- a/arch/powerpc/configs/tqm8xx_defconfig
+++ b/arch/powerpc/configs/tqm8xx_defconfig
@@ -29,7 +29,6 @@ CONFIG_SYN_COOKIES=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index 34eaf528fa87..dcdd51b57783 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -32,7 +32,6 @@ CONFIG_IP_PNP_RARP=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 CONFIG_BT=y
@@ -96,9 +95,7 @@ CONFIG_MMC_SDHCI=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_EXT4_FS=y
 CONFIG_FUSE_FS=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
diff --git a/arch/powerpc/include/asm/accounting.h b/arch/powerpc/include/asm/accounting.h
new file mode 100644
index 000000000000..c133246df467
--- /dev/null
+++ b/arch/powerpc/include/asm/accounting.h
@@ -0,0 +1,24 @@
+/*
+ * Common time accounting prototypes and such for all ppc machines.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __POWERPC_ACCOUNTING_H
+#define __POWERPC_ACCOUNTING_H
+
+/* Stuff for accurate time accounting */
+struct cpu_accounting_data {
+	unsigned long user_time;	/* accumulated usermode TB ticks */
+	unsigned long system_time;	/* accumulated system TB ticks */
+	unsigned long user_time_scaled;	/* accumulated usermode SPURR ticks */
+	unsigned long starttime;	/* TB value snapshot */
+	unsigned long starttime_user;	/* TB value on exit to usermode */
+	unsigned long startspurr;	/* SPURR value snapshot */
+	unsigned long utime_sspurr;	/* ->user_time when ->startspurr set */
+};
+
+#endif
diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index dc85dcb891cf..cee3aa087653 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -36,11 +36,13 @@
 #define PPC_MIN_STKFRM	112
 
 #ifdef __BIG_ENDIAN__
+#define LHZX_BE	stringify_in_c(lhzx)
 #define LWZX_BE	stringify_in_c(lwzx)
 #define LDX_BE	stringify_in_c(ldx)
 #define STWX_BE	stringify_in_c(stwx)
 #define STDX_BE	stringify_in_c(stdx)
 #else
+#define LHZX_BE	stringify_in_c(lhbrx)
 #define LWZX_BE	stringify_in_c(lwbrx)
 #define LDX_BE	stringify_in_c(ldbrx)
 #define STWX_BE	stringify_in_c(stwbrx)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
new file mode 100644
index 000000000000..e71b9097594c
--- /dev/null
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -0,0 +1,75 @@
+#ifndef _ASM_POWERPC_ASM_PROTOTYPES_H
+#define _ASM_POWERPC_ASM_PROTOTYPES_H
+/*
+ * This file is for prototypes of C functions that are only called
+ * from asm, and any associated variables.
+ *
+ * Copyright 2016, Daniel Axtens, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ */
+
+#include <linux/threads.h>
+#include <linux/kprobes.h>
+
+/* SMP */
+extern struct thread_info *current_set[NR_CPUS];
+extern struct thread_info *secondary_ti;
+void start_secondary(void *unused);
+
+/* kexec */
+struct paca_struct;
+struct kimage;
+extern struct paca_struct kexec_paca;
+void kexec_copy_flush(struct kimage *image);
+
+/* pseries hcall tracing */
+extern struct static_key hcall_tracepoint_key;
+void __trace_hcall_entry(unsigned long opcode, unsigned long *args);
+void __trace_hcall_exit(long opcode, unsigned long retval,
+			unsigned long *retbuf);
+/* OPAL tracing */
+#ifdef HAVE_JUMP_LABEL
+extern struct static_key opal_tracepoint_key;
+#endif
+
+void __trace_opal_entry(unsigned long opcode, unsigned long *args);
+void __trace_opal_exit(long opcode, unsigned long retval);
+
+/* VMX copying */
+int enter_vmx_usercopy(void);
+int exit_vmx_usercopy(void);
+int enter_vmx_copy(void);
+void * exit_vmx_copy(void *dest);
+
+/* Traps */
+long machine_check_early(struct pt_regs *regs);
+long hmi_exception_realmode(struct pt_regs *regs);
+void SMIException(struct pt_regs *regs);
+void handle_hmi_exception(struct pt_regs *regs);
+void instruction_breakpoint_exception(struct pt_regs *regs);
+void RunModeException(struct pt_regs *regs);
+void __kprobes single_step_exception(struct pt_regs *regs);
+void __kprobes program_check_exception(struct pt_regs *regs);
+void alignment_exception(struct pt_regs *regs);
+void StackOverflow(struct pt_regs *regs);
+void nonrecoverable_exception(struct pt_regs *regs);
+void kernel_fp_unavailable_exception(struct pt_regs *regs);
+void altivec_unavailable_exception(struct pt_regs *regs);
+void vsx_unavailable_exception(struct pt_regs *regs);
+void fp_unavailable_tm(struct pt_regs *regs);
+void altivec_unavailable_tm(struct pt_regs *regs);
+void vsx_unavailable_tm(struct pt_regs *regs);
+void facility_unavailable_exception(struct pt_regs *regs);
+void TAUException(struct pt_regs *regs);
+void altivec_assist_exception(struct pt_regs *regs);
+void unrecoverable_exception(struct pt_regs *regs);
+void kernel_bad_stack(struct pt_regs *regs);
+void system_reset_exception(struct pt_regs *regs);
+void machine_check_exception(struct pt_regs *regs);
+void __kprobes emulation_assist_interrupt(struct pt_regs *regs);
+
+#endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 74839f24f412..5eaf86ac143d 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -124,6 +124,45 @@
 
 #ifndef __ASSEMBLY__
 
+struct mmu_hash_ops {
+	void            (*hpte_invalidate)(unsigned long slot,
+					   unsigned long vpn,
+					   int bpsize, int apsize,
+					   int ssize, int local);
+	long		(*hpte_updatepp)(unsigned long slot,
+					 unsigned long newpp,
+					 unsigned long vpn,
+					 int bpsize, int apsize,
+					 int ssize, unsigned long flags);
+	void            (*hpte_updateboltedpp)(unsigned long newpp,
+					       unsigned long ea,
+					       int psize, int ssize);
+	long		(*hpte_insert)(unsigned long hpte_group,
+				       unsigned long vpn,
+				       unsigned long prpn,
+				       unsigned long rflags,
+				       unsigned long vflags,
+				       int psize, int apsize,
+				       int ssize);
+	long		(*hpte_remove)(unsigned long hpte_group);
+	int             (*hpte_removebolted)(unsigned long ea,
+					     int psize, int ssize);
+	void		(*flush_hash_range)(unsigned long number, int local);
+	void		(*hugepage_invalidate)(unsigned long vsid,
+					       unsigned long addr,
+					       unsigned char *hpte_slot_array,
+					       int psize, int ssize, int local);
+	/*
+	 * Special for kexec.
+	 * To be called in real mode with interrupts disabled. No locks are
+	 * taken as such, concurrent access on pre POWER5 hardware could result
+	 * in a deadlock.
+	 * The linear mapping is destroyed as well.
+	 */
+	void		(*hpte_clear_all)(void);
+};
+extern struct mmu_hash_ops mmu_hash_ops;
+
 struct hash_pte {
 	__be64 v;
 	__be64 r;
@@ -352,10 +391,13 @@ int htab_remove_mapping(unsigned long vstart, unsigned long vend,
 extern void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
 extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
 
+#ifdef CONFIG_PPC_PSERIES
+void hpte_init_pseries(void);
+#else
+static inline void hpte_init_pseries(void) { }
+#endif
+
 extern void hpte_init_native(void);
-extern void hpte_init_lpar(void);
-extern void hpte_init_beat(void);
-extern void hpte_init_beat_v3(void);
 
 extern void slb_initialize(void);
 extern void slb_flush_and_rebolt(void);
@@ -435,7 +477,7 @@ extern void slb_set_size(u16 size);
  * function.  Used in slb_allocate() and do_stab_bolted.  The function
  * computed is: (protovsid*VSID_MULTIPLIER) % VSID_MODULUS
  *
- *	rt = register continaing the proto-VSID and into which the
+ *	rt = register containing the proto-VSID and into which the
  *		VSID will be stored
  *	rx = scratch register (clobbered)
  *
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 5854263d4d6e..d4eda6420523 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -23,7 +23,12 @@ struct mmu_psize_def {
 };
 extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
 
+#ifdef CONFIG_PPC_RADIX_MMU
 #define radix_enabled() mmu_has_feature(MMU_FTR_RADIX)
+#else
+#define radix_enabled() (0)
+#endif
+
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
index 71e9abced493..9db83b4e017d 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
@@ -11,7 +11,7 @@ static inline int pmd_huge(pmd_t pmd)
 	 * leaf pte for huge page
 	 */
 	if (radix_enabled())
-		return !!(pmd_val(pmd) & _PAGE_PTE);
+		return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
 	return 0;
 }
 
@@ -21,7 +21,7 @@ static inline int pud_huge(pud_t pud)
 	 * leaf pte for huge page
 	 */
 	if (radix_enabled())
-		return !!(pud_val(pud) & _PAGE_PTE);
+		return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
 	return 0;
 }
 
@@ -31,7 +31,7 @@ static inline int pgd_huge(pgd_t pgd)
 	 * leaf pte for huge page
 	 */
 	if (radix_enabled())
-		return !!(pgd_val(pgd) & _PAGE_PTE);
+		return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE));
 	return 0;
 }
 #define pgd_huge pgd_huge
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
index cb2d0a5fa3f8..0d2845b44763 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
@@ -15,7 +15,7 @@ static inline int pmd_huge(pmd_t pmd)
 	/*
 	 * leaf pte for huge page
 	 */
-	return !!(pmd_val(pmd) & _PAGE_PTE);
+	return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
 }
 
 static inline int pud_huge(pud_t pud)
@@ -23,7 +23,7 @@ static inline int pud_huge(pud_t pud)
 	/*
 	 * leaf pte for huge page
 	 */
-	return !!(pud_val(pud) & _PAGE_PTE);
+	return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
 }
 
 static inline int pgd_huge(pgd_t pgd)
@@ -31,7 +31,7 @@ static inline int pgd_huge(pgd_t pgd)
 	/*
 	 * leaf pte for huge page
 	 */
-	return !!(pgd_val(pgd) & _PAGE_PTE);
+	return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE));
 }
 #define pgd_huge pgd_huge
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index ab84c89c9e98..263bf39ced40 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -318,7 +318,7 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 {
 	unsigned long old;
 
-	if ((pte_val(*ptep) & (_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
+	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
 		return 0;
 	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
 	return (old & _PAGE_ACCESSED) != 0;
@@ -336,8 +336,7 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-
-	if ((pte_val(*ptep) & _PAGE_WRITE) == 0)
+	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
 		return;
 
 	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
@@ -346,7 +345,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	if ((pte_val(*ptep) & _PAGE_WRITE) == 0)
+	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
 		return;
 
 	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
@@ -365,17 +364,35 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
 {
 	pte_update(mm, addr, ptep, ~0UL, 0, 0);
 }
-static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_WRITE);}
-static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
-static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
-static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
+
+static inline int pte_write(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
+}
+
+static inline int pte_dirty(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY));
+}
+
+static inline int pte_young(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_ACCESSED));
+}
+
+static inline int pte_special(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SPECIAL));
+}
+
 static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline bool pte_soft_dirty(pte_t pte)
 {
-	return !!(pte_val(pte) & _PAGE_SOFT_DIRTY);
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SOFT_DIRTY));
 }
+
 static inline pte_t pte_mksoft_dirty(pte_t pte)
 {
 	return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY);
@@ -395,14 +412,14 @@ static inline pte_t pte_clear_soft_dirty(pte_t pte)
  */
 static inline int pte_protnone(pte_t pte)
 {
-	return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PRIVILEGED)) ==
-		(_PAGE_PRESENT | _PAGE_PRIVILEGED);
+	return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED)) ==
+		cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED);
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
 static inline int pte_present(pte_t pte)
 {
-	return !!(pte_val(pte) & _PAGE_PRESENT);
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT));
 }
 /*
  * Conversion functions: convert a page and protection to a page entry,
@@ -474,7 +491,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 static inline bool pte_user(pte_t pte)
 {
-	return !(pte_val(pte) & _PAGE_PRIVILEGED);
+	return !(pte_raw(pte) & cpu_to_be64(_PAGE_PRIVILEGED));
 }
 
 /* Encode and de-code a swap entry */
@@ -517,10 +534,12 @@ static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
 {
 	return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY);
 }
+
 static inline bool pte_swp_soft_dirty(pte_t pte)
 {
-	return !!(pte_val(pte) & _PAGE_SWP_SOFT_DIRTY);
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_SOFT_DIRTY));
 }
+
 static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 {
 	return __pte(pte_val(pte) & ~_PAGE_SWP_SOFT_DIRTY);
@@ -626,8 +645,16 @@ static inline void pmd_clear(pmd_t *pmdp)
 	*pmdp = __pmd(0);
 }
 
-#define pmd_none(pmd)		(!pmd_val(pmd))
-#define	pmd_present(pmd)	(!pmd_none(pmd))
+static inline int pmd_none(pmd_t pmd)
+{
+	return !pmd_raw(pmd);
+}
+
+static inline int pmd_present(pmd_t pmd)
+{
+
+	return !pmd_none(pmd);
+}
 
 static inline int pmd_bad(pmd_t pmd)
 {
@@ -646,19 +673,26 @@ static inline void pud_clear(pud_t *pudp)
 	*pudp = __pud(0);
 }
 
-#define pud_none(pud)		(!pud_val(pud))
-#define pud_present(pud)	(pud_val(pud) != 0)
+static inline int pud_none(pud_t pud)
+{
+	return !pud_raw(pud);
+}
+
+static inline int pud_present(pud_t pud)
+{
+	return !pud_none(pud);
+}
 
 extern struct page *pud_page(pud_t pud);
 extern struct page *pmd_page(pmd_t pmd);
 static inline pte_t pud_pte(pud_t pud)
 {
-	return __pte(pud_val(pud));
+	return __pte_raw(pud_raw(pud));
 }
 
 static inline pud_t pte_pud(pte_t pte)
 {
-	return __pud(pte_val(pte));
+	return __pud_raw(pte_raw(pte));
 }
 #define pud_write(pud)		pte_write(pud_pte(pud))
 
@@ -681,17 +715,24 @@ static inline void pgd_clear(pgd_t *pgdp)
 	*pgdp = __pgd(0);
 }
 
-#define pgd_none(pgd)		(!pgd_val(pgd))
-#define pgd_present(pgd)	(!pgd_none(pgd))
+static inline int pgd_none(pgd_t pgd)
+{
+	return !pgd_raw(pgd);
+}
+
+static inline int pgd_present(pgd_t pgd)
+{
+	return !pgd_none(pgd);
+}
 
 static inline pte_t pgd_pte(pgd_t pgd)
 {
-	return __pte(pgd_val(pgd));
+	return __pte_raw(pgd_raw(pgd));
 }
 
 static inline pgd_t pte_pgd(pte_t pte)
 {
-	return __pgd(pte_val(pte));
+	return __pgd_raw(pte_raw(pte));
 }
 
 static inline int pgd_bad(pgd_t pgd)
@@ -783,12 +824,12 @@ struct page *realmode_pfn_to_page(unsigned long pfn);
 
 static inline pte_t pmd_pte(pmd_t pmd)
 {
-	return __pte(pmd_val(pmd));
+	return __pte_raw(pmd_raw(pmd));
 }
 
 static inline pmd_t pte_pmd(pte_t pte)
 {
-	return __pmd(pte_val(pte));
+	return __pmd_raw(pte_raw(pte));
 }
 
 static inline pte_t *pmdp_ptep(pmd_t *pmd)
@@ -849,7 +890,7 @@ pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp,
 
 static inline int pmd_large(pmd_t pmd)
 {
-	return !!(pmd_val(pmd) & _PAGE_PTE);
+	return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
 }
 
 static inline pmd_t pmd_mknotpresent(pmd_t pmd)
@@ -865,7 +906,7 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 {
 	unsigned long old;
 
-	if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
+	if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
 		return 0;
 	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
 	return ((old & _PAGE_ACCESSED) != 0);
@@ -876,7 +917,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pmd_t *pmdp)
 {
 
-	if ((pmd_val(*pmdp) & _PAGE_WRITE) == 0)
+	if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_WRITE)) == 0)
 		return;
 
 	pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 3fa94fcac628..00703e7e4c94 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -32,5 +32,7 @@ extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 #define radix___flush_tlb_page(mm,addr,p,i)	radix___local_flush_tlb_page(mm,addr,p,i)
 #define radix__flush_tlb_pwc(tlb, addr)	radix__local_flush_tlb_pwc(tlb, addr)
 #endif
-
+extern void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
+				     unsigned long page_size);
+extern void radix__flush_tlb_lpid(unsigned long lpid);
 #endif
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 994c60a857ce..2015b072422c 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -49,8 +49,7 @@ void __patch_exception(int exc, unsigned long addr);
 
 static inline unsigned long ppc_function_entry(void *func)
 {
-#if defined(CONFIG_PPC64)
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 	u32 *insn = func;
 
 	/*
@@ -75,14 +74,13 @@ static inline unsigned long ppc_function_entry(void *func)
 		return (unsigned long)(insn + 2);
 	else
 		return (unsigned long)func;
-#else
+#elif defined(PPC64_ELF_ABI_v1)
 	/*
 	 * On PPC64 ABIv1 the function pointer actually points to the
 	 * function's descriptor. The first entry in the descriptor is the
 	 * address of the function text.
 	 */
 	return ((func_descr_t *)func)->entry;
-#endif
 #else
 	return (unsigned long)func;
 #endif
@@ -90,7 +88,7 @@ static inline unsigned long ppc_function_entry(void *func)
 
 static inline unsigned long ppc_global_function_entry(void *func)
 {
-#if defined(CONFIG_PPC64) && defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 	/* PPC64 ABIv2 the global entry point is at the address */
 	return (unsigned long)func;
 #else
@@ -106,7 +104,7 @@ static inline unsigned long ppc_global_function_entry(void *func)
  */
 
 /* This must match the definition of STK_GOT in <asm/ppc_asm.h> */
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 #define R2_STACK_OFFSET         24
 #else
 #define R2_STACK_OFFSET         40
diff --git a/arch/powerpc/include/asm/cpufeature.h b/arch/powerpc/include/asm/cpufeature.h
new file mode 100644
index 000000000000..19e6290699ea
--- /dev/null
+++ b/arch/powerpc/include/asm/cpufeature.h
@@ -0,0 +1,40 @@
+/*
+ * CPU feature definitions for module loading, used by
+ * module_cpu_feature_match(), see asm/cputable.h for powerpc CPU features.
+ *
+ * Copyright 2016 Alastair D'Silva, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __ASM_POWERPC_CPUFEATURE_H
+#define __ASM_POWERPC_CPUFEATURE_H
+
+#include <asm/cputable.h>
+
+/* Keep these in step with powerpc/include/asm/cputable.h */
+#define MAX_CPU_FEATURES (2 * 32)
+
+/*
+ * Currently we don't have a need for any of the feature bits defined in
+ * cpu_user_features. When we do, they should be defined such as:
+ *
+ * #define PPC_MODULE_FEATURE_32 (ilog2(PPC_FEATURE_32))
+ */
+
+#define PPC_MODULE_FEATURE_VEC_CRYPTO			(32 + ilog2(PPC_FEATURE2_VEC_CRYPTO))
+
+#define cpu_feature(x)		(x)
+
+static inline bool cpu_have_feature(unsigned int num)
+{
+	if (num < 32)
+		return !!(cur_cpu_spec->cpu_user_features & 1UL << num);
+	else
+		return !!(cur_cpu_spec->cpu_user_features2 & 1UL << (num - 32));
+}
+
+#endif /* __ASM_POWERPC_CPUFEATURE_H */
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index d2f99ca1e3a6..3d7fc06532a1 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -13,6 +13,8 @@
 #ifndef __ASSEMBLY__
 extern u32 pnv_fastsleep_workaround_at_entry[];
 extern u32 pnv_fastsleep_workaround_at_exit[];
+
+extern u64 pnv_first_deep_stop_state;
 #endif
 
 #endif
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index e2452550bcb1..2dfd4fc41f3e 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -90,11 +90,10 @@ static inline void setup_cputime_one_jiffy(void)
 static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
 {
 	u64 ct;
-	u64 sec;
+	u64 sec = jif;
 
 	/* have to be a little careful about overflow */
-	ct = jif % HZ;
-	sec = jif / HZ;
+	ct = do_div(sec, HZ);
 	if (ct) {
 		ct *= tb_ticks_per_sec;
 		do_div(ct, HZ);
@@ -230,7 +229,16 @@ static inline cputime_t clock_t_to_cputime(const unsigned long clk)
 
 #define cputime64_to_clock_t(ct)	cputime_to_clock_t((cputime_t)(ct))
 
+/*
+ * PPC64 uses PACA which is task independent for storing accounting data while
+ * PPC32 uses struct thread_info, therefore at task switch the accounting data
+ * has to be populated in the new task
+ */
+#ifdef CONFIG_PPC64
 static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
+#else
+void arch_vtime_task_switch(struct task_struct *tsk);
+#endif
 
 #endif /* __KERNEL__ */
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index fb9f376ae27b..8e37b71674f4 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -57,7 +57,7 @@ struct pci_dn;
 /*
  * The struct is used to trace PE related EEH functionality.
  * In theory, there will have one instance of the struct to
- * be created against particular PE. In nature, PEs corelate
+ * be created against particular PE. In nature, PEs correlate
  * to each other. the struct has to reflect that hierarchy in
  * order to easily pick up those affected PEs when one particular
  * PE has EEH errors.
@@ -274,7 +274,7 @@ void eeh_pe_restore_bars(struct eeh_pe *pe);
 const char *eeh_pe_loc_get(struct eeh_pe *pe);
 struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe);
 
-void *eeh_dev_init(struct pci_dn *pdn, void *data);
+struct eeh_dev *eeh_dev_init(struct pci_dn *pdn);
 void eeh_dev_phb_init_dynamic(struct pci_controller *phb);
 int eeh_init(void);
 int __init eeh_ops_register(struct eeh_ops *ops);
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 93ae809fe5ea..bed66e5743b3 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -287,7 +287,7 @@ do_kvm_##n:								\
 	std	r0,GPR0(r1);		/* save r0 in stackframe	*/ \
 	std	r10,GPR1(r1);		/* save r1 in stackframe	*/ \
 	beq	4f;			/* if from kernel mode		*/ \
-	ACCOUNT_CPU_USER_ENTRY(r9, r10);				   \
+	ACCOUNT_CPU_USER_ENTRY(r13, r9, r10);				   \
 	SAVE_PPR(area, r9, r10);					   \
 4:	EXCEPTION_PROLOG_COMMON_2(area)					   \
 	EXCEPTION_PROLOG_COMMON_3(n)					   \
@@ -403,6 +403,8 @@ label##_relon_hv:						\
 #define SOFTEN_VALUE_0xe82	PACA_IRQ_DBELL
 #define SOFTEN_VALUE_0xe60	PACA_IRQ_HMI
 #define SOFTEN_VALUE_0xe62	PACA_IRQ_HMI
+#define SOFTEN_VALUE_0xea0	PACA_IRQ_EE
+#define SOFTEN_VALUE_0xea2	PACA_IRQ_EE
 
 #define __SOFTEN_TEST(h, vec)						\
 	lbz	r10,PACASOFTIRQEN(r13);					\
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 9a67a38bf7b9..57fec8ac7b92 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -184,4 +184,8 @@ label##3:					       	\
 	FTR_ENTRY_OFFSET label##1b-label##3b;		\
 	.popsection;
 
+#ifndef __ASSEMBLY__
+void apply_feature_fixups(void);
+#endif
+
 #endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index b0629249778b..1e0b5a5d660a 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -126,6 +126,12 @@ extern int fwnmi_active;
 
 extern unsigned int __start___fw_ftr_fixup, __stop___fw_ftr_fixup;
 
+#ifdef CONFIG_PPC_PSERIES
+void pseries_probe_fw_features(void);
+#else
+static inline void pseries_probe_fw_features(void) { };
+#endif
+
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_FIRMWARE_H */
diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h
index 90f604bbcd19..4508b322f2cd 100644
--- a/arch/powerpc/include/asm/fixmap.h
+++ b/arch/powerpc/include/asm/fixmap.h
@@ -51,6 +51,13 @@ enum fixed_addresses {
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
 #endif
+#ifdef CONFIG_PPC_8xx
+	/* For IMMR we need an aligned 512K area */
+#define FIX_IMMR_SIZE	(512 * 1024 / PAGE_SIZE)
+	FIX_IMMR_START,
+	FIX_IMMR_BASE = __ALIGN_MASK(FIX_IMMR_START, FIX_IMMR_SIZE - 1) - 1 +
+		       FIX_IMMR_SIZE,
+#endif
 	/* FIX_PCIE_MCFG, */
 	__end_of_fixed_addresses
 };
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 50ca7585abe2..686c5f70eb84 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_POWERPC_FTRACE
 #define _ASM_POWERPC_FTRACE
 
+#include <asm/types.h>
+
 #ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR		((unsigned long)(_mcount))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
@@ -65,8 +67,8 @@ struct dyn_arch_ftrace {
 #endif
 #endif
 
-#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__)
-#if !defined(_CALL_ELF) || _CALL_ELF != 2
+#if defined(CONFIG_FTRACE_SYSCALLS) && !defined(__ASSEMBLY__)
+#ifdef PPC64_ELF_ABI_v1
 #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
 static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
 {
@@ -79,6 +81,6 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name
 	return !strcmp(sym + 4, name + 3);
 }
 #endif
-#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 && !__ASSEMBLY__ */
+#endif /* CONFIG_FTRACE_SYSCALLS && !__ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_FTRACE */
diff --git a/arch/powerpc/include/asm/hmi.h b/arch/powerpc/include/asm/hmi.h
new file mode 100644
index 000000000000..88b4901ac4ee
--- /dev/null
+++ b/arch/powerpc/include/asm/hmi.h
@@ -0,0 +1,45 @@
+/*
+ * Hypervisor Maintenance Interrupt header file.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.
+ *
+ * Copyright 2015 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#ifndef __ASM_PPC64_HMI_H__
+#define __ASM_PPC64_HMI_H__
+
+#ifdef CONFIG_PPC_BOOK3S_64
+
+#define	CORE_TB_RESYNC_REQ_BIT		63
+#define MAX_SUBCORE_PER_CORE		4
+
+/*
+ * sibling_subcore_state structure is used to co-ordinate all threads
+ * during HMI to avoid TB corruption. This structure is allocated once
+ * per each core and shared by all threads on that core.
+ */
+struct sibling_subcore_state {
+	unsigned long	flags;
+	u8		in_guest[MAX_SUBCORE_PER_CORE];
+};
+
+extern void wait_for_subcore_guest_exit(void);
+extern void wait_for_tb_resync(void);
+#else
+static inline void wait_for_subcore_guest_exit(void) { }
+static inline void wait_for_tb_resync(void) { }
+#endif
+#endif /* __ASM_PPC64_HMI_H__ */
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 0bc9c284aa10..708edebcf147 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -431,17 +431,6 @@ static inline unsigned long cmo_get_page_size(void)
 {
 	return CMO_PageSize;
 }
-
-extern long pSeries_enable_reloc_on_exc(void);
-extern long pSeries_disable_reloc_on_exc(void);
-
-extern long pseries_big_endian_exceptions(void);
-
-#else
-
-#define pSeries_enable_reloc_on_exc()  do {} while (0)
-#define pSeries_disable_reloc_on_exc() do {} while (0)
-
 #endif /* CONFIG_PPC_PSERIES */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index b59ac27a6b7d..c7d82ff62a33 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -130,6 +130,8 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
 
 extern bool prep_irq_for_idle(void);
 
+extern void force_external_irq_replay(void);
+
 #else /* CONFIG_PPC64 */
 
 #define SET_MSR_EE(x)	mtmsr(x)
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 7b87bab09564..f49a72a9062d 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -273,7 +273,6 @@ extern void iommu_init_early_pSeries(void);
 extern void iommu_init_early_dart(struct pci_controller_ops *controller_ops);
 extern void iommu_init_early_pasemi(void);
 
-extern void alloc_dart_table(void);
 #if defined(CONFIG_PPC64) && defined(CONFIG_PM)
 static inline void iommu_save(void)
 {
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index 039b583db029..2c9759bdb63b 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -40,8 +40,7 @@ struct kprobe;
 typedef ppc_opcode_t kprobe_opcode_t;
 #define MAX_INSN_SIZE 1
 
-#ifdef CONFIG_PPC64
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 /* PPC64 ABIv2 needs local entry point */
 #define kprobe_lookup_name(name, addr)					\
 {									\
@@ -49,7 +48,7 @@ typedef ppc_opcode_t kprobe_opcode_t;
 	if (addr)							\
 		addr = (kprobe_opcode_t *)ppc_function_entry(addr);	\
 }
-#else
+#elif defined(PPC64_ELF_ABI_v1)
 /*
  * 64bit powerpc ABIv1 uses function descriptors:
  * - Check for the dot variant of the symbol first.
@@ -92,8 +91,7 @@ typedef ppc_opcode_t kprobe_opcode_t;
 		addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);	\
 	}								\
 }
-#endif /* defined(_CALL_ELF) && _CALL_ELF == 2 */
-#endif /* CONFIG_PPC64 */
+#endif
 
 #define flush_insn_slot(p)	do { } while (0)
 #define kretprobe_blacklist_size 0
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 72b6225aca73..d318d432caa9 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -162,7 +162,7 @@ struct kvmppc_book3s_shadow_vcpu {
 
 /* Values for kvm_state */
 #define KVM_HWTHREAD_IN_KERNEL	0
-#define KVM_HWTHREAD_IN_NAP	1
+#define KVM_HWTHREAD_IN_IDLE	1
 #define KVM_HWTHREAD_IN_KVM	2
 
 #endif /* __ASM_KVM_BOOK3S_ASM_H__ */
diff --git a/arch/powerpc/include/asm/linkage.h b/arch/powerpc/include/asm/linkage.h
index e3ad5c72724a..0cf5e21179fc 100644
--- a/arch/powerpc/include/asm/linkage.h
+++ b/arch/powerpc/include/asm/linkage.h
@@ -1,8 +1,9 @@
 #ifndef _ASM_POWERPC_LINKAGE_H
 #define _ASM_POWERPC_LINKAGE_H
 
-#ifdef CONFIG_PPC64
-#if !defined(_CALL_ELF) || _CALL_ELF != 2
+#include <asm/types.h>
+
+#ifdef PPC64_ELF_ABI_v1
 #define cond_syscall(x) \
 	asm ("\t.weak " #x "\n\t.set " #x ", sys_ni_syscall\n"		\
 	     "\t.weak ." #x "\n\t.set ." #x ", .sys_ni_syscall\n")
@@ -10,6 +11,5 @@
 	asm ("\t.globl " #alias "\n\t.set " #alias ", " #name "\n"	\
 	     "\t.globl ." #alias "\n\t.set ." #alias ", ." #name)
 #endif
-#endif
 
 #endif	/* _ASM_POWERPC_LINKAGE_H */
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 6bdcd0da9e21..76f5398e7152 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -34,42 +34,6 @@ struct pci_host_bridge;
 struct machdep_calls {
 	char		*name;
 #ifdef CONFIG_PPC64
-	void            (*hpte_invalidate)(unsigned long slot,
-					   unsigned long vpn,
-					   int bpsize, int apsize,
-					   int ssize, int local);
-	long		(*hpte_updatepp)(unsigned long slot, 
-					 unsigned long newpp, 
-					 unsigned long vpn,
-					 int bpsize, int apsize,
-					 int ssize, unsigned long flags);
-	void            (*hpte_updateboltedpp)(unsigned long newpp, 
-					       unsigned long ea,
-					       int psize, int ssize);
-	long		(*hpte_insert)(unsigned long hpte_group,
-				       unsigned long vpn,
-				       unsigned long prpn,
-				       unsigned long rflags,
-				       unsigned long vflags,
-				       int psize, int apsize,
-				       int ssize);
-	long		(*hpte_remove)(unsigned long hpte_group);
-	int             (*hpte_removebolted)(unsigned long ea,
-					     int psize, int ssize);
-	void		(*flush_hash_range)(unsigned long number, int local);
-	void		(*hugepage_invalidate)(unsigned long vsid,
-					       unsigned long addr,
-					       unsigned char *hpte_slot_array,
-					       int psize, int ssize, int local);
-	/*
-	 * Special for kexec.
-	 * To be called in real mode with interrupts disabled. No locks are
-	 * taken as such, concurrent access on pre POWER5 hardware could result
-	 * in a deadlock.
-	 * The linear mapping is destroyed as well.
-	 */
-	void		(*hpte_clear_all)(void);
-
 	void __iomem *	(*ioremap)(phys_addr_t addr, unsigned long size,
 				   unsigned long flags, void *caller);
 	void		(*iounmap)(volatile void __iomem *token);
@@ -89,7 +53,6 @@ struct machdep_calls {
 
 	int		(*probe)(void);
 	void		(*setup_arch)(void); /* Optional, may be NULL */
-	void		(*init_early)(void);
 	/* Optional, may be NULL. */
 	void		(*show_cpuinfo)(struct seq_file *m);
 	void		(*show_percpuinfo)(struct seq_file *m, int i);
@@ -111,8 +74,8 @@ struct machdep_calls {
 	/* To setup PHBs when using automatic OF platform driver for PCI */
 	int		(*pci_setup_phb)(struct pci_controller *host);
 
-	void		(*restart)(char *cmd);
-	void		(*halt)(void);
+	void __noreturn	(*restart)(char *cmd);
+	void __noreturn (*halt)(void);
 	void		(*panic)(char *str);
 	void		(*cpu_die)(void);
 
@@ -256,7 +219,8 @@ struct machdep_calls {
 #ifdef CONFIG_ARCH_RANDOM
 	int (*get_random_seed)(unsigned long *v);
 #endif
-	int (*update_partition_table)(u64);
+	int (*register_process_table)(unsigned long base, unsigned long page_size,
+				      unsigned long tbl_size);
 };
 
 extern void e500_idle(void);
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 2563c435a4b1..fc420cedecae 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -31,13 +31,13 @@ static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
 }
 #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
 
-static inline int arch_validate_prot(unsigned long prot)
+static inline bool arch_validate_prot(unsigned long prot)
 {
 	if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO))
-		return 0;
+		return false;
 	if ((prot & PROT_SAO) && !cpu_has_feature(CPU_FTR_SAO))
-		return 0;
-	return 1;
+		return false;
+	return true;
 }
 #define arch_validate_prot(prot) arch_validate_prot(prot)
 
diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index 0a566f15f985..3e0e4927811c 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -169,6 +169,9 @@ typedef struct {
 	unsigned int active;
 	unsigned long vdso_base;
 } mm_context_t;
+
+#define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000)
+#define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE))
 #endif /* !__ASSEMBLY__ */
 
 #if defined(CONFIG_PPC_4K_PAGES)
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index e53ebebff474..54471228f7b8 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -24,6 +24,11 @@
 /*
  * This is individual features
  */
+/*
+ * We need to clear top 16bits of va (from the remaining 64 bits )in
+ * tlbie* instructions
+ */
+#define MMU_FTR_TLBIE_CROP_VA		ASM_CONST(0x00008000)
 
 /* Enable use of high BAT registers */
 #define MMU_FTR_USE_HIGH_BATS		ASM_CONST(0x00010000)
@@ -97,7 +102,7 @@
 #define MMU_FTRS_DEFAULT_HPTE_ARCH_V2	\
 	MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2
 #define MMU_FTRS_POWER4		MMU_FTRS_DEFAULT_HPTE_ARCH_V2
-#define MMU_FTRS_PPC970		MMU_FTRS_POWER4
+#define MMU_FTRS_PPC970		MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA
 #define MMU_FTRS_POWER5		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
 #define MMU_FTRS_POWER6		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
 #define MMU_FTRS_POWER7		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
@@ -124,7 +129,7 @@ enum {
 		MMU_FTR_USE_TLBRSRV | MMU_FTR_USE_PAIRED_MAS |
 		MMU_FTR_NO_SLBIE_B | MMU_FTR_16M_PAGE | MMU_FTR_TLBIEL |
 		MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE |
-		MMU_FTR_1T_SEGMENT |
+		MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA |
 #ifdef CONFIG_PPC_RADIX_MMU
 		MMU_FTR_RADIX |
 #endif
diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h
index 0acc7c7c28d1..e94cede14522 100644
--- a/arch/powerpc/include/asm/mpc52xx.h
+++ b/arch/powerpc/include/asm/mpc52xx.h
@@ -275,7 +275,7 @@ extern int mpc5200_psc_ac97_gpio_reset(int psc_number);
 extern void mpc52xx_map_common_devices(void);
 extern int mpc52xx_set_psc_clkdiv(int psc_id, int clkdiv);
 extern unsigned int mpc52xx_get_xtal_freq(struct device_node *node);
-extern void mpc52xx_restart(char *cmd);
+extern void __noreturn mpc52xx_restart(char *cmd);
 
 /* mpc52xx_gpt.c */
 struct mpc52xx_gpt_priv;
diff --git a/arch/powerpc/include/asm/nohash/32/pte-44x.h b/arch/powerpc/include/asm/nohash/32/pte-44x.h
index fdab41c654ef..0656ff81e5b0 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-44x.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-44x.h
@@ -32,7 +32,7 @@
  *   -  -  -  -  -    - U0 U1 U2 U3 W  I  M  G  E   - UX UW UR SX SW SR
  *
  * Newer 440 cores (440x6 as used on AMCC 460EX/460GT) have additional
- * TLB2 storage attibute fields. Those are:
+ * TLB2 storage attribute fields. Those are:
  *
  *   TLB2:
  *   0...10    11   12   13   14   15   16...31
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
index 570fb30be21c..908324574f77 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
@@ -23,6 +23,7 @@
 #ifndef __ASSEMBLY__
 #define PTE_TABLE_SIZE	PTE_FRAG_SIZE
 #define PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
+#define PUD_TABLE_SIZE	(0)
 #define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index 9bb8ddf0be37..0e2e57bcab50 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -158,17 +158,33 @@
 #define OPAL_LEDS_SET_INDICATOR			115
 #define OPAL_CEC_REBOOT2			116
 #define OPAL_CONSOLE_FLUSH			117
-#define OPAL_LAST				117
+#define OPAL_GET_DEVICE_TREE			118
+#define OPAL_PCI_GET_PRESENCE_STATE		119
+#define OPAL_PCI_GET_POWER_STATE		120
+#define OPAL_PCI_SET_POWER_STATE		121
+#define OPAL_INT_GET_XIRR			122
+#define	OPAL_INT_SET_CPPR			123
+#define OPAL_INT_EOI				124
+#define OPAL_INT_SET_MFRR			125
+#define OPAL_PCI_TCE_KILL			126
+#define OPAL_LAST				126
 
 /* Device tree flags */
 
-/* Flags set in power-mgmt nodes in device tree if
- * respective idle states are supported in the platform.
+/*
+ * Flags set in power-mgmt nodes in device tree describing
+ * idle states that are supported in the platform.
  */
+
+#define OPAL_PM_TIMEBASE_STOP		0x00000002
+#define OPAL_PM_LOSE_HYP_CONTEXT	0x00002000
+#define OPAL_PM_LOSE_FULL_CONTEXT	0x00004000
 #define OPAL_PM_NAP_ENABLED		0x00010000
 #define OPAL_PM_SLEEP_ENABLED		0x00020000
 #define OPAL_PM_WINKLE_ENABLED		0x00040000
 #define OPAL_PM_SLEEP_ENABLED_ER1	0x00080000 /* with workaround */
+#define OPAL_PM_STOP_INST_FAST		0x00100000
+#define OPAL_PM_STOP_INST_DEEP		0x00200000
 
 /*
  * OPAL_CONFIG_CPU_IDLE_STATE parameters
@@ -344,6 +360,18 @@ enum OpalPciResetState {
 	OPAL_ASSERT_RESET   = 1
 };
 
+enum OpalPciSlotPresence {
+	OPAL_PCI_SLOT_EMPTY	= 0,
+	OPAL_PCI_SLOT_PRESENT	= 1
+};
+
+enum OpalPciSlotPower {
+	OPAL_PCI_SLOT_POWER_OFF	= 0,
+	OPAL_PCI_SLOT_POWER_ON	= 1,
+	OPAL_PCI_SLOT_OFFLINE	= 2,
+	OPAL_PCI_SLOT_ONLINE	= 3
+};
+
 enum OpalSlotLedType {
 	OPAL_SLOT_LED_TYPE_ID = 0,	/* IDENTIFY LED */
 	OPAL_SLOT_LED_TYPE_FAULT = 1,	/* FAULT LED */
@@ -802,7 +830,7 @@ struct opal_sg_entry {
 };
 
 /*
- * Candiate image SG list.
+ * Candidate image SG list.
  *
  * length = VER | length
  */
@@ -825,6 +853,7 @@ enum {
 	OPAL_PHB_CAPI_MODE_CAPI		= 1,
 	OPAL_PHB_CAPI_MODE_SNOOP_OFF    = 2,
 	OPAL_PHB_CAPI_MODE_SNOOP_ON	= 3,
+	OPAL_PHB_CAPI_MODE_DMA		= 4,
 };
 
 /* OPAL I2C request */
@@ -852,7 +881,7 @@ struct opal_i2c_request {
  * with individual elements being 16 bits wide to fetch the system
  * wide EPOW status. Each element in the buffer will contain the
  * EPOW status in it's bit representation for a particular EPOW sub
- * class as defiend here. So multiple detailed EPOW status bits
+ * class as defined here. So multiple detailed EPOW status bits
  * specific for any sub class can be represented in a single buffer
  * element as it's bit representation.
  */
@@ -891,6 +920,13 @@ enum {
 	OPAL_REBOOT_PLATFORM_ERROR	= 1,
 };
 
+/* Argument to OPAL_PCI_TCE_KILL */
+enum {
+	OPAL_PCI_TCE_KILL_PAGES,
+	OPAL_PCI_TCE_KILL_PE,
+	OPAL_PCI_TCE_KILL_ALL,
+};
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __OPAL_API_H */
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 9d86c6651716..ee05bd203630 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -131,7 +131,7 @@ int64_t opal_pci_map_pe_dma_window(uint64_t phb_id, uint16_t pe_number, uint16_t
 int64_t opal_pci_map_pe_dma_window_real(uint64_t phb_id, uint16_t pe_number,
 					uint16_t dma_window_number, uint64_t pci_start_addr,
 					uint64_t pci_mem_size);
-int64_t opal_pci_reset(uint64_t phb_id, uint8_t reset_scope, uint8_t assert_state);
+int64_t opal_pci_reset(uint64_t id, uint8_t reset_scope, uint8_t assert_state);
 
 int64_t opal_pci_get_hub_diag_data(uint64_t hub_id, void *diag_buffer,
 				   uint64_t diag_buffer_len);
@@ -148,7 +148,7 @@ int64_t opal_get_dpo_status(__be64 *dpo_timeout);
 int64_t opal_set_system_attention_led(uint8_t led_action);
 int64_t opal_pci_next_error(uint64_t phb_id, __be64 *first_frozen_pe,
 			    __be16 *pci_error_type, __be16 *severity);
-int64_t opal_pci_poll(uint64_t phb_id);
+int64_t opal_pci_poll(uint64_t id);
 int64_t opal_return_cpu(void);
 int64_t opal_check_token(uint64_t token);
 int64_t opal_reinit_cpus(uint64_t flags);
@@ -178,6 +178,8 @@ int64_t opal_dump_ack(uint32_t dump_id);
 int64_t opal_dump_resend_notification(void);
 
 int64_t opal_get_msg(uint64_t buffer, uint64_t size);
+int64_t opal_write_oppanel_async(uint64_t token, oppanel_line_t *lines,
+					uint64_t num_lines);
 int64_t opal_check_completion(uint64_t buffer, uint64_t size, uint64_t token);
 int64_t opal_sync_host_reboot(void);
 int64_t opal_get_param(uint64_t token, uint32_t param_id, uint64_t buffer,
@@ -209,12 +211,30 @@ int64_t opal_flash_write(uint64_t id, uint64_t offset, uint64_t buf,
 		uint64_t size, uint64_t token);
 int64_t opal_flash_erase(uint64_t id, uint64_t offset, uint64_t size,
 		uint64_t token);
+int64_t opal_get_device_tree(uint32_t phandle, uint64_t buf, uint64_t len);
+int64_t opal_pci_get_presence_state(uint64_t id, uint64_t data);
+int64_t opal_pci_get_power_state(uint64_t id, uint64_t data);
+int64_t opal_pci_set_power_state(uint64_t async_token, uint64_t id,
+				 uint64_t data);
+int64_t opal_pci_poll2(uint64_t id, uint64_t data);
+
+int64_t opal_int_get_xirr(uint32_t *out_xirr, bool just_poll);
+int64_t opal_int_set_cppr(uint8_t cppr);
+int64_t opal_int_eoi(uint32_t xirr);
+int64_t opal_int_set_mfrr(uint32_t cpu, uint8_t mfrr);
+int64_t opal_pci_tce_kill(uint64_t phb_id, uint32_t kill_type,
+			  uint32_t pe_num, uint32_t tce_size,
+			  uint64_t dma_addr, uint32_t npages);
+int64_t opal_rm_pci_tce_kill(uint64_t phb_id, uint32_t kill_type,
+			     uint32_t pe_num, uint32_t tce_size,
+			     uint64_t dma_addr, uint32_t npages);
 
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
 				   int depth, void *data);
 extern int early_init_dt_scan_recoverable_ranges(unsigned long node,
 				 const char *uname, int depth, void *data);
+extern void opal_configure_cores(void);
 
 extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
 extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
@@ -276,6 +296,16 @@ extern int opal_error_code(int rc);
 
 ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count);
 
+static inline int opal_get_async_rc(struct opal_msg msg)
+{
+	if (msg.msg_type != OPAL_MSG_ASYNC_COMP)
+		return OPAL_PARAMETER;
+	else
+		return be64_to_cpu(msg.params[1]);
+}
+
+void opal_wake_poller(void);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_OPAL_H */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 546540b91095..148303e7771f 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -25,6 +25,8 @@
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 #include <asm/kvm_book3s_asm.h>
 #endif
+#include <asm/accounting.h>
+#include <asm/hmi.h>
 
 register struct paca_struct *local_paca asm("r13");
 
@@ -181,16 +183,15 @@ struct paca_struct {
 	 */
 	u16 in_mce;
 	u8 hmi_event_available;		 /* HMI event is available */
+	/*
+	 * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
+	 * more details
+	 */
+	struct sibling_subcore_state *sibling_subcore_state;
 #endif
 
 	/* Stuff for accurate time accounting */
-	u64 user_time;			/* accumulated usermode TB ticks */
-	u64 system_time;		/* accumulated system TB ticks */
-	u64 user_time_scaled;		/* accumulated usermode SPURR ticks */
-	u64 starttime;			/* TB value snapshot */
-	u64 starttime_user;		/* TB value on exit to usermode */
-	u64 startspurr;			/* SPURR value snapshot */
-	u64 utime_sspurr;		/* ->user_time when ->startspurr set */
+	struct cpu_accounting_data accounting;
 	u64 stolen_time;		/* TB ticks taken by hypervisor */
 	u64 dtl_ridx;			/* read index in dispatch log */
 	struct dtl_entry *dtl_curr;	/* pointer corresponding to dtl_ridx */
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 51db3a37bced..56398e7e6100 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -96,7 +96,7 @@ extern unsigned int HPAGE_SHIFT;
 extern phys_addr_t memstart_addr;
 extern phys_addr_t kernstart_addr;
 
-#ifdef CONFIG_RELOCATABLE_PPC32
+#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_PPC32)
 extern long long virt_phys_offset;
 #endif
 
@@ -139,9 +139,9 @@ extern long long virt_phys_offset;
  * determine MEMORY_START until then.  However we can determine PHYSICAL_START
  * from information at hand (program counter, TLB lookup).
  *
- * On BookE with RELOCATABLE (RELOCATABLE_PPC32)
+ * On BookE with RELOCATABLE && PPC32
  *
- *   With RELOCATABLE_PPC32,  we support loading the kernel at any physical 
+ *   With RELOCATABLE && PPC32,  we support loading the kernel at any physical
  *   address without any restriction on the page alignment.
  *
  *   We find the runtime address of _stext and relocate ourselves based on 
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 467c0b05b6fb..b5e88e4a171a 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -33,6 +33,8 @@ struct pci_controller_ops {
 	/* Called during PCI resource reassignment */
 	resource_size_t (*window_alignment)(struct pci_bus *bus,
 					    unsigned long type);
+	void		(*setup_bridge)(struct pci_bus *bus,
+					unsigned long type);
 	void		(*reset_secondary_bus)(struct pci_dev *pdev);
 
 #ifdef CONFIG_PCI_MSI
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index a6f3ac0d4602..e9bd6cf0212f 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -136,9 +136,6 @@ extern pgprot_t	pci_phys_mem_access_prot(struct file *file,
 					 pgprot_t prot);
 
 #define HAVE_ARCH_PCI_RESOURCE_TO_USER
-extern void pci_resource_to_user(const struct pci_dev *dev, int bar,
-				 const struct resource *rsrc,
-				 resource_size_t *start, resource_size_t *end);
 
 extern resource_size_t pcibios_io_space_offset(struct pci_controller *hose);
 extern void pcibios_setup_bus_devices(struct pci_bus *bus);
diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h
index e2bf208605b1..49c0a5a80efa 100644
--- a/arch/powerpc/include/asm/pgtable-be-types.h
+++ b/arch/powerpc/include/asm/pgtable-be-types.h
@@ -6,6 +6,7 @@
 /* PTE level */
 typedef struct { __be64 pte; } pte_t;
 #define __pte(x)	((pte_t) { cpu_to_be64(x) })
+#define __pte_raw(x)	((pte_t) { (x) })
 static inline unsigned long pte_val(pte_t x)
 {
 	return be64_to_cpu(x.pte);
@@ -20,6 +21,7 @@ static inline __be64 pte_raw(pte_t x)
 #ifdef CONFIG_PPC64
 typedef struct { __be64 pmd; } pmd_t;
 #define __pmd(x)	((pmd_t) { cpu_to_be64(x) })
+#define __pmd_raw(x)	((pmd_t) { (x) })
 static inline unsigned long pmd_val(pmd_t x)
 {
 	return be64_to_cpu(x.pmd);
@@ -37,21 +39,34 @@ static inline __be64 pmd_raw(pmd_t x)
 #if defined(CONFIG_PPC_BOOK3S_64) || !defined(CONFIG_PPC_64K_PAGES)
 typedef struct { __be64 pud; } pud_t;
 #define __pud(x)	((pud_t) { cpu_to_be64(x) })
+#define __pud_raw(x)	((pud_t) { (x) })
 static inline unsigned long pud_val(pud_t x)
 {
 	return be64_to_cpu(x.pud);
 }
+
+static inline __be64 pud_raw(pud_t x)
+{
+	return x.pud;
+}
+
 #endif /* CONFIG_PPC_BOOK3S_64 || !CONFIG_PPC_64K_PAGES */
 #endif /* CONFIG_PPC64 */
 
 /* PGD level */
 typedef struct { __be64 pgd; } pgd_t;
 #define __pgd(x)	((pgd_t) { cpu_to_be64(x) })
+#define __pgd_raw(x)	((pgd_t) { (x) })
 static inline unsigned long pgd_val(pgd_t x)
 {
 	return be64_to_cpu(x.pgd);
 }
 
+static inline __be64 pgd_raw(pgd_t x)
+{
+	return x.pgd;
+}
+
 /* Page protection bits */
 typedef struct { unsigned long pgprot; } pgprot_t;
 #define pgprot_val(x)	((x).pgprot)
diff --git a/arch/powerpc/include/asm/pmac_feature.h b/arch/powerpc/include/asm/pmac_feature.h
index 925697968946..e08e829261b6 100644
--- a/arch/powerpc/include/asm/pmac_feature.h
+++ b/arch/powerpc/include/asm/pmac_feature.h
@@ -210,7 +210,7 @@ static inline long pmac_call_feature(int selector, struct device_node* node,
 
 /* PMAC_FTR_SOUND_CHIP_ENABLE	(struct device_node* node, 0, int value)
  * enable/disable the sound chip, whatever it is and provided it can
- * acually be controlled
+ * actually be controlled
  */
 #define PMAC_FTR_SOUND_CHIP_ENABLE	PMAC_FTR_DEF(9)
 
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
index 6f77f71ee964..0cbd8134ce81 100644
--- a/arch/powerpc/include/asm/pnv-pci.h
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -11,7 +11,20 @@
 #define _ASM_PNV_PCI_H
 
 #include <linux/pci.h>
+#include <linux/pci_hotplug.h>
 #include <misc/cxl-base.h>
+#include <asm/opal-api.h>
+
+#define PCI_SLOT_ID_PREFIX	0x8000000000000000
+#define PCI_SLOT_ID(phb_id, bdfn)	\
+	(PCI_SLOT_ID_PREFIX | ((uint64_t)(bdfn) << 16) | (phb_id))
+
+extern int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id);
+extern int pnv_pci_get_device_tree(uint32_t phandle, void *buf, uint64_t len);
+extern int pnv_pci_get_presence_state(uint64_t id, uint8_t *state);
+extern int pnv_pci_get_power_state(uint64_t id, uint8_t *state);
+extern int pnv_pci_set_power_state(uint64_t id, uint8_t state,
+				   struct opal_msg *msg);
 
 int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode);
 int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
@@ -26,6 +39,40 @@ int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
 			       struct pci_dev *dev, int num);
 void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
 				  struct pci_dev *dev);
+
+/* Support for the cxl kernel api on the real PHB (instead of vPHB) */
+int pnv_cxl_enable_phb_kernel_api(struct pci_controller *hose, bool enable);
+bool pnv_pci_on_cxl_phb(struct pci_dev *dev);
+struct cxl_afu *pnv_cxl_phb_to_afu(struct pci_controller *hose);
+void pnv_cxl_phb_set_peer_afu(struct pci_dev *dev, struct cxl_afu *afu);
+
 #endif
 
+struct pnv_php_slot {
+	struct hotplug_slot		slot;
+	struct hotplug_slot_info	slot_info;
+	uint64_t			id;
+	char				*name;
+	int				slot_no;
+	struct kref			kref;
+#define PNV_PHP_STATE_INITIALIZED	0
+#define PNV_PHP_STATE_REGISTERED	1
+#define PNV_PHP_STATE_POPULATED		2
+#define PNV_PHP_STATE_OFFLINE		3
+	int				state;
+	struct device_node		*dn;
+	struct pci_dev			*pdev;
+	struct pci_bus			*bus;
+	bool				power_state_check;
+	void				*fdt;
+	void				*dt;
+	struct of_changeset		ocs;
+	struct pnv_php_slot		*parent;
+	struct list_head		children;
+	struct list_head		link;
+};
+extern struct pnv_php_slot *pnv_php_find_slot(struct device_node *dn);
+extern int pnv_php_set_slot_power_state(struct hotplug_slot *slot,
+					uint8_t state);
+
 #endif
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 49cd8760aa7c..127ebf5862b4 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -131,6 +131,8 @@
 /* sorted alphabetically */
 #define PPC_INST_BHRBE			0x7c00025c
 #define PPC_INST_CLRBHRB		0x7c00035c
+#define PPC_INST_COPY			0x7c00060c
+#define PPC_INST_COPY_FIRST		0x7c20060c
 #define PPC_INST_CP_ABORT		0x7c00068c
 #define PPC_INST_DCBA			0x7c0005ec
 #define PPC_INST_DCBA_MASK		0xfc0007fe
@@ -142,9 +144,11 @@
 #define PPC_INST_ISEL			0x7c00001e
 #define PPC_INST_ISEL_MASK		0xfc00003e
 #define PPC_INST_LDARX			0x7c0000a8
+#define PPC_INST_STDCX			0x7c0001ad
 #define PPC_INST_LSWI			0x7c0004aa
 #define PPC_INST_LSWX			0x7c00042a
 #define PPC_INST_LWARX			0x7c000028
+#define PPC_INST_STWCX			0x7c00012d
 #define PPC_INST_LWSYNC			0x7c2004ac
 #define PPC_INST_SYNC			0x7c0004ac
 #define PPC_INST_SYNC_MASK		0xfc0007fe
@@ -159,6 +163,8 @@
 #define PPC_INST_MSGSNDP		0x7c00011c
 #define PPC_INST_MTTMR			0x7c0003dc
 #define PPC_INST_NOP			0x60000000
+#define PPC_INST_PASTE			0x7c00070c
+#define PPC_INST_PASTE_LAST		0x7c20070d
 #define PPC_INST_POPCNTB		0x7c0000f4
 #define PPC_INST_POPCNTB_MASK		0xfc0007fe
 #define PPC_INST_POPCNTD		0x7c0003f4
@@ -177,6 +183,7 @@
 #define PPC_INST_MFVSRD			0x7c000066
 #define PPC_INST_MTVSRD			0x7c000166
 #define PPC_INST_SLBFEE			0x7c0007a7
+#define PPC_INST_SLBIA			0x7c0003e4
 
 #define PPC_INST_STRING			0x7c00042a
 #define PPC_INST_STRING_MASK		0xfc0007fe
@@ -186,6 +193,7 @@
 #define PPC_INST_STSWX			0x7c00052a
 #define PPC_INST_STXVD2X		0x7c000798
 #define PPC_INST_TLBIE			0x7c000264
+#define PPC_INST_TLBIEL			0x7c000224
 #define PPC_INST_TLBILX			0x7c000024
 #define PPC_INST_WAIT			0x7c00007c
 #define PPC_INST_TLBIVAX		0x7c000624
@@ -203,6 +211,8 @@
 #define PPC_INST_SLEEP			0x4c0003a4
 #define PPC_INST_WINKLE			0x4c0003e4
 
+#define PPC_INST_STOP			0x4c0002e4
+
 /* A2 specific instructions */
 #define PPC_INST_ERATWE			0x7c0001a6
 #define PPC_INST_ERATRE			0x7c000166
@@ -215,8 +225,11 @@
 #define PPC_INST_LBZ			0x88000000
 #define PPC_INST_LD			0xe8000000
 #define PPC_INST_LHZ			0xa0000000
-#define PPC_INST_LHBRX			0x7c00062c
 #define PPC_INST_LWZ			0x80000000
+#define PPC_INST_LHBRX			0x7c00062c
+#define PPC_INST_LDBRX			0x7c000428
+#define PPC_INST_STB			0x98000000
+#define PPC_INST_STH			0xb0000000
 #define PPC_INST_STD			0xf8000000
 #define PPC_INST_STDU			0xf8000001
 #define PPC_INST_STW			0x90000000
@@ -225,22 +238,34 @@
 #define PPC_INST_MTLR			0x7c0803a6
 #define PPC_INST_CMPWI			0x2c000000
 #define PPC_INST_CMPDI			0x2c200000
+#define PPC_INST_CMPW			0x7c000000
+#define PPC_INST_CMPD			0x7c200000
 #define PPC_INST_CMPLW			0x7c000040
+#define PPC_INST_CMPLD			0x7c200040
 #define PPC_INST_CMPLWI			0x28000000
+#define PPC_INST_CMPLDI			0x28200000
 #define PPC_INST_ADDI			0x38000000
 #define PPC_INST_ADDIS			0x3c000000
 #define PPC_INST_ADD			0x7c000214
 #define PPC_INST_SUB			0x7c000050
 #define PPC_INST_BLR			0x4e800020
 #define PPC_INST_BLRL			0x4e800021
+#define PPC_INST_MULLD			0x7c0001d2
 #define PPC_INST_MULLW			0x7c0001d6
 #define PPC_INST_MULHWU			0x7c000016
 #define PPC_INST_MULLI			0x1c000000
 #define PPC_INST_DIVWU			0x7c000396
+#define PPC_INST_DIVD			0x7c0003d2
 #define PPC_INST_RLWINM			0x54000000
+#define PPC_INST_RLWIMI			0x50000000
+#define PPC_INST_RLDICL			0x78000000
 #define PPC_INST_RLDICR			0x78000004
 #define PPC_INST_SLW			0x7c000030
+#define PPC_INST_SLD			0x7c000036
 #define PPC_INST_SRW			0x7c000430
+#define PPC_INST_SRD			0x7c000436
+#define PPC_INST_SRAD			0x7c000634
+#define PPC_INST_SRADI			0x7c000674
 #define PPC_INST_AND			0x7c000038
 #define PPC_INST_ANDDOT			0x7c000039
 #define PPC_INST_OR			0x7c000378
@@ -251,6 +276,7 @@
 #define PPC_INST_XORI			0x68000000
 #define PPC_INST_XORIS			0x6c000000
 #define PPC_INST_NEG			0x7c0000d0
+#define PPC_INST_EXTSW			0x7c0007b4
 #define PPC_INST_BRANCH			0x48000000
 #define PPC_INST_BRANCH_COND		0x40800000
 #define PPC_INST_LBZCIX			0x7c0006aa
@@ -261,6 +287,9 @@
 #define ___PPC_RB(b)	(((b) & 0x1f) << 11)
 #define ___PPC_RS(s)	(((s) & 0x1f) << 21)
 #define ___PPC_RT(t)	___PPC_RS(t)
+#define ___PPC_R(r)	(((r) & 0x1) << 16)
+#define ___PPC_PRS(prs)	(((prs) & 0x1) << 17)
+#define ___PPC_RIC(ric)	(((ric) & 0x3) << 18)
 #define __PPC_RA(a)	___PPC_RA(__REG_##a)
 #define __PPC_RA0(a)	___PPC_RA(__REGA0_##a)
 #define __PPC_RB(b)	___PPC_RB(__REG_##b)
@@ -276,6 +305,8 @@
 #define __PPC_SH(s)	__PPC_WS(s)
 #define __PPC_MB(s)	(((s) & 0x1f) << 6)
 #define __PPC_ME(s)	(((s) & 0x1f) << 1)
+#define __PPC_MB64(s)	(__PPC_MB(s) | ((s) & 0x20))
+#define __PPC_ME64(s)	__PPC_MB64(s)
 #define __PPC_BI(s)	(((s) & 0x1f) << 16)
 #define __PPC_CT(t)	(((t) & 0x0f) << 21)
 
@@ -325,6 +356,16 @@
 					__PPC_WC(w))
 #define PPC_TLBIE(lp,a) 	stringify_in_c(.long PPC_INST_TLBIE | \
 					       ___PPC_RB(a) | ___PPC_RS(lp))
+#define	PPC_TLBIE_5(rb,rs,ric,prs,r) \
+				stringify_in_c(.long PPC_INST_TLBIE | \
+					___PPC_RB(rb) | ___PPC_RS(rs) | \
+					___PPC_RIC(ric) | ___PPC_PRS(prs) | \
+					___PPC_R(r))
+#define	PPC_TLBIEL(rb,rs,ric,prs,r) \
+				stringify_in_c(.long PPC_INST_TLBIEL | \
+					___PPC_RB(rb) | ___PPC_RS(rs) | \
+					___PPC_RIC(ric) | ___PPC_PRS(prs) | \
+					___PPC_R(r))
 #define PPC_TLBSRX_DOT(a,b)	stringify_in_c(.long PPC_INST_TLBSRX_DOT | \
 					__PPC_RA0(a) | __PPC_RB(b))
 #define PPC_TLBIVAX(a,b)	stringify_in_c(.long PPC_INST_TLBIVAX | \
@@ -382,6 +423,8 @@
 #define PPC_SLEEP		stringify_in_c(.long PPC_INST_SLEEP)
 #define PPC_WINKLE		stringify_in_c(.long PPC_INST_WINKLE)
 
+#define PPC_STOP		stringify_in_c(.long PPC_INST_STOP)
+
 /* BHRB instructions */
 #define PPC_CLRBHRB		stringify_in_c(.long PPC_INST_CLRBHRB)
 #define PPC_MFBHRBE(r, n)	stringify_in_c(.long PPC_INST_BHRBE | \
@@ -412,5 +455,7 @@
 					       ___PPC_RA(a) |		\
 					       ___PPC_RB(b))
 
+#define PPC_SLBIA(IH)	stringify_in_c(.long PPC_INST_SLBIA | \
+				       ((IH & 0x7) << 21))
 
 #endif /* _ASM_POWERPC_PPC_OPCODE_H */
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index 8753e4eb9ab5..0f73de069f19 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -39,8 +39,6 @@ void *pci_traverse_device_nodes(struct device_node *start,
 void *traverse_pci_dn(struct pci_dn *root,
 		      void *(*fn)(struct pci_dn *, void *),
 		      void *data);
-
-extern void pci_devs_phb_init(void);
 extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
 
 /* From rtas_pci.h */
diff --git a/arch/powerpc/include/asm/ppc4xx.h b/arch/powerpc/include/asm/ppc4xx.h
index 033039a80c42..610a5119ad8c 100644
--- a/arch/powerpc/include/asm/ppc4xx.h
+++ b/arch/powerpc/include/asm/ppc4xx.h
@@ -13,6 +13,6 @@
 #ifndef __ASM_POWERPC_PPC4xx_H__
 #define __ASM_POWERPC_PPC4xx_H__
 
-extern void ppc4xx_reset_system(char *cmd);
+extern void __noreturn ppc4xx_reset_system(char *cmd);
 
 #endif /* __ASM_POWERPC_PPC4xx_H__ */
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 051af612a7e1..d5d5b5e348f2 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -24,27 +24,27 @@
  */
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-#define ACCOUNT_CPU_USER_ENTRY(ra, rb)
-#define ACCOUNT_CPU_USER_EXIT(ra, rb)
+#define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb)
+#define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb)
 #define ACCOUNT_STOLEN_TIME
 #else
-#define ACCOUNT_CPU_USER_ENTRY(ra, rb)					\
+#define ACCOUNT_CPU_USER_ENTRY(ptr, ra, rb)				\
 	MFTB(ra);			/* get timebase */		\
-	ld	rb,PACA_STARTTIME_USER(r13);				\
-	std	ra,PACA_STARTTIME(r13);					\
+	PPC_LL	rb, ACCOUNT_STARTTIME_USER(ptr);			\
+	PPC_STL	ra, ACCOUNT_STARTTIME(ptr);				\
 	subf	rb,rb,ra;		/* subtract start value */	\
-	ld	ra,PACA_USER_TIME(r13);					\
+	PPC_LL	ra, ACCOUNT_USER_TIME(ptr);				\
 	add	ra,ra,rb;		/* add on to user time */	\
-	std	ra,PACA_USER_TIME(r13);					\
+	PPC_STL	ra, ACCOUNT_USER_TIME(ptr);				\
 
-#define ACCOUNT_CPU_USER_EXIT(ra, rb)					\
+#define ACCOUNT_CPU_USER_EXIT(ptr, ra, rb)				\
 	MFTB(ra);			/* get timebase */		\
-	ld	rb,PACA_STARTTIME(r13);					\
-	std	ra,PACA_STARTTIME_USER(r13);				\
+	PPC_LL	rb, ACCOUNT_STARTTIME(ptr);				\
+	PPC_STL	ra, ACCOUNT_STARTTIME_USER(ptr);			\
 	subf	rb,rb,ra;		/* subtract start value */	\
-	ld	ra,PACA_SYSTEM_TIME(r13);				\
+	PPC_LL	ra, ACCOUNT_SYSTEM_TIME(ptr);				\
 	add	ra,ra,rb;		/* add on to system time */	\
-	std	ra,PACA_SYSTEM_TIME(r13)
+	PPC_STL	ra, ACCOUNT_SYSTEM_TIME(ptr)
 
 #ifdef CONFIG_PPC_SPLPAR
 #define ACCOUNT_STOLEN_TIME						\
@@ -189,7 +189,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define __STK_REG(i)   (112 + ((i)-14)*8)
 #define STK_REG(i)     __STK_REG(__REG_##i)
 
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 #define STK_GOT		24
 #define __STK_PARAM(i)	(32 + ((i)-3)*8)
 #else
@@ -198,7 +198,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #endif
 #define STK_PARAM(i)	__STK_PARAM(__REG_##i)
 
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 
 #define _GLOBAL(name) \
 	.section ".text"; \
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 009fab130cd8..68e3bf57b027 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -224,7 +224,7 @@ struct thread_struct {
 	unsigned int	align_ctl;	/* alignment handling control */
 #ifdef CONFIG_PPC64
 	unsigned long	start_tb;	/* Start purr when proc switched in */
-	unsigned long	accum_tb;	/* Total accumilated purr for process */
+	unsigned long	accum_tb;	/* Total accumulated purr for process */
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	struct perf_event *ptrace_bps[HBP_NUM];
 	/*
@@ -314,6 +314,8 @@ struct thread_struct {
 	unsigned long	mmcr2;
 	unsigned 	mmcr0;
 	unsigned 	used_ebb;
+	unsigned long	lmrr;
+	unsigned long	lmser;
 #endif
 };
 
@@ -347,6 +349,7 @@ struct thread_struct {
 	.fs = KERNEL_DS, \
 	.fpexc_mode = 0, \
 	.ppr = INIT_PPR, \
+	.fscr = FSCR_TAR | FSCR_EBB \
 }
 #endif
 
@@ -457,6 +460,8 @@ extern int powersave_nap;	/* set if nap mode can be used in idle loop */
 extern unsigned long power7_nap(int check_irq);
 extern unsigned long power7_sleep(void);
 extern unsigned long power7_winkle(void);
+extern unsigned long power9_idle_stop(unsigned long stop_level);
+
 extern void flush_instruction_cache(void);
 extern void hard_reset_now(void);
 extern void poweroff_now(void);
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index a1bc7e758422..a19f831a4cc9 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -526,4 +526,6 @@ void ps3_sync_irq(int node);
 u32 ps3_get_hw_thread_id(int cpu);
 u64 ps3_get_spe_id(void *arg);
 
+void ps3_early_mm_init(void);
+
 #endif
diff --git a/arch/powerpc/include/asm/ps3av.h b/arch/powerpc/include/asm/ps3av.h
index 0427b0b53d2d..a1dc784d70e8 100644
--- a/arch/powerpc/include/asm/ps3av.h
+++ b/arch/powerpc/include/asm/ps3av.h
@@ -104,7 +104,7 @@
 #define PS3AV_CMD_AV_INPUTLEN_16			0x02
 #define PS3AV_CMD_AV_INPUTLEN_20			0x0a
 #define PS3AV_CMD_AV_INPUTLEN_24			0x0b
-/* alayout */
+/* av_layout */
 #define PS3AV_CMD_AV_LAYOUT_32				(1 << 0)
 #define PS3AV_CMD_AV_LAYOUT_44				(1 << 1)
 #define PS3AV_CMD_AV_LAYOUT_48				(1 << 2)
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index 2eeaf80d41b7..4ba26dd259fd 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -96,7 +96,7 @@ static inline bool pte_user(pte_t pte)
 #define PTE_RPN_SHIFT	(PAGE_SHIFT)
 #endif
 
-/* The mask convered by the RPN must be a ULL on 32-bit platforms with
+/* The mask covered by the RPN must be a ULL on 32-bit platforms with
  * 64-bit PTEs
  */
 #if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index c0c61fa9cd9e..e4923686e43a 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -47,7 +47,7 @@
 				 STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
 #define STACK_FRAME_MARKER	12
 
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 #define STACK_FRAME_MIN_SIZE	32
 #else
 #define STACK_FRAME_MIN_SIZE	STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index a0948f40bc7b..40f3615bf940 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -145,6 +145,15 @@
 #define MSR_64BIT	0
 #endif
 
+/* Power Management - Processor Stop Status and Control Register Fields */
+#define PSSCR_RL_MASK		0x0000000F /* Requested Level */
+#define PSSCR_MTL_MASK		0x000000F0 /* Maximum Transition Level */
+#define PSSCR_TR_MASK		0x00000300 /* Transition State */
+#define PSSCR_PSLL_MASK		0x000F0000 /* Power-Saving Level Limit */
+#define PSSCR_EC		0x00100000 /* Exit Criterion */
+#define PSSCR_ESL		0x00200000 /* Enable State Loss */
+#define PSSCR_SD		0x00400000 /* Status Disable */
+
 /* Floating Point Status and Control Register (FPSCR) Fields */
 #define FPSCR_FX	0x80000000	/* FPU exception summary */
 #define FPSCR_FEX	0x40000000	/* FPU enabled exception summary */
@@ -268,6 +277,7 @@
 #define   DSISR_KEYFAULT	0x00200000	/* Key fault */
 #define SPRN_TBRL	0x10C	/* Time Base Read Lower Register (user, R/O) */
 #define SPRN_TBRU	0x10D	/* Time Base Read Upper Register (user, R/O) */
+#define SPRN_CIR	0x11B	/* Chip Information Register (hyper, R/0) */
 #define SPRN_TBWL	0x11C	/* Time Base Lower Register (super, R/W) */
 #define SPRN_TBWU	0x11D	/* Time Base Upper Register (super, R/W) */
 #define SPRN_TBU40	0x11E	/* Timebase upper 40 bits (hyper, R/W) */
@@ -282,15 +292,19 @@
 #define SPRN_HRMOR	0x139	/* Real mode offset register */
 #define SPRN_HSRR0	0x13A	/* Hypervisor Save/Restore 0 */
 #define SPRN_HSRR1	0x13B	/* Hypervisor Save/Restore 1 */
+#define SPRN_LMRR	0x32D	/* Load Monitor Region Register */
+#define SPRN_LMSER	0x32E	/* Load Monitor Section Enable Register */
 #define SPRN_IC		0x350	/* Virtual Instruction Count */
 #define SPRN_VTB	0x351	/* Virtual Time Base */
 #define SPRN_LDBAR	0x352	/* LD Base Address Register */
 #define SPRN_PMICR	0x354   /* Power Management Idle Control Reg */
 #define SPRN_PMSR	0x355   /* Power Management Status Reg */
 #define SPRN_PMMAR	0x356	/* Power Management Memory Activity Register */
+#define SPRN_PSSCR	0x357	/* Processor Stop Status and Control Register (ISA 3.0) */
 #define SPRN_PMCR	0x374	/* Power Management Control Register */
 
 /* HFSCR and FSCR bit numbers are the same */
+#define FSCR_LM_LG	11	/* Enable Load Monitor Registers */
 #define FSCR_TAR_LG	8	/* Enable Target Address Register */
 #define FSCR_EBB_LG	7	/* Enable Event Based Branching */
 #define FSCR_TM_LG	5	/* Enable Transactional Memory */
@@ -300,10 +314,12 @@
 #define FSCR_VECVSX_LG	1	/* Enable VMX/VSX  */
 #define FSCR_FP_LG	0	/* Enable Floating Point */
 #define SPRN_FSCR	0x099	/* Facility Status & Control Register */
+#define   FSCR_LM	__MASK(FSCR_LM_LG)
 #define   FSCR_TAR	__MASK(FSCR_TAR_LG)
 #define   FSCR_EBB	__MASK(FSCR_EBB_LG)
 #define   FSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
+#define   HFSCR_LM	__MASK(FSCR_LM_LG)
 #define   HFSCR_TAR	__MASK(FSCR_TAR_LG)
 #define   HFSCR_EBB	__MASK(FSCR_EBB_LG)
 #define   HFSCR_TM	__MASK(FSCR_TM_LG)
@@ -314,40 +330,43 @@
 #define   HFSCR_FP	__MASK(FSCR_FP_LG)
 #define SPRN_TAR	0x32f	/* Target Address Register */
 #define SPRN_LPCR	0x13E	/* LPAR Control Register */
-#define   LPCR_VPM0	(1ul << (63-0))
-#define   LPCR_VPM1	(1ul << (63-1))
-#define   LPCR_ISL	(1ul << (63-2))
-#define   LPCR_VC_SH	(63-2)
-#define   LPCR_DPFD_SH	(63-11)
-#define   LPCR_DPFD	(7ul << LPCR_DPFD_SH)
-#define   LPCR_VRMASD	(0x1ful << (63-16))
-#define   LPCR_VRMA_L	(1ul << (63-12))
-#define   LPCR_VRMA_LP0	(1ul << (63-15))
-#define   LPCR_VRMA_LP1	(1ul << (63-16))
-#define   LPCR_VRMASD_SH (63-16)
-#define   LPCR_RMLS    0x1C000000      /* impl dependent rmo limit sel */
-#define	  LPCR_RMLS_SH	(63-37)
-#define   LPCR_ILE     0x02000000      /* !HV irqs set MSR:LE */
-#define   LPCR_AIL	0x01800000	/* Alternate interrupt location */
-#define   LPCR_AIL_0	0x00000000	/* MMU off exception offset 0x0 */
-#define   LPCR_AIL_3	0x01800000	/* MMU on exception offset 0xc00...4xxx */
-#define   LPCR_ONL	0x00040000	/* online - PURR/SPURR count */
-#define   LPCR_PECE	0x0001f000	/* powersave exit cause enable */
-#define     LPCR_PECEDP	0x00010000	/* directed priv dbells cause exit */
-#define     LPCR_PECEDH	0x00008000	/* directed hyp dbells cause exit */
-#define     LPCR_PECE0	0x00004000	/* ext. exceptions can cause exit */
-#define     LPCR_PECE1	0x00002000	/* decrementer can cause exit */
-#define     LPCR_PECE2	0x00001000	/* machine check etc can cause exit */
-#define   LPCR_MER	0x00000800	/* Mediated External Exception */
-#define   LPCR_MER_SH	11
-#define   LPCR_TC      0x00000200	/* Translation control */
-#define   LPCR_LPES    0x0000000c
-#define   LPCR_LPES0   0x00000008      /* LPAR Env selector 0 */
-#define   LPCR_LPES1   0x00000004      /* LPAR Env selector 1 */
-#define   LPCR_LPES_SH	2
-#define   LPCR_RMI     0x00000002      /* real mode is cache inhibit */
-#define   LPCR_HDICE   0x00000001      /* Hyp Decr enable (HV,PR,EE) */
-#define   LPCR_UPRT    0x00400000      /* Use Process Table (ISA 3) */
+#define   LPCR_VPM0		ASM_CONST(0x8000000000000000)
+#define   LPCR_VPM1		ASM_CONST(0x4000000000000000)
+#define   LPCR_ISL		ASM_CONST(0x2000000000000000)
+#define   LPCR_VC_SH		61
+#define   LPCR_DPFD_SH		52
+#define   LPCR_DPFD		(ASM_CONST(7) << LPCR_DPFD_SH)
+#define   LPCR_VRMASD_SH	47
+#define   LPCR_VRMASD		(ASM_CONST(1) << LPCR_VRMASD_SH)
+#define   LPCR_VRMA_L		ASM_CONST(0x0008000000000000)
+#define   LPCR_VRMA_LP0		ASM_CONST(0x0001000000000000)
+#define   LPCR_VRMA_LP1		ASM_CONST(0x0000800000000000)
+#define   LPCR_RMLS		0x1C000000	/* Implementation dependent RMO limit sel */
+#define   LPCR_RMLS_SH		26
+#define   LPCR_ILE		ASM_CONST(0x0000000002000000)   /* !HV irqs set MSR:LE */
+#define   LPCR_AIL		ASM_CONST(0x0000000001800000)	/* Alternate interrupt location */
+#define   LPCR_AIL_0		ASM_CONST(0x0000000000000000)	/* MMU off exception offset 0x0 */
+#define   LPCR_AIL_3		ASM_CONST(0x0000000001800000)   /* MMU on exception offset 0xc00...4xxx */
+#define   LPCR_ONL		ASM_CONST(0x0000000000040000)	/* online - PURR/SPURR count */
+#define   LPCR_LD		ASM_CONST(0x0000000000020000)	/* large decremeter */
+#define   LPCR_PECE		ASM_CONST(0x000000000001f000)	/* powersave exit cause enable */
+#define     LPCR_PECEDP	ASM_CONST(0x0000000000010000)	/* directed priv dbells cause exit */
+#define     LPCR_PECEDH	ASM_CONST(0x0000000000008000)	/* directed hyp dbells cause exit */
+#define     LPCR_PECE0		ASM_CONST(0x0000000000004000)	/* ext. exceptions can cause exit */
+#define     LPCR_PECE1		ASM_CONST(0x0000000000002000)	/* decrementer can cause exit */
+#define     LPCR_PECE2		ASM_CONST(0x0000000000001000)	/* machine check etc can cause exit */
+#define   LPCR_MER		ASM_CONST(0x0000000000000800)	/* Mediated External Exception */
+#define   LPCR_MER_SH		11
+#define   LPCR_TC		ASM_CONST(0x0000000000000200)	/* Translation control */
+#define   LPCR_LPES		0x0000000c
+#define   LPCR_LPES0		ASM_CONST(0x0000000000000008)      /* LPAR Env selector 0 */
+#define   LPCR_LPES1		ASM_CONST(0x0000000000000004)      /* LPAR Env selector 1 */
+#define   LPCR_LPES_SH		2
+#define   LPCR_RMI		ASM_CONST(0x0000000000000002)      /* real mode is cache inhibit */
+#define   LPCR_HVICE		ASM_CONST(0x0000000000000002)      /* P9: HV interrupt enable */
+#define   LPCR_HDICE		ASM_CONST(0x0000000000000001)      /* Hyp Decr enable (HV,PR,EE) */
+#define   LPCR_UPRT		ASM_CONST(0x0000000000400000)      /* Use Process Table (ISA 3) */
+#define   LPCR_HR		ASM_CONST(0x0000000000100000)
 #ifndef SPRN_LPID
 #define SPRN_LPID	0x13F	/* Logical Partition Identifier */
 #endif
@@ -1288,6 +1307,7 @@ static inline unsigned long mfvtb (void)
 			asm volatile("mfspr %0, %1" : "=r" (rval) : \
 				"i" (SPRN_TBRU)); rval;})
 #endif
+#define mftb()		mftbl()
 #endif /* !__powerpc64__ */
 
 #define mttbl(v)	asm volatile("mttbl %0":: "r"(v))
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 51400baa8d48..9c23baa10b81 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -339,9 +339,9 @@ extern int rtas_service_present(const char *service);
 extern int rtas_call(int token, int, int, int *, ...);
 void rtas_call_unlocked(struct rtas_args *args, int token, int nargs,
 			int nret, ...);
-extern void rtas_restart(char *cmd);
+extern void __noreturn rtas_restart(char *cmd);
 extern void rtas_power_off(void);
-extern void rtas_halt(void);
+extern void __noreturn rtas_halt(void);
 extern void rtas_os_term(char *str);
 extern int rtas_get_sensor(int sensor, int index, int *state);
 extern int rtas_get_sensor_fast(int sensor, int index, int *state);
@@ -351,7 +351,6 @@ extern bool rtas_indicator_present(int token, int *maxindex);
 extern int rtas_set_indicator(int indicator, int index, int new_value);
 extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
 extern void rtas_progress(char *s, unsigned short hex);
-extern void rtas_initialize(void);
 extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data);
 extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data);
 extern int rtas_online_cpus_mask(cpumask_var_t cpus);
@@ -460,9 +459,11 @@ static inline int page_is_rtas_user_buf(unsigned long pfn)
 /* Not the best place to put pSeries_coalesce_init, will be fixed when we
  * move some of the rtas suspend-me stuff to pseries */
 extern void pSeries_coalesce_init(void);
+void rtas_initialize(void);
 #else
 static inline int page_is_rtas_user_buf(unsigned long pfn) { return 0;}
 static inline void pSeries_coalesce_init(void) { }
+static inline void rtas_initialize(void) { };
 #endif
 
 extern int call_rtas(const char *, int, int, unsigned long *, ...);
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index abf5866e08c6..7dc006b58369 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -62,7 +62,7 @@ static inline int overlaps_kvm_tmp(unsigned long start, unsigned long end)
 #endif
 }
 
-#if !defined(_CALL_ELF) || _CALL_ELF != 2
+#ifdef PPC64_ELF_ABI_v1
 #undef dereference_function_descriptor
 static inline void *dereference_function_descriptor(void *ptr)
 {
@@ -73,7 +73,7 @@ static inline void *dereference_function_descriptor(void *ptr)
 		ptr = p;
 	return ptr;
 }
-#endif
+#endif /* PPC64_ELF_ABI_v1 */
 
 #endif
 
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index e9d384cbd021..654d64c9f3ac 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -26,6 +26,18 @@ void initmem_init(void);
 void setup_panic(void);
 #define ARCH_PANIC_TIMEOUT 180
 
+#ifdef CONFIG_PPC_PSERIES
+extern void pseries_enable_reloc_on_exc(void);
+extern void pseries_disable_reloc_on_exc(void);
+extern void pseries_big_endian_exceptions(void);
+extern void pseries_little_endian_exceptions(void);
+#else
+static inline void pseries_enable_reloc_on_exc(void) {}
+static inline void pseries_disable_reloc_on_exc(void) {}
+static inline void pseries_big_endian_exceptions(void) {}
+static inline void pseries_little_endian_exceptions(void) {}
+#endif /* CONFIG_PPC_PSERIES */
+
 #endif /* !__ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_SETUP_H */
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index e1afd4c4f695..0d02c11dc331 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -160,9 +160,6 @@ static inline void set_hard_smp_processor_id(int cpu, int phys)
 {
 	paca[cpu].hw_cpu_id = phys;
 }
-
-extern void smp_release_cpus(void);
-
 #else
 /* 32-bit */
 #ifndef CONFIG_SMP
@@ -179,6 +176,12 @@ static inline void set_hard_smp_processor_id(int cpu, int phys)
 #endif /* !CONFIG_SMP */
 #endif /* !CONFIG_PPC64 */
 
+#if defined(CONFIG_PPC64) && (defined(CONFIG_SMP) || defined(CONFIG_KEXEC))
+extern void smp_release_cpus(void);
+#else
+static inline void smp_release_cpus(void) { };
+#endif
+
 extern int smt_enabled_at_boot;
 
 extern void smp_mpic_probe(void);
diff --git a/arch/powerpc/include/asm/smu.h b/arch/powerpc/include/asm/smu.h
index f280dd11243f..09f98e861869 100644
--- a/arch/powerpc/include/asm/smu.h
+++ b/arch/powerpc/include/asm/smu.h
@@ -185,7 +185,7 @@
  *  x = processor mask
  *  y = op. point index
  *  z = processor freq. step index
- * I haven't yet decyphered result codes
+ * I haven't yet deciphered result codes
  *
  */
 #define SMU_CMD_POWER_COMMAND			0xaa
@@ -471,13 +471,6 @@ extern int smu_get_rtc_time(struct rtc_time *time, int spinwait);
 extern int smu_set_rtc_time(struct rtc_time *time, int spinwait);
 
 /*
- * SMU command buffer absolute address, exported by pmac_setup,
- * this is allocated very early during boot.
- */
-extern unsigned long smu_cmdbuf_abs;
-
-
-/*
  * Kernel asynchronous i2c interface
  */
 
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 523673d7583c..fa37fe93bc02 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -162,12 +162,38 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	lock->slock = 0;
 }
 
-#ifdef CONFIG_PPC64
-extern void arch_spin_unlock_wait(arch_spinlock_t *lock);
-#else
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
-#endif
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	arch_spinlock_t lock_val;
+
+	smp_mb();
+
+	/*
+	 * Atomically load and store back the lock value (unchanged). This
+	 * ensures that our observation of the lock value is ordered with
+	 * respect to other lock operations.
+	 */
+	__asm__ __volatile__(
+"1:	" PPC_LWARX(%0, 0, %2, 0) "\n"
+"	stwcx. %0, 0, %2\n"
+"	bne- 1b\n"
+	: "=&r" (lock_val), "+m" (*lock)
+	: "r" (lock)
+	: "cr0", "xer");
+
+	if (arch_spin_value_unlocked(lock_val))
+		goto out;
+
+	while (lock->slock) {
+		HMT_low();
+		if (SHARED_PROCESSOR)
+			__spin_yield(lock);
+	}
+	HMT_medium();
+
+out:
+	smp_mb();
+}
 
 /*
  * Read-write spinlocks, allowing multiple readers
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index e40010abcaf1..da3cdffca440 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -3,12 +3,8 @@
 
 #ifdef __KERNEL__
 
-#define __HAVE_ARCH_STRCPY
 #define __HAVE_ARCH_STRNCPY
-#define __HAVE_ARCH_STRLEN
-#define __HAVE_ARCH_STRCMP
 #define __HAVE_ARCH_STRNCMP
-#define __HAVE_ARCH_STRCAT
 #define __HAVE_ARCH_MEMSET
 #define __HAVE_ARCH_MEMCPY
 #define __HAVE_ARCH_MEMMOVE
diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h
index c50868681f9e..78efe8d5d775 100644
--- a/arch/powerpc/include/asm/synch.h
+++ b/arch/powerpc/include/asm/synch.h
@@ -13,7 +13,6 @@
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
 extern void do_lwsync_fixups(unsigned long value, void *fixup_start,
 			     void *fixup_end);
-extern void do_final_fixups(void);
 
 static inline void eieio(void)
 {
diff --git a/arch/powerpc/include/asm/tce.h b/arch/powerpc/include/asm/tce.h
index 743f36b38e5d..12e362935160 100644
--- a/arch/powerpc/include/asm/tce.h
+++ b/arch/powerpc/include/asm/tce.h
@@ -31,9 +31,6 @@
  */
 #define TCE_VB			0
 #define TCE_PCI			1
-#define TCE_PCI_SWINV_CREATE	2
-#define TCE_PCI_SWINV_FREE	4
-#define TCE_PCI_SWINV_PAIR	8
 
 /* TCE page size is 4096 bytes (1 << 12) */
 
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 8febc3f66d53..87e4b2d8dcd4 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -33,6 +33,7 @@
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <linux/stringify.h>
+#include <asm/accounting.h>
 
 /*
  * low level task data.
@@ -46,6 +47,9 @@ struct thread_info {
 #ifdef CONFIG_LIVEPATCH
 	unsigned long *livepatch_sp;
 #endif
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC32)
+	struct cpu_accounting_data accounting;
+#endif
 	/* low level flags - has atomic operations done on it */
 	unsigned long	flags ____cacheline_aligned_in_smp;
 };
@@ -134,40 +138,15 @@ static inline struct thread_info *current_thread_info(void)
 /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */
 #define TLF_NAPPING		0	/* idle thread enabled NAP mode */
 #define TLF_SLEEPING		1	/* suspend code enabled SLEEP mode */
-#define TLF_RESTORE_SIGMASK	2	/* Restore signal mask in do_signal */
 #define TLF_LAZY_MMU		3	/* tlb_batch is active */
 #define TLF_RUNLATCH		4	/* Is the runlatch enabled? */
 
 #define _TLF_NAPPING		(1 << TLF_NAPPING)
 #define _TLF_SLEEPING		(1 << TLF_SLEEPING)
-#define _TLF_RESTORE_SIGMASK	(1 << TLF_RESTORE_SIGMASK)
 #define _TLF_LAZY_MMU		(1 << TLF_LAZY_MMU)
 #define _TLF_RUNLATCH		(1 << TLF_RUNLATCH)
 
 #ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->local_flags |= _TLF_RESTORE_SIGMASK;
-	WARN_ON(!test_bit(TIF_SIGPENDING, &ti->flags));
-}
-static inline void clear_restore_sigmask(void)
-{
-	current_thread_info()->local_flags &= ~_TLF_RESTORE_SIGMASK;
-}
-static inline bool test_restore_sigmask(void)
-{
-	return current_thread_info()->local_flags & _TLF_RESTORE_SIGMASK;
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	if (!(ti->local_flags & _TLF_RESTORE_SIGMASK))
-		return false;
-	ti->local_flags &= ~_TLF_RESTORE_SIGMASK;
-	return true;
-}
 
 static inline bool test_thread_local_flags(unsigned int flags)
 {
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 1092fdd7e737..09211640a0e0 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -146,7 +146,7 @@ static inline void set_tb(unsigned int upper, unsigned int lower)
  * in auto-reload mode.  The problem is PIT stops counting when it
  * hits zero.  If it would wrap, we could use it just like a decrementer.
  */
-static inline unsigned int get_dec(void)
+static inline u64 get_dec(void)
 {
 #if defined(CONFIG_40x)
 	return (mfspr(SPRN_PIT));
@@ -160,10 +160,10 @@ static inline unsigned int get_dec(void)
  * in when the decrementer generates its interrupt: on the 1 to 0
  * transition for Book E/4xx, but on the 0 to -1 transition for others.
  */
-static inline void set_dec(int val)
+static inline void set_dec(u64 val)
 {
 #if defined(CONFIG_40x)
-	mtspr(SPRN_PIT, val);
+	mtspr(SPRN_PIT, (u32) val);
 #else
 #ifndef CONFIG_BOOKE
 	--val;
diff --git a/arch/powerpc/include/asm/tsi108.h b/arch/powerpc/include/asm/tsi108.h
index d531d9e173ef..c2a955bb0daa 100644
--- a/arch/powerpc/include/asm/tsi108.h
+++ b/arch/powerpc/include/asm/tsi108.h
@@ -77,7 +77,7 @@
  * nodes if your board uses the Broadcom PHYs
  */
 #define TSI108_PHY_MV88E	0	/* Marvel 88Exxxx PHY */
-#define TSI108_PHY_BCM54XX	1	/* Broardcom BCM54xx PHY */
+#define TSI108_PHY_BCM54XX	1	/* Broadcom BCM54xx PHY */
 
 /* Global variables */
 
diff --git a/arch/powerpc/include/asm/types.h b/arch/powerpc/include/asm/types.h
index bfb6ded38ffa..49a0678a53fa 100644
--- a/arch/powerpc/include/asm/types.h
+++ b/arch/powerpc/include/asm/types.h
@@ -15,6 +15,14 @@
 
 #include <uapi/asm/types.h>
 
+#ifdef __powerpc64__
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define PPC64_ELF_ABI_v2
+#else
+#define PPC64_ELF_ABI_v1
+#endif
+#endif /* __powerpc64__ */
+
 #ifndef __ASSEMBLY__
 
 typedef __vector128 vector128;
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index 04ef3ae511da..f5f729c11578 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -42,6 +42,12 @@ extern int icp_hv_init(void);
 static inline int icp_hv_init(void) { return -ENODEV; }
 #endif
 
+#ifdef CONFIG_PPC_POWERNV
+extern int icp_opal_init(void);
+#else
+static inline int icp_opal_init(void) { return -ENODEV; }
+#endif
+
 /* ICP ops */
 struct icp_ops {
 	unsigned int (*get_irq)(void);
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 2da380fcc34c..b2027a5cf508 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -41,13 +41,12 @@ obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
-obj64-$(CONFIG_RELOCATABLE)	+= reloc_64.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o hmi.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
-obj-$(CONFIG_PPC_P7_NAP)	+= idle_power7.o
+obj-$(CONFIG_PPC_P7_NAP)	+= idle_book3s.o
 procfs-y			:= proc_powerpc.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI)	:= rtas_pci.o
@@ -87,7 +86,7 @@ extra-$(CONFIG_FSL_BOOKE)	:= head_fsl_booke.o
 extra-$(CONFIG_8xx)		:= head_8xx.o
 extra-y				+= vmlinux.lds
 
-obj-$(CONFIG_RELOCATABLE_PPC32)	+= reloc_32.o
+obj-$(CONFIG_RELOCATABLE)	+= reloc_$(CONFIG_WORD_SIZE).o
 
 obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o
 obj-$(CONFIG_PPC64)		+= dma-iommu.o iommu.o
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 8e7cb8e2b21a..c7097f933114 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -228,9 +228,7 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr)
 #else
 #define REG_BYTE(rp, i)		*((u8 *)(rp) + (i))
 #endif
-#endif
-
-#ifdef __LITTLE_ENDIAN__
+#else
 #define REG_BYTE(rp, i)		(*(((u8 *)((rp) + ((i)>>2)) + ((i)&3))))
 #endif
 
@@ -875,6 +873,20 @@ int fix_alignment(struct pt_regs *regs)
 		return emulate_vsx(addr, reg, areg, regs, flags, nb, elsize);
 	}
 #endif
+
+	/*
+	 * ISA 3.0 (such as P9) copy, copy_first, paste and paste_last alignment
+	 * check.
+	 *
+	 * Send a SIGBUS to the process that caused the fault.
+	 *
+	 * We do not emulate these because paste may contain additional metadata
+	 * when pasting to a co-processor. Furthermore, paste_last is the
+	 * synchronisation point for preceding copy/paste sequences.
+	 */
+	if ((instruction & 0xfc0006fe) == PPC_INST_COPY)
+		return -EIO;
+
 	/* A size of 0 indicates an instruction we don't support, with
 	 * the exception of DCBZ which is handled as a special case here
 	 */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 9ea09551a2cd..b89d14c0352c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -68,17 +68,18 @@
 #include "../mm/mmu_decl.h"
 #endif
 
+#ifdef CONFIG_PPC_8xx
+#include <asm/fixmap.h>
+#endif
+
 int main(void)
 {
 	DEFINE(THREAD, offsetof(struct task_struct, thread));
 	DEFINE(MM, offsetof(struct task_struct, mm));
 	DEFINE(MMCONTEXTID, offsetof(struct mm_struct, context.id));
 #ifdef CONFIG_PPC64
-	DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context));
 	DEFINE(SIGSEGV, SIGSEGV);
 	DEFINE(NMI_MASK, NMI_MASK);
-	DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
-	DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit));
 	DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
@@ -132,17 +133,6 @@ int main(void)
 	DEFINE(THREAD_KVM_VCPU, offsetof(struct thread_struct, kvm_vcpu));
 #endif
 
-#ifdef CONFIG_PPC_BOOK3S_64
-	DEFINE(THREAD_TAR, offsetof(struct thread_struct, tar));
-	DEFINE(THREAD_BESCR, offsetof(struct thread_struct, bescr));
-	DEFINE(THREAD_EBBHR, offsetof(struct thread_struct, ebbhr));
-	DEFINE(THREAD_EBBRR, offsetof(struct thread_struct, ebbrr));
-	DEFINE(THREAD_SIAR, offsetof(struct thread_struct, siar));
-	DEFINE(THREAD_SDAR, offsetof(struct thread_struct, sdar));
-	DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier));
-	DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0));
-	DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2));
-#endif
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch));
 	DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
@@ -178,7 +168,6 @@ int main(void)
 	DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page));
 	/* paca */
 	DEFINE(PACA_SIZE, sizeof(struct paca_struct));
-	DEFINE(PACA_LOCK_TOKEN, offsetof(struct paca_struct, lock_token));
 	DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index));
 	DEFINE(PACAPROCSTART, offsetof(struct paca_struct, cpu_start));
 	DEFINE(PACAKSAVE, offsetof(struct paca_struct, kstack));
@@ -255,13 +244,28 @@ int main(void)
 	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
 	DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
 	DEFINE(PACA_DSCR_DEFAULT, offsetof(struct paca_struct, dscr_default));
-	DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime));
-	DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user));
-	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
-	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
+	DEFINE(ACCOUNT_STARTTIME,
+	       offsetof(struct paca_struct, accounting.starttime));
+	DEFINE(ACCOUNT_STARTTIME_USER,
+	       offsetof(struct paca_struct, accounting.starttime_user));
+	DEFINE(ACCOUNT_USER_TIME,
+	       offsetof(struct paca_struct, accounting.user_time));
+	DEFINE(ACCOUNT_SYSTEM_TIME,
+	       offsetof(struct paca_struct, accounting.system_time));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
 	DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost));
 	DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso));
+#else /* CONFIG_PPC64 */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	DEFINE(ACCOUNT_STARTTIME,
+	       offsetof(struct thread_info, accounting.starttime));
+	DEFINE(ACCOUNT_STARTTIME_USER,
+	       offsetof(struct thread_info, accounting.starttime_user));
+	DEFINE(ACCOUNT_USER_TIME,
+	       offsetof(struct thread_info, accounting.user_time));
+	DEFINE(ACCOUNT_SYSTEM_TIME,
+	       offsetof(struct thread_info, accounting.system_time));
+#endif
 #endif /* CONFIG_PPC64 */
 
 	/* RTAS */
@@ -275,12 +279,6 @@ int main(void)
 	/* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */
 	DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
 	DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
-
-	/* hcall statistics */
-	DEFINE(HCALL_STAT_SIZE, sizeof(struct hcall_stats));
-	DEFINE(HCALL_STAT_CALLS, offsetof(struct hcall_stats, num_calls));
-	DEFINE(HCALL_STAT_TB, offsetof(struct hcall_stats, tb_total));
-	DEFINE(HCALL_STAT_PURR, offsetof(struct hcall_stats, purr_total));
 #endif /* CONFIG_PPC64 */
 	DEFINE(GPR0, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[0]));
 	DEFINE(GPR1, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[1]));
@@ -298,23 +296,6 @@ int main(void)
 	DEFINE(GPR13, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[13]));
 #ifndef CONFIG_PPC64
 	DEFINE(GPR14, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[14]));
-	DEFINE(GPR15, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[15]));
-	DEFINE(GPR16, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[16]));
-	DEFINE(GPR17, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[17]));
-	DEFINE(GPR18, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[18]));
-	DEFINE(GPR19, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[19]));
-	DEFINE(GPR20, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[20]));
-	DEFINE(GPR21, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[21]));
-	DEFINE(GPR22, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[22]));
-	DEFINE(GPR23, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[23]));
-	DEFINE(GPR24, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[24]));
-	DEFINE(GPR25, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[25]));
-	DEFINE(GPR26, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[26]));
-	DEFINE(GPR27, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[27]));
-	DEFINE(GPR28, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[28]));
-	DEFINE(GPR29, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[29]));
-	DEFINE(GPR30, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[30]));
-	DEFINE(GPR31, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[31]));
 #endif /* CONFIG_PPC64 */
 	/*
 	 * Note: these symbols include _ because they overlap with special
@@ -332,7 +313,6 @@ int main(void)
 	DEFINE(RESULT, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, result));
 	DEFINE(_TRAP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, trap));
 #ifndef CONFIG_PPC64
-	DEFINE(_MQ, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, mq));
 	/*
 	 * The PowerPC 400-class & Book-E processors have neither the DAR
 	 * nor the DSISR SPRs. Hence, we overload them to hold the similar
@@ -369,8 +349,6 @@ int main(void)
 	DEFINE(SAVED_KSP_LIMIT, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, saved_ksp_limit));
 #endif
 #endif
-	DEFINE(CLONE_VM, CLONE_VM);
-	DEFINE(CLONE_UNTRACED, CLONE_UNTRACED);
 
 #ifndef CONFIG_PPC64
 	DEFINE(MM_PGD, offsetof(struct mm_struct, pgd));
@@ -380,7 +358,6 @@ int main(void)
 	DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features));
 	DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup));
 	DEFINE(CPU_SPEC_RESTORE, offsetof(struct cpu_spec, cpu_restore));
-	DEFINE(CPU_DOWN_FLUSH, offsetof(struct cpu_spec, cpu_down_flush));
 
 	DEFINE(pbe_address, offsetof(struct pbe, address));
 	DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
@@ -395,7 +372,6 @@ int main(void)
 	DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct vdso_data, tb_orig_stamp));
 	DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct vdso_data, tb_ticks_per_sec));
 	DEFINE(CFG_TB_TO_XS, offsetof(struct vdso_data, tb_to_xs));
-	DEFINE(CFG_STAMP_XSEC, offsetof(struct vdso_data, stamp_xsec));
 	DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct vdso_data, tb_update_count));
 	DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct vdso_data, tz_minuteswest));
 	DEFINE(CFG_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime));
@@ -517,7 +493,6 @@ int main(void)
 	DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1));
 	DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
 	DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls));
-	DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
 	DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
 	DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
 	DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
@@ -528,7 +503,6 @@ int main(void)
 	DEFINE(VCPU_THREAD_CPU, offsetof(struct kvm_vcpu, arch.thread_cpu));
 #endif
 #ifdef CONFIG_PPC_BOOK3S
-	DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
 	DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
 	DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
 	DEFINE(VCPU_IC, offsetof(struct kvm_vcpu, arch.ic));
@@ -566,7 +540,6 @@ int main(void)
 	DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar));
 	DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr));
 	DEFINE(VCPU_FSCR, offsetof(struct kvm_vcpu, arch.fscr));
-	DEFINE(VCPU_SHADOW_FSCR, offsetof(struct kvm_vcpu, arch.shadow_fscr));
 	DEFINE(VCPU_PSPB, offsetof(struct kvm_vcpu, arch.pspb));
 	DEFINE(VCPU_EBBHR, offsetof(struct kvm_vcpu, arch.ebbhr));
 	DEFINE(VCPU_EBBRR, offsetof(struct kvm_vcpu, arch.ebbrr));
@@ -576,7 +549,6 @@ int main(void)
 	DEFINE(VCPU_TCSCR, offsetof(struct kvm_vcpu, arch.tcscr));
 	DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
 	DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
-	DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
 	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
@@ -693,7 +665,6 @@ int main(void)
 	DEFINE(KVM_SPLIT_RPR, offsetof(struct kvm_split_mode, rpr));
 	DEFINE(KVM_SPLIT_PMMAR, offsetof(struct kvm_split_mode, pmmar));
 	DEFINE(KVM_SPLIT_LDBAR, offsetof(struct kvm_split_mode, ldbar));
-	DEFINE(KVM_SPLIT_SIZE, offsetof(struct kvm_split_mode, subcore_size));
 	DEFINE(KVM_SPLIT_DO_NAP, offsetof(struct kvm_split_mode, do_nap));
 	DEFINE(KVM_SPLIT_NAPPED, offsetof(struct kvm_split_mode, napped));
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
@@ -756,7 +727,6 @@ int main(void)
 #ifdef CONFIG_KVM_BOOKE_HV
 	DEFINE(VCPU_HOST_MAS4, offsetof(struct kvm_vcpu, arch.host_mas4));
 	DEFINE(VCPU_HOST_MAS6, offsetof(struct kvm_vcpu, arch.host_mas6));
-	DEFINE(VCPU_EPLC, offsetof(struct kvm_vcpu, arch.eplc));
 #endif
 
 #ifdef CONFIG_KVM_EXIT_TIMING
@@ -783,5 +753,9 @@ int main(void)
 
 	DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
 
+#ifdef CONFIG_PPC_8xx
+	DEFINE(VIRT_IMMR_BASE, (u64)__fix_to_virt(FIX_IMMR_BASE));
+#endif
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index f8cd9fba4d35..c5e5a94d9892 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -156,7 +156,7 @@ setup_7410_workarounds:
 	blr
 
 /* 740/750/7400/7410
- * Enable Store Gathering (SGE), Address Brodcast (ABE),
+ * Enable Store Gathering (SGE), Address Broadcast (ABE),
  * Branch History Table (BHTE), Branch Target ICache (BTIC)
  * Dynamic Power Management (DPM), Speculative (SPD)
  * Clear Instruction cache throttling (ICTC)
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 584e119fa8b0..52ff3f025437 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -51,6 +51,7 @@ _GLOBAL(__setup_cpu_power8)
 	mflr	r11
 	bl	__init_FSCR
 	bl	__init_PMU
+	bl	__init_PMU_ISA207
 	bl	__init_hvmode_206
 	mtlr	r11
 	beqlr
@@ -62,6 +63,7 @@ _GLOBAL(__setup_cpu_power8)
 	bl	__init_HFSCR
 	bl	__init_tlb_power8
 	bl	__init_PMU_HV
+	bl	__init_PMU_HV_ISA207
 	mtlr	r11
 	blr
 
@@ -69,6 +71,7 @@ _GLOBAL(__restore_cpu_power8)
 	mflr	r11
 	bl	__init_FSCR
 	bl	__init_PMU
+	bl	__init_PMU_ISA207
 	mfmsr	r3
 	rldicl.	r0,r3,4,63
 	mtlr	r11
@@ -81,12 +84,14 @@ _GLOBAL(__restore_cpu_power8)
 	bl	__init_HFSCR
 	bl	__init_tlb_power8
 	bl	__init_PMU_HV
+	bl	__init_PMU_HV_ISA207
 	mtlr	r11
 	blr
 
 _GLOBAL(__setup_cpu_power9)
 	mflr	r11
 	bl	__init_FSCR
+	bl	__init_PMU
 	bl	__init_hvmode_206
 	mtlr	r11
 	beqlr
@@ -94,15 +99,18 @@ _GLOBAL(__setup_cpu_power9)
 	mtspr	SPRN_LPID,r0
 	mfspr	r3,SPRN_LPCR
 	ori	r3, r3, LPCR_PECEDH
+	ori	r3, r3, LPCR_HVICE
 	bl	__init_LPCR
 	bl	__init_HFSCR
 	bl	__init_tlb_power9
+	bl	__init_PMU_HV
 	mtlr	r11
 	blr
 
 _GLOBAL(__restore_cpu_power9)
 	mflr	r11
 	bl	__init_FSCR
+	bl	__init_PMU
 	mfmsr	r3
 	rldicl.	r0,r3,4,63
 	mtlr	r11
@@ -111,9 +119,11 @@ _GLOBAL(__restore_cpu_power9)
 	mtspr	SPRN_LPID,r0
 	mfspr   r3,SPRN_LPCR
 	ori	r3, r3, LPCR_PECEDH
+	ori	r3, r3, LPCR_HVICE
 	bl	__init_LPCR
 	bl	__init_HFSCR
 	bl	__init_tlb_power9
+	bl	__init_PMU_HV
 	mtlr	r11
 	blr
 
@@ -208,14 +218,22 @@ __init_tlb_power9:
 __init_PMU_HV:
 	li	r5,0
 	mtspr	SPRN_MMCRC,r5
+	blr
+
+__init_PMU_HV_ISA207:
+	li	r5,0
 	mtspr	SPRN_MMCRH,r5
 	blr
 
 __init_PMU:
 	li	r5,0
-	mtspr	SPRN_MMCRS,r5
 	mtspr	SPRN_MMCRA,r5
 	mtspr	SPRN_MMCR0,r5
 	mtspr	SPRN_MMCR1,r5
 	mtspr	SPRN_MMCR2,r5
 	blr
+
+__init_PMU_ISA207:
+	li	r5,0
+	mtspr	SPRN_MMCRS,r5
+	blr
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index eeeacf6235a3..d81f826d1029 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -137,7 +137,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER4 (gp)",
 		.cpu_features		= CPU_FTRS_POWER4,
 		.cpu_user_features	= COMMON_USER_POWER4,
-		.mmu_features		= MMU_FTRS_POWER4,
+		.mmu_features		= MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -152,7 +152,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER4+ (gq)",
 		.cpu_features		= CPU_FTRS_POWER4,
 		.cpu_user_features	= COMMON_USER_POWER4,
-		.mmu_features		= MMU_FTRS_POWER4,
+		.mmu_features		= MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 2bb252c01f07..47b63de81f9b 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -48,8 +48,8 @@ int crashing_cpu = -1;
 static int time_to_dump;
 
 #define CRASH_HANDLER_MAX 3
-/* NULL terminated list of shutdown handles */
-static crash_shutdown_t crash_shutdown_handles[CRASH_HANDLER_MAX+1];
+/* List of shutdown handles */
+static crash_shutdown_t crash_shutdown_handles[CRASH_HANDLER_MAX];
 static DEFINE_SPINLOCK(crash_handlers_lock);
 
 static unsigned long crash_shutdown_buf[JMP_BUF_LEN];
@@ -65,7 +65,7 @@ static int handle_fault(struct pt_regs *regs)
 #ifdef CONFIG_SMP
 
 static atomic_t cpus_in_crash;
-void crash_ipi_callback(struct pt_regs *regs)
+static void crash_ipi_callback(struct pt_regs *regs)
 {
 	static cpumask_t cpus_state_saved = CPU_MASK_NONE;
 
@@ -288,9 +288,14 @@ int crash_shutdown_unregister(crash_shutdown_t handler)
 		rc = 1;
 	} else {
 		/* Shift handles down */
-		for (; crash_shutdown_handles[i]; i++)
+		for (; i < (CRASH_HANDLER_MAX - 1); i++)
 			crash_shutdown_handles[i] =
 				crash_shutdown_handles[i+1];
+		/*
+		 * Reset last entry to NULL now that it has been shifted down,
+		 * this will allow new handles to be added here.
+		 */
+		crash_shutdown_handles[i] = NULL;
 		rc = 0;
 	}
 
@@ -346,7 +351,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	old_handler = __debugger_fault_handler;
 	__debugger_fault_handler = handle_fault;
 	crash_shutdown_cpu = smp_processor_id();
-	for (i = 0; crash_shutdown_handles[i]; i++) {
+	for (i = 0; i < CRASH_HANDLER_MAX && crash_shutdown_handles[i]; i++) {
 		if (setjmp(crash_shutdown_buf) == 0) {
 			/*
 			 * Insert syncs and delay to ensure
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index ddbcfab7efdf..d4cc26618809 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -114,9 +114,9 @@ static void eeh_addr_cache_print(struct pci_io_addr_cache *cache)
 	while (n) {
 		struct pci_io_addr_range *piar;
 		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
-		pr_debug("PCI: %s addr range %d [%lx-%lx]: %s\n",
+		pr_debug("PCI: %s addr range %d [%pap-%pap]: %s\n",
 		       (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt,
-		       piar->addr_lo, piar->addr_hi, pci_name(piar->pcidev));
+		       &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev));
 		cnt++;
 		n = rb_next(n);
 	}
@@ -159,8 +159,8 @@ eeh_addr_cache_insert(struct pci_dev *dev, resource_size_t alo,
 	piar->flags = flags;
 
 #ifdef DEBUG
-	pr_debug("PIAR: insert range=[%lx:%lx] dev=%s\n",
-	                  alo, ahi, pci_name(dev));
+	pr_debug("PIAR: insert range=[%pap:%pap] dev=%s\n",
+		 &alo, &ahi, pci_name(dev));
 #endif
 
 	rb_link_node(&piar->rb_node, parent, p);
diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c
index 7815095fe3d8..d6b2ca70d14d 100644
--- a/arch/powerpc/kernel/eeh_dev.c
+++ b/arch/powerpc/kernel/eeh_dev.c
@@ -44,14 +44,13 @@
 /**
  * eeh_dev_init - Create EEH device according to OF node
  * @pdn: PCI device node
- * @data: PHB
  *
  * It will create EEH device according to the given OF node. The function
  * might be called by PCI emunation, DR, PHB hotplug.
  */
-void *eeh_dev_init(struct pci_dn *pdn, void *data)
+struct eeh_dev *eeh_dev_init(struct pci_dn *pdn)
 {
-	struct pci_controller *phb = data;
+	struct pci_controller *phb = pdn->phb;
 	struct eeh_dev *edev;
 
 	/* Allocate EEH device */
@@ -69,7 +68,7 @@ void *eeh_dev_init(struct pci_dn *pdn, void *data)
 	INIT_LIST_HEAD(&edev->list);
 	INIT_LIST_HEAD(&edev->rmv_list);
 
-	return NULL;
+	return edev;
 }
 
 /**
@@ -81,16 +80,8 @@ void *eeh_dev_init(struct pci_dn *pdn, void *data)
  */
 void eeh_dev_phb_init_dynamic(struct pci_controller *phb)
 {
-	struct pci_dn *root = phb->pci_data;
-
 	/* EEH PE for PHB */
 	eeh_phb_pe_create(phb);
-
-	/* EEH device for PHB */
-	eeh_dev_init(root, phb);
-
-	/* EEH devices for children OF nodes */
-	traverse_pci_dn(root, eeh_dev_init, phb);
 }
 
 /**
@@ -106,8 +97,6 @@ static int __init eeh_dev_phb_init(void)
 	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
 		eeh_dev_phb_init_dynamic(phb);
 
-	pr_info("EEH: devices created\n");
-
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index d70101e1e25c..5f36e8a70daa 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -139,7 +139,7 @@ static void eeh_enable_irq(struct pci_dev *dev)
 		 * into it.
 		 *
 		 * That's just wrong.The warning in the core code is
-		 * there to tell people to fix their assymetries in
+		 * there to tell people to fix their asymmetries in
 		 * their own code, not by abusing the core information
 		 * to avoid it.
 		 *
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 2405631e91a2..9899032230b4 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -175,6 +175,12 @@ transfer_to_handler:
 	addi	r12,r12,-1
 	stw	r12,4(r11)
 #endif
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	CURRENT_THREAD_INFO(r9, r1)
+	tophys(r9, r9)
+	ACCOUNT_CPU_USER_ENTRY(r9, r11, r12)
+#endif
+
 	b	3f
 
 2:	/* if from kernel, check interrupted DOZE/NAP mode and
@@ -398,6 +404,13 @@ BEGIN_FTR_SECTION
 	lwarx	r7,0,r1
 END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	stwcx.	r0,0,r1			/* to clear the reservation */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	andi.	r4,r8,MSR_PR
+	beq	3f
+	CURRENT_THREAD_INFO(r4, r1)
+	ACCOUNT_CPU_USER_EXIT(r4, r5, r7)
+3:
+#endif
 	lwz	r4,_LINK(r1)
 	lwz	r5,_CCR(r1)
 	mtlr	r4
@@ -769,6 +782,10 @@ restore_user:
 	andis.	r10,r0,DBCR0_IDM@h
 	bnel-	load_dbcr0
 #endif
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	CURRENT_THREAD_INFO(r9, r1)
+	ACCOUNT_CPU_USER_EXIT(r9, r10, r11)
+#endif
 
 	b	restore
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 73e461a3dfbb..fcb2887f5a33 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -72,7 +72,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
 	beq	2f			/* if from kernel mode */
-	ACCOUNT_CPU_USER_ENTRY(r10, r11)
+	ACCOUNT_CPU_USER_ENTRY(r13, r10, r11)
 2:	std	r2,GPR2(r1)
 	std	r3,GPR3(r1)
 	mfcr	r2
@@ -246,7 +246,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	ld	r4,_LINK(r1)
 
 	beq-	1f
-	ACCOUNT_CPU_USER_EXIT(r11, r12)
+	ACCOUNT_CPU_USER_EXIT(r13, r11, r12)
 
 BEGIN_FTR_SECTION
 	HMT_MEDIUM_LOW
@@ -453,7 +453,7 @@ _GLOBAL(ret_from_kernel_thread)
 	REST_NVGPRS(r1)
 	mtlr	r14
 	mr	r3,r15
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 	mr	r12,r14
 #endif
 	blrl
@@ -859,7 +859,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 BEGIN_FTR_SECTION
 	mtspr	SPRN_PPR,r2	/* Restore PPR */
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-	ACCOUNT_CPU_USER_EXIT(r2, r4)
+	ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
 	REST_GPR(13, r1)
 1:
 	mtspr	SPRN_SRR1,r3
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 488e6314f993..38a1f96430e1 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -386,7 +386,7 @@ exc_##n##_common:							    \
 	std	r10,_NIP(r1);		/* save SRR0 to stackframe */	    \
 	std	r11,_MSR(r1);		/* save SRR1 to stackframe */	    \
 	beq	2f;			/* if from kernel mode */	    \
-	ACCOUNT_CPU_USER_ENTRY(r10,r11);/* accounting (uses cr0+eq) */	    \
+	ACCOUNT_CPU_USER_ENTRY(r13,r10,r11);/* accounting (uses cr0+eq) */  \
 2:	ld	r3,excf+EX_R10(r13);	/* get back r10 */		    \
 	ld	r4,excf+EX_R11(r13);	/* get back r11 */		    \
 	mfspr	r5,scratch;		/* get back r13 */		    \
@@ -453,7 +453,7 @@ exc_##n##_bad_stack:							    \
 	sth	r1,PACA_TRAP_SAVE(r13);	/* store trap */		    \
 	b	bad_stack_book3e;	/* bad stack error */
 
-/* WARNING: If you change the layout of this stub, make sure you chcek
+/* WARNING: If you change the layout of this stub, make sure you check
 	*   the debug exception handler which handles single stepping
 	*   into exceptions from userspace, and the MM code in
 	*   arch/powerpc/mm/tlb_nohash.c which patches the branch here
@@ -1059,7 +1059,7 @@ fast_exception_return:
 	andi.	r6,r10,MSR_PR
 	REST_2GPRS(6, r1)
 	beq	1f
-	ACCOUNT_CPU_USER_EXIT(r10, r11)
+	ACCOUNT_CPU_USER_EXIT(r13, r10, r11)
 	ld	r0,GPR13(r1)
 
 1:	stdcx.	r0,0,r1		/* to clear the reservation */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 8bcc1b457115..694def6c9d61 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -107,25 +107,9 @@ BEGIN_FTR_SECTION
 	beq	9f
 
 	cmpwi	cr3,r13,2
-
-	/*
-	 * Check if last bit of HSPGR0 is set. This indicates whether we are
-	 * waking up from winkle.
-	 */
 	GET_PACA(r13)
-	clrldi	r5,r13,63
-	clrrdi	r13,r13,1
-	cmpwi	cr4,r5,1
-	mtspr	SPRN_HSPRG0,r13
-
-	lbz	r0,PACA_THREAD_IDLE_STATE(r13)
-	cmpwi   cr2,r0,PNV_THREAD_NAP
-	bgt     cr2,8f				/* Either sleep or Winkle */
+	bl	pnv_restore_hyp_resource
 
-	/* Waking up from nap should not cause hypervisor state loss */
-	bgt	cr3,.
-
-	/* Waking up from nap */
 	li	r0,PNV_THREAD_RUNNING
 	stb	r0,PACA_THREAD_IDLE_STATE(r13)	/* Clear thread state */
 
@@ -143,13 +127,9 @@ BEGIN_FTR_SECTION
 
 	/* Return SRR1 from power7_nap() */
 	mfspr	r3,SPRN_SRR1
-	beq	cr3,2f
-	b	power7_wakeup_noloss
-2:	b	power7_wakeup_loss
-
-	/* Fast Sleep wakeup on PowerNV */
-8:	GET_PACA(r13)
-	b 	power7_wakeup_tb_loss
+	blt	cr3,2f
+	b	pnv_wakeup_loss
+2:	b	pnv_wakeup_noloss
 
 9:
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
@@ -351,6 +331,12 @@ hv_doorbell_trampoline:
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	h_doorbell_hv
 
+	. = 0xea0
+hv_virt_irq_trampoline:
+	SET_SCRATCH0(r13)
+	EXCEPTION_PROLOG_0(PACA_EXGEN)
+	b	h_virt_irq_hv
+
 	/* We need to deal with the Altivec unavailable exception
 	 * here which is at 0xf20, thus in the middle of the
 	 * prolog code of the PerformanceMonitor one. A little
@@ -601,6 +587,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	MASKABLE_EXCEPTION_HV_OOL(0xe82, h_doorbell)
 	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe82)
 
+	MASKABLE_EXCEPTION_HV_OOL(0xea2, h_virt_irq)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xea2)
+
 	/* moved from 0xf00 */
 	STD_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
 	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00)
@@ -680,6 +669,10 @@ _GLOBAL(__replay_interrupt)
 BEGIN_FTR_SECTION
 	cmpwi	r3,0xe80
 	beq	h_doorbell_common
+	cmpwi	r3,0xea0
+	beq	h_virt_irq_common
+	cmpwi	r3,0xe60
+	beq	hmi_exception_common
 FTR_SECTION_ELSE
 	cmpwi	r3,0xa00
 	beq	doorbell_super_common
@@ -754,6 +747,7 @@ kvmppc_skip_Hinterrupt:
 #else
 	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception)
 #endif
+	STD_EXCEPTION_COMMON_ASYNC(0xea0, h_virt_irq, do_IRQ)
 	STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, performance_monitor_exception)
 	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, instruction_breakpoint_exception)
 	STD_EXCEPTION_COMMON(0x1502, denorm, unknown_exception)
@@ -762,11 +756,6 @@ kvmppc_skip_Hinterrupt:
 #else
 	STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception)
 #endif
-#ifdef CONFIG_CBE_RAS
-	STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception)
-	STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception)
-	STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception)
-#endif /* CONFIG_CBE_RAS */
 
 	/*
 	 * Relocation-on interrupts: A subset of the interrupts can be delivered
@@ -877,6 +866,12 @@ h_doorbell_relon_trampoline:
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	h_doorbell_relon_hv
 
+	. = 0x4ea0
+h_virt_irq_relon_trampoline:
+	SET_SCRATCH0(r13)
+	EXCEPTION_PROLOG_0(PACA_EXGEN)
+	b	h_virt_irq_relon_hv
+
 	. = 0x4f00
 performance_monitor_relon_pseries_trampoline:
 	SET_SCRATCH0(r13)
@@ -1131,12 +1126,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	bl	vsx_unavailable_exception
 	b	ret_from_except
 
-	STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception)
-	STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception)
-
 	/* Equivalents to the above handlers for relocation-on interrupt vectors */
 	STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist)
 	MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell)
+	MASKABLE_RELON_EXCEPTION_HV_OOL(0xea0, h_virt_irq)
 
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
@@ -1170,9 +1163,18 @@ fwnmi_data_area:
 	. = 0x8000
 #endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
 
+	STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception)
+	STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception)
+
+#ifdef CONFIG_CBE_RAS
+	STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception)
+	STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception)
+	STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception)
+#endif /* CONFIG_CBE_RAS */
+
 	.globl hmi_exception_early
 hmi_exception_early:
-	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0xe60)
+	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, 0xe62)
 	mr	r10,r1			/* Save r1			*/
 	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack		*/
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
@@ -1289,7 +1291,7 @@ machine_check_handle_early:
 	GET_PACA(r13)
 	ld	r1,PACAR1(r13)
 	li	r3,PNV_THREAD_NAP
-	b	power7_enter_nap_mode
+	b	pnv_enter_arch207_idle_mode
 4:
 #endif
 	/*
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 3cb3b02a13dd..b3a663333d36 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -1009,8 +1009,7 @@ static int fadump_invalidate_dump(struct fadump_mem_struct *fdm)
 	} while (wait_time);
 
 	if (rc) {
-		printk(KERN_ERR "Failed to invalidate firmware-assisted dump "
-			"rgistration. unexpected error(%d).\n", rc);
+		pr_err("Failed to invalidate firmware-assisted dump registration. Unexpected error (%d).\n", rc);
 		return rc;
 	}
 	fw_dump.dump_active = 0;
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 1123a4d8d8dd..cc52d9795f88 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -144,6 +144,21 @@ __ftrace_make_nop(struct module *mod,
 		return -EINVAL;
 	}
 
+#ifdef CC_USING_MPROFILE_KERNEL
+	/* When using -mkernel_profile there is no load to jump over */
+	pop = PPC_INST_NOP;
+
+	if (probe_kernel_read(&op, (void *)(ip - 4), 4)) {
+		pr_err("Fetching instruction at %lx failed.\n", ip - 4);
+		return -EFAULT;
+	}
+
+	/* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
+	if (op != PPC_INST_MFLR && op != PPC_INST_STD_LR) {
+		pr_err("Unexpected instruction %08x around bl _mcount\n", op);
+		return -EINVAL;
+	}
+#else
 	/*
 	 * Our original call site looks like:
 	 *
@@ -170,24 +185,10 @@ __ftrace_make_nop(struct module *mod,
 	}
 
 	if (op != PPC_INST_LD_TOC) {
-		unsigned int inst;
-
-		if (probe_kernel_read(&inst, (void *)(ip - 4), 4)) {
-			pr_err("Fetching instruction at %lx failed.\n", ip - 4);
-			return -EFAULT;
-		}
-
-		/* We expect either a mlfr r0, or a std r0, LRSAVE(r1) */
-		if (inst != PPC_INST_MFLR && inst != PPC_INST_STD_LR) {
-			pr_err("Unexpected instructions around bl _mcount\n"
-			       "when enabling dynamic ftrace!\t"
-			       "(%08x,bl,%08x)\n", inst, op);
-			return -EINVAL;
-		}
-
-		/* When using -mkernel_profile there is no load to jump over */
-		pop = PPC_INST_NOP;
+		pr_err("Expected %08x found %08x\n", PPC_INST_LD_TOC, op);
+		return -EINVAL;
 	}
+#endif /* CC_USING_MPROFILE_KERNEL */
 
 	if (patch_instruction((unsigned int *)ip, pop)) {
 		pr_err("Patching NOP failed.\n");
@@ -608,7 +609,7 @@ unsigned long __init arch_syscall_addr(int nr)
 }
 #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */
 
-#if defined(CONFIG_PPC64) && (!defined(_CALL_ELF) || _CALL_ELF != 2)
+#ifdef PPC64_ELF_ABI_v1
 char *arch_ftrace_match_adjust(char *str, const char *search)
 {
 	if (str[0] == '.' && search[0] != '.')
@@ -616,4 +617,4 @@ char *arch_ftrace_match_adjust(char *str, const char *search)
 	else
 		return str;
 }
-#endif /* defined(CONFIG_PPC64) && (!defined(_CALL_ELF) || _CALL_ELF != 2) */
+#endif /* PPC64_ELF_ABI_v1 */
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 2d14774af6b4..f765b0434731 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -401,7 +401,7 @@ generic_secondary_common_init:
 	ld	r12,CPU_SPEC_RESTORE(r23)
 	cmpdi	0,r12,0
 	beq	3f
-#if !defined(_CALL_ELF) || _CALL_ELF != 2
+#ifdef PPC64_ELF_ABI_v1
 	ld	r12,0(r12)
 #endif
 	mtctr	r12
@@ -941,7 +941,7 @@ start_here_multiplatform:
 	mtspr	SPRN_SRR1,r4
 	RFI
 	b	.	/* prevent speculative execution */
-	
+
 	/* This is where all platforms converge execution */
 
 start_here_common:
@@ -951,9 +951,6 @@ start_here_common:
 	/* Load the TOC (virtual address) */
 	ld	r2,PACATOC(r13)
 
-	/* Do more system initializations in virtual mode */
-	bl	setup_system
-
 	/* Mark interrupts soft and hard disabled (they might be enabled
 	 * in the PACA when doing hotplug)
 	 */
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 80c69472314e..43ddaae42baf 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -30,6 +30,7 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
+#include <asm/fixmap.h>
 
 /* Macro to make the code more readable. */
 #ifdef CONFIG_8xx_CPU6
@@ -383,28 +384,57 @@ InstructionTLBMiss:
 	EXCEPTION_EPILOG_0
 	rfi
 
+/*
+ * Bottom part of DataStoreTLBMiss handler for IMMR area
+ * not enough space in the DataStoreTLBMiss area
+ */
+DTLBMissIMMR:
+	mtcr	r10
+	/* Set 512k byte guarded page and mark it valid */
+	li	r10, MD_PS512K | MD_GUARDED | MD_SVALID
+	MTSPR_CPU6(SPRN_MD_TWC, r10, r11)
+	mfspr	r10, SPRN_IMMR			/* Get current IMMR */
+	rlwinm	r10, r10, 0, 0xfff80000		/* Get 512 kbytes boundary */
+	ori	r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY	| \
+			  _PAGE_PRESENT | _PAGE_NO_CACHE
+	MTSPR_CPU6(SPRN_MD_RPN, r10, r11)	/* Update TLB entry */
+
+	li	r11, RPN_PATTERN
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	EXCEPTION_EPILOG_0
+	rfi
+
 	. = 0x1200
 DataStoreTLBMiss:
-	mtspr	SPRN_SPRG_SCRATCH2, r3
 	EXCEPTION_PROLOG_0
-	mfcr	r3
+	mfcr	r10
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
 	 */
-	mfspr	r10, SPRN_MD_EPN
-	IS_KERNEL(r11, r10)
+	mfspr	r11, SPRN_MD_EPN
+	rlwinm	r11, r11, 16, 0xfff8
+#ifndef CONFIG_PIN_TLB_IMMR
+	cmpli	cr0, r11, VIRT_IMMR_BASE@h
+#endif
+	cmpli	cr7, r11, PAGE_OFFSET@h
+#ifndef CONFIG_PIN_TLB_IMMR
+_ENTRY(DTLBMiss_jmp)
+	beq-	DTLBMissIMMR
+#endif
+	bge-	cr7, 4f
+
 	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
-	BRANCH_UNLESS_KERNEL(3f)
-	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
 3:
+	mtcr	r10
+#ifdef CONFIG_8xx_CPU6
+	mtspr	SPRN_SPRG_SCRATCH2, r3
+#endif
+	mfspr	r10, SPRN_MD_EPN
 
 	/* Insert level 1 index */
 	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
-	mtcr	r11
-	bt-	28,DTLBMiss8M		/* bit 28 = Large page (8M) */
-	mtcr	r3
 
 	/* We have a pte table, so load fetch the pte from the table.
 	 */
@@ -452,29 +482,30 @@ DataStoreTLBMiss:
 	MTSPR_CPU6(SPRN_MD_RPN, r10, r3)	/* Update TLB entry */
 
 	/* Restore registers */
+#ifdef CONFIG_8xx_CPU6
 	mfspr	r3, SPRN_SPRG_SCRATCH2
+#endif
 	mtspr	SPRN_DAR, r11	/* Tag DAR */
 	EXCEPTION_EPILOG_0
 	rfi
 
-DTLBMiss8M:
-	mtcr	r3
-	ori	r11, r11, MD_SVALID
-	MTSPR_CPU6(SPRN_MD_TWC, r11, r3)
-#ifdef CONFIG_PPC_16K_PAGES
-	/*
-	 * In 16k pages mode, each PGD entry defines a 64M block.
-	 * Here we select the 8M page within the block.
-	 */
-	rlwimi	r11, r10, 0, 0x03800000
-#endif
-	rlwinm	r10, r11, 0, 0xff800000
+4:
+_ENTRY(DTLBMiss_cmp)
+	cmpli	cr0, r11, (PAGE_OFFSET + 0x1800000)@h
+	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
+	bge-	3b
+
+	mtcr	r10
+	/* Set 8M byte page and mark it valid */
+	li	r10, MD_PS8MEG | MD_SVALID
+	MTSPR_CPU6(SPRN_MD_TWC, r10, r11)
+	mfspr	r10, SPRN_MD_EPN
+	rlwinm	r10, r10, 0, 0x0f800000		/* 8xx supports max 256Mb RAM */
 	ori	r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY	| \
 			  _PAGE_PRESENT
-	MTSPR_CPU6(SPRN_MD_RPN, r10, r3)	/* Update TLB entry */
+	MTSPR_CPU6(SPRN_MD_RPN, r10, r11)	/* Update TLB entry */
 
 	li	r11, RPN_PATTERN
-	mfspr	r3, SPRN_SPRG_SCRATCH2
 	mtspr	SPRN_DAR, r11	/* Tag DAR */
 	EXCEPTION_EPILOG_0
 	rfi
@@ -553,12 +584,14 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	IS_KERNEL(r11, r10)
 	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
 	BRANCH_UNLESS_KERNEL(3f)
+	rlwinm	r11, r10, 16, 0xfff8
+_ENTRY(FixupDAR_cmp)
+	cmpli	cr7, r11, (PAGE_OFFSET + 0x1800000)@h
+	blt-	cr7, 200f
 	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
 	/* Insert level 1 index */
 3:	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
-	mtcr	r11
-	bt	28,200f		/* bit 28 = Large page (8M) */
 	rlwinm	r11, r11,0,0,19	/* Extract page descriptor page address */
 	/* Insert level 2 index */
 	rlwimi	r11, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
@@ -584,8 +617,8 @@ FixupDAR:/* Entry point for dcbx workaround. */
 141:	mfspr	r10,SPRN_SPRG_SCRATCH2
 	b	DARFixed	/* Nope, go back to normal TLB processing */
 
-	/* concat physical page address(r11) and page offset(r10) */
-200:	rlwimi	r11, r10, 0, 32 - (PAGE_SHIFT << 1), 31
+	/* create physical page address from effective address */
+200:	tophys(r11, r10)
 	b	201b
 
 144:	mfspr	r10, SPRN_DSISR
@@ -763,10 +796,18 @@ start_here:
  * virtual to physical.  Also, set the cache mode since that is defined
  * by TLB entries and perform any additional mapping (like of the IMMR).
  * If configured to pin some TLBs, we pin the first 8 Mbytes of kernel,
- * 24 Mbytes of data, and the 8M IMMR space.  Anything not covered by
+ * 24 Mbytes of data, and the 512k IMMR space.  Anything not covered by
  * these mappings is mapped by page tables.
  */
 initial_mmu:
+	li	r8, 0
+	mtspr	SPRN_MI_CTR, r8		/* remove PINNED ITLB entries */
+	lis	r10, MD_RESETVAL@h
+#ifndef CONFIG_8xx_COPYBACK
+	oris	r10, r10, MD_WTDEF@h
+#endif
+	mtspr	SPRN_MD_CTR, r10	/* remove PINNED DTLB entries */
+
 	tlbia			/* Invalidate all TLB entries */
 /* Always pin the first 8 MB ITLB to prevent ITLB
    misses while mucking around with SRR0/SRR1 in asm
@@ -777,34 +818,20 @@ initial_mmu:
 	mtspr	SPRN_MI_CTR, r8	/* Set instruction MMU control */
 
 #ifdef CONFIG_PIN_TLB
-	lis	r10, (MD_RSV4I | MD_RESETVAL)@h
-	ori	r10, r10, 0x1c00
-	mr	r8, r10
-#else
-	lis	r10, MD_RESETVAL@h
-#endif
-#ifndef CONFIG_8xx_COPYBACK
-	oris	r10, r10, MD_WTDEF@h
-#endif
+	oris	r10, r10, MD_RSV4I@h
 	mtspr	SPRN_MD_CTR, r10	/* Set data TLB control */
+#endif
 
-	/* Now map the lower 8 Meg into the TLBs.  For this quick hack,
-	 * we can load the instruction and data TLB registers with the
-	 * same values.
-	 */
+	/* Now map the lower 8 Meg into the ITLB. */
 	lis	r8, KERNELBASE@h	/* Create vaddr for TLB */
 	ori	r8, r8, MI_EVALID	/* Mark it valid */
 	mtspr	SPRN_MI_EPN, r8
-	mtspr	SPRN_MD_EPN, r8
 	li	r8, MI_PS8MEG | (2 << 5)	/* Set 8M byte page, APG 2 */
 	ori	r8, r8, MI_SVALID	/* Make it valid */
 	mtspr	SPRN_MI_TWC, r8
-	li	r8, MI_PS8MEG		/* Set 8M byte page, APG 0 */
-	ori	r8, r8, MI_SVALID	/* Make it valid */
-	mtspr	SPRN_MD_TWC, r8
 	li	r8, MI_BOOTINIT		/* Create RPN for address 0 */
 	mtspr	SPRN_MI_RPN, r8		/* Store TLB entry */
-	mtspr	SPRN_MD_RPN, r8
+
 	lis	r8, MI_APG_INIT@h	/* Set protection modes */
 	ori	r8, r8, MI_APG_INIT@l
 	mtspr	SPRN_MI_AP, r8
@@ -812,51 +839,25 @@ initial_mmu:
 	ori	r8, r8, MD_APG_INIT@l
 	mtspr	SPRN_MD_AP, r8
 
-	/* Map another 8 MByte at the IMMR to get the processor
+	/* Map a 512k page for the IMMR to get the processor
 	 * internal registers (among other things).
 	 */
-#ifdef CONFIG_PIN_TLB
-	addi	r10, r10, 0x0100
+#ifdef CONFIG_PIN_TLB_IMMR
+	ori	r10, r10, 0x1c00
 	mtspr	SPRN_MD_CTR, r10
-#endif
+
 	mfspr	r9, 638			/* Get current IMMR */
-	andis.	r9, r9, 0xff80		/* Get 8Mbyte boundary */
+	andis.	r9, r9, 0xfff8		/* Get 512 kbytes boundary */
 
-	mr	r8, r9			/* Create vaddr for TLB */
+	lis	r8, VIRT_IMMR_BASE@h	/* Create vaddr for TLB */
 	ori	r8, r8, MD_EVALID	/* Mark it valid */
 	mtspr	SPRN_MD_EPN, r8
-	li	r8, MD_PS8MEG		/* Set 8M byte page */
+	li	r8, MD_PS512K | MD_GUARDED	/* Set 512k byte page */
 	ori	r8, r8, MD_SVALID	/* Make it valid */
 	mtspr	SPRN_MD_TWC, r8
 	mr	r8, r9			/* Create paddr for TLB */
 	ori	r8, r8, MI_BOOTINIT|0x2 /* Inhibit cache -- Cort */
 	mtspr	SPRN_MD_RPN, r8
-
-#ifdef CONFIG_PIN_TLB
-	/* Map two more 8M kernel data pages.
-	*/
-	addi	r10, r10, 0x0100
-	mtspr	SPRN_MD_CTR, r10
-
-	lis	r8, KERNELBASE@h	/* Create vaddr for TLB */
-	addis	r8, r8, 0x0080		/* Add 8M */
-	ori	r8, r8, MI_EVALID	/* Mark it valid */
-	mtspr	SPRN_MD_EPN, r8
-	li	r9, MI_PS8MEG		/* Set 8M byte page */
-	ori	r9, r9, MI_SVALID	/* Make it valid */
-	mtspr	SPRN_MD_TWC, r9
-	li	r11, MI_BOOTINIT	/* Create RPN for address 0 */
-	addis	r11, r11, 0x0080	/* Add 8M */
-	mtspr	SPRN_MD_RPN, r11
-
-	addi	r10, r10, 0x0100
-	mtspr	SPRN_MD_CTR, r10
-
-	addis	r8, r8, 0x0080		/* Add 8M */
-	mtspr	SPRN_MD_EPN, r8
-	mtspr	SPRN_MD_TWC, r9
-	addis	r11, r11, 0x0080	/* Add 8M */
-	mtspr	SPRN_MD_RPN, r11
 #endif
 
 	/* Since the cache is enabled according to the information we
diff --git a/arch/powerpc/kernel/hmi.c b/arch/powerpc/kernel/hmi.c
new file mode 100644
index 000000000000..e3f738eb1cac
--- /dev/null
+++ b/arch/powerpc/kernel/hmi.c
@@ -0,0 +1,56 @@
+/*
+ * Hypervisor Maintenance Interrupt (HMI) handling.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.
+ *
+ * Copyright 2015 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <asm/paca.h>
+#include <asm/hmi.h>
+
+void wait_for_subcore_guest_exit(void)
+{
+	int i;
+
+	/*
+	 * NULL bitmap pointer indicates that KVM module hasn't
+	 * been loaded yet and hence no guests are running.
+	 * If no KVM is in use, no need to co-ordinate among threads
+	 * as all of them will always be in host and no one is going
+	 * to modify TB other than the opal hmi handler.
+	 * Hence, just return from here.
+	 */
+	if (!local_paca->sibling_subcore_state)
+		return;
+
+	for (i = 0; i < MAX_SUBCORE_PER_CORE; i++)
+		while (local_paca->sibling_subcore_state->in_guest[i])
+			cpu_relax();
+}
+
+void wait_for_tb_resync(void)
+{
+	if (!local_paca->sibling_subcore_state)
+		return;
+
+	while (test_bit(CORE_TB_RESYNC_REQ_BIT,
+				&local_paca->sibling_subcore_state->flags))
+		cpu_relax();
+}
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_book3s.S
index 470ceebd2d23..8a56a51fc0cb 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -1,5 +1,6 @@
 /*
- *  This file contains the power_save function for Power7 CPUs.
+ *  This file contains idle entry/exit functions for POWER7,
+ *  POWER8 and POWER9 CPUs.
  *
  *  This program is free software; you can redistribute it and/or
  *  modify it under the terms of the GNU General Public License
@@ -20,6 +21,7 @@
 #include <asm/opal.h>
 #include <asm/cpuidle.h>
 #include <asm/book3s/64/mmu-hash.h>
+#include <asm/mmu.h>
 
 #undef DEBUG
 
@@ -36,6 +38,11 @@
 #define _AMOR	GPR9
 #define _WORT	GPR10
 #define _WORC	GPR11
+#define _PTCR	GPR12
+
+#define PSSCR_HV_TEMPLATE	PSSCR_ESL | PSSCR_EC | \
+				PSSCR_PSLL_MASK | PSSCR_TR_MASK | \
+				PSSCR_MTL_MASK
 
 /* Idle state entry routines */
 
@@ -52,6 +59,45 @@
 	.text
 
 /*
+ * Used by threads before entering deep idle states. Saves SPRs
+ * in interrupt stack frame
+ */
+save_sprs_to_stack:
+	/*
+	 * Note all register i.e per-core, per-subcore or per-thread is saved
+	 * here since any thread in the core might wake up first
+	 */
+BEGIN_FTR_SECTION
+	mfspr	r3,SPRN_PTCR
+	std	r3,_PTCR(r1)
+	/*
+	 * Note - SDR1 is dropped in Power ISA v3. Hence not restoring
+	 * SDR1 here
+	 */
+FTR_SECTION_ELSE
+	mfspr	r3,SPRN_SDR1
+	std	r3,_SDR1(r1)
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
+	mfspr	r3,SPRN_RPR
+	std	r3,_RPR(r1)
+	mfspr	r3,SPRN_SPURR
+	std	r3,_SPURR(r1)
+	mfspr	r3,SPRN_PURR
+	std	r3,_PURR(r1)
+	mfspr	r3,SPRN_TSCR
+	std	r3,_TSCR(r1)
+	mfspr	r3,SPRN_DSCR
+	std	r3,_DSCR(r1)
+	mfspr	r3,SPRN_AMOR
+	std	r3,_AMOR(r1)
+	mfspr	r3,SPRN_WORT
+	std	r3,_WORT(r1)
+	mfspr	r3,SPRN_WORC
+	std	r3,_WORC(r1)
+
+	blr
+
+/*
  * Used by threads when the lock bit of core_idle_state is set.
  * Threads will spin in HMT_LOW until the lock bit is cleared.
  * r14 - pointer to core_idle_state
@@ -69,13 +115,16 @@ core_idle_lock_held:
 
 /*
  * Pass requested state in r3:
- *	r3 - PNV_THREAD_NAP/SLEEP/WINKLE
+ *	r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8
+ *	   - Requested STOP state in POWER9
  *
  * To check IRQ_HAPPENED in r4
  * 	0 - don't check
  * 	1 - check
+ *
+ * Address to 'rfid' to in r5
  */
-_GLOBAL(power7_powersave_common)
+_GLOBAL(pnv_powersave_common)
 	/* Use r3 to pass state nap/sleep/winkle */
 	/* NAP is a state loss, we create a regs frame on the
 	 * stack, fill it up with the state we care about and
@@ -126,28 +175,28 @@ _GLOBAL(power7_powersave_common)
 	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/* Tell KVM we're entering idle */
+	li	r4,KVM_HWTHREAD_IN_IDLE
+	stb	r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
+
 	/*
 	 * Go to real mode to do the nap, as required by the architecture.
 	 * Also, we need to be in real mode before setting hwthread_state,
 	 * because as soon as we do that, another thread can switch
 	 * the MMU context to the guest.
 	 */
-	LOAD_REG_IMMEDIATE(r5, MSR_IDLE)
+	LOAD_REG_IMMEDIATE(r7, MSR_IDLE)
 	li	r6, MSR_RI
 	andc	r6, r9, r6
-	LOAD_REG_ADDR(r7, power7_enter_nap_mode)
 	mtmsrd	r6, 1		/* clear RI before setting SRR0/1 */
-	mtspr	SPRN_SRR0, r7
-	mtspr	SPRN_SRR1, r5
+	mtspr	SPRN_SRR0, r5
+	mtspr	SPRN_SRR1, r7
 	rfid
 
-	.globl	power7_enter_nap_mode
-power7_enter_nap_mode:
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	/* Tell KVM we're napping */
-	li	r4,KVM_HWTHREAD_IN_NAP
-	stb	r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
+	.globl pnv_enter_arch207_idle_mode
+pnv_enter_arch207_idle_mode:
 	stb	r3,PACA_THREAD_IDLE_STATE(r13)
 	cmpwi	cr3,r3,PNV_THREAD_SLEEP
 	bge	cr3,2f
@@ -196,8 +245,7 @@ fastsleep_workaround_at_entry:
 	/* Fast sleep workaround */
 	li	r3,1
 	li	r4,1
-	li	r0,OPAL_CONFIG_CPU_IDLE_STATE
-	bl	opal_call_realmode
+	bl	opal_rm_config_cpu_idle_state
 
 	/* Clear Lock bit */
 	li	r0,0
@@ -206,30 +254,45 @@ fastsleep_workaround_at_entry:
 	b	common_enter
 
 enter_winkle:
-	/*
-	 * Note all register i.e per-core, per-subcore or per-thread is saved
-	 * here since any thread in the core might wake up first
-	 */
-	mfspr	r3,SPRN_SDR1
-	std	r3,_SDR1(r1)
-	mfspr	r3,SPRN_RPR
-	std	r3,_RPR(r1)
-	mfspr	r3,SPRN_SPURR
-	std	r3,_SPURR(r1)
-	mfspr	r3,SPRN_PURR
-	std	r3,_PURR(r1)
-	mfspr	r3,SPRN_TSCR
-	std	r3,_TSCR(r1)
-	mfspr	r3,SPRN_DSCR
-	std	r3,_DSCR(r1)
-	mfspr	r3,SPRN_AMOR
-	std	r3,_AMOR(r1)
-	mfspr	r3,SPRN_WORT
-	std	r3,_WORT(r1)
-	mfspr	r3,SPRN_WORC
-	std	r3,_WORC(r1)
+	bl	save_sprs_to_stack
+
 	IDLE_STATE_ENTER_SEQ(PPC_WINKLE)
 
+/*
+ * r3 - requested stop state
+ */
+power_enter_stop:
+/*
+ * Check if the requested state is a deep idle state.
+ */
+	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
+	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
+	cmpd	r3,r4
+	bge	2f
+	IDLE_STATE_ENTER_SEQ(PPC_STOP)
+2:
+/*
+ * Entering deep idle state.
+ * Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to
+ * stack and enter stop
+ */
+	lbz     r7,PACA_THREAD_MASK(r13)
+	ld      r14,PACA_CORE_IDLE_STATE_PTR(r13)
+
+lwarx_loop_stop:
+	lwarx   r15,0,r14
+	andi.   r9,r15,PNV_CORE_IDLE_LOCK_BIT
+	bnel    core_idle_lock_held
+	andc    r15,r15,r7                      /* Clear thread bit */
+
+	stwcx.  r15,0,r14
+	bne-    lwarx_loop_stop
+	isync
+
+	bl	save_sprs_to_stack
+
+	IDLE_STATE_ENTER_SEQ(PPC_STOP)
+
 _GLOBAL(power7_idle)
 	/* Now check if user or arch enabled NAP mode */
 	LOAD_REG_ADDRBASE(r3,powersave_nap)
@@ -242,19 +305,22 @@ _GLOBAL(power7_idle)
 _GLOBAL(power7_nap)
 	mr	r4,r3
 	li	r3,PNV_THREAD_NAP
-	b	power7_powersave_common
+	LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode)
+	b	pnv_powersave_common
 	/* No return */
 
 _GLOBAL(power7_sleep)
 	li	r3,PNV_THREAD_SLEEP
 	li	r4,1
-	b	power7_powersave_common
+	LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode)
+	b	pnv_powersave_common
 	/* No return */
 
 _GLOBAL(power7_winkle)
-	li	r3,3
+	li	r3,PNV_THREAD_WINKLE
 	li	r4,1
-	b	power7_powersave_common
+	LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode)
+	b	pnv_powersave_common
 	/* No return */
 
 #define CHECK_HMI_INTERRUPT						\
@@ -270,25 +336,106 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66);		\
 	ld	r2,PACATOC(r13);					\
 	ld	r1,PACAR1(r13);						\
 	std	r3,ORIG_GPR3(r1);	/* Save original r3 */		\
-	li	r0,OPAL_HANDLE_HMI;	/* Pass opal token argument*/	\
-	bl	opal_call_realmode;					\
+	li	r3,0;			/* NULL argument */		\
+	bl	hmi_exception_realmode;					\
+	nop;								\
 	ld	r3,ORIG_GPR3(r1);	/* Restore original r3 */	\
 20:	nop;
 
 
-_GLOBAL(power7_wakeup_tb_loss)
+/*
+ * r3 - requested stop state
+ */
+_GLOBAL(power9_idle_stop)
+	LOAD_REG_IMMEDIATE(r4, PSSCR_HV_TEMPLATE)
+	or	r4,r4,r3
+	mtspr	SPRN_PSSCR, r4
+	li	r4, 1
+	LOAD_REG_ADDR(r5,power_enter_stop)
+	b	pnv_powersave_common
+	/* No return */
+/*
+ * Called from reset vector. Check whether we have woken up with
+ * hypervisor state loss. If yes, restore hypervisor state and return
+ * back to reset vector.
+ *
+ * r13 - Contents of HSPRG0
+ * cr3 - set to gt if waking up with partial/complete hypervisor state loss
+ */
+_GLOBAL(pnv_restore_hyp_resource)
 	ld	r2,PACATOC(r13);
+BEGIN_FTR_SECTION
+	/*
+	 * POWER ISA 3. Use PSSCR to determine if we
+	 * are waking up from deep idle state
+	 */
+	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
+	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
+
+	mfspr	r5,SPRN_PSSCR
+	/*
+	 * 0-3 bits correspond to Power-Saving Level Status
+	 * which indicates the idle state we are waking up from
+	 */
+	rldicl  r5,r5,4,60
+	cmpd	cr4,r5,r4
+	bge	cr4,pnv_wakeup_tb_loss
+	/*
+	 * Waking up without hypervisor state loss. Return to
+	 * reset vector
+	 */
+	blr
+
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
+	/*
+	 * POWER ISA 2.07 or less.
+	 * Check if last bit of HSPGR0 is set. This indicates whether we are
+	 * waking up from winkle.
+	 */
+	clrldi	r5,r13,63
+	clrrdi	r13,r13,1
+	cmpwi	cr4,r5,1
+	mtspr	SPRN_HSPRG0,r13
+
+	lbz	r0,PACA_THREAD_IDLE_STATE(r13)
+	cmpwi   cr2,r0,PNV_THREAD_NAP
+	bgt     cr2,pnv_wakeup_tb_loss	/* Either sleep or Winkle */
+
+	/*
+	 * We fall through here if PACA_THREAD_IDLE_STATE shows we are waking
+	 * up from nap. At this stage CR3 shouldn't contains 'gt' since that
+	 * indicates we are waking with hypervisor state loss from nap.
+	 */
+	bgt	cr3,.
+
+	blr	/* Return back to System Reset vector from where
+		   pnv_restore_hyp_resource was invoked */
+
+/*
+ * Called if waking up from idle state which can cause either partial or
+ * complete hyp state loss.
+ * In POWER8, called if waking up from fastsleep or winkle
+ * In POWER9, called if waking up from stop state >= pnv_first_deep_stop_state
+ *
+ * r13 - PACA
+ * cr3 - gt if waking up with partial/complete hypervisor state loss
+ * cr4 - eq if waking up from complete hypervisor state loss.
+ */
+_GLOBAL(pnv_wakeup_tb_loss)
 	ld	r1,PACAR1(r13)
 	/*
 	 * Before entering any idle state, the NVGPRs are saved in the stack
 	 * and they are restored before switching to the process context. Hence
 	 * until they are restored, they are free to be used.
 	 *
-	 * Save SRR1 in a NVGPR as it might be clobbered in opal_call_realmode
-	 * (called in CHECK_HMI_INTERRUPT). SRR1 is required to determine the
-	 * wakeup reason if we branch to kvm_start_guest.
+	 * Save SRR1 and LR in NVGPRs as they might be clobbered in
+	 * opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required
+	 * to determine the wakeup reason if we branch to kvm_start_guest. LR
+	 * is required to return back to reset vector after hypervisor state
+	 * restore is complete.
 	 */
-
+	mflr	r17
 	mfspr	r16,SPRN_SRR1
 BEGIN_FTR_SECTION
 	CHECK_HMI_INTERRUPT
@@ -310,35 +457,35 @@ lwarx_loop2:
 	bnel	core_idle_lock_held
 
 	cmpwi	cr2,r15,0
-	lbz	r4,PACA_SUBCORE_SIBLING_MASK(r13)
-	and	r4,r4,r15
-	cmpwi	cr1,r4,0	/* Check if first in subcore */
 
 	/*
 	 * At this stage
-	 * cr1 - 0b0100 if first thread to wakeup in subcore
-	 * cr2 - 0b0100 if first thread to wakeup in core
-	 * cr3-  0b0010 if waking up from sleep or winkle
-	 * cr4 - 0b0100 if waking up from winkle
+	 * cr2 - eq if first thread to wakeup in core
+	 * cr3-  gt if waking up with partial/complete hypervisor state loss
+	 * cr4 - eq if waking up from complete hypervisor state loss.
 	 */
 
-	or	r15,r15,r7		/* Set thread bit */
-
-	beq	cr1,first_thread_in_subcore
-
-	/* Not first thread in subcore to wake up */
-	stwcx.	r15,0,r14
-	bne-	lwarx_loop2
-	isync
-	b	common_exit
-
-first_thread_in_subcore:
-	/* First thread in subcore to wakeup */
 	ori	r15,r15,PNV_CORE_IDLE_LOCK_BIT
 	stwcx.	r15,0,r14
 	bne-	lwarx_loop2
 	isync
 
+BEGIN_FTR_SECTION
+	lbz	r4,PACA_SUBCORE_SIBLING_MASK(r13)
+	and	r4,r4,r15
+	cmpwi	r4,0	/* Check if first in subcore */
+
+	or	r15,r15,r7		/* Set thread bit */
+	beq	first_thread_in_subcore
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+
+	or	r15,r15,r7		/* Set thread bit */
+	beq	cr2,first_thread_in_core
+
+	/* Not first thread in core or subcore to wake up */
+	b	clear_lock
+
+first_thread_in_subcore:
 	/*
 	 * If waking up from sleep, subcore state is not lost. Hence
 	 * skip subcore state restore
@@ -348,6 +495,7 @@ first_thread_in_subcore:
 	/* Restore per-subcore state */
 	ld      r4,_SDR1(r1)
 	mtspr   SPRN_SDR1,r4
+
 	ld      r4,_RPR(r1)
 	mtspr   SPRN_RPR,r4
 	ld	r4,_AMOR(r1)
@@ -363,32 +511,44 @@ subcore_state_restored:
 first_thread_in_core:
 
 	/*
-	 * First thread in the core waking up from fastsleep. It needs to
+	 * First thread in the core waking up from any state which can cause
+	 * partial or complete hypervisor state loss. It needs to
 	 * call the fastsleep workaround code if the platform requires it.
 	 * Call it unconditionally here. The below branch instruction will
-	 * be patched out when the idle states are discovered if platform
-	 * does not require workaround.
+	 * be patched out if the platform does not have fastsleep or does not
+	 * require the workaround. Patching will be performed during the
+	 * discovery of idle-states.
 	 */
 .global pnv_fastsleep_workaround_at_exit
 pnv_fastsleep_workaround_at_exit:
 	b	fastsleep_workaround_at_exit
 
 timebase_resync:
-	/* Do timebase resync if we are waking up from sleep. Use cr3 value
-	 * set in exceptions-64s.S */
+	/*
+	 * Use cr3 which indicates that we are waking up with atleast partial
+	 * hypervisor state loss to determine if TIMEBASE RESYNC is needed.
+	 */
 	ble	cr3,clear_lock
 	/* Time base re-sync */
-	li	r0,OPAL_RESYNC_TIMEBASE
-	bl	opal_call_realmode;
-	/* TODO: Check r3 for failure */
-
+	bl	opal_rm_resync_timebase;
 	/*
 	 * If waking up from sleep, per core state is not lost, skip to
 	 * clear_lock.
 	 */
 	bne	cr4,clear_lock
 
-	/* Restore per core state */
+	/*
+	 * First thread in the core to wake up and its waking up with
+	 * complete hypervisor state loss. Restore per core hypervisor
+	 * state.
+	 */
+BEGIN_FTR_SECTION
+	ld	r4,_PTCR(r1)
+	mtspr	SPRN_PTCR,r4
+	ld	r4,_RPR(r1)
+	mtspr	SPRN_RPR,r4
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
 	ld	r4,_TSCR(r1)
 	mtspr	SPRN_TSCR,r4
 	ld	r4,_WORC(r1)
@@ -410,9 +570,9 @@ common_exit:
 
 	/* Waking up from winkle */
 
-	/* Restore per thread state */
-	bl	__restore_cpu_power8
-
+BEGIN_MMU_FTR_SECTION
+	b	no_segments
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX)
 	/* Restore SLB  from PACA */
 	ld	r8,PACA_SLBSHADOWPTR(r13)
 
@@ -426,6 +586,9 @@ common_exit:
 	slbmte	r6,r5
 1:	addi	r8,r8,16
 	.endr
+no_segments:
+
+	/* Restore per thread state */
 
 	ld	r4,_SPURR(r1)
 	mtspr	SPRN_SPURR,r4
@@ -436,48 +599,34 @@ common_exit:
 	ld	r4,_WORT(r1)
 	mtspr	SPRN_WORT,r4
 
-hypervisor_state_restored:
+	/* Call cur_cpu_spec->cpu_restore() */
+	LOAD_REG_ADDR(r4, cur_cpu_spec)
+	ld	r4,0(r4)
+	ld	r12,CPU_SPEC_RESTORE(r4)
+#ifdef PPC64_ELF_ABI_v1
+	ld	r12,0(r12)
+#endif
+	mtctr	r12
+	bctrl
 
-	li	r5,PNV_THREAD_RUNNING
-	stb     r5,PACA_THREAD_IDLE_STATE(r13)
+hypervisor_state_restored:
 
 	mtspr	SPRN_SRR1,r16
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	li      r0,KVM_HWTHREAD_IN_KERNEL
-	stb     r0,HSTATE_HWTHREAD_STATE(r13)
-	/* Order setting hwthread_state vs. testing hwthread_req */
-	sync
-	lbz     r0,HSTATE_HWTHREAD_REQ(r13)
-	cmpwi   r0,0
-	beq     6f
-	b       kvm_start_guest
-6:
-#endif
-
-	REST_NVGPRS(r1)
-	REST_GPR(2, r1)
-	ld	r3,_CCR(r1)
-	ld	r4,_MSR(r1)
-	ld	r5,_NIP(r1)
-	addi	r1,r1,INT_FRAME_SIZE
-	mtcr	r3
-	mfspr	r3,SPRN_SRR1		/* Return SRR1 */
-	mtspr	SPRN_SRR1,r4
-	mtspr	SPRN_SRR0,r5
-	rfid
+	mtlr	r17
+	blr	/* Return back to System Reset vector from where
+		   pnv_restore_hyp_resource was invoked */
 
 fastsleep_workaround_at_exit:
 	li	r3,1
 	li	r4,0
-	li	r0,OPAL_CONFIG_CPU_IDLE_STATE
-	bl	opal_call_realmode
+	bl	opal_rm_config_cpu_idle_state
 	b	timebase_resync
 
 /*
  * R3 here contains the value that will be returned to the caller
  * of power7_nap.
  */
-_GLOBAL(power7_wakeup_loss)
+_GLOBAL(pnv_wakeup_loss)
 	ld	r1,PACAR1(r13)
 BEGIN_FTR_SECTION
 	CHECK_HMI_INTERRUPT
@@ -497,10 +646,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
  * R3 here contains the value that will be returned to the caller
  * of power7_nap.
  */
-_GLOBAL(power7_wakeup_noloss)
+_GLOBAL(pnv_wakeup_noloss)
 	lbz	r0,PACA_NAPSTATELOST(r13)
 	cmpwi	r0,0
-	bne	power7_wakeup_loss
+	bne	pnv_wakeup_loss
 BEGIN_FTR_SECTION
 	CHECK_HMI_INTERRUPT
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 3cb46a3b1de7..ac910d9982df 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -250,7 +250,7 @@ notrace void arch_local_irq_restore(unsigned long en)
 		if (WARN_ON(mfmsr() & MSR_EE))
 			__hard_irq_disable();
 	}
-#endif /* CONFIG_TRACE_IRQFLAG */
+#endif /* CONFIG_TRACE_IRQFLAGS */
 
 	set_soft_enabled(0);
 
@@ -342,6 +342,21 @@ bool prep_irq_for_idle(void)
 	return true;
 }
 
+/*
+ * Force a replay of the external interrupt handler on this CPU.
+ */
+void force_external_irq_replay(void)
+{
+	/*
+	 * This must only be called with interrupts soft-disabled,
+	 * the replay will happen when re-enabling.
+	 */
+	WARN_ON(!arch_irqs_disabled());
+
+	/* Indicate in the PACA that we have an interrupt to replay */
+	local_paca->irq_happened |= PACA_IRQ_EE;
+}
+
 #endif /* CONFIG_PPC64 */
 
 int arch_show_interrupts(struct seq_file *p, int prec)
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 7c053f281406..3ed8ec09b5c9 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -278,12 +278,11 @@ no_kprobe:
  * 	- When the probed function returns, this probe
  * 		causes the handlers to fire
  */
-static void __used kretprobe_trampoline_holder(void)
-{
-	asm volatile(".global kretprobe_trampoline\n"
-			"kretprobe_trampoline:\n"
-			"nop\n");
-}
+asm(".global kretprobe_trampoline\n"
+	".type kretprobe_trampoline, @function\n"
+	"kretprobe_trampoline:\n"
+	"nop\n"
+	".size kretprobe_trampoline, .-kretprobe_trampoline\n");
 
 /*
  * Called when the probe at kretprobe trampoline is hit
@@ -506,13 +505,11 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 
 	/* setup return addr to the jprobe handler routine */
 	regs->nip = arch_deref_entry_point(jp->entry);
-#ifdef CONFIG_PPC64
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 	regs->gpr[12] = (unsigned long)jp->entry;
-#else
+#elif defined(PPC64_ELF_ABI_v1)
 	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
 #endif
-#endif
 
 	return 1;
 }
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index b8c202d63ecb..4c780a342282 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -29,6 +29,7 @@
 #include <asm/prom.h>
 #include <asm/smp.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/asm-prototypes.h>
 
 #ifdef CONFIG_PPC_BOOK3E
 int default_machine_kexec_prepare(struct kimage *image)
@@ -54,7 +55,7 @@ int default_machine_kexec_prepare(struct kimage *image)
 	const unsigned long *basep;
 	const unsigned int *sizep;
 
-	if (!ppc_md.hpte_clear_all)
+	if (!mmu_hash_ops.hpte_clear_all)
 		return -ENOENT;
 
 	/*
@@ -379,7 +380,12 @@ void default_machine_kexec(struct kimage *image)
 	 */
 	kexec_sequence(&kexec_stack, image->start, image,
 			page_address(image->control_code_page),
-			ppc_md.hpte_clear_all);
+#ifdef CONFIG_PPC_STD_MMU
+			mmu_hash_ops.hpte_clear_all
+#else
+			NULL
+#endif
+	);
 	/* NOTREACHED */
 }
 
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 285ca8c6cc2e..d9c912b6e632 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -104,20 +104,6 @@ _GLOBAL(mulhdu)
 	blr
 
 /*
- * sub_reloc_offset(x) returns x - reloc_offset().
- */
-_GLOBAL(sub_reloc_offset)
-	mflr	r0
-	bl	1f
-1:	mflr	r5
-	lis	r4,1b@ha
-	addi	r4,r4,1b@l
-	subf	r5,r4,r5
-	subf	r3,r5,r3
-	mtlr	r0
-	blr
-
-/*
  * reloc_got2 runs through the .got2 section adding an offset
  * to each entry.
  */
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index f28754c497e5..cb195157b318 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -661,13 +661,13 @@ _GLOBAL(kexec_sequence)
 
 #ifndef CONFIG_PPC_BOOK3E
 	/* clear out hardware hash page table and tlb */
-#if !defined(_CALL_ELF) || _CALL_ELF != 2
+#ifdef PPC64_ELF_ABI_v1
 	ld	r12,0(r27)		/* deref function descriptor */
 #else
 	mr	r12,r27
 #endif
 	mtctr	r12
-	bctrl				/* ppc_md.hpte_clear_all(void); */
+	bctrl				/* mmu_hash_ops.hpte_clear_all(void); */
 #endif /* !CONFIG_PPC_BOOK3E */
 
 /*
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 9ce9a25f58b5..183368e008cf 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -41,7 +41,7 @@
    this, and makes other things simpler.  Anton?
    --RR.  */
 
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 
 /* An address is simply the address of the function. */
 typedef unsigned long func_desc_t;
@@ -132,7 +132,7 @@ static u32 ppc64_stub_insns[] = {
 	/* Save current r2 value in magic place on the stack. */
 	0xf8410000|R2_STACK_OFFSET,	/* std     r2,R2_STACK_OFFSET(r1) */
 	0xe98b0020,			/* ld      r12,32(r11) */
-#if !defined(_CALL_ELF) || _CALL_ELF != 2
+#ifdef PPC64_ELF_ABI_v1
 	/* Set up new r2 from function descriptor */
 	0xe84b0028,			/* ld      r2,40(r11) */
 #endif
@@ -494,9 +494,10 @@ static bool is_early_mcount_callsite(u32 *instruction)
    restore r2. */
 static int restore_r2(u32 *instruction, struct module *me)
 {
+	if (is_early_mcount_callsite(instruction - 1))
+		return 1;
+
 	if (*instruction != PPC_INST_NOP) {
-		if (is_early_mcount_callsite(instruction - 1))
-			return 1;
 		pr_err("%s: Expect noop after relocate, got %08x\n",
 		       me->name, *instruction);
 		return 0;
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 0f7a60f1e9f6..a5c0153ede37 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -41,11 +41,18 @@
 #include <asm/ppc-pci.h>
 #include <asm/eeh.h>
 
+/* hose_spinlock protects accesses to the the phb_bitmap. */
 static DEFINE_SPINLOCK(hose_spinlock);
 LIST_HEAD(hose_list);
 
-/* XXX kill that some day ... */
-static int global_phb_number;		/* Global phb counter */
+/* For dynamic PHB numbering on get_phb_number(): max number of PHBs. */
+#define MAX_PHBS 0x10000
+
+/*
+ * For dynamic PHB numbering: used/free PHBs tracking bitmap.
+ * Accesses to this bitmap should be protected by hose_spinlock.
+ */
+static DECLARE_BITMAP(phb_bitmap, MAX_PHBS);
 
 /* ISA Memory physical address */
 resource_size_t isa_mem_base;
@@ -64,6 +71,42 @@ struct dma_map_ops *get_pci_dma_ops(void)
 }
 EXPORT_SYMBOL(get_pci_dma_ops);
 
+/*
+ * This function should run under locking protection, specifically
+ * hose_spinlock.
+ */
+static int get_phb_number(struct device_node *dn)
+{
+	int ret, phb_id = -1;
+	u64 prop;
+
+	/*
+	 * Try fixed PHB numbering first, by checking archs and reading
+	 * the respective device-tree properties. Firstly, try powernv by
+	 * reading "ibm,opal-phbid", only present in OPAL environment.
+	 */
+	ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
+	if (ret)
+		ret = of_property_read_u32_index(dn, "reg", 1, (u32 *)&prop);
+
+	if (!ret)
+		phb_id = (int)(prop & (MAX_PHBS - 1));
+
+	/* We need to be sure to not use the same PHB number twice. */
+	if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap))
+		return phb_id;
+
+	/*
+	 * If not pseries nor powernv, or if fixed PHB numbering tried to add
+	 * the same PHB number twice, then fallback to dynamic PHB numbering.
+	 */
+	phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS);
+	BUG_ON(phb_id >= MAX_PHBS);
+	set_bit(phb_id, phb_bitmap);
+
+	return phb_id;
+}
+
 struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 {
 	struct pci_controller *phb;
@@ -72,7 +115,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 	if (phb == NULL)
 		return NULL;
 	spin_lock(&hose_spinlock);
-	phb->global_number = global_phb_number++;
+	phb->global_number = get_phb_number(dev);
 	list_add_tail(&phb->list_node, &hose_list);
 	spin_unlock(&hose_spinlock);
 	phb->dn = dev;
@@ -94,6 +137,11 @@ EXPORT_SYMBOL_GPL(pcibios_alloc_controller);
 void pcibios_free_controller(struct pci_controller *phb)
 {
 	spin_lock(&hose_spinlock);
+
+	/* Clear bit of phb_bitmap to allow reuse of this PHB number. */
+	if (phb->global_number < MAX_PHBS)
+		clear_bit(phb->global_number, phb_bitmap);
+
 	list_del(&phb->list_node);
 	spin_unlock(&hose_spinlock);
 
@@ -124,6 +172,14 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 	return 1;
 }
 
+void pcibios_setup_bridge(struct pci_bus *bus, unsigned long type)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+
+	if (hose->controller_ops.setup_bridge)
+		hose->controller_ops.setup_bridge(bus, type);
+}
+
 void pcibios_reset_secondary_bus(struct pci_dev *dev)
 {
 	struct pci_controller *phb = pci_bus_to_host(dev->bus);
@@ -356,36 +412,6 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 }
 
 /*
- * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
- * device mapping.
- */
-static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
-				      pgprot_t protection,
-				      enum pci_mmap_state mmap_state,
-				      int write_combine)
-{
-
-	/* Write combine is always 0 on non-memory space mappings. On
-	 * memory space, if the user didn't pass 1, we check for a
-	 * "prefetchable" resource. This is a bit hackish, but we use
-	 * this to workaround the inability of /sysfs to provide a write
-	 * combine bit
-	 */
-	if (mmap_state != pci_mmap_mem)
-		write_combine = 0;
-	else if (write_combine == 0) {
-		if (rp->flags & IORESOURCE_PREFETCH)
-			write_combine = 1;
-	}
-
-	/* XXX would be nice to have a way to ask for write-through */
-	if (write_combine)
-		return pgprot_noncached_wc(protection);
-	else
-		return pgprot_noncached(protection);
-}
-
-/*
  * This one is used by /dev/mem and fbdev who have no clue about the
  * PCI device, it tries to find the PCI device first and calls the
  * above routine
@@ -458,9 +484,10 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		return -EINVAL;
 
 	vma->vm_pgoff = offset >> PAGE_SHIFT;
-	vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
-						  vma->vm_page_prot,
-						  mmap_state, write_combine);
+	if (write_combine)
+		vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
 	ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
 			       vma->vm_end - vma->vm_start, vma->vm_page_prot);
@@ -610,39 +637,25 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 			  const struct resource *rsrc,
 			  resource_size_t *start, resource_size_t *end)
 {
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	resource_size_t offset = 0;
+	struct pci_bus_region region;
 
-	if (hose == NULL)
+	if (rsrc->flags & IORESOURCE_IO) {
+		pcibios_resource_to_bus(dev->bus, &region,
+					(struct resource *) rsrc);
+		*start = region.start;
+		*end = region.end;
 		return;
+	}
 
-	if (rsrc->flags & IORESOURCE_IO)
-		offset = (unsigned long)hose->io_base_virt - _IO_BASE;
-
-	/* We pass a fully fixed up address to userland for MMIO instead of
-	 * a BAR value because X is lame and expects to be able to use that
-	 * to pass to /dev/mem !
-	 *
-	 * That means that we'll have potentially 64 bits values where some
-	 * userland apps only expect 32 (like X itself since it thinks only
-	 * Sparc has 64 bits MMIO) but if we don't do that, we break it on
-	 * 32 bits CHRPs :-(
+	/* We pass a CPU physical address to userland for MMIO instead of a
+	 * BAR value because X is lame and expects to be able to use that
+	 * to pass to /dev/mem!
 	 *
-	 * Hopefully, the sysfs insterface is immune to that gunk. Once X
-	 * has been fixed (and the fix spread enough), we can re-enable the
-	 * 2 lines below and pass down a BAR value to userland. In that case
-	 * we'll also have to re-enable the matching code in
-	 * __pci_mmap_make_offset().
-	 *
-	 * BenH.
+	 * That means we may have 64-bit values where some apps only expect
+	 * 32 (like X itself since it thinks only Sparc has 64-bit MMIO).
 	 */
-#if 0
-	else if (rsrc->flags & IORESOURCE_MEM)
-		offset = hose->pci_mem_offset;
-#endif
-
-	*start = rsrc->start - offset;
-	*end = rsrc->end - offset;
+	*start = rsrc->start;
+	*end = rsrc->end;
 }
 
 /**
@@ -1362,8 +1375,10 @@ void __init pcibios_resource_survey(void)
 	/* Allocate and assign resources */
 	list_for_each_entry(b, &pci_root_buses, node)
 		pcibios_allocate_bus_resources(b);
-	pcibios_allocate_resources(0);
-	pcibios_allocate_resources(1);
+	if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC)) {
+		pcibios_allocate_resources(0);
+		pcibios_allocate_resources(1);
+	}
 
 	/* Before we start assigning unassigned resource, we try to reserve
 	 * the low IO area and the VGA memory area if they intersect the
@@ -1436,8 +1451,12 @@ void pcibios_finish_adding_to_bus(struct pci_bus *bus)
 	/* Allocate bus and devices resources */
 	pcibios_allocate_bus_resources(bus);
 	pcibios_claim_one_bus(bus);
-	if (!pci_has_flag(PCI_PROBE_ONLY))
-		pci_assign_unassigned_bus_resources(bus);
+	if (!pci_has_flag(PCI_PROBE_ONLY)) {
+		if (bus->self)
+			pci_assign_unassigned_bridge_resources(bus->self);
+		else
+			pci_assign_unassigned_bus_resources(bus);
+	}
 
 	/* Fixup EEH */
 	eeh_add_device_tree_late(bus);
@@ -1485,9 +1504,9 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose,
 	res = &hose->io_resource;
 
 	if (!res->flags) {
-		pr_info("PCI: I/O resource not set for host"
-		       " bridge %s (domain %d)\n",
-		       hose->dn->full_name, hose->global_number);
+		pr_debug("PCI: I/O resource not set for host"
+			 " bridge %s (domain %d)\n",
+			 hose->dn->full_name, hose->global_number);
 	} else {
 		offset = pcibios_io_space_offset(hose);
 
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index a5ae49a2dcc4..ed5e9ff61a68 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -81,7 +81,7 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 
 	/* If this is not a PHB, we only flush the hash table over
 	 * the area mapped by this bridge. We don't play with the PTE
-	 * mappings since we might have to deal with sub-page alignemnts
+	 * mappings since we might have to deal with sub-page alignments
 	 * so flushing the hash table is the only sane way to make sure
 	 * that no hash entries are covering that removed bridge area
 	 * while still allowing other busses overlapping those pages
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index ecdccce78719..592693437070 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -31,6 +31,7 @@
 #include <asm/pci-bridge.h>
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
+#include <asm/eeh.h>
 
 /*
  * The function is used to find the firmware data of one
@@ -181,7 +182,6 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 {
 #ifdef CONFIG_PCI_IOV
 	struct pci_dn *parent, *pdn;
-	struct eeh_dev *edev;
 	int i;
 
 	/* Only support IOV for now */
@@ -199,6 +199,8 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 		return NULL;
 
 	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		struct eeh_dev *edev __maybe_unused;
+
 		pdn = add_one_dev_pci_data(parent, NULL, i,
 					   pci_iov_virtfn_bus(pdev, i),
 					   pci_iov_virtfn_devfn(pdev, i));
@@ -208,11 +210,12 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 			return NULL;
 		}
 
+#ifdef CONFIG_EEH
 		/* Create the EEH device for the VF */
-		eeh_dev_init(pdn, pci_bus_to_host(pdev->bus));
-		edev = pdn_to_eeh_dev(pdn);
+		edev = eeh_dev_init(pdn);
 		BUG_ON(!edev);
 		edev->physfn = pdev;
+#endif /* CONFIG_EEH */
 	}
 #endif /* CONFIG_PCI_IOV */
 
@@ -224,7 +227,6 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 #ifdef CONFIG_PCI_IOV
 	struct pci_dn *parent;
 	struct pci_dn *pdn, *tmp;
-	struct eeh_dev *edev;
 	int i;
 
 	/*
@@ -260,18 +262,22 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 	 * a batch mode.
 	 */
 	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		struct eeh_dev *edev __maybe_unused;
+
 		list_for_each_entry_safe(pdn, tmp,
 			&parent->child_list, list) {
 			if (pdn->busno != pci_iov_virtfn_bus(pdev, i) ||
 			    pdn->devfn != pci_iov_virtfn_devfn(pdev, i))
 				continue;
 
+#ifdef CONFIG_EEH
 			/* Release EEH device for the VF */
 			edev = pdn_to_eeh_dev(pdn);
 			if (edev) {
 				pdn->edev = NULL;
 				kfree(edev);
 			}
+#endif /* CONFIG_EEH */
 
 			if (!list_empty(&pdn->list))
 				list_del(&pdn->list);
@@ -289,8 +295,11 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
 	const __be32 *regs;
 	struct device_node *parent;
 	struct pci_dn *pdn;
+#ifdef CONFIG_EEH
+	struct eeh_dev *edev;
+#endif
 
-	pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL);
+	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
 	if (pdn == NULL)
 		return NULL;
 	dn->data = pdn;
@@ -319,6 +328,15 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
 	/* Extended config space */
 	pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1);
 
+	/* Create EEH device */
+#ifdef CONFIG_EEH
+	edev = eeh_dev_init(pdn);
+	if (!edev) {
+		kfree(pdn);
+		return NULL;
+	}
+#endif
+
 	/* Attach to parent node */
 	INIT_LIST_HEAD(&pdn->child_list);
 	INIT_LIST_HEAD(&pdn->list);
@@ -504,15 +522,19 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb)
  * pci device found underneath.  This routine runs once,
  * early in the boot sequence.
  */
-void __init pci_devs_phb_init(void)
+static int __init pci_devs_phb_init(void)
 {
 	struct pci_controller *phb, *tmp;
 
 	/* This must be done first so the device nodes have valid pci info! */
 	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
 		pci_devs_phb_init_dynamic(phb);
+
+	return 0;
 }
 
+core_initcall(pci_devs_phb_init);
+
 static void pci_dev_pdn_setup(struct pci_dev *pdev)
 {
 	struct pci_dn *pdn;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 0b93893424f5..a8cca88e972f 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -139,12 +139,16 @@ EXPORT_SYMBOL(__msr_check_and_clear);
 #ifdef CONFIG_PPC_FPU
 void __giveup_fpu(struct task_struct *tsk)
 {
+	unsigned long msr;
+
 	save_fpu(tsk);
-	tsk->thread.regs->msr &= ~MSR_FP;
+	msr = tsk->thread.regs->msr;
+	msr &= ~MSR_FP;
 #ifdef CONFIG_VSX
 	if (cpu_has_feature(CPU_FTR_VSX))
-		tsk->thread.regs->msr &= ~MSR_VSX;
+		msr &= ~MSR_VSX;
 #endif
+	tsk->thread.regs->msr = msr;
 }
 
 void giveup_fpu(struct task_struct *tsk)
@@ -219,12 +223,16 @@ static int restore_fp(struct task_struct *tsk) { return 0; }
 
 static void __giveup_altivec(struct task_struct *tsk)
 {
+	unsigned long msr;
+
 	save_altivec(tsk);
-	tsk->thread.regs->msr &= ~MSR_VEC;
+	msr = tsk->thread.regs->msr;
+	msr &= ~MSR_VEC;
 #ifdef CONFIG_VSX
 	if (cpu_has_feature(CPU_FTR_VSX))
-		tsk->thread.regs->msr &= ~MSR_VSX;
+		msr &= ~MSR_VSX;
 #endif
+	tsk->thread.regs->msr = msr;
 }
 
 void giveup_altivec(struct task_struct *tsk)
@@ -794,7 +802,7 @@ static void tm_reclaim_thread(struct thread_struct *thr,
 	 * this state.
 	 * We do this using the current MSR, rather tracking it in
 	 * some specific thread_struct bit, as it has the additional
-	 * benifit of checking for a potential TM bad thing exception.
+	 * benefit of checking for a potential TM bad thing exception.
 	 */
 	if (!MSR_TM_SUSPENDED(mfmsr()))
 		return;
@@ -1009,6 +1017,14 @@ static inline void save_sprs(struct thread_struct *t)
 		 */
 		t->tar = mfspr(SPRN_TAR);
 	}
+
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		/* Conditionally save Load Monitor registers, if enabled */
+		if (t->fscr & FSCR_LM) {
+			t->lmrr = mfspr(SPRN_LMRR);
+			t->lmser = mfspr(SPRN_LMSER);
+		}
+	}
 #endif
 }
 
@@ -1023,18 +1039,11 @@ static inline void restore_sprs(struct thread_struct *old_thread,
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
 		u64 dscr = get_paca()->dscr_default;
-		u64 fscr = old_thread->fscr & ~FSCR_DSCR;
-
-		if (new_thread->dscr_inherit) {
+		if (new_thread->dscr_inherit)
 			dscr = new_thread->dscr;
-			fscr |= FSCR_DSCR;
-		}
 
 		if (old_thread->dscr != dscr)
 			mtspr(SPRN_DSCR, dscr);
-
-		if (old_thread->fscr != fscr)
-			mtspr(SPRN_FSCR, fscr);
 	}
 
 	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
@@ -1045,9 +1054,22 @@ static inline void restore_sprs(struct thread_struct *old_thread,
 		if (old_thread->ebbrr != new_thread->ebbrr)
 			mtspr(SPRN_EBBRR, new_thread->ebbrr);
 
+		if (old_thread->fscr != new_thread->fscr)
+			mtspr(SPRN_FSCR, new_thread->fscr);
+
 		if (old_thread->tar != new_thread->tar)
 			mtspr(SPRN_TAR, new_thread->tar);
 	}
+
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		/* Conditionally restore Load Monitor registers, if enabled */
+		if (new_thread->fscr & FSCR_LM) {
+			if (old_thread->lmrr != new_thread->lmrr)
+				mtspr(SPRN_LMRR, new_thread->lmrr);
+			if (old_thread->lmser != new_thread->lmser)
+				mtspr(SPRN_LMSER, new_thread->lmser);
+		}
+	}
 #endif
 }
 
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 946e34ffeae9..bae3db791150 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -56,6 +56,8 @@
 #include <asm/opal.h>
 #include <asm/fadump.h>
 #include <asm/debug.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/firmware.h>
 
 #include <mm/mmu_decl.h>
 
@@ -645,6 +647,14 @@ static void __init early_reserve_mem(void)
 #endif
 }
 
+static bool disable_radix;
+static int __init parse_disable_radix(char *p)
+{
+	disable_radix = true;
+	return 0;
+}
+early_param("disable_radix", parse_disable_radix);
+
 void __init early_init_devtree(void *params)
 {
 	phys_addr_t limit;
@@ -734,11 +744,26 @@ void __init early_init_devtree(void *params)
 	 */
 	spinning_secondaries = boot_cpu_count - 1;
 #endif
+	/*
+	 * now fixup radix MMU mode based on kernel command line
+	 */
+	if (disable_radix)
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_RADIX;
 
 #ifdef CONFIG_PPC_POWERNV
 	/* Scan and build the list of machine check recoverable ranges */
 	of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL);
 #endif
+	epapr_paravirt_early_init();
+
+	/* Now try to figure out if we are running on LPAR and so on */
+	pseries_probe_fw_features();
+
+#ifdef CONFIG_PPC_PS3
+	/* Identify PS3 firmware */
+	if (of_flat_dt_is_compatible(of_get_flat_dt_root(), "sony,ps3"))
+		powerpc_firmware_features |= FW_FEATURE_PS3_POSSIBLE;
+#endif
 
 	DBG(" <- early_init_devtree()\n");
 }
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index fb2fb3ea85e5..c82eed97bd22 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -698,7 +698,7 @@ static void check_location(struct seq_file *m, const char *c)
 /* 
  * Format: 
  * ${LETTER}${NUMBER}[[-/]${LETTER}${NUMBER} [ ... ] ]
- * the '.' may be an abbrevation
+ * the '.' may be an abbreviation
  */
 static void check_location_string(struct seq_file *m, const char *c)
 {
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 28736ff27fea..6a3e5de544ce 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -685,7 +685,7 @@ int rtas_set_indicator_fast(int indicator, int index, int new_value)
 	return rc;
 }
 
-void rtas_restart(char *cmd)
+void __noreturn rtas_restart(char *cmd)
 {
 	if (rtas_flash_term_hook)
 		rtas_flash_term_hook(SYS_RESTART);
@@ -704,7 +704,7 @@ void rtas_power_off(void)
 	for (;;);
 }
 
-void rtas_halt(void)
+void __noreturn rtas_halt(void)
 {
 	if (rtas_flash_term_hook)
 		rtas_flash_term_hook(SYS_HALT);
@@ -1070,7 +1070,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 	nret  = be32_to_cpu(args.nret);
 	token = be32_to_cpu(args.token);
 
-	if (nargs > ARRAY_SIZE(args.args)
+	if (nargs >= ARRAY_SIZE(args.args)
 	    || nret > ARRAY_SIZE(args.args)
 	    || nargs + nret > ARRAY_SIZE(args.args))
 		return -EINVAL;
@@ -1174,7 +1174,7 @@ void __init rtas_initialize(void)
 	 * the stop-self token if any
 	 */
 #ifdef CONFIG_PPC64
-	if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR)) {
+	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		rtas_region = min(ppc64_rma_size, RTAS_INSTANTIATE_MAX);
 		ibm_suspend_me_token = rtas_token("ibm,suspend-me");
 	}
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index c638e2487a9c..a26a02006576 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -483,7 +483,7 @@ static void rtas_event_scan(struct work_struct *w)
 }
 
 #ifdef CONFIG_PPC64
-static void retreive_nvram_error_log(void)
+static void retrieve_nvram_error_log(void)
 {
 	unsigned int err_type ;
 	int rc ;
@@ -501,7 +501,7 @@ static void retreive_nvram_error_log(void)
 	}
 }
 #else /* CONFIG_PPC64 */
-static void retreive_nvram_error_log(void)
+static void retrieve_nvram_error_log(void)
 {
 }
 #endif /* CONFIG_PPC64 */
@@ -513,7 +513,7 @@ static void start_event_scan(void)
 		 (30000 / rtas_event_scan_rate));
 
 	/* Retrieve errors from nvram if any */
-	retreive_nvram_error_log();
+	retrieve_nvram_error_log();
 
 	schedule_delayed_work_on(cpumask_first(cpu_online_mask),
 				 &event_scan_work, event_scan_delay);
@@ -526,10 +526,8 @@ void rtas_cancel_event_scan(void)
 }
 EXPORT_SYMBOL_GPL(rtas_cancel_event_scan);
 
-static int __init rtas_init(void)
+static int __init rtas_event_scan_init(void)
 {
-	struct proc_dir_entry *entry;
-
 	if (!machine_is(pseries) && !machine_is(chrp))
 		return 0;
 
@@ -562,13 +560,27 @@ static int __init rtas_init(void)
 		return -ENOMEM;
 	}
 
+	start_event_scan();
+
+	return 0;
+}
+arch_initcall(rtas_event_scan_init);
+
+static int __init rtas_init(void)
+{
+	struct proc_dir_entry *entry;
+
+	if (!machine_is(pseries) && !machine_is(chrp))
+		return 0;
+
+	if (!rtas_log_buf)
+		return -ENODEV;
+
 	entry = proc_create("powerpc/rtas/error_log", S_IRUSR, NULL,
 			    &proc_rtas_log_operations);
 	if (!entry)
 		printk(KERN_ERR "Failed to create error_log proc entry\n");
 
-	start_event_scan();
-
 	return 0;
 }
 __initcall(rtas_init);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 8ca79b7503d8..714b4ba7ab86 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -35,6 +35,7 @@
 #include <linux/percpu.h>
 #include <linux/memblock.h>
 #include <linux/of_platform.h>
+#include <linux/hugetlb.h>
 #include <asm/io.h>
 #include <asm/paca.h>
 #include <asm/prom.h>
@@ -61,6 +62,12 @@
 #include <asm/cputhreads.h>
 #include <mm/mmu_decl.h>
 #include <asm/fadump.h>
+#include <asm/udbg.h>
+#include <asm/hugetlb.h>
+#include <asm/livepatch.h>
+#include <asm/mmu_context.h>
+
+#include "setup.h"
 
 #ifdef DEBUG
 #include <asm/udbg.h>
@@ -494,7 +501,7 @@ void __init smp_setup_cpu_maps(void)
 	 * On pSeries LPAR, we need to know how many cpus
 	 * could possibly be added to this partition.
 	 */
-	if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR) &&
+	if (firmware_has_feature(FW_FEATURE_LPAR) &&
 	    (dn = of_find_node_by_path("/rtas"))) {
 		int num_addr_cell, num_size_cell, maxcpus;
 		const __be32 *ireg;
@@ -575,6 +582,7 @@ void probe_machine(void)
 {
 	extern struct machdep_calls __machine_desc_start;
 	extern struct machdep_calls __machine_desc_end;
+	unsigned int i;
 
 	/*
 	 * Iterate all ppc_md structures until we find the proper
@@ -582,6 +590,17 @@ void probe_machine(void)
 	 */
 	DBG("Probing machine type ...\n");
 
+	/*
+	 * Check ppc_md is empty, if not we have a bug, ie, we setup an
+	 * entry before probe_machine() which will be overwritten
+	 */
+	for (i = 0; i < (sizeof(ppc_md) / sizeof(void *)); i++) {
+		if (((void **)&ppc_md)[i]) {
+			printk(KERN_ERR "Entry %d in ppc_md non empty before"
+			       " machine probe !\n", i);
+		}
+	}
+
 	for (machine_id = &__machine_desc_start;
 	     machine_id < &__machine_desc_end;
 	     machine_id++) {
@@ -676,6 +695,8 @@ static struct notifier_block ppc_panic_block = {
 
 void __init setup_panic(void)
 {
+	if (!ppc_md.panic)
+		return;
 	atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block);
 }
 
@@ -744,3 +765,169 @@ void arch_setup_pdev_archdata(struct platform_device *pdev)
 	pdev->dev.dma_mask = &pdev->archdata.dma_mask;
  	set_dma_ops(&pdev->dev, &dma_direct_ops);
 }
+
+static __init void print_system_info(void)
+{
+	pr_info("-----------------------------------------------------\n");
+#ifdef CONFIG_PPC_STD_MMU_64
+	pr_info("ppc64_pft_size    = 0x%llx\n", ppc64_pft_size);
+#endif
+#ifdef CONFIG_PPC_STD_MMU_32
+	pr_info("Hash_size         = 0x%lx\n", Hash_size);
+#endif
+	pr_info("phys_mem_size     = 0x%llx\n",
+		(unsigned long long)memblock_phys_mem_size());
+
+	pr_info("dcache_bsize      = 0x%x\n", dcache_bsize);
+	pr_info("icache_bsize      = 0x%x\n", icache_bsize);
+	if (ucache_bsize != 0)
+		pr_info("ucache_bsize      = 0x%x\n", ucache_bsize);
+
+	pr_info("cpu_features      = 0x%016lx\n", cur_cpu_spec->cpu_features);
+	pr_info("  possible        = 0x%016lx\n",
+		(unsigned long)CPU_FTRS_POSSIBLE);
+	pr_info("  always          = 0x%016lx\n",
+		(unsigned long)CPU_FTRS_ALWAYS);
+	pr_info("cpu_user_features = 0x%08x 0x%08x\n",
+		cur_cpu_spec->cpu_user_features,
+		cur_cpu_spec->cpu_user_features2);
+	pr_info("mmu_features      = 0x%08x\n", cur_cpu_spec->mmu_features);
+#ifdef CONFIG_PPC64
+	pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features);
+#endif
+
+#ifdef CONFIG_PPC_STD_MMU_64
+	if (htab_address)
+		pr_info("htab_address      = 0x%p\n", htab_address);
+	if (htab_hash_mask)
+		pr_info("htab_hash_mask    = 0x%lx\n", htab_hash_mask);
+#endif
+#ifdef CONFIG_PPC_STD_MMU_32
+	if (Hash)
+		pr_info("Hash              = 0x%p\n", Hash);
+	if (Hash_mask)
+		pr_info("Hash_mask         = 0x%lx\n", Hash_mask);
+#endif
+
+	if (PHYSICAL_START > 0)
+		pr_info("physical_start    = 0x%llx\n",
+		       (unsigned long long)PHYSICAL_START);
+	pr_info("-----------------------------------------------------\n");
+}
+
+/*
+ * Called into from start_kernel this initializes memblock, which is used
+ * to manage page allocation until mem_init is called.
+ */
+void __init setup_arch(char **cmdline_p)
+{
+	*cmdline_p = boot_command_line;
+
+	/* Set a half-reasonable default so udelay does something sensible */
+	loops_per_jiffy = 500000000 / HZ;
+
+	/* Unflatten the device-tree passed by prom_init or kexec */
+	unflatten_device_tree();
+
+	/*
+	 * Initialize cache line/block info from device-tree (on ppc64) or
+	 * just cputable (on ppc32).
+	 */
+	initialize_cache_info();
+
+	/* Initialize RTAS if available. */
+	rtas_initialize();
+
+	/* Check if we have an initrd provided via the device-tree. */
+	check_for_initrd();
+
+	/* Probe the machine type, establish ppc_md. */
+	probe_machine();
+
+	/* Setup panic notifier if requested by the platform. */
+	setup_panic();
+
+	/*
+	 * Configure ppc_md.power_save (ppc32 only, 64-bit machines do
+	 * it from their respective probe() function.
+	 */
+	setup_power_save();
+
+	/* Discover standard serial ports. */
+	find_legacy_serial_ports();
+
+	/* Register early console with the printk subsystem. */
+	register_early_udbg_console();
+
+	/* Setup the various CPU maps based on the device-tree. */
+	smp_setup_cpu_maps();
+
+	/* Initialize xmon. */
+	xmon_setup();
+
+	/* Check the SMT related command line arguments (ppc64). */
+	check_smt_enabled();
+
+	/* On BookE, setup per-core TLB data structures. */
+	setup_tlb_core_data();
+
+	/*
+	 * Release secondary cpus out of their spinloops at 0x60 now that
+	 * we can map physical -> logical CPU ids.
+	 *
+	 * Freescale Book3e parts spin in a loop provided by firmware,
+	 * so smp_release_cpus() does nothing for them.
+	 */
+#ifdef CONFIG_SMP
+	smp_release_cpus();
+#endif
+
+	/* Print various info about the machine that has been gathered so far. */
+	print_system_info();
+
+	/* Reserve large chunks of memory for use by CMA for KVM. */
+	kvm_cma_reserve();
+
+	/*
+	 * Reserve any gigantic pages requested on the command line.
+	 * memblock needs to have been initialized by the time this is
+	 * called since this will reserve memory.
+	 */
+	reserve_hugetlb_gpages();
+
+	klp_init_thread_info(&init_thread_info);
+
+	init_mm.start_code = (unsigned long)_stext;
+	init_mm.end_code = (unsigned long) _etext;
+	init_mm.end_data = (unsigned long) _edata;
+	init_mm.brk = klimit;
+#ifdef CONFIG_PPC_64K_PAGES
+	init_mm.context.pte_frag = NULL;
+#endif
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	mm_iommu_init(&init_mm.context);
+#endif
+	irqstack_early_init();
+	exc_lvl_early_init();
+	emergency_stack_init();
+
+	initmem_init();
+
+#ifdef CONFIG_DUMMY_CONSOLE
+	conswitchp = &dummy_con;
+#endif
+	if (ppc_md.setup_arch)
+		ppc_md.setup_arch();
+
+	paging_init();
+
+	/* Initialize the MMU context management stuff. */
+	mmu_context_init();
+
+#ifdef CONFIG_PPC64
+	/* Interrupt code needs to be 64K-aligned. */
+	if ((unsigned long)_stext & 0xffff)
+		panic("Kernelbase not 64K-aligned (0x%lx)!\n",
+		      (unsigned long)_stext);
+#endif
+}
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
new file mode 100644
index 000000000000..cfba134b3024
--- /dev/null
+++ b/arch/powerpc/kernel/setup.h
@@ -0,0 +1,58 @@
+/*
+ * Prototypes for functions that are shared between setup_(32|64|common).c
+ *
+ * Copyright 2016 Michael Ellerman, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __ARCH_POWERPC_KERNEL_SETUP_H
+#define __ARCH_POWERPC_KERNEL_SETUP_H
+
+void initialize_cache_info(void);
+void irqstack_early_init(void);
+
+#ifdef CONFIG_PPC32
+void setup_power_save(void);
+#else
+static inline void setup_power_save(void) { };
+#endif
+
+#if defined(CONFIG_PPC64) && defined(CONFIG_SMP)
+void check_smt_enabled(void);
+#else
+static inline void check_smt_enabled(void) { };
+#endif
+
+#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP)
+void setup_tlb_core_data(void);
+#else
+static inline void setup_tlb_core_data(void) { };
+#endif
+
+#if defined(CONFIG_PPC_BOOK3E) || defined(CONFIG_BOOKE) || defined(CONFIG_40x)
+void exc_lvl_early_init(void);
+#else
+static inline void exc_lvl_early_init(void) { };
+#endif
+
+#ifdef CONFIG_PPC64
+void emergency_stack_init(void);
+#else
+static inline void emergency_stack_init(void) { };
+#endif
+
+/*
+ * Having this in kvm_ppc.h makes include dependencies too
+ * tricky to solve for setup-common.c so have it here.
+ */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void kvm_cma_reserve(void);
+#else
+static inline void kvm_cma_reserve(void) { };
+#endif
+
+#endif /* __ARCH_POWERPC_KERNEL_SETUP_H */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index d544fa311757..00f57754407e 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -36,8 +36,6 @@
 #include <asm/time.h>
 #include <asm/serial.h>
 #include <asm/udbg.h>
-#include <asm/mmu_context.h>
-#include <asm/epapr_hcalls.h>
 #include <asm/code-patching.h>
 
 #define DBG(fmt...)
@@ -62,9 +60,7 @@ int icache_bsize;
 int ucache_bsize;
 
 /*
- * We're called here very early in the boot.  We determine the machine
- * type and call the appropriate low-level setup functions.
- *  -- Cort <cort@fsmlabs.com>
+ * We're called here very early in the boot.
  *
  * Note that the kernel may be running at an address which is different
  * from the address that it was linked at, so we must use RELOC/PTRRELOC
@@ -73,7 +69,6 @@ int ucache_bsize;
 notrace unsigned long __init early_init(unsigned long dt_ptr)
 {
 	unsigned long offset = reloc_offset();
-	struct cpu_spec *spec;
 
 	/* First zero the BSS -- use memset_io, some platforms don't have
 	 * caches on yet */
@@ -84,27 +79,19 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
 	 * Identify the CPU type and fix up code sections
 	 * that depend on which cpu we have.
 	 */
-	spec = identify_cpu(offset, mfspr(SPRN_PVR));
+	identify_cpu(offset, mfspr(SPRN_PVR));
 
-	do_feature_fixups(spec->cpu_features,
-			  PTRRELOC(&__start___ftr_fixup),
-			  PTRRELOC(&__stop___ftr_fixup));
-
-	do_feature_fixups(spec->mmu_features,
-			  PTRRELOC(&__start___mmu_ftr_fixup),
-			  PTRRELOC(&__stop___mmu_ftr_fixup));
-
-	do_lwsync_fixups(spec->cpu_features,
-			 PTRRELOC(&__start___lwsync_fixup),
-			 PTRRELOC(&__stop___lwsync_fixup));
-
-	do_final_fixups();
+	apply_feature_fixups();
 
 	return KERNELBASE + offset;
 }
 
 
 /*
+ * This is run before start_kernel(), the kernel has been relocated
+ * and we are running with enough of the MMU enabled to have our
+ * proper kernel virtual addresses
+ *
  * Find out what kind of machine we're on and save any data we need
  * from the early boot process (devtree is copied on pmac by prom_init()).
  * This is called very early on the boot process, after a minimal
@@ -123,27 +110,9 @@ notrace void __init machine_init(u64 dt_ptr)
 	/* Do some early initialization based on the flat device tree */
 	early_init_devtree(__va(dt_ptr));
 
-	epapr_paravirt_early_init();
-
 	early_init_mmu();
 
-	probe_machine();
-
 	setup_kdump_trampoline();
-
-#ifdef CONFIG_6xx
-	if (cpu_has_feature(CPU_FTR_CAN_DOZE) ||
-	    cpu_has_feature(CPU_FTR_CAN_NAP))
-		ppc_md.power_save = ppc6xx_idle;
-#endif
-
-#ifdef CONFIG_E500
-	if (cpu_has_feature(CPU_FTR_CAN_DOZE) ||
-	    cpu_has_feature(CPU_FTR_CAN_NAP))
-		ppc_md.power_save = e500_idle;
-#endif
-	if (ppc_md.progress)
-		ppc_md.progress("id mach(): done", 0x200);
 }
 
 /* Checks "l2cr=xxxx" command-line option */
@@ -221,7 +190,7 @@ int __init ppc_init(void)
 
 arch_initcall(ppc_init);
 
-static void __init irqstack_early_init(void)
+void __init irqstack_early_init(void)
 {
 	unsigned int i;
 
@@ -236,7 +205,7 @@ static void __init irqstack_early_init(void)
 }
 
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
-static void __init exc_lvl_early_init(void)
+void __init exc_lvl_early_init(void)
 {
 	unsigned int i, hw_cpu;
 
@@ -259,33 +228,25 @@ static void __init exc_lvl_early_init(void)
 #endif
 	}
 }
-#else
-#define exc_lvl_early_init()
 #endif
 
-/* Warning, IO base is not yet inited */
-void __init setup_arch(char **cmdline_p)
+void __init setup_power_save(void)
 {
-	*cmdline_p = boot_command_line;
-
-	/* so udelay does something sensible, assume <= 1000 bogomips */
-	loops_per_jiffy = 500000000 / HZ;
-
-	unflatten_device_tree();
-	check_for_initrd();
-
-	if (ppc_md.init_early)
-		ppc_md.init_early();
-
-	find_legacy_serial_ports();
-
-	smp_setup_cpu_maps();
-
-	/* Register early console */
-	register_early_udbg_console();
+#ifdef CONFIG_6xx
+	if (cpu_has_feature(CPU_FTR_CAN_DOZE) ||
+	    cpu_has_feature(CPU_FTR_CAN_NAP))
+		ppc_md.power_save = ppc6xx_idle;
+#endif
 
-	xmon_setup();
+#ifdef CONFIG_E500
+	if (cpu_has_feature(CPU_FTR_CAN_DOZE) ||
+	    cpu_has_feature(CPU_FTR_CAN_NAP))
+		ppc_md.power_save = e500_idle;
+#endif
+}
 
+__init void initialize_cache_info(void)
+{
 	/*
 	 * Set cache line size based on type of cpu as a default.
 	 * Systems with OF can look in the properties on the cpu node(s)
@@ -296,32 +257,4 @@ void __init setup_arch(char **cmdline_p)
 	ucache_bsize = 0;
 	if (cpu_has_feature(CPU_FTR_UNIFIED_ID_CACHE))
 		ucache_bsize = icache_bsize = dcache_bsize;
-
-	if (ppc_md.panic)
-		setup_panic();
-
-	init_mm.start_code = (unsigned long)_stext;
-	init_mm.end_code = (unsigned long) _etext;
-	init_mm.end_data = (unsigned long) _edata;
-	init_mm.brk = klimit;
-
-	exc_lvl_early_init();
-
-	irqstack_early_init();
-
-	initmem_init();
-	if ( ppc_md.progress ) ppc_md.progress("setup_arch: initmem", 0x3eab);
-
-#ifdef CONFIG_DUMMY_CONSOLE
-	conswitchp = &dummy_con;
-#endif
-
-	if (ppc_md.setup_arch)
-		ppc_md.setup_arch();
-	if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab);
-
-	paging_init();
-
-	/* Initialize the MMU context management stuff */
-	mmu_context_init();
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 96d4a2b23d0f..d8216aed22b7 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -35,7 +35,6 @@
 #include <linux/pci.h>
 #include <linux/lockdep.h>
 #include <linux/memblock.h>
-#include <linux/hugetlb.h>
 #include <linux/memory.h>
 #include <linux/nmi.h>
 
@@ -64,12 +63,10 @@
 #include <asm/xmon.h>
 #include <asm/udbg.h>
 #include <asm/kexec.h>
-#include <asm/mmu_context.h>
 #include <asm/code-patching.h>
-#include <asm/kvm_ppc.h>
-#include <asm/hugetlb.h>
-#include <asm/epapr_hcalls.h>
 #include <asm/livepatch.h>
+#include <asm/opal.h>
+#include <asm/cputhreads.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -100,7 +97,7 @@ int icache_bsize;
 int ucache_bsize;
 
 #if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP)
-static void setup_tlb_core_data(void)
+void __init setup_tlb_core_data(void)
 {
 	int cpu;
 
@@ -133,10 +130,6 @@ static void setup_tlb_core_data(void)
 		}
 	}
 }
-#else
-static void setup_tlb_core_data(void)
-{
-}
 #endif
 
 #ifdef CONFIG_SMP
@@ -144,7 +137,7 @@ static void setup_tlb_core_data(void)
 static char *smt_enabled_cmdline;
 
 /* Look for ibm,smt-enabled OF option */
-static void check_smt_enabled(void)
+void __init check_smt_enabled(void)
 {
 	struct device_node *dn;
 	const char *smt_option;
@@ -193,12 +186,10 @@ static int __init early_smt_enabled(char *p)
 }
 early_param("smt-enabled", early_smt_enabled);
 
-#else
-#define check_smt_enabled()
 #endif /* CONFIG_SMP */
 
 /** Fix up paca fields required for the boot cpu */
-static void fixup_boot_paca(void)
+static void __init fixup_boot_paca(void)
 {
 	/* The boot cpu is started */
 	get_paca()->cpu_start = 1;
@@ -206,23 +197,50 @@ static void fixup_boot_paca(void)
 	get_paca()->data_offset = 0;
 }
 
-static void cpu_ready_for_interrupts(void)
+static void __init configure_exceptions(void)
 {
-	/* Set IR and DR in PACA MSR */
-	get_paca()->kernel_msr = MSR_KERNEL;
-
 	/*
-	 * Enable AIL if supported, and we are in hypervisor mode. If we are
-	 * not in hypervisor mode, we enable relocation-on interrupts later
-	 * in pSeries_setup_arch() using the H_SET_MODE hcall.
+	 * Setup the trampolines from the lowmem exception vectors
+	 * to the kdump kernel when not using a relocatable kernel.
 	 */
-	if (cpu_has_feature(CPU_FTR_HVMODE) &&
-	    cpu_has_feature(CPU_FTR_ARCH_207S)) {
-		unsigned long lpcr = mfspr(SPRN_LPCR);
-		mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
+	setup_kdump_trampoline();
+
+	/* Under a PAPR hypervisor, we need hypercalls */
+	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+		/* Enable AIL if possible */
+		pseries_enable_reloc_on_exc();
+
+		/*
+		 * Tell the hypervisor that we want our exceptions to
+		 * be taken in little endian mode.
+		 *
+		 * We don't call this for big endian as our calling convention
+		 * makes us always enter in BE, and the call may fail under
+		 * some circumstances with kdump.
+		 */
+#ifdef __LITTLE_ENDIAN__
+		pseries_little_endian_exceptions();
+#endif
+	} else {
+		/* Set endian mode using OPAL */
+		if (firmware_has_feature(FW_FEATURE_OPAL))
+			opal_configure_cores();
+
+		/* Enable AIL if supported, and we are in hypervisor mode */
+		if (cpu_has_feature(CPU_FTR_HVMODE) &&
+		    cpu_has_feature(CPU_FTR_ARCH_207S)) {
+			unsigned long lpcr = mfspr(SPRN_LPCR);
+			mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
+		}
 	}
 }
 
+static void cpu_ready_for_interrupts(void)
+{
+	/* Set IR and DR in PACA MSR */
+	get_paca()->kernel_msr = MSR_KERNEL;
+}
+
 /*
  * Early initialization entry point. This is called by head.S
  * with MMU translation disabled. We rely on the "feature" of
@@ -270,22 +288,22 @@ void __init early_setup(unsigned long dt_ptr)
 	 */
 	early_init_devtree(__va(dt_ptr));
 
-	epapr_paravirt_early_init();
-
 	/* Now we know the logical id of our boot cpu, setup the paca. */
 	setup_paca(&paca[boot_cpuid]);
 	fixup_boot_paca();
 
-	/* Probe the machine type */
-	probe_machine();
-
-	setup_kdump_trampoline();
-
-	DBG("Found, Initializing memory management...\n");
+	/*
+	 * Configure exception handlers. This include setting up trampolines
+	 * if needed, setting exception endian mode, etc...
+	 */
+	configure_exceptions();
 
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu();
 
+	/* Apply all the dynamic patching */
+	apply_feature_fixups();
+
 	/*
 	 * At this point, we can let interrupts switch to virtual mode
 	 * (the MMU has been setup), so adjust the MSR in the PACA to
@@ -293,16 +311,6 @@ void __init early_setup(unsigned long dt_ptr)
 	 */
 	cpu_ready_for_interrupts();
 
-	/* Reserve large chunks of memory for use by CMA for KVM */
-	kvm_cma_reserve();
-
-	/*
-	 * Reserve any gigantic pages requested on the command line.
-	 * memblock needs to have been initialized by the time this is
-	 * called since this will reserve memory.
-	 */
-	reserve_hugetlb_gpages();
-
 	DBG(" <- early_setup()\n");
 
 #ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
@@ -321,7 +329,7 @@ void __init early_setup(unsigned long dt_ptr)
 #ifdef CONFIG_SMP
 void early_setup_secondary(void)
 {
-	/* Mark interrupts enabled in PACA */
+	/* Mark interrupts disabled in PACA */
 	get_paca()->soft_enabled = 0;
 
 	/* Initialize the hash table or TLB handling */
@@ -391,7 +399,7 @@ void smp_release_cpus(void)
  * cache informations about the CPU that will be used by cache flush
  * routines and/or provided to userland
  */
-static void __init initialize_cache_info(void)
+void __init initialize_cache_info(void)
 {
 	struct device_node *np;
 	unsigned long num_cpus = 0;
@@ -456,127 +464,11 @@ static void __init initialize_cache_info(void)
 		}
 	}
 
-	DBG(" <- initialize_cache_info()\n");
-}
-
-
-/*
- * Do some initial setup of the system.  The parameters are those which 
- * were passed in from the bootloader.
- */
-void __init setup_system(void)
-{
-	DBG(" -> setup_system()\n");
-
-	/* Apply the CPUs-specific and firmware specific fixups to kernel
-	 * text (nop out sections not relevant to this CPU or this firmware)
-	 */
-	do_feature_fixups(cur_cpu_spec->cpu_features,
-			  &__start___ftr_fixup, &__stop___ftr_fixup);
-	do_feature_fixups(cur_cpu_spec->mmu_features,
-			  &__start___mmu_ftr_fixup, &__stop___mmu_ftr_fixup);
-	do_feature_fixups(powerpc_firmware_features,
-			  &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
-	do_lwsync_fixups(cur_cpu_spec->cpu_features,
-			 &__start___lwsync_fixup, &__stop___lwsync_fixup);
-	do_final_fixups();
-
-	/*
-	 * Unflatten the device-tree passed by prom_init or kexec
-	 */
-	unflatten_device_tree();
-
-	/*
-	 * Fill the ppc64_caches & systemcfg structures with informations
- 	 * retrieved from the device-tree.
-	 */
-	initialize_cache_info();
-
-#ifdef CONFIG_PPC_RTAS
-	/*
-	 * Initialize RTAS if available
-	 */
-	rtas_initialize();
-#endif /* CONFIG_PPC_RTAS */
-
-	/*
-	 * Check if we have an initrd provided via the device-tree
-	 */
-	check_for_initrd();
-
-	/*
-	 * Do some platform specific early initializations, that includes
-	 * setting up the hash table pointers. It also sets up some interrupt-mapping
-	 * related options that will be used by finish_device_tree()
-	 */
-	if (ppc_md.init_early)
-		ppc_md.init_early();
-
- 	/*
-	 * We can discover serial ports now since the above did setup the
-	 * hash table management for us, thus ioremap works. We do that early
-	 * so that further code can be debugged
-	 */
-	find_legacy_serial_ports();
-
-	/*
-	 * Register early console
-	 */
-	register_early_udbg_console();
-
-	/*
-	 * Initialize xmon
-	 */
-	xmon_setup();
-
-	smp_setup_cpu_maps();
-	check_smt_enabled();
-	setup_tlb_core_data();
-
-	/*
-	 * Freescale Book3e parts spin in a loop provided by firmware,
-	 * so smp_release_cpus() does nothing for them
-	 */
-#if defined(CONFIG_SMP)
-	/* Release secondary cpus out of their spinloops at 0x60 now that
-	 * we can map physical -> logical CPU ids
-	 */
-	smp_release_cpus();
-#endif
-
-	pr_info("Starting Linux %s %s\n", init_utsname()->machine,
-		 init_utsname()->version);
-
-	pr_info("-----------------------------------------------------\n");
-	pr_info("ppc64_pft_size    = 0x%llx\n", ppc64_pft_size);
-	pr_info("phys_mem_size     = 0x%llx\n", memblock_phys_mem_size());
-
-	if (ppc64_caches.dline_size != 0x80)
-		pr_info("dcache_line_size  = 0x%x\n", ppc64_caches.dline_size);
-	if (ppc64_caches.iline_size != 0x80)
-		pr_info("icache_line_size  = 0x%x\n", ppc64_caches.iline_size);
-
-	pr_info("cpu_features      = 0x%016lx\n", cur_cpu_spec->cpu_features);
-	pr_info("  possible        = 0x%016lx\n", CPU_FTRS_POSSIBLE);
-	pr_info("  always          = 0x%016lx\n", CPU_FTRS_ALWAYS);
-	pr_info("cpu_user_features = 0x%08x 0x%08x\n", cur_cpu_spec->cpu_user_features,
-		cur_cpu_spec->cpu_user_features2);
-	pr_info("mmu_features      = 0x%08x\n", cur_cpu_spec->mmu_features);
-	pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features);
-
-#ifdef CONFIG_PPC_STD_MMU_64
-	if (htab_address)
-		pr_info("htab_address      = 0x%p\n", htab_address);
-
-	pr_info("htab_hash_mask    = 0x%lx\n", htab_hash_mask);
-#endif
-
-	if (PHYSICAL_START > 0)
-		pr_info("physical_start    = 0x%llx\n",
-		       (unsigned long long)PHYSICAL_START);
-	pr_info("-----------------------------------------------------\n");
+	/* For use by binfmt_elf */
+	dcache_bsize = ppc64_caches.dline_size;
+	icache_bsize = ppc64_caches.iline_size;
 
-	DBG(" <- setup_system()\n");
+	DBG(" <- initialize_cache_info()\n");
 }
 
 /* This returns the limit below which memory accesses to the linear
@@ -584,7 +476,7 @@ void __init setup_system(void)
  * used to allocate interrupt or emergency stacks for which our
  * exception entry path doesn't deal with being interrupted.
  */
-static u64 safe_stack_limit(void)
+static __init u64 safe_stack_limit(void)
 {
 #ifdef CONFIG_PPC_BOOK3E
 	/* Freescale BookE bolts the entire linear mapping */
@@ -600,7 +492,7 @@ static u64 safe_stack_limit(void)
 #endif
 }
 
-static void __init irqstack_early_init(void)
+void __init irqstack_early_init(void)
 {
 	u64 limit = safe_stack_limit();
 	unsigned int i;
@@ -620,7 +512,7 @@ static void __init irqstack_early_init(void)
 }
 
 #ifdef CONFIG_PPC_BOOK3E
-static void __init exc_lvl_early_init(void)
+void __init exc_lvl_early_init(void)
 {
 	unsigned int i;
 	unsigned long sp;
@@ -642,8 +534,6 @@ static void __init exc_lvl_early_init(void)
 	if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC))
 		patch_exception(0x040, exc_debug_debug_book3e);
 }
-#else
-#define exc_lvl_early_init()
 #endif
 
 /*
@@ -651,7 +541,7 @@ static void __init exc_lvl_early_init(void)
  * early in SMP boots before relocation is enabled. Exclusive emergency
  * stack for machine checks.
  */
-static void __init emergency_stack_init(void)
+void __init emergency_stack_init(void)
 {
 	u64 limit;
 	unsigned int i;
@@ -682,61 +572,6 @@ static void __init emergency_stack_init(void)
 	}
 }
 
-/*
- * Called into from start_kernel this initializes memblock, which is used
- * to manage page allocation until mem_init is called.
- */
-void __init setup_arch(char **cmdline_p)
-{
-	*cmdline_p = boot_command_line;
-
-	/*
-	 * Set cache line size based on type of cpu as a default.
-	 * Systems with OF can look in the properties on the cpu node(s)
-	 * for a possibly more accurate value.
-	 */
-	dcache_bsize = ppc64_caches.dline_size;
-	icache_bsize = ppc64_caches.iline_size;
-
-	if (ppc_md.panic)
-		setup_panic();
-
-	klp_init_thread_info(&init_thread_info);
-
-	init_mm.start_code = (unsigned long)_stext;
-	init_mm.end_code = (unsigned long) _etext;
-	init_mm.end_data = (unsigned long) _edata;
-	init_mm.brk = klimit;
-#ifdef CONFIG_PPC_64K_PAGES
-	init_mm.context.pte_frag = NULL;
-#endif
-#ifdef CONFIG_SPAPR_TCE_IOMMU
-	mm_iommu_init(&init_mm.context);
-#endif
-	irqstack_early_init();
-	exc_lvl_early_init();
-	emergency_stack_init();
-
-	initmem_init();
-
-#ifdef CONFIG_DUMMY_CONSOLE
-	conswitchp = &dummy_con;
-#endif
-
-	if (ppc_md.setup_arch)
-		ppc_md.setup_arch();
-
-	paging_init();
-
-	/* Initialize the MMU context management stuff */
-	mmu_context_init();
-
-	/* Interrupt code needs to be 64K-aligned */
-	if ((unsigned long)_stext & 0xffff)
-		panic("Kernelbase not 64K-aligned (0x%lx)!\n",
-		      (unsigned long)_stext);
-}
-
 #ifdef CONFIG_SMP
 #define PCPU_DYN_SIZE		()
 
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 25520794aa37..7e49984d4331 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -104,6 +104,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	 */
 #ifdef CONFIG_ALTIVEC
 	elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc);
+	unsigned long vrsave;
 #endif
 	unsigned long msr = regs->msr;
 	long err = 0;
@@ -125,9 +126,13 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	/* We always copy to/from vrsave, it's 0 if we don't have or don't
 	 * use altivec.
 	 */
-	if (cpu_has_feature(CPU_FTR_ALTIVEC))
-		current->thread.vrsave = mfspr(SPRN_VRSAVE);
-	err |= __put_user(current->thread.vrsave, (u32 __user *)&v_regs[33]);
+	vrsave = 0;
+	if (cpu_has_feature(CPU_FTR_ALTIVEC)) {
+		vrsave = mfspr(SPRN_VRSAVE);
+		current->thread.vrsave = vrsave;
+	}
+
+	err |= __put_user(vrsave, (u32 __user *)&v_regs[33]);
 #else /* CONFIG_ALTIVEC */
 	err |= __put_user(0, &sc->v_regs);
 #endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 55c924b65f71..5a1f015ea9f3 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -31,6 +31,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/topology.h>
+#include <linux/profile.h>
 
 #include <asm/ptrace.h>
 #include <linux/atomic.h>
@@ -53,6 +54,7 @@
 #include <asm/vdso.h>
 #include <asm/debug.h>
 #include <asm/kexec.h>
+#include <asm/asm-prototypes.h>
 
 #ifdef DEBUG
 #include <asm/udbg.h>
@@ -593,6 +595,7 @@ out:
 	of_node_put(np);
 	return id;
 }
+EXPORT_SYMBOL_GPL(cpu_to_core_id);
 
 /* Helper routines for cpu to core mapping */
 int cpu_core_index_of_thread(int cpu)
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 692873bff334..c4f1d1f7bae0 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -35,7 +35,7 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices);
 #ifdef CONFIG_PPC64
 
 /* Time in microseconds we delay before sleeping in the idle loop */
-DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 };
+static DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 };
 
 static ssize_t store_smt_snooze_delay(struct device *dev,
 				      struct device_attribute *attr,
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 3ed9a5a21d77..4e7759c8ca30 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -96,7 +96,8 @@ static struct clocksource clocksource_timebase = {
 	.read         = timebase_read,
 };
 
-#define DECREMENTER_MAX	0x7fffffff
+#define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
+u64 decrementer_max = DECREMENTER_DEFAULT_MAX;
 
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev);
@@ -166,7 +167,15 @@ DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta);
 
 cputime_t cputime_one_jiffy;
 
+#ifdef CONFIG_PPC_SPLPAR
 void (*dtl_consumer)(struct dtl_entry *, u64);
+#endif
+
+#ifdef CONFIG_PPC64
+#define get_accounting(tsk)	(&get_paca()->accounting)
+#else
+#define get_accounting(tsk)	(&task_thread_info(tsk)->accounting)
+#endif
 
 static void calc_cputime_factors(void)
 {
@@ -186,7 +195,7 @@ static void calc_cputime_factors(void)
  * Read the SPURR on systems that have it, otherwise the PURR,
  * or if that doesn't exist return the timebase value passed in.
  */
-static u64 read_spurr(u64 tb)
+static unsigned long read_spurr(unsigned long tb)
 {
 	if (cpu_has_feature(CPU_FTR_SPURR))
 		return mfspr(SPRN_SPURR);
@@ -249,8 +258,8 @@ static u64 scan_dispatch_log(u64 stop_tb)
 void accumulate_stolen_time(void)
 {
 	u64 sst, ust;
-
 	u8 save_soft_enabled = local_paca->soft_enabled;
+	struct cpu_accounting_data *acct = &local_paca->accounting;
 
 	/* We are called early in the exception entry, before
 	 * soft/hard_enabled are sync'ed to the expected state
@@ -260,10 +269,10 @@ void accumulate_stolen_time(void)
 	 */
 	local_paca->soft_enabled = 0;
 
-	sst = scan_dispatch_log(local_paca->starttime_user);
-	ust = scan_dispatch_log(local_paca->starttime);
-	local_paca->system_time -= sst;
-	local_paca->user_time -= ust;
+	sst = scan_dispatch_log(acct->starttime_user);
+	ust = scan_dispatch_log(acct->starttime);
+	acct->system_time -= sst;
+	acct->user_time -= ust;
 	local_paca->stolen_time += ust + sst;
 
 	local_paca->soft_enabled = save_soft_enabled;
@@ -275,7 +284,7 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
 
 	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
 		stolen = scan_dispatch_log(stop_tb);
-		get_paca()->system_time -= stolen;
+		get_paca()->accounting.system_time -= stolen;
 	}
 
 	stolen += get_paca()->stolen_time;
@@ -295,27 +304,29 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
  * Account time for a transition between system, hard irq
  * or soft irq state.
  */
-static u64 vtime_delta(struct task_struct *tsk,
-			u64 *sys_scaled, u64 *stolen)
+static unsigned long vtime_delta(struct task_struct *tsk,
+				 unsigned long *sys_scaled,
+				 unsigned long *stolen)
 {
-	u64 now, nowscaled, deltascaled;
-	u64 udelta, delta, user_scaled;
+	unsigned long now, nowscaled, deltascaled;
+	unsigned long udelta, delta, user_scaled;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
 
 	WARN_ON_ONCE(!irqs_disabled());
 
 	now = mftb();
 	nowscaled = read_spurr(now);
-	get_paca()->system_time += now - get_paca()->starttime;
-	get_paca()->starttime = now;
-	deltascaled = nowscaled - get_paca()->startspurr;
-	get_paca()->startspurr = nowscaled;
+	acct->system_time += now - acct->starttime;
+	acct->starttime = now;
+	deltascaled = nowscaled - acct->startspurr;
+	acct->startspurr = nowscaled;
 
 	*stolen = calculate_stolen_time(now);
 
-	delta = get_paca()->system_time;
-	get_paca()->system_time = 0;
-	udelta = get_paca()->user_time - get_paca()->utime_sspurr;
-	get_paca()->utime_sspurr = get_paca()->user_time;
+	delta = acct->system_time;
+	acct->system_time = 0;
+	udelta = acct->user_time - acct->utime_sspurr;
+	acct->utime_sspurr = acct->user_time;
 
 	/*
 	 * Because we don't read the SPURR on every kernel entry/exit,
@@ -337,14 +348,14 @@ static u64 vtime_delta(struct task_struct *tsk,
 			*sys_scaled = deltascaled;
 		}
 	}
-	get_paca()->user_time_scaled += user_scaled;
+	acct->user_time_scaled += user_scaled;
 
 	return delta;
 }
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	u64 delta, sys_scaled, stolen;
+	unsigned long delta, sys_scaled, stolen;
 
 	delta = vtime_delta(tsk, &sys_scaled, &stolen);
 	account_system_time(tsk, 0, delta, sys_scaled);
@@ -355,7 +366,7 @@ EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
-	u64 delta, sys_scaled, stolen;
+	unsigned long delta, sys_scaled, stolen;
 
 	delta = vtime_delta(tsk, &sys_scaled, &stolen);
 	account_idle_time(delta + stolen);
@@ -373,15 +384,32 @@ void vtime_account_idle(struct task_struct *tsk)
 void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t utime, utimescaled;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
 
-	utime = get_paca()->user_time;
-	utimescaled = get_paca()->user_time_scaled;
-	get_paca()->user_time = 0;
-	get_paca()->user_time_scaled = 0;
-	get_paca()->utime_sspurr = 0;
+	utime = acct->user_time;
+	utimescaled = acct->user_time_scaled;
+	acct->user_time = 0;
+	acct->user_time_scaled = 0;
+	acct->utime_sspurr = 0;
 	account_user_time(tsk, utime, utimescaled);
 }
 
+#ifdef CONFIG_PPC32
+/*
+ * Called from the context switch with interrupts disabled, to charge all
+ * accumulated times to the current process, and to prepare accounting on
+ * the next process.
+ */
+void arch_vtime_task_switch(struct task_struct *prev)
+{
+	struct cpu_accounting_data *acct = get_accounting(current);
+
+	acct->starttime = get_accounting(prev)->starttime;
+	acct->system_time = 0;
+	acct->user_time = 0;
+}
+#endif /* CONFIG_PPC32 */
+
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #define calc_cputime_factors()
 #endif
@@ -504,8 +532,8 @@ static void __timer_interrupt(void)
 		__this_cpu_inc(irq_stat.timer_irqs_event);
 	} else {
 		now = *next_tb - now;
-		if (now <= DECREMENTER_MAX)
-			set_dec((int)now);
+		if (now <= decrementer_max)
+			set_dec(now);
 		/* We may have raced with new irq work */
 		if (test_irq_work_pending())
 			set_dec(1);
@@ -535,7 +563,7 @@ void timer_interrupt(struct pt_regs * regs)
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continue to take decrementer exceptions.
 	 */
-	set_dec(DECREMENTER_MAX);
+	set_dec(decrementer_max);
 
 	/* Some implementations of hotplug will get timer interrupts while
 	 * offline, just ignore these and we also need to set
@@ -583,9 +611,9 @@ static void generic_suspend_disable_irqs(void)
 	 * with suspending.
 	 */
 
-	set_dec(DECREMENTER_MAX);
+	set_dec(decrementer_max);
 	local_irq_disable();
-	set_dec(DECREMENTER_MAX);
+	set_dec(decrementer_max);
 }
 
 static void generic_suspend_enable_irqs(void)
@@ -866,7 +894,7 @@ static int decrementer_set_next_event(unsigned long evt,
 
 static int decrementer_shutdown(struct clock_event_device *dev)
 {
-	decrementer_set_next_event(DECREMENTER_MAX, dev);
+	decrementer_set_next_event(decrementer_max, dev);
 	return 0;
 }
 
@@ -892,6 +920,49 @@ static void register_decrementer_clockevent(int cpu)
 	clockevents_register_device(dec);
 }
 
+static void enable_large_decrementer(void)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		return;
+
+	if (decrementer_max <= DECREMENTER_DEFAULT_MAX)
+		return;
+
+	/*
+	 * If we're running as the hypervisor we need to enable the LD manually
+	 * otherwise firmware should have done it for us.
+	 */
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_LD);
+}
+
+static void __init set_decrementer_max(void)
+{
+	struct device_node *cpu;
+	u32 bits = 32;
+
+	/* Prior to ISAv3 the decrementer is always 32 bit */
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		return;
+
+	cpu = of_find_node_by_type(NULL, "cpu");
+
+	if (of_property_read_u32(cpu, "ibm,dec-bits", &bits) == 0) {
+		if (bits > 64 || bits < 32) {
+			pr_warn("time_init: firmware supplied invalid ibm,dec-bits");
+			bits = 32;
+		}
+
+		/* calculate the signed maximum given this many bits */
+		decrementer_max = (1ul << (bits - 1)) - 1;
+	}
+
+	of_node_put(cpu);
+
+	pr_info("time_init: %u bit decrementer (max: %llx)\n",
+		bits, decrementer_max);
+}
+
 static void __init init_decrementer_clockevent(void)
 {
 	int cpu = smp_processor_id();
@@ -899,7 +970,7 @@ static void __init init_decrementer_clockevent(void)
 	clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4);
 
 	decrementer_clockevent.max_delta_ns =
-		clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent);
+		clockevent_delta2ns(decrementer_max, &decrementer_clockevent);
 	decrementer_clockevent.min_delta_ns =
 		clockevent_delta2ns(2, &decrementer_clockevent);
 
@@ -908,6 +979,9 @@ static void __init init_decrementer_clockevent(void)
 
 void secondary_cpu_time_init(void)
 {
+	/* Enable and test the large decrementer for this cpu */
+	enable_large_decrementer();
+
 	/* Start the decrementer on CPUs that have manual control
 	 * such as BookE
 	 */
@@ -973,6 +1047,10 @@ void __init time_init(void)
 	vdso_data->tb_update_count = 0;
 	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
 
+	/* initialise and enable the large decrementer (if we have one) */
+	set_decrementer_max();
+	enable_large_decrementer();
+
 	/* Start the decrementer on CPUs that have manual control
 	 * such as BookE
 	 */
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index b7019b559ddb..298afcf3bf2a 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -338,8 +338,6 @@ _GLOBAL(__tm_recheckpoint)
 	 */
 	subi	r7, r7, STACK_FRAME_OVERHEAD
 
-	SET_SCRATCH0(r1)
-
 	mfmsr	r6
 	/* R4 = original MSR to indicate whether thread used FP/Vector etc. */
 
@@ -468,6 +466,7 @@ restore_gprs:
 	 * until we turn MSR RI back on.
 	 */
 
+	SET_SCRATCH0(r1)
 	ld	r5, -8(r1)
 	ld	r1, -16(r1)
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 9229ba63c370..2cb589264cb7 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -60,6 +60,8 @@
 #include <asm/switch_to.h>
 #include <asm/tm.h>
 #include <asm/debug.h>
+#include <asm/asm-prototypes.h>
+#include <asm/hmi.h>
 #include <sysdev/fsl_pci.h>
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
@@ -307,9 +309,13 @@ long hmi_exception_realmode(struct pt_regs *regs)
 {
 	__this_cpu_inc(irq_stat.hmi_exceptions);
 
+	wait_for_subcore_guest_exit();
+
 	if (ppc_md.hmi_exception_early)
 		ppc_md.hmi_exception_early(regs);
 
+	wait_for_tb_resync();
+
 	return 0;
 }
 
@@ -1376,6 +1382,7 @@ void facility_unavailable_exception(struct pt_regs *regs)
 		[FSCR_TM_LG] = "TM",
 		[FSCR_EBB_LG] = "EBB",
 		[FSCR_TAR_LG] = "TAR",
+		[FSCR_LM_LG] = "LM",
 	};
 	char *facility = "unknown";
 	u64 value;
@@ -1418,7 +1425,8 @@ void facility_unavailable_exception(struct pt_regs *regs)
 			rd = (instword >> 21) & 0x1f;
 			current->thread.dscr = regs->gpr[rd];
 			current->thread.dscr_inherit = 1;
-			mtspr(SPRN_FSCR, value | FSCR_DSCR);
+			current->thread.fscr |= FSCR_DSCR;
+			mtspr(SPRN_FSCR, current->thread.fscr);
 		}
 
 		/* Read from DSCR (mfspr RT, 0x03) */
@@ -1432,6 +1440,14 @@ void facility_unavailable_exception(struct pt_regs *regs)
 			emulate_single_step(regs);
 		}
 		return;
+	} else if ((status == FSCR_LM_LG) && cpu_has_feature(CPU_FTR_ARCH_300)) {
+		/*
+		 * This process has touched LM, so turn it on forever
+		 * for this process
+		 */
+		current->thread.fscr |= FSCR_LM;
+		mtspr(SPRN_FSCR, current->thread.fscr);
+		return;
 	}
 
 	if ((status < ARRAY_SIZE(facility_strings)) &&
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 1c2e7a343bf5..616a6d854638 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -70,10 +70,11 @@ _GLOBAL(load_up_altivec)
 	MTMSRD(r5)			/* enable use of AltiVec now */
 	isync
 
-	/* Hack: if we get an altivec unavailable trap with VRSAVE
-	 * set to all zeros, we assume this is a broken application
-	 * that fails to set it properly, and thus we switch it to
-	 * all 1's
+	/*
+	 * While userspace in general ignores VRSAVE, glibc uses it as a boolean
+	 * to optimise userspace context save/restore. Whenever we take an
+	 * altivec unavailable exception we must set VRSAVE to something non
+	 * zero. Set it to all 1s. See also the programming note in the ISA.
 	 */
 	mfspr	r4,SPRN_VRSAVE
 	cmpwi	0,r4,0
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 2dd91f79de05..b5fba689fca6 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -165,7 +165,7 @@ SECTIONS
 	. = ALIGN(8);
 	.dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET)
 	{
-#ifdef CONFIG_RELOCATABLE_PPC32
+#ifdef CONFIG_PPC32
 		__dynamic_symtab = .;
 #endif
 		*(.dynsym)
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index eba0bea6e032..1f9e5529e692 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -20,7 +20,7 @@ common-objs-y += powerpc.o emulate.o emulate_loadstore.o
 obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o
 obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o
 
-AFLAGS_booke_interrupts.o := -I$(obj)
+AFLAGS_booke_interrupts.o := -I$(objtree)/$(obj)
 
 kvm-e500-objs := \
 	$(common-objs-y) \
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 114edace6cdd..a587e8f4fd26 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -34,9 +34,9 @@
 
 void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
-	ppc_md.hpte_invalidate(pte->slot, pte->host_vpn,
-			       pte->pagesize, pte->pagesize, MMU_SEGSIZE_256M,
-			       false);
+	mmu_hash_ops.hpte_invalidate(pte->slot, pte->host_vpn,
+				     pte->pagesize, pte->pagesize,
+				     MMU_SEGSIZE_256M, false);
 }
 
 /* We keep 512 gvsid->hvsid entries, mapping the guest ones to the array using
@@ -169,13 +169,13 @@ map_again:
 
 	/* In case we tried normal mapping already, let's nuke old entries */
 	if (attempt > 1)
-		if (ppc_md.hpte_remove(hpteg) < 0) {
+		if (mmu_hash_ops.hpte_remove(hpteg) < 0) {
 			r = -1;
 			goto out_unlock;
 		}
 
-	ret = ppc_md.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
-				 hpsize, hpsize, MMU_SEGSIZE_256M);
+	ret = mmu_hash_ops.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
+				       hpsize, hpsize, MMU_SEGSIZE_256M);
 
 	if (ret < 0) {
 		/* If we couldn't map a primary PTE, try a secondary */
@@ -187,8 +187,10 @@ map_again:
 		trace_kvm_book3s_64_mmu_map(rflags, hpteg,
 					    vpn, hpaddr, orig_pte);
 
-		/* The ppc_md code may give us a secondary entry even though we
-		   asked for a primary. Fix up. */
+		/*
+		 * The mmu_hash_ops code may give us a secondary entry even
+		 * though we asked for a primary. Fix up.
+		 */
 		if ((ret & _PTEIDX_SECONDARY) && !(vflags & HPTE_V_SECONDARY)) {
 			hash = ~hash;
 			hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 18cf6d1f8174..c379ff5a4438 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -242,7 +242,8 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret = H_SUCCESS, idx;
 	unsigned long entry, ua = 0;
-	u64 __user *tces, tce;
+	u64 __user *tces;
+	u64 tce;
 
 	stt = kvmppc_find_table(vcpu, liobn);
 	if (!stt)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e20beae5ca7a..2fd5580c8f6e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -52,6 +52,7 @@
 #include <asm/switch_to.h>
 #include <asm/smp.h>
 #include <asm/dbell.h>
+#include <asm/hmi.h>
 #include <linux/gfp.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
@@ -2522,7 +2523,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 		list_for_each_entry(pvc, &core_info.vcs[sub], preempt_list)
 			spin_unlock(&pvc->lock);
 
-	kvm_guest_enter();
+	guest_enter();
 
 	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
 
@@ -2570,7 +2571,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 
 	/* make sure updates to secondary vcpu structs are visible now */
 	smp_mb();
-	kvm_guest_exit();
+	guest_exit();
 
 	for (sub = 0; sub < core_info.n_subcores; ++sub)
 		list_for_each_entry_safe(pvc, vcnext, &core_info.vcs[sub],
@@ -3401,6 +3402,38 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.hcall_implemented = kvmppc_hcall_impl_hv,
 };
 
+static int kvm_init_subcore_bitmap(void)
+{
+	int i, j;
+	int nr_cores = cpu_nr_cores();
+	struct sibling_subcore_state *sibling_subcore_state;
+
+	for (i = 0; i < nr_cores; i++) {
+		int first_cpu = i * threads_per_core;
+		int node = cpu_to_node(first_cpu);
+
+		/* Ignore if it is already allocated. */
+		if (paca[first_cpu].sibling_subcore_state)
+			continue;
+
+		sibling_subcore_state =
+			kmalloc_node(sizeof(struct sibling_subcore_state),
+							GFP_KERNEL, node);
+		if (!sibling_subcore_state)
+			return -ENOMEM;
+
+		memset(sibling_subcore_state, 0,
+				sizeof(struct sibling_subcore_state));
+
+		for (j = 0; j < threads_per_core; j++) {
+			int cpu = first_cpu + j;
+
+			paca[cpu].sibling_subcore_state = sibling_subcore_state;
+		}
+	}
+	return 0;
+}
+
 static int kvmppc_book3s_init_hv(void)
 {
 	int r;
@@ -3411,6 +3444,10 @@ static int kvmppc_book3s_init_hv(void)
 	if (r < 0)
 		return -ENODEV;
 
+	r = kvm_init_subcore_bitmap();
+	if (r)
+		return r;
+
 	kvm_ops_hv.owner = THIS_MODULE;
 	kvmppc_hv_ops = &kvm_ops_hv;
 
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index 93b5f5c9b445..0fa70a9618d7 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -13,6 +13,9 @@
 #include <linux/kernel.h>
 #include <asm/opal.h>
 #include <asm/mce.h>
+#include <asm/machdep.h>
+#include <asm/cputhreads.h>
+#include <asm/hmi.h>
 
 /* SRR1 bits for machine check on POWER7 */
 #define SRR1_MC_LDSTERR		(1ul << (63-42))
@@ -140,3 +143,176 @@ long kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
 {
 	return kvmppc_realmode_mc_power7(vcpu);
 }
+
+/* Check if dynamic split is in force and return subcore size accordingly. */
+static inline int kvmppc_cur_subcore_size(void)
+{
+	if (local_paca->kvm_hstate.kvm_split_mode)
+		return local_paca->kvm_hstate.kvm_split_mode->subcore_size;
+
+	return threads_per_subcore;
+}
+
+void kvmppc_subcore_enter_guest(void)
+{
+	int thread_id, subcore_id;
+
+	thread_id = cpu_thread_in_core(local_paca->paca_index);
+	subcore_id = thread_id / kvmppc_cur_subcore_size();
+
+	local_paca->sibling_subcore_state->in_guest[subcore_id] = 1;
+}
+
+void kvmppc_subcore_exit_guest(void)
+{
+	int thread_id, subcore_id;
+
+	thread_id = cpu_thread_in_core(local_paca->paca_index);
+	subcore_id = thread_id / kvmppc_cur_subcore_size();
+
+	local_paca->sibling_subcore_state->in_guest[subcore_id] = 0;
+}
+
+static bool kvmppc_tb_resync_required(void)
+{
+	if (test_and_set_bit(CORE_TB_RESYNC_REQ_BIT,
+				&local_paca->sibling_subcore_state->flags))
+		return false;
+
+	return true;
+}
+
+static void kvmppc_tb_resync_done(void)
+{
+	clear_bit(CORE_TB_RESYNC_REQ_BIT,
+			&local_paca->sibling_subcore_state->flags);
+}
+
+/*
+ * kvmppc_realmode_hmi_handler() is called only by primary thread during
+ * guest exit path.
+ *
+ * There are multiple reasons why HMI could occur, one of them is
+ * Timebase (TB) error. If this HMI is due to TB error, then TB would
+ * have been in stopped state. The opal hmi handler Will fix it and
+ * restore the TB value with host timebase value. For HMI caused due
+ * to non-TB errors, opal hmi handler will not touch/restore TB register
+ * and hence there won't be any change in TB value.
+ *
+ * Since we are not sure about the cause of this HMI, we can't be sure
+ * about the content of TB register whether it holds guest or host timebase
+ * value. Hence the idea is to resync the TB on every HMI, so that we
+ * know about the exact state of the TB value. Resync TB call will
+ * restore TB to host timebase.
+ *
+ * Things to consider:
+ * - On TB error, HMI interrupt is reported on all the threads of the core
+ *   that has encountered TB error irrespective of split-core mode.
+ * - The very first thread on the core that get chance to fix TB error
+ *   would rsync the TB with local chipTOD value.
+ * - The resync TB is a core level action i.e. it will sync all the TBs
+ *   in that core independent of split-core mode. This means if we trigger
+ *   TB sync from a thread from one subcore, it would affect TB values of
+ *   sibling subcores of the same core.
+ *
+ * All threads need to co-ordinate before making opal hmi handler.
+ * All threads will use sibling_subcore_state->in_guest[] (shared by all
+ * threads in the core) in paca which holds information about whether
+ * sibling subcores are in Guest mode or host mode. The in_guest[] array
+ * is of size MAX_SUBCORE_PER_CORE=4, indexed using subcore id to set/unset
+ * subcore status. Only primary threads from each subcore is responsible
+ * to set/unset its designated array element while entering/exiting the
+ * guset.
+ *
+ * After invoking opal hmi handler call, one of the thread (of entire core)
+ * will need to resync the TB. Bit 63 from subcore state bitmap flags
+ * (sibling_subcore_state->flags) will be used to co-ordinate between
+ * primary threads to decide who takes up the responsibility.
+ *
+ * This is what we do:
+ * - Primary thread from each subcore tries to set resync required bit[63]
+ *   of paca->sibling_subcore_state->flags.
+ * - The first primary thread that is able to set the flag takes the
+ *   responsibility of TB resync. (Let us call it as thread leader)
+ * - All other threads which are in host will call
+ *   wait_for_subcore_guest_exit() and wait for in_guest[0-3] from
+ *   paca->sibling_subcore_state to get cleared.
+ * - All the primary thread will clear its subcore status from subcore
+ *   state in_guest[] array respectively.
+ * - Once all primary threads clear in_guest[0-3], all of them will invoke
+ *   opal hmi handler.
+ * - Now all threads will wait for TB resync to complete by invoking
+ *   wait_for_tb_resync() except the thread leader.
+ * - Thread leader will do a TB resync by invoking opal_resync_timebase()
+ *   call and the it will clear the resync required bit.
+ * - All other threads will now come out of resync wait loop and proceed
+ *   with individual execution.
+ * - On return of this function, primary thread will signal all
+ *   secondary threads to proceed.
+ * - All secondary threads will eventually call opal hmi handler on
+ *   their exit path.
+ */
+
+long kvmppc_realmode_hmi_handler(void)
+{
+	int ptid = local_paca->kvm_hstate.ptid;
+	bool resync_req;
+
+	/* This is only called on primary thread. */
+	BUG_ON(ptid != 0);
+	__this_cpu_inc(irq_stat.hmi_exceptions);
+
+	/*
+	 * By now primary thread has already completed guest->host
+	 * partition switch but haven't signaled secondaries yet.
+	 * All the secondary threads on this subcore is waiting
+	 * for primary thread to signal them to go ahead.
+	 *
+	 * For threads from subcore which isn't in guest, they all will
+	 * wait until all other subcores on this core exit the guest.
+	 *
+	 * Now set the resync required bit. If you are the first to
+	 * set this bit then kvmppc_tb_resync_required() function will
+	 * return true. For rest all other subcores
+	 * kvmppc_tb_resync_required() will return false.
+	 *
+	 * If resync_req == true, then this thread is responsible to
+	 * initiate TB resync after hmi handler has completed.
+	 * All other threads on this core will wait until this thread
+	 * clears the resync required bit flag.
+	 */
+	resync_req = kvmppc_tb_resync_required();
+
+	/* Reset the subcore status to indicate it has exited guest */
+	kvmppc_subcore_exit_guest();
+
+	/*
+	 * Wait for other subcores on this core to exit the guest.
+	 * All the primary threads and threads from subcore that are
+	 * not in guest will wait here until all subcores are out
+	 * of guest context.
+	 */
+	wait_for_subcore_guest_exit();
+
+	/*
+	 * At this point we are sure that primary threads from each
+	 * subcore on this core have completed guest->host partition
+	 * switch. Now it is safe to call HMI handler.
+	 */
+	if (ppc_md.hmi_exception_early)
+		ppc_md.hmi_exception_early(NULL);
+
+	/*
+	 * Check if this thread is responsible to resync TB.
+	 * All other threads will wait until this thread completes the
+	 * TB resync.
+	 */
+	if (resync_req) {
+		opal_resync_timebase();
+		/* Reset TB resync req bit */
+		kvmppc_tb_resync_done();
+	} else {
+		wait_for_tb_resync();
+	}
+	return 0;
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e571ad277398..975655573844 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -29,6 +29,7 @@
 #include <asm/kvm_book3s_asm.h>
 #include <asm/book3s/64/mmu-hash.h>
 #include <asm/tm.h>
+#include <asm/opal.h>
 
 #define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
 
@@ -373,6 +374,18 @@ kvm_secondary_got_guest:
 	lwsync
 	std	r0, HSTATE_KVM_VCORE(r13)
 
+	/*
+	 * All secondaries exiting guest will fall through this path.
+	 * Before proceeding, just check for HMI interrupt and
+	 * invoke opal hmi handler. By now we are sure that the
+	 * primary thread on this core/subcore has already made partition
+	 * switch/TB resync and we are good to call opal hmi handler.
+	 */
+	cmpwi	r12, BOOK3S_INTERRUPT_HMI
+	bne	kvm_no_guest
+
+	li	r3,0			/* NULL argument */
+	bl	hmi_exception_realmode
 /*
  * At this point we have finished executing in the guest.
  * We need to wait for hwthread_req to become zero, since
@@ -392,7 +405,7 @@ kvm_no_guest:
 	cmpwi	r3, 0
 	bne	54f
 /*
- * We jump to power7_wakeup_loss, which will return to the caller
+ * We jump to pnv_wakeup_loss, which will return to the caller
  * of power7_nap in the powernv cpu offline loop.  The value we
  * put in r3 becomes the return value for power7_nap.
  */
@@ -401,7 +414,7 @@ kvm_no_guest:
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
 	li	r3, 0
-	b	power7_wakeup_loss
+	b	pnv_wakeup_loss
 
 53:	HMT_LOW
 	ld	r5, HSTATE_KVM_VCORE(r13)
@@ -428,6 +441,22 @@ kvm_no_guest:
  */
 kvm_unsplit_nap:
 	/*
+	 * When secondaries are napping in kvm_unsplit_nap() with
+	 * hwthread_req = 1, HMI goes ignored even though subcores are
+	 * already exited the guest. Hence HMI keeps waking up secondaries
+	 * from nap in a loop and secondaries always go back to nap since
+	 * no vcore is assigned to them. This makes impossible for primary
+	 * thread to get hold of secondary threads resulting into a soft
+	 * lockup in KVM path.
+	 *
+	 * Let us check if HMI is pending and handle it before we go to nap.
+	 */
+	cmpwi	r12, BOOK3S_INTERRUPT_HMI
+	bne	55f
+	li	r3, 0			/* NULL argument */
+	bl	hmi_exception_realmode
+55:
+	/*
 	 * Ensure that secondary doesn't nap when it has
 	 * its vcore pointer set.
 	 */
@@ -601,6 +630,11 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_DPDES, r8
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
+	/* Mark the subcore state as inside guest */
+	bl	kvmppc_subcore_enter_guest
+	nop
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	ld	r4, HSTATE_KVM_VCPU(r13)
 	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
 
@@ -655,112 +689,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 BEGIN_FTR_SECTION
-	b	skip_tm
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-
-	/* Turn on TM/FP/VSX/VMX so we can restore them. */
-	mfmsr	r5
-	li	r6, MSR_TM >> 32
-	sldi	r6, r6, 32
-	or	r5, r5, r6
-	ori	r5, r5, MSR_FP
-	oris	r5, r5, (MSR_VEC | MSR_VSX)@h
-	mtmsrd	r5
-
-	/*
-	 * The user may change these outside of a transaction, so they must
-	 * always be context switched.
-	 */
-	ld	r5, VCPU_TFHAR(r4)
-	ld	r6, VCPU_TFIAR(r4)
-	ld	r7, VCPU_TEXASR(r4)
-	mtspr	SPRN_TFHAR, r5
-	mtspr	SPRN_TFIAR, r6
-	mtspr	SPRN_TEXASR, r7
-
-	ld	r5, VCPU_MSR(r4)
-	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
-	beq	skip_tm	/* TM not active in guest */
-
-	/* Make sure the failure summary is set, otherwise we'll program check
-	 * when we trechkpt.  It's possible that this might have been not set
-	 * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
-	 * host.
-	 */
-	oris	r7, r7, (TEXASR_FS)@h
-	mtspr	SPRN_TEXASR, r7
-
-	/*
-	 * We need to load up the checkpointed state for the guest.
-	 * We need to do this early as it will blow away any GPRs, VSRs and
-	 * some SPRs.
-	 */
-
-	mr	r31, r4
-	addi	r3, r31, VCPU_FPRS_TM
-	bl	load_fp_state
-	addi	r3, r31, VCPU_VRS_TM
-	bl	load_vr_state
-	mr	r4, r31
-	lwz	r7, VCPU_VRSAVE_TM(r4)
-	mtspr	SPRN_VRSAVE, r7
-
-	ld	r5, VCPU_LR_TM(r4)
-	lwz	r6, VCPU_CR_TM(r4)
-	ld	r7, VCPU_CTR_TM(r4)
-	ld	r8, VCPU_AMR_TM(r4)
-	ld	r9, VCPU_TAR_TM(r4)
-	mtlr	r5
-	mtcr	r6
-	mtctr	r7
-	mtspr	SPRN_AMR, r8
-	mtspr	SPRN_TAR, r9
-
-	/*
-	 * Load up PPR and DSCR values but don't put them in the actual SPRs
-	 * till the last moment to avoid running with userspace PPR and DSCR for
-	 * too long.
-	 */
-	ld	r29, VCPU_DSCR_TM(r4)
-	ld	r30, VCPU_PPR_TM(r4)
-
-	std	r2, PACATMSCRATCH(r13) /* Save TOC */
-
-	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
-	li	r5, 0
-	mtmsrd	r5, 1
-
-	/* Load GPRs r0-r28 */
-	reg = 0
-	.rept	29
-	ld	reg, VCPU_GPRS_TM(reg)(r31)
-	reg = reg + 1
-	.endr
-
-	mtspr	SPRN_DSCR, r29
-	mtspr	SPRN_PPR, r30
-
-	/* Load final GPRs */
-	ld	29, VCPU_GPRS_TM(29)(r31)
-	ld	30, VCPU_GPRS_TM(30)(r31)
-	ld	31, VCPU_GPRS_TM(31)(r31)
-
-	/* TM checkpointed state is now setup.  All GPRs are now volatile. */
-	TRECHKPT
-
-	/* Now let's get back the state we need. */
-	HMT_MEDIUM
-	GET_PACA(r13)
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-	ld	r4, HSTATE_KVM_VCPU(r13)
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATMSCRATCH(r13)
-
-	/* Set the MSR RI since we have our registers back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-skip_tm:
+	bl	kvmppc_restore_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 
 	/* Load guest PMU registers */
@@ -841,12 +771,6 @@ BEGIN_FTR_SECTION
 	/* Skip next section on POWER7 */
 	b	8f
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
-	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
 	/* Load up POWER8-specific registers */
 	ld	r5, VCPU_IAMR(r4)
 	lwz	r6, VCPU_PSPB(r4)
@@ -1436,106 +1360,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 BEGIN_FTR_SECTION
-	b	2f
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-	/* Turn on TM. */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
-	ld	r5, VCPU_MSR(r9)
-	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
-	beq	1f	/* TM not active in guest. */
-
-	li	r3, TM_CAUSE_KVM_RESCHED
-
-	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
-	li	r5, 0
-	mtmsrd	r5, 1
-
-	/* All GPRs are volatile at this point. */
-	TRECLAIM(R3)
-
-	/* Temporarily store r13 and r9 so we have some regs to play with */
-	SET_SCRATCH0(r13)
-	GET_PACA(r13)
-	std	r9, PACATMSCRATCH(r13)
-	ld	r9, HSTATE_KVM_VCPU(r13)
-
-	/* Get a few more GPRs free. */
-	std	r29, VCPU_GPRS_TM(29)(r9)
-	std	r30, VCPU_GPRS_TM(30)(r9)
-	std	r31, VCPU_GPRS_TM(31)(r9)
-
-	/* Save away PPR and DSCR soon so don't run with user values. */
-	mfspr	r31, SPRN_PPR
-	HMT_MEDIUM
-	mfspr	r30, SPRN_DSCR
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-
-	/* Save all but r9, r13 & r29-r31 */
-	reg = 0
-	.rept	29
-	.if (reg != 9) && (reg != 13)
-	std	reg, VCPU_GPRS_TM(reg)(r9)
-	.endif
-	reg = reg + 1
-	.endr
-	/* ... now save r13 */
-	GET_SCRATCH0(r4)
-	std	r4, VCPU_GPRS_TM(13)(r9)
-	/* ... and save r9 */
-	ld	r4, PACATMSCRATCH(r13)
-	std	r4, VCPU_GPRS_TM(9)(r9)
-
-	/* Reload stack pointer and TOC. */
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATOC(r13)
-
-	/* Set MSR RI now we have r1 and r13 back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-
-	/* Save away checkpinted SPRs. */
-	std	r31, VCPU_PPR_TM(r9)
-	std	r30, VCPU_DSCR_TM(r9)
-	mflr	r5
-	mfcr	r6
-	mfctr	r7
-	mfspr	r8, SPRN_AMR
-	mfspr	r10, SPRN_TAR
-	std	r5, VCPU_LR_TM(r9)
-	stw	r6, VCPU_CR_TM(r9)
-	std	r7, VCPU_CTR_TM(r9)
-	std	r8, VCPU_AMR_TM(r9)
-	std	r10, VCPU_TAR_TM(r9)
-
-	/* Restore r12 as trap number. */
-	lwz	r12, VCPU_TRAP(r9)
-
-	/* Save FP/VSX. */
-	addi	r3, r9, VCPU_FPRS_TM
-	bl	store_fp_state
-	addi	r3, r9, VCPU_VRS_TM
-	bl	store_vr_state
-	mfspr	r6, SPRN_VRSAVE
-	stw	r6, VCPU_VRSAVE_TM(r9)
-1:
-	/*
-	 * We need to save these SPRs after the treclaim so that the software
-	 * error code is recorded correctly in the TEXASR.  Also the user may
-	 * change these outside of a transaction, so they must always be
-	 * context switched.
-	 */
-	mfspr	r5, SPRN_TFHAR
-	mfspr	r6, SPRN_TFIAR
-	mfspr	r7, SPRN_TEXASR
-	std	r5, VCPU_TFHAR(r9)
-	std	r6, VCPU_TFIAR(r9)
-	std	r7, VCPU_TEXASR(r9)
-2:
+	bl	kvmppc_save_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 
 	/* Increment yield count if they have a VPA */
@@ -1683,6 +1509,23 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_DPDES, r8
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
+	/* If HMI, call kvmppc_realmode_hmi_handler() */
+	cmpwi	r12, BOOK3S_INTERRUPT_HMI
+	bne	27f
+	bl	kvmppc_realmode_hmi_handler
+	nop
+	li	r12, BOOK3S_INTERRUPT_HMI
+	/*
+	 * At this point kvmppc_realmode_hmi_handler would have resync-ed
+	 * the TB. Hence it is not required to subtract guest timebase
+	 * offset from timebase. So, skip it.
+	 *
+	 * Also, do not call kvmppc_subcore_exit_guest() because it has
+	 * been invoked as part of kvmppc_realmode_hmi_handler().
+	 */
+	b	30f
+
+27:
 	/* Subtract timebase offset from timebase */
 	ld	r8,VCORE_TB_OFFSET(r5)
 	cmpdi	r8,0
@@ -1698,8 +1541,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	addis	r8,r8,0x100		/* if so, increment upper 40 bits */
 	mtspr	SPRN_TBU40,r8
 
+17:	bl	kvmppc_subcore_exit_guest
+	nop
+30:	ld	r5,HSTATE_KVM_VCORE(r13)
+	ld	r4,VCORE_KVM(r5)	/* pointer to struct kvm */
+
 	/* Reset PCR */
-17:	ld	r0, VCORE_PCR(r5)
+	ld	r0, VCORE_PCR(r5)
 	cmpdi	r0, 0
 	beq	18f
 	li	r0, 0
@@ -2245,6 +2093,13 @@ _GLOBAL(kvmppc_h_cede)		/* r3 = vcpu pointer, r11 = msr, r13 = paca */
 	/* save FP state */
 	bl	kvmppc_save_fp
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	bl	kvmppc_save_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+
 	/*
 	 * Set DEC to the smaller of DEC and HDEC, so that we wake
 	 * no later than the end of our timeslice (HDEC interrupts
@@ -2321,6 +2176,12 @@ kvm_end_cede:
 	bl	kvmhv_accumulate_time
 #endif
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	bl	kvmppc_restore_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+
 	/* load up FP state */
 	bl	kvmppc_load_fp
 
@@ -2461,6 +2322,8 @@ BEGIN_FTR_SECTION
 	cmpwi	r6, 3			/* hypervisor doorbell? */
 	beq	3f
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	cmpwi	r6, 0xa			/* Hypervisor maintenance ? */
+	beq	4f
 	li	r3, 1			/* anything else, return 1 */
 0:	blr
 
@@ -2482,6 +2345,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	li	r3, -1
 	blr
 
+	/* Woken up due to Hypervisor maintenance interrupt */
+4:	li	r12, BOOK3S_INTERRUPT_HMI
+	li	r3, 1
+	blr
+
 /*
  * Determine what sort of external interrupt is pending (if any).
  * Returns:
@@ -2631,6 +2499,239 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	mr	r4,r31
 	blr
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Save transactional state and TM-related registers.
+ * Called with r9 pointing to the vcpu struct.
+ * This can modify all checkpointed registers, but
+ * restores r1, r2 and r9 (vcpu pointer) before exit.
+ */
+kvmppc_save_tm:
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+
+	/* Turn on TM. */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	ld	r5, VCPU_MSR(r9)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beq	1f	/* TM not active in guest. */
+
+	std	r1, HSTATE_HOST_R1(r13)
+	li	r3, TM_CAUSE_KVM_RESCHED
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* All GPRs are volatile at this point. */
+	TRECLAIM(R3)
+
+	/* Temporarily store r13 and r9 so we have some regs to play with */
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9, PACATMSCRATCH(r13)
+	ld	r9, HSTATE_KVM_VCPU(r13)
+
+	/* Get a few more GPRs free. */
+	std	r29, VCPU_GPRS_TM(29)(r9)
+	std	r30, VCPU_GPRS_TM(30)(r9)
+	std	r31, VCPU_GPRS_TM(31)(r9)
+
+	/* Save away PPR and DSCR soon so don't run with user values. */
+	mfspr	r31, SPRN_PPR
+	HMT_MEDIUM
+	mfspr	r30, SPRN_DSCR
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+
+	/* Save all but r9, r13 & r29-r31 */
+	reg = 0
+	.rept	29
+	.if (reg != 9) && (reg != 13)
+	std	reg, VCPU_GPRS_TM(reg)(r9)
+	.endif
+	reg = reg + 1
+	.endr
+	/* ... now save r13 */
+	GET_SCRATCH0(r4)
+	std	r4, VCPU_GPRS_TM(13)(r9)
+	/* ... and save r9 */
+	ld	r4, PACATMSCRATCH(r13)
+	std	r4, VCPU_GPRS_TM(9)(r9)
+
+	/* Reload stack pointer and TOC. */
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATOC(r13)
+
+	/* Set MSR RI now we have r1 and r13 back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	/* Save away checkpinted SPRs. */
+	std	r31, VCPU_PPR_TM(r9)
+	std	r30, VCPU_DSCR_TM(r9)
+	mflr	r5
+	mfcr	r6
+	mfctr	r7
+	mfspr	r8, SPRN_AMR
+	mfspr	r10, SPRN_TAR
+	std	r5, VCPU_LR_TM(r9)
+	stw	r6, VCPU_CR_TM(r9)
+	std	r7, VCPU_CTR_TM(r9)
+	std	r8, VCPU_AMR_TM(r9)
+	std	r10, VCPU_TAR_TM(r9)
+
+	/* Restore r12 as trap number. */
+	lwz	r12, VCPU_TRAP(r9)
+
+	/* Save FP/VSX. */
+	addi	r3, r9, VCPU_FPRS_TM
+	bl	store_fp_state
+	addi	r3, r9, VCPU_VRS_TM
+	bl	store_vr_state
+	mfspr	r6, SPRN_VRSAVE
+	stw	r6, VCPU_VRSAVE_TM(r9)
+1:
+	/*
+	 * We need to save these SPRs after the treclaim so that the software
+	 * error code is recorded correctly in the TEXASR.  Also the user may
+	 * change these outside of a transaction, so they must always be
+	 * context switched.
+	 */
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+
+/*
+ * Restore transactional state and TM-related registers.
+ * Called with r4 pointing to the vcpu struct.
+ * This potentially modifies all checkpointed registers.
+ * It restores r1, r2, r4 from the PACA.
+ */
+kvmppc_restore_tm:
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+
+	/* Turn on TM/FP/VSX/VMX so we can restore them. */
+	mfmsr	r5
+	li	r6, MSR_TM >> 32
+	sldi	r6, r6, 32
+	or	r5, r5, r6
+	ori	r5, r5, MSR_FP
+	oris	r5, r5, (MSR_VEC | MSR_VSX)@h
+	mtmsrd	r5
+
+	/*
+	 * The user may change these outside of a transaction, so they must
+	 * always be context switched.
+	 */
+	ld	r5, VCPU_TFHAR(r4)
+	ld	r6, VCPU_TFIAR(r4)
+	ld	r7, VCPU_TEXASR(r4)
+	mtspr	SPRN_TFHAR, r5
+	mtspr	SPRN_TFIAR, r6
+	mtspr	SPRN_TEXASR, r7
+
+	ld	r5, VCPU_MSR(r4)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beqlr		/* TM not active in guest */
+	std	r1, HSTATE_HOST_R1(r13)
+
+	/* Make sure the failure summary is set, otherwise we'll program check
+	 * when we trechkpt.  It's possible that this might have been not set
+	 * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
+	 * host.
+	 */
+	oris	r7, r7, (TEXASR_FS)@h
+	mtspr	SPRN_TEXASR, r7
+
+	/*
+	 * We need to load up the checkpointed state for the guest.
+	 * We need to do this early as it will blow away any GPRs, VSRs and
+	 * some SPRs.
+	 */
+
+	mr	r31, r4
+	addi	r3, r31, VCPU_FPRS_TM
+	bl	load_fp_state
+	addi	r3, r31, VCPU_VRS_TM
+	bl	load_vr_state
+	mr	r4, r31
+	lwz	r7, VCPU_VRSAVE_TM(r4)
+	mtspr	SPRN_VRSAVE, r7
+
+	ld	r5, VCPU_LR_TM(r4)
+	lwz	r6, VCPU_CR_TM(r4)
+	ld	r7, VCPU_CTR_TM(r4)
+	ld	r8, VCPU_AMR_TM(r4)
+	ld	r9, VCPU_TAR_TM(r4)
+	mtlr	r5
+	mtcr	r6
+	mtctr	r7
+	mtspr	SPRN_AMR, r8
+	mtspr	SPRN_TAR, r9
+
+	/*
+	 * Load up PPR and DSCR values but don't put them in the actual SPRs
+	 * till the last moment to avoid running with userspace PPR and DSCR for
+	 * too long.
+	 */
+	ld	r29, VCPU_DSCR_TM(r4)
+	ld	r30, VCPU_PPR_TM(r4)
+
+	std	r2, PACATMSCRATCH(r13) /* Save TOC */
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* Load GPRs r0-r28 */
+	reg = 0
+	.rept	29
+	ld	reg, VCPU_GPRS_TM(reg)(r31)
+	reg = reg + 1
+	.endr
+
+	mtspr	SPRN_DSCR, r29
+	mtspr	SPRN_PPR, r30
+
+	/* Load final GPRs */
+	ld	29, VCPU_GPRS_TM(29)(r31)
+	ld	30, VCPU_GPRS_TM(30)(r31)
+	ld	31, VCPU_GPRS_TM(31)(r31)
+
+	/* TM checkpointed state is now setup.  All GPRs are now volatile. */
+	TRECHKPT
+
+	/* Now let's get back the state we need. */
+	HMT_MEDIUM
+	GET_PACA(r13)
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATMSCRATCH(r13)
+
+	/* Set the MSR RI since we have our registers back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+#endif
+
 /*
  * We come here if we get any exception or interrupt while we are
  * executing host real mode code while in guest MMU context.
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index d044b8b7c69d..901e6fe00c39 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -25,7 +25,7 @@
 #include <asm/exception-64s.h>
 
 #if defined(CONFIG_PPC_BOOK3S_64)
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 #define FUNC(name) 		name
 #else
 #define FUNC(name) 		GLUE(.,name)
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 8e4f64f0b774..e76f79a45988 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -35,7 +35,7 @@
 #include <asm/mmu_context.h>
 #include <asm/switch_to.h>
 #include <asm/firmware.h>
-#include <asm/hvcall.h>
+#include <asm/setup.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
@@ -914,7 +914,7 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	/* We get here with MSR.EE=1 */
 
 	trace_kvm_exit(exit_nr, vcpu);
-	kvm_guest_exit();
+	guest_exit();
 
 	switch (exit_nr) {
 	case BOOK3S_INTERRUPT_INST_STORAGE:
@@ -1049,7 +1049,17 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		int emul;
 
 program_interrupt:
-		flags = vcpu->arch.shadow_srr1 & 0x1f0000ull;
+		/*
+		 * shadow_srr1 only contains valid flags if we came here via
+		 * a program exception. The other exceptions (emulation assist,
+		 * FP unavailable, etc.) do not provide flags in SRR1, so use
+		 * an illegal-instruction exception when injecting a program
+		 * interrupt into the guest.
+		 */
+		if (exit_nr == BOOK3S_INTERRUPT_PROGRAM)
+			flags = vcpu->arch.shadow_srr1 & 0x1f0000ull;
+		else
+			flags = SRR1_PROGILL;
 
 		emul = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst);
 		if (emul != EMULATE_DONE) {
@@ -1531,7 +1541,7 @@ static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	kvmppc_clear_debug(vcpu);
 
-	/* No need for kvm_guest_exit. It's done in handle_exit.
+	/* No need for guest_exit. It's done in handle_exit.
 	   We also get here with interrupts enabled. */
 
 	/* Make sure we save the guest FPU/Altivec/VSX state */
@@ -1690,7 +1700,7 @@ static int kvmppc_core_init_vm_pr(struct kvm *kvm)
 	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
 		spin_lock(&kvm_global_user_count_lock);
 		if (++kvm_global_user_count == 1)
-			pSeries_disable_reloc_on_exc();
+			pseries_disable_reloc_on_exc();
 		spin_unlock(&kvm_global_user_count_lock);
 	}
 	return 0;
@@ -1706,7 +1716,7 @@ static void kvmppc_core_destroy_vm_pr(struct kvm *kvm)
 		spin_lock(&kvm_global_user_count_lock);
 		BUG_ON(kvm_global_user_count == 0);
 		if (--kvm_global_user_count == 0)
-			pSeries_enable_reloc_on_exc();
+			pseries_enable_reloc_on_exc();
 		spin_unlock(&kvm_global_user_count_lock);
 	}
 }
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 16c4d88ba27d..42a4b237df5f 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -36,7 +36,7 @@
 
 #if defined(CONFIG_PPC_BOOK3S_64)
 
-#if defined(_CALL_ELF) && _CALL_ELF == 2
+#ifdef PPC64_ELF_ABI_v2
 #define FUNC(name) 		name
 #else
 #define FUNC(name) 		GLUE(.,name)
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 4afae695899a..02b4672f7347 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -776,7 +776,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
-	/* No need for kvm_guest_exit. It's done in handle_exit.
+	/* No need for guest_exit. It's done in handle_exit.
 	   We also get here with interrupts enabled. */
 
 	/* Switch back to user space debug context */
@@ -1012,7 +1012,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	}
 
 	trace_kvm_exit(exit_nr, vcpu);
-	__kvm_guest_exit();
+	guest_exit_irqoff();
 
 	local_irq_enable();
 
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 5cc2e7af3a7b..b379146de55b 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -302,7 +302,6 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			advance = 0;
 			printk(KERN_ERR "Couldn't emulate instruction 0x%08x "
 			       "(op %d xop %d)\n", inst, get_op(inst), get_xop(inst));
-			kvmppc_core_queue_program(vcpu, 0);
 		}
 	}
 
diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c
index 6249cdc834d1..ed38f8114118 100644
--- a/arch/powerpc/kvm/mpic.c
+++ b/arch/powerpc/kvm/mpic.c
@@ -1823,7 +1823,8 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return 0;
 }
 
-int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm *kvm,
+			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
 {
 	int r = -EINVAL;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 02416fea7653..6ce40dd6fe51 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -119,7 +119,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 			continue;
 		}
 
-		__kvm_guest_enter();
+		guest_enter_irqoff();
 		return 1;
 	}
 
@@ -588,6 +588,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 #endif
+	case KVM_CAP_PPC_HTM:
+		r = cpu_has_feature(CPU_FTR_TM_COMP) &&
+		    is_kvmppc_hv_enabled(kvm);
+		break;
 	default:
 		r = 0;
 		break;
diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c
index 60b0b3fc8fc1..a58abe4afbd1 100644
--- a/arch/powerpc/lib/alloc.c
+++ b/arch/powerpc/lib/alloc.c
@@ -6,7 +6,7 @@
 #include <asm/setup.h>
 
 
-void * __init_refok zalloc_maybe_bootmem(size_t size, gfp_t mask)
+void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask)
 {
 	void *p;
 
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 8e6e51016cc5..fdec6e613e95 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -74,9 +74,9 @@ _GLOBAL(__csum_partial)
 	ld	r11,24(r3)
 
 	/*
-	 * On POWER6 and POWER7 back to back addes take 2 cycles because of
-	 * the XER dependency. This means the fastest this loop can go is
-	 * 16 cycles per iteration. The scheduling of the loop below has
+	 * On POWER6 and POWER7 back to back adde instructions take 2 cycles
+	 * because of the XER dependency. This means the fastest this loop can
+	 * go is 16 cycles per iteration. The scheduling of the loop below has
 	 * been shown to hit this on both POWER6 and POWER7.
 	 */
 	.align 5
@@ -275,9 +275,9 @@ source;	ld	r10,16(r3)
 source;	ld	r11,24(r3)
 
 	/*
-	 * On POWER6 and POWER7 back to back addes take 2 cycles because of
-	 * the XER dependency. This means the fastest this loop can go is
-	 * 16 cycles per iteration. The scheduling of the loop below has
+	 * On POWER6 and POWER7 back to back adde instructions take 2 cycles
+	 * because of the XER dependency. This means the fastest this loop can
+	 * go is 16 cycles per iteration. The scheduling of the loop below has
 	 * been shown to hit this on both POWER6 and POWER7.
 	 */
 	.align 5
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 7ce3870d7ddd..defb2998b818 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -20,7 +20,8 @@
 #include <asm/code-patching.h>
 #include <asm/page.h>
 #include <asm/sections.h>
-
+#include <asm/setup.h>
+#include <asm/firmware.h>
 
 struct fixup_entry {
 	unsigned long	mask;
@@ -130,7 +131,7 @@ void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 	}
 }
 
-void do_final_fixups(void)
+static void do_final_fixups(void)
 {
 #if defined(CONFIG_PPC64) && defined(CONFIG_RELOCATABLE)
 	int *src, *dest;
@@ -151,6 +152,33 @@ void do_final_fixups(void)
 #endif
 }
 
+void apply_feature_fixups(void)
+{
+	struct cpu_spec *spec = *PTRRELOC(&cur_cpu_spec);
+
+	/*
+	 * Apply the CPU-specific and firmware specific fixups to kernel text
+	 * (nop out sections not relevant to this CPU or this firmware).
+	 */
+	do_feature_fixups(spec->cpu_features,
+			  PTRRELOC(&__start___ftr_fixup),
+			  PTRRELOC(&__stop___ftr_fixup));
+
+	do_feature_fixups(spec->mmu_features,
+			  PTRRELOC(&__start___mmu_ftr_fixup),
+			  PTRRELOC(&__stop___mmu_ftr_fixup));
+
+	do_lwsync_fixups(spec->cpu_features,
+			 PTRRELOC(&__start___lwsync_fixup),
+			 PTRRELOC(&__stop___lwsync_fixup));
+
+#ifdef CONFIG_PPC64
+	do_feature_fixups(powerpc_firmware_features,
+			  &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
+#endif
+	do_final_fixups();
+}
+
 #ifdef CONFIG_FTR_FIXUP_SELFTEST
 
 #define check(x)	\
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index f7deebdf3365..b7b1237d4aa6 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -68,19 +68,3 @@ void __rw_yield(arch_rwlock_t *rw)
 		get_hard_smp_processor_id(holder_cpu), yield_count);
 }
 #endif
-
-void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_mb();
-
-	while (lock->slock) {
-		HMT_low();
-		if (SHARED_PROCESSOR)
-			__spin_yield(lock);
-	}
-	HMT_medium();
-
-	smp_mb();
-}
-
-EXPORT_SYMBOL(arch_spin_unlock_wait);
diff --git a/arch/powerpc/lib/ppc_ksyms.c b/arch/powerpc/lib/ppc_ksyms.c
index c422812f7405..ae69d846a841 100644
--- a/arch/powerpc/lib/ppc_ksyms.c
+++ b/arch/powerpc/lib/ppc_ksyms.c
@@ -9,11 +9,7 @@ EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memcmp);
 EXPORT_SYMBOL(memchr);
 
-EXPORT_SYMBOL(strcpy);
 EXPORT_SYMBOL(strncpy);
-EXPORT_SYMBOL(strcat);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strcmp);
 EXPORT_SYMBOL(strncmp);
 
 #ifndef CONFIG_GENERIC_CSUM
diff --git a/arch/powerpc/lib/rheap.c b/arch/powerpc/lib/rheap.c
index 69abf844c2c3..94058c21a482 100644
--- a/arch/powerpc/lib/rheap.c
+++ b/arch/powerpc/lib/rheap.c
@@ -325,7 +325,7 @@ void rh_init(rh_info_t * info, unsigned int alignment, int max_blocks,
 }
 EXPORT_SYMBOL_GPL(rh_init);
 
-/* Attach a free memory region, coalesces regions if adjuscent */
+/* Attach a free memory region, coalesces regions if adjacent */
 int rh_attach_region(rh_info_t * info, unsigned long start, int size)
 {
 	rh_block_t *blk;
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
index c80fb49ce607..beabc68d9a1e 100644
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -16,15 +16,6 @@
 	PPC_LONG_ALIGN
 	.text
 	
-_GLOBAL(strcpy)
-	addi	r5,r3,-1
-	addi	r4,r4,-1
-1:	lbzu	r0,1(r4)
-	cmpwi	0,r0,0
-	stbu	r0,1(r5)
-	bne	1b
-	blr
-
 /* This clears out any unused part of the destination buffer,
    just as the libc version does.  -- paulus */
 _GLOBAL(strncpy)
@@ -33,6 +24,7 @@ _GLOBAL(strncpy)
 	mtctr	r5
 	addi	r6,r3,-1
 	addi	r4,r4,-1
+	.balign 16
 1:	lbzu	r0,1(r4)
 	cmpwi	0,r0,0
 	stbu	r0,1(r6)
@@ -45,36 +37,13 @@ _GLOBAL(strncpy)
 	bdnz	2b
 	blr
 
-_GLOBAL(strcat)
-	addi	r5,r3,-1
-	addi	r4,r4,-1
-1:	lbzu	r0,1(r5)
-	cmpwi	0,r0,0
-	bne	1b
-	addi	r5,r5,-1
-1:	lbzu	r0,1(r4)
-	cmpwi	0,r0,0
-	stbu	r0,1(r5)
-	bne	1b
-	blr
-
-_GLOBAL(strcmp)
-	addi	r5,r3,-1
-	addi	r4,r4,-1
-1:	lbzu	r3,1(r5)
-	cmpwi	1,r3,0
-	lbzu	r0,1(r4)
-	subf.	r3,r0,r3
-	beqlr	1
-	beq	1b
-	blr
-
 _GLOBAL(strncmp)
 	PPC_LCMPI 0,r5,0
 	beq-	2f
 	mtctr	r5
 	addi	r5,r3,-1
 	addi	r4,r4,-1
+	.balign 16
 1:	lbzu	r3,1(r5)
 	cmpwi	1,r3,0
 	lbzu	r0,1(r4)
@@ -85,14 +54,6 @@ _GLOBAL(strncmp)
 2:	li	r3,0
 	blr
 
-_GLOBAL(strlen)
-	addi	r4,r3,-1
-1:	lbzu	r0,1(r4)
-	cmpwi	0,r0,0
-	bne	1b
-	subf	r3,r3,r4
-	blr
-
 #ifdef CONFIG_PPC32
 _GLOBAL(memcmp)
 	PPC_LCMPI 0,r5,0
@@ -114,6 +75,7 @@ _GLOBAL(memchr)
 	beq-	2f
 	mtctr	r5
 	addi	r3,r3,-1
+	.balign 16
 1:	lbzu	r0,1(r3)
 	cmpw	0,r0,r4
 	bdnzf	2,1b
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index b27e030fc9f8..bf925cdcaca9 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -21,6 +21,7 @@
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
 #include <asm/switch_to.h>
+#include <asm/asm-prototypes.h>
 
 int enter_vmx_usercopy(void)
 {
diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c
index 949100577db5..6c5025e81236 100644
--- a/arch/powerpc/mm/8xx_mmu.c
+++ b/arch/powerpc/mm/8xx_mmu.c
@@ -13,62 +13,115 @@
  */
 
 #include <linux/memblock.h>
+#include <asm/fixmap.h>
+#include <asm/code-patching.h>
 
 #include "mmu_decl.h"
 
+#define IMMR_SIZE (FIX_IMMR_SIZE << PAGE_SHIFT)
+
 extern int __map_without_ltlbs;
+
 /*
- * MMU_init_hw does the chip-specific initialization of the MMU hardware.
+ * Return PA for this VA if it is in IMMR area, or 0
  */
-void __init MMU_init_hw(void)
+phys_addr_t v_block_mapped(unsigned long va)
 {
-	/* Nothing to do for the time being but keep it similar to other PPC */
+	unsigned long p = PHYS_IMMR_BASE;
+
+	if (__map_without_ltlbs)
+		return 0;
+	if (va >= VIRT_IMMR_BASE && va < VIRT_IMMR_BASE + IMMR_SIZE)
+		return p + va - VIRT_IMMR_BASE;
+	return 0;
+}
+
+/*
+ * Return VA for a given PA or 0 if not mapped
+ */
+unsigned long p_block_mapped(phys_addr_t pa)
+{
+	unsigned long p = PHYS_IMMR_BASE;
+
+	if (__map_without_ltlbs)
+		return 0;
+	if (pa >= p && pa < p + IMMR_SIZE)
+		return VIRT_IMMR_BASE + pa - p;
+	return 0;
 }
 
-#define LARGE_PAGE_SIZE_4M	(1<<22)
 #define LARGE_PAGE_SIZE_8M	(1<<23)
-#define LARGE_PAGE_SIZE_64M	(1<<26)
 
-unsigned long __init mmu_mapin_ram(unsigned long top)
+/*
+ * MMU_init_hw does the chip-specific initialization of the MMU hardware.
+ */
+void __init MMU_init_hw(void)
 {
-	unsigned long v, s, mapped;
-	phys_addr_t p;
+	/* PIN up to the 3 first 8Mb after IMMR in DTLB table */
+#ifdef CONFIG_PIN_TLB
+	unsigned long ctr = mfspr(SPRN_MD_CTR) & 0xfe000000;
+	unsigned long flags = 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY;
+#ifdef CONFIG_PIN_TLB_IMMR
+	int i = 29;
+#else
+	int i = 28;
+#endif
+	unsigned long addr = 0;
+	unsigned long mem = total_lowmem;
+
+	for (; i < 32 && mem >= LARGE_PAGE_SIZE_8M; i++) {
+		mtspr(SPRN_MD_CTR, ctr | (i << 8));
+		mtspr(SPRN_MD_EPN, (unsigned long)__va(addr) | MD_EVALID);
+		mtspr(SPRN_MD_TWC, MD_PS8MEG | MD_SVALID);
+		mtspr(SPRN_MD_RPN, addr | flags | _PAGE_PRESENT);
+		addr += LARGE_PAGE_SIZE_8M;
+		mem -= LARGE_PAGE_SIZE_8M;
+	}
+#endif
+}
 
-	v = KERNELBASE;
-	p = 0;
-	s = top;
+static void mmu_mapin_immr(void)
+{
+	unsigned long p = PHYS_IMMR_BASE;
+	unsigned long v = VIRT_IMMR_BASE;
+	unsigned long f = pgprot_val(PAGE_KERNEL_NCG);
+	int offset;
 
-	if (__map_without_ltlbs)
-		return 0;
+	for (offset = 0; offset < IMMR_SIZE; offset += PAGE_SIZE)
+		map_page(v + offset, p + offset, f);
+}
 
-#ifdef CONFIG_PPC_4K_PAGES
-	while (s >= LARGE_PAGE_SIZE_8M) {
-		pmd_t *pmdp;
-		unsigned long val = p | MD_PS8MEG;
+/* Address of instructions to patch */
+#ifndef CONFIG_PIN_TLB_IMMR
+extern unsigned int DTLBMiss_jmp;
+#endif
+extern unsigned int DTLBMiss_cmp, FixupDAR_cmp;
 
-		pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
-		*pmdp++ = __pmd(val);
-		*pmdp++ = __pmd(val + LARGE_PAGE_SIZE_4M);
+void mmu_patch_cmp_limit(unsigned int *addr, unsigned long mapped)
+{
+	unsigned int instr = *addr;
 
-		v += LARGE_PAGE_SIZE_8M;
-		p += LARGE_PAGE_SIZE_8M;
-		s -= LARGE_PAGE_SIZE_8M;
-	}
-#else /* CONFIG_PPC_16K_PAGES */
-	while (s >= LARGE_PAGE_SIZE_64M) {
-		pmd_t *pmdp;
-		unsigned long val = p | MD_PS8MEG;
+	instr &= 0xffff0000;
+	instr |= (unsigned long)__va(mapped) >> 16;
+	patch_instruction(addr, instr);
+}
 
-		pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
-		*pmdp++ = __pmd(val);
+unsigned long __init mmu_mapin_ram(unsigned long top)
+{
+	unsigned long mapped;
 
-		v += LARGE_PAGE_SIZE_64M;
-		p += LARGE_PAGE_SIZE_64M;
-		s -= LARGE_PAGE_SIZE_64M;
-	}
+	if (__map_without_ltlbs) {
+		mapped = 0;
+		mmu_mapin_immr();
+#ifndef CONFIG_PIN_TLB_IMMR
+		patch_instruction(&DTLBMiss_jmp, PPC_INST_NOP);
 #endif
+	} else {
+		mapped = top & ~(LARGE_PAGE_SIZE_8M - 1);
+	}
 
-	mapped = top - s;
+	mmu_patch_cmp_limit(&DTLBMiss_cmp, mapped);
+	mmu_patch_cmp_limit(&FixupDAR_cmp, mapped);
 
 	/* If the size of RAM is not an exact power of two, we may not
 	 * have covered RAM in its entirety with 8 MiB
@@ -77,7 +130,8 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
 	 * coverage with normal-sized pages (or other reasons) do not
 	 * attempt to allocate outside the allowed range.
 	 */
-	memblock_set_current_limit(mapped);
+	if (mapped)
+		memblock_set_current_limit(mapped);
 
 	return mapped;
 }
@@ -90,13 +144,8 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 	 */
 	BUG_ON(first_memblock_base != 0);
 
-#ifdef CONFIG_PIN_TLB
 	/* 8xx can only access 24MB at the moment */
 	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01800000));
-#else
-	/* 8xx can only access 8MB at the moment */
-	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
-#endif
 }
 
 /*
diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c
index 6333b273d2d5..42c702b3be1f 100644
--- a/arch/powerpc/mm/hash64_4k.c
+++ b/arch/powerpc/mm/hash64_4k.c
@@ -70,8 +70,8 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
 
-		if (ppc_md.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_4K,
-					 MMU_PAGE_4K, ssize, flags) == -1)
+		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_4K,
+					       MMU_PAGE_4K, ssize, flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 
@@ -84,21 +84,23 @@ repeat:
 		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 
 		/* Insert into the hash table, primary slot */
-		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
-				  MMU_PAGE_4K, MMU_PAGE_4K, ssize);
+		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+						MMU_PAGE_4K, MMU_PAGE_4K, ssize);
 		/*
 		 * Primary is full, try the secondary
 		 */
 		if (unlikely(slot == -1)) {
 			hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
-			slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
-						  rflags, HPTE_V_SECONDARY,
-						  MMU_PAGE_4K, MMU_PAGE_4K, ssize);
+			slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
+							rflags,
+							HPTE_V_SECONDARY,
+							MMU_PAGE_4K,
+							MMU_PAGE_4K, ssize);
 			if (slot == -1) {
 				if (mftb() & 0x1)
 					hpte_group = ((hash & htab_hash_mask) *
 						      HPTES_PER_GROUP) & ~0x7UL;
-				ppc_md.hpte_remove(hpte_group);
+				mmu_hash_ops.hpte_remove(hpte_group);
 				/*
 				 * FIXME!! Should be try the group from which we removed ?
 				 */
diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index 16644e1f4e6b..3bbbea07378c 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -133,9 +133,9 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += hidx & _PTEIDX_GROUP_IX;
 
-		ret = ppc_md.hpte_updatepp(slot, rflags, vpn,
-					   MMU_PAGE_4K, MMU_PAGE_4K,
-					   ssize, flags);
+		ret = mmu_hash_ops.hpte_updatepp(slot, rflags, vpn,
+						 MMU_PAGE_4K, MMU_PAGE_4K,
+						 ssize, flags);
 		/*
 		 *if we failed because typically the HPTE wasn't really here
 		 * we try an insertion.
@@ -166,21 +166,22 @@ repeat:
 	hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 
 	/* Insert into the hash table, primary slot */
-	slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
-				  MMU_PAGE_4K, MMU_PAGE_4K, ssize);
+	slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+					MMU_PAGE_4K, MMU_PAGE_4K, ssize);
 	/*
 	 * Primary is full, try the secondary
 	 */
 	if (unlikely(slot == -1)) {
 		hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
-		slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
-					  rflags, HPTE_V_SECONDARY,
-					  MMU_PAGE_4K, MMU_PAGE_4K, ssize);
+		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
+						rflags, HPTE_V_SECONDARY,
+						MMU_PAGE_4K, MMU_PAGE_4K,
+						ssize);
 		if (slot == -1) {
 			if (mftb() & 0x1)
 				hpte_group = ((hash & htab_hash_mask) *
 					      HPTES_PER_GROUP) & ~0x7UL;
-			ppc_md.hpte_remove(hpte_group);
+			mmu_hash_ops.hpte_remove(hpte_group);
 			/*
 			 * FIXME!! Should be try the group from which we removed ?
 			 */
@@ -272,8 +273,9 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
 
-		if (ppc_md.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_64K,
-					 MMU_PAGE_64K, ssize, flags) == -1)
+		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_64K,
+					       MMU_PAGE_64K, ssize,
+					       flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 
@@ -286,21 +288,24 @@ repeat:
 		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 
 		/* Insert into the hash table, primary slot */
-		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
-				  MMU_PAGE_64K, MMU_PAGE_64K, ssize);
+		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+						MMU_PAGE_64K, MMU_PAGE_64K,
+						ssize);
 		/*
 		 * Primary is full, try the secondary
 		 */
 		if (unlikely(slot == -1)) {
 			hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
-			slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
-						  rflags, HPTE_V_SECONDARY,
-						  MMU_PAGE_64K, MMU_PAGE_64K, ssize);
+			slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
+							rflags,
+							HPTE_V_SECONDARY,
+							MMU_PAGE_64K,
+							MMU_PAGE_64K, ssize);
 			if (slot == -1) {
 				if (mftb() & 0x1)
 					hpte_group = ((hash & htab_hash_mask) *
 						      HPTES_PER_GROUP) & ~0x7UL;
-				ppc_md.hpte_remove(hpte_group);
+				mmu_hash_ops.hpte_remove(hpte_group);
 				/*
 				 * FIXME!! Should be try the group from which we removed ?
 				 */
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index f8a871a72985..88ce7d212320 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -55,7 +55,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 	 * We need 14 to 65 bits of va for a tlibe of 4K page
 	 * With vpn we ignore the lower VPN_SHIFT bits already.
 	 * And top two bits are already ignored because we can
-	 * only accomadate 76 bits in a 64 bit vpn with a VPN_SHIFT
+	 * only accomodate 76 bits in a 64 bit vpn with a VPN_SHIFT
 	 * of 12.
 	 */
 	va = vpn << VPN_SHIFT;
@@ -64,7 +64,8 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 	 * Older versions of the architecture (2.02 and earler) require the
 	 * masking of the top 16 bits.
 	 */
-	va &= ~(0xffffULL << 48);
+	if (mmu_has_feature(MMU_FTR_TLBIE_CROP_VA))
+		va &= ~(0xffffULL << 48);
 
 	switch (psize) {
 	case MMU_PAGE_4K:
@@ -113,7 +114,8 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 	 * Older versions of the architecture (2.02 and earler) require the
 	 * masking of the top 16 bits.
 	 */
-	va &= ~(0xffffULL << 48);
+	if (mmu_has_feature(MMU_FTR_TLBIE_CROP_VA))
+		va &= ~(0xffffULL << 48);
 
 	switch (psize) {
 	case MMU_PAGE_4K:
@@ -605,7 +607,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
  * crashdump and all bets are off anyway.
  *
  * TODO: add batching support when enabled.  remember, no dynamic memory here,
- * athough there is the control page available...
+ * although there is the control page available...
  */
 static void native_hpte_clear(void)
 {
@@ -723,23 +725,29 @@ static void native_flush_hash_range(unsigned long number, int local)
 	local_irq_restore(flags);
 }
 
-static int native_update_partition_table(u64 patb1)
+static int native_register_proc_table(unsigned long base, unsigned long page_size,
+				      unsigned long table_size)
 {
+	unsigned long patb1 = base << 25; /* VSID */
+
+	patb1 |= (page_size << 5);  /* sllp */
+	patb1 |= table_size;
+
 	partition_tb->patb1 = cpu_to_be64(patb1);
 	return 0;
 }
 
 void __init hpte_init_native(void)
 {
-	ppc_md.hpte_invalidate	= native_hpte_invalidate;
-	ppc_md.hpte_updatepp	= native_hpte_updatepp;
-	ppc_md.hpte_updateboltedpp = native_hpte_updateboltedpp;
-	ppc_md.hpte_insert	= native_hpte_insert;
-	ppc_md.hpte_remove	= native_hpte_remove;
-	ppc_md.hpte_clear_all	= native_hpte_clear;
-	ppc_md.flush_hash_range = native_flush_hash_range;
-	ppc_md.hugepage_invalidate   = native_hugepage_invalidate;
+	mmu_hash_ops.hpte_invalidate	= native_hpte_invalidate;
+	mmu_hash_ops.hpte_updatepp	= native_hpte_updatepp;
+	mmu_hash_ops.hpte_updateboltedpp = native_hpte_updateboltedpp;
+	mmu_hash_ops.hpte_insert	= native_hpte_insert;
+	mmu_hash_ops.hpte_remove	= native_hpte_remove;
+	mmu_hash_ops.hpte_clear_all	= native_hpte_clear;
+	mmu_hash_ops.flush_hash_range = native_flush_hash_range;
+	mmu_hash_ops.hugepage_invalidate   = native_hugepage_invalidate;
 
 	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		ppc_md.update_partition_table = native_update_partition_table;
+		ppc_md.register_process_table = native_register_proc_table;
 }
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 2971ea18c768..b78b5d211278 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -34,6 +34,7 @@
 #include <linux/signal.h>
 #include <linux/memblock.h>
 #include <linux/context_tracking.h>
+#include <linux/libfdt.h>
 
 #include <asm/processor.h>
 #include <asm/pgtable.h>
@@ -58,6 +59,7 @@
 #include <asm/firmware.h>
 #include <asm/tm.h>
 #include <asm/trace.h>
+#include <asm/ps3.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -87,10 +89,6 @@
  *
  */
 
-#ifdef CONFIG_U3_DART
-extern unsigned long dart_tablebase;
-#endif /* CONFIG_U3_DART */
-
 static unsigned long _SDR1;
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
 EXPORT_SYMBOL_GPL(mmu_psize_defs);
@@ -120,6 +118,8 @@ static u8 *linear_map_hash_slots;
 static unsigned long linear_map_hash_count;
 static DEFINE_SPINLOCK(linear_map_hash_lock);
 #endif /* CONFIG_DEBUG_PAGEALLOC */
+struct mmu_hash_ops mmu_hash_ops;
+EXPORT_SYMBOL(mmu_hash_ops);
 
 /* There are definitions of page sizes arrays to be used when none
  * is provided by the firmware.
@@ -278,9 +278,10 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		hash = hpt_hash(vpn, shift, ssize);
 		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
-		BUG_ON(!ppc_md.hpte_insert);
-		ret = ppc_md.hpte_insert(hpteg, vpn, paddr, tprot,
-					 HPTE_V_BOLTED, psize, psize, ssize);
+		BUG_ON(!mmu_hash_ops.hpte_insert);
+		ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot,
+					       HPTE_V_BOLTED, psize, psize,
+					       ssize);
 
 		if (ret < 0)
 			break;
@@ -305,11 +306,11 @@ int htab_remove_mapping(unsigned long vstart, unsigned long vend,
 	shift = mmu_psize_defs[psize].shift;
 	step = 1 << shift;
 
-	if (!ppc_md.hpte_removebolted)
+	if (!mmu_hash_ops.hpte_removebolted)
 		return -ENODEV;
 
 	for (vaddr = vstart; vaddr < vend; vaddr += step) {
-		rc = ppc_md.hpte_removebolted(vaddr, psize, ssize);
+		rc = mmu_hash_ops.hpte_removebolted(vaddr, psize, ssize);
 		if (rc == -ENOENT) {
 			ret = -ENOENT;
 			continue;
@@ -321,6 +322,15 @@ int htab_remove_mapping(unsigned long vstart, unsigned long vend,
 	return ret;
 }
 
+static bool disable_1tb_segments = false;
+
+static int __init parse_disable_1tb_segments(char *p)
+{
+	disable_1tb_segments = true;
+	return 0;
+}
+early_param("disable_1tb_segments", parse_disable_1tb_segments);
+
 static int __init htab_dt_scan_seg_sizes(unsigned long node,
 					 const char *uname, int depth,
 					 void *data)
@@ -339,6 +349,12 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node,
 	for (; size >= 4; size -= 4, ++prop) {
 		if (be32_to_cpu(prop[0]) == 40) {
 			DBG("1T segment support detected\n");
+
+			if (disable_1tb_segments) {
+				DBG("1T segments disabled by command line\n");
+				break;
+			}
+
 			cur_cpu_spec->mmu_features |= MMU_FTR_1T_SEGMENT;
 			return 1;
 		}
@@ -514,7 +530,8 @@ static bool might_have_hea(void)
 	 * we will never see an HEA ethernet device.
 	 */
 #ifdef CONFIG_IBMEBUS
-	return !cpu_has_feature(CPU_FTR_ARCH_207S);
+	return !cpu_has_feature(CPU_FTR_ARCH_207S) &&
+		!firmware_has_feature(FW_FEATURE_SPLPAR);
 #else
 	return false;
 #endif
@@ -580,7 +597,7 @@ found:
 			 * would stop us accessing the HEA ethernet. So if we
 			 * have the chance of ever seeing one, stay at 4k.
 			 */
-			if (!might_have_hea() || !machine_is(pseries))
+			if (!might_have_hea())
 				mmu_io_psize = MMU_PAGE_64K;
 		} else
 			mmu_ci_restrictions = 1;
@@ -699,10 +716,9 @@ int remove_section_mapping(unsigned long start, unsigned long end)
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static void __init hash_init_partition_table(phys_addr_t hash_table,
-					     unsigned long pteg_count)
+					     unsigned long htab_size)
 {
 	unsigned long ps_field;
-	unsigned long htab_size;
 	unsigned long patb_size = 1UL << PATB_SIZE_SHIFT;
 
 	/*
@@ -710,7 +726,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table,
 	 * We can ignore that for lpid 0
 	 */
 	ps_field = 0;
-	htab_size =  __ilog2(pteg_count) - 11;
+	htab_size =  __ilog2(htab_size) - 18;
 
 	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
 	partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
@@ -724,7 +740,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table,
 	 * For now UPRT is 0 for us.
 	 */
 	partition_tb->patb1 = 0;
-	DBG("Partition table %p\n", partition_tb);
+	pr_info("Partition table %p\n", partition_tb);
 	/*
 	 * update partition table control register,
 	 * 64 K size.
@@ -738,7 +754,7 @@ static void __init htab_initialize(void)
 	unsigned long table;
 	unsigned long pteg_count;
 	unsigned long prot;
-	unsigned long base = 0, size = 0, limit;
+	unsigned long base = 0, size = 0;
 	struct memblock_region *reg;
 
 	DBG(" -> htab_initialize()\n");
@@ -764,7 +780,8 @@ static void __init htab_initialize(void)
 
 	htab_hash_mask = pteg_count - 1;
 
-	if (firmware_has_feature(FW_FEATURE_LPAR)) {
+	if (firmware_has_feature(FW_FEATURE_LPAR) ||
+	    firmware_has_feature(FW_FEATURE_PS3_LV1)) {
 		/* Using a hypervisor which owns the htab */
 		htab_address = NULL;
 		_SDR1 = 0; 
@@ -775,20 +792,26 @@ static void __init htab_initialize(void)
 		 * Clear the htab if firmware assisted dump is active so
 		 * that we dont end up using old mappings.
 		 */
-		if (is_fadump_active() && ppc_md.hpte_clear_all)
-			ppc_md.hpte_clear_all();
+		if (is_fadump_active() && mmu_hash_ops.hpte_clear_all)
+			mmu_hash_ops.hpte_clear_all();
 #endif
 	} else {
-		/* Find storage for the HPT.  Must be contiguous in
-		 * the absolute address space. On cell we want it to be
-		 * in the first 2 Gig so we can use it for IOMMU hacks.
+		unsigned long limit = MEMBLOCK_ALLOC_ANYWHERE;
+
+#ifdef CONFIG_PPC_CELL
+		/*
+		 * Cell may require the hash table down low when using the
+		 * Axon IOMMU in order to fit the dynamic region over it, see
+		 * comments in cell/iommu.c
 		 */
-		if (machine_is(cell))
+		if (fdt_subnode_offset(initial_boot_params, 0, "axon") > 0) {
 			limit = 0x80000000;
-		else
-			limit = MEMBLOCK_ALLOC_ANYWHERE;
+			pr_info("Hash table forced below 2G for Axon IOMMU\n");
+		}
+#endif /* CONFIG_PPC_CELL */
 
-		table = memblock_alloc_base(htab_size_bytes, htab_size_bytes, limit);
+		table = memblock_alloc_base(htab_size_bytes, htab_size_bytes,
+					    limit);
 
 		DBG("Hash table allocated at %lx, size: %lx\n", table,
 		    htab_size_bytes);
@@ -796,7 +819,7 @@ static void __init htab_initialize(void)
 		htab_address = __va(table);
 
 		/* htab absolute addr + encoded htabsize */
-		_SDR1 = table + __ilog2(pteg_count) - 11;
+		_SDR1 = table + __ilog2(htab_size_bytes) - 18;
 
 		/* Initialize the HPT with no entries */
 		memset((void *)table, 0, htab_size_bytes);
@@ -805,7 +828,7 @@ static void __init htab_initialize(void)
 			/* Set SDR1 */
 			mtspr(SPRN_SDR1, _SDR1);
 		else
-			hash_init_partition_table(table, pteg_count);
+			hash_init_partition_table(table, htab_size_bytes);
 	}
 
 	prot = pgprot_val(PAGE_KERNEL);
@@ -832,34 +855,6 @@ static void __init htab_initialize(void)
 		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
 		    base, size, prot);
 
-#ifdef CONFIG_U3_DART
-		/* Do not map the DART space. Fortunately, it will be aligned
-		 * in such a way that it will not cross two memblock regions and
-		 * will fit within a single 16Mb page.
-		 * The DART space is assumed to be a full 16Mb region even if
-		 * we only use 2Mb of that space. We will use more of it later
-		 * for AGP GART. We have to use a full 16Mb large page.
-		 */
-		DBG("DART base: %lx\n", dart_tablebase);
-
-		if (dart_tablebase != 0 && dart_tablebase >= base
-		    && dart_tablebase < (base + size)) {
-			unsigned long dart_table_end = dart_tablebase + 16 * MB;
-			if (base != dart_tablebase)
-				BUG_ON(htab_bolt_mapping(base, dart_tablebase,
-							__pa(base), prot,
-							mmu_linear_psize,
-							mmu_kernel_ssize));
-			if ((base + size) > dart_table_end)
-				BUG_ON(htab_bolt_mapping(dart_tablebase+16*MB,
-							base + size,
-							__pa(dart_table_end),
-							 prot,
-							 mmu_linear_psize,
-							 mmu_kernel_ssize));
-			continue;
-		}
-#endif /* CONFIG_U3_DART */
 		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
 				prot, mmu_linear_psize, mmu_kernel_ssize));
 	}
@@ -926,12 +921,24 @@ void __init hash__early_init_mmu(void)
 	pci_io_base = ISA_IO_BASE;
 #endif
 
+	/* Select appropriate backend */
+	if (firmware_has_feature(FW_FEATURE_PS3_LV1))
+		ps3_early_mm_init();
+	else if (firmware_has_feature(FW_FEATURE_LPAR))
+		hpte_init_pseries();
+	else if (IS_ENABLED(CONFIG_PPC_NATIVE))
+		hpte_init_native();
+
+	if (!mmu_hash_ops.hpte_insert)
+		panic("hash__early_init_mmu: No MMU hash ops defined!\n");
+
 	/* Initialize the MMU Hash table and create the linear mapping
 	 * of memory. Has to be done before SLB initialization as this is
 	 * currently where the page size encoding is obtained.
 	 */
 	htab_initialize();
 
+	pr_info("Initializing hash mmu with SLB\n");
 	/* Initialize SLB management */
 	slb_initialize();
 }
@@ -1474,7 +1481,8 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
 		 * We use same base page size and actual psize, because we don't
 		 * use these functions for hugepage
 		 */
-		ppc_md.hpte_invalidate(slot, vpn, psize, psize, ssize, local);
+		mmu_hash_ops.hpte_invalidate(slot, vpn, psize, psize,
+					     ssize, local);
 	} pte_iterate_hashed_end();
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1515,9 +1523,9 @@ void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
 	if (!hpte_slot_array)
 		return;
 
-	if (ppc_md.hugepage_invalidate) {
-		ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
-					   psize, ssize, local);
+	if (mmu_hash_ops.hugepage_invalidate) {
+		mmu_hash_ops.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
+						 psize, ssize, local);
 		goto tm_abort;
 	}
 	/*
@@ -1544,8 +1552,8 @@ void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
 
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += hidx & _PTEIDX_GROUP_IX;
-		ppc_md.hpte_invalidate(slot, vpn, psize,
-				       MMU_PAGE_16M, ssize, local);
+		mmu_hash_ops.hpte_invalidate(slot, vpn, psize,
+					     MMU_PAGE_16M, ssize, local);
 	}
 tm_abort:
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1569,8 +1577,8 @@ tm_abort:
 
 void flush_hash_range(unsigned long number, int local)
 {
-	if (ppc_md.flush_hash_range)
-		ppc_md.flush_hash_range(number, local);
+	if (mmu_hash_ops.flush_hash_range)
+		mmu_hash_ops.flush_hash_range(number, local);
 	else {
 		int i;
 		struct ppc64_tlb_batch *batch =
@@ -1615,22 +1623,22 @@ repeat:
 		       HPTES_PER_GROUP) & ~0x7UL;
 
 	/* Insert into the hash table, primary slot */
-	slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, vflags,
-				  psize, psize, ssize);
+	slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, vflags,
+					psize, psize, ssize);
 
 	/* Primary is full, try the secondary */
 	if (unlikely(slot == -1)) {
 		hpte_group = ((~hash & htab_hash_mask) *
 			      HPTES_PER_GROUP) & ~0x7UL;
-		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags,
-					  vflags | HPTE_V_SECONDARY,
-					  psize, psize, ssize);
+		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags,
+						vflags | HPTE_V_SECONDARY,
+						psize, psize, ssize);
 		if (slot == -1) {
 			if (mftb() & 0x1)
 				hpte_group = ((hash & htab_hash_mask) *
 					      HPTES_PER_GROUP)&~0x7UL;
 
-			ppc_md.hpte_remove(hpte_group);
+			mmu_hash_ops.hpte_remove(hpte_group);
 			goto repeat;
 		}
 	}
@@ -1680,8 +1688,9 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
 		hash = ~hash;
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 	slot += hidx & _PTEIDX_GROUP_IX;
-	ppc_md.hpte_invalidate(slot, vpn, mmu_linear_psize, mmu_linear_psize,
-			       mmu_kernel_ssize, 0);
+	mmu_hash_ops.hpte_invalidate(slot, vpn, mmu_linear_psize,
+				     mmu_linear_psize,
+				     mmu_kernel_ssize, 0);
 }
 
 void __kernel_map_pages(struct page *page, int numpages, int enable)
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index ba3fc229468a..f20d16f849c5 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -103,8 +103,8 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += hidx & _PTEIDX_GROUP_IX;
 
-		ret = ppc_md.hpte_updatepp(slot, rflags, vpn,
-					   psize, lpsize, ssize, flags);
+		ret = mmu_hash_ops.hpte_updatepp(slot, rflags, vpn,
+						 psize, lpsize, ssize, flags);
 		/*
 		 * We failed to update, try to insert a new entry.
 		 */
@@ -131,23 +131,24 @@ repeat:
 		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 
 		/* Insert into the hash table, primary slot */
-		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
-					  psize, lpsize, ssize);
+		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+						psize, lpsize, ssize);
 		/*
 		 * Primary is full, try the secondary
 		 */
 		if (unlikely(slot == -1)) {
 			hpte_group = ((~hash & htab_hash_mask) *
 				      HPTES_PER_GROUP) & ~0x7UL;
-			slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
-						  rflags, HPTE_V_SECONDARY,
-						  psize, lpsize, ssize);
+			slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
+							rflags,
+							HPTE_V_SECONDARY,
+							psize, lpsize, ssize);
 			if (slot == -1) {
 				if (mftb() & 0x1)
 					hpte_group = ((hash & htab_hash_mask) *
 						      HPTES_PER_GROUP) & ~0x7UL;
 
-				ppc_md.hpte_remove(hpte_group);
+				mmu_hash_ops.hpte_remove(hpte_group);
 				goto repeat;
 			}
 		}
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index 3058560b6121..d5026f3800b6 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -79,8 +79,8 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
 
-		if (ppc_md.hpte_updatepp(slot, rflags, vpn, mmu_psize,
-					 mmu_psize, ssize, flags) == -1)
+		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, mmu_psize,
+					       mmu_psize, ssize, flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 119d18611500..7372ee13eb1e 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -81,6 +81,13 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	if (! new)
 		return -ENOMEM;
 
+	/*
+	 * Make sure other cpus find the hugepd set only after a
+	 * properly initialized page table is visible to them.
+	 * For more details look for comment in __pte_alloc().
+	 */
+	smp_wmb();
+
 	spin_lock(&mm->page_table_lock);
 #ifdef CONFIG_PPC_FSL_BOOK3E
 	/*
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index c899fe340bbd..448685fbf27c 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(memstart_addr);
 phys_addr_t kernstart_addr;
 EXPORT_SYMBOL(kernstart_addr);
 
-#ifdef CONFIG_RELOCATABLE_PPC32
+#ifdef CONFIG_RELOCATABLE
 /* Used in __va()/__pa() */
 long long virt_phys_offset;
 EXPORT_SYMBOL(virt_phys_offset);
@@ -80,9 +80,6 @@ EXPORT_SYMBOL(agp_special_page);
 
 void MMU_init(void);
 
-/* XXX should be in current.h  -- paulus */
-extern struct task_struct *current_set[NR_CPUS];
-
 /*
  * this tells the system to map all of ram with the segregs
  * (i.e. page tables) instead of the bats.
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 2fd57fa48429..5f844337de21 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -116,6 +116,16 @@ int memory_add_physaddr_to_nid(u64 start)
 }
 #endif
 
+int __weak create_section_mapping(unsigned long start, unsigned long end)
+{
+	return -ENODEV;
+}
+
+int __weak remove_section_mapping(unsigned long start, unsigned long end)
+{
+	return -ENODEV;
+}
+
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	struct pglist_data *pgdata;
@@ -239,8 +249,14 @@ static int __init mark_nonram_nosave(void)
 
 static bool zone_limits_final;
 
+/*
+ * The memory zones past TOP_ZONE are managed by generic mm code.
+ * These should be set to zero since that's what every other
+ * architecture does.
+ */
 static unsigned long max_zone_pfns[MAX_NR_ZONES] = {
-	[0 ... MAX_NR_ZONES - 1] = ~0UL
+	[0            ... TOP_ZONE        ] = ~0UL,
+	[TOP_ZONE + 1 ... MAX_NR_ZONES - 1] = 0
 };
 
 /*
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 196222227e82..b114f8b93ec9 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -181,7 +181,10 @@ void destroy_context(struct mm_struct *mm)
 #ifdef CONFIG_PPC_RADIX_MMU
 void radix__switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
 {
-	mtspr(SPRN_PID, next->context.id);
 	asm volatile("isync": : :"memory");
+	mtspr(SPRN_PID, next->context.id);
+	asm volatile("isync \n"
+		     PPC_SLBIA(0x7)
+		     : : :"memory");
 }
 #endif
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 6af65327c993..f988db655e5b 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -154,9 +154,10 @@ struct tlbcam {
 };
 #endif
 
-#if defined(CONFIG_6xx) || defined(CONFIG_FSL_BOOKE)
+#if defined(CONFIG_6xx) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx)
 /* 6xx have BATS */
 /* FSL_BOOKE have TLBCAM */
+/* 8xx have LTLB */
 phys_addr_t v_block_mapped(unsigned long va);
 unsigned long p_block_mapped(phys_addr_t pa);
 #else
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 6dc07ddbfd04..75b9cd6150cc 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1153,18 +1153,34 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
 
 static u64 hot_add_drconf_memory_max(void)
 {
-        struct device_node *memory = NULL;
-        unsigned int drconf_cell_cnt = 0;
-        u64 lmb_size = 0;
+	struct device_node *memory = NULL;
+	struct device_node *dn = NULL;
+	unsigned int drconf_cell_cnt = 0;
+	u64 lmb_size = 0;
 	const __be32 *dm = NULL;
+	const __be64 *lrdr = NULL;
+	struct of_drconf_cell drmem;
+
+	dn = of_find_node_by_path("/rtas");
+	if (dn) {
+		lrdr = of_get_property(dn, "ibm,lrdr-capacity", NULL);
+		of_node_put(dn);
+		if (lrdr)
+			return be64_to_cpup(lrdr);
+	}
+
+	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
+	if (memory) {
+		drconf_cell_cnt = of_get_drconf_memory(memory, &dm);
+		lmb_size = of_get_lmb_size(memory);
 
-        memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
-        if (memory) {
-                drconf_cell_cnt = of_get_drconf_memory(memory, &dm);
-                lmb_size = of_get_lmb_size(memory);
-                of_node_put(memory);
-        }
-        return lmb_size * drconf_cell_cnt;
+		/* Advance to the last cell, each cell has 6 32 bit integers */
+		dm += (drconf_cell_cnt - 1) * 6;
+		read_drconf_cell(&drmem, &dm);
+		of_node_put(memory);
+		return drmem.base_addr + lmb_size;
+	}
+	return 0;
 }
 
 /*
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 7931e1496f0d..003ff48a11b6 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -21,8 +21,11 @@
 
 #include <trace/events/thp.h>
 
-static int native_update_partition_table(u64 patb1)
+static int native_register_process_table(unsigned long base, unsigned long pg_sz,
+					 unsigned long table_size)
 {
+	unsigned long patb1 = base | table_size | PATB_GR;
+
 	partition_tb->patb1 = cpu_to_be64(patb1);
 	return 0;
 }
@@ -168,7 +171,7 @@ redo:
 	 * of process table here. But our linear mapping also enable us to use
 	 * physical address here.
 	 */
-	ppc_md.update_partition_table(__pa(process_tb) | (PRTB_SIZE_SHIFT - 12) | PATB_GR);
+	ppc_md.register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12);
 	pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd);
 }
 
@@ -182,7 +185,8 @@ static void __init radix_init_partition_table(void)
 	partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT);
 	partition_tb->patb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) |
 					  RADIX_PGD_INDEX_SIZE | PATB_HR);
-	printk("Partition table %p\n", partition_tb);
+	pr_info("Initializing Radix MMU\n");
+	pr_info("Partition table %p\n", partition_tb);
 
 	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 	/*
@@ -194,7 +198,7 @@ static void __init radix_init_partition_table(void)
 
 void __init radix_init_native(void)
 {
-	ppc_md.update_partition_table = native_update_partition_table;
+	ppc_md.register_process_table = native_register_process_table;
 }
 
 static int __init get_idx_from_shift(unsigned int shift)
@@ -341,8 +345,9 @@ void __init radix__early_init_mmu(void)
 
 	radix_init_page_sizes();
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+		radix_init_native();
 		lpcr = mfspr(SPRN_LPCR);
-		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 		radix_init_partition_table();
 	}
 
@@ -357,7 +362,7 @@ void radix__early_init_mmu_secondary(void)
 	 */
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		lpcr = mfspr(SPRN_LPCR);
-		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 
 		mtspr(SPRN_PTCR,
 		      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 7f922f557936..0ae0572bc239 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -79,7 +79,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 #endif
 }
 
-__init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
+__ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
 	pte_t *pte;
 
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index ab2f60e812e2..e1f22700fb16 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/memblock.h>
+#include <asm/ppc-opcode.h>
 
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
@@ -34,8 +35,7 @@ static inline void __tlbiel_pid(unsigned long pid, int set,
 	r = 1;   /* raidx format */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("ptesync": : :"memory");
 }
@@ -63,8 +63,7 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 	r = 1;   /* raidx format */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
@@ -81,8 +80,7 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 	r = 1;   /* raidx format */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("ptesync": : :"memory");
 }
@@ -99,8 +97,7 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 	r = 1;   /* raidx format */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
@@ -285,9 +282,61 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 }
 EXPORT_SYMBOL(radix__flush_tlb_range);
 
+static int radix_get_mmu_psize(int page_size)
+{
+	int psize;
+
+	if (page_size == (1UL << mmu_psize_defs[mmu_virtual_psize].shift))
+		psize = mmu_virtual_psize;
+	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_2M].shift))
+		psize = MMU_PAGE_2M;
+	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_1G].shift))
+		psize = MMU_PAGE_1G;
+	else
+		return -1;
+	return psize;
+}
 
 void radix__tlb_flush(struct mmu_gather *tlb)
 {
 	struct mm_struct *mm = tlb->mm;
 	radix__flush_tlb_mm(mm);
 }
+
+void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
+			      unsigned long page_size)
+{
+	unsigned long rb,rs,prs,r;
+	unsigned long ap;
+	unsigned long ric = RIC_FLUSH_TLB;
+
+	ap = mmu_get_ap(radix_get_mmu_psize(page_size));
+	rb = gpa & ~(PPC_BITMASK(52, 63));
+	rb |= ap << PPC_BITLSHIFT(58);
+	rs = lpid & ((1UL << 32) - 1);
+	prs = 0; /* process scoped */
+	r = 1;   /* raidx format */
+
+	asm volatile("ptesync": : :"memory");
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+EXPORT_SYMBOL(radix__flush_tlb_lpid_va);
+
+void radix__flush_tlb_lpid(unsigned long lpid)
+{
+	unsigned long rb,rs,prs,r;
+	unsigned long ric = RIC_FLUSH_ALL;
+
+	rb = 0x2 << PPC_BITLSHIFT(53); /* IS = 2 */
+	rs = lpid & ((1UL << 32) - 1);
+	prs = 0; /* partition scoped */
+	r = 1;   /* raidx format */
+
+	asm volatile("ptesync": : :"memory");
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+EXPORT_SYMBOL(radix__flush_tlb_lpid);
diff --git a/arch/powerpc/net/Makefile b/arch/powerpc/net/Makefile
index 1306a58ac541..c1ff16a6eb51 100644
--- a/arch/powerpc/net/Makefile
+++ b/arch/powerpc/net/Makefile
@@ -1,4 +1,8 @@
 #
 # Arch-specific network modules
 #
+ifeq ($(CONFIG_PPC64),y)
+obj-$(CONFIG_BPF_JIT) += bpf_jit_asm64.o bpf_jit_comp64.o
+else
 obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o
+endif
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 889fd199a821..d5301b6f20d0 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -1,6 +1,8 @@
-/* bpf_jit.h: BPF JIT compiler for PPC64
+/*
+ * bpf_jit.h: BPF JIT compiler for PPC
  *
  * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation
+ * 	     2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -10,67 +12,11 @@
 #ifndef _BPF_JIT_H
 #define _BPF_JIT_H
 
-#ifdef CONFIG_PPC64
-#define BPF_PPC_STACK_R3_OFF	48
-#define BPF_PPC_STACK_LOCALS	32
-#define BPF_PPC_STACK_BASIC	(48+64)
-#define BPF_PPC_STACK_SAVE	(18*8)
-#define BPF_PPC_STACKFRAME	(BPF_PPC_STACK_BASIC+BPF_PPC_STACK_LOCALS+ \
-				 BPF_PPC_STACK_SAVE)
-#define BPF_PPC_SLOWPATH_FRAME	(48+64)
-#else
-#define BPF_PPC_STACK_R3_OFF	24
-#define BPF_PPC_STACK_LOCALS	16
-#define BPF_PPC_STACK_BASIC	(24+32)
-#define BPF_PPC_STACK_SAVE	(18*4)
-#define BPF_PPC_STACKFRAME	(BPF_PPC_STACK_BASIC+BPF_PPC_STACK_LOCALS+ \
-				 BPF_PPC_STACK_SAVE)
-#define BPF_PPC_SLOWPATH_FRAME	(24+32)
-#endif
-
-#define REG_SZ         (BITS_PER_LONG/8)
-
-/*
- * Generated code register usage:
- *
- * As normal PPC C ABI (e.g. r1=sp, r2=TOC), with:
- *
- * skb		r3	(Entry parameter)
- * A register	r4
- * X register	r5
- * addr param	r6
- * r7-r10	scratch
- * skb->data	r14
- * skb headlen	r15	(skb->len - skb->data_len)
- * m[0]		r16
- * m[...]	...
- * m[15]	r31
- */
-#define r_skb		3
-#define r_ret		3
-#define r_A		4
-#define r_X		5
-#define r_addr		6
-#define r_scratch1	7
-#define r_scratch2	8
-#define r_D		14
-#define r_HL		15
-#define r_M		16
-
 #ifndef __ASSEMBLY__
 
-/*
- * Assembly helpers from arch/powerpc/net/bpf_jit.S:
- */
-#define DECLARE_LOAD_FUNC(func)	\
-	extern u8 func[], func##_negative_offset[], func##_positive_offset[]
-
-DECLARE_LOAD_FUNC(sk_load_word);
-DECLARE_LOAD_FUNC(sk_load_half);
-DECLARE_LOAD_FUNC(sk_load_byte);
-DECLARE_LOAD_FUNC(sk_load_byte_msh);
+#include <asm/types.h>
 
-#ifdef CONFIG_PPC64
+#ifdef PPC64_ELF_ABI_v1
 #define FUNCTION_DESCR_SIZE	24
 #else
 #define FUNCTION_DESCR_SIZE	0
@@ -83,7 +29,7 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
  */
 #define IMM_H(i)		((uintptr_t)(i)>>16)
 #define IMM_HA(i)		(((uintptr_t)(i)>>16) +			      \
-				 (((uintptr_t)(i) & 0x8000) >> 15))
+					(((uintptr_t)(i) & 0x8000) >> 15))
 #define IMM_L(i)		((uintptr_t)(i) & 0xffff)
 
 #define PLANT_INSTR(d, idx, instr)					      \
@@ -99,16 +45,20 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 #define PPC_MR(d, a)		PPC_OR(d, a, a)
 #define PPC_LI(r, i)		PPC_ADDI(r, 0, i)
 #define PPC_ADDIS(d, a, i)	EMIT(PPC_INST_ADDIS |			      \
-				     ___PPC_RS(d) | ___PPC_RA(a) | IMM_L(i))
+				     ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i))
 #define PPC_LIS(r, i)		PPC_ADDIS(r, 0, i)
 #define PPC_STD(r, base, i)	EMIT(PPC_INST_STD | ___PPC_RS(r) |	      \
 				     ___PPC_RA(base) | ((i) & 0xfffc))
 #define PPC_STDU(r, base, i)	EMIT(PPC_INST_STDU | ___PPC_RS(r) |	      \
 				     ___PPC_RA(base) | ((i) & 0xfffc))
 #define PPC_STW(r, base, i)	EMIT(PPC_INST_STW | ___PPC_RS(r) |	      \
-				     ___PPC_RA(base) | ((i) & 0xfffc))
+				     ___PPC_RA(base) | IMM_L(i))
 #define PPC_STWU(r, base, i)	EMIT(PPC_INST_STWU | ___PPC_RS(r) |	      \
-				     ___PPC_RA(base) | ((i) & 0xfffc))
+				     ___PPC_RA(base) | IMM_L(i))
+#define PPC_STH(r, base, i)	EMIT(PPC_INST_STH | ___PPC_RS(r) |	      \
+				     ___PPC_RA(base) | IMM_L(i))
+#define PPC_STB(r, base, i)	EMIT(PPC_INST_STB | ___PPC_RS(r) |	      \
+				     ___PPC_RA(base) | IMM_L(i))
 
 #define PPC_LBZ(r, base, i)	EMIT(PPC_INST_LBZ | ___PPC_RT(r) |	      \
 				     ___PPC_RA(base) | IMM_L(i))
@@ -120,6 +70,19 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 				     ___PPC_RA(base) | IMM_L(i))
 #define PPC_LHBRX(r, base, b)	EMIT(PPC_INST_LHBRX | ___PPC_RT(r) |	      \
 				     ___PPC_RA(base) | ___PPC_RB(b))
+#define PPC_LDBRX(r, base, b)	EMIT(PPC_INST_LDBRX | ___PPC_RT(r) |	      \
+				     ___PPC_RA(base) | ___PPC_RB(b))
+
+#define PPC_BPF_LDARX(t, a, b, eh) EMIT(PPC_INST_LDARX | ___PPC_RT(t) |	      \
+					___PPC_RA(a) | ___PPC_RB(b) |	      \
+					__PPC_EH(eh))
+#define PPC_BPF_LWARX(t, a, b, eh) EMIT(PPC_INST_LWARX | ___PPC_RT(t) |	      \
+					___PPC_RA(a) | ___PPC_RB(b) |	      \
+					__PPC_EH(eh))
+#define PPC_BPF_STWCX(s, a, b)	EMIT(PPC_INST_STWCX | ___PPC_RS(s) |	      \
+					___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_BPF_STDCX(s, a, b)	EMIT(PPC_INST_STDCX | ___PPC_RS(s) |	      \
+					___PPC_RA(a) | ___PPC_RB(b))
 
 #ifdef CONFIG_PPC64
 #define PPC_BPF_LL(r, base, i) do { PPC_LD(r, base, i); } while(0)
@@ -131,56 +94,26 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 #define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0)
 #endif
 
-/* Convenience helpers for the above with 'far' offsets: */
-#define PPC_LBZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LBZ(r, base, i);   \
-		else {	PPC_ADDIS(r, base, IMM_HA(i));			      \
-			PPC_LBZ(r, r, IMM_L(i)); } } while(0)
-
-#define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i);     \
-		else {	PPC_ADDIS(r, base, IMM_HA(i));			      \
-			PPC_LD(r, r, IMM_L(i)); } } while(0)
-
-#define PPC_LWZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LWZ(r, base, i);   \
-		else {	PPC_ADDIS(r, base, IMM_HA(i));			      \
-			PPC_LWZ(r, r, IMM_L(i)); } } while(0)
-
-#define PPC_LHZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LHZ(r, base, i);   \
-		else {	PPC_ADDIS(r, base, IMM_HA(i));			      \
-			PPC_LHZ(r, r, IMM_L(i)); } } while(0)
-
-#ifdef CONFIG_PPC64
-#define PPC_LL_OFFS(r, base, i) do { PPC_LD_OFFS(r, base, i); } while(0)
-#else
-#define PPC_LL_OFFS(r, base, i) do { PPC_LWZ_OFFS(r, base, i); } while(0)
-#endif
-
-#ifdef CONFIG_SMP
-#ifdef CONFIG_PPC64
-#define PPC_BPF_LOAD_CPU(r)		\
-	do { BUILD_BUG_ON(FIELD_SIZEOF(struct paca_struct, paca_index) != 2);	\
-		PPC_LHZ_OFFS(r, 13, offsetof(struct paca_struct, paca_index));		\
-	} while (0)
-#else
-#define PPC_BPF_LOAD_CPU(r)     \
-	do { BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4);			\
-		PPC_LHZ_OFFS(r, (1 & ~(THREAD_SIZE - 1)),							\
-				offsetof(struct thread_info, cpu));							\
-	} while(0)
-#endif
-#else
-#define PPC_BPF_LOAD_CPU(r) do { PPC_LI(r, 0); } while(0)
-#endif
-
 #define PPC_CMPWI(a, i)		EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i))
 #define PPC_CMPDI(a, i)		EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i))
+#define PPC_CMPW(a, b)		EMIT(PPC_INST_CMPW | ___PPC_RA(a) |	      \
+					___PPC_RB(b))
+#define PPC_CMPD(a, b)		EMIT(PPC_INST_CMPD | ___PPC_RA(a) |	      \
+					___PPC_RB(b))
 #define PPC_CMPLWI(a, i)	EMIT(PPC_INST_CMPLWI | ___PPC_RA(a) | IMM_L(i))
-#define PPC_CMPLW(a, b)		EMIT(PPC_INST_CMPLW | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_CMPLDI(a, i)	EMIT(PPC_INST_CMPLDI | ___PPC_RA(a) | IMM_L(i))
+#define PPC_CMPLW(a, b)		EMIT(PPC_INST_CMPLW | ___PPC_RA(a) |	      \
+					___PPC_RB(b))
+#define PPC_CMPLD(a, b)		EMIT(PPC_INST_CMPLD | ___PPC_RA(a) |	      \
+					___PPC_RB(b))
 
 #define PPC_SUB(d, a, b)	EMIT(PPC_INST_SUB | ___PPC_RT(d) |	      \
 				     ___PPC_RB(a) | ___PPC_RA(b))
 #define PPC_ADD(d, a, b)	EMIT(PPC_INST_ADD | ___PPC_RT(d) |	      \
 				     ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_MUL(d, a, b)	EMIT(PPC_INST_MULLW | ___PPC_RT(d) |	      \
+#define PPC_MULD(d, a, b)	EMIT(PPC_INST_MULLD | ___PPC_RT(d) |	      \
+				     ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_MULW(d, a, b)	EMIT(PPC_INST_MULLW | ___PPC_RT(d) |	      \
 				     ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_MULHWU(d, a, b)	EMIT(PPC_INST_MULHWU | ___PPC_RT(d) |	      \
 				     ___PPC_RA(a) | ___PPC_RB(b))
@@ -188,6 +121,8 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 				     ___PPC_RA(a) | IMM_L(i))
 #define PPC_DIVWU(d, a, b)	EMIT(PPC_INST_DIVWU | ___PPC_RT(d) |	      \
 				     ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_DIVD(d, a, b)	EMIT(PPC_INST_DIVD | ___PPC_RT(d) |	      \
+				     ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_AND(d, a, b)	EMIT(PPC_INST_AND | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(b))
 #define PPC_ANDI(d, a, i)	EMIT(PPC_INST_ANDI | ___PPC_RA(d) |	      \
@@ -196,6 +131,7 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 				     ___PPC_RS(a) | ___PPC_RB(b))
 #define PPC_OR(d, a, b)		EMIT(PPC_INST_OR | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(b))
+#define PPC_MR(d, a)		PPC_OR(d, a, a)
 #define PPC_ORI(d, a, i)	EMIT(PPC_INST_ORI | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | IMM_L(i))
 #define PPC_ORIS(d, a, i)	EMIT(PPC_INST_ORIS | ___PPC_RA(d) |	      \
@@ -206,22 +142,43 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 				     ___PPC_RS(a) | IMM_L(i))
 #define PPC_XORIS(d, a, i)	EMIT(PPC_INST_XORIS | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | IMM_L(i))
+#define PPC_EXTSW(d, a)		EMIT(PPC_INST_EXTSW | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a))
 #define PPC_SLW(d, a, s)	EMIT(PPC_INST_SLW | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SLD(d, a, s)	EMIT(PPC_INST_SLD | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(s))
 #define PPC_SRW(d, a, s)	EMIT(PPC_INST_SRW | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SRD(d, a, s)	EMIT(PPC_INST_SRD | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SRAD(d, a, s)	EMIT(PPC_INST_SRAD | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SRADI(d, a, i)	EMIT(PPC_INST_SRADI | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | __PPC_SH(i) |             \
+				     (((i) & 0x20) >> 4))
+#define PPC_RLWINM(d, a, i, mb, me)	EMIT(PPC_INST_RLWINM | ___PPC_RA(d) | \
+					___PPC_RS(a) | __PPC_SH(i) |	      \
+					__PPC_MB(mb) | __PPC_ME(me))
+#define PPC_RLWIMI(d, a, i, mb, me)	EMIT(PPC_INST_RLWIMI | ___PPC_RA(d) | \
+					___PPC_RS(a) | __PPC_SH(i) |	      \
+					__PPC_MB(mb) | __PPC_ME(me))
+#define PPC_RLDICL(d, a, i, mb)		EMIT(PPC_INST_RLDICL | ___PPC_RA(d) | \
+					___PPC_RS(a) | __PPC_SH(i) |	      \
+					__PPC_MB64(mb) | (((i) & 0x20) >> 4))
+#define PPC_RLDICR(d, a, i, me)		EMIT(PPC_INST_RLDICR | ___PPC_RA(d) | \
+					___PPC_RS(a) | __PPC_SH(i) |	      \
+					__PPC_ME64(me) | (((i) & 0x20) >> 4))
+
 /* slwi = rlwinm Rx, Ry, n, 0, 31-n */
-#define PPC_SLWI(d, a, i)	EMIT(PPC_INST_RLWINM | ___PPC_RA(d) |	      \
-				     ___PPC_RS(a) | __PPC_SH(i) |	      \
-				     __PPC_MB(0) | __PPC_ME(31-(i)))
+#define PPC_SLWI(d, a, i)	PPC_RLWINM(d, a, i, 0, 31-(i))
 /* srwi = rlwinm Rx, Ry, 32-n, n, 31 */
-#define PPC_SRWI(d, a, i)	EMIT(PPC_INST_RLWINM | ___PPC_RA(d) |	      \
-				     ___PPC_RS(a) | __PPC_SH(32-(i)) |	      \
-				     __PPC_MB(i) | __PPC_ME(31))
+#define PPC_SRWI(d, a, i)	PPC_RLWINM(d, a, 32-(i), i, 31)
 /* sldi = rldicr Rx, Ry, n, 63-n */
-#define PPC_SLDI(d, a, i)	EMIT(PPC_INST_RLDICR | ___PPC_RA(d) |	      \
-				     ___PPC_RS(a) | __PPC_SH(i) |	      \
-				     __PPC_MB(63-(i)) | (((i) & 0x20) >> 4))
+#define PPC_SLDI(d, a, i)	PPC_RLDICR(d, a, i, 63-(i))
+/* sldi = rldicl Rx, Ry, 64-n, n */
+#define PPC_SRDI(d, a, i)	PPC_RLDICL(d, a, 64-(i), i)
+
 #define PPC_NEG(d, a)		EMIT(PPC_INST_NEG | ___PPC_RT(d) | ___PPC_RA(a))
 
 /* Long jump; (unconditional 'branch') */
@@ -232,25 +189,37 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 					     (((cond) & 0x3ff) << 16) |	      \
 					     (((dest) - (ctx->idx * 4)) &     \
 					      0xfffc))
-#define PPC_LI32(d, i)		do { PPC_LI(d, IMM_L(i));		      \
-		if ((u32)(uintptr_t)(i) >= 32768) {			      \
-			PPC_ADDIS(d, d, IMM_HA(i));			      \
+/* Sign-extended 32-bit immediate load */
+#define PPC_LI32(d, i)		do {					      \
+		if ((int)(uintptr_t)(i) >= -32768 &&			      \
+				(int)(uintptr_t)(i) < 32768)		      \
+			PPC_LI(d, i);					      \
+		else {							      \
+			PPC_LIS(d, IMM_H(i));				      \
+			if (IMM_L(i))					      \
+				PPC_ORI(d, d, IMM_L(i));		      \
 		} } while(0)
+
 #define PPC_LI64(d, i)		do {					      \
-		if (!((uintptr_t)(i) & 0xffffffff00000000ULL))		      \
+		if ((long)(i) >= -2147483648 &&				      \
+				(long)(i) < 2147483648)			      \
 			PPC_LI32(d, i);					      \
 		else {							      \
-			PPC_LIS(d, ((uintptr_t)(i) >> 48));		      \
-			if ((uintptr_t)(i) & 0x0000ffff00000000ULL)	      \
-				PPC_ORI(d, d,				      \
-					((uintptr_t)(i) >> 32) & 0xffff);     \
+			if (!((uintptr_t)(i) & 0xffff800000000000ULL))	      \
+				PPC_LI(d, ((uintptr_t)(i) >> 32) & 0xffff);   \
+			else {						      \
+				PPC_LIS(d, ((uintptr_t)(i) >> 48));	      \
+				if ((uintptr_t)(i) & 0x0000ffff00000000ULL)   \
+					PPC_ORI(d, d,			      \
+					  ((uintptr_t)(i) >> 32) & 0xffff);   \
+			}						      \
 			PPC_SLDI(d, d, 32);				      \
 			if ((uintptr_t)(i) & 0x00000000ffff0000ULL)	      \
 				PPC_ORIS(d, d,				      \
 					 ((uintptr_t)(i) >> 16) & 0xffff);    \
 			if ((uintptr_t)(i) & 0x000000000000ffffULL)	      \
 				PPC_ORI(d, d, (uintptr_t)(i) & 0xffff);	      \
-		} } while (0);
+		} } while (0)
 
 #ifdef CONFIG_PPC64
 #define PPC_FUNC_ADDR(d,i) do { PPC_LI64(d, i); } while(0)
@@ -258,14 +227,6 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 #define PPC_FUNC_ADDR(d,i) do { PPC_LI32(d, i); } while(0)
 #endif
 
-#define PPC_LHBRX_OFFS(r, base, i) \
-		do { PPC_LI32(r, i); PPC_LHBRX(r, r, base); } while(0)
-#ifdef __LITTLE_ENDIAN__
-#define PPC_NTOHS_OFFS(r, base, i)	PPC_LHBRX_OFFS(r, base, i)
-#else
-#define PPC_NTOHS_OFFS(r, base, i)	PPC_LHZ_OFFS(r, base, i)
-#endif
-
 static inline bool is_nearbranch(int offset)
 {
 	return (offset < 32768) && (offset >= -32768);
@@ -302,18 +263,6 @@ static inline bool is_nearbranch(int offset)
 #define COND_NE		(CR0_EQ | COND_CMP_FALSE)
 #define COND_LT		(CR0_LT | COND_CMP_TRUE)
 
-#define SEEN_DATAREF 0x10000 /* might call external helpers */
-#define SEEN_XREG    0x20000 /* X reg is used */
-#define SEEN_MEM     0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary
-			      * storage */
-#define SEEN_MEM_MSK 0x0ffff
-
-struct codegen_context {
-	unsigned int seen;
-	unsigned int idx;
-	int pc_ret0; /* bpf index of first RET #0 instruction (if any) */
-};
-
 #endif
 
 #endif
diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h
new file mode 100644
index 000000000000..a8cd7e289ecd
--- /dev/null
+++ b/arch/powerpc/net/bpf_jit32.h
@@ -0,0 +1,139 @@
+/*
+ * bpf_jit32.h: BPF JIT compiler for PPC
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation
+ *
+ * Split from bpf_jit.h
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#ifndef _BPF_JIT32_H
+#define _BPF_JIT32_H
+
+#include "bpf_jit.h"
+
+#ifdef CONFIG_PPC64
+#define BPF_PPC_STACK_R3_OFF	48
+#define BPF_PPC_STACK_LOCALS	32
+#define BPF_PPC_STACK_BASIC	(48+64)
+#define BPF_PPC_STACK_SAVE	(18*8)
+#define BPF_PPC_STACKFRAME	(BPF_PPC_STACK_BASIC+BPF_PPC_STACK_LOCALS+ \
+				 BPF_PPC_STACK_SAVE)
+#define BPF_PPC_SLOWPATH_FRAME	(48+64)
+#else
+#define BPF_PPC_STACK_R3_OFF	24
+#define BPF_PPC_STACK_LOCALS	16
+#define BPF_PPC_STACK_BASIC	(24+32)
+#define BPF_PPC_STACK_SAVE	(18*4)
+#define BPF_PPC_STACKFRAME	(BPF_PPC_STACK_BASIC+BPF_PPC_STACK_LOCALS+ \
+				 BPF_PPC_STACK_SAVE)
+#define BPF_PPC_SLOWPATH_FRAME	(24+32)
+#endif
+
+#define REG_SZ         (BITS_PER_LONG/8)
+
+/*
+ * Generated code register usage:
+ *
+ * As normal PPC C ABI (e.g. r1=sp, r2=TOC), with:
+ *
+ * skb		r3	(Entry parameter)
+ * A register	r4
+ * X register	r5
+ * addr param	r6
+ * r7-r10	scratch
+ * skb->data	r14
+ * skb headlen	r15	(skb->len - skb->data_len)
+ * m[0]		r16
+ * m[...]	...
+ * m[15]	r31
+ */
+#define r_skb		3
+#define r_ret		3
+#define r_A		4
+#define r_X		5
+#define r_addr		6
+#define r_scratch1	7
+#define r_scratch2	8
+#define r_D		14
+#define r_HL		15
+#define r_M		16
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Assembly helpers from arch/powerpc/net/bpf_jit.S:
+ */
+#define DECLARE_LOAD_FUNC(func)	\
+	extern u8 func[], func##_negative_offset[], func##_positive_offset[]
+
+DECLARE_LOAD_FUNC(sk_load_word);
+DECLARE_LOAD_FUNC(sk_load_half);
+DECLARE_LOAD_FUNC(sk_load_byte);
+DECLARE_LOAD_FUNC(sk_load_byte_msh);
+
+#define PPC_LBZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LBZ(r, base, i);   \
+		else {	PPC_ADDIS(r, base, IMM_HA(i));			      \
+			PPC_LBZ(r, r, IMM_L(i)); } } while(0)
+
+#define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i);     \
+		else {	PPC_ADDIS(r, base, IMM_HA(i));			      \
+			PPC_LD(r, r, IMM_L(i)); } } while(0)
+
+#define PPC_LWZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LWZ(r, base, i);   \
+		else {	PPC_ADDIS(r, base, IMM_HA(i));			      \
+			PPC_LWZ(r, r, IMM_L(i)); } } while(0)
+
+#define PPC_LHZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LHZ(r, base, i);   \
+		else {	PPC_ADDIS(r, base, IMM_HA(i));			      \
+			PPC_LHZ(r, r, IMM_L(i)); } } while(0)
+
+#ifdef CONFIG_PPC64
+#define PPC_LL_OFFS(r, base, i) do { PPC_LD_OFFS(r, base, i); } while(0)
+#else
+#define PPC_LL_OFFS(r, base, i) do { PPC_LWZ_OFFS(r, base, i); } while(0)
+#endif
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_PPC64
+#define PPC_BPF_LOAD_CPU(r)		\
+	do { BUILD_BUG_ON(FIELD_SIZEOF(struct paca_struct, paca_index) != 2);	\
+		PPC_LHZ_OFFS(r, 13, offsetof(struct paca_struct, paca_index));	\
+	} while (0)
+#else
+#define PPC_BPF_LOAD_CPU(r)     \
+	do { BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4);		\
+		PPC_LHZ_OFFS(r, (1 & ~(THREAD_SIZE - 1)),			\
+				offsetof(struct thread_info, cpu));		\
+	} while(0)
+#endif
+#else
+#define PPC_BPF_LOAD_CPU(r) do { PPC_LI(r, 0); } while(0)
+#endif
+
+#define PPC_LHBRX_OFFS(r, base, i) \
+		do { PPC_LI32(r, i); PPC_LHBRX(r, r, base); } while(0)
+#ifdef __LITTLE_ENDIAN__
+#define PPC_NTOHS_OFFS(r, base, i)	PPC_LHBRX_OFFS(r, base, i)
+#else
+#define PPC_NTOHS_OFFS(r, base, i)	PPC_LHZ_OFFS(r, base, i)
+#endif
+
+#define SEEN_DATAREF 0x10000 /* might call external helpers */
+#define SEEN_XREG    0x20000 /* X reg is used */
+#define SEEN_MEM     0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary
+			      * storage */
+#define SEEN_MEM_MSK 0x0ffff
+
+struct codegen_context {
+	unsigned int seen;
+	unsigned int idx;
+	int pc_ret0; /* bpf index of first RET #0 instruction (if any) */
+};
+
+#endif
+
+#endif
diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
new file mode 100644
index 000000000000..5046d6f65c02
--- /dev/null
+++ b/arch/powerpc/net/bpf_jit64.h
@@ -0,0 +1,102 @@
+/*
+ * bpf_jit64.h: BPF JIT compiler for PPC64
+ *
+ * Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
+ *		  IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#ifndef _BPF_JIT64_H
+#define _BPF_JIT64_H
+
+#include "bpf_jit.h"
+
+/*
+ * Stack layout:
+ *
+ *		[	prev sp		] <-------------
+ *		[   nv gpr save area	] 8*8		|
+ * fp (r31) -->	[   ebpf stack space	] 512		|
+ *		[  local/tmp var space	] 16		|
+ *		[     frame header	] 32/112	|
+ * sp (r1) --->	[    stack pointer	] --------------
+ */
+
+/* for bpf JIT code internal usage */
+#define BPF_PPC_STACK_LOCALS	16
+/* for gpr non volatile registers BPG_REG_6 to 10, plus skb cache registers */
+#define BPF_PPC_STACK_SAVE	(8*8)
+/* Ensure this is quadword aligned */
+#define BPF_PPC_STACKFRAME	(STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS + \
+				 MAX_BPF_STACK + BPF_PPC_STACK_SAVE)
+
+#ifndef __ASSEMBLY__
+
+/* BPF register usage */
+#define SKB_HLEN_REG	(MAX_BPF_REG + 0)
+#define SKB_DATA_REG	(MAX_BPF_REG + 1)
+#define TMP_REG_1	(MAX_BPF_REG + 2)
+#define TMP_REG_2	(MAX_BPF_REG + 3)
+
+/* BPF to ppc register mappings */
+static const int b2p[] = {
+	/* function return value */
+	[BPF_REG_0] = 8,
+	/* function arguments */
+	[BPF_REG_1] = 3,
+	[BPF_REG_2] = 4,
+	[BPF_REG_3] = 5,
+	[BPF_REG_4] = 6,
+	[BPF_REG_5] = 7,
+	/* non volatile registers */
+	[BPF_REG_6] = 27,
+	[BPF_REG_7] = 28,
+	[BPF_REG_8] = 29,
+	[BPF_REG_9] = 30,
+	/* frame pointer aka BPF_REG_10 */
+	[BPF_REG_FP] = 31,
+	/* eBPF jit internal registers */
+	[SKB_HLEN_REG] = 25,
+	[SKB_DATA_REG] = 26,
+	[TMP_REG_1] = 9,
+	[TMP_REG_2] = 10
+};
+
+/* Assembly helpers */
+#define DECLARE_LOAD_FUNC(func)	u64 func(u64 r3, u64 r4);			\
+				u64 func##_negative_offset(u64 r3, u64 r4);	\
+				u64 func##_positive_offset(u64 r3, u64 r4);
+
+DECLARE_LOAD_FUNC(sk_load_word);
+DECLARE_LOAD_FUNC(sk_load_half);
+DECLARE_LOAD_FUNC(sk_load_byte);
+
+#define CHOOSE_LOAD_FUNC(imm, func)						\
+			(imm < 0 ?						\
+			(imm >= SKF_LL_OFF ? func##_negative_offset : func) :	\
+			func##_positive_offset)
+
+#define SEEN_FUNC	0x1000 /* might call external helpers */
+#define SEEN_STACK	0x2000 /* uses BPF stack */
+#define SEEN_SKB	0x4000 /* uses sk_buff */
+
+struct codegen_context {
+	/*
+	 * This is used to track register usage as well
+	 * as calls to external helpers.
+	 * - register usage is tracked with corresponding
+	 *   bits (r3-r10 and r25-r31)
+	 * - rest of the bits can be used to track other
+	 *   things -- for now, we use bits 16 to 23
+	 *   encoded in SEEN_* macros above
+	 */
+	unsigned int seen;
+	unsigned int idx;
+};
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff --git a/arch/powerpc/net/bpf_jit_asm.S b/arch/powerpc/net/bpf_jit_asm.S
index 8ff5a3b5d1c3..3dd9c43d40c9 100644
--- a/arch/powerpc/net/bpf_jit_asm.S
+++ b/arch/powerpc/net/bpf_jit_asm.S
@@ -10,7 +10,7 @@
  */
 
 #include <asm/ppc_asm.h>
-#include "bpf_jit.h"
+#include "bpf_jit32.h"
 
 /*
  * All of these routines are called directly from generated code,
diff --git a/arch/powerpc/net/bpf_jit_asm64.S b/arch/powerpc/net/bpf_jit_asm64.S
new file mode 100644
index 000000000000..7e4c51430b84
--- /dev/null
+++ b/arch/powerpc/net/bpf_jit_asm64.S
@@ -0,0 +1,180 @@
+/*
+ * bpf_jit_asm64.S: Packet/header access helper functions
+ * for PPC64 BPF compiler.
+ *
+ * Copyright 2016, Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
+ * 		   IBM Corporation
+ *
+ * Based on bpf_jit_asm.S by Matt Evans
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/ptrace.h>
+#include "bpf_jit64.h"
+
+/*
+ * All of these routines are called directly from generated code,
+ * with the below register usage:
+ * r27		skb pointer (ctx)
+ * r25		skb header length
+ * r26		skb->data pointer
+ * r4		offset
+ *
+ * Result is passed back in:
+ * r8		data read in host endian format (accumulator)
+ *
+ * r9 is used as a temporary register
+ */
+
+#define r_skb	r27
+#define r_hlen	r25
+#define r_data	r26
+#define r_off	r4
+#define r_val	r8
+#define r_tmp	r9
+
+_GLOBAL_TOC(sk_load_word)
+	cmpdi	r_off, 0
+	blt	bpf_slow_path_word_neg
+	b	sk_load_word_positive_offset
+
+_GLOBAL_TOC(sk_load_word_positive_offset)
+	/* Are we accessing past headlen? */
+	subi	r_tmp, r_hlen, 4
+	cmpd	r_tmp, r_off
+	blt	bpf_slow_path_word
+	/* Nope, just hitting the header.  cr0 here is eq or gt! */
+	LWZX_BE	r_val, r_data, r_off
+	blr	/* Return success, cr0 != LT */
+
+_GLOBAL_TOC(sk_load_half)
+	cmpdi	r_off, 0
+	blt	bpf_slow_path_half_neg
+	b	sk_load_half_positive_offset
+
+_GLOBAL_TOC(sk_load_half_positive_offset)
+	subi	r_tmp, r_hlen, 2
+	cmpd	r_tmp, r_off
+	blt	bpf_slow_path_half
+	LHZX_BE	r_val, r_data, r_off
+	blr
+
+_GLOBAL_TOC(sk_load_byte)
+	cmpdi	r_off, 0
+	blt	bpf_slow_path_byte_neg
+	b	sk_load_byte_positive_offset
+
+_GLOBAL_TOC(sk_load_byte_positive_offset)
+	cmpd	r_hlen, r_off
+	ble	bpf_slow_path_byte
+	lbzx	r_val, r_data, r_off
+	blr
+
+/*
+ * Call out to skb_copy_bits:
+ * Allocate a new stack frame here to remain ABI-compliant in
+ * stashing LR.
+ */
+#define bpf_slow_path_common(SIZE)					\
+	mflr	r0;							\
+	std	r0, PPC_LR_STKOFF(r1);					\
+	stdu	r1, -(STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS)(r1);	\
+	mr	r3, r_skb;						\
+	/* r4 = r_off as passed */					\
+	addi	r5, r1, STACK_FRAME_MIN_SIZE;				\
+	li	r6, SIZE;						\
+	bl	skb_copy_bits;						\
+	nop;								\
+	/* save r5 */							\
+	addi	r5, r1, STACK_FRAME_MIN_SIZE;				\
+	/* r3 = 0 on success */						\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS;	\
+	ld	r0, PPC_LR_STKOFF(r1);					\
+	mtlr	r0;							\
+	cmpdi	r3, 0;							\
+	blt	bpf_error;	/* cr0 = LT */
+
+bpf_slow_path_word:
+	bpf_slow_path_common(4)
+	/* Data value is on stack, and cr0 != LT */
+	LWZX_BE	r_val, 0, r5
+	blr
+
+bpf_slow_path_half:
+	bpf_slow_path_common(2)
+	LHZX_BE	r_val, 0, r5
+	blr
+
+bpf_slow_path_byte:
+	bpf_slow_path_common(1)
+	lbzx	r_val, 0, r5
+	blr
+
+/*
+ * Call out to bpf_internal_load_pointer_neg_helper
+ */
+#define sk_negative_common(SIZE)				\
+	mflr	r0;						\
+	std	r0, PPC_LR_STKOFF(r1);				\
+	stdu	r1, -STACK_FRAME_MIN_SIZE(r1);			\
+	mr	r3, r_skb;					\
+	/* r4 = r_off, as passed */				\
+	li	r5, SIZE;					\
+	bl	bpf_internal_load_pointer_neg_helper;		\
+	nop;							\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE;			\
+	ld	r0, PPC_LR_STKOFF(r1);				\
+	mtlr	r0;						\
+	/* R3 != 0 on success */				\
+	cmpldi	r3, 0;						\
+	beq	bpf_error_slow;	/* cr0 = EQ */
+
+bpf_slow_path_word_neg:
+	lis     r_tmp, -32	/* SKF_LL_OFF */
+	cmpd	r_off, r_tmp	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	b	sk_load_word_negative_offset
+
+_GLOBAL_TOC(sk_load_word_negative_offset)
+	sk_negative_common(4)
+	LWZX_BE	r_val, 0, r3
+	blr
+
+bpf_slow_path_half_neg:
+	lis     r_tmp, -32	/* SKF_LL_OFF */
+	cmpd	r_off, r_tmp	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	b	sk_load_half_negative_offset
+
+_GLOBAL_TOC(sk_load_half_negative_offset)
+	sk_negative_common(2)
+	LHZX_BE	r_val, 0, r3
+	blr
+
+bpf_slow_path_byte_neg:
+	lis     r_tmp, -32	/* SKF_LL_OFF */
+	cmpd	r_off, r_tmp	/* addr < SKF_* */
+	blt	bpf_error	/* cr0 = LT */
+	b	sk_load_byte_negative_offset
+
+_GLOBAL_TOC(sk_load_byte_negative_offset)
+	sk_negative_common(1)
+	lbzx	r_val, 0, r3
+	blr
+
+bpf_error_slow:
+	/* fabricate a cr0 = lt */
+	li	r_tmp, -1
+	cmpdi	r_tmp, 0
+bpf_error:
+	/*
+	 * Entered with cr0 = lt
+	 * Generated code will 'blt epilogue', returning 0.
+	 */
+	li	r_val, 0
+	blr
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 2d66a8446198..7e706f36e364 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -16,7 +16,7 @@
 #include <linux/filter.h>
 #include <linux/if_vlan.h>
 
-#include "bpf_jit.h"
+#include "bpf_jit32.h"
 
 int bpf_jit_enable __read_mostly;
 
@@ -161,14 +161,14 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			break;
 		case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */
 			ctx->seen |= SEEN_XREG;
-			PPC_MUL(r_A, r_A, r_X);
+			PPC_MULW(r_A, r_A, r_X);
 			break;
 		case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */
 			if (K < 32768)
 				PPC_MULI(r_A, r_A, K);
 			else {
 				PPC_LI32(r_scratch1, K);
-				PPC_MUL(r_A, r_A, r_scratch1);
+				PPC_MULW(r_A, r_A, r_scratch1);
 			}
 			break;
 		case BPF_ALU | BPF_MOD | BPF_X: /* A %= X; */
@@ -184,7 +184,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			}
 			if (code == (BPF_ALU | BPF_MOD | BPF_X)) {
 				PPC_DIVWU(r_scratch1, r_A, r_X);
-				PPC_MUL(r_scratch1, r_X, r_scratch1);
+				PPC_MULW(r_scratch1, r_X, r_scratch1);
 				PPC_SUB(r_A, r_A, r_scratch1);
 			} else {
 				PPC_DIVWU(r_A, r_A, r_X);
@@ -193,7 +193,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_ALU | BPF_MOD | BPF_K: /* A %= K; */
 			PPC_LI32(r_scratch2, K);
 			PPC_DIVWU(r_scratch1, r_A, r_scratch2);
-			PPC_MUL(r_scratch1, r_scratch2, r_scratch1);
+			PPC_MULW(r_scratch1, r_scratch2, r_scratch1);
 			PPC_SUB(r_A, r_A, r_scratch1);
 			break;
 		case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
new file mode 100644
index 000000000000..6073b78516f6
--- /dev/null
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -0,0 +1,954 @@
+/*
+ * bpf_jit_comp64.c: eBPF JIT compiler
+ *
+ * Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
+ *		  IBM Corporation
+ *
+ * Based on the powerpc classic BPF JIT compiler by Matt Evans
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#include <linux/moduleloader.h>
+#include <asm/cacheflush.h>
+#include <linux/netdevice.h>
+#include <linux/filter.h>
+#include <linux/if_vlan.h>
+#include <asm/kprobes.h>
+
+#include "bpf_jit64.h"
+
+int bpf_jit_enable __read_mostly;
+
+static void bpf_jit_fill_ill_insns(void *area, unsigned int size)
+{
+	int *p = area;
+
+	/* Fill whole space with trap instructions */
+	while (p < (int *)((char *)area + size))
+		*p++ = BREAKPOINT_INSTRUCTION;
+}
+
+static inline void bpf_flush_icache(void *start, void *end)
+{
+	smp_wmb();
+	flush_icache_range((unsigned long)start, (unsigned long)end);
+}
+
+static inline bool bpf_is_seen_register(struct codegen_context *ctx, int i)
+{
+	return (ctx->seen & (1 << (31 - b2p[i])));
+}
+
+static inline void bpf_set_seen_register(struct codegen_context *ctx, int i)
+{
+	ctx->seen |= (1 << (31 - b2p[i]));
+}
+
+static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
+{
+	/*
+	 * We only need a stack frame if:
+	 * - we call other functions (kernel helpers), or
+	 * - the bpf program uses its stack area
+	 * The latter condition is deduced from the usage of BPF_REG_FP
+	 */
+	return ctx->seen & SEEN_FUNC || bpf_is_seen_register(ctx, BPF_REG_FP);
+}
+
+static void bpf_jit_emit_skb_loads(u32 *image, struct codegen_context *ctx)
+{
+	/*
+	 * Load skb->len and skb->data_len
+	 * r3 points to skb
+	 */
+	PPC_LWZ(b2p[SKB_HLEN_REG], 3, offsetof(struct sk_buff, len));
+	PPC_LWZ(b2p[TMP_REG_1], 3, offsetof(struct sk_buff, data_len));
+	/* header_len = len - data_len */
+	PPC_SUB(b2p[SKB_HLEN_REG], b2p[SKB_HLEN_REG], b2p[TMP_REG_1]);
+
+	/* skb->data pointer */
+	PPC_BPF_LL(b2p[SKB_DATA_REG], 3, offsetof(struct sk_buff, data));
+}
+
+static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func)
+{
+#ifdef PPC64_ELF_ABI_v1
+	/* func points to the function descriptor */
+	PPC_LI64(b2p[TMP_REG_2], func);
+	/* Load actual entry point from function descriptor */
+	PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0);
+	/* ... and move it to LR */
+	PPC_MTLR(b2p[TMP_REG_1]);
+	/*
+	 * Load TOC from function descriptor at offset 8.
+	 * We can clobber r2 since we get called through a
+	 * function pointer (so caller will save/restore r2)
+	 * and since we don't use a TOC ourself.
+	 */
+	PPC_BPF_LL(2, b2p[TMP_REG_2], 8);
+#else
+	/* We can clobber r12 */
+	PPC_FUNC_ADDR(12, func);
+	PPC_MTLR(12);
+#endif
+	PPC_BLRL();
+}
+
+static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
+{
+	int i;
+	bool new_stack_frame = bpf_has_stack_frame(ctx);
+
+	if (new_stack_frame) {
+		/*
+		 * We need a stack frame, but we don't necessarily need to
+		 * save/restore LR unless we call other functions
+		 */
+		if (ctx->seen & SEEN_FUNC) {
+			EMIT(PPC_INST_MFLR | __PPC_RT(R0));
+			PPC_BPF_STL(0, 1, PPC_LR_STKOFF);
+		}
+
+		PPC_BPF_STLU(1, 1, -BPF_PPC_STACKFRAME);
+	}
+
+	/*
+	 * Back up non-volatile regs -- BPF registers 6-10
+	 * If we haven't created our own stack frame, we save these
+	 * in the protected zone below the previous stack frame
+	 */
+	for (i = BPF_REG_6; i <= BPF_REG_10; i++)
+		if (bpf_is_seen_register(ctx, i))
+			PPC_BPF_STL(b2p[i], 1,
+				(new_stack_frame ? BPF_PPC_STACKFRAME : 0) -
+					(8 * (32 - b2p[i])));
+
+	/*
+	 * Save additional non-volatile regs if we cache skb
+	 * Also, setup skb data
+	 */
+	if (ctx->seen & SEEN_SKB) {
+		PPC_BPF_STL(b2p[SKB_HLEN_REG], 1,
+			BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_HLEN_REG])));
+		PPC_BPF_STL(b2p[SKB_DATA_REG], 1,
+			BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_DATA_REG])));
+		bpf_jit_emit_skb_loads(image, ctx);
+	}
+
+	/* Setup frame pointer to point to the bpf stack area */
+	if (bpf_is_seen_register(ctx, BPF_REG_FP))
+		PPC_ADDI(b2p[BPF_REG_FP], 1,
+				BPF_PPC_STACKFRAME - BPF_PPC_STACK_SAVE);
+}
+
+static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
+{
+	int i;
+	bool new_stack_frame = bpf_has_stack_frame(ctx);
+
+	/* Move result to r3 */
+	PPC_MR(3, b2p[BPF_REG_0]);
+
+	/* Restore NVRs */
+	for (i = BPF_REG_6; i <= BPF_REG_10; i++)
+		if (bpf_is_seen_register(ctx, i))
+			PPC_BPF_LL(b2p[i], 1,
+				(new_stack_frame ? BPF_PPC_STACKFRAME : 0) -
+					(8 * (32 - b2p[i])));
+
+	/* Restore non-volatile registers used for skb cache */
+	if (ctx->seen & SEEN_SKB) {
+		PPC_BPF_LL(b2p[SKB_HLEN_REG], 1,
+			BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_HLEN_REG])));
+		PPC_BPF_LL(b2p[SKB_DATA_REG], 1,
+			BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_DATA_REG])));
+	}
+
+	/* Tear down our stack frame */
+	if (new_stack_frame) {
+		PPC_ADDI(1, 1, BPF_PPC_STACKFRAME);
+		if (ctx->seen & SEEN_FUNC) {
+			PPC_BPF_LL(0, 1, PPC_LR_STKOFF);
+			PPC_MTLR(0);
+		}
+	}
+
+	PPC_BLR();
+}
+
+/* Assemble the body code between the prologue & epilogue */
+static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
+			      struct codegen_context *ctx,
+			      u32 *addrs)
+{
+	const struct bpf_insn *insn = fp->insnsi;
+	int flen = fp->len;
+	int i;
+
+	/* Start of epilogue code - will only be valid 2nd pass onwards */
+	u32 exit_addr = addrs[flen];
+
+	for (i = 0; i < flen; i++) {
+		u32 code = insn[i].code;
+		u32 dst_reg = b2p[insn[i].dst_reg];
+		u32 src_reg = b2p[insn[i].src_reg];
+		s16 off = insn[i].off;
+		s32 imm = insn[i].imm;
+		u64 imm64;
+		u8 *func;
+		u32 true_cond;
+		int stack_local_off;
+
+		/*
+		 * addrs[] maps a BPF bytecode address into a real offset from
+		 * the start of the body code.
+		 */
+		addrs[i] = ctx->idx * 4;
+
+		/*
+		 * As an optimization, we note down which non-volatile registers
+		 * are used so that we can only save/restore those in our
+		 * prologue and epilogue. We do this here regardless of whether
+		 * the actual BPF instruction uses src/dst registers or not
+		 * (for instance, BPF_CALL does not use them). The expectation
+		 * is that those instructions will have src_reg/dst_reg set to
+		 * 0. Even otherwise, we just lose some prologue/epilogue
+		 * optimization but everything else should work without
+		 * any issues.
+		 */
+		if (dst_reg >= 24 && dst_reg <= 31)
+			bpf_set_seen_register(ctx, insn[i].dst_reg);
+		if (src_reg >= 24 && src_reg <= 31)
+			bpf_set_seen_register(ctx, insn[i].src_reg);
+
+		switch (code) {
+		/*
+		 * Arithmetic operations: ADD/SUB/MUL/DIV/MOD/NEG
+		 */
+		case BPF_ALU | BPF_ADD | BPF_X: /* (u32) dst += (u32) src */
+		case BPF_ALU64 | BPF_ADD | BPF_X: /* dst += src */
+			PPC_ADD(dst_reg, dst_reg, src_reg);
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_SUB | BPF_X: /* (u32) dst -= (u32) src */
+		case BPF_ALU64 | BPF_SUB | BPF_X: /* dst -= src */
+			PPC_SUB(dst_reg, dst_reg, src_reg);
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */
+		case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */
+		case BPF_ALU64 | BPF_ADD | BPF_K: /* dst += imm */
+		case BPF_ALU64 | BPF_SUB | BPF_K: /* dst -= imm */
+			if (BPF_OP(code) == BPF_SUB)
+				imm = -imm;
+			if (imm) {
+				if (imm >= -32768 && imm < 32768)
+					PPC_ADDI(dst_reg, dst_reg, IMM_L(imm));
+				else {
+					PPC_LI32(b2p[TMP_REG_1], imm);
+					PPC_ADD(dst_reg, dst_reg, b2p[TMP_REG_1]);
+				}
+			}
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */
+		case BPF_ALU64 | BPF_MUL | BPF_X: /* dst *= src */
+			if (BPF_CLASS(code) == BPF_ALU)
+				PPC_MULW(dst_reg, dst_reg, src_reg);
+			else
+				PPC_MULD(dst_reg, dst_reg, src_reg);
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_MUL | BPF_K: /* (u32) dst *= (u32) imm */
+		case BPF_ALU64 | BPF_MUL | BPF_K: /* dst *= imm */
+			if (imm >= -32768 && imm < 32768)
+				PPC_MULI(dst_reg, dst_reg, IMM_L(imm));
+			else {
+				PPC_LI32(b2p[TMP_REG_1], imm);
+				if (BPF_CLASS(code) == BPF_ALU)
+					PPC_MULW(dst_reg, dst_reg,
+							b2p[TMP_REG_1]);
+				else
+					PPC_MULD(dst_reg, dst_reg,
+							b2p[TMP_REG_1]);
+			}
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
+		case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
+			PPC_CMPWI(src_reg, 0);
+			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
+			PPC_LI(b2p[BPF_REG_0], 0);
+			PPC_JMP(exit_addr);
+			if (BPF_OP(code) == BPF_MOD) {
+				PPC_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg);
+				PPC_MULW(b2p[TMP_REG_1], src_reg,
+						b2p[TMP_REG_1]);
+				PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
+			} else
+				PPC_DIVWU(dst_reg, dst_reg, src_reg);
+			goto bpf_alu32_trunc;
+		case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
+		case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
+			PPC_CMPDI(src_reg, 0);
+			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
+			PPC_LI(b2p[BPF_REG_0], 0);
+			PPC_JMP(exit_addr);
+			if (BPF_OP(code) == BPF_MOD) {
+				PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg);
+				PPC_MULD(b2p[TMP_REG_1], src_reg,
+						b2p[TMP_REG_1]);
+				PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
+			} else
+				PPC_DIVD(dst_reg, dst_reg, src_reg);
+			break;
+		case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */
+		case BPF_ALU | BPF_DIV | BPF_K: /* (u32) dst /= (u32) imm */
+		case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */
+		case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */
+			if (imm == 0)
+				return -EINVAL;
+			else if (imm == 1)
+				goto bpf_alu32_trunc;
+
+			PPC_LI32(b2p[TMP_REG_1], imm);
+			switch (BPF_CLASS(code)) {
+			case BPF_ALU:
+				if (BPF_OP(code) == BPF_MOD) {
+					PPC_DIVWU(b2p[TMP_REG_2], dst_reg,
+							b2p[TMP_REG_1]);
+					PPC_MULW(b2p[TMP_REG_1],
+							b2p[TMP_REG_1],
+							b2p[TMP_REG_2]);
+					PPC_SUB(dst_reg, dst_reg,
+							b2p[TMP_REG_1]);
+				} else
+					PPC_DIVWU(dst_reg, dst_reg,
+							b2p[TMP_REG_1]);
+				break;
+			case BPF_ALU64:
+				if (BPF_OP(code) == BPF_MOD) {
+					PPC_DIVD(b2p[TMP_REG_2], dst_reg,
+							b2p[TMP_REG_1]);
+					PPC_MULD(b2p[TMP_REG_1],
+							b2p[TMP_REG_1],
+							b2p[TMP_REG_2]);
+					PPC_SUB(dst_reg, dst_reg,
+							b2p[TMP_REG_1]);
+				} else
+					PPC_DIVD(dst_reg, dst_reg,
+							b2p[TMP_REG_1]);
+				break;
+			}
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_NEG: /* (u32) dst = -dst */
+		case BPF_ALU64 | BPF_NEG: /* dst = -dst */
+			PPC_NEG(dst_reg, dst_reg);
+			goto bpf_alu32_trunc;
+
+		/*
+		 * Logical operations: AND/OR/XOR/[A]LSH/[A]RSH
+		 */
+		case BPF_ALU | BPF_AND | BPF_X: /* (u32) dst = dst & src */
+		case BPF_ALU64 | BPF_AND | BPF_X: /* dst = dst & src */
+			PPC_AND(dst_reg, dst_reg, src_reg);
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_AND | BPF_K: /* (u32) dst = dst & imm */
+		case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */
+			if (!IMM_H(imm))
+				PPC_ANDI(dst_reg, dst_reg, IMM_L(imm));
+			else {
+				/* Sign-extended */
+				PPC_LI32(b2p[TMP_REG_1], imm);
+				PPC_AND(dst_reg, dst_reg, b2p[TMP_REG_1]);
+			}
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_OR | BPF_X: /* dst = (u32) dst | (u32) src */
+		case BPF_ALU64 | BPF_OR | BPF_X: /* dst = dst | src */
+			PPC_OR(dst_reg, dst_reg, src_reg);
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_OR | BPF_K:/* dst = (u32) dst | (u32) imm */
+		case BPF_ALU64 | BPF_OR | BPF_K:/* dst = dst | imm */
+			if (imm < 0 && BPF_CLASS(code) == BPF_ALU64) {
+				/* Sign-extended */
+				PPC_LI32(b2p[TMP_REG_1], imm);
+				PPC_OR(dst_reg, dst_reg, b2p[TMP_REG_1]);
+			} else {
+				if (IMM_L(imm))
+					PPC_ORI(dst_reg, dst_reg, IMM_L(imm));
+				if (IMM_H(imm))
+					PPC_ORIS(dst_reg, dst_reg, IMM_H(imm));
+			}
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_XOR | BPF_X: /* (u32) dst ^= src */
+		case BPF_ALU64 | BPF_XOR | BPF_X: /* dst ^= src */
+			PPC_XOR(dst_reg, dst_reg, src_reg);
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_XOR | BPF_K: /* (u32) dst ^= (u32) imm */
+		case BPF_ALU64 | BPF_XOR | BPF_K: /* dst ^= imm */
+			if (imm < 0 && BPF_CLASS(code) == BPF_ALU64) {
+				/* Sign-extended */
+				PPC_LI32(b2p[TMP_REG_1], imm);
+				PPC_XOR(dst_reg, dst_reg, b2p[TMP_REG_1]);
+			} else {
+				if (IMM_L(imm))
+					PPC_XORI(dst_reg, dst_reg, IMM_L(imm));
+				if (IMM_H(imm))
+					PPC_XORIS(dst_reg, dst_reg, IMM_H(imm));
+			}
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_LSH | BPF_X: /* (u32) dst <<= (u32) src */
+			/* slw clears top 32 bits */
+			PPC_SLW(dst_reg, dst_reg, src_reg);
+			break;
+		case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */
+			PPC_SLD(dst_reg, dst_reg, src_reg);
+			break;
+		case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<== (u32) imm */
+			/* with imm 0, we still need to clear top 32 bits */
+			PPC_SLWI(dst_reg, dst_reg, imm);
+			break;
+		case BPF_ALU64 | BPF_LSH | BPF_K: /* dst <<== imm */
+			if (imm != 0)
+				PPC_SLDI(dst_reg, dst_reg, imm);
+			break;
+		case BPF_ALU | BPF_RSH | BPF_X: /* (u32) dst >>= (u32) src */
+			PPC_SRW(dst_reg, dst_reg, src_reg);
+			break;
+		case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */
+			PPC_SRD(dst_reg, dst_reg, src_reg);
+			break;
+		case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */
+			PPC_SRWI(dst_reg, dst_reg, imm);
+			break;
+		case BPF_ALU64 | BPF_RSH | BPF_K: /* dst >>= imm */
+			if (imm != 0)
+				PPC_SRDI(dst_reg, dst_reg, imm);
+			break;
+		case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
+			PPC_SRAD(dst_reg, dst_reg, src_reg);
+			break;
+		case BPF_ALU64 | BPF_ARSH | BPF_K: /* (s64) dst >>= imm */
+			if (imm != 0)
+				PPC_SRADI(dst_reg, dst_reg, imm);
+			break;
+
+		/*
+		 * MOV
+		 */
+		case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
+		case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
+			PPC_MR(dst_reg, src_reg);
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
+		case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */
+			PPC_LI32(dst_reg, imm);
+			if (imm < 0)
+				goto bpf_alu32_trunc;
+			break;
+
+bpf_alu32_trunc:
+		/* Truncate to 32-bits */
+		if (BPF_CLASS(code) == BPF_ALU)
+			PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
+		break;
+
+		/*
+		 * BPF_FROM_BE/LE
+		 */
+		case BPF_ALU | BPF_END | BPF_FROM_LE:
+		case BPF_ALU | BPF_END | BPF_FROM_BE:
+#ifdef __BIG_ENDIAN__
+			if (BPF_SRC(code) == BPF_FROM_BE)
+				goto emit_clear;
+#else /* !__BIG_ENDIAN__ */
+			if (BPF_SRC(code) == BPF_FROM_LE)
+				goto emit_clear;
+#endif
+			switch (imm) {
+			case 16:
+				/* Rotate 8 bits left & mask with 0x0000ff00 */
+				PPC_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 16, 23);
+				/* Rotate 8 bits right & insert LSB to reg */
+				PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 24, 31);
+				/* Move result back to dst_reg */
+				PPC_MR(dst_reg, b2p[TMP_REG_1]);
+				break;
+			case 32:
+				/*
+				 * Rotate word left by 8 bits:
+				 * 2 bytes are already in their final position
+				 * -- byte 2 and 4 (of bytes 1, 2, 3 and 4)
+				 */
+				PPC_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 0, 31);
+				/* Rotate 24 bits and insert byte 1 */
+				PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 0, 7);
+				/* Rotate 24 bits and insert byte 3 */
+				PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 16, 23);
+				PPC_MR(dst_reg, b2p[TMP_REG_1]);
+				break;
+			case 64:
+				/*
+				 * Way easier and faster(?) to store the value
+				 * into stack and then use ldbrx
+				 *
+				 * First, determine where in stack we can store
+				 * this:
+				 * - if we have allotted a stack frame, then we
+				 *   will utilize the area set aside by
+				 *   BPF_PPC_STACK_LOCALS
+				 * - else, we use the area beneath the NV GPR
+				 *   save area
+				 *
+				 * ctx->seen will be reliable in pass2, but
+				 * the instructions generated will remain the
+				 * same across all passes
+				 */
+				if (bpf_has_stack_frame(ctx))
+					stack_local_off = STACK_FRAME_MIN_SIZE;
+				else
+					stack_local_off = -(BPF_PPC_STACK_SAVE + 8);
+
+				PPC_STD(dst_reg, 1, stack_local_off);
+				PPC_ADDI(b2p[TMP_REG_1], 1, stack_local_off);
+				PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]);
+				break;
+			}
+			break;
+
+emit_clear:
+			switch (imm) {
+			case 16:
+				/* zero-extend 16 bits into 64 bits */
+				PPC_RLDICL(dst_reg, dst_reg, 0, 48);
+				break;
+			case 32:
+				/* zero-extend 32 bits into 64 bits */
+				PPC_RLDICL(dst_reg, dst_reg, 0, 32);
+				break;
+			case 64:
+				/* nop */
+				break;
+			}
+			break;
+
+		/*
+		 * BPF_ST(X)
+		 */
+		case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */
+		case BPF_ST | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = imm */
+			if (BPF_CLASS(code) == BPF_ST) {
+				PPC_LI(b2p[TMP_REG_1], imm);
+				src_reg = b2p[TMP_REG_1];
+			}
+			PPC_STB(src_reg, dst_reg, off);
+			break;
+		case BPF_STX | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = src */
+		case BPF_ST | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = imm */
+			if (BPF_CLASS(code) == BPF_ST) {
+				PPC_LI(b2p[TMP_REG_1], imm);
+				src_reg = b2p[TMP_REG_1];
+			}
+			PPC_STH(src_reg, dst_reg, off);
+			break;
+		case BPF_STX | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = src */
+		case BPF_ST | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = imm */
+			if (BPF_CLASS(code) == BPF_ST) {
+				PPC_LI32(b2p[TMP_REG_1], imm);
+				src_reg = b2p[TMP_REG_1];
+			}
+			PPC_STW(src_reg, dst_reg, off);
+			break;
+		case BPF_STX | BPF_MEM | BPF_DW: /* (u64 *)(dst + off) = src */
+		case BPF_ST | BPF_MEM | BPF_DW: /* *(u64 *)(dst + off) = imm */
+			if (BPF_CLASS(code) == BPF_ST) {
+				PPC_LI32(b2p[TMP_REG_1], imm);
+				src_reg = b2p[TMP_REG_1];
+			}
+			PPC_STD(src_reg, dst_reg, off);
+			break;
+
+		/*
+		 * BPF_STX XADD (atomic_add)
+		 */
+		/* *(u32 *)(dst + off) += src */
+		case BPF_STX | BPF_XADD | BPF_W:
+			/* Get EA into TMP_REG_1 */
+			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
+			/* error if EA is not word-aligned */
+			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03);
+			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12);
+			PPC_LI(b2p[BPF_REG_0], 0);
+			PPC_JMP(exit_addr);
+			/* load value from memory into TMP_REG_2 */
+			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
+			/* add value from src_reg into this */
+			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
+			/* store result back */
+			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
+			/* we're done if this succeeded */
+			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
+			/* otherwise, let's try once more */
+			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
+			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
+			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
+			/* exit if the store was not successful */
+			PPC_LI(b2p[BPF_REG_0], 0);
+			PPC_BCC(COND_NE, exit_addr);
+			break;
+		/* *(u64 *)(dst + off) += src */
+		case BPF_STX | BPF_XADD | BPF_DW:
+			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
+			/* error if EA is not doubleword-aligned */
+			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07);
+			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4));
+			PPC_LI(b2p[BPF_REG_0], 0);
+			PPC_JMP(exit_addr);
+			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
+			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
+			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
+			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
+			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
+			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
+			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
+			PPC_LI(b2p[BPF_REG_0], 0);
+			PPC_BCC(COND_NE, exit_addr);
+			break;
+
+		/*
+		 * BPF_LDX
+		 */
+		/* dst = *(u8 *)(ul) (src + off) */
+		case BPF_LDX | BPF_MEM | BPF_B:
+			PPC_LBZ(dst_reg, src_reg, off);
+			break;
+		/* dst = *(u16 *)(ul) (src + off) */
+		case BPF_LDX | BPF_MEM | BPF_H:
+			PPC_LHZ(dst_reg, src_reg, off);
+			break;
+		/* dst = *(u32 *)(ul) (src + off) */
+		case BPF_LDX | BPF_MEM | BPF_W:
+			PPC_LWZ(dst_reg, src_reg, off);
+			break;
+		/* dst = *(u64 *)(ul) (src + off) */
+		case BPF_LDX | BPF_MEM | BPF_DW:
+			PPC_LD(dst_reg, src_reg, off);
+			break;
+
+		/*
+		 * Doubleword load
+		 * 16 byte instruction that uses two 'struct bpf_insn'
+		 */
+		case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
+			imm64 = ((u64)(u32) insn[i].imm) |
+				    (((u64)(u32) insn[i+1].imm) << 32);
+			/* Adjust for two bpf instructions */
+			addrs[++i] = ctx->idx * 4;
+			PPC_LI64(dst_reg, imm64);
+			break;
+
+		/*
+		 * Return/Exit
+		 */
+		case BPF_JMP | BPF_EXIT:
+			/*
+			 * If this isn't the very last instruction, branch to
+			 * the epilogue. If we _are_ the last instruction,
+			 * we'll just fall through to the epilogue.
+			 */
+			if (i != flen - 1)
+				PPC_JMP(exit_addr);
+			/* else fall through to the epilogue */
+			break;
+
+		/*
+		 * Call kernel helper
+		 */
+		case BPF_JMP | BPF_CALL:
+			ctx->seen |= SEEN_FUNC;
+			func = (u8 *) __bpf_call_base + imm;
+
+			/* Save skb pointer if we need to re-cache skb data */
+			if (bpf_helper_changes_skb_data(func))
+				PPC_BPF_STL(3, 1, STACK_FRAME_MIN_SIZE);
+
+			bpf_jit_emit_func_call(image, ctx, (u64)func);
+
+			/* move return value from r3 to BPF_REG_0 */
+			PPC_MR(b2p[BPF_REG_0], 3);
+
+			/* refresh skb cache */
+			if (bpf_helper_changes_skb_data(func)) {
+				/* reload skb pointer to r3 */
+				PPC_BPF_LL(3, 1, STACK_FRAME_MIN_SIZE);
+				bpf_jit_emit_skb_loads(image, ctx);
+			}
+			break;
+
+		/*
+		 * Jumps and branches
+		 */
+		case BPF_JMP | BPF_JA:
+			PPC_JMP(addrs[i + 1 + off]);
+			break;
+
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JSGT | BPF_K:
+		case BPF_JMP | BPF_JSGT | BPF_X:
+			true_cond = COND_GT;
+			goto cond_branch;
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
+		case BPF_JMP | BPF_JSGE | BPF_K:
+		case BPF_JMP | BPF_JSGE | BPF_X:
+			true_cond = COND_GE;
+			goto cond_branch;
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
+			true_cond = COND_EQ;
+			goto cond_branch;
+		case BPF_JMP | BPF_JNE | BPF_K:
+		case BPF_JMP | BPF_JNE | BPF_X:
+			true_cond = COND_NE;
+			goto cond_branch;
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
+			true_cond = COND_NE;
+			/* Fall through */
+
+cond_branch:
+			switch (code) {
+			case BPF_JMP | BPF_JGT | BPF_X:
+			case BPF_JMP | BPF_JGE | BPF_X:
+			case BPF_JMP | BPF_JEQ | BPF_X:
+			case BPF_JMP | BPF_JNE | BPF_X:
+				/* unsigned comparison */
+				PPC_CMPLD(dst_reg, src_reg);
+				break;
+			case BPF_JMP | BPF_JSGT | BPF_X:
+			case BPF_JMP | BPF_JSGE | BPF_X:
+				/* signed comparison */
+				PPC_CMPD(dst_reg, src_reg);
+				break;
+			case BPF_JMP | BPF_JSET | BPF_X:
+				PPC_AND_DOT(b2p[TMP_REG_1], dst_reg, src_reg);
+				break;
+			case BPF_JMP | BPF_JNE | BPF_K:
+			case BPF_JMP | BPF_JEQ | BPF_K:
+			case BPF_JMP | BPF_JGT | BPF_K:
+			case BPF_JMP | BPF_JGE | BPF_K:
+				/*
+				 * Need sign-extended load, so only positive
+				 * values can be used as imm in cmpldi
+				 */
+				if (imm >= 0 && imm < 32768)
+					PPC_CMPLDI(dst_reg, imm);
+				else {
+					/* sign-extending load */
+					PPC_LI32(b2p[TMP_REG_1], imm);
+					/* ... but unsigned comparison */
+					PPC_CMPLD(dst_reg, b2p[TMP_REG_1]);
+				}
+				break;
+			case BPF_JMP | BPF_JSGT | BPF_K:
+			case BPF_JMP | BPF_JSGE | BPF_K:
+				/*
+				 * signed comparison, so any 16-bit value
+				 * can be used in cmpdi
+				 */
+				if (imm >= -32768 && imm < 32768)
+					PPC_CMPDI(dst_reg, imm);
+				else {
+					PPC_LI32(b2p[TMP_REG_1], imm);
+					PPC_CMPD(dst_reg, b2p[TMP_REG_1]);
+				}
+				break;
+			case BPF_JMP | BPF_JSET | BPF_K:
+				/* andi does not sign-extend the immediate */
+				if (imm >= 0 && imm < 32768)
+					/* PPC_ANDI is _only/always_ dot-form */
+					PPC_ANDI(b2p[TMP_REG_1], dst_reg, imm);
+				else {
+					PPC_LI32(b2p[TMP_REG_1], imm);
+					PPC_AND_DOT(b2p[TMP_REG_1], dst_reg,
+						    b2p[TMP_REG_1]);
+				}
+				break;
+			}
+			PPC_BCC(true_cond, addrs[i + 1 + off]);
+			break;
+
+		/*
+		 * Loads from packet header/data
+		 * Assume 32-bit input value in imm and X (src_reg)
+		 */
+
+		/* Absolute loads */
+		case BPF_LD | BPF_W | BPF_ABS:
+			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_word);
+			goto common_load_abs;
+		case BPF_LD | BPF_H | BPF_ABS:
+			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_half);
+			goto common_load_abs;
+		case BPF_LD | BPF_B | BPF_ABS:
+			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_byte);
+common_load_abs:
+			/*
+			 * Load from [imm]
+			 * Load into r4, which can just be passed onto
+			 *  skb load helpers as the second parameter
+			 */
+			PPC_LI32(4, imm);
+			goto common_load;
+
+		/* Indirect loads */
+		case BPF_LD | BPF_W | BPF_IND:
+			func = (u8 *)sk_load_word;
+			goto common_load_ind;
+		case BPF_LD | BPF_H | BPF_IND:
+			func = (u8 *)sk_load_half;
+			goto common_load_ind;
+		case BPF_LD | BPF_B | BPF_IND:
+			func = (u8 *)sk_load_byte;
+common_load_ind:
+			/*
+			 * Load from [src_reg + imm]
+			 * Treat src_reg as a 32-bit value
+			 */
+			PPC_EXTSW(4, src_reg);
+			if (imm) {
+				if (imm >= -32768 && imm < 32768)
+					PPC_ADDI(4, 4, IMM_L(imm));
+				else {
+					PPC_LI32(b2p[TMP_REG_1], imm);
+					PPC_ADD(4, 4, b2p[TMP_REG_1]);
+				}
+			}
+
+common_load:
+			ctx->seen |= SEEN_SKB;
+			ctx->seen |= SEEN_FUNC;
+			bpf_jit_emit_func_call(image, ctx, (u64)func);
+
+			/*
+			 * Helper returns 'lt' condition on error, and an
+			 * appropriate return value in BPF_REG_0
+			 */
+			PPC_BCC(COND_LT, exit_addr);
+			break;
+
+		/*
+		 * TODO: Tail call
+		 */
+		case BPF_JMP | BPF_CALL | BPF_X:
+
+		default:
+			/*
+			 * The filter contains something cruel & unusual.
+			 * We don't handle it, but also there shouldn't be
+			 * anything missing from our list.
+			 */
+			pr_err_ratelimited("eBPF filter opcode %04x (@%d) unsupported\n",
+					code, i);
+			return -ENOTSUPP;
+		}
+	}
+
+	/* Set end-of-body-code address for exit. */
+	addrs[i] = ctx->idx * 4;
+
+	return 0;
+}
+
+void bpf_jit_compile(struct bpf_prog *fp) { }
+
+struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
+{
+	u32 proglen;
+	u32 alloclen;
+	u8 *image = NULL;
+	u32 *code_base;
+	u32 *addrs;
+	struct codegen_context cgctx;
+	int pass;
+	int flen;
+	struct bpf_binary_header *bpf_hdr;
+
+	if (!bpf_jit_enable)
+		return fp;
+
+	flen = fp->len;
+	addrs = kzalloc((flen+1) * sizeof(*addrs), GFP_KERNEL);
+	if (addrs == NULL)
+		return fp;
+
+	cgctx.idx = 0;
+	cgctx.seen = 0;
+	/* Scouting faux-generate pass 0 */
+	if (bpf_jit_build_body(fp, 0, &cgctx, addrs))
+		/* We hit something illegal or unsupported. */
+		goto out;
+
+	/*
+	 * Pretend to build prologue, given the features we've seen.  This will
+	 * update ctgtx.idx as it pretends to output instructions, then we can
+	 * calculate total size from idx.
+	 */
+	bpf_jit_build_prologue(0, &cgctx);
+	bpf_jit_build_epilogue(0, &cgctx);
+
+	proglen = cgctx.idx * 4;
+	alloclen = proglen + FUNCTION_DESCR_SIZE;
+
+	bpf_hdr = bpf_jit_binary_alloc(alloclen, &image, 4,
+			bpf_jit_fill_ill_insns);
+	if (!bpf_hdr)
+		goto out;
+
+	code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
+
+	/* Code generation passes 1-2 */
+	for (pass = 1; pass < 3; pass++) {
+		/* Now build the prologue, body code & epilogue for real. */
+		cgctx.idx = 0;
+		bpf_jit_build_prologue(code_base, &cgctx);
+		bpf_jit_build_body(fp, code_base, &cgctx, addrs);
+		bpf_jit_build_epilogue(code_base, &cgctx);
+
+		if (bpf_jit_enable > 1)
+			pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass,
+				proglen - (cgctx.idx * 4), cgctx.seen);
+	}
+
+	if (bpf_jit_enable > 1)
+		/*
+		 * Note that we output the base address of the code_base
+		 * rather than image, since opcodes are in code_base.
+		 */
+		bpf_jit_dump(flen, proglen, pass, code_base);
+
+	if (image) {
+		bpf_flush_icache(bpf_hdr, image + alloclen);
+#ifdef PPC64_ELF_ABI_v1
+		/* Function descriptor nastiness: Address + TOC */
+		((u64 *)image)[0] = (u64)code_base;
+		((u64 *)image)[1] = local_paca->kernel_toc;
+#endif
+		fp->bpf_func = (void *)image;
+		fp->jited = 1;
+	}
+
+out:
+	kfree(addrs);
+	return fp;
+}
+
+void bpf_jit_free(struct bpf_prog *fp)
+{
+	unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
+	struct bpf_binary_header *bpf_hdr = (void *)addr;
+
+	if (fp->jited)
+		bpf_jit_binary_free(bpf_hdr);
+
+	bpf_prog_unlock_free(fp);
+}
diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c
index ed7b0977072a..ef2142ff7dbd 100644
--- a/arch/powerpc/oprofile/cell/spu_task_sync.c
+++ b/arch/powerpc/oprofile/cell/spu_task_sync.c
@@ -51,7 +51,7 @@ static void spu_buff_add(unsigned long int value, int spu)
 	 * That way we can tell the difference between the
 	 * buffer being full versus empty.
 	 *
-	 *  ASSUPTION: the buffer_lock is held when this function
+	 *  ASSUMPTION: the buffer_lock is held when this function
 	 *             is called to lock the buffer, head and tail.
 	 */
 	int full = 1;
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 77b6394a7c50..f102d5370101 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -5,7 +5,7 @@ obj-$(CONFIG_PERF_EVENTS)	+= callchain.o perf_regs.o
 obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o bhrb.o
 obj64-$(CONFIG_PPC_PERF_CTRS)	+= power4-pmu.o ppc970-pmu.o power5-pmu.o \
 				   power5+-pmu.o power6-pmu.o power7-pmu.o \
-				   power8-pmu.o
+				   isa207-common.o power8-pmu.o power9-pmu.o
 obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
 
 obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index ffd61d55fb25..4ed377f0f7b2 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -992,7 +992,7 @@ static u64 check_and_compute_delta(u64 prev, u64 val)
 	 * than the previous value it will cause the delta and the counter to
 	 * have bogus values unless we rolled a counter over.  If a coutner is
 	 * rolled back, it will be smaller, but within 256, which is the maximum
-	 * number of events to rollback at once.  If we dectect a rollback
+	 * number of events to rollback at once.  If we detect a rollback
 	 * return 0.  This can lead to a small lack of precision in the
 	 * counters.
 	 */
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 2da41b78cb6d..7b2ca16b1eb4 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -1298,7 +1298,7 @@ static void h_24x7_event_read(struct perf_event *event)
 			__this_cpu_write(hv_24x7_txn_err, ret);
 		} else {
 			/*
-			 * Assoicate the event with the HCALL request index,
+			 * Associate the event with the HCALL request index,
 			 * so ->commit_txn() can quickly find/update count.
 			 */
 			i = request_buffer->num_requests - 1;
diff --git a/arch/powerpc/perf/hv-24x7.h b/arch/powerpc/perf/hv-24x7.h
index 791455e7f5cf..634ef4082cdc 100644
--- a/arch/powerpc/perf/hv-24x7.h
+++ b/arch/powerpc/perf/hv-24x7.h
@@ -66,7 +66,7 @@ struct hv_24x7_result_element {
 	/* -1 if @performance_domain does not refer to a virtual processor */
 	__be32 lpar_cfg_instance_id;
 
-	/* size = @result_element_data_size of cointaining result. */
+	/* size = @result_element_data_size of containing result. */
 	__u64 element_data[1];
 } __packed;
 
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
new file mode 100644
index 000000000000..6143c99f3ec5
--- /dev/null
+++ b/arch/powerpc/perf/isa207-common.c
@@ -0,0 +1,263 @@
+/*
+ * Common Performance counter support functions for PowerISA v2.07 processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ * Copyright 2013 Michael Ellerman, IBM Corporation.
+ * Copyright 2016 Madhavan Srinivasan, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include "isa207-common.h"
+
+static inline bool event_is_fab_match(u64 event)
+{
+	/* Only check pmc, unit and pmcxsel, ignore the edge bit (0) */
+	event &= 0xff0fe;
+
+	/* PM_MRK_FAB_RSP_MATCH & PM_MRK_FAB_RSP_MATCH_CYC */
+	return (event == 0x30056 || event == 0x4f052);
+}
+
+int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
+{
+	unsigned int unit, pmc, cache, ebb;
+	unsigned long mask, value;
+
+	mask = value = 0;
+
+	if (event & ~EVENT_VALID_MASK)
+		return -1;
+
+	pmc   = (event >> EVENT_PMC_SHIFT)        & EVENT_PMC_MASK;
+	unit  = (event >> EVENT_UNIT_SHIFT)       & EVENT_UNIT_MASK;
+	cache = (event >> EVENT_CACHE_SEL_SHIFT)  & EVENT_CACHE_SEL_MASK;
+	ebb   = (event >> EVENT_EBB_SHIFT)        & EVENT_EBB_MASK;
+
+	if (pmc) {
+		u64 base_event;
+
+		if (pmc > 6)
+			return -1;
+
+		/* Ignore Linux defined bits when checking event below */
+		base_event = event & ~EVENT_LINUX_MASK;
+
+		if (pmc >= 5 && base_event != 0x500fa &&
+				base_event != 0x600f4)
+			return -1;
+
+		mask  |= CNST_PMC_MASK(pmc);
+		value |= CNST_PMC_VAL(pmc);
+	}
+
+	if (pmc <= 4) {
+		/*
+		 * Add to number of counters in use. Note this includes events with
+		 * a PMC of 0 - they still need a PMC, it's just assigned later.
+		 * Don't count events on PMC 5 & 6, there is only one valid event
+		 * on each of those counters, and they are handled above.
+		 */
+		mask  |= CNST_NC_MASK;
+		value |= CNST_NC_VAL;
+	}
+
+	if (unit >= 6 && unit <= 9) {
+		/*
+		 * L2/L3 events contain a cache selector field, which is
+		 * supposed to be programmed into MMCRC. However MMCRC is only
+		 * HV writable, and there is no API for guest kernels to modify
+		 * it. The solution is for the hypervisor to initialise the
+		 * field to zeroes, and for us to only ever allow events that
+		 * have a cache selector of zero. The bank selector (bit 3) is
+		 * irrelevant, as long as the rest of the value is 0.
+		 */
+		if (cache & 0x7)
+			return -1;
+
+	} else if (event & EVENT_IS_L1) {
+		mask  |= CNST_L1_QUAL_MASK;
+		value |= CNST_L1_QUAL_VAL(cache);
+	}
+
+	if (event & EVENT_IS_MARKED) {
+		mask  |= CNST_SAMPLE_MASK;
+		value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
+	}
+
+	/*
+	 * Special case for PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC,
+	 * the threshold control bits are used for the match value.
+	 */
+	if (event_is_fab_match(event)) {
+		mask  |= CNST_FAB_MATCH_MASK;
+		value |= CNST_FAB_MATCH_VAL(event >> EVENT_THR_CTL_SHIFT);
+	} else {
+		/*
+		 * Check the mantissa upper two bits are not zero, unless the
+		 * exponent is also zero. See the THRESH_CMP_MANTISSA doc.
+		 */
+		unsigned int cmp, exp;
+
+		cmp = (event >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
+		exp = cmp >> 7;
+
+		if (exp && (cmp & 0x60) == 0)
+			return -1;
+
+		mask  |= CNST_THRESH_MASK;
+		value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT);
+	}
+
+	if (!pmc && ebb)
+		/* EBB events must specify the PMC */
+		return -1;
+
+	if (event & EVENT_WANTS_BHRB) {
+		if (!ebb)
+			/* Only EBB events can request BHRB */
+			return -1;
+
+		mask  |= CNST_IFM_MASK;
+		value |= CNST_IFM_VAL(event >> EVENT_IFM_SHIFT);
+	}
+
+	/*
+	 * All events must agree on EBB, either all request it or none.
+	 * EBB events are pinned & exclusive, so this should never actually
+	 * hit, but we leave it as a fallback in case.
+	 */
+	mask  |= CNST_EBB_VAL(ebb);
+	value |= CNST_EBB_MASK;
+
+	*maskp = mask;
+	*valp = value;
+
+	return 0;
+}
+
+int isa207_compute_mmcr(u64 event[], int n_ev,
+			       unsigned int hwc[], unsigned long mmcr[],
+			       struct perf_event *pevents[])
+{
+	unsigned long mmcra, mmcr1, mmcr2, unit, combine, psel, cache, val;
+	unsigned int pmc, pmc_inuse;
+	int i;
+
+	pmc_inuse = 0;
+
+	/* First pass to count resource use */
+	for (i = 0; i < n_ev; ++i) {
+		pmc = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
+		if (pmc)
+			pmc_inuse |= 1 << pmc;
+	}
+
+	/* In continuous sampling mode, update SDAR on TLB miss */
+	mmcra = MMCRA_SDAR_MODE_TLB;
+	mmcr1 = mmcr2 = 0;
+
+	/* Second pass: assign PMCs, set all MMCR1 fields */
+	for (i = 0; i < n_ev; ++i) {
+		pmc     = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
+		unit    = (event[i] >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK;
+		combine = (event[i] >> EVENT_COMBINE_SHIFT) & EVENT_COMBINE_MASK;
+		psel    =  event[i] & EVENT_PSEL_MASK;
+
+		if (!pmc) {
+			for (pmc = 1; pmc <= 4; ++pmc) {
+				if (!(pmc_inuse & (1 << pmc)))
+					break;
+			}
+
+			pmc_inuse |= 1 << pmc;
+		}
+
+		if (pmc <= 4) {
+			mmcr1 |= unit << MMCR1_UNIT_SHIFT(pmc);
+			mmcr1 |= combine << MMCR1_COMBINE_SHIFT(pmc);
+			mmcr1 |= psel << MMCR1_PMCSEL_SHIFT(pmc);
+		}
+
+		if (event[i] & EVENT_IS_L1) {
+			cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
+			mmcr1 |= (cache & 1) << MMCR1_IC_QUAL_SHIFT;
+			cache >>= 1;
+			mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT;
+		}
+
+		if (event[i] & EVENT_IS_MARKED) {
+			mmcra |= MMCRA_SAMPLE_ENABLE;
+
+			val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK;
+			if (val) {
+				mmcra |= (val &  3) << MMCRA_SAMP_MODE_SHIFT;
+				mmcra |= (val >> 2) << MMCRA_SAMP_ELIG_SHIFT;
+			}
+		}
+
+		/*
+		 * PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC,
+		 * the threshold bits are used for the match value.
+		 */
+		if (event_is_fab_match(event[i])) {
+			mmcr1 |= ((event[i] >> EVENT_THR_CTL_SHIFT) &
+				  EVENT_THR_CTL_MASK) << MMCR1_FAB_SHIFT;
+		} else {
+			val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK;
+			mmcra |= val << MMCRA_THR_CTL_SHIFT;
+			val = (event[i] >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK;
+			mmcra |= val << MMCRA_THR_SEL_SHIFT;
+			val = (event[i] >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
+			mmcra |= val << MMCRA_THR_CMP_SHIFT;
+		}
+
+		if (event[i] & EVENT_WANTS_BHRB) {
+			val = (event[i] >> EVENT_IFM_SHIFT) & EVENT_IFM_MASK;
+			mmcra |= val << MMCRA_IFM_SHIFT;
+		}
+
+		if (pevents[i]->attr.exclude_user)
+			mmcr2 |= MMCR2_FCP(pmc);
+
+		if (pevents[i]->attr.exclude_hv)
+			mmcr2 |= MMCR2_FCH(pmc);
+
+		if (pevents[i]->attr.exclude_kernel) {
+			if (cpu_has_feature(CPU_FTR_HVMODE))
+				mmcr2 |= MMCR2_FCH(pmc);
+			else
+				mmcr2 |= MMCR2_FCS(pmc);
+		}
+
+		hwc[i] = pmc - 1;
+	}
+
+	/* Return MMCRx values */
+	mmcr[0] = 0;
+
+	/* pmc_inuse is 1-based */
+	if (pmc_inuse & 2)
+		mmcr[0] = MMCR0_PMC1CE;
+
+	if (pmc_inuse & 0x7c)
+		mmcr[0] |= MMCR0_PMCjCE;
+
+	/* If we're not using PMC 5 or 6, freeze them */
+	if (!(pmc_inuse & 0x60))
+		mmcr[0] |= MMCR0_FC56;
+
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcra;
+	mmcr[3] = mmcr2;
+
+	return 0;
+}
+
+void isa207_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+{
+	if (pmc <= 3)
+		mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1));
+}
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
new file mode 100644
index 000000000000..4d0a4e5017c2
--- /dev/null
+++ b/arch/powerpc/perf/isa207-common.h
@@ -0,0 +1,236 @@
+/*
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ * Copyright 2013 Michael Ellerman, IBM Corporation.
+ * Copyright 2016 Madhavan Srinivasan, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or any later version.
+ */
+
+#ifndef _LINUX_POWERPC_PERF_ISA207_COMMON_H_
+#define _LINUX_POWERPC_PERF_ISA207_COMMON_H_
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <asm/firmware.h>
+#include <asm/cputable.h>
+
+/*
+ * Raw event encoding for PowerISA v2.07:
+ *
+ *        60        56        52        48        44        40        36        32
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *   | | [ ]                           [      thresh_cmp     ]   [  thresh_ctl   ]
+ *   | |  |                                                              |
+ *   | |  *- IFM (Linux)                 thresh start/stop OR FAB match -*
+ *   | *- BHRB (Linux)
+ *   *- EBB (Linux)
+ *
+ *        28        24        20        16        12         8         4         0
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *   [   ] [  sample ]   [cache]   [ pmc ]   [unit ]   c     m   [    pmcxsel    ]
+ *     |        |           |                          |     |
+ *     |        |           |                          |     *- mark
+ *     |        |           *- L1/L2/L3 cache_sel      |
+ *     |        |                                      |
+ *     |        *- sampling mode for marked events     *- combine
+ *     |
+ *     *- thresh_sel
+ *
+ * Below uses IBM bit numbering.
+ *
+ * MMCR1[x:y] = unit    (PMCxUNIT)
+ * MMCR1[x]   = combine (PMCxCOMB)
+ *
+ * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011
+ *	# PM_MRK_FAB_RSP_MATCH
+ *	MMCR1[20:27] = thresh_ctl   (FAB_CRESP_MATCH / FAB_TYPE_MATCH)
+ * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001
+ *	# PM_MRK_FAB_RSP_MATCH_CYC
+ *	MMCR1[20:27] = thresh_ctl   (FAB_CRESP_MATCH / FAB_TYPE_MATCH)
+ * else
+ *	MMCRA[48:55] = thresh_ctl   (THRESH START/END)
+ *
+ * if thresh_sel:
+ *	MMCRA[45:47] = thresh_sel
+ *
+ * if thresh_cmp:
+ *	MMCRA[22:24] = thresh_cmp[0:2]
+ *	MMCRA[25:31] = thresh_cmp[3:9]
+ *
+ * if unit == 6 or unit == 7
+ *	MMCRC[53:55] = cache_sel[1:3]      (L2EVENT_SEL)
+ * else if unit == 8 or unit == 9:
+ *	if cache_sel[0] == 0: # L3 bank
+ *		MMCRC[47:49] = cache_sel[1:3]  (L3EVENT_SEL0)
+ *	else if cache_sel[0] == 1:
+ *		MMCRC[50:51] = cache_sel[2:3]  (L3EVENT_SEL1)
+ * else if cache_sel[1]: # L1 event
+ *	MMCR1[16] = cache_sel[2]
+ *	MMCR1[17] = cache_sel[3]
+ *
+ * if mark:
+ *	MMCRA[63]    = 1		(SAMPLE_ENABLE)
+ *	MMCRA[57:59] = sample[0:2]	(RAND_SAMP_ELIG)
+ *	MMCRA[61:62] = sample[3:4]	(RAND_SAMP_MODE)
+ *
+ * if EBB and BHRB:
+ *	MMCRA[32:33] = IFM
+ *
+ */
+
+#define EVENT_EBB_MASK		1ull
+#define EVENT_EBB_SHIFT		PERF_EVENT_CONFIG_EBB_SHIFT
+#define EVENT_BHRB_MASK		1ull
+#define EVENT_BHRB_SHIFT	62
+#define EVENT_WANTS_BHRB	(EVENT_BHRB_MASK << EVENT_BHRB_SHIFT)
+#define EVENT_IFM_MASK		3ull
+#define EVENT_IFM_SHIFT		60
+#define EVENT_THR_CMP_SHIFT	40	/* Threshold CMP value */
+#define EVENT_THR_CMP_MASK	0x3ff
+#define EVENT_THR_CTL_SHIFT	32	/* Threshold control value (start/stop) */
+#define EVENT_THR_CTL_MASK	0xffull
+#define EVENT_THR_SEL_SHIFT	29	/* Threshold select value */
+#define EVENT_THR_SEL_MASK	0x7
+#define EVENT_THRESH_SHIFT	29	/* All threshold bits */
+#define EVENT_THRESH_MASK	0x1fffffull
+#define EVENT_SAMPLE_SHIFT	24	/* Sampling mode & eligibility */
+#define EVENT_SAMPLE_MASK	0x1f
+#define EVENT_CACHE_SEL_SHIFT	20	/* L2/L3 cache select */
+#define EVENT_CACHE_SEL_MASK	0xf
+#define EVENT_IS_L1		(4 << EVENT_CACHE_SEL_SHIFT)
+#define EVENT_PMC_SHIFT		16	/* PMC number (1-based) */
+#define EVENT_PMC_MASK		0xf
+#define EVENT_UNIT_SHIFT	12	/* Unit */
+#define EVENT_UNIT_MASK		0xf
+#define EVENT_COMBINE_SHIFT	11	/* Combine bit */
+#define EVENT_COMBINE_MASK	0x1
+#define EVENT_MARKED_SHIFT	8	/* Marked bit */
+#define EVENT_MARKED_MASK	0x1
+#define EVENT_IS_MARKED		(EVENT_MARKED_MASK << EVENT_MARKED_SHIFT)
+#define EVENT_PSEL_MASK		0xff	/* PMCxSEL value */
+
+/* Bits defined by Linux */
+#define EVENT_LINUX_MASK	\
+	((EVENT_EBB_MASK  << EVENT_EBB_SHIFT)			|	\
+	 (EVENT_BHRB_MASK << EVENT_BHRB_SHIFT)			|	\
+	 (EVENT_IFM_MASK  << EVENT_IFM_SHIFT))
+
+#define EVENT_VALID_MASK	\
+	((EVENT_THRESH_MASK    << EVENT_THRESH_SHIFT)		|	\
+	 (EVENT_SAMPLE_MASK    << EVENT_SAMPLE_SHIFT)		|	\
+	 (EVENT_CACHE_SEL_MASK << EVENT_CACHE_SEL_SHIFT)	|	\
+	 (EVENT_PMC_MASK       << EVENT_PMC_SHIFT)		|	\
+	 (EVENT_UNIT_MASK      << EVENT_UNIT_SHIFT)		|	\
+	 (EVENT_COMBINE_MASK   << EVENT_COMBINE_SHIFT)		|	\
+	 (EVENT_MARKED_MASK    << EVENT_MARKED_SHIFT)		|	\
+	  EVENT_LINUX_MASK					|	\
+	  EVENT_PSEL_MASK)
+
+#define ONLY_PLM \
+	(PERF_SAMPLE_BRANCH_USER        |\
+	 PERF_SAMPLE_BRANCH_KERNEL      |\
+	 PERF_SAMPLE_BRANCH_HV)
+
+/*
+ * Layout of constraint bits:
+ *
+ *        60        56        52        48        44        40        36        32
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *   [   fab_match   ]         [       thresh_cmp      ] [   thresh_ctl    ] [   ]
+ *                                                                             |
+ *                                                                 thresh_sel -*
+ *
+ *        28        24        20        16        12         8         4         0
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *               [ ] |   [ ]   [  sample ]   [     ]   [6] [5]   [4] [3]   [2] [1]
+ *                |  |    |                     |
+ *      BHRB IFM -*  |    |                     |      Count of events for each PMC.
+ *              EBB -*    |                     |        p1, p2, p3, p4, p5, p6.
+ *      L1 I/D qualifier -*                     |
+ *                     nc - number of counters -*
+ *
+ * The PMC fields P1..P6, and NC, are adder fields. As we accumulate constraints
+ * we want the low bit of each field to be added to any existing value.
+ *
+ * Everything else is a value field.
+ */
+
+#define CNST_FAB_MATCH_VAL(v)	(((v) & EVENT_THR_CTL_MASK) << 56)
+#define CNST_FAB_MATCH_MASK	CNST_FAB_MATCH_VAL(EVENT_THR_CTL_MASK)
+
+/* We just throw all the threshold bits into the constraint */
+#define CNST_THRESH_VAL(v)	(((v) & EVENT_THRESH_MASK) << 32)
+#define CNST_THRESH_MASK	CNST_THRESH_VAL(EVENT_THRESH_MASK)
+
+#define CNST_EBB_VAL(v)		(((v) & EVENT_EBB_MASK) << 24)
+#define CNST_EBB_MASK		CNST_EBB_VAL(EVENT_EBB_MASK)
+
+#define CNST_IFM_VAL(v)		(((v) & EVENT_IFM_MASK) << 25)
+#define CNST_IFM_MASK		CNST_IFM_VAL(EVENT_IFM_MASK)
+
+#define CNST_L1_QUAL_VAL(v)	(((v) & 3) << 22)
+#define CNST_L1_QUAL_MASK	CNST_L1_QUAL_VAL(3)
+
+#define CNST_SAMPLE_VAL(v)	(((v) & EVENT_SAMPLE_MASK) << 16)
+#define CNST_SAMPLE_MASK	CNST_SAMPLE_VAL(EVENT_SAMPLE_MASK)
+
+/*
+ * For NC we are counting up to 4 events. This requires three bits, and we need
+ * the fifth event to overflow and set the 4th bit. To achieve that we bias the
+ * fields by 3 in test_adder.
+ */
+#define CNST_NC_SHIFT		12
+#define CNST_NC_VAL		(1 << CNST_NC_SHIFT)
+#define CNST_NC_MASK		(8 << CNST_NC_SHIFT)
+#define ISA207_TEST_ADDER	(3 << CNST_NC_SHIFT)
+
+/*
+ * For the per-PMC fields we have two bits. The low bit is added, so if two
+ * events ask for the same PMC the sum will overflow, setting the high bit,
+ * indicating an error. So our mask sets the high bit.
+ */
+#define CNST_PMC_SHIFT(pmc)	((pmc - 1) * 2)
+#define CNST_PMC_VAL(pmc)	(1 << CNST_PMC_SHIFT(pmc))
+#define CNST_PMC_MASK(pmc)	(2 << CNST_PMC_SHIFT(pmc))
+
+/* Our add_fields is defined as: */
+#define ISA207_ADD_FIELDS	\
+	CNST_PMC_VAL(1) | CNST_PMC_VAL(2) | CNST_PMC_VAL(3) | \
+	CNST_PMC_VAL(4) | CNST_PMC_VAL(5) | CNST_PMC_VAL(6) | CNST_NC_VAL
+
+
+/* Bits in MMCR1 for PowerISA v2.07 */
+#define MMCR1_UNIT_SHIFT(pmc)		(60 - (4 * ((pmc) - 1)))
+#define MMCR1_COMBINE_SHIFT(pmc)	(35 - ((pmc) - 1))
+#define MMCR1_PMCSEL_SHIFT(pmc)		(24 - (((pmc) - 1)) * 8)
+#define MMCR1_FAB_SHIFT			36
+#define MMCR1_DC_QUAL_SHIFT		47
+#define MMCR1_IC_QUAL_SHIFT		46
+
+/* Bits in MMCRA for PowerISA v2.07 */
+#define MMCRA_SAMP_MODE_SHIFT		1
+#define MMCRA_SAMP_ELIG_SHIFT		4
+#define MMCRA_THR_CTL_SHIFT		8
+#define MMCRA_THR_SEL_SHIFT		16
+#define MMCRA_THR_CMP_SHIFT		32
+#define MMCRA_SDAR_MODE_TLB		(1ull << 42)
+#define MMCRA_IFM_SHIFT			30
+
+/* Bits in MMCR2 for PowerISA v2.07 */
+#define MMCR2_FCS(pmc)			(1ull << (63 - (((pmc) - 1) * 9)))
+#define MMCR2_FCP(pmc)			(1ull << (62 - (((pmc) - 1) * 9)))
+#define MMCR2_FCH(pmc)			(1ull << (57 - (((pmc) - 1) * 9)))
+
+#define MAX_ALT				2
+#define MAX_PMU_COUNTERS		6
+
+int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp);
+int isa207_compute_mmcr(u64 event[], int n_ev,
+				unsigned int hwc[], unsigned long mmcr[],
+				struct perf_event *pevents[]);
+void isa207_disable_pmc(unsigned int pmc, unsigned long mmcr[]);
+
+#endif
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 7cf3b4378192..5fde2b192fec 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -12,10 +12,7 @@
 
 #define pr_fmt(fmt)	"power8-pmu: " fmt
 
-#include <linux/kernel.h>
-#include <linux/perf_event.h>
-#include <asm/firmware.h>
-#include <asm/cputable.h>
+#include "isa207-common.h"
 
 /*
  * Some power8 event codes.
@@ -28,465 +25,11 @@ enum {
 
 #undef EVENT
 
-/*
- * Raw event encoding for POWER8:
- *
- *        60        56        52        48        44        40        36        32
- * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- *   | | [ ]                           [      thresh_cmp     ]   [  thresh_ctl   ]
- *   | |  |                                                              |
- *   | |  *- IFM (Linux)                 thresh start/stop OR FAB match -*
- *   | *- BHRB (Linux)
- *   *- EBB (Linux)
- *
- *        28        24        20        16        12         8         4         0
- * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- *   [   ] [  sample ]   [cache]   [ pmc ]   [unit ]   c     m   [    pmcxsel    ]
- *     |        |           |                          |     |
- *     |        |           |                          |     *- mark
- *     |        |           *- L1/L2/L3 cache_sel      |
- *     |        |                                      |
- *     |        *- sampling mode for marked events     *- combine
- *     |
- *     *- thresh_sel
- *
- * Below uses IBM bit numbering.
- *
- * MMCR1[x:y] = unit    (PMCxUNIT)
- * MMCR1[x]   = combine (PMCxCOMB)
- *
- * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011
- *	# PM_MRK_FAB_RSP_MATCH
- *	MMCR1[20:27] = thresh_ctl   (FAB_CRESP_MATCH / FAB_TYPE_MATCH)
- * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001
- *	# PM_MRK_FAB_RSP_MATCH_CYC
- *	MMCR1[20:27] = thresh_ctl   (FAB_CRESP_MATCH / FAB_TYPE_MATCH)
- * else
- *	MMCRA[48:55] = thresh_ctl   (THRESH START/END)
- *
- * if thresh_sel:
- *	MMCRA[45:47] = thresh_sel
- *
- * if thresh_cmp:
- *	MMCRA[22:24] = thresh_cmp[0:2]
- *	MMCRA[25:31] = thresh_cmp[3:9]
- *
- * if unit == 6 or unit == 7
- *	MMCRC[53:55] = cache_sel[1:3]      (L2EVENT_SEL)
- * else if unit == 8 or unit == 9:
- *	if cache_sel[0] == 0: # L3 bank
- *		MMCRC[47:49] = cache_sel[1:3]  (L3EVENT_SEL0)
- *	else if cache_sel[0] == 1:
- *		MMCRC[50:51] = cache_sel[2:3]  (L3EVENT_SEL1)
- * else if cache_sel[1]: # L1 event
- *	MMCR1[16] = cache_sel[2]
- *	MMCR1[17] = cache_sel[3]
- *
- * if mark:
- *	MMCRA[63]    = 1		(SAMPLE_ENABLE)
- *	MMCRA[57:59] = sample[0:2]	(RAND_SAMP_ELIG)
- *	MMCRA[61:62] = sample[3:4]	(RAND_SAMP_MODE)
- *
- * if EBB and BHRB:
- *	MMCRA[32:33] = IFM
- *
- */
-
-#define EVENT_EBB_MASK		1ull
-#define EVENT_EBB_SHIFT		PERF_EVENT_CONFIG_EBB_SHIFT
-#define EVENT_BHRB_MASK		1ull
-#define EVENT_BHRB_SHIFT	62
-#define EVENT_WANTS_BHRB	(EVENT_BHRB_MASK << EVENT_BHRB_SHIFT)
-#define EVENT_IFM_MASK		3ull
-#define EVENT_IFM_SHIFT		60
-#define EVENT_THR_CMP_SHIFT	40	/* Threshold CMP value */
-#define EVENT_THR_CMP_MASK	0x3ff
-#define EVENT_THR_CTL_SHIFT	32	/* Threshold control value (start/stop) */
-#define EVENT_THR_CTL_MASK	0xffull
-#define EVENT_THR_SEL_SHIFT	29	/* Threshold select value */
-#define EVENT_THR_SEL_MASK	0x7
-#define EVENT_THRESH_SHIFT	29	/* All threshold bits */
-#define EVENT_THRESH_MASK	0x1fffffull
-#define EVENT_SAMPLE_SHIFT	24	/* Sampling mode & eligibility */
-#define EVENT_SAMPLE_MASK	0x1f
-#define EVENT_CACHE_SEL_SHIFT	20	/* L2/L3 cache select */
-#define EVENT_CACHE_SEL_MASK	0xf
-#define EVENT_IS_L1		(4 << EVENT_CACHE_SEL_SHIFT)
-#define EVENT_PMC_SHIFT		16	/* PMC number (1-based) */
-#define EVENT_PMC_MASK		0xf
-#define EVENT_UNIT_SHIFT	12	/* Unit */
-#define EVENT_UNIT_MASK		0xf
-#define EVENT_COMBINE_SHIFT	11	/* Combine bit */
-#define EVENT_COMBINE_MASK	0x1
-#define EVENT_MARKED_SHIFT	8	/* Marked bit */
-#define EVENT_MARKED_MASK	0x1
-#define EVENT_IS_MARKED		(EVENT_MARKED_MASK << EVENT_MARKED_SHIFT)
-#define EVENT_PSEL_MASK		0xff	/* PMCxSEL value */
-
-/* Bits defined by Linux */
-#define EVENT_LINUX_MASK	\
-	((EVENT_EBB_MASK  << EVENT_EBB_SHIFT)			|	\
-	 (EVENT_BHRB_MASK << EVENT_BHRB_SHIFT)			|	\
-	 (EVENT_IFM_MASK  << EVENT_IFM_SHIFT))
-
-#define EVENT_VALID_MASK	\
-	((EVENT_THRESH_MASK    << EVENT_THRESH_SHIFT)		|	\
-	 (EVENT_SAMPLE_MASK    << EVENT_SAMPLE_SHIFT)		|	\
-	 (EVENT_CACHE_SEL_MASK << EVENT_CACHE_SEL_SHIFT)	|	\
-	 (EVENT_PMC_MASK       << EVENT_PMC_SHIFT)		|	\
-	 (EVENT_UNIT_MASK      << EVENT_UNIT_SHIFT)		|	\
-	 (EVENT_COMBINE_MASK   << EVENT_COMBINE_SHIFT)		|	\
-	 (EVENT_MARKED_MASK    << EVENT_MARKED_SHIFT)		|	\
-	  EVENT_LINUX_MASK					|	\
-	  EVENT_PSEL_MASK)
-
 /* MMCRA IFM bits - POWER8 */
 #define	POWER8_MMCRA_IFM1		0x0000000040000000UL
 #define	POWER8_MMCRA_IFM2		0x0000000080000000UL
 #define	POWER8_MMCRA_IFM3		0x00000000C0000000UL
 
-#define ONLY_PLM \
-	(PERF_SAMPLE_BRANCH_USER        |\
-	 PERF_SAMPLE_BRANCH_KERNEL      |\
-	 PERF_SAMPLE_BRANCH_HV)
-
-/*
- * Layout of constraint bits:
- *
- *        60        56        52        48        44        40        36        32
- * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- *   [   fab_match   ]         [       thresh_cmp      ] [   thresh_ctl    ] [   ]
- *                                                                             |
- *                                                                 thresh_sel -*
- *
- *        28        24        20        16        12         8         4         0
- * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- *               [ ] |   [ ]   [  sample ]   [     ]   [6] [5]   [4] [3]   [2] [1]
- *                |  |    |                     |
- *      BHRB IFM -*  |    |                     |      Count of events for each PMC.
- *              EBB -*    |                     |        p1, p2, p3, p4, p5, p6.
- *      L1 I/D qualifier -*                     |
- *                     nc - number of counters -*
- *
- * The PMC fields P1..P6, and NC, are adder fields. As we accumulate constraints
- * we want the low bit of each field to be added to any existing value.
- *
- * Everything else is a value field.
- */
-
-#define CNST_FAB_MATCH_VAL(v)	(((v) & EVENT_THR_CTL_MASK) << 56)
-#define CNST_FAB_MATCH_MASK	CNST_FAB_MATCH_VAL(EVENT_THR_CTL_MASK)
-
-/* We just throw all the threshold bits into the constraint */
-#define CNST_THRESH_VAL(v)	(((v) & EVENT_THRESH_MASK) << 32)
-#define CNST_THRESH_MASK	CNST_THRESH_VAL(EVENT_THRESH_MASK)
-
-#define CNST_EBB_VAL(v)		(((v) & EVENT_EBB_MASK) << 24)
-#define CNST_EBB_MASK		CNST_EBB_VAL(EVENT_EBB_MASK)
-
-#define CNST_IFM_VAL(v)		(((v) & EVENT_IFM_MASK) << 25)
-#define CNST_IFM_MASK		CNST_IFM_VAL(EVENT_IFM_MASK)
-
-#define CNST_L1_QUAL_VAL(v)	(((v) & 3) << 22)
-#define CNST_L1_QUAL_MASK	CNST_L1_QUAL_VAL(3)
-
-#define CNST_SAMPLE_VAL(v)	(((v) & EVENT_SAMPLE_MASK) << 16)
-#define CNST_SAMPLE_MASK	CNST_SAMPLE_VAL(EVENT_SAMPLE_MASK)
-
-/*
- * For NC we are counting up to 4 events. This requires three bits, and we need
- * the fifth event to overflow and set the 4th bit. To achieve that we bias the
- * fields by 3 in test_adder.
- */
-#define CNST_NC_SHIFT		12
-#define CNST_NC_VAL		(1 << CNST_NC_SHIFT)
-#define CNST_NC_MASK		(8 << CNST_NC_SHIFT)
-#define POWER8_TEST_ADDER	(3 << CNST_NC_SHIFT)
-
-/*
- * For the per-PMC fields we have two bits. The low bit is added, so if two
- * events ask for the same PMC the sum will overflow, setting the high bit,
- * indicating an error. So our mask sets the high bit.
- */
-#define CNST_PMC_SHIFT(pmc)	((pmc - 1) * 2)
-#define CNST_PMC_VAL(pmc)	(1 << CNST_PMC_SHIFT(pmc))
-#define CNST_PMC_MASK(pmc)	(2 << CNST_PMC_SHIFT(pmc))
-
-/* Our add_fields is defined as: */
-#define POWER8_ADD_FIELDS	\
-	CNST_PMC_VAL(1) | CNST_PMC_VAL(2) | CNST_PMC_VAL(3) | \
-	CNST_PMC_VAL(4) | CNST_PMC_VAL(5) | CNST_PMC_VAL(6) | CNST_NC_VAL
-
-
-/* Bits in MMCR1 for POWER8 */
-#define MMCR1_UNIT_SHIFT(pmc)		(60 - (4 * ((pmc) - 1)))
-#define MMCR1_COMBINE_SHIFT(pmc)	(35 - ((pmc) - 1))
-#define MMCR1_PMCSEL_SHIFT(pmc)		(24 - (((pmc) - 1)) * 8)
-#define MMCR1_FAB_SHIFT			36
-#define MMCR1_DC_QUAL_SHIFT		47
-#define MMCR1_IC_QUAL_SHIFT		46
-
-/* Bits in MMCRA for POWER8 */
-#define MMCRA_SAMP_MODE_SHIFT		1
-#define MMCRA_SAMP_ELIG_SHIFT		4
-#define MMCRA_THR_CTL_SHIFT		8
-#define MMCRA_THR_SEL_SHIFT		16
-#define MMCRA_THR_CMP_SHIFT		32
-#define MMCRA_SDAR_MODE_TLB		(1ull << 42)
-#define MMCRA_IFM_SHIFT			30
-
-/* Bits in MMCR2 for POWER8 */
-#define MMCR2_FCS(pmc)			(1ull << (63 - (((pmc) - 1) * 9)))
-#define MMCR2_FCP(pmc)			(1ull << (62 - (((pmc) - 1) * 9)))
-#define MMCR2_FCH(pmc)			(1ull << (57 - (((pmc) - 1) * 9)))
-
-
-static inline bool event_is_fab_match(u64 event)
-{
-	/* Only check pmc, unit and pmcxsel, ignore the edge bit (0) */
-	event &= 0xff0fe;
-
-	/* PM_MRK_FAB_RSP_MATCH & PM_MRK_FAB_RSP_MATCH_CYC */
-	return (event == 0x30056 || event == 0x4f052);
-}
-
-static int power8_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
-{
-	unsigned int unit, pmc, cache, ebb;
-	unsigned long mask, value;
-
-	mask = value = 0;
-
-	if (event & ~EVENT_VALID_MASK)
-		return -1;
-
-	pmc   = (event >> EVENT_PMC_SHIFT)        & EVENT_PMC_MASK;
-	unit  = (event >> EVENT_UNIT_SHIFT)       & EVENT_UNIT_MASK;
-	cache = (event >> EVENT_CACHE_SEL_SHIFT)  & EVENT_CACHE_SEL_MASK;
-	ebb   = (event >> EVENT_EBB_SHIFT)        & EVENT_EBB_MASK;
-
-	if (pmc) {
-		u64 base_event;
-
-		if (pmc > 6)
-			return -1;
-
-		/* Ignore Linux defined bits when checking event below */
-		base_event = event & ~EVENT_LINUX_MASK;
-
-		if (pmc >= 5 && base_event != PM_RUN_INST_CMPL &&
-				base_event != PM_RUN_CYC)
-			return -1;
-
-		mask  |= CNST_PMC_MASK(pmc);
-		value |= CNST_PMC_VAL(pmc);
-	}
-
-	if (pmc <= 4) {
-		/*
-		 * Add to number of counters in use. Note this includes events with
-		 * a PMC of 0 - they still need a PMC, it's just assigned later.
-		 * Don't count events on PMC 5 & 6, there is only one valid event
-		 * on each of those counters, and they are handled above.
-		 */
-		mask  |= CNST_NC_MASK;
-		value |= CNST_NC_VAL;
-	}
-
-	if (unit >= 6 && unit <= 9) {
-		/*
-		 * L2/L3 events contain a cache selector field, which is
-		 * supposed to be programmed into MMCRC. However MMCRC is only
-		 * HV writable, and there is no API for guest kernels to modify
-		 * it. The solution is for the hypervisor to initialise the
-		 * field to zeroes, and for us to only ever allow events that
-		 * have a cache selector of zero. The bank selector (bit 3) is
-		 * irrelevant, as long as the rest of the value is 0.
-		 */
-		if (cache & 0x7)
-			return -1;
-
-	} else if (event & EVENT_IS_L1) {
-		mask  |= CNST_L1_QUAL_MASK;
-		value |= CNST_L1_QUAL_VAL(cache);
-	}
-
-	if (event & EVENT_IS_MARKED) {
-		mask  |= CNST_SAMPLE_MASK;
-		value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
-	}
-
-	/*
-	 * Special case for PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC,
-	 * the threshold control bits are used for the match value.
-	 */
-	if (event_is_fab_match(event)) {
-		mask  |= CNST_FAB_MATCH_MASK;
-		value |= CNST_FAB_MATCH_VAL(event >> EVENT_THR_CTL_SHIFT);
-	} else {
-		/*
-		 * Check the mantissa upper two bits are not zero, unless the
-		 * exponent is also zero. See the THRESH_CMP_MANTISSA doc.
-		 */
-		unsigned int cmp, exp;
-
-		cmp = (event >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
-		exp = cmp >> 7;
-
-		if (exp && (cmp & 0x60) == 0)
-			return -1;
-
-		mask  |= CNST_THRESH_MASK;
-		value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT);
-	}
-
-	if (!pmc && ebb)
-		/* EBB events must specify the PMC */
-		return -1;
-
-	if (event & EVENT_WANTS_BHRB) {
-		if (!ebb)
-			/* Only EBB events can request BHRB */
-			return -1;
-
-		mask  |= CNST_IFM_MASK;
-		value |= CNST_IFM_VAL(event >> EVENT_IFM_SHIFT);
-	}
-
-	/*
-	 * All events must agree on EBB, either all request it or none.
-	 * EBB events are pinned & exclusive, so this should never actually
-	 * hit, but we leave it as a fallback in case.
-	 */
-	mask  |= CNST_EBB_VAL(ebb);
-	value |= CNST_EBB_MASK;
-
-	*maskp = mask;
-	*valp = value;
-
-	return 0;
-}
-
-static int power8_compute_mmcr(u64 event[], int n_ev,
-			       unsigned int hwc[], unsigned long mmcr[],
-			       struct perf_event *pevents[])
-{
-	unsigned long mmcra, mmcr1, mmcr2, unit, combine, psel, cache, val;
-	unsigned int pmc, pmc_inuse;
-	int i;
-
-	pmc_inuse = 0;
-
-	/* First pass to count resource use */
-	for (i = 0; i < n_ev; ++i) {
-		pmc = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
-		if (pmc)
-			pmc_inuse |= 1 << pmc;
-	}
-
-	/* In continuous sampling mode, update SDAR on TLB miss */
-	mmcra = MMCRA_SDAR_MODE_TLB;
-	mmcr1 = mmcr2 = 0;
-
-	/* Second pass: assign PMCs, set all MMCR1 fields */
-	for (i = 0; i < n_ev; ++i) {
-		pmc     = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
-		unit    = (event[i] >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK;
-		combine = (event[i] >> EVENT_COMBINE_SHIFT) & EVENT_COMBINE_MASK;
-		psel    =  event[i] & EVENT_PSEL_MASK;
-
-		if (!pmc) {
-			for (pmc = 1; pmc <= 4; ++pmc) {
-				if (!(pmc_inuse & (1 << pmc)))
-					break;
-			}
-
-			pmc_inuse |= 1 << pmc;
-		}
-
-		if (pmc <= 4) {
-			mmcr1 |= unit << MMCR1_UNIT_SHIFT(pmc);
-			mmcr1 |= combine << MMCR1_COMBINE_SHIFT(pmc);
-			mmcr1 |= psel << MMCR1_PMCSEL_SHIFT(pmc);
-		}
-
-		if (event[i] & EVENT_IS_L1) {
-			cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
-			mmcr1 |= (cache & 1) << MMCR1_IC_QUAL_SHIFT;
-			cache >>= 1;
-			mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT;
-		}
-
-		if (event[i] & EVENT_IS_MARKED) {
-			mmcra |= MMCRA_SAMPLE_ENABLE;
-
-			val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK;
-			if (val) {
-				mmcra |= (val &  3) << MMCRA_SAMP_MODE_SHIFT;
-				mmcra |= (val >> 2) << MMCRA_SAMP_ELIG_SHIFT;
-			}
-		}
-
-		/*
-		 * PM_MRK_FAB_RSP_MATCH and PM_MRK_FAB_RSP_MATCH_CYC,
-		 * the threshold bits are used for the match value.
-		 */
-		if (event_is_fab_match(event[i])) {
-			mmcr1 |= ((event[i] >> EVENT_THR_CTL_SHIFT) &
-				  EVENT_THR_CTL_MASK) << MMCR1_FAB_SHIFT;
-		} else {
-			val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK;
-			mmcra |= val << MMCRA_THR_CTL_SHIFT;
-			val = (event[i] >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK;
-			mmcra |= val << MMCRA_THR_SEL_SHIFT;
-			val = (event[i] >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
-			mmcra |= val << MMCRA_THR_CMP_SHIFT;
-		}
-
-		if (event[i] & EVENT_WANTS_BHRB) {
-			val = (event[i] >> EVENT_IFM_SHIFT) & EVENT_IFM_MASK;
-			mmcra |= val << MMCRA_IFM_SHIFT;
-		}
-
-		if (pevents[i]->attr.exclude_user)
-			mmcr2 |= MMCR2_FCP(pmc);
-
-		if (pevents[i]->attr.exclude_hv)
-			mmcr2 |= MMCR2_FCH(pmc);
-
-		if (pevents[i]->attr.exclude_kernel) {
-			if (cpu_has_feature(CPU_FTR_HVMODE))
-				mmcr2 |= MMCR2_FCH(pmc);
-			else
-				mmcr2 |= MMCR2_FCS(pmc);
-		}
-
-		hwc[i] = pmc - 1;
-	}
-
-	/* Return MMCRx values */
-	mmcr[0] = 0;
-
-	/* pmc_inuse is 1-based */
-	if (pmc_inuse & 2)
-		mmcr[0] = MMCR0_PMC1CE;
-
-	if (pmc_inuse & 0x7c)
-		mmcr[0] |= MMCR0_PMCjCE;
-
-	/* If we're not using PMC 5 or 6, freeze them */
-	if (!(pmc_inuse & 0x60))
-		mmcr[0] |= MMCR0_FC56;
-
-	mmcr[1] = mmcr1;
-	mmcr[2] = mmcra;
-	mmcr[3] = mmcr2;
-
-	return 0;
-}
-
-#define MAX_ALT	2
-
 /* Table of alternatives, sorted by column 0 */
 static const unsigned int event_alternatives[][MAX_ALT] = {
 	{ PM_MRK_ST_CMPL,		PM_MRK_ST_CMPL_ALT },
@@ -567,12 +110,6 @@ static int power8_get_alternatives(u64 event, unsigned int flags, u64 alt[])
 	return num_alt;
 }
 
-static void power8_disable_pmc(unsigned int pmc, unsigned long mmcr[])
-{
-	if (pmc <= 3)
-		mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1));
-}
-
 GENERIC_EVENT_ATTR(cpu-cycles,			PM_CYC);
 GENERIC_EVENT_ATTR(stalled-cycles-frontend,	PM_GCT_NOSLOT_CYC);
 GENERIC_EVENT_ATTR(stalled-cycles-backend,	PM_CMPLU_STALL);
@@ -841,16 +378,16 @@ static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 
 static struct power_pmu power8_pmu = {
 	.name			= "POWER8",
-	.n_counter		= 6,
+	.n_counter		= MAX_PMU_COUNTERS,
 	.max_alternatives	= MAX_ALT + 1,
-	.add_fields		= POWER8_ADD_FIELDS,
-	.test_adder		= POWER8_TEST_ADDER,
-	.compute_mmcr		= power8_compute_mmcr,
+	.add_fields		= ISA207_ADD_FIELDS,
+	.test_adder		= ISA207_TEST_ADDER,
+	.compute_mmcr		= isa207_compute_mmcr,
 	.config_bhrb		= power8_config_bhrb,
 	.bhrb_filter_map	= power8_bhrb_filter_map,
-	.get_constraint		= power8_get_constraint,
+	.get_constraint		= isa207_get_constraint,
 	.get_alternatives	= power8_get_alternatives,
-	.disable_pmc		= power8_disable_pmc,
+	.disable_pmc		= isa207_disable_pmc,
 	.flags			= PPMU_HAS_SIER | PPMU_ARCH_207S,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h
new file mode 100644
index 000000000000..cda6fcb809ca
--- /dev/null
+++ b/arch/powerpc/perf/power9-events-list.h
@@ -0,0 +1,55 @@
+/*
+ * Performance counter support for POWER9 processors.
+ *
+ * Copyright 2016 Madhavan Srinivasan, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/*
+ * Power9 event codes.
+ */
+EVENT(PM_CYC,					0x0001e)
+EVENT(PM_ICT_NOSLOT_CYC,			0x100f8)
+EVENT(PM_CMPLU_STALL,				0x1e054)
+EVENT(PM_INST_CMPL,				0x00002)
+EVENT(PM_BRU_CMPL,				0x40060)
+EVENT(PM_BR_MPRED_CMPL,				0x400f6)
+
+/* All L1 D cache load references counted at finish, gated by reject */
+EVENT(PM_LD_REF_L1,				0x100fc)
+/* Load Missed L1 */
+EVENT(PM_LD_MISS_L1_FIN,			0x2c04e)
+/* Store Missed L1 */
+EVENT(PM_ST_MISS_L1,				0x300f0)
+/* L1 cache data prefetches */
+EVENT(PM_L1_PREF,				0x20054)
+/* Instruction fetches from L1 */
+EVENT(PM_INST_FROM_L1,				0x04080)
+/* Demand iCache Miss */
+EVENT(PM_L1_ICACHE_MISS,			0x200fd)
+/* Instruction Demand sectors wriittent into IL1 */
+EVENT(PM_L1_DEMAND_WRITE,			0x0408c)
+/* Instruction prefetch written into IL1 */
+EVENT(PM_IC_PREF_WRITE,				0x0408e)
+/* The data cache was reloaded from local core's L3 due to a demand load */
+EVENT(PM_DATA_FROM_L3,				0x4c042)
+/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */
+EVENT(PM_DATA_FROM_L3MISS,			0x300fe)
+/* All successful D-side store dispatches for this thread */
+EVENT(PM_L2_ST,					0x16081)
+/* All successful D-side store dispatches for this thread that were L2 Miss */
+EVENT(PM_L2_ST_MISS,				0x26081)
+/* Total HW L3 prefetches(Load+store) */
+EVENT(PM_L3_PREF_ALL,				0x4e052)
+/* Data PTEG reload */
+EVENT(PM_DTLB_MISS,				0x300fc)
+/* ITLB Reloaded */
+EVENT(PM_ITLB_MISS,				0x400fc)
+/* Run_Instructions */
+EVENT(PM_RUN_INST_CMPL,				0x500fa)
+/* Run_cycles */
+EVENT(PM_RUN_CYC,				0x600f4)
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
new file mode 100644
index 000000000000..788346303852
--- /dev/null
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -0,0 +1,330 @@
+/*
+ * Performance counter support for POWER9 processors.
+ *
+ * Copyright 2009 Paul Mackerras, IBM Corporation.
+ * Copyright 2013 Michael Ellerman, IBM Corporation.
+ * Copyright 2016 Madhavan Srinivasan, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or later version.
+ */
+
+#define pr_fmt(fmt)	"power9-pmu: " fmt
+
+#include "isa207-common.h"
+
+/*
+ * Some power9 event codes.
+ */
+#define EVENT(_name, _code)	_name = _code,
+
+enum {
+#include "power9-events-list.h"
+};
+
+#undef EVENT
+
+/* MMCRA IFM bits - POWER9 */
+#define POWER9_MMCRA_IFM1		0x0000000040000000UL
+#define POWER9_MMCRA_IFM2		0x0000000080000000UL
+#define POWER9_MMCRA_IFM3		0x00000000C0000000UL
+
+GENERIC_EVENT_ATTR(cpu-cycles,			PM_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-frontend,	PM_ICT_NOSLOT_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-backend,	PM_CMPLU_STALL);
+GENERIC_EVENT_ATTR(instructions,		PM_INST_CMPL);
+GENERIC_EVENT_ATTR(branch-instructions,		PM_BRU_CMPL);
+GENERIC_EVENT_ATTR(branch-misses,		PM_BR_MPRED_CMPL);
+GENERIC_EVENT_ATTR(cache-references,		PM_LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses,		PM_LD_MISS_L1_FIN);
+
+CACHE_EVENT_ATTR(L1-dcache-load-misses,		PM_LD_MISS_L1_FIN);
+CACHE_EVENT_ATTR(L1-dcache-loads,		PM_LD_REF_L1);
+CACHE_EVENT_ATTR(L1-dcache-prefetches,		PM_L1_PREF);
+CACHE_EVENT_ATTR(L1-dcache-store-misses,	PM_ST_MISS_L1);
+CACHE_EVENT_ATTR(L1-icache-load-misses,		PM_L1_ICACHE_MISS);
+CACHE_EVENT_ATTR(L1-icache-loads,		PM_INST_FROM_L1);
+CACHE_EVENT_ATTR(L1-icache-prefetches,		PM_IC_PREF_WRITE);
+CACHE_EVENT_ATTR(LLC-load-misses,		PM_DATA_FROM_L3MISS);
+CACHE_EVENT_ATTR(LLC-loads,			PM_DATA_FROM_L3);
+CACHE_EVENT_ATTR(LLC-prefetches,		PM_L3_PREF_ALL);
+CACHE_EVENT_ATTR(LLC-store-misses,		PM_L2_ST_MISS);
+CACHE_EVENT_ATTR(LLC-stores,			PM_L2_ST);
+CACHE_EVENT_ATTR(branch-load-misses,		PM_BR_MPRED_CMPL);
+CACHE_EVENT_ATTR(branch-loads,			PM_BRU_CMPL);
+CACHE_EVENT_ATTR(dTLB-load-misses,		PM_DTLB_MISS);
+CACHE_EVENT_ATTR(iTLB-load-misses,		PM_ITLB_MISS);
+
+static struct attribute *power9_events_attr[] = {
+	GENERIC_EVENT_PTR(PM_CYC),
+	GENERIC_EVENT_PTR(PM_ICT_NOSLOT_CYC),
+	GENERIC_EVENT_PTR(PM_CMPLU_STALL),
+	GENERIC_EVENT_PTR(PM_INST_CMPL),
+	GENERIC_EVENT_PTR(PM_BRU_CMPL),
+	GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL),
+	GENERIC_EVENT_PTR(PM_LD_REF_L1),
+	GENERIC_EVENT_PTR(PM_LD_MISS_L1_FIN),
+	CACHE_EVENT_PTR(PM_LD_MISS_L1_FIN),
+	CACHE_EVENT_PTR(PM_LD_REF_L1),
+	CACHE_EVENT_PTR(PM_L1_PREF),
+	CACHE_EVENT_PTR(PM_ST_MISS_L1),
+	CACHE_EVENT_PTR(PM_L1_ICACHE_MISS),
+	CACHE_EVENT_PTR(PM_INST_FROM_L1),
+	CACHE_EVENT_PTR(PM_IC_PREF_WRITE),
+	CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS),
+	CACHE_EVENT_PTR(PM_DATA_FROM_L3),
+	CACHE_EVENT_PTR(PM_L3_PREF_ALL),
+	CACHE_EVENT_PTR(PM_L2_ST_MISS),
+	CACHE_EVENT_PTR(PM_L2_ST),
+	CACHE_EVENT_PTR(PM_BR_MPRED_CMPL),
+	CACHE_EVENT_PTR(PM_BRU_CMPL),
+	CACHE_EVENT_PTR(PM_DTLB_MISS),
+	CACHE_EVENT_PTR(PM_ITLB_MISS),
+	NULL
+};
+
+static struct attribute_group power9_pmu_events_group = {
+	.name = "events",
+	.attrs = power9_events_attr,
+};
+
+PMU_FORMAT_ATTR(event,		"config:0-49");
+PMU_FORMAT_ATTR(pmcxsel,	"config:0-7");
+PMU_FORMAT_ATTR(mark,		"config:8");
+PMU_FORMAT_ATTR(combine,	"config:11");
+PMU_FORMAT_ATTR(unit,		"config:12-15");
+PMU_FORMAT_ATTR(pmc,		"config:16-19");
+PMU_FORMAT_ATTR(cache_sel,	"config:20-23");
+PMU_FORMAT_ATTR(sample_mode,	"config:24-28");
+PMU_FORMAT_ATTR(thresh_sel,	"config:29-31");
+PMU_FORMAT_ATTR(thresh_stop,	"config:32-35");
+PMU_FORMAT_ATTR(thresh_start,	"config:36-39");
+PMU_FORMAT_ATTR(thresh_cmp,	"config:40-49");
+
+static struct attribute *power9_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_pmcxsel.attr,
+	&format_attr_mark.attr,
+	&format_attr_combine.attr,
+	&format_attr_unit.attr,
+	&format_attr_pmc.attr,
+	&format_attr_cache_sel.attr,
+	&format_attr_sample_mode.attr,
+	&format_attr_thresh_sel.attr,
+	&format_attr_thresh_stop.attr,
+	&format_attr_thresh_start.attr,
+	&format_attr_thresh_cmp.attr,
+	NULL,
+};
+
+struct attribute_group power9_pmu_format_group = {
+	.name = "format",
+	.attrs = power9_pmu_format_attr,
+};
+
+static const struct attribute_group *power9_pmu_attr_groups[] = {
+	&power9_pmu_format_group,
+	&power9_pmu_events_group,
+	NULL,
+};
+
+static int power9_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES] =			PM_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =	PM_ICT_NOSLOT_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =	PM_CMPLU_STALL,
+	[PERF_COUNT_HW_INSTRUCTIONS] =			PM_INST_CMPL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PM_BRU_CMPL,
+	[PERF_COUNT_HW_BRANCH_MISSES] =			PM_BR_MPRED_CMPL,
+	[PERF_COUNT_HW_CACHE_REFERENCES] =		PM_LD_REF_L1,
+	[PERF_COUNT_HW_CACHE_MISSES] =			PM_LD_MISS_L1_FIN,
+};
+
+static u64 power9_bhrb_filter_map(u64 branch_sample_type)
+{
+	u64 pmu_bhrb_filter = 0;
+
+	/* BHRB and regular PMU events share the same privilege state
+	 * filter configuration. BHRB is always recorded along with a
+	 * regular PMU event. As the privilege state filter is handled
+	 * in the basic PMC configuration of the accompanying regular
+	 * PMU event, we ignore any separate BHRB specific request.
+	 */
+
+	/* No branch filter requested */
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY)
+		return pmu_bhrb_filter;
+
+	/* Invalid branch filter options - HW does not support */
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
+		return -1;
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL)
+		return -1;
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_CALL)
+		return -1;
+
+	if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_CALL) {
+		pmu_bhrb_filter |= POWER9_MMCRA_IFM1;
+		return pmu_bhrb_filter;
+	}
+
+	/* Every thing else is unsupported */
+	return -1;
+}
+
+static void power9_config_bhrb(u64 pmu_bhrb_filter)
+{
+	/* Enable BHRB filter in PMU */
+	mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
+}
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[ C(L1D) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
+			[ C(RESULT_MISS)   ] = PM_LD_MISS_L1_FIN,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ST_MISS_L1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_PREF,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(L1I) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_INST_FROM_L1,
+			[ C(RESULT_MISS)   ] = PM_L1_ICACHE_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(LL) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3,
+			[ C(RESULT_MISS)   ] = PM_DATA_FROM_L3MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L2_ST,
+			[ C(RESULT_MISS)   ] = PM_L2_ST_MISS,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(DTLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_DTLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(ITLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = PM_ITLB_MISS,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(BPU) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = PM_BRU_CMPL,
+			[ C(RESULT_MISS)   ] = PM_BR_MPRED_CMPL,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(NODE) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+};
+
+#undef C
+
+static struct power_pmu power9_pmu = {
+	.name			= "POWER9",
+	.n_counter		= MAX_PMU_COUNTERS,
+	.add_fields		= ISA207_ADD_FIELDS,
+	.test_adder		= ISA207_TEST_ADDER,
+	.compute_mmcr		= isa207_compute_mmcr,
+	.config_bhrb		= power9_config_bhrb,
+	.bhrb_filter_map	= power9_bhrb_filter_map,
+	.get_constraint		= isa207_get_constraint,
+	.disable_pmc		= isa207_disable_pmc,
+	.flags			= PPMU_HAS_SIER | PPMU_ARCH_207S,
+	.n_generic		= ARRAY_SIZE(power9_generic_events),
+	.generic_events		= power9_generic_events,
+	.cache_events		= &power9_cache_events,
+	.attr_groups		= power9_pmu_attr_groups,
+	.bhrb_nr		= 32,
+};
+
+static int __init init_power9_pmu(void)
+{
+	int rc;
+
+	/* Comes from cpu_specs[] */
+	if (!cur_cpu_spec->oprofile_cpu_type ||
+	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power9"))
+		return -ENODEV;
+
+	rc = register_power_pmu(&power9_pmu);
+	if (rc)
+		return rc;
+
+	/* Tell userspace that EBB is supported */
+	cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB;
+
+	return 0;
+}
+early_initcall(init_power9_pmu);
diff --git a/arch/powerpc/platforms/40x/ep405.c b/arch/powerpc/platforms/40x/ep405.c
index ddc12a1926ef..1c8aec6e9bb7 100644
--- a/arch/powerpc/platforms/40x/ep405.c
+++ b/arch/powerpc/platforms/40x/ep405.c
@@ -105,9 +105,7 @@ static void __init ep405_setup_arch(void)
 
 static int __init ep405_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "ep405"))
+	if (!of_machine_is_compatible("ep405"))
 		return 0;
 
 	return 1;
diff --git a/arch/powerpc/platforms/40x/ppc40x_simple.c b/arch/powerpc/platforms/40x/ppc40x_simple.c
index b0c46375dd95..2a050007bbae 100644
--- a/arch/powerpc/platforms/40x/ppc40x_simple.c
+++ b/arch/powerpc/platforms/40x/ppc40x_simple.c
@@ -63,7 +63,7 @@ static const char * const board[] __initconst = {
 
 static int __init ppc40x_probe(void)
 {
-	if (of_flat_dt_match(of_get_flat_dt_root(), board)) {
+	if (of_device_compatible_match(of_root, board)) {
 		pci_set_flags(PCI_REASSIGN_ALL_RSRC);
 		return 1;
 	}
diff --git a/arch/powerpc/platforms/40x/virtex.c b/arch/powerpc/platforms/40x/virtex.c
index 9aa7ae2f4164..91a08ea758a8 100644
--- a/arch/powerpc/platforms/40x/virtex.c
+++ b/arch/powerpc/platforms/40x/virtex.c
@@ -37,9 +37,7 @@ machine_device_initcall(virtex, virtex_device_probe);
 
 static int __init virtex_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "xlnx,virtex"))
+	if (!of_machine_is_compatible("xlnx,virtex"))
 		return 0;
 
 	return 1;
diff --git a/arch/powerpc/platforms/40x/walnut.c b/arch/powerpc/platforms/40x/walnut.c
index f7ac2d0fcb44..e5797815e2f1 100644
--- a/arch/powerpc/platforms/40x/walnut.c
+++ b/arch/powerpc/platforms/40x/walnut.c
@@ -46,9 +46,7 @@ machine_device_initcall(walnut, walnut_device_probe);
 
 static int __init walnut_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "ibm,walnut"))
+	if (!of_machine_is_compatible("ibm,walnut"))
 		return 0;
 
 	pci_set_flags(PCI_REASSIGN_ALL_RSRC);
diff --git a/arch/powerpc/platforms/44x/canyonlands.c b/arch/powerpc/platforms/44x/canyonlands.c
index 22ca5430c9cb..157f4ce46386 100644
--- a/arch/powerpc/platforms/44x/canyonlands.c
+++ b/arch/powerpc/platforms/44x/canyonlands.c
@@ -53,11 +53,10 @@ machine_device_initcall(canyonlands, ppc460ex_device_probe);
 
 static int __init ppc460ex_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	if (of_flat_dt_is_compatible(root, "amcc,canyonlands")) {
+	if (of_machine_is_compatible("amcc,canyonlands")) {
 		pci_set_flags(PCI_REASSIGN_ALL_RSRC);
 		return 1;
-		}
+	}
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/44x/ebony.c b/arch/powerpc/platforms/44x/ebony.c
index ae893226392d..1070225f5f9b 100644
--- a/arch/powerpc/platforms/44x/ebony.c
+++ b/arch/powerpc/platforms/44x/ebony.c
@@ -49,9 +49,7 @@ machine_device_initcall(ebony, ebony_device_probe);
  */
 static int __init ebony_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "ibm,ebony"))
+	if (!of_machine_is_compatible("ibm,ebony"))
 		return 0;
 
 	pci_set_flags(PCI_REASSIGN_ALL_RSRC);
diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c
index c7c6758b3cfe..5f296dd6b1c0 100644
--- a/arch/powerpc/platforms/44x/iss4xx.c
+++ b/arch/powerpc/platforms/44x/iss4xx.c
@@ -149,9 +149,7 @@ static void __init iss4xx_setup_arch(void)
  */
 static int __init iss4xx_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "ibm,iss-4xx"))
+	if (!of_machine_is_compatible("ibm,iss-4xx"))
 		return 0;
 
 	return 1;
diff --git a/arch/powerpc/platforms/44x/ppc44x_simple.c b/arch/powerpc/platforms/44x/ppc44x_simple.c
index 573c3d2689c6..8d6e4da9dfbe 100644
--- a/arch/powerpc/platforms/44x/ppc44x_simple.c
+++ b/arch/powerpc/platforms/44x/ppc44x_simple.c
@@ -67,11 +67,10 @@ static char *board[] __initdata = {
 
 static int __init ppc44x_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
 	int i = 0;
 
 	for (i = 0; i < ARRAY_SIZE(board); i++) {
-		if (of_flat_dt_is_compatible(root, board[i])) {
+		if (of_machine_is_compatible(board[i])) {
 			pci_set_flags(PCI_REASSIGN_ALL_RSRC);
 			return 1;
 		}
diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c
index c11ce6516c8f..e55933f9cd55 100644
--- a/arch/powerpc/platforms/44x/ppc476.c
+++ b/arch/powerpc/platforms/44x/ppc476.c
@@ -68,7 +68,7 @@ DECLARE_PCI_FIXUP_HEADER(0x1033, 0x0035, quirk_ppc_currituck_usb_fixup);
 #define AVR_PWRCTL_RESET (0x02)
 
 static struct i2c_client *avr_i2c_client;
-static void avr_halt_system(int pwrctl_flags)
+static void __noreturn avr_halt_system(int pwrctl_flags)
 {
 	/* Request the AVR to reset the system */
 	i2c_smbus_write_byte_data(avr_i2c_client,
@@ -84,7 +84,7 @@ static void avr_power_off_system(void)
 	avr_halt_system(AVR_PWRCTL_PWROFF);
 }
 
-static void avr_reset_system(char *cmd)
+static void __noreturn avr_reset_system(char *cmd)
 {
 	avr_halt_system(AVR_PWRCTL_RESET);
 }
@@ -275,12 +275,10 @@ static void ppc47x_pci_irq_fixup(struct pci_dev *dev)
  */
 static int __init ppc47x_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "ibm,akebono"))
+	if (of_machine_is_compatible("ibm,akebono"))
 		return 1;
 
-	if (of_flat_dt_is_compatible(root, "ibm,currituck")) {
+	if (of_machine_is_compatible("ibm,currituck")) {
 		ppc_md.pci_irq_fixup = ppc47x_pci_irq_fixup;
 		return 1;
 	}
diff --git a/arch/powerpc/platforms/44x/sam440ep.c b/arch/powerpc/platforms/44x/sam440ep.c
index 3ee4a03c1496..688ffeab0699 100644
--- a/arch/powerpc/platforms/44x/sam440ep.c
+++ b/arch/powerpc/platforms/44x/sam440ep.c
@@ -46,9 +46,7 @@ machine_device_initcall(sam440ep, sam440ep_device_probe);
 
 static int __init sam440ep_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "acube,sam440ep"))
+	if (!of_machine_is_compatible("acube,sam440ep"))
 		return 0;
 
 	pci_set_flags(PCI_REASSIGN_ALL_RSRC);
diff --git a/arch/powerpc/platforms/44x/virtex.c b/arch/powerpc/platforms/44x/virtex.c
index ad272c17c640..a7e08026097a 100644
--- a/arch/powerpc/platforms/44x/virtex.c
+++ b/arch/powerpc/platforms/44x/virtex.c
@@ -43,9 +43,7 @@ machine_device_initcall(virtex, virtex_device_probe);
 
 static int __init virtex_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "xlnx,virtex440"))
+	if (!of_machine_is_compatible("xlnx,virtex440"))
 		return 0;
 
 	return 1;
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index 501333cf42cf..5ecce543103e 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -44,9 +44,7 @@ machine_device_initcall(warp, warp_device_probe);
 
 static int __init warp_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "pika,warp"))
+	if (!of_machine_is_compatible("pika,warp"))
 		return 0;
 
 	/* For __dma_alloc_coherent */
diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c
index 6081fbd75330..add5a5374fa0 100644
--- a/arch/powerpc/platforms/512x/clock-commonclk.c
+++ b/arch/powerpc/platforms/512x/clock-commonclk.c
@@ -719,7 +719,7 @@ static void mpc512x_clk_setup_clock_tree(struct device_node *np, int busfreq)
 	 *   most one of a mux, div, and gate each into one 'struct clk'
 	 *   item
 	 * - PSC/MSCAN/SPDIF clock generation OTOH already is very
-	 *   specific and cannot get mapped to componsites (at least not
+	 *   specific and cannot get mapped to composites (at least not
 	 *   a single one, maybe two of them, but then some of these
 	 *   intermediate clock signals get referenced elsewhere (e.g.
 	 *   in the clock frequency measurement, CFM) and thus need
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads.c b/arch/powerpc/platforms/512x/mpc5121_ads.c
index 3e90ece10ae9..f65d5033cdb0 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads.c
@@ -57,9 +57,12 @@ static void __init mpc5121_ads_init_IRQ(void)
  */
 static int __init mpc5121_ads_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
+	if (!of_machine_is_compatible("fsl,mpc5121ads"))
+		return 0;
 
-	return of_flat_dt_is_compatible(root, "fsl,mpc5121ads");
+	mpc512x_init_early();
+
+	return 1;
 }
 
 define_machine(mpc5121_ads) {
@@ -67,7 +70,6 @@ define_machine(mpc5121_ads) {
 	.probe			= mpc5121_ads_probe,
 	.setup_arch		= mpc5121_ads_setup_arch,
 	.init			= mpc512x_init,
-	.init_early		= mpc512x_init_early,
 	.init_IRQ		= mpc5121_ads_init_IRQ,
 	.get_irq		= ipic_get_irq,
 	.calibrate_decr		= generic_calibrate_decr,
diff --git a/arch/powerpc/platforms/512x/mpc512x.h b/arch/powerpc/platforms/512x/mpc512x.h
index cc97f022d028..14ba49fd7938 100644
--- a/arch/powerpc/platforms/512x/mpc512x.h
+++ b/arch/powerpc/platforms/512x/mpc512x.h
@@ -18,6 +18,6 @@ extern void __init mpc512x_setup_arch(void);
 extern int __init mpc5121_clk_init(void);
 extern const char *mpc512x_select_psc_compat(void);
 extern const char *mpc512x_select_reset_compat(void);
-extern void mpc512x_restart(char *cmd);
+extern void __noreturn mpc512x_restart(char *cmd);
 
 #endif				/* __MPC512X_H__ */
diff --git a/arch/powerpc/platforms/512x/mpc512x_generic.c b/arch/powerpc/platforms/512x/mpc512x_generic.c
index ce71408781a0..bf884d3075e4 100644
--- a/arch/powerpc/platforms/512x/mpc512x_generic.c
+++ b/arch/powerpc/platforms/512x/mpc512x_generic.c
@@ -38,14 +38,18 @@ static const char * const board[] __initconst = {
  */
 static int __init mpc512x_generic_probe(void)
 {
-	return of_flat_dt_match(of_get_flat_dt_root(), board);
+	if (!of_device_compatible_match(of_root, board))
+		return 0;
+
+	mpc512x_init_early();
+
+	return 1;
 }
 
 define_machine(mpc512x_generic) {
 	.name			= "MPC512x generic",
 	.probe			= mpc512x_generic_probe,
 	.init			= mpc512x_init,
-	.init_early		= mpc512x_init_early,
 	.setup_arch		= mpc512x_setup_arch,
 	.init_IRQ		= mpc512x_init_IRQ,
 	.get_irq		= ipic_get_irq,
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index 452da2391153..6b4f4cb7009a 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -47,7 +47,7 @@ static void __init mpc512x_restart_init(void)
 	of_node_put(np);
 }
 
-void mpc512x_restart(char *cmd)
+void __noreturn mpc512x_restart(char *cmd)
 {
 	if (reset_module_base) {
 		/* Enable software reset "RSTE" */
diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c
index 116f2325b20b..dc81f05e0bce 100644
--- a/arch/powerpc/platforms/512x/pdm360ng.c
+++ b/arch/powerpc/platforms/512x/pdm360ng.c
@@ -113,9 +113,12 @@ void __init pdm360ng_init(void)
 
 static int __init pdm360ng_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
+	if (!of_machine_is_compatible("ifm,pdm360ng"))
+		return 0;
 
-	return of_flat_dt_is_compatible(root, "ifm,pdm360ng");
+	mpc512x_init_early();
+
+	return 1;
 }
 
 define_machine(pdm360ng) {
@@ -123,7 +126,6 @@ define_machine(pdm360ng) {
 	.probe			= pdm360ng_probe,
 	.setup_arch		= mpc512x_setup_arch,
 	.init			= pdm360ng_init,
-	.init_early		= mpc512x_init_early,
 	.init_IRQ		= mpc512x_init_IRQ,
 	.get_irq		= ipic_get_irq,
 	.calibrate_decr		= generic_calibrate_decr,
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index 6af651e69129..39b49822ace1 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -200,8 +200,7 @@ static void __init efika_setup_arch(void)
 
 static int __init efika_probe(void)
 {
-	const char *model = of_get_flat_dt_prop(of_get_flat_dt_root(),
-						"model", NULL);
+	const char *model = of_get_property(of_root, "model", NULL);
 
 	if (model == NULL)
 		return 0;
diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c
index 7492de3cf6d0..c94c385cc919 100644
--- a/arch/powerpc/platforms/52xx/lite5200.c
+++ b/arch/powerpc/platforms/52xx/lite5200.c
@@ -183,7 +183,7 @@ static const char * const board[] __initconst = {
  */
 static int __init lite5200_probe(void)
 {
-	return of_flat_dt_match(of_get_flat_dt_root(), board);
+	return of_device_compatible_match(of_root, board);
 }
 
 define_machine(lite5200) {
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 8fb95480fd73..a3227040cc86 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -242,7 +242,7 @@ static const char * const board[] __initconst = {
  */
 static int __init media5200_probe(void)
 {
-	return of_flat_dt_match(of_get_flat_dt_root(), board);
+	return of_device_compatible_match(of_root, board);
 }
 
 define_machine(media5200_platform) {
diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c
index 792a301a0bf0..a80c6278d515 100644
--- a/arch/powerpc/platforms/52xx/mpc5200_simple.c
+++ b/arch/powerpc/platforms/52xx/mpc5200_simple.c
@@ -70,7 +70,7 @@ static const char *board[] __initdata = {
  */
 static int __init mpc5200_simple_probe(void)
 {
-	return of_flat_dt_match(of_get_flat_dt_root(), board);
+	return of_device_compatible_match(of_root, board);
 }
 
 define_machine(mpc5200_simple_platform) {
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c
index 26993826a797..565e3a83dc9e 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_common.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c
@@ -243,8 +243,7 @@ EXPORT_SYMBOL(mpc52xx_get_xtal_freq);
 /**
  * mpc52xx_restart: ppc_md->restart hook for mpc5200 using the watchdog timer
  */
-void
-mpc52xx_restart(char *cmd)
+void __noreturn mpc52xx_restart(char *cmd)
 {
 	local_irq_disable();
 
diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c
index 6781bda117be..cdab847749e6 100644
--- a/arch/powerpc/platforms/82xx/ep8248e.c
+++ b/arch/powerpc/platforms/82xx/ep8248e.c
@@ -309,8 +309,7 @@ machine_device_initcall(ep8248e, declare_of_platform_devices);
  */
 static int __init ep8248e_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	return of_flat_dt_is_compatible(root, "fsl,ep8248e");
+	return of_machine_is_compatible("fsl,ep8248e");
 }
 
 define_machine(ep8248e)
diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c
index 387b446f4161..28860e40b5db 100644
--- a/arch/powerpc/platforms/82xx/km82xx.c
+++ b/arch/powerpc/platforms/82xx/km82xx.c
@@ -198,8 +198,7 @@ machine_device_initcall(km82xx, declare_of_platform_devices);
  */
 static int __init km82xx_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	return of_flat_dt_is_compatible(root, "keymile,km82xx");
+	return of_machine_is_compatible("keymile,km82xx");
 }
 
 define_machine(km82xx)
diff --git a/arch/powerpc/platforms/82xx/mpc8272_ads.c b/arch/powerpc/platforms/82xx/mpc8272_ads.c
index d24deacf07d0..d23c10a96bde 100644
--- a/arch/powerpc/platforms/82xx/mpc8272_ads.c
+++ b/arch/powerpc/platforms/82xx/mpc8272_ads.c
@@ -201,8 +201,7 @@ machine_device_initcall(mpc8272_ads, declare_of_platform_devices);
  */
 static int __init mpc8272_ads_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	return of_flat_dt_is_compatible(root, "fsl,mpc8272ads");
+	return of_machine_is_compatible("fsl,mpc8272ads");
 }
 
 define_machine(mpc8272_ads)
diff --git a/arch/powerpc/platforms/82xx/pq2.c b/arch/powerpc/platforms/82xx/pq2.c
index fc8b2d6a7d8d..c4f7029fc9ae 100644
--- a/arch/powerpc/platforms/82xx/pq2.c
+++ b/arch/powerpc/platforms/82xx/pq2.c
@@ -22,7 +22,7 @@
 
 #define RMR_CSRE 0x00000001
 
-void pq2_restart(char *cmd)
+void __noreturn pq2_restart(char *cmd)
 {
 	local_irq_disable();
 	setbits32(&cpm2_immr->im_clkrst.car_rmr, RMR_CSRE);
diff --git a/arch/powerpc/platforms/82xx/pq2.h b/arch/powerpc/platforms/82xx/pq2.h
index a41f84ae2325..3080ce3441c1 100644
--- a/arch/powerpc/platforms/82xx/pq2.h
+++ b/arch/powerpc/platforms/82xx/pq2.h
@@ -1,7 +1,7 @@
 #ifndef _PQ2_H
 #define _PQ2_H
 
-void pq2_restart(char *cmd);
+void __noreturn pq2_restart(char *cmd);
 
 #ifdef CONFIG_PCI
 int pq2ads_pci_init_irq(void);
diff --git a/arch/powerpc/platforms/82xx/pq2fads.c b/arch/powerpc/platforms/82xx/pq2fads.c
index 3a5164ad10ad..6c654dc74a4b 100644
--- a/arch/powerpc/platforms/82xx/pq2fads.c
+++ b/arch/powerpc/platforms/82xx/pq2fads.c
@@ -164,8 +164,7 @@ static void __init pq2fads_setup_arch(void)
  */
 static int __init pq2fads_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	return of_flat_dt_is_compatible(root, "fsl,pq2fads");
+	return of_machine_is_compatible("fsl,pq2fads");
 }
 
 static const struct of_device_id of_bus_ids[] __initconst = {
diff --git a/arch/powerpc/platforms/83xx/asp834x.c b/arch/powerpc/platforms/83xx/asp834x.c
index 464ea8e0292d..17e54339f8d9 100644
--- a/arch/powerpc/platforms/83xx/asp834x.c
+++ b/arch/powerpc/platforms/83xx/asp834x.c
@@ -43,8 +43,7 @@ machine_device_initcall(asp834x, mpc83xx_declare_of_platform_devices);
  */
 static int __init asp834x_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	return of_flat_dt_is_compatible(root, "analogue-and-micro,asp8347e");
+	return of_machine_is_compatible("analogue-and-micro,asp8347e");
 }
 
 define_machine(asp834x) {
diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c
index 4bc6bbbe9ada..e7fbd6366abb 100644
--- a/arch/powerpc/platforms/83xx/km83xx.c
+++ b/arch/powerpc/platforms/83xx/km83xx.c
@@ -171,11 +171,10 @@ static char *board[] __initdata = {
  */
 static int __init mpc83xx_km_probe(void)
 {
-	unsigned long node = of_get_flat_dt_root();
 	int i = 0;
 
 	while (board[i]) {
-		if (of_flat_dt_is_compatible(node, board[i]))
+		if (of_machine_is_compatible(board[i]))
 			break;
 		i++;
 	}
diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c
index 7e923cad56cf..8899aa9d11f5 100644
--- a/arch/powerpc/platforms/83xx/misc.c
+++ b/arch/powerpc/platforms/83xx/misc.c
@@ -35,7 +35,7 @@ static int __init mpc83xx_restart_init(void)
 
 arch_initcall(mpc83xx_restart_init);
 
-void mpc83xx_restart(char *cmd)
+void __noreturn mpc83xx_restart(char *cmd)
 {
 #define RST_OFFSET	0x00000900
 #define RST_PROT_REG	0x00000018
diff --git a/arch/powerpc/platforms/83xx/mpc830x_rdb.c b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
index 4f2d9fea77b7..040d5d085467 100644
--- a/arch/powerpc/platforms/83xx/mpc830x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
@@ -46,7 +46,7 @@ static const char *board[] __initdata = {
  */
 static int __init mpc830x_rdb_probe(void)
 {
-	return of_flat_dt_match(of_get_flat_dt_root(), board);
+	return of_device_compatible_match(of_root, board);
 }
 
 machine_device_initcall(mpc830x_rdb, mpc83xx_declare_of_platform_devices);
diff --git a/arch/powerpc/platforms/83xx/mpc831x_rdb.c b/arch/powerpc/platforms/83xx/mpc831x_rdb.c
index fa25977c52de..40e0d8307b59 100644
--- a/arch/powerpc/platforms/83xx/mpc831x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc831x_rdb.c
@@ -46,7 +46,7 @@ static const char *board[] __initdata = {
  */
 static int __init mpc831x_rdb_probe(void)
 {
-	return of_flat_dt_match(of_get_flat_dt_root(), board);
+	return of_device_compatible_match(of_root, board);
 }
 
 machine_device_initcall(mpc831x_rdb, mpc83xx_declare_of_platform_devices);
diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c
index a973b2ae5df6..cdfa47c4d394 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c
@@ -102,9 +102,7 @@ machine_device_initcall(mpc832x_mds, mpc83xx_declare_of_platform_devices);
  */
 static int __init mpc832x_sys_probe(void)
 {
-        unsigned long root = of_get_flat_dt_root();
-
-        return of_flat_dt_is_compatible(root, "MPC832xMDS");
+	return of_machine_is_compatible("MPC832xMDS");
 }
 
 define_machine(mpc832x_mds) {
diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
index ea2b87d202ca..2ef03e7d248c 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
@@ -220,9 +220,7 @@ machine_device_initcall(mpc832x_rdb, mpc83xx_declare_of_platform_devices);
  */
 static int __init mpc832x_rdb_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "MPC832xRDB");
+	return of_machine_is_compatible("MPC832xRDB");
 }
 
 define_machine(mpc832x_rdb) {
diff --git a/arch/powerpc/platforms/83xx/mpc834x_itx.c b/arch/powerpc/platforms/83xx/mpc834x_itx.c
index 80aea8c4b5a3..8fd0c1e8b182 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_itx.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_itx.c
@@ -70,9 +70,7 @@ static void __init mpc834x_itx_setup_arch(void)
  */
 static int __init mpc834x_itx_probe(void)
 {
-        unsigned long root = of_get_flat_dt_root();
-
-        return of_flat_dt_is_compatible(root, "MPC834xMITX");
+	return of_machine_is_compatible("MPC834xMITX");
 }
 
 define_machine(mpc834x_itx) {
diff --git a/arch/powerpc/platforms/83xx/mpc834x_mds.c b/arch/powerpc/platforms/83xx/mpc834x_mds.c
index 553e793a4a93..eeaee6123bb3 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_mds.c
@@ -91,9 +91,7 @@ machine_device_initcall(mpc834x_mds, mpc83xx_declare_of_platform_devices);
  */
 static int __init mpc834x_mds_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "MPC834xMDS");
+	return of_machine_is_compatible("MPC834xMDS");
 }
 
 define_machine(mpc834x_mds) {
diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c
index dd70b85f56d4..dacf4c2df069 100644
--- a/arch/powerpc/platforms/83xx/mpc836x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c
@@ -209,9 +209,7 @@ machine_arch_initcall(mpc836x_mds, mpc836x_usb_cfg);
  */
 static int __init mpc836x_mds_probe(void)
 {
-        unsigned long root = of_get_flat_dt_root();
-
-        return of_flat_dt_is_compatible(root, "MPC836xMDS");
+	return of_machine_is_compatible("MPC836xMDS");
 }
 
 define_machine(mpc836x_mds) {
diff --git a/arch/powerpc/platforms/83xx/mpc836x_rdk.c b/arch/powerpc/platforms/83xx/mpc836x_rdk.c
index 4cd7153a6c88..cf67ac93ddcb 100644
--- a/arch/powerpc/platforms/83xx/mpc836x_rdk.c
+++ b/arch/powerpc/platforms/83xx/mpc836x_rdk.c
@@ -42,9 +42,7 @@ static void __init mpc836x_rdk_setup_arch(void)
  */
 static int __init mpc836x_rdk_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,mpc8360rdk");
+	return of_machine_is_compatible("fsl,mpc8360rdk");
 }
 
 define_machine(mpc836x_rdk) {
diff --git a/arch/powerpc/platforms/83xx/mpc837x_mds.c b/arch/powerpc/platforms/83xx/mpc837x_mds.c
index e53a60b6c863..652b97d699c9 100644
--- a/arch/powerpc/platforms/83xx/mpc837x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc837x_mds.c
@@ -93,9 +93,7 @@ machine_device_initcall(mpc837x_mds, mpc83xx_declare_of_platform_devices);
  */
 static int __init mpc837x_mds_probe(void)
 {
-        unsigned long root = of_get_flat_dt_root();
-
-        return of_flat_dt_is_compatible(root, "fsl,mpc837xmds");
+	return of_machine_is_compatible("fsl,mpc837xmds");
 }
 
 define_machine(mpc837x_mds) {
diff --git a/arch/powerpc/platforms/83xx/mpc837x_rdb.c b/arch/powerpc/platforms/83xx/mpc837x_rdb.c
index 9813c81e8e5b..667731d81676 100644
--- a/arch/powerpc/platforms/83xx/mpc837x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc837x_rdb.c
@@ -73,7 +73,7 @@ static const char * const board[] __initconst = {
  */
 static int __init mpc837x_rdb_probe(void)
 {
-	return of_flat_dt_match(of_get_flat_dt_root(), board);
+	return of_device_compatible_match(of_root, board);
 }
 
 define_machine(mpc837x_rdb) {
diff --git a/arch/powerpc/platforms/83xx/mpc83xx.h b/arch/powerpc/platforms/83xx/mpc83xx.h
index 0cf74d7ea1c5..ad484199eff7 100644
--- a/arch/powerpc/platforms/83xx/mpc83xx.h
+++ b/arch/powerpc/platforms/83xx/mpc83xx.h
@@ -65,7 +65,7 @@
  * mpc83xx_* files. Mostly for use by mpc83xx_setup
  */
 
-extern void mpc83xx_restart(char *cmd);
+extern void __noreturn mpc83xx_restart(char *cmd);
 extern long mpc83xx_time_init(void);
 extern int mpc837x_usb_cfg(void);
 extern int mpc834x_usb_cfg(void);
diff --git a/arch/powerpc/platforms/83xx/sbc834x.c b/arch/powerpc/platforms/83xx/sbc834x.c
index 26cb3e934722..b867e88dfb0d 100644
--- a/arch/powerpc/platforms/83xx/sbc834x.c
+++ b/arch/powerpc/platforms/83xx/sbc834x.c
@@ -60,9 +60,7 @@ machine_device_initcall(sbc834x, mpc83xx_declare_of_platform_devices);
  */
 static int __init sbc834x_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "SBC834xE");
+	return of_machine_is_compatible("SBC834xE");
 }
 
 define_machine(sbc834x) {
diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c
index dcfafd6b91ee..07dd6ae3ec52 100644
--- a/arch/powerpc/platforms/85xx/bsc913x_qds.c
+++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c
@@ -60,9 +60,7 @@ machine_arch_initcall(bsc9132_qds, mpc85xx_common_publish_devices);
 
 static int __init bsc9132_qds_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,bsc9132qds");
+	return of_machine_is_compatible("fsl,bsc9132qds");
 }
 
 define_machine(bsc9132_qds) {
diff --git a/arch/powerpc/platforms/85xx/bsc913x_rdb.c b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
index 9d57bedb940c..e48f6710e6d5 100644
--- a/arch/powerpc/platforms/85xx/bsc913x_rdb.c
+++ b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
@@ -50,9 +50,7 @@ machine_device_initcall(bsc9131_rdb, mpc85xx_common_publish_devices);
 
 static int __init bsc9131_rdb_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,bsc9131rdb");
+	return of_machine_is_compatible("fsl,bsc9131rdb");
 }
 
 define_machine(bsc9131_rdb) {
diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c
index 61bc851e9a8e..3b9e3f0f9aec 100644
--- a/arch/powerpc/platforms/85xx/c293pcie.c
+++ b/arch/powerpc/platforms/85xx/c293pcie.c
@@ -54,9 +54,7 @@ machine_arch_initcall(c293_pcie, mpc85xx_common_publish_devices);
  */
 static int __init c293_pcie_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,C293PCIE"))
+	if (of_machine_is_compatible("fsl,C293PCIE"))
 		return 1;
 	return 0;
 }
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index a2b0bc859de0..3a6a84f07f43 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -170,20 +170,19 @@ static const char * const boards[] __initconst = {
  */
 static int __init corenet_generic_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
 	char hv_compat[24];
 	int i;
 #ifdef CONFIG_SMP
 	extern struct smp_ops_t smp_85xx_ops;
 #endif
 
-	if (of_flat_dt_match(root, boards))
+	if (of_device_compatible_match(of_root, boards))
 		return 1;
 
 	/* Check if we're running under the Freescale hypervisor */
 	for (i = 0; boards[i]; i++) {
 		snprintf(hv_compat, sizeof(hv_compat), "%s-hv", boards[i]);
-		if (of_flat_dt_is_compatible(root, hv_compat)) {
+		if (of_machine_is_compatible(hv_compat)) {
 			ppc_md.init_IRQ = ehv_pic_init;
 
 			ppc_md.get_irq = ehv_pic_get_irq;
diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c
index 11790e074c8a..14af36a7fa9c 100644
--- a/arch/powerpc/platforms/85xx/ge_imp3a.c
+++ b/arch/powerpc/platforms/85xx/ge_imp3a.c
@@ -47,9 +47,8 @@ void __init ge_imp3a_pic_init(void)
 	struct mpic *mpic;
 	struct device_node *np;
 	struct device_node *cascade_node = NULL;
-	unsigned long root = of_get_flat_dt_root();
 
-	if (of_flat_dt_is_compatible(root, "fsl,MPC8572DS-CAMP")) {
+	if (of_machine_is_compatible("fsl,MPC8572DS-CAMP")) {
 		mpic = mpic_alloc(NULL, 0,
 			MPIC_NO_RESET |
 			MPIC_BIG_ENDIAN |
@@ -198,9 +197,7 @@ static void ge_imp3a_show_cpuinfo(struct seq_file *m)
  */
 static int __init ge_imp3a_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "ge,IMP3A");
+	return of_machine_is_compatible("ge,IMP3A");
 }
 
 machine_arch_initcall(ge_imp3a, mpc85xx_common_publish_devices);
diff --git a/arch/powerpc/platforms/85xx/ksi8560.c b/arch/powerpc/platforms/85xx/ksi8560.c
index 3dc1bda3ddc3..6ef8580fdc0e 100644
--- a/arch/powerpc/platforms/85xx/ksi8560.c
+++ b/arch/powerpc/platforms/85xx/ksi8560.c
@@ -44,7 +44,7 @@
 
 static void __iomem *cpld_base = NULL;
 
-static void machine_restart(char *cmd)
+static void __noreturn machine_restart(char *cmd)
 {
 	if (cpld_base)
 		out_8(cpld_base + KSI8560_CPLD_RCR1, KSI8560_CPLD_RCR1_CPUHR);
@@ -176,9 +176,7 @@ machine_device_initcall(ksi8560, mpc85xx_common_publish_devices);
  */
 static int __init ksi8560_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "emerson,KSI8560");
+	return of_machine_is_compatible("emerson,KSI8560");
 }
 
 define_machine(ksi8560) {
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index a378ba3519e9..6ba687f19e45 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -64,9 +64,7 @@ machine_arch_initcall(mpc8536_ds, swiotlb_setup_bus_notifier);
  */
 static int __init mpc8536_ds_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,mpc8536ds");
+	return of_machine_is_compatible("fsl,mpc8536ds");
 }
 
 define_machine(mpc8536_ds) {
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
index de72a5f464b1..8756715c7a47 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
@@ -160,9 +160,7 @@ machine_arch_initcall(mpc85xx_ads, mpc85xx_common_publish_devices);
  */
 static int __init mpc85xx_ads_probe(void)
 {
-        unsigned long root = of_get_flat_dt_root();
-
-        return of_flat_dt_is_compatible(root, "MPC85xxADS");
+	return of_machine_is_compatible("MPC85xxADS");
 }
 
 define_machine(mpc85xx_ads) {
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
index d7e87ff912d7..62f171c71c4c 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
@@ -83,7 +83,7 @@ static int mpc85xx_exclude_device(struct pci_controller *hose,
 		return PCIBIOS_SUCCESSFUL;
 }
 
-static void mpc85xx_cds_restart(char *cmd)
+static void __noreturn mpc85xx_cds_restart(char *cmd)
 {
 	struct pci_dev *dev;
 	u_char tmp;
@@ -367,9 +367,7 @@ static void mpc85xx_cds_show_cpuinfo(struct seq_file *m)
  */
 static int __init mpc85xx_cds_probe(void)
 {
-        unsigned long root = of_get_flat_dt_root();
-
-        return of_flat_dt_is_compatible(root, "MPC85xxCDS");
+	return of_machine_is_compatible("MPC85xxCDS");
 }
 
 machine_arch_initcall(mpc85xx_cds, mpc85xx_common_publish_devices);
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index f858306dba6a..6bc07d837b1c 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -66,9 +66,7 @@ void __init mpc85xx_ds_pic_init(void)
 	struct device_node *cascade_node = NULL;
 	int cascade_irq;
 #endif
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,MPC8572DS-CAMP")) {
+	if (of_machine_is_compatible("fsl,MPC8572DS-CAMP")) {
 		mpic = mpic_alloc(NULL, 0,
 			MPIC_NO_RESET |
 			MPIC_BIG_ENDIAN |
@@ -169,9 +167,7 @@ static void __init mpc85xx_ds_setup_arch(void)
  */
 static int __init mpc8544_ds_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return !!of_flat_dt_is_compatible(root, "MPC8544DS");
+	return !!of_machine_is_compatible("MPC8544DS");
 }
 
 machine_arch_initcall(mpc8544_ds, mpc85xx_common_publish_devices);
@@ -187,9 +183,7 @@ machine_arch_initcall(p2020_ds, swiotlb_setup_bus_notifier);
  */
 static int __init mpc8572_ds_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return !!of_flat_dt_is_compatible(root, "fsl,MPC8572DS");
+	return !!of_machine_is_compatible("fsl,MPC8572DS");
 }
 
 /*
@@ -197,9 +191,7 @@ static int __init mpc8572_ds_probe(void)
  */
 static int __init p2020_ds_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return !!of_flat_dt_is_compatible(root, "fsl,P2020DS");
+	return !!of_machine_is_compatible("fsl,P2020DS");
 }
 
 define_machine(mpc8544_ds) {
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index f61cbe235581..fa9cd710d2ae 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -376,9 +376,7 @@ static void __init mpc85xx_mds_pic_init(void)
 
 static int __init mpc85xx_mds_probe(void)
 {
-        unsigned long root = of_get_flat_dt_root();
-
-        return of_flat_dt_is_compatible(root, "MPC85xxMDS");
+	return of_machine_is_compatible("MPC85xxMDS");
 }
 
 define_machine(mpc8568_mds) {
@@ -398,9 +396,7 @@ define_machine(mpc8568_mds) {
 
 static int __init mpc8569_mds_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,MPC8569EMDS");
+	return of_machine_is_compatible("fsl,MPC8569EMDS");
 }
 
 define_machine(mpc8569_mds) {
@@ -420,9 +416,7 @@ define_machine(mpc8569_mds) {
 
 static int __init p1021_mds_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,P1021MDS");
+	return of_machine_is_compatible("fsl,P1021MDS");
 
 }
 
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index 3f4dad133338..c1499cbf3786 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -47,13 +47,12 @@
 void __init mpc85xx_rdb_pic_init(void)
 {
 	struct mpic *mpic;
-	unsigned long root = of_get_flat_dt_root();
 
 #ifdef CONFIG_QUICC_ENGINE
 	struct device_node *np;
 #endif
 
-	if (of_flat_dt_is_compatible(root, "fsl,MPC85XXRDB-CAMP")) {
+	if (of_machine_is_compatible("fsl,MPC85XXRDB-CAMP")) {
 		mpic = mpic_alloc(NULL, 0, MPIC_NO_RESET |
 			MPIC_BIG_ENDIAN |
 			MPIC_SINGLE_DEST_CPU,
@@ -148,80 +147,60 @@ machine_arch_initcall(p1024_rdb, mpc85xx_common_publish_devices);
  */
 static int __init p2020_rdb_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,P2020RDB"))
+	if (of_machine_is_compatible("fsl,P2020RDB"))
 		return 1;
 	return 0;
 }
 
 static int __init p1020_rdb_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,P1020RDB"))
+	if (of_machine_is_compatible("fsl,P1020RDB"))
 		return 1;
 	return 0;
 }
 
 static int __init p1020_rdb_pc_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,P1020RDB-PC");
+	return of_machine_is_compatible("fsl,P1020RDB-PC");
 }
 
 static int __init p1020_rdb_pd_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,P1020RDB-PD");
+	return of_machine_is_compatible("fsl,P1020RDB-PD");
 }
 
 static int __init p1021_rdb_pc_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,P1021RDB-PC"))
+	if (of_machine_is_compatible("fsl,P1021RDB-PC"))
 		return 1;
 	return 0;
 }
 
 static int __init p2020_rdb_pc_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,P2020RDB-PC"))
+	if (of_machine_is_compatible("fsl,P2020RDB-PC"))
 		return 1;
 	return 0;
 }
 
 static int __init p1025_rdb_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,P1025RDB");
+	return of_machine_is_compatible("fsl,P1025RDB");
 }
 
 static int __init p1020_mbg_pc_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,P1020MBG-PC");
+	return of_machine_is_compatible("fsl,P1020MBG-PC");
 }
 
 static int __init p1020_utm_pc_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,P1020UTM-PC");
+	return of_machine_is_compatible("fsl,P1020UTM-PC");
 }
 
 static int __init p1024_rdb_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,P1024RDB");
+	return of_machine_is_compatible("fsl,P1024RDB");
 }
 
 define_machine(p2020_rdb) {
diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c
index 1233050560ae..acc3d0d6049d 100644
--- a/arch/powerpc/platforms/85xx/mvme2500.c
+++ b/arch/powerpc/platforms/85xx/mvme2500.c
@@ -53,9 +53,7 @@ machine_arch_initcall(mvme2500, mpc85xx_common_publish_devices);
  */
 static int __init mvme2500_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "artesyn,MVME2500");
+	return of_machine_is_compatible("artesyn,MVME2500");
 }
 
 define_machine(mvme2500) {
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index ad1a3d438a9e..661d7b59e413 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -62,11 +62,9 @@ machine_arch_initcall(p1010_rdb, swiotlb_setup_bus_notifier);
  */
 static int __init p1010_rdb_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,P1010RDB"))
+	if (of_machine_is_compatible("fsl,P1010RDB"))
 		return 1;
-	if (of_flat_dt_is_compatible(root, "fsl,P1010RDB-PB"))
+	if (of_machine_is_compatible("fsl,P1010RDB-PB"))
 		return 1;
 	return 0;
 }
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 371df822e88e..63568d68c76f 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -555,9 +555,7 @@ machine_arch_initcall(p1022_ds, swiotlb_setup_bus_notifier);
  */
 static int __init p1022_ds_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,p1022ds");
+	return of_machine_is_compatible("fsl,p1022ds");
 }
 
 define_machine(p1022_ds) {
diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c
index 5087becaa8bc..2f2943600301 100644
--- a/arch/powerpc/platforms/85xx/p1022_rdk.c
+++ b/arch/powerpc/platforms/85xx/p1022_rdk.c
@@ -135,9 +135,7 @@ machine_arch_initcall(p1022_rdk, swiotlb_setup_bus_notifier);
  */
 static int __init p1022_rdk_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,p1022rdk");
+	return of_machine_is_compatible("fsl,p1022rdk");
 }
 
 define_machine(p1022_rdk) {
diff --git a/arch/powerpc/platforms/85xx/p1023_rdb.c b/arch/powerpc/platforms/85xx/p1023_rdb.c
index d5b7509825de..40d8de57c341 100644
--- a/arch/powerpc/platforms/85xx/p1023_rdb.c
+++ b/arch/powerpc/platforms/85xx/p1023_rdb.c
@@ -100,9 +100,7 @@ static void __init mpc85xx_rdb_pic_init(void)
 
 static int __init p1023_rdb_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,P1023RDB");
+	return of_machine_is_compatible("fsl,P1023RDB");
 
 }
 
diff --git a/arch/powerpc/platforms/85xx/ppa8548.c b/arch/powerpc/platforms/85xx/ppa8548.c
index 12019f17f297..2410167b290a 100644
--- a/arch/powerpc/platforms/85xx/ppa8548.c
+++ b/arch/powerpc/platforms/85xx/ppa8548.c
@@ -81,9 +81,7 @@ machine_device_initcall(ppa8548, declare_of_platform_devices);
  */
 static int __init ppa8548_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "ppa8548");
+	return of_machine_is_compatible("ppa8548");
 }
 
 define_machine(ppa8548) {
diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c
index 8ad2fe6f200a..50d745809809 100644
--- a/arch/powerpc/platforms/85xx/qemu_e500.c
+++ b/arch/powerpc/platforms/85xx/qemu_e500.c
@@ -62,9 +62,7 @@ static void __init qemu_e500_setup_arch(void)
  */
 static int __init qemu_e500_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return !!of_flat_dt_is_compatible(root, "fsl,qemu-e500");
+	return !!of_machine_is_compatible("fsl,qemu-e500");
 }
 
 machine_arch_initcall(qemu_e500, mpc85xx_common_publish_devices);
diff --git a/arch/powerpc/platforms/85xx/sbc8548.c b/arch/powerpc/platforms/85xx/sbc8548.c
index b07214666d65..62b6c45a5a9b 100644
--- a/arch/powerpc/platforms/85xx/sbc8548.c
+++ b/arch/powerpc/platforms/85xx/sbc8548.c
@@ -120,9 +120,7 @@ machine_arch_initcall(sbc8548, mpc85xx_common_publish_devices);
  */
 static int __init sbc8548_probe(void)
 {
-        unsigned long root = of_get_flat_dt_root();
-
-        return of_flat_dt_is_compatible(root, "SBC8548");
+	return of_machine_is_compatible("SBC8548");
 }
 
 define_machine(sbc8548) {
diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c
index ae368e0e1076..cd255acde2e2 100644
--- a/arch/powerpc/platforms/85xx/socrates.c
+++ b/arch/powerpc/platforms/85xx/socrates.c
@@ -79,9 +79,7 @@ machine_arch_initcall(socrates, mpc85xx_common_publish_devices);
  */
 static int __init socrates_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "abb,socrates"))
+	if (of_machine_is_compatible("abb,socrates"))
 		return 1;
 
 	return 0;
diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c
index 6f4939b6309e..91b824c4dc08 100644
--- a/arch/powerpc/platforms/85xx/stx_gp3.c
+++ b/arch/powerpc/platforms/85xx/stx_gp3.c
@@ -93,9 +93,7 @@ machine_arch_initcall(stx_gp3, mpc85xx_common_publish_devices);
  */
 static int __init stx_gp3_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "stx,gp3-8560");
+	return of_machine_is_compatible("stx,gp3-8560");
 }
 
 define_machine(stx_gp3) {
diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c
index ec0b7272fae2..b7c54454d611 100644
--- a/arch/powerpc/platforms/85xx/tqm85xx.c
+++ b/arch/powerpc/platforms/85xx/tqm85xx.c
@@ -122,7 +122,7 @@ static const char * const board[] __initconst = {
  */
 static int __init tqm85xx_probe(void)
 {
-	return of_flat_dt_match(of_get_flat_dt_root(), board);
+	return of_device_compatible_match(of_root, board);
 }
 
 define_machine(tqm85xx) {
diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c
index 71bc255b4324..1bc02a87f597 100644
--- a/arch/powerpc/platforms/85xx/twr_p102x.c
+++ b/arch/powerpc/platforms/85xx/twr_p102x.c
@@ -128,9 +128,7 @@ machine_arch_initcall(twr_p1025, mpc85xx_common_publish_devices);
 
 static int __init twr_p1025_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,TWR-P1025");
+	return of_machine_is_compatible("fsl,TWR-P1025");
 }
 
 define_machine(twr_p1025) {
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index 1a9c1085855f..cf0c70ff026e 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -144,23 +144,17 @@ machine_arch_initcall(xes_mpc8540, mpc85xx_common_publish_devices);
  */
 static int __init xes_mpc8572_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "xes,MPC8572");
+	return of_machine_is_compatible("xes,MPC8572");
 }
 
 static int __init xes_mpc8548_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "xes,MPC8548");
+	return of_machine_is_compatible("xes,MPC8548");
 }
 
 static int __init xes_mpc8540_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "xes,MPC8540");
+	return of_machine_is_compatible("xes,MPC8540");
 }
 
 define_machine(xes_mpc8572) {
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 3988f16e46c1..ce619bd1f82d 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -60,6 +60,11 @@ config GEF_SBC610
 	help
 	  This option enables support for the GE SBC610.
 
+config MVME7100
+        bool "Artesyn MVME7100"
+        help
+          This option enables support for the Emerson/Artesyn MVME7100 board.
+
 endif
 
 config MPC8641
@@ -68,7 +73,8 @@ config MPC8641
 	select FSL_PCI if PCI
 	select PPC_UDBG_16550
 	select MPIC
-	default y if MPC8641_HPCN || SBC8641D || GEF_SBC610 || GEF_SBC310 || GEF_PPC9A
+	default y if MPC8641_HPCN || SBC8641D || GEF_SBC610 || GEF_SBC310 || GEF_PPC9A \
+			|| MVME7100
 
 config MPC8610
 	bool
diff --git a/arch/powerpc/platforms/86xx/Makefile b/arch/powerpc/platforms/86xx/Makefile
index 2d889ad7dc89..01958fedc3f2 100644
--- a/arch/powerpc/platforms/86xx/Makefile
+++ b/arch/powerpc/platforms/86xx/Makefile
@@ -10,3 +10,4 @@ obj-$(CONFIG_MPC8610_HPCD)	+= mpc8610_hpcd.o
 obj-$(CONFIG_GEF_SBC610)	+= gef_sbc610.o
 obj-$(CONFIG_GEF_SBC310)	+= gef_sbc310.o
 obj-$(CONFIG_GEF_PPC9A)		+= gef_ppc9a.o
+obj-$(CONFIG_MVME7100)          += mvme7100.o
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index 8e63b752712c..ef684afb63c6 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -189,9 +189,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_USB,
  */
 static int __init gef_ppc9a_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "gef,ppc9a"))
+	if (of_machine_is_compatible("gef,ppc9a"))
 		return 1;
 
 	return 0;
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index 0e0be94f551f..67dd0c231646 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -176,9 +176,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_USB,
  */
 static int __init gef_sbc310_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "gef,sbc310"))
+	if (of_machine_is_compatible("gef,sbc310"))
 		return 1;
 
 	return 0;
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index e8292b492d7e..805026976cac 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -166,9 +166,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_USB,
  */
 static int __init gef_sbc610_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "gef,sbc610"))
+	if (of_machine_is_compatible("gef,sbc610"))
 		return 1;
 
 	return 0;
diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index 957473e5c8e5..fef0582eddf1 100644
--- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -319,9 +319,7 @@ static void __init mpc86xx_hpcd_setup_arch(void)
  */
 static int __init mpc86xx_hpcd_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,MPC8610HPCD"))
+	if (of_machine_is_compatible("fsl,MPC8610HPCD"))
 		return 1;	/* Looks good */
 
 	return 0;
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index e5084811b9c6..5ae42a037065 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -96,13 +96,11 @@ mpc86xx_hpcn_show_cpuinfo(struct seq_file *m)
  */
 static int __init mpc86xx_hpcn_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "fsl,mpc8641hpcn"))
+	if (of_machine_is_compatible("fsl,mpc8641hpcn"))
 		return 1;	/* Looks good */
 
 	/* Be nice and don't give silent boot death.  Delete this in 2.6.27 */
-	if (of_flat_dt_is_compatible(root, "mpc86xx")) {
+	if (of_machine_is_compatible("mpc86xx")) {
 		pr_warning("WARNING: your dts/dtb is old. You must update before the next kernel release\n");
 		return 1;
 	}
diff --git a/arch/powerpc/platforms/86xx/mvme7100.c b/arch/powerpc/platforms/86xx/mvme7100.c
new file mode 100644
index 000000000000..addb41e7cd14
--- /dev/null
+++ b/arch/powerpc/platforms/86xx/mvme7100.c
@@ -0,0 +1,121 @@
+/*
+ * Board setup routines for the Emerson/Artesyn MVME7100
+ *
+ * Copyright 2016 Elettra-Sincrotrone Trieste S.C.p.A.
+ *
+ * Author: Alessio Igor Bogani <alessio.bogani@elettra.eu>
+ *
+ * Based on earlier code by:
+ *
+ *	Ajit Prem <ajit.prem@emerson.com>
+ *	Copyright 2008 Emerson
+ *
+ * USB host fixup is borrowed by:
+ *
+ *	Martyn Welch <martyn.welch@ge.com>
+ *	Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ */
+
+#include <linux/pci.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/of_address.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+
+#include "mpc86xx.h"
+
+#define MVME7100_INTERRUPT_REG_2_OFFSET	0x05
+#define MVME7100_DS1375_MASK		0x40
+#define MVME7100_MAX6649_MASK		0x20
+#define MVME7100_ABORT_MASK		0x10
+
+/*
+ * Setup the architecture
+ */
+static void __init mvme7100_setup_arch(void)
+{
+	struct device_node *bcsr_node;
+	void __iomem *mvme7100_regs = NULL;
+	u8 reg;
+
+	if (ppc_md.progress)
+		ppc_md.progress("mvme7100_setup_arch()", 0);
+
+#ifdef CONFIG_SMP
+	mpc86xx_smp_init();
+#endif
+
+	fsl_pci_assign_primary();
+
+	/* Remap BCSR registers */
+	bcsr_node = of_find_compatible_node(NULL, NULL,
+			"artesyn,mvme7100-bcsr");
+	if (bcsr_node) {
+		mvme7100_regs = of_iomap(bcsr_node, 0);
+		of_node_put(bcsr_node);
+	}
+
+	if (mvme7100_regs) {
+		/* Disable ds1375, max6649, and abort interrupts */
+		reg = readb(mvme7100_regs + MVME7100_INTERRUPT_REG_2_OFFSET);
+		reg |= MVME7100_DS1375_MASK | MVME7100_MAX6649_MASK
+			| MVME7100_ABORT_MASK;
+		writeb(reg, mvme7100_regs + MVME7100_INTERRUPT_REG_2_OFFSET);
+	} else
+		pr_warn("Unable to map board registers\n");
+
+	pr_info("MVME7100 board from Artesyn\n");
+}
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init mvme7100_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	return of_flat_dt_is_compatible(root, "artesyn,MVME7100");
+}
+
+static void mvme7100_usb_host_fixup(struct pci_dev *pdev)
+{
+	unsigned int val;
+
+	if (!machine_is(mvme7100))
+		return;
+
+	/* Ensure only ports 1 & 2 are enabled */
+	pci_read_config_dword(pdev, 0xe0, &val);
+	pci_write_config_dword(pdev, 0xe0, (val & ~7) | 0x2);
+
+	/* System clock is 48-MHz Oscillator and EHCI Enabled. */
+	pci_write_config_dword(pdev, 0xe4, 1 << 5);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_USB,
+	mvme7100_usb_host_fixup);
+
+machine_arch_initcall(mvme7100, mpc86xx_common_publish_devices);
+
+define_machine(mvme7100) {
+	.name			= "MVME7100",
+	.probe			= mvme7100_probe,
+	.setup_arch		= mvme7100_setup_arch,
+	.init_IRQ		= mpc86xx_init_irq,
+	.get_irq		= mpic_get_irq,
+	.restart		= fsl_rstcr_restart,
+	.time_init		= mpc86xx_time_init,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+};
diff --git a/arch/powerpc/platforms/86xx/sbc8641d.c b/arch/powerpc/platforms/86xx/sbc8641d.c
index 2a9cf278c12a..52af5735742e 100644
--- a/arch/powerpc/platforms/86xx/sbc8641d.c
+++ b/arch/powerpc/platforms/86xx/sbc8641d.c
@@ -67,9 +67,7 @@ sbc8641_show_cpuinfo(struct seq_file *m)
  */
 static int __init sbc8641_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "wind,sbc8641"))
+	if (of_machine_is_compatible("wind,sbc8641"))
 		return 1;	/* Looks good */
 
 	return 0;
diff --git a/arch/powerpc/platforms/8xx/adder875.c b/arch/powerpc/platforms/8xx/adder875.c
index 61cae4c1edb8..333dece79394 100644
--- a/arch/powerpc/platforms/8xx/adder875.c
+++ b/arch/powerpc/platforms/8xx/adder875.c
@@ -88,8 +88,7 @@ static void __init adder875_setup(void)
 
 static int __init adder875_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	return of_flat_dt_is_compatible(root, "analogue-and-micro,adder875");
+	return of_machine_is_compatible("analogue-and-micro,adder875");
 }
 
 static const struct of_device_id of_bus_ids[] __initconst = {
diff --git a/arch/powerpc/platforms/8xx/ep88xc.c b/arch/powerpc/platforms/8xx/ep88xc.c
index 2bedeb7d5f8f..cd0d90f1fb1c 100644
--- a/arch/powerpc/platforms/8xx/ep88xc.c
+++ b/arch/powerpc/platforms/8xx/ep88xc.c
@@ -143,8 +143,7 @@ static void __init ep88xc_setup_arch(void)
 
 static int __init ep88xc_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	return of_flat_dt_is_compatible(root, "fsl,ep88xc");
+	return of_machine_is_compatible("fsl,ep88xc");
 }
 
 static const struct of_device_id of_bus_ids[] __initconst = {
diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c
index c289fc77b4ba..b1ab6e96cb31 100644
--- a/arch/powerpc/platforms/8xx/m8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/m8xx_setup.c
@@ -198,7 +198,7 @@ void mpc8xx_get_rtc_time(struct rtc_time *tm)
 	return;
 }
 
-void mpc8xx_restart(char *cmd)
+void __noreturn mpc8xx_restart(char *cmd)
 {
 	car8xx_t __iomem *clk_r = immr_map(im_clkrst);
 
diff --git a/arch/powerpc/platforms/8xx/mpc86xads_setup.c b/arch/powerpc/platforms/8xx/mpc86xads_setup.c
index 78180c5e73ff..8d02f5ff4481 100644
--- a/arch/powerpc/platforms/8xx/mpc86xads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc86xads_setup.c
@@ -118,8 +118,7 @@ static void __init mpc86xads_setup_arch(void)
 
 static int __init mpc86xads_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	return of_flat_dt_is_compatible(root, "fsl,mpc866ads");
+	return of_machine_is_compatible("fsl,mpc866ads");
 }
 
 static const struct of_device_id of_bus_ids[] __initconst = {
diff --git a/arch/powerpc/platforms/8xx/mpc885ads_setup.c b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
index 4d62bf9dc789..e821a42d5816 100644
--- a/arch/powerpc/platforms/8xx/mpc885ads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
@@ -193,8 +193,7 @@ static void __init mpc885ads_setup_arch(void)
 
 static int __init mpc885ads_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	return of_flat_dt_is_compatible(root, "fsl,mpc885ads");
+	return of_machine_is_compatible("fsl,mpc885ads");
 }
 
 static const struct of_device_id of_bus_ids[] __initconst = {
diff --git a/arch/powerpc/platforms/8xx/mpc8xx.h b/arch/powerpc/platforms/8xx/mpc8xx.h
index 239a243a6161..31cc2ecace42 100644
--- a/arch/powerpc/platforms/8xx/mpc8xx.h
+++ b/arch/powerpc/platforms/8xx/mpc8xx.h
@@ -11,7 +11,7 @@
 #ifndef __MPC8xx_H
 #define __MPC8xx_H
 
-extern void mpc8xx_restart(char *cmd);
+extern void __noreturn mpc8xx_restart(char *cmd);
 extern void mpc8xx_calibrate_decr(void);
 extern int mpc8xx_set_rtc_time(struct rtc_time *tm);
 extern void mpc8xx_get_rtc_time(struct rtc_time *tm);
diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
index bee47a2b23e6..4cea8b1afa44 100644
--- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
@@ -119,9 +119,7 @@ static void __init tqm8xx_setup_arch(void)
 
 static int __init tqm8xx_probe(void)
 {
-	unsigned long node = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(node, "tqc,tqm8xx");
+	return of_machine_is_compatible("tqc,tqm8xx");
 }
 
 static const struct of_device_id of_bus_ids[] __initconst = {
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 77e9b8d591fb..f32edec13fd1 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -1,7 +1,6 @@
 config PPC64
 	bool "64-bit kernel"
 	default n
-	select HAVE_VIRT_CPU_ACCOUNTING
 	select ZLIB_DEFLATE
 	help
 	  This option selects whether a 32-bit or a 64-bit kernel
diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c
index 2fe12046279e..45cb9821173c 100644
--- a/arch/powerpc/platforms/amigaone/setup.c
+++ b/arch/powerpc/platforms/amigaone/setup.c
@@ -123,7 +123,7 @@ static int __init request_isa_regions(void)
 }
 machine_device_initcall(amigaone, request_isa_regions);
 
-void amigaone_restart(char *cmd)
+void __noreturn amigaone_restart(char *cmd)
 {
 	local_irq_disable();
 
@@ -143,9 +143,7 @@ void amigaone_restart(char *cmd)
 
 static int __init amigaone_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "eyetech,amigaone")) {
+	if (of_machine_is_compatible("eyetech,amigaone")) {
 		/*
 		 * Coherent memory access cause complete system lockup! Thus
 		 * disable this CPU feature, even if the CPU needs it.
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 14a582b21274..9027d7c48507 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -178,7 +178,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages,
 	 * default for now.*/
 #ifdef CELL_IOMMU_STRICT_PROTECTION
 	/* to avoid referencing a global, we use a trick here to setup the
-	 * protection bit. "prot" is setup to be 3 fields of 4 bits apprended
+	 * protection bit. "prot" is setup to be 3 fields of 4 bits appended
 	 * together for each of the 3 supported direction values. It is then
 	 * shifted left so that the fields matching the desired direction
 	 * lands on the appropriate bits, and other bits are masked out.
@@ -338,7 +338,7 @@ static unsigned long *cell_iommu_alloc_ptab(struct cbe_iommu *iommu,
 	start_seg = base >> IO_SEGMENT_SHIFT;
 	segments  = size >> IO_SEGMENT_SHIFT;
 	pages_per_segment = 1ull << IO_PAGENO_BITS(page_shift);
-	/* PTEs for each segment must start on a 4K bounday */
+	/* PTEs for each segment must start on a 4K boundary */
 	pages_per_segment = max(pages_per_segment,
 				(1 << 12) / sizeof(unsigned long));
 
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index 36cff28d0293..d3543e68efe8 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -255,13 +255,10 @@ static void __init cell_setup_arch(void)
 
 static int __init cell_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "IBM,CBEA") &&
-	    !of_flat_dt_is_compatible(root, "IBM,CPBW-1.0"))
+	if (!of_machine_is_compatible("IBM,CBEA") &&
+	    !of_machine_is_compatible("IBM,CPBW-1.0"))
 		return 0;
 
-	hpte_init_native();
 	pm_power_off = rtas_power_off;
 
 	return 1;
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 54ee5743cb72..d06dcac66fcb 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -217,7 +217,7 @@ static void spider_irq_cascade(struct irq_desc *desc)
 	chip->irq_eoi(&desc->irq_data);
 }
 
-/* For hooking up the cascace we have a problem. Our device-tree is
+/* For hooking up the cascade we have a problem. Our device-tree is
  * crap and we don't know on which BE iic interrupt we are hooked on at
  * least not the "standard" way. We can reconstitute it based on two
  * informations though: which BE node we are connected to and whether
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 3cbe38fad609..bb4a8e07c229 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -69,7 +69,7 @@ static DEFINE_SPINLOCK(spu_lock);
  * spu_full_list_lock and spu_full_list_mutex held, while iterating
  * through it requires either of these locks.
  *
- * In addition spu_full_list_lock protects all assignmens to
+ * In addition spu_full_list_lock protects all assignments to
  * spu->mm.
  */
 static LIST_HEAD(spu_full_list);
@@ -253,7 +253,7 @@ static inline int __slb_present(struct copro_slb *slbs, int nr_slbs,
  * Setup the SPU kernel SLBs, in preparation for a context save/restore. We
  * need to map both the context save area, and the save/restore code.
  *
- * Because the lscsa and code may cross segment boundaires, we check to see
+ * Because the lscsa and code may cross segment boundaries, we check to see
  * if mappings are required for the start and end of each range. We currently
  * assume that the mappings are smaller that one segment - if not, something
  * is seriously wrong.
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
index c3327f3d8cf7..21b4bfb97200 100644
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ b/arch/powerpc/platforms/cell/spu_manage.c
@@ -535,8 +535,7 @@ static int __init init_affinity(void)
 	if (of_has_vicinity()) {
 		init_affinity_fw();
 	} else {
-		long root = of_get_flat_dt_root();
-		if (of_flat_dt_is_compatible(root, "IBM,CPBW-1.0"))
+		if (of_machine_is_compatible("IBM,CPBW-1.0"))
 			init_affinity_qs20_harcoded();
 		else
 			printk("No affinity configuration found\n");
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 2936a0044c04..06254467e4dd 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -866,7 +866,7 @@ void spufs_wbox_callback(struct spu *spu)
  * - end of the mapped area
  *
  * If the file is opened without O_NONBLOCK, we wait here until
- * space is availabyl, but return when we have been able to
+ * space is available, but return when we have been able to
  * write something.
  */
 static ssize_t spufs_wbox_write(struct file *file, const char __user *buf,
diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c
index 9f79004e6d6f..cfacbee24d7b 100644
--- a/arch/powerpc/platforms/cell/spufs/run.c
+++ b/arch/powerpc/platforms/cell/spufs/run.c
@@ -435,7 +435,7 @@ long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *event)
 
 	/* Note: we don't need to force_sig SIGTRAP on single-step
 	 * since we have TIF_SINGLESTEP set, thus the kernel will do
-	 * it upon return from the syscall anyawy
+	 * it upon return from the syscall anyway.
 	 */
 	if (unlikely(status & SPU_STATUS_SINGLE_STEP))
 		ret = -ERESTARTSYS;
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 998f632e7cce..460f5f31d5cb 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -622,7 +622,7 @@ static struct spu *spu_get_idle(struct spu_context *ctx)
 
 /**
  * find_victim - find a lower priority context to preempt
- * @ctx:	canidate context for running
+ * @ctx:	candidate context for running
  *
  * Returns the freed physical spu to run the new context on.
  */
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index 987d1b8d68e3..bfb300633dfe 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -239,7 +239,7 @@ out:
 	of_node_put(np);
 }
 
-static void briq_restart(char *cmd)
+static void __noreturn briq_restart(char *cmd)
 {
 	local_irq_disable();
 	if (briq_SPOR)
@@ -253,7 +253,7 @@ static void briq_restart(char *cmd)
  * But unfortunately, the firmware does not connect /chosen/{stdin,stdout}
  * the the built-in serial node. Instead, a /failsafe node is created.
  */
-static __init void chrp_init_early(void)
+static __init void chrp_init(void)
 {
 	struct device_node *node;
 	const char *property;
@@ -587,6 +587,8 @@ static int __init chrp_probe(void)
 
 	pm_power_off = rtas_power_off;
 
+	chrp_init();
+
 	return 1;
 }
 
@@ -595,7 +597,6 @@ define_machine(chrp) {
 	.probe			= chrp_probe,
 	.setup_arch		= chrp_setup_arch,
 	.init			= chrp_init2,
-	.init_early		= chrp_init_early,
 	.show_cpuinfo		= chrp_show_cpuinfo,
 	.init_IRQ		= chrp_init_IRQ,
 	.restart		= rtas_restart,
diff --git a/arch/powerpc/platforms/embedded6xx/c2k.c b/arch/powerpc/platforms/embedded6xx/c2k.c
index ebd3963fdf91..d19e4e759597 100644
--- a/arch/powerpc/platforms/embedded6xx/c2k.c
+++ b/arch/powerpc/platforms/embedded6xx/c2k.c
@@ -99,7 +99,7 @@ static void c2k_reset_board(void)
 	out_le32(mv64x60_gpp_reg_base + MV64x60_GPP_VALUE_SET, 0x00080004);
 }
 
-static void c2k_restart(char *cmd)
+static void __noreturn c2k_restart(char *cmd)
 {
 	c2k_reset_board();
 	msleep(100);
@@ -123,15 +123,16 @@ void c2k_show_cpuinfo(struct seq_file *m)
  */
 static int __init c2k_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "GEFanuc,C2K"))
+	if (!of_machine_is_compatible("GEFanuc,C2K"))
 		return 0;
 
 	printk(KERN_INFO "Detected a GEFanuc C2K board\n");
 
 	_set_L2CR(0);
 	_set_L2CR(L2CR_L2E | L2CR_L2PE | L2CR_L2I);
+
+	mv64x60_init_early();
+
 	return 1;
 }
 
@@ -139,7 +140,6 @@ define_machine(c2k) {
 	.name			= "C2K",
 	.probe			= c2k_probe,
 	.setup_arch		= c2k_setup_arch,
-	.init_early		= mv64x60_init_early,
 	.show_cpuinfo		= c2k_show_cpuinfo,
 	.init_IRQ		= mv64x60_init_irq,
 	.get_irq		= mv64x60_get_irq,
diff --git a/arch/powerpc/platforms/embedded6xx/gamecube.c b/arch/powerpc/platforms/embedded6xx/gamecube.c
index fe0ed6ee285e..36789cec957c 100644
--- a/arch/powerpc/platforms/embedded6xx/gamecube.c
+++ b/arch/powerpc/platforms/embedded6xx/gamecube.c
@@ -29,14 +29,14 @@
 #include "usbgecko_udbg.h"
 
 
-static void gamecube_spin(void)
+static void __noreturn gamecube_spin(void)
 {
 	/* spin until power button pressed */
 	for (;;)
 		cpu_relax();
 }
 
-static void gamecube_restart(char *cmd)
+static void __noreturn gamecube_restart(char *cmd)
 {
 	local_irq_disable();
 	flipper_platform_reset();
@@ -49,26 +49,20 @@ static void gamecube_power_off(void)
 	gamecube_spin();
 }
 
-static void gamecube_halt(void)
+static void __noreturn gamecube_halt(void)
 {
 	gamecube_restart(NULL);
 }
 
-static void __init gamecube_init_early(void)
-{
-	ug_udbg_init();
-}
-
 static int __init gamecube_probe(void)
 {
-	unsigned long dt_root;
-
-	dt_root = of_get_flat_dt_root();
-	if (!of_flat_dt_is_compatible(dt_root, "nintendo,gamecube"))
+	if (!of_machine_is_compatible("nintendo,gamecube"))
 		return 0;
 
 	pm_power_off = gamecube_power_off;
 
+	ug_udbg_init();
+
 	return 1;
 }
 
@@ -80,7 +74,6 @@ static void gamecube_shutdown(void)
 define_machine(gamecube) {
 	.name			= "gamecube",
 	.probe			= gamecube_probe,
-	.init_early		= gamecube_init_early,
 	.restart		= gamecube_restart,
 	.halt			= gamecube_halt,
 	.init_IRQ		= flipper_pic_probe,
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c
index 8c305c7c8977..dafba1057a47 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -193,7 +193,7 @@ void holly_show_cpuinfo(struct seq_file *m)
 	seq_printf(m, "machine\t\t: PPC750 GX/CL\n");
 }
 
-void holly_restart(char *cmd)
+void __noreturn holly_restart(char *cmd)
 {
 	__be32 __iomem *ocn_bar1 = NULL;
 	unsigned long bar;
@@ -250,9 +250,7 @@ void holly_halt(void)
  */
 static int __init holly_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "ibm,holly"))
+	if (!of_machine_is_compatible("ibm,holly"))
 		return 0;
 	return 1;
 }
diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c
index 540eeb58d3f0..f29cf29b11f8 100644
--- a/arch/powerpc/platforms/embedded6xx/linkstation.c
+++ b/arch/powerpc/platforms/embedded6xx/linkstation.c
@@ -100,7 +100,7 @@ static void __init linkstation_init_IRQ(void)
 extern void avr_uart_configure(void);
 extern void avr_uart_send(const char);
 
-static void linkstation_restart(char *cmd)
+static void __noreturn linkstation_restart(char *cmd)
 {
 	local_irq_disable();
 
@@ -113,7 +113,7 @@ static void linkstation_restart(char *cmd)
 		avr_uart_send('G');	/* "kick" */
 }
 
-static void linkstation_power_off(void)
+static void __noreturn linkstation_power_off(void)
 {
 	local_irq_disable();
 
@@ -127,7 +127,7 @@ static void linkstation_power_off(void)
 	/* NOTREACHED */
 }
 
-static void linkstation_halt(void)
+static void __noreturn linkstation_halt(void)
 {
 	linkstation_power_off();
 	/* NOTREACHED */
@@ -141,11 +141,7 @@ static void linkstation_show_cpuinfo(struct seq_file *m)
 
 static int __init linkstation_probe(void)
 {
-	unsigned long root;
-
-	root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "linkstation"))
+	if (!of_machine_is_compatible("linkstation"))
 		return 0;
 
 	pm_power_off = linkstation_power_off;
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index df4ad95f183e..80804f9916ee 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -146,7 +146,7 @@ void mpc7448_hpc2_show_cpuinfo(struct seq_file *m)
 	seq_printf(m, "vendor\t\t: Freescale Semiconductor\n");
 }
 
-void mpc7448_hpc2_restart(char *cmd)
+static void __noreturn mpc7448_hpc2_restart(char *cmd)
 {
 	local_irq_disable();
 
@@ -161,9 +161,7 @@ void mpc7448_hpc2_restart(char *cmd)
  */
 static int __init mpc7448_hpc2_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "mpc74xx"))
+	if (!of_machine_is_compatible("mpc74xx"))
 		return 0;
 	return 1;
 }
diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c
index 8f65aa3747f5..ed7321d6772e 100644
--- a/arch/powerpc/platforms/embedded6xx/mvme5100.c
+++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c
@@ -177,7 +177,7 @@ static void mvme5100_show_cpuinfo(struct seq_file *m)
 	seq_puts(m, "Machine\t\t: MVME5100\n");
 }
 
-static void mvme5100_restart(char *cmd)
+static void __noreturn mvme5100_restart(char *cmd)
 {
 
 	local_irq_disable();
@@ -194,9 +194,7 @@ static void mvme5100_restart(char *cmd)
  */
 static int __init mvme5100_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "MVME5100");
+	return of_machine_is_compatible("MVME5100");
 }
 
 static int __init probe_of_platform_devices(void)
diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c
index d572833ebd00..471a50bcd074 100644
--- a/arch/powerpc/platforms/embedded6xx/storcenter.c
+++ b/arch/powerpc/platforms/embedded6xx/storcenter.c
@@ -96,7 +96,7 @@ static void __init storcenter_init_IRQ(void)
 	mpic_init(mpic);
 }
 
-static void storcenter_restart(char *cmd)
+static void __noreturn storcenter_restart(char *cmd)
 {
 	local_irq_disable();
 
@@ -109,9 +109,7 @@ static void storcenter_restart(char *cmd)
 
 static int __init storcenter_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "iomega,storcenter");
+	return of_machine_is_compatible("iomega,storcenter");
 }
 
 define_machine(storcenter){
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index 352592d3e44e..3fd683e40bc9 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -112,7 +112,7 @@ unsigned long __init wii_mmu_mapin_mem2(unsigned long top)
 	return delta + bl;
 }
 
-static void wii_spin(void)
+static void __noreturn wii_spin(void)
 {
 	local_irq_disable();
 	for (;;)
@@ -160,7 +160,7 @@ static void __init wii_setup_arch(void)
 	}
 }
 
-static void wii_restart(char *cmd)
+static void __noreturn wii_restart(char *cmd)
 {
 	local_irq_disable();
 
@@ -185,18 +185,13 @@ static void wii_power_off(void)
 	wii_spin();
 }
 
-static void wii_halt(void)
+static void __noreturn wii_halt(void)
 {
 	if (ppc_md.restart)
 		ppc_md.restart(NULL);
 	wii_spin();
 }
 
-static void __init wii_init_early(void)
-{
-	ug_udbg_init();
-}
-
 static void __init wii_pic_probe(void)
 {
 	flipper_pic_probe();
@@ -205,14 +200,13 @@ static void __init wii_pic_probe(void)
 
 static int __init wii_probe(void)
 {
-	unsigned long dt_root;
-
-	dt_root = of_get_flat_dt_root();
-	if (!of_flat_dt_is_compatible(dt_root, "nintendo,wii"))
+	if (!of_machine_is_compatible("nintendo,wii"))
 		return 0;
 
 	pm_power_off = wii_power_off;
 
+	ug_udbg_init();
+
 	return 1;
 }
 
@@ -225,7 +219,6 @@ static void wii_shutdown(void)
 define_machine(wii) {
 	.name			= "wii",
 	.probe			= wii_probe,
-	.init_early		= wii_init_early,
 	.setup_arch		= wii_setup_arch,
 	.restart		= wii_restart,
 	.halt			= wii_halt,
diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c
index a923230e575b..a2f89e6326ce 100644
--- a/arch/powerpc/platforms/maple/pci.c
+++ b/arch/powerpc/platforms/maple/pci.c
@@ -568,6 +568,26 @@ void maple_pci_irq_fixup(struct pci_dev *dev)
 	DBG(" <- maple_pci_irq_fixup\n");
 }
 
+static int maple_pci_root_bridge_prepare(struct pci_host_bridge *bridge)
+{
+	struct pci_controller *hose = pci_bus_to_host(bridge->bus);
+	struct device_node *np, *child;
+
+	if (hose != u3_agp)
+		return 0;
+
+	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
+	 * assume there is no P2P bridge on the AGP bus, which should be a
+	 * safe assumptions hopefully.
+	 */
+	np = hose->dn;
+	PCI_DN(np)->busno = 0xf0;
+	for_each_child_of_node(np, child)
+		PCI_DN(child)->busno = 0xf0;
+
+	return 0;
+}
+
 void __init maple_pci_init(void)
 {
 	struct device_node *np, *root;
@@ -605,19 +625,7 @@ void __init maple_pci_init(void)
 	if (ht && maple_add_bridge(ht) != 0)
 		of_node_put(ht);
 
-	/* Setup the linkage between OF nodes and PHBs */ 
-	pci_devs_phb_init();
-
-	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
-	 * assume there is no P2P bridge on the AGP bus, which should be a
-	 * safe assumptions hopefully.
-	 */
-	if (u3_agp) {
-		struct device_node *np = u3_agp->dn;
-		PCI_DN(np)->busno = 0xf0;
-		for (np = np->child; np; np = np->sibling)
-			PCI_DN(np)->busno = 0xf0;
-	}
+	ppc_md.pcibios_root_bridge_prepare = maple_pci_root_bridge_prepare;
 
 	/* Tell pci.c to not change any resource allocations.  */
 	pci_add_flags(PCI_PROBE_ONLY);
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index a837188544c8..3c30c7a4534d 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -94,7 +94,7 @@ static unsigned long maple_find_nvram_base(void)
 	return result;
 }
 
-static void maple_restart(char *cmd)
+static void __noreturn maple_restart(char *cmd)
 {
 	unsigned int maple_nvram_base;
 	const unsigned int *maple_nvram_offset, *maple_nvram_command;
@@ -119,9 +119,10 @@ static void maple_restart(char *cmd)
 	for (;;) ;
  fail:
 	printk(KERN_EMERG "Maple: Manual Restart Required\n");
+	for (;;) ;
 }
 
-static void maple_power_off(void)
+static void __noreturn maple_power_off(void)
 {
 	unsigned int maple_nvram_base;
 	const unsigned int *maple_nvram_offset, *maple_nvram_command;
@@ -146,9 +147,10 @@ static void maple_power_off(void)
 	for (;;) ;
  fail:
 	printk(KERN_EMERG "Maple: Manual Power-Down Required\n");
+	for (;;) ;
 }
 
-static void maple_halt(void)
+static void __noreturn maple_halt(void)
 {
 	maple_power_off();
 }
@@ -196,18 +198,6 @@ void __init maple_setup_arch(void)
 	mmio_nvram_init();
 }
 
-/* 
- * Early initialization.
- */
-static void __init maple_init_early(void)
-{
-	DBG(" -> maple_init_early\n");
-
-	iommu_init_early_dart(&maple_pci_controller_ops);
-
-	DBG(" <- maple_init_early\n");
-}
-
 /*
  * This is almost identical to pSeries and CHRP. We need to make that
  * code generic at one point, with appropriate bits in the device-tree to
@@ -298,22 +288,14 @@ static void __init maple_progress(char *s, unsigned short hex)
  */
 static int __init maple_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "Momentum,Maple") &&
-	    !of_flat_dt_is_compatible(root, "Momentum,Apache"))
+	if (!of_machine_is_compatible("Momentum,Maple") &&
+	    !of_machine_is_compatible("Momentum,Apache"))
 		return 0;
-	/*
-	 * On U3, the DART (iommu) must be allocated now since it
-	 * has an impact on htab_initialize (due to the large page it
-	 * occupies having to be broken up so the DART itself is not
-	 * part of the cacheable linar mapping
-	 */
-	alloc_dart_table();
 
-	hpte_init_native();
 	pm_power_off = maple_power_off;
 
+	iommu_init_early_dart(&maple_pci_controller_ops);
+
 	return 1;
 }
 
@@ -321,7 +303,6 @@ define_machine(maple) {
 	.name			= "Maple",
 	.probe			= maple_probe,
 	.setup_arch		= maple_setup_arch,
-	.init_early		= maple_init_early,
 	.init_IRQ		= maple_init_IRQ,
 	.pci_irq_fixup		= maple_pci_irq_fixup,
 	.pci_get_legacy_ide_irq	= maple_pci_get_legacy_ide_irq,
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index c929644e74a6..43dd3fb514e0 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -202,6 +202,11 @@ int __init iob_init(struct device_node *dn)
 
 	pr_debug(" -> %s\n", __func__);
 
+	/* For 2G space, 8x64 pages (2^21 bytes) is max total l2 size */
+	iob_l2_base = (u32 *)__va(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000));
+
+	printk(KERN_INFO "IOBMAP L2 allocated at: %p\n", iob_l2_base);
+
 	/* Allocate a spare page to map all invalid IOTLB pages. */
 	tmp = memblock_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE);
 	if (!tmp)
@@ -260,13 +265,3 @@ void __init iommu_init_early_pasemi(void)
 	set_pci_dma_ops(&dma_iommu_ops);
 }
 
-void __init alloc_iobmap_l2(void)
-{
-#ifndef CONFIG_PPC_PASEMI_IOMMU
-	return;
-#endif
-	/* For 2G space, 8x64 pages (2^21 bytes) is max total l2 size */
-	iob_l2_base = (u32 *)__va(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000));
-
-	printk(KERN_INFO "IOBMAP L2 allocated at: %p\n", iob_l2_base);
-}
diff --git a/arch/powerpc/platforms/pasemi/pasemi.h b/arch/powerpc/platforms/pasemi/pasemi.h
index 11f230a48227..74cbcb357612 100644
--- a/arch/powerpc/platforms/pasemi/pasemi.h
+++ b/arch/powerpc/platforms/pasemi/pasemi.h
@@ -8,7 +8,6 @@ extern void pas_pci_dma_dev_setup(struct pci_dev *dev);
 
 extern void __iomem *pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset);
 
-extern void __init alloc_iobmap_l2(void);
 extern void __init pasemi_map_registers(void);
 
 /* Power savings modes, implemented in asm */
diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c
index f3a68a0fef23..10c4e8fc6ea9 100644
--- a/arch/powerpc/platforms/pasemi/pci.c
+++ b/arch/powerpc/platforms/pasemi/pci.c
@@ -229,9 +229,6 @@ void __init pas_pci_init(void)
 			of_node_get(np);
 
 	of_node_put(root);
-
-	/* Setup the linkage between OF nodes and PHBs */
-	pci_devs_phb_init();
 }
 
 void __iomem *pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset)
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index d71b2c7e8403..e86c1bd08f1f 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -62,7 +62,7 @@ static int num_mce_regs;
 static int nmi_virq = NO_IRQ;
 
 
-static void pas_restart(char *cmd)
+static void __noreturn pas_restart(char *cmd)
 {
 	/* Need to put others cpu in hold loop so they're not sleeping */
 	smp_send_stop();
@@ -339,11 +339,6 @@ out:
 	return !!(srr1 & 0x2);
 }
 
-static void __init pas_init_early(void)
-{
-	iommu_init_early_pasemi();
-}
-
 #ifdef CONFIG_PCMCIA
 static int pcmcia_notify(struct notifier_block *nb, unsigned long action,
 			 void *data)
@@ -420,15 +415,11 @@ machine_device_initcall(pasemi, pasemi_publish_devices);
  */
 static int __init pas_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "PA6T-1682M") &&
-	    !of_flat_dt_is_compatible(root, "pasemi,pwrficient"))
+	if (!of_machine_is_compatible("PA6T-1682M") &&
+	    !of_machine_is_compatible("pasemi,pwrficient"))
 		return 0;
 
-	hpte_init_native();
-
-	alloc_iobmap_l2();
+	iommu_init_early_pasemi();
 
 	return 1;
 }
@@ -437,7 +428,6 @@ define_machine(pasemi) {
 	.name			= "PA Semi PWRficient",
 	.probe			= pas_probe,
 	.setup_arch		= pas_setup_arch,
-	.init_early		= pas_init_early,
 	.init_IRQ		= pas_init_IRQ,
 	.get_irq		= mpic_get_irq,
 	.restart		= pas_restart,
diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c
index 7553b6a77c64..6d6f277477aa 100644
--- a/arch/powerpc/platforms/powermac/low_i2c.c
+++ b/arch/powerpc/platforms/powermac/low_i2c.c
@@ -15,7 +15,7 @@
  * This file thus provides a simple low level unified i2c interface for
  * powermac that covers the various types of i2c busses used in Apple machines.
  * For now, keywest, PMU and SMU, though we could add Cuda, or other bit
- * banging busses found on older chipstes in earlier machines if we ever need
+ * banging busses found on older chipsets in earlier machines if we ever need
  * one of them.
  *
  * The drivers in this file are synchronous/blocking. In addition, the
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index 59ab16fa600f..6e06c3be2e9a 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -878,6 +878,29 @@ void pmac_pci_irq_fixup(struct pci_dev *dev)
 #endif /* CONFIG_PPC32 */
 }
 
+#ifdef CONFIG_PPC64
+static int pmac_pci_root_bridge_prepare(struct pci_host_bridge *bridge)
+{
+	struct pci_controller *hose = pci_bus_to_host(bridge->bus);
+	struct device_node *np, *child;
+
+	if (hose != u3_agp)
+		return 0;
+
+	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
+	 * assume there is no P2P bridge on the AGP bus, which should be a
+	 * safe assumptions for now. We should do something better in the
+	 * future though
+	 */
+	np = hose->dn;
+	PCI_DN(np)->busno = 0xf0;
+	for_each_child_of_node(np, child)
+		PCI_DN(child)->busno = 0xf0;
+
+	return 0;
+}
+#endif /* CONFIG_PPC64 */
+
 void __init pmac_pci_init(void)
 {
 	struct device_node *np, *root;
@@ -914,20 +937,7 @@ void __init pmac_pci_init(void)
 	if (ht && pmac_add_bridge(ht) != 0)
 		of_node_put(ht);
 
-	/* Setup the linkage between OF nodes and PHBs */
-	pci_devs_phb_init();
-
-	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
-	 * assume there is no P2P bridge on the AGP bus, which should be a
-	 * safe assumptions for now. We should do something better in the
-	 * future though
-	 */
-	if (u3_agp) {
-		struct device_node *np = u3_agp->dn;
-		PCI_DN(np)->busno = 0xf0;
-		for (np = np->child; np; np = np->sibling)
-			PCI_DN(np)->busno = 0xf0;
-	}
+	ppc_md.pcibios_root_bridge_prepare = pmac_pci_root_bridge_prepare;
 	/* pmac_check_ht_link(); */
 
 #else /* CONFIG_PPC64 */
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 8dd78f4e1af4..6b4e9d181126 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -52,7 +52,6 @@
 #include <linux/suspend.h>
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
-#include <linux/memblock.h>
 
 #include <asm/reg.h>
 #include <asm/sections.h>
@@ -97,11 +96,6 @@ int sccdbg;
 sys_ctrler_t sys_ctrler = SYS_CTRLER_UNKNOWN;
 EXPORT_SYMBOL(sys_ctrler);
 
-#ifdef CONFIG_PMAC_SMU
-unsigned long smu_cmdbuf_abs;
-EXPORT_SYMBOL(smu_cmdbuf_abs);
-#endif
-
 static void pmac_show_cpuinfo(struct seq_file *m)
 {
 	struct device_node *np;
@@ -325,7 +319,6 @@ static void __init pmac_setup_arch(void)
     defined(CONFIG_PPC64)
 	pmac_nvram_init();
 #endif
-
 #ifdef CONFIG_PPC32
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (initrd_start)
@@ -360,12 +353,12 @@ static int pmac_late_init(void)
 machine_late_initcall(powermac, pmac_late_init);
 
 /*
- * This is __init_refok because we check for "initializing" before
+ * This is __ref because we check for "initializing" before
  * touching any of the __init sensitive things and "initializing"
  * will be false after __init time. This can't be __init because it
  * can be called whenever a disk is first accessed.
  */
-void __init_refok note_bootable_part(dev_t dev, int part, int goodness)
+void __ref note_bootable_part(dev_t dev, int part, int goodness)
 {
 	char *p;
 
@@ -383,7 +376,7 @@ void __init_refok note_bootable_part(dev_t dev, int part, int goodness)
 }
 
 #ifdef CONFIG_ADB_CUDA
-static void cuda_restart(void)
+static void __noreturn cuda_restart(void)
 {
 	struct adb_request req;
 
@@ -392,7 +385,7 @@ static void cuda_restart(void)
 		cuda_poll();
 }
 
-static void cuda_shutdown(void)
+static void __noreturn cuda_shutdown(void)
 {
 	struct adb_request req;
 
@@ -416,7 +409,7 @@ static void cuda_shutdown(void)
 #define smu_shutdown()
 #endif
 
-static void pmac_restart(char *cmd)
+static void __noreturn pmac_restart(char *cmd)
 {
 	switch (sys_ctrler) {
 	case SYS_CTRLER_CUDA:
@@ -430,9 +423,10 @@ static void pmac_restart(char *cmd)
 		break;
 	default: ;
 	}
+	while (1) ;
 }
 
-static void pmac_power_off(void)
+static void __noreturn pmac_power_off(void)
 {
 	switch (sys_ctrler) {
 	case SYS_CTRLER_CUDA:
@@ -446,9 +440,10 @@ static void pmac_power_off(void)
 		break;
 	default: ;
 	}
+	while (1) ;
 }
 
-static void
+static void __noreturn
 pmac_halt(void)
 {
 	pmac_power_off();
@@ -457,7 +452,7 @@ pmac_halt(void)
 /* 
  * Early initialization.
  */
-static void __init pmac_init_early(void)
+static void __init pmac_init(void)
 {
 	/* Enable early btext debug if requested */
 	if (strstr(boot_command_line, "btextdbg")) {
@@ -489,9 +484,6 @@ static int __init pmac_declare_of_platform_devices(void)
 {
 	struct device_node *np;
 
-	if (machine_is(chrp))
-		return -1;
-
 	np = of_find_node_by_name(NULL, "valkyrie");
 	if (np) {
 		of_platform_device_create(np, "valkyrie", NULL);
@@ -598,24 +590,10 @@ console_initcall(check_pmac_serial_console);
  */
 static int __init pmac_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "Power Macintosh") &&
-	    !of_flat_dt_is_compatible(root, "MacRISC"))
+	if (!of_machine_is_compatible("Power Macintosh") &&
+	    !of_machine_is_compatible("MacRISC"))
 		return 0;
 
-#ifdef CONFIG_PPC64
-	/*
-	 * On U3, the DART (iommu) must be allocated now since it
-	 * has an impact on htab_initialize (due to the large page it
-	 * occupies having to be broken up so the DART itself is not
-	 * part of the cacheable linar mapping
-	 */
-	alloc_dart_table();
-
-	hpte_init_native();
-#endif
-
 #ifdef CONFIG_PPC32
 	/* isa_io_base gets set in pmac_pci_init */
 	ISA_DMA_THRESHOLD = ~0L;
@@ -623,17 +601,10 @@ static int __init pmac_probe(void)
 	DMA_MODE_WRITE = 2;
 #endif /* CONFIG_PPC32 */
 
-#ifdef CONFIG_PMAC_SMU
-	/*
-	 * SMU based G5s need some memory below 2Gb, at least the current
-	 * driver needs that. We have to allocate it now. We allocate 4k
-	 * (1 small page) for now.
-	 */
-	smu_cmdbuf_abs = memblock_alloc_base(4096, 4096, 0x80000000UL);
-#endif /* CONFIG_PMAC_SMU */
-
 	pm_power_off = pmac_power_off;
 
+	pmac_init();
+
 	return 1;
 }
 
@@ -641,7 +612,6 @@ define_machine(powermac) {
 	.name			= "PowerMac",
 	.probe			= pmac_probe,
 	.setup_arch		= pmac_setup_arch,
-	.init_early		= pmac_init_early,
 	.show_cpuinfo		= pmac_show_cpuinfo,
 	.init_IRQ		= pmac_pic_init,
 	.get_irq		= NULL,	/* changed later */
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 28a147ca32ba..834868b9fdc9 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -857,9 +857,8 @@ static int smp_core99_cpu_notify(struct notifier_block *self,
 {
 	int rc;
 
-	switch(action) {
+	switch(action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
 		/* Open i2c bus if it was used for tb sync */
 		if (pmac_tb_clock_chip_host) {
 			rc = pmac_i2c_open(pmac_tb_clock_chip_host, 1);
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index cd9711e72df6..b5d98cb3f482 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -6,6 +6,7 @@ obj-y			+= opal-kmsg.o
 
 obj-$(CONFIG_SMP)	+= smp.o subcore.o subcore-asm.o
 obj-$(CONFIG_PCI)	+= pci.o pci-ioda.o npu-dma.o
+obj-$(CONFIG_CXL_BASE)	+= pci-cxl.o
 obj-$(CONFIG_EEH)	+= eeh-powernv.o
 obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
 obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 9226df11bf39..86544ea85dc3 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -36,6 +36,7 @@
 #include <asm/msi_bitmap.h>
 #include <asm/opal.h>
 #include <asm/ppc-pci.h>
+#include <asm/pnv-pci.h>
 
 #include "powernv.h"
 #include "pci.h"
@@ -717,12 +718,12 @@ static int pnv_eeh_get_state(struct eeh_pe *pe, int *delay)
 	return ret;
 }
 
-static s64 pnv_eeh_phb_poll(struct pnv_phb *phb)
+static s64 pnv_eeh_poll(unsigned long id)
 {
 	s64 rc = OPAL_HARDWARE;
 
 	while (1) {
-		rc = opal_pci_poll(phb->opal_id);
+		rc = opal_pci_poll(id);
 		if (rc <= 0)
 			break;
 
@@ -762,7 +763,7 @@ int pnv_eeh_phb_reset(struct pci_controller *hose, int option)
 	 * reset followed by hot reset on root bus. So we also
 	 * need the PCI bus settlement delay.
 	 */
-	rc = pnv_eeh_phb_poll(phb);
+	rc = pnv_eeh_poll(phb->opal_id);
 	if (option == EEH_RESET_DEACTIVATE) {
 		if (system_state < SYSTEM_RUNNING)
 			udelay(1000 * EEH_PE_RST_SETTLE_TIME);
@@ -805,7 +806,7 @@ static int pnv_eeh_root_reset(struct pci_controller *hose, int option)
 		goto out;
 
 	/* Poll state of the PHB until the request is done */
-	rc = pnv_eeh_phb_poll(phb);
+	rc = pnv_eeh_poll(phb->opal_id);
 	if (option == EEH_RESET_DEACTIVATE)
 		msleep(EEH_PE_RST_SETTLE_TIME);
 out:
@@ -815,7 +816,7 @@ out:
 	return 0;
 }
 
-static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option)
+static int __pnv_eeh_bridge_reset(struct pci_dev *dev, int option)
 {
 	struct pci_dn *pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
@@ -866,6 +867,44 @@ static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option)
 	return 0;
 }
 
+static int pnv_eeh_bridge_reset(struct pci_dev *pdev, int option)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct device_node *dn = pci_device_to_OF_node(pdev);
+	uint64_t id = PCI_SLOT_ID(phb->opal_id,
+				  (pdev->bus->number << 8) | pdev->devfn);
+	uint8_t scope;
+	int64_t rc;
+
+	/* Hot reset to the bus if firmware cannot handle */
+	if (!dn || !of_get_property(dn, "ibm,reset-by-firmware", NULL))
+		return __pnv_eeh_bridge_reset(pdev, option);
+
+	switch (option) {
+	case EEH_RESET_FUNDAMENTAL:
+		scope = OPAL_RESET_PCI_FUNDAMENTAL;
+		break;
+	case EEH_RESET_HOT:
+		scope = OPAL_RESET_PCI_HOT;
+		break;
+	case EEH_RESET_DEACTIVATE:
+		return 0;
+	default:
+		dev_dbg(&pdev->dev, "%s: Unsupported reset %d\n",
+			__func__, option);
+		return -EINVAL;
+	}
+
+	rc = opal_pci_reset(id, scope, OPAL_ASSERT_RESET);
+	if (rc <= OPAL_SUCCESS)
+		goto out;
+
+	rc = pnv_eeh_poll(id);
+out:
+	return (rc == OPAL_SUCCESS) ? 0 : -EIO;
+}
+
 void pnv_pci_reset_secondary_bus(struct pci_dev *dev)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index fcc8b6861b63..479c25601612 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -27,9 +27,12 @@
 #include "powernv.h"
 #include "subcore.h"
 
+/* Power ISA 3.0 allows for stop states 0x0 - 0xF */
+#define MAX_STOP_STATE	0xF
+
 static u32 supported_cpuidle_states;
 
-int pnv_save_sprs_for_winkle(void)
+static int pnv_save_sprs_for_deep_states(void)
 {
 	int cpu;
 	int rc;
@@ -50,15 +53,19 @@ int pnv_save_sprs_for_winkle(void)
 		uint64_t pir = get_hard_smp_processor_id(cpu);
 		uint64_t hsprg0_val = (uint64_t)&paca[cpu];
 
-		/*
-		 * HSPRG0 is used to store the cpu's pointer to paca. Hence last
-		 * 3 bits are guaranteed to be 0. Program slw to restore HSPRG0
-		 * with 63rd bit set, so that when a thread wakes up at 0x100 we
-		 * can use this bit to distinguish between fastsleep and
-		 * deep winkle.
-		 */
-		hsprg0_val |= 1;
-
+		if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+			/*
+			 * HSPRG0 is used to store the cpu's pointer to paca.
+			 * Hence last 3 bits are guaranteed to be 0. Program
+			 * slw to restore HSPRG0 with 63rd bit set, so that
+			 * when a thread wakes up at 0x100 we can use this bit
+			 * to distinguish between fastsleep and deep winkle.
+			 * This is not necessary with stop/psscr since PLS
+			 * field of psscr indicates which state we are waking
+			 * up from.
+			 */
+			hsprg0_val |= 1;
+		}
 		rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
 		if (rc != 0)
 			return rc;
@@ -130,8 +137,8 @@ static void pnv_alloc_idle_core_states(void)
 
 	update_subcore_sibling_mask();
 
-	if (supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED)
-		pnv_save_sprs_for_winkle();
+	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT)
+		pnv_save_sprs_for_deep_states();
 }
 
 u32 pnv_get_supported_cpuidle_states(void)
@@ -230,43 +237,162 @@ static DEVICE_ATTR(fastsleep_workaround_applyonce, 0600,
 			show_fastsleep_workaround_applyonce,
 			store_fastsleep_workaround_applyonce);
 
-static int __init pnv_init_idle_states(void)
+
+/*
+ * Used for ppc_md.power_save which needs a function with no parameters
+ */
+static void power9_idle(void)
 {
-	struct device_node *power_mgt;
-	int dt_idle_states;
-	u32 *flags;
-	int i;
+	/* Requesting stop state 0 */
+	power9_idle_stop(0);
+}
+/*
+ * First deep stop state. Used to figure out when to save/restore
+ * hypervisor context.
+ */
+u64 pnv_first_deep_stop_state = MAX_STOP_STATE;
 
-	supported_cpuidle_states = 0;
+/*
+ * Deepest stop idle state. Used when a cpu is offlined
+ */
+u64 pnv_deepest_stop_state;
 
-	if (cpuidle_disable != IDLE_NO_OVERRIDE)
-		goto out;
+/*
+ * Power ISA 3.0 idle initialization.
+ *
+ * POWER ISA 3.0 defines a new SPR Processor stop Status and Control
+ * Register (PSSCR) to control idle behavior.
+ *
+ * PSSCR layout:
+ * ----------------------------------------------------------
+ * | PLS | /// | SD | ESL | EC | PSLL | /// | TR | MTL | RL |
+ * ----------------------------------------------------------
+ * 0      4     41   42    43   44     48    54   56    60
+ *
+ * PSSCR key fields:
+ *	Bits 0:3  - Power-Saving Level Status (PLS). This field indicates the
+ *	lowest power-saving state the thread entered since stop instruction was
+ *	last executed.
+ *
+ *	Bit 41 - Status Disable(SD)
+ *	0 - Shows PLS entries
+ *	1 - PLS entries are all 0
+ *
+ *	Bit 42 - Enable State Loss
+ *	0 - No state is lost irrespective of other fields
+ *	1 - Allows state loss
+ *
+ *	Bit 43 - Exit Criterion
+ *	0 - Exit from power-save mode on any interrupt
+ *	1 - Exit from power-save mode controlled by LPCR's PECE bits
+ *
+ *	Bits 44:47 - Power-Saving Level Limit
+ *	This limits the power-saving level that can be entered into.
+ *
+ *	Bits 60:63 - Requested Level
+ *	Used to specify which power-saving level must be entered on executing
+ *	stop instruction
+ *
+ * @np: /ibm,opal/power-mgt device node
+ * @flags: cpu-idle-state-flags array
+ * @dt_idle_states: Number of idle state entries
+ * Returns 0 on success
+ */
+static int __init pnv_arch300_idle_init(struct device_node *np, u32 *flags,
+					int dt_idle_states)
+{
+	u64 *psscr_val = NULL;
+	int rc = 0, i;
 
-	if (!firmware_has_feature(FW_FEATURE_OPAL))
+	psscr_val = kcalloc(dt_idle_states, sizeof(*psscr_val),
+				GFP_KERNEL);
+	if (!psscr_val) {
+		rc = -1;
+		goto out;
+	}
+	if (of_property_read_u64_array(np,
+		"ibm,cpu-idle-state-psscr",
+		psscr_val, dt_idle_states)) {
+		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-states-psscr in DT\n");
+		rc = -1;
 		goto out;
+	}
 
-	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
-	if (!power_mgt) {
+	/*
+	 * Set pnv_first_deep_stop_state and pnv_deepest_stop_state.
+	 * pnv_first_deep_stop_state should be set to the first stop
+	 * level to cause hypervisor state loss.
+	 * pnv_deepest_stop_state should be set to the deepest stop
+	 * stop state.
+	 */
+	pnv_first_deep_stop_state = MAX_STOP_STATE;
+	for (i = 0; i < dt_idle_states; i++) {
+		u64 psscr_rl = psscr_val[i] & PSSCR_RL_MASK;
+
+		if ((flags[i] & OPAL_PM_LOSE_FULL_CONTEXT) &&
+		     (pnv_first_deep_stop_state > psscr_rl))
+			pnv_first_deep_stop_state = psscr_rl;
+
+		if (pnv_deepest_stop_state < psscr_rl)
+			pnv_deepest_stop_state = psscr_rl;
+	}
+
+out:
+	kfree(psscr_val);
+	return rc;
+}
+
+/*
+ * Probe device tree for supported idle states
+ */
+static void __init pnv_probe_idle_states(void)
+{
+	struct device_node *np;
+	int dt_idle_states;
+	u32 *flags = NULL;
+	int i;
+
+	np = of_find_node_by_path("/ibm,opal/power-mgt");
+	if (!np) {
 		pr_warn("opal: PowerMgmt Node not found\n");
 		goto out;
 	}
-	dt_idle_states = of_property_count_u32_elems(power_mgt,
+	dt_idle_states = of_property_count_u32_elems(np,
 			"ibm,cpu-idle-state-flags");
 	if (dt_idle_states < 0) {
 		pr_warn("cpuidle-powernv: no idle states found in the DT\n");
 		goto out;
 	}
 
-	flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL);
-	if (of_property_read_u32_array(power_mgt,
+	flags = kcalloc(dt_idle_states, sizeof(*flags),  GFP_KERNEL);
+
+	if (of_property_read_u32_array(np,
 			"ibm,cpu-idle-state-flags", flags, dt_idle_states)) {
 		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n");
-		goto out_free;
+		goto out;
+	}
+
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (pnv_arch300_idle_init(np, flags, dt_idle_states))
+			goto out;
 	}
 
 	for (i = 0; i < dt_idle_states; i++)
 		supported_cpuidle_states |= flags[i];
 
+out:
+	kfree(flags);
+}
+static int __init pnv_init_idle_states(void)
+{
+
+	supported_cpuidle_states = 0;
+
+	if (cpuidle_disable != IDLE_NO_OVERRIDE)
+		goto out;
+
+	pnv_probe_idle_states();
+
 	if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
 		patch_instruction(
 			(unsigned int *)pnv_fastsleep_workaround_at_entry,
@@ -285,8 +411,12 @@ static int __init pnv_init_idle_states(void)
 	}
 
 	pnv_alloc_idle_core_states();
-out_free:
-	kfree(flags);
+
+	if (supported_cpuidle_states & OPAL_PM_NAP_ENABLED)
+		ppc_md.power_save = power7_idle;
+	else if (supported_cpuidle_states & OPAL_PM_STOP_INST_FAST)
+		ppc_md.power_save = power9_idle;
+
 out:
 	return 0;
 }
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 0459e100b4e7..4383a5ff82ba 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -180,7 +180,7 @@ long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num,
 		pe_err(npe, "Failed to configure TCE table, err %lld\n", rc);
 		return rc;
 	}
-	pnv_pci_ioda2_tce_invalidate_entire(phb, false);
+	pnv_pci_phb3_tce_invalidate_entire(phb, false);
 
 	/* Add the table to the list so its TCE cache will get invalidated */
 	pnv_pci_link_table_and_group(phb->hose->node, num,
@@ -204,7 +204,7 @@ long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num)
 		pe_err(npe, "Unmapping failed, ret = %lld\n", rc);
 		return rc;
 	}
-	pnv_pci_ioda2_tce_invalidate_entire(phb, false);
+	pnv_pci_phb3_tce_invalidate_entire(phb, false);
 
 	pnv_pci_unlink_table_and_group(npe->table_group.tables[num],
 			&npe->table_group);
@@ -270,7 +270,7 @@ static int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe)
 			0 /* bypass base */, top);
 
 	if (rc == OPAL_SUCCESS)
-		pnv_pci_ioda2_tce_invalidate_entire(phb, false);
+		pnv_pci_phb3_tce_invalidate_entire(phb, false);
 
 	return rc;
 }
@@ -334,7 +334,7 @@ void pnv_npu_take_ownership(struct pnv_ioda_pe *npe)
 		pe_err(npe, "Failed to disable bypass, err %lld\n", rc);
 		return;
 	}
-	pnv_pci_ioda2_tce_invalidate_entire(npe->phb, false);
+	pnv_pci_phb3_tce_invalidate_entire(npe->phb, false);
 }
 
 struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe)
diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c
index bdc8c0c71d15..83bebeec0fea 100644
--- a/arch/powerpc/platforms/powernv/opal-async.c
+++ b/arch/powerpc/platforms/powernv/opal-async.c
@@ -117,6 +117,11 @@ int opal_async_wait_response(uint64_t token, struct opal_msg *msg)
 		return -EINVAL;
 	}
 
+	/* Wakeup the poller before we wait for events to speed things
+	 * up on platforms or simulators where the interrupts aren't
+	 * functional.
+	 */
+	opal_wake_poller();
 	wait_event(opal_async_wait, test_bit(token, opal_async_complete_map));
 	memcpy(msg, &opal_async_responses[token], sizeof(*msg));
 
diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c
index 00a29432be39..4495f428b500 100644
--- a/arch/powerpc/platforms/powernv/opal-memory-errors.c
+++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c
@@ -44,7 +44,7 @@ static void handle_memory_error_event(struct OpalMemoryErrorData *merr_evt)
 {
 	uint64_t paddr_start, paddr_end;
 
-	pr_debug("%s: Retrived memory error event, type: 0x%x\n",
+	pr_debug("%s: Retrieved memory error event, type: 0x%x\n",
 		  __func__, merr_evt->type);
 	switch (merr_evt->type) {
 	case OPAL_MEM_ERR_TYPE_RESILIENCE:
diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c
index a06059df9239..308efd170c27 100644
--- a/arch/powerpc/platforms/powernv/opal-sensor.c
+++ b/arch/powerpc/platforms/powernv/opal-sensor.c
@@ -55,7 +55,7 @@ int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data)
 			goto out_token;
 		}
 
-		ret = opal_error_code(be64_to_cpu(msg.params[1]));
+		ret = opal_error_code(opal_get_async_rc(msg));
 		*sensor_data = be32_to_cpu(data);
 		break;
 
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
index afe66c576a38..23fb6647dced 100644
--- a/arch/powerpc/platforms/powernv/opal-sysparam.c
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -67,7 +67,7 @@ static ssize_t opal_get_sys_param(u32 param_id, u32 length, void *buffer)
 		goto out_token;
 	}
 
-	ret = opal_error_code(be64_to_cpu(msg.params[1]));
+	ret = opal_error_code(opal_get_async_rc(msg));
 
 out_token:
 	opal_async_release_token(token);
@@ -103,7 +103,7 @@ static int opal_set_sys_param(u32 param_id, u32 length, void *buffer)
 		goto out_token;
 	}
 
-	ret = opal_error_code(be64_to_cpu(msg.params[1]));
+	ret = opal_error_code(opal_get_async_rc(msg));
 
 out_token:
 	opal_async_release_token(token);
diff --git a/arch/powerpc/platforms/powernv/opal-tracepoints.c b/arch/powerpc/platforms/powernv/opal-tracepoints.c
index e11273b2386d..1e496b780efd 100644
--- a/arch/powerpc/platforms/powernv/opal-tracepoints.c
+++ b/arch/powerpc/platforms/powernv/opal-tracepoints.c
@@ -1,6 +1,7 @@
 #include <linux/percpu.h>
 #include <linux/jump_label.h>
 #include <asm/trace.h>
+#include <asm/asm-prototypes.h>
 
 #ifdef HAVE_JUMP_LABEL
 struct static_key opal_tracepoint_key = STATIC_KEY_INIT;
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index e45b88a5d7e0..3d29d40eb0e9 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -59,12 +59,11 @@ END_FTR_SECTION(0, 1);						\
 #define OPAL_CALL(name, token)		\
  _GLOBAL_TOC(name);			\
 	mflr	r0;			\
-	std	r0,16(r1);		\
+	std	r0,PPC_LR_STKOFF(r1);	\
 	li	r0,token;		\
 	OPAL_BRANCH(opal_tracepoint_entry) \
 	mfcr	r12;			\
 	stw	r12,8(r1);		\
-	std	r1,PACAR1(r13);		\
 	li	r11,0;			\
 	mfmsr	r12;			\
 	ori	r11,r11,MSR_EE;		\
@@ -92,7 +91,7 @@ opal_return:
 	FIXUP_ENDIAN
 	ld	r2,PACATOC(r13);
 	lwz	r4,8(r1);
-	ld	r5,16(r1);
+	ld	r5,PPC_LR_STKOFF(r1);
 	ld	r6,PACASAVEDMSR(r13);
 	mtspr	SPRN_SRR0,r5;
 	mtspr	SPRN_SRR1,r6;
@@ -127,7 +126,6 @@ opal_tracepoint_entry:
 	mfcr	r12
 	std	r11,16(r1)
 	stw	r12,8(r1)
-	std	r1,PACAR1(r13)
 	li	r11,0
 	mfmsr	r12
 	ori	r11,r11,MSR_EE
@@ -157,43 +155,37 @@ opal_tracepoint_return:
 	blr
 #endif
 
-/*
- * Make opal call in realmode. This is a generic function to be called
- * from realmode. It handles endianness.
- *
- * r13 - paca pointer
- * r1  - stack pointer
- * r0  - opal token
- */
-_GLOBAL(opal_call_realmode)
-	mflr	r12
-	std	r12,PPC_LR_STKOFF(r1)
-	ld	r2,PACATOC(r13)
-	/* Set opal return address */
-	LOAD_REG_ADDR(r12,return_from_opal_call)
-	mtlr	r12
-
-	mfmsr	r12
-#ifdef __LITTLE_ENDIAN__
-	/* Handle endian-ness */
-	li	r11,MSR_LE
-	andc	r12,r12,r11
-#endif
-	mtspr	SPRN_HSRR1,r12
-	LOAD_REG_ADDR(r11,opal)
-	ld	r12,8(r11)
-	ld	r2,0(r11)
-	mtspr	SPRN_HSRR0,r12
+#define OPAL_CALL_REAL(name, token)			\
+ _GLOBAL_TOC(name);					\
+	mflr	r0;					\
+	std	r0,PPC_LR_STKOFF(r1);			\
+	li	r0,token;				\
+	mfcr	r12;					\
+	stw	r12,8(r1);				\
+							\
+	/* Set opal return address */			\
+	LOAD_REG_ADDR(r11, opal_return_realmode);	\
+	mtlr	r11;					\
+	mfmsr	r12;					\
+	li	r11,MSR_LE;				\
+	andc	r12,r12,r11;				\
+	mtspr	SPRN_HSRR1,r12;				\
+	LOAD_REG_ADDR(r11,opal);			\
+	ld	r12,8(r11);				\
+	ld	r2,0(r11);				\
+	mtspr	SPRN_HSRR0,r12;				\
 	hrfid
 
-return_from_opal_call:
-#ifdef __LITTLE_ENDIAN__
+opal_return_realmode:
 	FIXUP_ENDIAN
-#endif
+	ld	r2,PACATOC(r13);
+	lwz	r11,8(r1);
 	ld	r12,PPC_LR_STKOFF(r1)
+	mtcr	r11;
 	mtlr	r12
 	blr
 
+
 OPAL_CALL(opal_invalid_call,			OPAL_INVALID_CALL);
 OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
 OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
@@ -271,6 +263,7 @@ OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
 OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
 OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
 OPAL_CALL(opal_resync_timebase,			OPAL_RESYNC_TIMEBASE);
+OPAL_CALL_REAL(opal_rm_resync_timebase,		OPAL_RESYNC_TIMEBASE);
 OPAL_CALL(opal_check_token,			OPAL_CHECK_TOKEN);
 OPAL_CALL(opal_dump_init,			OPAL_DUMP_INIT);
 OPAL_CALL(opal_dump_info,			OPAL_DUMP_INFO);
@@ -278,6 +271,7 @@ OPAL_CALL(opal_dump_info2,			OPAL_DUMP_INFO2);
 OPAL_CALL(opal_dump_read,			OPAL_DUMP_READ);
 OPAL_CALL(opal_dump_ack,			OPAL_DUMP_ACK);
 OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
+OPAL_CALL(opal_write_oppanel_async,		OPAL_WRITE_OPPANEL_ASYNC);
 OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
 OPAL_CALL(opal_dump_resend_notification,	OPAL_DUMP_RESEND);
 OPAL_CALL(opal_sync_host_reboot,		OPAL_SYNC_HOST_REBOOT);
@@ -285,7 +279,9 @@ OPAL_CALL(opal_sensor_read,			OPAL_SENSOR_READ);
 OPAL_CALL(opal_get_param,			OPAL_GET_PARAM);
 OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
 OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
+OPAL_CALL_REAL(opal_rm_handle_hmi,		OPAL_HANDLE_HMI);
 OPAL_CALL(opal_config_cpu_idle_state,		OPAL_CONFIG_CPU_IDLE_STATE);
+OPAL_CALL_REAL(opal_rm_config_cpu_idle_state,	OPAL_CONFIG_CPU_IDLE_STATE);
 OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
 OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
 OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
@@ -302,3 +298,13 @@ OPAL_CALL(opal_prd_msg,				OPAL_PRD_MSG);
 OPAL_CALL(opal_leds_get_ind,			OPAL_LEDS_GET_INDICATOR);
 OPAL_CALL(opal_leds_set_ind,			OPAL_LEDS_SET_INDICATOR);
 OPAL_CALL(opal_console_flush,			OPAL_CONSOLE_FLUSH);
+OPAL_CALL(opal_get_device_tree,			OPAL_GET_DEVICE_TREE);
+OPAL_CALL(opal_pci_get_presence_state,		OPAL_PCI_GET_PRESENCE_STATE);
+OPAL_CALL(opal_pci_get_power_state,		OPAL_PCI_GET_POWER_STATE);
+OPAL_CALL(opal_pci_set_power_state,		OPAL_PCI_SET_POWER_STATE);
+OPAL_CALL(opal_int_get_xirr,			OPAL_INT_GET_XIRR);
+OPAL_CALL(opal_int_set_cppr,			OPAL_INT_SET_CPPR);
+OPAL_CALL(opal_int_eoi,				OPAL_INT_EOI);
+OPAL_CALL(opal_int_set_mfrr,			OPAL_INT_SET_MFRR);
+OPAL_CALL(opal_pci_tce_kill,			OPAL_PCI_TCE_KILL);
+OPAL_CALL_REAL(opal_rm_pci_tce_kill,		OPAL_PCI_TCE_KILL);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 0256d0729252..8b4fc68cebcb 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -55,8 +55,9 @@ struct device_node *opal_node;
 static DEFINE_SPINLOCK(opal_write_lock);
 static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX];
 static uint32_t opal_heartbeat;
+static struct task_struct *kopald_tsk;
 
-static void opal_reinit_cores(void)
+void opal_configure_cores(void)
 {
 	/* Do the actual re-init, This will clobber all FPRs, VRs, etc...
 	 *
@@ -69,6 +70,10 @@ static void opal_reinit_cores(void)
 #else
 	opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_LE);
 #endif
+
+	/* Restore some bits */
+	if (cur_cpu_spec->cpu_restore)
+		cur_cpu_spec->cpu_restore();
 }
 
 int __init early_init_dt_scan_opal(unsigned long node,
@@ -105,13 +110,6 @@ int __init early_init_dt_scan_opal(unsigned long node,
 		panic("OPAL != V3 detected, no longer supported.\n");
 	}
 
-	/* Reinit all cores with the right endian */
-	opal_reinit_cores();
-
-	/* Restore some bits */
-	if (cur_cpu_spec->cpu_restore)
-		cur_cpu_spec->cpu_restore();
-
 	return 1;
 }
 
@@ -653,6 +651,7 @@ static void opal_i2c_create_devs(void)
 
 static int kopald(void *unused)
 {
+	unsigned long timeout = msecs_to_jiffies(opal_heartbeat) + 1;
 	__be64 events;
 
 	set_freezable();
@@ -660,12 +659,18 @@ static int kopald(void *unused)
 		try_to_freeze();
 		opal_poll_events(&events);
 		opal_handle_events(be64_to_cpu(events));
-		msleep_interruptible(opal_heartbeat);
+		schedule_timeout_interruptible(timeout);
 	} while (!kthread_should_stop());
 
 	return 0;
 }
 
+void opal_wake_poller(void)
+{
+	if (kopald_tsk)
+		wake_up_process(kopald_tsk);
+}
+
 static void opal_init_heartbeat(void)
 {
 	/* Old firwmware, we assume the HVC heartbeat is sufficient */
@@ -674,7 +679,7 @@ static void opal_init_heartbeat(void)
 		opal_heartbeat = 0;
 
 	if (opal_heartbeat)
-		kthread_run(kopald, NULL, "kopald");
+		kopald_tsk = kthread_run(kopald, NULL, "kopald");
 }
 
 static int __init opal_init(void)
@@ -751,6 +756,9 @@ static int __init opal_init(void)
 	opal_pdev_init(opal_node, "ibm,opal-flash");
 	opal_pdev_init(opal_node, "ibm,opal-prd");
 
+	/* Initialise platform device: oppanel interface */
+	opal_pdev_init(opal_node, "ibm,opal-oppanel");
+
 	/* Initialise OPAL kmsg dumper for flushing console on panic */
 	opal_kmsg_init();
 
@@ -885,3 +893,5 @@ EXPORT_SYMBOL_GPL(opal_i2c_request);
 /* Export these symbols for PowerNV LED class driver */
 EXPORT_SYMBOL_GPL(opal_leds_get_ind);
 EXPORT_SYMBOL_GPL(opal_leds_set_ind);
+/* Export this symbol for PowerNV Operator Panel class driver */
+EXPORT_SYMBOL_GPL(opal_write_oppanel_async);
diff --git a/arch/powerpc/platforms/powernv/pci-cxl.c b/arch/powerpc/platforms/powernv/pci-cxl.c
new file mode 100644
index 000000000000..1349a099c74c
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci-cxl.c
@@ -0,0 +1,385 @@
+/*
+ * Copyright 2014-2016 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <asm/pci-bridge.h>
+#include <asm/pnv-pci.h>
+#include <asm/opal.h>
+#include <misc/cxl.h>
+
+#include "pci.h"
+
+struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+
+	return of_node_get(hose->dn);
+}
+EXPORT_SYMBOL(pnv_pci_get_phb_node);
+
+int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pe;
+	int rc;
+
+	pe = pnv_ioda_get_pe(dev);
+	if (!pe)
+		return -ENODEV;
+
+	pe_info(pe, "Switching PHB to CXL\n");
+
+	rc = opal_pci_set_phb_cxl_mode(phb->opal_id, mode, pe->pe_number);
+	if (rc == OPAL_UNSUPPORTED)
+		dev_err(&dev->dev, "Required cxl mode not supported by firmware - update skiboot\n");
+	else if (rc)
+		dev_err(&dev->dev, "opal_pci_set_phb_cxl_mode failed: %i\n", rc);
+
+	return rc;
+}
+EXPORT_SYMBOL(pnv_phb_to_cxl_mode);
+
+/* Find PHB for cxl dev and allocate MSI hwirqs?
+ * Returns the absolute hardware IRQ number
+ */
+int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, num);
+
+	if (hwirq < 0) {
+		dev_warn(&dev->dev, "Failed to find a free MSI\n");
+		return -ENOSPC;
+	}
+
+	return phb->msi_base + hwirq;
+}
+EXPORT_SYMBOL(pnv_cxl_alloc_hwirqs);
+
+void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, num);
+}
+EXPORT_SYMBOL(pnv_cxl_release_hwirqs);
+
+void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
+				  struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int i, hwirq;
+
+	for (i = 1; i < CXL_IRQ_RANGES; i++) {
+		if (!irqs->range[i])
+			continue;
+		pr_devel("cxl release irq range 0x%x: offset: 0x%lx  limit: %ld\n",
+			 i, irqs->offset[i],
+			 irqs->range[i]);
+		hwirq = irqs->offset[i] - phb->msi_base;
+		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq,
+				       irqs->range[i]);
+	}
+}
+EXPORT_SYMBOL(pnv_cxl_release_hwirq_ranges);
+
+int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
+			       struct pci_dev *dev, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int i, hwirq, try;
+
+	memset(irqs, 0, sizeof(struct cxl_irq_ranges));
+
+	/* 0 is reserved for the multiplexed PSL DSI interrupt */
+	for (i = 1; i < CXL_IRQ_RANGES && num; i++) {
+		try = num;
+		while (try) {
+			hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, try);
+			if (hwirq >= 0)
+				break;
+			try /= 2;
+		}
+		if (!try)
+			goto fail;
+
+		irqs->offset[i] = phb->msi_base + hwirq;
+		irqs->range[i] = try;
+		pr_devel("cxl alloc irq range 0x%x: offset: 0x%lx  limit: %li\n",
+			 i, irqs->offset[i], irqs->range[i]);
+		num -= try;
+	}
+	if (num)
+		goto fail;
+
+	return 0;
+fail:
+	pnv_cxl_release_hwirq_ranges(irqs, dev);
+	return -ENOSPC;
+}
+EXPORT_SYMBOL(pnv_cxl_alloc_hwirq_ranges);
+
+int pnv_cxl_get_irq_count(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	return phb->msi_bmp.irq_count;
+}
+EXPORT_SYMBOL(pnv_cxl_get_irq_count);
+
+int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
+			   unsigned int virq)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	unsigned int xive_num = hwirq - phb->msi_base;
+	struct pnv_ioda_pe *pe;
+	int rc;
+
+	if (!(pe = pnv_ioda_get_pe(dev)))
+		return -ENODEV;
+
+	/* Assign XIVE to PE */
+	rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
+	if (rc) {
+		pe_warn(pe, "%s: OPAL error %d setting msi_base 0x%x "
+			"hwirq 0x%x XIVE 0x%x PE\n",
+			pci_name(dev), rc, phb->msi_base, hwirq, xive_num);
+		return -EIO;
+	}
+	pnv_set_msi_irq_chip(phb, virq);
+
+	return 0;
+}
+EXPORT_SYMBOL(pnv_cxl_ioda_msi_setup);
+
+#if IS_MODULE(CONFIG_CXL)
+static inline int get_cxl_module(void)
+{
+	struct module *cxl_module;
+
+	mutex_lock(&module_mutex);
+
+	cxl_module = find_module("cxl");
+	if (cxl_module)
+		__module_get(cxl_module);
+
+	mutex_unlock(&module_mutex);
+
+	if (!cxl_module)
+		return -ENODEV;
+
+	return 0;
+}
+#else
+static inline int get_cxl_module(void) { return 0; }
+#endif
+
+/*
+ * Sets flags and switches the controller ops to enable the cxl kernel api.
+ * Originally the cxl kernel API operated on a virtual PHB, but certain cards
+ * such as the Mellanox CX4 use a peer model instead and for these cards the
+ * cxl kernel api will operate on the real PHB.
+ */
+int pnv_cxl_enable_phb_kernel_api(struct pci_controller *hose, bool enable)
+{
+	struct pnv_phb *phb = hose->private_data;
+	int rc;
+
+	if (!enable) {
+		/*
+		 * Once cxl mode is enabled on the PHB, there is currently no
+		 * known safe method to disable it again, and trying risks a
+		 * checkstop. If we can find a way to safely disable cxl mode
+		 * in the future we can revisit this, but for now the only sane
+		 * thing to do is to refuse to disable cxl mode:
+		 */
+		return -EPERM;
+	}
+
+	/*
+	 * Hold a reference to the cxl module since several PHB operations now
+	 * depend on it, and it would be insane to allow it to be removed so
+	 * long as we are in this mode (and since we can't safely disable this
+	 * mode once enabled...).
+	 */
+	rc = get_cxl_module();
+	if (rc)
+		return rc;
+
+	phb->flags |= PNV_PHB_FLAG_CXL;
+	hose->controller_ops = pnv_cxl_cx4_ioda_controller_ops;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_cxl_enable_phb_kernel_api);
+
+bool pnv_pci_on_cxl_phb(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	return !!(phb->flags & PNV_PHB_FLAG_CXL);
+}
+EXPORT_SYMBOL_GPL(pnv_pci_on_cxl_phb);
+
+struct cxl_afu *pnv_cxl_phb_to_afu(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+
+	return (struct cxl_afu *)phb->cxl_afu;
+}
+EXPORT_SYMBOL_GPL(pnv_cxl_phb_to_afu);
+
+void pnv_cxl_phb_set_peer_afu(struct pci_dev *dev, struct cxl_afu *afu)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	phb->cxl_afu = afu;
+}
+EXPORT_SYMBOL_GPL(pnv_cxl_phb_set_peer_afu);
+
+/*
+ * In the peer cxl model, the XSL/PSL is physical function 0, and will be used
+ * by other functions on the device for memory access and interrupts. When the
+ * other functions are enabled we explicitly take a reference on the cxl
+ * function since they will use it, and allocate a default context associated
+ * with that function just like the vPHB model of the cxl kernel API.
+ */
+bool pnv_cxl_enable_device_hook(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct cxl_afu *afu = phb->cxl_afu;
+
+	if (!pnv_pci_enable_device_hook(dev))
+		return false;
+
+
+	/* No special handling for the cxl function, which is always PF 0 */
+	if (PCI_FUNC(dev->devfn) == 0)
+		return true;
+
+	if (!afu) {
+		dev_WARN(&dev->dev, "Attempted to enable function > 0 on CXL PHB without a peer AFU\n");
+		return false;
+	}
+
+	dev_info(&dev->dev, "Enabling function on CXL enabled PHB with peer AFU\n");
+
+	/* Make sure the peer AFU can't go away while this device is active */
+	cxl_afu_get(afu);
+
+	return cxl_pci_associate_default_context(dev, afu);
+}
+
+void pnv_cxl_disable_device(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct cxl_afu *afu = phb->cxl_afu;
+
+	/* No special handling for cxl function: */
+	if (PCI_FUNC(dev->devfn) == 0)
+		return;
+
+	cxl_pci_disable_device(dev);
+	cxl_afu_put(afu);
+}
+
+/*
+ * This is a special version of pnv_setup_msi_irqs for cards in cxl mode. This
+ * function handles setting up the IVTE entries for the XSL to use.
+ *
+ * We are currently not filling out the MSIX table, since the only currently
+ * supported adapter (CX4) uses a custom MSIX table format in cxl mode and it
+ * is up to their driver to fill that out. In the future we may fill out the
+ * MSIX table (and change the IVTE entries to be an index to the MSIX table)
+ * for adapters implementing the Full MSI-X mode described in the CAIA.
+ */
+int pnv_cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct msi_desc *entry;
+	struct cxl_context *ctx = NULL;
+	unsigned int virq;
+	int hwirq;
+	int afu_irq = 0;
+	int rc;
+
+	if (WARN_ON(!phb) || !phb->msi_bmp.bitmap)
+		return -ENODEV;
+
+	if (pdev->no_64bit_msi && !phb->msi32_support)
+		return -ENODEV;
+
+	rc = cxl_cx4_setup_msi_irqs(pdev, nvec, type);
+	if (rc)
+		return rc;
+
+	for_each_pci_msi_entry(entry, pdev) {
+		if (!entry->msi_attrib.is_64 && !phb->msi32_support) {
+			pr_warn("%s: Supports only 64-bit MSIs\n",
+				pci_name(pdev));
+			return -ENXIO;
+		}
+
+		hwirq = cxl_next_msi_hwirq(pdev, &ctx, &afu_irq);
+		if (WARN_ON(hwirq <= 0))
+			return (hwirq ? hwirq : -ENOMEM);
+
+		virq = irq_create_mapping(NULL, hwirq);
+		if (virq == NO_IRQ) {
+			pr_warn("%s: Failed to map cxl mode MSI to linux irq\n",
+				pci_name(pdev));
+			return -ENOMEM;
+		}
+
+		rc = pnv_cxl_ioda_msi_setup(pdev, hwirq, virq);
+		if (rc) {
+			pr_warn("%s: Failed to setup cxl mode MSI\n", pci_name(pdev));
+			irq_dispose_mapping(virq);
+			return rc;
+		}
+
+		irq_set_msi_desc(virq, entry);
+	}
+
+	return 0;
+}
+
+void pnv_cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct msi_desc *entry;
+	irq_hw_number_t hwirq;
+
+	if (WARN_ON(!phb))
+		return;
+
+	for_each_pci_msi_entry(entry, pdev) {
+		if (entry->irq == NO_IRQ)
+			continue;
+		hwirq = virq_to_hw(entry->irq);
+		irq_set_msi_desc(entry->irq, NULL);
+		irq_dispose_mapping(entry->irq);
+	}
+
+	cxl_cx4_teardown_msi_irqs(pdev);
+}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 3a5ea8236db8..891fc4a453df 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -55,6 +55,7 @@
 #define POWERNV_IOMMU_DEFAULT_LEVELS	1
 #define POWERNV_IOMMU_MAX_LEVELS	5
 
+static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU" };
 static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl);
 
 void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
@@ -141,16 +142,14 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no)
 
 static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
 {
-	unsigned long pe;
+	unsigned long pe = phb->ioda.total_pe_num - 1;
 
-	do {
-		pe = find_next_zero_bit(phb->ioda.pe_alloc,
-					phb->ioda.total_pe_num, 0);
-		if (pe >= phb->ioda.total_pe_num)
-			return NULL;
-	} while(test_and_set_bit(pe, phb->ioda.pe_alloc));
+	for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) {
+		if (!test_and_set_bit(pe, phb->ioda.pe_alloc))
+			return pnv_ioda_init_pe(phb, pe);
+	}
 
-	return pnv_ioda_init_pe(phb, pe);
+	return NULL;
 }
 
 static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
@@ -192,18 +191,15 @@ static int pnv_ioda2_init_m64(struct pnv_phb *phb)
 		goto fail;
 	}
 
-	/* Mark the M64 BAR assigned */
-	set_bit(phb->ioda.m64_bar_idx, &phb->ioda.m64_bar_alloc);
-
 	/*
-	 * Strip off the segment used by the reserved PE, which is
-	 * expected to be 0 or last one of PE capabicity.
+	 * Exclude the segments for reserved and root bus PE, which
+	 * are first or last two PEs.
 	 */
 	r = &phb->hose->mem_resources[1];
 	if (phb->ioda.reserved_pe_idx == 0)
-		r->start += phb->ioda.m64_segsize;
+		r->start += (2 * phb->ioda.m64_segsize);
 	else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1))
-		r->end -= phb->ioda.m64_segsize;
+		r->end -= (2 * phb->ioda.m64_segsize);
 	else
 		pr_warn("  Cannot strip M64 segment for reserved PE#%d\n",
 			phb->ioda.reserved_pe_idx);
@@ -283,14 +279,14 @@ static int pnv_ioda1_init_m64(struct pnv_phb *phb)
 	}
 
 	/*
-	 * Exclude the segment used by the reserved PE, which
-	 * is expected to be 0 or last supported PE#.
+	 * Exclude the segments for reserved and root bus PE, which
+	 * are first or last two PEs.
 	 */
 	r = &phb->hose->mem_resources[1];
 	if (phb->ioda.reserved_pe_idx == 0)
-		r->start += phb->ioda.m64_segsize;
+		r->start += (2 * phb->ioda.m64_segsize);
 	else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1))
-		r->end -= phb->ioda.m64_segsize;
+		r->end -= (2 * phb->ioda.m64_segsize);
 	else
 		WARN(1, "Wrong reserved PE#%d on PHB#%d\n",
 		     phb->ioda.reserved_pe_idx, phb->hose->global_number);
@@ -405,6 +401,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 	struct pci_controller *hose = phb->hose;
 	struct device_node *dn = hose->dn;
 	struct resource *res;
+	u32 m64_range[2], i;
 	const u32 *r;
 	u64 pci_addr;
 
@@ -425,6 +422,30 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 		return;
 	}
 
+	/*
+	 * Find the available M64 BAR range and pickup the last one for
+	 * covering the whole 64-bits space. We support only one range.
+	 */
+	if (of_property_read_u32_array(dn, "ibm,opal-available-m64-ranges",
+				       m64_range, 2)) {
+		/* In absence of the property, assume 0..15 */
+		m64_range[0] = 0;
+		m64_range[1] = 16;
+	}
+	/* We only support 64 bits in our allocator */
+	if (m64_range[1] > 63) {
+		pr_warn("%s: Limiting M64 range to 63 (from %d) on PHB#%x\n",
+			__func__, m64_range[1], phb->hose->global_number);
+		m64_range[1] = 63;
+	}
+	/* Empty range, no m64 */
+	if (m64_range[1] <= m64_range[0]) {
+		pr_warn("%s: M64 empty, disabling M64 usage on PHB#%x\n",
+			__func__, phb->hose->global_number);
+		return;
+	}
+
+	/* Configure M64 informations */
 	res = &hose->mem_resources[1];
 	res->name = dn->full_name;
 	res->start = of_translate_address(dn, r + 2);
@@ -437,11 +458,28 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 	phb->ioda.m64_segsize = phb->ioda.m64_size / phb->ioda.total_pe_num;
 	phb->ioda.m64_base = pci_addr;
 
-	pr_info(" MEM64 0x%016llx..0x%016llx -> 0x%016llx\n",
-			res->start, res->end, pci_addr);
+	/* This lines up nicely with the display from processing OF ranges */
+	pr_info(" MEM 0x%016llx..0x%016llx -> 0x%016llx (M64 #%d..%d)\n",
+		res->start, res->end, pci_addr, m64_range[0],
+		m64_range[0] + m64_range[1] - 1);
+
+	/* Mark all M64 used up by default */
+	phb->ioda.m64_bar_alloc = (unsigned long)-1;
 
 	/* Use last M64 BAR to cover M64 window */
-	phb->ioda.m64_bar_idx = 15;
+	m64_range[1]--;
+	phb->ioda.m64_bar_idx = m64_range[0] + m64_range[1];
+
+	pr_info(" Using M64 #%d as default window\n", phb->ioda.m64_bar_idx);
+
+	/* Mark remaining ones free */
+	for (i = m64_range[0]; i < m64_range[1]; i++)
+		clear_bit(i, &phb->ioda.m64_bar_alloc);
+
+	/*
+	 * Setup init functions for M64 based on IODA version, IODA3 uses
+	 * the IODA2 code.
+	 */
 	if (phb->type == PNV_PHB_IODA1)
 		phb->init_m64 = pnv_ioda1_init_m64;
 	else
@@ -596,7 +634,7 @@ static int pnv_ioda_get_pe_state(struct pnv_phb *phb, int pe_no)
  * but in the meantime, we need to protect them to avoid warnings
  */
 #ifdef CONFIG_PCI_MSI
-static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev)
+struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct pnv_phb *phb = hose->private_data;
@@ -714,7 +752,6 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb,
 	return 0;
 }
 
-#ifdef CONFIG_PCI_IOV
 static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 {
 	struct pci_dev *parent;
@@ -749,9 +786,11 @@ static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		}
 		rid_end = pe->rid + (count << 8);
 	} else {
+#ifdef CONFIG_PCI_IOV
 		if (pe->flags & PNV_IODA_PE_VF)
 			parent = pe->parent_dev;
 		else
+#endif
 			parent = pe->pdev->bus->self;
 		bcomp = OpalPciBusAll;
 		dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
@@ -761,7 +800,7 @@ static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 
 	/* Clear the reverse map */
 	for (rid = pe->rid; rid < rid_end; rid++)
-		phb->ioda.pe_rmap[rid] = 0;
+		phb->ioda.pe_rmap[rid] = IODA_INVALID_PE;
 
 	/* Release from all parents PELT-V */
 	while (parent) {
@@ -789,11 +828,12 @@ static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 
 	pe->pbus = NULL;
 	pe->pdev = NULL;
+#ifdef CONFIG_PCI_IOV
 	pe->parent_dev = NULL;
+#endif
 
 	return 0;
 }
-#endif /* CONFIG_PCI_IOV */
 
 static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 {
@@ -1024,6 +1064,16 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
 				pci_name(dev));
 			continue;
 		}
+
+		/*
+		 * In partial hotplug case, the PCI device might be still
+		 * associated with the PE and needn't attach it to the PE
+		 * again.
+		 */
+		if (pdn->pe_number != IODA_INVALID_PE)
+			continue;
+
+		pe->device_count++;
 		pdn->pcidev = dev;
 		pdn->pe_number = pe->pe_number;
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
@@ -1042,9 +1092,26 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 	struct pci_controller *hose = pci_bus_to_host(bus);
 	struct pnv_phb *phb = hose->private_data;
 	struct pnv_ioda_pe *pe = NULL;
+	unsigned int pe_num;
+
+	/*
+	 * In partial hotplug case, the PE instance might be still alive.
+	 * We should reuse it instead of allocating a new one.
+	 */
+	pe_num = phb->ioda.pe_rmap[bus->number << 8];
+	if (pe_num != IODA_INVALID_PE) {
+		pe = &phb->ioda.pe_array[pe_num];
+		pnv_ioda_setup_same_PE(bus, pe);
+		return NULL;
+	}
+
+	/* PE number for root bus should have been reserved */
+	if (pci_is_root_bus(bus) &&
+	    phb->ioda.root_pe_idx != IODA_INVALID_PE)
+		pe = &phb->ioda.pe_array[phb->ioda.root_pe_idx];
 
 	/* Check if PE is determined by M64 */
-	if (phb->pick_m64_pe)
+	if (!pe && phb->pick_m64_pe)
 		pe = phb->pick_m64_pe(bus, all);
 
 	/* The PE number isn't pinned by M64 */
@@ -1156,30 +1223,6 @@ static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus)
 		pnv_ioda_setup_npu_PE(pdev);
 }
 
-static void pnv_ioda_setup_PEs(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	pnv_ioda_setup_bus_PE(bus, false);
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		if (dev->subordinate) {
-			if (pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE)
-				pnv_ioda_setup_bus_PE(dev->subordinate, true);
-			else
-				pnv_ioda_setup_PEs(dev->subordinate);
-		}
-	}
-}
-
-/*
- * Configure PEs so that the downstream PCI buses and devices
- * could have their associated PE#. Unfortunately, we didn't
- * figure out the way to identify the PLX bridge yet. So we
- * simply put the PCI bus and the subordinate behind the root
- * port to PE# here. The game rule here is expected to be changed
- * as soon as we can detected PLX bridge correctly.
- */
 static void pnv_pci_ioda_setup_PEs(void)
 {
 	struct pci_controller *hose, *tmp;
@@ -1187,22 +1230,11 @@ static void pnv_pci_ioda_setup_PEs(void)
 
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
 		phb = hose->private_data;
-
-		/* M64 layout might affect PE allocation */
-		if (phb->reserve_m64_pe)
-			phb->reserve_m64_pe(hose->bus, NULL, true);
-
-		/*
-		 * On NPU PHB, we expect separate PEs for individual PCI
-		 * functions. PCI bus dependent PEs are required for the
-		 * remaining types of PHBs.
-		 */
 		if (phb->type == PNV_PHB_NPU) {
 			/* PE#0 is needed for error reporting */
 			pnv_ioda_reserve_pe(phb, 0);
 			pnv_ioda_setup_npu_PEs(hose->bus);
-		} else
-			pnv_ioda_setup_PEs(hose->bus);
+		}
 	}
 }
 
@@ -1728,7 +1760,14 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
 	}
 }
 
-static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
+static inline __be64 __iomem *pnv_ioda_get_inval_reg(struct pnv_phb *phb,
+						     bool real_mode)
+{
+	return real_mode ? (__be64 __iomem *)(phb->regs_phys + 0x210) :
+		(phb->regs + 0x210);
+}
+
+static void pnv_pci_p7ioc_tce_invalidate(struct iommu_table *tbl,
 		unsigned long index, unsigned long npages, bool rm)
 {
 	struct iommu_table_group_link *tgl = list_first_entry_or_null(
@@ -1736,33 +1775,17 @@ static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
 			next);
 	struct pnv_ioda_pe *pe = container_of(tgl->table_group,
 			struct pnv_ioda_pe, table_group);
-	__be64 __iomem *invalidate = rm ?
-		(__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys :
-		pe->phb->ioda.tce_inval_reg;
+	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm);
 	unsigned long start, end, inc;
-	const unsigned shift = tbl->it_page_shift;
 
 	start = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset);
 	end = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset +
 			npages - 1);
 
-	/* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */
-	if (tbl->it_busno) {
-		start <<= shift;
-		end <<= shift;
-		inc = 128ull << shift;
-		start |= tbl->it_busno;
-		end |= tbl->it_busno;
-	} else if (tbl->it_type & TCE_PCI_SWINV_PAIR) {
-		/* p7ioc-style invalidation, 2 TCEs per write */
-		start |= (1ull << 63);
-		end |= (1ull << 63);
-		inc = 16;
-        } else {
-		/* Default (older HW) */
-                inc = 128;
-	}
-
+	/* p7ioc-style invalidation, 2 TCEs per write */
+	start |= (1ull << 63);
+	end |= (1ull << 63);
+	inc = 16;
         end |= inc - 1;	/* round up end to be different than start */
 
         mb(); /* Ensure above stores are visible */
@@ -1788,8 +1811,8 @@ static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
 	int ret = pnv_tce_build(tbl, index, npages, uaddr, direction,
 			attrs);
 
-	if (!ret && (tbl->it_type & TCE_PCI_SWINV_CREATE))
-		pnv_pci_ioda1_tce_invalidate(tbl, index, npages, false);
+	if (!ret)
+		pnv_pci_p7ioc_tce_invalidate(tbl, index, npages, false);
 
 	return ret;
 }
@@ -1800,9 +1823,8 @@ static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
 {
 	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
 
-	if (!ret && (tbl->it_type &
-			(TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE)))
-		pnv_pci_ioda1_tce_invalidate(tbl, index, 1, false);
+	if (!ret)
+		pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, false);
 
 	return ret;
 }
@@ -1813,8 +1835,7 @@ static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
 {
 	pnv_tce_free(tbl, index, npages);
 
-	if (tbl->it_type & TCE_PCI_SWINV_FREE)
-		pnv_pci_ioda1_tce_invalidate(tbl, index, npages, false);
+	pnv_pci_p7ioc_tce_invalidate(tbl, index, npages, false);
 }
 
 static struct iommu_table_ops pnv_ioda1_iommu_ops = {
@@ -1826,45 +1847,42 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 	.get = pnv_tce_get,
 };
 
-#define TCE_KILL_INVAL_ALL  PPC_BIT(0)
-#define TCE_KILL_INVAL_PE   PPC_BIT(1)
-#define TCE_KILL_INVAL_TCE  PPC_BIT(2)
+#define PHB3_TCE_KILL_INVAL_ALL		PPC_BIT(0)
+#define PHB3_TCE_KILL_INVAL_PE		PPC_BIT(1)
+#define PHB3_TCE_KILL_INVAL_ONE		PPC_BIT(2)
 
-void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
+void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
 {
-	const unsigned long val = TCE_KILL_INVAL_ALL;
+	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(phb, rm);
+	const unsigned long val = PHB3_TCE_KILL_INVAL_ALL;
 
 	mb(); /* Ensure previous TCE table stores are visible */
 	if (rm)
-		__raw_rm_writeq(cpu_to_be64(val),
-				(__be64 __iomem *)
-				phb->ioda.tce_inval_reg_phys);
+		__raw_rm_writeq(cpu_to_be64(val), invalidate);
 	else
-		__raw_writeq(cpu_to_be64(val), phb->ioda.tce_inval_reg);
+		__raw_writeq(cpu_to_be64(val), invalidate);
 }
 
-static inline void pnv_pci_ioda2_tce_invalidate_pe(struct pnv_ioda_pe *pe)
+static inline void pnv_pci_phb3_tce_invalidate_pe(struct pnv_ioda_pe *pe)
 {
 	/* 01xb - invalidate TCEs that match the specified PE# */
-	unsigned long val = TCE_KILL_INVAL_PE | (pe->pe_number & 0xFF);
-	struct pnv_phb *phb = pe->phb;
-
-	if (!phb->ioda.tce_inval_reg)
-		return;
+	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false);
+	unsigned long val = PHB3_TCE_KILL_INVAL_PE | (pe->pe_number & 0xFF);
 
 	mb(); /* Ensure above stores are visible */
-	__raw_writeq(cpu_to_be64(val), phb->ioda.tce_inval_reg);
+	__raw_writeq(cpu_to_be64(val), invalidate);
 }
 
-static void pnv_pci_ioda2_do_tce_invalidate(unsigned pe_number, bool rm,
-		__be64 __iomem *invalidate, unsigned shift,
-		unsigned long index, unsigned long npages)
+static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm,
+					unsigned shift, unsigned long index,
+					unsigned long npages)
 {
+	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false);
 	unsigned long start, end, inc;
 
 	/* We'll invalidate DMA address in PE scope */
-	start = TCE_KILL_INVAL_TCE;
-	start |= (pe_number & 0xFF);
+	start = PHB3_TCE_KILL_INVAL_ONE;
+	start |= (pe->pe_number & 0xFF);
 	end = start;
 
 	/* Figure out the start, end and step */
@@ -1882,6 +1900,17 @@ static void pnv_pci_ioda2_do_tce_invalidate(unsigned pe_number, bool rm,
 	}
 }
 
+static inline void pnv_pci_ioda2_tce_invalidate_pe(struct pnv_ioda_pe *pe)
+{
+	struct pnv_phb *phb = pe->phb;
+
+	if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs)
+		pnv_pci_phb3_tce_invalidate_pe(pe);
+	else
+		opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL_PE,
+				  pe->pe_number, 0, 0, 0);
+}
+
 static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 		unsigned long index, unsigned long npages, bool rm)
 {
@@ -1890,22 +1919,31 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 	list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
 		struct pnv_ioda_pe *pe = container_of(tgl->table_group,
 				struct pnv_ioda_pe, table_group);
-		__be64 __iomem *invalidate = rm ?
-			(__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys :
-			pe->phb->ioda.tce_inval_reg;
+		struct pnv_phb *phb = pe->phb;
+		unsigned int shift = tbl->it_page_shift;
 
-		if (pe->phb->type == PNV_PHB_NPU) {
+		if (phb->type == PNV_PHB_NPU) {
 			/*
 			 * The NVLink hardware does not support TCE kill
 			 * per TCE entry so we have to invalidate
 			 * the entire cache for it.
 			 */
-			pnv_pci_ioda2_tce_invalidate_entire(pe->phb, rm);
+			pnv_pci_phb3_tce_invalidate_entire(phb, rm);
 			continue;
 		}
-		pnv_pci_ioda2_do_tce_invalidate(pe->pe_number, rm,
-			invalidate, tbl->it_page_shift,
-			index, npages);
+		if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs)
+			pnv_pci_phb3_tce_invalidate(pe, rm, shift,
+						    index, npages);
+		else if (rm)
+			opal_rm_pci_tce_kill(phb->opal_id,
+					     OPAL_PCI_TCE_KILL_PAGES,
+					     pe->pe_number, 1u << shift,
+					     index << shift, npages);
+		else
+			opal_pci_tce_kill(phb->opal_id,
+					  OPAL_PCI_TCE_KILL_PAGES,
+					  pe->pe_number, 1u << shift,
+					  index << shift, npages);
 	}
 }
 
@@ -1917,7 +1955,7 @@ static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
 	int ret = pnv_tce_build(tbl, index, npages, uaddr, direction,
 			attrs);
 
-	if (!ret && (tbl->it_type & TCE_PCI_SWINV_CREATE))
+	if (!ret)
 		pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
 
 	return ret;
@@ -1929,8 +1967,7 @@ static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
 {
 	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
 
-	if (!ret && (tbl->it_type &
-			(TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE)))
+	if (!ret)
 		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false);
 
 	return ret;
@@ -1942,8 +1979,7 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 {
 	pnv_tce_free(tbl, index, npages);
 
-	if (tbl->it_type & TCE_PCI_SWINV_FREE)
-		pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
+	pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
 }
 
 static void pnv_ioda2_table_free(struct iommu_table *tbl)
@@ -2112,12 +2148,6 @@ found:
 				  base * PNV_IODA1_DMA32_SEGSIZE,
 				  IOMMU_PAGE_SHIFT_4K);
 
-	/* OPAL variant of P7IOC SW invalidated TCEs */
-	if (phb->ioda.tce_inval_reg)
-		tbl->it_type |= (TCE_PCI_SWINV_CREATE |
-				 TCE_PCI_SWINV_FREE   |
-				 TCE_PCI_SWINV_PAIR);
-
 	tbl->it_ops = &pnv_ioda1_iommu_ops;
 	pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift;
 	pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift;
@@ -2179,7 +2209,7 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
 
 	pnv_pci_link_table_and_group(phb->hose->node, num,
 			tbl, &pe->table_group);
-	pnv_pci_ioda2_tce_invalidate_pe(pe);
+	pnv_pci_phb3_tce_invalidate_pe(pe);
 
 	return 0;
 }
@@ -2240,8 +2270,6 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 	}
 
 	tbl->it_ops = &pnv_ioda2_iommu_ops;
-	if (pe->phb->ioda.tce_inval_reg)
-		tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
 
 	*ptbl = tbl;
 
@@ -2290,10 +2318,6 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	if (!pnv_iommu_bypass_disabled)
 		pnv_pci_ioda2_set_bypass(pe, true);
 
-	/* OPAL variant of PHB3 invalidated TCEs */
-	if (pe->phb->ioda.tce_inval_reg)
-		tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
-
 	/*
 	 * Setting table base here only for carrying iommu_group
 	 * further down to let iommu_add_device() do the job.
@@ -2323,7 +2347,7 @@ static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
 	if (ret)
 		pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
 	else
-		pnv_pci_ioda2_tce_invalidate_pe(pe);
+		pnv_pci_phb3_tce_invalidate_pe(pe);
 
 	pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
 
@@ -2504,19 +2528,6 @@ static void pnv_pci_ioda_setup_iommu_api(void)
 static void pnv_pci_ioda_setup_iommu_api(void) { };
 #endif
 
-static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb)
-{
-	const __be64 *swinvp;
-
-	/* OPAL variant of PHB3 invalidated TCEs */
-	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
-	if (!swinvp)
-		return;
-
-	phb->ioda.tce_inval_reg_phys = be64_to_cpup(swinvp);
-	phb->ioda.tce_inval_reg = ioremap(phb->ioda.tce_inval_reg_phys, 8);
-}
-
 static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
 		unsigned levels, unsigned long limit,
 		unsigned long *current_offset, unsigned long *total_allocated)
@@ -2657,6 +2668,9 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 {
 	int64_t rc;
 
+	if (!pnv_pci_ioda_pe_dma_weight(pe))
+		return;
+
 	/* TVE #1 is selected by PCI address bit 59 */
 	pe->tce_bypass_base = 1ull << 59;
 
@@ -2688,49 +2702,6 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 }
 
-static void pnv_ioda_setup_dma(struct pnv_phb *phb)
-{
-	struct pci_controller *hose = phb->hose;
-	struct pnv_ioda_pe *pe;
-	unsigned int weight;
-
-	/* If we have more PE# than segments available, hand out one
-	 * per PE until we run out and let the rest fail. If not,
-	 * then we assign at least one segment per PE, plus more based
-	 * on the amount of devices under that PE
-	 */
-	pr_info("PCI: Domain %04x has %d available 32-bit DMA segments\n",
-		hose->global_number, phb->ioda.dma32_count);
-
-	pnv_pci_ioda_setup_opal_tce_kill(phb);
-
-	/* Walk our PE list and configure their DMA segments */
-	list_for_each_entry(pe, &phb->ioda.pe_list, list) {
-		weight = pnv_pci_ioda_pe_dma_weight(pe);
-		if (!weight)
-			continue;
-
-		/*
-		 * For IODA2 compliant PHB3, we needn't care about the weight.
-		 * The all available 32-bits DMA space will be assigned to
-		 * the specific PE.
-		 */
-		if (phb->type == PNV_PHB_IODA1) {
-			pnv_pci_ioda1_setup_dma_pe(phb, pe);
-		} else if (phb->type == PNV_PHB_IODA2) {
-			pe_info(pe, "Assign DMA32 space\n");
-			pnv_pci_ioda2_setup_dma_pe(phb, pe);
-		} else if (phb->type == PNV_PHB_NPU) {
-			/*
-			 * We initialise the DMA space for an NPU PHB
-			 * after setup of the PHB is complete as we
-			 * point the NPU TVT to the the same location
-			 * as the PHB3 TVT.
-			 */
-		}
-	}
-}
-
 #ifdef CONFIG_PCI_MSI
 static void pnv_ioda2_msi_eoi(struct irq_data *d)
 {
@@ -2747,12 +2718,13 @@ static void pnv_ioda2_msi_eoi(struct irq_data *d)
 }
 
 
-static void set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
+void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
 {
 	struct irq_data *idata;
 	struct irq_chip *ichip;
 
-	if (phb->type != PNV_PHB_IODA2)
+	/* The MSI EOI OPAL call is only needed on PHB3 */
+	if (phb->model != PNV_PHB_MODEL_PHB3)
 		return;
 
 	if (!phb->ioda.irq_chip_init) {
@@ -2769,157 +2741,6 @@ static void set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
 	irq_set_chip(virq, &phb->ioda.irq_chip);
 }
 
-#ifdef CONFIG_CXL_BASE
-
-struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-
-	return of_node_get(hose->dn);
-}
-EXPORT_SYMBOL(pnv_pci_get_phb_node);
-
-int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	struct pnv_ioda_pe *pe;
-	int rc;
-
-	pe = pnv_ioda_get_pe(dev);
-	if (!pe)
-		return -ENODEV;
-
-	pe_info(pe, "Switching PHB to CXL\n");
-
-	rc = opal_pci_set_phb_cxl_mode(phb->opal_id, mode, pe->pe_number);
-	if (rc)
-		dev_err(&dev->dev, "opal_pci_set_phb_cxl_mode failed: %i\n", rc);
-
-	return rc;
-}
-EXPORT_SYMBOL(pnv_phb_to_cxl_mode);
-
-/* Find PHB for cxl dev and allocate MSI hwirqs?
- * Returns the absolute hardware IRQ number
- */
-int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	int hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, num);
-
-	if (hwirq < 0) {
-		dev_warn(&dev->dev, "Failed to find a free MSI\n");
-		return -ENOSPC;
-	}
-
-	return phb->msi_base + hwirq;
-}
-EXPORT_SYMBOL(pnv_cxl_alloc_hwirqs);
-
-void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-
-	msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, num);
-}
-EXPORT_SYMBOL(pnv_cxl_release_hwirqs);
-
-void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
-				  struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	int i, hwirq;
-
-	for (i = 1; i < CXL_IRQ_RANGES; i++) {
-		if (!irqs->range[i])
-			continue;
-		pr_devel("cxl release irq range 0x%x: offset: 0x%lx  limit: %ld\n",
-			 i, irqs->offset[i],
-			 irqs->range[i]);
-		hwirq = irqs->offset[i] - phb->msi_base;
-		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq,
-				       irqs->range[i]);
-	}
-}
-EXPORT_SYMBOL(pnv_cxl_release_hwirq_ranges);
-
-int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
-			       struct pci_dev *dev, int num)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	int i, hwirq, try;
-
-	memset(irqs, 0, sizeof(struct cxl_irq_ranges));
-
-	/* 0 is reserved for the multiplexed PSL DSI interrupt */
-	for (i = 1; i < CXL_IRQ_RANGES && num; i++) {
-		try = num;
-		while (try) {
-			hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, try);
-			if (hwirq >= 0)
-				break;
-			try /= 2;
-		}
-		if (!try)
-			goto fail;
-
-		irqs->offset[i] = phb->msi_base + hwirq;
-		irqs->range[i] = try;
-		pr_devel("cxl alloc irq range 0x%x: offset: 0x%lx  limit: %li\n",
-			 i, irqs->offset[i], irqs->range[i]);
-		num -= try;
-	}
-	if (num)
-		goto fail;
-
-	return 0;
-fail:
-	pnv_cxl_release_hwirq_ranges(irqs, dev);
-	return -ENOSPC;
-}
-EXPORT_SYMBOL(pnv_cxl_alloc_hwirq_ranges);
-
-int pnv_cxl_get_irq_count(struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-
-	return phb->msi_bmp.irq_count;
-}
-EXPORT_SYMBOL(pnv_cxl_get_irq_count);
-
-int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
-			   unsigned int virq)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	unsigned int xive_num = hwirq - phb->msi_base;
-	struct pnv_ioda_pe *pe;
-	int rc;
-
-	if (!(pe = pnv_ioda_get_pe(dev)))
-		return -ENODEV;
-
-	/* Assign XIVE to PE */
-	rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
-	if (rc) {
-		pe_warn(pe, "%s: OPAL error %d setting msi_base 0x%x "
-			"hwirq 0x%x XIVE 0x%x PE\n",
-			pci_name(dev), rc, phb->msi_base, hwirq, xive_num);
-		return -EIO;
-	}
-	set_msi_irq_chip(phb, virq);
-
-	return 0;
-}
-EXPORT_SYMBOL(pnv_cxl_ioda_msi_setup);
-#endif
-
 static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 				  unsigned int hwirq, unsigned int virq,
 				  unsigned int is_64, struct msi_msg *msg)
@@ -2976,7 +2797,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 	}
 	msg->data = be32_to_cpu(data);
 
-	set_msi_irq_chip(phb, virq);
+	pnv_set_msi_irq_chip(phb, virq);
 
 	pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d),"
 		 " address=%x_%08x data=%x PE# %d\n",
@@ -3197,41 +3018,6 @@ static void pnv_ioda_setup_pe_seg(struct pnv_ioda_pe *pe)
 	}
 }
 
-static void pnv_pci_ioda_setup_seg(void)
-{
-	struct pci_controller *tmp, *hose;
-	struct pnv_phb *phb;
-	struct pnv_ioda_pe *pe;
-
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
-		phb = hose->private_data;
-
-		/* NPU PHB does not support IO or MMIO segmentation */
-		if (phb->type == PNV_PHB_NPU)
-			continue;
-
-		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
-			pnv_ioda_setup_pe_seg(pe);
-		}
-	}
-}
-
-static void pnv_pci_ioda_setup_DMA(void)
-{
-	struct pci_controller *hose, *tmp;
-	struct pnv_phb *phb;
-
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
-		pnv_ioda_setup_dma(hose->private_data);
-
-		/* Mark the PHB initialization done */
-		phb = hose->private_data;
-		phb->initialized = 1;
-	}
-
-	pnv_pci_ioda_setup_iommu_api();
-}
-
 static void pnv_pci_ioda_create_dbgfs(void)
 {
 #ifdef CONFIG_DEBUG_FS
@@ -3242,6 +3028,9 @@ static void pnv_pci_ioda_create_dbgfs(void)
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
 		phb = hose->private_data;
 
+		/* Notify initialization of PHB done */
+		phb->initialized = 1;
+
 		sprintf(name, "PCI%04x", hose->global_number);
 		phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root);
 		if (!phb->dbgfs)
@@ -3254,9 +3043,7 @@ static void pnv_pci_ioda_create_dbgfs(void)
 static void pnv_pci_ioda_fixup(void)
 {
 	pnv_pci_ioda_setup_PEs();
-	pnv_pci_ioda_setup_seg();
-	pnv_pci_ioda_setup_DMA();
-
+	pnv_pci_ioda_setup_iommu_api();
 	pnv_pci_ioda_create_dbgfs();
 
 #ifdef CONFIG_EEH
@@ -3306,6 +3093,115 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
 	return phb->ioda.io_segsize;
 }
 
+/*
+ * We are updating root port or the upstream port of the
+ * bridge behind the root port with PHB's windows in order
+ * to accommodate the changes on required resources during
+ * PCI (slot) hotplug, which is connected to either root
+ * port or the downstream ports of PCIe switch behind the
+ * root port.
+ */
+static void pnv_pci_fixup_bridge_resources(struct pci_bus *bus,
+					   unsigned long type)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pci_dev *bridge = bus->self;
+	struct resource *r, *w;
+	bool msi_region = false;
+	int i;
+
+	/* Check if we need apply fixup to the bridge's windows */
+	if (!pci_is_root_bus(bridge->bus) &&
+	    !pci_is_root_bus(bridge->bus->self->bus))
+		return;
+
+	/* Fixup the resources */
+	for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) {
+		r = &bridge->resource[PCI_BRIDGE_RESOURCES + i];
+		if (!r->flags || !r->parent)
+			continue;
+
+		w = NULL;
+		if (r->flags & type & IORESOURCE_IO)
+			w = &hose->io_resource;
+		else if (pnv_pci_is_mem_pref_64(r->flags) &&
+			 (type & IORESOURCE_PREFETCH) &&
+			 phb->ioda.m64_segsize)
+			w = &hose->mem_resources[1];
+		else if (r->flags & type & IORESOURCE_MEM) {
+			w = &hose->mem_resources[0];
+			msi_region = true;
+		}
+
+		r->start = w->start;
+		r->end = w->end;
+
+		/* The 64KB 32-bits MSI region shouldn't be included in
+		 * the 32-bits bridge window. Otherwise, we can see strange
+		 * issues. One of them is EEH error observed on Garrison.
+		 *
+		 * Exclude top 1MB region which is the minimal alignment of
+		 * 32-bits bridge window.
+		 */
+		if (msi_region) {
+			r->end += 0x10000;
+			r->end -= 0x100000;
+		}
+	}
+}
+
+static void pnv_pci_setup_bridge(struct pci_bus *bus, unsigned long type)
+{
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pci_dev *bridge = bus->self;
+	struct pnv_ioda_pe *pe;
+	bool all = (pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE);
+
+	/* Extend bridge's windows if necessary */
+	pnv_pci_fixup_bridge_resources(bus, type);
+
+	/* The PE for root bus should be realized before any one else */
+	if (!phb->ioda.root_pe_populated) {
+		pe = pnv_ioda_setup_bus_PE(phb->hose->bus, false);
+		if (pe) {
+			phb->ioda.root_pe_idx = pe->pe_number;
+			phb->ioda.root_pe_populated = true;
+		}
+	}
+
+	/* Don't assign PE to PCI bus, which doesn't have subordinate devices */
+	if (list_empty(&bus->devices))
+		return;
+
+	/* Reserve PEs according to used M64 resources */
+	if (phb->reserve_m64_pe)
+		phb->reserve_m64_pe(bus, NULL, all);
+
+	/*
+	 * Assign PE. We might run here because of partial hotplug.
+	 * For the case, we just pick up the existing PE and should
+	 * not allocate resources again.
+	 */
+	pe = pnv_ioda_setup_bus_PE(bus, all);
+	if (!pe)
+		return;
+
+	pnv_ioda_setup_pe_seg(pe);
+	switch (phb->type) {
+	case PNV_PHB_IODA1:
+		pnv_pci_ioda1_setup_dma_pe(phb, pe);
+		break;
+	case PNV_PHB_IODA2:
+		pnv_pci_ioda2_setup_dma_pe(phb, pe);
+		break;
+	default:
+		pr_warn("%s: No DMA for PHB#%d (type %d)\n",
+			__func__, phb->hose->global_number, phb->type);
+	}
+}
+
 #ifdef CONFIG_PCI_IOV
 static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
 						      int resno)
@@ -3345,7 +3241,7 @@ static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
 /* Prevent enabling devices for which we couldn't properly
  * assign a PE
  */
-static bool pnv_pci_enable_device_hook(struct pci_dev *dev)
+bool pnv_pci_enable_device_hook(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct pnv_phb *phb = hose->private_data;
@@ -3366,6 +3262,178 @@ static bool pnv_pci_enable_device_hook(struct pci_dev *dev)
 	return true;
 }
 
+static long pnv_pci_ioda1_unset_window(struct iommu_table_group *table_group,
+				       int num)
+{
+	struct pnv_ioda_pe *pe = container_of(table_group,
+					      struct pnv_ioda_pe, table_group);
+	struct pnv_phb *phb = pe->phb;
+	unsigned int idx;
+	long rc;
+
+	pe_info(pe, "Removing DMA window #%d\n", num);
+	for (idx = 0; idx < phb->ioda.dma32_count; idx++) {
+		if (phb->ioda.dma32_segmap[idx] != pe->pe_number)
+			continue;
+
+		rc = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
+						idx, 0, 0ul, 0ul, 0ul);
+		if (rc != OPAL_SUCCESS) {
+			pe_warn(pe, "Failure %ld unmapping DMA32 segment#%d\n",
+				rc, idx);
+			return rc;
+		}
+
+		phb->ioda.dma32_segmap[idx] = IODA_INVALID_PE;
+	}
+
+	pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
+	return OPAL_SUCCESS;
+}
+
+static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
+{
+	unsigned int weight = pnv_pci_ioda_pe_dma_weight(pe);
+	struct iommu_table *tbl = pe->table_group.tables[0];
+	int64_t rc;
+
+	if (!weight)
+		return;
+
+	rc = pnv_pci_ioda1_unset_window(&pe->table_group, 0);
+	if (rc != OPAL_SUCCESS)
+		return;
+
+	pnv_pci_p7ioc_tce_invalidate(tbl, tbl->it_offset, tbl->it_size, false);
+	if (pe->table_group.group) {
+		iommu_group_put(pe->table_group.group);
+		WARN_ON(pe->table_group.group);
+	}
+
+	free_pages(tbl->it_base, get_order(tbl->it_size << 3));
+	iommu_free_table(tbl, "pnv");
+}
+
+static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
+{
+	struct iommu_table *tbl = pe->table_group.tables[0];
+	unsigned int weight = pnv_pci_ioda_pe_dma_weight(pe);
+#ifdef CONFIG_IOMMU_API
+	int64_t rc;
+#endif
+
+	if (!weight)
+		return;
+
+#ifdef CONFIG_IOMMU_API
+	rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0);
+	if (rc)
+		pe_warn(pe, "OPAL error %ld release DMA window\n", rc);
+#endif
+
+	pnv_pci_ioda2_set_bypass(pe, false);
+	if (pe->table_group.group) {
+		iommu_group_put(pe->table_group.group);
+		WARN_ON(pe->table_group.group);
+	}
+
+	pnv_pci_ioda2_table_free_pages(tbl);
+	iommu_free_table(tbl, "pnv");
+}
+
+static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe,
+				 unsigned short win,
+				 unsigned int *map)
+{
+	struct pnv_phb *phb = pe->phb;
+	int idx;
+	int64_t rc;
+
+	for (idx = 0; idx < phb->ioda.total_pe_num; idx++) {
+		if (map[idx] != pe->pe_number)
+			continue;
+
+		if (win == OPAL_M64_WINDOW_TYPE)
+			rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+					phb->ioda.reserved_pe_idx, win,
+					idx / PNV_IODA1_M64_SEGS,
+					idx % PNV_IODA1_M64_SEGS);
+		else
+			rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+					phb->ioda.reserved_pe_idx, win, 0, idx);
+
+		if (rc != OPAL_SUCCESS)
+			pe_warn(pe, "Error %ld unmapping (%d) segment#%d\n",
+				rc, win, idx);
+
+		map[idx] = IODA_INVALID_PE;
+	}
+}
+
+static void pnv_ioda_release_pe_seg(struct pnv_ioda_pe *pe)
+{
+	struct pnv_phb *phb = pe->phb;
+
+	if (phb->type == PNV_PHB_IODA1) {
+		pnv_ioda_free_pe_seg(pe, OPAL_IO_WINDOW_TYPE,
+				     phb->ioda.io_segmap);
+		pnv_ioda_free_pe_seg(pe, OPAL_M32_WINDOW_TYPE,
+				     phb->ioda.m32_segmap);
+		pnv_ioda_free_pe_seg(pe, OPAL_M64_WINDOW_TYPE,
+				     phb->ioda.m64_segmap);
+	} else if (phb->type == PNV_PHB_IODA2) {
+		pnv_ioda_free_pe_seg(pe, OPAL_M32_WINDOW_TYPE,
+				     phb->ioda.m32_segmap);
+	}
+}
+
+static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
+{
+	struct pnv_phb *phb = pe->phb;
+	struct pnv_ioda_pe *slave, *tmp;
+
+	/* Release slave PEs in compound PE */
+	if (pe->flags & PNV_IODA_PE_MASTER) {
+		list_for_each_entry_safe(slave, tmp, &pe->slaves, list)
+			pnv_ioda_release_pe(slave);
+	}
+
+	list_del(&pe->list);
+	switch (phb->type) {
+	case PNV_PHB_IODA1:
+		pnv_pci_ioda1_release_pe_dma(pe);
+		break;
+	case PNV_PHB_IODA2:
+		pnv_pci_ioda2_release_pe_dma(pe);
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	pnv_ioda_release_pe_seg(pe);
+	pnv_ioda_deconfigure_pe(pe->phb, pe);
+	pnv_ioda_free_pe(pe);
+}
+
+static void pnv_pci_release_device(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	struct pnv_ioda_pe *pe;
+
+	if (pdev->is_virtfn)
+		return;
+
+	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
+		return;
+
+	pe = &phb->ioda.pe_array[pdn->pe_number];
+	WARN_ON(--pe->device_count < 0);
+	if (pe->device_count == 0)
+		pnv_ioda_release_pe(pe);
+}
+
 static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 {
 	struct pnv_phb *phb = hose->private_data;
@@ -3382,7 +3450,9 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
 #endif
 	.enable_device_hook	= pnv_pci_enable_device_hook,
+	.release_device		= pnv_pci_release_device,
 	.window_alignment	= pnv_pci_window_alignment,
+	.setup_bridge		= pnv_pci_setup_bridge,
 	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
 	.dma_set_mask		= pnv_pci_ioda_dma_set_mask,
 	.dma_get_required_mask	= pnv_pci_ioda_dma_get_required_mask,
@@ -3410,6 +3480,26 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 	.shutdown		= pnv_pci_ioda_shutdown,
 };
 
+#ifdef CONFIG_CXL_BASE
+const struct pci_controller_ops pnv_cxl_cx4_ioda_controller_ops = {
+	.dma_dev_setup		= pnv_pci_dma_dev_setup,
+	.dma_bus_setup		= pnv_pci_dma_bus_setup,
+#ifdef CONFIG_PCI_MSI
+	.setup_msi_irqs		= pnv_cxl_cx4_setup_msi_irqs,
+	.teardown_msi_irqs	= pnv_cxl_cx4_teardown_msi_irqs,
+#endif
+	.enable_device_hook	= pnv_cxl_enable_device_hook,
+	.disable_device		= pnv_cxl_disable_device,
+	.release_device		= pnv_pci_release_device,
+	.window_alignment	= pnv_pci_window_alignment,
+	.setup_bridge		= pnv_pci_setup_bridge,
+	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
+	.dma_set_mask		= pnv_pci_ioda_dma_set_mask,
+	.dma_get_required_mask	= pnv_pci_ioda_dma_get_required_mask,
+	.shutdown		= pnv_pci_ioda_shutdown,
+};
+#endif
+
 static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 					 u64 hub_id, int ioda_type)
 {
@@ -3417,6 +3507,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	struct pnv_phb *phb;
 	unsigned long size, m64map_off, m32map_off, pemap_off;
 	unsigned long iomap_off = 0, dma32map_off = 0;
+	struct resource r;
 	const __be64 *prop64;
 	const __be32 *prop32;
 	int len;
@@ -3425,7 +3516,11 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	void *aux;
 	long rc;
 
-	pr_info("Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name);
+	if (!of_device_is_available(np))
+		return;
+
+	pr_info("Initializing %s PHB (%s)\n",
+		pnv_phb_names[ioda_type], of_node_full_name(np));
 
 	prop64 = of_get_property(np, "ibm,opal-phbid", NULL);
 	if (!prop64) {
@@ -3476,9 +3571,12 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	pci_process_bridge_OF_ranges(hose, np, !hose->global_number);
 
 	/* Get registers */
-	phb->regs = of_iomap(np, 0);
-	if (phb->regs == NULL)
-		pr_err("  Failed to map registers !\n");
+	if (!of_address_to_resource(np, 0, &r)) {
+		phb->regs_phys = r.start;
+		phb->regs = ioremap(r.start, resource_size(&r));
+		if (phb->regs == NULL)
+			pr_err("  Failed to map registers !\n");
+	}
 
 	/* Initialize more IODA stuff */
 	phb->ioda.total_pe_num = 1;
@@ -3489,6 +3587,10 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	if (prop32)
 		phb->ioda.reserved_pe_idx = be32_to_cpup(prop32);
 
+	/* Invalidate RID to PE# mapping */
+	for (segno = 0; segno < ARRAY_SIZE(phb->ioda.pe_rmap); segno++)
+		phb->ioda.pe_rmap[segno] = IODA_INVALID_PE;
+
 	/* Parse 64-bit MMIO range */
 	pnv_ioda_parse_m64_window(phb);
 
@@ -3540,7 +3642,22 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 			phb->ioda.dma32_segmap[segno] = IODA_INVALID_PE;
 	}
 	phb->ioda.pe_array = aux + pemap_off;
-	set_bit(phb->ioda.reserved_pe_idx, phb->ioda.pe_alloc);
+
+	/*
+	 * Choose PE number for root bus, which shouldn't have
+	 * M64 resources consumed by its child devices. To pick
+	 * the PE number adjacent to the reserved one if possible.
+	 */
+	pnv_ioda_reserve_pe(phb, phb->ioda.reserved_pe_idx);
+	if (phb->ioda.reserved_pe_idx == 0) {
+		phb->ioda.root_pe_idx = 1;
+		pnv_ioda_reserve_pe(phb, phb->ioda.root_pe_idx);
+	} else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1)) {
+		phb->ioda.root_pe_idx = phb->ioda.reserved_pe_idx - 1;
+		pnv_ioda_reserve_pe(phb, phb->ioda.root_pe_idx);
+	} else {
+		phb->ioda.root_pe_idx = IODA_INVALID_PE;
+	}
 
 	INIT_LIST_HEAD(&phb->ioda.pe_list);
 	mutex_init(&phb->ioda.pe_list_mutex);
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 1d92bd93bcd9..6701dd5ded20 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -26,6 +26,7 @@
 #include <asm/machdep.h>
 #include <asm/msi_bitmap.h>
 #include <asm/ppc-pci.h>
+#include <asm/pnv-pci.h>
 #include <asm/opal.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
@@ -36,8 +37,124 @@
 #include "powernv.h"
 #include "pci.h"
 
-/* Delay in usec */
-#define PCI_RESET_DELAY_US	3000000
+int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
+{
+	struct device_node *parent = np;
+	u32 bdfn;
+	u64 phbid;
+	int ret;
+
+	ret = of_property_read_u32(np, "reg", &bdfn);
+	if (ret)
+		return -ENXIO;
+
+	bdfn = ((bdfn & 0x00ffff00) >> 8);
+	while ((parent = of_get_parent(parent))) {
+		if (!PCI_DN(parent)) {
+			of_node_put(parent);
+			break;
+		}
+
+		if (!of_device_is_compatible(parent, "ibm,ioda2-phb")) {
+			of_node_put(parent);
+			continue;
+		}
+
+		ret = of_property_read_u64(parent, "ibm,opal-phbid", &phbid);
+		if (ret) {
+			of_node_put(parent);
+			return -ENXIO;
+		}
+
+		*id = PCI_SLOT_ID(phbid, bdfn);
+		return 0;
+	}
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(pnv_pci_get_slot_id);
+
+int pnv_pci_get_device_tree(uint32_t phandle, void *buf, uint64_t len)
+{
+	int64_t rc;
+
+	if (!opal_check_token(OPAL_GET_DEVICE_TREE))
+		return -ENXIO;
+
+	rc = opal_get_device_tree(phandle, (uint64_t)buf, len);
+	if (rc < OPAL_SUCCESS)
+		return -EIO;
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pnv_pci_get_device_tree);
+
+int pnv_pci_get_presence_state(uint64_t id, uint8_t *state)
+{
+	int64_t rc;
+
+	if (!opal_check_token(OPAL_PCI_GET_PRESENCE_STATE))
+		return -ENXIO;
+
+	rc = opal_pci_get_presence_state(id, (uint64_t)state);
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_pci_get_presence_state);
+
+int pnv_pci_get_power_state(uint64_t id, uint8_t *state)
+{
+	int64_t rc;
+
+	if (!opal_check_token(OPAL_PCI_GET_POWER_STATE))
+		return -ENXIO;
+
+	rc = opal_pci_get_power_state(id, (uint64_t)state);
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnv_pci_get_power_state);
+
+int pnv_pci_set_power_state(uint64_t id, uint8_t state, struct opal_msg *msg)
+{
+	struct opal_msg m;
+	int token, ret;
+	int64_t rc;
+
+	if (!opal_check_token(OPAL_PCI_SET_POWER_STATE))
+		return -ENXIO;
+
+	token = opal_async_get_token_interruptible();
+	if (unlikely(token < 0))
+		return token;
+
+	rc = opal_pci_set_power_state(token, id, (uint64_t)&state);
+	if (rc == OPAL_SUCCESS) {
+		ret = 0;
+		goto exit;
+	} else if (rc != OPAL_ASYNC_COMPLETION) {
+		ret = -EIO;
+		goto exit;
+	}
+
+	ret = opal_async_wait_response(token, &m);
+	if (ret < 0)
+		goto exit;
+
+	if (msg) {
+		ret = 1;
+		memcpy(msg, &m, sizeof(m));
+	}
+
+exit:
+	opal_async_release_token(token);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pnv_pci_set_power_state);
 
 #ifdef CONFIG_PCI_MSI
 int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
@@ -620,8 +737,8 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index,
 	if (newtce & TCE_PCI_WRITE)
 		newtce |= TCE_PCI_READ;
 
-	oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce));
-	*hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+	oldtce = be64_to_cpu(xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce)));
+	*hpa = oldtce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
 	*direction = iommu_tce_direction(oldtce);
 
 	return 0;
@@ -815,13 +932,14 @@ void __init pnv_pci_init(void)
 	for_each_compatible_node(np, NULL, "ibm,ioda2-phb")
 		pnv_pci_init_ioda2_phb(np);
 
+	/* Look for ioda3 built-in PHB4's, we treat them as IODA2 */
+	for_each_compatible_node(np, NULL, "ibm,ioda3-phb")
+		pnv_pci_init_ioda2_phb(np);
+
 	/* Look for NPU PHBs */
 	for_each_compatible_node(np, NULL, "ibm,ioda2-npu-phb")
 		pnv_pci_init_npu_phb(np);
 
-	/* Setup the linkage between OF nodes and PHBs */
-	pci_devs_phb_init();
-
 	/* Configure IOMMU DMA hooks */
 	set_pci_dma_ops(&dma_iommu_ops);
 }
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 7dee25e304db..d088d4f06116 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -1,6 +1,10 @@
 #ifndef __POWERNV_PCI_H
 #define __POWERNV_PCI_H
 
+#include <linux/iommu.h>
+#include <asm/iommu.h>
+#include <asm/msi_bitmap.h>
+
 struct pci_dn;
 
 enum pnv_phb_type {
@@ -30,6 +34,7 @@ struct pnv_phb;
 struct pnv_ioda_pe {
 	unsigned long		flags;
 	struct pnv_phb		*phb;
+	int			device_count;
 
 	/* A PE can be associated with a single device or an
 	 * entire bus (& children). In the former case, pdev
@@ -71,6 +76,7 @@ struct pnv_ioda_pe {
 };
 
 #define PNV_PHB_FLAG_EEH	(1 << 0)
+#define PNV_PHB_FLAG_CXL	(1 << 1) /* Real PHB supporting the cxl kernel API */
 
 struct pnv_phb {
 	struct pci_controller	*hose;
@@ -80,6 +86,7 @@ struct pnv_phb {
 	u64			opal_id;
 	int			flags;
 	void __iomem		*regs;
+	u64			regs_phys;
 	int			initialized;
 	spinlock_t		lock;
 
@@ -110,6 +117,8 @@ struct pnv_phb {
 		/* Global bridge info */
 		unsigned int		total_pe_num;
 		unsigned int		reserved_pe_idx;
+		unsigned int		root_pe_idx;
+		bool			root_pe_populated;
 
 		/* 32-bit MMIO window */
 		unsigned int		m32_size;
@@ -152,17 +161,8 @@ struct pnv_phb {
 		struct list_head	pe_list;
 		struct mutex            pe_list_mutex;
 
-		/* Reverse map of PEs, will have to extend if
-		 * we are to support more than 256 PEs, indexed
-		 * bus { bus, devfn }
-		 */
-		unsigned char		pe_rmap[0x10000];
-
-		/* TCE cache invalidate registers (physical and
-		 * remapped)
-		 */
-		phys_addr_t		tce_inval_reg_phys;
-		__be64 __iomem		*tce_inval_reg;
+		/* Reverse map of PEs, indexed by {bus, devfn} */
+		unsigned int		pe_rmap[0x10000];
 	} ioda;
 
 	/* PHB and hub status structure */
@@ -173,6 +173,9 @@ struct pnv_phb {
 		struct OpalIoP7IOCErrorData 	hub_diag;
 	} diag;
 
+#ifdef CONFIG_CXL_BASE
+	struct cxl_afu *cxl_afu;
+#endif
 };
 
 extern struct pci_ops pnv_pci_ops;
@@ -203,8 +206,6 @@ extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_init_npu_phb(struct device_node *np);
-extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
-					__be64 *startp, __be64 *endp, bool rm);
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
@@ -212,6 +213,9 @@ extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev);
 extern void pnv_pci_dma_bus_setup(struct pci_bus *bus);
 extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
 extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
+extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev);
+extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq);
+extern bool pnv_pci_enable_device_hook(struct pci_dev *dev);
 
 extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 			    const char *fmt, ...);
@@ -224,7 +228,7 @@ extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 
 /* Nvlink functions */
 extern void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass);
-extern void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm);
+extern void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm);
 extern struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe);
 extern long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num,
 		struct iommu_table *tbl);
@@ -232,4 +236,15 @@ extern long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num);
 extern void pnv_npu_take_ownership(struct pnv_ioda_pe *npe);
 extern void pnv_npu_release_ownership(struct pnv_ioda_pe *npe);
 
+
+/* cxl functions */
+extern bool pnv_cxl_enable_device_hook(struct pci_dev *dev);
+extern void pnv_cxl_disable_device(struct pci_dev *dev);
+extern int pnv_cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
+extern void pnv_cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev);
+
+
+/* phb ops (cxl switches these when enabling the kernel api on the phb) */
+extern const struct pci_controller_ops pnv_cxl_cx4_ioda_controller_ops;
+
 #endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 6dbc0a1da1f6..da7c843ac7f1 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -18,6 +18,7 @@ static inline void pnv_pci_shutdown(void) { }
 #endif
 
 extern u32 pnv_get_supported_cpuidle_states(void);
+extern u64 pnv_deepest_stop_state;
 
 extern void pnv_lpc_init(void);
 
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index ee6430bedcc3..efe8b6bb168b 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -58,7 +58,7 @@ static void __init pnv_setup_arch(void)
 	/* XXX PMCS */
 }
 
-static void __init pnv_init_early(void)
+static void __init pnv_init(void)
 {
 	/*
 	 * Initialize the LPC bus now so that legacy serial
@@ -268,21 +268,16 @@ static void __init pnv_setup_machdep_opal(void)
 
 static int __init pnv_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "ibm,powernv"))
+	if (!of_machine_is_compatible("ibm,powernv"))
 		return 0;
 
-	if (IS_ENABLED(CONFIG_PPC_RADIX_MMU) && radix_enabled())
-		radix_init_native();
-	else if (IS_ENABLED(CONFIG_PPC_STD_MMU_64))
-		hpte_init_native();
-
 	if (firmware_has_feature(FW_FEATURE_OPAL))
 		pnv_setup_machdep_opal();
 
 	pr_debug("PowerNV detected !\n");
 
+	pnv_init();
+
 	return 1;
 }
 
@@ -308,14 +303,13 @@ static unsigned long pnv_get_proc_freq(unsigned int cpu)
 define_machine(powernv) {
 	.name			= "PowerNV",
 	.probe			= pnv_probe,
-	.init_early		= pnv_init_early,
 	.setup_arch		= pnv_setup_arch,
 	.init_IRQ		= pnv_init_IRQ,
 	.show_cpuinfo		= pnv_show_cpuinfo,
 	.get_proc_freq          = pnv_get_proc_freq,
 	.progress		= pnv_progress,
 	.machine_shutdown	= pnv_shutdown,
-	.power_save             = power7_idle,
+	.power_save             = NULL,
 	.calibrate_decr		= generic_calibrate_decr,
 #ifdef CONFIG_KEXEC
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index ad7b1a3dbed0..c789258ae1e1 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -182,7 +182,9 @@ static void pnv_smp_cpu_kill_self(void)
 
 		ppc64_runlatch_off();
 
-		if (idle_states & OPAL_PM_WINKLE_ENABLED)
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			srr1 = power9_idle_stop(pnv_deepest_stop_state);
+		else if (idle_states & OPAL_PM_WINKLE_ENABLED)
 			srr1 = power7_winkle();
 		else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
 				(idle_states & OPAL_PM_SLEEP_ENABLED_ER1))
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index 3f175e8aedb4..57caaf11a83f 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -189,7 +189,7 @@ fail_malloc:
 	return result;
 }
 
-static int __init_refok ps3_setup_uhc_device(
+static int __ref ps3_setup_uhc_device(
 	const struct ps3_repository_device *repo, enum ps3_match_id match_id,
 	enum ps3_interrupt_type interrupt_type, enum ps3_reg_type reg_type)
 {
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index c9a3e677192a..cb3c50328de8 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -195,12 +195,12 @@ static void ps3_hpte_clear(void)
 
 void __init ps3_hpte_init(unsigned long htab_size)
 {
-	ppc_md.hpte_invalidate = ps3_hpte_invalidate;
-	ppc_md.hpte_updatepp = ps3_hpte_updatepp;
-	ppc_md.hpte_updateboltedpp = ps3_hpte_updateboltedpp;
-	ppc_md.hpte_insert = ps3_hpte_insert;
-	ppc_md.hpte_remove = ps3_hpte_remove;
-	ppc_md.hpte_clear_all = ps3_hpte_clear;
+	mmu_hash_ops.hpte_invalidate = ps3_hpte_invalidate;
+	mmu_hash_ops.hpte_updatepp = ps3_hpte_updatepp;
+	mmu_hash_ops.hpte_updateboltedpp = ps3_hpte_updateboltedpp;
+	mmu_hash_ops.hpte_insert = ps3_hpte_insert;
+	mmu_hash_ops.hpte_remove = ps3_hpte_remove;
+	mmu_hash_ops.hpte_clear_all = ps3_hpte_clear;
 
 	ppc64_pft_size = __ilog2(htab_size);
 }
diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c
index bfccdc7cb85f..814a7eaa7769 100644
--- a/arch/powerpc/platforms/ps3/repository.c
+++ b/arch/powerpc/platforms/ps3/repository.c
@@ -1198,7 +1198,7 @@ int ps3_repository_delete_highmem_info(unsigned int region_index)
 	return result ? -1 : 0;
 }
 
-#endif /* defined(CONFIG_PS3_WRITE_REPOSITORY) */
+#endif /* defined(CONFIG_PS3_REPOSITORY_WRITE) */
 
 #if defined(DEBUG)
 
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 799c8580ab09..3a487e7f4a5e 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -80,7 +80,7 @@ static void ps3_power_save(void)
 	lv1_pause(0);
 }
 
-static void ps3_restart(char *cmd)
+static void __noreturn ps3_restart(char *cmd)
 {
 	DBG("%s:%d cmd '%s'\n", __func__, __LINE__, cmd);
 
@@ -96,7 +96,7 @@ static void ps3_power_off(void)
 	ps3_sys_manager_power_off(); /* never returns */
 }
 
-static void ps3_halt(void)
+static void __noreturn ps3_halt(void)
 {
 	DBG("%s:%d\n", __func__, __LINE__);
 
@@ -226,23 +226,24 @@ static void __init ps3_progress(char *s, unsigned short hex)
 	printk("*** %04x : %s\n", hex, s ? s : "");
 }
 
-static int __init ps3_probe(void)
+void __init ps3_early_mm_init(void)
 {
 	unsigned long htab_size;
-	unsigned long dt_root;
 
+	ps3_mm_init();
+	ps3_mm_vas_create(&htab_size);
+	ps3_hpte_init(htab_size);
+}
+
+static int __init ps3_probe(void)
+{
 	DBG(" -> %s:%d\n", __func__, __LINE__);
 
-	dt_root = of_get_flat_dt_root();
-	if (!of_flat_dt_is_compatible(dt_root, "sony,ps3"))
+	if (!of_machine_is_compatible("sony,ps3"))
 		return 0;
 
-	powerpc_firmware_features |= FW_FEATURE_PS3_POSSIBLE;
-
 	ps3_os_area_save_params();
-	ps3_mm_init();
-	ps3_mm_vas_create(&htab_size);
-	ps3_hpte_init(htab_size);
+
 	pm_power_off = ps3_power_off;
 
 	DBG(" <- %s:%d\n", __func__, __LINE__);
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index fc44ad0475f8..66e7227469b8 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -574,7 +574,7 @@ static int cmm_mem_going_offline(void *arg)
 				cmm_dbg("Failed to allocate memory for list "
 						"management. Memory hotplug "
 						"failed.\n");
-				return ENOMEM;
+				return -ENOMEM;
 			}
 			memcpy(npa, pa_curr, PAGE_SIZE);
 			if (pa_curr == cmm_page_list)
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 2b93ae8d557a..4748124faa10 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -27,6 +27,15 @@
 #include <asm/uaccess.h>
 #include <asm/rtas.h>
 
+struct workqueue_struct *pseries_hp_wq;
+
+struct pseries_hp_work {
+	struct work_struct work;
+	struct pseries_hp_errorlog *errlog;
+	struct completion *hp_completion;
+	int *rc;
+};
+
 struct cc_workarea {
 	__be32	drc_index;
 	__be32	zero;
@@ -368,10 +377,51 @@ static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
 	return rc;
 }
 
+void pseries_hp_work_fn(struct work_struct *work)
+{
+	struct pseries_hp_work *hp_work =
+			container_of(work, struct pseries_hp_work, work);
+
+	if (hp_work->rc)
+		*(hp_work->rc) = handle_dlpar_errorlog(hp_work->errlog);
+	else
+		handle_dlpar_errorlog(hp_work->errlog);
+
+	if (hp_work->hp_completion)
+		complete(hp_work->hp_completion);
+
+	kfree(hp_work->errlog);
+	kfree((void *)work);
+}
+
+void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog,
+			 struct completion *hotplug_done, int *rc)
+{
+	struct pseries_hp_work *work;
+	struct pseries_hp_errorlog *hp_errlog_copy;
+
+	hp_errlog_copy = kmalloc(sizeof(struct pseries_hp_errorlog),
+				 GFP_KERNEL);
+	memcpy(hp_errlog_copy, hp_errlog, sizeof(struct pseries_hp_errorlog));
+
+	work = kmalloc(sizeof(struct pseries_hp_work), GFP_KERNEL);
+	if (work) {
+		INIT_WORK((struct work_struct *)work, pseries_hp_work_fn);
+		work->errlog = hp_errlog_copy;
+		work->hp_completion = hotplug_done;
+		work->rc = rc;
+		queue_work(pseries_hp_wq, (struct work_struct *)work);
+	} else {
+		*rc = -ENOMEM;
+		complete(hotplug_done);
+	}
+}
+
 static ssize_t dlpar_store(struct class *class, struct class_attribute *attr,
 			   const char *buf, size_t count)
 {
 	struct pseries_hp_errorlog *hp_elog;
+	struct completion hotplug_done;
 	const char *arg;
 	int rc;
 
@@ -439,7 +489,9 @@ static ssize_t dlpar_store(struct class *class, struct class_attribute *attr,
 		goto dlpar_store_out;
 	}
 
-	rc = handle_dlpar_errorlog(hp_elog);
+	init_completion(&hotplug_done);
+	queue_hotplug_event(hp_elog, &hotplug_done, &rc);
+	wait_for_completion(&hotplug_done);
 
 dlpar_store_out:
 	kfree(hp_elog);
@@ -450,6 +502,8 @@ static CLASS_ATTR(dlpar, S_IWUSR, NULL, dlpar_store);
 
 static int __init pseries_dlpar_init(void)
 {
+	pseries_hp_wq = alloc_workqueue("pseries hotplug workqueue",
+					WQ_UNBOUND, 1);
 	return sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr);
 }
 machine_device_initcall(pseries, pseries_dlpar_init);
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 3998e0f9a03b..1c428f06b14c 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -2,7 +2,7 @@
  * The file intends to implement the platform dependent EEH operations on pseries.
  * Actually, the pseries platform is built based on RTAS heavily. That means the
  * pseries platform dependent EEH operations will be built on RTAS calls. The functions
- * are devired from arch/powerpc/platforms/pseries/eeh.c and necessary cleanup has
+ * are derived from arch/powerpc/platforms/pseries/eeh.c and necessary cleanup has
  * been done.
  *
  * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2011.
diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c
index 18380e8f6dfe..a6ddca833119 100644
--- a/arch/powerpc/platforms/pseries/event_sources.c
+++ b/arch/powerpc/platforms/pseries/event_sources.c
@@ -26,48 +26,21 @@ void request_event_sources_irqs(struct device_node *np,
 {
 	int i, index, count = 0;
 	struct of_phandle_args oirq;
-	const u32 *opicprop;
-	unsigned int opicplen;
 	unsigned int virqs[16];
 
-	/* Check for obsolete "open-pic-interrupt" property. If present, then
-	 * map those interrupts using the default interrupt host and default
-	 * trigger
-	 */
-	opicprop = of_get_property(np, "open-pic-interrupt", &opicplen);
-	if (opicprop) {
-		opicplen /= sizeof(u32);
-		for (i = 0; i < opicplen; i++) {
-			if (count > 15)
-				break;
-			virqs[count] = irq_create_mapping(NULL, *(opicprop++));
-			if (virqs[count] == NO_IRQ) {
-				pr_err("event-sources: Unable to allocate "
-				       "interrupt number for %s\n",
-				       np->full_name);
-				WARN_ON(1);
-			}
-			else
-				count++;
-
-		}
-	}
-	/* Else use normal interrupt tree parsing */
-	else {
-		/* First try to do a proper OF tree parsing */
-		for (index = 0; of_irq_parse_one(np, index, &oirq) == 0;
-		     index++) {
-			if (count > 15)
-				break;
-			virqs[count] = irq_create_of_mapping(&oirq);
-			if (virqs[count] == NO_IRQ) {
-				pr_err("event-sources: Unable to allocate "
-				       "interrupt number for %s\n",
-				       np->full_name);
-				WARN_ON(1);
-			}
-			else
-				count++;
+	/* First try to do a proper OF tree parsing */
+	for (index = 0; of_irq_parse_one(np, index, &oirq) == 0;
+	     index++) {
+		if (count > 15)
+			break;
+		virqs[count] = irq_create_of_mapping(&oirq);
+		if (virqs[count] == NO_IRQ) {
+			pr_err("event-sources: Unable to allocate "
+			       "interrupt number for %s\n",
+			       np->full_name);
+			WARN_ON(1);
+		} else {
+			count++;
 		}
 	}
 
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 8c80588abacc..ea7f09bd73b1 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -22,6 +22,7 @@
  */
 
 
+#include <linux/of_fdt.h>
 #include <asm/firmware.h>
 #include <asm/prom.h>
 #include <asm/udbg.h>
@@ -69,7 +70,8 @@ hypertas_fw_features_table[] = {
  * device-tree/ibm,hypertas-functions.  Ultimately this functionality may
  * be moved into prom.c prom_init().
  */
-void __init fw_hypertas_feature_init(const char *hypertas, unsigned long len)
+static void __init fw_hypertas_feature_init(const char *hypertas,
+					    unsigned long len)
 {
 	const char *s;
 	int i;
@@ -113,7 +115,7 @@ vec5_fw_features_table[] = {
 	{FW_FEATURE_PRRN,		OV5_PRRN},
 };
 
-void __init fw_vec5_feature_init(const char *vec5, unsigned long len)
+static void __init fw_vec5_feature_init(const char *vec5, unsigned long len)
 {
 	unsigned int index, feat;
 	int i;
@@ -131,3 +133,45 @@ void __init fw_vec5_feature_init(const char *vec5, unsigned long len)
 
 	pr_debug(" <- fw_vec5_feature_init()\n");
 }
+
+/*
+ * Called very early, MMU is off, device-tree isn't unflattened
+ */
+static int __init probe_fw_features(unsigned long node, const char *uname, int
+				    depth, void *data)
+{
+	const char *prop;
+	int len;
+	static int hypertas_found;
+	static int vec5_found;
+
+	if (depth != 1)
+		return 0;
+
+	if (!strcmp(uname, "rtas") || !strcmp(uname, "rtas@0")) {
+		prop = of_get_flat_dt_prop(node, "ibm,hypertas-functions",
+					   &len);
+		if (prop) {
+			powerpc_firmware_features |= FW_FEATURE_LPAR;
+			fw_hypertas_feature_init(prop, len);
+		}
+
+		hypertas_found = 1;
+	}
+
+	if (!strcmp(uname, "chosen")) {
+		prop = of_get_flat_dt_prop(node, "ibm,architecture-vec-5",
+					   &len);
+		if (prop)
+			fw_vec5_feature_init(prop, len);
+
+		vec5_found = 1;
+	}
+
+	return hypertas_found && vec5_found;
+}
+
+void __init pseries_probe_fw_features(void)
+{
+	of_scan_flat_dt(probe_fw_features, NULL);
+}
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 282837a1d74b..a1b63e00b2f7 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -903,8 +903,6 @@ static int parse_cede_parameters(void)
 
 static int __init pseries_cpu_hotplug_init(void)
 {
-	struct device_node *np;
-	const char *typep;
 	int cpu;
 	int qcss_tok;
 
@@ -913,17 +911,6 @@ static int __init pseries_cpu_hotplug_init(void)
 	ppc_md.cpu_release = dlpar_cpu_release;
 #endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
 
-	for_each_node_by_name(np, "interrupt-controller") {
-		typep = of_get_property(np, "compatible", NULL);
-		if (strstr(typep, "open-pic")) {
-			of_node_put(np);
-
-			printk(KERN_INFO "CPU Hotplug not supported on "
-				"systems using MPIC\n");
-			return 0;
-		}
-	}
-
 	rtas_stop_self_token = rtas_token("stop-self");
 	qcss_tok = rtas_token("query-cpu-stopped-state");
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 2ce138542083..43f7beb2902d 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -69,13 +69,36 @@ unsigned long pseries_memory_block_size(void)
 	return memblock_size;
 }
 
-static void dlpar_free_drconf_property(struct property *prop)
+static void dlpar_free_property(struct property *prop)
 {
 	kfree(prop->name);
 	kfree(prop->value);
 	kfree(prop);
 }
 
+static struct property *dlpar_clone_property(struct property *prop,
+					     u32 prop_size)
+{
+	struct property *new_prop;
+
+	new_prop = kzalloc(sizeof(*new_prop), GFP_KERNEL);
+	if (!new_prop)
+		return NULL;
+
+	new_prop->name = kstrdup(prop->name, GFP_KERNEL);
+	new_prop->value = kzalloc(prop_size, GFP_KERNEL);
+	if (!new_prop->name || !new_prop->value) {
+		dlpar_free_property(new_prop);
+		return NULL;
+	}
+
+	memcpy(new_prop->value, prop->value, prop->length);
+	new_prop->length = prop_size;
+
+	of_property_set_flag(new_prop, OF_DYNAMIC);
+	return new_prop;
+}
+
 static struct property *dlpar_clone_drconf_property(struct device_node *dn)
 {
 	struct property *prop, *new_prop;
@@ -87,19 +110,10 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn)
 	if (!prop)
 		return NULL;
 
-	new_prop = kzalloc(sizeof(*new_prop), GFP_KERNEL);
+	new_prop = dlpar_clone_property(prop, prop->length);
 	if (!new_prop)
 		return NULL;
 
-	new_prop->name = kstrdup(prop->name, GFP_KERNEL);
-	new_prop->value = kmemdup(prop->value, prop->length, GFP_KERNEL);
-	if (!new_prop->name || !new_prop->value) {
-		dlpar_free_drconf_property(new_prop);
-		return NULL;
-	}
-
-	new_prop->length = prop->length;
-
 	/* Convert the property to cpu endian-ness */
 	p = new_prop->value;
 	*p = be32_to_cpu(*p);
@@ -177,14 +191,74 @@ static int dlpar_update_device_tree_lmb(struct of_drconf_cell *lmb)
 	return 0;
 }
 
+static u32 find_aa_index(struct device_node *dr_node,
+			 struct property *ala_prop, const u32 *lmb_assoc)
+{
+	u32 *assoc_arrays;
+	u32 aa_index;
+	int aa_arrays, aa_array_entries, aa_array_sz;
+	int i, index;
+
+	/*
+	 * The ibm,associativity-lookup-arrays property is defined to be
+	 * a 32-bit value specifying the number of associativity arrays
+	 * followed by a 32-bitvalue specifying the number of entries per
+	 * array, followed by the associativity arrays.
+	 */
+	assoc_arrays = ala_prop->value;
+
+	aa_arrays = be32_to_cpu(assoc_arrays[0]);
+	aa_array_entries = be32_to_cpu(assoc_arrays[1]);
+	aa_array_sz = aa_array_entries * sizeof(u32);
+
+	aa_index = -1;
+	for (i = 0; i < aa_arrays; i++) {
+		index = (i * aa_array_entries) + 2;
+
+		if (memcmp(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz))
+			continue;
+
+		aa_index = i;
+		break;
+	}
+
+	if (aa_index == -1) {
+		struct property *new_prop;
+		u32 new_prop_size;
+
+		new_prop_size = ala_prop->length + aa_array_sz;
+		new_prop = dlpar_clone_property(ala_prop, new_prop_size);
+		if (!new_prop)
+			return -1;
+
+		assoc_arrays = new_prop->value;
+
+		/* increment the number of entries in the lookup array */
+		assoc_arrays[0] = cpu_to_be32(aa_arrays + 1);
+
+		/* copy the new associativity into the lookup array */
+		index = aa_arrays * aa_array_entries + 2;
+		memcpy(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz);
+
+		of_update_property(dr_node, new_prop);
+
+		/*
+		 * The associativity lookup array index for this lmb is
+		 * number of entries - 1 since we added its associativity
+		 * to the end of the lookup array.
+		 */
+		aa_index = be32_to_cpu(assoc_arrays[0]) - 1;
+	}
+
+	return aa_index;
+}
+
 static u32 lookup_lmb_associativity_index(struct of_drconf_cell *lmb)
 {
 	struct device_node *parent, *lmb_node, *dr_node;
+	struct property *ala_prop;
 	const u32 *lmb_assoc;
-	const u32 *assoc_arrays;
 	u32 aa_index;
-	int aa_arrays, aa_array_entries, aa_array_sz;
-	int i;
 
 	parent = of_find_node_by_path("/");
 	if (!parent)
@@ -208,34 +282,15 @@ static u32 lookup_lmb_associativity_index(struct of_drconf_cell *lmb)
 		return -ENODEV;
 	}
 
-	assoc_arrays = of_get_property(dr_node,
-				       "ibm,associativity-lookup-arrays",
-				       NULL);
-	of_node_put(dr_node);
-	if (!assoc_arrays) {
+	ala_prop = of_find_property(dr_node, "ibm,associativity-lookup-arrays",
+				    NULL);
+	if (!ala_prop) {
+		of_node_put(dr_node);
 		dlpar_free_cc_nodes(lmb_node);
 		return -ENODEV;
 	}
 
-	/* The ibm,associativity-lookup-arrays property is defined to be
-	 * a 32-bit value specifying the number of associativity arrays
-	 * followed by a 32-bitvalue specifying the number of entries per
-	 * array, followed by the associativity arrays.
-	 */
-	aa_arrays = be32_to_cpu(assoc_arrays[0]);
-	aa_array_entries = be32_to_cpu(assoc_arrays[1]);
-	aa_array_sz = aa_array_entries * sizeof(u32);
-
-	aa_index = -1;
-	for (i = 0; i < aa_arrays; i++) {
-		int indx = (i * aa_array_entries) + 2;
-
-		if (memcmp(&assoc_arrays[indx], &lmb_assoc[1], aa_array_sz))
-			continue;
-
-		aa_index = i;
-		break;
-	}
+	aa_index = find_aa_index(dr_node, ala_prop, lmb_assoc);
 
 	dlpar_free_cc_nodes(lmb_node);
 	return aa_index;
@@ -533,50 +588,11 @@ static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop)
 
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
-static int dlpar_add_lmb_memory(struct of_drconf_cell *lmb)
+static int dlpar_add_lmb(struct of_drconf_cell *lmb)
 {
-	struct memory_block *mem_block;
 	unsigned long block_sz;
 	int nid, rc;
 
-	block_sz = memory_block_size_bytes();
-
-	/* Find the node id for this address */
-	nid = memory_add_physaddr_to_nid(lmb->base_addr);
-
-	/* Add the memory */
-	rc = add_memory(nid, lmb->base_addr, block_sz);
-	if (rc)
-		return rc;
-
-	/* Register this block of memory */
-	rc = memblock_add(lmb->base_addr, block_sz);
-	if (rc) {
-		remove_memory(nid, lmb->base_addr, block_sz);
-		return rc;
-	}
-
-	mem_block = lmb_to_memblock(lmb);
-	if (!mem_block) {
-		remove_memory(nid, lmb->base_addr, block_sz);
-		return -EINVAL;
-	}
-
-	rc = device_online(&mem_block->dev);
-	put_device(&mem_block->dev);
-	if (rc) {
-		remove_memory(nid, lmb->base_addr, block_sz);
-		return rc;
-	}
-
-	lmb->flags |= DRCONF_MEM_ASSIGNED;
-	return 0;
-}
-
-static int dlpar_add_lmb(struct of_drconf_cell *lmb)
-{
-	int rc;
-
 	if (lmb->flags & DRCONF_MEM_ASSIGNED)
 		return -EINVAL;
 
@@ -592,10 +608,18 @@ static int dlpar_add_lmb(struct of_drconf_cell *lmb)
 		return rc;
 	}
 
-	rc = dlpar_add_lmb_memory(lmb);
+	block_sz = memory_block_size_bytes();
+
+	/* Find the node id for this address */
+	nid = memory_add_physaddr_to_nid(lmb->base_addr);
+
+	/* Add the memory */
+	rc = add_memory(nid, lmb->base_addr, block_sz);
 	if (rc) {
 		dlpar_remove_device_tree_lmb(lmb);
 		dlpar_release_drc(lmb->drc_index);
+	} else {
+		lmb->flags |= DRCONF_MEM_ASSIGNED;
 	}
 
 	return rc;
@@ -748,7 +772,7 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
 		break;
 	}
 
-	dlpar_free_drconf_property(prop);
+	dlpar_free_property(prop);
 
 dlpar_memory_out:
 	of_node_put(dn);
diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c
index 0240c4ff878a..f053bda64ee7 100644
--- a/arch/powerpc/platforms/pseries/io_event_irq.c
+++ b/arch/powerpc/platforms/pseries/io_event_irq.c
@@ -113,7 +113,7 @@ static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog)
  * - The owner of an event is determined by combinations of scope,
  *   event type, and sub-type. There is no easy way to pre-sort clients
  *   by scope or event type alone. For example, Torrent ISR route change
- *   event is reported with scope 0x00 (Not Applicatable) rather than
+ *   event is reported with scope 0x00 (Not Applicable) rather than
  *   0x3B (Torrent-hub). It is better to let the clients to identify
  *   who owns the event.
  */
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 3e8865b187de..770a753b52c9 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -120,35 +120,6 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
 	kfree(table_group);
 }
 
-static void tce_invalidate_pSeries_sw(struct iommu_table *tbl,
-				      __be64 *startp, __be64 *endp)
-{
-	u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
-	unsigned long start, end, inc;
-
-	start = __pa(startp);
-	end = __pa(endp);
-	inc = L1_CACHE_BYTES; /* invalidate a cacheline of TCEs at a time */
-
-	/* If this is non-zero, change the format.  We shift the
-	 * address and or in the magic from the device tree. */
-	if (tbl->it_busno) {
-		start <<= 12;
-		end <<= 12;
-		inc <<= 12;
-		start |= tbl->it_busno;
-		end |= tbl->it_busno;
-	}
-
-	end |= inc - 1; /* round up end to be different than start */
-
-	mb(); /* Make sure TCEs in memory are written */
-	while (start <= end) {
-		out_be64(invalidate, start);
-		start += inc;
-	}
-}
-
 static int tce_build_pSeries(struct iommu_table *tbl, long index,
 			      long npages, unsigned long uaddr,
 			      enum dma_data_direction direction,
@@ -173,9 +144,6 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
 		uaddr += TCE_PAGE_SIZE;
 		tcep++;
 	}
-
-	if (tbl->it_type & TCE_PCI_SWINV_CREATE)
-		tce_invalidate_pSeries_sw(tbl, tces, tcep - 1);
 	return 0;
 }
 
@@ -188,9 +156,6 @@ static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
 
 	while (npages--)
 		*(tcep++) = 0;
-
-	if (tbl->it_type & TCE_PCI_SWINV_FREE)
-		tce_invalidate_pSeries_sw(tbl, tces, tcep - 1);
 }
 
 static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
@@ -537,7 +502,7 @@ static void iommu_table_setparms(struct pci_controller *phb,
 				 struct iommu_table *tbl)
 {
 	struct device_node *node;
-	const unsigned long *basep, *sw_inval;
+	const unsigned long *basep;
 	const u32 *sizep;
 
 	node = phb->dn;
@@ -575,22 +540,6 @@ static void iommu_table_setparms(struct pci_controller *phb,
 	tbl->it_index = 0;
 	tbl->it_blocksize = 16;
 	tbl->it_type = TCE_PCI;
-
-	sw_inval = of_get_property(node, "linux,tce-sw-invalidate-info", NULL);
-	if (sw_inval) {
-		/*
-		 * This property contains information on how to
-		 * invalidate the TCE entry.  The first property is
-		 * the base MMIO address used to invalidate entries.
-		 * The second property tells us the format of the TCE
-		 * invalidate (whether it needs to be shifted) and
-		 * some magic routing info to add to our invalidate
-		 * command.
-		 */
-		tbl->it_index = (unsigned long) ioremap(sw_inval[0], 8);
-		tbl->it_busno = sw_inval[1]; /* overload this with magic */
-		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
-	}
 }
 
 /*
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index 13fa95b3aa8b..6681ac97fb18 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -14,14 +14,13 @@
 #include <asm/page.h>
 #include <asm/firmware.h>
 #include <asm/kexec.h>
-#include <asm/mpic.h>
 #include <asm/xics.h>
 #include <asm/smp.h>
 #include <asm/plpar_wrappers.h>
 
 #include "pseries.h"
 
-static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
+void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 {
 	/* Don't risk a hypervisor call if we're crashing */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR) && !crash_shutdown) {
@@ -51,26 +50,6 @@ static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 			       "(hw %d) failed with %d\n", cpu, hwcpu, ret);
 		}
 	}
-}
-
-static void pseries_kexec_cpu_down_mpic(int crash_shutdown, int secondary)
-{
-	pseries_kexec_cpu_down(crash_shutdown, secondary);
-	mpic_teardown_this_cpu(secondary);
-}
 
-void __init setup_kexec_cpu_down_mpic(void)
-{
-	ppc_md.kexec_cpu_down = pseries_kexec_cpu_down_mpic;
-}
-
-static void pseries_kexec_cpu_down_xics(int crash_shutdown, int secondary)
-{
-	pseries_kexec_cpu_down(crash_shutdown, secondary);
 	xics_kexec_teardown_cpu(secondary);
 }
-
-void __init setup_kexec_cpu_down_xics(void)
-{
-	ppc_md.kexec_cpu_down = pseries_kexec_cpu_down_xics;
-}
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 7f6100d91b4b..86707e67843f 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -45,6 +45,7 @@
 #include <asm/plpar_wrappers.h>
 #include <asm/kexec.h>
 #include <asm/fadump.h>
+#include <asm/asm-prototypes.h>
 
 #include "pseries.h"
 
@@ -260,24 +261,8 @@ static void pSeries_lpar_hptab_clear(void)
 	 * This is also called on boot when a fadump happens. In that case we
 	 * must not change the exception endian mode.
 	 */
-	if (firmware_has_feature(FW_FEATURE_SET_MODE) && !is_fadump_active()) {
-		long rc;
-
-		rc = pseries_big_endian_exceptions();
-		/*
-		 * At this point it is unlikely panic() will get anything
-		 * out to the user, but at least this will stop us from
-		 * continuing on further and creating an even more
-		 * difficult to debug situation.
-		 *
-		 * There is a known problem when kdump'ing, if cpus are offline
-		 * the above call will fail. Rather than panicking again, keep
-		 * going and hope the kdump kernel is also little endian, which
-		 * it usually is.
-		 */
-		if (rc && !kdump_in_progress())
-			panic("Could not enable big endian exceptions");
-	}
+	if (firmware_has_feature(FW_FEATURE_SET_MODE) && !is_fadump_active())
+		pseries_big_endian_exceptions();
 #endif
 }
 
@@ -604,17 +589,17 @@ static int __init disable_bulk_remove(char *str)
 
 __setup("bulk_remove=", disable_bulk_remove);
 
-void __init hpte_init_lpar(void)
+void __init hpte_init_pseries(void)
 {
-	ppc_md.hpte_invalidate	= pSeries_lpar_hpte_invalidate;
-	ppc_md.hpte_updatepp	= pSeries_lpar_hpte_updatepp;
-	ppc_md.hpte_updateboltedpp = pSeries_lpar_hpte_updateboltedpp;
-	ppc_md.hpte_insert	= pSeries_lpar_hpte_insert;
-	ppc_md.hpte_remove	= pSeries_lpar_hpte_remove;
-	ppc_md.hpte_removebolted = pSeries_lpar_hpte_removebolted;
-	ppc_md.flush_hash_range	= pSeries_lpar_flush_hash_range;
-	ppc_md.hpte_clear_all   = pSeries_lpar_hptab_clear;
-	ppc_md.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
+	mmu_hash_ops.hpte_invalidate	 = pSeries_lpar_hpte_invalidate;
+	mmu_hash_ops.hpte_updatepp	 = pSeries_lpar_hpte_updatepp;
+	mmu_hash_ops.hpte_updateboltedpp = pSeries_lpar_hpte_updateboltedpp;
+	mmu_hash_ops.hpte_insert	 = pSeries_lpar_hpte_insert;
+	mmu_hash_ops.hpte_remove	 = pSeries_lpar_hpte_remove;
+	mmu_hash_ops.hpte_removebolted   = pSeries_lpar_hpte_removebolted;
+	mmu_hash_ops.flush_hash_range	 = pSeries_lpar_flush_hash_range;
+	mmu_hash_ops.hpte_clear_all      = pSeries_lpar_hptab_clear;
+	mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
 }
 
 #ifdef CONFIG_PPC_SMLPAR
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 9f8184175c86..79aef8c1c5b3 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -17,8 +17,6 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
-#include <linux/kmsg_dump.h>
-#include <linux/pstore.h>
 #include <linux/ctype.h>
 #include <asm/uaccess.h>
 #include <asm/nvram.h>
diff --git a/arch/powerpc/platforms/pseries/power.c b/arch/powerpc/platforms/pseries/power.c
index c26eadde434c..a4a0b57d1d81 100644
--- a/arch/powerpc/platforms/pseries/power.c
+++ b/arch/powerpc/platforms/pseries/power.c
@@ -27,6 +27,8 @@
 #include <linux/init.h>
 #include <asm/machdep.h>
 
+#include "pseries.h"
+
 unsigned long rtas_poweron_auto; /* default and normal state is 0 */
 
 static ssize_t auto_poweron_show(struct kobject *kobj,
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 7aa83f00ac62..b1be7b713fe6 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -20,31 +20,18 @@ extern void request_event_sources_irqs(struct device_node *np,
 
 #include <linux/of.h>
 
-extern void __init fw_hypertas_feature_init(const char *hypertas,
-					    unsigned long len);
-extern void __init fw_vec5_feature_init(const char *hypertas,
-					unsigned long len);
-
 struct pt_regs;
 
 extern int pSeries_system_reset_exception(struct pt_regs *regs);
 extern int pSeries_machine_check_exception(struct pt_regs *regs);
 
 #ifdef CONFIG_SMP
-extern void smp_init_pseries_mpic(void);
-extern void smp_init_pseries_xics(void);
+extern void smp_init_pseries(void);
 #else
-static inline void smp_init_pseries_mpic(void) { };
-static inline void smp_init_pseries_xics(void) { };
+static inline void smp_init_pseries(void) { };
 #endif
 
-#ifdef CONFIG_KEXEC
-extern void setup_kexec_cpu_down_xics(void);
-extern void setup_kexec_cpu_down_mpic(void);
-#else
-static inline void setup_kexec_cpu_down_xics(void) { }
-static inline void setup_kexec_cpu_down_mpic(void) { }
-#endif
+extern void pseries_kexec_cpu_down(int crash_shutdown, int secondary);
 
 extern void pSeries_final_fixup(void);
 
@@ -64,6 +51,8 @@ extern int dlpar_detach_node(struct device_node *);
 extern int dlpar_acquire_drc(u32 drc_index);
 extern int dlpar_release_drc(u32 drc_index);
 
+void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog,
+			 struct completion *hotplug_done, int *rc);
 #ifdef CONFIG_MEMORY_HOTPLUG
 int dlpar_memory(struct pseries_hp_errorlog *hp_elog);
 #else
diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c
index 92767791f93b..164a13d3998a 100644
--- a/arch/powerpc/platforms/pseries/pseries_energy.c
+++ b/arch/powerpc/platforms/pseries/pseries_energy.c
@@ -208,19 +208,19 @@ static ssize_t percpu_deactivate_hint_show(struct device *dev,
  *	Per-cpu value of the hint
  */
 
-struct device_attribute attr_cpu_activate_hint_list =
+static struct device_attribute attr_cpu_activate_hint_list =
 		__ATTR(pseries_activate_hint_list, 0444,
 		cpu_activate_hint_list_show, NULL);
 
-struct device_attribute attr_cpu_deactivate_hint_list =
+static struct device_attribute attr_cpu_deactivate_hint_list =
 		__ATTR(pseries_deactivate_hint_list, 0444,
 		cpu_deactivate_hint_list_show, NULL);
 
-struct device_attribute attr_percpu_activate_hint =
+static struct device_attribute attr_percpu_activate_hint =
 		__ATTR(pseries_activate_hint, 0444,
 		percpu_activate_hint_show, NULL);
 
-struct device_attribute attr_percpu_deactivate_hint =
+static struct device_attribute attr_percpu_deactivate_hint =
 		__ATTR(pseries_deactivate_hint, 0444,
 		percpu_deactivate_hint_show, NULL);
 
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 9a3e27b863ce..904a677208d1 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -43,6 +43,7 @@ static int ras_check_exception_token;
 /* EPOW events counter variable */
 static int num_epow_events;
 
+static irqreturn_t ras_hotplug_interrupt(int irq, void *dev_id);
 static irqreturn_t ras_epow_interrupt(int irq, void *dev_id);
 static irqreturn_t ras_error_interrupt(int irq, void *dev_id);
 
@@ -65,6 +66,14 @@ static int __init init_ras_IRQ(void)
 		of_node_put(np);
 	}
 
+	/* Hotplug Events */
+	np = of_find_node_by_path("/event-sources/hot-plug-events");
+	if (np != NULL) {
+		request_event_sources_irqs(np, ras_hotplug_interrupt,
+					   "RAS_HOTPLUG");
+		of_node_put(np);
+	}
+
 	/* EPOW Events */
 	np = of_find_node_by_path("/event-sources/epow-events");
 	if (np != NULL) {
@@ -190,6 +199,36 @@ static void rtas_parse_epow_errlog(struct rtas_error_log *log)
 		num_epow_events++;
 }
 
+static irqreturn_t ras_hotplug_interrupt(int irq, void *dev_id)
+{
+	struct pseries_errorlog *pseries_log;
+	struct pseries_hp_errorlog *hp_elog;
+
+	spin_lock(&ras_log_buf_lock);
+
+	rtas_call(ras_check_exception_token, 6, 1, NULL,
+		  RTAS_VECTOR_EXTERNAL_INTERRUPT, virq_to_hw(irq),
+		  RTAS_HOTPLUG_EVENTS, 0, __pa(&ras_log_buf),
+		  rtas_get_error_log_max());
+
+	pseries_log = get_pseries_errorlog((struct rtas_error_log *)ras_log_buf,
+					   PSERIES_ELOG_SECT_ID_HOTPLUG);
+	hp_elog = (struct pseries_hp_errorlog *)pseries_log->data;
+
+	/*
+	 * Since PCI hotplug is not currently supported on pseries, put PCI
+	 * hotplug events on the ras_log_buf to be handled by rtas_errd.
+	 */
+	if (hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_MEM ||
+	    hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_CPU)
+		queue_hotplug_event(hp_elog, NULL, NULL);
+	else
+		log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, 0);
+
+	spin_unlock(&ras_log_buf_lock);
+	return IRQ_HANDLED;
+}
+
 /* Handle environmental and power warning (EPOW) interrupts. */
 static irqreturn_t ras_epow_interrupt(int irq, void *dev_id)
 {
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 9883bc7ea007..4ffcaa6f8670 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -57,7 +57,6 @@
 #include <asm/time.h>
 #include <asm/nvram.h>
 #include <asm/pmc.h>
-#include <asm/mpic.h>
 #include <asm/xics.h>
 #include <asm/ppc-pci.h>
 #include <asm/i8259.h>
@@ -77,8 +76,6 @@ EXPORT_SYMBOL(CMO_PageSize);
 
 int fwnmi_active;  /* TRUE if an FWNMI handler is present */
 
-static struct device_node *pSeries_mpic_node;
-
 static void pSeries_show_cpuinfo(struct seq_file *m)
 {
 	struct device_node *root;
@@ -172,48 +169,7 @@ static void __init pseries_setup_i8259_cascade(void)
 	irq_set_chained_handler(cascade, pseries_8259_cascade);
 }
 
-static void __init pseries_mpic_init_IRQ(void)
-{
-	struct device_node *np;
-	const unsigned int *opprop;
-	unsigned long openpic_addr = 0;
-	int naddr, n, i, opplen;
-	struct mpic *mpic;
-
-	np = of_find_node_by_path("/");
-	naddr = of_n_addr_cells(np);
-	opprop = of_get_property(np, "platform-open-pic", &opplen);
-	if (opprop != NULL) {
-		openpic_addr = of_read_number(opprop, naddr);
-		printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr);
-	}
-	of_node_put(np);
-
-	BUG_ON(openpic_addr == 0);
-
-	/* Setup the openpic driver */
-	mpic = mpic_alloc(pSeries_mpic_node, openpic_addr,
-			MPIC_NO_RESET, 16, 0, " MPIC     ");
-	BUG_ON(mpic == NULL);
-
-	/* Add ISUs */
-	opplen /= sizeof(u32);
-	for (n = 0, i = naddr; i < opplen; i += naddr, n++) {
-		unsigned long isuaddr = of_read_number(opprop + i, naddr);
-		mpic_assign_isu(mpic, n, isuaddr);
-	}
-
-	/* Setup top-level get_irq */
-	ppc_md.get_irq = mpic_get_irq;
-
-	/* All ISUs are setup, complete initialization */
-	mpic_init(mpic);
-
-	/* Look for cascade */
-	pseries_setup_i8259_cascade();
-}
-
-static void __init pseries_xics_init_IRQ(void)
+static void __init pseries_init_irq(void)
 {
 	xics_init();
 	pseries_setup_i8259_cascade();
@@ -228,32 +184,6 @@ static void pseries_lpar_enable_pmcs(void)
 	plpar_hcall_norets(H_PERFMON, set, reset);
 }
 
-static void __init pseries_discover_pic(void)
-{
-	struct device_node *np;
-	const char *typep;
-
-	for_each_node_by_name(np, "interrupt-controller") {
-		typep = of_get_property(np, "compatible", NULL);
-		if (!typep)
-			continue;
-		if (strstr(typep, "open-pic")) {
-			pSeries_mpic_node = of_node_get(np);
-			ppc_md.init_IRQ       = pseries_mpic_init_IRQ;
-			setup_kexec_cpu_down_mpic();
-			smp_init_pseries_mpic();
-			return;
-		} else if (strstr(typep, "ppc-xicp")) {
-			ppc_md.init_IRQ       = pseries_xics_init_IRQ;
-			setup_kexec_cpu_down_xics();
-			smp_init_pseries_xics();
-			return;
-		}
-	}
-	printk(KERN_ERR "pSeries_discover_pic: failed to recognize"
-	       " interrupt-controller\n");
-}
-
 static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct of_reconfig_data *rd = data;
@@ -265,11 +195,8 @@ static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long act
 	case OF_RECONFIG_ATTACH_NODE:
 		parent = of_get_parent(np);
 		pdn = parent ? PCI_DN(parent) : NULL;
-		if (pdn) {
-			/* Create pdn and EEH device */
+		if (pdn)
 			pci_add_device_node_info(pdn->phb, np);
-			eeh_dev_init(PCI_DN(np), pdn->phb);
-		}
 
 		of_node_put(parent);
 		break;
@@ -367,7 +294,7 @@ static void pseries_lpar_idle(void)
 {
 	/*
 	 * Default handler to go into low thread priority and possibly
-	 * low power mode by cedeing processor to hypervisor
+	 * low power mode by ceding processor to hypervisor
 	 */
 
 	/* Indicate to hypervisor that we are idle. */
@@ -392,15 +319,23 @@ static void pseries_lpar_idle(void)
  * to ever be a problem in practice we can move this into a kernel thread to
  * finish off the process later in boot.
  */
-long pSeries_enable_reloc_on_exc(void)
+void pseries_enable_reloc_on_exc(void)
 {
 	long rc;
 	unsigned int delay, total_delay = 0;
 
 	while (1) {
 		rc = enable_reloc_on_exceptions();
-		if (!H_IS_LONG_BUSY(rc))
-			return rc;
+		if (!H_IS_LONG_BUSY(rc)) {
+			if (rc == H_P2) {
+				pr_info("Relocation on exceptions not"
+					" supported\n");
+			} else if (rc != H_SUCCESS) {
+				pr_warn("Unable to enable relocation"
+					" on exceptions: %ld\n", rc);
+			}
+			break;
+		}
 
 		delay = get_longbusy_msecs(rc);
 		total_delay += delay;
@@ -408,66 +343,81 @@ long pSeries_enable_reloc_on_exc(void)
 			pr_warn("Warning: Giving up waiting to enable "
 				"relocation on exceptions (%u msec)!\n",
 				total_delay);
-			return rc;
+			return;
 		}
 
 		mdelay(delay);
 	}
 }
-EXPORT_SYMBOL(pSeries_enable_reloc_on_exc);
+EXPORT_SYMBOL(pseries_enable_reloc_on_exc);
 
-long pSeries_disable_reloc_on_exc(void)
+void pseries_disable_reloc_on_exc(void)
 {
 	long rc;
 
 	while (1) {
 		rc = disable_reloc_on_exceptions();
 		if (!H_IS_LONG_BUSY(rc))
-			return rc;
+			break;
 		mdelay(get_longbusy_msecs(rc));
 	}
+	if (rc != H_SUCCESS)
+		pr_warning("Warning: Failed to disable relocation on "
+			   "exceptions: %ld\n", rc);
 }
-EXPORT_SYMBOL(pSeries_disable_reloc_on_exc);
+EXPORT_SYMBOL(pseries_disable_reloc_on_exc);
 
 #ifdef CONFIG_KEXEC
 static void pSeries_machine_kexec(struct kimage *image)
 {
-	long rc;
-
-	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
-		rc = pSeries_disable_reloc_on_exc();
-		if (rc != H_SUCCESS)
-			pr_warning("Warning: Failed to disable relocation on "
-				   "exceptions: %ld\n", rc);
-	}
+	if (firmware_has_feature(FW_FEATURE_SET_MODE))
+		pseries_disable_reloc_on_exc();
 
 	default_machine_kexec(image);
 }
 #endif
 
 #ifdef __LITTLE_ENDIAN__
-long pseries_big_endian_exceptions(void)
+void pseries_big_endian_exceptions(void)
 {
 	long rc;
 
 	while (1) {
 		rc = enable_big_endian_exceptions();
 		if (!H_IS_LONG_BUSY(rc))
-			return rc;
+			break;
 		mdelay(get_longbusy_msecs(rc));
 	}
+
+	/*
+	 * At this point it is unlikely panic() will get anything
+	 * out to the user, since this is called very late in kexec
+	 * but at least this will stop us from continuing on further
+	 * and creating an even more difficult to debug situation.
+	 *
+	 * There is a known problem when kdump'ing, if cpus are offline
+	 * the above call will fail. Rather than panicking again, keep
+	 * going and hope the kdump kernel is also little endian, which
+	 * it usually is.
+	 */
+	if (rc && !kdump_in_progress())
+		panic("Could not enable big endian exceptions");
 }
 
-static long pseries_little_endian_exceptions(void)
+void pseries_little_endian_exceptions(void)
 {
 	long rc;
 
 	while (1) {
 		rc = enable_little_endian_exceptions();
 		if (!H_IS_LONG_BUSY(rc))
-			return rc;
+			break;
 		mdelay(get_longbusy_msecs(rc));
 	}
+	if (rc) {
+		ppc_md.progress("H_SET_MODE LE exception fail", 0);
+		panic("Could not enable little endian exceptions");
+	}
 }
 #endif
 
@@ -492,7 +442,6 @@ static void __init find_and_init_phbs(void)
 	}
 
 	of_node_put(root);
-	pci_devs_phb_init();
 
 	/*
 	 * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties
@@ -506,7 +455,8 @@ static void __init pSeries_setup_arch(void)
 	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
 
 	/* Discover PIC type and setup ppc_md accordingly */
-	pseries_discover_pic();
+	smp_init_pseries();
+
 
 	/* openpic global configuration register (64-bit format). */
 	/* openpic Interrupt Source Unit pointer (64-bit format). */
@@ -537,18 +487,6 @@ static void __init pSeries_setup_arch(void)
 	}
 
 	ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
-
-	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
-		long rc;
-
-		rc = pSeries_enable_reloc_on_exc();
-		if (rc == H_P2) {
-			pr_info("Relocation on exceptions not supported\n");
-		} else if (rc != H_SUCCESS) {
-			pr_warn("Unable to enable relocation on exceptions: "
-				"%ld\n", rc);
-		}
-	}
 }
 
 static int __init pSeries_init_panel(void)
@@ -682,9 +620,9 @@ static void pSeries_cmo_feature_init(void)
 /*
  * Early initialization.  Relocation is on but do not reference unbolted pages
  */
-static void __init pSeries_init_early(void)
+static void __init pseries_init(void)
 {
-	pr_debug(" -> pSeries_init_early()\n");
+	pr_debug(" -> pseries_init()\n");
 
 #ifdef CONFIG_HVC_CONSOLE
 	if (firmware_has_feature(FW_FEATURE_LPAR))
@@ -701,7 +639,7 @@ static void __init pSeries_init_early(void)
 	pSeries_cmo_feature_init();
 	iommu_init_early_pSeries();
 
-	pr_debug(" <- pSeries_init_early()\n");
+	pr_debug(" <- pseries_init()\n");
 }
 
 /**
@@ -732,49 +670,9 @@ static void pseries_power_off(void)
 	for (;;);
 }
 
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-
-static int __init pseries_probe_fw_features(unsigned long node,
-					    const char *uname, int depth,
-					    void *data)
-{
-	const char *prop;
-	int len;
-	static int hypertas_found;
-	static int vec5_found;
-
-	if (depth != 1)
-		return 0;
-
-	if (!strcmp(uname, "rtas") || !strcmp(uname, "rtas@0")) {
-		prop = of_get_flat_dt_prop(node, "ibm,hypertas-functions",
-					   &len);
-		if (prop) {
-			powerpc_firmware_features |= FW_FEATURE_LPAR;
-			fw_hypertas_feature_init(prop, len);
-		}
-
-		hypertas_found = 1;
-	}
-
-	if (!strcmp(uname, "chosen")) {
-		prop = of_get_flat_dt_prop(node, "ibm,architecture-vec-5",
-					   &len);
-		if (prop)
-			fw_vec5_feature_init(prop, len);
-
-		vec5_found = 1;
-	}
-
-	return hypertas_found && vec5_found;
-}
-
 static int __init pSeries_probe(void)
 {
-	unsigned long root = of_get_flat_dt_root();
-	const char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
+	const char *dtype = of_get_property(of_root, "device_type", NULL);
 
  	if (dtype == NULL)
  		return 0;
@@ -784,41 +682,17 @@ static int __init pSeries_probe(void)
 	/* Cell blades firmware claims to be chrp while it's not. Until this
 	 * is fixed, we need to avoid those here.
 	 */
-	if (of_flat_dt_is_compatible(root, "IBM,CPBW-1.0") ||
-	    of_flat_dt_is_compatible(root, "IBM,CBEA"))
+	if (of_machine_is_compatible("IBM,CPBW-1.0") ||
+	    of_machine_is_compatible("IBM,CBEA"))
 		return 0;
 
-	pr_debug("pSeries detected, looking for LPAR capability...\n");
-
-	/* Now try to figure out if we are running on LPAR */
-	of_scan_flat_dt(pseries_probe_fw_features, NULL);
-
-#ifdef __LITTLE_ENDIAN__
-	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
-		long rc;
-		/*
-		 * Tell the hypervisor that we want our exceptions to
-		 * be taken in little endian mode. If this fails we don't
-		 * want to use BUG() because it will trigger an exception.
-		 */
-		rc = pseries_little_endian_exceptions();
-		if (rc) {
-			ppc_md.progress("H_SET_MODE LE exception fail", 0);
-			panic("Could not enable little endian exceptions");
-		}
-	}
-#endif
-
-	if (firmware_has_feature(FW_FEATURE_LPAR))
-		hpte_init_lpar();
-	else
-		hpte_init_native();
-
 	pm_power_off = pseries_power_off;
 
 	pr_debug("Machine is%s LPAR !\n",
 	         (powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not");
 
+	pseries_init();
+
 	return 1;
 }
 
@@ -837,7 +711,7 @@ define_machine(pseries) {
 	.name			= "pSeries",
 	.probe			= pSeries_probe,
 	.setup_arch		= pSeries_setup_arch,
-	.init_early		= pSeries_init_early,
+	.init_IRQ		= pseries_init_irq,
 	.show_cpuinfo		= pSeries_show_cpuinfo,
 	.log_error		= pSeries_log_error,
 	.pcibios_fixup		= pSeries_final_fixup,
@@ -853,6 +727,7 @@ define_machine(pseries) {
 	.machine_check_exception = pSeries_machine_check_exception,
 #ifdef CONFIG_KEXEC
 	.machine_kexec          = pSeries_machine_kexec,
+	.kexec_cpu_down         = pseries_kexec_cpu_down,
 #endif
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 	.memory_block_size	= pseries_memory_block_size,
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 6932ea803e33..f6f83aeccaaa 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -38,7 +38,6 @@
 #include <asm/cputable.h>
 #include <asm/firmware.h>
 #include <asm/rtas.h>
-#include <asm/mpic.h>
 #include <asm/vdso_datapage.h>
 #include <asm/cputhreads.h>
 #include <asm/xics.h>
@@ -140,7 +139,7 @@ out:
 	return 1;
 }
 
-static void smp_xics_setup_cpu(int cpu)
+static void smp_setup_cpu(int cpu)
 {
 	if (cpu != boot_cpuid)
 		xics_setup_cpu();
@@ -207,28 +206,22 @@ static __init void pSeries_smp_probe(void)
 	}
 }
 
-static struct smp_ops_t pSeries_mpic_smp_ops = {
-	.message_pass	= smp_mpic_message_pass,
-	.probe		= smp_mpic_probe,
-	.kick_cpu	= smp_pSeries_kick_cpu,
-	.setup_cpu	= smp_mpic_setup_cpu,
-};
-
-static struct smp_ops_t pSeries_xics_smp_ops = {
+static struct smp_ops_t pseries_smp_ops = {
 	.message_pass	= NULL,	/* Use smp_muxed_ipi_message_pass */
 	.cause_ipi	= NULL,	/* Filled at runtime by pSeries_smp_probe() */
 	.probe		= pSeries_smp_probe,
 	.kick_cpu	= smp_pSeries_kick_cpu,
-	.setup_cpu	= smp_xics_setup_cpu,
+	.setup_cpu	= smp_setup_cpu,
 	.cpu_bootable	= smp_generic_cpu_bootable,
 };
 
 /* This is called very early */
-static void __init smp_init_pseries(void)
+void __init smp_init_pseries(void)
 {
 	int i;
 
 	pr_debug(" -> smp_init_pSeries()\n");
+	smp_ops = &pseries_smp_ops;
 
 	alloc_bootmem_cpumask_var(&of_spin_mask);
 
@@ -258,17 +251,3 @@ static void __init smp_init_pseries(void)
 
 	pr_debug(" <- smp_init_pSeries()\n");
 }
-
-void __init smp_init_pseries_mpic(void)
-{
-	smp_ops = &pSeries_mpic_smp_ops;
-
-	smp_init_pseries();
-}
-
-void __init smp_init_pseries_xics(void)
-{
-	smp_ops = &pSeries_xics_smp_ops;
-
-	smp_init_pseries();
-}
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index 0ac12e5fd8ab..911456d17713 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -28,6 +28,7 @@
 #include <asm/udbg.h>
 #include <asm/io.h>
 #include <asm/cpm.h>
+#include <asm/fixmap.h>
 #include <soc/fsl/qe/qe.h>
 
 #include <mm/mmu_decl.h>
@@ -37,25 +38,36 @@
 #endif
 
 #ifdef CONFIG_PPC_EARLY_DEBUG_CPM
-static u32 __iomem *cpm_udbg_txdesc =
-	(u32 __iomem __force *)CONFIG_PPC_EARLY_DEBUG_CPM_ADDR;
+static u32 __iomem *cpm_udbg_txdesc;
+static u8 __iomem *cpm_udbg_txbuf;
 
 static void udbg_putc_cpm(char c)
 {
-	u8 __iomem *txbuf = (u8 __iomem __force *)in_be32(&cpm_udbg_txdesc[1]);
-
 	if (c == '\n')
 		udbg_putc_cpm('\r');
 
 	while (in_be32(&cpm_udbg_txdesc[0]) & 0x80000000)
 		;
 
-	out_8(txbuf, c);
+	out_8(cpm_udbg_txbuf, c);
 	out_be32(&cpm_udbg_txdesc[0], 0xa0000001);
 }
 
 void __init udbg_init_cpm(void)
 {
+#ifdef CONFIG_PPC_8xx
+	cpm_udbg_txdesc = (u32 __iomem __force *)
+			  (CONFIG_PPC_EARLY_DEBUG_CPM_ADDR - PHYS_IMMR_BASE +
+			   VIRT_IMMR_BASE);
+	cpm_udbg_txbuf = (u8 __iomem __force *)
+			 (in_be32(&cpm_udbg_txdesc[1]) - PHYS_IMMR_BASE +
+			  VIRT_IMMR_BASE);
+#else
+	cpm_udbg_txdesc = (u32 __iomem __force *)
+			  CONFIG_PPC_EARLY_DEBUG_CPM_ADDR;
+	cpm_udbg_txbuf = (u8 __iomem __force *)in_be32(&cpm_udbg_txdesc[1]);
+#endif
+
 	if (cpm_udbg_txdesc) {
 #ifdef CONFIG_CPM2
 		setbat(1, 0xf0000000, 0xf0000000, 1024*1024, PAGE_KERNEL_NCG);
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index b7348637eae0..26904f4879ec 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -48,16 +48,10 @@
 
 #include "dart.h"
 
-/* Physical base address and size of the DART table */
-unsigned long dart_tablebase; /* exported to htab_initialize */
+/* DART table address and size */
+static u32 *dart_tablebase;
 static unsigned long dart_tablesize;
 
-/* Virtual base address of the DART table */
-static u32 *dart_vbase;
-#ifdef CONFIG_PM
-static u32 *dart_copy;
-#endif
-
 /* Mapped base address for the dart */
 static unsigned int __iomem *dart;
 
@@ -151,6 +145,34 @@ wait_more:
 	spin_unlock_irqrestore(&invalidate_lock, flags);
 }
 
+static void dart_cache_sync(unsigned int *base, unsigned int count)
+{
+	/*
+	 * We add 1 to the number of entries to flush, following a
+	 * comment in Darwin indicating that the memory controller
+	 * can prefetch unmapped memory under some circumstances.
+	 */
+	unsigned long start = (unsigned long)base;
+	unsigned long end = start + (count + 1) * sizeof(unsigned int);
+	unsigned int tmp;
+
+	/* Perform a standard cache flush */
+	flush_inval_dcache_range(start, end);
+
+	/*
+	 * Perform the sequence described in the CPC925 manual to
+	 * ensure all the data gets to a point the cache incoherent
+	 * DART hardware will see.
+	 */
+	asm volatile(" sync;"
+		     " isync;"
+		     " dcbf 0,%1;"
+		     " sync;"
+		     " isync;"
+		     " lwz %0,0(%1);"
+		     " isync" : "=r" (tmp) : "r" (end) : "memory");
+}
+
 static void dart_flush(struct iommu_table *tbl)
 {
 	mb();
@@ -165,13 +187,13 @@ static int dart_build(struct iommu_table *tbl, long index,
 		       enum dma_data_direction direction,
 		       struct dma_attrs *attrs)
 {
-	unsigned int *dp;
+	unsigned int *dp, *orig_dp;
 	unsigned int rpn;
 	long l;
 
 	DBG("dart: build at: %lx, %lx, addr: %x\n", index, npages, uaddr);
 
-	dp = ((unsigned int*)tbl->it_base) + index;
+	orig_dp = dp = ((unsigned int*)tbl->it_base) + index;
 
 	/* On U3, all memory is contiguous, so we can move this
 	 * out of the loop.
@@ -184,11 +206,7 @@ static int dart_build(struct iommu_table *tbl, long index,
 
 		uaddr += DART_PAGE_SIZE;
 	}
-
-	/* make sure all updates have reached memory */
-	mb();
-	in_be32((unsigned __iomem *)dp);
-	mb();
+	dart_cache_sync(orig_dp, npages);
 
 	if (dart_is_u4) {
 		rpn = index;
@@ -203,7 +221,8 @@ static int dart_build(struct iommu_table *tbl, long index,
 
 static void dart_free(struct iommu_table *tbl, long index, long npages)
 {
-	unsigned int *dp;
+	unsigned int *dp, *orig_dp;
+	long orig_npages = npages;
 
 	/* We don't worry about flushing the TLB cache. The only drawback of
 	 * not doing it is that we won't catch buggy device drivers doing
@@ -212,34 +231,30 @@ static void dart_free(struct iommu_table *tbl, long index, long npages)
 
 	DBG("dart: free at: %lx, %lx\n", index, npages);
 
-	dp  = ((unsigned int *)tbl->it_base) + index;
+	orig_dp = dp  = ((unsigned int *)tbl->it_base) + index;
 
 	while (npages--)
 		*(dp++) = dart_emptyval;
-}
 
+	dart_cache_sync(orig_dp, orig_npages);
+}
 
-static int __init dart_init(struct device_node *dart_node)
+static void allocate_dart(void)
 {
-	unsigned int i;
-	unsigned long tmp, base, size;
-	struct resource r;
-
-	if (dart_tablebase == 0 || dart_tablesize == 0) {
-		printk(KERN_INFO "DART: table not allocated, using "
-		       "direct DMA\n");
-		return -ENODEV;
-	}
+	unsigned long tmp;
 
-	if (of_address_to_resource(dart_node, 0, &r))
-		panic("DART: can't get register base ! ");
+	/* 512 pages (2MB) is max DART tablesize. */
+	dart_tablesize = 1UL << 21;
 
-	/* Make sure nothing from the DART range remains in the CPU cache
-	 * from a previous mapping that existed before the kernel took
-	 * over
+	/*
+	 * 16MB (1 << 24) alignment. We allocate a full 16Mb chuck since we
+	 * will blow up an entire large page anyway in the kernel mapping.
 	 */
-	flush_dcache_phys_range(dart_tablebase,
-				dart_tablebase + dart_tablesize);
+	dart_tablebase = __va(memblock_alloc_base(1UL<<24,
+						  1UL<<24, 0x80000000L));
+
+	/* There is no point scanning the DART space for leaks*/
+	kmemleak_no_scan((void *)dart_tablebase);
 
 	/* Allocate a spare page to map all invalid DART pages. We need to do
 	 * that to work around what looks like a problem with the HT bridge
@@ -249,20 +264,51 @@ static int __init dart_init(struct device_node *dart_node)
 	dart_emptyval = DARTMAP_VALID | ((tmp >> DART_PAGE_SHIFT) &
 					 DARTMAP_RPNMASK);
 
+	printk(KERN_INFO "DART table allocated at: %p\n", dart_tablebase);
+}
+
+static int __init dart_init(struct device_node *dart_node)
+{
+	unsigned int i;
+	unsigned long base, size;
+	struct resource r;
+
+	/* IOMMU disabled by the user ? bail out */
+	if (iommu_is_off)
+		return -ENODEV;
+
+	/*
+	 * Only use the DART if the machine has more than 1GB of RAM
+	 * or if requested with iommu=on on cmdline.
+	 *
+	 * 1GB of RAM is picked as limit because some default devices
+	 * (i.e. Airport Extreme) have 30 bit address range limits.
+	 */
+
+	if (!iommu_force_on && memblock_end_of_DRAM() <= 0x40000000ull)
+		return -ENODEV;
+
+	/* Get DART registers */
+	if (of_address_to_resource(dart_node, 0, &r))
+		panic("DART: can't get register base ! ");
+
 	/* Map in DART registers */
 	dart = ioremap(r.start, resource_size(&r));
 	if (dart == NULL)
 		panic("DART: Cannot map registers!");
 
-	/* Map in DART table */
-	dart_vbase = ioremap(__pa(dart_tablebase), dart_tablesize);
+	/* Allocate the DART and dummy page */
+	allocate_dart();
 
 	/* Fill initial table */
 	for (i = 0; i < dart_tablesize/4; i++)
-		dart_vbase[i] = dart_emptyval;
+		dart_tablebase[i] = dart_emptyval;
+
+	/* Push to memory */
+	dart_cache_sync(dart_tablebase, dart_tablesize / sizeof(u32));
 
 	/* Initialize DART with table base and enable it. */
-	base = dart_tablebase >> DART_PAGE_SHIFT;
+	base = ((unsigned long)dart_tablebase) >> DART_PAGE_SHIFT;
 	size = dart_tablesize >> DART_PAGE_SHIFT;
 	if (dart_is_u4) {
 		size &= DART_SIZE_U4_SIZE_MASK;
@@ -301,7 +347,7 @@ static void iommu_table_dart_setup(void)
 	iommu_table_dart.it_page_shift = IOMMU_PAGE_SHIFT_4K;
 
 	/* Initialize the common IOMMU code */
-	iommu_table_dart.it_base = (unsigned long)dart_vbase;
+	iommu_table_dart.it_base = (unsigned long)dart_tablebase;
 	iommu_table_dart.it_index = 0;
 	iommu_table_dart.it_blocksize = 1;
 	iommu_table_dart.it_ops = &iommu_dart_ops;
@@ -404,75 +450,21 @@ void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
 }
 
 #ifdef CONFIG_PM
-static void iommu_dart_save(void)
-{
-	memcpy(dart_copy, dart_vbase, 2*1024*1024);
-}
-
 static void iommu_dart_restore(void)
 {
-	memcpy(dart_vbase, dart_copy, 2*1024*1024);
+	dart_cache_sync(dart_tablebase, dart_tablesize / sizeof(u32));
 	dart_tlb_invalidate_all();
 }
 
 static int __init iommu_init_late_dart(void)
 {
-	unsigned long tbasepfn;
-	struct page *p;
-
-	/* if no dart table exists then we won't need to save it
-	 * and the area has also not been reserved */
 	if (!dart_tablebase)
 		return 0;
 
-	tbasepfn = __pa(dart_tablebase) >> PAGE_SHIFT;
-	register_nosave_region_late(tbasepfn,
-				    tbasepfn + ((1<<24) >> PAGE_SHIFT));
-
-	/* For suspend we need to copy the dart contents because
-	 * it is not part of the regular mapping (see above) and
-	 * thus not saved automatically. The memory for this copy
-	 * must be allocated early because we need 2 MB. */
-	p = alloc_pages(GFP_KERNEL, 21 - PAGE_SHIFT);
-	BUG_ON(!p);
-	dart_copy = page_address(p);
-
-	ppc_md.iommu_save = iommu_dart_save;
 	ppc_md.iommu_restore = iommu_dart_restore;
 
 	return 0;
 }
 
 late_initcall(iommu_init_late_dart);
-#endif
-
-void __init alloc_dart_table(void)
-{
-	/* Only reserve DART space if machine has more than 1GB of RAM
-	 * or if requested with iommu=on on cmdline.
-	 *
-	 * 1GB of RAM is picked as limit because some default devices
-	 * (i.e. Airport Extreme) have 30 bit address range limits.
-	 */
-
-	if (iommu_is_off)
-		return;
-
-	if (!iommu_force_on && memblock_end_of_DRAM() <= 0x40000000ull)
-		return;
-
-	/* 512 pages (2MB) is max DART tablesize. */
-	dart_tablesize = 1UL << 21;
-	/* 16MB (1 << 24) alignment. We allocate a full 16Mb chuck since we
-	 * will blow up an entire large page anyway in the kernel mapping
-	 */
-	dart_tablebase = (unsigned long)
-		__va(memblock_alloc_base(1UL<<24, 1UL<<24, 0x80000000L));
-	/*
-	 * The DART space is later unmapped from the kernel linear mapping and
-	 * accessing dart_tablebase during kmemleak scanning will fault.
-	 */
-	kmemleak_no_scan((void *)dart_tablebase);
-
-	printk(KERN_INFO "DART table allocated at: %lx\n", dart_tablebase);
-}
+#endif /* CONFIG_PM */
diff --git a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
index 861cebf9c292..c27058e5df26 100644
--- a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
+++ b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
@@ -90,12 +90,8 @@ static int mpc85xx_l2ctlr_of_probe(struct platform_device *dev)
 	}
 	l2cache_size = *prop;
 
-	if (get_cache_sram_params(&sram_params)) {
-		dev_err(&dev->dev,
-			"Entire L2 as cache, provide valid sram offset and size\n");
-		return -EINVAL;
-	}
-
+	if (get_cache_sram_params(&sram_params))
+		return 0; /* fall back to L2 cache only */
 
 	rem = l2cache_size % sram_params.sram_size;
 	ways = LOCK_WAYS_FULL * sram_params.sram_size / l2cache_size;
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index f5bf38b94595..984e816f3faf 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -289,7 +289,7 @@ static void fsl_rio_inbound_mem_init(struct rio_priv *priv)
 }
 
 int fsl_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
-	u64 rstart, u32 size, u32 flags)
+	u64 rstart, u64 size, u32 flags)
 {
 	struct rio_priv *priv = mport->priv;
 	u32 base_size;
@@ -298,7 +298,7 @@ int fsl_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
 	u32 riwar;
 	int i;
 
-	if ((size & (size - 1)) != 0)
+	if ((size & (size - 1)) != 0 || size > 0x400000000ULL)
 		return -EINVAL;
 
 	base_size_log = ilog2(size);
@@ -643,19 +643,11 @@ int fsl_rio_setup(struct platform_device *dev)
 		port->ops = ops;
 		port->priv = priv;
 		port->phys_efptr = 0x100;
+		port->phys_rmap = 1;
 		priv->regs_win = rio_regs_win;
 
-		/* Probe the master port phy type */
 		ccsr = in_be32(priv->regs_win + RIO_CCSR + i*0x20);
-		port->phy_type = (ccsr & 1) ? RIO_PHY_SERIAL : RIO_PHY_PARALLEL;
-		if (port->phy_type == RIO_PHY_PARALLEL) {
-			dev_err(&dev->dev, "RIO: Parallel PHY type, unsupported port type!\n");
-			release_resource(&port->iores);
-			kfree(priv);
-			kfree(port);
-			continue;
-		}
-		dev_info(&dev->dev, "RapidIO PHY type: Serial\n");
+
 		/* Checking the port training status */
 		if (in_be32((priv->regs_win + RIO_ESCSR + i*0x20)) & 1) {
 			dev_err(&dev->dev, "Port %d is not ready. "
@@ -705,11 +697,9 @@ int fsl_rio_setup(struct platform_device *dev)
 			((i == 0) ? RIO_INB_ATMU_REGS_PORT1_OFFSET :
 			RIO_INB_ATMU_REGS_PORT2_OFFSET));
 
-
-		/* Set to receive any dist ID for serial RapidIO controller. */
-		if (port->phy_type == RIO_PHY_SERIAL)
-			out_be32((priv->regs_win
-				+ RIO_ISR_AACR + i*0x80), RIO_ISR_AACR_AA);
+		/* Set to receive packets with any dest ID */
+		out_be32((priv->regs_win + RIO_ISR_AACR + i*0x80),
+			 RIO_ISR_AACR_AA);
 
 		/* Configure maintenance transaction window */
 		out_be32(&priv->maint_atmu_regs->rowbar,
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index 99269c041615..a09ca704de58 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -204,7 +204,7 @@ static int __init setup_rstcr(void)
 
 arch_initcall(setup_rstcr);
 
-void fsl_rstcr_restart(char *cmd)
+void __noreturn fsl_rstcr_restart(char *cmd)
 {
 	local_irq_disable();
 	if (rstcr)
@@ -228,10 +228,11 @@ EXPORT_SYMBOL(diu_ops);
  * to initiate a partition restart when we're running under the Freescale
  * hypervisor.
  */
-void fsl_hv_restart(char *cmd)
+void __noreturn fsl_hv_restart(char *cmd)
 {
 	pr_info("hv restart\n");
 	fh_partition_restart(-1);
+	while (1) ;
 }
 
 /*
@@ -241,9 +242,10 @@ void fsl_hv_restart(char *cmd)
  * function pointers, to shut down the partition when we're running under
  * the Freescale hypervisor.
  */
-void fsl_hv_halt(void)
+void __noreturn fsl_hv_halt(void)
 {
 	pr_info("hv exit\n");
 	fh_partition_stop(-1);
+	while (1) ;
 }
 #endif
diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h
index 4c5a19ef4f0b..433566a5ef19 100644
--- a/arch/powerpc/sysdev/fsl_soc.h
+++ b/arch/powerpc/sysdev/fsl_soc.h
@@ -19,7 +19,7 @@ extern u32 fsl_get_sys_freq(void);
 struct spi_board_info;
 struct device_node;
 
-extern void fsl_rstcr_restart(char *cmd);
+extern void __noreturn fsl_rstcr_restart(char *cmd);
 
 /* The different ports that the DIU can be connected to */
 enum fsl_diu_monitor_port {
@@ -42,8 +42,8 @@ struct platform_diu_data_ops {
 
 extern struct platform_diu_data_ops diu_ops;
 
-void fsl_hv_restart(char *cmd);
-void fsl_hv_halt(void);
+void __noreturn fsl_hv_restart(char *cmd);
+void __noreturn fsl_hv_halt(void);
 
 #endif
 #endif
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index ed5234ed8d3f..5ebd3f018295 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -112,7 +112,7 @@ int msi_bitmap_reserve_dt_hwirqs(struct msi_bitmap *bmp)
 	return 0;
 }
 
-int __init_refok msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count,
+int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count,
 		     struct device_node *of_node)
 {
 	int size;
diff --git a/arch/powerpc/sysdev/xics/Makefile b/arch/powerpc/sysdev/xics/Makefile
index c606aa8ba60a..5d7f5a6564de 100644
--- a/arch/powerpc/sysdev/xics/Makefile
+++ b/arch/powerpc/sysdev/xics/Makefile
@@ -4,4 +4,4 @@ obj-y				+= xics-common.o
 obj-$(CONFIG_PPC_ICP_NATIVE)	+= icp-native.o
 obj-$(CONFIG_PPC_ICP_HV)	+= icp-hv.o
 obj-$(CONFIG_PPC_ICS_RTAS)	+= ics-rtas.o
-obj-$(CONFIG_PPC_POWERNV)	+= ics-opal.o
+obj-$(CONFIG_PPC_POWERNV)	+= ics-opal.o icp-opal.o
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
new file mode 100644
index 000000000000..57d72f10a97f
--- /dev/null
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -0,0 +1,144 @@
+/*
+ * Copyright 2016 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+
+#include <asm/smp.h>
+#include <asm/irq.h>
+#include <asm/errno.h>
+#include <asm/xics.h>
+#include <asm/io.h>
+#include <asm/opal.h>
+
+static void icp_opal_teardown_cpu(void)
+{
+	int cpu = smp_processor_id();
+
+	/* Clear any pending IPI */
+	opal_int_set_mfrr(cpu, 0xff);
+}
+
+static void icp_opal_flush_ipi(void)
+{
+	/*
+	 * We take the ipi irq but and never return so we need to EOI the IPI,
+	 * but want to leave our priority 0.
+	 *
+	 * Should we check all the other interrupts too?
+	 * Should we be flagging idle loop instead?
+	 * Or creating some task to be scheduled?
+	 */
+	opal_int_eoi((0x00 << 24) | XICS_IPI);
+}
+
+static unsigned int icp_opal_get_irq(void)
+{
+	unsigned int xirr;
+	unsigned int vec;
+	unsigned int irq;
+	int64_t rc;
+
+	rc = opal_int_get_xirr(&xirr, false);
+	if (rc < 0)
+		return NO_IRQ;
+	xirr = be32_to_cpu(xirr);
+	vec = xirr & 0x00ffffff;
+	if (vec == XICS_IRQ_SPURIOUS)
+		return NO_IRQ;
+
+	irq = irq_find_mapping(xics_host, vec);
+	if (likely(irq != NO_IRQ)) {
+		xics_push_cppr(vec);
+		return irq;
+	}
+
+	/* We don't have a linux mapping, so have rtas mask it. */
+	xics_mask_unknown_vec(vec);
+
+	/* We might learn about it later, so EOI it */
+	opal_int_eoi(xirr);
+
+	return NO_IRQ;
+}
+
+static void icp_opal_set_cpu_priority(unsigned char cppr)
+{
+	xics_set_base_cppr(cppr);
+	opal_int_set_cppr(cppr);
+	iosync();
+}
+
+static void icp_opal_eoi(struct irq_data *d)
+{
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+	int64_t rc;
+
+	iosync();
+	rc = opal_int_eoi((xics_pop_cppr() << 24) | hw_irq);
+
+	/*
+	 * EOI tells us whether there are more interrupts to fetch.
+	 *
+	 * Some HW implementations might not be able to send us another
+	 * external interrupt in that case, so we force a replay.
+	 */
+	if (rc > 0)
+		force_external_irq_replay();
+}
+
+#ifdef CONFIG_SMP
+
+static void icp_opal_cause_ipi(int cpu, unsigned long data)
+{
+	opal_int_set_mfrr(cpu, IPI_PRIORITY);
+}
+
+static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id)
+{
+	int cpu = smp_processor_id();
+
+	opal_int_set_mfrr(cpu, 0xff);
+
+	return smp_ipi_demux();
+}
+
+#endif /* CONFIG_SMP */
+
+static const struct icp_ops icp_opal_ops = {
+	.get_irq	= icp_opal_get_irq,
+	.eoi		= icp_opal_eoi,
+	.set_priority	= icp_opal_set_cpu_priority,
+	.teardown_cpu	= icp_opal_teardown_cpu,
+	.flush_ipi	= icp_opal_flush_ipi,
+#ifdef CONFIG_SMP
+	.ipi_action	= icp_opal_ipi_action,
+	.cause_ipi	= icp_opal_cause_ipi,
+#endif
+};
+
+int icp_opal_init(void)
+{
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
+	if (!np)
+		return -ENODEV;
+
+	icp_ops = &icp_opal_ops;
+
+	printk("XICS: Using OPAL ICP fallbacks\n");
+
+	return 0;
+}
+
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 47e43b7b076b..a795a5f0301c 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -404,8 +404,11 @@ void __init xics_init(void)
 	/* Fist locate ICP */
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		rc = icp_hv_init();
-	if (rc < 0)
+	if (rc < 0) {
 		rc = icp_native_init();
+		if (rc == -ENODEV)
+		    rc = icp_opal_init();
+	}
 	if (rc < 0) {
 		pr_warning("XICS: Cannot find a Presentation Controller !\n");
 		return;
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index c5e155108be5..760545519a0b 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -184,9 +184,6 @@ static void dump_tlb_book3e(void);
 
 static int xmon_no_auto_backtrace;
 
-extern void xmon_enter(void);
-extern void xmon_leave(void);
-
 #ifdef CONFIG_PPC64
 #define REG		"%.16lx"
 #else
@@ -1685,9 +1682,78 @@ write_spr(int n, unsigned long val)
 	catch_spr_faults = 0;
 }
 
-static unsigned long regno;
-extern char exc_prolog;
-extern char dec_exc;
+static void dump_206_sprs(void)
+{
+#ifdef CONFIG_PPC64
+	if (!cpu_has_feature(CPU_FTR_ARCH_206))
+		return;
+
+	/* Actually some of these pre-date 2.06, but whatevs */
+
+	printf("srr0   = %.16x  srr1  = %.16x dsisr  = %.8x\n",
+		mfspr(SPRN_SRR0), mfspr(SPRN_SRR1), mfspr(SPRN_DSISR));
+	printf("dscr   = %.16x  ppr   = %.16x pir    = %.8x\n",
+		mfspr(SPRN_DSCR), mfspr(SPRN_PPR), mfspr(SPRN_PIR));
+
+	if (!(mfmsr() & MSR_HV))
+		return;
+
+	printf("sdr1   = %.16x  hdar  = %.16x hdsisr = %.8x\n",
+		mfspr(SPRN_SDR1), mfspr(SPRN_HDAR), mfspr(SPRN_HDSISR));
+	printf("hsrr0  = %.16x hsrr1  = %.16x hdec = %.8x\n",
+		mfspr(SPRN_HSRR0), mfspr(SPRN_HSRR1), mfspr(SPRN_HDEC));
+	printf("lpcr   = %.16x  pcr   = %.16x lpidr = %.8x\n",
+		mfspr(SPRN_LPCR), mfspr(SPRN_PCR), mfspr(SPRN_LPID));
+	printf("hsprg0 = %.16x hsprg1 = %.16x\n",
+		mfspr(SPRN_HSPRG0), mfspr(SPRN_HSPRG1));
+	printf("dabr   = %.16x dabrx  = %.16x\n",
+		mfspr(SPRN_DABR), mfspr(SPRN_DABRX));
+#endif
+}
+
+static void dump_207_sprs(void)
+{
+#ifdef CONFIG_PPC64
+	unsigned long msr;
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return;
+
+	printf("dpdes  = %.16x  tir   = %.16x cir    = %.8x\n",
+		mfspr(SPRN_DPDES), mfspr(SPRN_TIR), mfspr(SPRN_CIR));
+
+	printf("fscr   = %.16x  tar   = %.16x pspb   = %.8x\n",
+		mfspr(SPRN_FSCR), mfspr(SPRN_TAR), mfspr(SPRN_PSPB));
+
+	msr = mfmsr();
+	if (msr & MSR_TM) {
+		/* Only if TM has been enabled in the kernel */
+		printf("tfhar  = %.16x  tfiar = %.16x texasr = %.16x\n",
+			mfspr(SPRN_TFHAR), mfspr(SPRN_TFIAR),
+			mfspr(SPRN_TEXASR));
+	}
+
+	printf("mmcr0  = %.16x  mmcr1 = %.16x mmcr2  = %.16x\n",
+		mfspr(SPRN_MMCR0), mfspr(SPRN_MMCR1), mfspr(SPRN_MMCR2));
+	printf("pmc1   = %.8x pmc2 = %.8x  pmc3 = %.8x  pmc4   = %.8x\n",
+		mfspr(SPRN_PMC1), mfspr(SPRN_PMC2),
+		mfspr(SPRN_PMC3), mfspr(SPRN_PMC4));
+	printf("mmcra  = %.16x   siar = %.16x pmc5   = %.8x\n",
+		mfspr(SPRN_MMCRA), mfspr(SPRN_SIAR), mfspr(SPRN_PMC5));
+	printf("sdar   = %.16x   sier = %.16x pmc6   = %.8x\n",
+		mfspr(SPRN_SDAR), mfspr(SPRN_SIER), mfspr(SPRN_PMC6));
+	printf("ebbhr  = %.16x  ebbrr = %.16x bescr  = %.16x\n",
+		mfspr(SPRN_EBBHR), mfspr(SPRN_EBBRR), mfspr(SPRN_BESCR));
+
+	if (!(msr & MSR_HV))
+		return;
+
+	printf("hfscr  = %.16x  dhdes = %.16x rpr    = %.16x\n",
+		mfspr(SPRN_HFSCR), mfspr(SPRN_DHDES), mfspr(SPRN_RPR));
+	printf("dawr   = %.16x  dawrx = %.16x ciabr  = %.16x\n",
+		mfspr(SPRN_DAWR), mfspr(SPRN_DAWRX), mfspr(SPRN_CIABR));
+#endif
+}
 
 static void dump_one_spr(int spr, bool show_unimplemented)
 {
@@ -1719,6 +1785,7 @@ static void dump_one_spr(int spr, bool show_unimplemented)
 
 static void super_regs(void)
 {
+	static unsigned long regno;
 	int cmd;
 	int spr;
 
@@ -1730,14 +1797,18 @@ static void super_regs(void)
 		asm("mr %0,1" : "=r" (sp) :);
 		asm("mr %0,2" : "=r" (toc) :);
 
-		printf("msr  = "REG"  sprg0= "REG"\n",
+		printf("msr    = "REG"  sprg0 = "REG"\n",
 		       mfmsr(), mfspr(SPRN_SPRG0));
-		printf("pvr  = "REG"  sprg1= "REG"\n",
+		printf("pvr    = "REG"  sprg1 = "REG"\n",
 		       mfspr(SPRN_PVR), mfspr(SPRN_SPRG1));
-		printf("dec  = "REG"  sprg2= "REG"\n",
+		printf("dec    = "REG"  sprg2 = "REG"\n",
 		       mfspr(SPRN_DEC), mfspr(SPRN_SPRG2));
-		printf("sp   = "REG"  sprg3= "REG"\n", sp, mfspr(SPRN_SPRG3));
-		printf("toc  = "REG"  dar  = "REG"\n", toc, mfspr(SPRN_DAR));
+		printf("sp     = "REG"  sprg3 = "REG"\n", sp, mfspr(SPRN_SPRG3));
+		printf("toc    = "REG"  dar   = "REG"\n", toc, mfspr(SPRN_DAR));
+
+		dump_206_sprs();
+		dump_207_sprs();
+
 		return;
 	}
 	case 'w': {
@@ -2213,13 +2284,13 @@ static void dump_one_paca(int cpu)
 	DUMP(p, subcore_sibling_mask, "x");
 #endif
 
-	DUMP(p, user_time, "llx");
-	DUMP(p, system_time, "llx");
-	DUMP(p, user_time_scaled, "llx");
-	DUMP(p, starttime, "llx");
-	DUMP(p, starttime_user, "llx");
-	DUMP(p, startspurr, "llx");
-	DUMP(p, utime_sspurr, "llx");
+	DUMP(p, accounting.user_time, "llx");
+	DUMP(p, accounting.system_time, "llx");
+	DUMP(p, accounting.user_time_scaled, "llx");
+	DUMP(p, accounting.starttime, "llx");
+	DUMP(p, accounting.starttime_user, "llx");
+	DUMP(p, accounting.startspurr, "llx");
+	DUMP(p, accounting.utime_sspurr, "llx");
 	DUMP(p, stolen_time, "llx");
 #undef DUMP
 
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 98ec652cc332..33ba697c782d 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -18,7 +18,7 @@ KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 
 GCOV_PROFILE := n
 
-OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o sclp.o ebcdic.o)
+OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o sclp.o ebcdic.o als.o)
 OBJECTS += $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o
 
 LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
@@ -33,10 +33,10 @@ quiet_cmd_sizes = GEN $@
 $(obj)/sizes.h: vmlinux
 	$(call if_changed,sizes)
 
-AFLAGS_head.o += -I$(obj)
+AFLAGS_head.o += -I$(objtree)/$(obj)
 $(obj)/head.o: $(obj)/sizes.h
 
-CFLAGS_misc.o += -I$(obj)
+CFLAGS_misc.o += -I$(objtree)/$(obj)
 $(obj)/misc.o: $(obj)/sizes.h
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index 67d43a0eabb4..28f03ca60100 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -19,29 +19,10 @@
 #include <asm/ebcdic.h>
 #include "hypfs.h"
 
-#define LPAR_NAME_LEN 8		/* lpar name len in diag 204 data */
-#define CPU_NAME_LEN 16		/* type name len of cpus in diag224 name table */
 #define TMP_SIZE 64		/* size of temporary buffers */
 
 #define DBFS_D204_HDR_VERSION	0
 
-/* diag 204 subcodes */
-enum diag204_sc {
-	SUBC_STIB4 = 4,
-	SUBC_RSI = 5,
-	SUBC_STIB6 = 6,
-	SUBC_STIB7 = 7
-};
-
-/* The two available diag 204 data formats */
-enum diag204_format {
-	INFO_SIMPLE = 0,
-	INFO_EXT = 0x00010000
-};
-
-/* bit is set in flags, when physical cpu info is included in diag 204 data */
-#define LPAR_PHYS_FLG  0x80
-
 static char *diag224_cpu_names;			/* diag 224 name table */
 static enum diag204_sc diag204_store_sc;	/* used subcode for store */
 static enum diag204_format diag204_info_type;	/* used diag 204 data format */
@@ -53,7 +34,7 @@ static int diag204_buf_pages;		/* number of pages for diag204 data */
 static struct dentry *dbfs_d204_file;
 
 /*
- * DIAG 204 data structures and member access functions.
+ * DIAG 204 member access functions.
  *
  * Since we have two different diag 204 data formats for old and new s390
  * machines, we do not access the structs directly, but use getter functions for
@@ -62,304 +43,173 @@ static struct dentry *dbfs_d204_file;
 
 /* Time information block */
 
-struct info_blk_hdr {
-	__u8  npar;
-	__u8  flags;
-	__u16 tslice;
-	__u16 phys_cpus;
-	__u16 this_part;
-	__u64 curtod;
-} __attribute__ ((packed));
-
-struct x_info_blk_hdr {
-	__u8  npar;
-	__u8  flags;
-	__u16 tslice;
-	__u16 phys_cpus;
-	__u16 this_part;
-	__u64 curtod1;
-	__u64 curtod2;
-	char reserved[40];
-} __attribute__ ((packed));
-
 static inline int info_blk_hdr__size(enum diag204_format type)
 {
-	if (type == INFO_SIMPLE)
-		return sizeof(struct info_blk_hdr);
-	else /* INFO_EXT */
-		return sizeof(struct x_info_blk_hdr);
+	if (type == DIAG204_INFO_SIMPLE)
+		return sizeof(struct diag204_info_blk_hdr);
+	else /* DIAG204_INFO_EXT */
+		return sizeof(struct diag204_x_info_blk_hdr);
 }
 
 static inline __u8 info_blk_hdr__npar(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct info_blk_hdr *)hdr)->npar;
-	else /* INFO_EXT */
-		return ((struct x_info_blk_hdr *)hdr)->npar;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_info_blk_hdr *)hdr)->npar;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_info_blk_hdr *)hdr)->npar;
 }
 
 static inline __u8 info_blk_hdr__flags(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct info_blk_hdr *)hdr)->flags;
-	else /* INFO_EXT */
-		return ((struct x_info_blk_hdr *)hdr)->flags;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_info_blk_hdr *)hdr)->flags;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_info_blk_hdr *)hdr)->flags;
 }
 
 static inline __u16 info_blk_hdr__pcpus(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct info_blk_hdr *)hdr)->phys_cpus;
-	else /* INFO_EXT */
-		return ((struct x_info_blk_hdr *)hdr)->phys_cpus;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_info_blk_hdr *)hdr)->phys_cpus;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_info_blk_hdr *)hdr)->phys_cpus;
 }
 
 /* Partition header */
 
-struct part_hdr {
-	__u8 pn;
-	__u8 cpus;
-	char reserved[6];
-	char part_name[LPAR_NAME_LEN];
-} __attribute__ ((packed));
-
-struct x_part_hdr {
-	__u8  pn;
-	__u8  cpus;
-	__u8  rcpus;
-	__u8  pflag;
-	__u32 mlu;
-	char  part_name[LPAR_NAME_LEN];
-	char  lpc_name[8];
-	char  os_name[8];
-	__u64 online_cs;
-	__u64 online_es;
-	__u8  upid;
-	char  reserved1[3];
-	__u32 group_mlu;
-	char  group_name[8];
-	char  reserved2[32];
-} __attribute__ ((packed));
-
 static inline int part_hdr__size(enum diag204_format type)
 {
-	if (type == INFO_SIMPLE)
-		return sizeof(struct part_hdr);
-	else /* INFO_EXT */
-		return sizeof(struct x_part_hdr);
+	if (type == DIAG204_INFO_SIMPLE)
+		return sizeof(struct diag204_part_hdr);
+	else /* DIAG204_INFO_EXT */
+		return sizeof(struct diag204_x_part_hdr);
 }
 
 static inline __u8 part_hdr__rcpus(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct part_hdr *)hdr)->cpus;
-	else /* INFO_EXT */
-		return ((struct x_part_hdr *)hdr)->rcpus;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_part_hdr *)hdr)->cpus;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_part_hdr *)hdr)->rcpus;
 }
 
 static inline void part_hdr__part_name(enum diag204_format type, void *hdr,
 				       char *name)
 {
-	if (type == INFO_SIMPLE)
-		memcpy(name, ((struct part_hdr *)hdr)->part_name,
-		       LPAR_NAME_LEN);
-	else /* INFO_EXT */
-		memcpy(name, ((struct x_part_hdr *)hdr)->part_name,
-		       LPAR_NAME_LEN);
-	EBCASC(name, LPAR_NAME_LEN);
-	name[LPAR_NAME_LEN] = 0;
+	if (type == DIAG204_INFO_SIMPLE)
+		memcpy(name, ((struct diag204_part_hdr *)hdr)->part_name,
+		       DIAG204_LPAR_NAME_LEN);
+	else /* DIAG204_INFO_EXT */
+		memcpy(name, ((struct diag204_x_part_hdr *)hdr)->part_name,
+		       DIAG204_LPAR_NAME_LEN);
+	EBCASC(name, DIAG204_LPAR_NAME_LEN);
+	name[DIAG204_LPAR_NAME_LEN] = 0;
 	strim(name);
 }
 
-struct cpu_info {
-	__u16 cpu_addr;
-	char  reserved1[2];
-	__u8  ctidx;
-	__u8  cflag;
-	__u16 weight;
-	__u64 acc_time;
-	__u64 lp_time;
-} __attribute__ ((packed));
-
-struct x_cpu_info {
-	__u16 cpu_addr;
-	char  reserved1[2];
-	__u8  ctidx;
-	__u8  cflag;
-	__u16 weight;
-	__u64 acc_time;
-	__u64 lp_time;
-	__u16 min_weight;
-	__u16 cur_weight;
-	__u16 max_weight;
-	char  reseved2[2];
-	__u64 online_time;
-	__u64 wait_time;
-	__u32 pma_weight;
-	__u32 polar_weight;
-	char  reserved3[40];
-} __attribute__ ((packed));
-
 /* CPU info block */
 
 static inline int cpu_info__size(enum diag204_format type)
 {
-	if (type == INFO_SIMPLE)
-		return sizeof(struct cpu_info);
-	else /* INFO_EXT */
-		return sizeof(struct x_cpu_info);
+	if (type == DIAG204_INFO_SIMPLE)
+		return sizeof(struct diag204_cpu_info);
+	else /* DIAG204_INFO_EXT */
+		return sizeof(struct diag204_x_cpu_info);
 }
 
 static inline __u8 cpu_info__ctidx(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct cpu_info *)hdr)->ctidx;
-	else /* INFO_EXT */
-		return ((struct x_cpu_info *)hdr)->ctidx;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_cpu_info *)hdr)->ctidx;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_cpu_info *)hdr)->ctidx;
 }
 
 static inline __u16 cpu_info__cpu_addr(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct cpu_info *)hdr)->cpu_addr;
-	else /* INFO_EXT */
-		return ((struct x_cpu_info *)hdr)->cpu_addr;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_cpu_info *)hdr)->cpu_addr;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_cpu_info *)hdr)->cpu_addr;
 }
 
 static inline __u64 cpu_info__acc_time(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct cpu_info *)hdr)->acc_time;
-	else /* INFO_EXT */
-		return ((struct x_cpu_info *)hdr)->acc_time;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_cpu_info *)hdr)->acc_time;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_cpu_info *)hdr)->acc_time;
 }
 
 static inline __u64 cpu_info__lp_time(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct cpu_info *)hdr)->lp_time;
-	else /* INFO_EXT */
-		return ((struct x_cpu_info *)hdr)->lp_time;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_cpu_info *)hdr)->lp_time;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_cpu_info *)hdr)->lp_time;
 }
 
 static inline __u64 cpu_info__online_time(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
+	if (type == DIAG204_INFO_SIMPLE)
 		return 0;	/* online_time not available in simple info */
-	else /* INFO_EXT */
-		return ((struct x_cpu_info *)hdr)->online_time;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_cpu_info *)hdr)->online_time;
 }
 
 /* Physical header */
 
-struct phys_hdr {
-	char reserved1[1];
-	__u8 cpus;
-	char reserved2[6];
-	char mgm_name[8];
-} __attribute__ ((packed));
-
-struct x_phys_hdr {
-	char reserved1[1];
-	__u8 cpus;
-	char reserved2[6];
-	char mgm_name[8];
-	char reserved3[80];
-} __attribute__ ((packed));
-
 static inline int phys_hdr__size(enum diag204_format type)
 {
-	if (type == INFO_SIMPLE)
-		return sizeof(struct phys_hdr);
-	else /* INFO_EXT */
-		return sizeof(struct x_phys_hdr);
+	if (type == DIAG204_INFO_SIMPLE)
+		return sizeof(struct diag204_phys_hdr);
+	else /* DIAG204_INFO_EXT */
+		return sizeof(struct diag204_x_phys_hdr);
 }
 
 static inline __u8 phys_hdr__cpus(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct phys_hdr *)hdr)->cpus;
-	else /* INFO_EXT */
-		return ((struct x_phys_hdr *)hdr)->cpus;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_phys_hdr *)hdr)->cpus;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_phys_hdr *)hdr)->cpus;
 }
 
 /* Physical CPU info block */
 
-struct phys_cpu {
-	__u16 cpu_addr;
-	char  reserved1[2];
-	__u8  ctidx;
-	char  reserved2[3];
-	__u64 mgm_time;
-	char  reserved3[8];
-} __attribute__ ((packed));
-
-struct x_phys_cpu {
-	__u16 cpu_addr;
-	char  reserved1[2];
-	__u8  ctidx;
-	char  reserved2[3];
-	__u64 mgm_time;
-	char  reserved3[80];
-} __attribute__ ((packed));
-
 static inline int phys_cpu__size(enum diag204_format type)
 {
-	if (type == INFO_SIMPLE)
-		return sizeof(struct phys_cpu);
-	else /* INFO_EXT */
-		return sizeof(struct x_phys_cpu);
+	if (type == DIAG204_INFO_SIMPLE)
+		return sizeof(struct diag204_phys_cpu);
+	else /* DIAG204_INFO_EXT */
+		return sizeof(struct diag204_x_phys_cpu);
 }
 
 static inline __u16 phys_cpu__cpu_addr(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct phys_cpu *)hdr)->cpu_addr;
-	else /* INFO_EXT */
-		return ((struct x_phys_cpu *)hdr)->cpu_addr;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_phys_cpu *)hdr)->cpu_addr;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_phys_cpu *)hdr)->cpu_addr;
 }
 
 static inline __u64 phys_cpu__mgm_time(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct phys_cpu *)hdr)->mgm_time;
-	else /* INFO_EXT */
-		return ((struct x_phys_cpu *)hdr)->mgm_time;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_phys_cpu *)hdr)->mgm_time;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_phys_cpu *)hdr)->mgm_time;
 }
 
 static inline __u64 phys_cpu__ctidx(enum diag204_format type, void *hdr)
 {
-	if (type == INFO_SIMPLE)
-		return ((struct phys_cpu *)hdr)->ctidx;
-	else /* INFO_EXT */
-		return ((struct x_phys_cpu *)hdr)->ctidx;
+	if (type == DIAG204_INFO_SIMPLE)
+		return ((struct diag204_phys_cpu *)hdr)->ctidx;
+	else /* DIAG204_INFO_EXT */
+		return ((struct diag204_x_phys_cpu *)hdr)->ctidx;
 }
 
 /* Diagnose 204 functions */
-
-static inline int __diag204(unsigned long *subcode, unsigned long size, void *addr)
-{
-	register unsigned long _subcode asm("0") = *subcode;
-	register unsigned long _size asm("1") = size;
-
-	asm volatile(
-		"	diag	%2,%0,0x204\n"
-		"0:	nopr	%%r7\n"
-		EX_TABLE(0b,0b)
-		: "+d" (_subcode), "+d" (_size) : "d" (addr) : "memory");
-	*subcode = _subcode;
-	return _size;
-}
-
-static int diag204(unsigned long subcode, unsigned long size, void *addr)
-{
-	diag_stat_inc(DIAG_STAT_X204);
-	size = __diag204(&subcode, size, addr);
-	if (subcode)
-		return -1;
-	return size;
-}
-
 /*
  * For the old diag subcode 4 with simple data format we have to use real
  * memory. If we use subcode 6 or 7 with extended data format, we can (and
@@ -411,12 +261,12 @@ static void *diag204_get_buffer(enum diag204_format fmt, int *pages)
 		*pages = diag204_buf_pages;
 		return diag204_buf;
 	}
-	if (fmt == INFO_SIMPLE) {
+	if (fmt == DIAG204_INFO_SIMPLE) {
 		*pages = 1;
 		return diag204_alloc_rbuf();
-	} else {/* INFO_EXT */
-		*pages = diag204((unsigned long)SUBC_RSI |
-				 (unsigned long)INFO_EXT, 0, NULL);
+	} else {/* DIAG204_INFO_EXT */
+		*pages = diag204((unsigned long)DIAG204_SUBC_RSI |
+				 (unsigned long)DIAG204_INFO_EXT, 0, NULL);
 		if (*pages <= 0)
 			return ERR_PTR(-ENOSYS);
 		else
@@ -443,18 +293,18 @@ static int diag204_probe(void)
 	void *buf;
 	int pages, rc;
 
-	buf = diag204_get_buffer(INFO_EXT, &pages);
+	buf = diag204_get_buffer(DIAG204_INFO_EXT, &pages);
 	if (!IS_ERR(buf)) {
-		if (diag204((unsigned long)SUBC_STIB7 |
-			    (unsigned long)INFO_EXT, pages, buf) >= 0) {
-			diag204_store_sc = SUBC_STIB7;
-			diag204_info_type = INFO_EXT;
+		if (diag204((unsigned long)DIAG204_SUBC_STIB7 |
+			    (unsigned long)DIAG204_INFO_EXT, pages, buf) >= 0) {
+			diag204_store_sc = DIAG204_SUBC_STIB7;
+			diag204_info_type = DIAG204_INFO_EXT;
 			goto out;
 		}
-		if (diag204((unsigned long)SUBC_STIB6 |
-			    (unsigned long)INFO_EXT, pages, buf) >= 0) {
-			diag204_store_sc = SUBC_STIB6;
-			diag204_info_type = INFO_EXT;
+		if (diag204((unsigned long)DIAG204_SUBC_STIB6 |
+			    (unsigned long)DIAG204_INFO_EXT, pages, buf) >= 0) {
+			diag204_store_sc = DIAG204_SUBC_STIB6;
+			diag204_info_type = DIAG204_INFO_EXT;
 			goto out;
 		}
 		diag204_free_buffer();
@@ -462,15 +312,15 @@ static int diag204_probe(void)
 
 	/* subcodes 6 and 7 failed, now try subcode 4 */
 
-	buf = diag204_get_buffer(INFO_SIMPLE, &pages);
+	buf = diag204_get_buffer(DIAG204_INFO_SIMPLE, &pages);
 	if (IS_ERR(buf)) {
 		rc = PTR_ERR(buf);
 		goto fail_alloc;
 	}
-	if (diag204((unsigned long)SUBC_STIB4 |
-		    (unsigned long)INFO_SIMPLE, pages, buf) >= 0) {
-		diag204_store_sc = SUBC_STIB4;
-		diag204_info_type = INFO_SIMPLE;
+	if (diag204((unsigned long)DIAG204_SUBC_STIB4 |
+		    (unsigned long)DIAG204_INFO_SIMPLE, pages, buf) >= 0) {
+		diag204_store_sc = DIAG204_SUBC_STIB4;
+		diag204_info_type = DIAG204_INFO_SIMPLE;
 		goto out;
 	} else {
 		rc = -ENOSYS;
@@ -510,20 +360,6 @@ out:
 
 /* Diagnose 224 functions */
 
-static int diag224(void *ptr)
-{
-	int rc = -EOPNOTSUPP;
-
-	diag_stat_inc(DIAG_STAT_X224);
-	asm volatile(
-		"	diag	%1,%2,0x224\n"
-		"0:	lhi	%0,0x0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (rc) :"d" (0), "d" (ptr) : "memory");
-	return rc;
-}
-
 static int diag224_get_name_table(void)
 {
 	/* memory must be below 2GB */
@@ -545,9 +381,9 @@ static void diag224_delete_name_table(void)
 
 static int diag224_idx2name(int index, char *name)
 {
-	memcpy(name, diag224_cpu_names + ((index + 1) * CPU_NAME_LEN),
-		CPU_NAME_LEN);
-	name[CPU_NAME_LEN] = 0;
+	memcpy(name, diag224_cpu_names + ((index + 1) * DIAG204_CPU_NAME_LEN),
+	       DIAG204_CPU_NAME_LEN);
+	name[DIAG204_CPU_NAME_LEN] = 0;
 	strim(name);
 	return 0;
 }
@@ -603,7 +439,7 @@ __init int hypfs_diag_init(void)
 		pr_err("The hardware system does not support hypfs\n");
 		return -ENODATA;
 	}
-	if (diag204_info_type == INFO_EXT) {
+	if (diag204_info_type == DIAG204_INFO_EXT) {
 		rc = hypfs_dbfs_create_file(&dbfs_file_d204);
 		if (rc)
 			return rc;
@@ -651,7 +487,7 @@ static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info)
 			      cpu_info__lp_time(diag204_info_type, cpu_info));
 	if (IS_ERR(rc))
 		return PTR_ERR(rc);
-	if (diag204_info_type == INFO_EXT) {
+	if (diag204_info_type == DIAG204_INFO_EXT) {
 		rc = hypfs_create_u64(cpu_dir, "onlinetime",
 				      cpu_info__online_time(diag204_info_type,
 							    cpu_info));
@@ -667,12 +503,12 @@ static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr)
 {
 	struct dentry *cpus_dir;
 	struct dentry *lpar_dir;
-	char lpar_name[LPAR_NAME_LEN + 1];
+	char lpar_name[DIAG204_LPAR_NAME_LEN + 1];
 	void *cpu_info;
 	int i;
 
 	part_hdr__part_name(diag204_info_type, part_hdr, lpar_name);
-	lpar_name[LPAR_NAME_LEN] = 0;
+	lpar_name[DIAG204_LPAR_NAME_LEN] = 0;
 	lpar_dir = hypfs_mkdir(systems_dir, lpar_name);
 	if (IS_ERR(lpar_dir))
 		return lpar_dir;
@@ -755,7 +591,8 @@ int hypfs_diag_create_files(struct dentry *root)
 			goto err_out;
 		}
 	}
-	if (info_blk_hdr__flags(diag204_info_type, time_hdr) & LPAR_PHYS_FLG) {
+	if (info_blk_hdr__flags(diag204_info_type, time_hdr) &
+	    DIAG204_LPAR_PHYS_FLG) {
 		ptr = hypfs_create_phys_files(root, part_hdr);
 		if (IS_ERR(ptr)) {
 			rc = PTR_ERR(ptr);
diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h
index 1a82cf26ee11..d28621de8e0b 100644
--- a/arch/s390/include/asm/cpacf.h
+++ b/arch/s390/include/asm/cpacf.h
@@ -20,6 +20,9 @@
 #define CPACF_KMC		0xb92f		/* MSA	*/
 #define CPACF_KIMD		0xb93e		/* MSA	*/
 #define CPACF_KLMD		0xb93f		/* MSA	*/
+#define CPACF_PCKMO		0xb928		/* MSA3 */
+#define CPACF_KMF		0xb92a		/* MSA4 */
+#define CPACF_KMO		0xb92b		/* MSA4 */
 #define CPACF_PCC		0xb92c		/* MSA4 */
 #define CPACF_KMCTR		0xb92d		/* MSA4 */
 #define CPACF_PPNO		0xb93c		/* MSA5 */
@@ -136,6 +139,7 @@ static inline void __cpacf_query(unsigned int opcode, unsigned char *status)
 	register unsigned long r1 asm("1") = (unsigned long) status;
 
 	asm volatile(
+		"	spm 0\n" /* pckmo doesn't change the cc */
 		/* Parameter registers are ignored, but may not be 0 */
 		"0:	.insn	rrf,%[opc] << 16,2,2,2,0\n"
 		"	brc	1,0b\n"	/* handle partial completion */
@@ -157,6 +161,12 @@ static inline int cpacf_query(unsigned int opcode, unsigned int func)
 		if (!test_facility(17))	/* check for MSA */
 			return 0;
 		break;
+	case CPACF_PCKMO:
+		if (!test_facility(76))	/* check for MSA3 */
+			return 0;
+		break;
+	case CPACF_KMF:
+	case CPACF_KMO:
 	case CPACF_PCC:
 	case CPACF_KMCTR:
 		if (!test_facility(77))	/* check for MSA4 */
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index 86cae09e076a..8acf482162ed 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -78,4 +78,153 @@ struct diag210 {
 
 extern int diag210(struct diag210 *addr);
 
+/* bit is set in flags, when physical cpu info is included in diag 204 data */
+#define DIAG204_LPAR_PHYS_FLG 0x80
+#define DIAG204_LPAR_NAME_LEN 8		/* lpar name len in diag 204 data */
+#define DIAG204_CPU_NAME_LEN 16		/* type name len of cpus in diag224 name table */
+
+/* diag 204 subcodes */
+enum diag204_sc {
+	DIAG204_SUBC_STIB4 = 4,
+	DIAG204_SUBC_RSI = 5,
+	DIAG204_SUBC_STIB6 = 6,
+	DIAG204_SUBC_STIB7 = 7
+};
+
+/* The two available diag 204 data formats */
+enum diag204_format {
+	DIAG204_INFO_SIMPLE = 0,
+	DIAG204_INFO_EXT = 0x00010000
+};
+
+enum diag204_cpu_flags {
+	DIAG204_CPU_ONLINE = 0x20,
+	DIAG204_CPU_CAPPED = 0x40,
+};
+
+struct diag204_info_blk_hdr {
+	__u8  npar;
+	__u8  flags;
+	__u16 tslice;
+	__u16 phys_cpus;
+	__u16 this_part;
+	__u64 curtod;
+} __packed;
+
+struct diag204_x_info_blk_hdr {
+	__u8  npar;
+	__u8  flags;
+	__u16 tslice;
+	__u16 phys_cpus;
+	__u16 this_part;
+	__u64 curtod1;
+	__u64 curtod2;
+	char reserved[40];
+} __packed;
+
+struct diag204_part_hdr {
+	__u8 pn;
+	__u8 cpus;
+	char reserved[6];
+	char part_name[DIAG204_LPAR_NAME_LEN];
+} __packed;
+
+struct diag204_x_part_hdr {
+	__u8  pn;
+	__u8  cpus;
+	__u8  rcpus;
+	__u8  pflag;
+	__u32 mlu;
+	char  part_name[DIAG204_LPAR_NAME_LEN];
+	char  lpc_name[8];
+	char  os_name[8];
+	__u64 online_cs;
+	__u64 online_es;
+	__u8  upid;
+	__u8  reserved:3;
+	__u8  mtid:5;
+	char  reserved1[2];
+	__u32 group_mlu;
+	char  group_name[8];
+	char  hardware_group_name[8];
+	char  reserved2[24];
+} __packed;
+
+struct diag204_cpu_info {
+	__u16 cpu_addr;
+	char  reserved1[2];
+	__u8  ctidx;
+	__u8  cflag;
+	__u16 weight;
+	__u64 acc_time;
+	__u64 lp_time;
+} __packed;
+
+struct diag204_x_cpu_info {
+	__u16 cpu_addr;
+	char  reserved1[2];
+	__u8  ctidx;
+	__u8  cflag;
+	__u16 weight;
+	__u64 acc_time;
+	__u64 lp_time;
+	__u16 min_weight;
+	__u16 cur_weight;
+	__u16 max_weight;
+	char  reseved2[2];
+	__u64 online_time;
+	__u64 wait_time;
+	__u32 pma_weight;
+	__u32 polar_weight;
+	__u32 cpu_type_cap;
+	__u32 group_cpu_type_cap;
+	char  reserved3[32];
+} __packed;
+
+struct diag204_phys_hdr {
+	char reserved1[1];
+	__u8 cpus;
+	char reserved2[6];
+	char mgm_name[8];
+} __packed;
+
+struct diag204_x_phys_hdr {
+	char reserved1[1];
+	__u8 cpus;
+	char reserved2[6];
+	char mgm_name[8];
+	char reserved3[80];
+} __packed;
+
+struct diag204_phys_cpu {
+	__u16 cpu_addr;
+	char  reserved1[2];
+	__u8  ctidx;
+	char  reserved2[3];
+	__u64 mgm_time;
+	char  reserved3[8];
+} __packed;
+
+struct diag204_x_phys_cpu {
+	__u16 cpu_addr;
+	char  reserved1[2];
+	__u8  ctidx;
+	char  reserved2[1];
+	__u16 weight;
+	__u64 mgm_time;
+	char  reserved3[80];
+} __packed;
+
+struct diag204_x_part_block {
+	struct diag204_x_part_hdr hdr;
+	struct diag204_x_cpu_info cpus[];
+} __packed;
+
+struct diag204_x_phys_block {
+	struct diag204_x_phys_hdr hdr;
+	struct diag204_x_phys_cpu cpus[];
+} __packed;
+
+int diag204(unsigned long subcode, unsigned long size, void *addr);
+int diag224(void *ptr);
 #endif /* _ASM_S390_DIAG_H */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 563ab9f44874..1736c7d3c94c 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -225,6 +225,7 @@ do {								\
 #define MMAP_ALIGN_MASK	(is_compat_task() ? 0 : 0x7fUL)
 #define STACK_RND_MASK	MMAP_RND_MASK
 
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
 #define ARCH_DLINFO							    \
 do {									    \
 	if (vdso_enabled)						    \
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index d054c1b07a3c..741ddba0bf11 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -10,14 +10,25 @@
 
 /**
  * struct gmap_struct - guest address space
+ * @list: list head for the mm->context gmap list
  * @crst_list: list of all crst tables used in the guest address space
  * @mm: pointer to the parent mm_struct
  * @guest_to_host: radix tree with guest to host address translation
  * @host_to_guest: radix tree with pointer to segment table entries
  * @guest_table_lock: spinlock to protect all entries in the guest page table
+ * @ref_count: reference counter for the gmap structure
  * @table: pointer to the page directory
  * @asce: address space control element for gmap page table
  * @pfault_enabled: defines if pfaults are applicable for the guest
+ * @host_to_rmap: radix tree with gmap_rmap lists
+ * @children: list of shadow gmap structures
+ * @pt_list: list of all page tables used in the shadow guest address space
+ * @shadow_lock: spinlock to protect the shadow gmap list
+ * @parent: pointer to the parent gmap for shadow guest address spaces
+ * @orig_asce: ASCE for which the shadow page table has been created
+ * @edat_level: edat level to be used for the shadow translation
+ * @removed: flag to indicate if a shadow guest address space has been removed
+ * @initialized: flag to indicate if a shadow guest address space can be used
  */
 struct gmap {
 	struct list_head list;
@@ -26,26 +37,64 @@ struct gmap {
 	struct radix_tree_root guest_to_host;
 	struct radix_tree_root host_to_guest;
 	spinlock_t guest_table_lock;
+	atomic_t ref_count;
 	unsigned long *table;
 	unsigned long asce;
 	unsigned long asce_end;
 	void *private;
 	bool pfault_enabled;
+	/* Additional data for shadow guest address spaces */
+	struct radix_tree_root host_to_rmap;
+	struct list_head children;
+	struct list_head pt_list;
+	spinlock_t shadow_lock;
+	struct gmap *parent;
+	unsigned long orig_asce;
+	int edat_level;
+	bool removed;
+	bool initialized;
 };
 
 /**
+ * struct gmap_rmap - reverse mapping for shadow page table entries
+ * @next: pointer to next rmap in the list
+ * @raddr: virtual rmap address in the shadow guest address space
+ */
+struct gmap_rmap {
+	struct gmap_rmap *next;
+	unsigned long raddr;
+};
+
+#define gmap_for_each_rmap(pos, head) \
+	for (pos = (head); pos; pos = pos->next)
+
+#define gmap_for_each_rmap_safe(pos, n, head) \
+	for (pos = (head); n = pos ? pos->next : NULL, pos; pos = n)
+
+/**
  * struct gmap_notifier - notify function block for page invalidation
  * @notifier_call: address of callback function
  */
 struct gmap_notifier {
 	struct list_head list;
-	void (*notifier_call)(struct gmap *gmap, unsigned long gaddr);
+	struct rcu_head rcu;
+	void (*notifier_call)(struct gmap *gmap, unsigned long start,
+			      unsigned long end);
 };
 
-struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit);
-void gmap_free(struct gmap *gmap);
+static inline int gmap_is_shadow(struct gmap *gmap)
+{
+	return !!gmap->parent;
+}
+
+struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit);
+void gmap_remove(struct gmap *gmap);
+struct gmap *gmap_get(struct gmap *gmap);
+void gmap_put(struct gmap *gmap);
+
 void gmap_enable(struct gmap *gmap);
 void gmap_disable(struct gmap *gmap);
+struct gmap *gmap_get_enabled(void);
 int gmap_map_segment(struct gmap *gmap, unsigned long from,
 		     unsigned long to, unsigned long len);
 int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
@@ -57,8 +106,29 @@ void gmap_discard(struct gmap *, unsigned long from, unsigned long to);
 void __gmap_zap(struct gmap *, unsigned long gaddr);
 void gmap_unlink(struct mm_struct *, unsigned long *table, unsigned long vmaddr);
 
-void gmap_register_ipte_notifier(struct gmap_notifier *);
-void gmap_unregister_ipte_notifier(struct gmap_notifier *);
-int gmap_ipte_notify(struct gmap *, unsigned long start, unsigned long len);
+int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val);
+
+struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
+			 int edat_level);
+int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level);
+int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
+		    int fake);
+int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
+		    int fake);
+int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
+		    int fake);
+int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
+		    int fake);
+int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr,
+			   unsigned long *pgt, int *dat_protection, int *fake);
+int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte);
+
+void gmap_register_pte_notifier(struct gmap_notifier *);
+void gmap_unregister_pte_notifier(struct gmap_notifier *);
+void gmap_pte_notify(struct mm_struct *, unsigned long addr, pte_t *,
+		     unsigned long bits);
+
+int gmap_mprotect_notify(struct gmap *, unsigned long start,
+			 unsigned long len, int prot);
 
 #endif /* _ASM_S390_GMAP_H */
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index ac82e8eb936d..8e5daf7a76ce 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -43,6 +43,7 @@
 /* s390-specific vcpu->requests bit members */
 #define KVM_REQ_ENABLE_IBS         8
 #define KVM_REQ_DISABLE_IBS        9
+#define KVM_REQ_ICPT_OPEREXC       10
 
 #define SIGP_CTRL_C		0x80
 #define SIGP_CTRL_SCN_MASK	0x3f
@@ -145,7 +146,7 @@ struct kvm_s390_sie_block {
 	__u64	cputm;			/* 0x0028 */
 	__u64	ckc;			/* 0x0030 */
 	__u64	epoch;			/* 0x0038 */
-	__u8	reserved40[4];		/* 0x0040 */
+	__u32	svcc;			/* 0x0040 */
 #define LCTL_CR0	0x8000
 #define LCTL_CR6	0x0200
 #define LCTL_CR9	0x0040
@@ -154,6 +155,7 @@ struct kvm_s390_sie_block {
 #define LCTL_CR14	0x0002
 	__u16   lctl;			/* 0x0044 */
 	__s16	icpua;			/* 0x0046 */
+#define ICTL_OPEREXC	0x80000000
 #define ICTL_PINT	0x20000000
 #define ICTL_LPSW	0x00400000
 #define ICTL_STCTL	0x00040000
@@ -166,6 +168,9 @@ struct kvm_s390_sie_block {
 #define ICPT_INST	0x04
 #define ICPT_PROGI	0x08
 #define ICPT_INSTPROGI	0x0C
+#define ICPT_EXTINT	0x14
+#define ICPT_VALIDITY	0x20
+#define ICPT_STOP	0x28
 #define ICPT_OPEREXC	0x2C
 #define ICPT_PARTEXEC	0x38
 #define ICPT_IOINST	0x40
@@ -185,7 +190,9 @@ struct kvm_s390_sie_block {
 	__u32	scaol;			/* 0x0064 */
 	__u8	reserved68[4];		/* 0x0068 */
 	__u32	todpr;			/* 0x006c */
-	__u8	reserved70[32];		/* 0x0070 */
+	__u8	reserved70[16];		/* 0x0070 */
+	__u64	mso;			/* 0x0080 */
+	__u64	msl;			/* 0x0088 */
 	psw_t	gpsw;			/* 0x0090 */
 	__u64	gg14;			/* 0x00a0 */
 	__u64	gg15;			/* 0x00a8 */
@@ -223,7 +230,7 @@ struct kvm_s390_sie_block {
 	__u8	reserved1e6[2];		/* 0x01e6 */
 	__u64	itdba;			/* 0x01e8 */
 	__u64   riccbd;			/* 0x01f0 */
-	__u8    reserved1f8[8];		/* 0x01f8 */
+	__u64	gvrd;			/* 0x01f8 */
 } __attribute__((packed));
 
 struct kvm_s390_itdb {
@@ -256,6 +263,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_stctg;
 	u32 exit_program_interruption;
 	u32 exit_instr_and_program;
+	u32 exit_operation_exception;
 	u32 deliver_external_call;
 	u32 deliver_emergency_signal;
 	u32 deliver_service_signal;
@@ -278,7 +286,9 @@ struct kvm_vcpu_stat {
 	u32 instruction_stsi;
 	u32 instruction_stfl;
 	u32 instruction_tprot;
+	u32 instruction_sie;
 	u32 instruction_essa;
+	u32 instruction_sthyi;
 	u32 instruction_sigp_sense;
 	u32 instruction_sigp_sense_running;
 	u32 instruction_sigp_external_call;
@@ -541,12 +551,16 @@ struct kvm_guestdbg_info_arch {
 
 struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
+	/* if vsie is active, currently executed shadow sie control block */
+	struct kvm_s390_sie_block *vsie_block;
 	unsigned int      host_acrs[NUM_ACRS];
 	struct fpu	  host_fpregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct kvm_s390_pgm_info pgm;
 	struct gmap *gmap;
+	/* backup location for the currently enabled gmap when scheduled out */
+	struct gmap *enabled_gmap;
 	struct kvm_guestdbg_info_arch guestdbg;
 	unsigned long pfault_token;
 	unsigned long pfault_select;
@@ -631,6 +645,14 @@ struct sie_page2 {
 	u8 reserved900[0x1000 - 0x900];			/* 0x0900 */
 } __packed;
 
+struct kvm_s390_vsie {
+	struct mutex mutex;
+	struct radix_tree_root addr_to_page;
+	int page_count;
+	int next;
+	struct page *pages[KVM_MAX_VCPUS];
+};
+
 struct kvm_arch{
 	void *sca;
 	int use_esca;
@@ -646,15 +668,20 @@ struct kvm_arch{
 	int user_cpu_state_ctrl;
 	int user_sigp;
 	int user_stsi;
+	int user_instr0;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
 	wait_queue_head_t ipte_wq;
 	int ipte_lock_count;
 	struct mutex ipte_mutex;
+	struct ratelimit_state sthyi_limit;
 	spinlock_t start_stop_lock;
 	struct sie_page2 *sie_page2;
 	struct kvm_s390_cpu_model model;
 	struct kvm_s390_crypto crypto;
+	struct kvm_s390_vsie vsie;
 	u64 epoch;
+	/* subset of available cpu features enabled by user space */
+	DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
 };
 
 #define KVM_HVA_ERR_BAD		(-1UL)
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index 18226437a832..6d39329c894b 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -8,8 +8,9 @@ typedef struct {
 	cpumask_t cpu_attach_mask;
 	atomic_t flush_count;
 	unsigned int flush_mm;
-	spinlock_t list_lock;
+	spinlock_t pgtable_lock;
 	struct list_head pgtable_list;
+	spinlock_t gmap_lock;
 	struct list_head gmap_list;
 	unsigned long asce;
 	unsigned long asce_limit;
@@ -22,9 +23,11 @@ typedef struct {
 	unsigned int use_skey:1;
 } mm_context_t;
 
-#define INIT_MM_CONTEXT(name)						      \
-	.context.list_lock    = __SPIN_LOCK_UNLOCKED(name.context.list_lock), \
-	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list),    \
+#define INIT_MM_CONTEXT(name)						   \
+	.context.pgtable_lock =						   \
+			__SPIN_LOCK_UNLOCKED(name.context.pgtable_lock),   \
+	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list), \
+	.context.gmap_lock = __SPIN_LOCK_UNLOCKED(name.context.gmap_lock), \
 	.context.gmap_list = LIST_HEAD_INIT(name.context.gmap_list),
 
 static inline int tprot(unsigned long addr)
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index f77c638bf397..c6a088c91aee 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -15,8 +15,9 @@
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
-	spin_lock_init(&mm->context.list_lock);
+	spin_lock_init(&mm->context.pgtable_lock);
 	INIT_LIST_HEAD(&mm->context.pgtable_list);
+	spin_lock_init(&mm->context.gmap_lock);
 	INIT_LIST_HEAD(&mm->context.gmap_list);
 	cpumask_clear(&mm->context.cpu_attach_mask);
 	atomic_set(&mm->context.flush_count, 0);
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index b2146c4119b2..69b8a41fca84 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -111,13 +111,14 @@ static inline unsigned char page_get_storage_key(unsigned long addr)
 
 static inline int page_reset_referenced(unsigned long addr)
 {
-	unsigned int ipm;
+	int cc;
 
 	asm volatile(
 		"	rrbe	0,%1\n"
 		"	ipm	%0\n"
-		: "=d" (ipm) : "a" (addr) : "cc");
-	return !!(ipm & 0x20000000);
+		"	srl	%0,28\n"
+		: "=d" (cc) : "a" (addr) : "cc");
+	return cc;
 }
 
 /* Bits int the storage key */
@@ -148,6 +149,8 @@ static inline int devmem_is_allowed(unsigned long pfn)
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 #define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define pfn_to_virt(pfn)	__va((pfn) << PAGE_SHIFT)
+#define page_to_virt(page)	pfn_to_virt(page_to_pfn(page))
 
 #define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | \
 				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index da34cb6b1f3b..f4eb9843eed4 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -19,8 +19,10 @@ unsigned long *crst_table_alloc(struct mm_struct *);
 void crst_table_free(struct mm_struct *, unsigned long *);
 
 unsigned long *page_table_alloc(struct mm_struct *);
+struct page *page_table_alloc_pgste(struct mm_struct *mm);
 void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long);
+void page_table_free_pgste(struct page *page);
 extern int page_table_allocate_pgste;
 
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index ea1533e07271..72c7f60bfe83 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -242,8 +242,8 @@ static inline int is_module_addr(void *addr)
  * swap				.11..ttttt.0
  * prot-none, clean, old	.11.xx0000.1
  * prot-none, clean, young	.11.xx0001.1
- * prot-none, dirty, old	.10.xx0010.1
- * prot-none, dirty, young	.10.xx0011.1
+ * prot-none, dirty, old	.11.xx0010.1
+ * prot-none, dirty, young	.11.xx0011.1
  * read-only, clean, old	.11.xx0100.1
  * read-only, clean, young	.01.xx0101.1
  * read-only, dirty, old	.11.xx0110.1
@@ -277,6 +277,7 @@ static inline int is_module_addr(void *addr)
 /* Bits in the region table entry */
 #define _REGION_ENTRY_ORIGIN	~0xfffUL/* region/segment table origin	    */
 #define _REGION_ENTRY_PROTECT	0x200	/* region protection bit	    */
+#define _REGION_ENTRY_OFFSET	0xc0	/* region table offset		    */
 #define _REGION_ENTRY_INVALID	0x20	/* invalid region table entry	    */
 #define _REGION_ENTRY_TYPE_MASK	0x0c	/* region/segment table type mask   */
 #define _REGION_ENTRY_TYPE_R1	0x0c	/* region first table type	    */
@@ -323,8 +324,8 @@ static inline int is_module_addr(void *addr)
 #define _SEGMENT_ENTRY_DIRTY	0x2000	/* SW segment dirty bit */
 #define _SEGMENT_ENTRY_YOUNG	0x1000	/* SW segment young bit */
 #define _SEGMENT_ENTRY_LARGE	0x0400	/* STE-format control, large page */
-#define _SEGMENT_ENTRY_READ	0x0002	/* SW segment read bit */
-#define _SEGMENT_ENTRY_WRITE	0x0001	/* SW segment write bit */
+#define _SEGMENT_ENTRY_WRITE	0x0002	/* SW segment write bit */
+#define _SEGMENT_ENTRY_READ	0x0001	/* SW segment read bit */
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define _SEGMENT_ENTRY_SOFT_DIRTY 0x4000 /* SW segment soft dirty bit */
@@ -335,15 +336,15 @@ static inline int is_module_addr(void *addr)
 /*
  * Segment table and region3 table entry encoding
  * (R = read-only, I = invalid, y = young bit):
- *				dy..R...I...rw
+ *				dy..R...I...wr
  * prot-none, clean, old	00..1...1...00
  * prot-none, clean, young	01..1...1...00
  * prot-none, dirty, old	10..1...1...00
  * prot-none, dirty, young	11..1...1...00
- * read-only, clean, old	00..1...1...10
- * read-only, clean, young	01..1...0...10
- * read-only, dirty, old	10..1...1...10
- * read-only, dirty, young	11..1...0...10
+ * read-only, clean, old	00..1...1...01
+ * read-only, clean, young	01..1...0...01
+ * read-only, dirty, old	10..1...1...01
+ * read-only, dirty, young	11..1...0...01
  * read-write, clean, old	00..1...1...11
  * read-write, clean, young	01..1...0...11
  * read-write, dirty, old	10..0...1...11
@@ -364,6 +365,7 @@ static inline int is_module_addr(void *addr)
 #define PGSTE_GC_BIT	0x0002000000000000UL
 #define PGSTE_UC_BIT	0x0000800000000000UL	/* user dirty (migration) */
 #define PGSTE_IN_BIT	0x0000400000000000UL	/* IPTE notify bit */
+#define PGSTE_VSIE_BIT	0x0000200000000000UL	/* ref'd in a shadow table */
 
 /* Guest Page State used for virtualization */
 #define _PGSTE_GPS_ZERO		0x0000000080000000UL
@@ -382,7 +384,7 @@ static inline int is_module_addr(void *addr)
 /*
  * Page protection definitions.
  */
-#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_INVALID)
+#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_INVALID | _PAGE_PROTECT)
 #define PAGE_READ	__pgprot(_PAGE_PRESENT | _PAGE_READ | \
 				 _PAGE_INVALID | _PAGE_PROTECT)
 #define PAGE_WRITE	__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
@@ -1002,15 +1004,26 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 void ptep_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry);
 void ptep_set_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
-void ptep_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+void ptep_notify(struct mm_struct *mm, unsigned long addr,
+		 pte_t *ptep, unsigned long bits);
+int ptep_force_prot(struct mm_struct *mm, unsigned long gaddr,
+		    pte_t *ptep, int prot, unsigned long bit);
 void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep , int reset);
 void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr,
+		    pte_t *sptep, pte_t *tptep, pte_t pte);
+void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep);
 
 bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long address);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char key, bool nq);
-unsigned char get_guest_storage_key(struct mm_struct *mm, unsigned long addr);
+int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
+			       unsigned char key, unsigned char *oldkey,
+			       bool nq, bool mr, bool mc);
+int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr);
+int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
+			  unsigned char *key);
 
 /*
  * Certain architectures need to do special things when PTEs
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 09529202ea77..03323175de30 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -112,6 +112,8 @@ struct thread_struct {
         unsigned long ksp;              /* kernel stack pointer             */
 	mm_segment_t mm_segment;
 	unsigned long gmap_addr;	/* address of last gmap fault. */
+	unsigned int gmap_write_flag;	/* gmap fault write indication */
+	unsigned int gmap_int_code;	/* int code of last gmap fault */
 	unsigned int gmap_pfault;	/* signal of a pending guest pfault */
 	struct per_regs per_user;	/* User specified PER registers */
 	struct per_event per_event;	/* Cause of the last PER trap */
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index e4f6f73afe2f..2ad9c204b1a2 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -32,12 +32,19 @@ struct sclp_core_entry {
 	u8 reserved0;
 	u8 : 4;
 	u8 sief2 : 1;
-	u8 : 3;
-	u8 : 3;
+	u8 skey : 1;
+	u8 : 2;
+	u8 : 2;
+	u8 gpere : 1;
 	u8 siif : 1;
 	u8 sigpif : 1;
 	u8 : 3;
-	u8 reserved2[10];
+	u8 reserved2[3];
+	u8 : 2;
+	u8 ib : 1;
+	u8 cei : 1;
+	u8 : 4;
+	u8 reserved3[6];
 	u8 type;
 	u8 reserved1;
 } __attribute__((packed));
@@ -59,6 +66,15 @@ struct sclp_info {
 	unsigned char has_hvs : 1;
 	unsigned char has_esca : 1;
 	unsigned char has_sief2 : 1;
+	unsigned char has_64bscao : 1;
+	unsigned char has_gpere : 1;
+	unsigned char has_cmma : 1;
+	unsigned char has_gsls : 1;
+	unsigned char has_ib : 1;
+	unsigned char has_cei : 1;
+	unsigned char has_pfmfi : 1;
+	unsigned char has_ibs : 1;
+	unsigned char has_skey : 1;
 	unsigned int ibc;
 	unsigned int mtid;
 	unsigned int mtid_cp;
@@ -101,5 +117,6 @@ int memcpy_hsa_kernel(void *dest, unsigned long src, size_t count);
 int memcpy_hsa_user(void __user *dest, unsigned long src, size_t count);
 void sclp_early_detect(void);
 void _sclp_print_early(const char *);
+void sclp_ocf_cpc_name_copy(char *dst);
 
 #endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/include/uapi/asm/auxvec.h b/arch/s390/include/uapi/asm/auxvec.h
index a1f153e89133..c53e08442255 100644
--- a/arch/s390/include/uapi/asm/auxvec.h
+++ b/arch/s390/include/uapi/asm/auxvec.h
@@ -3,4 +3,6 @@
 
 #define AT_SYSINFO_EHDR		33
 
+#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */
+
 #endif
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 3b8e99ef9d58..a2ffec4139ad 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -93,6 +93,47 @@ struct kvm_s390_vm_cpu_machine {
 	__u64 fac_list[256];
 };
 
+#define KVM_S390_VM_CPU_PROCESSOR_FEAT	2
+#define KVM_S390_VM_CPU_MACHINE_FEAT	3
+
+#define KVM_S390_VM_CPU_FEAT_NR_BITS	1024
+#define KVM_S390_VM_CPU_FEAT_ESOP	0
+#define KVM_S390_VM_CPU_FEAT_SIEF2	1
+#define KVM_S390_VM_CPU_FEAT_64BSCAO	2
+#define KVM_S390_VM_CPU_FEAT_SIIF	3
+#define KVM_S390_VM_CPU_FEAT_GPERE	4
+#define KVM_S390_VM_CPU_FEAT_GSLS	5
+#define KVM_S390_VM_CPU_FEAT_IB		6
+#define KVM_S390_VM_CPU_FEAT_CEI	7
+#define KVM_S390_VM_CPU_FEAT_IBS	8
+#define KVM_S390_VM_CPU_FEAT_SKEY	9
+#define KVM_S390_VM_CPU_FEAT_CMMA	10
+#define KVM_S390_VM_CPU_FEAT_PFMFI	11
+#define KVM_S390_VM_CPU_FEAT_SIGPIF	12
+struct kvm_s390_vm_cpu_feat {
+	__u64 feat[16];
+};
+
+#define KVM_S390_VM_CPU_PROCESSOR_SUBFUNC	4
+#define KVM_S390_VM_CPU_MACHINE_SUBFUNC		5
+/* for "test bit" instructions MSB 0 bit ordering, for "query" raw blocks */
+struct kvm_s390_vm_cpu_subfunc {
+	__u8 plo[32];		/* always */
+	__u8 ptff[16];		/* with TOD-clock steering */
+	__u8 kmac[16];		/* with MSA */
+	__u8 kmc[16];		/* with MSA */
+	__u8 km[16];		/* with MSA */
+	__u8 kimd[16];		/* with MSA */
+	__u8 klmd[16];		/* with MSA */
+	__u8 pckmo[16];		/* with MSA3 */
+	__u8 kmctr[16];		/* with MSA4 */
+	__u8 kmf[16];		/* with MSA4 */
+	__u8 kmo[16];		/* with MSA4 */
+	__u8 pcc[16];		/* with MSA4 */
+	__u8 ppno[16];		/* with MSA5 */
+	__u8 reserved[1824];
+};
+
 /* kvm attributes for crypto */
 #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW	0
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h
index 8fb5d4a6dd25..3ac634368939 100644
--- a/arch/s390/include/uapi/asm/sie.h
+++ b/arch/s390/include/uapi/asm/sie.h
@@ -140,6 +140,7 @@
 	exit_code_ipa0(0xB2, 0x4c, "TAR"),	\
 	exit_code_ipa0(0xB2, 0x50, "CSP"),	\
 	exit_code_ipa0(0xB2, 0x54, "MVPG"),	\
+	exit_code_ipa0(0xB2, 0x56, "STHYI"),	\
 	exit_code_ipa0(0xB2, 0x58, "BSG"),	\
 	exit_code_ipa0(0xB2, 0x5a, "BSA"),	\
 	exit_code_ipa0(0xB2, 0x5f, "CHSC"),	\
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index f37be37edd3a..3234817c7d47 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -4,6 +4,7 @@
 
 KCOV_INSTRUMENT_early.o := n
 KCOV_INSTRUMENT_sclp.o := n
+KCOV_INSTRUMENT_als.o := n
 
 ifdef CONFIG_FUNCTION_TRACER
 # Don't trace early setup code and tracing code
@@ -32,21 +33,25 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 CFLAGS_sysinfo.o += -w
 
 #
-# Use -march=z900 for sclp.c to be able to print an error message if
-# the kernel is started on a machine which is too old
+# Use -march=z900 for sclp.c and als.c to be able to print an error
+# message if the kernel is started on a machine which is too old
 #
 CFLAGS_REMOVE_sclp.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_als.o = $(CC_FLAGS_FTRACE)
 ifneq ($(CC_FLAGS_MARCH),-march=z900)
 CFLAGS_REMOVE_sclp.o	+= $(CC_FLAGS_MARCH)
 CFLAGS_sclp.o		+= -march=z900
+CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_MARCH)
+CFLAGS_als.o		+= -march=z900
 AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
 AFLAGS_head.o		+= -march=z900
 endif
 GCOV_PROFILE_sclp.o := n
+GCOV_PROFILE_als.o := n
 
 obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
-obj-y	+= debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o
+obj-y	+= debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o als.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o
 obj-y	+= entry.o reipl.o relocate_kernel.o
diff --git a/arch/s390/kernel/als.c b/arch/s390/kernel/als.c
new file mode 100644
index 000000000000..a16e9d1bf9e3
--- /dev/null
+++ b/arch/s390/kernel/als.c
@@ -0,0 +1,124 @@
+/*
+ *    Copyright IBM Corp. 2016
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <asm/processor.h>
+#include <asm/facility.h>
+#include <asm/lowcore.h>
+#include <asm/sclp.h>
+#include "entry.h"
+
+/*
+ * The code within this file will be called very early. It may _not_
+ * access anything within the bss section, since that is not cleared
+ * yet and may contain data (e.g. initrd) that must be saved by other
+ * code.
+ * For temporary objects the stack (16k) should be used.
+ */
+
+static unsigned long als[] __initdata = { FACILITIES_ALS };
+
+static void __init u16_to_hex(char *str, u16 val)
+{
+	int i, num;
+
+	for (i = 1; i <= 4; i++) {
+		num = (val >> (16 - 4 * i)) & 0xf;
+		if (num >= 10)
+			num += 7;
+		*str++ = '0' + num;
+	}
+	*str = '\0';
+}
+
+static void __init print_machine_type(void)
+{
+	static char mach_str[80] __initdata = "Detected machine-type number: ";
+	char type_str[5];
+	struct cpuid id;
+
+	get_cpu_id(&id);
+	u16_to_hex(type_str, id.machine);
+	strcat(mach_str, type_str);
+	_sclp_print_early(mach_str);
+}
+
+static void __init u16_to_decimal(char *str, u16 val)
+{
+	int div = 1;
+
+	while (div * 10 <= val)
+		div *= 10;
+	while (div) {
+		*str++ = '0' + val / div;
+		val %= div;
+		div /= 10;
+	}
+	*str = '\0';
+}
+
+static void __init print_missing_facilities(void)
+{
+	static char als_str[80] __initdata = "Missing facilities: ";
+	unsigned long val;
+	char val_str[6];
+	int i, j, first;
+
+	first = 1;
+	for (i = 0; i < ARRAY_SIZE(als); i++) {
+		val = ~S390_lowcore.stfle_fac_list[i] & als[i];
+		for (j = 0; j < BITS_PER_LONG; j++) {
+			if (!(val & (1UL << (BITS_PER_LONG - 1 - j))))
+				continue;
+			if (!first)
+				strcat(als_str, ",");
+			/*
+			 * Make sure we stay within one line. Consider that
+			 * each facility bit adds up to five characters and
+			 * z/VM adds a four character prefix.
+			 */
+			if (strlen(als_str) > 70) {
+				_sclp_print_early(als_str);
+				*als_str = '\0';
+			}
+			u16_to_decimal(val_str, i * BITS_PER_LONG + j);
+			strcat(als_str, val_str);
+			first = 0;
+		}
+	}
+	_sclp_print_early(als_str);
+	_sclp_print_early("See Principles of Operations for facility bits");
+}
+
+static void __init facility_mismatch(void)
+{
+	_sclp_print_early("The Linux kernel requires more recent processor hardware");
+	print_machine_type();
+	print_missing_facilities();
+	disabled_wait(0x8badcccc);
+}
+
+void __init verify_facilities(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(S390_lowcore.stfle_fac_list); i++)
+		S390_lowcore.stfle_fac_list[i] = 0;
+	asm volatile(
+		"	stfl	0(0)\n"
+		: "=m" (S390_lowcore.stfl_fac_list));
+	S390_lowcore.stfle_fac_list[0] = (u64)S390_lowcore.stfl_fac_list << 32;
+	if (S390_lowcore.stfl_fac_list & 0x01000000) {
+		register unsigned long reg0 asm("0") = ARRAY_SIZE(als) - 1;
+
+		asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
+			     : "+d" (reg0)
+			     : "a" (&S390_lowcore.stfle_fac_list)
+			     : "memory", "cc");
+	}
+	for (i = 0; i < ARRAY_SIZE(als); i++) {
+		if ((S390_lowcore.stfle_fac_list[i] & als[i]) != als[i])
+			facility_mismatch();
+	}
+}
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index 48b37b8357e6..a97354c8c667 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -162,6 +162,30 @@ int diag14(unsigned long rx, unsigned long ry1, unsigned long subcode)
 }
 EXPORT_SYMBOL(diag14);
 
+static inline int __diag204(unsigned long *subcode, unsigned long size, void *addr)
+{
+	register unsigned long _subcode asm("0") = *subcode;
+	register unsigned long _size asm("1") = size;
+
+	asm volatile(
+		"	diag	%2,%0,0x204\n"
+		"0:	nopr	%%r7\n"
+		EX_TABLE(0b,0b)
+		: "+d" (_subcode), "+d" (_size) : "d" (addr) : "memory");
+	*subcode = _subcode;
+	return _size;
+}
+
+int diag204(unsigned long subcode, unsigned long size, void *addr)
+{
+	diag_stat_inc(DIAG_STAT_X204);
+	size = __diag204(&subcode, size, addr);
+	if (subcode)
+		return -1;
+	return size;
+}
+EXPORT_SYMBOL(diag204);
+
 /*
  * Diagnose 210: Get information about a virtual device
  */
@@ -196,3 +220,18 @@ int diag210(struct diag210 *addr)
 	return ccode;
 }
 EXPORT_SYMBOL(diag210);
+
+int diag224(void *ptr)
+{
+	int rc = -EOPNOTSUPP;
+
+	diag_stat_inc(DIAG_STAT_X224);
+	asm volatile(
+		"	diag	%1,%2,0x224\n"
+		"0:	lhi	%0,0x0\n"
+		"1:\n"
+		EX_TABLE(0b,1b)
+		: "+d" (rc) :"d" (0), "d" (ptr) : "memory");
+	return rc;
+}
+EXPORT_SYMBOL(diag224);
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index bedd2f55d860..e79f030dd276 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -79,4 +79,6 @@ long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t);
 
 DECLARE_PER_CPU(u64, mt_cycles[8]);
 
+void verify_facilities(void);
+
 #endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index fcaefb041364..56e4d8234ef2 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -306,49 +306,14 @@ ENTRY(startup_kdump)
 	stck	__LC_LAST_UPDATE_CLOCK
 	spt	6f-.LPG0(%r13)
 	mvc	__LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
-	stfl	0(%r0)			# store facilities @ __LC_STFL_FAC_LIST
-	mvc	__LC_STFLE_FAC_LIST(4),__LC_STFL_FAC_LIST
-	tm	__LC_STFLE_FAC_LIST,0x01	# stfle available ?
-	jz	0f
-	lghi	%r0,FACILITIES_ALS_DWORDS-1
-	.insn	s,0xb2b00000,__LC_STFLE_FAC_LIST # store facility list extended
-	# verify if all required facilities are supported by the machine
-0:	la	%r1,__LC_STFLE_FAC_LIST
-	la	%r2,3f+8-.LPG0(%r13)
-	lhi	%r3,FACILITIES_ALS_DWORDS
-1:	lg	%r0,0(%r1)
-	ng	%r0,0(%r2)
-	clg	%r0,0(%r2)
-	jne	2f
-	la	%r1,8(%r1)
-	la	%r2,8(%r2)
-	ahi	%r3,-1
-	jnz	1b
-	j	4f
-2:	l	%r15,.Lstack-.LPG0(%r13)
+	l	%r15,.Lstack-.LPG0(%r13)
 	ahi	%r15,-STACK_FRAME_OVERHEAD
-	la	%r2,.Lals_string-.LPG0(%r13)
-	l	%r3,.Lsclp_print-.LPG0(%r13)
-	basr	%r14,%r3
-	lpsw	3f-.LPG0(%r13)		# machine type not good enough, crash
-.Lals_string:
-	.asciz	"The Linux kernel requires more recent processor hardware"
-.Lsclp_print:
-	.long	_sclp_print_early
-.Lstack:
-	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER))
-	.align 16
-3:	.long	0x000a0000,0x8badcccc
-
-# List of facilities that are required. If not all facilities are present
-# the kernel will crash.
-
-	.quad FACILITIES_ALS
-
-4:
+	brasl	%r14,verify_facilities
 	/* Continue with startup code in head64.S */
 	jg	startup_continue
 
+.Lstack:
+	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER))
 	.align	8
 6:	.long	0x7fffffff,0xffffffff
 
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 250f5972536a..dd6306c51bd6 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -690,6 +690,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	stack = (unsigned long) regs->gprs[15];
 
 	memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack));
+
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer to get messed up.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
 	return 1;
 }
 NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -705,6 +714,9 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	unsigned long stack;
 
+	/* It's OK to start function graph tracing again */
+	unpause_graph_tracing();
+
 	stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15];
 
 	/* Put the regs back */
diff --git a/arch/s390/kernel/sclp.c b/arch/s390/kernel/sclp.c
index d88db40bdf15..f08af675f36f 100644
--- a/arch/s390/kernel/sclp.c
+++ b/arch/s390/kernel/sclp.c
@@ -12,8 +12,9 @@
 #define EVTYP_VT220MSG_MASK	0x00000040
 #define EVTYP_MSG_MASK		0x40000000
 
-static char _sclp_work_area[4096] __aligned(PAGE_SIZE);
-static bool have_vt220, have_linemode;
+static char _sclp_work_area[4096] __aligned(PAGE_SIZE) __section(data);
+static bool have_vt220 __section(data);
+static bool have_linemode __section(data);
 
 static void _sclp_wait_int(void)
 {
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index d42fa38c2429..09a9e6dfc09f 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -12,6 +12,6 @@ common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqch
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
 kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o
-kvm-objs += diag.o gaccess.o guestdbg.o
+kvm-objs += diag.o gaccess.o guestdbg.o sthyi.o vsie.o
 
 obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 1ea4095b67d7..ce865bd4f81d 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -212,6 +212,11 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
 	    (vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY))
 		return -EOPNOTSUPP;
 
+	VCPU_EVENT(vcpu, 4, "diag 0x500 schid 0x%8.8x queue 0x%x cookie 0x%llx",
+			    (u32) vcpu->run->s.regs.gprs[2],
+			    (u32) vcpu->run->s.regs.gprs[3],
+			    vcpu->run->s.regs.gprs[4]);
+
 	/*
 	 * The layout is as follows:
 	 * - gpr 2 contains the subchannel id (passed as addr)
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 66938d283b77..54200208bf24 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -8,6 +8,7 @@
 #include <linux/vmalloc.h>
 #include <linux/err.h>
 #include <asm/pgtable.h>
+#include <asm/gmap.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 #include <asm/switch_to.h>
@@ -476,18 +477,73 @@ enum {
 	FSI_FETCH   = 2  /* Exception was due to fetch operation */
 };
 
-static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
-			 ar_t ar, enum gacc_mode mode)
+enum prot_type {
+	PROT_TYPE_LA   = 0,
+	PROT_TYPE_KEYC = 1,
+	PROT_TYPE_ALC  = 2,
+	PROT_TYPE_DAT  = 3,
+};
+
+static int trans_exc(struct kvm_vcpu *vcpu, int code, unsigned long gva,
+		     ar_t ar, enum gacc_mode mode, enum prot_type prot)
 {
-	int rc;
-	struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw);
 	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
-	struct trans_exc_code_bits *tec_bits;
+	struct trans_exc_code_bits *tec;
 
 	memset(pgm, 0, sizeof(*pgm));
-	tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
-	tec_bits->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH;
-	tec_bits->as = psw.as;
+	pgm->code = code;
+	tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
+
+	switch (code) {
+	case PGM_ASCE_TYPE:
+	case PGM_PAGE_TRANSLATION:
+	case PGM_REGION_FIRST_TRANS:
+	case PGM_REGION_SECOND_TRANS:
+	case PGM_REGION_THIRD_TRANS:
+	case PGM_SEGMENT_TRANSLATION:
+		/*
+		 * op_access_id only applies to MOVE_PAGE -> set bit 61
+		 * exc_access_id has to be set to 0 for some instructions. Both
+		 * cases have to be handled by the caller. We can always store
+		 * exc_access_id, as it is undefined for non-ar cases.
+		 */
+		tec->addr = gva >> PAGE_SHIFT;
+		tec->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH;
+		tec->as = psw_bits(vcpu->arch.sie_block->gpsw).as;
+		/* FALL THROUGH */
+	case PGM_ALEN_TRANSLATION:
+	case PGM_ALE_SEQUENCE:
+	case PGM_ASTE_VALIDITY:
+	case PGM_ASTE_SEQUENCE:
+	case PGM_EXTENDED_AUTHORITY:
+		pgm->exc_access_id = ar;
+		break;
+	case PGM_PROTECTION:
+		switch (prot) {
+		case PROT_TYPE_ALC:
+			tec->b60 = 1;
+			/* FALL THROUGH */
+		case PROT_TYPE_DAT:
+			tec->b61 = 1;
+			tec->addr = gva >> PAGE_SHIFT;
+			tec->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH;
+			tec->as = psw_bits(vcpu->arch.sie_block->gpsw).as;
+			/* exc_access_id is undefined for most cases */
+			pgm->exc_access_id = ar;
+			break;
+		default: /* LA and KEYC set b61 to 0, other params undefined */
+			break;
+		}
+		break;
+	}
+	return code;
+}
+
+static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
+			 unsigned long ga, ar_t ar, enum gacc_mode mode)
+{
+	int rc;
+	struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw);
 
 	if (!psw.t) {
 		asce->val = 0;
@@ -510,21 +566,8 @@ static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
 		return 0;
 	case PSW_AS_ACCREG:
 		rc = ar_translation(vcpu, asce, ar, mode);
-		switch (rc) {
-		case PGM_ALEN_TRANSLATION:
-		case PGM_ALE_SEQUENCE:
-		case PGM_ASTE_VALIDITY:
-		case PGM_ASTE_SEQUENCE:
-		case PGM_EXTENDED_AUTHORITY:
-			vcpu->arch.pgm.exc_access_id = ar;
-			break;
-		case PGM_PROTECTION:
-			tec_bits->b60 = 1;
-			tec_bits->b61 = 1;
-			break;
-		}
 		if (rc > 0)
-			pgm->code = rc;
+			return trans_exc(vcpu, rc, ga, ar, mode, PROT_TYPE_ALC);
 		return rc;
 	}
 	return 0;
@@ -729,40 +772,31 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
+static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar,
 			    unsigned long *pages, unsigned long nr_pages,
 			    const union asce asce, enum gacc_mode mode)
 {
-	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-	struct trans_exc_code_bits *tec_bits;
-	int lap_enabled, rc;
+	int lap_enabled, rc = 0;
 
-	tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
 	lap_enabled = low_address_protection_enabled(vcpu, asce);
 	while (nr_pages) {
 		ga = kvm_s390_logical_to_effective(vcpu, ga);
-		tec_bits->addr = ga >> PAGE_SHIFT;
-		if (mode == GACC_STORE && lap_enabled && is_low_address(ga)) {
-			pgm->code = PGM_PROTECTION;
-			return pgm->code;
-		}
+		if (mode == GACC_STORE && lap_enabled && is_low_address(ga))
+			return trans_exc(vcpu, PGM_PROTECTION, ga, ar, mode,
+					 PROT_TYPE_LA);
 		ga &= PAGE_MASK;
 		if (psw_bits(*psw).t) {
 			rc = guest_translate(vcpu, ga, pages, asce, mode);
 			if (rc < 0)
 				return rc;
-			if (rc == PGM_PROTECTION)
-				tec_bits->b61 = 1;
-			if (rc)
-				pgm->code = rc;
 		} else {
 			*pages = kvm_s390_real_to_abs(vcpu, ga);
 			if (kvm_is_error_gpa(vcpu->kvm, *pages))
-				pgm->code = PGM_ADDRESSING;
+				rc = PGM_ADDRESSING;
 		}
-		if (pgm->code)
-			return pgm->code;
+		if (rc)
+			return trans_exc(vcpu, rc, ga, ar, mode, PROT_TYPE_DAT);
 		ga += PAGE_SIZE;
 		pages++;
 		nr_pages--;
@@ -783,7 +817,8 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 
 	if (!len)
 		return 0;
-	rc = get_vcpu_asce(vcpu, &asce, ar, mode);
+	ga = kvm_s390_logical_to_effective(vcpu, ga);
+	rc = get_vcpu_asce(vcpu, &asce, ga, ar, mode);
 	if (rc)
 		return rc;
 	nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1;
@@ -795,7 +830,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 	need_ipte_lock = psw_bits(*psw).t && !asce.r;
 	if (need_ipte_lock)
 		ipte_lock(vcpu);
-	rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, mode);
+	rc = guest_page_range(vcpu, ga, ar, pages, nr_pages, asce, mode);
 	for (idx = 0; idx < nr_pages && !rc; idx++) {
 		gpa = *(pages + idx) + (ga & ~PAGE_MASK);
 		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
@@ -846,37 +881,28 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
 			    unsigned long *gpa, enum gacc_mode mode)
 {
-	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-	struct trans_exc_code_bits *tec;
 	union asce asce;
 	int rc;
 
 	gva = kvm_s390_logical_to_effective(vcpu, gva);
-	tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
-	rc = get_vcpu_asce(vcpu, &asce, ar, mode);
-	tec->addr = gva >> PAGE_SHIFT;
+	rc = get_vcpu_asce(vcpu, &asce, gva, ar, mode);
 	if (rc)
 		return rc;
 	if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) {
-		if (mode == GACC_STORE) {
-			rc = pgm->code = PGM_PROTECTION;
-			return rc;
-		}
+		if (mode == GACC_STORE)
+			return trans_exc(vcpu, PGM_PROTECTION, gva, 0,
+					 mode, PROT_TYPE_LA);
 	}
 
 	if (psw_bits(*psw).t && !asce.r) {	/* Use DAT? */
 		rc = guest_translate(vcpu, gva, gpa, asce, mode);
-		if (rc > 0) {
-			if (rc == PGM_PROTECTION)
-				tec->b61 = 1;
-			pgm->code = rc;
-		}
+		if (rc > 0)
+			return trans_exc(vcpu, rc, gva, 0, mode, PROT_TYPE_DAT);
 	} else {
-		rc = 0;
 		*gpa = kvm_s390_real_to_abs(vcpu, gva);
 		if (kvm_is_error_gpa(vcpu->kvm, *gpa))
-			rc = pgm->code = PGM_ADDRESSING;
+			return trans_exc(vcpu, rc, gva, PGM_ADDRESSING, mode, 0);
 	}
 
 	return rc;
@@ -915,20 +941,247 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
  */
 int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra)
 {
-	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
-	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-	struct trans_exc_code_bits *tec_bits;
 	union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]};
 
 	if (!ctlreg0.lap || !is_low_address(gra))
 		return 0;
+	return trans_exc(vcpu, PGM_PROTECTION, gra, 0, GACC_STORE, PROT_TYPE_LA);
+}
 
-	memset(pgm, 0, sizeof(*pgm));
-	tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
-	tec_bits->fsi = FSI_STORE;
-	tec_bits->as = psw_bits(*psw).as;
-	tec_bits->addr = gra >> PAGE_SHIFT;
-	pgm->code = PGM_PROTECTION;
+/**
+ * kvm_s390_shadow_tables - walk the guest page table and create shadow tables
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @pgt: pointer to the page table address result
+ * @fake: pgt references contiguous guest memory block, not a pgtable
+ */
+static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
+				  unsigned long *pgt, int *dat_protection,
+				  int *fake)
+{
+	struct gmap *parent;
+	union asce asce;
+	union vaddress vaddr;
+	unsigned long ptr;
+	int rc;
+
+	*fake = 0;
+	*dat_protection = 0;
+	parent = sg->parent;
+	vaddr.addr = saddr;
+	asce.val = sg->orig_asce;
+	ptr = asce.origin * 4096;
+	if (asce.r) {
+		*fake = 1;
+		asce.dt = ASCE_TYPE_REGION1;
+	}
+	switch (asce.dt) {
+	case ASCE_TYPE_REGION1:
+		if (vaddr.rfx01 > asce.tl && !asce.r)
+			return PGM_REGION_FIRST_TRANS;
+		break;
+	case ASCE_TYPE_REGION2:
+		if (vaddr.rfx)
+			return PGM_ASCE_TYPE;
+		if (vaddr.rsx01 > asce.tl)
+			return PGM_REGION_SECOND_TRANS;
+		break;
+	case ASCE_TYPE_REGION3:
+		if (vaddr.rfx || vaddr.rsx)
+			return PGM_ASCE_TYPE;
+		if (vaddr.rtx01 > asce.tl)
+			return PGM_REGION_THIRD_TRANS;
+		break;
+	case ASCE_TYPE_SEGMENT:
+		if (vaddr.rfx || vaddr.rsx || vaddr.rtx)
+			return PGM_ASCE_TYPE;
+		if (vaddr.sx01 > asce.tl)
+			return PGM_SEGMENT_TRANSLATION;
+		break;
+	}
+
+	switch (asce.dt) {
+	case ASCE_TYPE_REGION1: {
+		union region1_table_entry rfte;
 
-	return pgm->code;
+		if (*fake) {
+			/* offset in 16EB guest memory block */
+			ptr = ptr + ((unsigned long) vaddr.rsx << 53UL);
+			rfte.val = ptr;
+			goto shadow_r2t;
+		}
+		rc = gmap_read_table(parent, ptr + vaddr.rfx * 8, &rfte.val);
+		if (rc)
+			return rc;
+		if (rfte.i)
+			return PGM_REGION_FIRST_TRANS;
+		if (rfte.tt != TABLE_TYPE_REGION1)
+			return PGM_TRANSLATION_SPEC;
+		if (vaddr.rsx01 < rfte.tf || vaddr.rsx01 > rfte.tl)
+			return PGM_REGION_SECOND_TRANS;
+		if (sg->edat_level >= 1)
+			*dat_protection |= rfte.p;
+		ptr = rfte.rto << 12UL;
+shadow_r2t:
+		rc = gmap_shadow_r2t(sg, saddr, rfte.val, *fake);
+		if (rc)
+			return rc;
+		/* fallthrough */
+	}
+	case ASCE_TYPE_REGION2: {
+		union region2_table_entry rste;
+
+		if (*fake) {
+			/* offset in 8PB guest memory block */
+			ptr = ptr + ((unsigned long) vaddr.rtx << 42UL);
+			rste.val = ptr;
+			goto shadow_r3t;
+		}
+		rc = gmap_read_table(parent, ptr + vaddr.rsx * 8, &rste.val);
+		if (rc)
+			return rc;
+		if (rste.i)
+			return PGM_REGION_SECOND_TRANS;
+		if (rste.tt != TABLE_TYPE_REGION2)
+			return PGM_TRANSLATION_SPEC;
+		if (vaddr.rtx01 < rste.tf || vaddr.rtx01 > rste.tl)
+			return PGM_REGION_THIRD_TRANS;
+		if (sg->edat_level >= 1)
+			*dat_protection |= rste.p;
+		ptr = rste.rto << 12UL;
+shadow_r3t:
+		rste.p |= *dat_protection;
+		rc = gmap_shadow_r3t(sg, saddr, rste.val, *fake);
+		if (rc)
+			return rc;
+		/* fallthrough */
+	}
+	case ASCE_TYPE_REGION3: {
+		union region3_table_entry rtte;
+
+		if (*fake) {
+			/* offset in 4TB guest memory block */
+			ptr = ptr + ((unsigned long) vaddr.sx << 31UL);
+			rtte.val = ptr;
+			goto shadow_sgt;
+		}
+		rc = gmap_read_table(parent, ptr + vaddr.rtx * 8, &rtte.val);
+		if (rc)
+			return rc;
+		if (rtte.i)
+			return PGM_REGION_THIRD_TRANS;
+		if (rtte.tt != TABLE_TYPE_REGION3)
+			return PGM_TRANSLATION_SPEC;
+		if (rtte.cr && asce.p && sg->edat_level >= 2)
+			return PGM_TRANSLATION_SPEC;
+		if (rtte.fc && sg->edat_level >= 2) {
+			*dat_protection |= rtte.fc0.p;
+			*fake = 1;
+			ptr = rtte.fc1.rfaa << 31UL;
+			rtte.val = ptr;
+			goto shadow_sgt;
+		}
+		if (vaddr.sx01 < rtte.fc0.tf || vaddr.sx01 > rtte.fc0.tl)
+			return PGM_SEGMENT_TRANSLATION;
+		if (sg->edat_level >= 1)
+			*dat_protection |= rtte.fc0.p;
+		ptr = rtte.fc0.sto << 12UL;
+shadow_sgt:
+		rtte.fc0.p |= *dat_protection;
+		rc = gmap_shadow_sgt(sg, saddr, rtte.val, *fake);
+		if (rc)
+			return rc;
+		/* fallthrough */
+	}
+	case ASCE_TYPE_SEGMENT: {
+		union segment_table_entry ste;
+
+		if (*fake) {
+			/* offset in 2G guest memory block */
+			ptr = ptr + ((unsigned long) vaddr.sx << 20UL);
+			ste.val = ptr;
+			goto shadow_pgt;
+		}
+		rc = gmap_read_table(parent, ptr + vaddr.sx * 8, &ste.val);
+		if (rc)
+			return rc;
+		if (ste.i)
+			return PGM_SEGMENT_TRANSLATION;
+		if (ste.tt != TABLE_TYPE_SEGMENT)
+			return PGM_TRANSLATION_SPEC;
+		if (ste.cs && asce.p)
+			return PGM_TRANSLATION_SPEC;
+		*dat_protection |= ste.fc0.p;
+		if (ste.fc && sg->edat_level >= 1) {
+			*fake = 1;
+			ptr = ste.fc1.sfaa << 20UL;
+			ste.val = ptr;
+			goto shadow_pgt;
+		}
+		ptr = ste.fc0.pto << 11UL;
+shadow_pgt:
+		ste.fc0.p |= *dat_protection;
+		rc = gmap_shadow_pgt(sg, saddr, ste.val, *fake);
+		if (rc)
+			return rc;
+	}
+	}
+	/* Return the parent address of the page table */
+	*pgt = ptr;
+	return 0;
+}
+
+/**
+ * kvm_s390_shadow_fault - handle fault on a shadow page table
+ * @vcpu: virtual cpu
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ *
+ * Returns: - 0 if the shadow fault was successfully resolved
+ *	    - > 0 (pgm exception code) on exceptions while faulting
+ *	    - -EAGAIN if the caller can retry immediately
+ *	    - -EFAULT when accessing invalid guest addresses
+ *	    - -ENOMEM if out of memory
+ */
+int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
+			  unsigned long saddr)
+{
+	union vaddress vaddr;
+	union page_table_entry pte;
+	unsigned long pgt;
+	int dat_protection, fake;
+	int rc;
+
+	down_read(&sg->mm->mmap_sem);
+	/*
+	 * We don't want any guest-2 tables to change - so the parent
+	 * tables/pointers we read stay valid - unshadowing is however
+	 * always possible - only guest_table_lock protects us.
+	 */
+	ipte_lock(vcpu);
+
+	rc = gmap_shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake);
+	if (rc)
+		rc = kvm_s390_shadow_tables(sg, saddr, &pgt, &dat_protection,
+					    &fake);
+
+	vaddr.addr = saddr;
+	if (fake) {
+		/* offset in 1MB guest memory block */
+		pte.val = pgt + ((unsigned long) vaddr.px << 12UL);
+		goto shadow_page;
+	}
+	if (!rc)
+		rc = gmap_read_table(sg->parent, pgt + vaddr.px * 8, &pte.val);
+	if (!rc && pte.i)
+		rc = PGM_PAGE_TRANSLATION;
+	if (!rc && (pte.z || (pte.co && sg->edat_level < 1)))
+		rc = PGM_TRANSLATION_SPEC;
+shadow_page:
+	pte.p |= dat_protection;
+	if (!rc)
+		rc = gmap_shadow_page(sg, saddr, __pte(pte.val));
+	ipte_unlock(vcpu);
+	up_read(&sg->mm->mmap_sem);
+	return rc;
 }
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index df0a79dd8159..8756569ad938 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -361,4 +361,7 @@ void ipte_unlock(struct kvm_vcpu *vcpu);
 int ipte_lock_held(struct kvm_vcpu *vcpu);
 int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra);
 
+int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *shadow,
+			  unsigned long saddr);
+
 #endif /* __KVM_S390_GACCESS_H */
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index e8c6843b9600..31a05330d11c 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -439,6 +439,23 @@ exit_required:
 #define guest_per_enabled(vcpu) \
 			     (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER)
 
+int kvm_s390_handle_per_ifetch_icpt(struct kvm_vcpu *vcpu)
+{
+	const u8 ilen = kvm_s390_get_ilen(vcpu);
+	struct kvm_s390_pgm_info pgm_info = {
+		.code = PGM_PER,
+		.per_code = PER_EVENT_IFETCH >> 24,
+		.per_address = __rewind_psw(vcpu->arch.sie_block->gpsw, ilen),
+	};
+
+	/*
+	 * The PSW points to the next instruction, therefore the intercepted
+	 * instruction generated a PER i-fetch event. PER address therefore
+	 * points at the previous PSW address (could be an EXECUTE function).
+	 */
+	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+}
+
 static void filter_guest_per_event(struct kvm_vcpu *vcpu)
 {
 	u32 perc = vcpu->arch.sie_block->perc << 24;
@@ -465,7 +482,7 @@ static void filter_guest_per_event(struct kvm_vcpu *vcpu)
 		guest_perc &= ~PER_EVENT_IFETCH;
 
 	/* All other PER events will be given to the guest */
-	/* TODO: Check alterated address/address space */
+	/* TODO: Check altered address/address space */
 
 	vcpu->arch.sie_block->perc = guest_perc >> 24;
 
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 252157181302..dfd0ca2638fa 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -351,8 +351,26 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu)
 	return -EOPNOTSUPP;
 }
 
+static int handle_operexc(struct kvm_vcpu *vcpu)
+{
+	vcpu->stat.exit_operation_exception++;
+	trace_kvm_s390_handle_operexc(vcpu, vcpu->arch.sie_block->ipa,
+				      vcpu->arch.sie_block->ipb);
+
+	if (vcpu->arch.sie_block->ipa == 0xb256 &&
+	    test_kvm_facility(vcpu->kvm, 74))
+		return handle_sthyi(vcpu);
+
+	if (vcpu->arch.sie_block->ipa == 0 && vcpu->kvm->arch.user_instr0)
+		return -EOPNOTSUPP;
+
+	return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
+}
+
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 {
+	int rc, per_rc = 0;
+
 	if (kvm_is_ucontrol(vcpu->kvm))
 		return -EOPNOTSUPP;
 
@@ -361,7 +379,8 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 	case 0x18:
 		return handle_noop(vcpu);
 	case 0x04:
-		return handle_instruction(vcpu);
+		rc = handle_instruction(vcpu);
+		break;
 	case 0x08:
 		return handle_prog(vcpu);
 	case 0x14:
@@ -372,9 +391,19 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 		return handle_validity(vcpu);
 	case 0x28:
 		return handle_stop(vcpu);
+	case 0x2c:
+		rc = handle_operexc(vcpu);
+		break;
 	case 0x38:
-		return handle_partial_execution(vcpu);
+		rc = handle_partial_execution(vcpu);
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
+
+	/* process PER, also if the instrution is processed in user space */
+	if (vcpu->arch.sie_block->icptstatus & 0x02 &&
+	    (!rc || rc == -EOPNOTSUPP))
+		per_rc = kvm_s390_handle_per_ifetch_icpt(vcpu);
+	return per_rc ? per_rc : rc;
 }
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 5a80af740d3e..24524c0f3ef8 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -28,9 +28,6 @@
 #include "gaccess.h"
 #include "trace-s390.h"
 
-#define IOINT_SCHID_MASK 0x0000ffff
-#define IOINT_SSID_MASK 0x00030000
-#define IOINT_CSSID_MASK 0x03fc0000
 #define PFAULT_INIT 0x0600
 #define PFAULT_DONE 0x0680
 #define VIRTIO_PARAM 0x0d00
@@ -821,7 +818,14 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
 					struct kvm_s390_interrupt_info,
 					list);
 	if (inti) {
-		VCPU_EVENT(vcpu, 4, "deliver: I/O 0x%llx", inti->type);
+		if (inti->type & KVM_S390_INT_IO_AI_MASK)
+			VCPU_EVENT(vcpu, 4, "%s", "deliver: I/O (AI)");
+		else
+			VCPU_EVENT(vcpu, 4, "deliver: I/O %x ss %x schid %04x",
+			inti->io.subchannel_id >> 8,
+			inti->io.subchannel_id >> 1 & 0x3,
+			inti->io.subchannel_nr);
+
 		vcpu->stat.deliver_io_int++;
 		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
 				inti->type,
@@ -991,6 +995,11 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 		swake_up(&vcpu->wq);
 		vcpu->stat.halt_wakeup++;
 	}
+	/*
+	 * The VCPU might not be sleeping but is executing the VSIE. Let's
+	 * kick it, so it leaves the SIE to process the request.
+	 */
+	kvm_s390_vsie_kick(vcpu);
 }
 
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
@@ -1415,6 +1424,13 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	}
 	fi->counters[FIRQ_CNTR_IO] += 1;
 
+	if (inti->type & KVM_S390_INT_IO_AI_MASK)
+		VM_EVENT(kvm, 4, "%s", "inject: I/O (AI)");
+	else
+		VM_EVENT(kvm, 4, "inject: I/O %x ss %x schid %04x",
+			inti->io.subchannel_id >> 8,
+			inti->io.subchannel_id >> 1 & 0x3,
+			inti->io.subchannel_nr);
 	isc = int_word_to_isc(inti->io.io_int_word);
 	list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc];
 	list_add_tail(&inti->list, list);
@@ -1531,13 +1547,6 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 		inti->mchk.mcic = s390int->parm64;
 		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		if (inti->type & KVM_S390_INT_IO_AI_MASK)
-			VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
-		else
-			VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x",
-				 s390int->type & IOINT_CSSID_MASK,
-				 s390int->type & IOINT_SSID_MASK,
-				 s390int->type & IOINT_SCHID_MASK);
 		inti->io.subchannel_id = s390int->parm >> 16;
 		inti->io.subchannel_nr = s390int->parm & 0x0000ffffu;
 		inti->io.io_int_parm = s390int->parm64 >> 32;
@@ -2237,7 +2246,8 @@ static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e,
 	return ret;
 }
 
-int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm *kvm,
+			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
 {
 	int ret;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6f5c344cd785..3f3ae4865d57 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -21,11 +21,13 @@
 #include <linux/init.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <linux/mman.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/timer.h>
 #include <linux/vmalloc.h>
+#include <linux/bitmap.h>
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
 #include <asm/stp.h>
@@ -35,6 +37,8 @@
 #include <asm/switch_to.h>
 #include <asm/isc.h>
 #include <asm/sclp.h>
+#include <asm/cpacf.h>
+#include <asm/timex.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
@@ -64,6 +68,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "exit_pei", VCPU_STAT(exit_pei) },
 	{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
 	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
+	{ "exit_operation_exception", VCPU_STAT(exit_operation_exception) },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
 	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
 	{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
@@ -94,6 +99,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
 	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
 	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
+	{ "instruction_sthyi", VCPU_STAT(instruction_sthyi) },
+	{ "instruction_sie", VCPU_STAT(instruction_sie) },
 	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
 	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
 	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
@@ -119,6 +126,11 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
+/* allow nested virtualization in KVM (if enabled by user space) */
+static int nested;
+module_param(nested, int, S_IRUGO);
+MODULE_PARM_DESC(nested, "Nested virtualization support");
+
 /* upper facilities limit for kvm */
 unsigned long kvm_s390_fac_list_mask[16] = {
 	0xffe6000000000000UL,
@@ -131,7 +143,13 @@ unsigned long kvm_s390_fac_list_mask_size(void)
 	return ARRAY_SIZE(kvm_s390_fac_list_mask);
 }
 
+/* available cpu features supported by kvm */
+static DECLARE_BITMAP(kvm_s390_available_cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
+/* available subfunctions indicated via query / "test bit" */
+static struct kvm_s390_vm_cpu_subfunc kvm_s390_available_subfunc;
+
 static struct gmap_notifier gmap_notifier;
+static struct gmap_notifier vsie_gmap_notifier;
 debug_info_t *kvm_s390_dbf;
 
 /* Section: not file related */
@@ -141,7 +159,8 @@ int kvm_arch_hardware_enable(void)
 	return 0;
 }
 
-static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);
+static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
+			      unsigned long end);
 
 /*
  * This callback is executed during stop_machine(). All CPUs are therefore
@@ -163,6 +182,8 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
 			vcpu->arch.sie_block->epoch -= *delta;
 			if (vcpu->arch.cputm_enabled)
 				vcpu->arch.cputm_start += *delta;
+			if (vcpu->arch.vsie_block)
+				vcpu->arch.vsie_block->epoch -= *delta;
 		}
 	}
 	return NOTIFY_OK;
@@ -175,7 +196,9 @@ static struct notifier_block kvm_clock_notifier = {
 int kvm_arch_hardware_setup(void)
 {
 	gmap_notifier.notifier_call = kvm_gmap_notifier;
-	gmap_register_ipte_notifier(&gmap_notifier);
+	gmap_register_pte_notifier(&gmap_notifier);
+	vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier;
+	gmap_register_pte_notifier(&vsie_gmap_notifier);
 	atomic_notifier_chain_register(&s390_epoch_delta_notifier,
 				       &kvm_clock_notifier);
 	return 0;
@@ -183,11 +206,109 @@ int kvm_arch_hardware_setup(void)
 
 void kvm_arch_hardware_unsetup(void)
 {
-	gmap_unregister_ipte_notifier(&gmap_notifier);
+	gmap_unregister_pte_notifier(&gmap_notifier);
+	gmap_unregister_pte_notifier(&vsie_gmap_notifier);
 	atomic_notifier_chain_unregister(&s390_epoch_delta_notifier,
 					 &kvm_clock_notifier);
 }
 
+static void allow_cpu_feat(unsigned long nr)
+{
+	set_bit_inv(nr, kvm_s390_available_cpu_feat);
+}
+
+static inline int plo_test_bit(unsigned char nr)
+{
+	register unsigned long r0 asm("0") = (unsigned long) nr | 0x100;
+	int cc = 3; /* subfunction not available */
+
+	asm volatile(
+		/* Parameter registers are ignored for "test bit" */
+		"	plo	0,0,0,0(0)\n"
+		"	ipm	%0\n"
+		"	srl	%0,28\n"
+		: "=d" (cc)
+		: "d" (r0)
+		: "cc");
+	return cc == 0;
+}
+
+static void kvm_s390_cpu_feat_init(void)
+{
+	int i;
+
+	for (i = 0; i < 256; ++i) {
+		if (plo_test_bit(i))
+			kvm_s390_available_subfunc.plo[i >> 3] |= 0x80 >> (i & 7);
+	}
+
+	if (test_facility(28)) /* TOD-clock steering */
+		ptff(kvm_s390_available_subfunc.ptff,
+		     sizeof(kvm_s390_available_subfunc.ptff),
+		     PTFF_QAF);
+
+	if (test_facility(17)) { /* MSA */
+		__cpacf_query(CPACF_KMAC, kvm_s390_available_subfunc.kmac);
+		__cpacf_query(CPACF_KMC, kvm_s390_available_subfunc.kmc);
+		__cpacf_query(CPACF_KM, kvm_s390_available_subfunc.km);
+		__cpacf_query(CPACF_KIMD, kvm_s390_available_subfunc.kimd);
+		__cpacf_query(CPACF_KLMD, kvm_s390_available_subfunc.klmd);
+	}
+	if (test_facility(76)) /* MSA3 */
+		__cpacf_query(CPACF_PCKMO, kvm_s390_available_subfunc.pckmo);
+	if (test_facility(77)) { /* MSA4 */
+		__cpacf_query(CPACF_KMCTR, kvm_s390_available_subfunc.kmctr);
+		__cpacf_query(CPACF_KMF, kvm_s390_available_subfunc.kmf);
+		__cpacf_query(CPACF_KMO, kvm_s390_available_subfunc.kmo);
+		__cpacf_query(CPACF_PCC, kvm_s390_available_subfunc.pcc);
+	}
+	if (test_facility(57)) /* MSA5 */
+		__cpacf_query(CPACF_PPNO, kvm_s390_available_subfunc.ppno);
+
+	if (MACHINE_HAS_ESOP)
+		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP);
+	/*
+	 * We need SIE support, ESOP (PROT_READ protection for gmap_shadow),
+	 * 64bit SCAO (SCA passthrough) and IDTE (for gmap_shadow unshadowing).
+	 */
+	if (!sclp.has_sief2 || !MACHINE_HAS_ESOP || !sclp.has_64bscao ||
+	    !test_facility(3) || !nested)
+		return;
+	allow_cpu_feat(KVM_S390_VM_CPU_FEAT_SIEF2);
+	if (sclp.has_64bscao)
+		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_64BSCAO);
+	if (sclp.has_siif)
+		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_SIIF);
+	if (sclp.has_gpere)
+		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_GPERE);
+	if (sclp.has_gsls)
+		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_GSLS);
+	if (sclp.has_ib)
+		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_IB);
+	if (sclp.has_cei)
+		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_CEI);
+	if (sclp.has_ibs)
+		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_IBS);
+	/*
+	 * KVM_S390_VM_CPU_FEAT_SKEY: Wrong shadow of PTE.I bits will make
+	 * all skey handling functions read/set the skey from the PGSTE
+	 * instead of the real storage key.
+	 *
+	 * KVM_S390_VM_CPU_FEAT_CMMA: Wrong shadow of PTE.I bits will make
+	 * pages being detected as preserved although they are resident.
+	 *
+	 * KVM_S390_VM_CPU_FEAT_PFMFI: Wrong shadow of PTE.I bits will
+	 * have the same effect as for KVM_S390_VM_CPU_FEAT_SKEY.
+	 *
+	 * For KVM_S390_VM_CPU_FEAT_SKEY, KVM_S390_VM_CPU_FEAT_CMMA and
+	 * KVM_S390_VM_CPU_FEAT_PFMFI, all PTE.I and PGSTE bits have to be
+	 * correctly shadowed. We can do that for the PGSTE but not for PTE.I.
+	 *
+	 * KVM_S390_VM_CPU_FEAT_SIGPIF: Wrong SCB addresses in the SCA. We
+	 * cannot easily shadow the SCA because of the ipte lock.
+	 */
+}
+
 int kvm_arch_init(void *opaque)
 {
 	kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long));
@@ -199,6 +320,8 @@ int kvm_arch_init(void *opaque)
 		return -ENOMEM;
 	}
 
+	kvm_s390_cpu_feat_init();
+
 	/* Register floating interrupt controller interface. */
 	return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
 }
@@ -244,6 +367,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_USER_STSI:
 	case KVM_CAP_S390_SKEYS:
 	case KVM_CAP_S390_IRQ_STATE:
+	case KVM_CAP_S390_USER_INSTR0:
 		r = 1;
 		break;
 	case KVM_CAP_S390_MEM_OP:
@@ -251,8 +375,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_NR_VCPUS:
 	case KVM_CAP_MAX_VCPUS:
-		r = sclp.has_esca ? KVM_S390_ESCA_CPU_SLOTS
-				  : KVM_S390_BSCA_CPU_SLOTS;
+		r = KVM_S390_BSCA_CPU_SLOTS;
+		if (sclp.has_esca && sclp.has_64bscao)
+			r = KVM_S390_ESCA_CPU_SLOTS;
 		break;
 	case KVM_CAP_NR_MEMSLOTS:
 		r = KVM_USER_MEM_SLOTS;
@@ -335,6 +460,16 @@ out:
 	return r;
 }
 
+static void icpt_operexc_on_all_vcpus(struct kvm *kvm)
+{
+	unsigned int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		kvm_s390_sync_request(KVM_REQ_ICPT_OPEREXC, vcpu);
+	}
+}
+
 static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 {
 	int r;
@@ -355,7 +490,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		break;
 	case KVM_CAP_S390_VECTOR_REGISTERS:
 		mutex_lock(&kvm->lock);
-		if (atomic_read(&kvm->online_vcpus)) {
+		if (kvm->created_vcpus) {
 			r = -EBUSY;
 		} else if (MACHINE_HAS_VX) {
 			set_kvm_facility(kvm->arch.model.fac_mask, 129);
@@ -370,7 +505,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 	case KVM_CAP_S390_RI:
 		r = -EINVAL;
 		mutex_lock(&kvm->lock);
-		if (atomic_read(&kvm->online_vcpus)) {
+		if (kvm->created_vcpus) {
 			r = -EBUSY;
 		} else if (test_facility(64)) {
 			set_kvm_facility(kvm->arch.model.fac_mask, 64);
@@ -386,6 +521,12 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		kvm->arch.user_stsi = 1;
 		r = 0;
 		break;
+	case KVM_CAP_S390_USER_INSTR0:
+		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_INSTR0");
+		kvm->arch.user_instr0 = 1;
+		icpt_operexc_on_all_vcpus(kvm);
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -418,21 +559,23 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 	unsigned int idx;
 	switch (attr->attr) {
 	case KVM_S390_VM_MEM_ENABLE_CMMA:
-		/* enable CMMA only for z10 and later (EDAT_1) */
-		ret = -EINVAL;
-		if (!MACHINE_IS_LPAR || !MACHINE_HAS_EDAT1)
+		ret = -ENXIO;
+		if (!sclp.has_cmma)
 			break;
 
 		ret = -EBUSY;
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
 		mutex_lock(&kvm->lock);
-		if (atomic_read(&kvm->online_vcpus) == 0) {
+		if (!kvm->created_vcpus) {
 			kvm->arch.use_cmma = 1;
 			ret = 0;
 		}
 		mutex_unlock(&kvm->lock);
 		break;
 	case KVM_S390_VM_MEM_CLR_CMMA:
+		ret = -ENXIO;
+		if (!sclp.has_cmma)
+			break;
 		ret = -EINVAL;
 		if (!kvm->arch.use_cmma)
 			break;
@@ -461,20 +604,20 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		if (!new_limit)
 			return -EINVAL;
 
-		/* gmap_alloc takes last usable address */
+		/* gmap_create takes last usable address */
 		if (new_limit != KVM_S390_NO_MEM_LIMIT)
 			new_limit -= 1;
 
 		ret = -EBUSY;
 		mutex_lock(&kvm->lock);
-		if (atomic_read(&kvm->online_vcpus) == 0) {
-			/* gmap_alloc will round the limit up */
-			struct gmap *new = gmap_alloc(current->mm, new_limit);
+		if (!kvm->created_vcpus) {
+			/* gmap_create will round the limit up */
+			struct gmap *new = gmap_create(current->mm, new_limit);
 
 			if (!new) {
 				ret = -ENOMEM;
 			} else {
-				gmap_free(kvm->arch.gmap);
+				gmap_remove(kvm->arch.gmap);
 				new->private = kvm;
 				kvm->arch.gmap = new;
 				ret = 0;
@@ -644,7 +787,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 	int ret = 0;
 
 	mutex_lock(&kvm->lock);
-	if (atomic_read(&kvm->online_vcpus)) {
+	if (kvm->created_vcpus) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -676,6 +819,39 @@ out:
 	return ret;
 }
 
+static int kvm_s390_set_processor_feat(struct kvm *kvm,
+				       struct kvm_device_attr *attr)
+{
+	struct kvm_s390_vm_cpu_feat data;
+	int ret = -EBUSY;
+
+	if (copy_from_user(&data, (void __user *)attr->addr, sizeof(data)))
+		return -EFAULT;
+	if (!bitmap_subset((unsigned long *) data.feat,
+			   kvm_s390_available_cpu_feat,
+			   KVM_S390_VM_CPU_FEAT_NR_BITS))
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+	if (!atomic_read(&kvm->online_vcpus)) {
+		bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat,
+			    KVM_S390_VM_CPU_FEAT_NR_BITS);
+		ret = 0;
+	}
+	mutex_unlock(&kvm->lock);
+	return ret;
+}
+
+static int kvm_s390_set_processor_subfunc(struct kvm *kvm,
+					  struct kvm_device_attr *attr)
+{
+	/*
+	 * Once supported by kernel + hw, we have to store the subfunctions
+	 * in kvm->arch and remember that user space configured them.
+	 */
+	return -ENXIO;
+}
+
 static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
 {
 	int ret = -ENXIO;
@@ -684,6 +860,12 @@ static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
 	case KVM_S390_VM_CPU_PROCESSOR:
 		ret = kvm_s390_set_processor(kvm, attr);
 		break;
+	case KVM_S390_VM_CPU_PROCESSOR_FEAT:
+		ret = kvm_s390_set_processor_feat(kvm, attr);
+		break;
+	case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
+		ret = kvm_s390_set_processor_subfunc(kvm, attr);
+		break;
 	}
 	return ret;
 }
@@ -732,6 +914,50 @@ out:
 	return ret;
 }
 
+static int kvm_s390_get_processor_feat(struct kvm *kvm,
+				       struct kvm_device_attr *attr)
+{
+	struct kvm_s390_vm_cpu_feat data;
+
+	bitmap_copy((unsigned long *) data.feat, kvm->arch.cpu_feat,
+		    KVM_S390_VM_CPU_FEAT_NR_BITS);
+	if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
+		return -EFAULT;
+	return 0;
+}
+
+static int kvm_s390_get_machine_feat(struct kvm *kvm,
+				     struct kvm_device_attr *attr)
+{
+	struct kvm_s390_vm_cpu_feat data;
+
+	bitmap_copy((unsigned long *) data.feat,
+		    kvm_s390_available_cpu_feat,
+		    KVM_S390_VM_CPU_FEAT_NR_BITS);
+	if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
+		return -EFAULT;
+	return 0;
+}
+
+static int kvm_s390_get_processor_subfunc(struct kvm *kvm,
+					  struct kvm_device_attr *attr)
+{
+	/*
+	 * Once we can actually configure subfunctions (kernel + hw support),
+	 * we have to check if they were already set by user space, if so copy
+	 * them from kvm->arch.
+	 */
+	return -ENXIO;
+}
+
+static int kvm_s390_get_machine_subfunc(struct kvm *kvm,
+					struct kvm_device_attr *attr)
+{
+	if (copy_to_user((void __user *)attr->addr, &kvm_s390_available_subfunc,
+	    sizeof(struct kvm_s390_vm_cpu_subfunc)))
+		return -EFAULT;
+	return 0;
+}
 static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
 {
 	int ret = -ENXIO;
@@ -743,6 +969,18 @@ static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
 	case KVM_S390_VM_CPU_MACHINE:
 		ret = kvm_s390_get_machine(kvm, attr);
 		break;
+	case KVM_S390_VM_CPU_PROCESSOR_FEAT:
+		ret = kvm_s390_get_processor_feat(kvm, attr);
+		break;
+	case KVM_S390_VM_CPU_MACHINE_FEAT:
+		ret = kvm_s390_get_machine_feat(kvm, attr);
+		break;
+	case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
+		ret = kvm_s390_get_processor_subfunc(kvm, attr);
+		break;
+	case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
+		ret = kvm_s390_get_machine_subfunc(kvm, attr);
+		break;
 	}
 	return ret;
 }
@@ -803,6 +1041,8 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
 		switch (attr->attr) {
 		case KVM_S390_VM_MEM_ENABLE_CMMA:
 		case KVM_S390_VM_MEM_CLR_CMMA:
+			ret = sclp.has_cmma ? 0 : -ENXIO;
+			break;
 		case KVM_S390_VM_MEM_LIMIT_SIZE:
 			ret = 0;
 			break;
@@ -826,8 +1066,13 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
 		switch (attr->attr) {
 		case KVM_S390_VM_CPU_PROCESSOR:
 		case KVM_S390_VM_CPU_MACHINE:
+		case KVM_S390_VM_CPU_PROCESSOR_FEAT:
+		case KVM_S390_VM_CPU_MACHINE_FEAT:
+		case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
 			ret = 0;
 			break;
+		/* configuring subfunctions is not supported yet */
+		case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
 		default:
 			ret = -ENXIO;
 			break;
@@ -858,7 +1103,6 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 {
 	uint8_t *keys;
 	uint64_t hva;
-	unsigned long curkey;
 	int i, r = 0;
 
 	if (args->flags != 0)
@@ -879,26 +1123,27 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	if (!keys)
 		return -ENOMEM;
 
+	down_read(&current->mm->mmap_sem);
 	for (i = 0; i < args->count; i++) {
 		hva = gfn_to_hva(kvm, args->start_gfn + i);
 		if (kvm_is_error_hva(hva)) {
 			r = -EFAULT;
-			goto out;
+			break;
 		}
 
-		curkey = get_guest_storage_key(current->mm, hva);
-		if (IS_ERR_VALUE(curkey)) {
-			r = curkey;
-			goto out;
-		}
-		keys[i] = curkey;
+		r = get_guest_storage_key(current->mm, hva, &keys[i]);
+		if (r)
+			break;
+	}
+	up_read(&current->mm->mmap_sem);
+
+	if (!r) {
+		r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys,
+				 sizeof(uint8_t) * args->count);
+		if (r)
+			r = -EFAULT;
 	}
 
-	r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys,
-			 sizeof(uint8_t) * args->count);
-	if (r)
-		r = -EFAULT;
-out:
 	kvfree(keys);
 	return r;
 }
@@ -935,24 +1180,25 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	if (r)
 		goto out;
 
+	down_read(&current->mm->mmap_sem);
 	for (i = 0; i < args->count; i++) {
 		hva = gfn_to_hva(kvm, args->start_gfn + i);
 		if (kvm_is_error_hva(hva)) {
 			r = -EFAULT;
-			goto out;
+			break;
 		}
 
 		/* Lowest order bit is reserved */
 		if (keys[i] & 0x01) {
 			r = -EINVAL;
-			goto out;
+			break;
 		}
 
-		r = set_guest_storage_key(current->mm, hva,
-					  (unsigned long)keys[i], 0);
+		r = set_guest_storage_key(current->mm, hva, keys[i], 0);
 		if (r)
-			goto out;
+			break;
 	}
+	up_read(&current->mm->mmap_sem);
 out:
 	kvfree(keys);
 	return r;
@@ -1129,6 +1375,7 @@ static void sca_dispose(struct kvm *kvm)
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
+	gfp_t alloc_flags = GFP_KERNEL;
 	int i, rc;
 	char debug_name[16];
 	static unsigned long sca_offset;
@@ -1150,9 +1397,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	rc = -ENOMEM;
 
+	ratelimit_state_init(&kvm->arch.sthyi_limit, 5 * HZ, 500);
+
 	kvm->arch.use_esca = 0; /* start with basic SCA */
+	if (!sclp.has_64bscao)
+		alloc_flags |= GFP_DMA;
 	rwlock_init(&kvm->arch.sca_lock);
-	kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
+	kvm->arch.sca = (struct bsca_block *) get_zeroed_page(alloc_flags);
 	if (!kvm->arch.sca)
 		goto out_err;
 	spin_lock(&kvm_lock);
@@ -1189,6 +1440,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 
+	set_kvm_facility(kvm->arch.model.fac_mask, 74);
+	set_kvm_facility(kvm->arch.model.fac_list, 74);
+
 	kvm->arch.model.cpuid = kvm_s390_get_initial_cpuid();
 	kvm->arch.model.ibc = sclp.ibc & 0x0fff;
 
@@ -1212,7 +1466,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		else
 			kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE,
 						    sclp.hamax + 1);
-		kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1);
+		kvm->arch.gmap = gmap_create(current->mm, kvm->arch.mem_limit - 1);
 		if (!kvm->arch.gmap)
 			goto out_err;
 		kvm->arch.gmap->private = kvm;
@@ -1224,6 +1478,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.epoch = 0;
 
 	spin_lock_init(&kvm->arch.start_stop_lock);
+	kvm_s390_vsie_init(kvm);
 	KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
 
 	return 0;
@@ -1245,7 +1500,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 		sca_del_vcpu(vcpu);
 
 	if (kvm_is_ucontrol(vcpu->kvm))
-		gmap_free(vcpu->arch.gmap);
+		gmap_remove(vcpu->arch.gmap);
 
 	if (vcpu->kvm->arch.use_cmma)
 		kvm_s390_vcpu_unsetup_cmma(vcpu);
@@ -1278,16 +1533,17 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	debug_unregister(kvm->arch.dbf);
 	free_page((unsigned long)kvm->arch.sie_page2);
 	if (!kvm_is_ucontrol(kvm))
-		gmap_free(kvm->arch.gmap);
+		gmap_remove(kvm->arch.gmap);
 	kvm_s390_destroy_adapters(kvm);
 	kvm_s390_clear_float_irqs(kvm);
+	kvm_s390_vsie_destroy(kvm);
 	KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
 }
 
 /* Section: vcpu related */
 static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.gmap = gmap_alloc(current->mm, -1UL);
+	vcpu->arch.gmap = gmap_create(current->mm, -1UL);
 	if (!vcpu->arch.gmap)
 		return -ENOMEM;
 	vcpu->arch.gmap->private = vcpu->kvm;
@@ -1396,7 +1652,7 @@ static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
 
 	if (id < KVM_S390_BSCA_CPU_SLOTS)
 		return true;
-	if (!sclp.has_esca)
+	if (!sclp.has_esca || !sclp.has_64bscao)
 		return false;
 
 	mutex_lock(&kvm->lock);
@@ -1537,7 +1793,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	save_access_regs(vcpu->arch.host_acrs);
 	restore_access_regs(vcpu->run->s.regs.acrs);
-	gmap_enable(vcpu->arch.gmap);
+	gmap_enable(vcpu->arch.enabled_gmap);
 	atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
 		__start_cpu_timer_accounting(vcpu);
@@ -1550,7 +1806,8 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
 		__stop_cpu_timer_accounting(vcpu);
 	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
-	gmap_disable(vcpu->arch.gmap);
+	vcpu->arch.enabled_gmap = gmap_get_enabled();
+	gmap_disable(vcpu->arch.enabled_gmap);
 
 	/* Save guest register state */
 	save_fpu_regs();
@@ -1599,7 +1856,10 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
 		sca_add_vcpu(vcpu);
 	}
-
+	if (test_kvm_facility(vcpu->kvm, 74) || vcpu->kvm->arch.user_instr0)
+		vcpu->arch.sie_block->ictl |= ICTL_OPEREXC;
+	/* make vcpu_load load the right gmap on the first trigger */
+	vcpu->arch.enabled_gmap = vcpu->arch.gmap;
 }
 
 static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
@@ -1658,15 +1918,21 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvm_s390_vcpu_setup_model(vcpu);
 
-	vcpu->arch.sie_block->ecb = 0x02;
+	/* pgste_set_pte has special handling for !MACHINE_HAS_ESOP */
+	if (MACHINE_HAS_ESOP)
+		vcpu->arch.sie_block->ecb |= 0x02;
 	if (test_kvm_facility(vcpu->kvm, 9))
 		vcpu->arch.sie_block->ecb |= 0x04;
-	if (test_kvm_facility(vcpu->kvm, 50) && test_kvm_facility(vcpu->kvm, 73))
+	if (test_kvm_facility(vcpu->kvm, 73))
 		vcpu->arch.sie_block->ecb |= 0x10;
 
-	if (test_kvm_facility(vcpu->kvm, 8))
+	if (test_kvm_facility(vcpu->kvm, 8) && sclp.has_pfmfi)
 		vcpu->arch.sie_block->ecb2 |= 0x08;
-	vcpu->arch.sie_block->eca   = 0xC1002000U;
+	vcpu->arch.sie_block->eca = 0x1002000U;
+	if (sclp.has_cei)
+		vcpu->arch.sie_block->eca |= 0x80000000U;
+	if (sclp.has_ib)
+		vcpu->arch.sie_block->eca |= 0x40000000U;
 	if (sclp.has_siif)
 		vcpu->arch.sie_block->eca |= 1;
 	if (sclp.has_sigpif)
@@ -1716,6 +1982,10 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.sie_block = &sie_page->sie_block;
 	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
 
+	/* the real guest size will always be smaller than msl */
+	vcpu->arch.sie_block->mso = 0;
+	vcpu->arch.sie_block->msl = sclp.hamax;
+
 	vcpu->arch.sie_block->icpua = id;
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
@@ -1784,16 +2054,25 @@ void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu)
 	kvm_s390_vcpu_request(vcpu);
 }
 
-static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address)
+static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
+			      unsigned long end)
 {
-	int i;
 	struct kvm *kvm = gmap->private;
 	struct kvm_vcpu *vcpu;
+	unsigned long prefix;
+	int i;
 
+	if (gmap_is_shadow(gmap))
+		return;
+	if (start >= 1UL << 31)
+		/* We are only interested in prefix pages */
+		return;
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		/* match against both prefix pages */
-		if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
-			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
+		prefix = kvm_s390_get_prefix(vcpu);
+		if (prefix <= end && start <= prefix + 2*PAGE_SIZE - 1) {
+			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx-%lx",
+				   start, end);
 			kvm_s390_sync_request(KVM_REQ_MMU_RELOAD, vcpu);
 		}
 	}
@@ -2002,6 +2281,8 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 
 	if (dbg->control & ~VALID_GUESTDBG_FLAGS)
 		return -EINVAL;
+	if (!sclp.has_gpere)
+		return -EINVAL;
 
 	if (dbg->control & KVM_GUESTDBG_ENABLE) {
 		vcpu->guest_debug = dbg->control;
@@ -2070,16 +2351,16 @@ retry:
 		return 0;
 	/*
 	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
-	 * guest prefix page. gmap_ipte_notify will wait on the ptl lock.
+	 * guest prefix page. gmap_mprotect_notify will wait on the ptl lock.
 	 * This ensures that the ipte instruction for this request has
 	 * already finished. We might race against a second unmapper that
 	 * wants to set the blocking bit. Lets just retry the request loop.
 	 */
 	if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
 		int rc;
-		rc = gmap_ipte_notify(vcpu->arch.gmap,
-				      kvm_s390_get_prefix(vcpu),
-				      PAGE_SIZE * 2);
+		rc = gmap_mprotect_notify(vcpu->arch.gmap,
+					  kvm_s390_get_prefix(vcpu),
+					  PAGE_SIZE * 2, PROT_WRITE);
 		if (rc)
 			return rc;
 		goto retry;
@@ -2108,6 +2389,11 @@ retry:
 		goto retry;
 	}
 
+	if (kvm_check_request(KVM_REQ_ICPT_OPEREXC, vcpu)) {
+		vcpu->arch.sie_block->ictl |= ICTL_OPEREXC;
+		goto retry;
+	}
+
 	/* nothing to do, just clear the request */
 	clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
 
@@ -2362,14 +2648,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		 * guest_enter and guest_exit should be no uaccess.
 		 */
 		local_irq_disable();
-		__kvm_guest_enter();
+		guest_enter_irqoff();
 		__disable_cpu_timer_accounting(vcpu);
 		local_irq_enable();
 		exit_reason = sie64a(vcpu->arch.sie_block,
 				     vcpu->run->s.regs.gprs);
 		local_irq_disable();
 		__enable_cpu_timer_accounting(vcpu);
-		__kvm_guest_exit();
+		guest_exit_irqoff();
 		local_irq_enable();
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 
@@ -2598,6 +2884,8 @@ static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
 
 static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 {
+	if (!sclp.has_ibs)
+		return;
 	kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu);
 	kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu);
 }
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 8621ab00ec8e..b8432862a817 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -56,7 +56,7 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
 
 static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
 {
-	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_WAIT;
+	return test_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
 }
 
 static inline int kvm_is_ucontrol(struct kvm *kvm)
@@ -175,6 +175,12 @@ static inline int set_kvm_facility(u64 *fac_list, unsigned long nr)
 	return 0;
 }
 
+static inline int test_kvm_cpu_feat(struct kvm *kvm, unsigned long nr)
+{
+	WARN_ON_ONCE(nr >= KVM_S390_VM_CPU_FEAT_NR_BITS);
+	return test_bit_inv(nr, kvm->arch.cpu_feat);
+}
+
 /* are cpu states controlled by user space */
 static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm)
 {
@@ -232,6 +238,8 @@ static inline void kvm_s390_forward_psw(struct kvm_vcpu *vcpu, int ilen)
 }
 static inline void kvm_s390_retry_instr(struct kvm_vcpu *vcpu)
 {
+	/* don't inject PER events if we re-execute the instruction */
+	vcpu->arch.sie_block->icptstatus &= ~0x02;
 	kvm_s390_rewind_psw(vcpu, kvm_s390_get_ilen(vcpu));
 }
 
@@ -246,10 +254,21 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_eb(struct kvm_vcpu *vcpu);
 
+/* implemented in vsie.c */
+int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu);
+void kvm_s390_vsie_kick(struct kvm_vcpu *vcpu);
+void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
+				 unsigned long end);
+void kvm_s390_vsie_init(struct kvm *kvm);
+void kvm_s390_vsie_destroy(struct kvm *kvm);
+
 /* implemented in sigp.c */
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
 
+/* implemented in sthyi.c */
+int handle_sthyi(struct kvm_vcpu *vcpu);
+
 /* implemented in kvm-s390.c */
 void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod);
 long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
@@ -360,6 +379,7 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu,
 			    struct kvm_guest_debug *dbg);
 void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu);
 void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_per_ifetch_icpt(struct kvm_vcpu *vcpu);
 void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
 
 /* support for Basic/Extended SCA handling */
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 95916fa7c670..46160388e996 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -27,6 +27,7 @@
 #include <asm/io.h>
 #include <asm/ptrace.h>
 #include <asm/compat.h>
+#include <asm/sclp.h>
 #include "gaccess.h"
 #include "kvm-s390.h"
 #include "trace.h"
@@ -152,30 +153,166 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 static int __skey_check_enable(struct kvm_vcpu *vcpu)
 {
 	int rc = 0;
+
+	trace_kvm_s390_skey_related_inst(vcpu);
 	if (!(vcpu->arch.sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)))
 		return rc;
 
 	rc = s390_enable_skey();
-	VCPU_EVENT(vcpu, 3, "%s", "enabling storage keys for guest");
-	trace_kvm_s390_skey_related_inst(vcpu);
-	vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE);
+	VCPU_EVENT(vcpu, 3, "enabling storage keys for guest: %d", rc);
+	if (!rc)
+		vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE);
 	return rc;
 }
 
-
-static int handle_skey(struct kvm_vcpu *vcpu)
+static int try_handle_skey(struct kvm_vcpu *vcpu)
 {
-	int rc = __skey_check_enable(vcpu);
+	int rc;
 
+	vcpu->stat.instruction_storage_key++;
+	rc = __skey_check_enable(vcpu);
 	if (rc)
 		return rc;
-	vcpu->stat.instruction_storage_key++;
-
+	if (sclp.has_skey) {
+		/* with storage-key facility, SIE interprets it for us */
+		kvm_s390_retry_instr(vcpu);
+		VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
+		return -EAGAIN;
+	}
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+	return 0;
+}
 
-	kvm_s390_retry_instr(vcpu);
-	VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
+static int handle_iske(struct kvm_vcpu *vcpu)
+{
+	unsigned long addr;
+	unsigned char key;
+	int reg1, reg2;
+	int rc;
+
+	rc = try_handle_skey(vcpu);
+	if (rc)
+		return rc != -EAGAIN ? rc : 0;
+
+	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
+
+	addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	addr = kvm_s390_logical_to_effective(vcpu, addr);
+	addr = kvm_s390_real_to_abs(vcpu, addr);
+	addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
+	if (kvm_is_error_hva(addr))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+	down_read(&current->mm->mmap_sem);
+	rc = get_guest_storage_key(current->mm, addr, &key);
+	up_read(&current->mm->mmap_sem);
+	if (rc)
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	vcpu->run->s.regs.gprs[reg1] &= ~0xff;
+	vcpu->run->s.regs.gprs[reg1] |= key;
+	return 0;
+}
+
+static int handle_rrbe(struct kvm_vcpu *vcpu)
+{
+	unsigned long addr;
+	int reg1, reg2;
+	int rc;
+
+	rc = try_handle_skey(vcpu);
+	if (rc)
+		return rc != -EAGAIN ? rc : 0;
+
+	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
+
+	addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	addr = kvm_s390_logical_to_effective(vcpu, addr);
+	addr = kvm_s390_real_to_abs(vcpu, addr);
+	addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
+	if (kvm_is_error_hva(addr))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+	down_read(&current->mm->mmap_sem);
+	rc = reset_guest_reference_bit(current->mm, addr);
+	up_read(&current->mm->mmap_sem);
+	if (rc < 0)
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+	kvm_s390_set_psw_cc(vcpu, rc);
+	return 0;
+}
+
+#define SSKE_NQ 0x8
+#define SSKE_MR 0x4
+#define SSKE_MC 0x2
+#define SSKE_MB 0x1
+static int handle_sske(struct kvm_vcpu *vcpu)
+{
+	unsigned char m3 = vcpu->arch.sie_block->ipb >> 28;
+	unsigned long start, end;
+	unsigned char key, oldkey;
+	int reg1, reg2;
+	int rc;
+
+	rc = try_handle_skey(vcpu);
+	if (rc)
+		return rc != -EAGAIN ? rc : 0;
+
+	if (!test_kvm_facility(vcpu->kvm, 8))
+		m3 &= ~SSKE_MB;
+	if (!test_kvm_facility(vcpu->kvm, 10))
+		m3 &= ~(SSKE_MC | SSKE_MR);
+	if (!test_kvm_facility(vcpu->kvm, 14))
+		m3 &= ~SSKE_NQ;
+
+	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
+
+	key = vcpu->run->s.regs.gprs[reg1] & 0xfe;
+	start = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	start = kvm_s390_logical_to_effective(vcpu, start);
+	if (m3 & SSKE_MB) {
+		/* start already designates an absolute address */
+		end = (start + (1UL << 20)) & ~((1UL << 20) - 1);
+	} else {
+		start = kvm_s390_real_to_abs(vcpu, start);
+		end = start + PAGE_SIZE;
+	}
+
+	while (start != end) {
+		unsigned long addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+
+		if (kvm_is_error_hva(addr))
+			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+		down_read(&current->mm->mmap_sem);
+		rc = cond_set_guest_storage_key(current->mm, addr, key, &oldkey,
+						m3 & SSKE_NQ, m3 & SSKE_MR,
+						m3 & SSKE_MC);
+		up_read(&current->mm->mmap_sem);
+		if (rc < 0)
+			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		start += PAGE_SIZE;
+	};
+
+	if (m3 & (SSKE_MC | SSKE_MR)) {
+		if (m3 & SSKE_MB) {
+			/* skey in reg1 is unpredictable */
+			kvm_s390_set_psw_cc(vcpu, 3);
+		} else {
+			kvm_s390_set_psw_cc(vcpu, rc);
+			vcpu->run->s.regs.gprs[reg1] &= ~0xff00UL;
+			vcpu->run->s.regs.gprs[reg1] |= (u64) oldkey << 8;
+		}
+	}
+	if (m3 & SSKE_MB) {
+		if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_64BIT)
+			vcpu->run->s.regs.gprs[reg2] &= ~PAGE_MASK;
+		else
+			vcpu->run->s.regs.gprs[reg2] &= ~0xfffff000UL;
+		end = kvm_s390_logical_to_effective(vcpu, end);
+		vcpu->run->s.regs.gprs[reg2] |= end;
+	}
 	return 0;
 }
 
@@ -582,10 +719,11 @@ static const intercept_handler_t b2_handlers[256] = {
 	[0x10] = handle_set_prefix,
 	[0x11] = handle_store_prefix,
 	[0x12] = handle_store_cpu_address,
+	[0x14] = kvm_s390_handle_vsie,
 	[0x21] = handle_ipte_interlock,
-	[0x29] = handle_skey,
-	[0x2a] = handle_skey,
-	[0x2b] = handle_skey,
+	[0x29] = handle_iske,
+	[0x2a] = handle_rrbe,
+	[0x2b] = handle_sske,
 	[0x2c] = handle_test_block,
 	[0x30] = handle_io_inst,
 	[0x31] = handle_io_inst,
@@ -654,8 +792,10 @@ static int handle_epsw(struct kvm_vcpu *vcpu)
 
 static int handle_pfmf(struct kvm_vcpu *vcpu)
 {
+	bool mr = false, mc = false, nq;
 	int reg1, reg2;
 	unsigned long start, end;
+	unsigned char key;
 
 	vcpu->stat.instruction_pfmf++;
 
@@ -675,15 +815,27 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 	    !test_kvm_facility(vcpu->kvm, 14))
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	/* No support for conditional-SSKE */
-	if (vcpu->run->s.regs.gprs[reg1] & (PFMF_MR | PFMF_MC))
-		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+	/* Only provide conditional-SSKE support if enabled for the guest */
+	if (vcpu->run->s.regs.gprs[reg1] & PFMF_SK &&
+	    test_kvm_facility(vcpu->kvm, 10)) {
+		mr = vcpu->run->s.regs.gprs[reg1] & PFMF_MR;
+		mc = vcpu->run->s.regs.gprs[reg1] & PFMF_MC;
+	}
 
+	nq = vcpu->run->s.regs.gprs[reg1] & PFMF_NQ;
+	key = vcpu->run->s.regs.gprs[reg1] & PFMF_KEY;
 	start = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
 	start = kvm_s390_logical_to_effective(vcpu, start);
 
+	if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
+		if (kvm_s390_check_low_addr_prot_real(vcpu, start))
+			return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
+	}
+
 	switch (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
 	case 0x00000000:
+		/* only 4k frames specify a real address */
+		start = kvm_s390_real_to_abs(vcpu, start);
 		end = (start + (1UL << 12)) & ~((1UL << 12) - 1);
 		break;
 	case 0x00001000:
@@ -701,20 +853,11 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 	}
 
-	if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
-		if (kvm_s390_check_low_addr_prot_real(vcpu, start))
-			return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
-	}
-
-	while (start < end) {
-		unsigned long useraddr, abs_addr;
+	while (start != end) {
+		unsigned long useraddr;
 
 		/* Translate guest address to host address */
-		if ((vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) == 0)
-			abs_addr = kvm_s390_real_to_abs(vcpu, start);
-		else
-			abs_addr = start;
-		useraddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(abs_addr));
+		useraddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
 		if (kvm_is_error_hva(useraddr))
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
@@ -728,16 +871,25 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 
 			if (rc)
 				return rc;
-			if (set_guest_storage_key(current->mm, useraddr,
-					vcpu->run->s.regs.gprs[reg1] & PFMF_KEY,
-					vcpu->run->s.regs.gprs[reg1] & PFMF_NQ))
+			down_read(&current->mm->mmap_sem);
+			rc = cond_set_guest_storage_key(current->mm, useraddr,
+							key, NULL, nq, mr, mc);
+			up_read(&current->mm->mmap_sem);
+			if (rc < 0)
 				return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 		}
 
 		start += PAGE_SIZE;
 	}
-	if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC)
-		vcpu->run->s.regs.gprs[reg2] = end;
+	if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
+		if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_64BIT) {
+			vcpu->run->s.regs.gprs[reg2] = end;
+		} else {
+			vcpu->run->s.regs.gprs[reg2] &= ~0xffffffffUL;
+			end = kvm_s390_logical_to_effective(vcpu, end);
+			vcpu->run->s.regs.gprs[reg2] |= end;
+		}
+	}
 	return 0;
 }
 
@@ -1033,7 +1185,15 @@ static int handle_sckpf(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int handle_ptff(struct kvm_vcpu *vcpu)
+{
+	/* we don't emulate any control instructions yet */
+	kvm_s390_set_psw_cc(vcpu, 3);
+	return 0;
+}
+
 static const intercept_handler_t x01_handlers[256] = {
+	[0x04] = handle_ptff,
 	[0x07] = handle_sckpf,
 };
 
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 28ea0cab1f1b..1a252f537081 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -77,18 +77,18 @@ static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu,
 	const u64 psw_int_mask = PSW_MASK_IO | PSW_MASK_EXT;
 	u16 p_asn, s_asn;
 	psw_t *psw;
-	u32 flags;
+	bool idle;
 
-	flags = atomic_read(&dst_vcpu->arch.sie_block->cpuflags);
+	idle = is_vcpu_idle(vcpu);
 	psw = &dst_vcpu->arch.sie_block->gpsw;
 	p_asn = dst_vcpu->arch.sie_block->gcr[4] & 0xffff;  /* Primary ASN */
 	s_asn = dst_vcpu->arch.sie_block->gcr[3] & 0xffff;  /* Secondary ASN */
 
 	/* Inject the emergency signal? */
-	if (!(flags & CPUSTAT_STOPPED)
+	if (!is_vcpu_stopped(vcpu)
 	    || (psw->mask & psw_int_mask) != psw_int_mask
-	    || ((flags & CPUSTAT_WAIT) && psw->addr != 0)
-	    || (!(flags & CPUSTAT_WAIT) && (asn == p_asn || asn == s_asn))) {
+	    || (idle && psw->addr != 0)
+	    || (!idle && (asn == p_asn || asn == s_asn))) {
 		return __inject_sigp_emergency(vcpu, dst_vcpu);
 	} else {
 		*reg &= 0xffffffff00000000UL;
diff --git a/arch/s390/kvm/sthyi.c b/arch/s390/kvm/sthyi.c
new file mode 100644
index 000000000000..bd98b7d25200
--- /dev/null
+++ b/arch/s390/kvm/sthyi.c
@@ -0,0 +1,471 @@
+/*
+ * store hypervisor information instruction emulation functions.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Copyright IBM Corp. 2016
+ * Author(s): Janosch Frank <frankja@linux.vnet.ibm.com>
+ */
+#include <linux/kvm_host.h>
+#include <linux/errno.h>
+#include <linux/pagemap.h>
+#include <linux/vmalloc.h>
+#include <linux/ratelimit.h>
+
+#include <asm/kvm_host.h>
+#include <asm/asm-offsets.h>
+#include <asm/sclp.h>
+#include <asm/diag.h>
+#include <asm/sysinfo.h>
+#include <asm/ebcdic.h>
+
+#include "kvm-s390.h"
+#include "gaccess.h"
+#include "trace.h"
+
+#define DED_WEIGHT 0xffff
+/*
+ * CP and IFL as EBCDIC strings, SP/0x40 determines the end of string
+ * as they are justified with spaces.
+ */
+#define CP  0xc3d7404040404040UL
+#define IFL 0xc9c6d34040404040UL
+
+enum hdr_flags {
+	HDR_NOT_LPAR   = 0x10,
+	HDR_STACK_INCM = 0x20,
+	HDR_STSI_UNAV  = 0x40,
+	HDR_PERF_UNAV  = 0x80,
+};
+
+enum mac_validity {
+	MAC_NAME_VLD = 0x20,
+	MAC_ID_VLD   = 0x40,
+	MAC_CNT_VLD  = 0x80,
+};
+
+enum par_flag {
+	PAR_MT_EN = 0x80,
+};
+
+enum par_validity {
+	PAR_GRP_VLD  = 0x08,
+	PAR_ID_VLD   = 0x10,
+	PAR_ABS_VLD  = 0x20,
+	PAR_WGHT_VLD = 0x40,
+	PAR_PCNT_VLD  = 0x80,
+};
+
+struct hdr_sctn {
+	u8 infhflg1;
+	u8 infhflg2; /* reserved */
+	u8 infhval1; /* reserved */
+	u8 infhval2; /* reserved */
+	u8 reserved[3];
+	u8 infhygct;
+	u16 infhtotl;
+	u16 infhdln;
+	u16 infmoff;
+	u16 infmlen;
+	u16 infpoff;
+	u16 infplen;
+	u16 infhoff1;
+	u16 infhlen1;
+	u16 infgoff1;
+	u16 infglen1;
+	u16 infhoff2;
+	u16 infhlen2;
+	u16 infgoff2;
+	u16 infglen2;
+	u16 infhoff3;
+	u16 infhlen3;
+	u16 infgoff3;
+	u16 infglen3;
+	u8 reserved2[4];
+} __packed;
+
+struct mac_sctn {
+	u8 infmflg1; /* reserved */
+	u8 infmflg2; /* reserved */
+	u8 infmval1;
+	u8 infmval2; /* reserved */
+	u16 infmscps;
+	u16 infmdcps;
+	u16 infmsifl;
+	u16 infmdifl;
+	char infmname[8];
+	char infmtype[4];
+	char infmmanu[16];
+	char infmseq[16];
+	char infmpman[4];
+	u8 reserved[4];
+} __packed;
+
+struct par_sctn {
+	u8 infpflg1;
+	u8 infpflg2; /* reserved */
+	u8 infpval1;
+	u8 infpval2; /* reserved */
+	u16 infppnum;
+	u16 infpscps;
+	u16 infpdcps;
+	u16 infpsifl;
+	u16 infpdifl;
+	u16 reserved;
+	char infppnam[8];
+	u32 infpwbcp;
+	u32 infpabcp;
+	u32 infpwbif;
+	u32 infpabif;
+	char infplgnm[8];
+	u32 infplgcp;
+	u32 infplgif;
+} __packed;
+
+struct sthyi_sctns {
+	struct hdr_sctn hdr;
+	struct mac_sctn mac;
+	struct par_sctn par;
+} __packed;
+
+struct cpu_inf {
+	u64 lpar_cap;
+	u64 lpar_grp_cap;
+	u64 lpar_weight;
+	u64 all_weight;
+	int cpu_num_ded;
+	int cpu_num_shd;
+};
+
+struct lpar_cpu_inf {
+	struct cpu_inf cp;
+	struct cpu_inf ifl;
+};
+
+static inline u64 cpu_id(u8 ctidx, void *diag224_buf)
+{
+	return *((u64 *)(diag224_buf + (ctidx + 1) * DIAG204_CPU_NAME_LEN));
+}
+
+/*
+ * Scales the cpu capping from the lpar range to the one expected in
+ * sthyi data.
+ *
+ * diag204 reports a cap in hundredths of processor units.
+ * z/VM's range for one core is 0 - 0x10000.
+ */
+static u32 scale_cap(u32 in)
+{
+	return (0x10000 * in) / 100;
+}
+
+static void fill_hdr(struct sthyi_sctns *sctns)
+{
+	sctns->hdr.infhdln = sizeof(sctns->hdr);
+	sctns->hdr.infmoff = sizeof(sctns->hdr);
+	sctns->hdr.infmlen = sizeof(sctns->mac);
+	sctns->hdr.infplen = sizeof(sctns->par);
+	sctns->hdr.infpoff = sctns->hdr.infhdln + sctns->hdr.infmlen;
+	sctns->hdr.infhtotl = sctns->hdr.infpoff + sctns->hdr.infplen;
+}
+
+static void fill_stsi_mac(struct sthyi_sctns *sctns,
+			  struct sysinfo_1_1_1 *sysinfo)
+{
+	if (stsi(sysinfo, 1, 1, 1))
+		return;
+
+	sclp_ocf_cpc_name_copy(sctns->mac.infmname);
+
+	memcpy(sctns->mac.infmtype, sysinfo->type, sizeof(sctns->mac.infmtype));
+	memcpy(sctns->mac.infmmanu, sysinfo->manufacturer, sizeof(sctns->mac.infmmanu));
+	memcpy(sctns->mac.infmpman, sysinfo->plant, sizeof(sctns->mac.infmpman));
+	memcpy(sctns->mac.infmseq, sysinfo->sequence, sizeof(sctns->mac.infmseq));
+
+	sctns->mac.infmval1 |= MAC_ID_VLD | MAC_NAME_VLD;
+}
+
+static void fill_stsi_par(struct sthyi_sctns *sctns,
+			  struct sysinfo_2_2_2 *sysinfo)
+{
+	if (stsi(sysinfo, 2, 2, 2))
+		return;
+
+	sctns->par.infppnum = sysinfo->lpar_number;
+	memcpy(sctns->par.infppnam, sysinfo->name, sizeof(sctns->par.infppnam));
+
+	sctns->par.infpval1 |= PAR_ID_VLD;
+}
+
+static void fill_stsi(struct sthyi_sctns *sctns)
+{
+	void *sysinfo;
+
+	/* Errors are handled through the validity bits in the response. */
+	sysinfo = (void *)__get_free_page(GFP_KERNEL);
+	if (!sysinfo)
+		return;
+
+	fill_stsi_mac(sctns, sysinfo);
+	fill_stsi_par(sctns, sysinfo);
+
+	free_pages((unsigned long)sysinfo, 0);
+}
+
+static void fill_diag_mac(struct sthyi_sctns *sctns,
+			  struct diag204_x_phys_block *block,
+			  void *diag224_buf)
+{
+	int i;
+
+	for (i = 0; i < block->hdr.cpus; i++) {
+		switch (cpu_id(block->cpus[i].ctidx, diag224_buf)) {
+		case CP:
+			if (block->cpus[i].weight == DED_WEIGHT)
+				sctns->mac.infmdcps++;
+			else
+				sctns->mac.infmscps++;
+			break;
+		case IFL:
+			if (block->cpus[i].weight == DED_WEIGHT)
+				sctns->mac.infmdifl++;
+			else
+				sctns->mac.infmsifl++;
+			break;
+		}
+	}
+	sctns->mac.infmval1 |= MAC_CNT_VLD;
+}
+
+/* Returns a pointer to the the next partition block. */
+static struct diag204_x_part_block *lpar_cpu_inf(struct lpar_cpu_inf *part_inf,
+						 bool this_lpar,
+						 void *diag224_buf,
+						 struct diag204_x_part_block *block)
+{
+	int i, capped = 0, weight_cp = 0, weight_ifl = 0;
+	struct cpu_inf *cpu_inf;
+
+	for (i = 0; i < block->hdr.rcpus; i++) {
+		if (!(block->cpus[i].cflag & DIAG204_CPU_ONLINE))
+			continue;
+
+		switch (cpu_id(block->cpus[i].ctidx, diag224_buf)) {
+		case CP:
+			cpu_inf = &part_inf->cp;
+			if (block->cpus[i].cur_weight < DED_WEIGHT)
+				weight_cp |= block->cpus[i].cur_weight;
+			break;
+		case IFL:
+			cpu_inf = &part_inf->ifl;
+			if (block->cpus[i].cur_weight < DED_WEIGHT)
+				weight_ifl |= block->cpus[i].cur_weight;
+			break;
+		default:
+			continue;
+		}
+
+		if (!this_lpar)
+			continue;
+
+		capped |= block->cpus[i].cflag & DIAG204_CPU_CAPPED;
+		cpu_inf->lpar_cap |= block->cpus[i].cpu_type_cap;
+		cpu_inf->lpar_grp_cap |= block->cpus[i].group_cpu_type_cap;
+
+		if (block->cpus[i].weight == DED_WEIGHT)
+			cpu_inf->cpu_num_ded += 1;
+		else
+			cpu_inf->cpu_num_shd += 1;
+	}
+
+	if (this_lpar && capped) {
+		part_inf->cp.lpar_weight = weight_cp;
+		part_inf->ifl.lpar_weight = weight_ifl;
+	}
+	part_inf->cp.all_weight += weight_cp;
+	part_inf->ifl.all_weight += weight_ifl;
+	return (struct diag204_x_part_block *)&block->cpus[i];
+}
+
+static void fill_diag(struct sthyi_sctns *sctns)
+{
+	int i, r, pages;
+	bool this_lpar;
+	void *diag204_buf;
+	void *diag224_buf = NULL;
+	struct diag204_x_info_blk_hdr *ti_hdr;
+	struct diag204_x_part_block *part_block;
+	struct diag204_x_phys_block *phys_block;
+	struct lpar_cpu_inf lpar_inf = {};
+
+	/* Errors are handled through the validity bits in the response. */
+	pages = diag204((unsigned long)DIAG204_SUBC_RSI |
+			(unsigned long)DIAG204_INFO_EXT, 0, NULL);
+	if (pages <= 0)
+		return;
+
+	diag204_buf = vmalloc(PAGE_SIZE * pages);
+	if (!diag204_buf)
+		return;
+
+	r = diag204((unsigned long)DIAG204_SUBC_STIB7 |
+		    (unsigned long)DIAG204_INFO_EXT, pages, diag204_buf);
+	if (r < 0)
+		goto out;
+
+	diag224_buf = kmalloc(PAGE_SIZE, GFP_KERNEL | GFP_DMA);
+	if (!diag224_buf || diag224(diag224_buf))
+		goto out;
+
+	ti_hdr = diag204_buf;
+	part_block = diag204_buf + sizeof(*ti_hdr);
+
+	for (i = 0; i < ti_hdr->npar; i++) {
+		/*
+		 * For the calling lpar we also need to get the cpu
+		 * caps and weights. The time information block header
+		 * specifies the offset to the partition block of the
+		 * caller lpar, so we know when we process its data.
+		 */
+		this_lpar = (void *)part_block - diag204_buf == ti_hdr->this_part;
+		part_block = lpar_cpu_inf(&lpar_inf, this_lpar, diag224_buf,
+					  part_block);
+	}
+
+	phys_block = (struct diag204_x_phys_block *)part_block;
+	part_block = diag204_buf + ti_hdr->this_part;
+	if (part_block->hdr.mtid)
+		sctns->par.infpflg1 = PAR_MT_EN;
+
+	sctns->par.infpval1 |= PAR_GRP_VLD;
+	sctns->par.infplgcp = scale_cap(lpar_inf.cp.lpar_grp_cap);
+	sctns->par.infplgif = scale_cap(lpar_inf.ifl.lpar_grp_cap);
+	memcpy(sctns->par.infplgnm, part_block->hdr.hardware_group_name,
+	       sizeof(sctns->par.infplgnm));
+
+	sctns->par.infpscps = lpar_inf.cp.cpu_num_shd;
+	sctns->par.infpdcps = lpar_inf.cp.cpu_num_ded;
+	sctns->par.infpsifl = lpar_inf.ifl.cpu_num_shd;
+	sctns->par.infpdifl = lpar_inf.ifl.cpu_num_ded;
+	sctns->par.infpval1 |= PAR_PCNT_VLD;
+
+	sctns->par.infpabcp = scale_cap(lpar_inf.cp.lpar_cap);
+	sctns->par.infpabif = scale_cap(lpar_inf.ifl.lpar_cap);
+	sctns->par.infpval1 |= PAR_ABS_VLD;
+
+	/*
+	 * Everything below needs global performance data to be
+	 * meaningful.
+	 */
+	if (!(ti_hdr->flags & DIAG204_LPAR_PHYS_FLG)) {
+		sctns->hdr.infhflg1 |= HDR_PERF_UNAV;
+		goto out;
+	}
+
+	fill_diag_mac(sctns, phys_block, diag224_buf);
+
+	if (lpar_inf.cp.lpar_weight) {
+		sctns->par.infpwbcp = sctns->mac.infmscps * 0x10000 *
+			lpar_inf.cp.lpar_weight / lpar_inf.cp.all_weight;
+	}
+
+	if (lpar_inf.ifl.lpar_weight) {
+		sctns->par.infpwbif = sctns->mac.infmsifl * 0x10000 *
+			lpar_inf.ifl.lpar_weight / lpar_inf.ifl.all_weight;
+	}
+	sctns->par.infpval1 |= PAR_WGHT_VLD;
+
+out:
+	kfree(diag224_buf);
+	vfree(diag204_buf);
+}
+
+static int sthyi(u64 vaddr)
+{
+	register u64 code asm("0") = 0;
+	register u64 addr asm("2") = vaddr;
+	int cc;
+
+	asm volatile(
+		".insn   rre,0xB2560000,%[code],%[addr]\n"
+		"ipm     %[cc]\n"
+		"srl     %[cc],28\n"
+		: [cc] "=d" (cc)
+		: [code] "d" (code), [addr] "a" (addr)
+		: "memory", "cc");
+	return cc;
+}
+
+int handle_sthyi(struct kvm_vcpu *vcpu)
+{
+	int reg1, reg2, r = 0;
+	u64 code, addr, cc = 0;
+	struct sthyi_sctns *sctns = NULL;
+
+	/*
+	 * STHYI requires extensive locking in the higher hypervisors
+	 * and is very computational/memory expensive. Therefore we
+	 * ratelimit the executions per VM.
+	 */
+	if (!__ratelimit(&vcpu->kvm->arch.sthyi_limit)) {
+		kvm_s390_retry_instr(vcpu);
+		return 0;
+	}
+
+	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
+	code = vcpu->run->s.regs.gprs[reg1];
+	addr = vcpu->run->s.regs.gprs[reg2];
+
+	vcpu->stat.instruction_sthyi++;
+	VCPU_EVENT(vcpu, 3, "STHYI: fc: %llu addr: 0x%016llx", code, addr);
+	trace_kvm_s390_handle_sthyi(vcpu, code, addr);
+
+	if (reg1 == reg2 || reg1 & 1 || reg2 & 1 || addr & ~PAGE_MASK)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	if (code & 0xffff) {
+		cc = 3;
+		goto out;
+	}
+
+	/*
+	 * If the page has not yet been faulted in, we want to do that
+	 * now and not after all the expensive calculations.
+	 */
+	r = write_guest(vcpu, addr, reg2, &cc, 1);
+	if (r)
+		return kvm_s390_inject_prog_cond(vcpu, r);
+
+	sctns = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!sctns)
+		return -ENOMEM;
+
+	/*
+	 * If we are a guest, we don't want to emulate an emulated
+	 * instruction. We ask the hypervisor to provide the data.
+	 */
+	if (test_facility(74)) {
+		cc = sthyi((u64)sctns);
+		goto out;
+	}
+
+	fill_hdr(sctns);
+	fill_stsi(sctns);
+	fill_diag(sctns);
+
+out:
+	if (!cc) {
+		r = write_guest(vcpu, addr, reg2, sctns, PAGE_SIZE);
+		if (r) {
+			free_page((unsigned long)sctns);
+			return kvm_s390_inject_prog_cond(vcpu, r);
+		}
+	}
+
+	free_page((unsigned long)sctns);
+	vcpu->run->s.regs.gprs[reg2 + 1] = cc ? 4 : 0;
+	kvm_s390_set_psw_cc(vcpu, cc);
+	return r;
+}
diff --git a/arch/s390/kvm/trace.h b/arch/s390/kvm/trace.h
index 916834d7a73a..4fc9d4e5be89 100644
--- a/arch/s390/kvm/trace.h
+++ b/arch/s390/kvm/trace.h
@@ -41,7 +41,7 @@ TRACE_EVENT(kvm_s390_skey_related_inst,
 	    TP_fast_assign(
 		    VCPU_ASSIGN_COMMON
 		    ),
-	    VCPU_TP_PRINTK("%s", "first instruction related to skeys on vcpu")
+	    VCPU_TP_PRINTK("%s", "storage key related instruction")
 	);
 
 TRACE_EVENT(kvm_s390_major_guest_pfault,
@@ -185,8 +185,10 @@ TRACE_EVENT(kvm_s390_intercept_prog,
 		    __entry->code = code;
 		    ),
 
-	    VCPU_TP_PRINTK("intercepted program interruption %04x",
-			   __entry->code)
+	    VCPU_TP_PRINTK("intercepted program interruption %04x (%s)",
+			   __entry->code,
+			   __print_symbolic(__entry->code,
+					    icpt_prog_codes))
 	);
 
 /*
@@ -412,6 +414,47 @@ TRACE_EVENT(kvm_s390_handle_stsi,
 			   __entry->addr)
 	);
 
+TRACE_EVENT(kvm_s390_handle_operexc,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u16 ipa, __u32 ipb),
+	    TP_ARGS(VCPU_ARGS_COMMON, ipa, ipb),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u64, instruction)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->instruction = ((__u64)ipa << 48) |
+		    ((__u64)ipb << 16);
+		    ),
+
+	    VCPU_TP_PRINTK("operation exception on instruction %016llx (%s)",
+			   __entry->instruction,
+			   __print_symbolic(icpt_insn_decoder(__entry->instruction),
+					    icpt_insn_codes))
+	);
+
+TRACE_EVENT(kvm_s390_handle_sthyi,
+	    TP_PROTO(VCPU_PROTO_COMMON, u64 code, u64 addr),
+	    TP_ARGS(VCPU_ARGS_COMMON, code, addr),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(u64, code)
+		    __field(u64, addr)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->code = code;
+		    __entry->addr = addr;
+		    ),
+
+	    VCPU_TP_PRINTK("STHYI fc: %llu addr: %016llx",
+			   __entry->code, __entry->addr)
+	);
+
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
new file mode 100644
index 000000000000..c106488b4137
--- /dev/null
+++ b/arch/s390/kvm/vsie.c
@@ -0,0 +1,1091 @@
+/*
+ * kvm nested virtualization support for s390x
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): David Hildenbrand <dahi@linux.vnet.ibm.com>
+ */
+#include <linux/vmalloc.h>
+#include <linux/kvm_host.h>
+#include <linux/bug.h>
+#include <linux/list.h>
+#include <linux/bitmap.h>
+#include <asm/gmap.h>
+#include <asm/mmu_context.h>
+#include <asm/sclp.h>
+#include <asm/nmi.h>
+#include <asm/dis.h>
+#include "kvm-s390.h"
+#include "gaccess.h"
+
+struct vsie_page {
+	struct kvm_s390_sie_block scb_s;	/* 0x0000 */
+	/* the pinned originial scb */
+	struct kvm_s390_sie_block *scb_o;	/* 0x0200 */
+	/* the shadow gmap in use by the vsie_page */
+	struct gmap *gmap;			/* 0x0208 */
+	/* address of the last reported fault to guest2 */
+	unsigned long fault_addr;		/* 0x0210 */
+	__u8 reserved[0x0700 - 0x0218];		/* 0x0218 */
+	struct kvm_s390_crypto_cb crycb;	/* 0x0700 */
+	__u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE];	/* 0x0800 */
+} __packed;
+
+/* trigger a validity icpt for the given scb */
+static int set_validity_icpt(struct kvm_s390_sie_block *scb,
+			     __u16 reason_code)
+{
+	scb->ipa = 0x1000;
+	scb->ipb = ((__u32) reason_code) << 16;
+	scb->icptcode = ICPT_VALIDITY;
+	return 1;
+}
+
+/* mark the prefix as unmapped, this will block the VSIE */
+static void prefix_unmapped(struct vsie_page *vsie_page)
+{
+	atomic_or(PROG_REQUEST, &vsie_page->scb_s.prog20);
+}
+
+/* mark the prefix as unmapped and wait until the VSIE has been left */
+static void prefix_unmapped_sync(struct vsie_page *vsie_page)
+{
+	prefix_unmapped(vsie_page);
+	if (vsie_page->scb_s.prog0c & PROG_IN_SIE)
+		atomic_or(CPUSTAT_STOP_INT, &vsie_page->scb_s.cpuflags);
+	while (vsie_page->scb_s.prog0c & PROG_IN_SIE)
+		cpu_relax();
+}
+
+/* mark the prefix as mapped, this will allow the VSIE to run */
+static void prefix_mapped(struct vsie_page *vsie_page)
+{
+	atomic_andnot(PROG_REQUEST, &vsie_page->scb_s.prog20);
+}
+
+/* test if the prefix is mapped into the gmap shadow */
+static int prefix_is_mapped(struct vsie_page *vsie_page)
+{
+	return !(atomic_read(&vsie_page->scb_s.prog20) & PROG_REQUEST);
+}
+
+/* copy the updated intervention request bits into the shadow scb */
+static void update_intervention_requests(struct vsie_page *vsie_page)
+{
+	const int bits = CPUSTAT_STOP_INT | CPUSTAT_IO_INT | CPUSTAT_EXT_INT;
+	int cpuflags;
+
+	cpuflags = atomic_read(&vsie_page->scb_o->cpuflags);
+	atomic_andnot(bits, &vsie_page->scb_s.cpuflags);
+	atomic_or(cpuflags & bits, &vsie_page->scb_s.cpuflags);
+}
+
+/* shadow (filter and validate) the cpuflags  */
+static int prepare_cpuflags(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	int newflags, cpuflags = atomic_read(&scb_o->cpuflags);
+
+	/* we don't allow ESA/390 guests */
+	if (!(cpuflags & CPUSTAT_ZARCH))
+		return set_validity_icpt(scb_s, 0x0001U);
+
+	if (cpuflags & (CPUSTAT_RRF | CPUSTAT_MCDS))
+		return set_validity_icpt(scb_s, 0x0001U);
+	else if (cpuflags & (CPUSTAT_SLSV | CPUSTAT_SLSR))
+		return set_validity_icpt(scb_s, 0x0007U);
+
+	/* intervention requests will be set later */
+	newflags = CPUSTAT_ZARCH;
+	if (cpuflags & CPUSTAT_GED && test_kvm_facility(vcpu->kvm, 8))
+		newflags |= CPUSTAT_GED;
+	if (cpuflags & CPUSTAT_GED2 && test_kvm_facility(vcpu->kvm, 78)) {
+		if (cpuflags & CPUSTAT_GED)
+			return set_validity_icpt(scb_s, 0x0001U);
+		newflags |= CPUSTAT_GED2;
+	}
+	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_GPERE))
+		newflags |= cpuflags & CPUSTAT_P;
+	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_GSLS))
+		newflags |= cpuflags & CPUSTAT_SM;
+	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_IBS))
+		newflags |= cpuflags & CPUSTAT_IBS;
+
+	atomic_set(&scb_s->cpuflags, newflags);
+	return 0;
+}
+
+/*
+ * Create a shadow copy of the crycb block and setup key wrapping, if
+ * requested for guest 3 and enabled for guest 2.
+ *
+ * We only accept format-1 (no AP in g2), but convert it into format-2
+ * There is nothing to do for format-0.
+ *
+ * Returns: - 0 if shadowed or nothing to do
+ *          - > 0 if control has to be given to guest 2
+ */
+static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	u32 crycb_addr = scb_o->crycbd & 0x7ffffff8U;
+	unsigned long *b1, *b2;
+	u8 ecb3_flags;
+
+	scb_s->crycbd = 0;
+	if (!(scb_o->crycbd & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1))
+		return 0;
+	/* format-1 is supported with message-security-assist extension 3 */
+	if (!test_kvm_facility(vcpu->kvm, 76))
+		return 0;
+	/* we may only allow it if enabled for guest 2 */
+	ecb3_flags = scb_o->ecb3 & vcpu->arch.sie_block->ecb3 &
+		     (ECB3_AES | ECB3_DEA);
+	if (!ecb3_flags)
+		return 0;
+
+	if ((crycb_addr & PAGE_MASK) != ((crycb_addr + 128) & PAGE_MASK))
+		return set_validity_icpt(scb_s, 0x003CU);
+	else if (!crycb_addr)
+		return set_validity_icpt(scb_s, 0x0039U);
+
+	/* copy only the wrapping keys */
+	if (read_guest_real(vcpu, crycb_addr + 72, &vsie_page->crycb, 56))
+		return set_validity_icpt(scb_s, 0x0035U);
+
+	scb_s->ecb3 |= ecb3_flags;
+	scb_s->crycbd = ((__u32)(__u64) &vsie_page->crycb) | CRYCB_FORMAT1 |
+			CRYCB_FORMAT2;
+
+	/* xor both blocks in one run */
+	b1 = (unsigned long *) vsie_page->crycb.dea_wrapping_key_mask;
+	b2 = (unsigned long *)
+			    vcpu->kvm->arch.crypto.crycb->dea_wrapping_key_mask;
+	/* as 56%8 == 0, bitmap_xor won't overwrite any data */
+	bitmap_xor(b1, b1, b2, BITS_PER_BYTE * 56);
+	return 0;
+}
+
+/* shadow (round up/down) the ibc to avoid validity icpt */
+static void prepare_ibc(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	__u64 min_ibc = (sclp.ibc >> 16) & 0x0fffU;
+
+	scb_s->ibc = 0;
+	/* ibc installed in g2 and requested for g3 */
+	if (vcpu->kvm->arch.model.ibc && (scb_o->ibc & 0x0fffU)) {
+		scb_s->ibc = scb_o->ibc & 0x0fffU;
+		/* takte care of the minimum ibc level of the machine */
+		if (scb_s->ibc < min_ibc)
+			scb_s->ibc = min_ibc;
+		/* take care of the maximum ibc level set for the guest */
+		if (scb_s->ibc > vcpu->kvm->arch.model.ibc)
+			scb_s->ibc = vcpu->kvm->arch.model.ibc;
+	}
+}
+
+/* unshadow the scb, copying parameters back to the real scb */
+static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+
+	/* interception */
+	scb_o->icptcode = scb_s->icptcode;
+	scb_o->icptstatus = scb_s->icptstatus;
+	scb_o->ipa = scb_s->ipa;
+	scb_o->ipb = scb_s->ipb;
+	scb_o->gbea = scb_s->gbea;
+
+	/* timer */
+	scb_o->cputm = scb_s->cputm;
+	scb_o->ckc = scb_s->ckc;
+	scb_o->todpr = scb_s->todpr;
+
+	/* guest state */
+	scb_o->gpsw = scb_s->gpsw;
+	scb_o->gg14 = scb_s->gg14;
+	scb_o->gg15 = scb_s->gg15;
+	memcpy(scb_o->gcr, scb_s->gcr, 128);
+	scb_o->pp = scb_s->pp;
+
+	/* interrupt intercept */
+	switch (scb_s->icptcode) {
+	case ICPT_PROGI:
+	case ICPT_INSTPROGI:
+	case ICPT_EXTINT:
+		memcpy((void *)((u64)scb_o + 0xc0),
+		       (void *)((u64)scb_s + 0xc0), 0xf0 - 0xc0);
+		break;
+	case ICPT_PARTEXEC:
+		/* MVPG only */
+		memcpy((void *)((u64)scb_o + 0xc0),
+		       (void *)((u64)scb_s + 0xc0), 0xd0 - 0xc0);
+		break;
+	}
+
+	if (scb_s->ihcpu != 0xffffU)
+		scb_o->ihcpu = scb_s->ihcpu;
+}
+
+/*
+ * Setup the shadow scb by copying and checking the relevant parts of the g2
+ * provided scb.
+ *
+ * Returns: - 0 if the scb has been shadowed
+ *          - > 0 if control has to be given to guest 2
+ */
+static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	bool had_tx = scb_s->ecb & 0x10U;
+	unsigned long new_mso = 0;
+	int rc;
+
+	/* make sure we don't have any leftovers when reusing the scb */
+	scb_s->icptcode = 0;
+	scb_s->eca = 0;
+	scb_s->ecb = 0;
+	scb_s->ecb2 = 0;
+	scb_s->ecb3 = 0;
+	scb_s->ecd = 0;
+	scb_s->fac = 0;
+
+	rc = prepare_cpuflags(vcpu, vsie_page);
+	if (rc)
+		goto out;
+
+	/* timer */
+	scb_s->cputm = scb_o->cputm;
+	scb_s->ckc = scb_o->ckc;
+	scb_s->todpr = scb_o->todpr;
+	scb_s->epoch = scb_o->epoch;
+
+	/* guest state */
+	scb_s->gpsw = scb_o->gpsw;
+	scb_s->gg14 = scb_o->gg14;
+	scb_s->gg15 = scb_o->gg15;
+	memcpy(scb_s->gcr, scb_o->gcr, 128);
+	scb_s->pp = scb_o->pp;
+
+	/* interception / execution handling */
+	scb_s->gbea = scb_o->gbea;
+	scb_s->lctl = scb_o->lctl;
+	scb_s->svcc = scb_o->svcc;
+	scb_s->ictl = scb_o->ictl;
+	/*
+	 * SKEY handling functions can't deal with false setting of PTE invalid
+	 * bits. Therefore we cannot provide interpretation and would later
+	 * have to provide own emulation handlers.
+	 */
+	scb_s->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
+	scb_s->icpua = scb_o->icpua;
+
+	if (!(atomic_read(&scb_s->cpuflags) & CPUSTAT_SM))
+		new_mso = scb_o->mso & 0xfffffffffff00000UL;
+	/* if the hva of the prefix changes, we have to remap the prefix */
+	if (scb_s->mso != new_mso || scb_s->prefix != scb_o->prefix)
+		prefix_unmapped(vsie_page);
+	 /* SIE will do mso/msl validity and exception checks for us */
+	scb_s->msl = scb_o->msl & 0xfffffffffff00000UL;
+	scb_s->mso = new_mso;
+	scb_s->prefix = scb_o->prefix;
+
+	/* We have to definetly flush the tlb if this scb never ran */
+	if (scb_s->ihcpu != 0xffffU)
+		scb_s->ihcpu = scb_o->ihcpu;
+
+	/* MVPG and Protection Exception Interpretation are always available */
+	scb_s->eca |= scb_o->eca & 0x01002000U;
+	/* Host-protection-interruption introduced with ESOP */
+	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP))
+		scb_s->ecb |= scb_o->ecb & 0x02U;
+	/* transactional execution */
+	if (test_kvm_facility(vcpu->kvm, 73)) {
+		/* remap the prefix is tx is toggled on */
+		if ((scb_o->ecb & 0x10U) && !had_tx)
+			prefix_unmapped(vsie_page);
+		scb_s->ecb |= scb_o->ecb & 0x10U;
+	}
+	/* SIMD */
+	if (test_kvm_facility(vcpu->kvm, 129)) {
+		scb_s->eca |= scb_o->eca & 0x00020000U;
+		scb_s->ecd |= scb_o->ecd & 0x20000000U;
+	}
+	/* Run-time-Instrumentation */
+	if (test_kvm_facility(vcpu->kvm, 64))
+		scb_s->ecb3 |= scb_o->ecb3 & 0x01U;
+	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_SIIF))
+		scb_s->eca |= scb_o->eca & 0x00000001U;
+	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_IB))
+		scb_s->eca |= scb_o->eca & 0x40000000U;
+	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_CEI))
+		scb_s->eca |= scb_o->eca & 0x80000000U;
+
+	prepare_ibc(vcpu, vsie_page);
+	rc = shadow_crycb(vcpu, vsie_page);
+out:
+	if (rc)
+		unshadow_scb(vcpu, vsie_page);
+	return rc;
+}
+
+void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
+				 unsigned long end)
+{
+	struct kvm *kvm = gmap->private;
+	struct vsie_page *cur;
+	unsigned long prefix;
+	struct page *page;
+	int i;
+
+	if (!gmap_is_shadow(gmap))
+		return;
+	if (start >= 1UL << 31)
+		/* We are only interested in prefix pages */
+		return;
+
+	/*
+	 * Only new shadow blocks are added to the list during runtime,
+	 * therefore we can safely reference them all the time.
+	 */
+	for (i = 0; i < kvm->arch.vsie.page_count; i++) {
+		page = READ_ONCE(kvm->arch.vsie.pages[i]);
+		if (!page)
+			continue;
+		cur = page_to_virt(page);
+		if (READ_ONCE(cur->gmap) != gmap)
+			continue;
+		prefix = cur->scb_s.prefix << GUEST_PREFIX_SHIFT;
+		/* with mso/msl, the prefix lies at an offset */
+		prefix += cur->scb_s.mso;
+		if (prefix <= end && start <= prefix + 2 * PAGE_SIZE - 1)
+			prefix_unmapped_sync(cur);
+	}
+}
+
+/*
+ * Map the first prefix page and if tx is enabled also the second prefix page.
+ *
+ * The prefix will be protected, a gmap notifier will inform about unmaps.
+ * The shadow scb must not be executed until the prefix is remapped, this is
+ * guaranteed by properly handling PROG_REQUEST.
+ *
+ * Returns: - 0 on if successfully mapped or already mapped
+ *          - > 0 if control has to be given to guest 2
+ *          - -EAGAIN if the caller can retry immediately
+ *          - -ENOMEM if out of memory
+ */
+static int map_prefix(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	u64 prefix = scb_s->prefix << GUEST_PREFIX_SHIFT;
+	int rc;
+
+	if (prefix_is_mapped(vsie_page))
+		return 0;
+
+	/* mark it as mapped so we can catch any concurrent unmappers */
+	prefix_mapped(vsie_page);
+
+	/* with mso/msl, the prefix lies at offset *mso* */
+	prefix += scb_s->mso;
+
+	rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap, prefix);
+	if (!rc && (scb_s->ecb & 0x10U))
+		rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
+					   prefix + PAGE_SIZE);
+	/*
+	 * We don't have to mprotect, we will be called for all unshadows.
+	 * SIE will detect if protection applies and trigger a validity.
+	 */
+	if (rc)
+		prefix_unmapped(vsie_page);
+	if (rc > 0 || rc == -EFAULT)
+		rc = set_validity_icpt(scb_s, 0x0037U);
+	return rc;
+}
+
+/*
+ * Pin the guest page given by gpa and set hpa to the pinned host address.
+ * Will always be pinned writable.
+ *
+ * Returns: - 0 on success
+ *          - -EINVAL if the gpa is not valid guest storage
+ *          - -ENOMEM if out of memory
+ */
+static int pin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t *hpa)
+{
+	struct page *page;
+	hva_t hva;
+	int rc;
+
+	hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
+	if (kvm_is_error_hva(hva))
+		return -EINVAL;
+	rc = get_user_pages_fast(hva, 1, 1, &page);
+	if (rc < 0)
+		return rc;
+	else if (rc != 1)
+		return -ENOMEM;
+	*hpa = (hpa_t) page_to_virt(page) + (gpa & ~PAGE_MASK);
+	return 0;
+}
+
+/* Unpins a page previously pinned via pin_guest_page, marking it as dirty. */
+static void unpin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t hpa)
+{
+	struct page *page;
+
+	page = virt_to_page(hpa);
+	set_page_dirty_lock(page);
+	put_page(page);
+	/* mark the page always as dirty for migration */
+	mark_page_dirty(kvm, gpa_to_gfn(gpa));
+}
+
+/* unpin all blocks previously pinned by pin_blocks(), marking them dirty */
+static void unpin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	hpa_t hpa;
+	gpa_t gpa;
+
+	hpa = (u64) scb_s->scaoh << 32 | scb_s->scaol;
+	if (hpa) {
+		gpa = scb_o->scaol & ~0xfUL;
+		if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO))
+			gpa |= (u64) scb_o->scaoh << 32;
+		unpin_guest_page(vcpu->kvm, gpa, hpa);
+		scb_s->scaol = 0;
+		scb_s->scaoh = 0;
+	}
+
+	hpa = scb_s->itdba;
+	if (hpa) {
+		gpa = scb_o->itdba & ~0xffUL;
+		unpin_guest_page(vcpu->kvm, gpa, hpa);
+		scb_s->itdba = 0;
+	}
+
+	hpa = scb_s->gvrd;
+	if (hpa) {
+		gpa = scb_o->gvrd & ~0x1ffUL;
+		unpin_guest_page(vcpu->kvm, gpa, hpa);
+		scb_s->gvrd = 0;
+	}
+
+	hpa = scb_s->riccbd;
+	if (hpa) {
+		gpa = scb_o->riccbd & ~0x3fUL;
+		unpin_guest_page(vcpu->kvm, gpa, hpa);
+		scb_s->riccbd = 0;
+	}
+}
+
+/*
+ * Instead of shadowing some blocks, we can simply forward them because the
+ * addresses in the scb are 64 bit long.
+ *
+ * This works as long as the data lies in one page. If blocks ever exceed one
+ * page, we have to fall back to shadowing.
+ *
+ * As we reuse the sca, the vcpu pointers contained in it are invalid. We must
+ * therefore not enable any facilities that access these pointers (e.g. SIGPIF).
+ *
+ * Returns: - 0 if all blocks were pinned.
+ *          - > 0 if control has to be given to guest 2
+ *          - -ENOMEM if out of memory
+ */
+static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	hpa_t hpa;
+	gpa_t gpa;
+	int rc = 0;
+
+	gpa = scb_o->scaol & ~0xfUL;
+	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO))
+		gpa |= (u64) scb_o->scaoh << 32;
+	if (gpa) {
+		if (!(gpa & ~0x1fffUL))
+			rc = set_validity_icpt(scb_s, 0x0038U);
+		else if ((gpa & ~0x1fffUL) == kvm_s390_get_prefix(vcpu))
+			rc = set_validity_icpt(scb_s, 0x0011U);
+		else if ((gpa & PAGE_MASK) !=
+			 ((gpa + sizeof(struct bsca_block) - 1) & PAGE_MASK))
+			rc = set_validity_icpt(scb_s, 0x003bU);
+		if (!rc) {
+			rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
+			if (rc == -EINVAL)
+				rc = set_validity_icpt(scb_s, 0x0034U);
+		}
+		if (rc)
+			goto unpin;
+		scb_s->scaoh = (u32)((u64)hpa >> 32);
+		scb_s->scaol = (u32)(u64)hpa;
+	}
+
+	gpa = scb_o->itdba & ~0xffUL;
+	if (gpa && (scb_s->ecb & 0x10U)) {
+		if (!(gpa & ~0x1fffU)) {
+			rc = set_validity_icpt(scb_s, 0x0080U);
+			goto unpin;
+		}
+		/* 256 bytes cannot cross page boundaries */
+		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
+		if (rc == -EINVAL)
+			rc = set_validity_icpt(scb_s, 0x0080U);
+		if (rc)
+			goto unpin;
+		scb_s->itdba = hpa;
+	}
+
+	gpa = scb_o->gvrd & ~0x1ffUL;
+	if (gpa && (scb_s->eca & 0x00020000U) &&
+	    !(scb_s->ecd & 0x20000000U)) {
+		if (!(gpa & ~0x1fffUL)) {
+			rc = set_validity_icpt(scb_s, 0x1310U);
+			goto unpin;
+		}
+		/*
+		 * 512 bytes vector registers cannot cross page boundaries
+		 * if this block gets bigger, we have to shadow it.
+		 */
+		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
+		if (rc == -EINVAL)
+			rc = set_validity_icpt(scb_s, 0x1310U);
+		if (rc)
+			goto unpin;
+		scb_s->gvrd = hpa;
+	}
+
+	gpa = scb_o->riccbd & ~0x3fUL;
+	if (gpa && (scb_s->ecb3 & 0x01U)) {
+		if (!(gpa & ~0x1fffUL)) {
+			rc = set_validity_icpt(scb_s, 0x0043U);
+			goto unpin;
+		}
+		/* 64 bytes cannot cross page boundaries */
+		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
+		if (rc == -EINVAL)
+			rc = set_validity_icpt(scb_s, 0x0043U);
+		/* Validity 0x0044 will be checked by SIE */
+		if (rc)
+			goto unpin;
+		scb_s->gvrd = hpa;
+	}
+	return 0;
+unpin:
+	unpin_blocks(vcpu, vsie_page);
+	return rc;
+}
+
+/* unpin the scb provided by guest 2, marking it as dirty */
+static void unpin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page,
+		      gpa_t gpa)
+{
+	hpa_t hpa = (hpa_t) vsie_page->scb_o;
+
+	if (hpa)
+		unpin_guest_page(vcpu->kvm, gpa, hpa);
+	vsie_page->scb_o = NULL;
+}
+
+/*
+ * Pin the scb at gpa provided by guest 2 at vsie_page->scb_o.
+ *
+ * Returns: - 0 if the scb was pinned.
+ *          - > 0 if control has to be given to guest 2
+ *          - -ENOMEM if out of memory
+ */
+static int pin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page,
+		   gpa_t gpa)
+{
+	hpa_t hpa;
+	int rc;
+
+	rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
+	if (rc == -EINVAL) {
+		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		if (!rc)
+			rc = 1;
+	}
+	if (!rc)
+		vsie_page->scb_o = (struct kvm_s390_sie_block *) hpa;
+	return rc;
+}
+
+/*
+ * Inject a fault into guest 2.
+ *
+ * Returns: - > 0 if control has to be given to guest 2
+ *            < 0 if an error occurred during injection.
+ */
+static int inject_fault(struct kvm_vcpu *vcpu, __u16 code, __u64 vaddr,
+			bool write_flag)
+{
+	struct kvm_s390_pgm_info pgm = {
+		.code = code,
+		.trans_exc_code =
+			/* 0-51: virtual address */
+			(vaddr & 0xfffffffffffff000UL) |
+			/* 52-53: store / fetch */
+			(((unsigned int) !write_flag) + 1) << 10,
+			/* 62-63: asce id (alway primary == 0) */
+		.exc_access_id = 0, /* always primary */
+		.op_access_id = 0, /* not MVPG */
+	};
+	int rc;
+
+	if (code == PGM_PROTECTION)
+		pgm.trans_exc_code |= 0x4UL;
+
+	rc = kvm_s390_inject_prog_irq(vcpu, &pgm);
+	return rc ? rc : 1;
+}
+
+/*
+ * Handle a fault during vsie execution on a gmap shadow.
+ *
+ * Returns: - 0 if the fault was resolved
+ *          - > 0 if control has to be given to guest 2
+ *          - < 0 if an error occurred
+ */
+static int handle_fault(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	int rc;
+
+	if (current->thread.gmap_int_code == PGM_PROTECTION)
+		/* we can directly forward all protection exceptions */
+		return inject_fault(vcpu, PGM_PROTECTION,
+				    current->thread.gmap_addr, 1);
+
+	rc = kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
+				   current->thread.gmap_addr);
+	if (rc > 0) {
+		rc = inject_fault(vcpu, rc,
+				  current->thread.gmap_addr,
+				  current->thread.gmap_write_flag);
+		if (rc >= 0)
+			vsie_page->fault_addr = current->thread.gmap_addr;
+	}
+	return rc;
+}
+
+/*
+ * Retry the previous fault that required guest 2 intervention. This avoids
+ * one superfluous SIE re-entry and direct exit.
+ *
+ * Will ignore any errors. The next SIE fault will do proper fault handling.
+ */
+static void handle_last_fault(struct kvm_vcpu *vcpu,
+			      struct vsie_page *vsie_page)
+{
+	if (vsie_page->fault_addr)
+		kvm_s390_shadow_fault(vcpu, vsie_page->gmap,
+				      vsie_page->fault_addr);
+	vsie_page->fault_addr = 0;
+}
+
+static inline void clear_vsie_icpt(struct vsie_page *vsie_page)
+{
+	vsie_page->scb_s.icptcode = 0;
+}
+
+/* rewind the psw and clear the vsie icpt, so we can retry execution */
+static void retry_vsie_icpt(struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	int ilen = insn_length(scb_s->ipa >> 8);
+
+	/* take care of EXECUTE instructions */
+	if (scb_s->icptstatus & 1) {
+		ilen = (scb_s->icptstatus >> 4) & 0x6;
+		if (!ilen)
+			ilen = 4;
+	}
+	scb_s->gpsw.addr = __rewind_psw(scb_s->gpsw, ilen);
+	clear_vsie_icpt(vsie_page);
+}
+
+/*
+ * Try to shadow + enable the guest 2 provided facility list.
+ * Retry instruction execution if enabled for and provided by guest 2.
+ *
+ * Returns: - 0 if handled (retry or guest 2 icpt)
+ *          - > 0 if control has to be given to guest 2
+ */
+static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	__u32 fac = vsie_page->scb_o->fac & 0x7ffffff8U;
+
+	if (fac && test_kvm_facility(vcpu->kvm, 7)) {
+		retry_vsie_icpt(vsie_page);
+		if (read_guest_real(vcpu, fac, &vsie_page->fac,
+				    sizeof(vsie_page->fac)))
+			return set_validity_icpt(scb_s, 0x1090U);
+		scb_s->fac = (__u32)(__u64) &vsie_page->fac;
+	}
+	return 0;
+}
+
+/*
+ * Run the vsie on a shadow scb and a shadow gmap, without any further
+ * sanity checks, handling SIE faults.
+ *
+ * Returns: - 0 everything went fine
+ *          - > 0 if control has to be given to guest 2
+ *          - < 0 if an error occurred
+ */
+static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	int rc;
+
+	handle_last_fault(vcpu, vsie_page);
+
+	if (need_resched())
+		schedule();
+	if (test_cpu_flag(CIF_MCCK_PENDING))
+		s390_handle_mcck();
+
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	local_irq_disable();
+	guest_enter_irqoff();
+	local_irq_enable();
+
+	rc = sie64a(scb_s, vcpu->run->s.regs.gprs);
+
+	local_irq_disable();
+	guest_exit_irqoff();
+	local_irq_enable();
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+
+	if (rc > 0)
+		rc = 0; /* we could still have an icpt */
+	else if (rc == -EFAULT)
+		return handle_fault(vcpu, vsie_page);
+
+	switch (scb_s->icptcode) {
+	case ICPT_INST:
+		if (scb_s->ipa == 0xb2b0)
+			rc = handle_stfle(vcpu, vsie_page);
+		break;
+	case ICPT_STOP:
+		/* stop not requested by g2 - must have been a kick */
+		if (!(atomic_read(&scb_o->cpuflags) & CPUSTAT_STOP_INT))
+			clear_vsie_icpt(vsie_page);
+		break;
+	case ICPT_VALIDITY:
+		if ((scb_s->ipa & 0xf000) != 0xf000)
+			scb_s->ipa += 0x1000;
+		break;
+	}
+	return rc;
+}
+
+static void release_gmap_shadow(struct vsie_page *vsie_page)
+{
+	if (vsie_page->gmap)
+		gmap_put(vsie_page->gmap);
+	WRITE_ONCE(vsie_page->gmap, NULL);
+	prefix_unmapped(vsie_page);
+}
+
+static int acquire_gmap_shadow(struct kvm_vcpu *vcpu,
+			       struct vsie_page *vsie_page)
+{
+	unsigned long asce;
+	union ctlreg0 cr0;
+	struct gmap *gmap;
+	int edat;
+
+	asce = vcpu->arch.sie_block->gcr[1];
+	cr0.val = vcpu->arch.sie_block->gcr[0];
+	edat = cr0.edat && test_kvm_facility(vcpu->kvm, 8);
+	edat += edat && test_kvm_facility(vcpu->kvm, 78);
+
+	/*
+	 * ASCE or EDAT could have changed since last icpt, or the gmap
+	 * we're holding has been unshadowed. If the gmap is still valid,
+	 * we can safely reuse it.
+	 */
+	if (vsie_page->gmap && gmap_shadow_valid(vsie_page->gmap, asce, edat))
+		return 0;
+
+	/* release the old shadow - if any, and mark the prefix as unmapped */
+	release_gmap_shadow(vsie_page);
+	gmap = gmap_shadow(vcpu->arch.gmap, asce, edat);
+	if (IS_ERR(gmap))
+		return PTR_ERR(gmap);
+	gmap->private = vcpu->kvm;
+	WRITE_ONCE(vsie_page->gmap, gmap);
+	return 0;
+}
+
+/*
+ * Register the shadow scb at the VCPU, e.g. for kicking out of vsie.
+ */
+static void register_shadow_scb(struct kvm_vcpu *vcpu,
+				struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+
+	WRITE_ONCE(vcpu->arch.vsie_block, &vsie_page->scb_s);
+	/*
+	 * External calls have to lead to a kick of the vcpu and
+	 * therefore the vsie -> Simulate Wait state.
+	 */
+	atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	/*
+	 * We have to adjust the g3 epoch by the g2 epoch. The epoch will
+	 * automatically be adjusted on tod clock changes via kvm_sync_clock.
+	 */
+	preempt_disable();
+	scb_s->epoch += vcpu->kvm->arch.epoch;
+	preempt_enable();
+}
+
+/*
+ * Unregister a shadow scb from a VCPU.
+ */
+static void unregister_shadow_scb(struct kvm_vcpu *vcpu)
+{
+	atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	WRITE_ONCE(vcpu->arch.vsie_block, NULL);
+}
+
+/*
+ * Run the vsie on a shadowed scb, managing the gmap shadow, handling
+ * prefix pages and faults.
+ *
+ * Returns: - 0 if no errors occurred
+ *          - > 0 if control has to be given to guest 2
+ *          - -ENOMEM if out of memory
+ */
+static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
+{
+	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	int rc = 0;
+
+	while (1) {
+		rc = acquire_gmap_shadow(vcpu, vsie_page);
+		if (!rc)
+			rc = map_prefix(vcpu, vsie_page);
+		if (!rc) {
+			gmap_enable(vsie_page->gmap);
+			update_intervention_requests(vsie_page);
+			rc = do_vsie_run(vcpu, vsie_page);
+			gmap_enable(vcpu->arch.gmap);
+		}
+		atomic_andnot(PROG_BLOCK_SIE, &scb_s->prog20);
+
+		if (rc == -EAGAIN)
+			rc = 0;
+		if (rc || scb_s->icptcode || signal_pending(current) ||
+		    kvm_s390_vcpu_has_irq(vcpu, 0))
+			break;
+	};
+
+	if (rc == -EFAULT) {
+		/*
+		 * Addressing exceptions are always presentes as intercepts.
+		 * As addressing exceptions are suppressing and our guest 3 PSW
+		 * points at the responsible instruction, we have to
+		 * forward the PSW and set the ilc. If we can't read guest 3
+		 * instruction, we can use an arbitrary ilc. Let's always use
+		 * ilen = 4 for now, so we can avoid reading in guest 3 virtual
+		 * memory. (we could also fake the shadow so the hardware
+		 * handles it).
+		 */
+		scb_s->icptcode = ICPT_PROGI;
+		scb_s->iprcc = PGM_ADDRESSING;
+		scb_s->pgmilc = 4;
+		scb_s->gpsw.addr = __rewind_psw(scb_s->gpsw, 4);
+	}
+	return rc;
+}
+
+/*
+ * Get or create a vsie page for a scb address.
+ *
+ * Returns: - address of a vsie page (cached or new one)
+ *          - NULL if the same scb address is already used by another VCPU
+ *          - ERR_PTR(-ENOMEM) if out of memory
+ */
+static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
+{
+	struct vsie_page *vsie_page;
+	struct page *page;
+	int nr_vcpus;
+
+	rcu_read_lock();
+	page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9);
+	rcu_read_unlock();
+	if (page) {
+		if (page_ref_inc_return(page) == 2)
+			return page_to_virt(page);
+		page_ref_dec(page);
+	}
+
+	/*
+	 * We want at least #online_vcpus shadows, so every VCPU can execute
+	 * the VSIE in parallel.
+	 */
+	nr_vcpus = atomic_read(&kvm->online_vcpus);
+
+	mutex_lock(&kvm->arch.vsie.mutex);
+	if (kvm->arch.vsie.page_count < nr_vcpus) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO | GFP_DMA);
+		if (!page) {
+			mutex_unlock(&kvm->arch.vsie.mutex);
+			return ERR_PTR(-ENOMEM);
+		}
+		page_ref_inc(page);
+		kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = page;
+		kvm->arch.vsie.page_count++;
+	} else {
+		/* reuse an existing entry that belongs to nobody */
+		while (true) {
+			page = kvm->arch.vsie.pages[kvm->arch.vsie.next];
+			if (page_ref_inc_return(page) == 2)
+				break;
+			page_ref_dec(page);
+			kvm->arch.vsie.next++;
+			kvm->arch.vsie.next %= nr_vcpus;
+		}
+		radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9);
+	}
+	page->index = addr;
+	/* double use of the same address */
+	if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, page)) {
+		page_ref_dec(page);
+		mutex_unlock(&kvm->arch.vsie.mutex);
+		return NULL;
+	}
+	mutex_unlock(&kvm->arch.vsie.mutex);
+
+	vsie_page = page_to_virt(page);
+	memset(&vsie_page->scb_s, 0, sizeof(struct kvm_s390_sie_block));
+	release_gmap_shadow(vsie_page);
+	vsie_page->fault_addr = 0;
+	vsie_page->scb_s.ihcpu = 0xffffU;
+	return vsie_page;
+}
+
+/* put a vsie page acquired via get_vsie_page */
+static void put_vsie_page(struct kvm *kvm, struct vsie_page *vsie_page)
+{
+	struct page *page = pfn_to_page(__pa(vsie_page) >> PAGE_SHIFT);
+
+	page_ref_dec(page);
+}
+
+int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu)
+{
+	struct vsie_page *vsie_page;
+	unsigned long scb_addr;
+	int rc;
+
+	vcpu->stat.instruction_sie++;
+	if (!test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_SIEF2))
+		return -EOPNOTSUPP;
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+	BUILD_BUG_ON(sizeof(struct vsie_page) != 4096);
+	scb_addr = kvm_s390_get_base_disp_s(vcpu, NULL);
+
+	/* 512 byte alignment */
+	if (unlikely(scb_addr & 0x1ffUL))
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	if (signal_pending(current) || kvm_s390_vcpu_has_irq(vcpu, 0))
+		return 0;
+
+	vsie_page = get_vsie_page(vcpu->kvm, scb_addr);
+	if (IS_ERR(vsie_page))
+		return PTR_ERR(vsie_page);
+	else if (!vsie_page)
+		/* double use of sie control block - simply do nothing */
+		return 0;
+
+	rc = pin_scb(vcpu, vsie_page, scb_addr);
+	if (rc)
+		goto out_put;
+	rc = shadow_scb(vcpu, vsie_page);
+	if (rc)
+		goto out_unpin_scb;
+	rc = pin_blocks(vcpu, vsie_page);
+	if (rc)
+		goto out_unshadow;
+	register_shadow_scb(vcpu, vsie_page);
+	rc = vsie_run(vcpu, vsie_page);
+	unregister_shadow_scb(vcpu);
+	unpin_blocks(vcpu, vsie_page);
+out_unshadow:
+	unshadow_scb(vcpu, vsie_page);
+out_unpin_scb:
+	unpin_scb(vcpu, vsie_page, scb_addr);
+out_put:
+	put_vsie_page(vcpu->kvm, vsie_page);
+
+	return rc < 0 ? rc : 0;
+}
+
+/* Init the vsie data structures. To be called when a vm is initialized. */
+void kvm_s390_vsie_init(struct kvm *kvm)
+{
+	mutex_init(&kvm->arch.vsie.mutex);
+	INIT_RADIX_TREE(&kvm->arch.vsie.addr_to_page, GFP_KERNEL);
+}
+
+/* Destroy the vsie data structures. To be called when a vm is destroyed. */
+void kvm_s390_vsie_destroy(struct kvm *kvm)
+{
+	struct vsie_page *vsie_page;
+	struct page *page;
+	int i;
+
+	mutex_lock(&kvm->arch.vsie.mutex);
+	for (i = 0; i < kvm->arch.vsie.page_count; i++) {
+		page = kvm->arch.vsie.pages[i];
+		kvm->arch.vsie.pages[i] = NULL;
+		vsie_page = page_to_virt(page);
+		release_gmap_shadow(vsie_page);
+		/* free the radix tree entry */
+		radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9);
+		__free_page(page);
+	}
+	kvm->arch.vsie.page_count = 0;
+	mutex_unlock(&kvm->arch.vsie.mutex);
+}
+
+void kvm_s390_vsie_kick(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_sie_block *scb = READ_ONCE(vcpu->arch.vsie_block);
+
+	/*
+	 * Even if the VCPU lets go of the shadow sie block reference, it is
+	 * still valid in the cache. So we can safely kick it.
+	 */
+	if (scb) {
+		atomic_or(PROG_BLOCK_SIE, &scb->prog20);
+		if (scb->prog0c & PROG_IN_SIE)
+			atomic_or(CPUSTAT_STOP_INT, &scb->cpuflags);
+	}
+}
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 25783dc3c813..a58bca62a93b 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -418,6 +418,8 @@ static inline int do_exception(struct pt_regs *regs, int access)
 		(struct gmap *) S390_lowcore.gmap : NULL;
 	if (gmap) {
 		current->thread.gmap_addr = address;
+		current->thread.gmap_write_flag = !!(flags & FAULT_FLAG_WRITE);
+		current->thread.gmap_int_code = regs->int_code & 0xffff;
 		address = __gmap_translate(gmap, address);
 		if (address == -EFAULT) {
 			fault = VM_FAULT_BADMAP;
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 063c721ec0dc..2ce6bb3bab32 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -20,14 +20,16 @@
 #include <asm/gmap.h>
 #include <asm/tlb.h>
 
+#define GMAP_SHADOW_FAKE_TABLE 1ULL
+
 /**
- * gmap_alloc - allocate a guest address space
+ * gmap_alloc - allocate and initialize a guest address space
  * @mm: pointer to the parent mm_struct
  * @limit: maximum address of the gmap address space
  *
  * Returns a guest address space structure.
  */
-struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit)
+static struct gmap *gmap_alloc(unsigned long limit)
 {
 	struct gmap *gmap;
 	struct page *page;
@@ -55,10 +57,14 @@ struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit)
 	if (!gmap)
 		goto out;
 	INIT_LIST_HEAD(&gmap->crst_list);
+	INIT_LIST_HEAD(&gmap->children);
+	INIT_LIST_HEAD(&gmap->pt_list);
 	INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL);
 	INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC);
+	INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC);
 	spin_lock_init(&gmap->guest_table_lock);
-	gmap->mm = mm;
+	spin_lock_init(&gmap->shadow_lock);
+	atomic_set(&gmap->ref_count, 1);
 	page = alloc_pages(GFP_KERNEL, 2);
 	if (!page)
 		goto out_free;
@@ -70,9 +76,6 @@ struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit)
 	gmap->asce = atype | _ASCE_TABLE_LENGTH |
 		_ASCE_USER_BITS | __pa(table);
 	gmap->asce_end = limit;
-	down_write(&mm->mmap_sem);
-	list_add(&gmap->list, &mm->context.gmap_list);
-	up_write(&mm->mmap_sem);
 	return gmap;
 
 out_free:
@@ -80,7 +83,28 @@ out_free:
 out:
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(gmap_alloc);
+
+/**
+ * gmap_create - create a guest address space
+ * @mm: pointer to the parent mm_struct
+ * @limit: maximum size of the gmap address space
+ *
+ * Returns a guest address space structure.
+ */
+struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit)
+{
+	struct gmap *gmap;
+
+	gmap = gmap_alloc(limit);
+	if (!gmap)
+		return NULL;
+	gmap->mm = mm;
+	spin_lock(&mm->context.gmap_lock);
+	list_add_rcu(&gmap->list, &mm->context.gmap_list);
+	spin_unlock(&mm->context.gmap_lock);
+	return gmap;
+}
+EXPORT_SYMBOL_GPL(gmap_create);
 
 static void gmap_flush_tlb(struct gmap *gmap)
 {
@@ -114,31 +138,117 @@ static void gmap_radix_tree_free(struct radix_tree_root *root)
 	} while (nr > 0);
 }
 
+static void gmap_rmap_radix_tree_free(struct radix_tree_root *root)
+{
+	struct gmap_rmap *rmap, *rnext, *head;
+	struct radix_tree_iter iter;
+	unsigned long indices[16];
+	unsigned long index;
+	void **slot;
+	int i, nr;
+
+	/* A radix tree is freed by deleting all of its entries */
+	index = 0;
+	do {
+		nr = 0;
+		radix_tree_for_each_slot(slot, root, &iter, index) {
+			indices[nr] = iter.index;
+			if (++nr == 16)
+				break;
+		}
+		for (i = 0; i < nr; i++) {
+			index = indices[i];
+			head = radix_tree_delete(root, index);
+			gmap_for_each_rmap_safe(rmap, rnext, head)
+				kfree(rmap);
+		}
+	} while (nr > 0);
+}
+
 /**
  * gmap_free - free a guest address space
  * @gmap: pointer to the guest address space structure
+ *
+ * No locks required. There are no references to this gmap anymore.
  */
-void gmap_free(struct gmap *gmap)
+static void gmap_free(struct gmap *gmap)
 {
 	struct page *page, *next;
 
-	/* Flush tlb. */
-	if (MACHINE_HAS_IDTE)
-		__tlb_flush_idte(gmap->asce);
-	else
-		__tlb_flush_global();
-
+	/* Flush tlb of all gmaps (if not already done for shadows) */
+	if (!(gmap_is_shadow(gmap) && gmap->removed))
+		gmap_flush_tlb(gmap);
 	/* Free all segment & region tables. */
 	list_for_each_entry_safe(page, next, &gmap->crst_list, lru)
 		__free_pages(page, 2);
 	gmap_radix_tree_free(&gmap->guest_to_host);
 	gmap_radix_tree_free(&gmap->host_to_guest);
-	down_write(&gmap->mm->mmap_sem);
-	list_del(&gmap->list);
-	up_write(&gmap->mm->mmap_sem);
+
+	/* Free additional data for a shadow gmap */
+	if (gmap_is_shadow(gmap)) {
+		/* Free all page tables. */
+		list_for_each_entry_safe(page, next, &gmap->pt_list, lru)
+			page_table_free_pgste(page);
+		gmap_rmap_radix_tree_free(&gmap->host_to_rmap);
+		/* Release reference to the parent */
+		gmap_put(gmap->parent);
+	}
+
 	kfree(gmap);
 }
-EXPORT_SYMBOL_GPL(gmap_free);
+
+/**
+ * gmap_get - increase reference counter for guest address space
+ * @gmap: pointer to the guest address space structure
+ *
+ * Returns the gmap pointer
+ */
+struct gmap *gmap_get(struct gmap *gmap)
+{
+	atomic_inc(&gmap->ref_count);
+	return gmap;
+}
+EXPORT_SYMBOL_GPL(gmap_get);
+
+/**
+ * gmap_put - decrease reference counter for guest address space
+ * @gmap: pointer to the guest address space structure
+ *
+ * If the reference counter reaches zero the guest address space is freed.
+ */
+void gmap_put(struct gmap *gmap)
+{
+	if (atomic_dec_return(&gmap->ref_count) == 0)
+		gmap_free(gmap);
+}
+EXPORT_SYMBOL_GPL(gmap_put);
+
+/**
+ * gmap_remove - remove a guest address space but do not free it yet
+ * @gmap: pointer to the guest address space structure
+ */
+void gmap_remove(struct gmap *gmap)
+{
+	struct gmap *sg, *next;
+
+	/* Remove all shadow gmaps linked to this gmap */
+	if (!list_empty(&gmap->children)) {
+		spin_lock(&gmap->shadow_lock);
+		list_for_each_entry_safe(sg, next, &gmap->children, list) {
+			list_del(&sg->list);
+			gmap_put(sg);
+		}
+		spin_unlock(&gmap->shadow_lock);
+	}
+	/* Remove gmap from the pre-mm list */
+	spin_lock(&gmap->mm->context.gmap_lock);
+	list_del_rcu(&gmap->list);
+	spin_unlock(&gmap->mm->context.gmap_lock);
+	synchronize_rcu();
+	/* Put reference */
+	gmap_put(gmap);
+}
+EXPORT_SYMBOL_GPL(gmap_remove);
 
 /**
  * gmap_enable - switch primary space to the guest address space
@@ -160,6 +270,17 @@ void gmap_disable(struct gmap *gmap)
 }
 EXPORT_SYMBOL_GPL(gmap_disable);
 
+/**
+ * gmap_get_enabled - get a pointer to the currently enabled gmap
+ *
+ * Returns a pointer to the currently enabled gmap. 0 if none is enabled.
+ */
+struct gmap *gmap_get_enabled(void)
+{
+	return (struct gmap *) S390_lowcore.gmap;
+}
+EXPORT_SYMBOL_GPL(gmap_get_enabled);
+
 /*
  * gmap_alloc_table is assumed to be called with mmap_sem held
  */
@@ -175,7 +296,7 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 		return -ENOMEM;
 	new = (unsigned long *) page_to_phys(page);
 	crst_table_init(new, init);
-	spin_lock(&gmap->mm->page_table_lock);
+	spin_lock(&gmap->guest_table_lock);
 	if (*table & _REGION_ENTRY_INVALID) {
 		list_add(&page->lru, &gmap->crst_list);
 		*table = (unsigned long) new | _REGION_ENTRY_LENGTH |
@@ -183,7 +304,7 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 		page->index = gaddr;
 		page = NULL;
 	}
-	spin_unlock(&gmap->mm->page_table_lock);
+	spin_unlock(&gmap->guest_table_lock);
 	if (page)
 		__free_pages(page, 2);
 	return 0;
@@ -219,6 +340,7 @@ static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr)
 	unsigned long *entry;
 	int flush = 0;
 
+	BUG_ON(gmap_is_shadow(gmap));
 	spin_lock(&gmap->guest_table_lock);
 	entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
 	if (entry) {
@@ -258,6 +380,7 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
 	unsigned long off;
 	int flush;
 
+	BUG_ON(gmap_is_shadow(gmap));
 	if ((to | len) & (PMD_SIZE - 1))
 		return -EINVAL;
 	if (len == 0 || to + len < to)
@@ -289,6 +412,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
 	unsigned long off;
 	int flush;
 
+	BUG_ON(gmap_is_shadow(gmap));
 	if ((from | to | len) & (PMD_SIZE - 1))
 		return -EINVAL;
 	if (len == 0 || from + len < from || to + len < to ||
@@ -326,6 +450,8 @@ EXPORT_SYMBOL_GPL(gmap_map_segment);
  * This function does not establish potentially missing page table entries.
  * The mmap_sem of the mm that belongs to the address space must be held
  * when this function gets called.
+ *
+ * Note: Can also be called for shadow gmaps.
  */
 unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
 {
@@ -333,6 +459,7 @@ unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
 
 	vmaddr = (unsigned long)
 		radix_tree_lookup(&gmap->guest_to_host, gaddr >> PMD_SHIFT);
+	/* Note: guest_to_host is empty for a shadow gmap */
 	return vmaddr ? (vmaddr | (gaddr & ~PMD_MASK)) : -EFAULT;
 }
 EXPORT_SYMBOL_GPL(__gmap_translate);
@@ -369,11 +496,13 @@ void gmap_unlink(struct mm_struct *mm, unsigned long *table,
 	struct gmap *gmap;
 	int flush;
 
-	list_for_each_entry(gmap, &mm->context.gmap_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
 		flush = __gmap_unlink_by_vmaddr(gmap, vmaddr);
 		if (flush)
 			gmap_flush_tlb(gmap);
 	}
+	rcu_read_unlock();
 }
 
 /**
@@ -397,6 +526,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	pmd_t *pmd;
 	int rc;
 
+	BUG_ON(gmap_is_shadow(gmap));
 	/* Create higher level tables in the gmap page table */
 	table = gmap->table;
 	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION1) {
@@ -552,116 +682,1412 @@ static LIST_HEAD(gmap_notifier_list);
 static DEFINE_SPINLOCK(gmap_notifier_lock);
 
 /**
- * gmap_register_ipte_notifier - register a pte invalidation callback
+ * gmap_register_pte_notifier - register a pte invalidation callback
  * @nb: pointer to the gmap notifier block
  */
-void gmap_register_ipte_notifier(struct gmap_notifier *nb)
+void gmap_register_pte_notifier(struct gmap_notifier *nb)
 {
 	spin_lock(&gmap_notifier_lock);
-	list_add(&nb->list, &gmap_notifier_list);
+	list_add_rcu(&nb->list, &gmap_notifier_list);
 	spin_unlock(&gmap_notifier_lock);
 }
-EXPORT_SYMBOL_GPL(gmap_register_ipte_notifier);
+EXPORT_SYMBOL_GPL(gmap_register_pte_notifier);
 
 /**
- * gmap_unregister_ipte_notifier - remove a pte invalidation callback
+ * gmap_unregister_pte_notifier - remove a pte invalidation callback
  * @nb: pointer to the gmap notifier block
  */
-void gmap_unregister_ipte_notifier(struct gmap_notifier *nb)
+void gmap_unregister_pte_notifier(struct gmap_notifier *nb)
 {
 	spin_lock(&gmap_notifier_lock);
-	list_del_init(&nb->list);
+	list_del_rcu(&nb->list);
 	spin_unlock(&gmap_notifier_lock);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(gmap_unregister_pte_notifier);
+
+/**
+ * gmap_call_notifier - call all registered invalidation callbacks
+ * @gmap: pointer to guest mapping meta data structure
+ * @start: start virtual address in the guest address space
+ * @end: end virtual address in the guest address space
+ */
+static void gmap_call_notifier(struct gmap *gmap, unsigned long start,
+			       unsigned long end)
+{
+	struct gmap_notifier *nb;
+
+	list_for_each_entry(nb, &gmap_notifier_list, list)
+		nb->notifier_call(gmap, start, end);
+}
+
+/**
+ * gmap_table_walk - walk the gmap page tables
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @level: page table level to stop at
+ *
+ * Returns a table entry pointer for the given guest address and @level
+ * @level=0 : returns a pointer to a page table table entry (or NULL)
+ * @level=1 : returns a pointer to a segment table entry (or NULL)
+ * @level=2 : returns a pointer to a region-3 table entry (or NULL)
+ * @level=3 : returns a pointer to a region-2 table entry (or NULL)
+ * @level=4 : returns a pointer to a region-1 table entry (or NULL)
+ *
+ * Returns NULL if the gmap page tables could not be walked to the
+ * requested level.
+ *
+ * Note: Can also be called for shadow gmaps.
+ */
+static inline unsigned long *gmap_table_walk(struct gmap *gmap,
+					     unsigned long gaddr, int level)
+{
+	unsigned long *table;
+
+	if ((gmap->asce & _ASCE_TYPE_MASK) + 4 < (level * 4))
+		return NULL;
+	if (gmap_is_shadow(gmap) && gmap->removed)
+		return NULL;
+	if (gaddr & (-1UL << (31 + ((gmap->asce & _ASCE_TYPE_MASK) >> 2)*11)))
+		return NULL;
+	table = gmap->table;
+	switch (gmap->asce & _ASCE_TYPE_MASK) {
+	case _ASCE_TYPE_REGION1:
+		table += (gaddr >> 53) & 0x7ff;
+		if (level == 4)
+			break;
+		if (*table & _REGION_ENTRY_INVALID)
+			return NULL;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		/* Fallthrough */
+	case _ASCE_TYPE_REGION2:
+		table += (gaddr >> 42) & 0x7ff;
+		if (level == 3)
+			break;
+		if (*table & _REGION_ENTRY_INVALID)
+			return NULL;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		/* Fallthrough */
+	case _ASCE_TYPE_REGION3:
+		table += (gaddr >> 31) & 0x7ff;
+		if (level == 2)
+			break;
+		if (*table & _REGION_ENTRY_INVALID)
+			return NULL;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		/* Fallthrough */
+	case _ASCE_TYPE_SEGMENT:
+		table += (gaddr >> 20) & 0x7ff;
+		if (level == 1)
+			break;
+		if (*table & _REGION_ENTRY_INVALID)
+			return NULL;
+		table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
+		table += (gaddr >> 12) & 0xff;
+	}
+	return table;
+}
+
+/**
+ * gmap_pte_op_walk - walk the gmap page table, get the page table lock
+ *		      and return the pte pointer
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @ptl: pointer to the spinlock pointer
+ *
+ * Returns a pointer to the locked pte for a guest address, or NULL
+ *
+ * Note: Can also be called for shadow gmaps.
+ */
+static pte_t *gmap_pte_op_walk(struct gmap *gmap, unsigned long gaddr,
+			       spinlock_t **ptl)
+{
+	unsigned long *table;
+
+	if (gmap_is_shadow(gmap))
+		spin_lock(&gmap->guest_table_lock);
+	/* Walk the gmap page table, lock and get pte pointer */
+	table = gmap_table_walk(gmap, gaddr, 1); /* get segment pointer */
+	if (!table || *table & _SEGMENT_ENTRY_INVALID) {
+		if (gmap_is_shadow(gmap))
+			spin_unlock(&gmap->guest_table_lock);
+		return NULL;
+	}
+	if (gmap_is_shadow(gmap)) {
+		*ptl = &gmap->guest_table_lock;
+		return pte_offset_map((pmd_t *) table, gaddr);
+	}
+	return pte_alloc_map_lock(gmap->mm, (pmd_t *) table, gaddr, ptl);
+}
+
+/**
+ * gmap_pte_op_fixup - force a page in and connect the gmap page table
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @vmaddr: address in the host process address space
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ *
+ * Returns 0 if the caller can retry __gmap_translate (might fail again),
+ * -ENOMEM if out of memory and -EFAULT if anything goes wrong while fixing
+ * up or connecting the gmap page table.
+ */
+static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
+			     unsigned long vmaddr, int prot)
+{
+	struct mm_struct *mm = gmap->mm;
+	unsigned int fault_flags;
+	bool unlocked = false;
+
+	BUG_ON(gmap_is_shadow(gmap));
+	fault_flags = (prot == PROT_WRITE) ? FAULT_FLAG_WRITE : 0;
+	if (fixup_user_fault(current, mm, vmaddr, fault_flags, &unlocked))
+		return -EFAULT;
+	if (unlocked)
+		/* lost mmap_sem, caller has to retry __gmap_translate */
+		return 0;
+	/* Connect the page tables */
+	return __gmap_link(gmap, gaddr, vmaddr);
 }
-EXPORT_SYMBOL_GPL(gmap_unregister_ipte_notifier);
 
 /**
- * gmap_ipte_notify - mark a range of ptes for invalidation notification
+ * gmap_pte_op_end - release the page table lock
+ * @ptl: pointer to the spinlock pointer
+ */
+static void gmap_pte_op_end(spinlock_t *ptl)
+{
+	spin_unlock(ptl);
+}
+
+/*
+ * gmap_protect_range - remove access rights to memory and set pgste bits
  * @gmap: pointer to guest mapping meta data structure
  * @gaddr: virtual address in the guest address space
  * @len: size of area
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: pgste notification bits to set
  *
- * Returns 0 if for each page in the given range a gmap mapping exists and
- * the invalidation notification could be set. If the gmap mapping is missing
- * for one or more pages -EFAULT is returned. If no memory could be allocated
- * -ENOMEM is returned. This function establishes missing page table entries.
+ * Returns 0 if successfully protected, -ENOMEM if out of memory and
+ * -EFAULT if gaddr is invalid (or mapping for shadows is missing).
+ *
+ * Called with sg->mm->mmap_sem in read.
+ *
+ * Note: Can also be called for shadow gmaps.
  */
-int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len)
+static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
+			      unsigned long len, int prot, unsigned long bits)
 {
-	unsigned long addr;
+	unsigned long vmaddr;
 	spinlock_t *ptl;
 	pte_t *ptep;
-	bool unlocked;
-	int rc = 0;
+	int rc;
+
+	while (len) {
+		rc = -EAGAIN;
+		ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
+		if (ptep) {
+			rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, bits);
+			gmap_pte_op_end(ptl);
+		}
+		if (rc) {
+			vmaddr = __gmap_translate(gmap, gaddr);
+			if (IS_ERR_VALUE(vmaddr))
+				return vmaddr;
+			rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot);
+			if (rc)
+				return rc;
+			continue;
+		}
+		gaddr += PAGE_SIZE;
+		len -= PAGE_SIZE;
+	}
+	return 0;
+}
+
+/**
+ * gmap_mprotect_notify - change access rights for a range of ptes and
+ *                        call the notifier if any pte changes again
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @len: size of area
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ *
+ * Returns 0 if for each page in the given range a gmap mapping exists,
+ * the new access rights could be set and the notifier could be armed.
+ * If the gmap mapping is missing for one or more pages -EFAULT is
+ * returned. If no memory could be allocated -ENOMEM is returned.
+ * This function establishes missing page table entries.
+ */
+int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr,
+			 unsigned long len, int prot)
+{
+	int rc;
 
-	if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK))
+	if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK) || gmap_is_shadow(gmap))
+		return -EINVAL;
+	if (!MACHINE_HAS_ESOP && prot == PROT_READ)
 		return -EINVAL;
 	down_read(&gmap->mm->mmap_sem);
-	while (len) {
-		unlocked = false;
-		/* Convert gmap address and connect the page tables */
-		addr = __gmap_translate(gmap, gaddr);
-		if (IS_ERR_VALUE(addr)) {
-			rc = addr;
+	rc = gmap_protect_range(gmap, gaddr, len, prot, PGSTE_IN_BIT);
+	up_read(&gmap->mm->mmap_sem);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_mprotect_notify);
+
+/**
+ * gmap_read_table - get an unsigned long value from a guest page table using
+ *                   absolute addressing, without marking the page referenced.
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @val: pointer to the unsigned long value to return
+ *
+ * Returns 0 if the value was read, -ENOMEM if out of memory and -EFAULT
+ * if reading using the virtual address failed.
+ *
+ * Called with gmap->mm->mmap_sem in read.
+ */
+int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val)
+{
+	unsigned long address, vmaddr;
+	spinlock_t *ptl;
+	pte_t *ptep, pte;
+	int rc;
+
+	while (1) {
+		rc = -EAGAIN;
+		ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
+		if (ptep) {
+			pte = *ptep;
+			if (pte_present(pte) && (pte_val(pte) & _PAGE_READ)) {
+				address = pte_val(pte) & PAGE_MASK;
+				address += gaddr & ~PAGE_MASK;
+				*val = *(unsigned long *) address;
+				pte_val(*ptep) |= _PAGE_YOUNG;
+				/* Do *NOT* clear the _PAGE_INVALID bit! */
+				rc = 0;
+			}
+			gmap_pte_op_end(ptl);
+		}
+		if (!rc)
+			break;
+		vmaddr = __gmap_translate(gmap, gaddr);
+		if (IS_ERR_VALUE(vmaddr)) {
+			rc = vmaddr;
 			break;
 		}
-		/* Get the page mapped */
-		if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE,
-				     &unlocked)) {
-			rc = -EFAULT;
+		rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, PROT_READ);
+		if (rc)
 			break;
+	}
+	return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_read_table);
+
+/**
+ * gmap_insert_rmap - add a rmap to the host_to_rmap radix tree
+ * @sg: pointer to the shadow guest address space structure
+ * @vmaddr: vm address associated with the rmap
+ * @rmap: pointer to the rmap structure
+ *
+ * Called with the sg->guest_table_lock
+ */
+static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr,
+				    struct gmap_rmap *rmap)
+{
+	void **slot;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	slot = radix_tree_lookup_slot(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT);
+	if (slot) {
+		rmap->next = radix_tree_deref_slot_protected(slot,
+							&sg->guest_table_lock);
+		radix_tree_replace_slot(slot, rmap);
+	} else {
+		rmap->next = NULL;
+		radix_tree_insert(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT,
+				  rmap);
+	}
+}
+
+/**
+ * gmap_protect_rmap - modify access rights to memory and create an rmap
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow gmap
+ * @paddr: address in the parent guest address space
+ * @len: length of the memory area to protect
+ * @prot: indicates access rights: none, read-only or read-write
+ *
+ * Returns 0 if successfully protected and the rmap was created, -ENOMEM
+ * if out of memory and -EFAULT if paddr is invalid.
+ */
+static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr,
+			     unsigned long paddr, unsigned long len, int prot)
+{
+	struct gmap *parent;
+	struct gmap_rmap *rmap;
+	unsigned long vmaddr;
+	spinlock_t *ptl;
+	pte_t *ptep;
+	int rc;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	parent = sg->parent;
+	while (len) {
+		vmaddr = __gmap_translate(parent, paddr);
+		if (IS_ERR_VALUE(vmaddr))
+			return vmaddr;
+		rmap = kzalloc(sizeof(*rmap), GFP_KERNEL);
+		if (!rmap)
+			return -ENOMEM;
+		rmap->raddr = raddr;
+		rc = radix_tree_preload(GFP_KERNEL);
+		if (rc) {
+			kfree(rmap);
+			return rc;
+		}
+		rc = -EAGAIN;
+		ptep = gmap_pte_op_walk(parent, paddr, &ptl);
+		if (ptep) {
+			spin_lock(&sg->guest_table_lock);
+			rc = ptep_force_prot(parent->mm, paddr, ptep, prot,
+					     PGSTE_VSIE_BIT);
+			if (!rc)
+				gmap_insert_rmap(sg, vmaddr, rmap);
+			spin_unlock(&sg->guest_table_lock);
+			gmap_pte_op_end(ptl);
 		}
-		/* While trying to map mmap_sem got unlocked. Let us retry */
-		if (unlocked)
+		radix_tree_preload_end();
+		if (rc) {
+			kfree(rmap);
+			rc = gmap_pte_op_fixup(parent, paddr, vmaddr, prot);
+			if (rc)
+				return rc;
 			continue;
-		rc = __gmap_link(gmap, gaddr, addr);
+		}
+		paddr += PAGE_SIZE;
+		len -= PAGE_SIZE;
+	}
+	return 0;
+}
+
+#define _SHADOW_RMAP_MASK	0x7
+#define _SHADOW_RMAP_REGION1	0x5
+#define _SHADOW_RMAP_REGION2	0x4
+#define _SHADOW_RMAP_REGION3	0x3
+#define _SHADOW_RMAP_SEGMENT	0x2
+#define _SHADOW_RMAP_PGTABLE	0x1
+
+/**
+ * gmap_idte_one - invalidate a single region or segment table entry
+ * @asce: region or segment table *origin* + table-type bits
+ * @vaddr: virtual address to identify the table entry to flush
+ *
+ * The invalid bit of a single region or segment table entry is set
+ * and the associated TLB entries depending on the entry are flushed.
+ * The table-type of the @asce identifies the portion of the @vaddr
+ * that is used as the invalidation index.
+ */
+static inline void gmap_idte_one(unsigned long asce, unsigned long vaddr)
+{
+	asm volatile(
+		"	.insn	rrf,0xb98e0000,%0,%1,0,0"
+		: : "a" (asce), "a" (vaddr) : "cc", "memory");
+}
+
+/**
+ * gmap_unshadow_page - remove a page from a shadow page table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ *
+ * Called with the sg->guest_table_lock
+ */
+static void gmap_unshadow_page(struct gmap *sg, unsigned long raddr)
+{
+	unsigned long *table;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	table = gmap_table_walk(sg, raddr, 0); /* get page table pointer */
+	if (!table || *table & _PAGE_INVALID)
+		return;
+	gmap_call_notifier(sg, raddr, raddr + (1UL << 12) - 1);
+	ptep_unshadow_pte(sg->mm, raddr, (pte_t *) table);
+}
+
+/**
+ * __gmap_unshadow_pgt - remove all entries from a shadow page table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ * @pgt: pointer to the start of a shadow page table
+ *
+ * Called with the sg->guest_table_lock
+ */
+static void __gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr,
+				unsigned long *pgt)
+{
+	int i;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	for (i = 0; i < 256; i++, raddr += 1UL << 12)
+		pgt[i] = _PAGE_INVALID;
+}
+
+/**
+ * gmap_unshadow_pgt - remove a shadow page table from a segment entry
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: address in the shadow guest address space
+ *
+ * Called with the sg->guest_table_lock
+ */
+static void gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr)
+{
+	unsigned long sto, *ste, *pgt;
+	struct page *page;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	ste = gmap_table_walk(sg, raddr, 1); /* get segment pointer */
+	if (!ste || !(*ste & _SEGMENT_ENTRY_ORIGIN))
+		return;
+	gmap_call_notifier(sg, raddr, raddr + (1UL << 20) - 1);
+	sto = (unsigned long) (ste - ((raddr >> 20) & 0x7ff));
+	gmap_idte_one(sto | _ASCE_TYPE_SEGMENT, raddr);
+	pgt = (unsigned long *)(*ste & _SEGMENT_ENTRY_ORIGIN);
+	*ste = _SEGMENT_ENTRY_EMPTY;
+	__gmap_unshadow_pgt(sg, raddr, pgt);
+	/* Free page table */
+	page = pfn_to_page(__pa(pgt) >> PAGE_SHIFT);
+	list_del(&page->lru);
+	page_table_free_pgste(page);
+}
+
+/**
+ * __gmap_unshadow_sgt - remove all entries from a shadow segment table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ * @sgt: pointer to the start of a shadow segment table
+ *
+ * Called with the sg->guest_table_lock
+ */
+static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr,
+				unsigned long *sgt)
+{
+	unsigned long asce, *pgt;
+	struct page *page;
+	int i;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	asce = (unsigned long) sgt | _ASCE_TYPE_SEGMENT;
+	for (i = 0; i < 2048; i++, raddr += 1UL << 20) {
+		if (!(sgt[i] & _SEGMENT_ENTRY_ORIGIN))
+			continue;
+		pgt = (unsigned long *)(sgt[i] & _REGION_ENTRY_ORIGIN);
+		sgt[i] = _SEGMENT_ENTRY_EMPTY;
+		__gmap_unshadow_pgt(sg, raddr, pgt);
+		/* Free page table */
+		page = pfn_to_page(__pa(pgt) >> PAGE_SHIFT);
+		list_del(&page->lru);
+		page_table_free_pgste(page);
+	}
+}
+
+/**
+ * gmap_unshadow_sgt - remove a shadow segment table from a region-3 entry
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ *
+ * Called with the shadow->guest_table_lock
+ */
+static void gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr)
+{
+	unsigned long r3o, *r3e, *sgt;
+	struct page *page;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	r3e = gmap_table_walk(sg, raddr, 2); /* get region-3 pointer */
+	if (!r3e || !(*r3e & _REGION_ENTRY_ORIGIN))
+		return;
+	gmap_call_notifier(sg, raddr, raddr + (1UL << 31) - 1);
+	r3o = (unsigned long) (r3e - ((raddr >> 31) & 0x7ff));
+	gmap_idte_one(r3o | _ASCE_TYPE_REGION3, raddr);
+	sgt = (unsigned long *)(*r3e & _REGION_ENTRY_ORIGIN);
+	*r3e = _REGION3_ENTRY_EMPTY;
+	__gmap_unshadow_sgt(sg, raddr, sgt);
+	/* Free segment table */
+	page = pfn_to_page(__pa(sgt) >> PAGE_SHIFT);
+	list_del(&page->lru);
+	__free_pages(page, 2);
+}
+
+/**
+ * __gmap_unshadow_r3t - remove all entries from a shadow region-3 table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: address in the shadow guest address space
+ * @r3t: pointer to the start of a shadow region-3 table
+ *
+ * Called with the sg->guest_table_lock
+ */
+static void __gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr,
+				unsigned long *r3t)
+{
+	unsigned long asce, *sgt;
+	struct page *page;
+	int i;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	asce = (unsigned long) r3t | _ASCE_TYPE_REGION3;
+	for (i = 0; i < 2048; i++, raddr += 1UL << 31) {
+		if (!(r3t[i] & _REGION_ENTRY_ORIGIN))
+			continue;
+		sgt = (unsigned long *)(r3t[i] & _REGION_ENTRY_ORIGIN);
+		r3t[i] = _REGION3_ENTRY_EMPTY;
+		__gmap_unshadow_sgt(sg, raddr, sgt);
+		/* Free segment table */
+		page = pfn_to_page(__pa(sgt) >> PAGE_SHIFT);
+		list_del(&page->lru);
+		__free_pages(page, 2);
+	}
+}
+
+/**
+ * gmap_unshadow_r3t - remove a shadow region-3 table from a region-2 entry
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ *
+ * Called with the sg->guest_table_lock
+ */
+static void gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr)
+{
+	unsigned long r2o, *r2e, *r3t;
+	struct page *page;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	r2e = gmap_table_walk(sg, raddr, 3); /* get region-2 pointer */
+	if (!r2e || !(*r2e & _REGION_ENTRY_ORIGIN))
+		return;
+	gmap_call_notifier(sg, raddr, raddr + (1UL << 42) - 1);
+	r2o = (unsigned long) (r2e - ((raddr >> 42) & 0x7ff));
+	gmap_idte_one(r2o | _ASCE_TYPE_REGION2, raddr);
+	r3t = (unsigned long *)(*r2e & _REGION_ENTRY_ORIGIN);
+	*r2e = _REGION2_ENTRY_EMPTY;
+	__gmap_unshadow_r3t(sg, raddr, r3t);
+	/* Free region 3 table */
+	page = pfn_to_page(__pa(r3t) >> PAGE_SHIFT);
+	list_del(&page->lru);
+	__free_pages(page, 2);
+}
+
+/**
+ * __gmap_unshadow_r2t - remove all entries from a shadow region-2 table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ * @r2t: pointer to the start of a shadow region-2 table
+ *
+ * Called with the sg->guest_table_lock
+ */
+static void __gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr,
+				unsigned long *r2t)
+{
+	unsigned long asce, *r3t;
+	struct page *page;
+	int i;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	asce = (unsigned long) r2t | _ASCE_TYPE_REGION2;
+	for (i = 0; i < 2048; i++, raddr += 1UL << 42) {
+		if (!(r2t[i] & _REGION_ENTRY_ORIGIN))
+			continue;
+		r3t = (unsigned long *)(r2t[i] & _REGION_ENTRY_ORIGIN);
+		r2t[i] = _REGION2_ENTRY_EMPTY;
+		__gmap_unshadow_r3t(sg, raddr, r3t);
+		/* Free region 3 table */
+		page = pfn_to_page(__pa(r3t) >> PAGE_SHIFT);
+		list_del(&page->lru);
+		__free_pages(page, 2);
+	}
+}
+
+/**
+ * gmap_unshadow_r2t - remove a shadow region-2 table from a region-1 entry
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ *
+ * Called with the sg->guest_table_lock
+ */
+static void gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr)
+{
+	unsigned long r1o, *r1e, *r2t;
+	struct page *page;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	r1e = gmap_table_walk(sg, raddr, 4); /* get region-1 pointer */
+	if (!r1e || !(*r1e & _REGION_ENTRY_ORIGIN))
+		return;
+	gmap_call_notifier(sg, raddr, raddr + (1UL << 53) - 1);
+	r1o = (unsigned long) (r1e - ((raddr >> 53) & 0x7ff));
+	gmap_idte_one(r1o | _ASCE_TYPE_REGION1, raddr);
+	r2t = (unsigned long *)(*r1e & _REGION_ENTRY_ORIGIN);
+	*r1e = _REGION1_ENTRY_EMPTY;
+	__gmap_unshadow_r2t(sg, raddr, r2t);
+	/* Free region 2 table */
+	page = pfn_to_page(__pa(r2t) >> PAGE_SHIFT);
+	list_del(&page->lru);
+	__free_pages(page, 2);
+}
+
+/**
+ * __gmap_unshadow_r1t - remove all entries from a shadow region-1 table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ * @r1t: pointer to the start of a shadow region-1 table
+ *
+ * Called with the shadow->guest_table_lock
+ */
+static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr,
+				unsigned long *r1t)
+{
+	unsigned long asce, *r2t;
+	struct page *page;
+	int i;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	asce = (unsigned long) r1t | _ASCE_TYPE_REGION1;
+	for (i = 0; i < 2048; i++, raddr += 1UL << 53) {
+		if (!(r1t[i] & _REGION_ENTRY_ORIGIN))
+			continue;
+		r2t = (unsigned long *)(r1t[i] & _REGION_ENTRY_ORIGIN);
+		__gmap_unshadow_r2t(sg, raddr, r2t);
+		/* Clear entry and flush translation r1t -> r2t */
+		gmap_idte_one(asce, raddr);
+		r1t[i] = _REGION1_ENTRY_EMPTY;
+		/* Free region 2 table */
+		page = pfn_to_page(__pa(r2t) >> PAGE_SHIFT);
+		list_del(&page->lru);
+		__free_pages(page, 2);
+	}
+}
+
+/**
+ * gmap_unshadow - remove a shadow page table completely
+ * @sg: pointer to the shadow guest address space structure
+ *
+ * Called with sg->guest_table_lock
+ */
+static void gmap_unshadow(struct gmap *sg)
+{
+	unsigned long *table;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	if (sg->removed)
+		return;
+	sg->removed = 1;
+	gmap_call_notifier(sg, 0, -1UL);
+	gmap_flush_tlb(sg);
+	table = (unsigned long *)(sg->asce & _ASCE_ORIGIN);
+	switch (sg->asce & _ASCE_TYPE_MASK) {
+	case _ASCE_TYPE_REGION1:
+		__gmap_unshadow_r1t(sg, 0, table);
+		break;
+	case _ASCE_TYPE_REGION2:
+		__gmap_unshadow_r2t(sg, 0, table);
+		break;
+	case _ASCE_TYPE_REGION3:
+		__gmap_unshadow_r3t(sg, 0, table);
+		break;
+	case _ASCE_TYPE_SEGMENT:
+		__gmap_unshadow_sgt(sg, 0, table);
+		break;
+	}
+}
+
+/**
+ * gmap_find_shadow - find a specific asce in the list of shadow tables
+ * @parent: pointer to the parent gmap
+ * @asce: ASCE for which the shadow table is created
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * Returns the pointer to a gmap if a shadow table with the given asce is
+ * already available, ERR_PTR(-EAGAIN) if another one is just being created,
+ * otherwise NULL
+ */
+static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce,
+				     int edat_level)
+{
+	struct gmap *sg;
+
+	list_for_each_entry(sg, &parent->children, list) {
+		if (sg->orig_asce != asce || sg->edat_level != edat_level ||
+		    sg->removed)
+			continue;
+		if (!sg->initialized)
+			return ERR_PTR(-EAGAIN);
+		atomic_inc(&sg->ref_count);
+		return sg;
+	}
+	return NULL;
+}
+
+/**
+ * gmap_shadow_valid - check if a shadow guest address space matches the
+ *                     given properties and is still valid
+ * @sg: pointer to the shadow guest address space structure
+ * @asce: ASCE for which the shadow table is requested
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * Returns 1 if the gmap shadow is still valid and matches the given
+ * properties, the caller can continue using it. Returns 0 otherwise, the
+ * caller has to request a new shadow gmap in this case.
+ *
+ */
+int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level)
+{
+	if (sg->removed)
+		return 0;
+	return sg->orig_asce == asce && sg->edat_level == edat_level;
+}
+EXPORT_SYMBOL_GPL(gmap_shadow_valid);
+
+/**
+ * gmap_shadow - create/find a shadow guest address space
+ * @parent: pointer to the parent gmap
+ * @asce: ASCE for which the shadow table is created
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * The pages of the top level page table referred by the asce parameter
+ * will be set to read-only and marked in the PGSTEs of the kvm process.
+ * The shadow table will be removed automatically on any change to the
+ * PTE mapping for the source table.
+ *
+ * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory,
+ * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the
+ * parent gmap table could not be protected.
+ */
+struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
+			 int edat_level)
+{
+	struct gmap *sg, *new;
+	unsigned long limit;
+	int rc;
+
+	BUG_ON(gmap_is_shadow(parent));
+	spin_lock(&parent->shadow_lock);
+	sg = gmap_find_shadow(parent, asce, edat_level);
+	spin_unlock(&parent->shadow_lock);
+	if (sg)
+		return sg;
+	/* Create a new shadow gmap */
+	limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11));
+	if (asce & _ASCE_REAL_SPACE)
+		limit = -1UL;
+	new = gmap_alloc(limit);
+	if (!new)
+		return ERR_PTR(-ENOMEM);
+	new->mm = parent->mm;
+	new->parent = gmap_get(parent);
+	new->orig_asce = asce;
+	new->edat_level = edat_level;
+	new->initialized = false;
+	spin_lock(&parent->shadow_lock);
+	/* Recheck if another CPU created the same shadow */
+	sg = gmap_find_shadow(parent, asce, edat_level);
+	if (sg) {
+		spin_unlock(&parent->shadow_lock);
+		gmap_free(new);
+		return sg;
+	}
+	if (asce & _ASCE_REAL_SPACE) {
+		/* only allow one real-space gmap shadow */
+		list_for_each_entry(sg, &parent->children, list) {
+			if (sg->orig_asce & _ASCE_REAL_SPACE) {
+				spin_lock(&sg->guest_table_lock);
+				gmap_unshadow(sg);
+				spin_unlock(&sg->guest_table_lock);
+				list_del(&sg->list);
+				gmap_put(sg);
+				break;
+			}
+		}
+	}
+	atomic_set(&new->ref_count, 2);
+	list_add(&new->list, &parent->children);
+	if (asce & _ASCE_REAL_SPACE) {
+		/* nothing to protect, return right away */
+		new->initialized = true;
+		spin_unlock(&parent->shadow_lock);
+		return new;
+	}
+	spin_unlock(&parent->shadow_lock);
+	/* protect after insertion, so it will get properly invalidated */
+	down_read(&parent->mm->mmap_sem);
+	rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN,
+				((asce & _ASCE_TABLE_LENGTH) + 1) * 4096,
+				PROT_READ, PGSTE_VSIE_BIT);
+	up_read(&parent->mm->mmap_sem);
+	spin_lock(&parent->shadow_lock);
+	new->initialized = true;
+	if (rc) {
+		list_del(&new->list);
+		gmap_free(new);
+		new = ERR_PTR(rc);
+	}
+	spin_unlock(&parent->shadow_lock);
+	return new;
+}
+EXPORT_SYMBOL_GPL(gmap_shadow);
+
+/**
+ * gmap_shadow_r2t - create an empty shadow region 2 table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @r2t: parent gmap address of the region 2 table to get shadowed
+ * @fake: r2t references contiguous guest memory block, not a r2t
+ *
+ * The r2t parameter specifies the address of the source table. The
+ * four pages of the source table are made read-only in the parent gmap
+ * address space. A write to the source table area @r2t will automatically
+ * remove the shadow r2 table and all of its decendents.
+ *
+ * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
+ * shadow table structure is incomplete, -ENOMEM if out of memory and
+ * -EFAULT if an address in the parent gmap could not be resolved.
+ *
+ * Called with sg->mm->mmap_sem in read.
+ */
+int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
+		    int fake)
+{
+	unsigned long raddr, origin, offset, len;
+	unsigned long *s_r2t, *table;
+	struct page *page;
+	int rc;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	/* Allocate a shadow region second table */
+	page = alloc_pages(GFP_KERNEL, 2);
+	if (!page)
+		return -ENOMEM;
+	page->index = r2t & _REGION_ENTRY_ORIGIN;
+	if (fake)
+		page->index |= GMAP_SHADOW_FAKE_TABLE;
+	s_r2t = (unsigned long *) page_to_phys(page);
+	/* Install shadow region second table */
+	spin_lock(&sg->guest_table_lock);
+	table = gmap_table_walk(sg, saddr, 4); /* get region-1 pointer */
+	if (!table) {
+		rc = -EAGAIN;		/* Race with unshadow */
+		goto out_free;
+	}
+	if (!(*table & _REGION_ENTRY_INVALID)) {
+		rc = 0;			/* Already established */
+		goto out_free;
+	} else if (*table & _REGION_ENTRY_ORIGIN) {
+		rc = -EAGAIN;		/* Race with shadow */
+		goto out_free;
+	}
+	crst_table_init(s_r2t, _REGION2_ENTRY_EMPTY);
+	/* mark as invalid as long as the parent table is not protected */
+	*table = (unsigned long) s_r2t | _REGION_ENTRY_LENGTH |
+		 _REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID;
+	if (sg->edat_level >= 1)
+		*table |= (r2t & _REGION_ENTRY_PROTECT);
+	list_add(&page->lru, &sg->crst_list);
+	if (fake) {
+		/* nothing to protect for fake tables */
+		*table &= ~_REGION_ENTRY_INVALID;
+		spin_unlock(&sg->guest_table_lock);
+		return 0;
+	}
+	spin_unlock(&sg->guest_table_lock);
+	/* Make r2t read-only in parent gmap page table */
+	raddr = (saddr & 0xffe0000000000000UL) | _SHADOW_RMAP_REGION1;
+	origin = r2t & _REGION_ENTRY_ORIGIN;
+	offset = ((r2t & _REGION_ENTRY_OFFSET) >> 6) * 4096;
+	len = ((r2t & _REGION_ENTRY_LENGTH) + 1) * 4096 - offset;
+	rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+	spin_lock(&sg->guest_table_lock);
+	if (!rc) {
+		table = gmap_table_walk(sg, saddr, 4);
+		if (!table || (*table & _REGION_ENTRY_ORIGIN) !=
+			      (unsigned long) s_r2t)
+			rc = -EAGAIN;		/* Race with unshadow */
+		else
+			*table &= ~_REGION_ENTRY_INVALID;
+	} else {
+		gmap_unshadow_r2t(sg, raddr);
+	}
+	spin_unlock(&sg->guest_table_lock);
+	return rc;
+out_free:
+	spin_unlock(&sg->guest_table_lock);
+	__free_pages(page, 2);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_shadow_r2t);
+
+/**
+ * gmap_shadow_r3t - create a shadow region 3 table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @r3t: parent gmap address of the region 3 table to get shadowed
+ * @fake: r3t references contiguous guest memory block, not a r3t
+ *
+ * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
+ * shadow table structure is incomplete, -ENOMEM if out of memory and
+ * -EFAULT if an address in the parent gmap could not be resolved.
+ *
+ * Called with sg->mm->mmap_sem in read.
+ */
+int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
+		    int fake)
+{
+	unsigned long raddr, origin, offset, len;
+	unsigned long *s_r3t, *table;
+	struct page *page;
+	int rc;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	/* Allocate a shadow region second table */
+	page = alloc_pages(GFP_KERNEL, 2);
+	if (!page)
+		return -ENOMEM;
+	page->index = r3t & _REGION_ENTRY_ORIGIN;
+	if (fake)
+		page->index |= GMAP_SHADOW_FAKE_TABLE;
+	s_r3t = (unsigned long *) page_to_phys(page);
+	/* Install shadow region second table */
+	spin_lock(&sg->guest_table_lock);
+	table = gmap_table_walk(sg, saddr, 3); /* get region-2 pointer */
+	if (!table) {
+		rc = -EAGAIN;		/* Race with unshadow */
+		goto out_free;
+	}
+	if (!(*table & _REGION_ENTRY_INVALID)) {
+		rc = 0;			/* Already established */
+		goto out_free;
+	} else if (*table & _REGION_ENTRY_ORIGIN) {
+		rc = -EAGAIN;		/* Race with shadow */
+	}
+	crst_table_init(s_r3t, _REGION3_ENTRY_EMPTY);
+	/* mark as invalid as long as the parent table is not protected */
+	*table = (unsigned long) s_r3t | _REGION_ENTRY_LENGTH |
+		 _REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID;
+	if (sg->edat_level >= 1)
+		*table |= (r3t & _REGION_ENTRY_PROTECT);
+	list_add(&page->lru, &sg->crst_list);
+	if (fake) {
+		/* nothing to protect for fake tables */
+		*table &= ~_REGION_ENTRY_INVALID;
+		spin_unlock(&sg->guest_table_lock);
+		return 0;
+	}
+	spin_unlock(&sg->guest_table_lock);
+	/* Make r3t read-only in parent gmap page table */
+	raddr = (saddr & 0xfffffc0000000000UL) | _SHADOW_RMAP_REGION2;
+	origin = r3t & _REGION_ENTRY_ORIGIN;
+	offset = ((r3t & _REGION_ENTRY_OFFSET) >> 6) * 4096;
+	len = ((r3t & _REGION_ENTRY_LENGTH) + 1) * 4096 - offset;
+	rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+	spin_lock(&sg->guest_table_lock);
+	if (!rc) {
+		table = gmap_table_walk(sg, saddr, 3);
+		if (!table || (*table & _REGION_ENTRY_ORIGIN) !=
+			      (unsigned long) s_r3t)
+			rc = -EAGAIN;		/* Race with unshadow */
+		else
+			*table &= ~_REGION_ENTRY_INVALID;
+	} else {
+		gmap_unshadow_r3t(sg, raddr);
+	}
+	spin_unlock(&sg->guest_table_lock);
+	return rc;
+out_free:
+	spin_unlock(&sg->guest_table_lock);
+	__free_pages(page, 2);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_shadow_r3t);
+
+/**
+ * gmap_shadow_sgt - create a shadow segment table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @sgt: parent gmap address of the segment table to get shadowed
+ * @fake: sgt references contiguous guest memory block, not a sgt
+ *
+ * Returns: 0 if successfully shadowed or already shadowed, -EAGAIN if the
+ * shadow table structure is incomplete, -ENOMEM if out of memory and
+ * -EFAULT if an address in the parent gmap could not be resolved.
+ *
+ * Called with sg->mm->mmap_sem in read.
+ */
+int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
+		    int fake)
+{
+	unsigned long raddr, origin, offset, len;
+	unsigned long *s_sgt, *table;
+	struct page *page;
+	int rc;
+
+	BUG_ON(!gmap_is_shadow(sg) || (sgt & _REGION3_ENTRY_LARGE));
+	/* Allocate a shadow segment table */
+	page = alloc_pages(GFP_KERNEL, 2);
+	if (!page)
+		return -ENOMEM;
+	page->index = sgt & _REGION_ENTRY_ORIGIN;
+	if (fake)
+		page->index |= GMAP_SHADOW_FAKE_TABLE;
+	s_sgt = (unsigned long *) page_to_phys(page);
+	/* Install shadow region second table */
+	spin_lock(&sg->guest_table_lock);
+	table = gmap_table_walk(sg, saddr, 2); /* get region-3 pointer */
+	if (!table) {
+		rc = -EAGAIN;		/* Race with unshadow */
+		goto out_free;
+	}
+	if (!(*table & _REGION_ENTRY_INVALID)) {
+		rc = 0;			/* Already established */
+		goto out_free;
+	} else if (*table & _REGION_ENTRY_ORIGIN) {
+		rc = -EAGAIN;		/* Race with shadow */
+		goto out_free;
+	}
+	crst_table_init(s_sgt, _SEGMENT_ENTRY_EMPTY);
+	/* mark as invalid as long as the parent table is not protected */
+	*table = (unsigned long) s_sgt | _REGION_ENTRY_LENGTH |
+		 _REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID;
+	if (sg->edat_level >= 1)
+		*table |= sgt & _REGION_ENTRY_PROTECT;
+	list_add(&page->lru, &sg->crst_list);
+	if (fake) {
+		/* nothing to protect for fake tables */
+		*table &= ~_REGION_ENTRY_INVALID;
+		spin_unlock(&sg->guest_table_lock);
+		return 0;
+	}
+	spin_unlock(&sg->guest_table_lock);
+	/* Make sgt read-only in parent gmap page table */
+	raddr = (saddr & 0xffffffff80000000UL) | _SHADOW_RMAP_REGION3;
+	origin = sgt & _REGION_ENTRY_ORIGIN;
+	offset = ((sgt & _REGION_ENTRY_OFFSET) >> 6) * 4096;
+	len = ((sgt & _REGION_ENTRY_LENGTH) + 1) * 4096 - offset;
+	rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+	spin_lock(&sg->guest_table_lock);
+	if (!rc) {
+		table = gmap_table_walk(sg, saddr, 2);
+		if (!table || (*table & _REGION_ENTRY_ORIGIN) !=
+			      (unsigned long) s_sgt)
+			rc = -EAGAIN;		/* Race with unshadow */
+		else
+			*table &= ~_REGION_ENTRY_INVALID;
+	} else {
+		gmap_unshadow_sgt(sg, raddr);
+	}
+	spin_unlock(&sg->guest_table_lock);
+	return rc;
+out_free:
+	spin_unlock(&sg->guest_table_lock);
+	__free_pages(page, 2);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_shadow_sgt);
+
+/**
+ * gmap_shadow_lookup_pgtable - find a shadow page table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: the address in the shadow aguest address space
+ * @pgt: parent gmap address of the page table to get shadowed
+ * @dat_protection: if the pgtable is marked as protected by dat
+ * @fake: pgt references contiguous guest memory block, not a pgtable
+ *
+ * Returns 0 if the shadow page table was found and -EAGAIN if the page
+ * table was not found.
+ *
+ * Called with sg->mm->mmap_sem in read.
+ */
+int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr,
+			   unsigned long *pgt, int *dat_protection,
+			   int *fake)
+{
+	unsigned long *table;
+	struct page *page;
+	int rc;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	spin_lock(&sg->guest_table_lock);
+	table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */
+	if (table && !(*table & _SEGMENT_ENTRY_INVALID)) {
+		/* Shadow page tables are full pages (pte+pgste) */
+		page = pfn_to_page(*table >> PAGE_SHIFT);
+		*pgt = page->index & ~GMAP_SHADOW_FAKE_TABLE;
+		*dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT);
+		*fake = !!(page->index & GMAP_SHADOW_FAKE_TABLE);
+		rc = 0;
+	} else  {
+		rc = -EAGAIN;
+	}
+	spin_unlock(&sg->guest_table_lock);
+	return rc;
+
+}
+EXPORT_SYMBOL_GPL(gmap_shadow_pgt_lookup);
+
+/**
+ * gmap_shadow_pgt - instantiate a shadow page table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @pgt: parent gmap address of the page table to get shadowed
+ * @fake: pgt references contiguous guest memory block, not a pgtable
+ *
+ * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
+ * shadow table structure is incomplete, -ENOMEM if out of memory,
+ * -EFAULT if an address in the parent gmap could not be resolved and
+ *
+ * Called with gmap->mm->mmap_sem in read
+ */
+int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
+		    int fake)
+{
+	unsigned long raddr, origin;
+	unsigned long *s_pgt, *table;
+	struct page *page;
+	int rc;
+
+	BUG_ON(!gmap_is_shadow(sg) || (pgt & _SEGMENT_ENTRY_LARGE));
+	/* Allocate a shadow page table */
+	page = page_table_alloc_pgste(sg->mm);
+	if (!page)
+		return -ENOMEM;
+	page->index = pgt & _SEGMENT_ENTRY_ORIGIN;
+	if (fake)
+		page->index |= GMAP_SHADOW_FAKE_TABLE;
+	s_pgt = (unsigned long *) page_to_phys(page);
+	/* Install shadow page table */
+	spin_lock(&sg->guest_table_lock);
+	table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */
+	if (!table) {
+		rc = -EAGAIN;		/* Race with unshadow */
+		goto out_free;
+	}
+	if (!(*table & _SEGMENT_ENTRY_INVALID)) {
+		rc = 0;			/* Already established */
+		goto out_free;
+	} else if (*table & _SEGMENT_ENTRY_ORIGIN) {
+		rc = -EAGAIN;		/* Race with shadow */
+		goto out_free;
+	}
+	/* mark as invalid as long as the parent table is not protected */
+	*table = (unsigned long) s_pgt | _SEGMENT_ENTRY |
+		 (pgt & _SEGMENT_ENTRY_PROTECT) | _SEGMENT_ENTRY_INVALID;
+	list_add(&page->lru, &sg->pt_list);
+	if (fake) {
+		/* nothing to protect for fake tables */
+		*table &= ~_SEGMENT_ENTRY_INVALID;
+		spin_unlock(&sg->guest_table_lock);
+		return 0;
+	}
+	spin_unlock(&sg->guest_table_lock);
+	/* Make pgt read-only in parent gmap page table (not the pgste) */
+	raddr = (saddr & 0xfffffffffff00000UL) | _SHADOW_RMAP_SEGMENT;
+	origin = pgt & _SEGMENT_ENTRY_ORIGIN & PAGE_MASK;
+	rc = gmap_protect_rmap(sg, raddr, origin, PAGE_SIZE, PROT_READ);
+	spin_lock(&sg->guest_table_lock);
+	if (!rc) {
+		table = gmap_table_walk(sg, saddr, 1);
+		if (!table || (*table & _SEGMENT_ENTRY_ORIGIN) !=
+			      (unsigned long) s_pgt)
+			rc = -EAGAIN;		/* Race with unshadow */
+		else
+			*table &= ~_SEGMENT_ENTRY_INVALID;
+	} else {
+		gmap_unshadow_pgt(sg, raddr);
+	}
+	spin_unlock(&sg->guest_table_lock);
+	return rc;
+out_free:
+	spin_unlock(&sg->guest_table_lock);
+	page_table_free_pgste(page);
+	return rc;
+
+}
+EXPORT_SYMBOL_GPL(gmap_shadow_pgt);
+
+/**
+ * gmap_shadow_page - create a shadow page mapping
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @pte: pte in parent gmap address space to get shadowed
+ *
+ * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
+ * shadow table structure is incomplete, -ENOMEM if out of memory and
+ * -EFAULT if an address in the parent gmap could not be resolved.
+ *
+ * Called with sg->mm->mmap_sem in read.
+ */
+int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
+{
+	struct gmap *parent;
+	struct gmap_rmap *rmap;
+	unsigned long vmaddr, paddr;
+	spinlock_t *ptl;
+	pte_t *sptep, *tptep;
+	int prot;
+	int rc;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	parent = sg->parent;
+	prot = (pte_val(pte) & _PAGE_PROTECT) ? PROT_READ : PROT_WRITE;
+
+	rmap = kzalloc(sizeof(*rmap), GFP_KERNEL);
+	if (!rmap)
+		return -ENOMEM;
+	rmap->raddr = (saddr & PAGE_MASK) | _SHADOW_RMAP_PGTABLE;
+
+	while (1) {
+		paddr = pte_val(pte) & PAGE_MASK;
+		vmaddr = __gmap_translate(parent, paddr);
+		if (IS_ERR_VALUE(vmaddr)) {
+			rc = vmaddr;
+			break;
+		}
+		rc = radix_tree_preload(GFP_KERNEL);
 		if (rc)
 			break;
-		/* Walk the process page table, lock and get pte pointer */
-		ptep = get_locked_pte(gmap->mm, addr, &ptl);
-		VM_BUG_ON(!ptep);
-		/* Set notification bit in the pgste of the pte */
-		if ((pte_val(*ptep) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) {
-			ptep_set_notify(gmap->mm, addr, ptep);
-			gaddr += PAGE_SIZE;
-			len -= PAGE_SIZE;
+		rc = -EAGAIN;
+		sptep = gmap_pte_op_walk(parent, paddr, &ptl);
+		if (sptep) {
+			spin_lock(&sg->guest_table_lock);
+			/* Get page table pointer */
+			tptep = (pte_t *) gmap_table_walk(sg, saddr, 0);
+			if (!tptep) {
+				spin_unlock(&sg->guest_table_lock);
+				gmap_pte_op_end(ptl);
+				radix_tree_preload_end();
+				break;
+			}
+			rc = ptep_shadow_pte(sg->mm, saddr, sptep, tptep, pte);
+			if (rc > 0) {
+				/* Success and a new mapping */
+				gmap_insert_rmap(sg, vmaddr, rmap);
+				rmap = NULL;
+				rc = 0;
+			}
+			gmap_pte_op_end(ptl);
+			spin_unlock(&sg->guest_table_lock);
 		}
-		pte_unmap_unlock(ptep, ptl);
+		radix_tree_preload_end();
+		if (!rc)
+			break;
+		rc = gmap_pte_op_fixup(parent, paddr, vmaddr, prot);
+		if (rc)
+			break;
 	}
-	up_read(&gmap->mm->mmap_sem);
+	kfree(rmap);
 	return rc;
 }
-EXPORT_SYMBOL_GPL(gmap_ipte_notify);
+EXPORT_SYMBOL_GPL(gmap_shadow_page);
+
+/**
+ * gmap_shadow_notify - handle notifications for shadow gmap
+ *
+ * Called with sg->parent->shadow_lock.
+ */
+static void gmap_shadow_notify(struct gmap *sg, unsigned long vmaddr,
+			       unsigned long offset, pte_t *pte)
+{
+	struct gmap_rmap *rmap, *rnext, *head;
+	unsigned long gaddr, start, end, bits, raddr;
+	unsigned long *table;
+
+	BUG_ON(!gmap_is_shadow(sg));
+	spin_lock(&sg->parent->guest_table_lock);
+	table = radix_tree_lookup(&sg->parent->host_to_guest,
+				  vmaddr >> PMD_SHIFT);
+	gaddr = table ? __gmap_segment_gaddr(table) + offset : 0;
+	spin_unlock(&sg->parent->guest_table_lock);
+	if (!table)
+		return;
+
+	spin_lock(&sg->guest_table_lock);
+	if (sg->removed) {
+		spin_unlock(&sg->guest_table_lock);
+		return;
+	}
+	/* Check for top level table */
+	start = sg->orig_asce & _ASCE_ORIGIN;
+	end = start + ((sg->orig_asce & _ASCE_TABLE_LENGTH) + 1) * 4096;
+	if (!(sg->orig_asce & _ASCE_REAL_SPACE) && gaddr >= start &&
+	    gaddr < end) {
+		/* The complete shadow table has to go */
+		gmap_unshadow(sg);
+		spin_unlock(&sg->guest_table_lock);
+		list_del(&sg->list);
+		gmap_put(sg);
+		return;
+	}
+	/* Remove the page table tree from on specific entry */
+	head = radix_tree_delete(&sg->host_to_rmap, vmaddr >> 12);
+	gmap_for_each_rmap_safe(rmap, rnext, head) {
+		bits = rmap->raddr & _SHADOW_RMAP_MASK;
+		raddr = rmap->raddr ^ bits;
+		switch (bits) {
+		case _SHADOW_RMAP_REGION1:
+			gmap_unshadow_r2t(sg, raddr);
+			break;
+		case _SHADOW_RMAP_REGION2:
+			gmap_unshadow_r3t(sg, raddr);
+			break;
+		case _SHADOW_RMAP_REGION3:
+			gmap_unshadow_sgt(sg, raddr);
+			break;
+		case _SHADOW_RMAP_SEGMENT:
+			gmap_unshadow_pgt(sg, raddr);
+			break;
+		case _SHADOW_RMAP_PGTABLE:
+			gmap_unshadow_page(sg, raddr);
+			break;
+		}
+		kfree(rmap);
+	}
+	spin_unlock(&sg->guest_table_lock);
+}
 
 /**
  * ptep_notify - call all invalidation callbacks for a specific pte.
  * @mm: pointer to the process mm_struct
  * @addr: virtual address in the process address space
  * @pte: pointer to the page table entry
+ * @bits: bits from the pgste that caused the notify call
  *
  * This function is assumed to be called with the page table lock held
  * for the pte to notify.
  */
-void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, pte_t *pte)
+void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
+		 pte_t *pte, unsigned long bits)
 {
 	unsigned long offset, gaddr;
 	unsigned long *table;
-	struct gmap_notifier *nb;
-	struct gmap *gmap;
+	struct gmap *gmap, *sg, *next;
 
 	offset = ((unsigned long) pte) & (255 * sizeof(pte_t));
 	offset = offset * (4096 / sizeof(pte_t));
-	spin_lock(&gmap_notifier_lock);
-	list_for_each_entry(gmap, &mm->context.gmap_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+		if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) {
+			spin_lock(&gmap->shadow_lock);
+			list_for_each_entry_safe(sg, next,
+						 &gmap->children, list)
+				gmap_shadow_notify(sg, vmaddr, offset, pte);
+			spin_unlock(&gmap->shadow_lock);
+		}
+		if (!(bits & PGSTE_IN_BIT))
+			continue;
+		spin_lock(&gmap->guest_table_lock);
 		table = radix_tree_lookup(&gmap->host_to_guest,
 					  vmaddr >> PMD_SHIFT);
-		if (!table)
-			continue;
-		gaddr = __gmap_segment_gaddr(table) + offset;
-		list_for_each_entry(nb, &gmap_notifier_list, list)
-			nb->notifier_call(gmap, gaddr);
+		if (table)
+			gaddr = __gmap_segment_gaddr(table) + offset;
+		spin_unlock(&gmap->guest_table_lock);
+		if (table)
+			gmap_call_notifier(gmap, gaddr, gaddr + PAGE_SIZE - 1);
 	}
-	spin_unlock(&gmap_notifier_lock);
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(ptep_notify);
 
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index e19d853883be..cd404aa3931c 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -11,6 +11,12 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 
+/*
+ * If the bit selected by single-bit bitmask "a" is set within "x", move
+ * it to the position indicated by single-bit bitmask "b".
+ */
+#define move_set_bit(x, a, b)	(((x) & (a)) >> ilog2(a) << ilog2(b))
+
 static inline unsigned long __pte_to_rste(pte_t pte)
 {
 	unsigned long rste;
@@ -37,13 +43,22 @@ static inline unsigned long __pte_to_rste(pte_t pte)
 	 */
 	if (pte_present(pte)) {
 		rste = pte_val(pte) & PAGE_MASK;
-		rste |= (pte_val(pte) & _PAGE_READ) >> 4;
-		rste |= (pte_val(pte) & _PAGE_WRITE) >> 4;
-		rste |= (pte_val(pte) & _PAGE_INVALID) >> 5;
-		rste |= (pte_val(pte) & _PAGE_PROTECT);
-		rste |= (pte_val(pte) & _PAGE_DIRTY) << 10;
-		rste |= (pte_val(pte) & _PAGE_YOUNG) << 10;
-		rste |= (pte_val(pte) & _PAGE_SOFT_DIRTY) << 13;
+		rste |= move_set_bit(pte_val(pte), _PAGE_READ,
+				     _SEGMENT_ENTRY_READ);
+		rste |= move_set_bit(pte_val(pte), _PAGE_WRITE,
+				     _SEGMENT_ENTRY_WRITE);
+		rste |= move_set_bit(pte_val(pte), _PAGE_INVALID,
+				     _SEGMENT_ENTRY_INVALID);
+		rste |= move_set_bit(pte_val(pte), _PAGE_PROTECT,
+				     _SEGMENT_ENTRY_PROTECT);
+		rste |= move_set_bit(pte_val(pte), _PAGE_DIRTY,
+				     _SEGMENT_ENTRY_DIRTY);
+		rste |= move_set_bit(pte_val(pte), _PAGE_YOUNG,
+				     _SEGMENT_ENTRY_YOUNG);
+#ifdef CONFIG_MEM_SOFT_DIRTY
+		rste |= move_set_bit(pte_val(pte), _PAGE_SOFT_DIRTY,
+				     _SEGMENT_ENTRY_SOFT_DIRTY);
+#endif
 	} else
 		rste = _SEGMENT_ENTRY_INVALID;
 	return rste;
@@ -82,13 +97,22 @@ static inline pte_t __rste_to_pte(unsigned long rste)
 	if (present) {
 		pte_val(pte) = rste & _SEGMENT_ENTRY_ORIGIN_LARGE;
 		pte_val(pte) |= _PAGE_LARGE | _PAGE_PRESENT;
-		pte_val(pte) |= (rste & _SEGMENT_ENTRY_READ) << 4;
-		pte_val(pte) |= (rste & _SEGMENT_ENTRY_WRITE) << 4;
-		pte_val(pte) |= (rste & _SEGMENT_ENTRY_INVALID) << 5;
-		pte_val(pte) |= (rste & _SEGMENT_ENTRY_PROTECT);
-		pte_val(pte) |= (rste & _SEGMENT_ENTRY_DIRTY) >> 10;
-		pte_val(pte) |= (rste & _SEGMENT_ENTRY_YOUNG) >> 10;
-		pte_val(pte) |= (rste & _SEGMENT_ENTRY_SOFT_DIRTY) >> 13;
+		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_READ,
+					     _PAGE_READ);
+		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_WRITE,
+					     _PAGE_WRITE);
+		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_INVALID,
+					     _PAGE_INVALID);
+		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_PROTECT,
+					     _PAGE_PROTECT);
+		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_DIRTY,
+					     _PAGE_DIRTY);
+		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_YOUNG,
+					     _PAGE_YOUNG);
+#ifdef CONFIG_MEM_SOFT_DIRTY
+		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY,
+					     _PAGE_DIRTY);
+#endif
 	} else
 		pte_val(pte) = _PAGE_INVALID;
 	return pte;
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index e2565d2d0c32..995f78532cc2 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -137,6 +137,29 @@ static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
 	return new;
 }
 
+#ifdef CONFIG_PGSTE
+
+struct page *page_table_alloc_pgste(struct mm_struct *mm)
+{
+	struct page *page;
+	unsigned long *table;
+
+	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+	if (page) {
+		table = (unsigned long *) page_to_phys(page);
+		clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
+		clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
+	}
+	return page;
+}
+
+void page_table_free_pgste(struct page *page)
+{
+	__free_page(page);
+}
+
+#endif /* CONFIG_PGSTE */
+
 /*
  * page table entry allocation/free routines.
  */
@@ -149,7 +172,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 	/* Try to get a fragment of a 4K page as a 2K page table */
 	if (!mm_alloc_pgste(mm)) {
 		table = NULL;
-		spin_lock_bh(&mm->context.list_lock);
+		spin_lock_bh(&mm->context.pgtable_lock);
 		if (!list_empty(&mm->context.pgtable_list)) {
 			page = list_first_entry(&mm->context.pgtable_list,
 						struct page, lru);
@@ -164,7 +187,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 				list_del(&page->lru);
 			}
 		}
-		spin_unlock_bh(&mm->context.list_lock);
+		spin_unlock_bh(&mm->context.pgtable_lock);
 		if (table)
 			return table;
 	}
@@ -187,9 +210,9 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 		/* Return the first 2K fragment of the page */
 		atomic_set(&page->_mapcount, 1);
 		clear_table(table, _PAGE_INVALID, PAGE_SIZE);
-		spin_lock_bh(&mm->context.list_lock);
+		spin_lock_bh(&mm->context.pgtable_lock);
 		list_add(&page->lru, &mm->context.pgtable_list);
-		spin_unlock_bh(&mm->context.list_lock);
+		spin_unlock_bh(&mm->context.pgtable_lock);
 	}
 	return table;
 }
@@ -203,13 +226,13 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	if (!mm_alloc_pgste(mm)) {
 		/* Free 2K page table fragment of a 4K page */
 		bit = (__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t));
-		spin_lock_bh(&mm->context.list_lock);
+		spin_lock_bh(&mm->context.pgtable_lock);
 		mask = atomic_xor_bits(&page->_mapcount, 1U << bit);
 		if (mask & 3)
 			list_add(&page->lru, &mm->context.pgtable_list);
 		else
 			list_del(&page->lru);
-		spin_unlock_bh(&mm->context.list_lock);
+		spin_unlock_bh(&mm->context.pgtable_lock);
 		if (mask != 0)
 			return;
 	}
@@ -235,13 +258,13 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
 		return;
 	}
 	bit = (__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t));
-	spin_lock_bh(&mm->context.list_lock);
+	spin_lock_bh(&mm->context.pgtable_lock);
 	mask = atomic_xor_bits(&page->_mapcount, 0x11U << bit);
 	if (mask & 3)
 		list_add_tail(&page->lru, &mm->context.pgtable_list);
 	else
 		list_del(&page->lru);
-	spin_unlock_bh(&mm->context.list_lock);
+	spin_unlock_bh(&mm->context.pgtable_lock);
 	table = (unsigned long *) (__pa(table) | (1U << bit));
 	tlb_remove_table(tlb, table);
 }
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index b98d1a152d46..5f092015aaa7 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -174,14 +174,17 @@ static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
 	return pgste;
 }
 
-static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,
-					unsigned long addr,
-					pte_t *ptep, pgste_t pgste)
+static inline pgste_t pgste_pte_notify(struct mm_struct *mm,
+				       unsigned long addr,
+				       pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-	if (pgste_val(pgste) & PGSTE_IN_BIT) {
-		pgste_val(pgste) &= ~PGSTE_IN_BIT;
-		ptep_notify(mm, addr, ptep);
+	unsigned long bits;
+
+	bits = pgste_val(pgste) & (PGSTE_IN_BIT | PGSTE_VSIE_BIT);
+	if (bits) {
+		pgste_val(pgste) ^= bits;
+		ptep_notify(mm, addr, ptep, bits);
 	}
 #endif
 	return pgste;
@@ -194,7 +197,7 @@ static inline pgste_t ptep_xchg_start(struct mm_struct *mm,
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(mm, addr, ptep, pgste);
+		pgste = pgste_pte_notify(mm, addr, ptep, pgste);
 	}
 	return pgste;
 }
@@ -459,6 +462,90 @@ void ptep_set_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	preempt_enable();
 }
 
+/**
+ * ptep_force_prot - change access rights of a locked pte
+ * @mm: pointer to the process mm_struct
+ * @addr: virtual address in the guest address space
+ * @ptep: pointer to the page table entry
+ * @prot: indicates guest access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bit: pgste bit to set (e.g. for notification)
+ *
+ * Returns 0 if the access rights were changed and -EAGAIN if the current
+ * and requested access rights are incompatible.
+ */
+int ptep_force_prot(struct mm_struct *mm, unsigned long addr,
+		    pte_t *ptep, int prot, unsigned long bit)
+{
+	pte_t entry;
+	pgste_t pgste;
+	int pte_i, pte_p;
+
+	pgste = pgste_get_lock(ptep);
+	entry = *ptep;
+	/* Check pte entry after all locks have been acquired */
+	pte_i = pte_val(entry) & _PAGE_INVALID;
+	pte_p = pte_val(entry) & _PAGE_PROTECT;
+	if ((pte_i && (prot != PROT_NONE)) ||
+	    (pte_p && (prot & PROT_WRITE))) {
+		pgste_set_unlock(ptep, pgste);
+		return -EAGAIN;
+	}
+	/* Change access rights and set pgste bit */
+	if (prot == PROT_NONE && !pte_i) {
+		ptep_flush_direct(mm, addr, ptep);
+		pgste = pgste_update_all(entry, pgste, mm);
+		pte_val(entry) |= _PAGE_INVALID;
+	}
+	if (prot == PROT_READ && !pte_p) {
+		ptep_flush_direct(mm, addr, ptep);
+		pte_val(entry) &= ~_PAGE_INVALID;
+		pte_val(entry) |= _PAGE_PROTECT;
+	}
+	pgste_val(pgste) |= bit;
+	pgste = pgste_set_pte(ptep, pgste, entry);
+	pgste_set_unlock(ptep, pgste);
+	return 0;
+}
+
+int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr,
+		    pte_t *sptep, pte_t *tptep, pte_t pte)
+{
+	pgste_t spgste, tpgste;
+	pte_t spte, tpte;
+	int rc = -EAGAIN;
+
+	if (!(pte_val(*tptep) & _PAGE_INVALID))
+		return 0;	/* already shadowed */
+	spgste = pgste_get_lock(sptep);
+	spte = *sptep;
+	if (!(pte_val(spte) & _PAGE_INVALID) &&
+	    !((pte_val(spte) & _PAGE_PROTECT) &&
+	      !(pte_val(pte) & _PAGE_PROTECT))) {
+		pgste_val(spgste) |= PGSTE_VSIE_BIT;
+		tpgste = pgste_get_lock(tptep);
+		pte_val(tpte) = (pte_val(spte) & PAGE_MASK) |
+				(pte_val(pte) & _PAGE_PROTECT);
+		/* don't touch the storage key - it belongs to parent pgste */
+		tpgste = pgste_set_pte(tptep, tpgste, tpte);
+		pgste_set_unlock(tptep, tpgste);
+		rc = 1;
+	}
+	pgste_set_unlock(sptep, spgste);
+	return rc;
+}
+
+void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep)
+{
+	pgste_t pgste;
+
+	pgste = pgste_get_lock(ptep);
+	/* notifier is called by the caller */
+	ptep_flush_direct(mm, saddr, ptep);
+	/* don't touch the storage key - it belongs to parent pgste */
+	pgste = pgste_set_pte(ptep, pgste, __pte(_PAGE_INVALID));
+	pgste_set_unlock(ptep, pgste);
+}
+
 static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry)
 {
 	if (!non_swap_entry(entry))
@@ -532,7 +619,7 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
 	pgste_val(pgste) &= ~PGSTE_UC_BIT;
 	pte = *ptep;
 	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
-		pgste = pgste_ipte_notify(mm, addr, ptep, pgste);
+		pgste = pgste_pte_notify(mm, addr, ptep, pgste);
 		__ptep_ipte(addr, ptep);
 		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
 			pte_val(pte) |= _PAGE_PROTECT;
@@ -555,12 +642,9 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	pgste_t old, new;
 	pte_t *ptep;
 
-	down_read(&mm->mmap_sem);
 	ptep = get_locked_pte(mm, addr, &ptl);
-	if (unlikely(!ptep)) {
-		up_read(&mm->mmap_sem);
+	if (unlikely(!ptep))
 		return -EFAULT;
-	}
 
 	new = old = pgste_get_lock(ptep);
 	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
@@ -587,45 +671,100 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 
 	pgste_set_unlock(ptep, new);
 	pte_unmap_unlock(ptep, ptl);
-	up_read(&mm->mmap_sem);
 	return 0;
 }
 EXPORT_SYMBOL(set_guest_storage_key);
 
-unsigned char get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
+/**
+ * Conditionally set a guest storage key (handling csske).
+ * oldkey will be updated when either mr or mc is set and a pointer is given.
+ *
+ * Returns 0 if a guests storage key update wasn't necessary, 1 if the guest
+ * storage key was updated and -EFAULT on access errors.
+ */
+int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
+			       unsigned char key, unsigned char *oldkey,
+			       bool nq, bool mr, bool mc)
+{
+	unsigned char tmp, mask = _PAGE_ACC_BITS | _PAGE_FP_BIT;
+	int rc;
+
+	/* we can drop the pgste lock between getting and setting the key */
+	if (mr | mc) {
+		rc = get_guest_storage_key(current->mm, addr, &tmp);
+		if (rc)
+			return rc;
+		if (oldkey)
+			*oldkey = tmp;
+		if (!mr)
+			mask |= _PAGE_REFERENCED;
+		if (!mc)
+			mask |= _PAGE_CHANGED;
+		if (!((tmp ^ key) & mask))
+			return 0;
+	}
+	rc = set_guest_storage_key(current->mm, addr, key, nq);
+	return rc < 0 ? rc : 1;
+}
+EXPORT_SYMBOL(cond_set_guest_storage_key);
+
+/**
+ * Reset a guest reference bit (rrbe), returning the reference and changed bit.
+ *
+ * Returns < 0 in case of error, otherwise the cc to be reported to the guest.
+ */
+int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 {
-	unsigned char key;
 	spinlock_t *ptl;
-	pgste_t pgste;
+	pgste_t old, new;
 	pte_t *ptep;
+	int cc = 0;
 
-	down_read(&mm->mmap_sem);
 	ptep = get_locked_pte(mm, addr, &ptl);
-	if (unlikely(!ptep)) {
-		up_read(&mm->mmap_sem);
+	if (unlikely(!ptep))
 		return -EFAULT;
-	}
-	pgste = pgste_get_lock(ptep);
 
-	if (pte_val(*ptep) & _PAGE_INVALID) {
-		key  = (pgste_val(pgste) & PGSTE_ACC_BITS) >> 56;
-		key |= (pgste_val(pgste) & PGSTE_FP_BIT) >> 56;
-		key |= (pgste_val(pgste) & PGSTE_GR_BIT) >> 48;
-		key |= (pgste_val(pgste) & PGSTE_GC_BIT) >> 48;
-	} else {
-		key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK);
+	new = old = pgste_get_lock(ptep);
+	/* Reset guest reference bit only */
+	pgste_val(new) &= ~PGSTE_GR_BIT;
 
-		/* Reflect guest's logical view, not physical */
-		if (pgste_val(pgste) & PGSTE_GR_BIT)
-			key |= _PAGE_REFERENCED;
-		if (pgste_val(pgste) & PGSTE_GC_BIT)
-			key |= _PAGE_CHANGED;
+	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
+		cc = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
+		/* Merge real referenced bit into host-set */
+		pgste_val(new) |= ((unsigned long) cc << 53) & PGSTE_HR_BIT;
 	}
+	/* Reflect guest's logical view, not physical */
+	cc |= (pgste_val(old) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 49;
+	/* Changing the guest storage key is considered a change of the page */
+	if ((pgste_val(new) ^ pgste_val(old)) & PGSTE_GR_BIT)
+		pgste_val(new) |= PGSTE_UC_BIT;
+
+	pgste_set_unlock(ptep, new);
+	pte_unmap_unlock(ptep, ptl);
+	return 0;
+}
+EXPORT_SYMBOL(reset_guest_reference_bit);
+
+int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
+			  unsigned char *key)
+{
+	spinlock_t *ptl;
+	pgste_t pgste;
+	pte_t *ptep;
 
+	ptep = get_locked_pte(mm, addr, &ptl);
+	if (unlikely(!ptep))
+		return -EFAULT;
+
+	pgste = pgste_get_lock(ptep);
+	*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
+	if (!(pte_val(*ptep) & _PAGE_INVALID))
+		*key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK);
+	/* Reflect guest's logical view, not physical */
+	*key |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
 	pgste_set_unlock(ptep, pgste);
 	pte_unmap_unlock(ptep, ptl);
-	up_read(&mm->mmap_sem);
-	return key;
+	return 0;
 }
 EXPORT_SYMBOL(get_guest_storage_key);
 #endif
diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c
index fbc394e16b2c..37e0bb835516 100644
--- a/arch/s390/numa/mode_emu.c
+++ b/arch/s390/numa/mode_emu.c
@@ -482,8 +482,12 @@ static int emu_setup_nodes_adjust(int nodes)
  */
 static void emu_setup(void)
 {
+	int nid;
+
 	emu_size = emu_setup_size_adjust(emu_size);
 	emu_nodes = emu_setup_nodes_adjust(emu_nodes);
+	for (nid = 0; nid < emu_nodes; nid++)
+		node_set(nid, node_possible_map);
 	pr_info("Creating %d nodes with memory stripe size %ld MB\n",
 		emu_nodes, emu_size >> 20);
 }
diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
index 2794845061c6..f576f1073378 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/numa/numa.c
@@ -26,8 +26,14 @@ EXPORT_SYMBOL(node_data);
 cpumask_t node_to_cpumask_map[MAX_NUMNODES];
 EXPORT_SYMBOL(node_to_cpumask_map);
 
+static void plain_setup(void)
+{
+	node_set(0, node_possible_map);
+}
+
 const struct numa_mode numa_mode_plain = {
 	.name = "plain",
+	.setup = plain_setup,
 };
 
 static const struct numa_mode *mode = &numa_mode_plain;
@@ -126,13 +132,13 @@ static void __init numa_setup_memory(void)
 void __init numa_setup(void)
 {
 	pr_info("NUMA mode: %s\n", mode->name);
+	nodes_clear(node_possible_map);
 	if (mode->setup)
 		mode->setup();
 	numa_setup_memory();
 	memblock_dump_all();
 }
 
-
 /*
  * numa_init_early() - Initialization initcall
  *
diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c
index e2660d27889b..fe4e6c910dd7 100644
--- a/arch/s390/tools/gen_facilities.c
+++ b/arch/s390/tools/gen_facilities.c
@@ -39,7 +39,6 @@ static void print_facility_list(struct facility_def *def)
 	printf("#define %s ", def->name);
 	for (i = 0; i <= high; i++)
 		printf("_AC(0x%016llx,UL)%c", array[i], i < high ? ',' : '\n');
-	printf("#define %s_DWORDS %d\n", def->name, high + 1);
 	free(array);
 }
 
diff --git a/arch/score/mm/init.c b/arch/score/mm/init.c
index 9fbce49ad3bd..444c26c0f750 100644
--- a/arch/score/mm/init.c
+++ b/arch/score/mm/init.c
@@ -91,7 +91,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
-void __init_refok free_initmem(void)
+void __ref free_initmem(void)
 {
 	free_initmem_default(POISON_FREE_INITMEM);
 }
diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c
index bf3a166a5407..911ffb9f115b 100644
--- a/arch/sh/boards/of-generic.c
+++ b/arch/sh/boards/of-generic.c
@@ -9,9 +9,7 @@
  */
 
 #include <linux/of.h>
-#include <linux/of_platform.h>
 #include <linux/of_fdt.h>
-#include <linux/of_iommu.h>
 #include <linux/clocksource.h>
 #include <linux/irqchip.h>
 #include <linux/clk-provider.h>
@@ -180,17 +178,3 @@ void __init arch_init_clk_ops(struct sh_clk_ops **ops, int idx)
 void __init plat_irq_setup(void)
 {
 }
-
-static int __init sh_of_device_init(void)
-{
-	pr_info("SH generic board support: populating platform devices\n");
-	if (of_have_populated_dt()) {
-		of_iommu_init();
-		of_platform_populate(NULL, of_default_bus_match_table,
-				     NULL, NULL);
-	} else {
-		pr_crit("Device tree not populated\n");
-	}
-	return 0;
-}
-arch_initcall_sync(sh_of_device_init);
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index d5462b7bc514..84563e39a5b8 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -221,7 +221,7 @@ pcibios_bus_report_status_early(struct pci_channel *hose,
  * We can't use pci_find_device() here since we are
  * called from interrupt context.
  */
-static void __init_refok
+static void __ref
 pcibios_bus_report_status(struct pci_bus *bus, unsigned int status_mask,
 			  int warn)
 {
@@ -256,7 +256,7 @@ pcibios_bus_report_status(struct pci_bus *bus, unsigned int status_mask,
 			pcibios_bus_report_status(dev->subordinate, status_mask, warn);
 }
 
-void __init_refok pcibios_report_status(unsigned int status_mask, int warn)
+void __ref pcibios_report_status(unsigned int status_mask, int warn)
 {
 	struct pci_channel *hose;
 
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
index 2afa321157be..6c65dcd470ab 100644
--- a/arch/sh/include/asm/thread_info.h
+++ b/arch/sh/include/asm/thread_info.h
@@ -151,19 +151,10 @@ extern void init_thread_xstate(void);
  * ever touches our thread-synchronous status, so we don't
  * have to worry about atomic accesses.
  */
-#define TS_RESTORE_SIGMASK	0x0001	/* restore signal mask in do_signal() */
 #define TS_USEDFPU		0x0002	/* FPU used by this task this quantum */
 
 #ifndef __ASSEMBLY__
 
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	WARN_ON(!test_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags));
-}
-
 #define TI_FLAG_FAULT_CODE_SHIFT	24
 
 /*
@@ -182,23 +173,6 @@ static inline unsigned int get_thread_fault_code(void)
 	return ti->flags >> TI_FLAG_FAULT_CODE_SHIFT;
 }
 
-static inline void clear_restore_sigmask(void)
-{
-	current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-}
-static inline bool test_restore_sigmask(void)
-{
-	return current_thread_info()->status & TS_RESTORE_SIGMASK;
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	if (!(ti->status & TS_RESTORE_SIGMASK))
-		return false;
-	ti->status &= ~TS_RESTORE_SIGMASK;
-	return true;
-}
-
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/sh/mm/ioremap.c b/arch/sh/mm/ioremap.c
index 0c99ec2e7ed8..d09ddfe58fd8 100644
--- a/arch/sh/mm/ioremap.c
+++ b/arch/sh/mm/ioremap.c
@@ -34,7 +34,7 @@
  * have to convert them into an offset in a page-aligned mapping, but the
  * caller shouldn't need to know that small detail.
  */
-void __iomem * __init_refok
+void __iomem * __ref
 __ioremap_caller(phys_addr_t phys_addr, unsigned long size,
 		 pgprot_t pgprot, void *caller)
 {
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index 022d16008a00..2303635158f5 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -55,9 +55,6 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 }
 
 #define HAVE_ARCH_PCI_RESOURCE_TO_USER
-void pci_resource_to_user(const struct pci_dev *dev, int bar,
-			  const struct resource *rsrc,
-			  resource_size_t *start, resource_size_t *end);
 #endif /* __KERNEL__ */
 
 #endif /* __SPARC64_PCI_H */
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index bde59825d06c..3d7b925f6516 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -222,32 +222,8 @@ register struct thread_info *current_thread_info_reg asm("g6");
  *
  * Note that there are only 8 bits available.
  */
-#define TS_RESTORE_SIGMASK	0x0001	/* restore signal mask in do_signal() */
 
 #ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	WARN_ON(!test_bit(TIF_SIGPENDING, &ti->flags));
-}
-static inline void clear_restore_sigmask(void)
-{
-	current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-}
-static inline bool test_restore_sigmask(void)
-{
-	return current_thread_info()->status & TS_RESTORE_SIGMASK;
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	if (!(ti->status & TS_RESTORE_SIGMASK))
-		return false;
-	ti->status &= ~TS_RESTORE_SIGMASK;
-	return true;
-}
 
 #define thread32_stack_is_64bit(__SP) (((__SP) & 0x1) != 0)
 #define test_thread_64bit_stack(__SP) \
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index c2b202d763a1..9c1878f4fa9f 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -986,16 +986,18 @@ void pci_resource_to_user(const struct pci_dev *pdev, int bar,
 			  const struct resource *rp, resource_size_t *start,
 			  resource_size_t *end)
 {
-	struct pci_pbm_info *pbm = pdev->dev.archdata.host_controller;
-	unsigned long offset;
-
-	if (rp->flags & IORESOURCE_IO)
-		offset = pbm->io_space.start;
-	else
-		offset = pbm->mem_space.start;
+	struct pci_bus_region region;
 
-	*start = rp->start - offset;
-	*end = rp->end - offset;
+	/*
+	 * "User" addresses are shown in /sys/devices/pci.../.../resource
+	 * and /proc/bus/pci/devices and used as mmap offsets for
+	 * /proc/bus/pci/BB/DD.F files (see proc_bus_pci_mmap()).
+	 *
+	 * On sparc, these are PCI bus addresses, i.e., raw BAR values.
+	 */
+	pcibios_resource_to_bus(pdev->bus, &region, (struct resource *) rp);
+	*start = region.start;
+	*end = region.end;
 }
 
 void pcibios_set_master(struct pci_dev *dev)
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index c1467ac59ce6..b7659b8f1117 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -166,32 +166,5 @@ extern void _cpu_idle(void);
 #ifdef __tilegx__
 #define TS_COMPAT		0x0001	/* 32-bit compatibility mode */
 #endif
-#define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal */
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	WARN_ON(!test_bit(TIF_SIGPENDING, &ti->flags));
-}
-static inline void clear_restore_sigmask(void)
-{
-	current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-}
-static inline bool test_restore_sigmask(void)
-{
-	return current_thread_info()->status & TS_RESTORE_SIGMASK;
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	if (!(ti->status & TS_RESTORE_SIGMASK))
-		return false;
-	ti->status &= ~TS_RESTORE_SIGMASK;
-	return true;
-}
-#endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_TILE_THREAD_INFO_H */
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index cc0013475444..58650d098fb4 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -9,6 +9,7 @@ config UML
 	select GENERIC_CPU_DEVICES
 	select GENERIC_IO
 	select GENERIC_CLOCKEVENTS
+	select HAVE_GCC_PLUGINS
 	select TTY # Needed for line.c
 
 config MMU
diff --git a/arch/um/Makefile b/arch/um/Makefile
index e3abe6f3156d..0ca46ededfc7 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -78,8 +78,8 @@ include $(ARCH_DIR)/Makefile-os-$(OS)
 
 KBUILD_CPPFLAGS += -I$(srctree)/$(HOST_DIR)/include \
 		   -I$(srctree)/$(HOST_DIR)/include/uapi \
-		   -I$(HOST_DIR)/include/generated \
-		   -I$(HOST_DIR)/include/generated/uapi
+		   -I$(objtree)/$(HOST_DIR)/include/generated \
+		   -I$(objtree)/$(HOST_DIR)/include/generated/uapi
 
 # -Derrno=kernel_errno - This turns all kernel references to errno into
 # kernel_errno to separate them from the libc errno.  This allows -fno-common
diff --git a/arch/unicore32/kernel/pci.c b/arch/unicore32/kernel/pci.c
index d45fa5f3e9c4..62137d13c6f9 100644
--- a/arch/unicore32/kernel/pci.c
+++ b/arch/unicore32/kernel/pci.c
@@ -265,10 +265,8 @@ static int __init pci_common_init(void)
 
 	pci_fixup_irqs(pci_common_swizzle, pci_puv3_map_irq);
 
-	if (!pci_has_flag(PCI_PROBE_ONLY)) {
-		pci_bus_size_bridges(puv3_bus);
-		pci_bus_assign_resources(puv3_bus);
-	}
+	pci_bus_size_bridges(puv3_bus);
+	pci_bus_assign_resources(puv3_bus);
 	pci_bus_add_devices(puv3_bus);
 	return 0;
 }
@@ -279,9 +277,6 @@ char * __init pcibios_setup(char *str)
 	if (!strcmp(str, "debug")) {
 		debug_pci = 1;
 		return NULL;
-	} else if (!strcmp(str, "firmware")) {
-		pci_add_flags(PCI_PROBE_ONLY);
-		return NULL;
 	}
 	return str;
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2fa55851d2a9..3a9add58d794 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -111,6 +111,7 @@ config X86
 	select HAVE_FUNCTION_GRAPH_FP_TEST
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
+	select HAVE_GCC_PLUGINS
 	select HAVE_GENERIC_DMA_COHERENT	if X86_32
 	select HAVE_HW_BREAKPOINT
 	select HAVE_IDE
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index be8e688fa0d4..12ea8f8384f4 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -96,7 +96,7 @@ $(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE
 	$(call if_changed,zoffset)
 
 
-AFLAGS_header.o += -I$(obj)
+AFLAGS_header.o += -I$(objtree)/$(obj)
 $(obj)/header.o: $(obj)/zoffset.h
 
 LDFLAGS_setup.elf	:= -T
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 6ba89a1ab0e5..d5409660f5de 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -75,7 +75,7 @@ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
        -fno-omit-frame-pointer -foptimize-sibling-calls \
        -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
 
-$(vobjs): KBUILD_CFLAGS += $(CFL)
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
@@ -145,6 +145,7 @@ KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
 KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 155ea5324ae0..b26ee32f73e8 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -7,7 +7,8 @@
  */
 
 #include <linux/perf_event.h>
-#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/export.h>
 #include <linux/pci.h>
 #include <linux/ptrace.h>
 #include <linux/syscore_ops.h>
diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index 6011a573dd64..b28200dea715 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -12,7 +12,7 @@
  */
 
 #include <linux/perf_event.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/cpumask.h>
 #include <linux/slab.h>
 
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index c17f0de5fd39..fad97886d8b1 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -17,7 +17,8 @@
 #include <linux/notifier.h>
 #include <linux/hardirq.h>
 #include <linux/kprobes.h>
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/init.h>
 #include <linux/kdebug.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 3f3d0d67749b..463dc7a5a6c3 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1,3 +1,5 @@
+#include <linux/module.h>
+
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
 #include "uncore.h"
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index d6063e438158..78b9c23e2d8d 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -1,4 +1,3 @@
-#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/pci.h>
 #include <asm/apicdef.h>
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 50b3a056f96b..4bb3ec69e8ea 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -36,11 +36,11 @@ static bool test_intel(int idx)
 
 	switch (boot_cpu_data.x86_model) {
 	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_NEHALEM_G:
 	case INTEL_FAM6_NEHALEM_EP:
 	case INTEL_FAM6_NEHALEM_EX:
 
 	case INTEL_FAM6_WESTMERE:
-	case INTEL_FAM6_WESTMERE2:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 483fb547e3c0..1d2b69fc0ceb 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -49,43 +49,59 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define test_cpu_cap(c, bit)						\
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-#define REQUIRED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & REQUIRED_MASK0 )) ||	\
-	   (((bit)>>5)==1  && (1UL<<((bit)&31) & REQUIRED_MASK1 )) ||	\
-	   (((bit)>>5)==2  && (1UL<<((bit)&31) & REQUIRED_MASK2 )) ||	\
-	   (((bit)>>5)==3  && (1UL<<((bit)&31) & REQUIRED_MASK3 )) ||	\
-	   (((bit)>>5)==4  && (1UL<<((bit)&31) & REQUIRED_MASK4 )) ||	\
-	   (((bit)>>5)==5  && (1UL<<((bit)&31) & REQUIRED_MASK5 )) ||	\
-	   (((bit)>>5)==6  && (1UL<<((bit)&31) & REQUIRED_MASK6 )) ||	\
-	   (((bit)>>5)==7  && (1UL<<((bit)&31) & REQUIRED_MASK7 )) ||	\
-	   (((bit)>>5)==8  && (1UL<<((bit)&31) & REQUIRED_MASK8 )) ||	\
-	   (((bit)>>5)==9  && (1UL<<((bit)&31) & REQUIRED_MASK9 )) ||	\
-	   (((bit)>>5)==10 && (1UL<<((bit)&31) & REQUIRED_MASK10)) ||	\
-	   (((bit)>>5)==11 && (1UL<<((bit)&31) & REQUIRED_MASK11)) ||	\
-	   (((bit)>>5)==12 && (1UL<<((bit)&31) & REQUIRED_MASK12)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
-	   (((bit)>>5)==15 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
-	   (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
-
-#define DISABLED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & DISABLED_MASK0 )) ||	\
-	   (((bit)>>5)==1  && (1UL<<((bit)&31) & DISABLED_MASK1 )) ||	\
-	   (((bit)>>5)==2  && (1UL<<((bit)&31) & DISABLED_MASK2 )) ||	\
-	   (((bit)>>5)==3  && (1UL<<((bit)&31) & DISABLED_MASK3 )) ||	\
-	   (((bit)>>5)==4  && (1UL<<((bit)&31) & DISABLED_MASK4 )) ||	\
-	   (((bit)>>5)==5  && (1UL<<((bit)&31) & DISABLED_MASK5 )) ||	\
-	   (((bit)>>5)==6  && (1UL<<((bit)&31) & DISABLED_MASK6 )) ||	\
-	   (((bit)>>5)==7  && (1UL<<((bit)&31) & DISABLED_MASK7 )) ||	\
-	   (((bit)>>5)==8  && (1UL<<((bit)&31) & DISABLED_MASK8 )) ||	\
-	   (((bit)>>5)==9  && (1UL<<((bit)&31) & DISABLED_MASK9 )) ||	\
-	   (((bit)>>5)==10 && (1UL<<((bit)&31) & DISABLED_MASK10)) ||	\
-	   (((bit)>>5)==11 && (1UL<<((bit)&31) & DISABLED_MASK11)) ||	\
-	   (((bit)>>5)==12 && (1UL<<((bit)&31) & DISABLED_MASK12)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
-	   (((bit)>>5)==15 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
-	   (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
+/*
+ * There are 32 bits/features in each mask word.  The high bits
+ * (selected with (bit>>5) give us the word number and the low 5
+ * bits give us the bit/feature number inside the word.
+ * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can
+ * see if it is set in the mask word.
+ */
+#define CHECK_BIT_IN_MASK_WORD(maskname, word, bit)	\
+	(((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word ))
+
+#define REQUIRED_MASK_BIT_SET(feature_bit)		\
+	 ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  0, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  1, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  2, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  3, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  4, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  5, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  6, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  7, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  8, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  9, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
+	   REQUIRED_MASK_CHECK					  ||	\
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+
+#define DISABLED_MASK_BIT_SET(feature_bit)				\
+	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  1, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  2, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  3, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  4, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  5, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  6, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  7, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  8, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  9, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
+	   DISABLED_MASK_CHECK					  ||	\
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index d683993248c8..92a8308b96f6 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -309,5 +309,5 @@
 #endif
 #define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
 #define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
-
+#define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 911e9358ceb1..85599ad4d024 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -56,5 +56,7 @@
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK17	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 6999f7d01a0d..627719475457 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -8,7 +8,7 @@
  * "Extreme" ones, like Broadwell-E.
  *
  * Things ending in "2" are usually because we have no better
- * name for them.  There's no processor called "WESTMERE2".
+ * name for them.  There's no processor called "SILVERMONT2".
  */
 
 #define INTEL_FAM6_CORE_YONAH		0x0E
@@ -18,10 +18,10 @@
 #define INTEL_FAM6_CORE2_DUNNINGTON	0x1D
 
 #define INTEL_FAM6_NEHALEM		0x1E
+#define INTEL_FAM6_NEHALEM_G		0x1F /* Auburndale / Havendale */
 #define INTEL_FAM6_NEHALEM_EP		0x1A
 #define INTEL_FAM6_NEHALEM_EX		0x2E
 #define INTEL_FAM6_WESTMERE		0x25
-#define INTEL_FAM6_WESTMERE2		0x1F
 #define INTEL_FAM6_WESTMERE_EP		0x2C
 #define INTEL_FAM6_WESTMERE_EX		0x2F
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 69e62862b622..33ae3a4d0159 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -35,8 +35,9 @@
 #include <asm/asm.h>
 #include <asm/kvm_page_track.h>
 
-#define KVM_MAX_VCPUS 255
-#define KVM_SOFT_MAX_VCPUS 160
+#define KVM_MAX_VCPUS 288
+#define KVM_SOFT_MAX_VCPUS 240
+#define KVM_MAX_VCPU_ID 1023
 #define KVM_USER_MEM_SLOTS 509
 /* memory slots that are not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 3
@@ -599,6 +600,7 @@ struct kvm_vcpu_arch {
 	u64 mcg_cap;
 	u64 mcg_status;
 	u64 mcg_ctl;
+	u64 mcg_ext_ctl;
 	u64 *mce_banks;
 
 	/* Cache MMIO info */
@@ -682,9 +684,12 @@ struct kvm_arch_memory_slot {
 struct kvm_apic_map {
 	struct rcu_head rcu;
 	u8 mode;
-	struct kvm_lapic *phys_map[256];
-	/* first index is cluster id second is cpu id in a cluster */
-	struct kvm_lapic *logical_map[16][16];
+	u32 max_apic_id;
+	union {
+		struct kvm_lapic *xapic_flat_map[8];
+		struct kvm_lapic *xapic_cluster_map[16][4];
+	};
+	struct kvm_lapic *phys_map[];
 };
 
 /* Hyper-V emulation context */
@@ -779,6 +784,9 @@ struct kvm_arch {
 	u32 ldr_mode;
 	struct page *avic_logical_id_table_page;
 	struct page *avic_physical_id_table_page;
+
+	bool x2apic_format;
+	bool x2apic_broadcast_quirk_disabled;
 };
 
 struct kvm_vm_stat {
@@ -1006,6 +1014,11 @@ struct kvm_x86_ops {
 	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
 			      uint32_t guest_irq, bool set);
 	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
+
+	int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc);
+	void (*cancel_hv_timer)(struct kvm_vcpu *vcpu);
+
+	void (*setup_mce)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_arch_async_pf {
@@ -1026,7 +1039,7 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_init_vm(struct kvm *kvm);
 void kvm_mmu_uninit_vm(struct kvm *kvm);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask);
+		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask);
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
@@ -1077,6 +1090,10 @@ extern u32  kvm_max_guest_tsc_khz;
 extern u8   kvm_tsc_scaling_ratio_frac_bits;
 /* maximum allowed value of TSC scaling ratio */
 extern u64  kvm_max_tsc_scaling_ratio;
+/* 1ull << kvm_tsc_scaling_ratio_frac_bits */
+extern u64  kvm_default_tsc_scaling_ratio;
+
+extern u64 kvm_mce_cap_supported;
 
 enum emulation_result {
 	EMULATE_DONE,         /* no further processing */
@@ -1352,7 +1369,7 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			     struct kvm_vcpu **dest_vcpu);
 
-void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 		     struct kvm_lapic_irq *irq);
 
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index a7f9181f63f3..ed80003ce3e2 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -22,7 +22,6 @@
 #define _ASM_X86_LIVEPATCH_H
 
 #include <asm/setup.h>
-#include <linux/module.h>
 #include <linux/ftrace.h>
 
 static inline int klp_check_compiler_support(void)
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 9d3a96c4da78..da0d81fa0b54 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -133,40 +133,14 @@ static inline unsigned int x86_cpuid_family(void)
 #ifdef CONFIG_MICROCODE
 extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
-extern int __init save_microcode_in_initrd(void);
 void reload_early_microcode(void);
 extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
 #else
 static inline void __init load_ucode_bsp(void)			{ }
 static inline void load_ucode_ap(void)				{ }
-static inline int __init save_microcode_in_initrd(void)		{ return 0; }
 static inline void reload_early_microcode(void)			{ }
 static inline bool
 get_builtin_firmware(struct cpio_data *cd, const char *name)	{ return false; }
 #endif
 
-static inline unsigned long get_initrd_start(void)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
-	return initrd_start;
-#else
-	return 0;
-#endif
-}
-
-static inline unsigned long get_initrd_start_addr(void)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
-#ifdef CONFIG_X86_32
-	unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
-
-	return (unsigned long)__pa_nodebug(*initrd_start_p);
-#else
-	return get_initrd_start();
-#endif
-#else /* CONFIG_BLK_DEV_INITRD */
-	return 0;
-#endif
-}
-
 #endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index adfc847a395e..15eb75484cc0 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -62,7 +62,6 @@ extern int apply_microcode_amd(int cpu);
 extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
 
 #define PATCH_MAX_SIZE PAGE_SIZE
-extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
 
 #ifdef CONFIG_MICROCODE_AMD
 extern void __init load_ucode_amd_bsp(unsigned int family);
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 603417f8dd6c..5e69154c9f07 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -70,9 +70,4 @@ static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL;
 static inline void reload_ucode_intel(void) {}
 #endif
 
-#ifdef CONFIG_HOTPLUG_CPU
-extern int save_mc_for_early(u8 *mc);
-#else
-static inline int save_mc_for_early(u8 *mc) { return 0; }
-#endif
 #endif /* _ASM_X86_MICROCODE_INTEL_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 0deeb2d26df7..f37f2d8a2989 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -97,7 +97,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
  */
 static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 {
-	if (!current_set_polling_and_test()) {
+	if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
 		if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {
 			mb();
 			clflush((void *)&current_thread_info()->flags);
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 3a52ee0e726d..3bae4969ac65 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -13,7 +13,8 @@
  * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
  * and CONFIG_HIGHMEM64G options in the kernel configuration.
  */
-#define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
+#define __PAGE_OFFSET_BASE	_AC(CONFIG_PAGE_OFFSET, UL)
+#define __PAGE_OFFSET		__PAGE_OFFSET_BASE
 
 #define __START_KERNEL_map	__PAGE_OFFSET
 
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 4916144e3c42..fac9a5c0abe9 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -99,5 +99,7 @@
 #define REQUIRED_MASK14	0
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	0
+#define REQUIRED_MASK17	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index d0fe23ec7e98..14824fc78f7e 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -193,7 +193,6 @@ struct __attribute__ ((__packed__)) vmcb {
 	struct vmcb_save_area save;
 };
 
-#define SVM_CPUID_FEATURE_SHIFT 2
 #define SVM_CPUID_FUNC 0x8000000a
 
 #define SVM_VM_CR_SVM_DISABLE 4
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 89bff044a6f5..b45ffdda3549 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -219,32 +219,8 @@ static inline unsigned long current_stack_pointer(void)
  * have to worry about atomic accesses.
  */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
-#define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal() */
 
 #ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	WARN_ON(!test_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags));
-}
-static inline void clear_restore_sigmask(void)
-{
-	current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-}
-static inline bool test_restore_sigmask(void)
-{
-	return current_thread_info()->status & TS_RESTORE_SIGMASK;
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	if (!(ti->status & TS_RESTORE_SIGMASK))
-		return false;
-	ti->status &= ~TS_RESTORE_SIGMASK;
-	return true;
-}
 
 static inline bool in_ia32_syscall(void)
 {
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 43e87a3dd95c..cf75871d2f81 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -36,6 +36,7 @@
 #include <linux/cpumask.h>
 
 #include <asm/mpspec.h>
+#include <asm/percpu.h>
 
 /* Mappings between logical cpu number and node number */
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index cce9ee68e335..0116b2ee9e64 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -83,23 +83,19 @@ static inline void cpu_emergency_vmxoff(void)
  */
 static inline int cpu_has_svm(const char **msg)
 {
-	uint32_t eax, ebx, ecx, edx;
-
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
 		if (msg)
 			*msg = "not amd";
 		return 0;
 	}
 
-	cpuid(0x80000000, &eax, &ebx, &ecx, &edx);
-	if (eax < SVM_CPUID_FUNC) {
+	if (boot_cpu_data.extended_cpuid_level < SVM_CPUID_FUNC) {
 		if (msg)
 			*msg = "can't execute cpuid_8000000a";
 		return 0;
 	}
 
-	cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
-	if (!(ecx & (1 << SVM_CPUID_FEATURE_SHIFT))) {
+	if (!boot_cpu_has(X86_FEATURE_SVM)) {
 		if (msg)
 			*msg = "svm not available";
 		return 0;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 6738e5c82cca..90d84c3eee53 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -28,7 +28,7 @@
 #include <linux/acpi_pmtmr.h>
 #include <linux/efi.h>
 #include <linux/cpumask.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/dmi.h>
 #include <linux/irq.h>
 #include <linux/slab.h>
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 4b28159e0421..bdfad642123f 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -5,7 +5,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/cpu.h>
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 8e3842fc8bea..42d27a62a404 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -20,7 +20,6 @@
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
-#include <linux/module.h>
 #include <linux/topology.h>
 #include <linux/interrupt.h>
 #include <linux/bitmap.h>
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index e991d5c8bb3a..4fdf6230d93c 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -9,7 +9,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/errno.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/spinlock.h>
 #include <asm/amd_nb.h>
 
@@ -219,24 +219,22 @@ int amd_set_subcaches(int cpu, unsigned long mask)
 	return 0;
 }
 
-static int amd_cache_gart(void)
+static void amd_cache_gart(void)
 {
 	u16 i;
 
-       if (!amd_nb_has_feature(AMD_NB_GART))
-               return 0;
-
-       flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL);
-       if (!flush_words) {
-               amd_northbridges.flags &= ~AMD_NB_GART;
-               return -ENOMEM;
-       }
+	if (!amd_nb_has_feature(AMD_NB_GART))
+		return;
 
-       for (i = 0; i != amd_nb_num(); i++)
-               pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c,
-                                     &flush_words[i]);
+	flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL);
+	if (!flush_words) {
+		amd_northbridges.flags &= ~AMD_NB_GART;
+		pr_notice("Cannot initialize GART flush words, GART support disabled\n");
+		return;
+	}
 
-       return 0;
+	for (i = 0; i != amd_nb_num(); i++)
+		pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c, &flush_words[i]);
 }
 
 void amd_flush_garts(void)
@@ -278,17 +276,10 @@ EXPORT_SYMBOL_GPL(amd_flush_garts);
 
 static __init int init_amd_nbs(void)
 {
-	int err = 0;
+	amd_cache_northbridges();
+	amd_cache_gart();
 
-	err = amd_cache_northbridges();
-
-	if (err < 0)
-		pr_notice("Cannot enumerate AMD northbridges\n");
-
-	if (amd_cache_gart() < 0)
-		pr_notice("Cannot initialize GART flush words, GART support disabled\n");
-
-	return err;
+	return 0;
 }
 
 /* This has to go after the PCI subsystem */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index ac8d8ad8b009..7943d38c57ca 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -23,7 +23,7 @@
 #include <linux/bootmem.h>
 #include <linux/ftrace.h>
 #include <linux/ioport.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/syscore_ops.h>
 #include <linux/delay.h>
 #include <linux/timex.h>
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 048747778d37..5b2ae106bd4a 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -15,7 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/ctype.h>
 #include <linux/hardirq.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/smp.h>
 #include <asm/apic.h>
 #include <asm/ipi.h>
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 2cebf59092d8..c05688b2deff 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -11,7 +11,6 @@
 
 #include <linux/threads.h>
 #include <linux/cpumask.h>
-#include <linux/module.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/ctype.h>
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 7788ce643bf4..f29501e1a5c1 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -16,7 +16,7 @@
 #include <linux/notifier.h>
 #include <linux/kprobes.h>
 #include <linux/nmi.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/delay.h>
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f072b9572634..7491f417a8e4 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -39,7 +39,7 @@
 #include <linux/mc146818rtc.h>
 #include <linux/compiler.h>
 #include <linux/acpi.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/syscore_ops.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 2a0f225afebd..3a205d4a12d0 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -8,7 +8,6 @@
 #include <linux/mc146818rtc.h>
 #include <linux/cache.h>
 #include <linux/cpu.h>
-#include <linux/module.h>
 
 #include <asm/smp.h>
 #include <asm/mtrr.h>
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 93edfa01b408..7c43e716c158 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -8,7 +8,7 @@
  */
 #include <linux/threads.h>
 #include <linux/cpumask.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/ctype.h>
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 1793dba7a741..c303054b90b5 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -11,10 +11,9 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/string.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/ctype.h>
-#include <linux/init.h>
 #include <linux/hardirq.h>
 #include <linux/dmar.h>
 
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 64dd38fbf218..09b59adaea3f 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -12,7 +12,7 @@
 #include <linux/proc_fs.h>
 #include <linux/threads.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/sched.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d22a7b9c4f0e..809eda03c527 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2,7 +2,7 @@
 #include <linux/linkage.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/percpu.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 73d391ae452f..27e46658ebe3 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -21,7 +21,8 @@
  *
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/export.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index c1a89bc026ac..fcd484d2bb03 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -5,7 +5,7 @@
 #include <linux/smp.h>
 #include <linux/sched.h>
 #include <linux/thread_info.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/uaccess.h>
 
 #include <asm/cpufeature.h>
@@ -13,6 +13,7 @@
 #include <asm/msr.h>
 #include <asm/bugs.h>
 #include <asm/cpu.h>
+#include <asm/intel-family.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -508,6 +509,10 @@ static void init_intel(struct cpuinfo_x86 *c)
 	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
 		set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
 
+	if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_MWAIT) &&
+		((c->x86_model == INTEL_FAM6_ATOM_GOLDMONT)))
+		set_cpu_bug(c, X86_BUG_MONITOR);
+
 #ifdef CONFIG_X86_64
 	if (c->x86 == 15)
 		c->x86_cache_alignment = c->x86_clflush_size * 2;
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index fbb5e90557a5..e42117d5f4d7 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -1,7 +1,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cpufeature.h>
 #include <linux/cpu.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 
 /**
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 8581963894c7..27a0228c9cae 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -56,24 +56,24 @@ static u8 *container;
 static size_t container_size;
 
 static u32 ucode_new_rev;
-u8 amd_ucode_patch[PATCH_MAX_SIZE];
+static u8 amd_ucode_patch[PATCH_MAX_SIZE];
 static u16 this_equiv_id;
 
 static struct cpio_data ucode_cpio;
 
-/*
- * Microcode patch container file is prepended to the initrd in cpio format.
- * See Documentation/x86/early-microcode.txt
- */
-static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin";
-
 static struct cpio_data __init find_ucode_in_initrd(void)
 {
-	long offset = 0;
+#ifdef CONFIG_BLK_DEV_INITRD
 	char *path;
 	void *start;
 	size_t size;
 
+	/*
+	 * Microcode patch container file is prepended to the initrd in cpio
+	 * format. See Documentation/x86/early-microcode.txt
+	 */
+	static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin";
+
 #ifdef CONFIG_X86_32
 	struct boot_params *p;
 
@@ -89,9 +89,12 @@ static struct cpio_data __init find_ucode_in_initrd(void)
 	path    = ucode_path;
 	start   = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET);
 	size    = boot_params.hdr.ramdisk_size;
-#endif
+#endif /* !CONFIG_X86_32 */
 
-	return find_cpio_data(path, start, size, &offset);
+	return find_cpio_data(path, start, size, NULL);
+#else
+	return (struct cpio_data){ NULL, 0, "" };
+#endif
 }
 
 static size_t compute_container_size(u8 *data, u32 total_size)
@@ -289,11 +292,11 @@ void __init load_ucode_amd_bsp(unsigned int family)
 	size = &ucode_cpio.size;
 #endif
 
-	cp = find_ucode_in_initrd();
-	if (!cp.data) {
-		if (!load_builtin_amd_microcode(&cp, family))
-			return;
-	}
+	if (!load_builtin_amd_microcode(&cp, family))
+		cp = find_ucode_in_initrd();
+
+	if (!(cp.data && cp.size))
+		return;
 
 	*data = cp.data;
 	*size = cp.size;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index ac360bfbbdb6..df04b2d033f6 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -60,7 +60,6 @@ static bool dis_ucode_ldr;
 static DEFINE_MUTEX(microcode_mutex);
 
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
-EXPORT_SYMBOL_GPL(ucode_cpu_info);
 
 /*
  * Operations that are run on a target cpu:
@@ -175,24 +174,24 @@ void load_ucode_ap(void)
 	}
 }
 
-int __init save_microcode_in_initrd(void)
+static int __init save_microcode_in_initrd(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
 		if (c->x86 >= 6)
-			save_microcode_in_initrd_intel();
+			return save_microcode_in_initrd_intel();
 		break;
 	case X86_VENDOR_AMD:
 		if (c->x86 >= 0x10)
-			save_microcode_in_initrd_amd();
+			return save_microcode_in_initrd_amd();
 		break;
 	default:
 		break;
 	}
 
-	return 0;
+	return -EINVAL;
 }
 
 void reload_early_microcode(void)
@@ -691,4 +690,5 @@ int __init microcode_init(void)
 	return error;
 
 }
+fs_initcall(save_microcode_in_initrd);
 late_initcall(microcode_init);
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 65cbbcd48fe4..cdc0deab00c9 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -40,9 +40,13 @@
 #include <asm/msr.h>
 
 /*
- * Temporary microcode blobs pointers storage. We note here the pointers to
- * microcode blobs we've got from whatever storage (detached initrd, builtin).
- * Later on, we put those into final storage mc_saved_data.mc_saved.
+ * Temporary microcode blobs pointers storage. We note here during early load
+ * the pointers to microcode blobs we've got from whatever storage (detached
+ * initrd, builtin). Later on, we put those into final storage
+ * mc_saved_data.mc_saved.
+ *
+ * Important: those are offsets from the beginning of initrd or absolute
+ * addresses within the kernel image when built-in.
  */
 static unsigned long mc_tmp_ptrs[MAX_UCODE_COUNT];
 
@@ -51,8 +55,15 @@ static struct mc_saved_data {
 	struct microcode_intel **mc_saved;
 } mc_saved_data;
 
+/* Microcode blobs within the initrd. 0 if builtin. */
+static struct ucode_blobs {
+	unsigned long start;
+	bool valid;
+} blobs;
+
+/* Go through saved patches and find the one suitable for the current CPU. */
 static enum ucode_state
-load_microcode_early(struct microcode_intel **saved,
+find_microcode_patch(struct microcode_intel **saved,
 		     unsigned int num_saved, struct ucode_cpu_info *uci)
 {
 	struct microcode_intel *ucode_ptr, *new_mc = NULL;
@@ -121,13 +132,13 @@ load_microcode(struct mc_saved_data *mcs, unsigned long *mc_ptrs,
 	if (!mcs->mc_saved) {
 		copy_ptrs(mc_saved_tmp, mc_ptrs, offset, count);
 
-		return load_microcode_early(mc_saved_tmp, count, uci);
+		return find_microcode_patch(mc_saved_tmp, count, uci);
 	} else {
 #ifdef CONFIG_X86_32
 		microcode_phys(mc_saved_tmp, mcs);
-		return load_microcode_early(mc_saved_tmp, count, uci);
+		return find_microcode_patch(mc_saved_tmp, count, uci);
 #else
-		return load_microcode_early(mcs->mc_saved, count, uci);
+		return find_microcode_patch(mcs->mc_saved, count, uci);
 #endif
 	}
 }
@@ -450,8 +461,6 @@ static void show_saved_mc(void)
 #endif
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-static DEFINE_MUTEX(x86_cpu_microcode_mutex);
 /*
  * Save this mc into mc_saved_data. So it will be loaded early when a CPU is
  * hot added or resumes.
@@ -459,19 +468,18 @@ static DEFINE_MUTEX(x86_cpu_microcode_mutex);
  * Please make sure this mc should be a valid microcode patch before calling
  * this function.
  */
-int save_mc_for_early(u8 *mc)
+static void save_mc_for_early(u8 *mc)
 {
+#ifdef CONFIG_HOTPLUG_CPU
+	/* Synchronization during CPU hotplug. */
+	static DEFINE_MUTEX(x86_cpu_microcode_mutex);
+
 	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
 	unsigned int mc_saved_count_init;
 	unsigned int num_saved;
 	struct microcode_intel **mc_saved;
-	int ret = 0;
-	int i;
+	int ret, i;
 
-	/*
-	 * Hold hotplug lock so mc_saved_data is not accessed by a CPU in
-	 * hotplug.
-	 */
 	mutex_lock(&x86_cpu_microcode_mutex);
 
 	mc_saved_count_init = mc_saved_data.num_saved;
@@ -509,11 +517,8 @@ int save_mc_for_early(u8 *mc)
 
 out:
 	mutex_unlock(&x86_cpu_microcode_mutex);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(save_mc_for_early);
 #endif
+}
 
 static bool __init load_builtin_intel_microcode(struct cpio_data *cp)
 {
@@ -532,37 +537,6 @@ static bool __init load_builtin_intel_microcode(struct cpio_data *cp)
 #endif
 }
 
-static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
-static __init enum ucode_state
-scan_microcode(struct mc_saved_data *mcs, unsigned long *mc_ptrs,
-	       unsigned long start, unsigned long size,
-	       struct ucode_cpu_info *uci)
-{
-	struct cpio_data cd;
-	long offset = 0;
-#ifdef CONFIG_X86_32
-	char *p = (char *)__pa_nodebug(ucode_name);
-#else
-	char *p = ucode_name;
-#endif
-
-	cd.data = NULL;
-	cd.size = 0;
-
-	/* try built-in microcode if no initrd */
-	if (!size) {
-		if (!load_builtin_intel_microcode(&cd))
-			return UCODE_ERROR;
-	} else {
-		cd = find_cpio_data(p, (void *)start, size, &offset);
-		if (!cd.data)
-			return UCODE_ERROR;
-	}
-
-	return get_matching_model_microcode(start, cd.data, cd.size,
-					    mcs, mc_ptrs, uci);
-}
-
 /*
  * Print ucode update info.
  */
@@ -680,38 +654,117 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
  */
 int __init save_microcode_in_initrd_intel(void)
 {
-	unsigned int count = mc_saved_data.num_saved;
 	struct microcode_intel *mc_saved[MAX_UCODE_COUNT];
-	int ret = 0;
+	unsigned int count = mc_saved_data.num_saved;
+	unsigned long offset = 0;
+	int ret;
 
 	if (!count)
-		return ret;
+		return 0;
+
+	/*
+	 * We have found a valid initrd but it might've been relocated in the
+	 * meantime so get its updated address.
+	 */
+	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && blobs.valid)
+		offset = initrd_start;
 
-	copy_ptrs(mc_saved, mc_tmp_ptrs, get_initrd_start(), count);
+	copy_ptrs(mc_saved, mc_tmp_ptrs, offset, count);
 
 	ret = save_microcode(&mc_saved_data, mc_saved, count);
 	if (ret)
 		pr_err("Cannot save microcode patches from initrd.\n");
-
-	show_saved_mc();
+	else
+		show_saved_mc();
 
 	return ret;
 }
 
+static __init enum ucode_state
+__scan_microcode_initrd(struct cpio_data *cd, struct ucode_blobs *blbp)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
+	char *p = IS_ENABLED(CONFIG_X86_32) ? (char *)__pa_nodebug(ucode_name)
+						    : ucode_name;
+# ifdef CONFIG_X86_32
+	unsigned long start = 0, size;
+	struct boot_params *params;
+
+	params = (struct boot_params *)__pa_nodebug(&boot_params);
+	size   = params->hdr.ramdisk_size;
+
+	/*
+	 * Set start only if we have an initrd image. We cannot use initrd_start
+	 * because it is not set that early yet.
+	 */
+	start = (size ? params->hdr.ramdisk_image : 0);
+
+# else /* CONFIG_X86_64 */
+	unsigned long start = 0, size;
+
+	size  = (u64)boot_params.ext_ramdisk_size << 32;
+	size |= boot_params.hdr.ramdisk_size;
+
+	if (size) {
+		start  = (u64)boot_params.ext_ramdisk_image << 32;
+		start |= boot_params.hdr.ramdisk_image;
+
+		start += PAGE_OFFSET;
+	}
+# endif
+
+	*cd = find_cpio_data(p, (void *)start, size, NULL);
+	if (cd->data) {
+		blbp->start = start;
+		blbp->valid = true;
+
+		return UCODE_OK;
+	} else
+#endif /* CONFIG_BLK_DEV_INITRD */
+		return UCODE_ERROR;
+}
+
+static __init enum ucode_state
+scan_microcode(struct mc_saved_data *mcs, unsigned long *mc_ptrs,
+	       struct ucode_cpu_info *uci, struct ucode_blobs *blbp)
+{
+	struct cpio_data cd = { NULL, 0, "" };
+	enum ucode_state ret;
+
+	/* try built-in microcode first */
+	if (load_builtin_intel_microcode(&cd))
+		/*
+		 * Invalidate blobs as we might've gotten an initrd too,
+		 * supplied by the boot loader, by mistake or simply forgotten
+		 * there. That's fine, we ignore it since we've found builtin
+		 * microcode already.
+		 */
+		blbp->valid = false;
+	else {
+		ret = __scan_microcode_initrd(&cd, blbp);
+		if (ret != UCODE_OK)
+			return ret;
+	}
+
+	return get_matching_model_microcode(blbp->start, cd.data, cd.size,
+					    mcs, mc_ptrs, uci);
+}
+
 static void __init
 _load_ucode_intel_bsp(struct mc_saved_data *mcs, unsigned long *mc_ptrs,
-		      unsigned long start, unsigned long size)
+		      struct ucode_blobs *blbp)
 {
 	struct ucode_cpu_info uci;
 	enum ucode_state ret;
 
 	collect_cpu_info_early(&uci);
 
-	ret = scan_microcode(mcs, mc_ptrs, start, size, &uci);
+	ret = scan_microcode(mcs, mc_ptrs, &uci, blbp);
 	if (ret != UCODE_OK)
 		return;
 
-	ret = load_microcode(mcs, mc_ptrs, start, &uci);
+	ret = load_microcode(mcs, mc_ptrs, blbp->start, &uci);
 	if (ret != UCODE_OK)
 		return;
 
@@ -720,54 +773,60 @@ _load_ucode_intel_bsp(struct mc_saved_data *mcs, unsigned long *mc_ptrs,
 
 void __init load_ucode_intel_bsp(void)
 {
-	u64 start, size;
-#ifdef CONFIG_X86_32
-	struct boot_params *p;
-
-	p	= (struct boot_params *)__pa_nodebug(&boot_params);
-	size	= p->hdr.ramdisk_size;
+	struct ucode_blobs *blobs_p;
+	struct mc_saved_data *mcs;
+	unsigned long *ptrs;
 
-	/*
-	 * Set start only if we have an initrd image. We cannot use initrd_start
-	 * because it is not set that early yet.
-	 */
-	start	= (size ? p->hdr.ramdisk_image : 0);
-
-	_load_ucode_intel_bsp((struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
-			      (unsigned long *)__pa_nodebug(&mc_tmp_ptrs),
-			      start, size);
+#ifdef CONFIG_X86_32
+	mcs	= (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
+	ptrs	= (unsigned long *)__pa_nodebug(&mc_tmp_ptrs);
+	blobs_p	= (struct ucode_blobs *)__pa_nodebug(&blobs);
 #else
-	size	= boot_params.hdr.ramdisk_size;
-	start	= (size ? boot_params.hdr.ramdisk_image + PAGE_OFFSET : 0);
-
-	_load_ucode_intel_bsp(&mc_saved_data, mc_tmp_ptrs, start, size);
+	mcs	= &mc_saved_data;
+	ptrs	= mc_tmp_ptrs;
+	blobs_p = &blobs;
 #endif
+
+	_load_ucode_intel_bsp(mcs, ptrs, blobs_p);
 }
 
 void load_ucode_intel_ap(void)
 {
-	unsigned long *mcs_tmp_p;
-	struct mc_saved_data *mcs_p;
+	struct ucode_blobs *blobs_p;
+	unsigned long *ptrs, start = 0;
+	struct mc_saved_data *mcs;
 	struct ucode_cpu_info uci;
 	enum ucode_state ret;
-#ifdef CONFIG_X86_32
 
-	mcs_tmp_p = (unsigned long *)__pa_nodebug(mc_tmp_ptrs);
-	mcs_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
+#ifdef CONFIG_X86_32
+	mcs	= (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
+	ptrs	= (unsigned long *)__pa_nodebug(mc_tmp_ptrs);
+	blobs_p	= (struct ucode_blobs *)__pa_nodebug(&blobs);
 #else
-	mcs_tmp_p = mc_tmp_ptrs;
-	mcs_p = &mc_saved_data;
+	mcs	= &mc_saved_data;
+	ptrs	= mc_tmp_ptrs;
+	blobs_p = &blobs;
 #endif
 
 	/*
 	 * If there is no valid ucode previously saved in memory, no need to
 	 * update ucode on this AP.
 	 */
-	if (!mcs_p->num_saved)
+	if (!mcs->num_saved)
 		return;
 
+	if (blobs_p->valid) {
+		start = blobs_p->start;
+
+		/*
+		 * Pay attention to CONFIG_RANDOMIZE_MEMORY=y as it shuffles
+		 * physmem mapping too and there we have the initrd.
+		 */
+		start += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+	}
+
 	collect_cpu_info_early(&uci);
-	ret = load_microcode(mcs_p, mcs_tmp_p, get_initrd_start_addr(), &uci);
+	ret = load_microcode(mcs, ptrs, start, &uci);
 	if (ret != UCODE_OK)
 		return;
 
@@ -784,7 +843,7 @@ void reload_ucode_intel(void)
 
 	collect_cpu_info_early(&uci);
 
-	ret = load_microcode_early(mc_saved_data.mc_saved,
+	ret = find_microcode_patch(mc_saved_data.mc_saved,
 				   mc_saved_data.num_saved, &uci);
 	if (ret != UCODE_OK)
 		return;
@@ -794,6 +853,7 @@ void reload_ucode_intel(void)
 
 static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 {
+	static struct cpu_signature prev;
 	struct cpuinfo_x86 *c = &cpu_data(cpu_num);
 	unsigned int val[2];
 
@@ -808,8 +868,13 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 	}
 
 	csig->rev = c->microcode;
-	pr_info("CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n",
-		cpu_num, csig->sig, csig->pf, csig->rev);
+
+	/* No extra locking on prev, races are harmless. */
+	if (csig->sig != prev.sig || csig->pf != prev.pf || csig->rev != prev.rev) {
+		pr_info("sig=0x%x, pf=0x%x, revision=0x%x\n",
+			csig->sig, csig->pf, csig->rev);
+		prev = *csig;
+	}
 
 	return 0;
 }
@@ -838,6 +903,7 @@ static int apply_microcode_intel(int cpu)
 	struct ucode_cpu_info *uci;
 	struct cpuinfo_x86 *c;
 	unsigned int val[2];
+	static int prev_rev;
 
 	/* We should bind the task to the CPU */
 	if (WARN_ON(raw_smp_processor_id() != cpu))
@@ -872,11 +938,14 @@ static int apply_microcode_intel(int cpu)
 		return -1;
 	}
 
-	pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x\n",
-		cpu, val[1],
-		mc->hdr.date & 0xffff,
-		mc->hdr.date >> 24,
-		(mc->hdr.date >> 16) & 0xff);
+	if (val[1] != prev_rev) {
+		pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
+			val[1],
+			mc->hdr.date & 0xffff,
+			mc->hdr.date >> 24,
+			(mc->hdr.date >> 16) & 0xff);
+		prev_rev = val[1];
+	}
 
 	c = &cpu_data(cpu);
 
diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c
index 2ce1a7dc45b7..406cb6c0d9dd 100644
--- a/arch/x86/kernel/cpu/microcode/intel_lib.c
+++ b/arch/x86/kernel/cpu/microcode/intel_lib.c
@@ -141,7 +141,6 @@ int microcode_sanity_check(void *mc, int print_err)
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(microcode_sanity_check);
 
 /*
  * Returns 1 if update has been found, 0 otherwise.
@@ -183,4 +182,3 @@ int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev)
 
 	return find_matching_signature(mc, csig, cpf);
 }
-EXPORT_SYMBOL_GPL(has_newer_microcode);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 10c11b4da31d..8f44c5a50ab8 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -13,7 +13,8 @@
 #include <linux/types.h>
 #include <linux/time.h>
 #include <linux/clocksource.h>
-#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/export.h>
 #include <linux/hardirq.h>
 #include <linux/efi.h>
 #include <linux/interrupt.h>
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 31e951ce6dff..3b442b64c72d 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -17,7 +17,6 @@
  * License along with this library; if not, write to the Free
  * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/smp.h>
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 16e37a2581ac..fdc55215d44d 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -4,7 +4,7 @@
  */
 #define DEBUG
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/mm.h>
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index d76f13d6d8d6..6d9b45549109 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -2,7 +2,6 @@
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 #include <linux/proc_fs.h>
-#include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/string.h>
 #include <linux/slab.h>
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 7d393ecdeee6..28f1b54b7fad 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -38,7 +38,7 @@
 #include <linux/stop_machine.h>
 #include <linux/kvm_para.h>
 #include <linux/uaccess.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/init.h>
 #include <linux/sort.h>
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 2e8caf03f593..181eabecae25 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -12,7 +12,7 @@
  */
 
 #include <linux/percpu.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
 #include <linux/smp.h>
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 8cac429b6a1d..1ff0598d309c 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -22,7 +22,8 @@
  */
 
 #include <linux/dmi.h>
-#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/export.h>
 #include <asm/div64.h>
 #include <asm/x86_init.h>
 #include <asm/hypervisor.h>
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 9ef978d69c22..9616cf76940c 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -20,7 +20,7 @@
 #include <linux/delay.h>
 #include <linux/elf.h>
 #include <linux/elfcore.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 948d77da3881..09675712eba8 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -7,7 +7,7 @@
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
 #include <linux/kdebug.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/ptrace.h>
 #include <linux/kexec.h>
 #include <linux/sysfs.h>
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6dede08dd98b..9ee4520ce83c 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -7,7 +7,7 @@
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
 #include <linux/kdebug.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/ptrace.h>
 #include <linux/kexec.h>
 #include <linux/sysfs.h>
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 57b71373bae3..de7501edb21c 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -237,36 +237,19 @@ static void __init intel_remapping_check(int num, int slot, int func)
  * despite the efforts of the "RAM buffer" approach, which simply rounds
  * memory boundaries up to 64M to try to catch space that may decode
  * as RAM and so is not suitable for MMIO.
- *
- * And yes, so far on current devices the base addr is always under 4G.
  */
-static u32 __init intel_stolen_base(int num, int slot, int func, size_t stolen_size)
-{
-	u32 base;
-
-	/*
-	 * For the PCI IDs in this quirk, the stolen base is always
-	 * in 0x5c, aka the BDSM register (yes that's really what
-	 * it's called).
-	 */
-	base = read_pci_config(num, slot, func, 0x5c);
-	base &= ~((1<<20) - 1);
-
-	return base;
-}
 
 #define KB(x)	((x) * 1024UL)
 #define MB(x)	(KB (KB (x)))
-#define GB(x)	(MB (KB (x)))
 
 static size_t __init i830_tseg_size(void)
 {
-	u8 tmp = read_pci_config_byte(0, 0, 0, I830_ESMRAMC);
+	u8 esmramc = read_pci_config_byte(0, 0, 0, I830_ESMRAMC);
 
-	if (!(tmp & TSEG_ENABLE))
+	if (!(esmramc & TSEG_ENABLE))
 		return 0;
 
-	if (tmp & I830_TSEG_SIZE_1M)
+	if (esmramc & I830_TSEG_SIZE_1M)
 		return MB(1);
 	else
 		return KB(512);
@@ -274,27 +257,26 @@ static size_t __init i830_tseg_size(void)
 
 static size_t __init i845_tseg_size(void)
 {
-	u8 tmp = read_pci_config_byte(0, 0, 0, I845_ESMRAMC);
+	u8 esmramc = read_pci_config_byte(0, 0, 0, I845_ESMRAMC);
+	u8 tseg_size = esmramc & I845_TSEG_SIZE_MASK;
 
-	if (!(tmp & TSEG_ENABLE))
+	if (!(esmramc & TSEG_ENABLE))
 		return 0;
 
-	switch (tmp & I845_TSEG_SIZE_MASK) {
-	case I845_TSEG_SIZE_512K:
-		return KB(512);
-	case I845_TSEG_SIZE_1M:
-		return MB(1);
+	switch (tseg_size) {
+	case I845_TSEG_SIZE_512K:	return KB(512);
+	case I845_TSEG_SIZE_1M:		return MB(1);
 	default:
-		WARN_ON(1);
-		return 0;
+		WARN(1, "Unknown ESMRAMC value: %x!\n", esmramc);
 	}
+	return 0;
 }
 
 static size_t __init i85x_tseg_size(void)
 {
-	u8 tmp = read_pci_config_byte(0, 0, 0, I85X_ESMRAMC);
+	u8 esmramc = read_pci_config_byte(0, 0, 0, I85X_ESMRAMC);
 
-	if (!(tmp & TSEG_ENABLE))
+	if (!(esmramc & TSEG_ENABLE))
 		return 0;
 
 	return MB(1);
@@ -314,285 +296,287 @@ static size_t __init i85x_mem_size(void)
  * On 830/845/85x the stolen memory base isn't available in any
  * register. We need to calculate it as TOM-TSEG_SIZE-stolen_size.
  */
-static u32 __init i830_stolen_base(int num, int slot, int func, size_t stolen_size)
+static phys_addr_t __init i830_stolen_base(int num, int slot, int func,
+					   size_t stolen_size)
 {
-	return i830_mem_size() - i830_tseg_size() - stolen_size;
+	return (phys_addr_t)i830_mem_size() - i830_tseg_size() - stolen_size;
 }
 
-static u32 __init i845_stolen_base(int num, int slot, int func, size_t stolen_size)
+static phys_addr_t __init i845_stolen_base(int num, int slot, int func,
+					   size_t stolen_size)
 {
-	return i830_mem_size() - i845_tseg_size() - stolen_size;
+	return (phys_addr_t)i830_mem_size() - i845_tseg_size() - stolen_size;
 }
 
-static u32 __init i85x_stolen_base(int num, int slot, int func, size_t stolen_size)
+static phys_addr_t __init i85x_stolen_base(int num, int slot, int func,
+					   size_t stolen_size)
 {
-	return i85x_mem_size() - i85x_tseg_size() - stolen_size;
+	return (phys_addr_t)i85x_mem_size() - i85x_tseg_size() - stolen_size;
 }
 
-static u32 __init i865_stolen_base(int num, int slot, int func, size_t stolen_size)
+static phys_addr_t __init i865_stolen_base(int num, int slot, int func,
+					   size_t stolen_size)
 {
+	u16 toud;
+
 	/*
 	 * FIXME is the graphics stolen memory region
 	 * always at TOUD? Ie. is it always the last
 	 * one to be allocated by the BIOS?
 	 */
-	return read_pci_config_16(0, 0, 0, I865_TOUD) << 16;
+	toud = read_pci_config_16(0, 0, 0, I865_TOUD);
+
+	return (phys_addr_t)toud << 16;
+}
+
+static phys_addr_t __init gen3_stolen_base(int num, int slot, int func,
+					   size_t stolen_size)
+{
+	u32 bsm;
+
+	/* Almost universally we can find the Graphics Base of Stolen Memory
+	 * at register BSM (0x5c) in the igfx configuration space. On a few
+	 * (desktop) machines this is also mirrored in the bridge device at
+	 * different locations, or in the MCHBAR.
+	 */
+	bsm = read_pci_config(num, slot, func, INTEL_BSM);
+
+	return (phys_addr_t)bsm & INTEL_BSM_MASK;
 }
 
 static size_t __init i830_stolen_size(int num, int slot, int func)
 {
-	size_t stolen_size;
 	u16 gmch_ctrl;
+	u16 gms;
 
 	gmch_ctrl = read_pci_config_16(0, 0, 0, I830_GMCH_CTRL);
-
-	switch (gmch_ctrl & I830_GMCH_GMS_MASK) {
-	case I830_GMCH_GMS_STOLEN_512:
-		stolen_size = KB(512);
-		break;
-	case I830_GMCH_GMS_STOLEN_1024:
-		stolen_size = MB(1);
-		break;
-	case I830_GMCH_GMS_STOLEN_8192:
-		stolen_size = MB(8);
-		break;
-	case I830_GMCH_GMS_LOCAL:
-		/* local memory isn't part of the normal address space */
-		stolen_size = 0;
-		break;
+	gms = gmch_ctrl & I830_GMCH_GMS_MASK;
+
+	switch (gms) {
+	case I830_GMCH_GMS_STOLEN_512:	return KB(512);
+	case I830_GMCH_GMS_STOLEN_1024:	return MB(1);
+	case I830_GMCH_GMS_STOLEN_8192:	return MB(8);
+	/* local memory isn't part of the normal address space */
+	case I830_GMCH_GMS_LOCAL:	return 0;
 	default:
-		return 0;
+		WARN(1, "Unknown GMCH_CTRL value: %x!\n", gmch_ctrl);
 	}
 
-	return stolen_size;
+	return 0;
 }
 
 static size_t __init gen3_stolen_size(int num, int slot, int func)
 {
-	size_t stolen_size;
 	u16 gmch_ctrl;
+	u16 gms;
 
 	gmch_ctrl = read_pci_config_16(0, 0, 0, I830_GMCH_CTRL);
-
-	switch (gmch_ctrl & I855_GMCH_GMS_MASK) {
-	case I855_GMCH_GMS_STOLEN_1M:
-		stolen_size = MB(1);
-		break;
-	case I855_GMCH_GMS_STOLEN_4M:
-		stolen_size = MB(4);
-		break;
-	case I855_GMCH_GMS_STOLEN_8M:
-		stolen_size = MB(8);
-		break;
-	case I855_GMCH_GMS_STOLEN_16M:
-		stolen_size = MB(16);
-		break;
-	case I855_GMCH_GMS_STOLEN_32M:
-		stolen_size = MB(32);
-		break;
-	case I915_GMCH_GMS_STOLEN_48M:
-		stolen_size = MB(48);
-		break;
-	case I915_GMCH_GMS_STOLEN_64M:
-		stolen_size = MB(64);
-		break;
-	case G33_GMCH_GMS_STOLEN_128M:
-		stolen_size = MB(128);
-		break;
-	case G33_GMCH_GMS_STOLEN_256M:
-		stolen_size = MB(256);
-		break;
-	case INTEL_GMCH_GMS_STOLEN_96M:
-		stolen_size = MB(96);
-		break;
-	case INTEL_GMCH_GMS_STOLEN_160M:
-		stolen_size = MB(160);
-		break;
-	case INTEL_GMCH_GMS_STOLEN_224M:
-		stolen_size = MB(224);
-		break;
-	case INTEL_GMCH_GMS_STOLEN_352M:
-		stolen_size = MB(352);
-		break;
+	gms = gmch_ctrl & I855_GMCH_GMS_MASK;
+
+	switch (gms) {
+	case I855_GMCH_GMS_STOLEN_1M:	return MB(1);
+	case I855_GMCH_GMS_STOLEN_4M:	return MB(4);
+	case I855_GMCH_GMS_STOLEN_8M:	return MB(8);
+	case I855_GMCH_GMS_STOLEN_16M:	return MB(16);
+	case I855_GMCH_GMS_STOLEN_32M:	return MB(32);
+	case I915_GMCH_GMS_STOLEN_48M:	return MB(48);
+	case I915_GMCH_GMS_STOLEN_64M:	return MB(64);
+	case G33_GMCH_GMS_STOLEN_128M:	return MB(128);
+	case G33_GMCH_GMS_STOLEN_256M:	return MB(256);
+	case INTEL_GMCH_GMS_STOLEN_96M:	return MB(96);
+	case INTEL_GMCH_GMS_STOLEN_160M:return MB(160);
+	case INTEL_GMCH_GMS_STOLEN_224M:return MB(224);
+	case INTEL_GMCH_GMS_STOLEN_352M:return MB(352);
 	default:
-		stolen_size = 0;
-		break;
+		WARN(1, "Unknown GMCH_CTRL value: %x!\n", gmch_ctrl);
 	}
 
-	return stolen_size;
+	return 0;
 }
 
 static size_t __init gen6_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
+	u16 gms;
 
 	gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
-	gmch_ctrl >>= SNB_GMCH_GMS_SHIFT;
-	gmch_ctrl &= SNB_GMCH_GMS_MASK;
+	gms = (gmch_ctrl >> SNB_GMCH_GMS_SHIFT) & SNB_GMCH_GMS_MASK;
 
-	return gmch_ctrl << 25; /* 32 MB units */
+	return (size_t)gms * MB(32);
 }
 
 static size_t __init gen8_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
+	u16 gms;
 
 	gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
-	gmch_ctrl >>= BDW_GMCH_GMS_SHIFT;
-	gmch_ctrl &= BDW_GMCH_GMS_MASK;
-	return gmch_ctrl << 25; /* 32 MB units */
+	gms = (gmch_ctrl >> BDW_GMCH_GMS_SHIFT) & BDW_GMCH_GMS_MASK;
+
+	return (size_t)gms * MB(32);
 }
 
 static size_t __init chv_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
+	u16 gms;
 
 	gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
-	gmch_ctrl >>= SNB_GMCH_GMS_SHIFT;
-	gmch_ctrl &= SNB_GMCH_GMS_MASK;
+	gms = (gmch_ctrl >> SNB_GMCH_GMS_SHIFT) & SNB_GMCH_GMS_MASK;
 
 	/*
 	 * 0x0  to 0x10: 32MB increments starting at 0MB
 	 * 0x11 to 0x16: 4MB increments starting at 8MB
 	 * 0x17 to 0x1d: 4MB increments start at 36MB
 	 */
-	if (gmch_ctrl < 0x11)
-		return gmch_ctrl << 25;
-	else if (gmch_ctrl < 0x17)
-		return (gmch_ctrl - 0x11 + 2) << 22;
+	if (gms < 0x11)
+		return (size_t)gms * MB(32);
+	else if (gms < 0x17)
+		return (size_t)(gms - 0x11 + 2) * MB(4);
 	else
-		return (gmch_ctrl - 0x17 + 9) << 22;
+		return (size_t)(gms - 0x17 + 9) * MB(4);
 }
 
-struct intel_stolen_funcs {
-	size_t (*size)(int num, int slot, int func);
-	u32 (*base)(int num, int slot, int func, size_t size);
-};
-
 static size_t __init gen9_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
+	u16 gms;
 
 	gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
-	gmch_ctrl >>= BDW_GMCH_GMS_SHIFT;
-	gmch_ctrl &= BDW_GMCH_GMS_MASK;
+	gms = (gmch_ctrl >> BDW_GMCH_GMS_SHIFT) & BDW_GMCH_GMS_MASK;
 
-	if (gmch_ctrl < 0xf0)
-		return gmch_ctrl << 25; /* 32 MB units */
+	/* 0x0  to 0xef: 32MB increments starting at 0MB */
+	/* 0xf0 to 0xfe: 4MB increments starting at 4MB */
+	if (gms < 0xf0)
+		return (size_t)gms * MB(32);
 	else
-		/* 4MB increments starting at 0xf0 for 4MB */
-		return (gmch_ctrl - 0xf0 + 1) << 22;
+		return (size_t)(gms - 0xf0 + 1) * MB(4);
 }
 
-typedef size_t (*stolen_size_fn)(int num, int slot, int func);
+struct intel_early_ops {
+	size_t (*stolen_size)(int num, int slot, int func);
+	phys_addr_t (*stolen_base)(int num, int slot, int func, size_t size);
+};
 
-static const struct intel_stolen_funcs i830_stolen_funcs __initconst = {
-	.base = i830_stolen_base,
-	.size = i830_stolen_size,
+static const struct intel_early_ops i830_early_ops __initconst = {
+	.stolen_base = i830_stolen_base,
+	.stolen_size = i830_stolen_size,
 };
 
-static const struct intel_stolen_funcs i845_stolen_funcs __initconst = {
-	.base = i845_stolen_base,
-	.size = i830_stolen_size,
+static const struct intel_early_ops i845_early_ops __initconst = {
+	.stolen_base = i845_stolen_base,
+	.stolen_size = i830_stolen_size,
 };
 
-static const struct intel_stolen_funcs i85x_stolen_funcs __initconst = {
-	.base = i85x_stolen_base,
-	.size = gen3_stolen_size,
+static const struct intel_early_ops i85x_early_ops __initconst = {
+	.stolen_base = i85x_stolen_base,
+	.stolen_size = gen3_stolen_size,
 };
 
-static const struct intel_stolen_funcs i865_stolen_funcs __initconst = {
-	.base = i865_stolen_base,
-	.size = gen3_stolen_size,
+static const struct intel_early_ops i865_early_ops __initconst = {
+	.stolen_base = i865_stolen_base,
+	.stolen_size = gen3_stolen_size,
 };
 
-static const struct intel_stolen_funcs gen3_stolen_funcs __initconst = {
-	.base = intel_stolen_base,
-	.size = gen3_stolen_size,
+static const struct intel_early_ops gen3_early_ops __initconst = {
+	.stolen_base = gen3_stolen_base,
+	.stolen_size = gen3_stolen_size,
 };
 
-static const struct intel_stolen_funcs gen6_stolen_funcs __initconst = {
-	.base = intel_stolen_base,
-	.size = gen6_stolen_size,
+static const struct intel_early_ops gen6_early_ops __initconst = {
+	.stolen_base = gen3_stolen_base,
+	.stolen_size = gen6_stolen_size,
 };
 
-static const struct intel_stolen_funcs gen8_stolen_funcs __initconst = {
-	.base = intel_stolen_base,
-	.size = gen8_stolen_size,
+static const struct intel_early_ops gen8_early_ops __initconst = {
+	.stolen_base = gen3_stolen_base,
+	.stolen_size = gen8_stolen_size,
 };
 
-static const struct intel_stolen_funcs gen9_stolen_funcs __initconst = {
-	.base = intel_stolen_base,
-	.size = gen9_stolen_size,
+static const struct intel_early_ops gen9_early_ops __initconst = {
+	.stolen_base = gen3_stolen_base,
+	.stolen_size = gen9_stolen_size,
 };
 
-static const struct intel_stolen_funcs chv_stolen_funcs __initconst = {
-	.base = intel_stolen_base,
-	.size = chv_stolen_size,
+static const struct intel_early_ops chv_early_ops __initconst = {
+	.stolen_base = gen3_stolen_base,
+	.stolen_size = chv_stolen_size,
 };
 
-static const struct pci_device_id intel_stolen_ids[] __initconst = {
-	INTEL_I830_IDS(&i830_stolen_funcs),
-	INTEL_I845G_IDS(&i845_stolen_funcs),
-	INTEL_I85X_IDS(&i85x_stolen_funcs),
-	INTEL_I865G_IDS(&i865_stolen_funcs),
-	INTEL_I915G_IDS(&gen3_stolen_funcs),
-	INTEL_I915GM_IDS(&gen3_stolen_funcs),
-	INTEL_I945G_IDS(&gen3_stolen_funcs),
-	INTEL_I945GM_IDS(&gen3_stolen_funcs),
-	INTEL_VLV_M_IDS(&gen6_stolen_funcs),
-	INTEL_VLV_D_IDS(&gen6_stolen_funcs),
-	INTEL_PINEVIEW_IDS(&gen3_stolen_funcs),
-	INTEL_I965G_IDS(&gen3_stolen_funcs),
-	INTEL_G33_IDS(&gen3_stolen_funcs),
-	INTEL_I965GM_IDS(&gen3_stolen_funcs),
-	INTEL_GM45_IDS(&gen3_stolen_funcs),
-	INTEL_G45_IDS(&gen3_stolen_funcs),
-	INTEL_IRONLAKE_D_IDS(&gen3_stolen_funcs),
-	INTEL_IRONLAKE_M_IDS(&gen3_stolen_funcs),
-	INTEL_SNB_D_IDS(&gen6_stolen_funcs),
-	INTEL_SNB_M_IDS(&gen6_stolen_funcs),
-	INTEL_IVB_M_IDS(&gen6_stolen_funcs),
-	INTEL_IVB_D_IDS(&gen6_stolen_funcs),
-	INTEL_HSW_D_IDS(&gen6_stolen_funcs),
-	INTEL_HSW_M_IDS(&gen6_stolen_funcs),
-	INTEL_BDW_M_IDS(&gen8_stolen_funcs),
-	INTEL_BDW_D_IDS(&gen8_stolen_funcs),
-	INTEL_CHV_IDS(&chv_stolen_funcs),
-	INTEL_SKL_IDS(&gen9_stolen_funcs),
-	INTEL_BXT_IDS(&gen9_stolen_funcs),
-	INTEL_KBL_IDS(&gen9_stolen_funcs),
+static const struct pci_device_id intel_early_ids[] __initconst = {
+	INTEL_I830_IDS(&i830_early_ops),
+	INTEL_I845G_IDS(&i845_early_ops),
+	INTEL_I85X_IDS(&i85x_early_ops),
+	INTEL_I865G_IDS(&i865_early_ops),
+	INTEL_I915G_IDS(&gen3_early_ops),
+	INTEL_I915GM_IDS(&gen3_early_ops),
+	INTEL_I945G_IDS(&gen3_early_ops),
+	INTEL_I945GM_IDS(&gen3_early_ops),
+	INTEL_VLV_M_IDS(&gen6_early_ops),
+	INTEL_VLV_D_IDS(&gen6_early_ops),
+	INTEL_PINEVIEW_IDS(&gen3_early_ops),
+	INTEL_I965G_IDS(&gen3_early_ops),
+	INTEL_G33_IDS(&gen3_early_ops),
+	INTEL_I965GM_IDS(&gen3_early_ops),
+	INTEL_GM45_IDS(&gen3_early_ops),
+	INTEL_G45_IDS(&gen3_early_ops),
+	INTEL_IRONLAKE_D_IDS(&gen3_early_ops),
+	INTEL_IRONLAKE_M_IDS(&gen3_early_ops),
+	INTEL_SNB_D_IDS(&gen6_early_ops),
+	INTEL_SNB_M_IDS(&gen6_early_ops),
+	INTEL_IVB_M_IDS(&gen6_early_ops),
+	INTEL_IVB_D_IDS(&gen6_early_ops),
+	INTEL_HSW_D_IDS(&gen6_early_ops),
+	INTEL_HSW_M_IDS(&gen6_early_ops),
+	INTEL_BDW_M_IDS(&gen8_early_ops),
+	INTEL_BDW_D_IDS(&gen8_early_ops),
+	INTEL_CHV_IDS(&chv_early_ops),
+	INTEL_SKL_IDS(&gen9_early_ops),
+	INTEL_BXT_IDS(&gen9_early_ops),
+	INTEL_KBL_IDS(&gen9_early_ops),
 };
 
-static void __init intel_graphics_stolen(int num, int slot, int func)
+static void __init
+intel_graphics_stolen(int num, int slot, int func,
+		      const struct intel_early_ops *early_ops)
 {
+	phys_addr_t base, end;
 	size_t size;
+
+	size = early_ops->stolen_size(num, slot, func);
+	base = early_ops->stolen_base(num, slot, func, size);
+
+	if (!size || !base)
+		return;
+
+	end = base + size - 1;
+	printk(KERN_INFO "Reserving Intel graphics memory at %pa-%pa\n",
+	       &base, &end);
+
+	/* Mark this space as reserved */
+	e820_add_region(base, size, E820_RESERVED);
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+}
+
+static void __init intel_graphics_quirks(int num, int slot, int func)
+{
+	const struct intel_early_ops *early_ops;
+	u16 device;
 	int i;
-	u32 start;
-	u16 device, subvendor, subdevice;
 
 	device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID);
-	subvendor = read_pci_config_16(num, slot, func,
-				       PCI_SUBSYSTEM_VENDOR_ID);
-	subdevice = read_pci_config_16(num, slot, func, PCI_SUBSYSTEM_ID);
-
-	for (i = 0; i < ARRAY_SIZE(intel_stolen_ids); i++) {
-		if (intel_stolen_ids[i].device == device) {
-			const struct intel_stolen_funcs *stolen_funcs =
-				(const struct intel_stolen_funcs *)intel_stolen_ids[i].driver_data;
-			size = stolen_funcs->size(num, slot, func);
-			start = stolen_funcs->base(num, slot, func, size);
-			if (size && start) {
-				printk(KERN_INFO "Reserving Intel graphics stolen memory at 0x%x-0x%x\n",
-				       start, start + (u32)size - 1);
-				/* Mark this space as reserved */
-				e820_add_region(start, size, E820_RESERVED);
-				sanitize_e820_map(e820.map,
-						  ARRAY_SIZE(e820.map),
-						  &e820.nr_map);
-			}
-			return;
-		}
+
+	for (i = 0; i < ARRAY_SIZE(intel_early_ids); i++) {
+		kernel_ulong_t driver_data = intel_early_ids[i].driver_data;
+
+		if (intel_early_ids[i].device != device)
+			continue;
+
+		early_ops = (typeof(early_ops))driver_data;
+
+		intel_graphics_stolen(num, slot, func, early_ops);
+
+		return;
 	}
 }
 
@@ -690,7 +674,7 @@ static struct chipset early_qrk[] __initdata = {
 	{ PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
 	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
 	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
-	  QFLAG_APPLY_ONCE, intel_graphics_stolen },
+	  QFLAG_APPLY_ONCE, intel_graphics_quirks },
 	/*
 	 * HPET on the current version of the Baytrail platform has accuracy
 	 * problems: it will halt in deep idle state - so we disable it.
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 2bcfb5f2bc44..8771766d46b6 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -36,13 +36,14 @@
 #include <linux/percpu.h>
 #include <linux/kdebug.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 
 #include <asm/hw_breakpoint.h>
 #include <asm/processor.h>
 #include <asm/debugreg.h>
+#include <asm/user.h>
 
 /* Per cpu debug control register value */
 DEFINE_PER_CPU(unsigned long, cpu_dr7);
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index d40ee8a38fed..1f9b878ef5ef 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -1,4 +1,5 @@
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/spinlock_types.h>
 
 #include <asm/checksum.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index efb82f07b29c..6ebe00cb4a3b 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -3,7 +3,7 @@
  *
  */
 #include <linux/clockchips.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/timex.h>
 #include <linux/i8253.h>
 
diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c
index a979b5bd2fc0..50c89e8a95f2 100644
--- a/arch/x86/kernel/io_delay.c
+++ b/arch/x86/kernel/io_delay.c
@@ -6,7 +6,7 @@
  * outb_p/inb_p API uses.
  */
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/dmi.h>
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index c627bf8d98ad..1f38d9a4d9de 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -8,7 +8,6 @@
  * io_apic.c.)
  */
 
-#include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 206d0b90a3ab..4a7903714065 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -11,7 +11,6 @@
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
 #include <linux/seq_file.h>
-#include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index dc1404bf8e4b..bdb83e431d89 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -8,7 +8,7 @@
  */
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/stat.h>
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 1ef5e48b3a36..1726c4c12336 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -21,7 +21,7 @@
  */
 
 #include <linux/context_tracking.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/kvm_para.h>
 #include <linux/cpu.h>
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 97340f2c437c..068c4a929de6 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -16,7 +16,6 @@
 #include <linux/mc146818rtc.h>
 #include <linux/bitops.h>
 #include <linux/acpi.h>
-#include <linux/module.h>
 #include <linux/smp.h>
 #include <linux/pci.h>
 
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 33ee3e0efd65..1939a0269377 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -3,7 +3,7 @@
  * compiled in a FTRACE-compatible way.
  */
 #include <linux/spinlock.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/jump_label.h>
 
 #include <asm/paravirt.h>
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 7b3b3f24c3ea..ad5bc9578a73 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -19,7 +19,8 @@
 */
 
 #include <linux/errno.h>
-#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/export.h>
 #include <linux/efi.h>
 #include <linux/bcd.h>
 #include <linux/highmem.h>
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 7c577a178859..5069ef560d83 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -2,7 +2,7 @@
 
 #include <linux/pci.h>
 #include <linux/cache.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/swiotlb.h>
 #include <linux/bootmem.h>
 #include <linux/dma-mapping.h>
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 92f70147a9a6..0c5315d322c8 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -3,7 +3,7 @@
  * Copyright (c) 2015, Intel Corporation.
  */
 #include <linux/platform_device.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/ioport.h>
 
 static int found(u64 start, u64 end, void *data)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 96becbbb52e0..62c0b0ea2ce4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -7,7 +7,8 @@
 #include <linux/prctl.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
-#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/export.h>
 #include <linux/pm.h>
 #include <linux/tick.h>
 #include <linux/random.h>
@@ -404,7 +405,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 	if (c->x86_vendor != X86_VENDOR_INTEL)
 		return 0;
 
-	if (!cpu_has(c, X86_FEATURE_MWAIT))
+	if (!cpu_has(c, X86_FEATURE_MWAIT) || static_cpu_has_bug(X86_BUG_MONITOR))
 		return 0;
 
 	return 1;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 9f950917528b..d86be29c38c7 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -25,7 +25,7 @@
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/mc146818rtc.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kallsyms.h>
 #include <linux/ptrace.h>
 #include <linux/personality.h>
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6e789ca1f841..63236d8f84bf 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -26,7 +26,7 @@
 #include <linux/user.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/ptrace.h>
 #include <linux/notifier.h>
 #include <linux/kprobes.h>
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 15ed70f8278b..63bf27d972b7 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -1,6 +1,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/reboot.h>
 #include <linux/init.h>
 #include <linux/pm.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 6cb2b02fcc87..991b77986d57 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -36,7 +36,7 @@
 #include <linux/console.h>
 #include <linux/root_dev.h>
 #include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/efi.h>
 #include <linux/init.h>
 #include <linux/edd.h>
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c93609c97406..2a6e84a30a54 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -43,7 +43,7 @@
 
 #include <linux/init.h>
 #include <linux/smp.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/percpu.h>
 #include <linux/bootmem.h>
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 9ee98eefc44d..4738f5e0f2ab 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -5,7 +5,7 @@
  */
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/uaccess.h>
 #include <asm/stacktrace.h>
 
diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c
index cb4a01b41e27..222e84e2432e 100644
--- a/arch/x86/kernel/test_rodata.c
+++ b/arch/x86/kernel/test_rodata.c
@@ -9,7 +9,6 @@
  * as published by the Free Software Foundation; version 2
  * of the License.
  */
-#include <linux/module.h>
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
 #include <asm/asm.h>
@@ -74,7 +73,3 @@ int rodata_test(void)
 
 	return 0;
 }
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Testcase for marking rodata as read-only");
-MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 00f03d82e69a..b70ca12dd389 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -21,7 +21,7 @@
 #include <linux/kdebug.h>
 #include <linux/kgdb.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/ptrace.h>
 #include <linux/uprobes.h>
 #include <linux/string.h>
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index a804b5ab32d0..1ef87e887051 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -3,7 +3,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/timer.h>
 #include <linux/acpi_pmtmr.h>
 #include <linux/cpufreq.h>
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index f1aebfb49c36..95e49f6e4fc3 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -1,7 +1,8 @@
 /* Exports for assembly files.
    All C exports should go in the respective C files. */
 
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/spinlock_types.h>
 #include <linux/smp.h>
 
 #include <net/checksum.h>
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 58b459296e13..76c5e52436c4 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -5,7 +5,7 @@
  */
 #include <linux/init.h>
 #include <linux/ioport.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/pci.h>
 
 #include <asm/bios_ebda.h>
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 639a6e34500c..ab8e32f7b9a8 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -32,7 +32,6 @@ config KVM
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_EVENTFD
-	select KVM_APIC_ARCHITECTURE
 	select KVM_ASYNC_PF
 	select USER_RETURN_NOTIFIER
 	select KVM_MMIO
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 643565364497..3235e0fe7792 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -13,7 +13,7 @@
  */
 
 #include <linux/kvm_host.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 #include <asm/fpu/internal.h> /* For use_eager_fpu.  Ugh! */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a2f24af3c999..4e95d3eb2955 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -22,7 +22,6 @@
 
 #include <linux/kvm_host.h>
 #include "kvm_cache_regs.h"
-#include <linux/module.h>
 #include <asm/kvm_emulate.h>
 #include <linux/stringify.h>
 #include <asm/debugreg.h>
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index a4bf5b45d65a..5fb6c620180e 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -645,7 +645,6 @@ static const struct kvm_io_device_ops speaker_dev_ops = {
 	.write    = speaker_ioport_write,
 };
 
-/* Caller must hold slots_lock */
 struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 {
 	struct kvm_pit *pit;
@@ -690,6 +689,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 
 	kvm_pit_set_reinject(pit, true);
 
+	mutex_lock(&kvm->slots_lock);
 	kvm_iodevice_init(&pit->dev, &pit_dev_ops);
 	ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, KVM_PIT_BASE_ADDRESS,
 				      KVM_PIT_MEM_LENGTH, &pit->dev);
@@ -704,12 +704,14 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 		if (ret < 0)
 			goto fail_register_speaker;
 	}
+	mutex_unlock(&kvm->slots_lock);
 
 	return pit;
 
 fail_register_speaker:
 	kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev);
 fail_register_pit:
+	mutex_unlock(&kvm->slots_lock);
 	kvm_pit_set_reinject(pit, false);
 	kthread_stop(pit->worker_task);
 fail_kthread:
diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c
index 3069281904d3..b181426f67b4 100644
--- a/arch/x86/kvm/iommu.c
+++ b/arch/x86/kvm/iommu.c
@@ -25,12 +25,10 @@
 
 #include <linux/list.h>
 #include <linux/kvm_host.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/pci.h>
 #include <linux/stat.h>
-#include <linux/dmar.h>
 #include <linux/iommu.h>
-#include <linux/intel-iommu.h>
 #include "assigned-dev.h"
 
 static bool allow_unsafe_assigned_interrupts;
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 95fcc7b13866..60d91c9d160c 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -20,7 +20,7 @@
  *
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kvm_host.h>
 
 #include "irq.h"
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index dfb4c6476877..25810b144b58 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -110,13 +110,17 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	return r;
 }
 
-void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 		     struct kvm_lapic_irq *irq)
 {
-	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+	trace_kvm_msi_set_irq(e->msi.address_lo | (kvm->arch.x2apic_format ?
+	                                     (u64)e->msi.address_hi << 32 : 0),
+	                      e->msi.data);
 
 	irq->dest_id = (e->msi.address_lo &
 			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+	if (kvm->arch.x2apic_format)
+		irq->dest_id |= MSI_ADDR_EXT_DEST_ID(e->msi.address_hi);
 	irq->vector = (e->msi.data &
 			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
 	irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
@@ -129,15 +133,24 @@ void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
 }
 EXPORT_SYMBOL_GPL(kvm_set_msi_irq);
 
+static inline bool kvm_msi_route_invalid(struct kvm *kvm,
+		struct kvm_kernel_irq_routing_entry *e)
+{
+	return kvm->arch.x2apic_format && (e->msi.address_hi & 0xff);
+}
+
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 		struct kvm *kvm, int irq_source_id, int level, bool line_status)
 {
 	struct kvm_lapic_irq irq;
 
+	if (kvm_msi_route_invalid(kvm, e))
+		return -EINVAL;
+
 	if (!level)
 		return -1;
 
-	kvm_set_msi_irq(e, &irq);
+	kvm_set_msi_irq(kvm, e, &irq);
 
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
 }
@@ -153,7 +166,10 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 	if (unlikely(e->type != KVM_IRQ_ROUTING_MSI))
 		return -EWOULDBLOCK;
 
-	kvm_set_msi_irq(e, &irq);
+	if (kvm_msi_route_invalid(kvm, e))
+		return -EINVAL;
+
+	kvm_set_msi_irq(kvm, e, &irq);
 
 	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
 		return r;
@@ -248,7 +264,8 @@ static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
 }
 
-int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm *kvm,
+			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
 {
 	int r = -EINVAL;
@@ -285,6 +302,9 @@ int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 		e->msi.address_lo = ue->u.msi.address_lo;
 		e->msi.address_hi = ue->u.msi.address_hi;
 		e->msi.data = ue->u.msi.data;
+
+		if (kvm_msi_route_invalid(kvm, e))
+			goto out;
 		break;
 	case KVM_IRQ_ROUTING_HV_SINT:
 		e->set = kvm_hv_set_sint;
@@ -388,21 +408,16 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 			       kvm->arch.nr_reserved_ioapic_pins);
 	for (i = 0; i < nr_ioapic_pins; ++i) {
 		hlist_for_each_entry(entry, &table->map[i], link) {
-			u32 dest_id, dest_mode;
-			bool level;
+			struct kvm_lapic_irq irq;
 
 			if (entry->type != KVM_IRQ_ROUTING_MSI)
 				continue;
-			dest_id = (entry->msi.address_lo >> 12) & 0xff;
-			dest_mode = (entry->msi.address_lo >> 2) & 0x1;
-			level = entry->msi.data & MSI_DATA_TRIGGER_LEVEL;
-			if (level && kvm_apic_match_dest(vcpu, NULL, 0,
-						dest_id, dest_mode)) {
-				u32 vector = entry->msi.data & 0xff;
-
-				__set_bit(vector,
-					  ioapic_handled_vectors);
-			}
+
+			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
+
+			if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0,
+						irq.dest_id, irq.dest_mode))
+				__set_bit(irq.vector, ioapic_handled_vectors);
 		}
 	}
 	srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index a397200281c1..730cf174090a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -25,7 +25,7 @@
 #include <linux/smp.h>
 #include <linux/hrtimer.h>
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/math64.h>
 #include <linux/slab.h>
 #include <asm/processor.h>
@@ -115,26 +115,43 @@ static inline int apic_enabled(struct kvm_lapic *apic)
 	(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
 	 APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
 
-/* The logical map is definitely wrong if we have multiple
- * modes at the same time.  (Physical map is always right.)
- */
-static inline bool kvm_apic_logical_map_valid(struct kvm_apic_map *map)
-{
-	return !(map->mode & (map->mode - 1));
+static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
+		u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) {
+	switch (map->mode) {
+	case KVM_APIC_MODE_X2APIC: {
+		u32 offset = (dest_id >> 16) * 16;
+		u32 max_apic_id = map->max_apic_id;
+
+		if (offset <= max_apic_id) {
+			u8 cluster_size = min(max_apic_id - offset + 1, 16U);
+
+			*cluster = &map->phys_map[offset];
+			*mask = dest_id & (0xffff >> (16 - cluster_size));
+		} else {
+			*mask = 0;
+		}
+
+		return true;
+		}
+	case KVM_APIC_MODE_XAPIC_FLAT:
+		*cluster = map->xapic_flat_map;
+		*mask = dest_id & 0xff;
+		return true;
+	case KVM_APIC_MODE_XAPIC_CLUSTER:
+		*cluster = map->xapic_cluster_map[dest_id >> 4];
+		*mask = dest_id & 0xf;
+		return true;
+	default:
+		/* Not optimized. */
+		return false;
+	}
 }
 
-static inline void
-apic_logical_id(struct kvm_apic_map *map, u32 dest_id, u16 *cid, u16 *lid)
+static void kvm_apic_map_free(struct rcu_head *rcu)
 {
-	unsigned lid_bits;
-
-	BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_CLUSTER !=  4);
-	BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_FLAT    !=  8);
-	BUILD_BUG_ON(KVM_APIC_MODE_X2APIC        != 16);
-	lid_bits = map->mode;
+	struct kvm_apic_map *map = container_of(rcu, struct kvm_apic_map, rcu);
 
-	*cid = dest_id >> lid_bits;
-	*lid = dest_id & ((1 << lid_bits) - 1);
+	kvfree(map);
 }
 
 static void recalculate_apic_map(struct kvm *kvm)
@@ -142,17 +159,26 @@ static void recalculate_apic_map(struct kvm *kvm)
 	struct kvm_apic_map *new, *old = NULL;
 	struct kvm_vcpu *vcpu;
 	int i;
-
-	new = kzalloc(sizeof(struct kvm_apic_map), GFP_KERNEL);
+	u32 max_id = 255;
 
 	mutex_lock(&kvm->arch.apic_map_lock);
 
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		if (kvm_apic_present(vcpu))
+			max_id = max(max_id, kvm_apic_id(vcpu->arch.apic));
+
+	new = kvm_kvzalloc(sizeof(struct kvm_apic_map) +
+	                   sizeof(struct kvm_lapic *) * ((u64)max_id + 1));
+
 	if (!new)
 		goto out;
 
+	new->max_apic_id = max_id;
+
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		struct kvm_lapic *apic = vcpu->arch.apic;
-		u16 cid, lid;
+		struct kvm_lapic **cluster;
+		u16 mask;
 		u32 ldr, aid;
 
 		if (!kvm_apic_present(vcpu))
@@ -161,7 +187,7 @@ static void recalculate_apic_map(struct kvm *kvm)
 		aid = kvm_apic_id(apic);
 		ldr = kvm_lapic_get_reg(apic, APIC_LDR);
 
-		if (aid < ARRAY_SIZE(new->phys_map))
+		if (aid <= new->max_apic_id)
 			new->phys_map[aid] = apic;
 
 		if (apic_x2apic_mode(apic)) {
@@ -174,13 +200,11 @@ static void recalculate_apic_map(struct kvm *kvm)
 				new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER;
 		}
 
-		if (!kvm_apic_logical_map_valid(new))
+		if (!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask))
 			continue;
 
-		apic_logical_id(new, ldr, &cid, &lid);
-
-		if (lid && cid < ARRAY_SIZE(new->logical_map))
-			new->logical_map[cid][ffs(lid) - 1] = apic;
+		if (mask)
+			cluster[ffs(mask) - 1] = apic;
 	}
 out:
 	old = rcu_dereference_protected(kvm->arch.apic_map,
@@ -189,7 +213,7 @@ out:
 	mutex_unlock(&kvm->arch.apic_map_lock);
 
 	if (old)
-		kfree_rcu(old, rcu);
+		call_rcu(&old->rcu, kvm_apic_map_free);
 
 	kvm_make_scan_ioapic_request(kvm);
 }
@@ -210,7 +234,7 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
 	}
 }
 
-static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
+static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id)
 {
 	kvm_lapic_set_reg(apic, APIC_ID, id << 24);
 	recalculate_apic_map(apic->vcpu->kvm);
@@ -222,11 +246,11 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 	recalculate_apic_map(apic->vcpu->kvm);
 }
 
-static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id)
+static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
 {
 	u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
 
-	kvm_lapic_set_reg(apic, APIC_ID, id << 24);
+	kvm_lapic_set_reg(apic, APIC_ID, id);
 	kvm_lapic_set_reg(apic, APIC_LDR, ldr);
 	recalculate_apic_map(apic->vcpu->kvm);
 }
@@ -599,17 +623,30 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
 	}
 }
 
-/* KVM APIC implementation has two quirks
- *  - dest always begins at 0 while xAPIC MDA has offset 24,
- *  - IOxAPIC messages have to be delivered (directly) to x2APIC.
+/* The KVM local APIC implementation has two quirks:
+ *
+ *  - the xAPIC MDA stores the destination at bits 24-31, while this
+ *    is not true of struct kvm_lapic_irq's dest_id field.  This is
+ *    just a quirk in the API and is not problematic.
+ *
+ *  - in-kernel IOAPIC messages have to be delivered directly to
+ *    x2APIC, because the kernel does not support interrupt remapping.
+ *    In order to support broadcast without interrupt remapping, x2APIC
+ *    rewrites the destination of non-IPI messages from APIC_BROADCAST
+ *    to X2APIC_BROADCAST.
+ *
+ * The broadcast quirk can be disabled with KVM_CAP_X2APIC_API.  This is
+ * important when userspace wants to use x2APIC-format MSIs, because
+ * APIC_BROADCAST (0xff) is a legal route for "cluster 0, CPUs 0-7".
  */
-static u32 kvm_apic_mda(unsigned int dest_id, struct kvm_lapic *source,
-                                              struct kvm_lapic *target)
+static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, unsigned int dest_id,
+		struct kvm_lapic *source, struct kvm_lapic *target)
 {
 	bool ipi = source != NULL;
 	bool x2apic_mda = apic_x2apic_mode(ipi ? source : target);
 
-	if (!ipi && dest_id == APIC_BROADCAST && x2apic_mda)
+	if (!vcpu->kvm->arch.x2apic_broadcast_quirk_disabled &&
+	    !ipi && dest_id == APIC_BROADCAST && x2apic_mda)
 		return X2APIC_BROADCAST;
 
 	return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id);
@@ -619,7 +656,7 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 			   int short_hand, unsigned int dest, int dest_mode)
 {
 	struct kvm_lapic *target = vcpu->arch.apic;
-	u32 mda = kvm_apic_mda(dest, source, target);
+	u32 mda = kvm_apic_mda(vcpu, dest, source, target);
 
 	apic_debug("target %p, source %p, dest 0x%x, "
 		   "dest_mode 0x%x, short_hand 0x%x\n",
@@ -671,102 +708,126 @@ static void kvm_apic_disabled_lapic_found(struct kvm *kvm)
 	}
 }
 
-bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
-		struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map)
+static bool kvm_apic_is_broadcast_dest(struct kvm *kvm, struct kvm_lapic **src,
+		struct kvm_lapic_irq *irq, struct kvm_apic_map *map)
 {
-	struct kvm_apic_map *map;
-	unsigned long bitmap = 1;
-	struct kvm_lapic **dst;
-	int i;
-	bool ret, x2apic_ipi;
+	if (kvm->arch.x2apic_broadcast_quirk_disabled) {
+		if ((irq->dest_id == APIC_BROADCAST &&
+				map->mode != KVM_APIC_MODE_X2APIC))
+			return true;
+		if (irq->dest_id == X2APIC_BROADCAST)
+			return true;
+	} else {
+		bool x2apic_ipi = src && *src && apic_x2apic_mode(*src);
+		if (irq->dest_id == (x2apic_ipi ?
+		                     X2APIC_BROADCAST : APIC_BROADCAST))
+			return true;
+	}
 
-	*r = -1;
+	return false;
+}
 
-	if (irq->shorthand == APIC_DEST_SELF) {
-		*r = kvm_apic_set_irq(src->vcpu, irq, dest_map);
-		return true;
-	}
+/* Return true if the interrupt can be handled by using *bitmap as index mask
+ * for valid destinations in *dst array.
+ * Return false if kvm_apic_map_get_dest_lapic did nothing useful.
+ * Note: we may have zero kvm_lapic destinations when we return true, which
+ * means that the interrupt should be dropped.  In this case, *bitmap would be
+ * zero and *dst undefined.
+ */
+static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm,
+		struct kvm_lapic **src, struct kvm_lapic_irq *irq,
+		struct kvm_apic_map *map, struct kvm_lapic ***dst,
+		unsigned long *bitmap)
+{
+	int i, lowest;
 
-	if (irq->shorthand)
+	if (irq->shorthand == APIC_DEST_SELF && src) {
+		*dst = src;
+		*bitmap = 1;
+		return true;
+	} else if (irq->shorthand)
 		return false;
 
-	x2apic_ipi = src && apic_x2apic_mode(src);
-	if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST))
+	if (!map || kvm_apic_is_broadcast_dest(kvm, src, irq, map))
 		return false;
 
-	ret = true;
-	rcu_read_lock();
-	map = rcu_dereference(kvm->arch.apic_map);
-
-	if (!map) {
-		ret = false;
-		goto out;
+	if (irq->dest_mode == APIC_DEST_PHYSICAL) {
+		if (irq->dest_id > map->max_apic_id) {
+			*bitmap = 0;
+		} else {
+			*dst = &map->phys_map[irq->dest_id];
+			*bitmap = 1;
+		}
+		return true;
 	}
 
-	if (irq->dest_mode == APIC_DEST_PHYSICAL) {
-		if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
-			goto out;
+	*bitmap = 0;
+	if (!kvm_apic_map_get_logical_dest(map, irq->dest_id, dst,
+				(u16 *)bitmap))
+		return false;
 
-		dst = &map->phys_map[irq->dest_id];
-	} else {
-		u16 cid;
+	if (!kvm_lowest_prio_delivery(irq))
+		return true;
 
-		if (!kvm_apic_logical_map_valid(map)) {
-			ret = false;
-			goto out;
+	if (!kvm_vector_hashing_enabled()) {
+		lowest = -1;
+		for_each_set_bit(i, bitmap, 16) {
+			if (!(*dst)[i])
+				continue;
+			if (lowest < 0)
+				lowest = i;
+			else if (kvm_apic_compare_prio((*dst)[i]->vcpu,
+						(*dst)[lowest]->vcpu) < 0)
+				lowest = i;
 		}
+	} else {
+		if (!*bitmap)
+			return true;
 
-		apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap);
+		lowest = kvm_vector_to_index(irq->vector, hweight16(*bitmap),
+				bitmap, 16);
 
-		if (cid >= ARRAY_SIZE(map->logical_map))
-			goto out;
+		if (!(*dst)[lowest]) {
+			kvm_apic_disabled_lapic_found(kvm);
+			*bitmap = 0;
+			return true;
+		}
+	}
 
-		dst = map->logical_map[cid];
+	*bitmap = (lowest >= 0) ? 1 << lowest : 0;
 
-		if (!kvm_lowest_prio_delivery(irq))
-			goto set_irq;
+	return true;
+}
 
-		if (!kvm_vector_hashing_enabled()) {
-			int l = -1;
-			for_each_set_bit(i, &bitmap, 16) {
-				if (!dst[i])
-					continue;
-				if (l < 0)
-					l = i;
-				else if (kvm_apic_compare_prio(dst[i]->vcpu,
-							dst[l]->vcpu) < 0)
-					l = i;
-			}
-			bitmap = (l >= 0) ? 1 << l : 0;
-		} else {
-			int idx;
-			unsigned int dest_vcpus;
+bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
+		struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map)
+{
+	struct kvm_apic_map *map;
+	unsigned long bitmap;
+	struct kvm_lapic **dst = NULL;
+	int i;
+	bool ret;
 
-			dest_vcpus = hweight16(bitmap);
-			if (dest_vcpus == 0)
-				goto out;
+	*r = -1;
 
-			idx = kvm_vector_to_index(irq->vector,
-				dest_vcpus, &bitmap, 16);
+	if (irq->shorthand == APIC_DEST_SELF) {
+		*r = kvm_apic_set_irq(src->vcpu, irq, dest_map);
+		return true;
+	}
 
-			if (!dst[idx]) {
-				kvm_apic_disabled_lapic_found(kvm);
-				goto out;
-			}
+	rcu_read_lock();
+	map = rcu_dereference(kvm->arch.apic_map);
 
-			bitmap = (idx >= 0) ? 1 << idx : 0;
+	ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dst, &bitmap);
+	if (ret)
+		for_each_set_bit(i, &bitmap, 16) {
+			if (!dst[i])
+				continue;
+			if (*r < 0)
+				*r = 0;
+			*r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map);
 		}
-	}
 
-set_irq:
-	for_each_set_bit(i, &bitmap, 16) {
-		if (!dst[i])
-			continue;
-		if (*r < 0)
-			*r = 0;
-		*r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map);
-	}
-out:
 	rcu_read_unlock();
 	return ret;
 }
@@ -789,8 +850,9 @@ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			struct kvm_vcpu **dest_vcpu)
 {
 	struct kvm_apic_map *map;
+	unsigned long bitmap;
+	struct kvm_lapic **dst = NULL;
 	bool ret = false;
-	struct kvm_lapic *dst = NULL;
 
 	if (irq->shorthand)
 		return false;
@@ -798,69 +860,16 @@ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 	rcu_read_lock();
 	map = rcu_dereference(kvm->arch.apic_map);
 
-	if (!map)
-		goto out;
-
-	if (irq->dest_mode == APIC_DEST_PHYSICAL) {
-		if (irq->dest_id == 0xFF)
-			goto out;
-
-		if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
-			goto out;
-
-		dst = map->phys_map[irq->dest_id];
-		if (dst && kvm_apic_present(dst->vcpu))
-			*dest_vcpu = dst->vcpu;
-		else
-			goto out;
-	} else {
-		u16 cid;
-		unsigned long bitmap = 1;
-		int i, r = 0;
-
-		if (!kvm_apic_logical_map_valid(map))
-			goto out;
-
-		apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap);
-
-		if (cid >= ARRAY_SIZE(map->logical_map))
-			goto out;
+	if (kvm_apic_map_get_dest_lapic(kvm, NULL, irq, map, &dst, &bitmap) &&
+			hweight16(bitmap) == 1) {
+		unsigned long i = find_first_bit(&bitmap, 16);
 
-		if (kvm_vector_hashing_enabled() &&
-				kvm_lowest_prio_delivery(irq)) {
-			int idx;
-			unsigned int dest_vcpus;
-
-			dest_vcpus = hweight16(bitmap);
-			if (dest_vcpus == 0)
-				goto out;
-
-			idx = kvm_vector_to_index(irq->vector, dest_vcpus,
-						  &bitmap, 16);
-
-			dst = map->logical_map[cid][idx];
-			if (!dst) {
-				kvm_apic_disabled_lapic_found(kvm);
-				goto out;
-			}
-
-			*dest_vcpu = dst->vcpu;
-		} else {
-			for_each_set_bit(i, &bitmap, 16) {
-				dst = map->logical_map[cid][i];
-				if (++r == 2)
-					goto out;
-			}
-
-			if (dst && kvm_apic_present(dst->vcpu))
-				*dest_vcpu = dst->vcpu;
-			else
-				goto out;
+		if (dst[i]) {
+			*dest_vcpu = dst[i]->vcpu;
+			ret = true;
 		}
 	}
 
-	ret = true;
-out:
 	rcu_read_unlock();
 	return ret;
 }
@@ -1127,12 +1136,6 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
 		return 0;
 
 	switch (offset) {
-	case APIC_ID:
-		if (apic_x2apic_mode(apic))
-			val = kvm_apic_id(apic);
-		else
-			val = kvm_apic_id(apic) << 24;
-		break;
 	case APIC_ARBPRI:
 		apic_debug("Access APIC ARBPRI register which is for P6\n");
 		break;
@@ -1314,6 +1317,108 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
 }
 
+static void start_sw_tscdeadline(struct kvm_lapic *apic)
+{
+	u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
+	u64 ns = 0;
+	ktime_t expire;
+	struct kvm_vcpu *vcpu = apic->vcpu;
+	unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz;
+	unsigned long flags;
+	ktime_t now;
+
+	if (unlikely(!tscdeadline || !this_tsc_khz))
+		return;
+
+	local_irq_save(flags);
+
+	now = apic->lapic_timer.timer.base->get_time();
+	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
+	if (likely(tscdeadline > guest_tsc)) {
+		ns = (tscdeadline - guest_tsc) * 1000000ULL;
+		do_div(ns, this_tsc_khz);
+		expire = ktime_add_ns(now, ns);
+		expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
+		hrtimer_start(&apic->lapic_timer.timer,
+				expire, HRTIMER_MODE_ABS_PINNED);
+	} else
+		apic_timer_expired(apic);
+
+	local_irq_restore(flags);
+}
+
+bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.apic->lapic_timer.hv_timer_in_use;
+}
+EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
+
+static void cancel_hv_tscdeadline(struct kvm_lapic *apic)
+{
+	kvm_x86_ops->cancel_hv_timer(apic->vcpu);
+	apic->lapic_timer.hv_timer_in_use = false;
+}
+
+void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
+	WARN_ON(swait_active(&vcpu->wq));
+	cancel_hv_tscdeadline(apic);
+	apic_timer_expired(apic);
+}
+EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
+
+static bool start_hv_tscdeadline(struct kvm_lapic *apic)
+{
+	u64 tscdeadline = apic->lapic_timer.tscdeadline;
+
+	if (atomic_read(&apic->lapic_timer.pending) ||
+		kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) {
+		if (apic->lapic_timer.hv_timer_in_use)
+			cancel_hv_tscdeadline(apic);
+	} else {
+		apic->lapic_timer.hv_timer_in_use = true;
+		hrtimer_cancel(&apic->lapic_timer.timer);
+
+		/* In case the sw timer triggered in the window */
+		if (atomic_read(&apic->lapic_timer.pending))
+			cancel_hv_tscdeadline(apic);
+	}
+	trace_kvm_hv_timer_state(apic->vcpu->vcpu_id,
+			apic->lapic_timer.hv_timer_in_use);
+	return apic->lapic_timer.hv_timer_in_use;
+}
+
+void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	WARN_ON(apic->lapic_timer.hv_timer_in_use);
+
+	if (apic_lvtt_tscdeadline(apic))
+		start_hv_tscdeadline(apic);
+}
+EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer);
+
+void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	/* Possibly the TSC deadline timer is not enabled yet */
+	if (!apic->lapic_timer.hv_timer_in_use)
+		return;
+
+	cancel_hv_tscdeadline(apic);
+
+	if (atomic_read(&apic->lapic_timer.pending))
+		return;
+
+	start_sw_tscdeadline(apic);
+}
+EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
+
 static void start_apic_timer(struct kvm_lapic *apic)
 {
 	ktime_t now;
@@ -1360,32 +1465,8 @@ static void start_apic_timer(struct kvm_lapic *apic)
 			   ktime_to_ns(ktime_add_ns(now,
 					apic->lapic_timer.period)));
 	} else if (apic_lvtt_tscdeadline(apic)) {
-		/* lapic timer in tsc deadline mode */
-		u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
-		u64 ns = 0;
-		ktime_t expire;
-		struct kvm_vcpu *vcpu = apic->vcpu;
-		unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz;
-		unsigned long flags;
-
-		if (unlikely(!tscdeadline || !this_tsc_khz))
-			return;
-
-		local_irq_save(flags);
-
-		now = apic->lapic_timer.timer.base->get_time();
-		guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-		if (likely(tscdeadline > guest_tsc)) {
-			ns = (tscdeadline - guest_tsc) * 1000000ULL;
-			do_div(ns, this_tsc_khz);
-			expire = ktime_add_ns(now, ns);
-			expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
-			hrtimer_start(&apic->lapic_timer.timer,
-				      expire, HRTIMER_MODE_ABS_PINNED);
-		} else
-			apic_timer_expired(apic);
-
-		local_irq_restore(flags);
+		if (!(kvm_x86_ops->set_hv_timer && start_hv_tscdeadline(apic)))
+			start_sw_tscdeadline(apic);
 	}
 }
 
@@ -1413,7 +1494,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	switch (reg) {
 	case APIC_ID:		/* Local APIC ID */
 		if (!apic_x2apic_mode(apic))
-			kvm_apic_set_id(apic, val >> 24);
+			kvm_apic_set_xapic_id(apic, val >> 24);
 		else
 			ret = 1;
 		break;
@@ -1674,9 +1755,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 
 	/* update jump label if enable bit changes */
 	if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) {
-		if (value & MSR_IA32_APICBASE_ENABLE)
+		if (value & MSR_IA32_APICBASE_ENABLE) {
+			kvm_apic_set_xapic_id(apic, vcpu->vcpu_id);
 			static_key_slow_dec_deferred(&apic_hw_disabled);
-		else
+		} else
 			static_key_slow_inc(&apic_hw_disabled.key);
 		recalculate_apic_map(vcpu->kvm);
 	}
@@ -1716,8 +1798,11 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
-	if (!init_event)
-		kvm_apic_set_id(apic, vcpu->vcpu_id);
+	if (!init_event) {
+		kvm_lapic_set_base(vcpu, APIC_DEFAULT_PHYS_BASE |
+		                         MSR_IA32_APICBASE_ENABLE);
+		kvm_apic_set_xapic_id(apic, vcpu->vcpu_id);
+	}
 	kvm_apic_set_version(apic->vcpu);
 
 	for (i = 0; i < KVM_APIC_LVT_NUM; i++)
@@ -1856,9 +1941,6 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 	 * thinking that APIC satet has changed.
 	 */
 	vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
-	kvm_lapic_set_base(vcpu,
-			APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE);
-
 	static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
 	kvm_lapic_reset(vcpu, false);
 	kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
@@ -1938,17 +2020,48 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	return vector;
 }
 
-void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
-		struct kvm_lapic_state *s)
+static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
+		struct kvm_lapic_state *s, bool set)
+{
+	if (apic_x2apic_mode(vcpu->arch.apic)) {
+		u32 *id = (u32 *)(s->regs + APIC_ID);
+
+		if (vcpu->kvm->arch.x2apic_format) {
+			if (*id != vcpu->vcpu_id)
+				return -EINVAL;
+		} else {
+			if (set)
+				*id >>= 24;
+			else
+				*id <<= 24;
+		}
+	}
+
+	return 0;
+}
+
+int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
+{
+	memcpy(s->regs, vcpu->arch.apic->regs, sizeof(*s));
+	return kvm_apic_state_fixup(vcpu, s, false);
+}
+
+int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
+	int r;
+
 
 	kvm_lapic_set_base(vcpu, vcpu->arch.apic_base);
 	/* set SPIV separately to get count of SW disabled APICs right */
 	apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV)));
+
+	r = kvm_apic_state_fixup(vcpu, s, true);
+	if (r)
+		return r;
 	memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
-	/* call kvm_apic_set_id() to put apic into apic_map */
-	kvm_apic_set_id(apic, kvm_apic_id(apic));
+
+	recalculate_apic_map(vcpu->kvm);
 	kvm_apic_set_version(vcpu);
 
 	apic_update_ppr(apic);
@@ -1974,6 +2087,8 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 		kvm_rtc_eoi_tracking_restore_one(vcpu);
 
 	vcpu->arch.apic_arb_prio = 0;
+
+	return 0;
 }
 
 void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 891c6da7d4aa..f60d01c29d51 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -20,6 +20,7 @@ struct kvm_timer {
 	u64 tscdeadline;
 	u64 expired_tscdeadline;
 	atomic_t pending;			/* accumulated triggered timers */
+	bool hv_timer_in_use;
 };
 
 struct kvm_lapic {
@@ -80,8 +81,8 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 
 u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
 int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
-void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
-		struct kvm_lapic_state *s);
+int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
+int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
 
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
@@ -199,9 +200,15 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu)
 	return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
 }
 
-static inline int kvm_apic_id(struct kvm_lapic *apic)
+static inline u32 kvm_apic_id(struct kvm_lapic *apic)
 {
-	return (kvm_lapic_get_reg(apic, APIC_ID) >> 24) & 0xff;
+	/* To avoid a race between apic_base and following APIC_ID update when
+	 * switching to x2apic_mode, the x2apic mode returns initial x2apic id.
+	 */
+	if (apic_x2apic_mode(apic))
+		return apic->vcpu->vcpu_id;
+
+	return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
 }
 
 bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
@@ -212,4 +219,8 @@ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			struct kvm_vcpu **dest_vcpu);
 int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
 			const unsigned long *bitmap, u32 bitmap_size);
+void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu);
+void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu);
+void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu);
+bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu);
 #endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index def97b3a392b..3d4cc8cc56a3 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -29,7 +29,8 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/export.h>
 #include <linux/swap.h>
 #include <linux/hugetlb.h>
 #include <linux/compiler.h>
@@ -175,6 +176,7 @@ static u64 __read_mostly shadow_user_mask;
 static u64 __read_mostly shadow_accessed_mask;
 static u64 __read_mostly shadow_dirty_mask;
 static u64 __read_mostly shadow_mmio_mask;
+static u64 __read_mostly shadow_present_mask;
 
 static void mmu_spte_set(u64 *sptep, u64 spte);
 static void mmu_free_roots(struct kvm_vcpu *vcpu);
@@ -282,13 +284,14 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
 }
 
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask)
+		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask)
 {
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
 	shadow_dirty_mask = dirty_mask;
 	shadow_nx_mask = nx_mask;
 	shadow_x_mask = x_mask;
+	shadow_present_mask = p_mask;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
@@ -304,7 +307,7 @@ static int is_nx(struct kvm_vcpu *vcpu)
 
 static int is_shadow_present_pte(u64 pte)
 {
-	return pte & PT_PRESENT_MASK && !is_mmio_spte(pte);
+	return (pte & 0xFFFFFFFFull) && !is_mmio_spte(pte);
 }
 
 static int is_large_pte(u64 pte)
@@ -523,7 +526,7 @@ static void mmu_spte_set(u64 *sptep, u64 new_spte)
 }
 
 /* Rules for using mmu_spte_update:
- * Update the state bits, it means the mapped pfn is not changged.
+ * Update the state bits, it means the mapped pfn is not changed.
  *
  * Whenever we overwrite a writable spte with a read-only one we
  * should flush remote TLBs. Otherwise rmap_write_protect
@@ -2245,10 +2248,9 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
 {
 	u64 spte;
 
-	BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK ||
-			VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
+	BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
 
-	spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
+	spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK |
 	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
 
 	mmu_spte_set(sptep, spte);
@@ -2515,13 +2517,19 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    gfn_t gfn, kvm_pfn_t pfn, bool speculative,
 		    bool can_unsync, bool host_writable)
 {
-	u64 spte;
+	u64 spte = 0;
 	int ret = 0;
 
 	if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
 		return 0;
 
-	spte = PT_PRESENT_MASK;
+	/*
+	 * For the EPT case, shadow_present_mask is 0 if hardware
+	 * supports exec-only page table entries.  In that case,
+	 * ACC_USER_MASK and shadow_user_mask are used to represent
+	 * read access.  See FNAME(gpte_access) in paging_tmpl.h.
+	 */
+	spte |= shadow_present_mask;
 	if (!speculative)
 		spte |= shadow_accessed_mask;
 
@@ -3189,7 +3197,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 		MMU_WARN_ON(VALID_PAGE(root));
 		if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
 			pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i);
-			if (!is_present_gpte(pdptr)) {
+			if (!(pdptr & PT_PRESENT_MASK)) {
 				vcpu->arch.mmu.pae_root[i] = 0;
 				continue;
 			}
@@ -3914,9 +3922,7 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu,
 				 *   clearer.
 				 */
 				smap = cr4_smap && u && !uf && !ff;
-			} else
-				/* Not really needed: no U/S accesses on ept  */
-				u = 1;
+			}
 
 			fault = (ff && !x) || (uf && !u) || (wf && !w) ||
 				(smapf && smap);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 66b33b96a31b..ddc56e91f2e4 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -93,11 +93,6 @@ static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
 	return kvm_mmu_load(vcpu);
 }
 
-static inline int is_present_gpte(unsigned long pte)
-{
-	return pte & PT_PRESENT_MASK;
-}
-
 /*
  * Currently, we have two sorts of write-protection, a) the first one
  * write-protects guest page to sync the guest modification, b) another one is
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index bc019f70e0b6..a01105485315 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -131,7 +131,7 @@ static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte)
 static inline int FNAME(is_present_gpte)(unsigned long pte)
 {
 #if PTTYPE != PTTYPE_EPT
-	return is_present_gpte(pte);
+	return pte & PT_PRESENT_MASK;
 #else
 	return pte & 7;
 #endif
@@ -181,13 +181,19 @@ no_present:
 	return true;
 }
 
+/*
+ * For PTTYPE_EPT, a page table can be executable but not readable
+ * on supported processors. Therefore, set_spte does not automatically
+ * set bit 0 if execute only is supported. Here, we repurpose ACC_USER_MASK
+ * to signify readability since it isn't used in the EPT case
+ */
 static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte)
 {
 	unsigned access;
 #if PTTYPE == PTTYPE_EPT
 	access = ((gpte & VMX_EPT_WRITABLE_MASK) ? ACC_WRITE_MASK : 0) |
 		((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) |
-		ACC_USER_MASK;
+		((gpte & VMX_EPT_READABLE_MASK) ? ACC_USER_MASK : 0);
 #else
 	BUILD_BUG_ON(ACC_EXEC_MASK != PT_PRESENT_MASK);
 	BUILD_BUG_ON(ACC_EXEC_MASK != 1);
diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c
index ab38af4f4947..9d4a8504a95a 100644
--- a/arch/x86/kvm/pmu_intel.c
+++ b/arch/x86/kvm/pmu_intel.c
@@ -93,7 +93,7 @@ static unsigned intel_find_fixed_event(int idx)
 	return intel_arch_events[fixed_pmc_events[idx]].event_type;
 }
 
-/* check if a PMC is enabled by comparising it with globl_ctrl bits. */
+/* check if a PMC is enabled by comparing it with globl_ctrl bits. */
 static bool intel_pmc_is_enabled(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 16ef31b87452..af523d84d102 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1577,7 +1577,7 @@ static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
 static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
        /*
-        * Any change of EFLAGS.VM is accompained by a reload of SS
+        * Any change of EFLAGS.VM is accompanied by a reload of SS
         * (caused by either a task switch or an inter-privilege IRET),
         * so we do not need to update the CPL here.
         */
@@ -4940,6 +4940,12 @@ out:
 static void svm_handle_external_intr(struct kvm_vcpu *vcpu)
 {
 	local_irq_enable();
+	/*
+	 * We must have an instruction with interrupts enabled, so
+	 * the timer interrupt isn't delayed by the interrupt shadow.
+	 */
+	asm("nop");
+	local_irq_disable();
 }
 
 static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 8de925031b5c..0a6cc6754ec5 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1348,6 +1348,21 @@ TRACE_EVENT(kvm_avic_unaccelerated_access,
 		  __entry->vec)
 );
 
+TRACE_EVENT(kvm_hv_timer_state,
+		TP_PROTO(unsigned int vcpu_id, unsigned int hv_timer_in_use),
+		TP_ARGS(vcpu_id, hv_timer_in_use),
+		TP_STRUCT__entry(
+			__field(unsigned int, vcpu_id)
+			__field(unsigned int, hv_timer_in_use)
+			),
+		TP_fast_assign(
+			__entry->vcpu_id = vcpu_id;
+			__entry->hv_timer_in_use = hv_timer_in_use;
+			),
+		TP_printk("vcpu_id %x hv_timer %x\n",
+			__entry->vcpu_id,
+			__entry->hv_timer_in_use)
+);
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index df07a0a4611f..bc354f003ce1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -110,6 +110,13 @@ module_param_named(pml, enable_pml, bool, S_IRUGO);
 
 #define KVM_VMX_TSC_MULTIPLIER_MAX     0xffffffffffffffffULL
 
+/* Guest_tsc -> host_tsc conversion requires 64-bit division.  */
+static int __read_mostly cpu_preemption_timer_multi;
+static bool __read_mostly enable_preemption_timer = 1;
+#ifdef CONFIG_X86_64
+module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
+#endif
+
 #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
 #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
 #define KVM_VM_CR0_ALWAYS_ON						\
@@ -398,6 +405,12 @@ struct nested_vmx {
 	/* The host-usable pointer to the above */
 	struct page *current_vmcs12_page;
 	struct vmcs12 *current_vmcs12;
+	/*
+	 * Cache of the guest's VMCS, existing outside of guest memory.
+	 * Loaded from guest memory during VMPTRLD. Flushed to guest
+	 * memory during VMXOFF, VMCLEAR, VMPTRLD.
+	 */
+	struct vmcs12 *cached_vmcs12;
 	struct vmcs *current_shadow_vmcs;
 	/*
 	 * Indicates if the shadow vmcs must be updated with the
@@ -421,7 +434,6 @@ struct nested_vmx {
 	struct pi_desc *pi_desc;
 	bool pi_pending;
 	u16 posted_intr_nv;
-	u64 msr_ia32_feature_control;
 
 	struct hrtimer preemption_timer;
 	bool preemption_timer_expired;
@@ -597,11 +609,22 @@ struct vcpu_vmx {
 #define PML_ENTITY_NUM		512
 	struct page *pml_pg;
 
+	/* apic deadline value in host tsc */
+	u64 hv_deadline_tsc;
+
 	u64 current_tsc_ratio;
 
 	bool guest_pkru_valid;
 	u32 guest_pkru;
 	u32 host_pkru;
+
+	/*
+	 * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
+	 * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included
+	 * in msr_ia32_feature_control_valid_bits.
+	 */
+	u64 msr_ia32_feature_control;
+	u64 msr_ia32_feature_control_valid_bits;
 };
 
 enum segment_cache_field {
@@ -841,7 +864,7 @@ static inline short vmcs_field_to_offset(unsigned long field)
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 {
-	return to_vmx(vcpu)->nested.current_vmcs12;
+	return to_vmx(vcpu)->nested.cached_vmcs12;
 }
 
 static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr)
@@ -1056,6 +1079,58 @@ static inline bool cpu_has_vmx_virtual_intr_delivery(void)
 		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
 }
 
+/*
+ * Comment's format: document - errata name - stepping - processor name.
+ * Refer from
+ * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp
+ */
+static u32 vmx_preemption_cpu_tfms[] = {
+/* 323344.pdf - BA86   - D0 - Xeon 7500 Series */
+0x000206E6,
+/* 323056.pdf - AAX65  - C2 - Xeon L3406 */
+/* 322814.pdf - AAT59  - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */
+/* 322911.pdf - AAU65  - C2 - i5-600, i3-500 Desktop and Pentium G6950 */
+0x00020652,
+/* 322911.pdf - AAU65  - K0 - i5-600, i3-500 Desktop and Pentium G6950 */
+0x00020655,
+/* 322373.pdf - AAO95  - B1 - Xeon 3400 Series */
+/* 322166.pdf - AAN92  - B1 - i7-800 and i5-700 Desktop */
+/*
+ * 320767.pdf - AAP86  - B1 -
+ * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile
+ */
+0x000106E5,
+/* 321333.pdf - AAM126 - C0 - Xeon 3500 */
+0x000106A0,
+/* 321333.pdf - AAM126 - C1 - Xeon 3500 */
+0x000106A1,
+/* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */
+0x000106A4,
+ /* 321333.pdf - AAM126 - D0 - Xeon 3500 */
+ /* 321324.pdf - AAK139 - D0 - Xeon 5500 */
+ /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */
+0x000106A5,
+};
+
+static inline bool cpu_has_broken_vmx_preemption_timer(void)
+{
+	u32 eax = cpuid_eax(0x00000001), i;
+
+	/* Clear the reserved bits */
+	eax &= ~(0x3U << 14 | 0xfU << 28);
+	for (i = 0; i < ARRAY_SIZE(vmx_preemption_cpu_tfms); i++)
+		if (eax == vmx_preemption_cpu_tfms[i])
+			return true;
+
+	return false;
+}
+
+static inline bool cpu_has_vmx_preemption_timer(void)
+{
+	return vmcs_config.pin_based_exec_ctrl &
+		PIN_BASED_VMX_PREEMPTION_TIMER;
+}
+
 static inline bool cpu_has_vmx_posted_intr(void)
 {
 	return IS_ENABLED(CONFIG_X86_LOCAL_APIC) &&
@@ -1603,6 +1678,11 @@ static __always_inline void vmcs_set_bits(unsigned long field, u32 mask)
 	__vmcs_writel(field, __vmcs_readl(field) | mask);
 }
 
+static inline void vm_entry_controls_reset_shadow(struct vcpu_vmx *vmx)
+{
+	vmx->vm_entry_controls_shadow = vmcs_read32(VM_ENTRY_CONTROLS);
+}
+
 static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val)
 {
 	vmcs_write32(VM_ENTRY_CONTROLS, val);
@@ -1631,6 +1711,11 @@ static inline void vm_entry_controls_clearbit(struct vcpu_vmx *vmx, u32 val)
 	vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) & ~val);
 }
 
+static inline void vm_exit_controls_reset_shadow(struct vcpu_vmx *vmx)
+{
+	vmx->vm_exit_controls_shadow = vmcs_read32(VM_EXIT_CONTROLS);
+}
+
 static inline void vm_exit_controls_init(struct vcpu_vmx *vmx, u32 val)
 {
 	vmcs_write32(VM_EXIT_CONTROLS, val);
@@ -2121,22 +2206,14 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
+	bool already_loaded = vmx->loaded_vmcs->cpu == cpu;
 
 	if (!vmm_exclusive)
 		kvm_cpu_vmxon(phys_addr);
-	else if (vmx->loaded_vmcs->cpu != cpu)
+	else if (!already_loaded)
 		loaded_vmcs_clear(vmx->loaded_vmcs);
 
-	if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
-		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
-		vmcs_load(vmx->loaded_vmcs->vmcs);
-	}
-
-	if (vmx->loaded_vmcs->cpu != cpu) {
-		struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
-		unsigned long sysenter_esp;
-
-		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+	if (!already_loaded) {
 		local_irq_disable();
 		crash_disable_local_vmclear(cpu);
 
@@ -2151,6 +2228,18 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 			 &per_cpu(loaded_vmcss_on_cpu, cpu));
 		crash_enable_local_vmclear(cpu);
 		local_irq_enable();
+	}
+
+	if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
+		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
+		vmcs_load(vmx->loaded_vmcs->vmcs);
+	}
+
+	if (!already_loaded) {
+		struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
+		unsigned long sysenter_esp;
+
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 
 		/*
 		 * Linux uses per-cpu TSS and GDT, so set these when switching
@@ -2716,6 +2805,9 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
 			 VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
 			 VMX_EPT_INVEPT_BIT;
+		if (cpu_has_vmx_ept_execute_only())
+			vmx->nested.nested_vmx_ept_caps |=
+				VMX_EPT_EXECUTE_ONLY_BIT;
 		vmx->nested.nested_vmx_ept_caps &= vmx_capability.ept;
 		/*
 		 * For nested guests, we don't do anything specific
@@ -2864,6 +2956,14 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 	return 0;
 }
 
+static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu,
+						 uint64_t val)
+{
+	uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits;
+
+	return !(val & ~valid_bits);
+}
+
 /*
  * Reads an msr value (of 'msr_index') into 'pdata'.
  * Returns 0 on success, non-0 otherwise.
@@ -2905,10 +3005,15 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
 		break;
-	case MSR_IA32_FEATURE_CONTROL:
-		if (!nested_vmx_allowed(vcpu))
+	case MSR_IA32_MCG_EXT_CTL:
+		if (!msr_info->host_initiated &&
+		    !(to_vmx(vcpu)->msr_ia32_feature_control &
+		      FEATURE_CONTROL_LMCE))
 			return 1;
-		msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control;
+		msr_info->data = vcpu->arch.mcg_ext_ctl;
+		break;
+	case MSR_IA32_FEATURE_CONTROL:
+		msr_info->data = to_vmx(vcpu)->msr_ia32_feature_control;
 		break;
 	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
 		if (!nested_vmx_allowed(vcpu))
@@ -2998,12 +3103,20 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC_ADJUST:
 		ret = kvm_set_msr_common(vcpu, msr_info);
 		break;
+	case MSR_IA32_MCG_EXT_CTL:
+		if ((!msr_info->host_initiated &&
+		     !(to_vmx(vcpu)->msr_ia32_feature_control &
+		       FEATURE_CONTROL_LMCE)) ||
+		    (data & ~MCG_EXT_CTL_LMCE_EN))
+			return 1;
+		vcpu->arch.mcg_ext_ctl = data;
+		break;
 	case MSR_IA32_FEATURE_CONTROL:
-		if (!nested_vmx_allowed(vcpu) ||
-		    (to_vmx(vcpu)->nested.msr_ia32_feature_control &
+		if (!vmx_feature_control_msr_valid(vcpu, data) ||
+		    (to_vmx(vcpu)->msr_ia32_feature_control &
 		     FEATURE_CONTROL_LOCKED && !msr_info->host_initiated))
 			return 1;
-		vmx->nested.msr_ia32_feature_control = data;
+		vmx->msr_ia32_feature_control = data;
 		if (msr_info->host_initiated && data == 0)
 			vmx_leave_nested(vcpu);
 		break;
@@ -3297,25 +3410,27 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 		      vmx_capability.ept, vmx_capability.vpid);
 	}
 
-	min = VM_EXIT_SAVE_DEBUG_CONTROLS;
+	min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT;
 #ifdef CONFIG_X86_64
 	min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
 #endif
 	opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT |
-		VM_EXIT_ACK_INTR_ON_EXIT | VM_EXIT_CLEAR_BNDCFGS;
+		VM_EXIT_CLEAR_BNDCFGS;
 	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
 				&_vmexit_control) < 0)
 		return -EIO;
 
 	min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING;
-	opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR;
+	opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR |
+		 PIN_BASED_VMX_PREEMPTION_TIMER;
 	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
 				&_pin_based_exec_control) < 0)
 		return -EIO;
 
+	if (cpu_has_broken_vmx_preemption_timer())
+		_pin_based_exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
 	if (!(_cpu_based_2nd_exec_control &
-		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) ||
-		!(_vmexit_control & VM_EXIT_ACK_INTR_ON_EXIT))
+		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY))
 		_pin_based_exec_control &= ~PIN_BASED_POSTED_INTR;
 
 	min = VM_ENTRY_LOAD_DEBUG_CONTROLS;
@@ -3364,7 +3479,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 
 	/*
 	 * Some cpus support VM_ENTRY_(LOAD|SAVE)_IA32_PERF_GLOBAL_CTRL
-	 * but due to arrata below it can't be used. Workaround is to use
+	 * but due to errata below it can't be used. Workaround is to use
 	 * msr load mechanism to switch IA32_PERF_GLOBAL_CTRL.
 	 *
 	 * VM Exit May Incorrectly Clear IA32_PERF_GLOBAL_CTRL [34:32]
@@ -4781,6 +4896,8 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx)
 
 	if (!kvm_vcpu_apicv_active(&vmx->vcpu))
 		pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
+	/* Enable the preemption timer dynamically */
+	pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
 	return pin_based_exec_ctrl;
 }
 
@@ -4896,6 +5013,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	/* Control */
 	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
+	vmx->hv_deadline_tsc = -1;
 
 	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx));
 
@@ -6016,12 +6134,14 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 	trace_kvm_page_fault(gpa, exit_qualification);
 
-	/* It is a write fault? */
-	error_code = exit_qualification & PFERR_WRITE_MASK;
+	/* it is a read fault? */
+	error_code = (exit_qualification << 2) & PFERR_USER_MASK;
+	/* it is a write fault? */
+	error_code |= exit_qualification & PFERR_WRITE_MASK;
 	/* It is a fetch fault? */
 	error_code |= (exit_qualification << 2) & PFERR_FETCH_MASK;
 	/* ept page table is present? */
-	error_code |= (exit_qualification >> 3) & PFERR_PRESENT_MASK;
+	error_code |= (exit_qualification & 0x38) != 0;
 
 	vcpu->arch.exit_qualification = exit_qualification;
 
@@ -6355,9 +6475,6 @@ static __init int hardware_setup(void)
 	for (msr = 0x800; msr <= 0x8ff; msr++)
 		vmx_disable_intercept_msr_read_x2apic(msr);
 
-	/* According SDM, in x2apic mode, the whole id reg is used.  But in
-	 * KVM, it only use the highest eight bits. Need to intercept it */
-	vmx_enable_intercept_msr_read_x2apic(0x802);
 	/* TMCCT */
 	vmx_enable_intercept_msr_read_x2apic(0x839);
 	/* TPR */
@@ -6368,10 +6485,12 @@ static __init int hardware_setup(void)
 	vmx_disable_intercept_msr_write_x2apic(0x83f);
 
 	if (enable_ept) {
-		kvm_mmu_set_mask_ptes(0ull,
+		kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK,
 			(enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
 			(enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull,
-			0ull, VMX_EPT_EXECUTABLE_MASK);
+			0ull, VMX_EPT_EXECUTABLE_MASK,
+			cpu_has_vmx_ept_execute_only() ?
+				      0ull : VMX_EPT_READABLE_MASK);
 		ept_set_mmio_spte_mask();
 		kvm_enable_tdp();
 	} else
@@ -6393,8 +6512,21 @@ static __init int hardware_setup(void)
 		kvm_x86_ops->enable_log_dirty_pt_masked = NULL;
 	}
 
+	if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) {
+		u64 vmx_msr;
+
+		rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
+		cpu_preemption_timer_multi =
+			 vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
+	} else {
+		kvm_x86_ops->set_hv_timer = NULL;
+		kvm_x86_ops->cancel_hv_timer = NULL;
+	}
+
 	kvm_set_posted_intr_wakeup_handler(wakeup_handler);
 
+	kvm_mce_cap_supported |= MCG_LMCE_P;
+
 	return alloc_kvm_area();
 
 out8:
@@ -6862,16 +6994,22 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
-	if ((vmx->nested.msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
+	if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
 			!= VMXON_NEEDED_FEATURES) {
 		kvm_inject_gp(vcpu, 0);
 		return 1;
 	}
 
+	vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
+	if (!vmx->nested.cached_vmcs12)
+		return -ENOMEM;
+
 	if (enable_shadow_vmcs) {
 		shadow_vmcs = alloc_vmcs();
-		if (!shadow_vmcs)
+		if (!shadow_vmcs) {
+			kfree(vmx->nested.cached_vmcs12);
 			return -ENOMEM;
+		}
 		/* mark vmcs as shadow */
 		shadow_vmcs->revision_id |= (1u << 31);
 		/* init shadow vmcs */
@@ -6942,6 +7080,11 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
 		vmcs_write64(VMCS_LINK_POINTER, -1ull);
 	}
 	vmx->nested.posted_intr_nv = -1;
+
+	/* Flush VMCS12 to guest memory */
+	memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12,
+	       VMCS12_SIZE);
+
 	kunmap(vmx->nested.current_vmcs12_page);
 	nested_release_page(vmx->nested.current_vmcs12_page);
 	vmx->nested.current_vmptr = -1ull;
@@ -6962,6 +7105,7 @@ static void free_nested(struct vcpu_vmx *vmx)
 	nested_release_vmcs12(vmx);
 	if (enable_shadow_vmcs)
 		free_vmcs(vmx->nested.current_shadow_vmcs);
+	kfree(vmx->nested.cached_vmcs12);
 	/* Unpin physical memory we referred to in current vmcs02 */
 	if (vmx->nested.apic_access_page) {
 		nested_release_page(vmx->nested.apic_access_page);
@@ -7365,6 +7509,13 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		vmx->nested.current_vmptr = vmptr;
 		vmx->nested.current_vmcs12 = new_vmcs12;
 		vmx->nested.current_vmcs12_page = page;
+		/*
+		 * Load VMCS12 from guest memory since it is not already
+		 * cached.
+		 */
+		memcpy(vmx->nested.cached_vmcs12,
+		       vmx->nested.current_vmcs12, VMCS12_SIZE);
+
 		if (enable_shadow_vmcs) {
 			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
 				      SECONDARY_EXEC_SHADOW_VMCS);
@@ -7560,6 +7711,12 @@ static int handle_pml_full(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_preemption_timer(struct kvm_vcpu *vcpu)
+{
+	kvm_lapic_expired_hv_timer(vcpu);
+	return 1;
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -7610,6 +7767,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_XSAVES]                  = handle_xsaves,
 	[EXIT_REASON_XRSTORS]                 = handle_xrstors,
 	[EXIT_REASON_PML_FULL]		      = handle_pml_full,
+	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -7918,6 +8076,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		 * the XSS exit bitmap in vmcs12.
 		 */
 		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
+	case EXIT_REASON_PREEMPTION_TIMER:
+		return false;
 	default:
 		return true;
 	}
@@ -8303,7 +8463,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 	 * the next L2->L1 exit.
 	 */
 	if (!is_guest_mode(vcpu) ||
-	    !nested_cpu_has2(vmx->nested.current_vmcs12,
+	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
 			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
 }
@@ -8436,7 +8596,6 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 			"push %[sp]\n\t"
 #endif
 			"pushf\n\t"
-			"orl $0x200, (%%" _ASM_SP ")\n\t"
 			__ASM_SIZE(push) " $%c[cs]\n\t"
 			"call *%[entry]\n\t"
 			:
@@ -8449,8 +8608,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 			[ss]"i"(__KERNEL_DS),
 			[cs]"i"(__KERNEL_CS)
 			);
-	} else
-		local_irq_enable();
+	}
 }
 
 static bool vmx_has_high_real_mode_segbase(void)
@@ -8601,6 +8759,26 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host);
 }
 
+void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u64 tscl;
+	u32 delta_tsc;
+
+	if (vmx->hv_deadline_tsc == -1)
+		return;
+
+	tscl = rdtsc();
+	if (vmx->hv_deadline_tsc > tscl)
+		/* sure to be 32 bit only because checked on set_hv_timer */
+		delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
+			cpu_preemption_timer_multi);
+	else
+		delta_tsc = 0;
+
+	vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
+}
+
 static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8650,6 +8828,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	atomic_switch_perf_msrs(vmx);
 	debugctlmsr = get_debugctlmsr();
 
+	vmx_arm_hv_timer(vcpu);
+
 	vmx->__launched = vmx->loaded_vmcs->launched;
 	asm(
 		/* Store host registers */
@@ -8940,6 +9120,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	vmx->nested.current_vmptr = -1ull;
 	vmx->nested.current_vmcs12 = NULL;
 
+	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
+
 	return &vmx->vcpu;
 
 free_vmcs:
@@ -9080,6 +9262,13 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 
 	if (cpu_has_secondary_exec_ctrls())
 		vmcs_set_secondary_exec_control(secondary_exec_ctl);
+
+	if (nested_vmx_allowed(vcpu))
+		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+			FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+	else
+		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
+			~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -9636,9 +9825,14 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmcs_write64(VMCS_LINK_POINTER, -1ull);
 
 	exec_control = vmcs12->pin_based_vm_exec_control;
-	exec_control |= vmcs_config.pin_based_exec_ctrl;
+
+	/* Preemption timer setting is only taken from vmcs01.  */
 	exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+	exec_control |= vmcs_config.pin_based_exec_ctrl;
+	if (vmx->hv_deadline_tsc == -1)
+		exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
 
+	/* Posted interrupts setting is only taken from vmcs12.  */
 	if (nested_cpu_has_posted_intr(vmcs12)) {
 		/*
 		 * Note that we use L0's vector here and in
@@ -10556,8 +10750,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 				       vmcs12->vm_exit_intr_error_code,
 				       KVM_ISA_VMX);
 
-	vm_entry_controls_init(vmx, vmcs_read32(VM_ENTRY_CONTROLS));
-	vm_exit_controls_init(vmx, vmcs_read32(VM_EXIT_CONTROLS));
+	vm_entry_controls_reset_shadow(vmx);
+	vm_exit_controls_reset_shadow(vmx);
 	vmx_segment_cache_clear(vmx);
 
 	/* if no vmcs02 cache requested, remove the one we used */
@@ -10566,8 +10760,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 
 	load_vmcs12_host_state(vcpu, vmcs12);
 
-	/* Update TSC_OFFSET if TSC was changed while L2 ran */
+	/* Update any VMCS fields that might have changed while L2 ran */
 	vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+	if (vmx->hv_deadline_tsc == -1)
+		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
+				PIN_BASED_VMX_PREEMPTION_TIMER);
+	else
+		vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
+			      PIN_BASED_VMX_PREEMPTION_TIMER);
 
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
 	vmx->host_rsp = 0;
@@ -10647,6 +10847,64 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 	return X86EMUL_CONTINUE;
 }
 
+#ifdef CONFIG_X86_64
+/* (a << shift) / divisor, return 1 if overflow otherwise 0 */
+static inline int u64_shl_div_u64(u64 a, unsigned int shift,
+				  u64 divisor, u64 *result)
+{
+	u64 low = a << shift, high = a >> (64 - shift);
+
+	/* To avoid the overflow on divq */
+	if (high >= divisor)
+		return 1;
+
+	/* Low hold the result, high hold rem which is discarded */
+	asm("divq %2\n\t" : "=a" (low), "=d" (high) :
+	    "rm" (divisor), "0" (low), "1" (high));
+	*result = low;
+
+	return 0;
+}
+
+static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u64 tscl = rdtsc();
+	u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
+	u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+
+	/* Convert to host delta tsc if tsc scaling is enabled */
+	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
+			u64_shl_div_u64(delta_tsc,
+				kvm_tsc_scaling_ratio_frac_bits,
+				vcpu->arch.tsc_scaling_ratio,
+				&delta_tsc))
+		return -ERANGE;
+
+	/*
+	 * If the delta tsc can't fit in the 32 bit after the multi shift,
+	 * we can't use the preemption timer.
+	 * It's possible that it fits on later vmentries, but checking
+	 * on every vmentry is costly so we just use an hrtimer.
+	 */
+	if (delta_tsc >> (cpu_preemption_timer_multi + 32))
+		return -ERANGE;
+
+	vmx->hv_deadline_tsc = tscl + delta_tsc;
+	vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
+			PIN_BASED_VMX_PREEMPTION_TIMER);
+	return 0;
+}
+
+static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	vmx->hv_deadline_tsc = -1;
+	vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
+			PIN_BASED_VMX_PREEMPTION_TIMER);
+}
+#endif
+
 static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
 	if (ple_gap)
@@ -10691,7 +10949,7 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
  *   this case, return 1, otherwise, return 0.
  *
  */
-static int vmx_pre_block(struct kvm_vcpu *vcpu)
+static int pi_pre_block(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags;
 	unsigned int dest;
@@ -10758,7 +11016,18 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static void vmx_post_block(struct kvm_vcpu *vcpu)
+static int vmx_pre_block(struct kvm_vcpu *vcpu)
+{
+	if (pi_pre_block(vcpu))
+		return 1;
+
+	if (kvm_lapic_hv_timer_in_use(vcpu))
+		kvm_lapic_switch_to_sw_timer(vcpu);
+
+	return 0;
+}
+
+static void pi_post_block(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 	struct pi_desc old, new;
@@ -10800,6 +11069,14 @@ static void vmx_post_block(struct kvm_vcpu *vcpu)
 	}
 }
 
+static void vmx_post_block(struct kvm_vcpu *vcpu)
+{
+	if (kvm_x86_ops->set_hv_timer)
+		kvm_lapic_switch_to_hv_timer(vcpu);
+
+	pi_post_block(vcpu);
+}
+
 /*
  * vmx_update_pi_irte - set IRTE for Posted-Interrupts
  *
@@ -10844,7 +11121,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		 * We will support full lowest-priority interrupt later.
 		 */
 
-		kvm_set_msi_irq(e, &irq);
+		kvm_set_msi_irq(kvm, e, &irq);
 		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
 			/*
 			 * Make sure the IRTE is in remapped mode if
@@ -10889,6 +11166,16 @@ out:
 	return ret;
 }
 
+static void vmx_setup_mce(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.mcg_cap & MCG_LMCE_P)
+		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+			FEATURE_CONTROL_LMCE;
+	else
+		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
+			~FEATURE_CONTROL_LMCE;
+}
+
 static struct kvm_x86_ops vmx_x86_ops = {
 	.cpu_has_kvm_support = cpu_has_kvm_support,
 	.disabled_by_bios = vmx_disabled_by_bios,
@@ -11013,6 +11300,13 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.pmu_ops = &intel_pmu_ops,
 
 	.update_pi_irte = vmx_update_pi_irte,
+
+#ifdef CONFIG_X86_64
+	.set_hv_timer = vmx_set_hv_timer,
+	.cancel_hv_timer = vmx_cancel_hv_timer,
+#endif
+
+	.setup_mce = vmx_setup_mce,
 };
 
 static int __init vmx_init(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 45608a7da9b3..19f9f9e05c2a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -36,7 +36,8 @@
 #include <linux/kvm.h>
 #include <linux/fs.h>
 #include <linux/vmalloc.h>
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/moduleparam.h>
 #include <linux/mman.h>
 #include <linux/highmem.h>
 #include <linux/iommu.h>
@@ -70,7 +71,8 @@
 
 #define MAX_IO_MSRS 256
 #define KVM_MAX_MCE_BANKS 32
-#define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P)
+u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P;
+EXPORT_SYMBOL_GPL(kvm_mce_cap_supported);
 
 #define emul_to_vcpu(ctxt) \
 	container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt)
@@ -89,8 +91,12 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
 
+#define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
+                                    KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
+
 static void update_cr8_intercept(struct kvm_vcpu *vcpu);
 static void process_nmi(struct kvm_vcpu *vcpu);
+static void enter_smm(struct kvm_vcpu *vcpu);
 static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 
 struct kvm_x86_ops *kvm_x86_ops __read_mostly;
@@ -113,7 +119,8 @@ u8   __read_mostly kvm_tsc_scaling_ratio_frac_bits;
 EXPORT_SYMBOL_GPL(kvm_tsc_scaling_ratio_frac_bits);
 u64  __read_mostly kvm_max_tsc_scaling_ratio;
 EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio);
-static u64 __read_mostly kvm_default_tsc_scaling_ratio;
+u64 __read_mostly kvm_default_tsc_scaling_ratio;
+EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio);
 
 /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */
 static u32 __read_mostly tsc_tolerance_ppm = 250;
@@ -537,7 +544,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 		goto out;
 	}
 	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
-		if (is_present_gpte(pdpte[i]) &&
+		if ((pdpte[i] & PT_PRESENT_MASK) &&
 		    (pdpte[i] &
 		     vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
 			ret = 0;
@@ -982,6 +989,7 @@ static u32 emulated_msrs[] = {
 	MSR_IA32_MISC_ENABLE,
 	MSR_IA32_MCG_STATUS,
 	MSR_IA32_MCG_CTL,
+	MSR_IA32_MCG_EXT_CTL,
 	MSR_IA32_SMBASE,
 };
 
@@ -1161,7 +1169,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	int version;
 	int r;
 	struct pvclock_wall_clock wc;
-	struct timespec boot;
+	struct timespec64 boot;
 
 	if (!wall_clock)
 		return;
@@ -1184,13 +1192,13 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	 * wall clock specified here.  guest system time equals host
 	 * system time for us, thus we must fill in host boot time here.
 	 */
-	getboottime(&boot);
+	getboottime64(&boot);
 
 	if (kvm->arch.kvmclock_offset) {
-		struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset);
-		boot = timespec_sub(boot, ts);
+		struct timespec64 ts = ns_to_timespec64(kvm->arch.kvmclock_offset);
+		boot = timespec64_sub(boot, ts);
 	}
-	wc.sec = boot.tv_sec;
+	wc.sec = (u32)boot.tv_sec; /* overflow in 2106 guest time */
 	wc.nsec = boot.tv_nsec;
 	wc.version = version;
 
@@ -2615,6 +2623,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_TSC_CONTROL:
 		r = kvm_has_tsc_control;
 		break;
+	case KVM_CAP_X2APIC_API:
+		r = KVM_X2APIC_API_VALID_FLAGS;
+		break;
 	default:
 		r = 0;
 		break;
@@ -2677,11 +2688,9 @@ long kvm_arch_dev_ioctl(struct file *filp,
 		break;
 	}
 	case KVM_X86_GET_MCE_CAP_SUPPORTED: {
-		u64 mce_cap;
-
-		mce_cap = KVM_MCE_CAP_SUPPORTED;
 		r = -EFAULT;
-		if (copy_to_user(argp, &mce_cap, sizeof mce_cap))
+		if (copy_to_user(argp, &kvm_mce_cap_supported,
+				 sizeof(kvm_mce_cap_supported)))
 			goto out;
 		r = 0;
 		break;
@@ -2733,6 +2742,11 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 				rdtsc() - vcpu->arch.last_host_tsc;
 		if (tsc_delta < 0)
 			mark_tsc_unstable("KVM discovered backwards TSC");
+
+		if (kvm_lapic_hv_timer_in_use(vcpu) &&
+				kvm_x86_ops->set_hv_timer(vcpu,
+					kvm_get_lapic_tscdeadline_msr(vcpu)))
+			kvm_lapic_switch_to_sw_timer(vcpu);
 		if (check_tsc_unstable()) {
 			u64 offset = kvm_compute_tsc_offset(vcpu,
 						vcpu->arch.last_guest_tsc);
@@ -2766,15 +2780,17 @@ static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 	if (vcpu->arch.apicv_active)
 		kvm_x86_ops->sync_pir_to_irr(vcpu);
 
-	memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s);
-
-	return 0;
+	return kvm_apic_get_state(vcpu, s);
 }
 
 static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
-	kvm_apic_post_state_restore(vcpu, s);
+	int r;
+
+	r = kvm_apic_set_state(vcpu, s);
+	if (r)
+		return r;
 	update_cr8_intercept(vcpu);
 
 	return 0;
@@ -2859,7 +2875,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
 	r = -EINVAL;
 	if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
 		goto out;
-	if (mcg_cap & ~(KVM_MCE_CAP_SUPPORTED | 0xff | 0xff0000))
+	if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000))
 		goto out;
 	r = 0;
 	vcpu->arch.mcg_cap = mcg_cap;
@@ -2869,6 +2885,9 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
 	/* Init IA32_MCi_CTL to all 1s */
 	for (bank = 0; bank < bank_num; bank++)
 		vcpu->arch.mce_banks[bank*4] = ~(u64)0;
+
+	if (kvm_x86_ops->setup_mce)
+		kvm_x86_ops->setup_mce(vcpu);
 out:
 	return r;
 }
@@ -3767,7 +3786,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		r = -EEXIST;
 		if (irqchip_in_kernel(kvm))
 			goto split_irqchip_unlock;
-		if (atomic_read(&kvm->online_vcpus))
+		if (kvm->created_vcpus)
 			goto split_irqchip_unlock;
 		r = kvm_setup_empty_irq_routing(kvm);
 		if (r)
@@ -3781,6 +3800,18 @@ split_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
 		break;
 	}
+	case KVM_CAP_X2APIC_API:
+		r = -EINVAL;
+		if (cap->args[0] & ~KVM_X2APIC_API_VALID_FLAGS)
+			break;
+
+		if (cap->args[0] & KVM_X2APIC_API_USE_32BIT_IDS)
+			kvm->arch.x2apic_format = true;
+		if (cap->args[0] & KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
+			kvm->arch.x2apic_broadcast_quirk_disabled = true;
+
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -3832,7 +3863,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (kvm->arch.vpic)
 			goto create_irqchip_unlock;
 		r = -EINVAL;
-		if (atomic_read(&kvm->online_vcpus))
+		if (kvm->created_vcpus)
 			goto create_irqchip_unlock;
 		r = -ENOMEM;
 		vpic = kvm_create_pic(kvm);
@@ -3872,7 +3903,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 				   sizeof(struct kvm_pit_config)))
 			goto out;
 	create_pit:
-		mutex_lock(&kvm->slots_lock);
+		mutex_lock(&kvm->lock);
 		r = -EEXIST;
 		if (kvm->arch.vpit)
 			goto create_pit_unlock;
@@ -3881,7 +3912,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (kvm->arch.vpit)
 			r = 0;
 	create_pit_unlock:
-		mutex_unlock(&kvm->slots_lock);
+		mutex_unlock(&kvm->lock);
 		break;
 	case KVM_GET_IRQCHIP: {
 		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
@@ -3988,7 +4019,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	case KVM_SET_BOOT_CPU_ID:
 		r = 0;
 		mutex_lock(&kvm->lock);
-		if (atomic_read(&kvm->online_vcpus) != 0)
+		if (kvm->created_vcpus)
 			r = -EBUSY;
 		else
 			kvm->arch.bsp_vcpu_id = arg;
@@ -5296,13 +5327,8 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu)
 		/* This is a good place to trace that we are exiting SMM.  */
 		trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false);
 
-		if (unlikely(vcpu->arch.smi_pending)) {
-			kvm_make_request(KVM_REQ_SMI, vcpu);
-			vcpu->arch.smi_pending = 0;
-		} else {
-			/* Process a latched INIT, if any.  */
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
-		}
+		/* Process a latched INIT or SMI, if any.  */
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
 	}
 
 	kvm_mmu_reset_context(vcpu);
@@ -5848,8 +5874,8 @@ int kvm_arch_init(void *opaque)
 	kvm_x86_ops = ops;
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
-			PT_DIRTY_MASK, PT64_NX_MASK, 0);
-
+			PT_DIRTY_MASK, PT64_NX_MASK, 0,
+			PT_PRESENT_MASK);
 	kvm_timer_init();
 
 	perf_register_guest_info_callbacks(&kvm_guest_cbs);
@@ -6083,7 +6109,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 	}
 
 	/* try to inject new event if pending */
-	if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
+	if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
+		vcpu->arch.smi_pending = false;
+		enter_smm(vcpu);
+	} else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
 		--vcpu->arch.nmi_pending;
 		vcpu->arch.nmi_injected = true;
 		kvm_x86_ops->set_nmi(vcpu);
@@ -6106,6 +6135,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 			kvm_x86_ops->set_irq(vcpu);
 		}
 	}
+
 	return 0;
 }
 
@@ -6129,7 +6159,7 @@ static void process_nmi(struct kvm_vcpu *vcpu)
 #define put_smstate(type, buf, offset, val)			  \
 	*(type *)((buf) + (offset) - 0x7e00) = val
 
-static u32 process_smi_get_segment_flags(struct kvm_segment *seg)
+static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
 {
 	u32 flags = 0;
 	flags |= seg->g       << 23;
@@ -6143,7 +6173,7 @@ static u32 process_smi_get_segment_flags(struct kvm_segment *seg)
 	return flags;
 }
 
-static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
+static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
 {
 	struct kvm_segment seg;
 	int offset;
@@ -6158,11 +6188,11 @@ static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
 
 	put_smstate(u32, buf, offset + 8, seg.base);
 	put_smstate(u32, buf, offset + 4, seg.limit);
-	put_smstate(u32, buf, offset, process_smi_get_segment_flags(&seg));
+	put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg));
 }
 
 #ifdef CONFIG_X86_64
-static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
+static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
 {
 	struct kvm_segment seg;
 	int offset;
@@ -6171,7 +6201,7 @@ static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
 	kvm_get_segment(vcpu, &seg, n);
 	offset = 0x7e00 + n * 16;
 
-	flags = process_smi_get_segment_flags(&seg) >> 8;
+	flags = enter_smm_get_segment_flags(&seg) >> 8;
 	put_smstate(u16, buf, offset, seg.selector);
 	put_smstate(u16, buf, offset + 2, flags);
 	put_smstate(u32, buf, offset + 4, seg.limit);
@@ -6179,7 +6209,7 @@ static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
 }
 #endif
 
-static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf)
+static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
 {
 	struct desc_ptr dt;
 	struct kvm_segment seg;
@@ -6203,13 +6233,13 @@ static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf)
 	put_smstate(u32, buf, 0x7fc4, seg.selector);
 	put_smstate(u32, buf, 0x7f64, seg.base);
 	put_smstate(u32, buf, 0x7f60, seg.limit);
-	put_smstate(u32, buf, 0x7f5c, process_smi_get_segment_flags(&seg));
+	put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg));
 
 	kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
 	put_smstate(u32, buf, 0x7fc0, seg.selector);
 	put_smstate(u32, buf, 0x7f80, seg.base);
 	put_smstate(u32, buf, 0x7f7c, seg.limit);
-	put_smstate(u32, buf, 0x7f78, process_smi_get_segment_flags(&seg));
+	put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg));
 
 	kvm_x86_ops->get_gdt(vcpu, &dt);
 	put_smstate(u32, buf, 0x7f74, dt.address);
@@ -6220,7 +6250,7 @@ static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf)
 	put_smstate(u32, buf, 0x7f54, dt.size);
 
 	for (i = 0; i < 6; i++)
-		process_smi_save_seg_32(vcpu, buf, i);
+		enter_smm_save_seg_32(vcpu, buf, i);
 
 	put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
 
@@ -6229,7 +6259,7 @@ static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf)
 	put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
 }
 
-static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
+static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 {
 #ifdef CONFIG_X86_64
 	struct desc_ptr dt;
@@ -6261,7 +6291,7 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 
 	kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
 	put_smstate(u16, buf, 0x7e90, seg.selector);
-	put_smstate(u16, buf, 0x7e92, process_smi_get_segment_flags(&seg) >> 8);
+	put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8);
 	put_smstate(u32, buf, 0x7e94, seg.limit);
 	put_smstate(u64, buf, 0x7e98, seg.base);
 
@@ -6271,7 +6301,7 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 
 	kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
 	put_smstate(u16, buf, 0x7e70, seg.selector);
-	put_smstate(u16, buf, 0x7e72, process_smi_get_segment_flags(&seg) >> 8);
+	put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8);
 	put_smstate(u32, buf, 0x7e74, seg.limit);
 	put_smstate(u64, buf, 0x7e78, seg.base);
 
@@ -6280,31 +6310,26 @@ static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 	put_smstate(u64, buf, 0x7e68, dt.address);
 
 	for (i = 0; i < 6; i++)
-		process_smi_save_seg_64(vcpu, buf, i);
+		enter_smm_save_seg_64(vcpu, buf, i);
 #else
 	WARN_ON_ONCE(1);
 #endif
 }
 
-static void process_smi(struct kvm_vcpu *vcpu)
+static void enter_smm(struct kvm_vcpu *vcpu)
 {
 	struct kvm_segment cs, ds;
 	struct desc_ptr dt;
 	char buf[512];
 	u32 cr0;
 
-	if (is_smm(vcpu)) {
-		vcpu->arch.smi_pending = true;
-		return;
-	}
-
 	trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
 	vcpu->arch.hflags |= HF_SMM_MASK;
 	memset(buf, 0, 512);
 	if (guest_cpuid_has_longmode(vcpu))
-		process_smi_save_state_64(vcpu, buf);
+		enter_smm_save_state_64(vcpu, buf);
 	else
-		process_smi_save_state_32(vcpu, buf);
+		enter_smm_save_state_32(vcpu, buf);
 
 	kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
 
@@ -6360,6 +6385,12 @@ static void process_smi(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 }
 
+static void process_smi(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.smi_pending = true;
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
+}
+
 void kvm_make_scan_ioapic_request(struct kvm *kvm)
 {
 	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
@@ -6554,8 +6585,18 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 		if (inject_pending_event(vcpu, req_int_win) != 0)
 			req_immediate_exit = true;
-		/* enable NMI/IRQ window open exits if needed */
 		else {
+			/* Enable NMI/IRQ window open exits if needed.
+			 *
+			 * SMIs have two cases: 1) they can be nested, and
+			 * then there is nothing to do here because RSM will
+			 * cause a vmexit anyway; 2) or the SMI can be pending
+			 * because inject_pending_event has completed the
+			 * injection of an IRQ or NMI from the previous vmexit,
+			 * and then we request an immediate exit to inject the SMI.
+			 */
+			if (vcpu->arch.smi_pending && !is_smm(vcpu))
+				req_immediate_exit = true;
 			if (vcpu->arch.nmi_pending)
 				kvm_x86_ops->enable_nmi_window(vcpu);
 			if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
@@ -6606,12 +6647,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	kvm_load_guest_xcr0(vcpu);
 
-	if (req_immediate_exit)
+	if (req_immediate_exit) {
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
 		smp_send_reschedule(vcpu->cpu);
+	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
 	wait_lapic_expire(vcpu);
-	__kvm_guest_enter();
+	guest_enter_irqoff();
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
@@ -6662,16 +6705,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	++vcpu->stat.exits;
 
-	/*
-	 * We must have an instruction between local_irq_enable() and
-	 * kvm_guest_exit(), so the timer interrupt isn't delayed by
-	 * the interrupt shadow.  The stat.exits increment will do nicely.
-	 * But we need to prevent reordering, hence this barrier():
-	 */
-	barrier();
-
-	kvm_guest_exit();
+	guest_exit_irqoff();
 
+	local_irq_enable();
 	preempt_enable();
 
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
@@ -7408,6 +7444,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	vcpu->arch.hflags = 0;
 
+	vcpu->arch.smi_pending = 0;
 	atomic_set(&vcpu->arch.nmi_queued, 0);
 	vcpu->arch.nmi_pending = 0;
 	vcpu->arch.nmi_injected = false;
@@ -7600,11 +7637,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 	return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0;
 }
 
-bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
-{
-	return irqchip_in_kernel(vcpu->kvm) == lapic_in_kernel(vcpu);
-}
-
 struct static_key kvm_no_apic_vcpu __read_mostly;
 EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu);
 
@@ -7871,7 +7903,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(kvm->arch.vpic);
 	kfree(kvm->arch.vioapic);
 	kvm_free_vcpus(kvm);
-	kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
+	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kvm_mmu_uninit_vm(kvm);
 }
 
@@ -8379,7 +8411,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	/*
 	 * When producer of consumer is unregistered, we change back to
 	 * remapped mode, so we can re-use the current implementation
-	 * when the irq is masked/disabed or the consumer side (KVM
+	 * when the irq is masked/disabled or the consumer side (KVM
 	 * int this case doesn't want to receive the interrupts.
 	*/
 	ret = kvm_x86_ops->update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0);
diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c
index a3c668875038..216a629a4a1a 100644
--- a/arch/x86/lib/cache-smp.c
+++ b/arch/x86/lib/cache-smp.c
@@ -1,5 +1,5 @@
 #include <linux/smp.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 static void __wbinvd(void *dummy)
 {
diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c
index aa417a97511c..d6f848d1211d 100644
--- a/arch/x86/lib/cpu.c
+++ b/arch/x86/lib/cpu.c
@@ -1,4 +1,5 @@
-#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/export.h>
 
 unsigned int x86_family(unsigned int sig)
 {
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index 9845371c5c36..9a7fe6a70491 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -6,7 +6,7 @@
  */
  
 #include <linux/compiler.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/checksum.h>
 
 static inline unsigned short from32to16(unsigned a) 
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index b6fcb9a9ddbc..8bd53589ecfb 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -5,7 +5,7 @@
  * Wrappers of assembly checksum functions for x86-64.
  */
 #include <asm/checksum.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/uaccess.h>
 #include <asm/smap.h>
 
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 2f07c291dcc8..073d1f1a620b 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -11,7 +11,7 @@
  *	we have to worry about.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/timex.h>
 #include <linux/preempt.h>
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index a404b4b75533..cad12634d6bd 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -1,5 +1,5 @@
 #include <linux/string.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #undef memcpy
 #undef memset
diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c
index e5e3ed8dc079..c2311a678332 100644
--- a/arch/x86/lib/mmx_32.c
+++ b/arch/x86/lib/mmx_32.c
@@ -18,7 +18,7 @@
  */
 #include <linux/hardirq.h>
 #include <linux/string.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/types.h>
 
diff --git a/arch/x86/lib/msr-reg-export.c b/arch/x86/lib/msr-reg-export.c
index 8d6ef78b5d01..ff29e8d39414 100644
--- a/arch/x86/lib/msr-reg-export.c
+++ b/arch/x86/lib/msr-reg-export.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/msr.h>
 
 EXPORT_SYMBOL(rdmsr_safe_regs);
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
index 518532e6a3fa..ce68b6a9d7d1 100644
--- a/arch/x86/lib/msr-smp.c
+++ b/arch/x86/lib/msr-smp.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/preempt.h>
 #include <linux/smp.h>
 #include <asm/msr.h>
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 004c861b1648..d1dee753b949 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -1,4 +1,5 @@
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/percpu.h>
 #include <linux/preempt.h>
 #include <asm/msr.h>
 #define CREATE_TRACE_POINTS
diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
index bd59090825db..dc0ad12f80bb 100644
--- a/arch/x86/lib/string_32.c
+++ b/arch/x86/lib/string_32.c
@@ -11,7 +11,7 @@
  */
 
 #include <linux/string.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #ifdef __HAVE_ARCH_STRCPY
 char *strcpy(char *dest, const char *src)
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index e342586db6e4..b4908789484e 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -5,7 +5,7 @@
  */
 
 #include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/word-at-a-time.h>
 #include <linux/sched.h>
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index b559d9238781..3bc7baf2a711 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -8,7 +8,7 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/blkdev.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/backing-dev.h>
 #include <linux/interrupt.h>
 #include <asm/uaccess.h>
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 9f760cdcaf40..69873589c0ba 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -5,7 +5,7 @@
  * Copyright 1997 Linus Torvalds
  * Copyright 2002 Andi Kleen <ak@suse.de>
  */
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/uaccess.h>
 
 /*
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index 2ca15b59fb3f..ba47524f56e8 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -9,7 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/module.h>
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/bootmem.h>
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 9a17250bcbe0..ea9c49adaa1f 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -14,7 +14,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/seq_file.h>
 
 #include <asm/pgtable.h>
@@ -454,8 +454,4 @@ static int __init pt_dump_init(void)
 
 	return 0;
 }
-
 __initcall(pt_dump_init);
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
-MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables");
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index a6d739258137..6d18b70ed5a9 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -1,5 +1,5 @@
 #include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/swap.h> /* for totalram_pages */
 #include <linux/bootmem.h>
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index cc82830bc8c4..620928903be3 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -208,7 +208,7 @@ static int __meminit save_mr(struct map_range *mr, int nr_range,
  * adjust the page_size_mask for small range to go with
  *	big page size instead small one if nearby are ram too.
  */
-static void __init_refok adjust_range_page_size_mask(struct map_range *mr,
+static void __ref adjust_range_page_size_mask(struct map_range *mr,
 							 int nr_range)
 {
 	int i;
@@ -396,7 +396,7 @@ bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn)
  * This runs before bootmem is initialized and gets pages directly from
  * the physical memory. To access them they are temporarily mapped.
  */
-unsigned long __init_refok init_memory_mapping(unsigned long start,
+unsigned long __ref init_memory_mapping(unsigned long start,
 					       unsigned long end)
 {
 	struct map_range mr[NR_RANGE_MR];
@@ -700,13 +700,6 @@ void free_initmem(void)
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
 	/*
-	 * Remember, initrd memory may contain microcode or other useful things.
-	 * Before we lose initrd mem, we need to find a place to hold them
-	 * now that normal virtual memory is enabled.
-	 */
-	save_microcode_in_initrd();
-
-	/*
 	 * end could be not aligned, and We can not align that,
 	 * decompresser could be confused by aligned initrd_end
 	 * We already reserve the end partial page before in
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 84df150ee77e..cf8059016ec8 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -5,7 +5,6 @@
  *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
  */
 
-#include <linux/module.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 53cc2256cf23..14b9dd71d9e8 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -27,7 +27,6 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/dma-mapping.h>
-#include <linux/module.h>
 #include <linux/memory.h>
 #include <linux/memory_hotplug.h>
 #include <linux/memremap.h>
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 9c0ff045fdd4..ada98b39b8ad 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -18,7 +18,7 @@
 
 #include <asm/iomap.h>
 #include <asm/pat.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/highmem.h>
 
 static int is_io_mapping_possible(resource_size_t base, unsigned long size)
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index f0894910bdd7..7aaa2635862d 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -9,7 +9,6 @@
 #include <linux/bootmem.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/mmiotrace.h>
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index b4f2e7e9e907..4515bae36bbe 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -14,7 +14,6 @@
 #include <linux/kernel.h>
 #include <linux/kmemcheck.h>
 #include <linux/mm.h>
-#include <linux/module.h>
 #include <linux/page-flags.h>
 #include <linux/percpu.h>
 #include <linux/ptrace.h>
diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c
index aec124214d97..c2638a7d2c10 100644
--- a/arch/x86/mm/kmemcheck/shadow.c
+++ b/arch/x86/mm/kmemcheck/shadow.c
@@ -1,5 +1,5 @@
 #include <linux/kmemcheck.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 
 #include <asm/page.h>
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index ddb2244b06a1..afc47f5c9531 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -11,7 +11,7 @@
 #include <linux/rculist.h>
 #include <linux/spinlock.h>
 #include <linux/hash.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 0057a7accfb1..bef36622e408 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -24,7 +24,7 @@
 
 #define DEBUG 1
 
-#include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/debugfs.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 968ac028c34e..fb682108f4dc 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -8,7 +8,6 @@
 #include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/ctype.h>
-#include <linux/module.h>
 #include <linux/nodemask.h>
 #include <linux/sched.h>
 #include <linux/topology.h>
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 47b6436e41c2..6b7ce6279133 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,7 +24,7 @@
 
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
-#include <linux/module.h>
+#include <linux/init.h>
 
 #include "numa_internal.h"
 
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index db00e3e2f3dc..ecb1b69c1651 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -11,7 +11,6 @@
 #include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 2f7702253ccf..de391b7bc19a 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -11,7 +11,6 @@
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/rbtree_augmented.h>
 #include <linux/sched.h>
 #include <linux/gfp.h>
diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c
index 9f0614daea85..a235869532bc 100644
--- a/arch/x86/mm/pf_in.c
+++ b/arch/x86/mm/pf_in.c
@@ -26,7 +26,6 @@
  *  Bjorn Steinbrink (B.Steinbrink@gmx.de), 2007
  */
 
-#include <linux/module.h>
 #include <linux/ptrace.h> /* struct pt_regs */
 #include "pf_in.h"
 
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index e67ae0e6c59d..9adce776852b 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -8,7 +8,6 @@
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c
index e666cbbb9261..cfc3b9121ce4 100644
--- a/arch/x86/mm/physaddr.c
+++ b/arch/x86/mm/physaddr.c
@@ -1,6 +1,6 @@
 #include <linux/bootmem.h>
 #include <linux/mmdebug.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 
 #include <asm/page.h>
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index b1ecff460a46..35fe69529bc1 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -13,7 +13,7 @@
 #include <linux/acpi.h>
 #include <linux/mmzone.h>
 #include <linux/bitmap.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/topology.h>
 #include <linux/mm.h>
 #include <asm/proto.h>
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5643fd0b1a7d..4dbe65622810 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -4,7 +4,7 @@
 #include <linux/spinlock.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/cpu.h>
 
 #include <asm/tlbflush.h>
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 8196054fedb0..7b6a9d14c8c0 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -133,7 +133,7 @@ static void pcibios_fixup_device_resources(struct pci_dev *dev)
 	if (pci_probe & PCI_NOASSIGN_BARS) {
 		/*
 		* If the BIOS did not assign the BAR, zero out the
-		* resource so the kernel doesn't attmept to assign
+		* resource so the kernel doesn't attempt to assign
 		* it later on in pci_assign_unassigned_resources
 		*/
 		for (bar = 0; bar <= PCI_STD_RESOURCE_END; bar++) {
diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c
index 613cac7395c4..e88b4176260f 100644
--- a/arch/x86/pci/vmd.c
+++ b/arch/x86/pci/vmd.c
@@ -119,10 +119,11 @@ static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 static void vmd_irq_enable(struct irq_data *data)
 {
 	struct vmd_irq *vmdirq = data->chip_data;
+	unsigned long flags;
 
-	raw_spin_lock(&list_lock);
+	raw_spin_lock_irqsave(&list_lock, flags);
 	list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list);
-	raw_spin_unlock(&list_lock);
+	raw_spin_unlock_irqrestore(&list_lock, flags);
 
 	data->chip->irq_unmask(data);
 }
@@ -130,12 +131,14 @@ static void vmd_irq_enable(struct irq_data *data)
 static void vmd_irq_disable(struct irq_data *data)
 {
 	struct vmd_irq *vmdirq = data->chip_data;
+	unsigned long flags;
 
 	data->chip->irq_mask(data);
 
-	raw_spin_lock(&list_lock);
+	raw_spin_lock_irqsave(&list_lock, flags);
 	list_del_rcu(&vmdirq->node);
-	raw_spin_unlock(&list_lock);
+	INIT_LIST_HEAD_RCU(&vmdirq->node);
+	raw_spin_unlock_irqrestore(&list_lock, flags);
 }
 
 /*
@@ -166,16 +169,20 @@ static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info,
  * XXX: We can be even smarter selecting the best IRQ once we solve the
  * affinity problem.
  */
-static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd)
+static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *desc)
 {
-	int i, best = 0;
+	int i, best = 1;
+	unsigned long flags;
 
-	raw_spin_lock(&list_lock);
+	if (!desc->msi_attrib.is_msix || vmd->msix_count == 1)
+		return &vmd->irqs[0];
+
+	raw_spin_lock_irqsave(&list_lock, flags);
 	for (i = 1; i < vmd->msix_count; i++)
 		if (vmd->irqs[i].count < vmd->irqs[best].count)
 			best = i;
 	vmd->irqs[best].count++;
-	raw_spin_unlock(&list_lock);
+	raw_spin_unlock_irqrestore(&list_lock, flags);
 
 	return &vmd->irqs[best];
 }
@@ -184,14 +191,15 @@ static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info,
 			unsigned int virq, irq_hw_number_t hwirq,
 			msi_alloc_info_t *arg)
 {
-	struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(arg->desc)->bus);
+	struct msi_desc *desc = arg->desc;
+	struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(desc)->bus);
 	struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL);
 
 	if (!vmdirq)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&vmdirq->node);
-	vmdirq->irq = vmd_next_irq(vmd);
+	vmdirq->irq = vmd_next_irq(vmd, desc);
 	vmdirq->virq = virq;
 
 	irq_domain_set_info(domain, virq, vmdirq->irq->vmd_vector, info->chip,
@@ -203,11 +211,12 @@ static void vmd_msi_free(struct irq_domain *domain,
 			struct msi_domain_info *info, unsigned int virq)
 {
 	struct vmd_irq *vmdirq = irq_get_chip_data(virq);
+	unsigned long flags;
 
 	/* XXX: Potential optimization to rebalance */
-	raw_spin_lock(&list_lock);
+	raw_spin_lock_irqsave(&list_lock, flags);
 	vmdirq->irq->count--;
-	raw_spin_unlock(&list_lock);
+	raw_spin_unlock_irqrestore(&list_lock, flags);
 
 	kfree_rcu(vmdirq, rcu);
 }
@@ -261,7 +270,7 @@ static struct device *to_vmd_dev(struct device *dev)
 
 static struct dma_map_ops *vmd_dma_ops(struct device *dev)
 {
-	return to_vmd_dev(dev)->archdata.dma_ops;
+	return get_dma_ops(to_vmd_dev(dev));
 }
 
 static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
@@ -367,7 +376,7 @@ static void vmd_teardown_dma_ops(struct vmd_dev *vmd)
 {
 	struct dma_domain *domain = &vmd->dma_domain;
 
-	if (vmd->dev->dev.archdata.dma_ops)
+	if (get_dma_ops(&vmd->dev->dev))
 		del_dma_domain(domain);
 }
 
@@ -379,7 +388,7 @@ static void vmd_teardown_dma_ops(struct vmd_dev *vmd)
 
 static void vmd_setup_dma_ops(struct vmd_dev *vmd)
 {
-	const struct dma_map_ops *source = vmd->dev->dev.archdata.dma_ops;
+	const struct dma_map_ops *source = get_dma_ops(&vmd->dev->dev);
 	struct dma_map_ops *dest = &vmd->dma_ops;
 	struct dma_domain *domain = &vmd->dma_domain;
 
@@ -594,7 +603,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd)
 	sd->node = pcibus_to_node(vmd->dev->bus);
 
 	vmd->irq_domain = pci_msi_create_irq_domain(NULL, &vmd_msi_domain_info,
-						    NULL);
+						    x86_vector_domain);
 	if (!vmd->irq_domain)
 		return -ENODEV;
 
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 99ddab79215e..3a483cb5ac81 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -9,7 +9,7 @@
  *           Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
  *           Stefano Stabellini <stefano.stabellini@eu.citrix.com>
  */
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/acpi.h>
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index 701fd5843c87..b27bccd4390f 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -11,11 +11,9 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/irq.h>
-#include <linux/module.h>
 #include <linux/reboot.h>
 #include <linux/serial_reg.h>
 #include <linux/serial_8250.h>
-#include <linux/reboot.h>
 
 #include <asm/ce4100.h>
 #include <asm/prom.h>
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 524142117296..5fdacb322ceb 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -44,7 +44,7 @@ early_initcall(early_efi_map_fb);
  * In case earlyprintk=efi,keep we have the whole framebuffer mapped already
  * so just return the offset efi_fb + start.
  */
-static __init_refok void *early_efi_map(unsigned long start, unsigned long len)
+static __ref void *early_efi_map(unsigned long start, unsigned long len)
 {
 	unsigned long base;
 
@@ -56,7 +56,7 @@ static __init_refok void *early_efi_map(unsigned long start, unsigned long len)
 		return early_ioremap(base + start, len);
 }
 
-static __init_refok void early_efi_unmap(void *addr, unsigned long len)
+static __ref void early_efi_unmap(void *addr, unsigned long len)
 {
 	if (!efi_fb)
 		early_iounmap(addr, len);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 3e12c44f88a2..04db6fbce96d 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -24,7 +24,7 @@
 #include <linux/spinlock.h>
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/efi.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index abbf49c6e9d3..ce119d2ba0d0 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -20,7 +20,7 @@
 #include <linux/scatterlist.h>
 #include <linux/sfi.h>
 #include <linux/irq.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/notifier.h>
 
 #include <asm/setup.h>
diff --git a/arch/x86/platform/intel-mid/pwr.c b/arch/x86/platform/intel-mid/pwr.c
index 5bc90dd102d4..c901a3423772 100644
--- a/arch/x86/platform/intel-mid/pwr.c
+++ b/arch/x86/platform/intel-mid/pwr.c
@@ -21,10 +21,9 @@
 
 #include <linux/delay.h>
 #include <linux/errno.h>
-#include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
 
@@ -407,7 +406,6 @@ static const struct pci_device_id mid_pwr_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_TANGIER), (kernel_ulong_t)&mid_info },
 	{}
 };
-MODULE_DEVICE_TABLE(pci, mid_pwr_pci_ids);
 
 static struct pci_driver mid_pwr_pci_driver = {
 	.name		= "intel_mid_pwr",
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 1555672d436f..051d264fce2e 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -24,7 +24,7 @@
 #include <linux/input.h>
 #include <linux/platform_device.h>
 #include <linux/irq.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/notifier.h>
 #include <linux/mmc/core.h>
 #include <linux/mmc/card.h>
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index 27376081ddec..7c3077e58fa0 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -12,7 +12,7 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/string.h>
diff --git a/arch/x86/platform/olpc/olpc_ofw.c b/arch/x86/platform/olpc/olpc_ofw.c
index e7604f62870d..f1aab8cdb33f 100644
--- a/arch/x86/platform/olpc/olpc_ofw.c
+++ b/arch/x86/platform/olpc/olpc_ofw.c
@@ -1,9 +1,12 @@
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/spinlock_types.h>
 #include <linux/init.h>
 #include <asm/page.h>
 #include <asm/setup.h>
 #include <asm/io.h>
+#include <asm/cpufeature.h>
+#include <asm/special_insns.h>
 #include <asm/pgtable.h>
 #include <asm/olpc_ofw.h>
 
diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c
index baf16e72e668..fd39301f25ac 100644
--- a/arch/x86/platform/ts5500/ts5500.c
+++ b/arch/x86/platform/ts5500/ts5500.c
@@ -23,7 +23,7 @@
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/leds.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/platform_data/gpio-ts5500.h>
 #include <linux/platform_data/max197.h>
 #include <linux/platform_device.h>
@@ -345,7 +345,3 @@ error:
 	return err;
 }
 device_initcall(ts5500_init);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Savoir-faire Linux Inc. <kernel@savoirfairelinux.com>");
-MODULE_DESCRIPTION("Technologic Systems TS-5500 platform driver");
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index e1c24631afbb..776c6592136c 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -8,7 +8,7 @@
  * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/irq.h>
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index 8dd80050d705..cd5173a2733f 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -24,7 +24,7 @@
 #include <linux/kdb.h>
 #include <linux/kexec.h>
 #include <linux/kgdb.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/nmi.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 12734a96df47..ac58c1616408 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -8,6 +8,8 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
 targets += purgatory.ro
 
+KCOV_INSTRUMENT := n
+
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
 # in turn leaves some undefined symbols like __fentry__ in purgatory and not
 # sure how to relocate those. Like kexec-tools, use custom flags.
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index c556c5ae8de5..25012abc3409 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -48,7 +48,7 @@ targets += realmode.lds
 $(obj)/realmode.lds: $(obj)/pasyms.h
 
 LDFLAGS_realmode.elf := --emit-relocs -T
-CPPFLAGS_realmode.lds += -P -C -I$(obj)
+CPPFLAGS_realmode.lds += -P -C -I$(objtree)/$(obj)
 
 targets += realmode.elf
 $(obj)/realmode.elf: $(obj)/realmode.lds $(REALMODE_OBJS) FORCE
diff --git a/arch/x86/um/delay.c b/arch/x86/um/delay.c
index f3fe1a688f7e..a8fb7ca4822b 100644
--- a/arch/x86/um/delay.c
+++ b/arch/x86/um/delay.c
@@ -7,7 +7,7 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <asm/param.h>
diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c
index c8377fb26cdf..1daff5545c0a 100644
--- a/arch/x86/xen/debugfs.c
+++ b/arch/x86/xen/debugfs.c
@@ -1,7 +1,6 @@
 #include <linux/init.h>
 #include <linux/debugfs.h>
 #include <linux/slab.h>
-#include <linux/module.h>
 
 #include "debugfs.h"
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 69b4b6d29738..8ffb089b19a5 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -23,7 +23,7 @@
 #include <linux/sched.h>
 #include <linux/kprobes.h>
 #include <linux/bootmem.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/page-flags.h>
 #include <linux/highmem.h>
@@ -34,9 +34,7 @@
 #include <linux/edd.h>
 #include <linux/frame.h>
 
-#ifdef CONFIG_KEXEC_CORE
 #include <linux/kexec.h>
-#endif
 
 #include <xen/xen.h>
 #include <xen/events.h>
@@ -1334,7 +1332,8 @@ static void xen_crash_shutdown(struct pt_regs *regs)
 static int
 xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
-	xen_reboot(SHUTDOWN_crash);
+	if (!kexec_crash_loaded())
+		xen_reboot(SHUTDOWN_crash);
 	return NOTIFY_DONE;
 }
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 67433714b791..7d5afdb417cc 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -43,7 +43,8 @@
 #include <linux/debugfs.h>
 #include <linux/bug.h>
 #include <linux/vmalloc.h>
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/init.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
 #include <linux/seq_file.h>
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index dd2a49a8aacc..37129db76d33 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -60,7 +60,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <linux/sched.h>
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 9586ff32810c..d37a0c7f82cb 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -21,7 +21,7 @@
 
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <xen/platform_pci.h>
 #include "xen-ops.h"
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index e345891450c3..176425233e4d 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -4,7 +4,7 @@
  * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/pm.h>
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 9735691f37f1..143251ede897 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -24,8 +24,8 @@
 #include <linux/percpu.h>
 #include <linux/clk-provider.h>
 #include <linux/cpu.h>
+#include <linux/of.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 
 #if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE)
 # include <linux/console.h>
@@ -255,7 +255,6 @@ void __init early_init_devtree(void *params)
 static int __init xtensa_device_probe(void)
 {
 	of_clk_init(NULL);
-	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	return 0;
 }
 
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index aebd944bdaa1..445ce28475b3 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -221,6 +221,9 @@ config ACPI_PROCESSOR_IDLE
 	bool
 	select CPU_IDLE
 
+config ACPI_MCFG
+	bool
+
 config ACPI_CPPC_LIB
 	bool
 	depends on ACPI_PROCESSOR
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 35a6ccbe3025..5ae9d85c5159 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -40,6 +40,7 @@ acpi-$(CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC) += processor_pdc.o
 acpi-y				+= ec.o
 acpi-$(CONFIG_ACPI_DOCK)	+= dock.o
 acpi-y				+= pci_root.o pci_link.o pci_irq.o
+obj-$(CONFIG_ACPI_MCFG)		+= pci_mcfg.o
 acpi-y				+= acpi_lpss.o acpi_apd.o
 acpi-y				+= acpi_platform.o
 acpi-y				+= acpi_pnp.o
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index b108f1358a32..4305ee9db4b2 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -309,7 +309,7 @@ static void acpi_unmap(acpi_physical_address pg_off, void __iomem *vaddr)
  * During early init (when acpi_gbl_permanent_mmap has not been set yet) this
  * routine simply calls __acpi_map_table() to get the job done.
  */
-void __iomem *__init_refok
+void __iomem *__ref
 acpi_os_map_iomem(acpi_physical_address phys, acpi_size size)
 {
 	struct acpi_ioremap *map;
@@ -362,8 +362,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(acpi_os_map_iomem);
 
-void *__init_refok
-acpi_os_map_memory(acpi_physical_address phys, acpi_size size)
+void *__ref acpi_os_map_memory(acpi_physical_address phys, acpi_size size)
 {
 	return (void *)acpi_os_map_iomem(phys, size);
 }
diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c
new file mode 100644
index 000000000000..b5b376e081f5
--- /dev/null
+++ b/drivers/acpi/pci_mcfg.c
@@ -0,0 +1,92 @@
+/*
+ * Copyright (C) 2016 Broadcom
+ *	Author: Jayachandran C <jchandra@broadcom.com>
+ * Copyright (C) 2016 Semihalf
+ * 	Author: Tomasz Nowicki <tn@semihalf.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation (the "GPL").
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License version 2 (GPLv2) for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 (GPLv2) along with this source code.
+ */
+
+#define pr_fmt(fmt) "ACPI: " fmt
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+
+/* Structure to hold entries from the MCFG table */
+struct mcfg_entry {
+	struct list_head	list;
+	phys_addr_t		addr;
+	u16			segment;
+	u8			bus_start;
+	u8			bus_end;
+};
+
+/* List to save MCFG entries */
+static LIST_HEAD(pci_mcfg_list);
+
+phys_addr_t pci_mcfg_lookup(u16 seg, struct resource *bus_res)
+{
+	struct mcfg_entry *e;
+
+	/*
+	 * We expect exact match, unless MCFG entry end bus covers more than
+	 * specified by caller.
+	 */
+	list_for_each_entry(e, &pci_mcfg_list, list) {
+		if (e->segment == seg && e->bus_start == bus_res->start &&
+		    e->bus_end >= bus_res->end)
+			return e->addr;
+	}
+
+	return 0;
+}
+
+static __init int pci_mcfg_parse(struct acpi_table_header *header)
+{
+	struct acpi_table_mcfg *mcfg;
+	struct acpi_mcfg_allocation *mptr;
+	struct mcfg_entry *e, *arr;
+	int i, n;
+
+	if (header->length < sizeof(struct acpi_table_mcfg))
+		return -EINVAL;
+
+	n = (header->length - sizeof(struct acpi_table_mcfg)) /
+					sizeof(struct acpi_mcfg_allocation);
+	mcfg = (struct acpi_table_mcfg *)header;
+	mptr = (struct acpi_mcfg_allocation *) &mcfg[1];
+
+	arr = kcalloc(n, sizeof(*arr), GFP_KERNEL);
+	if (!arr)
+		return -ENOMEM;
+
+	for (i = 0, e = arr; i < n; i++, mptr++, e++) {
+		e->segment = mptr->pci_segment;
+		e->addr =  mptr->address;
+		e->bus_start = mptr->start_bus_number;
+		e->bus_end = mptr->end_bus_number;
+		list_add(&e->list, &pci_mcfg_list);
+	}
+
+	pr_info("MCFG table detected, %d entries\n", n);
+	return 0;
+}
+
+/* Interface called by ACPI - parse and save MCFG table */
+void __init pci_mmcfg_late_init(void)
+{
+	int err = acpi_table_parse(ACPI_SIG_MCFG, pci_mcfg_parse);
+	if (err)
+		pr_err("Failed to parse MCFG (%d)\n", err);
+}
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index ae3fe4e64203..d144168d4ef9 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -720,6 +720,36 @@ next:
 	}
 }
 
+static void acpi_pci_root_remap_iospace(struct resource_entry *entry)
+{
+#ifdef PCI_IOBASE
+	struct resource *res = entry->res;
+	resource_size_t cpu_addr = res->start;
+	resource_size_t pci_addr = cpu_addr - entry->offset;
+	resource_size_t length = resource_size(res);
+	unsigned long port;
+
+	if (pci_register_io_range(cpu_addr, length))
+		goto err;
+
+	port = pci_address_to_pio(cpu_addr);
+	if (port == (unsigned long)-1)
+		goto err;
+
+	res->start = port;
+	res->end = port + length - 1;
+	entry->offset = port - pci_addr;
+
+	if (pci_remap_iospace(res, cpu_addr) < 0)
+		goto err;
+
+	pr_info("Remapped I/O %pa to %pR\n", &cpu_addr, res);
+	return;
+err:
+	res->flags |= IORESOURCE_DISABLED;
+#endif
+}
+
 int acpi_pci_probe_root_resources(struct acpi_pci_root_info *info)
 {
 	int ret;
@@ -740,6 +770,9 @@ int acpi_pci_probe_root_resources(struct acpi_pci_root_info *info)
 			"no IO and memory resources present in _CRS\n");
 	else {
 		resource_list_for_each_entry_safe(entry, tmp, list) {
+			if (entry->res->flags & IORESOURCE_IO)
+				acpi_pci_root_remap_iospace(entry);
+
 			if (entry->res->flags & IORESOURCE_DISABLED)
 				resource_list_destroy_entry(entry);
 			else
@@ -811,6 +844,8 @@ static void acpi_pci_root_release_info(struct pci_host_bridge *bridge)
 
 	resource_list_for_each_entry(entry, &bridge->windows) {
 		res = entry->res;
+		if (res->flags & IORESOURCE_IO)
+			pci_unmap_iospace(res);
 		if (res->parent &&
 		    (res->flags & (IORESOURCE_MEM | IORESOURCE_IO)))
 			release_resource(res);
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 773fc3099769..22d1760a4278 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -46,7 +46,8 @@ MODULE_LICENSE("GPL");
 extern struct builtin_fw __start_builtin_fw[];
 extern struct builtin_fw __end_builtin_fw[];
 
-static bool fw_get_builtin_firmware(struct firmware *fw, const char *name)
+static bool fw_get_builtin_firmware(struct firmware *fw, const char *name,
+				    void *buf, size_t size)
 {
 	struct builtin_fw *b_fw;
 
@@ -54,6 +55,9 @@ static bool fw_get_builtin_firmware(struct firmware *fw, const char *name)
 		if (strcmp(name, b_fw->name) == 0) {
 			fw->size = b_fw->size;
 			fw->data = b_fw->data;
+
+			if (buf && fw->size <= size)
+				memcpy(buf, fw->data, fw->size);
 			return true;
 		}
 	}
@@ -74,7 +78,9 @@ static bool fw_is_builtin_firmware(const struct firmware *fw)
 
 #else /* Module case - no builtin firmware support */
 
-static inline bool fw_get_builtin_firmware(struct firmware *fw, const char *name)
+static inline bool fw_get_builtin_firmware(struct firmware *fw,
+					   const char *name, void *buf,
+					   size_t size)
 {
 	return false;
 }
@@ -112,6 +118,7 @@ static inline long firmware_loading_timeout(void)
 #define FW_OPT_FALLBACK		0
 #endif
 #define FW_OPT_NO_WARN	(1U << 3)
+#define FW_OPT_NOCACHE	(1U << 4)
 
 struct firmware_cache {
 	/* firmware_buf instance will be added into the below list */
@@ -143,6 +150,7 @@ struct firmware_buf {
 	unsigned long status;
 	void *data;
 	size_t size;
+	size_t allocated_size;
 #ifdef CONFIG_FW_LOADER_USER_HELPER
 	bool is_paged_buf;
 	bool need_uevent;
@@ -178,7 +186,8 @@ static DEFINE_MUTEX(fw_lock);
 static struct firmware_cache fw_cache;
 
 static struct firmware_buf *__allocate_fw_buf(const char *fw_name,
-					      struct firmware_cache *fwc)
+					      struct firmware_cache *fwc,
+					      void *dbuf, size_t size)
 {
 	struct firmware_buf *buf;
 
@@ -194,6 +203,8 @@ static struct firmware_buf *__allocate_fw_buf(const char *fw_name,
 
 	kref_init(&buf->ref);
 	buf->fwc = fwc;
+	buf->data = dbuf;
+	buf->allocated_size = size;
 	init_completion(&buf->completion);
 #ifdef CONFIG_FW_LOADER_USER_HELPER
 	INIT_LIST_HEAD(&buf->pending_list);
@@ -217,7 +228,8 @@ static struct firmware_buf *__fw_lookup_buf(const char *fw_name)
 
 static int fw_lookup_and_allocate_buf(const char *fw_name,
 				      struct firmware_cache *fwc,
-				      struct firmware_buf **buf)
+				      struct firmware_buf **buf, void *dbuf,
+				      size_t size)
 {
 	struct firmware_buf *tmp;
 
@@ -229,7 +241,7 @@ static int fw_lookup_and_allocate_buf(const char *fw_name,
 		*buf = tmp;
 		return 1;
 	}
-	tmp = __allocate_fw_buf(fw_name, fwc);
+	tmp = __allocate_fw_buf(fw_name, fwc, dbuf, size);
 	if (tmp)
 		list_add(&tmp->list, &fwc->head);
 	spin_unlock(&fwc->lock);
@@ -261,6 +273,7 @@ static void __fw_free_buf(struct kref *ref)
 		vfree(buf->pages);
 	} else
 #endif
+	if (!buf->allocated_size)
 		vfree(buf->data);
 	kfree_const(buf->fw_id);
 	kfree(buf);
@@ -301,13 +314,21 @@ static void fw_finish_direct_load(struct device *device,
 	mutex_unlock(&fw_lock);
 }
 
-static int fw_get_filesystem_firmware(struct device *device,
-				       struct firmware_buf *buf)
+static int
+fw_get_filesystem_firmware(struct device *device, struct firmware_buf *buf)
 {
 	loff_t size;
 	int i, len;
 	int rc = -ENOENT;
 	char *path;
+	enum kernel_read_file_id id = READING_FIRMWARE;
+	size_t msize = INT_MAX;
+
+	/* Already populated data member means we're loading into a buffer */
+	if (buf->data) {
+		id = READING_FIRMWARE_PREALLOC_BUFFER;
+		msize = buf->allocated_size;
+	}
 
 	path = __getname();
 	if (!path)
@@ -326,8 +347,8 @@ static int fw_get_filesystem_firmware(struct device *device,
 		}
 
 		buf->size = 0;
-		rc = kernel_read_file_from_path(path, &buf->data, &size,
-						INT_MAX, READING_FIRMWARE);
+		rc = kernel_read_file_from_path(path, &buf->data, &size, msize,
+						id);
 		if (rc) {
 			if (rc == -ENOENT)
 				dev_dbg(device, "loading %s failed with error %d\n",
@@ -691,6 +712,38 @@ out:
 
 static DEVICE_ATTR(loading, 0644, firmware_loading_show, firmware_loading_store);
 
+static void firmware_rw_buf(struct firmware_buf *buf, char *buffer,
+			   loff_t offset, size_t count, bool read)
+{
+	if (read)
+		memcpy(buffer, buf->data + offset, count);
+	else
+		memcpy(buf->data + offset, buffer, count);
+}
+
+static void firmware_rw(struct firmware_buf *buf, char *buffer,
+			loff_t offset, size_t count, bool read)
+{
+	while (count) {
+		void *page_data;
+		int page_nr = offset >> PAGE_SHIFT;
+		int page_ofs = offset & (PAGE_SIZE-1);
+		int page_cnt = min_t(size_t, PAGE_SIZE - page_ofs, count);
+
+		page_data = kmap(buf->pages[page_nr]);
+
+		if (read)
+			memcpy(buffer, page_data + page_ofs, page_cnt);
+		else
+			memcpy(page_data + page_ofs, buffer, page_cnt);
+
+		kunmap(buf->pages[page_nr]);
+		buffer += page_cnt;
+		offset += page_cnt;
+		count -= page_cnt;
+	}
+}
+
 static ssize_t firmware_data_read(struct file *filp, struct kobject *kobj,
 				  struct bin_attribute *bin_attr,
 				  char *buffer, loff_t offset, size_t count)
@@ -715,21 +768,11 @@ static ssize_t firmware_data_read(struct file *filp, struct kobject *kobj,
 
 	ret_count = count;
 
-	while (count) {
-		void *page_data;
-		int page_nr = offset >> PAGE_SHIFT;
-		int page_ofs = offset & (PAGE_SIZE-1);
-		int page_cnt = min_t(size_t, PAGE_SIZE - page_ofs, count);
-
-		page_data = kmap(buf->pages[page_nr]);
-
-		memcpy(buffer, page_data + page_ofs, page_cnt);
+	if (buf->data)
+		firmware_rw_buf(buf, buffer, offset, count, true);
+	else
+		firmware_rw(buf, buffer, offset, count, true);
 
-		kunmap(buf->pages[page_nr]);
-		buffer += page_cnt;
-		offset += page_cnt;
-		count -= page_cnt;
-	}
 out:
 	mutex_unlock(&fw_lock);
 	return ret_count;
@@ -804,29 +847,23 @@ static ssize_t firmware_data_write(struct file *filp, struct kobject *kobj,
 		goto out;
 	}
 
-	retval = fw_realloc_buffer(fw_priv, offset + count);
-	if (retval)
-		goto out;
-
-	retval = count;
-
-	while (count) {
-		void *page_data;
-		int page_nr = offset >> PAGE_SHIFT;
-		int page_ofs = offset & (PAGE_SIZE - 1);
-		int page_cnt = min_t(size_t, PAGE_SIZE - page_ofs, count);
-
-		page_data = kmap(buf->pages[page_nr]);
-
-		memcpy(page_data + page_ofs, buffer, page_cnt);
+	if (buf->data) {
+		if (offset + count > buf->allocated_size) {
+			retval = -ENOMEM;
+			goto out;
+		}
+		firmware_rw_buf(buf, buffer, offset, count, false);
+		retval = count;
+	} else {
+		retval = fw_realloc_buffer(fw_priv, offset + count);
+		if (retval)
+			goto out;
 
-		kunmap(buf->pages[page_nr]);
-		buffer += page_cnt;
-		offset += page_cnt;
-		count -= page_cnt;
+		retval = count;
+		firmware_rw(buf, buffer, offset, count, false);
 	}
 
-	buf->size = max_t(size_t, offset, buf->size);
+	buf->size = max_t(size_t, offset + count, buf->size);
 out:
 	mutex_unlock(&fw_lock);
 	return retval;
@@ -894,7 +931,8 @@ static int _request_firmware_load(struct firmware_priv *fw_priv,
 	struct firmware_buf *buf = fw_priv->buf;
 
 	/* fall back on userspace loading */
-	buf->is_paged_buf = true;
+	if (!buf->data)
+		buf->is_paged_buf = true;
 
 	dev_set_uevent_suppress(f_dev, true);
 
@@ -929,7 +967,7 @@ static int _request_firmware_load(struct firmware_priv *fw_priv,
 
 	if (is_fw_load_aborted(buf))
 		retval = -EAGAIN;
-	else if (!buf->data)
+	else if (buf->is_paged_buf && !buf->data)
 		retval = -ENOMEM;
 
 	device_del(f_dev);
@@ -1012,7 +1050,7 @@ static int sync_cached_firmware_buf(struct firmware_buf *buf)
  */
 static int
 _request_firmware_prepare(struct firmware **firmware_p, const char *name,
-			  struct device *device)
+			  struct device *device, void *dbuf, size_t size)
 {
 	struct firmware *firmware;
 	struct firmware_buf *buf;
@@ -1025,12 +1063,12 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name,
 		return -ENOMEM;
 	}
 
-	if (fw_get_builtin_firmware(firmware, name)) {
+	if (fw_get_builtin_firmware(firmware, name, dbuf, size)) {
 		dev_dbg(device, "using built-in %s\n", name);
 		return 0; /* assigned */
 	}
 
-	ret = fw_lookup_and_allocate_buf(name, &fw_cache, &buf);
+	ret = fw_lookup_and_allocate_buf(name, &fw_cache, &buf, dbuf, size);
 
 	/*
 	 * bind with 'buf' now to avoid warning in failure path
@@ -1070,14 +1108,16 @@ static int assign_firmware_buf(struct firmware *fw, struct device *device,
 	 * should be fixed in devres or driver core.
 	 */
 	/* don't cache firmware handled without uevent */
-	if (device && (opt_flags & FW_OPT_UEVENT))
+	if (device && (opt_flags & FW_OPT_UEVENT) &&
+	    !(opt_flags & FW_OPT_NOCACHE))
 		fw_add_devm_name(device, buf->fw_id);
 
 	/*
 	 * After caching firmware image is started, let it piggyback
 	 * on request firmware.
 	 */
-	if (buf->fwc->state == FW_LOADER_START_CACHE) {
+	if (!(opt_flags & FW_OPT_NOCACHE) &&
+	    buf->fwc->state == FW_LOADER_START_CACHE) {
 		if (fw_cache_piggyback_on_request(buf->fw_id))
 			kref_get(&buf->ref);
 	}
@@ -1091,7 +1131,8 @@ static int assign_firmware_buf(struct firmware *fw, struct device *device,
 /* called from request_firmware() and request_firmware_work_func() */
 static int
 _request_firmware(const struct firmware **firmware_p, const char *name,
-		  struct device *device, unsigned int opt_flags)
+		  struct device *device, void *buf, size_t size,
+		  unsigned int opt_flags)
 {
 	struct firmware *fw = NULL;
 	long timeout;
@@ -1105,7 +1146,7 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 		goto out;
 	}
 
-	ret = _request_firmware_prepare(&fw, name, device);
+	ret = _request_firmware_prepare(&fw, name, device, buf, size);
 	if (ret <= 0) /* error or already assigned */
 		goto out;
 
@@ -1184,7 +1225,7 @@ request_firmware(const struct firmware **firmware_p, const char *name,
 
 	/* Need to pin this module until return */
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware_p, name, device,
+	ret = _request_firmware(firmware_p, name, device, NULL, 0,
 				FW_OPT_UEVENT | FW_OPT_FALLBACK);
 	module_put(THIS_MODULE);
 	return ret;
@@ -1208,7 +1249,7 @@ int request_firmware_direct(const struct firmware **firmware_p,
 	int ret;
 
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware_p, name, device,
+	ret = _request_firmware(firmware_p, name, device, NULL, 0,
 				FW_OPT_UEVENT | FW_OPT_NO_WARN);
 	module_put(THIS_MODULE);
 	return ret;
@@ -1216,6 +1257,36 @@ int request_firmware_direct(const struct firmware **firmware_p,
 EXPORT_SYMBOL_GPL(request_firmware_direct);
 
 /**
+ * request_firmware_into_buf - load firmware into a previously allocated buffer
+ * @firmware_p: pointer to firmware image
+ * @name: name of firmware file
+ * @device: device for which firmware is being loaded and DMA region allocated
+ * @buf: address of buffer to load firmware into
+ * @size: size of buffer
+ *
+ * This function works pretty much like request_firmware(), but it doesn't
+ * allocate a buffer to hold the firmware data. Instead, the firmware
+ * is loaded directly into the buffer pointed to by @buf and the @firmware_p
+ * data member is pointed at @buf.
+ *
+ * This function doesn't cache firmware either.
+ */
+int
+request_firmware_into_buf(const struct firmware **firmware_p, const char *name,
+			  struct device *device, void *buf, size_t size)
+{
+	int ret;
+
+	__module_get(THIS_MODULE);
+	ret = _request_firmware(firmware_p, name, device, buf, size,
+				FW_OPT_UEVENT | FW_OPT_FALLBACK |
+				FW_OPT_NOCACHE);
+	module_put(THIS_MODULE);
+	return ret;
+}
+EXPORT_SYMBOL(request_firmware_into_buf);
+
+/**
  * release_firmware: - release the resource associated with a firmware image
  * @fw: firmware resource to release
  **/
@@ -1247,7 +1318,7 @@ static void request_firmware_work_func(struct work_struct *work)
 
 	fw_work = container_of(work, struct firmware_work, work);
 
-	_request_firmware(&fw, fw_work->name, fw_work->device,
+	_request_firmware(&fw, fw_work->name, fw_work->device, NULL, 0,
 			  fw_work->opt_flags);
 	fw_work->cont(fw, fw_work->context);
 	put_device(fw_work->device); /* taken in request_firmware_nowait() */
@@ -1380,7 +1451,7 @@ static int uncache_firmware(const char *fw_name)
 
 	pr_debug("%s: %s\n", __func__, fw_name);
 
-	if (fw_get_builtin_firmware(&fw, fw_name))
+	if (fw_get_builtin_firmware(&fw, fw_name, NULL, 0))
 		return 0;
 
 	buf = fw_lookup_buf(fw_name);
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 29cd96661b30..5548f9686016 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -370,7 +370,7 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 #define page_initialized(page)  (page->lru.next)
 
-static int __init_refok get_nid_for_pfn(unsigned long pfn)
+static int __ref get_nid_for_pfn(unsigned long pfn)
 {
 	struct page *page;
 
diff --git a/drivers/base/property.c b/drivers/base/property.c
index f38c21de29b7..43a36d68c3fd 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -888,6 +888,34 @@ struct fwnode_handle *device_get_next_child_node(struct device *dev,
 EXPORT_SYMBOL_GPL(device_get_next_child_node);
 
 /**
+ * device_get_named_child_node - Return first matching named child node handle
+ * @dev: Device to find the named child node for.
+ * @childname: String to match child node name against.
+ */
+struct fwnode_handle *device_get_named_child_node(struct device *dev,
+						  const char *childname)
+{
+	struct fwnode_handle *child;
+
+	/*
+	 * Find first matching named child node of this device.
+	 * For ACPI this will be a data only sub-node.
+	 */
+	device_for_each_child_node(dev, child) {
+		if (is_of_node(child)) {
+			if (!of_node_cmp(to_of_node(child)->name, childname))
+				return child;
+		} else if (is_acpi_data_node(child)) {
+			if (acpi_data_node_match(child, childname))
+				return child;
+		}
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(device_get_named_child_node);
+
+/**
  * fwnode_handle_put - Drop reference to a device node
  * @fwnode: Pointer to the device node to drop the reference to.
  *
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 0a1aaf8c24c4..2d3d50ab74bf 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -27,7 +27,6 @@
 #include <linux/crc32c.h>
 #include <linux/drbd.h>
 #include <linux/drbd_limits.h>
-#include <linux/dynamic_debug.h>
 #include "drbd_int.h"
 
 
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 7b54354976a5..4cb8f21ff4ef 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -41,6 +41,7 @@
 #include <linux/backing-dev.h>
 #include <linux/genhd.h>
 #include <linux/idr.h>
+#include <linux/dynamic_debug.h>
 #include <net/tcp.h>
 #include <linux/lru_cache.h>
 #include <linux/prefetch.h>
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 450662055d97..1a04af6d2421 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1937,7 +1937,7 @@ static struct ceph_osd_request *rbd_osd_req_create(
 	osd_req->r_callback = rbd_osd_req_callback;
 	osd_req->r_priv = obj_request;
 
-	osd_req->r_base_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);
+	osd_req->r_base_oloc.pool = rbd_dev->layout.pool_id;
 	if (ceph_oid_aprintf(&osd_req->r_base_oid, GFP_NOIO, "%s",
 			     obj_request->object_name))
 		goto fail;
@@ -1991,7 +1991,7 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request)
 	osd_req->r_callback = rbd_osd_req_callback;
 	osd_req->r_priv = obj_request;
 
-	osd_req->r_base_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);
+	osd_req->r_base_oloc.pool = rbd_dev->layout.pool_id;
 	if (ceph_oid_aprintf(&osd_req->r_base_oid, GFP_NOIO, "%s",
 			     obj_request->object_name))
 		goto fail;
@@ -3995,10 +3995,11 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
 
 	/* Initialize the layout used for all rbd requests */
 
-	rbd_dev->layout.fl_stripe_unit = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
-	rbd_dev->layout.fl_stripe_count = cpu_to_le32(1);
-	rbd_dev->layout.fl_object_size = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
-	rbd_dev->layout.fl_pg_pool = cpu_to_le32((u32) spec->pool_id);
+	rbd_dev->layout.stripe_unit = 1 << RBD_MAX_OBJ_ORDER;
+	rbd_dev->layout.stripe_count = 1;
+	rbd_dev->layout.object_size = 1 << RBD_MAX_OBJ_ORDER;
+	rbd_dev->layout.pool_id = spec->pool_id;
+	RCU_INIT_POINTER(rbd_dev->layout.pool_ns, NULL);
 
 	/*
 	 * If this is a mapping rbd_dev (as opposed to a parent one),
@@ -5187,7 +5188,7 @@ static int rbd_dev_header_name(struct rbd_device *rbd_dev)
 
 	rbd_assert(rbd_image_format_valid(rbd_dev->image_format));
 
-	rbd_dev->header_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);
+	rbd_dev->header_oloc.pool = rbd_dev->layout.pool_id;
 	if (rbd_dev->image_format == 1)
 		ret = ceph_oid_aprintf(&rbd_dev->header_oid, GFP_KERNEL, "%s%s",
 				       spec->image_name, RBD_SUFFIX);
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index c5a7de9bc783..3b205e212337 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -132,6 +132,19 @@ config SUNXI_RSB
 	  with various RSB based devices, such as AXP223, AXP8XX PMICs,
 	  and AC100/AC200 ICs.
 
+# TODO: This uses pm_clk_*() symbols that aren't exported in v4.7 and hence
+# the driver will fail to build as a module. However there are patches to
+# address that queued for v4.8, so this can be turned into a tristate symbol
+# after v4.8-rc1.
+config TEGRA_ACONNECT
+	bool "Tegra ACONNECT Bus Driver"
+	depends on ARCH_TEGRA_210_SOC
+	depends on OF && PM
+	select PM_CLK
+	help
+	  Driver for the Tegra ACONNECT bus which is used to interface with
+	  the devices inside the Audio Processing Engine (APE) for Tegra210.
+
 config UNIPHIER_SYSTEM_BUS
 	tristate "UniPhier System Bus driver"
 	depends on ARCH_UNIPHIER && OF
diff --git a/drivers/bus/Makefile b/drivers/bus/Makefile
index ccff007ee7e8..ac84cc4348e3 100644
--- a/drivers/bus/Makefile
+++ b/drivers/bus/Makefile
@@ -17,5 +17,6 @@ obj-$(CONFIG_OMAP_INTERCONNECT)	+= omap_l3_smx.o omap_l3_noc.o
 obj-$(CONFIG_OMAP_OCP2SCP)	+= omap-ocp2scp.o
 obj-$(CONFIG_SUNXI_RSB)		+= sunxi-rsb.o
 obj-$(CONFIG_SIMPLE_PM_BUS)	+= simple-pm-bus.o
+obj-$(CONFIG_TEGRA_ACONNECT)	+= tegra-aconnect.o
 obj-$(CONFIG_UNIPHIER_SYSTEM_BUS)	+= uniphier-system-bus.o
 obj-$(CONFIG_VEXPRESS_CONFIG)	+= vexpress-config.o
diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c
index 1827fc4d15c1..4bd361d64270 100644
--- a/drivers/bus/imx-weim.c
+++ b/drivers/bus/imx-weim.c
@@ -163,9 +163,8 @@ static int __init weim_parse_dt(struct platform_device *pdev,
 	}
 
 	if (have_child)
-		ret = of_platform_populate(pdev->dev.of_node,
-				   of_default_bus_match_table,
-				   NULL, &pdev->dev);
+		ret = of_platform_default_populate(pdev->dev.of_node,
+						   NULL, &pdev->dev);
 	if (ret)
 		dev_err(&pdev->dev, "%s fail to create devices.\n",
 			pdev->dev.of_node->full_name);
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index ce54a0160faa..c7f396903184 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -117,7 +117,7 @@ struct mvebu_mbus_soc_data {
 	unsigned int (*win_remap_offset)(const int win);
 	void (*setup_cpu_target)(struct mvebu_mbus_state *s);
 	int (*save_cpu_target)(struct mvebu_mbus_state *s,
-			       u32 *store_addr);
+			       u32 __iomem *store_addr);
 	int (*show_cpu_target)(struct mvebu_mbus_state *s,
 			       struct seq_file *seq, void *v);
 };
@@ -728,7 +728,7 @@ mvebu_mbus_default_setup_cpu_target(struct mvebu_mbus_state *mbus)
 
 static int
 mvebu_mbus_default_save_cpu_target(struct mvebu_mbus_state *mbus,
-				   u32 *store_addr)
+				   u32 __iomem *store_addr)
 {
 	int i;
 
@@ -780,7 +780,7 @@ mvebu_mbus_dove_setup_cpu_target(struct mvebu_mbus_state *mbus)
 
 static int
 mvebu_mbus_dove_save_cpu_target(struct mvebu_mbus_state *mbus,
-				u32 *store_addr)
+				u32 __iomem *store_addr)
 {
 	int i;
 
@@ -796,7 +796,7 @@ mvebu_mbus_dove_save_cpu_target(struct mvebu_mbus_state *mbus,
 	return 4;
 }
 
-int mvebu_mbus_save_cpu_target(u32 *store_addr)
+int mvebu_mbus_save_cpu_target(u32 __iomem *store_addr)
 {
 	return mbus_state.soc->save_cpu_target(&mbus_state, store_addr);
 }
@@ -1089,7 +1089,7 @@ static void mvebu_mbus_resume(void)
 	}
 }
 
-struct syscore_ops mvebu_mbus_syscore_ops = {
+static struct syscore_ops mvebu_mbus_syscore_ops = {
 	.suspend	= mvebu_mbus_suspend,
 	.resume		= mvebu_mbus_resume,
 };
diff --git a/drivers/bus/tegra-aconnect.c b/drivers/bus/tegra-aconnect.c
new file mode 100644
index 000000000000..7e4104b74fa8
--- /dev/null
+++ b/drivers/bus/tegra-aconnect.c
@@ -0,0 +1,112 @@
+/*
+ * Tegra ACONNECT Bus Driver
+ *
+ * Copyright (C) 2016, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_clock.h>
+#include <linux/pm_runtime.h>
+
+static int tegra_aconnect_add_clock(struct device *dev, char *name)
+{
+	struct clk *clk;
+	int ret;
+
+	clk = clk_get(dev, name);
+	if (IS_ERR(clk)) {
+		dev_err(dev, "%s clock not found\n", name);
+		return PTR_ERR(clk);
+	}
+
+	ret = pm_clk_add_clk(dev, clk);
+	if (ret)
+		clk_put(clk);
+
+	return ret;
+}
+
+static int tegra_aconnect_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	if (!pdev->dev.of_node)
+		return -EINVAL;
+
+	ret = pm_clk_create(&pdev->dev);
+	if (ret)
+		return ret;
+
+	ret = tegra_aconnect_add_clock(&pdev->dev, "ape");
+	if (ret)
+		goto clk_destroy;
+
+	ret = tegra_aconnect_add_clock(&pdev->dev, "apb2ape");
+	if (ret)
+		goto clk_destroy;
+
+	pm_runtime_enable(&pdev->dev);
+
+	of_platform_populate(pdev->dev.of_node, NULL, NULL, &pdev->dev);
+
+	dev_info(&pdev->dev, "Tegra ACONNECT bus registered\n");
+
+	return 0;
+
+clk_destroy:
+	pm_clk_destroy(&pdev->dev);
+
+	return ret;
+}
+
+static int tegra_aconnect_remove(struct platform_device *pdev)
+{
+	pm_runtime_disable(&pdev->dev);
+
+	pm_clk_destroy(&pdev->dev);
+
+	return 0;
+}
+
+static int tegra_aconnect_runtime_resume(struct device *dev)
+{
+	return pm_clk_resume(dev);
+}
+
+static int tegra_aconnect_runtime_suspend(struct device *dev)
+{
+	return pm_clk_suspend(dev);
+}
+
+static const struct dev_pm_ops tegra_aconnect_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_aconnect_runtime_suspend,
+			   tegra_aconnect_runtime_resume, NULL)
+};
+
+static const struct of_device_id tegra_aconnect_of_match[] = {
+	{ .compatible = "nvidia,tegra210-aconnect", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, tegra_aconnect_of_match);
+
+static struct platform_driver tegra_aconnect_driver = {
+	.probe = tegra_aconnect_probe,
+	.remove = tegra_aconnect_remove,
+	.driver = {
+		.name = "tegra-aconnect",
+		.of_match_table = tegra_aconnect_of_match,
+		.pm = &tegra_aconnect_pm_ops,
+	},
+};
+module_platform_driver(tegra_aconnect_driver);
+
+MODULE_DESCRIPTION("NVIDIA Tegra ACONNECT Bus Driver");
+MODULE_AUTHOR("Jon Hunter <jonathanh@nvidia.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/bus/uniphier-system-bus.c b/drivers/bus/uniphier-system-bus.c
index 350b7309c26d..1e6e0269edcc 100644
--- a/drivers/bus/uniphier-system-bus.c
+++ b/drivers/bus/uniphier-system-bus.c
@@ -257,8 +257,7 @@ static int uniphier_system_bus_probe(struct platform_device *pdev)
 	uniphier_system_bus_set_reg(priv);
 
 	/* Now, the bus is configured.  Populate platform_devices below it */
-	return of_platform_populate(dev->of_node, of_default_bus_match_table,
-				    NULL, dev);
+	return of_platform_default_populate(dev->of_node, NULL, dev);
 }
 
 static const struct of_device_id uniphier_system_bus_match[] = {
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 601f64fcc890..fdb8f3e10b6f 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -178,6 +178,20 @@ config IBM_BSR
 	  of threads across a large system which avoids bouncing a cacheline
 	  between several cores on a system
 
+config POWERNV_OP_PANEL
+	tristate "IBM POWERNV Operator Panel Display support"
+	depends on PPC_POWERNV
+	default m
+	help
+	  If you say Y here, a special character device node, /dev/op_panel,
+	  will be created which exposes the operator panel display on IBM
+	  Power Systems machines with FSPs.
+
+	  If you don't require access to the operator panel display from user
+	  space, say N.
+
+	  If unsure, say M here to build it as a module called powernv-op-panel.
+
 source "drivers/char/ipmi/Kconfig"
 
 config DS1620
diff --git a/drivers/char/Makefile b/drivers/char/Makefile
index d8a7579300d2..55d16bf3ccc5 100644
--- a/drivers/char/Makefile
+++ b/drivers/char/Makefile
@@ -60,3 +60,4 @@ js-rtc-y = rtc.o
 
 obj-$(CONFIG_TILE_SROM)		+= tile-srom.o
 obj-$(CONFIG_XILLYBUS)		+= xillybus/
+obj-$(CONFIG_POWERNV_OP_PANEL)	+= powernv-op-panel.o
diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index aef87fdbd187..44311296ec02 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -840,6 +840,14 @@ static bool i830_check_flags(unsigned int flags)
 	return false;
 }
 
+void intel_gtt_insert_page(dma_addr_t addr,
+			   unsigned int pg,
+			   unsigned int flags)
+{
+	intel_private.driver->write_entry(addr, pg, flags);
+}
+EXPORT_SYMBOL(intel_gtt_insert_page);
+
 void intel_gtt_insert_sg_entries(struct sg_table *st,
 				 unsigned int pg_start,
 				 unsigned int flags)
diff --git a/drivers/char/powernv-op-panel.c b/drivers/char/powernv-op-panel.c
new file mode 100644
index 000000000000..a45dabcc8e10
--- /dev/null
+++ b/drivers/char/powernv-op-panel.c
@@ -0,0 +1,223 @@
+/*
+ * OPAL Operator Panel Display Driver
+ *
+ * Copyright 2016, Suraj Jitindar Singh, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/miscdevice.h>
+
+#include <asm/opal.h>
+
+/*
+ * This driver creates a character device (/dev/op_panel) which exposes the
+ * operator panel (character LCD display) on IBM Power Systems machines
+ * with FSPs.
+ * A character buffer written to the device will be displayed on the
+ * operator panel.
+ */
+
+static DEFINE_MUTEX(oppanel_mutex);
+
+static u32		num_lines, oppanel_size;
+static oppanel_line_t	*oppanel_lines;
+static char		*oppanel_data;
+
+static loff_t oppanel_llseek(struct file *filp, loff_t offset, int whence)
+{
+	return fixed_size_llseek(filp, offset, whence, oppanel_size);
+}
+
+static ssize_t oppanel_read(struct file *filp, char __user *userbuf, size_t len,
+			    loff_t *f_pos)
+{
+	return simple_read_from_buffer(userbuf, len, f_pos, oppanel_data,
+			oppanel_size);
+}
+
+static int __op_panel_update_display(void)
+{
+	struct opal_msg msg;
+	int rc, token;
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		if (token != -ERESTARTSYS)
+			pr_debug("Couldn't get OPAL async token [token=%d]\n",
+				token);
+		return token;
+	}
+
+	rc = opal_write_oppanel_async(token, oppanel_lines, num_lines);
+	switch (rc) {
+	case OPAL_ASYNC_COMPLETION:
+		rc = opal_async_wait_response(token, &msg);
+		if (rc) {
+			pr_debug("Failed to wait for async response [rc=%d]\n",
+				rc);
+			break;
+		}
+		rc = opal_get_async_rc(msg);
+		if (rc != OPAL_SUCCESS) {
+			pr_debug("OPAL async call returned failed [rc=%d]\n",
+				rc);
+			break;
+		}
+	case OPAL_SUCCESS:
+		break;
+	default:
+		pr_debug("OPAL write op-panel call failed [rc=%d]\n", rc);
+	}
+
+	opal_async_release_token(token);
+	return rc;
+}
+
+static ssize_t oppanel_write(struct file *filp, const char __user *userbuf,
+			     size_t len, loff_t *f_pos)
+{
+	loff_t f_pos_prev = *f_pos;
+	ssize_t ret;
+	int rc;
+
+	if (!*f_pos)
+		memset(oppanel_data, ' ', oppanel_size);
+	else if (*f_pos >= oppanel_size)
+		return -EFBIG;
+
+	ret = simple_write_to_buffer(oppanel_data, oppanel_size, f_pos, userbuf,
+			len);
+	if (ret > 0) {
+		rc = __op_panel_update_display();
+		if (rc != OPAL_SUCCESS) {
+			pr_err_ratelimited("OPAL call failed to write to op panel display [rc=%d]\n",
+				rc);
+			*f_pos = f_pos_prev;
+			return -EIO;
+		}
+	}
+	return ret;
+}
+
+static int oppanel_open(struct inode *inode, struct file *filp)
+{
+	if (!mutex_trylock(&oppanel_mutex)) {
+		pr_debug("Device Busy\n");
+		return -EBUSY;
+	}
+	return 0;
+}
+
+static int oppanel_release(struct inode *inode, struct file *filp)
+{
+	mutex_unlock(&oppanel_mutex);
+	return 0;
+}
+
+static const struct file_operations oppanel_fops = {
+	.owner		= THIS_MODULE,
+	.llseek		= oppanel_llseek,
+	.read		= oppanel_read,
+	.write		= oppanel_write,
+	.open		= oppanel_open,
+	.release	= oppanel_release
+};
+
+static struct miscdevice oppanel_dev = {
+	.minor		= MISC_DYNAMIC_MINOR,
+	.name		= "op_panel",
+	.fops		= &oppanel_fops
+};
+
+static int oppanel_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	u32 line_len;
+	int rc, i;
+
+	rc = of_property_read_u32(np, "#length", &line_len);
+	if (rc) {
+		pr_err_ratelimited("Operator panel length property not found\n");
+		return rc;
+	}
+	rc = of_property_read_u32(np, "#lines", &num_lines);
+	if (rc) {
+		pr_err_ratelimited("Operator panel lines property not found\n");
+		return rc;
+	}
+	oppanel_size = line_len * num_lines;
+
+	pr_devel("Operator panel of size %u found with %u lines of length %u\n",
+			oppanel_size, num_lines, line_len);
+
+	oppanel_data = kcalloc(oppanel_size, sizeof(*oppanel_data), GFP_KERNEL);
+	if (!oppanel_data)
+		return -ENOMEM;
+
+	oppanel_lines = kcalloc(num_lines, sizeof(oppanel_line_t), GFP_KERNEL);
+	if (!oppanel_lines) {
+		rc = -ENOMEM;
+		goto free_oppanel_data;
+	}
+
+	memset(oppanel_data, ' ', oppanel_size);
+	for (i = 0; i < num_lines; i++) {
+		oppanel_lines[i].line_len = cpu_to_be64(line_len);
+		oppanel_lines[i].line = cpu_to_be64(__pa(&oppanel_data[i *
+						line_len]));
+	}
+
+	rc = misc_register(&oppanel_dev);
+	if (rc) {
+		pr_err_ratelimited("Failed to register as misc device\n");
+		goto free_oppanel;
+	}
+
+	return 0;
+
+free_oppanel:
+	kfree(oppanel_lines);
+free_oppanel_data:
+	kfree(oppanel_data);
+	return rc;
+}
+
+static int oppanel_remove(struct platform_device *pdev)
+{
+	misc_deregister(&oppanel_dev);
+	kfree(oppanel_lines);
+	kfree(oppanel_data);
+	return 0;
+}
+
+static const struct of_device_id oppanel_match[] = {
+	{ .compatible = "ibm,opal-oppanel" },
+	{ },
+};
+
+static struct platform_driver oppanel_driver = {
+	.driver	= {
+		.name		= "powernv-op-panel",
+		.of_match_table	= oppanel_match,
+	},
+	.probe	= oppanel_probe,
+	.remove	= oppanel_remove,
+};
+
+module_platform_driver(oppanel_driver);
+
+MODULE_DEVICE_TABLE(of, oppanel_match);
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("PowerNV Operator Panel LCD Display Driver");
+MODULE_AUTHOR("Suraj Jitindar Singh <sjitindarsingh@gmail.com>");
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 7f0622426b97..3efb3bf0ab83 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -249,6 +249,7 @@
 #include <linux/genhd.h>
 #include <linux/interrupt.h>
 #include <linux/mm.h>
+#include <linux/nodemask.h>
 #include <linux/spinlock.h>
 #include <linux/kthread.h>
 #include <linux/percpu.h>
@@ -1656,7 +1657,6 @@ static int rand_initialize(void)
 {
 #ifdef CONFIG_NUMA
 	int i;
-	int num_nodes = num_possible_nodes();
 	struct crng_state *crng;
 	struct crng_state **pool;
 #endif
@@ -1666,8 +1666,7 @@ static int rand_initialize(void)
 	crng_initialize(&primary_crng);
 
 #ifdef CONFIG_NUMA
-	pool = kmalloc(num_nodes * sizeof(void *),
-		       GFP_KERNEL|__GFP_NOFAIL|__GFP_ZERO);
+	pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
 	for_each_online_node(i) {
 		crng = kmalloc_node(sizeof(struct crng_state),
 				    GFP_KERNEL | __GFP_NOFAIL, i);
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 98efbfcdb503..e2d9bd760c84 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -49,10 +49,10 @@ config COMMON_CLK_MAX77802
 	  This driver supports Maxim 77802 crystal oscillator clock.
 
 config COMMON_CLK_RK808
-	tristate "Clock driver for RK808"
+	tristate "Clock driver for RK808/RK818"
 	depends on MFD_RK808
 	---help---
-	  This driver supports RK808 crystal oscillator clock. These
+	  This driver supports RK808 and RK818 crystal oscillator clock. These
 	  multi-function devices have two fixed-rate oscillators,
 	  clocked at 32KHz each. Clkout1 is always on, Clkout2 can off
 	  by control register.
@@ -203,16 +203,19 @@ config COMMON_CLK_PIC32
 
 config COMMON_CLK_OXNAS
 	bool "Clock driver for the OXNAS SoC Family"
+	depends on ARCH_OXNAS || COMPILE_TEST
 	select MFD_SYSCON
 	---help---
 	  Support for the OXNAS SoC Family clocks.
 
 source "drivers/clk/bcm/Kconfig"
 source "drivers/clk/hisilicon/Kconfig"
+source "drivers/clk/meson/Kconfig"
 source "drivers/clk/mvebu/Kconfig"
 source "drivers/clk/qcom/Kconfig"
 source "drivers/clk/renesas/Kconfig"
 source "drivers/clk/samsung/Kconfig"
+source "drivers/clk/sunxi-ng/Kconfig"
 source "drivers/clk/tegra/Kconfig"
 source "drivers/clk/ti/Kconfig"
 
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index dcc5e698ff6d..3b6f9cf3464a 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -16,13 +16,14 @@ obj-$(CONFIG_COMMON_CLK)	+= clk-conf.o
 endif
 
 # hardware specific clock types
-# please keep this section sorted lexicographically by file/directory path name
+# please keep this section sorted lexicographically by file path name
 obj-$(CONFIG_MACH_ASM9260)		+= clk-asm9260.o
 obj-$(CONFIG_COMMON_CLK_AXI_CLKGEN)	+= clk-axi-clkgen.o
 obj-$(CONFIG_ARCH_AXXIA)		+= clk-axm5516.o
 obj-$(CONFIG_COMMON_CLK_CDCE706)	+= clk-cdce706.o
-obj-$(CONFIG_COMMON_CLK_CS2000_CP)	+= clk-cs2000-cp.o
+obj-$(CONFIG_COMMON_CLK_CDCE925)	+= clk-cdce925.o
 obj-$(CONFIG_ARCH_CLPS711X)		+= clk-clps711x.o
+obj-$(CONFIG_COMMON_CLK_CS2000_CP)	+= clk-cs2000-cp.o
 obj-$(CONFIG_ARCH_EFM32)		+= clk-efm32gg.o
 obj-$(CONFIG_ARCH_HIGHBANK)		+= clk-highbank.o
 obj-$(CONFIG_MACH_LOONGSON32)		+= clk-ls1x.o
@@ -35,6 +36,7 @@ obj-$(CONFIG_ARCH_NOMADIK)		+= clk-nomadik.o
 obj-$(CONFIG_ARCH_NSPIRE)		+= clk-nspire.o
 obj-$(CONFIG_COMMON_CLK_OXNAS)		+= clk-oxnas.o
 obj-$(CONFIG_COMMON_CLK_PALMAS)		+= clk-palmas.o
+obj-$(CONFIG_COMMON_CLK_PWM)		+= clk-pwm.o
 obj-$(CONFIG_CLK_QORIQ)			+= clk-qoriq.o
 obj-$(CONFIG_COMMON_CLK_RK808)		+= clk-rk808.o
 obj-$(CONFIG_COMMON_CLK_S2MPS11)	+= clk-s2mps11.o
@@ -42,7 +44,6 @@ obj-$(CONFIG_COMMON_CLK_SCPI)           += clk-scpi.o
 obj-$(CONFIG_COMMON_CLK_SI5351)		+= clk-si5351.o
 obj-$(CONFIG_COMMON_CLK_SI514)		+= clk-si514.o
 obj-$(CONFIG_COMMON_CLK_SI570)		+= clk-si570.o
-obj-$(CONFIG_COMMON_CLK_CDCE925)	+= clk-cdce925.o
 obj-$(CONFIG_ARCH_STM32)		+= clk-stm32f4.o
 obj-$(CONFIG_ARCH_TANGO)		+= clk-tango4.o
 obj-$(CONFIG_CLK_TWL6040)		+= clk-twl6040.o
@@ -50,35 +51,39 @@ obj-$(CONFIG_ARCH_U300)			+= clk-u300.o
 obj-$(CONFIG_ARCH_VT8500)		+= clk-vt8500.o
 obj-$(CONFIG_COMMON_CLK_WM831X)		+= clk-wm831x.o
 obj-$(CONFIG_COMMON_CLK_XGENE)		+= clk-xgene.o
-obj-$(CONFIG_COMMON_CLK_PWM)		+= clk-pwm.o
+
+# please keep this section sorted lexicographically by directory path name
 obj-$(CONFIG_COMMON_CLK_AT91)		+= at91/
 obj-$(CONFIG_ARCH_ARTPEC)		+= axis/
+obj-$(CONFIG_ARC_PLAT_AXS10X)		+= axs10x/
 obj-y					+= bcm/
 obj-$(CONFIG_ARCH_BERLIN)		+= berlin/
+obj-$(CONFIG_H8300)			+= h8300/
 obj-$(CONFIG_ARCH_HISI)			+= hisilicon/
 obj-$(CONFIG_ARCH_MXC)			+= imx/
 obj-$(CONFIG_MACH_INGENIC)		+= ingenic/
 obj-$(CONFIG_COMMON_CLK_KEYSTONE)	+= keystone/
 obj-$(CONFIG_ARCH_MEDIATEK)		+= mediatek/
+obj-$(CONFIG_COMMON_CLK_AMLOGIC)	+= meson/
 obj-$(CONFIG_MACH_PIC32)		+= microchip/
 ifeq ($(CONFIG_COMMON_CLK), y)
 obj-$(CONFIG_ARCH_MMP)			+= mmp/
 endif
 obj-y					+= mvebu/
-obj-$(CONFIG_ARCH_MESON)		+= meson/
 obj-$(CONFIG_ARCH_MXS)			+= mxs/
-obj-$(CONFIG_MACH_PISTACHIO)		+= pistachio/
 obj-$(CONFIG_COMMON_CLK_NXP)		+= nxp/
+obj-$(CONFIG_MACH_PISTACHIO)		+= pistachio/
 obj-$(CONFIG_COMMON_CLK_PXA)		+= pxa/
 obj-$(CONFIG_COMMON_CLK_QCOM)		+= qcom/
+obj-$(CONFIG_ARCH_RENESAS)		+= renesas/
 obj-$(CONFIG_ARCH_ROCKCHIP)		+= rockchip/
 obj-$(CONFIG_COMMON_CLK_SAMSUNG)	+= samsung/
-obj-$(CONFIG_ARCH_RENESAS)		+= renesas/
 obj-$(CONFIG_ARCH_SIRF)			+= sirf/
 obj-$(CONFIG_ARCH_SOCFPGA)		+= socfpga/
 obj-$(CONFIG_PLAT_SPEAR)		+= spear/
 obj-$(CONFIG_ARCH_STI)			+= st/
 obj-$(CONFIG_ARCH_SUNXI)		+= sunxi/
+obj-$(CONFIG_ARCH_SUNXI)		+= sunxi-ng/
 obj-$(CONFIG_ARCH_TEGRA)		+= tegra/
 obj-y					+= ti/
 obj-$(CONFIG_ARCH_U8500)		+= ux500/
@@ -86,5 +91,3 @@ obj-$(CONFIG_COMMON_CLK_VERSATILE)	+= versatile/
 obj-$(CONFIG_X86)			+= x86/
 obj-$(CONFIG_ARCH_ZX)			+= zte/
 obj-$(CONFIG_ARCH_ZYNQ)			+= zynq/
-obj-$(CONFIG_H8300)		+= h8300/
-obj-$(CONFIG_ARC_PLAT_AXS10X)		+= axs10x/
diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c
index e1aa210dd7aa..7f6bec8837ea 100644
--- a/drivers/clk/at91/clk-generated.c
+++ b/drivers/clk/at91/clk-generated.c
@@ -267,7 +267,7 @@ at91_clk_register_generated(struct regmap *regmap,  spinlock_t *lock, const char
 	return clk;
 }
 
-void __init of_sama5d2_clk_generated_setup(struct device_node *np)
+static void __init of_sama5d2_clk_generated_setup(struct device_node *np)
 {
 	int num;
 	u32 id;
diff --git a/drivers/clk/bcm/clk-iproc-armpll.c b/drivers/clk/bcm/clk-iproc-armpll.c
index a196ee28a17a..d7d628214b85 100644
--- a/drivers/clk/bcm/clk-iproc-armpll.c
+++ b/drivers/clk/bcm/clk-iproc-armpll.c
@@ -20,6 +20,8 @@
 #include <linux/clkdev.h>
 #include <linux/of_address.h>
 
+#include "clk-iproc.h"
+
 #define IPROC_CLK_MAX_FREQ_POLICY                    0x3
 #define IPROC_CLK_POLICY_FREQ_OFFSET                 0x008
 #define IPROC_CLK_POLICY_FREQ_POLICY_FREQ_SHIFT      8
@@ -242,7 +244,6 @@ static const struct clk_ops iproc_arm_pll_ops = {
 void __init iproc_armpll_setup(struct device_node *node)
 {
 	int ret;
-	struct clk *clk;
 	struct iproc_arm_pll *pll;
 	struct clk_init_data init;
 	const char *parent_name;
@@ -263,18 +264,18 @@ void __init iproc_armpll_setup(struct device_node *node)
 	init.num_parents = (parent_name ? 1 : 0);
 	pll->hw.init = &init;
 
-	clk = clk_register(NULL, &pll->hw);
-	if (WARN_ON(IS_ERR(clk)))
+	ret = clk_hw_register(NULL, &pll->hw);
+	if (WARN_ON(ret))
 		goto err_iounmap;
 
-	ret = of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	ret = of_clk_add_hw_provider(node, of_clk_hw_simple_get, &pll->hw);
 	if (WARN_ON(ret))
 		goto err_clk_unregister;
 
 	return;
 
 err_clk_unregister:
-	clk_unregister(clk);
+	clk_hw_unregister(&pll->hw);
 err_iounmap:
 	iounmap(pll->base);
 err_free_pll:
diff --git a/drivers/clk/bcm/clk-iproc-asiu.c b/drivers/clk/bcm/clk-iproc-asiu.c
index f630e1bbdcfe..4360e481368b 100644
--- a/drivers/clk/bcm/clk-iproc-asiu.c
+++ b/drivers/clk/bcm/clk-iproc-asiu.c
@@ -37,7 +37,7 @@ struct iproc_asiu {
 	void __iomem *div_base;
 	void __iomem *gate_base;
 
-	struct clk_onecell_data clk_data;
+	struct clk_hw_onecell_data *clk_data;
 	struct iproc_asiu_clk *clks;
 };
 
@@ -197,11 +197,11 @@ void __init iproc_asiu_setup(struct device_node *node,
 	if (WARN_ON(!asiu))
 		return;
 
-	asiu->clk_data.clk_num = num_clks;
-	asiu->clk_data.clks = kcalloc(num_clks, sizeof(*asiu->clk_data.clks),
-				      GFP_KERNEL);
-	if (WARN_ON(!asiu->clk_data.clks))
+	asiu->clk_data = kzalloc(sizeof(*asiu->clk_data->hws) * num_clks +
+				 sizeof(*asiu->clk_data), GFP_KERNEL);
+	if (WARN_ON(!asiu->clk_data))
 		goto err_clks;
+	asiu->clk_data->num = num_clks;
 
 	asiu->clks = kcalloc(num_clks, sizeof(*asiu->clks), GFP_KERNEL);
 	if (WARN_ON(!asiu->clks))
@@ -217,7 +217,6 @@ void __init iproc_asiu_setup(struct device_node *node,
 
 	for (i = 0; i < num_clks; i++) {
 		struct clk_init_data init;
-		struct clk *clk;
 		const char *parent_name;
 		struct iproc_asiu_clk *asiu_clk;
 		const char *clk_name;
@@ -240,22 +239,22 @@ void __init iproc_asiu_setup(struct device_node *node,
 		init.num_parents = (parent_name ? 1 : 0);
 		asiu_clk->hw.init = &init;
 
-		clk = clk_register(NULL, &asiu_clk->hw);
-		if (WARN_ON(IS_ERR(clk)))
+		ret = clk_hw_register(NULL, &asiu_clk->hw);
+		if (WARN_ON(ret))
 			goto err_clk_register;
-		asiu->clk_data.clks[i] = clk;
+		asiu->clk_data->hws[i] = &asiu_clk->hw;
 	}
 
-	ret = of_clk_add_provider(node, of_clk_src_onecell_get,
-				  &asiu->clk_data);
+	ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get,
+				     asiu->clk_data);
 	if (WARN_ON(ret))
 		goto err_clk_register;
 
 	return;
 
 err_clk_register:
-	for (i = 0; i < num_clks; i++)
-		clk_unregister(asiu->clk_data.clks[i]);
+	while (--i >= 0)
+		clk_hw_unregister(asiu->clk_data->hws[i]);
 	iounmap(asiu->gate_base);
 
 err_iomap_gate:
@@ -265,7 +264,7 @@ err_iomap_div:
 	kfree(asiu->clks);
 
 err_asiu_clks:
-	kfree(asiu->clk_data.clks);
+	kfree(asiu->clk_data);
 
 err_clks:
 	kfree(asiu);
diff --git a/drivers/clk/bcm/clk-iproc-pll.c b/drivers/clk/bcm/clk-iproc-pll.c
index fd492a5dad12..e04634c46395 100644
--- a/drivers/clk/bcm/clk-iproc-pll.c
+++ b/drivers/clk/bcm/clk-iproc-pll.c
@@ -89,7 +89,7 @@ struct iproc_pll {
 	const struct iproc_pll_vco_param *vco_param;
 	unsigned int num_vco_entries;
 
-	struct clk_onecell_data clk_data;
+	struct clk_hw_onecell_data *clk_data;
 	struct iproc_clk *clks;
 };
 
@@ -625,7 +625,6 @@ void __init iproc_pll_clk_setup(struct device_node *node,
 				unsigned int num_clks)
 {
 	int i, ret;
-	struct clk *clk;
 	struct iproc_pll *pll;
 	struct iproc_clk *iclk;
 	struct clk_init_data init;
@@ -638,11 +637,11 @@ void __init iproc_pll_clk_setup(struct device_node *node,
 	if (WARN_ON(!pll))
 		return;
 
-	pll->clk_data.clk_num = num_clks;
-	pll->clk_data.clks = kcalloc(num_clks, sizeof(*pll->clk_data.clks),
-				     GFP_KERNEL);
-	if (WARN_ON(!pll->clk_data.clks))
+	pll->clk_data = kzalloc(sizeof(*pll->clk_data->hws) * num_clks +
+				sizeof(*pll->clk_data), GFP_KERNEL);
+	if (WARN_ON(!pll->clk_data))
 		goto err_clk_data;
+	pll->clk_data->num = num_clks;
 
 	pll->clks = kcalloc(num_clks, sizeof(*pll->clks), GFP_KERNEL);
 	if (WARN_ON(!pll->clks))
@@ -694,11 +693,11 @@ void __init iproc_pll_clk_setup(struct device_node *node,
 
 	iproc_pll_sw_cfg(pll);
 
-	clk = clk_register(NULL, &iclk->hw);
-	if (WARN_ON(IS_ERR(clk)))
+	ret = clk_hw_register(NULL, &iclk->hw);
+	if (WARN_ON(ret))
 		goto err_pll_register;
 
-	pll->clk_data.clks[0] = clk;
+	pll->clk_data->hws[0] = &iclk->hw;
 
 	/* now initialize and register all leaf clocks */
 	for (i = 1; i < num_clks; i++) {
@@ -724,22 +723,23 @@ void __init iproc_pll_clk_setup(struct device_node *node,
 		init.num_parents = (parent_name ? 1 : 0);
 		iclk->hw.init = &init;
 
-		clk = clk_register(NULL, &iclk->hw);
-		if (WARN_ON(IS_ERR(clk)))
+		ret = clk_hw_register(NULL, &iclk->hw);
+		if (WARN_ON(ret))
 			goto err_clk_register;
 
-		pll->clk_data.clks[i] = clk;
+		pll->clk_data->hws[i] = &iclk->hw;
 	}
 
-	ret = of_clk_add_provider(node, of_clk_src_onecell_get, &pll->clk_data);
+	ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get,
+				     pll->clk_data);
 	if (WARN_ON(ret))
 		goto err_clk_register;
 
 	return;
 
 err_clk_register:
-	for (i = 0; i < num_clks; i++)
-		clk_unregister(pll->clk_data.clks[i]);
+	while (--i >= 0)
+		clk_hw_unregister(pll->clk_data->hws[i]);
 
 err_pll_register:
 	if (pll->status_base != pll->control_base)
@@ -759,7 +759,7 @@ err_pll_iomap:
 	kfree(pll->clks);
 
 err_clks:
-	kfree(pll->clk_data.clks);
+	kfree(pll->clk_data);
 
 err_clk_data:
 	kfree(pll);
diff --git a/drivers/clk/clk-clps711x.c b/drivers/clk/clk-clps711x.c
index 1f60b02416a7..adaf109f2fe2 100644
--- a/drivers/clk/clk-clps711x.c
+++ b/drivers/clk/clk-clps711x.c
@@ -184,5 +184,5 @@ static void __init clps711x_clk_init_dt(struct device_node *np)
 	of_clk_add_provider(np, of_clk_src_onecell_get,
 			    &clps711x_clk->clk_data);
 }
-CLK_OF_DECLARE(clps711x, "cirrus,clps711x-clk", clps711x_clk_init_dt);
+CLK_OF_DECLARE(clps711x, "cirrus,ep7209-clk", clps711x_clk_init_dt);
 #endif
diff --git a/drivers/clk/clk-conf.c b/drivers/clk/clk-conf.c
index 43a218f35b19..674785d968a3 100644
--- a/drivers/clk/clk-conf.c
+++ b/drivers/clk/clk-conf.c
@@ -55,7 +55,7 @@ static int __set_clk_parents(struct device_node *node, bool clk_supplier)
 		}
 		clk = of_clk_get_from_provider(&clkspec);
 		if (IS_ERR(clk)) {
-			pr_warn("clk: couldn't get parent clock %d for %s\n",
+			pr_warn("clk: couldn't get assigned clock %d for %s\n",
 				index, node->full_name);
 			rc = PTR_ERR(clk);
 			goto err;
diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c
index 75cd6c792cb8..4db3be214077 100644
--- a/drivers/clk/clk-fixed-factor.c
+++ b/drivers/clk/clk-fixed-factor.c
@@ -142,6 +142,11 @@ void clk_hw_unregister_fixed_factor(struct clk_hw *hw)
 EXPORT_SYMBOL_GPL(clk_hw_unregister_fixed_factor);
 
 #ifdef CONFIG_OF
+static const struct of_device_id set_rate_parent_matches[] = {
+	{ .compatible = "allwinner,sun4i-a10-pll3-2x-clk" },
+	{ /* Sentinel */ },
+};
+
 /**
  * of_fixed_factor_clk_setup() - Setup function for simple fixed factor clock
  */
@@ -150,6 +155,7 @@ void __init of_fixed_factor_clk_setup(struct device_node *node)
 	struct clk *clk;
 	const char *clk_name = node->name;
 	const char *parent_name;
+	unsigned long flags = 0;
 	u32 div, mult;
 
 	if (of_property_read_u32(node, "clock-div", &div)) {
@@ -167,7 +173,10 @@ void __init of_fixed_factor_clk_setup(struct device_node *node)
 	of_property_read_string(node, "clock-output-names", &clk_name);
 	parent_name = of_clk_get_parent_name(node, 0);
 
-	clk = clk_register_fixed_factor(NULL, clk_name, parent_name, 0,
+	if (of_match_node(set_rate_parent_matches, node))
+		flags |= CLK_SET_RATE_PARENT;
+
+	clk = clk_register_fixed_factor(NULL, clk_name, parent_name, flags,
 					mult, div);
 	if (!IS_ERR(clk))
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
diff --git a/drivers/clk/clk-fixed-rate.c b/drivers/clk/clk-fixed-rate.c
index 8e4453eb54e8..2edb39342a02 100644
--- a/drivers/clk/clk-fixed-rate.c
+++ b/drivers/clk/clk-fixed-rate.c
@@ -145,6 +145,17 @@ void clk_unregister_fixed_rate(struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(clk_unregister_fixed_rate);
 
+void clk_hw_unregister_fixed_rate(struct clk_hw *hw)
+{
+	struct clk_fixed_rate *fixed;
+
+	fixed = to_clk_fixed_rate(hw);
+
+	clk_hw_unregister(hw);
+	kfree(fixed);
+}
+EXPORT_SYMBOL_GPL(clk_hw_unregister_fixed_rate);
+
 #ifdef CONFIG_OF
 /**
  * of_fixed_clk_setup() - Setup function for simple fixed rate clock
diff --git a/drivers/clk/clk-highbank.c b/drivers/clk/clk-highbank.c
index be3a21abb185..727ed8e1bb72 100644
--- a/drivers/clk/clk-highbank.c
+++ b/drivers/clk/clk-highbank.c
@@ -275,7 +275,6 @@ static const struct clk_ops periclk_ops = {
 static __init struct clk *hb_clk_init(struct device_node *node, const struct clk_ops *ops)
 {
 	u32 reg;
-	struct clk *clk;
 	struct hb_clk *hb_clk;
 	const char *clk_name = node->name;
 	const char *parent_name;
@@ -308,13 +307,13 @@ static __init struct clk *hb_clk_init(struct device_node *node, const struct clk
 
 	hb_clk->hw.init = &init;
 
-	clk = clk_register(NULL, &hb_clk->hw);
-	if (WARN_ON(IS_ERR(clk))) {
+	rc = clk_hw_register(NULL, &hb_clk->hw);
+	if (WARN_ON(rc)) {
 		kfree(hb_clk);
 		return NULL;
 	}
-	rc = of_clk_add_provider(node, of_clk_src_simple_get, clk);
-	return clk;
+	rc = of_clk_add_hw_provider(node, of_clk_hw_simple_get, &hb_clk->hw);
+	return hb_clk->hw.clk;
 }
 
 static void __init hb_pll_init(struct device_node *node)
diff --git a/drivers/clk/clk-multiplier.c b/drivers/clk/clk-multiplier.c
index 9e449c7b751c..dc037c957acd 100644
--- a/drivers/clk/clk-multiplier.c
+++ b/drivers/clk/clk-multiplier.c
@@ -52,14 +52,28 @@ static unsigned long __bestmult(struct clk_hw *hw, unsigned long rate,
 				unsigned long *best_parent_rate,
 				u8 width, unsigned long flags)
 {
+	struct clk_multiplier *mult = to_clk_multiplier(hw);
 	unsigned long orig_parent_rate = *best_parent_rate;
 	unsigned long parent_rate, current_rate, best_rate = ~0;
 	unsigned int i, bestmult = 0;
+	unsigned int maxmult = (1 << width) - 1;
+
+	if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) {
+		bestmult = rate / orig_parent_rate;
+
+		/* Make sure we don't end up with a 0 multiplier */
+		if ((bestmult == 0) &&
+		    !(mult->flags & CLK_MULTIPLIER_ZERO_BYPASS))
+			bestmult = 1;
 
-	if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT))
-		return rate / *best_parent_rate;
+		/* Make sure we don't overflow the multiplier */
+		if (bestmult > maxmult)
+			bestmult = maxmult;
+
+		return bestmult;
+	}
 
-	for (i = 1; i < ((1 << width) - 1); i++) {
+	for (i = 1; i < maxmult; i++) {
 		if (rate == orig_parent_rate * i) {
 			/*
 			 * This is the best case for us if we have a
diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c
index e4d8a991c58f..71677eb12565 100644
--- a/drivers/clk/clk-nomadik.c
+++ b/drivers/clk/clk-nomadik.c
@@ -253,11 +253,11 @@ static const struct clk_ops pll_clk_ops = {
 	.recalc_rate = pll_clk_recalc_rate,
 };
 
-static struct clk * __init
+static struct clk_hw * __init
 pll_clk_register(struct device *dev, const char *name,
 		 const char *parent_name, u32 id)
 {
-	struct clk *clk;
+	int ret;
 	struct clk_pll *pll;
 	struct clk_init_data init;
 
@@ -281,11 +281,13 @@ pll_clk_register(struct device *dev, const char *name,
 
 	pr_debug("register PLL1 clock \"%s\"\n", name);
 
-	clk = clk_register(dev, &pll->hw);
-	if (IS_ERR(clk))
+	ret = clk_hw_register(dev, &pll->hw);
+	if (ret) {
 		kfree(pll);
+		return ERR_PTR(ret);
+	}
 
-	return clk;
+	return &pll->hw;
 }
 
 /*
@@ -345,11 +347,11 @@ static const struct clk_ops src_clk_ops = {
 	.recalc_rate = src_clk_recalc_rate,
 };
 
-static struct clk * __init
+static struct clk_hw * __init
 src_clk_register(struct device *dev, const char *name,
 		 const char *parent_name, u8 id)
 {
-	struct clk *clk;
+	int ret;
 	struct clk_src *sclk;
 	struct clk_init_data init;
 
@@ -376,11 +378,13 @@ src_clk_register(struct device *dev, const char *name,
 	pr_debug("register clock \"%s\" ID: %d group: %d bits: %08x\n",
 		 name, id, sclk->group1, sclk->clkbit);
 
-	clk = clk_register(dev, &sclk->hw);
-	if (IS_ERR(clk))
+	ret = clk_hw_register(dev, &sclk->hw);
+	if (ret) {
 		kfree(sclk);
+		return ERR_PTR(ret);
+	}
 
-	return clk;
+	return &sclk->hw;
 }
 
 #ifdef CONFIG_DEBUG_FS
@@ -508,7 +512,7 @@ device_initcall(nomadik_src_clk_init_debugfs);
 
 static void __init of_nomadik_pll_setup(struct device_node *np)
 {
-	struct clk *clk = ERR_PTR(-EINVAL);
+	struct clk_hw *hw;
 	const char *clk_name = np->name;
 	const char *parent_name;
 	u32 pll_id;
@@ -522,16 +526,16 @@ static void __init of_nomadik_pll_setup(struct device_node *np)
 		return;
 	}
 	parent_name = of_clk_get_parent_name(np, 0);
-	clk = pll_clk_register(NULL, clk_name, parent_name, pll_id);
-	if (!IS_ERR(clk))
-		of_clk_add_provider(np, of_clk_src_simple_get, clk);
+	hw = pll_clk_register(NULL, clk_name, parent_name, pll_id);
+	if (!IS_ERR(hw))
+		of_clk_add_hw_provider(np, of_clk_hw_simple_get, hw);
 }
 CLK_OF_DECLARE(nomadik_pll_clk,
 	"st,nomadik-pll-clock", of_nomadik_pll_setup);
 
 static void __init of_nomadik_hclk_setup(struct device_node *np)
 {
-	struct clk *clk = ERR_PTR(-EINVAL);
+	struct clk_hw *hw;
 	const char *clk_name = np->name;
 	const char *parent_name;
 
@@ -542,20 +546,20 @@ static void __init of_nomadik_hclk_setup(struct device_node *np)
 	/*
 	 * The HCLK divides PLL1 with 1 (passthru), 2, 3 or 4.
 	 */
-	clk = clk_register_divider(NULL, clk_name, parent_name,
+	hw = clk_hw_register_divider(NULL, clk_name, parent_name,
 			   0, src_base + SRC_CR,
 			   13, 2,
 			   CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
 			   &src_lock);
-	if (!IS_ERR(clk))
-		of_clk_add_provider(np, of_clk_src_simple_get, clk);
+	if (!IS_ERR(hw))
+		of_clk_add_hw_provider(np, of_clk_hw_simple_get, hw);
 }
 CLK_OF_DECLARE(nomadik_hclk_clk,
 	"st,nomadik-hclk-clock", of_nomadik_hclk_setup);
 
 static void __init of_nomadik_src_clk_setup(struct device_node *np)
 {
-	struct clk *clk = ERR_PTR(-EINVAL);
+	struct clk_hw *hw;
 	const char *clk_name = np->name;
 	const char *parent_name;
 	u32 clk_id;
@@ -569,9 +573,9 @@ static void __init of_nomadik_src_clk_setup(struct device_node *np)
 		return;
 	}
 	parent_name = of_clk_get_parent_name(np, 0);
-	clk = src_clk_register(NULL, clk_name, parent_name, clk_id);
-	if (!IS_ERR(clk))
-		of_clk_add_provider(np, of_clk_src_simple_get, clk);
+	hw = src_clk_register(NULL, clk_name, parent_name, clk_id);
+	if (!IS_ERR(hw))
+		of_clk_add_hw_provider(np, of_clk_hw_simple_get, hw);
 }
 CLK_OF_DECLARE(nomadik_src_clk,
 	"st,nomadik-src-clock", of_nomadik_src_clk_setup);
diff --git a/drivers/clk/clk-oxnas.c b/drivers/clk/clk-oxnas.c
index 79bcb2e42060..47649ac5d399 100644
--- a/drivers/clk/clk-oxnas.c
+++ b/drivers/clk/clk-oxnas.c
@@ -18,7 +18,7 @@
 
 #include <linux/clk-provider.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/stringify.h>
@@ -170,26 +170,17 @@ static int oxnas_stdclk_probe(struct platform_device *pdev)
 				   clk_oxnas->onecell_data);
 }
 
-static int oxnas_stdclk_remove(struct platform_device *pdev)
-{
-	of_clk_del_provider(pdev->dev.of_node);
-
-	return 0;
-}
-
 static const struct of_device_id oxnas_stdclk_dt_ids[] = {
 	{ .compatible = "oxsemi,ox810se-stdclk" },
 	{ }
 };
-MODULE_DEVICE_TABLE(of, oxnas_stdclk_dt_ids);
 
 static struct platform_driver oxnas_stdclk_driver = {
 	.probe = oxnas_stdclk_probe,
-	.remove = oxnas_stdclk_remove,
 	.driver	= {
 		.name = "oxnas-stdclk",
+		.suppress_bind_attrs = true,
 		.of_match_table = oxnas_stdclk_dt_ids,
 	},
 };
-
-module_platform_driver(oxnas_stdclk_driver);
+builtin_platform_driver(oxnas_stdclk_driver);
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index f8c83977c7fa..fbaa84a33c46 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -137,7 +137,7 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 {
 	struct sec_pmic_dev *iodev = dev_get_drvdata(pdev->dev.parent);
 	struct s2mps11_clk *s2mps11_clks;
-	struct clk_onecell_data *clk_data;
+	struct clk_hw_onecell_data *clk_data;
 	unsigned int s2mps11_reg;
 	int i, ret = 0;
 	enum sec_device_type hwid = platform_get_device_id(pdev)->driver_data;
@@ -147,15 +147,12 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 	if (!s2mps11_clks)
 		return -ENOMEM;
 
-	clk_data = devm_kzalloc(&pdev->dev, sizeof(*clk_data), GFP_KERNEL);
+	clk_data = devm_kzalloc(&pdev->dev, sizeof(*clk_data) +
+				sizeof(*clk_data->hws) * S2MPS11_CLKS_NUM,
+				GFP_KERNEL);
 	if (!clk_data)
 		return -ENOMEM;
 
-	clk_data->clks = devm_kcalloc(&pdev->dev, S2MPS11_CLKS_NUM,
-				sizeof(struct clk *), GFP_KERNEL);
-	if (!clk_data->clks)
-		return -ENOMEM;
-
 	switch (hwid) {
 	case S2MPS11X:
 		s2mps11_reg = S2MPS11_REG_RTC_CTRL;
@@ -196,18 +193,18 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 			goto err_reg;
 		}
 
-		s2mps11_clks[i].lookup = clkdev_create(s2mps11_clks[i].clk,
+		s2mps11_clks[i].lookup = clkdev_hw_create(&s2mps11_clks[i].hw,
 					s2mps11_clks_init[i].name, NULL);
 		if (!s2mps11_clks[i].lookup) {
 			ret = -ENOMEM;
 			goto err_reg;
 		}
-		clk_data->clks[i] = s2mps11_clks[i].clk;
+		clk_data->hws[i] = &s2mps11_clks[i].hw;
 	}
 
-	clk_data->clk_num = S2MPS11_CLKS_NUM;
-	of_clk_add_provider(s2mps11_clks->clk_np, of_clk_src_onecell_get,
-			clk_data);
+	clk_data->num = S2MPS11_CLKS_NUM;
+	of_clk_add_hw_provider(s2mps11_clks->clk_np, of_clk_hw_onecell_get,
+			       clk_data);
 
 	platform_set_drvdata(pdev, s2mps11_clks);
 
diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c
index fd89e771107e..02d681008401 100644
--- a/drivers/clk/clk-stm32f4.c
+++ b/drivers/clk/clk-stm32f4.c
@@ -136,7 +136,7 @@ static const u64 stm32f42xx_gate_map[] = { 0x000000f17ef417ffull,
 					   0x0000000000000001ull,
 					   0x04777f33f6fec9ffull };
 
-static struct clk *clks[MAX_CLKS];
+static struct clk_hw *clks[MAX_CLKS];
 static DEFINE_SPINLOCK(stm32f4_clk_lock);
 static void __iomem *base;
 
@@ -281,7 +281,7 @@ static int stm32f4_rcc_lookup_clk_idx(u8 primary, u8 secondary)
 	       (BIT_ULL_WORD(secondary) >= 2 ? hweight64(table[2]) : 0);
 }
 
-static struct clk *
+static struct clk_hw *
 stm32f4_rcc_lookup_clk(struct of_phandle_args *clkspec, void *data)
 {
 	int i = stm32f4_rcc_lookup_clk_idx(clkspec->args[0], clkspec->args[1]);
@@ -346,9 +346,9 @@ static void __init stm32f4_rcc_init(struct device_node *np)
 	clk_register_apb_mul(NULL, "apb2_mul", "apb2_div",
 			     CLK_SET_RATE_PARENT, 15);
 
-	clks[SYSTICK] = clk_register_fixed_factor(NULL, "systick", "ahb_div",
+	clks[SYSTICK] = clk_hw_register_fixed_factor(NULL, "systick", "ahb_div",
 						  0, 1, 8);
-	clks[FCLK] = clk_register_fixed_factor(NULL, "fclk", "ahb_div",
+	clks[FCLK] = clk_hw_register_fixed_factor(NULL, "fclk", "ahb_div",
 					       0, 1, 1);
 
 	for (n = 0; n < ARRAY_SIZE(stm32f4_gates); n++) {
@@ -360,18 +360,18 @@ static void __init stm32f4_rcc_init(struct device_node *np)
 		if (idx < 0)
 			goto fail;
 
-		clks[idx] = clk_register_gate(
+		clks[idx] = clk_hw_register_gate(
 		    NULL, gd->name, gd->parent_name, gd->flags,
 		    base + gd->offset, gd->bit_idx, 0, &stm32f4_clk_lock);
 
-		if (IS_ERR(clks[n])) {
+		if (IS_ERR(clks[idx])) {
 			pr_err("%s: Unable to register leaf clock %s\n",
 			       np->full_name, gd->name);
 			goto fail;
 		}
 	}
 
-	of_clk_add_provider(np, stm32f4_rcc_lookup_clk, NULL);
+	of_clk_add_hw_provider(np, stm32f4_rcc_lookup_clk, NULL);
 	return;
 fail:
 	iounmap(base);
diff --git a/drivers/clk/clk-u300.c b/drivers/clk/clk-u300.c
index 95d1742dac30..ec8aafda6e24 100644
--- a/drivers/clk/clk-u300.c
+++ b/drivers/clk/clk-u300.c
@@ -689,7 +689,7 @@ static const struct clk_ops syscon_clk_ops = {
 	.set_rate = syscon_clk_set_rate,
 };
 
-static struct clk * __init
+static struct clk_hw * __init
 syscon_clk_register(struct device *dev, const char *name,
 		    const char *parent_name, unsigned long flags,
 		    bool hw_ctrld,
@@ -697,9 +697,10 @@ syscon_clk_register(struct device *dev, const char *name,
 		    void __iomem *en_reg, u8 en_bit,
 		    u16 clk_val)
 {
-	struct clk *clk;
+	struct clk_hw *hw;
 	struct clk_syscon *sclk;
 	struct clk_init_data init;
+	int ret;
 
 	sclk = kzalloc(sizeof(struct clk_syscon), GFP_KERNEL);
 	if (!sclk) {
@@ -722,11 +723,14 @@ syscon_clk_register(struct device *dev, const char *name,
 	sclk->en_bit = en_bit;
 	sclk->clk_val = clk_val;
 
-	clk = clk_register(dev, &sclk->hw);
-	if (IS_ERR(clk))
+	hw = &sclk->hw;
+	ret = clk_hw_register(dev, hw);
+	if (ret) {
 		kfree(sclk);
+		hw = ERR_PTR(ret);
+	}
 
-	return clk;
+	return hw;
 }
 
 #define U300_CLK_TYPE_SLOW 0
@@ -868,7 +872,7 @@ static struct u300_clock const u300_clk_lookup[] __initconst = {
 
 static void __init of_u300_syscon_clk_init(struct device_node *np)
 {
-	struct clk *clk = ERR_PTR(-EINVAL);
+	struct clk_hw *hw = ERR_PTR(-EINVAL);
 	const char *clk_name = np->name;
 	const char *parent_name;
 	void __iomem *res_reg;
@@ -911,16 +915,15 @@ static void __init of_u300_syscon_clk_init(struct device_node *np)
 		const struct u300_clock *u3clk = &u300_clk_lookup[i];
 
 		if (u3clk->type == clk_type && u3clk->id == clk_id)
-			clk = syscon_clk_register(NULL,
-						  clk_name, parent_name,
-						  0, u3clk->hw_ctrld,
-						  res_reg, u3clk->id,
-						  en_reg, u3clk->id,
-						  u3clk->clk_val);
+			hw = syscon_clk_register(NULL, clk_name, parent_name,
+						 0, u3clk->hw_ctrld,
+						 res_reg, u3clk->id,
+						 en_reg, u3clk->id,
+						 u3clk->clk_val);
 	}
 
-	if (!IS_ERR(clk)) {
-		of_clk_add_provider(np, of_clk_src_simple_get, clk);
+	if (!IS_ERR(hw)) {
+		of_clk_add_hw_provider(np, of_clk_hw_simple_get, hw);
 
 		/*
 		 * Some few system clocks - device tree does not
@@ -928,11 +931,11 @@ static void __init of_u300_syscon_clk_init(struct device_node *np)
 		 * for now we add these three clocks here.
 		 */
 		if (clk_type == U300_CLK_TYPE_REST && clk_id == 5)
-			clk_register_clkdev(clk, NULL, "pl172");
+			clk_hw_register_clkdev(hw, NULL, "pl172");
 		if (clk_type == U300_CLK_TYPE_REST && clk_id == 9)
-			clk_register_clkdev(clk, NULL, "semi");
+			clk_hw_register_clkdev(hw, NULL, "semi");
 		if (clk_type == U300_CLK_TYPE_REST && clk_id == 12)
-			clk_register_clkdev(clk, NULL, "intcon");
+			clk_hw_register_clkdev(hw, NULL, "intcon");
 	}
 }
 
@@ -1111,13 +1114,14 @@ static const struct clk_ops mclk_ops = {
 	.set_rate = mclk_clk_set_rate,
 };
 
-static struct clk * __init
+static struct clk_hw * __init
 mclk_clk_register(struct device *dev, const char *name,
 		  const char *parent_name, bool is_mspro)
 {
-	struct clk *clk;
+	struct clk_hw *hw;
 	struct clk_mclk *mclk;
 	struct clk_init_data init;
+	int ret;
 
 	mclk = kzalloc(sizeof(struct clk_mclk), GFP_KERNEL);
 	if (!mclk) {
@@ -1133,23 +1137,26 @@ mclk_clk_register(struct device *dev, const char *name,
 	mclk->hw.init = &init;
 	mclk->is_mspro = is_mspro;
 
-	clk = clk_register(dev, &mclk->hw);
-	if (IS_ERR(clk))
+	hw = &mclk->hw;
+	ret = clk_hw_register(dev, hw);
+	if (ret) {
 		kfree(mclk);
+		hw = ERR_PTR(ret);
+	}
 
-	return clk;
+	return hw;
 }
 
 static void __init of_u300_syscon_mclk_init(struct device_node *np)
 {
-	struct clk *clk = ERR_PTR(-EINVAL);
+	struct clk_hw *hw;
 	const char *clk_name = np->name;
 	const char *parent_name;
 
 	parent_name = of_clk_get_parent_name(np, 0);
-	clk = mclk_clk_register(NULL, clk_name, parent_name, false);
-	if (!IS_ERR(clk))
-		of_clk_add_provider(np, of_clk_src_simple_get, clk);
+	hw = mclk_clk_register(NULL, clk_name, parent_name, false);
+	if (!IS_ERR(hw))
+		of_clk_add_hw_provider(np, of_clk_hw_simple_get, hw);
 }
 
 static const struct of_device_id u300_clk_match[] __initconst = {
diff --git a/drivers/clk/clk-vt8500.c b/drivers/clk/clk-vt8500.c
index b0f76a84f1e9..37368a399ff9 100644
--- a/drivers/clk/clk-vt8500.c
+++ b/drivers/clk/clk-vt8500.c
@@ -383,51 +383,49 @@ static int vt8500_find_pll_bits(unsigned long rate, unsigned long parent_rate,
 	return 0;
 }
 
-static int wm8650_find_pll_bits(unsigned long rate, unsigned long parent_rate,
-				u32 *multiplier, u32 *divisor1, u32 *divisor2)
+/*
+ * M * parent [O1] => / P [O2] => / D [O3]
+ * Where O1 is 900MHz...3GHz;
+ * O2 is 600MHz >= (M * parent) / P >= 300MHz;
+ * M is 36...120 [25MHz parent]; D is 1 or 2 or 4 or 8.
+ * Possible ranges (O3):
+ * D = 8: 37,5MHz...75MHz
+ * D = 4: 75MHz...150MHz
+ * D = 2: 150MHz...300MHz
+ * D = 1: 300MHz...600MHz
+ */
+static int wm8650_find_pll_bits(unsigned long rate,
+	unsigned long parent_rate, u32 *multiplier, u32 *divisor1,
+	u32 *divisor2)
 {
-	u32 mul, div1;
-	int div2;
-	u32 best_mul, best_div1, best_div2;
-	unsigned long tclk, rate_err, best_err;
-
-	best_err = (unsigned long)-1;
+	unsigned long O1, min_err, rate_err;
 
-	/* Find the closest match (lower or equal to requested) */
-	for (div1 = 5; div1 >= 3; div1--)
-		for (div2 = 3; div2 >= 0; div2--)
-			for (mul = 3; mul <= 1023; mul++) {
-				tclk = parent_rate * mul / (div1 * (1 << div2));
-				if (tclk > rate)
-					continue;
-				/* error will always be +ve */
-				rate_err = rate - tclk;
-				if (rate_err == 0) {
-					*multiplier = mul;
-					*divisor1 = div1;
-					*divisor2 = div2;
-					return 0;
-				}
+	if (!parent_rate || (rate < 37500000) || (rate > 600000000))
+		return -EINVAL;
 
-				if (rate_err < best_err) {
-					best_err = rate_err;
-					best_mul = mul;
-					best_div1 = div1;
-					best_div2 = div2;
-				}
-			}
+	*divisor2 = rate <= 75000000 ? 3 : rate <= 150000000 ? 2 :
+					   rate <= 300000000 ? 1 : 0;
+	/*
+	 * Divisor P cannot be calculated. Test all divisors and find where M
+	 * will be as close as possible to the requested rate.
+	 */
+	min_err = ULONG_MAX;
+	for (*divisor1 = 5; *divisor1 >= 3; (*divisor1)--) {
+		O1 = rate * *divisor1 * (1 << (*divisor2));
+		rate_err = O1 % parent_rate;
+		if (rate_err < min_err) {
+			*multiplier = O1 / parent_rate;
+			if (rate_err == 0)
+				return 0;
+
+			min_err = rate_err;
+		}
+	}
 
-	if (best_err == (unsigned long)-1) {
-		pr_warn("%s: impossible rate %lu\n", __func__, rate);
+	if ((*multiplier < 3) || (*multiplier > 1023))
 		return -EINVAL;
-	}
 
-	/* if we got here, it wasn't an exact match */
-	pr_warn("%s: requested rate %lu, found rate %lu\n", __func__, rate,
-							rate - best_err);
-	*multiplier = best_mul;
-	*divisor1 = best_div1;
-	*divisor2 = best_div2;
+	pr_warn("%s: rate error is %lu\n", __func__, min_err);
 
 	return 0;
 }
@@ -464,7 +462,6 @@ static int wm8750_find_pll_bits(unsigned long rate, unsigned long parent_rate,
 {
 	u32 mul;
 	int div1, div2;
-	u32 best_mul, best_div1, best_div2;
 	unsigned long tclk, rate_err, best_err;
 
 	best_err = (unsigned long)-1;
@@ -488,9 +485,9 @@ static int wm8750_find_pll_bits(unsigned long rate, unsigned long parent_rate,
 
 				if (rate_err < best_err) {
 					best_err = rate_err;
-					best_mul = mul;
-					best_div1 = div1;
-					best_div2 = div2;
+					*multiplier = mul;
+					*divisor1 = div1;
+					*divisor2 = div2;
 				}
 			}
 
@@ -503,10 +500,7 @@ static int wm8750_find_pll_bits(unsigned long rate, unsigned long parent_rate,
 	pr_warn("%s: requested rate %lu, found rate %lu\n", __func__, rate,
 							rate - best_err);
 
-	*filter = wm8750_get_filter(parent_rate, best_div1);
-	*multiplier = best_mul;
-	*divisor1 = best_div1;
-	*divisor2 = best_div2;
+	*filter = wm8750_get_filter(parent_rate, *divisor1);
 
 	return 0;
 }
@@ -516,7 +510,6 @@ static int wm8850_find_pll_bits(unsigned long rate, unsigned long parent_rate,
 {
 	u32 mul;
 	int div1, div2;
-	u32 best_mul, best_div1, best_div2;
 	unsigned long tclk, rate_err, best_err;
 
 	best_err = (unsigned long)-1;
@@ -540,9 +533,9 @@ static int wm8850_find_pll_bits(unsigned long rate, unsigned long parent_rate,
 
 				if (rate_err < best_err) {
 					best_err = rate_err;
-					best_mul = mul;
-					best_div1 = div1;
-					best_div2 = div2;
+					*multiplier = mul;
+					*divisor1 = div1;
+					*divisor2 = div2;
 				}
 			}
 
@@ -555,10 +548,6 @@ static int wm8850_find_pll_bits(unsigned long rate, unsigned long parent_rate,
 	pr_warn("%s: requested rate %lu, found rate %lu\n", __func__, rate,
 							rate - best_err);
 
-	*multiplier = best_mul;
-	*divisor1 = best_div1;
-	*divisor2 = best_div2;
-
 	return 0;
 }
 
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index d584004f7af7..820a939fb6bb 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -172,104 +172,6 @@ static bool clk_core_is_enabled(struct clk_core *core)
 	return core->ops->is_enabled(core->hw);
 }
 
-static void clk_unprepare_unused_subtree(struct clk_core *core)
-{
-	struct clk_core *child;
-
-	lockdep_assert_held(&prepare_lock);
-
-	hlist_for_each_entry(child, &core->children, child_node)
-		clk_unprepare_unused_subtree(child);
-
-	if (core->prepare_count)
-		return;
-
-	if (core->flags & CLK_IGNORE_UNUSED)
-		return;
-
-	if (clk_core_is_prepared(core)) {
-		trace_clk_unprepare(core);
-		if (core->ops->unprepare_unused)
-			core->ops->unprepare_unused(core->hw);
-		else if (core->ops->unprepare)
-			core->ops->unprepare(core->hw);
-		trace_clk_unprepare_complete(core);
-	}
-}
-
-static void clk_disable_unused_subtree(struct clk_core *core)
-{
-	struct clk_core *child;
-	unsigned long flags;
-
-	lockdep_assert_held(&prepare_lock);
-
-	hlist_for_each_entry(child, &core->children, child_node)
-		clk_disable_unused_subtree(child);
-
-	flags = clk_enable_lock();
-
-	if (core->enable_count)
-		goto unlock_out;
-
-	if (core->flags & CLK_IGNORE_UNUSED)
-		goto unlock_out;
-
-	/*
-	 * some gate clocks have special needs during the disable-unused
-	 * sequence.  call .disable_unused if available, otherwise fall
-	 * back to .disable
-	 */
-	if (clk_core_is_enabled(core)) {
-		trace_clk_disable(core);
-		if (core->ops->disable_unused)
-			core->ops->disable_unused(core->hw);
-		else if (core->ops->disable)
-			core->ops->disable(core->hw);
-		trace_clk_disable_complete(core);
-	}
-
-unlock_out:
-	clk_enable_unlock(flags);
-}
-
-static bool clk_ignore_unused;
-static int __init clk_ignore_unused_setup(char *__unused)
-{
-	clk_ignore_unused = true;
-	return 1;
-}
-__setup("clk_ignore_unused", clk_ignore_unused_setup);
-
-static int clk_disable_unused(void)
-{
-	struct clk_core *core;
-
-	if (clk_ignore_unused) {
-		pr_warn("clk: Not disabling unused clocks\n");
-		return 0;
-	}
-
-	clk_prepare_lock();
-
-	hlist_for_each_entry(core, &clk_root_list, child_node)
-		clk_disable_unused_subtree(core);
-
-	hlist_for_each_entry(core, &clk_orphan_list, child_node)
-		clk_disable_unused_subtree(core);
-
-	hlist_for_each_entry(core, &clk_root_list, child_node)
-		clk_unprepare_unused_subtree(core);
-
-	hlist_for_each_entry(core, &clk_orphan_list, child_node)
-		clk_unprepare_unused_subtree(core);
-
-	clk_prepare_unlock();
-
-	return 0;
-}
-late_initcall_sync(clk_disable_unused);
-
 /***    helper functions   ***/
 
 const char *__clk_get_name(const struct clk *clk)
@@ -591,6 +493,13 @@ static void clk_core_unprepare(struct clk_core *core)
 	clk_core_unprepare(core->parent);
 }
 
+static void clk_core_unprepare_lock(struct clk_core *core)
+{
+	clk_prepare_lock();
+	clk_core_unprepare(core);
+	clk_prepare_unlock();
+}
+
 /**
  * clk_unprepare - undo preparation of a clock source
  * @clk: the clk being unprepared
@@ -607,9 +516,7 @@ void clk_unprepare(struct clk *clk)
 	if (IS_ERR_OR_NULL(clk))
 		return;
 
-	clk_prepare_lock();
-	clk_core_unprepare(clk->core);
-	clk_prepare_unlock();
+	clk_core_unprepare_lock(clk->core);
 }
 EXPORT_SYMBOL_GPL(clk_unprepare);
 
@@ -645,6 +552,17 @@ static int clk_core_prepare(struct clk_core *core)
 	return 0;
 }
 
+static int clk_core_prepare_lock(struct clk_core *core)
+{
+	int ret;
+
+	clk_prepare_lock();
+	ret = clk_core_prepare(core);
+	clk_prepare_unlock();
+
+	return ret;
+}
+
 /**
  * clk_prepare - prepare a clock source
  * @clk: the clk being prepared
@@ -659,16 +577,10 @@ static int clk_core_prepare(struct clk_core *core)
  */
 int clk_prepare(struct clk *clk)
 {
-	int ret;
-
 	if (!clk)
 		return 0;
 
-	clk_prepare_lock();
-	ret = clk_core_prepare(clk->core);
-	clk_prepare_unlock();
-
-	return ret;
+	return clk_core_prepare_lock(clk->core);
 }
 EXPORT_SYMBOL_GPL(clk_prepare);
 
@@ -688,16 +600,25 @@ static void clk_core_disable(struct clk_core *core)
 	if (--core->enable_count > 0)
 		return;
 
-	trace_clk_disable(core);
+	trace_clk_disable_rcuidle(core);
 
 	if (core->ops->disable)
 		core->ops->disable(core->hw);
 
-	trace_clk_disable_complete(core);
+	trace_clk_disable_complete_rcuidle(core);
 
 	clk_core_disable(core->parent);
 }
 
+static void clk_core_disable_lock(struct clk_core *core)
+{
+	unsigned long flags;
+
+	flags = clk_enable_lock();
+	clk_core_disable(core);
+	clk_enable_unlock(flags);
+}
+
 /**
  * clk_disable - gate a clock
  * @clk: the clk being gated
@@ -712,14 +633,10 @@ static void clk_core_disable(struct clk_core *core)
  */
 void clk_disable(struct clk *clk)
 {
-	unsigned long flags;
-
 	if (IS_ERR_OR_NULL(clk))
 		return;
 
-	flags = clk_enable_lock();
-	clk_core_disable(clk->core);
-	clk_enable_unlock(flags);
+	clk_core_disable_lock(clk->core);
 }
 EXPORT_SYMBOL_GPL(clk_disable);
 
@@ -741,12 +658,12 @@ static int clk_core_enable(struct clk_core *core)
 		if (ret)
 			return ret;
 
-		trace_clk_enable(core);
+		trace_clk_enable_rcuidle(core);
 
 		if (core->ops->enable)
 			ret = core->ops->enable(core->hw);
 
-		trace_clk_enable_complete(core);
+		trace_clk_enable_complete_rcuidle(core);
 
 		if (ret) {
 			clk_core_disable(core->parent);
@@ -758,6 +675,18 @@ static int clk_core_enable(struct clk_core *core)
 	return 0;
 }
 
+static int clk_core_enable_lock(struct clk_core *core)
+{
+	unsigned long flags;
+	int ret;
+
+	flags = clk_enable_lock();
+	ret = clk_core_enable(core);
+	clk_enable_unlock(flags);
+
+	return ret;
+}
+
 /**
  * clk_enable - ungate a clock
  * @clk: the clk being ungated
@@ -773,19 +702,136 @@ static int clk_core_enable(struct clk_core *core)
  */
 int clk_enable(struct clk *clk)
 {
-	unsigned long flags;
-	int ret;
-
 	if (!clk)
 		return 0;
 
+	return clk_core_enable_lock(clk->core);
+}
+EXPORT_SYMBOL_GPL(clk_enable);
+
+static int clk_core_prepare_enable(struct clk_core *core)
+{
+	int ret;
+
+	ret = clk_core_prepare_lock(core);
+	if (ret)
+		return ret;
+
+	ret = clk_core_enable_lock(core);
+	if (ret)
+		clk_core_unprepare_lock(core);
+
+	return ret;
+}
+
+static void clk_core_disable_unprepare(struct clk_core *core)
+{
+	clk_core_disable_lock(core);
+	clk_core_unprepare_lock(core);
+}
+
+static void clk_unprepare_unused_subtree(struct clk_core *core)
+{
+	struct clk_core *child;
+
+	lockdep_assert_held(&prepare_lock);
+
+	hlist_for_each_entry(child, &core->children, child_node)
+		clk_unprepare_unused_subtree(child);
+
+	if (core->prepare_count)
+		return;
+
+	if (core->flags & CLK_IGNORE_UNUSED)
+		return;
+
+	if (clk_core_is_prepared(core)) {
+		trace_clk_unprepare(core);
+		if (core->ops->unprepare_unused)
+			core->ops->unprepare_unused(core->hw);
+		else if (core->ops->unprepare)
+			core->ops->unprepare(core->hw);
+		trace_clk_unprepare_complete(core);
+	}
+}
+
+static void clk_disable_unused_subtree(struct clk_core *core)
+{
+	struct clk_core *child;
+	unsigned long flags;
+
+	lockdep_assert_held(&prepare_lock);
+
+	hlist_for_each_entry(child, &core->children, child_node)
+		clk_disable_unused_subtree(child);
+
+	if (core->flags & CLK_OPS_PARENT_ENABLE)
+		clk_core_prepare_enable(core->parent);
+
 	flags = clk_enable_lock();
-	ret = clk_core_enable(clk->core);
+
+	if (core->enable_count)
+		goto unlock_out;
+
+	if (core->flags & CLK_IGNORE_UNUSED)
+		goto unlock_out;
+
+	/*
+	 * some gate clocks have special needs during the disable-unused
+	 * sequence.  call .disable_unused if available, otherwise fall
+	 * back to .disable
+	 */
+	if (clk_core_is_enabled(core)) {
+		trace_clk_disable(core);
+		if (core->ops->disable_unused)
+			core->ops->disable_unused(core->hw);
+		else if (core->ops->disable)
+			core->ops->disable(core->hw);
+		trace_clk_disable_complete(core);
+	}
+
+unlock_out:
 	clk_enable_unlock(flags);
+	if (core->flags & CLK_OPS_PARENT_ENABLE)
+		clk_core_disable_unprepare(core->parent);
+}
 
-	return ret;
+static bool clk_ignore_unused;
+static int __init clk_ignore_unused_setup(char *__unused)
+{
+	clk_ignore_unused = true;
+	return 1;
 }
-EXPORT_SYMBOL_GPL(clk_enable);
+__setup("clk_ignore_unused", clk_ignore_unused_setup);
+
+static int clk_disable_unused(void)
+{
+	struct clk_core *core;
+
+	if (clk_ignore_unused) {
+		pr_warn("clk: Not disabling unused clocks\n");
+		return 0;
+	}
+
+	clk_prepare_lock();
+
+	hlist_for_each_entry(core, &clk_root_list, child_node)
+		clk_disable_unused_subtree(core);
+
+	hlist_for_each_entry(core, &clk_orphan_list, child_node)
+		clk_disable_unused_subtree(core);
+
+	hlist_for_each_entry(core, &clk_root_list, child_node)
+		clk_unprepare_unused_subtree(core);
+
+	hlist_for_each_entry(core, &clk_orphan_list, child_node)
+		clk_unprepare_unused_subtree(core);
+
+	clk_prepare_unlock();
+
+	return 0;
+}
+late_initcall_sync(clk_disable_unused);
 
 static int clk_core_round_rate_nolock(struct clk_core *core,
 				      struct clk_rate_request *req)
@@ -828,9 +874,7 @@ static int clk_core_round_rate_nolock(struct clk_core *core,
 /**
  * __clk_determine_rate - get the closest rate actually supported by a clock
  * @hw: determine the rate of this clock
- * @rate: target rate
- * @min_rate: returned rate must be greater than this rate
- * @max_rate: returned rate must be less than this rate
+ * @req: target rate request
  *
  * Useful for clk_ops such as .set_rate and .determine_rate.
  */
@@ -1128,7 +1172,9 @@ static struct clk_core *__clk_set_parent_before(struct clk_core *core,
 	struct clk_core *old_parent = core->parent;
 
 	/*
-	 * Migrate prepare state between parents and prevent race with
+	 * 1. enable parents for CLK_OPS_PARENT_ENABLE clock
+	 *
+	 * 2. Migrate prepare state between parents and prevent race with
 	 * clk_enable().
 	 *
 	 * If the clock is not prepared, then a race with
@@ -1144,12 +1190,17 @@ static struct clk_core *__clk_set_parent_before(struct clk_core *core,
 	 *
 	 * See also: Comment for clk_set_parent() below.
 	 */
+
+	/* enable old_parent & parent if CLK_OPS_PARENT_ENABLE is set */
+	if (core->flags & CLK_OPS_PARENT_ENABLE) {
+		clk_core_prepare_enable(old_parent);
+		clk_core_prepare_enable(parent);
+	}
+
+	/* migrate prepare count if > 0 */
 	if (core->prepare_count) {
-		clk_core_prepare(parent);
-		flags = clk_enable_lock();
-		clk_core_enable(parent);
-		clk_core_enable(core);
-		clk_enable_unlock(flags);
+		clk_core_prepare_enable(parent);
+		clk_core_enable_lock(core);
 	}
 
 	/* update the clk tree topology */
@@ -1164,18 +1215,19 @@ static void __clk_set_parent_after(struct clk_core *core,
 				   struct clk_core *parent,
 				   struct clk_core *old_parent)
 {
-	unsigned long flags;
-
 	/*
 	 * Finish the migration of prepare state and undo the changes done
 	 * for preventing a race with clk_enable().
 	 */
 	if (core->prepare_count) {
-		flags = clk_enable_lock();
-		clk_core_disable(core);
-		clk_core_disable(old_parent);
-		clk_enable_unlock(flags);
-		clk_core_unprepare(old_parent);
+		clk_core_disable_lock(core);
+		clk_core_disable_unprepare(old_parent);
+	}
+
+	/* re-balance ref counting if CLK_OPS_PARENT_ENABLE is set */
+	if (core->flags & CLK_OPS_PARENT_ENABLE) {
+		clk_core_disable_unprepare(parent);
+		clk_core_disable_unprepare(old_parent);
 	}
 }
 
@@ -1422,13 +1474,17 @@ static void clk_change_rate(struct clk_core *core)
 	unsigned long best_parent_rate = 0;
 	bool skip_set_rate = false;
 	struct clk_core *old_parent;
+	struct clk_core *parent = NULL;
 
 	old_rate = core->rate;
 
-	if (core->new_parent)
+	if (core->new_parent) {
+		parent = core->new_parent;
 		best_parent_rate = core->new_parent->rate;
-	else if (core->parent)
+	} else if (core->parent) {
+		parent = core->parent;
 		best_parent_rate = core->parent->rate;
+	}
 
 	if (core->flags & CLK_SET_RATE_UNGATE) {
 		unsigned long flags;
@@ -1456,6 +1512,9 @@ static void clk_change_rate(struct clk_core *core)
 		__clk_set_parent_after(core, core->new_parent, old_parent);
 	}
 
+	if (core->flags & CLK_OPS_PARENT_ENABLE)
+		clk_core_prepare_enable(parent);
+
 	trace_clk_set_rate(core, core->new_rate);
 
 	if (!skip_set_rate && core->ops->set_rate)
@@ -1474,6 +1533,9 @@ static void clk_change_rate(struct clk_core *core)
 		clk_core_unprepare(core);
 	}
 
+	if (core->flags & CLK_OPS_PARENT_ENABLE)
+		clk_core_disable_unprepare(parent);
+
 	if (core->notifier_count && old_rate != core->rate)
 		__clk_notify(core, POST_RATE_CHANGE, old_rate, core->rate);
 
@@ -1501,7 +1563,6 @@ static int clk_core_set_rate_nolock(struct clk_core *core,
 {
 	struct clk_core *top, *fail_clk;
 	unsigned long rate = req_rate;
-	int ret = 0;
 
 	if (!core)
 		return 0;
@@ -1532,7 +1593,7 @@ static int clk_core_set_rate_nolock(struct clk_core *core,
 
 	core->req_rate = req_rate;
 
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 89cc700fbc37..97ae60fa1584 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -250,7 +250,7 @@ struct clk_lookup_alloc {
 	char	con_id[MAX_CON_ID];
 };
 
-static struct clk_lookup * __init_refok
+static struct clk_lookup * __ref
 vclkdev_alloc(struct clk_hw *hw, const char *con_id, const char *dev_fmt,
 	va_list ap)
 {
@@ -287,7 +287,7 @@ vclkdev_create(struct clk_hw *hw, const char *con_id, const char *dev_fmt,
 	return cl;
 }
 
-struct clk_lookup * __init_refok
+struct clk_lookup * __ref
 clkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt, ...)
 {
 	struct clk_lookup *cl;
diff --git a/drivers/clk/hisilicon/clk-hi3519.c b/drivers/clk/hisilicon/clk-hi3519.c
index 715c7301a66a..51b173ef1dda 100644
--- a/drivers/clk/hisilicon/clk-hi3519.c
+++ b/drivers/clk/hisilicon/clk-hi3519.c
@@ -38,6 +38,11 @@
 
 #define HI3519_NR_CLKS		128
 
+struct hi3519_crg_data {
+	struct hisi_clock_data *clk_data;
+	struct hisi_reset_controller *rstc;
+};
+
 static const struct hisi_fixed_rate_clock hi3519_fixed_rate_clks[] = {
 	{ HI3519_FIXED_24M, "24m", NULL, 0, 24000000, },
 	{ HI3519_FIXED_50M, "50m", NULL, 0, 50000000, },
@@ -80,33 +85,105 @@ static const struct hisi_gate_clock hi3519_gate_clks[] = {
 		CLK_SET_RATE_PARENT, 0xe4, 18, 0, },
 };
 
-static int hi3519_clk_probe(struct platform_device *pdev)
+static struct hisi_clock_data *hi3519_clk_register(struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node;
 	struct hisi_clock_data *clk_data;
-	struct hisi_reset_controller *rstc;
+	int ret;
 
-	rstc = hisi_reset_init(np);
-	if (!rstc)
+	clk_data = hisi_clk_alloc(pdev, HI3519_NR_CLKS);
+	if (!clk_data)
+		return ERR_PTR(-ENOMEM);
+
+	ret = hisi_clk_register_fixed_rate(hi3519_fixed_rate_clks,
+				     ARRAY_SIZE(hi3519_fixed_rate_clks),
+				     clk_data);
+	if (ret)
+		return ERR_PTR(ret);
+
+	ret = hisi_clk_register_mux(hi3519_mux_clks,
+				ARRAY_SIZE(hi3519_mux_clks),
+				clk_data);
+	if (ret)
+		goto unregister_fixed_rate;
+
+	ret = hisi_clk_register_gate(hi3519_gate_clks,
+				ARRAY_SIZE(hi3519_gate_clks),
+				clk_data);
+	if (ret)
+		goto unregister_mux;
+
+	ret = of_clk_add_provider(pdev->dev.of_node,
+			of_clk_src_onecell_get, &clk_data->clk_data);
+	if (ret)
+		goto unregister_gate;
+
+	return clk_data;
+
+unregister_fixed_rate:
+	hisi_clk_unregister_fixed_rate(hi3519_fixed_rate_clks,
+				ARRAY_SIZE(hi3519_fixed_rate_clks),
+				clk_data);
+
+unregister_mux:
+	hisi_clk_unregister_mux(hi3519_mux_clks,
+				ARRAY_SIZE(hi3519_mux_clks),
+				clk_data);
+unregister_gate:
+	hisi_clk_unregister_gate(hi3519_gate_clks,
+				ARRAY_SIZE(hi3519_gate_clks),
+				clk_data);
+	return ERR_PTR(ret);
+}
+
+static void hi3519_clk_unregister(struct platform_device *pdev)
+{
+	struct hi3519_crg_data *crg = platform_get_drvdata(pdev);
+
+	of_clk_del_provider(pdev->dev.of_node);
+
+	hisi_clk_unregister_gate(hi3519_gate_clks,
+				ARRAY_SIZE(hi3519_mux_clks),
+				crg->clk_data);
+	hisi_clk_unregister_mux(hi3519_mux_clks,
+				ARRAY_SIZE(hi3519_mux_clks),
+				crg->clk_data);
+	hisi_clk_unregister_fixed_rate(hi3519_fixed_rate_clks,
+				ARRAY_SIZE(hi3519_fixed_rate_clks),
+				crg->clk_data);
+}
+
+static int hi3519_clk_probe(struct platform_device *pdev)
+{
+	struct hi3519_crg_data *crg;
+
+	crg = devm_kmalloc(&pdev->dev, sizeof(*crg), GFP_KERNEL);
+	if (!crg)
+		return -ENOMEM;
+
+	crg->rstc = hisi_reset_init(pdev);
+	if (!crg->rstc)
 		return -ENOMEM;
 
-	clk_data = hisi_clk_init(np, HI3519_NR_CLKS);
-	if (!clk_data) {
-		hisi_reset_exit(rstc);
-		return -ENODEV;
+	crg->clk_data = hi3519_clk_register(pdev);
+	if (IS_ERR(crg->clk_data)) {
+		hisi_reset_exit(crg->rstc);
+		return PTR_ERR(crg->clk_data);
 	}
 
-	hisi_clk_register_fixed_rate(hi3519_fixed_rate_clks,
-				     ARRAY_SIZE(hi3519_fixed_rate_clks),
-				     clk_data);
-	hisi_clk_register_mux(hi3519_mux_clks, ARRAY_SIZE(hi3519_mux_clks),
-					clk_data);
-	hisi_clk_register_gate(hi3519_gate_clks,
-			ARRAY_SIZE(hi3519_gate_clks), clk_data);
+	platform_set_drvdata(pdev, crg);
+	return 0;
+}
+
+static int hi3519_clk_remove(struct platform_device *pdev)
+{
+	struct hi3519_crg_data *crg = platform_get_drvdata(pdev);
 
+	hisi_reset_exit(crg->rstc);
+	hi3519_clk_unregister(pdev);
 	return 0;
 }
 
+
 static const struct of_device_id hi3519_clk_match_table[] = {
 	{ .compatible = "hisilicon,hi3519-crg" },
 	{ }
@@ -115,6 +192,7 @@ MODULE_DEVICE_TABLE(of, hi3519_clk_match_table);
 
 static struct platform_driver hi3519_clk_driver = {
 	.probe          = hi3519_clk_probe,
+	.remove		= hi3519_clk_remove,
 	.driver         = {
 		.name   = "hi3519-clk",
 		.of_match_table = hi3519_clk_match_table,
@@ -127,5 +205,11 @@ static int __init hi3519_clk_init(void)
 }
 core_initcall(hi3519_clk_init);
 
+static void __exit hi3519_clk_exit(void)
+{
+	platform_driver_unregister(&hi3519_clk_driver);
+}
+module_exit(hi3519_clk_exit);
+
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("HiSilicon Hi3519 Clock Driver");
diff --git a/drivers/clk/hisilicon/clk-hi6220.c b/drivers/clk/hisilicon/clk-hi6220.c
index f02cb41d40a4..fe364e63f8de 100644
--- a/drivers/clk/hisilicon/clk-hi6220.c
+++ b/drivers/clk/hisilicon/clk-hi6220.c
@@ -34,8 +34,8 @@ static struct hisi_fixed_rate_clock hi6220_fixed_rate_clks[] __initdata = {
 	{ HI6220_PLL_BBP,	"bbppll0",	NULL, 0, 245760000, },
 	{ HI6220_PLL_GPU,	"gpupll",	NULL, 0, 1000000000,},
 	{ HI6220_PLL1_DDR,	"ddrpll1",	NULL, 0, 1066000000,},
-	{ HI6220_PLL_SYS,	"syspll",	NULL, 0, 1200000000,},
-	{ HI6220_PLL_SYS_MEDIA,	"media_syspll",	NULL, 0, 1200000000,},
+	{ HI6220_PLL_SYS,	"syspll",	NULL, 0, 1190400000,},
+	{ HI6220_PLL_SYS_MEDIA,	"media_syspll",	NULL, 0, 1190400000,},
 	{ HI6220_DDR_SRC,	"ddr_sel_src",  NULL, 0, 1200000000,},
 	{ HI6220_PLL_MEDIA,	"media_pll",    NULL, 0, 1440000000,},
 	{ HI6220_PLL_DDR,	"ddrpll0",      NULL, 0, 1600000000,},
@@ -68,6 +68,8 @@ static struct hisi_gate_clock hi6220_separated_gate_clks_ao[] __initdata = {
 	{ HI6220_TIMER7_PCLK, "timer7_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 22, 0, },
 	{ HI6220_TIMER8_PCLK, "timer8_pclk", "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 23, 0, },
 	{ HI6220_UART0_PCLK,  "uart0_pclk",  "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 24, 0, },
+	{ HI6220_RTC0_PCLK,   "rtc0_pclk",   "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 25, 0, },
+	{ HI6220_RTC1_PCLK,   "rtc1_pclk",   "clk_tcxo", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x630, 26, 0, },
 };
 
 static void __init hi6220_clk_ao_init(struct device_node *np)
diff --git a/drivers/clk/hisilicon/clk.c b/drivers/clk/hisilicon/clk.c
index 9b15adbfc30c..9ba2d91f4d3a 100644
--- a/drivers/clk/hisilicon/clk.c
+++ b/drivers/clk/hisilicon/clk.c
@@ -37,6 +37,35 @@
 
 static DEFINE_SPINLOCK(hisi_clk_lock);
 
+struct hisi_clock_data *hisi_clk_alloc(struct platform_device *pdev,
+						int nr_clks)
+{
+	struct hisi_clock_data *clk_data;
+	struct resource *res;
+	struct clk **clk_table;
+
+	clk_data = devm_kmalloc(&pdev->dev, sizeof(*clk_data), GFP_KERNEL);
+	if (!clk_data)
+		return NULL;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	clk_data->base = devm_ioremap(&pdev->dev,
+				res->start, resource_size(res));
+	if (!clk_data->base)
+		return NULL;
+
+	clk_table = devm_kmalloc(&pdev->dev, sizeof(struct clk *) * nr_clks,
+				GFP_KERNEL);
+	if (!clk_table)
+		return NULL;
+
+	clk_data->clk_data.clks = clk_table;
+	clk_data->clk_data.clk_num = nr_clks;
+
+	return clk_data;
+}
+EXPORT_SYMBOL_GPL(hisi_clk_alloc);
+
 struct hisi_clock_data *hisi_clk_init(struct device_node *np,
 					     int nr_clks)
 {
@@ -73,7 +102,7 @@ err:
 }
 EXPORT_SYMBOL_GPL(hisi_clk_init);
 
-void hisi_clk_register_fixed_rate(const struct hisi_fixed_rate_clock *clks,
+int hisi_clk_register_fixed_rate(const struct hisi_fixed_rate_clock *clks,
 					 int nums, struct hisi_clock_data *data)
 {
 	struct clk *clk;
@@ -87,14 +116,22 @@ void hisi_clk_register_fixed_rate(const struct hisi_fixed_rate_clock *clks,
 		if (IS_ERR(clk)) {
 			pr_err("%s: failed to register clock %s\n",
 			       __func__, clks[i].name);
-			continue;
+			goto err;
 		}
 		data->clk_data.clks[clks[i].id] = clk;
 	}
+
+	return 0;
+
+err:
+	while (i--)
+		clk_unregister_fixed_rate(data->clk_data.clks[clks[i].id]);
+
+	return PTR_ERR(clk);
 }
 EXPORT_SYMBOL_GPL(hisi_clk_register_fixed_rate);
 
-void hisi_clk_register_fixed_factor(const struct hisi_fixed_factor_clock *clks,
+int hisi_clk_register_fixed_factor(const struct hisi_fixed_factor_clock *clks,
 					   int nums,
 					   struct hisi_clock_data *data)
 {
@@ -109,14 +146,22 @@ void hisi_clk_register_fixed_factor(const struct hisi_fixed_factor_clock *clks,
 		if (IS_ERR(clk)) {
 			pr_err("%s: failed to register clock %s\n",
 			       __func__, clks[i].name);
-			continue;
+			goto err;
 		}
 		data->clk_data.clks[clks[i].id] = clk;
 	}
+
+	return 0;
+
+err:
+	while (i--)
+		clk_unregister_fixed_factor(data->clk_data.clks[clks[i].id]);
+
+	return PTR_ERR(clk);
 }
 EXPORT_SYMBOL_GPL(hisi_clk_register_fixed_factor);
 
-void hisi_clk_register_mux(const struct hisi_mux_clock *clks,
+int hisi_clk_register_mux(const struct hisi_mux_clock *clks,
 				  int nums, struct hisi_clock_data *data)
 {
 	struct clk *clk;
@@ -135,7 +180,7 @@ void hisi_clk_register_mux(const struct hisi_mux_clock *clks,
 		if (IS_ERR(clk)) {
 			pr_err("%s: failed to register clock %s\n",
 			       __func__, clks[i].name);
-			continue;
+			goto err;
 		}
 
 		if (clks[i].alias)
@@ -143,10 +188,18 @@ void hisi_clk_register_mux(const struct hisi_mux_clock *clks,
 
 		data->clk_data.clks[clks[i].id] = clk;
 	}
+
+	return 0;
+
+err:
+	while (i--)
+		clk_unregister_mux(data->clk_data.clks[clks[i].id]);
+
+	return PTR_ERR(clk);
 }
 EXPORT_SYMBOL_GPL(hisi_clk_register_mux);
 
-void hisi_clk_register_divider(const struct hisi_divider_clock *clks,
+int hisi_clk_register_divider(const struct hisi_divider_clock *clks,
 				      int nums, struct hisi_clock_data *data)
 {
 	struct clk *clk;
@@ -165,7 +218,7 @@ void hisi_clk_register_divider(const struct hisi_divider_clock *clks,
 		if (IS_ERR(clk)) {
 			pr_err("%s: failed to register clock %s\n",
 			       __func__, clks[i].name);
-			continue;
+			goto err;
 		}
 
 		if (clks[i].alias)
@@ -173,10 +226,18 @@ void hisi_clk_register_divider(const struct hisi_divider_clock *clks,
 
 		data->clk_data.clks[clks[i].id] = clk;
 	}
+
+	return 0;
+
+err:
+	while (i--)
+		clk_unregister_divider(data->clk_data.clks[clks[i].id]);
+
+	return PTR_ERR(clk);
 }
 EXPORT_SYMBOL_GPL(hisi_clk_register_divider);
 
-void hisi_clk_register_gate(const struct hisi_gate_clock *clks,
+int hisi_clk_register_gate(const struct hisi_gate_clock *clks,
 				       int nums, struct hisi_clock_data *data)
 {
 	struct clk *clk;
@@ -194,7 +255,7 @@ void hisi_clk_register_gate(const struct hisi_gate_clock *clks,
 		if (IS_ERR(clk)) {
 			pr_err("%s: failed to register clock %s\n",
 			       __func__, clks[i].name);
-			continue;
+			goto err;
 		}
 
 		if (clks[i].alias)
@@ -202,6 +263,14 @@ void hisi_clk_register_gate(const struct hisi_gate_clock *clks,
 
 		data->clk_data.clks[clks[i].id] = clk;
 	}
+
+	return 0;
+
+err:
+	while (i--)
+		clk_unregister_gate(data->clk_data.clks[clks[i].id]);
+
+	return PTR_ERR(clk);
 }
 EXPORT_SYMBOL_GPL(hisi_clk_register_gate);
 
diff --git a/drivers/clk/hisilicon/clk.h b/drivers/clk/hisilicon/clk.h
index 20d64afe4ad8..4e1d1affc6f5 100644
--- a/drivers/clk/hisilicon/clk.h
+++ b/drivers/clk/hisilicon/clk.h
@@ -30,6 +30,8 @@
 #include <linux/io.h>
 #include <linux/spinlock.h>
 
+struct platform_device;
+
 struct hisi_clock_data {
 	struct clk_onecell_data	clk_data;
 	void __iomem		*base;
@@ -110,19 +112,41 @@ struct clk *hi6220_register_clkdiv(struct device *dev, const char *name,
 	const char *parent_name, unsigned long flags, void __iomem *reg,
 	u8 shift, u8 width, u32 mask_bit, spinlock_t *lock);
 
+struct hisi_clock_data *hisi_clk_alloc(struct platform_device *, int);
 struct hisi_clock_data *hisi_clk_init(struct device_node *, int);
-void hisi_clk_register_fixed_rate(const struct hisi_fixed_rate_clock *,
+int hisi_clk_register_fixed_rate(const struct hisi_fixed_rate_clock *,
 				int, struct hisi_clock_data *);
-void hisi_clk_register_fixed_factor(const struct hisi_fixed_factor_clock *,
+int hisi_clk_register_fixed_factor(const struct hisi_fixed_factor_clock *,
 				int, struct hisi_clock_data *);
-void hisi_clk_register_mux(const struct hisi_mux_clock *, int,
+int hisi_clk_register_mux(const struct hisi_mux_clock *, int,
 				struct hisi_clock_data *);
-void hisi_clk_register_divider(const struct hisi_divider_clock *,
+int hisi_clk_register_divider(const struct hisi_divider_clock *,
 				int, struct hisi_clock_data *);
-void hisi_clk_register_gate(const struct hisi_gate_clock *,
+int hisi_clk_register_gate(const struct hisi_gate_clock *,
 				int, struct hisi_clock_data *);
 void hisi_clk_register_gate_sep(const struct hisi_gate_clock *,
 				int, struct hisi_clock_data *);
 void hi6220_clk_register_divider(const struct hi6220_divider_clock *,
 				int, struct hisi_clock_data *);
+
+#define hisi_clk_unregister(type) \
+static inline \
+void hisi_clk_unregister_##type(const struct hisi_##type##_clock *clks, \
+				int nums, struct hisi_clock_data *data) \
+{ \
+	struct clk **clocks = data->clk_data.clks; \
+	int i; \
+	for (i = 0; i < nums; i++) { \
+		int id = clks[i].id; \
+		if (clocks[id])  \
+			clk_unregister_##type(clocks[id]); \
+	} \
+}
+
+hisi_clk_unregister(fixed_rate)
+hisi_clk_unregister(fixed_factor)
+hisi_clk_unregister(mux)
+hisi_clk_unregister(divider)
+hisi_clk_unregister(gate)
+
 #endif	/* __HISI_CLK_H */
diff --git a/drivers/clk/hisilicon/clkdivider-hi6220.c b/drivers/clk/hisilicon/clkdivider-hi6220.c
index 113eee8ed23a..a1c1f684ad58 100644
--- a/drivers/clk/hisilicon/clkdivider-hi6220.c
+++ b/drivers/clk/hisilicon/clkdivider-hi6220.c
@@ -18,6 +18,8 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 
+#include "clk.h"
+
 #define div_mask(width)	((1 << (width)) - 1)
 
 /**
diff --git a/drivers/clk/hisilicon/reset.c b/drivers/clk/hisilicon/reset.c
index 6aa49c2204d0..2a5015c736ce 100644
--- a/drivers/clk/hisilicon/reset.c
+++ b/drivers/clk/hisilicon/reset.c
@@ -19,6 +19,7 @@
 
 #include <linux/io.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <linux/reset-controller.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -98,25 +99,25 @@ static const struct reset_control_ops hisi_reset_ops = {
 	.deassert	= hisi_reset_deassert,
 };
 
-struct hisi_reset_controller *hisi_reset_init(struct device_node *np)
+struct hisi_reset_controller *hisi_reset_init(struct platform_device *pdev)
 {
 	struct hisi_reset_controller *rstc;
+	struct resource *res;
 
-	rstc = kzalloc(sizeof(*rstc), GFP_KERNEL);
+	rstc = devm_kmalloc(&pdev->dev, sizeof(*rstc), GFP_KERNEL);
 	if (!rstc)
 		return NULL;
 
-	rstc->membase = of_iomap(np, 0);
-	if (!rstc->membase) {
-		kfree(rstc);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	rstc->membase = devm_ioremap(&pdev->dev,
+				res->start, resource_size(res));
+	if (!rstc->membase)
 		return NULL;
-	}
 
 	spin_lock_init(&rstc->lock);
-
 	rstc->rcdev.owner = THIS_MODULE;
 	rstc->rcdev.ops = &hisi_reset_ops;
-	rstc->rcdev.of_node = np;
+	rstc->rcdev.of_node = pdev->dev.of_node;
 	rstc->rcdev.of_reset_n_cells = 2;
 	rstc->rcdev.of_xlate = hisi_reset_of_xlate;
 	reset_controller_register(&rstc->rcdev);
@@ -128,7 +129,5 @@ EXPORT_SYMBOL_GPL(hisi_reset_init);
 void hisi_reset_exit(struct hisi_reset_controller *rstc)
 {
 	reset_controller_unregister(&rstc->rcdev);
-	iounmap(rstc->membase);
-	kfree(rstc);
 }
 EXPORT_SYMBOL_GPL(hisi_reset_exit);
diff --git a/drivers/clk/hisilicon/reset.h b/drivers/clk/hisilicon/reset.h
index 677d773ed27c..9a69374a0b32 100644
--- a/drivers/clk/hisilicon/reset.h
+++ b/drivers/clk/hisilicon/reset.h
@@ -22,10 +22,11 @@ struct device_node;
 struct hisi_reset_controller;
 
 #ifdef CONFIG_RESET_CONTROLLER
-struct hisi_reset_controller *hisi_reset_init(struct device_node *np);
+struct hisi_reset_controller *hisi_reset_init(struct platform_device *pdev);
 void hisi_reset_exit(struct hisi_reset_controller *rstc);
 #else
-static inline hisi_reset_controller *hisi_reset_init(struct device_node *np)
+static inline
+struct hisi_reset_controller *hisi_reset_init(struct platform_device *pdev)
 {
 	return 0;
 }
diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c
index 2beb396fe652..ba1c1ae72ac2 100644
--- a/drivers/clk/imx/clk-imx6q.c
+++ b/drivers/clk/imx/clk-imx6q.c
@@ -192,13 +192,13 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_PLL7_BYPASS_SRC] = imx_clk_mux("pll7_bypass_src", base + 0x20, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
 
 	/*                                    type               name    parent_name        base         div_mask */
-	clk[IMX6QDL_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,     "pll1", "pll1_bypass_src", base + 0x00, 0x7f);
-	clk[IMX6QDL_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "pll2_bypass_src", base + 0x30, 0x1);
-	clk[IMX6QDL_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll3", "pll3_bypass_src", base + 0x10, 0x3);
-	clk[IMX6QDL_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll4", "pll4_bypass_src", base + 0x70, 0x7f);
-	clk[IMX6QDL_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll5", "pll5_bypass_src", base + 0xa0, 0x7f);
-	clk[IMX6QDL_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,    "pll6", "pll6_bypass_src", base + 0xe0, 0x3);
-	clk[IMX6QDL_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7", "pll7_bypass_src", base + 0x20, 0x3);
+	clk[IMX6QDL_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,     "pll1", "osc", base + 0x00, 0x7f);
+	clk[IMX6QDL_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "osc", base + 0x30, 0x1);
+	clk[IMX6QDL_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll3", "osc", base + 0x10, 0x3);
+	clk[IMX6QDL_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll4", "osc", base + 0x70, 0x7f);
+	clk[IMX6QDL_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll5", "osc", base + 0xa0, 0x7f);
+	clk[IMX6QDL_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,    "pll6", "osc", base + 0xe0, 0x3);
+	clk[IMX6QDL_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7", "osc", base + 0x20, 0x3);
 
 	clk[IMX6QDL_PLL1_BYPASS] = imx_clk_mux_flags("pll1_bypass", base + 0x00, 16, 1, pll1_bypass_sels, ARRAY_SIZE(pll1_bypass_sels), CLK_SET_RATE_PARENT);
 	clk[IMX6QDL_PLL2_BYPASS] = imx_clk_mux_flags("pll2_bypass", base + 0x30, 16, 1, pll2_bypass_sels, ARRAY_SIZE(pll2_bypass_sels), CLK_SET_RATE_PARENT);
diff --git a/drivers/clk/imx/clk-imx6sl.c b/drivers/clk/imx/clk-imx6sl.c
index 1be6230a07af..5fd4ddac1bf1 100644
--- a/drivers/clk/imx/clk-imx6sl.c
+++ b/drivers/clk/imx/clk-imx6sl.c
@@ -218,13 +218,13 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SL_PLL7_BYPASS_SRC] = imx_clk_mux("pll7_bypass_src", base + 0x20, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
 
 	/*                                    type               name    parent_name        base         div_mask */
-	clks[IMX6SL_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,     "pll1", "pll1_bypass_src", base + 0x00, 0x7f);
-	clks[IMX6SL_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "pll2_bypass_src", base + 0x30, 0x1);
-	clks[IMX6SL_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll3", "pll3_bypass_src", base + 0x10, 0x3);
-	clks[IMX6SL_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll4", "pll4_bypass_src", base + 0x70, 0x7f);
-	clks[IMX6SL_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll5", "pll5_bypass_src", base + 0xa0, 0x7f);
-	clks[IMX6SL_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,    "pll6", "pll6_bypass_src", base + 0xe0, 0x3);
-	clks[IMX6SL_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7", "pll7_bypass_src", base + 0x20, 0x3);
+	clks[IMX6SL_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,     "pll1", "osc", base + 0x00, 0x7f);
+	clks[IMX6SL_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "osc", base + 0x30, 0x1);
+	clks[IMX6SL_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll3", "osc", base + 0x10, 0x3);
+	clks[IMX6SL_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll4", "osc", base + 0x70, 0x7f);
+	clks[IMX6SL_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll5", "osc", base + 0xa0, 0x7f);
+	clks[IMX6SL_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,    "pll6", "osc", base + 0xe0, 0x3);
+	clks[IMX6SL_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7", "osc", base + 0x20, 0x3);
 
 	clks[IMX6SL_PLL1_BYPASS] = imx_clk_mux_flags("pll1_bypass", base + 0x00, 16, 1, pll1_bypass_sels, ARRAY_SIZE(pll1_bypass_sels), CLK_SET_RATE_PARENT);
 	clks[IMX6SL_PLL2_BYPASS] = imx_clk_mux_flags("pll2_bypass", base + 0x30, 16, 1, pll2_bypass_sels, ARRAY_SIZE(pll2_bypass_sels), CLK_SET_RATE_PARENT);
diff --git a/drivers/clk/imx/clk-imx6sx.c b/drivers/clk/imx/clk-imx6sx.c
index 97e742a8be17..b5c96de41ccf 100644
--- a/drivers/clk/imx/clk-imx6sx.c
+++ b/drivers/clk/imx/clk-imx6sx.c
@@ -174,13 +174,13 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_PLL7_BYPASS_SRC] = imx_clk_mux("pll7_bypass_src", base + 0x20, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
 
 	/*                                    type               name    parent_name        base         div_mask */
-	clks[IMX6SX_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,     "pll1", "pll1_bypass_src", base + 0x00, 0x7f);
-	clks[IMX6SX_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "pll2_bypass_src", base + 0x30, 0x1);
-	clks[IMX6SX_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll3", "pll3_bypass_src", base + 0x10, 0x3);
-	clks[IMX6SX_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll4", "pll4_bypass_src", base + 0x70, 0x7f);
-	clks[IMX6SX_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll5", "pll5_bypass_src", base + 0xa0, 0x7f);
-	clks[IMX6SX_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,    "pll6", "pll6_bypass_src", base + 0xe0, 0x3);
-	clks[IMX6SX_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7", "pll7_bypass_src", base + 0x20, 0x3);
+	clks[IMX6SX_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,     "pll1", "osc", base + 0x00, 0x7f);
+	clks[IMX6SX_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "osc", base + 0x30, 0x1);
+	clks[IMX6SX_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll3", "osc", base + 0x10, 0x3);
+	clks[IMX6SX_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll4", "osc", base + 0x70, 0x7f);
+	clks[IMX6SX_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll5", "osc", base + 0xa0, 0x7f);
+	clks[IMX6SX_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,    "pll6", "osc", base + 0xe0, 0x3);
+	clks[IMX6SX_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7", "osc", base + 0x20, 0x3);
 
 	clks[IMX6SX_PLL1_BYPASS] = imx_clk_mux_flags("pll1_bypass", base + 0x00, 16, 1, pll1_bypass_sels, ARRAY_SIZE(pll1_bypass_sels), CLK_SET_RATE_PARENT);
 	clks[IMX6SX_PLL2_BYPASS] = imx_clk_mux_flags("pll2_bypass", base + 0x30, 16, 1, pll2_bypass_sels, ARRAY_SIZE(pll2_bypass_sels), CLK_SET_RATE_PARENT);
diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c
index 0f1f17a8f3ed..d1d7787ce211 100644
--- a/drivers/clk/imx/clk-imx6ul.c
+++ b/drivers/clk/imx/clk-imx6ul.c
@@ -130,13 +130,13 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_PLL6_BYPASS_SRC] = imx_clk_mux("pll6_bypass_src", base + 0xe0, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
 	clks[IMX6UL_PLL7_BYPASS_SRC] = imx_clk_mux("pll7_bypass_src", base + 0x20, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
 
-	clks[IMX6UL_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,	 "pll1", "pll1_bypass_src", base + 0x00, 0x7f);
-	clks[IMX6UL_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "pll2_bypass_src", base + 0x30, 0x1);
-	clks[IMX6UL_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,	 "pll3", "pll3_bypass_src", base + 0x10, 0x3);
-	clks[IMX6UL_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,	 "pll4", "pll4_bypass_src", base + 0x70, 0x7f);
-	clks[IMX6UL_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,	 "pll5", "pll5_bypass_src", base + 0xa0, 0x7f);
-	clks[IMX6UL_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,	 "pll6", "pll6_bypass_src", base + 0xe0, 0x3);
-	clks[IMX6UL_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,	 "pll7", "pll7_bypass_src", base + 0x20, 0x3);
+	clks[IMX6UL_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,	 "pll1", "osc", base + 0x00, 0x7f);
+	clks[IMX6UL_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "osc", base + 0x30, 0x1);
+	clks[IMX6UL_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,	 "pll3", "osc", base + 0x10, 0x3);
+	clks[IMX6UL_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,	 "pll4", "osc", base + 0x70, 0x7f);
+	clks[IMX6UL_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,	 "pll5", "osc", base + 0xa0, 0x7f);
+	clks[IMX6UL_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,	 "pll6", "osc", base + 0xe0, 0x3);
+	clks[IMX6UL_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,	 "pll7", "osc", base + 0x20, 0x3);
 
 	clks[IMX6UL_PLL1_BYPASS] = imx_clk_mux_flags("pll1_bypass", base + 0x00, 16, 1, pll1_bypass_sels, ARRAY_SIZE(pll1_bypass_sels), CLK_SET_RATE_PARENT);
 	clks[IMX6UL_PLL2_BYPASS] = imx_clk_mux_flags("pll2_bypass", base + 0x30, 16, 1, pll2_bypass_sels, ARRAY_SIZE(pll2_bypass_sels), CLK_SET_RATE_PARENT);
@@ -305,8 +305,8 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_CAN1_SERIAL]	= imx_clk_gate2("can1_serial",	"can_podf",	base + 0x68,	16);
 	clks[IMX6UL_CLK_CAN2_IPG]	= imx_clk_gate2("can2_ipg",	"ipg",		base + 0x68,	18);
 	clks[IMX6UL_CLK_CAN2_SERIAL]	= imx_clk_gate2("can2_serial",	"can_podf",	base + 0x68,	20);
-	clks[IMX6UL_CLK_GPT2_BUS]	= imx_clk_gate2("gpt_bus",	"perclk",	base + 0x68,	24);
-	clks[IMX6UL_CLK_GPT2_SERIAL]	= imx_clk_gate2("gpt_serial",	"perclk",	base + 0x68,	26);
+	clks[IMX6UL_CLK_GPT2_BUS]	= imx_clk_gate2("gpt2_bus",	"perclk",	base + 0x68,	24);
+	clks[IMX6UL_CLK_GPT2_SERIAL]	= imx_clk_gate2("gpt2_serial",	"perclk",	base + 0x68,	26);
 	clks[IMX6UL_CLK_UART2_IPG]	= imx_clk_gate2("uart2_ipg",	"ipg",		base + 0x68,	28);
 	clks[IMX6UL_CLK_UART2_SERIAL]	= imx_clk_gate2("uart2_serial",	"uart_podf",	base + 0x68,	28);
 	clks[IMX6UL_CLK_AIPSTZ3]	= imx_clk_gate2("aips_tz3",	"ahb",		base + 0x68,	30);
diff --git a/drivers/clk/imx/clk-imx7d.c b/drivers/clk/imx/clk-imx7d.c
index 522996800d5b..6ed4f8fa0667 100644
--- a/drivers/clk/imx/clk-imx7d.c
+++ b/drivers/clk/imx/clk-imx7d.c
@@ -65,7 +65,7 @@ static const char *dram_phym_sel[] = { "pll_dram_main_clk",
 	"dram_phym_alt_clk", };
 
 static const char *dram_sel[] = { "pll_dram_main_clk",
-	"dram_alt_clk", };
+	"dram_alt_root_clk", };
 
 static const char *dram_phym_alt_sel[] = { "osc", "pll_dram_533m_clk",
 	"pll_sys_main_clk", "pll_enet_500m_clk",
@@ -361,6 +361,14 @@ static const char *pll_enet_bypass_sel[] = { "pll_enet_main", "pll_enet_main_src
 static const char *pll_audio_bypass_sel[] = { "pll_audio_main", "pll_audio_main_src", };
 static const char *pll_video_bypass_sel[] = { "pll_video_main", "pll_video_main_src", };
 
+static int const clks_init_on[] __initconst = {
+	IMX7D_ARM_A7_ROOT_CLK, IMX7D_MAIN_AXI_ROOT_CLK,
+	IMX7D_PLL_SYS_MAIN_480M_CLK, IMX7D_NAND_USDHC_BUS_ROOT_CLK,
+	IMX7D_DRAM_PHYM_ROOT_CLK, IMX7D_DRAM_ROOT_CLK,
+	IMX7D_DRAM_PHYM_ALT_ROOT_CLK, IMX7D_DRAM_ALT_ROOT_CLK,
+	IMX7D_AHB_CHANNEL_ROOT_CLK,
+};
+
 static struct clk_onecell_data clk_data;
 
 static struct clk ** const uart_clks[] __initconst = {
@@ -395,12 +403,12 @@ static void __init imx7d_clocks_init(struct device_node *ccm_node)
 	clks[IMX7D_PLL_AUDIO_MAIN_SRC] = imx_clk_mux("pll_audio_main_src", base + 0xf0, 14, 2, pll_bypass_src_sel, ARRAY_SIZE(pll_bypass_src_sel));
 	clks[IMX7D_PLL_VIDEO_MAIN_SRC] = imx_clk_mux("pll_video_main_src", base + 0x130, 14, 2, pll_bypass_src_sel, ARRAY_SIZE(pll_bypass_src_sel));
 
-	clks[IMX7D_PLL_ARM_MAIN]  = imx_clk_pllv3(IMX_PLLV3_SYS, "pll_arm_main", "pll_arm_main_src", base + 0x60, 0x7f);
-	clks[IMX7D_PLL_DRAM_MAIN] = imx_clk_pllv3(IMX_PLLV3_SYS, "pll_dram_main", "pll_dram_main_src", base + 0x70, 0x7f);
-	clks[IMX7D_PLL_SYS_MAIN]  = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll_sys_main", "pll_sys_main_src", base + 0xb0, 0x1);
-	clks[IMX7D_PLL_ENET_MAIN] = imx_clk_pllv3(IMX_PLLV3_ENET_IMX7, "pll_enet_main", "pll_enet_main_src", base + 0xe0, 0x0);
-	clks[IMX7D_PLL_AUDIO_MAIN] = imx_clk_pllv3(IMX_PLLV3_AV, "pll_audio_main", "pll_audio_main_src", base + 0xf0, 0x7f);
-	clks[IMX7D_PLL_VIDEO_MAIN] = imx_clk_pllv3(IMX_PLLV3_AV, "pll_video_main", "pll_video_main_src", base + 0x130, 0x7f);
+	clks[IMX7D_PLL_ARM_MAIN]  = imx_clk_pllv3(IMX_PLLV3_SYS, "pll_arm_main", "osc", base + 0x60, 0x7f);
+	clks[IMX7D_PLL_DRAM_MAIN] = imx_clk_pllv3(IMX_PLLV3_AV, "pll_dram_main", "osc", base + 0x70, 0x7f);
+	clks[IMX7D_PLL_SYS_MAIN]  = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll_sys_main", "osc", base + 0xb0, 0x1);
+	clks[IMX7D_PLL_ENET_MAIN] = imx_clk_pllv3(IMX_PLLV3_ENET_IMX7, "pll_enet_main", "osc", base + 0xe0, 0x0);
+	clks[IMX7D_PLL_AUDIO_MAIN] = imx_clk_pllv3(IMX_PLLV3_AV, "pll_audio_main", "osc", base + 0xf0, 0x7f);
+	clks[IMX7D_PLL_VIDEO_MAIN] = imx_clk_pllv3(IMX_PLLV3_AV, "pll_video_main", "osc", base + 0x130, 0x7f);
 
 	clks[IMX7D_PLL_ARM_MAIN_BYPASS]  = imx_clk_mux_flags("pll_arm_main_bypass", base + 0x60, 16, 1, pll_arm_bypass_sel, ARRAY_SIZE(pll_arm_bypass_sel), CLK_SET_RATE_PARENT);
 	clks[IMX7D_PLL_DRAM_MAIN_BYPASS] = imx_clk_mux_flags("pll_dram_main_bypass", base + 0x70, 16, 1, pll_dram_bypass_sel, ARRAY_SIZE(pll_dram_bypass_sel), CLK_SET_RATE_PARENT);
@@ -474,363 +482,363 @@ static void __init imx7d_clocks_init(struct device_node *ccm_node)
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
 
-	clks[IMX7D_ARM_A7_ROOT_SRC] = imx_clk_mux("arm_a7_src", base + 0x8000, 24, 3, arm_a7_sel, ARRAY_SIZE(arm_a7_sel));
-	clks[IMX7D_ARM_M4_ROOT_SRC] = imx_clk_mux("arm_m4_src", base + 0x8080, 24, 3, arm_m4_sel, ARRAY_SIZE(arm_m4_sel));
-	clks[IMX7D_ARM_M0_ROOT_SRC] = imx_clk_mux("arm_m0_src", base + 0x8100, 24, 3, arm_m0_sel, ARRAY_SIZE(arm_m0_sel));
-	clks[IMX7D_MAIN_AXI_ROOT_SRC] = imx_clk_mux("axi_src", base + 0x8800, 24, 3, axi_sel, ARRAY_SIZE(axi_sel));
-	clks[IMX7D_DISP_AXI_ROOT_SRC] = imx_clk_mux("disp_axi_src", base + 0x8880, 24, 3, disp_axi_sel, ARRAY_SIZE(disp_axi_sel));
-	clks[IMX7D_ENET_AXI_ROOT_SRC] = imx_clk_mux("enet_axi_src", base + 0x8900, 24, 3, enet_axi_sel, ARRAY_SIZE(enet_axi_sel));
-	clks[IMX7D_NAND_USDHC_BUS_ROOT_SRC] = imx_clk_mux("nand_usdhc_src", base + 0x8980, 24, 3, nand_usdhc_bus_sel, ARRAY_SIZE(nand_usdhc_bus_sel));
-	clks[IMX7D_AHB_CHANNEL_ROOT_SRC] = imx_clk_mux("ahb_src", base + 0x9000, 24, 3, ahb_channel_sel, ARRAY_SIZE(ahb_channel_sel));
-	clks[IMX7D_DRAM_PHYM_ROOT_SRC] = imx_clk_mux("dram_phym_src", base + 0x9800, 24, 1, dram_phym_sel, ARRAY_SIZE(dram_phym_sel));
-	clks[IMX7D_DRAM_ROOT_SRC] = imx_clk_mux("dram_src", base + 0x9880, 24, 1, dram_sel, ARRAY_SIZE(dram_sel));
-	clks[IMX7D_DRAM_PHYM_ALT_ROOT_SRC] = imx_clk_mux("dram_phym_alt_src", base + 0xa000, 24, 3, dram_phym_alt_sel, ARRAY_SIZE(dram_phym_alt_sel));
-	clks[IMX7D_DRAM_ALT_ROOT_SRC]  = imx_clk_mux("dram_alt_src", base + 0xa080, 24, 3, dram_alt_sel, ARRAY_SIZE(dram_alt_sel));
-	clks[IMX7D_USB_HSIC_ROOT_SRC] = imx_clk_mux("usb_hsic_src", base + 0xa100, 24, 3, usb_hsic_sel, ARRAY_SIZE(usb_hsic_sel));
-	clks[IMX7D_PCIE_CTRL_ROOT_SRC] = imx_clk_mux("pcie_ctrl_src", base + 0xa180, 24, 3, pcie_ctrl_sel, ARRAY_SIZE(pcie_ctrl_sel));
-	clks[IMX7D_PCIE_PHY_ROOT_SRC] = imx_clk_mux("pcie_phy_src", base + 0xa200, 24, 3, pcie_phy_sel, ARRAY_SIZE(pcie_phy_sel));
-	clks[IMX7D_EPDC_PIXEL_ROOT_SRC] = imx_clk_mux("epdc_pixel_src", base + 0xa280, 24, 3, epdc_pixel_sel, ARRAY_SIZE(epdc_pixel_sel));
-	clks[IMX7D_LCDIF_PIXEL_ROOT_SRC] = imx_clk_mux("lcdif_pixel_src", base + 0xa300, 24, 3, lcdif_pixel_sel, ARRAY_SIZE(lcdif_pixel_sel));
-	clks[IMX7D_MIPI_DSI_ROOT_SRC] = imx_clk_mux("mipi_dsi_src", base + 0xa380, 24, 3,  mipi_dsi_sel, ARRAY_SIZE(mipi_dsi_sel));
-	clks[IMX7D_MIPI_CSI_ROOT_SRC] = imx_clk_mux("mipi_csi_src", base + 0xa400, 24, 3, mipi_csi_sel, ARRAY_SIZE(mipi_csi_sel));
-	clks[IMX7D_MIPI_DPHY_ROOT_SRC] = imx_clk_mux("mipi_dphy_src", base + 0xa480, 24, 3, mipi_dphy_sel, ARRAY_SIZE(mipi_dphy_sel));
-	clks[IMX7D_SAI1_ROOT_SRC] = imx_clk_mux("sai1_src", base + 0xa500, 24, 3, sai1_sel, ARRAY_SIZE(sai1_sel));
-	clks[IMX7D_SAI2_ROOT_SRC] = imx_clk_mux("sai2_src", base + 0xa580, 24, 3, sai2_sel, ARRAY_SIZE(sai2_sel));
-	clks[IMX7D_SAI3_ROOT_SRC] = imx_clk_mux("sai3_src", base + 0xa600, 24, 3, sai3_sel, ARRAY_SIZE(sai3_sel));
-	clks[IMX7D_SPDIF_ROOT_SRC] = imx_clk_mux("spdif_src", base + 0xa680, 24, 3, spdif_sel, ARRAY_SIZE(spdif_sel));
-	clks[IMX7D_ENET1_REF_ROOT_SRC] = imx_clk_mux("enet1_ref_src", base + 0xa700, 24, 3, enet1_ref_sel, ARRAY_SIZE(enet1_ref_sel));
-	clks[IMX7D_ENET1_TIME_ROOT_SRC] = imx_clk_mux("enet1_time_src", base + 0xa780, 24, 3, enet1_time_sel, ARRAY_SIZE(enet1_time_sel));
-	clks[IMX7D_ENET2_REF_ROOT_SRC] = imx_clk_mux("enet2_ref_src", base + 0xa800, 24, 3, enet2_ref_sel, ARRAY_SIZE(enet2_ref_sel));
-	clks[IMX7D_ENET2_TIME_ROOT_SRC] = imx_clk_mux("enet2_time_src", base + 0xa880, 24, 3, enet2_time_sel, ARRAY_SIZE(enet2_time_sel));
-	clks[IMX7D_ENET_PHY_REF_ROOT_SRC] = imx_clk_mux("enet_phy_ref_src", base + 0xa900, 24, 3, enet_phy_ref_sel, ARRAY_SIZE(enet_phy_ref_sel));
-	clks[IMX7D_EIM_ROOT_SRC] = imx_clk_mux("eim_src", base + 0xa980, 24, 3, eim_sel, ARRAY_SIZE(eim_sel));
-	clks[IMX7D_NAND_ROOT_SRC] = imx_clk_mux("nand_src", base + 0xaa00, 24, 3, nand_sel, ARRAY_SIZE(nand_sel));
-	clks[IMX7D_QSPI_ROOT_SRC] = imx_clk_mux("qspi_src", base + 0xaa80, 24, 3, qspi_sel, ARRAY_SIZE(qspi_sel));
-	clks[IMX7D_USDHC1_ROOT_SRC] = imx_clk_mux("usdhc1_src", base + 0xab00, 24, 3, usdhc1_sel, ARRAY_SIZE(usdhc1_sel));
-	clks[IMX7D_USDHC2_ROOT_SRC] = imx_clk_mux("usdhc2_src", base + 0xab80, 24, 3, usdhc2_sel, ARRAY_SIZE(usdhc2_sel));
-	clks[IMX7D_USDHC3_ROOT_SRC] = imx_clk_mux("usdhc3_src", base + 0xac00, 24, 3, usdhc3_sel, ARRAY_SIZE(usdhc3_sel));
-	clks[IMX7D_CAN1_ROOT_SRC] = imx_clk_mux("can1_src", base + 0xac80, 24, 3, can1_sel, ARRAY_SIZE(can1_sel));
-	clks[IMX7D_CAN2_ROOT_SRC] = imx_clk_mux("can2_src", base + 0xad00, 24, 3, can2_sel, ARRAY_SIZE(can2_sel));
-	clks[IMX7D_I2C1_ROOT_SRC] = imx_clk_mux("i2c1_src", base + 0xad80, 24, 3, i2c1_sel, ARRAY_SIZE(i2c1_sel));
-	clks[IMX7D_I2C2_ROOT_SRC] = imx_clk_mux("i2c2_src", base + 0xae00, 24, 3, i2c2_sel, ARRAY_SIZE(i2c2_sel));
-	clks[IMX7D_I2C3_ROOT_SRC] = imx_clk_mux("i2c3_src", base + 0xae80, 24, 3, i2c3_sel, ARRAY_SIZE(i2c3_sel));
-	clks[IMX7D_I2C4_ROOT_SRC] = imx_clk_mux("i2c4_src", base + 0xaf00, 24, 3, i2c4_sel, ARRAY_SIZE(i2c4_sel));
-	clks[IMX7D_UART1_ROOT_SRC] = imx_clk_mux("uart1_src", base + 0xaf80, 24, 3, uart1_sel, ARRAY_SIZE(uart1_sel));
-	clks[IMX7D_UART2_ROOT_SRC] = imx_clk_mux("uart2_src", base + 0xb000, 24, 3, uart2_sel, ARRAY_SIZE(uart2_sel));
-	clks[IMX7D_UART3_ROOT_SRC] = imx_clk_mux("uart3_src", base + 0xb080, 24, 3, uart3_sel, ARRAY_SIZE(uart3_sel));
-	clks[IMX7D_UART4_ROOT_SRC] = imx_clk_mux("uart4_src", base + 0xb100, 24, 3, uart4_sel, ARRAY_SIZE(uart4_sel));
-	clks[IMX7D_UART5_ROOT_SRC] = imx_clk_mux("uart5_src", base + 0xb180, 24, 3, uart5_sel, ARRAY_SIZE(uart5_sel));
-	clks[IMX7D_UART6_ROOT_SRC] = imx_clk_mux("uart6_src", base + 0xb200, 24, 3, uart6_sel, ARRAY_SIZE(uart6_sel));
-	clks[IMX7D_UART7_ROOT_SRC] = imx_clk_mux("uart7_src", base + 0xb280, 24, 3, uart7_sel, ARRAY_SIZE(uart7_sel));
-	clks[IMX7D_ECSPI1_ROOT_SRC] = imx_clk_mux("ecspi1_src", base + 0xb300, 24, 3, ecspi1_sel, ARRAY_SIZE(ecspi1_sel));
-	clks[IMX7D_ECSPI2_ROOT_SRC] = imx_clk_mux("ecspi2_src", base + 0xb380, 24, 3, ecspi2_sel, ARRAY_SIZE(ecspi2_sel));
-	clks[IMX7D_ECSPI3_ROOT_SRC] = imx_clk_mux("ecspi3_src", base + 0xb400, 24, 3, ecspi3_sel, ARRAY_SIZE(ecspi3_sel));
-	clks[IMX7D_ECSPI4_ROOT_SRC] = imx_clk_mux("ecspi4_src", base + 0xb480, 24, 3, ecspi4_sel, ARRAY_SIZE(ecspi4_sel));
-	clks[IMX7D_PWM1_ROOT_SRC] = imx_clk_mux("pwm1_src", base + 0xb500, 24, 3, pwm1_sel, ARRAY_SIZE(pwm1_sel));
-	clks[IMX7D_PWM2_ROOT_SRC] = imx_clk_mux("pwm2_src", base + 0xb580, 24, 3, pwm2_sel, ARRAY_SIZE(pwm2_sel));
-	clks[IMX7D_PWM3_ROOT_SRC] = imx_clk_mux("pwm3_src", base + 0xb600, 24, 3, pwm3_sel, ARRAY_SIZE(pwm3_sel));
-	clks[IMX7D_PWM4_ROOT_SRC] = imx_clk_mux("pwm4_src", base + 0xb680, 24, 3, pwm4_sel, ARRAY_SIZE(pwm4_sel));
-	clks[IMX7D_FLEXTIMER1_ROOT_SRC] = imx_clk_mux("flextimer1_src", base + 0xb700, 24, 3, flextimer1_sel, ARRAY_SIZE(flextimer1_sel));
-	clks[IMX7D_FLEXTIMER2_ROOT_SRC] = imx_clk_mux("flextimer2_src", base + 0xb780, 24, 3, flextimer2_sel, ARRAY_SIZE(flextimer2_sel));
-	clks[IMX7D_SIM1_ROOT_SRC] = imx_clk_mux("sim1_src", base + 0xb800, 24, 3, sim1_sel, ARRAY_SIZE(sim1_sel));
-	clks[IMX7D_SIM2_ROOT_SRC] = imx_clk_mux("sim2_src", base + 0xb880, 24, 3, sim2_sel, ARRAY_SIZE(sim2_sel));
-	clks[IMX7D_GPT1_ROOT_SRC] = imx_clk_mux("gpt1_src", base + 0xb900, 24, 3, gpt1_sel, ARRAY_SIZE(gpt1_sel));
-	clks[IMX7D_GPT2_ROOT_SRC] = imx_clk_mux("gpt2_src", base + 0xb980, 24, 3, gpt2_sel, ARRAY_SIZE(gpt2_sel));
-	clks[IMX7D_GPT3_ROOT_SRC] = imx_clk_mux("gpt3_src", base + 0xba00, 24, 3, gpt3_sel, ARRAY_SIZE(gpt3_sel));
-	clks[IMX7D_GPT4_ROOT_SRC] = imx_clk_mux("gpt4_src", base + 0xba80, 24, 3, gpt4_sel, ARRAY_SIZE(gpt4_sel));
-	clks[IMX7D_TRACE_ROOT_SRC] = imx_clk_mux("trace_src", base + 0xbb00, 24, 3, trace_sel, ARRAY_SIZE(trace_sel));
-	clks[IMX7D_WDOG_ROOT_SRC] = imx_clk_mux("wdog_src", base + 0xbb80, 24, 3, wdog_sel, ARRAY_SIZE(wdog_sel));
-	clks[IMX7D_CSI_MCLK_ROOT_SRC] = imx_clk_mux("csi_mclk_src", base + 0xbc00, 24, 3, csi_mclk_sel, ARRAY_SIZE(csi_mclk_sel));
-	clks[IMX7D_AUDIO_MCLK_ROOT_SRC] = imx_clk_mux("audio_mclk_src", base + 0xbc80, 24, 3, audio_mclk_sel, ARRAY_SIZE(audio_mclk_sel));
-	clks[IMX7D_WRCLK_ROOT_SRC] = imx_clk_mux("wrclk_src", base + 0xbd00, 24, 3, wrclk_sel, ARRAY_SIZE(wrclk_sel));
-	clks[IMX7D_CLKO1_ROOT_SRC] = imx_clk_mux("clko1_src", base + 0xbd80, 24, 3, clko1_sel, ARRAY_SIZE(clko1_sel));
-	clks[IMX7D_CLKO2_ROOT_SRC] = imx_clk_mux("clko2_src", base + 0xbe00, 24, 3, clko2_sel, ARRAY_SIZE(clko2_sel));
-
-	clks[IMX7D_ARM_A7_ROOT_CG] = imx_clk_gate("arm_a7_cg", "arm_a7_src", base + 0x8000, 28);
-	clks[IMX7D_ARM_M4_ROOT_CG] = imx_clk_gate("arm_m4_cg", "arm_m4_src", base + 0x8080, 28);
-	clks[IMX7D_ARM_M0_ROOT_CG] = imx_clk_gate("arm_m0_cg", "arm_m0_src", base + 0x8100, 28);
-	clks[IMX7D_MAIN_AXI_ROOT_CG] = imx_clk_gate("axi_cg", "axi_src", base + 0x8800, 28);
-	clks[IMX7D_DISP_AXI_ROOT_CG] = imx_clk_gate("disp_axi_cg", "disp_axi_src", base + 0x8880, 28);
-	clks[IMX7D_ENET_AXI_ROOT_CG] = imx_clk_gate("enet_axi_cg", "enet_axi_src", base + 0x8900, 28);
-	clks[IMX7D_NAND_USDHC_BUS_ROOT_CG] = imx_clk_gate("nand_usdhc_cg", "nand_usdhc_src", base + 0x8980, 28);
-	clks[IMX7D_AHB_CHANNEL_ROOT_CG] = imx_clk_gate("ahb_cg", "ahb_src", base + 0x9000, 28);
-	clks[IMX7D_DRAM_PHYM_ROOT_CG] = imx_clk_gate("dram_phym_cg", "dram_phym_src", base + 0x9800, 28);
-	clks[IMX7D_DRAM_ROOT_CG] = imx_clk_gate("dram_cg", "dram_src", base + 0x9880, 28);
-	clks[IMX7D_DRAM_PHYM_ALT_ROOT_CG] = imx_clk_gate("dram_phym_alt_cg", "dram_phym_alt_src", base + 0xa000, 28);
-	clks[IMX7D_DRAM_ALT_ROOT_CG] = imx_clk_gate("dram_alt_cg", "dram_alt_src", base + 0xa080, 28);
-	clks[IMX7D_USB_HSIC_ROOT_CG] = imx_clk_gate("usb_hsic_cg", "usb_hsic_src", base + 0xa100, 28);
-	clks[IMX7D_PCIE_CTRL_ROOT_CG] = imx_clk_gate("pcie_ctrl_cg", "pcie_ctrl_src", base + 0xa180, 28);
-	clks[IMX7D_PCIE_PHY_ROOT_CG] = imx_clk_gate("pcie_phy_cg", "pcie_phy_src", base + 0xa200, 28);
-	clks[IMX7D_EPDC_PIXEL_ROOT_CG] = imx_clk_gate("epdc_pixel_cg", "epdc_pixel_src", base + 0xa280, 28);
-	clks[IMX7D_LCDIF_PIXEL_ROOT_CG] = imx_clk_gate("lcdif_pixel_cg", "lcdif_pixel_src", base + 0xa300, 28);
-	clks[IMX7D_MIPI_DSI_ROOT_CG] = imx_clk_gate("mipi_dsi_cg", "mipi_dsi_src", base + 0xa380, 28);
-	clks[IMX7D_MIPI_CSI_ROOT_CG] = imx_clk_gate("mipi_csi_cg", "mipi_csi_src", base + 0xa400, 28);
-	clks[IMX7D_MIPI_DPHY_ROOT_CG] = imx_clk_gate("mipi_dphy_cg", "mipi_dphy_src", base + 0xa480, 28);
-	clks[IMX7D_SAI1_ROOT_CG] = imx_clk_gate("sai1_cg", "sai1_src", base + 0xa500, 28);
-	clks[IMX7D_SAI2_ROOT_CG] = imx_clk_gate("sai2_cg", "sai2_src", base + 0xa580, 28);
-	clks[IMX7D_SAI3_ROOT_CG] = imx_clk_gate("sai3_cg", "sai3_src", base + 0xa600, 28);
-	clks[IMX7D_SPDIF_ROOT_CG] = imx_clk_gate("spdif_cg", "spdif_src", base + 0xa680, 28);
-	clks[IMX7D_ENET1_REF_ROOT_CG] = imx_clk_gate("enet1_ref_cg", "enet1_ref_src", base + 0xa700, 28);
-	clks[IMX7D_ENET1_TIME_ROOT_CG] = imx_clk_gate("enet1_time_cg", "enet1_time_src", base + 0xa780, 28);
-	clks[IMX7D_ENET2_REF_ROOT_CG] = imx_clk_gate("enet2_ref_cg", "enet2_ref_src", base + 0xa800, 28);
-	clks[IMX7D_ENET2_TIME_ROOT_CG] = imx_clk_gate("enet2_time_cg", "enet2_time_src", base + 0xa880, 28);
-	clks[IMX7D_ENET_PHY_REF_ROOT_CG] = imx_clk_gate("enet_phy_ref_cg", "enet_phy_ref_src", base + 0xa900, 28);
-	clks[IMX7D_EIM_ROOT_CG] = imx_clk_gate("eim_cg", "eim_src", base + 0xa980, 28);
-	clks[IMX7D_NAND_ROOT_CG] = imx_clk_gate("nand_cg", "nand_src", base + 0xaa00, 28);
-	clks[IMX7D_QSPI_ROOT_CG] = imx_clk_gate("qspi_cg", "qspi_src", base + 0xaa80, 28);
-	clks[IMX7D_USDHC1_ROOT_CG] = imx_clk_gate("usdhc1_cg", "usdhc1_src", base + 0xab00, 28);
-	clks[IMX7D_USDHC2_ROOT_CG] = imx_clk_gate("usdhc2_cg", "usdhc2_src", base + 0xab80, 28);
-	clks[IMX7D_USDHC3_ROOT_CG] = imx_clk_gate("usdhc3_cg", "usdhc3_src", base + 0xac00, 28);
-	clks[IMX7D_CAN1_ROOT_CG] = imx_clk_gate("can1_cg", "can1_src", base + 0xac80, 28);
-	clks[IMX7D_CAN2_ROOT_CG] = imx_clk_gate("can2_cg", "can2_src", base + 0xad00, 28);
-	clks[IMX7D_I2C1_ROOT_CG] = imx_clk_gate("i2c1_cg", "i2c1_src", base + 0xad80, 28);
-	clks[IMX7D_I2C2_ROOT_CG] = imx_clk_gate("i2c2_cg", "i2c2_src", base + 0xae00, 28);
-	clks[IMX7D_I2C3_ROOT_CG] = imx_clk_gate("i2c3_cg", "i2c3_src", base + 0xae80, 28);
-	clks[IMX7D_I2C4_ROOT_CG] = imx_clk_gate("i2c4_cg", "i2c4_src", base + 0xaf00, 28);
-	clks[IMX7D_UART1_ROOT_CG] = imx_clk_gate("uart1_cg", "uart1_src", base + 0xaf80, 28);
-	clks[IMX7D_UART2_ROOT_CG] = imx_clk_gate("uart2_cg", "uart2_src", base + 0xb000, 28);
-	clks[IMX7D_UART3_ROOT_CG] = imx_clk_gate("uart3_cg", "uart3_src", base + 0xb080, 28);
-	clks[IMX7D_UART4_ROOT_CG] = imx_clk_gate("uart4_cg", "uart4_src", base + 0xb100, 28);
-	clks[IMX7D_UART5_ROOT_CG] = imx_clk_gate("uart5_cg", "uart5_src", base + 0xb180, 28);
-	clks[IMX7D_UART6_ROOT_CG] = imx_clk_gate("uart6_cg", "uart6_src", base + 0xb200, 28);
-	clks[IMX7D_UART7_ROOT_CG] = imx_clk_gate("uart7_cg", "uart7_src", base + 0xb280, 28);
-	clks[IMX7D_ECSPI1_ROOT_CG] = imx_clk_gate("ecspi1_cg", "ecspi1_src", base + 0xb300, 28);
-	clks[IMX7D_ECSPI2_ROOT_CG] = imx_clk_gate("ecspi2_cg", "ecspi2_src", base + 0xb380, 28);
-	clks[IMX7D_ECSPI3_ROOT_CG] = imx_clk_gate("ecspi3_cg", "ecspi3_src", base + 0xb400, 28);
-	clks[IMX7D_ECSPI4_ROOT_CG] = imx_clk_gate("ecspi4_cg", "ecspi4_src", base + 0xb480, 28);
-	clks[IMX7D_PWM1_ROOT_CG] = imx_clk_gate("pwm1_cg", "pwm1_src", base + 0xb500, 28);
-	clks[IMX7D_PWM2_ROOT_CG] = imx_clk_gate("pwm2_cg", "pwm2_src", base + 0xb580, 28);
-	clks[IMX7D_PWM3_ROOT_CG] = imx_clk_gate("pwm3_cg", "pwm3_src", base + 0xb600, 28);
-	clks[IMX7D_PWM4_ROOT_CG] = imx_clk_gate("pwm4_cg", "pwm4_src", base + 0xb680, 28);
-	clks[IMX7D_FLEXTIMER1_ROOT_CG] = imx_clk_gate("flextimer1_cg", "flextimer1_src", base + 0xb700, 28);
-	clks[IMX7D_FLEXTIMER2_ROOT_CG] = imx_clk_gate("flextimer2_cg", "flextimer2_src", base + 0xb780, 28);
-	clks[IMX7D_SIM1_ROOT_CG] = imx_clk_gate("sim1_cg", "sim1_src", base + 0xb800, 28);
-	clks[IMX7D_SIM2_ROOT_CG] = imx_clk_gate("sim2_cg", "sim2_src", base + 0xb880, 28);
-	clks[IMX7D_GPT1_ROOT_CG] = imx_clk_gate("gpt1_cg", "gpt1_src", base + 0xb900, 28);
-	clks[IMX7D_GPT2_ROOT_CG] = imx_clk_gate("gpt2_cg", "gpt2_src", base + 0xb980, 28);
-	clks[IMX7D_GPT3_ROOT_CG] = imx_clk_gate("gpt3_cg", "gpt3_src", base + 0xbA00, 28);
-	clks[IMX7D_GPT4_ROOT_CG] = imx_clk_gate("gpt4_cg", "gpt4_src", base + 0xbA80, 28);
-	clks[IMX7D_TRACE_ROOT_CG] = imx_clk_gate("trace_cg", "trace_src", base + 0xbb00, 28);
-	clks[IMX7D_WDOG_ROOT_CG] = imx_clk_gate("wdog_cg", "wdog_src", base + 0xbb80, 28);
-	clks[IMX7D_CSI_MCLK_ROOT_CG] = imx_clk_gate("csi_mclk_cg", "csi_mclk_src", base + 0xbc00, 28);
-	clks[IMX7D_AUDIO_MCLK_ROOT_CG] = imx_clk_gate("audio_mclk_cg", "audio_mclk_src", base + 0xbc80, 28);
-	clks[IMX7D_WRCLK_ROOT_CG] = imx_clk_gate("wrclk_cg", "wrclk_src", base + 0xbd00, 28);
-	clks[IMX7D_CLKO1_ROOT_CG] = imx_clk_gate("clko1_cg", "clko1_src", base + 0xbd80, 28);
-	clks[IMX7D_CLKO2_ROOT_CG] = imx_clk_gate("clko2_cg", "clko2_src", base + 0xbe00, 28);
-
-	clks[IMX7D_MAIN_AXI_ROOT_PRE_DIV] = imx_clk_divider("axi_pre_div", "axi_cg", base + 0x8800, 16, 3);
-	clks[IMX7D_DISP_AXI_ROOT_PRE_DIV] = imx_clk_divider("disp_axi_pre_div", "disp_axi_cg", base + 0x8880, 16, 3);
-	clks[IMX7D_ENET_AXI_ROOT_PRE_DIV] = imx_clk_divider("enet_axi_pre_div", "enet_axi_cg", base + 0x8900, 16, 3);
-	clks[IMX7D_NAND_USDHC_BUS_ROOT_PRE_DIV] = imx_clk_divider("nand_usdhc_pre_div", "nand_usdhc_cg", base + 0x8980, 16, 3);
-	clks[IMX7D_AHB_CHANNEL_ROOT_PRE_DIV] = imx_clk_divider("ahb_pre_div", "ahb_cg", base + 0x9000, 16, 3);
-	clks[IMX7D_DRAM_PHYM_ALT_ROOT_PRE_DIV] = imx_clk_divider("dram_phym_alt_pre_div", "dram_phym_alt_cg", base + 0xa000, 16, 3);
-	clks[IMX7D_DRAM_ALT_ROOT_PRE_DIV] = imx_clk_divider("dram_alt_pre_div", "dram_alt_cg", base + 0xa080, 16, 3);
-	clks[IMX7D_USB_HSIC_ROOT_PRE_DIV] = imx_clk_divider("usb_hsic_pre_div", "usb_hsic_cg", base + 0xa100, 16, 3);
-	clks[IMX7D_PCIE_CTRL_ROOT_PRE_DIV] = imx_clk_divider("pcie_ctrl_pre_div", "pcie_ctrl_cg", base + 0xa180, 16, 3);
-	clks[IMX7D_PCIE_PHY_ROOT_PRE_DIV] = imx_clk_divider("pcie_phy_pre_div", "pcie_phy_cg", base + 0xa200, 16, 3);
-	clks[IMX7D_EPDC_PIXEL_ROOT_PRE_DIV] = imx_clk_divider("epdc_pixel_pre_div", "epdc_pixel_cg", base + 0xa280, 16, 3);
-	clks[IMX7D_LCDIF_PIXEL_ROOT_PRE_DIV] = imx_clk_divider("lcdif_pixel_pre_div", "lcdif_pixel_cg", base + 0xa300, 16, 3);
-	clks[IMX7D_MIPI_DSI_ROOT_PRE_DIV] = imx_clk_divider("mipi_dsi_pre_div", "mipi_dsi_cg", base + 0xa380, 16, 3);
-	clks[IMX7D_MIPI_CSI_ROOT_PRE_DIV] = imx_clk_divider("mipi_csi_pre_div", "mipi_csi_cg", base + 0xa400, 16, 3);
-	clks[IMX7D_MIPI_DPHY_ROOT_PRE_DIV] = imx_clk_divider("mipi_dphy_pre_div", "mipi_dphy_cg", base + 0xa480, 16, 3);
-	clks[IMX7D_SAI1_ROOT_PRE_DIV] = imx_clk_divider("sai1_pre_div", "sai1_cg", base + 0xa500, 16, 3);
-	clks[IMX7D_SAI2_ROOT_PRE_DIV] = imx_clk_divider("sai2_pre_div", "sai2_cg", base + 0xa580, 16, 3);
-	clks[IMX7D_SAI3_ROOT_PRE_DIV] = imx_clk_divider("sai3_pre_div", "sai3_cg", base + 0xa600, 16, 3);
-	clks[IMX7D_SPDIF_ROOT_PRE_DIV] = imx_clk_divider("spdif_pre_div", "spdif_cg", base + 0xa680, 16, 3);
-	clks[IMX7D_ENET1_REF_ROOT_PRE_DIV] = imx_clk_divider("enet1_ref_pre_div", "enet1_ref_cg", base + 0xa700, 16, 3);
-	clks[IMX7D_ENET1_TIME_ROOT_PRE_DIV] = imx_clk_divider("enet1_time_pre_div", "enet1_time_cg", base + 0xa780, 16, 3);
-	clks[IMX7D_ENET2_REF_ROOT_PRE_DIV] = imx_clk_divider("enet2_ref_pre_div", "enet2_ref_cg", base + 0xa800, 16, 3);
-	clks[IMX7D_ENET2_TIME_ROOT_PRE_DIV] = imx_clk_divider("enet2_time_pre_div", "enet2_time_cg", base + 0xa880, 16, 3);
-	clks[IMX7D_ENET_PHY_REF_ROOT_PRE_DIV] = imx_clk_divider("enet_phy_ref_pre_div", "enet_phy_ref_cg", base + 0xa900, 16, 3);
-	clks[IMX7D_EIM_ROOT_PRE_DIV] = imx_clk_divider("eim_pre_div", "eim_cg", base + 0xa980, 16, 3);
-	clks[IMX7D_NAND_ROOT_PRE_DIV] = imx_clk_divider("nand_pre_div", "nand_cg", base + 0xaa00, 16, 3);
-	clks[IMX7D_QSPI_ROOT_PRE_DIV] = imx_clk_divider("qspi_pre_div", "qspi_cg", base + 0xaa80, 16, 3);
-	clks[IMX7D_USDHC1_ROOT_PRE_DIV] = imx_clk_divider("usdhc1_pre_div", "usdhc1_cg", base + 0xab00, 16, 3);
-	clks[IMX7D_USDHC2_ROOT_PRE_DIV] = imx_clk_divider("usdhc2_pre_div", "usdhc2_cg", base + 0xab80, 16, 3);
-	clks[IMX7D_USDHC3_ROOT_PRE_DIV] = imx_clk_divider("usdhc3_pre_div", "usdhc3_cg", base + 0xac00, 16, 3);
-	clks[IMX7D_CAN1_ROOT_PRE_DIV] = imx_clk_divider("can1_pre_div", "can1_cg", base + 0xac80, 16, 3);
-	clks[IMX7D_CAN2_ROOT_PRE_DIV] = imx_clk_divider("can2_pre_div", "can2_cg", base + 0xad00, 16, 3);
-	clks[IMX7D_I2C1_ROOT_PRE_DIV] = imx_clk_divider("i2c1_pre_div", "i2c1_cg", base + 0xad80, 16, 3);
-	clks[IMX7D_I2C2_ROOT_PRE_DIV] = imx_clk_divider("i2c2_pre_div", "i2c2_cg", base + 0xae00, 16, 3);
-	clks[IMX7D_I2C3_ROOT_PRE_DIV] = imx_clk_divider("i2c3_pre_div", "i2c3_cg", base + 0xae80, 16, 3);
-	clks[IMX7D_I2C4_ROOT_PRE_DIV] = imx_clk_divider("i2c4_pre_div", "i2c4_cg", base + 0xaf00, 16, 3);
-	clks[IMX7D_UART1_ROOT_PRE_DIV] = imx_clk_divider("uart1_pre_div", "uart1_cg", base + 0xaf80, 16, 3);
-	clks[IMX7D_UART2_ROOT_PRE_DIV] = imx_clk_divider("uart2_pre_div", "uart2_cg", base + 0xb000, 16, 3);
-	clks[IMX7D_UART3_ROOT_PRE_DIV] = imx_clk_divider("uart3_pre_div", "uart3_cg", base + 0xb080, 16, 3);
-	clks[IMX7D_UART4_ROOT_PRE_DIV] = imx_clk_divider("uart4_pre_div", "uart4_cg", base + 0xb100, 16, 3);
-	clks[IMX7D_UART5_ROOT_PRE_DIV] = imx_clk_divider("uart5_pre_div", "uart5_cg", base + 0xb180, 16, 3);
-	clks[IMX7D_UART6_ROOT_PRE_DIV] = imx_clk_divider("uart6_pre_div", "uart6_cg", base + 0xb200, 16, 3);
-	clks[IMX7D_UART7_ROOT_PRE_DIV] = imx_clk_divider("uart7_pre_div", "uart7_cg", base + 0xb280, 16, 3);
-	clks[IMX7D_ECSPI1_ROOT_PRE_DIV] = imx_clk_divider("ecspi1_pre_div", "ecspi1_cg", base + 0xb300, 16, 3);
-	clks[IMX7D_ECSPI2_ROOT_PRE_DIV] = imx_clk_divider("ecspi2_pre_div", "ecspi2_cg", base + 0xb380, 16, 3);
-	clks[IMX7D_ECSPI3_ROOT_PRE_DIV] = imx_clk_divider("ecspi3_pre_div", "ecspi3_cg", base + 0xb400, 16, 3);
-	clks[IMX7D_ECSPI4_ROOT_PRE_DIV] = imx_clk_divider("ecspi4_pre_div", "ecspi4_cg", base + 0xb480, 16, 3);
-	clks[IMX7D_PWM1_ROOT_PRE_DIV] = imx_clk_divider("pwm1_pre_div", "pwm1_cg", base + 0xb500, 16, 3);
-	clks[IMX7D_PWM2_ROOT_PRE_DIV] = imx_clk_divider("pwm2_pre_div", "pwm2_cg", base + 0xb580, 16, 3);
-	clks[IMX7D_PWM3_ROOT_PRE_DIV] = imx_clk_divider("pwm3_pre_div", "pwm3_cg", base + 0xb600, 16, 3);
-	clks[IMX7D_PWM4_ROOT_PRE_DIV] = imx_clk_divider("pwm4_pre_div", "pwm4_cg", base + 0xb680, 16, 3);
-	clks[IMX7D_FLEXTIMER1_ROOT_PRE_DIV] = imx_clk_divider("flextimer1_pre_div", "flextimer1_cg", base + 0xb700, 16, 3);
-	clks[IMX7D_FLEXTIMER2_ROOT_PRE_DIV] = imx_clk_divider("flextimer2_pre_div", "flextimer2_cg", base + 0xb780, 16, 3);
-	clks[IMX7D_SIM1_ROOT_PRE_DIV] = imx_clk_divider("sim1_pre_div", "sim1_cg", base + 0xb800, 16, 3);
-	clks[IMX7D_SIM2_ROOT_PRE_DIV] = imx_clk_divider("sim2_pre_div", "sim2_cg", base + 0xb880, 16, 3);
-	clks[IMX7D_GPT1_ROOT_PRE_DIV] = imx_clk_divider("gpt1_pre_div", "gpt1_cg", base + 0xb900, 16, 3);
-	clks[IMX7D_GPT2_ROOT_PRE_DIV] = imx_clk_divider("gpt2_pre_div", "gpt2_cg", base + 0xb980, 16, 3);
-	clks[IMX7D_GPT3_ROOT_PRE_DIV] = imx_clk_divider("gpt3_pre_div", "gpt3_cg", base + 0xba00, 16, 3);
-	clks[IMX7D_GPT4_ROOT_PRE_DIV] = imx_clk_divider("gpt4_pre_div", "gpt4_cg", base + 0xba80, 16, 3);
-	clks[IMX7D_TRACE_ROOT_PRE_DIV] = imx_clk_divider("trace_pre_div", "trace_cg", base + 0xbb00, 16, 3);
-	clks[IMX7D_WDOG_ROOT_PRE_DIV] = imx_clk_divider("wdog_pre_div", "wdog_cg", base + 0xbb80, 16, 3);
-	clks[IMX7D_CSI_MCLK_ROOT_PRE_DIV] = imx_clk_divider("csi_mclk_pre_div", "csi_mclk_cg", base + 0xbc00, 16, 3);
-	clks[IMX7D_AUDIO_MCLK_ROOT_PRE_DIV] = imx_clk_divider("audio_mclk_pre_div", "audio_mclk_cg", base + 0xbc80, 16, 3);
-	clks[IMX7D_WRCLK_ROOT_PRE_DIV] = imx_clk_divider("wrclk_pre_div", "wrclk_cg", base + 0xbd00, 16, 3);
-	clks[IMX7D_CLKO1_ROOT_PRE_DIV] = imx_clk_divider("clko1_pre_div", "clko1_cg", base + 0xbd80, 16, 3);
-	clks[IMX7D_CLKO2_ROOT_PRE_DIV] = imx_clk_divider("clko2_pre_div", "clko2_cg", base + 0xbe00, 16, 3);
-
-	clks[IMX7D_ARM_A7_ROOT_DIV] = imx_clk_divider("arm_a7_div", "arm_a7_cg", base + 0x8000, 0, 3);
-	clks[IMX7D_ARM_M4_ROOT_DIV] = imx_clk_divider("arm_m4_div", "arm_m4_cg", base + 0x8080, 0, 3);
-	clks[IMX7D_ARM_M0_ROOT_DIV] = imx_clk_divider("arm_m0_div", "arm_m0_cg", base + 0x8100, 0, 3);
-	clks[IMX7D_MAIN_AXI_ROOT_DIV] = imx_clk_divider("axi_post_div", "axi_pre_div", base + 0x8800, 0, 6);
-	clks[IMX7D_DISP_AXI_ROOT_DIV] = imx_clk_divider("disp_axi_post_div", "disp_axi_pre_div", base + 0x8880, 0, 6);
-	clks[IMX7D_ENET_AXI_ROOT_DIV] = imx_clk_divider("enet_axi_post_div", "enet_axi_pre_div", base + 0x8900, 0, 6);
-	clks[IMX7D_NAND_USDHC_BUS_ROOT_DIV] = imx_clk_divider("nand_usdhc_post_div", "nand_usdhc_pre_div", base + 0x8980, 0, 6);
-	clks[IMX7D_AHB_CHANNEL_ROOT_DIV] = imx_clk_divider("ahb_post_div", "ahb_pre_div", base + 0x9000, 0, 6);
-	clks[IMX7D_DRAM_ROOT_DIV] = imx_clk_divider("dram_post_div", "dram_cg", base + 0x9880, 0, 3);
-	clks[IMX7D_DRAM_PHYM_ALT_ROOT_DIV] = imx_clk_divider("dram_phym_alt_post_div", "dram_phym_alt_pre_div", base + 0xa000, 0, 3);
-	clks[IMX7D_DRAM_ALT_ROOT_DIV] = imx_clk_divider("dram_alt_post_div", "dram_alt_pre_div", base + 0xa080, 0, 3);
-	clks[IMX7D_USB_HSIC_ROOT_DIV] = imx_clk_divider("usb_hsic_post_div", "usb_hsic_pre_div", base + 0xa100, 0, 6);
-	clks[IMX7D_PCIE_CTRL_ROOT_DIV] = imx_clk_divider("pcie_ctrl_post_div", "pcie_ctrl_pre_div", base + 0xa180, 0, 6);
-	clks[IMX7D_PCIE_PHY_ROOT_DIV] = imx_clk_divider("pcie_phy_post_div", "pcie_phy_pre_div", base + 0xa200, 0, 6);
-	clks[IMX7D_EPDC_PIXEL_ROOT_DIV] = imx_clk_divider("epdc_pixel_post_div", "epdc_pixel_pre_div", base + 0xa280, 0, 6);
-	clks[IMX7D_LCDIF_PIXEL_ROOT_DIV] = imx_clk_divider("lcdif_pixel_post_div", "lcdif_pixel_pre_div", base + 0xa300, 0, 6);
-	clks[IMX7D_MIPI_DSI_ROOT_DIV] = imx_clk_divider("mipi_dsi_post_div", "mipi_dsi_pre_div", base + 0xa380, 0, 6);
-	clks[IMX7D_MIPI_CSI_ROOT_DIV] = imx_clk_divider("mipi_csi_post_div", "mipi_csi_pre_div", base + 0xa400, 0, 6);
-	clks[IMX7D_MIPI_DPHY_ROOT_DIV] = imx_clk_divider("mipi_dphy_post_div", "mipi_csi_dphy_div", base + 0xa480, 0, 6);
-	clks[IMX7D_SAI1_ROOT_DIV] = imx_clk_divider("sai1_post_div", "sai1_pre_div", base + 0xa500, 0, 6);
-	clks[IMX7D_SAI2_ROOT_DIV] = imx_clk_divider("sai2_post_div", "sai2_pre_div", base + 0xa580, 0, 6);
-	clks[IMX7D_SAI3_ROOT_DIV] = imx_clk_divider("sai3_post_div", "sai3_pre_div", base + 0xa600, 0, 6);
-	clks[IMX7D_SPDIF_ROOT_DIV] = imx_clk_divider("spdif_post_div", "spdif_pre_div", base + 0xa680, 0, 6);
-	clks[IMX7D_ENET1_REF_ROOT_DIV] = imx_clk_divider("enet1_ref_post_div", "enet1_ref_pre_div", base + 0xa700, 0, 6);
-	clks[IMX7D_ENET1_TIME_ROOT_DIV] = imx_clk_divider("enet1_time_post_div", "enet1_time_pre_div", base + 0xa780, 0, 6);
-	clks[IMX7D_ENET2_REF_ROOT_DIV] = imx_clk_divider("enet2_ref_post_div", "enet2_ref_pre_div", base + 0xa800, 0, 6);
-	clks[IMX7D_ENET2_TIME_ROOT_DIV] = imx_clk_divider("enet2_time_post_div", "enet2_time_pre_div", base + 0xa880, 0, 6);
-	clks[IMX7D_ENET_PHY_REF_ROOT_DIV] = imx_clk_divider("enet_phy_ref_post_div", "enet_phy_ref_pre_div", base + 0xa900, 0, 6);
-	clks[IMX7D_EIM_ROOT_DIV] = imx_clk_divider("eim_post_div", "eim_pre_div", base + 0xa980, 0, 6);
-	clks[IMX7D_NAND_ROOT_DIV] = imx_clk_divider("nand_post_div", "nand_pre_div", base + 0xaa00, 0, 6);
-	clks[IMX7D_QSPI_ROOT_DIV] = imx_clk_divider("qspi_post_div", "qspi_pre_div", base + 0xaa80, 0, 6);
-	clks[IMX7D_USDHC1_ROOT_DIV] = imx_clk_divider("usdhc1_post_div", "usdhc1_pre_div", base + 0xab00, 0, 6);
-	clks[IMX7D_USDHC2_ROOT_DIV] = imx_clk_divider("usdhc2_post_div", "usdhc2_pre_div", base + 0xab80, 0, 6);
-	clks[IMX7D_USDHC3_ROOT_DIV] = imx_clk_divider("usdhc3_post_div", "usdhc3_pre_div", base + 0xac00, 0, 6);
-	clks[IMX7D_CAN1_ROOT_DIV] = imx_clk_divider("can1_post_div", "can1_pre_div", base + 0xac80, 0, 6);
-	clks[IMX7D_CAN2_ROOT_DIV] = imx_clk_divider("can2_post_div", "can2_pre_div", base + 0xad00, 0, 6);
-	clks[IMX7D_I2C1_ROOT_DIV] = imx_clk_divider("i2c1_post_div", "i2c1_pre_div", base + 0xad80, 0, 6);
-	clks[IMX7D_I2C2_ROOT_DIV] = imx_clk_divider("i2c2_post_div", "i2c2_pre_div", base + 0xae00, 0, 6);
-	clks[IMX7D_I2C3_ROOT_DIV] = imx_clk_divider("i2c3_post_div", "i2c3_pre_div", base + 0xae80, 0, 6);
-	clks[IMX7D_I2C4_ROOT_DIV] = imx_clk_divider("i2c4_post_div", "i2c4_pre_div", base + 0xaf00, 0, 6);
-	clks[IMX7D_UART1_ROOT_DIV] = imx_clk_divider("uart1_post_div", "uart1_pre_div", base + 0xaf80, 0, 6);
-	clks[IMX7D_UART2_ROOT_DIV] = imx_clk_divider("uart2_post_div", "uart2_pre_div", base + 0xb000, 0, 6);
-	clks[IMX7D_UART3_ROOT_DIV] = imx_clk_divider("uart3_post_div", "uart3_pre_div", base + 0xb080, 0, 6);
-	clks[IMX7D_UART4_ROOT_DIV] = imx_clk_divider("uart4_post_div", "uart4_pre_div", base + 0xb100, 0, 6);
-	clks[IMX7D_UART5_ROOT_DIV] = imx_clk_divider("uart5_post_div", "uart5_pre_div", base + 0xb180, 0, 6);
-	clks[IMX7D_UART6_ROOT_DIV] = imx_clk_divider("uart6_post_div", "uart6_pre_div", base + 0xb200, 0, 6);
-	clks[IMX7D_UART7_ROOT_DIV] = imx_clk_divider("uart7_post_div", "uart7_pre_div", base + 0xb280, 0, 6);
-	clks[IMX7D_ECSPI1_ROOT_DIV] = imx_clk_divider("ecspi1_post_div", "ecspi1_pre_div", base + 0xb300, 0, 6);
-	clks[IMX7D_ECSPI2_ROOT_DIV] = imx_clk_divider("ecspi2_post_div", "ecspi2_pre_div", base + 0xb380, 0, 6);
-	clks[IMX7D_ECSPI3_ROOT_DIV] = imx_clk_divider("ecspi3_post_div", "ecspi3_pre_div", base + 0xb400, 0, 6);
-	clks[IMX7D_ECSPI4_ROOT_DIV] = imx_clk_divider("ecspi4_post_div", "ecspi4_pre_div", base + 0xb480, 0, 6);
-	clks[IMX7D_PWM1_ROOT_DIV] = imx_clk_divider("pwm1_post_div", "pwm1_pre_div", base + 0xb500, 0, 6);
-	clks[IMX7D_PWM2_ROOT_DIV] = imx_clk_divider("pwm2_post_div", "pwm2_pre_div", base + 0xb580, 0, 6);
-	clks[IMX7D_PWM3_ROOT_DIV] = imx_clk_divider("pwm3_post_div", "pwm3_pre_div", base + 0xb600, 0, 6);
-	clks[IMX7D_PWM4_ROOT_DIV] = imx_clk_divider("pwm4_post_div", "pwm4_pre_div", base + 0xb680, 0, 6);
-	clks[IMX7D_FLEXTIMER1_ROOT_DIV] = imx_clk_divider("flextimer1_post_div", "flextimer1_pre_div", base + 0xb700, 0, 6);
-	clks[IMX7D_FLEXTIMER2_ROOT_DIV] = imx_clk_divider("flextimer2_post_div", "flextimer2_pre_div", base + 0xb780, 0, 6);
-	clks[IMX7D_SIM1_ROOT_DIV] = imx_clk_divider("sim1_post_div", "sim1_pre_div", base + 0xb800, 0, 6);
-	clks[IMX7D_SIM2_ROOT_DIV] = imx_clk_divider("sim2_post_div", "sim2_pre_div", base + 0xb880, 0, 6);
-	clks[IMX7D_GPT1_ROOT_DIV] = imx_clk_divider("gpt1_post_div", "gpt1_pre_div", base + 0xb900, 0, 6);
-	clks[IMX7D_GPT2_ROOT_DIV] = imx_clk_divider("gpt2_post_div", "gpt2_pre_div", base + 0xb980, 0, 6);
-	clks[IMX7D_GPT3_ROOT_DIV] = imx_clk_divider("gpt3_post_div", "gpt3_pre_div", base + 0xba00, 0, 6);
-	clks[IMX7D_GPT4_ROOT_DIV] = imx_clk_divider("gpt4_post_div", "gpt4_pre_div", base + 0xba80, 0, 6);
-	clks[IMX7D_TRACE_ROOT_DIV] = imx_clk_divider("trace_post_div", "trace_pre_div", base + 0xbb00, 0, 6);
-	clks[IMX7D_WDOG_ROOT_DIV] = imx_clk_divider("wdog_post_div", "wdog_pre_div", base + 0xbb80, 0, 6);
-	clks[IMX7D_CSI_MCLK_ROOT_DIV] = imx_clk_divider("csi_mclk_post_div", "csi_mclk_pre_div", base + 0xbc00, 0, 6);
-	clks[IMX7D_AUDIO_MCLK_ROOT_DIV] = imx_clk_divider("audio_mclk_post_div", "audio_mclk_pre_div", base + 0xbc80, 0, 6);
-	clks[IMX7D_WRCLK_ROOT_DIV] = imx_clk_divider("wrclk_post_div", "wrclk_pre_div", base + 0xbd00, 0, 6);
-	clks[IMX7D_CLKO1_ROOT_DIV] = imx_clk_divider("clko1_post_div", "clko1_pre_div", base + 0xbd80, 0, 6);
-	clks[IMX7D_CLKO2_ROOT_DIV] = imx_clk_divider("clko2_post_div", "clko2_pre_div", base + 0xbe00, 0, 6);
-
-	clks[IMX7D_ARM_A7_ROOT_CLK] = imx_clk_gate2("arm_a7_root_clk", "arm_a7_div", base + 0x4000, 0);
-	clks[IMX7D_ARM_M4_ROOT_CLK] = imx_clk_gate2("arm_m4_root_clk", "arm_m4_div", base + 0x4010, 0);
-	clks[IMX7D_ARM_M0_ROOT_CLK] = imx_clk_gate2("arm_m0_root_clk", "arm_m0_div", base + 0x4020, 0);
-	clks[IMX7D_MAIN_AXI_ROOT_CLK] = imx_clk_gate2("main_axi_root_clk", "axi_post_div", base + 0x4040, 0);
-	clks[IMX7D_DISP_AXI_ROOT_CLK] = imx_clk_gate2("disp_axi_root_clk", "disp_axi_post_div", base + 0x4050, 0);
-	clks[IMX7D_ENET_AXI_ROOT_CLK] = imx_clk_gate2("enet_axi_root_clk", "enet_axi_post_div", base + 0x4060, 0);
-	clks[IMX7D_OCRAM_CLK] = imx_clk_gate2("ocram_clk", "axi_post_div", base + 0x4110, 0);
-	clks[IMX7D_OCRAM_S_CLK] = imx_clk_gate2("ocram_s_clk", "ahb_post_div", base + 0x4120, 0);
-	clks[IMX7D_NAND_USDHC_BUS_ROOT_CLK] = imx_clk_gate2("nand_usdhc_root_clk", "nand_usdhc_post_div", base + 0x4130, 0);
-	clks[IMX7D_AHB_CHANNEL_ROOT_CLK] = imx_clk_gate2("ahb_root_clk", "ahb_post_div", base + 0x4200, 0);
-	clks[IMX7D_DRAM_ROOT_CLK] = imx_clk_gate2("dram_root_clk", "dram_post_div", base + 0x4130, 0);
-	clks[IMX7D_DRAM_PHYM_ROOT_CLK] = imx_clk_gate2("dram_phym_root_clk", "dram_phym_cg", base + 0x4130, 0);
-	clks[IMX7D_DRAM_PHYM_ALT_ROOT_CLK] = imx_clk_gate2("dram_phym_alt_root_clk", "dram_phym_alt_post_div", base + 0x4130, 0);
-	clks[IMX7D_DRAM_ALT_ROOT_CLK] = imx_clk_gate2("dram_alt_root_clk", "dram_alt_post_div", base + 0x4130, 0);
-	clks[IMX7D_USB_HSIC_ROOT_CLK] = imx_clk_gate2("usb_hsic_root_clk", "usb_hsic_post_div", base + 0x4420, 0);
-	clks[IMX7D_PCIE_CTRL_ROOT_CLK] = imx_clk_gate2("pcie_ctrl_root_clk", "pcie_ctrl_post_div", base + 0x4600, 0);
-	clks[IMX7D_PCIE_PHY_ROOT_CLK] = imx_clk_gate2("pcie_phy_root_clk", "pcie_phy_post_div", base + 0x4600, 0);
-	clks[IMX7D_EPDC_PIXEL_ROOT_CLK] = imx_clk_gate2("epdc_pixel_root_clk", "epdc_pixel_post_div", base + 0x44a0, 0);
-	clks[IMX7D_LCDIF_PIXEL_ROOT_CLK] = imx_clk_gate2("lcdif_pixel_root_clk", "lcdif_pixel_post_div", base + 0x44b0, 0);
-	clks[IMX7D_MIPI_DSI_ROOT_CLK] = imx_clk_gate2("mipi_dsi_root_clk", "mipi_dsi_post_div", base + 0x4650, 0);
-	clks[IMX7D_MIPI_CSI_ROOT_CLK] = imx_clk_gate2("mipi_csi_root_clk", "mipi_csi_post_div", base + 0x4640, 0);
-	clks[IMX7D_MIPI_DPHY_ROOT_CLK] = imx_clk_gate2("mipi_dphy_root_clk", "mipi_dphy_post_div", base + 0x4660, 0);
-	clks[IMX7D_SAI1_ROOT_CLK] = imx_clk_gate2("sai1_root_clk", "sai1_post_div", base + 0x48c0, 0);
-	clks[IMX7D_SAI2_ROOT_CLK] = imx_clk_gate2("sai2_root_clk", "sai2_post_div", base + 0x48d0, 0);
-	clks[IMX7D_SAI3_ROOT_CLK] = imx_clk_gate2("sai3_root_clk", "sai3_post_div", base + 0x48e0, 0);
-	clks[IMX7D_SPDIF_ROOT_CLK] = imx_clk_gate2("spdif_root_clk", "spdif_post_div", base + 0x44d0, 0);
-	clks[IMX7D_ENET1_REF_ROOT_CLK] = imx_clk_gate2("enet1_ref_root_clk", "enet1_ref_post_div", base + 0x44e0, 0);
-	clks[IMX7D_ENET1_TIME_ROOT_CLK] = imx_clk_gate2("enet1_time_root_clk", "enet1_time_post_div", base + 0x44f0, 0);
-	clks[IMX7D_ENET2_REF_ROOT_CLK] = imx_clk_gate2("enet2_ref_root_clk", "enet2_ref_post_div", base + 0x4500, 0);
-	clks[IMX7D_ENET2_TIME_ROOT_CLK] = imx_clk_gate2("enet2_time_root_clk", "enet2_time_post_div", base + 0x4510, 0);
-	clks[IMX7D_ENET_PHY_REF_ROOT_CLK] = imx_clk_gate2("enet_phy_ref_root_clk", "enet_phy_ref_post_div", base + 0x4520, 0);
-	clks[IMX7D_EIM_ROOT_CLK] = imx_clk_gate2("eim_root_clk", "eim_post_div", base + 0x4160, 0);
-	clks[IMX7D_NAND_ROOT_CLK] = imx_clk_gate2("nand_root_clk", "nand_post_div", base + 0x4140, 0);
-	clks[IMX7D_QSPI_ROOT_CLK] = imx_clk_gate2("qspi_root_clk", "qspi_post_div", base + 0x4150, 0);
-	clks[IMX7D_USDHC1_ROOT_CLK] = imx_clk_gate2("usdhc1_root_clk", "usdhc1_post_div", base + 0x46c0, 0);
-	clks[IMX7D_USDHC2_ROOT_CLK] = imx_clk_gate2("usdhc2_root_clk", "usdhc2_post_div", base + 0x46d0, 0);
-	clks[IMX7D_USDHC3_ROOT_CLK] = imx_clk_gate2("usdhc3_root_clk", "usdhc3_post_div", base + 0x46e0, 0);
-	clks[IMX7D_CAN1_ROOT_CLK] = imx_clk_gate2("can1_root_clk", "can1_post_div", base + 0x4740, 0);
-	clks[IMX7D_CAN2_ROOT_CLK] = imx_clk_gate2("can2_root_clk", "can2_post_div", base + 0x4750, 0);
-	clks[IMX7D_I2C1_ROOT_CLK] = imx_clk_gate2("i2c1_root_clk", "i2c1_post_div", base + 0x4880, 0);
-	clks[IMX7D_I2C2_ROOT_CLK] = imx_clk_gate2("i2c2_root_clk", "i2c2_post_div", base + 0x4890, 0);
-	clks[IMX7D_I2C3_ROOT_CLK] = imx_clk_gate2("i2c3_root_clk", "i2c3_post_div", base + 0x48a0, 0);
-	clks[IMX7D_I2C4_ROOT_CLK] = imx_clk_gate2("i2c4_root_clk", "i2c4_post_div", base + 0x48b0, 0);
-	clks[IMX7D_UART1_ROOT_CLK] = imx_clk_gate2("uart1_root_clk", "uart1_post_div", base + 0x4940, 0);
-	clks[IMX7D_UART2_ROOT_CLK] = imx_clk_gate2("uart2_root_clk", "uart2_post_div", base + 0x4950, 0);
-	clks[IMX7D_UART3_ROOT_CLK] = imx_clk_gate2("uart3_root_clk", "uart3_post_div", base + 0x4960, 0);
-	clks[IMX7D_UART4_ROOT_CLK] = imx_clk_gate2("uart4_root_clk", "uart4_post_div", base + 0x4970, 0);
-	clks[IMX7D_UART5_ROOT_CLK] = imx_clk_gate2("uart5_root_clk", "uart5_post_div", base + 0x4980, 0);
-	clks[IMX7D_UART6_ROOT_CLK] = imx_clk_gate2("uart6_root_clk", "uart6_post_div", base + 0x4990, 0);
-	clks[IMX7D_UART7_ROOT_CLK] = imx_clk_gate2("uart7_root_clk", "uart7_post_div", base + 0x49a0, 0);
-	clks[IMX7D_ECSPI1_ROOT_CLK] = imx_clk_gate2("ecspi1_root_clk", "ecspi1_post_div", base + 0x4780, 0);
-	clks[IMX7D_ECSPI2_ROOT_CLK] = imx_clk_gate2("ecspi2_root_clk", "ecspi2_post_div", base + 0x4790, 0);
-	clks[IMX7D_ECSPI3_ROOT_CLK] = imx_clk_gate2("ecspi3_root_clk", "ecspi3_post_div", base + 0x47a0, 0);
-	clks[IMX7D_ECSPI4_ROOT_CLK] = imx_clk_gate2("ecspi4_root_clk", "ecspi4_post_div", base + 0x47b0, 0);
-	clks[IMX7D_PWM1_ROOT_CLK] = imx_clk_gate2("pwm1_root_clk", "pwm1_post_div", base + 0x4840, 0);
-	clks[IMX7D_PWM2_ROOT_CLK] = imx_clk_gate2("pwm2_root_clk", "pwm2_post_div", base + 0x4850, 0);
-	clks[IMX7D_PWM3_ROOT_CLK] = imx_clk_gate2("pwm3_root_clk", "pwm3_post_div", base + 0x4860, 0);
-	clks[IMX7D_PWM4_ROOT_CLK] = imx_clk_gate2("pwm4_root_clk", "pwm4_post_div", base + 0x4870, 0);
-	clks[IMX7D_FLEXTIMER1_ROOT_CLK] = imx_clk_gate2("flextimer1_root_clk", "flextimer1_post_div", base + 0x4800, 0);
-	clks[IMX7D_FLEXTIMER2_ROOT_CLK] = imx_clk_gate2("flextimer2_root_clk", "flextimer2_post_div", base + 0x4810, 0);
-	clks[IMX7D_SIM1_ROOT_CLK] = imx_clk_gate2("sim1_root_clk", "sim1_post_div", base + 0x4900, 0);
-	clks[IMX7D_SIM2_ROOT_CLK] = imx_clk_gate2("sim2_root_clk", "sim2_post_div", base + 0x4910, 0);
-	clks[IMX7D_GPT1_ROOT_CLK] = imx_clk_gate2("gpt1_root_clk", "gpt1_post_div", base + 0x47c0, 0);
-	clks[IMX7D_GPT2_ROOT_CLK] = imx_clk_gate2("gpt2_root_clk", "gpt2_post_div", base + 0x47d0, 0);
-	clks[IMX7D_GPT3_ROOT_CLK] = imx_clk_gate2("gpt3_root_clk", "gpt3_post_div", base + 0x47e0, 0);
-	clks[IMX7D_GPT4_ROOT_CLK] = imx_clk_gate2("gpt4_root_clk", "gpt4_post_div", base + 0x47f0, 0);
-	clks[IMX7D_TRACE_ROOT_CLK] = imx_clk_gate2("trace_root_clk", "trace_post_div", base + 0x4300, 0);
-	clks[IMX7D_WDOG1_ROOT_CLK] = imx_clk_gate2("wdog1_root_clk", "wdog_post_div", base + 0x49c0, 0);
-	clks[IMX7D_WDOG2_ROOT_CLK] = imx_clk_gate2("wdog2_root_clk", "wdog_post_div", base + 0x49d0, 0);
-	clks[IMX7D_WDOG3_ROOT_CLK] = imx_clk_gate2("wdog3_root_clk", "wdog_post_div", base + 0x49e0, 0);
-	clks[IMX7D_WDOG4_ROOT_CLK] = imx_clk_gate2("wdog4_root_clk", "wdog_post_div", base + 0x49f0, 0);
-	clks[IMX7D_CSI_MCLK_ROOT_CLK] = imx_clk_gate2("csi_mclk_root_clk", "csi_mclk_post_div", base + 0x4490, 0);
-	clks[IMX7D_AUDIO_MCLK_ROOT_CLK] = imx_clk_gate2("audio_mclk_root_clk", "audio_mclk_post_div", base + 0x4790, 0);
-	clks[IMX7D_WRCLK_ROOT_CLK] = imx_clk_gate2("wrclk_root_clk", "wrclk_post_div", base + 0x47a0, 0);
-	clks[IMX7D_ADC_ROOT_CLK] = imx_clk_gate2("adc_root_clk", "ipg_root_clk", base + 0x4200, 0);
+	clks[IMX7D_ARM_A7_ROOT_SRC] = imx_clk_mux2("arm_a7_src", base + 0x8000, 24, 3, arm_a7_sel, ARRAY_SIZE(arm_a7_sel));
+	clks[IMX7D_ARM_M4_ROOT_SRC] = imx_clk_mux2("arm_m4_src", base + 0x8080, 24, 3, arm_m4_sel, ARRAY_SIZE(arm_m4_sel));
+	clks[IMX7D_ARM_M0_ROOT_SRC] = imx_clk_mux2("arm_m0_src", base + 0x8100, 24, 3, arm_m0_sel, ARRAY_SIZE(arm_m0_sel));
+	clks[IMX7D_MAIN_AXI_ROOT_SRC] = imx_clk_mux2("axi_src", base + 0x8800, 24, 3, axi_sel, ARRAY_SIZE(axi_sel));
+	clks[IMX7D_DISP_AXI_ROOT_SRC] = imx_clk_mux2("disp_axi_src", base + 0x8880, 24, 3, disp_axi_sel, ARRAY_SIZE(disp_axi_sel));
+	clks[IMX7D_ENET_AXI_ROOT_SRC] = imx_clk_mux2("enet_axi_src", base + 0x8900, 24, 3, enet_axi_sel, ARRAY_SIZE(enet_axi_sel));
+	clks[IMX7D_NAND_USDHC_BUS_ROOT_SRC] = imx_clk_mux2("nand_usdhc_src", base + 0x8980, 24, 3, nand_usdhc_bus_sel, ARRAY_SIZE(nand_usdhc_bus_sel));
+	clks[IMX7D_AHB_CHANNEL_ROOT_SRC] = imx_clk_mux2("ahb_src", base + 0x9000, 24, 3, ahb_channel_sel, ARRAY_SIZE(ahb_channel_sel));
+	clks[IMX7D_DRAM_PHYM_ROOT_SRC] = imx_clk_mux2("dram_phym_src", base + 0x9800, 24, 1, dram_phym_sel, ARRAY_SIZE(dram_phym_sel));
+	clks[IMX7D_DRAM_ROOT_SRC] = imx_clk_mux2("dram_src", base + 0x9880, 24, 1, dram_sel, ARRAY_SIZE(dram_sel));
+	clks[IMX7D_DRAM_PHYM_ALT_ROOT_SRC] = imx_clk_mux2("dram_phym_alt_src", base + 0xa000, 24, 3, dram_phym_alt_sel, ARRAY_SIZE(dram_phym_alt_sel));
+	clks[IMX7D_DRAM_ALT_ROOT_SRC]  = imx_clk_mux2("dram_alt_src", base + 0xa080, 24, 3, dram_alt_sel, ARRAY_SIZE(dram_alt_sel));
+	clks[IMX7D_USB_HSIC_ROOT_SRC] = imx_clk_mux2("usb_hsic_src", base + 0xa100, 24, 3, usb_hsic_sel, ARRAY_SIZE(usb_hsic_sel));
+	clks[IMX7D_PCIE_CTRL_ROOT_SRC] = imx_clk_mux2("pcie_ctrl_src", base + 0xa180, 24, 3, pcie_ctrl_sel, ARRAY_SIZE(pcie_ctrl_sel));
+	clks[IMX7D_PCIE_PHY_ROOT_SRC] = imx_clk_mux2("pcie_phy_src", base + 0xa200, 24, 3, pcie_phy_sel, ARRAY_SIZE(pcie_phy_sel));
+	clks[IMX7D_EPDC_PIXEL_ROOT_SRC] = imx_clk_mux2("epdc_pixel_src", base + 0xa280, 24, 3, epdc_pixel_sel, ARRAY_SIZE(epdc_pixel_sel));
+	clks[IMX7D_LCDIF_PIXEL_ROOT_SRC] = imx_clk_mux2("lcdif_pixel_src", base + 0xa300, 24, 3, lcdif_pixel_sel, ARRAY_SIZE(lcdif_pixel_sel));
+	clks[IMX7D_MIPI_DSI_ROOT_SRC] = imx_clk_mux2("mipi_dsi_src", base + 0xa380, 24, 3,  mipi_dsi_sel, ARRAY_SIZE(mipi_dsi_sel));
+	clks[IMX7D_MIPI_CSI_ROOT_SRC] = imx_clk_mux2("mipi_csi_src", base + 0xa400, 24, 3, mipi_csi_sel, ARRAY_SIZE(mipi_csi_sel));
+	clks[IMX7D_MIPI_DPHY_ROOT_SRC] = imx_clk_mux2("mipi_dphy_src", base + 0xa480, 24, 3, mipi_dphy_sel, ARRAY_SIZE(mipi_dphy_sel));
+	clks[IMX7D_SAI1_ROOT_SRC] = imx_clk_mux2("sai1_src", base + 0xa500, 24, 3, sai1_sel, ARRAY_SIZE(sai1_sel));
+	clks[IMX7D_SAI2_ROOT_SRC] = imx_clk_mux2("sai2_src", base + 0xa580, 24, 3, sai2_sel, ARRAY_SIZE(sai2_sel));
+	clks[IMX7D_SAI3_ROOT_SRC] = imx_clk_mux2("sai3_src", base + 0xa600, 24, 3, sai3_sel, ARRAY_SIZE(sai3_sel));
+	clks[IMX7D_SPDIF_ROOT_SRC] = imx_clk_mux2("spdif_src", base + 0xa680, 24, 3, spdif_sel, ARRAY_SIZE(spdif_sel));
+	clks[IMX7D_ENET1_REF_ROOT_SRC] = imx_clk_mux2("enet1_ref_src", base + 0xa700, 24, 3, enet1_ref_sel, ARRAY_SIZE(enet1_ref_sel));
+	clks[IMX7D_ENET1_TIME_ROOT_SRC] = imx_clk_mux2("enet1_time_src", base + 0xa780, 24, 3, enet1_time_sel, ARRAY_SIZE(enet1_time_sel));
+	clks[IMX7D_ENET2_REF_ROOT_SRC] = imx_clk_mux2("enet2_ref_src", base + 0xa800, 24, 3, enet2_ref_sel, ARRAY_SIZE(enet2_ref_sel));
+	clks[IMX7D_ENET2_TIME_ROOT_SRC] = imx_clk_mux2("enet2_time_src", base + 0xa880, 24, 3, enet2_time_sel, ARRAY_SIZE(enet2_time_sel));
+	clks[IMX7D_ENET_PHY_REF_ROOT_SRC] = imx_clk_mux2("enet_phy_ref_src", base + 0xa900, 24, 3, enet_phy_ref_sel, ARRAY_SIZE(enet_phy_ref_sel));
+	clks[IMX7D_EIM_ROOT_SRC] = imx_clk_mux2("eim_src", base + 0xa980, 24, 3, eim_sel, ARRAY_SIZE(eim_sel));
+	clks[IMX7D_NAND_ROOT_SRC] = imx_clk_mux2("nand_src", base + 0xaa00, 24, 3, nand_sel, ARRAY_SIZE(nand_sel));
+	clks[IMX7D_QSPI_ROOT_SRC] = imx_clk_mux2("qspi_src", base + 0xaa80, 24, 3, qspi_sel, ARRAY_SIZE(qspi_sel));
+	clks[IMX7D_USDHC1_ROOT_SRC] = imx_clk_mux2("usdhc1_src", base + 0xab00, 24, 3, usdhc1_sel, ARRAY_SIZE(usdhc1_sel));
+	clks[IMX7D_USDHC2_ROOT_SRC] = imx_clk_mux2("usdhc2_src", base + 0xab80, 24, 3, usdhc2_sel, ARRAY_SIZE(usdhc2_sel));
+	clks[IMX7D_USDHC3_ROOT_SRC] = imx_clk_mux2("usdhc3_src", base + 0xac00, 24, 3, usdhc3_sel, ARRAY_SIZE(usdhc3_sel));
+	clks[IMX7D_CAN1_ROOT_SRC] = imx_clk_mux2("can1_src", base + 0xac80, 24, 3, can1_sel, ARRAY_SIZE(can1_sel));
+	clks[IMX7D_CAN2_ROOT_SRC] = imx_clk_mux2("can2_src", base + 0xad00, 24, 3, can2_sel, ARRAY_SIZE(can2_sel));
+	clks[IMX7D_I2C1_ROOT_SRC] = imx_clk_mux2("i2c1_src", base + 0xad80, 24, 3, i2c1_sel, ARRAY_SIZE(i2c1_sel));
+	clks[IMX7D_I2C2_ROOT_SRC] = imx_clk_mux2("i2c2_src", base + 0xae00, 24, 3, i2c2_sel, ARRAY_SIZE(i2c2_sel));
+	clks[IMX7D_I2C3_ROOT_SRC] = imx_clk_mux2("i2c3_src", base + 0xae80, 24, 3, i2c3_sel, ARRAY_SIZE(i2c3_sel));
+	clks[IMX7D_I2C4_ROOT_SRC] = imx_clk_mux2("i2c4_src", base + 0xaf00, 24, 3, i2c4_sel, ARRAY_SIZE(i2c4_sel));
+	clks[IMX7D_UART1_ROOT_SRC] = imx_clk_mux2("uart1_src", base + 0xaf80, 24, 3, uart1_sel, ARRAY_SIZE(uart1_sel));
+	clks[IMX7D_UART2_ROOT_SRC] = imx_clk_mux2("uart2_src", base + 0xb000, 24, 3, uart2_sel, ARRAY_SIZE(uart2_sel));
+	clks[IMX7D_UART3_ROOT_SRC] = imx_clk_mux2("uart3_src", base + 0xb080, 24, 3, uart3_sel, ARRAY_SIZE(uart3_sel));
+	clks[IMX7D_UART4_ROOT_SRC] = imx_clk_mux2("uart4_src", base + 0xb100, 24, 3, uart4_sel, ARRAY_SIZE(uart4_sel));
+	clks[IMX7D_UART5_ROOT_SRC] = imx_clk_mux2("uart5_src", base + 0xb180, 24, 3, uart5_sel, ARRAY_SIZE(uart5_sel));
+	clks[IMX7D_UART6_ROOT_SRC] = imx_clk_mux2("uart6_src", base + 0xb200, 24, 3, uart6_sel, ARRAY_SIZE(uart6_sel));
+	clks[IMX7D_UART7_ROOT_SRC] = imx_clk_mux2("uart7_src", base + 0xb280, 24, 3, uart7_sel, ARRAY_SIZE(uart7_sel));
+	clks[IMX7D_ECSPI1_ROOT_SRC] = imx_clk_mux2("ecspi1_src", base + 0xb300, 24, 3, ecspi1_sel, ARRAY_SIZE(ecspi1_sel));
+	clks[IMX7D_ECSPI2_ROOT_SRC] = imx_clk_mux2("ecspi2_src", base + 0xb380, 24, 3, ecspi2_sel, ARRAY_SIZE(ecspi2_sel));
+	clks[IMX7D_ECSPI3_ROOT_SRC] = imx_clk_mux2("ecspi3_src", base + 0xb400, 24, 3, ecspi3_sel, ARRAY_SIZE(ecspi3_sel));
+	clks[IMX7D_ECSPI4_ROOT_SRC] = imx_clk_mux2("ecspi4_src", base + 0xb480, 24, 3, ecspi4_sel, ARRAY_SIZE(ecspi4_sel));
+	clks[IMX7D_PWM1_ROOT_SRC] = imx_clk_mux2("pwm1_src", base + 0xb500, 24, 3, pwm1_sel, ARRAY_SIZE(pwm1_sel));
+	clks[IMX7D_PWM2_ROOT_SRC] = imx_clk_mux2("pwm2_src", base + 0xb580, 24, 3, pwm2_sel, ARRAY_SIZE(pwm2_sel));
+	clks[IMX7D_PWM3_ROOT_SRC] = imx_clk_mux2("pwm3_src", base + 0xb600, 24, 3, pwm3_sel, ARRAY_SIZE(pwm3_sel));
+	clks[IMX7D_PWM4_ROOT_SRC] = imx_clk_mux2("pwm4_src", base + 0xb680, 24, 3, pwm4_sel, ARRAY_SIZE(pwm4_sel));
+	clks[IMX7D_FLEXTIMER1_ROOT_SRC] = imx_clk_mux2("flextimer1_src", base + 0xb700, 24, 3, flextimer1_sel, ARRAY_SIZE(flextimer1_sel));
+	clks[IMX7D_FLEXTIMER2_ROOT_SRC] = imx_clk_mux2("flextimer2_src", base + 0xb780, 24, 3, flextimer2_sel, ARRAY_SIZE(flextimer2_sel));
+	clks[IMX7D_SIM1_ROOT_SRC] = imx_clk_mux2("sim1_src", base + 0xb800, 24, 3, sim1_sel, ARRAY_SIZE(sim1_sel));
+	clks[IMX7D_SIM2_ROOT_SRC] = imx_clk_mux2("sim2_src", base + 0xb880, 24, 3, sim2_sel, ARRAY_SIZE(sim2_sel));
+	clks[IMX7D_GPT1_ROOT_SRC] = imx_clk_mux2("gpt1_src", base + 0xb900, 24, 3, gpt1_sel, ARRAY_SIZE(gpt1_sel));
+	clks[IMX7D_GPT2_ROOT_SRC] = imx_clk_mux2("gpt2_src", base + 0xb980, 24, 3, gpt2_sel, ARRAY_SIZE(gpt2_sel));
+	clks[IMX7D_GPT3_ROOT_SRC] = imx_clk_mux2("gpt3_src", base + 0xba00, 24, 3, gpt3_sel, ARRAY_SIZE(gpt3_sel));
+	clks[IMX7D_GPT4_ROOT_SRC] = imx_clk_mux2("gpt4_src", base + 0xba80, 24, 3, gpt4_sel, ARRAY_SIZE(gpt4_sel));
+	clks[IMX7D_TRACE_ROOT_SRC] = imx_clk_mux2("trace_src", base + 0xbb00, 24, 3, trace_sel, ARRAY_SIZE(trace_sel));
+	clks[IMX7D_WDOG_ROOT_SRC] = imx_clk_mux2("wdog_src", base + 0xbb80, 24, 3, wdog_sel, ARRAY_SIZE(wdog_sel));
+	clks[IMX7D_CSI_MCLK_ROOT_SRC] = imx_clk_mux2("csi_mclk_src", base + 0xbc00, 24, 3, csi_mclk_sel, ARRAY_SIZE(csi_mclk_sel));
+	clks[IMX7D_AUDIO_MCLK_ROOT_SRC] = imx_clk_mux2("audio_mclk_src", base + 0xbc80, 24, 3, audio_mclk_sel, ARRAY_SIZE(audio_mclk_sel));
+	clks[IMX7D_WRCLK_ROOT_SRC] = imx_clk_mux2("wrclk_src", base + 0xbd00, 24, 3, wrclk_sel, ARRAY_SIZE(wrclk_sel));
+	clks[IMX7D_CLKO1_ROOT_SRC] = imx_clk_mux2("clko1_src", base + 0xbd80, 24, 3, clko1_sel, ARRAY_SIZE(clko1_sel));
+	clks[IMX7D_CLKO2_ROOT_SRC] = imx_clk_mux2("clko2_src", base + 0xbe00, 24, 3, clko2_sel, ARRAY_SIZE(clko2_sel));
+
+	clks[IMX7D_ARM_A7_ROOT_CG] = imx_clk_gate3("arm_a7_cg", "arm_a7_src", base + 0x8000, 28);
+	clks[IMX7D_ARM_M4_ROOT_CG] = imx_clk_gate3("arm_m4_cg", "arm_m4_src", base + 0x8080, 28);
+	clks[IMX7D_ARM_M0_ROOT_CG] = imx_clk_gate3("arm_m0_cg", "arm_m0_src", base + 0x8100, 28);
+	clks[IMX7D_MAIN_AXI_ROOT_CG] = imx_clk_gate3("axi_cg", "axi_src", base + 0x8800, 28);
+	clks[IMX7D_DISP_AXI_ROOT_CG] = imx_clk_gate3("disp_axi_cg", "disp_axi_src", base + 0x8880, 28);
+	clks[IMX7D_ENET_AXI_ROOT_CG] = imx_clk_gate3("enet_axi_cg", "enet_axi_src", base + 0x8900, 28);
+	clks[IMX7D_NAND_USDHC_BUS_ROOT_CG] = imx_clk_gate3("nand_usdhc_cg", "nand_usdhc_src", base + 0x8980, 28);
+	clks[IMX7D_AHB_CHANNEL_ROOT_CG] = imx_clk_gate3("ahb_cg", "ahb_src", base + 0x9000, 28);
+	clks[IMX7D_DRAM_PHYM_ROOT_CG] = imx_clk_gate3("dram_phym_cg", "dram_phym_src", base + 0x9800, 28);
+	clks[IMX7D_DRAM_ROOT_CG] = imx_clk_gate3("dram_cg", "dram_src", base + 0x9880, 28);
+	clks[IMX7D_DRAM_PHYM_ALT_ROOT_CG] = imx_clk_gate3("dram_phym_alt_cg", "dram_phym_alt_src", base + 0xa000, 28);
+	clks[IMX7D_DRAM_ALT_ROOT_CG] = imx_clk_gate3("dram_alt_cg", "dram_alt_src", base + 0xa080, 28);
+	clks[IMX7D_USB_HSIC_ROOT_CG] = imx_clk_gate3("usb_hsic_cg", "usb_hsic_src", base + 0xa100, 28);
+	clks[IMX7D_PCIE_CTRL_ROOT_CG] = imx_clk_gate3("pcie_ctrl_cg", "pcie_ctrl_src", base + 0xa180, 28);
+	clks[IMX7D_PCIE_PHY_ROOT_CG] = imx_clk_gate3("pcie_phy_cg", "pcie_phy_src", base + 0xa200, 28);
+	clks[IMX7D_EPDC_PIXEL_ROOT_CG] = imx_clk_gate3("epdc_pixel_cg", "epdc_pixel_src", base + 0xa280, 28);
+	clks[IMX7D_LCDIF_PIXEL_ROOT_CG] = imx_clk_gate3("lcdif_pixel_cg", "lcdif_pixel_src", base + 0xa300, 28);
+	clks[IMX7D_MIPI_DSI_ROOT_CG] = imx_clk_gate3("mipi_dsi_cg", "mipi_dsi_src", base + 0xa380, 28);
+	clks[IMX7D_MIPI_CSI_ROOT_CG] = imx_clk_gate3("mipi_csi_cg", "mipi_csi_src", base + 0xa400, 28);
+	clks[IMX7D_MIPI_DPHY_ROOT_CG] = imx_clk_gate3("mipi_dphy_cg", "mipi_dphy_src", base + 0xa480, 28);
+	clks[IMX7D_SAI1_ROOT_CG] = imx_clk_gate3("sai1_cg", "sai1_src", base + 0xa500, 28);
+	clks[IMX7D_SAI2_ROOT_CG] = imx_clk_gate3("sai2_cg", "sai2_src", base + 0xa580, 28);
+	clks[IMX7D_SAI3_ROOT_CG] = imx_clk_gate3("sai3_cg", "sai3_src", base + 0xa600, 28);
+	clks[IMX7D_SPDIF_ROOT_CG] = imx_clk_gate3("spdif_cg", "spdif_src", base + 0xa680, 28);
+	clks[IMX7D_ENET1_REF_ROOT_CG] = imx_clk_gate3("enet1_ref_cg", "enet1_ref_src", base + 0xa700, 28);
+	clks[IMX7D_ENET1_TIME_ROOT_CG] = imx_clk_gate3("enet1_time_cg", "enet1_time_src", base + 0xa780, 28);
+	clks[IMX7D_ENET2_REF_ROOT_CG] = imx_clk_gate3("enet2_ref_cg", "enet2_ref_src", base + 0xa800, 28);
+	clks[IMX7D_ENET2_TIME_ROOT_CG] = imx_clk_gate3("enet2_time_cg", "enet2_time_src", base + 0xa880, 28);
+	clks[IMX7D_ENET_PHY_REF_ROOT_CG] = imx_clk_gate3("enet_phy_ref_cg", "enet_phy_ref_src", base + 0xa900, 28);
+	clks[IMX7D_EIM_ROOT_CG] = imx_clk_gate3("eim_cg", "eim_src", base + 0xa980, 28);
+	clks[IMX7D_NAND_ROOT_CG] = imx_clk_gate3("nand_cg", "nand_src", base + 0xaa00, 28);
+	clks[IMX7D_QSPI_ROOT_CG] = imx_clk_gate3("qspi_cg", "qspi_src", base + 0xaa80, 28);
+	clks[IMX7D_USDHC1_ROOT_CG] = imx_clk_gate3("usdhc1_cg", "usdhc1_src", base + 0xab00, 28);
+	clks[IMX7D_USDHC2_ROOT_CG] = imx_clk_gate3("usdhc2_cg", "usdhc2_src", base + 0xab80, 28);
+	clks[IMX7D_USDHC3_ROOT_CG] = imx_clk_gate3("usdhc3_cg", "usdhc3_src", base + 0xac00, 28);
+	clks[IMX7D_CAN1_ROOT_CG] = imx_clk_gate3("can1_cg", "can1_src", base + 0xac80, 28);
+	clks[IMX7D_CAN2_ROOT_CG] = imx_clk_gate3("can2_cg", "can2_src", base + 0xad00, 28);
+	clks[IMX7D_I2C1_ROOT_CG] = imx_clk_gate3("i2c1_cg", "i2c1_src", base + 0xad80, 28);
+	clks[IMX7D_I2C2_ROOT_CG] = imx_clk_gate3("i2c2_cg", "i2c2_src", base + 0xae00, 28);
+	clks[IMX7D_I2C3_ROOT_CG] = imx_clk_gate3("i2c3_cg", "i2c3_src", base + 0xae80, 28);
+	clks[IMX7D_I2C4_ROOT_CG] = imx_clk_gate3("i2c4_cg", "i2c4_src", base + 0xaf00, 28);
+	clks[IMX7D_UART1_ROOT_CG] = imx_clk_gate3("uart1_cg", "uart1_src", base + 0xaf80, 28);
+	clks[IMX7D_UART2_ROOT_CG] = imx_clk_gate3("uart2_cg", "uart2_src", base + 0xb000, 28);
+	clks[IMX7D_UART3_ROOT_CG] = imx_clk_gate3("uart3_cg", "uart3_src", base + 0xb080, 28);
+	clks[IMX7D_UART4_ROOT_CG] = imx_clk_gate3("uart4_cg", "uart4_src", base + 0xb100, 28);
+	clks[IMX7D_UART5_ROOT_CG] = imx_clk_gate3("uart5_cg", "uart5_src", base + 0xb180, 28);
+	clks[IMX7D_UART6_ROOT_CG] = imx_clk_gate3("uart6_cg", "uart6_src", base + 0xb200, 28);
+	clks[IMX7D_UART7_ROOT_CG] = imx_clk_gate3("uart7_cg", "uart7_src", base + 0xb280, 28);
+	clks[IMX7D_ECSPI1_ROOT_CG] = imx_clk_gate3("ecspi1_cg", "ecspi1_src", base + 0xb300, 28);
+	clks[IMX7D_ECSPI2_ROOT_CG] = imx_clk_gate3("ecspi2_cg", "ecspi2_src", base + 0xb380, 28);
+	clks[IMX7D_ECSPI3_ROOT_CG] = imx_clk_gate3("ecspi3_cg", "ecspi3_src", base + 0xb400, 28);
+	clks[IMX7D_ECSPI4_ROOT_CG] = imx_clk_gate3("ecspi4_cg", "ecspi4_src", base + 0xb480, 28);
+	clks[IMX7D_PWM1_ROOT_CG] = imx_clk_gate3("pwm1_cg", "pwm1_src", base + 0xb500, 28);
+	clks[IMX7D_PWM2_ROOT_CG] = imx_clk_gate3("pwm2_cg", "pwm2_src", base + 0xb580, 28);
+	clks[IMX7D_PWM3_ROOT_CG] = imx_clk_gate3("pwm3_cg", "pwm3_src", base + 0xb600, 28);
+	clks[IMX7D_PWM4_ROOT_CG] = imx_clk_gate3("pwm4_cg", "pwm4_src", base + 0xb680, 28);
+	clks[IMX7D_FLEXTIMER1_ROOT_CG] = imx_clk_gate3("flextimer1_cg", "flextimer1_src", base + 0xb700, 28);
+	clks[IMX7D_FLEXTIMER2_ROOT_CG] = imx_clk_gate3("flextimer2_cg", "flextimer2_src", base + 0xb780, 28);
+	clks[IMX7D_SIM1_ROOT_CG] = imx_clk_gate3("sim1_cg", "sim1_src", base + 0xb800, 28);
+	clks[IMX7D_SIM2_ROOT_CG] = imx_clk_gate3("sim2_cg", "sim2_src", base + 0xb880, 28);
+	clks[IMX7D_GPT1_ROOT_CG] = imx_clk_gate3("gpt1_cg", "gpt1_src", base + 0xb900, 28);
+	clks[IMX7D_GPT2_ROOT_CG] = imx_clk_gate3("gpt2_cg", "gpt2_src", base + 0xb980, 28);
+	clks[IMX7D_GPT3_ROOT_CG] = imx_clk_gate3("gpt3_cg", "gpt3_src", base + 0xbA00, 28);
+	clks[IMX7D_GPT4_ROOT_CG] = imx_clk_gate3("gpt4_cg", "gpt4_src", base + 0xbA80, 28);
+	clks[IMX7D_TRACE_ROOT_CG] = imx_clk_gate3("trace_cg", "trace_src", base + 0xbb00, 28);
+	clks[IMX7D_WDOG_ROOT_CG] = imx_clk_gate3("wdog_cg", "wdog_src", base + 0xbb80, 28);
+	clks[IMX7D_CSI_MCLK_ROOT_CG] = imx_clk_gate3("csi_mclk_cg", "csi_mclk_src", base + 0xbc00, 28);
+	clks[IMX7D_AUDIO_MCLK_ROOT_CG] = imx_clk_gate3("audio_mclk_cg", "audio_mclk_src", base + 0xbc80, 28);
+	clks[IMX7D_WRCLK_ROOT_CG] = imx_clk_gate3("wrclk_cg", "wrclk_src", base + 0xbd00, 28);
+	clks[IMX7D_CLKO1_ROOT_CG] = imx_clk_gate3("clko1_cg", "clko1_src", base + 0xbd80, 28);
+	clks[IMX7D_CLKO2_ROOT_CG] = imx_clk_gate3("clko2_cg", "clko2_src", base + 0xbe00, 28);
+
+	clks[IMX7D_MAIN_AXI_ROOT_PRE_DIV] = imx_clk_divider2("axi_pre_div", "axi_cg", base + 0x8800, 16, 3);
+	clks[IMX7D_DISP_AXI_ROOT_PRE_DIV] = imx_clk_divider2("disp_axi_pre_div", "disp_axi_cg", base + 0x8880, 16, 3);
+	clks[IMX7D_ENET_AXI_ROOT_PRE_DIV] = imx_clk_divider2("enet_axi_pre_div", "enet_axi_cg", base + 0x8900, 16, 3);
+	clks[IMX7D_NAND_USDHC_BUS_ROOT_PRE_DIV] = imx_clk_divider2("nand_usdhc_pre_div", "nand_usdhc_cg", base + 0x8980, 16, 3);
+	clks[IMX7D_AHB_CHANNEL_ROOT_PRE_DIV] = imx_clk_divider2("ahb_pre_div", "ahb_cg", base + 0x9000, 16, 3);
+	clks[IMX7D_DRAM_PHYM_ALT_ROOT_PRE_DIV] = imx_clk_divider2("dram_phym_alt_pre_div", "dram_phym_alt_cg", base + 0xa000, 16, 3);
+	clks[IMX7D_DRAM_ALT_ROOT_PRE_DIV] = imx_clk_divider2("dram_alt_pre_div", "dram_alt_cg", base + 0xa080, 16, 3);
+	clks[IMX7D_USB_HSIC_ROOT_PRE_DIV] = imx_clk_divider2("usb_hsic_pre_div", "usb_hsic_cg", base + 0xa100, 16, 3);
+	clks[IMX7D_PCIE_CTRL_ROOT_PRE_DIV] = imx_clk_divider2("pcie_ctrl_pre_div", "pcie_ctrl_cg", base + 0xa180, 16, 3);
+	clks[IMX7D_PCIE_PHY_ROOT_PRE_DIV] = imx_clk_divider2("pcie_phy_pre_div", "pcie_phy_cg", base + 0xa200, 16, 3);
+	clks[IMX7D_EPDC_PIXEL_ROOT_PRE_DIV] = imx_clk_divider2("epdc_pixel_pre_div", "epdc_pixel_cg", base + 0xa280, 16, 3);
+	clks[IMX7D_LCDIF_PIXEL_ROOT_PRE_DIV] = imx_clk_divider2("lcdif_pixel_pre_div", "lcdif_pixel_cg", base + 0xa300, 16, 3);
+	clks[IMX7D_MIPI_DSI_ROOT_PRE_DIV] = imx_clk_divider2("mipi_dsi_pre_div", "mipi_dsi_cg", base + 0xa380, 16, 3);
+	clks[IMX7D_MIPI_CSI_ROOT_PRE_DIV] = imx_clk_divider2("mipi_csi_pre_div", "mipi_csi_cg", base + 0xa400, 16, 3);
+	clks[IMX7D_MIPI_DPHY_ROOT_PRE_DIV] = imx_clk_divider2("mipi_dphy_pre_div", "mipi_dphy_cg", base + 0xa480, 16, 3);
+	clks[IMX7D_SAI1_ROOT_PRE_DIV] = imx_clk_divider2("sai1_pre_div", "sai1_cg", base + 0xa500, 16, 3);
+	clks[IMX7D_SAI2_ROOT_PRE_DIV] = imx_clk_divider2("sai2_pre_div", "sai2_cg", base + 0xa580, 16, 3);
+	clks[IMX7D_SAI3_ROOT_PRE_DIV] = imx_clk_divider2("sai3_pre_div", "sai3_cg", base + 0xa600, 16, 3);
+	clks[IMX7D_SPDIF_ROOT_PRE_DIV] = imx_clk_divider2("spdif_pre_div", "spdif_cg", base + 0xa680, 16, 3);
+	clks[IMX7D_ENET1_REF_ROOT_PRE_DIV] = imx_clk_divider2("enet1_ref_pre_div", "enet1_ref_cg", base + 0xa700, 16, 3);
+	clks[IMX7D_ENET1_TIME_ROOT_PRE_DIV] = imx_clk_divider2("enet1_time_pre_div", "enet1_time_cg", base + 0xa780, 16, 3);
+	clks[IMX7D_ENET2_REF_ROOT_PRE_DIV] = imx_clk_divider2("enet2_ref_pre_div", "enet2_ref_cg", base + 0xa800, 16, 3);
+	clks[IMX7D_ENET2_TIME_ROOT_PRE_DIV] = imx_clk_divider2("enet2_time_pre_div", "enet2_time_cg", base + 0xa880, 16, 3);
+	clks[IMX7D_ENET_PHY_REF_ROOT_PRE_DIV] = imx_clk_divider2("enet_phy_ref_pre_div", "enet_phy_ref_cg", base + 0xa900, 16, 3);
+	clks[IMX7D_EIM_ROOT_PRE_DIV] = imx_clk_divider2("eim_pre_div", "eim_cg", base + 0xa980, 16, 3);
+	clks[IMX7D_NAND_ROOT_PRE_DIV] = imx_clk_divider2("nand_pre_div", "nand_cg", base + 0xaa00, 16, 3);
+	clks[IMX7D_QSPI_ROOT_PRE_DIV] = imx_clk_divider2("qspi_pre_div", "qspi_cg", base + 0xaa80, 16, 3);
+	clks[IMX7D_USDHC1_ROOT_PRE_DIV] = imx_clk_divider2("usdhc1_pre_div", "usdhc1_cg", base + 0xab00, 16, 3);
+	clks[IMX7D_USDHC2_ROOT_PRE_DIV] = imx_clk_divider2("usdhc2_pre_div", "usdhc2_cg", base + 0xab80, 16, 3);
+	clks[IMX7D_USDHC3_ROOT_PRE_DIV] = imx_clk_divider2("usdhc3_pre_div", "usdhc3_cg", base + 0xac00, 16, 3);
+	clks[IMX7D_CAN1_ROOT_PRE_DIV] = imx_clk_divider2("can1_pre_div", "can1_cg", base + 0xac80, 16, 3);
+	clks[IMX7D_CAN2_ROOT_PRE_DIV] = imx_clk_divider2("can2_pre_div", "can2_cg", base + 0xad00, 16, 3);
+	clks[IMX7D_I2C1_ROOT_PRE_DIV] = imx_clk_divider2("i2c1_pre_div", "i2c1_cg", base + 0xad80, 16, 3);
+	clks[IMX7D_I2C2_ROOT_PRE_DIV] = imx_clk_divider2("i2c2_pre_div", "i2c2_cg", base + 0xae00, 16, 3);
+	clks[IMX7D_I2C3_ROOT_PRE_DIV] = imx_clk_divider2("i2c3_pre_div", "i2c3_cg", base + 0xae80, 16, 3);
+	clks[IMX7D_I2C4_ROOT_PRE_DIV] = imx_clk_divider2("i2c4_pre_div", "i2c4_cg", base + 0xaf00, 16, 3);
+	clks[IMX7D_UART1_ROOT_PRE_DIV] = imx_clk_divider2("uart1_pre_div", "uart1_cg", base + 0xaf80, 16, 3);
+	clks[IMX7D_UART2_ROOT_PRE_DIV] = imx_clk_divider2("uart2_pre_div", "uart2_cg", base + 0xb000, 16, 3);
+	clks[IMX7D_UART3_ROOT_PRE_DIV] = imx_clk_divider2("uart3_pre_div", "uart3_cg", base + 0xb080, 16, 3);
+	clks[IMX7D_UART4_ROOT_PRE_DIV] = imx_clk_divider2("uart4_pre_div", "uart4_cg", base + 0xb100, 16, 3);
+	clks[IMX7D_UART5_ROOT_PRE_DIV] = imx_clk_divider2("uart5_pre_div", "uart5_cg", base + 0xb180, 16, 3);
+	clks[IMX7D_UART6_ROOT_PRE_DIV] = imx_clk_divider2("uart6_pre_div", "uart6_cg", base + 0xb200, 16, 3);
+	clks[IMX7D_UART7_ROOT_PRE_DIV] = imx_clk_divider2("uart7_pre_div", "uart7_cg", base + 0xb280, 16, 3);
+	clks[IMX7D_ECSPI1_ROOT_PRE_DIV] = imx_clk_divider2("ecspi1_pre_div", "ecspi1_cg", base + 0xb300, 16, 3);
+	clks[IMX7D_ECSPI2_ROOT_PRE_DIV] = imx_clk_divider2("ecspi2_pre_div", "ecspi2_cg", base + 0xb380, 16, 3);
+	clks[IMX7D_ECSPI3_ROOT_PRE_DIV] = imx_clk_divider2("ecspi3_pre_div", "ecspi3_cg", base + 0xb400, 16, 3);
+	clks[IMX7D_ECSPI4_ROOT_PRE_DIV] = imx_clk_divider2("ecspi4_pre_div", "ecspi4_cg", base + 0xb480, 16, 3);
+	clks[IMX7D_PWM1_ROOT_PRE_DIV] = imx_clk_divider2("pwm1_pre_div", "pwm1_cg", base + 0xb500, 16, 3);
+	clks[IMX7D_PWM2_ROOT_PRE_DIV] = imx_clk_divider2("pwm2_pre_div", "pwm2_cg", base + 0xb580, 16, 3);
+	clks[IMX7D_PWM3_ROOT_PRE_DIV] = imx_clk_divider2("pwm3_pre_div", "pwm3_cg", base + 0xb600, 16, 3);
+	clks[IMX7D_PWM4_ROOT_PRE_DIV] = imx_clk_divider2("pwm4_pre_div", "pwm4_cg", base + 0xb680, 16, 3);
+	clks[IMX7D_FLEXTIMER1_ROOT_PRE_DIV] = imx_clk_divider2("flextimer1_pre_div", "flextimer1_cg", base + 0xb700, 16, 3);
+	clks[IMX7D_FLEXTIMER2_ROOT_PRE_DIV] = imx_clk_divider2("flextimer2_pre_div", "flextimer2_cg", base + 0xb780, 16, 3);
+	clks[IMX7D_SIM1_ROOT_PRE_DIV] = imx_clk_divider2("sim1_pre_div", "sim1_cg", base + 0xb800, 16, 3);
+	clks[IMX7D_SIM2_ROOT_PRE_DIV] = imx_clk_divider2("sim2_pre_div", "sim2_cg", base + 0xb880, 16, 3);
+	clks[IMX7D_GPT1_ROOT_PRE_DIV] = imx_clk_divider2("gpt1_pre_div", "gpt1_cg", base + 0xb900, 16, 3);
+	clks[IMX7D_GPT2_ROOT_PRE_DIV] = imx_clk_divider2("gpt2_pre_div", "gpt2_cg", base + 0xb980, 16, 3);
+	clks[IMX7D_GPT3_ROOT_PRE_DIV] = imx_clk_divider2("gpt3_pre_div", "gpt3_cg", base + 0xba00, 16, 3);
+	clks[IMX7D_GPT4_ROOT_PRE_DIV] = imx_clk_divider2("gpt4_pre_div", "gpt4_cg", base + 0xba80, 16, 3);
+	clks[IMX7D_TRACE_ROOT_PRE_DIV] = imx_clk_divider2("trace_pre_div", "trace_cg", base + 0xbb00, 16, 3);
+	clks[IMX7D_WDOG_ROOT_PRE_DIV] = imx_clk_divider2("wdog_pre_div", "wdog_cg", base + 0xbb80, 16, 3);
+	clks[IMX7D_CSI_MCLK_ROOT_PRE_DIV] = imx_clk_divider2("csi_mclk_pre_div", "csi_mclk_cg", base + 0xbc00, 16, 3);
+	clks[IMX7D_AUDIO_MCLK_ROOT_PRE_DIV] = imx_clk_divider2("audio_mclk_pre_div", "audio_mclk_cg", base + 0xbc80, 16, 3);
+	clks[IMX7D_WRCLK_ROOT_PRE_DIV] = imx_clk_divider2("wrclk_pre_div", "wrclk_cg", base + 0xbd00, 16, 3);
+	clks[IMX7D_CLKO1_ROOT_PRE_DIV] = imx_clk_divider2("clko1_pre_div", "clko1_cg", base + 0xbd80, 16, 3);
+	clks[IMX7D_CLKO2_ROOT_PRE_DIV] = imx_clk_divider2("clko2_pre_div", "clko2_cg", base + 0xbe00, 16, 3);
+
+	clks[IMX7D_ARM_A7_ROOT_DIV] = imx_clk_divider2("arm_a7_div", "arm_a7_cg", base + 0x8000, 0, 3);
+	clks[IMX7D_ARM_M4_ROOT_DIV] = imx_clk_divider2("arm_m4_div", "arm_m4_cg", base + 0x8080, 0, 3);
+	clks[IMX7D_ARM_M0_ROOT_DIV] = imx_clk_divider2("arm_m0_div", "arm_m0_cg", base + 0x8100, 0, 3);
+	clks[IMX7D_MAIN_AXI_ROOT_DIV] = imx_clk_divider2("axi_post_div", "axi_pre_div", base + 0x8800, 0, 6);
+	clks[IMX7D_DISP_AXI_ROOT_DIV] = imx_clk_divider2("disp_axi_post_div", "disp_axi_pre_div", base + 0x8880, 0, 6);
+	clks[IMX7D_ENET_AXI_ROOT_DIV] = imx_clk_divider2("enet_axi_post_div", "enet_axi_pre_div", base + 0x8900, 0, 6);
+	clks[IMX7D_NAND_USDHC_BUS_ROOT_DIV] = imx_clk_divider2("nand_usdhc_post_div", "nand_usdhc_pre_div", base + 0x8980, 0, 6);
+	clks[IMX7D_AHB_CHANNEL_ROOT_DIV] = imx_clk_divider2("ahb_post_div", "ahb_pre_div", base + 0x9000, 0, 6);
+	clks[IMX7D_DRAM_ROOT_DIV] = imx_clk_divider2("dram_post_div", "dram_cg", base + 0x9880, 0, 3);
+	clks[IMX7D_DRAM_PHYM_ALT_ROOT_DIV] = imx_clk_divider2("dram_phym_alt_post_div", "dram_phym_alt_pre_div", base + 0xa000, 0, 3);
+	clks[IMX7D_DRAM_ALT_ROOT_DIV] = imx_clk_divider2("dram_alt_post_div", "dram_alt_pre_div", base + 0xa080, 0, 3);
+	clks[IMX7D_USB_HSIC_ROOT_DIV] = imx_clk_divider2("usb_hsic_post_div", "usb_hsic_pre_div", base + 0xa100, 0, 6);
+	clks[IMX7D_PCIE_CTRL_ROOT_DIV] = imx_clk_divider2("pcie_ctrl_post_div", "pcie_ctrl_pre_div", base + 0xa180, 0, 6);
+	clks[IMX7D_PCIE_PHY_ROOT_DIV] = imx_clk_divider2("pcie_phy_post_div", "pcie_phy_pre_div", base + 0xa200, 0, 6);
+	clks[IMX7D_EPDC_PIXEL_ROOT_DIV] = imx_clk_divider2("epdc_pixel_post_div", "epdc_pixel_pre_div", base + 0xa280, 0, 6);
+	clks[IMX7D_LCDIF_PIXEL_ROOT_DIV] = imx_clk_divider2("lcdif_pixel_post_div", "lcdif_pixel_pre_div", base + 0xa300, 0, 6);
+	clks[IMX7D_MIPI_DSI_ROOT_DIV] = imx_clk_divider2("mipi_dsi_post_div", "mipi_dsi_pre_div", base + 0xa380, 0, 6);
+	clks[IMX7D_MIPI_CSI_ROOT_DIV] = imx_clk_divider2("mipi_csi_post_div", "mipi_csi_pre_div", base + 0xa400, 0, 6);
+	clks[IMX7D_MIPI_DPHY_ROOT_DIV] = imx_clk_divider2("mipi_dphy_post_div", "mipi_csi_dphy_div", base + 0xa480, 0, 6);
+	clks[IMX7D_SAI1_ROOT_DIV] = imx_clk_divider2("sai1_post_div", "sai1_pre_div", base + 0xa500, 0, 6);
+	clks[IMX7D_SAI2_ROOT_DIV] = imx_clk_divider2("sai2_post_div", "sai2_pre_div", base + 0xa580, 0, 6);
+	clks[IMX7D_SAI3_ROOT_DIV] = imx_clk_divider2("sai3_post_div", "sai3_pre_div", base + 0xa600, 0, 6);
+	clks[IMX7D_SPDIF_ROOT_DIV] = imx_clk_divider2("spdif_post_div", "spdif_pre_div", base + 0xa680, 0, 6);
+	clks[IMX7D_ENET1_REF_ROOT_DIV] = imx_clk_divider2("enet1_ref_post_div", "enet1_ref_pre_div", base + 0xa700, 0, 6);
+	clks[IMX7D_ENET1_TIME_ROOT_DIV] = imx_clk_divider2("enet1_time_post_div", "enet1_time_pre_div", base + 0xa780, 0, 6);
+	clks[IMX7D_ENET2_REF_ROOT_DIV] = imx_clk_divider2("enet2_ref_post_div", "enet2_ref_pre_div", base + 0xa800, 0, 6);
+	clks[IMX7D_ENET2_TIME_ROOT_DIV] = imx_clk_divider2("enet2_time_post_div", "enet2_time_pre_div", base + 0xa880, 0, 6);
+	clks[IMX7D_ENET_PHY_REF_ROOT_DIV] = imx_clk_divider2("enet_phy_ref_post_div", "enet_phy_ref_pre_div", base + 0xa900, 0, 6);
+	clks[IMX7D_EIM_ROOT_DIV] = imx_clk_divider2("eim_post_div", "eim_pre_div", base + 0xa980, 0, 6);
+	clks[IMX7D_NAND_ROOT_DIV] = imx_clk_divider2("nand_post_div", "nand_pre_div", base + 0xaa00, 0, 6);
+	clks[IMX7D_QSPI_ROOT_DIV] = imx_clk_divider2("qspi_post_div", "qspi_pre_div", base + 0xaa80, 0, 6);
+	clks[IMX7D_USDHC1_ROOT_DIV] = imx_clk_divider2("usdhc1_post_div", "usdhc1_pre_div", base + 0xab00, 0, 6);
+	clks[IMX7D_USDHC2_ROOT_DIV] = imx_clk_divider2("usdhc2_post_div", "usdhc2_pre_div", base + 0xab80, 0, 6);
+	clks[IMX7D_USDHC3_ROOT_DIV] = imx_clk_divider2("usdhc3_post_div", "usdhc3_pre_div", base + 0xac00, 0, 6);
+	clks[IMX7D_CAN1_ROOT_DIV] = imx_clk_divider2("can1_post_div", "can1_pre_div", base + 0xac80, 0, 6);
+	clks[IMX7D_CAN2_ROOT_DIV] = imx_clk_divider2("can2_post_div", "can2_pre_div", base + 0xad00, 0, 6);
+	clks[IMX7D_I2C1_ROOT_DIV] = imx_clk_divider2("i2c1_post_div", "i2c1_pre_div", base + 0xad80, 0, 6);
+	clks[IMX7D_I2C2_ROOT_DIV] = imx_clk_divider2("i2c2_post_div", "i2c2_pre_div", base + 0xae00, 0, 6);
+	clks[IMX7D_I2C3_ROOT_DIV] = imx_clk_divider2("i2c3_post_div", "i2c3_pre_div", base + 0xae80, 0, 6);
+	clks[IMX7D_I2C4_ROOT_DIV] = imx_clk_divider2("i2c4_post_div", "i2c4_pre_div", base + 0xaf00, 0, 6);
+	clks[IMX7D_UART1_ROOT_DIV] = imx_clk_divider2("uart1_post_div", "uart1_pre_div", base + 0xaf80, 0, 6);
+	clks[IMX7D_UART2_ROOT_DIV] = imx_clk_divider2("uart2_post_div", "uart2_pre_div", base + 0xb000, 0, 6);
+	clks[IMX7D_UART3_ROOT_DIV] = imx_clk_divider2("uart3_post_div", "uart3_pre_div", base + 0xb080, 0, 6);
+	clks[IMX7D_UART4_ROOT_DIV] = imx_clk_divider2("uart4_post_div", "uart4_pre_div", base + 0xb100, 0, 6);
+	clks[IMX7D_UART5_ROOT_DIV] = imx_clk_divider2("uart5_post_div", "uart5_pre_div", base + 0xb180, 0, 6);
+	clks[IMX7D_UART6_ROOT_DIV] = imx_clk_divider2("uart6_post_div", "uart6_pre_div", base + 0xb200, 0, 6);
+	clks[IMX7D_UART7_ROOT_DIV] = imx_clk_divider2("uart7_post_div", "uart7_pre_div", base + 0xb280, 0, 6);
+	clks[IMX7D_ECSPI1_ROOT_DIV] = imx_clk_divider2("ecspi1_post_div", "ecspi1_pre_div", base + 0xb300, 0, 6);
+	clks[IMX7D_ECSPI2_ROOT_DIV] = imx_clk_divider2("ecspi2_post_div", "ecspi2_pre_div", base + 0xb380, 0, 6);
+	clks[IMX7D_ECSPI3_ROOT_DIV] = imx_clk_divider2("ecspi3_post_div", "ecspi3_pre_div", base + 0xb400, 0, 6);
+	clks[IMX7D_ECSPI4_ROOT_DIV] = imx_clk_divider2("ecspi4_post_div", "ecspi4_pre_div", base + 0xb480, 0, 6);
+	clks[IMX7D_PWM1_ROOT_DIV] = imx_clk_divider2("pwm1_post_div", "pwm1_pre_div", base + 0xb500, 0, 6);
+	clks[IMX7D_PWM2_ROOT_DIV] = imx_clk_divider2("pwm2_post_div", "pwm2_pre_div", base + 0xb580, 0, 6);
+	clks[IMX7D_PWM3_ROOT_DIV] = imx_clk_divider2("pwm3_post_div", "pwm3_pre_div", base + 0xb600, 0, 6);
+	clks[IMX7D_PWM4_ROOT_DIV] = imx_clk_divider2("pwm4_post_div", "pwm4_pre_div", base + 0xb680, 0, 6);
+	clks[IMX7D_FLEXTIMER1_ROOT_DIV] = imx_clk_divider2("flextimer1_post_div", "flextimer1_pre_div", base + 0xb700, 0, 6);
+	clks[IMX7D_FLEXTIMER2_ROOT_DIV] = imx_clk_divider2("flextimer2_post_div", "flextimer2_pre_div", base + 0xb780, 0, 6);
+	clks[IMX7D_SIM1_ROOT_DIV] = imx_clk_divider2("sim1_post_div", "sim1_pre_div", base + 0xb800, 0, 6);
+	clks[IMX7D_SIM2_ROOT_DIV] = imx_clk_divider2("sim2_post_div", "sim2_pre_div", base + 0xb880, 0, 6);
+	clks[IMX7D_GPT1_ROOT_DIV] = imx_clk_divider2("gpt1_post_div", "gpt1_pre_div", base + 0xb900, 0, 6);
+	clks[IMX7D_GPT2_ROOT_DIV] = imx_clk_divider2("gpt2_post_div", "gpt2_pre_div", base + 0xb980, 0, 6);
+	clks[IMX7D_GPT3_ROOT_DIV] = imx_clk_divider2("gpt3_post_div", "gpt3_pre_div", base + 0xba00, 0, 6);
+	clks[IMX7D_GPT4_ROOT_DIV] = imx_clk_divider2("gpt4_post_div", "gpt4_pre_div", base + 0xba80, 0, 6);
+	clks[IMX7D_TRACE_ROOT_DIV] = imx_clk_divider2("trace_post_div", "trace_pre_div", base + 0xbb00, 0, 6);
+	clks[IMX7D_WDOG_ROOT_DIV] = imx_clk_divider2("wdog_post_div", "wdog_pre_div", base + 0xbb80, 0, 6);
+	clks[IMX7D_CSI_MCLK_ROOT_DIV] = imx_clk_divider2("csi_mclk_post_div", "csi_mclk_pre_div", base + 0xbc00, 0, 6);
+	clks[IMX7D_AUDIO_MCLK_ROOT_DIV] = imx_clk_divider2("audio_mclk_post_div", "audio_mclk_pre_div", base + 0xbc80, 0, 6);
+	clks[IMX7D_WRCLK_ROOT_DIV] = imx_clk_divider2("wrclk_post_div", "wrclk_pre_div", base + 0xbd00, 0, 6);
+	clks[IMX7D_CLKO1_ROOT_DIV] = imx_clk_divider2("clko1_post_div", "clko1_pre_div", base + 0xbd80, 0, 6);
+	clks[IMX7D_CLKO2_ROOT_DIV] = imx_clk_divider2("clko2_post_div", "clko2_pre_div", base + 0xbe00, 0, 6);
+
+	clks[IMX7D_ARM_A7_ROOT_CLK] = imx_clk_gate4("arm_a7_root_clk", "arm_a7_div", base + 0x4000, 0);
+	clks[IMX7D_ARM_M4_ROOT_CLK] = imx_clk_gate4("arm_m4_root_clk", "arm_m4_div", base + 0x4010, 0);
+	clks[IMX7D_ARM_M0_ROOT_CLK] = imx_clk_gate4("arm_m0_root_clk", "arm_m0_div", base + 0x4020, 0);
+	clks[IMX7D_MAIN_AXI_ROOT_CLK] = imx_clk_gate4("main_axi_root_clk", "axi_post_div", base + 0x4040, 0);
+	clks[IMX7D_DISP_AXI_ROOT_CLK] = imx_clk_gate4("disp_axi_root_clk", "disp_axi_post_div", base + 0x4050, 0);
+	clks[IMX7D_ENET_AXI_ROOT_CLK] = imx_clk_gate4("enet_axi_root_clk", "enet_axi_post_div", base + 0x4060, 0);
+	clks[IMX7D_OCRAM_CLK] = imx_clk_gate4("ocram_clk", "axi_post_div", base + 0x4110, 0);
+	clks[IMX7D_OCRAM_S_CLK] = imx_clk_gate4("ocram_s_clk", "ahb_post_div", base + 0x4120, 0);
+	clks[IMX7D_NAND_USDHC_BUS_ROOT_CLK] = imx_clk_gate4("nand_usdhc_root_clk", "nand_usdhc_post_div", base + 0x4130, 0);
+	clks[IMX7D_AHB_CHANNEL_ROOT_CLK] = imx_clk_gate4("ahb_root_clk", "ahb_post_div", base + 0x4200, 0);
+	clks[IMX7D_DRAM_ROOT_CLK] = imx_clk_gate4("dram_root_clk", "dram_post_div", base + 0x4130, 0);
+	clks[IMX7D_DRAM_PHYM_ROOT_CLK] = imx_clk_gate4("dram_phym_root_clk", "dram_phym_cg", base + 0x4130, 0);
+	clks[IMX7D_DRAM_PHYM_ALT_ROOT_CLK] = imx_clk_gate4("dram_phym_alt_root_clk", "dram_phym_alt_post_div", base + 0x4130, 0);
+	clks[IMX7D_DRAM_ALT_ROOT_CLK] = imx_clk_gate4("dram_alt_root_clk", "dram_alt_post_div", base + 0x4130, 0);
+	clks[IMX7D_USB_HSIC_ROOT_CLK] = imx_clk_gate4("usb_hsic_root_clk", "usb_hsic_post_div", base + 0x4420, 0);
+	clks[IMX7D_PCIE_CTRL_ROOT_CLK] = imx_clk_gate4("pcie_ctrl_root_clk", "pcie_ctrl_post_div", base + 0x4600, 0);
+	clks[IMX7D_PCIE_PHY_ROOT_CLK] = imx_clk_gate4("pcie_phy_root_clk", "pcie_phy_post_div", base + 0x4600, 0);
+	clks[IMX7D_EPDC_PIXEL_ROOT_CLK] = imx_clk_gate4("epdc_pixel_root_clk", "epdc_pixel_post_div", base + 0x44a0, 0);
+	clks[IMX7D_LCDIF_PIXEL_ROOT_CLK] = imx_clk_gate4("lcdif_pixel_root_clk", "lcdif_pixel_post_div", base + 0x44b0, 0);
+	clks[IMX7D_MIPI_DSI_ROOT_CLK] = imx_clk_gate4("mipi_dsi_root_clk", "mipi_dsi_post_div", base + 0x4650, 0);
+	clks[IMX7D_MIPI_CSI_ROOT_CLK] = imx_clk_gate4("mipi_csi_root_clk", "mipi_csi_post_div", base + 0x4640, 0);
+	clks[IMX7D_MIPI_DPHY_ROOT_CLK] = imx_clk_gate4("mipi_dphy_root_clk", "mipi_dphy_post_div", base + 0x4660, 0);
+	clks[IMX7D_SAI1_ROOT_CLK] = imx_clk_gate4("sai1_root_clk", "sai1_post_div", base + 0x48c0, 0);
+	clks[IMX7D_SAI2_ROOT_CLK] = imx_clk_gate4("sai2_root_clk", "sai2_post_div", base + 0x48d0, 0);
+	clks[IMX7D_SAI3_ROOT_CLK] = imx_clk_gate4("sai3_root_clk", "sai3_post_div", base + 0x48e0, 0);
+	clks[IMX7D_SPDIF_ROOT_CLK] = imx_clk_gate4("spdif_root_clk", "spdif_post_div", base + 0x44d0, 0);
+	clks[IMX7D_ENET1_REF_ROOT_CLK] = imx_clk_gate4("enet1_ref_root_clk", "enet1_ref_post_div", base + 0x44e0, 0);
+	clks[IMX7D_ENET1_TIME_ROOT_CLK] = imx_clk_gate4("enet1_time_root_clk", "enet1_time_post_div", base + 0x44f0, 0);
+	clks[IMX7D_ENET2_REF_ROOT_CLK] = imx_clk_gate4("enet2_ref_root_clk", "enet2_ref_post_div", base + 0x4500, 0);
+	clks[IMX7D_ENET2_TIME_ROOT_CLK] = imx_clk_gate4("enet2_time_root_clk", "enet2_time_post_div", base + 0x4510, 0);
+	clks[IMX7D_ENET_PHY_REF_ROOT_CLK] = imx_clk_gate4("enet_phy_ref_root_clk", "enet_phy_ref_post_div", base + 0x4520, 0);
+	clks[IMX7D_EIM_ROOT_CLK] = imx_clk_gate4("eim_root_clk", "eim_post_div", base + 0x4160, 0);
+	clks[IMX7D_NAND_ROOT_CLK] = imx_clk_gate4("nand_root_clk", "nand_post_div", base + 0x4140, 0);
+	clks[IMX7D_QSPI_ROOT_CLK] = imx_clk_gate4("qspi_root_clk", "qspi_post_div", base + 0x4150, 0);
+	clks[IMX7D_USDHC1_ROOT_CLK] = imx_clk_gate4("usdhc1_root_clk", "usdhc1_post_div", base + 0x46c0, 0);
+	clks[IMX7D_USDHC2_ROOT_CLK] = imx_clk_gate4("usdhc2_root_clk", "usdhc2_post_div", base + 0x46d0, 0);
+	clks[IMX7D_USDHC3_ROOT_CLK] = imx_clk_gate4("usdhc3_root_clk", "usdhc3_post_div", base + 0x46e0, 0);
+	clks[IMX7D_CAN1_ROOT_CLK] = imx_clk_gate4("can1_root_clk", "can1_post_div", base + 0x4740, 0);
+	clks[IMX7D_CAN2_ROOT_CLK] = imx_clk_gate4("can2_root_clk", "can2_post_div", base + 0x4750, 0);
+	clks[IMX7D_I2C1_ROOT_CLK] = imx_clk_gate4("i2c1_root_clk", "i2c1_post_div", base + 0x4880, 0);
+	clks[IMX7D_I2C2_ROOT_CLK] = imx_clk_gate4("i2c2_root_clk", "i2c2_post_div", base + 0x4890, 0);
+	clks[IMX7D_I2C3_ROOT_CLK] = imx_clk_gate4("i2c3_root_clk", "i2c3_post_div", base + 0x48a0, 0);
+	clks[IMX7D_I2C4_ROOT_CLK] = imx_clk_gate4("i2c4_root_clk", "i2c4_post_div", base + 0x48b0, 0);
+	clks[IMX7D_UART1_ROOT_CLK] = imx_clk_gate4("uart1_root_clk", "uart1_post_div", base + 0x4940, 0);
+	clks[IMX7D_UART2_ROOT_CLK] = imx_clk_gate4("uart2_root_clk", "uart2_post_div", base + 0x4950, 0);
+	clks[IMX7D_UART3_ROOT_CLK] = imx_clk_gate4("uart3_root_clk", "uart3_post_div", base + 0x4960, 0);
+	clks[IMX7D_UART4_ROOT_CLK] = imx_clk_gate4("uart4_root_clk", "uart4_post_div", base + 0x4970, 0);
+	clks[IMX7D_UART5_ROOT_CLK] = imx_clk_gate4("uart5_root_clk", "uart5_post_div", base + 0x4980, 0);
+	clks[IMX7D_UART6_ROOT_CLK] = imx_clk_gate4("uart6_root_clk", "uart6_post_div", base + 0x4990, 0);
+	clks[IMX7D_UART7_ROOT_CLK] = imx_clk_gate4("uart7_root_clk", "uart7_post_div", base + 0x49a0, 0);
+	clks[IMX7D_ECSPI1_ROOT_CLK] = imx_clk_gate4("ecspi1_root_clk", "ecspi1_post_div", base + 0x4780, 0);
+	clks[IMX7D_ECSPI2_ROOT_CLK] = imx_clk_gate4("ecspi2_root_clk", "ecspi2_post_div", base + 0x4790, 0);
+	clks[IMX7D_ECSPI3_ROOT_CLK] = imx_clk_gate4("ecspi3_root_clk", "ecspi3_post_div", base + 0x47a0, 0);
+	clks[IMX7D_ECSPI4_ROOT_CLK] = imx_clk_gate4("ecspi4_root_clk", "ecspi4_post_div", base + 0x47b0, 0);
+	clks[IMX7D_PWM1_ROOT_CLK] = imx_clk_gate4("pwm1_root_clk", "pwm1_post_div", base + 0x4840, 0);
+	clks[IMX7D_PWM2_ROOT_CLK] = imx_clk_gate4("pwm2_root_clk", "pwm2_post_div", base + 0x4850, 0);
+	clks[IMX7D_PWM3_ROOT_CLK] = imx_clk_gate4("pwm3_root_clk", "pwm3_post_div", base + 0x4860, 0);
+	clks[IMX7D_PWM4_ROOT_CLK] = imx_clk_gate4("pwm4_root_clk", "pwm4_post_div", base + 0x4870, 0);
+	clks[IMX7D_FLEXTIMER1_ROOT_CLK] = imx_clk_gate4("flextimer1_root_clk", "flextimer1_post_div", base + 0x4800, 0);
+	clks[IMX7D_FLEXTIMER2_ROOT_CLK] = imx_clk_gate4("flextimer2_root_clk", "flextimer2_post_div", base + 0x4810, 0);
+	clks[IMX7D_SIM1_ROOT_CLK] = imx_clk_gate4("sim1_root_clk", "sim1_post_div", base + 0x4900, 0);
+	clks[IMX7D_SIM2_ROOT_CLK] = imx_clk_gate4("sim2_root_clk", "sim2_post_div", base + 0x4910, 0);
+	clks[IMX7D_GPT1_ROOT_CLK] = imx_clk_gate4("gpt1_root_clk", "gpt1_post_div", base + 0x47c0, 0);
+	clks[IMX7D_GPT2_ROOT_CLK] = imx_clk_gate4("gpt2_root_clk", "gpt2_post_div", base + 0x47d0, 0);
+	clks[IMX7D_GPT3_ROOT_CLK] = imx_clk_gate4("gpt3_root_clk", "gpt3_post_div", base + 0x47e0, 0);
+	clks[IMX7D_GPT4_ROOT_CLK] = imx_clk_gate4("gpt4_root_clk", "gpt4_post_div", base + 0x47f0, 0);
+	clks[IMX7D_TRACE_ROOT_CLK] = imx_clk_gate4("trace_root_clk", "trace_post_div", base + 0x4300, 0);
+	clks[IMX7D_WDOG1_ROOT_CLK] = imx_clk_gate4("wdog1_root_clk", "wdog_post_div", base + 0x49c0, 0);
+	clks[IMX7D_WDOG2_ROOT_CLK] = imx_clk_gate4("wdog2_root_clk", "wdog_post_div", base + 0x49d0, 0);
+	clks[IMX7D_WDOG3_ROOT_CLK] = imx_clk_gate4("wdog3_root_clk", "wdog_post_div", base + 0x49e0, 0);
+	clks[IMX7D_WDOG4_ROOT_CLK] = imx_clk_gate4("wdog4_root_clk", "wdog_post_div", base + 0x49f0, 0);
+	clks[IMX7D_CSI_MCLK_ROOT_CLK] = imx_clk_gate4("csi_mclk_root_clk", "csi_mclk_post_div", base + 0x4490, 0);
+	clks[IMX7D_AUDIO_MCLK_ROOT_CLK] = imx_clk_gate4("audio_mclk_root_clk", "audio_mclk_post_div", base + 0x4790, 0);
+	clks[IMX7D_WRCLK_ROOT_CLK] = imx_clk_gate4("wrclk_root_clk", "wrclk_post_div", base + 0x47a0, 0);
+	clks[IMX7D_ADC_ROOT_CLK] = imx_clk_gate4("adc_root_clk", "ipg_root_clk", base + 0x4200, 0);
 
 	clks[IMX7D_GPT_3M_CLK] = imx_clk_fixed_factor("gpt_3m", "osc", 1, 8);
 
@@ -846,28 +854,13 @@ static void __init imx7d_clocks_init(struct device_node *ccm_node)
 	clk_data.clk_num = ARRAY_SIZE(clks);
 	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
 
-	/* TO BE FIXED LATER
-	 * Enable all clock to bring up imx7, otherwise system will be halt and block
-	 * the other part upstream Because imx7d clock design changed, clock framework
-	 * need do a little modify.
-	 * Dong Aisheng is working on this. After that, this part need be changed.
-	 */
-	for (i = 0; i < IMX7D_CLK_END; i++)
-		clk_prepare_enable(clks[i]);
+	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
+		clk_prepare_enable(clks[clks_init_on[i]]);
 
 	/* use old gpt clk setting, gpt1 root clk must be twice as gpt counter freq */
 	clk_set_parent(clks[IMX7D_GPT1_ROOT_SRC], clks[IMX7D_OSC_24M_CLK]);
 
-	/*
-	 * init enet clock source:
-	 * 	AXI clock source is 250MHz
-	 *	Phy refrence clock is 25MHz
-	 *	1588 time clock source is 100MHz
-	 */
 	clk_set_parent(clks[IMX7D_ENET_AXI_ROOT_SRC], clks[IMX7D_PLL_ENET_MAIN_250M_CLK]);
-	clk_set_parent(clks[IMX7D_ENET_PHY_REF_ROOT_SRC], clks[IMX7D_PLL_ENET_MAIN_25M_CLK]);
-	clk_set_parent(clks[IMX7D_ENET1_TIME_ROOT_SRC], clks[IMX7D_PLL_ENET_MAIN_100M_CLK]);
-	clk_set_parent(clks[IMX7D_ENET2_TIME_ROOT_SRC], clks[IMX7D_PLL_ENET_MAIN_100M_CLK]);
 
 	/* set uart module clock's parent clock source that must be great then 80MHz */
 	clk_set_parent(clks[IMX7D_UART1_ROOT_SRC], clks[IMX7D_OSC_24M_CLK]);
diff --git a/drivers/clk/imx/clk-pllv3.c b/drivers/clk/imx/clk-pllv3.c
index 4826b3c9e19e..19f9b622981a 100644
--- a/drivers/clk/imx/clk-pllv3.c
+++ b/drivers/clk/imx/clk-pllv3.c
@@ -29,8 +29,8 @@
  * struct clk_pllv3 - IMX PLL clock version 3
  * @clk_hw:	 clock source
  * @base:	 base address of PLL registers
- * @powerup_set: set POWER bit to power up the PLL
- * @powerdown:   pll powerdown offset bit
+ * @power_bit:	 pll power bit mask
+ * @powerup_set: set power_bit to power up the PLL
  * @div_mask:	 mask of divider bits
  * @div_shift:	 shift of divider bits
  *
@@ -40,8 +40,8 @@
 struct clk_pllv3 {
 	struct clk_hw	hw;
 	void __iomem	*base;
+	u32		power_bit;
 	bool		powerup_set;
-	u32		powerdown;
 	u32		div_mask;
 	u32		div_shift;
 	unsigned long	ref_clock;
@@ -52,7 +52,7 @@ struct clk_pllv3 {
 static int clk_pllv3_wait_lock(struct clk_pllv3 *pll)
 {
 	unsigned long timeout = jiffies + msecs_to_jiffies(10);
-	u32 val = readl_relaxed(pll->base) & pll->powerdown;
+	u32 val = readl_relaxed(pll->base) & pll->power_bit;
 
 	/* No need to wait for lock when pll is not powered up */
 	if ((pll->powerup_set && !val) || (!pll->powerup_set && val))
@@ -77,9 +77,9 @@ static int clk_pllv3_prepare(struct clk_hw *hw)
 
 	val = readl_relaxed(pll->base);
 	if (pll->powerup_set)
-		val |= BM_PLL_POWER;
+		val |= pll->power_bit;
 	else
-		val &= ~BM_PLL_POWER;
+		val &= ~pll->power_bit;
 	writel_relaxed(val, pll->base);
 
 	return clk_pllv3_wait_lock(pll);
@@ -92,9 +92,9 @@ static void clk_pllv3_unprepare(struct clk_hw *hw)
 
 	val = readl_relaxed(pll->base);
 	if (pll->powerup_set)
-		val &= ~BM_PLL_POWER;
+		val &= ~pll->power_bit;
 	else
-		val |= BM_PLL_POWER;
+		val |= pll->power_bit;
 	writel_relaxed(val, pll->base);
 }
 
@@ -218,8 +218,12 @@ static unsigned long clk_pllv3_av_recalc_rate(struct clk_hw *hw,
 	u32 mfn = readl_relaxed(pll->base + PLL_NUM_OFFSET);
 	u32 mfd = readl_relaxed(pll->base + PLL_DENOM_OFFSET);
 	u32 div = readl_relaxed(pll->base) & pll->div_mask;
+	u64 temp64 = (u64)parent_rate;
 
-	return (parent_rate * div) + ((parent_rate / mfd) * mfn);
+	temp64 *= mfn;
+	do_div(temp64, mfd);
+
+	return (parent_rate * div) + (u32)temp64;
 }
 
 static long clk_pllv3_av_round_rate(struct clk_hw *hw, unsigned long rate,
@@ -243,7 +247,7 @@ static long clk_pllv3_av_round_rate(struct clk_hw *hw, unsigned long rate,
 	do_div(temp64, parent_rate);
 	mfn = temp64;
 
-	return parent_rate * div + parent_rate / mfd * mfn;
+	return parent_rate * div + parent_rate * mfn / mfd;
 }
 
 static int clk_pllv3_av_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -312,7 +316,7 @@ struct clk *imx_clk_pllv3(enum imx_pllv3_type type, const char *name,
 	if (!pll)
 		return ERR_PTR(-ENOMEM);
 
-	pll->powerdown = BM_PLL_POWER;
+	pll->power_bit = BM_PLL_POWER;
 
 	switch (type) {
 	case IMX_PLLV3_SYS:
@@ -328,7 +332,7 @@ struct clk *imx_clk_pllv3(enum imx_pllv3_type type, const char *name,
 		ops = &clk_pllv3_av_ops;
 		break;
 	case IMX_PLLV3_ENET_IMX7:
-		pll->powerdown = IMX7_ENET_PLL_POWER;
+		pll->power_bit = IMX7_ENET_PLL_POWER;
 		pll->ref_clock = 1000000000;
 		ops = &clk_pllv3_enet_ops;
 		break;
diff --git a/drivers/clk/imx/clk-vf610.c b/drivers/clk/imx/clk-vf610.c
index 3a1f24475ee4..0476353ab423 100644
--- a/drivers/clk/imx/clk-vf610.c
+++ b/drivers/clk/imx/clk-vf610.c
@@ -315,12 +315,12 @@ static void __init vf610_clocks_init(struct device_node *ccm_node)
 
 	clk[VF610_CLK_PIT] = imx_clk_gate2("pit", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(7));
 
-	clk[VF610_CLK_UART0] = imx_clk_gate2("uart0", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(7));
-	clk[VF610_CLK_UART1] = imx_clk_gate2("uart1", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(8));
-	clk[VF610_CLK_UART2] = imx_clk_gate2("uart2", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(9));
-	clk[VF610_CLK_UART3] = imx_clk_gate2("uart3", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(10));
-	clk[VF610_CLK_UART4] = imx_clk_gate2("uart4", "ipg_bus", CCM_CCGR6, CCM_CCGRx_CGn(9));
-	clk[VF610_CLK_UART5] = imx_clk_gate2("uart5", "ipg_bus", CCM_CCGR6, CCM_CCGRx_CGn(10));
+	clk[VF610_CLK_UART0] = imx_clk_gate2_cgr("uart0", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(7), 0x2);
+	clk[VF610_CLK_UART1] = imx_clk_gate2_cgr("uart1", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(8), 0x2);
+	clk[VF610_CLK_UART2] = imx_clk_gate2_cgr("uart2", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(9), 0x2);
+	clk[VF610_CLK_UART3] = imx_clk_gate2_cgr("uart3", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(10), 0x2);
+	clk[VF610_CLK_UART4] = imx_clk_gate2_cgr("uart4", "ipg_bus", CCM_CCGR6, CCM_CCGRx_CGn(9), 0x2);
+	clk[VF610_CLK_UART5] = imx_clk_gate2_cgr("uart5", "ipg_bus", CCM_CCGR6, CCM_CCGRx_CGn(10), 0x2);
 
 	clk[VF610_CLK_I2C0] = imx_clk_gate2("i2c0", "ipg_bus", CCM_CCGR4, CCM_CCGRx_CGn(6));
 	clk[VF610_CLK_I2C1] = imx_clk_gate2("i2c1", "ipg_bus", CCM_CCGR4, CCM_CCGRx_CGn(7));
diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h
index 508d0fad84cf..a81c0385ed64 100644
--- a/drivers/clk/imx/clk.h
+++ b/drivers/clk/imx/clk.h
@@ -51,28 +51,6 @@ struct clk * imx_obtain_fixed_clock(
 struct clk *imx_clk_gate_exclusive(const char *name, const char *parent,
 	 void __iomem *reg, u8 shift, u32 exclusive_mask);
 
-static inline struct clk *imx_clk_gate2(const char *name, const char *parent,
-		void __iomem *reg, u8 shift)
-{
-	return clk_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT, reg,
-			shift, 0x3, 0, &imx_ccm_lock, NULL);
-}
-
-static inline struct clk *imx_clk_gate2_shared(const char *name,
-		const char *parent, void __iomem *reg, u8 shift,
-		unsigned int *share_count)
-{
-	return clk_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT, reg,
-			shift, 0x3, 0, &imx_ccm_lock, share_count);
-}
-
-static inline struct clk *imx_clk_gate2_cgr(const char *name, const char *parent,
-		void __iomem *reg, u8 shift, u8 cgr_val)
-{
-	return clk_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT, reg,
-			shift, cgr_val, 0, &imx_ccm_lock, NULL);
-}
-
 struct clk *imx_clk_pfd(const char *name, const char *parent_name,
 		void __iomem *reg, u8 idx);
 
@@ -97,6 +75,13 @@ static inline struct clk *imx_clk_fixed(const char *name, int rate)
 	return clk_register_fixed_rate(NULL, name, NULL, 0, rate);
 }
 
+static inline struct clk *imx_clk_fixed_factor(const char *name,
+		const char *parent, unsigned int mult, unsigned int div)
+{
+	return clk_register_fixed_factor(NULL, name, parent,
+			CLK_SET_RATE_PARENT, mult, div);
+}
+
 static inline struct clk *imx_clk_divider(const char *name, const char *parent,
 		void __iomem *reg, u8 shift, u8 width)
 {
@@ -112,6 +97,14 @@ static inline struct clk *imx_clk_divider_flags(const char *name,
 			reg, shift, width, 0, &imx_ccm_lock);
 }
 
+static inline struct clk *imx_clk_divider2(const char *name, const char *parent,
+		void __iomem *reg, u8 shift, u8 width)
+{
+	return clk_register_divider(NULL, name, parent,
+			CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
+			reg, shift, width, 0, &imx_ccm_lock);
+}
+
 static inline struct clk *imx_clk_gate(const char *name, const char *parent,
 		void __iomem *reg, u8 shift)
 {
@@ -126,6 +119,44 @@ static inline struct clk *imx_clk_gate_dis(const char *name, const char *parent,
 			shift, CLK_GATE_SET_TO_DISABLE, &imx_ccm_lock);
 }
 
+static inline struct clk *imx_clk_gate2(const char *name, const char *parent,
+		void __iomem *reg, u8 shift)
+{
+	return clk_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT, reg,
+			shift, 0x3, 0, &imx_ccm_lock, NULL);
+}
+
+static inline struct clk *imx_clk_gate2_shared(const char *name,
+		const char *parent, void __iomem *reg, u8 shift,
+		unsigned int *share_count)
+{
+	return clk_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT, reg,
+			shift, 0x3, 0, &imx_ccm_lock, share_count);
+}
+
+static inline struct clk *imx_clk_gate2_cgr(const char *name,
+		const char *parent, void __iomem *reg, u8 shift, u8 cgr_val)
+{
+	return clk_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT, reg,
+			shift, cgr_val, 0, &imx_ccm_lock, NULL);
+}
+
+static inline struct clk *imx_clk_gate3(const char *name, const char *parent,
+		void __iomem *reg, u8 shift)
+{
+	return clk_register_gate(NULL, name, parent,
+			CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
+			reg, shift, 0, &imx_ccm_lock);
+}
+
+static inline struct clk *imx_clk_gate4(const char *name, const char *parent,
+		void __iomem *reg, u8 shift)
+{
+	return clk_register_gate2(NULL, name, parent,
+			CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
+			reg, shift, 0x3, 0, &imx_ccm_lock, NULL);
+}
+
 static inline struct clk *imx_clk_mux(const char *name, void __iomem *reg,
 		u8 shift, u8 width, const char **parents, int num_parents)
 {
@@ -134,6 +165,14 @@ static inline struct clk *imx_clk_mux(const char *name, void __iomem *reg,
 			width, 0, &imx_ccm_lock);
 }
 
+static inline struct clk *imx_clk_mux2(const char *name, void __iomem *reg,
+		u8 shift, u8 width, const char **parents, int num_parents)
+{
+	return clk_register_mux(NULL, name, parents, num_parents,
+			CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE,
+			reg, shift, width, 0, &imx_ccm_lock);
+}
+
 static inline struct clk *imx_clk_mux_flags(const char *name,
 		void __iomem *reg, u8 shift, u8 width, const char **parents,
 		int num_parents, unsigned long flags)
@@ -143,13 +182,6 @@ static inline struct clk *imx_clk_mux_flags(const char *name,
 			&imx_ccm_lock);
 }
 
-static inline struct clk *imx_clk_fixed_factor(const char *name,
-		const char *parent, unsigned int mult, unsigned int div)
-{
-	return clk_register_fixed_factor(NULL, name, parent,
-			CLK_SET_RATE_PARENT, mult, div);
-}
-
 struct clk *imx_clk_cpu(const char *name, const char *parent_name,
 		struct clk *div, struct clk *mux, struct clk *pll,
 		struct clk *step);
diff --git a/drivers/clk/meson/Kconfig b/drivers/clk/meson/Kconfig
new file mode 100644
index 000000000000..19480bcc7046
--- /dev/null
+++ b/drivers/clk/meson/Kconfig
@@ -0,0 +1,19 @@
+config COMMON_CLK_AMLOGIC
+	bool
+	depends on OF
+	depends on ARCH_MESON || COMPILE_TEST
+
+config COMMON_CLK_MESON8B
+	bool
+	depends on COMMON_CLK_AMLOGIC
+	help
+	  Support for the clock controller on AmLogic S805 devices, aka
+	  meson8b. Say Y if you want peripherals and CPU frequency scaling to
+	  work.
+
+config COMMON_CLK_GXBB
+	bool
+	depends on COMMON_CLK_AMLOGIC
+	help
+	  Support for the clock controller on AmLogic S905 devices, aka gxbb.
+	  Say Y if you want peripherals and CPU frequency scaling to work.
diff --git a/drivers/clk/meson/Makefile b/drivers/clk/meson/Makefile
index 6d45531df9ab..197e40175166 100644
--- a/drivers/clk/meson/Makefile
+++ b/drivers/clk/meson/Makefile
@@ -2,5 +2,6 @@
 # Makefile for Meson specific clk
 #
 
-obj-y += clkc.o clk-pll.o clk-cpu.o
-obj-y += meson8b-clkc.o
+obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-cpu.o clk-mpll.o
+obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b-clkc.o
+obj-$(CONFIG_COMMON_CLK_GXBB)	 += gxbb.o
diff --git a/drivers/clk/meson/clk-cpu.c b/drivers/clk/meson/clk-cpu.c
index f7c30ea54ca8..f8b2b7efd016 100644
--- a/drivers/clk/meson/clk-cpu.c
+++ b/drivers/clk/meson/clk-cpu.c
@@ -51,13 +51,6 @@
 
 #include "clkc.h"
 
-struct meson_clk_cpu {
-	struct notifier_block		clk_nb;
-	const struct clk_div_table	*div_table;
-	struct clk_hw			hw;
-	void __iomem			*base;
-	u16				reg_off;
-};
 #define to_meson_clk_cpu_hw(_hw) container_of(_hw, struct meson_clk_cpu, hw)
 #define to_meson_clk_cpu_nb(_nb) container_of(_nb, struct meson_clk_cpu, clk_nb)
 
@@ -119,6 +112,7 @@ static unsigned long meson_clk_cpu_recalc_rate(struct clk_hw *hw,
 	return parent_rate / div;
 }
 
+/* FIXME MUX1 & MUX2 should be struct clk_hw objects */
 static int meson_clk_cpu_pre_rate_change(struct meson_clk_cpu *clk_cpu,
 					 struct clk_notifier_data *ndata)
 {
@@ -140,6 +134,7 @@ static int meson_clk_cpu_pre_rate_change(struct meson_clk_cpu *clk_cpu,
 	return 0;
 }
 
+/* FIXME MUX1 & MUX2 should be struct clk_hw objects */
 static int meson_clk_cpu_post_rate_change(struct meson_clk_cpu *clk_cpu,
 					  struct clk_notifier_data *ndata)
 {
@@ -161,7 +156,7 @@ static int meson_clk_cpu_post_rate_change(struct meson_clk_cpu *clk_cpu,
  * PLL clock is to be changed. We use the xtal input as temporary parent
  * while the PLL frequency is stabilized.
  */
-static int meson_clk_cpu_notifier_cb(struct notifier_block *nb,
+int meson_clk_cpu_notifier_cb(struct notifier_block *nb,
 				     unsigned long event, void *data)
 {
 	struct clk_notifier_data *ndata = data;
@@ -176,68 +171,8 @@ static int meson_clk_cpu_notifier_cb(struct notifier_block *nb,
 	return notifier_from_errno(ret);
 }
 
-static const struct clk_ops meson_clk_cpu_ops = {
+const struct clk_ops meson_clk_cpu_ops = {
 	.recalc_rate	= meson_clk_cpu_recalc_rate,
 	.round_rate	= meson_clk_cpu_round_rate,
 	.set_rate	= meson_clk_cpu_set_rate,
 };
-
-struct clk *meson_clk_register_cpu(const struct clk_conf *clk_conf,
-				   void __iomem *reg_base,
-				   spinlock_t *lock)
-{
-	struct clk *clk;
-	struct clk *pclk;
-	struct meson_clk_cpu *clk_cpu;
-	struct clk_init_data init;
-	int ret;
-
-	clk_cpu = kzalloc(sizeof(*clk_cpu), GFP_KERNEL);
-	if (!clk_cpu)
-		return ERR_PTR(-ENOMEM);
-
-	clk_cpu->base = reg_base;
-	clk_cpu->reg_off = clk_conf->reg_off;
-	clk_cpu->div_table = clk_conf->conf.div_table;
-	clk_cpu->clk_nb.notifier_call = meson_clk_cpu_notifier_cb;
-
-	init.name = clk_conf->clk_name;
-	init.ops = &meson_clk_cpu_ops;
-	init.flags = clk_conf->flags | CLK_GET_RATE_NOCACHE;
-	init.flags |= CLK_SET_RATE_PARENT;
-	init.parent_names = clk_conf->clks_parent;
-	init.num_parents = 1;
-
-	clk_cpu->hw.init = &init;
-
-	pclk = __clk_lookup(clk_conf->clks_parent[0]);
-	if (!pclk) {
-		pr_err("%s: could not lookup parent clock %s\n",
-				__func__, clk_conf->clks_parent[0]);
-		ret = -EINVAL;
-		goto free_clk;
-	}
-
-	ret = clk_notifier_register(pclk, &clk_cpu->clk_nb);
-	if (ret) {
-		pr_err("%s: failed to register clock notifier for %s\n",
-				__func__, clk_conf->clk_name);
-		goto free_clk;
-	}
-
-	clk = clk_register(NULL, &clk_cpu->hw);
-	if (IS_ERR(clk)) {
-		ret = PTR_ERR(clk);
-		goto unregister_clk_nb;
-	}
-
-	return clk;
-
-unregister_clk_nb:
-	clk_notifier_unregister(pclk, &clk_cpu->clk_nb);
-free_clk:
-	kfree(clk_cpu);
-
-	return ERR_PTR(ret);
-}
-
diff --git a/drivers/clk/meson/clk-mpll.c b/drivers/clk/meson/clk-mpll.c
new file mode 100644
index 000000000000..03af79005ddb
--- /dev/null
+++ b/drivers/clk/meson/clk-mpll.c
@@ -0,0 +1,94 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (c) 2016 AmLogic, Inc.
+ * Author: Michael Turquette <mturquette@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING
+ *
+ * BSD LICENSE
+ *
+ * Copyright (c) 2016 AmLogic, Inc.
+ * Author: Michael Turquette <mturquette@baylibre.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/*
+ * MultiPhase Locked Loops are outputs from a PLL with additional frequency
+ * scaling capabilities. MPLL rates are calculated as:
+ *
+ * f(N2_integer, SDM_IN ) = 2.0G/(N2_integer + SDM_IN/16384)
+ */
+
+#include <linux/clk-provider.h>
+#include "clkc.h"
+
+#define SDM_MAX 16384
+
+#define to_meson_clk_mpll(_hw) container_of(_hw, struct meson_clk_mpll, hw)
+
+static unsigned long mpll_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct meson_clk_mpll *mpll = to_meson_clk_mpll(hw);
+	struct parm *p;
+	unsigned long rate = 0;
+	unsigned long reg, sdm, n2;
+
+	p = &mpll->sdm;
+	reg = readl(mpll->base + p->reg_off);
+	sdm = PARM_GET(p->width, p->shift, reg);
+
+	p = &mpll->n2;
+	reg = readl(mpll->base + p->reg_off);
+	n2 = PARM_GET(p->width, p->shift, reg);
+
+	rate = (parent_rate * SDM_MAX) / ((SDM_MAX * n2) + sdm);
+
+	return rate;
+}
+
+const struct clk_ops meson_clk_mpll_ro_ops = {
+	.recalc_rate = mpll_recalc_rate,
+};
diff --git a/drivers/clk/meson/clk-pll.c b/drivers/clk/meson/clk-pll.c
index 664edf0708ea..4adc1e89212c 100644
--- a/drivers/clk/meson/clk-pll.c
+++ b/drivers/clk/meson/clk-pll.c
@@ -44,13 +44,6 @@
 #define MESON_PLL_RESET				BIT(29)
 #define MESON_PLL_LOCK				BIT(31)
 
-struct meson_clk_pll {
-	struct clk_hw	hw;
-	void __iomem	*base;
-	struct pll_conf	*conf;
-	unsigned int	rate_count;
-	spinlock_t	*lock;
-};
 #define to_meson_clk_pll(_hw) container_of(_hw, struct meson_clk_pll, hw)
 
 static unsigned long meson_clk_pll_recalc_rate(struct clk_hw *hw,
@@ -60,22 +53,36 @@ static unsigned long meson_clk_pll_recalc_rate(struct clk_hw *hw,
 	struct parm *p;
 	unsigned long parent_rate_mhz = parent_rate / 1000000;
 	unsigned long rate_mhz;
-	u16 n, m, od;
+	u16 n, m, frac = 0, od, od2 = 0;
 	u32 reg;
 
-	p = &pll->conf->n;
+	p = &pll->n;
 	reg = readl(pll->base + p->reg_off);
 	n = PARM_GET(p->width, p->shift, reg);
 
-	p = &pll->conf->m;
+	p = &pll->m;
 	reg = readl(pll->base + p->reg_off);
 	m = PARM_GET(p->width, p->shift, reg);
 
-	p = &pll->conf->od;
+	p = &pll->od;
 	reg = readl(pll->base + p->reg_off);
 	od = PARM_GET(p->width, p->shift, reg);
 
-	rate_mhz = (parent_rate_mhz * m / n) >> od;
+	p = &pll->od2;
+	if (p->width) {
+		reg = readl(pll->base + p->reg_off);
+		od2 = PARM_GET(p->width, p->shift, reg);
+	}
+
+	p = &pll->frac;
+	if (p->width) {
+		reg = readl(pll->base + p->reg_off);
+		frac = PARM_GET(p->width, p->shift, reg);
+		rate_mhz = (parent_rate_mhz * m + \
+				(parent_rate_mhz * frac >> 12)) * 2 / n;
+		rate_mhz = rate_mhz >> od >> od2;
+	} else
+		rate_mhz = (parent_rate_mhz * m / n) >> od >> od2;
 
 	return rate_mhz * 1000000;
 }
@@ -84,7 +91,7 @@ static long meson_clk_pll_round_rate(struct clk_hw *hw, unsigned long rate,
 				     unsigned long *parent_rate)
 {
 	struct meson_clk_pll *pll = to_meson_clk_pll(hw);
-	const struct pll_rate_table *rate_table = pll->conf->rate_table;
+	const struct pll_rate_table *rate_table = pll->rate_table;
 	int i;
 
 	for (i = 0; i < pll->rate_count; i++) {
@@ -99,7 +106,7 @@ static long meson_clk_pll_round_rate(struct clk_hw *hw, unsigned long rate,
 static const struct pll_rate_table *meson_clk_get_pll_settings(struct meson_clk_pll *pll,
 							       unsigned long rate)
 {
-	const struct pll_rate_table *rate_table = pll->conf->rate_table;
+	const struct pll_rate_table *rate_table = pll->rate_table;
 	int i;
 
 	for (i = 0; i < pll->rate_count; i++) {
@@ -145,24 +152,38 @@ static int meson_clk_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 		return -EINVAL;
 
 	/* PLL reset */
-	p = &pll->conf->n;
+	p = &pll->n;
 	reg = readl(pll->base + p->reg_off);
 	writel(reg | MESON_PLL_RESET, pll->base + p->reg_off);
 
 	reg = PARM_SET(p->width, p->shift, reg, rate_set->n);
 	writel(reg, pll->base + p->reg_off);
 
-	p = &pll->conf->m;
+	p = &pll->m;
 	reg = readl(pll->base + p->reg_off);
 	reg = PARM_SET(p->width, p->shift, reg, rate_set->m);
 	writel(reg, pll->base + p->reg_off);
 
-	p = &pll->conf->od;
+	p = &pll->od;
 	reg = readl(pll->base + p->reg_off);
 	reg = PARM_SET(p->width, p->shift, reg, rate_set->od);
 	writel(reg, pll->base + p->reg_off);
 
-	p = &pll->conf->n;
+	p = &pll->od2;
+	if (p->width) {
+		reg = readl(pll->base + p->reg_off);
+		reg = PARM_SET(p->width, p->shift, reg, rate_set->od2);
+		writel(reg, pll->base + p->reg_off);
+	}
+
+	p = &pll->frac;
+	if (p->width) {
+		reg = readl(pll->base + p->reg_off);
+		reg = PARM_SET(p->width, p->shift, reg, rate_set->frac);
+		writel(reg, pll->base + p->reg_off);
+	}
+
+	p = &pll->n;
 	ret = meson_clk_pll_wait_lock(pll, p);
 	if (ret) {
 		pr_warn("%s: pll did not lock, trying to restore old rate %lu\n",
@@ -173,55 +194,12 @@ static int meson_clk_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	return ret;
 }
 
-static const struct clk_ops meson_clk_pll_ops = {
+const struct clk_ops meson_clk_pll_ops = {
 	.recalc_rate	= meson_clk_pll_recalc_rate,
 	.round_rate	= meson_clk_pll_round_rate,
 	.set_rate	= meson_clk_pll_set_rate,
 };
 
-static const struct clk_ops meson_clk_pll_ro_ops = {
+const struct clk_ops meson_clk_pll_ro_ops = {
 	.recalc_rate	= meson_clk_pll_recalc_rate,
 };
-
-struct clk *meson_clk_register_pll(const struct clk_conf *clk_conf,
-				   void __iomem *reg_base,
-				   spinlock_t *lock)
-{
-	struct clk *clk;
-	struct meson_clk_pll *clk_pll;
-	struct clk_init_data init;
-
-	clk_pll = kzalloc(sizeof(*clk_pll), GFP_KERNEL);
-	if (!clk_pll)
-		return ERR_PTR(-ENOMEM);
-
-	clk_pll->base = reg_base + clk_conf->reg_off;
-	clk_pll->lock = lock;
-	clk_pll->conf = clk_conf->conf.pll;
-
-	init.name = clk_conf->clk_name;
-	init.flags = clk_conf->flags | CLK_GET_RATE_NOCACHE;
-
-	init.parent_names = &clk_conf->clks_parent[0];
-	init.num_parents = 1;
-	init.ops = &meson_clk_pll_ro_ops;
-
-	/* If no rate_table is specified we assume the PLL is read-only */
-	if (clk_pll->conf->rate_table) {
-		int len;
-
-		for (len = 0; clk_pll->conf->rate_table[len].rate != 0; )
-			len++;
-
-		 clk_pll->rate_count = len;
-		 init.ops = &meson_clk_pll_ops;
-	}
-
-	clk_pll->hw.init = &init;
-
-	clk = clk_register(NULL, &clk_pll->hw);
-	if (IS_ERR(clk))
-		kfree(clk_pll);
-
-	return clk;
-}
diff --git a/drivers/clk/meson/clkc.c b/drivers/clk/meson/clkc.c
deleted file mode 100644
index d920d410b51d..000000000000
--- a/drivers/clk/meson/clkc.c
+++ /dev/null
@@ -1,249 +0,0 @@
-/*
- * Copyright (c) 2015 Endless Mobile, Inc.
- * Author: Carlo Caione <carlo@endlessm.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/clk-provider.h>
-#include <linux/mfd/syscon.h>
-#include <linux/slab.h>
-
-#include "clkc.h"
-
-static DEFINE_SPINLOCK(clk_lock);
-
-static struct clk **clks;
-static struct clk_onecell_data clk_data;
-
-struct clk ** __init meson_clk_init(struct device_node *np,
-				   unsigned long nr_clks)
-{
-	clks = kcalloc(nr_clks, sizeof(*clks), GFP_KERNEL);
-	if (!clks)
-		return ERR_PTR(-ENOMEM);
-
-	clk_data.clks = clks;
-	clk_data.clk_num = nr_clks;
-	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
-
-	return clks;
-}
-
-static void meson_clk_add_lookup(struct clk *clk, unsigned int id)
-{
-	if (clks && id)
-		clks[id] = clk;
-}
-
-static struct clk * __init
-meson_clk_register_composite(const struct clk_conf *clk_conf,
-			     void __iomem *clk_base)
-{
-	struct clk *clk;
-	struct clk_mux *mux = NULL;
-	struct clk_divider *div = NULL;
-	struct clk_gate *gate = NULL;
-	const struct clk_ops *mux_ops = NULL;
-	const struct composite_conf *composite_conf;
-
-	composite_conf = clk_conf->conf.composite;
-
-	if (clk_conf->num_parents > 1) {
-		mux = kzalloc(sizeof(*mux), GFP_KERNEL);
-		if (!mux)
-			return ERR_PTR(-ENOMEM);
-
-		mux->reg = clk_base + clk_conf->reg_off
-				+ composite_conf->mux_parm.reg_off;
-		mux->shift = composite_conf->mux_parm.shift;
-		mux->mask = BIT(composite_conf->mux_parm.width) - 1;
-		mux->flags = composite_conf->mux_flags;
-		mux->lock = &clk_lock;
-		mux->table = composite_conf->mux_table;
-		mux_ops = (composite_conf->mux_flags & CLK_MUX_READ_ONLY) ?
-			  &clk_mux_ro_ops : &clk_mux_ops;
-	}
-
-	if (MESON_PARM_APPLICABLE(&composite_conf->div_parm)) {
-		div = kzalloc(sizeof(*div), GFP_KERNEL);
-		if (!div) {
-			clk = ERR_PTR(-ENOMEM);
-			goto error;
-		}
-
-		div->reg = clk_base + clk_conf->reg_off
-				+ composite_conf->div_parm.reg_off;
-		div->shift = composite_conf->div_parm.shift;
-		div->width = composite_conf->div_parm.width;
-		div->lock = &clk_lock;
-		div->flags = composite_conf->div_flags;
-		div->table = composite_conf->div_table;
-	}
-
-	if (MESON_PARM_APPLICABLE(&composite_conf->gate_parm)) {
-		gate = kzalloc(sizeof(*gate), GFP_KERNEL);
-		if (!gate) {
-			clk = ERR_PTR(-ENOMEM);
-			goto error;
-		}
-
-		gate->reg = clk_base + clk_conf->reg_off
-				+ composite_conf->div_parm.reg_off;
-		gate->bit_idx = composite_conf->gate_parm.shift;
-		gate->flags = composite_conf->gate_flags;
-		gate->lock = &clk_lock;
-	}
-
-	clk = clk_register_composite(NULL, clk_conf->clk_name,
-				    clk_conf->clks_parent,
-				    clk_conf->num_parents,
-				    mux ? &mux->hw : NULL, mux_ops,
-				    div ? &div->hw : NULL, &clk_divider_ops,
-				    gate ? &gate->hw : NULL, &clk_gate_ops,
-				    clk_conf->flags);
-	if (IS_ERR(clk))
-		goto error;
-
-	return clk;
-
-error:
-	kfree(gate);
-	kfree(div);
-	kfree(mux);
-
-	return clk;
-}
-
-static struct clk * __init
-meson_clk_register_fixed_factor(const struct clk_conf *clk_conf,
-				void __iomem *clk_base)
-{
-	struct clk *clk;
-	const struct fixed_fact_conf *fixed_fact_conf;
-	const struct parm *p;
-	unsigned int mult, div;
-	u32 reg;
-
-	fixed_fact_conf = &clk_conf->conf.fixed_fact;
-
-	mult = clk_conf->conf.fixed_fact.mult;
-	div = clk_conf->conf.fixed_fact.div;
-
-	if (!mult) {
-		mult = 1;
-		p = &fixed_fact_conf->mult_parm;
-		if (MESON_PARM_APPLICABLE(p)) {
-			reg = readl(clk_base + clk_conf->reg_off + p->reg_off);
-			mult = PARM_GET(p->width, p->shift, reg);
-		}
-	}
-
-	if (!div) {
-		div = 1;
-		p = &fixed_fact_conf->div_parm;
-		if (MESON_PARM_APPLICABLE(p)) {
-			reg = readl(clk_base + clk_conf->reg_off + p->reg_off);
-			mult = PARM_GET(p->width, p->shift, reg);
-		}
-	}
-
-	clk = clk_register_fixed_factor(NULL,
-			clk_conf->clk_name,
-			clk_conf->clks_parent[0],
-			clk_conf->flags,
-			mult, div);
-
-	return clk;
-}
-
-static struct clk * __init
-meson_clk_register_fixed_rate(const struct clk_conf *clk_conf,
-			      void __iomem *clk_base)
-{
-	struct clk *clk;
-	const struct fixed_rate_conf *fixed_rate_conf;
-	const struct parm *r;
-	unsigned long rate;
-	u32 reg;
-
-	fixed_rate_conf = &clk_conf->conf.fixed_rate;
-	rate = fixed_rate_conf->rate;
-
-	if (!rate) {
-		r = &fixed_rate_conf->rate_parm;
-		reg = readl(clk_base + clk_conf->reg_off + r->reg_off);
-		rate = PARM_GET(r->width, r->shift, reg);
-	}
-
-	rate *= 1000000;
-
-	clk = clk_register_fixed_rate(NULL,
-			clk_conf->clk_name,
-			clk_conf->num_parents
-				? clk_conf->clks_parent[0] : NULL,
-			clk_conf->flags, rate);
-
-	return clk;
-}
-
-void __init meson_clk_register_clks(const struct clk_conf *clk_confs,
-				    unsigned int nr_confs,
-				    void __iomem *clk_base)
-{
-	unsigned int i;
-	struct clk *clk = NULL;
-
-	for (i = 0; i < nr_confs; i++) {
-		const struct clk_conf *clk_conf = &clk_confs[i];
-
-		switch (clk_conf->clk_type) {
-		case CLK_FIXED_RATE:
-			clk = meson_clk_register_fixed_rate(clk_conf,
-							    clk_base);
-			break;
-		case CLK_FIXED_FACTOR:
-			clk = meson_clk_register_fixed_factor(clk_conf,
-							      clk_base);
-			break;
-		case CLK_COMPOSITE:
-			clk = meson_clk_register_composite(clk_conf,
-							   clk_base);
-			break;
-		case CLK_CPU:
-			clk = meson_clk_register_cpu(clk_conf, clk_base,
-						     &clk_lock);
-			break;
-		case CLK_PLL:
-			clk = meson_clk_register_pll(clk_conf, clk_base,
-						     &clk_lock);
-			break;
-		default:
-			clk = NULL;
-		}
-
-		if (!clk) {
-			pr_err("%s: unknown clock type %d\n", __func__,
-			       clk_conf->clk_type);
-			continue;
-		}
-
-		if (IS_ERR(clk)) {
-			pr_warn("%s: Unable to create %s clock\n", __func__,
-				clk_conf->clk_name);
-			continue;
-		}
-
-		meson_clk_add_lookup(clk, clk_conf->clk_id);
-	}
-}
diff --git a/drivers/clk/meson/clkc.h b/drivers/clk/meson/clkc.h
index 609ae92cc13f..53326c32e853 100644
--- a/drivers/clk/meson/clkc.h
+++ b/drivers/clk/meson/clkc.h
@@ -34,19 +34,16 @@ struct parm {
 	u8	shift;
 	u8	width;
 };
-#define PARM(_r, _s, _w)						\
-	{								\
-		.reg_off	= (_r),					\
-		.shift		= (_s),					\
-		.width		= (_w),					\
-	}								\
 
 struct pll_rate_table {
 	unsigned long	rate;
 	u16		m;
 	u16		n;
 	u16		od;
+	u16		od2;
+	u16		frac;
 };
+
 #define PLL_RATE(_r, _m, _n, _od)					\
 	{								\
 		.rate		= (_r),					\
@@ -55,133 +52,69 @@ struct pll_rate_table {
 		.od		= (_od),				\
 	}								\
 
-struct pll_conf {
-	const struct pll_rate_table	*rate_table;
-	struct parm			m;
-	struct parm			n;
-	struct parm			od;
-};
+#define PLL_FRAC_RATE(_r, _m, _n, _od, _od2, _frac)			\
+	{								\
+		.rate		= (_r),					\
+		.m		= (_m),					\
+		.n		= (_n),					\
+		.od		= (_od),				\
+		.od2		= (_od2),				\
+		.frac		= (_frac),				\
+	}								\
 
-struct fixed_fact_conf {
-	unsigned int	div;
-	unsigned int	mult;
-	struct parm	div_parm;
-	struct parm	mult_parm;
+struct meson_clk_pll {
+	struct clk_hw hw;
+	void __iomem *base;
+	struct parm m;
+	struct parm n;
+	struct parm frac;
+	struct parm od;
+	struct parm od2;
+	const struct pll_rate_table *rate_table;
+	unsigned int rate_count;
+	spinlock_t *lock;
 };
 
-struct fixed_rate_conf {
-	unsigned long	rate;
-	struct parm	rate_parm;
-};
+#define to_meson_clk_pll(_hw) container_of(_hw, struct meson_clk_pll, hw)
 
-struct composite_conf {
-	struct parm		mux_parm;
-	struct parm		div_parm;
-	struct parm		gate_parm;
-	struct clk_div_table	*div_table;
-	u32			*mux_table;
-	u8			mux_flags;
-	u8			div_flags;
-	u8			gate_flags;
+struct meson_clk_cpu {
+	struct clk_hw hw;
+	void __iomem *base;
+	u16 reg_off;
+	struct notifier_block clk_nb;
+	const struct clk_div_table *div_table;
 };
 
-#define PNAME(x) static const char *x[]
+int meson_clk_cpu_notifier_cb(struct notifier_block *nb, unsigned long event,
+		void *data);
 
-enum clk_type {
-	CLK_FIXED_FACTOR,
-	CLK_FIXED_RATE,
-	CLK_COMPOSITE,
-	CLK_CPU,
-	CLK_PLL,
+struct meson_clk_mpll {
+	struct clk_hw hw;
+	void __iomem *base;
+	struct parm sdm;
+	struct parm n2;
+	/* FIXME ssen gate control? */
+	spinlock_t *lock;
 };
 
-struct clk_conf {
-	u16				reg_off;
-	enum clk_type			clk_type;
-	unsigned int			clk_id;
-	const char			*clk_name;
-	const char			**clks_parent;
-	int				num_parents;
-	unsigned long			flags;
-	union {
-		struct fixed_fact_conf		fixed_fact;
-		struct fixed_rate_conf		fixed_rate;
-		const struct composite_conf		*composite;
-		struct pll_conf			*pll;
-		const struct clk_div_table	*div_table;
-	} conf;
+#define MESON_GATE(_name, _reg, _bit)					\
+struct clk_gate gxbb_##_name = { 						\
+	.reg = (void __iomem *) _reg, 					\
+	.bit_idx = (_bit), 						\
+	.lock = &clk_lock,						\
+	.hw.init = &(struct clk_init_data) { 				\
+		.name = #_name,					\
+		.ops = &clk_gate_ops,					\
+		.parent_names = (const char *[]){ "clk81" },		\
+		.num_parents = 1,					\
+		.flags = (CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED), 	\
+	},								\
 };
 
-#define FIXED_RATE_P(_ro, _ci, _cn, _f, _c)				\
-	{								\
-		.reg_off			= (_ro),		\
-		.clk_type			= CLK_FIXED_RATE,	\
-		.clk_id				= (_ci),		\
-		.clk_name			= (_cn),		\
-		.flags				= (_f),			\
-		.conf.fixed_rate.rate_parm	= _c,			\
-	}								\
-
-#define FIXED_RATE(_ci, _cn, _f, _r)					\
-	{								\
-		.clk_type			= CLK_FIXED_RATE,	\
-		.clk_id				= (_ci),		\
-		.clk_name			= (_cn),		\
-		.flags				= (_f),			\
-		.conf.fixed_rate.rate		= (_r),			\
-	}								\
-
-#define PLL(_ro, _ci, _cn, _cp, _f, _c)					\
-	{								\
-		.reg_off			= (_ro),		\
-		.clk_type			= CLK_PLL,		\
-		.clk_id				= (_ci),		\
-		.clk_name			= (_cn),		\
-		.clks_parent			= (_cp),		\
-		.num_parents			= ARRAY_SIZE(_cp),	\
-		.flags				= (_f),			\
-		.conf.pll			= (_c),			\
-	}								\
-
-#define FIXED_FACTOR_DIV(_ci, _cn, _cp, _f, _d)				\
-	{								\
-		.clk_type			= CLK_FIXED_FACTOR,	\
-		.clk_id				= (_ci),		\
-		.clk_name			= (_cn),		\
-		.clks_parent			= (_cp),		\
-		.num_parents			= ARRAY_SIZE(_cp),	\
-		.conf.fixed_fact.div		= (_d),			\
-	}								\
-
-#define CPU(_ro, _ci, _cn, _cp, _dt)					\
-	{								\
-		.reg_off			= (_ro),		\
-		.clk_type			= CLK_CPU,		\
-		.clk_id				= (_ci),		\
-		.clk_name			= (_cn),		\
-		.clks_parent			= (_cp),		\
-		.num_parents			= ARRAY_SIZE(_cp),	\
-		.conf.div_table			= (_dt),		\
-	}								\
-
-#define COMPOSITE(_ro, _ci, _cn, _cp, _f, _c)				\
-	{								\
-		.reg_off			= (_ro),		\
-		.clk_type			= CLK_COMPOSITE,	\
-		.clk_id				= (_ci),		\
-		.clk_name			= (_cn),		\
-		.clks_parent			= (_cp),		\
-		.num_parents			= ARRAY_SIZE(_cp),	\
-		.flags				= (_f),			\
-		.conf.composite			= (_c),			\
-	}								\
-
-struct clk **meson_clk_init(struct device_node *np, unsigned long nr_clks);
-void meson_clk_register_clks(const struct clk_conf *clk_confs,
-			     unsigned int nr_confs, void __iomem *clk_base);
-struct clk *meson_clk_register_cpu(const struct clk_conf *clk_conf,
-				   void __iomem *reg_base, spinlock_t *lock);
-struct clk *meson_clk_register_pll(const struct clk_conf *clk_conf,
-				   void __iomem *reg_base, spinlock_t *lock);
+/* clk_ops */
+extern const struct clk_ops meson_clk_pll_ro_ops;
+extern const struct clk_ops meson_clk_pll_ops;
+extern const struct clk_ops meson_clk_cpu_ops;
+extern const struct clk_ops meson_clk_mpll_ro_ops;
 
 #endif /* __CLKC_H */
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
new file mode 100644
index 000000000000..a4c6684b3019
--- /dev/null
+++ b/drivers/clk/meson/gxbb.c
@@ -0,0 +1,944 @@
+/*
+ * AmLogic S905 / GXBB Clock Controller Driver
+ *
+ * Copyright (c) 2016 AmLogic, Inc.
+ * Michael Turquette <mturquette@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/init.h>
+
+#include "clkc.h"
+#include "gxbb.h"
+
+static DEFINE_SPINLOCK(clk_lock);
+
+static const struct pll_rate_table sys_pll_rate_table[] = {
+	PLL_RATE(24000000, 56, 1, 2),
+	PLL_RATE(48000000, 64, 1, 2),
+	PLL_RATE(72000000, 72, 1, 2),
+	PLL_RATE(96000000, 64, 1, 2),
+	PLL_RATE(120000000, 80, 1, 2),
+	PLL_RATE(144000000, 96, 1, 2),
+	PLL_RATE(168000000, 56, 1, 1),
+	PLL_RATE(192000000, 64, 1, 1),
+	PLL_RATE(216000000, 72, 1, 1),
+	PLL_RATE(240000000, 80, 1, 1),
+	PLL_RATE(264000000, 88, 1, 1),
+	PLL_RATE(288000000, 96, 1, 1),
+	PLL_RATE(312000000, 52, 1, 2),
+	PLL_RATE(336000000, 56, 1, 2),
+	PLL_RATE(360000000, 60, 1, 2),
+	PLL_RATE(384000000, 64, 1, 2),
+	PLL_RATE(408000000, 68, 1, 2),
+	PLL_RATE(432000000, 72, 1, 2),
+	PLL_RATE(456000000, 76, 1, 2),
+	PLL_RATE(480000000, 80, 1, 2),
+	PLL_RATE(504000000, 84, 1, 2),
+	PLL_RATE(528000000, 88, 1, 2),
+	PLL_RATE(552000000, 92, 1, 2),
+	PLL_RATE(576000000, 96, 1, 2),
+	PLL_RATE(600000000, 50, 1, 1),
+	PLL_RATE(624000000, 52, 1, 1),
+	PLL_RATE(648000000, 54, 1, 1),
+	PLL_RATE(672000000, 56, 1, 1),
+	PLL_RATE(696000000, 58, 1, 1),
+	PLL_RATE(720000000, 60, 1, 1),
+	PLL_RATE(744000000, 62, 1, 1),
+	PLL_RATE(768000000, 64, 1, 1),
+	PLL_RATE(792000000, 66, 1, 1),
+	PLL_RATE(816000000, 68, 1, 1),
+	PLL_RATE(840000000, 70, 1, 1),
+	PLL_RATE(864000000, 72, 1, 1),
+	PLL_RATE(888000000, 74, 1, 1),
+	PLL_RATE(912000000, 76, 1, 1),
+	PLL_RATE(936000000, 78, 1, 1),
+	PLL_RATE(960000000, 80, 1, 1),
+	PLL_RATE(984000000, 82, 1, 1),
+	PLL_RATE(1008000000, 84, 1, 1),
+	PLL_RATE(1032000000, 86, 1, 1),
+	PLL_RATE(1056000000, 88, 1, 1),
+	PLL_RATE(1080000000, 90, 1, 1),
+	PLL_RATE(1104000000, 92, 1, 1),
+	PLL_RATE(1128000000, 94, 1, 1),
+	PLL_RATE(1152000000, 96, 1, 1),
+	PLL_RATE(1176000000, 98, 1, 1),
+	PLL_RATE(1200000000, 50, 1, 0),
+	PLL_RATE(1224000000, 51, 1, 0),
+	PLL_RATE(1248000000, 52, 1, 0),
+	PLL_RATE(1272000000, 53, 1, 0),
+	PLL_RATE(1296000000, 54, 1, 0),
+	PLL_RATE(1320000000, 55, 1, 0),
+	PLL_RATE(1344000000, 56, 1, 0),
+	PLL_RATE(1368000000, 57, 1, 0),
+	PLL_RATE(1392000000, 58, 1, 0),
+	PLL_RATE(1416000000, 59, 1, 0),
+	PLL_RATE(1440000000, 60, 1, 0),
+	PLL_RATE(1464000000, 61, 1, 0),
+	PLL_RATE(1488000000, 62, 1, 0),
+	PLL_RATE(1512000000, 63, 1, 0),
+	PLL_RATE(1536000000, 64, 1, 0),
+	PLL_RATE(1560000000, 65, 1, 0),
+	PLL_RATE(1584000000, 66, 1, 0),
+	PLL_RATE(1608000000, 67, 1, 0),
+	PLL_RATE(1632000000, 68, 1, 0),
+	PLL_RATE(1656000000, 68, 1, 0),
+	PLL_RATE(1680000000, 68, 1, 0),
+	PLL_RATE(1704000000, 68, 1, 0),
+	PLL_RATE(1728000000, 69, 1, 0),
+	PLL_RATE(1752000000, 69, 1, 0),
+	PLL_RATE(1776000000, 69, 1, 0),
+	PLL_RATE(1800000000, 69, 1, 0),
+	PLL_RATE(1824000000, 70, 1, 0),
+	PLL_RATE(1848000000, 70, 1, 0),
+	PLL_RATE(1872000000, 70, 1, 0),
+	PLL_RATE(1896000000, 70, 1, 0),
+	PLL_RATE(1920000000, 71, 1, 0),
+	PLL_RATE(1944000000, 71, 1, 0),
+	PLL_RATE(1968000000, 71, 1, 0),
+	PLL_RATE(1992000000, 71, 1, 0),
+	PLL_RATE(2016000000, 72, 1, 0),
+	PLL_RATE(2040000000, 72, 1, 0),
+	PLL_RATE(2064000000, 72, 1, 0),
+	PLL_RATE(2088000000, 72, 1, 0),
+	PLL_RATE(2112000000, 73, 1, 0),
+	{ /* sentinel */ },
+};
+
+static const struct pll_rate_table gp0_pll_rate_table[] = {
+	PLL_RATE(96000000, 32, 1, 3),
+	PLL_RATE(99000000, 33, 1, 3),
+	PLL_RATE(102000000, 34, 1, 3),
+	PLL_RATE(105000000, 35, 1, 3),
+	PLL_RATE(108000000, 36, 1, 3),
+	PLL_RATE(111000000, 37, 1, 3),
+	PLL_RATE(114000000, 38, 1, 3),
+	PLL_RATE(117000000, 39, 1, 3),
+	PLL_RATE(120000000, 40, 1, 3),
+	PLL_RATE(123000000, 41, 1, 3),
+	PLL_RATE(126000000, 42, 1, 3),
+	PLL_RATE(129000000, 43, 1, 3),
+	PLL_RATE(132000000, 44, 1, 3),
+	PLL_RATE(135000000, 45, 1, 3),
+	PLL_RATE(138000000, 46, 1, 3),
+	PLL_RATE(141000000, 47, 1, 3),
+	PLL_RATE(144000000, 48, 1, 3),
+	PLL_RATE(147000000, 49, 1, 3),
+	PLL_RATE(150000000, 50, 1, 3),
+	PLL_RATE(153000000, 51, 1, 3),
+	PLL_RATE(156000000, 52, 1, 3),
+	PLL_RATE(159000000, 53, 1, 3),
+	PLL_RATE(162000000, 54, 1, 3),
+	PLL_RATE(165000000, 55, 1, 3),
+	PLL_RATE(168000000, 56, 1, 3),
+	PLL_RATE(171000000, 57, 1, 3),
+	PLL_RATE(174000000, 58, 1, 3),
+	PLL_RATE(177000000, 59, 1, 3),
+	PLL_RATE(180000000, 60, 1, 3),
+	PLL_RATE(183000000, 61, 1, 3),
+	PLL_RATE(186000000, 62, 1, 3),
+	PLL_RATE(192000000, 32, 1, 2),
+	PLL_RATE(198000000, 33, 1, 2),
+	PLL_RATE(204000000, 34, 1, 2),
+	PLL_RATE(210000000, 35, 1, 2),
+	PLL_RATE(216000000, 36, 1, 2),
+	PLL_RATE(222000000, 37, 1, 2),
+	PLL_RATE(228000000, 38, 1, 2),
+	PLL_RATE(234000000, 39, 1, 2),
+	PLL_RATE(240000000, 40, 1, 2),
+	PLL_RATE(246000000, 41, 1, 2),
+	PLL_RATE(252000000, 42, 1, 2),
+	PLL_RATE(258000000, 43, 1, 2),
+	PLL_RATE(264000000, 44, 1, 2),
+	PLL_RATE(270000000, 45, 1, 2),
+	PLL_RATE(276000000, 46, 1, 2),
+	PLL_RATE(282000000, 47, 1, 2),
+	PLL_RATE(288000000, 48, 1, 2),
+	PLL_RATE(294000000, 49, 1, 2),
+	PLL_RATE(300000000, 50, 1, 2),
+	PLL_RATE(306000000, 51, 1, 2),
+	PLL_RATE(312000000, 52, 1, 2),
+	PLL_RATE(318000000, 53, 1, 2),
+	PLL_RATE(324000000, 54, 1, 2),
+	PLL_RATE(330000000, 55, 1, 2),
+	PLL_RATE(336000000, 56, 1, 2),
+	PLL_RATE(342000000, 57, 1, 2),
+	PLL_RATE(348000000, 58, 1, 2),
+	PLL_RATE(354000000, 59, 1, 2),
+	PLL_RATE(360000000, 60, 1, 2),
+	PLL_RATE(366000000, 61, 1, 2),
+	PLL_RATE(372000000, 62, 1, 2),
+	PLL_RATE(384000000, 32, 1, 1),
+	PLL_RATE(396000000, 33, 1, 1),
+	PLL_RATE(408000000, 34, 1, 1),
+	PLL_RATE(420000000, 35, 1, 1),
+	PLL_RATE(432000000, 36, 1, 1),
+	PLL_RATE(444000000, 37, 1, 1),
+	PLL_RATE(456000000, 38, 1, 1),
+	PLL_RATE(468000000, 39, 1, 1),
+	PLL_RATE(480000000, 40, 1, 1),
+	PLL_RATE(492000000, 41, 1, 1),
+	PLL_RATE(504000000, 42, 1, 1),
+	PLL_RATE(516000000, 43, 1, 1),
+	PLL_RATE(528000000, 44, 1, 1),
+	PLL_RATE(540000000, 45, 1, 1),
+	PLL_RATE(552000000, 46, 1, 1),
+	PLL_RATE(564000000, 47, 1, 1),
+	PLL_RATE(576000000, 48, 1, 1),
+	PLL_RATE(588000000, 49, 1, 1),
+	PLL_RATE(600000000, 50, 1, 1),
+	PLL_RATE(612000000, 51, 1, 1),
+	PLL_RATE(624000000, 52, 1, 1),
+	PLL_RATE(636000000, 53, 1, 1),
+	PLL_RATE(648000000, 54, 1, 1),
+	PLL_RATE(660000000, 55, 1, 1),
+	PLL_RATE(672000000, 56, 1, 1),
+	PLL_RATE(684000000, 57, 1, 1),
+	PLL_RATE(696000000, 58, 1, 1),
+	PLL_RATE(708000000, 59, 1, 1),
+	PLL_RATE(720000000, 60, 1, 1),
+	PLL_RATE(732000000, 61, 1, 1),
+	PLL_RATE(744000000, 62, 1, 1),
+	PLL_RATE(768000000, 32, 1, 0),
+	PLL_RATE(792000000, 33, 1, 0),
+	PLL_RATE(816000000, 34, 1, 0),
+	PLL_RATE(840000000, 35, 1, 0),
+	PLL_RATE(864000000, 36, 1, 0),
+	PLL_RATE(888000000, 37, 1, 0),
+	PLL_RATE(912000000, 38, 1, 0),
+	PLL_RATE(936000000, 39, 1, 0),
+	PLL_RATE(960000000, 40, 1, 0),
+	PLL_RATE(984000000, 41, 1, 0),
+	PLL_RATE(1008000000, 42, 1, 0),
+	PLL_RATE(1032000000, 43, 1, 0),
+	PLL_RATE(1056000000, 44, 1, 0),
+	PLL_RATE(1080000000, 45, 1, 0),
+	PLL_RATE(1104000000, 46, 1, 0),
+	PLL_RATE(1128000000, 47, 1, 0),
+	PLL_RATE(1152000000, 48, 1, 0),
+	PLL_RATE(1176000000, 49, 1, 0),
+	PLL_RATE(1200000000, 50, 1, 0),
+	PLL_RATE(1224000000, 51, 1, 0),
+	PLL_RATE(1248000000, 52, 1, 0),
+	PLL_RATE(1272000000, 53, 1, 0),
+	PLL_RATE(1296000000, 54, 1, 0),
+	PLL_RATE(1320000000, 55, 1, 0),
+	PLL_RATE(1344000000, 56, 1, 0),
+	PLL_RATE(1368000000, 57, 1, 0),
+	PLL_RATE(1392000000, 58, 1, 0),
+	PLL_RATE(1416000000, 59, 1, 0),
+	PLL_RATE(1440000000, 60, 1, 0),
+	PLL_RATE(1464000000, 61, 1, 0),
+	PLL_RATE(1488000000, 62, 1, 0),
+	{ /* sentinel */ },
+};
+
+static const struct clk_div_table cpu_div_table[] = {
+	{ .val = 1, .div = 1 },
+	{ .val = 2, .div = 2 },
+	{ .val = 3, .div = 3 },
+	{ .val = 2, .div = 4 },
+	{ .val = 3, .div = 6 },
+	{ .val = 4, .div = 8 },
+	{ .val = 5, .div = 10 },
+	{ .val = 6, .div = 12 },
+	{ .val = 7, .div = 14 },
+	{ .val = 8, .div = 16 },
+	{ /* sentinel */ },
+};
+
+static struct meson_clk_pll gxbb_fixed_pll = {
+	.m = {
+		.reg_off = HHI_MPLL_CNTL,
+		.shift   = 0,
+		.width   = 9,
+	},
+	.n = {
+		.reg_off = HHI_MPLL_CNTL,
+		.shift   = 9,
+		.width   = 5,
+	},
+	.od = {
+		.reg_off = HHI_MPLL_CNTL,
+		.shift   = 16,
+		.width   = 2,
+	},
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "fixed_pll",
+		.ops = &meson_clk_pll_ro_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+		.flags = CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct meson_clk_pll gxbb_hdmi_pll = {
+	.m = {
+		.reg_off = HHI_HDMI_PLL_CNTL,
+		.shift   = 0,
+		.width   = 9,
+	},
+	.n = {
+		.reg_off = HHI_HDMI_PLL_CNTL,
+		.shift   = 9,
+		.width   = 5,
+	},
+	.frac = {
+		.reg_off = HHI_HDMI_PLL_CNTL2,
+		.shift   = 0,
+		.width   = 12,
+	},
+	.od = {
+		.reg_off = HHI_HDMI_PLL_CNTL2,
+		.shift   = 16,
+		.width   = 2,
+	},
+	.od2 = {
+		.reg_off = HHI_HDMI_PLL_CNTL2,
+		.shift   = 22,
+		.width   = 2,
+	},
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "hdmi_pll",
+		.ops = &meson_clk_pll_ro_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+		.flags = CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct meson_clk_pll gxbb_sys_pll = {
+	.m = {
+		.reg_off = HHI_SYS_PLL_CNTL,
+		.shift   = 0,
+		.width   = 9,
+	},
+	.n = {
+		.reg_off = HHI_SYS_PLL_CNTL,
+		.shift   = 9,
+		.width   = 5,
+	},
+	.od = {
+		.reg_off = HHI_SYS_PLL_CNTL,
+		.shift   = 10,
+		.width   = 2,
+	},
+	.rate_table = sys_pll_rate_table,
+	.rate_count = ARRAY_SIZE(sys_pll_rate_table),
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "sys_pll",
+		.ops = &meson_clk_pll_ro_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+		.flags = CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct meson_clk_pll gxbb_gp0_pll = {
+	.m = {
+		.reg_off = HHI_GP0_PLL_CNTL,
+		.shift   = 0,
+		.width   = 9,
+	},
+	.n = {
+		.reg_off = HHI_GP0_PLL_CNTL,
+		.shift   = 9,
+		.width   = 5,
+	},
+	.od = {
+		.reg_off = HHI_GP0_PLL_CNTL,
+		.shift   = 16,
+		.width   = 2,
+	},
+	.rate_table = gp0_pll_rate_table,
+	.rate_count = ARRAY_SIZE(gp0_pll_rate_table),
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "gp0_pll",
+		.ops = &meson_clk_pll_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+		.flags = CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct clk_fixed_factor gxbb_fclk_div2 = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div2",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor gxbb_fclk_div3 = {
+	.mult = 1,
+	.div = 3,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div3",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor gxbb_fclk_div4 = {
+	.mult = 1,
+	.div = 4,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div4",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor gxbb_fclk_div5 = {
+	.mult = 1,
+	.div = 5,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div5",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor gxbb_fclk_div7 = {
+	.mult = 1,
+	.div = 7,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div7",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct meson_clk_mpll gxbb_mpll0 = {
+	.sdm = {
+		.reg_off = HHI_MPLL_CNTL7,
+		.shift   = 0,
+		.width   = 14,
+	},
+	.n2 = {
+		.reg_off = HHI_MPLL_CNTL7,
+		.shift   = 16,
+		.width   = 9,
+	},
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpll0",
+		.ops = &meson_clk_mpll_ro_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct meson_clk_mpll gxbb_mpll1 = {
+	.sdm = {
+		.reg_off = HHI_MPLL_CNTL8,
+		.shift   = 0,
+		.width   = 14,
+	},
+	.n2 = {
+		.reg_off = HHI_MPLL_CNTL8,
+		.shift   = 16,
+		.width   = 9,
+	},
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpll1",
+		.ops = &meson_clk_mpll_ro_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct meson_clk_mpll gxbb_mpll2 = {
+	.sdm = {
+		.reg_off = HHI_MPLL_CNTL9,
+		.shift   = 0,
+		.width   = 14,
+	},
+	.n2 = {
+		.reg_off = HHI_MPLL_CNTL9,
+		.shift   = 16,
+		.width   = 9,
+	},
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpll2",
+		.ops = &meson_clk_mpll_ro_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+/*
+ * FIXME cpu clocks and the legacy composite clocks (e.g. clk81) are both PLL
+ * post-dividers and should be modeled with their respective PLLs via the
+ * forthcoming coordinated clock rates feature
+ */
+static struct meson_clk_cpu gxbb_cpu_clk = {
+	.reg_off = HHI_SYS_CPU_CLK_CNTL1,
+	.div_table = cpu_div_table,
+	.clk_nb.notifier_call = meson_clk_cpu_notifier_cb,
+	.hw.init = &(struct clk_init_data){
+		.name = "cpu_clk",
+		.ops = &meson_clk_cpu_ops,
+		.parent_names = (const char *[]){ "sys_pll" },
+		.num_parents = 1,
+	},
+};
+
+static u32 mux_table_clk81[]	= { 6, 5, 7 };
+
+static struct clk_mux gxbb_mpeg_clk_sel = {
+	.reg = (void *)HHI_MPEG_CLK_CNTL,
+	.mask = 0x7,
+	.shift = 12,
+	.flags = CLK_MUX_READ_ONLY,
+	.table = mux_table_clk81,
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpeg_clk_sel",
+		.ops = &clk_mux_ro_ops,
+		/*
+		 * FIXME bits 14:12 selects from 8 possible parents:
+		 * xtal, 1'b0 (wtf), fclk_div7, mpll_clkout1, mpll_clkout2,
+		 * fclk_div4, fclk_div3, fclk_div5
+		 */
+		.parent_names = (const char *[]){ "fclk_div3", "fclk_div4",
+			"fclk_div5" },
+		.num_parents = 3,
+		.flags = (CLK_SET_RATE_NO_REPARENT | CLK_IGNORE_UNUSED),
+	},
+};
+
+static struct clk_divider gxbb_mpeg_clk_div = {
+	.reg = (void *)HHI_MPEG_CLK_CNTL,
+	.shift = 0,
+	.width = 7,
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpeg_clk_div",
+		.ops = &clk_divider_ops,
+		.parent_names = (const char *[]){ "mpeg_clk_sel" },
+		.num_parents = 1,
+		.flags = (CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED),
+	},
+};
+
+/* the mother of dragons^W gates */
+static struct clk_gate gxbb_clk81 = {
+	.reg = (void *)HHI_MPEG_CLK_CNTL,
+	.bit_idx = 7,
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "clk81",
+		.ops = &clk_gate_ops,
+		.parent_names = (const char *[]){ "mpeg_clk_div" },
+		.num_parents = 1,
+		.flags = (CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED | CLK_IS_CRITICAL),
+	},
+};
+
+/* Everything Else (EE) domain gates */
+static MESON_GATE(ddr, HHI_GCLK_MPEG0, 0);
+static MESON_GATE(dos, HHI_GCLK_MPEG0, 1);
+static MESON_GATE(isa, HHI_GCLK_MPEG0, 5);
+static MESON_GATE(pl301, HHI_GCLK_MPEG0, 6);
+static MESON_GATE(periphs, HHI_GCLK_MPEG0, 7);
+static MESON_GATE(spicc, HHI_GCLK_MPEG0, 8);
+static MESON_GATE(i2c, HHI_GCLK_MPEG0, 9);
+static MESON_GATE(sar_adc, HHI_GCLK_MPEG0, 10);
+static MESON_GATE(smart_card, HHI_GCLK_MPEG0, 11);
+static MESON_GATE(rng0, HHI_GCLK_MPEG0, 12);
+static MESON_GATE(uart0, HHI_GCLK_MPEG0, 13);
+static MESON_GATE(sdhc, HHI_GCLK_MPEG0, 14);
+static MESON_GATE(stream, HHI_GCLK_MPEG0, 15);
+static MESON_GATE(async_fifo, HHI_GCLK_MPEG0, 16);
+static MESON_GATE(sdio, HHI_GCLK_MPEG0, 17);
+static MESON_GATE(abuf, HHI_GCLK_MPEG0, 18);
+static MESON_GATE(hiu_iface, HHI_GCLK_MPEG0, 19);
+static MESON_GATE(assist_misc, HHI_GCLK_MPEG0, 23);
+static MESON_GATE(spi, HHI_GCLK_MPEG0, 30);
+
+static MESON_GATE(i2s_spdif, HHI_GCLK_MPEG1, 2);
+static MESON_GATE(eth, HHI_GCLK_MPEG1, 3);
+static MESON_GATE(demux, HHI_GCLK_MPEG1, 4);
+static MESON_GATE(aiu_glue, HHI_GCLK_MPEG1, 6);
+static MESON_GATE(iec958, HHI_GCLK_MPEG1, 7);
+static MESON_GATE(i2s_out, HHI_GCLK_MPEG1, 8);
+static MESON_GATE(amclk, HHI_GCLK_MPEG1, 9);
+static MESON_GATE(aififo2, HHI_GCLK_MPEG1, 10);
+static MESON_GATE(mixer, HHI_GCLK_MPEG1, 11);
+static MESON_GATE(mixer_iface, HHI_GCLK_MPEG1, 12);
+static MESON_GATE(adc, HHI_GCLK_MPEG1, 13);
+static MESON_GATE(blkmv, HHI_GCLK_MPEG1, 14);
+static MESON_GATE(aiu, HHI_GCLK_MPEG1, 15);
+static MESON_GATE(uart1, HHI_GCLK_MPEG1, 16);
+static MESON_GATE(g2d, HHI_GCLK_MPEG1, 20);
+static MESON_GATE(usb0, HHI_GCLK_MPEG1, 21);
+static MESON_GATE(usb1, HHI_GCLK_MPEG1, 22);
+static MESON_GATE(reset, HHI_GCLK_MPEG1, 23);
+static MESON_GATE(nand, HHI_GCLK_MPEG1, 24);
+static MESON_GATE(dos_parser, HHI_GCLK_MPEG1, 25);
+static MESON_GATE(usb, HHI_GCLK_MPEG1, 26);
+static MESON_GATE(vdin1, HHI_GCLK_MPEG1, 28);
+static MESON_GATE(ahb_arb0, HHI_GCLK_MPEG1, 29);
+static MESON_GATE(efuse, HHI_GCLK_MPEG1, 30);
+static MESON_GATE(boot_rom, HHI_GCLK_MPEG1, 31);
+
+static MESON_GATE(ahb_data_bus, HHI_GCLK_MPEG2, 1);
+static MESON_GATE(ahb_ctrl_bus, HHI_GCLK_MPEG2, 2);
+static MESON_GATE(hdmi_intr_sync, HHI_GCLK_MPEG2, 3);
+static MESON_GATE(hdmi_pclk, HHI_GCLK_MPEG2, 4);
+static MESON_GATE(usb1_ddr_bridge, HHI_GCLK_MPEG2, 8);
+static MESON_GATE(usb0_ddr_bridge, HHI_GCLK_MPEG2, 9);
+static MESON_GATE(mmc_pclk, HHI_GCLK_MPEG2, 11);
+static MESON_GATE(dvin, HHI_GCLK_MPEG2, 12);
+static MESON_GATE(uart2, HHI_GCLK_MPEG2, 15);
+static MESON_GATE(sana, HHI_GCLK_MPEG2, 22);
+static MESON_GATE(vpu_intr, HHI_GCLK_MPEG2, 25);
+static MESON_GATE(sec_ahb_ahb3_bridge, HHI_GCLK_MPEG2, 26);
+static MESON_GATE(clk81_a53, HHI_GCLK_MPEG2, 29);
+
+static MESON_GATE(vclk2_venci0, HHI_GCLK_OTHER, 1);
+static MESON_GATE(vclk2_venci1, HHI_GCLK_OTHER, 2);
+static MESON_GATE(vclk2_vencp0, HHI_GCLK_OTHER, 3);
+static MESON_GATE(vclk2_vencp1, HHI_GCLK_OTHER, 4);
+static MESON_GATE(gclk_venci_int0, HHI_GCLK_OTHER, 8);
+static MESON_GATE(gclk_vencp_int, HHI_GCLK_OTHER, 9);
+static MESON_GATE(dac_clk, HHI_GCLK_OTHER, 10);
+static MESON_GATE(aoclk_gate, HHI_GCLK_OTHER, 14);
+static MESON_GATE(iec958_gate, HHI_GCLK_OTHER, 16);
+static MESON_GATE(enc480p, HHI_GCLK_OTHER, 20);
+static MESON_GATE(rng1, HHI_GCLK_OTHER, 21);
+static MESON_GATE(gclk_venci_int1, HHI_GCLK_OTHER, 22);
+static MESON_GATE(vclk2_venclmcc, HHI_GCLK_OTHER, 24);
+static MESON_GATE(vclk2_vencl, HHI_GCLK_OTHER, 25);
+static MESON_GATE(vclk_other, HHI_GCLK_OTHER, 26);
+static MESON_GATE(edp, HHI_GCLK_OTHER, 31);
+
+/* Always On (AO) domain gates */
+
+static MESON_GATE(ao_media_cpu, HHI_GCLK_AO, 0);
+static MESON_GATE(ao_ahb_sram, HHI_GCLK_AO, 1);
+static MESON_GATE(ao_ahb_bus, HHI_GCLK_AO, 2);
+static MESON_GATE(ao_iface, HHI_GCLK_AO, 3);
+static MESON_GATE(ao_i2c, HHI_GCLK_AO, 4);
+
+/* Array of all clocks provided by this provider */
+
+static struct clk_hw_onecell_data gxbb_hw_onecell_data = {
+	.hws = {
+		[CLKID_SYS_PLL]		    = &gxbb_sys_pll.hw,
+		[CLKID_CPUCLK]		    = &gxbb_cpu_clk.hw,
+		[CLKID_HDMI_PLL]	    = &gxbb_hdmi_pll.hw,
+		[CLKID_FIXED_PLL]	    = &gxbb_fixed_pll.hw,
+		[CLKID_FCLK_DIV2]	    = &gxbb_fclk_div2.hw,
+		[CLKID_FCLK_DIV3]	    = &gxbb_fclk_div3.hw,
+		[CLKID_FCLK_DIV4]	    = &gxbb_fclk_div4.hw,
+		[CLKID_FCLK_DIV5]	    = &gxbb_fclk_div5.hw,
+		[CLKID_FCLK_DIV7]	    = &gxbb_fclk_div7.hw,
+		[CLKID_GP0_PLL]		    = &gxbb_gp0_pll.hw,
+		[CLKID_MPEG_SEL]	    = &gxbb_mpeg_clk_sel.hw,
+		[CLKID_MPEG_DIV]	    = &gxbb_mpeg_clk_div.hw,
+		[CLKID_CLK81]		    = &gxbb_clk81.hw,
+		[CLKID_MPLL0]		    = &gxbb_mpll0.hw,
+		[CLKID_MPLL1]		    = &gxbb_mpll1.hw,
+		[CLKID_MPLL2]		    = &gxbb_mpll2.hw,
+		[CLKID_DDR]		    = &gxbb_ddr.hw,
+		[CLKID_DOS]		    = &gxbb_dos.hw,
+		[CLKID_ISA]		    = &gxbb_isa.hw,
+		[CLKID_PL301]		    = &gxbb_pl301.hw,
+		[CLKID_PERIPHS]		    = &gxbb_periphs.hw,
+		[CLKID_SPICC]		    = &gxbb_spicc.hw,
+		[CLKID_I2C]		    = &gxbb_i2c.hw,
+		[CLKID_SAR_ADC]		    = &gxbb_sar_adc.hw,
+		[CLKID_SMART_CARD]	    = &gxbb_smart_card.hw,
+		[CLKID_RNG0]		    = &gxbb_rng0.hw,
+		[CLKID_UART0]		    = &gxbb_uart0.hw,
+		[CLKID_SDHC]		    = &gxbb_sdhc.hw,
+		[CLKID_STREAM]		    = &gxbb_stream.hw,
+		[CLKID_ASYNC_FIFO]	    = &gxbb_async_fifo.hw,
+		[CLKID_SDIO]		    = &gxbb_sdio.hw,
+		[CLKID_ABUF]		    = &gxbb_abuf.hw,
+		[CLKID_HIU_IFACE]	    = &gxbb_hiu_iface.hw,
+		[CLKID_ASSIST_MISC]	    = &gxbb_assist_misc.hw,
+		[CLKID_SPI]		    = &gxbb_spi.hw,
+		[CLKID_I2S_SPDIF]	    = &gxbb_i2s_spdif.hw,
+		[CLKID_ETH]		    = &gxbb_eth.hw,
+		[CLKID_DEMUX]		    = &gxbb_demux.hw,
+		[CLKID_AIU_GLUE]	    = &gxbb_aiu_glue.hw,
+		[CLKID_IEC958]		    = &gxbb_iec958.hw,
+		[CLKID_I2S_OUT]		    = &gxbb_i2s_out.hw,
+		[CLKID_AMCLK]		    = &gxbb_amclk.hw,
+		[CLKID_AIFIFO2]		    = &gxbb_aififo2.hw,
+		[CLKID_MIXER]		    = &gxbb_mixer.hw,
+		[CLKID_MIXER_IFACE]	    = &gxbb_mixer_iface.hw,
+		[CLKID_ADC]		    = &gxbb_adc.hw,
+		[CLKID_BLKMV]		    = &gxbb_blkmv.hw,
+		[CLKID_AIU]		    = &gxbb_aiu.hw,
+		[CLKID_UART1]		    = &gxbb_uart1.hw,
+		[CLKID_G2D]		    = &gxbb_g2d.hw,
+		[CLKID_USB0]		    = &gxbb_usb0.hw,
+		[CLKID_USB1]		    = &gxbb_usb1.hw,
+		[CLKID_RESET]		    = &gxbb_reset.hw,
+		[CLKID_NAND]		    = &gxbb_nand.hw,
+		[CLKID_DOS_PARSER]	    = &gxbb_dos_parser.hw,
+		[CLKID_USB]		    = &gxbb_usb.hw,
+		[CLKID_VDIN1]		    = &gxbb_vdin1.hw,
+		[CLKID_AHB_ARB0]	    = &gxbb_ahb_arb0.hw,
+		[CLKID_EFUSE]		    = &gxbb_efuse.hw,
+		[CLKID_BOOT_ROM]	    = &gxbb_boot_rom.hw,
+		[CLKID_AHB_DATA_BUS]	    = &gxbb_ahb_data_bus.hw,
+		[CLKID_AHB_CTRL_BUS]	    = &gxbb_ahb_ctrl_bus.hw,
+		[CLKID_HDMI_INTR_SYNC]	    = &gxbb_hdmi_intr_sync.hw,
+		[CLKID_HDMI_PCLK]	    = &gxbb_hdmi_pclk.hw,
+		[CLKID_USB1_DDR_BRIDGE]	    = &gxbb_usb1_ddr_bridge.hw,
+		[CLKID_USB0_DDR_BRIDGE]	    = &gxbb_usb0_ddr_bridge.hw,
+		[CLKID_MMC_PCLK]	    = &gxbb_mmc_pclk.hw,
+		[CLKID_DVIN]		    = &gxbb_dvin.hw,
+		[CLKID_UART2]		    = &gxbb_uart2.hw,
+		[CLKID_SANA]		    = &gxbb_sana.hw,
+		[CLKID_VPU_INTR]	    = &gxbb_vpu_intr.hw,
+		[CLKID_SEC_AHB_AHB3_BRIDGE] = &gxbb_sec_ahb_ahb3_bridge.hw,
+		[CLKID_CLK81_A53]	    = &gxbb_clk81_a53.hw,
+		[CLKID_VCLK2_VENCI0]	    = &gxbb_vclk2_venci0.hw,
+		[CLKID_VCLK2_VENCI1]	    = &gxbb_vclk2_venci1.hw,
+		[CLKID_VCLK2_VENCP0]	    = &gxbb_vclk2_vencp0.hw,
+		[CLKID_VCLK2_VENCP1]	    = &gxbb_vclk2_vencp1.hw,
+		[CLKID_GCLK_VENCI_INT0]	    = &gxbb_gclk_venci_int0.hw,
+		[CLKID_GCLK_VENCI_INT]	    = &gxbb_gclk_vencp_int.hw,
+		[CLKID_DAC_CLK]		    = &gxbb_dac_clk.hw,
+		[CLKID_AOCLK_GATE]	    = &gxbb_aoclk_gate.hw,
+		[CLKID_IEC958_GATE]	    = &gxbb_iec958_gate.hw,
+		[CLKID_ENC480P]		    = &gxbb_enc480p.hw,
+		[CLKID_RNG1]		    = &gxbb_rng1.hw,
+		[CLKID_GCLK_VENCI_INT1]	    = &gxbb_gclk_venci_int1.hw,
+		[CLKID_VCLK2_VENCLMCC]	    = &gxbb_vclk2_venclmcc.hw,
+		[CLKID_VCLK2_VENCL]	    = &gxbb_vclk2_vencl.hw,
+		[CLKID_VCLK_OTHER]	    = &gxbb_vclk_other.hw,
+		[CLKID_EDP]		    = &gxbb_edp.hw,
+		[CLKID_AO_MEDIA_CPU]	    = &gxbb_ao_media_cpu.hw,
+		[CLKID_AO_AHB_SRAM]	    = &gxbb_ao_ahb_sram.hw,
+		[CLKID_AO_AHB_BUS]	    = &gxbb_ao_ahb_bus.hw,
+		[CLKID_AO_IFACE]	    = &gxbb_ao_iface.hw,
+		[CLKID_AO_I2C]		    = &gxbb_ao_i2c.hw,
+	},
+	.num = NR_CLKS,
+};
+
+/* Convenience tables to populate base addresses in .probe */
+
+static struct meson_clk_pll *const gxbb_clk_plls[] = {
+	&gxbb_fixed_pll,
+	&gxbb_hdmi_pll,
+	&gxbb_sys_pll,
+	&gxbb_gp0_pll,
+};
+
+static struct meson_clk_mpll *const gxbb_clk_mplls[] = {
+	&gxbb_mpll0,
+	&gxbb_mpll1,
+	&gxbb_mpll2,
+};
+
+static struct clk_gate *gxbb_clk_gates[] = {
+	&gxbb_clk81,
+	&gxbb_ddr,
+	&gxbb_dos,
+	&gxbb_isa,
+	&gxbb_pl301,
+	&gxbb_periphs,
+	&gxbb_spicc,
+	&gxbb_i2c,
+	&gxbb_sar_adc,
+	&gxbb_smart_card,
+	&gxbb_rng0,
+	&gxbb_uart0,
+	&gxbb_sdhc,
+	&gxbb_stream,
+	&gxbb_async_fifo,
+	&gxbb_sdio,
+	&gxbb_abuf,
+	&gxbb_hiu_iface,
+	&gxbb_assist_misc,
+	&gxbb_spi,
+	&gxbb_i2s_spdif,
+	&gxbb_eth,
+	&gxbb_demux,
+	&gxbb_aiu_glue,
+	&gxbb_iec958,
+	&gxbb_i2s_out,
+	&gxbb_amclk,
+	&gxbb_aififo2,
+	&gxbb_mixer,
+	&gxbb_mixer_iface,
+	&gxbb_adc,
+	&gxbb_blkmv,
+	&gxbb_aiu,
+	&gxbb_uart1,
+	&gxbb_g2d,
+	&gxbb_usb0,
+	&gxbb_usb1,
+	&gxbb_reset,
+	&gxbb_nand,
+	&gxbb_dos_parser,
+	&gxbb_usb,
+	&gxbb_vdin1,
+	&gxbb_ahb_arb0,
+	&gxbb_efuse,
+	&gxbb_boot_rom,
+	&gxbb_ahb_data_bus,
+	&gxbb_ahb_ctrl_bus,
+	&gxbb_hdmi_intr_sync,
+	&gxbb_hdmi_pclk,
+	&gxbb_usb1_ddr_bridge,
+	&gxbb_usb0_ddr_bridge,
+	&gxbb_mmc_pclk,
+	&gxbb_dvin,
+	&gxbb_uart2,
+	&gxbb_sana,
+	&gxbb_vpu_intr,
+	&gxbb_sec_ahb_ahb3_bridge,
+	&gxbb_clk81_a53,
+	&gxbb_vclk2_venci0,
+	&gxbb_vclk2_venci1,
+	&gxbb_vclk2_vencp0,
+	&gxbb_vclk2_vencp1,
+	&gxbb_gclk_venci_int0,
+	&gxbb_gclk_vencp_int,
+	&gxbb_dac_clk,
+	&gxbb_aoclk_gate,
+	&gxbb_iec958_gate,
+	&gxbb_enc480p,
+	&gxbb_rng1,
+	&gxbb_gclk_venci_int1,
+	&gxbb_vclk2_venclmcc,
+	&gxbb_vclk2_vencl,
+	&gxbb_vclk_other,
+	&gxbb_edp,
+	&gxbb_ao_media_cpu,
+	&gxbb_ao_ahb_sram,
+	&gxbb_ao_ahb_bus,
+	&gxbb_ao_iface,
+	&gxbb_ao_i2c,
+};
+
+static int gxbb_clkc_probe(struct platform_device *pdev)
+{
+	void __iomem *clk_base;
+	int ret, clkid, i;
+	struct clk_hw *parent_hw;
+	struct clk *parent_clk;
+	struct device *dev = &pdev->dev;
+
+	/*  Generic clocks and PLLs */
+	clk_base = of_iomap(dev->of_node, 0);
+	if (!clk_base) {
+		pr_err("%s: Unable to map clk base\n", __func__);
+		return -ENXIO;
+	}
+
+	/* Populate base address for PLLs */
+	for (i = 0; i < ARRAY_SIZE(gxbb_clk_plls); i++)
+		gxbb_clk_plls[i]->base = clk_base;
+
+	/* Populate base address for MPLLs */
+	for (i = 0; i < ARRAY_SIZE(gxbb_clk_mplls); i++)
+		gxbb_clk_mplls[i]->base = clk_base;
+
+	/* Populate the base address for CPU clk */
+	gxbb_cpu_clk.base = clk_base;
+
+	/* Populate the base address for the MPEG clks */
+	gxbb_mpeg_clk_sel.reg = clk_base + (u64)gxbb_mpeg_clk_sel.reg;
+	gxbb_mpeg_clk_div.reg = clk_base + (u64)gxbb_mpeg_clk_div.reg;
+
+	/* Populate base address for gates */
+	for (i = 0; i < ARRAY_SIZE(gxbb_clk_gates); i++)
+		gxbb_clk_gates[i]->reg = clk_base +
+			(u64)gxbb_clk_gates[i]->reg;
+
+	/*
+	 * register all clks
+	 */
+	for (clkid = 0; clkid < NR_CLKS; clkid++) {
+		ret = devm_clk_hw_register(dev, gxbb_hw_onecell_data.hws[clkid]);
+		if (ret)
+			goto iounmap;
+	}
+
+	/*
+	 * Register CPU clk notifier
+	 *
+	 * FIXME this is wrong for a lot of reasons. First, the muxes should be
+	 * struct clk_hw objects. Second, we shouldn't program the muxes in
+	 * notifier handlers. The tricky programming sequence will be handled
+	 * by the forthcoming coordinated clock rates mechanism once that
+	 * feature is released.
+	 *
+	 * Furthermore, looking up the parent this way is terrible. At some
+	 * point we will stop allocating a default struct clk when registering
+	 * a new clk_hw, and this hack will no longer work. Releasing the ccr
+	 * feature before that time solves the problem :-)
+	 */
+	parent_hw = clk_hw_get_parent(&gxbb_cpu_clk.hw);
+	parent_clk = parent_hw->clk;
+	ret = clk_notifier_register(parent_clk, &gxbb_cpu_clk.clk_nb);
+	if (ret) {
+		pr_err("%s: failed to register clock notifier for cpu_clk\n",
+				__func__);
+		goto iounmap;
+	}
+
+	return of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get,
+			&gxbb_hw_onecell_data);
+
+iounmap:
+	iounmap(clk_base);
+	return ret;
+}
+
+static const struct of_device_id gxbb_clkc_match_table[] = {
+	{ .compatible = "amlogic,gxbb-clkc" },
+	{ }
+};
+
+static struct platform_driver gxbb_driver = {
+	.probe		= gxbb_clkc_probe,
+	.driver		= {
+		.name	= "gxbb-clkc",
+		.of_match_table = gxbb_clkc_match_table,
+	},
+};
+
+static int __init gxbb_clkc_init(void)
+{
+	return platform_driver_register(&gxbb_driver);
+}
+device_initcall(gxbb_clkc_init);
diff --git a/drivers/clk/meson/gxbb.h b/drivers/clk/meson/gxbb.h
new file mode 100644
index 000000000000..a2adf3448b59
--- /dev/null
+++ b/drivers/clk/meson/gxbb.h
@@ -0,0 +1,271 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (c) 2016 AmLogic, Inc.
+ * Author: Michael Turquette <mturquette@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING
+ *
+ * BSD LICENSE
+ *
+ * Copyright (c) 2016 BayLibre, Inc.
+ * Author: Michael Turquette <mturquette@baylibre.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __GXBB_H
+#define __GXBB_H
+
+/*
+ * Clock controller register offsets
+ *
+ * Register offsets from the data sheet are listed in comment blocks below.
+ * Those offsets must be multiplied by 4 before adding them to the base address
+ * to get the right value
+ */
+#define SCR				0x2C /* 0x0b offset in data sheet */
+#define TIMEOUT_VALUE			0x3c /* 0x0f offset in data sheet */
+
+#define HHI_GP0_PLL_CNTL		0x40 /* 0x10 offset in data sheet */
+#define HHI_GP0_PLL_CNTL2		0x44 /* 0x11 offset in data sheet */
+#define HHI_GP0_PLL_CNTL3		0x48 /* 0x12 offset in data sheet */
+#define HHI_GP0_PLL_CNTL4		0x4c /* 0x13 offset in data sheet */
+
+#define HHI_XTAL_DIVN_CNTL		0xbc /* 0x2f offset in data sheet */
+#define HHI_TIMER90K			0xec /* 0x3b offset in data sheet */
+
+#define HHI_MEM_PD_REG0			0x100 /* 0x40 offset in data sheet */
+#define HHI_MEM_PD_REG1			0x104 /* 0x41 offset in data sheet */
+#define HHI_VPU_MEM_PD_REG1		0x108 /* 0x42 offset in data sheet */
+#define HHI_VIID_CLK_DIV		0x128 /* 0x4a offset in data sheet */
+#define HHI_VIID_CLK_CNTL		0x12c /* 0x4b offset in data sheet */
+
+#define HHI_GCLK_MPEG0			0x140 /* 0x50 offset in data sheet */
+#define HHI_GCLK_MPEG1			0x144 /* 0x51 offset in data sheet */
+#define HHI_GCLK_MPEG2			0x148 /* 0x52 offset in data sheet */
+#define HHI_GCLK_OTHER			0x150 /* 0x54 offset in data sheet */
+#define HHI_GCLK_AO			0x154 /* 0x55 offset in data sheet */
+#define HHI_SYS_OSCIN_CNTL		0x158 /* 0x56 offset in data sheet */
+#define HHI_SYS_CPU_CLK_CNTL1		0x15c /* 0x57 offset in data sheet */
+#define HHI_SYS_CPU_RESET_CNTL		0x160 /* 0x58 offset in data sheet */
+#define HHI_VID_CLK_DIV			0x164 /* 0x59 offset in data sheet */
+
+#define HHI_MPEG_CLK_CNTL		0x174 /* 0x5d offset in data sheet */
+#define HHI_AUD_CLK_CNTL		0x178 /* 0x5e offset in data sheet */
+#define HHI_VID_CLK_CNTL		0x17c /* 0x5f offset in data sheet */
+#define HHI_AUD_CLK_CNTL2		0x190 /* 0x64 offset in data sheet */
+#define HHI_VID_CLK_CNTL2		0x194 /* 0x65 offset in data sheet */
+#define HHI_SYS_CPU_CLK_CNTL0		0x19c /* 0x67 offset in data sheet */
+#define HHI_VID_PLL_CLK_DIV		0x1a0 /* 0x68 offset in data sheet */
+#define HHI_AUD_CLK_CNTL3		0x1a4 /* 0x69 offset in data sheet */
+#define HHI_MALI_CLK_CNTL		0x1b0 /* 0x6c offset in data sheet */
+#define HHI_VPU_CLK_CNTL		0x1bC /* 0x6f offset in data sheet */
+
+#define HHI_HDMI_CLK_CNTL		0x1CC /* 0x73 offset in data sheet */
+#define HHI_VDEC_CLK_CNTL		0x1E0 /* 0x78 offset in data sheet */
+#define HHI_VDEC2_CLK_CNTL		0x1E4 /* 0x79 offset in data sheet */
+#define HHI_VDEC3_CLK_CNTL		0x1E8 /* 0x7a offset in data sheet */
+#define HHI_VDEC4_CLK_CNTL		0x1EC /* 0x7b offset in data sheet */
+#define HHI_HDCP22_CLK_CNTL		0x1F0 /* 0x7c offset in data sheet */
+#define HHI_VAPBCLK_CNTL		0x1F4 /* 0x7d offset in data sheet */
+
+#define HHI_VPU_CLKB_CNTL		0x20C /* 0x83 offset in data sheet */
+#define HHI_USB_CLK_CNTL		0x220 /* 0x88 offset in data sheet */
+#define HHI_32K_CLK_CNTL		0x224 /* 0x89 offset in data sheet */
+#define HHI_GEN_CLK_CNTL		0x228 /* 0x8a offset in data sheet */
+#define HHI_GEN_CLK_CNTL		0x228 /* 0x8a offset in data sheet */
+
+#define HHI_PCM_CLK_CNTL		0x258 /* 0x96 offset in data sheet */
+#define HHI_NAND_CLK_CNTL		0x25C /* 0x97 offset in data sheet */
+#define HHI_SD_EMMC_CLK_CNTL		0x264 /* 0x99 offset in data sheet */
+
+#define HHI_MPLL_CNTL			0x280 /* 0xa0 offset in data sheet */
+#define HHI_MPLL_CNTL2			0x284 /* 0xa1 offset in data sheet */
+#define HHI_MPLL_CNTL3			0x288 /* 0xa2 offset in data sheet */
+#define HHI_MPLL_CNTL4			0x28C /* 0xa3 offset in data sheet */
+#define HHI_MPLL_CNTL5			0x290 /* 0xa4 offset in data sheet */
+#define HHI_MPLL_CNTL6			0x294 /* 0xa5 offset in data sheet */
+#define HHI_MPLL_CNTL7			0x298 /* MP0, 0xa6 offset in data sheet */
+#define HHI_MPLL_CNTL8			0x29C /* MP1, 0xa7 offset in data sheet */
+#define HHI_MPLL_CNTL9			0x2A0 /* MP2, 0xa8 offset in data sheet */
+#define HHI_MPLL_CNTL10			0x2A4 /* MP2, 0xa9 offset in data sheet */
+
+#define HHI_MPLL3_CNTL0			0x2E0 /* 0xb8 offset in data sheet */
+#define HHI_MPLL3_CNTL1			0x2E4 /* 0xb9 offset in data sheet */
+#define HHI_VDAC_CNTL0			0x2F4 /* 0xbd offset in data sheet */
+#define HHI_VDAC_CNTL1			0x2F8 /* 0xbe offset in data sheet */
+
+#define HHI_SYS_PLL_CNTL		0x300 /* 0xc0 offset in data sheet */
+#define HHI_SYS_PLL_CNTL2		0x304 /* 0xc1 offset in data sheet */
+#define HHI_SYS_PLL_CNTL3		0x308 /* 0xc2 offset in data sheet */
+#define HHI_SYS_PLL_CNTL4		0x30c /* 0xc3 offset in data sheet */
+#define HHI_SYS_PLL_CNTL5		0x310 /* 0xc4 offset in data sheet */
+#define HHI_DPLL_TOP_I			0x318 /* 0xc6 offset in data sheet */
+#define HHI_DPLL_TOP2_I			0x31C /* 0xc7 offset in data sheet */
+#define HHI_HDMI_PLL_CNTL		0x320 /* 0xc8 offset in data sheet */
+#define HHI_HDMI_PLL_CNTL2		0x324 /* 0xc9 offset in data sheet */
+#define HHI_HDMI_PLL_CNTL3		0x328 /* 0xca offset in data sheet */
+#define HHI_HDMI_PLL_CNTL4		0x32C /* 0xcb offset in data sheet */
+#define HHI_HDMI_PLL_CNTL5		0x330 /* 0xcc offset in data sheet */
+#define HHI_HDMI_PLL_CNTL6		0x334 /* 0xcd offset in data sheet */
+#define HHI_HDMI_PLL_CNTL_I		0x338 /* 0xce offset in data sheet */
+#define HHI_HDMI_PLL_CNTL7		0x33C /* 0xcf offset in data sheet */
+
+#define HHI_HDMI_PHY_CNTL0		0x3A0 /* 0xe8 offset in data sheet */
+#define HHI_HDMI_PHY_CNTL1		0x3A4 /* 0xe9 offset in data sheet */
+#define HHI_HDMI_PHY_CNTL2		0x3A8 /* 0xea offset in data sheet */
+#define HHI_HDMI_PHY_CNTL3		0x3AC /* 0xeb offset in data sheet */
+
+#define HHI_VID_LOCK_CLK_CNTL		0x3C8 /* 0xf2 offset in data sheet */
+#define HHI_BT656_CLK_CNTL		0x3D4 /* 0xf5 offset in data sheet */
+#define HHI_SAR_CLK_CNTL		0x3D8 /* 0xf6 offset in data sheet */
+
+/*
+ * CLKID index values
+ *
+ * These indices are entirely contrived and do not map onto the hardware.
+ * Migrate them out of this header and into the DT header file when they need
+ * to be exposed to client nodes in DT: include/dt-bindings/clock/gxbb-clkc.h
+ */
+#define CLKID_SYS_PLL		  0
+/* CLKID_CPUCLK */
+#define CLKID_HDMI_PLL		  2
+#define CLKID_FIXED_PLL		  3
+#define CLKID_FCLK_DIV2		  4
+#define CLKID_FCLK_DIV3		  5
+#define CLKID_FCLK_DIV4		  6
+#define CLKID_FCLK_DIV5		  7
+#define CLKID_FCLK_DIV7		  8
+#define CLKID_GP0_PLL		  9
+#define CLKID_MPEG_SEL		  10
+#define CLKID_MPEG_DIV		  11
+/* CLKID_CLK81 */
+#define CLKID_MPLL0		  13
+#define CLKID_MPLL1		  14
+#define CLKID_MPLL2		  15
+#define CLKID_DDR		  16
+#define CLKID_DOS		  17
+#define CLKID_ISA		  18
+#define CLKID_PL301		  19
+#define CLKID_PERIPHS		  20
+#define CLKID_SPICC		  21
+#define CLKID_I2C		  22
+#define CLKID_SAR_ADC		  23
+#define CLKID_SMART_CARD	  24
+#define CLKID_RNG0		  25
+#define CLKID_UART0		  26
+#define CLKID_SDHC		  27
+#define CLKID_STREAM		  28
+#define CLKID_ASYNC_FIFO	  29
+#define CLKID_SDIO		  30
+#define CLKID_ABUF		  31
+#define CLKID_HIU_IFACE		  32
+#define CLKID_ASSIST_MISC	  33
+#define CLKID_SPI		  34
+#define CLKID_I2S_SPDIF		  35
+#define CLKID_ETH		  36
+#define CLKID_DEMUX		  37
+#define CLKID_AIU_GLUE		  38
+#define CLKID_IEC958		  39
+#define CLKID_I2S_OUT		  40
+#define CLKID_AMCLK		  41
+#define CLKID_AIFIFO2		  42
+#define CLKID_MIXER		  43
+#define CLKID_MIXER_IFACE	  44
+#define CLKID_ADC		  45
+#define CLKID_BLKMV		  46
+#define CLKID_AIU		  47
+#define CLKID_UART1		  48
+#define CLKID_G2D		  49
+#define CLKID_USB0		  50
+#define CLKID_USB1		  51
+#define CLKID_RESET		  52
+#define CLKID_NAND		  53
+#define CLKID_DOS_PARSER	  54
+#define CLKID_USB		  55
+#define CLKID_VDIN1		  56
+#define CLKID_AHB_ARB0		  57
+#define CLKID_EFUSE		  58
+#define CLKID_BOOT_ROM		  59
+#define CLKID_AHB_DATA_BUS	  60
+#define CLKID_AHB_CTRL_BUS	  61
+#define CLKID_HDMI_INTR_SYNC	  62
+#define CLKID_HDMI_PCLK		  63
+#define CLKID_USB1_DDR_BRIDGE	  64
+#define CLKID_USB0_DDR_BRIDGE	  65
+#define CLKID_MMC_PCLK		  66
+#define CLKID_DVIN		  67
+#define CLKID_UART2		  68
+#define CLKID_SANA		  69
+#define CLKID_VPU_INTR		  70
+#define CLKID_SEC_AHB_AHB3_BRIDGE 71
+#define CLKID_CLK81_A53		  72
+#define CLKID_VCLK2_VENCI0	  73
+#define CLKID_VCLK2_VENCI1	  74
+#define CLKID_VCLK2_VENCP0	  75
+#define CLKID_VCLK2_VENCP1	  76
+#define CLKID_GCLK_VENCI_INT0	  77
+#define CLKID_GCLK_VENCI_INT	  78
+#define CLKID_DAC_CLK		  79
+#define CLKID_AOCLK_GATE	  80
+#define CLKID_IEC958_GATE	  81
+#define CLKID_ENC480P		  82
+#define CLKID_RNG1		  83
+#define CLKID_GCLK_VENCI_INT1	  84
+#define CLKID_VCLK2_VENCLMCC	  85
+#define CLKID_VCLK2_VENCL	  86
+#define CLKID_VCLK_OTHER	  87
+#define CLKID_EDP		  88
+#define CLKID_AO_MEDIA_CPU	  89
+#define CLKID_AO_AHB_SRAM	  90
+#define CLKID_AO_AHB_BUS	  91
+#define CLKID_AO_IFACE		  92
+#define CLKID_AO_I2C		  93
+
+#define NR_CLKS			  94
+
+/* include the CLKIDs that have been made part of the stable DT binding */
+#include <dt-bindings/clock/gxbb-clkc.h>
+
+#endif /* __GXBB_H */
diff --git a/drivers/clk/meson/meson8b-clkc.c b/drivers/clk/meson/meson8b-clkc.c
index 4d057b3e21b2..4c9413cdf373 100644
--- a/drivers/clk/meson/meson8b-clkc.c
+++ b/drivers/clk/meson/meson8b-clkc.c
@@ -1,7 +1,12 @@
 /*
+ * AmLogic S805 / Meson8b Clock Controller Driver
+ *
  * Copyright (c) 2015 Endless Mobile, Inc.
  * Author: Carlo Caione <carlo@endlessm.com>
  *
+ * Copyright (c) 2016 BayLibre, Inc.
+ * Michael Turquette <mturquette@baylibre.com>
+ *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
  * version 2, as published by the Free Software Foundation.
@@ -15,23 +20,33 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
-#include <linux/kernel.h>
-#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/slab.h>
 #include <dt-bindings/clock/meson8b-clkc.h>
+#include <linux/platform_device.h>
+#include <linux/init.h>
 
 #include "clkc.h"
 
-#define MESON8B_REG_CTL0_ADDR		0x0000
-#define MESON8B_REG_SYS_CPU_CNTL1	0x015c
-#define MESON8B_REG_HHI_MPEG		0x0174
-#define MESON8B_REG_MALI		0x01b0
+/*
+ * Clock controller register offsets
+ *
+ * Register offsets from the HardKernel[0] data sheet are listed in comment
+ * blocks below. Those offsets must be multiplied by 4 before adding them to
+ * the base address to get the right value
+ *
+ * [0] http://dn.odroid.com/S805/Datasheet/S805_Datasheet%20V0.8%2020150126.pdf
+ */
+#define MESON8B_REG_SYS_CPU_CNTL1	0x015c /* 0x57 offset in data sheet */
+#define MESON8B_REG_HHI_MPEG		0x0174 /* 0x5d offset in data sheet */
+#define MESON8B_REG_MALI		0x01b0 /* 0x6c offset in data sheet */
 #define MESON8B_REG_PLL_FIXED		0x0280
 #define MESON8B_REG_PLL_SYS		0x0300
 #define MESON8B_REG_PLL_VID		0x0320
 
+static DEFINE_SPINLOCK(clk_lock);
+
 static const struct pll_rate_table sys_pll_rate_table[] = {
 	PLL_RATE(312000000, 52, 1, 2),
 	PLL_RATE(336000000, 56, 1, 2),
@@ -102,95 +117,331 @@ static const struct clk_div_table cpu_div_table[] = {
 	{ /* sentinel */ },
 };
 
-PNAME(p_xtal)		= { "xtal" };
-PNAME(p_fclk_div)	= { "fixed_pll" };
-PNAME(p_cpu_clk)	= { "sys_pll" };
-PNAME(p_clk81)		= { "fclk_div3", "fclk_div4", "fclk_div5" };
-PNAME(p_mali)		= { "fclk_div3", "fclk_div4", "fclk_div5",
-			    "fclk_div7", "zero" };
+static struct clk_fixed_rate meson8b_xtal = {
+	.fixed_rate = 24000000,
+	.hw.init = &(struct clk_init_data){
+		.name = "xtal",
+		.num_parents = 0,
+		.ops = &clk_fixed_rate_ops,
+	},
+};
+
+static struct meson_clk_pll meson8b_fixed_pll = {
+	.m = {
+		.reg_off = MESON8B_REG_PLL_FIXED,
+		.shift   = 0,
+		.width   = 9,
+	},
+	.n = {
+		.reg_off = MESON8B_REG_PLL_FIXED,
+		.shift   = 9,
+		.width   = 5,
+	},
+	.od = {
+		.reg_off = MESON8B_REG_PLL_FIXED,
+		.shift   = 16,
+		.width   = 2,
+	},
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "fixed_pll",
+		.ops = &meson_clk_pll_ro_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+		.flags = CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct meson_clk_pll meson8b_vid_pll = {
+	.m = {
+		.reg_off = MESON8B_REG_PLL_VID,
+		.shift   = 0,
+		.width   = 9,
+	},
+	.n = {
+		.reg_off = MESON8B_REG_PLL_VID,
+		.shift   = 9,
+		.width   = 5,
+	},
+	.od = {
+		.reg_off = MESON8B_REG_PLL_VID,
+		.shift   = 16,
+		.width   = 2,
+	},
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "vid_pll",
+		.ops = &meson_clk_pll_ro_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+		.flags = CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct meson_clk_pll meson8b_sys_pll = {
+	.m = {
+		.reg_off = MESON8B_REG_PLL_SYS,
+		.shift   = 0,
+		.width   = 9,
+	},
+	.n = {
+		.reg_off = MESON8B_REG_PLL_SYS,
+		.shift   = 9,
+		.width   = 5,
+	},
+	.od = {
+		.reg_off = MESON8B_REG_PLL_SYS,
+		.shift   = 16,
+		.width   = 2,
+	},
+	.rate_table = sys_pll_rate_table,
+	.rate_count = ARRAY_SIZE(sys_pll_rate_table),
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "sys_pll",
+		.ops = &meson_clk_pll_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+		.flags = CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct clk_fixed_factor meson8b_fclk_div2 = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div2",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor meson8b_fclk_div3 = {
+	.mult = 1,
+	.div = 3,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div3",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor meson8b_fclk_div4 = {
+	.mult = 1,
+	.div = 4,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div4",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor meson8b_fclk_div5 = {
+	.mult = 1,
+	.div = 5,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div5",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor meson8b_fclk_div7 = {
+	.mult = 1,
+	.div = 7,
+	.hw.init = &(struct clk_init_data){
+		.name = "fclk_div7",
+		.ops = &clk_fixed_factor_ops,
+		.parent_names = (const char *[]){ "fixed_pll" },
+		.num_parents = 1,
+	},
+};
+
+/*
+ * FIXME cpu clocks and the legacy composite clocks (e.g. clk81) are both PLL
+ * post-dividers and should be modeled with their respective PLLs via the
+ * forthcoming coordinated clock rates feature
+ */
+static struct meson_clk_cpu meson8b_cpu_clk = {
+	.reg_off = MESON8B_REG_SYS_CPU_CNTL1,
+	.div_table = cpu_div_table,
+	.clk_nb.notifier_call = meson_clk_cpu_notifier_cb,
+	.hw.init = &(struct clk_init_data){
+		.name = "cpu_clk",
+		.ops = &meson_clk_cpu_ops,
+		.parent_names = (const char *[]){ "sys_pll" },
+		.num_parents = 1,
+	},
+};
 
 static u32 mux_table_clk81[]	= { 6, 5, 7 };
-static u32 mux_table_mali[]	= { 6, 5, 7, 4, 0 };
-
-static struct pll_conf pll_confs = {
-	.m		= PARM(0x00, 0,  9),
-	.n		= PARM(0x00, 9,  5),
-	.od		= PARM(0x00, 16, 2),
-};
-
-static struct pll_conf sys_pll_conf = {
-	.m		= PARM(0x00, 0,  9),
-	.n		= PARM(0x00, 9,  5),
-	.od		= PARM(0x00, 16, 2),
-	.rate_table	= sys_pll_rate_table,
-};
-
-static const struct composite_conf clk81_conf __initconst = {
-	.mux_table		= mux_table_clk81,
-	.mux_flags		= CLK_MUX_READ_ONLY,
-	.mux_parm		= PARM(0x00, 12, 3),
-	.div_parm		= PARM(0x00, 0, 7),
-	.gate_parm		= PARM(0x00, 7, 1),
-};
-
-static const struct composite_conf mali_conf __initconst = {
-	.mux_table		= mux_table_mali,
-	.mux_parm		= PARM(0x00, 9, 3),
-	.div_parm		= PARM(0x00, 0, 7),
-	.gate_parm		= PARM(0x00, 8, 1),
-};
-
-static const struct clk_conf meson8b_xtal_conf __initconst =
-	FIXED_RATE_P(MESON8B_REG_CTL0_ADDR, CLKID_XTAL, "xtal", 0,
-			PARM(0x00, 4, 7));
-
-static const struct clk_conf meson8b_clk_confs[] __initconst = {
-	FIXED_RATE(CLKID_ZERO, "zero", 0, 0),
-	PLL(MESON8B_REG_PLL_FIXED, CLKID_PLL_FIXED, "fixed_pll",
-	    p_xtal, 0, &pll_confs),
-	PLL(MESON8B_REG_PLL_VID, CLKID_PLL_VID, "vid_pll",
-	    p_xtal, 0, &pll_confs),
-	PLL(MESON8B_REG_PLL_SYS, CLKID_PLL_SYS, "sys_pll",
-	    p_xtal, 0, &sys_pll_conf),
-	FIXED_FACTOR_DIV(CLKID_FCLK_DIV2, "fclk_div2", p_fclk_div, 0, 2),
-	FIXED_FACTOR_DIV(CLKID_FCLK_DIV3, "fclk_div3", p_fclk_div, 0, 3),
-	FIXED_FACTOR_DIV(CLKID_FCLK_DIV4, "fclk_div4", p_fclk_div, 0, 4),
-	FIXED_FACTOR_DIV(CLKID_FCLK_DIV5, "fclk_div5", p_fclk_div, 0, 5),
-	FIXED_FACTOR_DIV(CLKID_FCLK_DIV7, "fclk_div7", p_fclk_div, 0, 7),
-	CPU(MESON8B_REG_SYS_CPU_CNTL1, CLKID_CPUCLK, "a5_clk", p_cpu_clk,
-	    cpu_div_table),
-	COMPOSITE(MESON8B_REG_HHI_MPEG, CLKID_CLK81, "clk81", p_clk81,
-		  CLK_SET_RATE_NO_REPARENT | CLK_IGNORE_UNUSED, &clk81_conf),
-	COMPOSITE(MESON8B_REG_MALI, CLKID_MALI, "mali", p_mali,
-		  CLK_IGNORE_UNUSED, &mali_conf),
-};
-
-static void __init meson8b_clkc_init(struct device_node *np)
-{
-	void __iomem *clk_base;
 
-	if (!meson_clk_init(np, CLK_NR_CLKS))
-		return;
+struct clk_mux meson8b_mpeg_clk_sel = {
+	.reg = (void *)MESON8B_REG_HHI_MPEG,
+	.mask = 0x7,
+	.shift = 12,
+	.flags = CLK_MUX_READ_ONLY,
+	.table = mux_table_clk81,
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpeg_clk_sel",
+		.ops = &clk_mux_ro_ops,
+		/*
+		 * FIXME bits 14:12 selects from 8 possible parents:
+		 * xtal, 1'b0 (wtf), fclk_div7, mpll_clkout1, mpll_clkout2,
+		 * fclk_div4, fclk_div3, fclk_div5
+		 */
+		.parent_names = (const char *[]){ "fclk_div3", "fclk_div4",
+			"fclk_div5" },
+		.num_parents = 3,
+		.flags = (CLK_SET_RATE_NO_REPARENT | CLK_IGNORE_UNUSED),
+	},
+};
 
-	/* XTAL */
-	clk_base = of_iomap(np, 0);
-	if (!clk_base) {
-		pr_err("%s: Unable to map xtal base\n", __func__);
-		return;
-	}
+struct clk_divider meson8b_mpeg_clk_div = {
+	.reg = (void *)MESON8B_REG_HHI_MPEG,
+	.shift = 0,
+	.width = 7,
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "mpeg_clk_div",
+		.ops = &clk_divider_ops,
+		.parent_names = (const char *[]){ "mpeg_clk_sel" },
+		.num_parents = 1,
+		.flags = (CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED),
+	},
+};
 
-	meson_clk_register_clks(&meson8b_xtal_conf, 1, clk_base);
-	iounmap(clk_base);
+struct clk_gate meson8b_clk81 = {
+	.reg = (void *)MESON8B_REG_HHI_MPEG,
+	.bit_idx = 7,
+	.lock = &clk_lock,
+	.hw.init = &(struct clk_init_data){
+		.name = "clk81",
+		.ops = &clk_gate_ops,
+		.parent_names = (const char *[]){ "mpeg_clk_div" },
+		.num_parents = 1,
+		.flags = (CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED),
+	},
+};
+
+static struct clk_hw_onecell_data meson8b_hw_onecell_data = {
+	.hws = {
+		[CLKID_XTAL] = &meson8b_xtal.hw,
+		[CLKID_PLL_FIXED] = &meson8b_fixed_pll.hw,
+		[CLKID_PLL_VID] = &meson8b_vid_pll.hw,
+		[CLKID_PLL_SYS] = &meson8b_sys_pll.hw,
+		[CLKID_FCLK_DIV2] = &meson8b_fclk_div2.hw,
+		[CLKID_FCLK_DIV3] = &meson8b_fclk_div3.hw,
+		[CLKID_FCLK_DIV4] = &meson8b_fclk_div4.hw,
+		[CLKID_FCLK_DIV5] = &meson8b_fclk_div5.hw,
+		[CLKID_FCLK_DIV7] = &meson8b_fclk_div7.hw,
+		[CLKID_CPUCLK] = &meson8b_cpu_clk.hw,
+		[CLKID_MPEG_SEL] = &meson8b_mpeg_clk_sel.hw,
+		[CLKID_MPEG_DIV] = &meson8b_mpeg_clk_div.hw,
+		[CLKID_CLK81] = &meson8b_clk81.hw,
+	},
+	.num = CLK_NR_CLKS,
+};
+
+static struct meson_clk_pll *const meson8b_clk_plls[] = {
+	&meson8b_fixed_pll,
+	&meson8b_vid_pll,
+	&meson8b_sys_pll,
+};
+
+static int meson8b_clkc_probe(struct platform_device *pdev)
+{
+	void __iomem *clk_base;
+	int ret, clkid, i;
+	struct clk_hw *parent_hw;
+	struct clk *parent_clk;
+	struct device *dev = &pdev->dev;
 
 	/*  Generic clocks and PLLs */
-	clk_base = of_iomap(np, 1);
+	clk_base = of_iomap(dev->of_node, 1);
 	if (!clk_base) {
 		pr_err("%s: Unable to map clk base\n", __func__);
-		return;
+		return -ENXIO;
+	}
+
+	/* Populate base address for PLLs */
+	for (i = 0; i < ARRAY_SIZE(meson8b_clk_plls); i++)
+		meson8b_clk_plls[i]->base = clk_base;
+
+	/* Populate the base address for CPU clk */
+	meson8b_cpu_clk.base = clk_base;
+
+	/* Populate the base address for the MPEG clks */
+	meson8b_mpeg_clk_sel.reg = clk_base + (u32)meson8b_mpeg_clk_sel.reg;
+	meson8b_mpeg_clk_div.reg = clk_base + (u32)meson8b_mpeg_clk_div.reg;
+	meson8b_clk81.reg = clk_base + (u32)meson8b_clk81.reg;
+
+	/*
+	 * register all clks
+	 * CLKID_UNUSED = 0, so skip it and start with CLKID_XTAL = 1
+	 */
+	for (clkid = CLKID_XTAL; clkid < CLK_NR_CLKS; clkid++) {
+		/* array might be sparse */
+		if (!meson8b_hw_onecell_data.hws[clkid])
+			continue;
+
+		/* FIXME convert to devm_clk_register */
+		ret = devm_clk_hw_register(dev, meson8b_hw_onecell_data.hws[clkid]);
+		if (ret)
+			goto iounmap;
 	}
 
-	meson_clk_register_clks(meson8b_clk_confs,
-				ARRAY_SIZE(meson8b_clk_confs),
-				clk_base);
+	/*
+	 * Register CPU clk notifier
+	 *
+	 * FIXME this is wrong for a lot of reasons. First, the muxes should be
+	 * struct clk_hw objects. Second, we shouldn't program the muxes in
+	 * notifier handlers. The tricky programming sequence will be handled
+	 * by the forthcoming coordinated clock rates mechanism once that
+	 * feature is released.
+	 *
+	 * Furthermore, looking up the parent this way is terrible. At some
+	 * point we will stop allocating a default struct clk when registering
+	 * a new clk_hw, and this hack will no longer work. Releasing the ccr
+	 * feature before that time solves the problem :-)
+	 */
+	parent_hw = clk_hw_get_parent(&meson8b_cpu_clk.hw);
+	parent_clk = parent_hw->clk;
+	ret = clk_notifier_register(parent_clk, &meson8b_cpu_clk.clk_nb);
+	if (ret) {
+		pr_err("%s: failed to register clock notifier for cpu_clk\n",
+				__func__);
+		goto iounmap;
+	}
+
+	return of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get,
+			&meson8b_hw_onecell_data);
+
+iounmap:
+	iounmap(clk_base);
+	return ret;
+}
+
+static const struct of_device_id meson8b_clkc_match_table[] = {
+	{ .compatible = "amlogic,meson8b-clkc" },
+	{ }
+};
+
+static struct platform_driver meson8b_driver = {
+	.probe		= meson8b_clkc_probe,
+	.driver		= {
+		.name	= "meson8b-clkc",
+		.of_match_table = meson8b_clkc_match_table,
+	},
+};
+
+static int __init meson8b_clkc_init(void)
+{
+	return platform_driver_register(&meson8b_driver);
 }
-CLK_OF_DECLARE(meson8b_clock, "amlogic,meson8b-clkc", meson8b_clkc_init);
+device_initcall(meson8b_clkc_init);
diff --git a/drivers/clk/nxp/clk-lpc32xx.c b/drivers/clk/nxp/clk-lpc32xx.c
index 481b2646b496..90d740a2fc0d 100644
--- a/drivers/clk/nxp/clk-lpc32xx.c
+++ b/drivers/clk/nxp/clk-lpc32xx.c
@@ -87,7 +87,7 @@ enum {
 
 enum {
 	/* Start from the last defined clock in dt bindings */
-	LPC32XX_CLK_ADC_DIV = LPC32XX_CLK_HCLK_PLL + 1,
+	LPC32XX_CLK_ADC_DIV = LPC32XX_CLK_PERIPH + 1,
 	LPC32XX_CLK_ADC_RTC,
 	LPC32XX_CLK_TEST1,
 	LPC32XX_CLK_TEST2,
@@ -99,7 +99,6 @@ enum {
 	LPC32XX_CLK_HCLK_DIV_PERIPH,
 	LPC32XX_CLK_HCLK_DIV,
 	LPC32XX_CLK_HCLK,
-	LPC32XX_CLK_PERIPH,
 	LPC32XX_CLK_ARM,
 	LPC32XX_CLK_ARM_VFP,
 
diff --git a/drivers/clk/qcom/gcc-msm8660.c b/drivers/clk/qcom/gcc-msm8660.c
index 6dc55864979c..c347a0d44bc8 100644
--- a/drivers/clk/qcom/gcc-msm8660.c
+++ b/drivers/clk/qcom/gcc-msm8660.c
@@ -2290,6 +2290,32 @@ static struct clk_branch sdc5_h_clk = {
 	},
 };
 
+static struct clk_branch ebi2_2x_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 18,
+	.clkr = {
+		.enable_reg = 0x2660,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "ebi2_2x_clk",
+			.ops = &clk_branch_ops,
+		},
+	},
+};
+
+static struct clk_branch ebi2_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 19,
+	.clkr = {
+		.enable_reg = 0x2664,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "ebi2_clk",
+			.ops = &clk_branch_ops,
+		},
+	},
+};
+
 static struct clk_branch adm0_clk = {
 	.halt_reg = 0x2fdc,
 	.halt_check = BRANCH_HALT_VOTED,
@@ -2533,6 +2559,8 @@ static struct clk_regmap *gcc_msm8660_clks[] = {
 	[SDC3_H_CLK] = &sdc3_h_clk.clkr,
 	[SDC4_H_CLK] = &sdc4_h_clk.clkr,
 	[SDC5_H_CLK] = &sdc5_h_clk.clkr,
+	[EBI2_2X_CLK] = &ebi2_2x_clk.clkr,
+	[EBI2_CLK] = &ebi2_clk.clkr,
 	[ADM0_CLK] = &adm0_clk.clkr,
 	[ADM0_PBUS_CLK] = &adm0_pbus_clk.clkr,
 	[ADM1_CLK] = &adm1_clk.clkr,
diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c
index c9b96f318d9c..bbf732bbc3fd 100644
--- a/drivers/clk/qcom/gcc-msm8996.c
+++ b/drivers/clk/qcom/gcc-msm8996.c
@@ -2891,21 +2891,6 @@ static struct clk_branch gcc_smmu_aggre0_ahb_clk = {
 	},
 };
 
-static struct clk_branch gcc_aggre1_pnoc_ahb_clk = {
-	.halt_reg = 0x82014,
-	.clkr = {
-		.enable_reg = 0x82014,
-		.enable_mask = BIT(0),
-		.hw.init = &(struct clk_init_data){
-			.name = "gcc_aggre1_pnoc_ahb_clk",
-			.parent_names = (const char *[]){ "periph_noc_clk_src" },
-			.num_parents = 1,
-			.flags = CLK_SET_RATE_PARENT,
-			.ops = &clk_branch2_ops,
-		},
-	},
-};
-
 static struct clk_branch gcc_aggre2_ufs_axi_clk = {
 	.halt_reg = 0x83014,
 	.clkr = {
@@ -3308,7 +3293,6 @@ static struct clk_regmap *gcc_msm8996_clocks[] = {
 	[GCC_AGGRE0_CNOC_AHB_CLK] = &gcc_aggre0_cnoc_ahb_clk.clkr,
 	[GCC_SMMU_AGGRE0_AXI_CLK] = &gcc_smmu_aggre0_axi_clk.clkr,
 	[GCC_SMMU_AGGRE0_AHB_CLK] = &gcc_smmu_aggre0_ahb_clk.clkr,
-	[GCC_AGGRE1_PNOC_AHB_CLK] = &gcc_aggre1_pnoc_ahb_clk.clkr,
 	[GCC_AGGRE2_UFS_AXI_CLK] = &gcc_aggre2_ufs_axi_clk.clkr,
 	[GCC_AGGRE2_USB3_AXI_CLK] = &gcc_aggre2_usb3_axi_clk.clkr,
 	[GCC_QSPI_AHB_CLK] = &gcc_qspi_ahb_clk.clkr,
diff --git a/drivers/clk/renesas/Kconfig b/drivers/clk/renesas/Kconfig
index 2115ce410cfb..41a12d376799 100644
--- a/drivers/clk/renesas/Kconfig
+++ b/drivers/clk/renesas/Kconfig
@@ -1,6 +1,7 @@
 config CLK_RENESAS_CPG_MSSR
 	bool
 	default y if ARCH_R8A7795
+	default y if ARCH_R8A7796
 
 config CLK_RENESAS_CPG_MSTP
 	bool
@@ -11,6 +12,7 @@ config CLK_RENESAS_CPG_MSTP
 	default y if ARCH_R8A7779
 	default y if ARCH_R8A7790
 	default y if ARCH_R8A7791
+	default y if ARCH_R8A7792
 	default y if ARCH_R8A7793
 	default y if ARCH_R8A7794
 	default y if ARCH_SH73A0
diff --git a/drivers/clk/renesas/Makefile b/drivers/clk/renesas/Makefile
index ead8bb843524..90dd0db7d9c6 100644
--- a/drivers/clk/renesas/Makefile
+++ b/drivers/clk/renesas/Makefile
@@ -6,9 +6,11 @@ obj-$(CONFIG_ARCH_R8A7778)		+= clk-r8a7778.o
 obj-$(CONFIG_ARCH_R8A7779)		+= clk-r8a7779.o
 obj-$(CONFIG_ARCH_R8A7790)		+= clk-rcar-gen2.o clk-div6.o
 obj-$(CONFIG_ARCH_R8A7791)		+= clk-rcar-gen2.o clk-div6.o
+obj-$(CONFIG_ARCH_R8A7792)		+= clk-rcar-gen2.o clk-div6.o
 obj-$(CONFIG_ARCH_R8A7793)		+= clk-rcar-gen2.o clk-div6.o
 obj-$(CONFIG_ARCH_R8A7794)		+= clk-rcar-gen2.o clk-div6.o
-obj-$(CONFIG_ARCH_R8A7795)		+= r8a7795-cpg-mssr.o
+obj-$(CONFIG_ARCH_R8A7795)		+= r8a7795-cpg-mssr.o rcar-gen3-cpg.o
+obj-$(CONFIG_ARCH_R8A7796)		+= r8a7796-cpg-mssr.o rcar-gen3-cpg.o
 obj-$(CONFIG_ARCH_SH73A0)		+= clk-sh73a0.o clk-div6.o
 
 obj-$(CONFIG_CLK_RENESAS_CPG_MSSR)	+= renesas-cpg-mssr.o clk-div6.o
diff --git a/drivers/clk/renesas/r8a7795-cpg-mssr.c b/drivers/clk/renesas/r8a7795-cpg-mssr.c
index ca5519c583d4..d359c92e13a6 100644
--- a/drivers/clk/renesas/r8a7795-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a7795-cpg-mssr.c
@@ -12,22 +12,14 @@
  * the Free Software Foundation; version 2 of the License.
  */
 
-#include <linux/bug.h>
-#include <linux/clk.h>
-#include <linux/clk-provider.h>
 #include <linux/device.h>
-#include <linux/err.h>
 #include <linux/init.h>
-#include <linux/io.h>
 #include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/slab.h>
 
 #include <dt-bindings/clock/r8a7795-cpg-mssr.h>
 
 #include "renesas-cpg-mssr.h"
-
-#define CPG_RCKCR	0x240
+#include "rcar-gen3-cpg.h"
 
 enum clk_ids {
 	/* Core Clock Outputs exported to DT */
@@ -58,20 +50,6 @@ enum clk_ids {
 	MOD_CLK_BASE
 };
 
-enum r8a7795_clk_types {
-	CLK_TYPE_GEN3_MAIN = CLK_TYPE_CUSTOM,
-	CLK_TYPE_GEN3_PLL0,
-	CLK_TYPE_GEN3_PLL1,
-	CLK_TYPE_GEN3_PLL2,
-	CLK_TYPE_GEN3_PLL3,
-	CLK_TYPE_GEN3_PLL4,
-	CLK_TYPE_GEN3_SD,
-	CLK_TYPE_GEN3_R,
-};
-
-#define DEF_GEN3_SD(_name, _id, _parent, _offset)	\
-	DEF_BASE(_name, _id, CLK_TYPE_GEN3_SD, _parent, .offset = _offset)
-
 static const struct cpg_core_clk r8a7795_core_clks[] __initconst = {
 	/* External Clock Inputs */
 	DEF_INPUT("extal",  CLK_EXTAL),
@@ -129,6 +107,9 @@ static const struct cpg_core_clk r8a7795_core_clks[] __initconst = {
 };
 
 static const struct mssr_mod_clk r8a7795_mod_clks[] __initconst = {
+	DEF_MOD("fdp1-2",		 117,	R8A7795_CLK_S2D1),
+	DEF_MOD("fdp1-1",		 118,	R8A7795_CLK_S2D1),
+	DEF_MOD("fdp1-0",		 119,	R8A7795_CLK_S2D1),
 	DEF_MOD("scif5",		 202,	R8A7795_CLK_S3D4),
 	DEF_MOD("scif4",		 203,	R8A7795_CLK_S3D4),
 	DEF_MOD("scif3",		 204,	R8A7795_CLK_S3D4),
@@ -157,11 +138,20 @@ static const struct mssr_mod_clk r8a7795_mod_clks[] __initconst = {
 	DEF_MOD("intc-ap",		 408,	R8A7795_CLK_S3D1),
 	DEF_MOD("audmac0",		 502,	R8A7795_CLK_S3D4),
 	DEF_MOD("audmac1",		 501,	R8A7795_CLK_S3D4),
+	DEF_MOD("drif7",		 508,	R8A7795_CLK_S3D2),
+	DEF_MOD("drif6",		 509,	R8A7795_CLK_S3D2),
+	DEF_MOD("drif5",		 510,	R8A7795_CLK_S3D2),
+	DEF_MOD("drif4",		 511,	R8A7795_CLK_S3D2),
+	DEF_MOD("drif3",		 512,	R8A7795_CLK_S3D2),
+	DEF_MOD("drif2",		 513,	R8A7795_CLK_S3D2),
+	DEF_MOD("drif1",		 514,	R8A7795_CLK_S3D2),
+	DEF_MOD("drif0",		 515,	R8A7795_CLK_S3D2),
 	DEF_MOD("hscif4",		 516,	R8A7795_CLK_S3D1),
 	DEF_MOD("hscif3",		 517,	R8A7795_CLK_S3D1),
 	DEF_MOD("hscif2",		 518,	R8A7795_CLK_S3D1),
 	DEF_MOD("hscif1",		 519,	R8A7795_CLK_S3D1),
 	DEF_MOD("hscif0",		 520,	R8A7795_CLK_S3D1),
+	DEF_MOD("thermal",		 522,	R8A7795_CLK_CP),
 	DEF_MOD("pwm",			 523,	R8A7795_CLK_S3D4),
 	DEF_MOD("fcpvd3",		 600,	R8A7795_CLK_S2D1),
 	DEF_MOD("fcpvd2",		 601,	R8A7795_CLK_S2D1),
@@ -199,7 +189,7 @@ static const struct mssr_mod_clk r8a7795_mod_clks[] __initconst = {
 	DEF_MOD("du2",			 722,	R8A7795_CLK_S2D1),
 	DEF_MOD("du1",			 723,	R8A7795_CLK_S2D1),
 	DEF_MOD("du0",			 724,	R8A7795_CLK_S2D1),
-	DEF_MOD("lvds",			 727,	R8A7795_CLK_S2D1),
+	DEF_MOD("lvds",			 727,	R8A7795_CLK_S0D4),
 	DEF_MOD("hdmi1",		 728,	R8A7795_CLK_HDMI),
 	DEF_MOD("hdmi0",		 729,	R8A7795_CLK_HDMI),
 	DEF_MOD("vin7",			 804,	R8A7795_CLK_S2D1),
@@ -262,225 +252,6 @@ static const unsigned int r8a7795_crit_mod_clks[] __initconst = {
 	MOD_CLK_ID(408),	/* INTC-AP (GIC) */
 };
 
-/* -----------------------------------------------------------------------------
- * SDn Clock
- *
- */
-#define CPG_SD_STP_HCK		BIT(9)
-#define CPG_SD_STP_CK		BIT(8)
-
-#define CPG_SD_STP_MASK		(CPG_SD_STP_HCK | CPG_SD_STP_CK)
-#define CPG_SD_FC_MASK		(0x7 << 2 | 0x3 << 0)
-
-#define CPG_SD_DIV_TABLE_DATA(stp_hck, stp_ck, sd_srcfc, sd_fc, sd_div) \
-{ \
-	.val = ((stp_hck) ? CPG_SD_STP_HCK : 0) | \
-	       ((stp_ck) ? CPG_SD_STP_CK : 0) | \
-	       ((sd_srcfc) << 2) | \
-	       ((sd_fc) << 0), \
-	.div = (sd_div), \
-}
-
-struct sd_div_table {
-	u32 val;
-	unsigned int div;
-};
-
-struct sd_clock {
-	struct clk_hw hw;
-	void __iomem *reg;
-	const struct sd_div_table *div_table;
-	unsigned int div_num;
-	unsigned int div_min;
-	unsigned int div_max;
-};
-
-/* SDn divider
- *                     sd_srcfc   sd_fc   div
- * stp_hck   stp_ck    (div)      (div)     = sd_srcfc x sd_fc
- *-------------------------------------------------------------------
- *  0         0         0 (1)      1 (4)      4
- *  0         0         1 (2)      1 (4)      8
- *  1         0         2 (4)      1 (4)     16
- *  1         0         3 (8)      1 (4)     32
- *  1         0         4 (16)     1 (4)     64
- *  0         0         0 (1)      0 (2)      2
- *  0         0         1 (2)      0 (2)      4
- *  1         0         2 (4)      0 (2)      8
- *  1         0         3 (8)      0 (2)     16
- *  1         0         4 (16)     0 (2)     32
- */
-static const struct sd_div_table cpg_sd_div_table[] = {
-/*	CPG_SD_DIV_TABLE_DATA(stp_hck,  stp_ck,   sd_srcfc,   sd_fc,  sd_div) */
-	CPG_SD_DIV_TABLE_DATA(0,        0,        0,          1,        4),
-	CPG_SD_DIV_TABLE_DATA(0,        0,        1,          1,        8),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        2,          1,       16),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        3,          1,       32),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        4,          1,       64),
-	CPG_SD_DIV_TABLE_DATA(0,        0,        0,          0,        2),
-	CPG_SD_DIV_TABLE_DATA(0,        0,        1,          0,        4),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        2,          0,        8),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        3,          0,       16),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        4,          0,       32),
-};
-
-#define to_sd_clock(_hw) container_of(_hw, struct sd_clock, hw)
-
-static int cpg_sd_clock_enable(struct clk_hw *hw)
-{
-	struct sd_clock *clock = to_sd_clock(hw);
-	u32 val, sd_fc;
-	unsigned int i;
-
-	val = clk_readl(clock->reg);
-
-	sd_fc = val & CPG_SD_FC_MASK;
-	for (i = 0; i < clock->div_num; i++)
-		if (sd_fc == (clock->div_table[i].val & CPG_SD_FC_MASK))
-			break;
-
-	if (i >= clock->div_num)
-		return -EINVAL;
-
-	val &= ~(CPG_SD_STP_MASK);
-	val |= clock->div_table[i].val & CPG_SD_STP_MASK;
-
-	clk_writel(val, clock->reg);
-
-	return 0;
-}
-
-static void cpg_sd_clock_disable(struct clk_hw *hw)
-{
-	struct sd_clock *clock = to_sd_clock(hw);
-
-	clk_writel(clk_readl(clock->reg) | CPG_SD_STP_MASK, clock->reg);
-}
-
-static int cpg_sd_clock_is_enabled(struct clk_hw *hw)
-{
-	struct sd_clock *clock = to_sd_clock(hw);
-
-	return !(clk_readl(clock->reg) & CPG_SD_STP_MASK);
-}
-
-static unsigned long cpg_sd_clock_recalc_rate(struct clk_hw *hw,
-						unsigned long parent_rate)
-{
-	struct sd_clock *clock = to_sd_clock(hw);
-	unsigned long rate = parent_rate;
-	u32 val, sd_fc;
-	unsigned int i;
-
-	val = clk_readl(clock->reg);
-
-	sd_fc = val & CPG_SD_FC_MASK;
-	for (i = 0; i < clock->div_num; i++)
-		if (sd_fc == (clock->div_table[i].val & CPG_SD_FC_MASK))
-			break;
-
-	if (i >= clock->div_num)
-		return -EINVAL;
-
-	return DIV_ROUND_CLOSEST(rate, clock->div_table[i].div);
-}
-
-static unsigned int cpg_sd_clock_calc_div(struct sd_clock *clock,
-					  unsigned long rate,
-					  unsigned long parent_rate)
-{
-	unsigned int div;
-
-	if (!rate)
-		rate = 1;
-
-	div = DIV_ROUND_CLOSEST(parent_rate, rate);
-
-	return clamp_t(unsigned int, div, clock->div_min, clock->div_max);
-}
-
-static long cpg_sd_clock_round_rate(struct clk_hw *hw, unsigned long rate,
-				      unsigned long *parent_rate)
-{
-	struct sd_clock *clock = to_sd_clock(hw);
-	unsigned int div = cpg_sd_clock_calc_div(clock, rate, *parent_rate);
-
-	return DIV_ROUND_CLOSEST(*parent_rate, div);
-}
-
-static int cpg_sd_clock_set_rate(struct clk_hw *hw, unsigned long rate,
-				   unsigned long parent_rate)
-{
-	struct sd_clock *clock = to_sd_clock(hw);
-	unsigned int div = cpg_sd_clock_calc_div(clock, rate, parent_rate);
-	u32 val;
-	unsigned int i;
-
-	for (i = 0; i < clock->div_num; i++)
-		if (div == clock->div_table[i].div)
-			break;
-
-	if (i >= clock->div_num)
-		return -EINVAL;
-
-	val = clk_readl(clock->reg);
-	val &= ~(CPG_SD_STP_MASK | CPG_SD_FC_MASK);
-	val |= clock->div_table[i].val & (CPG_SD_STP_MASK | CPG_SD_FC_MASK);
-	clk_writel(val, clock->reg);
-
-	return 0;
-}
-
-static const struct clk_ops cpg_sd_clock_ops = {
-	.enable = cpg_sd_clock_enable,
-	.disable = cpg_sd_clock_disable,
-	.is_enabled = cpg_sd_clock_is_enabled,
-	.recalc_rate = cpg_sd_clock_recalc_rate,
-	.round_rate = cpg_sd_clock_round_rate,
-	.set_rate = cpg_sd_clock_set_rate,
-};
-
-static struct clk * __init cpg_sd_clk_register(const struct cpg_core_clk *core,
-					       void __iomem *base,
-					       const char *parent_name)
-{
-	struct clk_init_data init;
-	struct sd_clock *clock;
-	struct clk *clk;
-	unsigned int i;
-
-	clock = kzalloc(sizeof(*clock), GFP_KERNEL);
-	if (!clock)
-		return ERR_PTR(-ENOMEM);
-
-	init.name = core->name;
-	init.ops = &cpg_sd_clock_ops;
-	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
-	init.parent_names = &parent_name;
-	init.num_parents = 1;
-
-	clock->reg = base + core->offset;
-	clock->hw.init = &init;
-	clock->div_table = cpg_sd_div_table;
-	clock->div_num = ARRAY_SIZE(cpg_sd_div_table);
-
-	clock->div_max = clock->div_table[0].div;
-	clock->div_min = clock->div_max;
-	for (i = 1; i < clock->div_num; i++) {
-		clock->div_max = max(clock->div_max, clock->div_table[i].div);
-		clock->div_min = min(clock->div_min, clock->div_table[i].div);
-	}
-
-	clk = clk_register(NULL, &clock->hw);
-	if (IS_ERR(clk))
-		kfree(clock);
-
-	return clk;
-}
-
-#define CPG_PLL0CR	0x00d8
-#define CPG_PLL2CR	0x002c
-#define CPG_PLL4CR	0x01f4
 
 /*
  * CPG Clock Data
@@ -512,13 +283,7 @@ static struct clk * __init cpg_sd_clk_register(const struct cpg_core_clk *core,
 					 (((md) & BIT(19)) >> 18) | \
 					 (((md) & BIT(17)) >> 17))
 
-struct cpg_pll_config {
-	unsigned int extal_div;
-	unsigned int pll1_mult;
-	unsigned int pll3_mult;
-};
-
-static const struct cpg_pll_config cpg_pll_configs[16] __initconst = {
+static const struct rcar_gen3_cpg_pll_config cpg_pll_configs[16] __initconst = {
 	/* EXTAL div	PLL1 mult	PLL3 mult */
 	{ 1,		192,		192,	},
 	{ 1,		192,		128,	},
@@ -538,112 +303,9 @@ static const struct cpg_pll_config cpg_pll_configs[16] __initconst = {
 	{ 2,		192,		192,	},
 };
 
-static const struct cpg_pll_config *cpg_pll_config __initdata;
-
-static
-struct clk * __init r8a7795_cpg_clk_register(struct device *dev,
-					     const struct cpg_core_clk *core,
-					     const struct cpg_mssr_info *info,
-					     struct clk **clks,
-					     void __iomem *base)
-{
-	const struct clk *parent;
-	unsigned int mult = 1;
-	unsigned int div = 1;
-	u32 value;
-
-	parent = clks[core->parent];
-	if (IS_ERR(parent))
-		return ERR_CAST(parent);
-
-	switch (core->type) {
-	case CLK_TYPE_GEN3_MAIN:
-		div = cpg_pll_config->extal_div;
-		break;
-
-	case CLK_TYPE_GEN3_PLL0:
-		/*
-		 * PLL0 is a configurable multiplier clock. Register it as a
-		 * fixed factor clock for now as there's no generic multiplier
-		 * clock implementation and we currently have no need to change
-		 * the multiplier value.
-		 */
-		value = readl(base + CPG_PLL0CR);
-		mult = (((value >> 24) & 0x7f) + 1) * 2;
-		break;
-
-	case CLK_TYPE_GEN3_PLL1:
-		mult = cpg_pll_config->pll1_mult;
-		break;
-
-	case CLK_TYPE_GEN3_PLL2:
-		/*
-		 * PLL2 is a configurable multiplier clock. Register it as a
-		 * fixed factor clock for now as there's no generic multiplier
-		 * clock implementation and we currently have no need to change
-		 * the multiplier value.
-		 */
-		value = readl(base + CPG_PLL2CR);
-		mult = (((value >> 24) & 0x7f) + 1) * 2;
-		break;
-
-	case CLK_TYPE_GEN3_PLL3:
-		mult = cpg_pll_config->pll3_mult;
-		break;
-
-	case CLK_TYPE_GEN3_PLL4:
-		/*
-		 * PLL4 is a configurable multiplier clock. Register it as a
-		 * fixed factor clock for now as there's no generic multiplier
-		 * clock implementation and we currently have no need to change
-		 * the multiplier value.
-		 */
-		value = readl(base + CPG_PLL4CR);
-		mult = (((value >> 24) & 0x7f) + 1) * 2;
-		break;
-
-	case CLK_TYPE_GEN3_SD:
-		return cpg_sd_clk_register(core, base, __clk_get_name(parent));
-
-	case CLK_TYPE_GEN3_R:
-		/* RINT is default. Only if EXTALR is populated, we switch to it */
-		value = readl(base + CPG_RCKCR) & 0x3f;
-
-		if (clk_get_rate(clks[CLK_EXTALR])) {
-			parent = clks[CLK_EXTALR];
-			value |= BIT(15);
-		}
-
-		writel(value, base + CPG_RCKCR);
-		break;
-
-	default:
-		return ERR_PTR(-EINVAL);
-	}
-
-	return clk_register_fixed_factor(NULL, core->name,
-					 __clk_get_name(parent), 0, mult, div);
-}
-
-/*
- * Reset register definitions.
- */
-#define MODEMR	0xe6160060
-
-static u32 rcar_gen3_read_mode_pins(void)
-{
-	void __iomem *modemr = ioremap_nocache(MODEMR, 4);
-	u32 mode;
-
-	BUG_ON(!modemr);
-	mode = ioread32(modemr);
-	iounmap(modemr);
-
-	return mode;
-}
-
 static int __init r8a7795_cpg_mssr_init(struct device *dev)
 {
+	const struct rcar_gen3_cpg_pll_config *cpg_pll_config;
 	u32 cpg_mode = rcar_gen3_read_mode_pins();
 
 	cpg_pll_config = &cpg_pll_configs[CPG_PLL_CONFIG_INDEX(cpg_mode)];
@@ -652,7 +314,7 @@ static int __init r8a7795_cpg_mssr_init(struct device *dev)
 		return -EINVAL;
 	}
 
-	return 0;
+	return rcar_gen3_cpg_init(cpg_pll_config, CLK_EXTALR);
 }
 
 const struct cpg_mssr_info r8a7795_cpg_mssr_info __initconst = {
@@ -673,5 +335,5 @@ const struct cpg_mssr_info r8a7795_cpg_mssr_info __initconst = {
 
 	/* Callbacks */
 	.init = r8a7795_cpg_mssr_init,
-	.cpg_clk_register = r8a7795_cpg_clk_register,
+	.cpg_clk_register = rcar_gen3_cpg_clk_register,
 };
diff --git a/drivers/clk/renesas/r8a7796-cpg-mssr.c b/drivers/clk/renesas/r8a7796-cpg-mssr.c
new file mode 100644
index 000000000000..c84b549c14d2
--- /dev/null
+++ b/drivers/clk/renesas/r8a7796-cpg-mssr.c
@@ -0,0 +1,192 @@
+/*
+ * r8a7796 Clock Pulse Generator / Module Standby and Software Reset
+ *
+ * Copyright (C) 2016 Glider bvba
+ *
+ * Based on r8a7795-cpg-mssr.c
+ *
+ * Copyright (C) 2015 Glider bvba
+ * Copyright (C) 2015 Renesas Electronics Corp.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+
+#include <dt-bindings/clock/r8a7796-cpg-mssr.h>
+
+#include "renesas-cpg-mssr.h"
+#include "rcar-gen3-cpg.h"
+
+enum clk_ids {
+	/* Core Clock Outputs exported to DT */
+	LAST_DT_CORE_CLK = R8A7796_CLK_OSC,
+
+	/* External Input Clocks */
+	CLK_EXTAL,
+	CLK_EXTALR,
+
+	/* Internal Core Clocks */
+	CLK_MAIN,
+	CLK_PLL0,
+	CLK_PLL1,
+	CLK_PLL2,
+	CLK_PLL3,
+	CLK_PLL4,
+	CLK_PLL1_DIV2,
+	CLK_PLL1_DIV4,
+	CLK_S0,
+	CLK_S1,
+	CLK_S2,
+	CLK_S3,
+	CLK_SDSRC,
+	CLK_SSPSRC,
+
+	/* Module Clocks */
+	MOD_CLK_BASE
+};
+
+static const struct cpg_core_clk r8a7796_core_clks[] __initconst = {
+	/* External Clock Inputs */
+	DEF_INPUT("extal",  CLK_EXTAL),
+	DEF_INPUT("extalr", CLK_EXTALR),
+
+	/* Internal Core Clocks */
+	DEF_BASE(".main",       CLK_MAIN, CLK_TYPE_GEN3_MAIN, CLK_EXTAL),
+	DEF_BASE(".pll0",       CLK_PLL0, CLK_TYPE_GEN3_PLL0, CLK_MAIN),
+	DEF_BASE(".pll1",       CLK_PLL1, CLK_TYPE_GEN3_PLL1, CLK_MAIN),
+	DEF_BASE(".pll2",       CLK_PLL2, CLK_TYPE_GEN3_PLL2, CLK_MAIN),
+	DEF_BASE(".pll3",       CLK_PLL3, CLK_TYPE_GEN3_PLL3, CLK_MAIN),
+	DEF_BASE(".pll4",       CLK_PLL4, CLK_TYPE_GEN3_PLL4, CLK_MAIN),
+
+	DEF_FIXED(".pll1_div2", CLK_PLL1_DIV2,     CLK_PLL1,       2, 1),
+	DEF_FIXED(".pll1_div4", CLK_PLL1_DIV4,     CLK_PLL1_DIV2,  2, 1),
+	DEF_FIXED(".s0",        CLK_S0,            CLK_PLL1_DIV2,  2, 1),
+	DEF_FIXED(".s1",        CLK_S1,            CLK_PLL1_DIV2,  3, 1),
+	DEF_FIXED(".s2",        CLK_S2,            CLK_PLL1_DIV2,  4, 1),
+	DEF_FIXED(".s3",        CLK_S3,            CLK_PLL1_DIV2,  6, 1),
+
+	/* Core Clock Outputs */
+	DEF_FIXED("ztr",        R8A7796_CLK_ZTR,   CLK_PLL1_DIV2,  6, 1),
+	DEF_FIXED("ztrd2",      R8A7796_CLK_ZTRD2, CLK_PLL1_DIV2, 12, 1),
+	DEF_FIXED("zt",         R8A7796_CLK_ZT,    CLK_PLL1_DIV2,  4, 1),
+	DEF_FIXED("zx",         R8A7796_CLK_ZX,    CLK_PLL1_DIV2,  2, 1),
+	DEF_FIXED("s0d1",       R8A7796_CLK_S0D1,  CLK_S0,         1, 1),
+	DEF_FIXED("s0d2",       R8A7796_CLK_S0D2,  CLK_S0,         2, 1),
+	DEF_FIXED("s0d3",       R8A7796_CLK_S0D3,  CLK_S0,         3, 1),
+	DEF_FIXED("s0d4",       R8A7796_CLK_S0D4,  CLK_S0,         4, 1),
+	DEF_FIXED("s0d6",       R8A7796_CLK_S0D6,  CLK_S0,         6, 1),
+	DEF_FIXED("s0d8",       R8A7796_CLK_S0D8,  CLK_S0,         8, 1),
+	DEF_FIXED("s0d12",      R8A7796_CLK_S0D12, CLK_S0,        12, 1),
+	DEF_FIXED("s1d1",       R8A7796_CLK_S1D1,  CLK_S1,         1, 1),
+	DEF_FIXED("s1d2",       R8A7796_CLK_S1D2,  CLK_S1,         2, 1),
+	DEF_FIXED("s1d4",       R8A7796_CLK_S1D4,  CLK_S1,         4, 1),
+	DEF_FIXED("s2d1",       R8A7796_CLK_S2D1,  CLK_S2,         1, 1),
+	DEF_FIXED("s2d2",       R8A7796_CLK_S2D2,  CLK_S2,         2, 1),
+	DEF_FIXED("s2d4",       R8A7796_CLK_S2D4,  CLK_S2,         4, 1),
+	DEF_FIXED("s3d1",       R8A7796_CLK_S3D1,  CLK_S3,         1, 1),
+	DEF_FIXED("s3d2",       R8A7796_CLK_S3D2,  CLK_S3,         2, 1),
+	DEF_FIXED("s3d4",       R8A7796_CLK_S3D4,  CLK_S3,         4, 1),
+
+	DEF_FIXED("cl",         R8A7796_CLK_CL,    CLK_PLL1_DIV2, 48, 1),
+	DEF_FIXED("cp",         R8A7796_CLK_CP,    CLK_EXTAL,      2, 1),
+};
+
+static const struct mssr_mod_clk r8a7796_mod_clks[] __initconst = {
+	DEF_MOD("scif2",		 310,	R8A7796_CLK_S3D4),
+	DEF_MOD("intc-ap",		 408,	R8A7796_CLK_S3D1),
+};
+
+static const unsigned int r8a7796_crit_mod_clks[] __initconst = {
+	MOD_CLK_ID(408),	/* INTC-AP (GIC) */
+};
+
+
+/*
+ * CPG Clock Data
+ */
+
+/*
+ *   MD		EXTAL		PLL0	PLL1	PLL2	PLL3	PLL4
+ * 14 13 19 17	(MHz)
+ *-------------------------------------------------------------------
+ * 0  0  0  0	16.66 x 1	x180	x192	x144	x192	x144
+ * 0  0  0  1	16.66 x 1	x180	x192	x144	x128	x144
+ * 0  0  1  0	Prohibited setting
+ * 0  0  1  1	16.66 x 1	x180	x192	x144	x192	x144
+ * 0  1  0  0	20    x 1	x150	x160	x120	x160	x120
+ * 0  1  0  1	20    x 1	x150	x160	x120	x106	x120
+ * 0  1  1  0	Prohibited setting
+ * 0  1  1  1	20    x 1	x150	x160	x120	x160	x120
+ * 1  0  0  0	25    x 1	x120	x128	x96	x128	x96
+ * 1  0  0  1	25    x 1	x120	x128	x96	x84	x96
+ * 1  0  1  0	Prohibited setting
+ * 1  0  1  1	25    x 1	x120	x128	x96	x128	x96
+ * 1  1  0  0	33.33 / 2	x180	x192	x144	x192	x144
+ * 1  1  0  1	33.33 / 2	x180	x192	x144	x128	x144
+ * 1  1  1  0	Prohibited setting
+ * 1  1  1  1	33.33 / 2	x180	x192	x144	x192	x144
+ */
+#define CPG_PLL_CONFIG_INDEX(md)	((((md) & BIT(14)) >> 11) | \
+					 (((md) & BIT(13)) >> 11) | \
+					 (((md) & BIT(19)) >> 18) | \
+					 (((md) & BIT(17)) >> 17))
+
+static const struct rcar_gen3_cpg_pll_config cpg_pll_configs[16] __initconst = {
+	/* EXTAL div	PLL1 mult	PLL3 mult */
+	{ 1,		192,		192,	},
+	{ 1,		192,		128,	},
+	{ 0, /* Prohibited setting */		},
+	{ 1,		192,		192,	},
+	{ 1,		160,		160,	},
+	{ 1,		160,		106,	},
+	{ 0, /* Prohibited setting */		},
+	{ 1,		160,		160,	},
+	{ 1,		128,		128,	},
+	{ 1,		128,		84,	},
+	{ 0, /* Prohibited setting */		},
+	{ 1,		128,		128,	},
+	{ 2,		192,		192,	},
+	{ 2,		192,		128,	},
+	{ 0, /* Prohibited setting */		},
+	{ 2,		192,		192,	},
+};
+
+static int __init r8a7796_cpg_mssr_init(struct device *dev)
+{
+	const struct rcar_gen3_cpg_pll_config *cpg_pll_config;
+	u32 cpg_mode = rcar_gen3_read_mode_pins();
+
+	cpg_pll_config = &cpg_pll_configs[CPG_PLL_CONFIG_INDEX(cpg_mode)];
+	if (!cpg_pll_config->extal_div) {
+		dev_err(dev, "Prohibited setting (cpg_mode=0x%x)\n", cpg_mode);
+		return -EINVAL;
+	}
+
+	return rcar_gen3_cpg_init(cpg_pll_config, CLK_EXTALR);
+}
+
+const struct cpg_mssr_info r8a7796_cpg_mssr_info __initconst = {
+	/* Core Clocks */
+	.core_clks = r8a7796_core_clks,
+	.num_core_clks = ARRAY_SIZE(r8a7796_core_clks),
+	.last_dt_core_clk = LAST_DT_CORE_CLK,
+	.num_total_core_clks = MOD_CLK_BASE,
+
+	/* Module Clocks */
+	.mod_clks = r8a7796_mod_clks,
+	.num_mod_clks = ARRAY_SIZE(r8a7796_mod_clks),
+	.num_hw_mod_clks = 12 * 32,
+
+	/* Critical Module Clocks */
+	.crit_mod_clks = r8a7796_crit_mod_clks,
+	.num_crit_mod_clks = ARRAY_SIZE(r8a7796_crit_mod_clks),
+
+	/* Callbacks */
+	.init = r8a7796_cpg_mssr_init,
+	.cpg_clk_register = rcar_gen3_cpg_clk_register,
+};
diff --git a/drivers/clk/renesas/rcar-gen3-cpg.c b/drivers/clk/renesas/rcar-gen3-cpg.c
new file mode 100644
index 000000000000..bb4f2f9a8c2f
--- /dev/null
+++ b/drivers/clk/renesas/rcar-gen3-cpg.c
@@ -0,0 +1,359 @@
+/*
+ * R-Car Gen3 Clock Pulse Generator
+ *
+ * Copyright (C) 2015-2016 Glider bvba
+ *
+ * Based on clk-rcar-gen3.c
+ *
+ * Copyright (C) 2015 Renesas Electronics Corp.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/bug.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+
+#include "renesas-cpg-mssr.h"
+#include "rcar-gen3-cpg.h"
+
+#define CPG_PLL0CR		0x00d8
+#define CPG_PLL2CR		0x002c
+#define CPG_PLL4CR		0x01f4
+
+
+/*
+ * SDn Clock
+ */
+#define CPG_SD_STP_HCK		BIT(9)
+#define CPG_SD_STP_CK		BIT(8)
+
+#define CPG_SD_STP_MASK		(CPG_SD_STP_HCK | CPG_SD_STP_CK)
+#define CPG_SD_FC_MASK		(0x7 << 2 | 0x3 << 0)
+
+#define CPG_SD_DIV_TABLE_DATA(stp_hck, stp_ck, sd_srcfc, sd_fc, sd_div) \
+{ \
+	.val = ((stp_hck) ? CPG_SD_STP_HCK : 0) | \
+	       ((stp_ck) ? CPG_SD_STP_CK : 0) | \
+	       ((sd_srcfc) << 2) | \
+	       ((sd_fc) << 0), \
+	.div = (sd_div), \
+}
+
+struct sd_div_table {
+	u32 val;
+	unsigned int div;
+};
+
+struct sd_clock {
+	struct clk_hw hw;
+	void __iomem *reg;
+	const struct sd_div_table *div_table;
+	unsigned int div_num;
+	unsigned int div_min;
+	unsigned int div_max;
+};
+
+/* SDn divider
+ *                     sd_srcfc   sd_fc   div
+ * stp_hck   stp_ck    (div)      (div)     = sd_srcfc x sd_fc
+ *-------------------------------------------------------------------
+ *  0         0         0 (1)      1 (4)      4
+ *  0         0         1 (2)      1 (4)      8
+ *  1         0         2 (4)      1 (4)     16
+ *  1         0         3 (8)      1 (4)     32
+ *  1         0         4 (16)     1 (4)     64
+ *  0         0         0 (1)      0 (2)      2
+ *  0         0         1 (2)      0 (2)      4
+ *  1         0         2 (4)      0 (2)      8
+ *  1         0         3 (8)      0 (2)     16
+ *  1         0         4 (16)     0 (2)     32
+ */
+static const struct sd_div_table cpg_sd_div_table[] = {
+/*	CPG_SD_DIV_TABLE_DATA(stp_hck,  stp_ck,   sd_srcfc,   sd_fc,  sd_div) */
+	CPG_SD_DIV_TABLE_DATA(0,        0,        0,          1,        4),
+	CPG_SD_DIV_TABLE_DATA(0,        0,        1,          1,        8),
+	CPG_SD_DIV_TABLE_DATA(1,        0,        2,          1,       16),
+	CPG_SD_DIV_TABLE_DATA(1,        0,        3,          1,       32),
+	CPG_SD_DIV_TABLE_DATA(1,        0,        4,          1,       64),
+	CPG_SD_DIV_TABLE_DATA(0,        0,        0,          0,        2),
+	CPG_SD_DIV_TABLE_DATA(0,        0,        1,          0,        4),
+	CPG_SD_DIV_TABLE_DATA(1,        0,        2,          0,        8),
+	CPG_SD_DIV_TABLE_DATA(1,        0,        3,          0,       16),
+	CPG_SD_DIV_TABLE_DATA(1,        0,        4,          0,       32),
+};
+
+#define to_sd_clock(_hw) container_of(_hw, struct sd_clock, hw)
+
+static int cpg_sd_clock_enable(struct clk_hw *hw)
+{
+	struct sd_clock *clock = to_sd_clock(hw);
+	u32 val, sd_fc;
+	unsigned int i;
+
+	val = clk_readl(clock->reg);
+
+	sd_fc = val & CPG_SD_FC_MASK;
+	for (i = 0; i < clock->div_num; i++)
+		if (sd_fc == (clock->div_table[i].val & CPG_SD_FC_MASK))
+			break;
+
+	if (i >= clock->div_num)
+		return -EINVAL;
+
+	val &= ~(CPG_SD_STP_MASK);
+	val |= clock->div_table[i].val & CPG_SD_STP_MASK;
+
+	clk_writel(val, clock->reg);
+
+	return 0;
+}
+
+static void cpg_sd_clock_disable(struct clk_hw *hw)
+{
+	struct sd_clock *clock = to_sd_clock(hw);
+
+	clk_writel(clk_readl(clock->reg) | CPG_SD_STP_MASK, clock->reg);
+}
+
+static int cpg_sd_clock_is_enabled(struct clk_hw *hw)
+{
+	struct sd_clock *clock = to_sd_clock(hw);
+
+	return !(clk_readl(clock->reg) & CPG_SD_STP_MASK);
+}
+
+static unsigned long cpg_sd_clock_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
+{
+	struct sd_clock *clock = to_sd_clock(hw);
+	unsigned long rate = parent_rate;
+	u32 val, sd_fc;
+	unsigned int i;
+
+	val = clk_readl(clock->reg);
+
+	sd_fc = val & CPG_SD_FC_MASK;
+	for (i = 0; i < clock->div_num; i++)
+		if (sd_fc == (clock->div_table[i].val & CPG_SD_FC_MASK))
+			break;
+
+	if (i >= clock->div_num)
+		return -EINVAL;
+
+	return DIV_ROUND_CLOSEST(rate, clock->div_table[i].div);
+}
+
+static unsigned int cpg_sd_clock_calc_div(struct sd_clock *clock,
+					  unsigned long rate,
+					  unsigned long parent_rate)
+{
+	unsigned int div;
+
+	if (!rate)
+		rate = 1;
+
+	div = DIV_ROUND_CLOSEST(parent_rate, rate);
+
+	return clamp_t(unsigned int, div, clock->div_min, clock->div_max);
+}
+
+static long cpg_sd_clock_round_rate(struct clk_hw *hw, unsigned long rate,
+				      unsigned long *parent_rate)
+{
+	struct sd_clock *clock = to_sd_clock(hw);
+	unsigned int div = cpg_sd_clock_calc_div(clock, rate, *parent_rate);
+
+	return DIV_ROUND_CLOSEST(*parent_rate, div);
+}
+
+static int cpg_sd_clock_set_rate(struct clk_hw *hw, unsigned long rate,
+				   unsigned long parent_rate)
+{
+	struct sd_clock *clock = to_sd_clock(hw);
+	unsigned int div = cpg_sd_clock_calc_div(clock, rate, parent_rate);
+	u32 val;
+	unsigned int i;
+
+	for (i = 0; i < clock->div_num; i++)
+		if (div == clock->div_table[i].div)
+			break;
+
+	if (i >= clock->div_num)
+		return -EINVAL;
+
+	val = clk_readl(clock->reg);
+	val &= ~(CPG_SD_STP_MASK | CPG_SD_FC_MASK);
+	val |= clock->div_table[i].val & (CPG_SD_STP_MASK | CPG_SD_FC_MASK);
+	clk_writel(val, clock->reg);
+
+	return 0;
+}
+
+static const struct clk_ops cpg_sd_clock_ops = {
+	.enable = cpg_sd_clock_enable,
+	.disable = cpg_sd_clock_disable,
+	.is_enabled = cpg_sd_clock_is_enabled,
+	.recalc_rate = cpg_sd_clock_recalc_rate,
+	.round_rate = cpg_sd_clock_round_rate,
+	.set_rate = cpg_sd_clock_set_rate,
+};
+
+static struct clk * __init cpg_sd_clk_register(const struct cpg_core_clk *core,
+					       void __iomem *base,
+					       const char *parent_name)
+{
+	struct clk_init_data init;
+	struct sd_clock *clock;
+	struct clk *clk;
+	unsigned int i;
+
+	clock = kzalloc(sizeof(*clock), GFP_KERNEL);
+	if (!clock)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = core->name;
+	init.ops = &cpg_sd_clock_ops;
+	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+
+	clock->reg = base + core->offset;
+	clock->hw.init = &init;
+	clock->div_table = cpg_sd_div_table;
+	clock->div_num = ARRAY_SIZE(cpg_sd_div_table);
+
+	clock->div_max = clock->div_table[0].div;
+	clock->div_min = clock->div_max;
+	for (i = 1; i < clock->div_num; i++) {
+		clock->div_max = max(clock->div_max, clock->div_table[i].div);
+		clock->div_min = min(clock->div_min, clock->div_table[i].div);
+	}
+
+	clk = clk_register(NULL, &clock->hw);
+	if (IS_ERR(clk))
+		kfree(clock);
+
+	return clk;
+}
+
+
+static const struct rcar_gen3_cpg_pll_config *cpg_pll_config __initdata;
+static unsigned int cpg_clk_extalr __initdata;
+
+struct clk * __init rcar_gen3_cpg_clk_register(struct device *dev,
+	const struct cpg_core_clk *core, const struct cpg_mssr_info *info,
+	struct clk **clks, void __iomem *base)
+{
+	const struct clk *parent;
+	unsigned int mult = 1;
+	unsigned int div = 1;
+	u32 value;
+
+	parent = clks[core->parent];
+	if (IS_ERR(parent))
+		return ERR_CAST(parent);
+
+	switch (core->type) {
+	case CLK_TYPE_GEN3_MAIN:
+		div = cpg_pll_config->extal_div;
+		break;
+
+	case CLK_TYPE_GEN3_PLL0:
+		/*
+		 * PLL0 is a configurable multiplier clock. Register it as a
+		 * fixed factor clock for now as there's no generic multiplier
+		 * clock implementation and we currently have no need to change
+		 * the multiplier value.
+		 */
+		value = readl(base + CPG_PLL0CR);
+		mult = (((value >> 24) & 0x7f) + 1) * 2;
+		break;
+
+	case CLK_TYPE_GEN3_PLL1:
+		mult = cpg_pll_config->pll1_mult;
+		break;
+
+	case CLK_TYPE_GEN3_PLL2:
+		/*
+		 * PLL2 is a configurable multiplier clock. Register it as a
+		 * fixed factor clock for now as there's no generic multiplier
+		 * clock implementation and we currently have no need to change
+		 * the multiplier value.
+		 */
+		value = readl(base + CPG_PLL2CR);
+		mult = (((value >> 24) & 0x7f) + 1) * 2;
+		break;
+
+	case CLK_TYPE_GEN3_PLL3:
+		mult = cpg_pll_config->pll3_mult;
+		break;
+
+	case CLK_TYPE_GEN3_PLL4:
+		/*
+		 * PLL4 is a configurable multiplier clock. Register it as a
+		 * fixed factor clock for now as there's no generic multiplier
+		 * clock implementation and we currently have no need to change
+		 * the multiplier value.
+		 */
+		value = readl(base + CPG_PLL4CR);
+		mult = (((value >> 24) & 0x7f) + 1) * 2;
+		break;
+
+	case CLK_TYPE_GEN3_SD:
+		return cpg_sd_clk_register(core, base, __clk_get_name(parent));
+
+	case CLK_TYPE_GEN3_R:
+		/*
+		 * RINT is default.
+		 * Only if EXTALR is populated, we switch to it.
+		 */
+		value = readl(base + CPG_RCKCR) & 0x3f;
+
+		if (clk_get_rate(clks[cpg_clk_extalr])) {
+			parent = clks[cpg_clk_extalr];
+			value |= BIT(15);
+		}
+
+		writel(value, base + CPG_RCKCR);
+		break;
+
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	return clk_register_fixed_factor(NULL, core->name,
+					 __clk_get_name(parent), 0, mult, div);
+}
+
+/*
+ * Reset register definitions.
+ */
+#define MODEMR	0xe6160060
+
+u32 __init rcar_gen3_read_mode_pins(void)
+{
+	void __iomem *modemr = ioremap_nocache(MODEMR, 4);
+	u32 mode;
+
+	BUG_ON(!modemr);
+	mode = ioread32(modemr);
+	iounmap(modemr);
+
+	return mode;
+}
+
+int __init rcar_gen3_cpg_init(const struct rcar_gen3_cpg_pll_config *config,
+			      unsigned int clk_extalr)
+{
+	cpg_pll_config = config;
+	cpg_clk_extalr = clk_extalr;
+	return 0;
+}
diff --git a/drivers/clk/renesas/rcar-gen3-cpg.h b/drivers/clk/renesas/rcar-gen3-cpg.h
new file mode 100644
index 000000000000..f699085147d1
--- /dev/null
+++ b/drivers/clk/renesas/rcar-gen3-cpg.h
@@ -0,0 +1,43 @@
+/*
+ * R-Car Gen3 Clock Pulse Generator
+ *
+ * Copyright (C) 2015-2016 Glider bvba
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#ifndef __CLK_RENESAS_RCAR_GEN3_CPG_H__
+#define __CLK_RENESAS_RCAR_GEN3_CPG_H__
+
+enum rcar_gen3_clk_types {
+	CLK_TYPE_GEN3_MAIN = CLK_TYPE_CUSTOM,
+	CLK_TYPE_GEN3_PLL0,
+	CLK_TYPE_GEN3_PLL1,
+	CLK_TYPE_GEN3_PLL2,
+	CLK_TYPE_GEN3_PLL3,
+	CLK_TYPE_GEN3_PLL4,
+	CLK_TYPE_GEN3_SD,
+	CLK_TYPE_GEN3_R,
+};
+
+#define DEF_GEN3_SD(_name, _id, _parent, _offset)	\
+	DEF_BASE(_name, _id, CLK_TYPE_GEN3_SD, _parent, .offset = _offset)
+
+struct rcar_gen3_cpg_pll_config {
+	unsigned int extal_div;
+	unsigned int pll1_mult;
+	unsigned int pll3_mult;
+};
+
+#define CPG_RCKCR	0x240
+
+u32 rcar_gen3_read_mode_pins(void);
+struct clk *rcar_gen3_cpg_clk_register(struct device *dev,
+	const struct cpg_core_clk *core, const struct cpg_mssr_info *info,
+	struct clk **clks, void __iomem *base);
+int rcar_gen3_cpg_init(const struct rcar_gen3_cpg_pll_config *config,
+		       unsigned int clk_extalr);
+
+#endif
diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c
index 210cd744a7a9..e1365e7491ae 100644
--- a/drivers/clk/renesas/renesas-cpg-mssr.c
+++ b/drivers/clk/renesas/renesas-cpg-mssr.c
@@ -509,6 +509,12 @@ static const struct of_device_id cpg_mssr_match[] = {
 		.data = &r8a7795_cpg_mssr_info,
 	},
 #endif
+#ifdef CONFIG_ARCH_R8A7796
+	{
+		.compatible = "renesas,r8a7796-cpg-mssr",
+		.data = &r8a7796_cpg_mssr_info,
+	},
+#endif
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/clk/renesas/renesas-cpg-mssr.h b/drivers/clk/renesas/renesas-cpg-mssr.h
index 0d1e3e811e79..ee7edfaf1408 100644
--- a/drivers/clk/renesas/renesas-cpg-mssr.h
+++ b/drivers/clk/renesas/renesas-cpg-mssr.h
@@ -131,4 +131,5 @@ struct cpg_mssr_info {
 };
 
 extern const struct cpg_mssr_info r8a7795_cpg_mssr_info;
+extern const struct cpg_mssr_info r8a7796_cpg_mssr_info;
 #endif
diff --git a/drivers/clk/rockchip/clk-rk3228.c b/drivers/clk/rockchip/clk-rk3228.c
index 016bdb0b793a..db6e5a9e6de6 100644
--- a/drivers/clk/rockchip/clk-rk3228.c
+++ b/drivers/clk/rockchip/clk-rk3228.c
@@ -151,8 +151,8 @@ PNAME(mux_uart0_p)		= { "uart0_src", "uart0_frac", "xin24m" };
 PNAME(mux_uart1_p)		= { "uart1_src", "uart1_frac", "xin24m" };
 PNAME(mux_uart2_p)		= { "uart2_src", "uart2_frac", "xin24m" };
 
-PNAME(mux_sclk_macphy_50m_p)	= { "ext_gmac", "phy_50m_out" };
-PNAME(mux_sclk_gmac_pre_p)	= { "sclk_gmac_src", "sclk_macphy_50m" };
+PNAME(mux_sclk_mac_extclk_p)	= { "ext_gmac", "phy_50m_out" };
+PNAME(mux_sclk_gmac_pre_p)	= { "sclk_gmac_src", "sclk_mac_extclk" };
 PNAME(mux_sclk_macphy_p)	= { "sclk_gmac_src", "ext_gmac" };
 
 static struct rockchip_pll_clock rk3228_pll_clks[] __initdata = {
@@ -170,6 +170,34 @@ static struct rockchip_pll_clock rk3228_pll_clks[] __initdata = {
 #define DFLAGS CLK_DIVIDER_HIWORD_MASK
 #define GFLAGS (CLK_GATE_HIWORD_MASK | CLK_GATE_SET_TO_DISABLE)
 
+static struct rockchip_clk_branch rk3228_i2s0_fracmux __initdata =
+	MUX(0, "i2s0_pre", mux_i2s0_p, CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(9), 8, 2, MFLAGS);
+
+static struct rockchip_clk_branch rk3228_i2s1_fracmux __initdata =
+	MUX(0, "i2s1_pre", mux_i2s1_pre_p, CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(3), 8, 2, MFLAGS);
+
+static struct rockchip_clk_branch rk3228_i2s2_fracmux __initdata =
+	MUX(0, "i2s2_pre", mux_i2s2_p, CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(16), 8, 2, MFLAGS);
+
+static struct rockchip_clk_branch rk3228_spdif_fracmux __initdata =
+	MUX(SCLK_SPDIF, "sclk_spdif", mux_sclk_spdif_p, CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(6), 8, 2, MFLAGS);
+
+static struct rockchip_clk_branch rk3228_uart0_fracmux __initdata =
+	MUX(SCLK_UART0, "sclk_uart0", mux_uart0_p, CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(13), 8, 2, MFLAGS);
+
+static struct rockchip_clk_branch rk3228_uart1_fracmux __initdata =
+	MUX(SCLK_UART1, "sclk_uart1", mux_uart1_p, CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(14), 8, 2, MFLAGS);
+
+static struct rockchip_clk_branch rk3228_uart2_fracmux __initdata =
+	MUX(SCLK_UART2, "sclk_uart2", mux_uart2_p, CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(15), 8, 2, MFLAGS);
+
 static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 	/*
 	 * Clock-Architecture Diagram 1
@@ -335,7 +363,7 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(2), 6, GFLAGS),
 
 	GATE(0, "sclk_hsadc", "ext_hsadc", 0,
-			RK3288_CLKGATE_CON(10), 12, GFLAGS),
+			RK2928_CLKGATE_CON(10), 12, GFLAGS),
 
 	COMPOSITE(0, "sclk_wifi", mux_pll_src_cpll_gpll_usb480m_p, 0,
 			RK2928_CLKSEL_CON(23), 5, 2, MFLAGS, 0, 6, DFLAGS,
@@ -379,22 +407,21 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 	COMPOSITE(0, "i2s0_src", mux_pll_src_2plls_p, 0,
 			RK2928_CLKSEL_CON(9), 15, 1, MFLAGS, 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(0), 3, GFLAGS),
-	COMPOSITE_FRAC(0, "i2s0_frac", "i2s0_src", CLK_SET_RATE_PARENT,
-			RK3288_CLKSEL_CON(8), 0,
-			RK3288_CLKGATE_CON(0), 4, GFLAGS),
-	COMPOSITE_NODIV(SCLK_I2S0, "sclk_i2s0", mux_i2s0_p, 0,
-			RK2928_CLKSEL_CON(9), 8, 2, MFLAGS,
+	COMPOSITE_FRACMUX(0, "i2s0_frac", "i2s0_src", CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(8), 0,
+			RK2928_CLKGATE_CON(0), 4, GFLAGS,
+			&rk3228_i2s0_fracmux),
+	GATE(SCLK_I2S0, "sclk_i2s0", "i2s0_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKGATE_CON(0), 5, GFLAGS),
 
 	COMPOSITE(0, "i2s1_src", mux_pll_src_2plls_p, 0,
 			RK2928_CLKSEL_CON(3), 15, 1, MFLAGS, 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(0), 10, GFLAGS),
-	COMPOSITE_FRAC(0, "i2s1_frac", "i2s1_src", CLK_SET_RATE_PARENT,
-			RK3288_CLKSEL_CON(7), 0,
-			RK3288_CLKGATE_CON(0), 11, GFLAGS),
-	MUX(0, "i2s1_pre", mux_i2s1_pre_p, 0,
-			RK2928_CLKSEL_CON(3), 8, 2, MFLAGS),
-	GATE(SCLK_I2S1, "sclk_i2s1", "i2s1_pre", 0,
+	COMPOSITE_FRACMUX(0, "i2s1_frac", "i2s1_src", CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(7), 0,
+			RK2928_CLKGATE_CON(0), 11, GFLAGS,
+			&rk3228_i2s1_fracmux),
+	GATE(SCLK_I2S1, "sclk_i2s1", "i2s1_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKGATE_CON(0), 14, GFLAGS),
 	COMPOSITE_NODIV(SCLK_I2S_OUT, "i2s_out", mux_i2s_out_p, 0,
 			RK2928_CLKSEL_CON(3), 12, 1, MFLAGS,
@@ -403,21 +430,20 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 	COMPOSITE(0, "i2s2_src", mux_pll_src_2plls_p, 0,
 			RK2928_CLKSEL_CON(16), 15, 1, MFLAGS, 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(0), 7, GFLAGS),
-	COMPOSITE_FRAC(0, "i2s2_frac", "i2s2_src", CLK_SET_RATE_PARENT,
-			RK3288_CLKSEL_CON(30), 0,
-			RK3288_CLKGATE_CON(0), 8, GFLAGS),
-	COMPOSITE_NODIV(SCLK_I2S2, "sclk_i2s2", mux_i2s2_p, 0,
-			RK2928_CLKSEL_CON(16), 8, 2, MFLAGS,
+	COMPOSITE_FRACMUX(0, "i2s2_frac", "i2s2_src", CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(30), 0,
+			RK2928_CLKGATE_CON(0), 8, GFLAGS,
+			&rk3228_i2s2_fracmux),
+	GATE(SCLK_I2S2, "sclk_i2s2", "i2s2_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKGATE_CON(0), 9, GFLAGS),
 
 	COMPOSITE(0, "sclk_spdif_src", mux_pll_src_2plls_p, 0,
 			RK2928_CLKSEL_CON(6), 15, 1, MFLAGS, 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(2), 10, GFLAGS),
-	COMPOSITE_FRAC(0, "spdif_frac", "sclk_spdif_src", CLK_SET_RATE_PARENT,
-			RK3288_CLKSEL_CON(20), 0,
-			RK3288_CLKGATE_CON(2), 12, GFLAGS),
-	MUX(SCLK_SPDIF, "sclk_spdif", mux_sclk_spdif_p, 0,
-			RK2928_CLKSEL_CON(6), 8, 2, MFLAGS),
+	COMPOSITE_FRACMUX(0, "spdif_frac", "sclk_spdif_src", CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(20), 0,
+			RK2928_CLKGATE_CON(2), 12, GFLAGS,
+			&rk3228_spdif_fracmux),
 
 	GATE(0, "jtag", "ext_jtag", 0,
 			RK2928_CLKGATE_CON(1), 3, GFLAGS),
@@ -456,45 +482,42 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 	COMPOSITE(0, "uart2_src", mux_pll_src_cpll_gpll_usb480m_p,
 			0, RK2928_CLKSEL_CON(15), 12, 2,
 			MFLAGS, 0, 7, DFLAGS, RK2928_CLKGATE_CON(1), 12, GFLAGS),
-	COMPOSITE_FRAC(0, "uart0_frac", "uart0_src", CLK_SET_RATE_PARENT,
+	COMPOSITE_FRACMUX(0, "uart0_frac", "uart0_src", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(17), 0,
-			RK2928_CLKGATE_CON(1), 9, GFLAGS),
-	COMPOSITE_FRAC(0, "uart1_frac", "uart1_src", CLK_SET_RATE_PARENT,
+			RK2928_CLKGATE_CON(1), 9, GFLAGS,
+			&rk3228_uart0_fracmux),
+	COMPOSITE_FRACMUX(0, "uart1_frac", "uart1_src", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(18), 0,
-			RK2928_CLKGATE_CON(1), 11, GFLAGS),
-	COMPOSITE_FRAC(0, "uart2_frac", "uart2_src", CLK_SET_RATE_PARENT,
+			RK2928_CLKGATE_CON(1), 11, GFLAGS,
+			&rk3228_uart1_fracmux),
+	COMPOSITE_FRACMUX(0, "uart2_frac", "uart2_src", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(19), 0,
-			RK2928_CLKGATE_CON(1), 13, GFLAGS),
-	MUX(SCLK_UART0, "sclk_uart0", mux_uart0_p, CLK_SET_RATE_PARENT,
-			RK2928_CLKSEL_CON(13), 8, 2, MFLAGS),
-	MUX(SCLK_UART1, "sclk_uart1", mux_uart1_p, CLK_SET_RATE_PARENT,
-			RK2928_CLKSEL_CON(14), 8, 2, MFLAGS),
-	MUX(SCLK_UART2, "sclk_uart2", mux_uart2_p, CLK_SET_RATE_PARENT,
-			RK2928_CLKSEL_CON(15), 8, 2, MFLAGS),
+			RK2928_CLKGATE_CON(1), 13, GFLAGS,
+			&rk3228_uart2_fracmux),
 
 	COMPOSITE(SCLK_NANDC, "sclk_nandc", mux_pll_src_2plls_p, 0,
 			RK2928_CLKSEL_CON(2), 14, 1, MFLAGS, 8, 5, DFLAGS,
 			RK2928_CLKGATE_CON(1), 0, GFLAGS),
 
-	COMPOSITE(0, "sclk_gmac_src", mux_pll_src_2plls_p, 0,
+	COMPOSITE(SCLK_MAC_SRC, "sclk_gmac_src", mux_pll_src_2plls_p, 0,
 			RK2928_CLKSEL_CON(5), 7, 1, MFLAGS, 0, 5, DFLAGS,
 			RK2928_CLKGATE_CON(1), 7, GFLAGS),
-	MUX(0, "sclk_macphy_50m", mux_sclk_macphy_50m_p, 0,
+	MUX(SCLK_MAC_EXTCLK, "sclk_mac_extclk", mux_sclk_mac_extclk_p, 0,
 			RK2928_CLKSEL_CON(29), 10, 1, MFLAGS),
-	MUX(0, "sclk_gmac_pre", mux_sclk_gmac_pre_p, 0,
+	MUX(SCLK_MAC, "sclk_gmac_pre", mux_sclk_gmac_pre_p, 0,
 			RK2928_CLKSEL_CON(5), 5, 1, MFLAGS),
-	GATE(0, "sclk_mac_refout", "sclk_gmac_pre", 0,
+	GATE(SCLK_MAC_REFOUT, "sclk_mac_refout", "sclk_gmac_pre", 0,
 			RK2928_CLKGATE_CON(5), 4, GFLAGS),
-	GATE(0, "sclk_mac_ref", "sclk_gmac_pre", 0,
+	GATE(SCLK_MAC_REF, "sclk_mac_ref", "sclk_gmac_pre", 0,
 			RK2928_CLKGATE_CON(5), 3, GFLAGS),
-	GATE(0, "sclk_mac_rx", "sclk_gmac_pre", 0,
+	GATE(SCLK_MAC_RX, "sclk_mac_rx", "sclk_gmac_pre", 0,
 			RK2928_CLKGATE_CON(5), 5, GFLAGS),
-	GATE(0, "sclk_mac_tx", "sclk_gmac_pre", 0,
+	GATE(SCLK_MAC_TX, "sclk_mac_tx", "sclk_gmac_pre", 0,
 			RK2928_CLKGATE_CON(5), 6, GFLAGS),
-	COMPOSITE(0, "sclk_macphy", mux_sclk_macphy_p, 0,
+	COMPOSITE(SCLK_MAC_PHY, "sclk_macphy", mux_sclk_macphy_p, 0,
 			RK2928_CLKSEL_CON(29), 12, 1, MFLAGS, 8, 2, DFLAGS,
 			RK2928_CLKGATE_CON(5), 7, GFLAGS),
-	COMPOSITE(0, "sclk_gmac_out", mux_pll_src_2plls_p, 0,
+	COMPOSITE(SCLK_MAC_OUT, "sclk_gmac_out", mux_pll_src_2plls_p, 0,
 			RK2928_CLKSEL_CON(5), 15, 1, MFLAGS, 8, 5, DFLAGS,
 			RK2928_CLKGATE_CON(2), 2, GFLAGS),
 
@@ -528,7 +551,7 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 
 	/* PD_PERI */
 	GATE(0, "aclk_peri_noc", "aclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(12), 0, GFLAGS),
-	GATE(0, "aclk_gmac", "aclk_peri", 0, RK2928_CLKGATE_CON(11), 4, GFLAGS),
+	GATE(ACLK_GMAC, "aclk_gmac", "aclk_peri", 0, RK2928_CLKGATE_CON(11), 4, GFLAGS),
 
 	GATE(HCLK_SDMMC, "hclk_sdmmc", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 0, GFLAGS),
 	GATE(HCLK_SDIO, "hclk_sdio", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 1, GFLAGS),
@@ -544,7 +567,7 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 	GATE(0, "hclk_host2_arb", "hclk_peri", 0, RK2928_CLKGATE_CON(11), 14, GFLAGS),
 	GATE(0, "hclk_peri_noc", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(12), 1, GFLAGS),
 
-	GATE(0, "pclk_gmac", "pclk_peri", 0, RK2928_CLKGATE_CON(11), 5, GFLAGS),
+	GATE(PCLK_GMAC, "pclk_gmac", "pclk_peri", 0, RK2928_CLKGATE_CON(11), 5, GFLAGS),
 	GATE(0, "pclk_peri_noc", "pclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(12), 2, GFLAGS),
 
 	/* PD_GPU */
@@ -558,10 +581,10 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 	GATE(0, "aclk_bus_noc", "aclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(10), 1, GFLAGS),
 
 	GATE(0, "hclk_rom", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 3, GFLAGS),
-	GATE(0, "hclk_i2s0_8ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 7, GFLAGS),
-	GATE(0, "hclk_i2s1_8ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 8, GFLAGS),
-	GATE(0, "hclk_i2s2_2ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 9, GFLAGS),
-	GATE(0, "hclk_spdif_8ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 10, GFLAGS),
+	GATE(HCLK_I2S0_8CH, "hclk_i2s0_8ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 7, GFLAGS),
+	GATE(HCLK_I2S1_8CH, "hclk_i2s1_8ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 8, GFLAGS),
+	GATE(HCLK_I2S2_2CH, "hclk_i2s2_2ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 9, GFLAGS),
+	GATE(HCLK_SPDIF_8CH, "hclk_spdif_8ch", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 10, GFLAGS),
 	GATE(0, "hclk_tsp", "hclk_cpu", 0, RK2928_CLKGATE_CON(10), 11, GFLAGS),
 	GATE(0, "hclk_crypto_mst", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 11, GFLAGS),
 	GATE(0, "hclk_crypto_slv", "hclk_cpu", 0, RK2928_CLKGATE_CON(8), 12, GFLAGS),
diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c
index 8059a8d3ea36..c109d80e7a8a 100644
--- a/drivers/clk/rockchip/clk-rk3399.c
+++ b/drivers/clk/rockchip/clk-rk3399.c
@@ -586,7 +586,7 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = {
 			RK3399_CLKGATE_CON(8), 15, GFLAGS),
 
 	COMPOSITE(SCLK_SPDIF_REC_DPTX, "clk_spdif_rec_dptx", mux_pll_src_cpll_gpll_p, 0,
-			RK3399_CLKSEL_CON(32), 15, 1, MFLAGS, 0, 5, DFLAGS,
+			RK3399_CLKSEL_CON(32), 15, 1, MFLAGS, 8, 5, DFLAGS,
 			RK3399_CLKGATE_CON(10), 6, GFLAGS),
 	/* i2s */
 	COMPOSITE(0, "clk_i2s0_div", mux_pll_src_cpll_gpll_p, 0,
@@ -1500,6 +1500,7 @@ static void __init rk3399_clk_init(struct device_node *np)
 {
 	struct rockchip_clk_provider *ctx;
 	void __iomem *reg_base;
+	struct clk *clk;
 
 	reg_base = of_iomap(np, 0);
 	if (!reg_base) {
@@ -1514,6 +1515,14 @@ static void __init rk3399_clk_init(struct device_node *np)
 		return;
 	}
 
+	/* Watchdog pclk is controlled by RK3399 SECURE_GRF_SOC_CON3[8]. */
+	clk = clk_register_fixed_factor(NULL, "pclk_wdt", "pclk_alive", 0, 1, 1);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock pclk_wdt: %ld\n",
+			__func__, PTR_ERR(clk));
+	else
+		rockchip_clk_add_lookup(ctx, clk, PCLK_WDT);
+
 	rockchip_clk_register_plls(ctx, rk3399_pll_clks,
 				   ARRAY_SIZE(rk3399_pll_clks), -1);
 
diff --git a/drivers/clk/samsung/Kconfig b/drivers/clk/samsung/Kconfig
index 20c5fe92ab4a..addc65270e43 100644
--- a/drivers/clk/samsung/Kconfig
+++ b/drivers/clk/samsung/Kconfig
@@ -9,6 +9,15 @@ config EXYNOS_ARM64_COMMON_CLK
 	bool "Samsung Exynos ARMv8-family clock controller support" if COMPILE_TEST
 	depends on COMMON_CLK_SAMSUNG
 
+config EXYNOS_AUDSS_CLK_CON
+	tristate "Samsung Exynos AUDSS clock controller support"
+	depends on COMMON_CLK_SAMSUNG
+	default y if ARCH_EXYNOS
+	help
+	  Support for the Audio Subsystem CLKCON clock controller present
+	  on some Exynos SoC variants. Choose M or Y here if you want to
+	  use audio devices such as I2S, PCM, etc.
+
 # For S3C24XX platforms, select following symbols:
 config S3C2410_COMMON_CLK
 	bool "Samsung S3C2410 clock controller support" if COMPILE_TEST
diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile
index fc367d4b2902..57f4dc6dc447 100644
--- a/drivers/clk/samsung/Makefile
+++ b/drivers/clk/samsung/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_SOC_EXYNOS5410)	+= clk-exynos5410.o
 obj-$(CONFIG_SOC_EXYNOS5420)	+= clk-exynos5420.o
 obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK)	+= clk-exynos5433.o
 obj-$(CONFIG_SOC_EXYNOS5440)	+= clk-exynos5440.o
-obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos-audss.o
+obj-$(CONFIG_EXYNOS_AUDSS_CLK_CON) += clk-exynos-audss.o
 obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos-clkout.o
 obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK)	+= clk-exynos7.o
 obj-$(CONFIG_S3C2410_COMMON_CLK)+= clk-s3c2410.o
diff --git a/drivers/clk/samsung/clk-cpu.c b/drivers/clk/samsung/clk-cpu.c
index 813003d6ce09..8bf7e805fd34 100644
--- a/drivers/clk/samsung/clk-cpu.c
+++ b/drivers/clk/samsung/clk-cpu.c
@@ -45,6 +45,13 @@
 #define E4210_DIV_STAT_CPU0	0x400
 #define E4210_DIV_STAT_CPU1	0x404
 
+#define E5433_MUX_SEL2		0x008
+#define E5433_MUX_STAT2		0x208
+#define E5433_DIV_CPU0		0x400
+#define E5433_DIV_CPU1		0x404
+#define E5433_DIV_STAT_CPU0	0x500
+#define E5433_DIV_STAT_CPU1	0x504
+
 #define E4210_DIV0_RATIO0_MASK	0x7
 #define E4210_DIV1_HPM_MASK	(0x7 << 4)
 #define E4210_DIV1_COPY_MASK	(0x7 << 0)
@@ -253,6 +260,102 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata,
 }
 
 /*
+ * Helper function to set the 'safe' dividers for the CPU clock. The parameters
+ * div and mask contain the divider value and the register bit mask of the
+ * dividers to be programmed.
+ */
+static void exynos5433_set_safe_div(void __iomem *base, unsigned long div,
+					unsigned long mask)
+{
+	unsigned long div0;
+
+	div0 = readl(base + E5433_DIV_CPU0);
+	div0 = (div0 & ~mask) | (div & mask);
+	writel(div0, base + E5433_DIV_CPU0);
+	wait_until_divider_stable(base + E5433_DIV_STAT_CPU0, mask);
+}
+
+/* handler for pre-rate change notification from parent clock */
+static int exynos5433_cpuclk_pre_rate_change(struct clk_notifier_data *ndata,
+			struct exynos_cpuclk *cpuclk, void __iomem *base)
+{
+	const struct exynos_cpuclk_cfg_data *cfg_data = cpuclk->cfg;
+	unsigned long alt_prate = clk_get_rate(cpuclk->alt_parent);
+	unsigned long alt_div = 0, alt_div_mask = DIV_MASK;
+	unsigned long div0, div1 = 0, mux_reg;
+	unsigned long flags;
+
+	/* find out the divider values to use for clock data */
+	while ((cfg_data->prate * 1000) != ndata->new_rate) {
+		if (cfg_data->prate == 0)
+			return -EINVAL;
+		cfg_data++;
+	}
+
+	spin_lock_irqsave(cpuclk->lock, flags);
+
+	/*
+	 * For the selected PLL clock frequency, get the pre-defined divider
+	 * values.
+	 */
+	div0 = cfg_data->div0;
+	div1 = cfg_data->div1;
+
+	/*
+	 * If the old parent clock speed is less than the clock speed of
+	 * the alternate parent, then it should be ensured that at no point
+	 * the armclk speed is more than the old_prate until the dividers are
+	 * set.  Also workaround the issue of the dividers being set to lower
+	 * values before the parent clock speed is set to new lower speed
+	 * (this can result in too high speed of armclk output clocks).
+	 */
+	if (alt_prate > ndata->old_rate || ndata->old_rate > ndata->new_rate) {
+		unsigned long tmp_rate = min(ndata->old_rate, ndata->new_rate);
+
+		alt_div = DIV_ROUND_UP(alt_prate, tmp_rate) - 1;
+		WARN_ON(alt_div >= MAX_DIV);
+
+		exynos5433_set_safe_div(base, alt_div, alt_div_mask);
+		div0 |= alt_div;
+	}
+
+	/* select the alternate parent */
+	mux_reg = readl(base + E5433_MUX_SEL2);
+	writel(mux_reg | 1, base + E5433_MUX_SEL2);
+	wait_until_mux_stable(base + E5433_MUX_STAT2, 0, 2);
+
+	/* alternate parent is active now. set the dividers */
+	writel(div0, base + E5433_DIV_CPU0);
+	wait_until_divider_stable(base + E5433_DIV_STAT_CPU0, DIV_MASK_ALL);
+
+	writel(div1, base + E5433_DIV_CPU1);
+	wait_until_divider_stable(base + E5433_DIV_STAT_CPU1, DIV_MASK_ALL);
+
+	spin_unlock_irqrestore(cpuclk->lock, flags);
+	return 0;
+}
+
+/* handler for post-rate change notification from parent clock */
+static int exynos5433_cpuclk_post_rate_change(struct clk_notifier_data *ndata,
+			struct exynos_cpuclk *cpuclk, void __iomem *base)
+{
+	unsigned long div = 0, div_mask = DIV_MASK;
+	unsigned long mux_reg;
+	unsigned long flags;
+
+	spin_lock_irqsave(cpuclk->lock, flags);
+
+	/* select apll as the alternate parent */
+	mux_reg = readl(base + E5433_MUX_SEL2);
+	writel(mux_reg & ~1, base + E5433_MUX_SEL2);
+	wait_until_mux_stable(base + E5433_MUX_STAT2, 0, 1);
+
+	exynos5433_set_safe_div(base, div, div_mask);
+	spin_unlock_irqrestore(cpuclk->lock, flags);
+	return 0;
+}
+
+/*
  * This notifier function is called for the pre-rate and post-rate change
  * notifications of the parent clock of cpuclk.
  */
@@ -275,6 +378,29 @@ static int exynos_cpuclk_notifier_cb(struct notifier_block *nb,
 	return notifier_from_errno(err);
 }
 
+/*
+ * This notifier function is called for the pre-rate and post-rate change
+ * notifications of the parent clock of cpuclk.
+ */
+static int exynos5433_cpuclk_notifier_cb(struct notifier_block *nb,
+				unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+	struct exynos_cpuclk *cpuclk;
+	void __iomem *base;
+	int err = 0;
+
+	cpuclk = container_of(nb, struct exynos_cpuclk, clk_nb);
+	base = cpuclk->ctrl_base;
+
+	if (event == PRE_RATE_CHANGE)
+		err = exynos5433_cpuclk_pre_rate_change(ndata, cpuclk, base);
+	else if (event == POST_RATE_CHANGE)
+		err = exynos5433_cpuclk_post_rate_change(ndata, cpuclk, base);
+
+	return notifier_from_errno(err);
+}
+
 /* helper function to register a CPU clock */
 int __init exynos_register_cpu_clock(struct samsung_clk_provider *ctx,
 		unsigned int lookup_id, const char *name, const char *parent,
@@ -301,7 +427,10 @@ int __init exynos_register_cpu_clock(struct samsung_clk_provider *ctx,
 	cpuclk->ctrl_base = ctx->reg_base + offset;
 	cpuclk->lock = &ctx->lock;
 	cpuclk->flags = flags;
-	cpuclk->clk_nb.notifier_call = exynos_cpuclk_notifier_cb;
+	if (flags & CLK_CPU_HAS_E5433_REGS_LAYOUT)
+		cpuclk->clk_nb.notifier_call = exynos5433_cpuclk_notifier_cb;
+	else
+		cpuclk->clk_nb.notifier_call = exynos_cpuclk_notifier_cb;
 
 	cpuclk->alt_parent = __clk_lookup(alt_parent);
 	if (!cpuclk->alt_parent) {
diff --git a/drivers/clk/samsung/clk-cpu.h b/drivers/clk/samsung/clk-cpu.h
index 37874d3c3165..d4b6b517fe1b 100644
--- a/drivers/clk/samsung/clk-cpu.h
+++ b/drivers/clk/samsung/clk-cpu.h
@@ -57,10 +57,12 @@ struct exynos_cpuclk {
 	struct notifier_block			clk_nb;
 	unsigned long				flags;
 
-/* The CPU clock registers has DIV1 configuration register */
+/* The CPU clock registers have DIV1 configuration register */
 #define CLK_CPU_HAS_DIV1		(1 << 0)
 /* When ALT parent is active, debug clocks need safe divider values */
 #define CLK_CPU_NEEDS_DEBUG_ALT_DIV	(1 << 1)
+/* The CPU clock registers have Exynos5433-compatible layout */
+#define CLK_CPU_HAS_E5433_REGS_LAYOUT	(1 << 2)
 };
 
 extern int __init exynos_register_cpu_clock(struct samsung_clk_provider *ctx,
diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c
index 4e9584d79089..bdf8b971f332 100644
--- a/drivers/clk/samsung/clk-exynos-audss.c
+++ b/drivers/clk/samsung/clk-exynos-audss.c
@@ -273,17 +273,7 @@ static struct platform_driver exynos_audss_clk_driver = {
 	.remove = exynos_audss_clk_remove,
 };
 
-static int __init exynos_audss_clk_init(void)
-{
-	return platform_driver_register(&exynos_audss_clk_driver);
-}
-core_initcall(exynos_audss_clk_init);
-
-static void __exit exynos_audss_clk_exit(void)
-{
-	platform_driver_unregister(&exynos_audss_clk_driver);
-}
-module_exit(exynos_audss_clk_exit);
+module_platform_driver(exynos_audss_clk_driver);
 
 MODULE_AUTHOR("Padmavathi Venna <padma.v@samsung.com>");
 MODULE_DESCRIPTION("Exynos Audio Subsystem Clock Controller");
diff --git a/drivers/clk/samsung/clk-exynos-clkout.c b/drivers/clk/samsung/clk-exynos-clkout.c
index 7cd02ff37a1f..96fab6cfb202 100644
--- a/drivers/clk/samsung/clk-exynos-clkout.c
+++ b/drivers/clk/samsung/clk-exynos-clkout.c
@@ -151,6 +151,8 @@ static void __init exynos5_clkout_init(struct device_node *node)
 }
 CLK_OF_DECLARE(exynos5250_clkout, "samsung,exynos5250-pmu",
 		exynos5_clkout_init);
+CLK_OF_DECLARE(exynos5410_clkout, "samsung,exynos5410-pmu",
+		exynos5_clkout_init);
 CLK_OF_DECLARE(exynos5420_clkout, "samsung,exynos5420-pmu",
 		exynos5_clkout_init);
 CLK_OF_DECLARE(exynos5433_clkout, "samsung,exynos5433-pmu",
diff --git a/drivers/clk/samsung/clk-exynos3250.c b/drivers/clk/samsung/clk-exynos3250.c
index 16575ee874cb..1b81e283f605 100644
--- a/drivers/clk/samsung/clk-exynos3250.c
+++ b/drivers/clk/samsung/clk-exynos3250.c
@@ -103,7 +103,7 @@
 #define PWR_CTRL1_USE_CORE1_WFI			(1 << 1)
 #define PWR_CTRL1_USE_CORE0_WFI			(1 << 0)
 
-static unsigned long exynos3250_cmu_clk_regs[] __initdata = {
+static const unsigned long exynos3250_cmu_clk_regs[] __initconst = {
 	SRC_LEFTBUS,
 	DIV_LEFTBUS,
 	GATE_IP_LEFTBUS,
@@ -226,7 +226,7 @@ PNAME(group_sclk_fimd0_p)	= { "xxti", "xusbxti",
 PNAME(mout_mfc_p)		= { "mout_mfc_0", "mout_mfc_1" };
 PNAME(mout_g3d_p)		= { "mout_g3d_0", "mout_g3d_1" };
 
-static struct samsung_fixed_factor_clock fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "sclk_mpll_1600", "mout_mpll", 1, 1, 0),
 	FFACTOR(0, "sclk_mpll_mif", "mout_mpll", 1, 2, 0),
 	FFACTOR(0, "sclk_bpll", "fout_bpll", 1, 2, 0),
@@ -237,7 +237,7 @@ static struct samsung_fixed_factor_clock fixed_factor_clks[] __initdata = {
 	FFACTOR(CLK_FIN_PLL, "fin_pll", "xusbxti", 1, 1, 0),
 };
 
-static struct samsung_mux_clock mux_clks[] __initdata = {
+static const struct samsung_mux_clock mux_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by register address in ascending
 	 * order and then bitfield shift in descending order, as it is done
@@ -326,7 +326,7 @@ static struct samsung_mux_clock mux_clks[] __initdata = {
 			CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_div_clock div_clks[] __initdata = {
+static const struct samsung_div_clock div_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by register address in ascending
 	 * order and then bitfield shift in descending order, as it is done
@@ -429,7 +429,7 @@ static struct samsung_div_clock div_clks[] __initdata = {
 	DIV(CLK_DIV_COPY, "div_copy", "mout_hpm", DIV_CPU1, 0, 3),
 };
 
-static struct samsung_gate_clock gate_clks[] __initdata = {
+static const struct samsung_gate_clock gate_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by register address in ascending
 	 * order and then bitfield shift in descending order, as it is done
@@ -669,7 +669,7 @@ static struct samsung_gate_clock gate_clks[] __initdata = {
 };
 
 /* APLL & MPLL & BPLL & UPLL */
-static struct samsung_pll_rate_table exynos3250_pll_rates[] = {
+static const struct samsung_pll_rate_table exynos3250_pll_rates[] __initconst = {
 	PLL_35XX_RATE(1200000000, 400, 4, 1),
 	PLL_35XX_RATE(1100000000, 275, 3, 1),
 	PLL_35XX_RATE(1066000000, 533, 6, 1),
@@ -691,7 +691,7 @@ static struct samsung_pll_rate_table exynos3250_pll_rates[] = {
 };
 
 /* EPLL */
-static struct samsung_pll_rate_table exynos3250_epll_rates[] = {
+static const struct samsung_pll_rate_table exynos3250_epll_rates[] __initconst = {
 	PLL_36XX_RATE(800000000, 200, 3, 1,     0),
 	PLL_36XX_RATE(288000000,  96, 2, 2,     0),
 	PLL_36XX_RATE(192000000, 128, 2, 3,     0),
@@ -710,7 +710,7 @@ static struct samsung_pll_rate_table exynos3250_epll_rates[] = {
 };
 
 /* VPLL */
-static struct samsung_pll_rate_table exynos3250_vpll_rates[] = {
+static const struct samsung_pll_rate_table exynos3250_vpll_rates[] __initconst = {
 	PLL_36XX_RATE(600000000, 100, 2, 1,     0),
 	PLL_36XX_RATE(533000000, 266, 3, 2, 32768),
 	PLL_36XX_RATE(519230987, 173, 2, 2,  5046),
@@ -740,7 +740,7 @@ static struct samsung_pll_rate_table exynos3250_vpll_rates[] = {
 	{ /* sentinel */ }
 };
 
-static struct samsung_pll_clock exynos3250_plls[] __initdata = {
+static const struct samsung_pll_clock exynos3250_plls[] __initconst = {
 	PLL(pll_35xx, CLK_FOUT_APLL, "fout_apll", "fin_pll",
 		APLL_LOCK, APLL_CON0, exynos3250_pll_rates),
 	PLL(pll_35xx, CLK_FOUT_MPLL, "fout_mpll", "fin_pll",
@@ -772,7 +772,7 @@ static void __init exynos3_core_down_clock(void __iomem *reg_base)
 	__raw_writel(0x0, reg_base + PWR_CTRL2);
 }
 
-static struct samsung_cmu_info cmu_info __initdata = {
+static const struct samsung_cmu_info cmu_info __initconst = {
 	.pll_clks		= exynos3250_plls,
 	.nr_pll_clks		= ARRAY_SIZE(exynos3250_plls),
 	.mux_clks		= mux_clks,
@@ -848,7 +848,7 @@ CLK_OF_DECLARE(exynos3250_cmu, "samsung,exynos3250-cmu", exynos3250_cmu_init);
 #define EPLL_CON2		0x111c
 #define SRC_EPLL		0x1120
 
-static unsigned long exynos3250_cmu_dmc_clk_regs[] __initdata = {
+static const unsigned long exynos3250_cmu_dmc_clk_regs[] __initconst = {
 	BPLL_LOCK,
 	BPLL_CON0,
 	BPLL_CON1,
@@ -874,7 +874,7 @@ PNAME(mout_bpll_p)	= { "fin_pll", "fout_bpll", };
 PNAME(mout_mpll_mif_p)	= { "fin_pll", "sclk_mpll_mif", };
 PNAME(mout_dphy_p)	= { "mout_mpll_mif", "mout_bpll", };
 
-static struct samsung_mux_clock dmc_mux_clks[] __initdata = {
+static const struct samsung_mux_clock dmc_mux_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by register address in ascending
 	 * order and then bitfield shift in descending order, as it is done
@@ -893,7 +893,7 @@ static struct samsung_mux_clock dmc_mux_clks[] __initdata = {
 	MUX(CLK_MOUT_EPLL, "mout_epll", mout_epll_p, SRC_EPLL, 4, 1),
 };
 
-static struct samsung_div_clock dmc_div_clks[] __initdata = {
+static const struct samsung_div_clock dmc_div_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by register address in ascending
 	 * order and then bitfield shift in descending order, as it is done
@@ -910,14 +910,14 @@ static struct samsung_div_clock dmc_div_clks[] __initdata = {
 	DIV(CLK_DIV_DMCD, "div_dmcd", "div_dmc", DIV_DMC1, 11, 3),
 };
 
-static struct samsung_pll_clock exynos3250_dmc_plls[] __initdata = {
+static const struct samsung_pll_clock exynos3250_dmc_plls[] __initconst = {
 	PLL(pll_35xx, CLK_FOUT_BPLL, "fout_bpll", "fin_pll",
 		BPLL_LOCK, BPLL_CON0, exynos3250_pll_rates),
 	PLL(pll_36xx, CLK_FOUT_EPLL, "fout_epll", "fin_pll",
 		EPLL_LOCK, EPLL_CON0, exynos3250_epll_rates),
 };
 
-static struct samsung_cmu_info dmc_cmu_info __initdata = {
+static const struct samsung_cmu_info dmc_cmu_info __initconst = {
 	.pll_clks		= exynos3250_dmc_plls,
 	.nr_pll_clks		= ARRAY_SIZE(exynos3250_dmc_plls),
 	.mux_clks		= dmc_mux_clks,
@@ -947,7 +947,7 @@ CLK_OF_DECLARE(exynos3250_cmu_dmc, "samsung,exynos3250-cmu-dmc",
 #define GATE_IP_ISP1		0x804
 #define GATE_SCLK_ISP		0x900
 
-static struct samsung_div_clock isp_div_clks[] __initdata = {
+static const struct samsung_div_clock isp_div_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by register address in ascending
 	 * order and then bitfield shift in descending order, as it is done
@@ -967,7 +967,7 @@ static struct samsung_div_clock isp_div_clks[] __initdata = {
 	DIV(CLK_DIV_MPWM, "div_mpwm", "div_isp1", DIV_ISP1, 0, 3),
 };
 
-static struct samsung_gate_clock isp_gate_clks[] __initdata = {
+static const struct samsung_gate_clock isp_gate_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by register address in ascending
 	 * order and then bitfield shift in descending order, as it is done
@@ -1063,7 +1063,7 @@ static struct samsung_gate_clock isp_gate_clks[] __initdata = {
 		GATE_SCLK_ISP, 0, CLK_IGNORE_UNUSED, 0),
 };
 
-static struct samsung_cmu_info isp_cmu_info __initdata = {
+static const struct samsung_cmu_info isp_cmu_info __initconst = {
 	.div_clks	= isp_div_clks,
 	.nr_div_clks	= ARRAY_SIZE(isp_div_clks),
 	.gate_clks	= isp_gate_clks,
@@ -1079,14 +1079,15 @@ static int __init exynos3250_cmu_isp_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id exynos3250_cmu_isp_of_match[] = {
+static const struct of_device_id exynos3250_cmu_isp_of_match[] __initconst = {
 	{ .compatible = "samsung,exynos3250-cmu-isp", },
 	{ /* sentinel */ }
 };
 
-static struct platform_driver exynos3250_cmu_isp_driver = {
+static struct platform_driver exynos3250_cmu_isp_driver __initdata = {
 	.driver = {
 		.name = "exynos3250-cmu-isp",
+		.suppress_bind_attrs = true,
 		.of_match_table = exynos3250_cmu_isp_of_match,
 	},
 };
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index 7b3d0f975987..faab9b31baf5 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -169,7 +169,7 @@ static struct samsung_clk_reg_dump *exynos4_save_pll;
  * list of controller registers to be saved and restored during a
  * suspend/resume cycle.
  */
-static unsigned long exynos4210_clk_save[] __initdata = {
+static const unsigned long exynos4210_clk_save[] __initconst = {
 	E4210_SRC_IMAGE,
 	E4210_SRC_LCD1,
 	E4210_SRC_MASK_LCD1,
@@ -181,7 +181,7 @@ static unsigned long exynos4210_clk_save[] __initdata = {
 	PWR_CTRL1,
 };
 
-static unsigned long exynos4x12_clk_save[] __initdata = {
+static const unsigned long exynos4x12_clk_save[] __initconst = {
 	E4X12_GATE_IP_IMAGE,
 	E4X12_GATE_IP_PERIR,
 	E4X12_SRC_CAM1,
@@ -192,7 +192,7 @@ static unsigned long exynos4x12_clk_save[] __initdata = {
 	E4X12_PWR_CTRL2,
 };
 
-static unsigned long exynos4_clk_pll_regs[] __initdata = {
+static const unsigned long exynos4_clk_pll_regs[] __initconst = {
 	EPLL_LOCK,
 	VPLL_LOCK,
 	EPLL_CON0,
@@ -203,7 +203,7 @@ static unsigned long exynos4_clk_pll_regs[] __initdata = {
 	VPLL_CON2,
 };
 
-static unsigned long exynos4_clk_regs[] __initdata = {
+static const unsigned long exynos4_clk_regs[] __initconst = {
 	SRC_LEFTBUS,
 	DIV_LEFTBUS,
 	GATE_IP_LEFTBUS,
@@ -505,28 +505,28 @@ static struct samsung_fixed_rate_clock exynos4_fixed_rate_ext_clks[] __initdata
 };
 
 /* fixed rate clocks generated inside the soc */
-static struct samsung_fixed_rate_clock exynos4_fixed_rate_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock exynos4_fixed_rate_clks[] __initconst = {
 	FRATE(0, "sclk_hdmi24m", NULL, 0, 24000000),
 	FRATE(CLK_SCLK_HDMIPHY, "sclk_hdmiphy", "hdmi", 0, 27000000),
 	FRATE(0, "sclk_usbphy0", NULL, 0, 48000000),
 };
 
-static struct samsung_fixed_rate_clock exynos4210_fixed_rate_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock exynos4210_fixed_rate_clks[] __initconst = {
 	FRATE(0, "sclk_usbphy1", NULL, 0, 48000000),
 };
 
-static struct samsung_fixed_factor_clock exynos4_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock exynos4_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "sclk_apll_div_2", "sclk_apll", 1, 2, 0),
 	FFACTOR(0, "fout_mpll_div_2", "fout_mpll", 1, 2, 0),
 	FFACTOR(0, "fout_apll_div_2", "fout_apll", 1, 2, 0),
 	FFACTOR(0, "arm_clk_div_2", "div_core2", 1, 2, 0),
 };
 
-static struct samsung_fixed_factor_clock exynos4210_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock exynos4210_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "sclk_mpll_div_2", "sclk_mpll", 1, 2, 0),
 };
 
-static struct samsung_fixed_factor_clock exynos4x12_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock exynos4x12_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "sclk_mpll_user_l_div_2", "mout_mpll_user_l", 1, 2, 0),
 	FFACTOR(0, "sclk_mpll_user_r_div_2", "mout_mpll_user_r", 1, 2, 0),
 	FFACTOR(0, "sclk_mpll_user_t_div_2", "mout_mpll_user_t", 1, 2, 0),
@@ -534,7 +534,7 @@ static struct samsung_fixed_factor_clock exynos4x12_fixed_factor_clks[] __initda
 };
 
 /* list of mux clocks supported in all exynos4 soc's */
-static struct samsung_mux_clock exynos4_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos4_mux_clks[] __initconst = {
 	MUX_FA(CLK_MOUT_APLL, "mout_apll", mout_apll_p, SRC_CPU, 0, 1,
 			CLK_SET_RATE_PARENT | CLK_RECALC_NEW_RATES, 0,
 			"mout_apll"),
@@ -555,11 +555,11 @@ static struct samsung_mux_clock exynos4_mux_clks[] __initdata = {
 };
 
 /* list of mux clocks supported in exynos4210 soc */
-static struct samsung_mux_clock exynos4210_mux_early[] __initdata = {
+static const struct samsung_mux_clock exynos4210_mux_early[] __initconst = {
 	MUX(0, "mout_vpllsrc", mout_vpllsrc_p, SRC_TOP1, 0, 1),
 };
 
-static struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos4210_mux_clks[] __initconst = {
 	MUX(0, "mout_gdl", sclk_ampll_p4210, SRC_LEFTBUS, 0, 1),
 	MUX(0, "mout_clkout_leftbus", clkout_left_p4210,
 			CLKOUT_CMU_LEFTBUS, 0, 5),
@@ -622,7 +622,7 @@ static struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
 };
 
 /* list of mux clocks supported in exynos4x12 soc */
-static struct samsung_mux_clock exynos4x12_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos4x12_mux_clks[] __initconst = {
 	MUX(0, "mout_mpll_user_l", mout_mpll_p, SRC_LEFTBUS, 4, 1),
 	MUX(0, "mout_gdl", mout_gdl_p4x12, SRC_LEFTBUS, 0, 1),
 	MUX(0, "mout_clkout_leftbus", clkout_left_p4x12,
@@ -705,7 +705,7 @@ static struct samsung_mux_clock exynos4x12_mux_clks[] __initdata = {
 };
 
 /* list of divider clocks supported in all exynos4 soc's */
-static struct samsung_div_clock exynos4_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos4_div_clks[] __initconst = {
 	DIV(CLK_DIV_GDL, "div_gdl", "mout_gdl", DIV_LEFTBUS, 0, 3),
 	DIV(0, "div_gpl", "div_gdl", DIV_LEFTBUS, 4, 3),
 	DIV(0, "div_clkout_leftbus", "mout_clkout_leftbus",
@@ -795,7 +795,7 @@ static struct samsung_div_clock exynos4_div_clks[] __initdata = {
 };
 
 /* list of divider clocks supported in exynos4210 soc */
-static struct samsung_div_clock exynos4210_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos4210_div_clks[] __initconst = {
 	DIV(CLK_ACLK200, "aclk200", "mout_aclk200", DIV_TOP, 0, 3),
 	DIV(CLK_SCLK_FIMG2D, "sclk_fimg2d", "mout_g2d", DIV_IMAGE, 0, 4),
 	DIV(0, "div_fimd1", "mout_fimd1", E4210_DIV_LCD1, 0, 4),
@@ -806,7 +806,7 @@ static struct samsung_div_clock exynos4210_div_clks[] __initdata = {
 };
 
 /* list of divider clocks supported in exynos4x12 soc */
-static struct samsung_div_clock exynos4x12_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos4x12_div_clks[] __initconst = {
 	DIV(0, "div_mdnie0", "mout_mdnie0", DIV_LCD0, 4, 4),
 	DIV(0, "div_mdnie_pwm0", "mout_mdnie_pwm0", DIV_LCD0, 8, 4),
 	DIV(0, "div_mdnie_pwm_pre0", "div_mdnie_pwm0", DIV_LCD0, 12, 4),
@@ -837,7 +837,7 @@ static struct samsung_div_clock exynos4x12_div_clks[] __initdata = {
 };
 
 /* list of gate clocks supported in all exynos4 soc's */
-static struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
+static const struct samsung_gate_clock exynos4_gate_clks[] __initconst = {
 	/*
 	 * After all Exynos4 based platforms are migrated to use device tree,
 	 * the device name and clock alias names specified below for some
@@ -1043,7 +1043,7 @@ static struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
 };
 
 /* list of gate clocks supported in exynos4210 soc */
-static struct samsung_gate_clock exynos4210_gate_clks[] __initdata = {
+static const struct samsung_gate_clock exynos4210_gate_clks[] __initconst = {
 	GATE(CLK_TVENC, "tvenc", "aclk160", GATE_IP_TV, 2, 0, 0),
 	GATE(CLK_G2D, "g2d", "aclk200", E4210_GATE_IP_IMAGE, 0, 0, 0),
 	GATE(CLK_ROTATOR, "rotator", "aclk200", E4210_GATE_IP_IMAGE, 1, 0, 0),
@@ -1090,7 +1090,7 @@ static struct samsung_gate_clock exynos4210_gate_clks[] __initdata = {
 };
 
 /* list of gate clocks supported in exynos4x12 soc */
-static struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
+static const struct samsung_gate_clock exynos4x12_gate_clks[] __initconst = {
 	GATE(CLK_AUDSS, "audss", "sclk_epll", E4X12_GATE_IP_MAUDIO, 0, 0, 0),
 	GATE(CLK_MDNIE0, "mdnie0", "aclk160", GATE_IP_LCD0, 2, 0, 0),
 	GATE(CLK_ROTATOR, "rotator", "aclk200", E4X12_GATE_IP_IMAGE, 1, 0, 0),
@@ -1190,17 +1190,17 @@ static struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 		0),
 };
 
-static struct samsung_clock_alias exynos4_aliases[] __initdata = {
+static const struct samsung_clock_alias exynos4_aliases[] __initconst = {
 	ALIAS(CLK_MOUT_CORE, NULL, "moutcore"),
 	ALIAS(CLK_ARM_CLK, NULL, "armclk"),
 	ALIAS(CLK_SCLK_APLL, NULL, "mout_apll"),
 };
 
-static struct samsung_clock_alias exynos4210_aliases[] __initdata = {
+static const struct samsung_clock_alias exynos4210_aliases[] __initconst = {
 	ALIAS(CLK_SCLK_MPLL, NULL, "mout_mpll"),
 };
 
-static struct samsung_clock_alias exynos4x12_aliases[] __initdata = {
+static const struct samsung_clock_alias exynos4x12_aliases[] __initconst = {
 	ALIAS(CLK_MOUT_MPLL_USER_C, NULL, "mout_mpll"),
 };
 
@@ -1211,7 +1211,7 @@ static struct samsung_clock_alias exynos4x12_aliases[] __initdata = {
  * controller is first remapped and the value of XOM[0] bit is read to
  * determine the parent clock.
  */
-static unsigned long exynos4_get_xom(void)
+static unsigned long __init exynos4_get_xom(void)
 {
 	unsigned long xom = 0;
 	void __iomem *chipid_base;
@@ -1264,7 +1264,7 @@ static const struct of_device_id ext_clk_match[] __initconst = {
 };
 
 /* PLLs PMS values */
-static struct samsung_pll_rate_table exynos4210_apll_rates[] __initdata = {
+static const struct samsung_pll_rate_table exynos4210_apll_rates[] __initconst = {
 	PLL_45XX_RATE(1200000000, 150,  3, 1, 28),
 	PLL_45XX_RATE(1000000000, 250,  6, 1, 28),
 	PLL_45XX_RATE( 800000000, 200,  6, 1, 28),
@@ -1277,7 +1277,7 @@ static struct samsung_pll_rate_table exynos4210_apll_rates[] __initdata = {
 	{ /* sentinel */ }
 };
 
-static struct samsung_pll_rate_table exynos4210_epll_rates[] __initdata = {
+static const struct samsung_pll_rate_table exynos4210_epll_rates[] __initconst = {
 	PLL_4600_RATE(192000000, 48, 3, 1,     0, 0),
 	PLL_4600_RATE(180633605, 45, 3, 1, 10381, 0),
 	PLL_4600_RATE(180000000, 45, 3, 1,     0, 0),
@@ -1288,7 +1288,7 @@ static struct samsung_pll_rate_table exynos4210_epll_rates[] __initdata = {
 	{ /* sentinel */ }
 };
 
-static struct samsung_pll_rate_table exynos4210_vpll_rates[] __initdata = {
+static const struct samsung_pll_rate_table exynos4210_vpll_rates[] __initconst = {
 	PLL_4650_RATE(360000000, 44, 3, 0, 1024, 0, 14, 0),
 	PLL_4650_RATE(324000000, 53, 2, 1, 1024, 1,  1, 1),
 	PLL_4650_RATE(259617187, 63, 3, 1, 1950, 0, 20, 1),
@@ -1297,7 +1297,7 @@ static struct samsung_pll_rate_table exynos4210_vpll_rates[] __initdata = {
 	{ /* sentinel */ }
 };
 
-static struct samsung_pll_rate_table exynos4x12_apll_rates[] __initdata = {
+static const struct samsung_pll_rate_table exynos4x12_apll_rates[] __initconst = {
 	PLL_35XX_RATE(1500000000, 250, 4, 0),
 	PLL_35XX_RATE(1400000000, 175, 3, 0),
 	PLL_35XX_RATE(1300000000, 325, 6, 0),
@@ -1315,7 +1315,7 @@ static struct samsung_pll_rate_table exynos4x12_apll_rates[] __initdata = {
 	{ /* sentinel */ }
 };
 
-static struct samsung_pll_rate_table exynos4x12_epll_rates[] __initdata = {
+static const struct samsung_pll_rate_table exynos4x12_epll_rates[] __initconst = {
 	PLL_36XX_RATE(192000000, 48, 3, 1,     0),
 	PLL_36XX_RATE(180633605, 45, 3, 1, 10381),
 	PLL_36XX_RATE(180000000, 45, 3, 1,     0),
@@ -1326,7 +1326,7 @@ static struct samsung_pll_rate_table exynos4x12_epll_rates[] __initdata = {
 	{ /* sentinel */ }
 };
 
-static struct samsung_pll_rate_table exynos4x12_vpll_rates[] __initdata = {
+static const struct samsung_pll_rate_table exynos4x12_vpll_rates[] __initconst = {
 	PLL_36XX_RATE(533000000, 133, 3, 1, 16384),
 	PLL_36XX_RATE(440000000, 110, 3, 1,     0),
 	PLL_36XX_RATE(350000000, 175, 3, 2,     0),
@@ -1375,12 +1375,12 @@ static void __init exynos4x12_core_down_clock(void)
 	if (num_possible_cpus() == 4)
 		tmp |= PWR_CTRL1_USE_CORE3_WFE | PWR_CTRL1_USE_CORE2_WFE |
 		       PWR_CTRL1_USE_CORE3_WFI | PWR_CTRL1_USE_CORE2_WFI;
-	__raw_writel(tmp, reg_base + PWR_CTRL1);
+	writel_relaxed(tmp, reg_base + PWR_CTRL1);
 
 	/*
 	 * Disable the clock up feature in case it was enabled by bootloader.
 	 */
-	__raw_writel(0x0, reg_base + E4X12_PWR_CTRL2);
+	writel_relaxed(0x0, reg_base + E4X12_PWR_CTRL2);
 }
 
 #define E4210_CPU_DIV0(apll, pclk_dbg, atb, periph, corem1, corem0)	\
@@ -1450,8 +1450,6 @@ static void __init exynos4_clk_init(struct device_node *np,
 		panic("%s: failed to map registers\n", __func__);
 
 	ctx = samsung_clk_init(np, reg_base, CLK_NR_CLKS);
-	if (!ctx)
-		panic("%s: unable to allocate context.\n", __func__);
 
 	samsung_clk_of_register_fixed_ext(ctx, exynos4_fixed_rate_ext_clks,
 			ARRAY_SIZE(exynos4_fixed_rate_ext_clks),
diff --git a/drivers/clk/samsung/clk-exynos4415.c b/drivers/clk/samsung/clk-exynos4415.c
index 86ee06b226bd..6c9063159717 100644
--- a/drivers/clk/samsung/clk-exynos4415.c
+++ b/drivers/clk/samsung/clk-exynos4415.c
@@ -111,7 +111,7 @@
 #define DIV_CPU0		0x14500
 #define DIV_CPU1		0x14504
 
-static unsigned long exynos4415_cmu_clk_regs[] __initdata = {
+static const unsigned long exynos4415_cmu_clk_regs[] __initconst = {
 	SRC_LEFTBUS,
 	DIV_LEFTBUS,
 	GATE_IP_LEFTBUS,
@@ -268,16 +268,16 @@ PNAME(group_aclk_isp0_300_user_p) = { "fin_pll", "mout_aclk_isp0_300" };
 PNAME(group_aclk_isp1_300_user_p) = { "fin_pll", "mout_aclk_isp1_300" };
 PNAME(group_mout_mpll_user_t_p)	= { "mout_mpll_user_t" };
 
-static struct samsung_fixed_factor_clock exynos4415_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock exynos4415_fixed_factor_clks[] __initconst = {
 	/* HACK: fin_pll hardcoded to xusbxti until detection is implemented. */
 	FFACTOR(CLK_FIN_PLL, "fin_pll", "xusbxti", 1, 1, 0),
 };
 
-static struct samsung_fixed_rate_clock exynos4415_fixed_rate_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock exynos4415_fixed_rate_clks[] __initconst = {
 	FRATE(CLK_SCLK_HDMIPHY, "sclk_hdmiphy", NULL, 0, 27000000),
 };
 
-static struct samsung_mux_clock exynos4415_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos4415_mux_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by register address in ascending
 	 * order and then bitfield shift in descending order, as it is done
@@ -427,7 +427,7 @@ static struct samsung_mux_clock exynos4415_mux_clks[] __initdata = {
 		group_aclk_isp1_300_user_p, SRC_TOP_ISP1, 0, 1),
 };
 
-static struct samsung_div_clock exynos4415_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos4415_div_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by register address in ascending
 	 * order and then bitfield shift in descending order, as it is done
@@ -566,7 +566,7 @@ static struct samsung_div_clock exynos4415_div_clks[] __initdata = {
 	DIV(CLK_DIV_COPY, "div_copy", "mout_hpm", DIV_CPU1, 0, 3),
 };
 
-static struct samsung_gate_clock exynos4415_gate_clks[] __initdata = {
+static const struct samsung_gate_clock exynos4415_gate_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by register address in ascending
 	 * order and then bitfield shift in descending order, as it is done
@@ -859,7 +859,7 @@ static struct samsung_gate_clock exynos4415_gate_clks[] __initdata = {
 /*
  * APLL & MPLL & BPLL & ISP_PLL & DISP_PLL & G3D_PLL
  */
-static struct samsung_pll_rate_table exynos4415_pll_rates[] = {
+static const struct samsung_pll_rate_table exynos4415_pll_rates[] __initconst = {
 	PLL_35XX_RATE(1600000000, 400, 3,  1),
 	PLL_35XX_RATE(1500000000, 250, 2,  1),
 	PLL_35XX_RATE(1400000000, 175, 3,  0),
@@ -891,7 +891,7 @@ static struct samsung_pll_rate_table exynos4415_pll_rates[] = {
 };
 
 /* EPLL */
-static struct samsung_pll_rate_table exynos4415_epll_rates[] = {
+static const struct samsung_pll_rate_table exynos4415_epll_rates[] __initconst = {
 	PLL_36XX_RATE(800000000, 200, 3, 1,     0),
 	PLL_36XX_RATE(288000000,  96, 2, 2,     0),
 	PLL_36XX_RATE(192000000, 128, 2, 3,     0),
@@ -909,7 +909,7 @@ static struct samsung_pll_rate_table exynos4415_epll_rates[] = {
 	{ /* sentinel */ }
 };
 
-static struct samsung_pll_clock exynos4415_plls[] __initdata = {
+static const struct samsung_pll_clock exynos4415_plls[] __initconst = {
 	PLL(pll_35xx, CLK_FOUT_APLL, "fout_apll", "fin_pll",
 		APLL_LOCK, APLL_CON0, exynos4415_pll_rates),
 	PLL(pll_36xx, CLK_FOUT_EPLL, "fout_epll", "fin_pll",
@@ -922,7 +922,7 @@ static struct samsung_pll_clock exynos4415_plls[] __initdata = {
 		"fin_pll", DISP_PLL_LOCK, DISP_PLL_CON0, exynos4415_pll_rates),
 };
 
-static struct samsung_cmu_info cmu_info __initdata = {
+static const struct samsung_cmu_info cmu_info __initconst = {
 	.pll_clks		= exynos4415_plls,
 	.nr_pll_clks		= ARRAY_SIZE(exynos4415_plls),
 	.mux_clks		= exynos4415_mux_clks,
@@ -961,7 +961,7 @@ CLK_OF_DECLARE(exynos4415_cmu, "samsung,exynos4415-cmu", exynos4415_cmu_init);
 #define SRC_DMC			0x300
 #define DIV_DMC1		0x504
 
-static unsigned long exynos4415_cmu_dmc_clk_regs[] __initdata = {
+static const unsigned long exynos4415_cmu_dmc_clk_regs[] __initconst = {
 	MPLL_LOCK,
 	MPLL_CON0,
 	MPLL_CON1,
@@ -978,14 +978,14 @@ PNAME(mout_mpll_p)		= { "fin_pll", "fout_mpll", };
 PNAME(mout_bpll_p)		= { "fin_pll", "fout_bpll", };
 PNAME(mbpll_p)			= { "mout_mpll", "mout_bpll", };
 
-static struct samsung_mux_clock exynos4415_dmc_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos4415_dmc_mux_clks[] __initconst = {
 	MUX(CLK_DMC_MOUT_MPLL, "mout_mpll", mout_mpll_p, SRC_DMC, 12, 1),
 	MUX(CLK_DMC_MOUT_BPLL, "mout_bpll", mout_bpll_p, SRC_DMC, 10, 1),
 	MUX(CLK_DMC_MOUT_DPHY, "mout_dphy", mbpll_p, SRC_DMC, 8, 1),
 	MUX(CLK_DMC_MOUT_DMC_BUS, "mout_dmc_bus", mbpll_p, SRC_DMC, 4, 1),
 };
 
-static struct samsung_div_clock exynos4415_dmc_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos4415_dmc_div_clks[] __initconst = {
 	DIV(CLK_DMC_DIV_DMC, "div_dmc", "div_dmc_pre", DIV_DMC1, 27, 3),
 	DIV(CLK_DMC_DIV_DPHY, "div_dphy", "mout_dphy", DIV_DMC1, 23, 3),
 	DIV(CLK_DMC_DIV_DMC_PRE, "div_dmc_pre", "mout_dmc_bus",
@@ -995,14 +995,14 @@ static struct samsung_div_clock exynos4415_dmc_div_clks[] __initdata = {
 	DIV(CLK_DMC_DIV_MPLL_PRE, "div_mpll_pre", "mout_mpll", DIV_DMC1, 8, 2),
 };
 
-static struct samsung_pll_clock exynos4415_dmc_plls[] __initdata = {
+static const struct samsung_pll_clock exynos4415_dmc_plls[] __initconst = {
 	PLL(pll_35xx, CLK_DMC_FOUT_MPLL, "fout_mpll", "fin_pll",
 		MPLL_LOCK, MPLL_CON0, exynos4415_pll_rates),
 	PLL(pll_35xx, CLK_DMC_FOUT_BPLL, "fout_bpll", "fin_pll",
 		BPLL_LOCK, BPLL_CON0, exynos4415_pll_rates),
 };
 
-static struct samsung_cmu_info cmu_dmc_info __initdata = {
+static const struct samsung_cmu_info cmu_dmc_info __initconst = {
 	.pll_clks		= exynos4415_dmc_plls,
 	.nr_pll_clks		= ARRAY_SIZE(exynos4415_dmc_plls),
 	.mux_clks		= exynos4415_dmc_mux_clks,
diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index 837197db4ffb..27a227d6620c 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -117,7 +117,7 @@ static struct samsung_clk_reg_dump *exynos5250_save;
  * list of controller registers to be saved and restored during a
  * suspend/resume cycle.
  */
-static unsigned long exynos5250_clk_regs[] __initdata = {
+static const unsigned long exynos5250_clk_regs[] __initconst = {
 	SRC_CPU,
 	DIV_CPU0,
 	PWR_CTRL1,
@@ -190,7 +190,7 @@ static struct syscore_ops exynos5250_clk_syscore_ops = {
 	.resume = exynos5250_clk_resume,
 };
 
-static void exynos5250_clk_sleep_init(void)
+static void __init exynos5250_clk_sleep_init(void)
 {
 	exynos5250_save = samsung_clk_alloc_reg_dump(exynos5250_clk_regs,
 					ARRAY_SIZE(exynos5250_clk_regs));
@@ -203,7 +203,7 @@ static void exynos5250_clk_sleep_init(void)
 	register_syscore_ops(&exynos5250_clk_syscore_ops);
 }
 #else
-static void exynos5250_clk_sleep_init(void) {}
+static void __init exynos5250_clk_sleep_init(void) {}
 #endif
 
 /* list of all parent clock list */
@@ -266,23 +266,23 @@ static struct samsung_fixed_rate_clock exynos5250_fixed_rate_ext_clks[] __initda
 };
 
 /* fixed rate clocks generated inside the soc */
-static struct samsung_fixed_rate_clock exynos5250_fixed_rate_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock exynos5250_fixed_rate_clks[] __initconst = {
 	FRATE(CLK_SCLK_HDMIPHY, "sclk_hdmiphy", NULL, 0, 24000000),
 	FRATE(0, "sclk_hdmi27m", NULL, 0, 27000000),
 	FRATE(0, "sclk_dptxphy", NULL, 0, 24000000),
 	FRATE(0, "sclk_uhostphy", NULL, 0, 48000000),
 };
 
-static struct samsung_fixed_factor_clock exynos5250_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock exynos5250_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "fout_mplldiv2", "fout_mpll", 1, 2, 0),
 	FFACTOR(0, "fout_bplldiv2", "fout_bpll", 1, 2, 0),
 };
 
-static struct samsung_mux_clock exynos5250_pll_pmux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos5250_pll_pmux_clks[] __initconst = {
 	MUX(0, "mout_vpllsrc", mout_vpllsrc_p, SRC_TOP2, 0, 1),
 };
 
-static struct samsung_mux_clock exynos5250_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos5250_mux_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by (clock domain, register address,
 	 * bitfield shift) triplet in ascending order. When adding new entries,
@@ -378,7 +378,7 @@ static struct samsung_mux_clock exynos5250_mux_clks[] __initdata = {
 	MUX(0, "mout_bpll_fout", mout_bpll_fout_p, PLL_DIV2_SEL, 0, 1),
 };
 
-static struct samsung_div_clock exynos5250_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos5250_div_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by (clock domain, register address,
 	 * bitfield shift) triplet in ascending order. When adding new entries,
@@ -470,7 +470,7 @@ static struct samsung_div_clock exynos5250_div_clks[] __initdata = {
 	DIV(CLK_DIV_I2S2, "div_i2s2", "sclk_audio2", DIV_PERIC5, 8, 6),
 };
 
-static struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
+static const struct samsung_gate_clock exynos5250_gate_clks[] __initconst = {
 	/*
 	 * NOTE: Following table is sorted by (clock domain, register address,
 	 * bitfield shift) triplet in ascending order. When adding new entries,
@@ -698,7 +698,7 @@ static struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
 			GATE_IP_ISP1, 7, 0, 0),
 };
 
-static struct samsung_pll_rate_table vpll_24mhz_tbl[] __initdata = {
+static const struct samsung_pll_rate_table vpll_24mhz_tbl[] __initconst = {
 	/* sorted in descending order */
 	/* PLL_36XX_RATE(rate, m, p, s, k) */
 	PLL_36XX_RATE(266000000, 266, 3, 3, 0),
@@ -707,7 +707,7 @@ static struct samsung_pll_rate_table vpll_24mhz_tbl[] __initdata = {
 	{ },
 };
 
-static struct samsung_pll_rate_table epll_24mhz_tbl[] __initdata = {
+static const struct samsung_pll_rate_table epll_24mhz_tbl[] __initconst = {
 	/* sorted in descending order */
 	/* PLL_36XX_RATE(rate, m, p, s, k) */
 	PLL_36XX_RATE(192000000, 64, 2, 2, 0),
@@ -721,7 +721,7 @@ static struct samsung_pll_rate_table epll_24mhz_tbl[] __initdata = {
 	{ },
 };
 
-static struct samsung_pll_rate_table apll_24mhz_tbl[] __initdata = {
+static const struct samsung_pll_rate_table apll_24mhz_tbl[] __initconst = {
 	/* sorted in descending order */
 	/* PLL_35XX_RATE(rate, m, p, s) */
 	PLL_35XX_RATE(1700000000, 425, 6, 0),
@@ -805,8 +805,7 @@ static void __init exynos5250_clk_init(struct device_node *np)
 	}
 
 	ctx = samsung_clk_init(np, reg_base, CLK_NR_CLKS);
-	if (!ctx)
-		panic("%s: unable to allocate context.\n", __func__);
+
 	samsung_clk_of_register_fixed_ext(ctx, exynos5250_fixed_rate_ext_clks,
 			ARRAY_SIZE(exynos5250_fixed_rate_ext_clks),
 			ext_clk_match);
diff --git a/drivers/clk/samsung/clk-exynos5260.c b/drivers/clk/samsung/clk-exynos5260.c
index 7a7ed075a573..a43642c36039 100644
--- a/drivers/clk/samsung/clk-exynos5260.c
+++ b/drivers/clk/samsung/clk-exynos5260.c
@@ -22,7 +22,7 @@
  * Applicable for all 2550 Type PLLS for Exynos5260, listed below
  * DISP_PLL, EGL_PLL, KFC_PLL, MEM_PLL, BUS_PLL, MEDIA_PLL, G3D_PLL.
  */
-static struct samsung_pll_rate_table pll2550_24mhz_tbl[] __initdata = {
+static const struct samsung_pll_rate_table pll2550_24mhz_tbl[] __initconst = {
 	PLL_35XX_RATE(1700000000, 425, 6, 0),
 	PLL_35XX_RATE(1600000000, 200, 3, 0),
 	PLL_35XX_RATE(1500000000, 250, 4, 0),
@@ -55,7 +55,7 @@ static struct samsung_pll_rate_table pll2550_24mhz_tbl[] __initdata = {
 /*
  * Applicable for 2650 Type PLL for AUD_PLL.
  */
-static struct samsung_pll_rate_table pll2650_24mhz_tbl[] __initdata = {
+static const struct samsung_pll_rate_table pll2650_24mhz_tbl[] __initconst = {
 	PLL_36XX_RATE(1600000000, 200, 3, 0, 0),
 	PLL_36XX_RATE(1200000000, 100, 2, 0, 0),
 	PLL_36XX_RATE(1000000000, 250, 3, 1, 0),
@@ -78,7 +78,7 @@ static struct samsung_pll_rate_table pll2650_24mhz_tbl[] __initdata = {
 
 /* CMU_AUD */
 
-static unsigned long aud_clk_regs[] __initdata = {
+static const unsigned long aud_clk_regs[] __initconst = {
 	MUX_SEL_AUD,
 	DIV_AUD0,
 	DIV_AUD1,
@@ -92,7 +92,7 @@ PNAME(mout_aud_pll_user_p) = {"fin_pll", "fout_aud_pll"};
 PNAME(mout_sclk_aud_i2s_p) = {"mout_aud_pll_user", "ioclk_i2s_cdclk"};
 PNAME(mout_sclk_aud_pcm_p) = {"mout_aud_pll_user", "ioclk_pcm_extclk"};
 
-static struct samsung_mux_clock aud_mux_clks[] __initdata = {
+static const struct samsung_mux_clock aud_mux_clks[] __initconst = {
 	MUX(AUD_MOUT_AUD_PLL_USER, "mout_aud_pll_user", mout_aud_pll_user_p,
 			MUX_SEL_AUD, 0, 1),
 	MUX(AUD_MOUT_SCLK_AUD_I2S, "mout_sclk_aud_i2s", mout_sclk_aud_i2s_p,
@@ -101,7 +101,7 @@ static struct samsung_mux_clock aud_mux_clks[] __initdata = {
 			MUX_SEL_AUD, 8, 1),
 };
 
-static struct samsung_div_clock aud_div_clks[] __initdata = {
+static const struct samsung_div_clock aud_div_clks[] __initconst = {
 	DIV(AUD_DOUT_ACLK_AUD_131, "dout_aclk_aud_131", "mout_aud_pll_user",
 			DIV_AUD0, 0, 4),
 
@@ -113,7 +113,7 @@ static struct samsung_div_clock aud_div_clks[] __initdata = {
 			DIV_AUD1, 12, 4),
 };
 
-static struct samsung_gate_clock aud_gate_clks[] __initdata = {
+static const struct samsung_gate_clock aud_gate_clks[] __initconst = {
 	GATE(AUD_SCLK_I2S, "sclk_aud_i2s", "dout_sclk_aud_i2s",
 			EN_SCLK_AUD, 0, CLK_SET_RATE_PARENT, 0),
 	GATE(AUD_SCLK_PCM, "sclk_aud_pcm", "dout_sclk_aud_pcm",
@@ -154,7 +154,7 @@ CLK_OF_DECLARE(exynos5260_clk_aud, "samsung,exynos5260-clock-aud",
 
 /* CMU_DISP */
 
-static unsigned long disp_clk_regs[] __initdata = {
+static const unsigned long disp_clk_regs[] __initconst = {
 	MUX_SEL_DISP0,
 	MUX_SEL_DISP1,
 	MUX_SEL_DISP2,
@@ -201,7 +201,7 @@ PNAME(mout_phyclk_mipi_dphy_4lmrxclk_esc0_user_p) = {"fin_pll",
 PNAME(mout_sclk_hdmi_spdif_p) = {"fin_pll", "ioclk_spdif_extclk",
 			"dout_aclk_peri_aud", "phyclk_hdmi_phy_ref_cko"};
 
-static struct samsung_mux_clock disp_mux_clks[] __initdata = {
+static const struct samsung_mux_clock disp_mux_clks[] __initconst = {
 	MUX(DISP_MOUT_ACLK_DISP_333_USER, "mout_aclk_disp_333_user",
 			mout_aclk_disp_333_user_p,
 			MUX_SEL_DISP0, 0, 1),
@@ -270,7 +270,7 @@ static struct samsung_mux_clock disp_mux_clks[] __initdata = {
 			MUX_SEL_DISP4, 4, 2),
 };
 
-static struct samsung_div_clock disp_div_clks[] __initdata = {
+static const struct samsung_div_clock disp_div_clks[] __initconst = {
 	DIV(DISP_DOUT_PCLK_DISP_111, "dout_pclk_disp_111",
 			"mout_aclk_disp_222_user",
 			DIV_DISP, 8, 4),
@@ -283,7 +283,7 @@ static struct samsung_div_clock disp_div_clks[] __initdata = {
 			DIV_DISP, 16, 4),
 };
 
-static struct samsung_gate_clock disp_gate_clks[] __initdata = {
+static const struct samsung_gate_clock disp_gate_clks[] __initconst = {
 	GATE(DISP_MOUT_HDMI_PHY_PIXEL_USER, "sclk_hdmi_link_i_pixel",
 			"mout_phyclk_hdmi_phy_pixel_clko_user",
 			EN_SCLK_DISP0, 26, CLK_SET_RATE_PARENT, 0),
@@ -344,7 +344,7 @@ CLK_OF_DECLARE(exynos5260_clk_disp, "samsung,exynos5260-clock-disp",
 
 /* CMU_EGL */
 
-static unsigned long egl_clk_regs[] __initdata = {
+static const unsigned long egl_clk_regs[] __initconst = {
 	EGL_PLL_LOCK,
 	EGL_PLL_CON0,
 	EGL_PLL_CON1,
@@ -361,13 +361,13 @@ static unsigned long egl_clk_regs[] __initdata = {
 PNAME(mout_egl_b_p) = {"mout_egl_pll", "dout_bus_pll"};
 PNAME(mout_egl_pll_p) = {"fin_pll", "fout_egl_pll"};
 
-static struct samsung_mux_clock egl_mux_clks[] __initdata = {
+static const struct samsung_mux_clock egl_mux_clks[] __initconst = {
 	MUX(EGL_MOUT_EGL_PLL, "mout_egl_pll", mout_egl_pll_p,
 			MUX_SEL_EGL, 4, 1),
 	MUX(EGL_MOUT_EGL_B, "mout_egl_b", mout_egl_b_p, MUX_SEL_EGL, 16, 1),
 };
 
-static struct samsung_div_clock egl_div_clks[] __initdata = {
+static const struct samsung_div_clock egl_div_clks[] __initconst = {
 	DIV(EGL_DOUT_EGL1, "dout_egl1", "mout_egl_b", DIV_EGL, 0, 3),
 	DIV(EGL_DOUT_EGL2, "dout_egl2", "dout_egl1", DIV_EGL, 4, 3),
 	DIV(EGL_DOUT_ACLK_EGL, "dout_aclk_egl", "dout_egl2", DIV_EGL, 8, 3),
@@ -379,7 +379,7 @@ static struct samsung_div_clock egl_div_clks[] __initdata = {
 	DIV(EGL_DOUT_EGL_PLL, "dout_egl_pll", "mout_egl_b", DIV_EGL, 24, 3),
 };
 
-static struct samsung_pll_clock egl_pll_clks[] __initdata = {
+static const struct samsung_pll_clock egl_pll_clks[] __initconst = {
 	PLL(pll_2550xx, EGL_FOUT_EGL_PLL, "fout_egl_pll", "fin_pll",
 		EGL_PLL_LOCK, EGL_PLL_CON0,
 		pll2550_24mhz_tbl),
@@ -408,7 +408,7 @@ CLK_OF_DECLARE(exynos5260_clk_egl, "samsung,exynos5260-clock-egl",
 
 /* CMU_FSYS */
 
-static unsigned long fsys_clk_regs[] __initdata = {
+static const unsigned long fsys_clk_regs[] __initconst = {
 	MUX_SEL_FSYS0,
 	MUX_SEL_FSYS1,
 	EN_ACLK_FSYS,
@@ -431,7 +431,7 @@ PNAME(mout_phyclk_usbdrd30_pipe_pclk_user_p) = {"fin_pll",
 PNAME(mout_phyclk_usbdrd30_phyclock_user_p) = {"fin_pll",
 			"phyclk_usbdrd30_udrd30_phyclock"};
 
-static struct samsung_mux_clock fsys_mux_clks[] __initdata = {
+static const struct samsung_mux_clock fsys_mux_clks[] __initconst = {
 	MUX(FSYS_MOUT_PHYCLK_USBDRD30_PHYCLOCK_USER,
 			"mout_phyclk_usbdrd30_phyclock_user",
 			mout_phyclk_usbdrd30_phyclock_user_p,
@@ -454,7 +454,7 @@ static struct samsung_mux_clock fsys_mux_clks[] __initdata = {
 			MUX_SEL_FSYS1, 16, 1),
 };
 
-static struct samsung_gate_clock fsys_gate_clks[] __initdata = {
+static const struct samsung_gate_clock fsys_gate_clks[] __initconst = {
 	GATE(FSYS_PHYCLK_USBHOST20, "phyclk_usbhost20_phyclock",
 			"mout_phyclk_usbdrd30_phyclock_user",
 			EN_SCLK_FSYS, 1, 0, 0),
@@ -508,7 +508,7 @@ CLK_OF_DECLARE(exynos5260_clk_fsys, "samsung,exynos5260-clock-fsys",
 
 /* CMU_G2D */
 
-static unsigned long g2d_clk_regs[] __initdata = {
+static const unsigned long g2d_clk_regs[] __initconst = {
 	MUX_SEL_G2D,
 	MUX_STAT_G2D,
 	DIV_G2D,
@@ -535,18 +535,18 @@ static unsigned long g2d_clk_regs[] __initdata = {
 
 PNAME(mout_aclk_g2d_333_user_p) = {"fin_pll", "dout_aclk_g2d_333"};
 
-static struct samsung_mux_clock g2d_mux_clks[] __initdata = {
+static const struct samsung_mux_clock g2d_mux_clks[] __initconst = {
 	MUX(G2D_MOUT_ACLK_G2D_333_USER, "mout_aclk_g2d_333_user",
 			mout_aclk_g2d_333_user_p,
 			MUX_SEL_G2D, 0, 1),
 };
 
-static struct samsung_div_clock g2d_div_clks[] __initdata = {
+static const struct samsung_div_clock g2d_div_clks[] __initconst = {
 	DIV(G2D_DOUT_PCLK_G2D_83, "dout_pclk_g2d_83", "mout_aclk_g2d_333_user",
 			DIV_G2D, 0, 3),
 };
 
-static struct samsung_gate_clock g2d_gate_clks[] __initdata = {
+static const struct samsung_gate_clock g2d_gate_clks[] __initconst = {
 	GATE(G2D_CLK_G2D, "clk_g2d", "mout_aclk_g2d_333_user",
 			EN_IP_G2D, 4, 0, 0),
 	GATE(G2D_CLK_JPEG, "clk_jpeg", "mout_aclk_g2d_333_user",
@@ -599,7 +599,7 @@ CLK_OF_DECLARE(exynos5260_clk_g2d, "samsung,exynos5260-clock-g2d",
 
 /* CMU_G3D */
 
-static unsigned long g3d_clk_regs[] __initdata = {
+static const unsigned long g3d_clk_regs[] __initconst = {
 	G3D_PLL_LOCK,
 	G3D_PLL_CON0,
 	G3D_PLL_CON1,
@@ -615,23 +615,23 @@ static unsigned long g3d_clk_regs[] __initdata = {
 
 PNAME(mout_g3d_pll_p) = {"fin_pll", "fout_g3d_pll"};
 
-static struct samsung_mux_clock g3d_mux_clks[] __initdata = {
+static const struct samsung_mux_clock g3d_mux_clks[] __initconst = {
 	MUX(G3D_MOUT_G3D_PLL, "mout_g3d_pll", mout_g3d_pll_p,
 			MUX_SEL_G3D, 0, 1),
 };
 
-static struct samsung_div_clock g3d_div_clks[] __initdata = {
+static const struct samsung_div_clock g3d_div_clks[] __initconst = {
 	DIV(G3D_DOUT_PCLK_G3D, "dout_pclk_g3d", "dout_aclk_g3d", DIV_G3D, 0, 3),
 	DIV(G3D_DOUT_ACLK_G3D, "dout_aclk_g3d", "mout_g3d_pll", DIV_G3D, 4, 3),
 };
 
-static struct samsung_gate_clock g3d_gate_clks[] __initdata = {
+static const struct samsung_gate_clock g3d_gate_clks[] __initconst = {
 	GATE(G3D_CLK_G3D, "clk_g3d", "dout_aclk_g3d", EN_IP_G3D, 2, 0, 0),
 	GATE(G3D_CLK_G3D_HPM, "clk_g3d_hpm", "dout_aclk_g3d",
 			EN_IP_G3D, 3, 0, 0),
 };
 
-static struct samsung_pll_clock g3d_pll_clks[] __initdata = {
+static const struct samsung_pll_clock g3d_pll_clks[] __initconst = {
 	PLL(pll_2550, G3D_FOUT_G3D_PLL, "fout_g3d_pll", "fin_pll",
 		G3D_PLL_LOCK, G3D_PLL_CON0,
 		pll2550_24mhz_tbl),
@@ -662,7 +662,7 @@ CLK_OF_DECLARE(exynos5260_clk_g3d, "samsung,exynos5260-clock-g3d",
 
 /* CMU_GSCL */
 
-static unsigned long gscl_clk_regs[] __initdata = {
+static const unsigned long gscl_clk_regs[] __initconst = {
 	MUX_SEL_GSCL,
 	DIV_GSCL,
 	EN_ACLK_GSCL,
@@ -692,7 +692,7 @@ PNAME(mout_aclk_m2m_400_user_p) = {"fin_pll", "dout_aclk_gscl_400"};
 PNAME(mout_aclk_gscl_fimc_user_p) = {"fin_pll", "dout_aclk_gscl_400"};
 PNAME(mout_aclk_csis_p) = {"dout_aclk_csis_200", "mout_aclk_gscl_fimc_user"};
 
-static struct samsung_mux_clock gscl_mux_clks[] __initdata = {
+static const struct samsung_mux_clock gscl_mux_clks[] __initconst = {
 	MUX(GSCL_MOUT_ACLK_GSCL_333_USER, "mout_aclk_gscl_333_user",
 			mout_aclk_gscl_333_user_p,
 			MUX_SEL_GSCL, 0, 1),
@@ -706,7 +706,7 @@ static struct samsung_mux_clock gscl_mux_clks[] __initdata = {
 			MUX_SEL_GSCL, 24, 1),
 };
 
-static struct samsung_div_clock gscl_div_clks[] __initdata = {
+static const struct samsung_div_clock gscl_div_clks[] __initconst = {
 	DIV(GSCL_DOUT_PCLK_M2M_100, "dout_pclk_m2m_100",
 			"mout_aclk_m2m_400_user",
 			DIV_GSCL, 0, 3),
@@ -715,7 +715,7 @@ static struct samsung_div_clock gscl_div_clks[] __initdata = {
 			DIV_GSCL, 4, 3),
 };
 
-static struct samsung_gate_clock gscl_gate_clks[] __initdata = {
+static const struct samsung_gate_clock gscl_gate_clks[] __initconst = {
 	GATE(GSCL_SCLK_CSIS0_WRAP, "sclk_csis0_wrap", "dout_aclk_csis_200",
 			EN_SCLK_GSCL_FIMC, 0, CLK_SET_RATE_PARENT, 0),
 	GATE(GSCL_SCLK_CSIS1_WRAP, "sclk_csis1_wrap", "dout_aclk_csis_200",
@@ -795,7 +795,7 @@ CLK_OF_DECLARE(exynos5260_clk_gscl, "samsung,exynos5260-clock-gscl",
 
 /* CMU_ISP */
 
-static unsigned long isp_clk_regs[] __initdata = {
+static const unsigned long isp_clk_regs[] __initconst = {
 	MUX_SEL_ISP0,
 	MUX_SEL_ISP1,
 	DIV_ISP,
@@ -811,14 +811,14 @@ static unsigned long isp_clk_regs[] __initdata = {
 PNAME(mout_isp_400_user_p) = {"fin_pll", "dout_aclk_isp1_400"};
 PNAME(mout_isp_266_user_p)	 = {"fin_pll", "dout_aclk_isp1_266"};
 
-static struct samsung_mux_clock isp_mux_clks[] __initdata = {
+static const struct samsung_mux_clock isp_mux_clks[] __initconst = {
 	MUX(ISP_MOUT_ISP_266_USER, "mout_isp_266_user", mout_isp_266_user_p,
 			MUX_SEL_ISP0, 0, 1),
 	MUX(ISP_MOUT_ISP_400_USER, "mout_isp_400_user", mout_isp_400_user_p,
 			MUX_SEL_ISP0, 4, 1),
 };
 
-static struct samsung_div_clock isp_div_clks[] __initdata = {
+static const struct samsung_div_clock isp_div_clks[] __initconst = {
 	DIV(ISP_DOUT_PCLK_ISP_66, "dout_pclk_isp_66", "mout_kfc",
 			DIV_ISP, 0, 3),
 	DIV(ISP_DOUT_PCLK_ISP_133, "dout_pclk_isp_133", "mout_kfc",
@@ -830,7 +830,7 @@ static struct samsung_div_clock isp_div_clks[] __initdata = {
 	DIV(ISP_DOUT_SCLK_MPWM, "dout_sclk_mpwm", "mout_kfc", DIV_ISP, 20, 2),
 };
 
-static struct samsung_gate_clock isp_gate_clks[] __initdata = {
+static const struct samsung_gate_clock isp_gate_clks[] __initconst = {
 	GATE(ISP_CLK_GIC, "clk_isp_gic", "mout_aclk_isp1_266",
 			EN_IP_ISP0, 15, 0, 0),
 
@@ -914,7 +914,7 @@ CLK_OF_DECLARE(exynos5260_clk_isp, "samsung,exynos5260-clock-isp",
 
 /* CMU_KFC */
 
-static unsigned long kfc_clk_regs[] __initdata = {
+static const unsigned long kfc_clk_regs[] __initconst = {
 	KFC_PLL_LOCK,
 	KFC_PLL_CON0,
 	KFC_PLL_CON1,
@@ -932,13 +932,13 @@ static unsigned long kfc_clk_regs[] __initdata = {
 PNAME(mout_kfc_pll_p) = {"fin_pll", "fout_kfc_pll"};
 PNAME(mout_kfc_p)	 = {"mout_kfc_pll", "dout_media_pll"};
 
-static struct samsung_mux_clock kfc_mux_clks[] __initdata = {
+static const struct samsung_mux_clock kfc_mux_clks[] __initconst = {
 	MUX(KFC_MOUT_KFC_PLL, "mout_kfc_pll", mout_kfc_pll_p,
 			MUX_SEL_KFC0, 0, 1),
 	MUX(KFC_MOUT_KFC, "mout_kfc", mout_kfc_p, MUX_SEL_KFC2, 0, 1),
 };
 
-static struct samsung_div_clock kfc_div_clks[] __initdata = {
+static const struct samsung_div_clock kfc_div_clks[] __initconst = {
 	DIV(KFC_DOUT_KFC1, "dout_kfc1", "mout_kfc", DIV_KFC, 0, 3),
 	DIV(KFC_DOUT_KFC2, "dout_kfc2", "dout_kfc1", DIV_KFC, 4, 3),
 	DIV(KFC_DOUT_KFC_ATCLK, "dout_kfc_atclk", "dout_kfc2", DIV_KFC, 8, 3),
@@ -949,7 +949,7 @@ static struct samsung_div_clock kfc_div_clks[] __initdata = {
 	DIV(KFC_DOUT_KFC_PLL, "dout_kfc_pll", "mout_kfc", DIV_KFC, 24, 3),
 };
 
-static struct samsung_pll_clock kfc_pll_clks[] __initdata = {
+static const struct samsung_pll_clock kfc_pll_clks[] __initconst = {
 	PLL(pll_2550xx, KFC_FOUT_KFC_PLL, "fout_kfc_pll", "fin_pll",
 		KFC_PLL_LOCK, KFC_PLL_CON0,
 		pll2550_24mhz_tbl),
@@ -978,7 +978,7 @@ CLK_OF_DECLARE(exynos5260_clk_kfc, "samsung,exynos5260-clock-kfc",
 
 /* CMU_MFC */
 
-static unsigned long mfc_clk_regs[] __initdata = {
+static const unsigned long mfc_clk_regs[] __initconst = {
 	MUX_SEL_MFC,
 	DIV_MFC,
 	EN_ACLK_MFC,
@@ -991,18 +991,18 @@ static unsigned long mfc_clk_regs[] __initdata = {
 
 PNAME(mout_aclk_mfc_333_user_p) = {"fin_pll", "dout_aclk_mfc_333"};
 
-static struct samsung_mux_clock mfc_mux_clks[] __initdata = {
+static const struct samsung_mux_clock mfc_mux_clks[] __initconst = {
 	MUX(MFC_MOUT_ACLK_MFC_333_USER, "mout_aclk_mfc_333_user",
 			mout_aclk_mfc_333_user_p,
 			MUX_SEL_MFC, 0, 1),
 };
 
-static struct samsung_div_clock mfc_div_clks[] __initdata = {
+static const struct samsung_div_clock mfc_div_clks[] __initconst = {
 	DIV(MFC_DOUT_PCLK_MFC_83, "dout_pclk_mfc_83", "mout_aclk_mfc_333_user",
 			DIV_MFC, 0, 3),
 };
 
-static struct samsung_gate_clock mfc_gate_clks[] __initdata = {
+static const struct samsung_gate_clock mfc_gate_clks[] __initconst = {
 	GATE(MFC_CLK_MFC, "clk_mfc", "mout_aclk_mfc_333_user",
 			EN_IP_MFC, 1, 0, 0),
 	GATE(MFC_CLK_SMMU2_MFCM0, "clk_smmu2_mfcm0", "mout_aclk_mfc_333_user",
@@ -1034,7 +1034,7 @@ CLK_OF_DECLARE(exynos5260_clk_mfc, "samsung,exynos5260-clock-mfc",
 
 /* CMU_MIF */
 
-static unsigned long mif_clk_regs[] __initdata = {
+static const unsigned long mif_clk_regs[] __initconst = {
 	MEM_PLL_LOCK,
 	BUS_PLL_LOCK,
 	MEDIA_PLL_LOCK,
@@ -1076,7 +1076,7 @@ PNAME(mout_mif_drex2x_p) = {"dout_mem_pll", "dout_bus_pll"};
 PNAME(mout_clkm_phy_p) = {"mout_mif_drex", "dout_media_pll"};
 PNAME(mout_clk2x_phy_p) = {"mout_mif_drex2x", "dout_media_pll"};
 
-static struct samsung_mux_clock mif_mux_clks[] __initdata = {
+static const struct samsung_mux_clock mif_mux_clks[] __initconst = {
 	MUX(MIF_MOUT_MEM_PLL, "mout_mem_pll", mout_mem_pll_p,
 			MUX_SEL_MIF, 0, 1),
 	MUX(MIF_MOUT_BUS_PLL, "mout_bus_pll", mout_bus_pll_p,
@@ -1093,7 +1093,7 @@ static struct samsung_mux_clock mif_mux_clks[] __initdata = {
 			MUX_SEL_MIF, 24, 1),
 };
 
-static struct samsung_div_clock mif_div_clks[] __initdata = {
+static const struct samsung_div_clock mif_div_clks[] __initconst = {
 	DIV(MIF_DOUT_MEDIA_PLL, "dout_media_pll", "mout_media_pll",
 			DIV_MIF, 0, 3),
 	DIV(MIF_DOUT_MEM_PLL, "dout_mem_pll", "mout_mem_pll",
@@ -1112,7 +1112,7 @@ static struct samsung_div_clock mif_div_clks[] __initdata = {
 			DIV_MIF, 28, 4),
 };
 
-static struct samsung_gate_clock mif_gate_clks[] __initdata = {
+static const struct samsung_gate_clock mif_gate_clks[] __initconst = {
 	GATE(MIF_CLK_LPDDR3PHY_WRAP0, "clk_lpddr3phy_wrap0", "dout_clk2x_phy",
 			EN_IP_MIF, 12, CLK_IGNORE_UNUSED, 0),
 	GATE(MIF_CLK_LPDDR3PHY_WRAP1, "clk_lpddr3phy_wrap1", "dout_clk2x_phy",
@@ -1146,7 +1146,7 @@ static struct samsung_gate_clock mif_gate_clks[] __initdata = {
 			CLK_IGNORE_UNUSED | CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_pll_clock mif_pll_clks[] __initdata = {
+static const struct samsung_pll_clock mif_pll_clks[] __initconst = {
 	PLL(pll_2550xx, MIF_FOUT_MEM_PLL, "fout_mem_pll", "fin_pll",
 		MEM_PLL_LOCK, MEM_PLL_CON0,
 		pll2550_24mhz_tbl),
@@ -1183,7 +1183,7 @@ CLK_OF_DECLARE(exynos5260_clk_mif, "samsung,exynos5260-clock-mif",
 
 /* CMU_PERI */
 
-static unsigned long peri_clk_regs[] __initdata = {
+static const unsigned long peri_clk_regs[] __initconst = {
 	MUX_SEL_PERI,
 	MUX_SEL_PERI1,
 	DIV_PERI,
@@ -1219,7 +1219,7 @@ PNAME(mout_sclk_i2scod_p) = {"ioclk_i2s_cdclk", "fin_pll", "dout_aclk_peri_aud",
 PNAME(mout_sclk_spdif_p) = {"ioclk_spdif_extclk", "fin_pll",
 			"dout_aclk_peri_aud", "phyclk_hdmi_phy_ref_cko"};
 
-static struct samsung_mux_clock peri_mux_clks[] __initdata = {
+static const struct samsung_mux_clock peri_mux_clks[] __initconst = {
 	MUX(PERI_MOUT_SCLK_PCM, "mout_sclk_pcm", mout_sclk_pcm_p,
 			MUX_SEL_PERI1, 4, 2),
 	MUX(PERI_MOUT_SCLK_I2SCOD, "mout_sclk_i2scod", mout_sclk_i2scod_p,
@@ -1228,12 +1228,12 @@ static struct samsung_mux_clock peri_mux_clks[] __initdata = {
 			MUX_SEL_PERI1, 20, 2),
 };
 
-static struct samsung_div_clock peri_div_clks[] __initdata = {
+static const struct samsung_div_clock peri_div_clks[] __initconst = {
 	DIV(PERI_DOUT_PCM, "dout_pcm", "mout_sclk_pcm", DIV_PERI, 0, 8),
 	DIV(PERI_DOUT_I2S, "dout_i2s", "mout_sclk_i2scod", DIV_PERI, 8, 6),
 };
 
-static struct samsung_gate_clock peri_gate_clks[] __initdata = {
+static const struct samsung_gate_clock peri_gate_clks[] __initconst = {
 	GATE(PERI_SCLK_PCM1, "sclk_pcm1", "dout_pcm", EN_SCLK_PERI, 0,
 			CLK_SET_RATE_PARENT, 0),
 	GATE(PERI_SCLK_I2S, "sclk_i2s", "dout_i2s", EN_SCLK_PERI, 1,
@@ -1389,7 +1389,7 @@ CLK_OF_DECLARE(exynos5260_clk_peri, "samsung,exynos5260-clock-peri",
 
 /* CMU_TOP */
 
-static unsigned long top_clk_regs[] __initdata = {
+static const unsigned long top_clk_regs[] __initconst = {
 	DISP_PLL_LOCK,
 	AUD_PLL_LOCK,
 	DISP_PLL_CON0,
@@ -1430,7 +1430,7 @@ static unsigned long top_clk_regs[] __initdata = {
 };
 
 /* fixed rate clocks generated inside the soc */
-static struct samsung_fixed_rate_clock fixed_rate_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock fixed_rate_clks[] __initconst = {
 	FRATE(PHYCLK_DPTX_PHY_CH3_TXD_CLK, "phyclk_dptx_phy_ch3_txd_clk", NULL,
 			0, 270000000),
 	FRATE(PHYCLK_DPTX_PHY_CH2_TXD_CLK, "phyclk_dptx_phy_ch2_txd_clk", NULL,
@@ -1513,7 +1513,7 @@ PNAME(mout_sclk_fsys_mmc1_sdclkin_b_p) = {"mout_sclk_fsys_mmc1_sdclkin_a",
 PNAME(mout_sclk_fsys_mmc2_sdclkin_b_p) = {"mout_sclk_fsys_mmc2_sdclkin_a",
 			"mout_mediatop_pll_user"};
 
-static struct samsung_mux_clock top_mux_clks[] __initdata = {
+static const struct samsung_mux_clock top_mux_clks[] __initconst = {
 	MUX(TOP_MOUT_MEDIATOP_PLL_USER, "mout_mediatop_pll_user",
 			mout_mediatop_pll_user_p,
 			MUX_SEL_TOP_PLL0, 0, 1),
@@ -1673,7 +1673,7 @@ static struct samsung_mux_clock top_mux_clks[] __initdata = {
 			MUX_SEL_TOP_GSCL, 20, 1),
 };
 
-static struct samsung_div_clock top_div_clks[] __initdata = {
+static const struct samsung_div_clock top_div_clks[] __initconst = {
 	DIV(TOP_DOUT_ACLK_G2D_333, "dout_aclk_g2d_333", "mout_aclk_g2d_333",
 			DIV_TOP_G2D_MFC, 0, 3),
 	DIV(TOP_DOUT_ACLK_MFC_333, "dout_aclk_mfc_333", "mout_aclk_mfc_333",
@@ -1794,7 +1794,7 @@ static struct samsung_div_clock top_div_clks[] __initdata = {
 
 };
 
-static struct samsung_gate_clock top_gate_clks[] __initdata = {
+static const struct samsung_gate_clock top_gate_clks[] __initconst = {
 	GATE(TOP_SCLK_MMC0, "sclk_fsys_mmc0_sdclkin",
 			"dout_sclk_fsys_mmc0_sdclkin_b",
 			EN_SCLK_TOP, 7, CLK_SET_RATE_PARENT, 0),
@@ -1809,7 +1809,7 @@ static struct samsung_gate_clock top_gate_clks[] __initdata = {
 			CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_pll_clock top_pll_clks[] __initdata = {
+static const struct samsung_pll_clock top_pll_clks[] __initconst = {
 	PLL(pll_2550xx, TOP_FOUT_DISP_PLL, "fout_disp_pll", "fin_pll",
 		DISP_PLL_LOCK, DISP_PLL_CON0,
 		pll2550_24mhz_tbl),
diff --git a/drivers/clk/samsung/clk-exynos5410.c b/drivers/clk/samsung/clk-exynos5410.c
index d5d5dcabc4a9..54ec486a5e45 100644
--- a/drivers/clk/samsung/clk-exynos5410.c
+++ b/drivers/clk/samsung/clk-exynos5410.c
@@ -31,11 +31,14 @@
 #define SRC_CPU			0x200
 #define DIV_CPU0		0x500
 #define SRC_CPERI1		0x4204
+#define GATE_IP_G2D		0x8800
 #define DIV_TOP0		0x10510
 #define DIV_TOP1		0x10514
+#define DIV_FSYS0		0x10548
 #define DIV_FSYS1		0x1054c
 #define DIV_FSYS2		0x10550
 #define DIV_PERIC0		0x10558
+#define DIV_PERIC3		0x10564
 #define SRC_TOP0		0x10210
 #define SRC_TOP1		0x10214
 #define SRC_TOP2		0x10218
@@ -44,6 +47,8 @@
 #define SRC_MASK_FSYS		0x10340
 #define SRC_MASK_PERIC0		0x10350
 #define GATE_BUS_FSYS0		0x10740
+#define GATE_TOP_SCLK_FSYS	0x10840
+#define GATE_TOP_SCLK_PERIC	0x10850
 #define GATE_IP_FSYS		0x10944
 #define GATE_IP_PERIC		0x10950
 #define GATE_IP_PERIS		0x10960
@@ -71,12 +76,13 @@ PNAME(mout_kfc_p)	= { "mout_kpll", "sclk_mpll", };
 PNAME(mpll_user_p)	= { "fin_pll", "sclk_mpll", };
 PNAME(bpll_user_p)	= { "fin_pll", "sclk_bpll", };
 PNAME(mpll_bpll_p)	= { "sclk_mpll_muxed", "sclk_bpll_muxed", };
+PNAME(sclk_mpll_bpll_p)	= { "sclk_mpll_bpll", "fin_pll", };
 
 PNAME(group2_p)		= { "fin_pll", "fin_pll", "none", "none",
 			"none", "none", "sclk_mpll_bpll",
 			 "none", "none", "sclk_cpll" };
 
-static struct samsung_mux_clock exynos5410_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos5410_mux_clks[] __initconst = {
 	MUX(0, "mout_apll", apll_p, SRC_CPU, 0, 1),
 	MUX(0, "mout_cpu", mout_cpu_p, SRC_CPU, 16, 1),
 
@@ -96,16 +102,20 @@ static struct samsung_mux_clock exynos5410_mux_clks[] __initdata = {
 	MUX(0, "mout_mmc0", group2_p, SRC_FSYS, 0, 4),
 	MUX(0, "mout_mmc1", group2_p, SRC_FSYS, 4, 4),
 	MUX(0, "mout_mmc2", group2_p, SRC_FSYS, 8, 4),
+	MUX(0, "mout_usbd300", sclk_mpll_bpll_p, SRC_FSYS, 28, 1),
+	MUX(0, "mout_usbd301", sclk_mpll_bpll_p, SRC_FSYS, 29, 1),
 
 	MUX(0, "mout_uart0", group2_p, SRC_PERIC0, 0, 4),
 	MUX(0, "mout_uart1", group2_p, SRC_PERIC0, 4, 4),
 	MUX(0, "mout_uart2", group2_p, SRC_PERIC0, 8, 4),
+	MUX(0, "mout_uart3", group2_p, SRC_PERIC0, 12, 4),
+	MUX(0, "mout_pwm", group2_p, SRC_PERIC0, 24, 4),
 
 	MUX(0, "mout_aclk200", mpll_bpll_p, SRC_TOP0, 12, 1),
 	MUX(0, "mout_aclk400", mpll_bpll_p, SRC_TOP0, 20, 1),
 };
 
-static struct samsung_div_clock exynos5410_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos5410_div_clks[] __initconst = {
 	DIV(0, "div_arm", "mout_cpu", DIV_CPU0, 0, 3),
 	DIV(0, "div_arm2", "div_arm", DIV_CPU0, 28, 3),
 
@@ -121,6 +131,11 @@ static struct samsung_div_clock exynos5410_div_clks[] __initdata = {
 	DIV(0, "aclk66_pre", "sclk_mpll_muxed", DIV_TOP1, 24, 3),
 	DIV(0, "aclk66", "aclk66_pre", DIV_TOP0, 0, 3),
 
+	DIV(0, "dout_usbphy300", "mout_usbd300", DIV_FSYS0, 16, 4),
+	DIV(0, "dout_usbphy301", "mout_usbd301", DIV_FSYS0, 20, 4),
+	DIV(0, "dout_usbd300", "mout_usbd300", DIV_FSYS0, 24, 4),
+	DIV(0, "dout_usbd301", "mout_usbd301", DIV_FSYS0, 28, 4),
+
 	DIV(0, "div_mmc0", "mout_mmc0", DIV_FSYS1, 0, 4),
 	DIV(0, "div_mmc1", "mout_mmc1", DIV_FSYS1, 16, 4),
 	DIV(0, "div_mmc2", "mout_mmc2", DIV_FSYS2, 0, 4),
@@ -137,12 +152,19 @@ static struct samsung_div_clock exynos5410_div_clks[] __initdata = {
 	DIV(0, "div_uart2", "mout_uart2", DIV_PERIC0, 8, 4),
 	DIV(0, "div_uart3", "mout_uart3", DIV_PERIC0, 12, 4),
 
+	DIV(0, "dout_pwm", "mout_pwm", DIV_PERIC3, 0, 4),
+
 	DIV(0, "aclk200", "mout_aclk200", DIV_TOP0, 12, 3),
+	DIV(0, "aclk266", "mpll_user_p", DIV_TOP0, 16, 3),
 	DIV(0, "aclk400", "mout_aclk400", DIV_TOP0, 24, 3),
 };
 
-static struct samsung_gate_clock exynos5410_gate_clks[] __initdata = {
+static const struct samsung_gate_clock exynos5410_gate_clks[] __initconst = {
+	GATE(CLK_SSS, "sss", "aclk266", GATE_IP_G2D, 2, 0, 0),
 	GATE(CLK_MCT, "mct", "aclk66", GATE_IP_PERIS, 18, 0, 0),
+	GATE(CLK_WDT, "wdt", "aclk66", GATE_IP_PERIS, 19, 0, 0),
+	GATE(CLK_RTC, "rtc", "aclk66", GATE_IP_PERIS, 20, 0, 0),
+	GATE(CLK_TMU, "tmu", "aclk66", GATE_IP_PERIS, 21, 0, 0),
 
 	GATE(CLK_SCLK_MMC0, "sclk_mmc0", "div_mmc_pre0",
 			SRC_MASK_FSYS, 0, CLK_SET_RATE_PARENT, 0),
@@ -155,9 +177,31 @@ static struct samsung_gate_clock exynos5410_gate_clks[] __initdata = {
 	GATE(CLK_MMC1, "sdmmc1", "aclk200", GATE_BUS_FSYS0, 13, 0, 0),
 	GATE(CLK_MMC2, "sdmmc2", "aclk200", GATE_BUS_FSYS0, 14, 0, 0),
 
+	GATE(CLK_SCLK_USBPHY301, "sclk_usbphy301", "dout_usbphy301",
+	     GATE_TOP_SCLK_FSYS, 7, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_USBPHY300, "sclk_usbphy300", "dout_usbphy300",
+	     GATE_TOP_SCLK_FSYS, 8, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_USBD300, "sclk_usbd300", "dout_usbd300",
+	     GATE_TOP_SCLK_FSYS, 9, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_USBD301, "sclk_usbd301", "dout_usbd301",
+	     GATE_TOP_SCLK_FSYS, 10, CLK_SET_RATE_PARENT, 0),
+
+	GATE(CLK_SCLK_PWM, "sclk_pwm", "dout_pwm",
+	     GATE_TOP_SCLK_PERIC, 11, CLK_SET_RATE_PARENT, 0),
+
 	GATE(CLK_UART0, "uart0", "aclk66", GATE_IP_PERIC, 0, 0, 0),
 	GATE(CLK_UART1, "uart1", "aclk66", GATE_IP_PERIC, 1, 0, 0),
 	GATE(CLK_UART2, "uart2", "aclk66", GATE_IP_PERIC, 2, 0, 0),
+	GATE(CLK_UART3, "uart3", "aclk66", GATE_IP_PERIC, 3, 0, 0),
+	GATE(CLK_I2C0, "i2c0", "aclk66", GATE_IP_PERIC, 6, 0, 0),
+	GATE(CLK_I2C1, "i2c1", "aclk66", GATE_IP_PERIC, 7, 0, 0),
+	GATE(CLK_I2C2, "i2c2", "aclk66", GATE_IP_PERIC, 8, 0, 0),
+	GATE(CLK_I2C3, "i2c3", "aclk66", GATE_IP_PERIC, 9, 0, 0),
+	GATE(CLK_USI0, "usi0", "aclk66", GATE_IP_PERIC, 10, 0, 0),
+	GATE(CLK_USI1, "usi1", "aclk66", GATE_IP_PERIC, 11, 0, 0),
+	GATE(CLK_USI2, "usi2", "aclk66", GATE_IP_PERIC, 12, 0, 0),
+	GATE(CLK_USI3, "usi3", "aclk66", GATE_IP_PERIC, 13, 0, 0),
+	GATE(CLK_PWM, "pwm", "aclk66", GATE_IP_PERIC, 24, 0, 0),
 
 	GATE(CLK_SCLK_UART0, "sclk_uart0", "div_uart0",
 			SRC_MASK_PERIC0, 0, CLK_SET_RATE_PARENT, 0),
@@ -165,9 +209,15 @@ static struct samsung_gate_clock exynos5410_gate_clks[] __initdata = {
 			SRC_MASK_PERIC0, 4, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_UART2, "sclk_uart2", "div_uart2",
 			SRC_MASK_PERIC0, 8, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_SCLK_UART3, "sclk_uart3", "div_uart3",
+			SRC_MASK_PERIC0, 12, CLK_SET_RATE_PARENT, 0),
+
+	GATE(CLK_USBH20, "usbh20", "aclk200_fsys", GATE_IP_FSYS, 18, 0, 0),
+	GATE(CLK_USBD300, "usbd300", "aclk200_fsys", GATE_IP_FSYS, 19, 0, 0),
+	GATE(CLK_USBD301, "usbd301", "aclk200_fsys", GATE_IP_FSYS, 20, 0, 0),
 };
 
-static struct samsung_pll_clock exynos5410_plls[nr_plls] __initdata = {
+static const struct samsung_pll_clock exynos5410_plls[nr_plls] __initconst = {
 	[apll] = PLL(pll_35xx, CLK_FOUT_APLL, "fout_apll", "fin_pll", APLL_LOCK,
 		APLL_CON0, NULL),
 	[cpll] = PLL(pll_35xx, CLK_FOUT_CPLL, "fout_cpll", "fin_pll", CPLL_LOCK,
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index 92382cef9f90..bb196ca21a77 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -160,7 +160,7 @@ static struct samsung_clk_reg_dump *exynos5800_save;
  * list of controller registers to be saved and restored during a
  * suspend/resume cycle.
  */
-static unsigned long exynos5x_clk_regs[] __initdata = {
+static const unsigned long exynos5x_clk_regs[] __initconst = {
 	SRC_CPU,
 	DIV_CPU0,
 	DIV_CPU1,
@@ -248,7 +248,7 @@ static unsigned long exynos5x_clk_regs[] __initdata = {
 	DIV_KFC0,
 };
 
-static unsigned long exynos5800_clk_regs[] __initdata = {
+static const unsigned long exynos5800_clk_regs[] __initconst = {
 	SRC_TOP8,
 	SRC_TOP9,
 	SRC_CAM,
@@ -306,7 +306,7 @@ static struct syscore_ops exynos5420_clk_syscore_ops = {
 	.resume = exynos5420_clk_resume,
 };
 
-static void exynos5420_clk_sleep_init(void)
+static void __init exynos5420_clk_sleep_init(void)
 {
 	exynos5x_save = samsung_clk_alloc_reg_dump(exynos5x_clk_regs,
 					ARRAY_SIZE(exynos5x_clk_regs));
@@ -333,7 +333,7 @@ err_soc:
 	return;
 }
 #else
-static void exynos5420_clk_sleep_init(void) {}
+static void __init exynos5420_clk_sleep_init(void) {}
 #endif
 
 /* list of all parent clocks */
@@ -484,7 +484,7 @@ static struct samsung_fixed_rate_clock
 };
 
 /* fixed rate clocks generated inside the soc */
-static struct samsung_fixed_rate_clock exynos5x_fixed_rate_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock exynos5x_fixed_rate_clks[] __initconst = {
 	FRATE(CLK_SCLK_HDMIPHY, "sclk_hdmiphy", NULL, 0, 24000000),
 	FRATE(0, "sclk_pwi", NULL, 0, 24000000),
 	FRATE(0, "sclk_usbh20", NULL, 0, 48000000),
@@ -492,19 +492,19 @@ static struct samsung_fixed_rate_clock exynos5x_fixed_rate_clks[] __initdata = {
 	FRATE(0, "sclk_usbh20_scan_clk", NULL, 0, 480000000),
 };
 
-static struct samsung_fixed_factor_clock
-		exynos5x_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock
+		exynos5x_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "ff_hsic_12m", "fin_pll", 1, 2, 0),
 	FFACTOR(0, "ff_sw_aclk66", "mout_sw_aclk66", 1, 2, 0),
 };
 
-static struct samsung_fixed_factor_clock
-		exynos5800_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock
+		exynos5800_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "ff_dout_epll2", "mout_sclk_epll", 1, 2, 0),
 	FFACTOR(0, "ff_dout_spll2", "mout_sclk_spll", 1, 2, 0),
 };
 
-static struct samsung_mux_clock exynos5800_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos5800_mux_clks[] __initconst = {
 	MUX(0, "mout_aclk400_isp", mout_group3_5800_p, SRC_TOP0, 0, 3),
 	MUX(0, "mout_aclk400_mscl", mout_group3_5800_p, SRC_TOP0, 4, 3),
 	MUX(0, "mout_aclk400_wcore", mout_group2_5800_p, SRC_TOP0, 16, 3),
@@ -553,7 +553,7 @@ static struct samsung_mux_clock exynos5800_mux_clks[] __initdata = {
 	MUX(0, "mout_fimd1", mout_group2_p, SRC_DISP10, 4, 3),
 };
 
-static struct samsung_div_clock exynos5800_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos5800_div_clks[] __initconst = {
 	DIV(CLK_DOUT_ACLK400_WCORE, "dout_aclk400_wcore",
 			"mout_aclk400_wcore", DIV_TOP0, 16, 3),
 	DIV(0, "dout_aclk550_cam", "mout_aclk550_cam",
@@ -569,14 +569,14 @@ static struct samsung_div_clock exynos5800_div_clks[] __initdata = {
 	DIV(0, "dout_sclk_sw", "sclk_spll", DIV_TOP9, 24, 6),
 };
 
-static struct samsung_gate_clock exynos5800_gate_clks[] __initdata = {
+static const struct samsung_gate_clock exynos5800_gate_clks[] __initconst = {
 	GATE(CLK_ACLK550_CAM, "aclk550_cam", "mout_user_aclk550_cam",
 				GATE_BUS_TOP, 24, 0, 0),
 	GATE(CLK_ACLK432_SCALER, "aclk432_scaler", "mout_user_aclk432_scaler",
 				GATE_BUS_TOP, 27, 0, 0),
 };
 
-static struct samsung_mux_clock exynos5420_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos5420_mux_clks[] __initconst = {
 	MUX(0, "sclk_bpll", mout_bpll_p, TOP_SPARE2, 0, 1),
 	MUX(0, "mout_aclk400_wcore_bpll", mout_aclk400_wcore_bpll_p,
 				TOP_SPARE2, 4, 1),
@@ -606,12 +606,12 @@ static struct samsung_mux_clock exynos5420_mux_clks[] __initdata = {
 	MUX(0, "mout_fimd1", mout_group3_p, SRC_DISP10, 4, 1),
 };
 
-static struct samsung_div_clock exynos5420_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos5420_div_clks[] __initconst = {
 	DIV(CLK_DOUT_ACLK400_WCORE, "dout_aclk400_wcore",
 			"mout_aclk400_wcore_bpll", DIV_TOP0, 16, 3),
 };
 
-static struct samsung_mux_clock exynos5x_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos5x_mux_clks[] __initconst = {
 	MUX(0, "mout_user_pclk66_gpio", mout_user_pclk66_gpio_p,
 			SRC_TOP7, 4, 1),
 	MUX(0, "mout_mspll_kfc", mout_mspll_cpu_p, SRC_TOP7, 8, 2),
@@ -778,7 +778,7 @@ static struct samsung_mux_clock exynos5x_mux_clks[] __initdata = {
 	MUX(0, "mout_isp_sensor", mout_group2_p, SRC_ISP, 28, 3),
 };
 
-static struct samsung_div_clock exynos5x_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos5x_div_clks[] __initconst = {
 	DIV(0, "div_arm", "mout_cpu", DIV_CPU0, 0, 3),
 	DIV(0, "sclk_apll", "mout_apll", DIV_CPU0, 24, 3),
 	DIV(0, "armclk2", "div_arm", DIV_CPU0, 28, 3),
@@ -911,7 +911,7 @@ static struct samsung_div_clock exynos5x_div_clks[] __initdata = {
 			CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_gate_clock exynos5x_gate_clks[] __initdata = {
+static const struct samsung_gate_clock exynos5x_gate_clks[] __initconst = {
 	/* G2D */
 	GATE(CLK_MDMA0, "mdma0", "aclk266_g2d", GATE_IP_G2D, 1, 0, 0),
 	GATE(CLK_SSS, "sss", "aclk266_g2d", GATE_IP_G2D, 2, 0, 0),
@@ -946,7 +946,7 @@ static struct samsung_gate_clock exynos5x_gate_clks[] __initdata = {
 			GATE_BUS_TOP, 13, 0, 0),
 	GATE(0, "aclk166", "mout_user_aclk166",
 			GATE_BUS_TOP, 14, CLK_IGNORE_UNUSED, 0),
-	GATE(0, "aclk333", "mout_user_aclk333",
+	GATE(CLK_ACLK333, "aclk333", "mout_user_aclk333",
 			GATE_BUS_TOP, 15, CLK_IGNORE_UNUSED, 0),
 	GATE(0, "aclk400_isp", "mout_user_aclk400_isp",
 			GATE_BUS_TOP, 16, 0, 0),
@@ -1219,7 +1219,7 @@ static struct samsung_gate_clock exynos5x_gate_clks[] __initdata = {
 	GATE(CLK_G3D, "g3d", "mout_user_aclk_g3d", GATE_IP_G3D, 9, 0, 0),
 };
 
-static const struct samsung_pll_rate_table exynos5420_pll2550x_24mhz_tbl[] = {
+static const struct samsung_pll_rate_table exynos5420_pll2550x_24mhz_tbl[] __initconst = {
 	PLL_35XX_RATE(2000000000, 250, 3, 0),
 	PLL_35XX_RATE(1900000000, 475, 6, 0),
 	PLL_35XX_RATE(1800000000, 225, 3, 0),
@@ -1356,8 +1356,6 @@ static void __init exynos5x_clk_init(struct device_node *np,
 	exynos5x_soc = soc;
 
 	ctx = samsung_clk_init(np, reg_base, CLK_NR_CLKS);
-	if (!ctx)
-		panic("%s: unable to allocate context.\n", __func__);
 
 	samsung_clk_of_register_fixed_ext(ctx, exynos5x_fixed_rate_ext_clks,
 			ARRAY_SIZE(exynos5x_fixed_rate_ext_clks),
diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c
index 128527b8fbeb..ea1608682d7f 100644
--- a/drivers/clk/samsung/clk-exynos5433.c
+++ b/drivers/clk/samsung/clk-exynos5433.c
@@ -11,10 +11,12 @@
 
 #include <linux/clk-provider.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 
 #include <dt-bindings/clock/exynos5433.h>
 
 #include "clk.h"
+#include "clk-cpu.h"
 #include "clk-pll.h"
 
 /*
@@ -108,7 +110,7 @@
 #define ENABLE_CMU_TOP			0x0c00
 #define ENABLE_CMU_TOP_DIV_STAT		0x0c04
 
-static unsigned long top_clk_regs[] __initdata = {
+static const unsigned long top_clk_regs[] __initconst = {
 	ISP_PLL_LOCK,
 	AUD_PLL_LOCK,
 	ISP_PLL_CON0,
@@ -218,11 +220,11 @@ PNAME(mout_sclk_audio0_p)	= { "ioclk_audiocdclk0", "oscclk",
 
 PNAME(mout_sclk_hdmi_spdif_p)	= { "sclk_audio1", "ioclk_spdif_extclk", };
 
-static struct samsung_fixed_factor_clock top_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock top_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "oscclk_efuse_common", "oscclk", 1, 1, 0),
 };
 
-static struct samsung_fixed_rate_clock top_fixed_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock top_fixed_clks[] __initconst = {
 	/* Xi2s{0|1}CDCLK input clock for I2S/PCM */
 	FRATE(0, "ioclk_audiocdclk1", NULL, 0, 100000000),
 	FRATE(0, "ioclk_audiocdclk0", NULL, 0, 100000000),
@@ -238,7 +240,7 @@ static struct samsung_fixed_rate_clock top_fixed_clks[] __initdata = {
 	FRATE(0, "ioclk_i2s1_bclk_in", NULL, 0, 12288000),
 };
 
-static struct samsung_mux_clock top_mux_clks[] __initdata = {
+static const struct samsung_mux_clock top_mux_clks[] __initconst = {
 	/* MUX_SEL_TOP0 */
 	MUX(CLK_MOUT_AUD_PLL, "mout_aud_pll", mout_aud_pll_p, MUX_SEL_TOP0,
 			4, 1),
@@ -374,7 +376,7 @@ static struct samsung_mux_clock top_mux_clks[] __initdata = {
 			mout_sclk_hdmi_spdif_p, MUX_SEL_TOP_DISP, 0, 1),
 };
 
-static struct samsung_div_clock top_div_clks[] __initdata = {
+static const struct samsung_div_clock top_div_clks[] __initconst = {
 	/* DIV_TOP0 */
 	DIV(CLK_DIV_ACLK_CAM1_333, "div_aclk_cam1_333", "mout_aclk_cam1_333",
 			DIV_TOP0, 28, 3),
@@ -538,7 +540,7 @@ static struct samsung_div_clock top_div_clks[] __initdata = {
 			DIV_TOP_PERIC4, 0, 4),
 };
 
-static struct samsung_gate_clock top_gate_clks[] __initdata = {
+static const struct samsung_gate_clock top_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_TOP */
 	GATE(CLK_ACLK_G3D_400, "aclk_g3d_400", "div_aclk_g3d_400",
 			ENABLE_ACLK_TOP, 30, 0, 0),
@@ -639,7 +641,7 @@ static struct samsung_gate_clock top_gate_clks[] __initdata = {
 
 	/* ENABLE_SCLK_TOP_FSYS */
 	GATE(CLK_SCLK_PCIE_100_FSYS, "sclk_pcie_100_fsys", "div_sclk_pcie_100",
-			ENABLE_SCLK_TOP_FSYS, 7, 0, 0),
+			ENABLE_SCLK_TOP_FSYS, 7, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_MMC2_FSYS, "sclk_mmc2_fsys", "div_sclk_mmc2_b",
 			ENABLE_SCLK_TOP_FSYS, 6, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_MMC1_FSYS, "sclk_mmc1_fsys", "div_sclk_mmc1_b",
@@ -668,11 +670,14 @@ static struct samsung_gate_clock top_gate_clks[] __initdata = {
 	GATE(CLK_SCLK_PCM1_PERIC, "sclk_pcm1_peric", "div_sclk_pcm1",
 			ENABLE_SCLK_TOP_PERIC, 7, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_UART2_PERIC, "sclk_uart2_peric", "div_sclk_uart2",
-			ENABLE_SCLK_TOP_PERIC, 5, CLK_SET_RATE_PARENT, 0),
+			ENABLE_SCLK_TOP_PERIC, 5, CLK_SET_RATE_PARENT |
+			CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_UART1_PERIC, "sclk_uart1_peric", "div_sclk_uart1",
-			ENABLE_SCLK_TOP_PERIC, 4, CLK_SET_RATE_PARENT, 0),
+			ENABLE_SCLK_TOP_PERIC, 4, CLK_SET_RATE_PARENT |
+			CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_UART0_PERIC, "sclk_uart0_peric", "div_sclk_uart0",
-			ENABLE_SCLK_TOP_PERIC, 3, CLK_SET_RATE_PARENT, 0),
+			ENABLE_SCLK_TOP_PERIC, 3, CLK_SET_RATE_PARENT |
+			CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_SPI2_PERIC, "sclk_spi2_peric", "div_sclk_spi2_b",
 			ENABLE_SCLK_TOP_PERIC, 2, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_SPI1_PERIC, "sclk_spi1_peric", "div_sclk_spi1_b",
@@ -693,7 +698,7 @@ static struct samsung_gate_clock top_gate_clks[] __initdata = {
  * ATLAS_PLL & APOLLO_PLL & MEM0_PLL & MEM1_PLL & BUS_PLL & MFC_PLL
  * & MPHY_PLL & G3D_PLL & DISP_PLL & ISP_PLL
  */
-static struct samsung_pll_rate_table exynos5443_pll_rates[] = {
+static const struct samsung_pll_rate_table exynos5443_pll_rates[] __initconst = {
 	PLL_35XX_RATE(2500000000U, 625, 6,  0),
 	PLL_35XX_RATE(2400000000U, 500, 5,  0),
 	PLL_35XX_RATE(2300000000U, 575, 6,  0),
@@ -744,7 +749,7 @@ static struct samsung_pll_rate_table exynos5443_pll_rates[] = {
 };
 
 /* AUD_PLL */
-static struct samsung_pll_rate_table exynos5443_aud_pll_rates[] = {
+static const struct samsung_pll_rate_table exynos5443_aud_pll_rates[] __initconst = {
 	PLL_36XX_RATE(400000000U, 200, 3, 2,      0),
 	PLL_36XX_RATE(393216000U, 197, 3, 2, -25690),
 	PLL_36XX_RATE(384000000U, 128, 2, 2,      0),
@@ -757,14 +762,14 @@ static struct samsung_pll_rate_table exynos5443_aud_pll_rates[] = {
 	{ /* sentinel */ }
 };
 
-static struct samsung_pll_clock top_pll_clks[] __initdata = {
+static const struct samsung_pll_clock top_pll_clks[] __initconst = {
 	PLL(pll_35xx, CLK_FOUT_ISP_PLL, "fout_isp_pll", "oscclk",
 		ISP_PLL_LOCK, ISP_PLL_CON0, exynos5443_pll_rates),
 	PLL(pll_36xx, CLK_FOUT_AUD_PLL, "fout_aud_pll", "oscclk",
 		AUD_PLL_LOCK, AUD_PLL_CON0, exynos5443_aud_pll_rates),
 };
 
-static struct samsung_cmu_info top_cmu_info __initdata = {
+static const struct samsung_cmu_info top_cmu_info __initconst = {
 	.pll_clks		= top_pll_clks,
 	.nr_pll_clks		= ARRAY_SIZE(top_pll_clks),
 	.mux_clks		= top_mux_clks,
@@ -800,7 +805,7 @@ CLK_OF_DECLARE(exynos5433_cmu_top, "samsung,exynos5433-cmu-top",
 #define DIV_CPIF		0x0600
 #define ENABLE_SCLK_CPIF	0x0a00
 
-static unsigned long cpif_clk_regs[] __initdata = {
+static const unsigned long cpif_clk_regs[] __initconst = {
 	MPHY_PLL_LOCK,
 	MPHY_PLL_CON0,
 	MPHY_PLL_CON1,
@@ -813,32 +818,32 @@ static unsigned long cpif_clk_regs[] __initdata = {
 /* list of all parent clock list */
 PNAME(mout_mphy_pll_p)		= { "oscclk", "fout_mphy_pll", };
 
-static struct samsung_pll_clock cpif_pll_clks[] __initdata = {
+static const struct samsung_pll_clock cpif_pll_clks[] __initconst = {
 	PLL(pll_35xx, CLK_FOUT_MPHY_PLL, "fout_mphy_pll", "oscclk",
 		MPHY_PLL_LOCK, MPHY_PLL_CON0, exynos5443_pll_rates),
 };
 
-static struct samsung_mux_clock cpif_mux_clks[] __initdata = {
+static const struct samsung_mux_clock cpif_mux_clks[] __initconst = {
 	/* MUX_SEL_CPIF0 */
 	MUX(CLK_MOUT_MPHY_PLL, "mout_mphy_pll", mout_mphy_pll_p, MUX_SEL_CPIF0,
 			0, 1),
 };
 
-static struct samsung_div_clock cpif_div_clks[] __initdata = {
+static const struct samsung_div_clock cpif_div_clks[] __initconst = {
 	/* DIV_CPIF */
 	DIV(CLK_DIV_SCLK_MPHY, "div_sclk_mphy", "mout_mphy_pll", DIV_CPIF,
 			0, 6),
 };
 
-static struct samsung_gate_clock cpif_gate_clks[] __initdata = {
+static const struct samsung_gate_clock cpif_gate_clks[] __initconst = {
 	/* ENABLE_SCLK_CPIF */
 	GATE(CLK_SCLK_MPHY_PLL, "sclk_mphy_pll", "mout_mphy_pll",
-			ENABLE_SCLK_CPIF, 9, 0, 0),
+			ENABLE_SCLK_CPIF, 9, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_UFS_MPHY, "sclk_ufs_mphy", "div_sclk_mphy",
 			ENABLE_SCLK_CPIF, 4, 0, 0),
 };
 
-static struct samsung_cmu_info cpif_cmu_info __initdata = {
+static const struct samsung_cmu_info cpif_cmu_info __initconst = {
 	.pll_clks		= cpif_pll_clks,
 	.nr_pll_clks		= ARRAY_SIZE(cpif_pll_clks),
 	.mux_clks		= cpif_mux_clks,
@@ -939,7 +944,7 @@ CLK_OF_DECLARE(exynos5433_cmu_cpif, "samsung,exynos5433-cmu-cpif",
 #define PAUSE				0x1008
 #define DDRPHY_LOCK_CTRL		0x100c
 
-static unsigned long mif_clk_regs[] __initdata = {
+static const unsigned long mif_clk_regs[] __initconst = {
 	MEM0_PLL_LOCK,
 	MEM1_PLL_LOCK,
 	BUS_PLL_LOCK,
@@ -1004,7 +1009,7 @@ static unsigned long mif_clk_regs[] __initdata = {
 	DDRPHY_LOCK_CTRL,
 };
 
-static struct samsung_pll_clock mif_pll_clks[] __initdata = {
+static const struct samsung_pll_clock mif_pll_clks[] __initconst = {
 	PLL(pll_35xx, CLK_FOUT_MEM0_PLL, "fout_mem0_pll", "oscclk",
 		MEM0_PLL_LOCK, MEM0_PLL_CON0, exynos5443_pll_rates),
 	PLL(pll_35xx, CLK_FOUT_MEM1_PLL, "fout_mem1_pll", "oscclk",
@@ -1065,7 +1070,7 @@ PNAME(mout_sclk_decon_tv_vclk_b_p) = { "mout_sclk_decon_tv_vclk_a",
 PNAME(mout_sclk_dsim1_c_p)	= { "mout_sclk_dsim1_b", "sclk_mphy_pll", };
 PNAME(mout_sclk_dsim1_b_p)	= { "mout_sclk_dsim1_a", "mout_mfc_pll_div2",};
 
-static struct samsung_fixed_factor_clock mif_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock mif_fixed_factor_clks[] __initconst = {
 	/* dout_{mfc|bus|mem1|mem0}_pll is half fixed rate from parent mux */
 	FFACTOR(CLK_DOUT_MFC_PLL, "dout_mfc_pll", "mout_mfc_pll", 1, 1, 0),
 	FFACTOR(CLK_DOUT_BUS_PLL, "dout_bus_pll", "mout_bus_pll", 1, 1, 0),
@@ -1073,7 +1078,7 @@ static struct samsung_fixed_factor_clock mif_fixed_factor_clks[] __initdata = {
 	FFACTOR(CLK_DOUT_MEM0_PLL, "dout_mem0_pll", "mout_mem0_pll", 1, 1, 0),
 };
 
-static struct samsung_mux_clock mif_mux_clks[] __initdata = {
+static const struct samsung_mux_clock mif_mux_clks[] __initconst = {
 	/* MUX_SEL_MIF0 */
 	MUX(CLK_MOUT_MFC_PLL_DIV2, "mout_mfc_pll_div2", mout_mfc_pll_div2_p,
 			MUX_SEL_MIF0, 28, 1),
@@ -1169,7 +1174,7 @@ static struct samsung_mux_clock mif_mux_clks[] __initdata = {
 			MUX_SEL_MIF7, 0, 1),
 };
 
-static struct samsung_div_clock mif_div_clks[] __initdata = {
+static const struct samsung_div_clock mif_div_clks[] __initconst = {
 	/* DIV_MIF1 */
 	DIV(CLK_DIV_SCLK_HPM_MIF, "div_sclk_hpm_mif", "div_clk2x_phy",
 			DIV_MIF1, 16, 2),
@@ -1223,7 +1228,7 @@ static struct samsung_div_clock mif_div_clks[] __initdata = {
 			0, 3),
 };
 
-static struct samsung_gate_clock mif_gate_clks[] __initdata = {
+static const struct samsung_gate_clock mif_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_MIF0 */
 	GATE(CLK_CLK2X_PHY1, "clk2k_phy1", "div_clk2x_phy", ENABLE_ACLK_MIF0,
 			19, CLK_IGNORE_UNUSED, 0),
@@ -1440,11 +1445,13 @@ static struct samsung_gate_clock mif_gate_clks[] __initdata = {
 
 	/* ENABLE_PCLK_MIF_SECURE_DREX0_TZ */
 	GATE(CLK_PCLK_DREX0_TZ, "pclk_drex0_tz", "div_aclk_mif_133",
-			ENABLE_PCLK_MIF_SECURE_DREX0_TZ, 0, 0, 0),
+			ENABLE_PCLK_MIF_SECURE_DREX0_TZ, 0,
+			CLK_IGNORE_UNUSED, 0),
 
 	/* ENABLE_PCLK_MIF_SECURE_DREX1_TZ */
 	GATE(CLK_PCLK_DREX1_TZ, "pclk_drex1_tz", "div_aclk_mif_133",
-			ENABLE_PCLK_MIF_SECURE_DREX1_TZ, 0, 0, 0),
+			ENABLE_PCLK_MIF_SECURE_DREX1_TZ, 0,
+			CLK_IGNORE_UNUSED, 0),
 
 	/* ENABLE_PCLK_MIF_SECURE_MONOTONIC_CNT */
 	GATE(CLK_PCLK_MONOTONIC_CNT, "pclk_monotonic_cnt", "div_aclk_mif_133",
@@ -1486,7 +1493,7 @@ static struct samsung_gate_clock mif_gate_clks[] __initdata = {
 			ENABLE_SCLK_MIF, 0, CLK_IGNORE_UNUSED, 0),
 };
 
-static struct samsung_cmu_info mif_cmu_info __initdata = {
+static const struct samsung_cmu_info mif_cmu_info __initconst = {
 	.pll_clks		= mif_pll_clks,
 	.nr_pll_clks		= ARRAY_SIZE(mif_pll_clks),
 	.mux_clks		= mif_mux_clks,
@@ -1522,7 +1529,7 @@ CLK_OF_DECLARE(exynos5433_cmu_mif, "samsung,exynos5433-cmu-mif",
 #define ENABLE_IP_PERIC1		0x0B04
 #define ENABLE_IP_PERIC2		0x0B08
 
-static unsigned long peric_clk_regs[] __initdata = {
+static const unsigned long peric_clk_regs[] __initconst = {
 	DIV_PERIC,
 	ENABLE_ACLK_PERIC,
 	ENABLE_PCLK_PERIC0,
@@ -1533,13 +1540,13 @@ static unsigned long peric_clk_regs[] __initdata = {
 	ENABLE_IP_PERIC2,
 };
 
-static struct samsung_div_clock peric_div_clks[] __initdata = {
+static const struct samsung_div_clock peric_div_clks[] __initconst = {
 	/* DIV_PERIC */
 	DIV(CLK_DIV_SCLK_SCI, "div_sclk_sci", "oscclk", DIV_PERIC, 4, 4),
 	DIV(CLK_DIV_SCLK_SC_IN, "div_sclk_sc_in", "oscclk", DIV_PERIC, 0, 4),
 };
 
-static struct samsung_gate_clock peric_gate_clks[] __initdata = {
+static const struct samsung_gate_clock peric_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_PERIC */
 	GATE(CLK_ACLK_AHB2APB_PERIC2P, "aclk_ahb2apb_peric2p", "aclk_peric_66",
 			ENABLE_ACLK_PERIC, 3, CLK_IGNORE_UNUSED, 0),
@@ -1654,8 +1661,7 @@ static struct samsung_gate_clock peric_gate_clks[] __initdata = {
 	GATE(CLK_SCLK_IOCLK_SPI2, "sclk_ioclk_spi2", "ioclk_spi2_clk_in",
 			ENABLE_SCLK_PERIC, 13, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_IOCLK_SPI1, "sclk_ioclk_spi1", "ioclk_spi1_clk_in",
-			ENABLE_SCLK_PERIC, 12,
-			CLK_IGNORE_UNUSED | CLK_SET_RATE_PARENT, 0),
+			ENABLE_SCLK_PERIC, 12, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_IOCLK_SPI0, "sclk_ioclk_spi0", "ioclk_spi0_clk_in",
 			ENABLE_SCLK_PERIC, 11, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_IOCLK_I2S1_BCLK, "sclk_ioclk_i2s1_bclk",
@@ -1670,18 +1676,21 @@ static struct samsung_gate_clock peric_gate_clks[] __initdata = {
 	GATE(CLK_SCLK_SPI2, "sclk_spi2", "sclk_spi2_peric", ENABLE_SCLK_PERIC,
 			5, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_SPI1, "sclk_spi1", "sclk_spi1_peric", ENABLE_SCLK_PERIC,
-			4, CLK_IGNORE_UNUSED | CLK_SET_RATE_PARENT, 0),
+			4, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_SPI0, "sclk_spi0", "sclk_spi0_peric", ENABLE_SCLK_PERIC,
 			3, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_SCLK_UART2, "sclk_uart2", "sclk_uart2_peric",
-			ENABLE_SCLK_PERIC, 2, CLK_SET_RATE_PARENT, 0),
+			ENABLE_SCLK_PERIC, 2,
+			CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_UART1, "sclk_uart1", "sclk_uart1_peric",
-			ENABLE_SCLK_PERIC, 1, CLK_SET_RATE_PARENT, 0),
+			ENABLE_SCLK_PERIC, 1,
+			CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_UART0, "sclk_uart0", "sclk_uart0_peric",
-			ENABLE_SCLK_PERIC, 0, CLK_SET_RATE_PARENT, 0),
+			ENABLE_SCLK_PERIC, 0,
+			CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED, 0),
 };
 
-static struct samsung_cmu_info peric_cmu_info __initdata = {
+static const struct samsung_cmu_info peric_cmu_info __initconst = {
 	.div_clks		= peric_div_clks,
 	.nr_div_clks		= ARRAY_SIZE(peric_div_clks),
 	.gate_clks		= peric_gate_clks,
@@ -1728,7 +1737,7 @@ CLK_OF_DECLARE(exynos5433_cmu_peric, "samsung,exynos5433-cmu-peric",
 #define ENABLE_IP_PERIS_SECURE_ANTIBRK_CNT		0x0b1c
 #define ENABLE_IP_PERIS_SECURE_OTP_CON			0x0b20
 
-static unsigned long peris_clk_regs[] __initdata = {
+static const unsigned long peris_clk_regs[] __initconst = {
 	ENABLE_ACLK_PERIS,
 	ENABLE_PCLK_PERIS,
 	ENABLE_PCLK_PERIS_SECURE_TZPC,
@@ -1756,7 +1765,7 @@ static unsigned long peris_clk_regs[] __initdata = {
 	ENABLE_IP_PERIS_SECURE_OTP_CON,
 };
 
-static struct samsung_gate_clock peris_gate_clks[] __initdata = {
+static const struct samsung_gate_clock peris_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_PERIS */
 	GATE(CLK_ACLK_AHB2APB_PERIS1P, "aclk_ahb2apb_peris1p", "aclk_peris_66",
 			ENABLE_ACLK_PERIS, 2, CLK_IGNORE_UNUSED, 0),
@@ -1875,7 +1884,7 @@ static struct samsung_gate_clock peris_gate_clks[] __initdata = {
 			ENABLE_SCLK_PERIS_SECURE_OTP_CON, 0, 0, 0),
 };
 
-static struct samsung_cmu_info peris_cmu_info __initdata = {
+static const struct samsung_cmu_info peris_cmu_info __initconst = {
 	.gate_clks		= peris_gate_clks,
 	.nr_gate_clks		= ARRAY_SIZE(peris_gate_clks),
 	.nr_clk_ids		= PERIS_NR_CLK,
@@ -1959,7 +1968,7 @@ PNAME(mout_sclk_mphy_p)
 		= { "mout_sclk_ufs_mphy_user",
 			    "mout_phyclk_lli_mphy_to_ufs_user", };
 
-static unsigned long fsys_clk_regs[] __initdata = {
+static const unsigned long fsys_clk_regs[] __initconst = {
 	MUX_SEL_FSYS0,
 	MUX_SEL_FSYS1,
 	MUX_SEL_FSYS2,
@@ -1980,7 +1989,7 @@ static unsigned long fsys_clk_regs[] __initdata = {
 	ENABLE_IP_FSYS1,
 };
 
-static struct samsung_fixed_rate_clock fsys_fixed_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock fsys_fixed_clks[] __initconst = {
 	/* PHY clocks from USBDRD30_PHY */
 	FRATE(CLK_PHYCLK_USBDRD30_UDRD30_PHYCLOCK_PHY,
 			"phyclk_usbdrd30_udrd30_phyclock_phy", NULL,
@@ -2020,7 +2029,7 @@ static struct samsung_fixed_rate_clock fsys_fixed_clks[] __initdata = {
 			NULL, 0, 26000000),
 };
 
-static struct samsung_mux_clock fsys_mux_clks[] __initdata = {
+static const struct samsung_mux_clock fsys_mux_clks[] __initconst = {
 	/* MUX_SEL_FSYS0 */
 	MUX(CLK_MOUT_SCLK_UFS_MPHY_USER, "mout_sclk_ufs_mphy_user",
 			mout_sclk_ufs_mphy_user_p, MUX_SEL_FSYS0, 4, 1),
@@ -2104,7 +2113,7 @@ static struct samsung_mux_clock fsys_mux_clks[] __initdata = {
 			MUX_SEL_FSYS4, 0, 1),
 };
 
-static struct samsung_gate_clock fsys_gate_clks[] __initdata = {
+static const struct samsung_gate_clock fsys_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_FSYS0 */
 	GATE(CLK_ACLK_PCIE, "aclk_pcie", "mout_aclk_fsys_200_user",
 			ENABLE_ACLK_FSYS0, 13, CLK_IGNORE_UNUSED, 0),
@@ -2138,7 +2147,7 @@ static struct samsung_gate_clock fsys_gate_clks[] __initdata = {
 	GATE(CLK_ACLK_SMMU_PDMA1, "aclk_smmu_pdma1", "mout_aclk_fsys_200_user",
 			ENABLE_ACLK_FSYS1, 25, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_BTS_PCIE, "aclk_bts_pcie", "mout_aclk_fsys_200_user",
-			ENABLE_ACLK_FSYS1, 24, 0, 0),
+			ENABLE_ACLK_FSYS1, 24, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_AXIUS_PDMA1, "aclk_axius_pdma1",
 			"mout_aclk_fsys_200_user", ENABLE_ACLK_FSYS1,
 			22, CLK_IGNORE_UNUSED, 0),
@@ -2185,13 +2194,13 @@ static struct samsung_gate_clock fsys_gate_clks[] __initdata = {
 
 	/* ENABLE_PCLK_FSYS */
 	GATE(CLK_PCLK_PCIE_CTRL, "pclk_pcie_ctrl", "mout_aclk_fsys_200_user",
-			ENABLE_PCLK_FSYS, 17, 0, 0),
+			ENABLE_PCLK_FSYS, 17, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_SMMU_PDMA1, "pclk_smmu_pdma1", "mout_aclk_fsys_200_user",
 			ENABLE_PCLK_FSYS, 16, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_PCIE_PHY, "pclk_pcie_phy", "mout_aclk_fsys_200_user",
-			ENABLE_PCLK_FSYS, 14, 0, 0),
+			ENABLE_PCLK_FSYS, 14, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_BTS_PCIE, "pclk_bts_pcie", "mout_aclk_fsys_200_user",
-			ENABLE_PCLK_FSYS, 13, 0, 0),
+			ENABLE_PCLK_FSYS, 13, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_SMMU_PDMA0, "pclk_smmu_pdma0", "mout_aclk_fsys_200_user",
 			ENABLE_PCLK_FSYS, 8, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_BTS_UFS, "pclk_bts_ufs", "mout_aclk_fsys_200_user",
@@ -2270,11 +2279,12 @@ static struct samsung_gate_clock fsys_gate_clks[] __initdata = {
 			ENABLE_SCLK_FSYS, 0, 0, 0),
 
 	/* ENABLE_IP_FSYS0 */
+	GATE(CLK_PCIE, "pcie", "sclk_pcie_100", ENABLE_IP_FSYS0, 17, 0, 0),
 	GATE(CLK_PDMA1, "pdma1", "aclk_pdma1", ENABLE_IP_FSYS0, 15, 0, 0),
 	GATE(CLK_PDMA0, "pdma0", "aclk_pdma0", ENABLE_IP_FSYS0, 0, 0, 0),
 };
 
-static struct samsung_cmu_info fsys_cmu_info __initdata = {
+static const struct samsung_cmu_info fsys_cmu_info __initconst = {
 	.mux_clks		= fsys_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(fsys_mux_clks),
 	.gate_clks		= fsys_gate_clks,
@@ -2310,7 +2320,7 @@ CLK_OF_DECLARE(exynos5433_cmu_fsys, "samsung,exynos5433-cmu-fsys",
 #define DIV_ENABLE_IP_G2D1			0x0b04
 #define DIV_ENABLE_IP_G2D_SECURE_SMMU_G2D	0x0b08
 
-static unsigned long g2d_clk_regs[] __initdata = {
+static const unsigned long g2d_clk_regs[] __initconst = {
 	MUX_SEL_G2D0,
 	MUX_SEL_ENABLE_G2D0,
 	DIV_G2D,
@@ -2327,7 +2337,7 @@ static unsigned long g2d_clk_regs[] __initdata = {
 PNAME(mout_aclk_g2d_266_user_p)		= { "oscclk", "aclk_g2d_266", };
 PNAME(mout_aclk_g2d_400_user_p)		= { "oscclk", "aclk_g2d_400", };
 
-static struct samsung_mux_clock g2d_mux_clks[] __initdata = {
+static const struct samsung_mux_clock g2d_mux_clks[] __initconst = {
 	/* MUX_SEL_G2D0 */
 	MUX(CLK_MUX_ACLK_G2D_266_USER, "mout_aclk_g2d_266_user",
 			mout_aclk_g2d_266_user_p, MUX_SEL_G2D0, 4, 1),
@@ -2335,13 +2345,13 @@ static struct samsung_mux_clock g2d_mux_clks[] __initdata = {
 			mout_aclk_g2d_400_user_p, MUX_SEL_G2D0, 0, 1),
 };
 
-static struct samsung_div_clock g2d_div_clks[] __initdata = {
+static const struct samsung_div_clock g2d_div_clks[] __initconst = {
 	/* DIV_G2D */
 	DIV(CLK_DIV_PCLK_G2D, "div_pclk_g2d", "mout_aclk_g2d_266_user",
 			DIV_G2D, 0, 2),
 };
 
-static struct samsung_gate_clock g2d_gate_clks[] __initdata = {
+static const struct samsung_gate_clock g2d_gate_clks[] __initconst = {
 	/* DIV_ENABLE_ACLK_G2D */
 	GATE(CLK_ACLK_SMMU_MDMA1, "aclk_smmu_mdma1", "mout_aclk_g2d_266_user",
 			DIV_ENABLE_ACLK_G2D, 12, 0, 0),
@@ -2398,7 +2408,7 @@ static struct samsung_gate_clock g2d_gate_clks[] __initdata = {
 		DIV_ENABLE_PCLK_G2D_SECURE_SMMU_G2D, 0, 0, 0),
 };
 
-static struct samsung_cmu_info g2d_cmu_info __initdata = {
+static const struct samsung_cmu_info g2d_cmu_info __initconst = {
 	.mux_clks		= g2d_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(g2d_mux_clks),
 	.div_clks		= g2d_div_clks,
@@ -2454,7 +2464,7 @@ CLK_OF_DECLARE(exynos5433_cmu_g2d, "samsung,exynos5433-cmu-g2d",
 #define CLKOUT_CMU_DISP			0x0c00
 #define CLKOUT_CMU_DISP_DIV_STAT	0x0c04
 
-static unsigned long disp_clk_regs[] __initdata = {
+static const unsigned long disp_clk_regs[] __initconst = {
 	DISP_PLL_LOCK,
 	DISP_PLL_CON0,
 	DISP_PLL_CON1,
@@ -2527,12 +2537,12 @@ PNAME(mout_sclk_decon_tv_vclk_c_disp_p)	= {
 PNAME(mout_sclk_decon_tv_vclk_b_disp_p)	= { "mout_sclk_decon_tv_vclk_a_disp",
 					    "mout_sclk_decon_tv_vclk_user", };
 
-static struct samsung_pll_clock disp_pll_clks[] __initdata = {
+static const struct samsung_pll_clock disp_pll_clks[] __initconst = {
 	PLL(pll_35xx, CLK_FOUT_DISP_PLL, "fout_disp_pll", "oscclk",
 		DISP_PLL_LOCK, DISP_PLL_CON0, exynos5443_pll_rates),
 };
 
-static struct samsung_fixed_factor_clock disp_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock disp_fixed_factor_clks[] __initconst = {
 	/*
 	 * sclk_rgb_{vclk|tv_vclk} is half clock of sclk_decon_{vclk|tv_vclk}.
 	 * The divider has fixed value (2) between sclk_rgb_{vclk|tv_vclk}
@@ -2544,7 +2554,7 @@ static struct samsung_fixed_factor_clock disp_fixed_factor_clks[] __initdata = {
 			1, 2, 0),
 };
 
-static struct samsung_fixed_rate_clock disp_fixed_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock disp_fixed_clks[] __initconst = {
 	/* PHY clocks from MIPI_DPHY1 */
 	FRATE(0, "phyclk_mipidphy1_bitclkdiv8_phy", NULL, 0, 188000000),
 	FRATE(0, "phyclk_mipidphy1_rxclkesc0_phy", NULL, 0, 100000000),
@@ -2558,7 +2568,7 @@ static struct samsung_fixed_rate_clock disp_fixed_clks[] __initdata = {
 			NULL, 0, 166000000),
 };
 
-static struct samsung_mux_clock disp_mux_clks[] __initdata = {
+static const struct samsung_mux_clock disp_mux_clks[] __initconst = {
 	/* MUX_SEL_DISP0 */
 	MUX(CLK_MOUT_DISP_PLL, "mout_disp_pll", mout_disp_pll_p, MUX_SEL_DISP0,
 			0, 1),
@@ -2633,7 +2643,7 @@ static struct samsung_mux_clock disp_mux_clks[] __initdata = {
 			mout_sclk_decon_vclk_p, MUX_SEL_DISP4, 0, 1),
 };
 
-static struct samsung_div_clock disp_div_clks[] __initdata = {
+static const struct samsung_div_clock disp_div_clks[] __initconst = {
 	/* DIV_DISP */
 	DIV(CLK_DIV_SCLK_DSIM1_DISP, "div_sclk_dsim1_disp",
 			"mout_sclk_dsim1_b_disp", DIV_DISP, 24, 3),
@@ -2651,7 +2661,7 @@ static struct samsung_div_clock disp_div_clks[] __initdata = {
 			DIV_DISP, 0, 2),
 };
 
-static struct samsung_gate_clock disp_gate_clks[] __initdata = {
+static const struct samsung_gate_clock disp_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_DISP0 */
 	GATE(CLK_ACLK_DECON_TV, "aclk_decon_tv", "mout_aclk_disp_333_user",
 			ENABLE_ACLK_DISP0, 2, 0, 0),
@@ -2811,7 +2821,7 @@ static struct samsung_gate_clock disp_gate_clks[] __initdata = {
 			"div_sclk_decon_eclk_disp", ENABLE_SCLK_DISP, 2, 0, 0),
 };
 
-static struct samsung_cmu_info disp_cmu_info __initdata = {
+static const struct samsung_cmu_info disp_cmu_info __initconst = {
 	.pll_clks		= disp_pll_clks,
 	.nr_pll_clks		= ARRAY_SIZE(disp_pll_clks),
 	.mux_clks		= disp_mux_clks,
@@ -2856,7 +2866,7 @@ CLK_OF_DECLARE(exynos5433_cmu_disp, "samsung,exynos5433-cmu-disp",
 #define ENABLE_IP_AUD0			0x0b00
 #define ENABLE_IP_AUD1			0x0b04
 
-static unsigned long aud_clk_regs[] __initdata = {
+static const unsigned long aud_clk_regs[] __initconst = {
 	MUX_SEL_AUD0,
 	MUX_SEL_AUD1,
 	MUX_ENABLE_AUD0,
@@ -2875,13 +2885,13 @@ static unsigned long aud_clk_regs[] __initdata = {
 PNAME(mout_aud_pll_user_aud_p)	= { "oscclk", "fout_aud_pll", };
 PNAME(mout_sclk_aud_pcm_p)	= { "mout_aud_pll_user", "ioclk_audiocdclk0",};
 
-static struct samsung_fixed_rate_clock aud_fixed_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock aud_fixed_clks[] __initconst = {
 	FRATE(0, "ioclk_jtag_tclk", NULL, 0, 33000000),
 	FRATE(0, "ioclk_slimbus_clk", NULL, 0, 25000000),
 	FRATE(0, "ioclk_i2s_bclk", NULL, 0, 50000000),
 };
 
-static struct samsung_mux_clock aud_mux_clks[] __initdata = {
+static const struct samsung_mux_clock aud_mux_clks[] __initconst = {
 	/* MUX_SEL_AUD0 */
 	MUX(CLK_MOUT_AUD_PLL_USER, "mout_aud_pll_user",
 			mout_aud_pll_user_aud_p, MUX_SEL_AUD0, 0, 1),
@@ -2893,7 +2903,7 @@ static struct samsung_mux_clock aud_mux_clks[] __initdata = {
 			MUX_SEL_AUD1, 0, 1),
 };
 
-static struct samsung_div_clock aud_div_clks[] __initdata = {
+static const struct samsung_div_clock aud_div_clks[] __initconst = {
 	/* DIV_AUD0 */
 	DIV(CLK_DIV_ATCLK_AUD, "div_atclk_aud", "div_aud_ca5", DIV_AUD0,
 			12, 4),
@@ -2915,7 +2925,7 @@ static struct samsung_div_clock aud_div_clks[] __initdata = {
 			DIV_AUD1, 0, 4),
 };
 
-static struct samsung_gate_clock aud_gate_clks[] __initdata = {
+static const struct samsung_gate_clock aud_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_AUD */
 	GATE(CLK_ACLK_INTR_CTRL, "aclk_intr_ctrl", "div_aclk_aud",
 			ENABLE_ACLK_AUD, 12, 0, 0),
@@ -2962,7 +2972,7 @@ static struct samsung_gate_clock aud_gate_clks[] __initdata = {
 
 	/* ENABLE_SCLK_AUD0 */
 	GATE(CLK_ATCLK_AUD, "atclk_aud", "div_atclk_aud", ENABLE_SCLK_AUD0,
-			2, 0, 0),
+			2, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_PCLK_DBG_AUD, "pclk_dbg_aud", "div_pclk_dbg_aud",
 			ENABLE_SCLK_AUD0, 1, 0, 0),
 	GATE(CLK_SCLK_AUD_CA5, "sclk_aud_ca5", "div_aud_ca5", ENABLE_SCLK_AUD0,
@@ -2976,7 +2986,7 @@ static struct samsung_gate_clock aud_gate_clks[] __initdata = {
 	GATE(CLK_SCLK_AUD_SLIMBUS, "sclk_aud_slimbus", "div_sclk_aud_slimbus",
 			ENABLE_SCLK_AUD1, 4, 0, 0),
 	GATE(CLK_SCLK_AUD_UART, "sclk_aud_uart", "div_sclk_aud_uart",
-			ENABLE_SCLK_AUD1, 3, 0, 0),
+			ENABLE_SCLK_AUD1, 3, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_AUD_PCM, "sclk_aud_pcm", "div_sclk_aud_pcm",
 			ENABLE_SCLK_AUD1, 2, 0, 0),
 	GATE(CLK_SCLK_I2S_BCLK, "sclk_i2s_bclk", "ioclk_i2s_bclk",
@@ -2985,7 +2995,7 @@ static struct samsung_gate_clock aud_gate_clks[] __initdata = {
 			ENABLE_SCLK_AUD1, 0, CLK_IGNORE_UNUSED, 0),
 };
 
-static struct samsung_cmu_info aud_cmu_info __initdata = {
+static const struct samsung_cmu_info aud_cmu_info __initconst = {
 	.mux_clks		= aud_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(aud_mux_clks),
 	.div_clks		= aud_div_clks,
@@ -3031,24 +3041,24 @@ PNAME(mout_aclk_bus2_400_p)	= { "oscclk", "aclk_bus2_400", };
 	ENABLE_IP_BUS0,		\
 	ENABLE_IP_BUS1
 
-static unsigned long bus01_clk_regs[] __initdata = {
+static const unsigned long bus01_clk_regs[] __initconst = {
 	CMU_BUS_COMMON_CLK_REGS,
 };
 
-static unsigned long bus2_clk_regs[] __initdata = {
+static const unsigned long bus2_clk_regs[] __initconst = {
 	MUX_SEL_BUS2,
 	MUX_ENABLE_BUS2,
 	CMU_BUS_COMMON_CLK_REGS,
 };
 
-static struct samsung_div_clock bus0_div_clks[] __initdata = {
+static const struct samsung_div_clock bus0_div_clks[] __initconst = {
 	/* DIV_BUS0 */
 	DIV(CLK_DIV_PCLK_BUS_133, "div_pclk_bus0_133", "aclk_bus0_400",
 			DIV_BUS, 0, 3),
 };
 
 /* CMU_BUS0 clocks */
-static struct samsung_gate_clock bus0_gate_clks[] __initdata = {
+static const struct samsung_gate_clock bus0_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_BUS0 */
 	GATE(CLK_ACLK_AHB2APB_BUSP, "aclk_ahb2apb_bus0p", "div_pclk_bus0_133",
 			ENABLE_ACLK_BUS, 4, CLK_IGNORE_UNUSED, 0),
@@ -3067,13 +3077,13 @@ static struct samsung_gate_clock bus0_gate_clks[] __initdata = {
 };
 
 /* CMU_BUS1 clocks */
-static struct samsung_div_clock bus1_div_clks[] __initdata = {
+static const struct samsung_div_clock bus1_div_clks[] __initconst = {
 	/* DIV_BUS1 */
 	DIV(CLK_DIV_PCLK_BUS_133, "div_pclk_bus1_133", "aclk_bus1_400",
 			DIV_BUS, 0, 3),
 };
 
-static struct samsung_gate_clock bus1_gate_clks[] __initdata = {
+static const struct samsung_gate_clock bus1_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_BUS1 */
 	GATE(CLK_ACLK_AHB2APB_BUSP, "aclk_ahb2apb_bus1p", "div_pclk_bus1_133",
 			ENABLE_ACLK_BUS, 4, CLK_IGNORE_UNUSED, 0),
@@ -3092,19 +3102,19 @@ static struct samsung_gate_clock bus1_gate_clks[] __initdata = {
 };
 
 /* CMU_BUS2 clocks */
-static struct samsung_mux_clock bus2_mux_clks[] __initdata = {
+static const struct samsung_mux_clock bus2_mux_clks[] __initconst = {
 	/* MUX_SEL_BUS2 */
 	MUX(CLK_MOUT_ACLK_BUS2_400_USER, "mout_aclk_bus2_400_user",
 			mout_aclk_bus2_400_p, MUX_SEL_BUS2, 0, 1),
 };
 
-static struct samsung_div_clock bus2_div_clks[] __initdata = {
+static const struct samsung_div_clock bus2_div_clks[] __initconst = {
 	/* DIV_BUS2 */
 	DIV(CLK_DIV_PCLK_BUS_133, "div_pclk_bus2_133",
 			"mout_aclk_bus2_400_user", DIV_BUS, 0, 3),
 };
 
-static struct samsung_gate_clock bus2_gate_clks[] __initdata = {
+static const struct samsung_gate_clock bus2_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_BUS2 */
 	GATE(CLK_ACLK_AHB2APB_BUSP, "aclk_ahb2apb_bus2p", "div_pclk_bus2_133",
 			ENABLE_ACLK_BUS, 3, CLK_IGNORE_UNUSED, 0),
@@ -3133,19 +3143,19 @@ static struct samsung_gate_clock bus2_gate_clks[] __initdata = {
 	.nr_gate_clks		= ARRAY_SIZE(bus##id##_gate_clks),	\
 	.nr_clk_ids		= BUSx_NR_CLK
 
-static struct samsung_cmu_info bus0_cmu_info __initdata = {
+static const struct samsung_cmu_info bus0_cmu_info __initconst = {
 	CMU_BUS_INFO_CLKS(0),
 	.clk_regs		= bus01_clk_regs,
 	.nr_clk_regs		= ARRAY_SIZE(bus01_clk_regs),
 };
 
-static struct samsung_cmu_info bus1_cmu_info __initdata = {
+static const struct samsung_cmu_info bus1_cmu_info __initconst = {
 	CMU_BUS_INFO_CLKS(1),
 	.clk_regs		= bus01_clk_regs,
 	.nr_clk_regs		= ARRAY_SIZE(bus01_clk_regs),
 };
 
-static struct samsung_cmu_info bus2_cmu_info __initdata = {
+static const struct samsung_cmu_info bus2_cmu_info __initconst = {
 	CMU_BUS_INFO_CLKS(2),
 	.mux_clks		= bus2_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(bus2_mux_clks),
@@ -3189,7 +3199,7 @@ exynos5433_cmu_bus_init(2);
 #define CLKOUT_CMU_G3D_DIV_STAT		0x0c04
 #define CLK_STOPCTRL			0x1000
 
-static unsigned long g3d_clk_regs[] __initdata = {
+static const unsigned long g3d_clk_regs[] __initconst = {
 	G3D_PLL_LOCK,
 	G3D_PLL_CON0,
 	G3D_PLL_CON1,
@@ -3212,12 +3222,12 @@ static unsigned long g3d_clk_regs[] __initdata = {
 PNAME(mout_aclk_g3d_400_p)	= { "mout_g3d_pll", "aclk_g3d_400", };
 PNAME(mout_g3d_pll_p)		= { "oscclk", "fout_g3d_pll", };
 
-static struct samsung_pll_clock g3d_pll_clks[] __initdata = {
+static const struct samsung_pll_clock g3d_pll_clks[] __initconst = {
 	PLL(pll_35xx, CLK_FOUT_G3D_PLL, "fout_g3d_pll", "oscclk",
 		G3D_PLL_LOCK, G3D_PLL_CON0, exynos5443_pll_rates),
 };
 
-static struct samsung_mux_clock g3d_mux_clks[] __initdata = {
+static const struct samsung_mux_clock g3d_mux_clks[] __initconst = {
 	/* MUX_SEL_G3D */
 	MUX_F(CLK_MOUT_ACLK_G3D_400, "mout_aclk_g3d_400", mout_aclk_g3d_400_p,
 			MUX_SEL_G3D, 8, 1, CLK_SET_RATE_PARENT, 0),
@@ -3225,7 +3235,7 @@ static struct samsung_mux_clock g3d_mux_clks[] __initdata = {
 			MUX_SEL_G3D, 0, 1, CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_div_clock g3d_div_clks[] __initdata = {
+static const struct samsung_div_clock g3d_div_clks[] __initconst = {
 	/* DIV_G3D */
 	DIV(CLK_DIV_SCLK_HPM_G3D, "div_sclk_hpm_g3d", "mout_g3d_pll", DIV_G3D,
 			8, 2),
@@ -3235,7 +3245,7 @@ static struct samsung_div_clock g3d_div_clks[] __initdata = {
 			0, 3, CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_gate_clock g3d_gate_clks[] __initdata = {
+static const struct samsung_gate_clock g3d_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_G3D */
 	GATE(CLK_ACLK_BTS_G3D1, "aclk_bts_g3d1", "div_aclk_g3d",
 			ENABLE_ACLK_G3D, 7, 0, 0),
@@ -3269,7 +3279,7 @@ static struct samsung_gate_clock g3d_gate_clks[] __initdata = {
 			ENABLE_SCLK_G3D, 0, 0, 0),
 };
 
-static struct samsung_cmu_info g3d_cmu_info __initdata = {
+static const struct samsung_cmu_info g3d_cmu_info __initconst = {
 	.pll_clks		= g3d_pll_clks,
 	.nr_pll_clks		= ARRAY_SIZE(g3d_pll_clks),
 	.mux_clks		= g3d_mux_clks,
@@ -3310,7 +3320,7 @@ CLK_OF_DECLARE(exynos5433_cmu_g3d, "samsung,exynos5433-cmu-g3d",
 #define ENABLE_IP_GSCL_SECURE_SMMU_GSCL1	0x0b0c
 #define ENABLE_IP_GSCL_SECURE_SMMU_GSCL2	0x0b10
 
-static unsigned long gscl_clk_regs[] __initdata = {
+static const unsigned long gscl_clk_regs[] __initconst = {
 	MUX_SEL_GSCL,
 	MUX_ENABLE_GSCL,
 	ENABLE_ACLK_GSCL,
@@ -3332,7 +3342,7 @@ static unsigned long gscl_clk_regs[] __initdata = {
 PNAME(aclk_gscl_111_user_p)	= { "oscclk", "aclk_gscl_111", };
 PNAME(aclk_gscl_333_user_p)	= { "oscclk", "aclk_gscl_333", };
 
-static struct samsung_mux_clock gscl_mux_clks[] __initdata = {
+static const struct samsung_mux_clock gscl_mux_clks[] __initconst = {
 	/* MUX_SEL_GSCL */
 	MUX(CLK_MOUT_ACLK_GSCL_111_USER, "mout_aclk_gscl_111_user",
 			aclk_gscl_111_user_p, MUX_SEL_GSCL, 4, 1),
@@ -3340,7 +3350,7 @@ static struct samsung_mux_clock gscl_mux_clks[] __initdata = {
 			aclk_gscl_333_user_p, MUX_SEL_GSCL, 0, 1),
 };
 
-static struct samsung_gate_clock gscl_gate_clks[] __initdata = {
+static const struct samsung_gate_clock gscl_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_GSCL */
 	GATE(CLK_ACLK_BTS_GSCL2, "aclk_bts_gscl2", "mout_aclk_gscl_333_user",
 			ENABLE_ACLK_GSCL, 11, 0, 0),
@@ -3356,9 +3366,11 @@ static struct samsung_gate_clock gscl_gate_clks[] __initdata = {
 	GATE(CLK_ACLK_GSCLNP_111, "aclk_gsclnp_111", "mout_aclk_gscl_111_user",
 			ENABLE_ACLK_GSCL, 6, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_GSCLRTND_333, "aclk_gsclrtnd_333",
-			"mout_aclk_gscl_333_user", ENABLE_ACLK_GSCL, 5, 0, 0),
+			"mout_aclk_gscl_333_user", ENABLE_ACLK_GSCL, 5,
+			CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_GSCLBEND_333, "aclk_gsclbend_333",
-			"mout_aclk_gscl_333_user", ENABLE_ACLK_GSCL, 4, 0, 0),
+			"mout_aclk_gscl_333_user", ENABLE_ACLK_GSCL, 4,
+			CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ACLK_GSD, "aclk_gsd", "mout_aclk_gscl_333_user",
 			ENABLE_ACLK_GSCL, 3, 0, 0),
 	GATE(CLK_ACLK_GSCL2, "aclk_gscl2", "mout_aclk_gscl_333_user",
@@ -3412,7 +3424,7 @@ static struct samsung_gate_clock gscl_gate_clks[] __initdata = {
 		ENABLE_PCLK_GSCL_SECURE_SMMU_GSCL2, 0, 0, 0),
 };
 
-static struct samsung_cmu_info gscl_cmu_info __initdata = {
+static const struct samsung_cmu_info gscl_cmu_info __initconst = {
 	.mux_clks		= gscl_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(gscl_mux_clks),
 	.gate_clks		= gscl_gate_clks,
@@ -3465,7 +3477,7 @@ CLK_OF_DECLARE(exynos5433_cmu_gscl, "samsung,exynos5433-cmu-gscl",
 #define APOLLO_INTR_SPREAD_USE_STANDBYWFI	0x1084
 #define APOLLO_INTR_SPREAD_BLOCKING_DURATION	0x1088
 
-static unsigned long apollo_clk_regs[] __initdata = {
+static const unsigned long apollo_clk_regs[] __initconst = {
 	APOLLO_PLL_LOCK,
 	APOLLO_PLL_CON0,
 	APOLLO_PLL_CON1,
@@ -3500,15 +3512,16 @@ PNAME(mout_bus_pll_apollo_user_p)	= { "oscclk", "sclk_bus_pll_apollo", };
 PNAME(mout_apollo_p)			= { "mout_apollo_pll",
 					    "mout_bus_pll_apollo_user", };
 
-static struct samsung_pll_clock apollo_pll_clks[] __initdata = {
+static const struct samsung_pll_clock apollo_pll_clks[] __initconst = {
 	PLL(pll_35xx, CLK_FOUT_APOLLO_PLL, "fout_apollo_pll", "oscclk",
 		APOLLO_PLL_LOCK, APOLLO_PLL_CON0, exynos5443_pll_rates),
 };
 
-static struct samsung_mux_clock apollo_mux_clks[] __initdata = {
+static const struct samsung_mux_clock apollo_mux_clks[] __initconst = {
 	/* MUX_SEL_APOLLO0 */
 	MUX_F(CLK_MOUT_APOLLO_PLL, "mout_apollo_pll", mout_apollo_pll_p,
-			MUX_SEL_APOLLO0, 0, 1, CLK_SET_RATE_PARENT, 0),
+			MUX_SEL_APOLLO0, 0, 1, CLK_SET_RATE_PARENT |
+			CLK_RECALC_NEW_RATES, 0),
 
 	/* MUX_SEL_APOLLO1 */
 	MUX(CLK_MOUT_BUS_PLL_APOLLO_USER, "mout_bus_pll_apollo_user",
@@ -3519,7 +3532,7 @@ static struct samsung_mux_clock apollo_mux_clks[] __initdata = {
 			0, 1, CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_div_clock apollo_div_clks[] __initdata = {
+static const struct samsung_div_clock apollo_div_clks[] __initconst = {
 	/* DIV_APOLLO0 */
 	DIV_F(CLK_DIV_CNTCLK_APOLLO, "div_cntclk_apollo", "div_apollo2",
 			DIV_APOLLO0, 24, 3, CLK_GET_RATE_NOCACHE,
@@ -3550,7 +3563,7 @@ static struct samsung_div_clock apollo_div_clks[] __initdata = {
 			CLK_DIVIDER_READ_ONLY),
 };
 
-static struct samsung_gate_clock apollo_gate_clks[] __initdata = {
+static const struct samsung_gate_clock apollo_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_APOLLO */
 	GATE(CLK_ACLK_ASATBSLV_APOLLO_3_CSSYS, "aclk_asatbslv_apollo_3_cssys",
 			"div_atclk_apollo", ENABLE_ACLK_APOLLO,
@@ -3589,28 +3602,64 @@ static struct samsung_gate_clock apollo_gate_clks[] __initdata = {
 			ENABLE_SCLK_APOLLO, 3, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_HPM_APOLLO, "sclk_hpm_apollo", "div_sclk_hpm_apollo",
 			ENABLE_SCLK_APOLLO, 1, CLK_IGNORE_UNUSED, 0),
-	GATE(CLK_SCLK_APOLLO, "sclk_apollo", "div_apollo2",
-			ENABLE_SCLK_APOLLO, 0,
-			CLK_IGNORE_UNUSED | CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_cmu_info apollo_cmu_info __initdata = {
-	.pll_clks		= apollo_pll_clks,
-	.nr_pll_clks		= ARRAY_SIZE(apollo_pll_clks),
-	.mux_clks		= apollo_mux_clks,
-	.nr_mux_clks		= ARRAY_SIZE(apollo_mux_clks),
-	.div_clks		= apollo_div_clks,
-	.nr_div_clks		= ARRAY_SIZE(apollo_div_clks),
-	.gate_clks		= apollo_gate_clks,
-	.nr_gate_clks		= ARRAY_SIZE(apollo_gate_clks),
-	.nr_clk_ids		= APOLLO_NR_CLK,
-	.clk_regs		= apollo_clk_regs,
-	.nr_clk_regs		= ARRAY_SIZE(apollo_clk_regs),
+#define E5433_APOLLO_DIV0(cntclk, pclk_dbg, atclk, pclk, aclk) \
+		(((cntclk) << 24) | ((pclk_dbg) << 20) | ((atclk) << 16) | \
+		 ((pclk) << 12) | ((aclk) << 8))
+
+#define E5433_APOLLO_DIV1(hpm, copy) \
+		(((hpm) << 4) | ((copy) << 0))
+
+static const struct exynos_cpuclk_cfg_data exynos5433_apolloclk_d[] __initconst = {
+	{ 1300000, E5433_APOLLO_DIV0(3, 7, 7, 7, 2), E5433_APOLLO_DIV1(7, 1), },
+	{ 1200000, E5433_APOLLO_DIV0(3, 7, 7, 7, 2), E5433_APOLLO_DIV1(7, 1), },
+	{ 1100000, E5433_APOLLO_DIV0(3, 7, 7, 7, 2), E5433_APOLLO_DIV1(7, 1), },
+	{ 1000000, E5433_APOLLO_DIV0(3, 7, 7, 7, 2), E5433_APOLLO_DIV1(7, 1), },
+	{  900000, E5433_APOLLO_DIV0(3, 7, 7, 7, 2), E5433_APOLLO_DIV1(7, 1), },
+	{  800000, E5433_APOLLO_DIV0(3, 7, 7, 7, 2), E5433_APOLLO_DIV1(7, 1), },
+	{  700000, E5433_APOLLO_DIV0(3, 7, 7, 7, 2), E5433_APOLLO_DIV1(7, 1), },
+	{  600000, E5433_APOLLO_DIV0(3, 7, 7, 7, 1), E5433_APOLLO_DIV1(7, 1), },
+	{  500000, E5433_APOLLO_DIV0(3, 7, 7, 7, 1), E5433_APOLLO_DIV1(7, 1), },
+	{  400000, E5433_APOLLO_DIV0(3, 7, 7, 7, 1), E5433_APOLLO_DIV1(7, 1), },
+	{  0 },
 };
 
 static void __init exynos5433_cmu_apollo_init(struct device_node *np)
 {
-	samsung_cmu_register_one(np, &apollo_cmu_info);
+	void __iomem *reg_base;
+	struct samsung_clk_provider *ctx;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		panic("%s: failed to map registers\n", __func__);
+		return;
+	}
+
+	ctx = samsung_clk_init(np, reg_base, APOLLO_NR_CLK);
+	if (!ctx) {
+		panic("%s: unable to allocate ctx\n", __func__);
+		return;
+	}
+
+	samsung_clk_register_pll(ctx, apollo_pll_clks,
+				 ARRAY_SIZE(apollo_pll_clks), reg_base);
+	samsung_clk_register_mux(ctx, apollo_mux_clks,
+				 ARRAY_SIZE(apollo_mux_clks));
+	samsung_clk_register_div(ctx, apollo_div_clks,
+				 ARRAY_SIZE(apollo_div_clks));
+	samsung_clk_register_gate(ctx, apollo_gate_clks,
+				  ARRAY_SIZE(apollo_gate_clks));
+
+	exynos_register_cpu_clock(ctx, CLK_SCLK_APOLLO, "apolloclk",
+		mout_apollo_p[0], mout_apollo_p[1], 0x200,
+		exynos5433_apolloclk_d, ARRAY_SIZE(exynos5433_apolloclk_d),
+		CLK_CPU_HAS_E5433_REGS_LAYOUT);
+
+	samsung_clk_sleep_init(reg_base, apollo_clk_regs,
+			       ARRAY_SIZE(apollo_clk_regs));
+
+	samsung_clk_of_add_provider(np, ctx);
 }
 CLK_OF_DECLARE(exynos5433_cmu_apollo, "samsung,exynos5433-cmu-apollo",
 		exynos5433_cmu_apollo_init);
@@ -3651,7 +3700,7 @@ CLK_OF_DECLARE(exynos5433_cmu_apollo, "samsung,exynos5433-cmu-apollo",
 #define ATLAS_INTR_SPREAD_USE_STANDBYWFI	0x1084
 #define ATLAS_INTR_SPREAD_BLOCKING_DURATION	0x1088
 
-static unsigned long atlas_clk_regs[] __initdata = {
+static const unsigned long atlas_clk_regs[] __initconst = {
 	ATLAS_PLL_LOCK,
 	ATLAS_PLL_CON0,
 	ATLAS_PLL_CON1,
@@ -3686,15 +3735,16 @@ PNAME(mout_bus_pll_atlas_user_p)	= { "oscclk", "sclk_bus_pll_atlas", };
 PNAME(mout_atlas_p)			= { "mout_atlas_pll",
 					    "mout_bus_pll_atlas_user", };
 
-static struct samsung_pll_clock atlas_pll_clks[] __initdata = {
+static const struct samsung_pll_clock atlas_pll_clks[] __initconst = {
 	PLL(pll_35xx, CLK_FOUT_ATLAS_PLL, "fout_atlas_pll", "oscclk",
 		ATLAS_PLL_LOCK, ATLAS_PLL_CON0, exynos5443_pll_rates),
 };
 
-static struct samsung_mux_clock atlas_mux_clks[] __initdata = {
+static const struct samsung_mux_clock atlas_mux_clks[] __initconst = {
 	/* MUX_SEL_ATLAS0 */
 	MUX_F(CLK_MOUT_ATLAS_PLL, "mout_atlas_pll", mout_atlas_pll_p,
-			MUX_SEL_ATLAS0, 0, 1, CLK_SET_RATE_PARENT, 0),
+			MUX_SEL_ATLAS0, 0, 1, CLK_SET_RATE_PARENT |
+			CLK_RECALC_NEW_RATES, 0),
 
 	/* MUX_SEL_ATLAS1 */
 	MUX(CLK_MOUT_BUS_PLL_ATLAS_USER, "mout_bus_pll_atlas_user",
@@ -3705,7 +3755,7 @@ static struct samsung_mux_clock atlas_mux_clks[] __initdata = {
 			0, 1, CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_div_clock atlas_div_clks[] __initdata = {
+static const struct samsung_div_clock atlas_div_clks[] __initconst = {
 	/* DIV_ATLAS0 */
 	DIV_F(CLK_DIV_CNTCLK_ATLAS, "div_cntclk_atlas", "div_atlas2",
 			DIV_ATLAS0, 24, 3, CLK_GET_RATE_NOCACHE,
@@ -3736,7 +3786,7 @@ static struct samsung_div_clock atlas_div_clks[] __initdata = {
 			CLK_DIVIDER_READ_ONLY),
 };
 
-static struct samsung_gate_clock atlas_gate_clks[] __initdata = {
+static const struct samsung_gate_clock atlas_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_ATLAS */
 	GATE(CLK_ACLK_ATB_AUD_CSSYS, "aclk_atb_aud_cssys",
 			"div_atclk_atlas", ENABLE_ACLK_ATLAS,
@@ -3801,28 +3851,69 @@ static struct samsung_gate_clock atlas_gate_clks[] __initdata = {
 			ENABLE_SCLK_ATLAS, 2, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_ATCLK, "atclk", "div_atclk_atlas",
 			ENABLE_SCLK_ATLAS, 1, CLK_IGNORE_UNUSED, 0),
-	GATE(CLK_SCLK_ATLAS, "sclk_atlas", "div_atlas2",
-			ENABLE_SCLK_ATLAS, 0,
-			CLK_IGNORE_UNUSED | CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_cmu_info atlas_cmu_info __initdata = {
-	.pll_clks		= atlas_pll_clks,
-	.nr_pll_clks		= ARRAY_SIZE(atlas_pll_clks),
-	.mux_clks		= atlas_mux_clks,
-	.nr_mux_clks		= ARRAY_SIZE(atlas_mux_clks),
-	.div_clks		= atlas_div_clks,
-	.nr_div_clks		= ARRAY_SIZE(atlas_div_clks),
-	.gate_clks		= atlas_gate_clks,
-	.nr_gate_clks		= ARRAY_SIZE(atlas_gate_clks),
-	.nr_clk_ids		= ATLAS_NR_CLK,
-	.clk_regs		= atlas_clk_regs,
-	.nr_clk_regs		= ARRAY_SIZE(atlas_clk_regs),
+#define E5433_ATLAS_DIV0(cntclk, pclk_dbg, atclk, pclk, aclk) \
+		(((cntclk) << 24) | ((pclk_dbg) << 20) | ((atclk) << 16) | \
+		 ((pclk) << 12) | ((aclk) << 8))
+
+#define E5433_ATLAS_DIV1(hpm, copy) \
+		(((hpm) << 4) | ((copy) << 0))
+
+static const struct exynos_cpuclk_cfg_data exynos5433_atlasclk_d[] __initconst = {
+	{ 1900000, E5433_ATLAS_DIV0(7, 7, 7, 7, 4), E5433_ATLAS_DIV1(7, 1), },
+	{ 1800000, E5433_ATLAS_DIV0(7, 7, 7, 7, 4), E5433_ATLAS_DIV1(7, 1), },
+	{ 1700000, E5433_ATLAS_DIV0(7, 7, 7, 7, 4), E5433_ATLAS_DIV1(7, 1), },
+	{ 1600000, E5433_ATLAS_DIV0(7, 7, 7, 7, 4), E5433_ATLAS_DIV1(7, 1), },
+	{ 1500000, E5433_ATLAS_DIV0(7, 7, 7, 7, 3), E5433_ATLAS_DIV1(7, 1), },
+	{ 1400000, E5433_ATLAS_DIV0(7, 7, 7, 7, 3), E5433_ATLAS_DIV1(7, 1), },
+	{ 1300000, E5433_ATLAS_DIV0(7, 7, 7, 7, 3), E5433_ATLAS_DIV1(7, 1), },
+	{ 1200000, E5433_ATLAS_DIV0(7, 7, 7, 7, 3), E5433_ATLAS_DIV1(7, 1), },
+	{ 1100000, E5433_ATLAS_DIV0(7, 7, 7, 7, 3), E5433_ATLAS_DIV1(7, 1), },
+	{ 1000000, E5433_ATLAS_DIV0(7, 7, 7, 7, 3), E5433_ATLAS_DIV1(7, 1), },
+	{  900000, E5433_ATLAS_DIV0(7, 7, 7, 7, 2), E5433_ATLAS_DIV1(7, 1), },
+	{  800000, E5433_ATLAS_DIV0(7, 7, 7, 7, 2), E5433_ATLAS_DIV1(7, 1), },
+	{  700000, E5433_ATLAS_DIV0(7, 7, 7, 7, 2), E5433_ATLAS_DIV1(7, 1), },
+	{  600000, E5433_ATLAS_DIV0(7, 7, 7, 7, 2), E5433_ATLAS_DIV1(7, 1), },
+	{  500000, E5433_ATLAS_DIV0(7, 7, 7, 7, 2), E5433_ATLAS_DIV1(7, 1), },
+	{  0 },
 };
 
 static void __init exynos5433_cmu_atlas_init(struct device_node *np)
 {
-	samsung_cmu_register_one(np, &atlas_cmu_info);
+	void __iomem *reg_base;
+	struct samsung_clk_provider *ctx;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		panic("%s: failed to map registers\n", __func__);
+		return;
+	}
+
+	ctx = samsung_clk_init(np, reg_base, ATLAS_NR_CLK);
+	if (!ctx) {
+		panic("%s: unable to allocate ctx\n", __func__);
+		return;
+	}
+
+	samsung_clk_register_pll(ctx, atlas_pll_clks,
+				 ARRAY_SIZE(atlas_pll_clks), reg_base);
+	samsung_clk_register_mux(ctx, atlas_mux_clks,
+				 ARRAY_SIZE(atlas_mux_clks));
+	samsung_clk_register_div(ctx, atlas_div_clks,
+				 ARRAY_SIZE(atlas_div_clks));
+	samsung_clk_register_gate(ctx, atlas_gate_clks,
+				  ARRAY_SIZE(atlas_gate_clks));
+
+	exynos_register_cpu_clock(ctx, CLK_SCLK_ATLAS, "atlasclk",
+		mout_atlas_p[0], mout_atlas_p[1], 0x200,
+		exynos5433_atlasclk_d, ARRAY_SIZE(exynos5433_atlasclk_d),
+		CLK_CPU_HAS_E5433_REGS_LAYOUT);
+
+	samsung_clk_sleep_init(reg_base, atlas_clk_regs,
+			       ARRAY_SIZE(atlas_clk_regs));
+
+	samsung_clk_of_add_provider(np, ctx);
 }
 CLK_OF_DECLARE(exynos5433_cmu_atlas, "samsung,exynos5433-cmu-atlas",
 		exynos5433_cmu_atlas_init);
@@ -3853,7 +3944,7 @@ CLK_OF_DECLARE(exynos5433_cmu_atlas, "samsung,exynos5433-cmu-atlas",
 #define ENABLE_IP_MSCL_SECURE_SMMU_M2MSCALER1		0x0b0c
 #define ENABLE_IP_MSCL_SECURE_SMMU_JPEG			0x0b10
 
-static unsigned long mscl_clk_regs[] __initdata = {
+static const unsigned long mscl_clk_regs[] __initconst = {
 	MUX_SEL_MSCL0,
 	MUX_SEL_MSCL1,
 	MUX_ENABLE_MSCL0,
@@ -3881,7 +3972,7 @@ PNAME(mout_aclk_mscl_400_user_p)	= { "oscclk", "aclk_mscl_400", };
 PNAME(mout_sclk_jpeg_p)			= { "mout_sclk_jpeg_user",
 					"mout_aclk_mscl_400_user", };
 
-static struct samsung_mux_clock mscl_mux_clks[] __initdata = {
+static const struct samsung_mux_clock mscl_mux_clks[] __initconst = {
 	/* MUX_SEL_MSCL0 */
 	MUX(CLK_MOUT_SCLK_JPEG_USER, "mout_sclk_jpeg_user",
 			mout_sclk_jpeg_user_p, MUX_SEL_MSCL0, 4, 1),
@@ -3893,13 +3984,13 @@ static struct samsung_mux_clock mscl_mux_clks[] __initdata = {
 			MUX_SEL_MSCL1, 0, 1),
 };
 
-static struct samsung_div_clock mscl_div_clks[] __initdata = {
+static const struct samsung_div_clock mscl_div_clks[] __initconst = {
 	/* DIV_MSCL */
 	DIV(CLK_DIV_PCLK_MSCL, "div_pclk_mscl", "mout_aclk_mscl_400_user",
 			DIV_MSCL, 0, 3),
 };
 
-static struct samsung_gate_clock mscl_gate_clks[] __initdata = {
+static const struct samsung_gate_clock mscl_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_MSCL */
 	GATE(CLK_ACLK_BTS_JPEG, "aclk_bts_jpeg", "mout_aclk_mscl_400_user",
 			ENABLE_ACLK_MSCL, 9, 0, 0),
@@ -3977,7 +4068,7 @@ static struct samsung_gate_clock mscl_gate_clks[] __initdata = {
 			CLK_IGNORE_UNUSED | CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_cmu_info mscl_cmu_info __initdata = {
+static const struct samsung_cmu_info mscl_cmu_info __initconst = {
 	.mux_clks		= mscl_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(mscl_mux_clks),
 	.div_clks		= mscl_div_clks,
@@ -4012,7 +4103,7 @@ CLK_OF_DECLARE(exynos5433_cmu_mscl, "samsung,exynos5433-cmu-mscl",
 #define ENABLE_IP_MFC1				0x0b04
 #define ENABLE_IP_MFC_SECURE_SMMU_MFC		0x0b08
 
-static unsigned long mfc_clk_regs[] __initdata = {
+static const unsigned long mfc_clk_regs[] __initconst = {
 	MUX_SEL_MFC,
 	MUX_ENABLE_MFC,
 	DIV_MFC,
@@ -4027,19 +4118,19 @@ static unsigned long mfc_clk_regs[] __initdata = {
 
 PNAME(mout_aclk_mfc_400_user_p)		= { "oscclk", "aclk_mfc_400", };
 
-static struct samsung_mux_clock mfc_mux_clks[] __initdata = {
+static const struct samsung_mux_clock mfc_mux_clks[] __initconst = {
 	/* MUX_SEL_MFC */
 	MUX(CLK_MOUT_ACLK_MFC_400_USER, "mout_aclk_mfc_400_user",
 			mout_aclk_mfc_400_user_p, MUX_SEL_MFC, 0, 0),
 };
 
-static struct samsung_div_clock mfc_div_clks[] __initdata = {
+static const struct samsung_div_clock mfc_div_clks[] __initconst = {
 	/* DIV_MFC */
 	DIV(CLK_DIV_PCLK_MFC, "div_pclk_mfc", "mout_aclk_mfc_400_user",
 			DIV_MFC, 0, 2),
 };
 
-static struct samsung_gate_clock mfc_gate_clks[] __initdata = {
+static const struct samsung_gate_clock mfc_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_MFC */
 	GATE(CLK_ACLK_BTS_MFC_1, "aclk_bts_mfc_1", "mout_aclk_mfc_400_user",
 			ENABLE_ACLK_MFC, 6, 0, 0),
@@ -4085,7 +4176,7 @@ static struct samsung_gate_clock mfc_gate_clks[] __initdata = {
 			0, CLK_IGNORE_UNUSED, 0),
 };
 
-static struct samsung_cmu_info mfc_cmu_info __initdata = {
+static const struct samsung_cmu_info mfc_cmu_info __initconst = {
 	.mux_clks		= mfc_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(mfc_mux_clks),
 	.div_clks		= mfc_div_clks,
@@ -4120,7 +4211,7 @@ CLK_OF_DECLARE(exynos5433_cmu_mfc, "samsung,exynos5433-cmu-mfc",
 #define ENABLE_IP_HEVC1				0x0b04
 #define ENABLE_IP_HEVC_SECURE_SMMU_HEVC		0x0b08
 
-static unsigned long hevc_clk_regs[] __initdata = {
+static const unsigned long hevc_clk_regs[] __initconst = {
 	MUX_SEL_HEVC,
 	MUX_ENABLE_HEVC,
 	DIV_HEVC,
@@ -4135,19 +4226,19 @@ static unsigned long hevc_clk_regs[] __initdata = {
 
 PNAME(mout_aclk_hevc_400_user_p)	= { "oscclk", "aclk_hevc_400", };
 
-static struct samsung_mux_clock hevc_mux_clks[] __initdata = {
+static const struct samsung_mux_clock hevc_mux_clks[] __initconst = {
 	/* MUX_SEL_HEVC */
 	MUX(CLK_MOUT_ACLK_HEVC_400_USER, "mout_aclk_hevc_400_user",
 			mout_aclk_hevc_400_user_p, MUX_SEL_HEVC, 0, 0),
 };
 
-static struct samsung_div_clock hevc_div_clks[] __initdata = {
+static const struct samsung_div_clock hevc_div_clks[] __initconst = {
 	/* DIV_HEVC */
 	DIV(CLK_DIV_PCLK_HEVC, "div_pclk_hevc", "mout_aclk_hevc_400_user",
 			DIV_HEVC, 0, 2),
 };
 
-static struct samsung_gate_clock hevc_gate_clks[] __initdata = {
+static const struct samsung_gate_clock hevc_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_HEVC */
 	GATE(CLK_ACLK_BTS_HEVC_1, "aclk_bts_hevc_1", "mout_aclk_hevc_400_user",
 			ENABLE_ACLK_HEVC, 6, 0, 0),
@@ -4195,7 +4286,7 @@ static struct samsung_gate_clock hevc_gate_clks[] __initdata = {
 			0, CLK_IGNORE_UNUSED, 0),
 };
 
-static struct samsung_cmu_info hevc_cmu_info __initdata = {
+static const struct samsung_cmu_info hevc_cmu_info __initconst = {
 	.mux_clks		= hevc_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(hevc_mux_clks),
 	.div_clks		= hevc_div_clks,
@@ -4232,7 +4323,7 @@ CLK_OF_DECLARE(exynos5433_cmu_hevc, "samsung,exynos5433-cmu-hevc",
 #define ENABLE_IP_ISP2			0x0b08
 #define ENABLE_IP_ISP3			0x0b0c
 
-static unsigned long isp_clk_regs[] __initdata = {
+static const unsigned long isp_clk_regs[] __initconst = {
 	MUX_SEL_ISP,
 	MUX_ENABLE_ISP,
 	DIV_ISP,
@@ -4250,7 +4341,7 @@ static unsigned long isp_clk_regs[] __initdata = {
 PNAME(mout_aclk_isp_dis_400_user_p)	= { "oscclk", "aclk_isp_dis_400", };
 PNAME(mout_aclk_isp_400_user_p)		= { "oscclk", "aclk_isp_400", };
 
-static struct samsung_mux_clock isp_mux_clks[] __initdata = {
+static const struct samsung_mux_clock isp_mux_clks[] __initconst = {
 	/* MUX_SEL_ISP */
 	MUX(CLK_MOUT_ACLK_ISP_DIS_400_USER, "mout_aclk_isp_dis_400_user",
 			mout_aclk_isp_dis_400_user_p, MUX_SEL_ISP, 4, 0),
@@ -4258,7 +4349,7 @@ static struct samsung_mux_clock isp_mux_clks[] __initdata = {
 			mout_aclk_isp_400_user_p, MUX_SEL_ISP, 0, 0),
 };
 
-static struct samsung_div_clock isp_div_clks[] __initdata = {
+static const struct samsung_div_clock isp_div_clks[] __initconst = {
 	/* DIV_ISP */
 	DIV(CLK_DIV_PCLK_ISP_DIS, "div_pclk_isp_dis",
 			"mout_aclk_isp_dis_400_user", DIV_ISP, 12, 3),
@@ -4270,7 +4361,7 @@ static struct samsung_div_clock isp_div_clks[] __initdata = {
 			"mout_aclk_isp_400_user", DIV_ISP, 0, 3),
 };
 
-static struct samsung_gate_clock isp_gate_clks[] __initdata = {
+static const struct samsung_gate_clock isp_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_ISP0 */
 	GATE(CLK_ACLK_ISP_D_GLUE, "aclk_isp_d_glue", "mout_aclk_isp_400_user",
 			ENABLE_ACLK_ISP0, 6, CLK_IGNORE_UNUSED, 0),
@@ -4448,7 +4539,7 @@ static struct samsung_gate_clock isp_gate_clks[] __initdata = {
 			0, CLK_IGNORE_UNUSED, 0),
 };
 
-static struct samsung_cmu_info isp_cmu_info __initdata = {
+static const struct samsung_cmu_info isp_cmu_info __initconst = {
 	.mux_clks		= isp_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(isp_mux_clks),
 	.div_clks		= isp_div_clks,
@@ -4504,7 +4595,7 @@ CLK_OF_DECLARE(exynos5433_cmu_isp, "samsung,exynos5433-cmu-isp",
 #define ENABLE_IP_CAM02			0X0b08
 #define ENABLE_IP_CAM03			0X0b0C
 
-static unsigned long cam0_clk_regs[] __initdata = {
+static const unsigned long cam0_clk_regs[] __initconst = {
 	MUX_SEL_CAM00,
 	MUX_SEL_CAM01,
 	MUX_SEL_CAM02,
@@ -4588,14 +4679,14 @@ PNAME(mout_sclk_pixelasync_lite_c_init_a_p) = {
 					"mout_aclk_cam0_552_user",
 					"mout_aclk_cam0_400_user", };
 
-static struct samsung_fixed_rate_clock cam0_fixed_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock cam0_fixed_clks[] __initconst = {
 	FRATE(CLK_PHYCLK_RXBYTEECLKHS0_S4_PHY, "phyclk_rxbyteclkhs0_s4_phy",
 			NULL, 0, 100000000),
 	FRATE(CLK_PHYCLK_RXBYTEECLKHS0_S2A_PHY, "phyclk_rxbyteclkhs0_s2a_phy",
 			NULL, 0, 100000000),
 };
 
-static struct samsung_mux_clock cam0_mux_clks[] __initdata = {
+static const struct samsung_mux_clock cam0_mux_clks[] __initconst = {
 	/* MUX_SEL_CAM00 */
 	MUX(CLK_MOUT_ACLK_CAM0_333_USER, "mout_aclk_cam0_333_user",
 			mout_aclk_cam0_333_user_p, MUX_SEL_CAM00, 8, 1),
@@ -4669,7 +4760,7 @@ static struct samsung_mux_clock cam0_mux_clks[] __initdata = {
 			MUX_SEL_CAM04, 0, 1),
 };
 
-static struct samsung_div_clock cam0_div_clks[] __initdata = {
+static const struct samsung_div_clock cam0_div_clks[] __initconst = {
 	/* DIV_CAM00 */
 	DIV(CLK_DIV_PCLK_CAM0_50, "div_pclk_cam0_50", "div_aclk_cam0_200",
 			DIV_CAM00, 8, 2),
@@ -4716,7 +4807,7 @@ static struct samsung_div_clock cam0_div_clks[] __initdata = {
 			"mout_sclk_pixelasync_lite_c_init_b", DIV_CAM03, 0, 3),
 };
 
-static struct samsung_gate_clock cam0_gate_clks[] __initdata = {
+static const struct samsung_gate_clock cam0_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_CAM00 */
 	GATE(CLK_ACLK_CSIS1, "aclk_csis1", "div_aclk_csis1", ENABLE_ACLK_CAM00,
 			6, 0, 0),
@@ -4923,7 +5014,7 @@ static struct samsung_gate_clock cam0_gate_clks[] __initdata = {
 			ENABLE_SCLK_CAM0, 0, 0, 0),
 };
 
-static struct samsung_cmu_info cam0_cmu_info __initdata = {
+static const struct samsung_cmu_info cam0_cmu_info __initconst = {
 	.mux_clks		= cam0_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(cam0_mux_clks),
 	.div_clks		= cam0_div_clks,
@@ -4970,7 +5061,7 @@ CLK_OF_DECLARE(exynos5433_cmu_cam0, "samsung,exynos5433-cmu-cam0",
 #define ENABLE_IP_CAM11			0X0b04
 #define ENABLE_IP_CAM12			0X0b08
 
-static unsigned long cam1_clk_regs[] __initdata = {
+static const unsigned long cam1_clk_regs[] __initconst = {
 	MUX_SEL_CAM10,
 	MUX_SEL_CAM11,
 	MUX_SEL_CAM12,
@@ -5016,12 +5107,12 @@ PNAME(mout_aclk_lite_c_b_p)		= { "mout_aclk_lite_c_a",
 PNAME(mout_aclk_lite_c_a_p)		= { "mout_aclk_cam1_552_user",
 					    "mout_aclk_cam1_400_user", };
 
-static struct samsung_fixed_rate_clock cam1_fixed_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock cam1_fixed_clks[] __initconst = {
 	FRATE(CLK_PHYCLK_RXBYTEECLKHS0_S2B, "phyclk_rxbyteclkhs0_s2b_phy", NULL,
 			0, 100000000),
 };
 
-static struct samsung_mux_clock cam1_mux_clks[] __initdata = {
+static const struct samsung_mux_clock cam1_mux_clks[] __initconst = {
 	/* MUX_SEL_CAM10 */
 	MUX(CLK_MOUT_SCLK_ISP_UART_USER, "mout_sclk_isp_uart_user",
 			mout_sclk_isp_uart_user_p, MUX_SEL_CAM10, 20, 1),
@@ -5057,7 +5148,7 @@ static struct samsung_mux_clock cam1_mux_clks[] __initdata = {
 			MUX_SEL_CAM12, 0, 1),
 };
 
-static struct samsung_div_clock cam1_div_clks[] __initdata = {
+static const struct samsung_div_clock cam1_div_clks[] __initconst = {
 	/* DIV_CAM10 */
 	DIV(CLK_DIV_SCLK_ISP_MPWM, "div_sclk_isp_mpwm",
 			"div_pclk_cam1_83", DIV_CAM10, 16, 2),
@@ -5081,7 +5172,7 @@ static struct samsung_div_clock cam1_div_clks[] __initdata = {
 			DIV_CAM11, 0, 3),
 };
 
-static struct samsung_gate_clock cam1_gate_clks[] __initdata = {
+static const struct samsung_gate_clock cam1_gate_clks[] __initconst = {
 	/* ENABLE_ACLK_CAM10 */
 	GATE(CLK_ACLK_ISP_GIC, "aclk_isp_gic", "mout_aclk_cam1_333_user",
 			ENABLE_ACLK_CAM10, 4, 0, 0),
@@ -5296,7 +5387,7 @@ static struct samsung_gate_clock cam1_gate_clks[] __initdata = {
 			ENABLE_SCLK_CAM1, 0, 0, 0),
 };
 
-static struct samsung_cmu_info cam1_cmu_info __initdata = {
+static const struct samsung_cmu_info cam1_cmu_info __initconst = {
 	.mux_clks		= cam1_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(cam1_mux_clks),
 	.div_clks		= cam1_div_clks,
diff --git a/drivers/clk/samsung/clk-exynos5440.c b/drivers/clk/samsung/clk-exynos5440.c
index c57cff1e1798..a57d01b99b76 100644
--- a/drivers/clk/samsung/clk-exynos5440.c
+++ b/drivers/clk/samsung/clk-exynos5440.c
@@ -35,7 +35,7 @@ static struct samsung_fixed_rate_clock exynos5440_fixed_rate_ext_clks[] __initda
 };
 
 /* fixed rate clocks */
-static struct samsung_fixed_rate_clock exynos5440_fixed_rate_clks[] __initdata = {
+static const struct samsung_fixed_rate_clock exynos5440_fixed_rate_clks[] __initconst = {
 	FRATE(0, "ppll", NULL, 0, 1000000000),
 	FRATE(0, "usb_phy0", NULL, 0, 60000000),
 	FRATE(0, "usb_phy1", NULL, 0, 60000000),
@@ -44,26 +44,26 @@ static struct samsung_fixed_rate_clock exynos5440_fixed_rate_clks[] __initdata =
 };
 
 /* fixed factor clocks */
-static struct samsung_fixed_factor_clock exynos5440_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock exynos5440_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "div250", "ppll", 1, 4, 0),
 	FFACTOR(0, "div200", "ppll", 1, 5, 0),
 	FFACTOR(0, "div125", "div250", 1, 2, 0),
 };
 
 /* mux clocks */
-static struct samsung_mux_clock exynos5440_mux_clks[] __initdata = {
+static const struct samsung_mux_clock exynos5440_mux_clks[] __initconst = {
 	MUX(0, "mout_spi", mout_spi_p, MISC_DOUT1, 5, 1),
 	MUX_A(CLK_ARM_CLK, "arm_clk", mout_armclk_p,
 			CPU_CLK_STATUS, 0, 1, "armclk"),
 };
 
 /* divider clocks */
-static struct samsung_div_clock exynos5440_div_clks[] __initdata = {
+static const struct samsung_div_clock exynos5440_div_clks[] __initconst = {
 	DIV(CLK_SPI_BAUD, "div_spi", "mout_spi", MISC_DOUT1, 3, 2),
 };
 
 /* gate clocks */
-static struct samsung_gate_clock exynos5440_gate_clks[] __initdata = {
+static const struct samsung_gate_clock exynos5440_gate_clks[] __initconst = {
 	GATE(CLK_PB0_250, "pb0_250", "div250", CLKEN_OV_VAL, 3, 0, 0),
 	GATE(CLK_PR0_250, "pr0_250", "div250", CLKEN_OV_VAL, 4, 0, 0),
 	GATE(CLK_PR1_250, "pr1_250", "div250", CLKEN_OV_VAL, 5, 0, 0),
@@ -125,8 +125,6 @@ static void __init exynos5440_clk_init(struct device_node *np)
 	}
 
 	ctx = samsung_clk_init(np, reg_base, CLK_NR_CLKS);
-	if (!ctx)
-		panic("%s: unable to allocate context.\n", __func__);
 
 	samsung_clk_of_register_fixed_ext(ctx, exynos5440_fixed_rate_ext_clks,
 		ARRAY_SIZE(exynos5440_fixed_rate_ext_clks), ext_clk_match);
diff --git a/drivers/clk/samsung/clk-exynos7.c b/drivers/clk/samsung/clk-exynos7.c
index ad68d463b12c..5931a4140c3d 100644
--- a/drivers/clk/samsung/clk-exynos7.c
+++ b/drivers/clk/samsung/clk-exynos7.c
@@ -36,7 +36,7 @@
 #define ENABLE_ACLK_TOPC1	0x0804
 #define ENABLE_SCLK_TOPC1	0x0A04
 
-static struct samsung_fixed_factor_clock topc_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock topc_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "ffac_topc_bus0_pll_div2", "mout_topc_bus0_pll", 1, 2, 0),
 	FFACTOR(0, "ffac_topc_bus0_pll_div4",
 		"ffac_topc_bus0_pll_div2", 1, 2, 0),
@@ -69,7 +69,7 @@ PNAME(mout_topc_mfc_pll_half_p) = { "mout_topc_mfc_pll",
 PNAME(mout_topc_bus0_pll_out_p) = {"mout_topc_bus0_pll",
 	"ffac_topc_bus0_pll_div2"};
 
-static unsigned long topc_clk_regs[] __initdata = {
+static const unsigned long topc_clk_regs[] __initconst = {
 	CC_PLL_LOCK,
 	BUS0_PLL_LOCK,
 	BUS1_DPLL_LOCK,
@@ -89,7 +89,7 @@ static unsigned long topc_clk_regs[] __initdata = {
 	DIV_TOPC3,
 };
 
-static struct samsung_mux_clock topc_mux_clks[] __initdata = {
+static const struct samsung_mux_clock topc_mux_clks[] __initconst = {
 	MUX(0, "mout_topc_bus0_pll", mout_topc_bus0_pll_ctrl_p,
 		MUX_SEL_TOPC0, 0, 1),
 	MUX(0, "mout_topc_bus1_pll", mout_topc_bus1_pll_ctrl_p,
@@ -118,7 +118,7 @@ static struct samsung_mux_clock topc_mux_clks[] __initdata = {
 	MUX(0, "mout_aclk_peris_66", mout_topc_group2, MUX_SEL_TOPC3, 24, 2),
 };
 
-static struct samsung_div_clock topc_div_clks[] __initdata = {
+static const struct samsung_div_clock topc_div_clks[] __initconst = {
 	DIV(DOUT_ACLK_CCORE_133, "dout_aclk_ccore_133", "mout_aclk_ccore_133",
 		DIV_TOPC0, 4, 4),
 
@@ -139,14 +139,14 @@ static struct samsung_div_clock topc_div_clks[] __initdata = {
 		DIV_TOPC3, 28, 4),
 };
 
-static struct samsung_pll_rate_table pll1460x_24mhz_tbl[] __initdata = {
+static const struct samsung_pll_rate_table pll1460x_24mhz_tbl[] __initconst = {
 	PLL_36XX_RATE(491520000, 20, 1, 0, 31457),
 	{},
 };
 
-static struct samsung_gate_clock topc_gate_clks[] __initdata = {
+static const struct samsung_gate_clock topc_gate_clks[] __initconst = {
 	GATE(ACLK_CCORE_133, "aclk_ccore_133", "dout_aclk_ccore_133",
-		ENABLE_ACLK_TOPC0, 4, 0, 0),
+		ENABLE_ACLK_TOPC0, 4, CLK_IS_CRITICAL, 0),
 
 	GATE(ACLK_MSCL_532, "aclk_mscl_532", "dout_aclk_mscl_532",
 		ENABLE_ACLK_TOPC1, 20, 0, 0),
@@ -174,7 +174,7 @@ static struct samsung_gate_clock topc_gate_clks[] __initdata = {
 		ENABLE_SCLK_TOPC1, 0, 0, 0),
 };
 
-static struct samsung_pll_clock topc_pll_clks[] __initdata = {
+static const struct samsung_pll_clock topc_pll_clks[] __initconst = {
 	PLL(pll_1451x, 0, "fout_bus0_pll", "fin_pll", BUS0_PLL_LOCK,
 		BUS0_PLL_CON0, NULL),
 	PLL(pll_1452x, 0, "fout_cc_pll", "fin_pll", CC_PLL_LOCK,
@@ -187,7 +187,7 @@ static struct samsung_pll_clock topc_pll_clks[] __initdata = {
 		AUD_PLL_CON0, pll1460x_24mhz_tbl),
 };
 
-static struct samsung_cmu_info topc_cmu_info __initdata = {
+static const struct samsung_cmu_info topc_cmu_info __initconst = {
 	.pll_clks		= topc_pll_clks,
 	.nr_pll_clks		= ARRAY_SIZE(topc_pll_clks),
 	.mux_clks		= topc_mux_clks,
@@ -256,7 +256,7 @@ PNAME(mout_top0_group3) = {"ioclk_audiocdclk0",
 PNAME(mout_top0_group4) = {"ioclk_audiocdclk1", "mout_top0_aud_pll_user",
 	"mout_top0_bus0_pll_half", "mout_top0_bus1_pll_half"};
 
-static unsigned long top0_clk_regs[] __initdata = {
+static const unsigned long top0_clk_regs[] __initconst = {
 	MUX_SEL_TOP00,
 	MUX_SEL_TOP01,
 	MUX_SEL_TOP03,
@@ -275,7 +275,7 @@ static unsigned long top0_clk_regs[] __initdata = {
 	ENABLE_SCLK_TOP0_PERIC3,
 };
 
-static struct samsung_mux_clock top0_mux_clks[] __initdata = {
+static const struct samsung_mux_clock top0_mux_clks[] __initconst = {
 	MUX(0, "mout_top0_aud_pll_user", mout_top0_aud_pll_user_p,
 		MUX_SEL_TOP00, 0, 1),
 	MUX(0, "mout_top0_mfc_pll_user", mout_top0_mfc_pll_user_p,
@@ -315,7 +315,7 @@ static struct samsung_mux_clock top0_mux_clks[] __initdata = {
 	MUX(0, "mout_sclk_spi4", mout_top0_group1, MUX_SEL_TOP0_PERIC3, 20, 2),
 };
 
-static struct samsung_div_clock top0_div_clks[] __initdata = {
+static const struct samsung_div_clock top0_div_clks[] __initconst = {
 	DIV(DOUT_ACLK_PERIC1, "dout_aclk_peric1_66", "mout_aclk_peric1_66",
 		DIV_TOP03, 12, 6),
 	DIV(DOUT_ACLK_PERIC0, "dout_aclk_peric0_66", "mout_aclk_peric0_66",
@@ -338,7 +338,7 @@ static struct samsung_div_clock top0_div_clks[] __initdata = {
 	DIV(0, "dout_sclk_spi4", "mout_sclk_spi4", DIV_TOP0_PERIC3, 20, 12),
 };
 
-static struct samsung_gate_clock top0_gate_clks[] __initdata = {
+static const struct samsung_gate_clock top0_gate_clks[] __initconst = {
 	GATE(CLK_ACLK_PERIC0_66, "aclk_peric0_66", "dout_aclk_peric0_66",
 		ENABLE_ACLK_TOP03, 20, CLK_SET_RATE_PARENT, 0),
 	GATE(CLK_ACLK_PERIC1_66, "aclk_peric1_66", "dout_aclk_peric1_66",
@@ -372,7 +372,7 @@ static struct samsung_gate_clock top0_gate_clks[] __initdata = {
 		ENABLE_SCLK_TOP0_PERIC3, 20, CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_fixed_factor_clock top0_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock top0_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "ffac_top0_bus0_pll_div2", "mout_top0_bus0_pll_user",
 		1, 2, 0),
 	FFACTOR(0, "ffac_top0_bus1_pll_div2", "mout_top0_bus1_pll_user",
@@ -381,7 +381,7 @@ static struct samsung_fixed_factor_clock top0_fixed_factor_clks[] __initdata = {
 	FFACTOR(0, "ffac_top0_mfc_pll_div2", "mout_top0_mfc_pll_user", 1, 2, 0),
 };
 
-static struct samsung_cmu_info top0_cmu_info __initdata = {
+static const struct samsung_cmu_info top0_cmu_info __initconst = {
 	.mux_clks		= top0_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(top0_mux_clks),
 	.div_clks		= top0_div_clks,
@@ -438,7 +438,7 @@ PNAME(mout_top1_group1) = {"mout_top1_bus0_pll_half",
 	"mout_top1_bus1_pll_half", "mout_top1_cc_pll_half",
 	"mout_top1_mfc_pll_half"};
 
-static unsigned long top1_clk_regs[] __initdata = {
+static const unsigned long top1_clk_regs[] __initconst = {
 	MUX_SEL_TOP10,
 	MUX_SEL_TOP11,
 	MUX_SEL_TOP13,
@@ -455,7 +455,7 @@ static unsigned long top1_clk_regs[] __initdata = {
 	ENABLE_SCLK_TOP1_FSYS11,
 };
 
-static struct samsung_mux_clock top1_mux_clks[] __initdata = {
+static const struct samsung_mux_clock top1_mux_clks[] __initconst = {
 	MUX(0, "mout_top1_mfc_pll_user", mout_top1_mfc_pll_user_p,
 		MUX_SEL_TOP10, 4, 1),
 	MUX(0, "mout_top1_cc_pll_user", mout_top1_cc_pll_user_p,
@@ -494,7 +494,7 @@ static struct samsung_mux_clock top1_mux_clks[] __initdata = {
 		MUX_SEL_TOP1_FSYS11, 24, 2),
 };
 
-static struct samsung_div_clock top1_div_clks[] __initdata = {
+static const struct samsung_div_clock top1_div_clks[] __initconst = {
 	DIV(DOUT_ACLK_FSYS1_200, "dout_aclk_fsys1_200", "mout_aclk_fsys1_200",
 		DIV_TOP13, 24, 4),
 	DIV(DOUT_ACLK_FSYS0_200, "dout_aclk_fsys0_200", "mout_aclk_fsys0_200",
@@ -521,7 +521,7 @@ static struct samsung_div_clock top1_div_clks[] __initdata = {
 		"mout_sclk_phy_fsys1_26m", DIV_TOP1_FSYS11, 24, 6),
 };
 
-static struct samsung_gate_clock top1_gate_clks[] __initdata = {
+static const struct samsung_gate_clock top1_gate_clks[] __initconst = {
 	GATE(CLK_SCLK_MMC2, "sclk_mmc2", "dout_sclk_mmc2",
 		ENABLE_SCLK_TOP1_FSYS0, 16, CLK_SET_RATE_PARENT, 0),
 	GATE(0, "sclk_usbdrd300", "dout_sclk_usbdrd300",
@@ -539,7 +539,8 @@ static struct samsung_gate_clock top1_gate_clks[] __initdata = {
 		ENABLE_SCLK_TOP1_FSYS11, 12, CLK_SET_RATE_PARENT, 0),
 
 	GATE(CLK_ACLK_FSYS0_200, "aclk_fsys0_200", "dout_aclk_fsys0_200",
-		ENABLE_ACLK_TOP13, 28, CLK_SET_RATE_PARENT, 0),
+		ENABLE_ACLK_TOP13, 28, CLK_SET_RATE_PARENT |
+		CLK_IS_CRITICAL, 0),
 	GATE(CLK_ACLK_FSYS1_200, "aclk_fsys1_200", "dout_aclk_fsys1_200",
 		ENABLE_ACLK_TOP13, 24, CLK_SET_RATE_PARENT, 0),
 
@@ -548,7 +549,7 @@ static struct samsung_gate_clock top1_gate_clks[] __initdata = {
 		24, CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_fixed_factor_clock top1_fixed_factor_clks[] __initdata = {
+static const struct samsung_fixed_factor_clock top1_fixed_factor_clks[] __initconst = {
 	FFACTOR(0, "ffac_top1_bus0_pll_div2", "mout_top1_bus0_pll_user",
 		1, 2, 0),
 	FFACTOR(0, "ffac_top1_bus1_pll_div2", "mout_top1_bus1_pll_user",
@@ -557,7 +558,7 @@ static struct samsung_fixed_factor_clock top1_fixed_factor_clks[] __initdata = {
 	FFACTOR(0, "ffac_top1_mfc_pll_div2", "mout_top1_mfc_pll_user", 1, 2, 0),
 };
 
-static struct samsung_cmu_info top1_cmu_info __initdata = {
+static const struct samsung_cmu_info top1_cmu_info __initconst = {
 	.mux_clks		= top1_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(top1_mux_clks),
 	.div_clks		= top1_div_clks,
@@ -591,22 +592,22 @@ CLK_OF_DECLARE(exynos7_clk_top1, "samsung,exynos7-clock-top1",
  */
 PNAME(mout_aclk_ccore_133_user_p)	= { "fin_pll", "aclk_ccore_133" };
 
-static unsigned long ccore_clk_regs[] __initdata = {
+static const unsigned long ccore_clk_regs[] __initconst = {
 	MUX_SEL_CCORE,
 	ENABLE_PCLK_CCORE,
 };
 
-static struct samsung_mux_clock ccore_mux_clks[] __initdata = {
+static const struct samsung_mux_clock ccore_mux_clks[] __initconst = {
 	MUX(0, "mout_aclk_ccore_133_user", mout_aclk_ccore_133_user_p,
 		MUX_SEL_CCORE, 1, 1),
 };
 
-static struct samsung_gate_clock ccore_gate_clks[] __initdata = {
+static const struct samsung_gate_clock ccore_gate_clks[] __initconst = {
 	GATE(PCLK_RTC, "pclk_rtc", "mout_aclk_ccore_133_user",
 		ENABLE_PCLK_CCORE, 8, 0, 0),
 };
 
-static struct samsung_cmu_info ccore_cmu_info __initdata = {
+static const struct samsung_cmu_info ccore_cmu_info __initconst = {
 	.mux_clks		= ccore_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(ccore_mux_clks),
 	.gate_clks		= ccore_gate_clks,
@@ -633,20 +634,20 @@ CLK_OF_DECLARE(exynos7_clk_ccore, "samsung,exynos7-clock-ccore",
 PNAME(mout_aclk_peric0_66_user_p)	= { "fin_pll", "aclk_peric0_66" };
 PNAME(mout_sclk_uart0_user_p)	= { "fin_pll", "sclk_uart0" };
 
-static unsigned long peric0_clk_regs[] __initdata = {
+static const unsigned long peric0_clk_regs[] __initconst = {
 	MUX_SEL_PERIC0,
 	ENABLE_PCLK_PERIC0,
 	ENABLE_SCLK_PERIC0,
 };
 
-static struct samsung_mux_clock peric0_mux_clks[] __initdata = {
+static const struct samsung_mux_clock peric0_mux_clks[] __initconst = {
 	MUX(0, "mout_aclk_peric0_66_user", mout_aclk_peric0_66_user_p,
 		MUX_SEL_PERIC0, 0, 1),
 	MUX(0, "mout_sclk_uart0_user", mout_sclk_uart0_user_p,
 		MUX_SEL_PERIC0, 16, 1),
 };
 
-static struct samsung_gate_clock peric0_gate_clks[] __initdata = {
+static const struct samsung_gate_clock peric0_gate_clks[] __initconst = {
 	GATE(PCLK_HSI2C0, "pclk_hsi2c0", "mout_aclk_peric0_66_user",
 		ENABLE_PCLK_PERIC0, 8, 0, 0),
 	GATE(PCLK_HSI2C1, "pclk_hsi2c1", "mout_aclk_peric0_66_user",
@@ -673,7 +674,7 @@ static struct samsung_gate_clock peric0_gate_clks[] __initdata = {
 	GATE(SCLK_PWM, "sclk_pwm", "fin_pll", ENABLE_SCLK_PERIC0, 21, 0, 0),
 };
 
-static struct samsung_cmu_info peric0_cmu_info __initdata = {
+static const struct samsung_cmu_info peric0_cmu_info __initconst = {
 	.mux_clks		= peric0_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(peric0_mux_clks),
 	.gate_clks		= peric0_gate_clks,
@@ -709,7 +710,7 @@ PNAME(mout_sclk_spi2_user_p)		= { "fin_pll", "sclk_spi2" };
 PNAME(mout_sclk_spi3_user_p)		= { "fin_pll", "sclk_spi3" };
 PNAME(mout_sclk_spi4_user_p)		= { "fin_pll", "sclk_spi4" };
 
-static unsigned long peric1_clk_regs[] __initdata = {
+static const unsigned long peric1_clk_regs[] __initconst = {
 	MUX_SEL_PERIC10,
 	MUX_SEL_PERIC11,
 	MUX_SEL_PERIC12,
@@ -717,7 +718,7 @@ static unsigned long peric1_clk_regs[] __initdata = {
 	ENABLE_SCLK_PERIC10,
 };
 
-static struct samsung_mux_clock peric1_mux_clks[] __initdata = {
+static const struct samsung_mux_clock peric1_mux_clks[] __initconst = {
 	MUX(0, "mout_aclk_peric1_66_user", mout_aclk_peric1_66_user_p,
 		MUX_SEL_PERIC10, 0, 1),
 
@@ -739,7 +740,7 @@ static struct samsung_mux_clock peric1_mux_clks[] __initdata = {
 		MUX_SEL_PERIC11, 28, 1),
 };
 
-static struct samsung_gate_clock peric1_gate_clks[] __initdata = {
+static const struct samsung_gate_clock peric1_gate_clks[] __initconst = {
 	GATE(PCLK_HSI2C2, "pclk_hsi2c2", "mout_aclk_peric1_66_user",
 		ENABLE_PCLK_PERIC1, 4, 0, 0),
 	GATE(PCLK_HSI2C3, "pclk_hsi2c3", "mout_aclk_peric1_66_user",
@@ -797,7 +798,7 @@ static struct samsung_gate_clock peric1_gate_clks[] __initdata = {
 		ENABLE_SCLK_PERIC10, 19, CLK_SET_RATE_PARENT, 0),
 };
 
-static struct samsung_cmu_info peric1_cmu_info __initdata = {
+static const struct samsung_cmu_info peric1_cmu_info __initconst = {
 	.mux_clks		= peric1_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(peric1_mux_clks),
 	.gate_clks		= peric1_gate_clks,
@@ -825,7 +826,7 @@ CLK_OF_DECLARE(exynos7_clk_peric1, "samsung,exynos7-clock-peric1",
 /* List of parent clocks for Muxes in CMU_PERIS */
 PNAME(mout_aclk_peris_66_user_p) = { "fin_pll", "aclk_peris_66" };
 
-static unsigned long peris_clk_regs[] __initdata = {
+static const unsigned long peris_clk_regs[] __initconst = {
 	MUX_SEL_PERIS,
 	ENABLE_PCLK_PERIS,
 	ENABLE_PCLK_PERIS_SECURE_CHIPID,
@@ -833,12 +834,12 @@ static unsigned long peris_clk_regs[] __initdata = {
 	ENABLE_SCLK_PERIS_SECURE_CHIPID,
 };
 
-static struct samsung_mux_clock peris_mux_clks[] __initdata = {
+static const struct samsung_mux_clock peris_mux_clks[] __initconst = {
 	MUX(0, "mout_aclk_peris_66_user",
 		mout_aclk_peris_66_user_p, MUX_SEL_PERIS, 0, 1),
 };
 
-static struct samsung_gate_clock peris_gate_clks[] __initdata = {
+static const struct samsung_gate_clock peris_gate_clks[] __initconst = {
 	GATE(PCLK_WDT, "pclk_wdt", "mout_aclk_peris_66_user",
 		ENABLE_PCLK_PERIS, 6, 0, 0),
 	GATE(PCLK_TMU, "pclk_tmu_apbif", "mout_aclk_peris_66_user",
@@ -852,7 +853,7 @@ static struct samsung_gate_clock peris_gate_clks[] __initdata = {
 	GATE(SCLK_TMU, "sclk_tmu", "fin_pll", ENABLE_SCLK_PERIS, 10, 0, 0),
 };
 
-static struct samsung_cmu_info peris_cmu_info __initdata = {
+static const struct samsung_cmu_info peris_cmu_info __initconst = {
 	.mux_clks		= peris_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(peris_mux_clks),
 	.gate_clks		= peris_gate_clks,
@@ -893,12 +894,12 @@ PNAME(mout_phyclk_usbdrd300_udrd30_pipe_pclk_user_p)	= { "fin_pll",
 				"phyclk_usbdrd300_udrd30_pipe_pclk" };
 
 /* fixed rate clocks used in the FSYS0 block */
-static struct samsung_fixed_rate_clock fixed_rate_clks_fsys0[] __initdata = {
+static const struct samsung_fixed_rate_clock fixed_rate_clks_fsys0[] __initconst = {
 	FRATE(0, "phyclk_usbdrd300_udrd30_phyclock", NULL, 0, 60000000),
 	FRATE(0, "phyclk_usbdrd300_udrd30_pipe_pclk", NULL, 0, 125000000),
 };
 
-static unsigned long fsys0_clk_regs[] __initdata = {
+static const unsigned long fsys0_clk_regs[] __initconst = {
 	MUX_SEL_FSYS00,
 	MUX_SEL_FSYS01,
 	MUX_SEL_FSYS02,
@@ -909,7 +910,7 @@ static unsigned long fsys0_clk_regs[] __initdata = {
 	ENABLE_SCLK_FSYS04,
 };
 
-static struct samsung_mux_clock fsys0_mux_clks[] __initdata = {
+static const struct samsung_mux_clock fsys0_mux_clks[] __initconst = {
 	MUX(0, "mout_aclk_fsys0_200_user", mout_aclk_fsys0_200_user_p,
 		MUX_SEL_FSYS00, 24, 1),
 
@@ -926,7 +927,7 @@ static struct samsung_mux_clock fsys0_mux_clks[] __initdata = {
 		MUX_SEL_FSYS02, 28, 1),
 };
 
-static struct samsung_gate_clock fsys0_gate_clks[] __initdata = {
+static const struct samsung_gate_clock fsys0_gate_clks[] __initconst = {
 	GATE(ACLK_PDMA1, "aclk_pdma1", "mout_aclk_fsys0_200_user",
 			ENABLE_ACLK_FSYS00, 3, 0, 0),
 	GATE(ACLK_PDMA0, "aclk_pdma0", "mout_aclk_fsys0_200_user",
@@ -960,7 +961,7 @@ static struct samsung_gate_clock fsys0_gate_clks[] __initdata = {
 		ENABLE_SCLK_FSYS04, 28, 0, 0),
 };
 
-static struct samsung_cmu_info fsys0_cmu_info __initdata = {
+static const struct samsung_cmu_info fsys0_cmu_info __initconst = {
 	.fixed_clks		= fixed_rate_clks_fsys0,
 	.nr_fixed_clks		= ARRAY_SIZE(fixed_rate_clks_fsys0),
 	.mux_clks		= fsys0_mux_clks,
@@ -1005,7 +1006,7 @@ PNAME(mout_phyclk_ufs20_rx0_user_p) = { "fin_pll", "phyclk_ufs20_rx0_symbol" };
 PNAME(mout_phyclk_ufs20_rx1_user_p) = { "fin_pll", "phyclk_ufs20_rx1_symbol" };
 
 /* fixed rate clocks used in the FSYS1 block */
-static struct samsung_fixed_rate_clock fixed_rate_clks_fsys1[] __initdata = {
+static const struct samsung_fixed_rate_clock fixed_rate_clks_fsys1[] __initconst = {
 	FRATE(PHYCLK_UFS20_TX0_SYMBOL, "phyclk_ufs20_tx0_symbol", NULL,
 			0, 300000000),
 	FRATE(PHYCLK_UFS20_RX0_SYMBOL, "phyclk_ufs20_rx0_symbol", NULL,
@@ -1014,7 +1015,7 @@ static struct samsung_fixed_rate_clock fixed_rate_clks_fsys1[] __initdata = {
 			0, 300000000),
 };
 
-static unsigned long fsys1_clk_regs[] __initdata = {
+static const unsigned long fsys1_clk_regs[] __initconst = {
 	MUX_SEL_FSYS10,
 	MUX_SEL_FSYS11,
 	MUX_SEL_FSYS12,
@@ -1026,7 +1027,7 @@ static unsigned long fsys1_clk_regs[] __initdata = {
 	ENABLE_SCLK_FSYS13,
 };
 
-static struct samsung_mux_clock fsys1_mux_clks[] __initdata = {
+static const struct samsung_mux_clock fsys1_mux_clks[] __initconst = {
 	MUX(MOUT_FSYS1_PHYCLK_SEL1, "mout_fsys1_phyclk_sel1",
 		mout_fsys1_group_p, MUX_SEL_FSYS10, 16, 2),
 	MUX(0, "mout_fsys1_phyclk_sel0", mout_fsys1_group_p,
@@ -1049,12 +1050,12 @@ static struct samsung_mux_clock fsys1_mux_clks[] __initdata = {
 		mout_phyclk_ufs20_tx0_user_p, MUX_SEL_FSYS12, 28, 1),
 };
 
-static struct samsung_div_clock fsys1_div_clks[] __initdata = {
+static const struct samsung_div_clock fsys1_div_clks[] __initconst = {
 	DIV(DOUT_PCLK_FSYS1, "dout_pclk_fsys1", "mout_aclk_fsys1_200_user",
 		DIV_FSYS1, 0, 2),
 };
 
-static struct samsung_gate_clock fsys1_gate_clks[] __initdata = {
+static const struct samsung_gate_clock fsys1_gate_clks[] __initconst = {
 	GATE(SCLK_UFSUNIPRO20_USER, "sclk_ufsunipro20_user",
 		"mout_sclk_ufsunipro20_user",
 		ENABLE_SCLK_FSYS11, 20, 0, 0),
@@ -1089,7 +1090,7 @@ static struct samsung_gate_clock fsys1_gate_clks[] __initdata = {
 		ENABLE_SCLK_FSYS13, 24, CLK_IGNORE_UNUSED, 0),
 };
 
-static struct samsung_cmu_info fsys1_cmu_info __initdata = {
+static const struct samsung_cmu_info fsys1_cmu_info __initconst = {
 	.fixed_clks		= fixed_rate_clks_fsys1,
 	.nr_fixed_clks		= ARRAY_SIZE(fixed_rate_clks_fsys1),
 	.mux_clks		= fsys1_mux_clks,
@@ -1119,22 +1120,22 @@ CLK_OF_DECLARE(exynos7_clk_fsys1, "samsung,exynos7-clock-fsys1",
 /* List of parent clocks for Muxes in CMU_MSCL */
 PNAME(mout_aclk_mscl_532_user_p)	= { "fin_pll", "aclk_mscl_532" };
 
-static unsigned long mscl_clk_regs[] __initdata = {
+static const unsigned long mscl_clk_regs[] __initconst = {
 	MUX_SEL_MSCL,
 	DIV_MSCL,
 	ENABLE_ACLK_MSCL,
 	ENABLE_PCLK_MSCL,
 };
 
-static struct samsung_mux_clock mscl_mux_clks[] __initdata = {
+static const struct samsung_mux_clock mscl_mux_clks[] __initconst = {
 	MUX(USERMUX_ACLK_MSCL_532, "usermux_aclk_mscl_532",
 		mout_aclk_mscl_532_user_p, MUX_SEL_MSCL, 0, 1),
 };
-static struct samsung_div_clock mscl_div_clks[] __initdata = {
+static const struct samsung_div_clock mscl_div_clks[] __initconst = {
 	DIV(DOUT_PCLK_MSCL, "dout_pclk_mscl", "usermux_aclk_mscl_532",
 			DIV_MSCL, 0, 3),
 };
-static struct samsung_gate_clock mscl_gate_clks[] __initdata = {
+static const struct samsung_gate_clock mscl_gate_clks[] __initconst = {
 
 	GATE(ACLK_MSCL_0, "aclk_mscl_0", "usermux_aclk_mscl_532",
 			ENABLE_ACLK_MSCL, 31, 0, 0),
@@ -1204,7 +1205,7 @@ static struct samsung_gate_clock mscl_gate_clks[] __initdata = {
 			ENABLE_PCLK_MSCL, 20, 0, 0),
 };
 
-static struct samsung_cmu_info mscl_cmu_info __initdata = {
+static const struct samsung_cmu_info mscl_cmu_info __initconst = {
 	.mux_clks		= mscl_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(mscl_mux_clks),
 	.div_clks		= mscl_div_clks,
@@ -1238,7 +1239,7 @@ CLK_OF_DECLARE(exynos7_clk_mscl, "samsung,exynos7-clock-mscl",
 PNAME(mout_aud_pll_user_p) = { "fin_pll", "fout_aud_pll" };
 PNAME(mout_aud_group_p) = { "dout_aud_cdclk", "ioclk_audiocdclk0" };
 
-static unsigned long aud_clk_regs[] __initdata = {
+static const unsigned long aud_clk_regs[] __initconst = {
 	MUX_SEL_AUD,
 	DIV_AUD0,
 	DIV_AUD1,
@@ -1247,13 +1248,13 @@ static unsigned long aud_clk_regs[] __initdata = {
 	ENABLE_SCLK_AUD,
 };
 
-static struct samsung_mux_clock aud_mux_clks[] __initdata = {
+static const struct samsung_mux_clock aud_mux_clks[] __initconst = {
 	MUX(0, "mout_sclk_i2s", mout_aud_group_p, MUX_SEL_AUD, 12, 1),
 	MUX(0, "mout_sclk_pcm", mout_aud_group_p, MUX_SEL_AUD, 16, 1),
 	MUX(0, "mout_aud_pll_user", mout_aud_pll_user_p, MUX_SEL_AUD, 20, 1),
 };
 
-static struct samsung_div_clock aud_div_clks[] __initdata = {
+static const struct samsung_div_clock aud_div_clks[] __initconst = {
 	DIV(0, "dout_aud_ca5", "mout_aud_pll_user", DIV_AUD0, 0, 4),
 	DIV(0, "dout_aclk_aud", "dout_aud_ca5", DIV_AUD0, 4, 4),
 	DIV(0, "dout_aud_pclk_dbg", "dout_aud_ca5", DIV_AUD0, 8, 4),
@@ -1265,7 +1266,7 @@ static struct samsung_div_clock aud_div_clks[] __initdata = {
 	DIV(0, "dout_aud_cdclk", "mout_aud_pll_user", DIV_AUD1, 24, 4),
 };
 
-static struct samsung_gate_clock aud_gate_clks[] __initdata = {
+static const struct samsung_gate_clock aud_gate_clks[] __initconst = {
 	GATE(SCLK_PCM, "sclk_pcm", "dout_sclk_pcm",
 			ENABLE_SCLK_AUD, 27, CLK_SET_RATE_PARENT, 0),
 	GATE(SCLK_I2S, "sclk_i2s", "dout_sclk_i2s",
@@ -1293,7 +1294,7 @@ static struct samsung_gate_clock aud_gate_clks[] __initdata = {
 	GATE(ACLK_ADMA, "aclk_dmac", "dout_aclk_aud", ENABLE_ACLK_AUD, 31, 0, 0),
 };
 
-static struct samsung_cmu_info aud_cmu_info __initdata = {
+static const struct samsung_cmu_info aud_cmu_info __initconst = {
 	.mux_clks		= aud_mux_clks,
 	.nr_mux_clks		= ARRAY_SIZE(aud_mux_clks),
 	.div_clks		= aud_div_clks,
diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c
index b7dd396100d8..48139bd510f1 100644
--- a/drivers/clk/samsung/clk-pll.c
+++ b/drivers/clk/samsung/clk-pll.c
@@ -79,7 +79,7 @@ static unsigned long samsung_pll2126_recalc_rate(struct clk_hw *hw,
 	u32 pll_con, mdiv, pdiv, sdiv;
 	u64 fvco = parent_rate;
 
-	pll_con = __raw_readl(pll->con_reg);
+	pll_con = readl_relaxed(pll->con_reg);
 	mdiv = (pll_con >> PLL2126_MDIV_SHIFT) & PLL2126_MDIV_MASK;
 	pdiv = (pll_con >> PLL2126_PDIV_SHIFT) & PLL2126_PDIV_MASK;
 	sdiv = (pll_con >> PLL2126_SDIV_SHIFT) & PLL2126_SDIV_MASK;
@@ -112,7 +112,7 @@ static unsigned long samsung_pll3000_recalc_rate(struct clk_hw *hw,
 	u32 pll_con, mdiv, pdiv, sdiv;
 	u64 fvco = parent_rate;
 
-	pll_con = __raw_readl(pll->con_reg);
+	pll_con = readl_relaxed(pll->con_reg);
 	mdiv = (pll_con >> PLL3000_MDIV_SHIFT) & PLL3000_MDIV_MASK;
 	pdiv = (pll_con >> PLL3000_PDIV_SHIFT) & PLL3000_PDIV_MASK;
 	sdiv = (pll_con >> PLL3000_SDIV_SHIFT) & PLL3000_SDIV_MASK;
@@ -149,7 +149,7 @@ static unsigned long samsung_pll35xx_recalc_rate(struct clk_hw *hw,
 	u32 mdiv, pdiv, sdiv, pll_con;
 	u64 fvco = parent_rate;
 
-	pll_con = __raw_readl(pll->con_reg);
+	pll_con = readl_relaxed(pll->con_reg);
 	mdiv = (pll_con >> PLL35XX_MDIV_SHIFT) & PLL35XX_MDIV_MASK;
 	pdiv = (pll_con >> PLL35XX_PDIV_SHIFT) & PLL35XX_PDIV_MASK;
 	sdiv = (pll_con >> PLL35XX_SDIV_SHIFT) & PLL35XX_SDIV_MASK;
@@ -186,19 +186,19 @@ static int samsung_pll35xx_set_rate(struct clk_hw *hw, unsigned long drate,
 		return -EINVAL;
 	}
 
-	tmp = __raw_readl(pll->con_reg);
+	tmp = readl_relaxed(pll->con_reg);
 
 	if (!(samsung_pll35xx_mp_change(rate, tmp))) {
 		/* If only s change, change just s value only*/
 		tmp &= ~(PLL35XX_SDIV_MASK << PLL35XX_SDIV_SHIFT);
 		tmp |= rate->sdiv << PLL35XX_SDIV_SHIFT;
-		__raw_writel(tmp, pll->con_reg);
+		writel_relaxed(tmp, pll->con_reg);
 
 		return 0;
 	}
 
 	/* Set PLL lock time. */
-	__raw_writel(rate->pdiv * PLL35XX_LOCK_FACTOR,
+	writel_relaxed(rate->pdiv * PLL35XX_LOCK_FACTOR,
 			pll->lock_reg);
 
 	/* Change PLL PMS values */
@@ -208,12 +208,12 @@ static int samsung_pll35xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	tmp |= (rate->mdiv << PLL35XX_MDIV_SHIFT) |
 			(rate->pdiv << PLL35XX_PDIV_SHIFT) |
 			(rate->sdiv << PLL35XX_SDIV_SHIFT);
-	__raw_writel(tmp, pll->con_reg);
+	writel_relaxed(tmp, pll->con_reg);
 
 	/* wait_lock_time */
 	do {
 		cpu_relax();
-		tmp = __raw_readl(pll->con_reg);
+		tmp = readl_relaxed(pll->con_reg);
 	} while (!(tmp & (PLL35XX_LOCK_STAT_MASK
 				<< PLL35XX_LOCK_STAT_SHIFT)));
 	return 0;
@@ -253,8 +253,8 @@ static unsigned long samsung_pll36xx_recalc_rate(struct clk_hw *hw,
 	s16 kdiv;
 	u64 fvco = parent_rate;
 
-	pll_con0 = __raw_readl(pll->con_reg);
-	pll_con1 = __raw_readl(pll->con_reg + 4);
+	pll_con0 = readl_relaxed(pll->con_reg);
+	pll_con1 = readl_relaxed(pll->con_reg + 4);
 	mdiv = (pll_con0 >> PLL36XX_MDIV_SHIFT) & PLL36XX_MDIV_MASK;
 	pdiv = (pll_con0 >> PLL36XX_PDIV_SHIFT) & PLL36XX_PDIV_MASK;
 	sdiv = (pll_con0 >> PLL36XX_SDIV_SHIFT) & PLL36XX_SDIV_MASK;
@@ -294,20 +294,20 @@ static int samsung_pll36xx_set_rate(struct clk_hw *hw, unsigned long drate,
 		return -EINVAL;
 	}
 
-	pll_con0 = __raw_readl(pll->con_reg);
-	pll_con1 = __raw_readl(pll->con_reg + 4);
+	pll_con0 = readl_relaxed(pll->con_reg);
+	pll_con1 = readl_relaxed(pll->con_reg + 4);
 
 	if (!(samsung_pll36xx_mpk_change(rate, pll_con0, pll_con1))) {
 		/* If only s change, change just s value only*/
 		pll_con0 &= ~(PLL36XX_SDIV_MASK << PLL36XX_SDIV_SHIFT);
 		pll_con0 |= (rate->sdiv << PLL36XX_SDIV_SHIFT);
-		__raw_writel(pll_con0, pll->con_reg);
+		writel_relaxed(pll_con0, pll->con_reg);
 
 		return 0;
 	}
 
 	/* Set PLL lock time. */
-	__raw_writel(rate->pdiv * PLL36XX_LOCK_FACTOR, pll->lock_reg);
+	writel_relaxed(rate->pdiv * PLL36XX_LOCK_FACTOR, pll->lock_reg);
 
 	 /* Change PLL PMS values */
 	pll_con0 &= ~((PLL36XX_MDIV_MASK << PLL36XX_MDIV_SHIFT) |
@@ -316,16 +316,16 @@ static int samsung_pll36xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	pll_con0 |= (rate->mdiv << PLL36XX_MDIV_SHIFT) |
 			(rate->pdiv << PLL36XX_PDIV_SHIFT) |
 			(rate->sdiv << PLL36XX_SDIV_SHIFT);
-	__raw_writel(pll_con0, pll->con_reg);
+	writel_relaxed(pll_con0, pll->con_reg);
 
 	pll_con1 &= ~(PLL36XX_KDIV_MASK << PLL36XX_KDIV_SHIFT);
 	pll_con1 |= rate->kdiv << PLL36XX_KDIV_SHIFT;
-	__raw_writel(pll_con1, pll->con_reg + 4);
+	writel_relaxed(pll_con1, pll->con_reg + 4);
 
 	/* wait_lock_time */
 	do {
 		cpu_relax();
-		tmp = __raw_readl(pll->con_reg);
+		tmp = readl_relaxed(pll->con_reg);
 	} while (!(tmp & (1 << PLL36XX_LOCK_STAT_SHIFT)));
 
 	return 0;
@@ -366,7 +366,7 @@ static unsigned long samsung_pll45xx_recalc_rate(struct clk_hw *hw,
 	u32 mdiv, pdiv, sdiv, pll_con;
 	u64 fvco = parent_rate;
 
-	pll_con = __raw_readl(pll->con_reg);
+	pll_con = readl_relaxed(pll->con_reg);
 	mdiv = (pll_con >> PLL45XX_MDIV_SHIFT) & PLL45XX_MDIV_MASK;
 	pdiv = (pll_con >> PLL45XX_PDIV_SHIFT) & PLL45XX_PDIV_MASK;
 	sdiv = (pll_con >> PLL45XX_SDIV_SHIFT) & PLL45XX_SDIV_MASK;
@@ -409,14 +409,14 @@ static int samsung_pll45xx_set_rate(struct clk_hw *hw, unsigned long drate,
 		return -EINVAL;
 	}
 
-	con0 = __raw_readl(pll->con_reg);
-	con1 = __raw_readl(pll->con_reg + 0x4);
+	con0 = readl_relaxed(pll->con_reg);
+	con1 = readl_relaxed(pll->con_reg + 0x4);
 
 	if (!(samsung_pll45xx_mp_change(con0, con1, rate))) {
 		/* If only s change, change just s value only*/
 		con0 &= ~(PLL45XX_SDIV_MASK << PLL45XX_SDIV_SHIFT);
 		con0 |= rate->sdiv << PLL45XX_SDIV_SHIFT;
-		__raw_writel(con0, pll->con_reg);
+		writel_relaxed(con0, pll->con_reg);
 
 		return 0;
 	}
@@ -430,29 +430,29 @@ static int samsung_pll45xx_set_rate(struct clk_hw *hw, unsigned long drate,
 			(rate->sdiv << PLL45XX_SDIV_SHIFT);
 
 	/* Set PLL AFC value. */
-	con1 = __raw_readl(pll->con_reg + 0x4);
+	con1 = readl_relaxed(pll->con_reg + 0x4);
 	con1 &= ~(PLL45XX_AFC_MASK << PLL45XX_AFC_SHIFT);
 	con1 |= (rate->afc << PLL45XX_AFC_SHIFT);
 
 	/* Set PLL lock time. */
 	switch (pll->type) {
 	case pll_4502:
-		__raw_writel(rate->pdiv * PLL4502_LOCK_FACTOR, pll->lock_reg);
+		writel_relaxed(rate->pdiv * PLL4502_LOCK_FACTOR, pll->lock_reg);
 		break;
 	case pll_4508:
-		__raw_writel(rate->pdiv * PLL4508_LOCK_FACTOR, pll->lock_reg);
+		writel_relaxed(rate->pdiv * PLL4508_LOCK_FACTOR, pll->lock_reg);
 		break;
 	default:
 		break;
 	}
 
 	/* Set new configuration. */
-	__raw_writel(con1, pll->con_reg + 0x4);
-	__raw_writel(con0, pll->con_reg);
+	writel_relaxed(con1, pll->con_reg + 0x4);
+	writel_relaxed(con0, pll->con_reg);
 
 	/* Wait for locking. */
 	start = ktime_get();
-	while (!(__raw_readl(pll->con_reg) & PLL45XX_LOCKED)) {
+	while (!(readl_relaxed(pll->con_reg) & PLL45XX_LOCKED)) {
 		ktime_t delta = ktime_sub(ktime_get(), start);
 
 		if (ktime_to_ms(delta) > PLL_TIMEOUT_MS) {
@@ -513,8 +513,8 @@ static unsigned long samsung_pll46xx_recalc_rate(struct clk_hw *hw,
 	u32 mdiv, pdiv, sdiv, kdiv, pll_con0, pll_con1, shift;
 	u64 fvco = parent_rate;
 
-	pll_con0 = __raw_readl(pll->con_reg);
-	pll_con1 = __raw_readl(pll->con_reg + 4);
+	pll_con0 = readl_relaxed(pll->con_reg);
+	pll_con1 = readl_relaxed(pll->con_reg + 4);
 	mdiv = (pll_con0 >> PLL46XX_MDIV_SHIFT) & ((pll->type == pll_1460x) ?
 				PLL1460X_MDIV_MASK : PLL46XX_MDIV_MASK);
 	pdiv = (pll_con0 >> PLL46XX_PDIV_SHIFT) & PLL46XX_PDIV_MASK;
@@ -560,14 +560,14 @@ static int samsung_pll46xx_set_rate(struct clk_hw *hw, unsigned long drate,
 		return -EINVAL;
 	}
 
-	con0 = __raw_readl(pll->con_reg);
-	con1 = __raw_readl(pll->con_reg + 0x4);
+	con0 = readl_relaxed(pll->con_reg);
+	con1 = readl_relaxed(pll->con_reg + 0x4);
 
 	if (!(samsung_pll46xx_mpk_change(con0, con1, rate))) {
 		/* If only s change, change just s value only*/
 		con0 &= ~(PLL46XX_SDIV_MASK << PLL46XX_SDIV_SHIFT);
 		con0 |= rate->sdiv << PLL46XX_SDIV_SHIFT;
-		__raw_writel(con0, pll->con_reg);
+		writel_relaxed(con0, pll->con_reg);
 
 		return 0;
 	}
@@ -596,7 +596,7 @@ static int samsung_pll46xx_set_rate(struct clk_hw *hw, unsigned long drate,
 			(rate->sdiv << PLL46XX_SDIV_SHIFT);
 
 	/* Set PLL K, MFR and MRR values. */
-	con1 = __raw_readl(pll->con_reg + 0x4);
+	con1 = readl_relaxed(pll->con_reg + 0x4);
 	con1 &= ~((PLL46XX_KDIV_MASK << PLL46XX_KDIV_SHIFT) |
 			(PLL46XX_MFR_MASK << PLL46XX_MFR_SHIFT) |
 			(PLL46XX_MRR_MASK << PLL46XX_MRR_SHIFT));
@@ -605,13 +605,13 @@ static int samsung_pll46xx_set_rate(struct clk_hw *hw, unsigned long drate,
 			(rate->mrr << PLL46XX_MRR_SHIFT);
 
 	/* Write configuration to PLL */
-	__raw_writel(lock, pll->lock_reg);
-	__raw_writel(con0, pll->con_reg);
-	__raw_writel(con1, pll->con_reg + 0x4);
+	writel_relaxed(lock, pll->lock_reg);
+	writel_relaxed(con0, pll->con_reg);
+	writel_relaxed(con1, pll->con_reg + 0x4);
 
 	/* Wait for locking. */
 	start = ktime_get();
-	while (!(__raw_readl(pll->con_reg) & PLL46XX_LOCKED)) {
+	while (!(readl_relaxed(pll->con_reg) & PLL46XX_LOCKED)) {
 		ktime_t delta = ktime_sub(ktime_get(), start);
 
 		if (ktime_to_ms(delta) > PLL_TIMEOUT_MS) {
@@ -656,7 +656,7 @@ static unsigned long samsung_pll6552_recalc_rate(struct clk_hw *hw,
 	u32 mdiv, pdiv, sdiv, pll_con;
 	u64 fvco = parent_rate;
 
-	pll_con = __raw_readl(pll->con_reg);
+	pll_con = readl_relaxed(pll->con_reg);
 	if (pll->type == pll_6552_s3c2416) {
 		mdiv = (pll_con >> PLL6552_MDIV_SHIFT_2416) & PLL6552_MDIV_MASK;
 		pdiv = (pll_con >> PLL6552_PDIV_SHIFT_2416) & PLL6552_PDIV_MASK;
@@ -696,8 +696,8 @@ static unsigned long samsung_pll6553_recalc_rate(struct clk_hw *hw,
 	u32 mdiv, pdiv, sdiv, kdiv, pll_con0, pll_con1;
 	u64 fvco = parent_rate;
 
-	pll_con0 = __raw_readl(pll->con_reg);
-	pll_con1 = __raw_readl(pll->con_reg + 0x4);
+	pll_con0 = readl_relaxed(pll->con_reg);
+	pll_con1 = readl_relaxed(pll->con_reg + 0x4);
 	mdiv = (pll_con0 >> PLL6553_MDIV_SHIFT) & PLL6553_MDIV_MASK;
 	pdiv = (pll_con0 >> PLL6553_PDIV_SHIFT) & PLL6553_PDIV_MASK;
 	sdiv = (pll_con0 >> PLL6553_SDIV_SHIFT) & PLL6553_SDIV_MASK;
@@ -734,7 +734,7 @@ static unsigned long samsung_s3c2410_pll_recalc_rate(struct clk_hw *hw,
 	u32 pll_con, mdiv, pdiv, sdiv;
 	u64 fvco = parent_rate;
 
-	pll_con = __raw_readl(pll->con_reg);
+	pll_con = readl_relaxed(pll->con_reg);
 	mdiv = (pll_con >> PLLS3C2410_MDIV_SHIFT) & PLLS3C2410_MDIV_MASK;
 	pdiv = (pll_con >> PLLS3C2410_PDIV_SHIFT) & PLLS3C2410_PDIV_MASK;
 	sdiv = (pll_con >> PLLS3C2410_SDIV_SHIFT) & PLLS3C2410_SDIV_MASK;
@@ -752,7 +752,7 @@ static unsigned long samsung_s3c2440_mpll_recalc_rate(struct clk_hw *hw,
 	u32 pll_con, mdiv, pdiv, sdiv;
 	u64 fvco = parent_rate;
 
-	pll_con = __raw_readl(pll->con_reg);
+	pll_con = readl_relaxed(pll->con_reg);
 	mdiv = (pll_con >> PLLS3C2410_MDIV_SHIFT) & PLLS3C2410_MDIV_MASK;
 	pdiv = (pll_con >> PLLS3C2410_PDIV_SHIFT) & PLLS3C2410_PDIV_MASK;
 	sdiv = (pll_con >> PLLS3C2410_SDIV_SHIFT) & PLLS3C2410_SDIV_MASK;
@@ -778,7 +778,7 @@ static int samsung_s3c2410_pll_set_rate(struct clk_hw *hw, unsigned long drate,
 		return -EINVAL;
 	}
 
-	tmp = __raw_readl(pll->con_reg);
+	tmp = readl_relaxed(pll->con_reg);
 
 	/* Change PLL PMS values */
 	tmp &= ~((PLLS3C2410_MDIV_MASK << PLLS3C2410_MDIV_SHIFT) |
@@ -787,7 +787,7 @@ static int samsung_s3c2410_pll_set_rate(struct clk_hw *hw, unsigned long drate,
 	tmp |= (rate->mdiv << PLLS3C2410_MDIV_SHIFT) |
 			(rate->pdiv << PLLS3C2410_PDIV_SHIFT) |
 			(rate->sdiv << PLLS3C2410_SDIV_SHIFT);
-	__raw_writel(tmp, pll->con_reg);
+	writel_relaxed(tmp, pll->con_reg);
 
 	/* Time to settle according to the manual */
 	udelay(300);
@@ -798,7 +798,7 @@ static int samsung_s3c2410_pll_set_rate(struct clk_hw *hw, unsigned long drate,
 static int samsung_s3c2410_pll_enable(struct clk_hw *hw, int bit, bool enable)
 {
 	struct samsung_clk_pll *pll = to_clk_pll(hw);
-	u32 pll_en = __raw_readl(pll->lock_reg + PLLS3C2410_ENABLE_REG_OFFSET);
+	u32 pll_en = readl_relaxed(pll->lock_reg + PLLS3C2410_ENABLE_REG_OFFSET);
 	u32 pll_en_orig = pll_en;
 
 	if (enable)
@@ -806,7 +806,7 @@ static int samsung_s3c2410_pll_enable(struct clk_hw *hw, int bit, bool enable)
 	else
 		pll_en |= BIT(bit);
 
-	__raw_writel(pll_en, pll->lock_reg + PLLS3C2410_ENABLE_REG_OFFSET);
+	writel_relaxed(pll_en, pll->lock_reg + PLLS3C2410_ENABLE_REG_OFFSET);
 
 	/* if we started the UPLL, then allow to settle */
 	if (enable && (pll_en_orig & BIT(bit)))
@@ -905,7 +905,7 @@ static unsigned long samsung_pll2550x_recalc_rate(struct clk_hw *hw,
 	u32 r, p, m, s, pll_stat;
 	u64 fvco = parent_rate;
 
-	pll_stat = __raw_readl(pll->reg_base + pll->offset * 3);
+	pll_stat = readl_relaxed(pll->reg_base + pll->offset * 3);
 	r = (pll_stat >> PLL2550X_R_SHIFT) & PLL2550X_R_MASK;
 	if (!r)
 		return 0;
@@ -983,7 +983,7 @@ static unsigned long samsung_pll2550xx_recalc_rate(struct clk_hw *hw,
 	u32 mdiv, pdiv, sdiv, pll_con;
 	u64 fvco = parent_rate;
 
-	pll_con = __raw_readl(pll->con_reg);
+	pll_con = readl_relaxed(pll->con_reg);
 	mdiv = (pll_con >> PLL2550XX_M_SHIFT) & PLL2550XX_M_MASK;
 	pdiv = (pll_con >> PLL2550XX_P_SHIFT) & PLL2550XX_P_MASK;
 	sdiv = (pll_con >> PLL2550XX_S_SHIFT) & PLL2550XX_S_MASK;
@@ -1019,19 +1019,19 @@ static int samsung_pll2550xx_set_rate(struct clk_hw *hw, unsigned long drate,
 		return -EINVAL;
 	}
 
-	tmp = __raw_readl(pll->con_reg);
+	tmp = readl_relaxed(pll->con_reg);
 
 	if (!(samsung_pll2550xx_mp_change(rate->mdiv, rate->pdiv, tmp))) {
 		/* If only s change, change just s value only*/
 		tmp &= ~(PLL2550XX_S_MASK << PLL2550XX_S_SHIFT);
 		tmp |= rate->sdiv << PLL2550XX_S_SHIFT;
-		__raw_writel(tmp, pll->con_reg);
+		writel_relaxed(tmp, pll->con_reg);
 
 		return 0;
 	}
 
 	/* Set PLL lock time. */
-	__raw_writel(rate->pdiv * PLL2550XX_LOCK_FACTOR, pll->lock_reg);
+	writel_relaxed(rate->pdiv * PLL2550XX_LOCK_FACTOR, pll->lock_reg);
 
 	/* Change PLL PMS values */
 	tmp &= ~((PLL2550XX_M_MASK << PLL2550XX_M_SHIFT) |
@@ -1040,12 +1040,12 @@ static int samsung_pll2550xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	tmp |= (rate->mdiv << PLL2550XX_M_SHIFT) |
 			(rate->pdiv << PLL2550XX_P_SHIFT) |
 			(rate->sdiv << PLL2550XX_S_SHIFT);
-	__raw_writel(tmp, pll->con_reg);
+	writel_relaxed(tmp, pll->con_reg);
 
 	/* wait_lock_time */
 	do {
 		cpu_relax();
-		tmp = __raw_readl(pll->con_reg);
+		tmp = readl_relaxed(pll->con_reg);
 	} while (!(tmp & (PLL2550XX_LOCK_STAT_MASK
 			<< PLL2550XX_LOCK_STAT_SHIFT)));
 
@@ -1089,8 +1089,8 @@ static unsigned long samsung_pll2650xx_recalc_rate(struct clk_hw *hw,
 	s16 kdiv;
 	u64 fvco = parent_rate;
 
-	pll_con0 = __raw_readl(pll->con_reg);
-	pll_con2 = __raw_readl(pll->con_reg + 8);
+	pll_con0 = readl_relaxed(pll->con_reg);
+	pll_con2 = readl_relaxed(pll->con_reg + 8);
 	mdiv = (pll_con0 >> PLL2650XX_MDIV_SHIFT) & PLL2650XX_MDIV_MASK;
 	pdiv = (pll_con0 >> PLL2650XX_PDIV_SHIFT) & PLL2650XX_PDIV_MASK;
 	sdiv = (pll_con0 >> PLL2650XX_SDIV_SHIFT) & PLL2650XX_SDIV_MASK;
@@ -1117,8 +1117,8 @@ static int samsung_pll2650xx_set_rate(struct clk_hw *hw, unsigned long drate,
 		return -EINVAL;
 	}
 
-	pll_con0 = __raw_readl(pll->con_reg);
-	pll_con2 = __raw_readl(pll->con_reg + 8);
+	pll_con0 = readl_relaxed(pll->con_reg);
+	pll_con2 = readl_relaxed(pll->con_reg + 8);
 
 	 /* Change PLL PMS values */
 	pll_con0 &= ~(PLL2650XX_MDIV_MASK << PLL2650XX_MDIV_SHIFT |
@@ -1135,13 +1135,13 @@ static int samsung_pll2650xx_set_rate(struct clk_hw *hw, unsigned long drate,
 			<< PLL2650XX_KDIV_SHIFT;
 
 	/* Set PLL lock time. */
-	__raw_writel(PLL2650XX_LOCK_FACTOR * rate->pdiv, pll->lock_reg);
+	writel_relaxed(PLL2650XX_LOCK_FACTOR * rate->pdiv, pll->lock_reg);
 
-	__raw_writel(pll_con0, pll->con_reg);
-	__raw_writel(pll_con2, pll->con_reg + 8);
+	writel_relaxed(pll_con0, pll->con_reg);
+	writel_relaxed(pll_con2, pll->con_reg + 8);
 
 	do {
-		tmp = __raw_readl(pll->con_reg);
+		tmp = readl_relaxed(pll->con_reg);
 	} while (!(tmp & (0x1 << PLL2650XX_PLL_LOCKTIME_SHIFT)));
 
 	return 0;
diff --git a/drivers/clk/samsung/clk-s3c2410-dclk.c b/drivers/clk/samsung/clk-s3c2410-dclk.c
index ec6fb14d951c..ae9a595c72d0 100644
--- a/drivers/clk/samsung/clk-s3c2410-dclk.c
+++ b/drivers/clk/samsung/clk-s3c2410-dclk.c
@@ -428,8 +428,9 @@ MODULE_DEVICE_TABLE(platform, s3c24xx_dclk_driver_ids);
 
 static struct platform_driver s3c24xx_dclk_driver = {
 	.driver = {
-		.name		= "s3c24xx-dclk",
-		.pm		= &s3c24xx_dclk_pm_ops,
+		.name			= "s3c24xx-dclk",
+		.pm			= &s3c24xx_dclk_pm_ops,
+		.suppress_bind_attrs	= true,
 	},
 	.probe = s3c24xx_dclk_probe,
 	.remove = s3c24xx_dclk_remove,
diff --git a/drivers/clk/samsung/clk-s3c2410.c b/drivers/clk/samsung/clk-s3c2410.c
index d7b011c1fcf8..d7a1e772d95a 100644
--- a/drivers/clk/samsung/clk-s3c2410.c
+++ b/drivers/clk/samsung/clk-s3c2410.c
@@ -374,8 +374,6 @@ void __init s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f,
 	}
 
 	ctx = samsung_clk_init(np, reg_base, NR_CLKS);
-	if (!ctx)
-		panic("%s: unable to allocate context.\n", __func__);
 
 	/* Register external clocks only in non-dt cases */
 	if (!np)
diff --git a/drivers/clk/samsung/clk-s3c2412.c b/drivers/clk/samsung/clk-s3c2412.c
index effe3736ec6b..ec873ee15d37 100644
--- a/drivers/clk/samsung/clk-s3c2412.c
+++ b/drivers/clk/samsung/clk-s3c2412.c
@@ -265,8 +265,6 @@ void __init s3c2412_common_clk_init(struct device_node *np, unsigned long xti_f,
 	}
 
 	ctx = samsung_clk_init(np, reg_base, NR_CLKS);
-	if (!ctx)
-		panic("%s: unable to allocate context.\n", __func__);
 
 	/* Register external clocks only in non-dt cases */
 	if (!np)
diff --git a/drivers/clk/samsung/clk-s3c2443.c b/drivers/clk/samsung/clk-s3c2443.c
index 37562783b25e..5e24a17e10e6 100644
--- a/drivers/clk/samsung/clk-s3c2443.c
+++ b/drivers/clk/samsung/clk-s3c2443.c
@@ -400,8 +400,6 @@ void __init s3c2443_common_clk_init(struct device_node *np, unsigned long xti_f,
 	}
 
 	ctx = samsung_clk_init(np, reg_base, NR_CLKS);
-	if (!ctx)
-		panic("%s: unable to allocate context.\n", __func__);
 
 	/* Register external clocks only in non-dt cases */
 	if (!np)
diff --git a/drivers/clk/samsung/clk-s3c64xx.c b/drivers/clk/samsung/clk-s3c64xx.c
index 60aa775bd374..a48bd5f17330 100644
--- a/drivers/clk/samsung/clk-s3c64xx.c
+++ b/drivers/clk/samsung/clk-s3c64xx.c
@@ -471,8 +471,6 @@ void __init s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f,
 	}
 
 	ctx = samsung_clk_init(np, reg_base, NR_CLKS);
-	if (!ctx)
-		panic("%s: unable to allocate context.\n", __func__);
 
 	/* Register external clocks. */
 	if (!np)
diff --git a/drivers/clk/samsung/clk-s5pv210-audss.c b/drivers/clk/samsung/clk-s5pv210-audss.c
index eefb84b22566..c66ed2d1450e 100644
--- a/drivers/clk/samsung/clk-s5pv210-audss.c
+++ b/drivers/clk/samsung/clk-s5pv210-audss.c
@@ -18,7 +18,7 @@
 #include <linux/clk-provider.h>
 #include <linux/of_address.h>
 #include <linux/syscore_ops.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/platform_device.h>
 
 #include <dt-bindings/clock/s5pv210-audss.h>
@@ -194,20 +194,6 @@ unregister:
 	return ret;
 }
 
-static int s5pv210_audss_clk_remove(struct platform_device *pdev)
-{
-	int i;
-
-	of_clk_del_provider(pdev->dev.of_node);
-
-	for (i = 0; i < clk_data.clk_num; i++) {
-		if (!IS_ERR(clk_table[i]))
-			clk_unregister(clk_table[i]);
-	}
-
-	return 0;
-}
-
 static const struct of_device_id s5pv210_audss_clk_of_match[] = {
 	{ .compatible = "samsung,s5pv210-audss-clock", },
 	{},
@@ -216,10 +202,10 @@ static const struct of_device_id s5pv210_audss_clk_of_match[] = {
 static struct platform_driver s5pv210_audss_clk_driver = {
 	.driver	= {
 		.name = "s5pv210-audss-clk",
+		.suppress_bind_attrs = true,
 		.of_match_table = s5pv210_audss_clk_of_match,
 	},
 	.probe = s5pv210_audss_clk_probe,
-	.remove = s5pv210_audss_clk_remove,
 };
 
 static int __init s5pv210_audss_clk_init(void)
@@ -227,14 +213,3 @@ static int __init s5pv210_audss_clk_init(void)
 	return platform_driver_register(&s5pv210_audss_clk_driver);
 }
 core_initcall(s5pv210_audss_clk_init);
-
-static void __exit s5pv210_audss_clk_exit(void)
-{
-	platform_driver_unregister(&s5pv210_audss_clk_driver);
-}
-module_exit(s5pv210_audss_clk_exit);
-
-MODULE_AUTHOR("Tomasz Figa <t.figa@samsung.com>");
-MODULE_DESCRIPTION("S5PV210 Audio Subsystem Clock Controller");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:s5pv210-audss-clk");
diff --git a/drivers/clk/samsung/clk-s5pv210.c b/drivers/clk/samsung/clk-s5pv210.c
index 52302262045d..fd2725710a6f 100644
--- a/drivers/clk/samsung/clk-s5pv210.c
+++ b/drivers/clk/samsung/clk-s5pv210.c
@@ -784,8 +784,6 @@ static void __init __s5pv210_clk_init(struct device_node *np,
 	struct samsung_clk_provider *ctx;
 
 	ctx = samsung_clk_init(np, reg_base, NR_CLKS);
-	if (!ctx)
-		panic("%s: unable to allocate context.\n", __func__);
 
 	samsung_clk_register_mux(ctx, early_mux_clks,
 					ARRAY_SIZE(early_mux_clks));
diff --git a/drivers/clk/samsung/clk.c b/drivers/clk/samsung/clk.c
index f38a6c49f744..b7d87d6db9dc 100644
--- a/drivers/clk/samsung/clk.c
+++ b/drivers/clk/samsung/clk.c
@@ -346,9 +346,9 @@ static struct syscore_ops samsung_clk_syscore_ops = {
 	.resume = samsung_clk_resume,
 };
 
-static void samsung_clk_sleep_init(void __iomem *reg_base,
-		const unsigned long *rdump,
-		unsigned long nr_rdump)
+void samsung_clk_sleep_init(void __iomem *reg_base,
+			const unsigned long *rdump,
+			unsigned long nr_rdump)
 {
 	struct samsung_clock_reg_cache *reg_cache;
 
@@ -370,9 +370,9 @@ static void samsung_clk_sleep_init(void __iomem *reg_base,
 }
 
 #else
-static void samsung_clk_sleep_init(void __iomem *reg_base,
-		const unsigned long *rdump,
-		unsigned long nr_rdump) {}
+void samsung_clk_sleep_init(void __iomem *reg_base,
+			const unsigned long *rdump,
+			unsigned long nr_rdump) {}
 #endif
 
 /*
@@ -381,7 +381,7 @@ static void samsung_clk_sleep_init(void __iomem *reg_base,
  */
 struct samsung_clk_provider * __init samsung_cmu_register_one(
 			struct device_node *np,
-			struct samsung_cmu_info *cmu)
+			const struct samsung_cmu_info *cmu)
 {
 	void __iomem *reg_base;
 	struct samsung_clk_provider *ctx;
diff --git a/drivers/clk/samsung/clk.h b/drivers/clk/samsung/clk.h
index aa872d2c5105..da3bdebabf1e 100644
--- a/drivers/clk/samsung/clk.h
+++ b/drivers/clk/samsung/clk.h
@@ -261,7 +261,7 @@ struct samsung_gate_clock {
 #define GATE_DA(_id, dname, cname, pname, o, b, f, gf, a)	\
 	__GATE(_id, dname, cname, pname, o, b, f, gf, a)
 
-#define PNAME(x) static const char *x[] __initdata
+#define PNAME(x) static const char * const x[] __initconst
 
 /**
  * struct samsung_clk_reg_dump: register dump of clock controller registers.
@@ -330,28 +330,28 @@ struct samsung_clock_reg_cache {
 
 struct samsung_cmu_info {
 	/* list of pll clocks and respective count */
-	struct samsung_pll_clock *pll_clks;
+	const struct samsung_pll_clock *pll_clks;
 	unsigned int nr_pll_clks;
 	/* list of mux clocks and respective count */
-	struct samsung_mux_clock *mux_clks;
+	const struct samsung_mux_clock *mux_clks;
 	unsigned int nr_mux_clks;
 	/* list of div clocks and respective count */
-	struct samsung_div_clock *div_clks;
+	const struct samsung_div_clock *div_clks;
 	unsigned int nr_div_clks;
 	/* list of gate clocks and respective count */
-	struct samsung_gate_clock *gate_clks;
+	const struct samsung_gate_clock *gate_clks;
 	unsigned int nr_gate_clks;
 	/* list of fixed clocks and respective count */
-	struct samsung_fixed_rate_clock *fixed_clks;
+	const struct samsung_fixed_rate_clock *fixed_clks;
 	unsigned int nr_fixed_clks;
 	/* list of fixed factor clocks and respective count */
-	struct samsung_fixed_factor_clock *fixed_factor_clks;
+	const struct samsung_fixed_factor_clock *fixed_factor_clks;
 	unsigned int nr_fixed_factor_clks;
 	/* total number of clocks with IDs assigned*/
 	unsigned int nr_clk_ids;
 
 	/* list and number of clocks registers */
-	unsigned long *clk_regs;
+	const unsigned long *clk_regs;
 	unsigned int nr_clk_regs;
 };
 
@@ -395,10 +395,14 @@ extern void __init samsung_clk_register_pll(struct samsung_clk_provider *ctx,
 
 extern struct samsung_clk_provider __init *samsung_cmu_register_one(
 			struct device_node *,
-			struct samsung_cmu_info *);
+			const struct samsung_cmu_info *);
 
 extern unsigned long _get_rate(const char *clk_name);
 
+extern void samsung_clk_sleep_init(void __iomem *reg_base,
+			const unsigned long *rdump,
+			unsigned long nr_rdump);
+
 extern void samsung_clk_save(void __iomem *base,
 			struct samsung_clk_reg_dump *rd,
 			unsigned int num_regs);
diff --git a/drivers/clk/st/clk-flexgen.c b/drivers/clk/st/clk-flexgen.c
index 627267c7ec5c..546bd79c8e3a 100644
--- a/drivers/clk/st/clk-flexgen.c
+++ b/drivers/clk/st/clk-flexgen.c
@@ -267,7 +267,6 @@ static void __init st_of_flexgen_setup(struct device_node *np)
 	const char **parents;
 	int num_parents, i;
 	spinlock_t *rlock = NULL;
-	unsigned long flex_flags = 0;
 	int ret;
 
 	pnode = of_get_parent(np);
@@ -308,12 +307,15 @@ static void __init st_of_flexgen_setup(struct device_node *np)
 	for (i = 0; i < clk_data->clk_num; i++) {
 		struct clk *clk;
 		const char *clk_name;
+		unsigned long flex_flags = 0;
 
 		if (of_property_read_string_index(np, "clock-output-names",
 						  i, &clk_name)) {
 			break;
 		}
 
+		of_clk_detect_critical(np, i, &flex_flags);
+
 		/*
 		 * If we read an empty clock name then the output is unused
 		 */
diff --git a/drivers/clk/st/clkgen-fsyn.c b/drivers/clk/st/clkgen-fsyn.c
index dec4eaaecc00..09afeb85109c 100644
--- a/drivers/clk/st/clkgen-fsyn.c
+++ b/drivers/clk/st/clkgen-fsyn.c
@@ -1027,7 +1027,7 @@ static const struct clk_ops st_quadfs_ops = {
 static struct clk * __init st_clk_register_quadfs_fsynth(
 		const char *name, const char *parent_name,
 		struct clkgen_quadfs_data *quadfs, void __iomem *reg, u32 chan,
-		spinlock_t *lock)
+		unsigned long flags, spinlock_t *lock)
 {
 	struct st_clk_quadfs_fsynth *fs;
 	struct clk *clk;
@@ -1045,7 +1045,7 @@ static struct clk * __init st_clk_register_quadfs_fsynth(
 
 	init.name = name;
 	init.ops = &st_quadfs_ops;
-	init.flags = CLK_GET_RATE_NOCACHE | CLK_IS_BASIC;
+	init.flags = flags | CLK_GET_RATE_NOCACHE | CLK_IS_BASIC;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
 
@@ -1115,6 +1115,7 @@ static void __init st_of_create_quadfs_fsynths(
 	for (fschan = 0; fschan < QUADFS_MAX_CHAN; fschan++) {
 		struct clk *clk;
 		const char *clk_name;
+		unsigned long flags = 0;
 
 		if (of_property_read_string_index(np, "clock-output-names",
 						  fschan, &clk_name)) {
@@ -1127,8 +1128,11 @@ static void __init st_of_create_quadfs_fsynths(
 		if (*clk_name == '\0')
 			continue;
 
+		of_clk_detect_critical(np, fschan, &flags);
+
 		clk = st_clk_register_quadfs_fsynth(clk_name, pll_name,
-				quadfs, reg, fschan, lock);
+						    quadfs, reg, fschan,
+						    flags, lock);
 
 		/*
 		 * If there was an error registering this clock output, clean
diff --git a/drivers/clk/st/clkgen-pll.c b/drivers/clk/st/clkgen-pll.c
index 38f6f3a9098e..0b5990e82e0d 100644
--- a/drivers/clk/st/clkgen-pll.c
+++ b/drivers/clk/st/clkgen-pll.c
@@ -840,7 +840,7 @@ static const struct clk_ops stm_pll4600c28_ops = {
 
 static struct clk * __init clkgen_pll_register(const char *parent_name,
 				struct clkgen_pll_data	*pll_data,
-				void __iomem *reg,
+				void __iomem *reg, unsigned long pll_flags,
 				const char *clk_name, spinlock_t *lock)
 {
 	struct clkgen_pll *pll;
@@ -854,7 +854,7 @@ static struct clk * __init clkgen_pll_register(const char *parent_name,
 	init.name = clk_name;
 	init.ops = pll_data->ops;
 
-	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
+	init.flags = pll_flags | CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
 	init.parent_names = &parent_name;
 	init.num_parents  = 1;
 
@@ -948,7 +948,7 @@ static void __init clkgena_c65_pll_setup(struct device_node *np)
 	 */
 	clk_data->clks[0] = clkgen_pll_register(parent_name,
 			(struct clkgen_pll_data *) &st_pll1600c65_ax,
-			reg + CLKGENAx_PLL0_OFFSET, clk_name, NULL);
+			reg + CLKGENAx_PLL0_OFFSET, 0, clk_name, NULL);
 
 	if (IS_ERR(clk_data->clks[0]))
 		goto err;
@@ -977,7 +977,7 @@ static void __init clkgena_c65_pll_setup(struct device_node *np)
 	 */
 	clk_data->clks[2] = clkgen_pll_register(parent_name,
 			(struct clkgen_pll_data *) &st_pll800c65_ax,
-			reg + CLKGENAx_PLL1_OFFSET, clk_name, NULL);
+			reg + CLKGENAx_PLL1_OFFSET, 0, clk_name, NULL);
 
 	if (IS_ERR(clk_data->clks[2]))
 		goto err;
@@ -995,7 +995,7 @@ CLK_OF_DECLARE(clkgena_c65_plls,
 static struct clk * __init clkgen_odf_register(const char *parent_name,
 					       void __iomem *reg,
 					       struct clkgen_pll_data *pll_data,
-					       int odf,
+					       unsigned long pll_flags, int odf,
 					       spinlock_t *odf_lock,
 					       const char *odf_name)
 {
@@ -1004,7 +1004,7 @@ static struct clk * __init clkgen_odf_register(const char *parent_name,
 	struct clk_gate *gate;
 	struct clk_divider *div;
 
-	flags = CLK_GET_RATE_NOCACHE | CLK_SET_RATE_PARENT;
+	flags = pll_flags | CLK_GET_RATE_NOCACHE | CLK_SET_RATE_PARENT;
 
 	gate = kzalloc(sizeof(*gate), GFP_KERNEL);
 	if (!gate)
@@ -1099,6 +1099,7 @@ static void __init clkgen_c32_pll_setup(struct device_node *np)
 	int num_odfs, odf;
 	struct clk_onecell_data *clk_data;
 	struct clkgen_pll_data	*data;
+	unsigned long pll_flags = 0;
 
 	match = of_match_node(c32_pll_of_match, np);
 	if (!match) {
@@ -1116,8 +1117,10 @@ static void __init clkgen_c32_pll_setup(struct device_node *np)
 	if (!pll_base)
 		return;
 
-	clk = clkgen_pll_register(parent_name, data, pll_base, np->name,
-				  data->lock);
+	of_clk_detect_critical(np, 0, &pll_flags);
+
+	clk = clkgen_pll_register(parent_name, data, pll_base, pll_flags,
+				  np->name, data->lock);
 	if (IS_ERR(clk))
 		return;
 
@@ -1139,12 +1142,15 @@ static void __init clkgen_c32_pll_setup(struct device_node *np)
 	for (odf = 0; odf < num_odfs; odf++) {
 		struct clk *clk;
 		const char *clk_name;
+		unsigned long odf_flags = 0;
 
 		if (of_property_read_string_index(np, "clock-output-names",
 						  odf, &clk_name))
 			return;
 
-		clk = clkgen_odf_register(pll_name, pll_base, data,
+		of_clk_detect_critical(np, odf, &odf_flags);
+
+		clk = clkgen_odf_register(pll_name, pll_base, data, odf_flags,
 				odf, &clkgena_c32_odf_lock, clk_name);
 		if (IS_ERR(clk))
 			goto err;
@@ -1206,7 +1212,8 @@ static void __init clkgengpu_c32_pll_setup(struct device_node *np)
 	/*
 	 * PLL 1200MHz output
 	 */
-	clk = clkgen_pll_register(parent_name, data, reg, clk_name, data->lock);
+	clk = clkgen_pll_register(parent_name, data, reg,
+				  0, clk_name, data->lock);
 
 	if (!IS_ERR(clk))
 		of_clk_add_provider(np, of_clk_src_simple_get, clk);
diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig
new file mode 100644
index 000000000000..2afcbd39e41e
--- /dev/null
+++ b/drivers/clk/sunxi-ng/Kconfig
@@ -0,0 +1,65 @@
+config SUNXI_CCU
+	bool "Clock support for Allwinner SoCs"
+	default ARCH_SUNXI
+
+if SUNXI_CCU
+
+# Base clock types
+
+config SUNXI_CCU_DIV
+	bool
+	select SUNXI_CCU_MUX
+
+config SUNXI_CCU_FRAC
+	bool
+
+config SUNXI_CCU_GATE
+	bool
+
+config SUNXI_CCU_MUX
+	bool
+
+config SUNXI_CCU_PHASE
+	bool
+
+# Multi-factor clocks
+
+config SUNXI_CCU_NK
+	bool
+	select SUNXI_CCU_GATE
+
+config SUNXI_CCU_NKM
+	bool
+	select RATIONAL
+	select SUNXI_CCU_GATE
+
+config SUNXI_CCU_NKMP
+	bool
+	select RATIONAL
+	select SUNXI_CCU_GATE
+
+config SUNXI_CCU_NM
+	bool
+	select RATIONAL
+	select SUNXI_CCU_FRAC
+	select SUNXI_CCU_GATE
+
+config SUNXI_CCU_MP
+	bool
+	select SUNXI_CCU_GATE
+	select SUNXI_CCU_MUX
+
+# SoC Drivers
+
+config SUN8I_H3_CCU
+	bool "Support for the Allwinner H3 CCU"
+	select SUNXI_CCU_DIV
+	select SUNXI_CCU_NK
+	select SUNXI_CCU_NKM
+	select SUNXI_CCU_NKMP
+	select SUNXI_CCU_NM
+	select SUNXI_CCU_MP
+	select SUNXI_CCU_PHASE
+	default MACH_SUN8I
+
+endif
diff --git a/drivers/clk/sunxi-ng/Makefile b/drivers/clk/sunxi-ng/Makefile
new file mode 100644
index 000000000000..633ce642ffae
--- /dev/null
+++ b/drivers/clk/sunxi-ng/Makefile
@@ -0,0 +1,20 @@
+# Common objects
+obj-$(CONFIG_SUNXI_CCU)		+= ccu_common.o
+obj-$(CONFIG_SUNXI_CCU)		+= ccu_reset.o
+
+# Base clock types
+obj-$(CONFIG_SUNXI_CCU_DIV)	+= ccu_div.o
+obj-$(CONFIG_SUNXI_CCU_FRAC)	+= ccu_frac.o
+obj-$(CONFIG_SUNXI_CCU_GATE)	+= ccu_gate.o
+obj-$(CONFIG_SUNXI_CCU_MUX)	+= ccu_mux.o
+obj-$(CONFIG_SUNXI_CCU_PHASE)	+= ccu_phase.o
+
+# Multi-factor clocks
+obj-$(CONFIG_SUNXI_CCU_NK)	+= ccu_nk.o
+obj-$(CONFIG_SUNXI_CCU_NKM)	+= ccu_nkm.o
+obj-$(CONFIG_SUNXI_CCU_NKMP)	+= ccu_nkmp.o
+obj-$(CONFIG_SUNXI_CCU_NM)	+= ccu_nm.o
+obj-$(CONFIG_SUNXI_CCU_MP)	+= ccu_mp.o
+
+# SoC support
+obj-$(CONFIG_SUN8I_H3_CCU)	+= ccu-sun8i-h3.o
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-h3.c b/drivers/clk/sunxi-ng/ccu-sun8i-h3.c
new file mode 100644
index 000000000000..9af359544110
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-h3.c
@@ -0,0 +1,826 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/of_address.h>
+
+#include "ccu_common.h"
+#include "ccu_reset.h"
+
+#include "ccu_div.h"
+#include "ccu_gate.h"
+#include "ccu_mp.h"
+#include "ccu_mult.h"
+#include "ccu_nk.h"
+#include "ccu_nkm.h"
+#include "ccu_nkmp.h"
+#include "ccu_nm.h"
+#include "ccu_phase.h"
+
+#include "ccu-sun8i-h3.h"
+
+static SUNXI_CCU_NKMP_WITH_GATE_LOCK(pll_cpux_clk, "pll-cpux",
+				     "osc24M", 0x000,
+				     8, 5,	/* N */
+				     4, 2,	/* K */
+				     0, 2,	/* M */
+				     16, 2,	/* P */
+				     BIT(31),	/* gate */
+				     BIT(28),	/* lock */
+				     0);
+
+/*
+ * The Audio PLL is supposed to have 4 outputs: 3 fixed factors from
+ * the base (2x, 4x and 8x), and one variable divider (the one true
+ * pll audio).
+ *
+ * We don't have any need for the variable divider for now, so we just
+ * hardcode it to match with the clock names
+ */
+#define SUN8I_H3_PLL_AUDIO_REG	0x008
+
+static SUNXI_CCU_NM_WITH_GATE_LOCK(pll_audio_base_clk, "pll-audio-base",
+				   "osc24M", 0x008,
+				   8, 7,	/* N */
+				   0, 5,	/* M */
+				   BIT(31),	/* gate */
+				   BIT(28),	/* lock */
+				   0);
+
+static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_video_clk, "pll-video",
+					"osc24M", 0x0010,
+					8, 7,		/* N */
+					0, 4,		/* M */
+					BIT(24),	/* frac enable */
+					BIT(25),	/* frac select */
+					270000000,	/* frac rate 0 */
+					297000000,	/* frac rate 1 */
+					BIT(31),	/* gate */
+					BIT(28),	/* lock */
+					0);
+
+static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_ve_clk, "pll-ve",
+					"osc24M", 0x0018,
+					8, 7,		/* N */
+					0, 4,		/* M */
+					BIT(24),	/* frac enable */
+					BIT(25),	/* frac select */
+					270000000,	/* frac rate 0 */
+					297000000,	/* frac rate 1 */
+					BIT(31),	/* gate */
+					BIT(28),	/* lock */
+					0);
+
+static SUNXI_CCU_NKM_WITH_GATE_LOCK(pll_ddr_clk, "pll-ddr",
+				    "osc24M", 0x020,
+				    8, 5,	/* N */
+				    4, 2,	/* K */
+				    0, 2,	/* M */
+				    BIT(31),	/* gate */
+				    BIT(28),	/* lock */
+				    0);
+
+static SUNXI_CCU_NK_WITH_GATE_LOCK_POSTDIV(pll_periph0_clk, "pll-periph0",
+					   "osc24M", 0x028,
+					   8, 5,	/* N */
+					   4, 2,	/* K */
+					   BIT(31),	/* gate */
+					   BIT(28),	/* lock */
+					   2,		/* post-div */
+					   0);
+
+static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_gpu_clk, "pll-gpu",
+					"osc24M", 0x0038,
+					8, 7,		/* N */
+					0, 4,		/* M */
+					BIT(24),	/* frac enable */
+					BIT(25),	/* frac select */
+					270000000,	/* frac rate 0 */
+					297000000,	/* frac rate 1 */
+					BIT(31),	/* gate */
+					BIT(28),	/* lock */
+					0);
+
+static SUNXI_CCU_NK_WITH_GATE_LOCK_POSTDIV(pll_periph1_clk, "pll-periph1",
+					   "osc24M", 0x044,
+					   8, 5,	/* N */
+					   4, 2,	/* K */
+					   BIT(31),	/* gate */
+					   BIT(28),	/* lock */
+					   2,		/* post-div */
+					   0);
+
+static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_de_clk, "pll-de",
+					"osc24M", 0x0048,
+					8, 7,		/* N */
+					0, 4,		/* M */
+					BIT(24),	/* frac enable */
+					BIT(25),	/* frac select */
+					270000000,	/* frac rate 0 */
+					297000000,	/* frac rate 1 */
+					BIT(31),	/* gate */
+					BIT(28),	/* lock */
+					0);
+
+static const char * const cpux_parents[] = { "osc32k", "osc24M",
+					     "pll-cpux" , "pll-cpux" };
+static SUNXI_CCU_MUX(cpux_clk, "cpux", cpux_parents,
+		     0x050, 16, 2, CLK_IS_CRITICAL);
+
+static SUNXI_CCU_M(axi_clk, "axi", "cpux", 0x050, 0, 2, 0);
+
+static const char * const ahb1_parents[] = { "osc32k", "osc24M",
+					     "axi" , "pll-periph0" };
+static struct ccu_div ahb1_clk = {
+	.div		= _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO),
+
+	.mux		= {
+		.shift	= 12,
+		.width	= 2,
+
+		.variable_prediv	= {
+			.index	= 3,
+			.shift	= 6,
+			.width	= 2,
+		},
+	},
+
+	.common		= {
+		.reg		= 0x054,
+		.features	= CCU_FEATURE_VARIABLE_PREDIV,
+		.hw.init	= CLK_HW_INIT_PARENTS("ahb1",
+						      ahb1_parents,
+						      &ccu_div_ops,
+						      0),
+	},
+};
+
+static struct clk_div_table apb1_div_table[] = {
+	{ .val = 0, .div = 2 },
+	{ .val = 1, .div = 2 },
+	{ .val = 2, .div = 4 },
+	{ .val = 3, .div = 8 },
+	{ /* Sentinel */ },
+};
+static SUNXI_CCU_DIV_TABLE(apb1_clk, "apb1", "ahb1",
+			   0x054, 8, 2, apb1_div_table, 0);
+
+static const char * const apb2_parents[] = { "osc32k", "osc24M",
+					     "pll-periph0" , "pll-periph0" };
+static SUNXI_CCU_MP_WITH_MUX(apb2_clk, "apb2", apb2_parents, 0x058,
+			     0, 5,	/* M */
+			     16, 2,	/* P */
+			     24, 2,	/* mux */
+			     0);
+
+static const char * const ahb2_parents[] = { "ahb1" , "pll-periph0" };
+static struct ccu_mux ahb2_clk = {
+	.mux		= {
+		.shift	= 0,
+		.width	= 1,
+
+		.fixed_prediv	= {
+			.index	= 1,
+			.div	= 2,
+		},
+	},
+
+	.common		= {
+		.reg		= 0x05c,
+		.features	= CCU_FEATURE_FIXED_PREDIV,
+		.hw.init	= CLK_HW_INIT_PARENTS("ahb2",
+						      ahb2_parents,
+						      &ccu_mux_ops,
+						      0),
+	},
+};
+
+static SUNXI_CCU_GATE(bus_ce_clk,	"bus-ce",	"ahb1",
+		      0x060, BIT(5), 0);
+static SUNXI_CCU_GATE(bus_dma_clk,	"bus-dma",	"ahb1",
+		      0x060, BIT(6), 0);
+static SUNXI_CCU_GATE(bus_mmc0_clk,	"bus-mmc0",	"ahb1",
+		      0x060, BIT(8), 0);
+static SUNXI_CCU_GATE(bus_mmc1_clk,	"bus-mmc1",	"ahb1",
+		      0x060, BIT(9), 0);
+static SUNXI_CCU_GATE(bus_mmc2_clk,	"bus-mmc2",	"ahb1",
+		      0x060, BIT(10), 0);
+static SUNXI_CCU_GATE(bus_nand_clk,	"bus-nand",	"ahb1",
+		      0x060, BIT(13), 0);
+static SUNXI_CCU_GATE(bus_dram_clk,	"bus-dram",	"ahb1",
+		      0x060, BIT(14), 0);
+static SUNXI_CCU_GATE(bus_emac_clk,	"bus-emac",	"ahb2",
+		      0x060, BIT(17), 0);
+static SUNXI_CCU_GATE(bus_ts_clk,	"bus-ts",	"ahb1",
+		      0x060, BIT(18), 0);
+static SUNXI_CCU_GATE(bus_hstimer_clk,	"bus-hstimer",	"ahb1",
+		      0x060, BIT(19), 0);
+static SUNXI_CCU_GATE(bus_spi0_clk,	"bus-spi0",	"ahb1",
+		      0x060, BIT(20), 0);
+static SUNXI_CCU_GATE(bus_spi1_clk,	"bus-spi1",	"ahb1",
+		      0x060, BIT(21), 0);
+static SUNXI_CCU_GATE(bus_otg_clk,	"bus-otg",	"ahb1",
+		      0x060, BIT(23), 0);
+static SUNXI_CCU_GATE(bus_ehci0_clk,	"bus-ehci0",	"ahb1",
+		      0x060, BIT(24), 0);
+static SUNXI_CCU_GATE(bus_ehci1_clk,	"bus-ehci1",	"ahb2",
+		      0x060, BIT(25), 0);
+static SUNXI_CCU_GATE(bus_ehci2_clk,	"bus-ehci2",	"ahb2",
+		      0x060, BIT(26), 0);
+static SUNXI_CCU_GATE(bus_ehci3_clk,	"bus-ehci3",	"ahb2",
+		      0x060, BIT(27), 0);
+static SUNXI_CCU_GATE(bus_ohci0_clk,	"bus-ohci0",	"ahb1",
+		      0x060, BIT(28), 0);
+static SUNXI_CCU_GATE(bus_ohci1_clk,	"bus-ohci1",	"ahb2",
+		      0x060, BIT(29), 0);
+static SUNXI_CCU_GATE(bus_ohci2_clk,	"bus-ohci2",	"ahb2",
+		      0x060, BIT(30), 0);
+static SUNXI_CCU_GATE(bus_ohci3_clk,	"bus-ohci3",	"ahb2",
+		      0x060, BIT(31), 0);
+
+static SUNXI_CCU_GATE(bus_ve_clk,	"bus-ve",	"ahb1",
+		      0x064, BIT(0), 0);
+static SUNXI_CCU_GATE(bus_tcon0_clk,	"bus-tcon0",	"ahb1",
+		      0x064, BIT(3), 0);
+static SUNXI_CCU_GATE(bus_tcon1_clk,	"bus-tcon1",	"ahb1",
+		      0x064, BIT(4), 0);
+static SUNXI_CCU_GATE(bus_deinterlace_clk,	"bus-deinterlace",	"ahb1",
+		      0x064, BIT(5), 0);
+static SUNXI_CCU_GATE(bus_csi_clk,	"bus-csi",	"ahb1",
+		      0x064, BIT(8), 0);
+static SUNXI_CCU_GATE(bus_tve_clk,	"bus-tve",	"ahb1",
+		      0x064, BIT(9), 0);
+static SUNXI_CCU_GATE(bus_hdmi_clk,	"bus-hdmi",	"ahb1",
+		      0x064, BIT(11), 0);
+static SUNXI_CCU_GATE(bus_de_clk,	"bus-de",	"ahb1",
+		      0x064, BIT(12), 0);
+static SUNXI_CCU_GATE(bus_gpu_clk,	"bus-gpu",	"ahb1",
+		      0x064, BIT(20), 0);
+static SUNXI_CCU_GATE(bus_msgbox_clk,	"bus-msgbox",	"ahb1",
+		      0x064, BIT(21), 0);
+static SUNXI_CCU_GATE(bus_spinlock_clk,	"bus-spinlock",	"ahb1",
+		      0x064, BIT(22), 0);
+
+static SUNXI_CCU_GATE(bus_codec_clk,	"bus-codec",	"apb1",
+		      0x068, BIT(0), 0);
+static SUNXI_CCU_GATE(bus_spdif_clk,	"bus-spdif",	"apb1",
+		      0x068, BIT(1), 0);
+static SUNXI_CCU_GATE(bus_pio_clk,	"bus-pio",	"apb1",
+		      0x068, BIT(5), 0);
+static SUNXI_CCU_GATE(bus_ths_clk,	"bus-ths",	"apb1",
+		      0x068, BIT(8), 0);
+static SUNXI_CCU_GATE(bus_i2s0_clk,	"bus-i2s0",	"apb1",
+		      0x068, BIT(12), 0);
+static SUNXI_CCU_GATE(bus_i2s1_clk,	"bus-i2s1",	"apb1",
+		      0x068, BIT(13), 0);
+static SUNXI_CCU_GATE(bus_i2s2_clk,	"bus-i2s2",	"apb1",
+		      0x068, BIT(14), 0);
+
+static SUNXI_CCU_GATE(bus_i2c0_clk,	"bus-i2c0",	"apb2",
+		      0x06c, BIT(0), 0);
+static SUNXI_CCU_GATE(bus_i2c1_clk,	"bus-i2c1",	"apb2",
+		      0x06c, BIT(1), 0);
+static SUNXI_CCU_GATE(bus_i2c2_clk,	"bus-i2c2",	"apb2",
+		      0x06c, BIT(2), 0);
+static SUNXI_CCU_GATE(bus_uart0_clk,	"bus-uart0",	"apb2",
+		      0x06c, BIT(16), 0);
+static SUNXI_CCU_GATE(bus_uart1_clk,	"bus-uart1",	"apb2",
+		      0x06c, BIT(17), 0);
+static SUNXI_CCU_GATE(bus_uart2_clk,	"bus-uart2",	"apb2",
+		      0x06c, BIT(18), 0);
+static SUNXI_CCU_GATE(bus_uart3_clk,	"bus-uart3",	"apb2",
+		      0x06c, BIT(19), 0);
+static SUNXI_CCU_GATE(bus_scr_clk,	"bus-scr",	"apb2",
+		      0x06c, BIT(20), 0);
+
+static SUNXI_CCU_GATE(bus_ephy_clk,	"bus-ephy",	"ahb1",
+		      0x070, BIT(0), 0);
+static SUNXI_CCU_GATE(bus_dbg_clk,	"bus-dbg",	"ahb1",
+		      0x070, BIT(7), 0);
+
+static struct clk_div_table ths_div_table[] = {
+	{ .val = 0, .div = 1 },
+	{ .val = 1, .div = 2 },
+	{ .val = 2, .div = 4 },
+	{ .val = 3, .div = 6 },
+};
+static SUNXI_CCU_DIV_TABLE_WITH_GATE(ths_clk, "ths", "osc24M",
+				     0x074, 0, 2, ths_div_table, BIT(31), 0);
+
+static const char * const mod0_default_parents[] = { "osc24M", "pll-periph0",
+						     "pll-periph1" };
+static SUNXI_CCU_MP_WITH_MUX_GATE(nand_clk, "nand", mod0_default_parents, 0x080,
+				  0, 4,		/* M */
+				  16, 2,	/* P */
+				  24, 2,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(mmc0_clk, "mmc0", mod0_default_parents, 0x088,
+				  0, 4,		/* M */
+				  16, 2,	/* P */
+				  24, 2,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_PHASE(mmc0_sample_clk, "mmc0_sample", "mmc0",
+		       0x088, 20, 3, 0);
+static SUNXI_CCU_PHASE(mmc0_output_clk, "mmc0_output", "mmc0",
+		       0x088, 8, 3, 0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(mmc1_clk, "mmc1", mod0_default_parents, 0x08c,
+				  0, 4,		/* M */
+				  16, 2,	/* P */
+				  24, 2,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_PHASE(mmc1_sample_clk, "mmc1_sample", "mmc1",
+		       0x08c, 20, 3, 0);
+static SUNXI_CCU_PHASE(mmc1_output_clk, "mmc1_output", "mmc1",
+		       0x08c, 8, 3, 0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(mmc2_clk, "mmc2", mod0_default_parents, 0x090,
+				  0, 4,		/* M */
+				  16, 2,	/* P */
+				  24, 2,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_PHASE(mmc2_sample_clk, "mmc2_sample", "mmc2",
+		       0x090, 20, 3, 0);
+static SUNXI_CCU_PHASE(mmc2_output_clk, "mmc2_output", "mmc2",
+		       0x090, 8, 3, 0);
+
+static const char * const ts_parents[] = { "osc24M", "pll-periph0", };
+static SUNXI_CCU_MP_WITH_MUX_GATE(ts_clk, "ts", ts_parents, 0x098,
+				  0, 4,		/* M */
+				  16, 2,	/* P */
+				  24, 2,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(ce_clk, "ce", mod0_default_parents, 0x09c,
+				  0, 4,		/* M */
+				  16, 2,	/* P */
+				  24, 2,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(spi0_clk, "spi0", mod0_default_parents, 0x0a0,
+				  0, 4,		/* M */
+				  16, 2,	/* P */
+				  24, 2,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(spi1_clk, "spi1", mod0_default_parents, 0x0a4,
+				  0, 4,		/* M */
+				  16, 2,	/* P */
+				  24, 2,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static const char * const i2s_parents[] = { "pll-audio-8x", "pll-audio-4x",
+					    "pll-audio-2x", "pll-audio" };
+static SUNXI_CCU_MUX_WITH_GATE(i2s0_clk, "i2s0", i2s_parents,
+			       0x0b0, 16, 2, BIT(31), 0);
+
+static SUNXI_CCU_MUX_WITH_GATE(i2s1_clk, "i2s1", i2s_parents,
+			       0x0b4, 16, 2, BIT(31), 0);
+
+static SUNXI_CCU_MUX_WITH_GATE(i2s2_clk, "i2s2", i2s_parents,
+			       0x0b8, 16, 2, BIT(31), 0);
+
+static SUNXI_CCU_M_WITH_GATE(spdif_clk, "spdif", "pll-audio",
+			     0x0c0, 0, 4, BIT(31), 0);
+
+static SUNXI_CCU_GATE(usb_phy0_clk,	"usb-phy0",	"osc24M",
+		      0x0cc, BIT(8), 0);
+static SUNXI_CCU_GATE(usb_phy1_clk,	"usb-phy1",	"osc24M",
+		      0x0cc, BIT(9), 0);
+static SUNXI_CCU_GATE(usb_phy2_clk,	"usb-phy2",	"osc24M",
+		      0x0cc, BIT(10), 0);
+static SUNXI_CCU_GATE(usb_phy3_clk,	"usb-phy3",	"osc24M",
+		      0x0cc, BIT(11), 0);
+static SUNXI_CCU_GATE(usb_ohci0_clk,	"usb-ohci0",	"osc24M",
+		      0x0cc, BIT(16), 0);
+static SUNXI_CCU_GATE(usb_ohci1_clk,	"usb-ohci1",	"osc24M",
+		      0x0cc, BIT(17), 0);
+static SUNXI_CCU_GATE(usb_ohci2_clk,	"usb-ohci2",	"osc24M",
+		      0x0cc, BIT(18), 0);
+static SUNXI_CCU_GATE(usb_ohci3_clk,	"usb-ohci3",	"osc24M",
+		      0x0cc, BIT(19), 0);
+
+static const char * const dram_parents[] = { "pll-ddr", "pll-periph0-2x" };
+static SUNXI_CCU_M_WITH_MUX(dram_clk, "dram", dram_parents,
+			    0x0f4, 0, 4, 20, 2, CLK_IS_CRITICAL);
+
+static SUNXI_CCU_GATE(dram_ve_clk,	"dram-ve",	"dram",
+		      0x100, BIT(0), 0);
+static SUNXI_CCU_GATE(dram_csi_clk,	"dram-csi",	"dram",
+		      0x100, BIT(1), 0);
+static SUNXI_CCU_GATE(dram_deinterlace_clk,	"dram-deinterlace",	"dram",
+		      0x100, BIT(2), 0);
+static SUNXI_CCU_GATE(dram_ts_clk,	"dram-ts",	"dram",
+		      0x100, BIT(3), 0);
+
+static const char * const de_parents[] = { "pll-periph0-2x", "pll-de" };
+static SUNXI_CCU_M_WITH_MUX_GATE(de_clk, "de", de_parents,
+				 0x104, 0, 4, 24, 3, BIT(31), 0);
+
+static const char * const tcon_parents[] = { "pll-video" };
+static SUNXI_CCU_M_WITH_MUX_GATE(tcon_clk, "tcon", tcon_parents,
+				 0x118, 0, 4, 24, 3, BIT(31), 0);
+
+static const char * const tve_parents[] = { "pll-de", "pll-periph1" };
+static SUNXI_CCU_M_WITH_MUX_GATE(tve_clk, "tve", tve_parents,
+				 0x120, 0, 4, 24, 3, BIT(31), 0);
+
+static const char * const deinterlace_parents[] = { "pll-periph0", "pll-periph1" };
+static SUNXI_CCU_M_WITH_MUX_GATE(deinterlace_clk, "deinterlace", deinterlace_parents,
+				 0x124, 0, 4, 24, 3, BIT(31), 0);
+
+static SUNXI_CCU_GATE(csi_misc_clk,	"csi-misc",	"osc24M",
+		      0x130, BIT(31), 0);
+
+static const char * const csi_sclk_parents[] = { "pll-periph0", "pll-periph1" };
+static SUNXI_CCU_M_WITH_MUX_GATE(csi_sclk_clk, "csi-sclk", csi_sclk_parents,
+				 0x134, 16, 4, 24, 3, BIT(31), 0);
+
+static const char * const csi_mclk_parents[] = { "osc24M", "pll-video", "pll-periph0" };
+static SUNXI_CCU_M_WITH_MUX_GATE(csi_mclk_clk, "csi-mclk", csi_mclk_parents,
+				 0x134, 0, 5, 8, 3, BIT(15), 0);
+
+static SUNXI_CCU_M_WITH_GATE(ve_clk, "ve", "pll-ve",
+			     0x13c, 16, 3, BIT(31), 0);
+
+static SUNXI_CCU_GATE(ac_dig_clk,	"ac-dig",	"pll-audio",
+		      0x140, BIT(31), 0);
+static SUNXI_CCU_GATE(avs_clk,		"avs",		"osc24M",
+		      0x144, BIT(31), 0);
+
+static const char * const hdmi_parents[] = { "pll-video" };
+static SUNXI_CCU_M_WITH_MUX_GATE(hdmi_clk, "hdmi", hdmi_parents,
+				 0x150, 0, 4, 24, 2, BIT(31), 0);
+
+static SUNXI_CCU_GATE(hdmi_ddc_clk,	"hdmi-ddc",	"osc24M",
+		      0x154, BIT(31), 0);
+
+static const char * const mbus_parents[] = { "osc24M", "pll-periph0-2x", "pll-ddr" };
+static SUNXI_CCU_M_WITH_MUX_GATE(mbus_clk, "mbus", mbus_parents,
+				 0x15c, 0, 3, 24, 2, BIT(31), CLK_IS_CRITICAL);
+
+static SUNXI_CCU_M_WITH_GATE(gpu_clk, "gpu", "pll-gpu",
+			     0x1a0, 0, 3, BIT(31), 0);
+
+static struct ccu_common *sun8i_h3_ccu_clks[] = {
+	&pll_cpux_clk.common,
+	&pll_audio_base_clk.common,
+	&pll_video_clk.common,
+	&pll_ve_clk.common,
+	&pll_ddr_clk.common,
+	&pll_periph0_clk.common,
+	&pll_gpu_clk.common,
+	&pll_periph1_clk.common,
+	&pll_de_clk.common,
+	&cpux_clk.common,
+	&axi_clk.common,
+	&ahb1_clk.common,
+	&apb1_clk.common,
+	&apb2_clk.common,
+	&ahb2_clk.common,
+	&bus_ce_clk.common,
+	&bus_dma_clk.common,
+	&bus_mmc0_clk.common,
+	&bus_mmc1_clk.common,
+	&bus_mmc2_clk.common,
+	&bus_nand_clk.common,
+	&bus_dram_clk.common,
+	&bus_emac_clk.common,
+	&bus_ts_clk.common,
+	&bus_hstimer_clk.common,
+	&bus_spi0_clk.common,
+	&bus_spi1_clk.common,
+	&bus_otg_clk.common,
+	&bus_ehci0_clk.common,
+	&bus_ehci1_clk.common,
+	&bus_ehci2_clk.common,
+	&bus_ehci3_clk.common,
+	&bus_ohci0_clk.common,
+	&bus_ohci1_clk.common,
+	&bus_ohci2_clk.common,
+	&bus_ohci3_clk.common,
+	&bus_ve_clk.common,
+	&bus_tcon0_clk.common,
+	&bus_tcon1_clk.common,
+	&bus_deinterlace_clk.common,
+	&bus_csi_clk.common,
+	&bus_tve_clk.common,
+	&bus_hdmi_clk.common,
+	&bus_de_clk.common,
+	&bus_gpu_clk.common,
+	&bus_msgbox_clk.common,
+	&bus_spinlock_clk.common,
+	&bus_codec_clk.common,
+	&bus_spdif_clk.common,
+	&bus_pio_clk.common,
+	&bus_ths_clk.common,
+	&bus_i2s0_clk.common,
+	&bus_i2s1_clk.common,
+	&bus_i2s2_clk.common,
+	&bus_i2c0_clk.common,
+	&bus_i2c1_clk.common,
+	&bus_i2c2_clk.common,
+	&bus_uart0_clk.common,
+	&bus_uart1_clk.common,
+	&bus_uart2_clk.common,
+	&bus_uart3_clk.common,
+	&bus_scr_clk.common,
+	&bus_ephy_clk.common,
+	&bus_dbg_clk.common,
+	&ths_clk.common,
+	&nand_clk.common,
+	&mmc0_clk.common,
+	&mmc0_sample_clk.common,
+	&mmc0_output_clk.common,
+	&mmc1_clk.common,
+	&mmc1_sample_clk.common,
+	&mmc1_output_clk.common,
+	&mmc2_clk.common,
+	&mmc2_sample_clk.common,
+	&mmc2_output_clk.common,
+	&ts_clk.common,
+	&ce_clk.common,
+	&spi0_clk.common,
+	&spi1_clk.common,
+	&i2s0_clk.common,
+	&i2s1_clk.common,
+	&i2s2_clk.common,
+	&spdif_clk.common,
+	&usb_phy0_clk.common,
+	&usb_phy1_clk.common,
+	&usb_phy2_clk.common,
+	&usb_phy3_clk.common,
+	&usb_ohci0_clk.common,
+	&usb_ohci1_clk.common,
+	&usb_ohci2_clk.common,
+	&usb_ohci3_clk.common,
+	&dram_clk.common,
+	&dram_ve_clk.common,
+	&dram_csi_clk.common,
+	&dram_deinterlace_clk.common,
+	&dram_ts_clk.common,
+	&de_clk.common,
+	&tcon_clk.common,
+	&tve_clk.common,
+	&deinterlace_clk.common,
+	&csi_misc_clk.common,
+	&csi_sclk_clk.common,
+	&csi_mclk_clk.common,
+	&ve_clk.common,
+	&ac_dig_clk.common,
+	&avs_clk.common,
+	&hdmi_clk.common,
+	&hdmi_ddc_clk.common,
+	&mbus_clk.common,
+	&gpu_clk.common,
+};
+
+/* We hardcode the divider to 4 for now */
+static CLK_FIXED_FACTOR(pll_audio_clk, "pll-audio",
+			"pll-audio-base", 4, 1, CLK_SET_RATE_PARENT);
+static CLK_FIXED_FACTOR(pll_audio_2x_clk, "pll-audio-2x",
+			"pll-audio-base", 2, 1, CLK_SET_RATE_PARENT);
+static CLK_FIXED_FACTOR(pll_audio_4x_clk, "pll-audio-4x",
+			"pll-audio-base", 1, 1, CLK_SET_RATE_PARENT);
+static CLK_FIXED_FACTOR(pll_audio_8x_clk, "pll-audio-8x",
+			"pll-audio-base", 1, 2, CLK_SET_RATE_PARENT);
+static CLK_FIXED_FACTOR(pll_periph0_2x_clk, "pll-periph0-2x",
+			"pll-periph0", 1, 2, 0);
+
+static struct clk_hw_onecell_data sun8i_h3_hw_clks = {
+	.hws	= {
+		[CLK_PLL_CPUX]		= &pll_cpux_clk.common.hw,
+		[CLK_PLL_AUDIO_BASE]	= &pll_audio_base_clk.common.hw,
+		[CLK_PLL_AUDIO]		= &pll_audio_clk.hw,
+		[CLK_PLL_AUDIO_2X]	= &pll_audio_2x_clk.hw,
+		[CLK_PLL_AUDIO_4X]	= &pll_audio_4x_clk.hw,
+		[CLK_PLL_AUDIO_8X]	= &pll_audio_8x_clk.hw,
+		[CLK_PLL_VIDEO]		= &pll_video_clk.common.hw,
+		[CLK_PLL_VE]		= &pll_ve_clk.common.hw,
+		[CLK_PLL_DDR]		= &pll_ddr_clk.common.hw,
+		[CLK_PLL_PERIPH0]	= &pll_periph0_clk.common.hw,
+		[CLK_PLL_PERIPH0_2X]	= &pll_periph0_2x_clk.hw,
+		[CLK_PLL_GPU]		= &pll_gpu_clk.common.hw,
+		[CLK_PLL_PERIPH1]	= &pll_periph1_clk.common.hw,
+		[CLK_PLL_DE]		= &pll_de_clk.common.hw,
+		[CLK_CPUX]		= &cpux_clk.common.hw,
+		[CLK_AXI]		= &axi_clk.common.hw,
+		[CLK_AHB1]		= &ahb1_clk.common.hw,
+		[CLK_APB1]		= &apb1_clk.common.hw,
+		[CLK_APB2]		= &apb2_clk.common.hw,
+		[CLK_AHB2]		= &ahb2_clk.common.hw,
+		[CLK_BUS_CE]		= &bus_ce_clk.common.hw,
+		[CLK_BUS_DMA]		= &bus_dma_clk.common.hw,
+		[CLK_BUS_MMC0]		= &bus_mmc0_clk.common.hw,
+		[CLK_BUS_MMC1]		= &bus_mmc1_clk.common.hw,
+		[CLK_BUS_MMC2]		= &bus_mmc2_clk.common.hw,
+		[CLK_BUS_NAND]		= &bus_nand_clk.common.hw,
+		[CLK_BUS_DRAM]		= &bus_dram_clk.common.hw,
+		[CLK_BUS_EMAC]		= &bus_emac_clk.common.hw,
+		[CLK_BUS_TS]		= &bus_ts_clk.common.hw,
+		[CLK_BUS_HSTIMER]	= &bus_hstimer_clk.common.hw,
+		[CLK_BUS_SPI0]		= &bus_spi0_clk.common.hw,
+		[CLK_BUS_SPI1]		= &bus_spi1_clk.common.hw,
+		[CLK_BUS_OTG]		= &bus_otg_clk.common.hw,
+		[CLK_BUS_EHCI0]		= &bus_ehci0_clk.common.hw,
+		[CLK_BUS_EHCI1]		= &bus_ehci1_clk.common.hw,
+		[CLK_BUS_EHCI2]		= &bus_ehci2_clk.common.hw,
+		[CLK_BUS_EHCI3]		= &bus_ehci3_clk.common.hw,
+		[CLK_BUS_OHCI0]		= &bus_ohci0_clk.common.hw,
+		[CLK_BUS_OHCI1]		= &bus_ohci1_clk.common.hw,
+		[CLK_BUS_OHCI2]		= &bus_ohci2_clk.common.hw,
+		[CLK_BUS_OHCI3]		= &bus_ohci3_clk.common.hw,
+		[CLK_BUS_VE]		= &bus_ve_clk.common.hw,
+		[CLK_BUS_TCON0]		= &bus_tcon0_clk.common.hw,
+		[CLK_BUS_TCON1]		= &bus_tcon1_clk.common.hw,
+		[CLK_BUS_DEINTERLACE]	= &bus_deinterlace_clk.common.hw,
+		[CLK_BUS_CSI]		= &bus_csi_clk.common.hw,
+		[CLK_BUS_TVE]		= &bus_tve_clk.common.hw,
+		[CLK_BUS_HDMI]		= &bus_hdmi_clk.common.hw,
+		[CLK_BUS_DE]		= &bus_de_clk.common.hw,
+		[CLK_BUS_GPU]		= &bus_gpu_clk.common.hw,
+		[CLK_BUS_MSGBOX]	= &bus_msgbox_clk.common.hw,
+		[CLK_BUS_SPINLOCK]	= &bus_spinlock_clk.common.hw,
+		[CLK_BUS_CODEC]		= &bus_codec_clk.common.hw,
+		[CLK_BUS_SPDIF]		= &bus_spdif_clk.common.hw,
+		[CLK_BUS_PIO]		= &bus_pio_clk.common.hw,
+		[CLK_BUS_THS]		= &bus_ths_clk.common.hw,
+		[CLK_BUS_I2S0]		= &bus_i2s0_clk.common.hw,
+		[CLK_BUS_I2S1]		= &bus_i2s1_clk.common.hw,
+		[CLK_BUS_I2S2]		= &bus_i2s2_clk.common.hw,
+		[CLK_BUS_I2C0]		= &bus_i2c0_clk.common.hw,
+		[CLK_BUS_I2C1]		= &bus_i2c1_clk.common.hw,
+		[CLK_BUS_I2C2]		= &bus_i2c2_clk.common.hw,
+		[CLK_BUS_UART0]		= &bus_uart0_clk.common.hw,
+		[CLK_BUS_UART1]		= &bus_uart1_clk.common.hw,
+		[CLK_BUS_UART2]		= &bus_uart2_clk.common.hw,
+		[CLK_BUS_UART3]		= &bus_uart3_clk.common.hw,
+		[CLK_BUS_SCR]		= &bus_scr_clk.common.hw,
+		[CLK_BUS_EPHY]		= &bus_ephy_clk.common.hw,
+		[CLK_BUS_DBG]		= &bus_dbg_clk.common.hw,
+		[CLK_THS]		= &ths_clk.common.hw,
+		[CLK_NAND]		= &nand_clk.common.hw,
+		[CLK_MMC0]		= &mmc0_clk.common.hw,
+		[CLK_MMC0_SAMPLE]	= &mmc0_sample_clk.common.hw,
+		[CLK_MMC0_OUTPUT]	= &mmc0_output_clk.common.hw,
+		[CLK_MMC1]		= &mmc1_clk.common.hw,
+		[CLK_MMC1_SAMPLE]	= &mmc1_sample_clk.common.hw,
+		[CLK_MMC1_OUTPUT]	= &mmc1_output_clk.common.hw,
+		[CLK_MMC2]		= &mmc2_clk.common.hw,
+		[CLK_MMC2_SAMPLE]	= &mmc2_sample_clk.common.hw,
+		[CLK_MMC2_OUTPUT]	= &mmc2_output_clk.common.hw,
+		[CLK_TS]		= &ts_clk.common.hw,
+		[CLK_CE]		= &ce_clk.common.hw,
+		[CLK_SPI0]		= &spi0_clk.common.hw,
+		[CLK_SPI1]		= &spi1_clk.common.hw,
+		[CLK_I2S0]		= &i2s0_clk.common.hw,
+		[CLK_I2S1]		= &i2s1_clk.common.hw,
+		[CLK_I2S2]		= &i2s2_clk.common.hw,
+		[CLK_SPDIF]		= &spdif_clk.common.hw,
+		[CLK_USB_PHY0]		= &usb_phy0_clk.common.hw,
+		[CLK_USB_PHY1]		= &usb_phy1_clk.common.hw,
+		[CLK_USB_PHY2]		= &usb_phy2_clk.common.hw,
+		[CLK_USB_PHY3]		= &usb_phy3_clk.common.hw,
+		[CLK_USB_OHCI0]		= &usb_ohci0_clk.common.hw,
+		[CLK_USB_OHCI1]		= &usb_ohci1_clk.common.hw,
+		[CLK_USB_OHCI2]		= &usb_ohci2_clk.common.hw,
+		[CLK_USB_OHCI3]		= &usb_ohci3_clk.common.hw,
+		[CLK_DRAM]		= &dram_clk.common.hw,
+		[CLK_DRAM_VE]		= &dram_ve_clk.common.hw,
+		[CLK_DRAM_CSI]		= &dram_csi_clk.common.hw,
+		[CLK_DRAM_DEINTERLACE]	= &dram_deinterlace_clk.common.hw,
+		[CLK_DRAM_TS]		= &dram_ts_clk.common.hw,
+		[CLK_DE]		= &de_clk.common.hw,
+		[CLK_TCON0]		= &tcon_clk.common.hw,
+		[CLK_TVE]		= &tve_clk.common.hw,
+		[CLK_DEINTERLACE]	= &deinterlace_clk.common.hw,
+		[CLK_CSI_MISC]		= &csi_misc_clk.common.hw,
+		[CLK_CSI_SCLK]		= &csi_sclk_clk.common.hw,
+		[CLK_CSI_MCLK]		= &csi_mclk_clk.common.hw,
+		[CLK_VE]		= &ve_clk.common.hw,
+		[CLK_AC_DIG]		= &ac_dig_clk.common.hw,
+		[CLK_AVS]		= &avs_clk.common.hw,
+		[CLK_HDMI]		= &hdmi_clk.common.hw,
+		[CLK_HDMI_DDC]		= &hdmi_ddc_clk.common.hw,
+		[CLK_MBUS]		= &mbus_clk.common.hw,
+		[CLK_GPU]		= &gpu_clk.common.hw,
+	},
+	.num	= CLK_NUMBER,
+};
+
+static struct ccu_reset_map sun8i_h3_ccu_resets[] = {
+	[RST_USB_PHY0]		=  { 0x0cc, BIT(0) },
+	[RST_USB_PHY1]		=  { 0x0cc, BIT(1) },
+	[RST_USB_PHY2]		=  { 0x0cc, BIT(2) },
+	[RST_USB_PHY3]		=  { 0x0cc, BIT(3) },
+
+	[RST_MBUS]		=  { 0x0fc, BIT(31) },
+
+	[RST_BUS_CE]		=  { 0x2c0, BIT(5) },
+	[RST_BUS_DMA]		=  { 0x2c0, BIT(6) },
+	[RST_BUS_MMC0]		=  { 0x2c0, BIT(8) },
+	[RST_BUS_MMC1]		=  { 0x2c0, BIT(9) },
+	[RST_BUS_MMC2]		=  { 0x2c0, BIT(10) },
+	[RST_BUS_NAND]		=  { 0x2c0, BIT(13) },
+	[RST_BUS_DRAM]		=  { 0x2c0, BIT(14) },
+	[RST_BUS_EMAC]		=  { 0x2c0, BIT(17) },
+	[RST_BUS_TS]		=  { 0x2c0, BIT(18) },
+	[RST_BUS_HSTIMER]	=  { 0x2c0, BIT(19) },
+	[RST_BUS_SPI0]		=  { 0x2c0, BIT(20) },
+	[RST_BUS_SPI1]		=  { 0x2c0, BIT(21) },
+	[RST_BUS_OTG]		=  { 0x2c0, BIT(23) },
+	[RST_BUS_EHCI0]		=  { 0x2c0, BIT(24) },
+	[RST_BUS_EHCI1]		=  { 0x2c0, BIT(25) },
+	[RST_BUS_EHCI2]		=  { 0x2c0, BIT(26) },
+	[RST_BUS_EHCI3]		=  { 0x2c0, BIT(27) },
+	[RST_BUS_OHCI0]		=  { 0x2c0, BIT(28) },
+	[RST_BUS_OHCI1]		=  { 0x2c0, BIT(29) },
+	[RST_BUS_OHCI2]		=  { 0x2c0, BIT(30) },
+	[RST_BUS_OHCI3]		=  { 0x2c0, BIT(31) },
+
+	[RST_BUS_VE]		=  { 0x2c4, BIT(0) },
+	[RST_BUS_TCON0]		=  { 0x2c4, BIT(3) },
+	[RST_BUS_TCON1]		=  { 0x2c4, BIT(4) },
+	[RST_BUS_DEINTERLACE]	=  { 0x2c4, BIT(5) },
+	[RST_BUS_CSI]		=  { 0x2c4, BIT(8) },
+	[RST_BUS_TVE]		=  { 0x2c4, BIT(9) },
+	[RST_BUS_HDMI0]		=  { 0x2c4, BIT(10) },
+	[RST_BUS_HDMI1]		=  { 0x2c4, BIT(11) },
+	[RST_BUS_DE]		=  { 0x2c4, BIT(12) },
+	[RST_BUS_GPU]		=  { 0x2c4, BIT(20) },
+	[RST_BUS_MSGBOX]	=  { 0x2c4, BIT(21) },
+	[RST_BUS_SPINLOCK]	=  { 0x2c4, BIT(22) },
+	[RST_BUS_DBG]		=  { 0x2c4, BIT(31) },
+
+	[RST_BUS_EPHY]		=  { 0x2c8, BIT(2) },
+
+	[RST_BUS_CODEC]		=  { 0x2d0, BIT(0) },
+	[RST_BUS_SPDIF]		=  { 0x2d0, BIT(1) },
+	[RST_BUS_THS]		=  { 0x2d0, BIT(8) },
+	[RST_BUS_I2S0]		=  { 0x2d0, BIT(12) },
+	[RST_BUS_I2S1]		=  { 0x2d0, BIT(13) },
+	[RST_BUS_I2S2]		=  { 0x2d0, BIT(14) },
+
+	[RST_BUS_I2C0]		=  { 0x2d4, BIT(0) },
+	[RST_BUS_I2C1]		=  { 0x2d4, BIT(1) },
+	[RST_BUS_I2C2]		=  { 0x2d4, BIT(2) },
+	[RST_BUS_UART0]		=  { 0x2d4, BIT(16) },
+	[RST_BUS_UART1]		=  { 0x2d4, BIT(17) },
+	[RST_BUS_UART2]		=  { 0x2d4, BIT(18) },
+	[RST_BUS_UART3]		=  { 0x2d4, BIT(19) },
+	[RST_BUS_SCR]		=  { 0x2d4, BIT(20) },
+};
+
+static const struct sunxi_ccu_desc sun8i_h3_ccu_desc = {
+	.ccu_clks	= sun8i_h3_ccu_clks,
+	.num_ccu_clks	= ARRAY_SIZE(sun8i_h3_ccu_clks),
+
+	.hw_clks	= &sun8i_h3_hw_clks,
+
+	.resets		= sun8i_h3_ccu_resets,
+	.num_resets	= ARRAY_SIZE(sun8i_h3_ccu_resets),
+};
+
+static void __init sun8i_h3_ccu_setup(struct device_node *node)
+{
+	void __iomem *reg;
+	u32 val;
+
+	reg = of_io_request_and_map(node, 0, of_node_full_name(node));
+	if (IS_ERR(reg)) {
+		pr_err("%s: Could not map the clock registers\n",
+		       of_node_full_name(node));
+		return;
+	}
+
+	/* Force the PLL-Audio-1x divider to 4 */
+	val = readl(reg + SUN8I_H3_PLL_AUDIO_REG);
+	val &= ~GENMASK(19, 16);
+	writel(val | (3 << 16), reg + SUN8I_H3_PLL_AUDIO_REG);
+
+	sunxi_ccu_probe(node, reg, &sun8i_h3_ccu_desc);
+}
+CLK_OF_DECLARE(sun8i_h3_ccu, "allwinner,sun8i-h3-ccu",
+	       sun8i_h3_ccu_setup);
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-h3.h b/drivers/clk/sunxi-ng/ccu-sun8i-h3.h
new file mode 100644
index 000000000000..78be712c7487
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-h3.h
@@ -0,0 +1,62 @@
+/*
+ * Copyright 2016 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_SUN8I_H3_H_
+#define _CCU_SUN8I_H3_H_
+
+#include <dt-bindings/clock/sun8i-h3-ccu.h>
+#include <dt-bindings/reset/sun8i-h3-ccu.h>
+
+#define CLK_PLL_CPUX		0
+#define CLK_PLL_AUDIO_BASE	1
+#define CLK_PLL_AUDIO		2
+#define CLK_PLL_AUDIO_2X	3
+#define CLK_PLL_AUDIO_4X	4
+#define CLK_PLL_AUDIO_8X	5
+#define CLK_PLL_VIDEO		6
+#define CLK_PLL_VE		7
+#define CLK_PLL_DDR		8
+#define CLK_PLL_PERIPH0		9
+#define CLK_PLL_PERIPH0_2X	10
+#define CLK_PLL_GPU		11
+#define CLK_PLL_PERIPH1		12
+#define CLK_PLL_DE		13
+
+/* The CPUX clock is exported */
+
+#define CLK_AXI			15
+#define CLK_AHB1		16
+#define CLK_APB1		17
+#define CLK_APB2		18
+#define CLK_AHB2		19
+
+/* All the bus gates are exported */
+
+/* The first bunch of module clocks are exported */
+
+#define CLK_DRAM		96
+
+/* All the DRAM gates are exported */
+
+/* Some more module clocks are exported */
+
+#define CLK_MBUS		113
+
+/* And the GPU module clock is exported */
+
+#define CLK_NUMBER		(CLK_GPU + 1)
+
+#endif /* _CCU_SUN8I_H3_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_common.c b/drivers/clk/sunxi-ng/ccu_common.c
new file mode 100644
index 000000000000..fc17b5295e16
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_common.c
@@ -0,0 +1,90 @@
+/*
+ * Copyright 2016 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/iopoll.h>
+#include <linux/slab.h>
+
+#include "ccu_common.h"
+#include "ccu_reset.h"
+
+static DEFINE_SPINLOCK(ccu_lock);
+
+void ccu_helper_wait_for_lock(struct ccu_common *common, u32 lock)
+{
+	u32 reg;
+
+	if (!lock)
+		return;
+
+	WARN_ON(readl_relaxed_poll_timeout(common->base + common->reg, reg,
+					   !(reg & lock), 100, 70000));
+}
+
+int sunxi_ccu_probe(struct device_node *node, void __iomem *reg,
+		    const struct sunxi_ccu_desc *desc)
+{
+	struct ccu_reset *reset;
+	int i, ret;
+
+	for (i = 0; i < desc->num_ccu_clks; i++) {
+		struct ccu_common *cclk = desc->ccu_clks[i];
+
+		if (!cclk)
+			continue;
+
+		cclk->base = reg;
+		cclk->lock = &ccu_lock;
+	}
+
+	for (i = 0; i < desc->hw_clks->num ; i++) {
+		struct clk_hw *hw = desc->hw_clks->hws[i];
+
+		if (!hw)
+			continue;
+
+		ret = clk_hw_register(NULL, hw);
+		if (ret) {
+			pr_err("Couldn't register clock %s\n",
+			       clk_hw_get_name(hw));
+			goto err_clk_unreg;
+		}
+	}
+
+	ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get,
+				     desc->hw_clks);
+	if (ret)
+		goto err_clk_unreg;
+
+	reset = kzalloc(sizeof(*reset), GFP_KERNEL);
+	reset->rcdev.of_node = node;
+	reset->rcdev.ops = &ccu_reset_ops;
+	reset->rcdev.owner = THIS_MODULE;
+	reset->rcdev.nr_resets = desc->num_resets;
+	reset->base = reg;
+	reset->lock = &ccu_lock;
+	reset->reset_map = desc->resets;
+
+	ret = reset_controller_register(&reset->rcdev);
+	if (ret)
+		goto err_of_clk_unreg;
+
+	return 0;
+
+err_of_clk_unreg:
+err_clk_unreg:
+	return ret;
+}
diff --git a/drivers/clk/sunxi-ng/ccu_common.h b/drivers/clk/sunxi-ng/ccu_common.h
new file mode 100644
index 000000000000..b3d9abfbd721
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_common.h
@@ -0,0 +1,85 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _COMMON_H_
+#define _COMMON_H_
+
+#include <linux/compiler.h>
+#include <linux/clk-provider.h>
+
+#define CCU_FEATURE_FRACTIONAL		BIT(0)
+#define CCU_FEATURE_VARIABLE_PREDIV	BIT(1)
+#define CCU_FEATURE_FIXED_PREDIV	BIT(2)
+#define CCU_FEATURE_FIXED_POSTDIV	BIT(3)
+
+struct device_node;
+
+#define CLK_HW_INIT(_name, _parent, _ops, _flags)			\
+	&(struct clk_init_data) {					\
+		.flags		= _flags,				\
+		.name		= _name,				\
+		.parent_names	= (const char *[]) { _parent },		\
+		.num_parents	= 1,					\
+		.ops 		= _ops,					\
+	}
+
+#define CLK_HW_INIT_PARENTS(_name, _parents, _ops, _flags)		\
+	&(struct clk_init_data) {					\
+		.flags		= _flags,				\
+		.name		= _name,				\
+		.parent_names	= _parents,				\
+		.num_parents	= ARRAY_SIZE(_parents),			\
+		.ops 		= _ops,					\
+	}
+
+#define CLK_FIXED_FACTOR(_struct, _name, _parent,			\
+			_div, _mult, _flags)				\
+	struct clk_fixed_factor _struct = {				\
+		.div		= _div,					\
+		.mult		= _mult,				\
+		.hw.init	= CLK_HW_INIT(_name,			\
+					      _parent,			\
+					      &clk_fixed_factor_ops,	\
+					      _flags),			\
+	}
+
+struct ccu_common {
+	void __iomem	*base;
+	u16		reg;
+
+	unsigned long	features;
+	spinlock_t	*lock;
+	struct clk_hw	hw;
+};
+
+static inline struct ccu_common *hw_to_ccu_common(struct clk_hw *hw)
+{
+	return container_of(hw, struct ccu_common, hw);
+}
+
+struct sunxi_ccu_desc {
+	struct ccu_common		**ccu_clks;
+	unsigned long			num_ccu_clks;
+
+	struct clk_hw_onecell_data	*hw_clks;
+
+	struct ccu_reset_map		*resets;
+	unsigned long			num_resets;
+};
+
+void ccu_helper_wait_for_lock(struct ccu_common *common, u32 lock);
+
+int sunxi_ccu_probe(struct device_node *node, void __iomem *reg,
+		    const struct sunxi_ccu_desc *desc);
+
+#endif /* _COMMON_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_div.c b/drivers/clk/sunxi-ng/ccu_div.c
new file mode 100644
index 000000000000..8659b4cb6c20
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_div.c
@@ -0,0 +1,136 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk-provider.h>
+
+#include "ccu_gate.h"
+#include "ccu_div.h"
+
+static unsigned long ccu_div_round_rate(struct ccu_mux_internal *mux,
+					unsigned long parent_rate,
+					unsigned long rate,
+					void *data)
+{
+	struct ccu_div *cd = data;
+	unsigned long val;
+
+	/*
+	 * We can't use divider_round_rate that assumes that there's
+	 * several parents, while we might be called to evaluate
+	 * several different parents.
+	 */
+	val = divider_get_val(rate, parent_rate, cd->div.table, cd->div.width,
+			      cd->div.flags);
+
+	return divider_recalc_rate(&cd->common.hw, parent_rate, val,
+				   cd->div.table, cd->div.flags);
+}
+
+static void ccu_div_disable(struct clk_hw *hw)
+{
+	struct ccu_div *cd = hw_to_ccu_div(hw);
+
+	return ccu_gate_helper_disable(&cd->common, cd->enable);
+}
+
+static int ccu_div_enable(struct clk_hw *hw)
+{
+	struct ccu_div *cd = hw_to_ccu_div(hw);
+
+	return ccu_gate_helper_enable(&cd->common, cd->enable);
+}
+
+static int ccu_div_is_enabled(struct clk_hw *hw)
+{
+	struct ccu_div *cd = hw_to_ccu_div(hw);
+
+	return ccu_gate_helper_is_enabled(&cd->common, cd->enable);
+}
+
+static unsigned long ccu_div_recalc_rate(struct clk_hw *hw,
+					unsigned long parent_rate)
+{
+	struct ccu_div *cd = hw_to_ccu_div(hw);
+	unsigned long val;
+	u32 reg;
+
+	reg = readl(cd->common.base + cd->common.reg);
+	val = reg >> cd->div.shift;
+	val &= (1 << cd->div.width) - 1;
+
+	ccu_mux_helper_adjust_parent_for_prediv(&cd->common, &cd->mux, -1,
+						&parent_rate);
+
+	return divider_recalc_rate(hw, parent_rate, val, cd->div.table,
+				   cd->div.flags);
+}
+
+static int ccu_div_determine_rate(struct clk_hw *hw,
+				struct clk_rate_request *req)
+{
+	struct ccu_div *cd = hw_to_ccu_div(hw);
+
+	return ccu_mux_helper_determine_rate(&cd->common, &cd->mux,
+					     req, ccu_div_round_rate, cd);
+}
+
+static int ccu_div_set_rate(struct clk_hw *hw, unsigned long rate,
+			   unsigned long parent_rate)
+{
+	struct ccu_div *cd = hw_to_ccu_div(hw);
+	unsigned long flags;
+	unsigned long val;
+	u32 reg;
+
+	ccu_mux_helper_adjust_parent_for_prediv(&cd->common, &cd->mux, -1,
+						&parent_rate);
+
+	val = divider_get_val(rate, parent_rate, cd->div.table, cd->div.width,
+			      cd->div.flags);
+
+	spin_lock_irqsave(cd->common.lock, flags);
+
+	reg = readl(cd->common.base + cd->common.reg);
+	reg &= ~GENMASK(cd->div.width + cd->div.shift - 1, cd->div.shift);
+
+	writel(reg | (val << cd->div.shift),
+	       cd->common.base + cd->common.reg);
+
+	spin_unlock_irqrestore(cd->common.lock, flags);
+
+	return 0;
+}
+
+static u8 ccu_div_get_parent(struct clk_hw *hw)
+{
+	struct ccu_div *cd = hw_to_ccu_div(hw);
+
+	return ccu_mux_helper_get_parent(&cd->common, &cd->mux);
+}
+
+static int ccu_div_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct ccu_div *cd = hw_to_ccu_div(hw);
+
+	return ccu_mux_helper_set_parent(&cd->common, &cd->mux, index);
+}
+
+const struct clk_ops ccu_div_ops = {
+	.disable	= ccu_div_disable,
+	.enable		= ccu_div_enable,
+	.is_enabled	= ccu_div_is_enabled,
+
+	.get_parent	= ccu_div_get_parent,
+	.set_parent	= ccu_div_set_parent,
+
+	.determine_rate	= ccu_div_determine_rate,
+	.recalc_rate	= ccu_div_recalc_rate,
+	.set_rate	= ccu_div_set_rate,
+};
diff --git a/drivers/clk/sunxi-ng/ccu_div.h b/drivers/clk/sunxi-ng/ccu_div.h
new file mode 100644
index 000000000000..653ade5769b3
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_div.h
@@ -0,0 +1,133 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_DIV_H_
+#define _CCU_DIV_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+#include "ccu_mux.h"
+
+struct _ccu_div {
+	u8			shift;
+	u8			width;
+
+	u32			flags;
+
+	struct clk_div_table	*table;
+};
+
+#define _SUNXI_CCU_DIV_TABLE_FLAGS(_shift, _width, _table, _flags)	\
+	{								\
+		.shift	= _shift,					\
+		.width	= _width,					\
+		.flags	= _flags,					\
+		.table	= _table,					\
+	}
+
+#define _SUNXI_CCU_DIV_FLAGS(_shift, _width, _flags)			\
+	_SUNXI_CCU_DIV_TABLE_FLAGS(_shift, _width, NULL, _flags)
+
+#define _SUNXI_CCU_DIV_TABLE(_shift, _width, _table)			\
+	_SUNXI_CCU_DIV_TABLE_FLAGS(_shift, _width, _table, 0)
+
+#define _SUNXI_CCU_DIV(_shift, _width)					\
+	_SUNXI_CCU_DIV_TABLE_FLAGS(_shift, _width, NULL, 0)
+
+struct ccu_div {
+	u32			enable;
+
+	struct _ccu_div		div;
+	struct ccu_mux_internal	mux;
+	struct ccu_common	common;
+};
+
+#define SUNXI_CCU_DIV_TABLE_WITH_GATE(_struct, _name, _parent, _reg,	\
+				      _shift, _width,			\
+				      _table, _gate, _flags)		\
+	struct ccu_div _struct = {					\
+		.div		= _SUNXI_CCU_DIV_TABLE(_shift, _width,	\
+						       _table),		\
+		.enable		= _gate,				\
+		.common	= {						\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &ccu_div_ops,	\
+						      _flags),		\
+		}							\
+	}
+
+
+#define SUNXI_CCU_DIV_TABLE(_struct, _name, _parent, _reg,		\
+			    _shift, _width,				\
+			    _table, _flags)				\
+	SUNXI_CCU_DIV_TABLE_WITH_GATE(_struct, _name, _parent, _reg,	\
+				      _shift, _width, _table, 0,	\
+				      _flags)
+
+#define SUNXI_CCU_M_WITH_MUX_GATE(_struct, _name, _parents, _reg,	\
+				  _mshift, _mwidth, _muxshift, _muxwidth, \
+				  _gate, _flags)			\
+	struct ccu_div _struct = {					\
+		.enable	= _gate,					\
+		.div	= _SUNXI_CCU_DIV(_mshift, _mwidth),		\
+		.mux	= SUNXI_CLK_MUX(_muxshift, _muxwidth),		\
+		.common	= {						\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT_PARENTS(_name,	\
+							      _parents, \
+							      &ccu_div_ops, \
+							      _flags),	\
+		},							\
+	}
+
+#define SUNXI_CCU_M_WITH_MUX(_struct, _name, _parents, _reg,		\
+			     _mshift, _mwidth, _muxshift, _muxwidth,	\
+			     _flags)					\
+	SUNXI_CCU_M_WITH_MUX_GATE(_struct, _name, _parents, _reg,	\
+				  _mshift, _mwidth, _muxshift, _muxwidth, \
+				  0, _flags)
+
+
+#define SUNXI_CCU_M_WITH_GATE(_struct, _name, _parent, _reg,		\
+			      _mshift, _mwidth,	_gate,			\
+			      _flags)					\
+	struct ccu_div _struct = {					\
+		.enable	= _gate,					\
+		.div	= _SUNXI_CCU_DIV(_mshift, _mwidth),		\
+		.common	= {						\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &ccu_div_ops,	\
+						      _flags),		\
+		},							\
+	}
+
+#define SUNXI_CCU_M(_struct, _name, _parent, _reg, _mshift, _mwidth,	\
+		    _flags)						\
+	SUNXI_CCU_M_WITH_GATE(_struct, _name, _parent, _reg,		\
+			      _mshift, _mwidth, 0, _flags)
+
+static inline struct ccu_div *hw_to_ccu_div(struct clk_hw *hw)
+{
+	struct ccu_common *common = hw_to_ccu_common(hw);
+
+	return container_of(common, struct ccu_div, common);
+}
+
+extern const struct clk_ops ccu_div_ops;
+
+#endif /* _CCU_DIV_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_frac.c b/drivers/clk/sunxi-ng/ccu_frac.c
new file mode 100644
index 000000000000..5c4b10cd15b5
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_frac.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/spinlock.h>
+
+#include "ccu_frac.h"
+
+bool ccu_frac_helper_is_enabled(struct ccu_common *common,
+				struct _ccu_frac *cf)
+{
+	if (!(common->features & CCU_FEATURE_FRACTIONAL))
+		return false;
+
+	return !(readl(common->base + common->reg) & cf->enable);
+}
+
+void ccu_frac_helper_enable(struct ccu_common *common,
+			    struct _ccu_frac *cf)
+{
+	unsigned long flags;
+	u32 reg;
+
+	if (!(common->features & CCU_FEATURE_FRACTIONAL))
+		return;
+
+	spin_lock_irqsave(common->lock, flags);
+	reg = readl(common->base + common->reg);
+	writel(reg & ~cf->enable, common->base + common->reg);
+	spin_unlock_irqrestore(common->lock, flags);
+}
+
+void ccu_frac_helper_disable(struct ccu_common *common,
+			     struct _ccu_frac *cf)
+{
+	unsigned long flags;
+	u32 reg;
+
+	if (!(common->features & CCU_FEATURE_FRACTIONAL))
+		return;
+
+	spin_lock_irqsave(common->lock, flags);
+	reg = readl(common->base + common->reg);
+	writel(reg | cf->enable, common->base + common->reg);
+	spin_unlock_irqrestore(common->lock, flags);
+}
+
+bool ccu_frac_helper_has_rate(struct ccu_common *common,
+			      struct _ccu_frac *cf,
+			      unsigned long rate)
+{
+	if (!(common->features & CCU_FEATURE_FRACTIONAL))
+		return false;
+
+	return (cf->rates[0] == rate) || (cf->rates[1] == rate);
+}
+
+unsigned long ccu_frac_helper_read_rate(struct ccu_common *common,
+					struct _ccu_frac *cf)
+{
+	u32 reg;
+
+	printk("%s: Read fractional\n", clk_hw_get_name(&common->hw));
+
+	if (!(common->features & CCU_FEATURE_FRACTIONAL))
+		return 0;
+
+	printk("%s: clock is fractional (rates %lu and %lu)\n",
+	       clk_hw_get_name(&common->hw), cf->rates[0], cf->rates[1]);
+
+	reg = readl(common->base + common->reg);
+
+	printk("%s: clock reg is 0x%x (select is 0x%x)\n",
+	       clk_hw_get_name(&common->hw), reg, cf->select);
+
+	return (reg & cf->select) ? cf->rates[1] : cf->rates[0];
+}
+
+int ccu_frac_helper_set_rate(struct ccu_common *common,
+			     struct _ccu_frac *cf,
+			     unsigned long rate)
+{
+	unsigned long flags;
+	u32 reg, sel;
+
+	if (!(common->features & CCU_FEATURE_FRACTIONAL))
+		return -EINVAL;
+
+	if (cf->rates[0] == rate)
+		sel = 0;
+	else if (cf->rates[1] == rate)
+		sel = cf->select;
+	else
+		return -EINVAL;
+
+	spin_lock_irqsave(common->lock, flags);
+	reg = readl(common->base + common->reg);
+	reg &= ~cf->select;
+	writel(reg | sel, common->base + common->reg);
+	spin_unlock_irqrestore(common->lock, flags);
+
+	return 0;
+}
diff --git a/drivers/clk/sunxi-ng/ccu_frac.h b/drivers/clk/sunxi-ng/ccu_frac.h
new file mode 100644
index 000000000000..e4c670b1cdfe
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_frac.h
@@ -0,0 +1,53 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_FRAC_H_
+#define _CCU_FRAC_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+
+struct _ccu_frac {
+	u32		enable;
+	u32		select;
+
+	unsigned long	rates[2];
+};
+
+#define _SUNXI_CCU_FRAC(_enable, _select, _rate1, _rate2)		\
+	{								\
+		.enable	= _enable,					\
+		.select	= _select,					\
+		.rates = { _rate1, _rate2 },				\
+	}
+
+bool ccu_frac_helper_is_enabled(struct ccu_common *common,
+				struct _ccu_frac *cf);
+void ccu_frac_helper_enable(struct ccu_common *common,
+			    struct _ccu_frac *cf);
+void ccu_frac_helper_disable(struct ccu_common *common,
+			     struct _ccu_frac *cf);
+
+bool ccu_frac_helper_has_rate(struct ccu_common *common,
+			      struct _ccu_frac *cf,
+			      unsigned long rate);
+
+unsigned long ccu_frac_helper_read_rate(struct ccu_common *common,
+					struct _ccu_frac *cf);
+
+int ccu_frac_helper_set_rate(struct ccu_common *common,
+			     struct _ccu_frac *cf,
+			     unsigned long rate);
+
+#endif /* _CCU_FRAC_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_gate.c b/drivers/clk/sunxi-ng/ccu_gate.c
new file mode 100644
index 000000000000..8a81f9d4a89f
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_gate.c
@@ -0,0 +1,82 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk-provider.h>
+
+#include "ccu_gate.h"
+
+void ccu_gate_helper_disable(struct ccu_common *common, u32 gate)
+{
+	unsigned long flags;
+	u32 reg;
+
+	if (!gate)
+		return;
+
+	spin_lock_irqsave(common->lock, flags);
+
+	reg = readl(common->base + common->reg);
+	writel(reg & ~gate, common->base + common->reg);
+
+	spin_unlock_irqrestore(common->lock, flags);
+}
+
+static void ccu_gate_disable(struct clk_hw *hw)
+{
+	struct ccu_gate *cg = hw_to_ccu_gate(hw);
+
+	return ccu_gate_helper_disable(&cg->common, cg->enable);
+}
+
+int ccu_gate_helper_enable(struct ccu_common *common, u32 gate)
+{
+	unsigned long flags;
+	u32 reg;
+
+	if (!gate)
+		return 0;
+
+	spin_lock_irqsave(common->lock, flags);
+
+	reg = readl(common->base + common->reg);
+	writel(reg | gate, common->base + common->reg);
+
+	spin_unlock_irqrestore(common->lock, flags);
+
+	return 0;
+}
+
+static int ccu_gate_enable(struct clk_hw *hw)
+{
+	struct ccu_gate *cg = hw_to_ccu_gate(hw);
+
+	return ccu_gate_helper_enable(&cg->common, cg->enable);
+}
+
+int ccu_gate_helper_is_enabled(struct ccu_common *common, u32 gate)
+{
+	if (!gate)
+		return 1;
+
+	return readl(common->base + common->reg) & gate;
+}
+
+static int ccu_gate_is_enabled(struct clk_hw *hw)
+{
+	struct ccu_gate *cg = hw_to_ccu_gate(hw);
+
+	return ccu_gate_helper_is_enabled(&cg->common, cg->enable);
+}
+
+const struct clk_ops ccu_gate_ops = {
+	.disable	= ccu_gate_disable,
+	.enable		= ccu_gate_enable,
+	.is_enabled	= ccu_gate_is_enabled,
+};
diff --git a/drivers/clk/sunxi-ng/ccu_gate.h b/drivers/clk/sunxi-ng/ccu_gate.h
new file mode 100644
index 000000000000..4466169bd2d7
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_gate.h
@@ -0,0 +1,52 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_GATE_H_
+#define _CCU_GATE_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+
+struct ccu_gate {
+	u32			enable;
+
+	struct ccu_common	common;
+};
+
+#define SUNXI_CCU_GATE(_struct, _name, _parent, _reg, _gate, _flags)	\
+	struct ccu_gate _struct = {					\
+		.enable	= _gate,					\
+		.common	= {						\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &ccu_gate_ops,	\
+						      _flags),		\
+		}							\
+	}
+
+static inline struct ccu_gate *hw_to_ccu_gate(struct clk_hw *hw)
+{
+	struct ccu_common *common = hw_to_ccu_common(hw);
+
+	return container_of(common, struct ccu_gate, common);
+}
+
+void ccu_gate_helper_disable(struct ccu_common *common, u32 gate);
+int ccu_gate_helper_enable(struct ccu_common *common, u32 gate);
+int ccu_gate_helper_is_enabled(struct ccu_common *common, u32 gate);
+
+extern const struct clk_ops ccu_gate_ops;
+
+#endif /* _CCU_GATE_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_mp.c b/drivers/clk/sunxi-ng/ccu_mp.c
new file mode 100644
index 000000000000..cbf33ef5faa9
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_mp.c
@@ -0,0 +1,158 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk-provider.h>
+
+#include "ccu_gate.h"
+#include "ccu_mp.h"
+
+static void ccu_mp_find_best(unsigned long parent, unsigned long rate,
+			     unsigned int max_m, unsigned int max_p,
+			     unsigned int *m, unsigned int *p)
+{
+	unsigned long best_rate = 0;
+	unsigned int best_m = 0, best_p = 0;
+	unsigned int _m, _p;
+
+	for (_p = 0; _p <= max_p; _p++) {
+		for (_m = 1; _m <= max_m; _m++) {
+			unsigned long tmp_rate = (parent >> _p) / _m;
+
+			if (tmp_rate > rate)
+				continue;
+
+			if ((rate - tmp_rate) < (rate - best_rate)) {
+				best_rate = tmp_rate;
+				best_m = _m;
+				best_p = _p;
+			}
+		}
+	}
+
+	*m = best_m;
+	*p = best_p;
+}
+
+static unsigned long ccu_mp_round_rate(struct ccu_mux_internal *mux,
+				       unsigned long parent_rate,
+				       unsigned long rate,
+				       void *data)
+{
+	struct ccu_mp *cmp = data;
+	unsigned int m, p;
+
+	ccu_mp_find_best(parent_rate, rate,
+			 1 << cmp->m.width, (1 << cmp->p.width) - 1,
+			 &m, &p);
+
+	return (parent_rate >> p) / m;
+}
+
+static void ccu_mp_disable(struct clk_hw *hw)
+{
+	struct ccu_mp *cmp = hw_to_ccu_mp(hw);
+
+	return ccu_gate_helper_disable(&cmp->common, cmp->enable);
+}
+
+static int ccu_mp_enable(struct clk_hw *hw)
+{
+	struct ccu_mp *cmp = hw_to_ccu_mp(hw);
+
+	return ccu_gate_helper_enable(&cmp->common, cmp->enable);
+}
+
+static int ccu_mp_is_enabled(struct clk_hw *hw)
+{
+	struct ccu_mp *cmp = hw_to_ccu_mp(hw);
+
+	return ccu_gate_helper_is_enabled(&cmp->common, cmp->enable);
+}
+
+static unsigned long ccu_mp_recalc_rate(struct clk_hw *hw,
+					unsigned long parent_rate)
+{
+	struct ccu_mp *cmp = hw_to_ccu_mp(hw);
+	unsigned int m, p;
+	u32 reg;
+
+	reg = readl(cmp->common.base + cmp->common.reg);
+
+	m = reg >> cmp->m.shift;
+	m &= (1 << cmp->m.width) - 1;
+
+	p = reg >> cmp->p.shift;
+	p &= (1 << cmp->p.width) - 1;
+
+	return (parent_rate >> p) / (m + 1);
+}
+
+static int ccu_mp_determine_rate(struct clk_hw *hw,
+				 struct clk_rate_request *req)
+{
+	struct ccu_mp *cmp = hw_to_ccu_mp(hw);
+
+	return ccu_mux_helper_determine_rate(&cmp->common, &cmp->mux,
+					     req, ccu_mp_round_rate, cmp);
+}
+
+static int ccu_mp_set_rate(struct clk_hw *hw, unsigned long rate,
+			   unsigned long parent_rate)
+{
+	struct ccu_mp *cmp = hw_to_ccu_mp(hw);
+	unsigned long flags;
+	unsigned int m, p;
+	u32 reg;
+
+	ccu_mp_find_best(parent_rate, rate,
+			 1 << cmp->m.width, (1 << cmp->p.width) - 1,
+			 &m, &p);
+
+
+	spin_lock_irqsave(cmp->common.lock, flags);
+
+	reg = readl(cmp->common.base + cmp->common.reg);
+	reg &= ~GENMASK(cmp->m.width + cmp->m.shift - 1, cmp->m.shift);
+	reg &= ~GENMASK(cmp->p.width + cmp->p.shift - 1, cmp->p.shift);
+
+	writel(reg | (p << cmp->p.shift) | ((m - 1) << cmp->m.shift),
+	       cmp->common.base + cmp->common.reg);
+
+	spin_unlock_irqrestore(cmp->common.lock, flags);
+
+	return 0;
+}
+
+static u8 ccu_mp_get_parent(struct clk_hw *hw)
+{
+	struct ccu_mp *cmp = hw_to_ccu_mp(hw);
+
+	return ccu_mux_helper_get_parent(&cmp->common, &cmp->mux);
+}
+
+static int ccu_mp_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct ccu_mp *cmp = hw_to_ccu_mp(hw);
+
+	return ccu_mux_helper_set_parent(&cmp->common, &cmp->mux, index);
+}
+
+const struct clk_ops ccu_mp_ops = {
+	.disable	= ccu_mp_disable,
+	.enable		= ccu_mp_enable,
+	.is_enabled	= ccu_mp_is_enabled,
+
+	.get_parent	= ccu_mp_get_parent,
+	.set_parent	= ccu_mp_set_parent,
+
+	.determine_rate	= ccu_mp_determine_rate,
+	.recalc_rate	= ccu_mp_recalc_rate,
+	.set_rate	= ccu_mp_set_rate,
+};
diff --git a/drivers/clk/sunxi-ng/ccu_mp.h b/drivers/clk/sunxi-ng/ccu_mp.h
new file mode 100644
index 000000000000..3cf12bf95962
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_mp.h
@@ -0,0 +1,77 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_MP_H_
+#define _CCU_MP_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+#include "ccu_div.h"
+#include "ccu_mult.h"
+#include "ccu_mux.h"
+
+/*
+ * struct ccu_mp - Definition of an M-P clock
+ *
+ * Clocks based on the formula parent >> P / M
+ */
+struct ccu_mp {
+	u32			enable;
+
+	struct _ccu_div		m;
+	struct _ccu_div		p;
+	struct ccu_mux_internal	mux;
+	struct ccu_common	common;
+};
+
+#define SUNXI_CCU_MP_WITH_MUX_GATE(_struct, _name, _parents, _reg,	\
+				   _mshift, _mwidth,			\
+				   _pshift, _pwidth,			\
+				   _muxshift, _muxwidth,		\
+				   _gate, _flags)			\
+	struct ccu_mp _struct = {					\
+		.enable	= _gate,					\
+		.m	= _SUNXI_CCU_DIV(_mshift, _mwidth),		\
+		.p	= _SUNXI_CCU_DIV(_pshift, _pwidth),		\
+		.mux	= SUNXI_CLK_MUX(_muxshift, _muxwidth),		\
+		.common	= {						\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT_PARENTS(_name,	\
+							      _parents, \
+							      &ccu_mp_ops, \
+							      _flags),	\
+		}							\
+	}
+
+#define SUNXI_CCU_MP_WITH_MUX(_struct, _name, _parents, _reg,		\
+			      _mshift, _mwidth,				\
+			      _pshift, _pwidth,				\
+			      _muxshift, _muxwidth,			\
+			      _flags)					\
+	SUNXI_CCU_MP_WITH_MUX_GATE(_struct, _name, _parents, _reg,	\
+				   _mshift, _mwidth,			\
+				   _pshift, _pwidth,			\
+				   _muxshift, _muxwidth,		\
+				   0, _flags)
+
+static inline struct ccu_mp *hw_to_ccu_mp(struct clk_hw *hw)
+{
+	struct ccu_common *common = hw_to_ccu_common(hw);
+
+	return container_of(common, struct ccu_mp, common);
+}
+
+extern const struct clk_ops ccu_mp_ops;
+
+#endif /* _CCU_MP_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_mult.h b/drivers/clk/sunxi-ng/ccu_mult.h
new file mode 100644
index 000000000000..609db6610880
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_mult.h
@@ -0,0 +1,15 @@
+#ifndef _CCU_MULT_H_
+#define _CCU_MULT_H_
+
+struct _ccu_mult {
+	u8	shift;
+	u8	width;
+};
+
+#define _SUNXI_CCU_MULT(_shift, _width)		\
+	{					\
+		.shift	= _shift,		\
+		.width	= _width,		\
+	}
+
+#endif /* _CCU_MULT_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_mux.c b/drivers/clk/sunxi-ng/ccu_mux.c
new file mode 100644
index 000000000000..58fc36e7dcce
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_mux.c
@@ -0,0 +1,187 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk-provider.h>
+
+#include "ccu_gate.h"
+#include "ccu_mux.h"
+
+void ccu_mux_helper_adjust_parent_for_prediv(struct ccu_common *common,
+					     struct ccu_mux_internal *cm,
+					     int parent_index,
+					     unsigned long *parent_rate)
+{
+	u8 prediv = 1;
+	u32 reg;
+
+	if (!((common->features & CCU_FEATURE_FIXED_PREDIV) ||
+	      (common->features & CCU_FEATURE_VARIABLE_PREDIV)))
+		return;
+
+	reg = readl(common->base + common->reg);
+	if (parent_index < 0) {
+		parent_index = reg >> cm->shift;
+		parent_index &= (1 << cm->width) - 1;
+	}
+
+	if (common->features & CCU_FEATURE_FIXED_PREDIV)
+		if (parent_index == cm->fixed_prediv.index)
+			prediv = cm->fixed_prediv.div;
+
+	if (common->features & CCU_FEATURE_VARIABLE_PREDIV)
+		if (parent_index == cm->variable_prediv.index) {
+			u8 div;
+
+			div = reg >> cm->variable_prediv.shift;
+			div &= (1 << cm->variable_prediv.width) - 1;
+			prediv = div + 1;
+		}
+
+	*parent_rate = *parent_rate / prediv;
+}
+
+int ccu_mux_helper_determine_rate(struct ccu_common *common,
+				  struct ccu_mux_internal *cm,
+				  struct clk_rate_request *req,
+				  unsigned long (*round)(struct ccu_mux_internal *,
+							 unsigned long,
+							 unsigned long,
+							 void *),
+				  void *data)
+{
+	unsigned long best_parent_rate = 0, best_rate = 0;
+	struct clk_hw *best_parent, *hw = &common->hw;
+	unsigned int i;
+
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+		unsigned long tmp_rate, parent_rate;
+		struct clk_hw *parent;
+
+		parent = clk_hw_get_parent_by_index(hw, i);
+		if (!parent)
+			continue;
+
+		parent_rate = clk_hw_get_rate(parent);
+		ccu_mux_helper_adjust_parent_for_prediv(common, cm, i,
+							&parent_rate);
+
+		tmp_rate = round(cm, clk_hw_get_rate(parent), req->rate, data);
+		if (tmp_rate == req->rate) {
+			best_parent = parent;
+			best_parent_rate = parent_rate;
+			best_rate = tmp_rate;
+			goto out;
+		}
+
+		if ((req->rate - tmp_rate) < (req->rate - best_rate)) {
+			best_rate = tmp_rate;
+			best_parent_rate = parent_rate;
+			best_parent = parent;
+		}
+	}
+
+	if (best_rate == 0)
+		return -EINVAL;
+
+out:
+	req->best_parent_hw = best_parent;
+	req->best_parent_rate = best_parent_rate;
+	req->rate = best_rate;
+	return 0;
+}
+
+u8 ccu_mux_helper_get_parent(struct ccu_common *common,
+			     struct ccu_mux_internal *cm)
+{
+	u32 reg;
+	u8 parent;
+
+	reg = readl(common->base + common->reg);
+	parent = reg >> cm->shift;
+	parent &= (1 << cm->width) - 1;
+
+	return parent;
+}
+
+int ccu_mux_helper_set_parent(struct ccu_common *common,
+			      struct ccu_mux_internal *cm,
+			      u8 index)
+{
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(common->lock, flags);
+
+	reg = readl(common->base + common->reg);
+	reg &= ~GENMASK(cm->width + cm->shift - 1, cm->shift);
+	writel(reg | (index << cm->shift), common->base + common->reg);
+
+	spin_unlock_irqrestore(common->lock, flags);
+
+	return 0;
+}
+
+static void ccu_mux_disable(struct clk_hw *hw)
+{
+	struct ccu_mux *cm = hw_to_ccu_mux(hw);
+
+	return ccu_gate_helper_disable(&cm->common, cm->enable);
+}
+
+static int ccu_mux_enable(struct clk_hw *hw)
+{
+	struct ccu_mux *cm = hw_to_ccu_mux(hw);
+
+	return ccu_gate_helper_enable(&cm->common, cm->enable);
+}
+
+static int ccu_mux_is_enabled(struct clk_hw *hw)
+{
+	struct ccu_mux *cm = hw_to_ccu_mux(hw);
+
+	return ccu_gate_helper_is_enabled(&cm->common, cm->enable);
+}
+
+static u8 ccu_mux_get_parent(struct clk_hw *hw)
+{
+	struct ccu_mux *cm = hw_to_ccu_mux(hw);
+
+	return ccu_mux_helper_get_parent(&cm->common, &cm->mux);
+}
+
+static int ccu_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct ccu_mux *cm = hw_to_ccu_mux(hw);
+
+	return ccu_mux_helper_set_parent(&cm->common, &cm->mux, index);
+}
+
+static unsigned long ccu_mux_recalc_rate(struct clk_hw *hw,
+					 unsigned long parent_rate)
+{
+	struct ccu_mux *cm = hw_to_ccu_mux(hw);
+
+	ccu_mux_helper_adjust_parent_for_prediv(&cm->common, &cm->mux, -1,
+						&parent_rate);
+
+	return parent_rate;
+}
+
+const struct clk_ops ccu_mux_ops = {
+	.disable	= ccu_mux_disable,
+	.enable		= ccu_mux_enable,
+	.is_enabled	= ccu_mux_is_enabled,
+
+	.get_parent	= ccu_mux_get_parent,
+	.set_parent	= ccu_mux_set_parent,
+
+	.determine_rate	= __clk_mux_determine_rate,
+	.recalc_rate	= ccu_mux_recalc_rate,
+};
diff --git a/drivers/clk/sunxi-ng/ccu_mux.h b/drivers/clk/sunxi-ng/ccu_mux.h
new file mode 100644
index 000000000000..945082631e7d
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_mux.h
@@ -0,0 +1,91 @@
+#ifndef _CCU_MUX_H_
+#define _CCU_MUX_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+
+struct ccu_mux_internal {
+	u8	shift;
+	u8	width;
+
+	struct {
+		u8	index;
+		u8	div;
+	} fixed_prediv;
+
+	struct {
+		u8	index;
+		u8	shift;
+		u8	width;
+	} variable_prediv;
+};
+
+#define SUNXI_CLK_MUX(_shift, _width)	\
+	{					\
+		.shift	= _shift,		\
+		.width	= _width,		\
+	}
+
+struct ccu_mux {
+	u16			reg;
+	u32			enable;
+
+	struct ccu_mux_internal	mux;
+	struct ccu_common	common;
+};
+
+#define SUNXI_CCU_MUX(_struct, _name, _parents, _reg, _shift, _width, _flags) \
+	struct ccu_mux _struct = {					\
+		.mux	= SUNXI_CLK_MUX(_shift, _width),		\
+		.common	= {						\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT_PARENTS(_name,	\
+							      _parents, \
+							      &ccu_mux_ops, \
+							      _flags),	\
+		}							\
+	}
+
+#define SUNXI_CCU_MUX_WITH_GATE(_struct, _name, _parents, _reg,		\
+				_shift, _width, _gate, _flags)		\
+	struct ccu_mux _struct = {					\
+		.enable	= _gate,					\
+		.mux	= SUNXI_CLK_MUX(_shift, _width),		\
+		.common	= {						\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT_PARENTS(_name,	\
+							      _parents, \
+							      &ccu_mux_ops, \
+							      _flags),	\
+		}							\
+	}
+
+static inline struct ccu_mux *hw_to_ccu_mux(struct clk_hw *hw)
+{
+	struct ccu_common *common = hw_to_ccu_common(hw);
+
+	return container_of(common, struct ccu_mux, common);
+}
+
+extern const struct clk_ops ccu_mux_ops;
+
+void ccu_mux_helper_adjust_parent_for_prediv(struct ccu_common *common,
+					     struct ccu_mux_internal *cm,
+					     int parent_index,
+					     unsigned long *parent_rate);
+int ccu_mux_helper_determine_rate(struct ccu_common *common,
+				  struct ccu_mux_internal *cm,
+				  struct clk_rate_request *req,
+				  unsigned long (*round)(struct ccu_mux_internal *,
+							 unsigned long,
+							 unsigned long,
+							 void *),
+				  void *data);
+u8 ccu_mux_helper_get_parent(struct ccu_common *common,
+			     struct ccu_mux_internal *cm);
+int ccu_mux_helper_set_parent(struct ccu_common *common,
+			      struct ccu_mux_internal *cm,
+			      u8 index);
+
+#endif /* _CCU_MUX_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_nk.c b/drivers/clk/sunxi-ng/ccu_nk.c
new file mode 100644
index 000000000000..4470ffc8cf0d
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_nk.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/rational.h>
+
+#include "ccu_gate.h"
+#include "ccu_nk.h"
+
+void ccu_nk_find_best(unsigned long parent, unsigned long rate,
+		      unsigned int max_n, unsigned int max_k,
+		      unsigned int *n, unsigned int *k)
+{
+	unsigned long best_rate = 0;
+	unsigned int best_k = 0, best_n = 0;
+	unsigned int _k, _n;
+
+	for (_k = 1; _k <= max_k; _k++) {
+		for (_n = 1; _n <= max_n; _n++) {
+			unsigned long tmp_rate = parent * _n * _k;
+
+			if (tmp_rate > rate)
+				continue;
+
+			if ((rate - tmp_rate) < (rate - best_rate)) {
+				best_rate = tmp_rate;
+				best_k = _k;
+				best_n = _n;
+			}
+		}
+	}
+
+	*k = best_k;
+	*n = best_n;
+}
+
+static void ccu_nk_disable(struct clk_hw *hw)
+{
+	struct ccu_nk *nk = hw_to_ccu_nk(hw);
+
+	return ccu_gate_helper_disable(&nk->common, nk->enable);
+}
+
+static int ccu_nk_enable(struct clk_hw *hw)
+{
+	struct ccu_nk *nk = hw_to_ccu_nk(hw);
+
+	return ccu_gate_helper_enable(&nk->common, nk->enable);
+}
+
+static int ccu_nk_is_enabled(struct clk_hw *hw)
+{
+	struct ccu_nk *nk = hw_to_ccu_nk(hw);
+
+	return ccu_gate_helper_is_enabled(&nk->common, nk->enable);
+}
+
+static unsigned long ccu_nk_recalc_rate(struct clk_hw *hw,
+					unsigned long parent_rate)
+{
+	struct ccu_nk *nk = hw_to_ccu_nk(hw);
+	unsigned long rate, n, k;
+	u32 reg;
+
+	reg = readl(nk->common.base + nk->common.reg);
+
+	n = reg >> nk->n.shift;
+	n &= (1 << nk->n.width) - 1;
+
+	k = reg >> nk->k.shift;
+	k &= (1 << nk->k.width) - 1;
+
+	rate = parent_rate * (n + 1) * (k + 1);
+
+	if (nk->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate /= nk->fixed_post_div;
+
+	return rate;
+}
+
+static long ccu_nk_round_rate(struct clk_hw *hw, unsigned long rate,
+			      unsigned long *parent_rate)
+{
+	struct ccu_nk *nk = hw_to_ccu_nk(hw);
+	unsigned int n, k;
+
+	if (nk->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate *= nk->fixed_post_div;
+
+	ccu_nk_find_best(*parent_rate, rate,
+			 1 << nk->n.width, 1 << nk->k.width,
+			 &n, &k);
+
+	rate = *parent_rate * n * k;
+	if (nk->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate = rate / nk->fixed_post_div;
+
+	return rate;
+}
+
+static int ccu_nk_set_rate(struct clk_hw *hw, unsigned long rate,
+			   unsigned long parent_rate)
+{
+	struct ccu_nk *nk = hw_to_ccu_nk(hw);
+	unsigned long flags;
+	unsigned int n, k;
+	u32 reg;
+
+	if (nk->common.features & CCU_FEATURE_FIXED_POSTDIV)
+		rate = rate * nk->fixed_post_div;
+
+	ccu_nk_find_best(parent_rate, rate,
+			 1 << nk->n.width, 1 << nk->k.width,
+			 &n, &k);
+
+	spin_lock_irqsave(nk->common.lock, flags);
+
+	reg = readl(nk->common.base + nk->common.reg);
+	reg &= ~GENMASK(nk->n.width + nk->n.shift - 1, nk->n.shift);
+	reg &= ~GENMASK(nk->k.width + nk->k.shift - 1, nk->k.shift);
+
+	writel(reg | ((k - 1) << nk->k.shift) | ((n - 1) << nk->n.shift),
+	       nk->common.base + nk->common.reg);
+
+	spin_unlock_irqrestore(nk->common.lock, flags);
+
+	ccu_helper_wait_for_lock(&nk->common, nk->lock);
+
+	return 0;
+}
+
+const struct clk_ops ccu_nk_ops = {
+	.disable	= ccu_nk_disable,
+	.enable		= ccu_nk_enable,
+	.is_enabled	= ccu_nk_is_enabled,
+
+	.recalc_rate	= ccu_nk_recalc_rate,
+	.round_rate	= ccu_nk_round_rate,
+	.set_rate	= ccu_nk_set_rate,
+};
diff --git a/drivers/clk/sunxi-ng/ccu_nk.h b/drivers/clk/sunxi-ng/ccu_nk.h
new file mode 100644
index 000000000000..4b52da0c29fe
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_nk.h
@@ -0,0 +1,71 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_NK_H_
+#define _CCU_NK_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+#include "ccu_div.h"
+#include "ccu_mult.h"
+
+/*
+ * struct ccu_nk - Definition of an N-K clock
+ *
+ * Clocks based on the formula parent * N * K
+ */
+struct ccu_nk {
+	u16			reg;
+	u32			enable;
+	u32			lock;
+
+	struct _ccu_mult	n;
+	struct _ccu_mult	k;
+
+	unsigned int		fixed_post_div;
+
+	struct ccu_common	common;
+};
+
+#define SUNXI_CCU_NK_WITH_GATE_LOCK_POSTDIV(_struct, _name, _parent, _reg, \
+					    _nshift, _nwidth,		\
+					    _kshift, _kwidth,		\
+					    _gate, _lock, _postdiv,	\
+					    _flags)			\
+	struct ccu_nk _struct = {					\
+		.enable		= _gate,				\
+		.lock		= _lock,				\
+		.k		= _SUNXI_CCU_MULT(_kshift, _kwidth),	\
+		.n		= _SUNXI_CCU_MULT(_nshift, _nwidth),	\
+		.fixed_post_div	= _postdiv,				\
+		.common		= {					\
+			.reg		= _reg,				\
+			.features	= CCU_FEATURE_FIXED_POSTDIV,	\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &ccu_nk_ops,	\
+						      _flags),		\
+		},							\
+	}
+
+static inline struct ccu_nk *hw_to_ccu_nk(struct clk_hw *hw)
+{
+	struct ccu_common *common = hw_to_ccu_common(hw);
+
+	return container_of(common, struct ccu_nk, common);
+}
+
+extern const struct clk_ops ccu_nk_ops;
+
+#endif /* _CCU_NK_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_nkm.c b/drivers/clk/sunxi-ng/ccu_nkm.c
new file mode 100644
index 000000000000..2071822b1e9c
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_nkm.c
@@ -0,0 +1,153 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/rational.h>
+
+#include "ccu_gate.h"
+#include "ccu_nkm.h"
+
+struct _ccu_nkm {
+	unsigned long	n, max_n;
+	unsigned long	k, max_k;
+	unsigned long	m, max_m;
+};
+
+static void ccu_nkm_find_best(unsigned long parent, unsigned long rate,
+			      struct _ccu_nkm *nkm)
+{
+	unsigned long best_rate = 0;
+	unsigned long best_n = 0, best_k = 0, best_m = 0;
+	unsigned long _n, _k, _m;
+
+	for (_k = 1; _k <= nkm->max_k; _k++) {
+		unsigned long tmp_rate;
+
+		rational_best_approximation(rate / _k, parent,
+					    nkm->max_n, nkm->max_m, &_n, &_m);
+
+		tmp_rate = parent * _n * _k / _m;
+
+		if (tmp_rate > rate)
+			continue;
+
+		if ((rate - tmp_rate) < (rate - best_rate)) {
+			best_rate = tmp_rate;
+			best_n = _n;
+			best_k = _k;
+			best_m = _m;
+		}
+	}
+
+	nkm->n = best_n;
+	nkm->k = best_k;
+	nkm->m = best_m;
+}
+
+static void ccu_nkm_disable(struct clk_hw *hw)
+{
+	struct ccu_nkm *nkm = hw_to_ccu_nkm(hw);
+
+	return ccu_gate_helper_disable(&nkm->common, nkm->enable);
+}
+
+static int ccu_nkm_enable(struct clk_hw *hw)
+{
+	struct ccu_nkm *nkm = hw_to_ccu_nkm(hw);
+
+	return ccu_gate_helper_enable(&nkm->common, nkm->enable);
+}
+
+static int ccu_nkm_is_enabled(struct clk_hw *hw)
+{
+	struct ccu_nkm *nkm = hw_to_ccu_nkm(hw);
+
+	return ccu_gate_helper_is_enabled(&nkm->common, nkm->enable);
+}
+
+static unsigned long ccu_nkm_recalc_rate(struct clk_hw *hw,
+					unsigned long parent_rate)
+{
+	struct ccu_nkm *nkm = hw_to_ccu_nkm(hw);
+	unsigned long n, m, k;
+	u32 reg;
+
+	reg = readl(nkm->common.base + nkm->common.reg);
+
+	n = reg >> nkm->n.shift;
+	n &= (1 << nkm->n.width) - 1;
+
+	k = reg >> nkm->k.shift;
+	k &= (1 << nkm->k.width) - 1;
+
+	m = reg >> nkm->m.shift;
+	m &= (1 << nkm->m.width) - 1;
+
+	return parent_rate * (n + 1) * (k + 1) / (m + 1);
+}
+
+static long ccu_nkm_round_rate(struct clk_hw *hw, unsigned long rate,
+			      unsigned long *parent_rate)
+{
+	struct ccu_nkm *nkm = hw_to_ccu_nkm(hw);
+	struct _ccu_nkm _nkm;
+
+	_nkm.max_n = 1 << nkm->n.width;
+	_nkm.max_k = 1 << nkm->k.width;
+	_nkm.max_m = 1 << nkm->m.width;
+
+	ccu_nkm_find_best(*parent_rate, rate, &_nkm);
+
+	return *parent_rate * _nkm.n * _nkm.k / _nkm.m;
+}
+
+static int ccu_nkm_set_rate(struct clk_hw *hw, unsigned long rate,
+			   unsigned long parent_rate)
+{
+	struct ccu_nkm *nkm = hw_to_ccu_nkm(hw);
+	struct _ccu_nkm _nkm;
+	unsigned long flags;
+	u32 reg;
+
+	_nkm.max_n = 1 << nkm->n.width;
+	_nkm.max_k = 1 << nkm->k.width;
+	_nkm.max_m = 1 << nkm->m.width;
+
+	ccu_nkm_find_best(parent_rate, rate, &_nkm);
+
+	spin_lock_irqsave(nkm->common.lock, flags);
+
+	reg = readl(nkm->common.base + nkm->common.reg);
+	reg &= ~GENMASK(nkm->n.width + nkm->n.shift - 1, nkm->n.shift);
+	reg &= ~GENMASK(nkm->k.width + nkm->k.shift - 1, nkm->k.shift);
+	reg &= ~GENMASK(nkm->m.width + nkm->m.shift - 1, nkm->m.shift);
+
+	reg |= (_nkm.n - 1) << nkm->n.shift;
+	reg |= (_nkm.k - 1) << nkm->k.shift;
+	reg |= (_nkm.m - 1) << nkm->m.shift;
+
+	writel(reg, nkm->common.base + nkm->common.reg);
+
+	spin_unlock_irqrestore(nkm->common.lock, flags);
+
+	ccu_helper_wait_for_lock(&nkm->common, nkm->lock);
+
+	return 0;
+}
+
+const struct clk_ops ccu_nkm_ops = {
+	.disable	= ccu_nkm_disable,
+	.enable		= ccu_nkm_enable,
+	.is_enabled	= ccu_nkm_is_enabled,
+
+	.recalc_rate	= ccu_nkm_recalc_rate,
+	.round_rate	= ccu_nkm_round_rate,
+	.set_rate	= ccu_nkm_set_rate,
+};
diff --git a/drivers/clk/sunxi-ng/ccu_nkm.h b/drivers/clk/sunxi-ng/ccu_nkm.h
new file mode 100644
index 000000000000..1936ac1c6b37
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_nkm.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_NKM_H_
+#define _CCU_NKM_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+#include "ccu_div.h"
+#include "ccu_mult.h"
+
+/*
+ * struct ccu_nkm - Definition of an N-K-M clock
+ *
+ * Clocks based on the formula parent * N * K / M
+ */
+struct ccu_nkm {
+	u32			enable;
+	u32			lock;
+
+	struct _ccu_mult	n;
+	struct _ccu_mult	k;
+	struct _ccu_div		m;
+
+	struct ccu_common	common;
+};
+
+#define SUNXI_CCU_NKM_WITH_GATE_LOCK(_struct, _name, _parent, _reg,	\
+				     _nshift, _nwidth,			\
+				     _kshift, _kwidth,			\
+				     _mshift, _mwidth,			\
+				     _gate, _lock, _flags)		\
+	struct ccu_nkm _struct = {					\
+		.enable		= _gate,				\
+		.lock		= _lock,				\
+		.k		= _SUNXI_CCU_MULT(_kshift, _kwidth),	\
+		.n		= _SUNXI_CCU_MULT(_nshift, _nwidth),	\
+		.m		= _SUNXI_CCU_DIV(_mshift, _mwidth),	\
+		.common		= {					\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &ccu_nkm_ops,	\
+						      _flags),		\
+		},							\
+	}
+
+static inline struct ccu_nkm *hw_to_ccu_nkm(struct clk_hw *hw)
+{
+	struct ccu_common *common = hw_to_ccu_common(hw);
+
+	return container_of(common, struct ccu_nkm, common);
+}
+
+extern const struct clk_ops ccu_nkm_ops;
+
+#endif /* _CCU_NKM_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_nkmp.c b/drivers/clk/sunxi-ng/ccu_nkmp.c
new file mode 100644
index 000000000000..9f2b98e19dc9
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_nkmp.c
@@ -0,0 +1,167 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/rational.h>
+
+#include "ccu_gate.h"
+#include "ccu_nkmp.h"
+
+struct _ccu_nkmp {
+	unsigned long	n, max_n;
+	unsigned long	k, max_k;
+	unsigned long	m, max_m;
+	unsigned long	p, max_p;
+};
+
+static void ccu_nkmp_find_best(unsigned long parent, unsigned long rate,
+			       struct _ccu_nkmp *nkmp)
+{
+	unsigned long best_rate = 0;
+	unsigned long best_n = 0, best_k = 0, best_m = 0, best_p = 0;
+	unsigned long _n, _k, _m, _p;
+
+	for (_k = 1; _k <= nkmp->max_k; _k++) {
+		for (_p = 0; _p <= nkmp->max_p; _p++) {
+			unsigned long tmp_rate;
+
+			rational_best_approximation(rate / _k, parent >> _p,
+						    nkmp->max_n, nkmp->max_m,
+						    &_n, &_m);
+
+			tmp_rate = (parent * _n * _k >> _p) / _m;
+
+			if (tmp_rate > rate)
+				continue;
+
+			if ((rate - tmp_rate) < (rate - best_rate)) {
+				best_rate = tmp_rate;
+				best_n = _n;
+				best_k = _k;
+				best_m = _m;
+				best_p = _p;
+			}
+		}
+	}
+
+	nkmp->n = best_n;
+	nkmp->k = best_k;
+	nkmp->m = best_m;
+	nkmp->p = best_p;
+}
+
+static void ccu_nkmp_disable(struct clk_hw *hw)
+{
+	struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw);
+
+	return ccu_gate_helper_disable(&nkmp->common, nkmp->enable);
+}
+
+static int ccu_nkmp_enable(struct clk_hw *hw)
+{
+	struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw);
+
+	return ccu_gate_helper_enable(&nkmp->common, nkmp->enable);
+}
+
+static int ccu_nkmp_is_enabled(struct clk_hw *hw)
+{
+	struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw);
+
+	return ccu_gate_helper_is_enabled(&nkmp->common, nkmp->enable);
+}
+
+static unsigned long ccu_nkmp_recalc_rate(struct clk_hw *hw,
+					unsigned long parent_rate)
+{
+	struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw);
+	unsigned long n, m, k, p;
+	u32 reg;
+
+	reg = readl(nkmp->common.base + nkmp->common.reg);
+
+	n = reg >> nkmp->n.shift;
+	n &= (1 << nkmp->n.width) - 1;
+
+	k = reg >> nkmp->k.shift;
+	k &= (1 << nkmp->k.width) - 1;
+
+	m = reg >> nkmp->m.shift;
+	m &= (1 << nkmp->m.width) - 1;
+
+	p = reg >> nkmp->p.shift;
+	p &= (1 << nkmp->p.width) - 1;
+
+	return (parent_rate * (n + 1) * (k + 1) >> p) / (m + 1);
+}
+
+static long ccu_nkmp_round_rate(struct clk_hw *hw, unsigned long rate,
+			      unsigned long *parent_rate)
+{
+	struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw);
+	struct _ccu_nkmp _nkmp;
+
+	_nkmp.max_n = 1 << nkmp->n.width;
+	_nkmp.max_k = 1 << nkmp->k.width;
+	_nkmp.max_m = 1 << nkmp->m.width;
+	_nkmp.max_p = (1 << nkmp->p.width) - 1;
+
+	ccu_nkmp_find_best(*parent_rate, rate,
+			   &_nkmp);
+
+	return (*parent_rate * _nkmp.n * _nkmp.k >> _nkmp.p) / _nkmp.m;
+}
+
+static int ccu_nkmp_set_rate(struct clk_hw *hw, unsigned long rate,
+			   unsigned long parent_rate)
+{
+	struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw);
+	struct _ccu_nkmp _nkmp;
+	unsigned long flags;
+	u32 reg;
+
+	_nkmp.max_n = 1 << nkmp->n.width;
+	_nkmp.max_k = 1 << nkmp->k.width;
+	_nkmp.max_m = 1 << nkmp->m.width;
+	_nkmp.max_p = (1 << nkmp->p.width) - 1;
+
+	ccu_nkmp_find_best(parent_rate, rate, &_nkmp);
+
+	spin_lock_irqsave(nkmp->common.lock, flags);
+
+	reg = readl(nkmp->common.base + nkmp->common.reg);
+	reg &= ~GENMASK(nkmp->n.width + nkmp->n.shift - 1, nkmp->n.shift);
+	reg &= ~GENMASK(nkmp->k.width + nkmp->k.shift - 1, nkmp->k.shift);
+	reg &= ~GENMASK(nkmp->m.width + nkmp->m.shift - 1, nkmp->m.shift);
+	reg &= ~GENMASK(nkmp->p.width + nkmp->p.shift - 1, nkmp->p.shift);
+
+	reg |= (_nkmp.n - 1) << nkmp->n.shift;
+	reg |= (_nkmp.k - 1) << nkmp->k.shift;
+	reg |= (_nkmp.m - 1) << nkmp->m.shift;
+	reg |= _nkmp.p << nkmp->p.shift;
+
+	writel(reg, nkmp->common.base + nkmp->common.reg);
+
+	spin_unlock_irqrestore(nkmp->common.lock, flags);
+
+	ccu_helper_wait_for_lock(&nkmp->common, nkmp->lock);
+
+	return 0;
+}
+
+const struct clk_ops ccu_nkmp_ops = {
+	.disable	= ccu_nkmp_disable,
+	.enable		= ccu_nkmp_enable,
+	.is_enabled	= ccu_nkmp_is_enabled,
+
+	.recalc_rate	= ccu_nkmp_recalc_rate,
+	.round_rate	= ccu_nkmp_round_rate,
+	.set_rate	= ccu_nkmp_set_rate,
+};
diff --git a/drivers/clk/sunxi-ng/ccu_nkmp.h b/drivers/clk/sunxi-ng/ccu_nkmp.h
new file mode 100644
index 000000000000..5adb0c92a614
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_nkmp.h
@@ -0,0 +1,71 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_NKMP_H_
+#define _CCU_NKMP_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+#include "ccu_div.h"
+#include "ccu_mult.h"
+
+/*
+ * struct ccu_nkmp - Definition of an N-K-M-P clock
+ *
+ * Clocks based on the formula parent * N * K >> P / M
+ */
+struct ccu_nkmp {
+	u32			enable;
+	u32			lock;
+
+	struct _ccu_mult	n;
+	struct _ccu_mult	k;
+	struct _ccu_div		m;
+	struct _ccu_div		p;
+
+	struct ccu_common	common;
+};
+
+#define SUNXI_CCU_NKMP_WITH_GATE_LOCK(_struct, _name, _parent, _reg,	\
+				      _nshift, _nwidth,			\
+				      _kshift, _kwidth,			\
+				      _mshift, _mwidth,			\
+				      _pshift, _pwidth,			\
+				      _gate, _lock, _flags)		\
+	struct ccu_nkmp _struct = {					\
+		.enable		= _gate,				\
+		.lock		= _lock,				\
+		.n		= _SUNXI_CCU_MULT(_nshift, _nwidth),	\
+		.k		= _SUNXI_CCU_MULT(_kshift, _kwidth),	\
+		.m		= _SUNXI_CCU_DIV(_mshift, _mwidth),	\
+		.p		= _SUNXI_CCU_DIV(_pshift, _pwidth),	\
+		.common		= {					\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &ccu_nkmp_ops,	\
+						      _flags),		\
+		},							\
+	}
+
+static inline struct ccu_nkmp *hw_to_ccu_nkmp(struct clk_hw *hw)
+{
+	struct ccu_common *common = hw_to_ccu_common(hw);
+
+	return container_of(common, struct ccu_nkmp, common);
+}
+
+extern const struct clk_ops ccu_nkmp_ops;
+
+#endif /* _CCU_NKMP_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_nm.c b/drivers/clk/sunxi-ng/ccu_nm.c
new file mode 100644
index 000000000000..e35ddd8eec8b
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_nm.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/rational.h>
+
+#include "ccu_frac.h"
+#include "ccu_gate.h"
+#include "ccu_nm.h"
+
+static void ccu_nm_disable(struct clk_hw *hw)
+{
+	struct ccu_nm *nm = hw_to_ccu_nm(hw);
+
+	return ccu_gate_helper_disable(&nm->common, nm->enable);
+}
+
+static int ccu_nm_enable(struct clk_hw *hw)
+{
+	struct ccu_nm *nm = hw_to_ccu_nm(hw);
+
+	return ccu_gate_helper_enable(&nm->common, nm->enable);
+}
+
+static int ccu_nm_is_enabled(struct clk_hw *hw)
+{
+	struct ccu_nm *nm = hw_to_ccu_nm(hw);
+
+	return ccu_gate_helper_is_enabled(&nm->common, nm->enable);
+}
+
+static unsigned long ccu_nm_recalc_rate(struct clk_hw *hw,
+					unsigned long parent_rate)
+{
+	struct ccu_nm *nm = hw_to_ccu_nm(hw);
+	unsigned long n, m;
+	u32 reg;
+
+	if (ccu_frac_helper_is_enabled(&nm->common, &nm->frac))
+		return ccu_frac_helper_read_rate(&nm->common, &nm->frac);
+
+	reg = readl(nm->common.base + nm->common.reg);
+
+	n = reg >> nm->n.shift;
+	n &= (1 << nm->n.width) - 1;
+
+	m = reg >> nm->m.shift;
+	m &= (1 << nm->m.width) - 1;
+
+	return parent_rate * (n + 1) / (m + 1);
+}
+
+static long ccu_nm_round_rate(struct clk_hw *hw, unsigned long rate,
+			      unsigned long *parent_rate)
+{
+	struct ccu_nm *nm = hw_to_ccu_nm(hw);
+	unsigned long n, m;
+
+	rational_best_approximation(rate, *parent_rate,
+				    1 << nm->n.width, 1 << nm->m.width,
+				    &n, &m);
+
+	return *parent_rate * n / m;
+}
+
+static int ccu_nm_set_rate(struct clk_hw *hw, unsigned long rate,
+			   unsigned long parent_rate)
+{
+	struct ccu_nm *nm = hw_to_ccu_nm(hw);
+	unsigned long flags;
+	unsigned long n, m;
+	u32 reg;
+
+	if (ccu_frac_helper_has_rate(&nm->common, &nm->frac, rate))
+		return ccu_frac_helper_set_rate(&nm->common, &nm->frac, rate);
+	else
+		ccu_frac_helper_disable(&nm->common, &nm->frac);
+
+	rational_best_approximation(rate, parent_rate,
+				    1 << nm->n.width, 1 << nm->m.width,
+				    &n, &m);
+
+	spin_lock_irqsave(nm->common.lock, flags);
+
+	reg = readl(nm->common.base + nm->common.reg);
+	reg &= ~GENMASK(nm->n.width + nm->n.shift - 1, nm->n.shift);
+	reg &= ~GENMASK(nm->m.width + nm->m.shift - 1, nm->m.shift);
+
+	writel(reg | ((m - 1) << nm->m.shift) | ((n - 1) << nm->n.shift),
+	       nm->common.base + nm->common.reg);
+
+	spin_unlock_irqrestore(nm->common.lock, flags);
+
+	ccu_helper_wait_for_lock(&nm->common, nm->lock);
+
+	return 0;
+}
+
+const struct clk_ops ccu_nm_ops = {
+	.disable	= ccu_nm_disable,
+	.enable		= ccu_nm_enable,
+	.is_enabled	= ccu_nm_is_enabled,
+
+	.recalc_rate	= ccu_nm_recalc_rate,
+	.round_rate	= ccu_nm_round_rate,
+	.set_rate	= ccu_nm_set_rate,
+};
diff --git a/drivers/clk/sunxi-ng/ccu_nm.h b/drivers/clk/sunxi-ng/ccu_nm.h
new file mode 100644
index 000000000000..0b7bcd33a2df
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_nm.h
@@ -0,0 +1,91 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_NM_H_
+#define _CCU_NM_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+#include "ccu_div.h"
+#include "ccu_frac.h"
+#include "ccu_mult.h"
+
+/*
+ * struct ccu_nm - Definition of an N-M clock
+ *
+ * Clocks based on the formula parent * N / M
+ */
+struct ccu_nm {
+	u32			enable;
+	u32			lock;
+
+	struct _ccu_mult	n;
+	struct _ccu_div		m;
+	struct _ccu_frac	frac;
+
+	struct ccu_common	common;
+};
+
+#define SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(_struct, _name, _parent, _reg,	\
+					 _nshift, _nwidth,		\
+					 _mshift, _mwidth,		\
+					 _frac_en, _frac_sel,		\
+					 _frac_rate_0, _frac_rate_1,	\
+					 _gate, _lock, _flags)		\
+	struct ccu_nm _struct = {					\
+		.enable		= _gate,				\
+		.lock		= _lock,				\
+		.n		= _SUNXI_CCU_MULT(_nshift, _nwidth),	\
+		.m		= _SUNXI_CCU_DIV(_mshift, _mwidth),	\
+		.frac		= _SUNXI_CCU_FRAC(_frac_en, _frac_sel,	\
+						  _frac_rate_0,		\
+						  _frac_rate_1),	\
+		.common		= {					\
+			.reg		= _reg,				\
+			.features	= CCU_FEATURE_FRACTIONAL,	\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &ccu_nm_ops,	\
+						      _flags),		\
+		},							\
+	}
+
+#define SUNXI_CCU_NM_WITH_GATE_LOCK(_struct, _name, _parent, _reg,	\
+				    _nshift, _nwidth,			\
+				    _mshift, _mwidth,			\
+				    _gate, _lock, _flags)		\
+	struct ccu_nm _struct = {					\
+		.enable		= _gate,				\
+		.lock		= _lock,				\
+		.n		= _SUNXI_CCU_MULT(_nshift, _nwidth),	\
+		.m		= _SUNXI_CCU_DIV(_mshift, _mwidth),	\
+		.common		= {					\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &ccu_nm_ops,	\
+						      _flags),		\
+		},							\
+	}
+
+static inline struct ccu_nm *hw_to_ccu_nm(struct clk_hw *hw)
+{
+	struct ccu_common *common = hw_to_ccu_common(hw);
+
+	return container_of(common, struct ccu_nm, common);
+}
+
+extern const struct clk_ops ccu_nm_ops;
+
+#endif /* _CCU_NM_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_phase.c b/drivers/clk/sunxi-ng/ccu_phase.c
new file mode 100644
index 000000000000..400c58ad72fd
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_phase.c
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/spinlock.h>
+
+#include "ccu_phase.h"
+
+static int ccu_phase_get_phase(struct clk_hw *hw)
+{
+	struct ccu_phase *phase = hw_to_ccu_phase(hw);
+	struct clk_hw *parent, *grandparent;
+	unsigned int parent_rate, grandparent_rate;
+	u16 step, parent_div;
+	u32 reg;
+	u8 delay;
+
+	reg = readl(phase->common.base + phase->common.reg);
+	delay = (reg >> phase->shift);
+	delay &= (1 << phase->width) - 1;
+
+	if (!delay)
+		return 180;
+
+	/* Get our parent clock, it's the one that can adjust its rate */
+	parent = clk_hw_get_parent(hw);
+	if (!parent)
+		return -EINVAL;
+
+	/* And its rate */
+	parent_rate = clk_hw_get_rate(parent);
+	if (!parent_rate)
+		return -EINVAL;
+
+	/* Now, get our parent's parent (most likely some PLL) */
+	grandparent = clk_hw_get_parent(parent);
+	if (!grandparent)
+		return -EINVAL;
+
+	/* And its rate */
+	grandparent_rate = clk_hw_get_rate(grandparent);
+	if (!grandparent_rate)
+		return -EINVAL;
+
+	/* Get our parent clock divider */
+	parent_div = grandparent_rate / parent_rate;
+
+	step = DIV_ROUND_CLOSEST(360, parent_div);
+	return delay * step;
+}
+
+static int ccu_phase_set_phase(struct clk_hw *hw, int degrees)
+{
+	struct ccu_phase *phase = hw_to_ccu_phase(hw);
+	struct clk_hw *parent, *grandparent;
+	unsigned int parent_rate, grandparent_rate;
+	unsigned long flags;
+	u32 reg;
+	u8 delay;
+
+	/* Get our parent clock, it's the one that can adjust its rate */
+	parent = clk_hw_get_parent(hw);
+	if (!parent)
+		return -EINVAL;
+
+	/* And its rate */
+	parent_rate = clk_hw_get_rate(parent);
+	if (!parent_rate)
+		return -EINVAL;
+
+	/* Now, get our parent's parent (most likely some PLL) */
+	grandparent = clk_hw_get_parent(parent);
+	if (!grandparent)
+		return -EINVAL;
+
+	/* And its rate */
+	grandparent_rate = clk_hw_get_rate(grandparent);
+	if (!grandparent_rate)
+		return -EINVAL;
+
+	if (degrees != 180) {
+		u16 step, parent_div;
+
+		/* Get our parent divider */
+		parent_div = grandparent_rate / parent_rate;
+
+		/*
+		 * We can only outphase the clocks by multiple of the
+		 * PLL's period.
+		 *
+		 * Since our parent clock is only a divider, and the
+		 * formula to get the outphasing in degrees is deg =
+		 * 360 * delta / period
+		 *
+		 * If we simplify this formula, we can see that the
+		 * only thing that we're concerned about is the number
+		 * of period we want to outphase our clock from, and
+		 * the divider set by our parent clock.
+		 */
+		step = DIV_ROUND_CLOSEST(360, parent_div);
+		delay = DIV_ROUND_CLOSEST(degrees, step);
+	} else {
+		delay = 0;
+	}
+
+	spin_lock_irqsave(phase->common.lock, flags);
+	reg = readl(phase->common.base + phase->common.reg);
+	reg &= ~GENMASK(phase->width + phase->shift - 1, phase->shift);
+	writel(reg | (delay << phase->shift),
+	       phase->common.base + phase->common.reg);
+	spin_unlock_irqrestore(phase->common.lock, flags);
+
+	return 0;
+}
+
+const struct clk_ops ccu_phase_ops = {
+	.get_phase	= ccu_phase_get_phase,
+	.set_phase	= ccu_phase_set_phase,
+};
diff --git a/drivers/clk/sunxi-ng/ccu_phase.h b/drivers/clk/sunxi-ng/ccu_phase.h
new file mode 100644
index 000000000000..75a091a4c565
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_phase.h
@@ -0,0 +1,50 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_PHASE_H_
+#define _CCU_PHASE_H_
+
+#include <linux/clk-provider.h>
+
+#include "ccu_common.h"
+
+struct ccu_phase {
+	u8			shift;
+	u8			width;
+
+	struct ccu_common	common;
+};
+
+#define SUNXI_CCU_PHASE(_struct, _name, _parent, _reg, _shift, _width, _flags) \
+	struct ccu_phase _struct = {					\
+		.shift	= _shift,					\
+		.width	= _width,					\
+		.common	= {						\
+			.reg		= _reg,				\
+			.hw.init	= CLK_HW_INIT(_name,		\
+						      _parent,		\
+						      &ccu_phase_ops,	\
+						      _flags),		\
+		}							\
+	}
+
+static inline struct ccu_phase *hw_to_ccu_phase(struct clk_hw *hw)
+{
+	struct ccu_common *common = hw_to_ccu_common(hw);
+
+	return container_of(common, struct ccu_phase, common);
+}
+
+extern const struct clk_ops ccu_phase_ops;
+
+#endif /* _CCU_PHASE_H_ */
diff --git a/drivers/clk/sunxi-ng/ccu_reset.c b/drivers/clk/sunxi-ng/ccu_reset.c
new file mode 100644
index 000000000000..6c31d48783a7
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_reset.c
@@ -0,0 +1,55 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/io.h>
+#include <linux/reset-controller.h>
+
+#include "ccu_reset.h"
+
+static int ccu_reset_assert(struct reset_controller_dev *rcdev,
+			    unsigned long id)
+{
+	struct ccu_reset *ccu = rcdev_to_ccu_reset(rcdev);
+	const struct ccu_reset_map *map = &ccu->reset_map[id];
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(ccu->lock, flags);
+
+	reg = readl(ccu->base + map->reg);
+	writel(reg & ~map->bit, ccu->base + map->reg);
+
+	spin_unlock_irqrestore(ccu->lock, flags);
+
+	return 0;
+}
+
+static int ccu_reset_deassert(struct reset_controller_dev *rcdev,
+			      unsigned long id)
+{
+	struct ccu_reset *ccu = rcdev_to_ccu_reset(rcdev);
+	const struct ccu_reset_map *map = &ccu->reset_map[id];
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(ccu->lock, flags);
+
+	reg = readl(ccu->base + map->reg);
+	writel(reg | map->bit, ccu->base + map->reg);
+
+	spin_unlock_irqrestore(ccu->lock, flags);
+
+	return 0;
+}
+
+const struct reset_control_ops ccu_reset_ops = {
+	.assert		= ccu_reset_assert,
+	.deassert	= ccu_reset_deassert,
+};
diff --git a/drivers/clk/sunxi-ng/ccu_reset.h b/drivers/clk/sunxi-ng/ccu_reset.h
new file mode 100644
index 000000000000..36a4679210bd
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu_reset.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (c) 2016 Maxime Ripard. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_RESET_H_
+#define _CCU_RESET_H_
+
+#include <linux/reset-controller.h>
+
+struct ccu_reset_map {
+	u16	reg;
+	u32	bit;
+};
+
+
+struct ccu_reset {
+	void __iomem			*base;
+	struct ccu_reset_map		*reset_map;
+	spinlock_t			*lock;
+
+	struct reset_controller_dev	rcdev;
+};
+
+static inline struct ccu_reset *rcdev_to_ccu_reset(struct reset_controller_dev *rcdev)
+{
+	return container_of(rcdev, struct ccu_reset, rcdev);
+}
+
+extern const struct reset_control_ops ccu_reset_ops;
+
+#endif /* _CCU_RESET_H_ */
diff --git a/drivers/clk/sunxi/clk-factors.c b/drivers/clk/sunxi/clk-factors.c
index ddefe9668863..dfe5e3e32d28 100644
--- a/drivers/clk/sunxi/clk-factors.c
+++ b/drivers/clk/sunxi/clk-factors.c
@@ -12,7 +12,6 @@
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/io.h>
-#include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/slab.h>
 #include <linux/string.h>
diff --git a/drivers/clk/sunxi/clk-sun6i-apb0-gates.c b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
index 68021fa5ecd9..09cdb9874636 100644
--- a/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
+++ b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
@@ -33,7 +33,6 @@ static const struct of_device_id sun6i_a31_apb0_gates_clk_dt_ids[] = {
 	{ .compatible = "allwinner,sun8i-a23-apb0-gates-clk", .data = &sun8i_a23_apb0_gates },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, sun6i_a31_apb0_gates_clk_dt_ids);
 
 static int sun6i_a31_apb0_gates_clk_probe(struct platform_device *pdev)
 {
@@ -102,8 +101,4 @@ static struct platform_driver sun6i_a31_apb0_gates_clk_driver = {
 	},
 	.probe = sun6i_a31_apb0_gates_clk_probe,
 };
-module_platform_driver(sun6i_a31_apb0_gates_clk_driver);
-
-MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
-MODULE_DESCRIPTION("Allwinner A31 APB0 gate clocks driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(sun6i_a31_apb0_gates_clk_driver);
diff --git a/drivers/clk/sunxi/clk-sun6i-apb0.c b/drivers/clk/sunxi/clk-sun6i-apb0.c
index e703e1895b76..b9c8d359288c 100644
--- a/drivers/clk/sunxi/clk-sun6i-apb0.c
+++ b/drivers/clk/sunxi/clk-sun6i-apb0.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 
@@ -61,7 +61,6 @@ static const struct of_device_id sun6i_a31_apb0_clk_dt_ids[] = {
 	{ .compatible = "allwinner,sun6i-a31-apb0-clk" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, sun6i_a31_apb0_clk_dt_ids);
 
 static struct platform_driver sun6i_a31_apb0_clk_driver = {
 	.driver = {
@@ -70,8 +69,4 @@ static struct platform_driver sun6i_a31_apb0_clk_driver = {
 	},
 	.probe = sun6i_a31_apb0_clk_probe,
 };
-module_platform_driver(sun6i_a31_apb0_clk_driver);
-
-MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
-MODULE_DESCRIPTION("Allwinner A31 APB0 clock Driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(sun6i_a31_apb0_clk_driver);
diff --git a/drivers/clk/sunxi/clk-sun6i-ar100.c b/drivers/clk/sunxi/clk-sun6i-ar100.c
index 84a187e55360..64ca3e9e38e6 100644
--- a/drivers/clk/sunxi/clk-sun6i-ar100.c
+++ b/drivers/clk/sunxi/clk-sun6i-ar100.c
@@ -10,7 +10,7 @@
 
 #include <linux/bitops.h>
 #include <linux/clk-provider.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/spinlock.h>
@@ -91,32 +91,17 @@ static int sun6i_a31_ar100_clk_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int sun6i_a31_ar100_clk_remove(struct platform_device *pdev)
-{
-	struct device_node *np = pdev->dev.of_node;
-	struct clk *clk = platform_get_drvdata(pdev);
-
-	sunxi_factors_unregister(np, clk);
-
-	return 0;
-}
-
 static const struct of_device_id sun6i_a31_ar100_clk_dt_ids[] = {
 	{ .compatible = "allwinner,sun6i-a31-ar100-clk" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, sun6i_a31_ar100_clk_dt_ids);
 
 static struct platform_driver sun6i_a31_ar100_clk_driver = {
 	.driver = {
 		.name = "sun6i-a31-ar100-clk",
 		.of_match_table = sun6i_a31_ar100_clk_dt_ids,
+		.suppress_bind_attrs = true,
 	},
 	.probe = sun6i_a31_ar100_clk_probe,
-	.remove = sun6i_a31_ar100_clk_remove,
 };
-module_platform_driver(sun6i_a31_ar100_clk_driver);
-
-MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
-MODULE_DESCRIPTION("Allwinner A31 AR100 clock Driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(sun6i_a31_ar100_clk_driver);
diff --git a/drivers/clk/sunxi/clk-sun8i-apb0.c b/drivers/clk/sunxi/clk-sun8i-apb0.c
index 2ea61debffc1..a5666e1d0ce7 100644
--- a/drivers/clk/sunxi/clk-sun8i-apb0.c
+++ b/drivers/clk/sunxi/clk-sun8i-apb0.c
@@ -15,7 +15,7 @@
  */
 
 #include <linux/clk-provider.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
@@ -108,7 +108,6 @@ static const struct of_device_id sun8i_a23_apb0_clk_dt_ids[] = {
 	{ .compatible = "allwinner,sun8i-a23-apb0-clk" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, sun8i_a23_apb0_clk_dt_ids);
 
 static struct platform_driver sun8i_a23_apb0_clk_driver = {
 	.driver = {
@@ -117,8 +116,4 @@ static struct platform_driver sun8i_a23_apb0_clk_driver = {
 	},
 	.probe = sun8i_a23_apb0_clk_probe,
 };
-module_platform_driver(sun8i_a23_apb0_clk_driver);
-
-MODULE_AUTHOR("Chen-Yu Tsai <wens@csie.org>");
-MODULE_DESCRIPTION("Allwinner A23 APB0 clock Driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(sun8i_a23_apb0_clk_driver);
diff --git a/drivers/clk/sunxi/clk-sun9i-mmc.c b/drivers/clk/sunxi/clk-sun9i-mmc.c
index 716737388b7d..6041bdba2e97 100644
--- a/drivers/clk/sunxi/clk-sun9i-mmc.c
+++ b/drivers/clk/sunxi/clk-sun9i-mmc.c
@@ -16,7 +16,7 @@
 
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/reset.h>
@@ -183,39 +183,17 @@ err_clk_register:
 	return ret;
 }
 
-static int sun9i_a80_mmc_config_clk_remove(struct platform_device *pdev)
-{
-	struct device_node *np = pdev->dev.of_node;
-	struct sun9i_mmc_clk_data *data = platform_get_drvdata(pdev);
-	struct clk_onecell_data *clk_data = &data->clk_data;
-	int i;
-
-	reset_controller_unregister(&data->rcdev);
-	of_clk_del_provider(np);
-	for (i = 0; i < clk_data->clk_num; i++)
-		clk_unregister(clk_data->clks[i]);
-
-	reset_control_assert(data->reset);
-
-	return 0;
-}
-
 static const struct of_device_id sun9i_a80_mmc_config_clk_dt_ids[] = {
 	{ .compatible = "allwinner,sun9i-a80-mmc-config-clk" },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, sun9i_a80_mmc_config_clk_dt_ids);
 
 static struct platform_driver sun9i_a80_mmc_config_clk_driver = {
 	.driver = {
 		.name = "sun9i-a80-mmc-config-clk",
+		.suppress_bind_attrs = true,
 		.of_match_table = sun9i_a80_mmc_config_clk_dt_ids,
 	},
 	.probe = sun9i_a80_mmc_config_clk_probe,
-	.remove = sun9i_a80_mmc_config_clk_remove,
 };
-module_platform_driver(sun9i_a80_mmc_config_clk_driver);
-
-MODULE_AUTHOR("Chen-Yu Tsai <wens@csie.org>");
-MODULE_DESCRIPTION("Allwinner A80 MMC clock/reset Driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(sun9i_a80_mmc_config_clk_driver);
diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h
index 36c974916d4f..5738635c5274 100644
--- a/drivers/clk/tegra/clk-id.h
+++ b/drivers/clk/tegra/clk-id.h
@@ -238,7 +238,6 @@ enum clk_id {
 	tegra_clk_sor0,
 	tegra_clk_sor0_lvds,
 	tegra_clk_sor1,
-	tegra_clk_sor1_brick,
 	tegra_clk_sor1_src,
 	tegra_clk_spdif,
 	tegra_clk_spdif_2x,
diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c
index 4e194ecc8d5e..b3855360d6bc 100644
--- a/drivers/clk/tegra/clk-pll.c
+++ b/drivers/clk/tegra/clk-pll.c
@@ -191,6 +191,53 @@
 #define PLLSS_REF_SRC_SEL_SHIFT	25
 #define PLLSS_REF_SRC_SEL_MASK	(3 << PLLSS_REF_SRC_SEL_SHIFT)
 
+#define UTMIP_PLL_CFG1 0x484
+#define UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(x) (((x) & 0xfff) << 0)
+#define UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(x) (((x) & 0x1f) << 27)
+#define UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN BIT(12)
+#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN BIT(14)
+#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP BIT(15)
+#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN BIT(16)
+#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERUP BIT(17)
+
+#define UTMIP_PLL_CFG2 0x488
+#define UTMIP_PLL_CFG2_STABLE_COUNT(x) (((x) & 0xfff) << 6)
+#define UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(x) (((x) & 0x3f) << 18)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN BIT(0)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERUP BIT(1)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN BIT(2)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERUP BIT(3)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN BIT(4)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERUP BIT(5)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERDOWN BIT(24)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERUP BIT(25)
+#define UTMIP_PLL_CFG2_PHY_XTAL_CLOCKEN BIT(30)
+
+#define UTMIPLL_HW_PWRDN_CFG0 0x52c
+#define UTMIPLL_HW_PWRDN_CFG0_IDDQ_SWCTL BIT(0)
+#define UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE BIT(1)
+#define UTMIPLL_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL BIT(2)
+#define UTMIPLL_HW_PWRDN_CFG0_SEQ_IN_SWCTL BIT(4)
+#define UTMIPLL_HW_PWRDN_CFG0_SEQ_RESET_INPUT_VALUE BIT(5)
+#define UTMIPLL_HW_PWRDN_CFG0_USE_LOCKDET BIT(6)
+#define UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE BIT(24)
+#define UTMIPLL_HW_PWRDN_CFG0_SEQ_START_STATE BIT(25)
+
+#define PLLU_HW_PWRDN_CFG0 0x530
+#define PLLU_HW_PWRDN_CFG0_CLK_SWITCH_SWCTL BIT(0)
+#define PLLU_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL BIT(2)
+#define PLLU_HW_PWRDN_CFG0_USE_LOCKDET BIT(6)
+#define PLLU_HW_PWRDN_CFG0_USE_SWITCH_DETECT BIT(7)
+#define PLLU_HW_PWRDN_CFG0_SEQ_ENABLE BIT(24)
+#define PLLU_HW_PWRDN_CFG0_IDDQ_PD_INCLUDE BIT(28)
+
+#define XUSB_PLL_CFG0 0x534
+#define XUSB_PLL_CFG0_UTMIPLL_LOCK_DLY 0x3ff
+#define XUSB_PLL_CFG0_PLLU_LOCK_DLY (0x3ff << 14)
+
+#define PLLU_BASE_CLKENABLE_USB BIT(21)
+#define PLLU_BASE_OVERRIDE BIT(24)
+
 #define pll_readl(offset, p) readl_relaxed(p->clk_base + offset)
 #define pll_readl_base(p) pll_readl(p->params->base_reg, p)
 #define pll_readl_misc(p) pll_readl(p->params->misc_reg, p)
@@ -973,6 +1020,133 @@ const struct clk_ops tegra_clk_plle_ops = {
 	.enable = clk_plle_enable,
 };
 
+/*
+ * Structure defining the fields for USB UTMI clocks Parameters.
+ */
+struct utmi_clk_param {
+	/* Oscillator Frequency in Hz */
+	u32 osc_frequency;
+	/* UTMIP PLL Enable Delay Count  */
+	u8 enable_delay_count;
+	/* UTMIP PLL Stable count */
+	u8 stable_count;
+	/*  UTMIP PLL Active delay count */
+	u8 active_delay_count;
+	/* UTMIP PLL Xtal frequency count */
+	u8 xtal_freq_count;
+};
+
+static const struct utmi_clk_param utmi_parameters[] = {
+	{
+		.osc_frequency = 13000000, .enable_delay_count = 0x02,
+		.stable_count = 0x33, .active_delay_count = 0x05,
+		.xtal_freq_count = 0x7f
+	}, {
+		.osc_frequency = 19200000, .enable_delay_count = 0x03,
+		.stable_count = 0x4b, .active_delay_count = 0x06,
+		.xtal_freq_count = 0xbb
+	}, {
+		.osc_frequency = 12000000, .enable_delay_count = 0x02,
+		.stable_count = 0x2f, .active_delay_count = 0x04,
+		.xtal_freq_count = 0x76
+	}, {
+		.osc_frequency = 26000000, .enable_delay_count = 0x04,
+		.stable_count = 0x66, .active_delay_count = 0x09,
+		.xtal_freq_count = 0xfe
+	}, {
+		.osc_frequency = 16800000, .enable_delay_count = 0x03,
+		.stable_count = 0x41, .active_delay_count = 0x0a,
+		.xtal_freq_count = 0xa4
+	}, {
+		.osc_frequency = 38400000, .enable_delay_count = 0x0,
+		.stable_count = 0x0, .active_delay_count = 0x6,
+		.xtal_freq_count = 0x80
+	},
+};
+
+static int clk_pllu_enable(struct clk_hw *hw)
+{
+	struct tegra_clk_pll *pll = to_clk_pll(hw);
+	struct clk_hw *pll_ref = clk_hw_get_parent(hw);
+	struct clk_hw *osc = clk_hw_get_parent(pll_ref);
+	const struct utmi_clk_param *params = NULL;
+	unsigned long flags = 0, input_rate;
+	unsigned int i;
+	int ret = 0;
+	u32 value;
+
+	if (!osc) {
+		pr_err("%s: failed to get OSC clock\n", __func__);
+		return -EINVAL;
+	}
+
+	input_rate = clk_hw_get_rate(osc);
+
+	if (pll->lock)
+		spin_lock_irqsave(pll->lock, flags);
+
+	_clk_pll_enable(hw);
+
+	ret = clk_pll_wait_for_lock(pll);
+	if (ret < 0)
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(utmi_parameters); i++) {
+		if (input_rate == utmi_parameters[i].osc_frequency) {
+			params = &utmi_parameters[i];
+			break;
+		}
+	}
+
+	if (!params) {
+		pr_err("%s: unexpected input rate %lu Hz\n", __func__,
+		       input_rate);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	value = pll_readl_base(pll);
+	value &= ~PLLU_BASE_OVERRIDE;
+	pll_writel_base(value, pll);
+
+	value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG2);
+	/* Program UTMIP PLL stable and active counts */
+	value &= ~UTMIP_PLL_CFG2_STABLE_COUNT(~0);
+	value |= UTMIP_PLL_CFG2_STABLE_COUNT(params->stable_count);
+	value &= ~UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(~0);
+	value |= UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(params->active_delay_count);
+	/* Remove power downs from UTMIP PLL control bits */
+	value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN;
+	value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN;
+	value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN;
+	writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG2);
+
+	value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG1);
+	/* Program UTMIP PLL delay and oscillator frequency counts */
+	value &= ~UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(~0);
+	value |= UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(params->enable_delay_count);
+	value &= ~UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(~0);
+	value |= UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(params->xtal_freq_count);
+	/* Remove power downs from UTMIP PLL control bits */
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN;
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN;
+	writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG1);
+
+out:
+	if (pll->lock)
+		spin_unlock_irqrestore(pll->lock, flags);
+
+	return ret;
+}
+
+static const struct clk_ops tegra_clk_pllu_ops = {
+	.is_enabled = clk_pll_is_enabled,
+	.enable = clk_pllu_enable,
+	.disable = clk_pll_disable,
+	.recalc_rate = clk_pll_recalc_rate,
+};
+
 static int _pll_fixed_mdiv(struct tegra_clk_pll_params *pll_params,
 			   unsigned long parent_rate)
 {
@@ -1505,6 +1679,112 @@ static void clk_plle_tegra114_disable(struct clk_hw *hw)
 	if (pll->lock)
 		spin_unlock_irqrestore(pll->lock, flags);
 }
+
+static int clk_pllu_tegra114_enable(struct clk_hw *hw)
+{
+	struct tegra_clk_pll *pll = to_clk_pll(hw);
+	const struct utmi_clk_param *params = NULL;
+	struct clk *osc = __clk_lookup("osc");
+	unsigned long flags = 0, input_rate;
+	unsigned int i;
+	int ret = 0;
+	u32 value;
+
+	if (!osc) {
+		pr_err("%s: failed to get OSC clock\n", __func__);
+		return -EINVAL;
+	}
+
+	input_rate = clk_hw_get_rate(__clk_get_hw(osc));
+
+	if (pll->lock)
+		spin_lock_irqsave(pll->lock, flags);
+
+	_clk_pll_enable(hw);
+
+	ret = clk_pll_wait_for_lock(pll);
+	if (ret < 0)
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(utmi_parameters); i++) {
+		if (input_rate == utmi_parameters[i].osc_frequency) {
+			params = &utmi_parameters[i];
+			break;
+		}
+	}
+
+	if (!params) {
+		pr_err("%s: unexpected input rate %lu Hz\n", __func__,
+		       input_rate);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	value = pll_readl_base(pll);
+	value &= ~PLLU_BASE_OVERRIDE;
+	pll_writel_base(value, pll);
+
+	value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG2);
+	/* Program UTMIP PLL stable and active counts */
+	value &= ~UTMIP_PLL_CFG2_STABLE_COUNT(~0);
+	value |= UTMIP_PLL_CFG2_STABLE_COUNT(params->stable_count);
+	value &= ~UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(~0);
+	value |= UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(params->active_delay_count);
+	/* Remove power downs from UTMIP PLL control bits */
+	value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN;
+	value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN;
+	value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN;
+	writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG2);
+
+	value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG1);
+	/* Program UTMIP PLL delay and oscillator frequency counts */
+	value &= ~UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(~0);
+	value |= UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(params->enable_delay_count);
+	value &= ~UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(~0);
+	value |= UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(params->xtal_freq_count);
+	/* Remove power downs from UTMIP PLL control bits */
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN;
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLLU_POWERUP;
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN;
+	writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG1);
+
+	/* Setup HW control of UTMIPLL */
+	value = readl_relaxed(pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+	value |= UTMIPLL_HW_PWRDN_CFG0_USE_LOCKDET;
+	value &= ~UTMIPLL_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL;
+	value |= UTMIPLL_HW_PWRDN_CFG0_SEQ_START_STATE;
+	writel_relaxed(value, pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+
+	value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG1);
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
+	writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG1);
+
+	udelay(1);
+
+	/*
+	 * Setup SW override of UTMIPLL assuming USB2.0 ports are assigned
+	 * to USB2
+	 */
+	value = readl_relaxed(pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+	value |= UTMIPLL_HW_PWRDN_CFG0_IDDQ_SWCTL;
+	value &= ~UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE;
+	writel_relaxed(value, pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+
+	udelay(1);
+
+	/* Enable HW control of UTMIPLL */
+	value = readl_relaxed(pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+	value |= UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE;
+	writel_relaxed(value, pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+
+out:
+	if (pll->lock)
+		spin_unlock_irqrestore(pll->lock, flags);
+
+	return ret;
+}
 #endif
 
 static struct tegra_clk_pll *_tegra_init_pll(void __iomem *clk_base,
@@ -1614,6 +1894,27 @@ struct clk *tegra_clk_register_plle(const char *name, const char *parent_name,
 	return clk;
 }
 
+struct clk *tegra_clk_register_pllu(const char *name, const char *parent_name,
+		void __iomem *clk_base, unsigned long flags,
+		struct tegra_clk_pll_params *pll_params, spinlock_t *lock)
+{
+	struct tegra_clk_pll *pll;
+	struct clk *clk;
+
+	pll_params->flags |= TEGRA_PLLU;
+
+	pll = _tegra_init_pll(clk_base, NULL, pll_params, lock);
+	if (IS_ERR(pll))
+		return ERR_CAST(pll);
+
+	clk = _tegra_clk_register_pll(pll, name, parent_name, flags,
+				      &tegra_clk_pllu_ops);
+	if (IS_ERR(clk))
+		kfree(pll);
+
+	return clk;
+}
+
 #if defined(CONFIG_ARCH_TEGRA_114_SOC) || \
 	defined(CONFIG_ARCH_TEGRA_124_SOC) || \
 	defined(CONFIG_ARCH_TEGRA_132_SOC) || \
@@ -1652,6 +1953,12 @@ static const struct clk_ops tegra_clk_plle_tegra114_ops = {
 	.recalc_rate = clk_pll_recalc_rate,
 };
 
+static const struct clk_ops tegra_clk_pllu_tegra114_ops = {
+	.is_enabled =  clk_pll_is_enabled,
+	.enable = clk_pllu_tegra114_enable,
+	.disable = clk_pll_disable,
+	.recalc_rate = clk_pll_recalc_rate,
+};
 
 struct clk *tegra_clk_register_pllxc(const char *name, const char *parent_name,
 			  void __iomem *clk_base, void __iomem *pmc,
@@ -1919,6 +2226,29 @@ struct clk *tegra_clk_register_plle_tegra114(const char *name,
 
 	return clk;
 }
+
+struct clk *
+tegra_clk_register_pllu_tegra114(const char *name, const char *parent_name,
+				 void __iomem *clk_base, unsigned long flags,
+				 struct tegra_clk_pll_params *pll_params,
+				 spinlock_t *lock)
+{
+	struct tegra_clk_pll *pll;
+	struct clk *clk;
+
+	pll_params->flags |= TEGRA_PLLU;
+
+	pll = _tegra_init_pll(clk_base, NULL, pll_params, lock);
+	if (IS_ERR(pll))
+		return ERR_CAST(pll);
+
+	clk = _tegra_clk_register_pll(pll, name, parent_name, flags,
+				      &tegra_clk_pllu_tegra114_ops);
+	if (IS_ERR(clk))
+		kfree(pll);
+
+	return clk;
+}
 #endif
 
 #if defined(CONFIG_ARCH_TEGRA_124_SOC) || defined(CONFIG_ARCH_TEGRA_132_SOC)
@@ -2187,6 +2517,152 @@ static int clk_plle_tegra210_is_enabled(struct clk_hw *hw)
 	return val & PLLE_BASE_ENABLE ? 1 : 0;
 }
 
+static int clk_pllu_tegra210_enable(struct clk_hw *hw)
+{
+	struct tegra_clk_pll *pll = to_clk_pll(hw);
+	struct clk_hw *pll_ref = clk_hw_get_parent(hw);
+	struct clk_hw *osc = clk_hw_get_parent(pll_ref);
+	const struct utmi_clk_param *params = NULL;
+	unsigned long flags = 0, input_rate;
+	unsigned int i;
+	int ret = 0;
+	u32 value;
+
+	if (!osc) {
+		pr_err("%s: failed to get OSC clock\n", __func__);
+		return -EINVAL;
+	}
+
+	input_rate = clk_hw_get_rate(osc);
+
+	if (pll->lock)
+		spin_lock_irqsave(pll->lock, flags);
+
+	_clk_pll_enable(hw);
+
+	ret = clk_pll_wait_for_lock(pll);
+	if (ret < 0)
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(utmi_parameters); i++) {
+		if (input_rate == utmi_parameters[i].osc_frequency) {
+			params = &utmi_parameters[i];
+			break;
+		}
+	}
+
+	if (!params) {
+		pr_err("%s: unexpected input rate %lu Hz\n", __func__,
+		       input_rate);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	value = pll_readl_base(pll);
+	value &= ~PLLU_BASE_OVERRIDE;
+	pll_writel_base(value, pll);
+
+	/* Put PLLU under HW control */
+	value = readl_relaxed(pll->clk_base + PLLU_HW_PWRDN_CFG0);
+	value |= PLLU_HW_PWRDN_CFG0_IDDQ_PD_INCLUDE |
+	         PLLU_HW_PWRDN_CFG0_USE_SWITCH_DETECT |
+	         PLLU_HW_PWRDN_CFG0_USE_LOCKDET;
+	value &= ~(PLLU_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL |
+		   PLLU_HW_PWRDN_CFG0_CLK_SWITCH_SWCTL);
+	writel_relaxed(value, pll->clk_base + PLLU_HW_PWRDN_CFG0);
+
+	value = readl_relaxed(pll->clk_base + XUSB_PLL_CFG0);
+	value &= ~XUSB_PLL_CFG0_PLLU_LOCK_DLY;
+	writel_relaxed(value, pll->clk_base + XUSB_PLL_CFG0);
+
+	udelay(1);
+
+	value = readl_relaxed(pll->clk_base + PLLU_HW_PWRDN_CFG0);
+	value |= PLLU_HW_PWRDN_CFG0_SEQ_ENABLE;
+	writel_relaxed(value, pll->clk_base + PLLU_HW_PWRDN_CFG0);
+
+	udelay(1);
+
+	/* Disable PLLU clock branch to UTMIPLL since it uses OSC */
+	value = pll_readl_base(pll);
+	value &= ~PLLU_BASE_CLKENABLE_USB;
+	pll_writel_base(value, pll);
+
+	value = readl_relaxed(pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+	if (value & UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE) {
+		pr_debug("UTMIPLL already enabled\n");
+		goto out;
+	}
+
+	value &= ~UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE;
+	writel_relaxed(value, pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+
+	/* Program UTMIP PLL stable and active counts */
+	value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG2);
+	value &= ~UTMIP_PLL_CFG2_STABLE_COUNT(~0);
+	value |= UTMIP_PLL_CFG2_STABLE_COUNT(params->stable_count);
+	value &= ~UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(~0);
+	value |= UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(params->active_delay_count);
+	value |= UTMIP_PLL_CFG2_PHY_XTAL_CLOCKEN;
+	writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG2);
+
+	/* Program UTMIP PLL delay and oscillator frequency counts */
+	value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG1);
+	value &= ~UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(~0);
+	value |= UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(params->enable_delay_count);
+	value &= ~UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(~0);
+	value |= UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(params->xtal_freq_count);
+	writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG1);
+
+	/* Remove power downs from UTMIP PLL control bits */
+	value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG1);
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
+	value |= UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
+	writel(value, pll->clk_base + UTMIP_PLL_CFG1);
+
+	udelay(1);
+
+	/* Enable samplers for SNPS, XUSB_HOST, XUSB_DEV */
+	value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG2);
+	value |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERUP;
+	value |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERUP;
+	value |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERUP;
+	value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN;
+	value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN;
+	value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERDOWN;
+	writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG2);
+
+	/* Setup HW control of UTMIPLL */
+	value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG1);
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
+	value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
+	writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG1);
+
+	value = readl_relaxed(pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+	value |= UTMIPLL_HW_PWRDN_CFG0_USE_LOCKDET;
+	value &= ~UTMIPLL_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL;
+	writel_relaxed(value, pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+
+	udelay(1);
+
+	value = readl_relaxed(pll->clk_base + XUSB_PLL_CFG0);
+	value &= ~XUSB_PLL_CFG0_UTMIPLL_LOCK_DLY;
+	writel_relaxed(value, pll->clk_base + XUSB_PLL_CFG0);
+
+	udelay(1);
+
+	/* Enable HW control of UTMIPLL */
+	value = readl_relaxed(pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+	value |= UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE;
+	writel_relaxed(value, pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
+
+out:
+	if (pll->lock)
+		spin_unlock_irqrestore(pll->lock, flags);
+
+	return ret;
+}
+
 static const struct clk_ops tegra_clk_plle_tegra210_ops = {
 	.is_enabled =  clk_plle_tegra210_is_enabled,
 	.enable = clk_plle_tegra210_enable,
@@ -2194,6 +2670,13 @@ static const struct clk_ops tegra_clk_plle_tegra210_ops = {
 	.recalc_rate = clk_pll_recalc_rate,
 };
 
+static const struct clk_ops tegra_clk_pllu_tegra210_ops = {
+	.is_enabled =  clk_pll_is_enabled,
+	.enable = clk_pllu_tegra210_enable,
+	.disable = clk_pll_disable,
+	.recalc_rate = clk_pllre_recalc_rate,
+};
+
 struct clk *tegra_clk_register_plle_tegra210(const char *name,
 				const char *parent_name,
 				void __iomem *clk_base, unsigned long flags,
@@ -2434,4 +2917,26 @@ struct clk *tegra_clk_register_pllmb(const char *name, const char *parent_name,
 
 	return clk;
 }
+
+struct clk *tegra_clk_register_pllu_tegra210(const char *name,
+		const char *parent_name, void __iomem *clk_base,
+		unsigned long flags, struct tegra_clk_pll_params *pll_params,
+		spinlock_t *lock)
+{
+	struct tegra_clk_pll *pll;
+	struct clk *clk;
+
+	pll_params->flags |= TEGRA_PLLU;
+
+	pll = _tegra_init_pll(clk_base, NULL, pll_params, lock);
+	if (IS_ERR(pll))
+		return ERR_CAST(pll);
+
+	clk = _tegra_clk_register_pll(pll, name, parent_name, flags,
+				      &tegra_clk_pllu_tegra210_ops);
+	if (IS_ERR(clk))
+		kfree(pll);
+
+	return clk;
+}
 #endif
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 29d04c663abf..4ce4e7fb1124 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -594,15 +594,17 @@ static u32 mux_pllp_plld_plld2_clkm_idx[] = {
 	[0] = 0, [1] = 2, [2] = 5, [3] = 6
 };
 
-static const char *mux_plldp_sor1_src[] = {
-	"pll_dp", "clk_sor1_src"
-};
-#define mux_plldp_sor1_src_idx NULL
-
-static const char *mux_clkm_sor1_brick_sor1_src[] = {
-	"clk_m", "sor1_brick", "sor1_src", "sor1_brick"
-};
-#define mux_clkm_sor1_brick_sor1_src_idx NULL
+static const char *mux_sor_safe_sor1_brick_sor1_src[] = {
+	/*
+	 * Bit 0 of the mux selects sor1_brick, irrespective of bit 1, so the
+	 * sor1_brick parent appears twice in the list below. This is merely
+	 * to support clk_get_parent() if firmware happened to set these bits
+	 * to 0b11. While not an invalid setting, code should always set the
+	 * bits to 0b01 to select sor1_brick.
+	 */
+	"sor_safe", "sor1_brick", "sor1_src", "sor1_brick"
+};
+#define mux_sor_safe_sor1_brick_sor1_src_idx NULL
 
 static const char *mux_pllp_pllre_clkm[] = {
 	"pll_p", "pll_re_out1", "clk_m"
@@ -778,8 +780,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 	MUX8("nvjpg", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVJPG, 195, 0, tegra_clk_nvjpg),
 	MUX8("ape", mux_plla_pllc4_out0_pllc_pllc4_out1_pllp_pllc4_out2_clkm, CLK_SOURCE_APE, 198, TEGRA_PERIPH_ON_APB, tegra_clk_ape),
 	MUX8_NOGATE_LOCK("sor1_src", mux_pllp_plld_plld2_clkm, CLK_SOURCE_SOR1, tegra_clk_sor1_src, &sor1_lock),
-	NODIV("sor1_brick", mux_plldp_sor1_src, CLK_SOURCE_SOR1, 14, MASK(1), 183, 0, tegra_clk_sor1_brick, &sor1_lock),
-	NODIV("sor1", mux_clkm_sor1_brick_sor1_src, CLK_SOURCE_SOR1, 15, MASK(1), 183, 0, tegra_clk_sor1, &sor1_lock),
+	NODIV("sor1", mux_sor_safe_sor1_brick_sor1_src, CLK_SOURCE_SOR1, 14, MASK(2), 183, 0, tegra_clk_sor1, &sor1_lock),
 	MUX8("sdmmc_legacy", mux_pllp_out3_clkm_pllp_pllc4, CLK_SOURCE_SDMMC_LEGACY, 193, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_sdmmc_legacy),
 	MUX8("qspi", mux_pllp_pllc_pllc_out1_pllc4_out2_pllc4_out1_clkm_pllc4_out0, CLK_SOURCE_QSPI, 211, TEGRA_PERIPH_ON_APB, tegra_clk_qspi),
 	I2C("vii2c", mux_pllp_pllc_clkm, CLK_SOURCE_VI_I2C, 208, tegra_clk_vi_i2c),
@@ -791,7 +792,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 
 static struct tegra_periph_init_data gate_clks[] = {
 	GATE("rtc", "clk_32k", 4, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_rtc, 0),
-	GATE("timer", "clk_m", 5, 0, tegra_clk_timer, 0),
+	GATE("timer", "clk_m", 5, 0, tegra_clk_timer, CLK_IS_CRITICAL),
 	GATE("isp", "clk_m", 23, 0, tegra_clk_isp, 0),
 	GATE("vcp", "clk_m", 29, 0, tegra_clk_vcp, 0),
 	GATE("apbdma", "clk_m", 34, 0, tegra_clk_apbdma, 0),
diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c
index b78054fac0a8..64da7b79a6e4 100644
--- a/drivers/clk/tegra/clk-tegra114.c
+++ b/drivers/clk/tegra/clk-tegra114.c
@@ -113,32 +113,6 @@
 
 #define CCLKG_BURST_POLICY 0x368
 
-#define UTMIP_PLL_CFG2 0x488
-#define UTMIP_PLL_CFG2_STABLE_COUNT(x) (((x) & 0xffff) << 6)
-#define UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(x) (((x) & 0x3f) << 18)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN BIT(0)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN BIT(2)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN BIT(4)
-
-#define UTMIP_PLL_CFG1 0x484
-#define UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(x) (((x) & 0x1f) << 6)
-#define UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(x) (((x) & 0xfff) << 0)
-#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERUP BIT(17)
-#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN BIT(16)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP BIT(15)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN BIT(14)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN BIT(12)
-
-#define UTMIPLL_HW_PWRDN_CFG0			0x52c
-#define UTMIPLL_HW_PWRDN_CFG0_SEQ_START_STATE	BIT(25)
-#define UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE	BIT(24)
-#define UTMIPLL_HW_PWRDN_CFG0_USE_LOCKDET	BIT(6)
-#define UTMIPLL_HW_PWRDN_CFG0_SEQ_RESET_INPUT_VALUE	BIT(5)
-#define UTMIPLL_HW_PWRDN_CFG0_SEQ_IN_SWCTL	BIT(4)
-#define UTMIPLL_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL	BIT(2)
-#define UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE	BIT(1)
-#define UTMIPLL_HW_PWRDN_CFG0_IDDQ_SWCTL	BIT(0)
-
 #define CLK_SOURCE_CSITE 0x1d4
 #define CLK_SOURCE_EMC 0x19c
 
@@ -649,43 +623,6 @@ static unsigned long tegra114_input_freq[] = {
 
 #define MASK(x) (BIT(x) - 1)
 
-struct utmi_clk_param {
-	/* Oscillator Frequency in KHz */
-	u32 osc_frequency;
-	/* UTMIP PLL Enable Delay Count  */
-	u8 enable_delay_count;
-	/* UTMIP PLL Stable count */
-	u8 stable_count;
-	/*  UTMIP PLL Active delay count */
-	u8 active_delay_count;
-	/* UTMIP PLL Xtal frequency count */
-	u8 xtal_freq_count;
-};
-
-static const struct utmi_clk_param utmi_parameters[] = {
-	{
-		.osc_frequency = 13000000, .enable_delay_count = 0x02,
-		.stable_count = 0x33, .active_delay_count = 0x05,
-		.xtal_freq_count = 0x7f
-	}, {
-		.osc_frequency = 19200000, .enable_delay_count = 0x03,
-		.stable_count = 0x4b, .active_delay_count = 0x06,
-		.xtal_freq_count = 0xbb
-	}, {
-		.osc_frequency = 12000000, .enable_delay_count = 0x02,
-		.stable_count = 0x2f, .active_delay_count = 0x04,
-		.xtal_freq_count = 0x76
-	}, {
-		.osc_frequency = 26000000, .enable_delay_count = 0x04,
-		.stable_count = 0x66, .active_delay_count = 0x09,
-		.xtal_freq_count = 0xfe
-	}, {
-		.osc_frequency = 16800000, .enable_delay_count = 0x03,
-		.stable_count = 0x41, .active_delay_count = 0x0a,
-		.xtal_freq_count = 0xa4
-	},
-};
-
 /* peripheral mux definitions */
 
 static const char *mux_plld_out0_plld2_out0[] = {
@@ -986,92 +923,9 @@ static void __init tegra114_fixed_clk_init(void __iomem *clk_base)
 
 }
 
-static __init void tegra114_utmi_param_configure(void __iomem *clk_base)
-{
-	unsigned int i;
-	u32 reg;
-
-	for (i = 0; i < ARRAY_SIZE(utmi_parameters); i++) {
-		if (osc_freq == utmi_parameters[i].osc_frequency)
-			break;
-	}
-
-	if (i >= ARRAY_SIZE(utmi_parameters)) {
-		pr_err("%s: Unexpected oscillator freq %lu\n", __func__,
-		       osc_freq);
-		return;
-	}
-
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG2);
-
-	/* Program UTMIP PLL stable and active counts */
-	/* [FIXME] arclk_rst.h says WRONG! This should be 1ms -> 0x50 Check! */
-	reg &= ~UTMIP_PLL_CFG2_STABLE_COUNT(~0);
-	reg |= UTMIP_PLL_CFG2_STABLE_COUNT(utmi_parameters[i].stable_count);
-
-	reg &= ~UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(~0);
-
-	reg |= UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(utmi_parameters[i].
-					    active_delay_count);
-
-	/* Remove power downs from UTMIP PLL control bits */
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN;
-
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG2);
-
-	/* Program UTMIP PLL delay and oscillator frequency counts */
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
-	reg &= ~UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(~0);
-
-	reg |= UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(utmi_parameters[i].
-					    enable_delay_count);
-
-	reg &= ~UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(~0);
-	reg |= UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(utmi_parameters[i].
-					   xtal_freq_count);
-
-	/* Remove power downs from UTMIP PLL control bits */
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLLU_POWERUP;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN;
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
-
-	/* Setup HW control of UTMIPLL */
-	reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
-	reg |= UTMIPLL_HW_PWRDN_CFG0_USE_LOCKDET;
-	reg &= ~UTMIPLL_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL;
-	reg |= UTMIPLL_HW_PWRDN_CFG0_SEQ_START_STATE;
-	writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
-
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
-
-	udelay(1);
-
-	/* Setup SW override of UTMIPLL assuming USB2.0
-	   ports are assigned to USB2 */
-	reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
-	reg |= UTMIPLL_HW_PWRDN_CFG0_IDDQ_SWCTL;
-	reg &= ~UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE;
-	writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
-
-	udelay(1);
-
-	/* Enable HW control UTMIPLL */
-	reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
-	reg |= UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE;
-	writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
-}
-
 static void __init tegra114_pll_init(void __iomem *clk_base,
 				     void __iomem *pmc)
 {
-	u32 val;
 	struct clk *clk;
 
 	/* PLLC */
@@ -1118,16 +972,10 @@ static void __init tegra114_pll_init(void __iomem *clk_base,
 					CLK_SET_RATE_PARENT, 1, 1);
 
 	/* PLLU */
-	val = readl(clk_base + pll_u_params.base_reg);
-	val &= ~BIT(24); /* disable PLLU_OVERRIDE */
-	writel(val, clk_base + pll_u_params.base_reg);
-
-	clk = tegra_clk_register_pll("pll_u", "pll_ref", clk_base, pmc, 0,
-			    &pll_u_params, &pll_u_lock);
+	clk = tegra_clk_register_pllu_tegra114("pll_u", "pll_ref", clk_base, 0,
+					       &pll_u_params, &pll_u_lock);
 	clks[TEGRA114_CLK_PLL_U] = clk;
 
-	tegra114_utmi_param_configure(clk_base);
-
 	/* PLLU_480M */
 	clk = clk_register_gate(NULL, "pll_u_480M", "pll_u",
 				CLK_SET_RATE_PARENT, clk_base + PLLU_BASE,
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index f4fbbf16a056..a112d3d2bff1 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -99,32 +99,6 @@
 
 #define CCLKG_BURST_POLICY 0x368
 
-#define UTMIP_PLL_CFG2 0x488
-#define UTMIP_PLL_CFG2_STABLE_COUNT(x) (((x) & 0xffff) << 6)
-#define UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(x) (((x) & 0x3f) << 18)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN BIT(0)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN BIT(2)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN BIT(4)
-
-#define UTMIP_PLL_CFG1 0x484
-#define UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(x) (((x) & 0x1f) << 6)
-#define UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(x) (((x) & 0xfff) << 0)
-#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERUP BIT(17)
-#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN BIT(16)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP BIT(15)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN BIT(14)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN BIT(12)
-
-#define UTMIPLL_HW_PWRDN_CFG0			0x52c
-#define UTMIPLL_HW_PWRDN_CFG0_SEQ_START_STATE	BIT(25)
-#define UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE	BIT(24)
-#define UTMIPLL_HW_PWRDN_CFG0_USE_LOCKDET	BIT(6)
-#define UTMIPLL_HW_PWRDN_CFG0_SEQ_RESET_INPUT_VALUE	BIT(5)
-#define UTMIPLL_HW_PWRDN_CFG0_SEQ_IN_SWCTL	BIT(4)
-#define UTMIPLL_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL	BIT(2)
-#define UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE	BIT(1)
-#define UTMIPLL_HW_PWRDN_CFG0_IDDQ_SWCTL	BIT(0)
-
 /* Tegra CPU clock and reset control regs */
 #define CLK_RST_CONTROLLER_CPU_CMPLX_STATUS	0x470
 
@@ -764,43 +738,6 @@ static struct tegra_clk_pll_params pll_u_params = {
 		 TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
 };
 
-struct utmi_clk_param {
-	/* Oscillator Frequency in KHz */
-	u32 osc_frequency;
-	/* UTMIP PLL Enable Delay Count  */
-	u8 enable_delay_count;
-	/* UTMIP PLL Stable count */
-	u8 stable_count;
-	/*  UTMIP PLL Active delay count */
-	u8 active_delay_count;
-	/* UTMIP PLL Xtal frequency count */
-	u8 xtal_freq_count;
-};
-
-static const struct utmi_clk_param utmi_parameters[] = {
-	{
-		.osc_frequency = 13000000, .enable_delay_count = 0x02,
-		.stable_count = 0x33, .active_delay_count = 0x05,
-		.xtal_freq_count = 0x7f
-	}, {
-		.osc_frequency = 19200000, .enable_delay_count = 0x03,
-		.stable_count = 0x4b, .active_delay_count = 0x06,
-		.xtal_freq_count = 0xbb
-	}, {
-		.osc_frequency = 12000000, .enable_delay_count = 0x02,
-		.stable_count = 0x2f, .active_delay_count = 0x04,
-		.xtal_freq_count = 0x76
-	}, {
-		.osc_frequency = 26000000, .enable_delay_count = 0x04,
-		.stable_count = 0x66, .active_delay_count = 0x09,
-		.xtal_freq_count = 0xfe
-	}, {
-		.osc_frequency = 16800000, .enable_delay_count = 0x03,
-		.stable_count = 0x41, .active_delay_count = 0x0a,
-		.xtal_freq_count = 0xa4
-	},
-};
-
 static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_ispb] = { .dt_id = TEGRA124_CLK_ISPB, .present = true },
 	[tegra_clk_rtc] = { .dt_id = TEGRA124_CLK_RTC, .present = true },
@@ -1063,88 +1000,6 @@ static struct tegra_devclk devclks[] __initdata = {
 
 static struct clk **clks;
 
-static void tegra124_utmi_param_configure(void __iomem *clk_base)
-{
-	unsigned int i;
-	u32 reg;
-
-	for (i = 0; i < ARRAY_SIZE(utmi_parameters); i++) {
-		if (osc_freq == utmi_parameters[i].osc_frequency)
-			break;
-	}
-
-	if (i >= ARRAY_SIZE(utmi_parameters)) {
-		pr_err("%s: Unexpected oscillator freq %lu\n", __func__,
-		       osc_freq);
-		return;
-	}
-
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG2);
-
-	/* Program UTMIP PLL stable and active counts */
-	/* [FIXME] arclk_rst.h says WRONG! This should be 1ms -> 0x50 Check! */
-	reg &= ~UTMIP_PLL_CFG2_STABLE_COUNT(~0);
-	reg |= UTMIP_PLL_CFG2_STABLE_COUNT(utmi_parameters[i].stable_count);
-
-	reg &= ~UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(~0);
-
-	reg |= UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(utmi_parameters[i].
-					    active_delay_count);
-
-	/* Remove power downs from UTMIP PLL control bits */
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN;
-
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG2);
-
-	/* Program UTMIP PLL delay and oscillator frequency counts */
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
-	reg &= ~UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(~0);
-
-	reg |= UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(utmi_parameters[i].
-					    enable_delay_count);
-
-	reg &= ~UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(~0);
-	reg |= UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(utmi_parameters[i].
-					   xtal_freq_count);
-
-	/* Remove power downs from UTMIP PLL control bits */
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLLU_POWERUP;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN;
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
-
-	/* Setup HW control of UTMIPLL */
-	reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
-	reg |= UTMIPLL_HW_PWRDN_CFG0_USE_LOCKDET;
-	reg &= ~UTMIPLL_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL;
-	reg |= UTMIPLL_HW_PWRDN_CFG0_SEQ_START_STATE;
-	writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
-
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
-
-	udelay(1);
-
-	/* Setup SW override of UTMIPLL assuming USB2.0
-	   ports are assigned to USB2 */
-	reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
-	reg |= UTMIPLL_HW_PWRDN_CFG0_IDDQ_SWCTL;
-	reg &= ~UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE;
-	writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
-
-	udelay(1);
-
-	/* Enable HW control UTMIPLL */
-	reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
-	reg |= UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE;
-	writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
-}
-
 static __init void tegra124_periph_clk_init(void __iomem *clk_base,
 					    void __iomem *pmc_base)
 {
@@ -1195,7 +1050,6 @@ static __init void tegra124_periph_clk_init(void __iomem *clk_base,
 static void __init tegra124_pll_init(void __iomem *clk_base,
 				     void __iomem *pmc)
 {
-	u32 val;
 	struct clk *clk;
 
 	/* PLLC */
@@ -1256,17 +1110,11 @@ static void __init tegra124_pll_init(void __iomem *clk_base,
 	clks[TEGRA124_CLK_PLL_M_UD] = clk;
 
 	/* PLLU */
-	val = readl(clk_base + pll_u_params.base_reg);
-	val &= ~BIT(24); /* disable PLLU_OVERRIDE */
-	writel(val, clk_base + pll_u_params.base_reg);
-
-	clk = tegra_clk_register_pll("pll_u", "pll_ref", clk_base, pmc, 0,
-			    &pll_u_params, &pll_u_lock);
+	clk = tegra_clk_register_pllu_tegra114("pll_u", "pll_ref", clk_base, 0,
+					       &pll_u_params, &pll_u_lock);
 	clk_register_clkdev(clk, "pll_u", NULL);
 	clks[TEGRA124_CLK_PLL_U] = clk;
 
-	tegra124_utmi_param_configure(clk_base);
-
 	/* PLLU_480M */
 	clk = clk_register_gate(NULL, "pll_u_480M", "pll_u",
 				CLK_SET_RATE_PARENT, clk_base + PLLU_BASE,
diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c
index 456cf586d2c2..2896d2e783ce 100644
--- a/drivers/clk/tegra/clk-tegra210.c
+++ b/drivers/clk/tegra/clk-tegra210.c
@@ -155,27 +155,6 @@
 #define PMC_PLLM_WB0_OVERRIDE 0x1dc
 #define PMC_PLLM_WB0_OVERRIDE_2 0x2b0
 
-#define UTMIP_PLL_CFG2 0x488
-#define UTMIP_PLL_CFG2_STABLE_COUNT(x) (((x) & 0xfff) << 6)
-#define UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(x) (((x) & 0x3f) << 18)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN BIT(0)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERUP BIT(1)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN BIT(2)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERUP BIT(3)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN BIT(4)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERUP BIT(5)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERDOWN BIT(24)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERUP BIT(25)
-
-#define UTMIP_PLL_CFG1 0x484
-#define UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(x) (((x) & 0x1f) << 27)
-#define UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(x) (((x) & 0xfff) << 0)
-#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERUP BIT(17)
-#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN BIT(16)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP BIT(15)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN BIT(14)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN BIT(12)
-
 #define SATA_PLL_CFG0				0x490
 #define SATA_PLL_CFG0_PADPLL_RESET_SWCTL	BIT(0)
 #define SATA_PLL_CFG0_PADPLL_USE_LOCKDET	BIT(2)
@@ -1366,9 +1345,9 @@ static u32 pll_expo_p_to_pdiv(u32 p, u32 *pdiv)
 
 static struct tegra_clk_pll_freq_table pll_x_freq_table[] = {
 	/* 1 GHz */
-	{ 12000000, 1000000000, 166, 1, 1, 0 }, /* actual: 996.0 MHz */
-	{ 13000000, 1000000000, 153, 1, 1, 0 }, /* actual: 994.0 MHz */
-	{ 38400000, 1000000000, 156, 3, 1, 0 }, /* actual: 998.4 MHz */
+	{ 12000000, 1000000000, 166, 1, 2, 0 }, /* actual: 996.0 MHz */
+	{ 13000000, 1000000000, 153, 1, 2, 0 }, /* actual: 994.0 MHz */
+	{ 38400000, 1000000000, 156, 3, 2, 0 }, /* actual: 998.4 MHz */
 	{        0,          0,   0, 0, 0, 0 },
 };
 
@@ -1417,9 +1396,9 @@ static struct div_nmp pllc_nmp = {
 };
 
 static struct tegra_clk_pll_freq_table pll_cx_freq_table[] = {
-	{ 12000000, 510000000, 85, 1, 1, 0 },
-	{ 13000000, 510000000, 78, 1, 1, 0 }, /* actual: 507.0 MHz */
-	{ 38400000, 510000000, 79, 3, 1, 0 }, /* actual: 505.6 MHz */
+	{ 12000000, 510000000, 85, 1, 2, 0 },
+	{ 13000000, 510000000, 78, 1, 2, 0 }, /* actual: 507.0 MHz */
+	{ 38400000, 510000000, 79, 3, 2, 0 }, /* actual: 505.6 MHz */
 	{        0,         0,  0, 0, 0, 0 },
 };
 
@@ -1532,9 +1511,9 @@ static struct div_nmp pllss_nmp = {
 };
 
 static struct tegra_clk_pll_freq_table pll_c4_vco_freq_table[] = {
-	{ 12000000, 600000000, 50, 1, 0, 0 },
-	{ 13000000, 600000000, 46, 1, 0, 0 }, /* actual: 598.0 MHz */
-	{ 38400000, 600000000, 62, 4, 0, 0 }, /* actual: 595.2 MHz */
+	{ 12000000, 600000000, 50, 1, 1, 0 },
+	{ 13000000, 600000000, 46, 1, 1, 0 }, /* actual: 598.0 MHz */
+	{ 38400000, 600000000, 62, 4, 1, 0 }, /* actual: 595.2 MHz */
 	{        0,         0,  0, 0, 0, 0 },
 };
 
@@ -1583,19 +1562,19 @@ static struct tegra_clk_pll_params pll_c4_vco_params = {
 };
 
 static struct tegra_clk_pll_freq_table pll_m_freq_table[] = {
-	{ 12000000,  800000000,  66, 1, 0, 0 }, /* actual: 792.0 MHz */
-	{ 13000000,  800000000,  61, 1, 0, 0 }, /* actual: 793.0 MHz */
-	{ 38400000,  297600000,  93, 4, 2, 0 },
-	{ 38400000,  400000000, 125, 4, 2, 0 },
-	{ 38400000,  532800000, 111, 4, 1, 0 },
-	{ 38400000,  665600000, 104, 3, 1, 0 },
-	{ 38400000,  800000000, 125, 3, 1, 0 },
-	{ 38400000,  931200000,  97, 4, 0, 0 },
-	{ 38400000, 1065600000, 111, 4, 0, 0 },
-	{ 38400000, 1200000000, 125, 4, 0, 0 },
-	{ 38400000, 1331200000, 104, 3, 0, 0 },
-	{ 38400000, 1459200000,  76, 2, 0, 0 },
-	{ 38400000, 1600000000, 125, 3, 0, 0 },
+	{ 12000000,  800000000,  66, 1, 1, 0 }, /* actual: 792.0 MHz */
+	{ 13000000,  800000000,  61, 1, 1, 0 }, /* actual: 793.0 MHz */
+	{ 38400000,  297600000,  93, 4, 3, 0 },
+	{ 38400000,  400000000, 125, 4, 3, 0 },
+	{ 38400000,  532800000, 111, 4, 2, 0 },
+	{ 38400000,  665600000, 104, 3, 2, 0 },
+	{ 38400000,  800000000, 125, 3, 2, 0 },
+	{ 38400000,  931200000,  97, 4, 1, 0 },
+	{ 38400000, 1065600000, 111, 4, 1, 0 },
+	{ 38400000, 1200000000, 125, 4, 1, 0 },
+	{ 38400000, 1331200000, 104, 3, 1, 0 },
+	{ 38400000, 1459200000,  76, 2, 1, 0 },
+	{ 38400000, 1600000000, 125, 3, 1, 0 },
 	{        0,          0,   0, 0, 0, 0 },
 };
 
@@ -1705,9 +1684,9 @@ static struct tegra_clk_pll_params pll_e_params = {
 };
 
 static struct tegra_clk_pll_freq_table pll_re_vco_freq_table[] = {
-	{ 12000000, 672000000, 56, 1, 0, 0 },
-	{ 13000000, 672000000, 51, 1, 0, 0 }, /* actual: 663.0 MHz */
-	{ 38400000, 672000000, 70, 4, 0, 0 },
+	{ 12000000, 672000000, 56, 1, 1, 0 },
+	{ 13000000, 672000000, 51, 1, 1, 0 }, /* actual: 663.0 MHz */
+	{ 38400000, 672000000, 70, 4, 1, 0 },
 	{        0,         0,  0, 0, 0, 0 },
 };
 
@@ -1754,8 +1733,8 @@ static struct div_nmp pllp_nmp = {
 };
 
 static struct tegra_clk_pll_freq_table pll_p_freq_table[] = {
-	{ 12000000, 408000000, 34, 1, 0, 0 },
-	{ 38400000, 408000000, 85, 8, 0, 0 }, /* cf = 4.8MHz, allowed exception */
+	{ 12000000, 408000000, 34, 1, 1, 0 },
+	{ 38400000, 408000000, 85, 8, 1, 0 }, /* cf = 4.8MHz, allowed exception */
 	{        0,         0,  0, 0, 0, 0 },
 };
 
@@ -1820,14 +1799,14 @@ static struct div_nmp plla_nmp = {
 };
 
 static struct tegra_clk_pll_freq_table pll_a_freq_table[] = {
-	{ 12000000, 282240000, 47, 1, 1, 1, 0xf148 }, /* actual: 282240234 */
-	{ 12000000, 368640000, 61, 1, 1, 1, 0xfe15 }, /* actual: 368640381 */
-	{ 12000000, 240000000, 60, 1, 2, 1,      0 },
-	{ 13000000, 282240000, 43, 1, 1, 1, 0xfd7d }, /* actual: 282239807 */
-	{ 13000000, 368640000, 56, 1, 1, 1, 0x06d8 }, /* actual: 368640137 */
-	{ 13000000, 240000000, 55, 1, 2, 1,      0 }, /* actual: 238.3 MHz */
-	{ 38400000, 282240000, 44, 3, 1, 1, 0xf333 }, /* actual: 282239844 */
-	{ 38400000, 368640000, 57, 3, 1, 1, 0x0333 }, /* actual: 368639844 */
+	{ 12000000, 282240000, 47, 1, 2, 1, 0xf148 }, /* actual: 282240234 */
+	{ 12000000, 368640000, 61, 1, 2, 1, 0xfe15 }, /* actual: 368640381 */
+	{ 12000000, 240000000, 60, 1, 3, 1,      0 },
+	{ 13000000, 282240000, 43, 1, 2, 1, 0xfd7d }, /* actual: 282239807 */
+	{ 13000000, 368640000, 56, 1, 2, 1, 0x06d8 }, /* actual: 368640137 */
+	{ 13000000, 240000000, 55, 1, 3, 1,      0 }, /* actual: 238.3 MHz */
+	{ 38400000, 282240000, 44, 3, 2, 1, 0xf333 }, /* actual: 282239844 */
+	{ 38400000, 368640000, 57, 3, 2, 1, 0x0333 }, /* actual: 368639844 */
 	{ 38400000, 240000000, 75, 3, 3, 1,      0 },
 	{        0,         0,  0, 0, 0, 0,      0 },
 };
@@ -1873,9 +1852,9 @@ static struct div_nmp plld_nmp = {
 };
 
 static struct tegra_clk_pll_freq_table pll_d_freq_table[] = {
-	{ 12000000, 594000000, 99, 1, 1, 0,      0 },
-	{ 13000000, 594000000, 91, 1, 1, 0, 0xfc4f }, /* actual: 594000183 */
-	{ 38400000, 594000000, 30, 1, 1, 0, 0x0e00 },
+	{ 12000000, 594000000, 99, 1, 2, 0,      0 },
+	{ 13000000, 594000000, 91, 1, 2, 0, 0xfc4f }, /* actual: 594000183 */
+	{ 38400000, 594000000, 30, 1, 2, 0, 0x0e00 },
 	{        0,         0,  0, 0, 0, 0,      0 },
 };
 
@@ -1911,9 +1890,9 @@ static struct tegra_clk_pll_params pll_d_params = {
 };
 
 static struct tegra_clk_pll_freq_table tegra210_pll_d2_freq_table[] = {
-	{ 12000000, 594000000, 99, 1, 1, 0, 0xf000 },
-	{ 13000000, 594000000, 91, 1, 1, 0, 0xfc4f }, /* actual: 594000183 */
-	{ 38400000, 594000000, 30, 1, 1, 0, 0x0e00 },
+	{ 12000000, 594000000, 99, 1, 2, 0, 0xf000 },
+	{ 13000000, 594000000, 91, 1, 2, 0, 0xfc4f }, /* actual: 594000183 */
+	{ 38400000, 594000000, 30, 1, 2, 0, 0x0e00 },
 	{        0,         0,  0, 0, 0, 0,      0 },
 };
 
@@ -1935,8 +1914,9 @@ static struct tegra_clk_pll_params pll_d2_params = {
 	.sdm_din_mask = PLLA_SDM_DIN_MASK,
 	.sdm_ctrl_reg = PLLD2_MISC1,
 	.sdm_ctrl_en_mask = PLLD2_SDM_EN_MASK,
-	.ssc_ctrl_reg = PLLD2_MISC1,
-	.ssc_ctrl_en_mask = PLLD2_SSC_EN_MASK,
+	/* disable spread-spectrum for pll_d2 */
+	.ssc_ctrl_reg = 0,
+	.ssc_ctrl_en_mask = 0,
 	.round_p_to_pdiv = pll_qlin_p_to_pdiv,
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
 	.div_nmp = &pllss_nmp,
@@ -1955,9 +1935,9 @@ static struct tegra_clk_pll_params pll_d2_params = {
 };
 
 static struct tegra_clk_pll_freq_table pll_dp_freq_table[] = {
-	{ 12000000, 270000000, 90, 1, 3, 0, 0xf000 },
-	{ 13000000, 270000000, 83, 1, 3, 0, 0xf000 }, /* actual: 269.8 MHz */
-	{ 38400000, 270000000, 28, 1, 3, 0, 0xf400 },
+	{ 12000000, 270000000, 90, 1, 4, 0, 0xf000 },
+	{ 13000000, 270000000, 83, 1, 4, 0, 0xf000 }, /* actual: 269.8 MHz */
+	{ 38400000, 270000000, 28, 1, 4, 0, 0xf400 },
 	{        0,         0,  0, 0, 0, 0,      0 },
 };
 
@@ -2007,9 +1987,9 @@ static struct div_nmp pllu_nmp = {
 };
 
 static struct tegra_clk_pll_freq_table pll_u_freq_table[] = {
-	{ 12000000, 480000000, 40, 1, 0, 0 },
-	{ 13000000, 480000000, 36, 1, 0, 0 }, /* actual: 468.0 MHz */
-	{ 38400000, 480000000, 25, 2, 0, 0 },
+	{ 12000000, 480000000, 40, 1, 1, 0 },
+	{ 13000000, 480000000, 36, 1, 1, 0 }, /* actual: 468.0 MHz */
+	{ 38400000, 480000000, 25, 2, 1, 0 },
 	{        0,         0,  0, 0, 0, 0 },
 };
 
@@ -2037,47 +2017,6 @@ static struct tegra_clk_pll_params pll_u_vco_params = {
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
 
-struct utmi_clk_param {
-	/* Oscillator Frequency in KHz */
-	u32 osc_frequency;
-	/* UTMIP PLL Enable Delay Count  */
-	u8 enable_delay_count;
-	/* UTMIP PLL Stable count */
-	u16 stable_count;
-	/*  UTMIP PLL Active delay count */
-	u8 active_delay_count;
-	/* UTMIP PLL Xtal frequency count */
-	u16 xtal_freq_count;
-};
-
-static const struct utmi_clk_param utmi_parameters[] = {
-	{
-		.osc_frequency = 38400000, .enable_delay_count = 0x0,
-		.stable_count = 0x0, .active_delay_count = 0x6,
-		.xtal_freq_count = 0x80
-	}, {
-		.osc_frequency = 13000000, .enable_delay_count = 0x02,
-		.stable_count = 0x33, .active_delay_count = 0x05,
-		.xtal_freq_count = 0x7f
-	}, {
-		.osc_frequency = 19200000, .enable_delay_count = 0x03,
-		.stable_count = 0x4b, .active_delay_count = 0x06,
-		.xtal_freq_count = 0xbb
-	}, {
-		.osc_frequency = 12000000, .enable_delay_count = 0x02,
-		.stable_count = 0x2f, .active_delay_count = 0x08,
-		.xtal_freq_count = 0x76
-	}, {
-		.osc_frequency = 26000000, .enable_delay_count = 0x04,
-		.stable_count = 0x66, .active_delay_count = 0x09,
-		.xtal_freq_count = 0xfe
-	}, {
-		.osc_frequency = 16800000, .enable_delay_count = 0x03,
-		.stable_count = 0x41, .active_delay_count = 0x0a,
-		.xtal_freq_count = 0xa4
-	},
-};
-
 static struct tegra_clk tegra210_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_ispb] = { .dt_id = TEGRA210_CLK_ISPB, .present = true },
 	[tegra_clk_rtc] = { .dt_id = TEGRA210_CLK_RTC, .present = true },
@@ -2154,6 +2093,8 @@ static struct tegra_clk tegra210_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_dpaux1] = { .dt_id = TEGRA210_CLK_DPAUX1, .present = true },
 	[tegra_clk_sor0] = { .dt_id = TEGRA210_CLK_SOR0, .present = true },
 	[tegra_clk_sor0_lvds] = { .dt_id = TEGRA210_CLK_SOR0_LVDS, .present = true },
+	[tegra_clk_sor1] = { .dt_id = TEGRA210_CLK_SOR1, .present = true },
+	[tegra_clk_sor1_src] = { .dt_id = TEGRA210_CLK_SOR1_SRC, .present = true },
 	[tegra_clk_gpu] = { .dt_id = TEGRA210_CLK_GPU, .present = true },
 	[tegra_clk_pll_g_ref] = { .dt_id = TEGRA210_CLK_PLL_G_REF, .present = true, },
 	[tegra_clk_uartb_8] = { .dt_id = TEGRA210_CLK_UARTB, .present = true },
@@ -2345,114 +2286,6 @@ static struct tegra_audio_clk_info tegra210_audio_plls[] = {
 
 static struct clk **clks;
 
-static void tegra210_utmi_param_configure(void __iomem *clk_base)
-{
-	u32 reg;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(utmi_parameters); i++) {
-		if (osc_freq == utmi_parameters[i].osc_frequency)
-			break;
-	}
-
-	if (i >= ARRAY_SIZE(utmi_parameters)) {
-		pr_err("%s: Unexpected oscillator freq %lu\n", __func__,
-		       osc_freq);
-		return;
-	}
-
-	reg = readl_relaxed(clk_base + PLLU_HW_PWRDN_CFG0);
-	reg |= PLLU_HW_PWRDN_CFG0_IDDQ_PD_INCLUDE |
-	       PLLU_HW_PWRDN_CFG0_USE_SWITCH_DETECT |
-	       PLLU_HW_PWRDN_CFG0_USE_LOCKDET;
-	reg &= ~(PLLU_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL |
-		  PLLU_HW_PWRDN_CFG0_CLK_SWITCH_SWCTL);
-	writel_relaxed(reg, clk_base + PLLU_HW_PWRDN_CFG0);
-
-	reg = readl_relaxed(clk_base + PLLU_HW_PWRDN_CFG0);
-	reg |= PLLU_HW_PWRDN_CFG0_SEQ_ENABLE;
-	writel_relaxed(reg, clk_base + PLLU_HW_PWRDN_CFG0);
-	udelay(1);
-
-	reg = readl_relaxed(clk_base + PLLU_BASE);
-	reg &= ~PLLU_BASE_CLKENABLE_USB;
-	writel_relaxed(reg, clk_base + PLLU_BASE);
-
-	reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
-	reg &= ~UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE;
-	writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
-
-	udelay(10);
-
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG2);
-
-	/* Program UTMIP PLL stable and active counts */
-	/* [FIXME] arclk_rst.h says WRONG! This should be 1ms -> 0x50 Check! */
-	reg &= ~UTMIP_PLL_CFG2_STABLE_COUNT(~0);
-	reg |= UTMIP_PLL_CFG2_STABLE_COUNT(utmi_parameters[i].stable_count);
-
-	reg &= ~UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(~0);
-
-	reg |= UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(utmi_parameters[i].
-					    active_delay_count);
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG2);
-
-	/* Program UTMIP PLL delay and oscillator frequency counts */
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
-	reg &= ~UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(~0);
-
-	reg |= UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(utmi_parameters[i].
-					    enable_delay_count);
-
-	reg &= ~UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(~0);
-	reg |= UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(utmi_parameters[i].
-					   xtal_freq_count);
-
-	reg |= UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN;
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
-
-	/* Remove power downs from UTMIP PLL control bits */
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
-	reg |= UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
-	udelay(1);
-
-	/* Enable samplers for SNPS, XUSB_HOST, XUSB_DEV */
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG2);
-	reg |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERUP;
-	reg |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERUP;
-	reg |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERUP;
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERDOWN;
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG2);
-
-	/* Setup HW control of UTMIPLL */
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
-
-	reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
-	reg |= UTMIPLL_HW_PWRDN_CFG0_USE_LOCKDET;
-	reg &= ~UTMIPLL_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL;
-	writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
-
-	udelay(1);
-
-	reg = readl_relaxed(clk_base + XUSB_PLL_CFG0);
-	reg &= ~XUSB_PLL_CFG0_UTMIPLL_LOCK_DLY;
-	writel_relaxed(reg, clk_base + XUSB_PLL_CFG0);
-
-	udelay(1);
-
-	/* Enable HW control UTMIPLL */
-	reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
-	reg |= UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE;
-	writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
-}
-
 static __init void tegra210_periph_clk_init(void __iomem *clk_base,
 					    void __iomem *pmc_base)
 {
@@ -2463,18 +2296,18 @@ static __init void tegra210_periph_clk_init(void __iomem *clk_base,
 					1, 2);
 	clks[TEGRA210_CLK_XUSB_SS_DIV2] = clk;
 
-	clk = tegra_clk_register_periph_fixed("dpaux", "pll_p", 0, clk_base,
+	clk = tegra_clk_register_periph_fixed("sor_safe", "pll_p", 0, clk_base,
+					      1, 17, 222);
+	clks[TEGRA210_CLK_SOR_SAFE] = clk;
+
+	clk = tegra_clk_register_periph_fixed("dpaux", "sor_safe", 0, clk_base,
 					      1, 17, 181);
 	clks[TEGRA210_CLK_DPAUX] = clk;
 
-	clk = tegra_clk_register_periph_fixed("dpaux1", "pll_p", 0, clk_base,
+	clk = tegra_clk_register_periph_fixed("dpaux1", "sor_safe", 0, clk_base,
 					      1, 17, 207);
 	clks[TEGRA210_CLK_DPAUX1] = clk;
 
-	clk = tegra_clk_register_periph_fixed("sor_safe", "pll_p", 0, clk_base,
-					      1, 17, 222);
-	clks[TEGRA210_CLK_SOR_SAFE] = clk;
-
 	/* pll_d_dsi_out */
 	clk = clk_register_gate(NULL, "pll_d_dsi_out", "pll_d_out0", 0,
 				clk_base + PLLD_MISC0, 21, 0, &pll_d_lock);
@@ -2520,7 +2353,6 @@ static __init void tegra210_periph_clk_init(void __iomem *clk_base,
 static void __init tegra210_pll_init(void __iomem *clk_base,
 				     void __iomem *pmc)
 {
-	u32 val;
 	struct clk *clk;
 
 	/* PLLC */
@@ -2580,12 +2412,9 @@ static void __init tegra210_pll_init(void __iomem *clk_base,
 	clks[TEGRA210_CLK_PLL_M_UD] = clk;
 
 	/* PLLU_VCO */
-	val = readl(clk_base + pll_u_vco_params.base_reg);
-	val &= ~PLLU_BASE_OVERRIDE; /* disable PLLU_OVERRIDE */
-	writel(val, clk_base + pll_u_vco_params.base_reg);
-
-	clk = tegra_clk_register_pllre("pll_u_vco", "pll_ref", clk_base, pmc,
-			    0, &pll_u_vco_params, &pll_u_lock, pll_ref_freq);
+	clk = tegra_clk_register_pllu_tegra210("pll_u_vco", "pll_ref",
+					       clk_base, 0, &pll_u_vco_params,
+					       &pll_u_lock);
 	clk_register_clkdev(clk, "pll_u_vco", NULL);
 	clks[TEGRA210_CLK_PLL_U] = clk;
 
@@ -2618,8 +2447,6 @@ static void __init tegra210_pll_init(void __iomem *clk_base,
 	clk_register_clkdev(clk, "pll_u_out2", NULL);
 	clks[TEGRA210_CLK_PLL_U_OUT2] = clk;
 
-	tegra210_utmi_param_configure(clk_base);
-
 	/* PLLU_480M */
 	clk = clk_register_gate(NULL, "pll_u_480M", "pll_u_vco",
 				CLK_SET_RATE_PARENT, clk_base + PLLU_BASE,
diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c
index 9396f4930da7..8e2db5ead8da 100644
--- a/drivers/clk/tegra/clk-tegra30.c
+++ b/drivers/clk/tegra/clk-tegra30.c
@@ -118,20 +118,6 @@
 
 #define AUDIO_SYNC_DOUBLER 0x49c
 
-#define UTMIP_PLL_CFG2 0x488
-#define UTMIP_PLL_CFG2_STABLE_COUNT(x) (((x) & 0xffff) << 6)
-#define UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(x) (((x) & 0x3f) << 18)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN BIT(0)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN BIT(2)
-#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN BIT(4)
-
-#define UTMIP_PLL_CFG1 0x484
-#define UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(x) (((x) & 0x1f) << 6)
-#define UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(x) (((x) & 0xfff) << 0)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN BIT(14)
-#define UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN BIT(12)
-#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN BIT(16)
-
 /* Tegra CPU clock and reset control regs */
 #define TEGRA_CLK_RST_CONTROLLER_CLK_CPU_CMPLX		0x4c
 #define TEGRA_CLK_RST_CONTROLLER_RST_CPU_CMPLX_SET	0x340
@@ -207,46 +193,6 @@ static DEFINE_SPINLOCK(emc_lock);
 
 static struct clk **clks;
 
-/*
- * Structure defining the fields for USB UTMI clocks Parameters.
- */
-struct utmi_clk_param {
-	/* Oscillator Frequency in KHz */
-	u32 osc_frequency;
-	/* UTMIP PLL Enable Delay Count  */
-	u8 enable_delay_count;
-	/* UTMIP PLL Stable count */
-	u8 stable_count;
-	/*  UTMIP PLL Active delay count */
-	u8 active_delay_count;
-	/* UTMIP PLL Xtal frequency count */
-	u8 xtal_freq_count;
-};
-
-static const struct utmi_clk_param utmi_parameters[] = {
-	{
-		.osc_frequency = 13000000, .enable_delay_count = 0x02,
-		.stable_count = 0x33, .active_delay_count = 0x05,
-		.xtal_freq_count = 0x7f
-	}, {
-		.osc_frequency = 19200000, .enable_delay_count = 0x03,
-		.stable_count = 0x4b, .active_delay_count = 0x06,
-		.xtal_freq_count = 0xbb
-	}, {
-		.osc_frequency = 12000000, .enable_delay_count = 0x02,
-		.stable_count = 0x2f, .active_delay_count = 0x04,
-		.xtal_freq_count = 0x76
-	}, {
-		.osc_frequency = 26000000, .enable_delay_count = 0x04,
-		.stable_count = 0x66, .active_delay_count = 0x09,
-		.xtal_freq_count = 0xfe
-	}, {
-		.osc_frequency = 16800000, .enable_delay_count = 0x03,
-		.stable_count = 0x41, .active_delay_count = 0x0a,
-		.xtal_freq_count = 0xa4
-	},
-};
-
 static struct tegra_clk_pll_freq_table pll_c_freq_table[] = {
 	{ 12000000, 1040000000, 520,  6, 1, 8 },
 	{ 13000000, 1040000000, 480,  6, 1, 8 },
@@ -873,59 +819,6 @@ static struct tegra_clk tegra30_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_pll_a_out0] = { .dt_id = TEGRA30_CLK_PLL_A_OUT0, .present = true },
 };
 
-static void tegra30_utmi_param_configure(void)
-{
-	unsigned int i;
-	u32 reg;
-
-	for (i = 0; i < ARRAY_SIZE(utmi_parameters); i++) {
-		if (input_freq == utmi_parameters[i].osc_frequency)
-			break;
-	}
-
-	if (i >= ARRAY_SIZE(utmi_parameters)) {
-		pr_err("%s: Unexpected input rate %lu\n", __func__, input_freq);
-		return;
-	}
-
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG2);
-
-	/* Program UTMIP PLL stable and active counts */
-	reg &= ~UTMIP_PLL_CFG2_STABLE_COUNT(~0);
-	reg |= UTMIP_PLL_CFG2_STABLE_COUNT(
-			utmi_parameters[i].stable_count);
-
-	reg &= ~UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(~0);
-
-	reg |= UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(
-			utmi_parameters[i].active_delay_count);
-
-	/* Remove power downs from UTMIP PLL control bits */
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN;
-
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG2);
-
-	/* Program UTMIP PLL delay and oscillator frequency counts */
-	reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
-	reg &= ~UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(~0);
-
-	reg |= UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(
-		utmi_parameters[i].enable_delay_count);
-
-	reg &= ~UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(~0);
-	reg |= UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(
-		utmi_parameters[i].xtal_freq_count);
-
-	/* Remove power downs from UTMIP PLL control bits */
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN;
-	reg &= ~UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN;
-
-	writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
-}
-
 static const char *pll_e_parents[] = { "pll_ref", "pll_p" };
 
 static void __init tegra30_pll_init(void)
@@ -972,12 +865,10 @@ static void __init tegra30_pll_init(void)
 	clks[TEGRA30_CLK_PLL_X_OUT0] = clk;
 
 	/* PLLU */
-	clk = tegra_clk_register_pll("pll_u", "pll_ref", clk_base, pmc_base, 0,
-			    &pll_u_params, NULL);
+	clk = tegra_clk_register_pllu("pll_u", "pll_ref", clk_base, 0,
+				      &pll_u_params, NULL);
 	clks[TEGRA30_CLK_PLL_U] = clk;
 
-	tegra30_utmi_param_configure();
-
 	/* PLLD */
 	clk = tegra_clk_register_pll("pll_d", "pll_ref", clk_base, pmc_base, 0,
 			    &pll_d_params, &pll_d_lock);
diff --git a/drivers/clk/tegra/clk.h b/drivers/clk/tegra/clk.h
index 9421f0310999..6ba82ecffd4d 100644
--- a/drivers/clk/tegra/clk.h
+++ b/drivers/clk/tegra/clk.h
@@ -427,6 +427,23 @@ struct clk *tegra_clk_register_pllmb(const char *name, const char *parent_name,
 			   struct tegra_clk_pll_params *pll_params,
 			   spinlock_t *lock);
 
+struct clk *tegra_clk_register_pllu(const char *name, const char *parent_name,
+				void __iomem *clk_base, unsigned long flags,
+				struct tegra_clk_pll_params *pll_params,
+				spinlock_t *lock);
+
+struct clk *tegra_clk_register_pllu_tegra114(const char *name,
+				const char *parent_name,
+				void __iomem *clk_base, unsigned long flags,
+				struct tegra_clk_pll_params *pll_params,
+				spinlock_t *lock);
+
+struct clk *tegra_clk_register_pllu_tegra210(const char *name,
+				const char *parent_name,
+				void __iomem *clk_base, unsigned long flags,
+				struct tegra_clk_pll_params *pll_params,
+				spinlock_t *lock);
+
 /**
  * struct tegra_clk_pll_out - PLL divider down clock
  *
diff --git a/drivers/clk/ti/clk-33xx.c b/drivers/clk/ti/clk-33xx.c
index ef2ec64fe547..0e47d95faf49 100644
--- a/drivers/clk/ti/clk-33xx.c
+++ b/drivers/clk/ti/clk-33xx.c
@@ -108,6 +108,9 @@ static struct ti_dt_clk am33xx_clks[] = {
 	DT_CLK("48300200.ehrpwm", "tbclk", "ehrpwm0_tbclk"),
 	DT_CLK("48302200.ehrpwm", "tbclk", "ehrpwm1_tbclk"),
 	DT_CLK("48304200.ehrpwm", "tbclk", "ehrpwm2_tbclk"),
+	DT_CLK("48300200.pwm", "tbclk", "ehrpwm0_tbclk"),
+	DT_CLK("48302200.pwm", "tbclk", "ehrpwm1_tbclk"),
+	DT_CLK("48304200.pwm", "tbclk", "ehrpwm2_tbclk"),
 	{ .node_name = NULL },
 };
 
diff --git a/drivers/clk/ti/clk-43xx.c b/drivers/clk/ti/clk-43xx.c
index 097fc90bf19a..e816a7500e43 100644
--- a/drivers/clk/ti/clk-43xx.c
+++ b/drivers/clk/ti/clk-43xx.c
@@ -58,6 +58,7 @@ static struct ti_dt_clk am43xx_clks[] = {
 	DT_CLK(NULL, "smartreflex1_fck", "smartreflex1_fck"),
 	DT_CLK(NULL, "sha0_fck", "sha0_fck"),
 	DT_CLK(NULL, "aes0_fck", "aes0_fck"),
+	DT_CLK(NULL, "rng_fck", "rng_fck"),
 	DT_CLK(NULL, "timer1_fck", "timer1_fck"),
 	DT_CLK(NULL, "timer2_fck", "timer2_fck"),
 	DT_CLK(NULL, "timer3_fck", "timer3_fck"),
@@ -115,6 +116,12 @@ static struct ti_dt_clk am43xx_clks[] = {
 	DT_CLK("48306200.ehrpwm", "tbclk", "ehrpwm3_tbclk"),
 	DT_CLK("48308200.ehrpwm", "tbclk", "ehrpwm4_tbclk"),
 	DT_CLK("4830a200.ehrpwm", "tbclk", "ehrpwm5_tbclk"),
+	DT_CLK("48300200.pwm", "tbclk", "ehrpwm0_tbclk"),
+	DT_CLK("48302200.pwm", "tbclk", "ehrpwm1_tbclk"),
+	DT_CLK("48304200.pwm", "tbclk", "ehrpwm2_tbclk"),
+	DT_CLK("48306200.pwm", "tbclk", "ehrpwm3_tbclk"),
+	DT_CLK("48308200.pwm", "tbclk", "ehrpwm4_tbclk"),
+	DT_CLK("4830a200.pwm", "tbclk", "ehrpwm5_tbclk"),
 	{ .node_name = NULL },
 };
 
diff --git a/drivers/clk/ux500/u8500_of_clk.c b/drivers/clk/ux500/u8500_of_clk.c
index 9a736d939806..e960d686d9db 100644
--- a/drivers/clk/ux500/u8500_of_clk.c
+++ b/drivers/clk/ux500/u8500_of_clk.c
@@ -11,7 +11,6 @@
 #include <linux/of_address.h>
 #include <linux/clk-provider.h>
 #include <linux/mfd/dbx500-prcmu.h>
-#include <linux/platform_data/clk-ux500.h>
 #include "clk.h"
 
 #define PRCC_NUM_PERIPH_CLUSTERS 6
@@ -48,11 +47,6 @@ static struct clk *ux500_twocell_get(struct of_phandle_args *clkspec,
 	return PRCC_SHOW(clk_data, base, bit);
 }
 
-static const struct of_device_id u8500_clk_of_match[] = {
-	{ .compatible = "stericsson,u8500-clks", },
-	{ },
-};
-
 /* CLKRST4 is missing making it hard to index things */
 enum clkrst_index {
 	CLKRST1_INDEX = 0,
@@ -63,22 +57,15 @@ enum clkrst_index {
 	CLKRST_MAX,
 };
 
-void u8500_clk_init(void)
+static void u8500_clk_init(struct device_node *np)
 {
 	struct prcmu_fw_version *fw_version;
-	struct device_node *np = NULL;
 	struct device_node *child = NULL;
 	const char *sgaclk_parent = NULL;
 	struct clk *clk, *rtc_clk, *twd_clk;
 	u32 bases[CLKRST_MAX];
 	int i;
 
-	if (of_have_populated_dt())
-		np = of_find_matching_node(NULL, u8500_clk_of_match);
-	if (!np) {
-		pr_err("Either DT or U8500 Clock node not found\n");
-		return;
-	}
 	for (i = 0; i < ARRAY_SIZE(bases); i++) {
 		struct resource r;
 
@@ -573,3 +560,4 @@ void u8500_clk_init(void)
 			of_clk_add_provider(child, of_clk_src_simple_get, twd_clk);
 	}
 }
+CLK_OF_DECLARE(u8500_clks, "stericsson,u8500-clks", u8500_clk_init);
diff --git a/drivers/clk/ux500/u8540_clk.c b/drivers/clk/ux500/u8540_clk.c
index 86549e59fb42..133859f0e2bf 100644
--- a/drivers/clk/ux500/u8540_clk.c
+++ b/drivers/clk/ux500/u8540_clk.c
@@ -12,14 +12,8 @@
 #include <linux/clkdev.h>
 #include <linux/clk-provider.h>
 #include <linux/mfd/dbx500-prcmu.h>
-#include <linux/platform_data/clk-ux500.h>
 #include "clk.h"
 
-static const struct of_device_id u8540_clk_of_match[] = {
-	{ .compatible = "stericsson,u8540-clks", },
-	{ }
-};
-
 /* CLKRST4 is missing making it hard to index things */
 enum clkrst_index {
 	CLKRST1_INDEX = 0,
@@ -30,19 +24,12 @@ enum clkrst_index {
 	CLKRST_MAX,
 };
 
-void u8540_clk_init(void)
+static void u8540_clk_init(struct device_node *np)
 {
 	struct clk *clk;
-	struct device_node *np = NULL;
 	u32 bases[CLKRST_MAX];
 	int i;
 
-	if (of_have_populated_dt())
-		np = of_find_matching_node(NULL, u8540_clk_of_match);
-	if (!np) {
-		pr_err("Either DT or U8540 Clock node not found\n");
-		return;
-	}
 	for (i = 0; i < ARRAY_SIZE(bases); i++) {
 		struct resource r;
 
@@ -607,3 +594,4 @@ void u8540_clk_init(void)
 			bases[CLKRST6_INDEX], BIT(0), CLK_SET_RATE_GATE);
 	clk_register_clkdev(clk, NULL, "rng");
 }
+CLK_OF_DECLARE(u8540_clks, "stericsson,u8540-clks", u8540_clk_init);
diff --git a/drivers/clk/ux500/u9540_clk.c b/drivers/clk/ux500/u9540_clk.c
index 2138a4c8cbca..7b6bca49ce42 100644
--- a/drivers/clk/ux500/u9540_clk.c
+++ b/drivers/clk/ux500/u9540_clk.c
@@ -9,10 +9,10 @@
 
 #include <linux/clk-provider.h>
 #include <linux/mfd/dbx500-prcmu.h>
-#include <linux/platform_data/clk-ux500.h>
 #include "clk.h"
 
-void u9540_clk_init(void)
+static void u9540_clk_init(struct device_node *np)
 {
 	/* register clocks here */
 }
+CLK_OF_DECLARE(u9540_clks, "stericsson,u9540-clks", u9540_clk_init);
diff --git a/drivers/clocksource/clps711x-timer.c b/drivers/clocksource/clps711x-timer.c
index 84aed78261e4..24db6d605549 100644
--- a/drivers/clocksource/clps711x-timer.c
+++ b/drivers/clocksource/clps711x-timer.c
@@ -119,5 +119,5 @@ static int __init clps711x_timer_init(struct device_node *np)
 		return -EINVAL;
 	}
 }
-CLOCKSOURCE_OF_DECLARE(clps711x, "cirrus,clps711x-timer", clps711x_timer_init);
+CLOCKSOURCE_OF_DECLARE(clps711x, "cirrus,ep7209-timer", clps711x_timer_init);
 #endif
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index 9e07588ea9f5..f82074eea779 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -220,7 +220,7 @@ static void s5pv210_set_refresh(enum s5pv210_dmc_port ch, unsigned long freq)
 
 	tmp1 /= tmp;
 
-	__raw_writel(tmp1, reg);
+	writel_relaxed(tmp1, reg);
 }
 
 static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
@@ -296,29 +296,29 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 		 * 1. Temporary Change divider for MFC and G3D
 		 * SCLKA2M(200/1=200)->(200/4=50)Mhz
 		 */
-		reg = __raw_readl(S5P_CLK_DIV2);
+		reg = readl_relaxed(S5P_CLK_DIV2);
 		reg &= ~(S5P_CLKDIV2_G3D_MASK | S5P_CLKDIV2_MFC_MASK);
 		reg |= (3 << S5P_CLKDIV2_G3D_SHIFT) |
 			(3 << S5P_CLKDIV2_MFC_SHIFT);
-		__raw_writel(reg, S5P_CLK_DIV2);
+		writel_relaxed(reg, S5P_CLK_DIV2);
 
 		/* For MFC, G3D dividing */
 		do {
-			reg = __raw_readl(S5P_CLKDIV_STAT0);
+			reg = readl_relaxed(S5P_CLKDIV_STAT0);
 		} while (reg & ((1 << 16) | (1 << 17)));
 
 		/*
 		 * 2. Change SCLKA2M(200Mhz)to SCLKMPLL in MFC_MUX, G3D MUX
 		 * (200/4=50)->(667/4=166)Mhz
 		 */
-		reg = __raw_readl(S5P_CLK_SRC2);
+		reg = readl_relaxed(S5P_CLK_SRC2);
 		reg &= ~(S5P_CLKSRC2_G3D_MASK | S5P_CLKSRC2_MFC_MASK);
 		reg |= (1 << S5P_CLKSRC2_G3D_SHIFT) |
 			(1 << S5P_CLKSRC2_MFC_SHIFT);
-		__raw_writel(reg, S5P_CLK_SRC2);
+		writel_relaxed(reg, S5P_CLK_SRC2);
 
 		do {
-			reg = __raw_readl(S5P_CLKMUX_STAT1);
+			reg = readl_relaxed(S5P_CLKMUX_STAT1);
 		} while (reg & ((1 << 7) | (1 << 3)));
 
 		/*
@@ -330,19 +330,19 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 			s5pv210_set_refresh(DMC1, 133000);
 
 		/* 4. SCLKAPLL -> SCLKMPLL */
-		reg = __raw_readl(S5P_CLK_SRC0);
+		reg = readl_relaxed(S5P_CLK_SRC0);
 		reg &= ~(S5P_CLKSRC0_MUX200_MASK);
 		reg |= (0x1 << S5P_CLKSRC0_MUX200_SHIFT);
-		__raw_writel(reg, S5P_CLK_SRC0);
+		writel_relaxed(reg, S5P_CLK_SRC0);
 
 		do {
-			reg = __raw_readl(S5P_CLKMUX_STAT0);
+			reg = readl_relaxed(S5P_CLKMUX_STAT0);
 		} while (reg & (0x1 << 18));
 
 	}
 
 	/* Change divider */
-	reg = __raw_readl(S5P_CLK_DIV0);
+	reg = readl_relaxed(S5P_CLK_DIV0);
 
 	reg &= ~(S5P_CLKDIV0_APLL_MASK | S5P_CLKDIV0_A2M_MASK |
 		S5P_CLKDIV0_HCLK200_MASK | S5P_CLKDIV0_PCLK100_MASK |
@@ -358,25 +358,25 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 		(clkdiv_val[index][6] << S5P_CLKDIV0_HCLK133_SHIFT) |
 		(clkdiv_val[index][7] << S5P_CLKDIV0_PCLK66_SHIFT));
 
-	__raw_writel(reg, S5P_CLK_DIV0);
+	writel_relaxed(reg, S5P_CLK_DIV0);
 
 	do {
-		reg = __raw_readl(S5P_CLKDIV_STAT0);
+		reg = readl_relaxed(S5P_CLKDIV_STAT0);
 	} while (reg & 0xff);
 
 	/* ARM MCS value changed */
-	reg = __raw_readl(S5P_ARM_MCS_CON);
+	reg = readl_relaxed(S5P_ARM_MCS_CON);
 	reg &= ~0x3;
 	if (index >= L3)
 		reg |= 0x3;
 	else
 		reg |= 0x1;
 
-	__raw_writel(reg, S5P_ARM_MCS_CON);
+	writel_relaxed(reg, S5P_ARM_MCS_CON);
 
 	if (pll_changing) {
 		/* 5. Set Lock time = 30us*24Mhz = 0x2cf */
-		__raw_writel(0x2cf, S5P_APLL_LOCK);
+		writel_relaxed(0x2cf, S5P_APLL_LOCK);
 
 		/*
 		 * 6. Turn on APLL
@@ -384,12 +384,12 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 		 * 6-2. Wait untile the PLL is locked
 		 */
 		if (index == L0)
-			__raw_writel(APLL_VAL_1000, S5P_APLL_CON);
+			writel_relaxed(APLL_VAL_1000, S5P_APLL_CON);
 		else
-			__raw_writel(APLL_VAL_800, S5P_APLL_CON);
+			writel_relaxed(APLL_VAL_800, S5P_APLL_CON);
 
 		do {
-			reg = __raw_readl(S5P_APLL_CON);
+			reg = readl_relaxed(S5P_APLL_CON);
 		} while (!(reg & (0x1 << 29)));
 
 		/*
@@ -397,39 +397,39 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 		 * to SCLKA2M(200Mhz) in MFC_MUX and G3D MUX
 		 * (667/4=166)->(200/4=50)Mhz
 		 */
-		reg = __raw_readl(S5P_CLK_SRC2);
+		reg = readl_relaxed(S5P_CLK_SRC2);
 		reg &= ~(S5P_CLKSRC2_G3D_MASK | S5P_CLKSRC2_MFC_MASK);
 		reg |= (0 << S5P_CLKSRC2_G3D_SHIFT) |
 			(0 << S5P_CLKSRC2_MFC_SHIFT);
-		__raw_writel(reg, S5P_CLK_SRC2);
+		writel_relaxed(reg, S5P_CLK_SRC2);
 
 		do {
-			reg = __raw_readl(S5P_CLKMUX_STAT1);
+			reg = readl_relaxed(S5P_CLKMUX_STAT1);
 		} while (reg & ((1 << 7) | (1 << 3)));
 
 		/*
 		 * 8. Change divider for MFC and G3D
 		 * (200/4=50)->(200/1=200)Mhz
 		 */
-		reg = __raw_readl(S5P_CLK_DIV2);
+		reg = readl_relaxed(S5P_CLK_DIV2);
 		reg &= ~(S5P_CLKDIV2_G3D_MASK | S5P_CLKDIV2_MFC_MASK);
 		reg |= (clkdiv_val[index][10] << S5P_CLKDIV2_G3D_SHIFT) |
 			(clkdiv_val[index][9] << S5P_CLKDIV2_MFC_SHIFT);
-		__raw_writel(reg, S5P_CLK_DIV2);
+		writel_relaxed(reg, S5P_CLK_DIV2);
 
 		/* For MFC, G3D dividing */
 		do {
-			reg = __raw_readl(S5P_CLKDIV_STAT0);
+			reg = readl_relaxed(S5P_CLKDIV_STAT0);
 		} while (reg & ((1 << 16) | (1 << 17)));
 
 		/* 9. Change MPLL to APLL in MSYS_MUX */
-		reg = __raw_readl(S5P_CLK_SRC0);
+		reg = readl_relaxed(S5P_CLK_SRC0);
 		reg &= ~(S5P_CLKSRC0_MUX200_MASK);
 		reg |= (0x0 << S5P_CLKSRC0_MUX200_SHIFT);
-		__raw_writel(reg, S5P_CLK_SRC0);
+		writel_relaxed(reg, S5P_CLK_SRC0);
 
 		do {
-			reg = __raw_readl(S5P_CLKMUX_STAT0);
+			reg = readl_relaxed(S5P_CLKMUX_STAT0);
 		} while (reg & (0x1 << 18));
 
 		/*
@@ -446,13 +446,13 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 	 * and memory refresh parameter should be changed
 	 */
 	if (bus_speed_changing) {
-		reg = __raw_readl(S5P_CLK_DIV6);
+		reg = readl_relaxed(S5P_CLK_DIV6);
 		reg &= ~S5P_CLKDIV6_ONEDRAM_MASK;
 		reg |= (clkdiv_val[index][8] << S5P_CLKDIV6_ONEDRAM_SHIFT);
-		__raw_writel(reg, S5P_CLK_DIV6);
+		writel_relaxed(reg, S5P_CLK_DIV6);
 
 		do {
-			reg = __raw_readl(S5P_CLKDIV_STAT1);
+			reg = readl_relaxed(S5P_CLKDIV_STAT1);
 		} while (reg & (1 << 15));
 
 		/* Reconfigure DRAM refresh counter value */
@@ -492,7 +492,7 @@ static int check_mem_type(void __iomem *dmc_reg)
 {
 	unsigned long val;
 
-	val = __raw_readl(dmc_reg + 0x4);
+	val = readl_relaxed(dmc_reg + 0x4);
 	val = (val & (0xf << 8));
 
 	return val >> 8;
@@ -537,10 +537,10 @@ static int s5pv210_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	/* Find current refresh counter and frequency each DMC */
-	s5pv210_dram_conf[0].refresh = (__raw_readl(dmc_base[0] + 0x30) * 1000);
+	s5pv210_dram_conf[0].refresh = (readl_relaxed(dmc_base[0] + 0x30) * 1000);
 	s5pv210_dram_conf[0].freq = clk_get_rate(dmc0_clk);
 
-	s5pv210_dram_conf[1].refresh = (__raw_readl(dmc_base[1] + 0x30) * 1000);
+	s5pv210_dram_conf[1].refresh = (readl_relaxed(dmc_base[1] + 0x30) * 1000);
 	s5pv210_dram_conf[1].freq = clk_get_rate(dmc1_clk);
 
 	policy->suspend_freq = SLEEP_FREQ;
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index e12dc30d8864..f7ca891b5b59 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -20,7 +20,7 @@
 #include <asm/opal.h>
 #include <asm/runlatch.h>
 
-#define MAX_POWERNV_IDLE_STATES	8
+#define POWERNV_THRESHOLD_LATENCY_NS 200000
 
 struct cpuidle_driver powernv_idle_driver = {
 	.name             = "powernv_idle",
@@ -29,6 +29,9 @@ struct cpuidle_driver powernv_idle_driver = {
 
 static int max_idle_state;
 static struct cpuidle_state *cpuidle_state_table;
+
+static u64 stop_psscr_table[CPUIDLE_STATE_MAX];
+
 static u64 snooze_timeout;
 static bool snooze_timeout_en;
 
@@ -93,16 +96,27 @@ static int fastsleep_loop(struct cpuidle_device *dev,
 	return index;
 }
 #endif
+
+static int stop_loop(struct cpuidle_device *dev,
+		     struct cpuidle_driver *drv,
+		     int index)
+{
+	ppc64_runlatch_off();
+	power9_idle_stop(stop_psscr_table[index]);
+	ppc64_runlatch_on();
+	return index;
+}
+
 /*
  * States for dedicated partition case.
  */
-static struct cpuidle_state powernv_states[MAX_POWERNV_IDLE_STATES] = {
+static struct cpuidle_state powernv_states[CPUIDLE_STATE_MAX] = {
 	{ /* Snooze */
 		.name = "snooze",
 		.desc = "snooze",
 		.exit_latency = 0,
 		.target_residency = 0,
-		.enter = &snooze_loop },
+		.enter = snooze_loop },
 };
 
 static int powernv_cpuidle_add_cpu_notifier(struct notifier_block *n,
@@ -168,7 +182,11 @@ static int powernv_add_idle_states(void)
 	struct device_node *power_mgt;
 	int nr_idle_states = 1; /* Snooze */
 	int dt_idle_states;
-	u32 *latency_ns, *residency_ns, *flags;
+	u32 latency_ns[CPUIDLE_STATE_MAX];
+	u32 residency_ns[CPUIDLE_STATE_MAX];
+	u32 flags[CPUIDLE_STATE_MAX];
+	u64 psscr_val[CPUIDLE_STATE_MAX];
+	const char *names[CPUIDLE_STATE_MAX];
 	int i, rc;
 
 	/* Currently we have snooze statically defined */
@@ -186,26 +204,55 @@ static int powernv_add_idle_states(void)
 		goto out;
 	}
 
-	flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL);
+	/*
+	 * Since snooze is used as first idle state, max idle states allowed is
+	 * CPUIDLE_STATE_MAX -1
+	 */
+	if (dt_idle_states > CPUIDLE_STATE_MAX - 1) {
+		pr_warn("cpuidle-powernv: discovered idle states more than allowed");
+		dt_idle_states = CPUIDLE_STATE_MAX - 1;
+	}
+
 	if (of_property_read_u32_array(power_mgt,
 			"ibm,cpu-idle-state-flags", flags, dt_idle_states)) {
 		pr_warn("cpuidle-powernv : missing ibm,cpu-idle-state-flags in DT\n");
-		goto out_free_flags;
+		goto out;
 	}
 
-	latency_ns = kzalloc(sizeof(*latency_ns) * dt_idle_states, GFP_KERNEL);
-	rc = of_property_read_u32_array(power_mgt,
-		"ibm,cpu-idle-state-latencies-ns", latency_ns, dt_idle_states);
-	if (rc) {
+	if (of_property_read_u32_array(power_mgt,
+		"ibm,cpu-idle-state-latencies-ns", latency_ns,
+		dt_idle_states)) {
 		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-latencies-ns in DT\n");
-		goto out_free_latency;
+		goto out;
+	}
+	if (of_property_read_string_array(power_mgt,
+		"ibm,cpu-idle-state-names", names, dt_idle_states) < 0) {
+		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-names in DT\n");
+		goto out;
 	}
 
-	residency_ns = kzalloc(sizeof(*residency_ns) * dt_idle_states, GFP_KERNEL);
+	/*
+	 * If the idle states use stop instruction, probe for psscr values
+	 * which are necessary to specify required stop level.
+	 */
+	if (flags[0] & (OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP))
+		if (of_property_read_u64_array(power_mgt,
+		    "ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) {
+			pr_warn("cpuidle-powernv: missing ibm,cpu-idle-states-psscr in DT\n");
+			goto out;
+		}
+
 	rc = of_property_read_u32_array(power_mgt,
 		"ibm,cpu-idle-state-residency-ns", residency_ns, dt_idle_states);
 
 	for (i = 0; i < dt_idle_states; i++) {
+		/*
+		 * If an idle state has exit latency beyond
+		 * POWERNV_THRESHOLD_LATENCY_NS then don't use it
+		 * in cpu-idle.
+		 */
+		if (latency_ns[i] > POWERNV_THRESHOLD_LATENCY_NS)
+			continue;
 
 		/*
 		 * Cpuidle accepts exit_latency and target_residency in us.
@@ -217,7 +264,17 @@ static int powernv_add_idle_states(void)
 			strcpy(powernv_states[nr_idle_states].desc, "Nap");
 			powernv_states[nr_idle_states].flags = 0;
 			powernv_states[nr_idle_states].target_residency = 100;
-			powernv_states[nr_idle_states].enter = &nap_loop;
+			powernv_states[nr_idle_states].enter = nap_loop;
+		} else if ((flags[i] & OPAL_PM_STOP_INST_FAST) &&
+				!(flags[i] & OPAL_PM_TIMEBASE_STOP)) {
+			strncpy(powernv_states[nr_idle_states].name,
+				names[i], CPUIDLE_NAME_LEN);
+			strncpy(powernv_states[nr_idle_states].desc,
+				names[i], CPUIDLE_NAME_LEN);
+			powernv_states[nr_idle_states].flags = 0;
+
+			powernv_states[nr_idle_states].enter = stop_loop;
+			stop_psscr_table[nr_idle_states] = psscr_val[i];
 		}
 
 		/*
@@ -232,7 +289,17 @@ static int powernv_add_idle_states(void)
 			strcpy(powernv_states[nr_idle_states].desc, "FastSleep");
 			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIMER_STOP;
 			powernv_states[nr_idle_states].target_residency = 300000;
-			powernv_states[nr_idle_states].enter = &fastsleep_loop;
+			powernv_states[nr_idle_states].enter = fastsleep_loop;
+		} else if ((flags[i] & OPAL_PM_STOP_INST_DEEP) &&
+				(flags[i] & OPAL_PM_TIMEBASE_STOP)) {
+			strncpy(powernv_states[nr_idle_states].name,
+				names[i], CPUIDLE_NAME_LEN);
+			strncpy(powernv_states[nr_idle_states].desc,
+				names[i], CPUIDLE_NAME_LEN);
+
+			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIMER_STOP;
+			powernv_states[nr_idle_states].enter = stop_loop;
+			stop_psscr_table[nr_idle_states] = psscr_val[i];
 		}
 #endif
 		powernv_states[nr_idle_states].exit_latency =
@@ -245,12 +312,6 @@ static int powernv_add_idle_states(void)
 
 		nr_idle_states++;
 	}
-
-	kfree(residency_ns);
-out_free_latency:
-	kfree(latency_ns);
-out_free_flags:
-	kfree(flags);
 out:
 	return nr_idle_states;
 }
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index e373cc6557c6..d64af8625d7e 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -180,10 +180,11 @@ int mv_cesa_queue_req(struct crypto_async_request *req,
 	struct mv_cesa_engine *engine = creq->engine;
 
 	spin_lock_bh(&engine->lock);
-	if (mv_cesa_req_get_type(creq) == CESA_DMA_REQ)
-		mv_cesa_tdma_chain(engine, creq);
-
 	ret = crypto_enqueue_request(&engine->queue, req);
+	if ((mv_cesa_req_get_type(creq) == CESA_DMA_REQ) &&
+	    (ret == -EINPROGRESS ||
+	    (ret == -EBUSY && req->flags & CRYPTO_TFM_REQ_MAY_BACKLOG)))
+		mv_cesa_tdma_chain(engine, creq);
 	spin_unlock_bh(&engine->lock);
 
 	if (ret != -EINPROGRESS)
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index 48df03a06066..d19dc9614e6e 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -139,20 +139,11 @@ static int mv_cesa_ablkcipher_process(struct crypto_async_request *req,
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
 	struct mv_cesa_req *basereq = &creq->base;
-	unsigned int ivsize;
-	int ret;
 
 	if (mv_cesa_req_get_type(basereq) == CESA_STD_REQ)
 		return mv_cesa_ablkcipher_std_process(ablkreq, status);
 
-	ret = mv_cesa_dma_process(basereq, status);
-	if (ret)
-		return ret;
-
-	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq));
-	memcpy_fromio(ablkreq->info, basereq->chain.last->data, ivsize);
-
-	return 0;
+	return mv_cesa_dma_process(basereq, status);
 }
 
 static void mv_cesa_ablkcipher_step(struct crypto_async_request *req)
@@ -320,7 +311,6 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 		      GFP_KERNEL : GFP_ATOMIC;
 	struct mv_cesa_req *basereq = &creq->base;
 	struct mv_cesa_ablkcipher_dma_iter iter;
-	struct mv_cesa_tdma_chain chain;
 	bool skip_ctx = false;
 	int ret;
 	unsigned int ivsize;
@@ -347,13 +337,13 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 			return -ENOMEM;
 	}
 
-	mv_cesa_tdma_desc_iter_init(&chain);
+	mv_cesa_tdma_desc_iter_init(&basereq->chain);
 	mv_cesa_ablkcipher_req_iter_init(&iter, req);
 
 	do {
 		struct mv_cesa_op_ctx *op;
 
-		op = mv_cesa_dma_add_op(&chain, op_templ, skip_ctx, flags);
+		op = mv_cesa_dma_add_op(&basereq->chain, op_templ, skip_ctx, flags);
 		if (IS_ERR(op)) {
 			ret = PTR_ERR(op);
 			goto err_free_tdma;
@@ -363,18 +353,18 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 		mv_cesa_set_crypt_op_len(op, iter.base.op_len);
 
 		/* Add input transfers */
-		ret = mv_cesa_dma_add_op_transfers(&chain, &iter.base,
+		ret = mv_cesa_dma_add_op_transfers(&basereq->chain, &iter.base,
 						   &iter.src, flags);
 		if (ret)
 			goto err_free_tdma;
 
 		/* Add dummy desc to launch the crypto operation */
-		ret = mv_cesa_dma_add_dummy_launch(&chain, flags);
+		ret = mv_cesa_dma_add_dummy_launch(&basereq->chain, flags);
 		if (ret)
 			goto err_free_tdma;
 
 		/* Add output transfers */
-		ret = mv_cesa_dma_add_op_transfers(&chain, &iter.base,
+		ret = mv_cesa_dma_add_op_transfers(&basereq->chain, &iter.base,
 						   &iter.dst, flags);
 		if (ret)
 			goto err_free_tdma;
@@ -383,13 +373,12 @@ static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
 
 	/* Add output data for IV */
 	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(req));
-	ret = mv_cesa_dma_add_iv_op(&chain, CESA_SA_CRYPT_IV_SRAM_OFFSET,
+	ret = mv_cesa_dma_add_iv_op(&basereq->chain, CESA_SA_CRYPT_IV_SRAM_OFFSET,
 				    ivsize, CESA_TDMA_SRC_IN_SRAM, flags);
 
 	if (ret)
 		goto err_free_tdma;
 
-	basereq->chain = chain;
 	basereq->chain.last->flags |= CESA_TDMA_END_OF_REQ;
 
 	return 0;
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index c35912b4fffb..82e0f4e6eb1c 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -315,12 +315,6 @@ static void mv_cesa_ahash_complete(struct crypto_async_request *req)
 	for (i = 0; i < digsize / 4; i++)
 		creq->state[i] = readl_relaxed(engine->regs + CESA_IVDIG(i));
 
-	if (creq->cache_ptr)
-		sg_pcopy_to_buffer(ahashreq->src, creq->src_nents,
-				   creq->cache,
-				   creq->cache_ptr,
-				   ahashreq->nbytes - creq->cache_ptr);
-
 	if (creq->last_req) {
 		/*
 		 * Hardware's MD5 digest is in little endian format, but
@@ -365,6 +359,12 @@ static void mv_cesa_ahash_req_cleanup(struct crypto_async_request *req)
 		mv_cesa_ahash_last_cleanup(ahashreq);
 
 	mv_cesa_ahash_cleanup(ahashreq);
+
+	if (creq->cache_ptr)
+		sg_pcopy_to_buffer(ahashreq->src, creq->src_nents,
+				   creq->cache,
+				   creq->cache_ptr,
+				   ahashreq->nbytes - creq->cache_ptr);
 }
 
 static const struct mv_cesa_req_ops mv_cesa_ahash_req_ops = {
diff --git a/drivers/crypto/vmx/Kconfig b/drivers/crypto/vmx/Kconfig
index 89d8208d9851..a83ead109d5f 100644
--- a/drivers/crypto/vmx/Kconfig
+++ b/drivers/crypto/vmx/Kconfig
@@ -1,7 +1,7 @@
 config CRYPTO_DEV_VMX_ENCRYPT
 	tristate "Encryption acceleration support on P8 CPU"
 	depends on CRYPTO_DEV_VMX
-	default y
+	default m
 	help
 	  Support for VMX cryptographic acceleration instructions on Power8 CPU.
 	  This module supports acceleration for AES and GHASH in hardware. If you
diff --git a/drivers/crypto/vmx/vmx.c b/drivers/crypto/vmx/vmx.c
index f688c32fbcc7..31a98dc6f849 100644
--- a/drivers/crypto/vmx/vmx.c
+++ b/drivers/crypto/vmx/vmx.c
@@ -23,6 +23,7 @@
 #include <linux/moduleparam.h>
 #include <linux/types.h>
 #include <linux/err.h>
+#include <linux/cpufeature.h>
 #include <linux/crypto.h>
 #include <asm/cputable.h>
 #include <crypto/internal/hash.h>
@@ -45,9 +46,6 @@ int __init p8_init(void)
 	int ret = 0;
 	struct crypto_alg **alg_it;
 
-	if (!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO))
-		return -ENODEV;
-
 	for (alg_it = algs; *alg_it; alg_it++) {
 		ret = crypto_register_alg(*alg_it);
 		printk(KERN_INFO "crypto_register_alg '%s' = %d\n",
@@ -80,7 +78,7 @@ void __exit p8_exit(void)
 	crypto_unregister_shash(&p8_ghash_alg);
 }
 
-module_init(p8_init);
+module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, p8_init);
 module_exit(p8_exit);
 
 MODULE_AUTHOR("Marcelo Cerri<mhcerri@br.ibm.com>");
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig
index 9824bc4addf8..25bcfa0b474f 100644
--- a/drivers/dma-buf/Kconfig
+++ b/drivers/dma-buf/Kconfig
@@ -1,11 +1,20 @@
 menu "DMABUF options"
 
 config SYNC_FILE
-	bool "sync_file support for fences"
+	bool "Explicit Synchronization Framework"
 	default n
 	select ANON_INODES
 	select DMA_SHARED_BUFFER
 	---help---
-	  This option enables the fence framework synchronization to export
-	  sync_files to userspace that can represent one or more fences.
+	  The Sync File Framework adds explicit syncronization via
+	  userspace. It enables send/receive 'struct fence' objects to/from
+	  userspace via Sync File fds for synchronization between drivers via
+	  userspace components. It has been ported from Android.
+
+	  The first and main user for this is graphics in which a fence is
+	  associated with a buffer. When a job is submitted to the GPU a fence
+	  is attached to the buffer and is transferred via userspace, using Sync
+	  Files fds, to the DRM driver for example. More details at
+	  Documentation/sync_file.txt.
+
 endmenu
diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 4a424eca75ed..f353db213a81 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,2 +1,2 @@
-obj-y := dma-buf.o fence.o reservation.o seqno-fence.o
+obj-y := dma-buf.o fence.o reservation.o seqno-fence.o fence-array.o
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 6355ab38d630..ddaee60ae52a 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -334,6 +334,7 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 	struct reservation_object *resv = exp_info->resv;
 	struct file *file;
 	size_t alloc_size = sizeof(struct dma_buf);
+	int ret;
 
 	if (!exp_info->resv)
 		alloc_size += sizeof(struct reservation_object);
@@ -357,8 +358,8 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 
 	dmabuf = kzalloc(alloc_size, GFP_KERNEL);
 	if (!dmabuf) {
-		module_put(exp_info->owner);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto err_module;
 	}
 
 	dmabuf->priv = exp_info->priv;
@@ -379,8 +380,8 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 	file = anon_inode_getfile("dmabuf", &dma_buf_fops, dmabuf,
 					exp_info->flags);
 	if (IS_ERR(file)) {
-		kfree(dmabuf);
-		return ERR_CAST(file);
+		ret = PTR_ERR(file);
+		goto err_dmabuf;
 	}
 
 	file->f_mode |= FMODE_LSEEK;
@@ -394,6 +395,12 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 	mutex_unlock(&db_list.lock);
 
 	return dmabuf;
+
+err_dmabuf:
+	kfree(dmabuf);
+err_module:
+	module_put(exp_info->owner);
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dma_buf_export);
 
@@ -824,7 +831,7 @@ void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
 EXPORT_SYMBOL_GPL(dma_buf_vunmap);
 
 #ifdef CONFIG_DEBUG_FS
-static int dma_buf_describe(struct seq_file *s)
+static int dma_buf_debug_show(struct seq_file *s, void *unused)
 {
 	int ret;
 	struct dma_buf *buf_obj;
@@ -879,17 +886,9 @@ static int dma_buf_describe(struct seq_file *s)
 	return 0;
 }
 
-static int dma_buf_show(struct seq_file *s, void *unused)
-{
-	void (*func)(struct seq_file *) = s->private;
-
-	func(s);
-	return 0;
-}
-
 static int dma_buf_debug_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, dma_buf_show, inode->i_private);
+	return single_open(file, dma_buf_debug_show, NULL);
 }
 
 static const struct file_operations dma_buf_debug_fops = {
@@ -903,20 +902,23 @@ static struct dentry *dma_buf_debugfs_dir;
 
 static int dma_buf_init_debugfs(void)
 {
+	struct dentry *d;
 	int err = 0;
 
-	dma_buf_debugfs_dir = debugfs_create_dir("dma_buf", NULL);
+	d = debugfs_create_dir("dma_buf", NULL);
+	if (IS_ERR(d))
+		return PTR_ERR(d);
 
-	if (IS_ERR(dma_buf_debugfs_dir)) {
-		err = PTR_ERR(dma_buf_debugfs_dir);
-		dma_buf_debugfs_dir = NULL;
-		return err;
-	}
-
-	err = dma_buf_debugfs_create_file("bufinfo", dma_buf_describe);
+	dma_buf_debugfs_dir = d;
 
-	if (err)
+	d = debugfs_create_file("bufinfo", S_IRUGO, dma_buf_debugfs_dir,
+				NULL, &dma_buf_debug_fops);
+	if (IS_ERR(d)) {
 		pr_debug("dma_buf: debugfs: failed to create node bufinfo\n");
+		debugfs_remove_recursive(dma_buf_debugfs_dir);
+		dma_buf_debugfs_dir = NULL;
+		err = PTR_ERR(d);
+	}
 
 	return err;
 }
@@ -926,17 +928,6 @@ static void dma_buf_uninit_debugfs(void)
 	if (dma_buf_debugfs_dir)
 		debugfs_remove_recursive(dma_buf_debugfs_dir);
 }
-
-int dma_buf_debugfs_create_file(const char *name,
-				int (*write)(struct seq_file *))
-{
-	struct dentry *d;
-
-	d = debugfs_create_file(name, S_IRUGO, dma_buf_debugfs_dir,
-			write, &dma_buf_debug_fops);
-
-	return PTR_ERR_OR_ZERO(d);
-}
 #else
 static inline int dma_buf_init_debugfs(void)
 {
diff --git a/drivers/dma-buf/fence-array.c b/drivers/dma-buf/fence-array.c
new file mode 100644
index 000000000000..a8731c853da6
--- /dev/null
+++ b/drivers/dma-buf/fence-array.c
@@ -0,0 +1,144 @@
+/*
+ * fence-array: aggregate fences to be waited together
+ *
+ * Copyright (C) 2016 Collabora Ltd
+ * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Gustavo Padovan <gustavo@padovan.org>
+ *	Christian König <christian.koenig@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/fence-array.h>
+
+static void fence_array_cb_func(struct fence *f, struct fence_cb *cb);
+
+static const char *fence_array_get_driver_name(struct fence *fence)
+{
+	return "fence_array";
+}
+
+static const char *fence_array_get_timeline_name(struct fence *fence)
+{
+	return "unbound";
+}
+
+static void fence_array_cb_func(struct fence *f, struct fence_cb *cb)
+{
+	struct fence_array_cb *array_cb =
+		container_of(cb, struct fence_array_cb, cb);
+	struct fence_array *array = array_cb->array;
+
+	if (atomic_dec_and_test(&array->num_pending))
+		fence_signal(&array->base);
+	fence_put(&array->base);
+}
+
+static bool fence_array_enable_signaling(struct fence *fence)
+{
+	struct fence_array *array = to_fence_array(fence);
+	struct fence_array_cb *cb = (void *)(&array[1]);
+	unsigned i;
+
+	for (i = 0; i < array->num_fences; ++i) {
+		cb[i].array = array;
+		/*
+		 * As we may report that the fence is signaled before all
+		 * callbacks are complete, we need to take an additional
+		 * reference count on the array so that we do not free it too
+		 * early. The core fence handling will only hold the reference
+		 * until we signal the array as complete (but that is now
+		 * insufficient).
+		 */
+		fence_get(&array->base);
+		if (fence_add_callback(array->fences[i], &cb[i].cb,
+				       fence_array_cb_func)) {
+			fence_put(&array->base);
+			if (atomic_dec_and_test(&array->num_pending))
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static bool fence_array_signaled(struct fence *fence)
+{
+	struct fence_array *array = to_fence_array(fence);
+
+	return atomic_read(&array->num_pending) <= 0;
+}
+
+static void fence_array_release(struct fence *fence)
+{
+	struct fence_array *array = to_fence_array(fence);
+	unsigned i;
+
+	for (i = 0; i < array->num_fences; ++i)
+		fence_put(array->fences[i]);
+
+	kfree(array->fences);
+	fence_free(fence);
+}
+
+const struct fence_ops fence_array_ops = {
+	.get_driver_name = fence_array_get_driver_name,
+	.get_timeline_name = fence_array_get_timeline_name,
+	.enable_signaling = fence_array_enable_signaling,
+	.signaled = fence_array_signaled,
+	.wait = fence_default_wait,
+	.release = fence_array_release,
+};
+
+/**
+ * fence_array_create - Create a custom fence array
+ * @num_fences:		[in]	number of fences to add in the array
+ * @fences:		[in]	array containing the fences
+ * @context:		[in]	fence context to use
+ * @seqno:		[in]	sequence number to use
+ * @signal_on_any	[in]	signal on any fence in the array
+ *
+ * Allocate a fence_array object and initialize the base fence with fence_init().
+ * In case of error it returns NULL.
+ *
+ * The caller should allocte the fences array with num_fences size
+ * and fill it with the fences it wants to add to the object. Ownership of this
+ * array is take and fence_put() is used on each fence on release.
+ *
+ * If @signal_on_any is true the fence array signals if any fence in the array
+ * signals, otherwise it signals when all fences in the array signal.
+ */
+struct fence_array *fence_array_create(int num_fences, struct fence **fences,
+				       u64 context, unsigned seqno,
+				       bool signal_on_any)
+{
+	struct fence_array *array;
+	size_t size = sizeof(*array);
+
+	/* Allocate the callback structures behind the array. */
+	size += num_fences * sizeof(struct fence_array_cb);
+	array = kzalloc(size, GFP_KERNEL);
+	if (!array)
+		return NULL;
+
+	spin_lock_init(&array->lock);
+	fence_init(&array->base, &fence_array_ops, &array->lock,
+		   context, seqno);
+
+	array->num_fences = num_fences;
+	atomic_set(&array->num_pending, signal_on_any ? 1 : num_fences);
+	array->fences = fences;
+
+	return array;
+}
+EXPORT_SYMBOL(fence_array_create);
diff --git a/drivers/dma-buf/fence.c b/drivers/dma-buf/fence.c
index 7b05dbe9b296..4d51f9e83fa8 100644
--- a/drivers/dma-buf/fence.c
+++ b/drivers/dma-buf/fence.c
@@ -35,7 +35,7 @@ EXPORT_TRACEPOINT_SYMBOL(fence_emit);
  * context or not. One device can have multiple separate contexts,
  * and they're used if some engine can run independently of another.
  */
-static atomic_t fence_context_counter = ATOMIC_INIT(0);
+static atomic64_t fence_context_counter = ATOMIC64_INIT(0);
 
 /**
  * fence_context_alloc - allocate an array of fence contexts
@@ -44,10 +44,10 @@ static atomic_t fence_context_counter = ATOMIC_INIT(0);
  * This function will return the first index of the number of fences allocated.
  * The fence context is used for setting fence->context to a unique number.
  */
-unsigned fence_context_alloc(unsigned num)
+u64 fence_context_alloc(unsigned num)
 {
 	BUG_ON(!num);
-	return atomic_add_return(num, &fence_context_counter) - num;
+	return atomic64_add_return(num, &fence_context_counter) - num;
 }
 EXPORT_SYMBOL(fence_context_alloc);
 
@@ -513,7 +513,7 @@ EXPORT_SYMBOL(fence_wait_any_timeout);
  */
 void
 fence_init(struct fence *fence, const struct fence_ops *ops,
-	     spinlock_t *lock, unsigned context, unsigned seqno)
+	     spinlock_t *lock, u64 context, unsigned seqno)
 {
 	BUG_ON(!lock);
 	BUG_ON(!ops || !ops->wait || !ops->enable_signaling ||
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index f08cf2d8309e..9aaa608dfe01 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -82,7 +82,7 @@ struct sync_file *sync_file_create(struct fence *fence)
 
 	sync_file->num_fences = 1;
 	atomic_set(&sync_file->status, 1);
-	snprintf(sync_file->name, sizeof(sync_file->name), "%s-%s%d-%d",
+	snprintf(sync_file->name, sizeof(sync_file->name), "%s-%s%llu-%d",
 		 fence->ops->get_driver_name(fence),
 		 fence->ops->get_timeline_name(fence), fence->context,
 		 fence->seqno);
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 6664f1108c7c..0e22f241403b 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -10,7 +10,7 @@ config ARM_PSCI_FW
 
 config ARM_SCPI_PROTOCOL
 	tristate "ARM System Control and Power Interface (SCPI) Message Protocol"
-	depends on ARM_MHU
+	depends on MAILBOX
 	help
 	  System Control and Power Interface (SCPI) Message Protocol is
 	  defined for the purpose of communication between the Application
@@ -27,6 +27,15 @@ config ARM_SCPI_PROTOCOL
 	  This protocol library provides interface for all the client drivers
 	  making use of the features offered by the SCP.
 
+config ARM_SCPI_POWER_DOMAIN
+	tristate "SCPI power domain driver"
+	depends on ARM_SCPI_PROTOCOL || (COMPILE_TEST && OF)
+	default y
+	select PM_GENERIC_DOMAINS if PM
+	help
+	  This enables support for the SCPI power domains which can be
+	  enabled or disabled via the SCP firmware
+
 config EDD
 	tristate "BIOS Enhanced Disk Drive calls determine boot disk"
 	depends on X86
@@ -184,6 +193,7 @@ config FW_CFG_SYSFS_CMDLINE
 config QCOM_SCM
 	bool
 	depends on ARM || ARM64
+	select RESET_CONTROLLER
 
 config QCOM_SCM_32
 	def_bool y
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 474bada56fcd..44a59dcfc398 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -3,6 +3,7 @@
 #
 obj-$(CONFIG_ARM_PSCI_FW)	+= psci.o
 obj-$(CONFIG_ARM_SCPI_PROTOCOL)	+= arm_scpi.o
+obj-$(CONFIG_ARM_SCPI_POWER_DOMAIN) += scpi_pm_domain.o
 obj-$(CONFIG_DMI)		+= dmi_scan.o
 obj-$(CONFIG_DMI_SYSFS)		+= dmi-sysfs.o
 obj-$(CONFIG_EDD)		+= edd.o
diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c
index 7e3e595c9f30..438893762076 100644
--- a/drivers/firmware/arm_scpi.c
+++ b/drivers/firmware/arm_scpi.c
@@ -210,10 +210,6 @@ struct dvfs_info {
 	} opps[MAX_DVFS_OPPS];
 } __packed;
 
-struct dvfs_get {
-	u8 index;
-} __packed;
-
 struct dvfs_set {
 	u8 domain;
 	u8 index;
@@ -235,6 +231,11 @@ struct sensor_value {
 	__le32 hi_val;
 } __packed;
 
+struct dev_pstate_set {
+	u16 dev_id;
+	u8 pstate;
+} __packed;
+
 static struct scpi_drvinfo *scpi_info;
 
 static int scpi_linux_errmap[SCPI_ERR_MAX] = {
@@ -431,11 +432,11 @@ static int scpi_clk_set_val(u16 clk_id, unsigned long rate)
 static int scpi_dvfs_get_idx(u8 domain)
 {
 	int ret;
-	struct dvfs_get dvfs;
+	u8 dvfs_idx;
 
 	ret = scpi_send_message(SCPI_CMD_GET_DVFS, &domain, sizeof(domain),
-				&dvfs, sizeof(dvfs));
-	return ret ? ret : dvfs.index;
+				&dvfs_idx, sizeof(dvfs_idx));
+	return ret ? ret : dvfs_idx;
 }
 
 static int scpi_dvfs_set_idx(u8 domain, u8 index)
@@ -526,7 +527,7 @@ static int scpi_sensor_get_info(u16 sensor_id, struct scpi_sensor_info *info)
 	return ret;
 }
 
-int scpi_sensor_get_value(u16 sensor, u64 *val)
+static int scpi_sensor_get_value(u16 sensor, u64 *val)
 {
 	__le16 id = cpu_to_le16(sensor);
 	struct sensor_value buf;
@@ -541,6 +542,29 @@ int scpi_sensor_get_value(u16 sensor, u64 *val)
 	return ret;
 }
 
+static int scpi_device_get_power_state(u16 dev_id)
+{
+	int ret;
+	u8 pstate;
+	__le16 id = cpu_to_le16(dev_id);
+
+	ret = scpi_send_message(SCPI_CMD_GET_DEVICE_PWR_STATE, &id,
+				sizeof(id), &pstate, sizeof(pstate));
+	return ret ? ret : pstate;
+}
+
+static int scpi_device_set_power_state(u16 dev_id, u8 pstate)
+{
+	int stat;
+	struct dev_pstate_set dev_set = {
+		.dev_id = cpu_to_le16(dev_id),
+		.pstate = pstate,
+	};
+
+	return scpi_send_message(SCPI_CMD_SET_DEVICE_PWR_STATE, &dev_set,
+				 sizeof(dev_set), &stat, sizeof(stat));
+}
+
 static struct scpi_ops scpi_ops = {
 	.get_version = scpi_get_version,
 	.clk_get_range = scpi_clk_get_range,
@@ -552,6 +576,8 @@ static struct scpi_ops scpi_ops = {
 	.sensor_get_capability = scpi_sensor_get_capability,
 	.sensor_get_info = scpi_sensor_get_info,
 	.sensor_get_value = scpi_sensor_get_value,
+	.device_get_power_state = scpi_device_get_power_state,
+	.device_set_power_state = scpi_device_set_power_state,
 };
 
 struct scpi_ops *get_scpi_ops(void)
diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c
index 0883292f640f..c6aeedbdcbb0 100644
--- a/drivers/firmware/qcom_scm-32.c
+++ b/drivers/firmware/qcom_scm-32.c
@@ -23,8 +23,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/qcom_scm.h>
-
-#include <asm/cacheflush.h>
+#include <linux/dma-mapping.h>
 
 #include "qcom_scm.h"
 
@@ -97,44 +96,6 @@ struct qcom_scm_response {
 };
 
 /**
- * alloc_qcom_scm_command() - Allocate an SCM command
- * @cmd_size: size of the command buffer
- * @resp_size: size of the response buffer
- *
- * Allocate an SCM command, including enough room for the command
- * and response headers as well as the command and response buffers.
- *
- * Returns a valid &qcom_scm_command on success or %NULL if the allocation fails.
- */
-static struct qcom_scm_command *alloc_qcom_scm_command(size_t cmd_size, size_t resp_size)
-{
-	struct qcom_scm_command *cmd;
-	size_t len = sizeof(*cmd) + sizeof(struct qcom_scm_response) + cmd_size +
-		resp_size;
-	u32 offset;
-
-	cmd = kzalloc(PAGE_ALIGN(len), GFP_KERNEL);
-	if (cmd) {
-		cmd->len = cpu_to_le32(len);
-		offset = offsetof(struct qcom_scm_command, buf);
-		cmd->buf_offset = cpu_to_le32(offset);
-		cmd->resp_hdr_offset = cpu_to_le32(offset + cmd_size);
-	}
-	return cmd;
-}
-
-/**
- * free_qcom_scm_command() - Free an SCM command
- * @cmd: command to free
- *
- * Free an SCM command.
- */
-static inline void free_qcom_scm_command(struct qcom_scm_command *cmd)
-{
-	kfree(cmd);
-}
-
-/**
  * qcom_scm_command_to_response() - Get a pointer to a qcom_scm_response
  * @cmd: command
  *
@@ -168,23 +129,6 @@ static inline void *qcom_scm_get_response_buffer(const struct qcom_scm_response
 	return (void *)rsp + le32_to_cpu(rsp->buf_offset);
 }
 
-static int qcom_scm_remap_error(int err)
-{
-	pr_err("qcom_scm_call failed with error code %d\n", err);
-	switch (err) {
-	case QCOM_SCM_ERROR:
-		return -EIO;
-	case QCOM_SCM_EINVAL_ADDR:
-	case QCOM_SCM_EINVAL_ARG:
-		return -EINVAL;
-	case QCOM_SCM_EOPNOTSUPP:
-		return -EOPNOTSUPP;
-	case QCOM_SCM_ENOMEM:
-		return -ENOMEM;
-	}
-	return -EINVAL;
-}
-
 static u32 smc(u32 cmd_addr)
 {
 	int context_id;
@@ -209,45 +153,9 @@ static u32 smc(u32 cmd_addr)
 	return r0;
 }
 
-static int __qcom_scm_call(const struct qcom_scm_command *cmd)
-{
-	int ret;
-	u32 cmd_addr = virt_to_phys(cmd);
-
-	/*
-	 * Flush the command buffer so that the secure world sees
-	 * the correct data.
-	 */
-	secure_flush_area(cmd, cmd->len);
-
-	ret = smc(cmd_addr);
-	if (ret < 0)
-		ret = qcom_scm_remap_error(ret);
-
-	return ret;
-}
-
-static void qcom_scm_inv_range(unsigned long start, unsigned long end)
-{
-	u32 cacheline_size, ctr;
-
-	asm volatile("mrc p15, 0, %0, c0, c0, 1" : "=r" (ctr));
-	cacheline_size = 4 << ((ctr >> 16) & 0xf);
-
-	start = round_down(start, cacheline_size);
-	end = round_up(end, cacheline_size);
-	outer_inv_range(start, end);
-	while (start < end) {
-		asm ("mcr p15, 0, %0, c7, c6, 1" : : "r" (start)
-		     : "memory");
-		start += cacheline_size;
-	}
-	dsb();
-	isb();
-}
-
 /**
  * qcom_scm_call() - Send an SCM command
+ * @dev: struct device
  * @svc_id: service identifier
  * @cmd_id: command identifier
  * @cmd_buf: command buffer
@@ -264,42 +172,59 @@ static void qcom_scm_inv_range(unsigned long start, unsigned long end)
  * and response buffers is taken care of by qcom_scm_call; however, callers are
  * responsible for any other cached buffers passed over to the secure world.
  */
-static int qcom_scm_call(u32 svc_id, u32 cmd_id, const void *cmd_buf,
-			size_t cmd_len, void *resp_buf, size_t resp_len)
+static int qcom_scm_call(struct device *dev, u32 svc_id, u32 cmd_id,
+			 const void *cmd_buf, size_t cmd_len, void *resp_buf,
+			 size_t resp_len)
 {
 	int ret;
 	struct qcom_scm_command *cmd;
 	struct qcom_scm_response *rsp;
-	unsigned long start, end;
+	size_t alloc_len = sizeof(*cmd) + cmd_len + sizeof(*rsp) + resp_len;
+	dma_addr_t cmd_phys;
 
-	cmd = alloc_qcom_scm_command(cmd_len, resp_len);
+	cmd = kzalloc(PAGE_ALIGN(alloc_len), GFP_KERNEL);
 	if (!cmd)
 		return -ENOMEM;
 
+	cmd->len = cpu_to_le32(alloc_len);
+	cmd->buf_offset = cpu_to_le32(sizeof(*cmd));
+	cmd->resp_hdr_offset = cpu_to_le32(sizeof(*cmd) + cmd_len);
+
 	cmd->id = cpu_to_le32((svc_id << 10) | cmd_id);
 	if (cmd_buf)
 		memcpy(qcom_scm_get_command_buffer(cmd), cmd_buf, cmd_len);
 
+	rsp = qcom_scm_command_to_response(cmd);
+
+	cmd_phys = dma_map_single(dev, cmd, alloc_len, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, cmd_phys)) {
+		kfree(cmd);
+		return -ENOMEM;
+	}
+
 	mutex_lock(&qcom_scm_lock);
-	ret = __qcom_scm_call(cmd);
+	ret = smc(cmd_phys);
+	if (ret < 0)
+		ret = qcom_scm_remap_error(ret);
 	mutex_unlock(&qcom_scm_lock);
 	if (ret)
 		goto out;
 
-	rsp = qcom_scm_command_to_response(cmd);
-	start = (unsigned long)rsp;
-
 	do {
-		qcom_scm_inv_range(start, start + sizeof(*rsp));
+		dma_sync_single_for_cpu(dev, cmd_phys + sizeof(*cmd) + cmd_len,
+					sizeof(*rsp), DMA_FROM_DEVICE);
 	} while (!rsp->is_complete);
 
-	end = (unsigned long)qcom_scm_get_response_buffer(rsp) + resp_len;
-	qcom_scm_inv_range(start, end);
-
-	if (resp_buf)
-		memcpy(resp_buf, qcom_scm_get_response_buffer(rsp), resp_len);
+	if (resp_buf) {
+		dma_sync_single_for_cpu(dev, cmd_phys + sizeof(*cmd) + cmd_len +
+					le32_to_cpu(rsp->buf_offset),
+					resp_len, DMA_FROM_DEVICE);
+		memcpy(resp_buf, qcom_scm_get_response_buffer(rsp),
+		       resp_len);
+	}
 out:
-	free_qcom_scm_command(cmd);
+	dma_unmap_single(dev, cmd_phys, alloc_len, DMA_TO_DEVICE);
+	kfree(cmd);
 	return ret;
 }
 
@@ -342,6 +267,41 @@ static s32 qcom_scm_call_atomic1(u32 svc, u32 cmd, u32 arg1)
 	return r0;
 }
 
+/**
+ * qcom_scm_call_atomic2() - Send an atomic SCM command with two arguments
+ * @svc_id:	service identifier
+ * @cmd_id:	command identifier
+ * @arg1:	first argument
+ * @arg2:	second argument
+ *
+ * This shall only be used with commands that are guaranteed to be
+ * uninterruptable, atomic and SMP safe.
+ */
+static s32 qcom_scm_call_atomic2(u32 svc, u32 cmd, u32 arg1, u32 arg2)
+{
+	int context_id;
+
+	register u32 r0 asm("r0") = SCM_ATOMIC(svc, cmd, 2);
+	register u32 r1 asm("r1") = (u32)&context_id;
+	register u32 r2 asm("r2") = arg1;
+	register u32 r3 asm("r3") = arg2;
+
+	asm volatile(
+			__asmeq("%0", "r0")
+			__asmeq("%1", "r0")
+			__asmeq("%2", "r1")
+			__asmeq("%3", "r2")
+			__asmeq("%4", "r3")
+#ifdef REQUIRES_SEC
+			".arch_extension sec\n"
+#endif
+			"smc    #0      @ switch to secure world\n"
+			: "=r" (r0)
+			: "r" (r0), "r" (r1), "r" (r2), "r" (r3)
+			);
+	return r0;
+}
+
 u32 qcom_scm_get_version(void)
 {
 	int context_id;
@@ -378,22 +338,6 @@ u32 qcom_scm_get_version(void)
 }
 EXPORT_SYMBOL(qcom_scm_get_version);
 
-/*
- * Set the cold/warm boot address for one of the CPU cores.
- */
-static int qcom_scm_set_boot_addr(u32 addr, int flags)
-{
-	struct {
-		__le32 flags;
-		__le32 addr;
-	} cmd;
-
-	cmd.addr = cpu_to_le32(addr);
-	cmd.flags = cpu_to_le32(flags);
-	return qcom_scm_call(QCOM_SCM_SVC_BOOT, QCOM_SCM_BOOT_ADDR,
-			&cmd, sizeof(cmd), NULL, 0);
-}
-
 /**
  * qcom_scm_set_cold_boot_addr() - Set the cold boot address for cpus
  * @entry: Entry point function for the cpus
@@ -423,7 +367,8 @@ int __qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus)
 			set_cpu_present(cpu, false);
 	}
 
-	return qcom_scm_set_boot_addr(virt_to_phys(entry), flags);
+	return qcom_scm_call_atomic2(QCOM_SCM_SVC_BOOT, QCOM_SCM_BOOT_ADDR,
+				    flags, virt_to_phys(entry));
 }
 
 /**
@@ -434,11 +379,16 @@ int __qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus)
  * Set the Linux entry point for the SCM to transfer control to when coming
  * out of a power down. CPU power down may be executed on cpuidle or hotplug.
  */
-int __qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus)
+int __qcom_scm_set_warm_boot_addr(struct device *dev, void *entry,
+				  const cpumask_t *cpus)
 {
 	int ret;
 	int flags = 0;
 	int cpu;
+	struct {
+		__le32 flags;
+		__le32 addr;
+	} cmd;
 
 	/*
 	 * Reassign only if we are switching from hotplug entry point
@@ -454,7 +404,10 @@ int __qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus)
 	if (!flags)
 		return 0;
 
-	ret = qcom_scm_set_boot_addr(virt_to_phys(entry), flags);
+	cmd.addr = cpu_to_le32(virt_to_phys(entry));
+	cmd.flags = cpu_to_le32(flags);
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_BOOT, QCOM_SCM_BOOT_ADDR,
+			    &cmd, sizeof(cmd), NULL, 0);
 	if (!ret) {
 		for_each_cpu(cpu, cpus)
 			qcom_scm_wb[cpu].entry = entry;
@@ -477,25 +430,133 @@ void __qcom_scm_cpu_power_down(u32 flags)
 			flags & QCOM_SCM_FLUSH_FLAG_MASK);
 }
 
-int __qcom_scm_is_call_available(u32 svc_id, u32 cmd_id)
+int __qcom_scm_is_call_available(struct device *dev, u32 svc_id, u32 cmd_id)
 {
 	int ret;
 	__le32 svc_cmd = cpu_to_le32((svc_id << 10) | cmd_id);
 	__le32 ret_val = 0;
 
-	ret = qcom_scm_call(QCOM_SCM_SVC_INFO, QCOM_IS_CALL_AVAIL_CMD, &svc_cmd,
-			sizeof(svc_cmd), &ret_val, sizeof(ret_val));
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_INFO, QCOM_IS_CALL_AVAIL_CMD,
+			    &svc_cmd, sizeof(svc_cmd), &ret_val,
+			    sizeof(ret_val));
 	if (ret)
 		return ret;
 
 	return le32_to_cpu(ret_val);
 }
 
-int __qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp)
+int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req,
+			u32 req_cnt, u32 *resp)
 {
 	if (req_cnt > QCOM_SCM_HDCP_MAX_REQ_CNT)
 		return -ERANGE;
 
-	return qcom_scm_call(QCOM_SCM_SVC_HDCP, QCOM_SCM_CMD_HDCP,
+	return qcom_scm_call(dev, QCOM_SCM_SVC_HDCP, QCOM_SCM_CMD_HDCP,
 		req, req_cnt * sizeof(*req), resp, sizeof(*resp));
 }
+
+void __qcom_scm_init(void)
+{
+}
+
+bool __qcom_scm_pas_supported(struct device *dev, u32 peripheral)
+{
+	__le32 out;
+	__le32 in;
+	int ret;
+
+	in = cpu_to_le32(peripheral);
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL,
+			    QCOM_SCM_PAS_IS_SUPPORTED_CMD,
+			    &in, sizeof(in),
+			    &out, sizeof(out));
+
+	return ret ? false : !!out;
+}
+
+int __qcom_scm_pas_init_image(struct device *dev, u32 peripheral,
+			      dma_addr_t metadata_phys)
+{
+	__le32 scm_ret;
+	int ret;
+	struct {
+		__le32 proc;
+		__le32 image_addr;
+	} request;
+
+	request.proc = cpu_to_le32(peripheral);
+	request.image_addr = cpu_to_le32(metadata_phys);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL,
+			    QCOM_SCM_PAS_INIT_IMAGE_CMD,
+			    &request, sizeof(request),
+			    &scm_ret, sizeof(scm_ret));
+
+	return ret ? : le32_to_cpu(scm_ret);
+}
+
+int __qcom_scm_pas_mem_setup(struct device *dev, u32 peripheral,
+			     phys_addr_t addr, phys_addr_t size)
+{
+	__le32 scm_ret;
+	int ret;
+	struct {
+		__le32 proc;
+		__le32 addr;
+		__le32 len;
+	} request;
+
+	request.proc = cpu_to_le32(peripheral);
+	request.addr = cpu_to_le32(addr);
+	request.len = cpu_to_le32(size);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL,
+			    QCOM_SCM_PAS_MEM_SETUP_CMD,
+			    &request, sizeof(request),
+			    &scm_ret, sizeof(scm_ret));
+
+	return ret ? : le32_to_cpu(scm_ret);
+}
+
+int __qcom_scm_pas_auth_and_reset(struct device *dev, u32 peripheral)
+{
+	__le32 out;
+	__le32 in;
+	int ret;
+
+	in = cpu_to_le32(peripheral);
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL,
+			    QCOM_SCM_PAS_AUTH_AND_RESET_CMD,
+			    &in, sizeof(in),
+			    &out, sizeof(out));
+
+	return ret ? : le32_to_cpu(out);
+}
+
+int __qcom_scm_pas_shutdown(struct device *dev, u32 peripheral)
+{
+	__le32 out;
+	__le32 in;
+	int ret;
+
+	in = cpu_to_le32(peripheral);
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL,
+			    QCOM_SCM_PAS_SHUTDOWN_CMD,
+			    &in, sizeof(in),
+			    &out, sizeof(out));
+
+	return ret ? : le32_to_cpu(out);
+}
+
+int __qcom_scm_pas_mss_reset(struct device *dev, bool reset)
+{
+	__le32 out;
+	__le32 in = cpu_to_le32(reset);
+	int ret;
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL, QCOM_SCM_PAS_MSS_RESET,
+			&in, sizeof(in),
+			&out, sizeof(out));
+
+	return ret ? : le32_to_cpu(out);
+}
diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c
index bb6555f6d63b..4a0f5ead4fb5 100644
--- a/drivers/firmware/qcom_scm-64.c
+++ b/drivers/firmware/qcom_scm-64.c
@@ -12,7 +12,150 @@
 
 #include <linux/io.h>
 #include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/types.h>
 #include <linux/qcom_scm.h>
+#include <linux/arm-smccc.h>
+#include <linux/dma-mapping.h>
+
+#include "qcom_scm.h"
+
+#define QCOM_SCM_FNID(s, c) ((((s) & 0xFF) << 8) | ((c) & 0xFF))
+
+#define MAX_QCOM_SCM_ARGS 10
+#define MAX_QCOM_SCM_RETS 3
+
+enum qcom_scm_arg_types {
+	QCOM_SCM_VAL,
+	QCOM_SCM_RO,
+	QCOM_SCM_RW,
+	QCOM_SCM_BUFVAL,
+};
+
+#define QCOM_SCM_ARGS_IMPL(num, a, b, c, d, e, f, g, h, i, j, ...) (\
+			   (((a) & 0x3) << 4) | \
+			   (((b) & 0x3) << 6) | \
+			   (((c) & 0x3) << 8) | \
+			   (((d) & 0x3) << 10) | \
+			   (((e) & 0x3) << 12) | \
+			   (((f) & 0x3) << 14) | \
+			   (((g) & 0x3) << 16) | \
+			   (((h) & 0x3) << 18) | \
+			   (((i) & 0x3) << 20) | \
+			   (((j) & 0x3) << 22) | \
+			   ((num) & 0xf))
+
+#define QCOM_SCM_ARGS(...) QCOM_SCM_ARGS_IMPL(__VA_ARGS__, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+
+/**
+ * struct qcom_scm_desc
+ * @arginfo:	Metadata describing the arguments in args[]
+ * @args:	The array of arguments for the secure syscall
+ * @res:	The values returned by the secure syscall
+ */
+struct qcom_scm_desc {
+	u32 arginfo;
+	u64 args[MAX_QCOM_SCM_ARGS];
+};
+
+static u64 qcom_smccc_convention = -1;
+static DEFINE_MUTEX(qcom_scm_lock);
+
+#define QCOM_SCM_EBUSY_WAIT_MS 30
+#define QCOM_SCM_EBUSY_MAX_RETRY 20
+
+#define N_EXT_QCOM_SCM_ARGS 7
+#define FIRST_EXT_ARG_IDX 3
+#define N_REGISTER_ARGS (MAX_QCOM_SCM_ARGS - N_EXT_QCOM_SCM_ARGS + 1)
+
+/**
+ * qcom_scm_call() - Invoke a syscall in the secure world
+ * @dev:	device
+ * @svc_id:	service identifier
+ * @cmd_id:	command identifier
+ * @desc:	Descriptor structure containing arguments and return values
+ *
+ * Sends a command to the SCM and waits for the command to finish processing.
+ * This should *only* be called in pre-emptible context.
+*/
+static int qcom_scm_call(struct device *dev, u32 svc_id, u32 cmd_id,
+			 const struct qcom_scm_desc *desc,
+			 struct arm_smccc_res *res)
+{
+	int arglen = desc->arginfo & 0xf;
+	int retry_count = 0, i;
+	u32 fn_id = QCOM_SCM_FNID(svc_id, cmd_id);
+	u64 cmd, x5 = desc->args[FIRST_EXT_ARG_IDX];
+	dma_addr_t args_phys = 0;
+	void *args_virt = NULL;
+	size_t alloc_len;
+
+	if (unlikely(arglen > N_REGISTER_ARGS)) {
+		alloc_len = N_EXT_QCOM_SCM_ARGS * sizeof(u64);
+		args_virt = kzalloc(PAGE_ALIGN(alloc_len), GFP_KERNEL);
+
+		if (!args_virt)
+			return -ENOMEM;
+
+		if (qcom_smccc_convention == ARM_SMCCC_SMC_32) {
+			__le32 *args = args_virt;
+
+			for (i = 0; i < N_EXT_QCOM_SCM_ARGS; i++)
+				args[i] = cpu_to_le32(desc->args[i +
+						      FIRST_EXT_ARG_IDX]);
+		} else {
+			__le64 *args = args_virt;
+
+			for (i = 0; i < N_EXT_QCOM_SCM_ARGS; i++)
+				args[i] = cpu_to_le64(desc->args[i +
+						      FIRST_EXT_ARG_IDX]);
+		}
+
+		args_phys = dma_map_single(dev, args_virt, alloc_len,
+					   DMA_TO_DEVICE);
+
+		if (dma_mapping_error(dev, args_phys)) {
+			kfree(args_virt);
+			return -ENOMEM;
+		}
+
+		x5 = args_phys;
+	}
+
+	do {
+		mutex_lock(&qcom_scm_lock);
+
+		cmd = ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL,
+					 qcom_smccc_convention,
+					 ARM_SMCCC_OWNER_SIP, fn_id);
+
+		do {
+			arm_smccc_smc(cmd, desc->arginfo, desc->args[0],
+				      desc->args[1], desc->args[2], x5, 0, 0,
+				      res);
+		} while (res->a0 == QCOM_SCM_INTERRUPTED);
+
+		mutex_unlock(&qcom_scm_lock);
+
+		if (res->a0 == QCOM_SCM_V2_EBUSY) {
+			if (retry_count++ > QCOM_SCM_EBUSY_MAX_RETRY)
+				break;
+			msleep(QCOM_SCM_EBUSY_WAIT_MS);
+		}
+	}  while (res->a0 == QCOM_SCM_V2_EBUSY);
+
+	if (args_virt) {
+		dma_unmap_single(dev, args_phys, alloc_len, DMA_TO_DEVICE);
+		kfree(args_virt);
+	}
+
+	if (res->a0 < 0)
+		return qcom_scm_remap_error(res->a0);
+
+	return 0;
+}
 
 /**
  * qcom_scm_set_cold_boot_addr() - Set the cold boot address for cpus
@@ -29,13 +172,15 @@ int __qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus)
 
 /**
  * qcom_scm_set_warm_boot_addr() - Set the warm boot address for cpus
+ * @dev: Device pointer
  * @entry: Entry point function for the cpus
  * @cpus: The cpumask of cpus that will use the entry point
  *
  * Set the Linux entry point for the SCM to transfer control to when coming
  * out of a power down. CPU power down may be executed on cpuidle or hotplug.
  */
-int __qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus)
+int __qcom_scm_set_warm_boot_addr(struct device *dev, void *entry,
+				  const cpumask_t *cpus)
 {
 	return -ENOTSUPP;
 }
@@ -52,12 +197,164 @@ void __qcom_scm_cpu_power_down(u32 flags)
 {
 }
 
-int __qcom_scm_is_call_available(u32 svc_id, u32 cmd_id)
+int __qcom_scm_is_call_available(struct device *dev, u32 svc_id, u32 cmd_id)
 {
-	return -ENOTSUPP;
+	int ret;
+	struct qcom_scm_desc desc = {0};
+	struct arm_smccc_res res;
+
+	desc.arginfo = QCOM_SCM_ARGS(1);
+	desc.args[0] = QCOM_SCM_FNID(svc_id, cmd_id) |
+			(ARM_SMCCC_OWNER_SIP << ARM_SMCCC_OWNER_SHIFT);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_INFO, QCOM_IS_CALL_AVAIL_CMD,
+			    &desc, &res);
+
+	return ret ? : res.a1;
 }
 
-int __qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp)
+int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req,
+			u32 req_cnt, u32 *resp)
 {
-	return -ENOTSUPP;
+	int ret;
+	struct qcom_scm_desc desc = {0};
+	struct arm_smccc_res res;
+
+	if (req_cnt > QCOM_SCM_HDCP_MAX_REQ_CNT)
+		return -ERANGE;
+
+	desc.args[0] = req[0].addr;
+	desc.args[1] = req[0].val;
+	desc.args[2] = req[1].addr;
+	desc.args[3] = req[1].val;
+	desc.args[4] = req[2].addr;
+	desc.args[5] = req[2].val;
+	desc.args[6] = req[3].addr;
+	desc.args[7] = req[3].val;
+	desc.args[8] = req[4].addr;
+	desc.args[9] = req[4].val;
+	desc.arginfo = QCOM_SCM_ARGS(10);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_HDCP, QCOM_SCM_CMD_HDCP, &desc,
+			    &res);
+	*resp = res.a1;
+
+	return ret;
+}
+
+void __qcom_scm_init(void)
+{
+	u64 cmd;
+	struct arm_smccc_res res;
+	u32 function = QCOM_SCM_FNID(QCOM_SCM_SVC_INFO, QCOM_IS_CALL_AVAIL_CMD);
+
+	/* First try a SMC64 call */
+	cmd = ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64,
+				 ARM_SMCCC_OWNER_SIP, function);
+
+	arm_smccc_smc(cmd, QCOM_SCM_ARGS(1), cmd & (~BIT(ARM_SMCCC_TYPE_SHIFT)),
+		      0, 0, 0, 0, 0, &res);
+
+	if (!res.a0 && res.a1)
+		qcom_smccc_convention = ARM_SMCCC_SMC_64;
+	else
+		qcom_smccc_convention = ARM_SMCCC_SMC_32;
+}
+
+bool __qcom_scm_pas_supported(struct device *dev, u32 peripheral)
+{
+	int ret;
+	struct qcom_scm_desc desc = {0};
+	struct arm_smccc_res res;
+
+	desc.args[0] = peripheral;
+	desc.arginfo = QCOM_SCM_ARGS(1);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL,
+				QCOM_SCM_PAS_IS_SUPPORTED_CMD,
+				&desc, &res);
+
+	return ret ? false : !!res.a1;
+}
+
+int __qcom_scm_pas_init_image(struct device *dev, u32 peripheral,
+			      dma_addr_t metadata_phys)
+{
+	int ret;
+	struct qcom_scm_desc desc = {0};
+	struct arm_smccc_res res;
+
+	desc.args[0] = peripheral;
+	desc.args[1] = metadata_phys;
+	desc.arginfo = QCOM_SCM_ARGS(2, QCOM_SCM_VAL, QCOM_SCM_RW);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL, QCOM_SCM_PAS_INIT_IMAGE_CMD,
+				&desc, &res);
+
+	return ret ? : res.a1;
+}
+
+int __qcom_scm_pas_mem_setup(struct device *dev, u32 peripheral,
+			      phys_addr_t addr, phys_addr_t size)
+{
+	int ret;
+	struct qcom_scm_desc desc = {0};
+	struct arm_smccc_res res;
+
+	desc.args[0] = peripheral;
+	desc.args[1] = addr;
+	desc.args[2] = size;
+	desc.arginfo = QCOM_SCM_ARGS(3);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL, QCOM_SCM_PAS_MEM_SETUP_CMD,
+				&desc, &res);
+
+	return ret ? : res.a1;
+}
+
+int __qcom_scm_pas_auth_and_reset(struct device *dev, u32 peripheral)
+{
+	int ret;
+	struct qcom_scm_desc desc = {0};
+	struct arm_smccc_res res;
+
+	desc.args[0] = peripheral;
+	desc.arginfo = QCOM_SCM_ARGS(1);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL,
+				QCOM_SCM_PAS_AUTH_AND_RESET_CMD,
+				&desc, &res);
+
+	return ret ? : res.a1;
+}
+
+int __qcom_scm_pas_shutdown(struct device *dev, u32 peripheral)
+{
+	int ret;
+	struct qcom_scm_desc desc = {0};
+	struct arm_smccc_res res;
+
+	desc.args[0] = peripheral;
+	desc.arginfo = QCOM_SCM_ARGS(1);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL, QCOM_SCM_PAS_SHUTDOWN_CMD,
+			&desc, &res);
+
+	return ret ? : res.a1;
+}
+
+int __qcom_scm_pas_mss_reset(struct device *dev, bool reset)
+{
+	struct qcom_scm_desc desc = {0};
+	struct arm_smccc_res res;
+	int ret;
+
+	desc.args[0] = reset;
+	desc.args[1] = 0;
+	desc.arginfo = QCOM_SCM_ARGS(2);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_PIL, QCOM_SCM_PAS_MSS_RESET, &desc,
+			    &res);
+
+	return ret ? : res.a1;
 }
diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index 45c008d68891..e64a501adbf4 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -10,19 +10,64 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA.
  */
-
+#include <linux/platform_device.h>
+#include <linux/module.h>
 #include <linux/cpumask.h>
 #include <linux/export.h>
+#include <linux/dma-mapping.h>
 #include <linux/types.h>
 #include <linux/qcom_scm.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/clk.h>
+#include <linux/reset-controller.h>
 
 #include "qcom_scm.h"
 
+struct qcom_scm {
+	struct device *dev;
+	struct clk *core_clk;
+	struct clk *iface_clk;
+	struct clk *bus_clk;
+	struct reset_controller_dev reset;
+};
+
+static struct qcom_scm *__scm;
+
+static int qcom_scm_clk_enable(void)
+{
+	int ret;
+
+	ret = clk_prepare_enable(__scm->core_clk);
+	if (ret)
+		goto bail;
+
+	ret = clk_prepare_enable(__scm->iface_clk);
+	if (ret)
+		goto disable_core;
+
+	ret = clk_prepare_enable(__scm->bus_clk);
+	if (ret)
+		goto disable_iface;
+
+	return 0;
+
+disable_iface:
+	clk_disable_unprepare(__scm->iface_clk);
+disable_core:
+	clk_disable_unprepare(__scm->core_clk);
+bail:
+	return ret;
+}
+
+static void qcom_scm_clk_disable(void)
+{
+	clk_disable_unprepare(__scm->core_clk);
+	clk_disable_unprepare(__scm->iface_clk);
+	clk_disable_unprepare(__scm->bus_clk);
+}
+
 /**
  * qcom_scm_set_cold_boot_addr() - Set the cold boot address for cpus
  * @entry: Entry point function for the cpus
@@ -47,7 +92,7 @@ EXPORT_SYMBOL(qcom_scm_set_cold_boot_addr);
  */
 int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus)
 {
-	return __qcom_scm_set_warm_boot_addr(entry, cpus);
+	return __qcom_scm_set_warm_boot_addr(__scm->dev, entry, cpus);
 }
 EXPORT_SYMBOL(qcom_scm_set_warm_boot_addr);
 
@@ -72,12 +117,17 @@ EXPORT_SYMBOL(qcom_scm_cpu_power_down);
  */
 bool qcom_scm_hdcp_available(void)
 {
-	int ret;
+	int ret = qcom_scm_clk_enable();
 
-	ret = __qcom_scm_is_call_available(QCOM_SCM_SVC_HDCP,
-		QCOM_SCM_CMD_HDCP);
+	if (ret)
+		return ret;
 
-	return (ret > 0) ? true : false;
+	ret = __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_HDCP,
+						QCOM_SCM_CMD_HDCP);
+
+	qcom_scm_clk_disable();
+
+	return ret > 0 ? true : false;
 }
 EXPORT_SYMBOL(qcom_scm_hdcp_available);
 
@@ -91,6 +141,287 @@ EXPORT_SYMBOL(qcom_scm_hdcp_available);
  */
 int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp)
 {
-	return __qcom_scm_hdcp_req(req, req_cnt, resp);
+	int ret = qcom_scm_clk_enable();
+
+	if (ret)
+		return ret;
+
+	ret = __qcom_scm_hdcp_req(__scm->dev, req, req_cnt, resp);
+	qcom_scm_clk_disable();
+	return ret;
 }
 EXPORT_SYMBOL(qcom_scm_hdcp_req);
+
+/**
+ * qcom_scm_pas_supported() - Check if the peripheral authentication service is
+ *			      available for the given peripherial
+ * @peripheral:	peripheral id
+ *
+ * Returns true if PAS is supported for this peripheral, otherwise false.
+ */
+bool qcom_scm_pas_supported(u32 peripheral)
+{
+	int ret;
+
+	ret = __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_PIL,
+					   QCOM_SCM_PAS_IS_SUPPORTED_CMD);
+	if (ret <= 0)
+		return false;
+
+	return __qcom_scm_pas_supported(__scm->dev, peripheral);
+}
+EXPORT_SYMBOL(qcom_scm_pas_supported);
+
+/**
+ * qcom_scm_pas_init_image() - Initialize peripheral authentication service
+ *			       state machine for a given peripheral, using the
+ *			       metadata
+ * @peripheral: peripheral id
+ * @metadata:	pointer to memory containing ELF header, program header table
+ *		and optional blob of data used for authenticating the metadata
+ *		and the rest of the firmware
+ * @size:	size of the metadata
+ *
+ * Returns 0 on success.
+ */
+int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, size_t size)
+{
+	dma_addr_t mdata_phys;
+	void *mdata_buf;
+	int ret;
+
+	/*
+	 * During the scm call memory protection will be enabled for the meta
+	 * data blob, so make sure it's physically contiguous, 4K aligned and
+	 * non-cachable to avoid XPU violations.
+	 */
+	mdata_buf = dma_alloc_coherent(__scm->dev, size, &mdata_phys,
+				       GFP_KERNEL);
+	if (!mdata_buf) {
+		dev_err(__scm->dev, "Allocation of metadata buffer failed.\n");
+		return -ENOMEM;
+	}
+	memcpy(mdata_buf, metadata, size);
+
+	ret = qcom_scm_clk_enable();
+	if (ret)
+		goto free_metadata;
+
+	ret = __qcom_scm_pas_init_image(__scm->dev, peripheral, mdata_phys);
+
+	qcom_scm_clk_disable();
+
+free_metadata:
+	dma_free_coherent(__scm->dev, size, mdata_buf, mdata_phys);
+
+	return ret;
+}
+EXPORT_SYMBOL(qcom_scm_pas_init_image);
+
+/**
+ * qcom_scm_pas_mem_setup() - Prepare the memory related to a given peripheral
+ *			      for firmware loading
+ * @peripheral:	peripheral id
+ * @addr:	start address of memory area to prepare
+ * @size:	size of the memory area to prepare
+ *
+ * Returns 0 on success.
+ */
+int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, phys_addr_t size)
+{
+	int ret;
+
+	ret = qcom_scm_clk_enable();
+	if (ret)
+		return ret;
+
+	ret = __qcom_scm_pas_mem_setup(__scm->dev, peripheral, addr, size);
+	qcom_scm_clk_disable();
+
+	return ret;
+}
+EXPORT_SYMBOL(qcom_scm_pas_mem_setup);
+
+/**
+ * qcom_scm_pas_auth_and_reset() - Authenticate the given peripheral firmware
+ *				   and reset the remote processor
+ * @peripheral:	peripheral id
+ *
+ * Return 0 on success.
+ */
+int qcom_scm_pas_auth_and_reset(u32 peripheral)
+{
+	int ret;
+
+	ret = qcom_scm_clk_enable();
+	if (ret)
+		return ret;
+
+	ret = __qcom_scm_pas_auth_and_reset(__scm->dev, peripheral);
+	qcom_scm_clk_disable();
+
+	return ret;
+}
+EXPORT_SYMBOL(qcom_scm_pas_auth_and_reset);
+
+/**
+ * qcom_scm_pas_shutdown() - Shut down the remote processor
+ * @peripheral: peripheral id
+ *
+ * Returns 0 on success.
+ */
+int qcom_scm_pas_shutdown(u32 peripheral)
+{
+	int ret;
+
+	ret = qcom_scm_clk_enable();
+	if (ret)
+		return ret;
+
+	ret = __qcom_scm_pas_shutdown(__scm->dev, peripheral);
+	qcom_scm_clk_disable();
+
+	return ret;
+}
+EXPORT_SYMBOL(qcom_scm_pas_shutdown);
+
+static int qcom_scm_pas_reset_assert(struct reset_controller_dev *rcdev,
+				     unsigned long idx)
+{
+	if (idx != 0)
+		return -EINVAL;
+
+	return __qcom_scm_pas_mss_reset(__scm->dev, 1);
+}
+
+static int qcom_scm_pas_reset_deassert(struct reset_controller_dev *rcdev,
+				       unsigned long idx)
+{
+	if (idx != 0)
+		return -EINVAL;
+
+	return __qcom_scm_pas_mss_reset(__scm->dev, 0);
+}
+
+static const struct reset_control_ops qcom_scm_pas_reset_ops = {
+	.assert = qcom_scm_pas_reset_assert,
+	.deassert = qcom_scm_pas_reset_deassert,
+};
+
+/**
+ * qcom_scm_is_available() - Checks if SCM is available
+ */
+bool qcom_scm_is_available(void)
+{
+	return !!__scm;
+}
+EXPORT_SYMBOL(qcom_scm_is_available);
+
+static int qcom_scm_probe(struct platform_device *pdev)
+{
+	struct qcom_scm *scm;
+	int ret;
+
+	scm = devm_kzalloc(&pdev->dev, sizeof(*scm), GFP_KERNEL);
+	if (!scm)
+		return -ENOMEM;
+
+	scm->core_clk = devm_clk_get(&pdev->dev, "core");
+	if (IS_ERR(scm->core_clk)) {
+		if (PTR_ERR(scm->core_clk) == -EPROBE_DEFER)
+			return PTR_ERR(scm->core_clk);
+
+		scm->core_clk = NULL;
+	}
+
+	if (of_device_is_compatible(pdev->dev.of_node, "qcom,scm")) {
+		scm->iface_clk = devm_clk_get(&pdev->dev, "iface");
+		if (IS_ERR(scm->iface_clk)) {
+			if (PTR_ERR(scm->iface_clk) != -EPROBE_DEFER)
+				dev_err(&pdev->dev, "failed to acquire iface clk\n");
+			return PTR_ERR(scm->iface_clk);
+		}
+
+		scm->bus_clk = devm_clk_get(&pdev->dev, "bus");
+		if (IS_ERR(scm->bus_clk)) {
+			if (PTR_ERR(scm->bus_clk) != -EPROBE_DEFER)
+				dev_err(&pdev->dev, "failed to acquire bus clk\n");
+			return PTR_ERR(scm->bus_clk);
+		}
+	}
+
+	scm->reset.ops = &qcom_scm_pas_reset_ops;
+	scm->reset.nr_resets = 1;
+	scm->reset.of_node = pdev->dev.of_node;
+	reset_controller_register(&scm->reset);
+
+	/* vote for max clk rate for highest performance */
+	ret = clk_set_rate(scm->core_clk, INT_MAX);
+	if (ret)
+		return ret;
+
+	__scm = scm;
+	__scm->dev = &pdev->dev;
+
+	__qcom_scm_init();
+
+	return 0;
+}
+
+static const struct of_device_id qcom_scm_dt_match[] = {
+	{ .compatible = "qcom,scm-apq8064",},
+	{ .compatible = "qcom,scm-msm8660",},
+	{ .compatible = "qcom,scm-msm8960",},
+	{ .compatible = "qcom,scm",},
+	{}
+};
+
+MODULE_DEVICE_TABLE(of, qcom_scm_dt_match);
+
+static struct platform_driver qcom_scm_driver = {
+	.driver = {
+		.name	= "qcom_scm",
+		.of_match_table = qcom_scm_dt_match,
+	},
+	.probe = qcom_scm_probe,
+};
+
+static int __init qcom_scm_init(void)
+{
+	struct device_node *np, *fw_np;
+	int ret;
+
+	fw_np = of_find_node_by_name(NULL, "firmware");
+
+	if (!fw_np)
+		return -ENODEV;
+
+	np = of_find_matching_node(fw_np, qcom_scm_dt_match);
+
+	if (!np) {
+		of_node_put(fw_np);
+		return -ENODEV;
+	}
+
+	of_node_put(np);
+
+	ret = of_platform_populate(fw_np, qcom_scm_dt_match, NULL, NULL);
+
+	of_node_put(fw_np);
+
+	if (ret)
+		return ret;
+
+	return platform_driver_register(&qcom_scm_driver);
+}
+
+subsys_initcall(qcom_scm_init);
+
+static void __exit qcom_scm_exit(void)
+{
+	platform_driver_unregister(&qcom_scm_driver);
+}
+module_exit(qcom_scm_exit);
+
+MODULE_DESCRIPTION("Qualcomm SCM driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h
index 2cce75c08b99..3584b00fe7e6 100644
--- a/drivers/firmware/qcom_scm.h
+++ b/drivers/firmware/qcom_scm.h
@@ -19,7 +19,8 @@
 #define QCOM_SCM_FLAG_HLOS		0x01
 #define QCOM_SCM_FLAG_COLDBOOT_MC	0x02
 #define QCOM_SCM_FLAG_WARMBOOT_MC	0x04
-extern int __qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus);
+extern int __qcom_scm_set_warm_boot_addr(struct device *dev, void *entry,
+		const cpumask_t *cpus);
 extern int __qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus);
 
 #define QCOM_SCM_CMD_TERMINATE_PC	0x2
@@ -29,14 +30,34 @@ extern void __qcom_scm_cpu_power_down(u32 flags);
 
 #define QCOM_SCM_SVC_INFO		0x6
 #define QCOM_IS_CALL_AVAIL_CMD		0x1
-extern int __qcom_scm_is_call_available(u32 svc_id, u32 cmd_id);
+extern int __qcom_scm_is_call_available(struct device *dev, u32 svc_id,
+		u32 cmd_id);
 
 #define QCOM_SCM_SVC_HDCP		0x11
 #define QCOM_SCM_CMD_HDCP		0x01
-extern int __qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt,
-		u32 *resp);
+extern int __qcom_scm_hdcp_req(struct device *dev,
+		struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp);
+
+extern void __qcom_scm_init(void);
+
+#define QCOM_SCM_SVC_PIL		0x2
+#define QCOM_SCM_PAS_INIT_IMAGE_CMD	0x1
+#define QCOM_SCM_PAS_MEM_SETUP_CMD	0x2
+#define QCOM_SCM_PAS_AUTH_AND_RESET_CMD	0x5
+#define QCOM_SCM_PAS_SHUTDOWN_CMD	0x6
+#define QCOM_SCM_PAS_IS_SUPPORTED_CMD	0x7
+#define QCOM_SCM_PAS_MSS_RESET		0xa
+extern bool __qcom_scm_pas_supported(struct device *dev, u32 peripheral);
+extern int  __qcom_scm_pas_init_image(struct device *dev, u32 peripheral,
+		dma_addr_t metadata_phys);
+extern int  __qcom_scm_pas_mem_setup(struct device *dev, u32 peripheral,
+		phys_addr_t addr, phys_addr_t size);
+extern int  __qcom_scm_pas_auth_and_reset(struct device *dev, u32 peripheral);
+extern int  __qcom_scm_pas_shutdown(struct device *dev, u32 peripheral);
+extern int  __qcom_scm_pas_mss_reset(struct device *dev, bool reset);
 
 /* common error codes */
+#define QCOM_SCM_V2_EBUSY	-12
 #define QCOM_SCM_ENOMEM		-5
 #define QCOM_SCM_EOPNOTSUPP	-4
 #define QCOM_SCM_EINVAL_ADDR	-3
@@ -44,4 +65,22 @@ extern int __qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt,
 #define QCOM_SCM_ERROR		-1
 #define QCOM_SCM_INTERRUPTED	1
 
+static inline int qcom_scm_remap_error(int err)
+{
+	switch (err) {
+	case QCOM_SCM_ERROR:
+		return -EIO;
+	case QCOM_SCM_EINVAL_ADDR:
+	case QCOM_SCM_EINVAL_ARG:
+		return -EINVAL;
+	case QCOM_SCM_EOPNOTSUPP:
+		return -EOPNOTSUPP;
+	case QCOM_SCM_ENOMEM:
+		return -ENOMEM;
+	case QCOM_SCM_V2_EBUSY:
+		return -EBUSY;
+	}
+	return -EINVAL;
+}
+
 #endif
diff --git a/drivers/firmware/scpi_pm_domain.c b/drivers/firmware/scpi_pm_domain.c
new file mode 100644
index 000000000000..f395dec27113
--- /dev/null
+++ b/drivers/firmware/scpi_pm_domain.c
@@ -0,0 +1,163 @@
+/*
+ * SCPI Generic power domain support.
+ *
+ * Copyright (C) 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/pm_domain.h>
+#include <linux/scpi_protocol.h>
+
+struct scpi_pm_domain {
+	struct generic_pm_domain genpd;
+	struct scpi_ops *ops;
+	u32 domain;
+	char name[30];
+};
+
+/*
+ * These device power state values are not well-defined in the specification.
+ * In case, different implementations use different values, we can make these
+ * specific to compatibles rather than getting these values from device tree.
+ */
+enum scpi_power_domain_state {
+	SCPI_PD_STATE_ON = 0,
+	SCPI_PD_STATE_OFF = 3,
+};
+
+#define to_scpi_pd(gpd) container_of(gpd, struct scpi_pm_domain, genpd)
+
+static int scpi_pd_power(struct scpi_pm_domain *pd, bool power_on)
+{
+	int ret;
+	enum scpi_power_domain_state state;
+
+	if (power_on)
+		state = SCPI_PD_STATE_ON;
+	else
+		state = SCPI_PD_STATE_OFF;
+
+	ret = pd->ops->device_set_power_state(pd->domain, state);
+	if (ret)
+		return ret;
+
+	return !(state == pd->ops->device_get_power_state(pd->domain));
+}
+
+static int scpi_pd_power_on(struct generic_pm_domain *domain)
+{
+	struct scpi_pm_domain *pd = to_scpi_pd(domain);
+
+	return scpi_pd_power(pd, true);
+}
+
+static int scpi_pd_power_off(struct generic_pm_domain *domain)
+{
+	struct scpi_pm_domain *pd = to_scpi_pd(domain);
+
+	return scpi_pd_power(pd, false);
+}
+
+static int scpi_pm_domain_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct scpi_pm_domain *scpi_pd;
+	struct genpd_onecell_data *scpi_pd_data;
+	struct generic_pm_domain **domains;
+	struct scpi_ops *scpi_ops;
+	int ret, num_domains, i;
+
+	scpi_ops = get_scpi_ops();
+	if (!scpi_ops)
+		return -EPROBE_DEFER;
+
+	if (!np) {
+		dev_err(dev, "device tree node not found\n");
+		return -ENODEV;
+	}
+
+	if (!scpi_ops->device_set_power_state ||
+	    !scpi_ops->device_get_power_state) {
+		dev_err(dev, "power domains not supported in the firmware\n");
+		return -ENODEV;
+	}
+
+	ret = of_property_read_u32(np, "num-domains", &num_domains);
+	if (ret) {
+		dev_err(dev, "number of domains not found\n");
+		return -EINVAL;
+	}
+
+	scpi_pd = devm_kcalloc(dev, num_domains, sizeof(*scpi_pd), GFP_KERNEL);
+	if (!scpi_pd)
+		return -ENOMEM;
+
+	scpi_pd_data = devm_kzalloc(dev, sizeof(*scpi_pd_data), GFP_KERNEL);
+	if (!scpi_pd_data)
+		return -ENOMEM;
+
+	domains = devm_kcalloc(dev, num_domains, sizeof(*domains), GFP_KERNEL);
+	if (!domains)
+		return -ENOMEM;
+
+	for (i = 0; i < num_domains; i++, scpi_pd++) {
+		domains[i] = &scpi_pd->genpd;
+
+		scpi_pd->domain = i;
+		scpi_pd->ops = scpi_ops;
+		sprintf(scpi_pd->name, "%s.%d", np->name, i);
+		scpi_pd->genpd.name = scpi_pd->name;
+		scpi_pd->genpd.power_off = scpi_pd_power_off;
+		scpi_pd->genpd.power_on = scpi_pd_power_on;
+
+		/*
+		 * Treat all power domains as off at boot.
+		 *
+		 * The SCP firmware itself may have switched on some domains,
+		 * but for reference counting purpose, keep it this way.
+		 */
+		pm_genpd_init(&scpi_pd->genpd, NULL, true);
+	}
+
+	scpi_pd_data->domains = domains;
+	scpi_pd_data->num_domains = num_domains;
+
+	of_genpd_add_provider_onecell(np, scpi_pd_data);
+
+	return 0;
+}
+
+static const struct of_device_id scpi_power_domain_ids[] = {
+	{ .compatible = "arm,scpi-power-domains", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, scpi_power_domain_ids);
+
+static struct platform_driver scpi_power_domain_driver = {
+	.driver	= {
+		.name = "scpi_power_domain",
+		.of_match_table = scpi_power_domain_ids,
+	},
+	.probe = scpi_pm_domain_probe,
+};
+module_platform_driver(scpi_power_domain_driver);
+
+MODULE_AUTHOR("Sudeep Holla <sudeep.holla@arm.com>");
+MODULE_DESCRIPTION("ARM SCPI power domain driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index be43afb08c69..e3dba6f44a79 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -8,7 +8,7 @@ drm-y       :=	drm_auth.o drm_bufs.o drm_cache.o \
 		drm_lock.o drm_memory.o drm_drv.o drm_vm.o \
 		drm_scatter.o drm_pci.o \
 		drm_platform.o drm_sysfs.o drm_hashtab.o drm_mm.o \
-		drm_crtc.o drm_modes.o drm_edid.o \
+		drm_crtc.o drm_fourcc.o drm_modes.o drm_edid.o \
 		drm_info.o drm_debugfs.o drm_encoder_slave.o \
 		drm_trace_points.o drm_global.o drm_prime.o \
 		drm_rect.o drm_vma_manager.o drm_flip_work.o \
@@ -23,7 +23,8 @@ drm-$(CONFIG_AGP) += drm_agpsupport.o
 
 drm_kms_helper-y := drm_crtc_helper.o drm_dp_helper.o drm_probe_helper.o \
 		drm_plane_helper.o drm_dp_mst_topology.o drm_atomic_helper.o \
-		drm_kms_helper_common.o drm_dp_dual_mode_helper.o
+		drm_kms_helper_common.o drm_dp_dual_mode_helper.o \
+		drm_simple_kms_helper.o
 
 drm_kms_helper-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o
 drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fb_helper.o
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index e055d5be1c3c..8ebc5f1eb4c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -85,8 +85,12 @@ extern int amdgpu_vm_debug;
 extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
 extern int amdgpu_powerplay;
+extern int amdgpu_powercontainment;
 extern unsigned amdgpu_pcie_gen_cap;
 extern unsigned amdgpu_pcie_lane_cap;
+extern unsigned amdgpu_cg_mask;
+extern unsigned amdgpu_pg_mask;
+extern char *amdgpu_disable_cu;
 
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
 #define AMDGPU_MAX_USEC_TIMEOUT			100000	/* 100 ms */
@@ -183,6 +187,10 @@ int amdgpu_set_clockgating_state(struct amdgpu_device *adev,
 int amdgpu_set_powergating_state(struct amdgpu_device *adev,
 				  enum amd_ip_block_type block_type,
 				  enum amd_powergating_state state);
+int amdgpu_wait_for_idle(struct amdgpu_device *adev,
+			 enum amd_ip_block_type block_type);
+bool amdgpu_is_idle(struct amdgpu_device *adev,
+		    enum amd_ip_block_type block_type);
 
 struct amdgpu_ip_block_version {
 	enum amd_ip_block_type type;
@@ -298,13 +306,16 @@ struct amdgpu_ring_funcs {
 				uint32_t oa_base, uint32_t oa_size);
 	/* testing functions */
 	int (*test_ring)(struct amdgpu_ring *ring);
-	int (*test_ib)(struct amdgpu_ring *ring);
+	int (*test_ib)(struct amdgpu_ring *ring, long timeout);
 	/* insert NOP packets */
 	void (*insert_nop)(struct amdgpu_ring *ring, uint32_t count);
 	/* pad the indirect buffer to the necessary number of dw */
 	void (*pad_ib)(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
 	unsigned (*init_cond_exec)(struct amdgpu_ring *ring);
 	void (*patch_cond_exec)(struct amdgpu_ring *ring, unsigned offset);
+	/* note usage for clock and power gating */
+	void (*begin_use)(struct amdgpu_ring *ring);
+	void (*end_use)(struct amdgpu_ring *ring);
 };
 
 /*
@@ -594,11 +605,9 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 		     struct amdgpu_sync *sync,
 		     struct reservation_object *resv,
 		     void *owner);
-bool amdgpu_sync_is_idle(struct amdgpu_sync *sync);
-int amdgpu_sync_cycle_fences(struct amdgpu_sync *dst, struct amdgpu_sync *src,
-			     struct fence *fence);
+struct fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync,
+				     struct amdgpu_ring *ring);
 struct fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync);
-int amdgpu_sync_wait(struct amdgpu_sync *sync);
 void amdgpu_sync_free(struct amdgpu_sync *sync);
 int amdgpu_sync_init(void);
 void amdgpu_sync_fini(void);
@@ -754,12 +763,11 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
 			     struct amdgpu_job **job);
 
+void amdgpu_job_free_resources(struct amdgpu_job *job);
 void amdgpu_job_free(struct amdgpu_job *job);
-void amdgpu_job_free_func(struct kref *refcount);
 int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 		      struct amd_sched_entity *entity, void *owner,
 		      struct fence **f);
-void amdgpu_job_timeout_func(struct work_struct *work);
 
 struct amdgpu_ring {
 	struct amdgpu_device		*adev;
@@ -767,12 +775,9 @@ struct amdgpu_ring {
 	struct amdgpu_fence_driver	fence_drv;
 	struct amd_gpu_scheduler	sched;
 
-	spinlock_t              fence_lock;
 	struct amdgpu_bo	*ring_obj;
 	volatile uint32_t	*ring;
 	unsigned		rptr_offs;
-	u64			next_rptr_gpu_addr;
-	volatile u32		*next_rptr_cpu_addr;
 	unsigned		wptr;
 	unsigned		wptr_old;
 	unsigned		ring_size;
@@ -791,14 +796,16 @@ struct amdgpu_ring {
 	u32			doorbell_index;
 	bool			use_doorbell;
 	unsigned		wptr_offs;
-	unsigned		next_rptr_offs;
 	unsigned		fence_offs;
 	uint64_t		current_ctx;
 	enum amdgpu_ring_type	type;
 	char			name[16];
 	unsigned		cond_exe_offs;
-	u64				cond_exe_gpu_addr;
-	volatile u32	*cond_exe_cpu_addr;
+	u64			cond_exe_gpu_addr;
+	volatile u32		*cond_exe_cpu_addr;
+#if defined(CONFIG_DEBUG_FS)
+	struct dentry *ent;
+#endif
 };
 
 /*
@@ -861,6 +868,7 @@ struct amdgpu_vm {
 	struct amdgpu_bo	*page_directory;
 	unsigned		max_pde_used;
 	struct fence		*page_directory_fence;
+	uint64_t		last_eviction_counter;
 
 	/* array of page tables, one for each page directory entry */
 	struct amdgpu_vm_pt	*page_tables;
@@ -883,13 +891,14 @@ struct amdgpu_vm_id {
 	struct fence		*first;
 	struct amdgpu_sync	active;
 	struct fence		*last_flush;
-	struct amdgpu_ring      *last_user;
 	atomic64_t		owner;
 
 	uint64_t		pd_gpu_addr;
 	/* last flushed PD/PT update */
 	struct fence		*flushed_updates;
 
+	uint32_t                current_gpu_reset_count;
+
 	uint32_t		gds_base;
 	uint32_t		gds_size;
 	uint32_t		gws_base;
@@ -905,6 +914,10 @@ struct amdgpu_vm_manager {
 	struct list_head			ids_lru;
 	struct amdgpu_vm_id			ids[AMDGPU_NUM_VM];
 
+	/* Handling of VM fences */
+	u64					fence_context;
+	unsigned				seqno[AMDGPU_MAX_RINGS];
+
 	uint32_t				max_pfn;
 	/* vram base address for page table entry  */
 	u64					vram_base_offset;
@@ -926,17 +939,14 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 			 struct list_head *validated,
 			 struct amdgpu_bo_list_entry *entry);
-void amdgpu_vm_get_pt_bos(struct amdgpu_vm *vm, struct list_head *duplicates);
+void amdgpu_vm_get_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			  struct list_head *duplicates);
 void amdgpu_vm_move_pt_bos_in_lru(struct amdgpu_device *adev,
 				  struct amdgpu_vm *vm);
 int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 		      struct amdgpu_sync *sync, struct fence *fence,
-		      unsigned *vm_id, uint64_t *vm_pd_addr);
-int amdgpu_vm_flush(struct amdgpu_ring *ring,
-		    unsigned vm_id, uint64_t pd_addr,
-		    uint32_t gds_base, uint32_t gds_size,
-		    uint32_t gws_base, uint32_t gws_size,
-		    uint32_t oa_base, uint32_t oa_size);
+		      struct amdgpu_job *job);
+int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job);
 void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vm_id);
 uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr);
 int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
@@ -1142,6 +1152,12 @@ struct amdgpu_cu_info {
 	uint32_t bitmap[4][4];
 };
 
+struct amdgpu_gfx_funcs {
+	/* get the gpu clock counter */
+	uint64_t (*get_gpu_clock_counter)(struct amdgpu_device *adev);
+	void (*select_se_sh)(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 instance);
+};
+
 struct amdgpu_gfx {
 	struct mutex			gpu_clock_mutex;
 	struct amdgpu_gca_config	config;
@@ -1178,6 +1194,7 @@ struct amdgpu_gfx {
 	/* ce ram size*/
 	unsigned			ce_ram_size;
 	struct amdgpu_cu_info		cu_info;
+	const struct amdgpu_gfx_funcs	*funcs;
 };
 
 int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
@@ -1195,10 +1212,6 @@ void amdgpu_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count);
 void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
 void amdgpu_ring_commit(struct amdgpu_ring *ring);
 void amdgpu_ring_undo(struct amdgpu_ring *ring);
-unsigned amdgpu_ring_backup(struct amdgpu_ring *ring,
-			    uint32_t **data);
-int amdgpu_ring_restore(struct amdgpu_ring *ring,
-			unsigned size, uint32_t *data);
 int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		     unsigned ring_size, u32 nop, u32 align_mask,
 		     struct amdgpu_irq_src *irq_src, unsigned irq_type,
@@ -1250,6 +1263,7 @@ struct amdgpu_job {
 	uint32_t		num_ibs;
 	void			*owner;
 	uint64_t		ctx;
+	bool                    vm_needs_flush;
 	unsigned		vm_id;
 	uint64_t		vm_pd_addr;
 	uint32_t		gds_base, gds_size;
@@ -1257,8 +1271,7 @@ struct amdgpu_job {
 	uint32_t		oa_base, oa_size;
 
 	/* user fence handling */
-	struct amdgpu_bo	*uf_bo;
-	uint32_t		uf_offset;
+	uint64_t		uf_addr;
 	uint64_t		uf_sequence;
 
 };
@@ -1560,6 +1573,12 @@ struct amdgpu_dpm_funcs {
 	u32 (*get_fan_control_mode)(struct amdgpu_device *adev);
 	int (*set_fan_speed_percent)(struct amdgpu_device *adev, u32 speed);
 	int (*get_fan_speed_percent)(struct amdgpu_device *adev, u32 *speed);
+	int (*force_clock_level)(struct amdgpu_device *adev, enum pp_clock_type type, uint32_t mask);
+	int (*print_clock_levels)(struct amdgpu_device *adev, enum pp_clock_type type, char *buf);
+	int (*get_sclk_od)(struct amdgpu_device *adev);
+	int (*set_sclk_od)(struct amdgpu_device *adev, uint32_t value);
+	int (*get_mclk_od)(struct amdgpu_device *adev);
+	int (*set_mclk_od)(struct amdgpu_device *adev, uint32_t value);
 };
 
 struct amdgpu_dpm {
@@ -1662,6 +1681,7 @@ struct amdgpu_uvd {
 	struct amdgpu_ring	ring;
 	struct amdgpu_irq_src	irq;
 	bool			address_64_bit;
+	bool			use_ctx_buf;
 	struct amd_sched_entity entity;
 };
 
@@ -1683,6 +1703,7 @@ struct amdgpu_vce {
 	struct drm_file		*filp[AMDGPU_MAX_VCE_HANDLES];
 	uint32_t		img_size[AMDGPU_MAX_VCE_HANDLES];
 	struct delayed_work	idle_work;
+	struct mutex		idle_mutex;
 	const struct firmware	*fw;	/* VCE firmware */
 	struct amdgpu_ring	ring[AMDGPU_MAX_VCE_RINGS];
 	struct amdgpu_irq_src	irq;
@@ -1767,6 +1788,8 @@ int amdgpu_debugfs_init(struct drm_minor *minor);
 void amdgpu_debugfs_cleanup(struct drm_minor *minor);
 #endif
 
+int amdgpu_debugfs_firmware_init(struct amdgpu_device *adev);
+
 /*
  * amdgpu smumgr functions
  */
@@ -1811,12 +1834,8 @@ struct amdgpu_asic_funcs {
 			     u32 sh_num, u32 reg_offset, u32 *value);
 	void (*set_vga_state)(struct amdgpu_device *adev, bool state);
 	int (*reset)(struct amdgpu_device *adev);
-	/* wait for mc_idle */
-	int (*wait_for_mc_idle)(struct amdgpu_device *adev);
 	/* get the reference clock */
 	u32 (*get_xclk)(struct amdgpu_device *adev);
-	/* get the gpu clock counter */
-	uint64_t (*get_gpu_clock_counter)(struct amdgpu_device *adev);
 	/* MM block clocks */
 	int (*set_uvd_clocks)(struct amdgpu_device *adev, u32 vclk, u32 dclk);
 	int (*set_vce_clocks)(struct amdgpu_device *adev, u32 evclk, u32 ecclk);
@@ -2003,6 +2022,10 @@ struct amdgpu_device {
 	spinlock_t didt_idx_lock;
 	amdgpu_rreg_t			didt_rreg;
 	amdgpu_wreg_t			didt_wreg;
+	/* protects concurrent gc_cac register access */
+	spinlock_t gc_cac_idx_lock;
+	amdgpu_rreg_t			gc_cac_rreg;
+	amdgpu_wreg_t			gc_cac_wreg;
 	/* protects concurrent ENDPOINT (audio) register access */
 	spinlock_t audio_endpt_idx_lock;
 	amdgpu_block_rreg_t		audio_endpt_rreg;
@@ -2028,6 +2051,7 @@ struct amdgpu_device {
 	atomic64_t			vram_vis_usage;
 	atomic64_t			gtt_usage;
 	atomic64_t			num_bytes_moved;
+	atomic64_t			num_evictions;
 	atomic_t			gpu_reset_counter;
 
 	/* display */
@@ -2038,7 +2062,7 @@ struct amdgpu_device {
 	struct amdgpu_irq_src		hpd_irq;
 
 	/* rings */
-	unsigned			fence_context;
+	u64				fence_context;
 	unsigned			num_rings;
 	struct amdgpu_ring		*rings[AMDGPU_MAX_RINGS];
 	bool				ib_pool_ready;
@@ -2131,6 +2155,8 @@ void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v);
 #define WREG32_UVD_CTX(reg, v) adev->uvd_ctx_wreg(adev, (reg), (v))
 #define RREG32_DIDT(reg) adev->didt_rreg(adev, (reg))
 #define WREG32_DIDT(reg, v) adev->didt_wreg(adev, (reg), (v))
+#define RREG32_GC_CAC(reg) adev->gc_cac_rreg(adev, (reg))
+#define WREG32_GC_CAC(reg, v) adev->gc_cac_wreg(adev, (reg), (v))
 #define RREG32_AUDIO_ENDPT(block, reg) adev->audio_endpt_rreg(adev, (block), (reg))
 #define WREG32_AUDIO_ENDPT(block, reg, v) adev->audio_endpt_wreg(adev, (block), (reg), (v))
 #define WREG32_P(reg, val, mask)				\
@@ -2206,12 +2232,10 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
  */
 #define amdgpu_asic_set_vga_state(adev, state) (adev)->asic_funcs->set_vga_state((adev), (state))
 #define amdgpu_asic_reset(adev) (adev)->asic_funcs->reset((adev))
-#define amdgpu_asic_wait_for_mc_idle(adev) (adev)->asic_funcs->wait_for_mc_idle((adev))
 #define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev))
 #define amdgpu_asic_set_uvd_clocks(adev, v, d) (adev)->asic_funcs->set_uvd_clocks((adev), (v), (d))
 #define amdgpu_asic_set_vce_clocks(adev, ev, ec) (adev)->asic_funcs->set_vce_clocks((adev), (ev), (ec))
 #define amdgpu_asic_get_virtual_caps(adev) ((adev)->asic_funcs->get_virtual_caps((adev)))
-#define amdgpu_asic_get_gpu_clock_counter(adev) (adev)->asic_funcs->get_gpu_clock_counter((adev))
 #define amdgpu_asic_read_disabled_bios(adev) (adev)->asic_funcs->read_disabled_bios((adev))
 #define amdgpu_asic_read_bios_from_rom(adev, b, l) (adev)->asic_funcs->read_bios_from_rom((adev), (b), (l))
 #define amdgpu_asic_read_register(adev, se, sh, offset, v)((adev)->asic_funcs->read_register((adev), (se), (sh), (offset), (v)))
@@ -2222,7 +2246,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_vm_set_pte_pde(adev, ib, pe, addr, count, incr, flags) ((adev)->vm_manager.vm_pte_funcs->set_pte_pde((ib), (pe), (addr), (count), (incr), (flags)))
 #define amdgpu_ring_parse_cs(r, p, ib) ((r)->funcs->parse_cs((p), (ib)))
 #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r))
-#define amdgpu_ring_test_ib(r) (r)->funcs->test_ib((r))
+#define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t))
 #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r))
 #define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r))
 #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r))
@@ -2264,6 +2288,8 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_dpm_print_power_state(adev, ps) (adev)->pm.funcs->print_power_state((adev), (ps))
 #define amdgpu_dpm_vblank_too_short(adev) (adev)->pm.funcs->vblank_too_short((adev))
 #define amdgpu_dpm_enable_bapm(adev, e) (adev)->pm.funcs->enable_bapm((adev), (e))
+#define amdgpu_gfx_get_gpu_clock_counter(adev) (adev)->gfx.funcs->get_gpu_clock_counter((adev))
+#define amdgpu_gfx_select_se_sh(adev, se, sh, instance) (adev)->gfx.funcs->select_se_sh((adev), (se), (sh), (instance))
 
 #define amdgpu_dpm_get_temperature(adev) \
 	((adev)->pp_enabled ?						\
@@ -2342,6 +2368,18 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_dpm_force_clock_level(adev, type, level) \
 		(adev)->powerplay.pp_funcs->force_clock_level((adev)->powerplay.pp_handle, type, level)
 
+#define amdgpu_dpm_get_sclk_od(adev) \
+	(adev)->powerplay.pp_funcs->get_sclk_od((adev)->powerplay.pp_handle)
+
+#define amdgpu_dpm_set_sclk_od(adev, value) \
+	(adev)->powerplay.pp_funcs->set_sclk_od((adev)->powerplay.pp_handle, value)
+
+#define amdgpu_dpm_get_mclk_od(adev) \
+	((adev)->powerplay.pp_funcs->get_mclk_od((adev)->powerplay.pp_handle))
+
+#define amdgpu_dpm_set_mclk_od(adev, value) \
+	((adev)->powerplay.pp_funcs->set_mclk_od((adev)->powerplay.pp_handle, value))
+
 #define amdgpu_dpm_dispatch_task(adev, event_id, input, output)		\
 	(adev)->powerplay.pp_funcs->dispatch_tasks((adev)->powerplay.pp_handle, (event_id), (input), (output))
 
@@ -2383,9 +2421,13 @@ bool amdgpu_device_is_px(struct drm_device *dev);
 #if defined(CONFIG_VGA_SWITCHEROO)
 void amdgpu_register_atpx_handler(void);
 void amdgpu_unregister_atpx_handler(void);
+bool amdgpu_has_atpx_dgpu_power_cntl(void);
+bool amdgpu_is_atpx_hybrid(void);
 #else
 static inline void amdgpu_register_atpx_handler(void) {}
 static inline void amdgpu_unregister_atpx_handler(void) {}
+static inline bool amdgpu_has_atpx_dgpu_power_cntl(void) { return false; }
+static inline bool amdgpu_is_atpx_hybrid(void) { return false; }
 #endif
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 32809f749903..d080d0807a5b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -240,8 +240,8 @@ uint64_t get_gpu_clock_counter(struct kgd_dev *kgd)
 {
 	struct amdgpu_device *rdev = (struct amdgpu_device *)kgd;
 
-	if (rdev->asic_funcs->get_gpu_clock_counter)
-		return rdev->asic_funcs->get_gpu_clock_counter(rdev);
+	if (rdev->gfx.funcs->get_gpu_clock_counter)
+		return rdev->gfx.funcs->get_gpu_clock_counter(rdev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 9df1bcb35bf0..983175363b06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -551,28 +551,19 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev)
 		    le16_to_cpu(firmware_info->info.usReferenceClock);
 		ppll->reference_div = 0;
 
-		if (crev < 2)
-			ppll->pll_out_min =
-				le16_to_cpu(firmware_info->info.usMinPixelClockPLL_Output);
-		else
-			ppll->pll_out_min =
-				le32_to_cpu(firmware_info->info_12.ulMinPixelClockPLL_Output);
+		ppll->pll_out_min =
+			le32_to_cpu(firmware_info->info_12.ulMinPixelClockPLL_Output);
 		ppll->pll_out_max =
 		    le32_to_cpu(firmware_info->info.ulMaxPixelClockPLL_Output);
 
-		if (crev >= 4) {
-			ppll->lcd_pll_out_min =
-				le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100;
-			if (ppll->lcd_pll_out_min == 0)
-				ppll->lcd_pll_out_min = ppll->pll_out_min;
-			ppll->lcd_pll_out_max =
-				le16_to_cpu(firmware_info->info_14.usLcdMaxPixelClockPLL_Output) * 100;
-			if (ppll->lcd_pll_out_max == 0)
-				ppll->lcd_pll_out_max = ppll->pll_out_max;
-		} else {
+		ppll->lcd_pll_out_min =
+			le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100;
+		if (ppll->lcd_pll_out_min == 0)
 			ppll->lcd_pll_out_min = ppll->pll_out_min;
+		ppll->lcd_pll_out_max =
+			le16_to_cpu(firmware_info->info_14.usLcdMaxPixelClockPLL_Output) * 100;
+		if (ppll->lcd_pll_out_max == 0)
 			ppll->lcd_pll_out_max = ppll->pll_out_max;
-		}
 
 		if (ppll->pll_out_min == 0)
 			ppll->pll_out_min = 64800;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index 35a1248aaa77..49de92600074 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/acpi.h>
 #include <linux/pci.h>
+#include <linux/delay.h>
 
 #include "amd_acpi.h"
 
@@ -27,6 +28,7 @@ struct amdgpu_atpx_functions {
 struct amdgpu_atpx {
 	acpi_handle handle;
 	struct amdgpu_atpx_functions functions;
+	bool is_hybrid;
 };
 
 static struct amdgpu_atpx_priv {
@@ -63,6 +65,14 @@ bool amdgpu_has_atpx(void) {
 	return amdgpu_atpx_priv.atpx_detected;
 }
 
+bool amdgpu_has_atpx_dgpu_power_cntl(void) {
+	return amdgpu_atpx_priv.atpx.functions.power_cntl;
+}
+
+bool amdgpu_is_atpx_hybrid(void) {
+	return amdgpu_atpx_priv.atpx.is_hybrid;
+}
+
 /**
  * amdgpu_atpx_call - call an ATPX method
  *
@@ -142,18 +152,12 @@ static void amdgpu_atpx_parse_functions(struct amdgpu_atpx_functions *f, u32 mas
  */
 static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx)
 {
-	/* make sure required functions are enabled */
-	/* dGPU power control is required */
-	if (atpx->functions.power_cntl == false) {
-		printk("ATPX dGPU power cntl not present, forcing\n");
-		atpx->functions.power_cntl = true;
-	}
+	u32 valid_bits = 0;
 
 	if (atpx->functions.px_params) {
 		union acpi_object *info;
 		struct atpx_px_params output;
 		size_t size;
-		u32 valid_bits;
 
 		info = amdgpu_atpx_call(atpx->handle, ATPX_FUNCTION_GET_PX_PARAMETERS, NULL);
 		if (!info)
@@ -172,19 +176,43 @@ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx)
 		memcpy(&output, info->buffer.pointer, size);
 
 		valid_bits = output.flags & output.valid_flags;
-		/* if separate mux flag is set, mux controls are required */
-		if (valid_bits & ATPX_SEPARATE_MUX_FOR_I2C) {
-			atpx->functions.i2c_mux_cntl = true;
-			atpx->functions.disp_mux_cntl = true;
-		}
-		/* if any outputs are muxed, mux controls are required */
-		if (valid_bits & (ATPX_CRT1_RGB_SIGNAL_MUXED |
-				  ATPX_TV_SIGNAL_MUXED |
-				  ATPX_DFP_SIGNAL_MUXED))
-			atpx->functions.disp_mux_cntl = true;
 
 		kfree(info);
 	}
+
+	/* if separate mux flag is set, mux controls are required */
+	if (valid_bits & ATPX_SEPARATE_MUX_FOR_I2C) {
+		atpx->functions.i2c_mux_cntl = true;
+		atpx->functions.disp_mux_cntl = true;
+	}
+	/* if any outputs are muxed, mux controls are required */
+	if (valid_bits & (ATPX_CRT1_RGB_SIGNAL_MUXED |
+			  ATPX_TV_SIGNAL_MUXED |
+			  ATPX_DFP_SIGNAL_MUXED))
+		atpx->functions.disp_mux_cntl = true;
+
+
+	/* some bioses set these bits rather than flagging power_cntl as supported */
+	if (valid_bits & (ATPX_DYNAMIC_PX_SUPPORTED |
+			  ATPX_DYNAMIC_DGPU_POWER_OFF_SUPPORTED))
+		atpx->functions.power_cntl = true;
+
+	atpx->is_hybrid = false;
+	if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) {
+		printk("ATPX Hybrid Graphics\n");
+#if 1
+		/* This is a temporary hack until the D3 cold support
+		 * makes it upstream.  The ATPX power_control method seems
+		 * to still work on even if the system should be using
+		 * the new standardized hybrid D3 cold ACPI interface.
+		 */
+		atpx->functions.power_cntl = true;
+#else
+		atpx->functions.power_cntl = false;
+#endif
+		atpx->is_hybrid = true;
+	}
+
 	return 0;
 }
 
@@ -259,6 +287,10 @@ static int amdgpu_atpx_set_discrete_state(struct amdgpu_atpx *atpx, u8 state)
 		if (!info)
 			return -EIO;
 		kfree(info);
+
+		/* 200ms delay is required after off */
+		if (state == 0)
+			msleep(200);
 	}
 	return 0;
 }
@@ -507,7 +539,6 @@ static int amdgpu_atpx_get_client_id(struct pci_dev *pdev)
 static const struct vga_switcheroo_handler amdgpu_atpx_handler = {
 	.switchto = amdgpu_atpx_switchto,
 	.power_state = amdgpu_atpx_power_state,
-	.init = amdgpu_atpx_init,
 	.get_client_id = amdgpu_atpx_get_client_id,
 };
 
@@ -542,6 +573,7 @@ static bool amdgpu_atpx_detect(void)
 		printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n",
 		       acpi_method_name);
 		amdgpu_atpx_priv.atpx_detected = true;
+		amdgpu_atpx_init();
 		return true;
 	}
 	return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index 99ca75baa47d..2b6afe123f3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -352,22 +352,22 @@ bool amdgpu_get_bios(struct amdgpu_device *adev)
 	uint16_t tmp, bios_header_start;
 
 	r = amdgpu_atrm_get_bios(adev);
-	if (r == false)
+	if (!r)
 		r = amdgpu_acpi_vfct_bios(adev);
-	if (r == false)
+	if (!r)
 		r = igp_read_bios_from_vram(adev);
-	if (r == false)
+	if (!r)
 		r = amdgpu_read_bios(adev);
-	if (r == false) {
+	if (!r) {
 		r = amdgpu_read_bios_from_rom(adev);
 	}
-	if (r == false) {
+	if (!r) {
 		r = amdgpu_read_disabled_bios(adev);
 	}
-	if (r == false) {
+	if (!r) {
 		r = amdgpu_read_platform_bios(adev);
 	}
-	if (r == false || adev->bios == NULL) {
+	if (!r || adev->bios == NULL) {
 		DRM_ERROR("Unable to locate a BIOS ROM\n");
 		adev->bios = NULL;
 		return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 823bf5e0b0c8..651115dcce12 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -94,6 +94,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 	unsigned last_entry = 0, first_userptr = num_entries;
 	unsigned i;
 	int r;
+	unsigned long total_size = 0;
 
 	array = drm_malloc_ab(num_entries, sizeof(struct amdgpu_bo_list_entry));
 	if (!array)
@@ -140,6 +141,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 		if (entry->robj->prefered_domains == AMDGPU_GEM_DOMAIN_OA)
 			oa_obj = entry->robj;
 
+		total_size += amdgpu_bo_size(entry->robj);
 		trace_amdgpu_bo_list_set(list, entry->robj);
 	}
 
@@ -155,6 +157,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 	list->array = array;
 	list->num_entries = num_entries;
 
+	trace_amdgpu_cs_bo_status(list->num_entries, total_size);
 	return 0;
 
 error_free:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index cf6f49fc1c75..bc0440f7a31d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -312,6 +312,8 @@ static uint32_t amdgpu_cgs_read_ind_register(struct cgs_device *cgs_device,
 		return RREG32_UVD_CTX(index);
 	case CGS_IND_REG__DIDT:
 		return RREG32_DIDT(index);
+	case CGS_IND_REG_GC_CAC:
+		return RREG32_GC_CAC(index);
 	case CGS_IND_REG__AUDIO_ENDPT:
 		DRM_ERROR("audio endpt register access not implemented.\n");
 		return 0;
@@ -336,6 +338,8 @@ static void amdgpu_cgs_write_ind_register(struct cgs_device *cgs_device,
 		return WREG32_UVD_CTX(index, value);
 	case CGS_IND_REG__DIDT:
 		return WREG32_DIDT(index, value);
+	case CGS_IND_REG_GC_CAC:
+		return WREG32_GC_CAC(index, value);
 	case CGS_IND_REG__AUDIO_ENDPT:
 		DRM_ERROR("audio endpt register access not implemented.\n");
 		return;
@@ -748,6 +752,9 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 
 		if (!adev->pm.fw) {
 			switch (adev->asic_type) {
+			case CHIP_TOPAZ:
+				strcpy(fw_name, "amdgpu/topaz_smc.bin");
+				break;
 			case CHIP_TONGA:
 				strcpy(fw_name, "amdgpu/tonga_smc.bin");
 				break;
@@ -787,6 +794,7 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 		}
 
 		hdr = (const struct smc_firmware_header_v1_0 *)	adev->pm.fw->data;
+		amdgpu_ucode_print_smc_hdr(&hdr->header);
 		adev->pm.fw_version = le32_to_cpu(hdr->header.ucode_version);
 		ucode_size = le32_to_cpu(hdr->header.ucode_size_bytes);
 		ucode_start_address = le32_to_cpu(hdr->ucode_start_addr);
@@ -795,13 +803,14 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 
 		info->version = adev->pm.fw_version;
 		info->image_size = ucode_size;
+		info->ucode_start_address = ucode_start_address;
 		info->kptr = (void *)src;
 	}
 	return 0;
 }
 
 static int amdgpu_cgs_query_system_info(struct cgs_device *cgs_device,
-				struct cgs_system_info *sys_info)
+					struct cgs_system_info *sys_info)
 {
 	CGS_FUNC_ADEV;
 
@@ -821,6 +830,12 @@ static int amdgpu_cgs_query_system_info(struct cgs_device *cgs_device,
 	case CGS_SYSTEM_INFO_PCIE_MLW:
 		sys_info->value = adev->pm.pcie_mlw_mask;
 		break;
+	case CGS_SYSTEM_INFO_PCIE_DEV:
+		sys_info->value = adev->pdev->device;
+		break;
+	case CGS_SYSTEM_INFO_PCIE_REV:
+		sys_info->value = adev->pdev->revision;
+		break;
 	case CGS_SYSTEM_INFO_CG_FLAGS:
 		sys_info->value = adev->cg_flags;
 		break;
@@ -830,6 +845,9 @@ static int amdgpu_cgs_query_system_info(struct cgs_device *cgs_device,
 	case CGS_SYSTEM_INFO_GFX_CU_INFO:
 		sys_info->value = adev->gfx.cu_info.number;
 		break;
+	case CGS_SYSTEM_INFO_GFX_SE_INFO:
+		sys_info->value = adev->gfx.config.max_shader_engines;
+		break;
 	default:
 		return -ENODEV;
 	}
@@ -903,14 +921,12 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 	acpi_handle handle;
 	struct acpi_object_list input;
 	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
-	union acpi_object *params = NULL;
-	union acpi_object *obj = NULL;
+	union acpi_object *params, *obj;
 	uint8_t name[5] = {'\0'};
-	struct cgs_acpi_method_argument *argument = NULL;
+	struct cgs_acpi_method_argument *argument;
 	uint32_t i, count;
 	acpi_status status;
-	int result = 0;
-	uint32_t func_no = 0xFFFFFFFF;
+	int result;
 
 	handle = ACPI_HANDLE(&adev->pdev->dev);
 	if (!handle)
@@ -927,7 +943,6 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 		if (info->pinput_argument == NULL)
 			return -EINVAL;
 		argument = info->pinput_argument;
-		func_no = argument->value;
 		for (i = 0; i < info->input_count; i++) {
 			if (((argument->type == ACPI_TYPE_STRING) ||
 			     (argument->type == ACPI_TYPE_BUFFER)) &&
@@ -972,11 +987,11 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 				params->integer.value = argument->value;
 				break;
 			case ACPI_TYPE_STRING:
-				params->string.length = argument->method_length;
+				params->string.length = argument->data_length;
 				params->string.pointer = argument->pointer;
 				break;
 			case ACPI_TYPE_BUFFER:
-				params->buffer.length = argument->method_length;
+				params->buffer.length = argument->data_length;
 				params->buffer.pointer = argument->pointer;
 				break;
 			default:
@@ -996,7 +1011,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 
 	if (ACPI_FAILURE(status)) {
 		result = -EIO;
-		goto error;
+		goto free_input;
 	}
 
 	/* return the output info */
@@ -1006,7 +1021,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 		if ((obj->type != ACPI_TYPE_PACKAGE) ||
 			(obj->package.count != count)) {
 			result = -EIO;
-			goto error;
+			goto free_obj;
 		}
 		params = obj->package.elements;
 	} else
@@ -1014,13 +1029,13 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 
 	if (params == NULL) {
 		result = -EIO;
-		goto error;
+		goto free_obj;
 	}
 
 	for (i = 0; i < count; i++) {
 		if (argument->type != params->type) {
 			result = -EIO;
-			goto error;
+			goto free_obj;
 		}
 		switch (params->type) {
 		case ACPI_TYPE_INTEGER:
@@ -1030,7 +1045,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 			if ((params->string.length != argument->data_length) ||
 				(params->string.pointer == NULL)) {
 				result = -EIO;
-				goto error;
+				goto free_obj;
 			}
 			strncpy(argument->pointer,
 				params->string.pointer,
@@ -1039,7 +1054,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 		case ACPI_TYPE_BUFFER:
 			if (params->buffer.pointer == NULL) {
 				result = -EIO;
-				goto error;
+				goto free_obj;
 			}
 			memcpy(argument->pointer,
 				params->buffer.pointer,
@@ -1052,9 +1067,10 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 		params++;
 	}
 
-error:
-	if (obj != NULL)
-		kfree(obj);
+	result = 0;
+free_obj:
+	kfree(obj);
+free_input:
 	kfree((void *)input.pointer);
 	return result;
 }
@@ -1066,7 +1082,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device,
 }
 #endif
 
-int amdgpu_cgs_call_acpi_method(struct cgs_device *cgs_device,
+static int amdgpu_cgs_call_acpi_method(struct cgs_device *cgs_device,
 					uint32_t acpi_method,
 					uint32_t acpi_function,
 					void *pinput, void *poutput,
@@ -1079,17 +1095,14 @@ int amdgpu_cgs_call_acpi_method(struct cgs_device *cgs_device,
 	struct cgs_acpi_method_info info = {0};
 
 	acpi_input[0].type = CGS_ACPI_TYPE_INTEGER;
-	acpi_input[0].method_length = sizeof(uint32_t);
 	acpi_input[0].data_length = sizeof(uint32_t);
 	acpi_input[0].value = acpi_function;
 
 	acpi_input[1].type = CGS_ACPI_TYPE_BUFFER;
-	acpi_input[1].method_length = CGS_ACPI_MAX_BUFFER_SIZE;
 	acpi_input[1].data_length = input_size;
 	acpi_input[1].pointer = pinput;
 
 	acpi_output.type = CGS_ACPI_TYPE_BUFFER;
-	acpi_output.method_length = CGS_ACPI_MAX_BUFFER_SIZE;
 	acpi_output.data_length = output_size;
 	acpi_output.pointer = poutput;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index cb07da41152b..ff0b55a65ca3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -1690,7 +1690,6 @@ amdgpu_connector_add(struct amdgpu_device *adev,
 						   DRM_MODE_SCALE_NONE);
 			/* no HPD on analog connectors */
 			amdgpu_connector->hpd.hpd = AMDGPU_HPD_NONE;
-			connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 			connector->interlace_allowed = true;
 			connector->doublescan_allowed = true;
 			break;
@@ -1893,8 +1892,10 @@ amdgpu_connector_add(struct amdgpu_device *adev,
 	}
 
 	if (amdgpu_connector->hpd.hpd == AMDGPU_HPD_NONE) {
-		if (i2c_bus->valid)
-			connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+		if (i2c_bus->valid) {
+			connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+			                    DRM_CONNECTOR_POLL_DISCONNECT;
+		}
 	} else
 		connector->polled = DRM_CONNECTOR_POLL_HPD;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 9bc8f1d99733..0307ff5887c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -216,11 +216,8 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 	if (ret)
 		goto free_all_kdata;
 
-	if (p->uf_entry.robj) {
-		p->job->uf_bo = amdgpu_bo_ref(p->uf_entry.robj);
-		p->job->uf_offset = uf_offset;
-	}
-
+	if (p->uf_entry.robj)
+		p->job->uf_addr = uf_offset;
 	kfree(chunk_array);
 	return 0;
 
@@ -459,7 +456,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		list_splice(&need_pages, &p->validated);
 	}
 
-	amdgpu_vm_get_pt_bos(&fpriv->vm, &duplicates);
+	amdgpu_vm_get_pt_bos(p->adev, &fpriv->vm, &duplicates);
 
 	p->bytes_moved_threshold = amdgpu_cs_get_threshold_for_moves(p->adev);
 	p->bytes_moved = 0;
@@ -472,6 +469,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	if (r)
 		goto error_validate;
 
+	fpriv->vm.last_eviction_counter =
+		atomic64_read(&p->adev->num_evictions);
+
 	if (p->bo_list) {
 		struct amdgpu_bo *gds = p->bo_list->gds_obj;
 		struct amdgpu_bo *gws = p->bo_list->gws_obj;
@@ -499,6 +499,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		}
 	}
 
+	if (p->uf_entry.robj)
+		p->job->uf_addr += amdgpu_bo_gpu_offset(p->uf_entry.robj);
+
 error_validate:
 	if (r) {
 		amdgpu_vm_move_pt_bos_in_lru(p->adev, &fpriv->vm);
@@ -653,18 +656,21 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 
 	/* Only for UVD/VCE VM emulation */
 	if (ring->funcs->parse_cs) {
+		p->job->vm = NULL;
 		for (i = 0; i < p->job->num_ibs; i++) {
 			r = amdgpu_ring_parse_cs(ring, p, i);
 			if (r)
 				return r;
 		}
-	}
+	} else {
+		p->job->vm_pd_addr = amdgpu_bo_gpu_offset(vm->page_directory);
 
-	r = amdgpu_bo_vm_update_pte(p, vm);
-	if (!r)
-		amdgpu_cs_sync_rings(p);
+		r = amdgpu_bo_vm_update_pte(p, vm);
+		if (r)
+			return r;
+	}
 
-	return r;
+	return amdgpu_cs_sync_rings(p);
 }
 
 static int amdgpu_cs_handle_lockup(struct amdgpu_device *adev, int r)
@@ -761,7 +767,7 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 	}
 
 	/* UVD & VCE fw doesn't support user fences */
-	if (parser->job->uf_bo && (
+	if (parser->job->uf_addr && (
 	    parser->job->ring->type == AMDGPU_RING_TYPE_UVD ||
 	    parser->job->ring->type == AMDGPU_RING_TYPE_VCE))
 		return -EINVAL;
@@ -830,17 +836,13 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 {
 	struct amdgpu_ring *ring = p->job->ring;
 	struct amd_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
-	struct fence *fence;
 	struct amdgpu_job *job;
 	int r;
 
 	job = p->job;
 	p->job = NULL;
 
-	r = amd_sched_job_init(&job->base, &ring->sched,
-			       entity, amdgpu_job_timeout_func,
-			       amdgpu_job_free_func,
-			       p->filp, &fence);
+	r = amd_sched_job_init(&job->base, &ring->sched, entity, p->filp);
 	if (r) {
 		amdgpu_job_free(job);
 		return r;
@@ -848,9 +850,10 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	job->owner = p->filp;
 	job->ctx = entity->fence_context;
-	p->fence = fence_get(fence);
-	cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, fence);
+	p->fence = fence_get(&job->base.s_fence->finished);
+	cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, p->fence);
 	job->uf_sequence = cs->out.handle;
+	amdgpu_job_free_resources(job);
 
 	trace_amdgpu_cs_ioctl(job);
 	amd_sched_entity_push_job(&job->base);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6e920086af46..df7ab2458e50 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -25,6 +25,7 @@
  *          Alex Deucher
  *          Jerome Glisse
  */
+#include <linux/kthread.h>
 #include <linux/console.h>
 #include <linux/slab.h>
 #include <linux/debugfs.h>
@@ -35,6 +36,7 @@
 #include <linux/vga_switcheroo.h>
 #include <linux/efi.h>
 #include "amdgpu.h"
+#include "amdgpu_trace.h"
 #include "amdgpu_i2c.h"
 #include "atom.h"
 #include "amdgpu_atombios.h"
@@ -79,24 +81,27 @@ bool amdgpu_device_is_px(struct drm_device *dev)
 uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
 			bool always_indirect)
 {
+	uint32_t ret;
+
 	if ((reg * 4) < adev->rmmio_size && !always_indirect)
-		return readl(((void __iomem *)adev->rmmio) + (reg * 4));
+		ret = readl(((void __iomem *)adev->rmmio) + (reg * 4));
 	else {
 		unsigned long flags;
-		uint32_t ret;
 
 		spin_lock_irqsave(&adev->mmio_idx_lock, flags);
 		writel((reg * 4), ((void __iomem *)adev->rmmio) + (mmMM_INDEX * 4));
 		ret = readl(((void __iomem *)adev->rmmio) + (mmMM_DATA * 4));
 		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
-
-		return ret;
 	}
+	trace_amdgpu_mm_rreg(adev->pdev->device, reg, ret);
+	return ret;
 }
 
 void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
 		    bool always_indirect)
 {
+	trace_amdgpu_mm_wreg(adev->pdev->device, reg, v);
+	
 	if ((reg * 4) < adev->rmmio_size && !always_indirect)
 		writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
 	else {
@@ -1070,11 +1075,14 @@ int amdgpu_set_clockgating_state(struct amdgpu_device *adev,
 	int i, r = 0;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_block_status[i].valid)
+			continue;
 		if (adev->ip_blocks[i].type == block_type) {
 			r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
 									    state);
 			if (r)
 				return r;
+			break;
 		}
 	}
 	return r;
@@ -1087,16 +1095,53 @@ int amdgpu_set_powergating_state(struct amdgpu_device *adev,
 	int i, r = 0;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_block_status[i].valid)
+			continue;
 		if (adev->ip_blocks[i].type == block_type) {
 			r = adev->ip_blocks[i].funcs->set_powergating_state((void *)adev,
 									    state);
 			if (r)
 				return r;
+			break;
 		}
 	}
 	return r;
 }
 
+int amdgpu_wait_for_idle(struct amdgpu_device *adev,
+			 enum amd_ip_block_type block_type)
+{
+	int i, r;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_block_status[i].valid)
+			continue;
+		if (adev->ip_blocks[i].type == block_type) {
+			r = adev->ip_blocks[i].funcs->wait_for_idle((void *)adev);
+			if (r)
+				return r;
+			break;
+		}
+	}
+	return 0;
+
+}
+
+bool amdgpu_is_idle(struct amdgpu_device *adev,
+		    enum amd_ip_block_type block_type)
+{
+	int i;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_block_status[i].valid)
+			continue;
+		if (adev->ip_blocks[i].type == block_type)
+			return adev->ip_blocks[i].funcs->is_idle((void *)adev);
+	}
+	return true;
+
+}
+
 const struct amdgpu_ip_block_version * amdgpu_get_ip_block(
 					struct amdgpu_device *adev,
 					enum amd_ip_block_type type)
@@ -1209,6 +1254,9 @@ static int amdgpu_early_init(struct amdgpu_device *adev)
 		}
 	}
 
+	adev->cg_flags &= amdgpu_cg_mask;
+	adev->pg_flags &= amdgpu_pg_mask;
+
 	return 0;
 }
 
@@ -1440,9 +1488,12 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	adev->uvd_ctx_wreg = &amdgpu_invalid_wreg;
 	adev->didt_rreg = &amdgpu_invalid_rreg;
 	adev->didt_wreg = &amdgpu_invalid_wreg;
+	adev->gc_cac_rreg = &amdgpu_invalid_rreg;
+	adev->gc_cac_wreg = &amdgpu_invalid_wreg;
 	adev->audio_endpt_rreg = &amdgpu_block_invalid_rreg;
 	adev->audio_endpt_wreg = &amdgpu_block_invalid_wreg;
 
+
 	DRM_INFO("initializing kernel modesetting (%s 0x%04X:0x%04X 0x%04X:0x%04X 0x%02X).\n",
 		 amdgpu_asic_name[adev->asic_type], pdev->vendor, pdev->device,
 		 pdev->subsystem_vendor, pdev->subsystem_device, pdev->revision);
@@ -1467,6 +1518,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	spin_lock_init(&adev->pcie_idx_lock);
 	spin_lock_init(&adev->uvd_ctx_idx_lock);
 	spin_lock_init(&adev->didt_idx_lock);
+	spin_lock_init(&adev->gc_cac_idx_lock);
 	spin_lock_init(&adev->audio_endpt_idx_lock);
 
 	adev->rmmio_base = pci_resource_start(adev->pdev, 5);
@@ -1511,17 +1563,20 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		vga_switcheroo_init_domain_pm_ops(adev->dev, &adev->vga_pm_domain);
 
 	/* Read BIOS */
-	if (!amdgpu_get_bios(adev))
-		return -EINVAL;
+	if (!amdgpu_get_bios(adev)) {
+		r = -EINVAL;
+		goto failed;
+	}
 	/* Must be an ATOMBIOS */
 	if (!adev->is_atom_bios) {
 		dev_err(adev->dev, "Expecting atombios for GPU\n");
-		return -EINVAL;
+		r = -EINVAL;
+		goto failed;
 	}
 	r = amdgpu_atombios_init(adev);
 	if (r) {
 		dev_err(adev->dev, "amdgpu_atombios_init failed\n");
-		return r;
+		goto failed;
 	}
 
 	/* See if the asic supports SR-IOV */
@@ -1538,7 +1593,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	     !(adev->virtualization.caps & AMDGPU_VIRT_CAPS_SRIOV_EN))) {
 		if (!adev->bios) {
 			dev_err(adev->dev, "Card not posted and no BIOS - ignoring\n");
-			return -EINVAL;
+			r = -EINVAL;
+			goto failed;
 		}
 		DRM_INFO("GPU not posted. posting now...\n");
 		amdgpu_atom_asic_init(adev->mode_info.atom_context);
@@ -1548,7 +1604,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	r = amdgpu_atombios_get_clock_info(adev);
 	if (r) {
 		dev_err(adev->dev, "amdgpu_atombios_get_clock_info failed\n");
-		return r;
+		goto failed;
 	}
 	/* init i2c buses */
 	amdgpu_atombios_i2c_init(adev);
@@ -1557,7 +1613,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	r = amdgpu_fence_driver_init(adev);
 	if (r) {
 		dev_err(adev->dev, "amdgpu_fence_driver_init failed\n");
-		return r;
+		goto failed;
 	}
 
 	/* init the mode config */
@@ -1567,7 +1623,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r) {
 		dev_err(adev->dev, "amdgpu_init failed\n");
 		amdgpu_fini(adev);
-		return r;
+		goto failed;
 	}
 
 	adev->accel_working = true;
@@ -1577,7 +1633,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	r = amdgpu_ib_pool_init(adev);
 	if (r) {
 		dev_err(adev->dev, "IB initialization failed (%d).\n", r);
-		return r;
+		goto failed;
 	}
 
 	r = amdgpu_ib_ring_tests(adev);
@@ -1594,6 +1650,12 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		DRM_ERROR("registering register debugfs failed (%d).\n", r);
 	}
 
+	r = amdgpu_debugfs_firmware_init(adev);
+	if (r) {
+		DRM_ERROR("registering firmware debugfs failed (%d).\n", r);
+		return r;
+	}
+
 	if ((amdgpu_testing & 1)) {
 		if (adev->accel_working)
 			amdgpu_test_moves(adev);
@@ -1619,10 +1681,15 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	r = amdgpu_late_init(adev);
 	if (r) {
 		dev_err(adev->dev, "amdgpu_late_init failed\n");
-		return r;
+		goto failed;
 	}
 
 	return 0;
+
+failed:
+	if (runtime)
+		vga_switcheroo_fini_domain_pm_ops(adev->dev);
+	return r;
 }
 
 static void amdgpu_debugfs_remove_files(struct amdgpu_device *adev);
@@ -1645,6 +1712,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	amdgpu_bo_evict_vram(adev);
 	amdgpu_ib_pool_fini(adev);
 	amdgpu_fence_driver_fini(adev);
+	drm_crtc_force_disable_all(adev->ddev);
 	amdgpu_fbdev_fini(adev);
 	r = amdgpu_fini(adev);
 	kfree(adev->ip_block_status);
@@ -1656,6 +1724,8 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	kfree(adev->bios);
 	adev->bios = NULL;
 	vga_switcheroo_unregister_client(adev->pdev);
+	if (adev->flags & AMD_IS_PX)
+		vga_switcheroo_fini_domain_pm_ops(adev->dev);
 	vga_client_register(adev->pdev, NULL, NULL, NULL);
 	if (adev->rio_mem)
 		pci_iounmap(adev->pdev, adev->rio_mem);
@@ -1841,7 +1911,23 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	}
 
 	drm_kms_helper_poll_enable(dev);
+
+	/*
+	 * Most of the connector probing functions try to acquire runtime pm
+	 * refs to ensure that the GPU is powered on when connector polling is
+	 * performed. Since we're calling this from a runtime PM callback,
+	 * trying to acquire rpm refs will cause us to deadlock.
+	 *
+	 * Since we're guaranteed to be holding the rpm lock, it's safe to
+	 * temporarily disable the rpm helpers so this doesn't deadlock us.
+	 */
+#ifdef CONFIG_PM
+	dev->dev->power.disable_depth++;
+#endif
 	drm_helper_hpd_irq_event(dev);
+#ifdef CONFIG_PM
+	dev->dev->power.disable_depth--;
+#endif
 
 	if (fbcon) {
 		amdgpu_fbdev_set_suspend(adev, 0);
@@ -1861,11 +1947,6 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
  */
 int amdgpu_gpu_reset(struct amdgpu_device *adev)
 {
-	unsigned ring_sizes[AMDGPU_MAX_RINGS];
-	uint32_t *ring_data[AMDGPU_MAX_RINGS];
-
-	bool saved = false;
-
 	int i, r;
 	int resched;
 
@@ -1874,22 +1955,30 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev)
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
 
-	r = amdgpu_suspend(adev);
-
+	/* block scheduler */
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
+
 		if (!ring)
 			continue;
-
-		ring_sizes[i] = amdgpu_ring_backup(ring, &ring_data[i]);
-		if (ring_sizes[i]) {
-			saved = true;
-			dev_info(adev->dev, "Saved %d dwords of commands "
-				 "on ring %d.\n", ring_sizes[i], i);
-		}
+		kthread_park(ring->sched.thread);
+		amd_sched_hw_job_reset(&ring->sched);
 	}
+	/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
+	amdgpu_fence_driver_force_completion(adev);
+
+	/* save scratch */
+	amdgpu_atombios_scratch_regs_save(adev);
+	r = amdgpu_suspend(adev);
 
 retry:
+	/* Disable fb access */
+	if (adev->mode_info.num_crtc) {
+		struct amdgpu_mode_mc_save save;
+		amdgpu_display_stop_mc_access(adev, &save);
+		amdgpu_wait_for_idle(adev, AMD_IP_BLOCK_TYPE_GMC);
+	}
+
 	r = amdgpu_asic_reset(adev);
 	/* post card */
 	amdgpu_atom_asic_init(adev->mode_info.atom_context);
@@ -1898,32 +1987,29 @@ retry:
 		dev_info(adev->dev, "GPU reset succeeded, trying to resume\n");
 		r = amdgpu_resume(adev);
 	}
-
+	/* restore scratch */
+	amdgpu_atombios_scratch_regs_restore(adev);
 	if (!r) {
+		r = amdgpu_ib_ring_tests(adev);
+		if (r) {
+			dev_err(adev->dev, "ib ring test failed (%d).\n", r);
+			r = amdgpu_suspend(adev);
+			goto retry;
+		}
+
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = adev->rings[i];
 			if (!ring)
 				continue;
-
-			amdgpu_ring_restore(ring, ring_sizes[i], ring_data[i]);
-			ring_sizes[i] = 0;
-			ring_data[i] = NULL;
-		}
-
-		r = amdgpu_ib_ring_tests(adev);
-		if (r) {
-			dev_err(adev->dev, "ib ring test failed (%d).\n", r);
-			if (saved) {
-				saved = false;
-				r = amdgpu_suspend(adev);
-				goto retry;
-			}
+			amd_sched_job_recovery(&ring->sched);
+			kthread_unpark(ring->sched.thread);
 		}
 	} else {
-		amdgpu_fence_driver_force_completion(adev);
+		dev_err(adev->dev, "asic resume failed (%d).\n", r);
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
-			if (adev->rings[i])
-				kfree(ring_data[i]);
+			if (adev->rings[i]) {
+				kthread_unpark(adev->rings[i]->sched.thread);
+			}
 		}
 	}
 
@@ -1934,13 +2020,11 @@ retry:
 		/* bad news, how to tell it to userspace ? */
 		dev_info(adev->dev, "GPU reset failed\n");
 	}
+	amdgpu_irq_gpu_reset_resume_helper(adev);
 
 	return r;
 }
 
-#define AMDGPU_DEFAULT_PCIE_GEN_MASK 0x30007  /* gen: chipset 1/2, asic 1/2/3 */
-#define AMDGPU_DEFAULT_PCIE_MLW_MASK 0x2f0000 /* 1/2/4/8/16 lanes */
-
 void amdgpu_get_pcie_info(struct amdgpu_device *adev)
 {
 	u32 mask;
@@ -2094,20 +2178,43 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf,
 	struct amdgpu_device *adev = f->f_inode->i_private;
 	ssize_t result = 0;
 	int r;
+	bool use_bank;
+	unsigned instance_bank, sh_bank, se_bank;
 
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	if (*pos & (1ULL << 62)) {
+		se_bank = (*pos >> 24) & 0x3FF;
+		sh_bank = (*pos >> 34) & 0x3FF;
+		instance_bank = (*pos >> 44) & 0x3FF;
+		use_bank = 1;
+		*pos &= 0xFFFFFF;
+	} else {
+		use_bank = 0;
+	}
+
+	if (use_bank) {
+		if (sh_bank >= adev->gfx.config.max_sh_per_se ||
+		    se_bank >= adev->gfx.config.max_shader_engines)
+			return -EINVAL;
+		mutex_lock(&adev->grbm_idx_mutex);
+		amdgpu_gfx_select_se_sh(adev, se_bank,
+					sh_bank, instance_bank);
+	}
+
 	while (size) {
 		uint32_t value;
 
 		if (*pos > adev->rmmio_size)
-			return result;
+			goto end;
 
 		value = RREG32(*pos >> 2);
 		r = put_user(value, (uint32_t *)buf);
-		if (r)
-			return r;
+		if (r) {
+			result = r;
+			goto end;
+		}
 
 		result += 4;
 		buf += 4;
@@ -2115,6 +2222,12 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
+end:
+	if (use_bank) {
+		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+		mutex_unlock(&adev->grbm_idx_mutex);
+	}
+
 	return result;
 }
 
@@ -2314,6 +2427,68 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *
 	return result;
 }
 
+static ssize_t amdgpu_debugfs_gca_config_read(struct file *f, char __user *buf,
+					size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = f->f_inode->i_private;
+	ssize_t result = 0;
+	int r;
+	uint32_t *config, no_regs = 0;
+
+	if (size & 0x3 || *pos & 0x3)
+		return -EINVAL;
+
+	config = kmalloc(256 * sizeof(*config), GFP_KERNEL);
+	if (!config)
+		return -ENOMEM;
+
+	/* version, increment each time something is added */
+	config[no_regs++] = 0;
+	config[no_regs++] = adev->gfx.config.max_shader_engines;
+	config[no_regs++] = adev->gfx.config.max_tile_pipes;
+	config[no_regs++] = adev->gfx.config.max_cu_per_sh;
+	config[no_regs++] = adev->gfx.config.max_sh_per_se;
+	config[no_regs++] = adev->gfx.config.max_backends_per_se;
+	config[no_regs++] = adev->gfx.config.max_texture_channel_caches;
+	config[no_regs++] = adev->gfx.config.max_gprs;
+	config[no_regs++] = adev->gfx.config.max_gs_threads;
+	config[no_regs++] = adev->gfx.config.max_hw_contexts;
+	config[no_regs++] = adev->gfx.config.sc_prim_fifo_size_frontend;
+	config[no_regs++] = adev->gfx.config.sc_prim_fifo_size_backend;
+	config[no_regs++] = adev->gfx.config.sc_hiz_tile_fifo_size;
+	config[no_regs++] = adev->gfx.config.sc_earlyz_tile_fifo_size;
+	config[no_regs++] = adev->gfx.config.num_tile_pipes;
+	config[no_regs++] = adev->gfx.config.backend_enable_mask;
+	config[no_regs++] = adev->gfx.config.mem_max_burst_length_bytes;
+	config[no_regs++] = adev->gfx.config.mem_row_size_in_kb;
+	config[no_regs++] = adev->gfx.config.shader_engine_tile_size;
+	config[no_regs++] = adev->gfx.config.num_gpus;
+	config[no_regs++] = adev->gfx.config.multi_gpu_tile_size;
+	config[no_regs++] = adev->gfx.config.mc_arb_ramcfg;
+	config[no_regs++] = adev->gfx.config.gb_addr_config;
+	config[no_regs++] = adev->gfx.config.num_rbs;
+
+	while (size && (*pos < no_regs * 4)) {
+		uint32_t value;
+
+		value = config[*pos >> 2];
+		r = put_user(value, (uint32_t *)buf);
+		if (r) {
+			kfree(config);
+			return r;
+		}
+
+		result += 4;
+		buf += 4;
+		*pos += 4;
+		size -= 4;
+	}
+
+	kfree(config);
+	return result;
+}
+
+
 static const struct file_operations amdgpu_debugfs_regs_fops = {
 	.owner = THIS_MODULE,
 	.read = amdgpu_debugfs_regs_read,
@@ -2339,11 +2514,18 @@ static const struct file_operations amdgpu_debugfs_regs_smc_fops = {
 	.llseek = default_llseek
 };
 
+static const struct file_operations amdgpu_debugfs_gca_config_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_gca_config_read,
+	.llseek = default_llseek
+};
+
 static const struct file_operations *debugfs_regs[] = {
 	&amdgpu_debugfs_regs_fops,
 	&amdgpu_debugfs_regs_didt_fops,
 	&amdgpu_debugfs_regs_pcie_fops,
 	&amdgpu_debugfs_regs_smc_fops,
+	&amdgpu_debugfs_gca_config_fops,
 };
 
 static const char *debugfs_regs_names[] = {
@@ -2351,6 +2533,7 @@ static const char *debugfs_regs_names[] = {
 	"amdgpu_regs_didt",
 	"amdgpu_regs_pcie",
 	"amdgpu_regs_smc",
+	"amdgpu_gca_config",
 };
 
 static int amdgpu_debugfs_regs_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index b0832da2ef7e..76f96028313d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -122,7 +122,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 		usleep_range(min_udelay, 2 * min_udelay);
 		spin_lock_irqsave(&crtc->dev->event_lock, flags);
-	};
+	}
 
 	if (!repcnt)
 		DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, "
@@ -220,19 +220,17 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
 
 	r = amdgpu_bo_pin_restricted(new_rbo, AMDGPU_GEM_DOMAIN_VRAM, 0, 0, &base);
 	if (unlikely(r != 0)) {
-		amdgpu_bo_unreserve(new_rbo);
 		r = -EINVAL;
 		DRM_ERROR("failed to pin new rbo buffer before flip\n");
-		goto cleanup;
+		goto unreserve;
 	}
 
 	r = reservation_object_get_fences_rcu(new_rbo->tbo.resv, &work->excl,
 					      &work->shared_count,
 					      &work->shared);
 	if (unlikely(r != 0)) {
-		amdgpu_bo_unreserve(new_rbo);
 		DRM_ERROR("failed to get fences for buffer\n");
-		goto cleanup;
+		goto unpin;
 	}
 
 	amdgpu_bo_get_tiling_flags(new_rbo, &tiling_flags);
@@ -240,7 +238,7 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
 
 	work->base = base;
 
-	r = drm_vblank_get(crtc->dev, amdgpu_crtc->crtc_id);
+	r = drm_crtc_vblank_get(crtc);
 	if (r) {
 		DRM_ERROR("failed to get vblank before flip\n");
 		goto pflip_cleanup;
@@ -268,16 +266,18 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
 	return 0;
 
 vblank_cleanup:
-	drm_vblank_put(crtc->dev, amdgpu_crtc->crtc_id);
+	drm_crtc_vblank_put(crtc);
 
 pflip_cleanup:
 	if (unlikely(amdgpu_bo_reserve(new_rbo, false) != 0)) {
 		DRM_ERROR("failed to reserve new rbo in error path\n");
 		goto cleanup;
 	}
+unpin:
 	if (unlikely(amdgpu_bo_unpin(new_rbo) != 0)) {
 		DRM_ERROR("failed to unpin new rbo in error path\n");
 	}
+unreserve:
 	amdgpu_bo_unreserve(new_rbo);
 
 cleanup:
@@ -516,9 +516,7 @@ static void amdgpu_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct amdgpu_framebuffer *amdgpu_fb = to_amdgpu_framebuffer(fb);
 
-	if (amdgpu_fb->obj) {
-		drm_gem_object_unreference_unlocked(amdgpu_fb->obj);
-	}
+	drm_gem_object_unreference_unlocked(amdgpu_fb->obj);
 	drm_framebuffer_cleanup(fb);
 	kfree(amdgpu_fb);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index f888c015f76c..9aa533cf4ad1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -52,9 +52,10 @@
  * - 3.1.0 - allow reading more status registers (GRBM, SRBM, SDMA, CP)
  * - 3.2.0 - GFX8: Uses EOP_TC_WB_ACTION_EN, so UMDs don't have to do the same
  *           at the end of IBs.
+ * - 3.3.0 - Add VM support for UVD on supported hardware.
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	2
+#define KMS_DRIVER_MINOR	3
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
@@ -82,8 +83,12 @@ int amdgpu_exp_hw_support = 0;
 int amdgpu_sched_jobs = 32;
 int amdgpu_sched_hw_submission = 2;
 int amdgpu_powerplay = -1;
+int amdgpu_powercontainment = 1;
 unsigned amdgpu_pcie_gen_cap = 0;
 unsigned amdgpu_pcie_lane_cap = 0;
+unsigned amdgpu_cg_mask = 0xffffffff;
+unsigned amdgpu_pg_mask = 0xffffffff;
+char *amdgpu_disable_cu = NULL;
 
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -160,6 +165,9 @@ module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444);
 #ifdef CONFIG_DRM_AMD_POWERPLAY
 MODULE_PARM_DESC(powerplay, "Powerplay component (1 = enable, 0 = disable, -1 = auto (default))");
 module_param_named(powerplay, amdgpu_powerplay, int, 0444);
+
+MODULE_PARM_DESC(powercontainment, "Power Containment (1 = enable (default), 0 = disable)");
+module_param_named(powercontainment, amdgpu_powercontainment, int, 0444);
 #endif
 
 MODULE_PARM_DESC(pcie_gen_cap, "PCIE Gen Caps (0: autodetect (default))");
@@ -168,6 +176,15 @@ module_param_named(pcie_gen_cap, amdgpu_pcie_gen_cap, uint, 0444);
 MODULE_PARM_DESC(pcie_lane_cap, "PCIE Lane Caps (0: autodetect (default))");
 module_param_named(pcie_lane_cap, amdgpu_pcie_lane_cap, uint, 0444);
 
+MODULE_PARM_DESC(cg_mask, "Clockgating flags mask (0 = disable clock gating)");
+module_param_named(cg_mask, amdgpu_cg_mask, uint, 0444);
+
+MODULE_PARM_DESC(pg_mask, "Powergating flags mask (0 = disable power gating)");
+module_param_named(pg_mask, amdgpu_pg_mask, uint, 0444);
+
+MODULE_PARM_DESC(disable_cu, "Disable CUs (se.sh.cu,...)");
+module_param_named(disable_cu, amdgpu_disable_cu, charp, 0444);
+
 static const struct pci_device_id pciidlist[] = {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	/* Kaveri */
@@ -413,7 +430,10 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 	pci_save_state(pdev);
 	pci_disable_device(pdev);
 	pci_ignore_hotplug(pdev);
-	pci_set_power_state(pdev, PCI_D3cold);
+	if (amdgpu_is_atpx_hybrid())
+		pci_set_power_state(pdev, PCI_D3cold);
+	else if (!amdgpu_has_atpx_dgpu_power_cntl())
+		pci_set_power_state(pdev, PCI_D3hot);
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
 
 	return 0;
@@ -430,7 +450,9 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 
-	pci_set_power_state(pdev, PCI_D0);
+	if (amdgpu_is_atpx_hybrid() ||
+	    !amdgpu_has_atpx_dgpu_power_cntl())
+		pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
 	ret = pci_enable_device(pdev);
 	if (ret)
@@ -515,7 +537,7 @@ static struct drm_driver kms_driver = {
 	.driver_features =
 	    DRIVER_USE_AGP |
 	    DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM |
-	    DRIVER_PRIME | DRIVER_RENDER,
+	    DRIVER_PRIME | DRIVER_RENDER | DRIVER_MODESET,
 	.dev_priv_size = 0,
 	.load = amdgpu_driver_load_kms,
 	.open = amdgpu_driver_open_kms,
@@ -590,7 +612,6 @@ static int __init amdgpu_init(void)
 	DRM_INFO("amdgpu kernel modesetting enabled.\n");
 	driver = &kms_driver;
 	pdriver = &amdgpu_kms_pci_driver;
-	driver->driver_features |= DRIVER_MODESET;
 	driver->num_ioctls = amdgpu_max_kms_ioctl;
 	amdgpu_register_atpx_handler();
 	/* let modprobe override vga console setting */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index d1558768cfb7..0b109aebfec6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -204,16 +204,25 @@ void amdgpu_fence_process(struct amdgpu_ring *ring)
 	if (seq != ring->fence_drv.sync_seq)
 		amdgpu_fence_schedule_fallback(ring);
 
-	while (last_seq != seq) {
+	if (unlikely(seq == last_seq))
+		return;
+
+	last_seq &= drv->num_fences_mask;
+	seq &= drv->num_fences_mask;
+
+	do {
 		struct fence *fence, **ptr;
 
-		ptr = &drv->fences[++last_seq & drv->num_fences_mask];
+		++last_seq;
+		last_seq &= drv->num_fences_mask;
+		ptr = &drv->fences[last_seq];
 
 		/* There is always exactly one thread signaling this fence slot */
 		fence = rcu_dereference_protected(*ptr, 1);
 		RCU_INIT_POINTER(*ptr, NULL);
 
-		BUG_ON(!fence);
+		if (!fence)
+			continue;
 
 		r = fence_signal(fence);
 		if (!r)
@@ -222,7 +231,7 @@ void amdgpu_fence_process(struct amdgpu_ring *ring)
 			BUG();
 
 		fence_put(fence);
-	}
+	} while (last_seq != seq);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 8fab6486064f..88fbed2389c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -503,7 +503,7 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 	if (r)
 		goto error_print;
 
-	amdgpu_vm_get_pt_bos(bo_va->vm, &duplicates);
+	amdgpu_vm_get_pt_bos(adev, bo_va->vm, &duplicates);
 	list_for_each_entry(entry, &list, head) {
 		domain = amdgpu_mem_type_to_domain(entry->bo->mem.mem_type);
 		/* if anything is swapped out don't swap it in here,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 9f95da4f0536..a074edd95c70 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -70,3 +70,47 @@ void amdgpu_gfx_scratch_free(struct amdgpu_device *adev, uint32_t reg)
 		}
 	}
 }
+
+/**
+ * amdgpu_gfx_parse_disable_cu - Parse the disable_cu module parameter
+ *
+ * @mask: array in which the per-shader array disable masks will be stored
+ * @max_se: number of SEs
+ * @max_sh: number of SHs
+ *
+ * The bitmask of CUs to be disabled in the shader array determined by se and
+ * sh is stored in mask[se * max_sh + sh].
+ */
+void amdgpu_gfx_parse_disable_cu(unsigned *mask, unsigned max_se, unsigned max_sh)
+{
+	unsigned se, sh, cu;
+	const char *p;
+
+	memset(mask, 0, sizeof(*mask) * max_se * max_sh);
+
+	if (!amdgpu_disable_cu || !*amdgpu_disable_cu)
+		return;
+
+	p = amdgpu_disable_cu;
+	for (;;) {
+		char *next;
+		int ret = sscanf(p, "%u.%u.%u", &se, &sh, &cu);
+		if (ret < 3) {
+			DRM_ERROR("amdgpu: could not parse disable_cu\n");
+			return;
+		}
+
+		if (se < max_se && sh < max_sh && cu < 16) {
+			DRM_INFO("amdgpu: disabling CU %u.%u.%u\n", se, sh, cu);
+			mask[se * max_sh + sh] |= 1u << cu;
+		} else {
+			DRM_ERROR("amdgpu: disable_cu %u.%u.%u is out of range\n",
+				  se, sh, cu);
+		}
+
+		next = strchr(p, ',');
+		if (!next)
+			break;
+		p = next + 1;
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index dc06cbda7be6..51321e154c09 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -27,4 +27,6 @@
 int amdgpu_gfx_scratch_get(struct amdgpu_device *adev, uint32_t *reg);
 void amdgpu_gfx_scratch_free(struct amdgpu_device *adev, uint32_t reg);
 
+unsigned amdgpu_gfx_parse_disable_cu(unsigned *mask, unsigned max_se, unsigned max_sh);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 34e35423b78e..a31d7ef3032c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -33,6 +33,8 @@
 #include "amdgpu.h"
 #include "atom.h"
 
+#define AMDGPU_IB_TEST_TIMEOUT	msecs_to_jiffies(1000)
+
 /*
  * IB
  * IBs (Indirect Buffers) and areas of GPU accessible memory where
@@ -122,7 +124,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	bool skip_preamble, need_ctx_switch;
 	unsigned patch_offset = ~0;
 	struct amdgpu_vm *vm;
-	struct fence *hwf;
 	uint64_t ctx;
 
 	unsigned i;
@@ -160,10 +161,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		patch_offset = amdgpu_ring_init_cond_exec(ring);
 
 	if (vm) {
-		r = amdgpu_vm_flush(ring, job->vm_id, job->vm_pd_addr,
-				    job->gds_base, job->gds_size,
-				    job->gws_base, job->gws_size,
-				    job->oa_base, job->oa_size);
+		r = amdgpu_vm_flush(ring, job);
 		if (r) {
 			amdgpu_ring_undo(ring);
 			return r;
@@ -193,7 +191,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	if (ring->funcs->emit_hdp_invalidate)
 		amdgpu_ring_emit_hdp_invalidate(ring);
 
-	r = amdgpu_fence_emit(ring, &hwf);
+	r = amdgpu_fence_emit(ring, f);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
 		if (job && job->vm_id)
@@ -203,17 +201,11 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	}
 
 	/* wrap the last IB with fence */
-	if (job && job->uf_bo) {
-		uint64_t addr = amdgpu_bo_gpu_offset(job->uf_bo);
-
-		addr += job->uf_offset;
-		amdgpu_ring_emit_fence(ring, addr, job->uf_sequence,
+	if (job && job->uf_addr) {
+		amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
 				       AMDGPU_FENCE_FLAG_64BIT);
 	}
 
-	if (f)
-		*f = fence_get(hwf);
-
 	if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
 		amdgpu_ring_patch_cond_exec(ring, patch_offset);
 
@@ -296,7 +288,7 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 		if (!ring || !ring->ready)
 			continue;
 
-		r = amdgpu_ring_test_ib(ring);
+		r = amdgpu_ring_test_ib(ring, AMDGPU_IB_TEST_TIMEOUT);
 		if (r) {
 			ring->ready = false;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 835a3fa8d8df..278708f5a744 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -383,6 +383,18 @@ int amdgpu_irq_update(struct amdgpu_device *adev,
 	return r;
 }
 
+void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
+{
+	int i, j;
+	for (i = 0; i < AMDGPU_MAX_IRQ_SRC_ID; i++) {
+		struct amdgpu_irq_src *src = adev->irq.sources[i];
+		if (!src)
+			continue;
+		for (j = 0; j < src->num_types; j++)
+			amdgpu_irq_update(adev, src, j);
+	}
+}
+
 /**
  * amdgpu_irq_get - enable interrupt
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
index e124b59f39c1..7ef09352e534 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h
@@ -94,6 +94,7 @@ int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type);
 bool amdgpu_irq_enabled(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 			unsigned type);
+void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev);
 
 int amdgpu_irq_add_domain(struct amdgpu_device *adev);
 void amdgpu_irq_remove_domain(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index f0dafa514fe4..6674d40eb3ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -28,21 +28,15 @@
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
 
-static void amdgpu_job_free_handler(struct work_struct *ws)
+static void amdgpu_job_timedout(struct amd_sched_job *s_job)
 {
-	struct amdgpu_job *job = container_of(ws, struct amdgpu_job, base.work_free_job);
-	amd_sched_job_put(&job->base);
-}
+	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
 
-void amdgpu_job_timeout_func(struct work_struct *work)
-{
-	struct amdgpu_job *job = container_of(work, struct amdgpu_job, base.work_tdr.work);
 	DRM_ERROR("ring %s timeout, last signaled seq=%u, last emitted seq=%u\n",
-				job->base.sched->name,
-				(uint32_t)atomic_read(&job->ring->fence_drv.last_seq),
-				job->ring->fence_drv.sync_seq);
-
-	amd_sched_job_put(&job->base);
+		  job->base.sched->name,
+		  atomic_read(&job->ring->fence_drv.last_seq),
+		  job->ring->fence_drv.sync_seq);
+	amdgpu_gpu_reset(job->adev);
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
@@ -63,7 +57,6 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 	(*job)->vm = vm;
 	(*job)->ibs = (void *)&(*job)[1];
 	(*job)->num_ibs = num_ibs;
-	INIT_WORK(&(*job)->base.work_free_job, amdgpu_job_free_handler);
 
 	amdgpu_sync_create(&(*job)->sync);
 
@@ -86,27 +79,33 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
 	return r;
 }
 
-void amdgpu_job_free(struct amdgpu_job *job)
+void amdgpu_job_free_resources(struct amdgpu_job *job)
 {
-	unsigned i;
 	struct fence *f;
+	unsigned i;
+
 	/* use sched fence if available */
-	f = (job->base.s_fence)? &job->base.s_fence->base : job->fence;
+	f = job->base.s_fence ? &job->base.s_fence->finished : job->fence;
 
 	for (i = 0; i < job->num_ibs; ++i)
-		amdgpu_sa_bo_free(job->adev, &job->ibs[i].sa_bo, f);
-	fence_put(job->fence);
+		amdgpu_ib_free(job->adev, &job->ibs[i], f);
+}
 
-	amdgpu_bo_unref(&job->uf_bo);
-	amdgpu_sync_free(&job->sync);
+void amdgpu_job_free_cb(struct amd_sched_job *s_job)
+{
+	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
 
-	if (!job->base.use_sched)
-		kfree(job);
+	fence_put(job->fence);
+	amdgpu_sync_free(&job->sync);
+	kfree(job);
 }
 
-void amdgpu_job_free_func(struct kref *refcount)
+void amdgpu_job_free(struct amdgpu_job *job)
 {
-	struct amdgpu_job *job = container_of(refcount, struct amdgpu_job, base.refcount);
+	amdgpu_job_free_resources(job);
+
+	fence_put(job->fence);
+	amdgpu_sync_free(&job->sync);
 	kfree(job);
 }
 
@@ -114,22 +113,20 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 		      struct amd_sched_entity *entity, void *owner,
 		      struct fence **f)
 {
-	struct fence *fence;
 	int r;
 	job->ring = ring;
 
 	if (!f)
 		return -EINVAL;
 
-	r = amd_sched_job_init(&job->base, &ring->sched,
-			       entity, amdgpu_job_timeout_func,
-			       amdgpu_job_free_func, owner, &fence);
+	r = amd_sched_job_init(&job->base, &ring->sched, entity, owner);
 	if (r)
 		return r;
 
 	job->owner = owner;
 	job->ctx = entity->fence_context;
-	*f = fence_get(fence);
+	*f = fence_get(&job->base.s_fence->finished);
+	amdgpu_job_free_resources(job);
 	amd_sched_entity_push_job(&job->base);
 
 	return 0;
@@ -147,8 +144,8 @@ static struct fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)
 		int r;
 
 		r = amdgpu_vm_grab_id(vm, ring, &job->sync,
-				      &job->base.s_fence->base,
-				      &job->vm_id, &job->vm_pd_addr);
+				      &job->base.s_fence->finished,
+				      job);
 		if (r)
 			DRM_ERROR("Error getting VM ID (%d)\n", r);
 
@@ -170,29 +167,24 @@ static struct fence *amdgpu_job_run(struct amd_sched_job *sched_job)
 	}
 	job = to_amdgpu_job(sched_job);
 
-	r = amdgpu_sync_wait(&job->sync);
-	if (r) {
-		DRM_ERROR("failed to sync wait (%d)\n", r);
-		return NULL;
-	}
+	BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
 
 	trace_amdgpu_sched_run_job(job);
 	r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs,
 			       job->sync.last_vm_update, job, &fence);
-	if (r) {
+	if (r)
 		DRM_ERROR("Error scheduling IBs (%d)\n", r);
-		goto err;
-	}
 
-err:
-	job->fence = fence;
-	amdgpu_job_free(job);
+	/* if gpu reset, hw fence will be replaced here */
+	fence_put(job->fence);
+	job->fence = fence_get(fence);
+	amdgpu_job_free_resources(job);
 	return fence;
 }
 
 const struct amd_sched_backend_ops amdgpu_sched_ops = {
 	.dependency = amdgpu_job_dependency,
 	.run_job = amdgpu_job_run,
-	.begin_job = amd_sched_job_begin,
-	.finish_job = amd_sched_job_finish,
+	.timedout_job = amdgpu_job_timedout,
+	.free_job = amdgpu_job_free_cb
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index d851ea15059f..d942654a1de0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -60,7 +60,10 @@ int amdgpu_driver_unload_kms(struct drm_device *dev)
 	if (adev->rmmio == NULL)
 		goto done_free;
 
-	pm_runtime_get_sync(dev->dev);
+	if (amdgpu_device_is_px(dev)) {
+		pm_runtime_get_sync(dev->dev);
+		pm_runtime_forbid(dev->dev);
+	}
 
 	amdgpu_amdkfd_device_fini(adev);
 
@@ -135,13 +138,75 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	}
 
 out:
-	if (r)
+	if (r) {
+		/* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */
+		if (adev->rmmio && amdgpu_device_is_px(dev))
+			pm_runtime_put_noidle(dev->dev);
 		amdgpu_driver_unload_kms(dev);
-
+	}
 
 	return r;
 }
 
+static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
+				struct drm_amdgpu_query_fw *query_fw,
+				struct amdgpu_device *adev)
+{
+	switch (query_fw->fw_type) {
+	case AMDGPU_INFO_FW_VCE:
+		fw_info->ver = adev->vce.fw_version;
+		fw_info->feature = adev->vce.fb_version;
+		break;
+	case AMDGPU_INFO_FW_UVD:
+		fw_info->ver = adev->uvd.fw_version;
+		fw_info->feature = 0;
+		break;
+	case AMDGPU_INFO_FW_GMC:
+		fw_info->ver = adev->mc.fw_version;
+		fw_info->feature = 0;
+		break;
+	case AMDGPU_INFO_FW_GFX_ME:
+		fw_info->ver = adev->gfx.me_fw_version;
+		fw_info->feature = adev->gfx.me_feature_version;
+		break;
+	case AMDGPU_INFO_FW_GFX_PFP:
+		fw_info->ver = adev->gfx.pfp_fw_version;
+		fw_info->feature = adev->gfx.pfp_feature_version;
+		break;
+	case AMDGPU_INFO_FW_GFX_CE:
+		fw_info->ver = adev->gfx.ce_fw_version;
+		fw_info->feature = adev->gfx.ce_feature_version;
+		break;
+	case AMDGPU_INFO_FW_GFX_RLC:
+		fw_info->ver = adev->gfx.rlc_fw_version;
+		fw_info->feature = adev->gfx.rlc_feature_version;
+		break;
+	case AMDGPU_INFO_FW_GFX_MEC:
+		if (query_fw->index == 0) {
+			fw_info->ver = adev->gfx.mec_fw_version;
+			fw_info->feature = adev->gfx.mec_feature_version;
+		} else if (query_fw->index == 1) {
+			fw_info->ver = adev->gfx.mec2_fw_version;
+			fw_info->feature = adev->gfx.mec2_feature_version;
+		} else
+			return -EINVAL;
+		break;
+	case AMDGPU_INFO_FW_SMC:
+		fw_info->ver = adev->pm.fw_version;
+		fw_info->feature = 0;
+		break;
+	case AMDGPU_INFO_FW_SDMA:
+		if (query_fw->index >= adev->sdma.num_instances)
+			return -EINVAL;
+		fw_info->ver = adev->sdma.instance[query_fw->index].fw_version;
+		fw_info->feature = adev->sdma.instance[query_fw->index].feature_version;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /*
  * Userspace get information ioctl
  */
@@ -288,67 +353,20 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		return copy_to_user(out, &count, min(size, 4u)) ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_TIMESTAMP:
-		ui64 = amdgpu_asic_get_gpu_clock_counter(adev);
+		ui64 = amdgpu_gfx_get_gpu_clock_counter(adev);
 		return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
 	case AMDGPU_INFO_FW_VERSION: {
 		struct drm_amdgpu_info_firmware fw_info;
+		int ret;
 
 		/* We only support one instance of each IP block right now. */
 		if (info->query_fw.ip_instance != 0)
 			return -EINVAL;
 
-		switch (info->query_fw.fw_type) {
-		case AMDGPU_INFO_FW_VCE:
-			fw_info.ver = adev->vce.fw_version;
-			fw_info.feature = adev->vce.fb_version;
-			break;
-		case AMDGPU_INFO_FW_UVD:
-			fw_info.ver = adev->uvd.fw_version;
-			fw_info.feature = 0;
-			break;
-		case AMDGPU_INFO_FW_GMC:
-			fw_info.ver = adev->mc.fw_version;
-			fw_info.feature = 0;
-			break;
-		case AMDGPU_INFO_FW_GFX_ME:
-			fw_info.ver = adev->gfx.me_fw_version;
-			fw_info.feature = adev->gfx.me_feature_version;
-			break;
-		case AMDGPU_INFO_FW_GFX_PFP:
-			fw_info.ver = adev->gfx.pfp_fw_version;
-			fw_info.feature = adev->gfx.pfp_feature_version;
-			break;
-		case AMDGPU_INFO_FW_GFX_CE:
-			fw_info.ver = adev->gfx.ce_fw_version;
-			fw_info.feature = adev->gfx.ce_feature_version;
-			break;
-		case AMDGPU_INFO_FW_GFX_RLC:
-			fw_info.ver = adev->gfx.rlc_fw_version;
-			fw_info.feature = adev->gfx.rlc_feature_version;
-			break;
-		case AMDGPU_INFO_FW_GFX_MEC:
-			if (info->query_fw.index == 0) {
-				fw_info.ver = adev->gfx.mec_fw_version;
-				fw_info.feature = adev->gfx.mec_feature_version;
-			} else if (info->query_fw.index == 1) {
-				fw_info.ver = adev->gfx.mec2_fw_version;
-				fw_info.feature = adev->gfx.mec2_feature_version;
-			} else
-				return -EINVAL;
-			break;
-		case AMDGPU_INFO_FW_SMC:
-			fw_info.ver = adev->pm.fw_version;
-			fw_info.feature = 0;
-			break;
-		case AMDGPU_INFO_FW_SDMA:
-			if (info->query_fw.index >= adev->sdma.num_instances)
-				return -EINVAL;
-			fw_info.ver = adev->sdma.instance[info->query_fw.index].fw_version;
-			fw_info.feature = adev->sdma.instance[info->query_fw.index].feature_version;
-			break;
-		default:
-			return -EINVAL;
-		}
+		ret = amdgpu_firmware_info(&fw_info, &info->query_fw, adev);
+		if (ret)
+			return ret;
+
 		return copy_to_user(out, &fw_info,
 				    min((size_t)size, sizeof(fw_info))) ? -EFAULT : 0;
 	}
@@ -566,6 +584,9 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 
 	amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr);
 
+	amdgpu_uvd_free_handles(adev, file_priv);
+	amdgpu_vce_free_handles(adev, file_priv);
+
 	amdgpu_vm_fini(adev, &fpriv->vm);
 
 	idr_for_each_entry(&fpriv->bo_list_handles, list, handle)
@@ -590,10 +611,6 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 void amdgpu_driver_preclose_kms(struct drm_device *dev,
 				struct drm_file *file_priv)
 {
-	struct amdgpu_device *adev = dev->dev_private;
-
-	amdgpu_uvd_free_handles(adev, file_priv);
-	amdgpu_vce_free_handles(adev, file_priv);
 }
 
 /*
@@ -756,3 +773,130 @@ const struct drm_ioctl_desc amdgpu_ioctls_kms[] = {
 	DRM_IOCTL_DEF_DRV(AMDGPU_GEM_USERPTR, amdgpu_gem_userptr_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 };
 const int amdgpu_max_kms_ioctl = ARRAY_SIZE(amdgpu_ioctls_kms);
+
+/*
+ * Debugfs info
+ */
+#if defined(CONFIG_DEBUG_FS)
+
+static int amdgpu_debugfs_firmware_info(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct amdgpu_device *adev = dev->dev_private;
+	struct drm_amdgpu_info_firmware fw_info;
+	struct drm_amdgpu_query_fw query_fw;
+	int ret, i;
+
+	/* VCE */
+	query_fw.fw_type = AMDGPU_INFO_FW_VCE;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "VCE feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* UVD */
+	query_fw.fw_type = AMDGPU_INFO_FW_UVD;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "UVD feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* GMC */
+	query_fw.fw_type = AMDGPU_INFO_FW_GMC;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "MC feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* ME */
+	query_fw.fw_type = AMDGPU_INFO_FW_GFX_ME;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "ME feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* PFP */
+	query_fw.fw_type = AMDGPU_INFO_FW_GFX_PFP;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "PFP feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* CE */
+	query_fw.fw_type = AMDGPU_INFO_FW_GFX_CE;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "CE feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* RLC */
+	query_fw.fw_type = AMDGPU_INFO_FW_GFX_RLC;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "RLC feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* MEC */
+	query_fw.fw_type = AMDGPU_INFO_FW_GFX_MEC;
+	query_fw.index = 0;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "MEC feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* MEC2 */
+	if (adev->asic_type == CHIP_KAVERI ||
+	    (adev->asic_type > CHIP_TOPAZ && adev->asic_type != CHIP_STONEY)) {
+		query_fw.index = 1;
+		ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+		if (ret)
+			return ret;
+		seq_printf(m, "MEC2 feature version: %u, firmware version: 0x%08x\n",
+			   fw_info.feature, fw_info.ver);
+	}
+
+	/* SMC */
+	query_fw.fw_type = AMDGPU_INFO_FW_SMC;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
+	/* SDMA */
+	query_fw.fw_type = AMDGPU_INFO_FW_SDMA;
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		query_fw.index = i;
+		ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+		if (ret)
+			return ret;
+		seq_printf(m, "SDMA%d feature version: %u, firmware version: 0x%08x\n",
+			   i, fw_info.feature, fw_info.ver);
+	}
+
+	return 0;
+}
+
+static const struct drm_info_list amdgpu_firmware_info_list[] = {
+	{"amdgpu_firmware_info", amdgpu_debugfs_firmware_info, 0, NULL},
+};
+#endif
+
+int amdgpu_debugfs_firmware_init(struct amdgpu_device *adev)
+{
+#if defined(CONFIG_DEBUG_FS)
+	return amdgpu_debugfs_add_files(adev, amdgpu_firmware_info_list,
+					ARRAY_SIZE(amdgpu_firmware_info_list));
+#else
+	return 0;
+#endif
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 7ecea83ce453..6f0873c75a25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -589,6 +589,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 			   struct ttm_mem_reg *new_mem)
 {
 	struct amdgpu_bo *rbo;
+	struct ttm_mem_reg *old_mem = &bo->mem;
 
 	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
 		return;
@@ -602,6 +603,8 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 
 	/* move_notify is called before move happens */
 	amdgpu_update_memory_usage(rbo->adev, &bo->mem, new_mem);
+
+	trace_amdgpu_ttm_bo_move(rbo, new_mem->mem_type, old_mem->mem_type);
 }
 
 int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 0e13d80d2a95..ff63b88b0ffa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -347,6 +347,8 @@ static ssize_t amdgpu_get_pp_dpm_sclk(struct device *dev,
 
 	if (adev->pp_enabled)
 		size = amdgpu_dpm_print_clock_levels(adev, PP_SCLK, buf);
+	else if (adev->pm.funcs->print_clock_levels)
+		size = adev->pm.funcs->print_clock_levels(adev, PP_SCLK, buf);
 
 	return size;
 }
@@ -363,7 +365,9 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
 	uint32_t i, mask = 0;
 	char sub_str[2];
 
-	for (i = 0; i < strlen(buf) - 1; i++) {
+	for (i = 0; i < strlen(buf); i++) {
+		if (*(buf + i) == '\n')
+			continue;
 		sub_str[0] = *(buf + i);
 		sub_str[1] = '\0';
 		ret = kstrtol(sub_str, 0, &level);
@@ -377,6 +381,8 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
 
 	if (adev->pp_enabled)
 		amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask);
+	else if (adev->pm.funcs->force_clock_level)
+		adev->pm.funcs->force_clock_level(adev, PP_SCLK, mask);
 fail:
 	return count;
 }
@@ -391,6 +397,8 @@ static ssize_t amdgpu_get_pp_dpm_mclk(struct device *dev,
 
 	if (adev->pp_enabled)
 		size = amdgpu_dpm_print_clock_levels(adev, PP_MCLK, buf);
+	else if (adev->pm.funcs->print_clock_levels)
+		size = adev->pm.funcs->print_clock_levels(adev, PP_MCLK, buf);
 
 	return size;
 }
@@ -407,7 +415,9 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
 	uint32_t i, mask = 0;
 	char sub_str[2];
 
-	for (i = 0; i < strlen(buf) - 1; i++) {
+	for (i = 0; i < strlen(buf); i++) {
+		if (*(buf + i) == '\n')
+			continue;
 		sub_str[0] = *(buf + i);
 		sub_str[1] = '\0';
 		ret = kstrtol(sub_str, 0, &level);
@@ -421,6 +431,8 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
 
 	if (adev->pp_enabled)
 		amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask);
+	else if (adev->pm.funcs->force_clock_level)
+		adev->pm.funcs->force_clock_level(adev, PP_MCLK, mask);
 fail:
 	return count;
 }
@@ -435,6 +447,8 @@ static ssize_t amdgpu_get_pp_dpm_pcie(struct device *dev,
 
 	if (adev->pp_enabled)
 		size = amdgpu_dpm_print_clock_levels(adev, PP_PCIE, buf);
+	else if (adev->pm.funcs->print_clock_levels)
+		size = adev->pm.funcs->print_clock_levels(adev, PP_PCIE, buf);
 
 	return size;
 }
@@ -451,7 +465,9 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 	uint32_t i, mask = 0;
 	char sub_str[2];
 
-	for (i = 0; i < strlen(buf) - 1; i++) {
+	for (i = 0; i < strlen(buf); i++) {
+		if (*(buf + i) == '\n')
+			continue;
 		sub_str[0] = *(buf + i);
 		sub_str[1] = '\0';
 		ret = kstrtol(sub_str, 0, &level);
@@ -465,6 +481,100 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 
 	if (adev->pp_enabled)
 		amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask);
+	else if (adev->pm.funcs->force_clock_level)
+		adev->pm.funcs->force_clock_level(adev, PP_PCIE, mask);
+fail:
+	return count;
+}
+
+static ssize_t amdgpu_get_pp_sclk_od(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	uint32_t value = 0;
+
+	if (adev->pp_enabled)
+		value = amdgpu_dpm_get_sclk_od(adev);
+	else if (adev->pm.funcs->get_sclk_od)
+		value = adev->pm.funcs->get_sclk_od(adev);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", value);
+}
+
+static ssize_t amdgpu_set_pp_sclk_od(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t count)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	int ret;
+	long int value;
+
+	ret = kstrtol(buf, 0, &value);
+
+	if (ret) {
+		count = -EINVAL;
+		goto fail;
+	}
+
+	if (adev->pp_enabled) {
+		amdgpu_dpm_set_sclk_od(adev, (uint32_t)value);
+		amdgpu_dpm_dispatch_task(adev, AMD_PP_EVENT_READJUST_POWER_STATE, NULL, NULL);
+	} else if (adev->pm.funcs->set_sclk_od) {
+		adev->pm.funcs->set_sclk_od(adev, (uint32_t)value);
+		adev->pm.dpm.current_ps = adev->pm.dpm.boot_ps;
+		amdgpu_pm_compute_clocks(adev);
+	}
+
+fail:
+	return count;
+}
+
+static ssize_t amdgpu_get_pp_mclk_od(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	uint32_t value = 0;
+
+	if (adev->pp_enabled)
+		value = amdgpu_dpm_get_mclk_od(adev);
+	else if (adev->pm.funcs->get_mclk_od)
+		value = adev->pm.funcs->get_mclk_od(adev);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", value);
+}
+
+static ssize_t amdgpu_set_pp_mclk_od(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t count)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	int ret;
+	long int value;
+
+	ret = kstrtol(buf, 0, &value);
+
+	if (ret) {
+		count = -EINVAL;
+		goto fail;
+	}
+
+	if (adev->pp_enabled) {
+		amdgpu_dpm_set_mclk_od(adev, (uint32_t)value);
+		amdgpu_dpm_dispatch_task(adev, AMD_PP_EVENT_READJUST_POWER_STATE, NULL, NULL);
+	} else if (adev->pm.funcs->set_mclk_od) {
+		adev->pm.funcs->set_mclk_od(adev, (uint32_t)value);
+		adev->pm.dpm.current_ps = adev->pm.dpm.boot_ps;
+		amdgpu_pm_compute_clocks(adev);
+	}
+
 fail:
 	return count;
 }
@@ -490,6 +600,12 @@ static DEVICE_ATTR(pp_dpm_mclk, S_IRUGO | S_IWUSR,
 static DEVICE_ATTR(pp_dpm_pcie, S_IRUGO | S_IWUSR,
 		amdgpu_get_pp_dpm_pcie,
 		amdgpu_set_pp_dpm_pcie);
+static DEVICE_ATTR(pp_sclk_od, S_IRUGO | S_IWUSR,
+		amdgpu_get_pp_sclk_od,
+		amdgpu_set_pp_sclk_od);
+static DEVICE_ATTR(pp_mclk_od, S_IRUGO | S_IWUSR,
+		amdgpu_get_pp_mclk_od,
+		amdgpu_set_pp_mclk_od);
 
 static ssize_t amdgpu_hwmon_show_temp(struct device *dev,
 				      struct device_attribute *attr,
@@ -1108,22 +1224,34 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 			DRM_ERROR("failed to create device file pp_table\n");
 			return ret;
 		}
-		ret = device_create_file(adev->dev, &dev_attr_pp_dpm_sclk);
-		if (ret) {
-			DRM_ERROR("failed to create device file pp_dpm_sclk\n");
-			return ret;
-		}
-		ret = device_create_file(adev->dev, &dev_attr_pp_dpm_mclk);
-		if (ret) {
-			DRM_ERROR("failed to create device file pp_dpm_mclk\n");
-			return ret;
-		}
-		ret = device_create_file(adev->dev, &dev_attr_pp_dpm_pcie);
-		if (ret) {
-			DRM_ERROR("failed to create device file pp_dpm_pcie\n");
-			return ret;
-		}
 	}
+
+	ret = device_create_file(adev->dev, &dev_attr_pp_dpm_sclk);
+	if (ret) {
+		DRM_ERROR("failed to create device file pp_dpm_sclk\n");
+		return ret;
+	}
+	ret = device_create_file(adev->dev, &dev_attr_pp_dpm_mclk);
+	if (ret) {
+		DRM_ERROR("failed to create device file pp_dpm_mclk\n");
+		return ret;
+	}
+	ret = device_create_file(adev->dev, &dev_attr_pp_dpm_pcie);
+	if (ret) {
+		DRM_ERROR("failed to create device file pp_dpm_pcie\n");
+		return ret;
+	}
+	ret = device_create_file(adev->dev, &dev_attr_pp_sclk_od);
+	if (ret) {
+		DRM_ERROR("failed to create device file pp_sclk_od\n");
+		return ret;
+	}
+	ret = device_create_file(adev->dev, &dev_attr_pp_mclk_od);
+	if (ret) {
+		DRM_ERROR("failed to create device file pp_mclk_od\n");
+		return ret;
+	}
+
 	ret = amdgpu_debugfs_pm_init(adev);
 	if (ret) {
 		DRM_ERROR("Failed to register debugfs file for dpm!\n");
@@ -1146,10 +1274,12 @@ void amdgpu_pm_sysfs_fini(struct amdgpu_device *adev)
 		device_remove_file(adev->dev, &dev_attr_pp_cur_state);
 		device_remove_file(adev->dev, &dev_attr_pp_force_state);
 		device_remove_file(adev->dev, &dev_attr_pp_table);
-		device_remove_file(adev->dev, &dev_attr_pp_dpm_sclk);
-		device_remove_file(adev->dev, &dev_attr_pp_dpm_mclk);
-		device_remove_file(adev->dev, &dev_attr_pp_dpm_pcie);
 	}
+	device_remove_file(adev->dev, &dev_attr_pp_dpm_sclk);
+	device_remove_file(adev->dev, &dev_attr_pp_dpm_mclk);
+	device_remove_file(adev->dev, &dev_attr_pp_dpm_pcie);
+	device_remove_file(adev->dev, &dev_attr_pp_sclk_od);
+	device_remove_file(adev->dev, &dev_attr_pp_mclk_od);
 }
 
 void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
index 82256558e0f5..c5738a22b690 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
@@ -52,6 +52,7 @@ static int amdgpu_powerplay_init(struct amdgpu_device *adev)
 		pp_init->chip_family = adev->family;
 		pp_init->chip_id = adev->asic_type;
 		pp_init->device = amdgpu_cgs_create_device(adev);
+		pp_init->powercontainment_enabled = amdgpu_powercontainment;
 
 		ret = amd_powerplay_init(pp_init, amd_pp);
 		kfree(pp_init);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 870f9494252c..85aeb0a804bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -28,6 +28,7 @@
  */
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/debugfs.h>
 #include <drm/drmP.h>
 #include <drm/amdgpu_drm.h>
 #include "amdgpu.h"
@@ -48,6 +49,7 @@
  */
 static int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
 				    struct amdgpu_ring *ring);
+static void amdgpu_debugfs_ring_fini(struct amdgpu_ring *ring);
 
 /**
  * amdgpu_ring_alloc - allocate space on the ring buffer
@@ -73,6 +75,10 @@ int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned ndw)
 
 	ring->count_dw = ndw;
 	ring->wptr_old = ring->wptr;
+
+	if (ring->funcs->begin_use)
+		ring->funcs->begin_use(ring);
+
 	return 0;
 }
 
@@ -125,6 +131,9 @@ void amdgpu_ring_commit(struct amdgpu_ring *ring)
 
 	mb();
 	amdgpu_ring_set_wptr(ring);
+
+	if (ring->funcs->end_use)
+		ring->funcs->end_use(ring);
 }
 
 /**
@@ -137,78 +146,9 @@ void amdgpu_ring_commit(struct amdgpu_ring *ring)
 void amdgpu_ring_undo(struct amdgpu_ring *ring)
 {
 	ring->wptr = ring->wptr_old;
-}
-
-/**
- * amdgpu_ring_backup - Back up the content of a ring
- *
- * @ring: the ring we want to back up
- *
- * Saves all unprocessed commits from a ring, returns the number of dwords saved.
- */
-unsigned amdgpu_ring_backup(struct amdgpu_ring *ring,
-			    uint32_t **data)
-{
-	unsigned size, ptr, i;
-
-	*data = NULL;
-
-	if (ring->ring_obj == NULL)
-		return 0;
-
-	/* it doesn't make sense to save anything if all fences are signaled */
-	if (!amdgpu_fence_count_emitted(ring))
-		return 0;
-
-	ptr = le32_to_cpu(*ring->next_rptr_cpu_addr);
-
-	size = ring->wptr + (ring->ring_size / 4);
-	size -= ptr;
-	size &= ring->ptr_mask;
-	if (size == 0)
-		return 0;
-
-	/* and then save the content of the ring */
-	*data = kmalloc_array(size, sizeof(uint32_t), GFP_KERNEL);
-	if (!*data)
-		return 0;
-	for (i = 0; i < size; ++i) {
-		(*data)[i] = ring->ring[ptr++];
-		ptr &= ring->ptr_mask;
-	}
-
-	return size;
-}
-
-/**
- * amdgpu_ring_restore - append saved commands to the ring again
- *
- * @ring: ring to append commands to
- * @size: number of dwords we want to write
- * @data: saved commands
- *
- * Allocates space on the ring and restore the previously saved commands.
- */
-int amdgpu_ring_restore(struct amdgpu_ring *ring,
-			unsigned size, uint32_t *data)
-{
-	int i, r;
-
-	if (!size || !data)
-		return 0;
-
-	/* restore the saved ring content */
-	r = amdgpu_ring_alloc(ring, size);
-	if (r)
-		return r;
-
-	for (i = 0; i < size; ++i) {
-		amdgpu_ring_write(ring, data[i]);
-	}
 
-	amdgpu_ring_commit(ring);
-	kfree(data);
-	return 0;
+	if (ring->funcs->end_use)
+		ring->funcs->end_use(ring);
 }
 
 /**
@@ -260,14 +200,6 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		return r;
 	}
 
-	r = amdgpu_wb_get(adev, &ring->next_rptr_offs);
-	if (r) {
-		dev_err(adev->dev, "(%d) ring next_rptr wb alloc failed\n", r);
-		return r;
-	}
-	ring->next_rptr_gpu_addr = adev->wb.gpu_addr + ring->next_rptr_offs * 4;
-	ring->next_rptr_cpu_addr = &adev->wb.wb[ring->next_rptr_offs];
-
 	r = amdgpu_wb_get(adev, &ring->cond_exe_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring cond_exec_polling wb alloc failed\n", r);
@@ -276,7 +208,6 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 	ring->cond_exe_gpu_addr = adev->wb.gpu_addr + (ring->cond_exe_offs * 4);
 	ring->cond_exe_cpu_addr = &adev->wb.wb[ring->cond_exe_offs];
 
-	spin_lock_init(&ring->fence_lock);
 	r = amdgpu_fence_driver_start_ring(ring, irq_src, irq_type);
 	if (r) {
 		dev_err(adev->dev, "failed initializing fences (%d).\n", r);
@@ -310,6 +241,9 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		}
 		r = amdgpu_bo_kmap(ring->ring_obj,
 				       (void **)&ring->ring);
+
+		memset((void *)ring->ring, 0, ring->ring_size);
+
 		amdgpu_bo_unreserve(ring->ring_obj);
 		if (r) {
 			dev_err(adev->dev, "(%d) ring map failed\n", r);
@@ -347,7 +281,6 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
 	amdgpu_wb_free(ring->adev, ring->fence_offs);
 	amdgpu_wb_free(ring->adev, ring->rptr_offs);
 	amdgpu_wb_free(ring->adev, ring->wptr_offs);
-	amdgpu_wb_free(ring->adev, ring->next_rptr_offs);
 
 	if (ring_obj) {
 		r = amdgpu_bo_reserve(ring_obj, false);
@@ -358,6 +291,7 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
 		}
 		amdgpu_bo_unref(&ring_obj);
 	}
+	amdgpu_debugfs_ring_fini(ring);
 }
 
 /*
@@ -365,57 +299,62 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
  */
 #if defined(CONFIG_DEBUG_FS)
 
-static int amdgpu_debugfs_ring_info(struct seq_file *m, void *data)
+/* Layout of file is 12 bytes consisting of
+ * - rptr
+ * - wptr
+ * - driver's copy of wptr
+ *
+ * followed by n-words of ring data
+ */
+static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf,
+					size_t size, loff_t *pos)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct amdgpu_device *adev = dev->dev_private;
-	int roffset = (unsigned long)node->info_ent->data;
-	struct amdgpu_ring *ring = (void *)(((uint8_t*)adev) + roffset);
-	uint32_t rptr, wptr, rptr_next;
-	unsigned i;
-
-	wptr = amdgpu_ring_get_wptr(ring);
-	seq_printf(m, "wptr: 0x%08x [%5d]\n", wptr, wptr);
-
-	rptr = amdgpu_ring_get_rptr(ring);
-	rptr_next = le32_to_cpu(*ring->next_rptr_cpu_addr);
-
-	seq_printf(m, "rptr: 0x%08x [%5d]\n", rptr, rptr);
-
-	seq_printf(m, "driver's copy of the wptr: 0x%08x [%5d]\n",
-		   ring->wptr, ring->wptr);
-
-	if (!ring->ready)
-		return 0;
-
-	/* print 8 dw before current rptr as often it's the last executed
-	 * packet that is the root issue
-	 */
-	i = (rptr + ring->ptr_mask + 1 - 32) & ring->ptr_mask;
-	while (i != rptr) {
-		seq_printf(m, "r[%5d]=0x%08x", i, ring->ring[i]);
-		if (i == rptr)
-			seq_puts(m, " *");
-		if (i == rptr_next)
-			seq_puts(m, " #");
-		seq_puts(m, "\n");
-		i = (i + 1) & ring->ptr_mask;
+	struct amdgpu_ring *ring = (struct amdgpu_ring*)f->f_inode->i_private;
+	int r, i;
+	uint32_t value, result, early[3];
+
+	if (*pos & 3 || size & 3)
+		return -EINVAL;
+
+	result = 0;
+
+	if (*pos < 12) {
+		early[0] = amdgpu_ring_get_rptr(ring);
+		early[1] = amdgpu_ring_get_wptr(ring);
+		early[2] = ring->wptr;
+		for (i = *pos / 4; i < 3 && size; i++) {
+			r = put_user(early[i], (uint32_t *)buf);
+			if (r)
+				return r;
+			buf += 4;
+			result += 4;
+			size -= 4;
+			*pos += 4;
+		}
 	}
-	while (i != wptr) {
-		seq_printf(m, "r[%5d]=0x%08x", i, ring->ring[i]);
-		if (i == rptr)
-			seq_puts(m, " *");
-		if (i == rptr_next)
-			seq_puts(m, " #");
-		seq_puts(m, "\n");
-		i = (i + 1) & ring->ptr_mask;
+
+	while (size) {
+		if (*pos >= (ring->ring_size + 12))
+			return result;
+			
+		value = ring->ring[(*pos - 12)/4];
+		r = put_user(value, (uint32_t*)buf);
+		if (r)
+			return r;
+		buf += 4;
+		result += 4;
+		size -= 4;
+		*pos += 4;
 	}
-	return 0;
+
+	return result;
 }
 
-static struct drm_info_list amdgpu_debugfs_ring_info_list[AMDGPU_MAX_RINGS];
-static char amdgpu_debugfs_ring_names[AMDGPU_MAX_RINGS][32];
+static const struct file_operations amdgpu_debugfs_ring_fops = {
+	.owner = THIS_MODULE,
+	.read = amdgpu_debugfs_ring_read,
+	.llseek = default_llseek
+};
 
 #endif
 
@@ -423,28 +362,27 @@ static int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
 				    struct amdgpu_ring *ring)
 {
 #if defined(CONFIG_DEBUG_FS)
-	unsigned offset = (uint8_t*)ring - (uint8_t*)adev;
-	unsigned i;
-	struct drm_info_list *info;
-	char *name;
-
-	for (i = 0; i < ARRAY_SIZE(amdgpu_debugfs_ring_info_list); ++i) {
-		info = &amdgpu_debugfs_ring_info_list[i];
-		if (!info->data)
-			break;
-	}
+	struct drm_minor *minor = adev->ddev->primary;
+	struct dentry *ent, *root = minor->debugfs_root;
+	char name[32];
 
-	if (i == ARRAY_SIZE(amdgpu_debugfs_ring_info_list))
-		return -ENOSPC;
-
-	name = &amdgpu_debugfs_ring_names[i][0];
 	sprintf(name, "amdgpu_ring_%s", ring->name);
-	info->name = name;
-	info->show = amdgpu_debugfs_ring_info;
-	info->driver_features = 0;
-	info->data = (void*)(uintptr_t)offset;
 
-	return amdgpu_debugfs_add_files(adev, info, 1);
+	ent = debugfs_create_file(name,
+				  S_IFREG | S_IRUGO, root,
+				  ring, &amdgpu_debugfs_ring_fops);
+	if (IS_ERR(ent))
+		return PTR_ERR(ent);
+
+	i_size_write(ent->d_inode, ring->ring_size + 12);
+	ring->ent = ent;
 #endif
 	return 0;
 }
+
+static void amdgpu_debugfs_ring_fini(struct amdgpu_ring *ring)
+{
+#if defined(CONFIG_DEBUG_FS)
+	debugfs_remove(ring->ent);
+#endif
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 48618ee324eb..d8af37a845f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -428,7 +428,7 @@ void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
 			   soffset, eoffset, eoffset - soffset);
 
 		if (i->fence)
-			seq_printf(m, " protected by 0x%08x on context %d",
+			seq_printf(m, " protected by 0x%08x on context %llu",
 				   i->fence->seqno, i->fence->context);
 
 		seq_printf(m, "\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index 34a92808bbd4..5c8d3022fb87 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -223,13 +223,16 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_sync_is_idle - test if all fences are signaled
+ * amdgpu_sync_peek_fence - get the next fence not signaled yet
  *
  * @sync: the sync object
+ * @ring: optional ring to use for test
  *
- * Returns true if all fences in the sync object are signaled.
+ * Returns the next fence not signaled yet without removing it from the sync
+ * object.
  */
-bool amdgpu_sync_is_idle(struct amdgpu_sync *sync)
+struct fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync,
+				     struct amdgpu_ring *ring)
 {
 	struct amdgpu_sync_entry *e;
 	struct hlist_node *tmp;
@@ -237,6 +240,19 @@ bool amdgpu_sync_is_idle(struct amdgpu_sync *sync)
 
 	hash_for_each_safe(sync->fences, i, tmp, e, node) {
 		struct fence *f = e->fence;
+		struct amd_sched_fence *s_fence = to_amd_sched_fence(f);
+
+		if (ring && s_fence) {
+			/* For fences from the same ring it is sufficient
+			 * when they are scheduled.
+			 */
+			if (s_fence->sched == &ring->sched) {
+				if (fence_is_signaled(&s_fence->scheduled))
+					continue;
+
+				return &s_fence->scheduled;
+			}
+		}
 
 		if (fence_is_signaled(f)) {
 			hash_del(&e->node);
@@ -245,58 +261,19 @@ bool amdgpu_sync_is_idle(struct amdgpu_sync *sync)
 			continue;
 		}
 
-		return false;
+		return f;
 	}
 
-	return true;
+	return NULL;
 }
 
 /**
- * amdgpu_sync_cycle_fences - move fences from one sync object into another
+ * amdgpu_sync_get_fence - get the next fence from the sync object
  *
- * @dst: the destination sync object
- * @src: the source sync object
- * @fence: fence to add to source
+ * @sync: sync object to use
  *
- * Remove all fences from source and put them into destination and add
- * fence as new one into source.
+ * Get and removes the next fence from the sync object not signaled yet.
  */
-int amdgpu_sync_cycle_fences(struct amdgpu_sync *dst, struct amdgpu_sync *src,
-			     struct fence *fence)
-{
-	struct amdgpu_sync_entry *e, *newone;
-	struct hlist_node *tmp;
-	int i;
-
-	/* Allocate the new entry before moving the old ones */
-	newone = kmem_cache_alloc(amdgpu_sync_slab, GFP_KERNEL);
-	if (!newone)
-		return -ENOMEM;
-
-	hash_for_each_safe(src->fences, i, tmp, e, node) {
-		struct fence *f = e->fence;
-
-		hash_del(&e->node);
-		if (fence_is_signaled(f)) {
-			fence_put(f);
-			kmem_cache_free(amdgpu_sync_slab, e);
-			continue;
-		}
-
-		if (amdgpu_sync_add_later(dst, f)) {
-			kmem_cache_free(amdgpu_sync_slab, e);
-			continue;
-		}
-
-		hash_add(dst->fences, &e->node, f->context);
-	}
-
-	hash_add(src->fences, &newone->node, fence->context);
-	newone->fence = fence_get(fence);
-
-	return 0;
-}
-
 struct fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync)
 {
 	struct amdgpu_sync_entry *e;
@@ -319,25 +296,6 @@ struct fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync)
 	return NULL;
 }
 
-int amdgpu_sync_wait(struct amdgpu_sync *sync)
-{
-	struct amdgpu_sync_entry *e;
-	struct hlist_node *tmp;
-	int i, r;
-
-	hash_for_each_safe(sync->fences, i, tmp, e, node) {
-		r = fence_wait(e->fence, false);
-		if (r)
-			return r;
-
-		hash_del(&e->node);
-		fence_put(e->fence);
-		kmem_cache_free(amdgpu_sync_slab, e);
-	}
-
-	return 0;
-}
-
 /**
  * amdgpu_sync_free - free the sync object
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 26a5f4acf584..0d8d65eb46cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -11,19 +11,68 @@
 #define TRACE_SYSTEM amdgpu
 #define TRACE_INCLUDE_FILE amdgpu_trace
 
+TRACE_EVENT(amdgpu_mm_rreg,
+	    TP_PROTO(unsigned did, uint32_t reg, uint32_t value),
+	    TP_ARGS(did, reg, value),
+	    TP_STRUCT__entry(
+				__field(unsigned, did)
+				__field(uint32_t, reg)
+				__field(uint32_t, value)
+			    ),
+	    TP_fast_assign(
+			   __entry->did = did;
+			   __entry->reg = reg;
+			   __entry->value = value;
+			   ),
+	    TP_printk("0x%04lx, 0x%04lx, 0x%08lx",
+		      (unsigned long)__entry->did,
+		      (unsigned long)__entry->reg,
+		      (unsigned long)__entry->value)
+);
+
+TRACE_EVENT(amdgpu_mm_wreg,
+	    TP_PROTO(unsigned did, uint32_t reg, uint32_t value),
+	    TP_ARGS(did, reg, value),
+	    TP_STRUCT__entry(
+				__field(unsigned, did)
+				__field(uint32_t, reg)
+				__field(uint32_t, value)
+			    ),
+	    TP_fast_assign(
+			   __entry->did = did;
+			   __entry->reg = reg;
+			   __entry->value = value;
+			   ),
+	    TP_printk("0x%04lx, 0x%04lx, 0x%08lx",
+		      (unsigned long)__entry->did,
+		      (unsigned long)__entry->reg,
+		      (unsigned long)__entry->value)
+);
+
 TRACE_EVENT(amdgpu_bo_create,
 	    TP_PROTO(struct amdgpu_bo *bo),
 	    TP_ARGS(bo),
 	    TP_STRUCT__entry(
 			     __field(struct amdgpu_bo *, bo)
 			     __field(u32, pages)
+			     __field(u32, type)
+			     __field(u32, prefer)
+			     __field(u32, allow)
+			     __field(u32, visible)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->bo = bo;
 			   __entry->pages = bo->tbo.num_pages;
+			   __entry->type = bo->tbo.mem.mem_type;
+			   __entry->prefer = bo->prefered_domains;
+			   __entry->allow = bo->allowed_domains;
+			   __entry->visible = bo->flags;
 			   ),
-	    TP_printk("bo=%p, pages=%u", __entry->bo, __entry->pages)
+
+	    TP_printk("bo=%p,pages=%u,type=%d,prefered=%d,allowed=%d,visible=%d",
+		       __entry->bo, __entry->pages, __entry->type,
+		       __entry->prefer, __entry->allow, __entry->visible)
 );
 
 TRACE_EVENT(amdgpu_cs,
@@ -64,7 +113,7 @@ TRACE_EVENT(amdgpu_cs_ioctl,
 			   __entry->adev = job->adev;
 			   __entry->sched_job = &job->base;
 			   __entry->ib = job->ibs;
-			   __entry->fence = &job->base.s_fence->base;
+			   __entry->fence = &job->base.s_fence->finished;
 			   __entry->ring_name = job->ring->name;
 			   __entry->num_ibs = job->num_ibs;
 			   ),
@@ -89,7 +138,7 @@ TRACE_EVENT(amdgpu_sched_run_job,
 			   __entry->adev = job->adev;
 			   __entry->sched_job = &job->base;
 			   __entry->ib = job->ibs;
-			   __entry->fence = &job->base.s_fence->base;
+			   __entry->fence = &job->base.s_fence->finished;
 			   __entry->ring_name = job->ring->name;
 			   __entry->num_ibs = job->num_ibs;
 			   ),
@@ -100,24 +149,26 @@ TRACE_EVENT(amdgpu_sched_run_job,
 
 
 TRACE_EVENT(amdgpu_vm_grab_id,
-	    TP_PROTO(struct amdgpu_vm *vm, int ring, unsigned vmid,
-		     uint64_t pd_addr),
-	    TP_ARGS(vm, ring, vmid, pd_addr),
+	    TP_PROTO(struct amdgpu_vm *vm, int ring, struct amdgpu_job *job),
+	    TP_ARGS(vm, ring, job),
 	    TP_STRUCT__entry(
 			     __field(struct amdgpu_vm *, vm)
 			     __field(u32, ring)
 			     __field(u32, vmid)
 			     __field(u64, pd_addr)
+			     __field(u32, needs_flush)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->vm = vm;
 			   __entry->ring = ring;
-			   __entry->vmid = vmid;
-			   __entry->pd_addr = pd_addr;
+			   __entry->vmid = job->vm_id;
+			   __entry->pd_addr = job->vm_pd_addr;
+			   __entry->needs_flush = job->vm_needs_flush;
 			   ),
-	    TP_printk("vm=%p, ring=%u, id=%u, pd_addr=%010Lx", __entry->vm,
-		      __entry->ring, __entry->vmid, __entry->pd_addr)
+	    TP_printk("vm=%p, ring=%u, id=%u, pd_addr=%010Lx needs_flush=%u",
+		      __entry->vm, __entry->ring, __entry->vmid,
+		      __entry->pd_addr, __entry->needs_flush)
 );
 
 TRACE_EVENT(amdgpu_vm_bo_map,
@@ -244,13 +295,55 @@ TRACE_EVENT(amdgpu_bo_list_set,
 	    TP_STRUCT__entry(
 			     __field(struct amdgpu_bo_list *, list)
 			     __field(struct amdgpu_bo *, bo)
+			     __field(u64, bo_size)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->list = list;
 			   __entry->bo = bo;
+			   __entry->bo_size = amdgpu_bo_size(bo);
 			   ),
-	    TP_printk("list=%p, bo=%p", __entry->list, __entry->bo)
+	    TP_printk("list=%p, bo=%p, bo_size = %Ld",
+		      __entry->list,
+		      __entry->bo,
+		      __entry->bo_size)
+);
+
+TRACE_EVENT(amdgpu_cs_bo_status,
+	    TP_PROTO(uint64_t total_bo, uint64_t total_size),
+	    TP_ARGS(total_bo, total_size),
+	    TP_STRUCT__entry(
+			__field(u64, total_bo)
+			__field(u64, total_size)
+			),
+
+	    TP_fast_assign(
+			__entry->total_bo = total_bo;
+			__entry->total_size = total_size;
+			),
+	    TP_printk("total bo size = %Ld, total bo count = %Ld",
+			__entry->total_bo, __entry->total_size)
+);
+
+TRACE_EVENT(amdgpu_ttm_bo_move,
+	    TP_PROTO(struct amdgpu_bo* bo, uint32_t new_placement, uint32_t old_placement),
+	    TP_ARGS(bo, new_placement, old_placement),
+	    TP_STRUCT__entry(
+			__field(struct amdgpu_bo *, bo)
+			__field(u64, bo_size)
+			__field(u32, new_placement)
+			__field(u32, old_placement)
+			),
+
+	    TP_fast_assign(
+			__entry->bo      = bo;
+			__entry->bo_size = amdgpu_bo_size(bo);
+			__entry->new_placement = new_placement;
+			__entry->old_placement = old_placement;
+			),
+	    TP_printk("bo=%p from:%d to %d with size = %Ld",
+			__entry->bo, __entry->old_placement,
+			__entry->new_placement, __entry->bo_size)
 );
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 3b9053af4762..b7742e62972a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -286,9 +286,10 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 	r = amdgpu_copy_buffer(ring, old_start, new_start,
 			       new_mem->num_pages * PAGE_SIZE, /* bytes */
 			       bo->resv, &fence);
-	/* FIXME: handle copy error */
-	r = ttm_bo_move_accel_cleanup(bo, fence,
-				      evict, no_wait_gpu, new_mem);
+	if (r)
+		return r;
+
+	r = ttm_bo_pipeline_move(bo, fence, evict, new_mem);
 	fence_put(fence);
 	return r;
 }
@@ -396,6 +397,11 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo,
 		return -EINVAL;
 
 	adev = amdgpu_get_adev(bo->bdev);
+
+	/* remember the eviction */
+	if (evict)
+		atomic64_inc(&adev->num_evictions);
+
 	if (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL) {
 		amdgpu_move_null(bo, new_mem);
 		return 0;
@@ -429,7 +435,8 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo,
 
 	if (r) {
 memcpy:
-		r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
+		r = ttm_bo_move_memcpy(bo, evict, interruptible,
+				       no_wait_gpu, new_mem);
 		if (r) {
 			return r;
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index d9c88d13f8db..b11f4e8868d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -40,9 +40,16 @@
 #include "uvd/uvd_4_2_d.h"
 
 /* 1 second timeout */
-#define UVD_IDLE_TIMEOUT_MS	1000
+#define UVD_IDLE_TIMEOUT	msecs_to_jiffies(1000)
+
+/* Firmware versions for VI */
+#define FW_1_65_10	((1 << 24) | (65 << 16) | (10 << 8))
+#define FW_1_87_11	((1 << 24) | (87 << 16) | (11 << 8))
+#define FW_1_87_12	((1 << 24) | (87 << 16) | (12 << 8))
+#define FW_1_37_15	((1 << 24) | (37 << 16) | (15 << 8))
+
 /* Polaris10/11 firmware version */
-#define FW_1_66_16 ((1 << 24) | (66 << 16) | (16 << 8))
+#define FW_1_66_16	((1 << 24) | (66 << 16) | (16 << 8))
 
 /* Firmware Names */
 #ifdef CONFIG_DRM_AMDGPU_CIK
@@ -92,7 +99,6 @@ MODULE_FIRMWARE(FIRMWARE_STONEY);
 MODULE_FIRMWARE(FIRMWARE_POLARIS10);
 MODULE_FIRMWARE(FIRMWARE_POLARIS11);
 
-static void amdgpu_uvd_note_usage(struct amdgpu_device *adev);
 static void amdgpu_uvd_idle_work_handler(struct work_struct *work);
 
 int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
@@ -246,6 +252,23 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	if (!amdgpu_ip_block_version_cmp(adev, AMD_IP_BLOCK_TYPE_UVD, 5, 0))
 		adev->uvd.address_64_bit = true;
 
+	switch (adev->asic_type) {
+	case CHIP_TONGA:
+		adev->uvd.use_ctx_buf = adev->uvd.fw_version >= FW_1_65_10;
+		break;
+	case CHIP_CARRIZO:
+		adev->uvd.use_ctx_buf = adev->uvd.fw_version >= FW_1_87_11;
+		break;
+	case CHIP_FIJI:
+		adev->uvd.use_ctx_buf = adev->uvd.fw_version >= FW_1_87_12;
+		break;
+	case CHIP_STONEY:
+		adev->uvd.use_ctx_buf = adev->uvd.fw_version >= FW_1_37_15;
+		break;
+	default:
+		adev->uvd.use_ctx_buf = adev->asic_type >= CHIP_POLARIS10;
+	}
+
 	return 0;
 }
 
@@ -346,8 +369,6 @@ void amdgpu_uvd_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
 		if (handle != 0 && adev->uvd.filp[i] == filp) {
 			struct fence *fence;
 
-			amdgpu_uvd_note_usage(adev);
-
 			r = amdgpu_uvd_get_destroy_msg(ring, handle,
 						       false, &fence);
 			if (r) {
@@ -438,7 +459,7 @@ static int amdgpu_uvd_cs_msg_decode(struct amdgpu_device *adev, uint32_t *msg,
 	unsigned fs_in_mb = width_in_mb * height_in_mb;
 
 	unsigned image_size, tmp, min_dpb_size, num_dpb_buffer;
-	unsigned min_ctx_size = 0;
+	unsigned min_ctx_size = ~0;
 
 	image_size = width * height;
 	image_size += image_size / 2;
@@ -557,7 +578,7 @@ static int amdgpu_uvd_cs_msg_decode(struct amdgpu_device *adev, uint32_t *msg,
 		/* reference picture buffer */
 		min_dpb_size = image_size * num_dpb_buffer;
 
-		if (adev->asic_type < CHIP_POLARIS10){
+		if (!adev->uvd.use_ctx_buf){
 			/* macroblock context buffer */
 			min_dpb_size +=
 				width_in_mb * height_in_mb * num_dpb_buffer * 192;
@@ -662,7 +683,7 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 		}
 
 		DRM_ERROR("No more free UVD handles!\n");
-		return -EINVAL;
+		return -ENOSPC;
 
 	case 1:
 		/* it's a decode msg, calc buffer sizes */
@@ -913,8 +934,6 @@ int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx)
 		return -EINVAL;
 	}
 
-	amdgpu_uvd_note_usage(ctx.parser->adev);
-
 	return 0;
 }
 
@@ -968,7 +987,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 
 	if (direct) {
 		r = amdgpu_ib_schedule(ring, 1, ib, NULL, NULL, &f);
-		job->fence = f;
+		job->fence = fence_get(f);
 		if (r)
 			goto err_free;
 
@@ -1106,24 +1125,18 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 	if (fences == 0 && handles == 0) {
 		if (adev->pm.dpm_enabled) {
 			amdgpu_dpm_enable_uvd(adev, false);
-			/* just work around for uvd clock remain high even
-			 * when uvd dpm disabled on Polaris10 */
-			if (adev->asic_type == CHIP_POLARIS10)
-				amdgpu_asic_set_uvd_clocks(adev, 0, 0);
 		} else {
 			amdgpu_asic_set_uvd_clocks(adev, 0, 0);
 		}
 	} else {
-		schedule_delayed_work(&adev->uvd.idle_work,
-				      msecs_to_jiffies(UVD_IDLE_TIMEOUT_MS));
+		schedule_delayed_work(&adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
 	}
 }
 
-static void amdgpu_uvd_note_usage(struct amdgpu_device *adev)
+void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring)
 {
+	struct amdgpu_device *adev = ring->adev;
 	bool set_clocks = !cancel_delayed_work_sync(&adev->uvd.idle_work);
-	set_clocks &= schedule_delayed_work(&adev->uvd.idle_work,
-					    msecs_to_jiffies(UVD_IDLE_TIMEOUT_MS));
 
 	if (set_clocks) {
 		if (adev->pm.dpm_enabled) {
@@ -1133,3 +1146,48 @@ static void amdgpu_uvd_note_usage(struct amdgpu_device *adev)
 		}
 	}
 }
+
+void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring)
+{
+	schedule_delayed_work(&ring->adev->uvd.idle_work, UVD_IDLE_TIMEOUT);
+}
+
+/**
+ * amdgpu_uvd_ring_test_ib - test ib execution
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Test if we can successfully execute an IB
+ */
+int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout)
+{
+	struct fence *fence;
+	long r;
+
+	r = amdgpu_uvd_get_create_msg(ring, 1, NULL);
+	if (r) {
+		DRM_ERROR("amdgpu: failed to get create msg (%ld).\n", r);
+		goto error;
+	}
+
+	r = amdgpu_uvd_get_destroy_msg(ring, 1, true, &fence);
+	if (r) {
+		DRM_ERROR("amdgpu: failed to get destroy ib (%ld).\n", r);
+		goto error;
+	}
+
+	r = fence_wait_timeout(fence, false, timeout);
+	if (r == 0) {
+		DRM_ERROR("amdgpu: IB test timed out.\n");
+		r = -ETIMEDOUT;
+	} else if (r < 0) {
+		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
+	} else {
+		DRM_INFO("ib test on ring %d succeeded\n",  ring->idx);
+		r = 0;
+	}
+
+error:
+	fence_put(fence);
+	return r;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
index 9a3b449081a7..c850009602d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
@@ -35,5 +35,8 @@ int amdgpu_uvd_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 void amdgpu_uvd_free_handles(struct amdgpu_device *adev,
 			     struct drm_file *filp);
 int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx);
+void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring);
+void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring);
+int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 875626a2eccb..05865ce35351 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -36,7 +36,7 @@
 #include "cikd.h"
 
 /* 1 second timeout */
-#define VCE_IDLE_TIMEOUT_MS	1000
+#define VCE_IDLE_TIMEOUT	msecs_to_jiffies(1000)
 
 /* Firmware Names */
 #ifdef CONFIG_DRM_AMDGPU_CIK
@@ -85,8 +85,6 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 	unsigned ucode_version, version_major, version_minor, binary_id;
 	int i, r;
 
-	INIT_DELAYED_WORK(&adev->vce.idle_work, amdgpu_vce_idle_work_handler);
-
 	switch (adev->asic_type) {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	case CHIP_BONAIRE:
@@ -197,6 +195,9 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 		adev->vce.filp[i] = NULL;
 	}
 
+	INIT_DELAYED_WORK(&adev->vce.idle_work, amdgpu_vce_idle_work_handler);
+	mutex_init(&adev->vce.idle_mutex);
+
 	return 0;
 }
 
@@ -220,6 +221,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 	amdgpu_ring_fini(&adev->vce.ring[1]);
 
 	release_firmware(adev->vce.fw);
+	mutex_destroy(&adev->vce.idle_mutex);
 
 	return 0;
 }
@@ -310,37 +312,44 @@ static void amdgpu_vce_idle_work_handler(struct work_struct *work)
 			amdgpu_asic_set_vce_clocks(adev, 0, 0);
 		}
 	} else {
-		schedule_delayed_work(&adev->vce.idle_work,
-				      msecs_to_jiffies(VCE_IDLE_TIMEOUT_MS));
+		schedule_delayed_work(&adev->vce.idle_work, VCE_IDLE_TIMEOUT);
 	}
 }
 
 /**
- * amdgpu_vce_note_usage - power up VCE
+ * amdgpu_vce_ring_begin_use - power up VCE
  *
- * @adev: amdgpu_device pointer
+ * @ring: amdgpu ring
  *
  * Make sure VCE is powerd up when we want to use it
  */
-static void amdgpu_vce_note_usage(struct amdgpu_device *adev)
+void amdgpu_vce_ring_begin_use(struct amdgpu_ring *ring)
 {
-	bool streams_changed = false;
-	bool set_clocks = !cancel_delayed_work_sync(&adev->vce.idle_work);
-	set_clocks &= schedule_delayed_work(&adev->vce.idle_work,
-					    msecs_to_jiffies(VCE_IDLE_TIMEOUT_MS));
-
-	if (adev->pm.dpm_enabled) {
-		/* XXX figure out if the streams changed */
-		streams_changed = false;
-	}
+	struct amdgpu_device *adev = ring->adev;
+	bool set_clocks;
 
-	if (set_clocks || streams_changed) {
+	mutex_lock(&adev->vce.idle_mutex);
+	set_clocks = !cancel_delayed_work_sync(&adev->vce.idle_work);
+	if (set_clocks) {
 		if (adev->pm.dpm_enabled) {
 			amdgpu_dpm_enable_vce(adev, true);
 		} else {
 			amdgpu_asic_set_vce_clocks(adev, 53300, 40000);
 		}
 	}
+	mutex_unlock(&adev->vce.idle_mutex);
+}
+
+/**
+ * amdgpu_vce_ring_end_use - power VCE down
+ *
+ * @ring: amdgpu ring
+ *
+ * Schedule work to power VCE down again
+ */
+void amdgpu_vce_ring_end_use(struct amdgpu_ring *ring)
+{
+	schedule_delayed_work(&ring->adev->vce.idle_work, VCE_IDLE_TIMEOUT);
 }
 
 /**
@@ -357,11 +366,10 @@ void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
 	int i, r;
 	for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) {
 		uint32_t handle = atomic_read(&adev->vce.handles[i]);
+
 		if (!handle || adev->vce.filp[i] != filp)
 			continue;
 
-		amdgpu_vce_note_usage(adev);
-
 		r = amdgpu_vce_get_destroy_msg(ring, handle, false, NULL);
 		if (r)
 			DRM_ERROR("Error destroying VCE handle (%d)!\n", r);
@@ -437,7 +445,7 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 		ib->ptr[i] = 0x0;
 
 	r = amdgpu_ib_schedule(ring, 1, ib, NULL, NULL, &f);
-	job->fence = f;
+	job->fence = fence_get(f);
 	if (r)
 		goto err;
 
@@ -469,7 +477,6 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct fence *f = NULL;
-	uint64_t dummy;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -477,7 +484,6 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
 
 	/* stitch together an VCE destroy msg */
 	ib->length_dw = 0;
@@ -485,11 +491,14 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session cmd */
 	ib->ptr[ib->length_dw++] = handle;
 
-	ib->ptr[ib->length_dw++] = 0x00000014; /* len */
-	ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
-	ib->ptr[ib->length_dw++] = 0x00000001;
+	ib->ptr[ib->length_dw++] = 0x00000020; /* len */
+	ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
+	ib->ptr[ib->length_dw++] = 0xffffffff; /* next task info, set to 0xffffffff if no */
+	ib->ptr[ib->length_dw++] = 0x00000001; /* destroy session */
+	ib->ptr[ib->length_dw++] = 0x00000000;
+	ib->ptr[ib->length_dw++] = 0x00000000;
+	ib->ptr[ib->length_dw++] = 0xffffffff; /* feedback is not needed, set to 0xffffffff and firmware will not output feedback */
+	ib->ptr[ib->length_dw++] = 0x00000000;
 
 	ib->ptr[ib->length_dw++] = 0x00000008; /* len */
 	ib->ptr[ib->length_dw++] = 0x02000001; /* destroy cmd */
@@ -499,7 +508,7 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 
 	if (direct) {
 		r = amdgpu_ib_schedule(ring, 1, ib, NULL, NULL, &f);
-		job->fence = f;
+		job->fence = fence_get(f);
 		if (r)
 			goto err;
 
@@ -580,12 +589,10 @@ static int amdgpu_vce_cs_reloc(struct amdgpu_cs_parser *p, uint32_t ib_idx,
  * we we don't have another free session index.
  */
 static int amdgpu_vce_validate_handle(struct amdgpu_cs_parser *p,
-				      uint32_t handle, bool *allocated)
+				      uint32_t handle, uint32_t *allocated)
 {
 	unsigned i;
 
-	*allocated = false;
-
 	/* validate the handle */
 	for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) {
 		if (atomic_read(&p->adev->vce.handles[i]) == handle) {
@@ -602,7 +609,7 @@ static int amdgpu_vce_validate_handle(struct amdgpu_cs_parser *p,
 		if (!atomic_cmpxchg(&p->adev->vce.handles[i], 0, handle)) {
 			p->adev->vce.filp[i] = p->filp;
 			p->adev->vce.img_size[i] = 0;
-			*allocated = true;
+			*allocated |= 1 << i;
 			return i;
 		}
 	}
@@ -622,15 +629,13 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 	struct amdgpu_ib *ib = &p->job->ibs[ib_idx];
 	unsigned fb_idx = 0, bs_idx = 0;
 	int session_idx = -1;
-	bool destroyed = false;
-	bool created = false;
-	bool allocated = false;
+	uint32_t destroyed = 0;
+	uint32_t created = 0;
+	uint32_t allocated = 0;
 	uint32_t tmp, handle = 0;
 	uint32_t *size = &tmp;
 	int i, r = 0, idx = 0;
 
-	amdgpu_vce_note_usage(p->adev);
-
 	while (idx < ib->length_dw) {
 		uint32_t len = amdgpu_get_ib_value(p, ib_idx, idx);
 		uint32_t cmd = amdgpu_get_ib_value(p, ib_idx, idx + 1);
@@ -641,30 +646,30 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 			goto out;
 		}
 
-		if (destroyed) {
-			DRM_ERROR("No other command allowed after destroy!\n");
-			r = -EINVAL;
-			goto out;
-		}
-
 		switch (cmd) {
-		case 0x00000001: // session
+		case 0x00000001: /* session */
 			handle = amdgpu_get_ib_value(p, ib_idx, idx + 2);
 			session_idx = amdgpu_vce_validate_handle(p, handle,
 								 &allocated);
-			if (session_idx < 0)
-				return session_idx;
+			if (session_idx < 0) {
+				r = session_idx;
+				goto out;
+			}
 			size = &p->adev->vce.img_size[session_idx];
 			break;
 
-		case 0x00000002: // task info
+		case 0x00000002: /* task info */
 			fb_idx = amdgpu_get_ib_value(p, ib_idx, idx + 6);
 			bs_idx = amdgpu_get_ib_value(p, ib_idx, idx + 7);
 			break;
 
-		case 0x01000001: // create
-			created = true;
-			if (!allocated) {
+		case 0x01000001: /* create */
+			created |= 1 << session_idx;
+			if (destroyed & (1 << session_idx)) {
+				destroyed &= ~(1 << session_idx);
+				allocated |= 1 << session_idx;
+
+			} else if (!(allocated & (1 << session_idx))) {
 				DRM_ERROR("Handle already in use!\n");
 				r = -EINVAL;
 				goto out;
@@ -675,16 +680,16 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 				8 * 3 / 2;
 			break;
 
-		case 0x04000001: // config extension
-		case 0x04000002: // pic control
-		case 0x04000005: // rate control
-		case 0x04000007: // motion estimation
-		case 0x04000008: // rdo
-		case 0x04000009: // vui
-		case 0x05000002: // auxiliary buffer
+		case 0x04000001: /* config extension */
+		case 0x04000002: /* pic control */
+		case 0x04000005: /* rate control */
+		case 0x04000007: /* motion estimation */
+		case 0x04000008: /* rdo */
+		case 0x04000009: /* vui */
+		case 0x05000002: /* auxiliary buffer */
 			break;
 
-		case 0x03000001: // encode
+		case 0x03000001: /* encode */
 			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 10, idx + 9,
 						*size, 0);
 			if (r)
@@ -696,18 +701,18 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 				goto out;
 			break;
 
-		case 0x02000001: // destroy
-			destroyed = true;
+		case 0x02000001: /* destroy */
+			destroyed |= 1 << session_idx;
 			break;
 
-		case 0x05000001: // context buffer
+		case 0x05000001: /* context buffer */
 			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2,
 						*size * 2, 0);
 			if (r)
 				goto out;
 			break;
 
-		case 0x05000004: // video bitstream buffer
+		case 0x05000004: /* video bitstream buffer */
 			tmp = amdgpu_get_ib_value(p, ib_idx, idx + 4);
 			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2,
 						tmp, bs_idx);
@@ -715,7 +720,7 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 				goto out;
 			break;
 
-		case 0x05000005: // feedback buffer
+		case 0x05000005: /* feedback buffer */
 			r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2,
 						4096, fb_idx);
 			if (r)
@@ -737,21 +742,24 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 		idx += len / 4;
 	}
 
-	if (allocated && !created) {
+	if (allocated & ~created) {
 		DRM_ERROR("New session without create command!\n");
 		r = -ENOENT;
 	}
 
 out:
-	if ((!r && destroyed) || (r && allocated)) {
-		/*
-		 * IB contains a destroy msg or we have allocated an
-		 * handle and got an error, anyway free the handle
-		 */
-		for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i)
-			atomic_cmpxchg(&p->adev->vce.handles[i], handle, 0);
+	if (!r) {
+		/* No error, free all destroyed handle slots */
+		tmp = destroyed;
+	} else {
+		/* Error during parsing, free all allocated handle slots */
+		tmp = allocated;
 	}
 
+	for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i)
+		if (tmp & (1 << i))
+			atomic_set(&p->adev->vce.handles[i], 0);
+
 	return r;
 }
 
@@ -837,10 +845,10 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring)
  * @ring: the engine to test on
  *
  */
-int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring)
+int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct fence *fence = NULL;
-	int r;
+	long r;
 
 	/* skip vce ring1 ib test for now, since it's not reliable */
 	if (ring == &ring->adev->vce.ring[1])
@@ -848,21 +856,25 @@ int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring)
 
 	r = amdgpu_vce_get_create_msg(ring, 1, NULL);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get create msg (%d).\n", r);
+		DRM_ERROR("amdgpu: failed to get create msg (%ld).\n", r);
 		goto error;
 	}
 
 	r = amdgpu_vce_get_destroy_msg(ring, 1, true, &fence);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get destroy ib (%d).\n", r);
+		DRM_ERROR("amdgpu: failed to get destroy ib (%ld).\n", r);
 		goto error;
 	}
 
-	r = fence_wait(fence, false);
-	if (r) {
-		DRM_ERROR("amdgpu: fence wait failed (%d).\n", r);
+	r = fence_wait_timeout(fence, false, timeout);
+	if (r == 0) {
+		DRM_ERROR("amdgpu: IB test timed out.\n");
+		r = -ETIMEDOUT;
+	} else if (r < 0) {
+		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 	} else {
 		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		r = 0;
 	}
 error:
 	fence_put(fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
index f40cf761c66f..63f83d0d985c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
@@ -39,6 +39,8 @@ void amdgpu_vce_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib,
 void amdgpu_vce_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
 				unsigned flags);
 int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring);
-int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring);
+int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout);
+void amdgpu_vce_ring_begin_use(struct amdgpu_ring *ring);
+void amdgpu_vce_ring_end_use(struct amdgpu_ring *ring);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 9f36ed30ba11..8e642fc48df4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -25,6 +25,7 @@
  *          Alex Deucher
  *          Jerome Glisse
  */
+#include <linux/fence-array.h>
 #include <drm/drmP.h>
 #include <drm/amdgpu_drm.h>
 #include "amdgpu.h"
@@ -114,16 +115,26 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 /**
  * amdgpu_vm_get_bos - add the vm BOs to a duplicates list
  *
+ * @adev: amdgpu device pointer
  * @vm: vm providing the BOs
  * @duplicates: head of duplicates list
  *
  * Add the page directory to the BO duplicates list
  * for command submission.
  */
-void amdgpu_vm_get_pt_bos(struct amdgpu_vm *vm, struct list_head *duplicates)
+void amdgpu_vm_get_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			  struct list_head *duplicates)
 {
+	uint64_t num_evictions;
 	unsigned i;
 
+	/* We only need to validate the page tables
+	 * if they aren't already valid.
+	 */
+	num_evictions = atomic64_read(&adev->num_evictions);
+	if (num_evictions == vm->last_eviction_counter)
+		return;
+
 	/* add the vm page table to the list */
 	for (i = 0; i <= vm->max_pde_used; ++i) {
 		struct amdgpu_bo_list_entry *entry = &vm->page_tables[i].entry;
@@ -162,6 +173,13 @@ void amdgpu_vm_move_pt_bos_in_lru(struct amdgpu_device *adev,
 	spin_unlock(&glob->lru_lock);
 }
 
+static bool amdgpu_vm_is_gpu_reset(struct amdgpu_device *adev,
+			      struct amdgpu_vm_id *id)
+{
+	return id->current_gpu_reset_count !=
+		atomic_read(&adev->gpu_reset_counter) ? true : false;
+}
+
 /**
  * amdgpu_vm_grab_id - allocate the next free VMID
  *
@@ -174,18 +192,67 @@ void amdgpu_vm_move_pt_bos_in_lru(struct amdgpu_device *adev,
  */
 int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 		      struct amdgpu_sync *sync, struct fence *fence,
-		      unsigned *vm_id, uint64_t *vm_pd_addr)
+		      struct amdgpu_job *job)
 {
-	uint64_t pd_addr = amdgpu_bo_gpu_offset(vm->page_directory);
 	struct amdgpu_device *adev = ring->adev;
+	uint64_t fence_context = adev->fence_context + ring->idx;
 	struct fence *updates = sync->last_vm_update;
-	struct amdgpu_vm_id *id;
-	unsigned i = ring->idx;
-	int r;
+	struct amdgpu_vm_id *id, *idle;
+	struct fence **fences;
+	unsigned i;
+	int r = 0;
+
+	fences = kmalloc_array(sizeof(void *), adev->vm_manager.num_ids,
+			       GFP_KERNEL);
+	if (!fences)
+		return -ENOMEM;
 
 	mutex_lock(&adev->vm_manager.lock);
 
+	/* Check if we have an idle VMID */
+	i = 0;
+	list_for_each_entry(idle, &adev->vm_manager.ids_lru, list) {
+		fences[i] = amdgpu_sync_peek_fence(&idle->active, ring);
+		if (!fences[i])
+			break;
+		++i;
+	}
+
+	/* If we can't find a idle VMID to use, wait till one becomes available */
+	if (&idle->list == &adev->vm_manager.ids_lru) {
+		u64 fence_context = adev->vm_manager.fence_context + ring->idx;
+		unsigned seqno = ++adev->vm_manager.seqno[ring->idx];
+		struct fence_array *array;
+		unsigned j;
+
+		for (j = 0; j < i; ++j)
+			fence_get(fences[j]);
+
+		array = fence_array_create(i, fences, fence_context,
+					   seqno, true);
+		if (!array) {
+			for (j = 0; j < i; ++j)
+				fence_put(fences[j]);
+			kfree(fences);
+			r = -ENOMEM;
+			goto error;
+		}
+
+
+		r = amdgpu_sync_fence(ring->adev, sync, &array->base);
+		fence_put(&array->base);
+		if (r)
+			goto error;
+
+		mutex_unlock(&adev->vm_manager.lock);
+		return 0;
+
+	}
+	kfree(fences);
+
+	job->vm_needs_flush = true;
 	/* Check if we can use a VMID already assigned to this VM */
+	i = ring->idx;
 	do {
 		struct fence *flushed;
 
@@ -196,67 +263,52 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 		/* Check all the prerequisites to using this VMID */
 		if (!id)
 			continue;
+		if (amdgpu_vm_is_gpu_reset(adev, id))
+			continue;
 
 		if (atomic64_read(&id->owner) != vm->client_id)
 			continue;
 
-		if (pd_addr != id->pd_gpu_addr)
+		if (job->vm_pd_addr != id->pd_gpu_addr)
 			continue;
 
-		if (id->last_user != ring &&
-		    (!id->last_flush || !fence_is_signaled(id->last_flush)))
+		if (!id->last_flush)
 			continue;
 
-		flushed  = id->flushed_updates;
-		if (updates && (!flushed || fence_is_later(updates, flushed)))
+		if (id->last_flush->context != fence_context &&
+		    !fence_is_signaled(id->last_flush))
 			continue;
 
-		/* Good we can use this VMID */
-		if (id->last_user == ring) {
-			r = amdgpu_sync_fence(ring->adev, sync,
-					      id->first);
-			if (r)
-				goto error;
-		}
+		flushed  = id->flushed_updates;
+		if (updates &&
+		    (!flushed || fence_is_later(updates, flushed)))
+			continue;
 
-		/* And remember this submission as user of the VMID */
+		/* Good we can use this VMID. Remember this submission as
+		 * user of the VMID.
+		 */
 		r = amdgpu_sync_fence(ring->adev, &id->active, fence);
 		if (r)
 			goto error;
 
+		id->current_gpu_reset_count = atomic_read(&adev->gpu_reset_counter);
 		list_move_tail(&id->list, &adev->vm_manager.ids_lru);
 		vm->ids[ring->idx] = id;
 
-		*vm_id = id - adev->vm_manager.ids;
-		*vm_pd_addr = AMDGPU_VM_NO_FLUSH;
-		trace_amdgpu_vm_grab_id(vm, ring->idx, *vm_id, *vm_pd_addr);
+		job->vm_id = id - adev->vm_manager.ids;
+		job->vm_needs_flush = false;
+		trace_amdgpu_vm_grab_id(vm, ring->idx, job);
 
 		mutex_unlock(&adev->vm_manager.lock);
 		return 0;
 
 	} while (i != ring->idx);
 
-	id = list_first_entry(&adev->vm_manager.ids_lru,
-			      struct amdgpu_vm_id,
-			      list);
-
-	if (!amdgpu_sync_is_idle(&id->active)) {
-		struct list_head *head = &adev->vm_manager.ids_lru;
-		struct amdgpu_vm_id *tmp;
+	/* Still no ID to use? Then use the idle one found earlier */
+	id = idle;
 
-		list_for_each_entry_safe(id, tmp, &adev->vm_manager.ids_lru,
-					 list) {
-			if (amdgpu_sync_is_idle(&id->active)) {
-				list_move(&id->list, head);
-				head = &id->list;
-			}
-		}
-		id = list_first_entry(&adev->vm_manager.ids_lru,
-				      struct amdgpu_vm_id,
-				      list);
-	}
-
-	r = amdgpu_sync_cycle_fences(sync, &id->active, fence);
+	/* Remember this submission as user of the VMID */
+	r = amdgpu_sync_fence(ring->adev, &id->active, fence);
 	if (r)
 		goto error;
 
@@ -269,22 +321,46 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 	fence_put(id->flushed_updates);
 	id->flushed_updates = fence_get(updates);
 
-	id->pd_gpu_addr = pd_addr;
-
+	id->pd_gpu_addr = job->vm_pd_addr;
+	id->current_gpu_reset_count = atomic_read(&adev->gpu_reset_counter);
 	list_move_tail(&id->list, &adev->vm_manager.ids_lru);
-	id->last_user = ring;
 	atomic64_set(&id->owner, vm->client_id);
 	vm->ids[ring->idx] = id;
 
-	*vm_id = id - adev->vm_manager.ids;
-	*vm_pd_addr = pd_addr;
-	trace_amdgpu_vm_grab_id(vm, ring->idx, *vm_id, *vm_pd_addr);
+	job->vm_id = id - adev->vm_manager.ids;
+	trace_amdgpu_vm_grab_id(vm, ring->idx, job);
 
 error:
 	mutex_unlock(&adev->vm_manager.lock);
 	return r;
 }
 
+static bool amdgpu_vm_ring_has_compute_vm_bug(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	const struct amdgpu_ip_block_version *ip_block;
+
+	if (ring->type != AMDGPU_RING_TYPE_COMPUTE)
+		/* only compute rings */
+		return false;
+
+	ip_block = amdgpu_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX);
+	if (!ip_block)
+		return false;
+
+	if (ip_block->major <= 7) {
+		/* gfx7 has no workaround */
+		return true;
+	} else if (ip_block->major == 8) {
+		if (adev->gfx.mec_fw_version >= 673)
+			/* gfx8 is fixed in MEC firmware 673 */
+			return false;
+		else
+			return true;
+	}
+	return false;
+}
+
 /**
  * amdgpu_vm_flush - hardware flush the vm
  *
@@ -294,59 +370,52 @@ error:
  *
  * Emit a VM flush when it is necessary.
  */
-int amdgpu_vm_flush(struct amdgpu_ring *ring,
-		    unsigned vm_id, uint64_t pd_addr,
-		    uint32_t gds_base, uint32_t gds_size,
-		    uint32_t gws_base, uint32_t gws_size,
-		    uint32_t oa_base, uint32_t oa_size)
+int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job)
 {
 	struct amdgpu_device *adev = ring->adev;
-	struct amdgpu_vm_id *id = &adev->vm_manager.ids[vm_id];
+	struct amdgpu_vm_id *id = &adev->vm_manager.ids[job->vm_id];
 	bool gds_switch_needed = ring->funcs->emit_gds_switch && (
-		id->gds_base != gds_base ||
-		id->gds_size != gds_size ||
-		id->gws_base != gws_base ||
-		id->gws_size != gws_size ||
-		id->oa_base != oa_base ||
-		id->oa_size != oa_size);
+		id->gds_base != job->gds_base ||
+		id->gds_size != job->gds_size ||
+		id->gws_base != job->gws_base ||
+		id->gws_size != job->gws_size ||
+		id->oa_base != job->oa_base ||
+		id->oa_size != job->oa_size);
 	int r;
 
 	if (ring->funcs->emit_pipeline_sync && (
-	    pd_addr != AMDGPU_VM_NO_FLUSH || gds_switch_needed ||
-		    ring->type == AMDGPU_RING_TYPE_COMPUTE))
+	    job->vm_needs_flush || gds_switch_needed ||
+	    amdgpu_vm_ring_has_compute_vm_bug(ring)))
 		amdgpu_ring_emit_pipeline_sync(ring);
 
-	if (ring->funcs->emit_vm_flush &&
-	    pd_addr != AMDGPU_VM_NO_FLUSH) {
+	if (ring->funcs->emit_vm_flush && (job->vm_needs_flush ||
+	    amdgpu_vm_is_gpu_reset(adev, id))) {
 		struct fence *fence;
 
-		trace_amdgpu_vm_flush(pd_addr, ring->idx, vm_id);
-		amdgpu_ring_emit_vm_flush(ring, vm_id, pd_addr);
+		trace_amdgpu_vm_flush(job->vm_pd_addr, ring->idx, job->vm_id);
+		amdgpu_ring_emit_vm_flush(ring, job->vm_id, job->vm_pd_addr);
+
+		r = amdgpu_fence_emit(ring, &fence);
+		if (r)
+			return r;
 
 		mutex_lock(&adev->vm_manager.lock);
-		if ((id->pd_gpu_addr == pd_addr) && (id->last_user == ring)) {
-			r = amdgpu_fence_emit(ring, &fence);
-			if (r) {
-				mutex_unlock(&adev->vm_manager.lock);
-				return r;
-			}
-			fence_put(id->last_flush);
-			id->last_flush = fence;
-		}
+		fence_put(id->last_flush);
+		id->last_flush = fence;
 		mutex_unlock(&adev->vm_manager.lock);
 	}
 
 	if (gds_switch_needed) {
-		id->gds_base = gds_base;
-		id->gds_size = gds_size;
-		id->gws_base = gws_base;
-		id->gws_size = gws_size;
-		id->oa_base = oa_base;
-		id->oa_size = oa_size;
-		amdgpu_ring_emit_gds_switch(ring, vm_id,
-					    gds_base, gds_size,
-					    gws_base, gws_size,
-					    oa_base, oa_size);
+		id->gds_base = job->gds_base;
+		id->gds_size = job->gds_size;
+		id->gws_base = job->gws_base;
+		id->gws_size = job->gws_size;
+		id->oa_base = job->oa_base;
+		id->oa_size = job->oa_size;
+		amdgpu_ring_emit_gds_switch(ring, job->vm_id,
+					    job->gds_base, job->gds_size,
+					    job->gws_base, job->gws_size,
+					    job->oa_base, job->oa_size);
 	}
 
 	return 0;
@@ -723,7 +792,7 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_device *adev,
  * @vm: requested vm
  * @start: start of GPU address range
  * @end: end of GPU address range
- * @dst: destination address to map to
+ * @dst: destination address to map to, the next dst inside the function
  * @flags: mapping flags
  *
  * Update the page tables in the range @start - @end.
@@ -737,49 +806,75 @@ static void amdgpu_vm_update_ptes(struct amdgpu_device *adev,
 {
 	const uint64_t mask = AMDGPU_VM_PTE_COUNT - 1;
 
-	uint64_t last_pe_start = ~0, last_pe_end = ~0, last_dst = ~0;
-	uint64_t addr;
+	uint64_t cur_pe_start, cur_pe_end, cur_dst;
+	uint64_t addr; /* next GPU address to be updated */
+	uint64_t pt_idx;
+	struct amdgpu_bo *pt;
+	unsigned nptes; /* next number of ptes to be updated */
+	uint64_t next_pe_start;
+
+	/* initialize the variables */
+	addr = start;
+	pt_idx = addr >> amdgpu_vm_block_size;
+	pt = vm->page_tables[pt_idx].entry.robj;
+
+	if ((addr & ~mask) == (end & ~mask))
+		nptes = end - addr;
+	else
+		nptes = AMDGPU_VM_PTE_COUNT - (addr & mask);
+
+	cur_pe_start = amdgpu_bo_gpu_offset(pt);
+	cur_pe_start += (addr & mask) * 8;
+	cur_pe_end = cur_pe_start + 8 * nptes;
+	cur_dst = dst;
+
+	/* for next ptb*/
+	addr += nptes;
+	dst += nptes * AMDGPU_GPU_PAGE_SIZE;
 
 	/* walk over the address space and update the page tables */
-	for (addr = start; addr < end; ) {
-		uint64_t pt_idx = addr >> amdgpu_vm_block_size;
-		struct amdgpu_bo *pt = vm->page_tables[pt_idx].entry.robj;
-		unsigned nptes;
-		uint64_t pe_start;
+	while (addr < end) {
+		pt_idx = addr >> amdgpu_vm_block_size;
+		pt = vm->page_tables[pt_idx].entry.robj;
 
 		if ((addr & ~mask) == (end & ~mask))
 			nptes = end - addr;
 		else
 			nptes = AMDGPU_VM_PTE_COUNT - (addr & mask);
 
-		pe_start = amdgpu_bo_gpu_offset(pt);
-		pe_start += (addr & mask) * 8;
-
-		if (last_pe_end != pe_start) {
+		next_pe_start = amdgpu_bo_gpu_offset(pt);
+		next_pe_start += (addr & mask) * 8;
 
+		if (cur_pe_end == next_pe_start) {
+			/* The next ptb is consecutive to current ptb.
+			 * Don't call amdgpu_vm_frag_ptes now.
+			 * Will update two ptbs together in future.
+			*/
+			cur_pe_end += 8 * nptes;
+		} else {
 			amdgpu_vm_frag_ptes(adev, vm_update_params,
-					    last_pe_start, last_pe_end,
-					    last_dst, flags);
+					    cur_pe_start, cur_pe_end,
+					    cur_dst, flags);
 
-			last_pe_start = pe_start;
-			last_pe_end = pe_start + 8 * nptes;
-			last_dst = dst;
-		} else {
-			last_pe_end += 8 * nptes;
+			cur_pe_start = next_pe_start;
+			cur_pe_end = next_pe_start + 8 * nptes;
+			cur_dst = dst;
 		}
 
+		/* for next ptb*/
 		addr += nptes;
 		dst += nptes * AMDGPU_GPU_PAGE_SIZE;
 	}
 
-	amdgpu_vm_frag_ptes(adev, vm_update_params, last_pe_start,
-			    last_pe_end, last_dst, flags);
+	amdgpu_vm_frag_ptes(adev, vm_update_params, cur_pe_start,
+			    cur_pe_end, cur_dst, flags);
 }
 
 /**
  * amdgpu_vm_bo_update_mapping - update a mapping in the vm page table
  *
  * @adev: amdgpu_device pointer
+ * @exclusive: fence we need to sync to
  * @src: address where to copy page table entries from
  * @pages_addr: DMA addresses to use for mapping
  * @vm: requested vm
@@ -793,6 +888,7 @@ static void amdgpu_vm_update_ptes(struct amdgpu_device *adev,
  * Returns 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
+				       struct fence *exclusive,
 				       uint64_t src,
 				       dma_addr_t *pages_addr,
 				       struct amdgpu_vm *vm,
@@ -853,6 +949,10 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 
 	vm_update_params.ib = &job->ibs[0];
 
+	r = amdgpu_sync_fence(adev, &job->sync, exclusive);
+	if (r)
+		goto error_free;
+
 	r = amdgpu_sync_resv(adev, &job->sync, vm->page_directory->tbo.resv,
 			     owner);
 	if (r)
@@ -889,6 +989,7 @@ error_free:
  * amdgpu_vm_bo_split_mapping - split a mapping into smaller chunks
  *
  * @adev: amdgpu_device pointer
+ * @exclusive: fence we need to sync to
  * @gtt_flags: flags as they are used for GTT
  * @pages_addr: DMA addresses to use for mapping
  * @vm: requested vm
@@ -902,6 +1003,7 @@ error_free:
  * Returns 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
+				      struct fence *exclusive,
 				      uint32_t gtt_flags,
 				      dma_addr_t *pages_addr,
 				      struct amdgpu_vm *vm,
@@ -932,7 +1034,8 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 	addr += mapping->offset;
 
 	if (!pages_addr || src)
-		return amdgpu_vm_bo_update_mapping(adev, src, pages_addr, vm,
+		return amdgpu_vm_bo_update_mapping(adev, exclusive,
+						   src, pages_addr, vm,
 						   start, mapping->it.last,
 						   flags, addr, fence);
 
@@ -940,7 +1043,8 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 		uint64_t last;
 
 		last = min((uint64_t)mapping->it.last, start + max_size - 1);
-		r = amdgpu_vm_bo_update_mapping(adev, src, pages_addr, vm,
+		r = amdgpu_vm_bo_update_mapping(adev, exclusive,
+						src, pages_addr, vm,
 						start, last, flags, addr,
 						fence);
 		if (r)
@@ -973,6 +1077,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	struct amdgpu_bo_va_mapping *mapping;
 	dma_addr_t *pages_addr = NULL;
 	uint32_t gtt_flags, flags;
+	struct fence *exclusive;
 	uint64_t addr;
 	int r;
 
@@ -994,8 +1099,11 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 		default:
 			break;
 		}
+
+		exclusive = reservation_object_get_excl(bo_va->bo->tbo.resv);
 	} else {
 		addr = 0;
+		exclusive = NULL;
 	}
 
 	flags = amdgpu_ttm_tt_pte_flags(adev, bo_va->bo->tbo.ttm, mem);
@@ -1007,7 +1115,8 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	spin_unlock(&vm->status_lock);
 
 	list_for_each_entry(mapping, &bo_va->invalids, list) {
-		r = amdgpu_vm_bo_split_mapping(adev, gtt_flags, pages_addr, vm,
+		r = amdgpu_vm_bo_split_mapping(adev, exclusive,
+					       gtt_flags, pages_addr, vm,
 					       mapping, flags, addr,
 					       &bo_va->last_pt_update);
 		if (r)
@@ -1054,7 +1163,7 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 			struct amdgpu_bo_va_mapping, list);
 		list_del(&mapping->list);
 
-		r = amdgpu_vm_bo_split_mapping(adev, 0, NULL, vm, mapping,
+		r = amdgpu_vm_bo_split_mapping(adev, NULL, 0, NULL, vm, mapping,
 					       0, 0, NULL);
 		kfree(mapping);
 		if (r)
@@ -1445,6 +1554,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	amdgpu_bo_unreserve(vm->page_directory);
 	if (r)
 		goto error_free_page_directory;
+	vm->last_eviction_counter = atomic64_read(&adev->num_evictions);
 
 	return 0;
 
@@ -1516,6 +1626,10 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
 			      &adev->vm_manager.ids_lru);
 	}
 
+	adev->vm_manager.fence_context = fence_context_alloc(AMDGPU_MAX_RINGS);
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
+		adev->vm_manager.seqno[i] = 0;
+
 	atomic_set(&adev->vm_manager.vm_pte_next_ring, 0);
 	atomic64_set(&adev->vm_manager.client_counter, 0);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
index 48b6bd671cda..c32eca26155c 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
@@ -98,6 +98,7 @@ amdgpu_atombios_encoder_set_backlight_level(struct amdgpu_encoder *amdgpu_encode
 		case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
 		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
 		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
+		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3:
 			if (dig->backlight_level == 0)
 				amdgpu_atombios_encoder_setup_dig_transmitter(encoder,
 								       ATOM_TRANSMITTER_ACTION_LCD_BLOFF, 0, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 5ec1f1e9c983..e2f0e5d58d5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -50,7 +50,9 @@
 #include "gmc/gmc_7_1_sh_mask.h"
 
 MODULE_FIRMWARE("radeon/bonaire_smc.bin");
+MODULE_FIRMWARE("radeon/bonaire_k_smc.bin");
 MODULE_FIRMWARE("radeon/hawaii_smc.bin");
+MODULE_FIRMWARE("radeon/hawaii_k_smc.bin");
 
 #define MC_CG_ARB_FREQ_F0           0x0a
 #define MC_CG_ARB_FREQ_F1           0x0b
@@ -84,12 +86,14 @@ static const struct ci_pt_defaults defaults_bonaire_xt =
 	{ 0x17C, 0x172, 0x180, 0x1BC, 0x1B3, 0x1BD, 0x206, 0x200, 0x203, 0x25D, 0x25A, 0x255, 0x2C3, 0x2C5, 0x2B4 }
 };
 
+#if 0
 static const struct ci_pt_defaults defaults_bonaire_pro =
 {
 	1, 0xF, 0xFD, 0x19, 5, 45, 0, 0x65062,
 	{ 0x8C,  0x23F, 0x244, 0xA6,  0x83,  0x85,  0x86,  0x86,  0x83,  0xDB,  0xDB,  0xDA,  0x67,  0x60,  0x5F  },
 	{ 0x187, 0x193, 0x193, 0x1C7, 0x1D1, 0x1D1, 0x210, 0x219, 0x219, 0x266, 0x26C, 0x26C, 0x2C9, 0x2CB, 0x2CB }
 };
+#endif
 
 static const struct ci_pt_defaults defaults_saturn_xt =
 {
@@ -98,12 +102,14 @@ static const struct ci_pt_defaults defaults_saturn_xt =
 	{ 0x187, 0x187, 0x187, 0x1C7, 0x1C7, 0x1C7, 0x210, 0x210, 0x210, 0x266, 0x266, 0x266, 0x2C9, 0x2C9, 0x2C9 }
 };
 
+#if 0
 static const struct ci_pt_defaults defaults_saturn_pro =
 {
 	1, 0xF, 0xFD, 0x19, 5, 55, 0, 0x30000,
 	{ 0x96,  0x21D, 0x23B, 0xA1,  0x85,  0x87,  0x83,  0x84,  0x81,  0xE6,  0xE6,  0xE6,  0x71,  0x6A,  0x6A  },
 	{ 0x193, 0x19E, 0x19E, 0x1D2, 0x1DC, 0x1DC, 0x21A, 0x223, 0x223, 0x26E, 0x27E, 0x274, 0x2CF, 0x2D2, 0x2D2 }
 };
+#endif
 
 static const struct ci_pt_config_reg didt_config_ci[] =
 {
@@ -736,19 +742,19 @@ static int ci_enable_didt(struct amdgpu_device *adev, bool enable)
 
 	if (pi->caps_sq_ramping || pi->caps_db_ramping ||
 	    pi->caps_td_ramping || pi->caps_tcp_ramping) {
-		gfx_v7_0_enter_rlc_safe_mode(adev);
+		adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
 		if (enable) {
 			ret = ci_program_pt_config_registers(adev, didt_config_ci);
 			if (ret) {
-				gfx_v7_0_exit_rlc_safe_mode(adev);
+				adev->gfx.rlc.funcs->exit_safe_mode(adev);
 				return ret;
 			}
 		}
 
 		ci_do_enable_didt(adev, enable);
 
-		gfx_v7_0_exit_rlc_safe_mode(adev);
+		adev->gfx.rlc.funcs->exit_safe_mode(adev);
 	}
 
 	return 0;
@@ -3030,7 +3036,7 @@ static int ci_populate_single_memory_level(struct amdgpu_device *adev,
 
 	if (pi->mclk_stutter_mode_threshold &&
 	    (memory_clock <= pi->mclk_stutter_mode_threshold) &&
-	    (pi->uvd_enabled == false) &&
+	    (!pi->uvd_enabled) &&
 	    (RREG32(mmDPG_PIPE_STUTTER_CONTROL) & DPG_PIPE_STUTTER_CONTROL__STUTTER_ENABLE_MASK) &&
 	    (adev->pm.dpm.new_active_crtc_count <= 2))
 		memory_level->StutterEnable = true;
@@ -3636,6 +3642,10 @@ static int ci_setup_default_dpm_tables(struct amdgpu_device *adev)
 
 	ci_setup_default_pcie_tables(adev);
 
+	/* save a copy of the default DPM table */
+	memcpy(&(pi->golden_dpm_table), &(pi->dpm_table),
+			sizeof(struct ci_dpm_table));
+
 	return 0;
 }
 
@@ -5754,10 +5764,18 @@ static int ci_dpm_init_microcode(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
-		chip_name = "bonaire";
+		if ((adev->pdev->revision == 0x80) ||
+		    (adev->pdev->revision == 0x81) ||
+		    (adev->pdev->device == 0x665f))
+			chip_name = "bonaire_k";
+		else
+			chip_name = "bonaire";
 		break;
 	case CHIP_HAWAII:
-		chip_name = "hawaii";
+		if (adev->pdev->revision == 0x80)
+			chip_name = "hawaii_k";
+		else
+			chip_name = "hawaii";
 		break;
 	case CHIP_KAVERI:
 	case CHIP_KABINI:
@@ -6404,6 +6422,186 @@ static int ci_dpm_set_powergating_state(void *handle,
 	return 0;
 }
 
+static int ci_dpm_print_clock_levels(struct amdgpu_device *adev,
+		enum pp_clock_type type, char *buf)
+{
+	struct ci_power_info *pi = ci_get_pi(adev);
+	struct ci_single_dpm_table *sclk_table = &pi->dpm_table.sclk_table;
+	struct ci_single_dpm_table *mclk_table = &pi->dpm_table.mclk_table;
+	struct ci_single_dpm_table *pcie_table = &pi->dpm_table.pcie_speed_table;
+
+	int i, now, size = 0;
+	uint32_t clock, pcie_speed;
+
+	switch (type) {
+	case PP_SCLK:
+		amdgpu_ci_send_msg_to_smc(adev, PPSMC_MSG_API_GetSclkFrequency);
+		clock = RREG32(mmSMC_MSG_ARG_0);
+
+		for (i = 0; i < sclk_table->count; i++) {
+			if (clock > sclk_table->dpm_levels[i].value)
+				continue;
+			break;
+		}
+		now = i;
+
+		for (i = 0; i < sclk_table->count; i++)
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
+					i, sclk_table->dpm_levels[i].value / 100,
+					(i == now) ? "*" : "");
+		break;
+	case PP_MCLK:
+		amdgpu_ci_send_msg_to_smc(adev, PPSMC_MSG_API_GetMclkFrequency);
+		clock = RREG32(mmSMC_MSG_ARG_0);
+
+		for (i = 0; i < mclk_table->count; i++) {
+			if (clock > mclk_table->dpm_levels[i].value)
+				continue;
+			break;
+		}
+		now = i;
+
+		for (i = 0; i < mclk_table->count; i++)
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
+					i, mclk_table->dpm_levels[i].value / 100,
+					(i == now) ? "*" : "");
+		break;
+	case PP_PCIE:
+		pcie_speed = ci_get_current_pcie_speed(adev);
+		for (i = 0; i < pcie_table->count; i++) {
+			if (pcie_speed != pcie_table->dpm_levels[i].value)
+				continue;
+			break;
+		}
+		now = i;
+
+		for (i = 0; i < pcie_table->count; i++)
+			size += sprintf(buf + size, "%d: %s %s\n", i,
+					(pcie_table->dpm_levels[i].value == 0) ? "2.5GB, x1" :
+					(pcie_table->dpm_levels[i].value == 1) ? "5.0GB, x16" :
+					(pcie_table->dpm_levels[i].value == 2) ? "8.0GB, x16" : "",
+					(i == now) ? "*" : "");
+		break;
+	default:
+		break;
+	}
+
+	return size;
+}
+
+static int ci_dpm_force_clock_level(struct amdgpu_device *adev,
+		enum pp_clock_type type, uint32_t mask)
+{
+	struct ci_power_info *pi = ci_get_pi(adev);
+
+	if (adev->pm.dpm.forced_level
+			!= AMDGPU_DPM_FORCED_LEVEL_MANUAL)
+		return -EINVAL;
+
+	switch (type) {
+	case PP_SCLK:
+		if (!pi->sclk_dpm_key_disabled)
+			amdgpu_ci_send_msg_to_smc_with_parameter(adev,
+					PPSMC_MSG_SCLKDPM_SetEnabledMask,
+					pi->dpm_level_enable_mask.sclk_dpm_enable_mask & mask);
+		break;
+
+	case PP_MCLK:
+		if (!pi->mclk_dpm_key_disabled)
+			amdgpu_ci_send_msg_to_smc_with_parameter(adev,
+					PPSMC_MSG_MCLKDPM_SetEnabledMask,
+					pi->dpm_level_enable_mask.mclk_dpm_enable_mask & mask);
+		break;
+
+	case PP_PCIE:
+	{
+		uint32_t tmp = mask & pi->dpm_level_enable_mask.pcie_dpm_enable_mask;
+		uint32_t level = 0;
+
+		while (tmp >>= 1)
+			level++;
+
+		if (!pi->pcie_dpm_key_disabled)
+			amdgpu_ci_send_msg_to_smc_with_parameter(adev,
+					PPSMC_MSG_PCIeDPM_ForceLevel,
+					level);
+		break;
+	}
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int ci_dpm_get_sclk_od(struct amdgpu_device *adev)
+{
+	struct ci_power_info *pi = ci_get_pi(adev);
+	struct ci_single_dpm_table *sclk_table = &(pi->dpm_table.sclk_table);
+	struct ci_single_dpm_table *golden_sclk_table =
+			&(pi->golden_dpm_table.sclk_table);
+	int value;
+
+	value = (sclk_table->dpm_levels[sclk_table->count - 1].value -
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value) *
+			100 /
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value;
+
+	return value;
+}
+
+static int ci_dpm_set_sclk_od(struct amdgpu_device *adev, uint32_t value)
+{
+	struct ci_power_info *pi = ci_get_pi(adev);
+	struct ci_ps *ps = ci_get_ps(adev->pm.dpm.requested_ps);
+	struct ci_single_dpm_table *golden_sclk_table =
+			&(pi->golden_dpm_table.sclk_table);
+
+	if (value > 20)
+		value = 20;
+
+	ps->performance_levels[ps->performance_level_count - 1].sclk =
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value *
+			value / 100 +
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value;
+
+	return 0;
+}
+
+static int ci_dpm_get_mclk_od(struct amdgpu_device *adev)
+{
+	struct ci_power_info *pi = ci_get_pi(adev);
+	struct ci_single_dpm_table *mclk_table = &(pi->dpm_table.mclk_table);
+	struct ci_single_dpm_table *golden_mclk_table =
+			&(pi->golden_dpm_table.mclk_table);
+	int value;
+
+	value = (mclk_table->dpm_levels[mclk_table->count - 1].value -
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value) *
+			100 /
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value;
+
+	return value;
+}
+
+static int ci_dpm_set_mclk_od(struct amdgpu_device *adev, uint32_t value)
+{
+	struct ci_power_info *pi = ci_get_pi(adev);
+	struct ci_ps *ps = ci_get_ps(adev->pm.dpm.requested_ps);
+	struct ci_single_dpm_table *golden_mclk_table =
+			&(pi->golden_dpm_table.mclk_table);
+
+	if (value > 20)
+		value = 20;
+
+	ps->performance_levels[ps->performance_level_count - 1].mclk =
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value *
+			value / 100 +
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value;
+
+	return 0;
+}
+
 const struct amd_ip_funcs ci_dpm_ip_funcs = {
 	.name = "ci_dpm",
 	.early_init = ci_dpm_early_init,
@@ -6438,6 +6636,12 @@ static const struct amdgpu_dpm_funcs ci_dpm_funcs = {
 	.get_fan_control_mode = &ci_dpm_get_fan_control_mode,
 	.set_fan_speed_percent = &ci_dpm_set_fan_speed_percent,
 	.get_fan_speed_percent = &ci_dpm_get_fan_speed_percent,
+	.print_clock_levels = ci_dpm_print_clock_levels,
+	.force_clock_level = ci_dpm_force_clock_level,
+	.get_sclk_od = ci_dpm_get_sclk_od,
+	.set_sclk_od = ci_dpm_set_sclk_od,
+	.get_mclk_od = ci_dpm_get_mclk_od,
+	.set_mclk_od = ci_dpm_set_mclk_od,
 };
 
 static void ci_dpm_set_dpm_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.h b/drivers/gpu/drm/amd/amdgpu/ci_dpm.h
index faccc30c93bf..91be2996ae7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.h
@@ -193,6 +193,7 @@ struct ci_pt_defaults {
 
 struct ci_power_info {
 	struct ci_dpm_table dpm_table;
+	struct ci_dpm_table golden_dpm_table;
 	u32 voltage_control;
 	u32 mvdd_control;
 	u32 vddci_control;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 910431808542..4efc901f658c 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -879,7 +879,7 @@ static void cik_vga_set_state(struct amdgpu_device *adev, bool state)
 	uint32_t tmp;
 
 	tmp = RREG32(mmCONFIG_CNTL);
-	if (state == false)
+	if (!state)
 		tmp |= CONFIG_CNTL__VGA_DIS_MASK;
 	else
 		tmp &= ~CONFIG_CNTL__VGA_DIS_MASK;
@@ -1035,12 +1035,12 @@ static uint32_t cik_read_indexed_register(struct amdgpu_device *adev,
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	if (se_num != 0xffffffff || sh_num != 0xffffffff)
-		gfx_v7_0_select_se_sh(adev, se_num, sh_num);
+		amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff);
 
 	val = RREG32(reg_offset);
 
 	if (se_num != 0xffffffff || sh_num != 0xffffffff)
-		gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 	return val;
 }
@@ -1158,10 +1158,11 @@ static void kv_restore_regs_for_reset(struct amdgpu_device *adev,
 	WREG32(mmGMCON_RENG_EXECUTE, save->gmcon_reng_execute);
 }
 
-static void cik_gpu_pci_config_reset(struct amdgpu_device *adev)
+static int cik_gpu_pci_config_reset(struct amdgpu_device *adev)
 {
 	struct kv_reset_save_regs kv_save = { 0 };
 	u32 i;
+	int r = -EINVAL;
 
 	dev_info(adev->dev, "GPU pci config reset\n");
 
@@ -1177,14 +1178,20 @@ static void cik_gpu_pci_config_reset(struct amdgpu_device *adev)
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff)
+		if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff) {
+			/* enable BM */
+			pci_set_master(adev->pdev);
+			r = 0;
 			break;
+		}
 		udelay(1);
 	}
 
 	/* does asic init need to be run first??? */
 	if (adev->flags & AMD_IS_APU)
 		kv_restore_regs_for_reset(adev, &kv_save);
+
+	return r;
 }
 
 static void cik_set_bios_scratch_engine_hung(struct amdgpu_device *adev, bool hung)
@@ -1210,13 +1217,14 @@ static void cik_set_bios_scratch_engine_hung(struct amdgpu_device *adev, bool hu
  */
 static int cik_asic_reset(struct amdgpu_device *adev)
 {
+	int r;
 	cik_set_bios_scratch_engine_hung(adev, true);
 
-	cik_gpu_pci_config_reset(adev);
+	r = cik_gpu_pci_config_reset(adev);
 
 	cik_set_bios_scratch_engine_hung(adev, false);
 
-	return 0;
+	return r;
 }
 
 static int cik_set_uvd_clock(struct amdgpu_device *adev, u32 clock,
@@ -2014,9 +2022,6 @@ static const struct amdgpu_asic_funcs cik_asic_funcs =
 	.set_uvd_clocks = &cik_set_uvd_clocks,
 	.set_vce_clocks = &cik_set_vce_clocks,
 	.get_virtual_caps = &cik_get_virtual_caps,
-	/* these should be moved to their own ip modules */
-	.get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter,
-	.wait_for_mc_idle = &gmc_v7_0_mc_wait_for_idle,
 };
 
 static int cik_common_early_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 9dc4e24e31e7..ee6466912497 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -224,17 +224,6 @@ static void cik_sdma_ring_emit_ib(struct amdgpu_ring *ring,
 				  unsigned vm_id, bool ctx_switch)
 {
 	u32 extra_bits = vm_id & 0xf;
-	u32 next_rptr = ring->wptr + 5;
-
-	while ((next_rptr & 7) != 4)
-		next_rptr++;
-
-	next_rptr += 4;
-	amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0));
-	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, 1); /* number of DWs to follow */
-	amdgpu_ring_write(ring, next_rptr);
 
 	/* IB packet must end on a 8 DW boundary */
 	cik_sdma_ring_insert_nop(ring, (12 - (ring->wptr & 7)) % 8);
@@ -365,7 +354,7 @@ static void cik_sdma_enable(struct amdgpu_device *adev, bool enable)
 	u32 me_cntl;
 	int i;
 
-	if (enable == false) {
+	if (!enable) {
 		cik_sdma_gfx_stop(adev);
 		cik_sdma_rlc_stop(adev);
 	}
@@ -628,20 +617,19 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring)
  * Test a simple IB in the DMA ring (CIK).
  * Returns 0 on success, error on failure.
  */
-static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring)
+static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib ib;
 	struct fence *f = NULL;
-	unsigned i;
 	unsigned index;
-	int r;
 	u32 tmp = 0;
 	u64 gpu_addr;
+	long r;
 
 	r = amdgpu_wb_get(adev, &index);
 	if (r) {
-		dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
+		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
 		return r;
 	}
 
@@ -651,11 +639,12 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring)
 	memset(&ib, 0, sizeof(ib));
 	r = amdgpu_ib_get(adev, NULL, 256, &ib);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get ib (%d).\n", r);
+		DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 		goto err0;
 	}
 
-	ib.ptr[0] = SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
+	ib.ptr[0] = SDMA_PACKET(SDMA_OPCODE_WRITE,
+				SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
 	ib.ptr[1] = lower_32_bits(gpu_addr);
 	ib.ptr[2] = upper_32_bits(gpu_addr);
 	ib.ptr[3] = 1;
@@ -665,28 +654,25 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring)
 	if (r)
 		goto err1;
 
-	r = fence_wait(f, false);
-	if (r) {
-		DRM_ERROR("amdgpu: fence wait failed (%d).\n", r);
+	r = fence_wait_timeout(f, false, timeout);
+	if (r == 0) {
+		DRM_ERROR("amdgpu: IB test timed out\n");
+		r = -ETIMEDOUT;
 		goto err1;
-	}
-	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = le32_to_cpu(adev->wb.wb[index]);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-	if (i < adev->usec_timeout) {
-		DRM_INFO("ib test on ring %d succeeded in %u usecs\n",
-			 ring->idx, i);
+	} else if (r < 0) {
+		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 		goto err1;
+	}
+	tmp = le32_to_cpu(adev->wb.wb[index]);
+	if (tmp == 0xDEADBEEF) {
+		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
 		r = -EINVAL;
 	}
 
 err1:
-	fence_put(f);
 	amdgpu_ib_free(adev, &ib, NULL);
 	fence_put(f);
 err0:
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index 933e425a8154..2a11413ed54a 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -425,7 +425,7 @@ static int cz_dpm_init(struct amdgpu_device *adev)
 	pi->mgcg_cgtt_local1 = 0x0;
 	pi->clock_slow_down_step = 25000;
 	pi->skip_clock_slow_down = 1;
-	pi->enable_nb_ps_policy = 0;
+	pi->enable_nb_ps_policy = false;
 	pi->caps_power_containment = true;
 	pi->caps_cac = true;
 	pi->didt_enabled = false;
@@ -2219,6 +2219,7 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate)
 			}
 		}
 	} else { /*pi->caps_vce_pg*/
+		pi->vce_power_gated = gate;
 		cz_update_vce_dpm(adev);
 		cz_enable_vce_dpm(adev, !gate);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 8227344d2ff6..c1b04e9aab57 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2667,19 +2667,21 @@ static void dce_v10_0_cursor_reset(struct drm_crtc *crtc)
 	}
 }
 
-static void dce_v10_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-				    u16 *blue, uint32_t start, uint32_t size)
+static int dce_v10_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
+				    u16 *blue, uint32_t size)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	int end = (start + size > 256) ? 256 : start + size, i;
+	int i;
 
 	/* userspace palettes are always correct as is */
-	for (i = start; i < end; i++) {
+	for (i = 0; i < size; i++) {
 		amdgpu_crtc->lut_r[i] = red[i] >> 6;
 		amdgpu_crtc->lut_g[i] = green[i] >> 6;
 		amdgpu_crtc->lut_b[i] = blue[i] >> 6;
 	}
 	dce_v10_0_crtc_load_lut(crtc);
+
+	return 0;
 }
 
 static void dce_v10_0_crtc_destroy(struct drm_crtc *crtc)
@@ -2717,13 +2719,13 @@ static void dce_v10_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 		type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id);
 		amdgpu_irq_update(adev, &adev->crtc_irq, type);
 		amdgpu_irq_update(adev, &adev->pageflip_irq, type);
-		drm_vblank_on(dev, amdgpu_crtc->crtc_id);
+		drm_crtc_vblank_on(crtc);
 		dce_v10_0_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
-		drm_vblank_off(dev, amdgpu_crtc->crtc_id);
+		drm_crtc_vblank_off(crtc);
 		if (amdgpu_crtc->enabled) {
 			dce_v10_0_vga_enable(crtc, true);
 			amdgpu_atombios_crtc_blank(crtc, ATOM_ENABLE);
@@ -3372,7 +3374,7 @@ static int dce_v10_0_pageflip_irq(struct amdgpu_device *adev,
 
 	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
 
-	drm_vblank_put(adev->ddev, amdgpu_crtc->crtc_id);
+	drm_crtc_vblank_put(&amdgpu_crtc->base);
 	schedule_work(&works->unpin_work);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index af26ec0bc59d..d4bf133908b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -307,11 +307,10 @@ static void dce_v11_0_page_flip(struct amdgpu_device *adev,
 	struct amdgpu_crtc *amdgpu_crtc = adev->mode_info.crtcs[crtc_id];
 	u32 tmp;
 
-	/* flip at hsync for async, default is vsync */
-	/* use UPDATE_IMMEDIATE_EN instead for async? */
+	/* flip immediate for async, default is vsync */
 	tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset);
 	tmp = REG_SET_FIELD(tmp, GRPH_FLIP_CONTROL,
-			    GRPH_SURFACE_UPDATE_H_RETRACE_EN, async ? 1 : 0);
+			    GRPH_SURFACE_UPDATE_IMMEDIATE_EN, async ? 1 : 0);
 	WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp);
 	/* update the scanout addresses */
 	WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
@@ -2678,19 +2677,21 @@ static void dce_v11_0_cursor_reset(struct drm_crtc *crtc)
 	}
 }
 
-static void dce_v11_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-				    u16 *blue, uint32_t start, uint32_t size)
+static int dce_v11_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
+				    u16 *blue, uint32_t size)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	int end = (start + size > 256) ? 256 : start + size, i;
+	int i;
 
 	/* userspace palettes are always correct as is */
-	for (i = start; i < end; i++) {
+	for (i = 0; i < size; i++) {
 		amdgpu_crtc->lut_r[i] = red[i] >> 6;
 		amdgpu_crtc->lut_g[i] = green[i] >> 6;
 		amdgpu_crtc->lut_b[i] = blue[i] >> 6;
 	}
 	dce_v11_0_crtc_load_lut(crtc);
+
+	return 0;
 }
 
 static void dce_v11_0_crtc_destroy(struct drm_crtc *crtc)
@@ -2728,13 +2729,13 @@ static void dce_v11_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 		type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id);
 		amdgpu_irq_update(adev, &adev->crtc_irq, type);
 		amdgpu_irq_update(adev, &adev->pageflip_irq, type);
-		drm_vblank_on(dev, amdgpu_crtc->crtc_id);
+		drm_crtc_vblank_on(crtc);
 		dce_v11_0_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
-		drm_vblank_off(dev, amdgpu_crtc->crtc_id);
+		drm_crtc_vblank_off(crtc);
 		if (amdgpu_crtc->enabled) {
 			dce_v11_0_vga_enable(crtc, true);
 			amdgpu_atombios_crtc_blank(crtc, ATOM_ENABLE);
@@ -3433,7 +3434,7 @@ static int dce_v11_0_pageflip_irq(struct amdgpu_device *adev,
 
 	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
 
-	drm_vblank_put(adev->ddev, amdgpu_crtc->crtc_id);
+	drm_crtc_vblank_put(&amdgpu_crtc->base);
 	schedule_work(&works->unpin_work);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 3fb65e41a6ef..4fdfab1e9200 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -526,36 +526,16 @@ static void dce_v8_0_stop_mc_access(struct amdgpu_device *adev,
 		crtc_enabled = REG_GET_FIELD(RREG32(mmCRTC_CONTROL + crtc_offsets[i]),
 					     CRTC_CONTROL, CRTC_MASTER_EN);
 		if (crtc_enabled) {
-#if 0
-			u32 frame_count;
-			int j;
-
+#if 1
 			save->crtc_enabled[i] = true;
 			tmp = RREG32(mmCRTC_BLANK_CONTROL + crtc_offsets[i]);
 			if (REG_GET_FIELD(tmp, CRTC_BLANK_CONTROL, CRTC_BLANK_DATA_EN) == 0) {
-				amdgpu_display_vblank_wait(adev, i);
-				WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 1);
+				/*it is correct only for RGB ; black is 0*/
+				WREG32(mmCRTC_BLANK_DATA_COLOR + crtc_offsets[i], 0);
 				tmp = REG_SET_FIELD(tmp, CRTC_BLANK_CONTROL, CRTC_BLANK_DATA_EN, 1);
 				WREG32(mmCRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
-				WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 0);
-			}
-			/* wait for the next frame */
-			frame_count = amdgpu_display_vblank_get_counter(adev, i);
-			for (j = 0; j < adev->usec_timeout; j++) {
-				if (amdgpu_display_vblank_get_counter(adev, i) != frame_count)
-					break;
-				udelay(1);
-			}
-			tmp = RREG32(mmGRPH_UPDATE + crtc_offsets[i]);
-			if (REG_GET_FIELD(tmp, GRPH_UPDATE, GRPH_UPDATE_LOCK) == 0) {
-				tmp = REG_SET_FIELD(tmp, GRPH_UPDATE, GRPH_UPDATE_LOCK, 1);
-				WREG32(mmGRPH_UPDATE + crtc_offsets[i], tmp);
-			}
-			tmp = RREG32(mmMASTER_UPDATE_LOCK + crtc_offsets[i]);
-			if (REG_GET_FIELD(tmp, MASTER_UPDATE_LOCK, MASTER_UPDATE_LOCK) == 0) {
-				tmp = REG_SET_FIELD(tmp, MASTER_UPDATE_LOCK, MASTER_UPDATE_LOCK, 1);
-				WREG32(mmMASTER_UPDATE_LOCK + crtc_offsets[i], tmp);
 			}
+			mdelay(20);
 #else
 			/* XXX this is a hack to avoid strange behavior with EFI on certain systems */
 			WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 1);
@@ -575,55 +555,22 @@ static void dce_v8_0_stop_mc_access(struct amdgpu_device *adev,
 static void dce_v8_0_resume_mc_access(struct amdgpu_device *adev,
 				      struct amdgpu_mode_mc_save *save)
 {
-	u32 tmp, frame_count;
-	int i, j;
+	u32 tmp;
+	int i;
 
 	/* update crtc base addresses */
 	for (i = 0; i < adev->mode_info.num_crtc; i++) {
 		WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + crtc_offsets[i],
 		       upper_32_bits(adev->mc.vram_start));
-		WREG32(mmGRPH_SECONDARY_SURFACE_ADDRESS_HIGH + crtc_offsets[i],
-		       upper_32_bits(adev->mc.vram_start));
 		WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + crtc_offsets[i],
 		       (u32)adev->mc.vram_start);
-		WREG32(mmGRPH_SECONDARY_SURFACE_ADDRESS + crtc_offsets[i],
-		       (u32)adev->mc.vram_start);
 
 		if (save->crtc_enabled[i]) {
-			tmp = RREG32(mmMASTER_UPDATE_MODE + crtc_offsets[i]);
-			if (REG_GET_FIELD(tmp, MASTER_UPDATE_MODE, MASTER_UPDATE_MODE) != 3) {
-				tmp = REG_SET_FIELD(tmp, MASTER_UPDATE_MODE, MASTER_UPDATE_MODE, 3);
-				WREG32(mmMASTER_UPDATE_MODE + crtc_offsets[i], tmp);
-			}
-			tmp = RREG32(mmGRPH_UPDATE + crtc_offsets[i]);
-			if (REG_GET_FIELD(tmp, GRPH_UPDATE, GRPH_UPDATE_LOCK)) {
-				tmp = REG_SET_FIELD(tmp, GRPH_UPDATE, GRPH_UPDATE_LOCK, 0);
-				WREG32(mmGRPH_UPDATE + crtc_offsets[i], tmp);
-			}
-			tmp = RREG32(mmMASTER_UPDATE_LOCK + crtc_offsets[i]);
-			if (REG_GET_FIELD(tmp, MASTER_UPDATE_LOCK, MASTER_UPDATE_LOCK)) {
-				tmp = REG_SET_FIELD(tmp, MASTER_UPDATE_LOCK, MASTER_UPDATE_LOCK, 0);
-				WREG32(mmMASTER_UPDATE_LOCK + crtc_offsets[i], tmp);
-			}
-			for (j = 0; j < adev->usec_timeout; j++) {
-				tmp = RREG32(mmGRPH_UPDATE + crtc_offsets[i]);
-				if (REG_GET_FIELD(tmp, GRPH_UPDATE, GRPH_SURFACE_UPDATE_PENDING) == 0)
-					break;
-				udelay(1);
-			}
 			tmp = RREG32(mmCRTC_BLANK_CONTROL + crtc_offsets[i]);
 			tmp = REG_SET_FIELD(tmp, CRTC_BLANK_CONTROL, CRTC_BLANK_DATA_EN, 0);
-			WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 			WREG32(mmCRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
-			WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 0);
-			/* wait for the next frame */
-			frame_count = amdgpu_display_vblank_get_counter(adev, i);
-			for (j = 0; j < adev->usec_timeout; j++) {
-				if (amdgpu_display_vblank_get_counter(adev, i) != frame_count)
-					break;
-				udelay(1);
-			}
 		}
+		mdelay(20);
 	}
 
 	WREG32(mmVGA_MEMORY_BASE_ADDRESS_HIGH, upper_32_bits(adev->mc.vram_start));
@@ -2574,19 +2521,21 @@ static void dce_v8_0_cursor_reset(struct drm_crtc *crtc)
 	}
 }
 
-static void dce_v8_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-				    u16 *blue, uint32_t start, uint32_t size)
+static int dce_v8_0_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
+				   u16 *blue, uint32_t size)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	int end = (start + size > 256) ? 256 : start + size, i;
+	int i;
 
 	/* userspace palettes are always correct as is */
-	for (i = start; i < end; i++) {
+	for (i = 0; i < size; i++) {
 		amdgpu_crtc->lut_r[i] = red[i] >> 6;
 		amdgpu_crtc->lut_g[i] = green[i] >> 6;
 		amdgpu_crtc->lut_b[i] = blue[i] >> 6;
 	}
 	dce_v8_0_crtc_load_lut(crtc);
+
+	return 0;
 }
 
 static void dce_v8_0_crtc_destroy(struct drm_crtc *crtc)
@@ -2624,13 +2573,13 @@ static void dce_v8_0_crtc_dpms(struct drm_crtc *crtc, int mode)
 		type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id);
 		amdgpu_irq_update(adev, &adev->crtc_irq, type);
 		amdgpu_irq_update(adev, &adev->pageflip_irq, type);
-		drm_vblank_on(dev, amdgpu_crtc->crtc_id);
+		drm_crtc_vblank_on(crtc);
 		dce_v8_0_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
-		drm_vblank_off(dev, amdgpu_crtc->crtc_id);
+		drm_crtc_vblank_off(crtc);
 		if (amdgpu_crtc->enabled) {
 			dce_v8_0_vga_enable(crtc, true);
 			amdgpu_atombios_crtc_blank(crtc, ATOM_ENABLE);
@@ -3376,7 +3325,7 @@ static int dce_v8_0_pageflip_irq(struct amdgpu_device *adev,
 
 	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
 
-	drm_vblank_put(adev->ddev, amdgpu_crtc->crtc_id);
+	drm_crtc_vblank_put(&amdgpu_crtc->base);
 	schedule_work(&works->unpin_work);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/fiji_smc.c b/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
index b336c918d6a7..b3e19ba4c57f 100644
--- a/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
@@ -173,7 +173,7 @@ static int fiji_send_msg_to_smc(struct amdgpu_device *adev, PPSMC_Msg msg)
 {
 	if (!fiji_is_smc_ram_running(adev))
 	{
-		return -EINVAL;;
+		return -EINVAL;
 	}
 
 	if (wait_smu_response(adev)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index fc8ff4d3ccf8..d869d058ef24 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -1583,9 +1583,15 @@ static void gfx_v7_0_tiling_mode_table_init(struct amdgpu_device *adev)
  * registers are instanced per SE or SH.  0xffffffff means
  * broadcast to all SEs or SHs (CIK).
  */
-void gfx_v7_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num)
+static void gfx_v7_0_select_se_sh(struct amdgpu_device *adev,
+				  u32 se_num, u32 sh_num, u32 instance)
 {
-	u32 data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK;
+	u32 data;
+
+	if (instance == 0xffffffff)
+		data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES, 1);
+	else
+		data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_INDEX, instance);
 
 	if ((se_num == 0xffffffff) && (sh_num == 0xffffffff))
 		data |= GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK |
@@ -1659,13 +1665,13 @@ static void gfx_v7_0_setup_rb(struct amdgpu_device *adev)
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
-			gfx_v7_0_select_se_sh(adev, i, j);
+			gfx_v7_0_select_se_sh(adev, i, j, 0xffffffff);
 			data = gfx_v7_0_get_rb_active_bitmap(adev);
 			active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) *
 					       rb_bitmap_width_per_sh);
 		}
 	}
-	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	adev->gfx.config.backend_enable_mask = active_rbs;
@@ -1746,7 +1752,7 @@ static void gfx_v7_0_gpu_init(struct amdgpu_device *adev)
 	 * making sure that the following register writes will be broadcasted
 	 * to all the shaders
 	 */
-	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 
 	/* XXX SH_MEM regs */
 	/* where to put LDS, scratch, GPUVM in FSA64 space */
@@ -2050,17 +2056,6 @@ static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				      unsigned vm_id, bool ctx_switch)
 {
 	u32 header, control = 0;
-	u32 next_rptr = ring->wptr + 5;
-
-	if (ctx_switch)
-		next_rptr += 2;
-
-	next_rptr += 4;
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM);
-	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, next_rptr);
 
 	/* insert SWITCH_BUFFER packet before first IB in the ring frame */
 	if (ctx_switch) {
@@ -2089,22 +2084,9 @@ static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
 					  struct amdgpu_ib *ib,
 					  unsigned vm_id, bool ctx_switch)
 {
-	u32 header, control = 0;
-	u32 next_rptr = ring->wptr + 5;
-
-	control |= INDIRECT_BUFFER_VALID;
-	next_rptr += 4;
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM);
-	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, next_rptr);
-
-	header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
+	u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vm_id << 24);
 
-	control |= ib->length_dw | (vm_id << 24);
-
-	amdgpu_ring_write(ring, header);
+	amdgpu_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	amdgpu_ring_write(ring,
 #ifdef __BIG_ENDIAN
 					  (2 << 0) |
@@ -2123,26 +2105,25 @@ static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
  * Provides a basic gfx ring test to verify that IBs are working.
  * Returns 0 on success, error on failure.
  */
-static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring)
+static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib ib;
 	struct fence *f = NULL;
 	uint32_t scratch;
 	uint32_t tmp = 0;
-	unsigned i;
-	int r;
+	long r;
 
 	r = amdgpu_gfx_scratch_get(adev, &scratch);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get scratch reg (%d).\n", r);
+		DRM_ERROR("amdgpu: failed to get scratch reg (%ld).\n", r);
 		return r;
 	}
 	WREG32(scratch, 0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
 	r = amdgpu_ib_get(adev, NULL, 256, &ib);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get ib (%d).\n", r);
+		DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 		goto err1;
 	}
 	ib.ptr[0] = PACKET3(PACKET3_SET_UCONFIG_REG, 1);
@@ -2154,21 +2135,19 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring)
 	if (r)
 		goto err2;
 
-	r = fence_wait(f, false);
-	if (r) {
-		DRM_ERROR("amdgpu: fence wait failed (%d).\n", r);
+	r = fence_wait_timeout(f, false, timeout);
+	if (r == 0) {
+		DRM_ERROR("amdgpu: IB test timed out\n");
+		r = -ETIMEDOUT;
 		goto err2;
-	}
-	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32(scratch);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-	if (i < adev->usec_timeout) {
-		DRM_INFO("ib test on ring %d succeeded in %u usecs\n",
-			 ring->idx, i);
+	} else if (r < 0) {
+		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 		goto err2;
+	}
+	tmp = RREG32(scratch);
+	if (tmp == 0xDEADBEEF) {
+		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
 			  scratch, tmp);
@@ -2176,7 +2155,6 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring)
 	}
 
 err2:
-	fence_put(f);
 	amdgpu_ib_free(adev, &ib, NULL);
 	fence_put(f);
 err1:
@@ -3221,7 +3199,8 @@ static int gfx_v7_0_rlc_init(struct amdgpu_device *adev)
 		}
 	}
 	adev->gfx.rlc.cs_data = ci_cs_data;
-	adev->gfx.rlc.cp_table_size = CP_ME_TABLE_SIZE * 5 * 4;
+	adev->gfx.rlc.cp_table_size = ALIGN(CP_ME_TABLE_SIZE * 5 * 4, 2048); /* CP JT */
+	adev->gfx.rlc.cp_table_size += 64 * 1024; /* GDS */
 
 	src_ptr = adev->gfx.rlc.reg_list;
 	dws = adev->gfx.rlc.reg_list_size;
@@ -3379,7 +3358,7 @@ static void gfx_v7_0_wait_for_rlc_serdes(struct amdgpu_device *adev)
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
-			gfx_v7_0_select_se_sh(adev, i, j);
+			gfx_v7_0_select_se_sh(adev, i, j, 0xffffffff);
 			for (k = 0; k < adev->usec_timeout; k++) {
 				if (RREG32(mmRLC_SERDES_CU_MASTER_BUSY) == 0)
 					break;
@@ -3387,7 +3366,7 @@ static void gfx_v7_0_wait_for_rlc_serdes(struct amdgpu_device *adev)
 			}
 		}
 	}
-	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	mask = RLC_SERDES_NONCU_MASTER_BUSY__SE_MASTER_BUSY_MASK |
@@ -3434,7 +3413,7 @@ static u32 gfx_v7_0_halt_rlc(struct amdgpu_device *adev)
 	return orig;
 }
 
-void gfx_v7_0_enter_rlc_safe_mode(struct amdgpu_device *adev)
+static void gfx_v7_0_enter_rlc_safe_mode(struct amdgpu_device *adev)
 {
 	u32 tmp, i, mask;
 
@@ -3456,7 +3435,7 @@ void gfx_v7_0_enter_rlc_safe_mode(struct amdgpu_device *adev)
 	}
 }
 
-void gfx_v7_0_exit_rlc_safe_mode(struct amdgpu_device *adev)
+static void gfx_v7_0_exit_rlc_safe_mode(struct amdgpu_device *adev)
 {
 	u32 tmp;
 
@@ -3471,7 +3450,7 @@ void gfx_v7_0_exit_rlc_safe_mode(struct amdgpu_device *adev)
  *
  * Halt the RLC ME (MicroEngine) (CIK).
  */
-void gfx_v7_0_rlc_stop(struct amdgpu_device *adev)
+static void gfx_v7_0_rlc_stop(struct amdgpu_device *adev)
 {
 	WREG32(mmRLC_CNTL, 0);
 
@@ -3547,7 +3526,7 @@ static int gfx_v7_0_rlc_resume(struct amdgpu_device *adev)
 	WREG32(mmRLC_LB_CNTR_MAX, 0x00008000);
 
 	mutex_lock(&adev->grbm_idx_mutex);
-	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	WREG32(mmRLC_LB_INIT_CU_MASK, 0xffffffff);
 	WREG32(mmRLC_LB_PARAMS, 0x00600408);
 	WREG32(mmRLC_LB_CNTL, 0x80000004);
@@ -3587,7 +3566,7 @@ static void gfx_v7_0_enable_cgcg(struct amdgpu_device *adev, bool enable)
 		tmp = gfx_v7_0_halt_rlc(adev);
 
 		mutex_lock(&adev->grbm_idx_mutex);
-		gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+		gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 		WREG32(mmRLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff);
 		WREG32(mmRLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff);
 		tmp2 = RLC_SERDES_WR_CTRL__BPM_ADDR_MASK |
@@ -3638,7 +3617,7 @@ static void gfx_v7_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 		tmp = gfx_v7_0_halt_rlc(adev);
 
 		mutex_lock(&adev->grbm_idx_mutex);
-		gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+		gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 		WREG32(mmRLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff);
 		WREG32(mmRLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff);
 		data = RLC_SERDES_WR_CTRL__BPM_ADDR_MASK |
@@ -3689,7 +3668,7 @@ static void gfx_v7_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 		tmp = gfx_v7_0_halt_rlc(adev);
 
 		mutex_lock(&adev->grbm_idx_mutex);
-		gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+		gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 		WREG32(mmRLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff);
 		WREG32(mmRLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff);
 		data = RLC_SERDES_WR_CTRL__BPM_ADDR_MASK | RLC_SERDES_WR_CTRL__MGCG_OVERRIDE_1_MASK;
@@ -3867,6 +3846,20 @@ static void gfx_v7_0_enable_gfx_cgpg(struct amdgpu_device *adev,
 	}
 }
 
+static void gfx_v7_0_set_user_cu_inactive_bitmap(struct amdgpu_device *adev,
+						 u32 bitmap)
+{
+	u32 data;
+
+	if (!bitmap)
+		return;
+
+	data = bitmap << GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT;
+	data &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK;
+
+	WREG32(mmGC_USER_SHADER_ARRAY_CONFIG, data);
+}
+
 static u32 gfx_v7_0_get_cu_active_bitmap(struct amdgpu_device *adev)
 {
 	u32 data, mask;
@@ -4123,7 +4116,7 @@ static void gfx_v7_0_fini_pg(struct amdgpu_device *adev)
  * Fetches a GPU clock counter snapshot (SI).
  * Returns the 64 bit clock counter snapshot.
  */
-uint64_t gfx_v7_0_get_gpu_clock_counter(struct amdgpu_device *adev)
+static uint64_t gfx_v7_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 {
 	uint64_t clock;
 
@@ -4183,12 +4176,24 @@ static void gfx_v7_0_ring_emit_gds_switch(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, (1 << (oa_size + oa_base)) - (1 << oa_base));
 }
 
+static const struct amdgpu_gfx_funcs gfx_v7_0_gfx_funcs = {
+	.get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter,
+	.select_se_sh = &gfx_v7_0_select_se_sh,
+};
+
+static const struct amdgpu_rlc_funcs gfx_v7_0_rlc_funcs = {
+	.enter_safe_mode = gfx_v7_0_enter_rlc_safe_mode,
+	.exit_safe_mode = gfx_v7_0_exit_rlc_safe_mode
+};
+
 static int gfx_v7_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	adev->gfx.num_gfx_rings = GFX7_NUM_GFX_RINGS;
 	adev->gfx.num_compute_rings = GFX7_NUM_COMPUTE_RINGS;
+	adev->gfx.funcs = &gfx_v7_0_gfx_funcs;
+	adev->gfx.rlc.funcs = &gfx_v7_0_rlc_funcs;
 	gfx_v7_0_set_ring_funcs(adev);
 	gfx_v7_0_set_irq_funcs(adev);
 	gfx_v7_0_set_gds_init(adev);
@@ -5032,16 +5037,22 @@ static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev)
 	int i, j, k, counter, active_cu_number = 0;
 	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0;
 	struct amdgpu_cu_info *cu_info = &adev->gfx.cu_info;
+	unsigned disable_masks[4 * 2];
 
 	memset(cu_info, 0, sizeof(*cu_info));
 
+	amdgpu_gfx_parse_disable_cu(disable_masks, 4, 2);
+
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
 			mask = 1;
 			ao_bitmap = 0;
 			counter = 0;
-			gfx_v7_0_select_se_sh(adev, i, j);
+			gfx_v7_0_select_se_sh(adev, i, j, 0xffffffff);
+			if (i < 4 && j < 2)
+				gfx_v7_0_set_user_cu_inactive_bitmap(
+					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v7_0_get_cu_active_bitmap(adev);
 			cu_info->bitmap[i][j] = bitmap;
 
@@ -5057,7 +5068,7 @@ static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev)
 			ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8));
 		}
 	}
-	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+	gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	cu_info->number = active_cu_number;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h
index e747aa935c88..94e3ea147c26 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h
@@ -26,11 +26,4 @@
 
 extern const struct amd_ip_funcs gfx_v7_0_ip_funcs;
 
-/* XXX these shouldn't be exported */
-void gfx_v7_0_enter_rlc_safe_mode(struct amdgpu_device *adev);
-void gfx_v7_0_exit_rlc_safe_mode(struct amdgpu_device *adev);
-void gfx_v7_0_rlc_stop(struct amdgpu_device *adev);
-uint64_t gfx_v7_0_get_gpu_clock_counter(struct amdgpu_device *adev);
-void gfx_v7_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num);
-
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index c2ef94511f70..bff8668e9e6d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -787,26 +787,25 @@ static int gfx_v8_0_ring_test_ring(struct amdgpu_ring *ring)
 	return r;
 }
 
-static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring)
+static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib ib;
 	struct fence *f = NULL;
 	uint32_t scratch;
 	uint32_t tmp = 0;
-	unsigned i;
-	int r;
+	long r;
 
 	r = amdgpu_gfx_scratch_get(adev, &scratch);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get scratch reg (%d).\n", r);
+		DRM_ERROR("amdgpu: failed to get scratch reg (%ld).\n", r);
 		return r;
 	}
 	WREG32(scratch, 0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
 	r = amdgpu_ib_get(adev, NULL, 256, &ib);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get ib (%d).\n", r);
+		DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 		goto err1;
 	}
 	ib.ptr[0] = PACKET3(PACKET3_SET_UCONFIG_REG, 1);
@@ -818,28 +817,25 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring)
 	if (r)
 		goto err2;
 
-	r = fence_wait(f, false);
-	if (r) {
-		DRM_ERROR("amdgpu: fence wait failed (%d).\n", r);
+	r = fence_wait_timeout(f, false, timeout);
+	if (r == 0) {
+		DRM_ERROR("amdgpu: IB test timed out.\n");
+		r = -ETIMEDOUT;
 		goto err2;
-	}
-	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32(scratch);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-	if (i < adev->usec_timeout) {
-		DRM_INFO("ib test on ring %d succeeded in %u usecs\n",
-			 ring->idx, i);
+	} else if (r < 0) {
+		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 		goto err2;
+	}
+	tmp = RREG32(scratch);
+	if (tmp == 0xDEADBEEF) {
+		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
 			  scratch, tmp);
 		r = -EINVAL;
 	}
 err2:
-	fence_put(f);
 	amdgpu_ib_free(adev, &ib, NULL);
 	fence_put(f);
 err1:
@@ -1160,6 +1156,71 @@ static void gfx_v8_0_get_csb_buffer(struct amdgpu_device *adev,
 	buffer[count++] = cpu_to_le32(0);
 }
 
+static void cz_init_cp_jump_table(struct amdgpu_device *adev)
+{
+	const __le32 *fw_data;
+	volatile u32 *dst_ptr;
+	int me, i, max_me = 4;
+	u32 bo_offset = 0;
+	u32 table_offset, table_size;
+
+	if (adev->asic_type == CHIP_CARRIZO)
+		max_me = 5;
+
+	/* write the cp table buffer */
+	dst_ptr = adev->gfx.rlc.cp_table_ptr;
+	for (me = 0; me < max_me; me++) {
+		if (me == 0) {
+			const struct gfx_firmware_header_v1_0 *hdr =
+				(const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data;
+			fw_data = (const __le32 *)
+				(adev->gfx.ce_fw->data +
+				 le32_to_cpu(hdr->header.ucode_array_offset_bytes));
+			table_offset = le32_to_cpu(hdr->jt_offset);
+			table_size = le32_to_cpu(hdr->jt_size);
+		} else if (me == 1) {
+			const struct gfx_firmware_header_v1_0 *hdr =
+				(const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data;
+			fw_data = (const __le32 *)
+				(adev->gfx.pfp_fw->data +
+				 le32_to_cpu(hdr->header.ucode_array_offset_bytes));
+			table_offset = le32_to_cpu(hdr->jt_offset);
+			table_size = le32_to_cpu(hdr->jt_size);
+		} else if (me == 2) {
+			const struct gfx_firmware_header_v1_0 *hdr =
+				(const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data;
+			fw_data = (const __le32 *)
+				(adev->gfx.me_fw->data +
+				 le32_to_cpu(hdr->header.ucode_array_offset_bytes));
+			table_offset = le32_to_cpu(hdr->jt_offset);
+			table_size = le32_to_cpu(hdr->jt_size);
+		} else if (me == 3) {
+			const struct gfx_firmware_header_v1_0 *hdr =
+				(const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
+			fw_data = (const __le32 *)
+				(adev->gfx.mec_fw->data +
+				 le32_to_cpu(hdr->header.ucode_array_offset_bytes));
+			table_offset = le32_to_cpu(hdr->jt_offset);
+			table_size = le32_to_cpu(hdr->jt_size);
+		} else  if (me == 4) {
+			const struct gfx_firmware_header_v1_0 *hdr =
+				(const struct gfx_firmware_header_v1_0 *)adev->gfx.mec2_fw->data;
+			fw_data = (const __le32 *)
+				(adev->gfx.mec2_fw->data +
+				 le32_to_cpu(hdr->header.ucode_array_offset_bytes));
+			table_offset = le32_to_cpu(hdr->jt_offset);
+			table_size = le32_to_cpu(hdr->jt_size);
+		}
+
+		for (i = 0; i < table_size; i ++) {
+			dst_ptr[bo_offset + i] =
+				cpu_to_le32(le32_to_cpu(fw_data[table_offset + i]));
+		}
+
+		bo_offset += table_size;
+	}
+}
+
 static void gfx_v8_0_rlc_fini(struct amdgpu_device *adev)
 {
 	int r;
@@ -1175,6 +1236,18 @@ static void gfx_v8_0_rlc_fini(struct amdgpu_device *adev)
 		amdgpu_bo_unref(&adev->gfx.rlc.clear_state_obj);
 		adev->gfx.rlc.clear_state_obj = NULL;
 	}
+
+	/* jump table block */
+	if (adev->gfx.rlc.cp_table_obj) {
+		r = amdgpu_bo_reserve(adev->gfx.rlc.cp_table_obj, false);
+		if (unlikely(r != 0))
+			dev_warn(adev->dev, "(%d) reserve RLC cp table bo failed\n", r);
+		amdgpu_bo_unpin(adev->gfx.rlc.cp_table_obj);
+		amdgpu_bo_unreserve(adev->gfx.rlc.cp_table_obj);
+
+		amdgpu_bo_unref(&adev->gfx.rlc.cp_table_obj);
+		adev->gfx.rlc.cp_table_obj = NULL;
+	}
 }
 
 static int gfx_v8_0_rlc_init(struct amdgpu_device *adev)
@@ -1231,6 +1304,46 @@ static int gfx_v8_0_rlc_init(struct amdgpu_device *adev)
 		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
 	}
 
+	if ((adev->asic_type == CHIP_CARRIZO) ||
+	    (adev->asic_type == CHIP_STONEY)) {
+		adev->gfx.rlc.cp_table_size = ALIGN(96 * 5 * 4, 2048) + (64 * 1024); /* JT + GDS */
+		if (adev->gfx.rlc.cp_table_obj == NULL) {
+			r = amdgpu_bo_create(adev, adev->gfx.rlc.cp_table_size, PAGE_SIZE, true,
+					     AMDGPU_GEM_DOMAIN_VRAM,
+					     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
+					     NULL, NULL,
+					     &adev->gfx.rlc.cp_table_obj);
+			if (r) {
+				dev_warn(adev->dev, "(%d) create RLC cp table bo failed\n", r);
+				return r;
+			}
+		}
+
+		r = amdgpu_bo_reserve(adev->gfx.rlc.cp_table_obj, false);
+		if (unlikely(r != 0)) {
+			dev_warn(adev->dev, "(%d) reserve RLC cp table bo failed\n", r);
+			return r;
+		}
+		r = amdgpu_bo_pin(adev->gfx.rlc.cp_table_obj, AMDGPU_GEM_DOMAIN_VRAM,
+				  &adev->gfx.rlc.cp_table_gpu_addr);
+		if (r) {
+			amdgpu_bo_unreserve(adev->gfx.rlc.cp_table_obj);
+			dev_warn(adev->dev, "(%d) pin RLC cp_table bo failed\n", r);
+			return r;
+		}
+		r = amdgpu_bo_kmap(adev->gfx.rlc.cp_table_obj, (void **)&adev->gfx.rlc.cp_table_ptr);
+		if (r) {
+			dev_warn(adev->dev, "(%d) map RLC cp table bo failed\n", r);
+			return r;
+		}
+
+		cz_init_cp_jump_table(adev);
+
+		amdgpu_bo_kunmap(adev->gfx.rlc.cp_table_obj);
+		amdgpu_bo_unreserve(adev->gfx.rlc.cp_table_obj);
+
+	}
+
 	return 0;
 }
 
@@ -1612,7 +1725,6 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 		RREG32(sec_ded_counter_registers[i]);
 
 fail:
-	fence_put(f);
 	amdgpu_ib_free(adev, &ib, NULL);
 	fence_put(f);
 
@@ -3339,9 +3451,15 @@ static void gfx_v8_0_tiling_mode_table_init(struct amdgpu_device *adev)
 	}
 }
 
-void gfx_v8_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num)
+static void gfx_v8_0_select_se_sh(struct amdgpu_device *adev,
+				  u32 se_num, u32 sh_num, u32 instance)
 {
-	u32 data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES, 1);
+	u32 data;
+
+	if (instance == 0xffffffff)
+		data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES, 1);
+	else
+		data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_INDEX, instance);
 
 	if ((se_num == 0xffffffff) && (sh_num == 0xffffffff)) {
 		data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SH_BROADCAST_WRITES, 1);
@@ -3391,13 +3509,13 @@ static void gfx_v8_0_setup_rb(struct amdgpu_device *adev)
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
-			gfx_v8_0_select_se_sh(adev, i, j);
+			gfx_v8_0_select_se_sh(adev, i, j, 0xffffffff);
 			data = gfx_v8_0_get_rb_active_bitmap(adev);
 			active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) *
 					       rb_bitmap_width_per_sh);
 		}
 	}
-	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	adev->gfx.config.backend_enable_mask = active_rbs;
@@ -3501,7 +3619,7 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
 	 * making sure that the following register writes will be broadcasted
 	 * to all the shaders
 	 */
-	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 
 	WREG32(mmPA_SC_FIFO_SIZE,
 		   (adev->gfx.config.sc_prim_fifo_size_frontend <<
@@ -3524,7 +3642,7 @@ static void gfx_v8_0_wait_for_rlc_serdes(struct amdgpu_device *adev)
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
-			gfx_v8_0_select_se_sh(adev, i, j);
+			gfx_v8_0_select_se_sh(adev, i, j, 0xffffffff);
 			for (k = 0; k < adev->usec_timeout; k++) {
 				if (RREG32(mmRLC_SERDES_CU_MASTER_BUSY) == 0)
 					break;
@@ -3532,7 +3650,7 @@ static void gfx_v8_0_wait_for_rlc_serdes(struct amdgpu_device *adev)
 			}
 		}
 	}
-	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	mask = RLC_SERDES_NONCU_MASTER_BUSY__SE_MASTER_BUSY_MASK |
@@ -3693,13 +3811,13 @@ static void gfx_v8_0_enable_save_restore_machine(struct amdgpu_device *adev)
 	WREG32(mmRLC_SRM_CNTL, data);
 }
 
-static void polaris11_init_power_gating(struct amdgpu_device *adev)
+static void gfx_v8_0_init_power_gating(struct amdgpu_device *adev)
 {
 	uint32_t data;
 
 	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
-			AMD_PG_SUPPORT_GFX_SMG |
-			AMD_PG_SUPPORT_GFX_DMG)) {
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG)) {
 		data = RREG32(mmCP_RB_WPTR_POLL_CNTL);
 		data &= ~CP_RB_WPTR_POLL_CNTL__IDLE_POLL_COUNT_MASK;
 		data |= (0x60 << CP_RB_WPTR_POLL_CNTL__IDLE_POLL_COUNT__SHIFT);
@@ -3724,6 +3842,53 @@ static void polaris11_init_power_gating(struct amdgpu_device *adev)
 	}
 }
 
+static void cz_enable_sck_slow_down_on_power_up(struct amdgpu_device *adev,
+						bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(mmRLC_PG_CNTL);
+
+	if (enable)
+		data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK;
+	else
+		data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK;
+
+	if (orig != data)
+		WREG32(mmRLC_PG_CNTL, data);
+}
+
+static void cz_enable_sck_slow_down_on_power_down(struct amdgpu_device *adev,
+						  bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(mmRLC_PG_CNTL);
+
+	if (enable)
+		data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK;
+	else
+		data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK;
+
+	if (orig != data)
+		WREG32(mmRLC_PG_CNTL, data);
+}
+
+static void cz_enable_cp_power_gating(struct amdgpu_device *adev, bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(mmRLC_PG_CNTL);
+
+	if (enable)
+		data &= ~RLC_PG_CNTL__CP_PG_DISABLE_MASK;
+	else
+		data |= RLC_PG_CNTL__CP_PG_DISABLE_MASK;
+
+	if (orig != data)
+		WREG32(mmRLC_PG_CNTL, data);
+}
+
 static void gfx_v8_0_init_pg(struct amdgpu_device *adev)
 {
 	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
@@ -3736,8 +3901,25 @@ static void gfx_v8_0_init_pg(struct amdgpu_device *adev)
 		gfx_v8_0_init_save_restore_list(adev);
 		gfx_v8_0_enable_save_restore_machine(adev);
 
-		if (adev->asic_type == CHIP_POLARIS11)
-			polaris11_init_power_gating(adev);
+		if ((adev->asic_type == CHIP_CARRIZO) ||
+		    (adev->asic_type == CHIP_STONEY)) {
+			WREG32(mmRLC_JUMP_TABLE_RESTORE, adev->gfx.rlc.cp_table_gpu_addr >> 8);
+			gfx_v8_0_init_power_gating(adev);
+			WREG32(mmRLC_PG_ALWAYS_ON_CU_MASK, adev->gfx.cu_info.ao_cu_mask);
+			if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) {
+				cz_enable_sck_slow_down_on_power_up(adev, true);
+				cz_enable_sck_slow_down_on_power_down(adev, true);
+			} else {
+				cz_enable_sck_slow_down_on_power_up(adev, false);
+				cz_enable_sck_slow_down_on_power_down(adev, false);
+			}
+			if (adev->pg_flags & AMD_PG_SUPPORT_CP)
+				cz_enable_cp_power_gating(adev, true);
+			else
+				cz_enable_cp_power_gating(adev, false);
+		} else if (adev->asic_type == CHIP_POLARIS11) {
+			gfx_v8_0_init_power_gating(adev);
+		}
 	}
 }
 
@@ -4976,7 +5158,7 @@ static int gfx_v8_0_soft_reset(void *handle)
  * Fetches a GPU clock counter snapshot.
  * Returns the 64 bit clock counter snapshot.
  */
-uint64_t gfx_v8_0_get_gpu_clock_counter(struct amdgpu_device *adev)
+static uint64_t gfx_v8_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 {
 	uint64_t clock;
 
@@ -5036,12 +5218,18 @@ static void gfx_v8_0_ring_emit_gds_switch(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, (1 << (oa_size + oa_base)) - (1 << oa_base));
 }
 
+static const struct amdgpu_gfx_funcs gfx_v8_0_gfx_funcs = {
+	.get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter,
+	.select_se_sh = &gfx_v8_0_select_se_sh,
+};
+
 static int gfx_v8_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	adev->gfx.num_gfx_rings = GFX8_NUM_GFX_RINGS;
 	adev->gfx.num_compute_rings = GFX8_NUM_COMPUTE_RINGS;
+	adev->gfx.funcs = &gfx_v8_0_gfx_funcs;
 	gfx_v8_0_set_ring_funcs(adev);
 	gfx_v8_0_set_irq_funcs(adev);
 	gfx_v8_0_set_gds_init(adev);
@@ -5074,51 +5262,43 @@ static int gfx_v8_0_late_init(void *handle)
 	return 0;
 }
 
-static void polaris11_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev,
-		bool enable)
+static void gfx_v8_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev,
+						       bool enable)
 {
 	uint32_t data, temp;
 
-	/* Send msg to SMU via Powerplay */
-	amdgpu_set_powergating_state(adev,
-			AMD_IP_BLOCK_TYPE_SMC,
-			enable ? AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE);
+	if (adev->asic_type == CHIP_POLARIS11)
+		/* Send msg to SMU via Powerplay */
+		amdgpu_set_powergating_state(adev,
+					     AMD_IP_BLOCK_TYPE_SMC,
+					     enable ?
+					     AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE);
 
-	if (enable) {
-		/* Enable static MGPG */
-		temp = data = RREG32(mmRLC_PG_CNTL);
+	temp = data = RREG32(mmRLC_PG_CNTL);
+	/* Enable static MGPG */
+	if (enable)
 		data |= RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK;
-
-		if (temp != data)
-			WREG32(mmRLC_PG_CNTL, data);
-	} else {
-		temp = data = RREG32(mmRLC_PG_CNTL);
+	else
 		data &= ~RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK;
 
-		if (temp != data)
-			WREG32(mmRLC_PG_CNTL, data);
-	}
+	if (temp != data)
+		WREG32(mmRLC_PG_CNTL, data);
 }
 
-static void polaris11_enable_gfx_dynamic_mg_power_gating(struct amdgpu_device *adev,
-		bool enable)
+static void gfx_v8_0_enable_gfx_dynamic_mg_power_gating(struct amdgpu_device *adev,
+							bool enable)
 {
 	uint32_t data, temp;
 
-	if (enable) {
-		/* Enable dynamic MGPG */
-		temp = data = RREG32(mmRLC_PG_CNTL);
+	temp = data = RREG32(mmRLC_PG_CNTL);
+	/* Enable dynamic MGPG */
+	if (enable)
 		data |= RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK;
-
-		if (temp != data)
-			WREG32(mmRLC_PG_CNTL, data);
-	} else {
-		temp = data = RREG32(mmRLC_PG_CNTL);
+	else
 		data &= ~RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK;
 
-		if (temp != data)
-			WREG32(mmRLC_PG_CNTL, data);
-	}
+	if (temp != data)
+		WREG32(mmRLC_PG_CNTL, data);
 }
 
 static void polaris11_enable_gfx_quick_mg_power_gating(struct amdgpu_device *adev,
@@ -5126,19 +5306,63 @@ static void polaris11_enable_gfx_quick_mg_power_gating(struct amdgpu_device *ade
 {
 	uint32_t data, temp;
 
-	if (enable) {
-		/* Enable quick PG */
-		temp = data = RREG32(mmRLC_PG_CNTL);
-		data |= 0x100000;
+	temp = data = RREG32(mmRLC_PG_CNTL);
+	/* Enable quick PG */
+	if (enable)
+		data |= RLC_PG_CNTL__QUICK_PG_ENABLE_MASK;
+	else
+		data &= ~RLC_PG_CNTL__QUICK_PG_ENABLE_MASK;
 
-		if (temp != data)
-			WREG32(mmRLC_PG_CNTL, data);
-	} else {
-		temp = data = RREG32(mmRLC_PG_CNTL);
-		data &= ~0x100000;
+	if (temp != data)
+		WREG32(mmRLC_PG_CNTL, data);
+}
 
-		if (temp != data)
-			WREG32(mmRLC_PG_CNTL, data);
+static void cz_enable_gfx_cg_power_gating(struct amdgpu_device *adev,
+					  bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(mmRLC_PG_CNTL);
+
+	if (enable)
+		data |= RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
+	else
+		data &= ~RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
+
+	if (orig != data)
+		WREG32(mmRLC_PG_CNTL, data);
+}
+
+static void cz_enable_gfx_pipeline_power_gating(struct amdgpu_device *adev,
+						bool enable)
+{
+	u32 data, orig;
+
+	orig = data = RREG32(mmRLC_PG_CNTL);
+
+	if (enable)
+		data |= RLC_PG_CNTL__GFX_PIPELINE_PG_ENABLE_MASK;
+	else
+		data &= ~RLC_PG_CNTL__GFX_PIPELINE_PG_ENABLE_MASK;
+
+	if (orig != data)
+		WREG32(mmRLC_PG_CNTL, data);
+
+	/* Read any GFX register to wake up GFX. */
+	if (!enable)
+		data = RREG32(mmDB_RENDER_CONTROL);
+}
+
+static void cz_update_gfx_cg_power_gating(struct amdgpu_device *adev,
+					  bool enable)
+{
+	if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) && enable) {
+		cz_enable_gfx_cg_power_gating(adev, true);
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PIPELINE)
+			cz_enable_gfx_pipeline_power_gating(adev, true);
+	} else {
+		cz_enable_gfx_cg_power_gating(adev, false);
+		cz_enable_gfx_pipeline_power_gating(adev, false);
 	}
 }
 
@@ -5146,21 +5370,42 @@ static int gfx_v8_0_set_powergating_state(void *handle,
 					  enum amd_powergating_state state)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	bool enable = (state == AMD_PG_STATE_GATE) ? true : false;
 
 	if (!(adev->pg_flags & AMD_PG_SUPPORT_GFX_PG))
 		return 0;
 
 	switch (adev->asic_type) {
+	case CHIP_CARRIZO:
+	case CHIP_STONEY:
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)
+			cz_update_gfx_cg_power_gating(adev, enable);
+
+		if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG) && enable)
+			gfx_v8_0_enable_gfx_static_mg_power_gating(adev, true);
+		else
+			gfx_v8_0_enable_gfx_static_mg_power_gating(adev, false);
+
+		if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_DMG) && enable)
+			gfx_v8_0_enable_gfx_dynamic_mg_power_gating(adev, true);
+		else
+			gfx_v8_0_enable_gfx_dynamic_mg_power_gating(adev, false);
+		break;
 	case CHIP_POLARIS11:
-		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG)
-			polaris11_enable_gfx_static_mg_power_gating(adev,
-					state == AMD_PG_STATE_GATE ? true : false);
-		else if (adev->pg_flags & AMD_PG_SUPPORT_GFX_DMG)
-			polaris11_enable_gfx_dynamic_mg_power_gating(adev,
-					state == AMD_PG_STATE_GATE ? true : false);
+		if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG) && enable)
+			gfx_v8_0_enable_gfx_static_mg_power_gating(adev, true);
+		else
+			gfx_v8_0_enable_gfx_static_mg_power_gating(adev, false);
+
+		if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_DMG) && enable)
+			gfx_v8_0_enable_gfx_dynamic_mg_power_gating(adev, true);
+		else
+			gfx_v8_0_enable_gfx_dynamic_mg_power_gating(adev, false);
+
+		if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_QUICK_MG) && enable)
+			polaris11_enable_gfx_quick_mg_power_gating(adev, true);
 		else
-			polaris11_enable_gfx_quick_mg_power_gating(adev,
-					state == AMD_PG_STATE_GATE ? true : false);
+			polaris11_enable_gfx_quick_mg_power_gating(adev, false);
 		break;
 	default:
 		break;
@@ -5174,7 +5419,7 @@ static void gfx_v8_0_send_serdes_cmd(struct amdgpu_device *adev,
 {
 	uint32_t data;
 
-	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 
 	WREG32(mmRLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff);
 	WREG32(mmRLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff);
@@ -5562,6 +5807,8 @@ static void gfx_v8_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev
 			WREG32(mmRLC_CGCG_CGLS_CTRL, data);
 	}
 
+	gfx_v8_0_wait_for_rlc_serdes(adev);
+
 	adev->gfx.rlc.funcs->exit_safe_mode(adev);
 }
 static int gfx_v8_0_update_gfx_clock_gating(struct amdgpu_device *adev,
@@ -5687,17 +5934,6 @@ static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				      unsigned vm_id, bool ctx_switch)
 {
 	u32 header, control = 0;
-	u32 next_rptr = ring->wptr + 5;
-
-	if (ctx_switch)
-		next_rptr += 2;
-
-	next_rptr += 4;
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM);
-	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, next_rptr);
 
 	/* insert SWITCH_BUFFER packet before first IB in the ring frame */
 	if (ctx_switch) {
@@ -5726,23 +5962,9 @@ static void gfx_v8_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
 					  struct amdgpu_ib *ib,
 					  unsigned vm_id, bool ctx_switch)
 {
-	u32 header, control = 0;
-	u32 next_rptr = ring->wptr + 5;
-
-	control |= INDIRECT_BUFFER_VALID;
-
-	next_rptr += 4;
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM);
-	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
-	amdgpu_ring_write(ring, next_rptr);
+	u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vm_id << 24);
 
-	header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
-
-	control |= ib->length_dw | (vm_id << 24);
-
-	amdgpu_ring_write(ring, header);
+	amdgpu_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	amdgpu_ring_write(ring,
 #ifdef __BIG_ENDIAN
 					  (2 << 0) |
@@ -6195,9 +6417,9 @@ static void gfx_v8_0_set_rlc_funcs(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_TOPAZ:
-	case CHIP_STONEY:
 		adev->gfx.rlc.funcs = &iceland_rlc_funcs;
 		break;
+	case CHIP_STONEY:
 	case CHIP_CARRIZO:
 		adev->gfx.rlc.funcs = &cz_rlc_funcs;
 		break;
@@ -6235,6 +6457,20 @@ static void gfx_v8_0_set_gds_init(struct amdgpu_device *adev)
 	}
 }
 
+static void gfx_v8_0_set_user_cu_inactive_bitmap(struct amdgpu_device *adev,
+						 u32 bitmap)
+{
+	u32 data;
+
+	if (!bitmap)
+		return;
+
+	data = bitmap << GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT;
+	data &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK;
+
+	WREG32(mmGC_USER_SHADER_ARRAY_CONFIG, data);
+}
+
 static u32 gfx_v8_0_get_cu_active_bitmap(struct amdgpu_device *adev)
 {
 	u32 data, mask;
@@ -6255,16 +6491,22 @@ static void gfx_v8_0_get_cu_info(struct amdgpu_device *adev)
 	int i, j, k, counter, active_cu_number = 0;
 	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0;
 	struct amdgpu_cu_info *cu_info = &adev->gfx.cu_info;
+	unsigned disable_masks[4 * 2];
 
 	memset(cu_info, 0, sizeof(*cu_info));
 
+	amdgpu_gfx_parse_disable_cu(disable_masks, 4, 2);
+
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
 			mask = 1;
 			ao_bitmap = 0;
 			counter = 0;
-			gfx_v8_0_select_se_sh(adev, i, j);
+			gfx_v8_0_select_se_sh(adev, i, j, 0xffffffff);
+			if (i < 4 && j < 2)
+				gfx_v8_0_set_user_cu_inactive_bitmap(
+					adev, disable_masks[i * 2 + j]);
 			bitmap = gfx_v8_0_get_cu_active_bitmap(adev);
 			cu_info->bitmap[i][j] = bitmap;
 
@@ -6280,7 +6522,7 @@ static void gfx_v8_0_get_cu_info(struct amdgpu_device *adev)
 			ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8));
 		}
 	}
-	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+	gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	cu_info->number = active_cu_number;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h
index 16a49f53a2fa..bc82c794312c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h
@@ -26,7 +26,6 @@
 
 extern const struct amd_ip_funcs gfx_v8_0_ip_funcs;
 
-uint64_t gfx_v8_0_get_gpu_clock_counter(struct amdgpu_device *adev);
 void gfx_v8_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 1feb6439cb0b..d24a82bd0c7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -39,6 +39,7 @@
 
 static void gmc_v7_0_set_gart_funcs(struct amdgpu_device *adev);
 static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev);
+static int gmc_v7_0_wait_for_idle(void *handle);
 
 MODULE_FIRMWARE("radeon/bonaire_mc.bin");
 MODULE_FIRMWARE("radeon/hawaii_mc.bin");
@@ -73,39 +74,15 @@ static void gmc_v7_0_init_golden_registers(struct amdgpu_device *adev)
 	}
 }
 
-/**
- * gmc7_mc_wait_for_idle - wait for MC idle callback.
- *
- * @adev: amdgpu_device pointer
- *
- * Wait for the MC (memory controller) to be idle.
- * (evergreen+).
- * Returns 0 if the MC is idle, -1 if not.
- */
-int gmc_v7_0_mc_wait_for_idle(struct amdgpu_device *adev)
-{
-	unsigned i;
-	u32 tmp;
-
-	for (i = 0; i < adev->usec_timeout; i++) {
-		/* read MC_STATUS */
-		tmp = RREG32(mmSRBM_STATUS) & 0x1F00;
-		if (!tmp)
-			return 0;
-		udelay(1);
-	}
-	return -1;
-}
-
-void gmc_v7_0_mc_stop(struct amdgpu_device *adev,
-		      struct amdgpu_mode_mc_save *save)
+static void gmc_v7_0_mc_stop(struct amdgpu_device *adev,
+			     struct amdgpu_mode_mc_save *save)
 {
 	u32 blackout;
 
 	if (adev->mode_info.num_crtc)
 		amdgpu_display_stop_mc_access(adev, save);
 
-	amdgpu_asic_wait_for_mc_idle(adev);
+	gmc_v7_0_wait_for_idle((void *)adev);
 
 	blackout = RREG32(mmMC_SHARED_BLACKOUT_CNTL);
 	if (REG_GET_FIELD(blackout, MC_SHARED_BLACKOUT_CNTL, BLACKOUT_MODE) != 1) {
@@ -120,8 +97,8 @@ void gmc_v7_0_mc_stop(struct amdgpu_device *adev,
 	udelay(100);
 }
 
-void gmc_v7_0_mc_resume(struct amdgpu_device *adev,
-			struct amdgpu_mode_mc_save *save)
+static void gmc_v7_0_mc_resume(struct amdgpu_device *adev,
+			       struct amdgpu_mode_mc_save *save)
 {
 	u32 tmp;
 
@@ -311,7 +288,7 @@ static void gmc_v7_0_mc_program(struct amdgpu_device *adev)
 		amdgpu_display_set_vga_render_state(adev, false);
 
 	gmc_v7_0_mc_stop(adev, &save);
-	if (amdgpu_asic_wait_for_mc_idle(adev)) {
+	if (gmc_v7_0_wait_for_idle((void *)adev)) {
 		dev_warn(adev->dev, "Wait for MC idle timedout !\n");
 	}
 	/* Update configuration */
@@ -331,7 +308,7 @@ static void gmc_v7_0_mc_program(struct amdgpu_device *adev)
 	WREG32(mmMC_VM_AGP_BASE, 0);
 	WREG32(mmMC_VM_AGP_TOP, 0x0FFFFFFF);
 	WREG32(mmMC_VM_AGP_BOT, 0x0FFFFFFF);
-	if (amdgpu_asic_wait_for_mc_idle(adev)) {
+	if (gmc_v7_0_wait_for_idle((void *)adev)) {
 		dev_warn(adev->dev, "Wait for MC idle timedout !\n");
 	}
 	gmc_v7_0_mc_resume(adev, &save);
@@ -1137,7 +1114,7 @@ static int gmc_v7_0_soft_reset(void *handle)
 
 	if (srbm_soft_reset) {
 		gmc_v7_0_mc_stop(adev, &save);
-		if (gmc_v7_0_wait_for_idle(adev)) {
+		if (gmc_v7_0_wait_for_idle((void *)adev)) {
 			dev_warn(adev->dev, "Wait for GMC idle timed out !\n");
 		}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.h b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.h
index 36fcbbc46ada..0b386b5d2f7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.h
@@ -26,11 +26,4 @@
 
 extern const struct amd_ip_funcs gmc_v7_0_ip_funcs;
 
-/* XXX these shouldn't be exported */
-void gmc_v7_0_mc_stop(struct amdgpu_device *adev,
-		      struct amdgpu_mode_mc_save *save);
-void gmc_v7_0_mc_resume(struct amdgpu_device *adev,
-			struct amdgpu_mode_mc_save *save);
-int gmc_v7_0_mc_wait_for_idle(struct amdgpu_device *adev);
-
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 9945d5bbf1fe..717359d3ba8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -41,6 +41,7 @@
 
 static void gmc_v8_0_set_gart_funcs(struct amdgpu_device *adev);
 static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev);
+static int gmc_v8_0_wait_for_idle(void *handle);
 
 MODULE_FIRMWARE("amdgpu/tonga_mc.bin");
 MODULE_FIRMWARE("amdgpu/polaris11_mc.bin");
@@ -147,44 +148,15 @@ static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev)
 	}
 }
 
-/**
- * gmc8_mc_wait_for_idle - wait for MC idle callback.
- *
- * @adev: amdgpu_device pointer
- *
- * Wait for the MC (memory controller) to be idle.
- * (evergreen+).
- * Returns 0 if the MC is idle, -1 if not.
- */
-int gmc_v8_0_mc_wait_for_idle(struct amdgpu_device *adev)
-{
-	unsigned i;
-	u32 tmp;
-
-	for (i = 0; i < adev->usec_timeout; i++) {
-		/* read MC_STATUS */
-		tmp = RREG32(mmSRBM_STATUS) & (SRBM_STATUS__VMC_BUSY_MASK |
-					       SRBM_STATUS__MCB_BUSY_MASK |
-					       SRBM_STATUS__MCB_NON_DISPLAY_BUSY_MASK |
-					       SRBM_STATUS__MCC_BUSY_MASK |
-					       SRBM_STATUS__MCD_BUSY_MASK |
-					       SRBM_STATUS__VMC1_BUSY_MASK);
-		if (!tmp)
-			return 0;
-		udelay(1);
-	}
-	return -1;
-}
-
-void gmc_v8_0_mc_stop(struct amdgpu_device *adev,
-		      struct amdgpu_mode_mc_save *save)
+static void gmc_v8_0_mc_stop(struct amdgpu_device *adev,
+			     struct amdgpu_mode_mc_save *save)
 {
 	u32 blackout;
 
 	if (adev->mode_info.num_crtc)
 		amdgpu_display_stop_mc_access(adev, save);
 
-	amdgpu_asic_wait_for_mc_idle(adev);
+	gmc_v8_0_wait_for_idle(adev);
 
 	blackout = RREG32(mmMC_SHARED_BLACKOUT_CNTL);
 	if (REG_GET_FIELD(blackout, MC_SHARED_BLACKOUT_CNTL, BLACKOUT_MODE) != 1) {
@@ -199,8 +171,8 @@ void gmc_v8_0_mc_stop(struct amdgpu_device *adev,
 	udelay(100);
 }
 
-void gmc_v8_0_mc_resume(struct amdgpu_device *adev,
-			struct amdgpu_mode_mc_save *save)
+static void gmc_v8_0_mc_resume(struct amdgpu_device *adev,
+			       struct amdgpu_mode_mc_save *save)
 {
 	u32 tmp;
 
@@ -393,7 +365,7 @@ static void gmc_v8_0_mc_program(struct amdgpu_device *adev)
 		amdgpu_display_set_vga_render_state(adev, false);
 
 	gmc_v8_0_mc_stop(adev, &save);
-	if (amdgpu_asic_wait_for_mc_idle(adev)) {
+	if (gmc_v8_0_wait_for_idle((void *)adev)) {
 		dev_warn(adev->dev, "Wait for MC idle timedout !\n");
 	}
 	/* Update configuration */
@@ -413,7 +385,7 @@ static void gmc_v8_0_mc_program(struct amdgpu_device *adev)
 	WREG32(mmMC_VM_AGP_BASE, 0);
 	WREG32(mmMC_VM_AGP_TOP, 0x0FFFFFFF);
 	WREG32(mmMC_VM_AGP_BOT, 0x0FFFFFFF);
-	if (amdgpu_asic_wait_for_mc_idle(adev)) {
+	if (gmc_v8_0_wait_for_idle((void *)adev)) {
 		dev_warn(adev->dev, "Wait for MC idle timedout !\n");
 	}
 	gmc_v8_0_mc_resume(adev, &save);
@@ -1140,7 +1112,7 @@ static int gmc_v8_0_soft_reset(void *handle)
 
 	if (srbm_soft_reset) {
 		gmc_v8_0_mc_stop(adev, &save);
-		if (gmc_v8_0_wait_for_idle(adev)) {
+		if (gmc_v8_0_wait_for_idle((void *)adev)) {
 			dev_warn(adev->dev, "Wait for GMC idle timed out !\n");
 		}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.h b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.h
index 973436086b38..fc5001a8119d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.h
@@ -26,11 +26,4 @@
 
 extern const struct amd_ip_funcs gmc_v8_0_ip_funcs;
 
-/* XXX these shouldn't be exported */
-void gmc_v8_0_mc_stop(struct amdgpu_device *adev,
-		      struct amdgpu_mode_mc_save *save);
-void gmc_v8_0_mc_resume(struct amdgpu_device *adev,
-			struct amdgpu_mode_mc_save *save);
-int gmc_v8_0_mc_wait_for_idle(struct amdgpu_device *adev);
-
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
index 825ccd63f2dc..2f078ad6095c 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
@@ -24,7 +24,7 @@
 #include <linux/firmware.h>
 #include "drmP.h"
 #include "amdgpu.h"
-#include "iceland_smumgr.h"
+#include "iceland_smum.h"
 
 MODULE_FIRMWARE("amdgpu/topaz_smc.bin");
 
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
index 52ee08193295..211839913728 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
@@ -25,7 +25,7 @@
 #include "drmP.h"
 #include "amdgpu.h"
 #include "ppsmc.h"
-#include "iceland_smumgr.h"
+#include "iceland_smum.h"
 #include "smu_ucode_xfer_vi.h"
 #include "amdgpu_ucode.h"
 
@@ -211,7 +211,7 @@ static int iceland_send_msg_to_smc_without_waiting(struct amdgpu_device *adev,
 						   PPSMC_Msg msg)
 {
 	if (!iceland_is_smc_ram_running(adev))
-		return -EINVAL;;
+		return -EINVAL;
 
 	if (wait_smu_response(adev)) {
 		DRM_ERROR("Failed to send previous message\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_smumgr.h b/drivers/gpu/drm/amd/amdgpu/iceland_smum.h
index 1e0769e110fa..5983e3150cc5 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_smumgr.h
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_smum.h
@@ -21,8 +21,8 @@
  *
  */
 
-#ifndef ICELAND_SMUMGR_H
-#define ICELAND_SMUMGR_H
+#ifndef ICELAND_SMUM_H
+#define ICELAND_SMUM_H
 
 #include "ppsmc.h"
 
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index a789a863d677..a845e883f5fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -191,6 +191,7 @@ static void sumo_construct_vid_mapping_table(struct amdgpu_device *adev,
 	vid_mapping_table->num_entries = i;
 }
 
+#if 0
 static const struct kv_lcac_config_values sx_local_cac_cfg_kv[] =
 {
 	{  0,       4,        1    },
@@ -289,6 +290,7 @@ static const struct kv_lcac_config_reg cpl_cac_config_reg[] =
 {
 	{ 0xc0400d80, 0x003e0000, 17, 0x3fc00000, 22, 0x0001fffe, 1, 0x00000001, 0 }
 };
+#endif
 
 static const struct kv_pt_config_reg didt_config_kv[] =
 {
@@ -507,19 +509,19 @@ static int kv_enable_didt(struct amdgpu_device *adev, bool enable)
 	    pi->caps_db_ramping ||
 	    pi->caps_td_ramping ||
 	    pi->caps_tcp_ramping) {
-		gfx_v7_0_enter_rlc_safe_mode(adev);
+		adev->gfx.rlc.funcs->enter_safe_mode(adev);
 
 		if (enable) {
 			ret = kv_program_pt_config_registers(adev, didt_config_kv);
 			if (ret) {
-				gfx_v7_0_exit_rlc_safe_mode(adev);
+				adev->gfx.rlc.funcs->exit_safe_mode(adev);
 				return ret;
 			}
 		}
 
 		kv_do_enable_didt(adev, enable);
 
-		gfx_v7_0_exit_rlc_safe_mode(adev);
+		adev->gfx.rlc.funcs->exit_safe_mode(adev);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/ppsmc.h b/drivers/gpu/drm/amd/amdgpu/ppsmc.h
index 7837f2ecc357..8463245f424f 100644
--- a/drivers/gpu/drm/amd/amdgpu/ppsmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/ppsmc.h
@@ -90,7 +90,9 @@ typedef uint8_t PPSMC_Result;
 #define PPSMC_StartFanControl               ((uint8_t)0x5B)
 #define PPSMC_StopFanControl                ((uint8_t)0x5C)
 #define PPSMC_MSG_NoDisplay                 ((uint8_t)0x5D)
+#define PPSMC_NoDisplay                     ((uint8_t)0x5D)
 #define PPSMC_MSG_HasDisplay                ((uint8_t)0x5E)
+#define PPSMC_HasDisplay                    ((uint8_t)0x5E)
 #define PPSMC_MSG_UVDPowerOFF               ((uint8_t)0x60)
 #define PPSMC_MSG_UVDPowerON                ((uint8_t)0x61)
 #define PPSMC_MSG_EnableULV                 ((uint8_t)0x62)
@@ -108,6 +110,7 @@ typedef uint8_t PPSMC_Result;
 #define PPSMC_MSG_DisableDTE                ((uint8_t)0x88)
 #define PPSMC_MSG_ThrottleOVRDSCLKDS        ((uint8_t)0x96)
 #define PPSMC_MSG_CancelThrottleOVRDSCLKDS  ((uint8_t)0x97)
+#define PPSMC_MSG_EnableACDCGPIOInterrupt   ((uint16_t) 0x149)
 
 /* CI/KV/KB */
 #define PPSMC_MSG_UVDDPM_SetEnabledMask       ((uint16_t) 0x12D)
@@ -161,6 +164,7 @@ typedef uint8_t PPSMC_Result;
 #define PPSMC_MSG_MASTER_DeepSleep_OFF        ((uint16_t) 0x190)
 #define PPSMC_MSG_Remove_DC_Clamp             ((uint16_t) 0x191)
 #define PPSMC_MSG_SetFanPwmMax                ((uint16_t) 0x19A)
+#define PPSMC_MSG_SetFanRpmMax                ((uint16_t) 0x205)
 
 #define PPSMC_MSG_ENABLE_THERMAL_DPM          ((uint16_t) 0x19C)
 #define PPSMC_MSG_DISABLE_THERMAL_DPM         ((uint16_t) 0x19D)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index b556bd0a8797..1351c7e834a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -255,19 +255,6 @@ static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring,
 				   unsigned vm_id, bool ctx_switch)
 {
 	u32 vmid = vm_id & 0xf;
-	u32 next_rptr = ring->wptr + 5;
-
-	while ((next_rptr & 7) != 2)
-		next_rptr++;
-
-	next_rptr += 6;
-
-	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_WRITE) |
-			  SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_WRITE_LINEAR));
-	amdgpu_ring_write(ring, lower_32_bits(ring->next_rptr_gpu_addr) & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr));
-	amdgpu_ring_write(ring, SDMA_PKT_WRITE_UNTILED_DW_3_COUNT(1));
-	amdgpu_ring_write(ring, next_rptr);
 
 	/* IB packet must end on a 8 DW boundary */
 	sdma_v2_4_ring_insert_nop(ring, (10 - (ring->wptr & 7)) % 8);
@@ -406,7 +393,7 @@ static void sdma_v2_4_enable(struct amdgpu_device *adev, bool enable)
 	u32 f32_cntl;
 	int i;
 
-	if (enable == false) {
+	if (!enable) {
 		sdma_v2_4_gfx_stop(adev);
 		sdma_v2_4_rlc_stop(adev);
 	}
@@ -580,19 +567,21 @@ static int sdma_v2_4_start(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (!adev->firmware.smu_load) {
-		r = sdma_v2_4_load_microcode(adev);
-		if (r)
-			return r;
-	} else {
-		r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
-						AMDGPU_UCODE_ID_SDMA0);
-		if (r)
-			return -EINVAL;
-		r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
-						AMDGPU_UCODE_ID_SDMA1);
-		if (r)
-			return -EINVAL;
+	if (!adev->pp_enabled) {
+		if (!adev->firmware.smu_load) {
+			r = sdma_v2_4_load_microcode(adev);
+			if (r)
+				return r;
+		} else {
+			r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
+							AMDGPU_UCODE_ID_SDMA0);
+			if (r)
+				return -EINVAL;
+			r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
+							AMDGPU_UCODE_ID_SDMA1);
+			if (r)
+				return -EINVAL;
+		}
 	}
 
 	/* halt the engine before programing */
@@ -679,20 +668,19 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring)
  * Test a simple IB in the DMA ring (VI).
  * Returns 0 on success, error on failure.
  */
-static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring)
+static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib ib;
 	struct fence *f = NULL;
-	unsigned i;
 	unsigned index;
-	int r;
 	u32 tmp = 0;
 	u64 gpu_addr;
+	long r;
 
 	r = amdgpu_wb_get(adev, &index);
 	if (r) {
-		dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
+		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
 		return r;
 	}
 
@@ -702,7 +690,7 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring)
 	memset(&ib, 0, sizeof(ib));
 	r = amdgpu_ib_get(adev, NULL, 256, &ib);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get ib (%d).\n", r);
+		DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 		goto err0;
 	}
 
@@ -721,28 +709,25 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring)
 	if (r)
 		goto err1;
 
-	r = fence_wait(f, false);
-	if (r) {
-		DRM_ERROR("amdgpu: fence wait failed (%d).\n", r);
+	r = fence_wait_timeout(f, false, timeout);
+	if (r == 0) {
+		DRM_ERROR("amdgpu: IB test timed out\n");
+		r = -ETIMEDOUT;
 		goto err1;
-	}
-	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = le32_to_cpu(adev->wb.wb[index]);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-	if (i < adev->usec_timeout) {
-		DRM_INFO("ib test on ring %d succeeded in %u usecs\n",
-			 ring->idx, i);
+	} else if (r) {
+		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 		goto err1;
+	}
+	tmp = le32_to_cpu(adev->wb.wb[index]);
+	if (tmp == 0xDEADBEEF) {
+		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
 		r = -EINVAL;
 	}
 
 err1:
-	fence_put(f);
 	amdgpu_ib_free(adev, &ib, NULL);
 	fence_put(f);
 err0:
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 532ea88da66a..653ce5ed55ae 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -415,18 +415,6 @@ static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
 				   unsigned vm_id, bool ctx_switch)
 {
 	u32 vmid = vm_id & 0xf;
-	u32 next_rptr = ring->wptr + 5;
-
-	while ((next_rptr & 7) != 2)
-		next_rptr++;
-	next_rptr += 6;
-
-	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_WRITE) |
-			  SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_WRITE_LINEAR));
-	amdgpu_ring_write(ring, lower_32_bits(ring->next_rptr_gpu_addr) & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr));
-	amdgpu_ring_write(ring, SDMA_PKT_WRITE_UNTILED_DW_3_COUNT(1));
-	amdgpu_ring_write(ring, next_rptr);
 
 	/* IB packet must end on a 8 DW boundary */
 	sdma_v3_0_ring_insert_nop(ring, (10 - (ring->wptr & 7)) % 8);
@@ -616,7 +604,7 @@ static void sdma_v3_0_enable(struct amdgpu_device *adev, bool enable)
 	u32 f32_cntl;
 	int i;
 
-	if (enable == false) {
+	if (!enable) {
 		sdma_v3_0_gfx_stop(adev);
 		sdma_v3_0_rlc_stop(adev);
 	}
@@ -908,20 +896,19 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring)
  * Test a simple IB in the DMA ring (VI).
  * Returns 0 on success, error on failure.
  */
-static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring)
+static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib ib;
 	struct fence *f = NULL;
-	unsigned i;
 	unsigned index;
-	int r;
 	u32 tmp = 0;
 	u64 gpu_addr;
+	long r;
 
 	r = amdgpu_wb_get(adev, &index);
 	if (r) {
-		dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
+		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
 		return r;
 	}
 
@@ -931,7 +918,7 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring)
 	memset(&ib, 0, sizeof(ib));
 	r = amdgpu_ib_get(adev, NULL, 256, &ib);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get ib (%d).\n", r);
+		DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 		goto err0;
 	}
 
@@ -950,27 +937,24 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring)
 	if (r)
 		goto err1;
 
-	r = fence_wait(f, false);
-	if (r) {
-		DRM_ERROR("amdgpu: fence wait failed (%d).\n", r);
+	r = fence_wait_timeout(f, false, timeout);
+	if (r == 0) {
+		DRM_ERROR("amdgpu: IB test timed out\n");
+		r = -ETIMEDOUT;
 		goto err1;
-	}
-	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = le32_to_cpu(adev->wb.wb[index]);
-		if (tmp == 0xDEADBEEF)
-			break;
-		DRM_UDELAY(1);
-	}
-	if (i < adev->usec_timeout) {
-		DRM_INFO("ib test on ring %d succeeded in %u usecs\n",
-			 ring->idx, i);
+	} else if (r < 0) {
+		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 		goto err1;
+	}
+	tmp = le32_to_cpu(adev->wb.wb[index]);
+	if (tmp == 0xDEADBEEF) {
+		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+		r = 0;
 	} else {
 		DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
 		r = -EINVAL;
 	}
 err1:
-	fence_put(f);
 	amdgpu_ib_free(adev, &ib, NULL);
 	fence_put(f);
 err0:
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_smc.c b/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
index 083893dd68c0..940de1836f8f 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
@@ -173,7 +173,7 @@ static int tonga_send_msg_to_smc(struct amdgpu_device *adev, PPSMC_Msg msg)
 {
 	if (!tonga_is_smc_ram_running(adev))
 	{
-		return -EINVAL;;
+		return -EINVAL;
 	}
 
 	if (wait_smu_response(adev)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index f07551476a70..132e613ed674 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -34,6 +34,8 @@
 #include "oss/oss_2_0_d.h"
 #include "oss/oss_2_0_sh_mask.h"
 
+#include "bif/bif_4_1_d.h"
+
 static void uvd_v4_2_mc_resume(struct amdgpu_device *adev);
 static void uvd_v4_2_init_cg(struct amdgpu_device *adev);
 static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev);
@@ -439,6 +441,32 @@ static void uvd_v4_2_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq
 }
 
 /**
+ * uvd_v4_2_ring_emit_hdp_flush - emit an hdp flush
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Emits an hdp flush.
+ */
+static void uvd_v4_2_ring_emit_hdp_flush(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKET0(mmHDP_MEM_COHERENCY_FLUSH_CNTL, 0));
+	amdgpu_ring_write(ring, 0);
+}
+
+/**
+ * uvd_v4_2_ring_hdp_invalidate - emit an hdp invalidate
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Emits an hdp invalidate.
+ */
+static void uvd_v4_2_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKET0(mmHDP_DEBUG0, 0));
+	amdgpu_ring_write(ring, 1);
+}
+
+/**
  * uvd_v4_2_ring_test_ring - register write test
  *
  * @ring: amdgpu_ring pointer
@@ -499,49 +527,6 @@ static void uvd_v4_2_ring_emit_ib(struct amdgpu_ring *ring,
 }
 
 /**
- * uvd_v4_2_ring_test_ib - test ib execution
- *
- * @ring: amdgpu_ring pointer
- *
- * Test if we can successfully execute an IB
- */
-static int uvd_v4_2_ring_test_ib(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-	struct fence *fence = NULL;
-	int r;
-
-	r = amdgpu_asic_set_uvd_clocks(adev, 53300, 40000);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to raise UVD clocks (%d).\n", r);
-		return r;
-	}
-
-	r = amdgpu_uvd_get_create_msg(ring, 1, NULL);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to get create msg (%d).\n", r);
-		goto error;
-	}
-
-	r = amdgpu_uvd_get_destroy_msg(ring, 1, true, &fence);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to get destroy ib (%d).\n", r);
-		goto error;
-	}
-
-	r = fence_wait(fence, false);
-	if (r) {
-		DRM_ERROR("amdgpu: fence wait failed (%d).\n", r);
-		goto error;
-	}
-	DRM_INFO("ib test on ring %d succeeded\n",  ring->idx);
-error:
-	fence_put(fence);
-	amdgpu_asic_set_uvd_clocks(adev, 0, 0);
-	return r;
-}
-
-/**
  * uvd_v4_2_mc_resume - memory controller programming
  *
  * @adev: amdgpu_device pointer
@@ -763,10 +748,14 @@ static const struct amdgpu_ring_funcs uvd_v4_2_ring_funcs = {
 	.parse_cs = amdgpu_uvd_ring_parse_cs,
 	.emit_ib = uvd_v4_2_ring_emit_ib,
 	.emit_fence = uvd_v4_2_ring_emit_fence,
+	.emit_hdp_flush = uvd_v4_2_ring_emit_hdp_flush,
+	.emit_hdp_invalidate = uvd_v4_2_ring_emit_hdp_invalidate,
 	.test_ring = uvd_v4_2_ring_test_ring,
-	.test_ib = uvd_v4_2_ring_test_ib,
+	.test_ib = amdgpu_uvd_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_uvd_ring_begin_use,
+	.end_use = amdgpu_uvd_ring_end_use,
 };
 
 static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index e0a76a883d46..101de136ba63 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -31,6 +31,7 @@
 #include "uvd/uvd_5_0_sh_mask.h"
 #include "oss/oss_2_0_d.h"
 #include "oss/oss_2_0_sh_mask.h"
+#include "bif/bif_5_0_d.h"
 #include "vi.h"
 
 static void uvd_v5_0_set_ring_funcs(struct amdgpu_device *adev);
@@ -489,6 +490,32 @@ static void uvd_v5_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq
 }
 
 /**
+ * uvd_v5_0_ring_emit_hdp_flush - emit an hdp flush
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Emits an hdp flush.
+ */
+static void uvd_v5_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKET0(mmHDP_MEM_COHERENCY_FLUSH_CNTL, 0));
+	amdgpu_ring_write(ring, 0);
+}
+
+/**
+ * uvd_v5_0_ring_hdp_invalidate - emit an hdp invalidate
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Emits an hdp invalidate.
+ */
+static void uvd_v5_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKET0(mmHDP_DEBUG0, 0));
+	amdgpu_ring_write(ring, 1);
+}
+
+/**
  * uvd_v5_0_ring_test_ring - register write test
  *
  * @ring: amdgpu_ring pointer
@@ -550,49 +577,6 @@ static void uvd_v5_0_ring_emit_ib(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
-/**
- * uvd_v5_0_ring_test_ib - test ib execution
- *
- * @ring: amdgpu_ring pointer
- *
- * Test if we can successfully execute an IB
- */
-static int uvd_v5_0_ring_test_ib(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-	struct fence *fence = NULL;
-	int r;
-
-	r = amdgpu_asic_set_uvd_clocks(adev, 53300, 40000);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to raise UVD clocks (%d).\n", r);
-		return r;
-	}
-
-	r = amdgpu_uvd_get_create_msg(ring, 1, NULL);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to get create msg (%d).\n", r);
-		goto error;
-	}
-
-	r = amdgpu_uvd_get_destroy_msg(ring, 1, true, &fence);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to get destroy ib (%d).\n", r);
-		goto error;
-	}
-
-	r = fence_wait(fence, false);
-	if (r) {
-		DRM_ERROR("amdgpu: fence wait failed (%d).\n", r);
-		goto error;
-	}
-	DRM_INFO("ib test on ring %d succeeded\n",  ring->idx);
-error:
-	fence_put(fence);
-	amdgpu_asic_set_uvd_clocks(adev, 0, 0);
-	return r;
-}
-
 static bool uvd_v5_0_is_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -815,10 +799,14 @@ static const struct amdgpu_ring_funcs uvd_v5_0_ring_funcs = {
 	.parse_cs = amdgpu_uvd_ring_parse_cs,
 	.emit_ib = uvd_v5_0_ring_emit_ib,
 	.emit_fence = uvd_v5_0_ring_emit_fence,
+	.emit_hdp_flush = uvd_v5_0_ring_emit_hdp_flush,
+	.emit_hdp_invalidate = uvd_v5_0_ring_emit_hdp_invalidate,
 	.test_ring = uvd_v5_0_ring_test_ring,
-	.test_ib = uvd_v5_0_ring_test_ib,
+	.test_ib = amdgpu_uvd_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_uvd_ring_begin_use,
+	.end_use = amdgpu_uvd_ring_end_use,
 };
 
 static void uvd_v5_0_set_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index c9929d665c01..7f21102bfb99 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -33,6 +33,8 @@
 #include "oss/oss_2_0_sh_mask.h"
 #include "smu/smu_7_1_3_d.h"
 #include "smu/smu_7_1_3_sh_mask.h"
+#include "bif/bif_5_1_d.h"
+#include "gmc/gmc_8_1_d.h"
 #include "vi.h"
 
 static void uvd_v6_0_set_ring_funcs(struct amdgpu_device *adev);
@@ -385,8 +387,8 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
 	uint32_t mp_swap_cntl;
 	int i, j, r;
 
-	/*disable DPG */
-	WREG32_P(mmUVD_POWER_STATUS, 0, ~(1 << 2));
+	/* disable DPG */
+	WREG32_P(mmUVD_POWER_STATUS, 0, ~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
 
 	/* disable byte swapping */
 	lmi_swap_cntl = 0;
@@ -405,17 +407,21 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
 	}
 
 	/* disable interupt */
-	WREG32_P(mmUVD_MASTINT_EN, 0, ~(1 << 1));
+	WREG32_P(mmUVD_MASTINT_EN, 0, ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
 	/* stall UMC and register bus before resetting VCPU */
-	WREG32_P(mmUVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
+	WREG32_P(mmUVD_LMI_CTRL2, UVD_LMI_CTRL2__STALL_ARB_UMC_MASK, ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
 	mdelay(1);
 
 	/* put LMI, VCPU, RBC etc... into reset */
-	WREG32(mmUVD_SOFT_RESET, UVD_SOFT_RESET__LMI_SOFT_RESET_MASK |
-		UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK | UVD_SOFT_RESET__LBSI_SOFT_RESET_MASK |
-		UVD_SOFT_RESET__RBC_SOFT_RESET_MASK | UVD_SOFT_RESET__CSM_SOFT_RESET_MASK |
-		UVD_SOFT_RESET__CXW_SOFT_RESET_MASK | UVD_SOFT_RESET__TAP_SOFT_RESET_MASK |
+	WREG32(mmUVD_SOFT_RESET,
+		UVD_SOFT_RESET__LMI_SOFT_RESET_MASK |
+		UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK |
+		UVD_SOFT_RESET__LBSI_SOFT_RESET_MASK |
+		UVD_SOFT_RESET__RBC_SOFT_RESET_MASK |
+		UVD_SOFT_RESET__CSM_SOFT_RESET_MASK |
+		UVD_SOFT_RESET__CXW_SOFT_RESET_MASK |
+		UVD_SOFT_RESET__TAP_SOFT_RESET_MASK |
 		UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK);
 	mdelay(5);
 
@@ -424,8 +430,13 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
 	mdelay(5);
 
 	/* initialize UVD memory controller */
-	WREG32(mmUVD_LMI_CTRL, 0x40 | (1 << 8) | (1 << 13) |
-			     (1 << 21) | (1 << 9) | (1 << 20));
+	WREG32(mmUVD_LMI_CTRL,
+		(0x40 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
+		UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK |
+		UVD_LMI_CTRL__REQ_MODE_MASK |
+		UVD_LMI_CTRL__DISABLE_ON_FWV_FAIL_MASK);
 
 #ifdef __BIG_ENDIAN
 	/* swap (8 in 32) RB and IB */
@@ -447,10 +458,10 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
 	mdelay(5);
 
 	/* enable VCPU clock */
-	WREG32(mmUVD_VCPU_CNTL,  1 << 9);
+	WREG32(mmUVD_VCPU_CNTL, UVD_VCPU_CNTL__CLK_EN_MASK);
 
 	/* enable UMC */
-	WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8));
+	WREG32_P(mmUVD_LMI_CTRL2, 0, ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
 
 	/* boot up the VCPU */
 	WREG32(mmUVD_SOFT_RESET, 0);
@@ -484,10 +495,12 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
 		return r;
 	}
 	/* enable master interrupt */
-	WREG32_P(mmUVD_MASTINT_EN, 3 << 1, ~(3 << 1));
+	WREG32_P(mmUVD_MASTINT_EN,
+		(UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK),
+		~(UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK));
 
 	/* clear the bit 4 of UVD_STATUS */
-	WREG32_P(mmUVD_STATUS, 0, ~(2 << 1));
+	WREG32_P(mmUVD_STATUS, 0, ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
 	rb_bufsz = order_base_2(ring->ring_size);
 	tmp = 0;
@@ -581,6 +594,32 @@ static void uvd_v6_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq
 }
 
 /**
+ * uvd_v6_0_ring_emit_hdp_flush - emit an hdp flush
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Emits an hdp flush.
+ */
+static void uvd_v6_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKET0(mmHDP_MEM_COHERENCY_FLUSH_CNTL, 0));
+	amdgpu_ring_write(ring, 0);
+}
+
+/**
+ * uvd_v6_0_ring_hdp_invalidate - emit an hdp invalidate
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Emits an hdp invalidate.
+ */
+static void uvd_v6_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKET0(mmHDP_DEBUG0, 0));
+	amdgpu_ring_write(ring, 1);
+}
+
+/**
  * uvd_v6_0_ring_test_ring - register write test
  *
  * @ring: amdgpu_ring pointer
@@ -634,6 +673,9 @@ static void uvd_v6_0_ring_emit_ib(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib,
 				  unsigned vm_id, bool ctx_switch)
 {
+	amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_VMID, 0));
+	amdgpu_ring_write(ring, vm_id);
+
 	amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_64BIT_BAR_LOW, 0));
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
 	amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH, 0));
@@ -642,39 +684,55 @@ static void uvd_v6_0_ring_emit_ib(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, ib->length_dw);
 }
 
-/**
- * uvd_v6_0_ring_test_ib - test ib execution
- *
- * @ring: amdgpu_ring pointer
- *
- * Test if we can successfully execute an IB
- */
-static int uvd_v6_0_ring_test_ib(struct amdgpu_ring *ring)
+static void uvd_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
+					 unsigned vm_id, uint64_t pd_addr)
 {
-	struct fence *fence = NULL;
-	int r;
+	uint32_t reg;
 
-	r = amdgpu_uvd_get_create_msg(ring, 1, NULL);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to get create msg (%d).\n", r);
-		goto error;
-	}
+	if (vm_id < 8)
+		reg = mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id;
+	else
+		reg = mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vm_id - 8;
 
-	r = amdgpu_uvd_get_destroy_msg(ring, 1, true, &fence);
-	if (r) {
-		DRM_ERROR("amdgpu: failed to get destroy ib (%d).\n", r);
-		goto error;
-	}
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0));
+	amdgpu_ring_write(ring, reg << 2);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0));
+	amdgpu_ring_write(ring, pd_addr >> 12);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0));
+	amdgpu_ring_write(ring, 0x8);
 
-	r = fence_wait(fence, false);
-	if (r) {
-		DRM_ERROR("amdgpu: fence wait failed (%d).\n", r);
-		goto error;
-	}
-	DRM_INFO("ib test on ring %d succeeded\n",  ring->idx);
-error:
-	fence_put(fence);
-	return r;
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0));
+	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST << 2);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0));
+	amdgpu_ring_write(ring, 1 << vm_id);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0));
+	amdgpu_ring_write(ring, 0x8);
+
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0));
+	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST << 2);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0));
+	amdgpu_ring_write(ring, 0);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GP_SCRATCH8, 0));
+	amdgpu_ring_write(ring, 1 << vm_id); /* mask */
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0));
+	amdgpu_ring_write(ring, 0xC);
+}
+
+static void uvd_v6_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
+{
+	uint32_t seq = ring->fence_drv.sync_seq;
+	uint64_t addr = ring->fence_drv.gpu_addr;
+
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GP_SCRATCH8, 0));
+	amdgpu_ring_write(ring, 0xffffffff); /* mask */
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GP_SCRATCH9, 0));
+	amdgpu_ring_write(ring, seq);
+	amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0));
+	amdgpu_ring_write(ring, 0xE);
 }
 
 static bool uvd_v6_0_is_idle(void *handle)
@@ -847,7 +905,8 @@ static int uvd_v6_0_set_clockgating_state(void *handle,
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 	static int curstate = -1;
 
-	if (adev->asic_type == CHIP_FIJI)
+	if (adev->asic_type == CHIP_FIJI ||
+			adev->asic_type == CHIP_POLARIS10)
 		uvd_v6_set_bypass_mode(adev, enable);
 
 	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
@@ -912,22 +971,51 @@ const struct amd_ip_funcs uvd_v6_0_ip_funcs = {
 	.set_powergating_state = uvd_v6_0_set_powergating_state,
 };
 
-static const struct amdgpu_ring_funcs uvd_v6_0_ring_funcs = {
+static const struct amdgpu_ring_funcs uvd_v6_0_ring_phys_funcs = {
 	.get_rptr = uvd_v6_0_ring_get_rptr,
 	.get_wptr = uvd_v6_0_ring_get_wptr,
 	.set_wptr = uvd_v6_0_ring_set_wptr,
 	.parse_cs = amdgpu_uvd_ring_parse_cs,
 	.emit_ib = uvd_v6_0_ring_emit_ib,
 	.emit_fence = uvd_v6_0_ring_emit_fence,
+	.emit_hdp_flush = uvd_v6_0_ring_emit_hdp_flush,
+	.emit_hdp_invalidate = uvd_v6_0_ring_emit_hdp_invalidate,
+	.test_ring = uvd_v6_0_ring_test_ring,
+	.test_ib = amdgpu_uvd_ring_test_ib,
+	.insert_nop = amdgpu_ring_insert_nop,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_uvd_ring_begin_use,
+	.end_use = amdgpu_uvd_ring_end_use,
+};
+
+static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = {
+	.get_rptr = uvd_v6_0_ring_get_rptr,
+	.get_wptr = uvd_v6_0_ring_get_wptr,
+	.set_wptr = uvd_v6_0_ring_set_wptr,
+	.parse_cs = NULL,
+	.emit_ib = uvd_v6_0_ring_emit_ib,
+	.emit_fence = uvd_v6_0_ring_emit_fence,
+	.emit_vm_flush = uvd_v6_0_ring_emit_vm_flush,
+	.emit_pipeline_sync = uvd_v6_0_ring_emit_pipeline_sync,
+	.emit_hdp_flush = uvd_v6_0_ring_emit_hdp_flush,
+	.emit_hdp_invalidate = uvd_v6_0_ring_emit_hdp_invalidate,
 	.test_ring = uvd_v6_0_ring_test_ring,
-	.test_ib = uvd_v6_0_ring_test_ib,
+	.test_ib = amdgpu_uvd_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_uvd_ring_begin_use,
+	.end_use = amdgpu_uvd_ring_end_use,
 };
 
 static void uvd_v6_0_set_ring_funcs(struct amdgpu_device *adev)
 {
-	adev->uvd.ring.funcs = &uvd_v6_0_ring_funcs;
+	if (adev->asic_type >= CHIP_POLARIS10) {
+		adev->uvd.ring.funcs = &uvd_v6_0_ring_vm_funcs;
+		DRM_INFO("UVD is enabled in VM mode\n");
+	} else {
+		adev->uvd.ring.funcs = &uvd_v6_0_ring_phys_funcs;
+		DRM_INFO("UVD is enabled in physical mode\n");
+	}
 }
 
 static const struct amdgpu_irq_src_funcs uvd_v6_0_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 45d92aceb485..80a37a602181 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -594,6 +594,8 @@ static const struct amdgpu_ring_funcs vce_v2_0_ring_funcs = {
 	.test_ib = amdgpu_vce_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_vce_ring_begin_use,
+	.end_use = amdgpu_vce_ring_end_use,
 };
 
 static void vce_v2_0_set_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 30e8099e94c5..c271abffd8dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -43,6 +43,7 @@
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0	0x8616
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1	0x8617
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2	0x8618
+#define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK	0x02
 
 #define VCE_V3_0_FW_SIZE	(384 * 1024)
 #define VCE_V3_0_STACK_SIZE	(64 * 1024)
@@ -51,6 +52,7 @@
 static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx);
 static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev);
 static void vce_v3_0_set_irq_funcs(struct amdgpu_device *adev);
+static int vce_v3_0_wait_for_idle(void *handle);
 
 /**
  * vce_v3_0_ring_get_rptr - get read pointer
@@ -205,6 +207,32 @@ static void vce_v3_0_set_vce_sw_clock_gating(struct amdgpu_device *adev,
 	vce_v3_0_override_vce_clock_gating(adev, false);
 }
 
+static int vce_v3_0_firmware_loaded(struct amdgpu_device *adev)
+{
+	int i, j;
+
+	for (i = 0; i < 10; ++i) {
+		for (j = 0; j < 100; ++j) {
+			uint32_t status = RREG32(mmVCE_STATUS);
+
+			if (status & VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK)
+				return 0;
+			mdelay(10);
+		}
+
+		DRM_ERROR("VCE not responding, trying to reset the ECPU!!!\n");
+		WREG32_P(mmVCE_SOFT_RESET,
+			VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK,
+			~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK);
+		mdelay(10);
+		WREG32_P(mmVCE_SOFT_RESET, 0,
+			~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK);
+		mdelay(10);
+	}
+
+	return -ETIMEDOUT;
+}
+
 /**
  * vce_v3_0_start - start VCE block
  *
@@ -215,11 +243,24 @@ static void vce_v3_0_set_vce_sw_clock_gating(struct amdgpu_device *adev,
 static int vce_v3_0_start(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	int idx, i, j, r;
+	int idx, r;
+
+	ring = &adev->vce.ring[0];
+	WREG32(mmVCE_RB_RPTR, ring->wptr);
+	WREG32(mmVCE_RB_WPTR, ring->wptr);
+	WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr);
+	WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32(mmVCE_RB_SIZE, ring->ring_size / 4);
+
+	ring = &adev->vce.ring[1];
+	WREG32(mmVCE_RB_RPTR2, ring->wptr);
+	WREG32(mmVCE_RB_WPTR2, ring->wptr);
+	WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr);
+	WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+	WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4);
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (idx = 0; idx < 2; ++idx) {
-
 		if (adev->vce.harvest_config & (1 << idx))
 			continue;
 
@@ -233,48 +274,24 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 
 		vce_v3_0_mc_resume(adev, idx);
 
-		/* set BUSY flag */
-		WREG32_P(mmVCE_STATUS, 1, ~1);
+		WREG32_P(mmVCE_STATUS, VCE_STATUS__JOB_BUSY_MASK,
+		         ~VCE_STATUS__JOB_BUSY_MASK);
+
 		if (adev->asic_type >= CHIP_STONEY)
 			WREG32_P(mmVCE_VCPU_CNTL, 1, ~0x200001);
 		else
 			WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK,
 				~VCE_VCPU_CNTL__CLK_EN_MASK);
 
-		WREG32_P(mmVCE_SOFT_RESET,
-			 VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK,
-			 ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK);
-
-		mdelay(100);
-
 		WREG32_P(mmVCE_SOFT_RESET, 0,
 			~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK);
 
-		for (i = 0; i < 10; ++i) {
-			uint32_t status;
-			for (j = 0; j < 100; ++j) {
-				status = RREG32(mmVCE_STATUS);
-				if (status & 2)
-					break;
-				mdelay(10);
-			}
-			r = 0;
-			if (status & 2)
-				break;
-
-			DRM_ERROR("VCE not responding, trying to reset the ECPU!!!\n");
-			WREG32_P(mmVCE_SOFT_RESET,
-				VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK,
-				~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK);
-			mdelay(10);
-			WREG32_P(mmVCE_SOFT_RESET, 0,
-				~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK);
-			mdelay(10);
-			r = -1;
-		}
+		mdelay(100);
+
+		r = vce_v3_0_firmware_loaded(adev);
 
 		/* clear BUSY flag */
-		WREG32_P(mmVCE_STATUS, 0, ~1);
+		WREG32_P(mmVCE_STATUS, 0, ~VCE_STATUS__JOB_BUSY_MASK);
 
 		/* Set Clock-Gating off */
 		if (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)
@@ -290,19 +307,46 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 	WREG32_P(mmGRBM_GFX_INDEX, 0, ~GRBM_GFX_INDEX__VCE_INSTANCE_MASK);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
-	ring = &adev->vce.ring[0];
-	WREG32(mmVCE_RB_RPTR, ring->wptr);
-	WREG32(mmVCE_RB_WPTR, ring->wptr);
-	WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr);
-	WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-	WREG32(mmVCE_RB_SIZE, ring->ring_size / 4);
+	return 0;
+}
 
-	ring = &adev->vce.ring[1];
-	WREG32(mmVCE_RB_RPTR2, ring->wptr);
-	WREG32(mmVCE_RB_WPTR2, ring->wptr);
-	WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr);
-	WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
-	WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4);
+static int vce_v3_0_stop(struct amdgpu_device *adev)
+{
+	int idx;
+
+	mutex_lock(&adev->grbm_idx_mutex);
+	for (idx = 0; idx < 2; ++idx) {
+		if (adev->vce.harvest_config & (1 << idx))
+			continue;
+
+		if (idx == 0)
+			WREG32_P(mmGRBM_GFX_INDEX, 0,
+				~GRBM_GFX_INDEX__VCE_INSTANCE_MASK);
+		else
+			WREG32_P(mmGRBM_GFX_INDEX,
+				GRBM_GFX_INDEX__VCE_INSTANCE_MASK,
+				~GRBM_GFX_INDEX__VCE_INSTANCE_MASK);
+
+		if (adev->asic_type >= CHIP_STONEY)
+			WREG32_P(mmVCE_VCPU_CNTL, 0, ~0x200001);
+		else
+			WREG32_P(mmVCE_VCPU_CNTL, 0,
+				~VCE_VCPU_CNTL__CLK_EN_MASK);
+		/* hold on ECPU */
+		WREG32_P(mmVCE_SOFT_RESET,
+			 VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK,
+			 ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK);
+
+		/* clear BUSY flag */
+		WREG32_P(mmVCE_STATUS, 0, ~VCE_STATUS__JOB_BUSY_MASK);
+
+		/* Set Clock-Gating off */
+		if (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)
+			vce_v3_0_set_vce_sw_clock_gating(adev, false);
+	}
+
+	WREG32_P(mmGRBM_GFX_INDEX, 0, ~GRBM_GFX_INDEX__VCE_INSTANCE_MASK);
+	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
 }
@@ -441,7 +485,14 @@ static int vce_v3_0_hw_init(void *handle)
 
 static int vce_v3_0_hw_fini(void *handle)
 {
-	return 0;
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = vce_v3_0_wait_for_idle(handle);
+	if (r)
+		return r;
+
+	return vce_v3_0_stop(adev);
 }
 
 static int vce_v3_0_suspend(void *handle)
@@ -604,6 +655,18 @@ static int vce_v3_0_process_interrupt(struct amdgpu_device *adev,
 	return 0;
 }
 
+static void vce_v3_set_bypass_mode(struct amdgpu_device *adev, bool enable)
+{
+	u32 tmp = RREG32_SMC(ixGCK_DFS_BYPASS_CNTL);
+
+	if (enable)
+		tmp |= GCK_DFS_BYPASS_CNTL__BYPASSECLK_MASK;
+	else
+		tmp &= ~GCK_DFS_BYPASS_CNTL__BYPASSECLK_MASK;
+
+	WREG32_SMC(ixGCK_DFS_BYPASS_CNTL, tmp);
+}
+
 static int vce_v3_0_set_clockgating_state(void *handle,
 					  enum amd_clockgating_state state)
 {
@@ -611,6 +674,9 @@ static int vce_v3_0_set_clockgating_state(void *handle,
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 	int i;
 
+	if (adev->asic_type == CHIP_POLARIS10)
+		vce_v3_set_bypass_mode(adev, enable);
+
 	if (!(adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG))
 		return 0;
 
@@ -701,6 +767,8 @@ static const struct amdgpu_ring_funcs vce_v3_0_ring_funcs = {
 	.test_ib = amdgpu_vce_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_vce_ring_begin_use,
+	.end_use = amdgpu_vce_ring_end_use,
 };
 
 static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index a65c96029476..03a31c53aec3 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -203,6 +203,29 @@ static void vi_didt_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 	spin_unlock_irqrestore(&adev->didt_idx_lock, flags);
 }
 
+static u32 vi_gc_cac_rreg(struct amdgpu_device *adev, u32 reg)
+{
+	unsigned long flags;
+	u32 r;
+
+	spin_lock_irqsave(&adev->gc_cac_idx_lock, flags);
+	WREG32(mmGC_CAC_IND_INDEX, (reg));
+	r = RREG32(mmGC_CAC_IND_DATA);
+	spin_unlock_irqrestore(&adev->gc_cac_idx_lock, flags);
+	return r;
+}
+
+static void vi_gc_cac_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&adev->gc_cac_idx_lock, flags);
+	WREG32(mmGC_CAC_IND_INDEX, (reg));
+	WREG32(mmGC_CAC_IND_DATA, (v));
+	spin_unlock_irqrestore(&adev->gc_cac_idx_lock, flags);
+}
+
+
 static const u32 tonga_mgcg_cgcg_init[] =
 {
 	mmCGTT_DRM_CLK_CTRL0, 0xffffffff, 0x00600100,
@@ -533,12 +556,12 @@ static uint32_t vi_read_indexed_register(struct amdgpu_device *adev, u32 se_num,
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	if (se_num != 0xffffffff || sh_num != 0xffffffff)
-		gfx_v8_0_select_se_sh(adev, se_num, sh_num);
+		amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff);
 
 	val = RREG32(reg_offset);
 
 	if (se_num != 0xffffffff || sh_num != 0xffffffff)
-		gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff);
+		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
 	mutex_unlock(&adev->grbm_idx_mutex);
 	return val;
 }
@@ -597,7 +620,7 @@ static int vi_read_register(struct amdgpu_device *adev, u32 se_num,
 	return -EINVAL;
 }
 
-static void vi_gpu_pci_config_reset(struct amdgpu_device *adev)
+static int vi_gpu_pci_config_reset(struct amdgpu_device *adev)
 {
 	u32 i;
 
@@ -612,11 +635,14 @@ static void vi_gpu_pci_config_reset(struct amdgpu_device *adev)
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
-		if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff)
-			break;
+		if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff) {
+			/* enable BM */
+			pci_set_master(adev->pdev);
+			return 0;
+		}
 		udelay(1);
 	}
-
+	return -EINVAL;
 }
 
 static void vi_set_bios_scratch_engine_hung(struct amdgpu_device *adev, bool hung)
@@ -642,13 +668,15 @@ static void vi_set_bios_scratch_engine_hung(struct amdgpu_device *adev, bool hun
  */
 static int vi_asic_reset(struct amdgpu_device *adev)
 {
+	int r;
+
 	vi_set_bios_scratch_engine_hung(adev, true);
 
-	vi_gpu_pci_config_reset(adev);
+	r = vi_gpu_pci_config_reset(adev);
 
 	vi_set_bios_scratch_engine_hung(adev, false);
 
-	return 0;
+	return r;
 }
 
 static int vi_set_uvd_clock(struct amdgpu_device *adev, u32 clock,
@@ -1133,9 +1161,6 @@ static const struct amdgpu_asic_funcs vi_asic_funcs =
 	.set_uvd_clocks = &vi_set_uvd_clocks,
 	.set_vce_clocks = &vi_set_vce_clocks,
 	.get_virtual_caps = &vi_get_virtual_caps,
-	/* these should be moved to their own ip modules */
-	.get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter,
-	.wait_for_mc_idle = &gmc_v8_0_mc_wait_for_idle,
 };
 
 static int vi_common_early_init(void *handle)
@@ -1156,6 +1181,8 @@ static int vi_common_early_init(void *handle)
 	adev->uvd_ctx_wreg = &vi_uvd_ctx_wreg;
 	adev->didt_rreg = &vi_didt_rreg;
 	adev->didt_wreg = &vi_didt_wreg;
+	adev->gc_cac_rreg = &vi_gc_cac_rreg;
+	adev->gc_cac_wreg = &vi_gc_cac_wreg;
 
 	adev->asic_funcs = &vi_asic_funcs;
 
@@ -1229,12 +1256,18 @@ static int vi_common_early_init(void *handle)
 		adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG |
 			AMD_CG_SUPPORT_GFX_MGCG |
 			AMD_CG_SUPPORT_GFX_MGLS |
+			AMD_CG_SUPPORT_GFX_RLC_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
 			AMD_CG_SUPPORT_BIF_LS |
 			AMD_CG_SUPPORT_HDP_MGCG |
 			AMD_CG_SUPPORT_HDP_LS |
 			AMD_CG_SUPPORT_SDMA_MGCG |
 			AMD_CG_SUPPORT_SDMA_LS;
-		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index ec4036a09f3e..a625b9137da2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -187,12 +187,12 @@ int init_pipelines(struct device_queue_manager *dqm,
 unsigned int get_first_pipe(struct device_queue_manager *dqm);
 unsigned int get_pipes_num(struct device_queue_manager *dqm);
 
-extern inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd)
+static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd)
 {
 	return (pdd->lds_base >> 16) & 0xFF;
 }
 
-extern inline unsigned int
+static inline unsigned int
 get_sh_mem_bases_nybble_64(struct kfd_process_device *pdd)
 {
 	return (pdd->lds_base >> 60) & 0x0E;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d0d5f4baf72d..80113c335966 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -617,10 +617,7 @@ int kgd2kfd_resume(struct kfd_dev *kfd);
 int kfd_init_apertures(struct kfd_process *process);
 
 /* Queue Context Management */
-inline uint32_t lower_32(uint64_t x);
-inline uint32_t upper_32(uint64_t x);
 struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd);
-inline uint32_t get_sdma_base_addr(struct cik_sdma_rlc_registers *m);
 
 int init_queue(struct queue **q, struct queue_properties properties);
 void uninit_queue(struct queue *q);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 7708d90b9da9..4f3849ac8c07 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -63,13 +63,12 @@ static struct kfd_process *create_process(const struct task_struct *thread);
 void kfd_process_create_wq(void)
 {
 	if (!kfd_process_wq)
-		kfd_process_wq = create_workqueue("kfd_process_wq");
+		kfd_process_wq = alloc_workqueue("kfd_process_wq", 0, 0);
 }
 
 void kfd_process_destroy_wq(void)
 {
 	if (kfd_process_wq) {
-		flush_workqueue(kfd_process_wq);
 		destroy_workqueue(kfd_process_wq);
 		kfd_process_wq = NULL;
 	}
@@ -330,6 +329,7 @@ err_process_pqm_init:
 	synchronize_rcu();
 	mmu_notifier_unregister_no_release(&process->mmu_notifier, process->mm);
 err_mmu_notifier:
+	mutex_destroy(&process->mutex);
 	kfd_pasid_free(process->pasid);
 err_alloc_pasid:
 	kfree(process->queues);
diff --git a/drivers/gpu/drm/amd/include/amd_pcie.h b/drivers/gpu/drm/amd/include/amd_pcie.h
index 7c2a916c1e63..5eb895fd98bf 100644
--- a/drivers/gpu/drm/amd/include/amd_pcie.h
+++ b/drivers/gpu/drm/amd/include/amd_pcie.h
@@ -37,6 +37,13 @@
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_MASK   0x0000FFFF
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_SHIFT  0
 
+/* gen: chipset 1/2, asic 1/2/3 */
+#define AMDGPU_DEFAULT_PCIE_GEN_MASK (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 \
+				      | CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 \
+				      | CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 \
+				      | CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 \
+				      | CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3)
+
 /* Following flags shows PCIe lane width switch supported in driver which are decided by chipset and ASIC */
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X1          0x00010000
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X2          0x00020000
@@ -47,4 +54,11 @@
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X32         0x00400000
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_SHIFT       16
 
+/* 1/2/4/8/16 lanes */
+#define AMDGPU_DEFAULT_PCIE_MLW_MASK (CAIL_PCIE_LINK_WIDTH_SUPPORT_X1 \
+				      | CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 \
+				      | CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 \
+				      | CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 \
+				      | CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
+
 #endif
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index afce1edbe250..a74a0d2ff1ca 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -26,15 +26,6 @@
 #define AMD_MAX_USEC_TIMEOUT		100000  /* 100 ms */
 
 /*
-* Supported GPU families (aligned with amdgpu_drm.h)
-*/
-#define AMD_FAMILY_UNKNOWN              0
-#define AMD_FAMILY_CI                   120 /* Bonaire, Hawaii */
-#define AMD_FAMILY_KV                   125 /* Kaveri, Kabini, Mullins */
-#define AMD_FAMILY_VI                   130 /* Iceland, Tonga */
-#define AMD_FAMILY_CZ                   135 /* Carrizo */
-
-/*
  * Supported ASIC types
  */
 enum amd_asic_type {
@@ -120,6 +111,8 @@ enum amd_powergating_state {
 #define AMD_PG_SUPPORT_SDMA			(1 << 8)
 #define AMD_PG_SUPPORT_ACP			(1 << 9)
 #define AMD_PG_SUPPORT_SAMU			(1 << 10)
+#define AMD_PG_SUPPORT_GFX_QUICK_MG		(1 << 11)
+#define AMD_PG_SUPPORT_GFX_PIPELINE		(1 << 12)
 
 enum amd_pm_state_type {
 	/* not used for dpm */
diff --git a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h
index 293329719bba..809759f7bb81 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h
@@ -27,6 +27,7 @@
 #define mmMM_INDEX                                                              0x0
 #define mmMM_INDEX_HI                                                           0x6
 #define mmMM_DATA                                                               0x1
+#define mmCC_BIF_BX_STRAP2							0x152A
 #define mmBIF_MM_INDACCESS_CNTL                                                 0x1500
 #define mmBIF_DOORBELL_APER_EN                                                  0x1501
 #define mmBUS_CNTL                                                              0x1508
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_d.h
index ebaf67bb1589..90ff7c8a6011 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_d.h
@@ -2823,4 +2823,7 @@
 #define mmDC_EDC_CSINVOC_CNT                                                    0x3192
 #define mmDC_EDC_RESTORE_CNT                                                    0x3193
 
+#define mmGC_CAC_IND_INDEX                                                      0x129a
+#define mmGC_CAC_IND_DATA                                                       0x129b
+
 #endif /* GFX_8_0_D_H */
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_sh_mask.h
index 7d722458d9f5..4070ca3a68eb 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_sh_mask.h
@@ -8730,8 +8730,6 @@
 #define RLC_GPM_STAT__DYN_CU_POWERING_DOWN__SHIFT 0x10
 #define RLC_GPM_STAT__ABORTED_PD_SEQUENCE_MASK 0x20000
 #define RLC_GPM_STAT__ABORTED_PD_SEQUENCE__SHIFT 0x11
-#define RLC_GPM_STAT__RESERVED_MASK 0xfc0000
-#define RLC_GPM_STAT__RESERVED__SHIFT 0x12
 #define RLC_GPM_STAT__PG_ERROR_STATUS_MASK 0xff000000
 #define RLC_GPM_STAT__PG_ERROR_STATUS__SHIFT 0x18
 #define RLC_GPU_CLOCK_32_RES_SEL__RES_SEL_MASK 0x3f
@@ -8764,8 +8762,10 @@
 #define RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE__SHIFT 0x12
 #define RLC_PG_CNTL__SMU_HANDSHAKE_ENABLE_MASK 0x80000
 #define RLC_PG_CNTL__SMU_HANDSHAKE_ENABLE__SHIFT 0x13
-#define RLC_PG_CNTL__RESERVED1_MASK 0xf00000
-#define RLC_PG_CNTL__RESERVED1__SHIFT 0x14
+#define RLC_PG_CNTL__QUICK_PG_ENABLE_MASK 0x100000
+#define RLC_PG_CNTL__QUICK_PG_ENABLE__SHIFT 0x14
+#define RLC_PG_CNTL__RESERVED1_MASK 0xe00000
+#define RLC_PG_CNTL__RESERVED1__SHIFT 0x15
 #define RLC_GPM_THREAD_PRIORITY__THREAD0_PRIORITY_MASK 0xff
 #define RLC_GPM_THREAD_PRIORITY__THREAD0_PRIORITY__SHIFT 0x0
 #define RLC_GPM_THREAD_PRIORITY__THREAD1_PRIORITY_MASK 0xff00
@@ -9102,8 +9102,6 @@
 #define RLC_GPM_LOG_CONT__CONT__SHIFT 0x0
 #define RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK 0xff
 #define RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG__SHIFT 0x0
-#define RLC_PG_DELAY_3__RESERVED_MASK 0xffffff00
-#define RLC_PG_DELAY_3__RESERVED__SHIFT 0x8
 #define RLC_GPM_INT_DISABLE_TH0__DISABLE_MASK 0xffffffff
 #define RLC_GPM_INT_DISABLE_TH0__DISABLE__SHIFT 0x0
 #define RLC_GPM_INT_DISABLE_TH1__DISABLE_MASK 0xffffffff
@@ -9124,14 +9122,8 @@
 #define RLC_SRM_DEBUG_SELECT__RESERVED__SHIFT 0x8
 #define RLC_SRM_DEBUG__DATA_MASK 0xffffffff
 #define RLC_SRM_DEBUG__DATA__SHIFT 0x0
-#define RLC_SRM_ARAM_ADDR__ADDR_MASK 0x3ff
-#define RLC_SRM_ARAM_ADDR__ADDR__SHIFT 0x0
-#define RLC_SRM_ARAM_ADDR__RESERVED_MASK 0xfffffc00
-#define RLC_SRM_ARAM_ADDR__RESERVED__SHIFT 0xa
 #define RLC_SRM_ARAM_DATA__DATA_MASK 0xffffffff
 #define RLC_SRM_ARAM_DATA__DATA__SHIFT 0x0
-#define RLC_SRM_DRAM_ADDR__ADDR_MASK 0x3ff
-#define RLC_SRM_DRAM_ADDR__ADDR__SHIFT 0x0
 #define RLC_SRM_DRAM_ADDR__RESERVED_MASK 0xfffffc00
 #define RLC_SRM_DRAM_ADDR__RESERVED__SHIFT 0xa
 #define RLC_SRM_DRAM_DATA__DATA_MASK 0xffffffff
@@ -17946,8 +17938,6 @@
 #define VGT_TESS_DISTRIBUTION__ACCUM_TRI__SHIFT 0x8
 #define VGT_TESS_DISTRIBUTION__ACCUM_QUAD_MASK 0xff0000
 #define VGT_TESS_DISTRIBUTION__ACCUM_QUAD__SHIFT 0x10
-#define VGT_TESS_DISTRIBUTION__DONUT_SPLIT_MASK 0xff000000
-#define VGT_TESS_DISTRIBUTION__DONUT_SPLIT__SHIFT 0x18
 #define VGT_TF_RING_SIZE__SIZE_MASK 0xffff
 #define VGT_TF_RING_SIZE__SIZE__SHIFT 0x0
 #define VGT_SYS_CONFIG__DUAL_CORE_EN_MASK 0x1
@@ -20502,8 +20492,6 @@
 #define DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT 0x4
 #define DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK 0x20
 #define DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT 0x5
-#define DIDT_SQ_CTRL0__UNUSED_0_MASK 0xffffffc0
-#define DIDT_SQ_CTRL0__UNUSED_0__SHIFT 0x6
 #define DIDT_SQ_CTRL1__MIN_POWER_MASK 0xffff
 #define DIDT_SQ_CTRL1__MIN_POWER__SHIFT 0x0
 #define DIDT_SQ_CTRL1__MAX_POWER_MASK 0xffff0000
@@ -20558,8 +20546,6 @@
 #define DIDT_DB_CTRL0__DIDT_CTRL_RST__SHIFT 0x4
 #define DIDT_DB_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK 0x20
 #define DIDT_DB_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT 0x5
-#define DIDT_DB_CTRL0__UNUSED_0_MASK 0xffffffc0
-#define DIDT_DB_CTRL0__UNUSED_0__SHIFT 0x6
 #define DIDT_DB_CTRL1__MIN_POWER_MASK 0xffff
 #define DIDT_DB_CTRL1__MIN_POWER__SHIFT 0x0
 #define DIDT_DB_CTRL1__MAX_POWER_MASK 0xffff0000
@@ -20614,8 +20600,6 @@
 #define DIDT_TD_CTRL0__DIDT_CTRL_RST__SHIFT 0x4
 #define DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK 0x20
 #define DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT 0x5
-#define DIDT_TD_CTRL0__UNUSED_0_MASK 0xffffffc0
-#define DIDT_TD_CTRL0__UNUSED_0__SHIFT 0x6
 #define DIDT_TD_CTRL1__MIN_POWER_MASK 0xffff
 #define DIDT_TD_CTRL1__MIN_POWER__SHIFT 0x0
 #define DIDT_TD_CTRL1__MAX_POWER_MASK 0xffff0000
@@ -20670,8 +20654,6 @@
 #define DIDT_TCP_CTRL0__DIDT_CTRL_RST__SHIFT 0x4
 #define DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK 0x20
 #define DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT 0x5
-#define DIDT_TCP_CTRL0__UNUSED_0_MASK 0xffffffc0
-#define DIDT_TCP_CTRL0__UNUSED_0__SHIFT 0x6
 #define DIDT_TCP_CTRL1__MIN_POWER_MASK 0xffff
 #define DIDT_TCP_CTRL1__MIN_POWER__SHIFT 0x0
 #define DIDT_TCP_CTRL1__MAX_POWER_MASK 0xffff0000
@@ -20726,8 +20708,6 @@
 #define DIDT_DBR_CTRL0__DIDT_CTRL_RST__SHIFT 0x4
 #define DIDT_DBR_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK 0x20
 #define DIDT_DBR_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT 0x5
-#define DIDT_DBR_CTRL0__UNUSED_0_MASK 0xffffffc0
-#define DIDT_DBR_CTRL0__UNUSED_0__SHIFT 0x6
 #define DIDT_DBR_CTRL1__MIN_POWER_MASK 0xffff
 #define DIDT_DBR_CTRL1__MIN_POWER__SHIFT 0x0
 #define DIDT_DBR_CTRL1__MAX_POWER_MASK 0xffff0000
@@ -20773,4 +20753,84 @@
 #define DIDT_DBR_WEIGHT8_11__WEIGHT11_MASK 0xff000000
 #define DIDT_DBR_WEIGHT8_11__WEIGHT11__SHIFT 0x18
 
+#define DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK    0x00000001
+#define DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT  0x00000000
+
+#define DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK       0x0000007e
+#define DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK       0x00001f80L
+#define DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT     0x00000001
+#define DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT     0x00000007
+
+#define DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK   0x1fffe000L
+#define DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT 0x0000000d
+
+#define DIDT_SQ_STALL_CTRL__UNUSED_0_MASK                  0xe0000000L
+#define DIDT_SQ_STALL_CTRL__UNUSED_0__SHIFT                0x0000001d
+
+#define DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK       0x00000001L
+#define DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT     0x00000000
+
+#define DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK       0x00007ffeL
+#define DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT     0x00000001
+#define DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK       0x1fff8000L
+#define DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT     0x0000000f
+
+#define DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK    0x00000001L
+#define DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT  0x00000000
+
+#define DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK       0x0000007eL
+#define DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK       0x00001f80L
+#define DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT     0x00000001
+#define DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT     0x00000007
+
+#define DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK   0x1fffe000L
+#define DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT 0x0000000d
+
+#define DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK     0x00000fc0L
+#define DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK     0x0003f000L
+#define DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT   0x00000006
+#define DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT   0x0000000c
+
+#define DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK       0x00000001L
+#define DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK       0x00007ffeL
+#define DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK       0x1fff8000L
+
+#define DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT     0x00000000
+#define DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT     0x00000001
+#define DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT     0x0000000f
+
+#define DIDT_TD_STALL_CTRL__UNUSED_0_MASK                  0xe0000000L
+#define DIDT_TD_STALL_CTRL__UNUSED_0__SHIFT                0x0000001d
+
+#define DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK     0x00000fc0L
+#define DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK     0x0003f000L
+#define DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT   0x00000006
+#define DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT   0x0000000c
+
+#define DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK   0x00000001L
+#define DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT 0x00000000
+
+#define DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK      0x0000007eL
+#define DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK      0x00001f80L
+#define DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT    0x00000001
+#define DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT    0x00000007
+
+#define DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK  0x1fffe000L
+#define DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT 0x0000000d
+
+#define DIDT_TCP_STALL_CTRL__UNUSED_0_MASK                 0xe0000000L
+#define DIDT_TCP_STALL_CTRL__UNUSED_0__SHIFT               0x0000001d
+
+#define DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK      0x00000001L
+#define DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK      0x00007ffeL
+#define DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK      0x1fff8000L
+#define DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT    0x00000000
+#define DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT    0x00000001
+#define DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT    0x0000000f
+
+#define DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK    0x00000fc0L
+#define DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK    0x0003f000L
+#define DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT  0x00000006
+#define DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT  0x0000000c
+
 #endif /* GFX_8_0_SH_MASK_H */
diff --git a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_6_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_6_0_d.h
index 6f6fb34742d2..ec69869c55ff 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_6_0_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_6_0_d.h
@@ -111,6 +111,8 @@
 #define mmUVD_MIF_RECON1_ADDR_CONFIG                                            0x39c5
 #define ixUVD_MIF_SCLR_ADDR_CONFIG                                              0x4
 #define mmUVD_JPEG_ADDR_CONFIG                                                  0x3a1f
+#define mmUVD_GP_SCRATCH8                                                       0x3c0a
+#define mmUVD_GP_SCRATCH9                                                       0x3c0b
 #define mmUVD_GP_SCRATCH4                                                       0x3d38
 
 #endif /* UVD_6_0_D_H */
diff --git a/drivers/gpu/drm/amd/include/cgs_common.h b/drivers/gpu/drm/amd/include/cgs_common.h
index 7464daf89ca1..b86aba9d019f 100644
--- a/drivers/gpu/drm/amd/include/cgs_common.h
+++ b/drivers/gpu/drm/amd/include/cgs_common.h
@@ -49,6 +49,7 @@ enum cgs_ind_reg {
 	CGS_IND_REG__SMC,
 	CGS_IND_REG__UVD_CTX,
 	CGS_IND_REG__DIDT,
+	CGS_IND_REG_GC_CAC,
 	CGS_IND_REG__AUDIO_ENDPT
 };
 
@@ -112,20 +113,23 @@ enum cgs_system_info_id {
 	CGS_SYSTEM_INFO_ADAPTER_BDF_ID = 1,
 	CGS_SYSTEM_INFO_PCIE_GEN_INFO,
 	CGS_SYSTEM_INFO_PCIE_MLW,
+	CGS_SYSTEM_INFO_PCIE_DEV,
+	CGS_SYSTEM_INFO_PCIE_REV,
 	CGS_SYSTEM_INFO_CG_FLAGS,
 	CGS_SYSTEM_INFO_PG_FLAGS,
 	CGS_SYSTEM_INFO_GFX_CU_INFO,
+	CGS_SYSTEM_INFO_GFX_SE_INFO,
 	CGS_SYSTEM_INFO_ID_MAXIMUM,
 };
 
 struct cgs_system_info {
-	uint64_t       size;
-	uint64_t       info_id;
+	uint64_t			size;
+	enum cgs_system_info_id		info_id;
 	union {
-		void           *ptr;
-		uint64_t        value;
+		void			*ptr;
+		uint64_t		value;
 	};
-	uint64_t               padding[13];
+	uint64_t			padding[13];
 };
 
 /*
@@ -158,6 +162,10 @@ struct cgs_firmware_info {
 	uint16_t		feature_version;
 	uint32_t		image_size;
 	uint64_t		mc_addr;
+
+	/* only for smc firmware */
+	uint32_t		ucode_start_address;
+
 	void			*kptr;
 };
 
@@ -189,7 +197,6 @@ typedef unsigned long cgs_handle_t;
 
 struct cgs_acpi_method_argument {
 	uint32_t type;
-	uint32_t method_length;
 	uint32_t data_length;
 	union{
 		uint32_t value;
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index e629f8a9fe93..abbb658bdc1e 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -176,7 +176,7 @@ static int pp_hw_fini(void *handle)
 
 static bool pp_is_idle(void *handle)
 {
-	return 0;
+	return false;
 }
 
 static int pp_wait_for_idle(void *handle)
@@ -536,6 +536,10 @@ int pp_dpm_dispatch_tasks(void *handle, enum amd_pp_event event_id, void *input,
 	case AMD_PP_EVENT_COMPLETE_INIT:
 		ret = pem_handle_event(pp_handle->eventmgr, event_id, &data);
 		break;
+	case AMD_PP_EVENT_READJUST_POWER_STATE:
+		pp_handle->hwmgr->current_ps = pp_handle->hwmgr->boot_ps;
+		ret = pem_handle_event(pp_handle->eventmgr, event_id, &data);
+		break;
 	default:
 		break;
 	}
@@ -740,12 +744,12 @@ static int pp_dpm_get_pp_table(void *handle, char **table)
 
 	PP_CHECK_HW(hwmgr);
 
-	if (hwmgr->hwmgr_func->get_pp_table == NULL) {
-		printk(KERN_INFO "%s was not implemented.\n", __func__);
-		return 0;
-	}
+	if (!hwmgr->soft_pp_table)
+		return -EINVAL;
 
-	return hwmgr->hwmgr_func->get_pp_table(hwmgr, table);
+	*table = (char *)hwmgr->soft_pp_table;
+
+	return hwmgr->soft_pp_table_size;
 }
 
 static int pp_dpm_set_pp_table(void *handle, const char *buf, size_t size)
@@ -759,12 +763,23 @@ static int pp_dpm_set_pp_table(void *handle, const char *buf, size_t size)
 
 	PP_CHECK_HW(hwmgr);
 
-	if (hwmgr->hwmgr_func->set_pp_table == NULL) {
-		printk(KERN_INFO "%s was not implemented.\n", __func__);
-		return 0;
+	if (!hwmgr->hardcode_pp_table) {
+		hwmgr->hardcode_pp_table =
+				kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL);
+
+		if (!hwmgr->hardcode_pp_table)
+			return -ENOMEM;
+
+		/* to avoid powerplay crash when hardcode pptable is empty */
+		memcpy(hwmgr->hardcode_pp_table, hwmgr->soft_pp_table,
+				hwmgr->soft_pp_table_size);
 	}
 
-	return hwmgr->hwmgr_func->set_pp_table(hwmgr, buf, size);
+	memcpy(hwmgr->hardcode_pp_table, buf, size);
+
+	hwmgr->soft_pp_table = hwmgr->hardcode_pp_table;
+
+	return amd_powerplay_reset(handle);
 }
 
 static int pp_dpm_force_clock_level(void *handle,
@@ -806,6 +821,82 @@ static int pp_dpm_print_clock_levels(void *handle,
 	return hwmgr->hwmgr_func->print_clock_levels(hwmgr, type, buf);
 }
 
+static int pp_dpm_get_sclk_od(void *handle)
+{
+	struct pp_hwmgr *hwmgr;
+
+	if (!handle)
+		return -EINVAL;
+
+	hwmgr = ((struct pp_instance *)handle)->hwmgr;
+
+	PP_CHECK_HW(hwmgr);
+
+	if (hwmgr->hwmgr_func->get_sclk_od == NULL) {
+		printk(KERN_INFO "%s was not implemented.\n", __func__);
+		return 0;
+	}
+
+	return hwmgr->hwmgr_func->get_sclk_od(hwmgr);
+}
+
+static int pp_dpm_set_sclk_od(void *handle, uint32_t value)
+{
+	struct pp_hwmgr *hwmgr;
+
+	if (!handle)
+		return -EINVAL;
+
+	hwmgr = ((struct pp_instance *)handle)->hwmgr;
+
+	PP_CHECK_HW(hwmgr);
+
+	if (hwmgr->hwmgr_func->set_sclk_od == NULL) {
+		printk(KERN_INFO "%s was not implemented.\n", __func__);
+		return 0;
+	}
+
+	return hwmgr->hwmgr_func->set_sclk_od(hwmgr, value);
+}
+
+static int pp_dpm_get_mclk_od(void *handle)
+{
+	struct pp_hwmgr *hwmgr;
+
+	if (!handle)
+		return -EINVAL;
+
+	hwmgr = ((struct pp_instance *)handle)->hwmgr;
+
+	PP_CHECK_HW(hwmgr);
+
+	if (hwmgr->hwmgr_func->get_mclk_od == NULL) {
+		printk(KERN_INFO "%s was not implemented.\n", __func__);
+		return 0;
+	}
+
+	return hwmgr->hwmgr_func->get_mclk_od(hwmgr);
+}
+
+static int pp_dpm_set_mclk_od(void *handle, uint32_t value)
+{
+	struct pp_hwmgr *hwmgr;
+
+	if (!handle)
+		return -EINVAL;
+
+	hwmgr = ((struct pp_instance *)handle)->hwmgr;
+
+	PP_CHECK_HW(hwmgr);
+
+	if (hwmgr->hwmgr_func->set_mclk_od == NULL) {
+		printk(KERN_INFO "%s was not implemented.\n", __func__);
+		return 0;
+	}
+
+	return hwmgr->hwmgr_func->set_mclk_od(hwmgr, value);
+}
+
 const struct amd_powerplay_funcs pp_dpm_funcs = {
 	.get_temperature = pp_dpm_get_temperature,
 	.load_firmware = pp_dpm_load_fw,
@@ -828,6 +919,10 @@ const struct amd_powerplay_funcs pp_dpm_funcs = {
 	.set_pp_table = pp_dpm_set_pp_table,
 	.force_clock_level = pp_dpm_force_clock_level,
 	.print_clock_levels = pp_dpm_print_clock_levels,
+	.get_sclk_od = pp_dpm_get_sclk_od,
+	.set_sclk_od = pp_dpm_set_sclk_od,
+	.get_mclk_od = pp_dpm_get_mclk_od,
+	.set_mclk_od = pp_dpm_set_mclk_od,
 };
 
 static int amd_pp_instance_init(struct amd_pp_init *pp_init,
@@ -909,6 +1004,44 @@ int amd_powerplay_fini(void *handle)
 	return 0;
 }
 
+int amd_powerplay_reset(void *handle)
+{
+	struct pp_instance *instance = (struct pp_instance *)handle;
+	struct pp_eventmgr *eventmgr;
+	struct pem_event_data event_data = { {0} };
+	int ret;
+
+	if (instance == NULL)
+		return -EINVAL;
+
+	eventmgr = instance->eventmgr;
+	if (!eventmgr || !eventmgr->pp_eventmgr_fini)
+		return -EINVAL;
+
+	eventmgr->pp_eventmgr_fini(eventmgr);
+
+	ret = pp_sw_fini(handle);
+	if (ret)
+		return ret;
+
+	kfree(instance->hwmgr->ps);
+
+	ret = pp_sw_init(handle);
+	if (ret)
+		return ret;
+
+	hw_init_power_state_table(instance->hwmgr);
+
+	if (eventmgr == NULL || eventmgr->pp_eventmgr_init == NULL)
+		return -EINVAL;
+
+	ret = eventmgr->pp_eventmgr_init(eventmgr);
+	if (ret)
+		return ret;
+
+	return pem_handle_event(eventmgr, AMD_PP_EVENT_COMPLETE_INIT, &event_data);
+}
+
 /* export this function to DAL */
 
 int amd_powerplay_display_configuration_change(void *handle,
diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c
index d6635cc4b0fc..635fc4b48184 100644
--- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c
+++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c
@@ -30,7 +30,6 @@ static const pem_event_action * const initialize_event[] = {
 	system_config_tasks,
 	setup_asic_tasks,
 	enable_dynamic_state_management_tasks,
-	enable_clock_power_gatings_tasks,
 	get_2d_performance_state_tasks,
 	set_performance_state_tasks,
 	initialize_thermal_controller_tasks,
@@ -140,7 +139,6 @@ static const pem_event_action * const resume_event[] = {
 	setup_asic_tasks,
 	enable_stutter_mode_tasks, /*must do this in boot state and before SMC is started */
 	enable_dynamic_state_management_tasks,
-	enable_clock_power_gatings_tasks,
 	enable_disable_bapm_tasks,
 	initialize_thermal_controller_tasks,
 	get_2d_performance_state_tasks,
diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventtasks.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventtasks.c
index 5cd123472db4..b6f45fd01fa6 100644
--- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventtasks.c
+++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventtasks.c
@@ -132,8 +132,7 @@ int pem_task_enable_dynamic_state_management(struct pp_eventmgr *eventmgr, struc
 
 int pem_task_disable_dynamic_state_management(struct pp_eventmgr *eventmgr, struct pem_event_data *event_data)
 {
-	/* TODO */
-	return 0;
+	return phm_disable_dynamic_state_management(eventmgr->hwmgr);
 }
 
 int pem_task_enable_clock_power_gatings_tasks(struct pp_eventmgr *eventmgr, struct pem_event_data *event_data)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
index 436fc16dabb6..2028980f1ed4 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
@@ -177,12 +177,12 @@ int cz_dpm_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate)
 		cz_dpm_powerdown_uvd(hwmgr);
 	} else {
 		cz_dpm_powerup_uvd(hwmgr);
-		cgs_set_clockgating_state(hwmgr->device,
-						AMD_IP_BLOCK_TYPE_UVD,
-						AMD_PG_STATE_GATE);
 		cgs_set_powergating_state(hwmgr->device,
 						AMD_IP_BLOCK_TYPE_UVD,
 						AMD_CG_STATE_UNGATE);
+		cgs_set_clockgating_state(hwmgr->device,
+						AMD_IP_BLOCK_TYPE_UVD,
+						AMD_PG_STATE_GATE);
 		cz_dpm_update_uvd_dpm(hwmgr, false);
 	}
 
@@ -206,25 +206,26 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 							AMD_IP_BLOCK_TYPE_VCE,
 							AMD_PG_STATE_GATE);
 				cz_enable_disable_vce_dpm(hwmgr, false);
-			/* TODO: to figure out why vce can't be poweroff*/
+				cz_dpm_powerdown_vce(hwmgr);
 				cz_hwmgr->vce_power_gated = true;
 			} else {
 				cz_dpm_powerup_vce(hwmgr);
 				cz_hwmgr->vce_power_gated = false;
-				cgs_set_clockgating_state(
-							hwmgr->device,
-							AMD_IP_BLOCK_TYPE_VCE,
-							AMD_PG_STATE_GATE);
 				cgs_set_powergating_state(
 							hwmgr->device,
 							AMD_IP_BLOCK_TYPE_VCE,
 							AMD_CG_STATE_UNGATE);
+				cgs_set_clockgating_state(
+							hwmgr->device,
+							AMD_IP_BLOCK_TYPE_VCE,
+							AMD_PG_STATE_GATE);
 				cz_dpm_update_vce_dpm(hwmgr);
 				cz_enable_disable_vce_dpm(hwmgr, true);
 				return 0;
 			}
 		}
 	} else {
+		cz_hwmgr->vce_power_gated = bgate;
 		cz_dpm_update_vce_dpm(hwmgr);
 		cz_enable_disable_vce_dpm(hwmgr, !bgate);
 		return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
index 1f14c477d15d..8cc0df9b534a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
@@ -1167,9 +1167,9 @@ static int cz_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 
 	cz_ps->action = cz_current_ps->action;
 
-	if ((force_high == false) && (cz_ps->action == FORCE_HIGH))
+	if (!force_high && (cz_ps->action == FORCE_HIGH))
 		cz_ps->action = CANCEL_FORCE_HIGH;
-	else if ((force_high == true) && (cz_ps->action != FORCE_HIGH))
+	else if (force_high && (cz_ps->action != FORCE_HIGH))
 		cz_ps->action = FORCE_HIGH;
 	else
 		cz_ps->action = DO_NOTHING;
@@ -1180,6 +1180,13 @@ static int cz_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 static int cz_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 {
 	int result = 0;
+	struct cz_hwmgr *data;
+
+	data = kzalloc(sizeof(struct cz_hwmgr), GFP_KERNEL);
+	if (data == NULL)
+		return -ENOMEM;
+
+	hwmgr->backend = data;
 
 	result = cz_initialize_dpm_defaults(hwmgr);
 	if (result != 0) {
@@ -1649,7 +1656,7 @@ static void cz_hw_print_display_cfg(
 	struct cz_hwmgr *hw_data = (struct cz_hwmgr *)(hwmgr->backend);
 	uint32_t data = 0;
 
-	if (hw_data->cc6_settings.cc6_setting_changed == true) {
+	if (hw_data->cc6_settings.cc6_setting_changed) {
 
 		hw_data->cc6_settings.cc6_setting_changed = false;
 
@@ -1909,15 +1916,7 @@ static const struct pp_hwmgr_func cz_hwmgr_funcs = {
 
 int cz_hwmgr_init(struct pp_hwmgr *hwmgr)
 {
-	struct cz_hwmgr *cz_hwmgr;
-	int ret = 0;
-
-	cz_hwmgr = kzalloc(sizeof(struct cz_hwmgr), GFP_KERNEL);
-	if (cz_hwmgr == NULL)
-		return -ENOMEM;
-
-	hwmgr->backend = cz_hwmgr;
 	hwmgr->hwmgr_func = &cz_hwmgr_funcs;
 	hwmgr->pptable_func = &pptable_funcs;
-	return ret;
+	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_clockpowergating.c
index e1b649bd5344..5afe82068b29 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_clockpowergating.c
@@ -56,7 +56,7 @@ int fiji_phm_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate)
 		fiji_update_uvd_dpm(hwmgr, false);
 		cgs_set_clockgating_state(hwmgr->device,
 					  AMD_IP_BLOCK_TYPE_UVD,
-					  AMD_PG_STATE_UNGATE);
+					  AMD_CG_STATE_UNGATE);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
index 92912ab20944..120a9e2c3152 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
@@ -581,25 +581,24 @@ static int fiji_patch_boot_state(struct pp_hwmgr *hwmgr,
 
 static int fiji_hwmgr_backend_fini(struct pp_hwmgr *hwmgr)
 {
-	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
-
-	if (data->soft_pp_table) {
-		kfree(data->soft_pp_table);
-		data->soft_pp_table = NULL;
-	}
-
 	return phm_hwmgr_backend_fini(hwmgr);
 }
 
 static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 {
-	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+	struct fiji_hwmgr *data;
 	uint32_t i;
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	bool stay_in_boot;
 	int result;
 
+	data = kzalloc(sizeof(struct fiji_hwmgr), GFP_KERNEL);
+	if (data == NULL)
+		return -ENOMEM;
+
+	hwmgr->backend = data;
+
 	data->dll_default_on = false;
 	data->sram_end = SMC_RAM_END;
 
@@ -699,7 +698,7 @@ static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	if (0 == result) {
 		struct cgs_system_info sys_info = {0};
 
-		data->is_tlu_enabled = 0;
+		data->is_tlu_enabled = false;
 		hwmgr->platform_descriptor.hardwareActivityPerformanceLevels =
 				FIJI_MAX_HARDWARE_POWERLEVELS;
 		hwmgr->platform_descriptor.hardwarePerformanceLevels = 2;
@@ -734,7 +733,7 @@ static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 		sys_info.info_id = CGS_SYSTEM_INFO_PCIE_GEN_INFO;
 		result = cgs_query_system_info(hwmgr->device, &sys_info);
 		if (result)
-			data->pcie_gen_cap = 0x30007;
+			data->pcie_gen_cap = AMDGPU_DEFAULT_PCIE_GEN_MASK;
 		else
 			data->pcie_gen_cap = (uint32_t)sys_info.value;
 		if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
@@ -743,7 +742,7 @@ static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 		sys_info.info_id = CGS_SYSTEM_INFO_PCIE_MLW;
 		result = cgs_query_system_info(hwmgr->device, &sys_info);
 		if (result)
-			data->pcie_lane_cap = 0x2f0000;
+			data->pcie_lane_cap = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		else
 			data->pcie_lane_cap = (uint32_t)sys_info.value;
 	} else {
@@ -1236,6 +1235,34 @@ static int fiji_program_voting_clients(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int fiji_clear_voting_clients(struct pp_hwmgr *hwmgr)
+{
+	/* Reset voting clients before disabling DPM */
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+			SCLK_PWRMGT_CNTL, RESET_SCLK_CNT, 1);
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+			SCLK_PWRMGT_CNTL, RESET_BUSY_CNT, 1);
+
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_0, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_1, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_2, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_3, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_4, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_5, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_6, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_7, 0);
+
+	return 0;
+}
+
 /**
 * Get the location of various tables inside the FW image.
 *
@@ -1363,6 +1390,17 @@ static int fiji_copy_and_switch_arb_sets(struct pp_hwmgr *hwmgr,
 }
 
 /**
+* Call SMC to reset S0/S1 to S1 and Reset SMIO to initial value
+*
+* @param    hwmgr  the address of the powerplay hardware manager.
+* @return   if success then 0;
+*/
+static int fiji_reset_to_default(struct pp_hwmgr *hwmgr)
+{
+	return smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_ResetToDefaults);
+}
+
+/**
 * Initial switch from ARB F0->F1
 *
 * @param    hwmgr  the address of the powerplay hardware manager.
@@ -1375,6 +1413,21 @@ static int fiji_initial_switch_from_arbf0_to_f1(struct pp_hwmgr *hwmgr)
 			MC_CG_ARB_FREQ_F0, MC_CG_ARB_FREQ_F1);
 }
 
+static int fiji_force_switch_to_arbf0(struct pp_hwmgr *hwmgr)
+{
+	uint32_t tmp;
+
+	tmp = (cgs_read_ind_register(hwmgr->device,
+			CGS_IND_REG__SMC, ixSMC_SCRATCH9) &
+			0x0000ff00) >> 8;
+
+	if (tmp == MC_CG_ARB_FREQ_F0)
+		return 0;
+
+	return fiji_copy_and_switch_arb_sets(hwmgr,
+			tmp, MC_CG_ARB_FREQ_F0);
+}
+
 static int fiji_reset_single_dpm_table(struct pp_hwmgr *hwmgr,
 		struct fiji_single_dpm_table *dpm_table, uint32_t count)
 {
@@ -1397,7 +1450,7 @@ static void fiji_setup_pcie_table_entry(
 {
 	dpm_table->dpm_levels[index].value = pcie_gen;
 	dpm_table->dpm_levels[index].param1 = pcie_lanes;
-	dpm_table->dpm_levels[index].enabled = 1;
+	dpm_table->dpm_levels[index].enabled = true;
 }
 
 static int fiji_setup_default_pcie_table(struct pp_hwmgr *hwmgr)
@@ -1609,7 +1662,6 @@ static int fiji_populate_cac_table(struct pp_hwmgr *hwmgr,
 {
 	uint32_t count;
 	uint8_t index;
-	int result = 0;
 	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
@@ -1631,7 +1683,7 @@ static int fiji_populate_cac_table(struct pp_hwmgr *hwmgr,
 						VOLTAGE_SCALE)) / 25);
 	}
 
-	return result;
+	return 0;
 }
 
 /**
@@ -3177,6 +3229,17 @@ static int fiji_enable_ulv(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int fiji_disable_ulv(struct pp_hwmgr *hwmgr)
+{
+	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+	struct fiji_ulv_parm *ulv = &(data->ulv);
+
+	if (ulv->ulv_supported)
+		return smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_DisableULV);
+
+	return 0;
+}
+
 static int fiji_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr)
 {
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
@@ -3197,6 +3260,21 @@ static int fiji_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int fiji_disable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr)
+{
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_SclkDeepSleep)) {
+		if (smum_send_msg_to_smc(hwmgr->smumgr,
+				PPSMC_MSG_MASTER_DeepSleep_OFF)) {
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to disable Master Deep Sleep switch failed!",
+					return -1);
+		}
+	}
+
+	return 0;
+}
+
 static int fiji_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 {
 	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
@@ -3357,6 +3435,70 @@ static int fiji_start_dpm(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int fiji_disable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
+{
+	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+
+	/* disable SCLK dpm */
+	if (!data->sclk_dpm_key_disabled)
+		PP_ASSERT_WITH_CODE(
+				(smum_send_msg_to_smc(hwmgr->smumgr,
+						PPSMC_MSG_DPM_Disable) == 0),
+				"Failed to disable SCLK DPM!",
+				return -1);
+
+	/* disable MCLK dpm */
+	if (!data->mclk_dpm_key_disabled) {
+		PP_ASSERT_WITH_CODE(
+				(smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+				PPSMC_MSG_MCLKDPM_SetEnabledMask, 1) == 0),
+				"Failed to force MCLK DPM0!",
+				return -1);
+
+		PP_ASSERT_WITH_CODE(
+				(smum_send_msg_to_smc(hwmgr->smumgr,
+						PPSMC_MSG_MCLKDPM_Disable) == 0),
+				"Failed to disable MCLK DPM!",
+				return -1);
+	}
+
+	return 0;
+}
+
+static int fiji_stop_dpm(struct pp_hwmgr *hwmgr)
+{
+	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+
+	/* disable general power management */
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, GENERAL_PWRMGT,
+			GLOBAL_PWRMGT_EN, 0);
+	/* disable sclk deep sleep */
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, SCLK_PWRMGT_CNTL,
+			DYNAMIC_PM_EN, 0);
+
+	/* disable PCIE dpm */
+	if (!data->pcie_dpm_key_disabled) {
+		PP_ASSERT_WITH_CODE(
+				(smum_send_msg_to_smc(hwmgr->smumgr,
+						PPSMC_MSG_PCIeDPM_Disable) == 0),
+				"Failed to disable pcie DPM during DPM Stop Function!",
+				return -1);
+	}
+
+	if (fiji_disable_sclk_mclk_dpm(hwmgr)) {
+		printk(KERN_ERR "Failed to disable Sclk DPM and Mclk DPM!");
+		return -1;
+	}
+
+	PP_ASSERT_WITH_CODE(
+			(smum_send_msg_to_smc(hwmgr->smumgr,
+					PPSMC_MSG_Voltage_Cntl_Disable) == 0),
+			"Failed to disable voltage DPM during DPM Stop Function!",
+			return -1);
+
+	return 0;
+}
+
 static void fiji_set_dpm_event_sources(struct pp_hwmgr *hwmgr,
 		uint32_t sources)
 {
@@ -3415,6 +3557,23 @@ static int fiji_enable_thermal_auto_throttle(struct pp_hwmgr *hwmgr)
 	return fiji_enable_auto_throttle_source(hwmgr, PHM_AutoThrottleSource_Thermal);
 }
 
+static int fiji_disable_auto_throttle_source(struct pp_hwmgr *hwmgr,
+		PHM_AutoThrottleSource source)
+{
+	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+
+	if (data->active_auto_throttle_sources & (1 << source)) {
+		data->active_auto_throttle_sources &= ~(1 << source);
+		fiji_set_dpm_event_sources(hwmgr, data->active_auto_throttle_sources);
+	}
+	return 0;
+}
+
+static int fiji_disable_thermal_auto_throttle(struct pp_hwmgr *hwmgr)
+{
+	return fiji_disable_auto_throttle_source(hwmgr, PHM_AutoThrottleSource_Thermal);
+}
+
 static int fiji_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
 	int tmp_result, result = 0;
@@ -3529,6 +3688,64 @@ static int fiji_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+static int fiji_disable_dpm_tasks(struct pp_hwmgr *hwmgr)
+{
+	int tmp_result, result = 0;
+
+	tmp_result = (fiji_is_dpm_running(hwmgr)) ? 0 : -1;
+	PP_ASSERT_WITH_CODE(tmp_result == 0,
+			"DPM is not running right now, no need to disable DPM!",
+			return 0);
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_ThermalController))
+		PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+				GENERAL_PWRMGT, THERMAL_PROTECTION_DIS, 1);
+
+	tmp_result = fiji_disable_power_containment(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to disable power containment!", result = tmp_result);
+
+	tmp_result = fiji_disable_smc_cac(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to disable SMC CAC!", result = tmp_result);
+
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+			CG_SPLL_SPREAD_SPECTRUM, SSEN, 0);
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+			GENERAL_PWRMGT, DYN_SPREAD_SPECTRUM_EN, 0);
+
+	tmp_result = fiji_disable_thermal_auto_throttle(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to disable thermal auto throttle!", result = tmp_result);
+
+	tmp_result = fiji_stop_dpm(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to stop DPM!", result = tmp_result);
+
+	tmp_result = fiji_disable_deep_sleep_master_switch(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to disable deep sleep master switch!", result = tmp_result);
+
+	tmp_result = fiji_disable_ulv(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to disable ULV!", result = tmp_result);
+
+	tmp_result = fiji_clear_voting_clients(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to clear voting clients!", result = tmp_result);
+
+	tmp_result = fiji_reset_to_default(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to reset to default!", result = tmp_result);
+
+	tmp_result = fiji_force_switch_to_arbf0(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to force to switch arbf0!", result = tmp_result);
+
+	return result;
+}
+
 static int fiji_force_dpm_highest(struct pp_hwmgr *hwmgr)
 {
 	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
@@ -4171,8 +4388,9 @@ static int fiji_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if ((0 == data->sclk_dpm_key_disabled) &&
 		(data->need_update_smu7_dpm_table &
 			(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) {
-		PP_ASSERT_WITH_CODE(true == fiji_is_dpm_running(hwmgr),
-				"Trying to freeze SCLK DPM when DPM is disabled",);
+		PP_ASSERT_WITH_CODE(fiji_is_dpm_running(hwmgr),
+				    "Trying to freeze SCLK DPM when DPM is disabled",
+				    );
 		PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr,
 				PPSMC_MSG_SCLKDPM_FreezeLevel),
 				"Failed to freeze SCLK DPM during FreezeSclkMclkDPM Function!",
@@ -4182,8 +4400,9 @@ static int fiji_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if ((0 == data->mclk_dpm_key_disabled) &&
 		(data->need_update_smu7_dpm_table &
 		 DPMTABLE_OD_UPDATE_MCLK)) {
-		PP_ASSERT_WITH_CODE(true == fiji_is_dpm_running(hwmgr),
-				"Trying to freeze MCLK DPM when DPM is disabled",);
+		PP_ASSERT_WITH_CODE(fiji_is_dpm_running(hwmgr),
+				    "Trying to freeze MCLK DPM when DPM is disabled",
+				    );
 		PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr,
 				PPSMC_MSG_MCLKDPM_FreezeLevel),
 				"Failed to freeze MCLK DPM during FreezeSclkMclkDPM Function!",
@@ -4353,7 +4572,6 @@ static int fiji_trim_single_dpm_states(struct pp_hwmgr *hwmgr,
 static int fiji_trim_dpm_states(struct pp_hwmgr *hwmgr,
 		const struct fiji_power_state *fiji_ps)
 {
-	int result = 0;
 	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
 	uint32_t high_limit_count;
 
@@ -4373,7 +4591,7 @@ static int fiji_trim_dpm_states(struct pp_hwmgr *hwmgr,
 			fiji_ps->performance_levels[0].memory_clock,
 			fiji_ps->performance_levels[high_limit_count].memory_clock);
 
-	return result;
+	return 0;
 }
 
 static int fiji_generate_dpm_level_enable_mask(
@@ -4632,8 +4850,9 @@ static int fiji_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 		(data->need_update_smu7_dpm_table &
 		(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) {
 
-		PP_ASSERT_WITH_CODE(true == fiji_is_dpm_running(hwmgr),
-				"Trying to Unfreeze SCLK DPM when DPM is disabled",);
+		PP_ASSERT_WITH_CODE(fiji_is_dpm_running(hwmgr),
+				    "Trying to Unfreeze SCLK DPM when DPM is disabled",
+				    );
 		PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr,
 				PPSMC_MSG_SCLKDPM_UnfreezeLevel),
 			"Failed to unfreeze SCLK DPM during UnFreezeSclkMclkDPM Function!",
@@ -4643,8 +4862,9 @@ static int fiji_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if ((0 == data->mclk_dpm_key_disabled) &&
 		(data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) {
 
-		PP_ASSERT_WITH_CODE(true == fiji_is_dpm_running(hwmgr),
-				"Trying to Unfreeze MCLK DPM when DPM is disabled",);
+		PP_ASSERT_WITH_CODE(fiji_is_dpm_running(hwmgr),
+				    "Trying to Unfreeze MCLK DPM when DPM is disabled",
+				    );
 		PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr,
 				PPSMC_MSG_SCLKDPM_UnfreezeLevel),
 		    "Failed to unfreeze MCLK DPM during UnFreezeSclkMclkDPM Function!",
@@ -5071,42 +5291,6 @@ static int fiji_get_fan_control_mode(struct pp_hwmgr *hwmgr)
 				CG_FDO_CTRL2, FDO_PWM_MODE);
 }
 
-static int fiji_get_pp_table(struct pp_hwmgr *hwmgr, char **table)
-{
-	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
-
-	if (!data->soft_pp_table) {
-		data->soft_pp_table = kmemdup(hwmgr->soft_pp_table,
-					      hwmgr->soft_pp_table_size,
-					      GFP_KERNEL);
-		if (!data->soft_pp_table)
-			return -ENOMEM;
-	}
-
-	*table = (char *)&data->soft_pp_table;
-
-	return hwmgr->soft_pp_table_size;
-}
-
-static int fiji_set_pp_table(struct pp_hwmgr *hwmgr, const char *buf, size_t size)
-{
-	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
-
-	if (!data->soft_pp_table) {
-		data->soft_pp_table = kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL);
-		if (!data->soft_pp_table)
-			return -ENOMEM;
-	}
-
-	memcpy(data->soft_pp_table, buf, size);
-
-	hwmgr->soft_pp_table = data->soft_pp_table;
-
-	/* TODO: re-init powerplay to implement modified pptable */
-
-	return 0;
-}
-
 static int fiji_force_clock_level(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, uint32_t mask)
 {
@@ -5276,12 +5460,96 @@ bool fiji_check_smc_update_required_for_display_configuration(struct pp_hwmgr *h
 	return is_update_required;
 }
 
+static int fiji_get_sclk_od(struct pp_hwmgr *hwmgr)
+{
+	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+	struct fiji_single_dpm_table *sclk_table = &(data->dpm_table.sclk_table);
+	struct fiji_single_dpm_table *golden_sclk_table =
+			&(data->golden_dpm_table.sclk_table);
+	int value;
+
+	value = (sclk_table->dpm_levels[sclk_table->count - 1].value -
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value) *
+			100 /
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value;
+
+	return value;
+}
+
+static int fiji_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value)
+{
+	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+	struct fiji_single_dpm_table *golden_sclk_table =
+			&(data->golden_dpm_table.sclk_table);
+	struct pp_power_state  *ps;
+	struct fiji_power_state  *fiji_ps;
+
+	if (value > 20)
+		value = 20;
+
+	ps = hwmgr->request_ps;
+
+	if (ps == NULL)
+		return -EINVAL;
+
+	fiji_ps = cast_phw_fiji_power_state(&ps->hardware);
+
+	fiji_ps->performance_levels[fiji_ps->performance_level_count - 1].engine_clock =
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value *
+			value / 100 +
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value;
+
+	return 0;
+}
+
+static int fiji_get_mclk_od(struct pp_hwmgr *hwmgr)
+{
+	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+	struct fiji_single_dpm_table *mclk_table = &(data->dpm_table.mclk_table);
+	struct fiji_single_dpm_table *golden_mclk_table =
+			&(data->golden_dpm_table.mclk_table);
+	int value;
+
+	value = (mclk_table->dpm_levels[mclk_table->count - 1].value -
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value) *
+			100 /
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value;
+
+	return value;
+}
+
+static int fiji_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value)
+{
+	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+	struct fiji_single_dpm_table *golden_mclk_table =
+			&(data->golden_dpm_table.mclk_table);
+	struct pp_power_state  *ps;
+	struct fiji_power_state  *fiji_ps;
+
+	if (value > 20)
+		value = 20;
+
+	ps = hwmgr->request_ps;
+
+	if (ps == NULL)
+		return -EINVAL;
+
+	fiji_ps = cast_phw_fiji_power_state(&ps->hardware);
+
+	fiji_ps->performance_levels[fiji_ps->performance_level_count - 1].memory_clock =
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value *
+			value / 100 +
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value;
+
+	return 0;
+}
 
 static const struct pp_hwmgr_func fiji_hwmgr_funcs = {
 	.backend_init = &fiji_hwmgr_backend_init,
 	.backend_fini = &fiji_hwmgr_backend_fini,
 	.asic_setup = &fiji_setup_asic_task,
 	.dynamic_state_management_enable = &fiji_enable_dpm_tasks,
+	.dynamic_state_management_disable = &fiji_disable_dpm_tasks,
 	.force_dpm_level = &fiji_dpm_force_dpm_level,
 	.get_num_of_pp_table_entries = &tonga_get_number_of_powerplay_table_entries,
 	.get_power_state_size = &fiji_get_power_state_size,
@@ -5314,24 +5582,18 @@ static const struct pp_hwmgr_func fiji_hwmgr_funcs = {
 	.get_fan_control_mode = fiji_get_fan_control_mode,
 	.check_states_equal = fiji_check_states_equal,
 	.check_smc_update_required_for_display_configuration = fiji_check_smc_update_required_for_display_configuration,
-	.get_pp_table = fiji_get_pp_table,
-	.set_pp_table = fiji_set_pp_table,
 	.force_clock_level = fiji_force_clock_level,
 	.print_clock_levels = fiji_print_clock_levels,
+	.get_sclk_od = fiji_get_sclk_od,
+	.set_sclk_od = fiji_set_sclk_od,
+	.get_mclk_od = fiji_get_mclk_od,
+	.set_mclk_od = fiji_set_mclk_od,
 };
 
 int fiji_hwmgr_init(struct pp_hwmgr *hwmgr)
 {
-	struct fiji_hwmgr  *data;
-	int ret = 0;
-
-	data = kzalloc(sizeof(struct fiji_hwmgr), GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
-
-	hwmgr->backend = data;
 	hwmgr->hwmgr_func = &fiji_hwmgr_funcs;
 	hwmgr->pptable_func = &tonga_pptable_funcs;
 	pp_fiji_thermal_initialize(hwmgr);
-	return ret;
+	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.h
index 170edf5a772d..bf67c2a92c68 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.h
@@ -302,9 +302,6 @@ struct fiji_hwmgr {
 	bool                           pg_acp_init;
 	bool                           frtc_enabled;
 	bool                           frtc_status_changed;
-
-	/* soft pptable for re-uploading into smu */
-	void *soft_pp_table;
 };
 
 /* To convert to Q8.8 format for firmware */
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.c
index db23a4068baf..44658451a8d2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.c
@@ -73,17 +73,18 @@ void fiji_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr)
 
 	if (!tmp) {
 		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
-				PHM_PlatformCaps_PowerContainment);
-
-		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 				PHM_PlatformCaps_CAC);
 
 		fiji_hwmgr->fast_watermark_threshold = 100;
 
-		tmp = 1;
-		fiji_hwmgr->enable_dte_feature = tmp ? false : true;
-		fiji_hwmgr->enable_tdc_limit_feature = tmp ? true : false;
-		fiji_hwmgr->enable_pkg_pwr_tracking_feature = tmp ? true : false;
+		if (hwmgr->powercontainment_enabled) {
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				    PHM_PlatformCaps_PowerContainment);
+			tmp = 1;
+			fiji_hwmgr->enable_dte_feature = tmp ? false : true;
+			fiji_hwmgr->enable_tdc_limit_feature = tmp ? true : false;
+			fiji_hwmgr->enable_pkg_pwr_tracking_feature = tmp ? true : false;
+		}
 	}
 }
 
@@ -459,6 +460,23 @@ int fiji_enable_smc_cac(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+int fiji_disable_smc_cac(struct pp_hwmgr *hwmgr)
+{
+	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+	int result = 0;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_CAC) && data->cac_enabled) {
+		int smc_result = smum_send_msg_to_smc(hwmgr->smumgr,
+				(uint16_t)(PPSMC_MSG_DisableCac));
+		PP_ASSERT_WITH_CODE((smc_result == 0),
+				"Failed to disable CAC in SMC.", result = -1);
+
+		data->cac_enabled = false;
+	}
+	return result;
+}
+
 int fiji_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n)
 {
 	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
@@ -528,6 +546,48 @@ int fiji_enable_power_containment(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+int fiji_disable_power_containment(struct pp_hwmgr *hwmgr)
+{
+	struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend);
+	int result = 0;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_PowerContainment) &&
+			data->power_containment_features) {
+		int smc_result;
+
+		if (data->power_containment_features &
+				POWERCONTAINMENT_FEATURE_TDCLimit) {
+			smc_result = smum_send_msg_to_smc(hwmgr->smumgr,
+					(uint16_t)(PPSMC_MSG_TDCLimitDisable));
+			PP_ASSERT_WITH_CODE((smc_result == 0),
+					"Failed to disable TDCLimit in SMC.",
+					result = smc_result);
+		}
+
+		if (data->power_containment_features &
+				POWERCONTAINMENT_FEATURE_DTE) {
+			smc_result = smum_send_msg_to_smc(hwmgr->smumgr,
+					(uint16_t)(PPSMC_MSG_DisableDTE));
+			PP_ASSERT_WITH_CODE((smc_result == 0),
+					"Failed to disable DTE in SMC.",
+					result = smc_result);
+		}
+
+		if (data->power_containment_features &
+				POWERCONTAINMENT_FEATURE_PkgPwrLimit) {
+			smc_result = smum_send_msg_to_smc(hwmgr->smumgr,
+					(uint16_t)(PPSMC_MSG_PkgPwrLimitDisable));
+			PP_ASSERT_WITH_CODE((smc_result == 0),
+					"Failed to disable PkgPwrTracking in SMC.",
+					result = smc_result);
+		}
+		data->power_containment_features = 0;
+	}
+
+	return result;
+}
+
 int fiji_power_control_set_level(struct pp_hwmgr *hwmgr)
 {
 	struct phm_ppt_v1_information *table_info =
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.h b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.h
index 55e58200f33a..fec772421733 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.h
@@ -36,6 +36,19 @@ enum fiji_pt_config_reg_type {
 #define POWERCONTAINMENT_FEATURE_TDCLimit        0x00000002
 #define POWERCONTAINMENT_FEATURE_PkgPwrLimit     0x00000004
 
+#define DIDT_SQ_CTRL0__UNUSED_0_MASK             0xffffffc0
+#define DIDT_SQ_CTRL0__UNUSED_0__SHIFT           0x6
+#define DIDT_TD_CTRL0__UNUSED_0_MASK             0xffffffc0
+#define DIDT_TD_CTRL0__UNUSED_0__SHIFT           0x6
+#define DIDT_TCP_CTRL0__UNUSED_0_MASK            0xffffffc0
+#define DIDT_TCP_CTRL0__UNUSED_0__SHIFT          0x6
+#define DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK                 0xe0000000
+#define DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT               0x0000001d
+#define DIDT_TD_TUNING_CTRL__UNUSED_0_MASK                 0xe0000000
+#define DIDT_TD_TUNING_CTRL__UNUSED_0__SHIFT               0x0000001d
+#define DIDT_TCP_TUNING_CTRL__UNUSED_0_MASK                0xe0000000
+#define DIDT_TCP_TUNING_CTRL__UNUSED_0__SHIFT              0x0000001d
+
 struct fiji_pt_config_reg {
 	uint32_t                           offset;
 	uint32_t                           mask;
@@ -58,7 +71,9 @@ void fiji_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr);
 int fiji_populate_bapm_parameters_in_dpm_table(struct pp_hwmgr *hwmgr);
 int fiji_populate_pm_fuses(struct pp_hwmgr *hwmgr);
 int fiji_enable_smc_cac(struct pp_hwmgr *hwmgr);
+int fiji_disable_smc_cac(struct pp_hwmgr *hwmgr);
 int fiji_enable_power_containment(struct pp_hwmgr *hwmgr);
+int fiji_disable_power_containment(struct pp_hwmgr *hwmgr);
 int fiji_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n);
 int fiji_power_control_set_level(struct pp_hwmgr *hwmgr);
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/functiontables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/functiontables.c
index 7a705cee0cc2..a6abe81bc843 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/functiontables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/functiontables.c
@@ -59,8 +59,8 @@ int phm_dispatch_table(struct pp_hwmgr *hwmgr,
 		       struct phm_runtime_table_header *rt_table,
 		       void *input, void *output)
 {
-	int result = 0;
-	void *temp_storage = NULL;
+	int result;
+	void *temp_storage;
 
 	if (hwmgr == NULL || rt_table == NULL) {
 		printk(KERN_ERR "[ powerplay ] Invalid Parameter!\n");
@@ -73,12 +73,13 @@ int phm_dispatch_table(struct pp_hwmgr *hwmgr,
 			printk(KERN_ERR "[ powerplay ] Could not allocate table temporary storage\n");
 			return -ENOMEM;
 		}
+	} else {
+		temp_storage = NULL;
 	}
 
 	result = phm_run_table(hwmgr, rt_table, input, output, temp_storage);
 
-	if (NULL != temp_storage)
-		kfree(temp_storage);
+	kfree(temp_storage);
 
 	return result;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index efb77eda7508..789f98ad2615 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -154,6 +154,30 @@ int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr)
 	return ret;
 }
 
+int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr)
+{
+	int ret = -1;
+	bool enabled;
+
+	PHM_FUNC_CHECK(hwmgr);
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+		PHM_PlatformCaps_TablelessHardwareInterface)) {
+		if (hwmgr->hwmgr_func->dynamic_state_management_disable)
+			ret = hwmgr->hwmgr_func->dynamic_state_management_disable(hwmgr);
+	} else {
+		ret = phm_dispatch_table(hwmgr,
+				&(hwmgr->disable_dynamic_state_management),
+				NULL, NULL);
+	}
+
+	enabled = ret == 0 ? false : true;
+
+	cgs_notify_dpm_enabled(hwmgr->device, enabled);
+
+	return ret;
+}
+
 int phm_force_dpm_levels(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_level level)
 {
 	PHM_FUNC_CHECK(hwmgr);
@@ -314,7 +338,7 @@ int phm_store_dal_configuration_data(struct pp_hwmgr *hwmgr,
 	if (hwmgr->hwmgr_func->store_cc6_data == NULL)
 		return -EINVAL;
 
-	/* to do pass other display configuration in furture */
+	/* TODO: pass other display configuration in the future */
 
 	if (hwmgr->hwmgr_func->store_cc6_data)
 		hwmgr->hwmgr_func->store_cc6_data(hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 20f20e075588..27e07624ac28 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -24,6 +24,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <drm/amdgpu_drm.h>
 #include "cgs_common.h"
 #include "power_state.h"
 #include "hwmgr.h"
@@ -58,12 +59,13 @@ int hwmgr_init(struct amd_pp_init *pp_init, struct pp_instance *handle)
 	hwmgr->hw_revision = pp_init->rev_id;
 	hwmgr->usec_timeout = AMD_MAX_USEC_TIMEOUT;
 	hwmgr->power_source = PP_PowerSource_AC;
+	hwmgr->powercontainment_enabled = pp_init->powercontainment_enabled;
 
 	switch (hwmgr->chip_family) {
-	case AMD_FAMILY_CZ:
+	case AMDGPU_FAMILY_CZ:
 		cz_hwmgr_init(hwmgr);
 		break;
-	case AMD_FAMILY_VI:
+	case AMDGPU_FAMILY_VI:
 		switch (hwmgr->chip_id) {
 		case CHIP_TONGA:
 			tonga_hwmgr_init(hwmgr);
@@ -94,6 +96,8 @@ int hwmgr_fini(struct pp_hwmgr *hwmgr)
 		return -EINVAL;
 
 	/* do hwmgr finish*/
+	kfree(hwmgr->hardcode_pp_table);
+
 	kfree(hwmgr->backend);
 
 	kfree(hwmgr->start_thermal_controller.function_list);
@@ -530,7 +534,7 @@ int phm_initializa_dynamic_state_adjustment_rule_settings(struct pp_hwmgr *hwmgr
 
 	/* initialize vddc_dep_on_dal_pwrl table */
 	table_size = sizeof(uint32_t) + 4 * sizeof(struct phm_clock_voltage_dependency_record);
-	table_clk_vlt = (struct phm_clock_voltage_dependency_table *)kzalloc(table_size, GFP_KERNEL);
+	table_clk_vlt = kzalloc(table_size, GFP_KERNEL);
 
 	if (NULL == table_clk_vlt) {
 		printk(KERN_ERR "[ powerplay ] Can not allocate space for vddc_dep_on_dal_pwrl! \n");
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_clockpowergating.c
index 8f142a74ad08..b5edb5105986 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_clockpowergating.c
@@ -106,11 +106,17 @@ int polaris10_phm_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate)
 	data->uvd_power_gated = bgate;
 
 	if (bgate) {
+		cgs_set_clockgating_state(hwmgr->device,
+				AMD_IP_BLOCK_TYPE_UVD,
+				AMD_CG_STATE_GATE);
 		polaris10_update_uvd_dpm(hwmgr, true);
 		polaris10_phm_powerdown_uvd(hwmgr);
 	} else {
 		polaris10_phm_powerup_uvd(hwmgr);
 		polaris10_update_uvd_dpm(hwmgr, false);
+		cgs_set_clockgating_state(hwmgr->device,
+				AMD_IP_BLOCK_TYPE_UVD,
+				AMD_CG_STATE_UNGATE);
 	}
 
 	return 0;
@@ -125,11 +131,19 @@ int polaris10_phm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 
 	data->vce_power_gated = bgate;
 
-	if (bgate)
+	if (bgate) {
+		cgs_set_clockgating_state(hwmgr->device,
+				AMD_IP_BLOCK_TYPE_VCE,
+				AMD_CG_STATE_GATE);
+		polaris10_update_vce_dpm(hwmgr, true);
 		polaris10_phm_powerdown_vce(hwmgr);
-	else
+	} else {
 		polaris10_phm_powerup_vce(hwmgr);
-
+		polaris10_update_vce_dpm(hwmgr, false);
+		cgs_set_clockgating_state(hwmgr->device,
+				AMD_IP_BLOCK_TYPE_VCE,
+				AMD_CG_STATE_UNGATE);
+	}
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
index 91e25f942d90..769636a0c5b5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
@@ -389,6 +389,34 @@ static int polaris10_program_voting_clients(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int polaris10_clear_voting_clients(struct pp_hwmgr *hwmgr)
+{
+	/* Reset voting clients before disabling DPM */
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+			SCLK_PWRMGT_CNTL, RESET_SCLK_CNT, 1);
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+			SCLK_PWRMGT_CNTL, RESET_BUSY_CNT, 1);
+
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_0, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_1, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_2, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_3, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_4, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_5, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_6, 0);
+	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+			ixCG_FREQ_TRAN_VOTING_7, 0);
+
+	return 0;
+}
+
 /**
 * Get the location of various tables inside the FW image.
 *
@@ -515,6 +543,11 @@ static int polaris10_copy_and_switch_arb_sets(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
+static int polaris10_reset_to_default(struct pp_hwmgr *hwmgr)
+{
+	return smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_ResetToDefaults);
+}
+
 /**
 * Initial switch from ARB F0->F1
 *
@@ -528,6 +561,21 @@ static int polaris10_initial_switch_from_arbf0_to_f1(struct pp_hwmgr *hwmgr)
 			MC_CG_ARB_FREQ_F0, MC_CG_ARB_FREQ_F1);
 }
 
+static int polaris10_force_switch_to_arbf0(struct pp_hwmgr *hwmgr)
+{
+	uint32_t tmp;
+
+	tmp = (cgs_read_ind_register(hwmgr->device,
+			CGS_IND_REG__SMC, ixSMC_SCRATCH9) &
+			0x0000ff00) >> 8;
+
+	if (tmp == MC_CG_ARB_FREQ_F0)
+		return 0;
+
+	return polaris10_copy_and_switch_arb_sets(hwmgr,
+			tmp, MC_CG_ARB_FREQ_F0);
+}
+
 static int polaris10_setup_default_pcie_table(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
@@ -1356,9 +1404,9 @@ static int polaris10_populate_all_memory_levels(struct pp_hwmgr *hwmgr)
 			return result;
 	}
 
-	/* in order to prevent MC activity from stutter mode to push DPM up.
+	/* In order to prevent MC activity from stutter mode to push DPM up,
 	 * the UVD change complements this by putting the MCLK in
-	 * a higher state by default such that we are not effected by
+	 * a higher state by default such that we are not affected by
 	 * up threshold or and MCLK DPM latency.
 	 */
 	levels[0].ActivityLevel = 0x1f;
@@ -1425,7 +1473,7 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 
 	/* Get MinVoltage and Frequency from DPM0,
 	 * already converted to SMC_UL */
-	sclk_frequency = data->dpm_table.sclk_table.dpm_levels[0].value;
+	sclk_frequency = data->vbios_boot_state.sclk_bootup_value;
 	result = polaris10_get_dependency_volt_by_clk(hwmgr,
 			table_info->vdd_dep_on_sclk,
 			sclk_frequency,
@@ -1461,8 +1509,7 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 
 
 	/* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */
-	table->MemoryACPILevel.MclkFrequency =
-			data->dpm_table.mclk_table.dpm_levels[0].value;
+	table->MemoryACPILevel.MclkFrequency = data->vbios_boot_state.mclk_bootup_value;
 	result = polaris10_get_dependency_volt_by_clk(hwmgr,
 			table_info->vdd_dep_on_mclk,
 			table->MemoryACPILevel.MclkFrequency,
@@ -1780,7 +1827,7 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 {
 	uint32_t ro, efuse, volt_without_cks, volt_with_cks, value, max, min;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
-	uint8_t i, stretch_amount, stretch_amount2, volt_offset = 0;
+	uint8_t i, stretch_amount, volt_offset = 0;
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
@@ -1831,11 +1878,8 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 
 	data->smc_state_table.LdoRefSel = (table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ? table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 6;
 	/* Populate CKS Lookup Table */
-	if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5)
-		stretch_amount2 = 0;
-	else if (stretch_amount == 3 || stretch_amount == 4)
-		stretch_amount2 = 1;
-	else {
+	if (stretch_amount != 1 && stretch_amount != 2 && stretch_amount != 3 &&
+			stretch_amount != 4 && stretch_amount != 5) {
 		phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
 				PHM_PlatformCaps_ClockStretcher);
 		PP_ASSERT_WITH_CODE(false,
@@ -1890,9 +1934,8 @@ static int polaris10_populate_vr_config(struct pp_hwmgr *hwmgr,
 	if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->mvdd_control) {
 		config = VR_SVI2_PLANE_2;
 		table->VRConfig |= (config << VRCONF_MVDD_SHIFT);
-	} else if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->mvdd_control) {
-		config = VR_SMIO_PATTERN_2;
-		table->VRConfig |= (config << VRCONF_MVDD_SHIFT);
+		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, data->soft_regs_start +
+			offsetof(SMU74_SoftRegisters, AllowMvddSwitch), 0x1);
 	} else {
 		config = VR_STATIC_VOLTAGE;
 		table->VRConfig |= (config << VRCONF_MVDD_SHIFT);
@@ -2262,6 +2305,17 @@ static int polaris10_enable_ulv(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int polaris10_disable_ulv(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	struct polaris10_ulv_parm *ulv = &(data->ulv);
+
+	if (ulv->ulv_supported)
+		return smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_DisableULV);
+
+	return 0;
+}
+
 static int polaris10_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr)
 {
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
@@ -2282,6 +2336,21 @@ static int polaris10_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int polaris10_disable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr)
+{
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_SclkDeepSleep)) {
+		if (smum_send_msg_to_smc(hwmgr->smumgr,
+				PPSMC_MSG_MASTER_DeepSleep_OFF)) {
+			PP_ASSERT_WITH_CODE(false,
+					"Attempt to disable Master Deep Sleep switch failed!",
+					return -1);
+		}
+	}
+
+	return 0;
+}
+
 static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
@@ -2379,6 +2448,58 @@ static int polaris10_start_dpm(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int polaris10_disable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+
+	/* disable SCLK dpm */
+	if (!data->sclk_dpm_key_disabled)
+		PP_ASSERT_WITH_CODE(
+				(smum_send_msg_to_smc(hwmgr->smumgr,
+						PPSMC_MSG_DPM_Disable) == 0),
+				"Failed to disable SCLK DPM!",
+				return -1);
+
+	/* disable MCLK dpm */
+	if (!data->mclk_dpm_key_disabled) {
+		PP_ASSERT_WITH_CODE(
+				(smum_send_msg_to_smc(hwmgr->smumgr,
+						PPSMC_MSG_MCLKDPM_Disable) == 0),
+				"Failed to disable MCLK DPM!",
+				return -1);
+	}
+
+	return 0;
+}
+
+static int polaris10_stop_dpm(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+
+	/* disable general power management */
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, GENERAL_PWRMGT,
+			GLOBAL_PWRMGT_EN, 0);
+	/* disable sclk deep sleep */
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, SCLK_PWRMGT_CNTL,
+			DYNAMIC_PM_EN, 0);
+
+	/* disable PCIE dpm */
+	if (!data->pcie_dpm_key_disabled) {
+		PP_ASSERT_WITH_CODE(
+				(smum_send_msg_to_smc(hwmgr->smumgr,
+						PPSMC_MSG_PCIeDPM_Disable) == 0),
+				"Failed to disable pcie DPM during DPM Stop Function!",
+				return -1);
+	}
+
+	if (polaris10_disable_sclk_mclk_dpm(hwmgr)) {
+		printk(KERN_ERR "Failed to disable Sclk DPM and Mclk DPM!");
+		return -1;
+	}
+
+	return 0;
+}
+
 static void polaris10_set_dpm_event_sources(struct pp_hwmgr *hwmgr, uint32_t sources)
 {
 	bool protection;
@@ -2436,6 +2557,23 @@ static int polaris10_enable_thermal_auto_throttle(struct pp_hwmgr *hwmgr)
 	return polaris10_enable_auto_throttle_source(hwmgr, PHM_AutoThrottleSource_Thermal);
 }
 
+static int polaris10_disable_auto_throttle_source(struct pp_hwmgr *hwmgr,
+		PHM_AutoThrottleSource source)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+
+	if (data->active_auto_throttle_sources & (1 << source)) {
+		data->active_auto_throttle_sources &= ~(1 << source);
+		polaris10_set_dpm_event_sources(hwmgr, data->active_auto_throttle_sources);
+	}
+	return 0;
+}
+
+static int polaris10_disable_thermal_auto_throttle(struct pp_hwmgr *hwmgr)
+{
+	return polaris10_disable_auto_throttle_source(hwmgr, PHM_AutoThrottleSource_Thermal);
+}
+
 int polaris10_pcie_performance_request(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
@@ -2530,6 +2668,10 @@ int polaris10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to enable deep sleep master switch!", result = tmp_result);
 
+	tmp_result = polaris10_enable_didt_config(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to enable deep sleep master switch!", result = tmp_result);
+
 	tmp_result = polaris10_start_dpm(hwmgr);
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to start DPM!", result = tmp_result);
@@ -2559,8 +2701,60 @@ int polaris10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 
 int polaris10_disable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
+	int tmp_result, result = 0;
 
-	return 0;
+	tmp_result = (polaris10_is_dpm_running(hwmgr)) ? 0 : -1;
+	PP_ASSERT_WITH_CODE(tmp_result == 0,
+			"DPM is not running right now, no need to disable DPM!",
+			return 0);
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_ThermalController))
+		PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+				GENERAL_PWRMGT, THERMAL_PROTECTION_DIS, 1);
+
+	tmp_result = polaris10_disable_power_containment(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to disable power containment!", result = tmp_result);
+
+	tmp_result = polaris10_disable_smc_cac(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to disable SMC CAC!", result = tmp_result);
+
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+			CG_SPLL_SPREAD_SPECTRUM, SSEN, 0);
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+			GENERAL_PWRMGT, DYN_SPREAD_SPECTRUM_EN, 0);
+
+	tmp_result = polaris10_disable_thermal_auto_throttle(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to disable thermal auto throttle!", result = tmp_result);
+
+	tmp_result = polaris10_stop_dpm(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to stop DPM!", result = tmp_result);
+
+	tmp_result = polaris10_disable_deep_sleep_master_switch(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to disable deep sleep master switch!", result = tmp_result);
+
+	tmp_result = polaris10_disable_ulv(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to disable ULV!", result = tmp_result);
+
+	tmp_result = polaris10_clear_voting_clients(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to clear voting clients!", result = tmp_result);
+
+	tmp_result = polaris10_reset_to_default(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to reset to default!", result = tmp_result);
+
+	tmp_result = polaris10_force_switch_to_arbf0(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to force to switch arbf0!", result = tmp_result);
+
+	return result;
 }
 
 int polaris10_reset_asic_tasks(struct pp_hwmgr *hwmgr)
@@ -2571,13 +2765,6 @@ int polaris10_reset_asic_tasks(struct pp_hwmgr *hwmgr)
 
 int polaris10_hwmgr_backend_fini(struct pp_hwmgr *hwmgr)
 {
-	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
-
-	if (data->soft_pp_table) {
-		kfree(data->soft_pp_table);
-		data->soft_pp_table = NULL;
-	}
-
 	return phm_hwmgr_backend_fini(hwmgr);
 }
 
@@ -2624,17 +2811,22 @@ int polaris10_set_features_platform_caps(struct pp_hwmgr *hwmgr)
 					PHM_PlatformCaps_DynamicUVDState);
 
 	/* power tune caps Assume disabled */
-	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 						PHM_PlatformCaps_SQRamping);
-	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 						PHM_PlatformCaps_DBRamping);
-	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 						PHM_PlatformCaps_TDRamping);
-	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 						PHM_PlatformCaps_TCPRamping);
 
-	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
-					PHM_PlatformCaps_PowerContainment);
+	if (hwmgr->powercontainment_enabled)
+		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+			    PHM_PlatformCaps_PowerContainment);
+	else
+		phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+			    PHM_PlatformCaps_PowerContainment);
+
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 							PHM_PlatformCaps_CAC);
 
@@ -2706,12 +2898,12 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr)
 				}
 			}
 
-
-			PP_ASSERT_WITH_CODE(0 == atomctrl_get_voltage_evv_on_sclk_ai(hwmgr,
-							VOLTAGE_TYPE_VDDC, sclk, vv_id, &vddc),
-						"Error retrieving EVV voltage value!",
-						continue);
-
+			if (atomctrl_get_voltage_evv_on_sclk_ai(hwmgr,
+						VOLTAGE_TYPE_VDDC,
+						sclk, vv_id, &vddc) != 0) {
+				printk(KERN_WARNING "failed to retrieving EVV voltage!\n");
+				continue;
+			}
 
 			/* need to make sure vddc is less than 2v or else, it could burn the ASIC.
 			 * real voltage level in unit of 0.01mv */
@@ -2968,13 +3160,19 @@ int polaris10_patch_voltage_workaround(struct pp_hwmgr *hwmgr)
 
 int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 {
-	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	struct polaris10_hwmgr *data;
 	struct pp_atomctrl_gpio_pin_assignment gpio_pin_assignment;
 	uint32_t temp_reg;
 	int result;
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 
+	data = kzalloc(sizeof(struct polaris10_hwmgr), GFP_KERNEL);
+	if (data == NULL)
+		return -ENOMEM;
+
+	hwmgr->backend = data;
+
 	data->dll_default_on = false;
 	data->sram_end = SMC_RAM_END;
 	data->mclk_dpm0_activity_target = 0xa;
@@ -3063,7 +3261,7 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	if (0 == result) {
 		struct cgs_system_info sys_info = {0};
 
-		data->is_tlu_enabled = 0;
+		data->is_tlu_enabled = false;
 
 		hwmgr->platform_descriptor.hardwareActivityPerformanceLevels =
 							POLARIS10_MAX_HARDWARE_POWERLEVELS;
@@ -3148,7 +3346,7 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 		sys_info.info_id = CGS_SYSTEM_INFO_PCIE_GEN_INFO;
 		result = cgs_query_system_info(hwmgr->device, &sys_info);
 		if (result)
-			data->pcie_gen_cap = 0x30007;
+			data->pcie_gen_cap = AMDGPU_DEFAULT_PCIE_GEN_MASK;
 		else
 			data->pcie_gen_cap = (uint32_t)sys_info.value;
 		if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
@@ -3157,7 +3355,7 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 		sys_info.info_id = CGS_SYSTEM_INFO_PCIE_MLW;
 		result = cgs_query_system_info(hwmgr->device, &sys_info);
 		if (result)
-			data->pcie_lane_cap = 0x2f0000;
+			data->pcie_lane_cap = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		else
 			data->pcie_lane_cap = (uint32_t)sys_info.value;
 
@@ -3446,6 +3644,7 @@ static int polaris10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				    hwmgr->platform_descriptor.platformCaps,
 				    PHM_PlatformCaps_DisableMclkSwitchingForFrameLock);
 
+
 	disable_mclk_switching = (1 < info.display_count) ||
 				    disable_mclk_switching_for_frame_lock;
 
@@ -3950,8 +4149,8 @@ static int polaris10_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if ((0 == data->sclk_dpm_key_disabled) &&
 		(data->need_update_smu7_dpm_table &
 			(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) {
-		PP_ASSERT_WITH_CODE(true == polaris10_is_dpm_running(hwmgr),
-				"Trying to freeze SCLK DPM when DPM is disabled",
+		PP_ASSERT_WITH_CODE(polaris10_is_dpm_running(hwmgr),
+				    "Trying to freeze SCLK DPM when DPM is disabled",
 				);
 		PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr,
 				PPSMC_MSG_SCLKDPM_FreezeLevel),
@@ -3962,8 +4161,8 @@ static int polaris10_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if ((0 == data->mclk_dpm_key_disabled) &&
 		(data->need_update_smu7_dpm_table &
 		 DPMTABLE_OD_UPDATE_MCLK)) {
-		PP_ASSERT_WITH_CODE(true == polaris10_is_dpm_running(hwmgr),
-				"Trying to freeze MCLK DPM when DPM is disabled",
+		PP_ASSERT_WITH_CODE(polaris10_is_dpm_running(hwmgr),
+				    "Trying to freeze MCLK DPM when DPM is disabled",
 				);
 		PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr,
 				PPSMC_MSG_MCLKDPM_FreezeLevel),
@@ -4123,7 +4322,6 @@ static int polaris10_trim_single_dpm_states(struct pp_hwmgr *hwmgr,
 static int polaris10_trim_dpm_states(struct pp_hwmgr *hwmgr,
 		const struct polaris10_power_state *polaris10_ps)
 {
-	int result = 0;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
 	uint32_t high_limit_count;
 
@@ -4143,7 +4341,7 @@ static int polaris10_trim_dpm_states(struct pp_hwmgr *hwmgr,
 			polaris10_ps->performance_levels[0].memory_clock,
 			polaris10_ps->performance_levels[high_limit_count].memory_clock);
 
-	return result;
+	return 0;
 }
 
 static int polaris10_generate_dpm_level_enable_mask(
@@ -4226,25 +4424,20 @@ int polaris10_update_uvd_dpm(struct pp_hwmgr *hwmgr, bool bgate)
 	return polaris10_enable_disable_uvd_dpm(hwmgr, !bgate);
 }
 
-static int polaris10_update_vce_dpm(struct pp_hwmgr *hwmgr, const void *input)
+int polaris10_update_vce_dpm(struct pp_hwmgr *hwmgr, bool bgate)
 {
-	const struct phm_set_power_state_input *states =
-			(const struct phm_set_power_state_input *)input;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
-	const struct polaris10_power_state *polaris10_nps =
-			cast_const_phw_polaris10_power_state(states->pnew_state);
-	const struct polaris10_power_state *polaris10_cps =
-			cast_const_phw_polaris10_power_state(states->pcurrent_state);
-
 	uint32_t mm_boot_level_offset, mm_boot_level_value;
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 
-	if (polaris10_nps->vce_clks.evclk > 0 &&
-	(polaris10_cps == NULL || polaris10_cps->vce_clks.evclk == 0)) {
-
-		data->smc_state_table.VceBootLevel =
+	if (!bgate) {
+		if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+						PHM_PlatformCaps_StablePState))
+			data->smc_state_table.VceBootLevel =
 				(uint8_t) (table_info->mm_dep_table->count - 1);
+		else
+			data->smc_state_table.VceBootLevel = 0;
 
 		mm_boot_level_offset = data->dpm_table_start +
 				offsetof(SMU74_Discrete_DpmTable, VceBootLevel);
@@ -4257,18 +4450,14 @@ static int polaris10_update_vce_dpm(struct pp_hwmgr *hwmgr, const void *input)
 		cgs_write_ind_register(hwmgr->device,
 				CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
 
-		if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_StablePState)) {
+		if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_StablePState))
 			smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
 					PPSMC_MSG_VCEDPM_SetEnabledMask,
 					(uint32_t)1 << data->smc_state_table.VceBootLevel);
-
-			polaris10_enable_disable_vce_dpm(hwmgr, true);
-		} else if (polaris10_nps->vce_clks.evclk == 0 &&
-				polaris10_cps != NULL &&
-				polaris10_cps->vce_clks.evclk > 0)
-			polaris10_enable_disable_vce_dpm(hwmgr, false);
 	}
 
+	polaris10_enable_disable_vce_dpm(hwmgr, !bgate);
+
 	return 0;
 }
 
@@ -4353,8 +4542,8 @@ static int polaris10_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 		(data->need_update_smu7_dpm_table &
 		(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) {
 
-		PP_ASSERT_WITH_CODE(true == polaris10_is_dpm_running(hwmgr),
-				"Trying to Unfreeze SCLK DPM when DPM is disabled",
+		PP_ASSERT_WITH_CODE(polaris10_is_dpm_running(hwmgr),
+				    "Trying to Unfreeze SCLK DPM when DPM is disabled",
 				);
 		PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr,
 				PPSMC_MSG_SCLKDPM_UnfreezeLevel),
@@ -4365,8 +4554,8 @@ static int polaris10_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if ((0 == data->mclk_dpm_key_disabled) &&
 		(data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) {
 
-		PP_ASSERT_WITH_CODE(true == polaris10_is_dpm_running(hwmgr),
-				"Trying to Unfreeze MCLK DPM when DPM is disabled",
+		PP_ASSERT_WITH_CODE(polaris10_is_dpm_running(hwmgr),
+				    "Trying to Unfreeze MCLK DPM when DPM is disabled",
 				);
 		PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr,
 				PPSMC_MSG_SCLKDPM_UnfreezeLevel),
@@ -4422,6 +4611,8 @@ static int polaris10_notify_smc_display(struct pp_hwmgr *hwmgr)
 	return (smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay) == 0) ?  0 : -EINVAL;
 }
 
+
+
 static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *input)
 {
 	int tmp_result, result = 0;
@@ -4455,11 +4646,6 @@ static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *i
 			"Failed to generate DPM level enabled mask!",
 			result = tmp_result);
 
-	tmp_result = polaris10_update_vce_dpm(hwmgr, input);
-	PP_ASSERT_WITH_CODE((0 == tmp_result),
-			"Failed to update VCE DPM!",
-			result = tmp_result);
-
 	tmp_result = polaris10_update_sclk_threshold(hwmgr);
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to update SCLK threshold!",
@@ -4530,6 +4716,7 @@ int polaris10_notify_smc_display_config_after_ps_adjustment(struct pp_hwmgr *hwm
 	if (num_active_displays > 1)  /* to do && (pHwMgr->pPECI->displayConfiguration.bMultiMonitorInSync != TRUE)) */
 		polaris10_notify_smc_display_change(hwmgr, false);
 
+
 	return 0;
 }
 
@@ -4579,6 +4766,7 @@ int polaris10_program_display_gap(struct pp_hwmgr *hwmgr)
 
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, data->soft_regs_start + offsetof(SMU74_SoftRegisters, VBlankTimeout), (frame_time_in_us - pre_vbi_time_in_us));
 
+
 	return 0;
 }
 
@@ -4820,42 +5008,6 @@ int polaris10_setup_asic_task(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
-static int polaris10_get_pp_table(struct pp_hwmgr *hwmgr, char **table)
-{
-	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
-
-	if (!data->soft_pp_table) {
-		data->soft_pp_table = kmemdup(hwmgr->soft_pp_table,
-					      hwmgr->soft_pp_table_size,
-					      GFP_KERNEL);
-		if (!data->soft_pp_table)
-			return -ENOMEM;
-	}
-
-	*table = (char *)&data->soft_pp_table;
-
-	return hwmgr->soft_pp_table_size;
-}
-
-static int polaris10_set_pp_table(struct pp_hwmgr *hwmgr, const char *buf, size_t size)
-{
-	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
-
-	if (!data->soft_pp_table) {
-		data->soft_pp_table = kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL);
-		if (!data->soft_pp_table)
-			return -ENOMEM;
-	}
-
-	memcpy(data->soft_pp_table, buf, size);
-
-	hwmgr->soft_pp_table = data->soft_pp_table;
-
-	/* TODO: re-init powerplay to implement modified pptable */
-
-	return 0;
-}
-
 static int polaris10_force_clock_level(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, uint32_t mask)
 {
@@ -4998,6 +5150,89 @@ static int polaris10_get_fan_control_mode(struct pp_hwmgr *hwmgr)
 				CG_FDO_CTRL2, FDO_PWM_MODE);
 }
 
+static int polaris10_get_sclk_od(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	struct polaris10_single_dpm_table *sclk_table = &(data->dpm_table.sclk_table);
+	struct polaris10_single_dpm_table *golden_sclk_table =
+			&(data->golden_dpm_table.sclk_table);
+	int value;
+
+	value = (sclk_table->dpm_levels[sclk_table->count - 1].value -
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value) *
+			100 /
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value;
+
+	return value;
+}
+
+static int polaris10_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	struct polaris10_single_dpm_table *golden_sclk_table =
+			&(data->golden_dpm_table.sclk_table);
+	struct pp_power_state  *ps;
+	struct polaris10_power_state  *polaris10_ps;
+
+	if (value > 20)
+		value = 20;
+
+	ps = hwmgr->request_ps;
+
+	if (ps == NULL)
+		return -EINVAL;
+
+	polaris10_ps = cast_phw_polaris10_power_state(&ps->hardware);
+
+	polaris10_ps->performance_levels[polaris10_ps->performance_level_count - 1].engine_clock =
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value *
+			value / 100 +
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value;
+
+	return 0;
+}
+
+static int polaris10_get_mclk_od(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	struct polaris10_single_dpm_table *mclk_table = &(data->dpm_table.mclk_table);
+	struct polaris10_single_dpm_table *golden_mclk_table =
+			&(data->golden_dpm_table.mclk_table);
+	int value;
+
+	value = (mclk_table->dpm_levels[mclk_table->count - 1].value -
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value) *
+			100 /
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value;
+
+	return value;
+}
+
+static int polaris10_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	struct polaris10_single_dpm_table *golden_mclk_table =
+			&(data->golden_dpm_table.mclk_table);
+	struct pp_power_state  *ps;
+	struct polaris10_power_state  *polaris10_ps;
+
+	if (value > 20)
+		value = 20;
+
+	ps = hwmgr->request_ps;
+
+	if (ps == NULL)
+		return -EINVAL;
+
+	polaris10_ps = cast_phw_polaris10_power_state(&ps->hardware);
+
+	polaris10_ps->performance_levels[polaris10_ps->performance_level_count - 1].memory_clock =
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value *
+			value / 100 +
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value;
+
+	return 0;
+}
 static const struct pp_hwmgr_func polaris10_hwmgr_funcs = {
 	.backend_init = &polaris10_hwmgr_backend_init,
 	.backend_fini = &polaris10_hwmgr_backend_fini,
@@ -5036,22 +5271,17 @@ static const struct pp_hwmgr_func polaris10_hwmgr_funcs = {
 	.check_states_equal = polaris10_check_states_equal,
 	.set_fan_control_mode = polaris10_set_fan_control_mode,
 	.get_fan_control_mode = polaris10_get_fan_control_mode,
-	.get_pp_table = polaris10_get_pp_table,
-	.set_pp_table = polaris10_set_pp_table,
 	.force_clock_level = polaris10_force_clock_level,
 	.print_clock_levels = polaris10_print_clock_levels,
 	.enable_per_cu_power_gating = polaris10_phm_enable_per_cu_power_gating,
+	.get_sclk_od = polaris10_get_sclk_od,
+	.set_sclk_od = polaris10_set_sclk_od,
+	.get_mclk_od = polaris10_get_mclk_od,
+	.set_mclk_od = polaris10_set_mclk_od,
 };
 
 int polaris10_hwmgr_init(struct pp_hwmgr *hwmgr)
 {
-	struct polaris10_hwmgr  *data;
-
-	data = kzalloc (sizeof(struct polaris10_hwmgr), GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
-
-	hwmgr->backend = data;
 	hwmgr->hwmgr_func = &polaris10_hwmgr_funcs;
 	hwmgr->pptable_func = &tonga_pptable_funcs;
 	pp_polaris10_thermal_initialize(hwmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
index afc3434822d1..33c33947e827 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
@@ -309,10 +309,6 @@ struct polaris10_hwmgr {
 	uint32_t                           up_hyst;
 	uint32_t disable_dpm_mask;
 	bool apply_optimized_settings;
-
-	/* soft pptable for re-uploading into smu */
-	void *soft_pp_table;
-
 	uint32_t                              avfs_vdroop_override_setting;
 	bool                                  apply_avfs_cks_off_voltage;
 	uint32_t                              frame_time_x2;
@@ -356,6 +352,6 @@ int polaris10_hwmgr_init(struct pp_hwmgr *hwmgr);
 int polaris10_update_uvd_dpm(struct pp_hwmgr *hwmgr, bool bgate);
 int polaris10_update_samu_dpm(struct pp_hwmgr *hwmgr, bool bgate);
 int polaris10_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable);
-
+int polaris10_update_vce_dpm(struct pp_hwmgr *hwmgr, bool bgate);
 #endif
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
index ae96f14b827c..b9cb240a135d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
@@ -28,10 +28,360 @@
 #include "polaris10_smumgr.h"
 #include "smu74_discrete.h"
 #include "pp_debug.h"
+#include "gca/gfx_8_0_d.h"
+#include "gca/gfx_8_0_sh_mask.h"
+#include "oss/oss_3_0_sh_mask.h"
 
 #define VOLTAGE_SCALE  4
 #define POWERTUNE_DEFAULT_SET_MAX    1
 
+uint32_t DIDTBlock_Info = SQ_IR_MASK | TCP_IR_MASK | TD_PCC_MASK;
+
+struct polaris10_pt_config_reg GCCACConfig_Polaris10[] = {
+/* ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ *      Offset                             Mask                                                Shift                                               Value       Type
+ * ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ */
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00060013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00860013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01060013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01860013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02060013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02860013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x03060013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x03860013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x04060013, POLARIS10_CONFIGREG_GC_CAC_IND },
+
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x000E0013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x008E0013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x010E0013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x018E0013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x020E0013, POLARIS10_CONFIGREG_GC_CAC_IND },
+
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00100013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00900013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01100013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01900013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02100013, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02900013, POLARIS10_CONFIGREG_GC_CAC_IND },
+
+	{   0xFFFFFFFF  }
+};
+
+struct polaris10_pt_config_reg GCCACConfig_Polaris11[] = {
+/* ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ *      Offset                             Mask                                                Shift                                               Value       Type
+ * ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ */
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00060011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00860011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01060011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01860011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02060011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02860011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x03060011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x03860011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x04060011, POLARIS10_CONFIGREG_GC_CAC_IND },
+
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x000E0011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x008E0011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x010E0011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x018E0011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x020E0011, POLARIS10_CONFIGREG_GC_CAC_IND },
+
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00100011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x00900011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01100011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x01900011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02100011, POLARIS10_CONFIGREG_GC_CAC_IND },
+	{   ixGC_CAC_CNTL,                     0xFFFFFFFF,                                         0,                                                  0x02900011, POLARIS10_CONFIGREG_GC_CAC_IND },
+
+	{   0xFFFFFFFF  }
+};
+
+struct polaris10_pt_config_reg DIDTConfig_Polaris10[] = {
+/* ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ *      Offset                             Mask                                                Shift                                               Value       Type
+ * ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ */
+	{   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT0_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT0__SHIFT,                  0x0073,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT1_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT1__SHIFT,                  0x00ab,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT2_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT2__SHIFT,                  0x0084,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT3_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT3__SHIFT,                  0x005a,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT4_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT4__SHIFT,                  0x0067,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT5_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT5__SHIFT,                  0x0084,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT6_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT6__SHIFT,                  0x0027,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT7_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT7__SHIFT,                  0x0046,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT8_MASK,                   DIDT_SQ_WEIGHT8_11__WEIGHT8__SHIFT,                 0x00aa,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT9_MASK,                   DIDT_SQ_WEIGHT8_11__WEIGHT9__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT10_MASK,                  DIDT_SQ_WEIGHT8_11__WEIGHT10__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT11_MASK,                  DIDT_SQ_WEIGHT8_11__WEIGHT11__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL1,                   DIDT_SQ_CTRL1__MIN_POWER_MASK,                      DIDT_SQ_CTRL1__MIN_POWER__SHIFT,                    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL1,                   DIDT_SQ_CTRL1__MAX_POWER_MASK,                      DIDT_SQ_CTRL1__MAX_POWER__SHIFT,                    0xffff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL_OCP,                DIDT_SQ_CTRL_OCP__UNUSED_0_MASK,                    DIDT_SQ_CTRL_OCP__UNUSED_0__SHIFT,                  0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL_OCP,                DIDT_SQ_CTRL_OCP__OCP_MAX_POWER_MASK,               DIDT_SQ_CTRL_OCP__OCP_MAX_POWER__SHIFT,             0xffff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__MAX_POWER_DELTA_MASK,                DIDT_SQ_CTRL2__MAX_POWER_DELTA__SHIFT,              0x3853,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_0_MASK,                       DIDT_SQ_CTRL2__UNUSED_0__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,       DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,     0x005a,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_1_MASK,                       DIDT_SQ_CTRL2__UNUSED_1__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,       DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_2_MASK,                       DIDT_SQ_CTRL2__UNUSED_2__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,    DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT,  0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,       DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,     0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,       DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,     0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,   DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x0ebb,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__UNUSED_0_MASK,                  DIDT_SQ_STALL_CTRL__UNUSED_0__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,       DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,     0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,       DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,     0x3853,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,       DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,     0x3153,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK,                 DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT,               0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_SQ_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__PHASE_OFFSET_MASK,                   DIDT_SQ_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0010,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0010,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__UNUSED_0_MASK,                       DIDT_SQ_CTRL0__UNUSED_0__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT0_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT0__SHIFT,                  0x000a,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT1_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT1__SHIFT,                  0x0010,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT2_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT2__SHIFT,                  0x0017,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT3_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT3__SHIFT,                  0x002f,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT4_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT4__SHIFT,                  0x0046,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT5_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT5__SHIFT,                  0x005d,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT6_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT6__SHIFT,                  0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT7_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT7__SHIFT,                  0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL1,                   DIDT_TD_CTRL1__MIN_POWER_MASK,                      DIDT_TD_CTRL1__MIN_POWER__SHIFT,                    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL1,                   DIDT_TD_CTRL1__MAX_POWER_MASK,                      DIDT_TD_CTRL1__MAX_POWER__SHIFT,                    0xffff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL_OCP,                DIDT_TD_CTRL_OCP__UNUSED_0_MASK,                    DIDT_TD_CTRL_OCP__UNUSED_0__SHIFT,                  0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL_OCP,                DIDT_TD_CTRL_OCP__OCP_MAX_POWER_MASK,               DIDT_TD_CTRL_OCP__OCP_MAX_POWER__SHIFT,             0x00ff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__MAX_POWER_DELTA_MASK,                DIDT_TD_CTRL2__MAX_POWER_DELTA__SHIFT,              0x3fff,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__UNUSED_0_MASK,                       DIDT_TD_CTRL2__UNUSED_0__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,       DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,     0x000f,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__UNUSED_1_MASK,                       DIDT_TD_CTRL2__UNUSED_1__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,       DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__UNUSED_2_MASK,                       DIDT_TD_CTRL2__UNUSED_2__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,    DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT,  0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,       DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,     0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,       DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,     0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,   DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__UNUSED_0_MASK,                  DIDT_TD_STALL_CTRL__UNUSED_0__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,       DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,       DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,     0x0dde,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,       DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,     0x0dde,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__UNUSED_0_MASK,                 DIDT_TD_TUNING_CTRL__UNUSED_0__SHIFT,               0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_TD_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_TD_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__PHASE_OFFSET_MASK,                   DIDT_TD_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_TD_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0009,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0009,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__UNUSED_0_MASK,                       DIDT_TD_CTRL0__UNUSED_0__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT0_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT0__SHIFT,                 0x0004,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT1_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT1__SHIFT,                 0x0037,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT2_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT2__SHIFT,                 0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT3_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT3__SHIFT,                 0x00ff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT4_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT4__SHIFT,                 0x0054,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT5_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT5__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT6_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT6__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT7_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT7__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_CTRL1,                  DIDT_TCP_CTRL1__MIN_POWER_MASK,                     DIDT_TCP_CTRL1__MIN_POWER__SHIFT,                   0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL1,                  DIDT_TCP_CTRL1__MAX_POWER_MASK,                     DIDT_TCP_CTRL1__MAX_POWER__SHIFT,                   0xffff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_CTRL_OCP,               DIDT_TCP_CTRL_OCP__UNUSED_0_MASK,                   DIDT_TCP_CTRL_OCP__UNUSED_0__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL_OCP,               DIDT_TCP_CTRL_OCP__OCP_MAX_POWER_MASK,              DIDT_TCP_CTRL_OCP__OCP_MAX_POWER__SHIFT,            0xffff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__MAX_POWER_DELTA_MASK,               DIDT_TCP_CTRL2__MAX_POWER_DELTA__SHIFT,             0x3dde,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__UNUSED_0_MASK,                      DIDT_TCP_CTRL2__UNUSED_0__SHIFT,                    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,      DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,    0x0032,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__UNUSED_1_MASK,                      DIDT_TCP_CTRL2__UNUSED_1__SHIFT,                    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,      DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__UNUSED_2_MASK,                      DIDT_TCP_CTRL2__UNUSED_2__SHIFT,                    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,   DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,      DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,    0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,      DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,    0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,  DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__UNUSED_0_MASK,                 DIDT_TCP_STALL_CTRL__UNUSED_0__SHIFT,               0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,      DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,    0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,      DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,    0x3dde,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,      DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,    0x3dde,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__UNUSED_0_MASK,                DIDT_TCP_TUNING_CTRL__UNUSED_0__SHIFT,              0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_TCP_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_TCP_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__PHASE_OFFSET_MASK,                   DIDT_TCP_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_TCP_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0010,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0010,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__UNUSED_0_MASK,                       DIDT_TCP_CTRL0__UNUSED_0__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   0xFFFFFFFF  }
+};
+
+struct polaris10_pt_config_reg DIDTConfig_Polaris11[] = {
+/* ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ *      Offset                             Mask                                                Shift                                               Value       Type
+ * ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ */
+	{   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT0_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT0__SHIFT,                  0x0073,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT1_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT1__SHIFT,                  0x00ab,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT2_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT2__SHIFT,                  0x0084,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT0_3,               DIDT_SQ_WEIGHT0_3__WEIGHT3_MASK,                    DIDT_SQ_WEIGHT0_3__WEIGHT3__SHIFT,                  0x005a,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT4_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT4__SHIFT,                  0x0067,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT5_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT5__SHIFT,                  0x0084,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT6_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT6__SHIFT,                  0x0027,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT4_7,               DIDT_SQ_WEIGHT4_7__WEIGHT7_MASK,                    DIDT_SQ_WEIGHT4_7__WEIGHT7__SHIFT,                  0x0046,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT8_MASK,                   DIDT_SQ_WEIGHT8_11__WEIGHT8__SHIFT,                 0x00aa,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT9_MASK,                   DIDT_SQ_WEIGHT8_11__WEIGHT9__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT10_MASK,                  DIDT_SQ_WEIGHT8_11__WEIGHT10__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_WEIGHT8_11,              DIDT_SQ_WEIGHT8_11__WEIGHT11_MASK,                  DIDT_SQ_WEIGHT8_11__WEIGHT11__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL1,                   DIDT_SQ_CTRL1__MIN_POWER_MASK,                      DIDT_SQ_CTRL1__MIN_POWER__SHIFT,                    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL1,                   DIDT_SQ_CTRL1__MAX_POWER_MASK,                      DIDT_SQ_CTRL1__MAX_POWER__SHIFT,                    0xffff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL_OCP,                DIDT_SQ_CTRL_OCP__UNUSED_0_MASK,                    DIDT_SQ_CTRL_OCP__UNUSED_0__SHIFT,                  0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL_OCP,                DIDT_SQ_CTRL_OCP__OCP_MAX_POWER_MASK,               DIDT_SQ_CTRL_OCP__OCP_MAX_POWER__SHIFT,             0xffff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__MAX_POWER_DELTA_MASK,                DIDT_SQ_CTRL2__MAX_POWER_DELTA__SHIFT,              0x3853,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_0_MASK,                       DIDT_SQ_CTRL2__UNUSED_0__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,       DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,     0x005a,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_1_MASK,                       DIDT_SQ_CTRL2__UNUSED_1__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,       DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_2_MASK,                       DIDT_SQ_CTRL2__UNUSED_2__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,    DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT,  0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,       DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,     0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,       DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,     0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,   DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x0ebb,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__UNUSED_0_MASK,                  DIDT_SQ_STALL_CTRL__UNUSED_0__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,       DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,     0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,       DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,     0x3853,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,       DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,     0x3153,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK,                 DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT,               0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_SQ_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__PHASE_OFFSET_MASK,                   DIDT_SQ_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0010,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0010,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__UNUSED_0_MASK,                       DIDT_SQ_CTRL0__UNUSED_0__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT0_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT0__SHIFT,                  0x000a,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT1_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT1__SHIFT,                  0x0010,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT2_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT2__SHIFT,                  0x0017,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT3_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT3__SHIFT,                  0x002f,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT4_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT4__SHIFT,                  0x0046,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT5_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT5__SHIFT,                  0x005d,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT6_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT6__SHIFT,                  0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT7_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT7__SHIFT,                  0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL1,                   DIDT_TD_CTRL1__MIN_POWER_MASK,                      DIDT_TD_CTRL1__MIN_POWER__SHIFT,                    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL1,                   DIDT_TD_CTRL1__MAX_POWER_MASK,                      DIDT_TD_CTRL1__MAX_POWER__SHIFT,                    0xffff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL_OCP,                DIDT_TD_CTRL_OCP__UNUSED_0_MASK,                    DIDT_TD_CTRL_OCP__UNUSED_0__SHIFT,                  0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL_OCP,                DIDT_TD_CTRL_OCP__OCP_MAX_POWER_MASK,               DIDT_TD_CTRL_OCP__OCP_MAX_POWER__SHIFT,             0x00ff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__MAX_POWER_DELTA_MASK,                DIDT_TD_CTRL2__MAX_POWER_DELTA__SHIFT,              0x3fff,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__UNUSED_0_MASK,                       DIDT_TD_CTRL2__UNUSED_0__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,       DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,     0x000f,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__UNUSED_1_MASK,                       DIDT_TD_CTRL2__UNUSED_1__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,       DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__UNUSED_2_MASK,                       DIDT_TD_CTRL2__UNUSED_2__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,    DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT,  0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,       DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,     0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,       DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,     0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,   DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_STALL_CTRL,              DIDT_TD_STALL_CTRL__UNUSED_0_MASK,                  DIDT_TD_STALL_CTRL__UNUSED_0__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,       DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,       DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,     0x0dde,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,       DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,     0x0dde,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_TUNING_CTRL,             DIDT_TD_TUNING_CTRL__UNUSED_0_MASK,                 DIDT_TD_TUNING_CTRL__UNUSED_0__SHIFT,               0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_TD_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_TD_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__PHASE_OFFSET_MASK,                   DIDT_TD_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_TD_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0008,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0008,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL0,                   DIDT_TD_CTRL0__UNUSED_0_MASK,                       DIDT_TD_CTRL0__UNUSED_0__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT0_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT0__SHIFT,                 0x0004,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT1_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT1__SHIFT,                 0x0037,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT2_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT2__SHIFT,                 0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT0_3,              DIDT_TCP_WEIGHT0_3__WEIGHT3_MASK,                   DIDT_TCP_WEIGHT0_3__WEIGHT3__SHIFT,                 0x00ff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT4_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT4__SHIFT,                 0x0054,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT5_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT5__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT6_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT6__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_WEIGHT4_7,              DIDT_TCP_WEIGHT4_7__WEIGHT7_MASK,                   DIDT_TCP_WEIGHT4_7__WEIGHT7__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_CTRL1,                  DIDT_TCP_CTRL1__MIN_POWER_MASK,                     DIDT_TCP_CTRL1__MIN_POWER__SHIFT,                   0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL1,                  DIDT_TCP_CTRL1__MAX_POWER_MASK,                     DIDT_TCP_CTRL1__MAX_POWER__SHIFT,                   0xffff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_CTRL_OCP,               DIDT_TCP_CTRL_OCP__UNUSED_0_MASK,                   DIDT_TCP_CTRL_OCP__UNUSED_0__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL_OCP,               DIDT_TCP_CTRL_OCP__OCP_MAX_POWER_MASK,              DIDT_TCP_CTRL_OCP__OCP_MAX_POWER__SHIFT,            0xffff,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__MAX_POWER_DELTA_MASK,               DIDT_TCP_CTRL2__MAX_POWER_DELTA__SHIFT,             0x3dde,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__UNUSED_0_MASK,                      DIDT_TCP_CTRL2__UNUSED_0__SHIFT,                    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,      DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,    0x0032,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__UNUSED_1_MASK,                      DIDT_TCP_CTRL2__UNUSED_1__SHIFT,                    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,      DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL2,                  DIDT_TCP_CTRL2__UNUSED_2_MASK,                      DIDT_TCP_CTRL2__UNUSED_2__SHIFT,                    0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,   DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,      DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,    0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,      DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,    0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,  DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_STALL_CTRL,             DIDT_TCP_STALL_CTRL__UNUSED_0_MASK,                 DIDT_TCP_STALL_CTRL__UNUSED_0__SHIFT,               0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,      DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,    0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,      DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,    0x3dde,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,      DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,    0x3dde,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_TUNING_CTRL,            DIDT_TCP_TUNING_CTRL__UNUSED_0_MASK,                DIDT_TCP_TUNING_CTRL__UNUSED_0__SHIFT,              0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_TCP_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_TCP_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__PHASE_OFFSET_MASK,                   DIDT_TCP_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_TCP_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0010,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0010,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TCP_CTRL0,                   DIDT_TCP_CTRL0__UNUSED_0_MASK,                       DIDT_TCP_CTRL0__UNUSED_0__SHIFT,                     0x0000,     POLARIS10_CONFIGREG_DIDT_IND },
+	{   0xFFFFFFFF  }
+};
+
 static const struct polaris10_pt_defaults polaris10_power_tune_data_set_array[POWERTUNE_DEFAULT_SET_MAX] = {
 	/* sviLoadLIneEn, SviLoadLineVddC, TDC_VDDC_ThrottleReleaseLimitPerc, TDC_MAWt,
 	 * TdcWaterfallCtl, DTEAmbientTempBase, DisplayCac, BAPM_TEMP_GRADIENT */
@@ -209,6 +559,187 @@ static int polaris10_min_max_vgnb_lpml_id_from_bapm_vddc(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int polaris10_enable_didt(struct pp_hwmgr *hwmgr, const bool enable)
+{
+
+	uint32_t en = enable ? 1 : 0;
+	int32_t result = 0;
+	uint32_t data;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SQRamping)) {
+		data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_SQ_CTRL0);
+		data &= ~DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK;
+		data |= ((en << DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT) & DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK);
+		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_SQ_CTRL0, data);
+		DIDTBlock_Info &= ~SQ_Enable_MASK;
+		DIDTBlock_Info |= en << SQ_Enable_SHIFT;
+	}
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DBRamping)) {
+		data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DB_CTRL0);
+		data &= ~DIDT_DB_CTRL0__DIDT_CTRL_EN_MASK;
+		data |= ((en << DIDT_DB_CTRL0__DIDT_CTRL_EN__SHIFT) & DIDT_DB_CTRL0__DIDT_CTRL_EN_MASK);
+		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DB_CTRL0, data);
+		DIDTBlock_Info &= ~DB_Enable_MASK;
+		DIDTBlock_Info |= en << DB_Enable_SHIFT;
+	}
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TDRamping)) {
+		data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TD_CTRL0);
+		data &= ~DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK;
+		data |= ((en << DIDT_TD_CTRL0__DIDT_CTRL_EN__SHIFT) & DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK);
+		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TD_CTRL0, data);
+		DIDTBlock_Info &= ~TD_Enable_MASK;
+		DIDTBlock_Info |= en << TD_Enable_SHIFT;
+	}
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TCPRamping)) {
+		data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TCP_CTRL0);
+		data &= ~DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK;
+		data |= ((en << DIDT_TCP_CTRL0__DIDT_CTRL_EN__SHIFT) & DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK);
+		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TCP_CTRL0, data);
+		DIDTBlock_Info &= ~TCP_Enable_MASK;
+		DIDTBlock_Info |= en << TCP_Enable_SHIFT;
+	}
+
+	if (enable)
+		result = smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, PPSMC_MSG_Didt_Block_Function, DIDTBlock_Info);
+
+	return result;
+}
+
+static int polaris10_program_pt_config_registers(struct pp_hwmgr *hwmgr,
+				struct polaris10_pt_config_reg *cac_config_regs)
+{
+	struct polaris10_pt_config_reg *config_regs = cac_config_regs;
+	uint32_t cache = 0;
+	uint32_t data = 0;
+
+	PP_ASSERT_WITH_CODE((config_regs != NULL), "Invalid config register table.", return -EINVAL);
+
+	while (config_regs->offset != 0xFFFFFFFF) {
+		if (config_regs->type == POLARIS10_CONFIGREG_CACHE)
+			cache |= ((config_regs->value << config_regs->shift) & config_regs->mask);
+		else {
+			switch (config_regs->type) {
+			case POLARIS10_CONFIGREG_SMC_IND:
+				data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, config_regs->offset);
+				break;
+
+			case POLARIS10_CONFIGREG_DIDT_IND:
+				data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, config_regs->offset);
+				break;
+
+			case POLARIS10_CONFIGREG_GC_CAC_IND:
+				data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG_GC_CAC, config_regs->offset);
+				break;
+
+			default:
+				data = cgs_read_register(hwmgr->device, config_regs->offset);
+				break;
+			}
+
+			data &= ~config_regs->mask;
+			data |= ((config_regs->value << config_regs->shift) & config_regs->mask);
+			data |= cache;
+
+			switch (config_regs->type) {
+			case POLARIS10_CONFIGREG_SMC_IND:
+				cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, config_regs->offset, data);
+				break;
+
+			case POLARIS10_CONFIGREG_DIDT_IND:
+				cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, config_regs->offset, data);
+				break;
+
+			case POLARIS10_CONFIGREG_GC_CAC_IND:
+				cgs_write_ind_register(hwmgr->device, CGS_IND_REG_GC_CAC, config_regs->offset, data);
+				break;
+
+			default:
+				cgs_write_register(hwmgr->device, config_regs->offset, data);
+				break;
+			}
+			cache = 0;
+		}
+
+		config_regs++;
+	}
+
+	return 0;
+}
+
+int polaris10_enable_didt_config(struct pp_hwmgr *hwmgr)
+{
+	int result;
+	uint32_t num_se = 0;
+	uint32_t count, value, value2;
+	struct cgs_system_info sys_info = {0};
+
+	sys_info.size = sizeof(struct cgs_system_info);
+	sys_info.info_id = CGS_SYSTEM_INFO_GFX_SE_INFO;
+	result = cgs_query_system_info(hwmgr->device, &sys_info);
+
+
+	if (result == 0)
+		num_se = sys_info.value;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SQRamping) ||
+		phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DBRamping) ||
+		phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TDRamping) ||
+		phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TCPRamping)) {
+
+		/* TO DO Pre DIDT disable clock gating */
+		value = 0;
+		value2 = cgs_read_register(hwmgr->device, mmGRBM_GFX_INDEX);
+		for (count = 0; count < num_se; count++) {
+			value = SYS_GRBM_GFX_INDEX_DATA__INSTANCE_BROADCAST_WRITES_MASK
+				| SYS_GRBM_GFX_INDEX_DATA__SH_BROADCAST_WRITES_MASK
+				| (count << SYS_GRBM_GFX_INDEX_DATA__SE_INDEX__SHIFT);
+			cgs_write_register(hwmgr->device, mmGRBM_GFX_INDEX, value);
+
+			if (hwmgr->chip_id == CHIP_POLARIS10) {
+				result = polaris10_program_pt_config_registers(hwmgr, GCCACConfig_Polaris10);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
+				result = polaris10_program_pt_config_registers(hwmgr, DIDTConfig_Polaris10);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
+			} else if (hwmgr->chip_id == CHIP_POLARIS11) {
+				result = polaris10_program_pt_config_registers(hwmgr, GCCACConfig_Polaris11);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
+				result = polaris10_program_pt_config_registers(hwmgr, DIDTConfig_Polaris11);
+				PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result);
+			}
+		}
+		cgs_write_register(hwmgr->device, mmGRBM_GFX_INDEX, value2);
+
+		result = polaris10_enable_didt(hwmgr, true);
+		PP_ASSERT_WITH_CODE((result == 0), "EnableDiDt failed.", return result);
+
+		/* TO DO Post DIDT enable clock gating */
+	}
+
+	return 0;
+}
+
+int polaris10_disable_didt_config(struct pp_hwmgr *hwmgr)
+{
+	int result;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SQRamping) ||
+		phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DBRamping) ||
+		phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TDRamping) ||
+		phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TCPRamping)) {
+		/* TO DO Pre DIDT disable clock gating */
+
+		result = polaris10_enable_didt(hwmgr, false);
+		PP_ASSERT_WITH_CODE((result == 0), "Post DIDT enable clock gating failed.", return result);
+		/* TO DO Post DIDT enable clock gating */
+	}
+
+	return 0;
+}
+
+
 static int polaris10_populate_bapm_vddc_base_leakage_sidd(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
@@ -312,6 +843,23 @@ int polaris10_enable_smc_cac(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+int polaris10_disable_smc_cac(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	int result = 0;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_CAC) && data->cac_enabled) {
+		int smc_result = smum_send_msg_to_smc(hwmgr->smumgr,
+				(uint16_t)(PPSMC_MSG_DisableCac));
+		PP_ASSERT_WITH_CODE((smc_result == 0),
+				"Failed to disable CAC in SMC.", result = -1);
+
+		data->cac_enabled = false;
+	}
+	return result;
+}
+
 int polaris10_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
@@ -373,6 +921,48 @@ int polaris10_enable_power_containment(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+int polaris10_disable_power_containment(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	int result = 0;
+
+	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_PowerContainment) &&
+			data->power_containment_features) {
+		int smc_result;
+
+		if (data->power_containment_features &
+				POWERCONTAINMENT_FEATURE_TDCLimit) {
+			smc_result = smum_send_msg_to_smc(hwmgr->smumgr,
+					(uint16_t)(PPSMC_MSG_TDCLimitDisable));
+			PP_ASSERT_WITH_CODE((smc_result == 0),
+					"Failed to disable TDCLimit in SMC.",
+					result = smc_result);
+		}
+
+		if (data->power_containment_features &
+				POWERCONTAINMENT_FEATURE_DTE) {
+			smc_result = smum_send_msg_to_smc(hwmgr->smumgr,
+					(uint16_t)(PPSMC_MSG_DisableDTE));
+			PP_ASSERT_WITH_CODE((smc_result == 0),
+					"Failed to disable DTE in SMC.",
+					result = smc_result);
+		}
+
+		if (data->power_containment_features &
+				POWERCONTAINMENT_FEATURE_PkgPwrLimit) {
+			smc_result = smum_send_msg_to_smc(hwmgr->smumgr,
+					(uint16_t)(PPSMC_MSG_PkgPwrLimitDisable));
+			PP_ASSERT_WITH_CODE((smc_result == 0),
+					"Failed to disable PkgPwrTracking in SMC.",
+					result = smc_result);
+		}
+		data->power_containment_features = 0;
+	}
+
+	return result;
+}
+
 int polaris10_power_control_set_level(struct pp_hwmgr *hwmgr)
 {
 	struct phm_ppt_v1_information *table_info =
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.h b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.h
index 68bc1cb6d40c..bc78e28f010d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.h
@@ -27,15 +27,37 @@ enum polaris10_pt_config_reg_type {
 	POLARIS10_CONFIGREG_MMR = 0,
 	POLARIS10_CONFIGREG_SMC_IND,
 	POLARIS10_CONFIGREG_DIDT_IND,
+	POLARIS10_CONFIGREG_GC_CAC_IND,
 	POLARIS10_CONFIGREG_CACHE,
 	POLARIS10_CONFIGREG_MAX
 };
 
+#define DIDT_SQ_CTRL0__UNUSED_0_MASK    0xfffc0000
+#define DIDT_SQ_CTRL0__UNUSED_0__SHIFT  0x12
+#define DIDT_TD_CTRL0__UNUSED_0_MASK    0xfffc0000
+#define DIDT_TD_CTRL0__UNUSED_0__SHIFT  0x12
+#define DIDT_TCP_CTRL0__UNUSED_0_MASK   0xfffc0000
+#define DIDT_TCP_CTRL0__UNUSED_0__SHIFT 0x12
+#define DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK                 0xc0000000
+#define DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT               0x0000001e
+#define DIDT_TD_TUNING_CTRL__UNUSED_0_MASK                 0xc0000000
+#define DIDT_TD_TUNING_CTRL__UNUSED_0__SHIFT               0x0000001e
+#define DIDT_TCP_TUNING_CTRL__UNUSED_0_MASK                0xc0000000
+#define DIDT_TCP_TUNING_CTRL__UNUSED_0__SHIFT              0x0000001e
+
 /* PowerContainment Features */
 #define POWERCONTAINMENT_FEATURE_DTE             0x00000001
 #define POWERCONTAINMENT_FEATURE_TDCLimit        0x00000002
 #define POWERCONTAINMENT_FEATURE_PkgPwrLimit     0x00000004
 
+#define ixGC_CAC_CNTL 0x0000
+#define ixDIDT_SQ_STALL_CTRL 0x0004
+#define  ixDIDT_SQ_TUNING_CTRL 0x0005
+#define ixDIDT_TD_STALL_CTRL 0x0044
+#define ixDIDT_TD_TUNING_CTRL 0x0045
+#define ixDIDT_TCP_STALL_CTRL 0x0064
+#define ixDIDT_TCP_TUNING_CTRL 0x0065
+
 struct polaris10_pt_config_reg {
 	uint32_t                           offset;
 	uint32_t                           mask;
@@ -62,9 +84,11 @@ void polaris10_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr);
 int polaris10_populate_bapm_parameters_in_dpm_table(struct pp_hwmgr *hwmgr);
 int polaris10_populate_pm_fuses(struct pp_hwmgr *hwmgr);
 int polaris10_enable_smc_cac(struct pp_hwmgr *hwmgr);
+int polaris10_disable_smc_cac(struct pp_hwmgr *hwmgr);
 int polaris10_enable_power_containment(struct pp_hwmgr *hwmgr);
+int polaris10_disable_power_containment(struct pp_hwmgr *hwmgr);
 int polaris10_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n);
 int polaris10_power_control_set_level(struct pp_hwmgr *hwmgr);
-
+int polaris10_enable_didt_config(struct pp_hwmgr *hwmgr);
 #endif  /* POLARIS10_POWERTUNE_H */
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
index a3c38bbd1e94..1944d289f846 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
@@ -66,7 +66,7 @@ int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise)
 	int result;
 	struct cgs_system_info info = {0};
 
-	if( 0 != acpi_atcs_notify_pcie_device_ready(device))
+	if (acpi_atcs_notify_pcie_device_ready(device))
 		return -EINVAL;
 
 	info.size = sizeof(struct cgs_system_info);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index 90b35c5c10a4..26f3e30d0fef 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -179,13 +179,12 @@ int atomctrl_set_engine_dram_timings_rv770(
 
 	/* They are both in 10KHz Units. */
 	engine_clock_parameters.ulTargetEngineClock =
-		(uint32_t) engine_clock & SET_CLOCK_FREQ_MASK;
-	engine_clock_parameters.ulTargetEngineClock |=
-		(COMPUTE_ENGINE_PLL_PARAM << 24);
+		cpu_to_le32((engine_clock & SET_CLOCK_FREQ_MASK) |
+			    ((COMPUTE_ENGINE_PLL_PARAM << 24)));
 
 	/* in 10 khz units.*/
 	engine_clock_parameters.sReserved.ulClock =
-		(uint32_t) memory_clock & SET_CLOCK_FREQ_MASK;
+		cpu_to_le32(memory_clock & SET_CLOCK_FREQ_MASK);
 	return cgs_atom_exec_cmd_table(hwmgr->device,
 			GetIndexIntoMasterTable(COMMAND, DynamicMemorySettings),
 			&engine_clock_parameters);
@@ -252,7 +251,7 @@ int atomctrl_get_memory_pll_dividers_si(
 	COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_1 mpll_parameters;
 	int result;
 
-	mpll_parameters.ulClock = (uint32_t) clock_value;
+	mpll_parameters.ulClock = cpu_to_le32(clock_value);
 	mpll_parameters.ucInputFlag = (uint8_t)((strobe_mode) ? 1 : 0);
 
 	result = cgs_atom_exec_cmd_table
@@ -262,9 +261,9 @@ int atomctrl_get_memory_pll_dividers_si(
 
 	if (0 == result) {
 		mpll_param->mpll_fb_divider.clk_frac =
-			mpll_parameters.ulFbDiv.usFbDivFrac;
+			le16_to_cpu(mpll_parameters.ulFbDiv.usFbDivFrac);
 		mpll_param->mpll_fb_divider.cl_kf =
-			mpll_parameters.ulFbDiv.usFbDiv;
+			le16_to_cpu(mpll_parameters.ulFbDiv.usFbDiv);
 		mpll_param->mpll_post_divider =
 			(uint32_t)mpll_parameters.ucPostDiv;
 		mpll_param->vco_mode =
@@ -300,7 +299,7 @@ int atomctrl_get_memory_pll_dividers_vi(struct pp_hwmgr *hwmgr,
 	COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_2 mpll_parameters;
 	int result;
 
-	mpll_parameters.ulClock.ulClock = (uint32_t)clock_value;
+	mpll_parameters.ulClock.ulClock = cpu_to_le32(clock_value);
 
 	result = cgs_atom_exec_cmd_table(hwmgr->device,
 			GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam),
@@ -320,7 +319,7 @@ int atomctrl_get_engine_pll_dividers_kong(struct pp_hwmgr *hwmgr,
 	COMPUTE_MEMORY_ENGINE_PLL_PARAMETERS_V4 pll_parameters;
 	int result;
 
-	pll_parameters.ulClock = clock_value;
+	pll_parameters.ulClock = cpu_to_le32(clock_value);
 
 	result = cgs_atom_exec_cmd_table
 		(hwmgr->device,
@@ -329,7 +328,7 @@ int atomctrl_get_engine_pll_dividers_kong(struct pp_hwmgr *hwmgr,
 
 	if (0 == result) {
 		dividers->pll_post_divider = pll_parameters.ucPostDiv;
-		dividers->real_clock = pll_parameters.ulClock;
+		dividers->real_clock = le32_to_cpu(pll_parameters.ulClock);
 	}
 
 	return result;
@@ -343,7 +342,7 @@ int atomctrl_get_engine_pll_dividers_vi(
 	COMPUTE_GPU_CLOCK_OUTPUT_PARAMETERS_V1_6 pll_patameters;
 	int result;
 
-	pll_patameters.ulClock.ulClock = clock_value;
+	pll_patameters.ulClock.ulClock = cpu_to_le32(clock_value);
 	pll_patameters.ulClock.ucPostDiv = COMPUTE_GPUCLK_INPUT_FLAG_SCLK;
 
 	result = cgs_atom_exec_cmd_table
@@ -355,12 +354,12 @@ int atomctrl_get_engine_pll_dividers_vi(
 		dividers->pll_post_divider =
 			pll_patameters.ulClock.ucPostDiv;
 		dividers->real_clock =
-			pll_patameters.ulClock.ulClock;
+			le32_to_cpu(pll_patameters.ulClock.ulClock);
 
 		dividers->ul_fb_div.ul_fb_div_frac =
-			pll_patameters.ulFbDiv.usFbDivFrac;
+			le16_to_cpu(pll_patameters.ulFbDiv.usFbDivFrac);
 		dividers->ul_fb_div.ul_fb_div =
-			pll_patameters.ulFbDiv.usFbDiv;
+			le16_to_cpu(pll_patameters.ulFbDiv.usFbDiv);
 
 		dividers->uc_pll_ref_div =
 			pll_patameters.ucPllRefDiv;
@@ -380,7 +379,7 @@ int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr,
 	COMPUTE_GPU_CLOCK_OUTPUT_PARAMETERS_V1_7 pll_patameters;
 	int result;
 
-	pll_patameters.ulClock.ulClock = clock_value;
+	pll_patameters.ulClock.ulClock = cpu_to_le32(clock_value);
 	pll_patameters.ulClock.ucPostDiv = COMPUTE_GPUCLK_INPUT_FLAG_SCLK;
 
 	result = cgs_atom_exec_cmd_table
@@ -412,7 +411,7 @@ int atomctrl_get_dfs_pll_dividers_vi(
 	COMPUTE_GPU_CLOCK_OUTPUT_PARAMETERS_V1_6 pll_patameters;
 	int result;
 
-	pll_patameters.ulClock.ulClock = clock_value;
+	pll_patameters.ulClock.ulClock = cpu_to_le32(clock_value);
 	pll_patameters.ulClock.ucPostDiv =
 		COMPUTE_GPUCLK_INPUT_FLAG_DEFAULT_GPUCLK;
 
@@ -425,12 +424,12 @@ int atomctrl_get_dfs_pll_dividers_vi(
 		dividers->pll_post_divider =
 			pll_patameters.ulClock.ucPostDiv;
 		dividers->real_clock =
-			pll_patameters.ulClock.ulClock;
+			le32_to_cpu(pll_patameters.ulClock.ulClock);
 
 		dividers->ul_fb_div.ul_fb_div_frac =
-			pll_patameters.ulFbDiv.usFbDivFrac;
+			le16_to_cpu(pll_patameters.ulFbDiv.usFbDivFrac);
 		dividers->ul_fb_div.ul_fb_div =
-			pll_patameters.ulFbDiv.usFbDiv;
+			le16_to_cpu(pll_patameters.ulFbDiv.usFbDiv);
 
 		dividers->uc_pll_ref_div =
 			pll_patameters.ucPllRefDiv;
@@ -519,13 +518,13 @@ int atomctrl_get_voltage_table_v3(
 
 	for (i = 0; i < voltage_object->asGpioVoltageObj.ucGpioEntryNum; i++) {
 		voltage_table->entries[i].value =
-			voltage_object->asGpioVoltageObj.asVolGpioLut[i].usVoltageValue;
+			le16_to_cpu(voltage_object->asGpioVoltageObj.asVolGpioLut[i].usVoltageValue);
 		voltage_table->entries[i].smio_low =
-			voltage_object->asGpioVoltageObj.asVolGpioLut[i].ulVoltageId;
+			le32_to_cpu(voltage_object->asGpioVoltageObj.asVolGpioLut[i].ulVoltageId);
 	}
 
 	voltage_table->mask_low    =
-		voltage_object->asGpioVoltageObj.ulGpioMaskVal;
+		le32_to_cpu(voltage_object->asGpioVoltageObj.ulGpioMaskVal);
 	voltage_table->count      =
 		voltage_object->asGpioVoltageObj.ucGpioEntryNum;
 	voltage_table->phase_delay =
@@ -552,13 +551,13 @@ static bool atomctrl_lookup_gpio_pin(
 				pin_assignment->ucGpioPinBitShift;
 			gpio_pin_assignment->us_gpio_pin_aindex =
 				le16_to_cpu(pin_assignment->usGpioPin_AIndex);
-			return false;
+			return true;
 		}
 
 		offset += offsetof(ATOM_GPIO_PIN_ASSIGNMENT, ucGPIO_ID) + 1;
 	}
 
-	return true;
+	return false;
 }
 
 /**
@@ -592,12 +591,12 @@ bool atomctrl_get_pp_assign_pin(
 		const uint32_t pinId,
 		pp_atomctrl_gpio_pin_assignment *gpio_pin_assignment)
 {
-	bool bRet = 0;
+	bool bRet = false;
 	ATOM_GPIO_PIN_LUT *gpio_lookup_table =
 		get_gpio_lookup_table(hwmgr->device);
 
 	PP_ASSERT_WITH_CODE((NULL != gpio_lookup_table),
-			"Could not find GPIO lookup Table in BIOS.", return -1);
+			"Could not find GPIO lookup Table in BIOS.", return false);
 
 	bRet = atomctrl_lookup_gpio_pin(gpio_lookup_table, pinId,
 		gpio_pin_assignment);
@@ -650,8 +649,8 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 		return -1;
 
 	if (getASICProfilingInfo->asHeader.ucTableFormatRevision < 3 ||
-			(getASICProfilingInfo->asHeader.ucTableFormatRevision == 3 &&
-			getASICProfilingInfo->asHeader.ucTableContentRevision < 4))
+	    (getASICProfilingInfo->asHeader.ucTableFormatRevision == 3 &&
+	     getASICProfilingInfo->asHeader.ucTableContentRevision < 4))
 		return -1;
 
 	/*-----------------------------------------------------------
@@ -662,37 +661,37 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 
 	switch (dpm_level) {
 	case 1:
-		fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm1);
-		fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM1, 1000);
+		fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm1));
+		fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM1), 1000);
 		break;
 	case 2:
-		fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm2);
-		fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM2, 1000);
+		fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm2));
+		fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM2), 1000);
 		break;
 	case 3:
-		fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm3);
-		fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM3, 1000);
+		fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm3));
+		fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM3), 1000);
 		break;
 	case 4:
-		fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm4);
-		fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM4, 1000);
+		fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm4));
+		fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM4), 1000);
 		break;
 	case 5:
-		fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm5);
-		fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM5, 1000);
+		fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm5));
+		fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM5), 1000);
 		break;
 	case 6:
-		fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm6);
-		fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM6, 1000);
+		fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm6));
+		fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM6), 1000);
 		break;
 	case 7:
-		fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm7);
-		fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM7, 1000);
+		fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm7));
+		fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM7), 1000);
 		break;
 	default:
 		printk(KERN_ERR "DPM Level not supported\n");
 		fPowerDPMx = Convert_ULONG_ToFraction(1);
-		fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM0, 1000);
+		fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM0), 1000);
 	}
 
 	/*-------------------------
@@ -716,9 +715,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 		return result;
 
 	/* Finally, the actual fuse value */
-	ul_RO_fused = sOutput_FuseValues.ulEfuseValue;
-	fMin = GetScaledFraction(sRO_fuse.ulEfuseMin, 1);
-	fRange = GetScaledFraction(sRO_fuse.ulEfuseEncodeRange, 1);
+	ul_RO_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue);
+	fMin = GetScaledFraction(le32_to_cpu(sRO_fuse.ulEfuseMin), 1);
+	fRange = GetScaledFraction(le32_to_cpu(sRO_fuse.ulEfuseEncodeRange), 1);
 	fRO_fused = fDecodeLinearFuse(ul_RO_fused, fMin, fRange, sRO_fuse.ucEfuseLength);
 
 	sCACm_fuse = getASICProfilingInfo->sCACm;
@@ -736,9 +735,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	if (result)
 		return result;
 
-	ul_CACm_fused = sOutput_FuseValues.ulEfuseValue;
-	fMin = GetScaledFraction(sCACm_fuse.ulEfuseMin, 1000);
-	fRange = GetScaledFraction(sCACm_fuse.ulEfuseEncodeRange, 1000);
+	ul_CACm_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue);
+	fMin = GetScaledFraction(le32_to_cpu(sCACm_fuse.ulEfuseMin), 1000);
+	fRange = GetScaledFraction(le32_to_cpu(sCACm_fuse.ulEfuseEncodeRange), 1000);
 
 	fCACm_fused = fDecodeLinearFuse(ul_CACm_fused, fMin, fRange, sCACm_fuse.ucEfuseLength);
 
@@ -756,9 +755,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	if (result)
 		return result;
 
-	ul_CACb_fused = sOutput_FuseValues.ulEfuseValue;
-	fMin = GetScaledFraction(sCACb_fuse.ulEfuseMin, 1000);
-	fRange = GetScaledFraction(sCACb_fuse.ulEfuseEncodeRange, 1000);
+	ul_CACb_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue);
+	fMin = GetScaledFraction(le32_to_cpu(sCACb_fuse.ulEfuseMin), 1000);
+	fRange = GetScaledFraction(le32_to_cpu(sCACb_fuse.ulEfuseEncodeRange), 1000);
 
 	fCACb_fused = fDecodeLinearFuse(ul_CACb_fused, fMin, fRange, sCACb_fuse.ucEfuseLength);
 
@@ -777,9 +776,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	if (result)
 		return result;
 
-	ul_Kt_Beta_fused = sOutput_FuseValues.ulEfuseValue;
-	fAverage = GetScaledFraction(sKt_Beta_fuse.ulEfuseEncodeAverage, 1000);
-	fRange = GetScaledFraction(sKt_Beta_fuse.ulEfuseEncodeRange, 1000);
+	ul_Kt_Beta_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue);
+	fAverage = GetScaledFraction(le32_to_cpu(sKt_Beta_fuse.ulEfuseEncodeAverage), 1000);
+	fRange = GetScaledFraction(le32_to_cpu(sKt_Beta_fuse.ulEfuseEncodeRange), 1000);
 
 	fKt_Beta_fused = fDecodeLogisticFuse(ul_Kt_Beta_fused,
 			fAverage, fRange, sKt_Beta_fuse.ucEfuseLength);
@@ -798,9 +797,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	if (result)
 		return result;
 
-	ul_Kv_m_fused = sOutput_FuseValues.ulEfuseValue;
-	fAverage = GetScaledFraction(sKv_m_fuse.ulEfuseEncodeAverage, 1000);
-	fRange = GetScaledFraction((sKv_m_fuse.ulEfuseEncodeRange & 0x7fffffff), 1000);
+	ul_Kv_m_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue);
+	fAverage = GetScaledFraction(le32_to_cpu(sKv_m_fuse.ulEfuseEncodeAverage), 1000);
+	fRange = GetScaledFraction((le32_to_cpu(sKv_m_fuse.ulEfuseEncodeRange) & 0x7fffffff), 1000);
 	fRange = fMultiply(fRange, ConvertToFraction(-1));
 
 	fKv_m_fused = fDecodeLogisticFuse(ul_Kv_m_fused,
@@ -820,9 +819,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	if (result)
 		return result;
 
-	ul_Kv_b_fused = sOutput_FuseValues.ulEfuseValue;
-	fAverage = GetScaledFraction(sKv_b_fuse.ulEfuseEncodeAverage, 1000);
-	fRange = GetScaledFraction(sKv_b_fuse.ulEfuseEncodeRange, 1000);
+	ul_Kv_b_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue);
+	fAverage = GetScaledFraction(le32_to_cpu(sKv_b_fuse.ulEfuseEncodeAverage), 1000);
+	fRange = GetScaledFraction(le32_to_cpu(sKv_b_fuse.ulEfuseEncodeRange), 1000);
 
 	fKv_b_fused = fDecodeLogisticFuse(ul_Kv_b_fused,
 			fAverage, fRange, sKv_b_fuse.ucEfuseLength);
@@ -851,9 +850,9 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	if (result)
 		return result;
 
-	ul_FT_Lkg_V0NORM = sOutput_FuseValues.ulEfuseValue;
-	fLn_MaxDivMin = GetScaledFraction(getASICProfilingInfo->ulLkgEncodeLn_MaxDivMin, 10000);
-	fMin = GetScaledFraction(getASICProfilingInfo->ulLkgEncodeMin, 10000);
+	ul_FT_Lkg_V0NORM = le32_to_cpu(sOutput_FuseValues.ulEfuseValue);
+	fLn_MaxDivMin = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulLkgEncodeLn_MaxDivMin), 10000);
+	fMin = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulLkgEncodeMin), 10000);
 
 	fFT_Lkg_V0NORM = fDecodeLeakageID(ul_FT_Lkg_V0NORM,
 			fLn_MaxDivMin, fMin, getASICProfilingInfo->ucLkgEfuseLength);
@@ -863,40 +862,40 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	 * PART 2 - Grabbing all required values
 	 *-------------------------------------------
 	 */
-	fSM_A0 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A0, 1000000),
+	fSM_A0 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A0), 1000000),
 			ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A0_sign)));
-	fSM_A1 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A1, 1000000),
+	fSM_A1 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A1), 1000000),
 			ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A1_sign)));
-	fSM_A2 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A2, 100000),
+	fSM_A2 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A2), 100000),
 			ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A2_sign)));
-	fSM_A3 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A3, 1000000),
+	fSM_A3 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A3), 1000000),
 			ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A3_sign)));
-	fSM_A4 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A4, 1000000),
+	fSM_A4 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A4), 1000000),
 			ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A4_sign)));
-	fSM_A5 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A5, 1000),
+	fSM_A5 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A5), 1000),
 			ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A5_sign)));
-	fSM_A6 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A6, 1000),
+	fSM_A6 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A6), 1000),
 			ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A6_sign)));
-	fSM_A7 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A7, 1000),
+	fSM_A7 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A7), 1000),
 			ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A7_sign)));
 
-	fMargin_RO_a = ConvertToFraction(getASICProfilingInfo->ulMargin_RO_a);
-	fMargin_RO_b = ConvertToFraction(getASICProfilingInfo->ulMargin_RO_b);
-	fMargin_RO_c = ConvertToFraction(getASICProfilingInfo->ulMargin_RO_c);
+	fMargin_RO_a = ConvertToFraction(le32_to_cpu(getASICProfilingInfo->ulMargin_RO_a));
+	fMargin_RO_b = ConvertToFraction(le32_to_cpu(getASICProfilingInfo->ulMargin_RO_b));
+	fMargin_RO_c = ConvertToFraction(le32_to_cpu(getASICProfilingInfo->ulMargin_RO_c));
 
-	fMargin_fixed = ConvertToFraction(getASICProfilingInfo->ulMargin_fixed);
+	fMargin_fixed = ConvertToFraction(le32_to_cpu(getASICProfilingInfo->ulMargin_fixed));
 
 	fMargin_FMAX_mean = GetScaledFraction(
-			getASICProfilingInfo->ulMargin_Fmax_mean, 10000);
+		le32_to_cpu(getASICProfilingInfo->ulMargin_Fmax_mean), 10000);
 	fMargin_Plat_mean = GetScaledFraction(
-			getASICProfilingInfo->ulMargin_plat_mean, 10000);
+		le32_to_cpu(getASICProfilingInfo->ulMargin_plat_mean), 10000);
 	fMargin_FMAX_sigma = GetScaledFraction(
-			getASICProfilingInfo->ulMargin_Fmax_sigma, 10000);
+		le32_to_cpu(getASICProfilingInfo->ulMargin_Fmax_sigma), 10000);
 	fMargin_Plat_sigma = GetScaledFraction(
-			getASICProfilingInfo->ulMargin_plat_sigma, 10000);
+		le32_to_cpu(getASICProfilingInfo->ulMargin_plat_sigma), 10000);
 
 	fMargin_DC_sigma = GetScaledFraction(
-			getASICProfilingInfo->ulMargin_DC_sigma, 100);
+		le32_to_cpu(getASICProfilingInfo->ulMargin_DC_sigma), 100);
 	fMargin_DC_sigma = fDivide(fMargin_DC_sigma, ConvertToFraction(1000));
 
 	fCACm_fused = fDivide(fCACm_fused, ConvertToFraction(100));
@@ -908,14 +907,14 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	fSclk = GetScaledFraction(sclk, 100);
 
 	fV_max = fDivide(GetScaledFraction(
-			getASICProfilingInfo->ulMaxVddc, 1000), ConvertToFraction(4));
-	fT_prod = GetScaledFraction(getASICProfilingInfo->ulBoardCoreTemp, 10);
-	fLKG_Factor = GetScaledFraction(getASICProfilingInfo->ulEvvLkgFactor, 100);
-	fT_FT = GetScaledFraction(getASICProfilingInfo->ulLeakageTemp, 10);
+				 le32_to_cpu(getASICProfilingInfo->ulMaxVddc), 1000), ConvertToFraction(4));
+	fT_prod = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulBoardCoreTemp), 10);
+	fLKG_Factor = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulEvvLkgFactor), 100);
+	fT_FT = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulLeakageTemp), 10);
 	fV_FT = fDivide(GetScaledFraction(
-			getASICProfilingInfo->ulLeakageVoltage, 1000), ConvertToFraction(4));
+				le32_to_cpu(getASICProfilingInfo->ulLeakageVoltage), 1000), ConvertToFraction(4));
 	fV_min = fDivide(GetScaledFraction(
-			getASICProfilingInfo->ulMinVddc, 1000), ConvertToFraction(4));
+				 le32_to_cpu(getASICProfilingInfo->ulMinVddc), 1000), ConvertToFraction(4));
 
 	/*-----------------------
 	 * PART 3
@@ -925,7 +924,7 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 	fA_Term = fAdd(fMargin_RO_a, fAdd(fMultiply(fSM_A4, fSclk), fSM_A5));
 	fB_Term = fAdd(fAdd(fMultiply(fSM_A2, fSclk), fSM_A6), fMargin_RO_b);
 	fC_Term = fAdd(fMargin_RO_c,
-			fAdd(fMultiply(fSM_A0,fLkg_FT),
+			fAdd(fMultiply(fSM_A0, fLkg_FT),
 			fAdd(fMultiply(fSM_A1, fMultiply(fLkg_FT, fSclk)),
 			fAdd(fMultiply(fSM_A3, fSclk),
 			fSubtract(fSM_A7, fRO_fused)))));
@@ -1063,9 +1062,55 @@ int atomctrl_get_voltage_evv_on_sclk(
 	get_voltage_info_param_space.ucVoltageMode   =
 		ATOM_GET_VOLTAGE_EVV_VOLTAGE;
 	get_voltage_info_param_space.usVoltageLevel  =
-		virtual_voltage_Id;
+		cpu_to_le16(virtual_voltage_Id);
 	get_voltage_info_param_space.ulSCLKFreq      =
-		sclk;
+		cpu_to_le32(sclk);
+
+	result = cgs_atom_exec_cmd_table(hwmgr->device,
+			GetIndexIntoMasterTable(COMMAND, GetVoltageInfo),
+			&get_voltage_info_param_space);
+
+	if (0 != result)
+		return result;
+
+	*voltage = le16_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 *)
+				(&get_voltage_info_param_space))->usVoltageLevel);
+
+	return result;
+}
+
+/**
+ * atomctrl_get_voltage_evv gets voltage via call to ATOM COMMAND table.
+ * @param hwmgr	input: pointer to hwManager
+ * @param virtual_voltage_id      input: voltage id which match per voltage DPM state: 0xff01, 0xff02.. 0xff08
+ * @param voltage		       output: real voltage level in unit of mv
+ */
+int atomctrl_get_voltage_evv(struct pp_hwmgr *hwmgr,
+			     uint16_t virtual_voltage_id,
+			     uint16_t *voltage)
+{
+	int result;
+	int entry_id;
+	GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 get_voltage_info_param_space;
+
+	/* search for leakage voltage ID 0xff01 ~ 0xff08 and sckl */
+	for (entry_id = 0; entry_id < hwmgr->dyn_state.vddc_dependency_on_sclk->count; entry_id++) {
+		if (hwmgr->dyn_state.vddc_dependency_on_sclk->entries[entry_id].v == virtual_voltage_id) {
+			/* found */
+			break;
+		}
+	}
+
+	PP_ASSERT_WITH_CODE(entry_id < hwmgr->dyn_state.vddc_dependency_on_sclk->count,
+	        "Can't find requested voltage id in vddc_dependency_on_sclk table!",
+	        return -EINVAL;
+	);
+
+	get_voltage_info_param_space.ucVoltageType = VOLTAGE_TYPE_VDDC;
+	get_voltage_info_param_space.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE;
+	get_voltage_info_param_space.usVoltageLevel = virtual_voltage_id;
+	get_voltage_info_param_space.ulSCLKFreq =
+		cpu_to_le32(hwmgr->dyn_state.vddc_dependency_on_sclk->entries[entry_id].clk);
 
 	result = cgs_atom_exec_cmd_table(hwmgr->device,
 			GetIndexIntoMasterTable(COMMAND, GetVoltageInfo),
@@ -1074,8 +1119,8 @@ int atomctrl_get_voltage_evv_on_sclk(
 	if (0 != result)
 		return result;
 
-	*voltage = ((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 *)
-			(&get_voltage_info_param_space))->usVoltageLevel;
+	*voltage = le16_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 *)
+				(&get_voltage_info_param_space))->usVoltageLevel);
 
 	return result;
 }
@@ -1165,8 +1210,8 @@ static int asic_internal_ss_get_ss_asignment(struct pp_hwmgr *hwmgr,
 
 	if (entry_found) {
 		ssEntry->speed_spectrum_percentage =
-			ssInfo->usSpreadSpectrumPercentage;
-		ssEntry->speed_spectrum_rate = ssInfo->usSpreadRateInKhz;
+			le16_to_cpu(ssInfo->usSpreadSpectrumPercentage);
+		ssEntry->speed_spectrum_rate = le16_to_cpu(ssInfo->usSpreadRateInKhz);
 
 		if (((GET_DATA_TABLE_MAJOR_REVISION(table) == 2) &&
 			(GET_DATA_TABLE_MINOR_REVISION(table) >= 2)) ||
@@ -1222,7 +1267,7 @@ int atomctrl_read_efuse(void *device, uint16_t start_index,
 	int result;
 	READ_EFUSE_VALUE_PARAMETER efuse_param;
 
-	efuse_param.sEfuse.usEfuseIndex = (start_index / 32) * 4;
+	efuse_param.sEfuse.usEfuseIndex = cpu_to_le16((start_index / 32) * 4);
 	efuse_param.sEfuse.ucBitShift = (uint8_t)
 			(start_index - ((start_index / 32) * 32));
 	efuse_param.sEfuse.ucBitLength  = (uint8_t)
@@ -1232,19 +1277,21 @@ int atomctrl_read_efuse(void *device, uint16_t start_index,
 			GetIndexIntoMasterTable(COMMAND, ReadEfuseValue),
 			&efuse_param);
 	if (!result)
-		*efuse = efuse_param.ulEfuseValue & mask;
+		*efuse = le32_to_cpu(efuse_param.ulEfuseValue) & mask;
 
 	return result;
 }
 
 int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
-								uint8_t level)
+			      uint8_t level)
 {
 	DYNAMICE_MEMORY_SETTINGS_PARAMETER_V2_1 memory_clock_parameters;
 	int result;
 
-	memory_clock_parameters.asDPMMCReg.ulClock.ulClockFreq = memory_clock & SET_CLOCK_FREQ_MASK;
-	memory_clock_parameters.asDPMMCReg.ulClock.ulComputeClockFlag = ADJUST_MC_SETTING_PARAM;
+	memory_clock_parameters.asDPMMCReg.ulClock.ulClockFreq =
+		memory_clock & SET_CLOCK_FREQ_MASK;
+	memory_clock_parameters.asDPMMCReg.ulClock.ulComputeClockFlag =
+		ADJUST_MC_SETTING_PARAM;
 	memory_clock_parameters.asDPMMCReg.ucMclkDPMState = level;
 
 	result = cgs_atom_exec_cmd_table
@@ -1264,8 +1311,8 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_
 
 	get_voltage_info_param_space.ucVoltageType = voltage_type;
 	get_voltage_info_param_space.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE;
-	get_voltage_info_param_space.usVoltageLevel = virtual_voltage_Id;
-	get_voltage_info_param_space.ulSCLKFreq = sclk;
+	get_voltage_info_param_space.usVoltageLevel = cpu_to_le16(virtual_voltage_Id);
+	get_voltage_info_param_space.ulSCLKFreq = cpu_to_le32(sclk);
 
 	result = cgs_atom_exec_cmd_table(hwmgr->device,
 			GetIndexIntoMasterTable(COMMAND, GetVoltageInfo),
@@ -1274,7 +1321,7 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_
 	if (0 != result)
 		return result;
 
-	*voltage = ((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel;
+	*voltage = le32_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel);
 
 	return result;
 }
@@ -1295,15 +1342,19 @@ int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctr
 	for (i = 0; i < psmu_info->ucSclkEntryNum; i++) {
 		table->entry[i].ucVco_setting = psmu_info->asSclkFcwRangeEntry[i].ucVco_setting;
 		table->entry[i].ucPostdiv = psmu_info->asSclkFcwRangeEntry[i].ucPostdiv;
-		table->entry[i].usFcw_pcc = psmu_info->asSclkFcwRangeEntry[i].ucFcw_pcc;
-		table->entry[i].usFcw_trans_upper = psmu_info->asSclkFcwRangeEntry[i].ucFcw_trans_upper;
-		table->entry[i].usRcw_trans_lower = psmu_info->asSclkFcwRangeEntry[i].ucRcw_trans_lower;
+		table->entry[i].usFcw_pcc =
+			le16_to_cpu(psmu_info->asSclkFcwRangeEntry[i].ucFcw_pcc);
+		table->entry[i].usFcw_trans_upper =
+			le16_to_cpu(psmu_info->asSclkFcwRangeEntry[i].ucFcw_trans_upper);
+		table->entry[i].usRcw_trans_lower =
+			le16_to_cpu(psmu_info->asSclkFcwRangeEntry[i].ucRcw_trans_lower);
 	}
 
 	return 0;
 }
 
-int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param)
+int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr,
+				  struct pp_atom_ctrl__avfs_parameters *param)
 {
 	ATOM_ASIC_PROFILING_INFO_V3_6 *profile = NULL;
 
@@ -1317,30 +1368,30 @@ int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__a
 	if (!profile)
 		return -1;
 
-	param->ulAVFS_meanNsigma_Acontant0 = profile->ulAVFS_meanNsigma_Acontant0;
-	param->ulAVFS_meanNsigma_Acontant1 = profile->ulAVFS_meanNsigma_Acontant1;
-	param->ulAVFS_meanNsigma_Acontant2 = profile->ulAVFS_meanNsigma_Acontant2;
-	param->usAVFS_meanNsigma_DC_tol_sigma = profile->usAVFS_meanNsigma_DC_tol_sigma;
-	param->usAVFS_meanNsigma_Platform_mean = profile->usAVFS_meanNsigma_Platform_mean;
-	param->usAVFS_meanNsigma_Platform_sigma = profile->usAVFS_meanNsigma_Platform_sigma;
-	param->ulGB_VDROOP_TABLE_CKSOFF_a0 = profile->ulGB_VDROOP_TABLE_CKSOFF_a0;
-	param->ulGB_VDROOP_TABLE_CKSOFF_a1 = profile->ulGB_VDROOP_TABLE_CKSOFF_a1;
-	param->ulGB_VDROOP_TABLE_CKSOFF_a2 = profile->ulGB_VDROOP_TABLE_CKSOFF_a2;
-	param->ulGB_VDROOP_TABLE_CKSON_a0 = profile->ulGB_VDROOP_TABLE_CKSON_a0;
-	param->ulGB_VDROOP_TABLE_CKSON_a1 = profile->ulGB_VDROOP_TABLE_CKSON_a1;
-	param->ulGB_VDROOP_TABLE_CKSON_a2 = profile->ulGB_VDROOP_TABLE_CKSON_a2;
-	param->ulAVFSGB_FUSE_TABLE_CKSOFF_m1 = profile->ulAVFSGB_FUSE_TABLE_CKSOFF_m1;
-	param->usAVFSGB_FUSE_TABLE_CKSOFF_m2 = profile->usAVFSGB_FUSE_TABLE_CKSOFF_m2;
-	param->ulAVFSGB_FUSE_TABLE_CKSOFF_b = profile->ulAVFSGB_FUSE_TABLE_CKSOFF_b;
-	param->ulAVFSGB_FUSE_TABLE_CKSON_m1 = profile->ulAVFSGB_FUSE_TABLE_CKSON_m1;
-	param->usAVFSGB_FUSE_TABLE_CKSON_m2 = profile->usAVFSGB_FUSE_TABLE_CKSON_m2;
-	param->ulAVFSGB_FUSE_TABLE_CKSON_b = profile->ulAVFSGB_FUSE_TABLE_CKSON_b;
-	param->usMaxVoltage_0_25mv = profile->usMaxVoltage_0_25mv;
+	param->ulAVFS_meanNsigma_Acontant0 = le32_to_cpu(profile->ulAVFS_meanNsigma_Acontant0);
+	param->ulAVFS_meanNsigma_Acontant1 = le32_to_cpu(profile->ulAVFS_meanNsigma_Acontant1);
+	param->ulAVFS_meanNsigma_Acontant2 = le32_to_cpu(profile->ulAVFS_meanNsigma_Acontant2);
+	param->usAVFS_meanNsigma_DC_tol_sigma = le16_to_cpu(profile->usAVFS_meanNsigma_DC_tol_sigma);
+	param->usAVFS_meanNsigma_Platform_mean = le16_to_cpu(profile->usAVFS_meanNsigma_Platform_mean);
+	param->usAVFS_meanNsigma_Platform_sigma = le16_to_cpu(profile->usAVFS_meanNsigma_Platform_sigma);
+	param->ulGB_VDROOP_TABLE_CKSOFF_a0 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSOFF_a0);
+	param->ulGB_VDROOP_TABLE_CKSOFF_a1 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSOFF_a1);
+	param->ulGB_VDROOP_TABLE_CKSOFF_a2 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSOFF_a2);
+	param->ulGB_VDROOP_TABLE_CKSON_a0 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSON_a0);
+	param->ulGB_VDROOP_TABLE_CKSON_a1 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSON_a1);
+	param->ulGB_VDROOP_TABLE_CKSON_a2 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSON_a2);
+	param->ulAVFSGB_FUSE_TABLE_CKSOFF_m1 = le32_to_cpu(profile->ulAVFSGB_FUSE_TABLE_CKSOFF_m1);
+	param->usAVFSGB_FUSE_TABLE_CKSOFF_m2 = le16_to_cpu(profile->usAVFSGB_FUSE_TABLE_CKSOFF_m2);
+	param->ulAVFSGB_FUSE_TABLE_CKSOFF_b = le32_to_cpu(profile->ulAVFSGB_FUSE_TABLE_CKSOFF_b);
+	param->ulAVFSGB_FUSE_TABLE_CKSON_m1 = le32_to_cpu(profile->ulAVFSGB_FUSE_TABLE_CKSON_m1);
+	param->usAVFSGB_FUSE_TABLE_CKSON_m2 = le16_to_cpu(profile->usAVFSGB_FUSE_TABLE_CKSON_m2);
+	param->ulAVFSGB_FUSE_TABLE_CKSON_b = le32_to_cpu(profile->ulAVFSGB_FUSE_TABLE_CKSON_b);
+	param->usMaxVoltage_0_25mv = le16_to_cpu(profile->usMaxVoltage_0_25mv);
 	param->ucEnableGB_VDROOP_TABLE_CKSOFF = profile->ucEnableGB_VDROOP_TABLE_CKSOFF;
 	param->ucEnableGB_VDROOP_TABLE_CKSON = profile->ucEnableGB_VDROOP_TABLE_CKSON;
 	param->ucEnableGB_FUSE_TABLE_CKSOFF = profile->ucEnableGB_FUSE_TABLE_CKSOFF;
 	param->ucEnableGB_FUSE_TABLE_CKSON = profile->ucEnableGB_FUSE_TABLE_CKSON;
-	param->usPSM_Age_ComFactor = profile->usPSM_Age_ComFactor;
+	param->usPSM_Age_ComFactor = le16_to_cpu(profile->usPSM_Age_ComFactor);
 	param->ucEnableApplyAVFS_CKS_OFF_Voltage = profile->ucEnableApplyAVFS_CKS_OFF_Voltage;
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
index 1e35a9625baf..fc898afce002 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
@@ -281,6 +281,7 @@ struct pp_atom_ctrl__avfs_parameters {
 
 extern bool atomctrl_get_pp_assign_pin(struct pp_hwmgr *hwmgr, const uint32_t pinId, pp_atomctrl_gpio_pin_assignment *gpio_pin_assignment);
 extern int atomctrl_get_voltage_evv_on_sclk(struct pp_hwmgr *hwmgr, uint8_t voltage_type, uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage);
+extern int atomctrl_get_voltage_evv(struct pp_hwmgr *hwmgr, uint16_t virtual_voltage_id, uint16_t *voltage);
 extern uint32_t atomctrl_get_mpll_reference_clock(struct pp_hwmgr *hwmgr);
 extern int atomctrl_get_memory_clock_spread_spectrum(struct pp_hwmgr *hwmgr, const uint32_t memory_clock, pp_atomctrl_internal_ss_info *ssInfo);
 extern int atomctrl_get_engine_clock_spread_spectrum(struct pp_hwmgr *hwmgr, const uint32_t engine_clock, pp_atomctrl_internal_ss_info *ssInfo);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppevvmath.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppevvmath.h
index 009bd5963ed8..8f50a038396c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppevvmath.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppevvmath.h
@@ -50,55 +50,45 @@ typedef union _fInt {
  * Function Declarations
  *  -------------------------------------------------------------------------------
  */
-fInt ConvertToFraction(int);                       /* Use this to convert an INT to a FINT */
-fInt Convert_ULONG_ToFraction(uint32_t);              /* Use this to convert an uint32_t to a FINT */
-fInt GetScaledFraction(int, int);                  /* Use this to convert an INT to a FINT after scaling it by a factor */
-int ConvertBackToInteger(fInt);                    /* Convert a FINT back to an INT that is scaled by 1000 (i.e. last 3 digits are the decimal digits) */
-
-fInt fNegate(fInt);                                /* Returns -1 * input fInt value */
-fInt fAdd (fInt, fInt);                            /* Returns the sum of two fInt numbers */
-fInt fSubtract (fInt A, fInt B);                   /* Returns A-B - Sometimes easier than Adding negative numbers */
-fInt fMultiply (fInt, fInt);                       /* Returns the product of two fInt numbers */
-fInt fDivide (fInt A, fInt B);                     /* Returns A/B */
-fInt fGetSquare(fInt);                             /* Returns the square of a fInt number */
-fInt fSqrt(fInt);                                  /* Returns the Square Root of a fInt number */
-
-int uAbs(int);                                     /* Returns the Absolute value of the Int */
-fInt fAbs(fInt);                                   /* Returns the Absolute value of the fInt */
-int uPow(int base, int exponent);                  /* Returns base^exponent an INT */
-
-void SolveQuadracticEqn(fInt, fInt, fInt, fInt[]); /* Returns the 2 roots via the array */
-bool Equal(fInt, fInt);                         /* Returns true if two fInts are equal to each other */
-bool GreaterThan(fInt A, fInt B);               /* Returns true if A > B */
-
-fInt fExponential(fInt exponent);                  /* Can be used to calculate e^exponent */
-fInt fNaturalLog(fInt value);                      /* Can be used to calculate ln(value) */
+static fInt ConvertToFraction(int);                       /* Use this to convert an INT to a FINT */
+static fInt Convert_ULONG_ToFraction(uint32_t);           /* Use this to convert an uint32_t to a FINT */
+static fInt GetScaledFraction(int, int);                  /* Use this to convert an INT to a FINT after scaling it by a factor */
+static int ConvertBackToInteger(fInt);                    /* Convert a FINT back to an INT that is scaled by 1000 (i.e. last 3 digits are the decimal digits) */
+
+static fInt fNegate(fInt);                                /* Returns -1 * input fInt value */
+static fInt fAdd (fInt, fInt);                            /* Returns the sum of two fInt numbers */
+static fInt fSubtract (fInt A, fInt B);                   /* Returns A-B - Sometimes easier than Adding negative numbers */
+static fInt fMultiply (fInt, fInt);                       /* Returns the product of two fInt numbers */
+static fInt fDivide (fInt A, fInt B);                     /* Returns A/B */
+static fInt fGetSquare(fInt);                             /* Returns the square of a fInt number */
+static fInt fSqrt(fInt);                                  /* Returns the Square Root of a fInt number */
+
+static int uAbs(int);                                     /* Returns the Absolute value of the Int */
+static int uPow(int base, int exponent);                  /* Returns base^exponent an INT */
+
+static void SolveQuadracticEqn(fInt, fInt, fInt, fInt[]); /* Returns the 2 roots via the array */
+static bool Equal(fInt, fInt);                            /* Returns true if two fInts are equal to each other */
+static bool GreaterThan(fInt A, fInt B);                  /* Returns true if A > B */
+
+static fInt fExponential(fInt exponent);                  /* Can be used to calculate e^exponent */
+static fInt fNaturalLog(fInt value);                      /* Can be used to calculate ln(value) */
 
 /* Fuse decoding functions
  * -------------------------------------------------------------------------------------
  */
-fInt fDecodeLinearFuse(uint32_t fuse_value, fInt f_min, fInt f_range, uint32_t bitlength);
-fInt fDecodeLogisticFuse(uint32_t fuse_value, fInt f_average, fInt f_range, uint32_t bitlength);
-fInt fDecodeLeakageID (uint32_t leakageID_fuse, fInt ln_max_div_min, fInt f_min, uint32_t bitlength);
+static fInt fDecodeLinearFuse(uint32_t fuse_value, fInt f_min, fInt f_range, uint32_t bitlength);
+static fInt fDecodeLogisticFuse(uint32_t fuse_value, fInt f_average, fInt f_range, uint32_t bitlength);
+static fInt fDecodeLeakageID (uint32_t leakageID_fuse, fInt ln_max_div_min, fInt f_min, uint32_t bitlength);
 
 /* Internal Support Functions - Use these ONLY for testing or adding to internal functions
  * -------------------------------------------------------------------------------------
  * Some of the following functions take two INTs as their input - This is unsafe for a variety of reasons.
  */
-fInt Add (int, int);                               /* Add two INTs and return Sum as FINT */
-fInt Multiply (int, int);                          /* Multiply two INTs and return Product as FINT */
-fInt Divide (int, int);                            /* You get the idea... */
-fInt fNegate(fInt);
+static fInt Divide (int, int);                            /* Divide two INTs and return result as FINT */
+static fInt fNegate(fInt);
 
-int uGetScaledDecimal (fInt);                      /* Internal function */
-int GetReal (fInt A);                              /* Internal function */
-
-/* Future Additions and Incomplete Functions
- * -------------------------------------------------------------------------------------
- */
-int GetRoundedValue(fInt);                         /* Incomplete function - Useful only when Precision is lacking */
-                                                   /* Let us say we have 2.126 but can only handle 2 decimal points. We could */
-                                                   /* either chop of 6 and keep 2.12 or use this function to get 2.13, which is more accurate */
+static int uGetScaledDecimal (fInt);                      /* Internal function */
+static int GetReal (fInt A);                              /* Internal function */
 
 /* -------------------------------------------------------------------------------------
  * TROUBLESHOOTING INFORMATION
@@ -115,7 +105,7 @@ int GetRoundedValue(fInt);                         /* Incomplete function - Usef
  * START OF CODE
  * -------------------------------------------------------------------------------------
  */
-fInt fExponential(fInt exponent)        /*Can be used to calculate e^exponent*/
+static fInt fExponential(fInt exponent)        /*Can be used to calculate e^exponent*/
 {
 	uint32_t i;
 	bool bNegated = false;
@@ -154,7 +144,7 @@ fInt fExponential(fInt exponent)        /*Can be used to calculate e^exponent*/
 	return solution;
 }
 
-fInt fNaturalLog(fInt value)
+static fInt fNaturalLog(fInt value)
 {
 	uint32_t i;
 	fInt upper_bound = Divide(8, 1000);
@@ -179,7 +169,7 @@ fInt fNaturalLog(fInt value)
 	return (fAdd(solution, error_term));
 }
 
-fInt fDecodeLinearFuse(uint32_t fuse_value, fInt f_min, fInt f_range, uint32_t bitlength)
+static fInt fDecodeLinearFuse(uint32_t fuse_value, fInt f_min, fInt f_range, uint32_t bitlength)
 {
 	fInt f_fuse_value = Convert_ULONG_ToFraction(fuse_value);
 	fInt f_bit_max_value = Convert_ULONG_ToFraction((uPow(2, bitlength)) - 1);
@@ -194,7 +184,7 @@ fInt fDecodeLinearFuse(uint32_t fuse_value, fInt f_min, fInt f_range, uint32_t b
 }
 
 
-fInt fDecodeLogisticFuse(uint32_t fuse_value, fInt f_average, fInt f_range, uint32_t bitlength)
+static fInt fDecodeLogisticFuse(uint32_t fuse_value, fInt f_average, fInt f_range, uint32_t bitlength)
 {
 	fInt f_fuse_value = Convert_ULONG_ToFraction(fuse_value);
 	fInt f_bit_max_value = Convert_ULONG_ToFraction((uPow(2, bitlength)) - 1);
@@ -212,7 +202,7 @@ fInt fDecodeLogisticFuse(uint32_t fuse_value, fInt f_average, fInt f_range, uint
 	return f_decoded_value;
 }
 
-fInt fDecodeLeakageID (uint32_t leakageID_fuse, fInt ln_max_div_min, fInt f_min, uint32_t bitlength)
+static fInt fDecodeLeakageID (uint32_t leakageID_fuse, fInt ln_max_div_min, fInt f_min, uint32_t bitlength)
 {
 	fInt fLeakage;
 	fInt f_bit_max_value = Convert_ULONG_ToFraction((uPow(2, bitlength)) - 1);
@@ -225,7 +215,7 @@ fInt fDecodeLeakageID (uint32_t leakageID_fuse, fInt ln_max_div_min, fInt f_min,
 	return fLeakage;
 }
 
-fInt ConvertToFraction(int X) /*Add all range checking here. Is it possible to make fInt a private declaration? */
+static fInt ConvertToFraction(int X) /*Add all range checking here. Is it possible to make fInt a private declaration? */
 {
 	fInt temp;
 
@@ -237,13 +227,13 @@ fInt ConvertToFraction(int X) /*Add all range checking here. Is it possible to m
 	return temp;
 }
 
-fInt fNegate(fInt X)
+static fInt fNegate(fInt X)
 {
 	fInt CONSTANT_NEGONE = ConvertToFraction(-1);
 	return (fMultiply(X, CONSTANT_NEGONE));
 }
 
-fInt Convert_ULONG_ToFraction(uint32_t X)
+static fInt Convert_ULONG_ToFraction(uint32_t X)
 {
 	fInt temp;
 
@@ -255,7 +245,7 @@ fInt Convert_ULONG_ToFraction(uint32_t X)
 	return temp;
 }
 
-fInt GetScaledFraction(int X, int factor)
+static fInt GetScaledFraction(int X, int factor)
 {
 	int times_shifted, factor_shifted;
 	bool bNEGATED;
@@ -304,7 +294,7 @@ fInt GetScaledFraction(int X, int factor)
 }
 
 /* Addition using two fInts */
-fInt fAdd (fInt X, fInt Y)
+static fInt fAdd (fInt X, fInt Y)
 {
 	fInt Sum;
 
@@ -314,7 +304,7 @@ fInt fAdd (fInt X, fInt Y)
 }
 
 /* Addition using two fInts */
-fInt fSubtract (fInt X, fInt Y)
+static fInt fSubtract (fInt X, fInt Y)
 {
 	fInt Difference;
 
@@ -323,7 +313,7 @@ fInt fSubtract (fInt X, fInt Y)
 	return Difference;
 }
 
-bool Equal(fInt A, fInt B)
+static bool Equal(fInt A, fInt B)
 {
 	if (A.full == B.full)
 		return true;
@@ -331,7 +321,7 @@ bool Equal(fInt A, fInt B)
 		return false;
 }
 
-bool GreaterThan(fInt A, fInt B)
+static bool GreaterThan(fInt A, fInt B)
 {
 	if (A.full > B.full)
 		return true;
@@ -339,7 +329,7 @@ bool GreaterThan(fInt A, fInt B)
 		return false;
 }
 
-fInt fMultiply (fInt X, fInt Y) /* Uses 64-bit integers (int64_t) */
+static fInt fMultiply (fInt X, fInt Y) /* Uses 64-bit integers (int64_t) */
 {
 	fInt Product;
 	int64_t tempProduct;
@@ -363,7 +353,7 @@ fInt fMultiply (fInt X, fInt Y) /* Uses 64-bit integers (int64_t) */
 	return Product;
 }
 
-fInt fDivide (fInt X, fInt Y)
+static fInt fDivide (fInt X, fInt Y)
 {
 	fInt fZERO, fQuotient;
 	int64_t longlongX, longlongY;
@@ -384,7 +374,7 @@ fInt fDivide (fInt X, fInt Y)
 	return fQuotient;
 }
 
-int ConvertBackToInteger (fInt A) /*THIS is the function that will be used to check with the Golden settings table*/
+static int ConvertBackToInteger (fInt A) /*THIS is the function that will be used to check with the Golden settings table*/
 {
 	fInt fullNumber, scaledDecimal, scaledReal;
 
@@ -397,13 +387,13 @@ int ConvertBackToInteger (fInt A) /*THIS is the function that will be used to ch
 	return fullNumber.full;
 }
 
-fInt fGetSquare(fInt A)
+static fInt fGetSquare(fInt A)
 {
 	return fMultiply(A,A);
 }
 
 /* x_new = x_old - (x_old^2 - C) / (2 * x_old) */
-fInt fSqrt(fInt num)
+static fInt fSqrt(fInt num)
 {
 	fInt F_divide_Fprime, Fprime;
 	fInt test;
@@ -460,7 +450,7 @@ fInt fSqrt(fInt num)
 	return (x_new);
 }
 
-void SolveQuadracticEqn(fInt A, fInt B, fInt C, fInt Roots[])
+static void SolveQuadracticEqn(fInt A, fInt B, fInt C, fInt Roots[])
 {
 	fInt *pRoots = &Roots[0];
 	fInt temp, root_first, root_second;
@@ -498,52 +488,13 @@ void SolveQuadracticEqn(fInt A, fInt B, fInt C, fInt Roots[])
  * -----------------------------------------------------------------------------
  */
 
-/* Addition using two normal ints - Temporary - Use only for testing purposes?. */
-fInt Add (int X, int Y)
-{
-	fInt A, B, Sum;
-
-	A.full = (X << SHIFT_AMOUNT);
-	B.full = (Y << SHIFT_AMOUNT);
-
-	Sum.full = A.full + B.full;
-
-	return Sum;
-}
-
 /* Conversion Functions */
-int GetReal (fInt A)
+static int GetReal (fInt A)
 {
 	return (A.full >> SHIFT_AMOUNT);
 }
 
-/* Temporarily Disabled */
-int GetRoundedValue(fInt A) /*For now, round the 3rd decimal place */
-{
-	/* ROUNDING TEMPORARLY DISABLED
-	int temp = A.full;
-	int decimal_cutoff, decimal_mask = 0x000001FF;
-	decimal_cutoff = temp & decimal_mask;
-	if (decimal_cutoff > 0x147) {
-		temp += 673;
-	}*/
-
-	return ConvertBackToInteger(A)/10000; /*Temporary - in case this was used somewhere else */
-}
-
-fInt Multiply (int X, int Y)
-{
-	fInt A, B, Product;
-
-	A.full = X << SHIFT_AMOUNT;
-	B.full = Y << SHIFT_AMOUNT;
-
-	Product = fMultiply(A, B);
-
-	return Product;
-}
-
-fInt Divide (int X, int Y)
+static fInt Divide (int X, int Y)
 {
 	fInt A, B, Quotient;
 
@@ -555,7 +506,7 @@ fInt Divide (int X, int Y)
 	return Quotient;
 }
 
-int uGetScaledDecimal (fInt A) /*Converts the fractional portion to whole integers - Costly function */
+static int uGetScaledDecimal (fInt A) /*Converts the fractional portion to whole integers - Costly function */
 {
 	int dec[PRECISION];
 	int i, scaledDecimal = 0, tmp = A.partial.decimal;
@@ -570,7 +521,7 @@ int uGetScaledDecimal (fInt A) /*Converts the fractional portion to whole intege
 	return scaledDecimal;
 }
 
-int uPow(int base, int power)
+static int uPow(int base, int power)
 {
 	if (power == 0)
 		return 1;
@@ -578,15 +529,7 @@ int uPow(int base, int power)
 		return (base)*uPow(base, power - 1);
 }
 
-fInt fAbs(fInt A)
-{
-	if (A.partial.real < 0)
-		return (fMultiply(A, ConvertToFraction(-1)));
-	else
-		return A;
-}
-
-int uAbs(int X)
+static int uAbs(int X)
 {
 	if (X < 0)
 		return (X * -1);
@@ -594,7 +537,7 @@ int uAbs(int X)
 		return X;
 }
 
-fInt fRoundUpByStepSize(fInt A, fInt fStepSize, bool error_term)
+static fInt fRoundUpByStepSize(fInt A, fInt fStepSize, bool error_term)
 {
 	fInt solution;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
index 2f1a14fe05b1..6c321b0d8a1e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
@@ -794,19 +794,35 @@ static const ATOM_PPLIB_STATE_V2 *get_state_entry_v2(
 static const ATOM_PPLIB_POWERPLAYTABLE *get_powerplay_table(
 				     struct pp_hwmgr *hwmgr)
 {
-	const void *table_addr = NULL;
+	const void *table_addr = hwmgr->soft_pp_table;
 	uint8_t frev, crev;
 	uint16_t size;
 
-	table_addr = cgs_atom_get_data_table(hwmgr->device,
-			GetIndexIntoMasterTable(DATA, PowerPlayInfo),
-			&size, &frev, &crev);
+	if (!table_addr) {
+		table_addr = cgs_atom_get_data_table(hwmgr->device,
+				GetIndexIntoMasterTable(DATA, PowerPlayInfo),
+				&size, &frev, &crev);
 
-	hwmgr->soft_pp_table = table_addr;
+		hwmgr->soft_pp_table = table_addr;
+		hwmgr->soft_pp_table_size = size;
+	}
 
 	return (const ATOM_PPLIB_POWERPLAYTABLE *)table_addr;
 }
 
+int pp_tables_get_response_times(struct pp_hwmgr *hwmgr,
+				uint32_t *vol_rep_time, uint32_t *bb_rep_time)
+{
+	const ATOM_PPLIB_POWERPLAYTABLE *powerplay_tab = get_powerplay_table(hwmgr);
+
+	PP_ASSERT_WITH_CODE(NULL != powerplay_tab,
+			    "Missing PowerPlay Table!", return -EINVAL);
+
+	*vol_rep_time = (uint32_t)le16_to_cpu(powerplay_tab->usVoltageTime);
+	*bb_rep_time = (uint32_t)le16_to_cpu(powerplay_tab->usBackbiasTime);
+
+	return 0;
+}
 
 int pp_tables_get_num_of_entries(struct pp_hwmgr *hwmgr,
 				     unsigned long *num_of_entries)
@@ -1499,7 +1515,7 @@ int get_number_of_vce_state_table_entries(
 	const ATOM_PPLIB_VCE_State_Table *vce_table =
 				    get_vce_state_table(hwmgr, table);
 
-	if (vce_table > 0)
+	if (vce_table)
 		return vce_table->numEntries;
 
 	return 0;
@@ -1589,11 +1605,6 @@ static int pp_tables_initialize(struct pp_hwmgr *hwmgr)
 
 static int pp_tables_uninitialize(struct pp_hwmgr *hwmgr)
 {
-	if (NULL != hwmgr->soft_pp_table) {
-		kfree(hwmgr->soft_pp_table);
-		hwmgr->soft_pp_table = NULL;
-	}
-
 	if (NULL != hwmgr->dyn_state.vddc_dependency_on_sclk) {
 		kfree(hwmgr->dyn_state.vddc_dependency_on_sclk);
 		hwmgr->dyn_state.vddc_dependency_on_sclk = NULL;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.h b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.h
index 30434802417e..baddaa75693b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.h
@@ -32,16 +32,19 @@ struct pp_hw_power_state;
 extern const struct pp_table_func pptable_funcs;
 
 typedef int (*pp_tables_hw_clock_info_callback)(struct pp_hwmgr *hwmgr,
-					struct pp_hw_power_state *hw_ps,
-							unsigned int index,
-						 const void *clock_info);
+						struct pp_hw_power_state *hw_ps,
+						unsigned int index,
+						const void *clock_info);
 
 int pp_tables_get_num_of_entries(struct pp_hwmgr *hwmgr,
-				     unsigned long *num_of_entries);
+				 unsigned long *num_of_entries);
 
 int pp_tables_get_entry(struct pp_hwmgr *hwmgr,
-						unsigned long entry_index,
-						struct pp_power_state *ps,
-				pp_tables_hw_clock_info_callback func);
+			unsigned long entry_index,
+			struct pp_power_state *ps,
+			pp_tables_hw_clock_info_callback func);
+
+int pp_tables_get_response_times(struct pp_hwmgr *hwmgr,
+				 uint32_t *vol_rep_time, uint32_t *bb_rep_time);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
index 5d0f655bf160..c7dc111221c2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
@@ -571,7 +571,7 @@ int tonga_disable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if (0 == data->sclk_dpm_key_disabled) {
 		/* Checking if DPM is running.  If we discover hang because of this, we should skip this message.*/
 		PP_ASSERT_WITH_CODE(
-				(0 == tonga_is_dpm_running(hwmgr)),
+				!tonga_is_dpm_running(hwmgr),
 				"Trying to Disable SCLK DPM when DPM is disabled",
 				return -1
 				);
@@ -587,7 +587,7 @@ int tonga_disable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if (0 == data->mclk_dpm_key_disabled) {
 		/* Checking if DPM is running.  If we discover hang because of this, we should skip this message. */
 		PP_ASSERT_WITH_CODE(
-				(0 == tonga_is_dpm_running(hwmgr)),
+				!tonga_is_dpm_running(hwmgr),
 				"Trying to Disable MCLK DPM when DPM is disabled",
 				return -1
 				);
@@ -614,7 +614,7 @@ int tonga_stop_dpm(struct pp_hwmgr *hwmgr)
 	if (0 == data->pcie_dpm_key_disabled) {
 		/* Checking if DPM is running.  If we discover hang because of this, we should skip this message.*/
 		PP_ASSERT_WITH_CODE(
-				(0 == tonga_is_dpm_running(hwmgr)),
+				!tonga_is_dpm_running(hwmgr),
 				"Trying to Disable PCIE DPM when DPM is disabled",
 				return -1
 				);
@@ -630,7 +630,7 @@ int tonga_stop_dpm(struct pp_hwmgr *hwmgr)
 
 	/* Checking if DPM is running.  If we discover hang because of this, we should skip this message.*/
 	PP_ASSERT_WITH_CODE(
-			(0 == tonga_is_dpm_running(hwmgr)),
+			!tonga_is_dpm_running(hwmgr),
 			"Trying to Disable Voltage CNTL when DPM is disabled",
 			return -1
 			);
@@ -688,8 +688,9 @@ int tonga_dpm_force_state(struct pp_hwmgr *hwmgr, uint32_t n)
 	uint32_t level_mask = 1 << n;
 
 	/* Checking if DPM is running.  If we discover hang because of this, we should skip this message. */
-	PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr),
-			"Trying to force SCLK when DPM is disabled", return -1;);
+	PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr),
+			    "Trying to force SCLK when DPM is disabled",
+			    return -1;);
 	if (0 == data->sclk_dpm_key_disabled)
 		return (0 == smum_send_msg_to_smc_with_parameter(
 							     hwmgr->smumgr,
@@ -712,8 +713,9 @@ int tonga_dpm_force_state_mclk(struct pp_hwmgr *hwmgr, uint32_t n)
 	uint32_t level_mask = 1 << n;
 
 	/* Checking if DPM is running.  If we discover hang because of this, we should skip this message. */
-	PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr),
-			"Trying to Force MCLK when DPM is disabled", return -1;);
+	PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr),
+			    "Trying to Force MCLK when DPM is disabled",
+			    return -1;);
 	if (0 == data->mclk_dpm_key_disabled)
 		return (0 == smum_send_msg_to_smc_with_parameter(
 								hwmgr->smumgr,
@@ -735,8 +737,9 @@ int tonga_dpm_force_state_pcie(struct pp_hwmgr *hwmgr, uint32_t n)
 	tonga_hwmgr *data = (tonga_hwmgr *)(hwmgr->backend);
 
 	/* Checking if DPM is running.  If we discover hang because of this, we should skip this message.*/
-	PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr),
-			"Trying to Force PCIE level when DPM is disabled", return -1;);
+	PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr),
+			    "Trying to Force PCIE level when DPM is disabled",
+			    return -1;);
 	if (0 == data->pcie_dpm_key_disabled)
 		return (0 == smum_send_msg_to_smc_with_parameter(
 							     hwmgr->smumgr,
@@ -774,7 +777,7 @@ int tonga_process_firmware_header(struct pp_hwmgr *hwmgr)
 
 	uint32_t tmp;
 	int result;
-	bool error = 0;
+	bool error = false;
 
 	result = tonga_read_smc_sram_dword(hwmgr->smumgr,
 				SMU72_FIRMWARE_HEADER_LOCATION +
@@ -933,11 +936,11 @@ int tonga_init_power_gate_state(struct pp_hwmgr *hwmgr)
 {
 	tonga_hwmgr *data = (tonga_hwmgr *)(hwmgr->backend);
 
-	data->uvd_power_gated = 0;
-	data->vce_power_gated = 0;
-	data->samu_power_gated = 0;
-	data->acp_power_gated = 0;
-	data->pg_acp_init = 1;
+	data->uvd_power_gated = false;
+	data->vce_power_gated = false;
+	data->samu_power_gated = false;
+	data->acp_power_gated = false;
+	data->pg_acp_init = true;
 
 	return 0;
 }
@@ -955,7 +958,7 @@ int tonga_check_for_dpm_running(struct pp_hwmgr *hwmgr)
 	 * because we may have test scenarios that need us intentionly disable SCLK/MCLK DPM,
 	 * whereas voltage control is a fundemental change that will not be disabled
 	 */
-	return (0 == tonga_is_dpm_running(hwmgr) ? 0 : 1);
+	return (!tonga_is_dpm_running(hwmgr) ? 0 : 1);
 }
 
 /**
@@ -968,7 +971,7 @@ int tonga_check_for_dpm_stopped(struct pp_hwmgr *hwmgr)
 {
 	tonga_hwmgr *data = (tonga_hwmgr *)(hwmgr->backend);
 
-	if (0 != tonga_is_dpm_running(hwmgr)) {
+	if (tonga_is_dpm_running(hwmgr)) {
 		/* If HW Virtualization is enabled, dpm_table_start will not have a valid value */
 		if (!data->dpm_table_start) {
 			return 1;
@@ -991,7 +994,7 @@ static int tonga_trim_voltage_table(struct pp_hwmgr *hwmgr,
 {
 	uint32_t table_size, i, j;
 	uint16_t vvalue;
-	bool bVoltageFound = 0;
+	bool bVoltageFound = false;
 	pp_atomctrl_voltage_table *table;
 
 	PP_ASSERT_WITH_CODE((NULL != voltage_table), "Voltage Table empty.", return -1;);
@@ -1007,11 +1010,11 @@ static int tonga_trim_voltage_table(struct pp_hwmgr *hwmgr,
 
 	for (i = 0; i < voltage_table->count; i++) {
 		vvalue = voltage_table->entries[i].value;
-		bVoltageFound = 0;
+		bVoltageFound = false;
 
 		for (j = 0; j < table->count; j++) {
 			if (vvalue == table->entries[j].value) {
-				bVoltageFound = 1;
+				bVoltageFound = true;
 				break;
 			}
 		}
@@ -1331,7 +1334,6 @@ static int tonga_populate_cac_tables(struct pp_hwmgr *hwmgr,
 {
 	uint32_t count;
 	uint8_t index;
-	int result = 0;
 	tonga_hwmgr *data = (tonga_hwmgr *)(hwmgr->backend);
 	struct phm_ppt_v1_information *pptable_info = (struct phm_ppt_v1_information *)(hwmgr->pptable);
 	struct phm_ppt_v1_voltage_lookup_table *vddgfx_lookup_table = pptable_info->vddgfx_lookup_table;
@@ -1378,7 +1380,7 @@ static int tonga_populate_cac_tables(struct pp_hwmgr *hwmgr,
 		}
 	}
 
-	return result;
+	return 0;
 }
 
 
@@ -2042,7 +2044,7 @@ static int tonga_populate_single_memory_level(
 
 	if ((data->mclk_stutter_mode_threshold != 0) &&
 	    (memory_clock <= data->mclk_stutter_mode_threshold) &&
-	    (data->is_uvd_enabled == 0)
+	    (!data->is_uvd_enabled)
 	    && (PHM_READ_FIELD(hwmgr->device, DPG_PIPE_STUTTER_CONTROL, STUTTER_ENABLE) & 0x1)
 	    && (data->display_timing.num_existing_displays <= 2)
 	    && (data->display_timing.num_existing_displays != 0))
@@ -2705,7 +2707,7 @@ static int tonga_reset_single_dpm_table(
 
 	dpm_table->count = count;
 	for (i = 0; i < MAX_REGULAR_DPM_NUMBER; i++) {
-		dpm_table->dpm_levels[i].enabled = 0;
+		dpm_table->dpm_levels[i].enabled = false;
 	}
 
 	return 0;
@@ -2718,7 +2720,7 @@ static void tonga_setup_pcie_table_entry(
 {
 	dpm_table->dpm_levels[index].value = pcie_gen;
 	dpm_table->dpm_levels[index].param1 = pcie_lanes;
-	dpm_table->dpm_levels[index].enabled = 1;
+	dpm_table->dpm_levels[index].enabled = true;
 }
 
 static int tonga_setup_default_pcie_tables(struct pp_hwmgr *hwmgr)
@@ -2828,7 +2830,7 @@ static int tonga_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 				allowed_vdd_sclk_table->entries[i].clk) {
 			data->dpm_table.sclk_table.dpm_levels[data->dpm_table.sclk_table.count].value =
 				allowed_vdd_sclk_table->entries[i].clk;
-			data->dpm_table.sclk_table.dpm_levels[data->dpm_table.sclk_table.count].enabled = 1; /*(i==0) ? 1 : 0; to do */
+			data->dpm_table.sclk_table.dpm_levels[data->dpm_table.sclk_table.count].enabled = true; /*(i==0) ? 1 : 0; to do */
 			data->dpm_table.sclk_table.count++;
 		}
 	}
@@ -2842,7 +2844,7 @@ static int tonga_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 			allowed_vdd_mclk_table->entries[i].clk) {
 			data->dpm_table.mclk_table.dpm_levels[data->dpm_table.mclk_table.count].value =
 				allowed_vdd_mclk_table->entries[i].clk;
-			data->dpm_table.mclk_table.dpm_levels[data->dpm_table.mclk_table.count].enabled = 1; /*(i==0) ? 1 : 0; */
+			data->dpm_table.mclk_table.dpm_levels[data->dpm_table.mclk_table.count].enabled = true; /*(i==0) ? 1 : 0; */
 			data->dpm_table.mclk_table.count++;
 		}
 	}
@@ -3026,8 +3028,8 @@ int tonga_init_smc_table(struct pp_hwmgr *hwmgr)
 
 	reg_value = 0;
 	if ((0 == reg_value) &&
-		(0 == atomctrl_get_pp_assign_pin(hwmgr,
-			VDDC_VRHOT_GPIO_PINID, &gpio_pin_assignment))) {
+		(atomctrl_get_pp_assign_pin(hwmgr, VDDC_VRHOT_GPIO_PINID,
+						&gpio_pin_assignment))) {
 		table->VRHotGpio = gpio_pin_assignment.uc_gpio_pin_bit_shift;
 		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 			PHM_PlatformCaps_RegulatorHot);
@@ -3040,8 +3042,8 @@ int tonga_init_smc_table(struct pp_hwmgr *hwmgr)
 	/* ACDC Switch GPIO */
 	reg_value = 0;
 	if ((0 == reg_value) &&
-		(0 == atomctrl_get_pp_assign_pin(hwmgr,
-			PP_AC_DC_SWITCH_GPIO_PINID, &gpio_pin_assignment))) {
+		(atomctrl_get_pp_assign_pin(hwmgr, PP_AC_DC_SWITCH_GPIO_PINID,
+						&gpio_pin_assignment))) {
 		table->AcDcGpio = gpio_pin_assignment.uc_gpio_pin_bit_shift;
 		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 			PHM_PlatformCaps_AutomaticDCTransition);
@@ -3063,8 +3065,7 @@ int tonga_init_smc_table(struct pp_hwmgr *hwmgr)
 	}
 
 	reg_value = 0;
-	if ((0 == reg_value) &&
-		(0 == atomctrl_get_pp_assign_pin(hwmgr,
+	if ((0 == reg_value) && (atomctrl_get_pp_assign_pin(hwmgr,
 			THERMAL_INT_OUTPUT_GPIO_PINID, &gpio_pin_assignment))) {
 		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 			PHM_PlatformCaps_ThermalOutGPIO);
@@ -3135,7 +3136,7 @@ int tonga_upload_dpm_level_enable_mask(struct pp_hwmgr *hwmgr)
 
 	if (0 == data->sclk_dpm_key_disabled) {
 		/* Checking if DPM is running.  If we discover hang because of this, we should skip this message.*/
-		if (0 != tonga_is_dpm_running(hwmgr))
+		if (tonga_is_dpm_running(hwmgr))
 			printk(KERN_ERR "[ powerplay ] Trying to set Enable Mask when DPM is disabled \n");
 
 		if (0 != data->dpm_level_enable_mask.sclk_dpm_enable_mask) {
@@ -3150,7 +3151,7 @@ int tonga_upload_dpm_level_enable_mask(struct pp_hwmgr *hwmgr)
 
 	if (0 == data->mclk_dpm_key_disabled) {
 		/* Checking if DPM is running.  If we discover hang because of this, we should skip this message.*/
-		if (0 != tonga_is_dpm_running(hwmgr))
+		if (tonga_is_dpm_running(hwmgr))
 			printk(KERN_ERR "[ powerplay ] Trying to set Enable Mask when DPM is disabled \n");
 
 		if (0 != data->dpm_level_enable_mask.mclk_dpm_enable_mask) {
@@ -3261,7 +3262,7 @@ int tonga_initializa_dynamic_state_adjustment_rule_settings(struct pp_hwmgr *hwm
 
 	/* initialize vddc_dep_on_dal_pwrl table */
 	table_size = sizeof(uint32_t) + 4 * sizeof(struct phm_clock_voltage_dependency_record);
-	table_clk_vlt = (struct phm_clock_voltage_dependency_table *)kzalloc(table_size, GFP_KERNEL);
+	table_clk_vlt = kzalloc(table_size, GFP_KERNEL);
 
 	if (NULL == table_clk_vlt) {
 		printk(KERN_ERR "[ powerplay ] Can not allocate space for vddc_dep_on_dal_pwrl! \n");
@@ -3336,9 +3337,9 @@ int tonga_unforce_dpm_levels(struct pp_hwmgr *hwmgr)
 	tonga_hwmgr *data = (tonga_hwmgr *)(hwmgr->backend);
 	int result = 1;
 
-	PP_ASSERT_WITH_CODE (0 == tonga_is_dpm_running(hwmgr),
-		"Trying to Unforce DPM when DPM is disabled. Returning without sending SMC message.",
-							return result);
+	PP_ASSERT_WITH_CODE (!tonga_is_dpm_running(hwmgr),
+			     "Trying to Unforce DPM when DPM is disabled. Returning without sending SMC message.",
+			     return result);
 
 	if (0 == data->pcie_dpm_key_disabled) {
 		PP_ASSERT_WITH_CODE((0 == smum_send_msg_to_smc(
@@ -3742,7 +3743,7 @@ uint8_t tonga_get_memory_modile_index(struct pp_hwmgr *hwmgr)
 
 bool tonga_check_s0_mc_reg_index(uint16_t inReg, uint16_t *outReg)
 {
-	bool result = 1;
+	bool result = true;
 
 	switch (inReg) {
 	case  mmMC_SEQ_RAS_TIMING:
@@ -3826,7 +3827,7 @@ bool tonga_check_s0_mc_reg_index(uint16_t inReg, uint16_t *outReg)
 		break;
 
 	default:
-		result = 0;
+		result = false;
 		break;
 	}
 
@@ -4422,13 +4423,6 @@ int tonga_reset_asic_tasks(struct pp_hwmgr *hwmgr)
 
 int tonga_hwmgr_backend_fini(struct pp_hwmgr *hwmgr)
 {
-	struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend);
-
-	if (data->soft_pp_table) {
-		kfree(data->soft_pp_table);
-		data->soft_pp_table = NULL;
-	}
-
 	return phm_hwmgr_backend_fini(hwmgr);
 }
 
@@ -4442,7 +4436,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 {
 	int result = 0;
 	SMU72_Discrete_DpmTable  *table = NULL;
-	tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend);
+	tonga_hwmgr *data;
 	pp_atomctrl_gpio_pin_assignment gpio_pin_assignment;
 	struct phm_ppt_v1_information *pptable_info = (struct phm_ppt_v1_information *)(hwmgr->pptable);
 	phw_tonga_ulv_parm *ulv;
@@ -4451,7 +4445,13 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE((NULL != hwmgr),
 		"Invalid Parameter!", return -1;);
 
-	data->dll_defaule_on = 0;
+	data = kzalloc(sizeof(struct tonga_hwmgr), GFP_KERNEL);
+	if (data == NULL)
+		return -ENOMEM;
+
+	hwmgr->backend = data;
+
+	data->dll_defaule_on = false;
 	data->sram_end = SMC_RAM_END;
 
 	data->activity_target[0] = PPTONGA_TARGETACTIVITY_DFLT;
@@ -4557,13 +4557,13 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 
 	/* ULV Support*/
 	ulv = &(data->ulv);
-	ulv->ulv_supported = 0;
+	ulv->ulv_supported = false;
 
 	/* Initalize Dynamic State Adjustment Rule Settings*/
 	result = tonga_initializa_dynamic_state_adjustment_rule_settings(hwmgr);
 	if (result)
 		printk(KERN_ERR "[ powerplay ] tonga_initializa_dynamic_state_adjustment_rule_settings failed!\n");
-	data->uvd_enabled = 0;
+	data->uvd_enabled = false;
 
 	table = &(data->smc_state_table);
 
@@ -4571,7 +4571,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	* if ucGPIO_ID=VDDC_PCC_GPIO_PINID in GPIO_LUTable,
 	* Peak Current Control feature is enabled and we should program PCC HW register
 	*/
-	if (0 == atomctrl_get_pp_assign_pin(hwmgr, VDDC_PCC_GPIO_PINID, &gpio_pin_assignment)) {
+	if (atomctrl_get_pp_assign_pin(hwmgr, VDDC_PCC_GPIO_PINID, &gpio_pin_assignment)) {
 		uint32_t temp_reg = cgs_read_ind_register(hwmgr->device,
 										CGS_IND_REG__SMC, ixCNB_PWRMGT_CNTL);
 
@@ -4610,7 +4610,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 		PHM_PlatformCaps_SMU7);
 
-	data->vddc_phase_shed_control = 0;
+	data->vddc_phase_shed_control = false;
 
 	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
 		      PHM_PlatformCaps_UVDPowerGating);
@@ -4629,7 +4629,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	}
 
 	if (0 == result) {
-		data->is_tlu_enabled = 0;
+		data->is_tlu_enabled = false;
 		hwmgr->platform_descriptor.hardwareActivityPerformanceLevels =
 			TONGA_MAX_HARDWARE_POWERLEVELS;
 		hwmgr->platform_descriptor.hardwarePerformanceLevels = 2;
@@ -4639,7 +4639,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 		sys_info.info_id = CGS_SYSTEM_INFO_PCIE_GEN_INFO;
 		result = cgs_query_system_info(hwmgr->device, &sys_info);
 		if (result)
-			data->pcie_gen_cap = 0x30007;
+			data->pcie_gen_cap = AMDGPU_DEFAULT_PCIE_GEN_MASK;
 		else
 			data->pcie_gen_cap = (uint32_t)sys_info.value;
 		if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
@@ -4648,7 +4648,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 		sys_info.info_id = CGS_SYSTEM_INFO_PCIE_MLW;
 		result = cgs_query_system_info(hwmgr->device, &sys_info);
 		if (result)
-			data->pcie_lane_cap = 0x2f0000;
+			data->pcie_lane_cap = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		else
 			data->pcie_lane_cap = (uint32_t)sys_info.value;
 	} else {
@@ -5310,9 +5310,8 @@ static int tonga_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if ((0 == data->sclk_dpm_key_disabled) &&
 		(data->need_update_smu7_dpm_table &
 		(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) {
-		PP_ASSERT_WITH_CODE(
-			0 == tonga_is_dpm_running(hwmgr),
-			"Trying to freeze SCLK DPM when DPM is disabled",
+		PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr),
+				    "Trying to freeze SCLK DPM when DPM is disabled",
 			);
 		PP_ASSERT_WITH_CODE(
 			0 == smum_send_msg_to_smc(hwmgr->smumgr,
@@ -5324,8 +5323,8 @@ static int tonga_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if ((0 == data->mclk_dpm_key_disabled) &&
 		(data->need_update_smu7_dpm_table &
 		 DPMTABLE_OD_UPDATE_MCLK)) {
-		PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr),
-			"Trying to freeze MCLK DPM when DPM is disabled",
+		PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr),
+				    "Trying to freeze MCLK DPM when DPM is disabled",
 			);
 		PP_ASSERT_WITH_CODE(
 			0 == smum_send_msg_to_smc(hwmgr->smumgr,
@@ -5460,7 +5459,6 @@ static	int tonga_trim_single_dpm_states(struct pp_hwmgr *hwmgr,
 
 static int tonga_trim_dpm_states(struct pp_hwmgr *hwmgr, const struct tonga_power_state *hw_state)
 {
-	int result = 0;
 	struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend);
 	uint32_t high_limit_count;
 
@@ -5480,7 +5478,7 @@ static int tonga_trim_dpm_states(struct pp_hwmgr *hwmgr, const struct tonga_powe
 						hw_state->performance_levels[0].memory_clock,
 						hw_state->performance_levels[high_limit_count].memory_clock);
 
-	return result;
+	return 0;
 }
 
 static int tonga_generate_dpm_level_enable_mask(struct pp_hwmgr *hwmgr, const void *input)
@@ -5627,8 +5625,8 @@ static int tonga_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 		(data->need_update_smu7_dpm_table &
 		(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) {
 
-		PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr),
-			"Trying to Unfreeze SCLK DPM when DPM is disabled",
+		PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr),
+				    "Trying to Unfreeze SCLK DPM when DPM is disabled",
 			);
 		PP_ASSERT_WITH_CODE(
 			 0 == smum_send_msg_to_smc(hwmgr->smumgr,
@@ -5640,9 +5638,8 @@ static int tonga_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 	if ((0 == data->mclk_dpm_key_disabled) &&
 		(data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) {
 
-		PP_ASSERT_WITH_CODE(
-				0 == tonga_is_dpm_running(hwmgr),
-				"Trying to Unfreeze MCLK DPM when DPM is disabled",
+		PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr),
+				    "Trying to Unfreeze MCLK DPM when DPM is disabled",
 				);
 		PP_ASSERT_WITH_CODE(
 			 0 == smum_send_msg_to_smc(hwmgr->smumgr,
@@ -6031,42 +6028,6 @@ static int tonga_get_fan_control_mode(struct pp_hwmgr *hwmgr)
 				CG_FDO_CTRL2, FDO_PWM_MODE);
 }
 
-static int tonga_get_pp_table(struct pp_hwmgr *hwmgr, char **table)
-{
-	struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend);
-
-	if (!data->soft_pp_table) {
-		data->soft_pp_table = kmemdup(hwmgr->soft_pp_table,
-					      hwmgr->soft_pp_table_size,
-					      GFP_KERNEL);
-		if (!data->soft_pp_table)
-			return -ENOMEM;
-	}
-
-	*table = (char *)&data->soft_pp_table;
-
-	return hwmgr->soft_pp_table_size;
-}
-
-static int tonga_set_pp_table(struct pp_hwmgr *hwmgr, const char *buf, size_t size)
-{
-	struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend);
-
-	if (!data->soft_pp_table) {
-		data->soft_pp_table = kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL);
-		if (!data->soft_pp_table)
-			return -ENOMEM;
-	}
-
-	memcpy(data->soft_pp_table, buf, size);
-
-	hwmgr->soft_pp_table = data->soft_pp_table;
-
-	/* TODO: re-init powerplay to implement modified pptable */
-
-	return 0;
-}
-
 static int tonga_force_clock_level(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, uint32_t mask)
 {
@@ -6174,11 +6135,96 @@ static int tonga_print_clock_levels(struct pp_hwmgr *hwmgr,
 	return size;
 }
 
+static int tonga_get_sclk_od(struct pp_hwmgr *hwmgr)
+{
+	struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend);
+	struct tonga_single_dpm_table *sclk_table = &(data->dpm_table.sclk_table);
+	struct tonga_single_dpm_table *golden_sclk_table =
+			&(data->golden_dpm_table.sclk_table);
+	int value;
+
+	value = (sclk_table->dpm_levels[sclk_table->count - 1].value -
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value) *
+			100 /
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value;
+
+	return value;
+}
+
+static int tonga_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value)
+{
+	struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend);
+	struct tonga_single_dpm_table *golden_sclk_table =
+			&(data->golden_dpm_table.sclk_table);
+	struct pp_power_state  *ps;
+	struct tonga_power_state  *tonga_ps;
+
+	if (value > 20)
+		value = 20;
+
+	ps = hwmgr->request_ps;
+
+	if (ps == NULL)
+		return -EINVAL;
+
+	tonga_ps = cast_phw_tonga_power_state(&ps->hardware);
+
+	tonga_ps->performance_levels[tonga_ps->performance_level_count - 1].engine_clock =
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value *
+			value / 100 +
+			golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value;
+
+	return 0;
+}
+
+static int tonga_get_mclk_od(struct pp_hwmgr *hwmgr)
+{
+	struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend);
+	struct tonga_single_dpm_table *mclk_table = &(data->dpm_table.mclk_table);
+	struct tonga_single_dpm_table *golden_mclk_table =
+			&(data->golden_dpm_table.mclk_table);
+	int value;
+
+	value = (mclk_table->dpm_levels[mclk_table->count - 1].value -
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value) *
+			100 /
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value;
+
+	return value;
+}
+
+static int tonga_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value)
+{
+	struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend);
+	struct tonga_single_dpm_table *golden_mclk_table =
+			&(data->golden_dpm_table.mclk_table);
+	struct pp_power_state  *ps;
+	struct tonga_power_state  *tonga_ps;
+
+	if (value > 20)
+		value = 20;
+
+	ps = hwmgr->request_ps;
+
+	if (ps == NULL)
+		return -EINVAL;
+
+	tonga_ps = cast_phw_tonga_power_state(&ps->hardware);
+
+	tonga_ps->performance_levels[tonga_ps->performance_level_count - 1].memory_clock =
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value *
+			value / 100 +
+			golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value;
+
+	return 0;
+}
+
 static const struct pp_hwmgr_func tonga_hwmgr_funcs = {
 	.backend_init = &tonga_hwmgr_backend_init,
 	.backend_fini = &tonga_hwmgr_backend_fini,
 	.asic_setup = &tonga_setup_asic_task,
 	.dynamic_state_management_enable = &tonga_enable_dpm_tasks,
+	.dynamic_state_management_disable = &tonga_disable_dpm_tasks,
 	.apply_state_adjust_rules = tonga_apply_state_adjust_rules,
 	.force_dpm_level = &tonga_force_dpm_level,
 	.power_state_set = tonga_set_power_state_tasks,
@@ -6212,22 +6258,16 @@ static const struct pp_hwmgr_func tonga_hwmgr_funcs = {
 	.check_states_equal = tonga_check_states_equal,
 	.set_fan_control_mode = tonga_set_fan_control_mode,
 	.get_fan_control_mode = tonga_get_fan_control_mode,
-	.get_pp_table = tonga_get_pp_table,
-	.set_pp_table = tonga_set_pp_table,
 	.force_clock_level = tonga_force_clock_level,
 	.print_clock_levels = tonga_print_clock_levels,
+	.get_sclk_od = tonga_get_sclk_od,
+	.set_sclk_od = tonga_set_sclk_od,
+	.get_mclk_od = tonga_get_mclk_od,
+	.set_mclk_od = tonga_set_mclk_od,
 };
 
 int tonga_hwmgr_init(struct pp_hwmgr *hwmgr)
 {
-	tonga_hwmgr  *data;
-
-	data = kzalloc (sizeof(tonga_hwmgr), GFP_KERNEL);
-	if (data == NULL)
-		return -ENOMEM;
-	memset(data, 0x00, sizeof(tonga_hwmgr));
-
-	hwmgr->backend = data;
 	hwmgr->hwmgr_func = &tonga_hwmgr_funcs;
 	hwmgr->pptable_func = &tonga_pptable_funcs;
 	pp_tonga_thermal_initialize(hwmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h
index 573cd39fe78d..3961884bfa9b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h
@@ -352,9 +352,6 @@ struct tonga_hwmgr {
 	bool                           samu_power_gated; /* 1: gated, 0:not gated */
 	bool                           acp_power_gated;  /* 1: gated, 0:not gated */
 	bool                           pg_acp_init;
-
-	/* soft pptable for re-uploading into smu */
-	void *soft_pp_table;
 };
 
 typedef struct tonga_hwmgr tonga_hwmgr;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
index dccc859f638c..cfb647f76cbe 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
@@ -167,8 +167,7 @@ static int get_vddc_lookup_table(
 	table_size = sizeof(uint32_t) +
 		sizeof(phm_ppt_v1_voltage_lookup_record) * max_levels;
 
-	table = (phm_ppt_v1_voltage_lookup_table *)
-		kzalloc(table_size, GFP_KERNEL);
+	table = kzalloc(table_size, GFP_KERNEL);
 
 	if (NULL == table)
 		return -ENOMEM;
@@ -327,7 +326,7 @@ static int get_valid_clk(
 	table_size = sizeof(uint32_t) +
 		sizeof(uint32_t) * clk_volt_pp_table->count;
 
-	table = (struct phm_clock_array *)kzalloc(table_size, GFP_KERNEL);
+	table = kzalloc(table_size, GFP_KERNEL);
 
 	if (NULL == table)
 		return -ENOMEM;
@@ -377,8 +376,7 @@ static int get_mclk_voltage_dependency_table(
 	table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record)
 		* mclk_dep_table->ucNumEntries;
 
-	mclk_table = (phm_ppt_v1_clock_voltage_dependency_table *)
-		kzalloc(table_size, GFP_KERNEL);
+	mclk_table = kzalloc(table_size, GFP_KERNEL);
 
 	if (NULL == mclk_table)
 		return -ENOMEM;
@@ -424,8 +422,7 @@ static int get_sclk_voltage_dependency_table(
 		table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record)
 			* tonga_table->ucNumEntries;
 
-		sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *)
-			kzalloc(table_size, GFP_KERNEL);
+		sclk_table = kzalloc(table_size, GFP_KERNEL);
 
 		if (NULL == sclk_table)
 			return -ENOMEM;
@@ -456,8 +453,7 @@ static int get_sclk_voltage_dependency_table(
 		table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record)
 			* polaris_table->ucNumEntries;
 
-		sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *)
-			kzalloc(table_size, GFP_KERNEL);
+		sclk_table = kzalloc(table_size, GFP_KERNEL);
 
 		if (NULL == sclk_table)
 			return -ENOMEM;
@@ -504,7 +500,7 @@ static int get_pcie_table(
 		table_size = sizeof(uint32_t) +
 			sizeof(phm_ppt_v1_pcie_record) * atom_pcie_table->ucNumEntries;
 
-		pcie_table = (phm_ppt_v1_pcie_table *)kzalloc(table_size, GFP_KERNEL);
+		pcie_table = kzalloc(table_size, GFP_KERNEL);
 
 		if (pcie_table == NULL)
 			return -ENOMEM;
@@ -541,7 +537,7 @@ static int get_pcie_table(
 		table_size = sizeof(uint32_t) +
 			sizeof(phm_ppt_v1_pcie_record) * atom_pcie_table->ucNumEntries;
 
-		pcie_table = (phm_ppt_v1_pcie_table *)kzalloc(table_size, GFP_KERNEL);
+		pcie_table = kzalloc(table_size, GFP_KERNEL);
 
 		if (pcie_table == NULL)
 			return -ENOMEM;
@@ -695,8 +691,7 @@ static int get_mm_clock_voltage_table(
 	table_size = sizeof(uint32_t) +
 		sizeof(phm_ppt_v1_mm_clock_voltage_dependency_record)
 		* mm_dependency_table->ucNumEntries;
-	mm_table = (phm_ppt_v1_mm_clock_voltage_dependency_table *)
-		kzalloc(table_size, GFP_KERNEL);
+	mm_table = kzalloc(table_size, GFP_KERNEL);
 
 	if (NULL == mm_table)
 		return -ENOMEM;
@@ -1073,13 +1068,9 @@ int tonga_pp_tables_initialize(struct pp_hwmgr *hwmgr)
 
 int tonga_pp_tables_uninitialize(struct pp_hwmgr *hwmgr)
 {
-	int result = 0;
 	struct phm_ppt_v1_information *pp_table_information =
 		(struct phm_ppt_v1_information *)(hwmgr->pptable);
 
-	if (NULL != hwmgr->soft_pp_table)
-		hwmgr->soft_pp_table = NULL;
-
 	kfree(pp_table_information->vdd_dep_on_sclk);
 	pp_table_information->vdd_dep_on_sclk = NULL;
 
@@ -1116,7 +1107,7 @@ int tonga_pp_tables_uninitialize(struct pp_hwmgr *hwmgr)
 	kfree(hwmgr->pptable);
 	hwmgr->pptable = NULL;
 
-	return result;
+	return 0;
 }
 
 const struct pp_table_func tonga_pptable_funcs = {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h b/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h
index 50b367d44307..b764c8c05ec8 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h
@@ -132,6 +132,7 @@ struct amd_pp_init {
 	uint32_t chip_family;
 	uint32_t chip_id;
 	uint32_t rev_id;
+	bool powercontainment_enabled;
 };
 enum amd_pp_display_config_type{
 	AMD_PP_DisplayConfigType_None = 0,
@@ -342,6 +343,10 @@ struct amd_powerplay_funcs {
 	int (*set_pp_table)(void *handle, const char *buf, size_t size);
 	int (*force_clock_level)(void *handle, enum pp_clock_type type, uint32_t mask);
 	int (*print_clock_levels)(void *handle, enum pp_clock_type type, char *buf);
+	int (*get_sclk_od)(void *handle);
+	int (*set_sclk_od)(void *handle, uint32_t value);
+	int (*get_mclk_od)(void *handle);
+	int (*set_mclk_od)(void *handle, uint32_t value);
 };
 
 struct amd_powerplay {
@@ -355,6 +360,8 @@ int amd_powerplay_init(struct amd_pp_init *pp_init,
 
 int amd_powerplay_fini(void *handle);
 
+int amd_powerplay_reset(void *handle);
+
 int amd_powerplay_display_configuration_change(void *handle,
 		const struct amd_pp_display_configuration *input);
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
index 56f712c7d07a..962cb5385951 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
@@ -340,6 +340,7 @@ extern int phm_powergate_vce(struct pp_hwmgr *hwmgr, bool gate);
 extern int phm_powerdown_uvd(struct pp_hwmgr *hwmgr);
 extern int phm_setup_asic(struct pp_hwmgr *hwmgr);
 extern int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr);
+extern int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr);
 extern void phm_init_dynamic_caps(struct pp_hwmgr *hwmgr);
 extern bool phm_is_hw_access_blocked(struct pp_hwmgr *hwmgr);
 extern int phm_block_hw_access(struct pp_hwmgr *hwmgr, bool block);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 77e8e33d5870..bf0d2accf7bf 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -278,6 +278,8 @@ struct pp_hwmgr_func {
 
 	int (*dynamic_state_management_enable)(
 						struct pp_hwmgr *hw_mgr);
+	int (*dynamic_state_management_disable)(
+						struct pp_hwmgr *hw_mgr);
 
 	int (*patch_boot_state)(struct pp_hwmgr *hwmgr,
 				     struct pp_hw_power_state *hw_ps);
@@ -333,11 +335,13 @@ struct pp_hwmgr_func {
 	int (*get_clock_by_type)(struct pp_hwmgr *hwmgr, enum amd_pp_clock_type type, struct amd_pp_clocks *clocks);
 	int (*get_max_high_clocks)(struct pp_hwmgr *hwmgr, struct amd_pp_simple_clock_info *clocks);
 	int (*power_off_asic)(struct pp_hwmgr *hwmgr);
-	int (*get_pp_table)(struct pp_hwmgr *hwmgr, char **table);
-	int (*set_pp_table)(struct pp_hwmgr *hwmgr, const char *buf, size_t size);
 	int (*force_clock_level)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, uint32_t mask);
 	int (*print_clock_levels)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, char *buf);
 	int (*enable_per_cu_power_gating)(struct pp_hwmgr *hwmgr, bool enable);
+	int (*get_sclk_od)(struct pp_hwmgr *hwmgr);
+	int (*set_sclk_od)(struct pp_hwmgr *hwmgr, uint32_t value);
+	int (*get_mclk_od)(struct pp_hwmgr *hwmgr);
+	int (*set_mclk_od)(struct pp_hwmgr *hwmgr, uint32_t value);
 };
 
 struct pp_table_func {
@@ -580,6 +584,7 @@ struct pp_hwmgr {
 	struct pp_smumgr *smumgr;
 	const void *soft_pp_table;
 	uint32_t soft_pp_table_size;
+	void *hardcode_pp_table;
 	bool need_pp_table_upload;
 	enum amd_dpm_forced_level dpm_level;
 	bool block_hw_access;
@@ -609,6 +614,7 @@ struct pp_hwmgr {
 	uint32_t num_ps;
 	struct pp_thermal_controller_info thermal_controller;
 	bool fan_ctrl_is_in_default_mode;
+	bool powercontainment_enabled;
 	uint32_t fan_ctrl_default_mode;
 	uint32_t tmin;
 	struct phm_microcode_version_info microcode_version_info;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
index fc9e3d1dd409..3c235f0177cd 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
@@ -131,6 +131,12 @@ extern int smu_free_memory(void *device, void *handle);
 	smum_wait_on_indirect_register(smumgr,				\
 				mm##port##_INDEX, index, value, mask)
 
+#define SMUM_WAIT_INDIRECT_REGISTER(smumgr, port, reg, value, mask)    \
+	    SMUM_WAIT_INDIRECT_REGISTER_GIVEN_INDEX(smumgr, port, ix##reg, value, mask)
+
+#define SMUM_WAIT_INDIRECT_FIELD(smumgr, port, reg, field, fieldval)                          \
+	    SMUM_WAIT_INDIRECT_REGISTER(smumgr, port, reg, (fieldval) << SMUM_FIELD_SHIFT(reg, field), \
+			            SMUM_FIELD_MASK(reg, field) )
 
 #define SMUM_WAIT_REGISTER_UNEQUAL_GIVEN_INDEX(smumgr,         \
 							index, value, mask) \
@@ -158,6 +164,10 @@ extern int smu_free_memory(void *device, void *handle);
 		(SMUM_FIELD_MASK(reg, field) & ((field_val) <<                 \
 			SMUM_FIELD_SHIFT(reg, field))))
 
+#define SMUM_READ_INDIRECT_FIELD(device, port, reg, field) \
+	    SMUM_GET_FIELD(cgs_read_ind_register(device, port, ix##reg), \
+			   reg, field)
+
 #define SMUM_WAIT_VFPF_INDIRECT_REGISTER_GIVEN_INDEX(smumgr,		\
 				port, index, value, mask)		\
 	smum_wait_on_indirect_register(smumgr,				\
@@ -191,6 +201,13 @@ extern int smu_free_memory(void *device, void *handle);
 			SMUM_SET_FIELD(cgs_read_ind_register(device, port, ix##reg), \
 			reg, field, fieldval))
 
+
+#define SMUM_WRITE_INDIRECT_FIELD(device, port, reg, field, fieldval)    		\
+		cgs_write_ind_register(device, port, ix##reg, 				\
+			SMUM_SET_FIELD(cgs_read_ind_register(device, port, ix##reg), 	\
+				       reg, field, fieldval))
+
+
 #define SMUM_WAIT_VFPF_INDIRECT_FIELD(smumgr, port, reg, field, fieldval) \
 	SMUM_WAIT_VFPF_INDIRECT_REGISTER(smumgr, port, reg,		\
 		(fieldval) << SMUM_FIELD_SHIFT(reg, field),		\
@@ -200,4 +217,16 @@ extern int smu_free_memory(void *device, void *handle);
 	SMUM_WAIT_VFPF_INDIRECT_REGISTER_UNEQUAL(smumgr, port, reg,	\
 		(fieldval) << SMUM_FIELD_SHIFT(reg, field),		\
 		SMUM_FIELD_MASK(reg, field))
+
+#define SMUM_WAIT_INDIRECT_REGISTER_UNEQUAL_GIVEN_INDEX(smumgr, port, index, value, mask)    \
+	smum_wait_for_indirect_register_unequal(smumgr,			\
+		mm##port##_INDEX, index, value, mask)
+
+#define SMUM_WAIT_INDIRECT_REGISTER_UNEQUAL(smumgr, port, reg, value, mask)    \
+	    SMUM_WAIT_INDIRECT_REGISTER_UNEQUAL_GIVEN_INDEX(smumgr, port, ix##reg, value, mask)
+
+#define SMUM_WAIT_INDIRECT_FIELD_UNEQUAL(smumgr, port, reg, field, fieldval)                          \
+	    SMUM_WAIT_INDIRECT_REGISTER_UNEQUAL(smumgr, port, reg, (fieldval) << SMUM_FIELD_SHIFT(reg, field), \
+			            SMUM_FIELD_MASK(reg, field) )
+
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
index 0728c1e3d97a..7723473e51a0 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <drm/amdgpu_drm.h>
 #include "pp_instance.h"
 #include "smumgr.h"
 #include "cgs_common.h"
@@ -52,10 +53,10 @@ int smum_init(struct amd_pp_init *pp_init, struct pp_instance *handle)
 	handle->smu_mgr = smumgr;
 
 	switch (smumgr->chip_family) {
-	case AMD_FAMILY_CZ:
+	case AMDGPU_FAMILY_CZ:
 		cz_smum_init(smumgr);
 		break;
-	case AMD_FAMILY_VI:
+	case AMDGPU_FAMILY_VI:
 		switch (smumgr->chip_id) {
 		case CHIP_TONGA:
 			tonga_smum_init(smumgr);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
index b22722eabafc..f42c536b3af1 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
@@ -479,7 +479,6 @@ static int tonga_request_smu_reload_fw(struct pp_smumgr *smumgr)
 	struct tonga_smumgr *tonga_smu =
 		(struct tonga_smumgr *)(smumgr->backend);
 	uint16_t fw_to_load;
-	int result = 0;
 	struct SMU_DRAMData_TOC *toc;
 	/**
 	 * First time this gets called during SmuMgr init,
@@ -563,7 +562,7 @@ static int tonga_request_smu_reload_fw(struct pp_smumgr *smumgr)
 		smumgr, PPSMC_MSG_LoadUcodes, fw_to_load),
 		"Fail to Request SMU Load uCode", return 0);
 
-	return result;
+	return 0;
 }
 
 static int tonga_request_smu_load_specific_fw(struct pp_smumgr *smumgr,
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
index c89dc777768f..b961a1c6caf3 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
@@ -26,7 +26,7 @@ TRACE_EVENT(amd_sched_job,
 	    TP_fast_assign(
 			   __entry->entity = sched_job->s_entity;
 			   __entry->sched_job = sched_job;
-			   __entry->fence = &sched_job->s_fence->base;
+			   __entry->fence = &sched_job->s_fence->finished;
 			   __entry->name = sched_job->sched->name;
 			   __entry->job_count = kfifo_len(
 				   &sched_job->s_entity->job_queue) / sizeof(sched_job);
@@ -46,7 +46,7 @@ TRACE_EVENT(amd_sched_process_job,
 		    ),
 
 	    TP_fast_assign(
-		    __entry->fence = &fence->base;
+		    __entry->fence = &fence->finished;
 		    ),
 	    TP_printk("fence=%p signaled", __entry->fence)
 );
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index c16248cee779..ef312bb75fda 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -32,6 +32,7 @@
 
 static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity);
 static void amd_sched_wakeup(struct amd_gpu_scheduler *sched);
+static void amd_sched_process_job(struct fence *f, struct fence_cb *cb);
 
 struct kmem_cache *sched_fence_slab;
 atomic_t sched_fence_slab_ref = ATOMIC_INIT(0);
@@ -140,7 +141,7 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 		return r;
 
 	atomic_set(&entity->fence_seq, 0);
-	entity->fence_context = fence_context_alloc(1);
+	entity->fence_context = fence_context_alloc(2);
 
 	return 0;
 }
@@ -251,17 +252,21 @@ static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)
 
 	s_fence = to_amd_sched_fence(fence);
 	if (s_fence && s_fence->sched == sched) {
-		/* Fence is from the same scheduler */
-		if (test_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &fence->flags)) {
-			/* Ignore it when it is already scheduled */
-			fence_put(entity->dependency);
-			return false;
-		}
 
-		/* Wait for fence to be scheduled */
-		entity->cb.func = amd_sched_entity_clear_dep;
-		list_add_tail(&entity->cb.node, &s_fence->scheduled_cb);
-		return true;
+		/*
+		 * Fence is from the same scheduler, only need to wait for
+		 * it to be scheduled
+		 */
+		fence = fence_get(&s_fence->scheduled);
+		fence_put(entity->dependency);
+		entity->dependency = fence;
+		if (!fence_add_callback(fence, &entity->cb,
+					amd_sched_entity_clear_dep))
+			return true;
+
+		/* Ignore it when it is already scheduled */
+		fence_put(fence);
+		return false;
 	}
 
 	if (!fence_add_callback(entity->dependency, &entity->cb,
@@ -319,46 +324,114 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 	return added;
 }
 
-static void amd_sched_free_job(struct fence *f, struct fence_cb *cb) {
-	struct amd_sched_job *job = container_of(cb, struct amd_sched_job, cb_free_job);
-	schedule_work(&job->work_free_job);
-}
-
 /* job_finish is called after hw fence signaled, and
  * the job had already been deleted from ring_mirror_list
  */
-void amd_sched_job_finish(struct amd_sched_job *s_job)
+static void amd_sched_job_finish(struct work_struct *work)
 {
-	struct amd_sched_job *next;
+	struct amd_sched_job *s_job = container_of(work, struct amd_sched_job,
+						   finish_work);
 	struct amd_gpu_scheduler *sched = s_job->sched;
 
+	/* remove job from ring_mirror_list */
+	spin_lock(&sched->job_list_lock);
+	list_del_init(&s_job->node);
 	if (sched->timeout != MAX_SCHEDULE_TIMEOUT) {
-		if (cancel_delayed_work(&s_job->work_tdr))
-			amd_sched_job_put(s_job);
+		struct amd_sched_job *next;
+
+		spin_unlock(&sched->job_list_lock);
+		cancel_delayed_work_sync(&s_job->work_tdr);
+		spin_lock(&sched->job_list_lock);
 
 		/* queue TDR for next job */
 		next = list_first_entry_or_null(&sched->ring_mirror_list,
 						struct amd_sched_job, node);
 
-		if (next) {
-			INIT_DELAYED_WORK(&next->work_tdr, s_job->timeout_callback);
-			amd_sched_job_get(next);
+		if (next)
 			schedule_delayed_work(&next->work_tdr, sched->timeout);
-		}
 	}
+	spin_unlock(&sched->job_list_lock);
+	sched->ops->free_job(s_job);
 }
 
-void amd_sched_job_begin(struct amd_sched_job *s_job)
+static void amd_sched_job_finish_cb(struct fence *f, struct fence_cb *cb)
+{
+	struct amd_sched_job *job = container_of(cb, struct amd_sched_job,
+						 finish_cb);
+	schedule_work(&job->finish_work);
+}
+
+static void amd_sched_job_begin(struct amd_sched_job *s_job)
 {
 	struct amd_gpu_scheduler *sched = s_job->sched;
 
+	spin_lock(&sched->job_list_lock);
+	list_add_tail(&s_job->node, &sched->ring_mirror_list);
 	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
-		list_first_entry_or_null(&sched->ring_mirror_list, struct amd_sched_job, node) == s_job)
-	{
-		INIT_DELAYED_WORK(&s_job->work_tdr, s_job->timeout_callback);
-		amd_sched_job_get(s_job);
+	    list_first_entry_or_null(&sched->ring_mirror_list,
+				     struct amd_sched_job, node) == s_job)
+		schedule_delayed_work(&s_job->work_tdr, sched->timeout);
+	spin_unlock(&sched->job_list_lock);
+}
+
+static void amd_sched_job_timedout(struct work_struct *work)
+{
+	struct amd_sched_job *job = container_of(work, struct amd_sched_job,
+						 work_tdr.work);
+
+	job->sched->ops->timedout_job(job);
+}
+
+void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched)
+{
+	struct amd_sched_job *s_job;
+
+	spin_lock(&sched->job_list_lock);
+	list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
+		if (fence_remove_callback(s_job->s_fence->parent, &s_job->s_fence->cb)) {
+			fence_put(s_job->s_fence->parent);
+			s_job->s_fence->parent = NULL;
+		}
+	}
+	atomic_set(&sched->hw_rq_count, 0);
+	spin_unlock(&sched->job_list_lock);
+}
+
+void amd_sched_job_recovery(struct amd_gpu_scheduler *sched)
+{
+	struct amd_sched_job *s_job, *tmp;
+	int r;
+
+	spin_lock(&sched->job_list_lock);
+	s_job = list_first_entry_or_null(&sched->ring_mirror_list,
+					 struct amd_sched_job, node);
+	if (s_job)
 		schedule_delayed_work(&s_job->work_tdr, sched->timeout);
+
+	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
+		struct amd_sched_fence *s_fence = s_job->s_fence;
+		struct fence *fence;
+
+		spin_unlock(&sched->job_list_lock);
+		fence = sched->ops->run_job(s_job);
+		atomic_inc(&sched->hw_rq_count);
+		if (fence) {
+			s_fence->parent = fence_get(fence);
+			r = fence_add_callback(fence, &s_fence->cb,
+					       amd_sched_process_job);
+			if (r == -ENOENT)
+				amd_sched_process_job(fence, &s_fence->cb);
+			else if (r)
+				DRM_ERROR("fence add callback failed (%d)\n",
+					  r);
+			fence_put(fence);
+		} else {
+			DRM_ERROR("Failed to run job!\n");
+			amd_sched_process_job(NULL, &s_fence->cb);
+		}
+		spin_lock(&sched->job_list_lock);
 	}
+	spin_unlock(&sched->job_list_lock);
 }
 
 /**
@@ -372,36 +445,29 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 {
 	struct amd_sched_entity *entity = sched_job->s_entity;
 
-	sched_job->use_sched = 1;
-	fence_add_callback(&sched_job->s_fence->base,
-					&sched_job->cb_free_job, amd_sched_free_job);
 	trace_amd_sched_job(sched_job);
+	fence_add_callback(&sched_job->s_fence->finished, &sched_job->finish_cb,
+			   amd_sched_job_finish_cb);
 	wait_event(entity->sched->job_scheduled,
 		   amd_sched_entity_in(sched_job));
 }
 
 /* init a sched_job with basic field */
 int amd_sched_job_init(struct amd_sched_job *job,
-						struct amd_gpu_scheduler *sched,
-						struct amd_sched_entity *entity,
-						void (*timeout_cb)(struct work_struct *work),
-						void (*free_cb)(struct kref *refcount),
-						void *owner, struct fence **fence)
+		       struct amd_gpu_scheduler *sched,
+		       struct amd_sched_entity *entity,
+		       void *owner)
 {
-	INIT_LIST_HEAD(&job->node);
-	kref_init(&job->refcount);
 	job->sched = sched;
 	job->s_entity = entity;
 	job->s_fence = amd_sched_fence_create(entity, owner);
 	if (!job->s_fence)
 		return -ENOMEM;
 
-	job->s_fence->s_job = job;
-	job->timeout_callback = timeout_cb;
-	job->free_callback = free_cb;
+	INIT_WORK(&job->finish_work, amd_sched_job_finish);
+	INIT_LIST_HEAD(&job->node);
+	INIT_DELAYED_WORK(&job->work_tdr, amd_sched_job_timedout);
 
-	if (fence)
-		*fence = &job->s_fence->base;
 	return 0;
 }
 
@@ -450,23 +516,25 @@ static void amd_sched_process_job(struct fence *f, struct fence_cb *cb)
 	struct amd_sched_fence *s_fence =
 		container_of(cb, struct amd_sched_fence, cb);
 	struct amd_gpu_scheduler *sched = s_fence->sched;
-	unsigned long flags;
 
 	atomic_dec(&sched->hw_rq_count);
-
-	/* remove job from ring_mirror_list */
-	spin_lock_irqsave(&sched->job_list_lock, flags);
-	list_del_init(&s_fence->s_job->node);
-	sched->ops->finish_job(s_fence->s_job);
-	spin_unlock_irqrestore(&sched->job_list_lock, flags);
-
-	amd_sched_fence_signal(s_fence);
+	amd_sched_fence_finished(s_fence);
 
 	trace_amd_sched_process_job(s_fence);
-	fence_put(&s_fence->base);
+	fence_put(&s_fence->finished);
 	wake_up_interruptible(&sched->wake_up_worker);
 }
 
+static bool amd_sched_blocked(struct amd_gpu_scheduler *sched)
+{
+	if (kthread_should_park()) {
+		kthread_parkme();
+		return true;
+	}
+
+	return false;
+}
+
 static int amd_sched_main(void *param)
 {
 	struct sched_param sparam = {.sched_priority = 1};
@@ -476,14 +544,15 @@ static int amd_sched_main(void *param)
 	sched_setscheduler(current, SCHED_FIFO, &sparam);
 
 	while (!kthread_should_stop()) {
-		struct amd_sched_entity *entity;
+		struct amd_sched_entity *entity = NULL;
 		struct amd_sched_fence *s_fence;
 		struct amd_sched_job *sched_job;
 		struct fence *fence;
 
 		wait_event_interruptible(sched->wake_up_worker,
-			(entity = amd_sched_select_entity(sched)) ||
-			kthread_should_stop());
+					 (!amd_sched_blocked(sched) &&
+					  (entity = amd_sched_select_entity(sched))) ||
+					 kthread_should_stop());
 
 		if (!entity)
 			continue;
@@ -495,16 +564,19 @@ static int amd_sched_main(void *param)
 		s_fence = sched_job->s_fence;
 
 		atomic_inc(&sched->hw_rq_count);
-		amd_sched_job_pre_schedule(sched, sched_job);
+		amd_sched_job_begin(sched_job);
+
 		fence = sched->ops->run_job(sched_job);
 		amd_sched_fence_scheduled(s_fence);
 		if (fence) {
+			s_fence->parent = fence_get(fence);
 			r = fence_add_callback(fence, &s_fence->cb,
 					       amd_sched_process_job);
 			if (r == -ENOENT)
 				amd_sched_process_job(fence, &s_fence->cb);
 			else if (r)
-				DRM_ERROR("fence add callback failed (%d)\n", r);
+				DRM_ERROR("fence add callback failed (%d)\n",
+					  r);
 			fence_put(fence);
 		} else {
 			DRM_ERROR("Failed to run job!\n");
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index 070095a9433c..7cbbbfb502ef 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -27,8 +27,6 @@
 #include <linux/kfifo.h>
 #include <linux/fence.h>
 
-#define AMD_SCHED_FENCE_SCHEDULED_BIT	FENCE_FLAG_USER_BITS
-
 struct amd_gpu_scheduler;
 struct amd_sched_rq;
 
@@ -68,36 +66,34 @@ struct amd_sched_rq {
 };
 
 struct amd_sched_fence {
-	struct fence                    base;
+	struct fence                    scheduled;
+	struct fence                    finished;
 	struct fence_cb                 cb;
-	struct list_head		scheduled_cb;
+	struct fence                    *parent;
 	struct amd_gpu_scheduler	*sched;
 	spinlock_t			lock;
 	void                            *owner;
-	struct amd_sched_job	*s_job;
 };
 
 struct amd_sched_job {
-	struct kref refcount;
 	struct amd_gpu_scheduler        *sched;
 	struct amd_sched_entity         *s_entity;
 	struct amd_sched_fence          *s_fence;
-	bool	use_sched;	/* true if the job goes to scheduler */
-	struct fence_cb                cb_free_job;
-	struct work_struct             work_free_job;
-	struct list_head			   node;
-	struct delayed_work work_tdr;
-	void (*timeout_callback) (struct work_struct *work);
-	void (*free_callback)(struct kref *refcount);
+	struct fence_cb			finish_cb;
+	struct work_struct		finish_work;
+	struct list_head		node;
+	struct delayed_work		work_tdr;
 };
 
-extern const struct fence_ops amd_sched_fence_ops;
+extern const struct fence_ops amd_sched_fence_ops_scheduled;
+extern const struct fence_ops amd_sched_fence_ops_finished;
 static inline struct amd_sched_fence *to_amd_sched_fence(struct fence *f)
 {
-	struct amd_sched_fence *__f = container_of(f, struct amd_sched_fence, base);
+	if (f->ops == &amd_sched_fence_ops_scheduled)
+		return container_of(f, struct amd_sched_fence, scheduled);
 
-	if (__f->base.ops == &amd_sched_fence_ops)
-		return __f;
+	if (f->ops == &amd_sched_fence_ops_finished)
+		return container_of(f, struct amd_sched_fence, finished);
 
 	return NULL;
 }
@@ -109,8 +105,8 @@ static inline struct amd_sched_fence *to_amd_sched_fence(struct fence *f)
 struct amd_sched_backend_ops {
 	struct fence *(*dependency)(struct amd_sched_job *sched_job);
 	struct fence *(*run_job)(struct amd_sched_job *sched_job);
-	void (*begin_job)(struct amd_sched_job *sched_job);
-	void (*finish_job)(struct amd_sched_job *sched_job);
+	void (*timedout_job)(struct amd_sched_job *sched_job);
+	void (*free_job)(struct amd_sched_job *sched_job);
 };
 
 enum amd_sched_priority {
@@ -152,25 +148,11 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job);
 struct amd_sched_fence *amd_sched_fence_create(
 	struct amd_sched_entity *s_entity, void *owner);
 void amd_sched_fence_scheduled(struct amd_sched_fence *fence);
-void amd_sched_fence_signal(struct amd_sched_fence *fence);
+void amd_sched_fence_finished(struct amd_sched_fence *fence);
 int amd_sched_job_init(struct amd_sched_job *job,
-					struct amd_gpu_scheduler *sched,
-					struct amd_sched_entity *entity,
-					void (*timeout_cb)(struct work_struct *work),
-					void (*free_cb)(struct kref* refcount),
-					void *owner, struct fence **fence);
-void amd_sched_job_pre_schedule(struct amd_gpu_scheduler *sched ,
-								struct amd_sched_job *s_job);
-void amd_sched_job_finish(struct amd_sched_job *s_job);
-void amd_sched_job_begin(struct amd_sched_job *s_job);
-static inline void amd_sched_job_get(struct amd_sched_job *job) {
-	if (job)
-		kref_get(&job->refcount);
-}
-
-static inline void amd_sched_job_put(struct amd_sched_job *job) {
-	if (job)
-		kref_put(&job->refcount, job->free_callback);
-}
-
+		       struct amd_gpu_scheduler *sched,
+		       struct amd_sched_entity *entity,
+		       void *owner);
+void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched);
+void amd_sched_job_recovery(struct amd_gpu_scheduler *sched);
 #endif
diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c
index 2a732c490375..6b63beaf7574 100644
--- a/drivers/gpu/drm/amd/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c
@@ -27,7 +27,8 @@
 #include <drm/drmP.h>
 #include "gpu_scheduler.h"
 
-struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *s_entity, void *owner)
+struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *entity,
+					       void *owner)
 {
 	struct amd_sched_fence *fence = NULL;
 	unsigned seq;
@@ -36,46 +37,37 @@ struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *s_entity
 	if (fence == NULL)
 		return NULL;
 
-	INIT_LIST_HEAD(&fence->scheduled_cb);
 	fence->owner = owner;
-	fence->sched = s_entity->sched;
+	fence->sched = entity->sched;
 	spin_lock_init(&fence->lock);
 
-	seq = atomic_inc_return(&s_entity->fence_seq);
-	fence_init(&fence->base, &amd_sched_fence_ops, &fence->lock,
-		   s_entity->fence_context, seq);
+	seq = atomic_inc_return(&entity->fence_seq);
+	fence_init(&fence->scheduled, &amd_sched_fence_ops_scheduled,
+		   &fence->lock, entity->fence_context, seq);
+	fence_init(&fence->finished, &amd_sched_fence_ops_finished,
+		   &fence->lock, entity->fence_context + 1, seq);
 
 	return fence;
 }
 
-void amd_sched_fence_signal(struct amd_sched_fence *fence)
+void amd_sched_fence_scheduled(struct amd_sched_fence *fence)
 {
-	int ret = fence_signal(&fence->base);
+	int ret = fence_signal(&fence->scheduled);
+
 	if (!ret)
-		FENCE_TRACE(&fence->base, "signaled from irq context\n");
+		FENCE_TRACE(&fence->scheduled, "signaled from irq context\n");
 	else
-		FENCE_TRACE(&fence->base, "was already signaled\n");
-}
-
-void amd_sched_job_pre_schedule(struct amd_gpu_scheduler *sched ,
-				struct amd_sched_job *s_job)
-{
-	unsigned long flags;
-	spin_lock_irqsave(&sched->job_list_lock, flags);
-	list_add_tail(&s_job->node, &sched->ring_mirror_list);
-	sched->ops->begin_job(s_job);
-	spin_unlock_irqrestore(&sched->job_list_lock, flags);
+		FENCE_TRACE(&fence->scheduled, "was already signaled\n");
 }
 
-void amd_sched_fence_scheduled(struct amd_sched_fence *s_fence)
+void amd_sched_fence_finished(struct amd_sched_fence *fence)
 {
-	struct fence_cb *cur, *tmp;
+	int ret = fence_signal(&fence->finished);
 
-	set_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &s_fence->base.flags);
-	list_for_each_entry_safe(cur, tmp, &s_fence->scheduled_cb, node) {
-		list_del_init(&cur->node);
-		cur->func(&s_fence->base, cur);
-	}
+	if (!ret)
+		FENCE_TRACE(&fence->finished, "signaled from irq context\n");
+	else
+		FENCE_TRACE(&fence->finished, "was already signaled\n");
 }
 
 static const char *amd_sched_fence_get_driver_name(struct fence *fence)
@@ -105,6 +97,8 @@ static void amd_sched_fence_free(struct rcu_head *rcu)
 {
 	struct fence *f = container_of(rcu, struct fence, rcu);
 	struct amd_sched_fence *fence = to_amd_sched_fence(f);
+
+	fence_put(fence->parent);
 	kmem_cache_free(sched_fence_slab, fence);
 }
 
@@ -116,16 +110,41 @@ static void amd_sched_fence_free(struct rcu_head *rcu)
  * This function is called when the reference count becomes zero.
  * It just RCU schedules freeing up the fence.
  */
-static void amd_sched_fence_release(struct fence *f)
+static void amd_sched_fence_release_scheduled(struct fence *f)
 {
-	call_rcu(&f->rcu, amd_sched_fence_free);
+	struct amd_sched_fence *fence = to_amd_sched_fence(f);
+
+	call_rcu(&fence->finished.rcu, amd_sched_fence_free);
 }
 
-const struct fence_ops amd_sched_fence_ops = {
+/**
+ * amd_sched_fence_release_scheduled - drop extra reference
+ *
+ * @f: fence
+ *
+ * Drop the extra reference from the scheduled fence to the base fence.
+ */
+static void amd_sched_fence_release_finished(struct fence *f)
+{
+	struct amd_sched_fence *fence = to_amd_sched_fence(f);
+
+	fence_put(&fence->scheduled);
+}
+
+const struct fence_ops amd_sched_fence_ops_scheduled = {
+	.get_driver_name = amd_sched_fence_get_driver_name,
+	.get_timeline_name = amd_sched_fence_get_timeline_name,
+	.enable_signaling = amd_sched_fence_enable_signaling,
+	.signaled = NULL,
+	.wait = fence_default_wait,
+	.release = amd_sched_fence_release_scheduled,
+};
+
+const struct fence_ops amd_sched_fence_ops_finished = {
 	.get_driver_name = amd_sched_fence_get_driver_name,
 	.get_timeline_name = amd_sched_fence_get_timeline_name,
 	.enable_signaling = amd_sched_fence_enable_signaling,
 	.signaled = NULL,
 	.wait = fence_default_wait,
-	.release = amd_sched_fence_release,
+	.release = amd_sched_fence_release_finished,
 };
diff --git a/drivers/gpu/drm/arc/Kconfig b/drivers/gpu/drm/arc/Kconfig
index f9a13b658fea..f47d88ba4fa5 100644
--- a/drivers/gpu/drm/arc/Kconfig
+++ b/drivers/gpu/drm/arc/Kconfig
@@ -2,7 +2,6 @@ config DRM_ARCPGU
 	tristate "ARC PGU"
 	depends on DRM && OF
 	select DRM_KMS_CMA_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_KMS_HELPER
 	help
 	  Choose this option if you have an ARC PGU controller.
diff --git a/drivers/gpu/drm/arc/Makefile b/drivers/gpu/drm/arc/Makefile
index d48fda70f857..73de56a0139a 100644
--- a/drivers/gpu/drm/arc/Makefile
+++ b/drivers/gpu/drm/arc/Makefile
@@ -1,2 +1,2 @@
-arcpgu-y := arcpgu_crtc.o arcpgu_hdmi.o arcpgu_drv.o
+arcpgu-y := arcpgu_crtc.o arcpgu_hdmi.o arcpgu_sim.o arcpgu_drv.o
 obj-$(CONFIG_DRM_ARCPGU) += arcpgu.o
diff --git a/drivers/gpu/drm/arc/arcpgu.h b/drivers/gpu/drm/arc/arcpgu.h
index 86574b698a78..e8fcf3ab1d9a 100644
--- a/drivers/gpu/drm/arc/arcpgu.h
+++ b/drivers/gpu/drm/arc/arcpgu.h
@@ -22,7 +22,6 @@ struct arcpgu_drm_private {
 	struct clk		*clk;
 	struct drm_fbdev_cma	*fbdev;
 	struct drm_framebuffer	*fb;
-	struct list_head	event_list;
 	struct drm_crtc		crtc;
 	struct drm_plane	*plane;
 };
@@ -43,6 +42,7 @@ static inline u32 arc_pgu_read(struct arcpgu_drm_private *arcpgu,
 
 int arc_pgu_setup_crtc(struct drm_device *dev);
 int arcpgu_drm_hdmi_init(struct drm_device *drm, struct device_node *np);
+int arcpgu_drm_sim_init(struct drm_device *drm, struct device_node *np);
 struct drm_fbdev_cma *arcpgu_fbdev_cma_init(struct drm_device *dev,
 	unsigned int preferred_bpp, unsigned int num_crtc,
 	unsigned int max_conn_count);
diff --git a/drivers/gpu/drm/arc/arcpgu_crtc.c b/drivers/gpu/drm/arc/arcpgu_crtc.c
index 92f8beff8e60..ee0a61c2861b 100644
--- a/drivers/gpu/drm/arc/arcpgu_crtc.c
+++ b/drivers/gpu/drm/arc/arcpgu_crtc.c
@@ -145,20 +145,14 @@ static int arc_pgu_crtc_atomic_check(struct drm_crtc *crtc,
 static void arc_pgu_crtc_atomic_begin(struct drm_crtc *crtc,
 				      struct drm_crtc_state *state)
 {
-	struct arcpgu_drm_private *arcpgu = crtc_to_arcpgu_priv(crtc);
-	unsigned long flags;
-
-	if (crtc->state->event) {
-		struct drm_pending_vblank_event *event = crtc->state->event;
+	struct drm_pending_vblank_event *event = crtc->state->event;
 
+	if (event) {
 		crtc->state->event = NULL;
-		event->pipe = drm_crtc_index(crtc);
-
-		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
 
-		spin_lock_irqsave(&crtc->dev->event_lock, flags);
-		list_add_tail(&event->base.link, &arcpgu->event_list);
-		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, event);
+		spin_unlock_irq(&crtc->dev->event_lock);
 	}
 }
 
diff --git a/drivers/gpu/drm/arc/arcpgu_drv.c b/drivers/gpu/drm/arc/arcpgu_drv.c
index 76e187a5bde0..6d4ff34737cb 100644
--- a/drivers/gpu/drm/arc/arcpgu_drv.c
+++ b/drivers/gpu/drm/arc/arcpgu_drv.c
@@ -28,21 +28,14 @@ static void arcpgu_fb_output_poll_changed(struct drm_device *dev)
 {
 	struct arcpgu_drm_private *arcpgu = dev->dev_private;
 
-	if (arcpgu->fbdev)
-		drm_fbdev_cma_hotplug_event(arcpgu->fbdev);
-}
-
-static int arcpgu_atomic_commit(struct drm_device *dev,
-				    struct drm_atomic_state *state, bool async)
-{
-	return drm_atomic_helper_commit(dev, state, false);
+	drm_fbdev_cma_hotplug_event(arcpgu->fbdev);
 }
 
 static struct drm_mode_config_funcs arcpgu_drm_modecfg_funcs = {
 	.fb_create  = drm_fb_cma_create,
 	.output_poll_changed = arcpgu_fb_output_poll_changed,
 	.atomic_check = drm_atomic_helper_check,
-	.atomic_commit = arcpgu_atomic_commit,
+	.atomic_commit = drm_atomic_helper_commit,
 };
 
 static void arcpgu_setup_mode_config(struct drm_device *drm)
@@ -55,7 +48,7 @@ static void arcpgu_setup_mode_config(struct drm_device *drm)
 	drm->mode_config.funcs = &arcpgu_drm_modecfg_funcs;
 }
 
-int arcpgu_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+static int arcpgu_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	int ret;
 
@@ -81,22 +74,6 @@ static const struct file_operations arcpgu_drm_ops = {
 	.mmap = arcpgu_gem_mmap,
 };
 
-static void arcpgu_preclose(struct drm_device *drm, struct drm_file *file)
-{
-	struct arcpgu_drm_private *arcpgu = drm->dev_private;
-	struct drm_pending_vblank_event *e, *t;
-	unsigned long flags;
-
-	spin_lock_irqsave(&drm->event_lock, flags);
-	list_for_each_entry_safe(e, t, &arcpgu->event_list, base.link) {
-		if (e->base.file_priv != file)
-			continue;
-		list_del(&e->base.link);
-		e->base.destroy(&e->base);
-	}
-	spin_unlock_irqrestore(&drm->event_lock, flags);
-}
-
 static void arcpgu_lastclose(struct drm_device *drm)
 {
 	struct arcpgu_drm_private *arcpgu = drm->dev_private;
@@ -122,16 +99,12 @@ static int arcpgu_load(struct drm_device *drm)
 	if (IS_ERR(arcpgu->clk))
 		return PTR_ERR(arcpgu->clk);
 
-	INIT_LIST_HEAD(&arcpgu->event_list);
-
 	arcpgu_setup_mode_config(drm);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	arcpgu->regs = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(arcpgu->regs)) {
-		dev_err(drm->dev, "Could not remap IO mem\n");
+	if (IS_ERR(arcpgu->regs))
 		return PTR_ERR(arcpgu->regs);
-	}
 
 	dev_info(drm->dev, "arc_pgu ID: 0x%x\n",
 		 arc_pgu_read(arcpgu, ARCPGU_REG_ID));
@@ -149,15 +122,17 @@ static int arcpgu_load(struct drm_device *drm)
 
 	/* find the encoder node and initialize it */
 	encoder_node = of_parse_phandle(drm->dev->of_node, "encoder-slave", 0);
-	if (!encoder_node) {
-		dev_err(drm->dev, "failed to get an encoder slave node\n");
-		return -ENODEV;
+	if (encoder_node) {
+		ret = arcpgu_drm_hdmi_init(drm, encoder_node);
+		of_node_put(encoder_node);
+		if (ret < 0)
+			return ret;
+	} else {
+		ret = arcpgu_drm_sim_init(drm, NULL);
+		if (ret < 0)
+			return ret;
 	}
 
-	ret = arcpgu_drm_hdmi_init(drm, encoder_node);
-	if (ret < 0)
-		return ret;
-
 	drm_mode_config_reset(drm);
 	drm_kms_helper_poll_init(drm);
 
@@ -174,7 +149,7 @@ static int arcpgu_load(struct drm_device *drm)
 	return 0;
 }
 
-int arcpgu_unload(struct drm_device *drm)
+static int arcpgu_unload(struct drm_device *drm)
 {
 	struct arcpgu_drm_private *arcpgu = drm->dev_private;
 
@@ -192,7 +167,6 @@ int arcpgu_unload(struct drm_device *drm)
 static struct drm_driver arcpgu_drm_driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME |
 			   DRIVER_ATOMIC,
-	.preclose = arcpgu_preclose,
 	.lastclose = arcpgu_lastclose,
 	.name = "drm-arcpgu",
 	.desc = "ARC PGU Controller",
@@ -207,7 +181,7 @@ static struct drm_driver arcpgu_drm_driver = {
 	.get_vblank_counter = drm_vblank_no_hw_counter,
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
-	.gem_free_object = drm_gem_cma_free_object,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops = &drm_gem_cma_vm_ops,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_import = drm_gem_prime_import,
@@ -235,15 +209,8 @@ static int arcpgu_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_unload;
 
-	ret = drm_connector_register_all(drm);
-	if (ret)
-		goto err_unregister;
-
 	return 0;
 
-err_unregister:
-	drm_dev_unregister(drm);
-
 err_unload:
 	arcpgu_unload(drm);
 
@@ -257,7 +224,6 @@ static int arcpgu_remove(struct platform_device *pdev)
 {
 	struct drm_device *drm = platform_get_drvdata(pdev);
 
-	drm_connector_unregister_all(drm);
 	drm_dev_unregister(drm);
 	arcpgu_unload(drm);
 	drm_dev_unref(drm);
diff --git a/drivers/gpu/drm/arc/arcpgu_hdmi.c b/drivers/gpu/drm/arc/arcpgu_hdmi.c
index 08b6baeb320d..b7a8b2ac4055 100644
--- a/drivers/gpu/drm/arc/arcpgu_hdmi.c
+++ b/drivers/gpu/drm/arc/arcpgu_hdmi.c
@@ -46,23 +46,6 @@ static int arcpgu_drm_connector_get_modes(struct drm_connector *connector)
 	return sfuncs->get_modes(&slave->base, connector);
 }
 
-struct drm_encoder *
-arcpgu_drm_connector_best_encoder(struct drm_connector *connector)
-{
-	struct drm_encoder_slave *slave;
-	struct arcpgu_drm_connector *con =
-		container_of(connector, struct arcpgu_drm_connector, connector);
-
-	slave = con->encoder_slave;
-	if (slave == NULL) {
-		dev_err(connector->dev->dev,
-			"connector_best_encoder: cannot find slave encoder for connector\n");
-		return NULL;
-	}
-
-	return &slave->base;
-}
-
 static enum drm_connector_status
 arcpgu_drm_connector_detect(struct drm_connector *connector, bool force)
 {
@@ -97,7 +80,6 @@ static void arcpgu_drm_connector_destroy(struct drm_connector *connector)
 static const struct drm_connector_helper_funcs
 arcpgu_drm_connector_helper_funcs = {
 	.get_modes = arcpgu_drm_connector_get_modes,
-	.best_encoder = arcpgu_drm_connector_best_encoder,
 };
 
 static const struct drm_connector_funcs arcpgu_drm_connector_funcs = {
diff --git a/drivers/gpu/drm/arc/arcpgu_sim.c b/drivers/gpu/drm/arc/arcpgu_sim.c
new file mode 100644
index 000000000000..2bf06d71556a
--- /dev/null
+++ b/drivers/gpu/drm/arc/arcpgu_sim.c
@@ -0,0 +1,128 @@
+/*
+ * ARC PGU DRM driver.
+ *
+ * Copyright (C) 2016 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_encoder_slave.h>
+#include <drm/drm_atomic_helper.h>
+
+#include "arcpgu.h"
+
+#define XRES_DEF	640
+#define YRES_DEF	480
+
+#define XRES_MAX	8192
+#define YRES_MAX	8192
+
+
+struct arcpgu_drm_connector {
+	struct drm_connector connector;
+	struct drm_encoder_slave *encoder_slave;
+};
+
+static int arcpgu_drm_connector_get_modes(struct drm_connector *connector)
+{
+	int count;
+
+	count = drm_add_modes_noedid(connector, XRES_MAX, YRES_MAX);
+	drm_set_preferred_mode(connector, XRES_DEF, YRES_DEF);
+	return count;
+}
+
+static enum drm_connector_status
+arcpgu_drm_connector_detect(struct drm_connector *connector, bool force)
+{
+	return connector_status_connected;
+}
+
+static void arcpgu_drm_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_helper_funcs
+arcpgu_drm_connector_helper_funcs = {
+	.get_modes = arcpgu_drm_connector_get_modes,
+};
+
+static const struct drm_connector_funcs arcpgu_drm_connector_funcs = {
+	.dpms = drm_helper_connector_dpms,
+	.reset = drm_atomic_helper_connector_reset,
+	.detect = arcpgu_drm_connector_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = arcpgu_drm_connector_destroy,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static struct drm_encoder_funcs arcpgu_drm_encoder_funcs = {
+	.destroy = drm_encoder_cleanup,
+};
+
+int arcpgu_drm_sim_init(struct drm_device *drm, struct device_node *np)
+{
+	struct arcpgu_drm_connector *arcpgu_connector;
+	struct drm_encoder_slave *encoder;
+	struct drm_connector *connector;
+	int ret;
+
+	encoder = devm_kzalloc(drm->dev, sizeof(*encoder), GFP_KERNEL);
+	if (encoder == NULL)
+		return -ENOMEM;
+
+	encoder->base.possible_crtcs = 1;
+	encoder->base.possible_clones = 0;
+
+	ret = drm_encoder_init(drm, &encoder->base, &arcpgu_drm_encoder_funcs,
+			       DRM_MODE_ENCODER_VIRTUAL, NULL);
+	if (ret)
+		return ret;
+
+	arcpgu_connector = devm_kzalloc(drm->dev, sizeof(*arcpgu_connector),
+					GFP_KERNEL);
+	if (!arcpgu_connector) {
+		ret = -ENOMEM;
+		goto error_encoder_cleanup;
+	}
+
+	connector = &arcpgu_connector->connector;
+	drm_connector_helper_add(connector, &arcpgu_drm_connector_helper_funcs);
+
+	ret = drm_connector_init(drm, connector, &arcpgu_drm_connector_funcs,
+			DRM_MODE_CONNECTOR_VIRTUAL);
+	if (ret < 0) {
+		dev_err(drm->dev, "failed to initialize drm connector\n");
+		goto error_encoder_cleanup;
+	}
+
+	ret = drm_mode_connector_attach_encoder(connector, &encoder->base);
+	if (ret < 0) {
+		dev_err(drm->dev, "could not attach connector to encoder\n");
+		drm_connector_unregister(connector);
+		goto error_connector_cleanup;
+	}
+
+	arcpgu_connector->encoder_slave = encoder;
+
+	return 0;
+
+error_connector_cleanup:
+	drm_connector_cleanup(connector);
+
+error_encoder_cleanup:
+	drm_encoder_cleanup(&encoder->base);
+	return ret;
+}
diff --git a/drivers/gpu/drm/arm/Kconfig b/drivers/gpu/drm/arm/Kconfig
index eaed454e043c..9a18e1bd57b4 100644
--- a/drivers/gpu/drm/arm/Kconfig
+++ b/drivers/gpu/drm/arm/Kconfig
@@ -9,7 +9,6 @@ config DRM_HDLCD
 	depends on COMMON_CLK
 	select DRM_ARM
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_KMS_CMA_HELPER
 	help
 	  Choose this option if you have an ARM High Definition Colour LCD
@@ -25,3 +24,19 @@ config DRM_HDLCD_SHOW_UNDERRUN
 	  Enable this option to show in red colour the pixels that the
 	  HDLCD device did not fetch from framebuffer due to underrun
 	  conditions.
+
+config DRM_MALI_DISPLAY
+	tristate "ARM Mali Display Processor"
+	depends on DRM && OF && (ARM || ARM64)
+	depends on COMMON_CLK
+	select DRM_ARM
+	select DRM_KMS_HELPER
+	select DRM_KMS_CMA_HELPER
+	select DRM_GEM_CMA_HELPER
+	select VIDEOMODE_HELPERS
+	help
+	  Choose this option if you want to compile the ARM Mali Display
+	  Processor driver. It supports the DP500, DP550 and DP650 variants
+	  of the hardware.
+
+	  If compiled as a module it will be called mali-dp.
diff --git a/drivers/gpu/drm/arm/Makefile b/drivers/gpu/drm/arm/Makefile
index 89dcb7bab93a..bb8b158ff90d 100644
--- a/drivers/gpu/drm/arm/Makefile
+++ b/drivers/gpu/drm/arm/Makefile
@@ -1,2 +1,4 @@
 hdlcd-y := hdlcd_drv.o hdlcd_crtc.o
 obj-$(CONFIG_DRM_HDLCD)	+= hdlcd.o
+mali-dp-y := malidp_drv.o malidp_hw.o malidp_planes.o malidp_crtc.o
+obj-$(CONFIG_DRM_MALI_DISPLAY)	+= mali-dp.o
diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index 0813c2f06931..48019ae22ddb 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -196,30 +196,11 @@ static void hdlcd_crtc_atomic_begin(struct drm_crtc *crtc,
 	}
 }
 
-static void hdlcd_crtc_atomic_flush(struct drm_crtc *crtc,
-				    struct drm_crtc_state *state)
-{
-}
-
-static bool hdlcd_crtc_mode_fixup(struct drm_crtc *crtc,
-			const struct drm_display_mode *mode,
-			struct drm_display_mode *adjusted_mode)
-{
-	return true;
-}
-
 static const struct drm_crtc_helper_funcs hdlcd_crtc_helper_funcs = {
-	.mode_fixup	= hdlcd_crtc_mode_fixup,
-	.mode_set	= drm_helper_crtc_mode_set,
-	.mode_set_base	= drm_helper_crtc_mode_set_base,
-	.mode_set_nofb	= hdlcd_crtc_mode_set_nofb,
 	.enable		= hdlcd_crtc_enable,
 	.disable	= hdlcd_crtc_disable,
-	.prepare	= hdlcd_crtc_disable,
-	.commit		= hdlcd_crtc_enable,
 	.atomic_check	= hdlcd_crtc_atomic_check,
 	.atomic_begin	= hdlcd_crtc_atomic_begin,
-	.atomic_flush	= hdlcd_crtc_atomic_flush,
 };
 
 static int hdlcd_plane_atomic_check(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index a6ca36f0096f..d83b46a30327 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -102,21 +102,14 @@ static void hdlcd_fb_output_poll_changed(struct drm_device *drm)
 {
 	struct hdlcd_drm_private *hdlcd = drm->dev_private;
 
-	if (hdlcd->fbdev)
-		drm_fbdev_cma_hotplug_event(hdlcd->fbdev);
-}
-
-static int hdlcd_atomic_commit(struct drm_device *dev,
-			       struct drm_atomic_state *state, bool nonblock)
-{
-	return drm_atomic_helper_commit(dev, state, false);
+	drm_fbdev_cma_hotplug_event(hdlcd->fbdev);
 }
 
 static const struct drm_mode_config_funcs hdlcd_mode_config_funcs = {
 	.fb_create = drm_fb_cma_create,
 	.output_poll_changed = hdlcd_fb_output_poll_changed,
 	.atomic_check = drm_atomic_helper_check,
-	.atomic_commit = hdlcd_atomic_commit,
+	.atomic_commit = drm_atomic_helper_commit,
 };
 
 static void hdlcd_setup_mode_config(struct drm_device *drm)
@@ -296,7 +289,7 @@ static struct drm_driver hdlcd_driver = {
 	.get_vblank_counter = drm_vblank_no_hw_counter,
 	.enable_vblank = hdlcd_enable_vblank,
 	.disable_vblank = hdlcd_disable_vblank,
-	.gem_free_object = drm_gem_cma_free_object,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops = &drm_gem_cma_vm_ops,
 	.dumb_create = drm_gem_cma_dumb_create,
 	.dumb_map_offset = drm_gem_cma_dumb_map_offset,
diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c
new file mode 100644
index 000000000000..08e6a71f5d05
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_crtc.c
@@ -0,0 +1,216 @@
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Liviu Dudau <Liviu.Dudau@arm.com>
+ *
+ * This program is free software and is provided to you under the terms of the
+ * GNU General Public License version 2 as published by the Free Software
+ * Foundation, and any use by you of this program is subject to the terms
+ * of such GNU licence.
+ *
+ * ARM Mali DP500/DP550/DP650 driver (crtc operations)
+ */
+
+#include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <linux/clk.h>
+#include <video/videomode.h>
+
+#include "malidp_drv.h"
+#include "malidp_hw.h"
+
+static bool malidp_crtc_mode_fixup(struct drm_crtc *crtc,
+				   const struct drm_display_mode *mode,
+				   struct drm_display_mode *adjusted_mode)
+{
+	struct malidp_drm *malidp = crtc_to_malidp_device(crtc);
+	struct malidp_hw_device *hwdev = malidp->dev;
+
+	/*
+	 * check that the hardware can drive the required clock rate,
+	 * but skip the check if the clock is meant to be disabled (req_rate = 0)
+	 */
+	long rate, req_rate = mode->crtc_clock * 1000;
+
+	if (req_rate) {
+		rate = clk_round_rate(hwdev->mclk, req_rate);
+		if (rate < req_rate) {
+			DRM_DEBUG_DRIVER("mclk clock unable to reach %d kHz\n",
+					 mode->crtc_clock);
+			return false;
+		}
+
+		rate = clk_round_rate(hwdev->pxlclk, req_rate);
+		if (rate != req_rate) {
+			DRM_DEBUG_DRIVER("pxlclk doesn't support %ld Hz\n",
+					 req_rate);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static void malidp_crtc_enable(struct drm_crtc *crtc)
+{
+	struct malidp_drm *malidp = crtc_to_malidp_device(crtc);
+	struct malidp_hw_device *hwdev = malidp->dev;
+	struct videomode vm;
+
+	drm_display_mode_to_videomode(&crtc->state->adjusted_mode, &vm);
+
+	clk_prepare_enable(hwdev->pxlclk);
+
+	/* mclk needs to be set to the same or higher rate than pxlclk */
+	clk_set_rate(hwdev->mclk, crtc->state->adjusted_mode.crtc_clock * 1000);
+	clk_set_rate(hwdev->pxlclk, crtc->state->adjusted_mode.crtc_clock * 1000);
+
+	hwdev->modeset(hwdev, &vm);
+	hwdev->leave_config_mode(hwdev);
+	drm_crtc_vblank_on(crtc);
+}
+
+static void malidp_crtc_disable(struct drm_crtc *crtc)
+{
+	struct malidp_drm *malidp = crtc_to_malidp_device(crtc);
+	struct malidp_hw_device *hwdev = malidp->dev;
+
+	drm_crtc_vblank_off(crtc);
+	hwdev->enter_config_mode(hwdev);
+	clk_disable_unprepare(hwdev->pxlclk);
+}
+
+static int malidp_crtc_atomic_check(struct drm_crtc *crtc,
+				    struct drm_crtc_state *state)
+{
+	struct malidp_drm *malidp = crtc_to_malidp_device(crtc);
+	struct malidp_hw_device *hwdev = malidp->dev;
+	struct drm_plane *plane;
+	const struct drm_plane_state *pstate;
+	u32 rot_mem_free, rot_mem_usable;
+	int rotated_planes = 0;
+
+	/*
+	 * check if there is enough rotation memory available for planes
+	 * that need 90° and 270° rotation. Each plane has set its required
+	 * memory size in the ->plane_check() callback, here we only make
+	 * sure that the sums are less that the total usable memory.
+	 *
+	 * The rotation memory allocation algorithm (for each plane):
+	 *  a. If no more rotated planes exist, all remaining rotate
+	 *     memory in the bank is available for use by the plane.
+	 *  b. If other rotated planes exist, and plane's layer ID is
+	 *     DE_VIDEO1, it can use all the memory from first bank if
+	 *     secondary rotation memory bank is available, otherwise it can
+	 *     use up to half the bank's memory.
+	 *  c. If other rotated planes exist, and plane's layer ID is not
+	 *     DE_VIDEO1, it can use half of the available memory
+	 *
+	 * Note: this algorithm assumes that the order in which the planes are
+	 * checked always has DE_VIDEO1 plane first in the list if it is
+	 * rotated. Because that is how we create the planes in the first
+	 * place, under current DRM version things work, but if ever the order
+	 * in which drm_atomic_crtc_state_for_each_plane() iterates over planes
+	 * changes, we need to pre-sort the planes before validation.
+	 */
+
+	/* first count the number of rotated planes */
+	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, state) {
+		if (pstate->rotation & MALIDP_ROTATED_MASK)
+			rotated_planes++;
+	}
+
+	rot_mem_free = hwdev->rotation_memory[0];
+	/*
+	 * if we have more than 1 plane using rotation memory, use the second
+	 * block of rotation memory as well
+	 */
+	if (rotated_planes > 1)
+		rot_mem_free += hwdev->rotation_memory[1];
+
+	/* now validate the rotation memory requirements */
+	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, state) {
+		struct malidp_plane *mp = to_malidp_plane(plane);
+		struct malidp_plane_state *ms = to_malidp_plane_state(pstate);
+
+		if (pstate->rotation & MALIDP_ROTATED_MASK) {
+			/* process current plane */
+			rotated_planes--;
+
+			if (!rotated_planes) {
+				/* no more rotated planes, we can use what's left */
+				rot_mem_usable = rot_mem_free;
+			} else {
+				if ((mp->layer->id != DE_VIDEO1) ||
+				    (hwdev->rotation_memory[1] == 0))
+					rot_mem_usable = rot_mem_free / 2;
+				else
+					rot_mem_usable = hwdev->rotation_memory[0];
+			}
+
+			rot_mem_free -= rot_mem_usable;
+
+			if (ms->rotmem_size > rot_mem_usable)
+				return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static const struct drm_crtc_helper_funcs malidp_crtc_helper_funcs = {
+	.mode_fixup = malidp_crtc_mode_fixup,
+	.enable = malidp_crtc_enable,
+	.disable = malidp_crtc_disable,
+	.atomic_check = malidp_crtc_atomic_check,
+};
+
+static const struct drm_crtc_funcs malidp_crtc_funcs = {
+	.destroy = drm_crtc_cleanup,
+	.set_config = drm_atomic_helper_set_config,
+	.page_flip = drm_atomic_helper_page_flip,
+	.reset = drm_atomic_helper_crtc_reset,
+	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
+};
+
+int malidp_crtc_init(struct drm_device *drm)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	struct drm_plane *primary = NULL, *plane;
+	int ret;
+
+	ret = malidp_de_planes_init(drm);
+	if (ret < 0) {
+		DRM_ERROR("Failed to initialise planes\n");
+		return ret;
+	}
+
+	drm_for_each_plane(plane, drm) {
+		if (plane->type == DRM_PLANE_TYPE_PRIMARY) {
+			primary = plane;
+			break;
+		}
+	}
+
+	if (!primary) {
+		DRM_ERROR("no primary plane found\n");
+		ret = -EINVAL;
+		goto crtc_cleanup_planes;
+	}
+
+	ret = drm_crtc_init_with_planes(drm, &malidp->crtc, primary, NULL,
+					&malidp_crtc_funcs, NULL);
+
+	if (!ret) {
+		drm_crtc_helper_add(&malidp->crtc, &malidp_crtc_helper_funcs);
+		return 0;
+	}
+
+crtc_cleanup_planes:
+	malidp_de_planes_destroy(drm);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
new file mode 100644
index 000000000000..82171d223f2d
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -0,0 +1,519 @@
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Liviu Dudau <Liviu.Dudau@arm.com>
+ *
+ * This program is free software and is provided to you under the terms of the
+ * GNU General Public License version 2 as published by the Free Software
+ * Foundation, and any use by you of this program is subject to the terms
+ * of such GNU licence.
+ *
+ * ARM Mali DP500/DP550/DP650 KMS/DRM driver
+ */
+
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/of_device.h>
+#include <linux/of_graph.h>
+#include <linux/of_reserved_mem.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_fb_helper.h>
+#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_of.h>
+
+#include "malidp_drv.h"
+#include "malidp_regs.h"
+#include "malidp_hw.h"
+
+#define MALIDP_CONF_VALID_TIMEOUT	250
+
+/*
+ * set the "config valid" bit and wait until the hardware acts on it
+ */
+static int malidp_set_and_wait_config_valid(struct drm_device *drm)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
+	int ret;
+
+	hwdev->set_config_valid(hwdev);
+	/* don't wait for config_valid flag if we are in config mode */
+	if (hwdev->in_config_mode(hwdev))
+		return 0;
+
+	ret = wait_event_interruptible_timeout(malidp->wq,
+			atomic_read(&malidp->config_valid) == 1,
+			msecs_to_jiffies(MALIDP_CONF_VALID_TIMEOUT));
+
+	return (ret > 0) ? 0 : -ETIMEDOUT;
+}
+
+static void malidp_output_poll_changed(struct drm_device *drm)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+
+	drm_fbdev_cma_hotplug_event(malidp->fbdev);
+}
+
+static void malidp_atomic_commit_hw_done(struct drm_atomic_state *state)
+{
+	struct drm_pending_vblank_event *event;
+	struct drm_device *drm = state->dev;
+	struct malidp_drm *malidp = drm->dev_private;
+	int ret = malidp_set_and_wait_config_valid(drm);
+
+	if (ret)
+		DRM_DEBUG_DRIVER("timed out waiting for updated configuration\n");
+
+	event = malidp->crtc.state->event;
+	if (event) {
+		malidp->crtc.state->event = NULL;
+
+		spin_lock_irq(&drm->event_lock);
+		if (drm_crtc_vblank_get(&malidp->crtc) == 0)
+			drm_crtc_arm_vblank_event(&malidp->crtc, event);
+		else
+			drm_crtc_send_vblank_event(&malidp->crtc, event);
+		spin_unlock_irq(&drm->event_lock);
+	}
+	drm_atomic_helper_commit_hw_done(state);
+}
+
+static void malidp_atomic_commit_tail(struct drm_atomic_state *state)
+{
+	struct drm_device *drm = state->dev;
+
+	drm_atomic_helper_commit_modeset_disables(drm, state);
+	drm_atomic_helper_commit_modeset_enables(drm, state);
+	drm_atomic_helper_commit_planes(drm, state, true);
+
+	malidp_atomic_commit_hw_done(state);
+
+	drm_atomic_helper_wait_for_vblanks(drm, state);
+
+	drm_atomic_helper_cleanup_planes(drm, state);
+}
+
+static struct drm_mode_config_helper_funcs malidp_mode_config_helpers = {
+	.atomic_commit_tail = malidp_atomic_commit_tail,
+};
+
+static const struct drm_mode_config_funcs malidp_mode_config_funcs = {
+	.fb_create = drm_fb_cma_create,
+	.output_poll_changed = malidp_output_poll_changed,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
+static int malidp_enable_vblank(struct drm_device *drm, unsigned int crtc)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
+
+	malidp_hw_enable_irq(hwdev, MALIDP_DE_BLOCK,
+			     hwdev->map.de_irq_map.vsync_irq);
+	return 0;
+}
+
+static void malidp_disable_vblank(struct drm_device *drm, unsigned int pipe)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
+
+	malidp_hw_disable_irq(hwdev, MALIDP_DE_BLOCK,
+			      hwdev->map.de_irq_map.vsync_irq);
+}
+
+static int malidp_init(struct drm_device *drm)
+{
+	int ret;
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
+
+	drm_mode_config_init(drm);
+
+	drm->mode_config.min_width = hwdev->min_line_size;
+	drm->mode_config.min_height = hwdev->min_line_size;
+	drm->mode_config.max_width = hwdev->max_line_size;
+	drm->mode_config.max_height = hwdev->max_line_size;
+	drm->mode_config.funcs = &malidp_mode_config_funcs;
+	drm->mode_config.helper_private = &malidp_mode_config_helpers;
+
+	ret = malidp_crtc_init(drm);
+	if (ret) {
+		drm_mode_config_cleanup(drm);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int malidp_irq_init(struct platform_device *pdev)
+{
+	int irq_de, irq_se, ret = 0;
+	struct drm_device *drm = dev_get_drvdata(&pdev->dev);
+
+	/* fetch the interrupts from DT */
+	irq_de = platform_get_irq_byname(pdev, "DE");
+	if (irq_de < 0) {
+		DRM_ERROR("no 'DE' IRQ specified!\n");
+		return irq_de;
+	}
+	irq_se = platform_get_irq_byname(pdev, "SE");
+	if (irq_se < 0) {
+		DRM_ERROR("no 'SE' IRQ specified!\n");
+		return irq_se;
+	}
+
+	ret = malidp_de_irq_init(drm, irq_de);
+	if (ret)
+		return ret;
+
+	ret = malidp_se_irq_init(drm, irq_se);
+	if (ret) {
+		malidp_de_irq_fini(drm);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void malidp_lastclose(struct drm_device *drm)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+
+	drm_fbdev_cma_restore_mode(malidp->fbdev);
+}
+
+static const struct file_operations fops = {
+	.owner = THIS_MODULE,
+	.open = drm_open,
+	.release = drm_release,
+	.unlocked_ioctl = drm_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = drm_compat_ioctl,
+#endif
+	.poll = drm_poll,
+	.read = drm_read,
+	.llseek = noop_llseek,
+	.mmap = drm_gem_cma_mmap,
+};
+
+static struct drm_driver malidp_driver = {
+	.driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC |
+			   DRIVER_PRIME,
+	.lastclose = malidp_lastclose,
+	.get_vblank_counter = drm_vblank_no_hw_counter,
+	.enable_vblank = malidp_enable_vblank,
+	.disable_vblank = malidp_disable_vblank,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
+	.gem_vm_ops = &drm_gem_cma_vm_ops,
+	.dumb_create = drm_gem_cma_dumb_create,
+	.dumb_map_offset = drm_gem_cma_dumb_map_offset,
+	.dumb_destroy = drm_gem_dumb_destroy,
+	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
+	.gem_prime_export = drm_gem_prime_export,
+	.gem_prime_import = drm_gem_prime_import,
+	.gem_prime_get_sg_table = drm_gem_cma_prime_get_sg_table,
+	.gem_prime_import_sg_table = drm_gem_cma_prime_import_sg_table,
+	.gem_prime_vmap = drm_gem_cma_prime_vmap,
+	.gem_prime_vunmap = drm_gem_cma_prime_vunmap,
+	.gem_prime_mmap = drm_gem_cma_prime_mmap,
+	.fops = &fops,
+	.name = "mali-dp",
+	.desc = "ARM Mali Display Processor driver",
+	.date = "20160106",
+	.major = 1,
+	.minor = 0,
+};
+
+static const struct of_device_id  malidp_drm_of_match[] = {
+	{
+		.compatible = "arm,mali-dp500",
+		.data = &malidp_device[MALIDP_500]
+	},
+	{
+		.compatible = "arm,mali-dp550",
+		.data = &malidp_device[MALIDP_550]
+	},
+	{
+		.compatible = "arm,mali-dp650",
+		.data = &malidp_device[MALIDP_650]
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, malidp_drm_of_match);
+
+#define MAX_OUTPUT_CHANNELS	3
+
+static int malidp_bind(struct device *dev)
+{
+	struct resource *res;
+	struct drm_device *drm;
+	struct device_node *ep;
+	struct malidp_drm *malidp;
+	struct malidp_hw_device *hwdev;
+	struct platform_device *pdev = to_platform_device(dev);
+	/* number of lines for the R, G and B output */
+	u8 output_width[MAX_OUTPUT_CHANNELS];
+	int ret = 0, i;
+	u32 version, out_depth = 0;
+
+	malidp = devm_kzalloc(dev, sizeof(*malidp), GFP_KERNEL);
+	if (!malidp)
+		return -ENOMEM;
+
+	hwdev = devm_kzalloc(dev, sizeof(*hwdev), GFP_KERNEL);
+	if (!hwdev)
+		return -ENOMEM;
+
+	/*
+	 * copy the associated data from malidp_drm_of_match to avoid
+	 * having to keep a reference to the OF node after binding
+	 */
+	memcpy(hwdev, of_device_get_match_data(dev), sizeof(*hwdev));
+	malidp->dev = hwdev;
+
+	INIT_LIST_HEAD(&malidp->event_list);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	hwdev->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(hwdev->regs))
+		return PTR_ERR(hwdev->regs);
+
+	hwdev->pclk = devm_clk_get(dev, "pclk");
+	if (IS_ERR(hwdev->pclk))
+		return PTR_ERR(hwdev->pclk);
+
+	hwdev->aclk = devm_clk_get(dev, "aclk");
+	if (IS_ERR(hwdev->aclk))
+		return PTR_ERR(hwdev->aclk);
+
+	hwdev->mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(hwdev->mclk))
+		return PTR_ERR(hwdev->mclk);
+
+	hwdev->pxlclk = devm_clk_get(dev, "pxlclk");
+	if (IS_ERR(hwdev->pxlclk))
+		return PTR_ERR(hwdev->pxlclk);
+
+	/* Get the optional framebuffer memory resource */
+	ret = of_reserved_mem_device_init(dev);
+	if (ret && ret != -ENODEV)
+		return ret;
+
+	drm = drm_dev_alloc(&malidp_driver, dev);
+	if (!drm) {
+		ret = -ENOMEM;
+		goto alloc_fail;
+	}
+
+	/* Enable APB clock in order to get access to the registers */
+	clk_prepare_enable(hwdev->pclk);
+	/*
+	 * Enable AXI clock and main clock so that prefetch can start once
+	 * the registers are set
+	 */
+	clk_prepare_enable(hwdev->aclk);
+	clk_prepare_enable(hwdev->mclk);
+
+	ret = hwdev->query_hw(hwdev);
+	if (ret) {
+		DRM_ERROR("Invalid HW configuration\n");
+		goto query_hw_fail;
+	}
+
+	version = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_DE_CORE_ID);
+	DRM_INFO("found ARM Mali-DP%3x version r%dp%d\n", version >> 16,
+		 (version >> 12) & 0xf, (version >> 8) & 0xf);
+
+	/* set the number of lines used for output of RGB data */
+	ret = of_property_read_u8_array(dev->of_node,
+					"arm,malidp-output-port-lines",
+					output_width, MAX_OUTPUT_CHANNELS);
+	if (ret)
+		goto query_hw_fail;
+
+	for (i = 0; i < MAX_OUTPUT_CHANNELS; i++)
+		out_depth = (out_depth << 8) | (output_width[i] & 0xf);
+	malidp_hw_write(hwdev, out_depth, hwdev->map.out_depth_base);
+
+	drm->dev_private = malidp;
+	dev_set_drvdata(dev, drm);
+	atomic_set(&malidp->config_valid, 0);
+	init_waitqueue_head(&malidp->wq);
+
+	ret = malidp_init(drm);
+	if (ret < 0)
+		goto init_fail;
+
+	ret = drm_dev_register(drm, 0);
+	if (ret)
+		goto register_fail;
+
+	/* Set the CRTC's port so that the encoder component can find it */
+	ep = of_graph_get_next_endpoint(dev->of_node, NULL);
+	if (!ep) {
+		ret = -EINVAL;
+		goto port_fail;
+	}
+	malidp->crtc.port = of_get_next_parent(ep);
+
+	ret = component_bind_all(dev, drm);
+	if (ret) {
+		DRM_ERROR("Failed to bind all components\n");
+		goto bind_fail;
+	}
+
+	ret = malidp_irq_init(pdev);
+	if (ret < 0)
+		goto irq_init_fail;
+
+	ret = drm_vblank_init(drm, drm->mode_config.num_crtc);
+	if (ret < 0) {
+		DRM_ERROR("failed to initialise vblank\n");
+		goto vblank_fail;
+	}
+
+	drm_mode_config_reset(drm);
+
+	malidp->fbdev = drm_fbdev_cma_init(drm, 32, drm->mode_config.num_crtc,
+					   drm->mode_config.num_connector);
+
+	if (IS_ERR(malidp->fbdev)) {
+		ret = PTR_ERR(malidp->fbdev);
+		malidp->fbdev = NULL;
+		goto fbdev_fail;
+	}
+
+	drm_kms_helper_poll_init(drm);
+	return 0;
+
+fbdev_fail:
+	drm_vblank_cleanup(drm);
+vblank_fail:
+	malidp_se_irq_fini(drm);
+	malidp_de_irq_fini(drm);
+irq_init_fail:
+	component_unbind_all(dev, drm);
+bind_fail:
+	of_node_put(malidp->crtc.port);
+	malidp->crtc.port = NULL;
+port_fail:
+	drm_dev_unregister(drm);
+register_fail:
+	malidp_de_planes_destroy(drm);
+	drm_mode_config_cleanup(drm);
+init_fail:
+	drm->dev_private = NULL;
+	dev_set_drvdata(dev, NULL);
+query_hw_fail:
+	clk_disable_unprepare(hwdev->mclk);
+	clk_disable_unprepare(hwdev->aclk);
+	clk_disable_unprepare(hwdev->pclk);
+	drm_dev_unref(drm);
+alloc_fail:
+	of_reserved_mem_device_release(dev);
+
+	return ret;
+}
+
+static void malidp_unbind(struct device *dev)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
+
+	if (malidp->fbdev) {
+		drm_fbdev_cma_fini(malidp->fbdev);
+		malidp->fbdev = NULL;
+	}
+	drm_kms_helper_poll_fini(drm);
+	malidp_se_irq_fini(drm);
+	malidp_de_irq_fini(drm);
+	drm_vblank_cleanup(drm);
+	component_unbind_all(dev, drm);
+	of_node_put(malidp->crtc.port);
+	malidp->crtc.port = NULL;
+	drm_dev_unregister(drm);
+	malidp_de_planes_destroy(drm);
+	drm_mode_config_cleanup(drm);
+	drm->dev_private = NULL;
+	dev_set_drvdata(dev, NULL);
+	clk_disable_unprepare(hwdev->mclk);
+	clk_disable_unprepare(hwdev->aclk);
+	clk_disable_unprepare(hwdev->pclk);
+	drm_dev_unref(drm);
+	of_reserved_mem_device_release(dev);
+}
+
+static const struct component_master_ops malidp_master_ops = {
+	.bind = malidp_bind,
+	.unbind = malidp_unbind,
+};
+
+static int malidp_compare_dev(struct device *dev, void *data)
+{
+	struct device_node *np = data;
+
+	return dev->of_node == np;
+}
+
+static int malidp_platform_probe(struct platform_device *pdev)
+{
+	struct device_node *port, *ep;
+	struct component_match *match = NULL;
+
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
+	/* there is only one output port inside each device, find it */
+	ep = of_graph_get_next_endpoint(pdev->dev.of_node, NULL);
+	if (!ep)
+		return -ENODEV;
+
+	if (!of_device_is_available(ep)) {
+		of_node_put(ep);
+		return -ENODEV;
+	}
+
+	/* add the remote encoder port as component */
+	port = of_graph_get_remote_port_parent(ep);
+	of_node_put(ep);
+	if (!port || !of_device_is_available(port)) {
+		of_node_put(port);
+		return -EAGAIN;
+	}
+
+	component_match_add(&pdev->dev, &match, malidp_compare_dev, port);
+	return component_master_add_with_match(&pdev->dev, &malidp_master_ops,
+					       match);
+}
+
+static int malidp_platform_remove(struct platform_device *pdev)
+{
+	component_master_del(&pdev->dev, &malidp_master_ops);
+	return 0;
+}
+
+static struct platform_driver malidp_platform_driver = {
+	.probe		= malidp_platform_probe,
+	.remove		= malidp_platform_remove,
+	.driver	= {
+		.name = "mali-dp",
+		.of_match_table	= malidp_drm_of_match,
+	},
+};
+
+module_platform_driver(malidp_platform_driver);
+
+MODULE_AUTHOR("Liviu Dudau <Liviu.Dudau@arm.com>");
+MODULE_DESCRIPTION("ARM Mali DP DRM driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/arm/malidp_drv.h b/drivers/gpu/drm/arm/malidp_drv.h
new file mode 100644
index 000000000000..95558fde214b
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_drv.h
@@ -0,0 +1,54 @@
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Liviu Dudau <Liviu.Dudau@arm.com>
+ *
+ * This program is free software and is provided to you under the terms of the
+ * GNU General Public License version 2 as published by the Free Software
+ * Foundation, and any use by you of this program is subject to the terms
+ * of such GNU licence.
+ *
+ * ARM Mali DP500/DP550/DP650 KMS/DRM driver structures
+ */
+
+#ifndef __MALIDP_DRV_H__
+#define __MALIDP_DRV_H__
+
+#include <linux/mutex.h>
+#include <linux/wait.h>
+#include "malidp_hw.h"
+
+struct malidp_drm {
+	struct malidp_hw_device *dev;
+	struct drm_fbdev_cma *fbdev;
+	struct list_head event_list;
+	struct drm_crtc crtc;
+	wait_queue_head_t wq;
+	atomic_t config_valid;
+};
+
+#define crtc_to_malidp_device(x) container_of(x, struct malidp_drm, crtc)
+
+struct malidp_plane {
+	struct drm_plane base;
+	struct malidp_hw_device *hwdev;
+	const struct malidp_layer *layer;
+};
+
+struct malidp_plane_state {
+	struct drm_plane_state base;
+
+	/* size of the required rotation memory if plane is rotated */
+	u32 rotmem_size;
+};
+
+#define to_malidp_plane(x) container_of(x, struct malidp_plane, base)
+#define to_malidp_plane_state(x) container_of(x, struct malidp_plane_state, base)
+
+int malidp_de_planes_init(struct drm_device *drm);
+void malidp_de_planes_destroy(struct drm_device *drm);
+int malidp_crtc_init(struct drm_device *drm);
+
+/* often used combination of rotational bits */
+#define MALIDP_ROTATED_MASK	(BIT(DRM_ROTATE_90) | BIT(DRM_ROTATE_270))
+
+#endif  /* __MALIDP_DRV_H__ */
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
new file mode 100644
index 000000000000..a6132f1d58c1
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -0,0 +1,691 @@
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Liviu Dudau <Liviu.Dudau@arm.com>
+ *
+ * This program is free software and is provided to you under the terms of the
+ * GNU General Public License version 2 as published by the Free Software
+ * Foundation, and any use by you of this program is subject to the terms
+ * of such GNU licence.
+ *
+ * ARM Mali DP500/DP550/DP650 hardware manipulation routines. This is where
+ * the difference between various versions of the hardware is being dealt with
+ * in an attempt to provide to the rest of the driver code a unified view
+ */
+
+#include <linux/types.h>
+#include <linux/io.h>
+#include <drm/drmP.h>
+#include <video/videomode.h>
+#include <video/display_timing.h>
+
+#include "malidp_drv.h"
+#include "malidp_hw.h"
+
+static const struct malidp_input_format malidp500_de_formats[] = {
+	/*    fourcc,   layers supporting the format,     internal id  */
+	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  0 },
+	{ DRM_FORMAT_ABGR2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  1 },
+	{ DRM_FORMAT_ARGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  2 },
+	{ DRM_FORMAT_ABGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  3 },
+	{ DRM_FORMAT_XRGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  4 },
+	{ DRM_FORMAT_XBGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  5 },
+	{ DRM_FORMAT_RGB888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  6 },
+	{ DRM_FORMAT_BGR888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  7 },
+	{ DRM_FORMAT_RGBA5551, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  8 },
+	{ DRM_FORMAT_ABGR1555, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  9 },
+	{ DRM_FORMAT_RGB565, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2, 10 },
+	{ DRM_FORMAT_BGR565, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2, 11 },
+	{ DRM_FORMAT_UYVY, DE_VIDEO1, 12 },
+	{ DRM_FORMAT_YUYV, DE_VIDEO1, 13 },
+	{ DRM_FORMAT_NV12, DE_VIDEO1, 14 },
+	{ DRM_FORMAT_YUV420, DE_VIDEO1, 15 },
+};
+
+#define MALIDP_ID(__group, __format) \
+	((((__group) & 0x7) << 3) | ((__format) & 0x7))
+
+#define MALIDP_COMMON_FORMATS \
+	/*    fourcc,   layers supporting the format,      internal id   */ \
+	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 0) }, \
+	{ DRM_FORMAT_ABGR2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 1) }, \
+	{ DRM_FORMAT_RGBA1010102, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 2) }, \
+	{ DRM_FORMAT_BGRA1010102, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 3) }, \
+	{ DRM_FORMAT_ARGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 0) }, \
+	{ DRM_FORMAT_ABGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 1) }, \
+	{ DRM_FORMAT_RGBA8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 2) }, \
+	{ DRM_FORMAT_BGRA8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 3) }, \
+	{ DRM_FORMAT_XRGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 0) }, \
+	{ DRM_FORMAT_XBGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 1) }, \
+	{ DRM_FORMAT_RGBX8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 2) }, \
+	{ DRM_FORMAT_BGRX8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 3) }, \
+	{ DRM_FORMAT_RGB888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(3, 0) }, \
+	{ DRM_FORMAT_BGR888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(3, 1) }, \
+	{ DRM_FORMAT_RGBA5551, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 0) }, \
+	{ DRM_FORMAT_ABGR1555, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 1) }, \
+	{ DRM_FORMAT_RGB565, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 2) }, \
+	{ DRM_FORMAT_BGR565, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 3) }, \
+	{ DRM_FORMAT_YUYV, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 2) },	\
+	{ DRM_FORMAT_UYVY, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 3) },	\
+	{ DRM_FORMAT_NV12, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 6) },	\
+	{ DRM_FORMAT_YUV420, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 7) }
+
+static const struct malidp_input_format malidp550_de_formats[] = {
+	MALIDP_COMMON_FORMATS,
+};
+
+static const struct malidp_layer malidp500_layers[] = {
+	{ DE_VIDEO1, MALIDP500_DE_LV_BASE, MALIDP500_DE_LV_PTR_BASE },
+	{ DE_GRAPHICS1, MALIDP500_DE_LG1_BASE, MALIDP500_DE_LG1_PTR_BASE },
+	{ DE_GRAPHICS2, MALIDP500_DE_LG2_BASE, MALIDP500_DE_LG2_PTR_BASE },
+};
+
+static const struct malidp_layer malidp550_layers[] = {
+	{ DE_VIDEO1, MALIDP550_DE_LV1_BASE, MALIDP550_DE_LV1_PTR_BASE },
+	{ DE_GRAPHICS1, MALIDP550_DE_LG_BASE, MALIDP550_DE_LG_PTR_BASE },
+	{ DE_VIDEO2, MALIDP550_DE_LV2_BASE, MALIDP550_DE_LV2_PTR_BASE },
+	{ DE_SMART, MALIDP550_DE_LS_BASE, MALIDP550_DE_LS_PTR_BASE },
+};
+
+#define MALIDP_DE_DEFAULT_PREFETCH_START	5
+
+static int malidp500_query_hw(struct malidp_hw_device *hwdev)
+{
+	u32 conf = malidp_hw_read(hwdev, MALIDP500_CONFIG_ID);
+	/* bit 4 of the CONFIG_ID register holds the line size multiplier */
+	u8 ln_size_mult = conf & 0x10 ? 2 : 1;
+
+	hwdev->min_line_size = 2;
+	hwdev->max_line_size = SZ_2K * ln_size_mult;
+	hwdev->rotation_memory[0] = SZ_1K * 64 * ln_size_mult;
+	hwdev->rotation_memory[1] = 0; /* no second rotation memory bank */
+
+	return 0;
+}
+
+static void malidp500_enter_config_mode(struct malidp_hw_device *hwdev)
+{
+	u32 status, count = 100;
+
+	malidp_hw_setbits(hwdev, MALIDP500_DC_CONFIG_REQ, MALIDP500_DC_CONTROL);
+	while (count) {
+		status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+		if ((status & MALIDP500_DC_CONFIG_REQ) == MALIDP500_DC_CONFIG_REQ)
+			break;
+		/*
+		 * entering config mode can take as long as the rendering
+		 * of a full frame, hence the long sleep here
+		 */
+		usleep_range(1000, 10000);
+		count--;
+	}
+	WARN(count == 0, "timeout while entering config mode");
+}
+
+static void malidp500_leave_config_mode(struct malidp_hw_device *hwdev)
+{
+	u32 status, count = 100;
+
+	malidp_hw_clearbits(hwdev, MALIDP500_DC_CONFIG_REQ, MALIDP500_DC_CONTROL);
+	while (count) {
+		status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+		if ((status & MALIDP500_DC_CONFIG_REQ) == 0)
+			break;
+		usleep_range(100, 1000);
+		count--;
+	}
+	WARN(count == 0, "timeout while leaving config mode");
+}
+
+static bool malidp500_in_config_mode(struct malidp_hw_device *hwdev)
+{
+	u32 status;
+
+	status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+	if ((status & MALIDP500_DC_CONFIG_REQ) == MALIDP500_DC_CONFIG_REQ)
+		return true;
+
+	return false;
+}
+
+static void malidp500_set_config_valid(struct malidp_hw_device *hwdev)
+{
+	malidp_hw_setbits(hwdev, MALIDP_CFG_VALID, MALIDP500_CONFIG_VALID);
+}
+
+static void malidp500_modeset(struct malidp_hw_device *hwdev, struct videomode *mode)
+{
+	u32 val = 0;
+
+	malidp_hw_clearbits(hwdev, MALIDP500_DC_CLEAR_MASK, MALIDP500_DC_CONTROL);
+	if (mode->flags & DISPLAY_FLAGS_HSYNC_HIGH)
+		val |= MALIDP500_HSYNCPOL;
+	if (mode->flags & DISPLAY_FLAGS_VSYNC_HIGH)
+		val |= MALIDP500_VSYNCPOL;
+	val |= MALIDP_DE_DEFAULT_PREFETCH_START;
+	malidp_hw_setbits(hwdev, val, MALIDP500_DC_CONTROL);
+
+	/*
+	 * Mali-DP500 encodes the background color like this:
+	 *    - red   @ MALIDP500_BGND_COLOR[12:0]
+	 *    - green @ MALIDP500_BGND_COLOR[27:16]
+	 *    - blue  @ (MALIDP500_BGND_COLOR + 4)[12:0]
+	 */
+	val = ((MALIDP_BGND_COLOR_G & 0xfff) << 16) |
+	      (MALIDP_BGND_COLOR_R & 0xfff);
+	malidp_hw_write(hwdev, val, MALIDP500_BGND_COLOR);
+	malidp_hw_write(hwdev, MALIDP_BGND_COLOR_B, MALIDP500_BGND_COLOR + 4);
+
+	val = MALIDP_DE_H_FRONTPORCH(mode->hfront_porch) |
+		MALIDP_DE_H_BACKPORCH(mode->hback_porch);
+	malidp_hw_write(hwdev, val, MALIDP500_TIMINGS_BASE + MALIDP_DE_H_TIMINGS);
+
+	val = MALIDP500_DE_V_FRONTPORCH(mode->vfront_porch) |
+		MALIDP_DE_V_BACKPORCH(mode->vback_porch);
+	malidp_hw_write(hwdev, val, MALIDP500_TIMINGS_BASE + MALIDP_DE_V_TIMINGS);
+
+	val = MALIDP_DE_H_SYNCWIDTH(mode->hsync_len) |
+		MALIDP_DE_V_SYNCWIDTH(mode->vsync_len);
+	malidp_hw_write(hwdev, val, MALIDP500_TIMINGS_BASE + MALIDP_DE_SYNC_WIDTH);
+
+	val = MALIDP_DE_H_ACTIVE(mode->hactive) | MALIDP_DE_V_ACTIVE(mode->vactive);
+	malidp_hw_write(hwdev, val, MALIDP500_TIMINGS_BASE + MALIDP_DE_HV_ACTIVE);
+
+	if (mode->flags & DISPLAY_FLAGS_INTERLACED)
+		malidp_hw_setbits(hwdev, MALIDP_DISP_FUNC_ILACED, MALIDP_DE_DISPLAY_FUNC);
+	else
+		malidp_hw_clearbits(hwdev, MALIDP_DISP_FUNC_ILACED, MALIDP_DE_DISPLAY_FUNC);
+}
+
+static int malidp500_rotmem_required(struct malidp_hw_device *hwdev, u16 w, u16 h, u32 fmt)
+{
+	unsigned int depth;
+	int bpp;
+
+	/* RGB888 or BGR888 can't be rotated */
+	if ((fmt == DRM_FORMAT_RGB888) || (fmt == DRM_FORMAT_BGR888))
+		return -EINVAL;
+
+	/*
+	 * Each layer needs enough rotation memory to fit 8 lines
+	 * worth of pixel data. Required size is then:
+	 *    size = rotated_width * (bpp / 8) * 8;
+	 */
+	drm_fb_get_bpp_depth(fmt, &depth, &bpp);
+
+	return w * bpp;
+}
+
+static int malidp550_query_hw(struct malidp_hw_device *hwdev)
+{
+	u32 conf = malidp_hw_read(hwdev, MALIDP550_CONFIG_ID);
+	u8 ln_size = (conf >> 4) & 0x3, rsize;
+
+	hwdev->min_line_size = 2;
+
+	switch (ln_size) {
+	case 0:
+		hwdev->max_line_size = SZ_2K;
+		/* two banks of 64KB for rotation memory */
+		rsize = 64;
+		break;
+	case 1:
+		hwdev->max_line_size = SZ_4K;
+		/* two banks of 128KB for rotation memory */
+		rsize = 128;
+		break;
+	case 2:
+		hwdev->max_line_size = 1280;
+		/* two banks of 40KB for rotation memory */
+		rsize = 40;
+		break;
+	case 3:
+		/* reserved value */
+		hwdev->max_line_size = 0;
+		return -EINVAL;
+	}
+
+	hwdev->rotation_memory[0] = hwdev->rotation_memory[1] = rsize * SZ_1K;
+	return 0;
+}
+
+static void malidp550_enter_config_mode(struct malidp_hw_device *hwdev)
+{
+	u32 status, count = 100;
+
+	malidp_hw_setbits(hwdev, MALIDP550_DC_CONFIG_REQ, MALIDP550_DC_CONTROL);
+	while (count) {
+		status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+		if ((status & MALIDP550_DC_CONFIG_REQ) == MALIDP550_DC_CONFIG_REQ)
+			break;
+		/*
+		 * entering config mode can take as long as the rendering
+		 * of a full frame, hence the long sleep here
+		 */
+		usleep_range(1000, 10000);
+		count--;
+	}
+	WARN(count == 0, "timeout while entering config mode");
+}
+
+static void malidp550_leave_config_mode(struct malidp_hw_device *hwdev)
+{
+	u32 status, count = 100;
+
+	malidp_hw_clearbits(hwdev, MALIDP550_DC_CONFIG_REQ, MALIDP550_DC_CONTROL);
+	while (count) {
+		status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+		if ((status & MALIDP550_DC_CONFIG_REQ) == 0)
+			break;
+		usleep_range(100, 1000);
+		count--;
+	}
+	WARN(count == 0, "timeout while leaving config mode");
+}
+
+static bool malidp550_in_config_mode(struct malidp_hw_device *hwdev)
+{
+	u32 status;
+
+	status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+	if ((status & MALIDP550_DC_CONFIG_REQ) == MALIDP550_DC_CONFIG_REQ)
+		return true;
+
+	return false;
+}
+
+static void malidp550_set_config_valid(struct malidp_hw_device *hwdev)
+{
+	malidp_hw_setbits(hwdev, MALIDP_CFG_VALID, MALIDP550_CONFIG_VALID);
+}
+
+static void malidp550_modeset(struct malidp_hw_device *hwdev, struct videomode *mode)
+{
+	u32 val = MALIDP_DE_DEFAULT_PREFETCH_START;
+
+	malidp_hw_write(hwdev, val, MALIDP550_DE_CONTROL);
+	/*
+	 * Mali-DP550 and Mali-DP650 encode the background color like this:
+	 *   - red   @ MALIDP550_DE_BGND_COLOR[23:16]
+	 *   - green @ MALIDP550_DE_BGND_COLOR[15:8]
+	 *   - blue  @ MALIDP550_DE_BGND_COLOR[7:0]
+	 *
+	 * We need to truncate the least significant 4 bits from the default
+	 * MALIDP_BGND_COLOR_x values
+	 */
+	val = (((MALIDP_BGND_COLOR_R >> 4) & 0xff) << 16) |
+	      (((MALIDP_BGND_COLOR_G >> 4) & 0xff) << 8) |
+	      ((MALIDP_BGND_COLOR_B >> 4) & 0xff);
+	malidp_hw_write(hwdev, val, MALIDP550_DE_BGND_COLOR);
+
+	val = MALIDP_DE_H_FRONTPORCH(mode->hfront_porch) |
+		MALIDP_DE_H_BACKPORCH(mode->hback_porch);
+	malidp_hw_write(hwdev, val, MALIDP550_TIMINGS_BASE + MALIDP_DE_H_TIMINGS);
+
+	val = MALIDP550_DE_V_FRONTPORCH(mode->vfront_porch) |
+		MALIDP_DE_V_BACKPORCH(mode->vback_porch);
+	malidp_hw_write(hwdev, val, MALIDP550_TIMINGS_BASE + MALIDP_DE_V_TIMINGS);
+
+	val = MALIDP_DE_H_SYNCWIDTH(mode->hsync_len) |
+		MALIDP_DE_V_SYNCWIDTH(mode->vsync_len);
+	if (mode->flags & DISPLAY_FLAGS_HSYNC_HIGH)
+		val |= MALIDP550_HSYNCPOL;
+	if (mode->flags & DISPLAY_FLAGS_VSYNC_HIGH)
+		val |= MALIDP550_VSYNCPOL;
+	malidp_hw_write(hwdev, val, MALIDP550_TIMINGS_BASE + MALIDP_DE_SYNC_WIDTH);
+
+	val = MALIDP_DE_H_ACTIVE(mode->hactive) | MALIDP_DE_V_ACTIVE(mode->vactive);
+	malidp_hw_write(hwdev, val, MALIDP550_TIMINGS_BASE + MALIDP_DE_HV_ACTIVE);
+
+	if (mode->flags & DISPLAY_FLAGS_INTERLACED)
+		malidp_hw_setbits(hwdev, MALIDP_DISP_FUNC_ILACED, MALIDP_DE_DISPLAY_FUNC);
+	else
+		malidp_hw_clearbits(hwdev, MALIDP_DISP_FUNC_ILACED, MALIDP_DE_DISPLAY_FUNC);
+}
+
+static int malidp550_rotmem_required(struct malidp_hw_device *hwdev, u16 w, u16 h, u32 fmt)
+{
+	u32 bytes_per_col;
+
+	/* raw RGB888 or BGR888 can't be rotated */
+	if ((fmt == DRM_FORMAT_RGB888) || (fmt == DRM_FORMAT_BGR888))
+		return -EINVAL;
+
+	switch (fmt) {
+	/* 8 lines at 4 bytes per pixel */
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
+	case DRM_FORMAT_RGBA1010102:
+	case DRM_FORMAT_BGRA1010102:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_RGBA8888:
+	case DRM_FORMAT_BGRA8888:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_RGBX8888:
+	case DRM_FORMAT_BGRX8888:
+	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_BGR888:
+	/* 16 lines at 2 bytes per pixel */
+	case DRM_FORMAT_RGBA5551:
+	case DRM_FORMAT_ABGR1555:
+	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_BGR565:
+	case DRM_FORMAT_UYVY:
+	case DRM_FORMAT_YUYV:
+		bytes_per_col = 32;
+		break;
+	/* 16 lines at 1.5 bytes per pixel */
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_YUV420:
+		bytes_per_col = 24;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return w * bytes_per_col;
+}
+
+static int malidp650_query_hw(struct malidp_hw_device *hwdev)
+{
+	u32 conf = malidp_hw_read(hwdev, MALIDP550_CONFIG_ID);
+	u8 ln_size = (conf >> 4) & 0x3, rsize;
+
+	hwdev->min_line_size = 4;
+
+	switch (ln_size) {
+	case 0:
+	case 2:
+		/* reserved values */
+		hwdev->max_line_size = 0;
+		return -EINVAL;
+	case 1:
+		hwdev->max_line_size = SZ_4K;
+		/* two banks of 128KB for rotation memory */
+		rsize = 128;
+		break;
+	case 3:
+		hwdev->max_line_size = 2560;
+		/* two banks of 80KB for rotation memory */
+		rsize = 80;
+	}
+
+	hwdev->rotation_memory[0] = hwdev->rotation_memory[1] = rsize * SZ_1K;
+	return 0;
+}
+
+const struct malidp_hw_device malidp_device[MALIDP_MAX_DEVICES] = {
+	[MALIDP_500] = {
+		.map = {
+			.se_base = MALIDP500_SE_BASE,
+			.dc_base = MALIDP500_DC_BASE,
+			.out_depth_base = MALIDP500_OUTPUT_DEPTH,
+			.features = 0,	/* no CLEARIRQ register */
+			.n_layers = ARRAY_SIZE(malidp500_layers),
+			.layers = malidp500_layers,
+			.de_irq_map = {
+				.irq_mask = MALIDP_DE_IRQ_UNDERRUN |
+					    MALIDP500_DE_IRQ_AXI_ERR |
+					    MALIDP500_DE_IRQ_VSYNC |
+					    MALIDP500_DE_IRQ_GLOBAL,
+				.vsync_irq = MALIDP500_DE_IRQ_VSYNC,
+			},
+			.se_irq_map = {
+				.irq_mask = MALIDP500_SE_IRQ_CONF_MODE,
+				.vsync_irq = 0,
+			},
+			.dc_irq_map = {
+				.irq_mask = MALIDP500_DE_IRQ_CONF_VALID,
+				.vsync_irq = MALIDP500_DE_IRQ_CONF_VALID,
+			},
+			.input_formats = malidp500_de_formats,
+			.n_input_formats = ARRAY_SIZE(malidp500_de_formats),
+		},
+		.query_hw = malidp500_query_hw,
+		.enter_config_mode = malidp500_enter_config_mode,
+		.leave_config_mode = malidp500_leave_config_mode,
+		.in_config_mode = malidp500_in_config_mode,
+		.set_config_valid = malidp500_set_config_valid,
+		.modeset = malidp500_modeset,
+		.rotmem_required = malidp500_rotmem_required,
+	},
+	[MALIDP_550] = {
+		.map = {
+			.se_base = MALIDP550_SE_BASE,
+			.dc_base = MALIDP550_DC_BASE,
+			.out_depth_base = MALIDP550_DE_OUTPUT_DEPTH,
+			.features = MALIDP_REGMAP_HAS_CLEARIRQ,
+			.n_layers = ARRAY_SIZE(malidp550_layers),
+			.layers = malidp550_layers,
+			.de_irq_map = {
+				.irq_mask = MALIDP_DE_IRQ_UNDERRUN |
+					    MALIDP550_DE_IRQ_VSYNC,
+				.vsync_irq = MALIDP550_DE_IRQ_VSYNC,
+			},
+			.se_irq_map = {
+				.irq_mask = MALIDP550_SE_IRQ_EOW |
+					    MALIDP550_SE_IRQ_AXI_ERR,
+			},
+			.dc_irq_map = {
+				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID,
+				.vsync_irq = MALIDP550_DC_IRQ_CONF_VALID,
+			},
+			.input_formats = malidp550_de_formats,
+			.n_input_formats = ARRAY_SIZE(malidp550_de_formats),
+		},
+		.query_hw = malidp550_query_hw,
+		.enter_config_mode = malidp550_enter_config_mode,
+		.leave_config_mode = malidp550_leave_config_mode,
+		.in_config_mode = malidp550_in_config_mode,
+		.set_config_valid = malidp550_set_config_valid,
+		.modeset = malidp550_modeset,
+		.rotmem_required = malidp550_rotmem_required,
+	},
+	[MALIDP_650] = {
+		.map = {
+			.se_base = MALIDP550_SE_BASE,
+			.dc_base = MALIDP550_DC_BASE,
+			.out_depth_base = MALIDP550_DE_OUTPUT_DEPTH,
+			.features = MALIDP_REGMAP_HAS_CLEARIRQ,
+			.n_layers = ARRAY_SIZE(malidp550_layers),
+			.layers = malidp550_layers,
+			.de_irq_map = {
+				.irq_mask = MALIDP_DE_IRQ_UNDERRUN |
+					    MALIDP650_DE_IRQ_DRIFT |
+					    MALIDP550_DE_IRQ_VSYNC,
+				.vsync_irq = MALIDP550_DE_IRQ_VSYNC,
+			},
+			.se_irq_map = {
+				.irq_mask = MALIDP550_SE_IRQ_EOW |
+					    MALIDP550_SE_IRQ_AXI_ERR,
+			},
+			.dc_irq_map = {
+				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID,
+				.vsync_irq = MALIDP550_DC_IRQ_CONF_VALID,
+			},
+			.input_formats = malidp550_de_formats,
+			.n_input_formats = ARRAY_SIZE(malidp550_de_formats),
+		},
+		.query_hw = malidp650_query_hw,
+		.enter_config_mode = malidp550_enter_config_mode,
+		.leave_config_mode = malidp550_leave_config_mode,
+		.in_config_mode = malidp550_in_config_mode,
+		.set_config_valid = malidp550_set_config_valid,
+		.modeset = malidp550_modeset,
+		.rotmem_required = malidp550_rotmem_required,
+	},
+};
+
+u8 malidp_hw_get_format_id(const struct malidp_hw_regmap *map,
+			   u8 layer_id, u32 format)
+{
+	unsigned int i;
+
+	for (i = 0; i < map->n_input_formats; i++) {
+		if (((map->input_formats[i].layer & layer_id) == layer_id) &&
+		    (map->input_formats[i].format == format))
+			return map->input_formats[i].id;
+	}
+
+	return MALIDP_INVALID_FORMAT_ID;
+}
+
+static void malidp_hw_clear_irq(struct malidp_hw_device *hwdev, u8 block, u32 irq)
+{
+	u32 base = malidp_get_block_base(hwdev, block);
+
+	if (hwdev->map.features & MALIDP_REGMAP_HAS_CLEARIRQ)
+		malidp_hw_write(hwdev, irq, base + MALIDP_REG_CLEARIRQ);
+	else
+		malidp_hw_write(hwdev, irq, base + MALIDP_REG_STATUS);
+}
+
+static irqreturn_t malidp_de_irq(int irq, void *arg)
+{
+	struct drm_device *drm = arg;
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev;
+	const struct malidp_irq_map *de;
+	u32 status, mask, dc_status;
+	irqreturn_t ret = IRQ_NONE;
+
+	if (!drm->dev_private)
+		return IRQ_HANDLED;
+
+	hwdev = malidp->dev;
+	de = &hwdev->map.de_irq_map;
+
+	/* first handle the config valid IRQ */
+	dc_status = malidp_hw_read(hwdev, hwdev->map.dc_base + MALIDP_REG_STATUS);
+	if (dc_status & hwdev->map.dc_irq_map.vsync_irq) {
+		/* we have a page flip event */
+		atomic_set(&malidp->config_valid, 1);
+		malidp_hw_clear_irq(hwdev, MALIDP_DC_BLOCK, dc_status);
+		ret = IRQ_WAKE_THREAD;
+	}
+
+	status = malidp_hw_read(hwdev, MALIDP_REG_STATUS);
+	if (!(status & de->irq_mask))
+		return ret;
+
+	mask = malidp_hw_read(hwdev, MALIDP_REG_MASKIRQ);
+	status &= mask;
+	if (status & de->vsync_irq)
+		drm_crtc_handle_vblank(&malidp->crtc);
+
+	malidp_hw_clear_irq(hwdev, MALIDP_DE_BLOCK, status);
+
+	return (ret == IRQ_NONE) ? IRQ_HANDLED : ret;
+}
+
+static irqreturn_t malidp_de_irq_thread_handler(int irq, void *arg)
+{
+	struct drm_device *drm = arg;
+	struct malidp_drm *malidp = drm->dev_private;
+
+	wake_up(&malidp->wq);
+
+	return IRQ_HANDLED;
+}
+
+int malidp_de_irq_init(struct drm_device *drm, int irq)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
+	int ret;
+
+	/* ensure interrupts are disabled */
+	malidp_hw_disable_irq(hwdev, MALIDP_DE_BLOCK, 0xffffffff);
+	malidp_hw_clear_irq(hwdev, MALIDP_DE_BLOCK, 0xffffffff);
+	malidp_hw_disable_irq(hwdev, MALIDP_DC_BLOCK, 0xffffffff);
+	malidp_hw_clear_irq(hwdev, MALIDP_DC_BLOCK, 0xffffffff);
+
+	ret = devm_request_threaded_irq(drm->dev, irq, malidp_de_irq,
+					malidp_de_irq_thread_handler,
+					IRQF_SHARED, "malidp-de", drm);
+	if (ret < 0) {
+		DRM_ERROR("failed to install DE IRQ handler\n");
+		return ret;
+	}
+
+	/* first enable the DC block IRQs */
+	malidp_hw_enable_irq(hwdev, MALIDP_DC_BLOCK,
+			     hwdev->map.dc_irq_map.irq_mask);
+
+	/* now enable the DE block IRQs */
+	malidp_hw_enable_irq(hwdev, MALIDP_DE_BLOCK,
+			     hwdev->map.de_irq_map.irq_mask);
+
+	return 0;
+}
+
+void malidp_de_irq_fini(struct drm_device *drm)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
+
+	malidp_hw_disable_irq(hwdev, MALIDP_DE_BLOCK,
+			      hwdev->map.de_irq_map.irq_mask);
+	malidp_hw_disable_irq(hwdev, MALIDP_DC_BLOCK,
+			      hwdev->map.dc_irq_map.irq_mask);
+}
+
+static irqreturn_t malidp_se_irq(int irq, void *arg)
+{
+	struct drm_device *drm = arg;
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
+	u32 status, mask;
+
+	status = malidp_hw_read(hwdev, hwdev->map.se_base + MALIDP_REG_STATUS);
+	if (!(status & hwdev->map.se_irq_map.irq_mask))
+		return IRQ_NONE;
+
+	mask = malidp_hw_read(hwdev, hwdev->map.se_base + MALIDP_REG_MASKIRQ);
+	status = malidp_hw_read(hwdev, hwdev->map.se_base + MALIDP_REG_STATUS);
+	status &= mask;
+	/* ToDo: status decoding and firing up of VSYNC and page flip events */
+
+	malidp_hw_clear_irq(hwdev, MALIDP_SE_BLOCK, status);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t malidp_se_irq_thread_handler(int irq, void *arg)
+{
+	return IRQ_HANDLED;
+}
+
+int malidp_se_irq_init(struct drm_device *drm, int irq)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
+	int ret;
+
+	/* ensure interrupts are disabled */
+	malidp_hw_disable_irq(hwdev, MALIDP_SE_BLOCK, 0xffffffff);
+	malidp_hw_clear_irq(hwdev, MALIDP_SE_BLOCK, 0xffffffff);
+
+	ret = devm_request_threaded_irq(drm->dev, irq, malidp_se_irq,
+					malidp_se_irq_thread_handler,
+					IRQF_SHARED, "malidp-se", drm);
+	if (ret < 0) {
+		DRM_ERROR("failed to install SE IRQ handler\n");
+		return ret;
+	}
+
+	malidp_hw_enable_irq(hwdev, MALIDP_SE_BLOCK,
+			     hwdev->map.se_irq_map.irq_mask);
+
+	return 0;
+}
+
+void malidp_se_irq_fini(struct drm_device *drm)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
+
+	malidp_hw_disable_irq(hwdev, MALIDP_SE_BLOCK,
+			      hwdev->map.se_irq_map.irq_mask);
+}
diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h
new file mode 100644
index 000000000000..141743e9f3a6
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_hw.h
@@ -0,0 +1,241 @@
+/*
+ *
+ * (C) COPYRIGHT 2013-2016 ARM Limited. All rights reserved.
+ *
+ * This program is free software and is provided to you under the terms of the
+ * GNU General Public License version 2 as published by the Free Software
+ * Foundation, and any use by you of this program is subject to the terms
+ * of such GNU licence.
+ *
+ * ARM Mali DP hardware manipulation routines.
+ */
+
+#ifndef __MALIDP_HW_H__
+#define __MALIDP_HW_H__
+
+#include <linux/bitops.h>
+#include "malidp_regs.h"
+
+struct videomode;
+struct clk;
+
+/* Mali DP IP blocks */
+enum {
+	MALIDP_DE_BLOCK = 0,
+	MALIDP_SE_BLOCK,
+	MALIDP_DC_BLOCK
+};
+
+/* Mali DP layer IDs */
+enum {
+	DE_VIDEO1 = BIT(0),
+	DE_GRAPHICS1 = BIT(1),
+	DE_GRAPHICS2 = BIT(2), /* used only in DP500 */
+	DE_VIDEO2 = BIT(3),
+	DE_SMART = BIT(4),
+};
+
+struct malidp_input_format {
+	u32 format;		/* DRM fourcc */
+	u8 layer;		/* bitmask of layers supporting it */
+	u8 id;			/* used internally */
+};
+
+#define MALIDP_INVALID_FORMAT_ID	0xff
+
+/*
+ * hide the differences between register maps
+ * by using a common structure to hold the
+ * base register offsets
+ */
+
+struct malidp_irq_map {
+	u32 irq_mask;		/* mask of IRQs that can be enabled in the block */
+	u32 vsync_irq;		/* IRQ bit used for signaling during VSYNC */
+};
+
+struct malidp_layer {
+	u16 id;			/* layer ID */
+	u16 base;		/* address offset for the register bank */
+	u16 ptr;		/* address offset for the pointer register */
+};
+
+/* regmap features */
+#define MALIDP_REGMAP_HAS_CLEARIRQ	(1 << 0)
+
+struct malidp_hw_regmap {
+	/* address offset of the DE register bank */
+	/* is always 0x0000 */
+	/* address offset of the SE registers bank */
+	const u16 se_base;
+	/* address offset of the DC registers bank */
+	const u16 dc_base;
+
+	/* address offset for the output depth register */
+	const u16 out_depth_base;
+
+	/* bitmap with register map features */
+	const u8 features;
+
+	/* list of supported layers */
+	const u8 n_layers;
+	const struct malidp_layer *layers;
+
+	const struct malidp_irq_map de_irq_map;
+	const struct malidp_irq_map se_irq_map;
+	const struct malidp_irq_map dc_irq_map;
+
+	/* list of supported input formats for each layer */
+	const struct malidp_input_format *input_formats;
+	const u8 n_input_formats;
+};
+
+struct malidp_hw_device {
+	const struct malidp_hw_regmap map;
+	void __iomem *regs;
+
+	/* APB clock */
+	struct clk *pclk;
+	/* AXI clock */
+	struct clk *aclk;
+	/* main clock for display core */
+	struct clk *mclk;
+	/* pixel clock for display core */
+	struct clk *pxlclk;
+
+	/*
+	 * Validate the driver instance against the hardware bits
+	 */
+	int (*query_hw)(struct malidp_hw_device *hwdev);
+
+	/*
+	 * Set the hardware into config mode, ready to accept mode changes
+	 */
+	void (*enter_config_mode)(struct malidp_hw_device *hwdev);
+
+	/*
+	 * Tell hardware to exit configuration mode
+	 */
+	void (*leave_config_mode)(struct malidp_hw_device *hwdev);
+
+	/*
+	 * Query if hardware is in configuration mode
+	 */
+	bool (*in_config_mode)(struct malidp_hw_device *hwdev);
+
+	/*
+	 * Set configuration valid flag for hardware parameters that can
+	 * be changed outside the configuration mode. Hardware will use
+	 * the new settings when config valid is set after the end of the
+	 * current buffer scanout
+	 */
+	void (*set_config_valid)(struct malidp_hw_device *hwdev);
+
+	/*
+	 * Set a new mode in hardware. Requires the hardware to be in
+	 * configuration mode before this function is called.
+	 */
+	void (*modeset)(struct malidp_hw_device *hwdev, struct videomode *m);
+
+	/*
+	 * Calculate the required rotation memory given the active area
+	 * and the buffer format.
+	 */
+	int (*rotmem_required)(struct malidp_hw_device *hwdev, u16 w, u16 h, u32 fmt);
+
+	u8 features;
+
+	u8 min_line_size;
+	u16 max_line_size;
+
+	/* size of memory used for rotating layers, up to two banks available */
+	u32 rotation_memory[2];
+};
+
+/* Supported variants of the hardware */
+enum {
+	MALIDP_500 = 0,
+	MALIDP_550,
+	MALIDP_650,
+	/* keep the next entry last */
+	MALIDP_MAX_DEVICES
+};
+
+extern const struct malidp_hw_device malidp_device[MALIDP_MAX_DEVICES];
+
+static inline u32 malidp_hw_read(struct malidp_hw_device *hwdev, u32 reg)
+{
+	return readl(hwdev->regs + reg);
+}
+
+static inline void malidp_hw_write(struct malidp_hw_device *hwdev,
+				   u32 value, u32 reg)
+{
+	writel(value, hwdev->regs + reg);
+}
+
+static inline void malidp_hw_setbits(struct malidp_hw_device *hwdev,
+				     u32 mask, u32 reg)
+{
+	u32 data = malidp_hw_read(hwdev, reg);
+
+	data |= mask;
+	malidp_hw_write(hwdev, data, reg);
+}
+
+static inline void malidp_hw_clearbits(struct malidp_hw_device *hwdev,
+				       u32 mask, u32 reg)
+{
+	u32 data = malidp_hw_read(hwdev, reg);
+
+	data &= ~mask;
+	malidp_hw_write(hwdev, data, reg);
+}
+
+static inline u32 malidp_get_block_base(struct malidp_hw_device *hwdev,
+					u8 block)
+{
+	switch (block) {
+	case MALIDP_SE_BLOCK:
+		return hwdev->map.se_base;
+	case MALIDP_DC_BLOCK:
+		return hwdev->map.dc_base;
+	}
+
+	return 0;
+}
+
+static inline void malidp_hw_disable_irq(struct malidp_hw_device *hwdev,
+					 u8 block, u32 irq)
+{
+	u32 base = malidp_get_block_base(hwdev, block);
+
+	malidp_hw_clearbits(hwdev, irq, base + MALIDP_REG_MASKIRQ);
+}
+
+static inline void malidp_hw_enable_irq(struct malidp_hw_device *hwdev,
+					u8 block, u32 irq)
+{
+	u32 base = malidp_get_block_base(hwdev, block);
+
+	malidp_hw_setbits(hwdev, irq, base + MALIDP_REG_MASKIRQ);
+}
+
+int malidp_de_irq_init(struct drm_device *drm, int irq);
+void malidp_de_irq_fini(struct drm_device *drm);
+int malidp_se_irq_init(struct drm_device *drm, int irq);
+void malidp_se_irq_fini(struct drm_device *drm);
+
+u8 malidp_hw_get_format_id(const struct malidp_hw_regmap *map,
+			   u8 layer_id, u32 format);
+
+/*
+ * background color components are defined as 12bits values,
+ * they will be shifted right when stored on hardware that
+ * supports only 8bits per channel
+ */
+#define MALIDP_BGND_COLOR_R		0x000
+#define MALIDP_BGND_COLOR_G		0x000
+#define MALIDP_BGND_COLOR_B		0x000
+
+#endif  /* __MALIDP_HW_H__ */
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
new file mode 100644
index 000000000000..725098d6179a
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -0,0 +1,298 @@
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Liviu Dudau <Liviu.Dudau@arm.com>
+ *
+ * This program is free software and is provided to you under the terms of the
+ * GNU General Public License version 2 as published by the Free Software
+ * Foundation, and any use by you of this program is subject to the terms
+ * of such GNU licence.
+ *
+ * ARM Mali DP plane manipulation routines.
+ */
+
+#include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_plane_helper.h>
+
+#include "malidp_hw.h"
+#include "malidp_drv.h"
+
+/* Layer specific register offsets */
+#define MALIDP_LAYER_FORMAT		0x000
+#define MALIDP_LAYER_CONTROL		0x004
+#define   LAYER_ENABLE			(1 << 0)
+#define   LAYER_ROT_OFFSET		8
+#define   LAYER_H_FLIP			(1 << 10)
+#define   LAYER_V_FLIP			(1 << 11)
+#define   LAYER_ROT_MASK		(0xf << 8)
+#define MALIDP_LAYER_SIZE		0x00c
+#define   LAYER_H_VAL(x)		(((x) & 0x1fff) << 0)
+#define   LAYER_V_VAL(x)		(((x) & 0x1fff) << 16)
+#define MALIDP_LAYER_COMP_SIZE		0x010
+#define MALIDP_LAYER_OFFSET		0x014
+#define MALIDP_LAYER_STRIDE		0x018
+
+static void malidp_de_plane_destroy(struct drm_plane *plane)
+{
+	struct malidp_plane *mp = to_malidp_plane(plane);
+
+	if (mp->base.fb)
+		drm_framebuffer_unreference(mp->base.fb);
+
+	drm_plane_helper_disable(plane);
+	drm_plane_cleanup(plane);
+	devm_kfree(plane->dev->dev, mp);
+}
+
+struct drm_plane_state *malidp_duplicate_plane_state(struct drm_plane *plane)
+{
+	struct malidp_plane_state *state, *m_state;
+
+	if (!plane->state)
+		return NULL;
+
+	state = kmalloc(sizeof(*state), GFP_KERNEL);
+	if (state) {
+		m_state = to_malidp_plane_state(plane->state);
+		__drm_atomic_helper_plane_duplicate_state(plane, &state->base);
+		state->rotmem_size = m_state->rotmem_size;
+	}
+
+	return &state->base;
+}
+
+void malidp_destroy_plane_state(struct drm_plane *plane,
+				struct drm_plane_state *state)
+{
+	struct malidp_plane_state *m_state = to_malidp_plane_state(state);
+
+	__drm_atomic_helper_plane_destroy_state(state);
+	kfree(m_state);
+}
+
+static const struct drm_plane_funcs malidp_de_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = malidp_de_plane_destroy,
+	.reset = drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = malidp_duplicate_plane_state,
+	.atomic_destroy_state = malidp_destroy_plane_state,
+};
+
+static int malidp_de_plane_check(struct drm_plane *plane,
+				 struct drm_plane_state *state)
+{
+	struct malidp_plane *mp = to_malidp_plane(plane);
+	struct malidp_plane_state *ms = to_malidp_plane_state(state);
+	u8 format_id;
+	u32 src_w, src_h;
+
+	if (!state->crtc || !state->fb)
+		return 0;
+
+	format_id = malidp_hw_get_format_id(&mp->hwdev->map, mp->layer->id,
+					    state->fb->pixel_format);
+	if (format_id == MALIDP_INVALID_FORMAT_ID)
+		return -EINVAL;
+
+	src_w = state->src_w >> 16;
+	src_h = state->src_h >> 16;
+
+	if ((state->crtc_w > mp->hwdev->max_line_size) ||
+	    (state->crtc_h > mp->hwdev->max_line_size) ||
+	    (state->crtc_w < mp->hwdev->min_line_size) ||
+	    (state->crtc_h < mp->hwdev->min_line_size) ||
+	    (state->crtc_w != src_w) || (state->crtc_h != src_h))
+		return -EINVAL;
+
+	/* packed RGB888 / BGR888 can't be rotated or flipped */
+	if (state->rotation != BIT(DRM_ROTATE_0) &&
+	    (state->fb->pixel_format == DRM_FORMAT_RGB888 ||
+	     state->fb->pixel_format == DRM_FORMAT_BGR888))
+		return -EINVAL;
+
+	ms->rotmem_size = 0;
+	if (state->rotation & MALIDP_ROTATED_MASK) {
+		int val;
+
+		val = mp->hwdev->rotmem_required(mp->hwdev, state->crtc_h,
+						 state->crtc_w,
+						 state->fb->pixel_format);
+		if (val < 0)
+			return val;
+
+		ms->rotmem_size = val;
+	}
+
+	return 0;
+}
+
+static void malidp_de_plane_update(struct drm_plane *plane,
+				   struct drm_plane_state *old_state)
+{
+	struct drm_gem_cma_object *obj;
+	struct malidp_plane *mp;
+	const struct malidp_hw_regmap *map;
+	u8 format_id;
+	u16 ptr;
+	u32 format, src_w, src_h, dest_w, dest_h, val = 0;
+	int num_planes, i;
+
+	mp = to_malidp_plane(plane);
+
+	map = &mp->hwdev->map;
+	format = plane->state->fb->pixel_format;
+	format_id = malidp_hw_get_format_id(map, mp->layer->id, format);
+	num_planes = drm_format_num_planes(format);
+
+	/* convert src values from Q16 fixed point to integer */
+	src_w = plane->state->src_w >> 16;
+	src_h = plane->state->src_h >> 16;
+	if (plane->state->rotation & MALIDP_ROTATED_MASK) {
+		dest_w = plane->state->crtc_h;
+		dest_h = plane->state->crtc_w;
+	} else {
+		dest_w = plane->state->crtc_w;
+		dest_h = plane->state->crtc_h;
+	}
+
+	malidp_hw_write(mp->hwdev, format_id, mp->layer->base);
+
+	for (i = 0; i < num_planes; i++) {
+		/* calculate the offset for the layer's plane registers */
+		ptr = mp->layer->ptr + (i << 4);
+
+		obj = drm_fb_cma_get_gem_obj(plane->state->fb, i);
+		malidp_hw_write(mp->hwdev, lower_32_bits(obj->paddr), ptr);
+		malidp_hw_write(mp->hwdev, upper_32_bits(obj->paddr), ptr + 4);
+		malidp_hw_write(mp->hwdev, plane->state->fb->pitches[i],
+				mp->layer->base + MALIDP_LAYER_STRIDE);
+	}
+
+	malidp_hw_write(mp->hwdev, LAYER_H_VAL(src_w) | LAYER_V_VAL(src_h),
+			mp->layer->base + MALIDP_LAYER_SIZE);
+
+	malidp_hw_write(mp->hwdev, LAYER_H_VAL(dest_w) | LAYER_V_VAL(dest_h),
+			mp->layer->base + MALIDP_LAYER_COMP_SIZE);
+
+	malidp_hw_write(mp->hwdev, LAYER_H_VAL(plane->state->crtc_x) |
+			LAYER_V_VAL(plane->state->crtc_y),
+			mp->layer->base + MALIDP_LAYER_OFFSET);
+
+	/* first clear the rotation bits in the register */
+	malidp_hw_clearbits(mp->hwdev, LAYER_ROT_MASK,
+			    mp->layer->base + MALIDP_LAYER_CONTROL);
+
+	/* setup the rotation and axis flip bits */
+	if (plane->state->rotation & DRM_ROTATE_MASK)
+		val = ilog2(plane->state->rotation & DRM_ROTATE_MASK) << LAYER_ROT_OFFSET;
+	if (plane->state->rotation & BIT(DRM_REFLECT_X))
+		val |= LAYER_V_FLIP;
+	if (plane->state->rotation & BIT(DRM_REFLECT_Y))
+		val |= LAYER_H_FLIP;
+
+	/* set the 'enable layer' bit */
+	val |= LAYER_ENABLE;
+
+	malidp_hw_setbits(mp->hwdev, val,
+			  mp->layer->base + MALIDP_LAYER_CONTROL);
+}
+
+static void malidp_de_plane_disable(struct drm_plane *plane,
+				    struct drm_plane_state *state)
+{
+	struct malidp_plane *mp = to_malidp_plane(plane);
+
+	malidp_hw_clearbits(mp->hwdev, LAYER_ENABLE,
+			    mp->layer->base + MALIDP_LAYER_CONTROL);
+}
+
+static const struct drm_plane_helper_funcs malidp_de_plane_helper_funcs = {
+	.atomic_check = malidp_de_plane_check,
+	.atomic_update = malidp_de_plane_update,
+	.atomic_disable = malidp_de_plane_disable,
+};
+
+int malidp_de_planes_init(struct drm_device *drm)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	const struct malidp_hw_regmap *map = &malidp->dev->map;
+	struct malidp_plane *plane = NULL;
+	enum drm_plane_type plane_type;
+	unsigned long crtcs = 1 << drm->mode_config.num_crtc;
+	u32 *formats;
+	int ret, i, j, n;
+
+	formats = kcalloc(map->n_input_formats, sizeof(*formats), GFP_KERNEL);
+	if (!formats) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	for (i = 0; i < map->n_layers; i++) {
+		u8 id = map->layers[i].id;
+
+		plane = kzalloc(sizeof(*plane), GFP_KERNEL);
+		if (!plane) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+
+		/* build the list of DRM supported formats based on the map */
+		for (n = 0, j = 0;  j < map->n_input_formats; j++) {
+			if ((map->input_formats[j].layer & id) == id)
+				formats[n++] = map->input_formats[j].format;
+		}
+
+		plane_type = (i == 0) ? DRM_PLANE_TYPE_PRIMARY :
+					DRM_PLANE_TYPE_OVERLAY;
+		ret = drm_universal_plane_init(drm, &plane->base, crtcs,
+					       &malidp_de_plane_funcs, formats,
+					       n, plane_type, NULL);
+		if (ret < 0)
+			goto cleanup;
+
+		if (!drm->mode_config.rotation_property) {
+			unsigned long flags = BIT(DRM_ROTATE_0) |
+					      BIT(DRM_ROTATE_90) |
+					      BIT(DRM_ROTATE_180) |
+					      BIT(DRM_ROTATE_270) |
+					      BIT(DRM_REFLECT_X) |
+					      BIT(DRM_REFLECT_Y);
+			drm->mode_config.rotation_property =
+				drm_mode_create_rotation_property(drm, flags);
+		}
+		/* SMART layer can't be rotated */
+		if (drm->mode_config.rotation_property && (id != DE_SMART))
+			drm_object_attach_property(&plane->base.base,
+						   drm->mode_config.rotation_property,
+						   BIT(DRM_ROTATE_0));
+
+		drm_plane_helper_add(&plane->base,
+				     &malidp_de_plane_helper_funcs);
+		plane->hwdev = malidp->dev;
+		plane->layer = &map->layers[i];
+	}
+
+	kfree(formats);
+
+	return 0;
+
+cleanup:
+	malidp_de_planes_destroy(drm);
+	kfree(formats);
+
+	return ret;
+}
+
+void malidp_de_planes_destroy(struct drm_device *drm)
+{
+	struct drm_plane *p, *pt;
+
+	list_for_each_entry_safe(p, pt, &drm->mode_config.plane_list, head) {
+		drm_plane_cleanup(p);
+		kfree(p);
+	}
+}
diff --git a/drivers/gpu/drm/arm/malidp_regs.h b/drivers/gpu/drm/arm/malidp_regs.h
new file mode 100644
index 000000000000..73fecb38f955
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_regs.h
@@ -0,0 +1,172 @@
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Liviu Dudau <Liviu.Dudau@arm.com>
+ *
+ * This program is free software and is provided to you under the terms of the
+ * GNU General Public License version 2 as published by the Free Software
+ * Foundation, and any use by you of this program is subject to the terms
+ * of such GNU licence.
+ *
+ * ARM Mali DP500/DP550/DP650 registers definition.
+ */
+
+#ifndef __MALIDP_REGS_H__
+#define __MALIDP_REGS_H__
+
+/*
+ * abbreviations used:
+ *    - DC - display core (general settings)
+ *    - DE - display engine
+ *    - SE - scaling engine
+ */
+
+/* interrupt bit masks */
+#define MALIDP_DE_IRQ_UNDERRUN			(1 << 0)
+
+#define MALIDP500_DE_IRQ_AXI_ERR		(1 << 4)
+#define MALIDP500_DE_IRQ_VSYNC			(1 << 5)
+#define MALIDP500_DE_IRQ_PROG_LINE		(1 << 6)
+#define MALIDP500_DE_IRQ_SATURATION		(1 << 7)
+#define MALIDP500_DE_IRQ_CONF_VALID		(1 << 8)
+#define MALIDP500_DE_IRQ_CONF_MODE		(1 << 11)
+#define MALIDP500_DE_IRQ_CONF_ACTIVE		(1 << 17)
+#define MALIDP500_DE_IRQ_PM_ACTIVE		(1 << 18)
+#define MALIDP500_DE_IRQ_TESTMODE_ACTIVE	(1 << 19)
+#define MALIDP500_DE_IRQ_FORCE_BLNK_ACTIVE	(1 << 24)
+#define MALIDP500_DE_IRQ_AXI_BUSY		(1 << 28)
+#define MALIDP500_DE_IRQ_GLOBAL			(1 << 31)
+#define MALIDP500_SE_IRQ_CONF_MODE		(1 << 0)
+#define MALIDP500_SE_IRQ_CONF_VALID		(1 << 4)
+#define MALIDP500_SE_IRQ_INIT_BUSY		(1 << 5)
+#define MALIDP500_SE_IRQ_AXI_ERROR		(1 << 8)
+#define MALIDP500_SE_IRQ_OVERRUN		(1 << 9)
+#define MALIDP500_SE_IRQ_PROG_LINE1		(1 << 12)
+#define MALIDP500_SE_IRQ_PROG_LINE2		(1 << 13)
+#define MALIDP500_SE_IRQ_CONF_ACTIVE		(1 << 17)
+#define MALIDP500_SE_IRQ_PM_ACTIVE		(1 << 18)
+#define MALIDP500_SE_IRQ_AXI_BUSY		(1 << 28)
+#define MALIDP500_SE_IRQ_GLOBAL			(1 << 31)
+
+#define MALIDP550_DE_IRQ_SATURATION		(1 << 8)
+#define MALIDP550_DE_IRQ_VSYNC			(1 << 12)
+#define MALIDP550_DE_IRQ_PROG_LINE		(1 << 13)
+#define MALIDP550_DE_IRQ_AXI_ERR		(1 << 16)
+#define MALIDP550_SE_IRQ_EOW			(1 << 0)
+#define MALIDP550_SE_IRQ_AXI_ERR		(1 << 16)
+#define MALIDP550_DC_IRQ_CONF_VALID		(1 << 0)
+#define MALIDP550_DC_IRQ_CONF_MODE		(1 << 4)
+#define MALIDP550_DC_IRQ_CONF_ACTIVE		(1 << 16)
+#define MALIDP550_DC_IRQ_DE			(1 << 20)
+#define MALIDP550_DC_IRQ_SE			(1 << 24)
+
+#define MALIDP650_DE_IRQ_DRIFT			(1 << 4)
+
+/* bit masks that are common between products */
+#define   MALIDP_CFG_VALID		(1 << 0)
+#define   MALIDP_DISP_FUNC_ILACED	(1 << 8)
+
+/* register offsets for IRQ management */
+#define MALIDP_REG_STATUS		0x00000
+#define MALIDP_REG_SETIRQ		0x00004
+#define MALIDP_REG_MASKIRQ		0x00008
+#define MALIDP_REG_CLEARIRQ		0x0000c
+
+/* register offsets */
+#define MALIDP_DE_CORE_ID		0x00018
+#define MALIDP_DE_DISPLAY_FUNC		0x00020
+
+/* these offsets are relative to MALIDP5x0_TIMINGS_BASE */
+#define MALIDP_DE_H_TIMINGS		0x0
+#define MALIDP_DE_V_TIMINGS		0x4
+#define MALIDP_DE_SYNC_WIDTH		0x8
+#define MALIDP_DE_HV_ACTIVE		0xc
+
+/* macros to set values into registers */
+#define MALIDP_DE_H_FRONTPORCH(x)	(((x) & 0xfff) << 0)
+#define MALIDP_DE_H_BACKPORCH(x)	(((x) & 0x3ff) << 16)
+#define MALIDP500_DE_V_FRONTPORCH(x)	(((x) & 0xff) << 0)
+#define MALIDP550_DE_V_FRONTPORCH(x)	(((x) & 0xfff) << 0)
+#define MALIDP_DE_V_BACKPORCH(x)	(((x) & 0xff) << 16)
+#define MALIDP_DE_H_SYNCWIDTH(x)	(((x) & 0x3ff) << 0)
+#define MALIDP_DE_V_SYNCWIDTH(x)	(((x) & 0xff) << 16)
+#define MALIDP_DE_H_ACTIVE(x)		(((x) & 0x1fff) << 0)
+#define MALIDP_DE_V_ACTIVE(x)		(((x) & 0x1fff) << 16)
+
+/* register offsets and bits specific to DP500 */
+#define MALIDP500_DC_BASE		0x00000
+#define MALIDP500_DC_CONTROL		0x0000c
+#define   MALIDP500_DC_CONFIG_REQ	(1 << 17)
+#define   MALIDP500_HSYNCPOL		(1 << 20)
+#define   MALIDP500_VSYNCPOL		(1 << 21)
+#define   MALIDP500_DC_CLEAR_MASK	0x300fff
+#define MALIDP500_DE_LINE_COUNTER	0x00010
+#define MALIDP500_DE_AXI_CONTROL	0x00014
+#define MALIDP500_DE_SECURE_CTRL	0x0001c
+#define MALIDP500_DE_CHROMA_KEY		0x00024
+#define MALIDP500_TIMINGS_BASE		0x00028
+
+#define MALIDP500_CONFIG_3D		0x00038
+#define MALIDP500_BGND_COLOR		0x0003c
+#define MALIDP500_OUTPUT_DEPTH		0x00044
+#define MALIDP500_YUV_RGB_COEF		0x00048
+#define MALIDP500_COLOR_ADJ_COEF	0x00078
+#define MALIDP500_COEF_TABLE_ADDR	0x000a8
+#define MALIDP500_COEF_TABLE_DATA	0x000ac
+#define MALIDP500_DE_LV_BASE		0x00100
+#define MALIDP500_DE_LV_PTR_BASE	0x00124
+#define MALIDP500_DE_LG1_BASE		0x00200
+#define MALIDP500_DE_LG1_PTR_BASE	0x0021c
+#define MALIDP500_DE_LG2_BASE		0x00300
+#define MALIDP500_DE_LG2_PTR_BASE	0x0031c
+#define MALIDP500_SE_BASE		0x00c00
+#define MALIDP500_SE_PTR_BASE		0x00e0c
+#define MALIDP500_DC_IRQ_BASE		0x00f00
+#define MALIDP500_CONFIG_VALID		0x00f00
+#define MALIDP500_CONFIG_ID		0x00fd4
+
+/* register offsets and bits specific to DP550/DP650 */
+#define MALIDP550_DE_CONTROL		0x00010
+#define MALIDP550_DE_LINE_COUNTER	0x00014
+#define MALIDP550_DE_AXI_CONTROL	0x00018
+#define MALIDP550_DE_QOS		0x0001c
+#define MALIDP550_TIMINGS_BASE		0x00030
+#define MALIDP550_HSYNCPOL		(1 << 12)
+#define MALIDP550_VSYNCPOL		(1 << 28)
+
+#define MALIDP550_DE_DISP_SIDEBAND	0x00040
+#define MALIDP550_DE_BGND_COLOR		0x00044
+#define MALIDP550_DE_OUTPUT_DEPTH	0x0004c
+#define MALIDP550_DE_COLOR_COEF		0x00050
+#define MALIDP550_DE_COEF_TABLE_ADDR	0x00080
+#define MALIDP550_DE_COEF_TABLE_DATA	0x00084
+#define MALIDP550_DE_LV1_BASE		0x00100
+#define MALIDP550_DE_LV1_PTR_BASE	0x00124
+#define MALIDP550_DE_LV2_BASE		0x00200
+#define MALIDP550_DE_LV2_PTR_BASE	0x00224
+#define MALIDP550_DE_LG_BASE		0x00300
+#define MALIDP550_DE_LG_PTR_BASE	0x0031c
+#define MALIDP550_DE_LS_BASE		0x00400
+#define MALIDP550_DE_LS_PTR_BASE	0x0042c
+#define MALIDP550_DE_PERF_BASE		0x00500
+#define MALIDP550_SE_BASE		0x08000
+#define MALIDP550_DC_BASE		0x0c000
+#define MALIDP550_DC_CONTROL		0x0c010
+#define   MALIDP550_DC_CONFIG_REQ	(1 << 16)
+#define MALIDP550_CONFIG_VALID		0x0c014
+#define MALIDP550_CONFIG_ID		0x0ffd4
+
+/*
+ * Starting with DP550 the register map blocks has been standardised to the
+ * following layout:
+ *
+ *   Offset            Block registers
+ *  0x00000            Display Engine
+ *  0x08000            Scaling Engine
+ *  0x0c000            Display Core
+ *  0x10000            Secure control
+ *
+ * The old DP500 IP mixes some DC with the DE registers, hence the need
+ * for a mapping structure.
+ */
+
+#endif /* __MALIDP_REGS_H__ */
diff --git a/drivers/gpu/drm/armada/Kconfig b/drivers/gpu/drm/armada/Kconfig
index eb773e9af313..15f3ecfb16f1 100644
--- a/drivers/gpu/drm/armada/Kconfig
+++ b/drivers/gpu/drm/armada/Kconfig
@@ -1,11 +1,7 @@
 config DRM_ARMADA
 	tristate "DRM support for Marvell Armada SoCs"
 	depends on DRM && HAVE_CLK && ARM
-	select FB_CFB_FILLRECT
-	select FB_CFB_COPYAREA
-	select FB_CFB_IMAGEBLIT
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	help
 	  Support the "LCD" controllers found on the Marvell Armada 510
 	  devices.  There are two controllers on the device, each controller
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 3130aa8bcdd0..2f58e9e2a59c 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -199,7 +199,7 @@ static void armada_drm_plane_work_run(struct armada_crtc *dcrtc,
 	/* Handle any pending frame work. */
 	if (work) {
 		work->fn(dcrtc, plane, work);
-		drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
+		drm_crtc_vblank_put(&dcrtc->crtc);
 	}
 
 	wake_up(&plane->frame_wait);
@@ -210,7 +210,7 @@ int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
 {
 	int ret;
 
-	ret = drm_vblank_get(dcrtc->crtc.dev, dcrtc->num);
+	ret = drm_crtc_vblank_get(&dcrtc->crtc);
 	if (ret) {
 		DRM_ERROR("failed to acquire vblank counter\n");
 		return ret;
@@ -218,7 +218,7 @@ int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
 
 	ret = cmpxchg(&plane->work, NULL, work) ? -EBUSY : 0;
 	if (ret)
-		drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
+		drm_crtc_vblank_put(&dcrtc->crtc);
 
 	return ret;
 }
@@ -234,7 +234,7 @@ struct armada_plane_work *armada_drm_plane_work_cancel(
 	struct armada_plane_work *work = xchg(&plane->work, NULL);
 
 	if (work)
-		drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
+		drm_crtc_vblank_put(&dcrtc->crtc);
 
 	return work;
 }
@@ -260,7 +260,7 @@ static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc,
 
 	if (fwork->event) {
 		spin_lock_irqsave(&dev->event_lock, flags);
-		drm_send_vblank_event(dev, dcrtc->num, fwork->event);
+		drm_crtc_send_vblank_event(&dcrtc->crtc, fwork->event);
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 	}
 
@@ -410,7 +410,7 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 		DRM_ERROR("graphics underflow on crtc %u\n", dcrtc->num);
 
 	if (stat & VSYNC_IRQ)
-		drm_handle_vblank(dcrtc->crtc.dev, dcrtc->num);
+		drm_crtc_handle_vblank(&dcrtc->crtc);
 
 	spin_lock(&dcrtc->irq_lock);
 	ovl_plane = dcrtc->plane;
@@ -592,9 +592,9 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 
 	if (interlaced ^ dcrtc->interlaced) {
 		if (adj->flags & DRM_MODE_FLAG_INTERLACE)
-			drm_vblank_get(dcrtc->crtc.dev, dcrtc->num);
+			drm_crtc_vblank_get(&dcrtc->crtc);
 		else
-			drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
+			drm_crtc_vblank_put(&dcrtc->crtc);
 		dcrtc->interlaced = interlaced;
 	}
 
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index 439824a61aa5..f5ebdd681445 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -189,7 +189,6 @@ static struct drm_driver armada_drm_driver = {
 	.load			= armada_drm_load,
 	.lastclose		= armada_drm_lastclose,
 	.unload			= armada_drm_unload,
-	.set_busid		= drm_platform_set_busid,
 	.get_vblank_counter	= drm_vblank_no_hw_counter,
 	.enable_vblank		= armada_drm_enable_vblank,
 	.disable_vblank		= armada_drm_disable_vblank,
@@ -197,7 +196,7 @@ static struct drm_driver armada_drm_driver = {
 	.debugfs_init		= armada_drm_debugfs_init,
 	.debugfs_cleanup	= armada_drm_debugfs_cleanup,
 #endif
-	.gem_free_object	= armada_gem_free_object,
+	.gem_free_object_unlocked = armada_gem_free_object,
 	.prime_handle_to_fd	= drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle	= drm_gem_prime_fd_to_handle,
 	.gem_prime_export	= armada_gem_prime_export,
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index 148e8a42b2c6..1ee707ef6b8d 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -121,6 +121,7 @@ armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	int ret;
 
 	ret = drm_plane_helper_check_update(plane, crtc, fb, &src, &dest, &clip,
+					    BIT(DRM_ROTATE_0),
 					    0, INT_MAX, true, false, &visible);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/ast/Kconfig b/drivers/gpu/drm/ast/Kconfig
index 8a784c460c89..15f6ce7acb2a 100644
--- a/drivers/gpu/drm/ast/Kconfig
+++ b/drivers/gpu/drm/ast/Kconfig
@@ -2,11 +2,7 @@ config DRM_AST
 	tristate "AST server chips"
 	depends on DRM && PCI
 	select DRM_TTM
-	select FB_SYS_COPYAREA
-	select FB_SYS_FILLRECT
-	select FB_SYS_IMAGEBLIT
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_TTM
 	help
 	 Say yes for experimental AST GPU driver. Do not enable
diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index fcd9c0714836..f54afd2113a9 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -209,7 +209,7 @@ static struct drm_driver driver = {
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
 
-	.gem_free_object = ast_gem_free_object,
+	.gem_free_object_unlocked = ast_gem_free_object,
 	.dumb_create = ast_dumb_create,
 	.dumb_map_offset = ast_dumb_mmap_offset,
 	.dumb_destroy = drm_gem_dumb_destroy,
diff --git a/drivers/gpu/drm/ast/ast_fb.c b/drivers/gpu/drm/ast/ast_fb.c
index 5320f8c57884..c017a9330a18 100644
--- a/drivers/gpu/drm/ast/ast_fb.c
+++ b/drivers/gpu/drm/ast/ast_fb.c
@@ -167,12 +167,9 @@ static int astfb_create_object(struct ast_fbdev *afbdev,
 			       struct drm_gem_object **gobj_p)
 {
 	struct drm_device *dev = afbdev->helper.dev;
-	u32 bpp, depth;
 	u32 size;
 	struct drm_gem_object *gobj;
-
 	int ret = 0;
-	drm_fb_get_bpp_depth(mode_cmd->pixel_format, &depth, &bpp);
 
 	size = mode_cmd->pitches[0] * mode_cmd->height;
 	ret = ast_gem_create(dev, size, true, &gobj);
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index 7bc3aa6dda8c..904beaa932d0 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -295,9 +295,8 @@ static int ast_get_dram_info(struct drm_device *dev)
 static void ast_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct ast_framebuffer *ast_fb = to_ast_framebuffer(fb);
-	if (ast_fb->obj)
-		drm_gem_object_unreference_unlocked(ast_fb->obj);
 
+	drm_gem_object_unreference_unlocked(ast_fb->obj);
 	drm_framebuffer_cleanup(fb);
 	kfree(fb);
 }
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index c337922606e3..5957c3e659fe 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -624,19 +624,21 @@ static void ast_crtc_reset(struct drm_crtc *crtc)
 
 }
 
-static void ast_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-				 u16 *blue, uint32_t start, uint32_t size)
+static int ast_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
+			      u16 *blue, uint32_t size)
 {
 	struct ast_crtc *ast_crtc = to_ast_crtc(crtc);
-	int end = (start + size > 256) ? 256 : start + size, i;
+	int i;
 
 	/* userspace palettes are always correct as is */
-	for (i = start; i < end; i++) {
+	for (i = 0; i < size; i++) {
 		ast_crtc->lut_r[i] = red[i] >> 8;
 		ast_crtc->lut_g[i] = green[i] >> 8;
 		ast_crtc->lut_b[i] = blue[i] >> 8;
 	}
 	ast_crtc_load_lut(crtc);
+
+	return 0;
 }
 
 
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 59f2f93b6f84..b29a41218fc9 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -186,17 +186,6 @@ static void ast_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *
 {
 }
 
-static int ast_bo_move(struct ttm_buffer_object *bo,
-		       bool evict, bool interruptible,
-		       bool no_wait_gpu,
-		       struct ttm_mem_reg *new_mem)
-{
-	int r;
-	r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
-	return r;
-}
-
-
 static void ast_ttm_backend_destroy(struct ttm_tt *tt)
 {
 	ttm_tt_fini(tt);
@@ -241,7 +230,7 @@ struct ttm_bo_driver ast_bo_driver = {
 	.ttm_tt_unpopulate = ast_ttm_tt_unpopulate,
 	.init_mem_type = ast_bo_init_mem_type,
 	.evict_flags = ast_bo_evict_flags,
-	.move = ast_bo_move,
+	.move = NULL,
 	.verify_access = ast_bo_verify_access,
 	.io_mem_reserve = &ast_ttm_io_mem_reserve,
 	.io_mem_free = &ast_ttm_io_mem_free,
diff --git a/drivers/gpu/drm/atmel-hlcdc/Kconfig b/drivers/gpu/drm/atmel-hlcdc/Kconfig
index 99b4f0698a30..32bcc4bad06a 100644
--- a/drivers/gpu/drm/atmel-hlcdc/Kconfig
+++ b/drivers/gpu/drm/atmel-hlcdc/Kconfig
@@ -3,7 +3,6 @@ config DRM_ATMEL_HLCDC
 	depends on DRM && OF && COMMON_CLK && MFD_ATMEL_HLCDC && ARM
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_PANEL
 	help
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index bd12231ab0cd..a978381ef95b 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -374,8 +374,8 @@ static void atmel_hlcdc_crtc_finish_page_flip(struct atmel_hlcdc_crtc *crtc)
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 	if (crtc->event) {
-		drm_send_vblank_event(dev, crtc->id, crtc->event);
-		drm_vblank_put(dev, crtc->id);
+		drm_crtc_send_vblank_event(&crtc->base, crtc->event);
+		drm_crtc_vblank_put(&crtc->base);
 		crtc->event = NULL;
 	}
 	spin_unlock_irqrestore(&dev->event_lock, flags);
@@ -383,7 +383,7 @@ static void atmel_hlcdc_crtc_finish_page_flip(struct atmel_hlcdc_crtc *crtc)
 
 void atmel_hlcdc_crtc_irq(struct drm_crtc *c)
 {
-	drm_handle_vblank(c->dev, 0);
+	drm_crtc_handle_vblank(c);
 	atmel_hlcdc_crtc_finish_page_flip(drm_crtc_to_atmel_hlcdc_crtc(c));
 }
 
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
index 8ded7645747e..d4a3d61b7b06 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
@@ -519,7 +519,7 @@ static int atmel_hlcdc_dc_atomic_commit(struct drm_device *dev,
 	}
 
 	/* Swap the state, this is the point of no return. */
-	drm_atomic_helper_swap_state(dev, state);
+	drm_atomic_helper_swap_state(state, true);
 
 	if (async)
 		queue_work(dc->wq, &commit->work);
@@ -691,13 +691,6 @@ static void atmel_hlcdc_dc_unload(struct drm_device *dev)
 	destroy_workqueue(dc->wq);
 }
 
-static void atmel_hlcdc_dc_connector_unplug_all(struct drm_device *dev)
-{
-	mutex_lock(&dev->mode_config.mutex);
-	drm_connector_unregister_all(dev);
-	mutex_unlock(&dev->mode_config.mutex);
-}
-
 static void atmel_hlcdc_dc_lastclose(struct drm_device *dev)
 {
 	struct atmel_hlcdc_dc *dc = dev->dev_private;
@@ -776,7 +769,7 @@ static struct drm_driver atmel_hlcdc_dc_driver = {
 	.get_vblank_counter = drm_vblank_no_hw_counter,
 	.enable_vblank = atmel_hlcdc_dc_enable_vblank,
 	.disable_vblank = atmel_hlcdc_dc_disable_vblank,
-	.gem_free_object = drm_gem_cma_free_object,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops = &drm_gem_cma_vm_ops,
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
@@ -815,15 +808,8 @@ static int atmel_hlcdc_dc_drm_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_unload;
 
-	ret = drm_connector_register_all(ddev);
-	if (ret)
-		goto err_unregister;
-
 	return 0;
 
-err_unregister:
-	drm_dev_unregister(ddev);
-
 err_unload:
 	atmel_hlcdc_dc_unload(ddev);
 
@@ -837,7 +823,6 @@ static int atmel_hlcdc_dc_drm_remove(struct platform_device *pdev)
 {
 	struct drm_device *ddev = platform_get_drvdata(pdev);
 
-	atmel_hlcdc_dc_connector_unplug_all(ddev);
 	drm_dev_unregister(ddev);
 	atmel_hlcdc_dc_unload(ddev);
 	drm_dev_unref(ddev);
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
index 3d34fc4ca826..6119b5085501 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
@@ -113,21 +113,9 @@ static int atmel_hlcdc_rgb_mode_valid(struct drm_connector *connector,
 	return atmel_hlcdc_dc_mode_valid(rgb->dc, mode);
 }
 
-
-
-static struct drm_encoder *
-atmel_hlcdc_rgb_best_encoder(struct drm_connector *connector)
-{
-	struct atmel_hlcdc_rgb_output *rgb =
-			drm_connector_to_atmel_hlcdc_rgb_output(connector);
-
-	return &rgb->encoder;
-}
-
 static const struct drm_connector_helper_funcs atmel_hlcdc_panel_connector_helper_funcs = {
 	.get_modes = atmel_hlcdc_panel_get_modes,
 	.mode_valid = atmel_hlcdc_rgb_mode_valid,
-	.best_encoder = atmel_hlcdc_rgb_best_encoder,
 };
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/bochs/Kconfig b/drivers/gpu/drm/bochs/Kconfig
index 5f8b0c2b9a44..f739763f47ce 100644
--- a/drivers/gpu/drm/bochs/Kconfig
+++ b/drivers/gpu/drm/bochs/Kconfig
@@ -2,10 +2,6 @@ config DRM_BOCHS
 	tristate "DRM Support for bochs dispi vga interface (qemu stdvga)"
 	depends on DRM && PCI
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
-	select FB_SYS_FILLRECT
-	select FB_SYS_COPYAREA
-	select FB_SYS_IMAGEBLIT
 	select DRM_TTM
 	help
 	  Choose this option for qemu.
diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c
index b332b4d3b0e2..abace82de6ea 100644
--- a/drivers/gpu/drm/bochs/bochs_drv.c
+++ b/drivers/gpu/drm/bochs/bochs_drv.c
@@ -89,7 +89,7 @@ static struct drm_driver bochs_driver = {
 	.date			= "20130925",
 	.major			= 1,
 	.minor			= 0,
-	.gem_free_object        = bochs_gem_free_object,
+	.gem_free_object_unlocked = bochs_gem_free_object,
 	.dumb_create            = bochs_dumb_create,
 	.dumb_map_offset        = bochs_dumb_mmap_offset,
 	.dumb_destroy           = drm_gem_dumb_destroy,
diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
index 6cf912c45e48..5c5638a777a1 100644
--- a/drivers/gpu/drm/bochs/bochs_mm.c
+++ b/drivers/gpu/drm/bochs/bochs_mm.c
@@ -165,15 +165,6 @@ static void bochs_ttm_io_mem_free(struct ttm_bo_device *bdev,
 {
 }
 
-static int bochs_bo_move(struct ttm_buffer_object *bo,
-			 bool evict, bool interruptible,
-			 bool no_wait_gpu,
-			 struct ttm_mem_reg *new_mem)
-{
-	return ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
-}
-
-
 static void bochs_ttm_backend_destroy(struct ttm_tt *tt)
 {
 	ttm_tt_fini(tt);
@@ -208,7 +199,7 @@ struct ttm_bo_driver bochs_bo_driver = {
 	.ttm_tt_unpopulate = ttm_pool_unpopulate,
 	.init_mem_type = bochs_bo_init_mem_type,
 	.evict_flags = bochs_bo_evict_flags,
-	.move = bochs_bo_move,
+	.move = NULL,
 	.verify_access = bochs_bo_verify_access,
 	.io_mem_reserve = &bochs_ttm_io_mem_reserve,
 	.io_mem_free = &bochs_ttm_io_mem_free,
@@ -474,8 +465,8 @@ int bochs_dumb_mmap_offset(struct drm_file *file, struct drm_device *dev,
 static void bochs_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct bochs_framebuffer *bochs_fb = to_bochs_framebuffer(fb);
-	if (bochs_fb->obj)
-		drm_gem_object_unreference_unlocked(bochs_fb->obj);
+
+	drm_gem_object_unreference_unlocked(bochs_fb->obj);
 	drm_framebuffer_cleanup(fb);
 	kfree(fb);
 }
diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index 8f7423f18da5..b590e678052d 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -50,6 +50,25 @@ config DRM_PARADE_PS8622
 	---help---
 	  Parade eDP-LVDS bridge chip driver.
 
+config DRM_SII902X
+	tristate "Silicon Image sii902x RGB/HDMI bridge"
+	depends on OF
+	select DRM_KMS_HELPER
+	select REGMAP_I2C
+	---help---
+	  Silicon Image sii902x bridge chip driver.
+
+config DRM_TOSHIBA_TC358767
+	tristate "Toshiba TC358767 eDP bridge"
+	depends on OF
+	select DRM_KMS_HELPER
+	select REGMAP_I2C
+	select DRM_PANEL
+	---help---
+	  Toshiba TC358767 eDP bridge chip driver.
+
 source "drivers/gpu/drm/bridge/analogix/Kconfig"
 
+source "drivers/gpu/drm/bridge/adv7511/Kconfig"
+
 endmenu
diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile
index 96b13b30e6ab..efdb07e878f5 100644
--- a/drivers/gpu/drm/bridge/Makefile
+++ b/drivers/gpu/drm/bridge/Makefile
@@ -5,4 +5,7 @@ obj-$(CONFIG_DRM_DW_HDMI) += dw-hdmi.o
 obj-$(CONFIG_DRM_DW_HDMI_AHB_AUDIO) += dw-hdmi-ahb-audio.o
 obj-$(CONFIG_DRM_NXP_PTN3460) += nxp-ptn3460.o
 obj-$(CONFIG_DRM_PARADE_PS8622) += parade-ps8622.o
+obj-$(CONFIG_DRM_SII902X) += sii902x.o
+obj-$(CONFIG_DRM_TOSHIBA_TC358767) += tc358767.o
 obj-$(CONFIG_DRM_ANALOGIX_DP) += analogix/
+obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511/
diff --git a/drivers/gpu/drm/bridge/adv7511/Kconfig b/drivers/gpu/drm/bridge/adv7511/Kconfig
new file mode 100644
index 000000000000..d2b0499ab7d7
--- /dev/null
+++ b/drivers/gpu/drm/bridge/adv7511/Kconfig
@@ -0,0 +1,15 @@
+config DRM_I2C_ADV7511
+	tristate "AV7511 encoder"
+	depends on OF
+	select DRM_KMS_HELPER
+	select REGMAP_I2C
+	help
+	  Support for the Analog Device ADV7511(W) and ADV7513 HDMI encoders.
+
+config DRM_I2C_ADV7533
+	bool "ADV7533 encoder"
+	depends on DRM_I2C_ADV7511
+	select DRM_MIPI_DSI
+	default y
+	help
+	  Support for the Analog Devices ADV7533 DSI to HDMI encoder.
diff --git a/drivers/gpu/drm/bridge/adv7511/Makefile b/drivers/gpu/drm/bridge/adv7511/Makefile
new file mode 100644
index 000000000000..9019327fff4c
--- /dev/null
+++ b/drivers/gpu/drm/bridge/adv7511/Makefile
@@ -0,0 +1,3 @@
+adv7511-y := adv7511_drv.o
+adv7511-$(CONFIG_DRM_I2C_ADV7533) += adv7533.o
+obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511.o
diff --git a/drivers/gpu/drm/i2c/adv7511.h b/drivers/gpu/drm/bridge/adv7511/adv7511.h
index 38515b30cedf..161c923d6162 100644
--- a/drivers/gpu/drm/i2c/adv7511.h
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511.h
@@ -10,6 +10,11 @@
 #define __DRM_I2C_ADV7511_H__
 
 #include <linux/hdmi.h>
+#include <linux/i2c.h>
+#include <linux/regmap.h>
+
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_mipi_dsi.h>
 
 #define ADV7511_REG_CHIP_REVISION		0x00
 #define ADV7511_REG_N0				0x01
@@ -286,4 +291,102 @@ struct adv7511_video_config {
 	struct hdmi_avi_infoframe avi_infoframe;
 };
 
+enum adv7511_type {
+	ADV7511,
+	ADV7533,
+};
+
+struct adv7511 {
+	struct i2c_client *i2c_main;
+	struct i2c_client *i2c_edid;
+	struct i2c_client *i2c_cec;
+
+	struct regmap *regmap;
+	struct regmap *regmap_cec;
+	enum drm_connector_status status;
+	bool powered;
+
+	struct drm_display_mode curr_mode;
+
+	unsigned int f_tmds;
+
+	unsigned int current_edid_segment;
+	uint8_t edid_buf[256];
+	bool edid_read;
+
+	wait_queue_head_t wq;
+	struct drm_bridge bridge;
+	struct drm_connector connector;
+
+	bool embedded_sync;
+	enum adv7511_sync_polarity vsync_polarity;
+	enum adv7511_sync_polarity hsync_polarity;
+	bool rgb;
+
+	struct edid *edid;
+
+	struct gpio_desc *gpio_pd;
+
+	/* ADV7533 DSI RX related params */
+	struct device_node *host_node;
+	struct mipi_dsi_device *dsi;
+	u8 num_dsi_lanes;
+	bool use_timing_gen;
+
+	enum adv7511_type type;
+};
+
+#ifdef CONFIG_DRM_I2C_ADV7533
+void adv7533_dsi_power_on(struct adv7511 *adv);
+void adv7533_dsi_power_off(struct adv7511 *adv);
+void adv7533_mode_set(struct adv7511 *adv, struct drm_display_mode *mode);
+int adv7533_patch_registers(struct adv7511 *adv);
+void adv7533_uninit_cec(struct adv7511 *adv);
+int adv7533_init_cec(struct adv7511 *adv);
+int adv7533_attach_dsi(struct adv7511 *adv);
+void adv7533_detach_dsi(struct adv7511 *adv);
+int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv);
+#else
+static inline void adv7533_dsi_power_on(struct adv7511 *adv)
+{
+}
+
+static inline void adv7533_dsi_power_off(struct adv7511 *adv)
+{
+}
+
+static inline void adv7533_mode_set(struct adv7511 *adv,
+				    struct drm_display_mode *mode)
+{
+}
+
+static inline int adv7533_patch_registers(struct adv7511 *adv)
+{
+	return -ENODEV;
+}
+
+static inline void adv7533_uninit_cec(struct adv7511 *adv)
+{
+}
+
+static inline int adv7533_init_cec(struct adv7511 *adv)
+{
+	return -ENODEV;
+}
+
+static inline int adv7533_attach_dsi(struct adv7511 *adv)
+{
+	return -ENODEV;
+}
+
+static inline void adv7533_detach_dsi(struct adv7511 *adv)
+{
+}
+
+static inline int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv)
+{
+	return -ENODEV;
+}
+#endif
+
 #endif /* __DRM_I2C_ADV7511_H__ */
diff --git a/drivers/gpu/drm/i2c/adv7511.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index a02112ba1c3d..ec8fb2ed3275 100644
--- a/drivers/gpu/drm/i2c/adv7511.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -8,51 +8,17 @@
 
 #include <linux/device.h>
 #include <linux/gpio/consumer.h>
-#include <linux/i2c.h>
 #include <linux/module.h>
-#include <linux/regmap.h>
+#include <linux/of_device.h>
 #include <linux/slab.h>
 
 #include <drm/drmP.h>
-#include <drm/drm_crtc_helper.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_edid.h>
-#include <drm/drm_encoder_slave.h>
 
 #include "adv7511.h"
 
-struct adv7511 {
-	struct i2c_client *i2c_main;
-	struct i2c_client *i2c_edid;
-
-	struct regmap *regmap;
-	struct regmap *packet_memory_regmap;
-	enum drm_connector_status status;
-	bool powered;
-
-	unsigned int f_tmds;
-
-	unsigned int current_edid_segment;
-	uint8_t edid_buf[256];
-	bool edid_read;
-
-	wait_queue_head_t wq;
-	struct drm_encoder *encoder;
-
-	bool embedded_sync;
-	enum adv7511_sync_polarity vsync_polarity;
-	enum adv7511_sync_polarity hsync_polarity;
-	bool rgb;
-
-	struct edid *edid;
-
-	struct gpio_desc *gpio_pd;
-};
-
-static struct adv7511 *encoder_to_adv7511(struct drm_encoder *encoder)
-{
-	return to_encoder_slave(encoder)->slave_priv;
-}
-
 /* ADI recommended values for proper operation. */
 static const struct reg_sequence adv7511_fixed_registers[] = {
 	{ 0x98, 0x03 },
@@ -394,6 +360,9 @@ static void adv7511_power_on(struct adv7511 *adv7511)
 	 */
 	regcache_sync(adv7511->regmap);
 
+	if (adv7511->type == ADV7533)
+		adv7533_dsi_power_on(adv7511);
+
 	adv7511->powered = true;
 }
 
@@ -405,6 +374,9 @@ static void adv7511_power_off(struct adv7511 *adv7511)
 			   ADV7511_POWER_POWER_DOWN);
 	regcache_mark_dirty(adv7511->regmap);
 
+	if (adv7511->type == ADV7533)
+		adv7533_dsi_power_off(adv7511);
+
 	adv7511->powered = false;
 }
 
@@ -430,7 +402,7 @@ static bool adv7511_hpd(struct adv7511 *adv7511)
 	return false;
 }
 
-static int adv7511_irq_process(struct adv7511 *adv7511)
+static int adv7511_irq_process(struct adv7511 *adv7511, bool process_hpd)
 {
 	unsigned int irq0, irq1;
 	int ret;
@@ -446,8 +418,8 @@ static int adv7511_irq_process(struct adv7511 *adv7511)
 	regmap_write(adv7511->regmap, ADV7511_REG_INT(0), irq0);
 	regmap_write(adv7511->regmap, ADV7511_REG_INT(1), irq1);
 
-	if (irq0 & ADV7511_INT0_HPD && adv7511->encoder)
-		drm_helper_hpd_irq_event(adv7511->encoder->dev);
+	if (process_hpd && irq0 & ADV7511_INT0_HPD && adv7511->bridge.encoder)
+		drm_helper_hpd_irq_event(adv7511->connector.dev);
 
 	if (irq0 & ADV7511_INT0_EDID_READY || irq1 & ADV7511_INT1_DDC_ERROR) {
 		adv7511->edid_read = true;
@@ -464,7 +436,7 @@ static irqreturn_t adv7511_irq_handler(int irq, void *devid)
 	struct adv7511 *adv7511 = devid;
 	int ret;
 
-	ret = adv7511_irq_process(adv7511);
+	ret = adv7511_irq_process(adv7511, true);
 	return ret < 0 ? IRQ_NONE : IRQ_HANDLED;
 }
 
@@ -481,7 +453,7 @@ static int adv7511_wait_for_edid(struct adv7511 *adv7511, int timeout)
 				adv7511->edid_read, msecs_to_jiffies(timeout));
 	} else {
 		for (; timeout > 0; timeout -= 25) {
-			ret = adv7511_irq_process(adv7511);
+			ret = adv7511_irq_process(adv7511, false);
 			if (ret < 0)
 				break;
 
@@ -563,13 +535,12 @@ static int adv7511_get_edid_block(void *data, u8 *buf, unsigned int block,
 }
 
 /* -----------------------------------------------------------------------------
- * Encoder operations
+ * ADV75xx helpers
  */
 
-static int adv7511_get_modes(struct drm_encoder *encoder,
+static int adv7511_get_modes(struct adv7511 *adv7511,
 			     struct drm_connector *connector)
 {
-	struct adv7511 *adv7511 = encoder_to_adv7511(encoder);
 	struct edid *edid;
 	unsigned int count;
 
@@ -606,21 +577,9 @@ static int adv7511_get_modes(struct drm_encoder *encoder,
 	return count;
 }
 
-static void adv7511_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-	struct adv7511 *adv7511 = encoder_to_adv7511(encoder);
-
-	if (mode == DRM_MODE_DPMS_ON)
-		adv7511_power_on(adv7511);
-	else
-		adv7511_power_off(adv7511);
-}
-
 static enum drm_connector_status
-adv7511_encoder_detect(struct drm_encoder *encoder,
-		       struct drm_connector *connector)
+adv7511_detect(struct adv7511 *adv7511, struct drm_connector *connector)
 {
-	struct adv7511 *adv7511 = encoder_to_adv7511(encoder);
 	enum drm_connector_status status;
 	unsigned int val;
 	bool hpd;
@@ -644,7 +603,7 @@ adv7511_encoder_detect(struct drm_encoder *encoder,
 	if (status == connector_status_connected && hpd && adv7511->powered) {
 		regcache_mark_dirty(adv7511->regmap);
 		adv7511_power_on(adv7511);
-		adv7511_get_modes(encoder, connector);
+		adv7511_get_modes(adv7511, connector);
 		if (adv7511->status == connector_status_connected)
 			status = connector_status_disconnected;
 	} else {
@@ -658,8 +617,8 @@ adv7511_encoder_detect(struct drm_encoder *encoder,
 	return status;
 }
 
-static int adv7511_encoder_mode_valid(struct drm_encoder *encoder,
-				      struct drm_display_mode *mode)
+static int adv7511_mode_valid(struct adv7511 *adv7511,
+			      struct drm_display_mode *mode)
 {
 	if (mode->clock > 165000)
 		return MODE_CLOCK_HIGH;
@@ -667,11 +626,10 @@ static int adv7511_encoder_mode_valid(struct drm_encoder *encoder,
 	return MODE_OK;
 }
 
-static void adv7511_encoder_mode_set(struct drm_encoder *encoder,
-				     struct drm_display_mode *mode,
-				     struct drm_display_mode *adj_mode)
+static void adv7511_mode_set(struct adv7511 *adv7511,
+			     struct drm_display_mode *mode,
+			     struct drm_display_mode *adj_mode)
 {
-	struct adv7511 *adv7511 = encoder_to_adv7511(encoder);
 	unsigned int low_refresh_rate;
 	unsigned int hsync_polarity = 0;
 	unsigned int vsync_polarity = 0;
@@ -754,6 +712,11 @@ static void adv7511_encoder_mode_set(struct drm_encoder *encoder,
 	regmap_update_bits(adv7511->regmap, 0x17,
 		0x60, (vsync_polarity << 6) | (hsync_polarity << 5));
 
+	if (adv7511->type == ADV7533)
+		adv7533_mode_set(adv7511, adj_mode);
+
+	drm_mode_copy(&adv7511->curr_mode, adj_mode);
+
 	/*
 	 * TODO Test first order 4:2:2 to 4:4:4 up conversion method, which is
 	 * supposed to give better results.
@@ -762,12 +725,114 @@ static void adv7511_encoder_mode_set(struct drm_encoder *encoder,
 	adv7511->f_tmds = mode->clock;
 }
 
-static const struct drm_encoder_slave_funcs adv7511_encoder_funcs = {
-	.dpms = adv7511_encoder_dpms,
-	.mode_valid = adv7511_encoder_mode_valid,
-	.mode_set = adv7511_encoder_mode_set,
-	.detect = adv7511_encoder_detect,
-	.get_modes = adv7511_get_modes,
+/* Connector funcs */
+static struct adv7511 *connector_to_adv7511(struct drm_connector *connector)
+{
+	return container_of(connector, struct adv7511, connector);
+}
+
+static int adv7511_connector_get_modes(struct drm_connector *connector)
+{
+	struct adv7511 *adv = connector_to_adv7511(connector);
+
+	return adv7511_get_modes(adv, connector);
+}
+
+static enum drm_mode_status
+adv7511_connector_mode_valid(struct drm_connector *connector,
+			     struct drm_display_mode *mode)
+{
+	struct adv7511 *adv = connector_to_adv7511(connector);
+
+	return adv7511_mode_valid(adv, mode);
+}
+
+static struct drm_connector_helper_funcs adv7511_connector_helper_funcs = {
+	.get_modes = adv7511_connector_get_modes,
+	.mode_valid = adv7511_connector_mode_valid,
+};
+
+static enum drm_connector_status
+adv7511_connector_detect(struct drm_connector *connector, bool force)
+{
+	struct adv7511 *adv = connector_to_adv7511(connector);
+
+	return adv7511_detect(adv, connector);
+}
+
+static struct drm_connector_funcs adv7511_connector_funcs = {
+	.dpms = drm_atomic_helper_connector_dpms,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.detect = adv7511_connector_detect,
+	.destroy = drm_connector_cleanup,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+/* Bridge funcs */
+static struct adv7511 *bridge_to_adv7511(struct drm_bridge *bridge)
+{
+	return container_of(bridge, struct adv7511, bridge);
+}
+
+static void adv7511_bridge_enable(struct drm_bridge *bridge)
+{
+	struct adv7511 *adv = bridge_to_adv7511(bridge);
+
+	adv7511_power_on(adv);
+}
+
+static void adv7511_bridge_disable(struct drm_bridge *bridge)
+{
+	struct adv7511 *adv = bridge_to_adv7511(bridge);
+
+	adv7511_power_off(adv);
+}
+
+static void adv7511_bridge_mode_set(struct drm_bridge *bridge,
+				    struct drm_display_mode *mode,
+				    struct drm_display_mode *adj_mode)
+{
+	struct adv7511 *adv = bridge_to_adv7511(bridge);
+
+	adv7511_mode_set(adv, mode, adj_mode);
+}
+
+static int adv7511_bridge_attach(struct drm_bridge *bridge)
+{
+	struct adv7511 *adv = bridge_to_adv7511(bridge);
+	int ret;
+
+	if (!bridge->encoder) {
+		DRM_ERROR("Parent encoder object not found");
+		return -ENODEV;
+	}
+
+	adv->connector.polled = DRM_CONNECTOR_POLL_HPD;
+
+	ret = drm_connector_init(bridge->dev, &adv->connector,
+				 &adv7511_connector_funcs,
+				 DRM_MODE_CONNECTOR_HDMIA);
+	if (ret) {
+		DRM_ERROR("Failed to initialize connector with drm\n");
+		return ret;
+	}
+	drm_connector_helper_add(&adv->connector,
+				 &adv7511_connector_helper_funcs);
+	drm_mode_connector_attach_encoder(&adv->connector, bridge->encoder);
+
+	if (adv->type == ADV7533)
+		ret = adv7533_attach_dsi(adv);
+
+	return ret;
+}
+
+static struct drm_bridge_funcs adv7511_bridge_funcs = {
+	.enable = adv7511_bridge_enable,
+	.disable = adv7511_bridge_disable,
+	.mode_set = adv7511_bridge_mode_set,
+	.attach = adv7511_bridge_attach,
 };
 
 /* -----------------------------------------------------------------------------
@@ -780,8 +845,6 @@ static int adv7511_parse_dt(struct device_node *np,
 	const char *str;
 	int ret;
 
-	memset(config, 0, sizeof(*config));
-
 	of_property_read_u32(np, "adi,input-depth", &config->input_color_depth);
 	if (config->input_color_depth != 8 && config->input_color_depth != 10 &&
 	    config->input_color_depth != 12)
@@ -881,7 +944,17 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 	adv7511->powered = false;
 	adv7511->status = connector_status_disconnected;
 
-	ret = adv7511_parse_dt(dev->of_node, &link_config);
+	if (dev->of_node)
+		adv7511->type = (enum adv7511_type)of_device_get_match_data(dev);
+	else
+		adv7511->type = id->driver_data;
+
+	memset(&link_config, 0, sizeof(link_config));
+
+	if (adv7511->type == ADV7511)
+		ret = adv7511_parse_dt(dev->of_node, &link_config);
+	else
+		ret = adv7533_parse_dt(dev->of_node, adv7511);
 	if (ret)
 		return ret;
 
@@ -907,8 +980,12 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 		return ret;
 	dev_dbg(dev, "Rev. %d\n", val);
 
-	ret = regmap_register_patch(adv7511->regmap, adv7511_fixed_registers,
-				    ARRAY_SIZE(adv7511_fixed_registers));
+	if (adv7511->type == ADV7511)
+		ret = regmap_register_patch(adv7511->regmap,
+					    adv7511_fixed_registers,
+					    ARRAY_SIZE(adv7511_fixed_registers));
+	else
+		ret = adv7533_patch_registers(adv7511);
 	if (ret)
 		return ret;
 
@@ -923,6 +1000,12 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 	if (!adv7511->i2c_edid)
 		return -ENOMEM;
 
+	if (adv7511->type == ADV7533) {
+		ret = adv7533_init_cec(adv7511);
+		if (ret)
+			goto err_i2c_unregister_edid;
+	}
+
 	if (i2c->irq) {
 		init_waitqueue_head(&adv7511->wq);
 
@@ -931,7 +1014,7 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 						IRQF_ONESHOT, dev_name(dev),
 						adv7511);
 		if (ret)
-			goto err_i2c_unregister_device;
+			goto err_unregister_cec;
 	}
 
 	/* CEC is unused for now */
@@ -942,11 +1025,23 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id)
 
 	i2c_set_clientdata(i2c, adv7511);
 
-	adv7511_set_link_config(adv7511, &link_config);
+	if (adv7511->type == ADV7511)
+		adv7511_set_link_config(adv7511, &link_config);
+
+	adv7511->bridge.funcs = &adv7511_bridge_funcs;
+	adv7511->bridge.of_node = dev->of_node;
+
+	ret = drm_bridge_add(&adv7511->bridge);
+	if (ret) {
+		dev_err(dev, "failed to add adv7511 bridge\n");
+		goto err_unregister_cec;
+	}
 
 	return 0;
 
-err_i2c_unregister_device:
+err_unregister_cec:
+	adv7533_uninit_cec(adv7511);
+err_i2c_unregister_edid:
 	i2c_unregister_device(adv7511->i2c_edid);
 
 	return ret;
@@ -956,66 +1051,71 @@ static int adv7511_remove(struct i2c_client *i2c)
 {
 	struct adv7511 *adv7511 = i2c_get_clientdata(i2c);
 
-	i2c_unregister_device(adv7511->i2c_edid);
-
-	kfree(adv7511->edid);
-
-	return 0;
-}
-
-static int adv7511_encoder_init(struct i2c_client *i2c, struct drm_device *dev,
-				struct drm_encoder_slave *encoder)
-{
+	if (adv7511->type == ADV7533) {
+		adv7533_detach_dsi(adv7511);
+		adv7533_uninit_cec(adv7511);
+	}
 
-	struct adv7511 *adv7511 = i2c_get_clientdata(i2c);
+	drm_bridge_remove(&adv7511->bridge);
 
-	encoder->slave_priv = adv7511;
-	encoder->slave_funcs = &adv7511_encoder_funcs;
+	i2c_unregister_device(adv7511->i2c_edid);
 
-	adv7511->encoder = &encoder->base;
+	kfree(adv7511->edid);
 
 	return 0;
 }
 
 static const struct i2c_device_id adv7511_i2c_ids[] = {
-	{ "adv7511", 0 },
-	{ "adv7511w", 0 },
-	{ "adv7513", 0 },
+	{ "adv7511", ADV7511 },
+	{ "adv7511w", ADV7511 },
+	{ "adv7513", ADV7511 },
+#ifdef CONFIG_DRM_I2C_ADV7533
+	{ "adv7533", ADV7533 },
+#endif
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, adv7511_i2c_ids);
 
 static const struct of_device_id adv7511_of_ids[] = {
-	{ .compatible = "adi,adv7511", },
-	{ .compatible = "adi,adv7511w", },
-	{ .compatible = "adi,adv7513", },
+	{ .compatible = "adi,adv7511", .data = (void *)ADV7511 },
+	{ .compatible = "adi,adv7511w", .data = (void *)ADV7511 },
+	{ .compatible = "adi,adv7513", .data = (void *)ADV7511 },
+#ifdef CONFIG_DRM_I2C_ADV7533
+	{ .compatible = "adi,adv7533", .data = (void *)ADV7533 },
+#endif
 	{ }
 };
 MODULE_DEVICE_TABLE(of, adv7511_of_ids);
 
-static struct drm_i2c_encoder_driver adv7511_driver = {
-	.i2c_driver = {
-		.driver = {
-			.name = "adv7511",
-			.of_match_table = adv7511_of_ids,
-		},
-		.id_table = adv7511_i2c_ids,
-		.probe = adv7511_probe,
-		.remove = adv7511_remove,
-	},
+static struct mipi_dsi_driver adv7533_dsi_driver = {
+	.driver.name = "adv7533",
+};
 
-	.encoder_init = adv7511_encoder_init,
+static struct i2c_driver adv7511_driver = {
+	.driver = {
+		.name = "adv7511",
+		.of_match_table = adv7511_of_ids,
+	},
+	.id_table = adv7511_i2c_ids,
+	.probe = adv7511_probe,
+	.remove = adv7511_remove,
 };
 
 static int __init adv7511_init(void)
 {
-	return drm_i2c_encoder_register(THIS_MODULE, &adv7511_driver);
+	if (IS_ENABLED(CONFIG_DRM_MIPI_DSI))
+		mipi_dsi_driver_register(&adv7533_dsi_driver);
+
+	return i2c_add_driver(&adv7511_driver);
 }
 module_init(adv7511_init);
 
 static void __exit adv7511_exit(void)
 {
-	drm_i2c_encoder_unregister(&adv7511_driver);
+	i2c_del_driver(&adv7511_driver);
+
+	if (IS_ENABLED(CONFIG_DRM_MIPI_DSI))
+		mipi_dsi_driver_unregister(&adv7533_dsi_driver);
 }
 module_exit(adv7511_exit);
 
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7533.c b/drivers/gpu/drm/bridge/adv7511/adv7533.c
new file mode 100644
index 000000000000..5eebd15899b1
--- /dev/null
+++ b/drivers/gpu/drm/bridge/adv7511/adv7533.c
@@ -0,0 +1,265 @@
+/*
+ * Copyright (c) 2016, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of_graph.h>
+
+#include "adv7511.h"
+
+static const struct reg_sequence adv7533_fixed_registers[] = {
+	{ 0x16, 0x20 },
+	{ 0x9a, 0xe0 },
+	{ 0xba, 0x70 },
+	{ 0xde, 0x82 },
+	{ 0xe4, 0x40 },
+	{ 0xe5, 0x80 },
+};
+
+static const struct reg_sequence adv7533_cec_fixed_registers[] = {
+	{ 0x15, 0xd0 },
+	{ 0x17, 0xd0 },
+	{ 0x24, 0x20 },
+	{ 0x57, 0x11 },
+};
+
+static const struct regmap_config adv7533_cec_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = 0xff,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static void adv7511_dsi_config_timing_gen(struct adv7511 *adv)
+{
+	struct mipi_dsi_device *dsi = adv->dsi;
+	struct drm_display_mode *mode = &adv->curr_mode;
+	unsigned int hsw, hfp, hbp, vsw, vfp, vbp;
+	u8 clock_div_by_lanes[] = { 6, 4, 3 };	/* 2, 3, 4 lanes */
+
+	hsw = mode->hsync_end - mode->hsync_start;
+	hfp = mode->hsync_start - mode->hdisplay;
+	hbp = mode->htotal - mode->hsync_end;
+	vsw = mode->vsync_end - mode->vsync_start;
+	vfp = mode->vsync_start - mode->vdisplay;
+	vbp = mode->vtotal - mode->vsync_end;
+
+	/* set pixel clock divider mode */
+	regmap_write(adv->regmap_cec, 0x16,
+		     clock_div_by_lanes[dsi->lanes - 2] << 3);
+
+	/* horizontal porch params */
+	regmap_write(adv->regmap_cec, 0x28, mode->htotal >> 4);
+	regmap_write(adv->regmap_cec, 0x29, (mode->htotal << 4) & 0xff);
+	regmap_write(adv->regmap_cec, 0x2a, hsw >> 4);
+	regmap_write(adv->regmap_cec, 0x2b, (hsw << 4) & 0xff);
+	regmap_write(adv->regmap_cec, 0x2c, hfp >> 4);
+	regmap_write(adv->regmap_cec, 0x2d, (hfp << 4) & 0xff);
+	regmap_write(adv->regmap_cec, 0x2e, hbp >> 4);
+	regmap_write(adv->regmap_cec, 0x2f, (hbp << 4) & 0xff);
+
+	/* vertical porch params */
+	regmap_write(adv->regmap_cec, 0x30, mode->vtotal >> 4);
+	regmap_write(adv->regmap_cec, 0x31, (mode->vtotal << 4) & 0xff);
+	regmap_write(adv->regmap_cec, 0x32, vsw >> 4);
+	regmap_write(adv->regmap_cec, 0x33, (vsw << 4) & 0xff);
+	regmap_write(adv->regmap_cec, 0x34, vfp >> 4);
+	regmap_write(adv->regmap_cec, 0x35, (vfp << 4) & 0xff);
+	regmap_write(adv->regmap_cec, 0x36, vbp >> 4);
+	regmap_write(adv->regmap_cec, 0x37, (vbp << 4) & 0xff);
+}
+
+void adv7533_dsi_power_on(struct adv7511 *adv)
+{
+	struct mipi_dsi_device *dsi = adv->dsi;
+
+	if (adv->use_timing_gen)
+		adv7511_dsi_config_timing_gen(adv);
+
+	/* set number of dsi lanes */
+	regmap_write(adv->regmap_cec, 0x1c, dsi->lanes << 4);
+
+	if (adv->use_timing_gen) {
+		/* reset internal timing generator */
+		regmap_write(adv->regmap_cec, 0x27, 0xcb);
+		regmap_write(adv->regmap_cec, 0x27, 0x8b);
+		regmap_write(adv->regmap_cec, 0x27, 0xcb);
+	} else {
+		/* disable internal timing generator */
+		regmap_write(adv->regmap_cec, 0x27, 0x0b);
+	}
+
+	/* enable hdmi */
+	regmap_write(adv->regmap_cec, 0x03, 0x89);
+	/* disable test mode */
+	regmap_write(adv->regmap_cec, 0x55, 0x00);
+
+	regmap_register_patch(adv->regmap_cec, adv7533_cec_fixed_registers,
+			      ARRAY_SIZE(adv7533_cec_fixed_registers));
+}
+
+void adv7533_dsi_power_off(struct adv7511 *adv)
+{
+	/* disable hdmi */
+	regmap_write(adv->regmap_cec, 0x03, 0x0b);
+	/* disable internal timing generator */
+	regmap_write(adv->regmap_cec, 0x27, 0x0b);
+}
+
+void adv7533_mode_set(struct adv7511 *adv, struct drm_display_mode *mode)
+{
+	struct mipi_dsi_device *dsi = adv->dsi;
+	int lanes, ret;
+
+	if (adv->num_dsi_lanes != 4)
+		return;
+
+	if (mode->clock > 80000)
+		lanes = 4;
+	else
+		lanes = 3;
+
+	if (lanes != dsi->lanes) {
+		mipi_dsi_detach(dsi);
+		dsi->lanes = lanes;
+		ret = mipi_dsi_attach(dsi);
+		if (ret)
+			dev_err(&dsi->dev, "failed to change host lanes\n");
+	}
+}
+
+int adv7533_patch_registers(struct adv7511 *adv)
+{
+	return regmap_register_patch(adv->regmap,
+				     adv7533_fixed_registers,
+				     ARRAY_SIZE(adv7533_fixed_registers));
+}
+
+void adv7533_uninit_cec(struct adv7511 *adv)
+{
+	i2c_unregister_device(adv->i2c_cec);
+}
+
+static const int cec_i2c_addr = 0x78;
+
+int adv7533_init_cec(struct adv7511 *adv)
+{
+	int ret;
+
+	adv->i2c_cec = i2c_new_dummy(adv->i2c_main->adapter, cec_i2c_addr >> 1);
+	if (!adv->i2c_cec)
+		return -ENOMEM;
+
+	adv->regmap_cec = devm_regmap_init_i2c(adv->i2c_cec,
+					&adv7533_cec_regmap_config);
+	if (IS_ERR(adv->regmap_cec)) {
+		ret = PTR_ERR(adv->regmap_cec);
+		goto err;
+	}
+
+	ret = regmap_register_patch(adv->regmap_cec,
+				    adv7533_cec_fixed_registers,
+				    ARRAY_SIZE(adv7533_cec_fixed_registers));
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	adv7533_uninit_cec(adv);
+	return ret;
+}
+
+int adv7533_attach_dsi(struct adv7511 *adv)
+{
+	struct device *dev = &adv->i2c_main->dev;
+	struct mipi_dsi_host *host;
+	struct mipi_dsi_device *dsi;
+	int ret = 0;
+	const struct mipi_dsi_device_info info = { .type = "adv7533",
+						   .channel = 0,
+						   .node = NULL,
+						 };
+
+	host = of_find_mipi_dsi_host_by_node(adv->host_node);
+	if (!host) {
+		dev_err(dev, "failed to find dsi host\n");
+		return -EPROBE_DEFER;
+	}
+
+	dsi = mipi_dsi_device_register_full(host, &info);
+	if (IS_ERR(dsi)) {
+		dev_err(dev, "failed to create dsi device\n");
+		ret = PTR_ERR(dsi);
+		goto err_dsi_device;
+	}
+
+	adv->dsi = dsi;
+
+	dsi->lanes = adv->num_dsi_lanes;
+	dsi->format = MIPI_DSI_FMT_RGB888;
+	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
+			  MIPI_DSI_MODE_EOT_PACKET | MIPI_DSI_MODE_VIDEO_HSE;
+
+	ret = mipi_dsi_attach(dsi);
+	if (ret < 0) {
+		dev_err(dev, "failed to attach dsi to host\n");
+		goto err_dsi_attach;
+	}
+
+	return 0;
+
+err_dsi_attach:
+	mipi_dsi_device_unregister(dsi);
+err_dsi_device:
+	return ret;
+}
+
+void adv7533_detach_dsi(struct adv7511 *adv)
+{
+	mipi_dsi_detach(adv->dsi);
+	mipi_dsi_device_unregister(adv->dsi);
+}
+
+int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv)
+{
+	u32 num_lanes;
+	struct device_node *endpoint;
+
+	of_property_read_u32(np, "adi,dsi-lanes", &num_lanes);
+
+	if (num_lanes < 1 || num_lanes > 4)
+		return -EINVAL;
+
+	adv->num_dsi_lanes = num_lanes;
+
+	endpoint = of_graph_get_next_endpoint(np, NULL);
+	if (!endpoint)
+		return -ENODEV;
+
+	adv->host_node = of_graph_get_remote_port_parent(endpoint);
+	if (!adv->host_node) {
+		of_node_put(endpoint);
+		return -ENODEV;
+	}
+
+	of_node_put(endpoint);
+	of_node_put(adv->host_node);
+
+	adv->use_timing_gen = !of_property_read_bool(np,
+						"adi,disable-timing-generator");
+
+	/* TODO: Check if these need to be parsed by DT or not */
+	adv->rgb = true;
+	adv->embedded_sync = false;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix-anx78xx.c
index d087b054c360..f9f03bcba0af 100644
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix-anx78xx.c
@@ -986,16 +986,8 @@ unlock:
 	return num_modes;
 }
 
-static struct drm_encoder *anx78xx_best_encoder(struct drm_connector *connector)
-{
-	struct anx78xx *anx78xx = connector_to_anx78xx(connector);
-
-	return anx78xx->bridge.encoder;
-}
-
 static const struct drm_connector_helper_funcs anx78xx_connector_helper_funcs = {
 	.get_modes = anx78xx_get_modes,
-	.best_encoder = anx78xx_best_encoder,
 };
 
 static enum drm_connector_status anx78xx_detect(struct drm_connector *connector,
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index 7699597070a1..32715daf73cb 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -938,7 +938,7 @@ int analogix_dp_get_modes(struct drm_connector *connector)
 		num_modes += drm_panel_get_modes(dp->plat_data->panel);
 
 	if (dp->plat_data->get_modes)
-		num_modes += dp->plat_data->get_modes(dp->plat_data);
+		num_modes += dp->plat_data->get_modes(dp->plat_data, connector);
 
 	return num_modes;
 }
@@ -1208,6 +1208,7 @@ static int analogix_dp_dt_parse_pdata(struct analogix_dp_device *dp)
 
 	switch (dp->plat_data->dev_type) {
 	case RK3288_DP:
+	case RK3399_EDP:
 		/*
 		 * Like Rk3288 DisplayPort TRM indicate that "Main link
 		 * containing 4 physical lanes of 2.7/1.62 Gbps/lane".
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h
index f09275d40f70..b45638043ec4 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h
@@ -127,10 +127,10 @@ enum analog_power_block {
 };
 
 enum dp_irq_type {
-	DP_IRQ_TYPE_HP_CABLE_IN,
-	DP_IRQ_TYPE_HP_CABLE_OUT,
-	DP_IRQ_TYPE_HP_CHANGE,
-	DP_IRQ_TYPE_UNKNOWN,
+	DP_IRQ_TYPE_HP_CABLE_IN  = BIT(0),
+	DP_IRQ_TYPE_HP_CABLE_OUT = BIT(1),
+	DP_IRQ_TYPE_HP_CHANGE    = BIT(2),
+	DP_IRQ_TYPE_UNKNOWN      = BIT(3),
 };
 
 struct video_info {
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c
index 49205ef02be3..48030f0cf497 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c
@@ -74,8 +74,12 @@ void analogix_dp_init_analog_param(struct analogix_dp_device *dp)
 	reg = SEL_24M | TX_DVDD_BIT_1_0625V;
 	writel(reg, dp->reg_base + ANALOGIX_DP_ANALOG_CTL_2);
 
-	if (dp->plat_data && (dp->plat_data->dev_type == RK3288_DP)) {
-		writel(REF_CLK_24M, dp->reg_base + ANALOGIX_DP_PLL_REG_1);
+	if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) {
+		reg = REF_CLK_24M;
+		if (dp->plat_data->dev_type == RK3288_DP)
+			reg ^= REF_CLK_MASK;
+
+		writel(reg, dp->reg_base + ANALOGIX_DP_PLL_REG_1);
 		writel(0x95, dp->reg_base + ANALOGIX_DP_PLL_REG_2);
 		writel(0x40, dp->reg_base + ANALOGIX_DP_PLL_REG_3);
 		writel(0x58, dp->reg_base + ANALOGIX_DP_PLL_REG_4);
@@ -244,7 +248,7 @@ void analogix_dp_set_analog_power_down(struct analogix_dp_device *dp,
 	u32 reg;
 	u32 phy_pd_addr = ANALOGIX_DP_PHY_PD;
 
-	if (dp->plat_data && (dp->plat_data->dev_type == RK3288_DP))
+	if (dp->plat_data && is_rockchip(dp->plat_data->dev_type))
 		phy_pd_addr = ANALOGIX_DP_PD;
 
 	switch (block) {
@@ -448,7 +452,7 @@ void analogix_dp_init_aux(struct analogix_dp_device *dp)
 	analogix_dp_reset_aux(dp);
 
 	/* Disable AUX transaction H/W retry */
-	if (dp->plat_data && (dp->plat_data->dev_type == RK3288_DP))
+	if (dp->plat_data && is_rockchip(dp->plat_data->dev_type))
 		reg = AUX_BIT_PERIOD_EXPECTED_DELAY(0) |
 		      AUX_HW_RETRY_COUNT_SEL(3) |
 		      AUX_HW_RETRY_INTERVAL_600_MICROSECONDS;
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h
index 337912b0aeab..cdcc6c5add5e 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h
@@ -163,8 +163,9 @@
 #define HSYNC_POLARITY_CFG			(0x1 << 0)
 
 /* ANALOGIX_DP_PLL_REG_1 */
-#define REF_CLK_24M				(0x1 << 1)
-#define REF_CLK_27M				(0x0 << 1)
+#define REF_CLK_24M				(0x1 << 0)
+#define REF_CLK_27M				(0x0 << 0)
+#define REF_CLK_MASK				(0x1 << 0)
 
 /* ANALOGIX_DP_LANE_MAP */
 #define LANE3_MAP_LOGIC_LANE_0			(0x0 << 6)
diff --git a/drivers/gpu/drm/bridge/dw-hdmi.c b/drivers/gpu/drm/bridge/dw-hdmi.c
index c9d941283d30..77ab47341658 100644
--- a/drivers/gpu/drm/bridge/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/dw-hdmi.c
@@ -1476,15 +1476,6 @@ dw_hdmi_connector_mode_valid(struct drm_connector *connector,
 	return mode_status;
 }
 
-static struct drm_encoder *dw_hdmi_connector_best_encoder(struct drm_connector
-							   *connector)
-{
-	struct dw_hdmi *hdmi = container_of(connector, struct dw_hdmi,
-					     connector);
-
-	return hdmi->encoder;
-}
-
 static void dw_hdmi_connector_destroy(struct drm_connector *connector)
 {
 	drm_connector_unregister(connector);
@@ -1504,14 +1495,6 @@ static void dw_hdmi_connector_force(struct drm_connector *connector)
 }
 
 static const struct drm_connector_funcs dw_hdmi_connector_funcs = {
-	.dpms = drm_helper_connector_dpms,
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.detect = dw_hdmi_connector_detect,
-	.destroy = dw_hdmi_connector_destroy,
-	.force = dw_hdmi_connector_force,
-};
-
-static const struct drm_connector_funcs dw_hdmi_atomic_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.detect = dw_hdmi_connector_detect,
@@ -1525,7 +1508,7 @@ static const struct drm_connector_funcs dw_hdmi_atomic_connector_funcs = {
 static const struct drm_connector_helper_funcs dw_hdmi_connector_helper_funcs = {
 	.get_modes = dw_hdmi_connector_get_modes,
 	.mode_valid = dw_hdmi_connector_mode_valid,
-	.best_encoder = dw_hdmi_connector_best_encoder,
+	.best_encoder = drm_atomic_helper_best_encoder,
 };
 
 static const struct drm_bridge_funcs dw_hdmi_bridge_funcs = {
@@ -1643,14 +1626,9 @@ static int dw_hdmi_register(struct drm_device *drm, struct dw_hdmi *hdmi)
 	drm_connector_helper_add(&hdmi->connector,
 				 &dw_hdmi_connector_helper_funcs);
 
-	if (drm_core_check_feature(drm, DRIVER_ATOMIC))
-		drm_connector_init(drm, &hdmi->connector,
-				   &dw_hdmi_atomic_connector_funcs,
-				   DRM_MODE_CONNECTOR_HDMIA);
-	else
-		drm_connector_init(drm, &hdmi->connector,
-				   &dw_hdmi_connector_funcs,
-				   DRM_MODE_CONNECTOR_HDMIA);
+	drm_connector_init(drm, &hdmi->connector,
+			   &dw_hdmi_connector_funcs,
+			   DRM_MODE_CONNECTOR_HDMIA);
 
 	drm_mode_connector_attach_encoder(&hdmi->connector, encoder);
 
diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c
index 7ecd59f70b8e..93f3dacf9e27 100644
--- a/drivers/gpu/drm/bridge/nxp-ptn3460.c
+++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c
@@ -235,16 +235,8 @@ out:
 	return num_modes;
 }
 
-static struct drm_encoder *ptn3460_best_encoder(struct drm_connector *connector)
-{
-	struct ptn3460_bridge *ptn_bridge = connector_to_ptn3460(connector);
-
-	return ptn_bridge->bridge.encoder;
-}
-
 static const struct drm_connector_helper_funcs ptn3460_connector_helper_funcs = {
 	.get_modes = ptn3460_get_modes,
-	.best_encoder = ptn3460_best_encoder,
 };
 
 static enum drm_connector_status ptn3460_detect(struct drm_connector *connector,
diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c
index be881e9fef8f..583b8ce614e3 100644
--- a/drivers/gpu/drm/bridge/parade-ps8622.c
+++ b/drivers/gpu/drm/bridge/parade-ps8622.c
@@ -474,18 +474,8 @@ static int ps8622_get_modes(struct drm_connector *connector)
 	return drm_panel_get_modes(ps8622->panel);
 }
 
-static struct drm_encoder *ps8622_best_encoder(struct drm_connector *connector)
-{
-	struct ps8622_bridge *ps8622;
-
-	ps8622 = connector_to_ps8622(connector);
-
-	return ps8622->bridge.encoder;
-}
-
 static const struct drm_connector_helper_funcs ps8622_connector_helper_funcs = {
 	.get_modes = ps8622_get_modes,
-	.best_encoder = ps8622_best_encoder,
 };
 
 static enum drm_connector_status ps8622_detect(struct drm_connector *connector,
@@ -646,9 +636,7 @@ static int ps8622_remove(struct i2c_client *client)
 {
 	struct ps8622_bridge *ps8622 = i2c_get_clientdata(client);
 
-	if (ps8622->bl)
-		backlight_device_unregister(ps8622->bl);
-
+	backlight_device_unregister(ps8622->bl);
 	drm_bridge_remove(&ps8622->bridge);
 
 	return 0;
diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c
new file mode 100644
index 000000000000..9126d0306ab5
--- /dev/null
+++ b/drivers/gpu/drm/bridge/sii902x.c
@@ -0,0 +1,467 @@
+/*
+ * Copyright (C) 2016 Atmel
+ *		      Bo Shen <voice.shen@atmel.com>
+ *
+ * Authors:	      Bo Shen <voice.shen@atmel.com>
+ *		      Boris Brezillon <boris.brezillon@free-electrons.com>
+ *		      Wu, Songjun <Songjun.Wu@atmel.com>
+ *
+ *
+ * Copyright (C) 2010-2011 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_edid.h>
+
+#define SII902X_TPI_VIDEO_DATA			0x0
+
+#define SII902X_TPI_PIXEL_REPETITION		0x8
+#define SII902X_TPI_AVI_PIXEL_REP_BUS_24BIT     BIT(5)
+#define SII902X_TPI_AVI_PIXEL_REP_RISING_EDGE   BIT(4)
+#define SII902X_TPI_AVI_PIXEL_REP_4X		3
+#define SII902X_TPI_AVI_PIXEL_REP_2X		1
+#define SII902X_TPI_AVI_PIXEL_REP_NONE		0
+#define SII902X_TPI_CLK_RATIO_HALF		(0 << 6)
+#define SII902X_TPI_CLK_RATIO_1X		(1 << 6)
+#define SII902X_TPI_CLK_RATIO_2X		(2 << 6)
+#define SII902X_TPI_CLK_RATIO_4X		(3 << 6)
+
+#define SII902X_TPI_AVI_IN_FORMAT		0x9
+#define SII902X_TPI_AVI_INPUT_BITMODE_12BIT	BIT(7)
+#define SII902X_TPI_AVI_INPUT_DITHER		BIT(6)
+#define SII902X_TPI_AVI_INPUT_RANGE_LIMITED	(2 << 2)
+#define SII902X_TPI_AVI_INPUT_RANGE_FULL	(1 << 2)
+#define SII902X_TPI_AVI_INPUT_RANGE_AUTO	(0 << 2)
+#define SII902X_TPI_AVI_INPUT_COLORSPACE_BLACK	(3 << 0)
+#define SII902X_TPI_AVI_INPUT_COLORSPACE_YUV422	(2 << 0)
+#define SII902X_TPI_AVI_INPUT_COLORSPACE_YUV444	(1 << 0)
+#define SII902X_TPI_AVI_INPUT_COLORSPACE_RGB	(0 << 0)
+
+#define SII902X_TPI_AVI_INFOFRAME		0x0c
+
+#define SII902X_SYS_CTRL_DATA			0x1a
+#define SII902X_SYS_CTRL_PWR_DWN		BIT(4)
+#define SII902X_SYS_CTRL_AV_MUTE		BIT(3)
+#define SII902X_SYS_CTRL_DDC_BUS_REQ		BIT(2)
+#define SII902X_SYS_CTRL_DDC_BUS_GRTD		BIT(1)
+#define SII902X_SYS_CTRL_OUTPUT_MODE		BIT(0)
+#define SII902X_SYS_CTRL_OUTPUT_HDMI		1
+#define SII902X_SYS_CTRL_OUTPUT_DVI		0
+
+#define SII902X_REG_CHIPID(n)			(0x1b + (n))
+
+#define SII902X_PWR_STATE_CTRL			0x1e
+#define SII902X_AVI_POWER_STATE_MSK		GENMASK(1, 0)
+#define SII902X_AVI_POWER_STATE_D(l)		((l) & SII902X_AVI_POWER_STATE_MSK)
+
+#define SII902X_INT_ENABLE			0x3c
+#define SII902X_INT_STATUS			0x3d
+#define SII902X_HOTPLUG_EVENT			BIT(0)
+#define SII902X_PLUGGED_STATUS			BIT(2)
+
+#define SII902X_REG_TPI_RQB			0xc7
+
+#define SII902X_I2C_BUS_ACQUISITION_TIMEOUT_MS	500
+
+struct sii902x {
+	struct i2c_client *i2c;
+	struct regmap *regmap;
+	struct drm_bridge bridge;
+	struct drm_connector connector;
+	struct gpio_desc *reset_gpio;
+};
+
+static inline struct sii902x *bridge_to_sii902x(struct drm_bridge *bridge)
+{
+	return container_of(bridge, struct sii902x, bridge);
+}
+
+static inline struct sii902x *connector_to_sii902x(struct drm_connector *con)
+{
+	return container_of(con, struct sii902x, connector);
+}
+
+static void sii902x_reset(struct sii902x *sii902x)
+{
+	if (!sii902x->reset_gpio)
+		return;
+
+	gpiod_set_value(sii902x->reset_gpio, 1);
+
+	/* The datasheet says treset-min = 100us. Make it 150us to be sure. */
+	usleep_range(150, 200);
+
+	gpiod_set_value(sii902x->reset_gpio, 0);
+}
+
+static enum drm_connector_status
+sii902x_connector_detect(struct drm_connector *connector, bool force)
+{
+	struct sii902x *sii902x = connector_to_sii902x(connector);
+	unsigned int status;
+
+	regmap_read(sii902x->regmap, SII902X_INT_STATUS, &status);
+
+	return (status & SII902X_PLUGGED_STATUS) ?
+	       connector_status_connected : connector_status_disconnected;
+}
+
+static const struct drm_connector_funcs sii902x_connector_funcs = {
+	.dpms = drm_atomic_helper_connector_dpms,
+	.detect = sii902x_connector_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = drm_connector_cleanup,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static int sii902x_get_modes(struct drm_connector *connector)
+{
+	struct sii902x *sii902x = connector_to_sii902x(connector);
+	struct regmap *regmap = sii902x->regmap;
+	u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+	unsigned long timeout;
+	unsigned int status;
+	struct edid *edid;
+	int num = 0;
+	int ret;
+
+	ret = regmap_update_bits(regmap, SII902X_SYS_CTRL_DATA,
+				 SII902X_SYS_CTRL_DDC_BUS_REQ,
+				 SII902X_SYS_CTRL_DDC_BUS_REQ);
+	if (ret)
+		return ret;
+
+	timeout = jiffies +
+		  msecs_to_jiffies(SII902X_I2C_BUS_ACQUISITION_TIMEOUT_MS);
+	do {
+		ret = regmap_read(regmap, SII902X_SYS_CTRL_DATA, &status);
+		if (ret)
+			return ret;
+	} while (!(status & SII902X_SYS_CTRL_DDC_BUS_GRTD) &&
+		 time_before(jiffies, timeout));
+
+	if (!(status & SII902X_SYS_CTRL_DDC_BUS_GRTD)) {
+		dev_err(&sii902x->i2c->dev, "failed to acquire the i2c bus");
+		return -ETIMEDOUT;
+	}
+
+	ret = regmap_write(regmap, SII902X_SYS_CTRL_DATA, status);
+	if (ret)
+		return ret;
+
+	edid = drm_get_edid(connector, sii902x->i2c->adapter);
+	drm_mode_connector_update_edid_property(connector, edid);
+	if (edid) {
+		num = drm_add_edid_modes(connector, edid);
+		kfree(edid);
+	}
+
+	ret = drm_display_info_set_bus_formats(&connector->display_info,
+					       &bus_format, 1);
+	if (ret)
+		return ret;
+
+	ret = regmap_read(regmap, SII902X_SYS_CTRL_DATA, &status);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(regmap, SII902X_SYS_CTRL_DATA,
+				 SII902X_SYS_CTRL_DDC_BUS_REQ |
+				 SII902X_SYS_CTRL_DDC_BUS_GRTD, 0);
+	if (ret)
+		return ret;
+
+	timeout = jiffies +
+		  msecs_to_jiffies(SII902X_I2C_BUS_ACQUISITION_TIMEOUT_MS);
+	do {
+		ret = regmap_read(regmap, SII902X_SYS_CTRL_DATA, &status);
+		if (ret)
+			return ret;
+	} while (status & (SII902X_SYS_CTRL_DDC_BUS_REQ |
+			   SII902X_SYS_CTRL_DDC_BUS_GRTD) &&
+		 time_before(jiffies, timeout));
+
+	if (status & (SII902X_SYS_CTRL_DDC_BUS_REQ |
+		      SII902X_SYS_CTRL_DDC_BUS_GRTD)) {
+		dev_err(&sii902x->i2c->dev, "failed to release the i2c bus");
+		return -ETIMEDOUT;
+	}
+
+	return num;
+}
+
+static enum drm_mode_status sii902x_mode_valid(struct drm_connector *connector,
+					       struct drm_display_mode *mode)
+{
+	/* TODO: check mode */
+
+	return MODE_OK;
+}
+
+static const struct drm_connector_helper_funcs sii902x_connector_helper_funcs = {
+	.get_modes = sii902x_get_modes,
+	.mode_valid = sii902x_mode_valid,
+};
+
+static void sii902x_bridge_disable(struct drm_bridge *bridge)
+{
+	struct sii902x *sii902x = bridge_to_sii902x(bridge);
+
+	regmap_update_bits(sii902x->regmap, SII902X_SYS_CTRL_DATA,
+			   SII902X_SYS_CTRL_PWR_DWN,
+			   SII902X_SYS_CTRL_PWR_DWN);
+}
+
+static void sii902x_bridge_enable(struct drm_bridge *bridge)
+{
+	struct sii902x *sii902x = bridge_to_sii902x(bridge);
+
+	regmap_update_bits(sii902x->regmap, SII902X_PWR_STATE_CTRL,
+			   SII902X_AVI_POWER_STATE_MSK,
+			   SII902X_AVI_POWER_STATE_D(0));
+	regmap_update_bits(sii902x->regmap, SII902X_SYS_CTRL_DATA,
+			   SII902X_SYS_CTRL_PWR_DWN, 0);
+}
+
+static void sii902x_bridge_mode_set(struct drm_bridge *bridge,
+				    struct drm_display_mode *mode,
+				    struct drm_display_mode *adj)
+{
+	struct sii902x *sii902x = bridge_to_sii902x(bridge);
+	struct regmap *regmap = sii902x->regmap;
+	u8 buf[HDMI_INFOFRAME_SIZE(AVI)];
+	struct hdmi_avi_infoframe frame;
+	int ret;
+
+	buf[0] = adj->clock;
+	buf[1] = adj->clock >> 8;
+	buf[2] = adj->vrefresh;
+	buf[3] = 0x00;
+	buf[4] = adj->hdisplay;
+	buf[5] = adj->hdisplay >> 8;
+	buf[6] = adj->vdisplay;
+	buf[7] = adj->vdisplay >> 8;
+	buf[8] = SII902X_TPI_CLK_RATIO_1X | SII902X_TPI_AVI_PIXEL_REP_NONE |
+		 SII902X_TPI_AVI_PIXEL_REP_BUS_24BIT;
+	buf[9] = SII902X_TPI_AVI_INPUT_RANGE_AUTO |
+		 SII902X_TPI_AVI_INPUT_COLORSPACE_RGB;
+
+	ret = regmap_bulk_write(regmap, SII902X_TPI_VIDEO_DATA, buf, 10);
+	if (ret)
+		return;
+
+	ret = drm_hdmi_avi_infoframe_from_display_mode(&frame, adj);
+	if (ret < 0) {
+		DRM_ERROR("couldn't fill AVI infoframe\n");
+		return;
+	}
+
+	ret = hdmi_avi_infoframe_pack(&frame, buf, sizeof(buf));
+	if (ret < 0) {
+		DRM_ERROR("failed to pack AVI infoframe: %d\n", ret);
+		return;
+	}
+
+	/* Do not send the infoframe header, but keep the CRC field. */
+	regmap_bulk_write(regmap, SII902X_TPI_AVI_INFOFRAME,
+			  buf + HDMI_INFOFRAME_HEADER_SIZE - 1,
+			  HDMI_AVI_INFOFRAME_SIZE + 1);
+}
+
+static int sii902x_bridge_attach(struct drm_bridge *bridge)
+{
+	struct sii902x *sii902x = bridge_to_sii902x(bridge);
+	struct drm_device *drm = bridge->dev;
+	int ret;
+
+	drm_connector_helper_add(&sii902x->connector,
+				 &sii902x_connector_helper_funcs);
+
+	if (!drm_core_check_feature(drm, DRIVER_ATOMIC)) {
+		dev_err(&sii902x->i2c->dev,
+			"sii902x driver is only compatible with DRM devices supporting atomic updates");
+		return -ENOTSUPP;
+	}
+
+	ret = drm_connector_init(drm, &sii902x->connector,
+				 &sii902x_connector_funcs,
+				 DRM_MODE_CONNECTOR_HDMIA);
+	if (ret)
+		return ret;
+
+	if (sii902x->i2c->irq > 0)
+		sii902x->connector.polled = DRM_CONNECTOR_POLL_HPD;
+	else
+		sii902x->connector.polled = DRM_CONNECTOR_POLL_CONNECT;
+
+	drm_mode_connector_attach_encoder(&sii902x->connector, bridge->encoder);
+
+	return 0;
+}
+
+static const struct drm_bridge_funcs sii902x_bridge_funcs = {
+	.attach = sii902x_bridge_attach,
+	.mode_set = sii902x_bridge_mode_set,
+	.disable = sii902x_bridge_disable,
+	.enable = sii902x_bridge_enable,
+};
+
+static const struct regmap_range sii902x_volatile_ranges[] = {
+	{ .range_min = 0, .range_max = 0xff },
+};
+
+static const struct regmap_access_table sii902x_volatile_table = {
+	.yes_ranges = sii902x_volatile_ranges,
+	.n_yes_ranges = ARRAY_SIZE(sii902x_volatile_ranges),
+};
+
+static const struct regmap_config sii902x_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.volatile_table = &sii902x_volatile_table,
+	.cache_type = REGCACHE_NONE,
+};
+
+static irqreturn_t sii902x_interrupt(int irq, void *data)
+{
+	struct sii902x *sii902x = data;
+	unsigned int status = 0;
+
+	regmap_read(sii902x->regmap, SII902X_INT_STATUS, &status);
+	regmap_write(sii902x->regmap, SII902X_INT_STATUS, status);
+
+	if ((status & SII902X_HOTPLUG_EVENT) && sii902x->bridge.dev)
+		drm_helper_hpd_irq_event(sii902x->bridge.dev);
+
+	return IRQ_HANDLED;
+}
+
+static int sii902x_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	struct device *dev = &client->dev;
+	unsigned int status = 0;
+	struct sii902x *sii902x;
+	u8 chipid[4];
+	int ret;
+
+	sii902x = devm_kzalloc(dev, sizeof(*sii902x), GFP_KERNEL);
+	if (!sii902x)
+		return -ENOMEM;
+
+	sii902x->i2c = client;
+	sii902x->regmap = devm_regmap_init_i2c(client, &sii902x_regmap_config);
+	if (IS_ERR(sii902x->regmap))
+		return PTR_ERR(sii902x->regmap);
+
+	sii902x->reset_gpio = devm_gpiod_get_optional(dev, "reset",
+						      GPIOD_OUT_LOW);
+	if (IS_ERR(sii902x->reset_gpio)) {
+		dev_err(dev, "Failed to retrieve/request reset gpio: %ld\n",
+			PTR_ERR(sii902x->reset_gpio));
+		return PTR_ERR(sii902x->reset_gpio);
+	}
+
+	sii902x_reset(sii902x);
+
+	ret = regmap_write(sii902x->regmap, SII902X_REG_TPI_RQB, 0x0);
+	if (ret)
+		return ret;
+
+	ret = regmap_bulk_read(sii902x->regmap, SII902X_REG_CHIPID(0),
+			       &chipid, 4);
+	if (ret) {
+		dev_err(dev, "regmap_read failed %d\n", ret);
+		return ret;
+	}
+
+	if (chipid[0] != 0xb0) {
+		dev_err(dev, "Invalid chipid: %02x (expecting 0xb0)\n",
+			chipid[0]);
+		return -EINVAL;
+	}
+
+	/* Clear all pending interrupts */
+	regmap_read(sii902x->regmap, SII902X_INT_STATUS, &status);
+	regmap_write(sii902x->regmap, SII902X_INT_STATUS, status);
+
+	if (client->irq > 0) {
+		regmap_write(sii902x->regmap, SII902X_INT_ENABLE,
+			     SII902X_HOTPLUG_EVENT);
+
+		ret = devm_request_threaded_irq(dev, client->irq, NULL,
+						sii902x_interrupt,
+						IRQF_ONESHOT, dev_name(dev),
+						sii902x);
+		if (ret)
+			return ret;
+	}
+
+	sii902x->bridge.funcs = &sii902x_bridge_funcs;
+	sii902x->bridge.of_node = dev->of_node;
+	ret = drm_bridge_add(&sii902x->bridge);
+	if (ret) {
+		dev_err(dev, "Failed to add drm_bridge\n");
+		return ret;
+	}
+
+	i2c_set_clientdata(client, sii902x);
+
+	return 0;
+}
+
+static int sii902x_remove(struct i2c_client *client)
+
+{
+	struct sii902x *sii902x = i2c_get_clientdata(client);
+
+	drm_bridge_remove(&sii902x->bridge);
+
+	return 0;
+}
+
+static const struct of_device_id sii902x_dt_ids[] = {
+	{ .compatible = "sil,sii9022", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, sii902x_dt_ids);
+
+static const struct i2c_device_id sii902x_i2c_ids[] = {
+	{ "sii9022", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(i2c, sii902x_i2c_ids);
+
+static struct i2c_driver sii902x_driver = {
+	.probe = sii902x_probe,
+	.remove = sii902x_remove,
+	.driver = {
+		.name = "sii902x",
+		.of_match_table = sii902x_dt_ids,
+	},
+	.id_table = sii902x_i2c_ids,
+};
+module_i2c_driver(sii902x_driver);
+
+MODULE_AUTHOR("Boris Brezillon <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("SII902x RGB -> HDMI bridges");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
new file mode 100644
index 000000000000..a09825d8c94a
--- /dev/null
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -0,0 +1,1413 @@
+/*
+ * tc358767 eDP bridge driver
+ *
+ * Copyright (C) 2016 CogentEmbedded Inc
+ * Author: Andrey Gusakov <andrey.gusakov@cogentembedded.com>
+ *
+ * Copyright (C) 2016 Pengutronix, Philipp Zabel <p.zabel@pengutronix.de>
+ *
+ * Initially based on: drivers/gpu/drm/i2c/tda998x_drv.c
+ *
+ * Copyright (C) 2012 Texas Instruments
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_dp_helper.h>
+#include <drm/drm_edid.h>
+#include <drm/drm_of.h>
+#include <drm/drm_panel.h>
+
+/* Registers */
+
+/* Display Parallel Interface */
+#define DPIPXLFMT		0x0440
+#define VS_POL_ACTIVE_LOW		(1 << 10)
+#define HS_POL_ACTIVE_LOW		(1 << 9)
+#define DE_POL_ACTIVE_HIGH		(0 << 8)
+#define SUB_CFG_TYPE_CONFIG1		(0 << 2) /* LSB aligned */
+#define SUB_CFG_TYPE_CONFIG2		(1 << 2) /* Loosely Packed */
+#define SUB_CFG_TYPE_CONFIG3		(2 << 2) /* LSB aligned 8-bit */
+#define DPI_BPP_RGB888			(0 << 0)
+#define DPI_BPP_RGB666			(1 << 0)
+#define DPI_BPP_RGB565			(2 << 0)
+
+/* Video Path */
+#define VPCTRL0			0x0450
+#define OPXLFMT_RGB666			(0 << 8)
+#define OPXLFMT_RGB888			(1 << 8)
+#define FRMSYNC_DISABLED		(0 << 4) /* Video Timing Gen Disabled */
+#define FRMSYNC_ENABLED			(1 << 4) /* Video Timing Gen Enabled */
+#define MSF_DISABLED			(0 << 0) /* Magic Square FRC disabled */
+#define MSF_ENABLED			(1 << 0) /* Magic Square FRC enabled */
+#define HTIM01			0x0454
+#define HTIM02			0x0458
+#define VTIM01			0x045c
+#define VTIM02			0x0460
+#define VFUEN0			0x0464
+#define VFUEN				BIT(0)   /* Video Frame Timing Upload */
+
+/* System */
+#define TC_IDREG		0x0500
+#define SYSCTRL			0x0510
+#define DP0_AUDSRC_NO_INPUT		(0 << 3)
+#define DP0_AUDSRC_I2S_RX		(1 << 3)
+#define DP0_VIDSRC_NO_INPUT		(0 << 0)
+#define DP0_VIDSRC_DSI_RX		(1 << 0)
+#define DP0_VIDSRC_DPI_RX		(2 << 0)
+#define DP0_VIDSRC_COLOR_BAR		(3 << 0)
+
+/* Control */
+#define DP0CTL			0x0600
+#define VID_MN_GEN			BIT(6)   /* Auto-generate M/N values */
+#define EF_EN				BIT(5)   /* Enable Enhanced Framing */
+#define VID_EN				BIT(1)   /* Video transmission enable */
+#define DP_EN				BIT(0)   /* Enable DPTX function */
+
+/* Clocks */
+#define DP0_VIDMNGEN0		0x0610
+#define DP0_VIDMNGEN1		0x0614
+#define DP0_VMNGENSTATUS	0x0618
+
+/* Main Channel */
+#define DP0_SECSAMPLE		0x0640
+#define DP0_VIDSYNCDELAY	0x0644
+#define DP0_TOTALVAL		0x0648
+#define DP0_STARTVAL		0x064c
+#define DP0_ACTIVEVAL		0x0650
+#define DP0_SYNCVAL		0x0654
+#define DP0_MISC		0x0658
+#define TU_SIZE_RECOMMENDED		(0x3f << 16) /* LSCLK cycles per TU */
+#define BPC_6				(0 << 5)
+#define BPC_8				(1 << 5)
+
+/* AUX channel */
+#define DP0_AUXCFG0		0x0660
+#define DP0_AUXCFG1		0x0664
+#define AUX_RX_FILTER_EN		BIT(16)
+
+#define DP0_AUXADDR		0x0668
+#define DP0_AUXWDATA(i)		(0x066c + (i) * 4)
+#define DP0_AUXRDATA(i)		(0x067c + (i) * 4)
+#define DP0_AUXSTATUS		0x068c
+#define AUX_STATUS_MASK			0xf0
+#define AUX_STATUS_SHIFT		4
+#define AUX_TIMEOUT			BIT(1)
+#define AUX_BUSY			BIT(0)
+#define DP0_AUXI2CADR		0x0698
+
+/* Link Training */
+#define DP0_SRCCTRL		0x06a0
+#define DP0_SRCCTRL_SCRMBLDIS		BIT(13)
+#define DP0_SRCCTRL_EN810B		BIT(12)
+#define DP0_SRCCTRL_NOTP		(0 << 8)
+#define DP0_SRCCTRL_TP1			(1 << 8)
+#define DP0_SRCCTRL_TP2			(2 << 8)
+#define DP0_SRCCTRL_LANESKEW		BIT(7)
+#define DP0_SRCCTRL_SSCG		BIT(3)
+#define DP0_SRCCTRL_LANES_1		(0 << 2)
+#define DP0_SRCCTRL_LANES_2		(1 << 2)
+#define DP0_SRCCTRL_BW27		(1 << 1)
+#define DP0_SRCCTRL_BW162		(0 << 1)
+#define DP0_SRCCTRL_AUTOCORRECT		BIT(0)
+#define DP0_LTSTAT		0x06d0
+#define LT_LOOPDONE			BIT(13)
+#define LT_STATUS_MASK			(0x1f << 8)
+#define LT_CHANNEL1_EQ_BITS		(DP_CHANNEL_EQ_BITS << 4)
+#define LT_INTERLANE_ALIGN_DONE		BIT(3)
+#define LT_CHANNEL0_EQ_BITS		(DP_CHANNEL_EQ_BITS)
+#define DP0_SNKLTCHGREQ		0x06d4
+#define DP0_LTLOOPCTRL		0x06d8
+#define DP0_SNKLTCTRL		0x06e4
+
+/* PHY */
+#define DP_PHY_CTRL		0x0800
+#define DP_PHY_RST			BIT(28)  /* DP PHY Global Soft Reset */
+#define BGREN				BIT(25)  /* AUX PHY BGR Enable */
+#define PWR_SW_EN			BIT(24)  /* PHY Power Switch Enable */
+#define PHY_M1_RST			BIT(12)  /* Reset PHY1 Main Channel */
+#define PHY_RDY				BIT(16)  /* PHY Main Channels Ready */
+#define PHY_M0_RST			BIT(8)   /* Reset PHY0 Main Channel */
+#define PHY_A0_EN			BIT(1)   /* PHY Aux Channel0 Enable */
+#define PHY_M0_EN			BIT(0)   /* PHY Main Channel0 Enable */
+
+/* PLL */
+#define DP0_PLLCTRL		0x0900
+#define DP1_PLLCTRL		0x0904	/* not defined in DS */
+#define PXL_PLLCTRL		0x0908
+#define PLLUPDATE			BIT(2)
+#define PLLBYP				BIT(1)
+#define PLLEN				BIT(0)
+#define PXL_PLLPARAM		0x0914
+#define IN_SEL_REFCLK			(0 << 14)
+#define SYS_PLLPARAM		0x0918
+#define REF_FREQ_38M4			(0 << 8) /* 38.4 MHz */
+#define REF_FREQ_19M2			(1 << 8) /* 19.2 MHz */
+#define REF_FREQ_26M			(2 << 8) /* 26 MHz */
+#define REF_FREQ_13M			(3 << 8) /* 13 MHz */
+#define SYSCLK_SEL_LSCLK		(0 << 4)
+#define LSCLK_DIV_1			(0 << 0)
+#define LSCLK_DIV_2			(1 << 0)
+
+/* Test & Debug */
+#define TSTCTL			0x0a00
+#define PLL_DBG			0x0a04
+
+static bool tc_test_pattern;
+module_param_named(test, tc_test_pattern, bool, 0644);
+
+struct tc_edp_link {
+	struct drm_dp_link	base;
+	u8			assr;
+	int			scrambler_dis;
+	int			spread;
+	int			coding8b10b;
+	u8			swing;
+	u8			preemp;
+};
+
+struct tc_data {
+	struct device		*dev;
+	struct regmap		*regmap;
+	struct drm_dp_aux	aux;
+
+	struct drm_bridge	bridge;
+	struct drm_connector	connector;
+	struct drm_panel	*panel;
+
+	/* link settings */
+	struct tc_edp_link	link;
+
+	/* display edid */
+	struct edid		*edid;
+	/* current mode */
+	struct drm_display_mode	*mode;
+
+	u32			rev;
+	u8			assr;
+
+	struct gpio_desc	*sd_gpio;
+	struct gpio_desc	*reset_gpio;
+	struct clk		*refclk;
+};
+
+static inline struct tc_data *aux_to_tc(struct drm_dp_aux *a)
+{
+	return container_of(a, struct tc_data, aux);
+}
+
+static inline struct tc_data *bridge_to_tc(struct drm_bridge *b)
+{
+	return container_of(b, struct tc_data, bridge);
+}
+
+static inline struct tc_data *connector_to_tc(struct drm_connector *c)
+{
+	return container_of(c, struct tc_data, connector);
+}
+
+/* Simple macros to avoid repeated error checks */
+#define tc_write(reg, var)					\
+	do {							\
+		ret = regmap_write(tc->regmap, reg, var);	\
+		if (ret)					\
+			goto err;				\
+	} while (0)
+#define tc_read(reg, var)					\
+	do {							\
+		ret = regmap_read(tc->regmap, reg, var);	\
+		if (ret)					\
+			goto err;				\
+	} while (0)
+
+static inline int tc_poll_timeout(struct regmap *map, unsigned int addr,
+				  unsigned int cond_mask,
+				  unsigned int cond_value,
+				  unsigned long sleep_us, u64 timeout_us)
+{
+	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us);
+	unsigned int val;
+	int ret;
+
+	for (;;) {
+		ret = regmap_read(map, addr, &val);
+		if (ret)
+			break;
+		if ((val & cond_mask) == cond_value)
+			break;
+		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) {
+			ret = regmap_read(map, addr, &val);
+			break;
+		}
+		if (sleep_us)
+			usleep_range((sleep_us >> 2) + 1, sleep_us);
+	}
+	return ret ?: (((val & cond_mask) == cond_value) ? 0 : -ETIMEDOUT);
+}
+
+static int tc_aux_wait_busy(struct tc_data *tc, unsigned int timeout_ms)
+{
+	return tc_poll_timeout(tc->regmap, DP0_AUXSTATUS, AUX_BUSY, 0,
+			       1000, 1000 * timeout_ms);
+}
+
+static int tc_aux_get_status(struct tc_data *tc, u8 *reply)
+{
+	int ret;
+	u32 value;
+
+	ret = regmap_read(tc->regmap, DP0_AUXSTATUS, &value);
+	if (ret < 0)
+		return ret;
+	if (value & AUX_BUSY) {
+		if (value & AUX_TIMEOUT) {
+			dev_err(tc->dev, "i2c access timeout!\n");
+			return -ETIMEDOUT;
+		}
+		return -EBUSY;
+	}
+
+	*reply = (value & AUX_STATUS_MASK) >> AUX_STATUS_SHIFT;
+	return 0;
+}
+
+static ssize_t tc_aux_transfer(struct drm_dp_aux *aux,
+			       struct drm_dp_aux_msg *msg)
+{
+	struct tc_data *tc = aux_to_tc(aux);
+	size_t size = min_t(size_t, 8, msg->size);
+	u8 request = msg->request & ~DP_AUX_I2C_MOT;
+	u8 *buf = msg->buffer;
+	u32 tmp = 0;
+	int i = 0;
+	int ret;
+
+	if (size == 0)
+		return 0;
+
+	ret = tc_aux_wait_busy(tc, 100);
+	if (ret)
+		goto err;
+
+	if (request == DP_AUX_I2C_WRITE || request == DP_AUX_NATIVE_WRITE) {
+		/* Store data */
+		while (i < size) {
+			if (request == DP_AUX_NATIVE_WRITE)
+				tmp = tmp | (buf[i] << (8 * (i & 0x3)));
+			else
+				tmp = (tmp << 8) | buf[i];
+			i++;
+			if (((i % 4) == 0) || (i == size)) {
+				tc_write(DP0_AUXWDATA(i >> 2), tmp);
+				tmp = 0;
+			}
+		}
+	} else if (request != DP_AUX_I2C_READ &&
+		   request != DP_AUX_NATIVE_READ) {
+		return -EINVAL;
+	}
+
+	/* Store address */
+	tc_write(DP0_AUXADDR, msg->address);
+	/* Start transfer */
+	tc_write(DP0_AUXCFG0, ((size - 1) << 8) | request);
+
+	ret = tc_aux_wait_busy(tc, 100);
+	if (ret)
+		goto err;
+
+	ret = tc_aux_get_status(tc, &msg->reply);
+	if (ret)
+		goto err;
+
+	if (request == DP_AUX_I2C_READ || request == DP_AUX_NATIVE_READ) {
+		/* Read data */
+		while (i < size) {
+			if ((i % 4) == 0)
+				tc_read(DP0_AUXRDATA(i >> 2), &tmp);
+			buf[i] = tmp & 0xff;
+			tmp = tmp >> 8;
+			i++;
+		}
+	}
+
+	return size;
+err:
+	return ret;
+}
+
+static const char * const training_pattern1_errors[] = {
+	"No errors",
+	"Aux write error",
+	"Aux read error",
+	"Max voltage reached error",
+	"Loop counter expired error",
+	"res", "res", "res"
+};
+
+static const char * const training_pattern2_errors[] = {
+	"No errors",
+	"Aux write error",
+	"Aux read error",
+	"Clock recovery failed error",
+	"Loop counter expired error",
+	"res", "res", "res"
+};
+
+static u32 tc_srcctrl(struct tc_data *tc)
+{
+	/*
+	 * No training pattern, skew lane 1 data by two LSCLK cycles with
+	 * respect to lane 0 data, AutoCorrect Mode = 0
+	 */
+	u32 reg = DP0_SRCCTRL_NOTP | DP0_SRCCTRL_LANESKEW;
+
+	if (tc->link.scrambler_dis)
+		reg |= DP0_SRCCTRL_SCRMBLDIS;	/* Scrambler Disabled */
+	if (tc->link.coding8b10b)
+		/* Enable 8/10B Encoder (TxData[19:16] not used) */
+		reg |= DP0_SRCCTRL_EN810B;
+	if (tc->link.spread)
+		reg |= DP0_SRCCTRL_SSCG;	/* Spread Spectrum Enable */
+	if (tc->link.base.num_lanes == 2)
+		reg |= DP0_SRCCTRL_LANES_2;	/* Two Main Channel Lanes */
+	if (tc->link.base.rate != 162000)
+		reg |= DP0_SRCCTRL_BW27;	/* 2.7 Gbps link */
+	return reg;
+}
+
+static void tc_wait_pll_lock(struct tc_data *tc)
+{
+	/* Wait for PLL to lock: up to 2.09 ms, depending on refclk */
+	usleep_range(3000, 6000);
+}
+
+static int tc_pxl_pll_en(struct tc_data *tc, u32 refclk, u32 pixelclock)
+{
+	int ret;
+	int i_pre, best_pre = 1;
+	int i_post, best_post = 1;
+	int div, best_div = 1;
+	int mul, best_mul = 1;
+	int delta, best_delta;
+	int ext_div[] = {1, 2, 3, 5, 7};
+	int best_pixelclock = 0;
+	int vco_hi = 0;
+
+	dev_dbg(tc->dev, "PLL: requested %d pixelclock, ref %d\n", pixelclock,
+		refclk);
+	best_delta = pixelclock;
+	/* Loop over all possible ext_divs, skipping invalid configurations */
+	for (i_pre = 0; i_pre < ARRAY_SIZE(ext_div); i_pre++) {
+		/*
+		 * refclk / ext_pre_div should be in the 1 to 200 MHz range.
+		 * We don't allow any refclk > 200 MHz, only check lower bounds.
+		 */
+		if (refclk / ext_div[i_pre] < 1000000)
+			continue;
+		for (i_post = 0; i_post < ARRAY_SIZE(ext_div); i_post++) {
+			for (div = 1; div <= 16; div++) {
+				u32 clk;
+				u64 tmp;
+
+				tmp = pixelclock * ext_div[i_pre] *
+				      ext_div[i_post] * div;
+				do_div(tmp, refclk);
+				mul = tmp;
+
+				/* Check limits */
+				if ((mul < 1) || (mul > 128))
+					continue;
+
+				clk = (refclk / ext_div[i_pre] / div) * mul;
+				/*
+				 * refclk * mul / (ext_pre_div * pre_div)
+				 * should be in the 150 to 650 MHz range
+				 */
+				if ((clk > 650000000) || (clk < 150000000))
+					continue;
+
+				clk = clk / ext_div[i_post];
+				delta = clk - pixelclock;
+
+				if (abs(delta) < abs(best_delta)) {
+					best_pre = i_pre;
+					best_post = i_post;
+					best_div = div;
+					best_mul = mul;
+					best_delta = delta;
+					best_pixelclock = clk;
+				}
+			}
+		}
+	}
+	if (best_pixelclock == 0) {
+		dev_err(tc->dev, "Failed to calc clock for %d pixelclock\n",
+			pixelclock);
+		return -EINVAL;
+	}
+
+	dev_dbg(tc->dev, "PLL: got %d, delta %d\n", best_pixelclock,
+		best_delta);
+	dev_dbg(tc->dev, "PLL: %d / %d / %d * %d / %d\n", refclk,
+		ext_div[best_pre], best_div, best_mul, ext_div[best_post]);
+
+	/* if VCO >= 300 MHz */
+	if (refclk / ext_div[best_pre] / best_div * best_mul >= 300000000)
+		vco_hi = 1;
+	/* see DS */
+	if (best_div == 16)
+		best_div = 0;
+	if (best_mul == 128)
+		best_mul = 0;
+
+	/* Power up PLL and switch to bypass */
+	tc_write(PXL_PLLCTRL, PLLBYP | PLLEN);
+
+	tc_write(PXL_PLLPARAM,
+		 (vco_hi << 24) |		/* For PLL VCO >= 300 MHz = 1 */
+		 (ext_div[best_pre] << 20) |	/* External Pre-divider */
+		 (ext_div[best_post] << 16) |	/* External Post-divider */
+		 IN_SEL_REFCLK |		/* Use RefClk as PLL input */
+		 (best_div << 8) |		/* Divider for PLL RefClk */
+		 (best_mul << 0));		/* Multiplier for PLL */
+
+	/* Force PLL parameter update and disable bypass */
+	tc_write(PXL_PLLCTRL, PLLUPDATE | PLLEN);
+
+	tc_wait_pll_lock(tc);
+
+	return 0;
+err:
+	return ret;
+}
+
+static int tc_pxl_pll_dis(struct tc_data *tc)
+{
+	/* Enable PLL bypass, power down PLL */
+	return regmap_write(tc->regmap, PXL_PLLCTRL, PLLBYP);
+}
+
+static int tc_stream_clock_calc(struct tc_data *tc)
+{
+	int ret;
+	/*
+	 * If the Stream clock and Link Symbol clock are
+	 * asynchronous with each other, the value of M changes over
+	 * time. This way of generating link clock and stream
+	 * clock is called Asynchronous Clock mode. The value M
+	 * must change while the value N stays constant. The
+	 * value of N in this Asynchronous Clock mode must be set
+	 * to 2^15 or 32,768.
+	 *
+	 * LSCLK = 1/10 of high speed link clock
+	 *
+	 * f_STRMCLK = M/N * f_LSCLK
+	 * M/N = f_STRMCLK / f_LSCLK
+	 *
+	 */
+	tc_write(DP0_VIDMNGEN1, 32768);
+
+	return 0;
+err:
+	return ret;
+}
+
+static int tc_aux_link_setup(struct tc_data *tc)
+{
+	unsigned long rate;
+	u32 value;
+	int ret;
+
+	rate = clk_get_rate(tc->refclk);
+	switch (rate) {
+	case 38400000:
+		value = REF_FREQ_38M4;
+		break;
+	case 26000000:
+		value = REF_FREQ_26M;
+		break;
+	case 19200000:
+		value = REF_FREQ_19M2;
+		break;
+	case 13000000:
+		value = REF_FREQ_13M;
+		break;
+	default:
+		dev_err(tc->dev, "Invalid refclk rate: %lu Hz\n", rate);
+		return -EINVAL;
+	}
+
+	/* Setup DP-PHY / PLL */
+	value |= SYSCLK_SEL_LSCLK | LSCLK_DIV_2;
+	tc_write(SYS_PLLPARAM, value);
+
+	tc_write(DP_PHY_CTRL, BGREN | PWR_SW_EN | BIT(2) | PHY_A0_EN);
+
+	/*
+	 * Initially PLLs are in bypass. Force PLL parameter update,
+	 * disable PLL bypass, enable PLL
+	 */
+	tc_write(DP0_PLLCTRL, PLLUPDATE | PLLEN);
+	tc_wait_pll_lock(tc);
+
+	tc_write(DP1_PLLCTRL, PLLUPDATE | PLLEN);
+	tc_wait_pll_lock(tc);
+
+	ret = tc_poll_timeout(tc->regmap, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1,
+			      1000);
+	if (ret == -ETIMEDOUT) {
+		dev_err(tc->dev, "Timeout waiting for PHY to become ready");
+		return ret;
+	} else if (ret)
+		goto err;
+
+	/* Setup AUX link */
+	tc_write(DP0_AUXCFG1, AUX_RX_FILTER_EN |
+		 (0x06 << 8) |	/* Aux Bit Period Calculator Threshold */
+		 (0x3f << 0));	/* Aux Response Timeout Timer */
+
+	return 0;
+err:
+	dev_err(tc->dev, "tc_aux_link_setup failed: %d\n", ret);
+	return ret;
+}
+
+static int tc_get_display_props(struct tc_data *tc)
+{
+	int ret;
+	/* temp buffer */
+	u8 tmp[8];
+
+	/* Read DP Rx Link Capability */
+	ret = drm_dp_link_probe(&tc->aux, &tc->link.base);
+	if (ret < 0)
+		goto err_dpcd_read;
+	if ((tc->link.base.rate != 162000) && (tc->link.base.rate != 270000))
+		goto err_dpcd_inval;
+
+	ret = drm_dp_dpcd_readb(&tc->aux, DP_MAX_DOWNSPREAD, tmp);
+	if (ret < 0)
+		goto err_dpcd_read;
+	tc->link.spread = tmp[0] & BIT(0); /* 0.5% down spread */
+
+	ret = drm_dp_dpcd_readb(&tc->aux, DP_MAIN_LINK_CHANNEL_CODING, tmp);
+	if (ret < 0)
+		goto err_dpcd_read;
+	tc->link.coding8b10b = tmp[0] & BIT(0);
+	tc->link.scrambler_dis = 0;
+	/* read assr */
+	ret = drm_dp_dpcd_readb(&tc->aux, DP_EDP_CONFIGURATION_SET, tmp);
+	if (ret < 0)
+		goto err_dpcd_read;
+	tc->link.assr = tmp[0] & DP_ALTERNATE_SCRAMBLER_RESET_ENABLE;
+
+	dev_dbg(tc->dev, "DPCD rev: %d.%d, rate: %s, lanes: %d, framing: %s\n",
+		tc->link.base.revision >> 4, tc->link.base.revision & 0x0f,
+		(tc->link.base.rate == 162000) ? "1.62Gbps" : "2.7Gbps",
+		tc->link.base.num_lanes,
+		(tc->link.base.capabilities & DP_LINK_CAP_ENHANCED_FRAMING) ?
+		"enhanced" : "non-enhanced");
+	dev_dbg(tc->dev, "ANSI 8B/10B: %d\n", tc->link.coding8b10b);
+	dev_dbg(tc->dev, "Display ASSR: %d, TC358767 ASSR: %d\n",
+		tc->link.assr, tc->assr);
+
+	return 0;
+
+err_dpcd_read:
+	dev_err(tc->dev, "failed to read DPCD: %d\n", ret);
+	return ret;
+err_dpcd_inval:
+	dev_err(tc->dev, "invalid DPCD\n");
+	return -EINVAL;
+}
+
+static int tc_set_video_mode(struct tc_data *tc, struct drm_display_mode *mode)
+{
+	int ret;
+	int vid_sync_dly;
+	int max_tu_symbol;
+
+	int left_margin = mode->htotal - mode->hsync_end;
+	int right_margin = mode->hsync_start - mode->hdisplay;
+	int hsync_len = mode->hsync_end - mode->hsync_start;
+	int upper_margin = mode->vtotal - mode->vsync_end;
+	int lower_margin = mode->vsync_start - mode->vdisplay;
+	int vsync_len = mode->vsync_end - mode->vsync_start;
+
+	dev_dbg(tc->dev, "set mode %dx%d\n",
+		mode->hdisplay, mode->vdisplay);
+	dev_dbg(tc->dev, "H margin %d,%d sync %d\n",
+		left_margin, right_margin, hsync_len);
+	dev_dbg(tc->dev, "V margin %d,%d sync %d\n",
+		upper_margin, lower_margin, vsync_len);
+	dev_dbg(tc->dev, "total: %dx%d\n", mode->htotal, mode->vtotal);
+
+
+	/* LCD Ctl Frame Size */
+	tc_write(VPCTRL0, (0x40 << 20) /* VSDELAY */ |
+		 OPXLFMT_RGB888 | FRMSYNC_DISABLED | MSF_DISABLED);
+	tc_write(HTIM01, (left_margin << 16) |		/* H back porch */
+			 (hsync_len << 0));		/* Hsync */
+	tc_write(HTIM02, (right_margin << 16) |		/* H front porch */
+			 (mode->hdisplay << 0));	/* width */
+	tc_write(VTIM01, (upper_margin << 16) |		/* V back porch */
+			 (vsync_len << 0));		/* Vsync */
+	tc_write(VTIM02, (lower_margin << 16) |		/* V front porch */
+			 (mode->vdisplay << 0));	/* height */
+	tc_write(VFUEN0, VFUEN);		/* update settings */
+
+	/* Test pattern settings */
+	tc_write(TSTCTL,
+		 (120 << 24) |	/* Red Color component value */
+		 (20 << 16) |	/* Green Color component value */
+		 (99 << 8) |	/* Blue Color component value */
+		 (1 << 4) |	/* Enable I2C Filter */
+		 (2 << 0) |	/* Color bar Mode */
+		 0);
+
+	/* DP Main Stream Attributes */
+	vid_sync_dly = hsync_len + left_margin + mode->hdisplay;
+	tc_write(DP0_VIDSYNCDELAY,
+		 (0x003e << 16) |	/* thresh_dly */
+		 (vid_sync_dly << 0));
+
+	tc_write(DP0_TOTALVAL, (mode->vtotal << 16) | (mode->htotal));
+
+	tc_write(DP0_STARTVAL,
+		 ((upper_margin + vsync_len) << 16) |
+		 ((left_margin + hsync_len) << 0));
+
+	tc_write(DP0_ACTIVEVAL, (mode->vdisplay << 16) | (mode->hdisplay));
+
+	tc_write(DP0_SYNCVAL, (vsync_len << 16) | (hsync_len << 0));
+
+	tc_write(DPIPXLFMT, VS_POL_ACTIVE_LOW | HS_POL_ACTIVE_LOW |
+		 DE_POL_ACTIVE_HIGH | SUB_CFG_TYPE_CONFIG1 | DPI_BPP_RGB888);
+
+	/*
+	 * Recommended maximum number of symbols transferred in a transfer unit:
+	 * DIV_ROUND_UP((input active video bandwidth in bytes) * tu_size,
+	 *              (output active video bandwidth in bytes))
+	 * Must be less than tu_size.
+	 */
+	max_tu_symbol = TU_SIZE_RECOMMENDED - 1;
+	tc_write(DP0_MISC, (max_tu_symbol << 23) | TU_SIZE_RECOMMENDED | BPC_8);
+
+	return 0;
+err:
+	return ret;
+}
+
+static int tc_link_training(struct tc_data *tc, int pattern)
+{
+	const char * const *errors;
+	u32 srcctrl = tc_srcctrl(tc) | DP0_SRCCTRL_SCRMBLDIS |
+		      DP0_SRCCTRL_AUTOCORRECT;
+	int timeout;
+	int retry;
+	u32 value;
+	int ret;
+
+	if (pattern == DP_TRAINING_PATTERN_1) {
+		srcctrl |= DP0_SRCCTRL_TP1;
+		errors = training_pattern1_errors;
+	} else {
+		srcctrl |= DP0_SRCCTRL_TP2;
+		errors = training_pattern2_errors;
+	}
+
+	/* Set DPCD 0x102 for Training Part 1 or 2 */
+	tc_write(DP0_SNKLTCTRL, DP_LINK_SCRAMBLING_DISABLE | pattern);
+
+	tc_write(DP0_LTLOOPCTRL,
+		 (0x0f << 28) |	/* Defer Iteration Count */
+		 (0x0f << 24) |	/* Loop Iteration Count */
+		 (0x0d << 0));	/* Loop Timer Delay */
+
+	retry = 5;
+	do {
+		/* Set DP0 Training Pattern */
+		tc_write(DP0_SRCCTRL, srcctrl);
+
+		/* Enable DP0 to start Link Training */
+		tc_write(DP0CTL, DP_EN);
+
+		/* wait */
+		timeout = 1000;
+		do {
+			tc_read(DP0_LTSTAT, &value);
+			udelay(1);
+		} while ((!(value & LT_LOOPDONE)) && (--timeout));
+		if (timeout == 0) {
+			dev_err(tc->dev, "Link training timeout!\n");
+		} else {
+			int pattern = (value >> 11) & 0x3;
+			int error = (value >> 8) & 0x7;
+
+			dev_dbg(tc->dev,
+				"Link training phase %d done after %d uS: %s\n",
+				pattern, 1000 - timeout, errors[error]);
+			if (pattern == DP_TRAINING_PATTERN_1 && error == 0)
+				break;
+			if (pattern == DP_TRAINING_PATTERN_2) {
+				value &= LT_CHANNEL1_EQ_BITS |
+					 LT_INTERLANE_ALIGN_DONE |
+					 LT_CHANNEL0_EQ_BITS;
+				/* in case of two lanes */
+				if ((tc->link.base.num_lanes == 2) &&
+				    (value == (LT_CHANNEL1_EQ_BITS |
+					       LT_INTERLANE_ALIGN_DONE |
+					       LT_CHANNEL0_EQ_BITS)))
+					break;
+				/* in case of one line */
+				if ((tc->link.base.num_lanes == 1) &&
+				    (value == (LT_INTERLANE_ALIGN_DONE |
+					       LT_CHANNEL0_EQ_BITS)))
+					break;
+			}
+		}
+		/* restart */
+		tc_write(DP0CTL, 0);
+		usleep_range(10, 20);
+	} while (--retry);
+	if (retry == 0) {
+		dev_err(tc->dev, "Failed to finish training phase %d\n",
+			pattern);
+	}
+
+	return 0;
+err:
+	return ret;
+}
+
+static int tc_main_link_setup(struct tc_data *tc)
+{
+	struct drm_dp_aux *aux = &tc->aux;
+	struct device *dev = tc->dev;
+	unsigned int rate;
+	u32 dp_phy_ctrl;
+	int timeout;
+	bool aligned;
+	bool ready;
+	u32 value;
+	int ret;
+	u8 tmp[8];
+
+	/* display mode should be set at this point */
+	if (!tc->mode)
+		return -EINVAL;
+
+	/* from excel file - DP0_SrcCtrl */
+	tc_write(DP0_SRCCTRL, DP0_SRCCTRL_SCRMBLDIS | DP0_SRCCTRL_EN810B |
+		 DP0_SRCCTRL_LANESKEW | DP0_SRCCTRL_LANES_2 |
+		 DP0_SRCCTRL_BW27 | DP0_SRCCTRL_AUTOCORRECT);
+	/* from excel file - DP1_SrcCtrl */
+	tc_write(0x07a0, 0x00003083);
+
+	rate = clk_get_rate(tc->refclk);
+	switch (rate) {
+	case 38400000:
+		value = REF_FREQ_38M4;
+		break;
+	case 26000000:
+		value = REF_FREQ_26M;
+		break;
+	case 19200000:
+		value = REF_FREQ_19M2;
+		break;
+	case 13000000:
+		value = REF_FREQ_13M;
+		break;
+	default:
+		return -EINVAL;
+	}
+	value |= SYSCLK_SEL_LSCLK | LSCLK_DIV_2;
+	tc_write(SYS_PLLPARAM, value);
+	/* Setup Main Link */
+	dp_phy_ctrl = BGREN | PWR_SW_EN | BIT(2) | PHY_A0_EN |  PHY_M0_EN;
+	tc_write(DP_PHY_CTRL, dp_phy_ctrl);
+	msleep(100);
+
+	/* PLL setup */
+	tc_write(DP0_PLLCTRL, PLLUPDATE | PLLEN);
+	tc_wait_pll_lock(tc);
+
+	tc_write(DP1_PLLCTRL, PLLUPDATE | PLLEN);
+	tc_wait_pll_lock(tc);
+
+	/* PXL PLL setup */
+	if (tc_test_pattern) {
+		ret = tc_pxl_pll_en(tc, clk_get_rate(tc->refclk),
+				    1000 * tc->mode->clock);
+		if (ret)
+			goto err;
+	}
+
+	/* Reset/Enable Main Links */
+	dp_phy_ctrl |= DP_PHY_RST | PHY_M1_RST | PHY_M0_RST;
+	tc_write(DP_PHY_CTRL, dp_phy_ctrl);
+	usleep_range(100, 200);
+	dp_phy_ctrl &= ~(DP_PHY_RST | PHY_M1_RST | PHY_M0_RST);
+	tc_write(DP_PHY_CTRL, dp_phy_ctrl);
+
+	timeout = 1000;
+	do {
+		tc_read(DP_PHY_CTRL, &value);
+		udelay(1);
+	} while ((!(value & PHY_RDY)) && (--timeout));
+
+	if (timeout == 0) {
+		dev_err(dev, "timeout waiting for phy become ready");
+		return -ETIMEDOUT;
+	}
+
+	/* Set misc: 8 bits per color */
+	ret = regmap_update_bits(tc->regmap, DP0_MISC, BPC_8, BPC_8);
+	if (ret)
+		goto err;
+
+	/*
+	 * ASSR mode
+	 * on TC358767 side ASSR configured through strap pin
+	 * seems there is no way to change this setting from SW
+	 *
+	 * check is tc configured for same mode
+	 */
+	if (tc->assr != tc->link.assr) {
+		dev_dbg(dev, "Trying to set display to ASSR: %d\n",
+			tc->assr);
+		/* try to set ASSR on display side */
+		tmp[0] = tc->assr;
+		ret = drm_dp_dpcd_writeb(aux, DP_EDP_CONFIGURATION_SET, tmp[0]);
+		if (ret < 0)
+			goto err_dpcd_read;
+		/* read back */
+		ret = drm_dp_dpcd_readb(aux, DP_EDP_CONFIGURATION_SET, tmp);
+		if (ret < 0)
+			goto err_dpcd_read;
+
+		if (tmp[0] != tc->assr) {
+			dev_warn(dev, "Failed to switch display ASSR to %d, falling back to unscrambled mode\n",
+				 tc->assr);
+			/* trying with disabled scrambler */
+			tc->link.scrambler_dis = 1;
+		}
+	}
+
+	/* Setup Link & DPRx Config for Training */
+	ret = drm_dp_link_configure(aux, &tc->link.base);
+	if (ret < 0)
+		goto err_dpcd_write;
+
+	/* DOWNSPREAD_CTRL */
+	tmp[0] = tc->link.spread ? DP_SPREAD_AMP_0_5 : 0x00;
+	/* MAIN_LINK_CHANNEL_CODING_SET */
+	tmp[1] =  tc->link.coding8b10b ? DP_SET_ANSI_8B10B : 0x00;
+	ret = drm_dp_dpcd_write(aux, DP_DOWNSPREAD_CTRL, tmp, 2);
+	if (ret < 0)
+		goto err_dpcd_write;
+
+	ret = tc_link_training(tc, DP_TRAINING_PATTERN_1);
+	if (ret)
+		goto err;
+
+	ret = tc_link_training(tc, DP_TRAINING_PATTERN_2);
+	if (ret)
+		goto err;
+
+	/* Clear DPCD 0x102 */
+	/* Note: Can Not use DP0_SNKLTCTRL (0x06E4) short cut */
+	tmp[0] = tc->link.scrambler_dis ? DP_LINK_SCRAMBLING_DISABLE : 0x00;
+	ret = drm_dp_dpcd_writeb(aux, DP_TRAINING_PATTERN_SET, tmp[0]);
+	if (ret < 0)
+		goto err_dpcd_write;
+
+	/* Clear Training Pattern, set AutoCorrect Mode = 1 */
+	tc_write(DP0_SRCCTRL, tc_srcctrl(tc) | DP0_SRCCTRL_AUTOCORRECT);
+
+	/* Wait */
+	timeout = 100;
+	do {
+		udelay(1);
+		/* Read DPCD 0x202-0x207 */
+		ret = drm_dp_dpcd_read_link_status(aux, tmp + 2);
+		if (ret < 0)
+			goto err_dpcd_read;
+		ready = (tmp[2] == ((DP_CHANNEL_EQ_BITS << 4) | /* Lane1 */
+				     DP_CHANNEL_EQ_BITS));      /* Lane0 */
+		aligned = tmp[4] & DP_INTERLANE_ALIGN_DONE;
+	} while ((--timeout) && !(ready && aligned));
+
+	if (timeout == 0) {
+		/* Read DPCD 0x200-0x201 */
+		ret = drm_dp_dpcd_read(aux, DP_SINK_COUNT, tmp, 2);
+		if (ret < 0)
+			goto err_dpcd_read;
+		dev_info(dev, "0x0200 SINK_COUNT: 0x%02x\n", tmp[0]);
+		dev_info(dev, "0x0201 DEVICE_SERVICE_IRQ_VECTOR: 0x%02x\n",
+			 tmp[1]);
+		dev_info(dev, "0x0202 LANE0_1_STATUS: 0x%02x\n", tmp[2]);
+		dev_info(dev, "0x0204 LANE_ALIGN_STATUS_UPDATED: 0x%02x\n",
+			 tmp[4]);
+		dev_info(dev, "0x0205 SINK_STATUS: 0x%02x\n", tmp[5]);
+		dev_info(dev, "0x0206 ADJUST_REQUEST_LANE0_1: 0x%02x\n",
+			 tmp[6]);
+
+		if (!ready)
+			dev_err(dev, "Lane0/1 not ready\n");
+		if (!aligned)
+			dev_err(dev, "Lane0/1 not aligned\n");
+		return -EAGAIN;
+	}
+
+	ret = tc_set_video_mode(tc, tc->mode);
+	if (ret)
+		goto err;
+
+	/* Set M/N */
+	ret = tc_stream_clock_calc(tc);
+	if (ret)
+		goto err;
+
+	return 0;
+err_dpcd_read:
+	dev_err(tc->dev, "Failed to read DPCD: %d\n", ret);
+	return ret;
+err_dpcd_write:
+	dev_err(tc->dev, "Failed to write DPCD: %d\n", ret);
+err:
+	return ret;
+}
+
+static int tc_main_link_stream(struct tc_data *tc, int state)
+{
+	int ret;
+	u32 value;
+
+	dev_dbg(tc->dev, "stream: %d\n", state);
+
+	if (state) {
+		value = VID_MN_GEN | DP_EN;
+		if (tc->link.base.capabilities & DP_LINK_CAP_ENHANCED_FRAMING)
+			value |= EF_EN;
+		tc_write(DP0CTL, value);
+		/*
+		 * VID_EN assertion should be delayed by at least N * LSCLK
+		 * cycles from the time VID_MN_GEN is enabled in order to
+		 * generate stable values for VID_M. LSCLK is 270 MHz or
+		 * 162 MHz, VID_N is set to 32768 in  tc_stream_clock_calc(),
+		 * so a delay of at least 203 us should suffice.
+		 */
+		usleep_range(500, 1000);
+		value |= VID_EN;
+		tc_write(DP0CTL, value);
+		/* Set input interface */
+		value = DP0_AUDSRC_NO_INPUT;
+		if (tc_test_pattern)
+			value |= DP0_VIDSRC_COLOR_BAR;
+		else
+			value |= DP0_VIDSRC_DPI_RX;
+		tc_write(SYSCTRL, value);
+	} else {
+		tc_write(DP0CTL, 0);
+	}
+
+	return 0;
+err:
+	return ret;
+}
+
+static enum drm_connector_status
+tc_connector_detect(struct drm_connector *connector, bool force)
+{
+	return connector_status_connected;
+}
+
+static void tc_bridge_pre_enable(struct drm_bridge *bridge)
+{
+	struct tc_data *tc = bridge_to_tc(bridge);
+
+	drm_panel_prepare(tc->panel);
+}
+
+static void tc_bridge_enable(struct drm_bridge *bridge)
+{
+	struct tc_data *tc = bridge_to_tc(bridge);
+	int ret;
+
+	ret = tc_main_link_setup(tc);
+	if (ret < 0) {
+		dev_err(tc->dev, "main link setup error: %d\n", ret);
+		return;
+	}
+
+	ret = tc_main_link_stream(tc, 1);
+	if (ret < 0) {
+		dev_err(tc->dev, "main link stream start error: %d\n", ret);
+		return;
+	}
+
+	drm_panel_enable(tc->panel);
+}
+
+static void tc_bridge_disable(struct drm_bridge *bridge)
+{
+	struct tc_data *tc = bridge_to_tc(bridge);
+	int ret;
+
+	drm_panel_disable(tc->panel);
+
+	ret = tc_main_link_stream(tc, 0);
+	if (ret < 0)
+		dev_err(tc->dev, "main link stream stop error: %d\n", ret);
+}
+
+static void tc_bridge_post_disable(struct drm_bridge *bridge)
+{
+	struct tc_data *tc = bridge_to_tc(bridge);
+
+	drm_panel_unprepare(tc->panel);
+}
+
+static bool tc_bridge_mode_fixup(struct drm_bridge *bridge,
+				 const struct drm_display_mode *mode,
+				 struct drm_display_mode *adj)
+{
+	/* Fixup sync polarities, both hsync and vsync are active low */
+	adj->flags = mode->flags;
+	adj->flags |= (DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC);
+	adj->flags &= ~(DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC);
+
+	return true;
+}
+
+static int tc_connector_mode_valid(struct drm_connector *connector,
+				   struct drm_display_mode *mode)
+{
+	/* Accept any mode */
+	return MODE_OK;
+}
+
+static void tc_bridge_mode_set(struct drm_bridge *bridge,
+			       struct drm_display_mode *mode,
+			       struct drm_display_mode *adj)
+{
+	struct tc_data *tc = bridge_to_tc(bridge);
+
+	tc->mode = mode;
+}
+
+static int tc_connector_get_modes(struct drm_connector *connector)
+{
+	struct tc_data *tc = connector_to_tc(connector);
+	struct edid *edid;
+	unsigned int count;
+
+	if (tc->panel && tc->panel->funcs && tc->panel->funcs->get_modes) {
+		count = tc->panel->funcs->get_modes(tc->panel);
+		if (count > 0)
+			return count;
+	}
+
+	edid = drm_get_edid(connector, &tc->aux.ddc);
+
+	kfree(tc->edid);
+	tc->edid = edid;
+	if (!edid)
+		return 0;
+
+	drm_mode_connector_update_edid_property(connector, edid);
+	count = drm_add_edid_modes(connector, edid);
+
+	return count;
+}
+
+static void tc_connector_set_polling(struct tc_data *tc,
+				     struct drm_connector *connector)
+{
+	/* TODO: add support for HPD */
+	connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+			    DRM_CONNECTOR_POLL_DISCONNECT;
+}
+
+static struct drm_encoder *
+tc_connector_best_encoder(struct drm_connector *connector)
+{
+	struct tc_data *tc = connector_to_tc(connector);
+
+	return tc->bridge.encoder;
+}
+
+static const struct drm_connector_helper_funcs tc_connector_helper_funcs = {
+	.get_modes = tc_connector_get_modes,
+	.mode_valid = tc_connector_mode_valid,
+	.best_encoder = tc_connector_best_encoder,
+};
+
+static void tc_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_funcs tc_connector_funcs = {
+	.dpms = drm_atomic_helper_connector_dpms,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.detect = tc_connector_detect,
+	.destroy = tc_connector_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static int tc_bridge_attach(struct drm_bridge *bridge)
+{
+	u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+	struct tc_data *tc = bridge_to_tc(bridge);
+	struct drm_device *drm = bridge->dev;
+	int ret;
+
+	/* Create eDP connector */
+	drm_connector_helper_add(&tc->connector, &tc_connector_helper_funcs);
+	ret = drm_connector_init(drm, &tc->connector, &tc_connector_funcs,
+				 DRM_MODE_CONNECTOR_eDP);
+	if (ret)
+		return ret;
+
+	if (tc->panel)
+		drm_panel_attach(tc->panel, &tc->connector);
+
+	drm_display_info_set_bus_formats(&tc->connector.display_info,
+					 &bus_format, 1);
+	drm_mode_connector_attach_encoder(&tc->connector, tc->bridge.encoder);
+
+	return 0;
+}
+
+static const struct drm_bridge_funcs tc_bridge_funcs = {
+	.attach = tc_bridge_attach,
+	.mode_set = tc_bridge_mode_set,
+	.pre_enable = tc_bridge_pre_enable,
+	.enable = tc_bridge_enable,
+	.disable = tc_bridge_disable,
+	.post_disable = tc_bridge_post_disable,
+	.mode_fixup = tc_bridge_mode_fixup,
+};
+
+static bool tc_readable_reg(struct device *dev, unsigned int reg)
+{
+	return reg != SYSCTRL;
+}
+
+static const struct regmap_range tc_volatile_ranges[] = {
+	regmap_reg_range(DP0_AUXWDATA(0), DP0_AUXSTATUS),
+	regmap_reg_range(DP0_LTSTAT, DP0_SNKLTCHGREQ),
+	regmap_reg_range(DP_PHY_CTRL, DP_PHY_CTRL),
+	regmap_reg_range(DP0_PLLCTRL, PXL_PLLCTRL),
+	regmap_reg_range(VFUEN0, VFUEN0),
+};
+
+static const struct regmap_access_table tc_volatile_table = {
+	.yes_ranges = tc_volatile_ranges,
+	.n_yes_ranges = ARRAY_SIZE(tc_volatile_ranges),
+};
+
+static bool tc_writeable_reg(struct device *dev, unsigned int reg)
+{
+	return (reg != TC_IDREG) &&
+	       (reg != DP0_LTSTAT) &&
+	       (reg != DP0_SNKLTCHGREQ);
+}
+
+static const struct regmap_config tc_regmap_config = {
+	.name = "tc358767",
+	.reg_bits = 16,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = PLL_DBG,
+	.cache_type = REGCACHE_RBTREE,
+	.readable_reg = tc_readable_reg,
+	.volatile_table = &tc_volatile_table,
+	.writeable_reg = tc_writeable_reg,
+	.reg_format_endian = REGMAP_ENDIAN_BIG,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE,
+};
+
+static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id)
+{
+	struct device *dev = &client->dev;
+	struct device_node *ep;
+	struct tc_data *tc;
+	int ret;
+
+	tc = devm_kzalloc(dev, sizeof(*tc), GFP_KERNEL);
+	if (!tc)
+		return -ENOMEM;
+
+	tc->dev = dev;
+
+	/* port@2 is the output port */
+	ep = of_graph_get_endpoint_by_regs(dev->of_node, 2, -1);
+	if (ep) {
+		struct device_node *remote;
+
+		remote = of_graph_get_remote_port_parent(ep);
+		if (!remote) {
+			dev_warn(dev, "endpoint %s not connected\n",
+				 ep->full_name);
+			of_node_put(ep);
+			return -ENODEV;
+		}
+		of_node_put(ep);
+		tc->panel = of_drm_find_panel(remote);
+		if (tc->panel) {
+			dev_dbg(dev, "found panel %s\n", remote->full_name);
+		} else {
+			dev_dbg(dev, "waiting for panel %s\n",
+				remote->full_name);
+			of_node_put(remote);
+			return -EPROBE_DEFER;
+		}
+		of_node_put(remote);
+	}
+
+	/* Shut down GPIO is optional */
+	tc->sd_gpio = devm_gpiod_get_optional(dev, "shutdown", GPIOD_OUT_HIGH);
+	if (IS_ERR(tc->sd_gpio))
+		return PTR_ERR(tc->sd_gpio);
+
+	if (tc->sd_gpio) {
+		gpiod_set_value_cansleep(tc->sd_gpio, 0);
+		usleep_range(5000, 10000);
+	}
+
+	/* Reset GPIO is optional */
+	tc->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(tc->reset_gpio))
+		return PTR_ERR(tc->reset_gpio);
+
+	if (tc->reset_gpio) {
+		gpiod_set_value_cansleep(tc->reset_gpio, 1);
+		usleep_range(5000, 10000);
+	}
+
+	tc->refclk = devm_clk_get(dev, "ref");
+	if (IS_ERR(tc->refclk)) {
+		ret = PTR_ERR(tc->refclk);
+		dev_err(dev, "Failed to get refclk: %d\n", ret);
+		return ret;
+	}
+
+	tc->regmap = devm_regmap_init_i2c(client, &tc_regmap_config);
+	if (IS_ERR(tc->regmap)) {
+		ret = PTR_ERR(tc->regmap);
+		dev_err(dev, "Failed to initialize regmap: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_read(tc->regmap, TC_IDREG, &tc->rev);
+	if (ret) {
+		dev_err(tc->dev, "can not read device ID: %d\n", ret);
+		return ret;
+	}
+
+	if ((tc->rev != 0x6601) && (tc->rev != 0x6603)) {
+		dev_err(tc->dev, "invalid device ID: 0x%08x\n", tc->rev);
+		return -EINVAL;
+	}
+
+	tc->assr = (tc->rev == 0x6601); /* Enable ASSR for eDP panels */
+
+	ret = tc_aux_link_setup(tc);
+	if (ret)
+		return ret;
+
+	/* Register DP AUX channel */
+	tc->aux.name = "TC358767 AUX i2c adapter";
+	tc->aux.dev = tc->dev;
+	tc->aux.transfer = tc_aux_transfer;
+	ret = drm_dp_aux_register(&tc->aux);
+	if (ret)
+		return ret;
+
+	ret = tc_get_display_props(tc);
+	if (ret)
+		goto err_unregister_aux;
+
+	tc_connector_set_polling(tc, &tc->connector);
+
+	tc->bridge.funcs = &tc_bridge_funcs;
+	tc->bridge.of_node = dev->of_node;
+	ret = drm_bridge_add(&tc->bridge);
+	if (ret) {
+		dev_err(dev, "Failed to add drm_bridge: %d\n", ret);
+		goto err_unregister_aux;
+	}
+
+	i2c_set_clientdata(client, tc);
+
+	return 0;
+err_unregister_aux:
+	drm_dp_aux_unregister(&tc->aux);
+	return ret;
+}
+
+static int tc_remove(struct i2c_client *client)
+{
+	struct tc_data *tc = i2c_get_clientdata(client);
+
+	drm_bridge_remove(&tc->bridge);
+	drm_dp_aux_unregister(&tc->aux);
+
+	tc_pxl_pll_dis(tc);
+
+	return 0;
+}
+
+static const struct i2c_device_id tc358767_i2c_ids[] = {
+	{ "tc358767", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, tc358767_i2c_ids);
+
+static const struct of_device_id tc358767_of_ids[] = {
+	{ .compatible = "toshiba,tc358767", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, tc358767_of_ids);
+
+static struct i2c_driver tc358767_driver = {
+	.driver = {
+		.name = "tc358767",
+		.of_match_table = tc358767_of_ids,
+	},
+	.id_table = tc358767_i2c_ids,
+	.probe = tc_probe,
+	.remove	= tc_remove,
+};
+module_i2c_driver(tc358767_driver);
+
+MODULE_AUTHOR("Andrey Gusakov <andrey.gusakov@cogentembedded.com>");
+MODULE_DESCRIPTION("tc358767 eDP encoder driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/cirrus/Kconfig b/drivers/gpu/drm/cirrus/Kconfig
index 9864559e5fb9..04b3c161dfae 100644
--- a/drivers/gpu/drm/cirrus/Kconfig
+++ b/drivers/gpu/drm/cirrus/Kconfig
@@ -1,11 +1,7 @@
 config DRM_CIRRUS_QEMU
 	tristate "Cirrus driver for QEMU emulated device"
 	depends on DRM && PCI
-	select FB_SYS_FILLRECT
-	select FB_SYS_COPYAREA
-	select FB_SYS_IMAGEBLIT
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_TTM
 	help
 	 This is a KMS driver for emulated cirrus device in qemu.
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index dc83f69da6f1..b05f7eae32ce 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -142,7 +142,7 @@ static struct drm_driver driver = {
 	.major = DRIVER_MAJOR,
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
-	.gem_free_object = cirrus_gem_free_object,
+	.gem_free_object_unlocked = cirrus_gem_free_object,
 	.dumb_create = cirrus_dumb_create,
 	.dumb_map_offset = cirrus_dumb_mmap_offset,
 	.dumb_destroy = drm_gem_dumb_destroy,
diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c
index 32d32c5b7b17..80446e2d3ab6 100644
--- a/drivers/gpu/drm/cirrus/cirrus_main.c
+++ b/drivers/gpu/drm/cirrus/cirrus_main.c
@@ -17,8 +17,8 @@
 static void cirrus_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct cirrus_framebuffer *cirrus_fb = to_cirrus_framebuffer(fb);
-	if (cirrus_fb->obj)
-		drm_gem_object_unreference_unlocked(cirrus_fb->obj);
+
+	drm_gem_object_unreference_unlocked(cirrus_fb->obj);
 	drm_framebuffer_cleanup(fb);
 	kfree(fb);
 }
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index d3d8d7bfcc57..17c915d9a03e 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -325,21 +325,20 @@ static void cirrus_crtc_commit(struct drm_crtc *crtc)
  * use this for 8-bit mode so can't perform smooth fades on deeper modes,
  * but it's a requirement that we provide the function
  */
-static void cirrus_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-				  u16 *blue, uint32_t start, uint32_t size)
+static int cirrus_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
+				 u16 *blue, uint32_t size)
 {
 	struct cirrus_crtc *cirrus_crtc = to_cirrus_crtc(crtc);
 	int i;
 
-	if (size != CIRRUS_LUT_SIZE)
-		return;
-
-	for (i = 0; i < CIRRUS_LUT_SIZE; i++) {
+	for (i = 0; i < size; i++) {
 		cirrus_crtc->lut_r[i] = red[i];
 		cirrus_crtc->lut_g[i] = green[i];
 		cirrus_crtc->lut_b[i] = blue[i];
 	}
 	cirrus_crtc_load_lut(crtc);
+
+	return 0;
 }
 
 /* Simple cleanup function */
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 6768b7b1af32..1cc9ee607128 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -186,17 +186,6 @@ static void cirrus_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_re
 {
 }
 
-static int cirrus_bo_move(struct ttm_buffer_object *bo,
-		       bool evict, bool interruptible,
-		       bool no_wait_gpu,
-		       struct ttm_mem_reg *new_mem)
-{
-	int r;
-	r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
-	return r;
-}
-
-
 static void cirrus_ttm_backend_destroy(struct ttm_tt *tt)
 {
 	ttm_tt_fini(tt);
@@ -241,7 +230,7 @@ struct ttm_bo_driver cirrus_bo_driver = {
 	.ttm_tt_unpopulate = cirrus_ttm_tt_unpopulate,
 	.init_mem_type = cirrus_bo_init_mem_type,
 	.evict_flags = cirrus_bo_evict_flags,
-	.move = cirrus_bo_move,
+	.move = NULL,
 	.verify_access = cirrus_bo_verify_access,
 	.io_mem_reserve = &cirrus_ttm_io_mem_reserve,
 	.io_mem_free = &cirrus_ttm_io_mem_free,
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 9bb99e274d23..8d2f111fa113 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -33,6 +33,20 @@
 
 #include "drm_crtc_internal.h"
 
+static void crtc_commit_free(struct kref *kref)
+{
+	struct drm_crtc_commit *commit =
+		container_of(kref, struct drm_crtc_commit, ref);
+
+	kfree(commit);
+}
+
+void drm_crtc_commit_put(struct drm_crtc_commit *commit)
+{
+	kref_put(&commit->ref, crtc_commit_free);
+}
+EXPORT_SYMBOL(drm_crtc_commit_put);
+
 /**
  * drm_atomic_state_default_release -
  * release memory initialized by drm_atomic_state_init
@@ -44,11 +58,8 @@
 void drm_atomic_state_default_release(struct drm_atomic_state *state)
 {
 	kfree(state->connectors);
-	kfree(state->connector_states);
 	kfree(state->crtcs);
-	kfree(state->crtc_states);
 	kfree(state->planes);
-	kfree(state->plane_states);
 }
 EXPORT_SYMBOL(drm_atomic_state_default_release);
 
@@ -72,18 +83,10 @@ drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state)
 			       sizeof(*state->crtcs), GFP_KERNEL);
 	if (!state->crtcs)
 		goto fail;
-	state->crtc_states = kcalloc(dev->mode_config.num_crtc,
-				     sizeof(*state->crtc_states), GFP_KERNEL);
-	if (!state->crtc_states)
-		goto fail;
 	state->planes = kcalloc(dev->mode_config.num_total_plane,
 				sizeof(*state->planes), GFP_KERNEL);
 	if (!state->planes)
 		goto fail;
-	state->plane_states = kcalloc(dev->mode_config.num_total_plane,
-				      sizeof(*state->plane_states), GFP_KERNEL);
-	if (!state->plane_states)
-		goto fail;
 
 	state->dev = dev;
 
@@ -139,40 +142,48 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
 	DRM_DEBUG_ATOMIC("Clearing atomic state %p\n", state);
 
 	for (i = 0; i < state->num_connector; i++) {
-		struct drm_connector *connector = state->connectors[i];
+		struct drm_connector *connector = state->connectors[i].ptr;
 
 		if (!connector)
 			continue;
 
 		connector->funcs->atomic_destroy_state(connector,
-						       state->connector_states[i]);
-		state->connectors[i] = NULL;
-		state->connector_states[i] = NULL;
+						       state->connectors[i].state);
+		state->connectors[i].ptr = NULL;
+		state->connectors[i].state = NULL;
 		drm_connector_unreference(connector);
 	}
 
 	for (i = 0; i < config->num_crtc; i++) {
-		struct drm_crtc *crtc = state->crtcs[i];
+		struct drm_crtc *crtc = state->crtcs[i].ptr;
 
 		if (!crtc)
 			continue;
 
 		crtc->funcs->atomic_destroy_state(crtc,
-						  state->crtc_states[i]);
-		state->crtcs[i] = NULL;
-		state->crtc_states[i] = NULL;
+						  state->crtcs[i].state);
+
+		if (state->crtcs[i].commit) {
+			kfree(state->crtcs[i].commit->event);
+			state->crtcs[i].commit->event = NULL;
+			drm_crtc_commit_put(state->crtcs[i].commit);
+		}
+
+		state->crtcs[i].commit = NULL;
+		state->crtcs[i].ptr = NULL;
+		state->crtcs[i].state = NULL;
 	}
 
 	for (i = 0; i < config->num_total_plane; i++) {
-		struct drm_plane *plane = state->planes[i];
+		struct drm_plane *plane = state->planes[i].ptr;
 
 		if (!plane)
 			continue;
 
 		plane->funcs->atomic_destroy_state(plane,
-						   state->plane_states[i]);
-		state->planes[i] = NULL;
-		state->plane_states[i] = NULL;
+						   state->planes[i].state);
+		state->planes[i].ptr = NULL;
+		state->planes[i].state = NULL;
 	}
 }
 EXPORT_SYMBOL(drm_atomic_state_default_clear);
@@ -270,8 +281,8 @@ drm_atomic_get_crtc_state(struct drm_atomic_state *state,
 	if (!crtc_state)
 		return ERR_PTR(-ENOMEM);
 
-	state->crtc_states[index] = crtc_state;
-	state->crtcs[index] = crtc;
+	state->crtcs[index].state = crtc_state;
+	state->crtcs[index].ptr = crtc;
 	crtc_state->state = state;
 
 	DRM_DEBUG_ATOMIC("Added [CRTC:%d:%s] %p state to %p\n",
@@ -393,8 +404,7 @@ drm_atomic_replace_property_blob(struct drm_property_blob **blob,
 	if (old_blob == new_blob)
 		return;
 
-	if (old_blob)
-		drm_property_unreference_blob(old_blob);
+	drm_property_unreference_blob(old_blob);
 	if (new_blob)
 		drm_property_reference_blob(new_blob);
 	*blob = new_blob;
@@ -632,8 +642,8 @@ drm_atomic_get_plane_state(struct drm_atomic_state *state,
 	if (!plane_state)
 		return ERR_PTR(-ENOMEM);
 
-	state->plane_states[index] = plane_state;
-	state->planes[index] = plane;
+	state->planes[index].state = plane_state;
+	state->planes[index].ptr = plane;
 	plane_state->state = state;
 
 	DRM_DEBUG_ATOMIC("Added [PLANE:%d:%s] %p state to %p\n",
@@ -897,8 +907,7 @@ drm_atomic_get_connector_state(struct drm_atomic_state *state,
 	index = drm_connector_index(connector);
 
 	if (index >= state->num_connector) {
-		struct drm_connector **c;
-		struct drm_connector_state **cs;
+		struct __drm_connnectors_state *c;
 		int alloc = max(index + 1, config->num_connector);
 
 		c = krealloc(state->connectors, alloc * sizeof(*state->connectors), GFP_KERNEL);
@@ -909,26 +918,19 @@ drm_atomic_get_connector_state(struct drm_atomic_state *state,
 		memset(&state->connectors[state->num_connector], 0,
 		       sizeof(*state->connectors) * (alloc - state->num_connector));
 
-		cs = krealloc(state->connector_states, alloc * sizeof(*state->connector_states), GFP_KERNEL);
-		if (!cs)
-			return ERR_PTR(-ENOMEM);
-
-		state->connector_states = cs;
-		memset(&state->connector_states[state->num_connector], 0,
-		       sizeof(*state->connector_states) * (alloc - state->num_connector));
 		state->num_connector = alloc;
 	}
 
-	if (state->connector_states[index])
-		return state->connector_states[index];
+	if (state->connectors[index].state)
+		return state->connectors[index].state;
 
 	connector_state = connector->funcs->atomic_duplicate_state(connector);
 	if (!connector_state)
 		return ERR_PTR(-ENOMEM);
 
 	drm_connector_reference(connector);
-	state->connector_states[index] = connector_state;
-	state->connectors[index] = connector;
+	state->connectors[index].state = connector_state;
+	state->connectors[index].ptr = connector;
 	connector_state->state = state;
 
 	DRM_DEBUG_ATOMIC("Added [CONNECTOR:%d] %p state to %p\n",
@@ -1457,7 +1459,8 @@ EXPORT_SYMBOL(drm_atomic_nonblocking_commit);
  */
 
 static struct drm_pending_vblank_event *create_vblank_event(
-		struct drm_device *dev, struct drm_file *file_priv, uint64_t user_data)
+		struct drm_device *dev, struct drm_file *file_priv,
+		struct fence *fence, uint64_t user_data)
 {
 	struct drm_pending_vblank_event *e = NULL;
 	int ret;
@@ -1470,12 +1473,17 @@ static struct drm_pending_vblank_event *create_vblank_event(
 	e->event.base.length = sizeof(e->event);
 	e->event.user_data = user_data;
 
-	ret = drm_event_reserve_init(dev, file_priv, &e->base, &e->event.base);
-	if (ret) {
-		kfree(e);
-		return NULL;
+	if (file_priv) {
+		ret = drm_event_reserve_init(dev, file_priv, &e->base,
+					     &e->event.base);
+		if (ret) {
+			kfree(e);
+			return NULL;
+		}
 	}
 
+	e->base.fence = fence;
+
 	return e;
 }
 
@@ -1715,7 +1723,8 @@ retry:
 		for_each_crtc_in_state(state, crtc, crtc_state, i) {
 			struct drm_pending_vblank_event *e;
 
-			e = create_vblank_event(dev, file_priv, arg->user_data);
+			e = create_vblank_event(dev, file_priv, NULL,
+						arg->user_data);
 			if (!e) {
 				ret = -ENOMEM;
 				goto out;
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index ddfa0d120e39..de7fddce3cef 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -110,8 +110,10 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state,
 
 		if (funcs->atomic_best_encoder)
 			new_encoder = funcs->atomic_best_encoder(connector, conn_state);
-		else
+		else if (funcs->best_encoder)
 			new_encoder = funcs->best_encoder(connector);
+		else
+			new_encoder = drm_atomic_helper_best_encoder(connector);
 
 		if (new_encoder) {
 			if (encoder_mask & (1 << drm_encoder_index(new_encoder))) {
@@ -298,8 +300,10 @@ update_connector_routing(struct drm_atomic_state *state,
 	if (funcs->atomic_best_encoder)
 		new_encoder = funcs->atomic_best_encoder(connector,
 							 connector_state);
-	else
+	else if (funcs->best_encoder)
 		new_encoder = funcs->best_encoder(connector);
+	else
+		new_encoder = drm_atomic_helper_best_encoder(connector);
 
 	if (!new_encoder) {
 		DRM_DEBUG_ATOMIC("No suitable encoder found for [CONNECTOR:%d:%s]\n",
@@ -414,6 +418,9 @@ mode_fixup(struct drm_atomic_state *state)
 	for_each_crtc_in_state(state, crtc, crtc_state, i) {
 		const struct drm_crtc_helper_funcs *funcs;
 
+		if (!crtc_state->enable)
+			continue;
+
 		if (!crtc_state->mode_changed &&
 		    !crtc_state->connectors_changed)
 			continue;
@@ -458,7 +465,7 @@ mode_fixup(struct drm_atomic_state *state)
  * times for the same update, e.g. when the ->atomic_check functions depend upon
  * the adjusted dotclock for fifo space allocation and watermark computation.
  *
- * RETURNS
+ * RETURNS:
  * Zero for success or -errno
  */
 int
@@ -572,7 +579,7 @@ EXPORT_SYMBOL(drm_atomic_helper_check_modeset);
  * It also sets crtc_state->planes_changed to indicate that a crtc has
  * updated planes.
  *
- * RETURNS
+ * RETURNS:
  * Zero for success or -errno
  */
 int
@@ -611,7 +618,7 @@ drm_atomic_helper_check_planes(struct drm_device *dev,
 		if (!funcs || !funcs->atomic_check)
 			continue;
 
-		ret = funcs->atomic_check(crtc, state->crtc_states[i]);
+		ret = funcs->atomic_check(crtc, crtc_state);
 		if (ret) {
 			DRM_DEBUG_ATOMIC("[CRTC:%d:%s] atomic driver check failed\n",
 					 crtc->base.id, crtc->name);
@@ -640,7 +647,7 @@ EXPORT_SYMBOL(drm_atomic_helper_check_planes);
  * ->atomic_check functions depend upon an updated adjusted_mode.clock to
  * e.g. properly compute watermarks.
  *
- * RETURNS
+ * RETURNS:
  * Zero for success or -errno
  */
 int drm_atomic_helper_check(struct drm_device *dev,
@@ -1113,22 +1120,17 @@ drm_atomic_helper_wait_for_vblanks(struct drm_device *dev,
 EXPORT_SYMBOL(drm_atomic_helper_wait_for_vblanks);
 
 /**
- * drm_atomic_helper_commit - commit validated state object
- * @dev: DRM device
- * @state: the driver state object
- * @nonblocking: whether nonblocking behavior is requested.
+ * drm_atomic_helper_commit_tail - commit atomic update to hardware
+ * @state: new modeset state to be committed
  *
- * This function commits a with drm_atomic_helper_check() pre-validated state
- * object. This can still fail when e.g. the framebuffer reservation fails. For
- * now this doesn't implement nonblocking commits.
+ * This is the default implemenation for the ->atomic_commit_tail() hook of the
+ * &drm_mode_config_helper_funcs vtable.
  *
- * Note that right now this function does not support nonblocking commits, hence
- * driver writers must implement their own version for now. Also note that the
- * default ordering of how the various stages are called is to match the legacy
- * modeset helper library closest. One peculiarity of that is that it doesn't
- * mesh well with runtime PM at all.
+ * Note that the default ordering of how the various stages are called is to
+ * match the legacy modeset helper library closest. One peculiarity of that is
+ * that it doesn't mesh well with runtime PM at all.
  *
- * For drivers supporting runtime PM the recommended sequence is
+ * For drivers supporting runtime PM the recommended sequence is instead ::
  *
  *     drm_atomic_helper_commit_modeset_disables(dev, state);
  *
@@ -1136,9 +1138,75 @@ EXPORT_SYMBOL(drm_atomic_helper_wait_for_vblanks);
  *
  *     drm_atomic_helper_commit_planes(dev, state, true);
  *
- * See the kerneldoc entries for these three functions for more details.
+ * for committing the atomic update to hardware.  See the kerneldoc entries for
+ * these three functions for more details.
+ */
+void drm_atomic_helper_commit_tail(struct drm_atomic_state *state)
+{
+	struct drm_device *dev = state->dev;
+
+	drm_atomic_helper_commit_modeset_disables(dev, state);
+
+	drm_atomic_helper_commit_planes(dev, state, false);
+
+	drm_atomic_helper_commit_modeset_enables(dev, state);
+
+	drm_atomic_helper_commit_hw_done(state);
+
+	drm_atomic_helper_wait_for_vblanks(dev, state);
+
+	drm_atomic_helper_cleanup_planes(dev, state);
+}
+EXPORT_SYMBOL(drm_atomic_helper_commit_tail);
+
+static void commit_tail(struct drm_atomic_state *state)
+{
+	struct drm_device *dev = state->dev;
+	struct drm_mode_config_helper_funcs *funcs;
+
+	funcs = dev->mode_config.helper_private;
+
+	drm_atomic_helper_wait_for_fences(dev, state);
+
+	drm_atomic_helper_wait_for_dependencies(state);
+
+	if (funcs && funcs->atomic_commit_tail)
+		funcs->atomic_commit_tail(state);
+	else
+		drm_atomic_helper_commit_tail(state);
+
+	drm_atomic_helper_commit_cleanup_done(state);
+
+	drm_atomic_state_free(state);
+}
+
+static void commit_work(struct work_struct *work)
+{
+	struct drm_atomic_state *state = container_of(work,
+						      struct drm_atomic_state,
+						      commit_work);
+	commit_tail(state);
+}
+
+/**
+ * drm_atomic_helper_commit - commit validated state object
+ * @dev: DRM device
+ * @state: the driver state object
+ * @nonblock: whether nonblocking behavior is requested.
+ *
+ * This function commits a with drm_atomic_helper_check() pre-validated state
+ * object. This can still fail when e.g. the framebuffer reservation fails. This
+ * function implements nonblocking commits, using
+ * drm_atomic_helper_setup_commit() and related functions.
+ *
+ * Note that right now this function does not support nonblocking commits, hence
+ * driver writers must implement their own version for now.
+ *
+ * Committing the actual hardware state is done through the
+ * ->atomic_commit_tail() callback of the &drm_mode_config_helper_funcs vtable,
+ * or it's default implementation drm_atomic_helper_commit_tail().
  *
- * RETURNS
+ * RETURNS:
  * Zero for success or -errno.
  */
 int drm_atomic_helper_commit(struct drm_device *dev,
@@ -1147,8 +1215,11 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 {
 	int ret;
 
-	if (nonblock)
-		return -EBUSY;
+	ret = drm_atomic_helper_setup_commit(state, nonblock);
+	if (ret)
+		return ret;
+
+	INIT_WORK(&state->commit_work, commit_work);
 
 	ret = drm_atomic_helper_prepare_planes(dev, state);
 	if (ret)
@@ -1160,7 +1231,7 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 	 * the software side now.
 	 */
 
-	drm_atomic_helper_swap_state(dev, state);
+	drm_atomic_helper_swap_state(state, true);
 
 	/*
 	 * Everything below can be run asynchronously without the need to grab
@@ -1176,21 +1247,16 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 	 * update. Which is important since compositors need to figure out the
 	 * composition of the next frame right after having submitted the
 	 * current layout.
+	 *
+	 * NOTE: Commit work has multiple phases, first hardware commit, then
+	 * cleanup. We want them to overlap, hence need system_unbound_wq to
+	 * make sure work items don't artifically stall on each another.
 	 */
 
-	drm_atomic_helper_wait_for_fences(dev, state);
-
-	drm_atomic_helper_commit_modeset_disables(dev, state);
-
-	drm_atomic_helper_commit_planes(dev, state, false);
-
-	drm_atomic_helper_commit_modeset_enables(dev, state);
-
-	drm_atomic_helper_wait_for_vblanks(dev, state);
-
-	drm_atomic_helper_cleanup_planes(dev, state);
-
-	drm_atomic_state_free(state);
+	if (nonblock)
+		queue_work(system_unbound_wq, &state->commit_work);
+	else
+		commit_tail(state);
 
 	return 0;
 }
@@ -1199,12 +1265,7 @@ EXPORT_SYMBOL(drm_atomic_helper_commit);
 /**
  * DOC: implementing nonblocking commit
  *
- * For now the atomic helpers don't support nonblocking commit directly. If
- * there is real need it could be added though, using the dma-buf fence
- * infrastructure for generic synchronization with outstanding rendering.
- *
- * For now drivers have to implement nonblocking commit themselves, with the
- * following sequence being the recommended one:
+ * Nonblocking atomic commits have to be implemented in the following sequence:
  *
  * 1. Run drm_atomic_helper_prepare_planes() first. This is the only function
  * which commit needs to call which can fail, so we want to run it first and
@@ -1216,10 +1277,14 @@ EXPORT_SYMBOL(drm_atomic_helper_commit);
  * cancelled updates. Note that it is important to ensure that the framebuffer
  * cleanup is still done when cancelling.
  *
- * For sufficient parallelism it is recommended to have a work item per crtc
- * (for updates which don't touch global state) and a global one. Then we only
- * need to synchronize with the crtc work items for changed crtcs and the global
- * work item, which allows nice concurrent updates on disjoint sets of crtcs.
+ * Asynchronous workers need to have sufficient parallelism to be able to run
+ * different atomic commits on different CRTCs in parallel. The simplest way to
+ * achive this is by running them on the &system_unbound_wq work queue. Note
+ * that drivers are not required to split up atomic commits and run an
+ * individual commit in parallel - userspace is supposed to do that if it cares.
+ * But it might be beneficial to do that for modesets, since those necessarily
+ * must be done as one global operation, and enabling or disabling a CRTC can
+ * take a long time. But even that is not required.
  *
  * 3. The software state is updated synchronously with
  * drm_atomic_helper_swap_state(). Doing this under the protection of all modeset
@@ -1232,8 +1297,310 @@ EXPORT_SYMBOL(drm_atomic_helper_commit);
  * commit helpers: a) pre-plane commit b) plane commit c) post-plane commit and
  * then cleaning up the framebuffers after the old framebuffer is no longer
  * being displayed.
+ *
+ * The above scheme is implemented in the atomic helper libraries in
+ * drm_atomic_helper_commit() using a bunch of helper functions. See
+ * drm_atomic_helper_setup_commit() for a starting point.
  */
 
+static int stall_checks(struct drm_crtc *crtc, bool nonblock)
+{
+	struct drm_crtc_commit *commit, *stall_commit = NULL;
+	bool completed = true;
+	int i;
+	long ret = 0;
+
+	spin_lock(&crtc->commit_lock);
+	i = 0;
+	list_for_each_entry(commit, &crtc->commit_list, commit_entry) {
+		if (i == 0) {
+			completed = try_wait_for_completion(&commit->flip_done);
+			/* Userspace is not allowed to get ahead of the previous
+			 * commit with nonblocking ones. */
+			if (!completed && nonblock) {
+				spin_unlock(&crtc->commit_lock);
+				return -EBUSY;
+			}
+		} else if (i == 1) {
+			stall_commit = commit;
+			drm_crtc_commit_get(stall_commit);
+			break;
+		}
+
+		i++;
+	}
+	spin_unlock(&crtc->commit_lock);
+
+	if (!stall_commit)
+		return 0;
+
+	/* We don't want to let commits get ahead of cleanup work too much,
+	 * stalling on 2nd previous commit means triple-buffer won't ever stall.
+	 */
+	ret = wait_for_completion_interruptible_timeout(&stall_commit->cleanup_done,
+							10*HZ);
+	if (ret == 0)
+		DRM_ERROR("[CRTC:%d:%s] cleanup_done timed out\n",
+			  crtc->base.id, crtc->name);
+
+	drm_crtc_commit_put(stall_commit);
+
+	return ret < 0 ? ret : 0;
+}
+
+/**
+ * drm_atomic_helper_setup_commit - setup possibly nonblocking commit
+ * @state: new modeset state to be committed
+ * @nonblock: whether nonblocking behavior is requested.
+ *
+ * This function prepares @state to be used by the atomic helper's support for
+ * nonblocking commits. Drivers using the nonblocking commit infrastructure
+ * should always call this function from their ->atomic_commit hook.
+ *
+ * To be able to use this support drivers need to use a few more helper
+ * functions. drm_atomic_helper_wait_for_dependencies() must be called before
+ * actually committing the hardware state, and for nonblocking commits this call
+ * must be placed in the async worker. See also drm_atomic_helper_swap_state()
+ * and it's stall parameter, for when a driver's commit hooks look at the
+ * ->state pointers of struct &drm_crtc, &drm_plane or &drm_connector directly.
+ *
+ * Completion of the hardware commit step must be signalled using
+ * drm_atomic_helper_commit_hw_done(). After this step the driver is not allowed
+ * to read or change any permanent software or hardware modeset state. The only
+ * exception is state protected by other means than &drm_modeset_lock locks.
+ * Only the free standing @state with pointers to the old state structures can
+ * be inspected, e.g. to clean up old buffers using
+ * drm_atomic_helper_cleanup_planes().
+ *
+ * At the very end, before cleaning up @state drivers must call
+ * drm_atomic_helper_commit_cleanup_done().
+ *
+ * This is all implemented by in drm_atomic_helper_commit(), giving drivers a
+ * complete and esay-to-use default implementation of the atomic_commit() hook.
+ *
+ * The tracking of asynchronously executed and still pending commits is done
+ * using the core structure &drm_crtc_commit.
+ *
+ * By default there's no need to clean up resources allocated by this function
+ * explicitly: drm_atomic_state_default_clear() will take care of that
+ * automatically.
+ *
+ * Returns:
+ *
+ * 0 on success. -EBUSY when userspace schedules nonblocking commits too fast,
+ * -ENOMEM on allocation failures and -EINTR when a signal is pending.
+ */
+int drm_atomic_helper_setup_commit(struct drm_atomic_state *state,
+				   bool nonblock)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_crtc_commit *commit;
+	int i, ret;
+
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		commit = kzalloc(sizeof(*commit), GFP_KERNEL);
+		if (!commit)
+			return -ENOMEM;
+
+		init_completion(&commit->flip_done);
+		init_completion(&commit->hw_done);
+		init_completion(&commit->cleanup_done);
+		INIT_LIST_HEAD(&commit->commit_entry);
+		kref_init(&commit->ref);
+		commit->crtc = crtc;
+
+		state->crtcs[i].commit = commit;
+
+		ret = stall_checks(crtc, nonblock);
+		if (ret)
+			return ret;
+
+		/* Drivers only send out events when at least either current or
+		 * new CRTC state is active. Complete right away if everything
+		 * stays off. */
+		if (!crtc->state->active && !crtc_state->active) {
+			complete_all(&commit->flip_done);
+			continue;
+		}
+
+		/* Legacy cursor updates are fully unsynced. */
+		if (state->legacy_cursor_update) {
+			complete_all(&commit->flip_done);
+			continue;
+		}
+
+		if (!crtc_state->event) {
+			commit->event = kzalloc(sizeof(*commit->event),
+						GFP_KERNEL);
+			if (!commit->event)
+				return -ENOMEM;
+
+			crtc_state->event = commit->event;
+		}
+
+		crtc_state->event->base.completion = &commit->flip_done;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_atomic_helper_setup_commit);
+
+
+static struct drm_crtc_commit *preceeding_commit(struct drm_crtc *crtc)
+{
+	struct drm_crtc_commit *commit;
+	int i = 0;
+
+	list_for_each_entry(commit, &crtc->commit_list, commit_entry) {
+		/* skip the first entry, that's the current commit */
+		if (i == 1)
+			return commit;
+		i++;
+	}
+
+	return NULL;
+}
+
+/**
+ * drm_atomic_helper_wait_for_dependencies - wait for required preceeding commits
+ * @state: new modeset state to be committed
+ *
+ * This function waits for all preceeding commits that touch the same CRTC as
+ * @state to both be committed to the hardware (as signalled by
+ * drm_atomic_helper_commit_hw_done) and executed by the hardware (as signalled
+ * by calling drm_crtc_vblank_send_event on the event member of
+ * &drm_crtc_state).
+ *
+ * This is part of the atomic helper support for nonblocking commits, see
+ * drm_atomic_helper_setup_commit() for an overview.
+ */
+void drm_atomic_helper_wait_for_dependencies(struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_crtc_commit *commit;
+	int i;
+	long ret;
+
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		spin_lock(&crtc->commit_lock);
+		commit = preceeding_commit(crtc);
+		if (commit)
+			drm_crtc_commit_get(commit);
+		spin_unlock(&crtc->commit_lock);
+
+		if (!commit)
+			continue;
+
+		ret = wait_for_completion_timeout(&commit->hw_done,
+						  10*HZ);
+		if (ret == 0)
+			DRM_ERROR("[CRTC:%d:%s] hw_done timed out\n",
+				  crtc->base.id, crtc->name);
+
+		/* Currently no support for overwriting flips, hence
+		 * stall for previous one to execute completely. */
+		ret = wait_for_completion_timeout(&commit->flip_done,
+						  10*HZ);
+		if (ret == 0)
+			DRM_ERROR("[CRTC:%d:%s] flip_done timed out\n",
+				  crtc->base.id, crtc->name);
+
+		drm_crtc_commit_put(commit);
+	}
+}
+EXPORT_SYMBOL(drm_atomic_helper_wait_for_dependencies);
+
+/**
+ * drm_atomic_helper_commit_hw_done - setup possible nonblocking commit
+ * @state: new modeset state to be committed
+ *
+ * This function is used to signal completion of the hardware commit step. After
+ * this step the driver is not allowed to read or change any permanent software
+ * or hardware modeset state. The only exception is state protected by other
+ * means than &drm_modeset_lock locks.
+ *
+ * Drivers should try to postpone any expensive or delayed cleanup work after
+ * this function is called.
+ *
+ * This is part of the atomic helper support for nonblocking commits, see
+ * drm_atomic_helper_setup_commit() for an overview.
+ */
+void drm_atomic_helper_commit_hw_done(struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_crtc_commit *commit;
+	int i;
+
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		commit = state->crtcs[i].commit;
+		if (!commit)
+			continue;
+
+		/* backend must have consumed any event by now */
+		WARN_ON(crtc->state->event);
+		spin_lock(&crtc->commit_lock);
+		complete_all(&commit->hw_done);
+		spin_unlock(&crtc->commit_lock);
+	}
+}
+EXPORT_SYMBOL(drm_atomic_helper_commit_hw_done);
+
+/**
+ * drm_atomic_helper_commit_cleanup_done - signal completion of commit
+ * @state: new modeset state to be committed
+ *
+ * This signals completion of the atomic update @state, including any cleanup
+ * work. If used, it must be called right before calling
+ * drm_atomic_state_free().
+ *
+ * This is part of the atomic helper support for nonblocking commits, see
+ * drm_atomic_helper_setup_commit() for an overview.
+ */
+void drm_atomic_helper_commit_cleanup_done(struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_crtc_commit *commit;
+	int i;
+	long ret;
+
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		commit = state->crtcs[i].commit;
+		if (WARN_ON(!commit))
+			continue;
+
+		spin_lock(&crtc->commit_lock);
+		complete_all(&commit->cleanup_done);
+		WARN_ON(!try_wait_for_completion(&commit->hw_done));
+
+		/* commit_list borrows our reference, need to remove before we
+		 * clean up our drm_atomic_state. But only after it actually
+		 * completed, otherwise subsequent commits won't stall properly. */
+		if (try_wait_for_completion(&commit->flip_done))
+			goto del_commit;
+
+		spin_unlock(&crtc->commit_lock);
+
+		/* We must wait for the vblank event to signal our completion
+		 * before releasing our reference, since the vblank work does
+		 * not hold a reference of its own. */
+		ret = wait_for_completion_timeout(&commit->flip_done,
+						  10*HZ);
+		if (ret == 0)
+			DRM_ERROR("[CRTC:%d:%s] flip_done timed out\n",
+				  crtc->base.id, crtc->name);
+
+		spin_lock(&crtc->commit_lock);
+del_commit:
+		list_del(&commit->commit_entry);
+		spin_unlock(&crtc->commit_lock);
+	}
+}
+EXPORT_SYMBOL(drm_atomic_helper_commit_cleanup_done);
+
 /**
  * drm_atomic_helper_prepare_planes - prepare plane resources before commit
  * @dev: DRM device
@@ -1249,16 +1616,12 @@ EXPORT_SYMBOL(drm_atomic_helper_commit);
 int drm_atomic_helper_prepare_planes(struct drm_device *dev,
 				     struct drm_atomic_state *state)
 {
-	int nplanes = dev->mode_config.num_total_plane;
-	int ret, i;
+	struct drm_plane *plane;
+	struct drm_plane_state *plane_state;
+	int ret, i, j;
 
-	for (i = 0; i < nplanes; i++) {
+	for_each_plane_in_state(state, plane, plane_state, i) {
 		const struct drm_plane_helper_funcs *funcs;
-		struct drm_plane *plane = state->planes[i];
-		struct drm_plane_state *plane_state = state->plane_states[i];
-
-		if (!plane)
-			continue;
 
 		funcs = plane->helper_private;
 
@@ -1272,12 +1635,10 @@ int drm_atomic_helper_prepare_planes(struct drm_device *dev,
 	return 0;
 
 fail:
-	for (i--; i >= 0; i--) {
+	for_each_plane_in_state(state, plane, plane_state, j) {
 		const struct drm_plane_helper_funcs *funcs;
-		struct drm_plane *plane = state->planes[i];
-		struct drm_plane_state *plane_state = state->plane_states[i];
 
-		if (!plane)
+		if (j >= i)
 			continue;
 
 		funcs = plane->helper_private;
@@ -1537,8 +1898,8 @@ EXPORT_SYMBOL(drm_atomic_helper_cleanup_planes);
 
 /**
  * drm_atomic_helper_swap_state - store atomic state into current sw state
- * @dev: DRM device
  * @state: atomic state
+ * @stall: stall for proceeding commits
  *
  * This function stores the atomic state into the current state pointers in all
  * driver objects. It should be called after all failing steps have been done
@@ -1559,42 +1920,70 @@ EXPORT_SYMBOL(drm_atomic_helper_cleanup_planes);
  *
  * 5. Call drm_atomic_helper_cleanup_planes() with @state, which since step 3
  * contains the old state. Also do any other cleanup required with that state.
+ *
+ * @stall must be set when nonblocking commits for this driver directly access
+ * the ->state pointer of &drm_plane, &drm_crtc or &drm_connector. With the
+ * current atomic helpers this is almost always the case, since the helpers
+ * don't pass the right state structures to the callbacks.
  */
-void drm_atomic_helper_swap_state(struct drm_device *dev,
-				  struct drm_atomic_state *state)
+void drm_atomic_helper_swap_state(struct drm_atomic_state *state,
+				  bool stall)
 {
 	int i;
+	long ret;
+	struct drm_connector *connector;
+	struct drm_connector_state *conn_state;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_plane *plane;
+	struct drm_plane_state *plane_state;
+	struct drm_crtc_commit *commit;
+
+	if (stall) {
+		for_each_crtc_in_state(state, crtc, crtc_state, i) {
+			spin_lock(&crtc->commit_lock);
+			commit = list_first_entry_or_null(&crtc->commit_list,
+					struct drm_crtc_commit, commit_entry);
+			if (commit)
+				drm_crtc_commit_get(commit);
+			spin_unlock(&crtc->commit_lock);
+
+			if (!commit)
+				continue;
 
-	for (i = 0; i < state->num_connector; i++) {
-		struct drm_connector *connector = state->connectors[i];
-
-		if (!connector)
-			continue;
+			ret = wait_for_completion_timeout(&commit->hw_done,
+							  10*HZ);
+			if (ret == 0)
+				DRM_ERROR("[CRTC:%d:%s] hw_done timed out\n",
+					  crtc->base.id, crtc->name);
+			drm_crtc_commit_put(commit);
+		}
+	}
 
+	for_each_connector_in_state(state, connector, conn_state, i) {
 		connector->state->state = state;
-		swap(state->connector_states[i], connector->state);
+		swap(state->connectors[i].state, connector->state);
 		connector->state->state = NULL;
 	}
 
-	for (i = 0; i < dev->mode_config.num_crtc; i++) {
-		struct drm_crtc *crtc = state->crtcs[i];
-
-		if (!crtc)
-			continue;
-
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
 		crtc->state->state = state;
-		swap(state->crtc_states[i], crtc->state);
+		swap(state->crtcs[i].state, crtc->state);
 		crtc->state->state = NULL;
-	}
 
-	for (i = 0; i < dev->mode_config.num_total_plane; i++) {
-		struct drm_plane *plane = state->planes[i];
+		if (state->crtcs[i].commit) {
+			spin_lock(&crtc->commit_lock);
+			list_add(&state->crtcs[i].commit->commit_entry,
+				 &crtc->commit_list);
+			spin_unlock(&crtc->commit_lock);
 
-		if (!plane)
-			continue;
+			state->crtcs[i].commit->event = NULL;
+		}
+	}
 
+	for_each_plane_in_state(state, plane, plane_state, i) {
 		plane->state->state = state;
-		swap(state->plane_states[i], plane->state);
+		swap(state->planes[i].state, plane->state);
 		plane->state->state = NULL;
 	}
 }
@@ -2409,7 +2798,7 @@ EXPORT_SYMBOL(drm_atomic_helper_page_flip);
  * This is the main helper function provided by the atomic helper framework for
  * implementing the legacy DPMS connector interface. It computes the new desired
  * ->active state for the corresponding CRTC (if the connector is enabled) and
- *  updates it.
+ * updates it.
  *
  * Returns:
  * Returns 0 on success, negative errno numbers on failure.
@@ -2930,16 +3319,15 @@ EXPORT_SYMBOL(drm_atomic_helper_connector_destroy_state);
  * @red: red correction table
  * @green: green correction table
  * @blue: green correction table
- * @start:
  * @size: size of the tables
  *
  * Implements support for legacy gamma correction table for drivers
  * that support color management through the DEGAMMA_LUT/GAMMA_LUT
  * properties.
  */
-void drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
-					u16 *red, u16 *green, u16 *blue,
-					uint32_t start, uint32_t size)
+int drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
+				       u16 *red, u16 *green, u16 *blue,
+				       uint32_t size)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_mode_config *config = &dev->mode_config;
@@ -2951,7 +3339,7 @@ void drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
 
 	state = drm_atomic_state_alloc(crtc->dev);
 	if (!state)
-		return;
+		return -ENOMEM;
 
 	blob = drm_property_create_blob(dev,
 					sizeof(struct drm_color_lut) * size,
@@ -3002,7 +3390,7 @@ retry:
 
 	drm_property_unreference_blob(blob);
 
-	return;
+	return 0;
 fail:
 	if (ret == -EDEADLK)
 		goto backoff;
@@ -3010,7 +3398,7 @@ fail:
 	drm_atomic_state_free(state);
 	drm_property_unreference_blob(blob);
 
-	return;
+	return ret;
 backoff:
 	drm_atomic_state_clear(state);
 	drm_atomic_legacy_backoff(state);
diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c
index 50d0baa06db0..4153e8a193af 100644
--- a/drivers/gpu/drm/drm_auth.c
+++ b/drivers/gpu/drm/drm_auth.c
@@ -30,25 +30,36 @@
 
 #include <drm/drmP.h>
 #include "drm_internal.h"
+#include "drm_legacy.h"
 
 /**
- * drm_getmagic - Get unique magic of a client
- * @dev: DRM device to operate on
- * @data: ioctl data containing the drm_auth object
- * @file_priv: DRM file that performs the operation
+ * DOC: master and authentication
  *
- * This looks up the unique magic of the passed client and returns it. If the
- * client did not have a magic assigned, yet, a new one is registered. The magic
- * is stored in the passed drm_auth object.
+ * struct &drm_master is used to track groups of clients with open
+ * primary/legacy device nodes. For every struct &drm_file which has had at
+ * least once successfully became the device master (either through the
+ * SET_MASTER IOCTL, or implicitly through opening the primary device node when
+ * no one else is the current master that time) there exists one &drm_master.
+ * This is noted in the is_master member of &drm_file. All other clients have
+ * just a pointer to the &drm_master they are associated with.
  *
- * Returns: 0 on success, negative error code on failure.
+ * In addition only one &drm_master can be the current master for a &drm_device.
+ * It can be switched through the DROP_MASTER and SET_MASTER IOCTL, or
+ * implicitly through closing/openeing the primary device node. See also
+ * drm_is_current_master().
+ *
+ * Clients can authenticate against the current master (if it matches their own)
+ * using the GETMAGIC and AUTHMAGIC IOCTLs. Together with exchanging masters,
+ * this allows controlled access to the device for an entire group of mutually
+ * trusted clients.
  */
+
 int drm_getmagic(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	struct drm_auth *auth = data;
 	int ret = 0;
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&dev->master_mutex);
 	if (!file_priv->magic) {
 		ret = idr_alloc(&file_priv->master->magic_map, file_priv,
 				1, 0, GFP_KERNEL);
@@ -56,23 +67,13 @@ int drm_getmagic(struct drm_device *dev, void *data, struct drm_file *file_priv)
 			file_priv->magic = ret;
 	}
 	auth->magic = file_priv->magic;
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&dev->master_mutex);
 
 	DRM_DEBUG("%u\n", auth->magic);
 
 	return ret < 0 ? ret : 0;
 }
 
-/**
- * drm_authmagic - Authenticate client with a magic
- * @dev: DRM device to operate on
- * @data: ioctl data containing the drm_auth object
- * @file_priv: DRM file that performs the operation
- *
- * This looks up a DRM client by the passed magic and authenticates it.
- *
- * Returns: 0 on success, negative error code on failure.
- */
 int drm_authmagic(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
@@ -81,13 +82,253 @@ int drm_authmagic(struct drm_device *dev, void *data,
 
 	DRM_DEBUG("%u\n", auth->magic);
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&dev->master_mutex);
 	file = idr_find(&file_priv->master->magic_map, auth->magic);
 	if (file) {
 		file->authenticated = 1;
 		idr_replace(&file_priv->master->magic_map, NULL, auth->magic);
 	}
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&dev->master_mutex);
 
 	return file ? 0 : -EINVAL;
 }
+
+static struct drm_master *drm_master_create(struct drm_device *dev)
+{
+	struct drm_master *master;
+
+	master = kzalloc(sizeof(*master), GFP_KERNEL);
+	if (!master)
+		return NULL;
+
+	kref_init(&master->refcount);
+	spin_lock_init(&master->lock.spinlock);
+	init_waitqueue_head(&master->lock.lock_queue);
+	idr_init(&master->magic_map);
+	master->dev = dev;
+
+	return master;
+}
+
+static int drm_set_master(struct drm_device *dev, struct drm_file *fpriv,
+			  bool new_master)
+{
+	int ret = 0;
+
+	dev->master = drm_master_get(fpriv->master);
+	if (dev->driver->master_set) {
+		ret = dev->driver->master_set(dev, fpriv, new_master);
+		if (unlikely(ret != 0)) {
+			drm_master_put(&dev->master);
+		}
+	}
+
+	return ret;
+}
+
+static int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv)
+{
+	struct drm_master *old_master;
+	int ret;
+
+	lockdep_assert_held_once(&dev->master_mutex);
+
+	old_master = fpriv->master;
+	fpriv->master = drm_master_create(dev);
+	if (!fpriv->master) {
+		fpriv->master = old_master;
+		return -ENOMEM;
+	}
+
+	if (dev->driver->master_create) {
+		ret = dev->driver->master_create(dev, fpriv->master);
+		if (ret)
+			goto out_err;
+	}
+	fpriv->is_master = 1;
+	fpriv->authenticated = 1;
+
+	ret = drm_set_master(dev, fpriv, true);
+	if (ret)
+		goto out_err;
+
+	if (old_master)
+		drm_master_put(&old_master);
+
+	return 0;
+
+out_err:
+	/* drop references and restore old master on failure */
+	drm_master_put(&fpriv->master);
+	fpriv->master = old_master;
+
+	return ret;
+}
+
+int drm_setmaster_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
+{
+	int ret = 0;
+
+	mutex_lock(&dev->master_mutex);
+	if (drm_is_current_master(file_priv))
+		goto out_unlock;
+
+	if (dev->master) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (!file_priv->master) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (!file_priv->is_master) {
+		ret = drm_new_set_master(dev, file_priv);
+		goto out_unlock;
+	}
+
+	ret = drm_set_master(dev, file_priv, false);
+out_unlock:
+	mutex_unlock(&dev->master_mutex);
+	return ret;
+}
+
+static void drm_drop_master(struct drm_device *dev,
+			    struct drm_file *fpriv)
+{
+	if (dev->driver->master_drop)
+		dev->driver->master_drop(dev, fpriv);
+	drm_master_put(&dev->master);
+}
+
+int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
+			 struct drm_file *file_priv)
+{
+	int ret = -EINVAL;
+
+	mutex_lock(&dev->master_mutex);
+	if (!drm_is_current_master(file_priv))
+		goto out_unlock;
+
+	if (!dev->master)
+		goto out_unlock;
+
+	ret = 0;
+	drm_drop_master(dev, file_priv);
+out_unlock:
+	mutex_unlock(&dev->master_mutex);
+	return ret;
+}
+
+int drm_master_open(struct drm_file *file_priv)
+{
+	struct drm_device *dev = file_priv->minor->dev;
+	int ret = 0;
+
+	/* if there is no current master make this fd it, but do not create
+	 * any master object for render clients */
+	mutex_lock(&dev->master_mutex);
+	if (!dev->master)
+		ret = drm_new_set_master(dev, file_priv);
+	else
+		file_priv->master = drm_master_get(dev->master);
+	mutex_unlock(&dev->master_mutex);
+
+	return ret;
+}
+
+void drm_master_release(struct drm_file *file_priv)
+{
+	struct drm_device *dev = file_priv->minor->dev;
+	struct drm_master *master = file_priv->master;
+
+	mutex_lock(&dev->master_mutex);
+	if (file_priv->magic)
+		idr_remove(&file_priv->master->magic_map, file_priv->magic);
+
+	if (!drm_is_current_master(file_priv))
+		goto out;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET)) {
+		/*
+		 * Since the master is disappearing, so is the
+		 * possibility to lock.
+		 */
+		mutex_lock(&dev->struct_mutex);
+		if (master->lock.hw_lock) {
+			if (dev->sigdata.lock == master->lock.hw_lock)
+				dev->sigdata.lock = NULL;
+			master->lock.hw_lock = NULL;
+			master->lock.file_priv = NULL;
+			wake_up_interruptible_all(&master->lock.lock_queue);
+		}
+		mutex_unlock(&dev->struct_mutex);
+	}
+
+	if (dev->master == file_priv->master)
+		drm_drop_master(dev, file_priv);
+out:
+	/* drop the master reference held by the file priv */
+	if (file_priv->master)
+		drm_master_put(&file_priv->master);
+	mutex_unlock(&dev->master_mutex);
+}
+
+/**
+ * drm_is_current_master - checks whether @priv is the current master
+ * @fpriv: DRM file private
+ *
+ * Checks whether @fpriv is current master on its device. This decides whether a
+ * client is allowed to run DRM_MASTER IOCTLs.
+ *
+ * Most of the modern IOCTL which require DRM_MASTER are for kernel modesetting
+ * - the current master is assumed to own the non-shareable display hardware.
+ */
+bool drm_is_current_master(struct drm_file *fpriv)
+{
+	return fpriv->is_master && fpriv->master == fpriv->minor->dev->master;
+}
+EXPORT_SYMBOL(drm_is_current_master);
+
+/**
+ * drm_master_get - reference a master pointer
+ * @master: struct &drm_master
+ *
+ * Increments the reference count of @master and returns a pointer to @master.
+ */
+struct drm_master *drm_master_get(struct drm_master *master)
+{
+	kref_get(&master->refcount);
+	return master;
+}
+EXPORT_SYMBOL(drm_master_get);
+
+static void drm_master_destroy(struct kref *kref)
+{
+	struct drm_master *master = container_of(kref, struct drm_master, refcount);
+	struct drm_device *dev = master->dev;
+
+	if (dev->driver->master_destroy)
+		dev->driver->master_destroy(dev, master);
+
+	drm_legacy_master_rmmaps(dev, master);
+
+	idr_destroy(&master->magic_map);
+	kfree(master->unique);
+	kfree(master);
+}
+
+/**
+ * drm_master_put - unreference and clear a master pointer
+ * @master: pointer to a pointer of struct &drm_master
+ *
+ * This decrements the &drm_master behind @master and sets it to NULL.
+ */
+void drm_master_put(struct drm_master **master)
+{
+	kref_put(&(*master)->refcount, drm_master_destroy);
+	*master = NULL;
+}
+EXPORT_SYMBOL(drm_master_put);
diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c
index b3654404abd0..255543086590 100644
--- a/drivers/gpu/drm/drm_bridge.c
+++ b/drivers/gpu/drm/drm_bridge.c
@@ -36,7 +36,7 @@
  * encoder chain.
  *
  * A bridge is always attached to a single &drm_encoder at a time, but can be
- * either connected to it directly, or through an intermediate bridge:
+ * either connected to it directly, or through an intermediate bridge::
  *
  *     encoder ---> bridge B ---> bridge A
  *
diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index 9b34158c0f77..c3a12cd8bd0d 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -51,7 +51,7 @@ static struct drm_map_list *drm_find_matching_map(struct drm_device *dev,
 		 */
 		if (!entry->map ||
 		    map->type != entry->map->type ||
-		    entry->master != dev->primary->master)
+		    entry->master != dev->master)
 			continue;
 		switch (map->type) {
 		case _DRM_SHM:
@@ -245,12 +245,12 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset,
 		map->offset = (unsigned long)map->handle;
 		if (map->flags & _DRM_CONTAINS_LOCK) {
 			/* Prevent a 2nd X Server from creating a 2nd lock */
-			if (dev->primary->master->lock.hw_lock != NULL) {
+			if (dev->master->lock.hw_lock != NULL) {
 				vfree(map->handle);
 				kfree(map);
 				return -EBUSY;
 			}
-			dev->sigdata.lock = dev->primary->master->lock.hw_lock = map->handle;	/* Pointer to lock */
+			dev->sigdata.lock = dev->master->lock.hw_lock = map->handle;	/* Pointer to lock */
 		}
 		break;
 	case _DRM_AGP: {
@@ -356,7 +356,7 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset,
 	mutex_unlock(&dev->struct_mutex);
 
 	if (!(map->flags & _DRM_DRIVER))
-		list->master = dev->primary->master;
+		list->master = dev->master;
 	*maplist = list;
 	return 0;
 }
diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c
index 059f7c39c582..a7916e5f8864 100644
--- a/drivers/gpu/drm/drm_cache.c
+++ b/drivers/gpu/drm/drm_cache.c
@@ -136,6 +136,7 @@ drm_clflush_virt_range(void *addr, unsigned long length)
 		mb();
 		for (; addr < end; addr += size)
 			clflushopt(addr);
+		clflushopt(end - 1); /* force serialisation */
 		mb();
 		return;
 	}
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 0e3cc66aa8b7..f1d9f0569d7f 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -39,6 +39,7 @@
 #include <drm/drm_fourcc.h>
 #include <drm/drm_modeset_lock.h>
 #include <drm/drm_atomic.h>
+#include <drm/drm_auth.h>
 
 #include "drm_crtc_internal.h"
 #include "drm_internal.h"
@@ -239,37 +240,6 @@ const char *drm_get_subpixel_order_name(enum subpixel_order order)
 }
 EXPORT_SYMBOL(drm_get_subpixel_order_name);
 
-static char printable_char(int c)
-{
-	return isascii(c) && isprint(c) ? c : '?';
-}
-
-/**
- * drm_get_format_name - return a string for drm fourcc format
- * @format: format to compute name of
- *
- * Note that the buffer used by this function is globally shared and owned by
- * the function itself.
- *
- * FIXME: This isn't really multithreading safe.
- */
-const char *drm_get_format_name(uint32_t format)
-{
-	static char buf[32];
-
-	snprintf(buf, sizeof(buf),
-		 "%c%c%c%c %s-endian (0x%08x)",
-		 printable_char(format & 0xff),
-		 printable_char((format >> 8) & 0xff),
-		 printable_char((format >> 16) & 0xff),
-		 printable_char((format >> 24) & 0x7f),
-		 format & DRM_FORMAT_BIG_ENDIAN ? "big" : "little",
-		 format);
-
-	return buf;
-}
-EXPORT_SYMBOL(drm_get_format_name);
-
 /*
  * Internal function to assign a slot in the object idr and optionally
  * register the object into the idr.
@@ -426,6 +396,51 @@ void drm_mode_object_reference(struct drm_mode_object *obj)
 }
 EXPORT_SYMBOL(drm_mode_object_reference);
 
+/**
+ * drm_crtc_force_disable - Forcibly turn off a CRTC
+ * @crtc: CRTC to turn off
+ *
+ * Returns:
+ * Zero on success, error code on failure.
+ */
+int drm_crtc_force_disable(struct drm_crtc *crtc)
+{
+	struct drm_mode_set set = {
+		.crtc = crtc,
+	};
+
+	return drm_mode_set_config_internal(&set);
+}
+EXPORT_SYMBOL(drm_crtc_force_disable);
+
+/**
+ * drm_crtc_force_disable_all - Forcibly turn off all enabled CRTCs
+ * @dev: DRM device whose CRTCs to turn off
+ *
+ * Drivers may want to call this on unload to ensure that all displays are
+ * unlit and the GPU is in a consistent, low power state. Takes modeset locks.
+ *
+ * Returns:
+ * Zero on success, error code on failure.
+ */
+int drm_crtc_force_disable_all(struct drm_device *dev)
+{
+	struct drm_crtc *crtc;
+	int ret = 0;
+
+	drm_modeset_lock_all(dev);
+	drm_for_each_crtc(crtc, dev)
+		if (crtc->enabled) {
+			ret = drm_crtc_force_disable(crtc);
+			if (ret)
+				goto out;
+		}
+out:
+	drm_modeset_unlock_all(dev);
+	return ret;
+}
+EXPORT_SYMBOL(drm_crtc_force_disable_all);
+
 static void drm_framebuffer_free(struct kref *kref)
 {
 	struct drm_framebuffer *fb =
@@ -535,7 +550,7 @@ EXPORT_SYMBOL(drm_framebuffer_unregister_private);
  *
  * Cleanup framebuffer. This function is intended to be used from the drivers
  * ->destroy callback. It can also be used to clean up driver private
- *  framebuffers embedded into a larger structure.
+ * framebuffers embedded into a larger structure.
  *
  * Note that this function does not remove the fb from active usuage - if it is
  * still used anywhere, hilarity can ensue since userspace could call getfb on
@@ -574,8 +589,6 @@ void drm_framebuffer_remove(struct drm_framebuffer *fb)
 	struct drm_device *dev;
 	struct drm_crtc *crtc;
 	struct drm_plane *plane;
-	struct drm_mode_set set;
-	int ret;
 
 	if (!fb)
 		return;
@@ -605,11 +618,7 @@ void drm_framebuffer_remove(struct drm_framebuffer *fb)
 		drm_for_each_crtc(crtc, dev) {
 			if (crtc->primary->fb == fb) {
 				/* should turn off the crtc */
-				memset(&set, 0, sizeof(struct drm_mode_set));
-				set.crtc = crtc;
-				set.fb = NULL;
-				ret = drm_mode_set_config_internal(&set);
-				if (ret)
+				if (drm_crtc_force_disable(crtc))
 					DRM_ERROR("failed to reset crtc %p when fb was deleted\n", crtc);
 			}
 		}
@@ -639,6 +648,31 @@ static unsigned int drm_num_crtcs(struct drm_device *dev)
 	return num;
 }
 
+static int drm_crtc_register_all(struct drm_device *dev)
+{
+	struct drm_crtc *crtc;
+	int ret = 0;
+
+	drm_for_each_crtc(crtc, dev) {
+		if (crtc->funcs->late_register)
+			ret = crtc->funcs->late_register(crtc);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void drm_crtc_unregister_all(struct drm_device *dev)
+{
+	struct drm_crtc *crtc;
+
+	drm_for_each_crtc(crtc, dev) {
+		if (crtc->funcs->early_unregister)
+			crtc->funcs->early_unregister(crtc);
+	}
+}
+
 /**
  * drm_crtc_init_with_planes - Initialise a new CRTC object with
  *    specified primary and cursor planes.
@@ -669,6 +703,9 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 	crtc->dev = dev;
 	crtc->funcs = funcs;
 
+	INIT_LIST_HEAD(&crtc->commit_list);
+	spin_lock_init(&crtc->commit_lock);
+
 	drm_modeset_lock_init(&crtc->mutex);
 	ret = drm_mode_object_get(dev, &crtc->base, DRM_MODE_OBJECT_CRTC);
 	if (ret)
@@ -692,7 +729,7 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 	crtc->base.properties = &crtc->properties;
 
 	list_add_tail(&crtc->head, &config->crtc_list);
-	config->num_crtc++;
+	crtc->index = config->num_crtc++;
 
 	crtc->primary = primary;
 	crtc->cursor = cursor;
@@ -722,6 +759,11 @@ void drm_crtc_cleanup(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 
+	/* Note that the crtc_list is considered to be static; should we
+	 * remove the drm_crtc at runtime we would have to decrement all
+	 * the indices on the drm_crtc after us in the crtc_list.
+	 */
+
 	kfree(crtc->gamma_store);
 	crtc->gamma_store = NULL;
 
@@ -741,29 +783,6 @@ void drm_crtc_cleanup(struct drm_crtc *crtc)
 }
 EXPORT_SYMBOL(drm_crtc_cleanup);
 
-/**
- * drm_crtc_index - find the index of a registered CRTC
- * @crtc: CRTC to find index for
- *
- * Given a registered CRTC, return the index of that CRTC within a DRM
- * device's list of CRTCs.
- */
-unsigned int drm_crtc_index(struct drm_crtc *crtc)
-{
-	unsigned int index = 0;
-	struct drm_crtc *tmp;
-
-	drm_for_each_crtc(tmp, crtc->dev) {
-		if (tmp == crtc)
-			return index;
-
-		index++;
-	}
-
-	BUG();
-}
-EXPORT_SYMBOL(drm_crtc_index);
-
 /*
  * drm_mode_remove - remove and free a mode
  * @connector: connector list to modify
@@ -909,11 +928,11 @@ int drm_connector_init(struct drm_device *dev,
 	connector->dev = dev;
 	connector->funcs = funcs;
 
-	connector->connector_id = ida_simple_get(&config->connector_ida, 0, 0, GFP_KERNEL);
-	if (connector->connector_id < 0) {
-		ret = connector->connector_id;
+	ret = ida_simple_get(&config->connector_ida, 0, 0, GFP_KERNEL);
+	if (ret < 0)
 		goto out_put;
-	}
+	connector->index = ret;
+	ret = 0;
 
 	connector->connector_type = connector_type;
 	connector->connector_type_id =
@@ -961,7 +980,7 @@ out_put_type_id:
 		ida_remove(connector_ida, connector->connector_type_id);
 out_put_id:
 	if (ret)
-		ida_remove(&config->connector_ida, connector->connector_id);
+		ida_remove(&config->connector_ida, connector->index);
 out_put:
 	if (ret)
 		drm_mode_object_unregister(dev, &connector->base);
@@ -984,6 +1003,12 @@ void drm_connector_cleanup(struct drm_connector *connector)
 	struct drm_device *dev = connector->dev;
 	struct drm_display_mode *mode, *t;
 
+	/* The connector should have been removed from userspace long before
+	 * it is finally destroyed.
+	 */
+	if (WARN_ON(connector->registered))
+		drm_connector_unregister(connector);
+
 	if (connector->tile_group) {
 		drm_mode_put_tile_group(dev, connector->tile_group);
 		connector->tile_group = NULL;
@@ -999,7 +1024,7 @@ void drm_connector_cleanup(struct drm_connector *connector)
 		   connector->connector_type_id);
 
 	ida_remove(&dev->mode_config.connector_ida,
-		   connector->connector_id);
+		   connector->index);
 
 	kfree(connector->display_info.bus_formats);
 	drm_mode_object_unregister(dev, &connector->base);
@@ -1030,19 +1055,34 @@ int drm_connector_register(struct drm_connector *connector)
 {
 	int ret;
 
+	if (connector->registered)
+		return 0;
+
 	ret = drm_sysfs_connector_add(connector);
 	if (ret)
 		return ret;
 
 	ret = drm_debugfs_connector_add(connector);
 	if (ret) {
-		drm_sysfs_connector_remove(connector);
-		return ret;
+		goto err_sysfs;
+	}
+
+	if (connector->funcs->late_register) {
+		ret = connector->funcs->late_register(connector);
+		if (ret)
+			goto err_debugfs;
 	}
 
 	drm_mode_object_register(connector->dev, &connector->base);
 
+	connector->registered = true;
 	return 0;
+
+err_debugfs:
+	drm_debugfs_connector_remove(connector);
+err_sysfs:
+	drm_sysfs_connector_remove(connector);
+	return ret;
 }
 EXPORT_SYMBOL(drm_connector_register);
 
@@ -1054,28 +1094,29 @@ EXPORT_SYMBOL(drm_connector_register);
  */
 void drm_connector_unregister(struct drm_connector *connector)
 {
+	if (!connector->registered)
+		return;
+
+	if (connector->funcs->early_unregister)
+		connector->funcs->early_unregister(connector);
+
 	drm_sysfs_connector_remove(connector);
 	drm_debugfs_connector_remove(connector);
+
+	connector->registered = false;
 }
 EXPORT_SYMBOL(drm_connector_unregister);
 
-/**
- * drm_connector_register_all - register all connectors
- * @dev: drm device
- *
- * This function registers all connectors in sysfs and other places so that
- * userspace can start to access them. Drivers can call it after calling
- * drm_dev_register() to complete the device registration, if they don't call
- * drm_connector_register() on each connector individually.
- *
- * When a device is unplugged and should be removed from userspace access,
- * call drm_connector_unregister_all(), which is the inverse of this
- * function.
- *
- * Returns:
- * Zero on success, error code on failure.
- */
-int drm_connector_register_all(struct drm_device *dev)
+static void drm_connector_unregister_all(struct drm_device *dev)
+{
+	struct drm_connector *connector;
+
+	/* FIXME: taking the mode config mutex ends up in a clash with sysfs */
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
+		drm_connector_unregister(connector);
+}
+
+static int drm_connector_register_all(struct drm_device *dev)
 {
 	struct drm_connector *connector;
 	int ret;
@@ -1097,27 +1138,31 @@ err:
 	drm_connector_unregister_all(dev);
 	return ret;
 }
-EXPORT_SYMBOL(drm_connector_register_all);
 
-/**
- * drm_connector_unregister_all - unregister connector userspace interfaces
- * @dev: drm device
- *
- * This functions unregisters all connectors from sysfs and other places so
- * that userspace can no longer access them. Drivers should call this as the
- * first step tearing down the device instace, or when the underlying
- * physical device disappeared (e.g. USB unplug), right before calling
- * drm_dev_unregister().
- */
-void drm_connector_unregister_all(struct drm_device *dev)
+static int drm_encoder_register_all(struct drm_device *dev)
 {
-	struct drm_connector *connector;
+	struct drm_encoder *encoder;
+	int ret = 0;
 
-	/* FIXME: taking the mode config mutex ends up in a clash with sysfs */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
-		drm_connector_unregister(connector);
+	drm_for_each_encoder(encoder, dev) {
+		if (encoder->funcs->late_register)
+			ret = encoder->funcs->late_register(encoder);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void drm_encoder_unregister_all(struct drm_device *dev)
+{
+	struct drm_encoder *encoder;
+
+	drm_for_each_encoder(encoder, dev) {
+		if (encoder->funcs->early_unregister)
+			encoder->funcs->early_unregister(encoder);
+	}
 }
-EXPORT_SYMBOL(drm_connector_unregister_all);
 
 /**
  * drm_encoder_init - Init a preallocated encoder
@@ -1166,7 +1211,7 @@ int drm_encoder_init(struct drm_device *dev,
 	}
 
 	list_add_tail(&encoder->head, &dev->mode_config.encoder_list);
-	dev->mode_config.num_encoder++;
+	encoder->index = dev->mode_config.num_encoder++;
 
 out_put:
 	if (ret)
@@ -1180,29 +1225,6 @@ out_unlock:
 EXPORT_SYMBOL(drm_encoder_init);
 
 /**
- * drm_encoder_index - find the index of a registered encoder
- * @encoder: encoder to find index for
- *
- * Given a registered encoder, return the index of that encoder within a DRM
- * device's list of encoders.
- */
-unsigned int drm_encoder_index(struct drm_encoder *encoder)
-{
-	unsigned int index = 0;
-	struct drm_encoder *tmp;
-
-	drm_for_each_encoder(tmp, encoder->dev) {
-		if (tmp == encoder)
-			return index;
-
-		index++;
-	}
-
-	BUG();
-}
-EXPORT_SYMBOL(drm_encoder_index);
-
-/**
  * drm_encoder_cleanup - cleans up an initialised encoder
  * @encoder: encoder to cleanup
  *
@@ -1212,6 +1234,11 @@ void drm_encoder_cleanup(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
 
+	/* Note that the encoder_list is considered to be static; should we
+	 * remove the drm_encoder at runtime we would have to decrement all
+	 * the indices on the drm_encoder after us in the encoder_list.
+	 */
+
 	drm_modeset_lock_all(dev);
 	drm_mode_object_unregister(dev, &encoder->base);
 	kfree(encoder->name);
@@ -1300,7 +1327,7 @@ int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane,
 	plane->type = type;
 
 	list_add_tail(&plane->head, &config->plane_list);
-	config->num_total_plane++;
+	plane->index = config->num_total_plane++;
 	if (plane->type == DRM_PLANE_TYPE_OVERLAY)
 		config->num_overlay_plane++;
 
@@ -1325,6 +1352,31 @@ int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane,
 }
 EXPORT_SYMBOL(drm_universal_plane_init);
 
+static int drm_plane_register_all(struct drm_device *dev)
+{
+	struct drm_plane *plane;
+	int ret = 0;
+
+	drm_for_each_plane(plane, dev) {
+		if (plane->funcs->late_register)
+			ret = plane->funcs->late_register(plane);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void drm_plane_unregister_all(struct drm_device *dev)
+{
+	struct drm_plane *plane;
+
+	drm_for_each_plane(plane, dev) {
+		if (plane->funcs->early_unregister)
+			plane->funcs->early_unregister(plane);
+	}
+}
+
 /**
  * drm_plane_init - Initialize a legacy plane
  * @dev: DRM device
@@ -1374,6 +1426,11 @@ void drm_plane_cleanup(struct drm_plane *plane)
 
 	BUG_ON(list_empty(&plane->head));
 
+	/* Note that the plane_list is considered to be static; should we
+	 * remove the drm_plane at runtime we would have to decrement all
+	 * the indices on the drm_plane after us in the plane_list.
+	 */
+
 	list_del(&plane->head);
 	dev->mode_config.num_total_plane--;
 	if (plane->type == DRM_PLANE_TYPE_OVERLAY)
@@ -1391,29 +1448,6 @@ void drm_plane_cleanup(struct drm_plane *plane)
 EXPORT_SYMBOL(drm_plane_cleanup);
 
 /**
- * drm_plane_index - find the index of a registered plane
- * @plane: plane to find index for
- *
- * Given a registered plane, return the index of that CRTC within a DRM
- * device's list of planes.
- */
-unsigned int drm_plane_index(struct drm_plane *plane)
-{
-	unsigned int index = 0;
-	struct drm_plane *tmp;
-
-	drm_for_each_plane(tmp, plane->dev) {
-		if (tmp == plane)
-			return index;
-
-		index++;
-	}
-
-	BUG();
-}
-EXPORT_SYMBOL(drm_plane_index);
-
-/**
  * drm_plane_from_index - find the registered plane at an index
  * @dev: DRM device
  * @idx: index of registered plane to find for
@@ -1425,13 +1459,11 @@ struct drm_plane *
 drm_plane_from_index(struct drm_device *dev, int idx)
 {
 	struct drm_plane *plane;
-	unsigned int i = 0;
 
-	drm_for_each_plane(plane, dev) {
-		if (i == idx)
+	drm_for_each_plane(plane, dev)
+		if (idx == plane->index)
 			return plane;
-		i++;
-	}
+
 	return NULL;
 }
 EXPORT_SYMBOL(drm_plane_from_index);
@@ -1467,6 +1499,46 @@ void drm_plane_force_disable(struct drm_plane *plane)
 }
 EXPORT_SYMBOL(drm_plane_force_disable);
 
+int drm_modeset_register_all(struct drm_device *dev)
+{
+	int ret;
+
+	ret = drm_plane_register_all(dev);
+	if (ret)
+		goto err_plane;
+
+	ret = drm_crtc_register_all(dev);
+	if  (ret)
+		goto err_crtc;
+
+	ret = drm_encoder_register_all(dev);
+	if (ret)
+		goto err_encoder;
+
+	ret = drm_connector_register_all(dev);
+	if (ret)
+		goto err_connector;
+
+	return 0;
+
+err_connector:
+	drm_encoder_unregister_all(dev);
+err_encoder:
+	drm_crtc_unregister_all(dev);
+err_crtc:
+	drm_plane_unregister_all(dev);
+err_plane:
+	return ret;
+}
+
+void drm_modeset_unregister_all(struct drm_device *dev)
+{
+	drm_connector_unregister_all(dev);
+	drm_encoder_unregister_all(dev);
+	drm_crtc_unregister_all(dev);
+	drm_plane_unregister_all(dev);
+}
+
 static int drm_mode_create_standard_properties(struct drm_device *dev)
 {
 	struct drm_property *prop;
@@ -2975,6 +3047,8 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 				DRM_DEBUG_KMS("failed to wrap cursor buffer in drm framebuffer\n");
 				return PTR_ERR(fb);
 			}
+			fb->hot_x = req->hot_x;
+			fb->hot_y = req->hot_y;
 		} else {
 			fb = NULL;
 		}
@@ -3581,7 +3655,7 @@ int drm_mode_getfb(struct drm_device *dev,
 	r->bpp = fb->bits_per_pixel;
 	r->pitch = fb->pitches[0];
 	if (fb->funcs->create_handle) {
-		if (file_priv->is_master || capable(CAP_SYS_ADMIN) ||
+		if (drm_is_current_master(file_priv) || capable(CAP_SYS_ADMIN) ||
 		    drm_is_control_client(file_priv)) {
 			ret = fb->funcs->create_handle(fb, file_priv,
 						       &r->handle);
@@ -3738,6 +3812,13 @@ void drm_fb_release(struct drm_file *priv)
 	}
 }
 
+static bool drm_property_type_valid(struct drm_property *property)
+{
+	if (property->flags & DRM_MODE_PROP_EXTENDED_TYPE)
+		return !(property->flags & DRM_MODE_PROP_LEGACY_TYPE);
+	return !!(property->flags & DRM_MODE_PROP_LEGACY_TYPE);
+}
+
 /**
  * drm_property_create - create a new property type
  * @dev: drm device
@@ -5138,6 +5219,9 @@ EXPORT_SYMBOL(drm_mode_connector_attach_encoder);
 int drm_mode_crtc_set_gamma_size(struct drm_crtc *crtc,
 				 int gamma_size)
 {
+	uint16_t *r_base, *g_base, *b_base;
+	int i;
+
 	crtc->gamma_size = gamma_size;
 
 	crtc->gamma_store = kcalloc(gamma_size, sizeof(uint16_t) * 3,
@@ -5147,6 +5231,16 @@ int drm_mode_crtc_set_gamma_size(struct drm_crtc *crtc,
 		return -ENOMEM;
 	}
 
+	r_base = crtc->gamma_store;
+	g_base = r_base + gamma_size;
+	b_base = g_base + gamma_size;
+	for (i = 0; i < gamma_size; i++) {
+		r_base[i] = i << 8;
+		g_base[i] = i << 8;
+		b_base[i] = i << 8;
+	}
+
+
 	return 0;
 }
 EXPORT_SYMBOL(drm_mode_crtc_set_gamma_size);
@@ -5214,7 +5308,7 @@ int drm_mode_gamma_set_ioctl(struct drm_device *dev,
 		goto out;
 	}
 
-	crtc->funcs->gamma_set(crtc, r_base, g_base, b_base, 0, crtc->gamma_size);
+	ret = crtc->funcs->gamma_set(crtc, r_base, g_base, b_base, crtc->gamma_size);
 
 out:
 	drm_modeset_unlock_all(dev);
@@ -5544,264 +5638,6 @@ int drm_mode_destroy_dumb_ioctl(struct drm_device *dev,
 }
 
 /**
- * drm_fb_get_bpp_depth - get the bpp/depth values for format
- * @format: pixel format (DRM_FORMAT_*)
- * @depth: storage for the depth value
- * @bpp: storage for the bpp value
- *
- * This only supports RGB formats here for compat with code that doesn't use
- * pixel formats directly yet.
- */
-void drm_fb_get_bpp_depth(uint32_t format, unsigned int *depth,
-			  int *bpp)
-{
-	switch (format) {
-	case DRM_FORMAT_C8:
-	case DRM_FORMAT_RGB332:
-	case DRM_FORMAT_BGR233:
-		*depth = 8;
-		*bpp = 8;
-		break;
-	case DRM_FORMAT_XRGB1555:
-	case DRM_FORMAT_XBGR1555:
-	case DRM_FORMAT_RGBX5551:
-	case DRM_FORMAT_BGRX5551:
-	case DRM_FORMAT_ARGB1555:
-	case DRM_FORMAT_ABGR1555:
-	case DRM_FORMAT_RGBA5551:
-	case DRM_FORMAT_BGRA5551:
-		*depth = 15;
-		*bpp = 16;
-		break;
-	case DRM_FORMAT_RGB565:
-	case DRM_FORMAT_BGR565:
-		*depth = 16;
-		*bpp = 16;
-		break;
-	case DRM_FORMAT_RGB888:
-	case DRM_FORMAT_BGR888:
-		*depth = 24;
-		*bpp = 24;
-		break;
-	case DRM_FORMAT_XRGB8888:
-	case DRM_FORMAT_XBGR8888:
-	case DRM_FORMAT_RGBX8888:
-	case DRM_FORMAT_BGRX8888:
-		*depth = 24;
-		*bpp = 32;
-		break;
-	case DRM_FORMAT_XRGB2101010:
-	case DRM_FORMAT_XBGR2101010:
-	case DRM_FORMAT_RGBX1010102:
-	case DRM_FORMAT_BGRX1010102:
-	case DRM_FORMAT_ARGB2101010:
-	case DRM_FORMAT_ABGR2101010:
-	case DRM_FORMAT_RGBA1010102:
-	case DRM_FORMAT_BGRA1010102:
-		*depth = 30;
-		*bpp = 32;
-		break;
-	case DRM_FORMAT_ARGB8888:
-	case DRM_FORMAT_ABGR8888:
-	case DRM_FORMAT_RGBA8888:
-	case DRM_FORMAT_BGRA8888:
-		*depth = 32;
-		*bpp = 32;
-		break;
-	default:
-		DRM_DEBUG_KMS("unsupported pixel format %s\n",
-			      drm_get_format_name(format));
-		*depth = 0;
-		*bpp = 0;
-		break;
-	}
-}
-EXPORT_SYMBOL(drm_fb_get_bpp_depth);
-
-/**
- * drm_format_num_planes - get the number of planes for format
- * @format: pixel format (DRM_FORMAT_*)
- *
- * Returns:
- * The number of planes used by the specified pixel format.
- */
-int drm_format_num_planes(uint32_t format)
-{
-	switch (format) {
-	case DRM_FORMAT_YUV410:
-	case DRM_FORMAT_YVU410:
-	case DRM_FORMAT_YUV411:
-	case DRM_FORMAT_YVU411:
-	case DRM_FORMAT_YUV420:
-	case DRM_FORMAT_YVU420:
-	case DRM_FORMAT_YUV422:
-	case DRM_FORMAT_YVU422:
-	case DRM_FORMAT_YUV444:
-	case DRM_FORMAT_YVU444:
-		return 3;
-	case DRM_FORMAT_NV12:
-	case DRM_FORMAT_NV21:
-	case DRM_FORMAT_NV16:
-	case DRM_FORMAT_NV61:
-	case DRM_FORMAT_NV24:
-	case DRM_FORMAT_NV42:
-		return 2;
-	default:
-		return 1;
-	}
-}
-EXPORT_SYMBOL(drm_format_num_planes);
-
-/**
- * drm_format_plane_cpp - determine the bytes per pixel value
- * @format: pixel format (DRM_FORMAT_*)
- * @plane: plane index
- *
- * Returns:
- * The bytes per pixel value for the specified plane.
- */
-int drm_format_plane_cpp(uint32_t format, int plane)
-{
-	unsigned int depth;
-	int bpp;
-
-	if (plane >= drm_format_num_planes(format))
-		return 0;
-
-	switch (format) {
-	case DRM_FORMAT_YUYV:
-	case DRM_FORMAT_YVYU:
-	case DRM_FORMAT_UYVY:
-	case DRM_FORMAT_VYUY:
-		return 2;
-	case DRM_FORMAT_NV12:
-	case DRM_FORMAT_NV21:
-	case DRM_FORMAT_NV16:
-	case DRM_FORMAT_NV61:
-	case DRM_FORMAT_NV24:
-	case DRM_FORMAT_NV42:
-		return plane ? 2 : 1;
-	case DRM_FORMAT_YUV410:
-	case DRM_FORMAT_YVU410:
-	case DRM_FORMAT_YUV411:
-	case DRM_FORMAT_YVU411:
-	case DRM_FORMAT_YUV420:
-	case DRM_FORMAT_YVU420:
-	case DRM_FORMAT_YUV422:
-	case DRM_FORMAT_YVU422:
-	case DRM_FORMAT_YUV444:
-	case DRM_FORMAT_YVU444:
-		return 1;
-	default:
-		drm_fb_get_bpp_depth(format, &depth, &bpp);
-		return bpp >> 3;
-	}
-}
-EXPORT_SYMBOL(drm_format_plane_cpp);
-
-/**
- * drm_format_horz_chroma_subsampling - get the horizontal chroma subsampling factor
- * @format: pixel format (DRM_FORMAT_*)
- *
- * Returns:
- * The horizontal chroma subsampling factor for the
- * specified pixel format.
- */
-int drm_format_horz_chroma_subsampling(uint32_t format)
-{
-	switch (format) {
-	case DRM_FORMAT_YUV411:
-	case DRM_FORMAT_YVU411:
-	case DRM_FORMAT_YUV410:
-	case DRM_FORMAT_YVU410:
-		return 4;
-	case DRM_FORMAT_YUYV:
-	case DRM_FORMAT_YVYU:
-	case DRM_FORMAT_UYVY:
-	case DRM_FORMAT_VYUY:
-	case DRM_FORMAT_NV12:
-	case DRM_FORMAT_NV21:
-	case DRM_FORMAT_NV16:
-	case DRM_FORMAT_NV61:
-	case DRM_FORMAT_YUV422:
-	case DRM_FORMAT_YVU422:
-	case DRM_FORMAT_YUV420:
-	case DRM_FORMAT_YVU420:
-		return 2;
-	default:
-		return 1;
-	}
-}
-EXPORT_SYMBOL(drm_format_horz_chroma_subsampling);
-
-/**
- * drm_format_vert_chroma_subsampling - get the vertical chroma subsampling factor
- * @format: pixel format (DRM_FORMAT_*)
- *
- * Returns:
- * The vertical chroma subsampling factor for the
- * specified pixel format.
- */
-int drm_format_vert_chroma_subsampling(uint32_t format)
-{
-	switch (format) {
-	case DRM_FORMAT_YUV410:
-	case DRM_FORMAT_YVU410:
-		return 4;
-	case DRM_FORMAT_YUV420:
-	case DRM_FORMAT_YVU420:
-	case DRM_FORMAT_NV12:
-	case DRM_FORMAT_NV21:
-		return 2;
-	default:
-		return 1;
-	}
-}
-EXPORT_SYMBOL(drm_format_vert_chroma_subsampling);
-
-/**
- * drm_format_plane_width - width of the plane given the first plane
- * @width: width of the first plane
- * @format: pixel format
- * @plane: plane index
- *
- * Returns:
- * The width of @plane, given that the width of the first plane is @width.
- */
-int drm_format_plane_width(int width, uint32_t format, int plane)
-{
-	if (plane >= drm_format_num_planes(format))
-		return 0;
-
-	if (plane == 0)
-		return width;
-
-	return width / drm_format_horz_chroma_subsampling(format);
-}
-EXPORT_SYMBOL(drm_format_plane_width);
-
-/**
- * drm_format_plane_height - height of the plane given the first plane
- * @height: height of the first plane
- * @format: pixel format
- * @plane: plane index
- *
- * Returns:
- * The height of @plane, given that the height of the first plane is @height.
- */
-int drm_format_plane_height(int height, uint32_t format, int plane)
-{
-	if (plane >= drm_format_num_planes(format))
-		return 0;
-
-	if (plane == 0)
-		return height;
-
-	return height / drm_format_vert_chroma_subsampling(format);
-}
-EXPORT_SYMBOL(drm_format_plane_height);
-
-/**
  * drm_rotation_simplify() - Try to simplify the rotation
  * @rotation: Rotation to be simplified
  * @supported_rotations: Supported rotations
@@ -6064,3 +5900,48 @@ struct drm_tile_group *drm_mode_create_tile_group(struct drm_device *dev,
 	return tg;
 }
 EXPORT_SYMBOL(drm_mode_create_tile_group);
+
+/**
+ * drm_crtc_enable_color_mgmt - enable color management properties
+ * @crtc: DRM CRTC
+ * @degamma_lut_size: the size of the degamma lut (before CSC)
+ * @has_ctm: whether to attach ctm_property for CSC matrix
+ * @gamma_lut_size: the size of the gamma lut (after CSC)
+ *
+ * This function lets the driver enable the color correction
+ * properties on a CRTC. This includes 3 degamma, csc and gamma
+ * properties that userspace can set and 2 size properties to inform
+ * the userspace of the lut sizes. Each of the properties are
+ * optional. The gamma and degamma properties are only attached if
+ * their size is not 0 and ctm_property is only attached if has_ctm is
+ * true.
+ */
+void drm_crtc_enable_color_mgmt(struct drm_crtc *crtc,
+				uint degamma_lut_size,
+				bool has_ctm,
+				uint gamma_lut_size)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_mode_config *config = &dev->mode_config;
+
+	if (degamma_lut_size) {
+		drm_object_attach_property(&crtc->base,
+					   config->degamma_lut_property, 0);
+		drm_object_attach_property(&crtc->base,
+					   config->degamma_lut_size_property,
+					   degamma_lut_size);
+	}
+
+	if (has_ctm)
+		drm_object_attach_property(&crtc->base,
+					   config->ctm_property, 0);
+
+	if (gamma_lut_size) {
+		drm_object_attach_property(&crtc->base,
+					   config->gamma_lut_property, 0);
+		drm_object_attach_property(&crtc->base,
+					   config->gamma_lut_size_property,
+					   gamma_lut_size);
+	}
+}
+EXPORT_SYMBOL(drm_crtc_enable_color_mgmt);
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 26feb2f8453f..604d3ef72ffa 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -232,6 +232,9 @@ static void __drm_helper_disable_unused_functions(struct drm_device *dev)
  */
 void drm_helper_disable_unused_functions(struct drm_device *dev)
 {
+	if (drm_core_check_feature(dev, DRIVER_ATOMIC))
+		DRM_ERROR("Called for atomic driver, this is not what you want.\n");
+
 	drm_modeset_lock_all(dev);
 	__drm_helper_disable_unused_functions(dev);
 	drm_modeset_unlock_all(dev);
@@ -1123,36 +1126,3 @@ int drm_helper_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
 	return drm_plane_helper_commit(plane, plane_state, old_fb);
 }
 EXPORT_SYMBOL(drm_helper_crtc_mode_set_base);
-
-/**
- * drm_helper_crtc_enable_color_mgmt - enable color management properties
- * @crtc: DRM CRTC
- * @degamma_lut_size: the size of the degamma lut (before CSC)
- * @gamma_lut_size: the size of the gamma lut (after CSC)
- *
- * This function lets the driver enable the color correction properties on a
- * CRTC. This includes 3 degamma, csc and gamma properties that userspace can
- * set and 2 size properties to inform the userspace of the lut sizes.
- */
-void drm_helper_crtc_enable_color_mgmt(struct drm_crtc *crtc,
-				       int degamma_lut_size,
-				       int gamma_lut_size)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_mode_config *config = &dev->mode_config;
-
-	drm_object_attach_property(&crtc->base,
-				   config->degamma_lut_property, 0);
-	drm_object_attach_property(&crtc->base,
-				   config->ctm_property, 0);
-	drm_object_attach_property(&crtc->base,
-				   config->gamma_lut_property, 0);
-
-	drm_object_attach_property(&crtc->base,
-				   config->degamma_lut_size_property,
-				   degamma_lut_size);
-	drm_object_attach_property(&crtc->base,
-				   config->gamma_lut_size_property,
-				   gamma_lut_size);
-}
-EXPORT_SYMBOL(drm_helper_crtc_enable_color_mgmt);
diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
index a78c138282ea..47a500b90fd7 100644
--- a/drivers/gpu/drm/drm_crtc_internal.h
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -31,14 +31,100 @@
  * and are not exported to drivers.
  */
 
+
+/* drm_crtc.c */
+void drm_connector_ida_init(void);
+void drm_connector_ida_destroy(void);
 int drm_mode_object_get(struct drm_device *dev,
 			struct drm_mode_object *obj, uint32_t obj_type);
 void drm_mode_object_unregister(struct drm_device *dev,
 				struct drm_mode_object *object);
+bool drm_property_change_valid_get(struct drm_property *property,
+				   uint64_t value,
+				   struct drm_mode_object **ref);
+void drm_property_change_valid_put(struct drm_property *property,
+				   struct drm_mode_object *ref);
+
+int drm_plane_check_pixel_format(const struct drm_plane *plane,
+				 u32 format);
+int drm_crtc_check_viewport(const struct drm_crtc *crtc,
+			    int x, int y,
+			    const struct drm_display_mode *mode,
+			    const struct drm_framebuffer *fb);
+
+void drm_fb_release(struct drm_file *file_priv);
+void drm_property_destroy_user_blobs(struct drm_device *dev,
+				     struct drm_file *file_priv);
+
+/* dumb buffer support IOCTLs */
+int drm_mode_create_dumb_ioctl(struct drm_device *dev,
+			       void *data, struct drm_file *file_priv);
+int drm_mode_mmap_dumb_ioctl(struct drm_device *dev,
+			     void *data, struct drm_file *file_priv);
+int drm_mode_destroy_dumb_ioctl(struct drm_device *dev,
+				void *data, struct drm_file *file_priv);
+
+/* framebuffer IOCTLs */
+extern int drm_mode_addfb(struct drm_device *dev,
+			  void *data, struct drm_file *file_priv);
+extern int drm_mode_addfb2(struct drm_device *dev,
+			   void *data, struct drm_file *file_priv);
+int drm_mode_rmfb(struct drm_device *dev,
+			 void *data, struct drm_file *file_priv);
+int drm_mode_getfb(struct drm_device *dev,
+		   void *data, struct drm_file *file_priv);
+int drm_mode_dirtyfb_ioctl(struct drm_device *dev,
+			   void *data, struct drm_file *file_priv);
+
+/* IOCTLs */
+int drm_mode_obj_get_properties_ioctl(struct drm_device *dev, void *data,
+				      struct drm_file *file_priv);
+int drm_mode_obj_set_property_ioctl(struct drm_device *dev, void *data,
+				    struct drm_file *file_priv);
+
+int drm_mode_getresources(struct drm_device *dev,
+			  void *data, struct drm_file *file_priv);
+int drm_mode_getplane_res(struct drm_device *dev, void *data,
+			  struct drm_file *file_priv);
+int drm_mode_getcrtc(struct drm_device *dev,
+		     void *data, struct drm_file *file_priv);
+int drm_mode_getconnector(struct drm_device *dev,
+			  void *data, struct drm_file *file_priv);
+int drm_mode_setcrtc(struct drm_device *dev,
+		     void *data, struct drm_file *file_priv);
+int drm_mode_getplane(struct drm_device *dev,
+		      void *data, struct drm_file *file_priv);
+int drm_mode_setplane(struct drm_device *dev,
+		      void *data, struct drm_file *file_priv);
+int drm_mode_cursor_ioctl(struct drm_device *dev,
+			  void *data, struct drm_file *file_priv);
+int drm_mode_cursor2_ioctl(struct drm_device *dev,
+			   void *data, struct drm_file *file_priv);
+int drm_mode_getproperty_ioctl(struct drm_device *dev,
+			       void *data, struct drm_file *file_priv);
+int drm_mode_getblob_ioctl(struct drm_device *dev,
+			   void *data, struct drm_file *file_priv);
+int drm_mode_createblob_ioctl(struct drm_device *dev,
+			      void *data, struct drm_file *file_priv);
+int drm_mode_destroyblob_ioctl(struct drm_device *dev,
+			       void *data, struct drm_file *file_priv);
+int drm_mode_connector_property_set_ioctl(struct drm_device *dev,
+					  void *data, struct drm_file *file_priv);
+int drm_mode_getencoder(struct drm_device *dev,
+			void *data, struct drm_file *file_priv);
+int drm_mode_gamma_get_ioctl(struct drm_device *dev,
+			     void *data, struct drm_file *file_priv);
+int drm_mode_gamma_set_ioctl(struct drm_device *dev,
+			     void *data, struct drm_file *file_priv);
+
+int drm_mode_page_flip_ioctl(struct drm_device *dev,
+			     void *data, struct drm_file *file_priv);
 
 /* drm_atomic.c */
 int drm_atomic_get_property(struct drm_mode_object *obj,
-			   struct drm_property *property, uint64_t *val);
+			    struct drm_property *property, uint64_t *val);
 int drm_mode_atomic_ioctl(struct drm_device *dev,
 			  void *data, struct drm_file *file_priv);
 
+int drm_modeset_register_all(struct drm_device *dev);
+void drm_modeset_unregister_all(struct drm_device *dev);
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index 3bcf8e6a85b3..fa10cef2ba37 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -46,11 +46,8 @@
 
 static const struct drm_info_list drm_debugfs_list[] = {
 	{"name", drm_name_info, 0},
-	{"vm", drm_vm_info, 0},
 	{"clients", drm_clients_info, 0},
-	{"bufs", drm_bufs_info, 0},
 	{"gem_names", drm_gem_name_info, DRIVER_GEM},
-	{"vma", drm_vma_info, 0},
 };
 #define DRM_DEBUGFS_ENTRIES ARRAY_SIZE(drm_debugfs_list)
 
diff --git a/drivers/gpu/drm/drm_dp_aux_dev.c b/drivers/gpu/drm/drm_dp_aux_dev.c
index 3334baacf43d..734f86a345f6 100644
--- a/drivers/gpu/drm/drm_dp_aux_dev.c
+++ b/drivers/gpu/drm/drm_dp_aux_dev.c
@@ -355,8 +355,7 @@ int drm_dp_aux_dev_init(void)
 
 	drm_dp_aux_dev_class = class_create(THIS_MODULE, "drm_dp_aux_dev");
 	if (IS_ERR(drm_dp_aux_dev_class)) {
-		res = PTR_ERR(drm_dp_aux_dev_class);
-		goto out;
+		return PTR_ERR(drm_dp_aux_dev_class);
 	}
 	drm_dp_aux_dev_class->dev_groups = drm_dp_aux_groups;
 
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index eeaf5a7c3aa7..eae5ef963cb7 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -203,7 +203,7 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request,
 
 		ret = aux->transfer(aux, &msg);
 
-		if (ret > 0) {
+		if (ret >= 0) {
 			native_reply = msg.reply & DP_AUX_NATIVE_REPLY_MASK;
 			if (native_reply == DP_AUX_NATIVE_REPLY_ACK) {
 				if (ret == size)
@@ -708,8 +708,6 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs,
 
 	memset(&msg, 0, sizeof(msg));
 
-	mutex_lock(&aux->hw_mutex);
-
 	for (i = 0; i < num; i++) {
 		msg.address = msgs[i].addr;
 		drm_dp_i2c_msg_set_request(&msg, &msgs[i]);
@@ -764,8 +762,6 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs,
 	msg.size = 0;
 	(void)drm_dp_i2c_do_msg(aux, &msg);
 
-	mutex_unlock(&aux->hw_mutex);
-
 	return err;
 }
 
@@ -774,22 +770,64 @@ static const struct i2c_algorithm drm_dp_i2c_algo = {
 	.master_xfer = drm_dp_i2c_xfer,
 };
 
+static struct drm_dp_aux *i2c_to_aux(struct i2c_adapter *i2c)
+{
+	return container_of(i2c, struct drm_dp_aux, ddc);
+}
+
+static void lock_bus(struct i2c_adapter *i2c, unsigned int flags)
+{
+	mutex_lock(&i2c_to_aux(i2c)->hw_mutex);
+}
+
+static int trylock_bus(struct i2c_adapter *i2c, unsigned int flags)
+{
+	return mutex_trylock(&i2c_to_aux(i2c)->hw_mutex);
+}
+
+static void unlock_bus(struct i2c_adapter *i2c, unsigned int flags)
+{
+	mutex_unlock(&i2c_to_aux(i2c)->hw_mutex);
+}
+
 /**
- * drm_dp_aux_register() - initialise and register aux channel
+ * drm_dp_aux_init() - minimally initialise an aux channel
  * @aux: DisplayPort AUX channel
  *
- * Returns 0 on success or a negative error code on failure.
+ * If you need to use the drm_dp_aux's i2c adapter prior to registering it
+ * with the outside world, call drm_dp_aux_init() first. You must still
+ * call drm_dp_aux_register() once the connector has been registered to
+ * allow userspace access to the auxiliary DP channel.
  */
-int drm_dp_aux_register(struct drm_dp_aux *aux)
+void drm_dp_aux_init(struct drm_dp_aux *aux)
 {
-	int ret;
-
 	mutex_init(&aux->hw_mutex);
 
 	aux->ddc.algo = &drm_dp_i2c_algo;
 	aux->ddc.algo_data = aux;
 	aux->ddc.retries = 3;
 
+	aux->ddc.lock_bus = lock_bus;
+	aux->ddc.trylock_bus = trylock_bus;
+	aux->ddc.unlock_bus = unlock_bus;
+}
+EXPORT_SYMBOL(drm_dp_aux_init);
+
+/**
+ * drm_dp_aux_register() - initialise and register aux channel
+ * @aux: DisplayPort AUX channel
+ *
+ * Automatically calls drm_dp_aux_init() if this hasn't been done yet.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+int drm_dp_aux_register(struct drm_dp_aux *aux)
+{
+	int ret;
+
+	if (!aux->ddc.algo)
+		drm_dp_aux_init(aux);
+
 	aux->ddc.class = I2C_CLASS_DDC;
 	aux->ddc.owner = THIS_MODULE;
 	aux->ddc.dev.parent = aux->dev;
@@ -822,3 +860,35 @@ void drm_dp_aux_unregister(struct drm_dp_aux *aux)
 	i2c_del_adapter(&aux->ddc);
 }
 EXPORT_SYMBOL(drm_dp_aux_unregister);
+
+#define PSR_SETUP_TIME(x) [DP_PSR_SETUP_TIME_ ## x >> DP_PSR_SETUP_TIME_SHIFT] = (x)
+
+/**
+ * drm_dp_psr_setup_time() - PSR setup in time usec
+ * @psr_cap: PSR capabilities from DPCD
+ *
+ * Returns:
+ * PSR setup time for the panel in microseconds,  negative
+ * error code on failure.
+ */
+int drm_dp_psr_setup_time(const u8 psr_cap[EDP_PSR_RECEIVER_CAP_SIZE])
+{
+	static const u16 psr_setup_time_us[] = {
+		PSR_SETUP_TIME(330),
+		PSR_SETUP_TIME(275),
+		PSR_SETUP_TIME(165),
+		PSR_SETUP_TIME(110),
+		PSR_SETUP_TIME(55),
+		PSR_SETUP_TIME(0),
+	};
+	int i;
+
+	i = (psr_cap[1] & DP_PSR_SETUP_TIME_MASK) >> DP_PSR_SETUP_TIME_SHIFT;
+	if (i >= ARRAY_SIZE(psr_setup_time_us))
+		return -EINVAL;
+
+	return psr_setup_time_us[i];
+}
+EXPORT_SYMBOL(drm_dp_psr_setup_time);
+
+#undef PSR_SETUP_TIME
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 6537908050d7..04e457117980 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1493,11 +1493,8 @@ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr)
 	WARN_ON(!mutex_is_locked(&mgr->qlock));
 
 	/* construct a chunk from the first msg in the tx_msg queue */
-	if (list_empty(&mgr->tx_msg_downq)) {
-		mgr->tx_down_in_progress = false;
+	if (list_empty(&mgr->tx_msg_downq))
 		return;
-	}
-	mgr->tx_down_in_progress = true;
 
 	txmsg = list_first_entry(&mgr->tx_msg_downq, struct drm_dp_sideband_msg_tx, next);
 	ret = process_single_tx_qlock(mgr, txmsg, false);
@@ -1512,10 +1509,6 @@ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr)
 		txmsg->state = DRM_DP_SIDEBAND_TX_TIMEOUT;
 		wake_up(&mgr->tx_waitq);
 	}
-	if (list_empty(&mgr->tx_msg_downq)) {
-		mgr->tx_down_in_progress = false;
-		return;
-	}
 }
 
 /* called holding qlock */
@@ -1538,7 +1531,7 @@ static void drm_dp_queue_down_tx(struct drm_dp_mst_topology_mgr *mgr,
 {
 	mutex_lock(&mgr->qlock);
 	list_add_tail(&txmsg->next, &mgr->tx_msg_downq);
-	if (!mgr->tx_down_in_progress)
+	if (list_is_singular(&mgr->tx_msg_downq))
 		process_single_down_tx_qlock(mgr);
 	mutex_unlock(&mgr->qlock);
 }
@@ -2372,6 +2365,7 @@ EXPORT_SYMBOL(drm_dp_mst_hpd_irq);
 
 /**
  * drm_dp_mst_detect_port() - get connection status for an MST port
+ * @connector: DRM connector for this port
  * @mgr: manager for this port
  * @port: unverified pointer to a port
  *
@@ -2887,7 +2881,7 @@ static void drm_dp_tx_work(struct work_struct *work)
 	struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, tx_work);
 
 	mutex_lock(&mgr->qlock);
-	if (mgr->tx_down_in_progress)
+	if (!list_empty(&mgr->tx_msg_downq))
 		process_single_down_tx_qlock(mgr);
 	mutex_unlock(&mgr->qlock);
 }
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index bff89226a344..be27ed36f56e 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -34,8 +34,10 @@
 #include <linux/slab.h>
 #include <drm/drmP.h>
 #include <drm/drm_core.h>
+#include "drm_crtc_internal.h"
 #include "drm_legacy.h"
 #include "drm_internal.h"
+#include "drm_crtc_internal.h"
 
 /*
  * drm_debug: Enable debug output.
@@ -93,114 +95,6 @@ void drm_ut_debug_printk(const char *function_name, const char *format, ...)
 }
 EXPORT_SYMBOL(drm_ut_debug_printk);
 
-struct drm_master *drm_master_create(struct drm_minor *minor)
-{
-	struct drm_master *master;
-
-	master = kzalloc(sizeof(*master), GFP_KERNEL);
-	if (!master)
-		return NULL;
-
-	kref_init(&master->refcount);
-	spin_lock_init(&master->lock.spinlock);
-	init_waitqueue_head(&master->lock.lock_queue);
-	idr_init(&master->magic_map);
-	master->minor = minor;
-
-	return master;
-}
-
-struct drm_master *drm_master_get(struct drm_master *master)
-{
-	kref_get(&master->refcount);
-	return master;
-}
-EXPORT_SYMBOL(drm_master_get);
-
-static void drm_master_destroy(struct kref *kref)
-{
-	struct drm_master *master = container_of(kref, struct drm_master, refcount);
-	struct drm_device *dev = master->minor->dev;
-
-	if (dev->driver->master_destroy)
-		dev->driver->master_destroy(dev, master);
-
-	drm_legacy_master_rmmaps(dev, master);
-
-	idr_destroy(&master->magic_map);
-	kfree(master->unique);
-	kfree(master);
-}
-
-void drm_master_put(struct drm_master **master)
-{
-	kref_put(&(*master)->refcount, drm_master_destroy);
-	*master = NULL;
-}
-EXPORT_SYMBOL(drm_master_put);
-
-int drm_setmaster_ioctl(struct drm_device *dev, void *data,
-			struct drm_file *file_priv)
-{
-	int ret = 0;
-
-	mutex_lock(&dev->master_mutex);
-	if (file_priv->is_master)
-		goto out_unlock;
-
-	if (file_priv->minor->master) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
-	if (!file_priv->master) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
-	if (!file_priv->allowed_master) {
-		ret = drm_new_set_master(dev, file_priv);
-		goto out_unlock;
-	}
-
-	file_priv->minor->master = drm_master_get(file_priv->master);
-	file_priv->is_master = 1;
-	if (dev->driver->master_set) {
-		ret = dev->driver->master_set(dev, file_priv, false);
-		if (unlikely(ret != 0)) {
-			file_priv->is_master = 0;
-			drm_master_put(&file_priv->minor->master);
-		}
-	}
-
-out_unlock:
-	mutex_unlock(&dev->master_mutex);
-	return ret;
-}
-
-int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv)
-{
-	int ret = -EINVAL;
-
-	mutex_lock(&dev->master_mutex);
-	if (!file_priv->is_master)
-		goto out_unlock;
-
-	if (!file_priv->minor->master)
-		goto out_unlock;
-
-	ret = 0;
-	if (dev->driver->master_drop)
-		dev->driver->master_drop(dev, file_priv, false);
-	drm_master_put(&file_priv->minor->master);
-	file_priv->is_master = 0;
-
-out_unlock:
-	mutex_unlock(&dev->master_mutex);
-	return ret;
-}
-
 /*
  * DRM Minors
  * A DRM device can provide several char-dev interfaces on the DRM-Major. Each
@@ -405,10 +299,9 @@ void drm_minor_release(struct drm_minor *minor)
  * callbacks implemented by the driver. The driver then needs to initialize all
  * the various subsystems for the drm device like memory management, vblank
  * handling, modesetting support and intial output configuration plus obviously
- * initialize all the corresponding hardware bits. An important part of this is
- * also calling drm_dev_set_unique() to set the userspace-visible unique name of
- * this device instance. Finally when everything is up and running and ready for
- * userspace the device instance can be published using drm_dev_register().
+ * initialize all the corresponding hardware bits. Finally when everything is up
+ * and running and ready for userspace the device instance can be published
+ * using drm_dev_register().
  *
  * There is also deprecated support for initalizing device instances using
  * bus-specific helpers and the ->load() callback. But due to
@@ -430,6 +323,14 @@ void drm_minor_release(struct drm_minor *minor)
  * dev_priv field of &drm_device.
  */
 
+static int drm_dev_set_unique(struct drm_device *dev, const char *name)
+{
+	kfree(dev->unique);
+	dev->unique = kstrdup(name, GFP_KERNEL);
+
+	return dev->unique ? 0 : -ENOMEM;
+}
+
 /**
  * drm_put_dev - Unregister and release a DRM device
  * @dev: DRM device
@@ -461,9 +362,7 @@ EXPORT_SYMBOL(drm_put_dev);
 void drm_unplug_dev(struct drm_device *dev)
 {
 	/* for a USB device */
-	drm_minor_unregister(dev, DRM_MINOR_LEGACY);
-	drm_minor_unregister(dev, DRM_MINOR_RENDER);
-	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
+	drm_dev_unregister(dev);
 
 	mutex_lock(&drm_global_mutex);
 
@@ -549,11 +448,12 @@ static void drm_fs_inode_free(struct inode *inode)
 }
 
 /**
- * drm_dev_alloc - Allocate new DRM device
- * @driver: DRM driver to allocate device for
+ * drm_dev_init - Initialise new DRM device
+ * @dev: DRM device
+ * @driver: DRM driver
  * @parent: Parent device object
  *
- * Allocate and initialize a new DRM device. No device registration is done.
+ * Initialize a new DRM device. No device registration is done.
  * Call drm_dev_register() to advertice the device to user space and register it
  * with other core subsystems. This should be done last in the device
  * initialization sequence to make sure userspace can't access an inconsistent
@@ -564,19 +464,18 @@ static void drm_fs_inode_free(struct inode *inode)
  *
  * Note that for purely virtual devices @parent can be NULL.
  *
+ * Drivers that do not want to allocate their own device struct
+ * embedding struct &drm_device can call drm_dev_alloc() instead.
+ *
  * RETURNS:
- * Pointer to new DRM device, or NULL if out of memory.
+ * 0 on success, or error code on failure.
  */
-struct drm_device *drm_dev_alloc(struct drm_driver *driver,
-				 struct device *parent)
+int drm_dev_init(struct drm_device *dev,
+		 struct drm_driver *driver,
+		 struct device *parent)
 {
-	struct drm_device *dev;
 	int ret;
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return NULL;
-
 	kref_init(&dev->ref);
 	dev->dev = parent;
 	dev->driver = driver;
@@ -605,8 +504,6 @@ struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 		ret = drm_minor_alloc(dev, DRM_MINOR_CONTROL);
 		if (ret)
 			goto err_minors;
-
-		WARN_ON(driver->suspend || driver->resume);
 	}
 
 	if (drm_core_check_feature(dev, DRIVER_RENDER)) {
@@ -619,7 +516,8 @@ struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 	if (ret)
 		goto err_minors;
 
-	if (drm_ht_create(&dev->map_hash, 12))
+	ret = drm_ht_create(&dev->map_hash, 12);
+	if (ret)
 		goto err_minors;
 
 	drm_legacy_ctxbitmap_init(dev);
@@ -632,13 +530,13 @@ struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 		}
 	}
 
-	if (parent) {
-		ret = drm_dev_set_unique(dev, dev_name(parent));
-		if (ret)
-			goto err_setunique;
-	}
+	/* Use the parent device name as DRM device unique identifier, but fall
+	 * back to the driver name for virtual devices like vgem. */
+	ret = drm_dev_set_unique(dev, parent ? dev_name(parent) : driver->name);
+	if (ret)
+		goto err_setunique;
 
-	return dev;
+	return 0;
 
 err_setunique:
 	if (drm_core_check_feature(dev, DRIVER_GEM))
@@ -653,8 +551,49 @@ err_minors:
 	drm_fs_inode_free(dev->anon_inode);
 err_free:
 	mutex_destroy(&dev->master_mutex);
-	kfree(dev);
-	return NULL;
+	return ret;
+}
+EXPORT_SYMBOL(drm_dev_init);
+
+/**
+ * drm_dev_alloc - Allocate new DRM device
+ * @driver: DRM driver to allocate device for
+ * @parent: Parent device object
+ *
+ * Allocate and initialize a new DRM device. No device registration is done.
+ * Call drm_dev_register() to advertice the device to user space and register it
+ * with other core subsystems. This should be done last in the device
+ * initialization sequence to make sure userspace can't access an inconsistent
+ * state.
+ *
+ * The initial ref-count of the object is 1. Use drm_dev_ref() and
+ * drm_dev_unref() to take and drop further ref-counts.
+ *
+ * Note that for purely virtual devices @parent can be NULL.
+ *
+ * Drivers that wish to subclass or embed struct &drm_device into their
+ * own struct should look at using drm_dev_init() instead.
+ *
+ * RETURNS:
+ * Pointer to new DRM device, or NULL if out of memory.
+ */
+struct drm_device *drm_dev_alloc(struct drm_driver *driver,
+				 struct device *parent)
+{
+	struct drm_device *dev;
+	int ret;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	ret = drm_dev_init(dev, driver, parent);
+	if (ret) {
+		kfree(dev);
+		return NULL;
+	}
+
+	return dev;
 }
 EXPORT_SYMBOL(drm_dev_alloc);
 
@@ -718,11 +657,7 @@ EXPORT_SYMBOL(drm_dev_unref);
  *
  * Register the DRM device @dev with the system, advertise device to user-space
  * and start normal device operation. @dev must be allocated via drm_dev_alloc()
- * previously. Right after drm_dev_register() the driver should call
- * drm_connector_register_all() to register all connectors in sysfs. This is
- * a separate call for backward compatibility with drivers still using
- * the deprecated ->load() callback, where connectors are registered from within
- * the ->load() callback.
+ * previously.
  *
  * Never call this twice on any device!
  *
@@ -759,6 +694,9 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags)
 			goto err_minors;
 	}
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		drm_modeset_register_all(dev);
+
 	ret = 0;
 	goto out_unlock;
 
@@ -789,6 +727,9 @@ void drm_dev_unregister(struct drm_device *dev)
 
 	drm_lastclose(dev);
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		drm_modeset_unregister_all(dev);
+
 	if (dev->driver->unload)
 		dev->driver->unload(dev);
 
@@ -806,26 +747,6 @@ void drm_dev_unregister(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_dev_unregister);
 
-/**
- * drm_dev_set_unique - Set the unique name of a DRM device
- * @dev: device of which to set the unique name
- * @name: unique name
- *
- * Sets the unique name of a DRM device using the specified string. Drivers
- * can use this at driver probe time if the unique name of the devices they
- * drive is static.
- *
- * Return: 0 on success or a negative error code on failure.
- */
-int drm_dev_set_unique(struct drm_device *dev, const char *name)
-{
-	kfree(dev->unique);
-	dev->unique = kstrdup(name, GFP_KERNEL);
-
-	return dev->unique ? 0 : -ENOMEM;
-}
-EXPORT_SYMBOL(drm_dev_set_unique);
-
 /*
  * DRM Core
  * The DRM core module initializes all global DRM objects and makes them
diff --git a/drivers/gpu/drm/drm_edid_load.c b/drivers/gpu/drm/drm_edid_load.c
index 9a401aed98e0..622f788bff46 100644
--- a/drivers/gpu/drm/drm_edid_load.c
+++ b/drivers/gpu/drm/drm_edid_load.c
@@ -271,7 +271,7 @@ int drm_load_edid_firmware(struct drm_connector *connector)
 	 * by commas, search through the list looking for one that
 	 * matches the connector.
 	 *
-	 * If there's one or more that don't't specify a connector, keep
+	 * If there's one or more that doesn't specify a connector, keep
 	 * the last one found one as a fallback.
 	 */
 	fwstr = kstrdup(edid_firmware, GFP_KERNEL);
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 5075fae3c4e2..1fd6eac1400c 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -23,6 +23,7 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_fb_cma_helper.h>
+#include <linux/dma-mapping.h>
 #include <linux/module.h>
 
 #define DEFAULT_FBDEFIO_DELAY_MS 50
@@ -52,7 +53,7 @@ struct drm_fbdev_cma {
  * will be set up automatically. dirty() is called by
  * drm_fb_helper_deferred_io() in process context (struct delayed_work).
  *
- * Example fbdev deferred io code:
+ * Example fbdev deferred io code::
  *
  *     static int driver_fbdev_fb_dirty(struct drm_framebuffer *fb,
  *                                      struct drm_file *file_priv,
@@ -162,6 +163,10 @@ static struct drm_fb_cma *drm_fb_cma_alloc(struct drm_device *dev,
  * drm_fb_cma_create_with_funcs() - helper function for the
  *                                  &drm_mode_config_funcs ->fb_create
  *                                  callback function
+ * @dev: DRM device
+ * @file_priv: drm file for the ioctl call
+ * @mode_cmd: metadata from the userspace fb creation request
+ * @funcs: vtable to be used for the new framebuffer object
  *
  * This can be used to set &drm_framebuffer_funcs for drivers that need the
  * dirty() callback. Use drm_fb_cma_create() if you don't need to change
@@ -223,6 +228,9 @@ EXPORT_SYMBOL_GPL(drm_fb_cma_create_with_funcs);
 
 /**
  * drm_fb_cma_create() - &drm_mode_config_funcs ->fb_create callback function
+ * @dev: DRM device
+ * @file_priv: drm file for the ioctl call
+ * @mode_cmd: metadata from the userspace fb creation request
  *
  * If your hardware has special alignment or pitch requirements these should be
  * checked before calling this function. Use drm_fb_cma_create_with_funcs() if
@@ -246,7 +254,7 @@ EXPORT_SYMBOL_GPL(drm_fb_cma_create);
  * This function will usually be called from the CRTC callback functions.
  */
 struct drm_gem_cma_object *drm_fb_cma_get_gem_obj(struct drm_framebuffer *fb,
-	unsigned int plane)
+						  unsigned int plane)
 {
 	struct drm_fb_cma *fb_cma = to_fb_cma(fb);
 
@@ -258,10 +266,6 @@ struct drm_gem_cma_object *drm_fb_cma_get_gem_obj(struct drm_framebuffer *fb,
 EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_obj);
 
 #ifdef CONFIG_DEBUG_FS
-/*
- * drm_fb_cma_describe() - Helper to dump information about a single
- * CMA framebuffer object
- */
 static void drm_fb_cma_describe(struct drm_framebuffer *fb, struct seq_file *m)
 {
 	struct drm_fb_cma *fb_cma = to_fb_cma(fb);
@@ -279,7 +283,9 @@ static void drm_fb_cma_describe(struct drm_framebuffer *fb, struct seq_file *m)
 
 /**
  * drm_fb_cma_debugfs_show() - Helper to list CMA framebuffer objects
- * in debugfs.
+ *			       in debugfs.
+ * @m: output file
+ * @arg: private data for the callback
  */
 int drm_fb_cma_debugfs_show(struct seq_file *m, void *arg)
 {
@@ -297,6 +303,12 @@ int drm_fb_cma_debugfs_show(struct seq_file *m, void *arg)
 EXPORT_SYMBOL_GPL(drm_fb_cma_debugfs_show);
 #endif
 
+static int drm_fb_cma_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+	return dma_mmap_writecombine(info->device, vma, info->screen_base,
+				     info->fix.smem_start, info->fix.smem_len);
+}
+
 static struct fb_ops drm_fbdev_cma_ops = {
 	.owner		= THIS_MODULE,
 	.fb_fillrect	= drm_fb_helper_sys_fillrect,
@@ -307,6 +319,7 @@ static struct fb_ops drm_fbdev_cma_ops = {
 	.fb_blank	= drm_fb_helper_blank,
 	.fb_pan_display	= drm_fb_helper_pan_display,
 	.fb_setcmap	= drm_fb_helper_setcmap,
+	.fb_mmap	= drm_fb_cma_mmap,
 };
 
 static int drm_fbdev_cma_deferred_io_mmap(struct fb_info *info,
@@ -333,6 +346,7 @@ static int drm_fbdev_cma_defio_init(struct fb_info *fbi,
 	fbops = kzalloc(sizeof(*fbops), GFP_KERNEL);
 	if (!fbdefio || !fbops) {
 		kfree(fbdefio);
+		kfree(fbops);
 		return -ENOMEM;
 	}
 
@@ -582,3 +596,18 @@ void drm_fbdev_cma_hotplug_event(struct drm_fbdev_cma *fbdev_cma)
 		drm_fb_helper_hotplug_event(&fbdev_cma->fb_helper);
 }
 EXPORT_SYMBOL_GPL(drm_fbdev_cma_hotplug_event);
+
+/**
+ * drm_fbdev_cma_set_suspend - wrapper around drm_fb_helper_set_suspend
+ * @fbdev_cma: The drm_fbdev_cma struct, may be NULL
+ * @state: desired state, zero to resume, non-zero to suspend
+ *
+ * Calls drm_fb_helper_set_suspend, which is a wrapper around
+ * fb_set_suspend implemented by fbdev core.
+ */
+void drm_fbdev_cma_set_suspend(struct drm_fbdev_cma *fbdev_cma, int state)
+{
+	if (fbdev_cma)
+		drm_fb_helper_set_suspend(&fbdev_cma->fb_helper, state);
+}
+EXPORT_SYMBOL(drm_fbdev_cma_set_suspend);
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 7c2eb75db60f..ce54e985d91b 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -227,7 +227,7 @@ static void drm_fb_helper_restore_lut_atomic(struct drm_crtc *crtc)
 	g_base = r_base + crtc->gamma_size;
 	b_base = g_base + crtc->gamma_size;
 
-	crtc->funcs->gamma_set(crtc, r_base, g_base, b_base, 0, crtc->gamma_size);
+	crtc->funcs->gamma_set(crtc, r_base, g_base, b_base, crtc->gamma_size);
 }
 
 /**
@@ -385,7 +385,7 @@ static int restore_fbdev_mode(struct drm_fb_helper *fb_helper)
 
 	drm_warn_on_modeset_not_all_locked(dev);
 
-	if (fb_helper->atomic)
+	if (dev->mode_config.funcs->atomic_commit)
 		return restore_fbdev_mode_atomic(fb_helper);
 
 	drm_for_each_plane(plane, dev) {
@@ -464,7 +464,7 @@ static bool drm_fb_helper_is_bound(struct drm_fb_helper *fb_helper)
 
 	/* Sometimes user space wants everything disabled, so don't steal the
 	 * display if there's a master. */
-	if (dev->primary->master)
+	if (lockless_dereference(dev->master))
 		return false;
 
 	drm_for_each_crtc(crtc, dev) {
@@ -716,8 +716,6 @@ int drm_fb_helper_init(struct drm_device *dev,
 		i++;
 	}
 
-	fb_helper->atomic = !!drm_core_check_feature(dev, DRIVER_ATOMIC);
-
 	return 0;
 out_free:
 	drm_fb_helper_crtc_free(fb_helper);
@@ -1042,7 +1040,6 @@ static int setcolreg(struct drm_crtc *crtc, u16 red, u16 green,
 {
 	struct drm_fb_helper *fb_helper = info->par;
 	struct drm_framebuffer *fb = fb_helper->fb;
-	int pindex;
 
 	if (info->fix.visual == FB_VISUAL_TRUECOLOR) {
 		u32 *palette;
@@ -1074,38 +1071,10 @@ static int setcolreg(struct drm_crtc *crtc, u16 red, u16 green,
 		    !fb_helper->funcs->gamma_get))
 		return -EINVAL;
 
-	pindex = regno;
-
-	if (fb->bits_per_pixel == 16) {
-		pindex = regno << 3;
-
-		if (fb->depth == 16 && regno > 63)
-			return -EINVAL;
-		if (fb->depth == 15 && regno > 31)
-			return -EINVAL;
-
-		if (fb->depth == 16) {
-			u16 r, g, b;
-			int i;
-			if (regno < 32) {
-				for (i = 0; i < 8; i++)
-					fb_helper->funcs->gamma_set(crtc, red,
-						green, blue, pindex + i);
-			}
+	WARN_ON(fb->bits_per_pixel != 8);
 
-			fb_helper->funcs->gamma_get(crtc, &r,
-						    &g, &b,
-						    pindex >> 1);
+	fb_helper->funcs->gamma_set(crtc, red, green, blue, regno);
 
-			for (i = 0; i < 4; i++)
-				fb_helper->funcs->gamma_set(crtc, r,
-							    green, b,
-							    (pindex >> 1) + i);
-		}
-	}
-
-	if (fb->depth != 16)
-		fb_helper->funcs->gamma_set(crtc, red, green, blue, pindex);
 	return 0;
 }
 
@@ -1373,7 +1342,7 @@ int drm_fb_helper_pan_display(struct fb_var_screeninfo *var,
 		return -EBUSY;
 	}
 
-	if (fb_helper->atomic) {
+	if (dev->mode_config.funcs->atomic_commit) {
 		ret = pan_display_atomic(var, info);
 		goto unlock;
 	}
@@ -2000,7 +1969,18 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 		my_score++;
 
 	connector_funcs = connector->helper_private;
-	encoder = connector_funcs->best_encoder(connector);
+
+	/*
+	 * If the DRM device implements atomic hooks and ->best_encoder() is
+	 * NULL we fallback to the default drm_atomic_helper_best_encoder()
+	 * helper.
+	 */
+	if (fb_helper->dev->mode_config.funcs->atomic_commit &&
+	    !connector_funcs->best_encoder)
+		encoder = drm_atomic_helper_best_encoder(connector);
+	else
+		encoder = connector_funcs->best_encoder(connector);
+
 	if (!encoder)
 		goto out;
 
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 7af7f8bcb355..323c238fcac7 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -40,6 +40,7 @@
 #include <linux/module.h>
 #include "drm_legacy.h"
 #include "drm_internal.h"
+#include "drm_crtc_internal.h"
 
 /* from BKL pushdown */
 DEFINE_MUTEX(drm_global_mutex);
@@ -67,7 +68,7 @@ DEFINE_MUTEX(drm_global_mutex);
  * specific implementations. For GEM-based drivers this is drm_gem_mmap().
  *
  * No other file operations are supported by the DRM userspace API. Overall the
- * following is an example #file_operations structure:
+ * following is an example #file_operations structure::
  *
  *     static const example_drm_fops = {
  *             .owner = THIS_MODULE,
@@ -168,60 +169,6 @@ static int drm_cpu_valid(void)
 }
 
 /*
- * drm_new_set_master - Allocate a new master object and become master for the
- * associated master realm.
- *
- * @dev: The associated device.
- * @fpriv: File private identifying the client.
- *
- * This function must be called with dev::struct_mutex held.
- * Returns negative error code on failure. Zero on success.
- */
-int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv)
-{
-	struct drm_master *old_master;
-	int ret;
-
-	lockdep_assert_held_once(&dev->master_mutex);
-
-	/* create a new master */
-	fpriv->minor->master = drm_master_create(fpriv->minor);
-	if (!fpriv->minor->master)
-		return -ENOMEM;
-
-	/* take another reference for the copy in the local file priv */
-	old_master = fpriv->master;
-	fpriv->master = drm_master_get(fpriv->minor->master);
-
-	if (dev->driver->master_create) {
-		ret = dev->driver->master_create(dev, fpriv->master);
-		if (ret)
-			goto out_err;
-	}
-	if (dev->driver->master_set) {
-		ret = dev->driver->master_set(dev, fpriv, true);
-		if (ret)
-			goto out_err;
-	}
-
-	fpriv->is_master = 1;
-	fpriv->allowed_master = 1;
-	fpriv->authenticated = 1;
-	if (old_master)
-		drm_master_put(&old_master);
-
-	return 0;
-
-out_err:
-	/* drop both references and restore old master on failure */
-	drm_master_put(&fpriv->minor->master);
-	drm_master_put(&fpriv->master);
-	fpriv->master = old_master;
-
-	return ret;
-}
-
-/*
  * Called whenever a process opens /dev/drm.
  *
  * \param filp file pointer.
@@ -283,19 +230,11 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 			goto out_prime_destroy;
 	}
 
-	/* if there is no current master make this fd it, but do not create
-	 * any master object for render clients */
-	mutex_lock(&dev->master_mutex);
-	if (drm_is_primary_client(priv) && !priv->minor->master) {
-		/* create a new master */
-		ret = drm_new_set_master(dev, priv);
+	if (drm_is_primary_client(priv)) {
+		ret = drm_master_open(priv);
 		if (ret)
 			goto out_close;
-	} else if (drm_is_primary_client(priv)) {
-		/* get a reference to the master */
-		priv->master = drm_master_get(priv->minor->master);
 	}
-	mutex_unlock(&dev->master_mutex);
 
 	mutex_lock(&dev->filelist_mutex);
 	list_add(&priv->lhead, &dev->filelist);
@@ -324,7 +263,6 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 	return 0;
 
 out_close:
-	mutex_unlock(&dev->master_mutex);
 	if (dev->driver->postclose)
 		dev->driver->postclose(dev, priv);
 out_prime_destroy:
@@ -338,18 +276,6 @@ out_prime_destroy:
 	return ret;
 }
 
-static void drm_master_release(struct drm_device *dev, struct file *filp)
-{
-	struct drm_file *file_priv = filp->private_data;
-
-	if (drm_legacy_i_have_hw_lock(dev, file_priv)) {
-		DRM_DEBUG("File %p released, freeing lock for context %d\n",
-			  filp, _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock));
-		drm_legacy_lock_free(&file_priv->master->lock,
-				     _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock));
-	}
-}
-
 static void drm_events_release(struct drm_file *file_priv)
 {
 	struct drm_device *dev = file_priv->minor->dev;
@@ -368,7 +294,7 @@ static void drm_events_release(struct drm_file *file_priv)
 	/* Remove unconsumed events */
 	list_for_each_entry_safe(e, et, &file_priv->event_list, link) {
 		list_del(&e->link);
-		e->destroy(e);
+		kfree(e);
 	}
 
 	spin_unlock_irqrestore(&dev->event_lock, flags);
@@ -451,11 +377,6 @@ int drm_release(struct inode *inode, struct file *filp)
 	list_del(&file_priv->lhead);
 	mutex_unlock(&dev->filelist_mutex);
 
-	mutex_lock(&dev->struct_mutex);
-	if (file_priv->magic)
-		idr_remove(&file_priv->master->magic_map, file_priv->magic);
-	mutex_unlock(&dev->struct_mutex);
-
 	if (dev->driver->preclose)
 		dev->driver->preclose(dev, file_priv);
 
@@ -468,9 +389,8 @@ int drm_release(struct inode *inode, struct file *filp)
 		  (long)old_encode_dev(file_priv->minor->kdev->devt),
 		  dev->open_count);
 
-	/* if the master has gone away we can't do anything with the lock */
-	if (file_priv->minor->master)
-		drm_master_release(dev, filp);
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		drm_legacy_lock_release(dev, filp);
 
 	if (drm_core_check_feature(dev, DRIVER_HAVE_DMA))
 		drm_legacy_reclaim_buffers(dev, file_priv);
@@ -487,43 +407,12 @@ int drm_release(struct inode *inode, struct file *filp)
 
 	drm_legacy_ctxbitmap_flush(dev, file_priv);
 
-	mutex_lock(&dev->master_mutex);
-
-	if (file_priv->is_master) {
-		struct drm_master *master = file_priv->master;
-
-		/*
-		 * Since the master is disappearing, so is the
-		 * possibility to lock.
-		 */
-		mutex_lock(&dev->struct_mutex);
-		if (master->lock.hw_lock) {
-			if (dev->sigdata.lock == master->lock.hw_lock)
-				dev->sigdata.lock = NULL;
-			master->lock.hw_lock = NULL;
-			master->lock.file_priv = NULL;
-			wake_up_interruptible_all(&master->lock.lock_queue);
-		}
-		mutex_unlock(&dev->struct_mutex);
-
-		if (file_priv->minor->master == file_priv->master) {
-			/* drop the reference held my the minor */
-			if (dev->driver->master_drop)
-				dev->driver->master_drop(dev, file_priv, true);
-			drm_master_put(&file_priv->minor->master);
-		}
-	}
-
-	/* drop the master reference held by the file priv */
-	if (file_priv->master)
-		drm_master_put(&file_priv->master);
-	file_priv->is_master = 0;
-	mutex_unlock(&dev->master_mutex);
+	if (drm_is_primary_client(file_priv))
+		drm_master_release(file_priv);
 
 	if (dev->driver->postclose)
 		dev->driver->postclose(dev, file_priv);
 
-
 	if (drm_core_check_feature(dev, DRIVER_PRIME))
 		drm_prime_destroy_file_private(&file_priv->prime);
 
@@ -636,7 +525,7 @@ put_back_event:
 			}
 
 			ret += length;
-			e->destroy(e);
+			kfree(e);
 		}
 	}
 	mutex_unlock(&file_priv->event_read_lock);
@@ -713,9 +602,6 @@ int drm_event_reserve_init_locked(struct drm_device *dev,
 	list_add(&p->pending_link, &file_priv->pending_event_list);
 	p->file_priv = file_priv;
 
-	/* we *could* pass this in as arg, but everyone uses kfree: */
-	p->destroy = (void (*) (struct drm_pending_event *)) kfree;
-
 	return 0;
 }
 EXPORT_SYMBOL(drm_event_reserve_init_locked);
@@ -778,7 +664,7 @@ void drm_event_cancel_free(struct drm_device *dev,
 		list_del(&p->pending_link);
 	}
 	spin_unlock_irqrestore(&dev->event_lock, flags);
-	p->destroy(p);
+	kfree(p);
 }
 EXPORT_SYMBOL(drm_event_cancel_free);
 
@@ -800,8 +686,19 @@ void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e)
 {
 	assert_spin_locked(&dev->event_lock);
 
+	if (e->completion) {
+		/* ->completion might disappear as soon as it signalled. */
+		complete_all(e->completion);
+		e->completion = NULL;
+	}
+
+	if (e->fence) {
+		fence_signal(e->fence);
+		fence_put(e->fence);
+	}
+
 	if (!e->file_priv) {
-		e->destroy(e);
+		kfree(e);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
new file mode 100644
index 000000000000..0645c85d5f95
--- /dev/null
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -0,0 +1,320 @@
+/*
+ * Copyright (c) 2016 Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ *
+ * DRM core format related functions
+ *
+ * Permission to use, copy, modify, distribute, and sell this software and its
+ * documentation for any purpose is hereby granted without fee, provided that
+ * the above copyright notice appear in all copies and that both that copyright
+ * notice and this permission notice appear in supporting documentation, and
+ * that the name of the copyright holders not be used in advertising or
+ * publicity pertaining to distribution of the software without specific,
+ * written prior permission.  The copyright holders make no representations
+ * about the suitability of this software for any purpose.  It is provided "as
+ * is" without express or implied warranty.
+ *
+ * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
+ * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO
+ * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR
+ * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
+ * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+ * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
+ * OF THIS SOFTWARE.
+ */
+
+#include <linux/bug.h>
+#include <linux/ctype.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_fourcc.h>
+
+static char printable_char(int c)
+{
+	return isascii(c) && isprint(c) ? c : '?';
+}
+
+/**
+ * drm_get_format_name - return a string for drm fourcc format
+ * @format: format to compute name of
+ *
+ * Note that the buffer used by this function is globally shared and owned by
+ * the function itself.
+ *
+ * FIXME: This isn't really multithreading safe.
+ */
+const char *drm_get_format_name(uint32_t format)
+{
+	static char buf[32];
+
+	snprintf(buf, sizeof(buf),
+		 "%c%c%c%c %s-endian (0x%08x)",
+		 printable_char(format & 0xff),
+		 printable_char((format >> 8) & 0xff),
+		 printable_char((format >> 16) & 0xff),
+		 printable_char((format >> 24) & 0x7f),
+		 format & DRM_FORMAT_BIG_ENDIAN ? "big" : "little",
+		 format);
+
+	return buf;
+}
+EXPORT_SYMBOL(drm_get_format_name);
+
+/**
+ * drm_fb_get_bpp_depth - get the bpp/depth values for format
+ * @format: pixel format (DRM_FORMAT_*)
+ * @depth: storage for the depth value
+ * @bpp: storage for the bpp value
+ *
+ * This only supports RGB formats here for compat with code that doesn't use
+ * pixel formats directly yet.
+ */
+void drm_fb_get_bpp_depth(uint32_t format, unsigned int *depth,
+			  int *bpp)
+{
+	switch (format) {
+	case DRM_FORMAT_C8:
+	case DRM_FORMAT_RGB332:
+	case DRM_FORMAT_BGR233:
+		*depth = 8;
+		*bpp = 8;
+		break;
+	case DRM_FORMAT_XRGB1555:
+	case DRM_FORMAT_XBGR1555:
+	case DRM_FORMAT_RGBX5551:
+	case DRM_FORMAT_BGRX5551:
+	case DRM_FORMAT_ARGB1555:
+	case DRM_FORMAT_ABGR1555:
+	case DRM_FORMAT_RGBA5551:
+	case DRM_FORMAT_BGRA5551:
+		*depth = 15;
+		*bpp = 16;
+		break;
+	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_BGR565:
+		*depth = 16;
+		*bpp = 16;
+		break;
+	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_BGR888:
+		*depth = 24;
+		*bpp = 24;
+		break;
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_RGBX8888:
+	case DRM_FORMAT_BGRX8888:
+		*depth = 24;
+		*bpp = 32;
+		break;
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_RGBX1010102:
+	case DRM_FORMAT_BGRX1010102:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
+	case DRM_FORMAT_RGBA1010102:
+	case DRM_FORMAT_BGRA1010102:
+		*depth = 30;
+		*bpp = 32;
+		break;
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_RGBA8888:
+	case DRM_FORMAT_BGRA8888:
+		*depth = 32;
+		*bpp = 32;
+		break;
+	default:
+		DRM_DEBUG_KMS("unsupported pixel format %s\n",
+			      drm_get_format_name(format));
+		*depth = 0;
+		*bpp = 0;
+		break;
+	}
+}
+EXPORT_SYMBOL(drm_fb_get_bpp_depth);
+
+/**
+ * drm_format_num_planes - get the number of planes for format
+ * @format: pixel format (DRM_FORMAT_*)
+ *
+ * Returns:
+ * The number of planes used by the specified pixel format.
+ */
+int drm_format_num_planes(uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_YUV410:
+	case DRM_FORMAT_YVU410:
+	case DRM_FORMAT_YUV411:
+	case DRM_FORMAT_YVU411:
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YVU422:
+	case DRM_FORMAT_YUV444:
+	case DRM_FORMAT_YVU444:
+		return 3;
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
+	case DRM_FORMAT_NV24:
+	case DRM_FORMAT_NV42:
+		return 2;
+	default:
+		return 1;
+	}
+}
+EXPORT_SYMBOL(drm_format_num_planes);
+
+/**
+ * drm_format_plane_cpp - determine the bytes per pixel value
+ * @format: pixel format (DRM_FORMAT_*)
+ * @plane: plane index
+ *
+ * Returns:
+ * The bytes per pixel value for the specified plane.
+ */
+int drm_format_plane_cpp(uint32_t format, int plane)
+{
+	unsigned int depth;
+	int bpp;
+
+	if (plane >= drm_format_num_planes(format))
+		return 0;
+
+	switch (format) {
+	case DRM_FORMAT_YUYV:
+	case DRM_FORMAT_YVYU:
+	case DRM_FORMAT_UYVY:
+	case DRM_FORMAT_VYUY:
+		return 2;
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
+	case DRM_FORMAT_NV24:
+	case DRM_FORMAT_NV42:
+		return plane ? 2 : 1;
+	case DRM_FORMAT_YUV410:
+	case DRM_FORMAT_YVU410:
+	case DRM_FORMAT_YUV411:
+	case DRM_FORMAT_YVU411:
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YVU422:
+	case DRM_FORMAT_YUV444:
+	case DRM_FORMAT_YVU444:
+		return 1;
+	default:
+		drm_fb_get_bpp_depth(format, &depth, &bpp);
+		return bpp >> 3;
+	}
+}
+EXPORT_SYMBOL(drm_format_plane_cpp);
+
+/**
+ * drm_format_horz_chroma_subsampling - get the horizontal chroma subsampling factor
+ * @format: pixel format (DRM_FORMAT_*)
+ *
+ * Returns:
+ * The horizontal chroma subsampling factor for the
+ * specified pixel format.
+ */
+int drm_format_horz_chroma_subsampling(uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_YUV411:
+	case DRM_FORMAT_YVU411:
+	case DRM_FORMAT_YUV410:
+	case DRM_FORMAT_YVU410:
+		return 4;
+	case DRM_FORMAT_YUYV:
+	case DRM_FORMAT_YVYU:
+	case DRM_FORMAT_UYVY:
+	case DRM_FORMAT_VYUY:
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YVU422:
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+		return 2;
+	default:
+		return 1;
+	}
+}
+EXPORT_SYMBOL(drm_format_horz_chroma_subsampling);
+
+/**
+ * drm_format_vert_chroma_subsampling - get the vertical chroma subsampling factor
+ * @format: pixel format (DRM_FORMAT_*)
+ *
+ * Returns:
+ * The vertical chroma subsampling factor for the
+ * specified pixel format.
+ */
+int drm_format_vert_chroma_subsampling(uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_YUV410:
+	case DRM_FORMAT_YVU410:
+		return 4;
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+		return 2;
+	default:
+		return 1;
+	}
+}
+EXPORT_SYMBOL(drm_format_vert_chroma_subsampling);
+
+/**
+ * drm_format_plane_width - width of the plane given the first plane
+ * @width: width of the first plane
+ * @format: pixel format
+ * @plane: plane index
+ *
+ * Returns:
+ * The width of @plane, given that the width of the first plane is @width.
+ */
+int drm_format_plane_width(int width, uint32_t format, int plane)
+{
+	if (plane >= drm_format_num_planes(format))
+		return 0;
+
+	if (plane == 0)
+		return width;
+
+	return width / drm_format_horz_chroma_subsampling(format);
+}
+EXPORT_SYMBOL(drm_format_plane_width);
+
+/**
+ * drm_format_plane_height - height of the plane given the first plane
+ * @height: height of the first plane
+ * @format: pixel format
+ * @plane: plane index
+ *
+ * Returns:
+ * The height of @plane, given that the height of the first plane is @height.
+ */
+int drm_format_plane_height(int height, uint32_t format, int plane)
+{
+	if (plane >= drm_format_num_planes(format))
+		return 0;
+
+	if (plane == 0)
+		return height;
+
+	return height / drm_format_vert_chroma_subsampling(format);
+}
+EXPORT_SYMBOL(drm_format_plane_height);
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index ad89db36ca25..9134ae134667 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -787,7 +787,7 @@ EXPORT_SYMBOL(drm_gem_object_release);
  * @kref: kref of the object to free
  *
  * Called after the last reference to the object has been lost.
- * Must be called holding struct_ mutex
+ * Must be called holding &drm_device->struct_mutex.
  *
  * Frees the object
  */
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index 5d469b2f26f4..9ae353f4dd06 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -50,106 +50,24 @@ int drm_name_info(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_minor *minor = node->minor;
 	struct drm_device *dev = minor->dev;
-	struct drm_master *master = minor->master;
-	if (!master)
-		return 0;
-
-	if (master->unique) {
-		seq_printf(m, "%s %s %s\n",
-			   dev->driver->name,
-			   dev_name(dev->dev), master->unique);
-	} else {
-		seq_printf(m, "%s %s\n",
-			   dev->driver->name, dev_name(dev->dev));
-	}
-	return 0;
-}
-
-/**
- * Called when "/proc/dri/.../vm" is read.
- *
- * Prints information about all mappings in drm_device::maplist.
- */
-int drm_vm_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct drm_local_map *map;
-	struct drm_map_list *r_list;
-
-	/* Hardcoded from _DRM_FRAME_BUFFER,
-	   _DRM_REGISTERS, _DRM_SHM, _DRM_AGP, and
-	   _DRM_SCATTER_GATHER and _DRM_CONSISTENT */
-	const char *types[] = { "FB", "REG", "SHM", "AGP", "SG", "PCI" };
-	const char *type;
-	int i;
-
-	mutex_lock(&dev->struct_mutex);
-	seq_printf(m, "slot	 offset	      size type flags	 address mtrr\n\n");
-	i = 0;
-	list_for_each_entry(r_list, &dev->maplist, head) {
-		map = r_list->map;
-		if (!map)
-			continue;
-		if (map->type < 0 || map->type > 5)
-			type = "??";
-		else
-			type = types[map->type];
-
-		seq_printf(m, "%4d 0x%016llx 0x%08lx %4.4s  0x%02x 0x%08lx ",
-			   i,
-			   (unsigned long long)map->offset,
-			   map->size, type, map->flags,
-			   (unsigned long) r_list->user_token);
-		if (map->mtrr < 0)
-			seq_printf(m, "none\n");
-		else
-			seq_printf(m, "%4d\n", map->mtrr);
-		i++;
-	}
-	mutex_unlock(&dev->struct_mutex);
-	return 0;
-}
+	struct drm_master *master;
 
-/**
- * Called when "/proc/dri/.../bufs" is read.
- */
-int drm_bufs_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct drm_device_dma *dma;
-	int i, seg_pages;
-
-	mutex_lock(&dev->struct_mutex);
-	dma = dev->dma;
-	if (!dma) {
-		mutex_unlock(&dev->struct_mutex);
-		return 0;
-	}
-
-	seq_printf(m, " o     size count  free	 segs pages    kB\n\n");
-	for (i = 0; i <= DRM_MAX_ORDER; i++) {
-		if (dma->bufs[i].buf_count) {
-			seg_pages = dma->bufs[i].seg_count * (1 << dma->bufs[i].page_order);
-			seq_printf(m, "%2d %8d %5d %5d %5d %5d %5ld\n",
-				   i,
-				   dma->bufs[i].buf_size,
-				   dma->bufs[i].buf_count,
-				   0,
-				   dma->bufs[i].seg_count,
-				   seg_pages,
-				   seg_pages * PAGE_SIZE / 1024);
-		}
-	}
-	seq_printf(m, "\n");
-	for (i = 0; i < dma->buf_count; i++) {
-		if (i && !(i % 32))
-			seq_printf(m, "\n");
-		seq_printf(m, " %d", dma->buflist[i]->list);
-	}
+	mutex_lock(&dev->master_mutex);
+	master = dev->master;
+	if (!master)
+		goto out_unlock;
+
+	seq_printf(m, "%s", dev->driver->name);
+	if (dev->dev)
+		seq_printf(m, " dev=%s", dev_name(dev->dev));
+	if (master && master->unique)
+		seq_printf(m, " master=%s", master->unique);
+	if (dev->unique)
+		seq_printf(m, " unique=%s", dev->unique);
 	seq_printf(m, "\n");
-	mutex_unlock(&dev->struct_mutex);
+out_unlock:
+	mutex_unlock(&dev->master_mutex);
+
 	return 0;
 }
 
@@ -184,7 +102,7 @@ int drm_clients_info(struct seq_file *m, void *data)
 			   task ? task->comm : "<unknown>",
 			   pid_vnr(priv->pid),
 			   priv->minor->index,
-			   priv->is_master ? 'y' : 'n',
+			   drm_is_current_master(priv) ? 'y' : 'n',
 			   priv->authenticated ? 'y' : 'n',
 			   from_kuid_munged(seq_user_ns(m), priv->uid),
 			   priv->magic);
@@ -194,7 +112,6 @@ int drm_clients_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-
 static int drm_gem_one_name_info(int id, void *ptr, void *data)
 {
 	struct drm_gem_object *obj = ptr;
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 902cf6a15212..b86dc9b921a5 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -29,15 +29,9 @@ extern struct mutex drm_global_mutex;
 void drm_lastclose(struct drm_device *dev);
 
 /* drm_pci.c */
-int drm_pci_set_unique(struct drm_device *dev,
-		       struct drm_master *master,
-		       struct drm_unique *u);
 int drm_irq_by_busid(struct drm_device *dev, void *data,
 		     struct drm_file *file_priv);
 
-/* drm_vm.c */
-int drm_vma_info(struct seq_file *m, void *data);
-
 /* drm_prime.c */
 int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv);
@@ -51,8 +45,6 @@ void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpr
 
 /* drm_info.c */
 int drm_name_info(struct seq_file *m, void *data);
-int drm_vm_info(struct seq_file *m, void *data);
-int drm_bufs_info(struct seq_file *m, void *data);
 int drm_clients_info(struct seq_file *m, void* data);
 int drm_gem_name_info(struct seq_file *m, void *data);
 
@@ -67,6 +59,12 @@ int drm_getmagic(struct drm_device *dev, void *data,
 		 struct drm_file *file_priv);
 int drm_authmagic(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv);
+int drm_setmaster_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
+			 struct drm_file *file_priv);
+int drm_master_open(struct drm_file *file_priv);
+void drm_master_release(struct drm_file *file_priv);
 
 /* drm_sysfs.c */
 extern struct class *drm_class;
@@ -92,13 +90,6 @@ int drm_gem_open_ioctl(struct drm_device *dev, void *data,
 void drm_gem_open(struct drm_device *dev, struct drm_file *file_private);
 void drm_gem_release(struct drm_device *dev, struct drm_file *file_private);
 
-/* drm_drv.c */
-int drm_setmaster_ioctl(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-struct drm_master *drm_master_create(struct drm_minor *minor);
-
 /* drm_debugfs.c */
 #if defined(CONFIG_DEBUG_FS)
 int drm_debugfs_init(struct drm_minor *minor, int minor_id,
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index b7a39771c152..33af4a5ddca1 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -30,6 +30,7 @@
 
 #include <drm/drmP.h>
 #include <drm/drm_core.h>
+#include <drm/drm_auth.h>
 #include "drm_legacy.h"
 #include "drm_internal.h"
 #include "drm_crtc_internal.h"
@@ -37,6 +38,64 @@
 #include <linux/pci.h>
 #include <linux/export.h>
 
+/**
+ * DOC: getunique and setversion story
+ *
+ * BEWARE THE DRAGONS! MIND THE TRAPDOORS!
+ *
+ * In an attempt to warn anyone else who's trying to figure out what's going
+ * on here, I'll try to summarize the story. First things first, let's clear up
+ * the names, because the kernel internals, libdrm and the ioctls are all named
+ * differently:
+ *
+ *  - GET_UNIQUE ioctl, implemented by drm_getunique is wrapped up in libdrm
+ *    through the drmGetBusid function.
+ *  - The libdrm drmSetBusid function is backed by the SET_UNIQUE ioctl. All
+ *    that code is nerved in the kernel with drm_invalid_op().
+ *  - The internal set_busid kernel functions and driver callbacks are
+ *    exclusively use by the SET_VERSION ioctl, because only drm 1.0 (which is
+ *    nerved) allowed userspace to set the busid through the above ioctl.
+ *  - Other ioctls and functions involved are named consistently.
+ *
+ * For anyone wondering what's the difference between drm 1.1 and 1.4: Correctly
+ * handling pci domains in the busid on ppc. Doing this correctly was only
+ * implemented in libdrm in 2010, hence can't be nerved yet. No one knows what's
+ * special with drm 1.2 and 1.3.
+ *
+ * Now the actual horror story of how device lookup in drm works. At large,
+ * there's 2 different ways, either by busid, or by device driver name.
+ *
+ * Opening by busid is fairly simple:
+ *
+ * 1. First call SET_VERSION to make sure pci domains are handled properly. As a
+ *    side-effect this fills out the unique name in the master structure.
+ * 2. Call GET_UNIQUE to read out the unique name from the master structure,
+ *    which matches the busid thanks to step 1. If it doesn't, proceed to try
+ *    the next device node.
+ *
+ * Opening by name is slightly different:
+ *
+ * 1. Directly call VERSION to get the version and to match against the driver
+ *    name returned by that ioctl. Note that SET_VERSION is not called, which
+ *    means the the unique name for the master node just opening is _not_ filled
+ *    out. This despite that with current drm device nodes are always bound to
+ *    one device, and can't be runtime assigned like with drm 1.0.
+ * 2. Match driver name. If it mismatches, proceed to the next device node.
+ * 3. Call GET_UNIQUE, and check whether the unique name has length zero (by
+ *    checking that the first byte in the string is 0). If that's not the case
+ *    libdrm skips and proceeds to the next device node. Probably this is just
+ *    copypasta from drm 1.0 times where a set unique name meant that the driver
+ *    was in use already, but that's just conjecture.
+ *
+ * Long story short: To keep the open by name logic working, GET_UNIQUE must
+ * _not_ return a unique string when SET_VERSION hasn't been called yet,
+ * otherwise libdrm breaks. Even when that unique string can't ever change, and
+ * is totally irrelevant for actually opening the device because runtime
+ * assignable device instances were only support in drm 1.0, which is long dead.
+ * But the libdrm code in drmOpenByName somehow survived, hence this can't be
+ * broken.
+ */
+
 static int drm_version(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
 
@@ -75,51 +134,6 @@ drm_unset_busid(struct drm_device *dev,
 	master->unique_len = 0;
 }
 
-/*
- * Set the bus id.
- *
- * \param inode device inode.
- * \param file_priv DRM file private.
- * \param cmd command.
- * \param arg user argument, pointing to a drm_unique structure.
- * \return zero on success or a negative number on failure.
- *
- * Copies the bus id from userspace into drm_device::unique, and verifies that
- * it matches the device this DRM is attached to (EINVAL otherwise).  Deprecated
- * in interface version 1.1 and will return EBUSY when setversion has requested
- * version 1.1 or greater. Also note that KMS is all version 1.1 and later and
- * UMS was only ever supported on pci devices.
- */
-static int drm_setunique(struct drm_device *dev, void *data,
-		  struct drm_file *file_priv)
-{
-	struct drm_unique *u = data;
-	struct drm_master *master = file_priv->master;
-	int ret;
-
-	if (master->unique_len || master->unique)
-		return -EBUSY;
-
-	if (!u->unique_len || u->unique_len > 1024)
-		return -EINVAL;
-
-	if (drm_core_check_feature(dev, DRIVER_MODESET))
-		return 0;
-
-	if (WARN_ON(!dev->pdev))
-		return -EINVAL;
-
-	ret = drm_pci_set_unique(dev, master, u);
-	if (ret)
-		goto err;
-
-	return 0;
-
-err:
-	drm_unset_busid(dev, master);
-	return ret;
-}
-
 static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv)
 {
 	struct drm_master *master = file_priv->master;
@@ -135,12 +149,7 @@ static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv)
 			return ret;
 		}
 	} else {
-		if (WARN(dev->unique == NULL,
-			 "No drm_driver.set_busid() implementation provided by "
-			 "%ps. Use drm_dev_set_unique() to set the unique "
-			 "name explicitly.", dev->driver))
-			return -EINVAL;
-
+		WARN_ON(!dev->unique);
 		master->unique = kstrdup(dev->unique, GFP_KERNEL);
 		if (master->unique)
 			master->unique_len = strlen(dev->unique);
@@ -473,7 +482,8 @@ int drm_ioctl_permit(u32 flags, struct drm_file *file_priv)
 		return -EACCES;
 
 	/* MASTER is only for master or control clients */
-	if (unlikely((flags & DRM_MASTER) && !file_priv->is_master &&
+	if (unlikely((flags & DRM_MASTER) && 
+		     !drm_is_current_master(file_priv) &&
 		     !drm_is_control_client(file_priv)))
 		return -EACCES;
 
@@ -504,7 +514,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version,
 		      DRM_UNLOCKED|DRM_RENDER_ALLOW|DRM_CONTROL_ALLOW),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAP, drm_legacy_getmap_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_CLIENT, drm_getclient, DRM_UNLOCKED),
@@ -513,10 +523,10 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_SET_CLIENT_CAP, drm_setclientcap, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_SET_VERSION, drm_setversion, DRM_MASTER),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_UNIQUE, drm_setunique, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_UNIQUE, drm_invalid_op, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_BLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_UNBLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AUTH_MAGIC, drm_authmagic, DRM_AUTH|DRM_MASTER),
+	DRM_IOCTL_DEF(DRM_IOCTL_AUTH_MAGIC, drm_authmagic, DRM_AUTH|DRM_UNLOCKED|DRM_MASTER),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_ADD_MAP, drm_legacy_addmap_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_RM_MAP, drm_legacy_rmmap_ioctl, DRM_AUTH),
@@ -524,8 +534,8 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_SET_SAREA_CTX, drm_legacy_setsareactx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_SAREA_CTX, drm_legacy_getsareactx, DRM_AUTH),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_MASTER, drm_setmaster_ioctl, DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_DROP_MASTER, drm_dropmaster_ioctl, DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_MASTER, drm_setmaster_ioctl, DRM_UNLOCKED|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_DROP_MASTER, drm_dropmaster_ioctl, DRM_UNLOCKED|DRM_ROOT_ONLY),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_ADD_CTX, drm_legacy_addctx, DRM_AUTH|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_RM_CTX, drm_legacy_rmctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
@@ -638,7 +648,7 @@ long drm_ioctl(struct file *filp,
 	int retcode = -EINVAL;
 	char stack_kdata[128];
 	char *kdata = NULL;
-	unsigned int usize, asize, drv_size;
+	unsigned int in_size, out_size, drv_size, ksize;
 	bool is_driver_ioctl;
 
 	dev = file_priv->minor->dev;
@@ -661,9 +671,12 @@ long drm_ioctl(struct file *filp,
 	}
 
 	drv_size = _IOC_SIZE(ioctl->cmd);
-	usize = _IOC_SIZE(cmd);
-	asize = max(usize, drv_size);
-	cmd = ioctl->cmd;
+	out_size = in_size = _IOC_SIZE(cmd);
+	if ((cmd & ioctl->cmd & IOC_IN) == 0)
+		in_size = 0;
+	if ((cmd & ioctl->cmd & IOC_OUT) == 0)
+		out_size = 0;
+	ksize = max(max(in_size, out_size), drv_size);
 
 	DRM_DEBUG("pid=%d, dev=0x%lx, auth=%d, %s\n",
 		  task_pid_nr(current),
@@ -683,30 +696,24 @@ long drm_ioctl(struct file *filp,
 	if (unlikely(retcode))
 		goto err_i1;
 
-	if (cmd & (IOC_IN | IOC_OUT)) {
-		if (asize <= sizeof(stack_kdata)) {
-			kdata = stack_kdata;
-		} else {
-			kdata = kmalloc(asize, GFP_KERNEL);
-			if (!kdata) {
-				retcode = -ENOMEM;
-				goto err_i1;
-			}
+	if (ksize <= sizeof(stack_kdata)) {
+		kdata = stack_kdata;
+	} else {
+		kdata = kmalloc(ksize, GFP_KERNEL);
+		if (!kdata) {
+			retcode = -ENOMEM;
+			goto err_i1;
 		}
-		if (asize > usize)
-			memset(kdata + usize, 0, asize - usize);
 	}
 
-	if (cmd & IOC_IN) {
-		if (copy_from_user(kdata, (void __user *)arg,
-				   usize) != 0) {
-			retcode = -EFAULT;
-			goto err_i1;
-		}
-	} else if (cmd & IOC_OUT) {
-		memset(kdata, 0, usize);
+	if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) {
+		retcode = -EFAULT;
+		goto err_i1;
 	}
 
+	if (ksize > in_size)
+		memset(kdata + in_size, 0, ksize - in_size);
+
 	/* Enforce sane locking for kms driver ioctls. Core ioctls are
 	 * too messy still. */
 	if ((drm_core_check_feature(dev, DRIVER_MODESET) && is_driver_ioctl) ||
@@ -718,11 +725,8 @@ long drm_ioctl(struct file *filp,
 		mutex_unlock(&drm_global_mutex);
 	}
 
-	if (cmd & IOC_OUT) {
-		if (copy_to_user((void __user *)arg, kdata,
-				 usize) != 0)
-			retcode = -EFAULT;
-	}
+	if (copy_to_user((void __user *)arg, kdata, out_size) != 0)
+		retcode = -EFAULT;
 
       err_i1:
 	if (!ioctl)
@@ -749,7 +753,7 @@ EXPORT_SYMBOL(drm_ioctl);
  * shouldn't be used by any drivers.
  *
  * Returns:
- * True if the @nr corresponds to a DRM core ioctl numer, false otherwise.
+ * True if the @nr corresponds to a DRM core ioctl number, false otherwise.
  */
 bool drm_ioctl_flags(unsigned int nr, unsigned int *flags)
 {
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 0fac801c18fe..77f357b2c386 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -42,10 +42,6 @@
 #include <linux/vgaarb.h>
 #include <linux/export.h>
 
-/* Access macro for slots in vblank timestamp ringbuffer. */
-#define vblanktimestamp(dev, pipe, count) \
-	((dev)->vblank[pipe].time[(count) % DRM_VBLANKTIME_RBSIZE])
-
 /* Retry timestamp calculation up to 3 times to satisfy
  * drm_timestamp_precision before giving up.
  */
@@ -82,36 +78,18 @@ static void store_vblank(struct drm_device *dev, unsigned int pipe,
 			 struct timeval *t_vblank, u32 last)
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
-	u32 tslot;
 
 	assert_spin_locked(&dev->vblank_time_lock);
 
 	vblank->last = last;
 
-	/* All writers hold the spinlock, but readers are serialized by
-	 * the latching of vblank->count below.
-	 */
-	tslot = vblank->count + vblank_count_inc;
-	vblanktimestamp(dev, pipe, tslot) = *t_vblank;
-
-	/*
-	 * vblank timestamp updates are protected on the write side with
-	 * vblank_time_lock, but on the read side done locklessly using a
-	 * sequence-lock on the vblank counter. Ensure correct ordering using
-	 * memory barrriers. We need the barrier both before and also after the
-	 * counter update to synchronize with the next timestamp write.
-	 * The read-side barriers for this are in drm_vblank_count_and_time.
-	 */
-	smp_wmb();
+	write_seqlock(&vblank->seqlock);
+	vblank->time = *t_vblank;
 	vblank->count += vblank_count_inc;
-	smp_wmb();
+	write_sequnlock(&vblank->seqlock);
 }
 
-/**
- * drm_reset_vblank_timestamp - reset the last timestamp to the last vblank
- * @dev: DRM device
- * @pipe: index of CRTC for which to reset the timestamp
- *
+/*
  * Reset the stored timestamp for the current vblank count to correspond
  * to the last vblank occurred.
  *
@@ -155,11 +133,7 @@ static void drm_reset_vblank_timestamp(struct drm_device *dev, unsigned int pipe
 	spin_unlock(&dev->vblank_time_lock);
 }
 
-/**
- * drm_update_vblank_count - update the master vblank counter
- * @dev: DRM device
- * @pipe: counter to update
- *
+/*
  * Call back into the driver to update the appropriate vblank counter
  * (specified by @pipe).  Deal with wraparound, if it occurred, and
  * update the last read value so we can deal with wraparound on the next
@@ -205,7 +179,7 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,
 		const struct timeval *t_old;
 		u64 diff_ns;
 
-		t_old = &vblanktimestamp(dev, pipe, vblank->count);
+		t_old = &vblank->time;
 		diff_ns = timeval_to_ns(&t_vblank) - timeval_to_ns(t_old);
 
 		/*
@@ -239,49 +213,6 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,
 		diff = 1;
 	}
 
-	/*
-	 * FIMXE: Need to replace this hack with proper seqlocks.
-	 *
-	 * Restrict the bump of the software vblank counter to a safe maximum
-	 * value of +1 whenever there is the possibility that concurrent readers
-	 * of vblank timestamps could be active at the moment, as the current
-	 * implementation of the timestamp caching and updating is not safe
-	 * against concurrent readers for calls to store_vblank() with a bump
-	 * of anything but +1. A bump != 1 would very likely return corrupted
-	 * timestamps to userspace, because the same slot in the cache could
-	 * be concurrently written by store_vblank() and read by one of those
-	 * readers without the read-retry logic detecting the collision.
-	 *
-	 * Concurrent readers can exist when we are called from the
-	 * drm_vblank_off() or drm_vblank_on() functions and other non-vblank-
-	 * irq callers. However, all those calls to us are happening with the
-	 * vbl_lock locked to prevent drm_vblank_get(), so the vblank refcount
-	 * can't increase while we are executing. Therefore a zero refcount at
-	 * this point is safe for arbitrary counter bumps if we are called
-	 * outside vblank irq, a non-zero count is not 100% safe. Unfortunately
-	 * we must also accept a refcount of 1, as whenever we are called from
-	 * drm_vblank_get() -> drm_vblank_enable() the refcount will be 1 and
-	 * we must let that one pass through in order to not lose vblank counts
-	 * during vblank irq off - which would completely defeat the whole
-	 * point of this routine.
-	 *
-	 * Whenever we are called from vblank irq, we have to assume concurrent
-	 * readers exist or can show up any time during our execution, even if
-	 * the refcount is currently zero, as vblank irqs are usually only
-	 * enabled due to the presence of readers, and because when we are called
-	 * from vblank irq we can't hold the vbl_lock to protect us from sudden
-	 * bumps in vblank refcount. Therefore also restrict bumps to +1 when
-	 * called from vblank irq.
-	 */
-	if ((diff > 1) && (atomic_read(&vblank->refcount) > 1 ||
-	    (flags & DRM_CALLED_FROM_VBLIRQ))) {
-		DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u "
-			      "refcount %u, vblirq %u\n", pipe, diff,
-			      atomic_read(&vblank->refcount),
-			      (flags & DRM_CALLED_FROM_VBLIRQ) != 0);
-		diff = 1;
-	}
-
 	DRM_DEBUG_VBL("updating vblank count on crtc %u:"
 		      " current=%u, diff=%u, hw=%u hw_last=%u\n",
 		      pipe, vblank->count, diff, cur_vblank, vblank->last);
@@ -303,6 +234,37 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,
 	store_vblank(dev, pipe, diff, &t_vblank, cur_vblank);
 }
 
+/**
+ * drm_accurate_vblank_count - retrieve the master vblank counter
+ * @crtc: which counter to retrieve
+ *
+ * This function is similar to @drm_crtc_vblank_count but this
+ * function interpolates to handle a race with vblank irq's.
+ *
+ * This is mostly useful for hardware that can obtain the scanout
+ * position, but doesn't have a frame counter.
+ */
+u32 drm_accurate_vblank_count(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	unsigned int pipe = drm_crtc_index(crtc);
+	u32 vblank;
+	unsigned long flags;
+
+	WARN(!dev->driver->get_vblank_timestamp,
+	     "This function requires support for accurate vblank timestamps.");
+
+	spin_lock_irqsave(&dev->vblank_time_lock, flags);
+
+	drm_update_vblank_count(dev, pipe, 0);
+	vblank = drm_vblank_count(dev, pipe);
+
+	spin_unlock_irqrestore(&dev->vblank_time_lock, flags);
+
+	return vblank;
+}
+EXPORT_SYMBOL(drm_accurate_vblank_count);
+
 /*
  * Disable vblank irq's on crtc, make sure that last vblank count
  * of hardware and corresponding consistent software vblank counter
@@ -417,6 +379,7 @@ int drm_vblank_init(struct drm_device *dev, unsigned int num_crtcs)
 		init_waitqueue_head(&vblank->queue);
 		setup_timer(&vblank->disable_timer, vblank_disable_fn,
 			    (unsigned long)vblank);
+		seqlock_init(&vblank->seqlock);
 	}
 
 	DRM_INFO("Supports vblank timestamp caching Rev 2 (21.10.2013).\n");
@@ -569,7 +532,7 @@ int drm_irq_uninstall(struct drm_device *dev)
 
 	/*
 	 * Wake up any waiters so they don't hang. This is just to paper over
-	 * isssues for UMS drivers which aren't in full control of their
+	 * issues for UMS drivers which aren't in full control of their
 	 * vblank/irq handling. KMS drivers must ensure that vblanks are all
 	 * disabled when uninstalling the irq handler.
 	 */
@@ -631,7 +594,7 @@ int drm_control(struct drm_device *dev, void *data,
 		return 0;
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return 0;
-	/* UMS was only ever support on pci devices. */
+	/* UMS was only ever supported on pci devices. */
 	if (WARN_ON(!dev->pdev))
 		return -EINVAL;
 
@@ -982,31 +945,24 @@ EXPORT_SYMBOL(drm_crtc_vblank_count);
  *
  * This is the legacy version of drm_crtc_vblank_count_and_time().
  */
-u32 drm_vblank_count_and_time(struct drm_device *dev, unsigned int pipe,
-			      struct timeval *vblanktime)
+static u32 drm_vblank_count_and_time(struct drm_device *dev, unsigned int pipe,
+				     struct timeval *vblanktime)
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
-	int count = DRM_TIMESTAMP_MAXRETRIES;
-	u32 cur_vblank;
+	u32 vblank_count;
+	unsigned int seq;
 
 	if (WARN_ON(pipe >= dev->num_crtcs))
 		return 0;
 
-	/*
-	 * Vblank timestamps are read lockless. To ensure consistency the vblank
-	 * counter is rechecked and ordering is ensured using memory barriers.
-	 * This works like a seqlock. The write-side barriers are in store_vblank.
-	 */
 	do {
-		cur_vblank = vblank->count;
-		smp_rmb();
-		*vblanktime = vblanktimestamp(dev, pipe, cur_vblank);
-		smp_rmb();
-	} while (cur_vblank != vblank->count && --count > 0);
+		seq = read_seqbegin(&vblank->seqlock);
+		vblank_count = vblank->count;
+		*vblanktime = vblank->time;
+	} while (read_seqretry(&vblank->seqlock, seq));
 
-	return cur_vblank;
+	return vblank_count;
 }
-EXPORT_SYMBOL(drm_vblank_count_and_time);
 
 /**
  * drm_crtc_vblank_count_and_time - retrieve "cooked" vblank counter value
@@ -1018,8 +974,6 @@ EXPORT_SYMBOL(drm_vblank_count_and_time);
  * vblank events since the system was booted, including lost events due to
  * modesetting activity. Returns corresponding system timestamp of the time
  * of the vblank interval that corresponds to the current vblank counter value.
- *
- * This is the native KMS version of drm_vblank_count_and_time().
  */
 u32 drm_crtc_vblank_count_and_time(struct drm_crtc *crtc,
 				   struct timeval *vblanktime)
@@ -1037,39 +991,11 @@ static void send_vblank_event(struct drm_device *dev,
 	e->event.tv_sec = now->tv_sec;
 	e->event.tv_usec = now->tv_usec;
 
-	drm_send_event_locked(dev, &e->base);
-
 	trace_drm_vblank_event_delivered(e->base.pid, e->pipe,
 					 e->event.sequence);
-}
-
-/**
- * drm_arm_vblank_event - arm vblank event after pageflip
- * @dev: DRM device
- * @pipe: CRTC index
- * @e: the event to prepare to send
- *
- * A lot of drivers need to generate vblank events for the very next vblank
- * interrupt. For example when the page flip interrupt happens when the page
- * flip gets armed, but not when it actually executes within the next vblank
- * period. This helper function implements exactly the required vblank arming
- * behaviour.
- *
- * Caller must hold event lock. Caller must also hold a vblank reference for
- * the event @e, which will be dropped when the next vblank arrives.
- *
- * This is the legacy version of drm_crtc_arm_vblank_event().
- */
-void drm_arm_vblank_event(struct drm_device *dev, unsigned int pipe,
-			  struct drm_pending_vblank_event *e)
-{
-	assert_spin_locked(&dev->event_lock);
 
-	e->pipe = pipe;
-	e->event.sequence = drm_vblank_count(dev, pipe);
-	list_add_tail(&e->base.link, &dev->vblank_event_list);
+	drm_send_event_locked(dev, &e->base);
 }
-EXPORT_SYMBOL(drm_arm_vblank_event);
 
 /**
  * drm_crtc_arm_vblank_event - arm vblank event after pageflip
@@ -1084,32 +1010,35 @@ EXPORT_SYMBOL(drm_arm_vblank_event);
  *
  * Caller must hold event lock. Caller must also hold a vblank reference for
  * the event @e, which will be dropped when the next vblank arrives.
- *
- * This is the native KMS version of drm_arm_vblank_event().
  */
 void drm_crtc_arm_vblank_event(struct drm_crtc *crtc,
 			       struct drm_pending_vblank_event *e)
 {
-	drm_arm_vblank_event(crtc->dev, drm_crtc_index(crtc), e);
+	struct drm_device *dev = crtc->dev;
+	unsigned int pipe = drm_crtc_index(crtc);
+
+	assert_spin_locked(&dev->event_lock);
+
+	e->pipe = pipe;
+	e->event.sequence = drm_vblank_count(dev, pipe);
+	list_add_tail(&e->base.link, &dev->vblank_event_list);
 }
 EXPORT_SYMBOL(drm_crtc_arm_vblank_event);
 
 /**
- * drm_send_vblank_event - helper to send vblank event after pageflip
- * @dev: DRM device
- * @pipe: CRTC index
+ * drm_crtc_send_vblank_event - helper to send vblank event after pageflip
+ * @crtc: the source CRTC of the vblank event
  * @e: the event to send
  *
  * Updates sequence # and timestamp on event, and sends it to userspace.
  * Caller must hold event lock.
- *
- * This is the legacy version of drm_crtc_send_vblank_event().
  */
-void drm_send_vblank_event(struct drm_device *dev, unsigned int pipe,
-			   struct drm_pending_vblank_event *e)
+void drm_crtc_send_vblank_event(struct drm_crtc *crtc,
+				struct drm_pending_vblank_event *e)
 {
+	struct drm_device *dev = crtc->dev;
+	unsigned int seq, pipe = drm_crtc_index(crtc);
 	struct timeval now;
-	unsigned int seq;
 
 	if (dev->num_crtcs > 0) {
 		seq = drm_vblank_count_and_time(dev, pipe, &now);
@@ -1121,23 +1050,6 @@ void drm_send_vblank_event(struct drm_device *dev, unsigned int pipe,
 	e->pipe = pipe;
 	send_vblank_event(dev, e, seq, &now);
 }
-EXPORT_SYMBOL(drm_send_vblank_event);
-
-/**
- * drm_crtc_send_vblank_event - helper to send vblank event after pageflip
- * @crtc: the source CRTC of the vblank event
- * @e: the event to send
- *
- * Updates sequence # and timestamp on event, and sends it to userspace.
- * Caller must hold event lock.
- *
- * This is the native KMS version of drm_send_vblank_event().
- */
-void drm_crtc_send_vblank_event(struct drm_crtc *crtc,
-				struct drm_pending_vblank_event *e)
-{
-	drm_send_vblank_event(crtc->dev, drm_crtc_index(crtc), e);
-}
 EXPORT_SYMBOL(drm_crtc_send_vblank_event);
 
 /**
@@ -1193,7 +1105,7 @@ static int drm_vblank_enable(struct drm_device *dev, unsigned int pipe)
  * Returns:
  * Zero on success or a negative error code on failure.
  */
-int drm_vblank_get(struct drm_device *dev, unsigned int pipe)
+static int drm_vblank_get(struct drm_device *dev, unsigned int pipe)
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
 	unsigned long irqflags;
@@ -1219,7 +1131,6 @@ int drm_vblank_get(struct drm_device *dev, unsigned int pipe)
 
 	return ret;
 }
-EXPORT_SYMBOL(drm_vblank_get);
 
 /**
  * drm_crtc_vblank_get - get a reference count on vblank events
@@ -1228,8 +1139,6 @@ EXPORT_SYMBOL(drm_vblank_get);
  * Acquire a reference count on vblank events to avoid having them disabled
  * while in use.
  *
- * This is the native kms version of drm_vblank_get().
- *
  * Returns:
  * Zero on success or a negative error code on failure.
  */
@@ -1249,7 +1158,7 @@ EXPORT_SYMBOL(drm_crtc_vblank_get);
  *
  * This is the legacy version of drm_crtc_vblank_put().
  */
-void drm_vblank_put(struct drm_device *dev, unsigned int pipe)
+static void drm_vblank_put(struct drm_device *dev, unsigned int pipe)
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
 
@@ -1270,7 +1179,6 @@ void drm_vblank_put(struct drm_device *dev, unsigned int pipe)
 				  jiffies + ((drm_vblank_offdelay * HZ)/1000));
 	}
 }
-EXPORT_SYMBOL(drm_vblank_put);
 
 /**
  * drm_crtc_vblank_put - give up ownership of vblank events
@@ -1278,8 +1186,6 @@ EXPORT_SYMBOL(drm_vblank_put);
  *
  * Release ownership of a given vblank counter, turning off interrupts
  * if possible. Disable interrupts after drm_vblank_offdelay milliseconds.
- *
- * This is the native kms version of drm_vblank_put().
  */
 void drm_crtc_vblank_put(struct drm_crtc *crtc)
 {
@@ -1679,12 +1585,6 @@ static int drm_queue_vblank_event(struct drm_device *dev, unsigned int pipe,
 
 	seq = drm_vblank_count_and_time(dev, pipe, &now);
 
-	if ((vblwait->request.type & _DRM_VBLANK_NEXTONMISS) &&
-	    (seq - vblwait->request.sequence) <= (1 << 23)) {
-		vblwait->request.sequence = seq + 1;
-		vblwait->reply.sequence = vblwait->request.sequence;
-	}
-
 	DRM_DEBUG("event on vblank count %d, current %d, crtc %u\n",
 		  vblwait->request.sequence, seq, pipe);
 
@@ -1781,6 +1681,11 @@ int drm_wait_vblank(struct drm_device *dev, void *data,
 		goto done;
 	}
 
+	if ((flags & _DRM_VBLANK_NEXTONMISS) &&
+	    (seq - vblwait->request.sequence) <= (1 << 23)) {
+		vblwait->request.sequence = seq + 1;
+	}
+
 	if (flags & _DRM_VBLANK_EVENT) {
 		/* must hold on to the vblank ref until the event fires
 		 * drm_vblank_put will be called asynchronously
@@ -1788,14 +1693,8 @@ int drm_wait_vblank(struct drm_device *dev, void *data,
 		return drm_queue_vblank_event(dev, pipe, vblwait, file_priv);
 	}
 
-	if ((flags & _DRM_VBLANK_NEXTONMISS) &&
-	    (seq - vblwait->request.sequence) <= (1<<23)) {
-		vblwait->request.sequence = seq + 1;
-	}
-
 	DRM_DEBUG("waiting on vblank count %d, crtc %u\n",
 		  vblwait->request.sequence, pipe);
-	vblank->last_wait = vblwait->request.sequence;
 	DRM_WAIT_ON(ret, vblank->queue, 3 * HZ,
 		    (((drm_vblank_count(dev, pipe) -
 		       vblwait->request.sequence) <= (1 << 23)) ||
diff --git a/drivers/gpu/drm/drm_legacy.h b/drivers/gpu/drm/drm_legacy.h
index d3b6ee357a2b..c6f422e879dd 100644
--- a/drivers/gpu/drm/drm_legacy.h
+++ b/drivers/gpu/drm/drm_legacy.h
@@ -88,14 +88,10 @@ struct drm_agp_mem {
 	struct list_head head;
 };
 
-/*
- * Generic Userspace Locking-API
- */
-
-int drm_legacy_i_have_hw_lock(struct drm_device *d, struct drm_file *f);
+/* drm_lock.c */
 int drm_legacy_lock(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_unlock(struct drm_device *d, void *v, struct drm_file *f);
-int drm_legacy_lock_free(struct drm_lock_data *lock, unsigned int ctx);
+void drm_legacy_lock_release(struct drm_device *dev, struct file *filp);
 
 /* DMA support */
 int drm_legacy_dma_setup(struct drm_device *dev);
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index daa2ff12101b..48ac0ebbd663 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -41,6 +41,110 @@
 static int drm_lock_take(struct drm_lock_data *lock_data, unsigned int context);
 
 /**
+ * Take the heavyweight lock.
+ *
+ * \param lock lock pointer.
+ * \param context locking context.
+ * \return one if the lock is held, or zero otherwise.
+ *
+ * Attempt to mark the lock as held by the given context, via the \p cmpxchg instruction.
+ */
+static
+int drm_lock_take(struct drm_lock_data *lock_data,
+		  unsigned int context)
+{
+	unsigned int old, new, prev;
+	volatile unsigned int *lock = &lock_data->hw_lock->lock;
+
+	spin_lock_bh(&lock_data->spinlock);
+	do {
+		old = *lock;
+		if (old & _DRM_LOCK_HELD)
+			new = old | _DRM_LOCK_CONT;
+		else {
+			new = context | _DRM_LOCK_HELD |
+				((lock_data->user_waiters + lock_data->kernel_waiters > 1) ?
+				 _DRM_LOCK_CONT : 0);
+		}
+		prev = cmpxchg(lock, old, new);
+	} while (prev != old);
+	spin_unlock_bh(&lock_data->spinlock);
+
+	if (_DRM_LOCKING_CONTEXT(old) == context) {
+		if (old & _DRM_LOCK_HELD) {
+			if (context != DRM_KERNEL_CONTEXT) {
+				DRM_ERROR("%d holds heavyweight lock\n",
+					  context);
+			}
+			return 0;
+		}
+	}
+
+	if ((_DRM_LOCKING_CONTEXT(new)) == context && (new & _DRM_LOCK_HELD)) {
+		/* Have lock */
+		return 1;
+	}
+	return 0;
+}
+
+/**
+ * This takes a lock forcibly and hands it to context.	Should ONLY be used
+ * inside *_unlock to give lock to kernel before calling *_dma_schedule.
+ *
+ * \param dev DRM device.
+ * \param lock lock pointer.
+ * \param context locking context.
+ * \return always one.
+ *
+ * Resets the lock file pointer.
+ * Marks the lock as held by the given context, via the \p cmpxchg instruction.
+ */
+static int drm_lock_transfer(struct drm_lock_data *lock_data,
+			     unsigned int context)
+{
+	unsigned int old, new, prev;
+	volatile unsigned int *lock = &lock_data->hw_lock->lock;
+
+	lock_data->file_priv = NULL;
+	do {
+		old = *lock;
+		new = context | _DRM_LOCK_HELD;
+		prev = cmpxchg(lock, old, new);
+	} while (prev != old);
+	return 1;
+}
+
+static int drm_legacy_lock_free(struct drm_lock_data *lock_data,
+				unsigned int context)
+{
+	unsigned int old, new, prev;
+	volatile unsigned int *lock = &lock_data->hw_lock->lock;
+
+	spin_lock_bh(&lock_data->spinlock);
+	if (lock_data->kernel_waiters != 0) {
+		drm_lock_transfer(lock_data, 0);
+		lock_data->idle_has_lock = 1;
+		spin_unlock_bh(&lock_data->spinlock);
+		return 1;
+	}
+	spin_unlock_bh(&lock_data->spinlock);
+
+	do {
+		old = *lock;
+		new = _DRM_LOCKING_CONTEXT(old);
+		prev = cmpxchg(lock, old, new);
+	} while (prev != old);
+
+	if (_DRM_LOCK_IS_HELD(old) && _DRM_LOCKING_CONTEXT(old) != context) {
+		DRM_ERROR("%d freed heavyweight lock held by %d\n",
+			  context, _DRM_LOCKING_CONTEXT(old));
+		return 1;
+	}
+	wake_up_interruptible(&lock_data->lock_queue);
+	return 0;
+}
+
+/**
  * Lock ioctl.
  *
  * \param inode device inode.
@@ -115,7 +219,7 @@ int drm_legacy_lock(struct drm_device *dev, void *data,
 	/* don't set the block all signals on the master process for now 
 	 * really probably not the correct answer but lets us debug xkb
  	 * xserver for now */
-	if (!file_priv->is_master) {
+	if (!drm_is_current_master(file_priv)) {
 		dev->sigdata.context = lock->context;
 		dev->sigdata.lock = master->lock.hw_lock;
 	}
@@ -165,120 +269,6 @@ int drm_legacy_unlock(struct drm_device *dev, void *data, struct drm_file *file_
 }
 
 /**
- * Take the heavyweight lock.
- *
- * \param lock lock pointer.
- * \param context locking context.
- * \return one if the lock is held, or zero otherwise.
- *
- * Attempt to mark the lock as held by the given context, via the \p cmpxchg instruction.
- */
-static
-int drm_lock_take(struct drm_lock_data *lock_data,
-		  unsigned int context)
-{
-	unsigned int old, new, prev;
-	volatile unsigned int *lock = &lock_data->hw_lock->lock;
-
-	spin_lock_bh(&lock_data->spinlock);
-	do {
-		old = *lock;
-		if (old & _DRM_LOCK_HELD)
-			new = old | _DRM_LOCK_CONT;
-		else {
-			new = context | _DRM_LOCK_HELD |
-				((lock_data->user_waiters + lock_data->kernel_waiters > 1) ?
-				 _DRM_LOCK_CONT : 0);
-		}
-		prev = cmpxchg(lock, old, new);
-	} while (prev != old);
-	spin_unlock_bh(&lock_data->spinlock);
-
-	if (_DRM_LOCKING_CONTEXT(old) == context) {
-		if (old & _DRM_LOCK_HELD) {
-			if (context != DRM_KERNEL_CONTEXT) {
-				DRM_ERROR("%d holds heavyweight lock\n",
-					  context);
-			}
-			return 0;
-		}
-	}
-
-	if ((_DRM_LOCKING_CONTEXT(new)) == context && (new & _DRM_LOCK_HELD)) {
-		/* Have lock */
-		return 1;
-	}
-	return 0;
-}
-
-/**
- * This takes a lock forcibly and hands it to context.	Should ONLY be used
- * inside *_unlock to give lock to kernel before calling *_dma_schedule.
- *
- * \param dev DRM device.
- * \param lock lock pointer.
- * \param context locking context.
- * \return always one.
- *
- * Resets the lock file pointer.
- * Marks the lock as held by the given context, via the \p cmpxchg instruction.
- */
-static int drm_lock_transfer(struct drm_lock_data *lock_data,
-			     unsigned int context)
-{
-	unsigned int old, new, prev;
-	volatile unsigned int *lock = &lock_data->hw_lock->lock;
-
-	lock_data->file_priv = NULL;
-	do {
-		old = *lock;
-		new = context | _DRM_LOCK_HELD;
-		prev = cmpxchg(lock, old, new);
-	} while (prev != old);
-	return 1;
-}
-
-/**
- * Free lock.
- *
- * \param dev DRM device.
- * \param lock lock.
- * \param context context.
- *
- * Resets the lock file pointer.
- * Marks the lock as not held, via the \p cmpxchg instruction. Wakes any task
- * waiting on the lock queue.
- */
-int drm_legacy_lock_free(struct drm_lock_data *lock_data, unsigned int context)
-{
-	unsigned int old, new, prev;
-	volatile unsigned int *lock = &lock_data->hw_lock->lock;
-
-	spin_lock_bh(&lock_data->spinlock);
-	if (lock_data->kernel_waiters != 0) {
-		drm_lock_transfer(lock_data, 0);
-		lock_data->idle_has_lock = 1;
-		spin_unlock_bh(&lock_data->spinlock);
-		return 1;
-	}
-	spin_unlock_bh(&lock_data->spinlock);
-
-	do {
-		old = *lock;
-		new = _DRM_LOCKING_CONTEXT(old);
-		prev = cmpxchg(lock, old, new);
-	} while (prev != old);
-
-	if (_DRM_LOCK_IS_HELD(old) && _DRM_LOCKING_CONTEXT(old) != context) {
-		DRM_ERROR("%d freed heavyweight lock held by %d\n",
-			  context, _DRM_LOCKING_CONTEXT(old));
-		return 1;
-	}
-	wake_up_interruptible(&lock_data->lock_queue);
-	return 0;
-}
-
-/**
  * This function returns immediately and takes the hw lock
  * with the kernel context if it is free, otherwise it gets the highest priority when and if
  * it is eventually released.
@@ -330,11 +320,27 @@ void drm_legacy_idlelock_release(struct drm_lock_data *lock_data)
 }
 EXPORT_SYMBOL(drm_legacy_idlelock_release);
 
-int drm_legacy_i_have_hw_lock(struct drm_device *dev,
-			      struct drm_file *file_priv)
+static int drm_legacy_i_have_hw_lock(struct drm_device *dev,
+				     struct drm_file *file_priv)
 {
 	struct drm_master *master = file_priv->master;
 	return (file_priv->lock_count && master->lock.hw_lock &&
 		_DRM_LOCK_IS_HELD(master->lock.hw_lock->lock) &&
 		master->lock.file_priv == file_priv);
 }
+
+void drm_legacy_lock_release(struct drm_device *dev, struct file *filp)
+{
+	struct drm_file *file_priv = filp->private_data;
+
+	/* if the master has gone away we can't do anything with the lock */
+	if (!dev->master)
+		return;
+
+	if (drm_legacy_i_have_hw_lock(dev, file_priv)) {
+		DRM_DEBUG("File %p released, freeing lock for context %d\n",
+			  filp, _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock));
+		drm_legacy_lock_free(&file_priv->master->lock,
+				     _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock));
+	}
+}
diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c
index 87a8cb73366f..fc0ebd273ef8 100644
--- a/drivers/gpu/drm/drm_memory.c
+++ b/drivers/gpu/drm/drm_memory.c
@@ -44,7 +44,7 @@
 # include <asm/agp.h>
 #else
 # ifdef __powerpc__
-#  define PAGE_AGP	__pgprot(_PAGE_KERNEL | _PAGE_NO_CACHE)
+#  define PAGE_AGP	pgprot_noncached_wc(PAGE_KERNEL)
 # else
 #  define PAGE_AGP	PAGE_KERNEL
 # endif
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index f5d80839a90c..af0d471ee246 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -60,6 +60,21 @@ static int mipi_dsi_device_match(struct device *dev, struct device_driver *drv)
 	return 0;
 }
 
+static int mipi_dsi_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev);
+	int err;
+
+	err = of_device_uevent_modalias(dev, env);
+	if (err != -ENODEV)
+		return err;
+
+	add_uevent_var(env, "MODALIAS=%s%s", MIPI_DSI_MODULE_PREFIX,
+		       dsi->name);
+
+	return 0;
+}
+
 static const struct dev_pm_ops mipi_dsi_device_pm_ops = {
 	.runtime_suspend = pm_generic_runtime_suspend,
 	.runtime_resume = pm_generic_runtime_resume,
@@ -74,6 +89,7 @@ static const struct dev_pm_ops mipi_dsi_device_pm_ops = {
 static struct bus_type mipi_dsi_bus_type = {
 	.name = "mipi-dsi",
 	.match = mipi_dsi_device_match,
+	.uevent = mipi_dsi_uevent,
 	.pm = &mipi_dsi_device_pm_ops,
 };
 
@@ -983,6 +999,28 @@ int mipi_dsi_dcs_set_tear_on(struct mipi_dsi_device *dsi,
 EXPORT_SYMBOL(mipi_dsi_dcs_set_tear_on);
 
 /**
+ * mipi_dsi_dcs_set_tear_scanline() - set the scanline to use as trigger for
+ *    the Tearing Effect output signal of the display module
+ * @dsi: DSI peripheral device
+ * @scanline: scanline to use as trigger
+ *
+ * Return: 0 on success or a negative error code on failure
+ */
+int mipi_dsi_dcs_set_tear_scanline(struct mipi_dsi_device *dsi, u16 scanline)
+{
+	u8 payload[3] = { MIPI_DCS_SET_TEAR_SCANLINE, scanline >> 8,
+			  scanline & 0xff };
+	ssize_t err;
+
+	err = mipi_dsi_generic_write(dsi, payload, sizeof(payload));
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+EXPORT_SYMBOL(mipi_dsi_dcs_set_tear_scanline);
+
+/**
  * mipi_dsi_dcs_set_pixel_format() - sets the pixel format for the RGB image
  *    data used by the interface
  * @dsi: DSI peripheral device
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 04de6fd88f8c..cb39f45d6a16 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -179,12 +179,14 @@ static void drm_mm_insert_helper(struct drm_mm_node *hole_node,
 int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node)
 {
 	struct drm_mm_node *hole;
-	u64 end = node->start + node->size;
+	u64 end;
 	u64 hole_start;
 	u64 hole_end;
 
 	BUG_ON(node == NULL);
 
+	end = node->start + node->size;
+
 	/* Find the relevant hole to add our node to */
 	drm_mm_for_each_hole(hole, mm, hole_start, hole_end) {
 		if (hole_start > node->start || hole_end < end)
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index e5e6f504d8cc..fc5040ae5f25 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -544,6 +544,7 @@ EXPORT_SYMBOL(drm_gtf_mode_complex);
  *
  * This function is to create the modeline based on the GTF algorithm.
  * Generalized Timing Formula is derived from:
+ *
  *	GTF Spreadsheet by Andy Morrish (1/5/97)
  *	available at http://www.vesa.org
  *
@@ -552,7 +553,8 @@ EXPORT_SYMBOL(drm_gtf_mode_complex);
  * I also refer to the function of fb_get_mode in the file of
  * drivers/video/fbmon.c
  *
- * Standard GTF parameters:
+ * Standard GTF parameters::
+ *
  *     M = 600
  *     C = 40
  *     K = 128
diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c
index e3a4adf03e7b..61146f5b4f56 100644
--- a/drivers/gpu/drm/drm_modeset_lock.c
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@@ -30,14 +30,14 @@
  *
  * As KMS moves toward more fine grained locking, and atomic ioctl where
  * userspace can indirectly control locking order, it becomes necessary
- * to use ww_mutex and acquire-contexts to avoid deadlocks.  But because
+ * to use &ww_mutex and acquire-contexts to avoid deadlocks.  But because
  * the locking is more distributed around the driver code, we want a bit
  * of extra utility/tracking out of our acquire-ctx.  This is provided
  * by drm_modeset_lock / drm_modeset_acquire_ctx.
  *
- * For basic principles of ww_mutex, see: Documentation/locking/ww-mutex-design.txt
+ * For basic principles of &ww_mutex, see: Documentation/locking/ww-mutex-design.txt
  *
- * The basic usage pattern is to:
+ * The basic usage pattern is to::
  *
  *     drm_modeset_acquire_init(&ctx)
  *     retry:
@@ -51,6 +51,13 @@
  *     ... do stuff ...
  *     drm_modeset_drop_locks(&ctx);
  *     drm_modeset_acquire_fini(&ctx);
+ *
+ *  On top of of these per-object locks using &ww_mutex there's also an overall
+ *  dev->mode_config.lock, for protecting everything else. Mostly this means
+ *  probe state of connectors, and preventing hotplug add/removal of connectors.
+ *
+ *  Finally there's a bunch of dedicated locks to protect drm core internal
+ *  lists and lookup data structures.
  */
 
 /**
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 29d5a548d07a..b2f8f1062d5f 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -144,50 +144,6 @@ int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master)
 }
 EXPORT_SYMBOL(drm_pci_set_busid);
 
-int drm_pci_set_unique(struct drm_device *dev,
-		       struct drm_master *master,
-		       struct drm_unique *u)
-{
-	int domain, bus, slot, func, ret;
-
-	master->unique_len = u->unique_len;
-	master->unique = kmalloc(master->unique_len + 1, GFP_KERNEL);
-	if (!master->unique) {
-		ret = -ENOMEM;
-		goto err;
-	}
-
-	if (copy_from_user(master->unique, u->unique, master->unique_len)) {
-		ret = -EFAULT;
-		goto err;
-	}
-
-	master->unique[master->unique_len] = '\0';
-
-	/* Return error if the busid submitted doesn't match the device's actual
-	 * busid.
-	 */
-	ret = sscanf(master->unique, "PCI:%d:%d:%d", &bus, &slot, &func);
-	if (ret != 3) {
-		ret = -EINVAL;
-		goto err;
-	}
-
-	domain = bus >> 8;
-	bus &= 0xff;
-
-	if ((domain != drm_get_pci_domain(dev)) ||
-	    (bus != dev->pdev->bus->number) ||
-	    (slot != PCI_SLOT(dev->pdev->devfn)) ||
-	    (func != PCI_FUNC(dev->pdev->devfn))) {
-		ret = -EINVAL;
-		goto err;
-	}
-	return 0;
-err:
-	return ret;
-}
-
 static int drm_pci_irq_by_busid(struct drm_device *dev, struct drm_irq_busid *p)
 {
 	if ((p->busnum >> 8) != drm_get_pci_domain(dev) ||
@@ -444,13 +400,6 @@ int drm_irq_by_busid(struct drm_device *dev, void *data,
 {
 	return -EINVAL;
 }
-
-int drm_pci_set_unique(struct drm_device *dev,
-		       struct drm_master *master,
-		       struct drm_unique *u)
-{
-	return -EINVAL;
-}
 #endif
 
 EXPORT_SYMBOL(drm_pci_init);
diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c
index 369d2898ff9e..16c4a7bd7465 100644
--- a/drivers/gpu/drm/drm_plane_helper.c
+++ b/drivers/gpu/drm/drm_plane_helper.c
@@ -115,6 +115,7 @@ static int get_connectors_for_crtc(struct drm_crtc *crtc,
  * @src: source coordinates in 16.16 fixed point
  * @dest: integer destination coordinates
  * @clip: integer clipping coordinates
+ * @rotation: plane rotation
  * @min_scale: minimum @src:@dest scaling factor in 16.16 fixed point
  * @max_scale: maximum @src:@dest scaling factor in 16.16 fixed point
  * @can_position: is it legal to position the plane such that it
@@ -134,16 +135,17 @@ static int get_connectors_for_crtc(struct drm_crtc *crtc,
  * Zero if update appears valid, error code on failure
  */
 int drm_plane_helper_check_update(struct drm_plane *plane,
-				    struct drm_crtc *crtc,
-				    struct drm_framebuffer *fb,
-				    struct drm_rect *src,
-				    struct drm_rect *dest,
-				    const struct drm_rect *clip,
-				    int min_scale,
-				    int max_scale,
-				    bool can_position,
-				    bool can_update_disabled,
-				    bool *visible)
+				  struct drm_crtc *crtc,
+				  struct drm_framebuffer *fb,
+				  struct drm_rect *src,
+				  struct drm_rect *dest,
+				  const struct drm_rect *clip,
+				  unsigned int rotation,
+				  int min_scale,
+				  int max_scale,
+				  bool can_position,
+				  bool can_update_disabled,
+				  bool *visible)
 {
 	int hscale, vscale;
 
@@ -163,6 +165,8 @@ int drm_plane_helper_check_update(struct drm_plane *plane,
 		return -EINVAL;
 	}
 
+	drm_rect_rotate(src, fb->width << 16, fb->height << 16, rotation);
+
 	/* Check scaling */
 	hscale = drm_rect_calc_hscale(src, dest, min_scale, max_scale);
 	vscale = drm_rect_calc_vscale(src, dest, min_scale, max_scale);
@@ -174,6 +178,9 @@ int drm_plane_helper_check_update(struct drm_plane *plane,
 	}
 
 	*visible = drm_rect_clip_scaled(src, dest, clip, hscale, vscale);
+
+	drm_rect_rotate_inv(src, fb->width << 16, fb->height << 16, rotation);
+
 	if (!*visible)
 		/*
 		 * Plane isn't visible; some drivers can handle this
@@ -219,10 +226,12 @@ EXPORT_SYMBOL(drm_plane_helper_check_update);
  *
  * Note that we make some assumptions about hardware limitations that may not be
  * true for all hardware --
- *   1) Primary plane cannot be repositioned.
- *   2) Primary plane cannot be scaled.
- *   3) Primary plane must cover the entire CRTC.
- *   4) Subpixel positioning is not supported.
+ *
+ * 1. Primary plane cannot be repositioned.
+ * 2. Primary plane cannot be scaled.
+ * 3. Primary plane must cover the entire CRTC.
+ * 4. Subpixel positioning is not supported.
+ *
  * Drivers for hardware that don't have these restrictions can provide their
  * own implementation rather than using this helper.
  *
@@ -265,6 +274,7 @@ int drm_primary_helper_update(struct drm_plane *plane, struct drm_crtc *crtc,
 
 	ret = drm_plane_helper_check_update(plane, crtc, fb,
 					    &src, &dest, &clip,
+					    BIT(DRM_ROTATE_0),
 					    DRM_PLANE_HELPER_NO_SCALING,
 					    DRM_PLANE_HELPER_NO_SCALING,
 					    false, false, &visible);
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index 644169e1a029..2c819ef90090 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -68,24 +68,6 @@ err_free:
 	return ret;
 }
 
-int drm_platform_set_busid(struct drm_device *dev, struct drm_master *master)
-{
-	int id;
-
-	id = dev->platformdev->id;
-	if (id < 0)
-		id = 0;
-
-	master->unique = kasprintf(GFP_KERNEL, "platform:%s:%02d",
-						dev->platformdev->name, id);
-	if (!master->unique)
-		return -ENOMEM;
-
-	master->unique_len = strlen(master->unique);
-	return 0;
-}
-EXPORT_SYMBOL(drm_platform_set_busid);
-
 /**
  * drm_platform_init - Register a platform device with the DRM subsystem
  * @driver: DRM device driver
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index aab0f3f1f42d..780589b420a4 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -593,7 +593,7 @@ int drm_gem_prime_fd_to_handle(struct drm_device *dev,
 		get_dma_buf(dma_buf);
 	}
 
-	/* drm_gem_handle_create_tail unlocks dev->object_name_lock. */
+	/* _handle_create_tail unconditionally unlocks dev->object_name_lock. */
 	ret = drm_gem_handle_create_tail(file_priv, obj, handle);
 	drm_gem_object_unreference_unlocked(obj);
 	if (ret)
@@ -601,11 +601,10 @@ int drm_gem_prime_fd_to_handle(struct drm_device *dev,
 
 	ret = drm_prime_add_buf_handle(&file_priv->prime,
 			dma_buf, *handle);
+	mutex_unlock(&file_priv->prime.lock);
 	if (ret)
 		goto fail;
 
-	mutex_unlock(&file_priv->prime.lock);
-
 	dma_buf_put(dma_buf);
 
 	return 0;
@@ -615,11 +614,14 @@ fail:
 	 * to detach.. which seems ok..
 	 */
 	drm_gem_handle_delete(file_priv, *handle);
+	dma_buf_put(dma_buf);
+	return ret;
+
 out_unlock:
 	mutex_unlock(&dev->object_name_lock);
 out_put:
-	dma_buf_put(dma_buf);
 	mutex_unlock(&file_priv->prime.lock);
+	dma_buf_put(dma_buf);
 	return ret;
 }
 EXPORT_SYMBOL(drm_gem_prime_fd_to_handle);
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 0329080d7f7c..a0df377d7d1c 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -82,13 +82,30 @@ drm_mode_validate_flag(const struct drm_display_mode *mode,
 
 static int drm_helper_probe_add_cmdline_mode(struct drm_connector *connector)
 {
+	struct drm_cmdline_mode *cmdline_mode;
 	struct drm_display_mode *mode;
 
-	if (!connector->cmdline_mode.specified)
+	cmdline_mode = &connector->cmdline_mode;
+	if (!cmdline_mode->specified)
 		return 0;
 
+	/* Only add a GTF mode if we find no matching probed modes */
+	list_for_each_entry(mode, &connector->probed_modes, head) {
+		if (mode->hdisplay != cmdline_mode->xres ||
+		    mode->vdisplay != cmdline_mode->yres)
+			continue;
+
+		if (cmdline_mode->refresh_specified) {
+			/* The probed mode's vrefresh is set until later */
+			if (drm_mode_vrefresh(mode) != cmdline_mode->refresh)
+				continue;
+		}
+
+		return 0;
+	}
+
 	mode = drm_mode_create_from_cmdline_mode(connector->dev,
-						 &connector->cmdline_mode);
+						 cmdline_mode);
 	if (mode == NULL)
 		return 0;
 
diff --git a/drivers/gpu/drm/drm_scatter.c b/drivers/gpu/drm/drm_scatter.c
index 4f0f3b36d537..bf70431073f6 100644
--- a/drivers/gpu/drm/drm_scatter.c
+++ b/drivers/gpu/drm/drm_scatter.c
@@ -41,7 +41,7 @@
 static inline void *drm_vmalloc_dma(unsigned long size)
 {
 #if defined(__powerpc__) && defined(CONFIG_NOT_COHERENT_CACHE)
-	return __vmalloc(size, GFP_KERNEL, PAGE_KERNEL | _PAGE_NO_CACHE);
+	return __vmalloc(size, GFP_KERNEL, pgprot_noncached_wc(PAGE_KERNEL));
 #else
 	return vmalloc_32(size);
 #endif
diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c
new file mode 100644
index 000000000000..0db36d27e90b
--- /dev/null
+++ b/drivers/gpu/drm/drm_simple_kms_helper.c
@@ -0,0 +1,206 @@
+/*
+ * Copyright (C) 2016 Noralf Trønnes
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_plane_helper.h>
+#include <drm/drm_simple_kms_helper.h>
+#include <linux/slab.h>
+
+/**
+ * DOC: overview
+ *
+ * This helper library provides helpers for drivers for simple display
+ * hardware.
+ *
+ * drm_simple_display_pipe_init() initializes a simple display pipeline
+ * which has only one full-screen scanout buffer feeding one output. The
+ * pipeline is represented by struct &drm_simple_display_pipe and binds
+ * together &drm_plane, &drm_crtc and &drm_encoder structures into one fixed
+ * entity. Some flexibility for code reuse is provided through a separately
+ * allocated &drm_connector object and supporting optional &drm_bridge
+ * encoder drivers.
+ */
+
+static const struct drm_encoder_funcs drm_simple_kms_encoder_funcs = {
+	.destroy = drm_encoder_cleanup,
+};
+
+static void drm_simple_kms_crtc_enable(struct drm_crtc *crtc)
+{
+	struct drm_simple_display_pipe *pipe;
+
+	pipe = container_of(crtc, struct drm_simple_display_pipe, crtc);
+	if (!pipe->funcs || !pipe->funcs->enable)
+		return;
+
+	pipe->funcs->enable(pipe, crtc->state);
+}
+
+static void drm_simple_kms_crtc_disable(struct drm_crtc *crtc)
+{
+	struct drm_simple_display_pipe *pipe;
+
+	pipe = container_of(crtc, struct drm_simple_display_pipe, crtc);
+	if (!pipe->funcs || !pipe->funcs->disable)
+		return;
+
+	pipe->funcs->disable(pipe);
+}
+
+static const struct drm_crtc_helper_funcs drm_simple_kms_crtc_helper_funcs = {
+	.disable = drm_simple_kms_crtc_disable,
+	.enable = drm_simple_kms_crtc_enable,
+};
+
+static const struct drm_crtc_funcs drm_simple_kms_crtc_funcs = {
+	.reset = drm_atomic_helper_crtc_reset,
+	.destroy = drm_crtc_cleanup,
+	.set_config = drm_atomic_helper_set_config,
+	.page_flip = drm_atomic_helper_page_flip,
+	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
+};
+
+static int drm_simple_kms_plane_atomic_check(struct drm_plane *plane,
+					struct drm_plane_state *plane_state)
+{
+	struct drm_rect src = {
+		.x1 = plane_state->src_x,
+		.y1 = plane_state->src_y,
+		.x2 = plane_state->src_x + plane_state->src_w,
+		.y2 = plane_state->src_y + plane_state->src_h,
+	};
+	struct drm_rect dest = {
+		.x1 = plane_state->crtc_x,
+		.y1 = plane_state->crtc_y,
+		.x2 = plane_state->crtc_x + plane_state->crtc_w,
+		.y2 = plane_state->crtc_y + plane_state->crtc_h,
+	};
+	struct drm_rect clip = { 0 };
+	struct drm_simple_display_pipe *pipe;
+	struct drm_crtc_state *crtc_state;
+	bool visible;
+	int ret;
+
+	pipe = container_of(plane, struct drm_simple_display_pipe, plane);
+	crtc_state = drm_atomic_get_existing_crtc_state(plane_state->state,
+							&pipe->crtc);
+	if (crtc_state->enable != !!plane_state->crtc)
+		return -EINVAL; /* plane must match crtc enable state */
+
+	if (!crtc_state->enable)
+		return 0; /* nothing to check when disabling or disabled */
+
+	clip.x2 = crtc_state->adjusted_mode.hdisplay;
+	clip.y2 = crtc_state->adjusted_mode.vdisplay;
+	ret = drm_plane_helper_check_update(plane, &pipe->crtc,
+					    plane_state->fb,
+					    &src, &dest, &clip,
+					    plane_state->rotation,
+					    DRM_PLANE_HELPER_NO_SCALING,
+					    DRM_PLANE_HELPER_NO_SCALING,
+					    false, true, &visible);
+	if (ret)
+		return ret;
+
+	if (!visible)
+		return -EINVAL;
+
+	if (!pipe->funcs || !pipe->funcs->check)
+		return 0;
+
+	return pipe->funcs->check(pipe, plane_state, crtc_state);
+}
+
+static void drm_simple_kms_plane_atomic_update(struct drm_plane *plane,
+					struct drm_plane_state *pstate)
+{
+	struct drm_simple_display_pipe *pipe;
+
+	pipe = container_of(plane, struct drm_simple_display_pipe, plane);
+	if (!pipe->funcs || !pipe->funcs->update)
+		return;
+
+	pipe->funcs->update(pipe, pstate);
+}
+
+static const struct drm_plane_helper_funcs drm_simple_kms_plane_helper_funcs = {
+	.atomic_check = drm_simple_kms_plane_atomic_check,
+	.atomic_update = drm_simple_kms_plane_atomic_update,
+};
+
+static const struct drm_plane_funcs drm_simple_kms_plane_funcs = {
+	.update_plane		= drm_atomic_helper_update_plane,
+	.disable_plane		= drm_atomic_helper_disable_plane,
+	.destroy		= drm_plane_cleanup,
+	.reset			= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state	= drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+};
+
+/**
+ * drm_simple_display_pipe_init - Initialize a simple display pipeline
+ * @dev: DRM device
+ * @pipe: simple display pipe object to initialize
+ * @funcs: callbacks for the display pipe (optional)
+ * @formats: array of supported formats (%DRM_FORMAT_*)
+ * @format_count: number of elements in @formats
+ * @connector: connector to attach and register
+ *
+ * Sets up a display pipeline which consist of a really simple
+ * plane-crtc-encoder pipe coupled with the provided connector.
+ * Teardown of a simple display pipe is all handled automatically by the drm
+ * core through calling drm_mode_config_cleanup(). Drivers afterwards need to
+ * release the memory for the structure themselves.
+ *
+ * Returns:
+ * Zero on success, negative error code on failure.
+ */
+int drm_simple_display_pipe_init(struct drm_device *dev,
+			struct drm_simple_display_pipe *pipe,
+			const struct drm_simple_display_pipe_funcs *funcs,
+			const uint32_t *formats, unsigned int format_count,
+			struct drm_connector *connector)
+{
+	struct drm_encoder *encoder = &pipe->encoder;
+	struct drm_plane *plane = &pipe->plane;
+	struct drm_crtc *crtc = &pipe->crtc;
+	int ret;
+
+	pipe->connector = connector;
+	pipe->funcs = funcs;
+
+	drm_plane_helper_add(plane, &drm_simple_kms_plane_helper_funcs);
+	ret = drm_universal_plane_init(dev, plane, 0,
+				       &drm_simple_kms_plane_funcs,
+				       formats, format_count,
+				       DRM_PLANE_TYPE_PRIMARY, NULL);
+	if (ret)
+		return ret;
+
+	drm_crtc_helper_add(crtc, &drm_simple_kms_crtc_helper_funcs);
+	ret = drm_crtc_init_with_planes(dev, crtc, plane, NULL,
+					&drm_simple_kms_crtc_funcs, NULL);
+	if (ret)
+		return ret;
+
+	encoder->possible_crtcs = 1 << drm_crtc_index(crtc);
+	ret = drm_encoder_init(dev, encoder, &drm_simple_kms_encoder_funcs,
+			       DRM_MODE_ENCODER_NONE, NULL);
+	if (ret)
+		return ret;
+
+	return drm_mode_connector_attach_encoder(connector, encoder);
+}
+EXPORT_SYMBOL(drm_simple_display_pipe_init);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index fa7fadce8063..32dd821b7202 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -32,75 +32,6 @@ static struct device_type drm_sysfs_device_minor = {
 
 struct class *drm_class;
 
-/**
- * __drm_class_suspend - internal DRM class suspend routine
- * @dev: Linux device to suspend
- * @state: power state to enter
- *
- * Just figures out what the actual struct drm_device associated with
- * @dev is and calls its suspend hook, if present.
- */
-static int __drm_class_suspend(struct device *dev, pm_message_t state)
-{
-	if (dev->type == &drm_sysfs_device_minor) {
-		struct drm_minor *drm_minor = to_drm_minor(dev);
-		struct drm_device *drm_dev = drm_minor->dev;
-
-		if (drm_minor->type == DRM_MINOR_LEGACY &&
-		    !drm_core_check_feature(drm_dev, DRIVER_MODESET) &&
-		    drm_dev->driver->suspend)
-			return drm_dev->driver->suspend(drm_dev, state);
-	}
-	return 0;
-}
-
-/**
- * drm_class_suspend - internal DRM class suspend hook. Simply calls
- * __drm_class_suspend() with the correct pm state.
- * @dev: Linux device to suspend
- */
-static int drm_class_suspend(struct device *dev)
-{
-	return __drm_class_suspend(dev, PMSG_SUSPEND);
-}
-
-/**
- * drm_class_freeze - internal DRM class freeze hook. Simply calls
- * __drm_class_suspend() with the correct pm state.
- * @dev: Linux device to freeze
- */
-static int drm_class_freeze(struct device *dev)
-{
-	return __drm_class_suspend(dev, PMSG_FREEZE);
-}
-
-/**
- * drm_class_resume - DRM class resume hook
- * @dev: Linux device to resume
- *
- * Just figures out what the actual struct drm_device associated with
- * @dev is and calls its resume hook, if present.
- */
-static int drm_class_resume(struct device *dev)
-{
-	if (dev->type == &drm_sysfs_device_minor) {
-		struct drm_minor *drm_minor = to_drm_minor(dev);
-		struct drm_device *drm_dev = drm_minor->dev;
-
-		if (drm_minor->type == DRM_MINOR_LEGACY &&
-		    !drm_core_check_feature(drm_dev, DRIVER_MODESET) &&
-		    drm_dev->driver->resume)
-			return drm_dev->driver->resume(drm_dev);
-	}
-	return 0;
-}
-
-static const struct dev_pm_ops drm_class_dev_pm_ops = {
-	.suspend	= drm_class_suspend,
-	.resume		= drm_class_resume,
-	.freeze		= drm_class_freeze,
-};
-
 static char *drm_devnode(struct device *dev, umode_t *mode)
 {
 	return kasprintf(GFP_KERNEL, "dri/%s", dev_name(dev));
@@ -131,8 +62,6 @@ int drm_sysfs_init(void)
 	if (IS_ERR(drm_class))
 		return PTR_ERR(drm_class);
 
-	drm_class->pm = &drm_class_dev_pm_ops;
-
 	err = class_create_file(drm_class, &class_attr_version.attr);
 	if (err) {
 		class_destroy(drm_class);
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index ac9f4b3ec615..caa4e4ca616d 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -80,7 +80,7 @@ static pgprot_t drm_dma_prot(uint32_t map_type, struct vm_area_struct *vma)
 	pgprot_t tmp = vm_get_page_prot(vma->vm_flags);
 
 #if defined(__powerpc__) && defined(CONFIG_NOT_COHERENT_CACHE)
-	tmp |= _PAGE_NO_CACHE;
+	tmp = pgprot_noncached_wc(tmp);
 #endif
 	return tmp;
 }
@@ -593,7 +593,7 @@ static int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma)
 			 * pages and mappings in fault()
 			 */
 #if defined(__powerpc__)
-			pgprot_val(vma->vm_page_prot) |= _PAGE_NO_CACHE;
+			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 #endif
 			vma->vm_ops = &drm_vm_ops;
 			break;
@@ -670,57 +670,3 @@ void drm_legacy_vma_flush(struct drm_device *dev)
 		kfree(vma);
 	}
 }
-
-int drm_vma_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct drm_vma_entry *pt;
-	struct vm_area_struct *vma;
-	unsigned long vma_count = 0;
-#if defined(__i386__)
-	unsigned int pgprot;
-#endif
-
-	mutex_lock(&dev->struct_mutex);
-	list_for_each_entry(pt, &dev->vmalist, head)
-		vma_count++;
-
-	seq_printf(m, "vma use count: %lu, high_memory = %pK, 0x%pK\n",
-		   vma_count, high_memory,
-		   (void *)(unsigned long)virt_to_phys(high_memory));
-
-	list_for_each_entry(pt, &dev->vmalist, head) {
-		vma = pt->vma;
-		if (!vma)
-			continue;
-		seq_printf(m,
-			   "\n%5d 0x%pK-0x%pK %c%c%c%c%c%c 0x%08lx000",
-			   pt->pid,
-			   (void *)vma->vm_start, (void *)vma->vm_end,
-			   vma->vm_flags & VM_READ ? 'r' : '-',
-			   vma->vm_flags & VM_WRITE ? 'w' : '-',
-			   vma->vm_flags & VM_EXEC ? 'x' : '-',
-			   vma->vm_flags & VM_MAYSHARE ? 's' : 'p',
-			   vma->vm_flags & VM_LOCKED ? 'l' : '-',
-			   vma->vm_flags & VM_IO ? 'i' : '-',
-			   vma->vm_pgoff);
-
-#if defined(__i386__)
-		pgprot = pgprot_val(vma->vm_page_prot);
-		seq_printf(m, " %c%c%c%c%c%c%c%c%c",
-			   pgprot & _PAGE_PRESENT ? 'p' : '-',
-			   pgprot & _PAGE_RW ? 'w' : 'r',
-			   pgprot & _PAGE_USER ? 'u' : 's',
-			   pgprot & _PAGE_PWT ? 't' : 'b',
-			   pgprot & _PAGE_PCD ? 'u' : 'c',
-			   pgprot & _PAGE_ACCESSED ? 'a' : '-',
-			   pgprot & _PAGE_DIRTY ? 'd' : '-',
-			   pgprot & _PAGE_PSE ? 'm' : 'k',
-			   pgprot & _PAGE_GLOBAL ? 'g' : 'l');
-#endif
-		seq_printf(m, "\n");
-	}
-	mutex_unlock(&dev->struct_mutex);
-	return 0;
-}
diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c
index 2f2ecde8285b..f306c8855978 100644
--- a/drivers/gpu/drm/drm_vma_manager.c
+++ b/drivers/gpu/drm/drm_vma_manager.c
@@ -127,6 +127,9 @@ EXPORT_SYMBOL(drm_vma_offset_manager_destroy);
  * used to implement weakly referenced lookups using kref_get_unless_zero().
  *
  * Example:
+ *
+ * ::
+ *
  *     drm_vma_offset_lock_lookup(mgr);
  *     node = drm_vma_offset_lookup_locked(mgr);
  *     if (node)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index 3d4f56df8359..ffd1b32caa8d 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -91,10 +91,8 @@ static void load_gpu(struct drm_device *dev)
 			int ret;
 
 			ret = etnaviv_gpu_init(g);
-			if (ret) {
-				dev_err(g->dev, "hw init failed: %d\n", ret);
+			if (ret)
 				priv->gpu[i] = NULL;
-			}
 		}
 	}
 }
@@ -496,7 +494,6 @@ static struct drm_driver etnaviv_drm_driver = {
 				DRIVER_RENDER,
 	.open               = etnaviv_open,
 	.preclose           = etnaviv_preclose,
-	.set_busid          = drm_platform_set_busid,
 	.gem_free_object_unlocked = etnaviv_gem_free_object,
 	.gem_vm_ops         = &vm_ops,
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 8c6f750634af..5ce3603e6eac 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -535,8 +535,7 @@ void etnaviv_gem_describe_objects(struct etnaviv_drm_private *priv,
 
 static void etnaviv_gem_shmem_release(struct etnaviv_gem_object *etnaviv_obj)
 {
-	if (etnaviv_obj->vaddr)
-		vunmap(etnaviv_obj->vaddr);
+	vunmap(etnaviv_obj->vaddr);
 	put_pages(etnaviv_obj);
 }
 
@@ -670,9 +669,7 @@ static struct drm_gem_object *__etnaviv_gem_new(struct drm_device *dev,
 	return obj;
 
 fail:
-	if (obj)
-		drm_gem_object_unreference_unlocked(obj);
-
+	drm_gem_object_unreference_unlocked(obj);
 	return ERR_PTR(ret);
 }
 
@@ -916,15 +913,12 @@ int etnaviv_gem_new_userptr(struct drm_device *dev, struct drm_file *file,
 	get_task_struct(current);
 
 	ret = etnaviv_gem_obj_add(dev, &etnaviv_obj->base);
-	if (ret) {
-		drm_gem_object_unreference_unlocked(&etnaviv_obj->base);
-		return ret;
-	}
+	if (ret)
+		goto unreference;
 
 	ret = drm_gem_handle_create(file, &etnaviv_obj->base, handle);
-
+unreference:
 	/* drop reference from allocate - handle holds it now */
 	drm_gem_object_unreference_unlocked(&etnaviv_obj->base);
-
 	return ret;
 }
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index ff6aa5dfb2d7..87ef34150d46 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -487,6 +487,47 @@ static int etnaviv_hw_reset(struct etnaviv_gpu *gpu)
 	return 0;
 }
 
+static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu)
+{
+	u32 pmc, ppc;
+
+	/* enable clock gating */
+	ppc = gpu_read(gpu, VIVS_PM_POWER_CONTROLS);
+	ppc |= VIVS_PM_POWER_CONTROLS_ENABLE_MODULE_CLOCK_GATING;
+
+	/* Disable stall module clock gating for 4.3.0.1 and 4.3.0.2 revs */
+	if (gpu->identity.revision == 0x4301 ||
+	    gpu->identity.revision == 0x4302)
+		ppc |= VIVS_PM_POWER_CONTROLS_DISABLE_STALL_MODULE_CLOCK_GATING;
+
+	gpu_write(gpu, VIVS_PM_POWER_CONTROLS, ppc);
+
+	pmc = gpu_read(gpu, VIVS_PM_MODULE_CONTROLS);
+
+	/* Disable PA clock gating for GC400+ except for GC420 */
+	if (gpu->identity.model >= chipModel_GC400 &&
+	    gpu->identity.model != chipModel_GC420)
+		pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_PA;
+
+	/*
+	 * Disable PE clock gating on revs < 5.0.0.0 when HZ is
+	 * present without a bug fix.
+	 */
+	if (gpu->identity.revision < 0x5000 &&
+	    gpu->identity.minor_features0 & chipMinorFeatures0_HZ &&
+	    !(gpu->identity.minor_features1 &
+	      chipMinorFeatures1_DISABLE_PE_GATING))
+		pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_PE;
+
+	if (gpu->identity.revision < 0x5422)
+		pmc |= BIT(15); /* Unknown bit */
+
+	pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_HZ;
+	pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_EZ;
+
+	gpu_write(gpu, VIVS_PM_MODULE_CONTROLS, pmc);
+}
+
 static void etnaviv_gpu_hw_init(struct etnaviv_gpu *gpu)
 {
 	u16 prefetch;
@@ -506,6 +547,9 @@ static void etnaviv_gpu_hw_init(struct etnaviv_gpu *gpu)
 		gpu_write(gpu, VIVS_MC_DEBUG_MEMORY, mc_memory_debug);
 	}
 
+	/* enable module-level clock gating */
+	etnaviv_gpu_enable_mlcg(gpu);
+
 	/*
 	 * Update GPU AXI cache atttribute to "cacheable, no allocate".
 	 * This is necessary to prevent the iMX6 SoC locking up.
@@ -553,8 +597,10 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 	bool mmuv2;
 
 	ret = pm_runtime_get_sync(gpu->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		dev_err(gpu->dev, "Failed to enable GPU power domain\n");
 		return ret;
+	}
 
 	etnaviv_hw_identify(gpu);
 
@@ -591,8 +637,10 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 	}
 
 	ret = etnaviv_hw_reset(gpu);
-	if (ret)
+	if (ret) {
+		dev_err(gpu->dev, "GPU reset failed\n");
 		goto fail;
+	}
 
 	/* Setup IOMMU.. eventually we will (I think) do this once per context
 	 * and have separate page tables per context.  For now, to keep things
@@ -610,12 +658,14 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 	}
 
 	if (!iommu) {
+		dev_err(gpu->dev, "Failed to allocate GPU IOMMU domain\n");
 		ret = -ENOMEM;
 		goto fail;
 	}
 
 	gpu->mmu = etnaviv_iommu_new(gpu, iommu, version);
 	if (!gpu->mmu) {
+		dev_err(gpu->dev, "Failed to instantiate GPU IOMMU\n");
 		iommu_domain_free(iommu);
 		ret = -ENOMEM;
 		goto fail;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index f5321e2f25ff..a69cdd526bf8 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -125,7 +125,7 @@ struct etnaviv_gpu {
 	u32 completed_fence;
 	u32 retired_fence;
 	wait_queue_head_t fence_event;
-	unsigned int fence_context;
+	u64 fence_context;
 	spinlock_t fence_spinlock;
 
 	/* worker for handling active-list retiring: */
diff --git a/drivers/gpu/drm/etnaviv/state_hi.xml.h b/drivers/gpu/drm/etnaviv/state_hi.xml.h
index 6a7de5f1454a..807a3d9e0dd5 100644
--- a/drivers/gpu/drm/etnaviv/state_hi.xml.h
+++ b/drivers/gpu/drm/etnaviv/state_hi.xml.h
@@ -218,6 +218,13 @@ Copyright (C) 2015
 #define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_FE	0x00000001
 #define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_DE	0x00000002
 #define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_PE	0x00000004
+#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_SH	0x00000008
+#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_PA	0x00000010
+#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_SE	0x00000020
+#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA	0x00000040
+#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX	0x00000080
+#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_EZ	0x00010000
+#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_HZ	0x00020000
 
 #define VIVS_PM_MODULE_STATUS					0x00000108
 #define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_FE		0x00000001
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index d814b3048ee5..83f61c513b7e 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -2,10 +2,6 @@ config DRM_EXYNOS
 	tristate "DRM Support for Samsung SoC EXYNOS Series"
 	depends on OF && DRM && (ARCH_S3C64XX || ARCH_EXYNOS || ARCH_MULTIPLATFORM)
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
-	select FB_CFB_FILLRECT
-	select FB_CFB_COPYAREA
-	select FB_CFB_IMAGEBLIT
 	select VIDEOMODE_HELPERS
 	help
 	  Choose this option if you have a Samsung SoC EXYNOS chipset.
@@ -15,7 +11,7 @@ if DRM_EXYNOS
 
 config DRM_EXYNOS_IOMMU
 	bool
-	depends on EXYNOS_IOMMU && ARM_DMA_USE_IOMMU
+	depends on EXYNOS_IOMMU
 	default y
 
 comment "CRTCs"
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 4c1fb3f8b5a6..4f0850585b8e 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -67,10 +67,10 @@ static int exynos_dp_poweroff(struct analogix_dp_plat_data *plat_data)
 	return exynos_dp_crtc_clock_enable(plat_data, false);
 }
 
-static int exynos_dp_get_modes(struct analogix_dp_plat_data *plat_data)
+static int exynos_dp_get_modes(struct analogix_dp_plat_data *plat_data,
+			       struct drm_connector *connector)
 {
 	struct exynos_dp_device *dp = to_dp(plat_data);
-	struct drm_connector *connector = dp->connector;
 	struct drm_display_mode *mode;
 	int num_modes = 0;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
index 5e38e749ac17..ad6b73c7fc59 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
@@ -93,17 +93,8 @@ static int exynos_dpi_get_modes(struct drm_connector *connector)
 	return 0;
 }
 
-static struct drm_encoder *
-exynos_dpi_best_encoder(struct drm_connector *connector)
-{
-	struct exynos_dpi *ctx = connector_to_dpi(connector);
-
-	return &ctx->encoder;
-}
-
 static const struct drm_connector_helper_funcs exynos_dpi_connector_helper_funcs = {
 	.get_modes = exynos_dpi_get_modes,
-	.best_encoder = exynos_dpi_best_encoder,
 };
 
 static int exynos_dpi_create_connector(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 2dd820e23b0c..877d2efa28e2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -159,12 +159,7 @@ static int exynos_drm_load(struct drm_device *dev, unsigned long flags)
 	DRM_INFO("Exynos DRM: using %s device for DMA mapping operations\n",
 		 dev_name(private->dma_dev));
 
-	/*
-	 * create mapping to manage iommu table and set a pointer to iommu
-	 * mapping structure to iommu_mapping of private data.
-	 * also this iommu_mapping can be used to check if iommu is supported
-	 * or not.
-	 */
+	/* create common IOMMU mapping for all devices attached to Exynos DRM */
 	ret = drm_create_iommu_mapping(dev);
 	if (ret < 0) {
 		DRM_ERROR("failed to create iommu mapping.\n");
@@ -267,6 +262,8 @@ int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state,
 {
 	struct exynos_drm_private *priv = dev->dev_private;
 	struct exynos_atomic_commit *commit;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
 	int i, ret;
 
 	commit = kzalloc(sizeof(*commit), GFP_KERNEL);
@@ -288,10 +285,8 @@ int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state,
 	/* Wait until all affected CRTCs have completed previous commits and
 	 * mark them as pending.
 	 */
-	for (i = 0; i < dev->mode_config.num_crtc; ++i) {
-		if (state->crtcs[i])
-			commit->crtcs |= 1 << drm_crtc_index(state->crtcs[i]);
-	}
+	for_each_crtc_in_state(state, crtc, crtc_state, i)
+		commit->crtcs |= drm_crtc_mask(crtc);
 
 	wait_event(priv->wait, !commit_is_pending(priv, commit->crtcs));
 
@@ -299,7 +294,7 @@ int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state,
 	priv->pending |= commit->crtcs;
 	spin_unlock(&priv->lock);
 
-	drm_atomic_helper_swap_state(dev, state);
+	drm_atomic_helper_swap_state(state, true);
 
 	if (nonblock)
 		schedule_work(&commit->work);
@@ -407,7 +402,6 @@ static struct drm_driver exynos_drm_driver = {
 	.preclose		= exynos_drm_preclose,
 	.lastclose		= exynos_drm_lastclose,
 	.postclose		= exynos_drm_postclose,
-	.set_busid		= drm_platform_set_busid,
 	.get_vblank_counter	= drm_vblank_no_hw_counter,
 	.enable_vblank		= exynos_drm_crtc_enable_vblank,
 	.disable_vblank		= exynos_drm_crtc_disable_vblank,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index cc33ec9296e7..b39d521f093d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -224,8 +224,6 @@ struct exynos_drm_private {
 	struct drm_property *plane_zpos_property;
 
 	struct device *dma_dev;
-	unsigned long da_start;
-	unsigned long da_space_size;
 	void *mapping;
 
 	unsigned int pipe;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 601ecf8006a7..e07cb1fe4860 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1566,17 +1566,8 @@ static int exynos_dsi_get_modes(struct drm_connector *connector)
 	return 0;
 }
 
-static struct drm_encoder *
-exynos_dsi_best_encoder(struct drm_connector *connector)
-{
-	struct exynos_dsi *dsi = connector_to_dsi(connector);
-
-	return &dsi->encoder;
-}
-
 static const struct drm_connector_helper_funcs exynos_dsi_connector_helper_funcs = {
 	.get_modes = exynos_dsi_get_modes,
-	.best_encoder = exynos_dsi_best_encoder,
 };
 
 static int exynos_dsi_create_connector(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index 67dcd6831291..fb49443bfd32 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -269,8 +269,7 @@ static void exynos_drm_fbdev_destroy(struct drm_device *dev,
 	struct exynos_drm_gem *exynos_gem = exynos_fbd->exynos_gem;
 	struct drm_framebuffer *fb;
 
-	if (exynos_gem->kvaddr)
-		vunmap(exynos_gem->kvaddr);
+	vunmap(exynos_gem->kvaddr);
 
 	/* release drm framebuffer and real buffer */
 	if (fb_helper->fb && fb_helper->fb->funcs) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_iommu.c b/drivers/gpu/drm/exynos/exynos_drm_iommu.c
index 7ca09ee19656..0f373702414e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_iommu.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_iommu.c
@@ -14,13 +14,27 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/iommu.h>
-#include <linux/kref.h>
-
-#include <asm/dma-iommu.h>
 
 #include "exynos_drm_drv.h"
 #include "exynos_drm_iommu.h"
 
+static inline int configure_dma_max_seg_size(struct device *dev)
+{
+	if (!dev->dma_parms)
+		dev->dma_parms = kzalloc(sizeof(*dev->dma_parms), GFP_KERNEL);
+	if (!dev->dma_parms)
+		return -ENOMEM;
+
+	dma_set_max_seg_size(dev, DMA_BIT_MASK(32));
+	return 0;
+}
+
+static inline void clear_dma_max_seg_size(struct device *dev)
+{
+	kfree(dev->dma_parms);
+	dev->dma_parms = NULL;
+}
+
 /*
  * drm_create_iommu_mapping - create a mapping structure
  *
@@ -28,38 +42,22 @@
  */
 int drm_create_iommu_mapping(struct drm_device *drm_dev)
 {
-	struct dma_iommu_mapping *mapping = NULL;
 	struct exynos_drm_private *priv = drm_dev->dev_private;
 
-	if (!priv->da_start)
-		priv->da_start = EXYNOS_DEV_ADDR_START;
-	if (!priv->da_space_size)
-		priv->da_space_size = EXYNOS_DEV_ADDR_SIZE;
-
-	mapping = arm_iommu_create_mapping(&platform_bus_type, priv->da_start,
-						priv->da_space_size);
-
-	if (IS_ERR(mapping))
-		return PTR_ERR(mapping);
-
-	priv->mapping = mapping;
-
-	return 0;
+	return __exynos_iommu_create_mapping(priv, EXYNOS_DEV_ADDR_START,
+					     EXYNOS_DEV_ADDR_SIZE);
 }
 
 /*
  * drm_release_iommu_mapping - release iommu mapping structure
  *
  * @drm_dev: DRM device
- *
- * if mapping->kref becomes 0 then all things related to iommu mapping
- * will be released
  */
 void drm_release_iommu_mapping(struct drm_device *drm_dev)
 {
 	struct exynos_drm_private *priv = drm_dev->dev_private;
 
-	arm_iommu_release_mapping(priv->mapping);
+	__exynos_iommu_release_mapping(priv);
 }
 
 /*
@@ -77,25 +75,19 @@ int drm_iommu_attach_device(struct drm_device *drm_dev,
 	struct exynos_drm_private *priv = drm_dev->dev_private;
 	int ret;
 
-	if (!priv->mapping)
-		return 0;
-
-	subdrv_dev->dma_parms = devm_kzalloc(subdrv_dev,
-					sizeof(*subdrv_dev->dma_parms),
-					GFP_KERNEL);
-	if (!subdrv_dev->dma_parms)
-		return -ENOMEM;
-
-	dma_set_max_seg_size(subdrv_dev, 0xffffffffu);
-
-	if (subdrv_dev->archdata.mapping)
-		arm_iommu_detach_device(subdrv_dev);
+	if (get_dma_ops(priv->dma_dev) != get_dma_ops(subdrv_dev)) {
+		DRM_ERROR("Device %s lacks support for IOMMU\n",
+			  dev_name(subdrv_dev));
+		return -EINVAL;
+	}
 
-	ret = arm_iommu_attach_device(subdrv_dev, priv->mapping);
-	if (ret < 0) {
-		DRM_DEBUG_KMS("failed iommu attach.\n");
+	ret = configure_dma_max_seg_size(subdrv_dev);
+	if (ret)
 		return ret;
-	}
+
+	ret = __exynos_iommu_attach(priv, subdrv_dev);
+	if (ret)
+		clear_dma_max_seg_size(subdrv_dev);
 
 	return 0;
 }
@@ -113,10 +105,7 @@ void drm_iommu_detach_device(struct drm_device *drm_dev,
 				struct device *subdrv_dev)
 {
 	struct exynos_drm_private *priv = drm_dev->dev_private;
-	struct dma_iommu_mapping *mapping = priv->mapping;
-
-	if (!mapping || !mapping->domain)
-		return;
 
-	arm_iommu_detach_device(subdrv_dev);
+	__exynos_iommu_detach(priv, subdrv_dev);
+	clear_dma_max_seg_size(subdrv_dev);
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_iommu.h b/drivers/gpu/drm/exynos/exynos_drm_iommu.h
index 5ffebe02ee4d..c8de4913fdbe 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_iommu.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_iommu.h
@@ -17,6 +17,97 @@
 
 #ifdef CONFIG_DRM_EXYNOS_IOMMU
 
+#if defined(CONFIG_ARM_DMA_USE_IOMMU)
+#include <asm/dma-iommu.h>
+
+static inline int __exynos_iommu_create_mapping(struct exynos_drm_private *priv,
+					unsigned long start, unsigned long size)
+{
+	priv->mapping = arm_iommu_create_mapping(&platform_bus_type, start,
+						 size);
+	return IS_ERR(priv->mapping);
+}
+
+static inline void
+__exynos_iommu_release_mapping(struct exynos_drm_private *priv)
+{
+	arm_iommu_release_mapping(priv->mapping);
+}
+
+static inline int __exynos_iommu_attach(struct exynos_drm_private *priv,
+					struct device *dev)
+{
+	if (dev->archdata.mapping)
+		arm_iommu_detach_device(dev);
+
+	return arm_iommu_attach_device(dev, priv->mapping);
+}
+
+static inline void __exynos_iommu_detach(struct exynos_drm_private *priv,
+					 struct device *dev)
+{
+	arm_iommu_detach_device(dev);
+}
+
+#elif defined(CONFIG_IOMMU_DMA)
+#include <linux/dma-iommu.h>
+
+static inline int __exynos_iommu_create_mapping(struct exynos_drm_private *priv,
+					unsigned long start, unsigned long size)
+{
+	struct iommu_domain *domain;
+	int ret;
+
+	domain = iommu_domain_alloc(priv->dma_dev->bus);
+	if (!domain)
+		return -ENOMEM;
+
+	ret = iommu_get_dma_cookie(domain);
+	if (ret)
+		goto free_domain;
+
+	ret = iommu_dma_init_domain(domain, start, size);
+	if (ret)
+		goto put_cookie;
+
+	priv->mapping = domain;
+	return 0;
+
+put_cookie:
+	iommu_put_dma_cookie(domain);
+free_domain:
+	iommu_domain_free(domain);
+	return ret;
+}
+
+static inline void __exynos_iommu_release_mapping(struct exynos_drm_private *priv)
+{
+	struct iommu_domain *domain = priv->mapping;
+
+	iommu_put_dma_cookie(domain);
+	iommu_domain_free(domain);
+	priv->mapping = NULL;
+}
+
+static inline int __exynos_iommu_attach(struct exynos_drm_private *priv,
+					struct device *dev)
+{
+	struct iommu_domain *domain = priv->mapping;
+
+	return iommu_attach_device(domain, dev);
+}
+
+static inline void __exynos_iommu_detach(struct exynos_drm_private *priv,
+					 struct device *dev)
+{
+	struct iommu_domain *domain = priv->mapping;
+
+	iommu_detach_device(domain, dev);
+}
+#else
+#error Unsupported architecture and IOMMU/DMA-mapping glue code
+#endif
+
 int drm_create_iommu_mapping(struct drm_device *drm_dev);
 
 void drm_release_iommu_mapping(struct drm_device *drm_dev);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 608b0afa337f..e8f6c92b2a36 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -378,16 +378,8 @@ static int vidi_get_modes(struct drm_connector *connector)
 	return drm_add_edid_modes(connector, edid);
 }
 
-static struct drm_encoder *vidi_best_encoder(struct drm_connector *connector)
-{
-	struct vidi_context *ctx = ctx_from_connector(connector);
-
-	return &ctx->encoder;
-}
-
 static const struct drm_connector_helper_funcs vidi_connector_helper_funcs = {
 	.get_modes = vidi_get_modes,
-	.best_encoder = vidi_best_encoder,
 };
 
 static int vidi_create_connector(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 58de5a430508..2275efe41acd 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -937,17 +937,9 @@ static int hdmi_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-static struct drm_encoder *hdmi_best_encoder(struct drm_connector *connector)
-{
-	struct hdmi_context *hdata = connector_to_hdmi(connector);
-
-	return &hdata->encoder;
-}
-
 static const struct drm_connector_helper_funcs hdmi_connector_helper_funcs = {
 	.get_modes = hdmi_get_modes,
 	.mode_valid = hdmi_mode_valid,
-	.best_encoder = hdmi_best_encoder,
 };
 
 static int hdmi_create_connector(struct drm_encoder *encoder)
@@ -1828,6 +1820,7 @@ static int hdmi_probe(struct platform_device *pdev)
 		DRM_ERROR("Failed to find ddc node in device tree\n");
 		return -ENODEV;
 	}
+	of_node_put(dev->of_node);
 
 out_get_ddc_adpt:
 	hdata->ddc_adpt = of_find_i2c_adapter_by_node(ddc_node);
@@ -1846,6 +1839,7 @@ out_get_ddc_adpt:
 		ret = -ENODEV;
 		goto err_ddc;
 	}
+	of_node_put(dev->of_node);
 
 out_get_phy_port:
 	if (hdata->drv_data->is_apb_phy) {
diff --git a/drivers/gpu/drm/fsl-dcu/Kconfig b/drivers/gpu/drm/fsl-dcu/Kconfig
index b9c714de6e40..14a72c4c496d 100644
--- a/drivers/gpu/drm/fsl-dcu/Kconfig
+++ b/drivers/gpu/drm/fsl-dcu/Kconfig
@@ -5,12 +5,7 @@ config DRM_FSL_DCU
 	select BACKLIGHT_LCD_SUPPORT
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_PANEL
-	select FB_SYS_FILLRECT
-	select FB_SYS_COPYAREA
-	select FB_SYS_IMAGEBLIT
-	select FB_SYS_FOPS
 	select REGMAP_MMIO
 	select VIDEOMODE_HELPERS
 	help
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
index 89c0084c2814..3371635cd4d7 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
@@ -22,20 +22,21 @@
 #include "fsl_dcu_drm_drv.h"
 #include "fsl_dcu_drm_plane.h"
 
-static void fsl_dcu_drm_crtc_atomic_begin(struct drm_crtc *crtc,
+static void fsl_dcu_drm_crtc_atomic_flush(struct drm_crtc *crtc,
 					  struct drm_crtc_state *old_crtc_state)
 {
-}
+	struct drm_pending_vblank_event *event = crtc->state->event;
 
-static int fsl_dcu_drm_crtc_atomic_check(struct drm_crtc *crtc,
-					 struct drm_crtc_state *state)
-{
-	return 0;
-}
+	if (event) {
+		crtc->state->event = NULL;
 
-static void fsl_dcu_drm_crtc_atomic_flush(struct drm_crtc *crtc,
-					  struct drm_crtc_state *old_crtc_state)
-{
+		spin_lock_irq(&crtc->dev->event_lock);
+		if (drm_crtc_vblank_get(crtc) == 0)
+			drm_crtc_arm_vblank_event(crtc, event);
+		else
+			drm_crtc_send_vblank_event(crtc, event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
 }
 
 static void fsl_dcu_drm_disable_crtc(struct drm_crtc *crtc)
@@ -43,6 +44,8 @@ static void fsl_dcu_drm_disable_crtc(struct drm_crtc *crtc)
 	struct drm_device *dev = crtc->dev;
 	struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
 
+	drm_crtc_vblank_off(crtc);
+
 	regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE,
 			   DCU_MODE_DCU_MODE_MASK,
 			   DCU_MODE_DCU_MODE(DCU_MODE_OFF));
@@ -60,6 +63,8 @@ static void fsl_dcu_drm_crtc_enable(struct drm_crtc *crtc)
 			   DCU_MODE_DCU_MODE(DCU_MODE_NORMAL));
 	regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
 		     DCU_UPDATE_MODE_READREG);
+
+	drm_crtc_vblank_on(crtc);
 }
 
 static void fsl_dcu_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
@@ -117,8 +122,6 @@ static void fsl_dcu_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 }
 
 static const struct drm_crtc_helper_funcs fsl_dcu_drm_crtc_helper_funcs = {
-	.atomic_begin = fsl_dcu_drm_crtc_atomic_begin,
-	.atomic_check = fsl_dcu_drm_crtc_atomic_check,
 	.atomic_flush = fsl_dcu_drm_crtc_atomic_flush,
 	.disable = fsl_dcu_drm_disable_crtc,
 	.enable = fsl_dcu_drm_crtc_enable,
@@ -138,9 +141,10 @@ int fsl_dcu_drm_crtc_create(struct fsl_dcu_drm_device *fsl_dev)
 {
 	struct drm_plane *primary;
 	struct drm_crtc *crtc = &fsl_dev->crtc;
-	unsigned int i, j, reg_num;
 	int ret;
 
+	fsl_dcu_drm_init_planes(fsl_dev->drm);
+
 	primary = fsl_dcu_drm_primary_create_plane(fsl_dev->drm);
 	if (!primary)
 		return -ENOMEM;
@@ -154,19 +158,5 @@ int fsl_dcu_drm_crtc_create(struct fsl_dcu_drm_device *fsl_dev)
 
 	drm_crtc_helper_add(crtc, &fsl_dcu_drm_crtc_helper_funcs);
 
-	if (!strcmp(fsl_dev->soc->name, "ls1021a"))
-		reg_num = LS1021A_LAYER_REG_NUM;
-	else
-		reg_num = VF610_LAYER_REG_NUM;
-	for (i = 0; i < fsl_dev->soc->total_layer; i++) {
-		for (j = 1; j <= reg_num; j++)
-			regmap_write(fsl_dev->regmap, DCU_CTRLDESCLN(i, j), 0);
-	}
-	regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE,
-			   DCU_MODE_DCU_MODE_MASK,
-			   DCU_MODE_DCU_MODE(DCU_MODE_OFF));
-	regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
-		     DCU_UPDATE_MODE_READREG);
-
 	return 0;
 }
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
index dc723f7ead7d..7882387f9bff 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
@@ -11,6 +11,7 @@
 
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
+#include <linux/console.h>
 #include <linux/io.h>
 #include <linux/mfd/syscon.h>
 #include <linux/mm.h>
@@ -22,6 +23,7 @@
 #include <linux/regmap.h>
 
 #include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_cma_helper.h>
@@ -42,10 +44,8 @@ static const struct regmap_config fsl_dcu_regmap_config = {
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
-	.cache_type = REGCACHE_FLAT,
 
 	.volatile_reg = fsl_dcu_drm_is_volatile_reg,
-	.max_register = 0x11fc,
 };
 
 static int fsl_dcu_drm_irq_init(struct drm_device *dev)
@@ -199,7 +199,7 @@ static struct drm_driver fsl_dcu_drm_driver = {
 	.get_vblank_counter	= drm_vblank_no_hw_counter,
 	.enable_vblank		= fsl_dcu_drm_enable_vblank,
 	.disable_vblank		= fsl_dcu_drm_disable_vblank,
-	.gem_free_object	= drm_gem_cma_free_object,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops		= &drm_gem_cma_vm_ops,
 	.prime_handle_to_fd	= drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle	= drm_gem_prime_fd_to_handle,
@@ -229,11 +229,26 @@ static int fsl_dcu_drm_pm_suspend(struct device *dev)
 	if (!fsl_dev)
 		return 0;
 
+	disable_irq(fsl_dev->irq);
 	drm_kms_helper_poll_disable(fsl_dev->drm);
-	regcache_cache_only(fsl_dev->regmap, true);
-	regcache_mark_dirty(fsl_dev->regmap);
-	clk_disable(fsl_dev->clk);
-	clk_unprepare(fsl_dev->clk);
+
+	console_lock();
+	drm_fbdev_cma_set_suspend(fsl_dev->fbdev, 1);
+	console_unlock();
+
+	fsl_dev->state = drm_atomic_helper_suspend(fsl_dev->drm);
+	if (IS_ERR(fsl_dev->state)) {
+		console_lock();
+		drm_fbdev_cma_set_suspend(fsl_dev->fbdev, 0);
+		console_unlock();
+
+		drm_kms_helper_poll_enable(fsl_dev->drm);
+		enable_irq(fsl_dev->irq);
+		return PTR_ERR(fsl_dev->state);
+	}
+
+	clk_disable_unprepare(fsl_dev->pix_clk);
+	clk_disable_unprepare(fsl_dev->clk);
 
 	return 0;
 }
@@ -246,21 +261,27 @@ static int fsl_dcu_drm_pm_resume(struct device *dev)
 	if (!fsl_dev)
 		return 0;
 
-	ret = clk_enable(fsl_dev->clk);
+	ret = clk_prepare_enable(fsl_dev->clk);
 	if (ret < 0) {
 		dev_err(dev, "failed to enable dcu clk\n");
-		clk_unprepare(fsl_dev->clk);
 		return ret;
 	}
-	ret = clk_prepare(fsl_dev->clk);
+
+	ret = clk_prepare_enable(fsl_dev->pix_clk);
 	if (ret < 0) {
-		dev_err(dev, "failed to prepare dcu clk\n");
+		dev_err(dev, "failed to enable pix clk\n");
 		return ret;
 	}
 
+	fsl_dcu_drm_init_planes(fsl_dev->drm);
+	drm_atomic_helper_resume(fsl_dev->drm, fsl_dev->state);
+
+	console_lock();
+	drm_fbdev_cma_set_suspend(fsl_dev->fbdev, 0);
+	console_unlock();
+
 	drm_kms_helper_poll_enable(fsl_dev->drm);
-	regcache_cache_only(fsl_dev->regmap, false);
-	regcache_sync(fsl_dev->regmap);
+	enable_irq(fsl_dev->irq);
 
 	return 0;
 }
@@ -274,12 +295,14 @@ static const struct fsl_dcu_soc_data fsl_dcu_ls1021a_data = {
 	.name = "ls1021a",
 	.total_layer = 16,
 	.max_layer = 4,
+	.layer_regs = LS1021A_LAYER_REG_NUM,
 };
 
 static const struct fsl_dcu_soc_data fsl_dcu_vf610_data = {
 	.name = "vf610",
 	.total_layer = 64,
 	.max_layer = 6,
+	.layer_regs = VF610_LAYER_REG_NUM,
 };
 
 static const struct of_device_id fsl_dcu_of_match[] = {
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.h b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.h
index c275f900ff23..3b371fe7491e 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.h
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.h
@@ -175,6 +175,7 @@ struct fsl_dcu_soc_data {
 	unsigned int total_layer;
 	/*max layer number DCU supported*/
 	unsigned int max_layer;
+	unsigned int layer_regs;
 };
 
 struct fsl_dcu_drm_device {
@@ -193,6 +194,7 @@ struct fsl_dcu_drm_device {
 	struct drm_encoder encoder;
 	struct fsl_dcu_drm_connector connector;
 	const struct fsl_dcu_soc_data *soc;
+	struct drm_atomic_state *state;
 };
 
 void fsl_dcu_fbdev_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_kms.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_kms.c
index c564ec612b59..d9d6cc1c8e39 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_kms.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_kms.c
@@ -37,23 +37,22 @@ int fsl_dcu_drm_modeset_init(struct fsl_dcu_drm_device *fsl_dev)
 
 	ret = fsl_dcu_drm_crtc_create(fsl_dev);
 	if (ret)
-		return ret;
+		goto err;
 
 	ret = fsl_dcu_drm_encoder_create(fsl_dev, &fsl_dev->crtc);
 	if (ret)
-		goto fail_encoder;
+		goto err;
 
-	ret = fsl_dcu_drm_connector_create(fsl_dev, &fsl_dev->encoder);
+	ret = fsl_dcu_create_outputs(fsl_dev);
 	if (ret)
-		goto fail_connector;
+		goto err;
 
 	drm_mode_config_reset(fsl_dev->drm);
 	drm_kms_helper_poll_init(fsl_dev->drm);
 
 	return 0;
-fail_encoder:
-	fsl_dev->crtc.funcs->destroy(&fsl_dev->crtc);
-fail_connector:
-	fsl_dev->encoder.funcs->destroy(&fsl_dev->encoder);
+
+err:
+	drm_mode_config_cleanup(fsl_dev->drm);
 	return ret;
 }
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_output.h b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_output.h
index 7093109fbc21..5a7b88e19e44 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_output.h
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_output.h
@@ -25,9 +25,8 @@ to_fsl_dcu_connector(struct drm_connector *con)
 		     : NULL;
 }
 
-int fsl_dcu_drm_connector_create(struct fsl_dcu_drm_device *fsl_dev,
-				 struct drm_encoder *encoder);
 int fsl_dcu_drm_encoder_create(struct fsl_dcu_drm_device *fsl_dev,
 			       struct drm_crtc *crtc);
+int fsl_dcu_create_outputs(struct fsl_dcu_drm_device *fsl_dev);
 
 #endif /* __FSL_DCU_DRM_CONNECTOR_H__ */
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
index 274558b3b32b..e50467a0deb0 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
@@ -217,6 +217,22 @@ static const u32 fsl_dcu_drm_plane_formats[] = {
 	DRM_FORMAT_YUV422,
 };
 
+void fsl_dcu_drm_init_planes(struct drm_device *dev)
+{
+	struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
+	int i, j;
+
+	for (i = 0; i < fsl_dev->soc->total_layer; i++) {
+		for (j = 1; j <= fsl_dev->soc->layer_regs; j++)
+			regmap_write(fsl_dev->regmap, DCU_CTRLDESCLN(i, j), 0);
+	}
+	regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE,
+			   DCU_MODE_DCU_MODE_MASK,
+			   DCU_MODE_DCU_MODE(DCU_MODE_OFF));
+	regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
+		     DCU_UPDATE_MODE_READREG);
+}
+
 struct drm_plane *fsl_dcu_drm_primary_create_plane(struct drm_device *dev)
 {
 	struct drm_plane *primary;
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.h b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.h
index d657f088d859..8ee45f813ee8 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.h
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.h
@@ -12,6 +12,7 @@
 #ifndef __FSL_DCU_DRM_PLANE_H__
 #define __FSL_DCU_DRM_PLANE_H__
 
+void fsl_dcu_drm_init_planes(struct drm_device *dev);
 struct drm_plane *fsl_dcu_drm_primary_create_plane(struct drm_device *dev);
 
 #endif /* __FSL_DCU_DRM_PLANE_H__ */
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
index 98c998da91eb..26edcc899712 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/backlight.h>
+#include <linux/of_graph.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_atomic_helper.h>
@@ -102,14 +103,6 @@ static const struct drm_connector_funcs fsl_dcu_drm_connector_funcs = {
 	.reset = drm_atomic_helper_connector_reset,
 };
 
-static struct drm_encoder *
-fsl_dcu_drm_connector_best_encoder(struct drm_connector *connector)
-{
-	struct fsl_dcu_drm_connector *fsl_con = to_fsl_dcu_connector(connector);
-
-	return fsl_con->encoder;
-}
-
 static int fsl_dcu_drm_connector_get_modes(struct drm_connector *connector)
 {
 	struct fsl_dcu_drm_connector *fsl_connector;
@@ -136,17 +129,16 @@ static int fsl_dcu_drm_connector_mode_valid(struct drm_connector *connector,
 }
 
 static const struct drm_connector_helper_funcs connector_helper_funcs = {
-	.best_encoder = fsl_dcu_drm_connector_best_encoder,
 	.get_modes = fsl_dcu_drm_connector_get_modes,
 	.mode_valid = fsl_dcu_drm_connector_mode_valid,
 };
 
-int fsl_dcu_drm_connector_create(struct fsl_dcu_drm_device *fsl_dev,
-				 struct drm_encoder *encoder)
+static int fsl_dcu_attach_panel(struct fsl_dcu_drm_device *fsl_dev,
+				 struct drm_panel *panel)
 {
+	struct drm_encoder *encoder = &fsl_dev->encoder;
 	struct drm_connector *connector = &fsl_dev->connector.base;
 	struct drm_mode_config *mode_config = &fsl_dev->drm->mode_config;
-	struct device_node *panel_node;
 	int ret;
 
 	fsl_dev->connector.encoder = encoder;
@@ -170,21 +162,7 @@ int fsl_dcu_drm_connector_create(struct fsl_dcu_drm_device *fsl_dev,
 				      mode_config->dpms_property,
 				      DRM_MODE_DPMS_OFF);
 
-	panel_node = of_parse_phandle(fsl_dev->np, "fsl,panel", 0);
-	if (!panel_node) {
-		dev_err(fsl_dev->dev, "fsl,panel property not found\n");
-		ret = -ENODEV;
-		goto err_sysfs;
-	}
-
-	fsl_dev->connector.panel = of_drm_find_panel(panel_node);
-	if (!fsl_dev->connector.panel) {
-		ret = -EPROBE_DEFER;
-		goto err_panel;
-	}
-	of_node_put(panel_node);
-
-	ret = drm_panel_attach(fsl_dev->connector.panel, connector);
+	ret = drm_panel_attach(panel, connector);
 	if (ret) {
 		dev_err(fsl_dev->dev, "failed to attach panel\n");
 		goto err_sysfs;
@@ -192,11 +170,62 @@ int fsl_dcu_drm_connector_create(struct fsl_dcu_drm_device *fsl_dev,
 
 	return 0;
 
-err_panel:
-	of_node_put(panel_node);
 err_sysfs:
 	drm_connector_unregister(connector);
 err_cleanup:
 	drm_connector_cleanup(connector);
 	return ret;
 }
+
+static int fsl_dcu_attach_endpoint(struct fsl_dcu_drm_device *fsl_dev,
+				   const struct of_endpoint *ep)
+{
+	struct drm_bridge *bridge;
+	struct device_node *np;
+
+	np = of_graph_get_remote_port_parent(ep->local_node);
+
+	fsl_dev->connector.panel = of_drm_find_panel(np);
+	if (fsl_dev->connector.panel) {
+		of_node_put(np);
+		return fsl_dcu_attach_panel(fsl_dev, fsl_dev->connector.panel);
+	}
+
+	bridge = of_drm_find_bridge(np);
+	of_node_put(np);
+	if (!bridge)
+		return -ENODEV;
+
+	fsl_dev->encoder.bridge = bridge;
+	bridge->encoder = &fsl_dev->encoder;
+
+	return drm_bridge_attach(fsl_dev->drm, bridge);
+}
+
+int fsl_dcu_create_outputs(struct fsl_dcu_drm_device *fsl_dev)
+{
+	struct of_endpoint ep;
+	struct device_node *ep_node, *panel_node;
+	int ret;
+
+	/* This is for backward compatibility */
+	panel_node = of_parse_phandle(fsl_dev->np, "fsl,panel", 0);
+	if (panel_node) {
+		fsl_dev->connector.panel = of_drm_find_panel(panel_node);
+		of_node_put(panel_node);
+		if (!fsl_dev->connector.panel)
+			return -EPROBE_DEFER;
+		return fsl_dcu_attach_panel(fsl_dev, fsl_dev->connector.panel);
+	}
+
+	ep_node = of_graph_get_next_endpoint(fsl_dev->np, NULL);
+	if (!ep_node)
+		return -ENODEV;
+
+	ret = of_graph_parse_endpoint(ep_node, &ep);
+	of_node_put(ep_node);
+	if (ret)
+		return -ENODEV;
+
+	return fsl_dcu_attach_endpoint(fsl_dev, &ep);
+}
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_tcon.c b/drivers/gpu/drm/fsl-dcu/fsl_tcon.c
index bbe34f1c0505..bca09ea24632 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_tcon.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_tcon.c
@@ -92,6 +92,7 @@ struct fsl_tcon *fsl_tcon_init(struct device *dev)
 		goto err_node_put;
 	}
 
+	of_node_put(np);
 	clk_prepare_enable(tcon->ipg_clk);
 
 	dev_info(dev, "Using TCON in bypass mode\n");
diff --git a/drivers/gpu/drm/gma500/Kconfig b/drivers/gpu/drm/gma500/Kconfig
index 17f928ec84ea..8906d67494fc 100644
--- a/drivers/gpu/drm/gma500/Kconfig
+++ b/drivers/gpu/drm/gma500/Kconfig
@@ -1,11 +1,7 @@
 config DRM_GMA500
 	tristate "Intel GMA5/600 KMS Framebuffer"
 	depends on DRM && PCI && X86
-	select FB_CFB_COPYAREA
-	select FB_CFB_FILLRECT
-	select FB_CFB_IMAGEBLIT
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_TTM
 	# GMA500 depends on ACPI_VIDEO when ACPI is enabled, just like i915
 	select ACPI_VIDEO if ACPI
diff --git a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
index 28f9d90988ff..563f193fcfac 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
@@ -246,8 +246,7 @@ static void cdv_hdmi_destroy(struct drm_connector *connector)
 {
 	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 
-	if (gma_encoder->i2c_bus)
-		psb_intel_i2c_destroy(gma_encoder->i2c_bus);
+	psb_intel_i2c_destroy(gma_encoder->i2c_bus);
 	drm_connector_unregister(connector);
 	drm_connector_cleanup(connector);
 	kfree(connector);
diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
index 813ef23a8054..38dc89083148 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
@@ -444,8 +444,7 @@ static void cdv_intel_lvds_destroy(struct drm_connector *connector)
 {
 	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 
-	if (gma_encoder->i2c_bus)
-		psb_intel_i2c_destroy(gma_encoder->i2c_bus);
+	psb_intel_i2c_destroy(gma_encoder->i2c_bus);
 	drm_connector_unregister(connector);
 	drm_connector_cleanup(connector);
 	kfree(connector);
@@ -780,12 +779,10 @@ out:
 failed_find:
 	mutex_unlock(&dev->mode_config.mutex);
 	printk(KERN_ERR "Failed find\n");
-	if (gma_encoder->ddc_bus)
-		psb_intel_i2c_destroy(gma_encoder->ddc_bus);
+	psb_intel_i2c_destroy(gma_encoder->ddc_bus);
 failed_ddc:
 	printk(KERN_ERR "Failed DDC\n");
-	if (gma_encoder->i2c_bus)
-		psb_intel_i2c_destroy(gma_encoder->i2c_bus);
+	psb_intel_i2c_destroy(gma_encoder->i2c_bus);
 failed_blc_i2c:
 	printk(KERN_ERR "Failed BLC\n");
 	drm_encoder_cleanup(encoder);
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index 7440bf90ac9c..0fcdce0817de 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -184,12 +184,6 @@ static int psbfb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 	return 0;
 }
 
-static int psbfb_ioctl(struct fb_info *info, unsigned int cmd,
-						unsigned long arg)
-{
-	return -ENOTTY;
-}
-
 static struct fb_ops psbfb_ops = {
 	.owner = THIS_MODULE,
 	.fb_check_var = drm_fb_helper_check_var,
@@ -201,7 +195,6 @@ static struct fb_ops psbfb_ops = {
 	.fb_imageblit = drm_fb_helper_cfb_imageblit,
 	.fb_mmap = psbfb_mmap,
 	.fb_sync = psbfb_sync,
-	.fb_ioctl = psbfb_ioctl,
 };
 
 static struct fb_ops psbfb_roll_ops = {
@@ -215,7 +208,6 @@ static struct fb_ops psbfb_roll_ops = {
 	.fb_imageblit = drm_fb_helper_cfb_imageblit,
 	.fb_pan_display = psbfb_pan,
 	.fb_mmap = psbfb_mmap,
-	.fb_ioctl = psbfb_ioctl,
 };
 
 static struct fb_ops psbfb_unaccel_ops = {
@@ -228,7 +220,6 @@ static struct fb_ops psbfb_unaccel_ops = {
 	.fb_copyarea = drm_fb_helper_cfb_copyarea,
 	.fb_imageblit = drm_fb_helper_cfb_imageblit,
 	.fb_mmap = psbfb_mmap,
-	.fb_ioctl = psbfb_ioctl,
 };
 
 /**
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index c95406e6f44d..1a1cf7a3b5ef 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -175,20 +175,21 @@ void gma_crtc_load_lut(struct drm_crtc *crtc)
 	}
 }
 
-void gma_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, u16 *blue,
-			u32 start, u32 size)
+int gma_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, u16 *blue,
+		       u32 size)
 {
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	int i;
-	int end = (start + size > 256) ? 256 : start + size;
 
-	for (i = start; i < end; i++) {
+	for (i = 0; i < size; i++) {
 		gma_crtc->lut_r[i] = red[i] >> 8;
 		gma_crtc->lut_g[i] = green[i] >> 8;
 		gma_crtc->lut_b[i] = blue[i] >> 8;
 	}
 
 	gma_crtc_load_lut(crtc);
+
+	return 0;
 }
 
 /**
@@ -281,7 +282,7 @@ void gma_crtc_dpms(struct drm_crtc *crtc, int mode)
 		REG_WRITE(VGACNTRL, VGA_DISP_DISABLE);
 
 		/* Turn off vblank interrupts */
-		drm_vblank_off(dev, pipe);
+		drm_crtc_vblank_off(crtc);
 
 		/* Wait for vblank for the disable to take effect */
 		gma_wait_for_vblank(dev);
diff --git a/drivers/gpu/drm/gma500/gma_display.h b/drivers/gpu/drm/gma500/gma_display.h
index b2491c65f053..e72dd08b701b 100644
--- a/drivers/gpu/drm/gma500/gma_display.h
+++ b/drivers/gpu/drm/gma500/gma_display.h
@@ -72,8 +72,8 @@ extern int gma_crtc_cursor_set(struct drm_crtc *crtc,
 			       uint32_t width, uint32_t height);
 extern int gma_crtc_cursor_move(struct drm_crtc *crtc, int x, int y);
 extern void gma_crtc_load_lut(struct drm_crtc *crtc);
-extern void gma_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-			       u16 *blue, u32 start, u32 size);
+extern int gma_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
+			      u16 *blue, u32 size);
 extern void gma_crtc_dpms(struct drm_crtc *crtc, int mode);
 extern void gma_crtc_prepare(struct drm_crtc *crtc);
 extern void gma_crtc_commit(struct drm_crtc *crtc);
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index 82b8ce418b27..50eb944fb78a 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -210,10 +210,8 @@ static int psb_driver_unload(struct drm_device *dev)
 			iounmap(dev_priv->aux_reg);
 			dev_priv->aux_reg = NULL;
 		}
-		if (dev_priv->aux_pdev)
-			pci_dev_put(dev_priv->aux_pdev);
-		if (dev_priv->lpc_pdev)
-			pci_dev_put(dev_priv->lpc_pdev);
+		pci_dev_put(dev_priv->aux_pdev);
+		pci_dev_put(dev_priv->lpc_pdev);
 
 		/* Destroy VBT data */
 		psb_intel_destroy_bios(dev);
diff --git a/drivers/gpu/drm/gma500/psb_intel_display.c b/drivers/gpu/drm/gma500/psb_intel_display.c
index 398015be87e4..7b6c84925098 100644
--- a/drivers/gpu/drm/gma500/psb_intel_display.c
+++ b/drivers/gpu/drm/gma500/psb_intel_display.c
@@ -491,7 +491,6 @@ void psb_intel_crtc_init(struct drm_device *dev, int pipe,
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct gma_crtc *gma_crtc;
 	int i;
-	uint16_t *r_base, *g_base, *b_base;
 
 	/* We allocate a extra array of drm_connector pointers
 	 * for fbdev after the crtc */
@@ -519,16 +518,10 @@ void psb_intel_crtc_init(struct drm_device *dev, int pipe,
 	gma_crtc->pipe = pipe;
 	gma_crtc->plane = pipe;
 
-	r_base = gma_crtc->base.gamma_store;
-	g_base = r_base + 256;
-	b_base = g_base + 256;
 	for (i = 0; i < 256; i++) {
 		gma_crtc->lut_r[i] = i;
 		gma_crtc->lut_g[i] = i;
 		gma_crtc->lut_b[i] = i;
-		r_base[i] = i << 8;
-		g_base[i] = i << 8;
-		b_base[i] = i << 8;
 
 		gma_crtc->lut_adj[i] = 0;
 	}
diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c
index b1b93317d054..e55733ca46d2 100644
--- a/drivers/gpu/drm/gma500/psb_intel_lvds.c
+++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c
@@ -561,8 +561,7 @@ void psb_intel_lvds_destroy(struct drm_connector *connector)
 	struct gma_encoder *gma_encoder = gma_attached_encoder(connector);
 	struct psb_intel_lvds_priv *lvds_priv = gma_encoder->dev_priv;
 
-	if (lvds_priv->ddc_bus)
-		psb_intel_i2c_destroy(lvds_priv->ddc_bus);
+	psb_intel_i2c_destroy(lvds_priv->ddc_bus);
 	drm_connector_unregister(connector);
 	drm_connector_cleanup(connector);
 	kfree(connector);
@@ -835,11 +834,9 @@ out:
 
 failed_find:
 	mutex_unlock(&dev->mode_config.mutex);
-	if (lvds_priv->ddc_bus)
-		psb_intel_i2c_destroy(lvds_priv->ddc_bus);
+	psb_intel_i2c_destroy(lvds_priv->ddc_bus);
 failed_ddc:
-	if (lvds_priv->i2c_bus)
-		psb_intel_i2c_destroy(lvds_priv->i2c_bus);
+	psb_intel_i2c_destroy(lvds_priv->i2c_bus);
 failed_blc_i2c:
 	drm_encoder_cleanup(encoder);
 	drm_connector_cleanup(connector);
diff --git a/drivers/gpu/drm/hisilicon/kirin/Kconfig b/drivers/gpu/drm/hisilicon/kirin/Kconfig
index ea0df6115f7e..499f64405dac 100644
--- a/drivers/gpu/drm/hisilicon/kirin/Kconfig
+++ b/drivers/gpu/drm/hisilicon/kirin/Kconfig
@@ -4,6 +4,7 @@ config DRM_HISI_KIRIN
 	select DRM_KMS_HELPER
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_CMA_HELPER
+	select HISI_KIRIN_DW_DSI
 	help
 	  Choose this option if you have a hisilicon Kirin chipsets(hi6220).
 	  If M is selected the module will be called kirin-drm.
diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
index fba6372d060e..c3707d47cd89 100644
--- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
+++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
@@ -487,6 +487,7 @@ static void ade_crtc_enable(struct drm_crtc *crtc)
 	ade_set_medianoc_qos(acrtc);
 	ade_display_enable(acrtc);
 	ade_dump_regs(ctx->base);
+	drm_crtc_vblank_on(crtc);
 	acrtc->enable = true;
 }
 
@@ -498,17 +499,11 @@ static void ade_crtc_disable(struct drm_crtc *crtc)
 	if (!acrtc->enable)
 		return;
 
+	drm_crtc_vblank_off(crtc);
 	ade_power_down(ctx);
 	acrtc->enable = false;
 }
 
-static int ade_crtc_atomic_check(struct drm_crtc *crtc,
-				 struct drm_crtc_state *state)
-{
-	/* do nothing */
-	return 0;
-}
-
 static void ade_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
 	struct ade_crtc *acrtc = to_ade_crtc(crtc);
@@ -537,6 +532,7 @@ static void ade_crtc_atomic_flush(struct drm_crtc *crtc,
 {
 	struct ade_crtc *acrtc = to_ade_crtc(crtc);
 	struct ade_hw_ctx *ctx = acrtc->ctx;
+	struct drm_pending_vblank_event *event = crtc->state->event;
 	void __iomem *base = ctx->base;
 
 	/* only crtc is enabled regs take effect */
@@ -545,12 +541,22 @@ static void ade_crtc_atomic_flush(struct drm_crtc *crtc,
 		/* flush ade registers */
 		writel(ADE_ENABLE, base + ADE_EN);
 	}
+
+	if (event) {
+		crtc->state->event = NULL;
+
+		spin_lock_irq(&crtc->dev->event_lock);
+		if (drm_crtc_vblank_get(crtc) == 0)
+			drm_crtc_arm_vblank_event(crtc, event);
+		else
+			drm_crtc_send_vblank_event(crtc, event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
 }
 
 static const struct drm_crtc_helper_funcs ade_crtc_helper_funcs = {
 	.enable		= ade_crtc_enable,
 	.disable	= ade_crtc_disable,
-	.atomic_check	= ade_crtc_atomic_check,
 	.mode_set_nofb	= ade_crtc_mode_set_nofb,
 	.atomic_begin	= ade_crtc_atomic_begin,
 	.atomic_flush	= ade_crtc_atomic_flush,
@@ -961,21 +967,21 @@ static int ade_dts_parse(struct platform_device *pdev, struct ade_hw_ctx *ctx)
 	}
 
 	ctx->ade_core_clk = devm_clk_get(dev, "clk_ade_core");
-	if (!ctx->ade_core_clk) {
+	if (IS_ERR(ctx->ade_core_clk)) {
 		DRM_ERROR("failed to parse clk ADE_CORE\n");
-		return -ENODEV;
+		return PTR_ERR(ctx->ade_core_clk);
 	}
 
 	ctx->media_noc_clk = devm_clk_get(dev, "clk_codec_jpeg");
-	if (!ctx->media_noc_clk) {
+	if (IS_ERR(ctx->media_noc_clk)) {
 		DRM_ERROR("failed to parse clk CODEC_JPEG\n");
-	    return -ENODEV;
+		return PTR_ERR(ctx->media_noc_clk);
 	}
 
 	ctx->ade_pix_clk = devm_clk_get(dev, "clk_ade_pix");
-	if (!ctx->ade_pix_clk) {
+	if (IS_ERR(ctx->ade_pix_clk)) {
 		DRM_ERROR("failed to parse clk ADE_PIX\n");
-	    return -ENODEV;
+		return PTR_ERR(ctx->ade_pix_clk);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c
index 3f94785fbcca..1edd9bc80294 100644
--- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c
@@ -171,9 +171,8 @@ static struct drm_driver kirin_drm_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME |
 				  DRIVER_ATOMIC | DRIVER_HAVE_IRQ,
 	.fops			= &kirin_drm_fops,
-	.set_busid		= drm_platform_set_busid,
 
-	.gem_free_object	= drm_gem_cma_free_object,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops		= &drm_gem_cma_vm_ops,
 	.dumb_create		= kirin_gem_cma_dumb_create,
 	.dumb_map_offset	= drm_gem_cma_dumb_map_offset,
@@ -221,19 +220,12 @@ static int kirin_drm_bind(struct device *dev)
 	if (ret)
 		goto err_kms_cleanup;
 
-	/* connectors should be registered after drm device register */
-	ret = drm_connector_register_all(drm_dev);
-	if (ret)
-		goto err_drm_dev_unregister;
-
 	DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n",
 		 driver->name, driver->major, driver->minor, driver->patchlevel,
 		 driver->date, drm_dev->primary->index);
 
 	return 0;
 
-err_drm_dev_unregister:
-	drm_dev_unregister(drm_dev);
 err_kms_cleanup:
 	kirin_drm_kms_cleanup(drm_dev);
 err_drm_dev_unref:
@@ -246,7 +238,6 @@ static void kirin_drm_unbind(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
-	drm_connector_unregister_all(drm_dev);
 	drm_dev_unregister(drm_dev);
 	kirin_drm_kms_cleanup(drm_dev);
 	drm_dev_unref(drm_dev);
diff --git a/drivers/gpu/drm/i2c/Kconfig b/drivers/gpu/drm/i2c/Kconfig
index 22c7ed63a001..4d341db462a2 100644
--- a/drivers/gpu/drm/i2c/Kconfig
+++ b/drivers/gpu/drm/i2c/Kconfig
@@ -1,12 +1,6 @@
 menu "I2C encoder or helper chips"
      depends on DRM && DRM_KMS_HELPER && I2C
 
-config DRM_I2C_ADV7511
-	tristate "AV7511 encoder"
-	select REGMAP_I2C
-	help
-	  Support for the Analog Device ADV7511(W) and ADV7513 HDMI encoders.
-
 config DRM_I2C_CH7006
 	tristate "Chrontel ch7006 TV encoder"
 	default m if DRM_NOUVEAU
diff --git a/drivers/gpu/drm/i2c/Makefile b/drivers/gpu/drm/i2c/Makefile
index 2c72eb584ab7..43aa33baebed 100644
--- a/drivers/gpu/drm/i2c/Makefile
+++ b/drivers/gpu/drm/i2c/Makefile
@@ -1,7 +1,5 @@
 ccflags-y := -Iinclude/drm
 
-obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511.o
-
 ch7006-y := ch7006_drv.o ch7006_mode.o
 obj-$(CONFIG_DRM_I2C_CH7006) += ch7006.o
 
diff --git a/drivers/gpu/drm/i2c/ch7006_drv.c b/drivers/gpu/drm/i2c/ch7006_drv.c
index 0594c45f7164..e9e8ae2ec06b 100644
--- a/drivers/gpu/drm/i2c/ch7006_drv.c
+++ b/drivers/gpu/drm/i2c/ch7006_drv.c
@@ -361,13 +361,8 @@ static int ch7006_encoder_set_property(struct drm_encoder *encoder,
 
 		/* Disable the crtc to ensure a full modeset is
 		 * performed whenever it's turned on again. */
-		if (crtc) {
-			struct drm_mode_set modeset = {
-				.crtc = crtc,
-			};
-
-			drm_mode_set_config_internal(&modeset);
-		}
+		if (crtc)
+			drm_crtc_force_disable(crtc);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 29a32b11953b..7769e469118f 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -57,6 +57,28 @@ config DRM_I915_USERPTR
 
 	  If in doubt, say "Y".
 
+config DRM_I915_GVT
+        bool "Enable Intel GVT-g graphics virtualization host support"
+        depends on DRM_I915
+        default n
+        help
+	  Choose this option if you want to enable Intel GVT-g graphics
+	  virtualization technology host support with integrated graphics.
+	  With GVT-g, it's possible to have one integrated graphics
+	  device shared by multiple VMs under different hypervisors.
+
+	  Note that at least one hypervisor like Xen or KVM is required for
+	  this driver to work, and it only supports newer device from
+	  Broadwell+. For further information and setup guide, you can
+	  visit: http://01.org/igvt-g.
+
+	  Now it's just a stub to support the modifications of i915 for
+	  GVT device model. It requires at least one MPT modules for Xen/KVM
+	  and other components of GVT device model to work. Use it under
+	  you own risk.
+
+	  If in doubt, say "N".
+
 menu "drm/i915 Debugging"
 depends on DRM_I915
 depends on EXPERT
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 8f404103341d..cee87bfd10c4 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -18,6 +18,9 @@ config DRM_I915_WERROR
 config DRM_I915_DEBUG
         bool "Enable additional driver debugging"
         depends on DRM_I915
+        select PREEMPT_COUNT
+        select X86_MSR # used by igt/pm_rpm
+        select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
         default n
         help
           Choose this option to turn on extra driver debugging that may affect
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 0b88ba0f3c1f..684fc1cd08fa 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -10,9 +10,11 @@ subdir-ccflags-$(CONFIG_DRM_I915_WERROR) := -Werror
 i915-y := i915_drv.o \
 	  i915_irq.o \
 	  i915_params.o \
+	  i915_pci.o \
           i915_suspend.o \
 	  i915_sysfs.o \
 	  intel_csr.o \
+	  intel_device_info.o \
 	  intel_pm.o \
 	  intel_runtime_pm.o
 
@@ -37,6 +39,7 @@ i915-y += i915_cmd_parser.o \
 	  i915_gem_userptr.o \
 	  i915_gpu_error.o \
 	  i915_trace_points.o \
+	  intel_breadcrumbs.o \
 	  intel_lrc.o \
 	  intel_mocs.o \
 	  intel_ringbuffer.o \
@@ -59,6 +62,7 @@ i915-y += intel_audio.o \
 	  intel_bios.o \
 	  intel_color.o \
 	  intel_display.o \
+	  intel_dpio_phy.o \
 	  intel_dpll_mgr.o \
 	  intel_fbc.o \
 	  intel_fifo_underrun.o \
@@ -81,10 +85,12 @@ i915-y += dvo_ch7017.o \
 	  dvo_tfp410.o \
 	  intel_crt.o \
 	  intel_ddi.o \
+	  intel_dp_aux_backlight.o \
 	  intel_dp_link_training.o \
 	  intel_dp_mst.o \
 	  intel_dp.o \
 	  intel_dsi.o \
+	  intel_dsi_dcs_backlight.o \
 	  intel_dsi_panel_vbt.o \
 	  intel_dsi_pll.o \
 	  intel_dvo.o \
@@ -98,8 +104,10 @@ i915-y += dvo_ch7017.o \
 # virtual gpu code
 i915-y += i915_vgpu.o
 
-# legacy horrors
-i915-y += i915_dma.o
+ifeq ($(CONFIG_DRM_I915_GVT),y)
+i915-y += intel_gvt.o
+include $(src)/gvt/Makefile
+endif
 
 obj-$(CONFIG_DRM_I915)  += i915.o
 
diff --git a/drivers/gpu/drm/i915/gvt/Makefile b/drivers/gpu/drm/i915/gvt/Makefile
new file mode 100644
index 000000000000..d0f21a6ad60d
--- /dev/null
+++ b/drivers/gpu/drm/i915/gvt/Makefile
@@ -0,0 +1,5 @@
+GVT_DIR := gvt
+GVT_SOURCE := gvt.o
+
+ccflags-y                      += -I$(src) -I$(src)/$(GVT_DIR) -Wall
+i915-y			       += $(addprefix $(GVT_DIR)/, $(GVT_SOURCE))
diff --git a/drivers/gpu/drm/i915/gvt/debug.h b/drivers/gpu/drm/i915/gvt/debug.h
new file mode 100644
index 000000000000..7ef412be665f
--- /dev/null
+++ b/drivers/gpu/drm/i915/gvt/debug.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright(c) 2011-2016 Intel Corporation. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __GVT_DEBUG_H__
+#define __GVT_DEBUG_H__
+
+#define gvt_dbg_core(fmt, args...) \
+	DRM_DEBUG_DRIVER("gvt: core: "fmt, ##args)
+
+/*
+ * Other GVT debug stuff will be introduced in the GVT device model patches.
+ */
+
+#endif
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
new file mode 100644
index 000000000000..927f4579f5b6
--- /dev/null
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -0,0 +1,145 @@
+/*
+ * Copyright(c) 2011-2016 Intel Corporation. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/types.h>
+#include <xen/xen.h>
+
+#include "i915_drv.h"
+
+struct intel_gvt_host intel_gvt_host;
+
+static const char * const supported_hypervisors[] = {
+	[INTEL_GVT_HYPERVISOR_XEN] = "XEN",
+	[INTEL_GVT_HYPERVISOR_KVM] = "KVM",
+};
+
+/**
+ * intel_gvt_init_host - Load MPT modules and detect if we're running in host
+ * @gvt: intel gvt device
+ *
+ * This function is called at the driver loading stage. If failed to find a
+ * loadable MPT module or detect currently we're running in a VM, then GVT-g
+ * will be disabled
+ *
+ * Returns:
+ * Zero on success, negative error code if failed.
+ *
+ */
+int intel_gvt_init_host(void)
+{
+	if (intel_gvt_host.initialized)
+		return 0;
+
+	/* Xen DOM U */
+	if (xen_domain() && !xen_initial_domain())
+		return -ENODEV;
+
+	/* Try to load MPT modules for hypervisors */
+	if (xen_initial_domain()) {
+		/* In Xen dom0 */
+		intel_gvt_host.mpt = try_then_request_module(
+				symbol_get(xengt_mpt), "xengt");
+		intel_gvt_host.hypervisor_type = INTEL_GVT_HYPERVISOR_XEN;
+	} else {
+		/* not in Xen. Try KVMGT */
+		intel_gvt_host.mpt = try_then_request_module(
+				symbol_get(kvmgt_mpt), "kvm");
+		intel_gvt_host.hypervisor_type = INTEL_GVT_HYPERVISOR_KVM;
+	}
+
+	/* Fail to load MPT modules - bail out */
+	if (!intel_gvt_host.mpt)
+		return -EINVAL;
+
+	/* Try to detect if we're running in host instead of VM. */
+	if (!intel_gvt_hypervisor_detect_host())
+		return -ENODEV;
+
+	gvt_dbg_core("Running with hypervisor %s in host mode\n",
+			supported_hypervisors[intel_gvt_host.hypervisor_type]);
+
+	intel_gvt_host.initialized = true;
+	return 0;
+}
+
+static void init_device_info(struct intel_gvt *gvt)
+{
+	if (IS_BROADWELL(gvt->dev_priv))
+		gvt->device_info.max_support_vgpus = 8;
+	/* This function will grow large in GVT device model patches. */
+}
+
+/**
+ * intel_gvt_clean_device - clean a GVT device
+ * @gvt: intel gvt device
+ *
+ * This function is called at the driver unloading stage, to free the
+ * resources owned by a GVT device.
+ *
+ */
+void intel_gvt_clean_device(struct drm_i915_private *dev_priv)
+{
+	struct intel_gvt *gvt = &dev_priv->gvt;
+
+	if (WARN_ON(!gvt->initialized))
+		return;
+
+	/* Other de-initialization of GVT components will be introduced. */
+
+	gvt->initialized = false;
+}
+
+/**
+ * intel_gvt_init_device - initialize a GVT device
+ * @dev_priv: drm i915 private data
+ *
+ * This function is called at the initialization stage, to initialize
+ * necessary GVT components.
+ *
+ * Returns:
+ * Zero on success, negative error code if failed.
+ *
+ */
+int intel_gvt_init_device(struct drm_i915_private *dev_priv)
+{
+	struct intel_gvt *gvt = &dev_priv->gvt;
+	/*
+	 * Cannot initialize GVT device without intel_gvt_host gets
+	 * initialized first.
+	 */
+	if (WARN_ON(!intel_gvt_host.initialized))
+		return -EINVAL;
+
+	if (WARN_ON(gvt->initialized))
+		return -EEXIST;
+
+	gvt_dbg_core("init gvt device\n");
+
+	init_device_info(gvt);
+	/*
+	 * Other initialization of GVT components will be introduce here.
+	 */
+	gvt_dbg_core("gvt device creation is done\n");
+	gvt->initialized = true;
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
new file mode 100644
index 000000000000..fb619a6e519d
--- /dev/null
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright(c) 2011-2016 Intel Corporation. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _GVT_H_
+#define _GVT_H_
+
+#include "debug.h"
+#include "hypercall.h"
+
+#define GVT_MAX_VGPU 8
+
+enum {
+	INTEL_GVT_HYPERVISOR_XEN = 0,
+	INTEL_GVT_HYPERVISOR_KVM,
+};
+
+struct intel_gvt_host {
+	bool initialized;
+	int hypervisor_type;
+	struct intel_gvt_mpt *mpt;
+};
+
+extern struct intel_gvt_host intel_gvt_host;
+
+/* Describe per-platform limitations. */
+struct intel_gvt_device_info {
+	u32 max_support_vgpus;
+	/* This data structure will grow bigger in GVT device model patches */
+};
+
+struct intel_vgpu {
+	struct intel_gvt *gvt;
+	int id;
+	unsigned long handle; /* vGPU handle used by hypervisor MPT modules */
+};
+
+struct intel_gvt {
+	struct mutex lock;
+	bool initialized;
+
+	struct drm_i915_private *dev_priv;
+	struct idr vgpu_idr;	/* vGPU IDR pool */
+
+	struct intel_gvt_device_info device_info;
+};
+
+#include "mpt.h"
+
+#endif
diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h
new file mode 100644
index 000000000000..254df8bf1f35
--- /dev/null
+++ b/drivers/gpu/drm/i915/gvt/hypercall.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright(c) 2011-2016 Intel Corporation. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _GVT_HYPERCALL_H_
+#define _GVT_HYPERCALL_H_
+
+/*
+ * Specific GVT-g MPT modules function collections. Currently GVT-g supports
+ * both Xen and KVM by providing dedicated hypervisor-related MPT modules.
+ */
+struct intel_gvt_mpt {
+	int (*detect_host)(void);
+};
+
+extern struct intel_gvt_mpt xengt_mpt;
+extern struct intel_gvt_mpt kvmgt_mpt;
+
+#endif /* _GVT_HYPERCALL_H_ */
diff --git a/drivers/gpu/drm/i915/gvt/mpt.h b/drivers/gpu/drm/i915/gvt/mpt.h
new file mode 100644
index 000000000000..03601e3ffa7c
--- /dev/null
+++ b/drivers/gpu/drm/i915/gvt/mpt.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright(c) 2011-2016 Intel Corporation. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _GVT_MPT_H_
+#define _GVT_MPT_H_
+
+/**
+ * DOC: Hypervisor Service APIs for GVT-g Core Logic
+ *
+ * This is the glue layer between specific hypervisor MPT modules and GVT-g core
+ * logic. Each kind of hypervisor MPT module provides a collection of function
+ * callbacks and will be attached to GVT host when the driver is loading.
+ * GVT-g core logic will call these APIs to request specific services from
+ * hypervisor.
+ */
+
+/**
+ * intel_gvt_hypervisor_detect_host - check if GVT-g is running within
+ * hypervisor host/privilged domain
+ *
+ * Returns:
+ * Zero on success, -ENODEV if current kernel is running inside a VM
+ */
+static inline int intel_gvt_hypervisor_detect_host(void)
+{
+	return intel_gvt_host.mpt->detect_host();
+}
+
+#endif /* _GVT_MPT_H_ */
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index a337f33bec5b..b0fd6a7b0603 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -215,7 +215,8 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
 	CMD(  MI_RS_CONTEXT,                    SMI,    F,  1,      S  ),
 	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   M  ),
 	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
-	CMD(  MI_LOAD_REGISTER_REG,             SMI,   !F,  0xFF,   R  ),
+	CMD(  MI_LOAD_REGISTER_REG,             SMI,   !F,  0xFF,   W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
 	CMD(  MI_RS_STORE_DATA_IMM,             SMI,   !F,  0xFF,   S  ),
 	CMD(  MI_LOAD_URB_MEM,                  SMI,   !F,  0xFF,   S  ),
 	CMD(  MI_STORE_URB_MEM,                 SMI,   !F,  0xFF,   S  ),
@@ -736,7 +737,7 @@ static void fini_hash_table(struct intel_engine_cs *engine)
 
 /**
  * i915_cmd_parser_init_ring() - set cmd parser related fields for a ringbuffer
- * @ring: the ringbuffer to initialize
+ * @engine: the engine to initialize
  *
  * Optionally initializes fields related to batch buffer command parsing in the
  * struct intel_engine_cs based on whether the platform requires software
@@ -750,12 +751,12 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 	int cmd_table_count;
 	int ret;
 
-	if (!IS_GEN7(engine->dev))
+	if (!IS_GEN7(engine->i915))
 		return 0;
 
 	switch (engine->id) {
 	case RCS:
-		if (IS_HASWELL(engine->dev)) {
+		if (IS_HASWELL(engine->i915)) {
 			cmd_tables = hsw_render_ring_cmds;
 			cmd_table_count =
 				ARRAY_SIZE(hsw_render_ring_cmds);
@@ -764,7 +765,7 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 			cmd_table_count = ARRAY_SIZE(gen7_render_cmds);
 		}
 
-		if (IS_HASWELL(engine->dev)) {
+		if (IS_HASWELL(engine->i915)) {
 			engine->reg_tables = hsw_render_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(hsw_render_reg_tables);
 		} else {
@@ -780,7 +781,7 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
 	case BCS:
-		if (IS_HASWELL(engine->dev)) {
+		if (IS_HASWELL(engine->i915)) {
 			cmd_tables = hsw_blt_ring_cmds;
 			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds);
 		} else {
@@ -788,7 +789,7 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 			cmd_table_count = ARRAY_SIZE(gen7_blt_cmds);
 		}
 
-		if (IS_HASWELL(engine->dev)) {
+		if (IS_HASWELL(engine->i915)) {
 			engine->reg_tables = hsw_blt_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables);
 		} else {
@@ -829,7 +830,7 @@ int i915_cmd_parser_init_ring(struct intel_engine_cs *engine)
 
 /**
  * i915_cmd_parser_fini_ring() - clean up cmd parser related fields
- * @ring: the ringbuffer to clean up
+ * @engine: the engine to clean up
  *
  * Releases any resources related to command parsing that may have been
  * initialized for the specified ring.
@@ -1023,7 +1024,7 @@ unpin_src:
 
 /**
  * i915_needs_cmd_parser() - should a given ring use software command parsing?
- * @ring: the ring in question
+ * @engine: the engine in question
  *
  * Only certain platforms require software batch buffer command parsing, and
  * only when enabled via module parameter.
@@ -1035,7 +1036,7 @@ bool i915_needs_cmd_parser(struct intel_engine_cs *engine)
 	if (!engine->needs_cmd_parser)
 		return false;
 
-	if (!USES_PPGTT(engine->dev))
+	if (!USES_PPGTT(engine->i915))
 		return false;
 
 	return (i915.enable_cmd_parser == 1);
@@ -1098,6 +1099,11 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 					return false;
 				}
 
+				if (desc->cmd.value == MI_LOAD_REGISTER_REG) {
+					DRM_DEBUG_DRIVER("CMD: Rejected LRR to OACONTROL\n");
+					return false;
+				}
+
 				if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1))
 					*oacontrol_set = (cmd[offset + 1] != 0);
 			}
@@ -1113,6 +1119,12 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 					return false;
 				}
 
+				if (desc->cmd.value == MI_LOAD_REGISTER_REG) {
+					DRM_DEBUG_DRIVER("CMD: Rejected LRR to masked register 0x%08X\n",
+							 reg_addr);
+					return false;
+				}
+
 				if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) &&
 				    (offset + 2 > length ||
 				     (cmd[offset + 1] & reg->mask) != reg->value)) {
@@ -1164,7 +1176,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 
 /**
  * i915_parse_cmds() - parse a submitted batch buffer for privilege violations
- * @ring: the ring on which the batch is to execute
+ * @engine: the engine on which the batch is to execute
  * @batch_obj: the batch buffer in question
  * @shadow_batch_obj: copy of the batch buffer in question
  * @batch_start_offset: byte offset in the batch at which execution starts
@@ -1269,14 +1281,28 @@ int i915_parse_cmds(struct intel_engine_cs *engine,
 
 /**
  * i915_cmd_parser_get_version() - get the cmd parser version number
+ * @dev_priv: i915 device private
  *
  * The cmd parser maintains a simple increasing integer version number suitable
  * for passing to userspace clients to determine what operations are permitted.
  *
  * Return: the current version number of the cmd parser
  */
-int i915_cmd_parser_get_version(void)
+int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 {
+	struct intel_engine_cs *engine;
+	bool active = false;
+
+	/* If the command parser is not enabled, report 0 - unsupported */
+	for_each_engine(engine, dev_priv) {
+		if (i915_needs_cmd_parser(engine)) {
+			active = true;
+			break;
+		}
+	}
+	if (!active)
+		return 0;
+
 	/*
 	 * Command parser version history
 	 *
@@ -1288,6 +1314,7 @@ int i915_cmd_parser_get_version(void)
 	 * 4. L3 atomic chicken bits of HSW_SCRATCH1 and HSW_ROW_CHICKEN3.
 	 * 5. GPGPU dispatch compute indirect registers.
 	 * 6. TIMESTAMP register and Haswell CS GPR registers
+	 * 7. Allow MI_LOAD_REGISTER_REG between whitelisted registers.
 	 */
-	return 6;
+	return 7;
 }
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 2a6e12956baf..844fea795bae 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -89,17 +89,17 @@ static int i915_capabilities(struct seq_file *m, void *data)
 	return 0;
 }
 
-static const char get_active_flag(struct drm_i915_gem_object *obj)
+static char get_active_flag(struct drm_i915_gem_object *obj)
 {
 	return obj->active ? '*' : ' ';
 }
 
-static const char get_pin_flag(struct drm_i915_gem_object *obj)
+static char get_pin_flag(struct drm_i915_gem_object *obj)
 {
 	return obj->pin_display ? 'p' : ' ';
 }
 
-static const char get_tiling_flag(struct drm_i915_gem_object *obj)
+static char get_tiling_flag(struct drm_i915_gem_object *obj)
 {
 	switch (obj->tiling_mode) {
 	default:
@@ -109,12 +109,12 @@ static const char get_tiling_flag(struct drm_i915_gem_object *obj)
 	}
 }
 
-static inline const char get_global_flag(struct drm_i915_gem_object *obj)
+static char get_global_flag(struct drm_i915_gem_object *obj)
 {
 	return i915_gem_obj_to_ggtt(obj) ? 'g' : ' ';
 }
 
-static inline const char get_pin_mapped_flag(struct drm_i915_gem_object *obj)
+static char get_pin_mapped_flag(struct drm_i915_gem_object *obj)
 {
 	return obj->mapping ? 'M' : ' ';
 }
@@ -199,13 +199,6 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (frontbuffer: 0x%03x)", obj->frontbuffer_bits);
 }
 
-static void describe_ctx(struct seq_file *m, struct intel_context *ctx)
-{
-	seq_putc(m, ctx->legacy_hw_ctx.initialized ? 'I' : 'i');
-	seq_putc(m, ctx->remap_slice ? 'R' : 'r');
-	seq_putc(m, ' ');
-}
-
 static int i915_gem_object_list_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
@@ -272,7 +265,7 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
 	u64 total_obj_size, total_gtt_size;
 	LIST_HEAD(stolen);
@@ -424,6 +417,42 @@ static void print_batch_pool_stats(struct seq_file *m,
 	print_file_stats(m, "[k]batch pool", stats);
 }
 
+static int per_file_ctx_stats(int id, void *ptr, void *data)
+{
+	struct i915_gem_context *ctx = ptr;
+	int n;
+
+	for (n = 0; n < ARRAY_SIZE(ctx->engine); n++) {
+		if (ctx->engine[n].state)
+			per_file_stats(0, ctx->engine[n].state, data);
+		if (ctx->engine[n].ringbuf)
+			per_file_stats(0, ctx->engine[n].ringbuf->obj, data);
+	}
+
+	return 0;
+}
+
+static void print_context_stats(struct seq_file *m,
+				struct drm_i915_private *dev_priv)
+{
+	struct file_stats stats;
+	struct drm_file *file;
+
+	memset(&stats, 0, sizeof(stats));
+
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	if (dev_priv->kernel_context)
+		per_file_ctx_stats(0, dev_priv->kernel_context, &stats);
+
+	list_for_each_entry(file, &dev_priv->drm.filelist, lhead) {
+		struct drm_i915_file_private *fpriv = file->driver_priv;
+		idr_for_each(&fpriv->context_idr, per_file_ctx_stats, &stats);
+	}
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
+	print_file_stats(m, "[k]contexts", stats);
+}
+
 #define count_vmas(list, member) do { \
 	list_for_each_entry(vma, list, member) { \
 		size += i915_gem_obj_total_ggtt_size(vma->obj); \
@@ -528,10 +557,10 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 
 	seq_putc(m, '\n');
 	print_batch_pool_stats(m, dev_priv);
-
 	mutex_unlock(&dev->struct_mutex);
 
 	mutex_lock(&dev->filelist_mutex);
+	print_context_stats(m, dev_priv);
 	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
 		struct file_stats stats;
 		struct task_struct *task;
@@ -562,7 +591,7 @@ static int i915_gem_gtt_info(struct seq_file *m, void *data)
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	uintptr_t list = (uintptr_t) node->info_ent->data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
 	u64 total_obj_size, total_gtt_size;
 	int count, ret;
@@ -596,7 +625,7 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc;
 	int ret;
 
@@ -607,18 +636,20 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 	for_each_intel_crtc(dev, crtc) {
 		const char pipe = pipe_name(crtc->pipe);
 		const char plane = plane_name(crtc->plane);
-		struct intel_unpin_work *work;
+		struct intel_flip_work *work;
 
 		spin_lock_irq(&dev->event_lock);
-		work = crtc->unpin_work;
+		work = crtc->flip_work;
 		if (work == NULL) {
 			seq_printf(m, "No flip due on pipe %c (plane %c)\n",
 				   pipe, plane);
 		} else {
+			u32 pending;
 			u32 addr;
 
-			if (atomic_read(&work->pending) < INTEL_FLIP_COMPLETE) {
-				seq_printf(m, "Flip queued on pipe %c (plane %c)\n",
+			pending = atomic_read(&work->pending);
+			if (pending) {
+				seq_printf(m, "Flip ioctl preparing on pipe %c (plane %c)\n",
 					   pipe, plane);
 			} else {
 				seq_printf(m, "Flip pending (waiting for vsync) on pipe %c (plane %c)\n",
@@ -631,18 +662,14 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 					   engine->name,
 					   i915_gem_request_get_seqno(work->flip_queued_req),
 					   dev_priv->next_seqno,
-					   engine->get_seqno(engine),
-					   i915_gem_request_completed(work->flip_queued_req, true));
+					   intel_engine_get_seqno(engine),
+					   i915_gem_request_completed(work->flip_queued_req));
 			} else
 				seq_printf(m, "Flip not associated with any ring\n");
 			seq_printf(m, "Flip queued on frame %d, (was ready on frame %d), now %d\n",
 				   work->flip_queued_vblank,
 				   work->flip_ready_vblank,
-				   drm_crtc_vblank_count(&crtc->base));
-			if (work->enable_stall_check)
-				seq_puts(m, "Stall check enabled, ");
-			else
-				seq_puts(m, "Stall check waiting for page flip ioctl, ");
+				   intel_crtc_get_vblank_counter(crtc));
 			seq_printf(m, "%d prepares\n", atomic_read(&work->pending));
 
 			if (INTEL_INFO(dev)->gen >= 4)
@@ -668,7 +695,7 @@ static int i915_gem_batch_pool_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
 	struct intel_engine_cs *engine;
 	int total = 0;
@@ -713,7 +740,7 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 	struct drm_i915_gem_request *req;
 	int ret, any;
@@ -761,17 +788,29 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 static void i915_ring_seqno_info(struct seq_file *m,
 				 struct intel_engine_cs *engine)
 {
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	struct rb_node *rb;
+
 	seq_printf(m, "Current sequence (%s): %x\n",
-		   engine->name, engine->get_seqno(engine));
-	seq_printf(m, "Current user interrupts (%s): %x\n",
-		   engine->name, READ_ONCE(engine->user_interrupts));
+		   engine->name, intel_engine_get_seqno(engine));
+	seq_printf(m, "Current user interrupts (%s): %lx\n",
+		   engine->name, READ_ONCE(engine->breadcrumbs.irq_wakeups));
+
+	spin_lock(&b->lock);
+	for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
+		struct intel_wait *w = container_of(rb, typeof(*w), node);
+
+		seq_printf(m, "Waiting (%s): %s [%d] on %x\n",
+			   engine->name, w->tsk->comm, w->tsk->pid, w->seqno);
+	}
+	spin_unlock(&b->lock);
 }
 
 static int i915_gem_seqno_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 	int ret;
 
@@ -794,7 +833,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 	int ret, i, pipe;
 
@@ -985,7 +1024,7 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i, ret;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -1013,7 +1052,7 @@ static int i915_hws_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 	const u32 *hws;
 	int i;
@@ -1124,7 +1163,7 @@ static int
 i915_next_seqno_get(void *data, u64 *val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -1161,7 +1200,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret = 0;
 
 	intel_runtime_pm_get(dev_priv);
@@ -1281,6 +1320,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		}
 		seq_printf(m, "PM IER=0x%08x IMR=0x%08x ISR=0x%08x IIR=0x%08x, MASK=0x%08x\n",
 			   pm_ier, pm_imr, pm_isr, pm_iir, pm_mask);
+		seq_printf(m, "pm_intr_keep: 0x%08x\n", dev_priv->rps.pm_intr_keep);
 		seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
 		seq_printf(m, "Render p-state ratio: %d\n",
 			   (gt_perf_status & (IS_GEN9(dev) ? 0x1ff00 : 0xff00)) >> 8);
@@ -1363,7 +1403,7 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 	u64 acthd[I915_NUM_ENGINES];
 	u32 seqno[I915_NUM_ENGINES];
@@ -1380,10 +1420,10 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 
 	for_each_engine_id(engine, dev_priv, id) {
 		acthd[id] = intel_ring_get_active_head(engine);
-		seqno[id] = engine->get_seqno(engine);
+		seqno[id] = intel_engine_get_seqno(engine);
 	}
 
-	i915_get_extra_instdone(dev, instdone);
+	i915_get_extra_instdone(dev_priv, instdone);
 
 	intel_runtime_pm_put(dev_priv);
 
@@ -1400,9 +1440,11 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 			   engine->hangcheck.seqno,
 			   seqno[id],
 			   engine->last_submitted_seqno);
-		seq_printf(m, "\tuser interrupts = %x [current %x]\n",
+		seq_printf(m, "\twaiters? %d\n",
+			   intel_engine_has_waiter(engine));
+		seq_printf(m, "\tuser interrupts = %lx [current %lx]\n",
 			   engine->hangcheck.user_interrupts,
-			   READ_ONCE(engine->user_interrupts));
+			   READ_ONCE(engine->breadcrumbs.irq_wakeups));
 		seq_printf(m, "\tACTHD = 0x%08llx [current 0x%08llx]\n",
 			   (long long)engine->hangcheck.acthd,
 			   (long long)acthd[id]);
@@ -1432,7 +1474,7 @@ static int ironlake_drpc_info(struct seq_file *m)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 rgvmodectl, rstdbyctl;
 	u16 crstandvid;
 	int ret;
@@ -1500,7 +1542,7 @@ static int i915_forcewake_domains(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_uncore_forcewake_domain *fw_domain;
 
 	spin_lock_irq(&dev_priv->uncore.lock);
@@ -1518,7 +1560,7 @@ static int vlv_drpc_info(struct seq_file *m)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 rpmodectl1, rcctl1, pw_status;
 
 	intel_runtime_pm_get(dev_priv);
@@ -1558,7 +1600,7 @@ static int gen6_drpc_info(struct seq_file *m)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 rpmodectl1, gt_core_status, rcctl1, rc6vids = 0;
 	unsigned forcewake_count;
 	int count = 0, ret;
@@ -1670,7 +1712,7 @@ static int i915_frontbuffer_tracking(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	seq_printf(m, "FB tracking busy bits: 0x%08x\n",
 		   dev_priv->fb_tracking.busy_bits);
@@ -1685,7 +1727,7 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!HAS_FBC(dev)) {
 		seq_puts(m, "FBC unsupported on this chipset\n");
@@ -1715,7 +1757,7 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 static int i915_fbc_fc_get(void *data, u64 *val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (INTEL_INFO(dev)->gen < 7 || !HAS_FBC(dev))
 		return -ENODEV;
@@ -1728,7 +1770,7 @@ static int i915_fbc_fc_get(void *data, u64 *val)
 static int i915_fbc_fc_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 reg;
 
 	if (INTEL_INFO(dev)->gen < 7 || !HAS_FBC(dev))
@@ -1755,7 +1797,7 @@ static int i915_ips_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!HAS_IPS(dev)) {
 		seq_puts(m, "not supported\n");
@@ -1785,7 +1827,7 @@ static int i915_sr_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	bool sr_enabled = false;
 
 	intel_runtime_pm_get(dev_priv);
@@ -1814,7 +1856,7 @@ static int i915_emon_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned long temp, chipset, gfx;
 	int ret;
 
@@ -1842,7 +1884,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret = 0;
 	int gpu_freq, ia_freq;
 	unsigned int max_gpu_freq, min_gpu_freq;
@@ -1897,7 +1939,7 @@ static int i915_opregion(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_opregion *opregion = &dev_priv->opregion;
 	int ret;
 
@@ -1918,7 +1960,7 @@ static int i915_vbt(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_opregion *opregion = &dev_priv->opregion;
 
 	if (opregion->vbt)
@@ -1940,19 +1982,19 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 		return ret;
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
-       if (to_i915(dev)->fbdev) {
-               fbdev_fb = to_intel_framebuffer(to_i915(dev)->fbdev->helper.fb);
-
-               seq_printf(m, "fbcon size: %d x %d, depth %d, %d bpp, modifier 0x%llx, refcount %d, obj ",
-                         fbdev_fb->base.width,
-                         fbdev_fb->base.height,
-                         fbdev_fb->base.depth,
-                         fbdev_fb->base.bits_per_pixel,
-                         fbdev_fb->base.modifier[0],
-                         drm_framebuffer_read_refcount(&fbdev_fb->base));
-               describe_obj(m, fbdev_fb->obj);
-               seq_putc(m, '\n');
-       }
+	if (to_i915(dev)->fbdev) {
+		fbdev_fb = to_intel_framebuffer(to_i915(dev)->fbdev->helper.fb);
+
+		seq_printf(m, "fbcon size: %d x %d, depth %d, %d bpp, modifier 0x%llx, refcount %d, obj ",
+			   fbdev_fb->base.width,
+			   fbdev_fb->base.height,
+			   fbdev_fb->base.depth,
+			   fbdev_fb->base.bits_per_pixel,
+			   fbdev_fb->base.modifier[0],
+			   drm_framebuffer_read_refcount(&fbdev_fb->base));
+		describe_obj(m, fbdev_fb->obj);
+		seq_putc(m, '\n');
+	}
 #endif
 
 	mutex_lock(&dev->mode_config.fb_lock);
@@ -1989,10 +2031,9 @@ static int i915_context_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
-	struct intel_context *ctx;
-	enum intel_engine_id id;
+	struct i915_gem_context *ctx;
 	int ret;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -2000,32 +2041,36 @@ static int i915_context_status(struct seq_file *m, void *unused)
 		return ret;
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
-		if (!i915.enable_execlists &&
-		    ctx->legacy_hw_ctx.rcs_state == NULL)
-			continue;
-
-		seq_puts(m, "HW context ");
-		describe_ctx(m, ctx);
-		if (ctx == dev_priv->kernel_context)
-			seq_printf(m, "(kernel context) ");
+		seq_printf(m, "HW context %u ", ctx->hw_id);
+		if (IS_ERR(ctx->file_priv)) {
+			seq_puts(m, "(deleted) ");
+		} else if (ctx->file_priv) {
+			struct pid *pid = ctx->file_priv->file->pid;
+			struct task_struct *task;
 
-		if (i915.enable_execlists) {
-			seq_putc(m, '\n');
-			for_each_engine_id(engine, dev_priv, id) {
-				struct drm_i915_gem_object *ctx_obj =
-					ctx->engine[id].state;
-				struct intel_ringbuffer *ringbuf =
-					ctx->engine[id].ringbuf;
-
-				seq_printf(m, "%s: ", engine->name);
-				if (ctx_obj)
-					describe_obj(m, ctx_obj);
-				if (ringbuf)
-					describe_ctx_ringbuf(m, ringbuf);
-				seq_putc(m, '\n');
+			task = get_pid_task(pid, PIDTYPE_PID);
+			if (task) {
+				seq_printf(m, "(%s [%d]) ",
+					   task->comm, task->pid);
+				put_task_struct(task);
 			}
 		} else {
-			describe_obj(m, ctx->legacy_hw_ctx.rcs_state);
+			seq_puts(m, "(kernel) ");
+		}
+
+		seq_putc(m, ctx->remap_slice ? 'R' : 'r');
+		seq_putc(m, '\n');
+
+		for_each_engine(engine, dev_priv) {
+			struct intel_context *ce = &ctx->engine[engine->id];
+
+			seq_printf(m, "%s: ", engine->name);
+			seq_putc(m, ce->initialised ? 'I' : 'i');
+			if (ce->state)
+				describe_obj(m, ce->state);
+			if (ce->ringbuf)
+				describe_ctx_ringbuf(m, ce->ringbuf);
+			seq_putc(m, '\n');
 		}
 
 		seq_putc(m, '\n');
@@ -2037,24 +2082,22 @@ static int i915_context_status(struct seq_file *m, void *unused)
 }
 
 static void i915_dump_lrc_obj(struct seq_file *m,
-			      struct intel_context *ctx,
+			      struct i915_gem_context *ctx,
 			      struct intel_engine_cs *engine)
 {
+	struct drm_i915_gem_object *ctx_obj = ctx->engine[engine->id].state;
 	struct page *page;
 	uint32_t *reg_state;
 	int j;
-	struct drm_i915_gem_object *ctx_obj = ctx->engine[engine->id].state;
 	unsigned long ggtt_offset = 0;
 
+	seq_printf(m, "CONTEXT: %s %u\n", engine->name, ctx->hw_id);
+
 	if (ctx_obj == NULL) {
-		seq_printf(m, "Context on %s with no gem object\n",
-			   engine->name);
+		seq_puts(m, "\tNot allocated\n");
 		return;
 	}
 
-	seq_printf(m, "CONTEXT: %s %u\n", engine->name,
-		   intel_execlists_ctx_id(ctx, engine));
-
 	if (!i915_gem_obj_ggtt_bound(ctx_obj))
 		seq_puts(m, "\tNot bound in GGTT\n");
 	else
@@ -2085,9 +2128,9 @@ static int i915_dump_lrc(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
-	struct intel_context *ctx;
+	struct i915_gem_context *ctx;
 	int ret;
 
 	if (!i915.enable_execlists) {
@@ -2100,10 +2143,8 @@ static int i915_dump_lrc(struct seq_file *m, void *unused)
 		return ret;
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link)
-		if (ctx != dev_priv->kernel_context) {
-			for_each_engine(engine, dev_priv)
-				i915_dump_lrc_obj(m, ctx, engine);
-		}
+		for_each_engine(engine, dev_priv)
+			i915_dump_lrc_obj(m, ctx, engine);
 
 	mutex_unlock(&dev->struct_mutex);
 
@@ -2114,7 +2155,7 @@ static int i915_execlists(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 	u32 status_pointer;
 	u8 read_pointer;
@@ -2174,8 +2215,8 @@ static int i915_execlists(struct seq_file *m, void *data)
 
 		seq_printf(m, "\t%d requests in queue\n", count);
 		if (head_req) {
-			seq_printf(m, "\tHead request id: %u\n",
-				   intel_execlists_ctx_id(head_req->ctx, engine));
+			seq_printf(m, "\tHead request context: %u\n",
+				   head_req->ctx->hw_id);
 			seq_printf(m, "\tHead request tail: %u\n",
 				   head_req->tail);
 		}
@@ -2217,7 +2258,7 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -2269,7 +2310,7 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
 
 static int per_file_ctx(int id, void *ptr, void *data)
 {
-	struct intel_context *ctx = ptr;
+	struct i915_gem_context *ctx = ptr;
 	struct seq_file *m = data;
 	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;
 
@@ -2290,7 +2331,7 @@ static int per_file_ctx(int id, void *ptr, void *data)
 
 static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
 	int i;
@@ -2311,15 +2352,15 @@ static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 
 static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 
-	if (INTEL_INFO(dev)->gen == 6)
+	if (IS_GEN6(dev_priv))
 		seq_printf(m, "GFX_MODE: 0x%08x\n", I915_READ(GFX_MODE));
 
 	for_each_engine(engine, dev_priv) {
 		seq_printf(m, "%s\n", engine->name);
-		if (INTEL_INFO(dev)->gen == 7)
+		if (IS_GEN7(dev_priv))
 			seq_printf(m, "GFX_MODE: 0x%08x\n",
 				   I915_READ(RING_MODE_GEN7(engine)));
 		seq_printf(m, "PP_DIR_BASE: 0x%08x\n",
@@ -2345,7 +2386,7 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_file *file;
 
 	int ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -2388,7 +2429,7 @@ static int count_irq_waiters(struct drm_i915_private *i915)
 	int count = 0;
 
 	for_each_engine(engine, i915)
-		count += engine->irq_refcount;
+		count += intel_engine_has_waiter(engine);
 
 	return count;
 }
@@ -2397,11 +2438,12 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_file *file;
 
 	seq_printf(m, "RPS enabled? %d\n", dev_priv->rps.enabled);
-	seq_printf(m, "GPU busy? %d\n", dev_priv->mm.busy);
+	seq_printf(m, "GPU busy? %s [%x]\n",
+		   yesno(dev_priv->gt.awake), dev_priv->gt.active_engines);
 	seq_printf(m, "CPU waiting? %d\n", count_irq_waiters(dev_priv));
 	seq_printf(m, "Frequency requested %d; min hard:%d, soft:%d; max soft:%d, hard:%d\n",
 		   intel_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
@@ -2442,7 +2484,7 @@ static int i915_llc(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	const bool edram = INTEL_GEN(dev_priv) > 8;
 
 	seq_printf(m, "LLC: %s\n", yesno(HAS_LLC(dev)));
@@ -2455,7 +2497,7 @@ static int i915_llc(struct seq_file *m, void *data)
 static int i915_guc_load_status_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
-	struct drm_i915_private *dev_priv = node->minor->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(node->minor->dev);
 	struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
 	u32 tmp, i;
 
@@ -2510,15 +2552,16 @@ static void i915_guc_client_info(struct seq_file *m,
 	seq_printf(m, "\tWQ size %d, offset: 0x%x, tail %d\n",
 		client->wq_size, client->wq_offset, client->wq_tail);
 
+	seq_printf(m, "\tWork queue full: %u\n", client->no_wq_space);
 	seq_printf(m, "\tFailed to queue: %u\n", client->q_fail);
 	seq_printf(m, "\tFailed doorbell: %u\n", client->b_fail);
 	seq_printf(m, "\tLast submission result: %d\n", client->retcode);
 
 	for_each_engine(engine, dev_priv) {
 		seq_printf(m, "\tSubmissions: %llu %s\n",
-				client->submissions[engine->guc_id],
+				client->submissions[engine->id],
 				engine->name);
-		tot += client->submissions[engine->guc_id];
+		tot += client->submissions[engine->id];
 	}
 	seq_printf(m, "\tTotal: %llu\n", tot);
 }
@@ -2527,7 +2570,7 @@ static int i915_guc_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_guc guc;
 	struct i915_guc_client client = {};
 	struct intel_engine_cs *engine;
@@ -2546,6 +2589,10 @@ static int i915_guc_info(struct seq_file *m, void *data)
 
 	mutex_unlock(&dev->struct_mutex);
 
+	seq_printf(m, "Doorbell map:\n");
+	seq_printf(m, "\t%*pb\n", GUC_MAX_DOORBELLS, guc.doorbell_bitmap);
+	seq_printf(m, "Doorbell next cacheline: 0x%x\n\n", guc.db_cacheline);
+
 	seq_printf(m, "GuC total action count: %llu\n", guc.action_count);
 	seq_printf(m, "GuC action failure count: %u\n", guc.action_fail);
 	seq_printf(m, "GuC last action command: 0x%x\n", guc.action_cmd);
@@ -2555,9 +2602,9 @@ static int i915_guc_info(struct seq_file *m, void *data)
 	seq_printf(m, "\nGuC submissions:\n");
 	for_each_engine(engine, dev_priv) {
 		seq_printf(m, "\t%-24s: %10llu, last seqno 0x%08x\n",
-			engine->name, guc.submissions[engine->guc_id],
-			guc.last_seqno[engine->guc_id]);
-		total += guc.submissions[engine->guc_id];
+			engine->name, guc.submissions[engine->id],
+			guc.last_seqno[engine->id]);
+		total += guc.submissions[engine->id];
 	}
 	seq_printf(m, "\t%s: %llu\n", "Total", total);
 
@@ -2573,7 +2620,7 @@ static int i915_guc_log_dump(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *log_obj = dev_priv->guc.log_obj;
 	u32 *log;
 	int i = 0, pg;
@@ -2601,7 +2648,7 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 psrperf = 0;
 	u32 stat[3];
 	enum pipe pipe;
@@ -2669,7 +2716,6 @@ static int i915_sink_crc(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct intel_encoder *encoder;
 	struct intel_connector *connector;
 	struct intel_dp *intel_dp = NULL;
 	int ret;
@@ -2677,18 +2723,19 @@ static int i915_sink_crc(struct seq_file *m, void *data)
 
 	drm_modeset_lock_all(dev);
 	for_each_intel_connector(dev, connector) {
+		struct drm_crtc *crtc;
 
-		if (connector->base.dpms != DRM_MODE_DPMS_ON)
+		if (!connector->base.state->best_encoder)
 			continue;
 
-		if (!connector->base.encoder)
+		crtc = connector->base.state->crtc;
+		if (!crtc->state->active)
 			continue;
 
-		encoder = to_intel_encoder(connector->base.encoder);
-		if (encoder->type != INTEL_OUTPUT_EDP)
+		if (connector->base.connector_type != DRM_MODE_CONNECTOR_eDP)
 			continue;
 
-		intel_dp = enc_to_intel_dp(&encoder->base);
+		intel_dp = enc_to_intel_dp(connector->base.state->best_encoder);
 
 		ret = intel_dp_sink_crc(intel_dp, crc);
 		if (ret)
@@ -2709,7 +2756,7 @@ static int i915_energy_uJ(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u64 power;
 	u32 units;
 
@@ -2735,12 +2782,12 @@ static int i915_runtime_pm_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!HAS_RUNTIME_PM(dev_priv))
 		seq_puts(m, "Runtime power management not supported\n");
 
-	seq_printf(m, "GPU idle: %s\n", yesno(!dev_priv->mm.busy));
+	seq_printf(m, "GPU idle: %s\n", yesno(!dev_priv->gt.awake));
 	seq_printf(m, "IRQs disabled: %s\n",
 		   yesno(!intel_irqs_enabled(dev_priv)));
 #ifdef CONFIG_PM
@@ -2750,8 +2797,8 @@ static int i915_runtime_pm_status(struct seq_file *m, void *unused)
 	seq_printf(m, "Device Power Management (CONFIG_PM) disabled\n");
 #endif
 	seq_printf(m, "PCI device power state: %s [%d]\n",
-		   pci_power_name(dev_priv->dev->pdev->current_state),
-		   dev_priv->dev->pdev->current_state);
+		   pci_power_name(dev_priv->drm.pdev->current_state),
+		   dev_priv->drm.pdev->current_state);
 
 	return 0;
 }
@@ -2760,7 +2807,7 @@ static int i915_power_domain_info(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
 	int i;
 
@@ -2795,7 +2842,7 @@ static int i915_dmc_info(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_csr *csr;
 
 	if (!HAS_CSR(dev)) {
@@ -2918,7 +2965,7 @@ static void intel_dp_info(struct seq_file *m,
 
 	seq_printf(m, "\tDPCD rev: %x\n", intel_dp->dpcd[DP_DPCD_REV]);
 	seq_printf(m, "\taudio support: %s\n", yesno(intel_dp->has_audio));
-	if (intel_encoder->type == INTEL_OUTPUT_EDP)
+	if (intel_connector->base.connector_type == DRM_MODE_CONNECTOR_eDP)
 		intel_panel_info(m, &intel_connector->panel);
 }
 
@@ -2957,14 +3004,26 @@ static void intel_connector_info(struct seq_file *m,
 		seq_printf(m, "\tCEA rev: %d\n",
 			   connector->display_info.cea_rev);
 	}
-	if (intel_encoder) {
-		if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT ||
-		    intel_encoder->type == INTEL_OUTPUT_EDP)
-			intel_dp_info(m, intel_connector);
-		else if (intel_encoder->type == INTEL_OUTPUT_HDMI)
-			intel_hdmi_info(m, intel_connector);
-		else if (intel_encoder->type == INTEL_OUTPUT_LVDS)
+
+	if (!intel_encoder || intel_encoder->type == INTEL_OUTPUT_DP_MST)
+		return;
+
+	switch (connector->connector_type) {
+	case DRM_MODE_CONNECTOR_DisplayPort:
+	case DRM_MODE_CONNECTOR_eDP:
+		intel_dp_info(m, intel_connector);
+		break;
+	case DRM_MODE_CONNECTOR_LVDS:
+		if (intel_encoder->type == INTEL_OUTPUT_LVDS)
 			intel_lvds_info(m, intel_connector);
+		break;
+	case DRM_MODE_CONNECTOR_HDMIA:
+		if (intel_encoder->type == INTEL_OUTPUT_HDMI ||
+		    intel_encoder->type == INTEL_OUTPUT_UNKNOWN)
+			intel_hdmi_info(m, intel_connector);
+		break;
+	default:
+		break;
 	}
 
 	seq_printf(m, "\tmodes:\n");
@@ -2974,7 +3033,7 @@ static void intel_connector_info(struct seq_file *m,
 
 static bool cursor_active(struct drm_device *dev, int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 state;
 
 	if (IS_845G(dev) || IS_I865G(dev))
@@ -2987,7 +3046,7 @@ static bool cursor_active(struct drm_device *dev, int pipe)
 
 static bool cursor_position(struct drm_device *dev, int pipe, int *x, int *y)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 pos;
 
 	pos = I915_READ(CURPOS(pipe));
@@ -3108,7 +3167,7 @@ static int i915_display_info(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc;
 	struct drm_connector *connector;
 
@@ -3163,13 +3222,13 @@ static int i915_semaphore_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 	int num_rings = hweight32(INTEL_INFO(dev)->ring_mask);
 	enum intel_engine_id id;
 	int j, ret;
 
-	if (!i915_semaphore_is_enabled(dev)) {
+	if (!i915_semaphore_is_enabled(dev_priv)) {
 		seq_puts(m, "Semaphores are disabled\n");
 		return 0;
 	}
@@ -3236,7 +3295,7 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
 	drm_modeset_lock_all(dev);
@@ -3266,7 +3325,7 @@ static int i915_wa_registers(struct seq_file *m, void *unused)
 	struct intel_engine_cs *engine;
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_workarounds *workarounds = &dev_priv->workarounds;
 	enum intel_engine_id id;
 
@@ -3304,7 +3363,7 @@ static int i915_ddb_info(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct skl_ddb_allocation *ddb;
 	struct skl_ddb_entry *entry;
 	enum pipe pipe;
@@ -3342,31 +3401,16 @@ static int i915_ddb_info(struct seq_file *m, void *unused)
 static void drrs_status_per_crtc(struct seq_file *m,
 		struct drm_device *dev, struct intel_crtc *intel_crtc)
 {
-	struct intel_encoder *intel_encoder;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_drrs *drrs = &dev_priv->drrs;
 	int vrefresh = 0;
+	struct drm_connector *connector;
 
-	for_each_encoder_on_crtc(dev, &intel_crtc->base, intel_encoder) {
-		/* Encoder connected on this CRTC */
-		switch (intel_encoder->type) {
-		case INTEL_OUTPUT_EDP:
-			seq_puts(m, "eDP:\n");
-			break;
-		case INTEL_OUTPUT_DSI:
-			seq_puts(m, "DSI:\n");
-			break;
-		case INTEL_OUTPUT_HDMI:
-			seq_puts(m, "HDMI:\n");
-			break;
-		case INTEL_OUTPUT_DISPLAYPORT:
-			seq_puts(m, "DP:\n");
-			break;
-		default:
-			seq_printf(m, "Other encoder (id=%d).\n",
-						intel_encoder->type);
-			return;
-		}
+	drm_for_each_connector(connector, dev) {
+		if (connector->state->crtc != &intel_crtc->base)
+			continue;
+
+		seq_printf(m, "%s:\n", connector->name);
 	}
 
 	if (dev_priv->vbt.drrs_type == STATIC_DRRS_SUPPORT)
@@ -3429,18 +3473,16 @@ static int i915_drrs_status(struct seq_file *m, void *unused)
 	struct intel_crtc *intel_crtc;
 	int active_crtc_cnt = 0;
 
+	drm_modeset_lock_all(dev);
 	for_each_intel_crtc(dev, intel_crtc) {
-		drm_modeset_lock(&intel_crtc->base.mutex, NULL);
-
 		if (intel_crtc->base.state->active) {
 			active_crtc_cnt++;
 			seq_printf(m, "\nCRTC %d:  ", active_crtc_cnt);
 
 			drrs_status_per_crtc(m, dev, intel_crtc);
 		}
-
-		drm_modeset_unlock(&intel_crtc->base.mutex);
 	}
+	drm_modeset_unlock_all(dev);
 
 	if (!active_crtc_cnt)
 		seq_puts(m, "No active crtc found\n");
@@ -3458,17 +3500,23 @@ static int i915_dp_mst_info(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
-	struct drm_encoder *encoder;
 	struct intel_encoder *intel_encoder;
 	struct intel_digital_port *intel_dig_port;
+	struct drm_connector *connector;
+
 	drm_modeset_lock_all(dev);
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		intel_encoder = to_intel_encoder(encoder);
-		if (intel_encoder->type != INTEL_OUTPUT_DISPLAYPORT)
+	drm_for_each_connector(connector, dev) {
+		if (connector->connector_type != DRM_MODE_CONNECTOR_DisplayPort)
 			continue;
-		intel_dig_port = enc_to_dig_port(encoder);
+
+		intel_encoder = intel_attached_encoder(connector);
+		if (!intel_encoder || intel_encoder->type == INTEL_OUTPUT_DP_MST)
+			continue;
+
+		intel_dig_port = enc_to_dig_port(&intel_encoder->base);
 		if (!intel_dig_port->dp.can_mst)
 			continue;
+
 		seq_printf(m, "MST Source Port %c\n",
 			   port_name(intel_dig_port->port));
 		drm_dp_mst_dump_topology(m, &intel_dig_port->dp.mst_mgr);
@@ -3480,7 +3528,7 @@ static int i915_dp_mst_info(struct seq_file *m, void *unused)
 static int i915_pipe_crc_open(struct inode *inode, struct file *filep)
 {
 	struct pipe_crc_info *info = inode->i_private;
-	struct drm_i915_private *dev_priv = info->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(info->dev);
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
 
 	if (info->pipe >= INTEL_INFO(info->dev)->num_pipes)
@@ -3504,7 +3552,7 @@ static int i915_pipe_crc_open(struct inode *inode, struct file *filep)
 static int i915_pipe_crc_release(struct inode *inode, struct file *filep)
 {
 	struct pipe_crc_info *info = inode->i_private;
-	struct drm_i915_private *dev_priv = info->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(info->dev);
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
 
 	spin_lock_irq(&pipe_crc->lock);
@@ -3532,7 +3580,7 @@ i915_pipe_crc_read(struct file *filep, char __user *user_buf, size_t count,
 {
 	struct pipe_crc_info *info = filep->private_data;
 	struct drm_device *dev = info->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
 	char buf[PIPE_CRC_BUFFER_LEN];
 	int n_entries;
@@ -3665,7 +3713,7 @@ static const char *pipe_crc_source_name(enum intel_pipe_crc_source source)
 static int display_crc_ctl_show(struct seq_file *m, void *data)
 {
 	struct drm_device *dev = m->private;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
 	for (i = 0; i < I915_MAX_PIPES; i++)
@@ -3726,7 +3774,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_device *dev, enum pipe pipe,
 		case INTEL_OUTPUT_TVOUT:
 			*source = INTEL_PIPE_CRC_SOURCE_TV;
 			break;
-		case INTEL_OUTPUT_DISPLAYPORT:
+		case INTEL_OUTPUT_DP:
 		case INTEL_OUTPUT_EDP:
 			dig_port = enc_to_dig_port(&encoder->base);
 			switch (dig_port->port) {
@@ -3759,7 +3807,7 @@ static int vlv_pipe_crc_ctl_reg(struct drm_device *dev,
 				enum intel_pipe_crc_source *source,
 				uint32_t *val)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	bool need_stable_symbols = false;
 
 	if (*source == INTEL_PIPE_CRC_SOURCE_AUTO) {
@@ -3830,7 +3878,7 @@ static int i9xx_pipe_crc_ctl_reg(struct drm_device *dev,
 				 enum intel_pipe_crc_source *source,
 				 uint32_t *val)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	bool need_stable_symbols = false;
 
 	if (*source == INTEL_PIPE_CRC_SOURCE_AUTO) {
@@ -3904,7 +3952,7 @@ static int i9xx_pipe_crc_ctl_reg(struct drm_device *dev,
 static void vlv_undo_pipe_scramble_reset(struct drm_device *dev,
 					 enum pipe pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t tmp = I915_READ(PORT_DFT2_G4X);
 
 	switch (pipe) {
@@ -3929,7 +3977,7 @@ static void vlv_undo_pipe_scramble_reset(struct drm_device *dev,
 static void g4x_undo_pipe_scramble_reset(struct drm_device *dev,
 					 enum pipe pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t tmp = I915_READ(PORT_DFT2_G4X);
 
 	if (pipe == PIPE_A)
@@ -3972,7 +4020,7 @@ static int ilk_pipe_crc_ctl_reg(enum intel_pipe_crc_source *source,
 
 static void hsw_trans_edp_pipe_A_crc_wa(struct drm_device *dev, bool enable)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc =
 		to_intel_crtc(dev_priv->pipe_to_crtc_mapping[PIPE_A]);
 	struct intel_crtc_state *pipe_config;
@@ -4040,7 +4088,7 @@ static int ivb_pipe_crc_ctl_reg(struct drm_device *dev,
 static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 			       enum intel_pipe_crc_source source)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
 	struct intel_crtc *crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev,
 									pipe));
@@ -4547,7 +4595,7 @@ static void wm_latency_show(struct seq_file *m, const uint16_t wm[8])
 static int pri_wm_latency_show(struct seq_file *m, void *data)
 {
 	struct drm_device *dev = m->private;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	const uint16_t *latencies;
 
 	if (INTEL_INFO(dev)->gen >= 9)
@@ -4563,7 +4611,7 @@ static int pri_wm_latency_show(struct seq_file *m, void *data)
 static int spr_wm_latency_show(struct seq_file *m, void *data)
 {
 	struct drm_device *dev = m->private;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	const uint16_t *latencies;
 
 	if (INTEL_INFO(dev)->gen >= 9)
@@ -4579,7 +4627,7 @@ static int spr_wm_latency_show(struct seq_file *m, void *data)
 static int cur_wm_latency_show(struct seq_file *m, void *data)
 {
 	struct drm_device *dev = m->private;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	const uint16_t *latencies;
 
 	if (INTEL_INFO(dev)->gen >= 9)
@@ -4670,7 +4718,7 @@ static ssize_t pri_wm_latency_write(struct file *file, const char __user *ubuf,
 {
 	struct seq_file *m = file->private_data;
 	struct drm_device *dev = m->private;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint16_t *latencies;
 
 	if (INTEL_INFO(dev)->gen >= 9)
@@ -4686,7 +4734,7 @@ static ssize_t spr_wm_latency_write(struct file *file, const char __user *ubuf,
 {
 	struct seq_file *m = file->private_data;
 	struct drm_device *dev = m->private;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint16_t *latencies;
 
 	if (INTEL_INFO(dev)->gen >= 9)
@@ -4702,7 +4750,7 @@ static ssize_t cur_wm_latency_write(struct file *file, const char __user *ubuf,
 {
 	struct seq_file *m = file->private_data;
 	struct drm_device *dev = m->private;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint16_t *latencies;
 
 	if (INTEL_INFO(dev)->gen >= 9)
@@ -4744,7 +4792,7 @@ static int
 i915_wedged_get(void *data, u64 *val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	*val = i915_terminally_wedged(&dev_priv->gpu_error);
 
@@ -4755,7 +4803,7 @@ static int
 i915_wedged_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/*
 	 * There is no safeguard against this debugfs entry colliding
@@ -4770,7 +4818,7 @@ i915_wedged_set(void *data, u64 val)
 
 	intel_runtime_pm_get(dev_priv);
 
-	i915_handle_error(dev, val,
+	i915_handle_error(dev_priv, val,
 			  "Manually setting wedged to %llu", val);
 
 	intel_runtime_pm_put(dev_priv);
@@ -4783,44 +4831,10 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_wedged_fops,
 			"%llu\n");
 
 static int
-i915_ring_stop_get(void *data, u64 *val)
-{
-	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	*val = dev_priv->gpu_error.stop_rings;
-
-	return 0;
-}
-
-static int
-i915_ring_stop_set(void *data, u64 val)
-{
-	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret;
-
-	DRM_DEBUG_DRIVER("Stopping rings 0x%08llx\n", val);
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
-
-	dev_priv->gpu_error.stop_rings = val;
-	mutex_unlock(&dev->struct_mutex);
-
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(i915_ring_stop_fops,
-			i915_ring_stop_get, i915_ring_stop_set,
-			"0x%08llx\n");
-
-static int
 i915_ring_missed_irq_get(void *data, u64 *val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	*val = dev_priv->gpu_error.missed_irq_rings;
 	return 0;
@@ -4830,7 +4844,7 @@ static int
 i915_ring_missed_irq_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	/* Lock against concurrent debugfs callers */
@@ -4851,7 +4865,7 @@ static int
 i915_ring_test_irq_get(void *data, u64 *val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	*val = dev_priv->gpu_error.test_irq_rings;
 
@@ -4862,18 +4876,11 @@ static int
 i915_ring_test_irq_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
+	val &= INTEL_INFO(dev_priv)->ring_mask;
 	DRM_DEBUG_DRIVER("Masking interrupts on rings 0x%08llx\n", val);
-
-	/* Lock against concurrent debugfs callers */
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
-
 	dev_priv->gpu_error.test_irq_rings = val;
-	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
 }
@@ -4902,7 +4909,7 @@ static int
 i915_drop_caches_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	DRM_DEBUG("Dropping caches: 0x%08llx\n", val);
@@ -4914,13 +4921,13 @@ i915_drop_caches_set(void *data, u64 val)
 		return ret;
 
 	if (val & DROP_ACTIVE) {
-		ret = i915_gpu_idle(dev);
+		ret = i915_gem_wait_for_idle(dev_priv);
 		if (ret)
 			goto unlock;
 	}
 
 	if (val & (DROP_RETIRE | DROP_ACTIVE))
-		i915_gem_retire_requests(dev);
+		i915_gem_retire_requests(dev_priv);
 
 	if (val & DROP_BOUND)
 		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND);
@@ -4942,7 +4949,7 @@ static int
 i915_max_freq_get(void *data, u64 *val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	if (INTEL_INFO(dev)->gen < 6)
@@ -4964,7 +4971,7 @@ static int
 i915_max_freq_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 hw_max, hw_min;
 	int ret;
 
@@ -4994,7 +5001,7 @@ i915_max_freq_set(void *data, u64 val)
 
 	dev_priv->rps.max_freq_softlimit = val;
 
-	intel_set_rps(dev, val);
+	intel_set_rps(dev_priv, val);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
@@ -5009,7 +5016,7 @@ static int
 i915_min_freq_get(void *data, u64 *val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	if (INTEL_INFO(dev)->gen < 6)
@@ -5031,7 +5038,7 @@ static int
 i915_min_freq_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 hw_max, hw_min;
 	int ret;
 
@@ -5061,7 +5068,7 @@ i915_min_freq_set(void *data, u64 val)
 
 	dev_priv->rps.min_freq_softlimit = val;
 
-	intel_set_rps(dev, val);
+	intel_set_rps(dev_priv, val);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
@@ -5076,7 +5083,7 @@ static int
 i915_cache_sharing_get(void *data, u64 *val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 snpcr;
 	int ret;
 
@@ -5091,7 +5098,7 @@ i915_cache_sharing_get(void *data, u64 *val)
 	snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
 
 	intel_runtime_pm_put(dev_priv);
-	mutex_unlock(&dev_priv->dev->struct_mutex);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	*val = (snpcr & GEN6_MBC_SNPCR_MASK) >> GEN6_MBC_SNPCR_SHIFT;
 
@@ -5102,7 +5109,7 @@ static int
 i915_cache_sharing_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 snpcr;
 
 	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
@@ -5139,7 +5146,7 @@ struct sseu_dev_status {
 static void cherryview_sseu_device_status(struct drm_device *dev,
 					  struct sseu_dev_status *stat)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ss_max = 2;
 	int ss;
 	u32 sig1[ss_max], sig2[ss_max];
@@ -5171,7 +5178,7 @@ static void cherryview_sseu_device_status(struct drm_device *dev,
 static void gen9_sseu_device_status(struct drm_device *dev,
 				    struct sseu_dev_status *stat)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int s_max = 3, ss_max = 4;
 	int s, ss;
 	u32 s_reg[s_max], eu_reg[2*s_max], eu_mask[2];
@@ -5236,7 +5243,7 @@ static void gen9_sseu_device_status(struct drm_device *dev,
 static void broadwell_sseu_device_status(struct drm_device *dev,
 					 struct sseu_dev_status *stat)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int s;
 	u32 slice_info = I915_READ(GEN8_GT_SLICE_INFO);
 
@@ -5278,6 +5285,10 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 		   INTEL_INFO(dev)->eu_total);
 	seq_printf(m, "  Available EU Per Subslice: %u\n",
 		   INTEL_INFO(dev)->eu_per_subslice);
+	seq_printf(m, "  Has Pooled EU: %s\n", yesno(HAS_POOLED_EU(dev)));
+	if (HAS_POOLED_EU(dev))
+		seq_printf(m, "  Min EU in pool: %u\n",
+			   INTEL_INFO(dev)->min_eu_in_pool);
 	seq_printf(m, "  Has Slice Power Gating: %s\n",
 		   yesno(INTEL_INFO(dev)->has_slice_pg));
 	seq_printf(m, "  Has Subslice Power Gating: %s\n",
@@ -5311,7 +5322,7 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 static int i915_forcewake_open(struct inode *inode, struct file *file)
 {
 	struct drm_device *dev = inode->i_private;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (INTEL_INFO(dev)->gen < 6)
 		return 0;
@@ -5325,7 +5336,7 @@ static int i915_forcewake_open(struct inode *inode, struct file *file)
 static int i915_forcewake_release(struct inode *inode, struct file *file)
 {
 	struct drm_device *dev = inode->i_private;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (INTEL_INFO(dev)->gen < 6)
 		return 0;
@@ -5441,7 +5452,6 @@ static const struct i915_debugfs_files {
 	{"i915_max_freq", &i915_max_freq_fops},
 	{"i915_min_freq", &i915_min_freq_fops},
 	{"i915_cache_sharing", &i915_cache_sharing_fops},
-	{"i915_ring_stop", &i915_ring_stop_fops},
 	{"i915_ring_missed_irq", &i915_ring_missed_irq_fops},
 	{"i915_ring_test_irq", &i915_ring_test_irq_fops},
 	{"i915_gem_drop_caches", &i915_drop_caches_fops},
@@ -5459,7 +5469,7 @@ static const struct i915_debugfs_files {
 
 void intel_display_crc_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe;
 
 	for_each_pipe(dev_priv, pipe) {
@@ -5471,8 +5481,9 @@ void intel_display_crc_init(struct drm_device *dev)
 	}
 }
 
-int i915_debugfs_init(struct drm_minor *minor)
+int i915_debugfs_register(struct drm_i915_private *dev_priv)
 {
+	struct drm_minor *minor = dev_priv->drm.primary;
 	int ret, i;
 
 	ret = i915_forcewake_create(minor->debugfs_root, minor);
@@ -5498,8 +5509,9 @@ int i915_debugfs_init(struct drm_minor *minor)
 					minor->debugfs_root, minor);
 }
 
-void i915_debugfs_cleanup(struct drm_minor *minor)
+void i915_debugfs_unregister(struct drm_i915_private *dev_priv)
 {
+	struct drm_minor *minor = dev_priv->drm.primary;
 	int i;
 
 	drm_debugfs_remove_files(i915_debugfs_list,
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
deleted file mode 100644
index b3198fcd0536..000000000000
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ /dev/null
@@ -1,1587 +0,0 @@
-/* i915_dma.c -- DMA support for the I915 -*- linux-c -*-
- */
-/*
- * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas.
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the
- * "Software"), to deal in the Software without restriction, including
- * without limitation the rights to use, copy, modify, merge, publish,
- * distribute, sub license, and/or sell copies of the Software, and to
- * permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice (including the
- * next paragraph) shall be included in all copies or substantial portions
- * of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
- * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
- * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR
- * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
- * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
- * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <drm/drmP.h>
-#include <drm/drm_crtc_helper.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_legacy.h>
-#include "intel_drv.h"
-#include <drm/i915_drm.h>
-#include "i915_drv.h"
-#include "i915_vgpu.h"
-#include "i915_trace.h"
-#include <linux/pci.h>
-#include <linux/console.h>
-#include <linux/vt.h>
-#include <linux/vgaarb.h>
-#include <linux/acpi.h>
-#include <linux/pnp.h>
-#include <linux/vga_switcheroo.h>
-#include <linux/slab.h>
-#include <acpi/video.h>
-#include <linux/pm.h>
-#include <linux/pm_runtime.h>
-#include <linux/oom.h>
-
-static unsigned int i915_load_fail_count;
-
-bool __i915_inject_load_failure(const char *func, int line)
-{
-	if (i915_load_fail_count >= i915.inject_load_failure)
-		return false;
-
-	if (++i915_load_fail_count == i915.inject_load_failure) {
-		DRM_INFO("Injecting failure at checkpoint %u [%s:%d]\n",
-			 i915.inject_load_failure, func, line);
-		return true;
-	}
-
-	return false;
-}
-
-#define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI"
-#define FDO_BUG_MSG "Please file a bug at " FDO_BUG_URL " against DRM/Intel " \
-		    "providing the dmesg log by booting with drm.debug=0xf"
-
-void
-__i915_printk(struct drm_i915_private *dev_priv, const char *level,
-	      const char *fmt, ...)
-{
-	static bool shown_bug_once;
-	struct device *dev = dev_priv->dev->dev;
-	bool is_error = level[1] <= KERN_ERR[1];
-	bool is_debug = level[1] == KERN_DEBUG[1];
-	struct va_format vaf;
-	va_list args;
-
-	if (is_debug && !(drm_debug & DRM_UT_DRIVER))
-		return;
-
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	dev_printk(level, dev, "[" DRM_NAME ":%ps] %pV",
-		   __builtin_return_address(0), &vaf);
-
-	if (is_error && !shown_bug_once) {
-		dev_notice(dev, "%s", FDO_BUG_MSG);
-		shown_bug_once = true;
-	}
-
-	va_end(args);
-}
-
-static bool i915_error_injected(struct drm_i915_private *dev_priv)
-{
-	return i915.inject_load_failure &&
-	       i915_load_fail_count == i915.inject_load_failure;
-}
-
-#define i915_load_error(dev_priv, fmt, ...)				     \
-	__i915_printk(dev_priv,						     \
-		      i915_error_injected(dev_priv) ? KERN_DEBUG : KERN_ERR, \
-		      fmt, ##__VA_ARGS__)
-
-static int i915_getparam(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	drm_i915_getparam_t *param = data;
-	int value;
-
-	switch (param->param) {
-	case I915_PARAM_IRQ_ACTIVE:
-	case I915_PARAM_ALLOW_BATCHBUFFER:
-	case I915_PARAM_LAST_DISPATCH:
-		/* Reject all old ums/dri params. */
-		return -ENODEV;
-	case I915_PARAM_CHIPSET_ID:
-		value = dev->pdev->device;
-		break;
-	case I915_PARAM_REVISION:
-		value = dev->pdev->revision;
-		break;
-	case I915_PARAM_HAS_GEM:
-		value = 1;
-		break;
-	case I915_PARAM_NUM_FENCES_AVAIL:
-		value = dev_priv->num_fence_regs;
-		break;
-	case I915_PARAM_HAS_OVERLAY:
-		value = dev_priv->overlay ? 1 : 0;
-		break;
-	case I915_PARAM_HAS_PAGEFLIPPING:
-		value = 1;
-		break;
-	case I915_PARAM_HAS_EXECBUF2:
-		/* depends on GEM */
-		value = 1;
-		break;
-	case I915_PARAM_HAS_BSD:
-		value = intel_engine_initialized(&dev_priv->engine[VCS]);
-		break;
-	case I915_PARAM_HAS_BLT:
-		value = intel_engine_initialized(&dev_priv->engine[BCS]);
-		break;
-	case I915_PARAM_HAS_VEBOX:
-		value = intel_engine_initialized(&dev_priv->engine[VECS]);
-		break;
-	case I915_PARAM_HAS_BSD2:
-		value = intel_engine_initialized(&dev_priv->engine[VCS2]);
-		break;
-	case I915_PARAM_HAS_RELAXED_FENCING:
-		value = 1;
-		break;
-	case I915_PARAM_HAS_COHERENT_RINGS:
-		value = 1;
-		break;
-	case I915_PARAM_HAS_EXEC_CONSTANTS:
-		value = INTEL_INFO(dev)->gen >= 4;
-		break;
-	case I915_PARAM_HAS_RELAXED_DELTA:
-		value = 1;
-		break;
-	case I915_PARAM_HAS_GEN7_SOL_RESET:
-		value = 1;
-		break;
-	case I915_PARAM_HAS_LLC:
-		value = HAS_LLC(dev);
-		break;
-	case I915_PARAM_HAS_WT:
-		value = HAS_WT(dev);
-		break;
-	case I915_PARAM_HAS_ALIASING_PPGTT:
-		value = USES_PPGTT(dev);
-		break;
-	case I915_PARAM_HAS_WAIT_TIMEOUT:
-		value = 1;
-		break;
-	case I915_PARAM_HAS_SEMAPHORES:
-		value = i915_semaphore_is_enabled(dev);
-		break;
-	case I915_PARAM_HAS_PRIME_VMAP_FLUSH:
-		value = 1;
-		break;
-	case I915_PARAM_HAS_SECURE_BATCHES:
-		value = capable(CAP_SYS_ADMIN);
-		break;
-	case I915_PARAM_HAS_PINNED_BATCHES:
-		value = 1;
-		break;
-	case I915_PARAM_HAS_EXEC_NO_RELOC:
-		value = 1;
-		break;
-	case I915_PARAM_HAS_EXEC_HANDLE_LUT:
-		value = 1;
-		break;
-	case I915_PARAM_CMD_PARSER_VERSION:
-		value = i915_cmd_parser_get_version();
-		break;
-	case I915_PARAM_HAS_COHERENT_PHYS_GTT:
-		value = 1;
-		break;
-	case I915_PARAM_MMAP_VERSION:
-		value = 1;
-		break;
-	case I915_PARAM_SUBSLICE_TOTAL:
-		value = INTEL_INFO(dev)->subslice_total;
-		if (!value)
-			return -ENODEV;
-		break;
-	case I915_PARAM_EU_TOTAL:
-		value = INTEL_INFO(dev)->eu_total;
-		if (!value)
-			return -ENODEV;
-		break;
-	case I915_PARAM_HAS_GPU_RESET:
-		value = i915.enable_hangcheck &&
-			intel_has_gpu_reset(dev);
-		break;
-	case I915_PARAM_HAS_RESOURCE_STREAMER:
-		value = HAS_RESOURCE_STREAMER(dev);
-		break;
-	case I915_PARAM_HAS_EXEC_SOFTPIN:
-		value = 1;
-		break;
-	default:
-		DRM_DEBUG("Unknown parameter %d\n", param->param);
-		return -EINVAL;
-	}
-
-	if (copy_to_user(param->value, &value, sizeof(int))) {
-		DRM_ERROR("copy_to_user failed\n");
-		return -EFAULT;
-	}
-
-	return 0;
-}
-
-static int i915_get_bridge_dev(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	dev_priv->bridge_dev = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0));
-	if (!dev_priv->bridge_dev) {
-		DRM_ERROR("bridge device not found\n");
-		return -1;
-	}
-	return 0;
-}
-
-/* Allocate space for the MCH regs if needed, return nonzero on error */
-static int
-intel_alloc_mchbar_resource(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int reg = INTEL_INFO(dev)->gen >= 4 ? MCHBAR_I965 : MCHBAR_I915;
-	u32 temp_lo, temp_hi = 0;
-	u64 mchbar_addr;
-	int ret;
-
-	if (INTEL_INFO(dev)->gen >= 4)
-		pci_read_config_dword(dev_priv->bridge_dev, reg + 4, &temp_hi);
-	pci_read_config_dword(dev_priv->bridge_dev, reg, &temp_lo);
-	mchbar_addr = ((u64)temp_hi << 32) | temp_lo;
-
-	/* If ACPI doesn't have it, assume we need to allocate it ourselves */
-#ifdef CONFIG_PNP
-	if (mchbar_addr &&
-	    pnp_range_reserved(mchbar_addr, mchbar_addr + MCHBAR_SIZE))
-		return 0;
-#endif
-
-	/* Get some space for it */
-	dev_priv->mch_res.name = "i915 MCHBAR";
-	dev_priv->mch_res.flags = IORESOURCE_MEM;
-	ret = pci_bus_alloc_resource(dev_priv->bridge_dev->bus,
-				     &dev_priv->mch_res,
-				     MCHBAR_SIZE, MCHBAR_SIZE,
-				     PCIBIOS_MIN_MEM,
-				     0, pcibios_align_resource,
-				     dev_priv->bridge_dev);
-	if (ret) {
-		DRM_DEBUG_DRIVER("failed bus alloc: %d\n", ret);
-		dev_priv->mch_res.start = 0;
-		return ret;
-	}
-
-	if (INTEL_INFO(dev)->gen >= 4)
-		pci_write_config_dword(dev_priv->bridge_dev, reg + 4,
-				       upper_32_bits(dev_priv->mch_res.start));
-
-	pci_write_config_dword(dev_priv->bridge_dev, reg,
-			       lower_32_bits(dev_priv->mch_res.start));
-	return 0;
-}
-
-/* Setup MCHBAR if possible, return true if we should disable it again */
-static void
-intel_setup_mchbar(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int mchbar_reg = INTEL_INFO(dev)->gen >= 4 ? MCHBAR_I965 : MCHBAR_I915;
-	u32 temp;
-	bool enabled;
-
-	if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))
-		return;
-
-	dev_priv->mchbar_need_disable = false;
-
-	if (IS_I915G(dev) || IS_I915GM(dev)) {
-		pci_read_config_dword(dev_priv->bridge_dev, DEVEN, &temp);
-		enabled = !!(temp & DEVEN_MCHBAR_EN);
-	} else {
-		pci_read_config_dword(dev_priv->bridge_dev, mchbar_reg, &temp);
-		enabled = temp & 1;
-	}
-
-	/* If it's already enabled, don't have to do anything */
-	if (enabled)
-		return;
-
-	if (intel_alloc_mchbar_resource(dev))
-		return;
-
-	dev_priv->mchbar_need_disable = true;
-
-	/* Space is allocated or reserved, so enable it. */
-	if (IS_I915G(dev) || IS_I915GM(dev)) {
-		pci_write_config_dword(dev_priv->bridge_dev, DEVEN,
-				       temp | DEVEN_MCHBAR_EN);
-	} else {
-		pci_read_config_dword(dev_priv->bridge_dev, mchbar_reg, &temp);
-		pci_write_config_dword(dev_priv->bridge_dev, mchbar_reg, temp | 1);
-	}
-}
-
-static void
-intel_teardown_mchbar(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int mchbar_reg = INTEL_INFO(dev)->gen >= 4 ? MCHBAR_I965 : MCHBAR_I915;
-
-	if (dev_priv->mchbar_need_disable) {
-		if (IS_I915G(dev) || IS_I915GM(dev)) {
-			u32 deven_val;
-
-			pci_read_config_dword(dev_priv->bridge_dev, DEVEN,
-					      &deven_val);
-			deven_val &= ~DEVEN_MCHBAR_EN;
-			pci_write_config_dword(dev_priv->bridge_dev, DEVEN,
-					       deven_val);
-		} else {
-			u32 mchbar_val;
-
-			pci_read_config_dword(dev_priv->bridge_dev, mchbar_reg,
-					      &mchbar_val);
-			mchbar_val &= ~1;
-			pci_write_config_dword(dev_priv->bridge_dev, mchbar_reg,
-					       mchbar_val);
-		}
-	}
-
-	if (dev_priv->mch_res.start)
-		release_resource(&dev_priv->mch_res);
-}
-
-/* true = enable decode, false = disable decoder */
-static unsigned int i915_vga_set_decode(void *cookie, bool state)
-{
-	struct drm_device *dev = cookie;
-
-	intel_modeset_vga_set_state(dev, state);
-	if (state)
-		return VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM |
-		       VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
-	else
-		return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
-}
-
-static void i915_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_state state)
-{
-	struct drm_device *dev = pci_get_drvdata(pdev);
-	pm_message_t pmm = { .event = PM_EVENT_SUSPEND };
-
-	if (state == VGA_SWITCHEROO_ON) {
-		pr_info("switched on\n");
-		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
-		/* i915 resume handler doesn't set to D0 */
-		pci_set_power_state(dev->pdev, PCI_D0);
-		i915_resume_switcheroo(dev);
-		dev->switch_power_state = DRM_SWITCH_POWER_ON;
-	} else {
-		pr_info("switched off\n");
-		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
-		i915_suspend_switcheroo(dev, pmm);
-		dev->switch_power_state = DRM_SWITCH_POWER_OFF;
-	}
-}
-
-static bool i915_switcheroo_can_switch(struct pci_dev *pdev)
-{
-	struct drm_device *dev = pci_get_drvdata(pdev);
-
-	/*
-	 * FIXME: open_count is protected by drm_global_mutex but that would lead to
-	 * locking inversion with the driver load path. And the access here is
-	 * completely racy anyway. So don't bother with locking for now.
-	 */
-	return dev->open_count == 0;
-}
-
-static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
-	.set_gpu_state = i915_switcheroo_set_state,
-	.reprobe = NULL,
-	.can_switch = i915_switcheroo_can_switch,
-};
-
-static int i915_load_modeset_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret;
-
-	if (i915_inject_load_failure())
-		return -ENODEV;
-
-	ret = intel_bios_init(dev_priv);
-	if (ret)
-		DRM_INFO("failed to find VBIOS tables\n");
-
-	/* If we have > 1 VGA cards, then we need to arbitrate access
-	 * to the common VGA resources.
-	 *
-	 * If we are a secondary display controller (!PCI_DISPLAY_CLASS_VGA),
-	 * then we do not take part in VGA arbitration and the
-	 * vga_client_register() fails with -ENODEV.
-	 */
-	ret = vga_client_register(dev->pdev, dev, NULL, i915_vga_set_decode);
-	if (ret && ret != -ENODEV)
-		goto out;
-
-	intel_register_dsm_handler();
-
-	ret = vga_switcheroo_register_client(dev->pdev, &i915_switcheroo_ops, false);
-	if (ret)
-		goto cleanup_vga_client;
-
-	intel_power_domains_init_hw(dev_priv, false);
-
-	intel_csr_ucode_init(dev_priv);
-
-	ret = intel_irq_install(dev_priv);
-	if (ret)
-		goto cleanup_csr;
-
-	intel_setup_gmbus(dev);
-
-	/* Important: The output setup functions called by modeset_init need
-	 * working irqs for e.g. gmbus and dp aux transfers. */
-	intel_modeset_init(dev);
-
-	intel_guc_ucode_init(dev);
-
-	ret = i915_gem_init(dev);
-	if (ret)
-		goto cleanup_irq;
-
-	intel_modeset_gem_init(dev);
-
-	if (INTEL_INFO(dev)->num_pipes == 0)
-		return 0;
-
-	ret = intel_fbdev_init(dev);
-	if (ret)
-		goto cleanup_gem;
-
-	/* Only enable hotplug handling once the fbdev is fully set up. */
-	intel_hpd_init(dev_priv);
-
-	/*
-	 * Some ports require correctly set-up hpd registers for detection to
-	 * work properly (leading to ghost connected connector status), e.g. VGA
-	 * on gm45.  Hence we can only set up the initial fbdev config after hpd
-	 * irqs are fully enabled. Now we should scan for the initial config
-	 * only once hotplug handling is enabled, but due to screwed-up locking
-	 * around kms/fbdev init we can't protect the fdbev initial config
-	 * scanning against hotplug events. Hence do this first and ignore the
-	 * tiny window where we will loose hotplug notifactions.
-	 */
-	intel_fbdev_initial_config_async(dev);
-
-	drm_kms_helper_poll_init(dev);
-
-	return 0;
-
-cleanup_gem:
-	mutex_lock(&dev->struct_mutex);
-	i915_gem_cleanup_engines(dev);
-	i915_gem_context_fini(dev);
-	mutex_unlock(&dev->struct_mutex);
-cleanup_irq:
-	intel_guc_ucode_fini(dev);
-	drm_irq_uninstall(dev);
-	intel_teardown_gmbus(dev);
-cleanup_csr:
-	intel_csr_ucode_fini(dev_priv);
-	intel_power_domains_fini(dev_priv);
-	vga_switcheroo_unregister_client(dev->pdev);
-cleanup_vga_client:
-	vga_client_register(dev->pdev, NULL, NULL, NULL);
-out:
-	return ret;
-}
-
-#if IS_ENABLED(CONFIG_FB)
-static int i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
-{
-	struct apertures_struct *ap;
-	struct pci_dev *pdev = dev_priv->dev->pdev;
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	bool primary;
-	int ret;
-
-	ap = alloc_apertures(1);
-	if (!ap)
-		return -ENOMEM;
-
-	ap->ranges[0].base = ggtt->mappable_base;
-	ap->ranges[0].size = ggtt->mappable_end;
-
-	primary =
-		pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;
-
-	ret = remove_conflicting_framebuffers(ap, "inteldrmfb", primary);
-
-	kfree(ap);
-
-	return ret;
-}
-#else
-static int i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
-{
-	return 0;
-}
-#endif
-
-#if !defined(CONFIG_VGA_CONSOLE)
-static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
-{
-	return 0;
-}
-#elif !defined(CONFIG_DUMMY_CONSOLE)
-static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
-{
-	return -ENODEV;
-}
-#else
-static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
-{
-	int ret = 0;
-
-	DRM_INFO("Replacing VGA console driver\n");
-
-	console_lock();
-	if (con_is_bound(&vga_con))
-		ret = do_take_over_console(&dummy_con, 0, MAX_NR_CONSOLES - 1, 1);
-	if (ret == 0) {
-		ret = do_unregister_con_driver(&vga_con);
-
-		/* Ignore "already unregistered". */
-		if (ret == -ENODEV)
-			ret = 0;
-	}
-	console_unlock();
-
-	return ret;
-}
-#endif
-
-static void i915_dump_device_info(struct drm_i915_private *dev_priv)
-{
-	const struct intel_device_info *info = &dev_priv->info;
-
-#define PRINT_S(name) "%s"
-#define SEP_EMPTY
-#define PRINT_FLAG(name) info->name ? #name "," : ""
-#define SEP_COMMA ,
-	DRM_DEBUG_DRIVER("i915 device info: gen=%i, pciid=0x%04x rev=0x%02x flags="
-			 DEV_INFO_FOR_EACH_FLAG(PRINT_S, SEP_EMPTY),
-			 info->gen,
-			 dev_priv->dev->pdev->device,
-			 dev_priv->dev->pdev->revision,
-			 DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG, SEP_COMMA));
-#undef PRINT_S
-#undef SEP_EMPTY
-#undef PRINT_FLAG
-#undef SEP_COMMA
-}
-
-static void cherryview_sseu_info_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_device_info *info;
-	u32 fuse, eu_dis;
-
-	info = (struct intel_device_info *)&dev_priv->info;
-	fuse = I915_READ(CHV_FUSE_GT);
-
-	info->slice_total = 1;
-
-	if (!(fuse & CHV_FGT_DISABLE_SS0)) {
-		info->subslice_per_slice++;
-		eu_dis = fuse & (CHV_FGT_EU_DIS_SS0_R0_MASK |
-				 CHV_FGT_EU_DIS_SS0_R1_MASK);
-		info->eu_total += 8 - hweight32(eu_dis);
-	}
-
-	if (!(fuse & CHV_FGT_DISABLE_SS1)) {
-		info->subslice_per_slice++;
-		eu_dis = fuse & (CHV_FGT_EU_DIS_SS1_R0_MASK |
-				 CHV_FGT_EU_DIS_SS1_R1_MASK);
-		info->eu_total += 8 - hweight32(eu_dis);
-	}
-
-	info->subslice_total = info->subslice_per_slice;
-	/*
-	 * CHV expected to always have a uniform distribution of EU
-	 * across subslices.
-	*/
-	info->eu_per_subslice = info->subslice_total ?
-				info->eu_total / info->subslice_total :
-				0;
-	/*
-	 * CHV supports subslice power gating on devices with more than
-	 * one subslice, and supports EU power gating on devices with
-	 * more than one EU pair per subslice.
-	*/
-	info->has_slice_pg = 0;
-	info->has_subslice_pg = (info->subslice_total > 1);
-	info->has_eu_pg = (info->eu_per_subslice > 2);
-}
-
-static void gen9_sseu_info_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_device_info *info;
-	int s_max = 3, ss_max = 4, eu_max = 8;
-	int s, ss;
-	u32 fuse2, s_enable, ss_disable, eu_disable;
-	u8 eu_mask = 0xff;
-
-	info = (struct intel_device_info *)&dev_priv->info;
-	fuse2 = I915_READ(GEN8_FUSE2);
-	s_enable = (fuse2 & GEN8_F2_S_ENA_MASK) >>
-		   GEN8_F2_S_ENA_SHIFT;
-	ss_disable = (fuse2 & GEN9_F2_SS_DIS_MASK) >>
-		     GEN9_F2_SS_DIS_SHIFT;
-
-	info->slice_total = hweight32(s_enable);
-	/*
-	 * The subslice disable field is global, i.e. it applies
-	 * to each of the enabled slices.
-	*/
-	info->subslice_per_slice = ss_max - hweight32(ss_disable);
-	info->subslice_total = info->slice_total *
-			       info->subslice_per_slice;
-
-	/*
-	 * Iterate through enabled slices and subslices to
-	 * count the total enabled EU.
-	*/
-	for (s = 0; s < s_max; s++) {
-		if (!(s_enable & (0x1 << s)))
-			/* skip disabled slice */
-			continue;
-
-		eu_disable = I915_READ(GEN9_EU_DISABLE(s));
-		for (ss = 0; ss < ss_max; ss++) {
-			int eu_per_ss;
-
-			if (ss_disable & (0x1 << ss))
-				/* skip disabled subslice */
-				continue;
-
-			eu_per_ss = eu_max - hweight8((eu_disable >> (ss*8)) &
-						      eu_mask);
-
-			/*
-			 * Record which subslice(s) has(have) 7 EUs. we
-			 * can tune the hash used to spread work among
-			 * subslices if they are unbalanced.
-			 */
-			if (eu_per_ss == 7)
-				info->subslice_7eu[s] |= 1 << ss;
-
-			info->eu_total += eu_per_ss;
-		}
-	}
-
-	/*
-	 * SKL is expected to always have a uniform distribution
-	 * of EU across subslices with the exception that any one
-	 * EU in any one subslice may be fused off for die
-	 * recovery. BXT is expected to be perfectly uniform in EU
-	 * distribution.
-	*/
-	info->eu_per_subslice = info->subslice_total ?
-				DIV_ROUND_UP(info->eu_total,
-					     info->subslice_total) : 0;
-	/*
-	 * SKL supports slice power gating on devices with more than
-	 * one slice, and supports EU power gating on devices with
-	 * more than one EU pair per subslice. BXT supports subslice
-	 * power gating on devices with more than one subslice, and
-	 * supports EU power gating on devices with more than one EU
-	 * pair per subslice.
-	*/
-	info->has_slice_pg = ((IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) &&
-			       (info->slice_total > 1));
-	info->has_subslice_pg = (IS_BROXTON(dev) && (info->subslice_total > 1));
-	info->has_eu_pg = (info->eu_per_subslice > 2);
-}
-
-static void broadwell_sseu_info_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_device_info *info;
-	const int s_max = 3, ss_max = 3, eu_max = 8;
-	int s, ss;
-	u32 fuse2, eu_disable[s_max], s_enable, ss_disable;
-
-	fuse2 = I915_READ(GEN8_FUSE2);
-	s_enable = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
-	ss_disable = (fuse2 & GEN8_F2_SS_DIS_MASK) >> GEN8_F2_SS_DIS_SHIFT;
-
-	eu_disable[0] = I915_READ(GEN8_EU_DISABLE0) & GEN8_EU_DIS0_S0_MASK;
-	eu_disable[1] = (I915_READ(GEN8_EU_DISABLE0) >> GEN8_EU_DIS0_S1_SHIFT) |
-			((I915_READ(GEN8_EU_DISABLE1) & GEN8_EU_DIS1_S1_MASK) <<
-			 (32 - GEN8_EU_DIS0_S1_SHIFT));
-	eu_disable[2] = (I915_READ(GEN8_EU_DISABLE1) >> GEN8_EU_DIS1_S2_SHIFT) |
-			((I915_READ(GEN8_EU_DISABLE2) & GEN8_EU_DIS2_S2_MASK) <<
-			 (32 - GEN8_EU_DIS1_S2_SHIFT));
-
-
-	info = (struct intel_device_info *)&dev_priv->info;
-	info->slice_total = hweight32(s_enable);
-
-	/*
-	 * The subslice disable field is global, i.e. it applies
-	 * to each of the enabled slices.
-	 */
-	info->subslice_per_slice = ss_max - hweight32(ss_disable);
-	info->subslice_total = info->slice_total * info->subslice_per_slice;
-
-	/*
-	 * Iterate through enabled slices and subslices to
-	 * count the total enabled EU.
-	 */
-	for (s = 0; s < s_max; s++) {
-		if (!(s_enable & (0x1 << s)))
-			/* skip disabled slice */
-			continue;
-
-		for (ss = 0; ss < ss_max; ss++) {
-			u32 n_disabled;
-
-			if (ss_disable & (0x1 << ss))
-				/* skip disabled subslice */
-				continue;
-
-			n_disabled = hweight8(eu_disable[s] >> (ss * eu_max));
-
-			/*
-			 * Record which subslices have 7 EUs.
-			 */
-			if (eu_max - n_disabled == 7)
-				info->subslice_7eu[s] |= 1 << ss;
-
-			info->eu_total += eu_max - n_disabled;
-		}
-	}
-
-	/*
-	 * BDW is expected to always have a uniform distribution of EU across
-	 * subslices with the exception that any one EU in any one subslice may
-	 * be fused off for die recovery.
-	 */
-	info->eu_per_subslice = info->subslice_total ?
-		DIV_ROUND_UP(info->eu_total, info->subslice_total) : 0;
-
-	/*
-	 * BDW supports slice power gating on devices with more than
-	 * one slice.
-	 */
-	info->has_slice_pg = (info->slice_total > 1);
-	info->has_subslice_pg = 0;
-	info->has_eu_pg = 0;
-}
-
-/*
- * Determine various intel_device_info fields at runtime.
- *
- * Use it when either:
- *   - it's judged too laborious to fill n static structures with the limit
- *     when a simple if statement does the job,
- *   - run-time checks (eg read fuse/strap registers) are needed.
- *
- * This function needs to be called:
- *   - after the MMIO has been setup as we are reading registers,
- *   - after the PCH has been detected,
- *   - before the first usage of the fields it can tweak.
- */
-static void intel_device_info_runtime_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_device_info *info;
-	enum pipe pipe;
-
-	info = (struct intel_device_info *)&dev_priv->info;
-
-	/*
-	 * Skylake and Broxton currently don't expose the topmost plane as its
-	 * use is exclusive with the legacy cursor and we only want to expose
-	 * one of those, not both. Until we can safely expose the topmost plane
-	 * as a DRM_PLANE_TYPE_CURSOR with all the features exposed/supported,
-	 * we don't expose the topmost plane at all to prevent ABI breakage
-	 * down the line.
-	 */
-	if (IS_BROXTON(dev)) {
-		info->num_sprites[PIPE_A] = 2;
-		info->num_sprites[PIPE_B] = 2;
-		info->num_sprites[PIPE_C] = 1;
-	} else if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))
-		for_each_pipe(dev_priv, pipe)
-			info->num_sprites[pipe] = 2;
-	else
-		for_each_pipe(dev_priv, pipe)
-			info->num_sprites[pipe] = 1;
-
-	if (i915.disable_display) {
-		DRM_INFO("Display disabled (module parameter)\n");
-		info->num_pipes = 0;
-	} else if (info->num_pipes > 0 &&
-		   (INTEL_INFO(dev)->gen == 7 || INTEL_INFO(dev)->gen == 8) &&
-		   HAS_PCH_SPLIT(dev)) {
-		u32 fuse_strap = I915_READ(FUSE_STRAP);
-		u32 sfuse_strap = I915_READ(SFUSE_STRAP);
-
-		/*
-		 * SFUSE_STRAP is supposed to have a bit signalling the display
-		 * is fused off. Unfortunately it seems that, at least in
-		 * certain cases, fused off display means that PCH display
-		 * reads don't land anywhere. In that case, we read 0s.
-		 *
-		 * On CPT/PPT, we can detect this case as SFUSE_STRAP_FUSE_LOCK
-		 * should be set when taking over after the firmware.
-		 */
-		if (fuse_strap & ILK_INTERNAL_DISPLAY_DISABLE ||
-		    sfuse_strap & SFUSE_STRAP_DISPLAY_DISABLED ||
-		    (dev_priv->pch_type == PCH_CPT &&
-		     !(sfuse_strap & SFUSE_STRAP_FUSE_LOCK))) {
-			DRM_INFO("Display fused off, disabling\n");
-			info->num_pipes = 0;
-		} else if (fuse_strap & IVB_PIPE_C_DISABLE) {
-			DRM_INFO("PipeC fused off\n");
-			info->num_pipes -= 1;
-		}
-	} else if (info->num_pipes > 0 && INTEL_INFO(dev)->gen == 9) {
-		u32 dfsm = I915_READ(SKL_DFSM);
-		u8 disabled_mask = 0;
-		bool invalid;
-		int num_bits;
-
-		if (dfsm & SKL_DFSM_PIPE_A_DISABLE)
-			disabled_mask |= BIT(PIPE_A);
-		if (dfsm & SKL_DFSM_PIPE_B_DISABLE)
-			disabled_mask |= BIT(PIPE_B);
-		if (dfsm & SKL_DFSM_PIPE_C_DISABLE)
-			disabled_mask |= BIT(PIPE_C);
-
-		num_bits = hweight8(disabled_mask);
-
-		switch (disabled_mask) {
-		case BIT(PIPE_A):
-		case BIT(PIPE_B):
-		case BIT(PIPE_A) | BIT(PIPE_B):
-		case BIT(PIPE_A) | BIT(PIPE_C):
-			invalid = true;
-			break;
-		default:
-			invalid = false;
-		}
-
-		if (num_bits > info->num_pipes || invalid)
-			DRM_ERROR("invalid pipe fuse configuration: 0x%x\n",
-				  disabled_mask);
-		else
-			info->num_pipes -= num_bits;
-	}
-
-	/* Initialize slice/subslice/EU info */
-	if (IS_CHERRYVIEW(dev))
-		cherryview_sseu_info_init(dev);
-	else if (IS_BROADWELL(dev))
-		broadwell_sseu_info_init(dev);
-	else if (INTEL_INFO(dev)->gen >= 9)
-		gen9_sseu_info_init(dev);
-
-	/* Snooping is broken on BXT A stepping. */
-	info->has_snoop = !info->has_llc;
-	info->has_snoop &= !IS_BXT_REVID(dev, 0, BXT_REVID_A1);
-
-	DRM_DEBUG_DRIVER("slice total: %u\n", info->slice_total);
-	DRM_DEBUG_DRIVER("subslice total: %u\n", info->subslice_total);
-	DRM_DEBUG_DRIVER("subslice per slice: %u\n", info->subslice_per_slice);
-	DRM_DEBUG_DRIVER("EU total: %u\n", info->eu_total);
-	DRM_DEBUG_DRIVER("EU per subslice: %u\n", info->eu_per_subslice);
-	DRM_DEBUG_DRIVER("has slice power gating: %s\n",
-			 info->has_slice_pg ? "y" : "n");
-	DRM_DEBUG_DRIVER("has subslice power gating: %s\n",
-			 info->has_subslice_pg ? "y" : "n");
-	DRM_DEBUG_DRIVER("has EU power gating: %s\n",
-			 info->has_eu_pg ? "y" : "n");
-}
-
-static void intel_init_dpio(struct drm_i915_private *dev_priv)
-{
-	/*
-	 * IOSF_PORT_DPIO is used for VLV x2 PHY (DP/HDMI B and C),
-	 * CHV x1 PHY (DP/HDMI D)
-	 * IOSF_PORT_DPIO_2 is used for CHV x2 PHY (DP/HDMI B and C)
-	 */
-	if (IS_CHERRYVIEW(dev_priv)) {
-		DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO_2;
-		DPIO_PHY_IOSF_PORT(DPIO_PHY1) = IOSF_PORT_DPIO;
-	} else if (IS_VALLEYVIEW(dev_priv)) {
-		DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO;
-	}
-}
-
-static int i915_workqueues_init(struct drm_i915_private *dev_priv)
-{
-	/*
-	 * The i915 workqueue is primarily used for batched retirement of
-	 * requests (and thus managing bo) once the task has been completed
-	 * by the GPU. i915_gem_retire_requests() is called directly when we
-	 * need high-priority retirement, such as waiting for an explicit
-	 * bo.
-	 *
-	 * It is also used for periodic low-priority events, such as
-	 * idle-timers and recording error state.
-	 *
-	 * All tasks on the workqueue are expected to acquire the dev mutex
-	 * so there is no point in running more than one instance of the
-	 * workqueue at any time.  Use an ordered one.
-	 */
-	dev_priv->wq = alloc_ordered_workqueue("i915", 0);
-	if (dev_priv->wq == NULL)
-		goto out_err;
-
-	dev_priv->hotplug.dp_wq = alloc_ordered_workqueue("i915-dp", 0);
-	if (dev_priv->hotplug.dp_wq == NULL)
-		goto out_free_wq;
-
-	dev_priv->gpu_error.hangcheck_wq =
-		alloc_ordered_workqueue("i915-hangcheck", 0);
-	if (dev_priv->gpu_error.hangcheck_wq == NULL)
-		goto out_free_dp_wq;
-
-	return 0;
-
-out_free_dp_wq:
-	destroy_workqueue(dev_priv->hotplug.dp_wq);
-out_free_wq:
-	destroy_workqueue(dev_priv->wq);
-out_err:
-	DRM_ERROR("Failed to allocate workqueues.\n");
-
-	return -ENOMEM;
-}
-
-static void i915_workqueues_cleanup(struct drm_i915_private *dev_priv)
-{
-	destroy_workqueue(dev_priv->gpu_error.hangcheck_wq);
-	destroy_workqueue(dev_priv->hotplug.dp_wq);
-	destroy_workqueue(dev_priv->wq);
-}
-
-/**
- * i915_driver_init_early - setup state not requiring device access
- * @dev_priv: device private
- *
- * Initialize everything that is a "SW-only" state, that is state not
- * requiring accessing the device or exposing the driver via kernel internal
- * or userspace interfaces. Example steps belonging here: lock initialization,
- * system memory allocation, setting up device specific attributes and
- * function hooks not requiring accessing the device.
- */
-static int i915_driver_init_early(struct drm_i915_private *dev_priv,
-				  struct drm_device *dev,
-				  struct intel_device_info *info)
-{
-	struct intel_device_info *device_info;
-	int ret = 0;
-
-	if (i915_inject_load_failure())
-		return -ENODEV;
-
-	/* Setup the write-once "constant" device info */
-	device_info = (struct intel_device_info *)&dev_priv->info;
-	memcpy(device_info, info, sizeof(dev_priv->info));
-	device_info->device_id = dev->pdev->device;
-
-	spin_lock_init(&dev_priv->irq_lock);
-	spin_lock_init(&dev_priv->gpu_error.lock);
-	mutex_init(&dev_priv->backlight_lock);
-	spin_lock_init(&dev_priv->uncore.lock);
-	spin_lock_init(&dev_priv->mm.object_stat_lock);
-	spin_lock_init(&dev_priv->mmio_flip_lock);
-	mutex_init(&dev_priv->sb_lock);
-	mutex_init(&dev_priv->modeset_restore_lock);
-	mutex_init(&dev_priv->av_mutex);
-	mutex_init(&dev_priv->wm.wm_mutex);
-	mutex_init(&dev_priv->pps_mutex);
-
-	ret = i915_workqueues_init(dev_priv);
-	if (ret < 0)
-		return ret;
-
-	/* This must be called before any calls to HAS_PCH_* */
-	intel_detect_pch(dev);
-
-	intel_pm_setup(dev);
-	intel_init_dpio(dev_priv);
-	intel_power_domains_init(dev_priv);
-	intel_irq_init(dev_priv);
-	intel_init_display_hooks(dev_priv);
-	intel_init_clock_gating_hooks(dev_priv);
-	intel_init_audio_hooks(dev_priv);
-	i915_gem_load_init(dev);
-
-	intel_display_crc_init(dev);
-
-	i915_dump_device_info(dev_priv);
-
-	/* Not all pre-production machines fall into this category, only the
-	 * very first ones. Almost everything should work, except for maybe
-	 * suspend/resume. And we don't implement workarounds that affect only
-	 * pre-production machines. */
-	if (IS_HSW_EARLY_SDV(dev))
-		DRM_INFO("This is an early pre-production Haswell machine. "
-			 "It may not be fully functional.\n");
-
-	return 0;
-}
-
-/**
- * i915_driver_cleanup_early - cleanup the setup done in i915_driver_init_early()
- * @dev_priv: device private
- */
-static void i915_driver_cleanup_early(struct drm_i915_private *dev_priv)
-{
-	i915_gem_load_cleanup(dev_priv->dev);
-	i915_workqueues_cleanup(dev_priv);
-}
-
-static int i915_mmio_setup(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	int mmio_bar;
-	int mmio_size;
-
-	mmio_bar = IS_GEN2(dev) ? 1 : 0;
-	/*
-	 * Before gen4, the registers and the GTT are behind different BARs.
-	 * However, from gen4 onwards, the registers and the GTT are shared
-	 * in the same BAR, so we want to restrict this ioremap from
-	 * clobbering the GTT which we want ioremap_wc instead. Fortunately,
-	 * the register BAR remains the same size for all the earlier
-	 * generations up to Ironlake.
-	 */
-	if (INTEL_INFO(dev)->gen < 5)
-		mmio_size = 512 * 1024;
-	else
-		mmio_size = 2 * 1024 * 1024;
-	dev_priv->regs = pci_iomap(dev->pdev, mmio_bar, mmio_size);
-	if (dev_priv->regs == NULL) {
-		DRM_ERROR("failed to map registers\n");
-
-		return -EIO;
-	}
-
-	/* Try to make sure MCHBAR is enabled before poking at it */
-	intel_setup_mchbar(dev);
-
-	return 0;
-}
-
-static void i915_mmio_cleanup(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	intel_teardown_mchbar(dev);
-	pci_iounmap(dev->pdev, dev_priv->regs);
-}
-
-/**
- * i915_driver_init_mmio - setup device MMIO
- * @dev_priv: device private
- *
- * Setup minimal device state necessary for MMIO accesses later in the
- * initialization sequence. The setup here should avoid any other device-wide
- * side effects or exposing the driver via kernel internal or user space
- * interfaces.
- */
-static int i915_driver_init_mmio(struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = dev_priv->dev;
-	int ret;
-
-	if (i915_inject_load_failure())
-		return -ENODEV;
-
-	if (i915_get_bridge_dev(dev))
-		return -EIO;
-
-	ret = i915_mmio_setup(dev);
-	if (ret < 0)
-		goto put_bridge;
-
-	intel_uncore_init(dev);
-
-	return 0;
-
-put_bridge:
-	pci_dev_put(dev_priv->bridge_dev);
-
-	return ret;
-}
-
-/**
- * i915_driver_cleanup_mmio - cleanup the setup done in i915_driver_init_mmio()
- * @dev_priv: device private
- */
-static void i915_driver_cleanup_mmio(struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = dev_priv->dev;
-
-	intel_uncore_fini(dev);
-	i915_mmio_cleanup(dev);
-	pci_dev_put(dev_priv->bridge_dev);
-}
-
-/**
- * i915_driver_init_hw - setup state requiring device access
- * @dev_priv: device private
- *
- * Setup state that requires accessing the device, but doesn't require
- * exposing the driver via kernel internal or userspace interfaces.
- */
-static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = dev_priv->dev;
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	uint32_t aperture_size;
-	int ret;
-
-	if (i915_inject_load_failure())
-		return -ENODEV;
-
-	intel_device_info_runtime_init(dev);
-
-	ret = i915_ggtt_init_hw(dev);
-	if (ret)
-		return ret;
-
-	ret = i915_ggtt_enable_hw(dev);
-	if (ret) {
-		DRM_ERROR("failed to enable GGTT\n");
-		goto out_ggtt;
-	}
-
-	/* WARNING: Apparently we must kick fbdev drivers before vgacon,
-	 * otherwise the vga fbdev driver falls over. */
-	ret = i915_kick_out_firmware_fb(dev_priv);
-	if (ret) {
-		DRM_ERROR("failed to remove conflicting framebuffer drivers\n");
-		goto out_ggtt;
-	}
-
-	ret = i915_kick_out_vgacon(dev_priv);
-	if (ret) {
-		DRM_ERROR("failed to remove conflicting VGA console\n");
-		goto out_ggtt;
-	}
-
-	pci_set_master(dev->pdev);
-
-	/* overlay on gen2 is broken and can't address above 1G */
-	if (IS_GEN2(dev))
-		dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(30));
-
-	/* 965GM sometimes incorrectly writes to hardware status page (HWS)
-	 * using 32bit addressing, overwriting memory if HWS is located
-	 * above 4GB.
-	 *
-	 * The documentation also mentions an issue with undefined
-	 * behaviour if any general state is accessed within a page above 4GB,
-	 * which also needs to be handled carefully.
-	 */
-	if (IS_BROADWATER(dev) || IS_CRESTLINE(dev))
-		dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(32));
-
-	aperture_size = ggtt->mappable_end;
-
-	ggtt->mappable =
-		io_mapping_create_wc(ggtt->mappable_base,
-				     aperture_size);
-	if (!ggtt->mappable) {
-		ret = -EIO;
-		goto out_ggtt;
-	}
-
-	ggtt->mtrr = arch_phys_wc_add(ggtt->mappable_base,
-					      aperture_size);
-
-	pm_qos_add_request(&dev_priv->pm_qos, PM_QOS_CPU_DMA_LATENCY,
-			   PM_QOS_DEFAULT_VALUE);
-
-	intel_uncore_sanitize(dev);
-
-	intel_opregion_setup(dev);
-
-	i915_gem_load_init_fences(dev_priv);
-
-	/* On the 945G/GM, the chipset reports the MSI capability on the
-	 * integrated graphics even though the support isn't actually there
-	 * according to the published specs.  It doesn't appear to function
-	 * correctly in testing on 945G.
-	 * This may be a side effect of MSI having been made available for PEG
-	 * and the registers being closely associated.
-	 *
-	 * According to chipset errata, on the 965GM, MSI interrupts may
-	 * be lost or delayed, but we use them anyways to avoid
-	 * stuck interrupts on some machines.
-	 */
-	if (!IS_I945G(dev) && !IS_I945GM(dev)) {
-		if (pci_enable_msi(dev->pdev) < 0)
-			DRM_DEBUG_DRIVER("can't enable MSI");
-	}
-
-	return 0;
-
-out_ggtt:
-	i915_ggtt_cleanup_hw(dev);
-
-	return ret;
-}
-
-/**
- * i915_driver_cleanup_hw - cleanup the setup done in i915_driver_init_hw()
- * @dev_priv: device private
- */
-static void i915_driver_cleanup_hw(struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = dev_priv->dev;
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-
-	if (dev->pdev->msi_enabled)
-		pci_disable_msi(dev->pdev);
-
-	pm_qos_remove_request(&dev_priv->pm_qos);
-	arch_phys_wc_del(ggtt->mtrr);
-	io_mapping_free(ggtt->mappable);
-	i915_ggtt_cleanup_hw(dev);
-}
-
-/**
- * i915_driver_register - register the driver with the rest of the system
- * @dev_priv: device private
- *
- * Perform any steps necessary to make the driver available via kernel
- * internal or userspace interfaces.
- */
-static void i915_driver_register(struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = dev_priv->dev;
-
-	i915_gem_shrinker_init(dev_priv);
-	/*
-	 * Notify a valid surface after modesetting,
-	 * when running inside a VM.
-	 */
-	if (intel_vgpu_active(dev))
-		I915_WRITE(vgtif_reg(display_ready), VGT_DRV_DISPLAY_READY);
-
-	i915_setup_sysfs(dev);
-
-	if (INTEL_INFO(dev_priv)->num_pipes) {
-		/* Must be done after probing outputs */
-		intel_opregion_init(dev);
-		acpi_video_register();
-	}
-
-	if (IS_GEN5(dev_priv))
-		intel_gpu_ips_init(dev_priv);
-
-	i915_audio_component_init(dev_priv);
-}
-
-/**
- * i915_driver_unregister - cleanup the registration done in i915_driver_regiser()
- * @dev_priv: device private
- */
-static void i915_driver_unregister(struct drm_i915_private *dev_priv)
-{
-	i915_audio_component_cleanup(dev_priv);
-	intel_gpu_ips_teardown();
-	acpi_video_unregister();
-	intel_opregion_fini(dev_priv->dev);
-	i915_teardown_sysfs(dev_priv->dev);
-	i915_gem_shrinker_cleanup(dev_priv);
-}
-
-/**
- * i915_driver_load - setup chip and create an initial config
- * @dev: DRM device
- * @flags: startup flags
- *
- * The driver load routine has to do several things:
- *   - drive output discovery via intel_modeset_init()
- *   - initialize the memory manager
- *   - allocate initial config memory
- *   - setup the DRM framebuffer with the allocated memory
- */
-int i915_driver_load(struct drm_device *dev, unsigned long flags)
-{
-	struct drm_i915_private *dev_priv;
-	int ret = 0;
-
-	dev_priv = kzalloc(sizeof(*dev_priv), GFP_KERNEL);
-	if (dev_priv == NULL)
-		return -ENOMEM;
-
-	dev->dev_private = dev_priv;
-	/* Must be set before calling __i915_printk */
-	dev_priv->dev = dev;
-
-	ret = i915_driver_init_early(dev_priv, dev,
-				     (struct intel_device_info *)flags);
-
-	if (ret < 0)
-		goto out_free_priv;
-
-	intel_runtime_pm_get(dev_priv);
-
-	ret = i915_driver_init_mmio(dev_priv);
-	if (ret < 0)
-		goto out_runtime_pm_put;
-
-	ret = i915_driver_init_hw(dev_priv);
-	if (ret < 0)
-		goto out_cleanup_mmio;
-
-	/*
-	 * TODO: move the vblank init and parts of modeset init steps into one
-	 * of the i915_driver_init_/i915_driver_register functions according
-	 * to the role/effect of the given init step.
-	 */
-	if (INTEL_INFO(dev)->num_pipes) {
-		ret = drm_vblank_init(dev, INTEL_INFO(dev)->num_pipes);
-		if (ret)
-			goto out_cleanup_hw;
-	}
-
-	ret = i915_load_modeset_init(dev);
-	if (ret < 0)
-		goto out_cleanup_vblank;
-
-	i915_driver_register(dev_priv);
-
-	intel_runtime_pm_enable(dev_priv);
-
-	intel_runtime_pm_put(dev_priv);
-
-	return 0;
-
-out_cleanup_vblank:
-	drm_vblank_cleanup(dev);
-out_cleanup_hw:
-	i915_driver_cleanup_hw(dev_priv);
-out_cleanup_mmio:
-	i915_driver_cleanup_mmio(dev_priv);
-out_runtime_pm_put:
-	intel_runtime_pm_put(dev_priv);
-	i915_driver_cleanup_early(dev_priv);
-out_free_priv:
-	i915_load_error(dev_priv, "Device initialization failed (%d)\n", ret);
-
-	kfree(dev_priv);
-
-	return ret;
-}
-
-int i915_driver_unload(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret;
-
-	intel_fbdev_fini(dev);
-
-	ret = i915_gem_suspend(dev);
-	if (ret) {
-		DRM_ERROR("failed to idle hardware: %d\n", ret);
-		return ret;
-	}
-
-	intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
-
-	i915_driver_unregister(dev_priv);
-
-	drm_vblank_cleanup(dev);
-
-	intel_modeset_cleanup(dev);
-
-	/*
-	 * free the memory space allocated for the child device
-	 * config parsed from VBT
-	 */
-	if (dev_priv->vbt.child_dev && dev_priv->vbt.child_dev_num) {
-		kfree(dev_priv->vbt.child_dev);
-		dev_priv->vbt.child_dev = NULL;
-		dev_priv->vbt.child_dev_num = 0;
-	}
-	kfree(dev_priv->vbt.sdvo_lvds_vbt_mode);
-	dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
-	kfree(dev_priv->vbt.lfp_lvds_vbt_mode);
-	dev_priv->vbt.lfp_lvds_vbt_mode = NULL;
-
-	vga_switcheroo_unregister_client(dev->pdev);
-	vga_client_register(dev->pdev, NULL, NULL, NULL);
-
-	intel_csr_ucode_fini(dev_priv);
-
-	/* Free error state after interrupts are fully disabled. */
-	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
-	i915_destroy_error_state(dev);
-
-	/* Flush any outstanding unpin_work. */
-	flush_workqueue(dev_priv->wq);
-
-	intel_guc_ucode_fini(dev);
-	mutex_lock(&dev->struct_mutex);
-	i915_gem_cleanup_engines(dev);
-	i915_gem_context_fini(dev);
-	mutex_unlock(&dev->struct_mutex);
-	intel_fbc_cleanup_cfb(dev_priv);
-
-	intel_power_domains_fini(dev_priv);
-
-	i915_driver_cleanup_hw(dev_priv);
-	i915_driver_cleanup_mmio(dev_priv);
-
-	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
-
-	i915_driver_cleanup_early(dev_priv);
-	kfree(dev_priv);
-
-	return 0;
-}
-
-int i915_driver_open(struct drm_device *dev, struct drm_file *file)
-{
-	int ret;
-
-	ret = i915_gem_open(dev, file);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-/**
- * i915_driver_lastclose - clean up after all DRM clients have exited
- * @dev: DRM device
- *
- * Take care of cleaning up after all DRM clients have exited.  In the
- * mode setting case, we want to restore the kernel's initial mode (just
- * in case the last client left us in a bad state).
- *
- * Additionally, in the non-mode setting case, we'll tear down the GTT
- * and DMA structures, since the kernel won't be using them, and clea
- * up any GEM state.
- */
-void i915_driver_lastclose(struct drm_device *dev)
-{
-	intel_fbdev_restore_mode(dev);
-	vga_switcheroo_process_delayed_switch();
-}
-
-void i915_driver_preclose(struct drm_device *dev, struct drm_file *file)
-{
-	mutex_lock(&dev->struct_mutex);
-	i915_gem_context_close(dev, file);
-	i915_gem_release(dev, file);
-	mutex_unlock(&dev->struct_mutex);
-}
-
-void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
-{
-	struct drm_i915_file_private *file_priv = file->driver_priv;
-
-	kfree(file_priv);
-}
-
-static int
-i915_gem_reject_pin_ioctl(struct drm_device *dev, void *data,
-			  struct drm_file *file)
-{
-	return -ENODEV;
-}
-
-const struct drm_ioctl_desc i915_ioctls[] = {
-	DRM_IOCTL_DEF_DRV(I915_INIT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_FLUSH, drm_noop, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_FLIP, drm_noop, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_BATCHBUFFER, drm_noop, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_IRQ_EMIT, drm_noop, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_IRQ_WAIT, drm_noop, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_GETPARAM, i915_getparam, DRM_AUTH|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_SETPARAM, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_ALLOC, drm_noop, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_FREE, drm_noop, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_INIT_HEAP, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_CMDBUFFER, drm_noop, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_DESTROY_HEAP,  drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_SET_VBLANK_PIPE,  drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_GET_VBLANK_PIPE,  drm_noop, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_VBLANK_SWAP, drm_noop, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_HWS_ADDR, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_GEM_INIT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER, i915_gem_execbuffer, DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER2, i915_gem_execbuffer2, DRM_AUTH|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_PIN, i915_gem_reject_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_GEM_UNPIN, i915_gem_reject_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_GEM_BUSY, i915_gem_busy_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_SET_CACHING, i915_gem_set_caching_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_GET_CACHING, i915_gem_get_caching_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_THROTTLE, i915_gem_throttle_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_ENTERVT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_GEM_LEAVEVT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(I915_GEM_CREATE, i915_gem_create_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_PREAD, i915_gem_pread_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_PWRITE, i915_gem_pwrite_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP, i915_gem_mmap_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP_GTT, i915_gem_mmap_gtt_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_SET_DOMAIN, i915_gem_set_domain_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_SET_TILING, i915_gem_set_tiling, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_GET_TILING, i915_gem_get_tiling, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_GET_APERTURE, i915_gem_get_aperture_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GET_PIPE_FROM_CRTC_ID, intel_get_pipe_from_crtc_id, 0),
-	DRM_IOCTL_DEF_DRV(I915_GEM_MADVISE, i915_gem_madvise_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image, DRM_MASTER|DRM_CONTROL_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_OVERLAY_ATTRS, intel_overlay_attrs, DRM_MASTER|DRM_CONTROL_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_SET_SPRITE_COLORKEY, intel_sprite_set_colorkey, DRM_MASTER|DRM_CONTROL_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GET_SPRITE_COLORKEY, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_WAIT, i915_gem_wait_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE, i915_gem_context_create_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GET_RESET_STATS, i915_get_reset_stats_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_USERPTR, i915_gem_userptr_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_GETPARAM, i915_gem_context_getparam_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_SETPARAM, i915_gem_context_setparam_ioctl, DRM_RENDER_ALLOW),
-};
-
-int i915_max_ioctl = ARRAY_SIZE(i915_ioctls);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 85c4debf47e0..95ddd56b89f0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -27,400 +27,92 @@
  *
  */
 
-#include <linux/device.h>
 #include <linux/acpi.h>
-#include <drm/drmP.h>
-#include <drm/i915_drm.h>
-#include "i915_drv.h"
-#include "i915_trace.h"
-#include "intel_drv.h"
-
-#include <linux/apple-gmux.h>
-#include <linux/console.h>
+#include <linux/device.h>
+#include <linux/oom.h>
 #include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pm.h>
 #include <linux/pm_runtime.h>
+#include <linux/pnp.h>
+#include <linux/slab.h>
 #include <linux/vgaarb.h>
 #include <linux/vga_switcheroo.h>
-#include <drm/drm_crtc_helper.h>
-
-static struct drm_driver driver;
-
-#define GEN_DEFAULT_PIPEOFFSETS \
-	.pipe_offsets = { PIPE_A_OFFSET, PIPE_B_OFFSET, \
-			  PIPE_C_OFFSET, PIPE_EDP_OFFSET }, \
-	.trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \
-			   TRANSCODER_C_OFFSET, TRANSCODER_EDP_OFFSET }, \
-	.palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET }
-
-#define GEN_CHV_PIPEOFFSETS \
-	.pipe_offsets = { PIPE_A_OFFSET, PIPE_B_OFFSET, \
-			  CHV_PIPE_C_OFFSET }, \
-	.trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \
-			   CHV_TRANSCODER_C_OFFSET, }, \
-	.palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET, \
-			     CHV_PALETTE_C_OFFSET }
-
-#define CURSOR_OFFSETS \
-	.cursor_offsets = { CURSOR_A_OFFSET, CURSOR_B_OFFSET, CHV_CURSOR_C_OFFSET }
-
-#define IVB_CURSOR_OFFSETS \
-	.cursor_offsets = { CURSOR_A_OFFSET, IVB_CURSOR_B_OFFSET, IVB_CURSOR_C_OFFSET }
-
-#define BDW_COLORS \
-	.color = { .degamma_lut_size = 512, .gamma_lut_size = 512 }
-#define CHV_COLORS \
-	.color = { .degamma_lut_size = 65, .gamma_lut_size = 257 }
-
-static const struct intel_device_info intel_i830_info = {
-	.gen = 2, .is_mobile = 1, .cursor_needs_physical = 1, .num_pipes = 2,
-	.has_overlay = 1, .overlay_needs_physical = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_845g_info = {
-	.gen = 2, .num_pipes = 1,
-	.has_overlay = 1, .overlay_needs_physical = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_i85x_info = {
-	.gen = 2, .is_i85x = 1, .is_mobile = 1, .num_pipes = 2,
-	.cursor_needs_physical = 1,
-	.has_overlay = 1, .overlay_needs_physical = 1,
-	.has_fbc = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_i865g_info = {
-	.gen = 2, .num_pipes = 1,
-	.has_overlay = 1, .overlay_needs_physical = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_i915g_info = {
-	.gen = 3, .is_i915g = 1, .cursor_needs_physical = 1, .num_pipes = 2,
-	.has_overlay = 1, .overlay_needs_physical = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-static const struct intel_device_info intel_i915gm_info = {
-	.gen = 3, .is_mobile = 1, .num_pipes = 2,
-	.cursor_needs_physical = 1,
-	.has_overlay = 1, .overlay_needs_physical = 1,
-	.supports_tv = 1,
-	.has_fbc = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-static const struct intel_device_info intel_i945g_info = {
-	.gen = 3, .has_hotplug = 1, .cursor_needs_physical = 1, .num_pipes = 2,
-	.has_overlay = 1, .overlay_needs_physical = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-static const struct intel_device_info intel_i945gm_info = {
-	.gen = 3, .is_i945gm = 1, .is_mobile = 1, .num_pipes = 2,
-	.has_hotplug = 1, .cursor_needs_physical = 1,
-	.has_overlay = 1, .overlay_needs_physical = 1,
-	.supports_tv = 1,
-	.has_fbc = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_i965g_info = {
-	.gen = 4, .is_broadwater = 1, .num_pipes = 2,
-	.has_hotplug = 1,
-	.has_overlay = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_i965gm_info = {
-	.gen = 4, .is_crestline = 1, .num_pipes = 2,
-	.is_mobile = 1, .has_fbc = 1, .has_hotplug = 1,
-	.has_overlay = 1,
-	.supports_tv = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_g33_info = {
-	.gen = 3, .is_g33 = 1, .num_pipes = 2,
-	.need_gfx_hws = 1, .has_hotplug = 1,
-	.has_overlay = 1,
-	.ring_mask = RENDER_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_g45_info = {
-	.gen = 4, .is_g4x = 1, .need_gfx_hws = 1, .num_pipes = 2,
-	.has_pipe_cxsr = 1, .has_hotplug = 1,
-	.ring_mask = RENDER_RING | BSD_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_gm45_info = {
-	.gen = 4, .is_g4x = 1, .num_pipes = 2,
-	.is_mobile = 1, .need_gfx_hws = 1, .has_fbc = 1,
-	.has_pipe_cxsr = 1, .has_hotplug = 1,
-	.supports_tv = 1,
-	.ring_mask = RENDER_RING | BSD_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_pineview_info = {
-	.gen = 3, .is_g33 = 1, .is_pineview = 1, .is_mobile = 1, .num_pipes = 2,
-	.need_gfx_hws = 1, .has_hotplug = 1,
-	.has_overlay = 1,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_ironlake_d_info = {
-	.gen = 5, .num_pipes = 2,
-	.need_gfx_hws = 1, .has_hotplug = 1,
-	.ring_mask = RENDER_RING | BSD_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
+#include <linux/vt.h>
+#include <acpi/video.h>
 
-static const struct intel_device_info intel_ironlake_m_info = {
-	.gen = 5, .is_mobile = 1, .num_pipes = 2,
-	.need_gfx_hws = 1, .has_hotplug = 1,
-	.has_fbc = 1,
-	.ring_mask = RENDER_RING | BSD_RING,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_sandybridge_d_info = {
-	.gen = 6, .num_pipes = 2,
-	.need_gfx_hws = 1, .has_hotplug = 1,
-	.has_fbc = 1,
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING,
-	.has_llc = 1,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-static const struct intel_device_info intel_sandybridge_m_info = {
-	.gen = 6, .is_mobile = 1, .num_pipes = 2,
-	.need_gfx_hws = 1, .has_hotplug = 1,
-	.has_fbc = 1,
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING,
-	.has_llc = 1,
-	GEN_DEFAULT_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-};
-
-#define GEN7_FEATURES  \
-	.gen = 7, .num_pipes = 3, \
-	.need_gfx_hws = 1, .has_hotplug = 1, \
-	.has_fbc = 1, \
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING, \
-	.has_llc = 1, \
-	GEN_DEFAULT_PIPEOFFSETS, \
-	IVB_CURSOR_OFFSETS
-
-static const struct intel_device_info intel_ivybridge_d_info = {
-	GEN7_FEATURES,
-	.is_ivybridge = 1,
-};
-
-static const struct intel_device_info intel_ivybridge_m_info = {
-	GEN7_FEATURES,
-	.is_ivybridge = 1,
-	.is_mobile = 1,
-};
-
-static const struct intel_device_info intel_ivybridge_q_info = {
-	GEN7_FEATURES,
-	.is_ivybridge = 1,
-	.num_pipes = 0, /* legal, last one wins */
-};
-
-#define VLV_FEATURES  \
-	.gen = 7, .num_pipes = 2, \
-	.need_gfx_hws = 1, .has_hotplug = 1, \
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING, \
-	.display_mmio_offset = VLV_DISPLAY_BASE, \
-	GEN_DEFAULT_PIPEOFFSETS, \
-	CURSOR_OFFSETS
-
-static const struct intel_device_info intel_valleyview_m_info = {
-	VLV_FEATURES,
-	.is_valleyview = 1,
-	.is_mobile = 1,
-};
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/i915_drm.h>
 
-static const struct intel_device_info intel_valleyview_d_info = {
-	VLV_FEATURES,
-	.is_valleyview = 1,
-};
+#include "i915_drv.h"
+#include "i915_trace.h"
+#include "i915_vgpu.h"
+#include "intel_drv.h"
 
-#define HSW_FEATURES  \
-	GEN7_FEATURES, \
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, \
-	.has_ddi = 1, \
-	.has_fpga_dbg = 1
+static struct drm_driver driver;
 
-static const struct intel_device_info intel_haswell_d_info = {
-	HSW_FEATURES,
-	.is_haswell = 1,
-};
+static unsigned int i915_load_fail_count;
 
-static const struct intel_device_info intel_haswell_m_info = {
-	HSW_FEATURES,
-	.is_haswell = 1,
-	.is_mobile = 1,
-};
+bool __i915_inject_load_failure(const char *func, int line)
+{
+	if (i915_load_fail_count >= i915.inject_load_failure)
+		return false;
 
-#define BDW_FEATURES \
-	HSW_FEATURES, \
-	BDW_COLORS
+	if (++i915_load_fail_count == i915.inject_load_failure) {
+		DRM_INFO("Injecting failure at checkpoint %u [%s:%d]\n",
+			 i915.inject_load_failure, func, line);
+		return true;
+	}
 
-static const struct intel_device_info intel_broadwell_d_info = {
-	BDW_FEATURES,
-	.gen = 8,
-};
+	return false;
+}
 
-static const struct intel_device_info intel_broadwell_m_info = {
-	BDW_FEATURES,
-	.gen = 8, .is_mobile = 1,
-};
+#define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI"
+#define FDO_BUG_MSG "Please file a bug at " FDO_BUG_URL " against DRM/Intel " \
+		    "providing the dmesg log by booting with drm.debug=0xf"
 
-static const struct intel_device_info intel_broadwell_gt3d_info = {
-	BDW_FEATURES,
-	.gen = 8,
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
-};
+void
+__i915_printk(struct drm_i915_private *dev_priv, const char *level,
+	      const char *fmt, ...)
+{
+	static bool shown_bug_once;
+	struct device *dev = dev_priv->drm.dev;
+	bool is_error = level[1] <= KERN_ERR[1];
+	bool is_debug = level[1] == KERN_DEBUG[1];
+	struct va_format vaf;
+	va_list args;
+
+	if (is_debug && !(drm_debug & DRM_UT_DRIVER))
+		return;
 
-static const struct intel_device_info intel_broadwell_gt3m_info = {
-	BDW_FEATURES,
-	.gen = 8, .is_mobile = 1,
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
-};
+	va_start(args, fmt);
 
-static const struct intel_device_info intel_cherryview_info = {
-	.gen = 8, .num_pipes = 3,
-	.need_gfx_hws = 1, .has_hotplug = 1,
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
-	.is_cherryview = 1,
-	.display_mmio_offset = VLV_DISPLAY_BASE,
-	GEN_CHV_PIPEOFFSETS,
-	CURSOR_OFFSETS,
-	CHV_COLORS,
-};
+	vaf.fmt = fmt;
+	vaf.va = &args;
 
-static const struct intel_device_info intel_skylake_info = {
-	BDW_FEATURES,
-	.is_skylake = 1,
-	.gen = 9,
-};
+	dev_printk(level, dev, "[" DRM_NAME ":%ps] %pV",
+		   __builtin_return_address(0), &vaf);
 
-static const struct intel_device_info intel_skylake_gt3_info = {
-	BDW_FEATURES,
-	.is_skylake = 1,
-	.gen = 9,
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
-};
+	if (is_error && !shown_bug_once) {
+		dev_notice(dev, "%s", FDO_BUG_MSG);
+		shown_bug_once = true;
+	}
 
-static const struct intel_device_info intel_broxton_info = {
-	.is_preliminary = 1,
-	.is_broxton = 1,
-	.gen = 9,
-	.need_gfx_hws = 1, .has_hotplug = 1,
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
-	.num_pipes = 3,
-	.has_ddi = 1,
-	.has_fpga_dbg = 1,
-	.has_fbc = 1,
-	GEN_DEFAULT_PIPEOFFSETS,
-	IVB_CURSOR_OFFSETS,
-	BDW_COLORS,
-};
+	va_end(args);
+}
 
-static const struct intel_device_info intel_kabylake_info = {
-	BDW_FEATURES,
-	.is_kabylake = 1,
-	.gen = 9,
-};
+static bool i915_error_injected(struct drm_i915_private *dev_priv)
+{
+	return i915.inject_load_failure &&
+	       i915_load_fail_count == i915.inject_load_failure;
+}
 
-static const struct intel_device_info intel_kabylake_gt3_info = {
-	BDW_FEATURES,
-	.is_kabylake = 1,
-	.gen = 9,
-	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
-};
+#define i915_load_error(dev_priv, fmt, ...)				     \
+	__i915_printk(dev_priv,						     \
+		      i915_error_injected(dev_priv) ? KERN_DEBUG : KERN_ERR, \
+		      fmt, ##__VA_ARGS__)
 
-/*
- * Make sure any device matches here are from most specific to most
- * general.  For example, since the Quanta match is based on the subsystem
- * and subvendor IDs, we need it to come before the more general IVB
- * PCI ID matches, otherwise we'll use the wrong info struct above.
- */
-static const struct pci_device_id pciidlist[] = {
-	INTEL_I830_IDS(&intel_i830_info),
-	INTEL_I845G_IDS(&intel_845g_info),
-	INTEL_I85X_IDS(&intel_i85x_info),
-	INTEL_I865G_IDS(&intel_i865g_info),
-	INTEL_I915G_IDS(&intel_i915g_info),
-	INTEL_I915GM_IDS(&intel_i915gm_info),
-	INTEL_I945G_IDS(&intel_i945g_info),
-	INTEL_I945GM_IDS(&intel_i945gm_info),
-	INTEL_I965G_IDS(&intel_i965g_info),
-	INTEL_G33_IDS(&intel_g33_info),
-	INTEL_I965GM_IDS(&intel_i965gm_info),
-	INTEL_GM45_IDS(&intel_gm45_info),
-	INTEL_G45_IDS(&intel_g45_info),
-	INTEL_PINEVIEW_IDS(&intel_pineview_info),
-	INTEL_IRONLAKE_D_IDS(&intel_ironlake_d_info),
-	INTEL_IRONLAKE_M_IDS(&intel_ironlake_m_info),
-	INTEL_SNB_D_IDS(&intel_sandybridge_d_info),
-	INTEL_SNB_M_IDS(&intel_sandybridge_m_info),
-	INTEL_IVB_Q_IDS(&intel_ivybridge_q_info), /* must be first IVB */
-	INTEL_IVB_M_IDS(&intel_ivybridge_m_info),
-	INTEL_IVB_D_IDS(&intel_ivybridge_d_info),
-	INTEL_HSW_D_IDS(&intel_haswell_d_info),
-	INTEL_HSW_M_IDS(&intel_haswell_m_info),
-	INTEL_VLV_M_IDS(&intel_valleyview_m_info),
-	INTEL_VLV_D_IDS(&intel_valleyview_d_info),
-	INTEL_BDW_GT12M_IDS(&intel_broadwell_m_info),
-	INTEL_BDW_GT12D_IDS(&intel_broadwell_d_info),
-	INTEL_BDW_GT3M_IDS(&intel_broadwell_gt3m_info),
-	INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info),
-	INTEL_CHV_IDS(&intel_cherryview_info),
-	INTEL_SKL_GT1_IDS(&intel_skylake_info),
-	INTEL_SKL_GT2_IDS(&intel_skylake_info),
-	INTEL_SKL_GT3_IDS(&intel_skylake_gt3_info),
-	INTEL_SKL_GT4_IDS(&intel_skylake_gt3_info),
-	INTEL_BXT_IDS(&intel_broxton_info),
-	INTEL_KBL_GT1_IDS(&intel_kabylake_info),
-	INTEL_KBL_GT2_IDS(&intel_kabylake_info),
-	INTEL_KBL_GT3_IDS(&intel_kabylake_gt3_info),
-	INTEL_KBL_GT4_IDS(&intel_kabylake_gt3_info),
-	{0, 0, 0}
-};
-
-MODULE_DEVICE_TABLE(pci, pciidlist);
 
 static enum intel_pch intel_virt_detect_pch(struct drm_device *dev)
 {
@@ -450,9 +142,9 @@ static enum intel_pch intel_virt_detect_pch(struct drm_device *dev)
 	return ret;
 }
 
-void intel_detect_pch(struct drm_device *dev)
+static void intel_detect_pch(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct pci_dev *pch = NULL;
 
 	/* In all current cases, num_pipes is equivalent to the PCH_NOP setting
@@ -519,8 +211,10 @@ void intel_detect_pch(struct drm_device *dev)
 			} else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) ||
 				   (id == INTEL_PCH_P3X_DEVICE_ID_TYPE) ||
 				   ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) &&
-				    pch->subsystem_vendor == 0x1af4 &&
-				    pch->subsystem_device == 0x1100)) {
+				    pch->subsystem_vendor ==
+					    PCI_SUBVENDOR_ID_REDHAT_QUMRANET &&
+				    pch->subsystem_device ==
+					    PCI_SUBDEVICE_ID_QEMU)) {
 				dev_priv->pch_type = intel_virt_detect_pch(dev);
 			} else
 				continue;
@@ -534,9 +228,9 @@ void intel_detect_pch(struct drm_device *dev)
 	pci_dev_put(pch);
 }
 
-bool i915_semaphore_is_enabled(struct drm_device *dev)
+bool i915_semaphore_is_enabled(struct drm_i915_private *dev_priv)
 {
-	if (INTEL_INFO(dev)->gen < 6)
+	if (INTEL_GEN(dev_priv) < 6)
 		return false;
 
 	if (i915.semaphores >= 0)
@@ -546,22 +240,1172 @@ bool i915_semaphore_is_enabled(struct drm_device *dev)
 	if (i915.enable_execlists)
 		return false;
 
-	/* Until we get further testing... */
-	if (IS_GEN8(dev))
-		return false;
-
 #ifdef CONFIG_INTEL_IOMMU
 	/* Enable semaphores on SNB when IO remapping is off */
-	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped)
+	if (IS_GEN6(dev_priv) && intel_iommu_gfx_mapped)
 		return false;
 #endif
 
 	return true;
 }
 
+static int i915_getparam(struct drm_device *dev, void *data,
+			 struct drm_file *file_priv)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	drm_i915_getparam_t *param = data;
+	int value;
+
+	switch (param->param) {
+	case I915_PARAM_IRQ_ACTIVE:
+	case I915_PARAM_ALLOW_BATCHBUFFER:
+	case I915_PARAM_LAST_DISPATCH:
+		/* Reject all old ums/dri params. */
+		return -ENODEV;
+	case I915_PARAM_CHIPSET_ID:
+		value = dev->pdev->device;
+		break;
+	case I915_PARAM_REVISION:
+		value = dev->pdev->revision;
+		break;
+	case I915_PARAM_HAS_GEM:
+		value = 1;
+		break;
+	case I915_PARAM_NUM_FENCES_AVAIL:
+		value = dev_priv->num_fence_regs;
+		break;
+	case I915_PARAM_HAS_OVERLAY:
+		value = dev_priv->overlay ? 1 : 0;
+		break;
+	case I915_PARAM_HAS_PAGEFLIPPING:
+		value = 1;
+		break;
+	case I915_PARAM_HAS_EXECBUF2:
+		/* depends on GEM */
+		value = 1;
+		break;
+	case I915_PARAM_HAS_BSD:
+		value = intel_engine_initialized(&dev_priv->engine[VCS]);
+		break;
+	case I915_PARAM_HAS_BLT:
+		value = intel_engine_initialized(&dev_priv->engine[BCS]);
+		break;
+	case I915_PARAM_HAS_VEBOX:
+		value = intel_engine_initialized(&dev_priv->engine[VECS]);
+		break;
+	case I915_PARAM_HAS_BSD2:
+		value = intel_engine_initialized(&dev_priv->engine[VCS2]);
+		break;
+	case I915_PARAM_HAS_RELAXED_FENCING:
+		value = 1;
+		break;
+	case I915_PARAM_HAS_COHERENT_RINGS:
+		value = 1;
+		break;
+	case I915_PARAM_HAS_EXEC_CONSTANTS:
+		value = INTEL_INFO(dev)->gen >= 4;
+		break;
+	case I915_PARAM_HAS_RELAXED_DELTA:
+		value = 1;
+		break;
+	case I915_PARAM_HAS_GEN7_SOL_RESET:
+		value = 1;
+		break;
+	case I915_PARAM_HAS_LLC:
+		value = HAS_LLC(dev);
+		break;
+	case I915_PARAM_HAS_WT:
+		value = HAS_WT(dev);
+		break;
+	case I915_PARAM_HAS_ALIASING_PPGTT:
+		value = USES_PPGTT(dev);
+		break;
+	case I915_PARAM_HAS_WAIT_TIMEOUT:
+		value = 1;
+		break;
+	case I915_PARAM_HAS_SEMAPHORES:
+		value = i915_semaphore_is_enabled(dev_priv);
+		break;
+	case I915_PARAM_HAS_PRIME_VMAP_FLUSH:
+		value = 1;
+		break;
+	case I915_PARAM_HAS_SECURE_BATCHES:
+		value = capable(CAP_SYS_ADMIN);
+		break;
+	case I915_PARAM_HAS_PINNED_BATCHES:
+		value = 1;
+		break;
+	case I915_PARAM_HAS_EXEC_NO_RELOC:
+		value = 1;
+		break;
+	case I915_PARAM_HAS_EXEC_HANDLE_LUT:
+		value = 1;
+		break;
+	case I915_PARAM_CMD_PARSER_VERSION:
+		value = i915_cmd_parser_get_version(dev_priv);
+		break;
+	case I915_PARAM_HAS_COHERENT_PHYS_GTT:
+		value = 1;
+		break;
+	case I915_PARAM_MMAP_VERSION:
+		value = 1;
+		break;
+	case I915_PARAM_SUBSLICE_TOTAL:
+		value = INTEL_INFO(dev)->subslice_total;
+		if (!value)
+			return -ENODEV;
+		break;
+	case I915_PARAM_EU_TOTAL:
+		value = INTEL_INFO(dev)->eu_total;
+		if (!value)
+			return -ENODEV;
+		break;
+	case I915_PARAM_HAS_GPU_RESET:
+		value = i915.enable_hangcheck && intel_has_gpu_reset(dev_priv);
+		break;
+	case I915_PARAM_HAS_RESOURCE_STREAMER:
+		value = HAS_RESOURCE_STREAMER(dev);
+		break;
+	case I915_PARAM_HAS_EXEC_SOFTPIN:
+		value = 1;
+		break;
+	case I915_PARAM_HAS_POOLED_EU:
+		value = HAS_POOLED_EU(dev);
+		break;
+	case I915_PARAM_MIN_EU_IN_POOL:
+		value = INTEL_INFO(dev)->min_eu_in_pool;
+		break;
+	default:
+		DRM_DEBUG("Unknown parameter %d\n", param->param);
+		return -EINVAL;
+	}
+
+	if (put_user(value, param->value))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int i915_get_bridge_dev(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	dev_priv->bridge_dev = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0));
+	if (!dev_priv->bridge_dev) {
+		DRM_ERROR("bridge device not found\n");
+		return -1;
+	}
+	return 0;
+}
+
+/* Allocate space for the MCH regs if needed, return nonzero on error */
+static int
+intel_alloc_mchbar_resource(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int reg = INTEL_INFO(dev)->gen >= 4 ? MCHBAR_I965 : MCHBAR_I915;
+	u32 temp_lo, temp_hi = 0;
+	u64 mchbar_addr;
+	int ret;
+
+	if (INTEL_INFO(dev)->gen >= 4)
+		pci_read_config_dword(dev_priv->bridge_dev, reg + 4, &temp_hi);
+	pci_read_config_dword(dev_priv->bridge_dev, reg, &temp_lo);
+	mchbar_addr = ((u64)temp_hi << 32) | temp_lo;
+
+	/* If ACPI doesn't have it, assume we need to allocate it ourselves */
+#ifdef CONFIG_PNP
+	if (mchbar_addr &&
+	    pnp_range_reserved(mchbar_addr, mchbar_addr + MCHBAR_SIZE))
+		return 0;
+#endif
+
+	/* Get some space for it */
+	dev_priv->mch_res.name = "i915 MCHBAR";
+	dev_priv->mch_res.flags = IORESOURCE_MEM;
+	ret = pci_bus_alloc_resource(dev_priv->bridge_dev->bus,
+				     &dev_priv->mch_res,
+				     MCHBAR_SIZE, MCHBAR_SIZE,
+				     PCIBIOS_MIN_MEM,
+				     0, pcibios_align_resource,
+				     dev_priv->bridge_dev);
+	if (ret) {
+		DRM_DEBUG_DRIVER("failed bus alloc: %d\n", ret);
+		dev_priv->mch_res.start = 0;
+		return ret;
+	}
+
+	if (INTEL_INFO(dev)->gen >= 4)
+		pci_write_config_dword(dev_priv->bridge_dev, reg + 4,
+				       upper_32_bits(dev_priv->mch_res.start));
+
+	pci_write_config_dword(dev_priv->bridge_dev, reg,
+			       lower_32_bits(dev_priv->mch_res.start));
+	return 0;
+}
+
+/* Setup MCHBAR if possible, return true if we should disable it again */
+static void
+intel_setup_mchbar(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int mchbar_reg = INTEL_INFO(dev)->gen >= 4 ? MCHBAR_I965 : MCHBAR_I915;
+	u32 temp;
+	bool enabled;
+
+	if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))
+		return;
+
+	dev_priv->mchbar_need_disable = false;
+
+	if (IS_I915G(dev) || IS_I915GM(dev)) {
+		pci_read_config_dword(dev_priv->bridge_dev, DEVEN, &temp);
+		enabled = !!(temp & DEVEN_MCHBAR_EN);
+	} else {
+		pci_read_config_dword(dev_priv->bridge_dev, mchbar_reg, &temp);
+		enabled = temp & 1;
+	}
+
+	/* If it's already enabled, don't have to do anything */
+	if (enabled)
+		return;
+
+	if (intel_alloc_mchbar_resource(dev))
+		return;
+
+	dev_priv->mchbar_need_disable = true;
+
+	/* Space is allocated or reserved, so enable it. */
+	if (IS_I915G(dev) || IS_I915GM(dev)) {
+		pci_write_config_dword(dev_priv->bridge_dev, DEVEN,
+				       temp | DEVEN_MCHBAR_EN);
+	} else {
+		pci_read_config_dword(dev_priv->bridge_dev, mchbar_reg, &temp);
+		pci_write_config_dword(dev_priv->bridge_dev, mchbar_reg, temp | 1);
+	}
+}
+
+static void
+intel_teardown_mchbar(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int mchbar_reg = INTEL_INFO(dev)->gen >= 4 ? MCHBAR_I965 : MCHBAR_I915;
+
+	if (dev_priv->mchbar_need_disable) {
+		if (IS_I915G(dev) || IS_I915GM(dev)) {
+			u32 deven_val;
+
+			pci_read_config_dword(dev_priv->bridge_dev, DEVEN,
+					      &deven_val);
+			deven_val &= ~DEVEN_MCHBAR_EN;
+			pci_write_config_dword(dev_priv->bridge_dev, DEVEN,
+					       deven_val);
+		} else {
+			u32 mchbar_val;
+
+			pci_read_config_dword(dev_priv->bridge_dev, mchbar_reg,
+					      &mchbar_val);
+			mchbar_val &= ~1;
+			pci_write_config_dword(dev_priv->bridge_dev, mchbar_reg,
+					       mchbar_val);
+		}
+	}
+
+	if (dev_priv->mch_res.start)
+		release_resource(&dev_priv->mch_res);
+}
+
+/* true = enable decode, false = disable decoder */
+static unsigned int i915_vga_set_decode(void *cookie, bool state)
+{
+	struct drm_device *dev = cookie;
+
+	intel_modeset_vga_set_state(dev, state);
+	if (state)
+		return VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM |
+		       VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
+	else
+		return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
+}
+
+static void i915_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_state state)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+	pm_message_t pmm = { .event = PM_EVENT_SUSPEND };
+
+	if (state == VGA_SWITCHEROO_ON) {
+		pr_info("switched on\n");
+		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+		/* i915 resume handler doesn't set to D0 */
+		pci_set_power_state(dev->pdev, PCI_D0);
+		i915_resume_switcheroo(dev);
+		dev->switch_power_state = DRM_SWITCH_POWER_ON;
+	} else {
+		pr_info("switched off\n");
+		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+		i915_suspend_switcheroo(dev, pmm);
+		dev->switch_power_state = DRM_SWITCH_POWER_OFF;
+	}
+}
+
+static bool i915_switcheroo_can_switch(struct pci_dev *pdev)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+
+	/*
+	 * FIXME: open_count is protected by drm_global_mutex but that would lead to
+	 * locking inversion with the driver load path. And the access here is
+	 * completely racy anyway. So don't bother with locking for now.
+	 */
+	return dev->open_count == 0;
+}
+
+static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
+	.set_gpu_state = i915_switcheroo_set_state,
+	.reprobe = NULL,
+	.can_switch = i915_switcheroo_can_switch,
+};
+
+static void i915_gem_fini(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	/*
+	 * Neither the BIOS, ourselves or any other kernel
+	 * expects the system to be in execlists mode on startup,
+	 * so we need to reset the GPU back to legacy mode. And the only
+	 * known way to disable logical contexts is through a GPU reset.
+	 *
+	 * So in order to leave the system in a known default configuration,
+	 * always reset the GPU upon unload. Afterwards we then clean up the
+	 * GEM state tracking, flushing off the requests and leaving the
+	 * system in a known idle state.
+	 *
+	 * Note that is of the upmost importance that the GPU is idle and
+	 * all stray writes are flushed *before* we dismantle the backing
+	 * storage for the pinned objects.
+	 *
+	 * However, since we are uncertain that reseting the GPU on older
+	 * machines is a good idea, we don't - just in case it leaves the
+	 * machine in an unusable condition.
+	 */
+	if (HAS_HW_CONTEXTS(dev)) {
+		int reset = intel_gpu_reset(dev_priv, ALL_ENGINES);
+		WARN_ON(reset && reset != -ENODEV);
+	}
+
+	mutex_lock(&dev->struct_mutex);
+	i915_gem_reset(dev);
+	i915_gem_cleanup_engines(dev);
+	i915_gem_context_fini(dev);
+	mutex_unlock(&dev->struct_mutex);
+
+	WARN_ON(!list_empty(&to_i915(dev)->context_list));
+}
+
+static int i915_load_modeset_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int ret;
+
+	if (i915_inject_load_failure())
+		return -ENODEV;
+
+	ret = intel_bios_init(dev_priv);
+	if (ret)
+		DRM_INFO("failed to find VBIOS tables\n");
+
+	/* If we have > 1 VGA cards, then we need to arbitrate access
+	 * to the common VGA resources.
+	 *
+	 * If we are a secondary display controller (!PCI_DISPLAY_CLASS_VGA),
+	 * then we do not take part in VGA arbitration and the
+	 * vga_client_register() fails with -ENODEV.
+	 */
+	ret = vga_client_register(dev->pdev, dev, NULL, i915_vga_set_decode);
+	if (ret && ret != -ENODEV)
+		goto out;
+
+	intel_register_dsm_handler();
+
+	ret = vga_switcheroo_register_client(dev->pdev, &i915_switcheroo_ops, false);
+	if (ret)
+		goto cleanup_vga_client;
+
+	/* must happen before intel_power_domains_init_hw() on VLV/CHV */
+	intel_update_rawclk(dev_priv);
+
+	intel_power_domains_init_hw(dev_priv, false);
+
+	intel_csr_ucode_init(dev_priv);
+
+	ret = intel_irq_install(dev_priv);
+	if (ret)
+		goto cleanup_csr;
+
+	intel_setup_gmbus(dev);
+
+	/* Important: The output setup functions called by modeset_init need
+	 * working irqs for e.g. gmbus and dp aux transfers. */
+	intel_modeset_init(dev);
+
+	intel_guc_init(dev);
+
+	ret = i915_gem_init(dev);
+	if (ret)
+		goto cleanup_irq;
+
+	intel_modeset_gem_init(dev);
+
+	if (INTEL_INFO(dev)->num_pipes == 0)
+		return 0;
+
+	ret = intel_fbdev_init(dev);
+	if (ret)
+		goto cleanup_gem;
+
+	/* Only enable hotplug handling once the fbdev is fully set up. */
+	intel_hpd_init(dev_priv);
+
+	drm_kms_helper_poll_init(dev);
+
+	return 0;
+
+cleanup_gem:
+	i915_gem_fini(dev);
+cleanup_irq:
+	intel_guc_fini(dev);
+	drm_irq_uninstall(dev);
+	intel_teardown_gmbus(dev);
+cleanup_csr:
+	intel_csr_ucode_fini(dev_priv);
+	intel_power_domains_fini(dev_priv);
+	vga_switcheroo_unregister_client(dev->pdev);
+cleanup_vga_client:
+	vga_client_register(dev->pdev, NULL, NULL, NULL);
+out:
+	return ret;
+}
+
+#if IS_ENABLED(CONFIG_FB)
+static int i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
+{
+	struct apertures_struct *ap;
+	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	bool primary;
+	int ret;
+
+	ap = alloc_apertures(1);
+	if (!ap)
+		return -ENOMEM;
+
+	ap->ranges[0].base = ggtt->mappable_base;
+	ap->ranges[0].size = ggtt->mappable_end;
+
+	primary =
+		pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;
+
+	ret = remove_conflicting_framebuffers(ap, "inteldrmfb", primary);
+
+	kfree(ap);
+
+	return ret;
+}
+#else
+static int i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
+{
+	return 0;
+}
+#endif
+
+#if !defined(CONFIG_VGA_CONSOLE)
+static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
+{
+	return 0;
+}
+#elif !defined(CONFIG_DUMMY_CONSOLE)
+static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
+{
+	return -ENODEV;
+}
+#else
+static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
+{
+	int ret = 0;
+
+	DRM_INFO("Replacing VGA console driver\n");
+
+	console_lock();
+	if (con_is_bound(&vga_con))
+		ret = do_take_over_console(&dummy_con, 0, MAX_NR_CONSOLES - 1, 1);
+	if (ret == 0) {
+		ret = do_unregister_con_driver(&vga_con);
+
+		/* Ignore "already unregistered". */
+		if (ret == -ENODEV)
+			ret = 0;
+	}
+	console_unlock();
+
+	return ret;
+}
+#endif
+
+static void intel_init_dpio(struct drm_i915_private *dev_priv)
+{
+	/*
+	 * IOSF_PORT_DPIO is used for VLV x2 PHY (DP/HDMI B and C),
+	 * CHV x1 PHY (DP/HDMI D)
+	 * IOSF_PORT_DPIO_2 is used for CHV x2 PHY (DP/HDMI B and C)
+	 */
+	if (IS_CHERRYVIEW(dev_priv)) {
+		DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO_2;
+		DPIO_PHY_IOSF_PORT(DPIO_PHY1) = IOSF_PORT_DPIO;
+	} else if (IS_VALLEYVIEW(dev_priv)) {
+		DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO;
+	}
+}
+
+static int i915_workqueues_init(struct drm_i915_private *dev_priv)
+{
+	/*
+	 * The i915 workqueue is primarily used for batched retirement of
+	 * requests (and thus managing bo) once the task has been completed
+	 * by the GPU. i915_gem_retire_requests() is called directly when we
+	 * need high-priority retirement, such as waiting for an explicit
+	 * bo.
+	 *
+	 * It is also used for periodic low-priority events, such as
+	 * idle-timers and recording error state.
+	 *
+	 * All tasks on the workqueue are expected to acquire the dev mutex
+	 * so there is no point in running more than one instance of the
+	 * workqueue at any time.  Use an ordered one.
+	 */
+	dev_priv->wq = alloc_ordered_workqueue("i915", 0);
+	if (dev_priv->wq == NULL)
+		goto out_err;
+
+	dev_priv->hotplug.dp_wq = alloc_ordered_workqueue("i915-dp", 0);
+	if (dev_priv->hotplug.dp_wq == NULL)
+		goto out_free_wq;
+
+	return 0;
+
+out_free_wq:
+	destroy_workqueue(dev_priv->wq);
+out_err:
+	DRM_ERROR("Failed to allocate workqueues.\n");
+
+	return -ENOMEM;
+}
+
+static void i915_workqueues_cleanup(struct drm_i915_private *dev_priv)
+{
+	destroy_workqueue(dev_priv->hotplug.dp_wq);
+	destroy_workqueue(dev_priv->wq);
+}
+
+/**
+ * i915_driver_init_early - setup state not requiring device access
+ * @dev_priv: device private
+ *
+ * Initialize everything that is a "SW-only" state, that is state not
+ * requiring accessing the device or exposing the driver via kernel internal
+ * or userspace interfaces. Example steps belonging here: lock initialization,
+ * system memory allocation, setting up device specific attributes and
+ * function hooks not requiring accessing the device.
+ */
+static int i915_driver_init_early(struct drm_i915_private *dev_priv,
+				  const struct pci_device_id *ent)
+{
+	const struct intel_device_info *match_info =
+		(struct intel_device_info *)ent->driver_data;
+	struct intel_device_info *device_info;
+	int ret = 0;
+
+	if (i915_inject_load_failure())
+		return -ENODEV;
+
+	/* Setup the write-once "constant" device info */
+	device_info = mkwrite_device_info(dev_priv);
+	memcpy(device_info, match_info, sizeof(*device_info));
+	device_info->device_id = dev_priv->drm.pdev->device;
+
+	BUG_ON(device_info->gen > sizeof(device_info->gen_mask) * BITS_PER_BYTE);
+	device_info->gen_mask = BIT(device_info->gen - 1);
+
+	spin_lock_init(&dev_priv->irq_lock);
+	spin_lock_init(&dev_priv->gpu_error.lock);
+	mutex_init(&dev_priv->backlight_lock);
+	spin_lock_init(&dev_priv->uncore.lock);
+	spin_lock_init(&dev_priv->mm.object_stat_lock);
+	spin_lock_init(&dev_priv->mmio_flip_lock);
+	mutex_init(&dev_priv->sb_lock);
+	mutex_init(&dev_priv->modeset_restore_lock);
+	mutex_init(&dev_priv->av_mutex);
+	mutex_init(&dev_priv->wm.wm_mutex);
+	mutex_init(&dev_priv->pps_mutex);
+
+	ret = i915_workqueues_init(dev_priv);
+	if (ret < 0)
+		return ret;
+
+	ret = intel_gvt_init(dev_priv);
+	if (ret < 0)
+		goto err_workqueues;
+
+	/* This must be called before any calls to HAS_PCH_* */
+	intel_detect_pch(&dev_priv->drm);
+
+	intel_pm_setup(&dev_priv->drm);
+	intel_init_dpio(dev_priv);
+	intel_power_domains_init(dev_priv);
+	intel_irq_init(dev_priv);
+	intel_init_display_hooks(dev_priv);
+	intel_init_clock_gating_hooks(dev_priv);
+	intel_init_audio_hooks(dev_priv);
+	i915_gem_load_init(&dev_priv->drm);
+
+	intel_display_crc_init(&dev_priv->drm);
+
+	intel_device_info_dump(dev_priv);
+
+	/* Not all pre-production machines fall into this category, only the
+	 * very first ones. Almost everything should work, except for maybe
+	 * suspend/resume. And we don't implement workarounds that affect only
+	 * pre-production machines. */
+	if (IS_HSW_EARLY_SDV(dev_priv))
+		DRM_INFO("This is an early pre-production Haswell machine. "
+			 "It may not be fully functional.\n");
+
+	return 0;
+
+err_workqueues:
+	i915_workqueues_cleanup(dev_priv);
+	return ret;
+}
+
+/**
+ * i915_driver_cleanup_early - cleanup the setup done in i915_driver_init_early()
+ * @dev_priv: device private
+ */
+static void i915_driver_cleanup_early(struct drm_i915_private *dev_priv)
+{
+	i915_gem_load_cleanup(&dev_priv->drm);
+	i915_workqueues_cleanup(dev_priv);
+}
+
+static int i915_mmio_setup(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int mmio_bar;
+	int mmio_size;
+
+	mmio_bar = IS_GEN2(dev) ? 1 : 0;
+	/*
+	 * Before gen4, the registers and the GTT are behind different BARs.
+	 * However, from gen4 onwards, the registers and the GTT are shared
+	 * in the same BAR, so we want to restrict this ioremap from
+	 * clobbering the GTT which we want ioremap_wc instead. Fortunately,
+	 * the register BAR remains the same size for all the earlier
+	 * generations up to Ironlake.
+	 */
+	if (INTEL_INFO(dev)->gen < 5)
+		mmio_size = 512 * 1024;
+	else
+		mmio_size = 2 * 1024 * 1024;
+	dev_priv->regs = pci_iomap(dev->pdev, mmio_bar, mmio_size);
+	if (dev_priv->regs == NULL) {
+		DRM_ERROR("failed to map registers\n");
+
+		return -EIO;
+	}
+
+	/* Try to make sure MCHBAR is enabled before poking at it */
+	intel_setup_mchbar(dev);
+
+	return 0;
+}
+
+static void i915_mmio_cleanup(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	intel_teardown_mchbar(dev);
+	pci_iounmap(dev->pdev, dev_priv->regs);
+}
+
+/**
+ * i915_driver_init_mmio - setup device MMIO
+ * @dev_priv: device private
+ *
+ * Setup minimal device state necessary for MMIO accesses later in the
+ * initialization sequence. The setup here should avoid any other device-wide
+ * side effects or exposing the driver via kernel internal or user space
+ * interfaces.
+ */
+static int i915_driver_init_mmio(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = &dev_priv->drm;
+	int ret;
+
+	if (i915_inject_load_failure())
+		return -ENODEV;
+
+	if (i915_get_bridge_dev(dev))
+		return -EIO;
+
+	ret = i915_mmio_setup(dev);
+	if (ret < 0)
+		goto put_bridge;
+
+	intel_uncore_init(dev_priv);
+
+	return 0;
+
+put_bridge:
+	pci_dev_put(dev_priv->bridge_dev);
+
+	return ret;
+}
+
+/**
+ * i915_driver_cleanup_mmio - cleanup the setup done in i915_driver_init_mmio()
+ * @dev_priv: device private
+ */
+static void i915_driver_cleanup_mmio(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = &dev_priv->drm;
+
+	intel_uncore_fini(dev_priv);
+	i915_mmio_cleanup(dev);
+	pci_dev_put(dev_priv->bridge_dev);
+}
+
+static void intel_sanitize_options(struct drm_i915_private *dev_priv)
+{
+	i915.enable_execlists =
+		intel_sanitize_enable_execlists(dev_priv,
+						i915.enable_execlists);
+
+	/*
+	 * i915.enable_ppgtt is read-only, so do an early pass to validate the
+	 * user's requested state against the hardware/driver capabilities.  We
+	 * do this now so that we can print out any log messages once rather
+	 * than every time we check intel_enable_ppgtt().
+	 */
+	i915.enable_ppgtt =
+		intel_sanitize_enable_ppgtt(dev_priv, i915.enable_ppgtt);
+	DRM_DEBUG_DRIVER("ppgtt mode: %i\n", i915.enable_ppgtt);
+}
+
+/**
+ * i915_driver_init_hw - setup state requiring device access
+ * @dev_priv: device private
+ *
+ * Setup state that requires accessing the device, but doesn't require
+ * exposing the driver via kernel internal or userspace interfaces.
+ */
+static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = &dev_priv->drm;
+	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	uint32_t aperture_size;
+	int ret;
+
+	if (i915_inject_load_failure())
+		return -ENODEV;
+
+	intel_device_info_runtime_init(dev_priv);
+
+	intel_sanitize_options(dev_priv);
+
+	ret = i915_ggtt_init_hw(dev);
+	if (ret)
+		return ret;
+
+	ret = i915_ggtt_enable_hw(dev);
+	if (ret) {
+		DRM_ERROR("failed to enable GGTT\n");
+		goto out_ggtt;
+	}
+
+	/* WARNING: Apparently we must kick fbdev drivers before vgacon,
+	 * otherwise the vga fbdev driver falls over. */
+	ret = i915_kick_out_firmware_fb(dev_priv);
+	if (ret) {
+		DRM_ERROR("failed to remove conflicting framebuffer drivers\n");
+		goto out_ggtt;
+	}
+
+	ret = i915_kick_out_vgacon(dev_priv);
+	if (ret) {
+		DRM_ERROR("failed to remove conflicting VGA console\n");
+		goto out_ggtt;
+	}
+
+	pci_set_master(dev->pdev);
+
+	/* overlay on gen2 is broken and can't address above 1G */
+	if (IS_GEN2(dev)) {
+		ret = dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(30));
+		if (ret) {
+			DRM_ERROR("failed to set DMA mask\n");
+
+			goto out_ggtt;
+		}
+	}
+
+
+	/* 965GM sometimes incorrectly writes to hardware status page (HWS)
+	 * using 32bit addressing, overwriting memory if HWS is located
+	 * above 4GB.
+	 *
+	 * The documentation also mentions an issue with undefined
+	 * behaviour if any general state is accessed within a page above 4GB,
+	 * which also needs to be handled carefully.
+	 */
+	if (IS_BROADWATER(dev) || IS_CRESTLINE(dev)) {
+		ret = dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(32));
+
+		if (ret) {
+			DRM_ERROR("failed to set DMA mask\n");
+
+			goto out_ggtt;
+		}
+	}
+
+	aperture_size = ggtt->mappable_end;
+
+	ggtt->mappable =
+		io_mapping_create_wc(ggtt->mappable_base,
+				     aperture_size);
+	if (!ggtt->mappable) {
+		ret = -EIO;
+		goto out_ggtt;
+	}
+
+	ggtt->mtrr = arch_phys_wc_add(ggtt->mappable_base,
+					      aperture_size);
+
+	pm_qos_add_request(&dev_priv->pm_qos, PM_QOS_CPU_DMA_LATENCY,
+			   PM_QOS_DEFAULT_VALUE);
+
+	intel_uncore_sanitize(dev_priv);
+
+	intel_opregion_setup(dev_priv);
+
+	i915_gem_load_init_fences(dev_priv);
+
+	/* On the 945G/GM, the chipset reports the MSI capability on the
+	 * integrated graphics even though the support isn't actually there
+	 * according to the published specs.  It doesn't appear to function
+	 * correctly in testing on 945G.
+	 * This may be a side effect of MSI having been made available for PEG
+	 * and the registers being closely associated.
+	 *
+	 * According to chipset errata, on the 965GM, MSI interrupts may
+	 * be lost or delayed, but we use them anyways to avoid
+	 * stuck interrupts on some machines.
+	 */
+	if (!IS_I945G(dev) && !IS_I945GM(dev)) {
+		if (pci_enable_msi(dev->pdev) < 0)
+			DRM_DEBUG_DRIVER("can't enable MSI");
+	}
+
+	return 0;
+
+out_ggtt:
+	i915_ggtt_cleanup_hw(dev);
+
+	return ret;
+}
+
+/**
+ * i915_driver_cleanup_hw - cleanup the setup done in i915_driver_init_hw()
+ * @dev_priv: device private
+ */
+static void i915_driver_cleanup_hw(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = &dev_priv->drm;
+	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+
+	if (dev->pdev->msi_enabled)
+		pci_disable_msi(dev->pdev);
+
+	pm_qos_remove_request(&dev_priv->pm_qos);
+	arch_phys_wc_del(ggtt->mtrr);
+	io_mapping_free(ggtt->mappable);
+	i915_ggtt_cleanup_hw(dev);
+}
+
+/**
+ * i915_driver_register - register the driver with the rest of the system
+ * @dev_priv: device private
+ *
+ * Perform any steps necessary to make the driver available via kernel
+ * internal or userspace interfaces.
+ */
+static void i915_driver_register(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = &dev_priv->drm;
+
+	i915_gem_shrinker_init(dev_priv);
+
+	/*
+	 * Notify a valid surface after modesetting,
+	 * when running inside a VM.
+	 */
+	if (intel_vgpu_active(dev_priv))
+		I915_WRITE(vgtif_reg(display_ready), VGT_DRV_DISPLAY_READY);
+
+	/* Reveal our presence to userspace */
+	if (drm_dev_register(dev, 0) == 0) {
+		i915_debugfs_register(dev_priv);
+		i915_setup_sysfs(dev);
+	} else
+		DRM_ERROR("Failed to register driver for userspace access!\n");
+
+	if (INTEL_INFO(dev_priv)->num_pipes) {
+		/* Must be done after probing outputs */
+		intel_opregion_register(dev_priv);
+		acpi_video_register();
+	}
+
+	if (IS_GEN5(dev_priv))
+		intel_gpu_ips_init(dev_priv);
+
+	i915_audio_component_init(dev_priv);
+
+	/*
+	 * Some ports require correctly set-up hpd registers for detection to
+	 * work properly (leading to ghost connected connector status), e.g. VGA
+	 * on gm45.  Hence we can only set up the initial fbdev config after hpd
+	 * irqs are fully enabled. We do it last so that the async config
+	 * cannot run before the connectors are registered.
+	 */
+	intel_fbdev_initial_config_async(dev);
+}
+
+/**
+ * i915_driver_unregister - cleanup the registration done in i915_driver_regiser()
+ * @dev_priv: device private
+ */
+static void i915_driver_unregister(struct drm_i915_private *dev_priv)
+{
+	i915_audio_component_cleanup(dev_priv);
+
+	intel_gpu_ips_teardown();
+	acpi_video_unregister();
+	intel_opregion_unregister(dev_priv);
+
+	i915_teardown_sysfs(&dev_priv->drm);
+	i915_debugfs_unregister(dev_priv);
+	drm_dev_unregister(&dev_priv->drm);
+
+	i915_gem_shrinker_cleanup(dev_priv);
+}
+
+/**
+ * i915_driver_load - setup chip and create an initial config
+ * @dev: DRM device
+ * @flags: startup flags
+ *
+ * The driver load routine has to do several things:
+ *   - drive output discovery via intel_modeset_init()
+ *   - initialize the memory manager
+ *   - allocate initial config memory
+ *   - setup the DRM framebuffer with the allocated memory
+ */
+int i915_driver_load(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct drm_i915_private *dev_priv;
+	int ret;
+
+	if (i915.nuclear_pageflip)
+		driver.driver_features |= DRIVER_ATOMIC;
+
+	ret = -ENOMEM;
+	dev_priv = kzalloc(sizeof(*dev_priv), GFP_KERNEL);
+	if (dev_priv)
+		ret = drm_dev_init(&dev_priv->drm, &driver, &pdev->dev);
+	if (ret) {
+		dev_printk(KERN_ERR, &pdev->dev,
+			   "[" DRM_NAME ":%s] allocation failed\n", __func__);
+		kfree(dev_priv);
+		return ret;
+	}
+
+	dev_priv->drm.pdev = pdev;
+	dev_priv->drm.dev_private = dev_priv;
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		goto out_free_priv;
+
+	pci_set_drvdata(pdev, &dev_priv->drm);
+
+	ret = i915_driver_init_early(dev_priv, ent);
+	if (ret < 0)
+		goto out_pci_disable;
+
+	intel_runtime_pm_get(dev_priv);
+
+	ret = i915_driver_init_mmio(dev_priv);
+	if (ret < 0)
+		goto out_runtime_pm_put;
+
+	ret = i915_driver_init_hw(dev_priv);
+	if (ret < 0)
+		goto out_cleanup_mmio;
+
+	/*
+	 * TODO: move the vblank init and parts of modeset init steps into one
+	 * of the i915_driver_init_/i915_driver_register functions according
+	 * to the role/effect of the given init step.
+	 */
+	if (INTEL_INFO(dev_priv)->num_pipes) {
+		ret = drm_vblank_init(&dev_priv->drm,
+				      INTEL_INFO(dev_priv)->num_pipes);
+		if (ret)
+			goto out_cleanup_hw;
+	}
+
+	ret = i915_load_modeset_init(&dev_priv->drm);
+	if (ret < 0)
+		goto out_cleanup_vblank;
+
+	i915_driver_register(dev_priv);
+
+	intel_runtime_pm_enable(dev_priv);
+
+	intel_runtime_pm_put(dev_priv);
+
+	return 0;
+
+out_cleanup_vblank:
+	drm_vblank_cleanup(&dev_priv->drm);
+out_cleanup_hw:
+	i915_driver_cleanup_hw(dev_priv);
+out_cleanup_mmio:
+	i915_driver_cleanup_mmio(dev_priv);
+out_runtime_pm_put:
+	intel_runtime_pm_put(dev_priv);
+	i915_driver_cleanup_early(dev_priv);
+out_pci_disable:
+	pci_disable_device(pdev);
+out_free_priv:
+	i915_load_error(dev_priv, "Device initialization failed (%d)\n", ret);
+	drm_dev_unref(&dev_priv->drm);
+	return ret;
+}
+
+void i915_driver_unload(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	intel_fbdev_fini(dev);
+
+	if (i915_gem_suspend(dev))
+		DRM_ERROR("failed to idle hardware; continuing to unload!\n");
+
+	intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+
+	i915_driver_unregister(dev_priv);
+
+	drm_vblank_cleanup(dev);
+
+	intel_modeset_cleanup(dev);
+
+	/*
+	 * free the memory space allocated for the child device
+	 * config parsed from VBT
+	 */
+	if (dev_priv->vbt.child_dev && dev_priv->vbt.child_dev_num) {
+		kfree(dev_priv->vbt.child_dev);
+		dev_priv->vbt.child_dev = NULL;
+		dev_priv->vbt.child_dev_num = 0;
+	}
+	kfree(dev_priv->vbt.sdvo_lvds_vbt_mode);
+	dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
+	kfree(dev_priv->vbt.lfp_lvds_vbt_mode);
+	dev_priv->vbt.lfp_lvds_vbt_mode = NULL;
+
+	vga_switcheroo_unregister_client(dev->pdev);
+	vga_client_register(dev->pdev, NULL, NULL, NULL);
+
+	intel_csr_ucode_fini(dev_priv);
+
+	/* Free error state after interrupts are fully disabled. */
+	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
+	i915_destroy_error_state(dev);
+
+	/* Flush any outstanding unpin_work. */
+	flush_workqueue(dev_priv->wq);
+
+	intel_guc_fini(dev);
+	i915_gem_fini(dev);
+	intel_fbc_cleanup_cfb(dev_priv);
+
+	intel_power_domains_fini(dev_priv);
+
+	i915_driver_cleanup_hw(dev_priv);
+	i915_driver_cleanup_mmio(dev_priv);
+
+	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+
+	i915_driver_cleanup_early(dev_priv);
+}
+
+static int i915_driver_open(struct drm_device *dev, struct drm_file *file)
+{
+	int ret;
+
+	ret = i915_gem_open(dev, file);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/**
+ * i915_driver_lastclose - clean up after all DRM clients have exited
+ * @dev: DRM device
+ *
+ * Take care of cleaning up after all DRM clients have exited.  In the
+ * mode setting case, we want to restore the kernel's initial mode (just
+ * in case the last client left us in a bad state).
+ *
+ * Additionally, in the non-mode setting case, we'll tear down the GTT
+ * and DMA structures, since the kernel won't be using them, and clea
+ * up any GEM state.
+ */
+static void i915_driver_lastclose(struct drm_device *dev)
+{
+	intel_fbdev_restore_mode(dev);
+	vga_switcheroo_process_delayed_switch();
+}
+
+static void i915_driver_preclose(struct drm_device *dev, struct drm_file *file)
+{
+	mutex_lock(&dev->struct_mutex);
+	i915_gem_context_close(dev, file);
+	i915_gem_release(dev, file);
+	mutex_unlock(&dev->struct_mutex);
+}
+
+static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
+{
+	struct drm_i915_file_private *file_priv = file->driver_priv;
+
+	kfree(file_priv);
+}
+
 static void intel_suspend_encoders(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct intel_encoder *encoder;
 
 	drm_modeset_lock_all(dev);
@@ -586,7 +1430,7 @@ static bool suspend_to_idle(struct drm_i915_private *dev_priv)
 
 static int i915_drm_suspend(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	pci_power_t opregion_target_state;
 	int error;
 
@@ -614,7 +1458,7 @@ static int i915_drm_suspend(struct drm_device *dev)
 
 	intel_guc_suspend(dev);
 
-	intel_suspend_gt_powersave(dev);
+	intel_suspend_gt_powersave(dev_priv);
 
 	intel_display_suspend(dev);
 
@@ -632,10 +1476,10 @@ static int i915_drm_suspend(struct drm_device *dev)
 	i915_save_state(dev);
 
 	opregion_target_state = suspend_to_idle(dev_priv) ? PCI_D1 : PCI_D3cold;
-	intel_opregion_notify_adapter(dev, opregion_target_state);
+	intel_opregion_notify_adapter(dev_priv, opregion_target_state);
 
-	intel_uncore_forcewake_reset(dev, false);
-	intel_opregion_fini(dev);
+	intel_uncore_forcewake_reset(dev_priv, false);
+	intel_opregion_unregister(dev_priv);
 
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED, true);
 
@@ -653,7 +1497,7 @@ out:
 
 static int i915_drm_suspend_late(struct drm_device *drm_dev, bool hibernation)
 {
-	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(drm_dev);
 	bool fw_csr;
 	int ret;
 
@@ -715,7 +1559,7 @@ int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state)
 {
 	int error;
 
-	if (!dev || !dev->dev_private) {
+	if (!dev) {
 		DRM_ERROR("dev: %p\n", dev);
 		DRM_ERROR("DRM not initialized, aborting suspend.\n");
 		return -ENODEV;
@@ -737,7 +1581,7 @@ int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state)
 
 static int i915_drm_resume(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	disable_rpm_wakeref_asserts(dev_priv);
@@ -753,7 +1597,7 @@ static int i915_drm_resume(struct drm_device *dev)
 	mutex_unlock(&dev->struct_mutex);
 
 	i915_restore_state(dev);
-	intel_opregion_setup(dev);
+	intel_opregion_setup(dev_priv);
 
 	intel_init_pch_refclk(dev);
 	drm_mode_config_reset(dev);
@@ -771,7 +1615,7 @@ static int i915_drm_resume(struct drm_device *dev)
 	mutex_lock(&dev->struct_mutex);
 	if (i915_gem_init_hw(dev)) {
 		DRM_ERROR("failed to re-initialize GPU, declaring wedged!\n");
-			atomic_or(I915_WEDGED, &dev_priv->gpu_error.reset_counter);
+		atomic_or(I915_WEDGED, &dev_priv->gpu_error.reset_counter);
 	}
 	mutex_unlock(&dev->struct_mutex);
 
@@ -781,7 +1625,7 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	spin_lock_irq(&dev_priv->irq_lock);
 	if (dev_priv->display.hpd_irq_setup)
-		dev_priv->display.hpd_irq_setup(dev);
+		dev_priv->display.hpd_irq_setup(dev_priv);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
 	intel_dp_mst_resume(dev);
@@ -798,7 +1642,7 @@ static int i915_drm_resume(struct drm_device *dev)
 	/* Config may have changed between suspend and resume */
 	drm_helper_hpd_irq_event(dev);
 
-	intel_opregion_init(dev);
+	intel_opregion_register(dev_priv);
 
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING, false);
 
@@ -806,7 +1650,7 @@ static int i915_drm_resume(struct drm_device *dev)
 	dev_priv->modeset_restore = MODESET_DONE;
 	mutex_unlock(&dev_priv->modeset_restore_lock);
 
-	intel_opregion_notify_adapter(dev, PCI_D0);
+	intel_opregion_notify_adapter(dev_priv, PCI_D0);
 
 	drm_kms_helper_poll_enable(dev);
 
@@ -817,7 +1661,7 @@ static int i915_drm_resume(struct drm_device *dev)
 
 static int i915_drm_resume_early(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	/*
@@ -874,9 +1718,9 @@ static int i915_drm_resume_early(struct drm_device *dev)
 		DRM_ERROR("Resume prepare failed: %d, continuing anyway\n",
 			  ret);
 
-	intel_uncore_early_sanitize(dev, true);
+	intel_uncore_early_sanitize(dev_priv, true);
 
-	if (IS_BROXTON(dev)) {
+	if (IS_BROXTON(dev_priv)) {
 		if (!dev_priv->suspended_to_idle)
 			gen9_sanitize_dc_state(dev_priv);
 		bxt_disable_dc9(dev_priv);
@@ -884,7 +1728,7 @@ static int i915_drm_resume_early(struct drm_device *dev)
 		hsw_disable_pc8(dev_priv);
 	}
 
-	intel_uncore_sanitize(dev);
+	intel_uncore_sanitize(dev_priv);
 
 	if (IS_BROXTON(dev_priv) ||
 	    !(dev_priv->suspended_to_idle && dev_priv->csr.dmc_payload))
@@ -927,14 +1771,14 @@ int i915_resume_switcheroo(struct drm_device *dev)
  *   - re-init interrupt state
  *   - re-init display
  */
-int i915_reset(struct drm_device *dev)
+int i915_reset(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_device *dev = &dev_priv->drm;
 	struct i915_gpu_error *error = &dev_priv->gpu_error;
 	unsigned reset_counter;
 	int ret;
 
-	intel_reset_gt_powersave(dev);
+	intel_reset_gt_powersave(dev_priv);
 
 	mutex_lock(&dev->struct_mutex);
 
@@ -948,24 +1792,11 @@ int i915_reset(struct drm_device *dev)
 		goto error;
 	}
 
-	i915_gem_reset(dev);
-
-	ret = intel_gpu_reset(dev, ALL_ENGINES);
-
-	/* Also reset the gpu hangman. */
-	if (error->stop_rings != 0) {
-		DRM_INFO("Simulated gpu hang, resetting stop_rings\n");
-		error->stop_rings = 0;
-		if (ret == -ENODEV) {
-			DRM_INFO("Reset not implemented, but ignoring "
-				 "error for simulated gpu hangs\n");
-			ret = 0;
-		}
-	}
+	pr_notice("drm/i915: Resetting chip after gpu hang\n");
 
-	if (i915_stop_ring_allow_warn(dev_priv))
-		pr_notice("drm/i915: Resetting chip after gpu hang\n");
+	i915_gem_reset(dev);
 
+	ret = intel_gpu_reset(dev_priv, ALL_ENGINES);
 	if (ret) {
 		if (ret != -ENODEV)
 			DRM_ERROR("Failed to reset chip: %i\n", ret);
@@ -1005,7 +1836,7 @@ int i915_reset(struct drm_device *dev)
 	 * of re-init after reset.
 	 */
 	if (INTEL_INFO(dev)->gen > 5)
-		intel_enable_gt_powersave(dev);
+		intel_enable_gt_powersave(dev_priv);
 
 	return 0;
 
@@ -1015,51 +1846,12 @@ error:
 	return ret;
 }
 
-static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
-{
-	struct intel_device_info *intel_info =
-		(struct intel_device_info *) ent->driver_data;
-
-	if (IS_PRELIMINARY_HW(intel_info) && !i915.preliminary_hw_support) {
-		DRM_INFO("This hardware requires preliminary hardware support.\n"
-			 "See CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT, and/or modparam preliminary_hw_support\n");
-		return -ENODEV;
-	}
-
-	/* Only bind to function 0 of the device. Early generations
-	 * used function 1 as a placeholder for multi-head. This causes
-	 * us confusion instead, especially on the systems where both
-	 * functions have the same PCI-ID!
-	 */
-	if (PCI_FUNC(pdev->devfn))
-		return -ENODEV;
-
-	/*
-	 * apple-gmux is needed on dual GPU MacBook Pro
-	 * to probe the panel if we're the inactive GPU.
-	 */
-	if (IS_ENABLED(CONFIG_VGA_ARB) && IS_ENABLED(CONFIG_VGA_SWITCHEROO) &&
-	    apple_gmux_present() && pdev != vga_default_device() &&
-	    !vga_switcheroo_handler_flags())
-		return -EPROBE_DEFER;
-
-	return drm_get_pci_dev(pdev, ent, &driver);
-}
-
-static void
-i915_pci_remove(struct pci_dev *pdev)
-{
-	struct drm_device *dev = pci_get_drvdata(pdev);
-
-	drm_put_dev(dev);
-}
-
 static int i915_pm_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 
-	if (!drm_dev || !drm_dev->dev_private) {
+	if (!drm_dev) {
 		dev_err(dev, "DRM not initialized, aborting suspend.\n");
 		return -ENODEV;
 	}
@@ -1072,7 +1864,7 @@ static int i915_pm_suspend(struct device *dev)
 
 static int i915_pm_suspend_late(struct device *dev)
 {
-	struct drm_device *drm_dev = dev_to_i915(dev)->dev;
+	struct drm_device *drm_dev = &dev_to_i915(dev)->drm;
 
 	/*
 	 * We have a suspend ordering issue with the snd-hda driver also
@@ -1091,7 +1883,7 @@ static int i915_pm_suspend_late(struct device *dev)
 
 static int i915_pm_poweroff_late(struct device *dev)
 {
-	struct drm_device *drm_dev = dev_to_i915(dev)->dev;
+	struct drm_device *drm_dev = &dev_to_i915(dev)->drm;
 
 	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
@@ -1101,7 +1893,7 @@ static int i915_pm_poweroff_late(struct device *dev)
 
 static int i915_pm_resume_early(struct device *dev)
 {
-	struct drm_device *drm_dev = dev_to_i915(dev)->dev;
+	struct drm_device *drm_dev = &dev_to_i915(dev)->drm;
 
 	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
@@ -1111,7 +1903,7 @@ static int i915_pm_resume_early(struct device *dev)
 
 static int i915_pm_resume(struct device *dev)
 {
-	struct drm_device *drm_dev = dev_to_i915(dev)->dev;
+	struct drm_device *drm_dev = &dev_to_i915(dev)->drm;
 
 	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
@@ -1119,6 +1911,49 @@ static int i915_pm_resume(struct device *dev)
 	return i915_drm_resume(drm_dev);
 }
 
+/* freeze: before creating the hibernation_image */
+static int i915_pm_freeze(struct device *dev)
+{
+	return i915_pm_suspend(dev);
+}
+
+static int i915_pm_freeze_late(struct device *dev)
+{
+	int ret;
+
+	ret = i915_pm_suspend_late(dev);
+	if (ret)
+		return ret;
+
+	ret = i915_gem_freeze_late(dev_to_i915(dev));
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/* thaw: called after creating the hibernation image, but before turning off. */
+static int i915_pm_thaw_early(struct device *dev)
+{
+	return i915_pm_resume_early(dev);
+}
+
+static int i915_pm_thaw(struct device *dev)
+{
+	return i915_pm_resume(dev);
+}
+
+/* restore: called after loading the hibernation image. */
+static int i915_pm_restore_early(struct device *dev)
+{
+	return i915_pm_resume_early(dev);
+}
+
+static int i915_pm_restore(struct device *dev)
+{
+	return i915_pm_resume(dev);
+}
+
 /*
  * Save all Gunit registers that may be lost after a D3 and a subsequent
  * S0i[R123] transition. The list of registers needing a save/restore is
@@ -1318,8 +2153,6 @@ int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool force_on)
 	u32 val;
 	int err;
 
-#define COND (I915_READ(VLV_GTLC_SURVIVABILITY_REG) & VLV_GFX_CLK_STATUS_BIT)
-
 	val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
 	val &= ~VLV_GFX_CLK_FORCE_ON_BIT;
 	if (force_on)
@@ -1329,13 +2162,16 @@ int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool force_on)
 	if (!force_on)
 		return 0;
 
-	err = wait_for(COND, 20);
+	err = intel_wait_for_register(dev_priv,
+				      VLV_GTLC_SURVIVABILITY_REG,
+				      VLV_GFX_CLK_STATUS_BIT,
+				      VLV_GFX_CLK_STATUS_BIT,
+				      20);
 	if (err)
 		DRM_ERROR("timeout waiting for GFX clock force-on (%08x)\n",
 			  I915_READ(VLV_GTLC_SURVIVABILITY_REG));
 
 	return err;
-#undef COND
 }
 
 static int vlv_allow_gt_wake(struct drm_i915_private *dev_priv, bool allow)
@@ -1350,13 +2186,15 @@ static int vlv_allow_gt_wake(struct drm_i915_private *dev_priv, bool allow)
 	I915_WRITE(VLV_GTLC_WAKE_CTRL, val);
 	POSTING_READ(VLV_GTLC_WAKE_CTRL);
 
-#define COND (!!(I915_READ(VLV_GTLC_PW_STATUS) & VLV_GTLC_ALLOWWAKEACK) == \
-	      allow)
-	err = wait_for(COND, 1);
+	err = intel_wait_for_register(dev_priv,
+				      VLV_GTLC_PW_STATUS,
+				      VLV_GTLC_ALLOWWAKEACK,
+				      allow,
+				      1);
 	if (err)
 		DRM_ERROR("timeout disabling GT waking\n");
+
 	return err;
-#undef COND
 }
 
 static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv,
@@ -1368,8 +2206,7 @@ static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv,
 
 	mask = VLV_GTLC_PW_MEDIA_STATUS_MASK | VLV_GTLC_PW_RENDER_STATUS_MASK;
 	val = wait_for_on ? mask : 0;
-#define COND ((I915_READ(VLV_GTLC_PW_STATUS) & mask) == val)
-	if (COND)
+	if ((I915_READ(VLV_GTLC_PW_STATUS) & mask) == val)
 		return 0;
 
 	DRM_DEBUG_KMS("waiting for GT wells to go %s (%08x)\n",
@@ -1380,13 +2217,14 @@ static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv,
 	 * RC6 transitioning can be delayed up to 2 msec (see
 	 * valleyview_enable_rps), use 3 msec for safety.
 	 */
-	err = wait_for(COND, 3);
+	err = intel_wait_for_register(dev_priv,
+				      VLV_GTLC_PW_STATUS, mask, val,
+				      3);
 	if (err)
 		DRM_ERROR("timeout waiting for GT wells to go %s\n",
 			  onoff(wait_for_on));
 
 	return err;
-#undef COND
 }
 
 static void vlv_check_no_gt_access(struct drm_i915_private *dev_priv)
@@ -1443,7 +2281,7 @@ err1:
 static int vlv_resume_prepare(struct drm_i915_private *dev_priv,
 				bool rpm_resume)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	int err;
 	int ret;
 
@@ -1479,10 +2317,10 @@ static int intel_runtime_suspend(struct device *device)
 {
 	struct pci_dev *pdev = to_pci_dev(device);
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
-	if (WARN_ON_ONCE(!(dev_priv->rps.enabled && intel_enable_rc6(dev))))
+	if (WARN_ON_ONCE(!(dev_priv->rps.enabled && intel_enable_rc6())))
 		return -ENODEV;
 
 	if (WARN_ON_ONCE(!HAS_RUNTIME_PM(dev)))
@@ -1517,11 +2355,8 @@ static int intel_runtime_suspend(struct device *device)
 	i915_gem_release_all_mmaps(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
-	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
-
 	intel_guc_suspend(dev);
 
-	intel_suspend_gt_powersave(dev);
 	intel_runtime_pm_disable_interrupts(dev_priv);
 
 	ret = 0;
@@ -1543,7 +2378,7 @@ static int intel_runtime_suspend(struct device *device)
 		return ret;
 	}
 
-	intel_uncore_forcewake_reset(dev, false);
+	intel_uncore_forcewake_reset(dev_priv, false);
 
 	enable_rpm_wakeref_asserts(dev_priv);
 	WARN_ON_ONCE(atomic_read(&dev_priv->pm.wakeref_count));
@@ -1557,14 +2392,14 @@ static int intel_runtime_suspend(struct device *device)
 	 * FIXME: We really should find a document that references the arguments
 	 * used below!
 	 */
-	if (IS_BROADWELL(dev)) {
+	if (IS_BROADWELL(dev_priv)) {
 		/*
 		 * On Broadwell, if we use PCI_D1 the PCH DDI ports will stop
 		 * being detected, and the call we do at intel_runtime_resume()
 		 * won't be able to restore them. Since PCI_D3hot matches the
 		 * actual specification and appears to be working, use it.
 		 */
-		intel_opregion_notify_adapter(dev, PCI_D3hot);
+		intel_opregion_notify_adapter(dev_priv, PCI_D3hot);
 	} else {
 		/*
 		 * current versions of firmware which depend on this opregion
@@ -1573,11 +2408,14 @@ static int intel_runtime_suspend(struct device *device)
 		 * to distinguish it from notifications that might be sent via
 		 * the suspend path.
 		 */
-		intel_opregion_notify_adapter(dev, PCI_D1);
+		intel_opregion_notify_adapter(dev_priv, PCI_D1);
 	}
 
 	assert_forcewakes_inactive(dev_priv);
 
+	if (!IS_VALLEYVIEW(dev_priv) || !IS_CHERRYVIEW(dev_priv))
+		intel_hpd_poll_init(dev_priv);
+
 	DRM_DEBUG_KMS("Device suspended\n");
 	return 0;
 }
@@ -1586,7 +2424,7 @@ static int intel_runtime_resume(struct device *device)
 {
 	struct pci_dev *pdev = to_pci_dev(device);
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret = 0;
 
 	if (WARN_ON_ONCE(!HAS_RUNTIME_PM(dev)))
@@ -1597,7 +2435,7 @@ static int intel_runtime_resume(struct device *device)
 	WARN_ON_ONCE(atomic_read(&dev_priv->pm.wakeref_count));
 	disable_rpm_wakeref_asserts(dev_priv);
 
-	intel_opregion_notify_adapter(dev, PCI_D0);
+	intel_opregion_notify_adapter(dev_priv, PCI_D0);
 	dev_priv->pm.suspended = false;
 	if (intel_uncore_unclaimed_mmio(dev_priv))
 		DRM_DEBUG_DRIVER("Unclaimed access during suspend, bios?\n");
@@ -1624,7 +2462,7 @@ static int intel_runtime_resume(struct device *device)
 	 * we can do is to hope that things will still work (and disable RPM).
 	 */
 	i915_gem_init_swizzling(dev);
-	gen6_update_ring_freq(dev);
+	gen6_update_ring_freq(dev_priv);
 
 	intel_runtime_pm_enable_interrupts(dev_priv);
 
@@ -1636,8 +2474,6 @@ static int intel_runtime_resume(struct device *device)
 	if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
 		intel_hpd_init(dev_priv);
 
-	intel_enable_gt_powersave(dev);
-
 	enable_rpm_wakeref_asserts(dev_priv);
 
 	if (ret)
@@ -1648,7 +2484,7 @@ static int intel_runtime_resume(struct device *device)
 	return ret;
 }
 
-static const struct dev_pm_ops i915_pm_ops = {
+const struct dev_pm_ops i915_pm_ops = {
 	/*
 	 * S0ix (via system suspend) and S3 event handlers [PMSG_SUSPEND,
 	 * PMSG_RESUME]
@@ -1673,14 +2509,14 @@ static const struct dev_pm_ops i915_pm_ops = {
 	 * @restore, @restore_early : called after rebooting and restoring the
 	 *                            hibernation image [PMSG_RESTORE]
 	 */
-	.freeze = i915_pm_suspend,
-	.freeze_late = i915_pm_suspend_late,
-	.thaw_early = i915_pm_resume_early,
-	.thaw = i915_pm_resume,
+	.freeze = i915_pm_freeze,
+	.freeze_late = i915_pm_freeze_late,
+	.thaw_early = i915_pm_thaw_early,
+	.thaw = i915_pm_thaw,
 	.poweroff = i915_pm_suspend,
 	.poweroff_late = i915_pm_poweroff_late,
-	.restore_early = i915_pm_resume_early,
-	.restore = i915_pm_resume,
+	.restore_early = i915_pm_restore_early,
+	.restore = i915_pm_restore,
 
 	/* S0ix (via runtime suspend) event handlers */
 	.runtime_suspend = intel_runtime_suspend,
@@ -1707,6 +2543,68 @@ static const struct file_operations i915_driver_fops = {
 	.llseek = noop_llseek,
 };
 
+static int
+i915_gem_reject_pin_ioctl(struct drm_device *dev, void *data,
+			  struct drm_file *file)
+{
+	return -ENODEV;
+}
+
+static const struct drm_ioctl_desc i915_ioctls[] = {
+	DRM_IOCTL_DEF_DRV(I915_INIT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_FLUSH, drm_noop, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_FLIP, drm_noop, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_BATCHBUFFER, drm_noop, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_IRQ_EMIT, drm_noop, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_IRQ_WAIT, drm_noop, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_GETPARAM, i915_getparam, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_SETPARAM, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_ALLOC, drm_noop, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_FREE, drm_noop, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_INIT_HEAP, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_CMDBUFFER, drm_noop, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_DESTROY_HEAP,  drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_SET_VBLANK_PIPE,  drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_GET_VBLANK_PIPE,  drm_noop, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_VBLANK_SWAP, drm_noop, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_HWS_ADDR, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_GEM_INIT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER, i915_gem_execbuffer, DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(I915_GEM_EXECBUFFER2, i915_gem_execbuffer2, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_PIN, i915_gem_reject_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_GEM_UNPIN, i915_gem_reject_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_GEM_BUSY, i915_gem_busy_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_SET_CACHING, i915_gem_set_caching_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_GET_CACHING, i915_gem_get_caching_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_THROTTLE, i915_gem_throttle_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_ENTERVT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_GEM_LEAVEVT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(I915_GEM_CREATE, i915_gem_create_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_PREAD, i915_gem_pread_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_PWRITE, i915_gem_pwrite_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP, i915_gem_mmap_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP_GTT, i915_gem_mmap_gtt_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_SET_DOMAIN, i915_gem_set_domain_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_SET_TILING, i915_gem_set_tiling, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_GET_TILING, i915_gem_get_tiling, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_GET_APERTURE, i915_gem_get_aperture_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GET_PIPE_FROM_CRTC_ID, intel_get_pipe_from_crtc_id, 0),
+	DRM_IOCTL_DEF_DRV(I915_GEM_MADVISE, i915_gem_madvise_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_OVERLAY_ATTRS, intel_overlay_attrs_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_SET_SPRITE_COLORKEY, intel_sprite_set_colorkey, DRM_MASTER|DRM_CONTROL_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GET_SPRITE_COLORKEY, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_WAIT, i915_gem_wait_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE, i915_gem_context_create_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GET_RESET_STATS, i915_gem_context_reset_stats_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_USERPTR, i915_gem_userptr_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_GETPARAM, i915_gem_context_getparam_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_SETPARAM, i915_gem_context_setparam_ioctl, DRM_RENDER_ALLOW),
+};
+
 static struct drm_driver driver = {
 	/* Don't use MTRRs here; the Xserver or userspace app should
 	 * deal with them for Intel hardware.
@@ -1714,18 +2612,12 @@ static struct drm_driver driver = {
 	.driver_features =
 	    DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM | DRIVER_PRIME |
 	    DRIVER_RENDER | DRIVER_MODESET,
-	.load = i915_driver_load,
-	.unload = i915_driver_unload,
 	.open = i915_driver_open,
 	.lastclose = i915_driver_lastclose,
 	.preclose = i915_driver_preclose,
 	.postclose = i915_driver_postclose,
 	.set_busid = drm_pci_set_busid,
 
-#if defined(CONFIG_DEBUG_FS)
-	.debugfs_init = i915_debugfs_init,
-	.debugfs_cleanup = i915_debugfs_cleanup,
-#endif
 	.gem_free_object = i915_gem_free_object,
 	.gem_vm_ops = &i915_gem_vm_ops,
 
@@ -1738,6 +2630,7 @@ static struct drm_driver driver = {
 	.dumb_map_offset = i915_gem_mmap_gtt,
 	.dumb_destroy = drm_gem_dumb_destroy,
 	.ioctls = i915_ioctls,
+	.num_ioctls = ARRAY_SIZE(i915_ioctls),
 	.fops = &i915_driver_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
@@ -1746,56 +2639,3 @@ static struct drm_driver driver = {
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
 };
-
-static struct pci_driver i915_pci_driver = {
-	.name = DRIVER_NAME,
-	.id_table = pciidlist,
-	.probe = i915_pci_probe,
-	.remove = i915_pci_remove,
-	.driver.pm = &i915_pm_ops,
-};
-
-static int __init i915_init(void)
-{
-	driver.num_ioctls = i915_max_ioctl;
-
-	/*
-	 * Enable KMS by default, unless explicitly overriden by
-	 * either the i915.modeset prarameter or by the
-	 * vga_text_mode_force boot option.
-	 */
-
-	if (i915.modeset == 0)
-		driver.driver_features &= ~DRIVER_MODESET;
-
-	if (vgacon_text_force() && i915.modeset == -1)
-		driver.driver_features &= ~DRIVER_MODESET;
-
-	if (!(driver.driver_features & DRIVER_MODESET)) {
-		/* Silently fail loading to not upset userspace. */
-		DRM_DEBUG_DRIVER("KMS and UMS disabled.\n");
-		return 0;
-	}
-
-	if (i915.nuclear_pageflip)
-		driver.driver_features |= DRIVER_ATOMIC;
-
-	return drm_pci_init(&driver, &i915_pci_driver);
-}
-
-static void __exit i915_exit(void)
-{
-	if (!(driver.driver_features & DRIVER_MODESET))
-		return; /* Never loaded a driver. */
-
-	drm_pci_exit(&driver, &i915_pci_driver);
-}
-
-module_init(i915_init);
-module_exit(i915_exit);
-
-MODULE_AUTHOR("Tungsten Graphics, Inc.");
-MODULE_AUTHOR("Intel Corporation");
-
-MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index bc3f2e6842e7..915a3d0acff3 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -47,6 +47,7 @@
 #include <drm/intel-gtt.h>
 #include <drm/drm_legacy.h> /* for struct drm_dma_handle */
 #include <drm/drm_gem.h>
+#include <drm/drm_auth.h>
 
 #include "i915_params.h"
 #include "i915_reg.h"
@@ -61,12 +62,14 @@
 #include "i915_gem_gtt.h"
 #include "i915_gem_render_state.h"
 
+#include "intel_gvt.h"
+
 /* General customization:
  */
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20160425"
+#define DRIVER_DATE		"20160711"
 
 #undef WARN_ON
 /* Many gcc seem to no see through this and fall over :( */
@@ -281,6 +284,9 @@ struct i915_hotplug {
 	u32 short_port_mask;
 	struct work_struct dig_port_work;
 
+	struct work_struct poll_init_work;
+	bool poll_enabled;
+
 	/*
 	 * if we get a HPD irq from DP and a HPD irq from non-DP
 	 * the non-DP HPD could block the workqueue on a mode config
@@ -317,21 +323,36 @@ struct i915_hotplug {
 		for_each_if ((__ports_mask) & (1 << (__port)))
 
 #define for_each_crtc(dev, crtc) \
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
+	list_for_each_entry(crtc, &(dev)->mode_config.crtc_list, head)
 
 #define for_each_intel_plane(dev, intel_plane) \
 	list_for_each_entry(intel_plane,			\
-			    &dev->mode_config.plane_list,	\
+			    &(dev)->mode_config.plane_list,	\
 			    base.head)
 
+#define for_each_intel_plane_mask(dev, intel_plane, plane_mask)		\
+	list_for_each_entry(intel_plane,				\
+			    &(dev)->mode_config.plane_list,		\
+			    base.head)					\
+		for_each_if ((plane_mask) &				\
+			     (1 << drm_plane_index(&intel_plane->base)))
+
 #define for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane)	\
 	list_for_each_entry(intel_plane,				\
 			    &(dev)->mode_config.plane_list,		\
 			    base.head)					\
 		for_each_if ((intel_plane)->pipe == (intel_crtc)->pipe)
 
-#define for_each_intel_crtc(dev, intel_crtc) \
-	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head)
+#define for_each_intel_crtc(dev, intel_crtc)				\
+	list_for_each_entry(intel_crtc,					\
+			    &(dev)->mode_config.crtc_list,		\
+			    base.head)
+
+#define for_each_intel_crtc_mask(dev, intel_crtc, crtc_mask)		\
+	list_for_each_entry(intel_crtc,					\
+			    &(dev)->mode_config.crtc_list,		\
+			    base.head)					\
+		for_each_if ((crtc_mask) & (1 << drm_crtc_index(&intel_crtc->base)))
 
 #define for_each_intel_encoder(dev, intel_encoder)		\
 	list_for_each_entry(intel_encoder,			\
@@ -340,7 +361,7 @@ struct i915_hotplug {
 
 #define for_each_intel_connector(dev, intel_connector)		\
 	list_for_each_entry(intel_connector,			\
-			    &dev->mode_config.connector_list,	\
+			    &(dev)->mode_config.connector_list,	\
 			    base.head)
 
 #define for_each_encoder_on_crtc(dev, __crtc, intel_encoder) \
@@ -462,6 +483,7 @@ struct drm_i915_error_state {
 	struct timeval time;
 
 	char error_msg[128];
+	bool simulated;
 	int iommu;
 	u32 reset_count;
 	u32 suspend_count;
@@ -493,6 +515,7 @@ struct drm_i915_error_state {
 		bool valid;
 		/* Software tracked state */
 		bool waiting;
+		int num_waiters;
 		int hangcheck_score;
 		enum intel_ring_hangcheck_action hangcheck_action;
 		int num_requests;
@@ -538,6 +561,12 @@ struct drm_i915_error_state {
 			u32 tail;
 		} *requests;
 
+		struct drm_i915_error_waiter {
+			char comm[TASK_COMM_LEN];
+			pid_t pid;
+			u32 seqno;
+		} *waiters;
+
 		struct {
 			u32 gfx_mode;
 			union {
@@ -588,6 +617,7 @@ struct drm_i915_display_funcs {
 				       struct intel_crtc_state *newstate);
 	void (*initial_watermarks)(struct intel_crtc_state *cstate);
 	void (*optimize_watermarks)(struct intel_crtc_state *cstate);
+	int (*compute_global_watermarks)(struct drm_atomic_state *state);
 	void (*update_wm)(struct drm_crtc *crtc);
 	int (*modeset_calc_cdclk)(struct drm_atomic_state *state);
 	void (*modeset_commit_cdclk)(struct drm_atomic_state *state);
@@ -612,7 +642,7 @@ struct drm_i915_display_funcs {
 			  struct drm_i915_gem_object *obj,
 			  struct drm_i915_gem_request *req,
 			  uint32_t flags);
-	void (*hpd_irq_setup)(struct drm_device *dev);
+	void (*hpd_irq_setup)(struct drm_i915_private *dev_priv);
 	/* clock updates for mode set */
 	/* cursor updates */
 	/* render clock increase/decrease */
@@ -735,6 +765,7 @@ struct intel_csr {
 	func(is_valleyview) sep \
 	func(is_cherryview) sep \
 	func(is_haswell) sep \
+	func(is_broadwell) sep \
 	func(is_skylake) sep \
 	func(is_broxton) sep \
 	func(is_kabylake) sep \
@@ -749,7 +780,8 @@ struct intel_csr {
 	func(has_llc) sep \
 	func(has_snoop) sep \
 	func(has_ddi) sep \
-	func(has_fpga_dbg)
+	func(has_fpga_dbg) sep \
+	func(has_pooled_eu)
 
 #define DEFINE_FLAG(name) u8 name:1
 #define SEP_SEMICOLON ;
@@ -757,9 +789,10 @@ struct intel_csr {
 struct intel_device_info {
 	u32 display_mmio_offset;
 	u16 device_id;
-	u8 num_pipes:3;
+	u8 num_pipes;
 	u8 num_sprites[I915_MAX_PIPES];
 	u8 gen;
+	u16 gen_mask;
 	u8 ring_mask; /* Rings supported by the HW */
 	DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG, SEP_SEMICOLON);
 	/* Register offsets for the various display pipes and transcoders */
@@ -774,6 +807,7 @@ struct intel_device_info {
 	u8 subslice_per_slice;
 	u8 eu_total;
 	u8 eu_per_subslice;
+	u8 min_eu_in_pool;
 	/* For each slice, which subslice(s) has(have) 7 EUs (bitfield)? */
 	u8 subslice_7eu[3];
 	u8 has_slice_pg:1;
@@ -821,9 +855,8 @@ struct i915_ctx_hang_stats {
 /* This must match up with the value previously used for execbuf2.rsvd1. */
 #define DEFAULT_CONTEXT_HANDLE 0
 
-#define CONTEXT_NO_ZEROMAP (1<<0)
 /**
- * struct intel_context - as the name implies, represents a context.
+ * struct i915_gem_context - as the name implies, represents a context.
  * @ref: reference count.
  * @user_handle: userspace tracking identity for this context.
  * @remap_slice: l3 row remapping information.
@@ -841,33 +874,40 @@ struct i915_ctx_hang_stats {
  * Contexts are memory images used by the hardware to store copies of their
  * internal state.
  */
-struct intel_context {
+struct i915_gem_context {
 	struct kref ref;
-	int user_handle;
-	uint8_t remap_slice;
 	struct drm_i915_private *i915;
-	int flags;
 	struct drm_i915_file_private *file_priv;
-	struct i915_ctx_hang_stats hang_stats;
 	struct i915_hw_ppgtt *ppgtt;
 
-	/* Legacy ring buffer submission */
-	struct {
-		struct drm_i915_gem_object *rcs_state;
-		bool initialized;
-	} legacy_hw_ctx;
+	struct i915_ctx_hang_stats hang_stats;
 
-	/* Execlists */
-	struct {
+	/* Unique identifier for this context, used by the hw for tracking */
+	unsigned long flags;
+#define CONTEXT_NO_ZEROMAP		BIT(0)
+#define CONTEXT_NO_ERROR_CAPTURE	BIT(1)
+	unsigned hw_id;
+	u32 user_handle;
+
+	u32 ggtt_alignment;
+
+	struct intel_context {
 		struct drm_i915_gem_object *state;
 		struct intel_ringbuffer *ringbuf;
-		int pin_count;
 		struct i915_vma *lrc_vma;
-		u64 lrc_desc;
 		uint32_t *lrc_reg_state;
+		u64 lrc_desc;
+		int pin_count;
+		bool initialised;
 	} engine[I915_NUM_ENGINES];
+	u32 ring_size;
+	u32 desc_template;
+	struct atomic_notifier_head status_notifier;
+	bool execlists_force_single_submission;
 
 	struct list_head link;
+
+	u8 remap_slice;
 };
 
 enum fb_op_origin {
@@ -1116,6 +1156,8 @@ struct intel_gen6_power_mgmt {
 	bool interrupts_enabled;
 	u32 pm_iir;
 
+	u32 pm_intr_keep;
+
 	/* Frequencies are stored in potentially platform dependent multiples.
 	 * In other words, *_freq needs to be multiplied by X to be interesting.
 	 * Soft limits are those which are used for the dynamic reclocking done
@@ -1283,37 +1325,11 @@ struct i915_gem_mm {
 	struct list_head fence_list;
 
 	/**
-	 * We leave the user IRQ off as much as possible,
-	 * but this means that requests will finish and never
-	 * be retired once the system goes idle. Set a timer to
-	 * fire periodically while the ring is running. When it
-	 * fires, go retire requests.
-	 */
-	struct delayed_work retire_work;
-
-	/**
-	 * When we detect an idle GPU, we want to turn on
-	 * powersaving features. So once we see that there
-	 * are no more requests outstanding and no more
-	 * arrive within a small period of time, we fire
-	 * off the idle_work.
-	 */
-	struct delayed_work idle_work;
-
-	/**
 	 * Are we in a non-interruptible section of code like
 	 * modesetting?
 	 */
 	bool interruptible;
 
-	/**
-	 * Is the GPU currently considered idle, or busy executing userspace
-	 * requests?  Whilst idle, we attempt to power down the hardware and
-	 * display clocks. In order to reduce the effect on performance, there
-	 * is a slight delay before we do so.
-	 */
-	bool busy;
-
 	/* the indicator for dispatch video commands on two BSD rings */
 	unsigned int bsd_ring_dispatch_index;
 
@@ -1350,7 +1366,6 @@ struct i915_gpu_error {
 	/* Hang gpu twice in this window and your context gets banned */
 #define DRM_I915_CTX_BAN_PERIOD DIV_ROUND_UP(8*DRM_I915_HANGCHECK_PERIOD, 1000)
 
-	struct workqueue_struct *hangcheck_wq;
 	struct delayed_work hangcheck_work;
 
 	/* For reset and error_state handling. */
@@ -1387,20 +1402,19 @@ struct i915_gpu_error {
 #define I915_WEDGED			(1 << 31)
 
 	/**
+	 * Waitqueue to signal when a hang is detected. Used to for waiters
+	 * to release the struct_mutex for the reset to procede.
+	 */
+	wait_queue_head_t wait_queue;
+
+	/**
 	 * Waitqueue to signal when the reset has completed. Used by clients
 	 * that wait for dev_priv->mm.wedged to settle.
 	 */
 	wait_queue_head_t reset_queue;
 
-	/* Userspace knobs for gpu hang simulation;
-	 * combines both a ring mask, and extra flags
-	 */
-	u32 stop_rings;
-#define I915_STOP_RING_ALLOW_BAN       (1 << 31)
-#define I915_STOP_RING_ALLOW_WARN      (1 << 30)
-
 	/* For missed irq/seqno simulation. */
-	unsigned int test_irq_rings;
+	unsigned long test_irq_rings;
 };
 
 enum modeset_restore {
@@ -1489,6 +1503,7 @@ struct intel_vbt_data {
 		bool present;
 		bool active_low_pwm;
 		u8 min_brightness;	/* min_brightness/255 of max */
+		enum intel_backlight_type type;
 	} backlight;
 
 	/* MIPI DSI */
@@ -1581,7 +1596,7 @@ struct skl_ddb_allocation {
 };
 
 struct skl_wm_values {
-	bool dirty[I915_MAX_PIPES];
+	unsigned dirty_pipes;
 	struct skl_ddb_allocation ddb;
 	uint32_t wm_linetime[I915_MAX_PIPES];
 	uint32_t plane[I915_MAX_PIPES][I915_MAX_PLANES][8];
@@ -1698,7 +1713,7 @@ struct i915_execbuffer_params {
 	uint64_t                        batch_obj_vm_offset;
 	struct intel_engine_cs *engine;
 	struct drm_i915_gem_object      *batch_obj;
-	struct intel_context            *ctx;
+	struct i915_gem_context            *ctx;
 	struct drm_i915_gem_request     *request;
 };
 
@@ -1710,7 +1725,8 @@ struct intel_wm_config {
 };
 
 struct drm_i915_private {
-	struct drm_device *dev;
+	struct drm_device drm;
+
 	struct kmem_cache *objects;
 	struct kmem_cache *vmas;
 	struct kmem_cache *requests;
@@ -1725,6 +1741,8 @@ struct drm_i915_private {
 
 	struct i915_virtual_gpu vgpu;
 
+	struct intel_gvt gvt;
+
 	struct intel_guc guc;
 
 	struct intel_csr csr;
@@ -1748,6 +1766,7 @@ struct drm_i915_private {
 	wait_queue_head_t gmbus_wait_queue;
 
 	struct pci_dev *bridge_dev;
+	struct i915_gem_context *kernel_context;
 	struct intel_engine_cs engine[I915_NUM_ENGINES];
 	struct drm_i915_gem_object *semaphore_obj;
 	uint32_t last_seqno, next_seqno;
@@ -1803,13 +1822,17 @@ struct drm_i915_private {
 	int num_fence_regs; /* 8 on pre-965, 16 otherwise */
 
 	unsigned int fsb_freq, mem_freq, is_ddr3;
-	unsigned int skl_boot_cdclk;
+	unsigned int skl_preferred_vco_freq;
 	unsigned int cdclk_freq, max_cdclk_freq, atomic_cdclk_freq;
 	unsigned int max_dotclk_freq;
 	unsigned int rawclk_freq;
 	unsigned int hpll_freq;
 	unsigned int czclk_freq;
 
+	struct {
+		unsigned int vco, ref;
+	} cdclk_pll;
+
 	/**
 	 * wq - Driver workqueue for GEM.
 	 *
@@ -1839,6 +1862,13 @@ struct drm_i915_private {
 	DECLARE_HASHTABLE(mm_structs, 7);
 	struct mutex mm_lock;
 
+	/* The hw wants to have a stable context identifier for the lifetime
+	 * of the context (for OA, PASID, faults, etc). This is limited
+	 * in execlists to 21 bits.
+	 */
+	struct ida context_hw_ida;
+#define MAX_CONTEXT_HW_ID (1<<21) /* exclusive */
+
 	/* Kernel Modesetting */
 
 	struct drm_crtc *plane_to_crtc_mapping[I915_MAX_PIPES];
@@ -1951,9 +1981,6 @@ struct drm_i915_private {
 		 */
 		uint16_t skl_latency[8];
 
-		/* Committed wm config */
-		struct intel_wm_config config;
-
 		/*
 		 * The skl_wm_values structure is a bit too big for stack
 		 * allocation, so we keep the staging struct where we store
@@ -1976,6 +2003,13 @@ struct drm_i915_private {
 		 * cstate->wm.need_postvbl_update.
 		 */
 		struct mutex wm_mutex;
+
+		/*
+		 * Set during HW readout of watermarks/DDB.  Some platforms
+		 * need to know when we're still using BIOS-provided values
+		 * (which we don't fully trust).
+		 */
+		bool distrust_bios_wm;
 	} wm;
 
 	struct i915_runtime_pm pm;
@@ -1988,9 +2022,35 @@ struct drm_i915_private {
 		int (*init_engines)(struct drm_device *dev);
 		void (*cleanup_engine)(struct intel_engine_cs *engine);
 		void (*stop_engine)(struct intel_engine_cs *engine);
-	} gt;
 
-	struct intel_context *kernel_context;
+		/**
+		 * Is the GPU currently considered idle, or busy executing
+		 * userspace requests? Whilst idle, we allow runtime power
+		 * management to power down the hardware and display clocks.
+		 * In order to reduce the effect on performance, there
+		 * is a slight delay before we do so.
+		 */
+		unsigned int active_engines;
+		bool awake;
+
+		/**
+		 * We leave the user IRQ off as much as possible,
+		 * but this means that requests will finish and never
+		 * be retired once the system goes idle. Set a timer to
+		 * fire periodically while the ring is running. When it
+		 * fires, go retire requests.
+		 */
+		struct delayed_work retire_work;
+
+		/**
+		 * When we detect an idle GPU, we want to turn on
+		 * powersaving features. So once we see that there
+		 * are no more requests outstanding and no more
+		 * arrive within a small period of time, we fire
+		 * off the idle_work.
+		 */
+		struct delayed_work idle_work;
+	} gt;
 
 	/* perform PHY state sanity checks? */
 	bool chv_phy_assert[2];
@@ -2005,7 +2065,7 @@ struct drm_i915_private {
 
 static inline struct drm_i915_private *to_i915(const struct drm_device *dev)
 {
-	return dev->dev_private;
+	return container_of(dev, struct drm_i915_private, drm);
 }
 
 static inline struct drm_i915_private *dev_to_i915(struct device *dev)
@@ -2176,6 +2236,7 @@ struct drm_i915_gem_object {
 
 	unsigned int frontbuffer_bits:INTEL_FRONTBUFFER_BITS;
 
+	unsigned int has_wc_mmap;
 	unsigned int pin_display;
 
 	struct sg_table *pages;
@@ -2228,9 +2289,81 @@ struct drm_i915_gem_object {
 };
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
-void i915_gem_track_fb(struct drm_i915_gem_object *old,
-		       struct drm_i915_gem_object *new,
-		       unsigned frontbuffer_bits);
+static inline bool
+i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj)
+{
+	return obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE;
+}
+
+/*
+ * Optimised SGL iterator for GEM objects
+ */
+static __always_inline struct sgt_iter {
+	struct scatterlist *sgp;
+	union {
+		unsigned long pfn;
+		dma_addr_t dma;
+	};
+	unsigned int curr;
+	unsigned int max;
+} __sgt_iter(struct scatterlist *sgl, bool dma) {
+	struct sgt_iter s = { .sgp = sgl };
+
+	if (s.sgp) {
+		s.max = s.curr = s.sgp->offset;
+		s.max += s.sgp->length;
+		if (dma)
+			s.dma = sg_dma_address(s.sgp);
+		else
+			s.pfn = page_to_pfn(sg_page(s.sgp));
+	}
+
+	return s;
+}
+
+/**
+ * __sg_next - return the next scatterlist entry in a list
+ * @sg:		The current sg entry
+ *
+ * Description:
+ *   If the entry is the last, return NULL; otherwise, step to the next
+ *   element in the array (@sg@+1). If that's a chain pointer, follow it;
+ *   otherwise just return the pointer to the current element.
+ **/
+static inline struct scatterlist *__sg_next(struct scatterlist *sg)
+{
+#ifdef CONFIG_DEBUG_SG
+	BUG_ON(sg->sg_magic != SG_MAGIC);
+#endif
+	return sg_is_last(sg) ? NULL :
+		likely(!sg_is_chain(++sg)) ? sg :
+		sg_chain_ptr(sg);
+}
+
+/**
+ * for_each_sgt_dma - iterate over the DMA addresses of the given sg_table
+ * @__dmap:	DMA address (output)
+ * @__iter:	'struct sgt_iter' (iterator state, internal)
+ * @__sgt:	sg_table to iterate over (input)
+ */
+#define for_each_sgt_dma(__dmap, __iter, __sgt)				\
+	for ((__iter) = __sgt_iter((__sgt)->sgl, true);			\
+	     ((__dmap) = (__iter).dma + (__iter).curr);			\
+	     (((__iter).curr += PAGE_SIZE) < (__iter).max) ||		\
+	     ((__iter) = __sgt_iter(__sg_next((__iter).sgp), true), 0))
+
+/**
+ * for_each_sgt_page - iterate over the pages of the given sg_table
+ * @__pp:	page pointer (output)
+ * @__iter:	'struct sgt_iter' (iterator state, internal)
+ * @__sgt:	sg_table to iterate over (input)
+ */
+#define for_each_sgt_page(__pp, __iter, __sgt)				\
+	for ((__iter) = __sgt_iter((__sgt)->sgl, false);		\
+	     ((__pp) = (__iter).pfn == 0 ? NULL :			\
+	      pfn_to_page((__iter).pfn + ((__iter).curr >> PAGE_SHIFT))); \
+	     (((__iter).curr += PAGE_SIZE) < (__iter).max) ||		\
+	     ((__iter) = __sgt_iter(__sg_next((__iter).sgp), false), 0))
 
 /**
  * Request queue structure.
@@ -2252,7 +2385,7 @@ struct drm_i915_gem_request {
 	/** On Which ring this request was generated */
 	struct drm_i915_private *i915;
 	struct intel_engine_cs *engine;
-	unsigned reset_counter;
+	struct intel_signal_node signaling;
 
 	 /** GEM sequence number associated with the previous request,
 	  * when the HWS breadcrumb is equal to this the GPU is processing
@@ -2279,6 +2412,9 @@ struct drm_i915_gem_request {
 	/** Position in the ringbuffer of the end of the whole request */
 	u32 tail;
 
+	/** Preallocate space in the ringbuffer for the emitting the request */
+	u32 reserved_space;
+
 	/**
 	 * Context and ring buffer related to this request
 	 * Contexts are refcounted, so when this request is associated with a
@@ -2289,9 +2425,20 @@ struct drm_i915_gem_request {
 	 * i915_gem_request_free() will then decrement the refcount on the
 	 * context.
 	 */
-	struct intel_context *ctx;
+	struct i915_gem_context *ctx;
 	struct intel_ringbuffer *ringbuf;
 
+	/**
+	 * Context related to the previous request.
+	 * As the contexts are accessed by the hardware until the switch is
+	 * completed to a new context, the hardware may still be writing
+	 * to the context object after the breadcrumb is visible. We must
+	 * not unpin/unbind/prune that object whilst still active and so
+	 * we keep the previous context pinned until the following (this)
+	 * request is retired.
+	 */
+	struct i915_gem_context *previous_context;
+
 	/** Batch buffer related to this request if any (used for
 	    error state dump only) */
 	struct drm_i915_gem_object *batch_obj;
@@ -2328,11 +2475,13 @@ struct drm_i915_gem_request {
 	/** Execlists no. of times this request has been sent to the ELSP */
 	int elsp_submitted;
 
+	/** Execlists context hardware id. */
+	unsigned ctx_hw_id;
 };
 
 struct drm_i915_gem_request * __must_check
 i915_gem_request_alloc(struct intel_engine_cs *engine,
-		       struct intel_context *ctx);
+		       struct i915_gem_context *ctx);
 void i915_gem_request_free(struct kref *req_ref);
 int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
 				   struct drm_file *file);
@@ -2360,23 +2509,9 @@ i915_gem_request_reference(struct drm_i915_gem_request *req)
 static inline void
 i915_gem_request_unreference(struct drm_i915_gem_request *req)
 {
-	WARN_ON(!mutex_is_locked(&req->engine->dev->struct_mutex));
 	kref_put(&req->ref, i915_gem_request_free);
 }
 
-static inline void
-i915_gem_request_unreference__unlocked(struct drm_i915_gem_request *req)
-{
-	struct drm_device *dev;
-
-	if (!req)
-		return;
-
-	dev = req->engine->dev;
-	if (kref_put_mutex(&req->ref, i915_gem_request_free, &dev->struct_mutex))
-		mutex_unlock(&dev->struct_mutex);
-}
-
 static inline void i915_gem_request_assign(struct drm_i915_gem_request **pdst,
 					   struct drm_i915_gem_request *src)
 {
@@ -2504,9 +2639,29 @@ struct drm_i915_cmd_table {
 #define INTEL_INFO(p) 	(&__I915__(p)->info)
 #define INTEL_GEN(p)	(INTEL_INFO(p)->gen)
 #define INTEL_DEVID(p)	(INTEL_INFO(p)->device_id)
-#define INTEL_REVID(p)	(__I915__(p)->dev->pdev->revision)
 
 #define REVID_FOREVER		0xff
+#define INTEL_REVID(p)	(__I915__(p)->drm.pdev->revision)
+
+#define GEN_FOREVER (0)
+/*
+ * Returns true if Gen is in inclusive range [Start, End].
+ *
+ * Use GEN_FOREVER for unbound start and or end.
+ */
+#define IS_GEN(p, s, e) ({ \
+	unsigned int __s = (s), __e = (e); \
+	BUILD_BUG_ON(!__builtin_constant_p(s)); \
+	BUILD_BUG_ON(!__builtin_constant_p(e)); \
+	if ((__s) != GEN_FOREVER) \
+		__s = (s) - 1; \
+	if ((__e) == GEN_FOREVER) \
+		__e = BITS_PER_LONG - 1; \
+	else \
+		__e = (e) - 1; \
+	!!(INTEL_INFO(p)->gen_mask & GENMASK((__e), (__s))); \
+})
+
 /*
  * Return true if revision is in range [since,until] inclusive.
  *
@@ -2539,7 +2694,7 @@ struct drm_i915_cmd_table {
 #define IS_VALLEYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview)
 #define IS_CHERRYVIEW(dev)	(INTEL_INFO(dev)->is_cherryview)
 #define IS_HASWELL(dev)	(INTEL_INFO(dev)->is_haswell)
-#define IS_BROADWELL(dev)	(!INTEL_INFO(dev)->is_cherryview && IS_GEN8(dev))
+#define IS_BROADWELL(dev)	(INTEL_INFO(dev)->is_broadwell)
 #define IS_SKYLAKE(dev)	(INTEL_INFO(dev)->is_skylake)
 #define IS_BROXTON(dev)		(INTEL_INFO(dev)->is_broxton)
 #define IS_KABYLAKE(dev)	(INTEL_INFO(dev)->is_kabylake)
@@ -2591,6 +2746,8 @@ struct drm_i915_cmd_table {
 #define SKL_REVID_D0		0x3
 #define SKL_REVID_E0		0x4
 #define SKL_REVID_F0		0x5
+#define SKL_REVID_G0		0x6
+#define SKL_REVID_H0		0x7
 
 #define IS_SKL_REVID(p, since, until) (IS_SKYLAKE(p) && IS_REVID(p, since, until))
 
@@ -2616,29 +2773,34 @@ struct drm_i915_cmd_table {
  * have their own (e.g. HAS_PCH_SPLIT for ILK+ display, IS_foo for particular
  * chips, etc.).
  */
-#define IS_GEN2(dev)	(INTEL_INFO(dev)->gen == 2)
-#define IS_GEN3(dev)	(INTEL_INFO(dev)->gen == 3)
-#define IS_GEN4(dev)	(INTEL_INFO(dev)->gen == 4)
-#define IS_GEN5(dev)	(INTEL_INFO(dev)->gen == 5)
-#define IS_GEN6(dev)	(INTEL_INFO(dev)->gen == 6)
-#define IS_GEN7(dev)	(INTEL_INFO(dev)->gen == 7)
-#define IS_GEN8(dev)	(INTEL_INFO(dev)->gen == 8)
-#define IS_GEN9(dev)	(INTEL_INFO(dev)->gen == 9)
-
-#define RENDER_RING		(1<<RCS)
-#define BSD_RING		(1<<VCS)
-#define BLT_RING		(1<<BCS)
-#define VEBOX_RING		(1<<VECS)
-#define BSD2_RING		(1<<VCS2)
-#define ALL_ENGINES		(~0)
-
-#define HAS_BSD(dev)		(INTEL_INFO(dev)->ring_mask & BSD_RING)
-#define HAS_BSD2(dev)		(INTEL_INFO(dev)->ring_mask & BSD2_RING)
-#define HAS_BLT(dev)		(INTEL_INFO(dev)->ring_mask & BLT_RING)
-#define HAS_VEBOX(dev)		(INTEL_INFO(dev)->ring_mask & VEBOX_RING)
+#define IS_GEN2(dev)	(!!(INTEL_INFO(dev)->gen_mask & BIT(1)))
+#define IS_GEN3(dev)	(!!(INTEL_INFO(dev)->gen_mask & BIT(2)))
+#define IS_GEN4(dev)	(!!(INTEL_INFO(dev)->gen_mask & BIT(3)))
+#define IS_GEN5(dev)	(!!(INTEL_INFO(dev)->gen_mask & BIT(4)))
+#define IS_GEN6(dev)	(!!(INTEL_INFO(dev)->gen_mask & BIT(5)))
+#define IS_GEN7(dev)	(!!(INTEL_INFO(dev)->gen_mask & BIT(6)))
+#define IS_GEN8(dev)	(!!(INTEL_INFO(dev)->gen_mask & BIT(7)))
+#define IS_GEN9(dev)	(!!(INTEL_INFO(dev)->gen_mask & BIT(8)))
+
+#define ENGINE_MASK(id)	BIT(id)
+#define RENDER_RING	ENGINE_MASK(RCS)
+#define BSD_RING	ENGINE_MASK(VCS)
+#define BLT_RING	ENGINE_MASK(BCS)
+#define VEBOX_RING	ENGINE_MASK(VECS)
+#define BSD2_RING	ENGINE_MASK(VCS2)
+#define ALL_ENGINES	(~0)
+
+#define HAS_ENGINE(dev_priv, id) \
+	(!!(INTEL_INFO(dev_priv)->ring_mask & ENGINE_MASK(id)))
+
+#define HAS_BSD(dev_priv)	HAS_ENGINE(dev_priv, VCS)
+#define HAS_BSD2(dev_priv)	HAS_ENGINE(dev_priv, VCS2)
+#define HAS_BLT(dev_priv)	HAS_ENGINE(dev_priv, BCS)
+#define HAS_VEBOX(dev_priv)	HAS_ENGINE(dev_priv, VECS)
+
 #define HAS_LLC(dev)		(INTEL_INFO(dev)->has_llc)
 #define HAS_SNOOP(dev)		(INTEL_INFO(dev)->has_snoop)
-#define HAS_EDRAM(dev)		(__I915__(dev)->edram_cap & EDRAM_ENABLED)
+#define HAS_EDRAM(dev)		(!!(__I915__(dev)->edram_cap & EDRAM_ENABLED))
 #define HAS_WT(dev)		((IS_HASWELL(dev) || IS_BROADWELL(dev)) && \
 				 HAS_EDRAM(dev))
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
@@ -2656,9 +2818,10 @@ struct drm_i915_cmd_table {
 #define HAS_BROKEN_CS_TLB(dev)		(IS_I830(dev) || IS_845G(dev))
 
 /* WaRsDisableCoarsePowerGating:skl,bxt */
-#define NEEDS_WaRsDisableCoarsePowerGating(dev) (IS_BXT_REVID(dev, 0, BXT_REVID_A1) || \
-						 IS_SKL_GT3(dev) || \
-						 IS_SKL_GT4(dev))
+#define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
+	(IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1) || \
+	 IS_SKL_GT3(dev_priv) || \
+	 IS_SKL_GT4(dev_priv))
 
 /*
  * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
@@ -2696,12 +2859,18 @@ struct drm_i915_cmd_table {
 				 IS_CHERRYVIEW(dev) || IS_SKYLAKE(dev) || \
 				 IS_KABYLAKE(dev) || IS_BROXTON(dev))
 #define HAS_RC6(dev)		(INTEL_INFO(dev)->gen >= 6)
-#define HAS_RC6p(dev)		(INTEL_INFO(dev)->gen == 6 || IS_IVYBRIDGE(dev))
+#define HAS_RC6p(dev)		(IS_GEN6(dev) || IS_IVYBRIDGE(dev))
 
 #define HAS_CSR(dev)	(IS_GEN9(dev))
 
-#define HAS_GUC_UCODE(dev)	(IS_GEN9(dev) && !IS_KABYLAKE(dev))
-#define HAS_GUC_SCHED(dev)	(IS_GEN9(dev) && !IS_KABYLAKE(dev))
+/*
+ * For now, anything with a GuC requires uCode loading, and then supports
+ * command submission once loaded. But these are logically independent
+ * properties, so we have separate macros to test them.
+ */
+#define HAS_GUC(dev)		(IS_GEN9(dev))
+#define HAS_GUC_UCODE(dev)	(HAS_GUC(dev))
+#define HAS_GUC_SCHED(dev)	(HAS_GUC(dev))
 
 #define HAS_RESOURCE_STREAMER(dev) (IS_HASWELL(dev) || \
 				    INTEL_INFO(dev)->gen >= 8)
@@ -2710,6 +2879,8 @@ struct drm_i915_cmd_table {
 				 !IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev) && \
 				 !IS_BROXTON(dev))
 
+#define HAS_POOLED_EU(dev)	(INTEL_INFO(dev)->has_pooled_eu)
+
 #define INTEL_PCH_DEVICE_ID_MASK		0xff00
 #define INTEL_PCH_IBX_DEVICE_ID_TYPE		0x3b00
 #define INTEL_PCH_CPT_DEVICE_ID_TYPE		0x1c00
@@ -2746,13 +2917,22 @@ struct drm_i915_cmd_table {
 
 #include "i915_trace.h"
 
-extern const struct drm_ioctl_desc i915_ioctls[];
-extern int i915_max_ioctl;
+static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv)
+{
+#ifdef CONFIG_INTEL_IOMMU
+	if (INTEL_GEN(dev_priv) >= 6 && intel_iommu_gfx_mapped)
+		return true;
+#endif
+	return false;
+}
 
 extern int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state);
 extern int i915_resume_switcheroo(struct drm_device *dev);
 
-/* i915_dma.c */
+int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
+			       	int enable_ppgtt);
+
+/* i915_drv.c */
 void __printf(3, 4)
 __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 	      const char *fmt, ...);
@@ -2760,21 +2940,13 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 #define i915_report_error(dev_priv, fmt, ...)				   \
 	__i915_printk(dev_priv, KERN_ERR, fmt, ##__VA_ARGS__)
 
-extern int i915_driver_load(struct drm_device *, unsigned long flags);
-extern int i915_driver_unload(struct drm_device *);
-extern int i915_driver_open(struct drm_device *dev, struct drm_file *file);
-extern void i915_driver_lastclose(struct drm_device * dev);
-extern void i915_driver_preclose(struct drm_device *dev,
-				 struct drm_file *file);
-extern void i915_driver_postclose(struct drm_device *dev,
-				  struct drm_file *file);
 #ifdef CONFIG_COMPAT
 extern long i915_compat_ioctl(struct file *filp, unsigned int cmd,
 			      unsigned long arg);
 #endif
-extern int intel_gpu_reset(struct drm_device *dev, u32 engine_mask);
-extern bool intel_has_gpu_reset(struct drm_device *dev);
-extern int i915_reset(struct drm_device *dev);
+extern int intel_gpu_reset(struct drm_i915_private *dev_priv, u32 engine_mask);
+extern bool intel_has_gpu_reset(struct drm_i915_private *dev_priv);
+extern int i915_reset(struct drm_i915_private *dev_priv);
 extern int intel_guc_reset(struct drm_i915_private *dev_priv);
 extern void intel_engine_init_hangcheck(struct intel_engine_cs *engine);
 extern unsigned long i915_chipset_val(struct drm_i915_private *dev_priv);
@@ -2784,30 +2956,51 @@ extern void i915_update_gfx_val(struct drm_i915_private *dev_priv);
 int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
 
 /* intel_hotplug.c */
-void intel_hpd_irq_handler(struct drm_device *dev, u32 pin_mask, u32 long_mask);
+void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
+			   u32 pin_mask, u32 long_mask);
 void intel_hpd_init(struct drm_i915_private *dev_priv);
 void intel_hpd_init_work(struct drm_i915_private *dev_priv);
 void intel_hpd_cancel_work(struct drm_i915_private *dev_priv);
 bool intel_hpd_pin_to_port(enum hpd_pin pin, enum port *port);
+bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin);
+void intel_hpd_enable(struct drm_i915_private *dev_priv, enum hpd_pin pin);
 
 /* i915_irq.c */
-void i915_queue_hangcheck(struct drm_device *dev);
+static inline void i915_queue_hangcheck(struct drm_i915_private *dev_priv)
+{
+	unsigned long delay;
+
+	if (unlikely(!i915.enable_hangcheck))
+		return;
+
+	/* Don't continually defer the hangcheck so that it is always run at
+	 * least once after work has been scheduled on any ring. Otherwise,
+	 * we will ignore a hung ring if a second ring is kept busy.
+	 */
+
+	delay = round_jiffies_up_relative(DRM_I915_HANGCHECK_JIFFIES);
+	queue_delayed_work(system_long_wq,
+			   &dev_priv->gpu_error.hangcheck_work, delay);
+}
+
 __printf(3, 4)
-void i915_handle_error(struct drm_device *dev, u32 engine_mask,
+void i915_handle_error(struct drm_i915_private *dev_priv,
+		       u32 engine_mask,
 		       const char *fmt, ...);
 
 extern void intel_irq_init(struct drm_i915_private *dev_priv);
 int intel_irq_install(struct drm_i915_private *dev_priv);
 void intel_irq_uninstall(struct drm_i915_private *dev_priv);
 
-extern void intel_uncore_sanitize(struct drm_device *dev);
-extern void intel_uncore_early_sanitize(struct drm_device *dev,
+extern void intel_uncore_sanitize(struct drm_i915_private *dev_priv);
+extern void intel_uncore_early_sanitize(struct drm_i915_private *dev_priv,
 					bool restore_forcewake);
-extern void intel_uncore_init(struct drm_device *dev);
+extern void intel_uncore_init(struct drm_i915_private *dev_priv);
 extern bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv);
 extern bool intel_uncore_arm_unclaimed_mmio_detection(struct drm_i915_private *dev_priv);
-extern void intel_uncore_fini(struct drm_device *dev);
-extern void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore);
+extern void intel_uncore_fini(struct drm_i915_private *dev_priv);
+extern void intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv,
+					 bool restore);
 const char *intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id);
 void intel_uncore_forcewake_get(struct drm_i915_private *dev_priv,
 				enum forcewake_domains domains);
@@ -2823,9 +3016,26 @@ void intel_uncore_forcewake_put__locked(struct drm_i915_private *dev_priv,
 u64 intel_uncore_edram_size(struct drm_i915_private *dev_priv);
 
 void assert_forcewakes_inactive(struct drm_i915_private *dev_priv);
-static inline bool intel_vgpu_active(struct drm_device *dev)
+
+int intel_wait_for_register(struct drm_i915_private *dev_priv,
+			    i915_reg_t reg,
+			    const u32 mask,
+			    const u32 value,
+			    const unsigned long timeout_ms);
+int intel_wait_for_register_fw(struct drm_i915_private *dev_priv,
+			       i915_reg_t reg,
+			       const u32 mask,
+			       const u32 value,
+			       const unsigned long timeout_ms);
+
+static inline bool intel_gvt_active(struct drm_i915_private *dev_priv)
+{
+	return dev_priv->gvt.initialized;
+}
+
+static inline bool intel_vgpu_active(struct drm_i915_private *dev_priv)
 {
-	return to_i915(dev)->vgpu.active;
+	return dev_priv->vgpu.active;
 }
 
 void
@@ -2882,7 +3092,6 @@ ibx_disable_display_interrupt(struct drm_i915_private *dev_priv, uint32_t bits)
 	ibx_display_interrupt_update(dev_priv, bits, 0);
 }
 
-
 /* i915_gem.c */
 int i915_gem_create_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *file_priv);
@@ -2921,7 +3130,7 @@ int i915_gem_set_tiling(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 int i915_gem_get_tiling(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
-int i915_gem_init_userptr(struct drm_device *dev);
+void i915_gem_init_userptr(struct drm_i915_private *dev_priv);
 int i915_gem_userptr_ioctl(struct drm_device *dev, void *data,
 			   struct drm_file *file);
 int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
@@ -2931,11 +3140,13 @@ int i915_gem_wait_ioctl(struct drm_device *dev, void *data,
 void i915_gem_load_init(struct drm_device *dev);
 void i915_gem_load_cleanup(struct drm_device *dev);
 void i915_gem_load_init_fences(struct drm_i915_private *dev_priv);
+int i915_gem_freeze_late(struct drm_i915_private *dev_priv);
+
 void *i915_gem_object_alloc(struct drm_device *dev);
 void i915_gem_object_free(struct drm_i915_gem_object *obj);
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
 			 const struct drm_i915_gem_object_ops *ops);
-struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
+struct drm_i915_gem_object *i915_gem_object_create(struct drm_device *dev,
 						  size_t size);
 struct drm_i915_gem_object *i915_gem_object_create_from_data(
 		struct drm_device *dev, const void *data, size_t size);
@@ -2990,6 +3201,23 @@ static inline int __sg_page_count(struct scatterlist *sg)
 struct page *
 i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, int n);
 
+static inline dma_addr_t
+i915_gem_object_get_dma_address(struct drm_i915_gem_object *obj, int n)
+{
+	if (n < obj->get_page.last) {
+		obj->get_page.sg = obj->pages->sgl;
+		obj->get_page.last = 0;
+	}
+
+	while (obj->get_page.last + __sg_page_count(obj->get_page.sg) <= n) {
+		obj->get_page.last += __sg_page_count(obj->get_page.sg++);
+		if (unlikely(sg_is_chain(obj->get_page.sg)))
+			obj->get_page.sg = sg_chain_ptr(obj->get_page.sg);
+	}
+
+	return sg_dma_address(obj->get_page.sg) + ((n - obj->get_page.last) << PAGE_SHIFT);
+}
+
 static inline struct page *
 i915_gem_object_get_page(struct drm_i915_gem_object *obj, int n)
 {
@@ -3066,6 +3294,11 @@ int i915_gem_dumb_create(struct drm_file *file_priv,
 			 struct drm_mode_create_dumb *args);
 int i915_gem_mmap_gtt(struct drm_file *file_priv, struct drm_device *dev,
 		      uint32_t handle, uint64_t *offset);
+
+void i915_gem_track_fb(struct drm_i915_gem_object *old,
+		       struct drm_i915_gem_object *new,
+		       unsigned frontbuffer_bits);
+
 /**
  * Returns true if seq1 is later than seq2.
  */
@@ -3075,31 +3308,34 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2)
 	return (int32_t)(seq1 - seq2) >= 0;
 }
 
-static inline bool i915_gem_request_started(struct drm_i915_gem_request *req,
-					   bool lazy_coherency)
+static inline bool i915_gem_request_started(const struct drm_i915_gem_request *req)
 {
-	if (!lazy_coherency && req->engine->irq_seqno_barrier)
-		req->engine->irq_seqno_barrier(req->engine);
-	return i915_seqno_passed(req->engine->get_seqno(req->engine),
+	return i915_seqno_passed(intel_engine_get_seqno(req->engine),
 				 req->previous_seqno);
 }
 
-static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req,
-					      bool lazy_coherency)
+static inline bool i915_gem_request_completed(const struct drm_i915_gem_request *req)
 {
-	if (!lazy_coherency && req->engine->irq_seqno_barrier)
-		req->engine->irq_seqno_barrier(req->engine);
-	return i915_seqno_passed(req->engine->get_seqno(req->engine),
+	return i915_seqno_passed(intel_engine_get_seqno(req->engine),
 				 req->seqno);
 }
 
-int __must_check i915_gem_get_seqno(struct drm_device *dev, u32 *seqno);
+bool __i915_spin_request(const struct drm_i915_gem_request *request,
+			 int state, unsigned long timeout_us);
+static inline bool i915_spin_request(const struct drm_i915_gem_request *request,
+				     int state, unsigned long timeout_us)
+{
+	return (i915_gem_request_started(request) &&
+		__i915_spin_request(request, state, timeout_us));
+}
+
+int __must_check i915_gem_get_seqno(struct drm_i915_private *dev_priv, u32 *seqno);
 int __must_check i915_gem_set_seqno(struct drm_device *dev, u32 seqno);
 
 struct drm_i915_gem_request *
 i915_gem_find_active_request(struct intel_engine_cs *engine);
 
-bool i915_gem_retire_requests(struct drm_device *dev);
+void i915_gem_retire_requests(struct drm_i915_private *dev_priv);
 void i915_gem_retire_requests_ring(struct intel_engine_cs *engine);
 
 static inline u32 i915_reset_counter(struct i915_gpu_error *error)
@@ -3142,27 +3378,14 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 	return ((i915_reset_counter(error) & ~I915_WEDGED) + 1) / 2;
 }
 
-static inline bool i915_stop_ring_allow_ban(struct drm_i915_private *dev_priv)
-{
-	return dev_priv->gpu_error.stop_rings == 0 ||
-		dev_priv->gpu_error.stop_rings & I915_STOP_RING_ALLOW_BAN;
-}
-
-static inline bool i915_stop_ring_allow_warn(struct drm_i915_private *dev_priv)
-{
-	return dev_priv->gpu_error.stop_rings == 0 ||
-		dev_priv->gpu_error.stop_rings & I915_STOP_RING_ALLOW_WARN;
-}
-
 void i915_gem_reset(struct drm_device *dev);
 bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_init(struct drm_device *dev);
 int i915_gem_init_engines(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
-int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_engines(struct drm_device *dev);
-int __must_check i915_gpu_idle(struct drm_device *dev);
+int __must_check i915_gem_wait_for_idle(struct drm_i915_private *dev_priv);
 int __must_check i915_gem_suspend(struct drm_device *dev);
 void __i915_add_request(struct drm_i915_gem_request *req,
 			struct drm_i915_gem_object *batch_obj,
@@ -3227,8 +3450,6 @@ bool i915_gem_obj_ggtt_bound_view(struct drm_i915_gem_object *o,
 bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
 			struct i915_address_space *vm);
 
-unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
-				struct i915_address_space *vm);
 struct i915_vma *
 i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
 		    struct i915_address_space *vm);
@@ -3263,14 +3484,8 @@ static inline bool i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *obj)
 	return i915_gem_obj_ggtt_bound_view(obj, &i915_ggtt_view_normal);
 }
 
-static inline unsigned long
-i915_gem_obj_ggtt_size(struct drm_i915_gem_object *obj)
-{
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-
-	return i915_gem_obj_size(obj, &ggtt->base);
-}
+unsigned long
+i915_gem_obj_ggtt_size(struct drm_i915_gem_object *obj);
 
 static inline int __must_check
 i915_gem_obj_ggtt_pin(struct drm_i915_gem_object *obj,
@@ -3284,12 +3499,6 @@ i915_gem_obj_ggtt_pin(struct drm_i915_gem_object *obj,
 				   alignment, flags | PIN_GLOBAL);
 }
 
-static inline int
-i915_gem_object_ggtt_unbind(struct drm_i915_gem_object *obj)
-{
-	return i915_vma_unbind(i915_gem_obj_to_ggtt(obj));
-}
-
 void i915_gem_object_ggtt_unpin_view(struct drm_i915_gem_object *obj,
 				     const struct i915_ggtt_view *view);
 static inline void
@@ -3313,28 +3522,44 @@ void i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj);
 
 /* i915_gem_context.c */
 int __must_check i915_gem_context_init(struct drm_device *dev);
+void i915_gem_context_lost(struct drm_i915_private *dev_priv);
 void i915_gem_context_fini(struct drm_device *dev);
 void i915_gem_context_reset(struct drm_device *dev);
 int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
-int i915_gem_context_enable(struct drm_i915_gem_request *req);
 void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
 int i915_switch_context(struct drm_i915_gem_request *req);
-struct intel_context *
-i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id);
 void i915_gem_context_free(struct kref *ctx_ref);
 struct drm_i915_gem_object *
 i915_gem_alloc_context_obj(struct drm_device *dev, size_t size);
-static inline void i915_gem_context_reference(struct intel_context *ctx)
+struct i915_gem_context *
+i915_gem_context_create_gvt(struct drm_device *dev);
+
+static inline struct i915_gem_context *
+i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id)
+{
+	struct i915_gem_context *ctx;
+
+	lockdep_assert_held(&file_priv->dev_priv->drm.struct_mutex);
+
+	ctx = idr_find(&file_priv->context_idr, id);
+	if (!ctx)
+		return ERR_PTR(-ENOENT);
+
+	return ctx;
+}
+
+static inline void i915_gem_context_reference(struct i915_gem_context *ctx)
 {
 	kref_get(&ctx->ref);
 }
 
-static inline void i915_gem_context_unreference(struct intel_context *ctx)
+static inline void i915_gem_context_unreference(struct i915_gem_context *ctx)
 {
+	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
 	kref_put(&ctx->ref, i915_gem_context_free);
 }
 
-static inline bool i915_gem_context_is_default(const struct intel_context *c)
+static inline bool i915_gem_context_is_default(const struct i915_gem_context *c)
 {
 	return c->user_handle == DEFAULT_CONTEXT_HANDLE;
 }
@@ -3347,6 +3572,8 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *file_priv);
 int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *file_priv);
+int i915_gem_context_reset_stats_ioctl(struct drm_device *dev, void *data,
+				       struct drm_file *file);
 
 /* i915_gem_evict.c */
 int __must_check i915_gem_evict_something(struct drm_device *dev,
@@ -3361,9 +3588,9 @@ int __must_check i915_gem_evict_for_vma(struct i915_vma *target);
 int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle);
 
 /* belongs in i915_gem_gtt.h */
-static inline void i915_gem_chipset_flush(struct drm_device *dev)
+static inline void i915_gem_chipset_flush(struct drm_i915_private *dev_priv)
 {
-	if (INTEL_INFO(dev)->gen < 6)
+	if (INTEL_GEN(dev_priv) < 6)
 		intel_gtt_chipset_flush();
 }
 
@@ -3404,7 +3631,7 @@ void i915_gem_shrinker_cleanup(struct drm_i915_private *dev_priv);
 /* i915_gem_tiling.c */
 static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 
 	return dev_priv->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_9_10_17 &&
 		obj->tiling_mode != I915_TILING_NONE;
@@ -3418,12 +3645,14 @@ int i915_verify_lists(struct drm_device *dev);
 #endif
 
 /* i915_debugfs.c */
-int i915_debugfs_init(struct drm_minor *minor);
-void i915_debugfs_cleanup(struct drm_minor *minor);
 #ifdef CONFIG_DEBUG_FS
+int i915_debugfs_register(struct drm_i915_private *dev_priv);
+void i915_debugfs_unregister(struct drm_i915_private *dev_priv);
 int i915_debugfs_connector_add(struct drm_connector *connector);
 void intel_display_crc_init(struct drm_device *dev);
 #else
+static inline int i915_debugfs_register(struct drm_i915_private *) {return 0;}
+static inline void i915_debugfs_unregister(struct drm_i915_private *) {}
 static inline int i915_debugfs_connector_add(struct drm_connector *connector)
 { return 0; }
 static inline void intel_display_crc_init(struct drm_device *dev) {}
@@ -3442,18 +3671,19 @@ static inline void i915_error_state_buf_release(
 {
 	kfree(eb->buf);
 }
-void i915_capture_error_state(struct drm_device *dev, u32 engine_mask,
+void i915_capture_error_state(struct drm_i915_private *dev_priv,
+			      u32 engine_mask,
 			      const char *error_msg);
 void i915_error_state_get(struct drm_device *dev,
 			  struct i915_error_state_file_priv *error_priv);
 void i915_error_state_put(struct i915_error_state_file_priv *error_priv);
 void i915_destroy_error_state(struct drm_device *dev);
 
-void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone);
+void i915_get_extra_instdone(struct drm_i915_private *dev_priv, uint32_t *instdone);
 const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 
 /* i915_cmd_parser.c */
-int i915_cmd_parser_get_version(void);
+int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
 int i915_cmd_parser_init_ring(struct intel_engine_cs *engine);
 void i915_cmd_parser_fini_ring(struct intel_engine_cs *engine);
 bool i915_needs_cmd_parser(struct intel_engine_cs *engine);
@@ -3502,31 +3732,33 @@ bool intel_bios_is_port_hpd_inverted(struct drm_i915_private *dev_priv,
 
 /* intel_opregion.c */
 #ifdef CONFIG_ACPI
-extern int intel_opregion_setup(struct drm_device *dev);
-extern void intel_opregion_init(struct drm_device *dev);
-extern void intel_opregion_fini(struct drm_device *dev);
-extern void intel_opregion_asle_intr(struct drm_device *dev);
+extern int intel_opregion_setup(struct drm_i915_private *dev_priv);
+extern void intel_opregion_register(struct drm_i915_private *dev_priv);
+extern void intel_opregion_unregister(struct drm_i915_private *dev_priv);
+extern void intel_opregion_asle_intr(struct drm_i915_private *dev_priv);
 extern int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder,
 					 bool enable);
-extern int intel_opregion_notify_adapter(struct drm_device *dev,
+extern int intel_opregion_notify_adapter(struct drm_i915_private *dev_priv,
 					 pci_power_t state);
-extern int intel_opregion_get_panel_type(struct drm_device *dev);
+extern int intel_opregion_get_panel_type(struct drm_i915_private *dev_priv);
 #else
-static inline int intel_opregion_setup(struct drm_device *dev) { return 0; }
-static inline void intel_opregion_init(struct drm_device *dev) { return; }
-static inline void intel_opregion_fini(struct drm_device *dev) { return; }
-static inline void intel_opregion_asle_intr(struct drm_device *dev) { return; }
+static inline int intel_opregion_setup(struct drm_i915_private *dev) { return 0; }
+static inline void intel_opregion_register(struct drm_i915_private *dev_priv) { }
+static inline void intel_opregion_unregister(struct drm_i915_private *dev_priv) { }
+static inline void intel_opregion_asle_intr(struct drm_i915_private *dev_priv)
+{
+}
 static inline int
 intel_opregion_notify_encoder(struct intel_encoder *intel_encoder, bool enable)
 {
 	return 0;
 }
 static inline int
-intel_opregion_notify_adapter(struct drm_device *dev, pci_power_t state)
+intel_opregion_notify_adapter(struct drm_i915_private *dev, pci_power_t state)
 {
 	return 0;
 }
-static inline int intel_opregion_get_panel_type(struct drm_device *dev)
+static inline int intel_opregion_get_panel_type(struct drm_i915_private *dev)
 {
 	return -ENODEV;
 }
@@ -3541,36 +3773,45 @@ static inline void intel_register_dsm_handler(void) { return; }
 static inline void intel_unregister_dsm_handler(void) { return; }
 #endif /* CONFIG_ACPI */
 
+/* intel_device_info.c */
+static inline struct intel_device_info *
+mkwrite_device_info(struct drm_i915_private *dev_priv)
+{
+	return (struct intel_device_info *)&dev_priv->info;
+}
+
+void intel_device_info_runtime_init(struct drm_i915_private *dev_priv);
+void intel_device_info_dump(struct drm_i915_private *dev_priv);
+
 /* modesetting */
 extern void intel_modeset_init_hw(struct drm_device *dev);
 extern void intel_modeset_init(struct drm_device *dev);
 extern void intel_modeset_gem_init(struct drm_device *dev);
 extern void intel_modeset_cleanup(struct drm_device *dev);
-extern void intel_connector_unregister(struct intel_connector *);
+extern int intel_connector_register(struct drm_connector *);
+extern void intel_connector_unregister(struct drm_connector *);
 extern int intel_modeset_vga_set_state(struct drm_device *dev, bool state);
 extern void intel_display_resume(struct drm_device *dev);
 extern void i915_redisable_vga(struct drm_device *dev);
 extern void i915_redisable_vga_power_on(struct drm_device *dev);
-extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
+extern bool ironlake_set_drps(struct drm_i915_private *dev_priv, u8 val);
 extern void intel_init_pch_refclk(struct drm_device *dev);
-extern void intel_set_rps(struct drm_device *dev, u8 val);
+extern void intel_set_rps(struct drm_i915_private *dev_priv, u8 val);
 extern void intel_set_memory_cxsr(struct drm_i915_private *dev_priv,
 				  bool enable);
-extern void intel_detect_pch(struct drm_device *dev);
-extern int intel_enable_rc6(const struct drm_device *dev);
 
-extern bool i915_semaphore_is_enabled(struct drm_device *dev);
+extern bool i915_semaphore_is_enabled(struct drm_i915_private *dev_priv);
 int i915_reg_read_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file);
-int i915_get_reset_stats_ioctl(struct drm_device *dev, void *data,
-			       struct drm_file *file);
 
 /* overlay */
-extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
+extern struct intel_overlay_error_state *
+intel_overlay_capture_error_state(struct drm_i915_private *dev_priv);
 extern void intel_overlay_print_error_state(struct drm_i915_error_state_buf *e,
 					    struct intel_overlay_error_state *error);
 
-extern struct intel_display_error_state *intel_display_capture_error_state(struct drm_device *dev);
+extern struct intel_display_error_state *
+intel_display_capture_error_state(struct drm_i915_private *dev_priv);
 extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 					    struct drm_device *dev,
 					    struct intel_display_error_state *error);
@@ -3599,6 +3840,24 @@ void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
 u32 vlv_flisdsi_read(struct drm_i915_private *dev_priv, u32 reg);
 void vlv_flisdsi_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
 
+/* intel_dpio_phy.c */
+void chv_set_phy_signal_level(struct intel_encoder *encoder,
+			      u32 deemph_reg_value, u32 margin_reg_value,
+			      bool uniq_trans_scale);
+void chv_data_lane_soft_reset(struct intel_encoder *encoder,
+			      bool reset);
+void chv_phy_pre_pll_enable(struct intel_encoder *encoder);
+void chv_phy_pre_encoder_enable(struct intel_encoder *encoder);
+void chv_phy_release_cl2_override(struct intel_encoder *encoder);
+void chv_phy_post_pll_disable(struct intel_encoder *encoder);
+
+void vlv_set_phy_signal_level(struct intel_encoder *encoder,
+			      u32 demph_reg_value, u32 preemph_reg_value,
+			      u32 uniqtranscale_reg_value, u32 tx3_demph);
+void vlv_phy_pre_pll_enable(struct intel_encoder *encoder);
+void vlv_phy_pre_encoder_enable(struct intel_encoder *encoder);
+void vlv_phy_reset_lanes(struct intel_encoder *encoder);
+
 int intel_gpu_freq(struct drm_i915_private *dev_priv, int val);
 int intel_freq_opcode(struct drm_i915_private *dev_priv, int val);
 
@@ -3672,6 +3931,7 @@ __raw_write(64, q)
  */
 #define I915_READ_FW(reg__) __raw_i915_read32(dev_priv, (reg__))
 #define I915_WRITE_FW(reg__, val__) __raw_i915_write32(dev_priv, (reg__), (val__))
+#define I915_WRITE64_FW(reg__, val__) __raw_i915_write64(dev_priv, (reg__), (val__))
 #define POSTING_READ_FW(reg__) (void)I915_READ_FW(reg__)
 
 /* "Broadcast RGB" property */
@@ -3735,12 +3995,80 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms)
 			    schedule_timeout_uninterruptible(remaining_jiffies);
 	}
 }
-
-static inline void i915_trace_irq_get(struct intel_engine_cs *engine,
-				      struct drm_i915_gem_request *req)
+static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req)
 {
-	if (engine->trace_irq_req == NULL && engine->irq_get(engine))
-		i915_gem_request_assign(&engine->trace_irq_req, req);
+	struct intel_engine_cs *engine = req->engine;
+
+	/* Before we do the heavier coherent read of the seqno,
+	 * check the value (hopefully) in the CPU cacheline.
+	 */
+	if (i915_gem_request_completed(req))
+		return true;
+
+	/* Ensure our read of the seqno is coherent so that we
+	 * do not "miss an interrupt" (i.e. if this is the last
+	 * request and the seqno write from the GPU is not visible
+	 * by the time the interrupt fires, we will see that the
+	 * request is incomplete and go back to sleep awaiting
+	 * another interrupt that will never come.)
+	 *
+	 * Strictly, we only need to do this once after an interrupt,
+	 * but it is easier and safer to do it every time the waiter
+	 * is woken.
+	 */
+	if (engine->irq_seqno_barrier &&
+	    READ_ONCE(engine->breadcrumbs.irq_seqno_bh) == current &&
+	    cmpxchg_relaxed(&engine->breadcrumbs.irq_posted, 1, 0)) {
+		struct task_struct *tsk;
+
+		/* The ordering of irq_posted versus applying the barrier
+		 * is crucial. The clearing of the current irq_posted must
+		 * be visible before we perform the barrier operation,
+		 * such that if a subsequent interrupt arrives, irq_posted
+		 * is reasserted and our task rewoken (which causes us to
+		 * do another __i915_request_irq_complete() immediately
+		 * and reapply the barrier). Conversely, if the clear
+		 * occurs after the barrier, then an interrupt that arrived
+		 * whilst we waited on the barrier would not trigger a
+		 * barrier on the next pass, and the read may not see the
+		 * seqno update.
+		 */
+		engine->irq_seqno_barrier(engine);
+
+		/* If we consume the irq, but we are no longer the bottom-half,
+		 * the real bottom-half may not have serialised their own
+		 * seqno check with the irq-barrier (i.e. may have inspected
+		 * the seqno before we believe it coherent since they see
+		 * irq_posted == false but we are still running).
+		 */
+		rcu_read_lock();
+		tsk = READ_ONCE(engine->breadcrumbs.irq_seqno_bh);
+		if (tsk && tsk != current)
+			/* Note that if the bottom-half is changed as we
+			 * are sending the wake-up, the new bottom-half will
+			 * be woken by whomever made the change. We only have
+			 * to worry about when we steal the irq-posted for
+			 * ourself.
+			 */
+			wake_up_process(tsk);
+		rcu_read_unlock();
+
+		if (i915_gem_request_completed(req))
+			return true;
+	}
+
+	/* We need to check whether any gpu reset happened in between
+	 * the request being submitted and now. If a reset has occurred,
+	 * the seqno will have been advance past ours and our request
+	 * is complete. If we are in the process of handling a reset,
+	 * the request is effectively complete as the rendering will
+	 * be discarded, but we need to return in order to drop the
+	 * struct_mutex.
+	 */
+	if (i915_reset_in_progress(&req->i915->gpu_error))
+		return true;
+
+	return false;
 }
 
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ed6117a0ee84..11681501d7b1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -54,12 +54,33 @@ static bool cpu_cache_is_coherent(struct drm_device *dev,
 
 static bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
 {
+	if (obj->base.write_domain == I915_GEM_DOMAIN_CPU)
+		return false;
+
 	if (!cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
 		return true;
 
 	return obj->pin_display;
 }
 
+static int
+insert_mappable_node(struct drm_i915_private *i915,
+                     struct drm_mm_node *node, u32 size)
+{
+	memset(node, 0, sizeof(*node));
+	return drm_mm_insert_node_in_range_generic(&i915->ggtt.base.mm, node,
+						   size, 0, 0, 0,
+						   i915->ggtt.mappable_end,
+						   DRM_MM_SEARCH_DEFAULT,
+						   DRM_MM_CREATE_DEFAULT);
+}
+
+static void
+remove_mappable_node(struct drm_mm_node *node)
+{
+	drm_mm_remove_node(node);
+}
+
 /* some bookkeeping */
 static void i915_gem_info_add_obj(struct drm_i915_private *dev_priv,
 				  size_t size)
@@ -107,7 +128,7 @@ i915_gem_wait_for_error(struct i915_gpu_error *error)
 
 int i915_mutex_lock_interruptible(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	ret = i915_gem_wait_for_error(&dev_priv->gpu_error);
@@ -177,7 +198,7 @@ i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 		vaddr += PAGE_SIZE;
 	}
 
-	i915_gem_chipset_flush(obj->base.dev);
+	i915_gem_chipset_flush(to_i915(obj->base.dev));
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
 	if (st == NULL)
@@ -347,7 +368,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
 	}
 
 	drm_clflush_virt_range(vaddr, args->size);
-	i915_gem_chipset_flush(dev);
+	i915_gem_chipset_flush(to_i915(dev));
 
 out:
 	intel_fb_obj_flush(obj, false, ORIGIN_CPU);
@@ -356,13 +377,13 @@ out:
 
 void *i915_gem_object_alloc(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	return kmem_cache_zalloc(dev_priv->objects, GFP_KERNEL);
 }
 
 void i915_gem_object_free(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	kmem_cache_free(dev_priv->objects, obj);
 }
 
@@ -381,9 +402,9 @@ i915_gem_create(struct drm_file *file,
 		return -EINVAL;
 
 	/* Allocate the new object */
-	obj = i915_gem_alloc_object(dev, size);
-	if (obj == NULL)
-		return -ENOMEM;
+	obj = i915_gem_object_create(dev, size);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
 	ret = drm_gem_handle_create(file, &obj->base, &handle);
 	/* drop reference from allocate - handle holds it now */
@@ -409,6 +430,9 @@ i915_gem_dumb_create(struct drm_file *file,
 
 /**
  * Creates a new mm object and returns a handle to it.
+ * @dev: drm device pointer
+ * @data: ioctl data blob
+ * @file: drm file pointer
  */
 int
 i915_gem_create_ioctl(struct drm_device *dev, void *data,
@@ -484,7 +508,7 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj,
 
 	*needs_clflush = 0;
 
-	if (WARN_ON((obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE) == 0))
+	if (WARN_ON(!i915_gem_object_has_struct_page(obj)))
 		return -EINVAL;
 
 	if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU)) {
@@ -585,6 +609,142 @@ shmem_pread_slow(struct page *page, int shmem_page_offset, int page_length,
 	return ret ? - EFAULT : 0;
 }
 
+static inline unsigned long
+slow_user_access(struct io_mapping *mapping,
+		 uint64_t page_base, int page_offset,
+		 char __user *user_data,
+		 unsigned long length, bool pwrite)
+{
+	void __iomem *ioaddr;
+	void *vaddr;
+	uint64_t unwritten;
+
+	ioaddr = io_mapping_map_wc(mapping, page_base, PAGE_SIZE);
+	/* We can use the cpu mem copy function because this is X86. */
+	vaddr = (void __force *)ioaddr + page_offset;
+	if (pwrite)
+		unwritten = __copy_from_user(vaddr, user_data, length);
+	else
+		unwritten = __copy_to_user(user_data, vaddr, length);
+
+	io_mapping_unmap(ioaddr);
+	return unwritten;
+}
+
+static int
+i915_gem_gtt_pread(struct drm_device *dev,
+		   struct drm_i915_gem_object *obj, uint64_t size,
+		   uint64_t data_offset, uint64_t data_ptr)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct drm_mm_node node;
+	char __user *user_data;
+	uint64_t remain;
+	uint64_t offset;
+	int ret;
+
+	ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE);
+	if (ret) {
+		ret = insert_mappable_node(dev_priv, &node, PAGE_SIZE);
+		if (ret)
+			goto out;
+
+		ret = i915_gem_object_get_pages(obj);
+		if (ret) {
+			remove_mappable_node(&node);
+			goto out;
+		}
+
+		i915_gem_object_pin_pages(obj);
+	} else {
+		node.start = i915_gem_obj_ggtt_offset(obj);
+		node.allocated = false;
+		ret = i915_gem_object_put_fence(obj);
+		if (ret)
+			goto out_unpin;
+	}
+
+	ret = i915_gem_object_set_to_gtt_domain(obj, false);
+	if (ret)
+		goto out_unpin;
+
+	user_data = u64_to_user_ptr(data_ptr);
+	remain = size;
+	offset = data_offset;
+
+	mutex_unlock(&dev->struct_mutex);
+	if (likely(!i915.prefault_disable)) {
+		ret = fault_in_multipages_writeable(user_data, remain);
+		if (ret) {
+			mutex_lock(&dev->struct_mutex);
+			goto out_unpin;
+		}
+	}
+
+	while (remain > 0) {
+		/* Operation in this page
+		 *
+		 * page_base = page offset within aperture
+		 * page_offset = offset within page
+		 * page_length = bytes to copy for this page
+		 */
+		u32 page_base = node.start;
+		unsigned page_offset = offset_in_page(offset);
+		unsigned page_length = PAGE_SIZE - page_offset;
+		page_length = remain < page_length ? remain : page_length;
+		if (node.allocated) {
+			wmb();
+			ggtt->base.insert_page(&ggtt->base,
+					       i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
+					       node.start,
+					       I915_CACHE_NONE, 0);
+			wmb();
+		} else {
+			page_base += offset & PAGE_MASK;
+		}
+		/* This is a slow read/write as it tries to read from
+		 * and write to user memory which may result into page
+		 * faults, and so we cannot perform this under struct_mutex.
+		 */
+		if (slow_user_access(ggtt->mappable, page_base,
+				     page_offset, user_data,
+				     page_length, false)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		remain -= page_length;
+		user_data += page_length;
+		offset += page_length;
+	}
+
+	mutex_lock(&dev->struct_mutex);
+	if (ret == 0 && (obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0) {
+		/* The user has modified the object whilst we tried
+		 * reading from it, and we now have no idea what domain
+		 * the pages should be in. As we have just been touching
+		 * them directly, flush everything back to the GTT
+		 * domain.
+		 */
+		ret = i915_gem_object_set_to_gtt_domain(obj, false);
+	}
+
+out_unpin:
+	if (node.allocated) {
+		wmb();
+		ggtt->base.clear_range(&ggtt->base,
+				       node.start, node.size,
+				       true);
+		i915_gem_object_unpin_pages(obj);
+		remove_mappable_node(&node);
+	} else {
+		i915_gem_object_ggtt_unpin(obj);
+	}
+out:
+	return ret;
+}
+
 static int
 i915_gem_shmem_pread(struct drm_device *dev,
 		     struct drm_i915_gem_object *obj,
@@ -600,6 +760,9 @@ i915_gem_shmem_pread(struct drm_device *dev,
 	int needs_clflush = 0;
 	struct sg_page_iter sg_iter;
 
+	if (!i915_gem_object_has_struct_page(obj))
+		return -ENODEV;
+
 	user_data = u64_to_user_ptr(args->data_ptr);
 	remain = args->size;
 
@@ -672,6 +835,9 @@ out:
 
 /**
  * Reads data from the object referenced by handle.
+ * @dev: drm device pointer
+ * @data: ioctl data blob
+ * @file: drm file pointer
  *
  * On error, the contents of *data are undefined.
  */
@@ -708,18 +874,15 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	/* prime objects have no backing filp to GEM pread/pwrite
-	 * pages from.
-	 */
-	if (!obj->base.filp) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	trace_i915_gem_object_pread(obj, args->offset, args->size);
 
 	ret = i915_gem_shmem_pread(dev, obj, args, file);
 
+	/* pread for non shmem backed objects */
+	if (ret == -EFAULT || ret == -ENODEV)
+		ret = i915_gem_gtt_pread(dev, obj, args->size,
+					args->offset, args->data_ptr);
+
 out:
 	drm_gem_object_unreference(&obj->base);
 unlock:
@@ -753,60 +916,99 @@ fast_user_write(struct io_mapping *mapping,
 /**
  * This is the fast pwrite path, where we copy the data directly from the
  * user into the GTT, uncached.
+ * @dev: drm device pointer
+ * @obj: i915 gem object
+ * @args: pwrite arguments structure
+ * @file: drm file pointer
  */
 static int
-i915_gem_gtt_pwrite_fast(struct drm_device *dev,
+i915_gem_gtt_pwrite_fast(struct drm_i915_private *i915,
 			 struct drm_i915_gem_object *obj,
 			 struct drm_i915_gem_pwrite *args,
 			 struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	ssize_t remain;
-	loff_t offset, page_base;
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct drm_device *dev = obj->base.dev;
+	struct drm_mm_node node;
+	uint64_t remain, offset;
 	char __user *user_data;
-	int page_offset, page_length, ret;
+	int ret;
+	bool hit_slow_path = false;
+
+	if (obj->tiling_mode != I915_TILING_NONE)
+		return -EFAULT;
 
 	ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE | PIN_NONBLOCK);
-	if (ret)
-		goto out;
+	if (ret) {
+		ret = insert_mappable_node(i915, &node, PAGE_SIZE);
+		if (ret)
+			goto out;
+
+		ret = i915_gem_object_get_pages(obj);
+		if (ret) {
+			remove_mappable_node(&node);
+			goto out;
+		}
+
+		i915_gem_object_pin_pages(obj);
+	} else {
+		node.start = i915_gem_obj_ggtt_offset(obj);
+		node.allocated = false;
+		ret = i915_gem_object_put_fence(obj);
+		if (ret)
+			goto out_unpin;
+	}
 
 	ret = i915_gem_object_set_to_gtt_domain(obj, true);
 	if (ret)
 		goto out_unpin;
 
-	ret = i915_gem_object_put_fence(obj);
-	if (ret)
-		goto out_unpin;
+	intel_fb_obj_invalidate(obj, ORIGIN_GTT);
+	obj->dirty = true;
 
 	user_data = u64_to_user_ptr(args->data_ptr);
+	offset = args->offset;
 	remain = args->size;
-
-	offset = i915_gem_obj_ggtt_offset(obj) + args->offset;
-
-	intel_fb_obj_invalidate(obj, ORIGIN_GTT);
-
-	while (remain > 0) {
+	while (remain) {
 		/* Operation in this page
 		 *
 		 * page_base = page offset within aperture
 		 * page_offset = offset within page
 		 * page_length = bytes to copy for this page
 		 */
-		page_base = offset & PAGE_MASK;
-		page_offset = offset_in_page(offset);
-		page_length = remain;
-		if ((page_offset + remain) > PAGE_SIZE)
-			page_length = PAGE_SIZE - page_offset;
-
+		u32 page_base = node.start;
+		unsigned page_offset = offset_in_page(offset);
+		unsigned page_length = PAGE_SIZE - page_offset;
+		page_length = remain < page_length ? remain : page_length;
+		if (node.allocated) {
+			wmb(); /* flush the write before we modify the GGTT */
+			ggtt->base.insert_page(&ggtt->base,
+					       i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
+					       node.start, I915_CACHE_NONE, 0);
+			wmb(); /* flush modifications to the GGTT (insert_page) */
+		} else {
+			page_base += offset & PAGE_MASK;
+		}
 		/* If we get a fault while copying data, then (presumably) our
 		 * source page isn't available.  Return the error and we'll
 		 * retry in the slow path.
+		 * If the object is non-shmem backed, we retry again with the
+		 * path that handles page fault.
 		 */
 		if (fast_user_write(ggtt->mappable, page_base,
 				    page_offset, user_data, page_length)) {
-			ret = -EFAULT;
-			goto out_flush;
+			hit_slow_path = true;
+			mutex_unlock(&dev->struct_mutex);
+			if (slow_user_access(ggtt->mappable,
+					     page_base,
+					     page_offset, user_data,
+					     page_length, true)) {
+				ret = -EFAULT;
+				mutex_lock(&dev->struct_mutex);
+				goto out_flush;
+			}
+
+			mutex_lock(&dev->struct_mutex);
 		}
 
 		remain -= page_length;
@@ -815,9 +1017,31 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 	}
 
 out_flush:
+	if (hit_slow_path) {
+		if (ret == 0 &&
+		    (obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0) {
+			/* The user has modified the object whilst we tried
+			 * reading from it, and we now have no idea what domain
+			 * the pages should be in. As we have just been touching
+			 * them directly, flush everything back to the GTT
+			 * domain.
+			 */
+			ret = i915_gem_object_set_to_gtt_domain(obj, false);
+		}
+	}
+
 	intel_fb_obj_flush(obj, false, ORIGIN_GTT);
 out_unpin:
-	i915_gem_object_ggtt_unpin(obj);
+	if (node.allocated) {
+		wmb();
+		ggtt->base.clear_range(&ggtt->base,
+				       node.start, node.size,
+				       true);
+		i915_gem_object_unpin_pages(obj);
+		remove_mappable_node(&node);
+	} else {
+		i915_gem_object_ggtt_unpin(obj);
+	}
 out:
 	return ret;
 }
@@ -1006,7 +1230,7 @@ out:
 	}
 
 	if (needs_clflush_after)
-		i915_gem_chipset_flush(dev);
+		i915_gem_chipset_flush(to_i915(dev));
 	else
 		obj->cache_dirty = true;
 
@@ -1016,6 +1240,9 @@ out:
 
 /**
  * Writes data to the object referenced by handle.
+ * @dev: drm device
+ * @data: ioctl data blob
+ * @file: drm file
  *
  * On error, the contents of the buffer that were to be modified are undefined.
  */
@@ -1023,7 +1250,7 @@ int
 i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_pwrite *args = data;
 	struct drm_i915_gem_object *obj;
 	int ret;
@@ -1062,14 +1289,6 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	/* prime objects have no backing filp to GEM pread/pwrite
-	 * pages from.
-	 */
-	if (!obj->base.filp) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	trace_i915_gem_object_pwrite(obj, args->offset, args->size);
 
 	ret = -EFAULT;
@@ -1079,20 +1298,21 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 	 * pread/pwrite currently are reading and writing from the CPU
 	 * perspective, requiring manual detiling by the client.
 	 */
-	if (obj->tiling_mode == I915_TILING_NONE &&
-	    obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
+	if (!i915_gem_object_has_struct_page(obj) ||
 	    cpu_write_needs_clflush(obj)) {
-		ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file);
+		ret = i915_gem_gtt_pwrite_fast(dev_priv, obj, args, file);
 		/* Note that the gtt paths might fail with non-page-backed user
 		 * pointers (e.g. gtt mappings when moving data between
 		 * textures). Fallback to the shmem path in that case. */
 	}
 
-	if (ret == -EFAULT || ret == -ENOSPC) {
+	if (ret == -EFAULT) {
 		if (obj->phys_handle)
 			ret = i915_gem_phys_pwrite(obj, args, file);
-		else
+		else if (i915_gem_object_has_struct_page(obj))
 			ret = i915_gem_shmem_pwrite(dev, obj, args, file);
+		else
+			ret = -ENODEV;
 	}
 
 out:
@@ -1123,17 +1343,6 @@ i915_gem_check_wedge(unsigned reset_counter, bool interruptible)
 	return 0;
 }
 
-static void fake_irq(unsigned long data)
-{
-	wake_up_process((struct task_struct *)data);
-}
-
-static bool missed_irq(struct drm_i915_private *dev_priv,
-		       struct intel_engine_cs *engine)
-{
-	return test_bit(engine->id, &dev_priv->gpu_error.missed_irq_rings);
-}
-
 static unsigned long local_clock_us(unsigned *cpu)
 {
 	unsigned long t;
@@ -1166,9 +1375,9 @@ static bool busywait_stop(unsigned long timeout, unsigned cpu)
 	return this_cpu != cpu;
 }
 
-static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
+bool __i915_spin_request(const struct drm_i915_gem_request *req,
+			 int state, unsigned long timeout_us)
 {
-	unsigned long timeout;
 	unsigned cpu;
 
 	/* When waiting for high frequency requests, e.g. during synchronous
@@ -1181,31 +1390,21 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
 	 * takes to sleep on a request, on the order of a microsecond.
 	 */
 
-	if (req->engine->irq_refcount)
-		return -EBUSY;
-
-	/* Only spin if we know the GPU is processing this request */
-	if (!i915_gem_request_started(req, true))
-		return -EAGAIN;
-
-	timeout = local_clock_us(&cpu) + 5;
-	while (!need_resched()) {
-		if (i915_gem_request_completed(req, true))
-			return 0;
+	timeout_us += local_clock_us(&cpu);
+	do {
+		if (i915_gem_request_completed(req))
+			return true;
 
 		if (signal_pending_state(state, current))
 			break;
 
-		if (busywait_stop(timeout, cpu))
+		if (busywait_stop(timeout_us, cpu))
 			break;
 
 		cpu_relax_lowlatency();
-	}
+	} while (!need_resched());
 
-	if (i915_gem_request_completed(req, false))
-		return 0;
-
-	return -EAGAIN;
+	return false;
 }
 
 /**
@@ -1213,6 +1412,7 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
  * @req: duh!
  * @interruptible: do an interruptible wait (normally yes)
  * @timeout: in - how long to wait (NULL forever); out - how much time remaining
+ * @rps: RPS client
  *
  * Note: It is of utmost importance that the passed in seqno and reset_counter
  * values have been read by the caller in an smp safe manner. Where read-side
@@ -1229,26 +1429,22 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 			s64 *timeout,
 			struct intel_rps_client *rps)
 {
-	struct intel_engine_cs *engine = i915_gem_request_get_engine(req);
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const bool irq_test_in_progress =
-		ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_engine_flag(engine);
 	int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE;
-	DEFINE_WAIT(wait);
-	unsigned long timeout_expire;
+	DEFINE_WAIT(reset);
+	struct intel_wait wait;
+	unsigned long timeout_remain;
 	s64 before = 0; /* Only to silence a compiler warning. */
-	int ret;
+	int ret = 0;
 
-	WARN(!intel_irqs_enabled(dev_priv), "IRQs disabled");
+	might_sleep();
 
 	if (list_empty(&req->list))
 		return 0;
 
-	if (i915_gem_request_completed(req, true))
+	if (i915_gem_request_completed(req))
 		return 0;
 
-	timeout_expire = 0;
+	timeout_remain = MAX_SCHEDULE_TIMEOUT;
 	if (timeout) {
 		if (WARN_ON(*timeout < 0))
 			return -EINVAL;
@@ -1256,7 +1452,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 		if (*timeout == 0)
 			return -ETIME;
 
-		timeout_expire = jiffies + nsecs_to_jiffies_timeout(*timeout);
+		timeout_remain = nsecs_to_jiffies_timeout(*timeout);
 
 		/*
 		 * Record current time in case interrupted by signal, or wedged.
@@ -1264,75 +1460,76 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 		before = ktime_get_raw_ns();
 	}
 
-	if (INTEL_INFO(dev_priv)->gen >= 6)
-		gen6_rps_boost(dev_priv, rps, req->emitted_jiffies);
-
 	trace_i915_gem_request_wait_begin(req);
 
-	/* Optimistic spin for the next jiffie before touching IRQs */
-	ret = __i915_spin_request(req, state);
-	if (ret == 0)
-		goto out;
-
-	if (!irq_test_in_progress && WARN_ON(!engine->irq_get(engine))) {
-		ret = -ENODEV;
-		goto out;
-	}
+	/* This client is about to stall waiting for the GPU. In many cases
+	 * this is undesirable and limits the throughput of the system, as
+	 * many clients cannot continue processing user input/output whilst
+	 * blocked. RPS autotuning may take tens of milliseconds to respond
+	 * to the GPU load and thus incurs additional latency for the client.
+	 * We can circumvent that by promoting the GPU frequency to maximum
+	 * before we wait. This makes the GPU throttle up much more quickly
+	 * (good for benchmarks and user experience, e.g. window animations),
+	 * but at a cost of spending more power processing the workload
+	 * (bad for battery). Not all clients even want their results
+	 * immediately and for them we should just let the GPU select its own
+	 * frequency to maximise efficiency. To prevent a single client from
+	 * forcing the clocks too high for the whole system, we only allow
+	 * each client to waitboost once in a busy period.
+	 */
+	if (INTEL_INFO(req->i915)->gen >= 6)
+		gen6_rps_boost(req->i915, rps, req->emitted_jiffies);
 
-	for (;;) {
-		struct timer_list timer;
+	/* Optimistic spin for the next ~jiffie before touching IRQs */
+	if (i915_spin_request(req, state, 5))
+		goto complete;
 
-		prepare_to_wait(&engine->irq_queue, &wait, state);
+	set_current_state(state);
+	add_wait_queue(&req->i915->gpu_error.wait_queue, &reset);
 
-		/* We need to check whether any gpu reset happened in between
-		 * the request being submitted and now. If a reset has occurred,
-		 * the request is effectively complete (we either are in the
-		 * process of or have discarded the rendering and completely
-		 * reset the GPU. The results of the request are lost and we
-		 * are free to continue on with the original operation.
+	intel_wait_init(&wait, req->seqno);
+	if (intel_engine_add_wait(req->engine, &wait))
+		/* In order to check that we haven't missed the interrupt
+		 * as we enabled it, we need to kick ourselves to do a
+		 * coherent check on the seqno before we sleep.
 		 */
-		if (req->reset_counter != i915_reset_counter(&dev_priv->gpu_error)) {
-			ret = 0;
-			break;
-		}
-
-		if (i915_gem_request_completed(req, false)) {
-			ret = 0;
-			break;
-		}
+		goto wakeup;
 
+	for (;;) {
 		if (signal_pending_state(state, current)) {
 			ret = -ERESTARTSYS;
 			break;
 		}
 
-		if (timeout && time_after_eq(jiffies, timeout_expire)) {
+		timeout_remain = io_schedule_timeout(timeout_remain);
+		if (timeout_remain == 0) {
 			ret = -ETIME;
 			break;
 		}
 
-		timer.function = NULL;
-		if (timeout || missed_irq(dev_priv, engine)) {
-			unsigned long expire;
+		if (intel_wait_complete(&wait))
+			break;
 
-			setup_timer_on_stack(&timer, fake_irq, (unsigned long)current);
-			expire = missed_irq(dev_priv, engine) ? jiffies + 1 : timeout_expire;
-			mod_timer(&timer, expire);
-		}
+		set_current_state(state);
 
-		io_schedule();
+wakeup:
+		/* Carefully check if the request is complete, giving time
+		 * for the seqno to be visible following the interrupt.
+		 * We also have to check in case we are kicked by the GPU
+		 * reset in order to drop the struct_mutex.
+		 */
+		if (__i915_request_irq_complete(req))
+			break;
 
-		if (timer.function) {
-			del_singleshot_timer_sync(&timer);
-			destroy_timer_on_stack(&timer);
-		}
+		/* Only spin if we know the GPU is processing this request */
+		if (i915_spin_request(req, state, 2))
+			break;
 	}
-	if (!irq_test_in_progress)
-		engine->irq_put(engine);
+	remove_wait_queue(&req->i915->gpu_error.wait_queue, &reset);
 
-	finish_wait(&engine->irq_queue, &wait);
-
-out:
+	intel_engine_remove_wait(req->engine, &wait);
+	__set_current_state(TASK_RUNNING);
+complete:
 	trace_i915_gem_request_wait_end(req);
 
 	if (timeout) {
@@ -1351,6 +1548,22 @@ out:
 			*timeout = 0;
 	}
 
+	if (rps && req->seqno == req->engine->last_submitted_seqno) {
+		/* The GPU is now idle and this client has stalled.
+		 * Since no other client has submitted a request in the
+		 * meantime, assume that this client is the only one
+		 * supplying work to the GPU but is unable to keep that
+		 * work supplied because it is waiting. Since the GPU is
+		 * then never kept fully busy, RPS autoclocking will
+		 * keep the clocks relatively low, causing further delays.
+		 * Compensate by giving the synchronous client credit for
+		 * a waitboost next time.
+		 */
+		spin_lock(&req->i915->rps.client_lock);
+		list_del_init(&rps->link);
+		spin_unlock(&req->i915->rps.client_lock);
+	}
+
 	return ret;
 }
 
@@ -1413,6 +1626,13 @@ static void i915_gem_request_retire(struct drm_i915_gem_request *request)
 	list_del_init(&request->list);
 	i915_gem_request_remove_from_client(request);
 
+	if (request->previous_context) {
+		if (i915.enable_execlists)
+			intel_lr_context_unpin(request->previous_context,
+					       request->engine);
+	}
+
+	i915_gem_context_unreference(request->ctx);
 	i915_gem_request_unreference(request);
 }
 
@@ -1422,7 +1642,7 @@ __i915_gem_request_retire__upto(struct drm_i915_gem_request *req)
 	struct intel_engine_cs *engine = req->engine;
 	struct drm_i915_gem_request *tmp;
 
-	lockdep_assert_held(&engine->dev->struct_mutex);
+	lockdep_assert_held(&engine->i915->drm.struct_mutex);
 
 	if (list_empty(&req->list))
 		return;
@@ -1440,6 +1660,7 @@ __i915_gem_request_retire__upto(struct drm_i915_gem_request *req)
 /**
  * Waits for a request to be signaled, and cleans up the
  * request and object lists appropriately for that event.
+ * @req: request to wait on
  */
 int
 i915_wait_request(struct drm_i915_gem_request *req)
@@ -1450,14 +1671,14 @@ i915_wait_request(struct drm_i915_gem_request *req)
 
 	interruptible = dev_priv->mm.interruptible;
 
-	BUG_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
+	BUG_ON(!mutex_is_locked(&dev_priv->drm.struct_mutex));
 
 	ret = __i915_wait_request(req, interruptible, NULL, NULL);
 	if (ret)
 		return ret;
 
 	/* If the GPU hung, we want to keep the requests to find the guilty. */
-	if (req->reset_counter == i915_reset_counter(&dev_priv->gpu_error))
+	if (!i915_reset_in_progress(&dev_priv->gpu_error))
 		__i915_gem_request_retire__upto(req);
 
 	return 0;
@@ -1466,6 +1687,8 @@ i915_wait_request(struct drm_i915_gem_request *req)
 /**
  * Ensures that all rendering to the object has completed and the object is
  * safe to unbind from the GTT or access from the CPU.
+ * @obj: i915 gem object
+ * @readonly: waiting for read access or write
  */
 int
 i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
@@ -1516,7 +1739,7 @@ i915_gem_object_retire_request(struct drm_i915_gem_object *obj,
 	else if (obj->last_write_req == req)
 		i915_gem_object_retire__write(obj);
 
-	if (req->reset_counter == i915_reset_counter(&req->i915->gpu_error))
+	if (!i915_reset_in_progress(&req->i915->gpu_error))
 		__i915_gem_request_retire__upto(req);
 }
 
@@ -1529,7 +1752,7 @@ i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj,
 					    bool readonly)
 {
 	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_request *requests[I915_NUM_ENGINES];
 	int ret, i, n = 0;
 
@@ -1580,9 +1803,19 @@ static struct intel_rps_client *to_rps_client(struct drm_file *file)
 	return &fpriv->rps;
 }
 
+static enum fb_op_origin
+write_origin(struct drm_i915_gem_object *obj, unsigned domain)
+{
+	return domain == I915_GEM_DOMAIN_GTT && !obj->has_wc_mmap ?
+	       ORIGIN_GTT : ORIGIN_CPU;
+}
+
 /**
  * Called when user space prepares to use an object with the CPU, either
  * through the mmap ioctl's mapping or a GTT mapping.
+ * @dev: drm device
+ * @data: ioctl data blob
+ * @file: drm file
  */
 int
 i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
@@ -1633,9 +1866,7 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 		ret = i915_gem_object_set_to_cpu_domain(obj, write_domain != 0);
 
 	if (write_domain != 0)
-		intel_fb_obj_invalidate(obj,
-					write_domain == I915_GEM_DOMAIN_GTT ?
-					ORIGIN_GTT : ORIGIN_CPU);
+		intel_fb_obj_invalidate(obj, write_origin(obj, write_domain));
 
 unref:
 	drm_gem_object_unreference(&obj->base);
@@ -1646,6 +1877,9 @@ unlock:
 
 /**
  * Called when user space has done writes to this buffer
+ * @dev: drm device
+ * @data: ioctl data blob
+ * @file: drm file
  */
 int
 i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
@@ -1676,8 +1910,11 @@ unlock:
 }
 
 /**
- * Maps the contents of an object, returning the address it is mapped
- * into.
+ * i915_gem_mmap_ioctl - Maps the contents of an object, returning the address
+ *			 it is mapped to.
+ * @dev: drm device
+ * @data: ioctl data blob
+ * @file: drm file
  *
  * While the mapping holds a reference on the contents of the object, it doesn't
  * imply a ref on the object itself.
@@ -1736,6 +1973,9 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 		else
 			addr = -ENOMEM;
 		up_write(&mm->mmap_sem);
+
+		/* This may race, but that's ok, it only gets set */
+		WRITE_ONCE(to_intel_bo(obj)->has_wc_mmap, true);
 	}
 	drm_gem_object_unreference_unlocked(obj);
 	if (IS_ERR((void *)addr))
@@ -1982,7 +2222,7 @@ i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode)
 		return size;
 
 	/* Previous chips need a power-of-two fence region when tiling */
-	if (INTEL_INFO(dev)->gen == 3)
+	if (IS_GEN3(dev))
 		gtt_size = 1024*1024;
 	else
 		gtt_size = 512*1024;
@@ -1995,7 +2235,10 @@ i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode)
 
 /**
  * i915_gem_get_gtt_alignment - return required GTT alignment for an object
- * @obj: object to check
+ * @dev: drm device
+ * @size: object size
+ * @tiling_mode: tiling mode
+ * @fenced: is fenced alignemned required or not
  *
  * Return the required GTT alignment for an object, taking into account
  * potential fence register mapping.
@@ -2021,7 +2264,7 @@ i915_gem_get_gtt_alignment(struct drm_device *dev, uint32_t size,
 
 static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	int ret;
 
 	dev_priv->mm.shrinker_no_lock_stealing = true;
@@ -2162,7 +2405,8 @@ i915_gem_object_invalidate(struct drm_i915_gem_object *obj)
 static void
 i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj)
 {
-	struct sg_page_iter sg_iter;
+	struct sgt_iter sgt_iter;
+	struct page *page;
 	int ret;
 
 	BUG_ON(obj->madv == __I915_MADV_PURGED);
@@ -2184,9 +2428,7 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj)
 	if (obj->madv == I915_MADV_DONTNEED)
 		obj->dirty = 0;
 
-	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
-		struct page *page = sg_page_iter_page(&sg_iter);
-
+	for_each_sgt_page(page, sgt_iter, obj->pages) {
 		if (obj->dirty)
 			set_page_dirty(page);
 
@@ -2238,12 +2480,12 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 static int
 i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	int page_count, i;
 	struct address_space *mapping;
 	struct sg_table *st;
 	struct scatterlist *sg;
-	struct sg_page_iter sg_iter;
+	struct sgt_iter sgt_iter;
 	struct page *page;
 	unsigned long last_pfn = 0;	/* suppress gcc warning */
 	int ret;
@@ -2340,8 +2582,8 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 
 err_pages:
 	sg_mark_end(sg);
-	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0)
-		put_page(sg_page_iter_page(&sg_iter));
+	for_each_sgt_page(page, sgt_iter, st)
+		put_page(page);
 	sg_free_table(st);
 	kfree(st);
 
@@ -2369,7 +2611,7 @@ err_pages:
 int
 i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	const struct drm_i915_gem_object_ops *ops = obj->ops;
 	int ret;
 
@@ -2395,6 +2637,44 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
+/* The 'mapping' part of i915_gem_object_pin_map() below */
+static void *i915_gem_object_map(const struct drm_i915_gem_object *obj)
+{
+	unsigned long n_pages = obj->base.size >> PAGE_SHIFT;
+	struct sg_table *sgt = obj->pages;
+	struct sgt_iter sgt_iter;
+	struct page *page;
+	struct page *stack_pages[32];
+	struct page **pages = stack_pages;
+	unsigned long i = 0;
+	void *addr;
+
+	/* A single page can always be kmapped */
+	if (n_pages == 1)
+		return kmap(sg_page(sgt->sgl));
+
+	if (n_pages > ARRAY_SIZE(stack_pages)) {
+		/* Too big for stack -- allocate temporary array instead */
+		pages = drm_malloc_gfp(n_pages, sizeof(*pages), GFP_TEMPORARY);
+		if (!pages)
+			return NULL;
+	}
+
+	for_each_sgt_page(page, sgt_iter, sgt)
+		pages[i++] = page;
+
+	/* Check that we have the expected number of pages */
+	GEM_BUG_ON(i != n_pages);
+
+	addr = vmap(pages, n_pages, 0, PAGE_KERNEL);
+
+	if (pages != stack_pages)
+		drm_free_large(pages);
+
+	return addr;
+}
+
+/* get, pin, and map the pages of the object into kernel space */
 void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj)
 {
 	int ret;
@@ -2407,29 +2687,9 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj)
 
 	i915_gem_object_pin_pages(obj);
 
-	if (obj->mapping == NULL) {
-		struct page **pages;
-
-		pages = NULL;
-		if (obj->base.size == PAGE_SIZE)
-			obj->mapping = kmap(sg_page(obj->pages->sgl));
-		else
-			pages = drm_malloc_gfp(obj->base.size >> PAGE_SHIFT,
-					       sizeof(*pages),
-					       GFP_TEMPORARY);
-		if (pages != NULL) {
-			struct sg_page_iter sg_iter;
-			int n;
-
-			n = 0;
-			for_each_sg_page(obj->pages->sgl, &sg_iter,
-					 obj->pages->nents, 0)
-				pages[n++] = sg_page_iter_page(&sg_iter);
-
-			obj->mapping = vmap(pages, n, 0, PAGE_KERNEL);
-			drm_free_large(pages);
-		}
-		if (obj->mapping == NULL) {
+	if (!obj->mapping) {
+		obj->mapping = i915_gem_object_map(obj);
+		if (!obj->mapping) {
 			i915_gem_object_unpin_pages(obj);
 			return ERR_PTR(-ENOMEM);
 		}
@@ -2502,9 +2762,8 @@ i915_gem_object_retire__read(struct drm_i915_gem_object *obj, int ring)
 }
 
 static int
-i915_gem_init_seqno(struct drm_device *dev, u32 seqno)
+i915_gem_init_seqno(struct drm_i915_private *dev_priv, u32 seqno)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
 	int ret;
 
@@ -2514,7 +2773,14 @@ i915_gem_init_seqno(struct drm_device *dev, u32 seqno)
 		if (ret)
 			return ret;
 	}
-	i915_gem_retire_requests(dev);
+	i915_gem_retire_requests(dev_priv);
+
+	/* If the seqno wraps around, we need to clear the breadcrumb rbtree */
+	if (!i915_seqno_passed(seqno, dev_priv->next_seqno)) {
+		while (intel_kick_waiters(dev_priv) ||
+		       intel_kick_signalers(dev_priv))
+			yield();
+	}
 
 	/* Finally reset hw state */
 	for_each_engine(engine, dev_priv)
@@ -2525,7 +2791,7 @@ i915_gem_init_seqno(struct drm_device *dev, u32 seqno)
 
 int i915_gem_set_seqno(struct drm_device *dev, u32 seqno)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	if (seqno == 0)
@@ -2534,7 +2800,7 @@ int i915_gem_set_seqno(struct drm_device *dev, u32 seqno)
 	/* HWS page needs to be set less than what we
 	 * will inject to ring
 	 */
-	ret = i915_gem_init_seqno(dev, seqno - 1);
+	ret = i915_gem_init_seqno(dev_priv, seqno - 1);
 	if (ret)
 		return ret;
 
@@ -2550,13 +2816,11 @@ int i915_gem_set_seqno(struct drm_device *dev, u32 seqno)
 }
 
 int
-i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
+i915_gem_get_seqno(struct drm_i915_private *dev_priv, u32 *seqno)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	/* reserve 0 for non-seqno */
 	if (dev_priv->next_seqno == 0) {
-		int ret = i915_gem_init_seqno(dev, 0);
+		int ret = i915_gem_init_seqno(dev_priv, 0);
 		if (ret)
 			return ret;
 
@@ -2567,6 +2831,26 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
 	return 0;
 }
 
+static void i915_gem_mark_busy(const struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+
+	dev_priv->gt.active_engines |= intel_engine_flag(engine);
+	if (dev_priv->gt.awake)
+		return;
+
+	intel_runtime_pm_get_noresume(dev_priv);
+	dev_priv->gt.awake = true;
+
+	i915_update_gfx_val(dev_priv);
+	if (INTEL_GEN(dev_priv) >= 6)
+		gen6_rps_busy(dev_priv);
+
+	queue_delayed_work(dev_priv->wq,
+			   &dev_priv->gt.retire_work,
+			   round_jiffies_up_relative(HZ));
+}
+
 /*
  * NB: This function is not allowed to fail. Doing so would mean the the
  * request is not being tracked for completion but the work itself is
@@ -2577,16 +2861,15 @@ void __i915_add_request(struct drm_i915_gem_request *request,
 			bool flush_caches)
 {
 	struct intel_engine_cs *engine;
-	struct drm_i915_private *dev_priv;
 	struct intel_ringbuffer *ringbuf;
 	u32 request_start;
+	u32 reserved_tail;
 	int ret;
 
 	if (WARN_ON(request == NULL))
 		return;
 
 	engine = request->engine;
-	dev_priv = request->i915;
 	ringbuf = request->ringbuf;
 
 	/*
@@ -2594,9 +2877,10 @@ void __i915_add_request(struct drm_i915_gem_request *request,
 	 * should already have been reserved in the ring buffer. Let the ring
 	 * know that it is time to use that space up.
 	 */
-	intel_ring_reserved_space_use(ringbuf);
-
 	request_start = intel_ring_get_tail(ringbuf);
+	reserved_tail = request->reserved_space;
+	request->reserved_space = 0;
+
 	/*
 	 * Emit any outstanding flushes - execbuf can fail to emit the flush
 	 * after having emitted the batchbuffer command. Hence we need to fix
@@ -2651,56 +2935,42 @@ void __i915_add_request(struct drm_i915_gem_request *request,
 	}
 	/* Not allowed to fail! */
 	WARN(ret, "emit|add_request failed: %d!\n", ret);
-
-	i915_queue_hangcheck(engine->dev);
-
-	queue_delayed_work(dev_priv->wq,
-			   &dev_priv->mm.retire_work,
-			   round_jiffies_up_relative(HZ));
-	intel_mark_busy(dev_priv->dev);
-
 	/* Sanity check that the reserved size was large enough. */
-	intel_ring_reserved_space_end(ringbuf);
+	ret = intel_ring_get_tail(ringbuf) - request_start;
+	if (ret < 0)
+		ret += ringbuf->size;
+	WARN_ONCE(ret > reserved_tail,
+		  "Not enough space reserved (%d bytes) "
+		  "for adding the request (%d bytes)\n",
+		  reserved_tail, ret);
+
+	i915_gem_mark_busy(engine);
 }
 
-static bool i915_context_is_banned(struct drm_i915_private *dev_priv,
-				   const struct intel_context *ctx)
+static bool i915_context_is_banned(const struct i915_gem_context *ctx)
 {
 	unsigned long elapsed;
 
-	elapsed = get_seconds() - ctx->hang_stats.guilty_ts;
-
 	if (ctx->hang_stats.banned)
 		return true;
 
+	elapsed = get_seconds() - ctx->hang_stats.guilty_ts;
 	if (ctx->hang_stats.ban_period_seconds &&
 	    elapsed <= ctx->hang_stats.ban_period_seconds) {
-		if (!i915_gem_context_is_default(ctx)) {
-			DRM_DEBUG("context hanging too fast, banning!\n");
-			return true;
-		} else if (i915_stop_ring_allow_ban(dev_priv)) {
-			if (i915_stop_ring_allow_warn(dev_priv))
-				DRM_ERROR("gpu hanging too fast, banning!\n");
-			return true;
-		}
+		DRM_DEBUG("context hanging too fast, banning!\n");
+		return true;
 	}
 
 	return false;
 }
 
-static void i915_set_reset_status(struct drm_i915_private *dev_priv,
-				  struct intel_context *ctx,
+static void i915_set_reset_status(struct i915_gem_context *ctx,
 				  const bool guilty)
 {
-	struct i915_ctx_hang_stats *hs;
-
-	if (WARN_ON(!ctx))
-		return;
-
-	hs = &ctx->hang_stats;
+	struct i915_ctx_hang_stats *hs = &ctx->hang_stats;
 
 	if (guilty) {
-		hs->banned = i915_context_is_banned(dev_priv, ctx);
+		hs->banned = i915_context_is_banned(ctx);
 		hs->batch_active++;
 		hs->guilty_ts = get_seconds();
 	} else {
@@ -2712,27 +2982,15 @@ void i915_gem_request_free(struct kref *req_ref)
 {
 	struct drm_i915_gem_request *req = container_of(req_ref,
 						 typeof(*req), ref);
-	struct intel_context *ctx = req->ctx;
-
-	if (req->file_priv)
-		i915_gem_request_remove_from_client(req);
-
-	if (ctx) {
-		if (i915.enable_execlists && ctx != req->i915->kernel_context)
-			intel_lr_context_unpin(ctx, req->engine);
-
-		i915_gem_context_unreference(ctx);
-	}
-
 	kmem_cache_free(req->i915->requests, req);
 }
 
 static inline int
 __i915_gem_request_alloc(struct intel_engine_cs *engine,
-			 struct intel_context *ctx,
+			 struct i915_gem_context *ctx,
 			 struct drm_i915_gem_request **req_out)
 {
-	struct drm_i915_private *dev_priv = to_i915(engine->dev);
+	struct drm_i915_private *dev_priv = engine->i915;
 	unsigned reset_counter = i915_reset_counter(&dev_priv->gpu_error);
 	struct drm_i915_gem_request *req;
 	int ret;
@@ -2754,26 +3012,16 @@ __i915_gem_request_alloc(struct intel_engine_cs *engine,
 	if (req == NULL)
 		return -ENOMEM;
 
-	ret = i915_gem_get_seqno(engine->dev, &req->seqno);
+	ret = i915_gem_get_seqno(engine->i915, &req->seqno);
 	if (ret)
 		goto err;
 
 	kref_init(&req->ref);
 	req->i915 = dev_priv;
 	req->engine = engine;
-	req->reset_counter = reset_counter;
 	req->ctx  = ctx;
 	i915_gem_context_reference(req->ctx);
 
-	if (i915.enable_execlists)
-		ret = intel_logical_ring_alloc_request_extras(req);
-	else
-		ret = intel_ring_alloc_request_extras(req);
-	if (ret) {
-		i915_gem_context_unreference(req->ctx);
-		goto err;
-	}
-
 	/*
 	 * Reserve space in the ring buffer for all the commands required to
 	 * eventually emit this request. This is to guarantee that the
@@ -2781,24 +3029,20 @@ __i915_gem_request_alloc(struct intel_engine_cs *engine,
 	 * to be redone if the request is not actually submitted straight
 	 * away, e.g. because a GPU scheduler has deferred it.
 	 */
+	req->reserved_space = MIN_SPACE_FOR_ADD_REQUEST;
+
 	if (i915.enable_execlists)
-		ret = intel_logical_ring_reserve_space(req);
+		ret = intel_logical_ring_alloc_request_extras(req);
 	else
-		ret = intel_ring_reserve_space(req);
-	if (ret) {
-		/*
-		 * At this point, the request is fully allocated even if not
-		 * fully prepared. Thus it can be cleaned up using the proper
-		 * free code.
-		 */
-		intel_ring_reserved_space_cancel(req->ringbuf);
-		i915_gem_request_unreference(req);
-		return ret;
-	}
+		ret = intel_ring_alloc_request_extras(req);
+	if (ret)
+		goto err_ctx;
 
 	*req_out = req;
 	return 0;
 
+err_ctx:
+	i915_gem_context_unreference(ctx);
 err:
 	kmem_cache_free(dev_priv->requests, req);
 	return ret;
@@ -2818,13 +3062,13 @@ err:
  */
 struct drm_i915_gem_request *
 i915_gem_request_alloc(struct intel_engine_cs *engine,
-		       struct intel_context *ctx)
+		       struct i915_gem_context *ctx)
 {
 	struct drm_i915_gem_request *req;
 	int err;
 
 	if (ctx == NULL)
-		ctx = to_i915(engine->dev)->kernel_context;
+		ctx = engine->i915->kernel_context;
 	err = __i915_gem_request_alloc(engine, ctx, &req);
 	return err ? ERR_PTR(err) : req;
 }
@@ -2834,8 +3078,16 @@ i915_gem_find_active_request(struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_request *request;
 
+	/* We are called by the error capture and reset at a random
+	 * point in time. In particular, note that neither is crucially
+	 * ordered with an interrupt. After a hang, the GPU is dead and we
+	 * assume that no more writes can happen (we waited long enough for
+	 * all writes that were in transaction to be flushed) - adding an
+	 * extra delay for a recent interrupt is pointless. Hence, we do
+	 * not need an engine->irq_seqno_barrier() before the seqno reads.
+	 */
 	list_for_each_entry(request, &engine->request_list, list) {
-		if (i915_gem_request_completed(request, false))
+		if (i915_gem_request_completed(request))
 			continue;
 
 		return request;
@@ -2844,27 +3096,23 @@ i915_gem_find_active_request(struct intel_engine_cs *engine)
 	return NULL;
 }
 
-static void i915_gem_reset_engine_status(struct drm_i915_private *dev_priv,
-				       struct intel_engine_cs *engine)
+static void i915_gem_reset_engine_status(struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_request *request;
 	bool ring_hung;
 
 	request = i915_gem_find_active_request(engine);
-
 	if (request == NULL)
 		return;
 
 	ring_hung = engine->hangcheck.score >= HANGCHECK_SCORE_RING_HUNG;
 
-	i915_set_reset_status(dev_priv, request->ctx, ring_hung);
-
+	i915_set_reset_status(request->ctx, ring_hung);
 	list_for_each_entry_continue(request, &engine->request_list, list)
-		i915_set_reset_status(dev_priv, request->ctx, false);
+		i915_set_reset_status(request->ctx, false);
 }
 
-static void i915_gem_reset_engine_cleanup(struct drm_i915_private *dev_priv,
-					struct intel_engine_cs *engine)
+static void i915_gem_reset_engine_cleanup(struct intel_engine_cs *engine)
 {
 	struct intel_ringbuffer *buffer;
 
@@ -2888,13 +3136,7 @@ static void i915_gem_reset_engine_cleanup(struct drm_i915_private *dev_priv,
 		/* Ensure irq handler finishes or is cancelled. */
 		tasklet_kill(&engine->irq_tasklet);
 
-		spin_lock_bh(&engine->execlist_lock);
-		/* list_splice_tail_init checks for empty lists */
-		list_splice_tail_init(&engine->execlist_queue,
-				      &engine->execlist_retired_req_list);
-		spin_unlock_bh(&engine->execlist_lock);
-
-		intel_execlists_retire_requests(engine);
+		intel_execlists_cancel_requests(engine);
 	}
 
 	/*
@@ -2931,7 +3173,7 @@ static void i915_gem_reset_engine_cleanup(struct drm_i915_private *dev_priv,
 
 void i915_gem_reset(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 
 	/*
@@ -2940,10 +3182,10 @@ void i915_gem_reset(struct drm_device *dev)
 	 * their reference to the objects, the inspection must be done first.
 	 */
 	for_each_engine(engine, dev_priv)
-		i915_gem_reset_engine_status(dev_priv, engine);
+		i915_gem_reset_engine_status(engine);
 
 	for_each_engine(engine, dev_priv)
-		i915_gem_reset_engine_cleanup(dev_priv, engine);
+		i915_gem_reset_engine_cleanup(engine);
 
 	i915_gem_context_reset(dev);
 
@@ -2954,6 +3196,7 @@ void i915_gem_reset(struct drm_device *dev)
 
 /**
  * This function clears the request list as sequence numbers are passed.
+ * @engine: engine to retire requests on
  */
 void
 i915_gem_retire_requests_ring(struct intel_engine_cs *engine)
@@ -2972,7 +3215,7 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *engine)
 					   struct drm_i915_gem_request,
 					   list);
 
-		if (!i915_gem_request_completed(request, true))
+		if (!i915_gem_request_completed(request))
 			break;
 
 		i915_gem_request_retire(request);
@@ -2995,58 +3238,52 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *engine)
 		i915_gem_object_retire__read(obj, engine->id);
 	}
 
-	if (unlikely(engine->trace_irq_req &&
-		     i915_gem_request_completed(engine->trace_irq_req, true))) {
-		engine->irq_put(engine);
-		i915_gem_request_assign(&engine->trace_irq_req, NULL);
-	}
-
 	WARN_ON(i915_verify_lists(engine->dev));
 }
 
-bool
-i915_gem_retire_requests(struct drm_device *dev)
+void i915_gem_retire_requests(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
-	bool idle = true;
+
+	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+
+	if (dev_priv->gt.active_engines == 0)
+		return;
+
+	GEM_BUG_ON(!dev_priv->gt.awake);
 
 	for_each_engine(engine, dev_priv) {
 		i915_gem_retire_requests_ring(engine);
-		idle &= list_empty(&engine->request_list);
-		if (i915.enable_execlists) {
-			spin_lock_bh(&engine->execlist_lock);
-			idle &= list_empty(&engine->execlist_queue);
-			spin_unlock_bh(&engine->execlist_lock);
-
-			intel_execlists_retire_requests(engine);
-		}
+		if (list_empty(&engine->request_list))
+			dev_priv->gt.active_engines &= ~intel_engine_flag(engine);
 	}
 
-	if (idle)
-		mod_delayed_work(dev_priv->wq,
-				   &dev_priv->mm.idle_work,
+	if (dev_priv->gt.active_engines == 0)
+		queue_delayed_work(dev_priv->wq,
+				   &dev_priv->gt.idle_work,
 				   msecs_to_jiffies(100));
-
-	return idle;
 }
 
 static void
 i915_gem_retire_work_handler(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
-		container_of(work, typeof(*dev_priv), mm.retire_work.work);
-	struct drm_device *dev = dev_priv->dev;
-	bool idle;
+		container_of(work, typeof(*dev_priv), gt.retire_work.work);
+	struct drm_device *dev = &dev_priv->drm;
 
 	/* Come back later if the device is busy... */
-	idle = false;
 	if (mutex_trylock(&dev->struct_mutex)) {
-		idle = i915_gem_retire_requests(dev);
+		i915_gem_retire_requests(dev_priv);
 		mutex_unlock(&dev->struct_mutex);
 	}
-	if (!idle)
-		queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work,
+
+	/* Keep the retire handler running until we are finally idle.
+	 * We do not need to do this test under locking as in the worst-case
+	 * we queue the retire worker once too often.
+	 */
+	if (READ_ONCE(dev_priv->gt.awake))
+		queue_delayed_work(dev_priv->wq,
+				   &dev_priv->gt.retire_work,
 				   round_jiffies_up_relative(HZ));
 }
 
@@ -3054,25 +3291,55 @@ static void
 i915_gem_idle_work_handler(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
-		container_of(work, typeof(*dev_priv), mm.idle_work.work);
-	struct drm_device *dev = dev_priv->dev;
+		container_of(work, typeof(*dev_priv), gt.idle_work.work);
+	struct drm_device *dev = &dev_priv->drm;
 	struct intel_engine_cs *engine;
+	unsigned int stuck_engines;
+	bool rearm_hangcheck;
+
+	if (!READ_ONCE(dev_priv->gt.awake))
+		return;
+
+	if (READ_ONCE(dev_priv->gt.active_engines))
+		return;
+
+	rearm_hangcheck =
+		cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
+
+	if (!mutex_trylock(&dev->struct_mutex)) {
+		/* Currently busy, come back later */
+		mod_delayed_work(dev_priv->wq,
+				 &dev_priv->gt.idle_work,
+				 msecs_to_jiffies(50));
+		goto out_rearm;
+	}
+
+	if (dev_priv->gt.active_engines)
+		goto out_unlock;
 
 	for_each_engine(engine, dev_priv)
-		if (!list_empty(&engine->request_list))
-			return;
+		i915_gem_batch_pool_fini(&engine->batch_pool);
 
-	/* we probably should sync with hangcheck here, using cancel_work_sync.
-	 * Also locking seems to be fubar here, engine->request_list is protected
-	 * by dev->struct_mutex. */
+	GEM_BUG_ON(!dev_priv->gt.awake);
+	dev_priv->gt.awake = false;
+	rearm_hangcheck = false;
 
-	intel_mark_idle(dev);
+	stuck_engines = intel_kick_waiters(dev_priv);
+	if (unlikely(stuck_engines)) {
+		DRM_DEBUG_DRIVER("kicked stuck waiters...missed irq\n");
+		dev_priv->gpu_error.missed_irq_rings |= stuck_engines;
+	}
 
-	if (mutex_trylock(&dev->struct_mutex)) {
-		for_each_engine(engine, dev_priv)
-			i915_gem_batch_pool_fini(&engine->batch_pool);
+	if (INTEL_GEN(dev_priv) >= 6)
+		gen6_rps_idle(dev_priv);
+	intel_runtime_pm_put(dev_priv);
+out_unlock:
+	mutex_unlock(&dev->struct_mutex);
 
-		mutex_unlock(&dev->struct_mutex);
+out_rearm:
+	if (rearm_hangcheck) {
+		GEM_BUG_ON(!dev_priv->gt.awake);
+		i915_queue_hangcheck(dev_priv);
 	}
 }
 
@@ -3080,6 +3347,7 @@ i915_gem_idle_work_handler(struct work_struct *work)
  * Ensures that an object will eventually get non-busy by flushing any required
  * write domains, emitting any outstanding lazy request and retiring and
  * completed requests.
+ * @obj: object to flush
  */
 static int
 i915_gem_object_flush_active(struct drm_i915_gem_object *obj)
@@ -3096,14 +3364,8 @@ i915_gem_object_flush_active(struct drm_i915_gem_object *obj)
 		if (req == NULL)
 			continue;
 
-		if (list_empty(&req->list))
-			goto retire;
-
-		if (i915_gem_request_completed(req, true)) {
-			__i915_gem_request_retire__upto(req);
-retire:
+		if (i915_gem_request_completed(req))
 			i915_gem_object_retire__read(obj, i);
-		}
 	}
 
 	return 0;
@@ -3111,7 +3373,9 @@ retire:
 
 /**
  * i915_gem_wait_ioctl - implements DRM_IOCTL_I915_GEM_WAIT
- * @DRM_IOCTL_ARGS: standard ioctl arguments
+ * @dev: drm device pointer
+ * @data: ioctl data blob
+ * @file: drm file pointer
  *
  * Returns 0 if successful, else an error is returned with the remaining time in
  * the timeout parameter.
@@ -3185,7 +3449,7 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 			ret = __i915_wait_request(req[i], true,
 						  args->timeout_ns > 0 ? &args->timeout_ns : NULL,
 						  to_rps_client(file));
-		i915_gem_request_unreference__unlocked(req[i]);
+		i915_gem_request_unreference(req[i]);
 	}
 	return ret;
 
@@ -3208,10 +3472,10 @@ __i915_gem_object_sync(struct drm_i915_gem_object *obj,
 	if (to == from)
 		return 0;
 
-	if (i915_gem_request_completed(from_req, true))
+	if (i915_gem_request_completed(from_req))
 		return 0;
 
-	if (!i915_semaphore_is_enabled(obj->base.dev)) {
+	if (!i915_semaphore_is_enabled(to_i915(obj->base.dev))) {
 		struct drm_i915_private *i915 = to_i915(obj->base.dev);
 		ret = __i915_wait_request(from_req,
 					  i915->mm.interruptible,
@@ -3345,10 +3609,21 @@ static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj)
 					    old_write_domain);
 }
 
+static void __i915_vma_iounmap(struct i915_vma *vma)
+{
+	GEM_BUG_ON(vma->pin_count);
+
+	if (vma->iomap == NULL)
+		return;
+
+	io_mapping_unmap(vma->iomap);
+	vma->iomap = NULL;
+}
+
 static int __i915_vma_unbind(struct i915_vma *vma, bool wait)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	int ret;
 
 	if (list_empty(&vma->obj_link))
@@ -3377,6 +3652,8 @@ static int __i915_vma_unbind(struct i915_vma *vma, bool wait)
 		ret = i915_gem_object_put_fence(obj);
 		if (ret)
 			return ret;
+
+		__i915_vma_iounmap(vma);
 	}
 
 	trace_i915_vma_unbind(vma);
@@ -3422,26 +3699,16 @@ int __i915_vma_unbind_no_wait(struct i915_vma *vma)
 	return __i915_vma_unbind(vma, false);
 }
 
-int i915_gpu_idle(struct drm_device *dev)
+int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
 	int ret;
 
-	/* Flush everything onto the inactive list. */
-	for_each_engine(engine, dev_priv) {
-		if (!i915.enable_execlists) {
-			struct drm_i915_gem_request *req;
+	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-			req = i915_gem_request_alloc(engine, NULL);
-			if (IS_ERR(req))
-				return PTR_ERR(req);
-
-			ret = i915_switch_context(req);
-			i915_add_request_no_flush(req);
-			if (ret)
-				return ret;
-		}
+	for_each_engine(engine, dev_priv) {
+		if (engine->last_context == NULL)
+			continue;
 
 		ret = intel_engine_idle(engine);
 		if (ret)
@@ -3488,6 +3755,11 @@ static bool i915_gem_valid_gtt_space(struct i915_vma *vma,
 /**
  * Finds free space in the GTT aperture and binds the object or a view of it
  * there.
+ * @obj: object to bind
+ * @vm: address space to bind into
+ * @ggtt_view: global gtt view if applicable
+ * @alignment: requested alignment
+ * @flags: mask of PIN_* flags to use
  */
 static struct i915_vma *
 i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
@@ -3731,7 +4003,7 @@ i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj)
 		return;
 
 	if (i915_gem_clflush_object(obj, obj->pin_display))
-		i915_gem_chipset_flush(obj->base.dev);
+		i915_gem_chipset_flush(to_i915(obj->base.dev));
 
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
@@ -3745,6 +4017,8 @@ i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj)
 
 /**
  * Moves a single object to the GTT read, and possibly write domain.
+ * @obj: object to act on
+ * @write: ask for write access or read only
  *
  * This function returns when the move is complete, including waiting on
  * flushes to occur.
@@ -3816,6 +4090,8 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 
 /**
  * Changes the cache-level of an object across all VMA.
+ * @obj: object to act on
+ * @cache_level: new cache level to set for the object
  *
  * After this function returns, the object will be in the new cache-level
  * across all GTT and the contents of the backing storage will be coherent,
@@ -3925,11 +4201,9 @@ out:
 	 * object is now coherent at its new cache level (with respect
 	 * to the access domain).
 	 */
-	if (obj->cache_dirty &&
-	    obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
-	    cpu_write_needs_clflush(obj)) {
+	if (obj->cache_dirty && cpu_write_needs_clflush(obj)) {
 		if (i915_gem_clflush_object(obj, true))
-			i915_gem_chipset_flush(obj->base.dev);
+			i915_gem_chipset_flush(to_i915(obj->base.dev));
 	}
 
 	return 0;
@@ -3967,7 +4241,7 @@ int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
 int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_caching *args = data;
 	struct drm_i915_gem_object *obj;
 	enum i915_cache_level level;
@@ -4097,6 +4371,8 @@ i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj,
 
 /**
  * Moves a single object to the CPU read, and possibly write domain.
+ * @obj: object to act on
+ * @write: requesting write or read-only access
  *
  * This function returns when the move is complete, including waiting on
  * flushes to occur.
@@ -4159,7 +4435,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 static int
 i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	unsigned long recent_enough = jiffies - DRM_I915_THROTTLE_JIFFIES;
 	struct drm_i915_gem_request *request, *target = NULL;
@@ -4195,10 +4471,7 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
 		return 0;
 
 	ret = __i915_wait_request(target, true, NULL, NULL);
-	if (ret == 0)
-		queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, 0);
-
-	i915_gem_request_unreference__unlocked(target);
+	i915_gem_request_unreference(target);
 
 	return ret;
 }
@@ -4256,7 +4529,7 @@ i915_gem_object_do_pin(struct drm_i915_gem_object *obj,
 		       uint32_t alignment,
 		       uint64_t flags)
 {
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 	unsigned bound;
 	int ret;
@@ -4420,7 +4693,7 @@ int
 i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_madvise *args = data;
 	struct drm_i915_gem_object *obj;
 	int ret;
@@ -4490,7 +4763,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 	obj->fence_reg = I915_FENCE_REG_NONE;
 	obj->madv = I915_MADV_WILLNEED;
 
-	i915_gem_info_add_obj(obj->base.dev->dev_private, obj->base.size);
+	i915_gem_info_add_obj(to_i915(obj->base.dev), obj->base.size);
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_ops = {
@@ -4499,21 +4772,21 @@ static const struct drm_i915_gem_object_ops i915_gem_object_ops = {
 	.put_pages = i915_gem_object_put_pages_gtt,
 };
 
-struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
+struct drm_i915_gem_object *i915_gem_object_create(struct drm_device *dev,
 						  size_t size)
 {
 	struct drm_i915_gem_object *obj;
 	struct address_space *mapping;
 	gfp_t mask;
+	int ret;
 
 	obj = i915_gem_object_alloc(dev);
 	if (obj == NULL)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
-	if (drm_gem_object_init(dev, &obj->base, size) != 0) {
-		i915_gem_object_free(obj);
-		return NULL;
-	}
+	ret = drm_gem_object_init(dev, &obj->base, size);
+	if (ret)
+		goto fail;
 
 	mask = GFP_HIGHUSER | __GFP_RECLAIMABLE;
 	if (IS_CRESTLINE(dev) || IS_BROADWATER(dev)) {
@@ -4550,6 +4823,11 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 	trace_i915_gem_object_create(obj);
 
 	return obj;
+
+fail:
+	i915_gem_object_free(obj);
+
+	return ERR_PTR(ret);
 }
 
 static bool discard_backing_storage(struct drm_i915_gem_object *obj)
@@ -4580,7 +4858,7 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 {
 	struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
 	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_vma *vma, *next;
 
 	intel_runtime_pm_get(dev_priv);
@@ -4655,16 +4933,12 @@ struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
 struct i915_vma *i915_gem_obj_to_ggtt_view(struct drm_i915_gem_object *obj,
 					   const struct i915_ggtt_view *view)
 {
-	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	struct i915_vma *vma;
 
-	BUG_ON(!view);
+	GEM_BUG_ON(!view);
 
 	list_for_each_entry(vma, &obj->vma_list, obj_link)
-		if (vma->vm == &ggtt->base &&
-		    i915_ggtt_view_equal(&vma->ggtt_view, view))
+		if (vma->is_ggtt && i915_ggtt_view_equal(&vma->ggtt_view, view))
 			return vma;
 	return NULL;
 }
@@ -4688,7 +4962,7 @@ void i915_gem_vma_destroy(struct i915_vma *vma)
 static void
 i915_gem_stop_engines(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 
 	for_each_engine(engine, dev_priv)
@@ -4698,27 +4972,28 @@ i915_gem_stop_engines(struct drm_device *dev)
 int
 i915_gem_suspend(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret = 0;
 
 	mutex_lock(&dev->struct_mutex);
-	ret = i915_gpu_idle(dev);
+	ret = i915_gem_wait_for_idle(dev_priv);
 	if (ret)
 		goto err;
 
-	i915_gem_retire_requests(dev);
+	i915_gem_retire_requests(dev_priv);
 
 	i915_gem_stop_engines(dev);
+	i915_gem_context_lost(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
-	cancel_delayed_work_sync(&dev_priv->mm.retire_work);
-	flush_delayed_work(&dev_priv->mm.idle_work);
+	cancel_delayed_work_sync(&dev_priv->gt.retire_work);
+	flush_delayed_work(&dev_priv->gt.idle_work);
 
 	/* Assert that we sucessfully flushed all the work and
 	 * reset the GPU back to its idle, low power state.
 	 */
-	WARN_ON(dev_priv->mm.busy);
+	WARN_ON(dev_priv->gt.awake);
 
 	return 0;
 
@@ -4727,40 +5002,9 @@ err:
 	return ret;
 }
 
-int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
-{
-	struct intel_engine_cs *engine = req->engine;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
-	int i, ret;
-
-	if (!HAS_L3_DPF(dev) || !remap_info)
-		return 0;
-
-	ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
-	if (ret)
-		return ret;
-
-	/*
-	 * Note: We do not worry about the concurrent register cacheline hang
-	 * here because no other code should access these registers other than
-	 * at initialization time.
-	 */
-	for (i = 0; i < GEN7_L3LOG_SIZE / 4; i++) {
-		intel_ring_emit(engine, MI_LOAD_REGISTER_IMM(1));
-		intel_ring_emit_reg(engine, GEN7_L3LOG(slice, i));
-		intel_ring_emit(engine, remap_info[i]);
-	}
-
-	intel_ring_advance(engine);
-
-	return ret;
-}
-
 void i915_gem_init_swizzling(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (INTEL_INFO(dev)->gen < 5 ||
 	    dev_priv->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE)
@@ -4785,7 +5029,7 @@ void i915_gem_init_swizzling(struct drm_device *dev)
 
 static void init_unused_ring(struct drm_device *dev, u32 base)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(RING_CTL(base), 0);
 	I915_WRITE(RING_HEAD(base), 0);
@@ -4812,7 +5056,7 @@ static void init_unused_rings(struct drm_device *dev)
 
 int i915_gem_init_engines(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	ret = intel_init_render_ring_buffer(dev);
@@ -4860,9 +5104,9 @@ cleanup_render_ring:
 int
 i915_gem_init_hw(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
-	int ret, j;
+	int ret;
 
 	/* Double layer security blanket, see i915_gem_init() */
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
@@ -4914,59 +5158,10 @@ i915_gem_init_hw(struct drm_device *dev)
 	intel_mocs_init_l3cc_table(dev);
 
 	/* We can't enable contexts until all firmware is loaded */
-	if (HAS_GUC_UCODE(dev)) {
-		ret = intel_guc_ucode_load(dev);
-		if (ret) {
-			DRM_ERROR("Failed to initialize GuC, error %d\n", ret);
-			ret = -EIO;
-			goto out;
-		}
-	}
-
-	/*
-	 * Increment the next seqno by 0x100 so we have a visible break
-	 * on re-initialisation
-	 */
-	ret = i915_gem_set_seqno(dev, dev_priv->next_seqno+0x100);
+	ret = intel_guc_setup(dev);
 	if (ret)
 		goto out;
 
-	/* Now it is safe to go back round and do everything else: */
-	for_each_engine(engine, dev_priv) {
-		struct drm_i915_gem_request *req;
-
-		req = i915_gem_request_alloc(engine, NULL);
-		if (IS_ERR(req)) {
-			ret = PTR_ERR(req);
-			break;
-		}
-
-		if (engine->id == RCS) {
-			for (j = 0; j < NUM_L3_SLICES(dev); j++) {
-				ret = i915_gem_l3_remap(req, j);
-				if (ret)
-					goto err_request;
-			}
-		}
-
-		ret = i915_ppgtt_init_ring(req);
-		if (ret)
-			goto err_request;
-
-		ret = i915_gem_context_enable(req);
-		if (ret)
-			goto err_request;
-
-err_request:
-		i915_add_request_no_flush(req);
-		if (ret) {
-			DRM_ERROR("Failed to enable %s, error=%d\n",
-				  engine->name, ret);
-			i915_gem_cleanup_engines(dev);
-			break;
-		}
-	}
-
 out:
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 	return ret;
@@ -4974,12 +5169,9 @@ out:
 
 int i915_gem_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
-	i915.enable_execlists = intel_sanitize_enable_execlists(dev,
-			i915.enable_execlists);
-
 	mutex_lock(&dev->struct_mutex);
 
 	if (!i915.enable_execlists) {
@@ -5002,10 +5194,7 @@ int i915_gem_init(struct drm_device *dev)
 	 */
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
-	ret = i915_gem_init_userptr(dev);
-	if (ret)
-		goto out_unlock;
-
+	i915_gem_init_userptr(dev_priv);
 	i915_gem_init_ggtt(dev);
 
 	ret = i915_gem_context_init(dev);
@@ -5037,19 +5226,11 @@ out_unlock:
 void
 i915_gem_cleanup_engines(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 
 	for_each_engine(engine, dev_priv)
 		dev_priv->gt.cleanup_engine(engine);
-
-	if (i915.enable_execlists)
-		/*
-		 * Neither the BIOS, ourselves or any other kernel
-		 * expects the system to be in execlists mode on startup,
-		 * so we need to reset the GPU back to legacy mode.
-		 */
-		intel_gpu_reset(dev, ALL_ENGINES);
 }
 
 static void
@@ -5062,7 +5243,7 @@ init_engine_lists(struct intel_engine_cs *engine)
 void
 i915_gem_load_init_fences(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 
 	if (INTEL_INFO(dev_priv)->gen >= 7 && !IS_VALLEYVIEW(dev_priv) &&
 	    !IS_CHERRYVIEW(dev_priv))
@@ -5073,7 +5254,7 @@ i915_gem_load_init_fences(struct drm_i915_private *dev_priv)
 	else
 		dev_priv->num_fence_regs = 8;
 
-	if (intel_vgpu_active(dev))
+	if (intel_vgpu_active(dev_priv))
 		dev_priv->num_fence_regs =
 				I915_READ(vgtif_reg(avail_rs.fence_num));
 
@@ -5086,7 +5267,7 @@ i915_gem_load_init_fences(struct drm_i915_private *dev_priv)
 void
 i915_gem_load_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
 	dev_priv->objects =
@@ -5114,22 +5295,15 @@ i915_gem_load_init(struct drm_device *dev)
 		init_engine_lists(&dev_priv->engine[i]);
 	for (i = 0; i < I915_MAX_NUM_FENCES; i++)
 		INIT_LIST_HEAD(&dev_priv->fence_regs[i].lru_list);
-	INIT_DELAYED_WORK(&dev_priv->mm.retire_work,
+	INIT_DELAYED_WORK(&dev_priv->gt.retire_work,
 			  i915_gem_retire_work_handler);
-	INIT_DELAYED_WORK(&dev_priv->mm.idle_work,
+	INIT_DELAYED_WORK(&dev_priv->gt.idle_work,
 			  i915_gem_idle_work_handler);
+	init_waitqueue_head(&dev_priv->gpu_error.wait_queue);
 	init_waitqueue_head(&dev_priv->gpu_error.reset_queue);
 
 	dev_priv->relative_constants_mode = I915_EXEC_CONSTANTS_REL_GENERAL;
 
-	/*
-	 * Set initial sequence number for requests.
-	 * Using this number allows the wraparound to happen early,
-	 * catching any obvious problems.
-	 */
-	dev_priv->next_seqno = ((u32)~0 - 0x1100);
-	dev_priv->last_seqno = ((u32)~0 - 0x1101);
-
 	INIT_LIST_HEAD(&dev_priv->mm.fence_list);
 
 	init_waitqueue_head(&dev_priv->pending_flip_queue);
@@ -5148,6 +5322,34 @@ void i915_gem_load_cleanup(struct drm_device *dev)
 	kmem_cache_destroy(dev_priv->objects);
 }
 
+int i915_gem_freeze_late(struct drm_i915_private *dev_priv)
+{
+	struct drm_i915_gem_object *obj;
+
+	/* Called just before we write the hibernation image.
+	 *
+	 * We need to update the domain tracking to reflect that the CPU
+	 * will be accessing all the pages to create and restore from the
+	 * hibernation, and so upon restoration those pages will be in the
+	 * CPU domain.
+	 *
+	 * To make sure the hibernation image contains the latest state,
+	 * we update that state just before writing out the image.
+	 */
+
+	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) {
+		obj->base.read_domains = I915_GEM_DOMAIN_CPU;
+		obj->base.write_domain = I915_GEM_DOMAIN_CPU;
+	}
+
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+		obj->base.read_domains = I915_GEM_DOMAIN_CPU;
+		obj->base.write_domain = I915_GEM_DOMAIN_CPU;
+	}
+
+	return 0;
+}
+
 void i915_gem_release(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
@@ -5187,7 +5389,7 @@ int i915_gem_open(struct drm_device *dev, struct drm_file *file)
 		return -ENOMEM;
 
 	file->driver_priv = file_priv;
-	file_priv->dev_priv = dev->dev_private;
+	file_priv->dev_priv = to_i915(dev);
 	file_priv->file = file;
 	INIT_LIST_HEAD(&file_priv->rps.link);
 
@@ -5233,7 +5435,7 @@ void i915_gem_track_fb(struct drm_i915_gem_object *old,
 u64 i915_gem_obj_offset(struct drm_i915_gem_object *o,
 			struct i915_address_space *vm)
 {
-	struct drm_i915_private *dev_priv = o->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(o->base.dev);
 	struct i915_vma *vma;
 
 	WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base);
@@ -5254,13 +5456,10 @@ u64 i915_gem_obj_offset(struct drm_i915_gem_object *o,
 u64 i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o,
 				  const struct i915_ggtt_view *view)
 {
-	struct drm_i915_private *dev_priv = to_i915(o->base.dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	struct i915_vma *vma;
 
 	list_for_each_entry(vma, &o->vma_list, obj_link)
-		if (vma->vm == &ggtt->base &&
-		    i915_ggtt_view_equal(&vma->ggtt_view, view))
+		if (vma->is_ggtt && i915_ggtt_view_equal(&vma->ggtt_view, view))
 			return vma->node.start;
 
 	WARN(1, "global vma for this object not found. (view=%u)\n", view->type);
@@ -5286,12 +5485,10 @@ bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
 bool i915_gem_obj_ggtt_bound_view(struct drm_i915_gem_object *o,
 				  const struct i915_ggtt_view *view)
 {
-	struct drm_i915_private *dev_priv = to_i915(o->base.dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	struct i915_vma *vma;
 
 	list_for_each_entry(vma, &o->vma_list, obj_link)
-		if (vma->vm == &ggtt->base &&
+		if (vma->is_ggtt &&
 		    i915_ggtt_view_equal(&vma->ggtt_view, view) &&
 		    drm_mm_node_allocated(&vma->node))
 			return true;
@@ -5310,23 +5507,18 @@ bool i915_gem_obj_bound_any(struct drm_i915_gem_object *o)
 	return false;
 }
 
-unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
-				struct i915_address_space *vm)
+unsigned long i915_gem_obj_ggtt_size(struct drm_i915_gem_object *o)
 {
-	struct drm_i915_private *dev_priv = o->base.dev->dev_private;
 	struct i915_vma *vma;
 
-	WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base);
-
-	BUG_ON(list_empty(&o->vma_list));
+	GEM_BUG_ON(list_empty(&o->vma_list));
 
 	list_for_each_entry(vma, &o->vma_list, obj_link) {
 		if (vma->is_ggtt &&
-		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
-			continue;
-		if (vma->vm == vm)
+		    vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL)
 			return vma->node.size;
 	}
+
 	return 0;
 }
 
@@ -5347,7 +5539,7 @@ i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, int n)
 	struct page *page;
 
 	/* Only default objects have per-page dirty tracking */
-	if (WARN_ON((obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE) == 0))
+	if (WARN_ON(!i915_gem_object_has_struct_page(obj)))
 		return NULL;
 
 	page = i915_gem_object_get_page(obj, n);
@@ -5365,8 +5557,8 @@ i915_gem_object_create_from_data(struct drm_device *dev,
 	size_t bytes;
 	int ret;
 
-	obj = i915_gem_alloc_object(dev, round_up(size, PAGE_SIZE));
-	if (IS_ERR_OR_NULL(obj))
+	obj = i915_gem_object_create(dev, round_up(size, PAGE_SIZE));
+	if (IS_ERR(obj))
 		return obj;
 
 	ret = i915_gem_object_set_to_cpu_domain(obj, true);
diff --git a/drivers/gpu/drm/i915/i915_gem_batch_pool.c b/drivers/gpu/drm/i915/i915_gem_batch_pool.c
index 7bf2f3f2968e..3752d5daa4b2 100644
--- a/drivers/gpu/drm/i915/i915_gem_batch_pool.c
+++ b/drivers/gpu/drm/i915/i915_gem_batch_pool.c
@@ -134,9 +134,9 @@ i915_gem_batch_pool_get(struct i915_gem_batch_pool *pool,
 	if (obj == NULL) {
 		int ret;
 
-		obj = i915_gem_alloc_object(pool->dev, size);
-		if (obj == NULL)
-			return ERR_PTR(-ENOMEM);
+		obj = i915_gem_object_create(pool->dev, size);
+		if (IS_ERR(obj))
+			return obj;
 
 		ret = i915_gem_object_get_pages(obj);
 		if (ret)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index e5acc3916f75..3c97f0e7a003 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -90,6 +90,8 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 
+#define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1
+
 /* This is a HW constraint. The value below is the largest known requirement
  * I've seen in a spec to date, and that was a workaround for a non-shipping
  * part. It should be safe to decrease this, but it's more future proof as is.
@@ -97,28 +99,27 @@
 #define GEN6_CONTEXT_ALIGN (64<<10)
 #define GEN7_CONTEXT_ALIGN 4096
 
-static size_t get_context_alignment(struct drm_device *dev)
+static size_t get_context_alignment(struct drm_i915_private *dev_priv)
 {
-	if (IS_GEN6(dev))
+	if (IS_GEN6(dev_priv))
 		return GEN6_CONTEXT_ALIGN;
 
 	return GEN7_CONTEXT_ALIGN;
 }
 
-static int get_context_size(struct drm_device *dev)
+static int get_context_size(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 	u32 reg;
 
-	switch (INTEL_INFO(dev)->gen) {
+	switch (INTEL_GEN(dev_priv)) {
 	case 6:
 		reg = I915_READ(CXT_SIZE);
 		ret = GEN6_CXT_TOTAL_SIZE(reg) * 64;
 		break;
 	case 7:
 		reg = I915_READ(GEN7_CXT_SIZE);
-		if (IS_HASWELL(dev))
+		if (IS_HASWELL(dev_priv))
 			ret = HSW_CXT_TOTAL_SIZE;
 		else
 			ret = GEN7_CXT_TOTAL_SIZE(reg) * 64;
@@ -133,7 +134,7 @@ static int get_context_size(struct drm_device *dev)
 	return ret;
 }
 
-static void i915_gem_context_clean(struct intel_context *ctx)
+static void i915_gem_context_clean(struct i915_gem_context *ctx)
 {
 	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;
 	struct i915_vma *vma, *next;
@@ -150,13 +151,12 @@ static void i915_gem_context_clean(struct intel_context *ctx)
 
 void i915_gem_context_free(struct kref *ctx_ref)
 {
-	struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref);
+	struct i915_gem_context *ctx = container_of(ctx_ref, typeof(*ctx), ref);
+	int i;
 
+	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
 	trace_i915_context_free(ctx);
 
-	if (i915.enable_execlists)
-		intel_lr_context_free(ctx);
-
 	/*
 	 * This context is going away and we need to remove all VMAs still
 	 * around. This is to handle imported shared objects for which
@@ -166,9 +166,22 @@ void i915_gem_context_free(struct kref *ctx_ref)
 
 	i915_ppgtt_put(ctx->ppgtt);
 
-	if (ctx->legacy_hw_ctx.rcs_state)
-		drm_gem_object_unreference(&ctx->legacy_hw_ctx.rcs_state->base);
+	for (i = 0; i < I915_NUM_ENGINES; i++) {
+		struct intel_context *ce = &ctx->engine[i];
+
+		if (!ce->state)
+			continue;
+
+		WARN_ON(ce->pin_count);
+		if (ce->ringbuf)
+			intel_ringbuffer_free(ce->ringbuf);
+
+		drm_gem_object_unreference(&ce->state->base);
+	}
+
 	list_del(&ctx->link);
+
+	ida_simple_remove(&ctx->i915->context_hw_ida, ctx->hw_id);
 	kfree(ctx);
 }
 
@@ -178,9 +191,11 @@ i915_gem_alloc_context_obj(struct drm_device *dev, size_t size)
 	struct drm_i915_gem_object *obj;
 	int ret;
 
-	obj = i915_gem_alloc_object(dev, size);
-	if (obj == NULL)
-		return ERR_PTR(-ENOMEM);
+	lockdep_assert_held(&dev->struct_mutex);
+
+	obj = i915_gem_object_create(dev, size);
+	if (IS_ERR(obj))
+		return obj;
 
 	/*
 	 * Try to make the context utilize L3 as well as LLC.
@@ -209,22 +224,52 @@ i915_gem_alloc_context_obj(struct drm_device *dev, size_t size)
 	return obj;
 }
 
-static struct intel_context *
+static int assign_hw_id(struct drm_i915_private *dev_priv, unsigned *out)
+{
+	int ret;
+
+	ret = ida_simple_get(&dev_priv->context_hw_ida,
+			     0, MAX_CONTEXT_HW_ID, GFP_KERNEL);
+	if (ret < 0) {
+		/* Contexts are only released when no longer active.
+		 * Flush any pending retires to hopefully release some
+		 * stale contexts and try again.
+		 */
+		i915_gem_retire_requests(dev_priv);
+		ret = ida_simple_get(&dev_priv->context_hw_ida,
+				     0, MAX_CONTEXT_HW_ID, GFP_KERNEL);
+		if (ret < 0)
+			return ret;
+	}
+
+	*out = ret;
+	return 0;
+}
+
+static struct i915_gem_context *
 __create_hw_context(struct drm_device *dev,
 		    struct drm_i915_file_private *file_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_context *ctx;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i915_gem_context *ctx;
 	int ret;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (ctx == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	ret = assign_hw_id(dev_priv, &ctx->hw_id);
+	if (ret) {
+		kfree(ctx);
+		return ERR_PTR(ret);
+	}
+
 	kref_init(&ctx->ref);
 	list_add_tail(&ctx->link, &dev_priv->context_list);
 	ctx->i915 = dev_priv;
 
+	ctx->ggtt_alignment = get_context_alignment(dev_priv);
+
 	if (dev_priv->hw_context_size) {
 		struct drm_i915_gem_object *obj =
 				i915_gem_alloc_context_obj(dev, dev_priv->hw_context_size);
@@ -232,7 +277,7 @@ __create_hw_context(struct drm_device *dev,
 			ret = PTR_ERR(obj);
 			goto err_out;
 		}
-		ctx->legacy_hw_ctx.rcs_state = obj;
+		ctx->engine[RCS].state = obj;
 	}
 
 	/* Default context will never have a file_priv */
@@ -249,9 +294,13 @@ __create_hw_context(struct drm_device *dev,
 	/* NB: Mark all slices as needing a remap so that when the context first
 	 * loads it will restore whatever remap state already exists. If there
 	 * is no remap info, it will be a NOP. */
-	ctx->remap_slice = (1 << NUM_L3_SLICES(dev)) - 1;
+	ctx->remap_slice = ALL_L3_SLICES(dev_priv);
 
 	ctx->hang_stats.ban_period_seconds = DRM_I915_CTX_BAN_PERIOD;
+	ctx->ring_size = 4 * PAGE_SIZE;
+	ctx->desc_template = GEN8_CTX_ADDRESSING_MODE(dev_priv) <<
+			     GEN8_CTX_ADDRESSING_MODE_SHIFT;
+	ATOMIC_INIT_NOTIFIER_HEAD(&ctx->status_notifier);
 
 	return ctx;
 
@@ -265,44 +314,27 @@ err_out:
  * context state of the GPU for applications that don't utilize HW contexts, as
  * well as an idle case.
  */
-static struct intel_context *
+static struct i915_gem_context *
 i915_gem_create_context(struct drm_device *dev,
 			struct drm_i915_file_private *file_priv)
 {
-	const bool is_global_default_ctx = file_priv == NULL;
-	struct intel_context *ctx;
-	int ret = 0;
+	struct i915_gem_context *ctx;
 
-	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
+	lockdep_assert_held(&dev->struct_mutex);
 
 	ctx = __create_hw_context(dev, file_priv);
 	if (IS_ERR(ctx))
 		return ctx;
 
-	if (is_global_default_ctx && ctx->legacy_hw_ctx.rcs_state) {
-		/* We may need to do things with the shrinker which
-		 * require us to immediately switch back to the default
-		 * context. This can cause a problem as pinning the
-		 * default context also requires GTT space which may not
-		 * be available. To avoid this we always pin the default
-		 * context.
-		 */
-		ret = i915_gem_obj_ggtt_pin(ctx->legacy_hw_ctx.rcs_state,
-					    get_context_alignment(dev), 0);
-		if (ret) {
-			DRM_DEBUG_DRIVER("Couldn't pin %d\n", ret);
-			goto err_destroy;
-		}
-	}
-
 	if (USES_FULL_PPGTT(dev)) {
 		struct i915_hw_ppgtt *ppgtt = i915_ppgtt_create(dev, file_priv);
 
-		if (IS_ERR_OR_NULL(ppgtt)) {
+		if (IS_ERR(ppgtt)) {
 			DRM_DEBUG_DRIVER("PPGTT setup failed (%ld)\n",
 					 PTR_ERR(ppgtt));
-			ret = PTR_ERR(ppgtt);
-			goto err_unpin;
+			idr_remove(&file_priv->context_idr, ctx->user_handle);
+			i915_gem_context_unreference(ctx);
+			return ERR_CAST(ppgtt);
 		}
 
 		ctx->ppgtt = ppgtt;
@@ -311,76 +343,102 @@ i915_gem_create_context(struct drm_device *dev,
 	trace_i915_context_create(ctx);
 
 	return ctx;
+}
 
-err_unpin:
-	if (is_global_default_ctx && ctx->legacy_hw_ctx.rcs_state)
-		i915_gem_object_ggtt_unpin(ctx->legacy_hw_ctx.rcs_state);
-err_destroy:
-	idr_remove(&file_priv->context_idr, ctx->user_handle);
-	i915_gem_context_unreference(ctx);
-	return ERR_PTR(ret);
+/**
+ * i915_gem_context_create_gvt - create a GVT GEM context
+ * @dev: drm device *
+ *
+ * This function is used to create a GVT specific GEM context.
+ *
+ * Returns:
+ * pointer to i915_gem_context on success, error pointer if failed
+ *
+ */
+struct i915_gem_context *
+i915_gem_context_create_gvt(struct drm_device *dev)
+{
+	struct i915_gem_context *ctx;
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_DRM_I915_GVT))
+		return ERR_PTR(-ENODEV);
+
+	ret = i915_mutex_lock_interruptible(dev);
+	if (ret)
+		return ERR_PTR(ret);
+
+	ctx = i915_gem_create_context(dev, NULL);
+	if (IS_ERR(ctx))
+		goto out;
+
+	ctx->execlists_force_single_submission = true;
+	ctx->ring_size = 512 * PAGE_SIZE; /* Max ring buffer size */
+out:
+	mutex_unlock(&dev->struct_mutex);
+	return ctx;
 }
 
-static void i915_gem_context_unpin(struct intel_context *ctx,
+static void i915_gem_context_unpin(struct i915_gem_context *ctx,
 				   struct intel_engine_cs *engine)
 {
 	if (i915.enable_execlists) {
 		intel_lr_context_unpin(ctx, engine);
 	} else {
-		if (engine->id == RCS && ctx->legacy_hw_ctx.rcs_state)
-			i915_gem_object_ggtt_unpin(ctx->legacy_hw_ctx.rcs_state);
+		struct intel_context *ce = &ctx->engine[engine->id];
+
+		if (ce->state)
+			i915_gem_object_ggtt_unpin(ce->state);
+
 		i915_gem_context_unreference(ctx);
 	}
 }
 
 void i915_gem_context_reset(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int i;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	lockdep_assert_held(&dev->struct_mutex);
 
 	if (i915.enable_execlists) {
-		struct intel_context *ctx;
+		struct i915_gem_context *ctx;
 
 		list_for_each_entry(ctx, &dev_priv->context_list, link)
 			intel_lr_context_reset(dev_priv, ctx);
 	}
 
-	for (i = 0; i < I915_NUM_ENGINES; i++) {
-		struct intel_engine_cs *engine = &dev_priv->engine[i];
-
-		if (engine->last_context) {
-			i915_gem_context_unpin(engine->last_context, engine);
-			engine->last_context = NULL;
-		}
-	}
-
-	/* Force the GPU state to be reinitialised on enabling */
-	dev_priv->kernel_context->legacy_hw_ctx.initialized = false;
+	i915_gem_context_lost(dev_priv);
 }
 
 int i915_gem_context_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_context *ctx;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i915_gem_context *ctx;
 
 	/* Init should only be called once per module load. Eventually the
 	 * restriction on the context_disabled check can be loosened. */
 	if (WARN_ON(dev_priv->kernel_context))
 		return 0;
 
-	if (intel_vgpu_active(dev) && HAS_LOGICAL_RING_CONTEXTS(dev)) {
+	if (intel_vgpu_active(dev_priv) &&
+	    HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 		if (!i915.enable_execlists) {
 			DRM_INFO("Only EXECLIST mode is supported in vgpu.\n");
 			return -EINVAL;
 		}
 	}
 
+	/* Using the simple ida interface, the max is limited by sizeof(int) */
+	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > INT_MAX);
+	ida_init(&dev_priv->context_hw_ida);
+
 	if (i915.enable_execlists) {
 		/* NB: intentionally left blank. We will allocate our own
 		 * backing objects as we need them, thank you very much */
 		dev_priv->hw_context_size = 0;
-	} else if (HAS_HW_CONTEXTS(dev)) {
-		dev_priv->hw_context_size = round_up(get_context_size(dev), 4096);
+	} else if (HAS_HW_CONTEXTS(dev_priv)) {
+		dev_priv->hw_context_size =
+			round_up(get_context_size(dev_priv), 4096);
 		if (dev_priv->hw_context_size > (1<<20)) {
 			DRM_DEBUG_DRIVER("Disabling HW Contexts; invalid size %d\n",
 					 dev_priv->hw_context_size);
@@ -403,67 +461,60 @@ int i915_gem_context_init(struct drm_device *dev)
 	return 0;
 }
 
-void i915_gem_context_fini(struct drm_device *dev)
+void i915_gem_context_lost(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_context *dctx = dev_priv->kernel_context;
-	int i;
-
-	if (dctx->legacy_hw_ctx.rcs_state) {
-		/* The only known way to stop the gpu from accessing the hw context is
-		 * to reset it. Do this as the very last operation to avoid confusing
-		 * other code, leading to spurious errors. */
-		intel_gpu_reset(dev, ALL_ENGINES);
+	struct intel_engine_cs *engine;
 
-		/* When default context is created and switched to, base object refcount
-		 * will be 2 (+1 from object creation and +1 from do_switch()).
-		 * i915_gem_context_fini() will be called after gpu_idle() has switched
-		 * to default context. So we need to unreference the base object once
-		 * to offset the do_switch part, so that i915_gem_context_unreference()
-		 * can then free the base object correctly. */
-		WARN_ON(!dev_priv->engine[RCS].last_context);
-
-		i915_gem_object_ggtt_unpin(dctx->legacy_hw_ctx.rcs_state);
-	}
-
-	for (i = I915_NUM_ENGINES; --i >= 0;) {
-		struct intel_engine_cs *engine = &dev_priv->engine[i];
+	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
+	for_each_engine(engine, dev_priv) {
 		if (engine->last_context) {
 			i915_gem_context_unpin(engine->last_context, engine);
 			engine->last_context = NULL;
 		}
 	}
 
-	i915_gem_context_unreference(dctx);
-	dev_priv->kernel_context = NULL;
-}
+	/* Force the GPU state to be restored on enabling */
+	if (!i915.enable_execlists) {
+		struct i915_gem_context *ctx;
 
-int i915_gem_context_enable(struct drm_i915_gem_request *req)
-{
-	struct intel_engine_cs *engine = req->engine;
-	int ret;
+		list_for_each_entry(ctx, &dev_priv->context_list, link) {
+			if (!i915_gem_context_is_default(ctx))
+				continue;
 
-	if (i915.enable_execlists) {
-		if (engine->init_context == NULL)
-			return 0;
+			for_each_engine(engine, dev_priv)
+				ctx->engine[engine->id].initialised = false;
 
-		ret = engine->init_context(req);
-	} else
-		ret = i915_switch_context(req);
+			ctx->remap_slice = ALL_L3_SLICES(dev_priv);
+		}
 
-	if (ret) {
-		DRM_ERROR("ring init context: %d\n", ret);
-		return ret;
+		for_each_engine(engine, dev_priv) {
+			struct intel_context *kce =
+				&dev_priv->kernel_context->engine[engine->id];
+
+			kce->initialised = true;
+		}
 	}
+}
 
-	return 0;
+void i915_gem_context_fini(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i915_gem_context *dctx = dev_priv->kernel_context;
+
+	lockdep_assert_held(&dev->struct_mutex);
+
+	i915_gem_context_unreference(dctx);
+	dev_priv->kernel_context = NULL;
+
+	ida_destroy(&dev_priv->context_hw_ida);
 }
 
 static int context_idr_cleanup(int id, void *p, void *data)
 {
-	struct intel_context *ctx = p;
+	struct i915_gem_context *ctx = p;
 
+	ctx->file_priv = ERR_PTR(-EBADF);
 	i915_gem_context_unreference(ctx);
 	return 0;
 }
@@ -471,7 +522,7 @@ static int context_idr_cleanup(int id, void *p, void *data)
 int i915_gem_context_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
-	struct intel_context *ctx;
+	struct i915_gem_context *ctx;
 
 	idr_init(&file_priv->context_idr);
 
@@ -491,31 +542,22 @@ void i915_gem_context_close(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 
+	lockdep_assert_held(&dev->struct_mutex);
+
 	idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL);
 	idr_destroy(&file_priv->context_idr);
 }
 
-struct intel_context *
-i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
-{
-	struct intel_context *ctx;
-
-	ctx = (struct intel_context *)idr_find(&file_priv->context_idr, id);
-	if (!ctx)
-		return ERR_PTR(-ENOENT);
-
-	return ctx;
-}
-
 static inline int
 mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 {
+	struct drm_i915_private *dev_priv = req->i915;
 	struct intel_engine_cs *engine = req->engine;
 	u32 flags = hw_flags | MI_MM_SPACE_GTT;
 	const int num_rings =
 		/* Use an extended w/a on ivb+ if signalling from other rings */
-		i915_semaphore_is_enabled(engine->dev) ?
-		hweight32(INTEL_INFO(engine->dev)->ring_mask) - 1 :
+		i915_semaphore_is_enabled(dev_priv) ?
+		hweight32(INTEL_INFO(dev_priv)->ring_mask) - 1 :
 		0;
 	int len, ret;
 
@@ -524,21 +566,21 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 	 * explicitly, so we rely on the value at ring init, stored in
 	 * itlb_before_ctx_switch.
 	 */
-	if (IS_GEN6(engine->dev)) {
+	if (IS_GEN6(dev_priv)) {
 		ret = engine->flush(req, I915_GEM_GPU_DOMAINS, 0);
 		if (ret)
 			return ret;
 	}
 
 	/* These flags are for resource streamer on HSW+ */
-	if (IS_HASWELL(engine->dev) || INTEL_INFO(engine->dev)->gen >= 8)
+	if (IS_HASWELL(dev_priv) || INTEL_GEN(dev_priv) >= 8)
 		flags |= (HSW_MI_RS_SAVE_STATE_EN | HSW_MI_RS_RESTORE_STATE_EN);
-	else if (INTEL_INFO(engine->dev)->gen < 8)
+	else if (INTEL_GEN(dev_priv) < 8)
 		flags |= (MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN);
 
 
 	len = 4;
-	if (INTEL_INFO(engine->dev)->gen >= 7)
+	if (INTEL_GEN(dev_priv) >= 7)
 		len += 2 + (num_rings ? 4*num_rings + 6 : 0);
 
 	ret = intel_ring_begin(req, len);
@@ -546,14 +588,14 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 		return ret;
 
 	/* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw,bdw,chv */
-	if (INTEL_INFO(engine->dev)->gen >= 7) {
+	if (INTEL_GEN(dev_priv) >= 7) {
 		intel_ring_emit(engine, MI_ARB_ON_OFF | MI_ARB_DISABLE);
 		if (num_rings) {
 			struct intel_engine_cs *signaller;
 
 			intel_ring_emit(engine,
 					MI_LOAD_REGISTER_IMM(num_rings));
-			for_each_engine(signaller, to_i915(engine->dev)) {
+			for_each_engine(signaller, dev_priv) {
 				if (signaller == engine)
 					continue;
 
@@ -568,7 +610,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 	intel_ring_emit(engine, MI_NOOP);
 	intel_ring_emit(engine, MI_SET_CONTEXT);
 	intel_ring_emit(engine,
-			i915_gem_obj_ggtt_offset(req->ctx->legacy_hw_ctx.rcs_state) |
+			i915_gem_obj_ggtt_offset(req->ctx->engine[RCS].state) |
 			flags);
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
@@ -576,14 +618,14 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 	 */
 	intel_ring_emit(engine, MI_NOOP);
 
-	if (INTEL_INFO(engine->dev)->gen >= 7) {
+	if (INTEL_GEN(dev_priv) >= 7) {
 		if (num_rings) {
 			struct intel_engine_cs *signaller;
 			i915_reg_t last_reg = {}; /* keep gcc quiet */
 
 			intel_ring_emit(engine,
 					MI_LOAD_REGISTER_IMM(num_rings));
-			for_each_engine(signaller, to_i915(engine->dev)) {
+			for_each_engine(signaller, dev_priv) {
 				if (signaller == engine)
 					continue;
 
@@ -609,45 +651,83 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 	return ret;
 }
 
-static inline bool skip_rcs_switch(struct intel_engine_cs *engine,
-				   struct intel_context *to)
+static int remap_l3(struct drm_i915_gem_request *req, int slice)
+{
+	u32 *remap_info = req->i915->l3_parity.remap_info[slice];
+	struct intel_engine_cs *engine = req->engine;
+	int i, ret;
+
+	if (!remap_info)
+		return 0;
+
+	ret = intel_ring_begin(req, GEN7_L3LOG_SIZE/4 * 2 + 2);
+	if (ret)
+		return ret;
+
+	/*
+	 * Note: We do not worry about the concurrent register cacheline hang
+	 * here because no other code should access these registers other than
+	 * at initialization time.
+	 */
+	intel_ring_emit(engine, MI_LOAD_REGISTER_IMM(GEN7_L3LOG_SIZE/4));
+	for (i = 0; i < GEN7_L3LOG_SIZE/4; i++) {
+		intel_ring_emit_reg(engine, GEN7_L3LOG(slice, i));
+		intel_ring_emit(engine, remap_info[i]);
+	}
+	intel_ring_emit(engine, MI_NOOP);
+	intel_ring_advance(engine);
+
+	return 0;
+}
+
+static inline bool skip_rcs_switch(struct i915_hw_ppgtt *ppgtt,
+				   struct intel_engine_cs *engine,
+				   struct i915_gem_context *to)
 {
 	if (to->remap_slice)
 		return false;
 
-	if (!to->legacy_hw_ctx.initialized)
+	if (!to->engine[RCS].initialised)
 		return false;
 
-	if (to->ppgtt &&
-	    !(intel_engine_flag(engine) & to->ppgtt->pd_dirty_rings))
+	if (ppgtt && (intel_engine_flag(engine) & ppgtt->pd_dirty_rings))
 		return false;
 
 	return to == engine->last_context;
 }
 
 static bool
-needs_pd_load_pre(struct intel_engine_cs *engine, struct intel_context *to)
+needs_pd_load_pre(struct i915_hw_ppgtt *ppgtt,
+		  struct intel_engine_cs *engine,
+		  struct i915_gem_context *to)
 {
-	if (!to->ppgtt)
+	if (!ppgtt)
 		return false;
 
+	/* Always load the ppgtt on first use */
+	if (!engine->last_context)
+		return true;
+
+	/* Same context without new entries, skip */
 	if (engine->last_context == to &&
-	    !(intel_engine_flag(engine) & to->ppgtt->pd_dirty_rings))
+	    !(intel_engine_flag(engine) & ppgtt->pd_dirty_rings))
 		return false;
 
 	if (engine->id != RCS)
 		return true;
 
-	if (INTEL_INFO(engine->dev)->gen < 8)
+	if (INTEL_GEN(engine->i915) < 8)
 		return true;
 
 	return false;
 }
 
 static bool
-needs_pd_load_post(struct intel_context *to, u32 hw_flags)
+needs_pd_load_post(struct i915_hw_ppgtt *ppgtt,
+		   struct i915_gem_context *to,
+		   u32 hw_flags)
 {
-	if (!to->ppgtt)
+	if (!ppgtt)
 		return false;
 
 	if (!IS_GEN8(to->i915))
@@ -661,18 +741,19 @@ needs_pd_load_post(struct intel_context *to, u32 hw_flags)
 
 static int do_rcs_switch(struct drm_i915_gem_request *req)
 {
-	struct intel_context *to = req->ctx;
+	struct i915_gem_context *to = req->ctx;
 	struct intel_engine_cs *engine = req->engine;
-	struct intel_context *from;
+	struct i915_hw_ppgtt *ppgtt = to->ppgtt ?: req->i915->mm.aliasing_ppgtt;
+	struct i915_gem_context *from;
 	u32 hw_flags;
 	int ret, i;
 
-	if (skip_rcs_switch(engine, to))
+	if (skip_rcs_switch(ppgtt, engine, to))
 		return 0;
 
 	/* Trying to pin first makes error handling easier. */
-	ret = i915_gem_obj_ggtt_pin(to->legacy_hw_ctx.rcs_state,
-				    get_context_alignment(engine->dev),
+	ret = i915_gem_obj_ggtt_pin(to->engine[RCS].state,
+				    to->ggtt_alignment,
 				    0);
 	if (ret)
 		return ret;
@@ -694,37 +775,32 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 	 *
 	 * XXX: We need a real interface to do this instead of trickery.
 	 */
-	ret = i915_gem_object_set_to_gtt_domain(to->legacy_hw_ctx.rcs_state, false);
+	ret = i915_gem_object_set_to_gtt_domain(to->engine[RCS].state, false);
 	if (ret)
 		goto unpin_out;
 
-	if (needs_pd_load_pre(engine, to)) {
+	if (needs_pd_load_pre(ppgtt, engine, to)) {
 		/* Older GENs and non render rings still want the load first,
 		 * "PP_DCLV followed by PP_DIR_BASE register through Load
 		 * Register Immediate commands in Ring Buffer before submitting
 		 * a context."*/
 		trace_switch_mm(engine, to);
-		ret = to->ppgtt->switch_mm(to->ppgtt, req);
+		ret = ppgtt->switch_mm(ppgtt, req);
 		if (ret)
 			goto unpin_out;
 	}
 
-	if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to))
+	if (!to->engine[RCS].initialised || i915_gem_context_is_default(to))
 		/* NB: If we inhibit the restore, the context is not allowed to
 		 * die because future work may end up depending on valid address
 		 * space. This means we must enforce that a page table load
 		 * occur when this occurs. */
 		hw_flags = MI_RESTORE_INHIBIT;
-	else if (to->ppgtt &&
-		 intel_engine_flag(engine) & to->ppgtt->pd_dirty_rings)
+	else if (ppgtt && intel_engine_flag(engine) & ppgtt->pd_dirty_rings)
 		hw_flags = MI_FORCE_RESTORE;
 	else
 		hw_flags = 0;
 
-	/* We should never emit switch_mm more than once */
-	WARN_ON(needs_pd_load_pre(engine, to) &&
-		needs_pd_load_post(to, hw_flags));
-
 	if (to != from || (hw_flags & MI_FORCE_RESTORE)) {
 		ret = mi_set_context(req, hw_flags);
 		if (ret)
@@ -738,8 +814,8 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 	 * MI_SET_CONTEXT instead of when the next seqno has completed.
 	 */
 	if (from != NULL) {
-		from->legacy_hw_ctx.rcs_state->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
-		i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), req);
+		from->engine[RCS].state->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
+		i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->engine[RCS].state), req);
 		/* As long as MI_SET_CONTEXT is serializing, ie. it flushes the
 		 * whole damn pipeline, we don't need to explicitly mark the
 		 * object dirty. The only exception is that the context must be
@@ -747,10 +823,10 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 		 * able to defer doing this until we know the object would be
 		 * swapped, but there is no way to do that yet.
 		 */
-		from->legacy_hw_ctx.rcs_state->dirty = 1;
+		from->engine[RCS].state->dirty = 1;
 
 		/* obj is kept alive until the next request by its active ref */
-		i915_gem_object_ggtt_unpin(from->legacy_hw_ctx.rcs_state);
+		i915_gem_object_ggtt_unpin(from->engine[RCS].state);
 		i915_gem_context_unreference(from);
 	}
 	i915_gem_context_reference(to);
@@ -759,9 +835,9 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 	/* GEN8 does *not* require an explicit reload if the PDPs have been
 	 * setup, and we do not wish to move them.
 	 */
-	if (needs_pd_load_post(to, hw_flags)) {
+	if (needs_pd_load_post(ppgtt, to, hw_flags)) {
 		trace_switch_mm(engine, to);
-		ret = to->ppgtt->switch_mm(to->ppgtt, req);
+		ret = ppgtt->switch_mm(ppgtt, req);
 		/* The hardware context switch is emitted, but we haven't
 		 * actually changed the state - so it's probably safe to bail
 		 * here. Still, let the user know something dangerous has
@@ -771,33 +847,33 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 			return ret;
 	}
 
-	if (to->ppgtt)
-		to->ppgtt->pd_dirty_rings &= ~intel_engine_flag(engine);
+	if (ppgtt)
+		ppgtt->pd_dirty_rings &= ~intel_engine_flag(engine);
 
 	for (i = 0; i < MAX_L3_SLICES; i++) {
 		if (!(to->remap_slice & (1<<i)))
 			continue;
 
-		ret = i915_gem_l3_remap(req, i);
+		ret = remap_l3(req, i);
 		if (ret)
 			return ret;
 
 		to->remap_slice &= ~(1<<i);
 	}
 
-	if (!to->legacy_hw_ctx.initialized) {
+	if (!to->engine[RCS].initialised) {
 		if (engine->init_context) {
 			ret = engine->init_context(req);
 			if (ret)
 				return ret;
 		}
-		to->legacy_hw_ctx.initialized = true;
+		to->engine[RCS].initialised = true;
 	}
 
 	return 0;
 
 unpin_out:
-	i915_gem_object_ggtt_unpin(to->legacy_hw_ctx.rcs_state);
+	i915_gem_object_ggtt_unpin(to->engine[RCS].state);
 	return ret;
 }
 
@@ -817,25 +893,24 @@ unpin_out:
 int i915_switch_context(struct drm_i915_gem_request *req)
 {
 	struct intel_engine_cs *engine = req->engine;
-	struct drm_i915_private *dev_priv = req->i915;
 
 	WARN_ON(i915.enable_execlists);
-	WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
+	lockdep_assert_held(&req->i915->drm.struct_mutex);
 
-	if (engine->id != RCS ||
-	    req->ctx->legacy_hw_ctx.rcs_state == NULL) {
-		struct intel_context *to = req->ctx;
+	if (!req->ctx->engine[engine->id].state) {
+		struct i915_gem_context *to = req->ctx;
+		struct i915_hw_ppgtt *ppgtt =
+			to->ppgtt ?: req->i915->mm.aliasing_ppgtt;
 
-		if (needs_pd_load_pre(engine, to)) {
+		if (needs_pd_load_pre(ppgtt, engine, to)) {
 			int ret;
 
 			trace_switch_mm(engine, to);
-			ret = to->ppgtt->switch_mm(to->ppgtt, req);
+			ret = ppgtt->switch_mm(ppgtt, req);
 			if (ret)
 				return ret;
 
-			/* Doing a PD load always reloads the page dirs */
-			to->ppgtt->pd_dirty_rings &= ~intel_engine_flag(engine);
+			ppgtt->pd_dirty_rings &= ~intel_engine_flag(engine);
 		}
 
 		if (to != engine->last_context) {
@@ -861,7 +936,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_gem_context_create *args = data;
 	struct drm_i915_file_private *file_priv = file->driver_priv;
-	struct intel_context *ctx;
+	struct i915_gem_context *ctx;
 	int ret;
 
 	if (!contexts_enabled(dev))
@@ -890,7 +965,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_gem_context_destroy *args = data;
 	struct drm_i915_file_private *file_priv = file->driver_priv;
-	struct intel_context *ctx;
+	struct i915_gem_context *ctx;
 	int ret;
 
 	if (args->pad != 0)
@@ -903,13 +978,13 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		return ret;
 
-	ctx = i915_gem_context_get(file_priv, args->ctx_id);
+	ctx = i915_gem_context_lookup(file_priv, args->ctx_id);
 	if (IS_ERR(ctx)) {
 		mutex_unlock(&dev->struct_mutex);
 		return PTR_ERR(ctx);
 	}
 
-	idr_remove(&ctx->file_priv->context_idr, ctx->user_handle);
+	idr_remove(&file_priv->context_idr, ctx->user_handle);
 	i915_gem_context_unreference(ctx);
 	mutex_unlock(&dev->struct_mutex);
 
@@ -922,14 +997,14 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	struct drm_i915_gem_context_param *args = data;
-	struct intel_context *ctx;
+	struct i915_gem_context *ctx;
 	int ret;
 
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
 		return ret;
 
-	ctx = i915_gem_context_get(file_priv, args->ctx_id);
+	ctx = i915_gem_context_lookup(file_priv, args->ctx_id);
 	if (IS_ERR(ctx)) {
 		mutex_unlock(&dev->struct_mutex);
 		return PTR_ERR(ctx);
@@ -951,6 +1026,9 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 		else
 			args->value = to_i915(dev)->ggtt.base.total;
 		break;
+	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
+		args->value = !!(ctx->flags & CONTEXT_NO_ERROR_CAPTURE);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -965,14 +1043,14 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	struct drm_i915_gem_context_param *args = data;
-	struct intel_context *ctx;
+	struct i915_gem_context *ctx;
 	int ret;
 
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
 		return ret;
 
-	ctx = i915_gem_context_get(file_priv, args->ctx_id);
+	ctx = i915_gem_context_lookup(file_priv, args->ctx_id);
 	if (IS_ERR(ctx)) {
 		mutex_unlock(&dev->struct_mutex);
 		return PTR_ERR(ctx);
@@ -996,6 +1074,16 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 			ctx->flags |= args->value ? CONTEXT_NO_ZEROMAP : 0;
 		}
 		break;
+	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
+		if (args->size) {
+			ret = -EINVAL;
+		} else {
+			if (args->value)
+				ctx->flags |= CONTEXT_NO_ERROR_CAPTURE;
+			else
+				ctx->flags &= ~CONTEXT_NO_ERROR_CAPTURE;
+		}
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -1004,3 +1092,42 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 
 	return ret;
 }
+
+int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
+				       void *data, struct drm_file *file)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_reset_stats *args = data;
+	struct i915_ctx_hang_stats *hs;
+	struct i915_gem_context *ctx;
+	int ret;
+
+	if (args->flags || args->pad)
+		return -EINVAL;
+
+	if (args->ctx_id == DEFAULT_CONTEXT_HANDLE && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ret = i915_mutex_lock_interruptible(dev);
+	if (ret)
+		return ret;
+
+	ctx = i915_gem_context_lookup(file->driver_priv, args->ctx_id);
+	if (IS_ERR(ctx)) {
+		mutex_unlock(&dev->struct_mutex);
+		return PTR_ERR(ctx);
+	}
+	hs = &ctx->hang_stats;
+
+	if (capable(CAP_SYS_ADMIN))
+		args->reset_count = i915_reset_count(&dev_priv->gpu_error);
+	else
+		args->reset_count = 0;
+
+	args->batch_active = hs->batch_active;
+	args->batch_pending = hs->batch_pending;
+
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.h b/drivers/gpu/drm/i915/i915_gem_dmabuf.h
new file mode 100644
index 000000000000..91315557e421
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _I915_GEM_DMABUF_H_
+#define _I915_GEM_DMABUF_H_
+
+#include <linux/dma-buf.h>
+
+static inline struct reservation_object *
+i915_gem_object_get_dmabuf_resv(struct drm_i915_gem_object *obj)
+{
+	struct dma_buf *dma_buf;
+
+	if (obj->base.dma_buf)
+		dma_buf = obj->base.dma_buf;
+	else if (obj->base.import_attach)
+		dma_buf = obj->base.import_attach->dmabuf;
+	else
+		return NULL;
+
+	return dma_buf->resv;
+}
+
+#endif
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index ea1f8d1bd228..3c1280ec7ff6 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -33,6 +33,37 @@
 #include "intel_drv.h"
 #include "i915_trace.h"
 
+static int switch_to_pinned_context(struct drm_i915_private *dev_priv)
+{
+	struct intel_engine_cs *engine;
+
+	if (i915.enable_execlists)
+		return 0;
+
+	for_each_engine(engine, dev_priv) {
+		struct drm_i915_gem_request *req;
+		int ret;
+
+		if (engine->last_context == NULL)
+			continue;
+
+		if (engine->last_context == dev_priv->kernel_context)
+			continue;
+
+		req = i915_gem_request_alloc(engine, dev_priv->kernel_context);
+		if (IS_ERR(req))
+			return PTR_ERR(req);
+
+		ret = i915_switch_context(req);
+		i915_add_request_no_flush(req);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+
 static bool
 mark_free(struct i915_vma *vma, struct list_head *unwind)
 {
@@ -150,11 +181,19 @@ none:
 
 	/* Only idle the GPU and repeat the search once */
 	if (pass++ == 0) {
-		ret = i915_gpu_idle(dev);
+		struct drm_i915_private *dev_priv = to_i915(dev);
+
+		if (i915_is_ggtt(vm)) {
+			ret = switch_to_pinned_context(dev_priv);
+			if (ret)
+				return ret;
+		}
+
+		ret = i915_gem_wait_for_idle(dev_priv);
 		if (ret)
 			return ret;
 
-		i915_gem_retire_requests(dev);
+		i915_gem_retire_requests(dev_priv);
 		goto search_again;
 	}
 
@@ -261,11 +300,19 @@ int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle)
 	trace_i915_gem_evict_vm(vm);
 
 	if (do_idle) {
-		ret = i915_gpu_idle(vm->dev);
+		struct drm_i915_private *dev_priv = to_i915(vm->dev);
+
+		if (i915_is_ggtt(vm)) {
+			ret = switch_to_pinned_context(dev_priv);
+			if (ret)
+				return ret;
+		}
+
+		ret = i915_gem_wait_for_idle(dev_priv);
 		if (ret)
 			return ret;
 
-		i915_gem_retire_requests(vm->dev);
+		i915_gem_retire_requests(dev_priv);
 
 		WARN_ON(!list_empty(&vm->active_list));
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 33df74d98269..1978633e7549 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -714,7 +714,7 @@ eb_vma_misplaced(struct i915_vma *vma)
 static int
 i915_gem_execbuffer_reserve(struct intel_engine_cs *engine,
 			    struct list_head *vmas,
-			    struct intel_context *ctx,
+			    struct i915_gem_context *ctx,
 			    bool *need_relocs)
 {
 	struct drm_i915_gem_object *obj;
@@ -722,7 +722,7 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *engine,
 	struct i915_address_space *vm;
 	struct list_head ordered_vmas;
 	struct list_head pinned_vmas;
-	bool has_fenced_gpu_access = INTEL_INFO(engine->dev)->gen < 4;
+	bool has_fenced_gpu_access = INTEL_GEN(engine->i915) < 4;
 	int retry;
 
 	i915_gem_retire_requests_ring(engine);
@@ -826,7 +826,7 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 				  struct intel_engine_cs *engine,
 				  struct eb_vmas *eb,
 				  struct drm_i915_gem_exec_object2 *exec,
-				  struct intel_context *ctx)
+				  struct i915_gem_context *ctx)
 {
 	struct drm_i915_gem_relocation_entry *reloc;
 	struct i915_address_space *vm;
@@ -963,7 +963,7 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
 	}
 
 	if (flush_chipset)
-		i915_gem_chipset_flush(req->engine->dev);
+		i915_gem_chipset_flush(req->engine->i915);
 
 	if (flush_domains & I915_GEM_DOMAIN_GTT)
 		wmb();
@@ -1063,17 +1063,17 @@ validate_exec_list(struct drm_device *dev,
 	return 0;
 }
 
-static struct intel_context *
+static struct i915_gem_context *
 i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
 			  struct intel_engine_cs *engine, const u32 ctx_id)
 {
-	struct intel_context *ctx = NULL;
+	struct i915_gem_context *ctx = NULL;
 	struct i915_ctx_hang_stats *hs;
 
 	if (engine->id != RCS && ctx_id != DEFAULT_CONTEXT_HANDLE)
 		return ERR_PTR(-EINVAL);
 
-	ctx = i915_gem_context_get(file->driver_priv, ctx_id);
+	ctx = i915_gem_context_lookup(file->driver_priv, ctx_id);
 	if (IS_ERR(ctx))
 		return ctx;
 
@@ -1083,14 +1083,6 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
 		return ERR_PTR(-EIO);
 	}
 
-	if (i915.enable_execlists && !ctx->engine[engine->id].state) {
-		int ret = intel_lr_context_deferred_alloc(ctx, engine);
-		if (ret) {
-			DRM_DEBUG("Could not create LRC %u: %d\n", ctx_id, ret);
-			return ERR_PTR(ret);
-		}
-	}
-
 	return ctx;
 }
 
@@ -1125,7 +1117,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 		if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) {
 			i915_gem_request_assign(&obj->last_fenced_req, req);
 			if (entry->flags & __EXEC_OBJECT_HAS_FENCE) {
-				struct drm_i915_private *dev_priv = to_i915(engine->dev);
+				struct drm_i915_private *dev_priv = engine->i915;
 				list_move_tail(&dev_priv->fence_regs[obj->fence_reg].lru_list,
 					       &dev_priv->mm.fence_list);
 			}
@@ -1150,7 +1142,7 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
 			    struct drm_i915_gem_request *req)
 {
 	struct intel_engine_cs *engine = req->engine;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret, i;
 
 	if (!IS_GEN7(dev) || engine != &dev_priv->engine[RCS]) {
@@ -1233,7 +1225,7 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
 {
 	struct drm_device *dev = params->dev;
 	struct intel_engine_cs *engine = params->engine;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u64 exec_start, exec_len;
 	int instp_mode;
 	u32 instp_mask;
@@ -1336,10 +1328,10 @@ gen8_dispatch_bsd_ring(struct drm_i915_private *dev_priv, struct drm_file *file)
 	/* Check whether the file_priv has already selected one ring. */
 	if ((int)file_priv->bsd_ring < 0) {
 		/* If not, use the ping-pong mechanism to select one. */
-		mutex_lock(&dev_priv->dev->struct_mutex);
+		mutex_lock(&dev_priv->drm.struct_mutex);
 		file_priv->bsd_ring = dev_priv->mm.bsd_ring_dispatch_index;
 		dev_priv->mm.bsd_ring_dispatch_index ^= 1;
-		mutex_unlock(&dev_priv->dev->struct_mutex);
+		mutex_unlock(&dev_priv->drm.struct_mutex);
 	}
 
 	return file_priv->bsd_ring;
@@ -1436,7 +1428,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	struct drm_i915_gem_object *batch_obj;
 	struct drm_i915_gem_exec_object2 shadow_exec_entry;
 	struct intel_engine_cs *engine;
-	struct intel_context *ctx;
+	struct i915_gem_context *ctx;
 	struct i915_address_space *vm;
 	struct i915_execbuffer_params params_master; /* XXX: will be removed later */
 	struct i915_execbuffer_params *params = &params_master;
@@ -1454,7 +1446,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	dispatch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
-		if (!file->is_master || !capable(CAP_SYS_ADMIN))
+		if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN))
 		    return -EPERM;
 
 		dispatch_flags |= I915_DISPATCH_SECURE;
@@ -1485,6 +1477,12 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		dispatch_flags |= I915_DISPATCH_RS;
 	}
 
+	/* Take a local wakeref for preparing to dispatch the execbuf as
+	 * we expect to access the hardware fairly frequently in the
+	 * process. Upon first dispatch, we acquire another prolonged
+	 * wakeref that we hold until the GPU has been idle for at least
+	 * 100ms.
+	 */
 	intel_runtime_pm_get(dev_priv);
 
 	ret = i915_mutex_lock_interruptible(dev);
@@ -1561,7 +1559,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 							     batch_obj,
 							     args->batch_start_offset,
 							     args->batch_len,
-							     file->is_master);
+							     drm_is_current_master(file));
 		if (IS_ERR(parsed_batch_obj)) {
 			ret = PTR_ERR(parsed_batch_obj);
 			goto err;
diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c
index a2b938ec01a7..251d7a95af89 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence.c
@@ -58,7 +58,7 @@
 static void i965_write_fence_reg(struct drm_device *dev, int reg,
 				 struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t fence_reg_lo, fence_reg_hi;
 	int fence_pitch_shift;
 
@@ -117,7 +117,7 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 static void i915_write_fence_reg(struct drm_device *dev, int reg,
 				 struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val;
 
 	if (obj) {
@@ -156,7 +156,7 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg,
 static void i830_write_fence_reg(struct drm_device *dev, int reg,
 				struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t val;
 
 	if (obj) {
@@ -193,7 +193,7 @@ inline static bool i915_gem_object_needs_mb(struct drm_i915_gem_object *obj)
 static void i915_gem_write_fence(struct drm_device *dev, int reg,
 				 struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* Ensure that all CPU reads are completed before installing a fence
 	 * and all writes before removing the fence.
@@ -229,7 +229,7 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 					 struct drm_i915_fence_reg *fence,
 					 bool enable)
 {
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	int reg = fence_number(dev_priv, fence);
 
 	i915_gem_write_fence(obj->base.dev, reg, enable ? obj : NULL);
@@ -286,7 +286,7 @@ i915_gem_object_wait_fence(struct drm_i915_gem_object *obj)
 int
 i915_gem_object_put_fence(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct drm_i915_fence_reg *fence;
 	int ret;
 
@@ -311,7 +311,7 @@ i915_gem_object_put_fence(struct drm_i915_gem_object *obj)
 static struct drm_i915_fence_reg *
 i915_find_fence_reg(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_fence_reg *reg, *avail;
 	int i;
 
@@ -367,7 +367,7 @@ int
 i915_gem_object_get_fence(struct drm_i915_gem_object *obj)
 {
 	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	bool enable = obj->tiling_mode != I915_TILING_NONE;
 	struct drm_i915_fence_reg *reg;
 	int ret;
@@ -433,7 +433,7 @@ bool
 i915_gem_object_pin_fence(struct drm_i915_gem_object *obj)
 {
 	if (obj->fence_reg != I915_FENCE_REG_NONE) {
-		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+		struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 		struct i915_vma *ggtt_vma = i915_gem_obj_to_ggtt(obj);
 
 		WARN_ON(!ggtt_vma ||
@@ -457,7 +457,7 @@ void
 i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj)
 {
 	if (obj->fence_reg != I915_FENCE_REG_NONE) {
-		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+		struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 		WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count <= 0);
 		dev_priv->fence_regs[obj->fence_reg].pin_count--;
 	}
@@ -472,7 +472,7 @@ i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj)
  */
 void i915_gem_restore_fences(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
 	for (i = 0; i < dev_priv->num_fence_regs; i++) {
@@ -549,7 +549,7 @@ void i915_gem_restore_fences(struct drm_device *dev)
 void
 i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
 	uint32_t swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
 
@@ -745,15 +745,15 @@ i915_gem_swizzle_page(struct page *page)
 void
 i915_gem_object_do_bit_17_swizzle(struct drm_i915_gem_object *obj)
 {
-	struct sg_page_iter sg_iter;
+	struct sgt_iter sgt_iter;
+	struct page *page;
 	int i;
 
 	if (obj->bit_17 == NULL)
 		return;
 
 	i = 0;
-	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
-		struct page *page = sg_page_iter_page(&sg_iter);
+	for_each_sgt_page(page, sgt_iter, obj->pages) {
 		char new_bit_17 = page_to_phys(page) >> 17;
 		if ((new_bit_17 & 0x1) !=
 		    (test_bit(i, obj->bit_17) != 0)) {
@@ -775,7 +775,8 @@ i915_gem_object_do_bit_17_swizzle(struct drm_i915_gem_object *obj)
 void
 i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj)
 {
-	struct sg_page_iter sg_iter;
+	struct sgt_iter sgt_iter;
+	struct page *page;
 	int page_count = obj->base.size >> PAGE_SHIFT;
 	int i;
 
@@ -790,8 +791,9 @@ i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj)
 	}
 
 	i = 0;
-	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
-		if (page_to_phys(sg_page_iter_page(&sg_iter)) & (1 << 17))
+
+	for_each_sgt_page(page, sgt_iter, obj->pages) {
+		if (page_to_phys(page) & (1 << 17))
 			__set_bit(i, obj->bit_17);
 		else
 			__clear_bit(i, obj->bit_17);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 92acdff9dad3..10f1e32767e6 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -93,6 +93,13 @@
  *
  */
 
+static inline struct i915_ggtt *
+i915_vm_to_ggtt(struct i915_address_space *vm)
+{
+	GEM_BUG_ON(!i915_is_ggtt(vm));
+	return container_of(vm, struct i915_ggtt, base);
+}
+
 static int
 i915_get_ggtt_vma_pages(struct i915_vma *vma);
 
@@ -103,25 +110,29 @@ const struct i915_ggtt_view i915_ggtt_view_rotated = {
 	.type = I915_GGTT_VIEW_ROTATED,
 };
 
-static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
+int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
+			       	int enable_ppgtt)
 {
 	bool has_aliasing_ppgtt;
 	bool has_full_ppgtt;
 	bool has_full_48bit_ppgtt;
 
-	has_aliasing_ppgtt = INTEL_INFO(dev)->gen >= 6;
-	has_full_ppgtt = INTEL_INFO(dev)->gen >= 7;
-	has_full_48bit_ppgtt = IS_BROADWELL(dev) || INTEL_INFO(dev)->gen >= 9;
+	has_aliasing_ppgtt = INTEL_GEN(dev_priv) >= 6;
+	has_full_ppgtt = INTEL_GEN(dev_priv) >= 7;
+	has_full_48bit_ppgtt =
+	       	IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9;
 
-	if (intel_vgpu_active(dev))
+	if (intel_vgpu_active(dev_priv))
 		has_full_ppgtt = false; /* emulation is too hard */
 
+	if (!has_aliasing_ppgtt)
+		return 0;
+
 	/*
 	 * We don't allow disabling PPGTT for gen9+ as it's a requirement for
 	 * execlists, the sole mechanism available to submit work.
 	 */
-	if (INTEL_INFO(dev)->gen < 9 &&
-	    (enable_ppgtt == 0 || !has_aliasing_ppgtt))
+	if (enable_ppgtt == 0 && INTEL_GEN(dev_priv) < 9)
 		return 0;
 
 	if (enable_ppgtt == 1)
@@ -135,19 +146,19 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
 
 #ifdef CONFIG_INTEL_IOMMU
 	/* Disable ppgtt on SNB if VT-d is on. */
-	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped) {
+	if (IS_GEN6(dev_priv) && intel_iommu_gfx_mapped) {
 		DRM_INFO("Disabling PPGTT because VT-d is on\n");
 		return 0;
 	}
 #endif
 
 	/* Early VLV doesn't have this */
-	if (IS_VALLEYVIEW(dev) && dev->pdev->revision < 0xb) {
+	if (IS_VALLEYVIEW(dev_priv) && dev_priv->drm.pdev->revision < 0xb) {
 		DRM_DEBUG_DRIVER("disabling PPGTT on pre-B3 step VLV\n");
 		return 0;
 	}
 
-	if (INTEL_INFO(dev)->gen >= 8 && i915.enable_execlists)
+	if (INTEL_GEN(dev_priv) >= 8 && i915.enable_execlists)
 		return has_full_48bit_ppgtt ? 3 : 2;
 	else
 		return has_aliasing_ppgtt ? 1 : 0;
@@ -866,6 +877,7 @@ static void gen8_free_page_tables(struct drm_device *dev,
 static int gen8_init_scratch(struct i915_address_space *vm)
 {
 	struct drm_device *dev = vm->dev;
+	int ret;
 
 	vm->scratch_page = alloc_scratch_page(dev);
 	if (IS_ERR(vm->scratch_page))
@@ -873,24 +885,21 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 
 	vm->scratch_pt = alloc_pt(dev);
 	if (IS_ERR(vm->scratch_pt)) {
-		free_scratch_page(dev, vm->scratch_page);
-		return PTR_ERR(vm->scratch_pt);
+		ret = PTR_ERR(vm->scratch_pt);
+		goto free_scratch_page;
 	}
 
 	vm->scratch_pd = alloc_pd(dev);
 	if (IS_ERR(vm->scratch_pd)) {
-		free_pt(dev, vm->scratch_pt);
-		free_scratch_page(dev, vm->scratch_page);
-		return PTR_ERR(vm->scratch_pd);
+		ret = PTR_ERR(vm->scratch_pd);
+		goto free_pt;
 	}
 
 	if (USES_FULL_48BIT_PPGTT(dev)) {
 		vm->scratch_pdp = alloc_pdp(dev);
 		if (IS_ERR(vm->scratch_pdp)) {
-			free_pd(dev, vm->scratch_pd);
-			free_pt(dev, vm->scratch_pt);
-			free_scratch_page(dev, vm->scratch_page);
-			return PTR_ERR(vm->scratch_pdp);
+			ret = PTR_ERR(vm->scratch_pdp);
+			goto free_pd;
 		}
 	}
 
@@ -900,6 +909,15 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 		gen8_initialize_pdp(vm, vm->scratch_pdp);
 
 	return 0;
+
+free_pd:
+	free_pd(dev, vm->scratch_pd);
+free_pt:
+	free_pt(dev, vm->scratch_pt);
+free_scratch_page:
+	free_scratch_page(dev, vm->scratch_page);
+
+	return ret;
 }
 
 static int gen8_ppgtt_notify_vgt(struct i915_hw_ppgtt *ppgtt, bool create)
@@ -978,7 +996,7 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 
-	if (intel_vgpu_active(vm->dev))
+	if (intel_vgpu_active(to_i915(vm->dev)))
 		gen8_ppgtt_notify_vgt(ppgtt, false);
 
 	if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev))
@@ -1529,14 +1547,14 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 							      0, 0,
 							      GEN8_PML4E_SHIFT);
 
-		if (intel_vgpu_active(ppgtt->base.dev)) {
+		if (intel_vgpu_active(to_i915(ppgtt->base.dev))) {
 			ret = gen8_preallocate_top_level_pdps(ppgtt);
 			if (ret)
 				goto free_scratch;
 		}
 	}
 
-	if (intel_vgpu_active(ppgtt->base.dev))
+	if (intel_vgpu_active(to_i915(ppgtt->base.dev)))
 		gen8_ppgtt_notify_vgt(ppgtt, true);
 
 	return 0;
@@ -1552,13 +1570,13 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 	struct i915_page_table *unused;
 	gen6_pte_t scratch_pte;
 	uint32_t pd_entry;
-	uint32_t  pte, pde, temp;
+	uint32_t  pte, pde;
 	uint32_t start = ppgtt->base.start, length = ppgtt->base.total;
 
 	scratch_pte = vm->pte_encode(px_dma(vm->scratch_page),
 				     I915_CACHE_LLC, true, 0);
 
-	gen6_for_each_pde(unused, &ppgtt->pd, start, length, temp, pde) {
+	gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde) {
 		u32 expected;
 		gen6_pte_t *pt_vaddr;
 		const dma_addr_t pt_addr = px_dma(ppgtt->pd.page_table[pde]);
@@ -1622,9 +1640,9 @@ static void gen6_write_page_range(struct drm_i915_private *dev_priv,
 {
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	struct i915_page_table *pt;
-	uint32_t pde, temp;
+	uint32_t pde;
 
-	gen6_for_each_pde(pt, pd, start, length, temp, pde)
+	gen6_for_each_pde(pt, pd, start, length, pde)
 		gen6_write_pde(pd, pde, pt);
 
 	/* Make sure write is complete before other code can use this page
@@ -1665,17 +1683,6 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
 	return 0;
 }
 
-static int vgpu_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct drm_i915_gem_request *req)
-{
-	struct intel_engine_cs *engine = req->engine;
-	struct drm_i915_private *dev_priv = to_i915(ppgtt->base.dev);
-
-	I915_WRITE(RING_PP_DIR_DCLV(engine), PP_DIR_DCLV_2G);
-	I915_WRITE(RING_PP_DIR_BASE(engine), get_pd_offset(ppgtt));
-	return 0;
-}
-
 static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
 			  struct drm_i915_gem_request *req)
 {
@@ -1713,21 +1720,16 @@ static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
 			  struct drm_i915_gem_request *req)
 {
 	struct intel_engine_cs *engine = req->engine;
-	struct drm_device *dev = ppgtt->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
+	struct drm_i915_private *dev_priv = req->i915;
 
 	I915_WRITE(RING_PP_DIR_DCLV(engine), PP_DIR_DCLV_2G);
 	I915_WRITE(RING_PP_DIR_BASE(engine), get_pd_offset(ppgtt));
-
-	POSTING_READ(RING_PP_DIR_DCLV(engine));
-
 	return 0;
 }
 
 static void gen8_ppgtt_enable(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 
 	for_each_engine(engine, dev_priv) {
@@ -1739,7 +1741,7 @@ static void gen8_ppgtt_enable(struct drm_device *dev)
 
 static void gen7_ppgtt_enable(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine;
 	uint32_t ecochk, ecobits;
 
@@ -1764,7 +1766,7 @@ static void gen7_ppgtt_enable(struct drm_device *dev)
 
 static void gen6_ppgtt_enable(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t ecochk, gab_ctl, ecobits;
 
 	ecobits = I915_READ(GAC_ECO_BITS);
@@ -1821,20 +1823,19 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 				      enum i915_cache_level cache_level, u32 flags)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-	gen6_pte_t *pt_vaddr;
 	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned act_pt = first_entry / GEN6_PTES;
 	unsigned act_pte = first_entry % GEN6_PTES;
-	struct sg_page_iter sg_iter;
+	gen6_pte_t *pt_vaddr = NULL;
+	struct sgt_iter sgt_iter;
+	dma_addr_t addr;
 
-	pt_vaddr = NULL;
-	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
+	for_each_sgt_dma(addr, sgt_iter, pages) {
 		if (pt_vaddr == NULL)
 			pt_vaddr = kmap_px(ppgtt->pd.page_table[act_pt]);
 
 		pt_vaddr[act_pte] =
-			vm->pte_encode(sg_page_iter_dma_address(&sg_iter),
-				       cache_level, true, flags);
+			vm->pte_encode(addr, cache_level, true, flags);
 
 		if (++act_pte == GEN6_PTES) {
 			kunmap_px(ppgtt, pt_vaddr);
@@ -1843,6 +1844,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 			act_pte = 0;
 		}
 	}
+
 	if (pt_vaddr)
 		kunmap_px(ppgtt, pt_vaddr);
 }
@@ -1857,7 +1859,7 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 	struct i915_page_table *pt;
 	uint32_t start, length, start_save, length_save;
-	uint32_t pde, temp;
+	uint32_t pde;
 	int ret;
 
 	if (WARN_ON(start_in + length_in > ppgtt->base.total))
@@ -1873,7 +1875,7 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 	 * need allocation. The second stage marks use ptes within the page
 	 * tables.
 	 */
-	gen6_for_each_pde(pt, &ppgtt->pd, start, length, temp, pde) {
+	gen6_for_each_pde(pt, &ppgtt->pd, start, length, pde) {
 		if (pt != vm->scratch_pt) {
 			WARN_ON(bitmap_empty(pt->used_ptes, GEN6_PTES));
 			continue;
@@ -1898,7 +1900,7 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 	start = start_save;
 	length = length_save;
 
-	gen6_for_each_pde(pt, &ppgtt->pd, start, length, temp, pde) {
+	gen6_for_each_pde(pt, &ppgtt->pd, start, length, pde) {
 		DECLARE_BITMAP(tmp_bitmap, GEN6_PTES);
 
 		bitmap_zero(tmp_bitmap, GEN6_PTES);
@@ -1967,15 +1969,16 @@ static void gen6_free_scratch(struct i915_address_space *vm)
 static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+	struct i915_page_directory *pd = &ppgtt->pd;
+	struct drm_device *dev = vm->dev;
 	struct i915_page_table *pt;
 	uint32_t pde;
 
 	drm_mm_remove_node(&ppgtt->node);
 
-	gen6_for_all_pdes(pt, ppgtt, pde) {
+	gen6_for_all_pdes(pt, pd, pde)
 		if (pt != vm->scratch_pt)
-			free_pt(ppgtt->base.dev, pt);
-	}
+			free_pt(dev, pt);
 
 	gen6_free_scratch(vm);
 }
@@ -2041,9 +2044,9 @@ static void gen6_scratch_va_range(struct i915_hw_ppgtt *ppgtt,
 				  uint64_t start, uint64_t length)
 {
 	struct i915_page_table *unused;
-	uint32_t pde, temp;
+	uint32_t pde;
 
-	gen6_for_each_pde(unused, &ppgtt->pd, start, length, temp, pde)
+	gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde)
 		ppgtt->pd.page_table[pde] = ppgtt->base.scratch_pt;
 }
 
@@ -2055,18 +2058,15 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	int ret;
 
 	ppgtt->base.pte_encode = ggtt->base.pte_encode;
-	if (IS_GEN6(dev)) {
+	if (intel_vgpu_active(dev_priv) || IS_GEN6(dev))
 		ppgtt->switch_mm = gen6_mm_switch;
-	} else if (IS_HASWELL(dev)) {
+	else if (IS_HASWELL(dev))
 		ppgtt->switch_mm = hsw_mm_switch;
-	} else if (IS_GEN7(dev)) {
+	else if (IS_GEN7(dev))
 		ppgtt->switch_mm = gen7_mm_switch;
-	} else
+	else
 		BUG();
 
-	if (intel_vgpu_active(dev))
-		ppgtt->switch_mm = vgpu_mm_switch;
-
 	ret = gen6_ppgtt_alloc(ppgtt);
 	if (ret)
 		return ret;
@@ -2115,7 +2115,7 @@ static void i915_address_space_init(struct i915_address_space *vm,
 				    struct drm_i915_private *dev_priv)
 {
 	drm_mm_init(&vm->mm, vm->start, vm->total);
-	vm->dev = dev_priv->dev;
+	vm->dev = &dev_priv->drm;
 	INIT_LIST_HEAD(&vm->active_list);
 	INIT_LIST_HEAD(&vm->inactive_list);
 	list_add_tail(&vm->global_link, &dev_priv->vm_list);
@@ -2123,7 +2123,7 @@ static void i915_address_space_init(struct i915_address_space *vm,
 
 static void gtt_write_workarounds(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* This function is for gtt related workarounds. This function is
 	 * called on driver load and after a GPU reset, so you can place
@@ -2140,9 +2140,9 @@ static void gtt_write_workarounds(struct drm_device *dev)
 		I915_WRITE(GEN8_L3_LRA_1_GPGPU, GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT);
 }
 
-int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
+static int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret = 0;
 
 	ret = __hw_ppgtt_init(dev, ppgtt);
@@ -2179,20 +2179,6 @@ int i915_ppgtt_init_hw(struct drm_device *dev)
 	return 0;
 }
 
-int i915_ppgtt_init_ring(struct drm_i915_gem_request *req)
-{
-	struct drm_i915_private *dev_priv = req->i915;
-	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
-
-	if (i915.enable_execlists)
-		return 0;
-
-	if (!ppgtt)
-		return 0;
-
-	return ppgtt->switch_mm(ppgtt, req);
-}
-
 struct i915_hw_ppgtt *
 i915_ppgtt_create(struct drm_device *dev, struct drm_i915_file_private *fpriv)
 {
@@ -2257,8 +2243,8 @@ static bool do_idling(struct drm_i915_private *dev_priv)
 
 	if (unlikely(ggtt->do_idle_maps)) {
 		dev_priv->mm.interruptible = false;
-		if (i915_gpu_idle(dev_priv->dev)) {
-			DRM_ERROR("Couldn't idle GPU\n");
+		if (i915_gem_wait_for_idle(dev_priv)) {
+			DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
 			/* Wait a bit, in hopes it avoids the hang */
 			udelay(10);
 		}
@@ -2275,12 +2261,11 @@ static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible)
 		dev_priv->mm.interruptible = interruptible;
 }
 
-void i915_check_and_clear_faults(struct drm_device *dev)
+void i915_check_and_clear_faults(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
 
-	if (INTEL_INFO(dev)->gen < 6)
+	if (INTEL_INFO(dev_priv)->gen < 6)
 		return;
 
 	for_each_engine(engine, dev_priv) {
@@ -2324,7 +2309,7 @@ void i915_gem_suspend_gtt_mappings(struct drm_device *dev)
 	if (INTEL_INFO(dev)->gen < 6)
 		return;
 
-	i915_check_and_clear_faults(dev);
+	i915_check_and_clear_faults(dev_priv);
 
 	ggtt->base.clear_range(&ggtt->base, ggtt->base.start, ggtt->base.total,
 			     true);
@@ -2352,29 +2337,49 @@ static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
 #endif
 }
 
+static void gen8_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  uint64_t offset,
+				  enum i915_cache_level level,
+				  u32 unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(vm->dev);
+	gen8_pte_t __iomem *pte =
+		(gen8_pte_t __iomem *)dev_priv->ggtt.gsm +
+		(offset >> PAGE_SHIFT);
+	int rpm_atomic_seq;
+
+	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);
+
+	gen8_set_pte(pte, gen8_pte_encode(addr, level, true));
+
+	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+	POSTING_READ(GFX_FLSH_CNTL_GEN6);
+
+	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
+}
+
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
 				     uint64_t start,
 				     enum i915_cache_level level, u32 unused)
 {
 	struct drm_i915_private *dev_priv = to_i915(vm->dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	unsigned first_entry = start >> PAGE_SHIFT;
-	gen8_pte_t __iomem *gtt_entries =
-		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
-	int i = 0;
-	struct sg_page_iter sg_iter;
-	dma_addr_t addr = 0; /* shut up gcc */
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	struct sgt_iter sgt_iter;
+	gen8_pte_t __iomem *gtt_entries;
+	gen8_pte_t gtt_entry;
+	dma_addr_t addr;
 	int rpm_atomic_seq;
+	int i = 0;
 
 	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);
 
-	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
-		addr = sg_dma_address(sg_iter.sg) +
-			(sg_iter.sg_pgoffset << PAGE_SHIFT);
-		gen8_set_pte(&gtt_entries[i],
-			     gen8_pte_encode(addr, level, true));
-		i++;
+	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm + (start >> PAGE_SHIFT);
+
+	for_each_sgt_dma(addr, sgt_iter, st) {
+		gtt_entry = gen8_pte_encode(addr, level, true);
+		gen8_set_pte(&gtt_entries[i++], gtt_entry);
 	}
 
 	/*
@@ -2385,8 +2390,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 	 * hardware should work, we must keep this posting read for paranoia.
 	 */
 	if (i != 0)
-		WARN_ON(readq(&gtt_entries[i-1])
-			!= gen8_pte_encode(addr, level, true));
+		WARN_ON(readq(&gtt_entries[i-1]) != gtt_entry);
 
 	/* This next bit makes the above posting read even more important. We
 	 * want to flush the TLBs only after we're certain all the PTE updates
@@ -2424,6 +2428,28 @@ static void gen8_ggtt_insert_entries__BKL(struct i915_address_space *vm,
 	stop_machine(gen8_ggtt_insert_entries__cb, &arg, NULL);
 }
 
+static void gen6_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  uint64_t offset,
+				  enum i915_cache_level level,
+				  u32 flags)
+{
+	struct drm_i915_private *dev_priv = to_i915(vm->dev);
+	gen6_pte_t __iomem *pte =
+		(gen6_pte_t __iomem *)dev_priv->ggtt.gsm +
+		(offset >> PAGE_SHIFT);
+	int rpm_atomic_seq;
+
+	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);
+
+	iowrite32(vm->pte_encode(addr, level, true, flags), pte);
+
+	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+	POSTING_READ(GFX_FLSH_CNTL_GEN6);
+
+	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
+}
+
 /*
  * Binds an object into the global gtt with the specified cache level. The object
  * will be accessible to the GPU via commands whose operands reference offsets
@@ -2436,21 +2462,21 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 				     enum i915_cache_level level, u32 flags)
 {
 	struct drm_i915_private *dev_priv = to_i915(vm->dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	unsigned first_entry = start >> PAGE_SHIFT;
-	gen6_pte_t __iomem *gtt_entries =
-		(gen6_pte_t __iomem *)ggtt->gsm + first_entry;
-	int i = 0;
-	struct sg_page_iter sg_iter;
-	dma_addr_t addr = 0;
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	struct sgt_iter sgt_iter;
+	gen6_pte_t __iomem *gtt_entries;
+	gen6_pte_t gtt_entry;
+	dma_addr_t addr;
 	int rpm_atomic_seq;
+	int i = 0;
 
 	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);
 
-	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
-		addr = sg_page_iter_dma_address(&sg_iter);
-		iowrite32(vm->pte_encode(addr, level, true, flags), &gtt_entries[i]);
-		i++;
+	gtt_entries = (gen6_pte_t __iomem *)ggtt->gsm + (start >> PAGE_SHIFT);
+
+	for_each_sgt_dma(addr, sgt_iter, st) {
+		gtt_entry = vm->pte_encode(addr, level, true, flags);
+		iowrite32(gtt_entry, &gtt_entries[i++]);
 	}
 
 	/* XXX: This serves as a posting read to make sure that the PTE has
@@ -2459,10 +2485,8 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 	 * of NUMA access patterns. Therefore, even with the way we assume
 	 * hardware should work, we must keep this posting read for paranoia.
 	 */
-	if (i != 0) {
-		unsigned long gtt = readl(&gtt_entries[i-1]);
-		WARN_ON(gtt != vm->pte_encode(addr, level, true, flags));
-	}
+	if (i != 0)
+		WARN_ON(readl(&gtt_entries[i-1]) != gtt_entry);
 
 	/* This next bit makes the above posting read even more important. We
 	 * want to flush the TLBs only after we're certain all the PTE updates
@@ -2474,13 +2498,20 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
 }
 
+static void nop_clear_range(struct i915_address_space *vm,
+			    uint64_t start,
+			    uint64_t length,
+			    bool use_scratch)
+{
+}
+
 static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 				  uint64_t start,
 				  uint64_t length,
 				  bool use_scratch)
 {
 	struct drm_i915_private *dev_priv = to_i915(vm->dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned num_entries = length >> PAGE_SHIFT;
 	gen8_pte_t scratch_pte, __iomem *gtt_base =
@@ -2512,7 +2543,7 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 				  bool use_scratch)
 {
 	struct drm_i915_private *dev_priv = to_i915(vm->dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned num_entries = length >> PAGE_SHIFT;
 	gen6_pte_t scratch_pte, __iomem *gtt_base =
@@ -2538,12 +2569,30 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
 }
 
+static void i915_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  uint64_t offset,
+				  enum i915_cache_level cache_level,
+				  u32 unused)
+{
+	struct drm_i915_private *dev_priv = to_i915(vm->dev);
+	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+	int rpm_atomic_seq;
+
+	rpm_atomic_seq = assert_rpm_atomic_begin(dev_priv);
+
+	intel_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags);
+
+	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
+}
+
 static void i915_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *pages,
 				     uint64_t start,
 				     enum i915_cache_level cache_level, u32 unused)
 {
-	struct drm_i915_private *dev_priv = vm->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(vm->dev);
 	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
 		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
 	int rpm_atomic_seq;
@@ -2561,7 +2610,7 @@ static void i915_ggtt_clear_range(struct i915_address_space *vm,
 				  uint64_t length,
 				  bool unused)
 {
-	struct drm_i915_private *dev_priv = vm->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(vm->dev);
 	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned num_entries = length >> PAGE_SHIFT;
 	int rpm_atomic_seq;
@@ -2642,7 +2691,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 static void ggtt_unbind_vma(struct i915_vma *vma)
 {
 	struct drm_device *dev = vma->vm->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj = vma->obj;
 	const uint64_t size = min_t(uint64_t,
 				    obj->base.size,
@@ -2668,7 +2717,7 @@ static void ggtt_unbind_vma(struct i915_vma *vma)
 void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj)
 {
 	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	bool interruptible;
 
 	interruptible = do_idling(dev_priv);
@@ -2727,11 +2776,9 @@ static int i915_gem_setup_global_gtt(struct drm_device *dev,
 	i915_address_space_init(&ggtt->base, dev_priv);
 	ggtt->base.total += PAGE_SIZE;
 
-	if (intel_vgpu_active(dev)) {
-		ret = intel_vgt_balloon(dev);
-		if (ret)
-			return ret;
-	}
+	ret = intel_vgt_balloon(dev_priv);
+	if (ret)
+		return ret;
 
 	if (!HAS_LLC(dev))
 		ggtt->base.mm.color_adjust = i915_gtt_color_adjust;
@@ -2831,8 +2878,7 @@ void i915_ggtt_cleanup_hw(struct drm_device *dev)
 	i915_gem_cleanup_stolen(dev);
 
 	if (drm_mm_initialized(&ggtt->base.mm)) {
-		if (intel_vgpu_active(dev))
-			intel_vgt_deballoon();
+		intel_vgt_deballoon(dev_priv);
 
 		drm_mm_takedown(&ggtt->base.mm);
 		list_del(&ggtt->base.global_link);
@@ -3069,13 +3115,16 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ret = ggtt_probe_common(dev, ggtt->size);
 
-	ggtt->base.clear_range = gen8_ggtt_clear_range;
-	if (IS_CHERRYVIEW(dev_priv))
-		ggtt->base.insert_entries = gen8_ggtt_insert_entries__BKL;
-	else
-		ggtt->base.insert_entries = gen8_ggtt_insert_entries;
 	ggtt->base.bind_vma = ggtt_bind_vma;
 	ggtt->base.unbind_vma = ggtt_unbind_vma;
+	ggtt->base.insert_page = gen8_ggtt_insert_page;
+	ggtt->base.clear_range = nop_clear_range;
+	if (!USES_FULL_PPGTT(dev_priv) || intel_scanout_needs_vtd_wa(dev_priv))
+		ggtt->base.clear_range = gen8_ggtt_clear_range;
+
+	ggtt->base.insert_entries = gen8_ggtt_insert_entries;
+	if (IS_CHERRYVIEW(dev_priv))
+		ggtt->base.insert_entries = gen8_ggtt_insert_entries__BKL;
 
 	return ret;
 }
@@ -3108,6 +3157,7 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	ret = ggtt_probe_common(dev, ggtt->size);
 
 	ggtt->base.clear_range = gen6_ggtt_clear_range;
+	ggtt->base.insert_page = gen6_ggtt_insert_page;
 	ggtt->base.insert_entries = gen6_ggtt_insert_entries;
 	ggtt->base.bind_vma = ggtt_bind_vma;
 	ggtt->base.unbind_vma = ggtt_unbind_vma;
@@ -3129,7 +3179,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
-	ret = intel_gmch_probe(dev_priv->bridge_dev, dev_priv->dev->pdev, NULL);
+	ret = intel_gmch_probe(dev_priv->bridge_dev, dev_priv->drm.pdev, NULL);
 	if (!ret) {
 		DRM_ERROR("failed to set up gmch\n");
 		return -EIO;
@@ -3138,7 +3188,8 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
 	intel_gtt_get(&ggtt->base.total, &ggtt->stolen_size,
 		      &ggtt->mappable_base, &ggtt->mappable_end);
 
-	ggtt->do_idle_maps = needs_idle_maps(dev_priv->dev);
+	ggtt->do_idle_maps = needs_idle_maps(&dev_priv->drm);
+	ggtt->base.insert_page = i915_ggtt_insert_page;
 	ggtt->base.insert_entries = i915_ggtt_insert_entries;
 	ggtt->base.clear_range = i915_ggtt_clear_range;
 	ggtt->base.bind_vma = ggtt_bind_vma;
@@ -3219,14 +3270,6 @@ int i915_ggtt_init_hw(struct drm_device *dev)
 	if (intel_iommu_gfx_mapped)
 		DRM_INFO("VT-d active for gfx access\n");
 #endif
-	/*
-	 * i915.enable_ppgtt is read-only, so do an early pass to validate the
-	 * user's requested state against the hardware/driver capabilities.  We
-	 * do this now so that we can print out any log messages once rather
-	 * than every time we check intel_enable_ppgtt().
-	 */
-	i915.enable_ppgtt = sanitize_enable_ppgtt(dev, i915.enable_ppgtt);
-	DRM_DEBUG_DRIVER("ppgtt mode: %i\n", i915.enable_ppgtt);
 
 	return 0;
 
@@ -3250,9 +3293,8 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
-	bool flush;
 
-	i915_check_and_clear_faults(dev);
+	i915_check_and_clear_faults(dev_priv);
 
 	/* First fill our portion of the GTT with scratch pages */
 	ggtt->base.clear_range(&ggtt->base, ggtt->base.start, ggtt->base.total,
@@ -3260,19 +3302,16 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 
 	/* Cache flush objects bound into GGTT and rebind them. */
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		flush = false;
 		list_for_each_entry(vma, &obj->vma_list, obj_link) {
 			if (vma->vm != &ggtt->base)
 				continue;
 
 			WARN_ON(i915_vma_bind(vma, obj->cache_level,
 					      PIN_UPDATE));
-
-			flush = true;
 		}
 
-		if (flush)
-			i915_gem_clflush_object(obj, obj->pin_display);
+		if (obj->pin_display)
+			WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false));
 	}
 
 	if (INTEL_INFO(dev)->gen >= 8) {
@@ -3398,9 +3437,11 @@ static struct sg_table *
 intel_rotate_fb_obj_pages(struct intel_rotation_info *rot_info,
 			  struct drm_i915_gem_object *obj)
 {
+	const size_t n_pages = obj->base.size / PAGE_SIZE;
 	unsigned int size_pages = rot_info->plane[0].width * rot_info->plane[0].height;
 	unsigned int size_pages_uv;
-	struct sg_page_iter sg_iter;
+	struct sgt_iter sgt_iter;
+	dma_addr_t dma_addr;
 	unsigned long i;
 	dma_addr_t *page_addr_list;
 	struct sg_table *st;
@@ -3409,7 +3450,7 @@ intel_rotate_fb_obj_pages(struct intel_rotation_info *rot_info,
 	int ret = -ENOMEM;
 
 	/* Allocate a temporary list of source pages for random access. */
-	page_addr_list = drm_malloc_gfp(obj->base.size / PAGE_SIZE,
+	page_addr_list = drm_malloc_gfp(n_pages,
 					sizeof(dma_addr_t),
 					GFP_TEMPORARY);
 	if (!page_addr_list)
@@ -3432,11 +3473,10 @@ intel_rotate_fb_obj_pages(struct intel_rotation_info *rot_info,
 
 	/* Populate source page list from the object. */
 	i = 0;
-	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
-		page_addr_list[i] = sg_page_iter_dma_address(&sg_iter);
-		i++;
-	}
+	for_each_sgt_dma(dma_addr, sgt_iter, obj->pages)
+		page_addr_list[i++] = dma_addr;
 
+	GEM_BUG_ON(i != n_pages);
 	st->nents = 0;
 	sg = st->sgl;
 
@@ -3634,3 +3674,29 @@ i915_ggtt_view_size(struct drm_i915_gem_object *obj,
 		return obj->base.size;
 	}
 }
+
+void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
+{
+	void __iomem *ptr;
+
+	lockdep_assert_held(&vma->vm->dev->struct_mutex);
+	if (WARN_ON(!vma->obj->map_and_fenceable))
+		return ERR_PTR(-ENODEV);
+
+	GEM_BUG_ON(!vma->is_ggtt);
+	GEM_BUG_ON((vma->bound & GLOBAL_BIND) == 0);
+
+	ptr = vma->iomap;
+	if (ptr == NULL) {
+		ptr = io_mapping_map_wc(i915_vm_to_ggtt(vma->vm)->mappable,
+					vma->node.start,
+					vma->node.size);
+		if (ptr == NULL)
+			return ERR_PTR(-ENOMEM);
+
+		vma->iomap = ptr;
+	}
+
+	vma->pin_count++;
+	return ptr;
+}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 0008543d55f6..aa5f31d1c2ed 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -34,6 +34,8 @@
 #ifndef __I915_GEM_GTT_H__
 #define __I915_GEM_GTT_H__
 
+#include <linux/io-mapping.h>
+
 struct drm_i915_file_private;
 
 typedef uint32_t gen6_pte_t;
@@ -175,6 +177,7 @@ struct i915_vma {
 	struct drm_mm_node node;
 	struct drm_i915_gem_object *obj;
 	struct i915_address_space *vm;
+	void __iomem *iomap;
 
 	/** Flags and address space this VMA is bound to */
 #define GLOBAL_BIND	(1<<0)
@@ -316,6 +319,11 @@ struct i915_address_space {
 			    uint64_t start,
 			    uint64_t length,
 			    bool use_scratch);
+	void (*insert_page)(struct i915_address_space *vm,
+			    dma_addr_t addr,
+			    uint64_t offset,
+			    enum i915_cache_level cache_level,
+			    u32 flags);
 	void (*insert_entries)(struct i915_address_space *vm,
 			       struct sg_table *st,
 			       uint64_t start,
@@ -382,27 +390,27 @@ struct i915_hw_ppgtt {
 	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
 };
 
-/* For each pde iterates over every pde between from start until start + length.
- * If start, and start+length are not perfectly divisible, the macro will round
- * down, and up as needed. The macro modifies pde, start, and length. Dev is
- * only used to differentiate shift values. Temp is temp.  On gen6/7, start = 0,
- * and length = 2G effectively iterates over every PDE in the system.
- *
- * XXX: temp is not actually needed, but it saves doing the ALIGN operation.
+/*
+ * gen6_for_each_pde() iterates over every pde from start until start+length.
+ * If start and start+length are not perfectly divisible, the macro will round
+ * down and up as needed. Start=0 and length=2G effectively iterates over
+ * every PDE in the system. The macro modifies ALL its parameters except 'pd',
+ * so each of the other parameters should preferably be a simple variable, or
+ * at most an lvalue with no side-effects!
  */
-#define gen6_for_each_pde(pt, pd, start, length, temp, iter) \
-	for (iter = gen6_pde_index(start); \
-	     length > 0 && iter < I915_PDES ? \
-			(pt = (pd)->page_table[iter]), 1 : 0; \
-	     iter++, \
-	     temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT) - start, \
-	     temp = min_t(unsigned, temp, length), \
-	     start += temp, length -= temp)
-
-#define gen6_for_all_pdes(pt, ppgtt, iter)  \
-	for (iter = 0;		\
-	     pt = ppgtt->pd.page_table[iter], iter < I915_PDES;	\
-	     iter++)
+#define gen6_for_each_pde(pt, pd, start, length, iter)			\
+	for (iter = gen6_pde_index(start);				\
+	     length > 0 && iter < I915_PDES &&				\
+		(pt = (pd)->page_table[iter], true);			\
+	     ({ u32 temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT);		\
+		    temp = min(temp - start, length);			\
+		    start += temp, length -= temp; }), ++iter)
+
+#define gen6_for_all_pdes(pt, pd, iter)					\
+	for (iter = 0;							\
+	     iter < I915_PDES &&					\
+		(pt = (pd)->page_table[iter], true);			\
+	     ++iter)
 
 static inline uint32_t i915_pte_index(uint64_t address, uint32_t pde_shift)
 {
@@ -518,9 +526,7 @@ int i915_ggtt_enable_hw(struct drm_device *dev);
 void i915_gem_init_ggtt(struct drm_device *dev);
 void i915_ggtt_cleanup_hw(struct drm_device *dev);
 
-int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
 int i915_ppgtt_init_hw(struct drm_device *dev);
-int i915_ppgtt_init_ring(struct drm_i915_gem_request *req);
 void i915_ppgtt_release(struct kref *kref);
 struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_device *dev,
 					struct drm_i915_file_private *fpriv);
@@ -535,7 +541,7 @@ static inline void i915_ppgtt_put(struct i915_hw_ppgtt *ppgtt)
 		kref_put(&ppgtt->ref, i915_ppgtt_release);
 }
 
-void i915_check_and_clear_faults(struct drm_device *dev);
+void i915_check_and_clear_faults(struct drm_i915_private *dev_priv);
 void i915_gem_suspend_gtt_mappings(struct drm_device *dev);
 void i915_gem_restore_gtt_mappings(struct drm_device *dev);
 
@@ -560,4 +566,36 @@ size_t
 i915_ggtt_view_size(struct drm_i915_gem_object *obj,
 		    const struct i915_ggtt_view *view);
 
+/**
+ * i915_vma_pin_iomap - calls ioremap_wc to map the GGTT VMA via the aperture
+ * @vma: VMA to iomap
+ *
+ * The passed in VMA has to be pinned in the global GTT mappable region.
+ * An extra pinning of the VMA is acquired for the return iomapping,
+ * the caller must call i915_vma_unpin_iomap to relinquish the pinning
+ * after the iomapping is no longer required.
+ *
+ * Callers must hold the struct_mutex.
+ *
+ * Returns a valid iomapped pointer or ERR_PTR.
+ */
+void __iomem *i915_vma_pin_iomap(struct i915_vma *vma);
+
+/**
+ * i915_vma_unpin_iomap - unpins the mapping returned from i915_vma_iomap
+ * @vma: VMA to unpin
+ *
+ * Unpins the previously iomapped VMA from i915_vma_pin_iomap().
+ *
+ * Callers must hold the struct_mutex. This function is only valid to be
+ * called on a VMA previously iomapped by the caller with i915_vma_pin_iomap().
+ */
+static inline void i915_vma_unpin_iomap(struct i915_vma *vma)
+{
+	lockdep_assert_held(&vma->vm->dev->struct_mutex);
+	GEM_BUG_ON(vma->pin_count == 0);
+	GEM_BUG_ON(vma->iomap == NULL);
+	vma->pin_count--;
+}
+
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 71611bf21fca..f75bbd67a13a 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -29,7 +29,7 @@
 #include "intel_renderstate.h"
 
 static const struct intel_renderstate_rodata *
-render_state_get_rodata(struct drm_device *dev, const int gen)
+render_state_get_rodata(const int gen)
 {
 	switch (gen) {
 	case 6:
@@ -45,21 +45,22 @@ render_state_get_rodata(struct drm_device *dev, const int gen)
 	return NULL;
 }
 
-static int render_state_init(struct render_state *so, struct drm_device *dev)
+static int render_state_init(struct render_state *so,
+			     struct drm_i915_private *dev_priv)
 {
 	int ret;
 
-	so->gen = INTEL_INFO(dev)->gen;
-	so->rodata = render_state_get_rodata(dev, so->gen);
+	so->gen = INTEL_GEN(dev_priv);
+	so->rodata = render_state_get_rodata(so->gen);
 	if (so->rodata == NULL)
 		return 0;
 
 	if (so->rodata->batch_items * 4 > 4096)
 		return -EINVAL;
 
-	so->obj = i915_gem_alloc_object(dev, 4096);
-	if (so->obj == NULL)
-		return -ENOMEM;
+	so->obj = i915_gem_object_create(&dev_priv->drm, 4096);
+	if (IS_ERR(so->obj))
+		return PTR_ERR(so->obj);
 
 	ret = i915_gem_obj_ggtt_pin(so->obj, 4096, 0);
 	if (ret)
@@ -93,6 +94,7 @@ free_gem:
 
 static int render_state_setup(struct render_state *so)
 {
+	struct drm_device *dev = so->obj->base.dev;
 	const struct intel_renderstate_rodata *rodata = so->rodata;
 	unsigned int i = 0, reloc_index = 0;
 	struct page *page;
@@ -134,6 +136,33 @@ static int render_state_setup(struct render_state *so)
 
 	so->aux_batch_offset = i * sizeof(u32);
 
+	if (HAS_POOLED_EU(dev)) {
+		/*
+		 * We always program 3x6 pool config but depending upon which
+		 * subslice is disabled HW drops down to appropriate config
+		 * shown below.
+		 *
+		 * In the below table 2x6 config always refers to
+		 * fused-down version, native 2x6 is not available and can
+		 * be ignored
+		 *
+		 * SNo  subslices config                eu pool configuration
+		 * -----------------------------------------------------------
+		 * 1    3 subslices enabled (3x6)  -    0x00777000  (9+9)
+		 * 2    ss0 disabled (2x6)         -    0x00777000  (3+9)
+		 * 3    ss1 disabled (2x6)         -    0x00770000  (6+6)
+		 * 4    ss2 disabled (2x6)         -    0x00007000  (9+3)
+		 */
+		u32 eu_pool_config = 0x00777000;
+
+		OUT_BATCH(d, i, GEN9_MEDIA_POOL_STATE);
+		OUT_BATCH(d, i, GEN9_MEDIA_POOL_ENABLE);
+		OUT_BATCH(d, i, eu_pool_config);
+		OUT_BATCH(d, i, 0);
+		OUT_BATCH(d, i, 0);
+		OUT_BATCH(d, i, 0);
+	}
+
 	OUT_BATCH(d, i, MI_BATCH_BUFFER_END);
 	so->aux_batch_size = (i * sizeof(u32)) - so->aux_batch_offset;
 
@@ -177,7 +206,7 @@ int i915_gem_render_state_prepare(struct intel_engine_cs *engine,
 	if (WARN_ON(engine->id != RCS))
 		return -ENOENT;
 
-	ret = render_state_init(so, engine->dev);
+	ret = render_state_init(so, engine->i915);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 66571466e9a8..6f10b421487b 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -131,7 +131,16 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 	unsigned long count = 0;
 
 	trace_i915_gem_shrink(dev_priv, target, flags);
-	i915_gem_retire_requests(dev_priv->dev);
+	i915_gem_retire_requests(dev_priv);
+
+	/*
+	 * Unbinding of objects will require HW access; Let us not wake the
+	 * device just to recover a little memory. If absolutely necessary,
+	 * we will force the wake during oom-notifier.
+	 */
+	if ((flags & I915_SHRINK_BOUND) &&
+	    !intel_runtime_pm_get_if_in_use(dev_priv))
+		flags &= ~I915_SHRINK_BOUND;
 
 	/*
 	 * As we may completely rewrite the (un)bound list whilst unbinding
@@ -197,7 +206,10 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 		list_splice(&still_in_list, phase->list);
 	}
 
-	i915_gem_retire_requests(dev_priv->dev);
+	if (flags & I915_SHRINK_BOUND)
+		intel_runtime_pm_put(dev_priv);
+
+	i915_gem_retire_requests(dev_priv);
 
 	return count;
 }
@@ -245,7 +257,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(shrinker, struct drm_i915_private, mm.shrinker);
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct drm_i915_gem_object *obj;
 	unsigned long count;
 	bool unlock;
@@ -253,6 +265,8 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 	if (!i915_gem_shrinker_lock(dev, &unlock))
 		return 0;
 
+	i915_gem_retire_requests(dev_priv);
+
 	count = 0;
 	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
 		if (can_release_pages(obj))
@@ -274,7 +288,7 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(shrinker, struct drm_i915_private, mm.shrinker);
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	unsigned long freed;
 	bool unlock;
 
@@ -309,7 +323,7 @@ i915_gem_shrinker_lock_uninterruptible(struct drm_i915_private *dev_priv,
 {
 	unsigned long timeout = msecs_to_jiffies(timeout_ms) + 1;
 
-	while (!i915_gem_shrinker_lock(dev_priv->dev, &slu->unlock)) {
+	while (!i915_gem_shrinker_lock(&dev_priv->drm, &slu->unlock)) {
 		schedule_timeout_killable(1);
 		if (fatal_signal_pending(current))
 			return false;
@@ -330,7 +344,7 @@ i915_gem_shrinker_unlock_uninterruptible(struct drm_i915_private *dev_priv,
 {
 	dev_priv->mm.interruptible = slu->was_interruptible;
 	if (slu->unlock)
-		mutex_unlock(&dev_priv->dev->struct_mutex);
+		mutex_unlock(&dev_priv->drm.struct_mutex);
 }
 
 static int
@@ -345,7 +359,9 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
 	if (!i915_gem_shrinker_lock_uninterruptible(dev_priv, &slu, 5000))
 		return NOTIFY_DONE;
 
+	intel_runtime_pm_get(dev_priv);
 	freed_pages = i915_gem_shrink_all(dev_priv);
+	intel_runtime_pm_put(dev_priv);
 
 	/* Because we may be allocating inside our own driver, we cannot
 	 * assert that there are no objects with pinned pages that are not
@@ -386,17 +402,35 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 	struct drm_i915_private *dev_priv =
 		container_of(nb, struct drm_i915_private, mm.vmap_notifier);
 	struct shrinker_lock_uninterruptible slu;
-	unsigned long freed_pages;
+	struct i915_vma *vma, *next;
+	unsigned long freed_pages = 0;
+	int ret;
 
 	if (!i915_gem_shrinker_lock_uninterruptible(dev_priv, &slu, 5000))
 		return NOTIFY_DONE;
 
-	freed_pages = i915_gem_shrink(dev_priv, -1UL,
-				      I915_SHRINK_BOUND |
-				      I915_SHRINK_UNBOUND |
-				      I915_SHRINK_ACTIVE |
-				      I915_SHRINK_VMAPS);
+	/* Force everything onto the inactive lists */
+	ret = i915_gem_wait_for_idle(dev_priv);
+	if (ret)
+		goto out;
+
+	intel_runtime_pm_get(dev_priv);
+	freed_pages += i915_gem_shrink(dev_priv, -1UL,
+				       I915_SHRINK_BOUND |
+				       I915_SHRINK_UNBOUND |
+				       I915_SHRINK_ACTIVE |
+				       I915_SHRINK_VMAPS);
+	intel_runtime_pm_put(dev_priv);
+
+	/* We also want to clear any cached iomaps as they wrap vmap */
+	list_for_each_entry_safe(vma, next,
+				 &dev_priv->ggtt.base.inactive_list, vm_link) {
+		unsigned long count = vma->node.size >> PAGE_SHIFT;
+		if (vma->iomap && i915_vma_unbind(vma) == 0)
+			freed_pages += count;
+	}
 
+out:
 	i915_gem_shrinker_unlock_uninterruptible(dev_priv, &slu);
 
 	*(unsigned long *)ptr += freed_pages;
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 44004e3f09e4..66be299a1486 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -111,9 +111,9 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev)
 	if (INTEL_INFO(dev)->gen >= 3) {
 		u32 bsm;
 
-		pci_read_config_dword(dev->pdev, BSM, &bsm);
+		pci_read_config_dword(dev->pdev, INTEL_BSM, &bsm);
 
-		base = bsm & BSM_MASK;
+		base = bsm & INTEL_BSM_MASK;
 	} else if (IS_I865G(dev)) {
 		u16 toud = 0;
 
@@ -270,7 +270,7 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev)
 
 void i915_gem_cleanup_stolen(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return;
@@ -550,7 +550,7 @@ static void i915_gem_object_put_pages_stolen(struct drm_i915_gem_object *obj)
 static void
 i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 
 	if (obj->stolen) {
 		i915_gem_stolen_remove_node(dev_priv, obj->stolen);
@@ -601,7 +601,7 @@ cleanup:
 struct drm_i915_gem_object *
 i915_gem_object_create_stolen(struct drm_device *dev, u32 size)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
 	int ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index b9bdb34032cd..8030199731db 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -125,7 +125,7 @@ i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode)
 	if (INTEL_INFO(obj->base.dev)->gen >= 4)
 		return true;
 
-	if (INTEL_INFO(obj->base.dev)->gen == 3) {
+	if (IS_GEN3(obj->base.dev)) {
 		if (i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK)
 			return false;
 	} else {
@@ -162,7 +162,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		   struct drm_file *file)
 {
 	struct drm_i915_gem_set_tiling *args = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
 	int ret = 0;
 
@@ -229,7 +229,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		 */
 		if (obj->map_and_fenceable &&
 		    !i915_gem_object_fence_ok(obj, args->tiling_mode))
-			ret = i915_gem_object_ggtt_unbind(obj);
+			ret = i915_vma_unbind(i915_gem_obj_to_ggtt(obj));
 
 		if (ret == 0) {
 			if (obj->pages &&
@@ -294,7 +294,7 @@ i915_gem_get_tiling(struct drm_device *dev, void *data,
 		   struct drm_file *file)
 {
 	struct drm_i915_gem_get_tiling *args = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
 
 	obj = to_intel_bo(drm_gem_object_lookup(file, args->handle));
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 32d9726e38b1..2314c88323e3 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -706,7 +706,8 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 static void
 i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj)
 {
-	struct sg_page_iter sg_iter;
+	struct sgt_iter sgt_iter;
+	struct page *page;
 
 	BUG_ON(obj->userptr.work != NULL);
 	__i915_gem_userptr_set_active(obj, false);
@@ -716,9 +717,7 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj)
 
 	i915_gem_gtt_finish_object(obj);
 
-	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
-		struct page *page = sg_page_iter_page(&sg_iter);
-
+	for_each_sgt_page(page, sgt_iter, obj->pages) {
 		if (obj->dirty)
 			set_page_dirty(page);
 
@@ -855,11 +854,8 @@ i915_gem_userptr_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 	return 0;
 }
 
-int
-i915_gem_init_userptr(struct drm_device *dev)
+void i915_gem_init_userptr(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	mutex_init(&dev_priv->mm_lock);
 	hash_init(dev_priv->mm_structs);
-	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 89725c9efc25..9d73d2216adc 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -332,7 +332,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			    const struct i915_error_state_file_priv *error_priv)
 {
 	struct drm_device *dev = error_priv->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_error_state *error = error_priv->error;
 	struct drm_i915_error_object *obj;
 	int i, j, offset, elt;
@@ -411,7 +411,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
 	}
 
-	if (INTEL_INFO(dev)->gen == 7)
+	if (IS_GEN7(dev))
 		err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
 
 	for (i = 0; i < ARRAY_SIZE(error->ring); i++)
@@ -463,6 +463,18 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			}
 		}
 
+		if (error->ring[i].num_waiters) {
+			err_printf(m, "%s --- %d waiters\n",
+				   dev_priv->engine[i].name,
+				   error->ring[i].num_waiters);
+			for (j = 0; j < error->ring[i].num_waiters; j++) {
+				err_printf(m, " seqno 0x%08x for %s [%d]\n",
+					   error->ring[i].waiters[j].seqno,
+					   error->ring[i].waiters[j].comm,
+					   error->ring[i].waiters[j].pid);
+			}
+		}
+
 		if ((obj = error->ring[i].ringbuffer)) {
 			err_printf(m, "%s --- ringbuffer = 0x%08x\n",
 				   dev_priv->engine[i].name,
@@ -488,7 +500,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 					   hws_page[elt+1],
 					   hws_page[elt+2],
 					   hws_page[elt+3]);
-					offset += 16;
+				offset += 16;
 			}
 		}
 
@@ -605,8 +617,9 @@ static void i915_error_state_free(struct kref *error_ref)
 		i915_error_object_free(error->ring[i].ringbuffer);
 		i915_error_object_free(error->ring[i].hws_page);
 		i915_error_object_free(error->ring[i].ctx);
-		kfree(error->ring[i].requests);
 		i915_error_object_free(error->ring[i].wa_ctx);
+		kfree(error->ring[i].requests);
+		kfree(error->ring[i].waiters);
 	}
 
 	i915_error_object_free(error->semaphore_obj);
@@ -824,19 +837,18 @@ static uint32_t i915_error_generate_code(struct drm_i915_private *dev_priv,
 	return error_code;
 }
 
-static void i915_gem_record_fences(struct drm_device *dev,
+static void i915_gem_record_fences(struct drm_i915_private *dev_priv,
 				   struct drm_i915_error_state *error)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
 
-	if (IS_GEN3(dev) || IS_GEN2(dev)) {
+	if (IS_GEN3(dev_priv) || IS_GEN2(dev_priv)) {
 		for (i = 0; i < dev_priv->num_fence_regs; i++)
 			error->fence[i] = I915_READ(FENCE_REG(i));
-	} else if (IS_GEN5(dev) || IS_GEN4(dev)) {
+	} else if (IS_GEN5(dev_priv) || IS_GEN4(dev_priv)) {
 		for (i = 0; i < dev_priv->num_fence_regs; i++)
 			error->fence[i] = I915_READ64(FENCE_REG_965_LO(i));
-	} else if (INTEL_INFO(dev)->gen >= 6) {
+	} else if (INTEL_GEN(dev_priv) >= 6) {
 		for (i = 0; i < dev_priv->num_fence_regs; i++)
 			error->fence[i] = I915_READ64(FENCE_REG_GEN6_LO(i));
 	}
@@ -851,7 +863,7 @@ static void gen8_record_semaphore_state(struct drm_i915_private *dev_priv,
 	struct intel_engine_cs *to;
 	enum intel_engine_id id;
 
-	if (!i915_semaphore_is_enabled(dev_priv->dev))
+	if (!i915_semaphore_is_enabled(dev_priv))
 		return;
 
 	if (!error->semaphore_obj)
@@ -893,31 +905,71 @@ static void gen6_record_semaphore_state(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void i915_record_ring_state(struct drm_device *dev,
+static void engine_record_waiters(struct intel_engine_cs *engine,
+				  struct drm_i915_error_ring *ering)
+{
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	struct drm_i915_error_waiter *waiter;
+	struct rb_node *rb;
+	int count;
+
+	ering->num_waiters = 0;
+	ering->waiters = NULL;
+
+	spin_lock(&b->lock);
+	count = 0;
+	for (rb = rb_first(&b->waiters); rb != NULL; rb = rb_next(rb))
+		count++;
+	spin_unlock(&b->lock);
+
+	waiter = NULL;
+	if (count)
+		waiter = kmalloc_array(count,
+				       sizeof(struct drm_i915_error_waiter),
+				       GFP_ATOMIC);
+	if (!waiter)
+		return;
+
+	ering->waiters = waiter;
+
+	spin_lock(&b->lock);
+	for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
+		struct intel_wait *w = container_of(rb, typeof(*w), node);
+
+		strcpy(waiter->comm, w->tsk->comm);
+		waiter->pid = w->tsk->pid;
+		waiter->seqno = w->seqno;
+		waiter++;
+
+		if (++ering->num_waiters == count)
+			break;
+	}
+	spin_unlock(&b->lock);
+}
+
+static void i915_record_ring_state(struct drm_i915_private *dev_priv,
 				   struct drm_i915_error_state *error,
 				   struct intel_engine_cs *engine,
 				   struct drm_i915_error_ring *ering)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (INTEL_INFO(dev)->gen >= 6) {
+	if (INTEL_GEN(dev_priv) >= 6) {
 		ering->rc_psmi = I915_READ(RING_PSMI_CTL(engine->mmio_base));
 		ering->fault_reg = I915_READ(RING_FAULT_REG(engine));
-		if (INTEL_INFO(dev)->gen >= 8)
+		if (INTEL_GEN(dev_priv) >= 8)
 			gen8_record_semaphore_state(dev_priv, error, engine,
 						    ering);
 		else
 			gen6_record_semaphore_state(dev_priv, engine, ering);
 	}
 
-	if (INTEL_INFO(dev)->gen >= 4) {
+	if (INTEL_GEN(dev_priv) >= 4) {
 		ering->faddr = I915_READ(RING_DMA_FADD(engine->mmio_base));
 		ering->ipeir = I915_READ(RING_IPEIR(engine->mmio_base));
 		ering->ipehr = I915_READ(RING_IPEHR(engine->mmio_base));
 		ering->instdone = I915_READ(RING_INSTDONE(engine->mmio_base));
 		ering->instps = I915_READ(RING_INSTPS(engine->mmio_base));
 		ering->bbaddr = I915_READ(RING_BBADDR(engine->mmio_base));
-		if (INTEL_INFO(dev)->gen >= 8) {
+		if (INTEL_GEN(dev_priv) >= 8) {
 			ering->faddr |= (u64) I915_READ(RING_DMA_FADD_UDW(engine->mmio_base)) << 32;
 			ering->bbaddr |= (u64) I915_READ(RING_BBADDR_UDW(engine->mmio_base)) << 32;
 		}
@@ -929,20 +981,20 @@ static void i915_record_ring_state(struct drm_device *dev,
 		ering->instdone = I915_READ(GEN2_INSTDONE);
 	}
 
-	ering->waiting = waitqueue_active(&engine->irq_queue);
+	ering->waiting = intel_engine_has_waiter(engine);
 	ering->instpm = I915_READ(RING_INSTPM(engine->mmio_base));
 	ering->acthd = intel_ring_get_active_head(engine);
-	ering->seqno = engine->get_seqno(engine);
+	ering->seqno = intel_engine_get_seqno(engine);
 	ering->last_seqno = engine->last_submitted_seqno;
 	ering->start = I915_READ_START(engine);
 	ering->head = I915_READ_HEAD(engine);
 	ering->tail = I915_READ_TAIL(engine);
 	ering->ctl = I915_READ_CTL(engine);
 
-	if (I915_NEED_GFX_HWS(dev)) {
+	if (I915_NEED_GFX_HWS(dev_priv)) {
 		i915_reg_t mmio;
 
-		if (IS_GEN7(dev)) {
+		if (IS_GEN7(dev_priv)) {
 			switch (engine->id) {
 			default:
 			case RCS:
@@ -958,7 +1010,7 @@ static void i915_record_ring_state(struct drm_device *dev,
 				mmio = VEBOX_HWS_PGA_GEN7;
 				break;
 			}
-		} else if (IS_GEN6(engine->dev)) {
+		} else if (IS_GEN6(engine->i915)) {
 			mmio = RING_HWS_PGA_GEN6(engine->mmio_base);
 		} else {
 			/* XXX: gen8 returns to sanity */
@@ -971,18 +1023,18 @@ static void i915_record_ring_state(struct drm_device *dev,
 	ering->hangcheck_score = engine->hangcheck.score;
 	ering->hangcheck_action = engine->hangcheck.action;
 
-	if (USES_PPGTT(dev)) {
+	if (USES_PPGTT(dev_priv)) {
 		int i;
 
 		ering->vm_info.gfx_mode = I915_READ(RING_MODE_GEN7(engine));
 
-		if (IS_GEN6(dev))
+		if (IS_GEN6(dev_priv))
 			ering->vm_info.pp_dir_base =
 				I915_READ(RING_PP_DIR_BASE_READ(engine));
-		else if (IS_GEN7(dev))
+		else if (IS_GEN7(dev_priv))
 			ering->vm_info.pp_dir_base =
 				I915_READ(RING_PP_DIR_BASE(engine));
-		else if (INTEL_INFO(dev)->gen >= 8)
+		else if (INTEL_GEN(dev_priv) >= 8)
 			for (i = 0; i < 4; i++) {
 				ering->vm_info.pdp[i] =
 					I915_READ(GEN8_RING_PDP_UDW(engine, i));
@@ -998,7 +1050,7 @@ static void i915_gem_record_active_context(struct intel_engine_cs *engine,
 					   struct drm_i915_error_state *error,
 					   struct drm_i915_error_ring *ering)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	struct drm_i915_gem_object *obj;
 
 	/* Currently render ring is the only HW context user */
@@ -1016,34 +1068,33 @@ static void i915_gem_record_active_context(struct intel_engine_cs *engine,
 	}
 }
 
-static void i915_gem_record_rings(struct drm_device *dev,
+static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 				  struct drm_i915_error_state *error)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	struct drm_i915_gem_request *request;
 	int i, count;
 
 	for (i = 0; i < I915_NUM_ENGINES; i++) {
 		struct intel_engine_cs *engine = &dev_priv->engine[i];
-		struct intel_ringbuffer *rbuf;
 
 		error->ring[i].pid = -1;
 
-		if (engine->dev == NULL)
+		if (!intel_engine_initialized(engine))
 			continue;
 
 		error->ring[i].valid = true;
 
-		i915_record_ring_state(dev, error, engine, &error->ring[i]);
+		i915_record_ring_state(dev_priv, error, engine, &error->ring[i]);
+		engine_record_waiters(engine, &error->ring[i]);
 
 		request = i915_gem_find_active_request(engine);
 		if (request) {
 			struct i915_address_space *vm;
+			struct intel_ringbuffer *rb;
 
-			vm = request->ctx && request->ctx->ppgtt ?
-				&request->ctx->ppgtt->base :
-				&ggtt->base;
+			vm = request->ctx->ppgtt ?
+				&request->ctx->ppgtt->base : &ggtt->base;
 
 			/* We need to copy these to an anonymous buffer
 			 * as the simplest method to avoid being overwritten
@@ -1070,26 +1121,17 @@ static void i915_gem_record_rings(struct drm_device *dev,
 				}
 				rcu_read_unlock();
 			}
-		}
 
-		if (i915.enable_execlists) {
-			/* TODO: This is only a small fix to keep basic error
-			 * capture working, but we need to add more information
-			 * for it to be useful (e.g. dump the context being
-			 * executed).
-			 */
-			if (request)
-				rbuf = request->ctx->engine[engine->id].ringbuf;
-			else
-				rbuf = dev_priv->kernel_context->engine[engine->id].ringbuf;
-		} else
-			rbuf = engine->buffer;
-
-		error->ring[i].cpu_ring_head = rbuf->head;
-		error->ring[i].cpu_ring_tail = rbuf->tail;
+			error->simulated |=
+				request->ctx->flags & CONTEXT_NO_ERROR_CAPTURE;
 
-		error->ring[i].ringbuffer =
-			i915_error_ggtt_object_create(dev_priv, rbuf->obj);
+			rb = request->ringbuf;
+			error->ring[i].cpu_ring_head = rb->head;
+			error->ring[i].cpu_ring_tail = rb->tail;
+			error->ring[i].ringbuffer =
+				i915_error_ggtt_object_create(dev_priv,
+							      rb->obj);
+		}
 
 		error->ring[i].hws_page =
 			i915_error_ggtt_object_create(dev_priv,
@@ -1234,7 +1276,7 @@ static void i915_gem_capture_buffers(struct drm_i915_private *dev_priv,
 static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 				   struct drm_i915_error_state *error)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	int i;
 
 	/* General organization
@@ -1301,15 +1343,14 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 	error->eir = I915_READ(EIR);
 	error->pgtbl_er = I915_READ(PGTBL_ER);
 
-	i915_get_extra_instdone(dev, error->extra_instdone);
+	i915_get_extra_instdone(dev_priv, error->extra_instdone);
 }
 
-static void i915_error_capture_msg(struct drm_device *dev,
+static void i915_error_capture_msg(struct drm_i915_private *dev_priv,
 				   struct drm_i915_error_state *error,
 				   u32 engine_mask,
 				   const char *error_msg)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 ecode;
 	int ring_id = -1, len;
 
@@ -1317,7 +1358,7 @@ static void i915_error_capture_msg(struct drm_device *dev,
 
 	len = scnprintf(error->error_msg, sizeof(error->error_msg),
 			"GPU HANG: ecode %d:%d:0x%08x",
-			INTEL_INFO(dev)->gen, ring_id, ecode);
+			INTEL_GEN(dev_priv), ring_id, ecode);
 
 	if (ring_id != -1 && error->ring[ring_id].pid != -1)
 		len += scnprintf(error->error_msg + len,
@@ -1352,14 +1393,17 @@ static void i915_capture_gen_state(struct drm_i915_private *dev_priv,
  * out a structure which becomes available in debugfs for user level tools
  * to pick up.
  */
-void i915_capture_error_state(struct drm_device *dev, u32 engine_mask,
+void i915_capture_error_state(struct drm_i915_private *dev_priv,
+			      u32 engine_mask,
 			      const char *error_msg)
 {
 	static bool warned;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_error_state *error;
 	unsigned long flags;
 
+	if (READ_ONCE(dev_priv->gpu_error.first_error))
+		return;
+
 	/* Account for pipe specific data like PIPE*STAT */
 	error = kzalloc(sizeof(*error), GFP_ATOMIC);
 	if (!error) {
@@ -1372,23 +1416,25 @@ void i915_capture_error_state(struct drm_device *dev, u32 engine_mask,
 	i915_capture_gen_state(dev_priv, error);
 	i915_capture_reg_state(dev_priv, error);
 	i915_gem_capture_buffers(dev_priv, error);
-	i915_gem_record_fences(dev, error);
-	i915_gem_record_rings(dev, error);
+	i915_gem_record_fences(dev_priv, error);
+	i915_gem_record_rings(dev_priv, error);
 
 	do_gettimeofday(&error->time);
 
-	error->overlay = intel_overlay_capture_error_state(dev);
-	error->display = intel_display_capture_error_state(dev);
+	error->overlay = intel_overlay_capture_error_state(dev_priv);
+	error->display = intel_display_capture_error_state(dev_priv);
 
-	i915_error_capture_msg(dev, error, engine_mask, error_msg);
+	i915_error_capture_msg(dev_priv, error, engine_mask, error_msg);
 	DRM_INFO("%s\n", error->error_msg);
 
-	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
-	if (dev_priv->gpu_error.first_error == NULL) {
-		dev_priv->gpu_error.first_error = error;
-		error = NULL;
+	if (!error->simulated) {
+		spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
+		if (!dev_priv->gpu_error.first_error) {
+			dev_priv->gpu_error.first_error = error;
+			error = NULL;
+		}
+		spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
 	}
-	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
 
 	if (error) {
 		i915_error_state_free(&error->ref);
@@ -1400,7 +1446,8 @@ void i915_capture_error_state(struct drm_device *dev, u32 engine_mask,
 		DRM_INFO("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n");
 		DRM_INFO("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n");
 		DRM_INFO("The gpu crash dump is required to analyze gpu hangs, so please always attach it.\n");
-		DRM_INFO("GPU crash dump saved to /sys/class/drm/card%d/error\n", dev->primary->index);
+		DRM_INFO("GPU crash dump saved to /sys/class/drm/card%d/error\n",
+			 dev_priv->drm.primary->index);
 		warned = true;
 	}
 }
@@ -1408,7 +1455,7 @@ void i915_capture_error_state(struct drm_device *dev, u32 engine_mask,
 void i915_error_state_get(struct drm_device *dev,
 			  struct i915_error_state_file_priv *error_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	spin_lock_irq(&dev_priv->gpu_error.lock);
 	error_priv->error = dev_priv->gpu_error.first_error;
@@ -1426,7 +1473,7 @@ void i915_error_state_put(struct i915_error_state_file_priv *error_priv)
 
 void i915_destroy_error_state(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_error_state *error;
 
 	spin_lock_irq(&dev_priv->gpu_error.lock);
@@ -1450,17 +1497,17 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 }
 
 /* NB: please notice the memset */
-void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone)
+void i915_get_extra_instdone(struct drm_i915_private *dev_priv,
+			     uint32_t *instdone)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	memset(instdone, 0, sizeof(*instdone) * I915_NUM_INSTDONE_REG);
 
-	if (IS_GEN2(dev) || IS_GEN3(dev))
+	if (IS_GEN2(dev_priv) || IS_GEN3(dev_priv))
 		instdone[0] = I915_READ(GEN2_INSTDONE);
-	else if (IS_GEN4(dev) || IS_GEN5(dev) || IS_GEN6(dev)) {
+	else if (IS_GEN4(dev_priv) || IS_GEN5(dev_priv) || IS_GEN6(dev_priv)) {
 		instdone[0] = I915_READ(RING_INSTDONE(RENDER_RING_BASE));
 		instdone[1] = I915_READ(GEN4_INSTDONE1);
-	} else if (INTEL_INFO(dev)->gen >= 7) {
+	} else if (INTEL_GEN(dev_priv) >= 7) {
 		instdone[0] = I915_READ(RING_INSTDONE(RENDER_RING_BASE));
 		instdone[1] = I915_READ(GEN7_SC_INSTDONE);
 		instdone[2] = I915_READ(GEN7_SAMPLER_INSTDONE);
diff --git a/drivers/gpu/drm/i915/i915_guc_reg.h b/drivers/gpu/drm/i915/i915_guc_reg.h
index 80786d9f9ad3..cf5a65be4fe0 100644
--- a/drivers/gpu/drm/i915/i915_guc_reg.h
+++ b/drivers/gpu/drm/i915/i915_guc_reg.h
@@ -67,11 +67,11 @@
 #define   GUC_WOPCM_OFFSET_VALUE	  0x80000	/* 512KB */
 #define GUC_MAX_IDLE_COUNT		_MMIO(0xC3E4)
 
+/* Defines WOPCM space available to GuC firmware */
 #define GUC_WOPCM_SIZE			_MMIO(0xc050)
-#define   GUC_WOPCM_SIZE_VALUE  	  (0x80 << 12)	/* 512KB */
-
 /* GuC addresses below GUC_WOPCM_TOP don't map through the GTT */
-#define	GUC_WOPCM_TOP			(GUC_WOPCM_SIZE_VALUE)
+#define   GUC_WOPCM_TOP			  (0x80 << 12)	/* 512KB */
+#define   BXT_GUC_WOPCM_RC6_RESERVED	  (0x10 << 12)	/* 64KB  */
 
 #define GEN8_GT_PM_CONFIG		_MMIO(0x138140)
 #define GEN9LP_GT_PM_CONFIG		_MMIO(0x138140)
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index d40c13fb6643..2112e029db6a 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -97,8 +97,14 @@ static int host2guc_action(struct intel_guc *guc, u32 *data, u32 len)
 
 	I915_WRITE(HOST2GUC_INTERRUPT, HOST2GUC_TRIGGER);
 
-	/* No HOST2GUC command should take longer than 10ms */
-	ret = wait_for_atomic(host2guc_action_response(dev_priv, &status), 10);
+	/*
+	 * Fast commands should complete in less than 10us, so sample quickly
+	 * up to that length of time, then switch to a slower sleep-wait loop.
+	 * No HOST2GUC command should ever take longer than 10ms.
+	 */
+	ret = wait_for_us(host2guc_action_response(dev_priv, &status), 10);
+	if (ret)
+		ret = wait_for(host2guc_action_response(dev_priv, &status), 10);
 	if (status != GUC2HOST_STATUS_SUCCESS) {
 		/*
 		 * Either the GuC explicitly returned an error (which
@@ -153,13 +159,11 @@ static int host2guc_sample_forcewake(struct intel_guc *guc,
 				     struct i915_guc_client *client)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	struct drm_device *dev = dev_priv->dev;
 	u32 data[2];
 
 	data[0] = HOST2GUC_ACTION_SAMPLE_FORCEWAKE;
 	/* WaRsDisableCoarsePowerGating:skl,bxt */
-	if (!intel_enable_rc6(dev) ||
-	    NEEDS_WaRsDisableCoarsePowerGating(dev))
+	if (!intel_enable_rc6() || NEEDS_WaRsDisableCoarsePowerGating(dev_priv))
 		data[1] = 0;
 	else
 		/* bit 0 and 1 are for Render and Media domain separately */
@@ -175,94 +179,88 @@ static int host2guc_sample_forcewake(struct intel_guc *guc,
  * client object which contains the page being used for the doorbell
  */
 
-static void guc_init_doorbell(struct intel_guc *guc,
-			      struct i915_guc_client *client)
+static int guc_update_doorbell_id(struct intel_guc *guc,
+				  struct i915_guc_client *client,
+				  u16 new_id)
 {
+	struct sg_table *sg = guc->ctx_pool_obj->pages;
+	void *doorbell_bitmap = guc->doorbell_bitmap;
 	struct guc_doorbell_info *doorbell;
+	struct guc_context_desc desc;
+	size_t len;
 
 	doorbell = client->client_base + client->doorbell_offset;
 
-	doorbell->db_status = GUC_DOORBELL_ENABLED;
-	doorbell->cookie = 0;
-}
-
-static int guc_ring_doorbell(struct i915_guc_client *gc)
-{
-	struct guc_process_desc *desc;
-	union guc_doorbell_qw db_cmp, db_exc, db_ret;
-	union guc_doorbell_qw *db;
-	int attempt = 2, ret = -EAGAIN;
-
-	desc = gc->client_base + gc->proc_desc_offset;
-
-	/* Update the tail so it is visible to GuC */
-	desc->tail = gc->wq_tail;
-
-	/* current cookie */
-	db_cmp.db_status = GUC_DOORBELL_ENABLED;
-	db_cmp.cookie = gc->cookie;
-
-	/* cookie to be updated */
-	db_exc.db_status = GUC_DOORBELL_ENABLED;
-	db_exc.cookie = gc->cookie + 1;
-	if (db_exc.cookie == 0)
-		db_exc.cookie = 1;
-
-	/* pointer of current doorbell cacheline */
-	db = gc->client_base + gc->doorbell_offset;
-
-	while (attempt--) {
-		/* lets ring the doorbell */
-		db_ret.value_qw = atomic64_cmpxchg((atomic64_t *)db,
-			db_cmp.value_qw, db_exc.value_qw);
-
-		/* if the exchange was successfully executed */
-		if (db_ret.value_qw == db_cmp.value_qw) {
-			/* db was successfully rung */
-			gc->cookie = db_exc.cookie;
-			ret = 0;
-			break;
-		}
+	if (client->doorbell_id != GUC_INVALID_DOORBELL_ID &&
+	    test_bit(client->doorbell_id, doorbell_bitmap)) {
+		/* Deactivate the old doorbell */
+		doorbell->db_status = GUC_DOORBELL_DISABLED;
+		(void)host2guc_release_doorbell(guc, client);
+		__clear_bit(client->doorbell_id, doorbell_bitmap);
+	}
 
-		/* XXX: doorbell was lost and need to acquire it again */
-		if (db_ret.db_status == GUC_DOORBELL_DISABLED)
-			break;
+	/* Update the GuC's idea of the doorbell ID */
+	len = sg_pcopy_to_buffer(sg->sgl, sg->nents, &desc, sizeof(desc),
+			     sizeof(desc) * client->ctx_index);
+	if (len != sizeof(desc))
+		return -EFAULT;
+	desc.db_id = new_id;
+	len = sg_pcopy_from_buffer(sg->sgl, sg->nents, &desc, sizeof(desc),
+			     sizeof(desc) * client->ctx_index);
+	if (len != sizeof(desc))
+		return -EFAULT;
 
-		DRM_ERROR("Cookie mismatch. Expected %d, returned %d\n",
-			  db_cmp.cookie, db_ret.cookie);
+	client->doorbell_id = new_id;
+	if (new_id == GUC_INVALID_DOORBELL_ID)
+		return 0;
 
-		/* update the cookie to newly read cookie from GuC */
-		db_cmp.cookie = db_ret.cookie;
-		db_exc.cookie = db_ret.cookie + 1;
-		if (db_exc.cookie == 0)
-			db_exc.cookie = 1;
-	}
+	/* Activate the new doorbell */
+	__set_bit(new_id, doorbell_bitmap);
+	doorbell->cookie = 0;
+	doorbell->db_status = GUC_DOORBELL_ENABLED;
+	return host2guc_allocate_doorbell(guc, client);
+}
 
-	return ret;
+static int guc_init_doorbell(struct intel_guc *guc,
+			      struct i915_guc_client *client,
+			      uint16_t db_id)
+{
+	return guc_update_doorbell_id(guc, client, db_id);
 }
 
 static void guc_disable_doorbell(struct intel_guc *guc,
 				 struct i915_guc_client *client)
 {
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	struct guc_doorbell_info *doorbell;
-	i915_reg_t drbreg = GEN8_DRBREGL(client->doorbell_id);
-	int value;
-
-	doorbell = client->client_base + client->doorbell_offset;
+	(void)guc_update_doorbell_id(guc, client, GUC_INVALID_DOORBELL_ID);
 
-	doorbell->db_status = GUC_DOORBELL_DISABLED;
+	/* XXX: wait for any interrupts */
+	/* XXX: wait for workqueue to drain */
+}
 
-	I915_WRITE(drbreg, I915_READ(drbreg) & ~GEN8_DRB_VALID);
+static uint16_t
+select_doorbell_register(struct intel_guc *guc, uint32_t priority)
+{
+	/*
+	 * The bitmap tracks which doorbell registers are currently in use.
+	 * It is split into two halves; the first half is used for normal
+	 * priority contexts, the second half for high-priority ones.
+	 * Note that logically higher priorities are numerically less than
+	 * normal ones, so the test below means "is it high-priority?"
+	 */
+	const bool hi_pri = (priority <= GUC_CTX_PRIORITY_HIGH);
+	const uint16_t half = GUC_MAX_DOORBELLS / 2;
+	const uint16_t start = hi_pri ? half : 0;
+	const uint16_t end = start + half;
+	uint16_t id;
 
-	value = I915_READ(drbreg);
-	WARN_ON((value & GEN8_DRB_VALID) != 0);
+	id = find_next_zero_bit(guc->doorbell_bitmap, end, start);
+	if (id == end)
+		id = GUC_INVALID_DOORBELL_ID;
 
-	I915_WRITE(GEN8_DRBREGU(client->doorbell_id), 0);
-	I915_WRITE(drbreg, 0);
+	DRM_DEBUG_DRIVER("assigned %s priority doorbell id 0x%x\n",
+			hi_pri ? "high" : "normal", id);
 
-	/* XXX: wait for any interrupts */
-	/* XXX: wait for workqueue to drain */
+	return id;
 }
 
 /*
@@ -289,37 +287,6 @@ static uint32_t select_doorbell_cacheline(struct intel_guc *guc)
 	return offset;
 }
 
-static uint16_t assign_doorbell(struct intel_guc *guc, uint32_t priority)
-{
-	/*
-	 * The bitmap is split into two halves; the first half is used for
-	 * normal priority contexts, the second half for high-priority ones.
-	 * Note that logically higher priorities are numerically less than
-	 * normal ones, so the test below means "is it high-priority?"
-	 */
-	const bool hi_pri = (priority <= GUC_CTX_PRIORITY_HIGH);
-	const uint16_t half = GUC_MAX_DOORBELLS / 2;
-	const uint16_t start = hi_pri ? half : 0;
-	const uint16_t end = start + half;
-	uint16_t id;
-
-	id = find_next_zero_bit(guc->doorbell_bitmap, end, start);
-	if (id == end)
-		id = GUC_INVALID_DOORBELL_ID;
-	else
-		bitmap_set(guc->doorbell_bitmap, id, 1);
-
-	DRM_DEBUG_DRIVER("assigned %s priority doorbell id 0x%x\n",
-			hi_pri ? "high" : "normal", id);
-
-	return id;
-}
-
-static void release_doorbell(struct intel_guc *guc, uint16_t id)
-{
-	bitmap_clear(guc->doorbell_bitmap, id, 1);
-}
-
 /*
  * Initialise the process descriptor shared with the GuC firmware.
  */
@@ -361,10 +328,9 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 	struct drm_i915_gem_object *client_obj = client->client_obj;
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	struct intel_engine_cs *engine;
-	struct intel_context *ctx = client->owner;
+	struct i915_gem_context *ctx = client->owner;
 	struct guc_context_desc desc;
 	struct sg_table *sg;
-	enum intel_engine_id id;
 	u32 gfx_addr;
 
 	memset(&desc, 0, sizeof(desc));
@@ -374,10 +340,10 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 	desc.priority = client->priority;
 	desc.db_id = client->doorbell_id;
 
-	for_each_engine_id(engine, dev_priv, id) {
+	for_each_engine(engine, dev_priv) {
+		struct intel_context *ce = &ctx->engine[engine->id];
 		struct guc_execlist_context *lrc = &desc.lrc[engine->guc_id];
 		struct drm_i915_gem_object *obj;
-		uint64_t ctx_desc;
 
 		/* TODO: We have a design issue to be solved here. Only when we
 		 * receive the first batch, we know which engine is used by the
@@ -386,20 +352,18 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 		 * for now who owns a GuC client. But for future owner of GuC
 		 * client, need to make sure lrc is pinned prior to enter here.
 		 */
-		obj = ctx->engine[id].state;
-		if (!obj)
+		if (!ce->state)
 			break;	/* XXX: continue? */
 
-		ctx_desc = intel_lr_context_descriptor(ctx, engine);
-		lrc->context_desc = (u32)ctx_desc;
+		lrc->context_desc = lower_32_bits(ce->lrc_desc);
 
 		/* The state page is after PPHWSP */
-		gfx_addr = i915_gem_obj_ggtt_offset(obj);
+		gfx_addr = i915_gem_obj_ggtt_offset(ce->state);
 		lrc->ring_lcra = gfx_addr + LRC_STATE_PN * PAGE_SIZE;
 		lrc->context_id = (client->ctx_index << GUC_ELC_CTXID_OFFSET) |
 				(engine->guc_id << GUC_ELC_ENGINE_OFFSET);
 
-		obj = ctx->engine[id].ringbuf->obj;
+		obj = ce->ringbuf->obj;
 		gfx_addr = i915_gem_obj_ggtt_offset(obj);
 
 		lrc->ring_begin = gfx_addr;
@@ -427,7 +391,7 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 	desc.wq_size = client->wq_size;
 
 	/*
-	 * XXX: Take LRCs from an existing intel_context if this is not an
+	 * XXX: Take LRCs from an existing context if this is not an
 	 * IsKMDCreatedContext client
 	 */
 	desc.desc_private = (uintptr_t)client;
@@ -451,47 +415,64 @@ static void guc_fini_ctx_desc(struct intel_guc *guc,
 			     sizeof(desc) * client->ctx_index);
 }
 
-int i915_guc_wq_check_space(struct i915_guc_client *gc)
+/**
+ * i915_guc_wq_check_space() - check that the GuC can accept a request
+ * @request:	request associated with the commands
+ *
+ * Return:	0 if space is available
+ *		-EAGAIN if space is not currently available
+ *
+ * This function must be called (and must return 0) before a request
+ * is submitted to the GuC via i915_guc_submit() below. Once a result
+ * of 0 has been returned, it remains valid until (but only until)
+ * the next call to submit().
+ *
+ * This precheck allows the caller to determine in advance that space
+ * will be available for the next submission before committing resources
+ * to it, and helps avoid late failures with complicated recovery paths.
+ */
+int i915_guc_wq_check_space(struct drm_i915_gem_request *request)
 {
+	const size_t wqi_size = sizeof(struct guc_wq_item);
+	struct i915_guc_client *gc = request->i915->guc.execbuf_client;
 	struct guc_process_desc *desc;
-	u32 size = sizeof(struct guc_wq_item);
-	int ret = -ETIMEDOUT, timeout_counter = 200;
+	u32 freespace;
 
-	if (!gc)
-		return 0;
+	GEM_BUG_ON(gc == NULL);
 
 	desc = gc->client_base + gc->proc_desc_offset;
 
-	while (timeout_counter-- > 0) {
-		if (CIRC_SPACE(gc->wq_tail, desc->head, gc->wq_size) >= size) {
-			ret = 0;
-			break;
-		}
+	freespace = CIRC_SPACE(gc->wq_tail, desc->head, gc->wq_size);
+	if (likely(freespace >= wqi_size))
+		return 0;
 
-		if (timeout_counter)
-			usleep_range(1000, 2000);
-	};
+	gc->no_wq_space += 1;
 
-	return ret;
+	return -EAGAIN;
 }
 
-static int guc_add_workqueue_item(struct i915_guc_client *gc,
-				  struct drm_i915_gem_request *rq)
+static void guc_add_workqueue_item(struct i915_guc_client *gc,
+				   struct drm_i915_gem_request *rq)
 {
+	/* wqi_len is in DWords, and does not include the one-word header */
+	const size_t wqi_size = sizeof(struct guc_wq_item);
+	const u32 wqi_len = wqi_size/sizeof(u32) - 1;
 	struct guc_process_desc *desc;
 	struct guc_wq_item *wqi;
 	void *base;
-	u32 tail, wq_len, wq_off, space;
+	u32 freespace, tail, wq_off, wq_page;
 
 	desc = gc->client_base + gc->proc_desc_offset;
-	space = CIRC_SPACE(gc->wq_tail, desc->head, gc->wq_size);
-	if (WARN_ON(space < sizeof(struct guc_wq_item)))
-		return -ENOSPC; /* shouldn't happen */
 
-	/* postincrement WQ tail for next time */
-	wq_off = gc->wq_tail;
-	gc->wq_tail += sizeof(struct guc_wq_item);
-	gc->wq_tail &= gc->wq_size - 1;
+	/* Free space is guaranteed, see i915_guc_wq_check_space() above */
+	freespace = CIRC_SPACE(gc->wq_tail, desc->head, gc->wq_size);
+	GEM_BUG_ON(freespace < wqi_size);
+
+	/* The GuC firmware wants the tail index in QWords, not bytes */
+	tail = rq->tail;
+	GEM_BUG_ON(tail & 7);
+	tail >>= 3;
+	GEM_BUG_ON(tail > WQ_RING_TAIL_MAX);
 
 	/* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we
 	 * should not have the case where structure wqi is across page, neither
@@ -500,19 +481,23 @@ static int guc_add_workqueue_item(struct i915_guc_client *gc,
 	 * XXX: if not the case, we need save data to a temp wqi and copy it to
 	 * workqueue buffer dw by dw.
 	 */
-	WARN_ON(sizeof(struct guc_wq_item) != 16);
-	WARN_ON(wq_off & 3);
+	BUILD_BUG_ON(wqi_size != 16);
+
+	/* postincrement WQ tail for next time */
+	wq_off = gc->wq_tail;
+	gc->wq_tail += wqi_size;
+	gc->wq_tail &= gc->wq_size - 1;
+	GEM_BUG_ON(wq_off & (wqi_size - 1));
 
-	/* wq starts from the page after doorbell / process_desc */
-	base = kmap_atomic(i915_gem_object_get_page(gc->client_obj,
-			(wq_off + GUC_DB_SIZE) >> PAGE_SHIFT));
+	/* WQ starts from the page after doorbell / process_desc */
+	wq_page = (wq_off + GUC_DB_SIZE) >> PAGE_SHIFT;
 	wq_off &= PAGE_SIZE - 1;
+	base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, wq_page));
 	wqi = (struct guc_wq_item *)((char *)base + wq_off);
 
-	/* len does not include the header */
-	wq_len = sizeof(struct guc_wq_item) / sizeof(u32) - 1;
+	/* Now fill in the 4-word work queue item */
 	wqi->header = WQ_TYPE_INORDER |
-			(wq_len << WQ_LEN_SHIFT) |
+			(wqi_len << WQ_LEN_SHIFT) |
 			(rq->engine->guc_id << WQ_TARGET_SHIFT) |
 			WQ_NO_WCFLUSH_WAIT;
 
@@ -520,48 +505,105 @@ static int guc_add_workqueue_item(struct i915_guc_client *gc,
 	wqi->context_desc = (u32)intel_lr_context_descriptor(rq->ctx,
 							     rq->engine);
 
-	/* The GuC firmware wants the tail index in QWords, not bytes */
-	tail = rq->ringbuf->tail >> 3;
 	wqi->ring_tail = tail << WQ_RING_TAIL_SHIFT;
-	wqi->fence_id = 0; /*XXX: what fence to be here */
+	wqi->fence_id = rq->seqno;
 
 	kunmap_atomic(base);
+}
 
-	return 0;
+static int guc_ring_doorbell(struct i915_guc_client *gc)
+{
+	struct guc_process_desc *desc;
+	union guc_doorbell_qw db_cmp, db_exc, db_ret;
+	union guc_doorbell_qw *db;
+	int attempt = 2, ret = -EAGAIN;
+
+	desc = gc->client_base + gc->proc_desc_offset;
+
+	/* Update the tail so it is visible to GuC */
+	desc->tail = gc->wq_tail;
+
+	/* current cookie */
+	db_cmp.db_status = GUC_DOORBELL_ENABLED;
+	db_cmp.cookie = gc->cookie;
+
+	/* cookie to be updated */
+	db_exc.db_status = GUC_DOORBELL_ENABLED;
+	db_exc.cookie = gc->cookie + 1;
+	if (db_exc.cookie == 0)
+		db_exc.cookie = 1;
+
+	/* pointer of current doorbell cacheline */
+	db = gc->client_base + gc->doorbell_offset;
+
+	while (attempt--) {
+		/* lets ring the doorbell */
+		db_ret.value_qw = atomic64_cmpxchg((atomic64_t *)db,
+			db_cmp.value_qw, db_exc.value_qw);
+
+		/* if the exchange was successfully executed */
+		if (db_ret.value_qw == db_cmp.value_qw) {
+			/* db was successfully rung */
+			gc->cookie = db_exc.cookie;
+			ret = 0;
+			break;
+		}
+
+		/* XXX: doorbell was lost and need to acquire it again */
+		if (db_ret.db_status == GUC_DOORBELL_DISABLED)
+			break;
+
+		DRM_ERROR("Cookie mismatch. Expected %d, returned %d\n",
+			  db_cmp.cookie, db_ret.cookie);
+
+		/* update the cookie to newly read cookie from GuC */
+		db_cmp.cookie = db_ret.cookie;
+		db_exc.cookie = db_ret.cookie + 1;
+		if (db_exc.cookie == 0)
+			db_exc.cookie = 1;
+	}
+
+	return ret;
 }
 
 /**
  * i915_guc_submit() - Submit commands through GuC
- * @client:	the guc client where commands will go through
  * @rq:		request associated with the commands
  *
- * Return:	0 if succeed
+ * Return:	0 on success, otherwise an errno.
+ * 		(Note: nonzero really shouldn't happen!)
+ *
+ * The caller must have already called i915_guc_wq_check_space() above
+ * with a result of 0 (success) since the last request submission. This
+ * guarantees that there is space in the work queue for the new request,
+ * so enqueuing the item cannot fail.
+ *
+ * Bad Things Will Happen if the caller violates this protocol e.g. calls
+ * submit() when check() says there's no space, or calls submit() multiple
+ * times with no intervening check().
+ *
+ * The only error here arises if the doorbell hardware isn't functioning
+ * as expected, which really shouln't happen.
  */
-int i915_guc_submit(struct i915_guc_client *client,
-		    struct drm_i915_gem_request *rq)
+int i915_guc_submit(struct drm_i915_gem_request *rq)
 {
-	struct intel_guc *guc = client->guc;
-	unsigned int engine_id = rq->engine->guc_id;
-	int q_ret, b_ret;
+	unsigned int engine_id = rq->engine->id;
+	struct intel_guc *guc = &rq->i915->guc;
+	struct i915_guc_client *client = guc->execbuf_client;
+	int b_ret;
 
-	q_ret = guc_add_workqueue_item(client, rq);
-	if (q_ret == 0)
-		b_ret = guc_ring_doorbell(client);
+	guc_add_workqueue_item(client, rq);
+	b_ret = guc_ring_doorbell(client);
 
 	client->submissions[engine_id] += 1;
-	if (q_ret) {
-		client->q_fail += 1;
-		client->retcode = q_ret;
-	} else if (b_ret) {
+	client->retcode = b_ret;
+	if (b_ret)
 		client->b_fail += 1;
-		client->retcode = q_ret = b_ret;
-	} else {
-		client->retcode = 0;
-	}
+
 	guc->submissions[engine_id] += 1;
 	guc->last_seqno[engine_id] = rq->seqno;
 
-	return q_ret;
+	return b_ret;
 }
 
 /*
@@ -572,7 +614,7 @@ int i915_guc_submit(struct i915_guc_client *client,
 
 /**
  * gem_allocate_guc_obj() - Allocate gem object for GuC usage
- * @dev:	drm device
+ * @dev_priv:	driver private data structure
  * @size:	size of object
  *
  * This is a wrapper to create a gem obj. In order to use it inside GuC, the
@@ -581,14 +623,13 @@ int i915_guc_submit(struct i915_guc_client *client,
  *
  * Return:	A drm_i915_gem_object if successful, otherwise NULL.
  */
-static struct drm_i915_gem_object *gem_allocate_guc_obj(struct drm_device *dev,
-							u32 size)
+static struct drm_i915_gem_object *
+gem_allocate_guc_obj(struct drm_i915_private *dev_priv, u32 size)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
 
-	obj = i915_gem_alloc_object(dev, size);
-	if (!obj)
+	obj = i915_gem_object_create(&dev_priv->drm, size);
+	if (IS_ERR(obj))
 		return NULL;
 
 	if (i915_gem_object_get_pages(obj)) {
@@ -623,10 +664,10 @@ static void gem_release_guc_obj(struct drm_i915_gem_object *obj)
 	drm_gem_object_unreference(&obj->base);
 }
 
-static void guc_client_free(struct drm_device *dev,
-			    struct i915_guc_client *client)
+static void
+guc_client_free(struct drm_i915_private *dev_priv,
+		struct i915_guc_client *client)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_guc *guc = &dev_priv->guc;
 
 	if (!client)
@@ -639,17 +680,10 @@ static void guc_client_free(struct drm_device *dev,
 
 	if (client->client_base) {
 		/*
-		 * If we got as far as setting up a doorbell, make sure
-		 * we shut it down before unmapping & deallocating the
-		 * memory. So first disable the doorbell, then tell the
-		 * GuC that we've finished with it, finally deallocate
-		 * it in our bitmap
+		 * If we got as far as setting up a doorbell, make sure we
+		 * shut it down before unmapping & deallocating the memory.
 		 */
-		if (client->doorbell_id != GUC_INVALID_DOORBELL_ID) {
-			guc_disable_doorbell(guc, client);
-			host2guc_release_doorbell(guc, client);
-			release_doorbell(guc, client->doorbell_id);
-		}
+		guc_disable_doorbell(guc, client);
 
 		kunmap(kmap_to_page(client->client_base));
 	}
@@ -664,9 +698,51 @@ static void guc_client_free(struct drm_device *dev,
 	kfree(client);
 }
 
+/*
+ * Borrow the first client to set up & tear down every doorbell
+ * in turn, to ensure that all doorbell h/w is (re)initialised.
+ */
+static void guc_init_doorbell_hw(struct intel_guc *guc)
+{
+	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	struct i915_guc_client *client = guc->execbuf_client;
+	uint16_t db_id, i;
+	int err;
+
+	db_id = client->doorbell_id;
+
+	for (i = 0; i < GUC_MAX_DOORBELLS; ++i) {
+		i915_reg_t drbreg = GEN8_DRBREGL(i);
+		u32 value = I915_READ(drbreg);
+
+		err = guc_update_doorbell_id(guc, client, i);
+
+		/* Report update failure or unexpectedly active doorbell */
+		if (err || (i != db_id && (value & GUC_DOORBELL_ENABLED)))
+			DRM_DEBUG_DRIVER("Doorbell %d (reg 0x%x) was 0x%x, err %d\n",
+					  i, drbreg.reg, value, err);
+	}
+
+	/* Restore to original value */
+	err = guc_update_doorbell_id(guc, client, db_id);
+	if (err)
+		DRM_ERROR("Failed to restore doorbell to %d, err %d\n",
+			db_id, err);
+
+	for (i = 0; i < GUC_MAX_DOORBELLS; ++i) {
+		i915_reg_t drbreg = GEN8_DRBREGL(i);
+		u32 value = I915_READ(drbreg);
+
+		if (i != db_id && (value & GUC_DOORBELL_ENABLED))
+			DRM_DEBUG_DRIVER("Doorbell %d (reg 0x%x) finally 0x%x\n",
+					  i, drbreg.reg, value);
+
+	}
+}
+
 /**
  * guc_client_alloc() - Allocate an i915_guc_client
- * @dev:	drm device
+ * @dev_priv:	driver private data structure
  * @priority:	four levels priority _CRITICAL, _HIGH, _NORMAL and _LOW
  * 		The kernel client to replace ExecList submission is created with
  * 		NORMAL priority. Priority of a client for scheduler can be HIGH,
@@ -676,14 +752,15 @@ static void guc_client_free(struct drm_device *dev,
  *
  * Return:	An i915_guc_client object if success, else NULL.
  */
-static struct i915_guc_client *guc_client_alloc(struct drm_device *dev,
-						uint32_t priority,
-						struct intel_context *ctx)
+static struct i915_guc_client *
+guc_client_alloc(struct drm_i915_private *dev_priv,
+		 uint32_t priority,
+		 struct i915_gem_context *ctx)
 {
 	struct i915_guc_client *client;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_guc *guc = &dev_priv->guc;
 	struct drm_i915_gem_object *obj;
+	uint16_t db_id;
 
 	client = kzalloc(sizeof(*client), GFP_KERNEL);
 	if (!client)
@@ -702,7 +779,7 @@ static struct i915_guc_client *guc_client_alloc(struct drm_device *dev,
 	}
 
 	/* The first page is doorbell/proc_desc. Two followed pages are wq. */
-	obj = gem_allocate_guc_obj(dev, GUC_DB_SIZE + GUC_WQ_SIZE);
+	obj = gem_allocate_guc_obj(dev_priv, GUC_DB_SIZE + GUC_WQ_SIZE);
 	if (!obj)
 		goto err;
 
@@ -712,6 +789,11 @@ static struct i915_guc_client *guc_client_alloc(struct drm_device *dev,
 	client->wq_offset = GUC_DB_SIZE;
 	client->wq_size = GUC_WQ_SIZE;
 
+	db_id = select_doorbell_register(guc, client->priority);
+	if (db_id == GUC_INVALID_DOORBELL_ID)
+		/* XXX: evict a doorbell instead? */
+		goto err;
+
 	client->doorbell_offset = select_doorbell_cacheline(guc);
 
 	/*
@@ -724,29 +806,22 @@ static struct i915_guc_client *guc_client_alloc(struct drm_device *dev,
 	else
 		client->proc_desc_offset = (GUC_DB_SIZE / 2);
 
-	client->doorbell_id = assign_doorbell(guc, client->priority);
-	if (client->doorbell_id == GUC_INVALID_DOORBELL_ID)
-		/* XXX: evict a doorbell instead */
-		goto err;
-
 	guc_init_proc_desc(guc, client);
 	guc_init_ctx_desc(guc, client);
-	guc_init_doorbell(guc, client);
-
-	/* XXX: Any cache flushes needed? General domain mgmt calls? */
-
-	if (host2guc_allocate_doorbell(guc, client))
+	if (guc_init_doorbell(guc, client, db_id))
 		goto err;
 
-	DRM_DEBUG_DRIVER("new priority %u client %p: ctx_index %u db_id %u\n",
-		priority, client, client->ctx_index, client->doorbell_id);
+	DRM_DEBUG_DRIVER("new priority %u client %p: ctx_index %u\n",
+		priority, client, client->ctx_index);
+	DRM_DEBUG_DRIVER("doorbell id %u, cacheline offset 0x%x\n",
+		client->doorbell_id, client->doorbell_offset);
 
 	return client;
 
 err:
 	DRM_ERROR("FAILED to create priority %u GuC client!\n", priority);
 
-	guc_client_free(dev, client);
+	guc_client_free(dev_priv, client);
 	return NULL;
 }
 
@@ -771,7 +846,7 @@ static void guc_create_log(struct intel_guc *guc)
 
 	obj = guc->log_obj;
 	if (!obj) {
-		obj = gem_allocate_guc_obj(dev_priv->dev, size);
+		obj = gem_allocate_guc_obj(dev_priv, size);
 		if (!obj) {
 			/* logging will be off */
 			i915.guc_log_level = -1;
@@ -831,7 +906,7 @@ static void guc_create_ads(struct intel_guc *guc)
 
 	obj = guc->ads_obj;
 	if (!obj) {
-		obj = gem_allocate_guc_obj(dev_priv->dev, PAGE_ALIGN(size));
+		obj = gem_allocate_guc_obj(dev_priv, PAGE_ALIGN(size));
 		if (!obj)
 			return;
 
@@ -885,66 +960,65 @@ static void guc_create_ads(struct intel_guc *guc)
  * Set up the memory resources to be shared with the GuC.  At this point,
  * we require just one object that can be mapped through the GGTT.
  */
-int i915_guc_submission_init(struct drm_device *dev)
+int i915_guc_submission_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	const size_t ctxsize = sizeof(struct guc_context_desc);
 	const size_t poolsize = GUC_MAX_GPU_CONTEXTS * ctxsize;
 	const size_t gemsize = round_up(poolsize, PAGE_SIZE);
 	struct intel_guc *guc = &dev_priv->guc;
 
+	/* Wipe bitmap & delete client in case of reinitialisation */
+	bitmap_clear(guc->doorbell_bitmap, 0, GUC_MAX_DOORBELLS);
+	i915_guc_submission_disable(dev_priv);
+
 	if (!i915.enable_guc_submission)
 		return 0; /* not enabled  */
 
 	if (guc->ctx_pool_obj)
 		return 0; /* already allocated */
 
-	guc->ctx_pool_obj = gem_allocate_guc_obj(dev_priv->dev, gemsize);
+	guc->ctx_pool_obj = gem_allocate_guc_obj(dev_priv, gemsize);
 	if (!guc->ctx_pool_obj)
 		return -ENOMEM;
 
 	ida_init(&guc->ctx_ids);
-
 	guc_create_log(guc);
-
 	guc_create_ads(guc);
 
 	return 0;
 }
 
-int i915_guc_submission_enable(struct drm_device *dev)
+int i915_guc_submission_enable(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_guc *guc = &dev_priv->guc;
-	struct intel_context *ctx = dev_priv->kernel_context;
 	struct i915_guc_client *client;
 
 	/* client for execbuf submission */
-	client = guc_client_alloc(dev, GUC_CTX_PRIORITY_KMD_NORMAL, ctx);
+	client = guc_client_alloc(dev_priv,
+				  GUC_CTX_PRIORITY_KMD_NORMAL,
+				  dev_priv->kernel_context);
 	if (!client) {
 		DRM_ERROR("Failed to create execbuf guc_client\n");
 		return -ENOMEM;
 	}
 
 	guc->execbuf_client = client;
-
 	host2guc_sample_forcewake(guc, client);
+	guc_init_doorbell_hw(guc);
 
 	return 0;
 }
 
-void i915_guc_submission_disable(struct drm_device *dev)
+void i915_guc_submission_disable(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_guc *guc = &dev_priv->guc;
 
-	guc_client_free(dev, guc->execbuf_client);
+	guc_client_free(dev_priv, guc->execbuf_client);
 	guc->execbuf_client = NULL;
 }
 
-void i915_guc_submission_fini(struct drm_device *dev)
+void i915_guc_submission_fini(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_guc *guc = &dev_priv->guc;
 
 	gem_release_guc_obj(dev_priv->guc.ads_obj);
@@ -965,12 +1039,12 @@ void i915_guc_submission_fini(struct drm_device *dev)
  */
 int intel_guc_suspend(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_guc *guc = &dev_priv->guc;
-	struct intel_context *ctx;
+	struct i915_gem_context *ctx;
 	u32 data[3];
 
-	if (!i915.enable_guc_submission)
+	if (guc->guc_fw.guc_fw_load_status != GUC_FIRMWARE_SUCCESS)
 		return 0;
 
 	ctx = dev_priv->kernel_context;
@@ -991,12 +1065,12 @@ int intel_guc_suspend(struct drm_device *dev)
  */
 int intel_guc_resume(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_guc *guc = &dev_priv->guc;
-	struct intel_context *ctx;
+	struct i915_gem_context *ctx;
 	u32 data[3];
 
-	if (!i915.enable_guc_submission)
+	if (guc->guc_fw.guc_fw_load_status != GUC_FIRMWARE_SUCCESS)
 		return 0;
 
 	ctx = dev_priv->kernel_context;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index aab47f7bb61b..1c2aec392412 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -259,12 +259,12 @@ static void ilk_update_gt_irq(struct drm_i915_private *dev_priv,
 	dev_priv->gt_irq_mask &= ~interrupt_mask;
 	dev_priv->gt_irq_mask |= (~enabled_irq_mask & interrupt_mask);
 	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-	POSTING_READ(GTIMR);
 }
 
 void gen5_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask)
 {
 	ilk_update_gt_irq(dev_priv, mask, mask);
+	POSTING_READ_FW(GTIMR);
 }
 
 void gen5_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask)
@@ -336,9 +336,8 @@ void gen6_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
 	__gen6_disable_pm_irq(dev_priv, mask);
 }
 
-void gen6_reset_rps_interrupts(struct drm_device *dev)
+void gen6_reset_rps_interrupts(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	i915_reg_t reg = gen6_pm_iir(dev_priv);
 
 	spin_lock_irq(&dev_priv->irq_lock);
@@ -349,14 +348,11 @@ void gen6_reset_rps_interrupts(struct drm_device *dev)
 	spin_unlock_irq(&dev_priv->irq_lock);
 }
 
-void gen6_enable_rps_interrupts(struct drm_device *dev)
+void gen6_enable_rps_interrupts(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	spin_lock_irq(&dev_priv->irq_lock);
-
-	WARN_ON(dev_priv->rps.pm_iir);
-	WARN_ON(I915_READ(gen6_pm_iir(dev_priv)) & dev_priv->pm_rps_events);
+	WARN_ON_ONCE(dev_priv->rps.pm_iir);
+	WARN_ON_ONCE(I915_READ(gen6_pm_iir(dev_priv)) & dev_priv->pm_rps_events);
 	dev_priv->rps.interrupts_enabled = true;
 	I915_WRITE(gen6_pm_ier(dev_priv), I915_READ(gen6_pm_ier(dev_priv)) |
 				dev_priv->pm_rps_events);
@@ -367,32 +363,13 @@ void gen6_enable_rps_interrupts(struct drm_device *dev)
 
 u32 gen6_sanitize_rps_pm_mask(struct drm_i915_private *dev_priv, u32 mask)
 {
-	/*
-	 * SNB,IVB can while VLV,CHV may hard hang on looping batchbuffer
-	 * if GEN6_PM_UP_EI_EXPIRED is masked.
-	 *
-	 * TODO: verify if this can be reproduced on VLV,CHV.
-	 */
-	if (INTEL_INFO(dev_priv)->gen <= 7 && !IS_HASWELL(dev_priv))
-		mask &= ~GEN6_PM_RP_UP_EI_EXPIRED;
-
-	if (INTEL_INFO(dev_priv)->gen >= 8)
-		mask &= ~GEN8_PMINTR_REDIRECT_TO_NON_DISP;
-
-	return mask;
+	return (mask & ~dev_priv->rps.pm_intr_keep);
 }
 
-void gen6_disable_rps_interrupts(struct drm_device *dev)
+void gen6_disable_rps_interrupts(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	spin_lock_irq(&dev_priv->irq_lock);
 	dev_priv->rps.interrupts_enabled = false;
-	spin_unlock_irq(&dev_priv->irq_lock);
-
-	cancel_work_sync(&dev_priv->rps.work);
-
-	spin_lock_irq(&dev_priv->irq_lock);
 
 	I915_WRITE(GEN6_PMINTRMSK, gen6_sanitize_rps_pm_mask(dev_priv, ~0));
 
@@ -401,8 +378,15 @@ void gen6_disable_rps_interrupts(struct drm_device *dev)
 				~dev_priv->pm_rps_events);
 
 	spin_unlock_irq(&dev_priv->irq_lock);
+	synchronize_irq(dev_priv->drm.irq);
 
-	synchronize_irq(dev->irq);
+	/* Now that we will not be generating any more work, flush any
+	 * outsanding tasks. As we are called on the RPS idle path,
+	 * we will reset the GPU to minimum frequencies, so the current
+	 * state of the worker can be discarded.
+	 */
+	cancel_work_sync(&dev_priv->rps.work);
+	gen6_reset_rps_interrupts(dev_priv);
 }
 
 /**
@@ -582,7 +566,7 @@ i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
 	u32 enable_mask;
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		enable_mask = vlv_get_pipestat_enable_mask(dev_priv->dev,
+		enable_mask = vlv_get_pipestat_enable_mask(&dev_priv->drm,
 							   status_mask);
 	else
 		enable_mask = status_mask << 16;
@@ -596,7 +580,7 @@ i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
 	u32 enable_mask;
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		enable_mask = vlv_get_pipestat_enable_mask(dev_priv->dev,
+		enable_mask = vlv_get_pipestat_enable_mask(&dev_priv->drm,
 							   status_mask);
 	else
 		enable_mask = status_mask << 16;
@@ -605,19 +589,17 @@ i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
 
 /**
  * i915_enable_asle_pipestat - enable ASLE pipestat for OpRegion
- * @dev: drm device
+ * @dev_priv: i915 device private
  */
-static void i915_enable_asle_pipestat(struct drm_device *dev)
+static void i915_enable_asle_pipestat(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (!dev_priv->opregion.asle || !IS_MOBILE(dev))
+	if (!dev_priv->opregion.asle || !IS_MOBILE(dev_priv))
 		return;
 
 	spin_lock_irq(&dev_priv->irq_lock);
 
 	i915_enable_pipestat(dev_priv, PIPE_B, PIPE_LEGACY_BLC_EVENT_STATUS);
-	if (INTEL_INFO(dev)->gen >= 4)
+	if (INTEL_GEN(dev_priv) >= 4)
 		i915_enable_pipestat(dev_priv, PIPE_A,
 				     PIPE_LEGACY_BLC_EVENT_STATUS);
 
@@ -685,7 +667,7 @@ static u32 i8xx_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
  */
 static u32 i915_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t high_frame, low_frame;
 	u32 high1, high2, low, pixel, vbl_start, hsync_start, htotal;
 	struct intel_crtc *intel_crtc =
@@ -732,7 +714,7 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 
 static u32 g4x_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	return I915_READ(PIPE_FRMCOUNT_G4X(pipe));
 }
@@ -741,7 +723,7 @@ static u32 g4x_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 static int __intel_get_crtc_scanline(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	const struct drm_display_mode *mode = &crtc->base.hwmode;
 	enum pipe pipe = crtc->pipe;
 	int position, vtotal;
@@ -750,7 +732,7 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc)
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
 		vtotal /= 2;
 
-	if (IS_GEN2(dev))
+	if (IS_GEN2(dev_priv))
 		position = I915_READ_FW(PIPEDSL(pipe)) & DSL_LINEMASK_GEN2;
 	else
 		position = I915_READ_FW(PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
@@ -767,7 +749,7 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc)
 	 * problem.  We may need to extend this to include other platforms,
 	 * but so far testing only shows the problem on HSW.
 	 */
-	if (HAS_DDI(dev) && !position) {
+	if (HAS_DDI(dev_priv) && !position) {
 		int i, temp;
 
 		for (i = 0; i < 100; i++) {
@@ -793,7 +775,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 				    ktime_t *stime, ktime_t *etime,
 				    const struct drm_display_mode *mode)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int position;
@@ -835,7 +817,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 	if (stime)
 		*stime = ktime_get();
 
-	if (IS_GEN2(dev) || IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5) {
+	if (IS_GEN2(dev_priv) || IS_G4X(dev_priv) || INTEL_GEN(dev_priv) >= 5) {
 		/* No obvious pixelcount register. Only query vertical
 		 * scanout position from Display scan line register.
 		 */
@@ -897,7 +879,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 	else
 		position += vtotal - vbl_end;
 
-	if (IS_GEN2(dev) || IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5) {
+	if (IS_GEN2(dev_priv) || IS_G4X(dev_priv) || INTEL_GEN(dev_priv) >= 5) {
 		*vpos = position;
 		*hpos = 0;
 	} else {
@@ -914,7 +896,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 
 int intel_get_crtc_scanline(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	unsigned long irqflags;
 	int position;
 
@@ -955,9 +937,8 @@ static int i915_get_vblank_timestamp(struct drm_device *dev, unsigned int pipe,
 						     &crtc->hwmode);
 }
 
-static void ironlake_rps_change_irq_handler(struct drm_device *dev)
+static void ironlake_rps_change_irq_handler(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 busy_up, busy_down, max_avg, min_avg;
 	u8 new_delay;
 
@@ -986,7 +967,7 @@ static void ironlake_rps_change_irq_handler(struct drm_device *dev)
 			new_delay = dev_priv->ips.min_delay;
 	}
 
-	if (ironlake_set_drps(dev, new_delay))
+	if (ironlake_set_drps(dev_priv, new_delay))
 		dev_priv->ips.cur_delay = new_delay;
 
 	spin_unlock(&mchdev_lock);
@@ -996,13 +977,11 @@ static void ironlake_rps_change_irq_handler(struct drm_device *dev)
 
 static void notify_ring(struct intel_engine_cs *engine)
 {
-	if (!intel_engine_initialized(engine))
-		return;
-
-	trace_i915_gem_request_notify(engine);
-	engine->user_interrupts++;
-
-	wake_up_all(&engine->irq_queue);
+	smp_store_mb(engine->breadcrumbs.irq_posted, true);
+	if (intel_engine_wakeup(engine)) {
+		trace_i915_gem_request_notify(engine);
+		engine->breadcrumbs.irq_wakeups++;
+	}
 }
 
 static void vlv_c0_read(struct drm_i915_private *dev_priv,
@@ -1083,7 +1062,7 @@ static bool any_waiters(struct drm_i915_private *dev_priv)
 	struct intel_engine_cs *engine;
 
 	for_each_engine(engine, dev_priv)
-		if (engine->irq_refcount)
+		if (intel_engine_has_waiter(engine))
 			return true;
 
 	return false;
@@ -1104,13 +1083,6 @@ static void gen6_pm_rps_work(struct work_struct *work)
 		return;
 	}
 
-	/*
-	 * The RPS work is synced during runtime suspend, we don't require a
-	 * wakeref. TODO: instead of disabling the asserts make sure that we
-	 * always hold an RPM reference while the work is running.
-	 */
-	DISABLE_RPM_WAKEREF_ASSERTS(dev_priv);
-
 	pm_iir = dev_priv->rps.pm_iir;
 	dev_priv->rps.pm_iir = 0;
 	/* Make sure not to corrupt PMIMR state used by ringbuffer on GEN6 */
@@ -1123,7 +1095,7 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	WARN_ON(pm_iir & ~dev_priv->pm_rps_events);
 
 	if ((pm_iir & dev_priv->pm_rps_events) == 0 && !client_boost)
-		goto out;
+		return;
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
@@ -1175,11 +1147,9 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	new_delay += adj;
 	new_delay = clamp_t(int, new_delay, min, max);
 
-	intel_set_rps(dev_priv->dev, new_delay);
+	intel_set_rps(dev_priv, new_delay);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
-out:
-	ENABLE_RPM_WAKEREF_ASSERTS(dev_priv);
 }
 
 
@@ -1205,7 +1175,7 @@ static void ivybridge_parity_work(struct work_struct *work)
 	 * In order to prevent a get/put style interface, acquire struct mutex
 	 * any time we access those registers.
 	 */
-	mutex_lock(&dev_priv->dev->struct_mutex);
+	mutex_lock(&dev_priv->drm.struct_mutex);
 
 	/* If we've screwed up tracking, just let the interrupt fire again */
 	if (WARN_ON(!dev_priv->l3_parity.which_slice))
@@ -1241,7 +1211,7 @@ static void ivybridge_parity_work(struct work_struct *work)
 		parity_event[4] = kasprintf(GFP_KERNEL, "SLICE=%d", slice);
 		parity_event[5] = NULL;
 
-		kobject_uevent_env(&dev_priv->dev->primary->kdev->kobj,
+		kobject_uevent_env(&dev_priv->drm.primary->kdev->kobj,
 				   KOBJ_CHANGE, parity_event);
 
 		DRM_DEBUG("Parity error: Slice = %d, Row = %d, Bank = %d, Sub bank = %d.\n",
@@ -1261,7 +1231,7 @@ out:
 	gen5_enable_gt_irq(dev_priv, GT_PARITY_ERROR(dev_priv));
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	mutex_unlock(&dev_priv->dev->struct_mutex);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
 }
 
 static void ivybridge_parity_error_irq_handler(struct drm_i915_private *dev_priv,
@@ -1287,8 +1257,7 @@ static void ivybridge_parity_error_irq_handler(struct drm_i915_private *dev_priv
 static void ilk_gt_irq_handler(struct drm_i915_private *dev_priv,
 			       u32 gt_iir)
 {
-	if (gt_iir &
-	    (GT_RENDER_USER_INTERRUPT | GT_RENDER_PIPECTL_NOTIFY_INTERRUPT))
+	if (gt_iir & GT_RENDER_USER_INTERRUPT)
 		notify_ring(&dev_priv->engine[RCS]);
 	if (gt_iir & ILK_BSD_USER_INTERRUPT)
 		notify_ring(&dev_priv->engine[VCS]);
@@ -1297,9 +1266,7 @@ static void ilk_gt_irq_handler(struct drm_i915_private *dev_priv,
 static void snb_gt_irq_handler(struct drm_i915_private *dev_priv,
 			       u32 gt_iir)
 {
-
-	if (gt_iir &
-	    (GT_RENDER_USER_INTERRUPT | GT_RENDER_PIPECTL_NOTIFY_INTERRUPT))
+	if (gt_iir & GT_RENDER_USER_INTERRUPT)
 		notify_ring(&dev_priv->engine[RCS]);
 	if (gt_iir & GT_BSD_USER_INTERRUPT)
 		notify_ring(&dev_priv->engine[VCS]);
@@ -1506,27 +1473,23 @@ static void intel_get_hpd_pins(u32 *pin_mask, u32 *long_mask,
 
 }
 
-static void gmbus_irq_handler(struct drm_device *dev)
+static void gmbus_irq_handler(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	wake_up_all(&dev_priv->gmbus_wait_queue);
 }
 
-static void dp_aux_irq_handler(struct drm_device *dev)
+static void dp_aux_irq_handler(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	wake_up_all(&dev_priv->gmbus_wait_queue);
 }
 
 #if defined(CONFIG_DEBUG_FS)
-static void display_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe,
+static void display_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
+					 enum pipe pipe,
 					 uint32_t crc0, uint32_t crc1,
 					 uint32_t crc2, uint32_t crc3,
 					 uint32_t crc4)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
 	struct intel_pipe_crc_entry *entry;
 	int head, tail;
@@ -1550,7 +1513,8 @@ static void display_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe,
 
 	entry = &pipe_crc->entries[head];
 
-	entry->frame = dev->driver->get_vblank_counter(dev, pipe);
+	entry->frame = dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm,
+								 pipe);
 	entry->crc[0] = crc0;
 	entry->crc[1] = crc1;
 	entry->crc[2] = crc2;
@@ -1566,27 +1530,26 @@ static void display_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe,
 }
 #else
 static inline void
-display_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe,
+display_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
+			     enum pipe pipe,
 			     uint32_t crc0, uint32_t crc1,
 			     uint32_t crc2, uint32_t crc3,
 			     uint32_t crc4) {}
 #endif
 
 
-static void hsw_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe)
+static void hsw_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
+				     enum pipe pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	display_pipe_crc_irq_handler(dev, pipe,
+	display_pipe_crc_irq_handler(dev_priv, pipe,
 				     I915_READ(PIPE_CRC_RES_1_IVB(pipe)),
 				     0, 0, 0, 0);
 }
 
-static void ivb_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe)
+static void ivb_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
+				     enum pipe pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	display_pipe_crc_irq_handler(dev, pipe,
+	display_pipe_crc_irq_handler(dev_priv, pipe,
 				     I915_READ(PIPE_CRC_RES_1_IVB(pipe)),
 				     I915_READ(PIPE_CRC_RES_2_IVB(pipe)),
 				     I915_READ(PIPE_CRC_RES_3_IVB(pipe)),
@@ -1594,22 +1557,22 @@ static void ivb_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe)
 				     I915_READ(PIPE_CRC_RES_5_IVB(pipe)));
 }
 
-static void i9xx_pipe_crc_irq_handler(struct drm_device *dev, enum pipe pipe)
+static void i9xx_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
+				      enum pipe pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t res1, res2;
 
-	if (INTEL_INFO(dev)->gen >= 3)
+	if (INTEL_GEN(dev_priv) >= 3)
 		res1 = I915_READ(PIPE_CRC_RES_RES1_I915(pipe));
 	else
 		res1 = 0;
 
-	if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev))
+	if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
 		res2 = I915_READ(PIPE_CRC_RES_RES2_G4X(pipe));
 	else
 		res2 = 0;
 
-	display_pipe_crc_irq_handler(dev, pipe,
+	display_pipe_crc_irq_handler(dev_priv, pipe,
 				     I915_READ(PIPE_CRC_RES_RED(pipe)),
 				     I915_READ(PIPE_CRC_RES_GREEN(pipe)),
 				     I915_READ(PIPE_CRC_RES_BLUE(pipe)),
@@ -1626,7 +1589,7 @@ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
 		gen6_disable_pm_irq(dev_priv, pm_iir & dev_priv->pm_rps_events);
 		if (dev_priv->rps.interrupts_enabled) {
 			dev_priv->rps.pm_iir |= pm_iir & dev_priv->pm_rps_events;
-			queue_work(dev_priv->wq, &dev_priv->rps.work);
+			schedule_work(&dev_priv->rps.work);
 		}
 		spin_unlock(&dev_priv->irq_lock);
 	}
@@ -1643,18 +1606,21 @@ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
 	}
 }
 
-static bool intel_pipe_handle_vblank(struct drm_device *dev, enum pipe pipe)
+static bool intel_pipe_handle_vblank(struct drm_i915_private *dev_priv,
+				     enum pipe pipe)
 {
-	if (!drm_handle_vblank(dev, pipe))
-		return false;
+	bool ret;
 
-	return true;
+	ret = drm_handle_vblank(&dev_priv->drm, pipe);
+	if (ret)
+		intel_finish_page_flip_mmio(dev_priv, pipe);
+
+	return ret;
 }
 
-static void valleyview_pipestat_irq_ack(struct drm_device *dev, u32 iir,
-					u32 pipe_stats[I915_MAX_PIPES])
+static void valleyview_pipestat_irq_ack(struct drm_i915_private *dev_priv,
+					u32 iir, u32 pipe_stats[I915_MAX_PIPES])
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe;
 
 	spin_lock(&dev_priv->irq_lock);
@@ -1710,31 +1676,28 @@ static void valleyview_pipestat_irq_ack(struct drm_device *dev, u32 iir,
 	spin_unlock(&dev_priv->irq_lock);
 }
 
-static void valleyview_pipestat_irq_handler(struct drm_device *dev,
+static void valleyview_pipestat_irq_handler(struct drm_i915_private *dev_priv,
 					    u32 pipe_stats[I915_MAX_PIPES])
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe;
 
 	for_each_pipe(dev_priv, pipe) {
 		if (pipe_stats[pipe] & PIPE_START_VBLANK_INTERRUPT_STATUS &&
-		    intel_pipe_handle_vblank(dev, pipe))
-			intel_check_page_flip(dev, pipe);
+		    intel_pipe_handle_vblank(dev_priv, pipe))
+			intel_check_page_flip(dev_priv, pipe);
 
-		if (pipe_stats[pipe] & PLANE_FLIP_DONE_INT_STATUS_VLV) {
-			intel_prepare_page_flip(dev, pipe);
-			intel_finish_page_flip(dev, pipe);
-		}
+		if (pipe_stats[pipe] & PLANE_FLIP_DONE_INT_STATUS_VLV)
+			intel_finish_page_flip_cs(dev_priv, pipe);
 
 		if (pipe_stats[pipe] & PIPE_CRC_DONE_INTERRUPT_STATUS)
-			i9xx_pipe_crc_irq_handler(dev, pipe);
+			i9xx_pipe_crc_irq_handler(dev_priv, pipe);
 
 		if (pipe_stats[pipe] & PIPE_FIFO_UNDERRUN_STATUS)
 			intel_cpu_fifo_underrun_irq_handler(dev_priv, pipe);
 	}
 
 	if (pipe_stats[0] & PIPE_GMBUS_INTERRUPT_STATUS)
-		gmbus_irq_handler(dev);
+		gmbus_irq_handler(dev_priv);
 }
 
 static u32 i9xx_hpd_irq_ack(struct drm_i915_private *dev_priv)
@@ -1747,12 +1710,13 @@ static u32 i9xx_hpd_irq_ack(struct drm_i915_private *dev_priv)
 	return hotplug_status;
 }
 
-static void i9xx_hpd_irq_handler(struct drm_device *dev,
+static void i9xx_hpd_irq_handler(struct drm_i915_private *dev_priv,
 				 u32 hotplug_status)
 {
 	u32 pin_mask = 0, long_mask = 0;
 
-	if (IS_G4X(dev) || IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
+	if (IS_G4X(dev_priv) || IS_VALLEYVIEW(dev_priv) ||
+	    IS_CHERRYVIEW(dev_priv)) {
 		u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X;
 
 		if (hotplug_trigger) {
@@ -1760,11 +1724,11 @@ static void i9xx_hpd_irq_handler(struct drm_device *dev,
 					   hotplug_trigger, hpd_status_g4x,
 					   i9xx_port_hotplug_long_detect);
 
-			intel_hpd_irq_handler(dev, pin_mask, long_mask);
+			intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
 		}
 
 		if (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
-			dp_aux_irq_handler(dev);
+			dp_aux_irq_handler(dev_priv);
 	} else {
 		u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
 
@@ -1772,7 +1736,7 @@ static void i9xx_hpd_irq_handler(struct drm_device *dev,
 			intel_get_hpd_pins(&pin_mask, &long_mask, hotplug_trigger,
 					   hotplug_trigger, hpd_status_i915,
 					   i9xx_port_hotplug_long_detect);
-			intel_hpd_irq_handler(dev, pin_mask, long_mask);
+			intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
 		}
 	}
 }
@@ -1780,7 +1744,7 @@ static void i9xx_hpd_irq_handler(struct drm_device *dev,
 static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	irqreturn_t ret = IRQ_NONE;
 
 	if (!intel_irqs_enabled(dev_priv))
@@ -1831,7 +1795,7 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 
 		/* Call regardless, as some status bits might not be
 		 * signalled in iir */
-		valleyview_pipestat_irq_ack(dev, iir, pipe_stats);
+		valleyview_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
 		/*
 		 * VLV_IIR is single buffered, and reflects the level
@@ -1850,9 +1814,9 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 			gen6_rps_irq_handler(dev_priv, pm_iir);
 
 		if (hotplug_status)
-			i9xx_hpd_irq_handler(dev, hotplug_status);
+			i9xx_hpd_irq_handler(dev_priv, hotplug_status);
 
-		valleyview_pipestat_irq_handler(dev, pipe_stats);
+		valleyview_pipestat_irq_handler(dev_priv, pipe_stats);
 	} while (0);
 
 	enable_rpm_wakeref_asserts(dev_priv);
@@ -1863,7 +1827,7 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	irqreturn_t ret = IRQ_NONE;
 
 	if (!intel_irqs_enabled(dev_priv))
@@ -1911,7 +1875,7 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 
 		/* Call regardless, as some status bits might not be
 		 * signalled in iir */
-		valleyview_pipestat_irq_ack(dev, iir, pipe_stats);
+		valleyview_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
 		/*
 		 * VLV_IIR is single buffered, and reflects the level
@@ -1927,9 +1891,9 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 		gen8_gt_irq_handler(dev_priv, gt_iir);
 
 		if (hotplug_status)
-			i9xx_hpd_irq_handler(dev, hotplug_status);
+			i9xx_hpd_irq_handler(dev_priv, hotplug_status);
 
-		valleyview_pipestat_irq_handler(dev, pipe_stats);
+		valleyview_pipestat_irq_handler(dev_priv, pipe_stats);
 	} while (0);
 
 	enable_rpm_wakeref_asserts(dev_priv);
@@ -1937,10 +1901,10 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 	return ret;
 }
 
-static void ibx_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger,
+static void ibx_hpd_irq_handler(struct drm_i915_private *dev_priv,
+				u32 hotplug_trigger,
 				const u32 hpd[HPD_NUM_PINS])
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
 
 	/*
@@ -1966,16 +1930,15 @@ static void ibx_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger,
 			   dig_hotplug_reg, hpd,
 			   pch_port_hotplug_long_detect);
 
-	intel_hpd_irq_handler(dev, pin_mask, long_mask);
+	intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
 }
 
-static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir)
+static void ibx_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe;
 	u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK;
 
-	ibx_hpd_irq_handler(dev, hotplug_trigger, hpd_ibx);
+	ibx_hpd_irq_handler(dev_priv, hotplug_trigger, hpd_ibx);
 
 	if (pch_iir & SDE_AUDIO_POWER_MASK) {
 		int port = ffs((pch_iir & SDE_AUDIO_POWER_MASK) >>
@@ -1985,10 +1948,10 @@ static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir)
 	}
 
 	if (pch_iir & SDE_AUX_MASK)
-		dp_aux_irq_handler(dev);
+		dp_aux_irq_handler(dev_priv);
 
 	if (pch_iir & SDE_GMBUS)
-		gmbus_irq_handler(dev);
+		gmbus_irq_handler(dev_priv);
 
 	if (pch_iir & SDE_AUDIO_HDCP_MASK)
 		DRM_DEBUG_DRIVER("PCH HDCP audio interrupt\n");
@@ -2018,9 +1981,8 @@ static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir)
 		intel_pch_fifo_underrun_irq_handler(dev_priv, TRANSCODER_B);
 }
 
-static void ivb_err_int_handler(struct drm_device *dev)
+static void ivb_err_int_handler(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 err_int = I915_READ(GEN7_ERR_INT);
 	enum pipe pipe;
 
@@ -2032,19 +1994,18 @@ static void ivb_err_int_handler(struct drm_device *dev)
 			intel_cpu_fifo_underrun_irq_handler(dev_priv, pipe);
 
 		if (err_int & ERR_INT_PIPE_CRC_DONE(pipe)) {
-			if (IS_IVYBRIDGE(dev))
-				ivb_pipe_crc_irq_handler(dev, pipe);
+			if (IS_IVYBRIDGE(dev_priv))
+				ivb_pipe_crc_irq_handler(dev_priv, pipe);
 			else
-				hsw_pipe_crc_irq_handler(dev, pipe);
+				hsw_pipe_crc_irq_handler(dev_priv, pipe);
 		}
 	}
 
 	I915_WRITE(GEN7_ERR_INT, err_int);
 }
 
-static void cpt_serr_int_handler(struct drm_device *dev)
+static void cpt_serr_int_handler(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 serr_int = I915_READ(SERR_INT);
 
 	if (serr_int & SERR_INT_POISON)
@@ -2062,13 +2023,12 @@ static void cpt_serr_int_handler(struct drm_device *dev)
 	I915_WRITE(SERR_INT, serr_int);
 }
 
-static void cpt_irq_handler(struct drm_device *dev, u32 pch_iir)
+static void cpt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe;
 	u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_CPT;
 
-	ibx_hpd_irq_handler(dev, hotplug_trigger, hpd_cpt);
+	ibx_hpd_irq_handler(dev_priv, hotplug_trigger, hpd_cpt);
 
 	if (pch_iir & SDE_AUDIO_POWER_MASK_CPT) {
 		int port = ffs((pch_iir & SDE_AUDIO_POWER_MASK_CPT) >>
@@ -2078,10 +2038,10 @@ static void cpt_irq_handler(struct drm_device *dev, u32 pch_iir)
 	}
 
 	if (pch_iir & SDE_AUX_MASK_CPT)
-		dp_aux_irq_handler(dev);
+		dp_aux_irq_handler(dev_priv);
 
 	if (pch_iir & SDE_GMBUS_CPT)
-		gmbus_irq_handler(dev);
+		gmbus_irq_handler(dev_priv);
 
 	if (pch_iir & SDE_AUDIO_CP_REQ_CPT)
 		DRM_DEBUG_DRIVER("Audio CP request interrupt\n");
@@ -2096,12 +2056,11 @@ static void cpt_irq_handler(struct drm_device *dev, u32 pch_iir)
 					 I915_READ(FDI_RX_IIR(pipe)));
 
 	if (pch_iir & SDE_ERROR_CPT)
-		cpt_serr_int_handler(dev);
+		cpt_serr_int_handler(dev_priv);
 }
 
-static void spt_irq_handler(struct drm_device *dev, u32 pch_iir)
+static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_SPT &
 		~SDE_PORTE_HOTPLUG_SPT;
 	u32 hotplug2_trigger = pch_iir & SDE_PORTE_HOTPLUG_SPT;
@@ -2130,16 +2089,16 @@ static void spt_irq_handler(struct drm_device *dev, u32 pch_iir)
 	}
 
 	if (pin_mask)
-		intel_hpd_irq_handler(dev, pin_mask, long_mask);
+		intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
 
 	if (pch_iir & SDE_GMBUS_CPT)
-		gmbus_irq_handler(dev);
+		gmbus_irq_handler(dev_priv);
 }
 
-static void ilk_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger,
+static void ilk_hpd_irq_handler(struct drm_i915_private *dev_priv,
+				u32 hotplug_trigger,
 				const u32 hpd[HPD_NUM_PINS])
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
 
 	dig_hotplug_reg = I915_READ(DIGITAL_PORT_HOTPLUG_CNTRL);
@@ -2149,97 +2108,93 @@ static void ilk_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger,
 			   dig_hotplug_reg, hpd,
 			   ilk_port_hotplug_long_detect);
 
-	intel_hpd_irq_handler(dev, pin_mask, long_mask);
+	intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
 }
 
-static void ilk_display_irq_handler(struct drm_device *dev, u32 de_iir)
+static void ilk_display_irq_handler(struct drm_i915_private *dev_priv,
+				    u32 de_iir)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum pipe pipe;
 	u32 hotplug_trigger = de_iir & DE_DP_A_HOTPLUG;
 
 	if (hotplug_trigger)
-		ilk_hpd_irq_handler(dev, hotplug_trigger, hpd_ilk);
+		ilk_hpd_irq_handler(dev_priv, hotplug_trigger, hpd_ilk);
 
 	if (de_iir & DE_AUX_CHANNEL_A)
-		dp_aux_irq_handler(dev);
+		dp_aux_irq_handler(dev_priv);
 
 	if (de_iir & DE_GSE)
-		intel_opregion_asle_intr(dev);
+		intel_opregion_asle_intr(dev_priv);
 
 	if (de_iir & DE_POISON)
 		DRM_ERROR("Poison interrupt\n");
 
 	for_each_pipe(dev_priv, pipe) {
 		if (de_iir & DE_PIPE_VBLANK(pipe) &&
-		    intel_pipe_handle_vblank(dev, pipe))
-			intel_check_page_flip(dev, pipe);
+		    intel_pipe_handle_vblank(dev_priv, pipe))
+			intel_check_page_flip(dev_priv, pipe);
 
 		if (de_iir & DE_PIPE_FIFO_UNDERRUN(pipe))
 			intel_cpu_fifo_underrun_irq_handler(dev_priv, pipe);
 
 		if (de_iir & DE_PIPE_CRC_DONE(pipe))
-			i9xx_pipe_crc_irq_handler(dev, pipe);
+			i9xx_pipe_crc_irq_handler(dev_priv, pipe);
 
 		/* plane/pipes map 1:1 on ilk+ */
-		if (de_iir & DE_PLANE_FLIP_DONE(pipe)) {
-			intel_prepare_page_flip(dev, pipe);
-			intel_finish_page_flip_plane(dev, pipe);
-		}
+		if (de_iir & DE_PLANE_FLIP_DONE(pipe))
+			intel_finish_page_flip_cs(dev_priv, pipe);
 	}
 
 	/* check event from PCH */
 	if (de_iir & DE_PCH_EVENT) {
 		u32 pch_iir = I915_READ(SDEIIR);
 
-		if (HAS_PCH_CPT(dev))
-			cpt_irq_handler(dev, pch_iir);
+		if (HAS_PCH_CPT(dev_priv))
+			cpt_irq_handler(dev_priv, pch_iir);
 		else
-			ibx_irq_handler(dev, pch_iir);
+			ibx_irq_handler(dev_priv, pch_iir);
 
 		/* should clear PCH hotplug event before clear CPU irq */
 		I915_WRITE(SDEIIR, pch_iir);
 	}
 
-	if (IS_GEN5(dev) && de_iir & DE_PCU_EVENT)
-		ironlake_rps_change_irq_handler(dev);
+	if (IS_GEN5(dev_priv) && de_iir & DE_PCU_EVENT)
+		ironlake_rps_change_irq_handler(dev_priv);
 }
 
-static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir)
+static void ivb_display_irq_handler(struct drm_i915_private *dev_priv,
+				    u32 de_iir)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum pipe pipe;
 	u32 hotplug_trigger = de_iir & DE_DP_A_HOTPLUG_IVB;
 
 	if (hotplug_trigger)
-		ilk_hpd_irq_handler(dev, hotplug_trigger, hpd_ivb);
+		ilk_hpd_irq_handler(dev_priv, hotplug_trigger, hpd_ivb);
 
 	if (de_iir & DE_ERR_INT_IVB)
-		ivb_err_int_handler(dev);
+		ivb_err_int_handler(dev_priv);
 
 	if (de_iir & DE_AUX_CHANNEL_A_IVB)
-		dp_aux_irq_handler(dev);
+		dp_aux_irq_handler(dev_priv);
 
 	if (de_iir & DE_GSE_IVB)
-		intel_opregion_asle_intr(dev);
+		intel_opregion_asle_intr(dev_priv);
 
 	for_each_pipe(dev_priv, pipe) {
 		if (de_iir & (DE_PIPE_VBLANK_IVB(pipe)) &&
-		    intel_pipe_handle_vblank(dev, pipe))
-			intel_check_page_flip(dev, pipe);
+		    intel_pipe_handle_vblank(dev_priv, pipe))
+			intel_check_page_flip(dev_priv, pipe);
 
 		/* plane/pipes map 1:1 on ilk+ */
-		if (de_iir & DE_PLANE_FLIP_DONE_IVB(pipe)) {
-			intel_prepare_page_flip(dev, pipe);
-			intel_finish_page_flip_plane(dev, pipe);
-		}
+		if (de_iir & DE_PLANE_FLIP_DONE_IVB(pipe))
+			intel_finish_page_flip_cs(dev_priv, pipe);
 	}
 
 	/* check event from PCH */
-	if (!HAS_PCH_NOP(dev) && (de_iir & DE_PCH_EVENT_IVB)) {
+	if (!HAS_PCH_NOP(dev_priv) && (de_iir & DE_PCH_EVENT_IVB)) {
 		u32 pch_iir = I915_READ(SDEIIR);
 
-		cpt_irq_handler(dev, pch_iir);
+		cpt_irq_handler(dev_priv, pch_iir);
 
 		/* clear PCH hotplug event before clear CPU irq */
 		I915_WRITE(SDEIIR, pch_iir);
@@ -2257,7 +2212,7 @@ static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir)
 static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 de_iir, gt_iir, de_ier, sde_ier = 0;
 	irqreturn_t ret = IRQ_NONE;
 
@@ -2277,7 +2232,7 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	 * able to process them after we restore SDEIER (as soon as we restore
 	 * it, we'll get an interrupt if SDEIIR still has something to process
 	 * due to its back queue). */
-	if (!HAS_PCH_NOP(dev)) {
+	if (!HAS_PCH_NOP(dev_priv)) {
 		sde_ier = I915_READ(SDEIER);
 		I915_WRITE(SDEIER, 0);
 		POSTING_READ(SDEIER);
@@ -2289,7 +2244,7 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	if (gt_iir) {
 		I915_WRITE(GTIIR, gt_iir);
 		ret = IRQ_HANDLED;
-		if (INTEL_INFO(dev)->gen >= 6)
+		if (INTEL_GEN(dev_priv) >= 6)
 			snb_gt_irq_handler(dev_priv, gt_iir);
 		else
 			ilk_gt_irq_handler(dev_priv, gt_iir);
@@ -2299,13 +2254,13 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	if (de_iir) {
 		I915_WRITE(DEIIR, de_iir);
 		ret = IRQ_HANDLED;
-		if (INTEL_INFO(dev)->gen >= 7)
-			ivb_display_irq_handler(dev, de_iir);
+		if (INTEL_GEN(dev_priv) >= 7)
+			ivb_display_irq_handler(dev_priv, de_iir);
 		else
-			ilk_display_irq_handler(dev, de_iir);
+			ilk_display_irq_handler(dev_priv, de_iir);
 	}
 
-	if (INTEL_INFO(dev)->gen >= 6) {
+	if (INTEL_GEN(dev_priv) >= 6) {
 		u32 pm_iir = I915_READ(GEN6_PMIIR);
 		if (pm_iir) {
 			I915_WRITE(GEN6_PMIIR, pm_iir);
@@ -2316,7 +2271,7 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 
 	I915_WRITE(DEIER, de_ier);
 	POSTING_READ(DEIER);
-	if (!HAS_PCH_NOP(dev)) {
+	if (!HAS_PCH_NOP(dev_priv)) {
 		I915_WRITE(SDEIER, sde_ier);
 		POSTING_READ(SDEIER);
 	}
@@ -2327,10 +2282,10 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	return ret;
 }
 
-static void bxt_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger,
+static void bxt_hpd_irq_handler(struct drm_i915_private *dev_priv,
+				u32 hotplug_trigger,
 				const u32 hpd[HPD_NUM_PINS])
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 dig_hotplug_reg, pin_mask = 0, long_mask = 0;
 
 	dig_hotplug_reg = I915_READ(PCH_PORT_HOTPLUG);
@@ -2340,13 +2295,12 @@ static void bxt_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger,
 			   dig_hotplug_reg, hpd,
 			   bxt_port_hotplug_long_detect);
 
-	intel_hpd_irq_handler(dev, pin_mask, long_mask);
+	intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
 }
 
 static irqreturn_t
 gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 {
-	struct drm_device *dev = dev_priv->dev;
 	irqreturn_t ret = IRQ_NONE;
 	u32 iir;
 	enum pipe pipe;
@@ -2357,7 +2311,7 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 			I915_WRITE(GEN8_DE_MISC_IIR, iir);
 			ret = IRQ_HANDLED;
 			if (iir & GEN8_DE_MISC_GSE)
-				intel_opregion_asle_intr(dev);
+				intel_opregion_asle_intr(dev_priv);
 			else
 				DRM_ERROR("Unexpected DE Misc interrupt\n");
 		}
@@ -2381,26 +2335,28 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 					    GEN9_AUX_CHANNEL_D;
 
 			if (iir & tmp_mask) {
-				dp_aux_irq_handler(dev);
+				dp_aux_irq_handler(dev_priv);
 				found = true;
 			}
 
 			if (IS_BROXTON(dev_priv)) {
 				tmp_mask = iir & BXT_DE_PORT_HOTPLUG_MASK;
 				if (tmp_mask) {
-					bxt_hpd_irq_handler(dev, tmp_mask, hpd_bxt);
+					bxt_hpd_irq_handler(dev_priv, tmp_mask,
+							    hpd_bxt);
 					found = true;
 				}
 			} else if (IS_BROADWELL(dev_priv)) {
 				tmp_mask = iir & GEN8_PORT_DP_A_HOTPLUG;
 				if (tmp_mask) {
-					ilk_hpd_irq_handler(dev, tmp_mask, hpd_bdw);
+					ilk_hpd_irq_handler(dev_priv,
+							    tmp_mask, hpd_bdw);
 					found = true;
 				}
 			}
 
-			if (IS_BROXTON(dev) && (iir & BXT_DE_PORT_GMBUS)) {
-				gmbus_irq_handler(dev);
+			if (IS_BROXTON(dev_priv) && (iir & BXT_DE_PORT_GMBUS)) {
+				gmbus_irq_handler(dev_priv);
 				found = true;
 			}
 
@@ -2427,8 +2383,8 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 		I915_WRITE(GEN8_DE_PIPE_IIR(pipe), iir);
 
 		if (iir & GEN8_PIPE_VBLANK &&
-		    intel_pipe_handle_vblank(dev, pipe))
-			intel_check_page_flip(dev, pipe);
+		    intel_pipe_handle_vblank(dev_priv, pipe))
+			intel_check_page_flip(dev_priv, pipe);
 
 		flip_done = iir;
 		if (INTEL_INFO(dev_priv)->gen >= 9)
@@ -2436,13 +2392,11 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 		else
 			flip_done &= GEN8_PIPE_PRIMARY_FLIP_DONE;
 
-		if (flip_done) {
-			intel_prepare_page_flip(dev, pipe);
-			intel_finish_page_flip_plane(dev, pipe);
-		}
+		if (flip_done)
+			intel_finish_page_flip_cs(dev_priv, pipe);
 
 		if (iir & GEN8_PIPE_CDCLK_CRC_DONE)
-			hsw_pipe_crc_irq_handler(dev, pipe);
+			hsw_pipe_crc_irq_handler(dev_priv, pipe);
 
 		if (iir & GEN8_PIPE_FIFO_UNDERRUN)
 			intel_cpu_fifo_underrun_irq_handler(dev_priv, pipe);
@@ -2459,7 +2413,7 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 				  fault_errors);
 	}
 
-	if (HAS_PCH_SPLIT(dev) && !HAS_PCH_NOP(dev) &&
+	if (HAS_PCH_SPLIT(dev_priv) && !HAS_PCH_NOP(dev_priv) &&
 	    master_ctl & GEN8_DE_PCH_IRQ) {
 		/*
 		 * FIXME(BDW): Assume for now that the new interrupt handling
@@ -2472,9 +2426,9 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 			ret = IRQ_HANDLED;
 
 			if (HAS_PCH_SPT(dev_priv) || HAS_PCH_KBP(dev_priv))
-				spt_irq_handler(dev, iir);
+				spt_irq_handler(dev_priv, iir);
 			else
-				cpt_irq_handler(dev, iir);
+				cpt_irq_handler(dev_priv, iir);
 		} else {
 			/*
 			 * Like on previous PCH there seems to be something
@@ -2490,7 +2444,7 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 static irqreturn_t gen8_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 master_ctl;
 	u32 gt_iir[4] = {};
 	irqreturn_t ret;
@@ -2521,11 +2475,8 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 	return ret;
 }
 
-static void i915_error_wake_up(struct drm_i915_private *dev_priv,
-			       bool reset_completed)
+static void i915_error_wake_up(struct drm_i915_private *dev_priv)
 {
-	struct intel_engine_cs *engine;
-
 	/*
 	 * Notify all waiters for GPU completion events that reset state has
 	 * been changed, and that they need to restart their wait after
@@ -2534,36 +2485,28 @@ static void i915_error_wake_up(struct drm_i915_private *dev_priv,
 	 */
 
 	/* Wake up __wait_seqno, potentially holding dev->struct_mutex. */
-	for_each_engine(engine, dev_priv)
-		wake_up_all(&engine->irq_queue);
+	wake_up_all(&dev_priv->gpu_error.wait_queue);
 
 	/* Wake up intel_crtc_wait_for_pending_flips, holding crtc->mutex. */
 	wake_up_all(&dev_priv->pending_flip_queue);
-
-	/*
-	 * Signal tasks blocked in i915_gem_wait_for_error that the pending
-	 * reset state is cleared.
-	 */
-	if (reset_completed)
-		wake_up_all(&dev_priv->gpu_error.reset_queue);
 }
 
 /**
  * i915_reset_and_wakeup - do process context error handling work
- * @dev: drm device
+ * @dev_priv: i915 device private
  *
  * Fire an error uevent so userspace can see that a hang or error
  * was detected.
  */
-static void i915_reset_and_wakeup(struct drm_device *dev)
+static void i915_reset_and_wakeup(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct kobject *kobj = &dev_priv->drm.primary->kdev->kobj;
 	char *error_event[] = { I915_ERROR_UEVENT "=1", NULL };
 	char *reset_event[] = { I915_RESET_UEVENT "=1", NULL };
 	char *reset_done_event[] = { I915_ERROR_UEVENT "=0", NULL };
 	int ret;
 
-	kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE, error_event);
+	kobject_uevent_env(kobj, KOBJ_CHANGE, error_event);
 
 	/*
 	 * Note that there's only one work item which does gpu resets, so we
@@ -2577,8 +2520,7 @@ static void i915_reset_and_wakeup(struct drm_device *dev)
 	 */
 	if (i915_reset_in_progress(&dev_priv->gpu_error)) {
 		DRM_DEBUG_DRIVER("resetting chip\n");
-		kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE,
-				   reset_event);
+		kobject_uevent_env(kobj, KOBJ_CHANGE, reset_event);
 
 		/*
 		 * In most cases it's guaranteed that we get here with an RPM
@@ -2589,7 +2531,7 @@ static void i915_reset_and_wakeup(struct drm_device *dev)
 		 */
 		intel_runtime_pm_get(dev_priv);
 
-		intel_prepare_reset(dev);
+		intel_prepare_reset(dev_priv);
 
 		/*
 		 * All state reset _must_ be completed before we update the
@@ -2597,27 +2539,26 @@ static void i915_reset_and_wakeup(struct drm_device *dev)
 		 * pending state and not properly drop locks, resulting in
 		 * deadlocks with the reset work.
 		 */
-		ret = i915_reset(dev);
+		ret = i915_reset(dev_priv);
 
-		intel_finish_reset(dev);
+		intel_finish_reset(dev_priv);
 
 		intel_runtime_pm_put(dev_priv);
 
 		if (ret == 0)
-			kobject_uevent_env(&dev->primary->kdev->kobj,
+			kobject_uevent_env(kobj,
 					   KOBJ_CHANGE, reset_done_event);
 
 		/*
 		 * Note: The wake_up also serves as a memory barrier so that
 		 * waiters see the update value of the reset counter atomic_t.
 		 */
-		i915_error_wake_up(dev_priv, true);
+		wake_up_all(&dev_priv->gpu_error.reset_queue);
 	}
 }
 
-static void i915_report_and_clear_eir(struct drm_device *dev)
+static void i915_report_and_clear_eir(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t instdone[I915_NUM_INSTDONE_REG];
 	u32 eir = I915_READ(EIR);
 	int pipe, i;
@@ -2627,9 +2568,9 @@ static void i915_report_and_clear_eir(struct drm_device *dev)
 
 	pr_err("render error detected, EIR: 0x%08x\n", eir);
 
-	i915_get_extra_instdone(dev, instdone);
+	i915_get_extra_instdone(dev_priv, instdone);
 
-	if (IS_G4X(dev)) {
+	if (IS_G4X(dev_priv)) {
 		if (eir & (GM45_ERROR_MEM_PRIV | GM45_ERROR_CP_PRIV)) {
 			u32 ipeir = I915_READ(IPEIR_I965);
 
@@ -2651,7 +2592,7 @@ static void i915_report_and_clear_eir(struct drm_device *dev)
 		}
 	}
 
-	if (!IS_GEN2(dev)) {
+	if (!IS_GEN2(dev_priv)) {
 		if (eir & I915_ERROR_PAGE_TABLE) {
 			u32 pgtbl_err = I915_READ(PGTBL_ER);
 			pr_err("page table error\n");
@@ -2673,7 +2614,7 @@ static void i915_report_and_clear_eir(struct drm_device *dev)
 		pr_err("  INSTPM: 0x%08x\n", I915_READ(INSTPM));
 		for (i = 0; i < ARRAY_SIZE(instdone); i++)
 			pr_err("  INSTDONE_%d: 0x%08x\n", i, instdone[i]);
-		if (INTEL_INFO(dev)->gen < 4) {
+		if (INTEL_GEN(dev_priv) < 4) {
 			u32 ipeir = I915_READ(IPEIR);
 
 			pr_err("  IPEIR: 0x%08x\n", I915_READ(IPEIR));
@@ -2709,18 +2650,19 @@ static void i915_report_and_clear_eir(struct drm_device *dev)
 
 /**
  * i915_handle_error - handle a gpu error
- * @dev: drm device
+ * @dev_priv: i915 device private
  * @engine_mask: mask representing engines that are hung
  * Do some basic checking of register state at error time and
  * dump it to the syslog.  Also call i915_capture_error_state() to make
  * sure we get a record and make it available in debugfs.  Fire a uevent
  * so userspace knows something bad happened (should trigger collection
  * of a ring dump etc.).
+ * @fmt: Error message format string
  */
-void i915_handle_error(struct drm_device *dev, u32 engine_mask,
+void i915_handle_error(struct drm_i915_private *dev_priv,
+		       u32 engine_mask,
 		       const char *fmt, ...)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	va_list args;
 	char error_msg[80];
 
@@ -2728,8 +2670,8 @@ void i915_handle_error(struct drm_device *dev, u32 engine_mask,
 	vscnprintf(error_msg, sizeof(error_msg), fmt, args);
 	va_end(args);
 
-	i915_capture_error_state(dev, engine_mask, error_msg);
-	i915_report_and_clear_eir(dev);
+	i915_capture_error_state(dev_priv, engine_mask, error_msg);
+	i915_report_and_clear_eir(dev_priv);
 
 	if (engine_mask) {
 		atomic_or(I915_RESET_IN_PROGRESS_FLAG,
@@ -2748,10 +2690,10 @@ void i915_handle_error(struct drm_device *dev, u32 engine_mask,
 		 * ensure that the waiters see the updated value of the reset
 		 * counter atomic_t.
 		 */
-		i915_error_wake_up(dev_priv, false);
+		i915_error_wake_up(dev_priv);
 	}
 
-	i915_reset_and_wakeup(dev);
+	i915_reset_and_wakeup(dev_priv);
 }
 
 /* Called from drm generic code, passed 'crtc' which
@@ -2759,7 +2701,7 @@ void i915_handle_error(struct drm_device *dev, u32 engine_mask,
  */
 static int i915_enable_vblank(struct drm_device *dev, unsigned int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
@@ -2776,7 +2718,7 @@ static int i915_enable_vblank(struct drm_device *dev, unsigned int pipe)
 
 static int ironlake_enable_vblank(struct drm_device *dev, unsigned int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned long irqflags;
 	uint32_t bit = (INTEL_INFO(dev)->gen >= 7) ? DE_PIPE_VBLANK_IVB(pipe) :
 						     DE_PIPE_VBLANK(pipe);
@@ -2790,7 +2732,7 @@ static int ironlake_enable_vblank(struct drm_device *dev, unsigned int pipe)
 
 static int valleyview_enable_vblank(struct drm_device *dev, unsigned int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
@@ -2803,7 +2745,7 @@ static int valleyview_enable_vblank(struct drm_device *dev, unsigned int pipe)
 
 static int gen8_enable_vblank(struct drm_device *dev, unsigned int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
@@ -2818,7 +2760,7 @@ static int gen8_enable_vblank(struct drm_device *dev, unsigned int pipe)
  */
 static void i915_disable_vblank(struct drm_device *dev, unsigned int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
@@ -2830,7 +2772,7 @@ static void i915_disable_vblank(struct drm_device *dev, unsigned int pipe)
 
 static void ironlake_disable_vblank(struct drm_device *dev, unsigned int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned long irqflags;
 	uint32_t bit = (INTEL_INFO(dev)->gen >= 7) ? DE_PIPE_VBLANK_IVB(pipe) :
 						     DE_PIPE_VBLANK(pipe);
@@ -2842,7 +2784,7 @@ static void ironlake_disable_vblank(struct drm_device *dev, unsigned int pipe)
 
 static void valleyview_disable_vblank(struct drm_device *dev, unsigned int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
@@ -2853,7 +2795,7 @@ static void valleyview_disable_vblank(struct drm_device *dev, unsigned int pipe)
 
 static void gen8_disable_vblank(struct drm_device *dev, unsigned int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
@@ -2869,9 +2811,9 @@ ring_idle(struct intel_engine_cs *engine, u32 seqno)
 }
 
 static bool
-ipehr_is_semaphore_wait(struct drm_device *dev, u32 ipehr)
+ipehr_is_semaphore_wait(struct intel_engine_cs *engine, u32 ipehr)
 {
-	if (INTEL_INFO(dev)->gen >= 8) {
+	if (INTEL_GEN(engine->i915) >= 8) {
 		return (ipehr >> 23) == 0x1c;
 	} else {
 		ipehr &= ~MI_SEMAPHORE_SYNC_MASK;
@@ -2884,10 +2826,10 @@ static struct intel_engine_cs *
 semaphore_wait_to_signaller_ring(struct intel_engine_cs *engine, u32 ipehr,
 				 u64 offset)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	struct intel_engine_cs *signaller;
 
-	if (INTEL_INFO(dev_priv)->gen >= 8) {
+	if (INTEL_GEN(dev_priv) >= 8) {
 		for_each_engine(signaller, dev_priv) {
 			if (engine == signaller)
 				continue;
@@ -2916,7 +2858,7 @@ semaphore_wait_to_signaller_ring(struct intel_engine_cs *engine, u32 ipehr,
 static struct intel_engine_cs *
 semaphore_waits_for(struct intel_engine_cs *engine, u32 *seqno)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	u32 cmd, ipehr, head;
 	u64 offset = 0;
 	int i, backwards;
@@ -2942,7 +2884,7 @@ semaphore_waits_for(struct intel_engine_cs *engine, u32 *seqno)
 		return NULL;
 
 	ipehr = I915_READ(RING_IPEHR(engine->mmio_base));
-	if (!ipehr_is_semaphore_wait(engine->dev, ipehr))
+	if (!ipehr_is_semaphore_wait(engine, ipehr))
 		return NULL;
 
 	/*
@@ -2954,7 +2896,7 @@ semaphore_waits_for(struct intel_engine_cs *engine, u32 *seqno)
 	 * ringbuffer itself.
 	 */
 	head = I915_READ_HEAD(engine) & HEAD_ADDR;
-	backwards = (INTEL_INFO(engine->dev)->gen >= 8) ? 5 : 4;
+	backwards = (INTEL_GEN(dev_priv) >= 8) ? 5 : 4;
 
 	for (i = backwards; i; --i) {
 		/*
@@ -2976,7 +2918,7 @@ semaphore_waits_for(struct intel_engine_cs *engine, u32 *seqno)
 		return NULL;
 
 	*seqno = ioread32(engine->buffer->virtual_start + head + 4) + 1;
-	if (INTEL_INFO(engine->dev)->gen >= 8) {
+	if (INTEL_GEN(dev_priv) >= 8) {
 		offset = ioread32(engine->buffer->virtual_start + head + 12);
 		offset <<= 32;
 		offset = ioread32(engine->buffer->virtual_start + head + 8);
@@ -2986,7 +2928,7 @@ semaphore_waits_for(struct intel_engine_cs *engine, u32 *seqno)
 
 static int semaphore_passed(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	struct intel_engine_cs *signaller;
 	u32 seqno;
 
@@ -3000,7 +2942,7 @@ static int semaphore_passed(struct intel_engine_cs *engine)
 	if (signaller->hangcheck.deadlock >= I915_NUM_ENGINES)
 		return -1;
 
-	if (i915_seqno_passed(signaller->get_seqno(signaller), seqno))
+	if (i915_seqno_passed(intel_engine_get_seqno(signaller), seqno))
 		return 1;
 
 	/* cursory check for an unkickable deadlock */
@@ -3028,7 +2970,7 @@ static bool subunits_stuck(struct intel_engine_cs *engine)
 	if (engine->id != RCS)
 		return true;
 
-	i915_get_extra_instdone(engine->dev, instdone);
+	i915_get_extra_instdone(engine->i915, instdone);
 
 	/* There might be unstable subunit states even when
 	 * actual head is not moving. Filter out the unstable ones by
@@ -3069,8 +3011,7 @@ head_stuck(struct intel_engine_cs *engine, u64 acthd)
 static enum intel_ring_hangcheck_action
 ring_stuck(struct intel_engine_cs *engine, u64 acthd)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	enum intel_ring_hangcheck_action ha;
 	u32 tmp;
 
@@ -3078,7 +3019,7 @@ ring_stuck(struct intel_engine_cs *engine, u64 acthd)
 	if (ha != HANGCHECK_HUNG)
 		return ha;
 
-	if (IS_GEN2(dev))
+	if (IS_GEN2(dev_priv))
 		return HANGCHECK_HUNG;
 
 	/* Is the chip hanging on a WAIT_FOR_EVENT?
@@ -3088,19 +3029,19 @@ ring_stuck(struct intel_engine_cs *engine, u64 acthd)
 	 */
 	tmp = I915_READ_CTL(engine);
 	if (tmp & RING_WAIT) {
-		i915_handle_error(dev, 0,
+		i915_handle_error(dev_priv, 0,
 				  "Kicking stuck wait on %s",
 				  engine->name);
 		I915_WRITE_CTL(engine, tmp);
 		return HANGCHECK_KICK;
 	}
 
-	if (INTEL_INFO(dev)->gen >= 6 && tmp & RING_WAIT_SEMAPHORE) {
+	if (INTEL_GEN(dev_priv) >= 6 && tmp & RING_WAIT_SEMAPHORE) {
 		switch (semaphore_passed(engine)) {
 		default:
 			return HANGCHECK_HUNG;
 		case 1:
-			i915_handle_error(dev, 0,
+			i915_handle_error(dev_priv, 0,
 					  "Kicking stuck semaphore on %s",
 					  engine->name);
 			I915_WRITE_CTL(engine, tmp);
@@ -3113,23 +3054,21 @@ ring_stuck(struct intel_engine_cs *engine, u64 acthd)
 	return HANGCHECK_HUNG;
 }
 
-static unsigned kick_waiters(struct intel_engine_cs *engine)
+static unsigned long kick_waiters(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *i915 = to_i915(engine->dev);
-	unsigned user_interrupts = READ_ONCE(engine->user_interrupts);
+	struct drm_i915_private *i915 = engine->i915;
+	unsigned long irq_count = READ_ONCE(engine->breadcrumbs.irq_wakeups);
 
-	if (engine->hangcheck.user_interrupts == user_interrupts &&
+	if (engine->hangcheck.user_interrupts == irq_count &&
 	    !test_and_set_bit(engine->id, &i915->gpu_error.missed_irq_rings)) {
-		if (!(i915->gpu_error.test_irq_rings & intel_engine_flag(engine)))
+		if (!test_bit(engine->id, &i915->gpu_error.test_irq_rings))
 			DRM_ERROR("Hangcheck timer elapsed... %s idle\n",
 				  engine->name);
-		else
-			DRM_INFO("Fake missed irq on %s\n",
-				 engine->name);
-		wake_up_all(&engine->irq_queue);
+
+		intel_engine_enable_fake_irq(engine);
 	}
 
-	return user_interrupts;
+	return irq_count;
 }
 /*
  * This is called when the chip hasn't reported back with completed
@@ -3144,11 +3083,9 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	struct drm_i915_private *dev_priv =
 		container_of(work, typeof(*dev_priv),
 			     gpu_error.hangcheck_work.work);
-	struct drm_device *dev = dev_priv->dev;
 	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int busy_count = 0, rings_hung = 0;
-	bool stuck[I915_NUM_ENGINES] = { 0 };
+	unsigned int hung = 0, stuck = 0;
+	int busy_count = 0;
 #define BUSY 1
 #define KICK 5
 #define HUNG 20
@@ -3157,12 +3094,8 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	if (!i915.enable_hangcheck)
 		return;
 
-	/*
-	 * The hangcheck work is synced during runtime suspend, we don't
-	 * require a wakeref. TODO: instead of disabling the asserts make
-	 * sure that we hold a reference when this work is running.
-	 */
-	DISABLE_RPM_WAKEREF_ASSERTS(dev_priv);
+	if (!READ_ONCE(dev_priv->gt.awake))
+		return;
 
 	/* As enabling the GPU requires fairly extensive mmio access,
 	 * periodically arm the mmio checker to see if we are triggering
@@ -3170,11 +3103,11 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 	 */
 	intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
 
-	for_each_engine_id(engine, dev_priv, id) {
+	for_each_engine(engine, dev_priv) {
+		bool busy = intel_engine_has_waiter(engine);
 		u64 acthd;
 		u32 seqno;
 		unsigned user_interrupts;
-		bool busy = true;
 
 		semaphore_clear_deadlocks(dev_priv);
 
@@ -3189,7 +3122,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 			engine->irq_seqno_barrier(engine);
 
 		acthd = intel_ring_get_active_head(engine);
-		seqno = engine->get_seqno(engine);
+		seqno = intel_engine_get_seqno(engine);
 
 		/* Reset stuck interrupts between batch advances */
 		user_interrupts = 0;
@@ -3197,12 +3130,11 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 		if (engine->hangcheck.seqno == seqno) {
 			if (ring_idle(engine, seqno)) {
 				engine->hangcheck.action = HANGCHECK_IDLE;
-				if (waitqueue_active(&engine->irq_queue)) {
+				if (busy) {
 					/* Safeguard against driver failure */
 					user_interrupts = kick_waiters(engine);
 					engine->hangcheck.score += BUSY;
-				} else
-					busy = false;
+				}
 			} else {
 				/* We always increment the hangcheck score
 				 * if the ring is busy and still processing
@@ -3234,10 +3166,15 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 					break;
 				case HANGCHECK_HUNG:
 					engine->hangcheck.score += HUNG;
-					stuck[id] = true;
 					break;
 				}
 			}
+
+			if (engine->hangcheck.score >= HANGCHECK_SCORE_RING_HUNG) {
+				hung |= intel_engine_flag(engine);
+				if (engine->hangcheck.action != HANGCHECK_HUNG)
+					stuck |= intel_engine_flag(engine);
+			}
 		} else {
 			engine->hangcheck.action = HANGCHECK_ACTIVE;
 
@@ -3262,48 +3199,33 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 		busy_count += busy;
 	}
 
-	for_each_engine_id(engine, dev_priv, id) {
-		if (engine->hangcheck.score >= HANGCHECK_SCORE_RING_HUNG) {
-			DRM_INFO("%s on %s\n",
-				 stuck[id] ? "stuck" : "no progress",
-				 engine->name);
-			rings_hung |= intel_engine_flag(engine);
-		}
-	}
+	if (hung) {
+		char msg[80];
+		int len;
 
-	if (rings_hung) {
-		i915_handle_error(dev, rings_hung, "Engine(s) hung");
-		goto out;
+		/* If some rings hung but others were still busy, only
+		 * blame the hanging rings in the synopsis.
+		 */
+		if (stuck != hung)
+			hung &= ~stuck;
+		len = scnprintf(msg, sizeof(msg),
+				"%s on ", stuck == hung ? "No progress" : "Hang");
+		for_each_engine_masked(engine, dev_priv, hung)
+			len += scnprintf(msg + len, sizeof(msg) - len,
+					 "%s, ", engine->name);
+		msg[len-2] = '\0';
+
+		return i915_handle_error(dev_priv, hung, msg);
 	}
 
+	/* Reset timer in case GPU hangs without another request being added */
 	if (busy_count)
-		/* Reset timer case chip hangs without another request
-		 * being added */
-		i915_queue_hangcheck(dev);
-
-out:
-	ENABLE_RPM_WAKEREF_ASSERTS(dev_priv);
-}
-
-void i915_queue_hangcheck(struct drm_device *dev)
-{
-	struct i915_gpu_error *e = &to_i915(dev)->gpu_error;
-
-	if (!i915.enable_hangcheck)
-		return;
-
-	/* Don't continually defer the hangcheck so that it is always run at
-	 * least once after work has been scheduled on any ring. Otherwise,
-	 * we will ignore a hung ring if a second ring is kept busy.
-	 */
-
-	queue_delayed_work(e->hangcheck_wq, &e->hangcheck_work,
-			   round_jiffies_up_relative(DRM_I915_HANGCHECK_JIFFIES));
+		i915_queue_hangcheck(dev_priv);
 }
 
 static void ibx_irq_reset(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (HAS_PCH_NOP(dev))
 		return;
@@ -3324,7 +3246,7 @@ static void ibx_irq_reset(struct drm_device *dev)
  */
 static void ibx_irq_pre_postinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (HAS_PCH_NOP(dev))
 		return;
@@ -3336,7 +3258,7 @@ static void ibx_irq_pre_postinstall(struct drm_device *dev)
 
 static void gen5_gt_irq_reset(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	GEN5_IRQ_RESET(GT);
 	if (INTEL_INFO(dev)->gen >= 6)
@@ -3396,7 +3318,7 @@ static void vlv_display_irq_postinstall(struct drm_i915_private *dev_priv)
 */
 static void ironlake_irq_reset(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(HWSTAM, 0xffffffff);
 
@@ -3411,7 +3333,7 @@ static void ironlake_irq_reset(struct drm_device *dev)
 
 static void valleyview_irq_preinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(VLV_MASTER_IER, 0);
 	POSTING_READ(VLV_MASTER_IER);
@@ -3434,7 +3356,7 @@ static void gen8_gt_irq_reset(struct drm_i915_private *dev_priv)
 
 static void gen8_irq_reset(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe;
 
 	I915_WRITE(GEN8_MASTER_IRQ, 0);
@@ -3480,12 +3402,12 @@ void gen8_irq_power_well_pre_disable(struct drm_i915_private *dev_priv,
 	spin_unlock_irq(&dev_priv->irq_lock);
 
 	/* make sure we're done processing display irqs */
-	synchronize_irq(dev_priv->dev->irq);
+	synchronize_irq(dev_priv->drm.irq);
 }
 
 static void cherryview_irq_preinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(GEN8_MASTER_IRQ, 0);
 	POSTING_READ(GEN8_MASTER_IRQ);
@@ -3500,31 +3422,29 @@ static void cherryview_irq_preinstall(struct drm_device *dev)
 	spin_unlock_irq(&dev_priv->irq_lock);
 }
 
-static u32 intel_hpd_enabled_irqs(struct drm_device *dev,
+static u32 intel_hpd_enabled_irqs(struct drm_i915_private *dev_priv,
 				  const u32 hpd[HPD_NUM_PINS])
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *encoder;
 	u32 enabled_irqs = 0;
 
-	for_each_intel_encoder(dev, encoder)
+	for_each_intel_encoder(&dev_priv->drm, encoder)
 		if (dev_priv->hotplug.stats[encoder->hpd_pin].state == HPD_ENABLED)
 			enabled_irqs |= hpd[encoder->hpd_pin];
 
 	return enabled_irqs;
 }
 
-static void ibx_hpd_irq_setup(struct drm_device *dev)
+static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 hotplug_irqs, hotplug, enabled_irqs;
 
-	if (HAS_PCH_IBX(dev)) {
+	if (HAS_PCH_IBX(dev_priv)) {
 		hotplug_irqs = SDE_HOTPLUG_MASK;
-		enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_ibx);
+		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_ibx);
 	} else {
 		hotplug_irqs = SDE_HOTPLUG_MASK_CPT;
-		enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_cpt);
+		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_cpt);
 	}
 
 	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
@@ -3543,18 +3463,17 @@ static void ibx_hpd_irq_setup(struct drm_device *dev)
 	 * When CPU and PCH are on the same package, port A
 	 * HPD must be enabled in both north and south.
 	 */
-	if (HAS_PCH_LPT_LP(dev))
+	if (HAS_PCH_LPT_LP(dev_priv))
 		hotplug |= PORTA_HOTPLUG_ENABLE;
 	I915_WRITE(PCH_PORT_HOTPLUG, hotplug);
 }
 
-static void spt_hpd_irq_setup(struct drm_device *dev)
+static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 hotplug_irqs, hotplug, enabled_irqs;
 
 	hotplug_irqs = SDE_HOTPLUG_MASK_SPT;
-	enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_spt);
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_spt);
 
 	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
 
@@ -3569,24 +3488,23 @@ static void spt_hpd_irq_setup(struct drm_device *dev)
 	I915_WRITE(PCH_PORT_HOTPLUG2, hotplug);
 }
 
-static void ilk_hpd_irq_setup(struct drm_device *dev)
+static void ilk_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 hotplug_irqs, hotplug, enabled_irqs;
 
-	if (INTEL_INFO(dev)->gen >= 8) {
+	if (INTEL_GEN(dev_priv) >= 8) {
 		hotplug_irqs = GEN8_PORT_DP_A_HOTPLUG;
-		enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_bdw);
+		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_bdw);
 
 		bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs);
-	} else if (INTEL_INFO(dev)->gen >= 7) {
+	} else if (INTEL_GEN(dev_priv) >= 7) {
 		hotplug_irqs = DE_DP_A_HOTPLUG_IVB;
-		enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_ivb);
+		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_ivb);
 
 		ilk_update_display_irq(dev_priv, hotplug_irqs, enabled_irqs);
 	} else {
 		hotplug_irqs = DE_DP_A_HOTPLUG;
-		enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_ilk);
+		enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_ilk);
 
 		ilk_update_display_irq(dev_priv, hotplug_irqs, enabled_irqs);
 	}
@@ -3601,15 +3519,14 @@ static void ilk_hpd_irq_setup(struct drm_device *dev)
 	hotplug |= DIGITAL_PORTA_HOTPLUG_ENABLE | DIGITAL_PORTA_PULSE_DURATION_2ms;
 	I915_WRITE(DIGITAL_PORT_HOTPLUG_CNTRL, hotplug);
 
-	ibx_hpd_irq_setup(dev);
+	ibx_hpd_irq_setup(dev_priv);
 }
 
-static void bxt_hpd_irq_setup(struct drm_device *dev)
+static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 hotplug_irqs, hotplug, enabled_irqs;
 
-	enabled_irqs = intel_hpd_enabled_irqs(dev, hpd_bxt);
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_bxt);
 	hotplug_irqs = BXT_DE_PORT_HOTPLUG_MASK;
 
 	bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs);
@@ -3642,7 +3559,7 @@ static void bxt_hpd_irq_setup(struct drm_device *dev)
 
 static void ibx_irq_postinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 mask;
 
 	if (HAS_PCH_NOP(dev))
@@ -3659,7 +3576,7 @@ static void ibx_irq_postinstall(struct drm_device *dev)
 
 static void gen5_gt_irq_postinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 pm_irqs, gt_irqs;
 
 	pm_irqs = gt_irqs = 0;
@@ -3673,8 +3590,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 
 	gt_irqs |= GT_RENDER_USER_INTERRUPT;
 	if (IS_GEN5(dev)) {
-		gt_irqs |= GT_RENDER_PIPECTL_NOTIFY_INTERRUPT |
-			   ILK_BSD_USER_INTERRUPT;
+		gt_irqs |= ILK_BSD_USER_INTERRUPT;
 	} else {
 		gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT;
 	}
@@ -3696,7 +3612,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 
 static int ironlake_irq_postinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 display_mask, extra_mask;
 
 	if (INTEL_INFO(dev)->gen >= 7) {
@@ -3775,7 +3691,7 @@ void valleyview_disable_display_irqs(struct drm_i915_private *dev_priv)
 
 static int valleyview_irq_postinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	gen5_gt_irq_postinstall(dev);
 
@@ -3827,6 +3743,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	uint32_t de_pipe_enables;
 	u32 de_port_masked = GEN8_AUX_CHANNEL_A;
 	u32 de_port_enables;
+	u32 de_misc_masked = GEN8_DE_MISC_GSE;
 	enum pipe pipe;
 
 	if (INTEL_INFO(dev_priv)->gen >= 9) {
@@ -3862,11 +3779,12 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 					  de_pipe_enables);
 
 	GEN5_IRQ_INIT(GEN8_DE_PORT_, ~de_port_masked, de_port_enables);
+	GEN5_IRQ_INIT(GEN8_DE_MISC_, ~de_misc_masked, de_misc_masked);
 }
 
 static int gen8_irq_postinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (HAS_PCH_SPLIT(dev))
 		ibx_irq_pre_postinstall(dev);
@@ -3885,7 +3803,7 @@ static int gen8_irq_postinstall(struct drm_device *dev)
 
 static int cherryview_irq_postinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	gen8_gt_irq_postinstall(dev_priv);
 
@@ -3902,7 +3820,7 @@ static int cherryview_irq_postinstall(struct drm_device *dev)
 
 static void gen8_irq_uninstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!dev_priv)
 		return;
@@ -3912,7 +3830,7 @@ static void gen8_irq_uninstall(struct drm_device *dev)
 
 static void valleyview_irq_uninstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!dev_priv)
 		return;
@@ -3932,7 +3850,7 @@ static void valleyview_irq_uninstall(struct drm_device *dev)
 
 static void cherryview_irq_uninstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!dev_priv)
 		return;
@@ -3952,7 +3870,7 @@ static void cherryview_irq_uninstall(struct drm_device *dev)
 
 static void ironlake_irq_uninstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!dev_priv)
 		return;
@@ -3962,7 +3880,7 @@ static void ironlake_irq_uninstall(struct drm_device *dev)
 
 static void i8xx_irq_preinstall(struct drm_device * dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe;
 
 	for_each_pipe(dev_priv, pipe)
@@ -3974,7 +3892,7 @@ static void i8xx_irq_preinstall(struct drm_device * dev)
 
 static int i8xx_irq_postinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE16(EMR,
 		     ~(I915_ERROR_PAGE_TABLE | I915_ERROR_MEMORY_REFRESH));
@@ -4006,13 +3924,12 @@ static int i8xx_irq_postinstall(struct drm_device *dev)
 /*
  * Returns true when a page flip has completed.
  */
-static bool i8xx_handle_vblank(struct drm_device *dev,
+static bool i8xx_handle_vblank(struct drm_i915_private *dev_priv,
 			       int plane, int pipe, u32 iir)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u16 flip_pending = DISPLAY_PLANE_FLIP_PENDING(plane);
 
-	if (!intel_pipe_handle_vblank(dev, pipe))
+	if (!intel_pipe_handle_vblank(dev_priv, pipe))
 		return false;
 
 	if ((iir & flip_pending) == 0)
@@ -4027,19 +3944,18 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	if (I915_READ16(ISR) & flip_pending)
 		goto check_page_flip;
 
-	intel_prepare_page_flip(dev, plane);
-	intel_finish_page_flip(dev, pipe);
+	intel_finish_page_flip_cs(dev_priv, pipe);
 	return true;
 
 check_page_flip:
-	intel_check_page_flip(dev, pipe);
+	intel_check_page_flip(dev_priv, pipe);
 	return false;
 }
 
 static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u16 iir, new_iir;
 	u32 pipe_stats[2];
 	int pipe;
@@ -4089,15 +4005,15 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 
 		for_each_pipe(dev_priv, pipe) {
 			int plane = pipe;
-			if (HAS_FBC(dev))
+			if (HAS_FBC(dev_priv))
 				plane = !plane;
 
 			if (pipe_stats[pipe] & PIPE_VBLANK_INTERRUPT_STATUS &&
-			    i8xx_handle_vblank(dev, plane, pipe, iir))
+			    i8xx_handle_vblank(dev_priv, plane, pipe, iir))
 				flip_mask &= ~DISPLAY_PLANE_FLIP_PENDING(plane);
 
 			if (pipe_stats[pipe] & PIPE_CRC_DONE_INTERRUPT_STATUS)
-				i9xx_pipe_crc_irq_handler(dev, pipe);
+				i9xx_pipe_crc_irq_handler(dev_priv, pipe);
 
 			if (pipe_stats[pipe] & PIPE_FIFO_UNDERRUN_STATUS)
 				intel_cpu_fifo_underrun_irq_handler(dev_priv,
@@ -4116,7 +4032,7 @@ out:
 
 static void i8xx_irq_uninstall(struct drm_device * dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe;
 
 	for_each_pipe(dev_priv, pipe) {
@@ -4131,7 +4047,7 @@ static void i8xx_irq_uninstall(struct drm_device * dev)
 
 static void i915_irq_preinstall(struct drm_device * dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe;
 
 	if (I915_HAS_HOTPLUG(dev)) {
@@ -4149,7 +4065,7 @@ static void i915_irq_preinstall(struct drm_device * dev)
 
 static int i915_irq_postinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 enable_mask;
 
 	I915_WRITE(EMR, ~(I915_ERROR_PAGE_TABLE | I915_ERROR_MEMORY_REFRESH));
@@ -4182,7 +4098,7 @@ static int i915_irq_postinstall(struct drm_device *dev)
 	I915_WRITE(IER, enable_mask);
 	POSTING_READ(IER);
 
-	i915_enable_asle_pipestat(dev);
+	i915_enable_asle_pipestat(dev_priv);
 
 	/* Interrupt setup is already guaranteed to be single-threaded, this is
 	 * just to make the assert_spin_locked check happy. */
@@ -4197,13 +4113,12 @@ static int i915_irq_postinstall(struct drm_device *dev)
 /*
  * Returns true when a page flip has completed.
  */
-static bool i915_handle_vblank(struct drm_device *dev,
+static bool i915_handle_vblank(struct drm_i915_private *dev_priv,
 			       int plane, int pipe, u32 iir)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 flip_pending = DISPLAY_PLANE_FLIP_PENDING(plane);
 
-	if (!intel_pipe_handle_vblank(dev, pipe))
+	if (!intel_pipe_handle_vblank(dev_priv, pipe))
 		return false;
 
 	if ((iir & flip_pending) == 0)
@@ -4218,19 +4133,18 @@ static bool i915_handle_vblank(struct drm_device *dev,
 	if (I915_READ(ISR) & flip_pending)
 		goto check_page_flip;
 
-	intel_prepare_page_flip(dev, plane);
-	intel_finish_page_flip(dev, pipe);
+	intel_finish_page_flip_cs(dev_priv, pipe);
 	return true;
 
 check_page_flip:
-	intel_check_page_flip(dev, pipe);
+	intel_check_page_flip(dev_priv, pipe);
 	return false;
 }
 
 static irqreturn_t i915_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 iir, new_iir, pipe_stats[I915_MAX_PIPES];
 	u32 flip_mask =
 		I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
@@ -4273,11 +4187,11 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 			break;
 
 		/* Consume port.  Then clear IIR or we'll miss events */
-		if (I915_HAS_HOTPLUG(dev) &&
+		if (I915_HAS_HOTPLUG(dev_priv) &&
 		    iir & I915_DISPLAY_PORT_INTERRUPT) {
 			u32 hotplug_status = i9xx_hpd_irq_ack(dev_priv);
 			if (hotplug_status)
-				i9xx_hpd_irq_handler(dev, hotplug_status);
+				i9xx_hpd_irq_handler(dev_priv, hotplug_status);
 		}
 
 		I915_WRITE(IIR, iir & ~flip_mask);
@@ -4288,18 +4202,18 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 
 		for_each_pipe(dev_priv, pipe) {
 			int plane = pipe;
-			if (HAS_FBC(dev))
+			if (HAS_FBC(dev_priv))
 				plane = !plane;
 
 			if (pipe_stats[pipe] & PIPE_VBLANK_INTERRUPT_STATUS &&
-			    i915_handle_vblank(dev, plane, pipe, iir))
+			    i915_handle_vblank(dev_priv, plane, pipe, iir))
 				flip_mask &= ~DISPLAY_PLANE_FLIP_PENDING(plane);
 
 			if (pipe_stats[pipe] & PIPE_LEGACY_BLC_EVENT_STATUS)
 				blc_event = true;
 
 			if (pipe_stats[pipe] & PIPE_CRC_DONE_INTERRUPT_STATUS)
-				i9xx_pipe_crc_irq_handler(dev, pipe);
+				i9xx_pipe_crc_irq_handler(dev_priv, pipe);
 
 			if (pipe_stats[pipe] & PIPE_FIFO_UNDERRUN_STATUS)
 				intel_cpu_fifo_underrun_irq_handler(dev_priv,
@@ -4307,7 +4221,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		}
 
 		if (blc_event || (iir & I915_ASLE_INTERRUPT))
-			intel_opregion_asle_intr(dev);
+			intel_opregion_asle_intr(dev_priv);
 
 		/* With MSI, interrupts are only generated when iir
 		 * transitions from zero to nonzero.  If another bit got
@@ -4335,7 +4249,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 
 static void i915_irq_uninstall(struct drm_device * dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe;
 
 	if (I915_HAS_HOTPLUG(dev)) {
@@ -4357,7 +4271,7 @@ static void i915_irq_uninstall(struct drm_device * dev)
 
 static void i965_irq_preinstall(struct drm_device * dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe;
 
 	i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
@@ -4373,7 +4287,7 @@ static void i965_irq_preinstall(struct drm_device * dev)
 
 static int i965_irq_postinstall(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 enable_mask;
 	u32 error_mask;
 
@@ -4391,7 +4305,7 @@ static int i965_irq_postinstall(struct drm_device *dev)
 			 I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT);
 	enable_mask |= I915_USER_INTERRUPT;
 
-	if (IS_G4X(dev))
+	if (IS_G4X(dev_priv))
 		enable_mask |= I915_BSD_USER_INTERRUPT;
 
 	/* Interrupt setup is already guaranteed to be single-threaded, this is
@@ -4406,7 +4320,7 @@ static int i965_irq_postinstall(struct drm_device *dev)
 	 * Enable some error detection, note the instruction error mask
 	 * bit is reserved, so we leave it masked.
 	 */
-	if (IS_G4X(dev)) {
+	if (IS_G4X(dev_priv)) {
 		error_mask = ~(GM45_ERROR_PAGE_TABLE |
 			       GM45_ERROR_MEM_PRIV |
 			       GM45_ERROR_CP_PRIV |
@@ -4424,26 +4338,25 @@ static int i965_irq_postinstall(struct drm_device *dev)
 	i915_hotplug_interrupt_update(dev_priv, 0xffffffff, 0);
 	POSTING_READ(PORT_HOTPLUG_EN);
 
-	i915_enable_asle_pipestat(dev);
+	i915_enable_asle_pipestat(dev_priv);
 
 	return 0;
 }
 
-static void i915_hpd_irq_setup(struct drm_device *dev)
+static void i915_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 hotplug_en;
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
 	/* Note HDMI and DP share hotplug bits */
 	/* enable bits are the same for all generations */
-	hotplug_en = intel_hpd_enabled_irqs(dev, hpd_mask_i915);
+	hotplug_en = intel_hpd_enabled_irqs(dev_priv, hpd_mask_i915);
 	/* Programming the CRT detection parameters tends
 	   to generate a spurious hotplug event about three
 	   seconds later.  So just do it once.
 	*/
-	if (IS_G4X(dev))
+	if (IS_G4X(dev_priv))
 		hotplug_en |= CRT_HOTPLUG_ACTIVATION_PERIOD_64;
 	hotplug_en |= CRT_HOTPLUG_VOLTAGE_COMPARE_50;
 
@@ -4458,7 +4371,7 @@ static void i915_hpd_irq_setup(struct drm_device *dev)
 static irqreturn_t i965_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 iir, new_iir;
 	u32 pipe_stats[I915_MAX_PIPES];
 	int ret = IRQ_NONE, pipe;
@@ -4510,7 +4423,7 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		if (iir & I915_DISPLAY_PORT_INTERRUPT) {
 			u32 hotplug_status = i9xx_hpd_irq_ack(dev_priv);
 			if (hotplug_status)
-				i9xx_hpd_irq_handler(dev, hotplug_status);
+				i9xx_hpd_irq_handler(dev_priv, hotplug_status);
 		}
 
 		I915_WRITE(IIR, iir & ~flip_mask);
@@ -4523,24 +4436,24 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 
 		for_each_pipe(dev_priv, pipe) {
 			if (pipe_stats[pipe] & PIPE_START_VBLANK_INTERRUPT_STATUS &&
-			    i915_handle_vblank(dev, pipe, pipe, iir))
+			    i915_handle_vblank(dev_priv, pipe, pipe, iir))
 				flip_mask &= ~DISPLAY_PLANE_FLIP_PENDING(pipe);
 
 			if (pipe_stats[pipe] & PIPE_LEGACY_BLC_EVENT_STATUS)
 				blc_event = true;
 
 			if (pipe_stats[pipe] & PIPE_CRC_DONE_INTERRUPT_STATUS)
-				i9xx_pipe_crc_irq_handler(dev, pipe);
+				i9xx_pipe_crc_irq_handler(dev_priv, pipe);
 
 			if (pipe_stats[pipe] & PIPE_FIFO_UNDERRUN_STATUS)
 				intel_cpu_fifo_underrun_irq_handler(dev_priv, pipe);
 		}
 
 		if (blc_event || (iir & I915_ASLE_INTERRUPT))
-			intel_opregion_asle_intr(dev);
+			intel_opregion_asle_intr(dev_priv);
 
 		if (pipe_stats[0] & PIPE_GMBUS_INTERRUPT_STATUS)
-			gmbus_irq_handler(dev);
+			gmbus_irq_handler(dev_priv);
 
 		/* With MSI, interrupts are only generated when iir
 		 * transitions from zero to nonzero.  If another bit got
@@ -4567,7 +4480,7 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 
 static void i965_irq_uninstall(struct drm_device * dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe;
 
 	if (!dev_priv)
@@ -4597,7 +4510,7 @@ static void i965_irq_uninstall(struct drm_device * dev)
  */
 void intel_irq_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 
 	intel_hpd_init_work(dev_priv);
 
@@ -4611,6 +4524,20 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 	else
 		dev_priv->pm_rps_events = GEN6_PM_RPS_EVENTS;
 
+	dev_priv->rps.pm_intr_keep = 0;
+
+	/*
+	 * SNB,IVB can while VLV,CHV may hard hang on looping batchbuffer
+	 * if GEN6_PM_UP_EI_EXPIRED is masked.
+	 *
+	 * TODO: verify if this can be reproduced on VLV,CHV.
+	 */
+	if (INTEL_INFO(dev_priv)->gen <= 7 && !IS_HASWELL(dev_priv))
+		dev_priv->rps.pm_intr_keep |= GEN6_PM_RP_UP_EI_EXPIRED;
+
+	if (INTEL_INFO(dev_priv)->gen >= 8)
+		dev_priv->rps.pm_intr_keep |= GEN8_PMINTR_REDIRECT_TO_NON_DISP;
+
 	INIT_DELAYED_WORK(&dev_priv->gpu_error.hangcheck_work,
 			  i915_hangcheck_elapsed);
 
@@ -4674,12 +4601,12 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 		dev->driver->disable_vblank = ironlake_disable_vblank;
 		dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup;
 	} else {
-		if (INTEL_INFO(dev_priv)->gen == 2) {
+		if (IS_GEN2(dev_priv)) {
 			dev->driver->irq_preinstall = i8xx_irq_preinstall;
 			dev->driver->irq_postinstall = i8xx_irq_postinstall;
 			dev->driver->irq_handler = i8xx_irq_handler;
 			dev->driver->irq_uninstall = i8xx_irq_uninstall;
-		} else if (INTEL_INFO(dev_priv)->gen == 3) {
+		} else if (IS_GEN3(dev_priv)) {
 			dev->driver->irq_preinstall = i915_irq_preinstall;
 			dev->driver->irq_postinstall = i915_irq_postinstall;
 			dev->driver->irq_uninstall = i915_irq_uninstall;
@@ -4717,7 +4644,7 @@ int intel_irq_install(struct drm_i915_private *dev_priv)
 	 */
 	dev_priv->pm.irqs_enabled = true;
 
-	return drm_irq_install(dev_priv->dev, dev_priv->dev->pdev->irq);
+	return drm_irq_install(&dev_priv->drm, dev_priv->drm.pdev->irq);
 }
 
 /**
@@ -4729,7 +4656,7 @@ int intel_irq_install(struct drm_i915_private *dev_priv)
  */
 void intel_irq_uninstall(struct drm_i915_private *dev_priv)
 {
-	drm_irq_uninstall(dev_priv->dev);
+	drm_irq_uninstall(&dev_priv->drm);
 	intel_hpd_cancel_work(dev_priv);
 	dev_priv->pm.irqs_enabled = false;
 }
@@ -4743,9 +4670,9 @@ void intel_irq_uninstall(struct drm_i915_private *dev_priv)
  */
 void intel_runtime_pm_disable_interrupts(struct drm_i915_private *dev_priv)
 {
-	dev_priv->dev->driver->irq_uninstall(dev_priv->dev);
+	dev_priv->drm.driver->irq_uninstall(&dev_priv->drm);
 	dev_priv->pm.irqs_enabled = false;
-	synchronize_irq(dev_priv->dev->irq);
+	synchronize_irq(dev_priv->drm.irq);
 }
 
 /**
@@ -4758,6 +4685,6 @@ void intel_runtime_pm_disable_interrupts(struct drm_i915_private *dev_priv)
 void intel_runtime_pm_enable_interrupts(struct drm_i915_private *dev_priv)
 {
 	dev_priv->pm.irqs_enabled = true;
-	dev_priv->dev->driver->irq_preinstall(dev_priv->dev);
-	dev_priv->dev->driver->irq_postinstall(dev_priv->dev);
+	dev_priv->drm.driver->irq_preinstall(&dev_priv->drm);
+	dev_priv->drm.driver->irq_postinstall(&dev_priv->drm);
 }
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 1779f02e6df8..b6e404c91eed 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -54,10 +54,13 @@ struct i915_params i915 __read_mostly = {
 	.verbose_state_checks = 1,
 	.nuclear_pageflip = 0,
 	.edp_vswing = 0,
-	.enable_guc_submission = false,
+	.enable_guc_loading = 0,
+	.enable_guc_submission = 0,
 	.guc_log_level = -1,
 	.enable_dp_mst = true,
 	.inject_load_failure = 0,
+	.enable_dpcd_backlight = false,
+	.enable_gvt = false,
 };
 
 module_param_named(modeset, i915.modeset, int, 0400);
@@ -197,8 +200,15 @@ MODULE_PARM_DESC(edp_vswing,
 		 "(0=use value from vbt [default], 1=low power swing(200mV),"
 		 "2=default swing(400mV))");
 
-module_param_named_unsafe(enable_guc_submission, i915.enable_guc_submission, bool, 0400);
-MODULE_PARM_DESC(enable_guc_submission, "Enable GuC submission (default:false)");
+module_param_named_unsafe(enable_guc_loading, i915.enable_guc_loading, int, 0400);
+MODULE_PARM_DESC(enable_guc_loading,
+		"Enable GuC firmware loading "
+		"(-1=auto, 0=never [default], 1=if available, 2=required)");
+
+module_param_named_unsafe(enable_guc_submission, i915.enable_guc_submission, int, 0400);
+MODULE_PARM_DESC(enable_guc_submission,
+		"Enable GuC submission "
+		"(-1=auto, 0=never [default], 1=if available, 2=required)");
 
 module_param_named(guc_log_level, i915.guc_log_level, int, 0400);
 MODULE_PARM_DESC(guc_log_level,
@@ -210,3 +220,10 @@ MODULE_PARM_DESC(enable_dp_mst,
 module_param_named_unsafe(inject_load_failure, i915.inject_load_failure, uint, 0400);
 MODULE_PARM_DESC(inject_load_failure,
 	"Force an error after a number of failure check points (0:disabled (default), N:force failure at the Nth failure check point)");
+module_param_named(enable_dpcd_backlight, i915.enable_dpcd_backlight, bool, 0600);
+MODULE_PARM_DESC(enable_dpcd_backlight,
+	"Enable support for DPCD backlight control (default:false)");
+
+module_param_named(enable_gvt, i915.enable_gvt, bool, 0400);
+MODULE_PARM_DESC(enable_gvt,
+	"Enable support for Intel GVT-g graphics virtualization host support(default:false)");
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index 02bc27804291..0ad020b4a925 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -45,6 +45,8 @@ struct i915_params {
 	int enable_ips;
 	int invert_brightness;
 	int enable_cmd_parser;
+	int enable_guc_loading;
+	int enable_guc_submission;
 	int guc_log_level;
 	int use_mmio_flip;
 	int mmio_debug;
@@ -57,10 +59,11 @@ struct i915_params {
 	bool load_detect_test;
 	bool reset;
 	bool disable_display;
-	bool enable_guc_submission;
 	bool verbose_state_checks;
 	bool nuclear_pageflip;
 	bool enable_dp_mst;
+	bool enable_dpcd_backlight;
+	bool enable_gvt;
 };
 
 extern struct i915_params i915 __read_mostly;
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
new file mode 100644
index 000000000000..949c01686a66
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -0,0 +1,503 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#include <linux/console.h>
+#include <linux/vgaarb.h>
+#include <linux/vga_switcheroo.h>
+
+#include "i915_drv.h"
+
+#define GEN_DEFAULT_PIPEOFFSETS \
+	.pipe_offsets = { PIPE_A_OFFSET, PIPE_B_OFFSET, \
+			  PIPE_C_OFFSET, PIPE_EDP_OFFSET }, \
+	.trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \
+			   TRANSCODER_C_OFFSET, TRANSCODER_EDP_OFFSET }, \
+	.palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET }
+
+#define GEN_CHV_PIPEOFFSETS \
+	.pipe_offsets = { PIPE_A_OFFSET, PIPE_B_OFFSET, \
+			  CHV_PIPE_C_OFFSET }, \
+	.trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \
+			   CHV_TRANSCODER_C_OFFSET, }, \
+	.palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET, \
+			     CHV_PALETTE_C_OFFSET }
+
+#define CURSOR_OFFSETS \
+	.cursor_offsets = { CURSOR_A_OFFSET, CURSOR_B_OFFSET, CHV_CURSOR_C_OFFSET }
+
+#define IVB_CURSOR_OFFSETS \
+	.cursor_offsets = { CURSOR_A_OFFSET, IVB_CURSOR_B_OFFSET, IVB_CURSOR_C_OFFSET }
+
+#define BDW_COLORS \
+	.color = { .degamma_lut_size = 512, .gamma_lut_size = 512 }
+#define CHV_COLORS \
+	.color = { .degamma_lut_size = 65, .gamma_lut_size = 257 }
+
+static const struct intel_device_info intel_i830_info = {
+	.gen = 2, .is_mobile = 1, .cursor_needs_physical = 1, .num_pipes = 2,
+	.has_overlay = 1, .overlay_needs_physical = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_845g_info = {
+	.gen = 2, .num_pipes = 1,
+	.has_overlay = 1, .overlay_needs_physical = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_i85x_info = {
+	.gen = 2, .is_i85x = 1, .is_mobile = 1, .num_pipes = 2,
+	.cursor_needs_physical = 1,
+	.has_overlay = 1, .overlay_needs_physical = 1,
+	.has_fbc = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_i865g_info = {
+	.gen = 2, .num_pipes = 1,
+	.has_overlay = 1, .overlay_needs_physical = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_i915g_info = {
+	.gen = 3, .is_i915g = 1, .cursor_needs_physical = 1, .num_pipes = 2,
+	.has_overlay = 1, .overlay_needs_physical = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+static const struct intel_device_info intel_i915gm_info = {
+	.gen = 3, .is_mobile = 1, .num_pipes = 2,
+	.cursor_needs_physical = 1,
+	.has_overlay = 1, .overlay_needs_physical = 1,
+	.supports_tv = 1,
+	.has_fbc = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+static const struct intel_device_info intel_i945g_info = {
+	.gen = 3, .has_hotplug = 1, .cursor_needs_physical = 1, .num_pipes = 2,
+	.has_overlay = 1, .overlay_needs_physical = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+static const struct intel_device_info intel_i945gm_info = {
+	.gen = 3, .is_i945gm = 1, .is_mobile = 1, .num_pipes = 2,
+	.has_hotplug = 1, .cursor_needs_physical = 1,
+	.has_overlay = 1, .overlay_needs_physical = 1,
+	.supports_tv = 1,
+	.has_fbc = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_i965g_info = {
+	.gen = 4, .is_broadwater = 1, .num_pipes = 2,
+	.has_hotplug = 1,
+	.has_overlay = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_i965gm_info = {
+	.gen = 4, .is_crestline = 1, .num_pipes = 2,
+	.is_mobile = 1, .has_fbc = 1, .has_hotplug = 1,
+	.has_overlay = 1,
+	.supports_tv = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_g33_info = {
+	.gen = 3, .is_g33 = 1, .num_pipes = 2,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.has_overlay = 1,
+	.ring_mask = RENDER_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_g45_info = {
+	.gen = 4, .is_g4x = 1, .need_gfx_hws = 1, .num_pipes = 2,
+	.has_pipe_cxsr = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_gm45_info = {
+	.gen = 4, .is_g4x = 1, .num_pipes = 2,
+	.is_mobile = 1, .need_gfx_hws = 1, .has_fbc = 1,
+	.has_pipe_cxsr = 1, .has_hotplug = 1,
+	.supports_tv = 1,
+	.ring_mask = RENDER_RING | BSD_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_pineview_info = {
+	.gen = 3, .is_g33 = 1, .is_pineview = 1, .is_mobile = 1, .num_pipes = 2,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.has_overlay = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_ironlake_d_info = {
+	.gen = 5, .num_pipes = 2,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_ironlake_m_info = {
+	.gen = 5, .is_mobile = 1, .num_pipes = 2,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.has_fbc = 1,
+	.ring_mask = RENDER_RING | BSD_RING,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_sandybridge_d_info = {
+	.gen = 6, .num_pipes = 2,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.has_fbc = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING,
+	.has_llc = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_sandybridge_m_info = {
+	.gen = 6, .is_mobile = 1, .num_pipes = 2,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.has_fbc = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING,
+	.has_llc = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+};
+
+#define GEN7_FEATURES  \
+	.gen = 7, .num_pipes = 3, \
+	.need_gfx_hws = 1, .has_hotplug = 1, \
+	.has_fbc = 1, \
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING, \
+	.has_llc = 1, \
+	GEN_DEFAULT_PIPEOFFSETS, \
+	IVB_CURSOR_OFFSETS
+
+static const struct intel_device_info intel_ivybridge_d_info = {
+	GEN7_FEATURES,
+	.is_ivybridge = 1,
+};
+
+static const struct intel_device_info intel_ivybridge_m_info = {
+	GEN7_FEATURES,
+	.is_ivybridge = 1,
+	.is_mobile = 1,
+};
+
+static const struct intel_device_info intel_ivybridge_q_info = {
+	GEN7_FEATURES,
+	.is_ivybridge = 1,
+	.num_pipes = 0, /* legal, last one wins */
+};
+
+#define VLV_FEATURES  \
+	.gen = 7, .num_pipes = 2, \
+	.need_gfx_hws = 1, .has_hotplug = 1, \
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING, \
+	.display_mmio_offset = VLV_DISPLAY_BASE, \
+	GEN_DEFAULT_PIPEOFFSETS, \
+	CURSOR_OFFSETS
+
+static const struct intel_device_info intel_valleyview_m_info = {
+	VLV_FEATURES,
+	.is_valleyview = 1,
+	.is_mobile = 1,
+};
+
+static const struct intel_device_info intel_valleyview_d_info = {
+	VLV_FEATURES,
+	.is_valleyview = 1,
+};
+
+#define HSW_FEATURES  \
+	GEN7_FEATURES, \
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, \
+	.has_ddi = 1, \
+	.has_fpga_dbg = 1
+
+static const struct intel_device_info intel_haswell_d_info = {
+	HSW_FEATURES,
+	.is_haswell = 1,
+};
+
+static const struct intel_device_info intel_haswell_m_info = {
+	HSW_FEATURES,
+	.is_haswell = 1,
+	.is_mobile = 1,
+};
+
+#define BDW_FEATURES \
+	HSW_FEATURES, \
+	BDW_COLORS
+
+static const struct intel_device_info intel_broadwell_d_info = {
+	BDW_FEATURES,
+	.gen = 8,
+	.is_broadwell = 1,
+};
+
+static const struct intel_device_info intel_broadwell_m_info = {
+	BDW_FEATURES,
+	.gen = 8, .is_mobile = 1,
+	.is_broadwell = 1,
+};
+
+static const struct intel_device_info intel_broadwell_gt3d_info = {
+	BDW_FEATURES,
+	.gen = 8,
+	.is_broadwell = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
+};
+
+static const struct intel_device_info intel_broadwell_gt3m_info = {
+	BDW_FEATURES,
+	.gen = 8, .is_mobile = 1,
+	.is_broadwell = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
+};
+
+static const struct intel_device_info intel_cherryview_info = {
+	.gen = 8, .num_pipes = 3,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
+	.is_cherryview = 1,
+	.display_mmio_offset = VLV_DISPLAY_BASE,
+	GEN_CHV_PIPEOFFSETS,
+	CURSOR_OFFSETS,
+	CHV_COLORS,
+};
+
+static const struct intel_device_info intel_skylake_info = {
+	BDW_FEATURES,
+	.is_skylake = 1,
+	.gen = 9,
+};
+
+static const struct intel_device_info intel_skylake_gt3_info = {
+	BDW_FEATURES,
+	.is_skylake = 1,
+	.gen = 9,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
+};
+
+static const struct intel_device_info intel_broxton_info = {
+	.is_broxton = 1,
+	.gen = 9,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
+	.num_pipes = 3,
+	.has_ddi = 1,
+	.has_fpga_dbg = 1,
+	.has_fbc = 1,
+	.has_pooled_eu = 0,
+	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
+	BDW_COLORS,
+};
+
+static const struct intel_device_info intel_kabylake_info = {
+	BDW_FEATURES,
+	.is_kabylake = 1,
+	.gen = 9,
+};
+
+static const struct intel_device_info intel_kabylake_gt3_info = {
+	BDW_FEATURES,
+	.is_kabylake = 1,
+	.gen = 9,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
+};
+
+/*
+ * Make sure any device matches here are from most specific to most
+ * general.  For example, since the Quanta match is based on the subsystem
+ * and subvendor IDs, we need it to come before the more general IVB
+ * PCI ID matches, otherwise we'll use the wrong info struct above.
+ */
+static const struct pci_device_id pciidlist[] = {
+	INTEL_I830_IDS(&intel_i830_info),
+	INTEL_I845G_IDS(&intel_845g_info),
+	INTEL_I85X_IDS(&intel_i85x_info),
+	INTEL_I865G_IDS(&intel_i865g_info),
+	INTEL_I915G_IDS(&intel_i915g_info),
+	INTEL_I915GM_IDS(&intel_i915gm_info),
+	INTEL_I945G_IDS(&intel_i945g_info),
+	INTEL_I945GM_IDS(&intel_i945gm_info),
+	INTEL_I965G_IDS(&intel_i965g_info),
+	INTEL_G33_IDS(&intel_g33_info),
+	INTEL_I965GM_IDS(&intel_i965gm_info),
+	INTEL_GM45_IDS(&intel_gm45_info),
+	INTEL_G45_IDS(&intel_g45_info),
+	INTEL_PINEVIEW_IDS(&intel_pineview_info),
+	INTEL_IRONLAKE_D_IDS(&intel_ironlake_d_info),
+	INTEL_IRONLAKE_M_IDS(&intel_ironlake_m_info),
+	INTEL_SNB_D_IDS(&intel_sandybridge_d_info),
+	INTEL_SNB_M_IDS(&intel_sandybridge_m_info),
+	INTEL_IVB_Q_IDS(&intel_ivybridge_q_info), /* must be first IVB */
+	INTEL_IVB_M_IDS(&intel_ivybridge_m_info),
+	INTEL_IVB_D_IDS(&intel_ivybridge_d_info),
+	INTEL_HSW_D_IDS(&intel_haswell_d_info),
+	INTEL_HSW_M_IDS(&intel_haswell_m_info),
+	INTEL_VLV_M_IDS(&intel_valleyview_m_info),
+	INTEL_VLV_D_IDS(&intel_valleyview_d_info),
+	INTEL_BDW_GT12M_IDS(&intel_broadwell_m_info),
+	INTEL_BDW_GT12D_IDS(&intel_broadwell_d_info),
+	INTEL_BDW_GT3M_IDS(&intel_broadwell_gt3m_info),
+	INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info),
+	INTEL_CHV_IDS(&intel_cherryview_info),
+	INTEL_SKL_GT1_IDS(&intel_skylake_info),
+	INTEL_SKL_GT2_IDS(&intel_skylake_info),
+	INTEL_SKL_GT3_IDS(&intel_skylake_gt3_info),
+	INTEL_SKL_GT4_IDS(&intel_skylake_gt3_info),
+	INTEL_BXT_IDS(&intel_broxton_info),
+	INTEL_KBL_GT1_IDS(&intel_kabylake_info),
+	INTEL_KBL_GT2_IDS(&intel_kabylake_info),
+	INTEL_KBL_GT3_IDS(&intel_kabylake_gt3_info),
+	INTEL_KBL_GT4_IDS(&intel_kabylake_gt3_info),
+	{0, 0, 0}
+};
+MODULE_DEVICE_TABLE(pci, pciidlist);
+
+extern int i915_driver_load(struct pci_dev *pdev,
+			    const struct pci_device_id *ent);
+
+static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct intel_device_info *intel_info =
+		(struct intel_device_info *) ent->driver_data;
+
+	if (IS_PRELIMINARY_HW(intel_info) && !i915.preliminary_hw_support) {
+		DRM_INFO("This hardware requires preliminary hardware support.\n"
+			 "See CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT, and/or modparam preliminary_hw_support\n");
+		return -ENODEV;
+	}
+
+	/* Only bind to function 0 of the device. Early generations
+	 * used function 1 as a placeholder for multi-head. This causes
+	 * us confusion instead, especially on the systems where both
+	 * functions have the same PCI-ID!
+	 */
+	if (PCI_FUNC(pdev->devfn))
+		return -ENODEV;
+
+	/*
+	 * apple-gmux is needed on dual GPU MacBook Pro
+	 * to probe the panel if we're the inactive GPU.
+	 */
+	if (vga_switcheroo_client_probe_defer(pdev))
+		return -EPROBE_DEFER;
+
+	return i915_driver_load(pdev, ent);
+}
+
+extern void i915_driver_unload(struct drm_device *dev);
+
+static void i915_pci_remove(struct pci_dev *pdev)
+{
+	struct drm_device *dev = pci_get_drvdata(pdev);
+
+	i915_driver_unload(dev);
+	drm_dev_unref(dev);
+}
+
+extern const struct dev_pm_ops i915_pm_ops;
+
+static struct pci_driver i915_pci_driver = {
+	.name = DRIVER_NAME,
+	.id_table = pciidlist,
+	.probe = i915_pci_probe,
+	.remove = i915_pci_remove,
+	.driver.pm = &i915_pm_ops,
+};
+
+static int __init i915_init(void)
+{
+	bool use_kms = true;
+
+	/*
+	 * Enable KMS by default, unless explicitly overriden by
+	 * either the i915.modeset prarameter or by the
+	 * vga_text_mode_force boot option.
+	 */
+
+	if (i915.modeset == 0)
+		use_kms = false;
+
+	if (vgacon_text_force() && i915.modeset == -1)
+		use_kms = false;
+
+	if (!use_kms) {
+		/* Silently fail loading to not upset userspace. */
+		DRM_DEBUG_DRIVER("KMS disabled.\n");
+		return 0;
+	}
+
+	return pci_register_driver(&i915_pci_driver);
+}
+
+static void __exit i915_exit(void)
+{
+	if (!i915_pci_driver.driver.owner)
+		return;
+
+	pci_unregister_driver(&i915_pci_driver);
+}
+
+module_init(i915_init);
+module_exit(i915_exit);
+
+MODULE_AUTHOR("Tungsten Graphics, Inc.");
+MODULE_AUTHOR("Intel Corporation");
+
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/i915/i915_pvinfo.h b/drivers/gpu/drm/i915/i915_pvinfo.h
new file mode 100644
index 000000000000..c0cb2974caac
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_pvinfo.h
@@ -0,0 +1,113 @@
+/*
+ * Copyright(c) 2011-2016 Intel Corporation. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _I915_PVINFO_H_
+#define _I915_PVINFO_H_
+
+/* The MMIO offset of the shared info between guest and host emulator */
+#define VGT_PVINFO_PAGE	0x78000
+#define VGT_PVINFO_SIZE	0x1000
+
+/*
+ * The following structure pages are defined in GEN MMIO space
+ * for virtualization. (One page for now)
+ */
+#define VGT_MAGIC         0x4776544776544776ULL	/* 'vGTvGTvG' */
+#define VGT_VERSION_MAJOR 1
+#define VGT_VERSION_MINOR 0
+
+#define INTEL_VGT_IF_VERSION_ENCODE(major, minor) ((major) << 16 | (minor))
+#define INTEL_VGT_IF_VERSION \
+	INTEL_VGT_IF_VERSION_ENCODE(VGT_VERSION_MAJOR, VGT_VERSION_MINOR)
+
+/*
+ * notifications from guest to vgpu device model
+ */
+enum vgt_g2v_type {
+	VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE = 2,
+	VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY,
+	VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE,
+	VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY,
+	VGT_G2V_EXECLIST_CONTEXT_CREATE,
+	VGT_G2V_EXECLIST_CONTEXT_DESTROY,
+	VGT_G2V_MAX,
+};
+
+struct vgt_if {
+	u64 magic;		/* VGT_MAGIC */
+	uint16_t version_major;
+	uint16_t version_minor;
+	u32 vgt_id;		/* ID of vGT instance */
+	u32 rsv1[12];		/* pad to offset 0x40 */
+	/*
+	 *  Data structure to describe the balooning info of resources.
+	 *  Each VM can only have one portion of continuous area for now.
+	 *  (May support scattered resource in future)
+	 *  (starting from offset 0x40)
+	 */
+	struct {
+		/* Aperture register balooning */
+		struct {
+			u32 base;
+			u32 size;
+		} mappable_gmadr;	/* aperture */
+		/* GMADR register balooning */
+		struct {
+			u32 base;
+			u32 size;
+		} nonmappable_gmadr;	/* non aperture */
+		/* allowed fence registers */
+		u32 fence_num;
+		u32 rsv2[3];
+	} avail_rs;		/* available/assigned resource */
+	u32 rsv3[0x200 - 24];	/* pad to half page */
+	/*
+	 * The bottom half page is for response from Gfx driver to hypervisor.
+	 */
+	u32 rsv4;
+	u32 display_ready;	/* ready for display owner switch */
+
+	u32 rsv5[4];
+
+	u32 g2v_notify;
+	u32 rsv6[7];
+
+	struct {
+		u32 lo;
+		u32 hi;
+	} pdp[4];
+
+	u32 execlist_context_descriptor_lo;
+	u32 execlist_context_descriptor_hi;
+
+	u32  rsv7[0x200 - 24];    /* pad to one page */
+} __packed;
+
+#define vgtif_reg(x) \
+	_MMIO((VGT_PVINFO_PAGE + offsetof(struct vgt_if, x)))
+
+/* vGPU display status to be used by the host side */
+#define VGT_DRV_DISPLAY_NOT_READY 0
+#define VGT_DRV_DISPLAY_READY     1  /* ready for display switch */
+
+#endif /* _I915_PVINFO_H_ */
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3fcf7dd5b6ca..ce14fe09d962 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -445,6 +445,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
  */
 #define GFX_INSTR(opcode, flags) ((0x3 << 29) | ((opcode) << 24) | (flags))
 
+#define GEN9_MEDIA_POOL_STATE     ((0x3 << 29) | (0x2 << 27) | (0x5 << 16) | 4)
+#define   GEN9_MEDIA_POOL_ENABLE  (1 << 31)
 #define GFX_OP_RASTER_RULES    ((0x3<<29)|(0x7<<24))
 #define GFX_OP_SCISSOR         ((0x3<<29)|(0x1c<<24)|(0x10<<19))
 #define   SC_UPDATE_SCISSOR       (0x1<<1)
@@ -716,6 +718,9 @@ enum skl_disp_power_wells {
 	/* Not actual bit groups. Used as IDs for lookup_power_well() */
 	SKL_DISP_PW_ALWAYS_ON,
 	SKL_DISP_PW_DC_OFF,
+
+	BXT_DPIO_CMN_A,
+	BXT_DPIO_CMN_BC,
 };
 
 #define SKL_POWER_WELL_STATE(pw) (1 << ((pw) * 2))
@@ -889,7 +894,7 @@ enum skl_disp_power_wells {
  * PLLs can be routed to any transcoder A/B/C.
  *
  * Note: DDI0 is digital port B, DD1 is digital port C, and DDI2 is
- * digital port D (CHV) or port A (BXT).
+ * digital port D (CHV) or port A (BXT). ::
  *
  *
  *     Dual channel PHY (VLV/CHV/BXT)
@@ -1276,6 +1281,15 @@ enum skl_disp_power_wells {
 #define BXT_P_CR_GT_DISP_PWRON		_MMIO(0x138090)
 #define   GT_DISPLAY_POWER_ON(phy)	(1 << (phy))
 
+#define _BXT_PHY_CTL_DDI_A		0x64C00
+#define _BXT_PHY_CTL_DDI_B		0x64C10
+#define _BXT_PHY_CTL_DDI_C		0x64C20
+#define   BXT_PHY_CMNLANE_POWERDOWN_ACK	(1 << 10)
+#define   BXT_PHY_LANE_POWERDOWN_ACK	(1 << 9)
+#define   BXT_PHY_LANE_ENABLED		(1 << 8)
+#define BXT_PHY_CTL(port)		_MMIO_PORT(port, _BXT_PHY_CTL_DDI_A, \
+							 _BXT_PHY_CTL_DDI_B)
+
 #define _PHY_CTL_FAMILY_EDP		0x64C80
 #define _PHY_CTL_FAMILY_DDI		0x64C90
 #define   COMMON_RESET_DIS		(1 << 31)
@@ -1672,6 +1686,9 @@ enum skl_disp_power_wells {
 
 #define GEN7_TLB_RD_ADDR	_MMIO(0x4700)
 
+#define GEN9_GAMT_ECO_REG_RW_IA _MMIO(0x4ab0)
+#define   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS	(1<<18)
+
 #define GAMT_CHKN_BIT_REG	_MMIO(0x4ab8)
 #define   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING	(1<<28)
 
@@ -2171,6 +2188,9 @@ enum skl_disp_power_wells {
 
 #define FBC_LL_SIZE		(1536)
 
+#define FBC_LLC_READ_CTRL	_MMIO(0x9044)
+#define   FBC_LLC_FULLY_OPEN	(1<<30)
+
 /* Framebuffer compression for GM45+ */
 #define DPFC_CB_BASE		_MMIO(0x3200)
 #define DPFC_CONTROL		_MMIO(0x3208)
@@ -2461,6 +2481,8 @@ enum skl_disp_power_wells {
 #define   DPLL_MD_VGA_UDI_MULTIPLIER_MASK	0x0000003f
 #define   DPLL_MD_VGA_UDI_MULTIPLIER_SHIFT	0
 
+#define RAWCLK_FREQ_VLV		_MMIO(VLV_DISPLAY_BASE + 0x6024)
+
 #define _FPA0	0x6040
 #define _FPA1	0x6044
 #define _FPB0	0x6048
@@ -3032,6 +3054,18 @@ enum skl_disp_power_wells {
 /* Same as Haswell, but 72064 bytes now. */
 #define GEN8_CXT_TOTAL_SIZE		(18 * PAGE_SIZE)
 
+enum {
+	INTEL_ADVANCED_CONTEXT = 0,
+	INTEL_LEGACY_32B_CONTEXT,
+	INTEL_ADVANCED_AD_CONTEXT,
+	INTEL_LEGACY_64B_CONTEXT
+};
+
+#define GEN8_CTX_ADDRESSING_MODE_SHIFT 3
+#define GEN8_CTX_ADDRESSING_MODE(dev_priv) (USES_FULL_48BIT_PPGTT(dev_priv) ?\
+				INTEL_LEGACY_64B_CONTEXT : \
+				INTEL_LEGACY_32B_CONTEXT)
+
 #define CHV_CLK_CTL1			_MMIO(0x101100)
 #define VLV_CLK_CTL2			_MMIO(0x101104)
 #define   CLK_CTL2_CZCOUNT_30NS_SHIFT	28
@@ -6045,6 +6079,9 @@ enum skl_disp_power_wells {
 #define  FORCE_ARB_IDLE_PLANES	(1 << 14)
 #define  SKL_EDP_PSR_FIX_RDWRAP	(1 << 3)
 
+#define CHICKEN_PAR2_1		_MMIO(0x42090)
+#define  KVM_CONFIG_CHANGE_NOTIFICATION_SELECT	(1 << 14)
+
 #define _CHICKEN_PIPESL_1_A	0x420b0
 #define _CHICKEN_PIPESL_1_B	0x420b4
 #define  HSW_FBCQ_DIS			(1 << 22)
@@ -6084,6 +6121,7 @@ enum skl_disp_power_wells {
 
 #define FF_SLICE_CS_CHICKEN2			_MMIO(0x20e4)
 #define  GEN9_TSG_BARRIER_ACK_DISABLE		(1<<8)
+#define  GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE  (1<<10)
 
 #define GEN9_CS_DEBUG_MODE1		_MMIO(0x20ec)
 #define GEN9_CTX_PREEMPT_REG		_MMIO(0x2248)
@@ -6108,7 +6146,14 @@ enum skl_disp_power_wells {
 #define  VLV_B0_WA_L3SQCREG1_VALUE		0x00D30000
 
 #define GEN8_L3SQCREG1				_MMIO(0xB100)
-#define  BDW_WA_L3SQCREG1_DEFAULT		0x784000
+/*
+ * Note that on CHV the following has an off-by-one error wrt. to BSpec.
+ * Using the formula in BSpec leads to a hang, while the formula here works
+ * fine and matches the formulas for all other platforms. A BSpec change
+ * request has been filed to clarify this.
+ */
+#define  L3_GENERAL_PRIO_CREDITS(x)		(((x) >> 1) << 19)
+#define  L3_HIGH_PRIO_CREDITS(x)		(((x) >> 1) << 14)
 
 #define GEN7_L3CNTLREG1				_MMIO(0xB01C)
 #define  GEN7_WA_FOR_GEN7_L3_CONTROL			0x3C47FF8C
@@ -7028,7 +7073,8 @@ enum skl_disp_power_wells {
 #define GEN6_RPDEUC				_MMIO(0xA084)
 #define GEN6_RPDEUCSW				_MMIO(0xA088)
 #define GEN6_RC_STATE				_MMIO(0xA094)
-#define   RC6_STATE				(1 << 18)
+#define   RC_SW_TARGET_STATE_SHIFT		16
+#define   RC_SW_TARGET_STATE_MASK		(7 << RC_SW_TARGET_STATE_SHIFT)
 #define GEN6_RC1_WAKE_RATE_LIMIT		_MMIO(0xA098)
 #define GEN6_RC6_WAKE_RATE_LIMIT		_MMIO(0xA09C)
 #define GEN6_RC6pp_WAKE_RATE_LIMIT		_MMIO(0xA0A0)
@@ -7042,13 +7088,17 @@ enum skl_disp_power_wells {
 #define VLV_RCEDATA				_MMIO(0xA0BC)
 #define GEN6_RC6pp_THRESHOLD			_MMIO(0xA0C0)
 #define GEN6_PMINTRMSK				_MMIO(0xA168)
-#define GEN8_PMINTR_REDIRECT_TO_NON_DISP	(1<<31)
+#define   GEN8_PMINTR_REDIRECT_TO_NON_DISP	(1<<31)
+#define GEN8_MISC_CTRL0				_MMIO(0xA180)
 #define VLV_PWRDWNUPCTL				_MMIO(0xA294)
 #define GEN9_MEDIA_PG_IDLE_HYSTERESIS		_MMIO(0xA0C4)
 #define GEN9_RENDER_PG_IDLE_HYSTERESIS		_MMIO(0xA0C8)
 #define GEN9_PG_ENABLE				_MMIO(0xA210)
 #define GEN9_RENDER_PG_ENABLE			(1<<0)
 #define GEN9_MEDIA_PG_ENABLE			(1<<1)
+#define GEN8_PUSHBUS_CONTROL			_MMIO(0xA248)
+#define GEN8_PUSHBUS_ENABLE			_MMIO(0xA250)
+#define GEN8_PUSHBUS_SHIFT			_MMIO(0xA25C)
 
 #define VLV_CHICKEN_3				_MMIO(VLV_DISPLAY_BASE + 0x7040C)
 #define  PIXEL_OVERLAP_CNT_MASK			(3 << 30)
@@ -7578,14 +7628,15 @@ enum skl_disp_power_wells {
 #define  CDCLK_FREQ_540			(1<<26)
 #define  CDCLK_FREQ_337_308		(2<<26)
 #define  CDCLK_FREQ_675_617		(3<<26)
-#define  CDCLK_FREQ_DECIMAL_MASK	(0x7ff)
-
 #define  BXT_CDCLK_CD2X_DIV_SEL_MASK	(3<<22)
 #define  BXT_CDCLK_CD2X_DIV_SEL_1	(0<<22)
 #define  BXT_CDCLK_CD2X_DIV_SEL_1_5	(1<<22)
 #define  BXT_CDCLK_CD2X_DIV_SEL_2	(2<<22)
 #define  BXT_CDCLK_CD2X_DIV_SEL_4	(3<<22)
+#define  BXT_CDCLK_CD2X_PIPE(pipe)	((pipe)<<20)
+#define  BXT_CDCLK_CD2X_PIPE_NONE	BXT_CDCLK_CD2X_PIPE(3)
 #define  BXT_CDCLK_SSA_PRECHARGE_ENABLE	(1<<16)
+#define  CDCLK_FREQ_DECIMAL_MASK	(0x7ff)
 
 /* LCPLL_CTL */
 #define LCPLL1_CTL		_MMIO(0x46010)
@@ -8161,6 +8212,8 @@ enum skl_disp_power_wells {
 #define _MIPIA_EOT_DISABLE		(dev_priv->mipi_mmio_base + 0xb05c)
 #define _MIPIC_EOT_DISABLE		(dev_priv->mipi_mmio_base + 0xb85c)
 #define MIPI_EOT_DISABLE(port)		_MMIO_MIPI(port, _MIPIA_EOT_DISABLE, _MIPIC_EOT_DISABLE)
+#define  BXT_DEFEATURE_DPI_FIFO_CTR			(1 << 9)
+#define  BXT_DPHY_DEFEATURE_EN				(1 << 8)
 #define  LP_RX_TIMEOUT_ERROR_RECOVERY_DISABLE		(1 << 7)
 #define  HS_RX_TIMEOUT_ERROR_RECOVERY_DISABLE		(1 << 6)
 #define  LOW_CONTENTION_RECOVERY_DISABLE		(1 << 5)
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 34e061a9ef06..5cfe4c7716b4 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -31,7 +31,7 @@
 
 static void i915_save_display(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* Display arbitration control */
 	if (INTEL_INFO(dev)->gen <= 4)
@@ -63,7 +63,7 @@ static void i915_save_display(struct drm_device *dev)
 
 static void i915_restore_display(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 mask = 0xffffffff;
 
 	/* Display arbitration */
@@ -103,7 +103,7 @@ static void i915_restore_display(struct drm_device *dev)
 
 int i915_save_state(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
 	mutex_lock(&dev->struct_mutex);
@@ -148,7 +148,7 @@ int i915_save_state(struct drm_device *dev)
 
 int i915_restore_state(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
 	mutex_lock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 2d576b7ff299..d61829e54f93 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -38,12 +38,12 @@
 static u32 calc_residency(struct drm_device *dev,
 			  i915_reg_t reg)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u64 raw_time; /* 32b value may overflow during fixed point math */
 	u64 units = 128ULL, div = 100000ULL;
 	u32 ret;
 
-	if (!intel_enable_rc6(dev))
+	if (!intel_enable_rc6())
 		return 0;
 
 	intel_runtime_pm_get(dev_priv);
@@ -70,8 +70,7 @@ static u32 calc_residency(struct drm_device *dev,
 static ssize_t
 show_rc6_mask(struct device *kdev, struct device_attribute *attr, char *buf)
 {
-	struct drm_minor *dminor = dev_to_drm_minor(kdev);
-	return snprintf(buf, PAGE_SIZE, "%x\n", intel_enable_rc6(dminor->dev));
+	return snprintf(buf, PAGE_SIZE, "%x\n", intel_enable_rc6());
 }
 
 static ssize_t
@@ -167,7 +166,7 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct device *dev = kobj_to_dev(kobj);
 	struct drm_minor *dminor = dev_to_drm_minor(dev);
 	struct drm_device *drm_dev = dminor->dev;
-	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(drm_dev);
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
 
@@ -203,8 +202,8 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct device *dev = kobj_to_dev(kobj);
 	struct drm_minor *dminor = dev_to_drm_minor(dev);
 	struct drm_device *drm_dev = dminor->dev;
-	struct drm_i915_private *dev_priv = drm_dev->dev_private;
-	struct intel_context *ctx;
+	struct drm_i915_private *dev_priv = to_i915(drm_dev);
+	struct i915_gem_context *ctx;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
@@ -228,13 +227,6 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 		}
 	}
 
-	ret = i915_gpu_idle(drm_dev);
-	if (ret) {
-		kfree(temp);
-		mutex_unlock(&drm_dev->struct_mutex);
-		return ret;
-	}
-
 	/* TODO: Ideally we really want a GPU reset here to make sure errors
 	 * aren't propagated. Since I cannot find a stable way to reset the GPU
 	 * at this point it is left as a TODO.
@@ -276,7 +268,7 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 {
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
@@ -310,7 +302,7 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 {
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
@@ -331,7 +323,7 @@ static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev,
 {
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	return snprintf(buf, PAGE_SIZE,
 			"%d\n",
@@ -342,7 +334,7 @@ static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute
 {
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
@@ -360,7 +352,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 {
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val;
 	ssize_t ret;
 
@@ -397,7 +389,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 	/* We still need *_set_rps to process the new max_delay and
 	 * update the interrupt limits and PMINTRMSK even though
 	 * frequency request may be unchanged. */
-	intel_set_rps(dev, val);
+	intel_set_rps(dev_priv, val);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
@@ -410,7 +402,7 @@ static ssize_t gt_min_freq_mhz_show(struct device *kdev, struct device_attribute
 {
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
@@ -428,7 +420,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 {
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val;
 	ssize_t ret;
 
@@ -461,7 +453,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 	/* We still need *_set_rps to process the new min_delay and
 	 * update the interrupt limits and PMINTRMSK even though
 	 * frequency request may be unchanged. */
-	intel_set_rps(dev, val);
+	intel_set_rps(dev_priv, val);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
@@ -488,7 +480,7 @@ static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr
 {
 	struct drm_minor *minor = dev_to_drm_minor(kdev);
 	struct drm_device *dev = minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val;
 
 	if (attr == &dev_attr_gt_RP0_freq_mhz)
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index dc0def210097..534154e05fbe 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -118,7 +118,7 @@ TRACE_EVENT(i915_gem_shrink,
 			     ),
 
 	    TP_fast_assign(
-			   __entry->dev = i915->dev->primary->index;
+			   __entry->dev = i915->drm.primary->index;
 			   __entry->target = target;
 			   __entry->flags = flags;
 			   ),
@@ -462,7 +462,7 @@ TRACE_EVENT(i915_gem_ring_sync_to,
 			     ),
 
 	    TP_fast_assign(
-			   __entry->dev = from->dev->primary->index;
+			   __entry->dev = from->i915->drm.primary->index;
 			   __entry->sync_from = from->id;
 			   __entry->sync_to = to_req->engine->id;
 			   __entry->seqno = i915_gem_request_get_seqno(req);
@@ -486,13 +486,11 @@ TRACE_EVENT(i915_gem_ring_dispatch,
 			     ),
 
 	    TP_fast_assign(
-			   struct intel_engine_cs *engine =
-						i915_gem_request_get_engine(req);
-			   __entry->dev = engine->dev->primary->index;
-			   __entry->ring = engine->id;
-			   __entry->seqno = i915_gem_request_get_seqno(req);
+			   __entry->dev = req->i915->drm.primary->index;
+			   __entry->ring = req->engine->id;
+			   __entry->seqno = req->seqno;
 			   __entry->flags = flags;
-			   i915_trace_irq_get(engine, req);
+			   intel_engine_enable_signaling(req);
 			   ),
 
 	    TP_printk("dev=%u, ring=%u, seqno=%u, flags=%x",
@@ -511,7 +509,7 @@ TRACE_EVENT(i915_gem_ring_flush,
 			     ),
 
 	    TP_fast_assign(
-			   __entry->dev = req->engine->dev->primary->index;
+			   __entry->dev = req->i915->drm.primary->index;
 			   __entry->ring = req->engine->id;
 			   __entry->invalidate = invalidate;
 			   __entry->flush = flush;
@@ -533,11 +531,9 @@ DECLARE_EVENT_CLASS(i915_gem_request,
 			     ),
 
 	    TP_fast_assign(
-			   struct intel_engine_cs *engine =
-						i915_gem_request_get_engine(req);
-			   __entry->dev = engine->dev->primary->index;
-			   __entry->ring = engine->id;
-			   __entry->seqno = i915_gem_request_get_seqno(req);
+			   __entry->dev = req->i915->drm.primary->index;
+			   __entry->ring = req->engine->id;
+			   __entry->seqno = req->seqno;
 			   ),
 
 	    TP_printk("dev=%u, ring=%u, seqno=%u",
@@ -560,9 +556,9 @@ TRACE_EVENT(i915_gem_request_notify,
 			     ),
 
 	    TP_fast_assign(
-			   __entry->dev = engine->dev->primary->index;
+			   __entry->dev = engine->i915->drm.primary->index;
 			   __entry->ring = engine->id;
-			   __entry->seqno = engine->get_seqno(engine);
+			   __entry->seqno = intel_engine_get_seqno(engine);
 			   ),
 
 	    TP_printk("dev=%u, ring=%u, seqno=%u",
@@ -597,13 +593,11 @@ TRACE_EVENT(i915_gem_request_wait_begin,
 	     * less desirable.
 	     */
 	    TP_fast_assign(
-			   struct intel_engine_cs *engine =
-						i915_gem_request_get_engine(req);
-			   __entry->dev = engine->dev->primary->index;
-			   __entry->ring = engine->id;
-			   __entry->seqno = i915_gem_request_get_seqno(req);
+			   __entry->dev = req->i915->drm.primary->index;
+			   __entry->ring = req->engine->id;
+			   __entry->seqno = req->seqno;
 			   __entry->blocking =
-				     mutex_is_locked(&engine->dev->struct_mutex);
+				     mutex_is_locked(&req->i915->drm.struct_mutex);
 			   ),
 
 	    TP_printk("dev=%u, ring=%u, seqno=%u, blocking=%s",
@@ -740,19 +734,19 @@ DEFINE_EVENT(i915_ppgtt, i915_ppgtt_release,
  * the context.
  */
 DECLARE_EVENT_CLASS(i915_context,
-	TP_PROTO(struct intel_context *ctx),
+	TP_PROTO(struct i915_gem_context *ctx),
 	TP_ARGS(ctx),
 
 	TP_STRUCT__entry(
 			__field(u32, dev)
-			__field(struct intel_context *, ctx)
+			__field(struct i915_gem_context *, ctx)
 			__field(struct i915_address_space *, vm)
 	),
 
 	TP_fast_assign(
 			__entry->ctx = ctx;
 			__entry->vm = ctx->ppgtt ? &ctx->ppgtt->base : NULL;
-			__entry->dev = ctx->i915->dev->primary->index;
+			__entry->dev = ctx->i915->drm.primary->index;
 	),
 
 	TP_printk("dev=%u, ctx=%p, ctx_vm=%p",
@@ -760,12 +754,12 @@ DECLARE_EVENT_CLASS(i915_context,
 )
 
 DEFINE_EVENT(i915_context, i915_context_create,
-	TP_PROTO(struct intel_context *ctx),
+	TP_PROTO(struct i915_gem_context *ctx),
 	TP_ARGS(ctx)
 );
 
 DEFINE_EVENT(i915_context, i915_context_free,
-	TP_PROTO(struct intel_context *ctx),
+	TP_PROTO(struct i915_gem_context *ctx),
 	TP_ARGS(ctx)
 );
 
@@ -777,13 +771,13 @@ DEFINE_EVENT(i915_context, i915_context_free,
  * called only if full ppgtt is enabled.
  */
 TRACE_EVENT(switch_mm,
-	TP_PROTO(struct intel_engine_cs *engine, struct intel_context *to),
+	TP_PROTO(struct intel_engine_cs *engine, struct i915_gem_context *to),
 
 	TP_ARGS(engine, to),
 
 	TP_STRUCT__entry(
 			__field(u32, ring)
-			__field(struct intel_context *, to)
+			__field(struct i915_gem_context *, to)
 			__field(struct i915_address_space *, vm)
 			__field(u32, dev)
 	),
@@ -792,7 +786,7 @@ TRACE_EVENT(switch_mm,
 			__entry->ring = engine->id;
 			__entry->to = to;
 			__entry->vm = to->ppgtt? &to->ppgtt->base : NULL;
-			__entry->dev = engine->dev->primary->index;
+			__entry->dev = engine->i915->drm.primary->index;
 	),
 
 	TP_printk("dev=%u, ring=%u, ctx=%p, ctx_vm=%p",
diff --git a/drivers/gpu/drm/i915/i915_vgpu.c b/drivers/gpu/drm/i915/i915_vgpu.c
index d02efb8cad4d..f6acb5a0e701 100644
--- a/drivers/gpu/drm/i915/i915_vgpu.c
+++ b/drivers/gpu/drm/i915/i915_vgpu.c
@@ -53,20 +53,19 @@
 
 /**
  * i915_check_vgpu - detect virtual GPU
- * @dev: drm device *
+ * @dev_priv: i915 device private
  *
  * This function is called at the initialization stage, to detect whether
  * running on a vGPU.
  */
-void i915_check_vgpu(struct drm_device *dev)
+void i915_check_vgpu(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint64_t magic;
 	uint32_t version;
 
 	BUILD_BUG_ON(sizeof(struct vgt_if) != VGT_PVINFO_SIZE);
 
-	if (!IS_HASWELL(dev))
+	if (!IS_HASWELL(dev_priv))
 		return;
 
 	magic = __raw_i915_read64(dev_priv, vgtif_reg(magic));
@@ -102,10 +101,13 @@ static struct _balloon_info_ bl_info;
  * This function is called to deallocate the ballooned-out graphic memory, when
  * driver is unloaded or when ballooning fails.
  */
-void intel_vgt_deballoon(void)
+void intel_vgt_deballoon(struct drm_i915_private *dev_priv)
 {
 	int i;
 
+	if (!intel_vgpu_active(dev_priv))
+		return;
+
 	DRM_DEBUG("VGT deballoon.\n");
 
 	for (i = 0; i < 4; i++) {
@@ -151,36 +153,35 @@ static int vgt_balloon_space(struct drm_mm *mm,
  * of its graphic space being zero. Yet there are some portions ballooned out(
  * the shadow part, which are marked as reserved by drm allocator). From the
  * host point of view, the graphic address space is partitioned by multiple
- * vGPUs in different VMs.
+ * vGPUs in different VMs. ::
  *
  *                        vGPU1 view         Host view
  *             0 ------> +-----------+     +-----------+
- *               ^       |///////////|     |   vGPU3   |
- *               |       |///////////|     +-----------+
- *               |       |///////////|     |   vGPU2   |
+ *               ^       |###########|     |   vGPU3   |
+ *               |       |###########|     +-----------+
+ *               |       |###########|     |   vGPU2   |
  *               |       +-----------+     +-----------+
  *        mappable GM    | available | ==> |   vGPU1   |
  *               |       +-----------+     +-----------+
- *               |       |///////////|     |           |
- *               v       |///////////|     |   Host    |
+ *               |       |###########|     |           |
+ *               v       |###########|     |   Host    |
  *               +=======+===========+     +===========+
- *               ^       |///////////|     |   vGPU3   |
- *               |       |///////////|     +-----------+
- *               |       |///////////|     |   vGPU2   |
+ *               ^       |###########|     |   vGPU3   |
+ *               |       |###########|     +-----------+
+ *               |       |###########|     |   vGPU2   |
  *               |       +-----------+     +-----------+
  *      unmappable GM    | available | ==> |   vGPU1   |
  *               |       +-----------+     +-----------+
- *               |       |///////////|     |           |
- *               |       |///////////|     |   Host    |
- *               v       |///////////|     |           |
+ *               |       |###########|     |           |
+ *               |       |###########|     |   Host    |
+ *               v       |###########|     |           |
  * total GM size ------> +-----------+     +-----------+
  *
  * Returns:
  * zero on success, non-zero if configuration invalid or ballooning failed
  */
-int intel_vgt_balloon(struct drm_device *dev)
+int intel_vgt_balloon(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	unsigned long ggtt_end = ggtt->base.start + ggtt->base.total;
 
@@ -188,6 +189,9 @@ int intel_vgt_balloon(struct drm_device *dev)
 	unsigned long unmappable_base, unmappable_size, unmappable_end;
 	int ret;
 
+	if (!intel_vgpu_active(dev_priv))
+		return 0;
+
 	mappable_base = I915_READ(vgtif_reg(avail_rs.mappable_gmadr.base));
 	mappable_size = I915_READ(vgtif_reg(avail_rs.mappable_gmadr.size));
 	unmappable_base = I915_READ(vgtif_reg(avail_rs.nonmappable_gmadr.base));
@@ -259,6 +263,6 @@ int intel_vgt_balloon(struct drm_device *dev)
 
 err:
 	DRM_ERROR("VGT balloon fail\n");
-	intel_vgt_deballoon();
+	intel_vgt_deballoon(dev_priv);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/i915_vgpu.h b/drivers/gpu/drm/i915/i915_vgpu.h
index 3c83b47b5f69..3c3b2d24e830 100644
--- a/drivers/gpu/drm/i915/i915_vgpu.h
+++ b/drivers/gpu/drm/i915/i915_vgpu.h
@@ -24,94 +24,10 @@
 #ifndef _I915_VGPU_H_
 #define _I915_VGPU_H_
 
-/* The MMIO offset of the shared info between guest and host emulator */
-#define VGT_PVINFO_PAGE	0x78000
-#define VGT_PVINFO_SIZE	0x1000
+#include "i915_pvinfo.h"
 
-/*
- * The following structure pages are defined in GEN MMIO space
- * for virtualization. (One page for now)
- */
-#define VGT_MAGIC         0x4776544776544776ULL	/* 'vGTvGTvG' */
-#define VGT_VERSION_MAJOR 1
-#define VGT_VERSION_MINOR 0
-
-#define INTEL_VGT_IF_VERSION_ENCODE(major, minor) ((major) << 16 | (minor))
-#define INTEL_VGT_IF_VERSION \
-	INTEL_VGT_IF_VERSION_ENCODE(VGT_VERSION_MAJOR, VGT_VERSION_MINOR)
-
-/*
- * notifications from guest to vgpu device model
- */
-enum vgt_g2v_type {
-	VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE = 2,
-	VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY,
-	VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE,
-	VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY,
-	VGT_G2V_EXECLIST_CONTEXT_CREATE,
-	VGT_G2V_EXECLIST_CONTEXT_DESTROY,
-	VGT_G2V_MAX,
-};
-
-struct vgt_if {
-	uint64_t magic;		/* VGT_MAGIC */
-	uint16_t version_major;
-	uint16_t version_minor;
-	uint32_t vgt_id;	/* ID of vGT instance */
-	uint32_t rsv1[12];	/* pad to offset 0x40 */
-	/*
-	 *  Data structure to describe the balooning info of resources.
-	 *  Each VM can only have one portion of continuous area for now.
-	 *  (May support scattered resource in future)
-	 *  (starting from offset 0x40)
-	 */
-	struct {
-		/* Aperture register balooning */
-		struct {
-			uint32_t base;
-			uint32_t size;
-		} mappable_gmadr;	/* aperture */
-		/* GMADR register balooning */
-		struct {
-			uint32_t base;
-			uint32_t size;
-		} nonmappable_gmadr;	/* non aperture */
-		/* allowed fence registers */
-		uint32_t fence_num;
-		uint32_t rsv2[3];
-	} avail_rs;		/* available/assigned resource */
-	uint32_t rsv3[0x200 - 24];	/* pad to half page */
-	/*
-	 * The bottom half page is for response from Gfx driver to hypervisor.
-	 */
-	uint32_t rsv4;
-	uint32_t display_ready;	/* ready for display owner switch */
-
-	uint32_t rsv5[4];
-
-	uint32_t g2v_notify;
-	uint32_t rsv6[7];
-
-	struct {
-		uint32_t lo;
-		uint32_t hi;
-	} pdp[4];
-
-	uint32_t execlist_context_descriptor_lo;
-	uint32_t execlist_context_descriptor_hi;
-
-	uint32_t  rsv7[0x200 - 24];    /* pad to one page */
-} __packed;
-
-#define vgtif_reg(x) \
-	_MMIO((VGT_PVINFO_PAGE + (long)&((struct vgt_if *)NULL)->x))
-
-/* vGPU display status to be used by the host side */
-#define VGT_DRV_DISPLAY_NOT_READY 0
-#define VGT_DRV_DISPLAY_READY     1  /* ready for display switch */
-
-extern void i915_check_vgpu(struct drm_device *dev);
-extern int intel_vgt_balloon(struct drm_device *dev);
-extern void intel_vgt_deballoon(void);
+void i915_check_vgpu(struct drm_i915_private *dev_priv);
+int intel_vgt_balloon(struct drm_i915_private *dev_priv);
+void intel_vgt_deballoon(struct drm_i915_private *dev_priv);
 
 #endif /* _I915_VGPU_H_ */
diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c
index 50ff90aea721..c5a166752eda 100644
--- a/drivers/gpu/drm/i915/intel_atomic.c
+++ b/drivers/gpu/drm/i915/intel_atomic.c
@@ -191,7 +191,7 @@ int intel_atomic_setup_scalers(struct drm_device *dev,
 
 			/* plane scaler case: assign as a plane scaler */
 			/* find the plane that set the bit as scaler_user */
-			plane = drm_state->planes[i];
+			plane = drm_state->planes[i].ptr;
 
 			/*
 			 * to enable/disable hq mode, add planes that are using scaler
@@ -223,7 +223,8 @@ int intel_atomic_setup_scalers(struct drm_device *dev,
 				continue;
 			}
 
-			plane_state = to_intel_plane_state(drm_state->plane_states[i]);
+			plane_state = intel_atomic_get_existing_plane_state(drm_state,
+									    intel_plane);
 			scaler_id = &plane_state->scaler_id;
 		}
 
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 02a7527ce7bb..6700a7be7f78 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -154,7 +154,7 @@ static bool audio_rate_need_prog(struct intel_crtc *crtc,
 {
 	if (((mode->clock == TMDS_297M) ||
 		 (mode->clock == TMDS_296M)) &&
-		intel_pipe_has_type(crtc, INTEL_OUTPUT_HDMI))
+		intel_crtc_has_type(crtc->config, INTEL_OUTPUT_HDMI))
 		return true;
 	else
 		return false;
@@ -165,7 +165,7 @@ static bool intel_eld_uptodate(struct drm_connector *connector,
 			       i915_reg_t reg_elda, uint32_t bits_elda,
 			       i915_reg_t reg_edid)
 {
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	uint8_t *eld = connector->eld;
 	uint32_t tmp;
 	int i;
@@ -189,7 +189,7 @@ static bool intel_eld_uptodate(struct drm_connector *connector,
 
 static void g4x_audio_codec_disable(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	uint32_t eldv, tmp;
 
 	DRM_DEBUG_KMS("Disable audio codec\n");
@@ -210,7 +210,7 @@ static void g4x_audio_codec_enable(struct drm_connector *connector,
 				   struct intel_encoder *encoder,
 				   const struct drm_display_mode *adjusted_mode)
 {
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	uint8_t *eld = connector->eld;
 	uint32_t eldv;
 	uint32_t tmp;
@@ -247,7 +247,7 @@ static void g4x_audio_codec_enable(struct drm_connector *connector,
 
 static void hsw_audio_codec_disable(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	enum pipe pipe = intel_crtc->pipe;
 	uint32_t tmp;
@@ -262,7 +262,7 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder)
 	tmp |= AUD_CONFIG_N_PROG_ENABLE;
 	tmp &= ~AUD_CONFIG_UPPER_N_MASK;
 	tmp &= ~AUD_CONFIG_LOWER_N_MASK;
-	if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT))
+	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		tmp |= AUD_CONFIG_N_VALUE_INDEX;
 	I915_WRITE(HSW_AUD_CFG(pipe), tmp);
 
@@ -279,7 +279,7 @@ static void hsw_audio_codec_enable(struct drm_connector *connector,
 				   struct intel_encoder *encoder,
 				   const struct drm_display_mode *adjusted_mode)
 {
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	enum pipe pipe = intel_crtc->pipe;
 	struct i915_audio_component *acomp = dev_priv->audio_component;
@@ -328,7 +328,7 @@ static void hsw_audio_codec_enable(struct drm_connector *connector,
 	tmp = I915_READ(HSW_AUD_CFG(pipe));
 	tmp &= ~AUD_CONFIG_N_VALUE_INDEX;
 	tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK;
-	if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT))
+	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		tmp |= AUD_CONFIG_N_VALUE_INDEX;
 	else
 		tmp |= audio_config_hdmi_pixel_clock(adjusted_mode);
@@ -357,7 +357,7 @@ static void hsw_audio_codec_enable(struct drm_connector *connector,
 
 static void ilk_audio_codec_disable(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	struct intel_digital_port *intel_dig_port =
 		enc_to_dig_port(&encoder->base);
@@ -389,7 +389,7 @@ static void ilk_audio_codec_disable(struct intel_encoder *encoder)
 	tmp |= AUD_CONFIG_N_PROG_ENABLE;
 	tmp &= ~AUD_CONFIG_UPPER_N_MASK;
 	tmp &= ~AUD_CONFIG_LOWER_N_MASK;
-	if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT))
+	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		tmp |= AUD_CONFIG_N_VALUE_INDEX;
 	I915_WRITE(aud_config, tmp);
 
@@ -405,7 +405,7 @@ static void ilk_audio_codec_enable(struct drm_connector *connector,
 				   struct intel_encoder *encoder,
 				   const struct drm_display_mode *adjusted_mode)
 {
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	struct intel_digital_port *intel_dig_port =
 		enc_to_dig_port(&encoder->base);
@@ -475,7 +475,7 @@ static void ilk_audio_codec_enable(struct drm_connector *connector,
 	tmp &= ~AUD_CONFIG_N_VALUE_INDEX;
 	tmp &= ~AUD_CONFIG_N_PROG_ENABLE;
 	tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK;
-	if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_DISPLAYPORT))
+	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		tmp |= AUD_CONFIG_N_VALUE_INDEX;
 	else
 		tmp |= audio_config_hdmi_pixel_clock(adjusted_mode);
@@ -496,7 +496,7 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder)
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	struct drm_connector *connector;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_audio_component *acomp = dev_priv->audio_component;
 	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	enum port port = intel_dig_port->port;
@@ -513,7 +513,7 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder)
 
 	/* ELD Conn_Type */
 	connector->eld[5] &= ~(3 << 2);
-	if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT))
+	if (intel_crtc_has_dp_encoder(crtc->config))
 		connector->eld[5] |= (1 << 2);
 
 	connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2;
@@ -543,7 +543,7 @@ void intel_audio_codec_disable(struct intel_encoder *intel_encoder)
 {
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_audio_component *acomp = dev_priv->audio_component;
 	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	enum port port = intel_dig_port->port;
@@ -621,17 +621,11 @@ static void i915_audio_component_codec_wake_override(struct device *dev,
 static int i915_audio_component_get_cdclk_freq(struct device *dev)
 {
 	struct drm_i915_private *dev_priv = dev_to_i915(dev);
-	int ret;
 
 	if (WARN_ON_ONCE(!HAS_DDI(dev_priv)))
 		return -ENODEV;
 
-	intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
-	ret = dev_priv->display.get_display_clock_speed(dev_priv->dev);
-
-	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
-
-	return ret;
+	return dev_priv->cdclk_freq;
 }
 
 static int i915_audio_component_sync_audio_rate(struct device *dev,
@@ -755,14 +749,14 @@ static int i915_audio_component_bind(struct device *i915_dev,
 	if (WARN_ON(acomp->ops || acomp->dev))
 		return -EEXIST;
 
-	drm_modeset_lock_all(dev_priv->dev);
+	drm_modeset_lock_all(&dev_priv->drm);
 	acomp->ops = &i915_audio_component_ops;
 	acomp->dev = i915_dev;
 	BUILD_BUG_ON(MAX_PORTS != I915_MAX_PORTS);
 	for (i = 0; i < ARRAY_SIZE(acomp->aud_sample_rate); i++)
 		acomp->aud_sample_rate[i] = 0;
 	dev_priv->audio_component = acomp;
-	drm_modeset_unlock_all(dev_priv->dev);
+	drm_modeset_unlock_all(&dev_priv->drm);
 
 	return 0;
 }
@@ -773,11 +767,11 @@ static void i915_audio_component_unbind(struct device *i915_dev,
 	struct i915_audio_component *acomp = data;
 	struct drm_i915_private *dev_priv = dev_to_i915(i915_dev);
 
-	drm_modeset_lock_all(dev_priv->dev);
+	drm_modeset_lock_all(&dev_priv->drm);
 	acomp->ops = NULL;
 	acomp->dev = NULL;
 	dev_priv->audio_component = NULL;
-	drm_modeset_unlock_all(dev_priv->dev);
+	drm_modeset_unlock_all(&dev_priv->drm);
 }
 
 static const struct component_ops i915_audio_component_bind_ops = {
@@ -805,7 +799,7 @@ void i915_audio_component_init(struct drm_i915_private *dev_priv)
 {
 	int ret;
 
-	ret = component_add(dev_priv->dev->dev, &i915_audio_component_bind_ops);
+	ret = component_add(dev_priv->drm.dev, &i915_audio_component_bind_ops);
 	if (ret < 0) {
 		DRM_ERROR("failed to add audio component (%d)\n", ret);
 		/* continue with reduced functionality */
@@ -827,6 +821,6 @@ void i915_audio_component_cleanup(struct drm_i915_private *dev_priv)
 	if (!dev_priv->audio_component_registered)
 		return;
 
-	component_del(dev_priv->dev->dev, &i915_audio_component_bind_ops);
+	component_del(dev_priv->drm.dev, &i915_audio_component_bind_ops);
 	dev_priv->audio_component_registered = false;
 }
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index b9022fa053d6..c6e69e4cfa83 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -218,7 +218,7 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 
 	dev_priv->vbt.lvds_dither = lvds_options->pixel_dither;
 
-	ret = intel_opregion_get_panel_type(dev_priv->dev);
+	ret = intel_opregion_get_panel_type(dev_priv);
 	if (ret >= 0) {
 		WARN_ON(ret > 0xf);
 		panel_type = ret;
@@ -323,6 +323,15 @@ parse_lfp_backlight(struct drm_i915_private *dev_priv,
 		return;
 	}
 
+	dev_priv->vbt.backlight.type = INTEL_BACKLIGHT_DISPLAY_DDI;
+	if (bdb->version >= 191 &&
+	    get_blocksize(backlight_data) >= sizeof(*backlight_data)) {
+		const struct bdb_lfp_backlight_control_method *method;
+
+		method = &backlight_data->backlight_control[panel_type];
+		dev_priv->vbt.backlight.type = method->type;
+	}
+
 	dev_priv->vbt.backlight.pwm_freq_hz = entry->pwm_freq_hz;
 	dev_priv->vbt.backlight.active_low_pwm = entry->active_low_pwm;
 	dev_priv->vbt.backlight.min_brightness = entry->min_brightness;
@@ -768,6 +777,16 @@ parse_mipi_config(struct drm_i915_private *dev_priv,
 		return;
 	}
 
+	/*
+	 * These fields are introduced from the VBT version 197 onwards,
+	 * so making sure that these bits are set zero in the previous
+	 * versions.
+	 */
+	if (dev_priv->vbt.dsi.config->dual_link && bdb->version < 197) {
+		dev_priv->vbt.dsi.config->dl_dcs_cabc_ports = 0;
+		dev_priv->vbt.dsi.config->dl_dcs_backlight_ports = 0;
+	}
+
 	/* We have mandatory mipi config blocks. Initialize as generic panel */
 	dev_priv->vbt.dsi.panel_id = MIPI_DSI_GENERIC_PANEL_ID;
 }
@@ -1407,7 +1426,7 @@ static const struct vbt_header *find_vbt(void __iomem *bios, size_t size)
 int
 intel_bios_init(struct drm_i915_private *dev_priv)
 {
-	struct pci_dev *pdev = dev_priv->dev->pdev;
+	struct pci_dev *pdev = dev_priv->drm.pdev;
 	const struct vbt_header *vbt = dev_priv->opregion.vbt;
 	const struct bdb_header *bdb;
 	u8 __iomem *bios = NULL;
diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h
index ab0ea315eddb..8405b5a367d7 100644
--- a/drivers/gpu/drm/i915/intel_bios.h
+++ b/drivers/gpu/drm/i915/intel_bios.h
@@ -30,6 +30,14 @@
 #ifndef _INTEL_BIOS_H_
 #define _INTEL_BIOS_H_
 
+enum intel_backlight_type {
+	INTEL_BACKLIGHT_PMIC,
+	INTEL_BACKLIGHT_LPSS,
+	INTEL_BACKLIGHT_DISPLAY_DDI,
+	INTEL_BACKLIGHT_DSI_DCS,
+	INTEL_BACKLIGHT_PANEL_DRIVER_INTERFACE,
+};
+
 struct edp_power_seq {
 	u16 t1_t3;
 	u16 t8;
@@ -113,7 +121,13 @@ struct mipi_config {
 	u16 dual_link:2;
 	u16 lane_cnt:2;
 	u16 pixel_overlap:3;
-	u16 rsvd3:9;
+	u16 rgb_flip:1;
+#define DL_DCS_PORT_A			0x00
+#define DL_DCS_PORT_C			0x01
+#define DL_DCS_PORT_A_AND_C		0x02
+	u16 dl_dcs_cabc_ports:2;
+	u16 dl_dcs_backlight_ports:2;
+	u16 rsvd3:4;
 
 	u16 rsvd4;
 
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
new file mode 100644
index 000000000000..b074f3d6d127
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -0,0 +1,595 @@
+/*
+ * Copyright © 2015 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#include <linux/kthread.h>
+
+#include "i915_drv.h"
+
+static void intel_breadcrumbs_fake_irq(unsigned long data)
+{
+	struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
+
+	/*
+	 * The timer persists in case we cannot enable interrupts,
+	 * or if we have previously seen seqno/interrupt incoherency
+	 * ("missed interrupt" syndrome). Here the worker will wake up
+	 * every jiffie in order to kick the oldest waiter to do the
+	 * coherent seqno check.
+	 */
+	rcu_read_lock();
+	if (intel_engine_wakeup(engine))
+		mod_timer(&engine->breadcrumbs.fake_irq, jiffies + 1);
+	rcu_read_unlock();
+}
+
+static void irq_enable(struct intel_engine_cs *engine)
+{
+	/* Enabling the IRQ may miss the generation of the interrupt, but
+	 * we still need to force the barrier before reading the seqno,
+	 * just in case.
+	 */
+	engine->breadcrumbs.irq_posted = true;
+
+	spin_lock_irq(&engine->i915->irq_lock);
+	engine->irq_enable(engine);
+	spin_unlock_irq(&engine->i915->irq_lock);
+}
+
+static void irq_disable(struct intel_engine_cs *engine)
+{
+	spin_lock_irq(&engine->i915->irq_lock);
+	engine->irq_disable(engine);
+	spin_unlock_irq(&engine->i915->irq_lock);
+
+	engine->breadcrumbs.irq_posted = false;
+}
+
+static void __intel_breadcrumbs_enable_irq(struct intel_breadcrumbs *b)
+{
+	struct intel_engine_cs *engine =
+		container_of(b, struct intel_engine_cs, breadcrumbs);
+	struct drm_i915_private *i915 = engine->i915;
+
+	assert_spin_locked(&b->lock);
+	if (b->rpm_wakelock)
+		return;
+
+	/* Since we are waiting on a request, the GPU should be busy
+	 * and should have its own rpm reference. For completeness,
+	 * record an rpm reference for ourselves to cover the
+	 * interrupt we unmask.
+	 */
+	intel_runtime_pm_get_noresume(i915);
+	b->rpm_wakelock = true;
+
+	/* No interrupts? Kick the waiter every jiffie! */
+	if (intel_irqs_enabled(i915)) {
+		if (!test_bit(engine->id, &i915->gpu_error.test_irq_rings))
+			irq_enable(engine);
+		b->irq_enabled = true;
+	}
+
+	if (!b->irq_enabled ||
+	    test_bit(engine->id, &i915->gpu_error.missed_irq_rings))
+		mod_timer(&b->fake_irq, jiffies + 1);
+
+	/* Ensure that even if the GPU hangs, we get woken up.
+	 *
+	 * However, note that if no one is waiting, we never notice
+	 * a gpu hang. Eventually, we will have to wait for a resource
+	 * held by the GPU and so trigger a hangcheck. In the most
+	 * pathological case, this will be upon memory starvation!
+	 */
+	i915_queue_hangcheck(i915);
+}
+
+static void __intel_breadcrumbs_disable_irq(struct intel_breadcrumbs *b)
+{
+	struct intel_engine_cs *engine =
+		container_of(b, struct intel_engine_cs, breadcrumbs);
+
+	assert_spin_locked(&b->lock);
+	if (!b->rpm_wakelock)
+		return;
+
+	if (b->irq_enabled) {
+		irq_disable(engine);
+		b->irq_enabled = false;
+	}
+
+	intel_runtime_pm_put(engine->i915);
+	b->rpm_wakelock = false;
+}
+
+static inline struct intel_wait *to_wait(struct rb_node *node)
+{
+	return container_of(node, struct intel_wait, node);
+}
+
+static inline void __intel_breadcrumbs_finish(struct intel_breadcrumbs *b,
+					      struct intel_wait *wait)
+{
+	assert_spin_locked(&b->lock);
+
+	/* This request is completed, so remove it from the tree, mark it as
+	 * complete, and *then* wake up the associated task.
+	 */
+	rb_erase(&wait->node, &b->waiters);
+	RB_CLEAR_NODE(&wait->node);
+
+	wake_up_process(wait->tsk); /* implicit smp_wmb() */
+}
+
+static bool __intel_engine_add_wait(struct intel_engine_cs *engine,
+				    struct intel_wait *wait)
+{
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	struct rb_node **p, *parent, *completed;
+	bool first;
+	u32 seqno;
+
+	/* Insert the request into the retirement ordered list
+	 * of waiters by walking the rbtree. If we are the oldest
+	 * seqno in the tree (the first to be retired), then
+	 * set ourselves as the bottom-half.
+	 *
+	 * As we descend the tree, prune completed branches since we hold the
+	 * spinlock we know that the first_waiter must be delayed and can
+	 * reduce some of the sequential wake up latency if we take action
+	 * ourselves and wake up the completed tasks in parallel. Also, by
+	 * removing stale elements in the tree, we may be able to reduce the
+	 * ping-pong between the old bottom-half and ourselves as first-waiter.
+	 */
+	first = true;
+	parent = NULL;
+	completed = NULL;
+	seqno = intel_engine_get_seqno(engine);
+
+	 /* If the request completed before we managed to grab the spinlock,
+	  * return now before adding ourselves to the rbtree. We let the
+	  * current bottom-half handle any pending wakeups and instead
+	  * try and get out of the way quickly.
+	  */
+	if (i915_seqno_passed(seqno, wait->seqno)) {
+		RB_CLEAR_NODE(&wait->node);
+		return first;
+	}
+
+	p = &b->waiters.rb_node;
+	while (*p) {
+		parent = *p;
+		if (wait->seqno == to_wait(parent)->seqno) {
+			/* We have multiple waiters on the same seqno, select
+			 * the highest priority task (that with the smallest
+			 * task->prio) to serve as the bottom-half for this
+			 * group.
+			 */
+			if (wait->tsk->prio > to_wait(parent)->tsk->prio) {
+				p = &parent->rb_right;
+				first = false;
+			} else {
+				p = &parent->rb_left;
+			}
+		} else if (i915_seqno_passed(wait->seqno,
+					     to_wait(parent)->seqno)) {
+			p = &parent->rb_right;
+			if (i915_seqno_passed(seqno, to_wait(parent)->seqno))
+				completed = parent;
+			else
+				first = false;
+		} else {
+			p = &parent->rb_left;
+		}
+	}
+	rb_link_node(&wait->node, parent, p);
+	rb_insert_color(&wait->node, &b->waiters);
+	GEM_BUG_ON(!first && !b->irq_seqno_bh);
+
+	if (completed) {
+		struct rb_node *next = rb_next(completed);
+
+		GEM_BUG_ON(!next && !first);
+		if (next && next != &wait->node) {
+			GEM_BUG_ON(first);
+			b->first_wait = to_wait(next);
+			smp_store_mb(b->irq_seqno_bh, b->first_wait->tsk);
+			/* As there is a delay between reading the current
+			 * seqno, processing the completed tasks and selecting
+			 * the next waiter, we may have missed the interrupt
+			 * and so need for the next bottom-half to wakeup.
+			 *
+			 * Also as we enable the IRQ, we may miss the
+			 * interrupt for that seqno, so we have to wake up
+			 * the next bottom-half in order to do a coherent check
+			 * in case the seqno passed.
+			 */
+			__intel_breadcrumbs_enable_irq(b);
+			if (READ_ONCE(b->irq_posted))
+				wake_up_process(to_wait(next)->tsk);
+		}
+
+		do {
+			struct intel_wait *crumb = to_wait(completed);
+			completed = rb_prev(completed);
+			__intel_breadcrumbs_finish(b, crumb);
+		} while (completed);
+	}
+
+	if (first) {
+		GEM_BUG_ON(rb_first(&b->waiters) != &wait->node);
+		b->first_wait = wait;
+		smp_store_mb(b->irq_seqno_bh, wait->tsk);
+		/* After assigning ourselves as the new bottom-half, we must
+		 * perform a cursory check to prevent a missed interrupt.
+		 * Either we miss the interrupt whilst programming the hardware,
+		 * or if there was a previous waiter (for a later seqno) they
+		 * may be woken instead of us (due to the inherent race
+		 * in the unlocked read of b->irq_seqno_bh in the irq handler)
+		 * and so we miss the wake up.
+		 */
+		__intel_breadcrumbs_enable_irq(b);
+	}
+	GEM_BUG_ON(!b->irq_seqno_bh);
+	GEM_BUG_ON(!b->first_wait);
+	GEM_BUG_ON(rb_first(&b->waiters) != &b->first_wait->node);
+
+	return first;
+}
+
+bool intel_engine_add_wait(struct intel_engine_cs *engine,
+			   struct intel_wait *wait)
+{
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	bool first;
+
+	spin_lock(&b->lock);
+	first = __intel_engine_add_wait(engine, wait);
+	spin_unlock(&b->lock);
+
+	return first;
+}
+
+void intel_engine_enable_fake_irq(struct intel_engine_cs *engine)
+{
+	mod_timer(&engine->breadcrumbs.fake_irq, jiffies + 1);
+}
+
+static inline bool chain_wakeup(struct rb_node *rb, int priority)
+{
+	return rb && to_wait(rb)->tsk->prio <= priority;
+}
+
+static inline int wakeup_priority(struct intel_breadcrumbs *b,
+				  struct task_struct *tsk)
+{
+	if (tsk == b->signaler)
+		return INT_MIN;
+	else
+		return tsk->prio;
+}
+
+void intel_engine_remove_wait(struct intel_engine_cs *engine,
+			      struct intel_wait *wait)
+{
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+
+	/* Quick check to see if this waiter was already decoupled from
+	 * the tree by the bottom-half to avoid contention on the spinlock
+	 * by the herd.
+	 */
+	if (RB_EMPTY_NODE(&wait->node))
+		return;
+
+	spin_lock(&b->lock);
+
+	if (RB_EMPTY_NODE(&wait->node))
+		goto out_unlock;
+
+	if (b->first_wait == wait) {
+		const int priority = wakeup_priority(b, wait->tsk);
+		struct rb_node *next;
+
+		GEM_BUG_ON(b->irq_seqno_bh != wait->tsk);
+
+		/* We are the current bottom-half. Find the next candidate,
+		 * the first waiter in the queue on the remaining oldest
+		 * request. As multiple seqnos may complete in the time it
+		 * takes us to wake up and find the next waiter, we have to
+		 * wake up that waiter for it to perform its own coherent
+		 * completion check.
+		 */
+		next = rb_next(&wait->node);
+		if (chain_wakeup(next, priority)) {
+			/* If the next waiter is already complete,
+			 * wake it up and continue onto the next waiter. So
+			 * if have a small herd, they will wake up in parallel
+			 * rather than sequentially, which should reduce
+			 * the overall latency in waking all the completed
+			 * clients.
+			 *
+			 * However, waking up a chain adds extra latency to
+			 * the first_waiter. This is undesirable if that
+			 * waiter is a high priority task.
+			 */
+			u32 seqno = intel_engine_get_seqno(engine);
+
+			while (i915_seqno_passed(seqno, to_wait(next)->seqno)) {
+				struct rb_node *n = rb_next(next);
+
+				__intel_breadcrumbs_finish(b, to_wait(next));
+				next = n;
+				if (!chain_wakeup(next, priority))
+					break;
+			}
+		}
+
+		if (next) {
+			/* In our haste, we may have completed the first waiter
+			 * before we enabled the interrupt. Do so now as we
+			 * have a second waiter for a future seqno. Afterwards,
+			 * we have to wake up that waiter in case we missed
+			 * the interrupt, or if we have to handle an
+			 * exception rather than a seqno completion.
+			 */
+			b->first_wait = to_wait(next);
+			smp_store_mb(b->irq_seqno_bh, b->first_wait->tsk);
+			if (b->first_wait->seqno != wait->seqno)
+				__intel_breadcrumbs_enable_irq(b);
+			wake_up_process(b->irq_seqno_bh);
+		} else {
+			b->first_wait = NULL;
+			WRITE_ONCE(b->irq_seqno_bh, NULL);
+			__intel_breadcrumbs_disable_irq(b);
+		}
+	} else {
+		GEM_BUG_ON(rb_first(&b->waiters) == &wait->node);
+	}
+
+	GEM_BUG_ON(RB_EMPTY_NODE(&wait->node));
+	rb_erase(&wait->node, &b->waiters);
+
+out_unlock:
+	GEM_BUG_ON(b->first_wait == wait);
+	GEM_BUG_ON(rb_first(&b->waiters) !=
+		   (b->first_wait ? &b->first_wait->node : NULL));
+	GEM_BUG_ON(!b->irq_seqno_bh ^ RB_EMPTY_ROOT(&b->waiters));
+	spin_unlock(&b->lock);
+}
+
+static bool signal_complete(struct drm_i915_gem_request *request)
+{
+	if (!request)
+		return false;
+
+	/* If another process served as the bottom-half it may have already
+	 * signalled that this wait is already completed.
+	 */
+	if (intel_wait_complete(&request->signaling.wait))
+		return true;
+
+	/* Carefully check if the request is complete, giving time for the
+	 * seqno to be visible or if the GPU hung.
+	 */
+	if (__i915_request_irq_complete(request))
+		return true;
+
+	return false;
+}
+
+static struct drm_i915_gem_request *to_signaler(struct rb_node *rb)
+{
+	return container_of(rb, struct drm_i915_gem_request, signaling.node);
+}
+
+static void signaler_set_rtpriority(void)
+{
+	 struct sched_param param = { .sched_priority = 1 };
+
+	 sched_setscheduler_nocheck(current, SCHED_FIFO, &param);
+}
+
+static int intel_breadcrumbs_signaler(void *arg)
+{
+	struct intel_engine_cs *engine = arg;
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	struct drm_i915_gem_request *request;
+
+	/* Install ourselves with high priority to reduce signalling latency */
+	signaler_set_rtpriority();
+
+	do {
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		/* We are either woken up by the interrupt bottom-half,
+		 * or by a client adding a new signaller. In both cases,
+		 * the GPU seqno may have advanced beyond our oldest signal.
+		 * If it has, propagate the signal, remove the waiter and
+		 * check again with the next oldest signal. Otherwise we
+		 * need to wait for a new interrupt from the GPU or for
+		 * a new client.
+		 */
+		request = READ_ONCE(b->first_signal);
+		if (signal_complete(request)) {
+			/* Wake up all other completed waiters and select the
+			 * next bottom-half for the next user interrupt.
+			 */
+			intel_engine_remove_wait(engine,
+						 &request->signaling.wait);
+
+			/* Find the next oldest signal. Note that as we have
+			 * not been holding the lock, another client may
+			 * have installed an even older signal than the one
+			 * we just completed - so double check we are still
+			 * the oldest before picking the next one.
+			 */
+			spin_lock(&b->lock);
+			if (request == b->first_signal) {
+				struct rb_node *rb =
+					rb_next(&request->signaling.node);
+				b->first_signal = rb ? to_signaler(rb) : NULL;
+			}
+			rb_erase(&request->signaling.node, &b->signals);
+			spin_unlock(&b->lock);
+
+			i915_gem_request_unreference(request);
+		} else {
+			if (kthread_should_stop())
+				break;
+
+			schedule();
+		}
+	} while (1);
+	__set_current_state(TASK_RUNNING);
+
+	return 0;
+}
+
+void intel_engine_enable_signaling(struct drm_i915_gem_request *request)
+{
+	struct intel_engine_cs *engine = request->engine;
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	struct rb_node *parent, **p;
+	bool first, wakeup;
+
+	if (unlikely(READ_ONCE(request->signaling.wait.tsk)))
+		return;
+
+	spin_lock(&b->lock);
+	if (unlikely(request->signaling.wait.tsk)) {
+		wakeup = false;
+		goto unlock;
+	}
+
+	request->signaling.wait.tsk = b->signaler;
+	request->signaling.wait.seqno = request->seqno;
+	i915_gem_request_reference(request);
+
+	/* First add ourselves into the list of waiters, but register our
+	 * bottom-half as the signaller thread. As per usual, only the oldest
+	 * waiter (not just signaller) is tasked as the bottom-half waking
+	 * up all completed waiters after the user interrupt.
+	 *
+	 * If we are the oldest waiter, enable the irq (after which we
+	 * must double check that the seqno did not complete).
+	 */
+	wakeup = __intel_engine_add_wait(engine, &request->signaling.wait);
+
+	/* Now insert ourselves into the retirement ordered list of signals
+	 * on this engine. We track the oldest seqno as that will be the
+	 * first signal to complete.
+	 */
+	parent = NULL;
+	first = true;
+	p = &b->signals.rb_node;
+	while (*p) {
+		parent = *p;
+		if (i915_seqno_passed(request->seqno,
+				      to_signaler(parent)->seqno)) {
+			p = &parent->rb_right;
+			first = false;
+		} else {
+			p = &parent->rb_left;
+		}
+	}
+	rb_link_node(&request->signaling.node, parent, p);
+	rb_insert_color(&request->signaling.node, &b->signals);
+	if (first)
+		smp_store_mb(b->first_signal, request);
+
+unlock:
+	spin_unlock(&b->lock);
+
+	if (wakeup)
+		wake_up_process(b->signaler);
+}
+
+int intel_engine_init_breadcrumbs(struct intel_engine_cs *engine)
+{
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	struct task_struct *tsk;
+
+	spin_lock_init(&b->lock);
+	setup_timer(&b->fake_irq,
+		    intel_breadcrumbs_fake_irq,
+		    (unsigned long)engine);
+
+	/* Spawn a thread to provide a common bottom-half for all signals.
+	 * As this is an asynchronous interface we cannot steal the current
+	 * task for handling the bottom-half to the user interrupt, therefore
+	 * we create a thread to do the coherent seqno dance after the
+	 * interrupt and then signal the waitqueue (via the dma-buf/fence).
+	 */
+	tsk = kthread_run(intel_breadcrumbs_signaler, engine,
+			  "i915/signal:%d", engine->id);
+	if (IS_ERR(tsk))
+		return PTR_ERR(tsk);
+
+	b->signaler = tsk;
+
+	return 0;
+}
+
+void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine)
+{
+	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+
+	if (!IS_ERR_OR_NULL(b->signaler))
+		kthread_stop(b->signaler);
+
+	del_timer_sync(&b->fake_irq);
+}
+
+unsigned int intel_kick_waiters(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	unsigned int mask = 0;
+
+	/* To avoid the task_struct disappearing beneath us as we wake up
+	 * the process, we must first inspect the task_struct->state under the
+	 * RCU lock, i.e. as we call wake_up_process() we must be holding the
+	 * rcu_read_lock().
+	 */
+	rcu_read_lock();
+	for_each_engine(engine, i915)
+		if (unlikely(intel_engine_wakeup(engine)))
+			mask |= intel_engine_flag(engine);
+	rcu_read_unlock();
+
+	return mask;
+}
+
+unsigned int intel_kick_signalers(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	unsigned int mask = 0;
+
+	for_each_engine(engine, i915) {
+		if (unlikely(READ_ONCE(engine->breadcrumbs.first_signal))) {
+			wake_up_process(engine->breadcrumbs.signaler);
+			mask |= intel_engine_flag(engine);
+		}
+	}
+
+	return mask;
+}
diff --git a/drivers/gpu/drm/i915/intel_color.c b/drivers/gpu/drm/i915/intel_color.c
index 1b3f97449395..bc0fef3d3335 100644
--- a/drivers/gpu/drm/i915/intel_color.c
+++ b/drivers/gpu/drm/i915/intel_color.c
@@ -96,7 +96,7 @@ static void i9xx_load_csc_matrix(struct drm_crtc_state *crtc_state)
 {
 	struct drm_crtc *crtc = crtc_state->crtc;
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int i, pipe = intel_crtc->pipe;
 	uint16_t coeffs[9] = { 0, };
@@ -207,7 +207,7 @@ static void cherryview_load_csc_matrix(struct drm_crtc_state *state)
 {
 	struct drm_crtc *crtc = state->crtc;
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = to_intel_crtc(crtc)->pipe;
 	uint32_t mode;
 
@@ -255,7 +255,7 @@ static void cherryview_load_csc_matrix(struct drm_crtc_state *state)
 void intel_color_set_csc(struct drm_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc_state->crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (dev_priv->display.load_csc_matrix)
 		dev_priv->display.load_csc_matrix(crtc_state);
@@ -266,13 +266,13 @@ static void i9xx_load_luts_internal(struct drm_crtc *crtc,
 				    struct drm_property_blob *blob)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum pipe pipe = intel_crtc->pipe;
 	int i;
 
 	if (HAS_GMCH_DISPLAY(dev)) {
-		if (intel_crtc->config->has_dsi_encoder)
+		if (intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_DSI))
 			assert_dsi_pll_enabled(dev_priv);
 		else
 			assert_pll_enabled(dev_priv, pipe);
@@ -313,7 +313,7 @@ static void haswell_load_luts(struct drm_crtc_state *crtc_state)
 {
 	struct drm_crtc *crtc = crtc_state->crtc;
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_crtc_state *intel_crtc_state =
 		to_intel_crtc_state(crtc_state);
@@ -343,7 +343,7 @@ static void broadwell_load_luts(struct drm_crtc_state *state)
 {
 	struct drm_crtc *crtc = state->crtc;
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc_state *intel_state = to_intel_crtc_state(state);
 	enum pipe pipe = to_intel_crtc(crtc)->pipe;
 	uint32_t i, lut_size = INTEL_INFO(dev)->color.degamma_lut_size;
@@ -426,7 +426,7 @@ static void cherryview_load_luts(struct drm_crtc_state *state)
 {
 	struct drm_crtc *crtc = state->crtc;
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = to_intel_crtc(crtc)->pipe;
 	struct drm_color_lut *lut;
 	uint32_t i, lut_size;
@@ -485,7 +485,7 @@ static void cherryview_load_luts(struct drm_crtc_state *state)
 void intel_color_load_luts(struct drm_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc_state->crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	dev_priv->display.load_luts(crtc_state);
 }
@@ -526,7 +526,7 @@ int intel_color_check(struct drm_crtc *crtc,
 void intel_color_init(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	drm_mode_crtc_set_gamma_size(crtc, 256);
 
@@ -547,7 +547,8 @@ void intel_color_init(struct drm_crtc *crtc)
 	/* Enable color management support when we have degamma & gamma LUTs. */
 	if (INTEL_INFO(dev)->color.degamma_lut_size != 0 &&
 	    INTEL_INFO(dev)->color.gamma_lut_size != 0)
-		drm_helper_crtc_enable_color_mgmt(crtc,
+		drm_crtc_enable_color_mgmt(crtc,
 					INTEL_INFO(dev)->color.degamma_lut_size,
+					true,
 					INTEL_INFO(dev)->color.gamma_lut_size);
 }
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 3fbb6fc66451..827b6ef4e9ae 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -67,7 +67,7 @@ static bool intel_crt_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
@@ -98,7 +98,7 @@ out:
 
 static unsigned int intel_crt_get_flags(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
 	u32 tmp, flags = 0;
 
@@ -146,7 +146,7 @@ static void hsw_crt_get_config(struct intel_encoder *encoder,
 static void intel_crt_set_dpms(struct intel_encoder *encoder, int mode)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
@@ -281,7 +281,7 @@ static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	struct intel_crt *crt = intel_attached_crt(connector);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 adpa;
 	bool ret;
 
@@ -301,8 +301,10 @@ static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
 
 		I915_WRITE(crt->adpa_reg, adpa);
 
-		if (wait_for((I915_READ(crt->adpa_reg) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) == 0,
-			     1000))
+		if (intel_wait_for_register(dev_priv,
+					    crt->adpa_reg,
+					    ADPA_CRT_HOTPLUG_FORCE_TRIGGER, 0,
+					    1000))
 			DRM_DEBUG_KMS("timed out waiting for FORCE_TRIGGER");
 
 		if (turn_off_dac) {
@@ -326,11 +328,26 @@ static bool valleyview_crt_detect_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	struct intel_crt *crt = intel_attached_crt(connector);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	bool reenable_hpd;
 	u32 adpa;
 	bool ret;
 	u32 save_adpa;
 
+	/*
+	 * Doing a force trigger causes a hpd interrupt to get sent, which can
+	 * get us stuck in a loop if we're polling:
+	 *  - We enable power wells and reset the ADPA
+	 *  - output_poll_exec does force probe on VGA, triggering a hpd
+	 *  - HPD handler waits for poll to unlock dev->mode_config.mutex
+	 *  - output_poll_exec shuts off the ADPA, unlocks
+	 *    dev->mode_config.mutex
+	 *  - HPD handler runs, resets ADPA and brings us back to the start
+	 *
+	 * Just disable HPD interrupts here to prevent this
+	 */
+	reenable_hpd = intel_hpd_disable(dev_priv, crt->base.hpd_pin);
+
 	save_adpa = adpa = I915_READ(crt->adpa_reg);
 	DRM_DEBUG_KMS("trigger hotplug detect cycle: adpa=0x%x\n", adpa);
 
@@ -338,8 +355,10 @@ static bool valleyview_crt_detect_hotplug(struct drm_connector *connector)
 
 	I915_WRITE(crt->adpa_reg, adpa);
 
-	if (wait_for((I915_READ(crt->adpa_reg) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) == 0,
-		     1000)) {
+	if (intel_wait_for_register(dev_priv,
+				    crt->adpa_reg,
+				    ADPA_CRT_HOTPLUG_FORCE_TRIGGER, 0,
+				    1000)) {
 		DRM_DEBUG_KMS("timed out waiting for FORCE_TRIGGER");
 		I915_WRITE(crt->adpa_reg, save_adpa);
 	}
@@ -353,6 +372,9 @@ static bool valleyview_crt_detect_hotplug(struct drm_connector *connector)
 
 	DRM_DEBUG_KMS("valleyview hotplug adpa=0x%x, result %d\n", adpa, ret);
 
+	if (reenable_hpd)
+		intel_hpd_enable(dev_priv, crt->base.hpd_pin);
+
 	return ret;
 }
 
@@ -367,7 +389,7 @@ static bool valleyview_crt_detect_hotplug(struct drm_connector *connector)
 static bool intel_crt_detect_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 stat;
 	bool ret = false;
 	int i, tries = 0;
@@ -394,9 +416,9 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector)
 					      CRT_HOTPLUG_FORCE_DETECT,
 					      CRT_HOTPLUG_FORCE_DETECT);
 		/* wait for FORCE_DETECT to go off */
-		if (wait_for((I915_READ(PORT_HOTPLUG_EN) &
-			      CRT_HOTPLUG_FORCE_DETECT) == 0,
-			     1000))
+		if (intel_wait_for_register(dev_priv, PORT_HOTPLUG_EN,
+					    CRT_HOTPLUG_FORCE_DETECT, 0,
+					    1000))
 			DRM_DEBUG_KMS("timed out waiting for FORCE_DETECT to go off");
 	}
 
@@ -449,7 +471,7 @@ static int intel_crt_ddc_get_modes(struct drm_connector *connector,
 static bool intel_crt_detect_ddc(struct drm_connector *connector)
 {
 	struct intel_crt *crt = intel_attached_crt(connector);
-	struct drm_i915_private *dev_priv = crt->base.base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crt->base.base.dev);
 	struct edid *edid;
 	struct i2c_adapter *i2c;
 
@@ -485,7 +507,7 @@ static enum drm_connector_status
 intel_crt_load_detect(struct intel_crt *crt, uint32_t pipe)
 {
 	struct drm_device *dev = crt->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t save_bclrpat;
 	uint32_t save_vtotal;
 	uint32_t vtotal, vactive;
@@ -600,7 +622,7 @@ static enum drm_connector_status
 intel_crt_detect(struct drm_connector *connector, bool force)
 {
 	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crt *crt = intel_attached_crt(connector);
 	struct intel_encoder *intel_encoder = &crt->base;
 	enum intel_display_power_domain power_domain;
@@ -681,7 +703,7 @@ static void intel_crt_destroy(struct drm_connector *connector)
 static int intel_crt_get_modes(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crt *crt = intel_attached_crt(connector);
 	struct intel_encoder *intel_encoder = &crt->base;
 	enum intel_display_power_domain power_domain;
@@ -713,11 +735,11 @@ static int intel_crt_set_property(struct drm_connector *connector,
 	return 0;
 }
 
-static void intel_crt_reset(struct drm_connector *connector)
+void intel_crt_reset(struct drm_encoder *encoder)
 {
-	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct drm_device *dev = encoder->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_crt *crt = intel_encoder_to_crt(to_intel_encoder(encoder));
 
 	if (INTEL_INFO(dev)->gen >= 5) {
 		u32 adpa;
@@ -739,10 +761,11 @@ static void intel_crt_reset(struct drm_connector *connector)
  */
 
 static const struct drm_connector_funcs intel_crt_connector_funcs = {
-	.reset = intel_crt_reset,
 	.dpms = drm_atomic_helper_connector_dpms,
 	.detect = intel_crt_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
 	.destroy = intel_crt_destroy,
 	.set_property = intel_crt_set_property,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
@@ -753,10 +776,10 @@ static const struct drm_connector_funcs intel_crt_connector_funcs = {
 static const struct drm_connector_helper_funcs intel_crt_connector_helper_funcs = {
 	.mode_valid = intel_crt_mode_valid,
 	.get_modes = intel_crt_get_modes,
-	.best_encoder = intel_best_encoder,
 };
 
 static const struct drm_encoder_funcs intel_crt_enc_funcs = {
+	.reset = intel_crt_reset,
 	.destroy = intel_encoder_destroy,
 };
 
@@ -791,7 +814,7 @@ void intel_crt_init(struct drm_device *dev)
 	struct drm_connector *connector;
 	struct intel_crt *crt;
 	struct intel_connector *intel_connector;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t adpa_reg;
 	u32 adpa;
 
@@ -839,7 +862,7 @@ void intel_crt_init(struct drm_device *dev)
 			   &intel_crt_connector_funcs, DRM_MODE_CONNECTOR_VGA);
 
 	drm_encoder_init(dev, &crt->base.base, &intel_crt_enc_funcs,
-			 DRM_MODE_ENCODER_DAC, NULL);
+			 DRM_MODE_ENCODER_DAC, "CRT");
 
 	intel_connector_attach_encoder(intel_connector, &crt->base);
 
@@ -876,12 +899,9 @@ void intel_crt_init(struct drm_device *dev)
 		crt->base.get_hw_state = intel_crt_get_hw_state;
 	}
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
-	intel_connector->unregister = intel_connector_unregister;
 
 	drm_connector_helper_add(connector, &intel_crt_connector_helper_funcs);
 
-	drm_connector_register(connector);
-
 	if (!I915_HAS_HOTPLUG(dev))
 		intel_connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 
@@ -902,5 +922,5 @@ void intel_crt_init(struct drm_device *dev)
 		dev_priv->fdi_rx_config = I915_READ(FDI_RX_CTL(PIPE_A)) & fdi_config;
 	}
 
-	intel_crt_reset(connector);
+	intel_crt_reset(&crt->base.base);
 }
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 2b3b428d9cd2..3edb9580928e 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -286,7 +286,7 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv,
 	uint32_t dmc_offset = CSR_DEFAULT_FW_OFFSET, readcount = 0, nbytes;
 	uint32_t i;
 	uint32_t *dmc_payload;
-	uint32_t required_min_version;
+	uint32_t required_version;
 
 	if (!fw)
 		return NULL;
@@ -303,24 +303,23 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv,
 	csr->version = css_header->version;
 
 	if (IS_KABYLAKE(dev_priv)) {
-		required_min_version = KBL_CSR_VERSION_REQUIRED;
+		required_version = KBL_CSR_VERSION_REQUIRED;
 	} else if (IS_SKYLAKE(dev_priv)) {
-		required_min_version = SKL_CSR_VERSION_REQUIRED;
+		required_version = SKL_CSR_VERSION_REQUIRED;
 	} else if (IS_BROXTON(dev_priv)) {
-		required_min_version = BXT_CSR_VERSION_REQUIRED;
+		required_version = BXT_CSR_VERSION_REQUIRED;
 	} else {
 		MISSING_CASE(INTEL_REVID(dev_priv));
-		required_min_version = 0;
+		required_version = 0;
 	}
 
-	if (csr->version < required_min_version) {
-		DRM_INFO("Refusing to load old DMC firmware v%u.%u,"
-			 " please upgrade to v%u.%u or later"
-			   " [" FIRMWARE_URL "].\n",
+	if (csr->version != required_version) {
+		DRM_INFO("Refusing to load DMC firmware v%u.%u,"
+			 " please use v%u.%u [" FIRMWARE_URL "].\n",
 			 CSR_VERSION_MAJOR(csr->version),
 			 CSR_VERSION_MINOR(csr->version),
-			 CSR_VERSION_MAJOR(required_min_version),
-			 CSR_VERSION_MINOR(required_min_version));
+			 CSR_VERSION_MAJOR(required_version),
+			 CSR_VERSION_MINOR(required_version));
 		return NULL;
 	}
 
@@ -413,7 +412,7 @@ static void csr_load_work_fn(struct work_struct *work)
 	csr = &dev_priv->csr;
 
 	ret = request_firmware(&fw, dev_priv->csr.fw_path,
-			       &dev_priv->dev->pdev->dev);
+			       &dev_priv->drm.pdev->dev);
 	if (fw)
 		dev_priv->csr.dmc_payload = parse_csr_fw(dev_priv, fw);
 
@@ -427,7 +426,7 @@ static void csr_load_work_fn(struct work_struct *work)
 			 CSR_VERSION_MAJOR(csr->version),
 			 CSR_VERSION_MINOR(csr->version));
 	} else {
-		dev_notice(dev_priv->dev->dev,
+		dev_notice(dev_priv->drm.dev,
 			   "Failed to load DMC firmware"
 			   " [" FIRMWARE_URL "],"
 			   " disabling runtime power management.\n");
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 01e523df363b..dd1d6fe12297 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -318,7 +318,7 @@ static void ddi_get_encoder_port(struct intel_encoder *intel_encoder,
 	default:
 		WARN(1, "Invalid DDI encoder type %d\n", intel_encoder->type);
 		/* fallthrough and treat as unknown */
-	case INTEL_OUTPUT_DISPLAYPORT:
+	case INTEL_OUTPUT_DP:
 	case INTEL_OUTPUT_EDP:
 	case INTEL_OUTPUT_HDMI:
 	case INTEL_OUTPUT_UNKNOWN:
@@ -482,7 +482,7 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder)
 		ddi_translations = ddi_translations_edp;
 		size = n_edp_entries;
 		break;
-	case INTEL_OUTPUT_DISPLAYPORT:
+	case INTEL_OUTPUT_DP:
 	case INTEL_OUTPUT_HDMI:
 		ddi_translations = ddi_translations_dp;
 		size = n_dp_entries;
@@ -543,7 +543,7 @@ static void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv,
 void hsw_fdi_link_train(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	u32 temp, i, rx_ctl_val;
@@ -834,7 +834,7 @@ static void ddi_dotclock_get(struct intel_crtc_state *pipe_config)
 	if (pipe_config->has_pch_encoder)
 		dotclock = intel_dotclock_calculate(pipe_config->port_clock,
 						    &pipe_config->fdi_m_n);
-	else if (pipe_config->has_dp_encoder)
+	else if (intel_crtc_has_dp_encoder(pipe_config))
 		dotclock = intel_dotclock_calculate(pipe_config->port_clock,
 						    &pipe_config->dp_m_n);
 	else if (pipe_config->has_hdmi_sink && pipe_config->pipe_bpp == 36)
@@ -851,7 +851,7 @@ static void ddi_dotclock_get(struct intel_crtc_state *pipe_config)
 static void skl_ddi_clock_get(struct intel_encoder *encoder,
 				struct intel_crtc_state *pipe_config)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	int link_clock = 0;
 	uint32_t dpll_ctl1, dpll;
 
@@ -899,7 +899,7 @@ static void skl_ddi_clock_get(struct intel_encoder *encoder,
 static void hsw_ddi_clock_get(struct intel_encoder *encoder,
 			      struct intel_crtc_state *pipe_config)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	int link_clock = 0;
 	u32 val, pll;
 
@@ -948,7 +948,7 @@ static int bxt_calc_pll_link(struct drm_i915_private *dev_priv,
 {
 	struct intel_shared_dpll *pll;
 	struct intel_dpll_hw_state *state;
-	intel_clock_t clock;
+	struct dpll clock;
 
 	/* For DDI ports we always use a shared PLL. */
 	if (WARN_ON(dpll == DPLL_ID_PRIVATE))
@@ -971,7 +971,7 @@ static int bxt_calc_pll_link(struct drm_i915_private *dev_priv,
 static void bxt_ddi_clock_get(struct intel_encoder *encoder,
 				struct intel_crtc_state *pipe_config)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum port port = intel_ddi_get_encoder_port(encoder);
 	uint32_t dpll = port;
 
@@ -1061,14 +1061,14 @@ bool intel_ddi_pll_select(struct intel_crtc *intel_crtc,
 
 void intel_ddi_set_pipe_settings(struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc);
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
 	int type = intel_encoder->type;
 	uint32_t temp;
 
-	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP || type == INTEL_OUTPUT_DP_MST) {
+	if (type == INTEL_OUTPUT_DP || type == INTEL_OUTPUT_EDP || type == INTEL_OUTPUT_DP_MST) {
 		WARN_ON(transcoder_is_dsi(cpu_transcoder));
 
 		temp = TRANS_MSA_SYNC_CLK;
@@ -1096,7 +1096,7 @@ void intel_ddi_set_vc_payload_alloc(struct drm_crtc *crtc, bool state)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
 	uint32_t temp;
 	temp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
@@ -1113,7 +1113,7 @@ void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc)
 	struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc);
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = intel_crtc->pipe;
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
 	enum port port = intel_ddi_get_encoder_port(intel_encoder);
@@ -1182,7 +1182,7 @@ void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc)
 		temp |= TRANS_DDI_MODE_SELECT_FDI;
 		temp |= (intel_crtc->config->fdi_lanes - 1) << 1;
 
-	} else if (type == INTEL_OUTPUT_DISPLAYPORT ||
+	} else if (type == INTEL_OUTPUT_DP ||
 		   type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
@@ -1223,7 +1223,7 @@ void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
 bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector)
 {
 	struct drm_device *dev = intel_connector->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *intel_encoder = intel_connector->encoder;
 	int type = intel_connector->base.connector_type;
 	enum port port = intel_ddi_get_encoder_port(intel_encoder);
@@ -1285,7 +1285,7 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 			    enum pipe *pipe)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_ddi_get_encoder_port(encoder);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
@@ -1342,6 +1342,14 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 	DRM_DEBUG_KMS("No pipe for ddi port %c found\n", port_name(port));
 
 out:
+	if (ret && IS_BROXTON(dev_priv)) {
+		tmp = I915_READ(BXT_PHY_CTL(port));
+		if ((tmp & (BXT_PHY_LANE_POWERDOWN_ACK |
+			    BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED)
+			DRM_ERROR("Port %c enabled but PHY powered down? "
+				  "(PHY_CTL %08x)\n", port_name(port), tmp);
+	}
+
 	intel_display_power_put(dev_priv, power_domain);
 
 	return ret;
@@ -1351,7 +1359,7 @@ void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc)
 {
 	struct drm_crtc *crtc = &intel_crtc->base;
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc);
 	enum port port = intel_ddi_get_encoder_port(intel_encoder);
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
@@ -1363,7 +1371,7 @@ void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc)
 
 void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc)
 {
-	struct drm_i915_private *dev_priv = intel_crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
 
 	if (cpu_transcoder != TRANSCODER_EDP)
@@ -1384,7 +1392,7 @@ static void skl_ddi_set_iboost(struct drm_i915_private *dev_priv,
 	dp_iboost = dev_priv->vbt.ddi_port_info[port].dp_boost_level;
 	hdmi_iboost = dev_priv->vbt.ddi_port_info[port].hdmi_boost_level;
 
-	if (type == INTEL_OUTPUT_DISPLAYPORT) {
+	if (type == INTEL_OUTPUT_DP) {
 		if (dp_iboost) {
 			iboost = dp_iboost;
 		} else {
@@ -1442,7 +1450,7 @@ static void bxt_ddi_vswing_sequence(struct drm_i915_private *dev_priv,
 	if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) {
 		n_entries = ARRAY_SIZE(bxt_ddi_translations_edp);
 		ddi_translations = bxt_ddi_translations_edp;
-	} else if (type == INTEL_OUTPUT_DISPLAYPORT
+	} else if (type == INTEL_OUTPUT_DP
 			|| type == INTEL_OUTPUT_EDP) {
 		n_entries = ARRAY_SIZE(bxt_ddi_translations_dp);
 		ddi_translations = bxt_ddi_translations_dp;
@@ -1616,7 +1624,7 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder)
 
 	intel_ddi_clk_select(intel_encoder, crtc->config);
 
-	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
+	if (type == INTEL_OUTPUT_DP || type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		intel_dp_set_link_params(intel_dp, crtc->config);
@@ -1640,7 +1648,7 @@ static void intel_ddi_post_disable(struct intel_encoder *intel_encoder)
 {
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_ddi_get_encoder_port(intel_encoder);
 	int type = intel_encoder->type;
 	uint32_t val;
@@ -1661,7 +1669,7 @@ static void intel_ddi_post_disable(struct intel_encoder *intel_encoder)
 	if (wait)
 		intel_wait_ddi_buf_idle(dev_priv, port);
 
-	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
+	if (type == INTEL_OUTPUT_DP || type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
 		intel_edp_panel_vdd_on(intel_dp);
@@ -1687,7 +1695,7 @@ static void intel_enable_ddi(struct intel_encoder *intel_encoder)
 	struct drm_crtc *crtc = encoder->crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_ddi_get_encoder_port(intel_encoder);
 	int type = intel_encoder->type;
 
@@ -1726,7 +1734,7 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int type = intel_encoder->type;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (intel_crtc->config->has_audio) {
 		intel_audio_codec_disable(intel_encoder);
@@ -1742,9 +1750,11 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder)
 	}
 }
 
-static bool broxton_phy_is_enabled(struct drm_i915_private *dev_priv,
-				   enum dpio_phy phy)
+bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv,
+			    enum dpio_phy phy)
 {
+	enum port port;
+
 	if (!(I915_READ(BXT_P_CR_GT_DISP_PWRON) & GT_DISPLAY_POWER_ON(phy)))
 		return false;
 
@@ -1770,38 +1780,51 @@ static bool broxton_phy_is_enabled(struct drm_i915_private *dev_priv,
 		return false;
 	}
 
+	for_each_port_masked(port,
+			     phy == DPIO_PHY0 ? BIT(PORT_B) | BIT(PORT_C) :
+						BIT(PORT_A)) {
+		u32 tmp = I915_READ(BXT_PHY_CTL(port));
+
+		if (tmp & BXT_PHY_CMNLANE_POWERDOWN_ACK) {
+			DRM_DEBUG_DRIVER("DDI PHY %d powered, but common lane "
+					 "for port %c powered down "
+					 "(PHY_CTL %08x)\n",
+					 phy, port_name(port), tmp);
+
+			return false;
+		}
+	}
+
 	return true;
 }
 
-static u32 broxton_get_grc(struct drm_i915_private *dev_priv, enum dpio_phy phy)
+static u32 bxt_get_grc(struct drm_i915_private *dev_priv, enum dpio_phy phy)
 {
 	u32 val = I915_READ(BXT_PORT_REF_DW6(phy));
 
 	return (val & GRC_CODE_MASK) >> GRC_CODE_SHIFT;
 }
 
-static void broxton_phy_wait_grc_done(struct drm_i915_private *dev_priv,
-				      enum dpio_phy phy)
+static void bxt_phy_wait_grc_done(struct drm_i915_private *dev_priv,
+				  enum dpio_phy phy)
 {
-	if (wait_for(I915_READ(BXT_PORT_REF_DW3(phy)) & GRC_DONE, 10))
+	if (intel_wait_for_register(dev_priv,
+				    BXT_PORT_REF_DW3(phy),
+				    GRC_DONE, GRC_DONE,
+				    10))
 		DRM_ERROR("timeout waiting for PHY%d GRC\n", phy);
 }
 
-static bool broxton_phy_verify_state(struct drm_i915_private *dev_priv,
-				     enum dpio_phy phy);
-
-static void broxton_phy_init(struct drm_i915_private *dev_priv,
-			     enum dpio_phy phy)
+void bxt_ddi_phy_init(struct drm_i915_private *dev_priv, enum dpio_phy phy)
 {
-	enum port port;
-	u32 ports, val;
+	u32 val;
 
-	if (broxton_phy_is_enabled(dev_priv, phy)) {
+	if (bxt_ddi_phy_is_enabled(dev_priv, phy)) {
 		/* Still read out the GRC value for state verification */
 		if (phy == DPIO_PHY0)
-			dev_priv->bxt_phy_grc = broxton_get_grc(dev_priv, phy);
+			dev_priv->bxt_phy_grc = bxt_get_grc(dev_priv, phy);
 
-		if (broxton_phy_verify_state(dev_priv, phy)) {
+		if (bxt_ddi_phy_verify_state(dev_priv, phy)) {
 			DRM_DEBUG_DRIVER("DDI PHY %d already enabled, "
 					 "won't reprogram it\n", phy);
 
@@ -1810,8 +1833,6 @@ static void broxton_phy_init(struct drm_i915_private *dev_priv,
 
 		DRM_DEBUG_DRIVER("DDI PHY %d enabled with invalid state, "
 				 "force reprogramming it\n", phy);
-	} else {
-		DRM_DEBUG_DRIVER("DDI PHY %d not enabled, enabling it\n", phy);
 	}
 
 	val = I915_READ(BXT_P_CR_GT_DISP_PWRON);
@@ -1831,28 +1852,6 @@ static void broxton_phy_init(struct drm_i915_private *dev_priv,
 		DRM_ERROR("timeout during PHY%d power on\n", phy);
 	}
 
-	if (phy == DPIO_PHY0)
-		ports = BIT(PORT_B) | BIT(PORT_C);
-	else
-		ports = BIT(PORT_A);
-
-	for_each_port_masked(port, ports) {
-		int lane;
-
-		for (lane = 0; lane < 4; lane++) {
-			val = I915_READ(BXT_PORT_TX_DW14_LN(port, lane));
-			/*
-			 * Note that on CHV this flag is called UPAR, but has
-			 * the same function.
-			 */
-			val &= ~LATENCY_OPTIM;
-			if (lane != 1)
-				val |= LATENCY_OPTIM;
-
-			I915_WRITE(BXT_PORT_TX_DW14_LN(port, lane), val);
-		}
-	}
-
 	/* Program PLL Rcomp code offset */
 	val = I915_READ(BXT_PORT_CL1CM_DW9(phy));
 	val &= ~IREF0RC_OFFSET_MASK;
@@ -1899,10 +1898,7 @@ static void broxton_phy_init(struct drm_i915_private *dev_priv,
 		 * the corresponding calibrated value from PHY1, and disable
 		 * the automatic calibration on PHY0.
 		 */
-		broxton_phy_wait_grc_done(dev_priv, DPIO_PHY1);
-
-		val = dev_priv->bxt_phy_grc = broxton_get_grc(dev_priv,
-							      DPIO_PHY1);
+		val = dev_priv->bxt_phy_grc = bxt_get_grc(dev_priv, DPIO_PHY1);
 		grc_code = val << GRC_CODE_FAST_SHIFT |
 			   val << GRC_CODE_SLOW_SHIFT |
 			   val;
@@ -1912,31 +1908,16 @@ static void broxton_phy_init(struct drm_i915_private *dev_priv,
 		val |= GRC_DIS | GRC_RDY_OVRD;
 		I915_WRITE(BXT_PORT_REF_DW8(DPIO_PHY0), val);
 	}
-	/*
-	 * During PHY1 init delay waiting for GRC calibration to finish, since
-	 * it can happen in parallel with the subsequent PHY0 init.
-	 */
 
 	val = I915_READ(BXT_PHY_CTL_FAMILY(phy));
 	val |= COMMON_RESET_DIS;
 	I915_WRITE(BXT_PHY_CTL_FAMILY(phy), val);
-}
-
-void broxton_ddi_phy_init(struct drm_i915_private *dev_priv)
-{
-	/* Enable PHY1 first since it provides Rcomp for PHY0 */
-	broxton_phy_init(dev_priv, DPIO_PHY1);
-	broxton_phy_init(dev_priv, DPIO_PHY0);
 
-	/*
-	 * If BIOS enabled only PHY0 and not PHY1, we skipped waiting for the
-	 * PHY1 GRC calibration to finish, so wait for it here.
-	 */
-	broxton_phy_wait_grc_done(dev_priv, DPIO_PHY1);
+	if (phy == DPIO_PHY1)
+		bxt_phy_wait_grc_done(dev_priv, DPIO_PHY1);
 }
 
-static void broxton_phy_uninit(struct drm_i915_private *dev_priv,
-			       enum dpio_phy phy)
+void bxt_ddi_phy_uninit(struct drm_i915_private *dev_priv, enum dpio_phy phy)
 {
 	uint32_t val;
 
@@ -1949,12 +1930,6 @@ static void broxton_phy_uninit(struct drm_i915_private *dev_priv,
 	I915_WRITE(BXT_P_CR_GT_DISP_PWRON, val);
 }
 
-void broxton_ddi_phy_uninit(struct drm_i915_private *dev_priv)
-{
-	broxton_phy_uninit(dev_priv, DPIO_PHY1);
-	broxton_phy_uninit(dev_priv, DPIO_PHY0);
-}
-
 static bool __printf(6, 7)
 __phy_reg_verify_state(struct drm_i915_private *dev_priv, enum dpio_phy phy,
 		       i915_reg_t reg, u32 mask, u32 expected,
@@ -1982,11 +1957,9 @@ __phy_reg_verify_state(struct drm_i915_private *dev_priv, enum dpio_phy phy,
 	return false;
 }
 
-static bool broxton_phy_verify_state(struct drm_i915_private *dev_priv,
-				     enum dpio_phy phy)
+bool bxt_ddi_phy_verify_state(struct drm_i915_private *dev_priv,
+			      enum dpio_phy phy)
 {
-	enum port port;
-	u32 ports;
 	uint32_t mask;
 	bool ok;
 
@@ -1994,27 +1967,11 @@ static bool broxton_phy_verify_state(struct drm_i915_private *dev_priv,
 	__phy_reg_verify_state(dev_priv, phy, reg, mask, exp, fmt,	\
 			       ## __VA_ARGS__)
 
-	/* We expect the PHY to be always enabled */
-	if (!broxton_phy_is_enabled(dev_priv, phy))
+	if (!bxt_ddi_phy_is_enabled(dev_priv, phy))
 		return false;
 
 	ok = true;
 
-	if (phy == DPIO_PHY0)
-		ports = BIT(PORT_B) | BIT(PORT_C);
-	else
-		ports = BIT(PORT_A);
-
-	for_each_port_masked(port, ports) {
-		int lane;
-
-		for (lane = 0; lane < 4; lane++)
-			ok &= _CHK(BXT_PORT_TX_DW14_LN(port, lane),
-				    LATENCY_OPTIM,
-				    lane != 1 ? LATENCY_OPTIM : 0,
-				    "BXT_PORT_TX_DW14_LN(%d, %d)", port, lane);
-	}
-
 	/* PLL Rcomp code offset */
 	ok &= _CHK(BXT_PORT_CL1CM_DW9(phy),
 		    IREF0RC_OFFSET_MASK, 0xe4 << IREF0RC_OFFSET_SHIFT,
@@ -2058,11 +2015,65 @@ static bool broxton_phy_verify_state(struct drm_i915_private *dev_priv,
 #undef _CHK
 }
 
-void broxton_ddi_phy_verify_state(struct drm_i915_private *dev_priv)
+static uint8_t
+bxt_ddi_phy_calc_lane_lat_optim_mask(struct intel_encoder *encoder,
+				     struct intel_crtc_state *pipe_config)
 {
-	if (!broxton_phy_verify_state(dev_priv, DPIO_PHY0) ||
-	    !broxton_phy_verify_state(dev_priv, DPIO_PHY1))
-		i915_report_error(dev_priv, "DDI PHY state mismatch\n");
+	switch (pipe_config->lane_count) {
+	case 1:
+		return 0;
+	case 2:
+		return BIT(2) | BIT(0);
+	case 4:
+		return BIT(3) | BIT(2) | BIT(0);
+	default:
+		MISSING_CASE(pipe_config->lane_count);
+
+		return 0;
+	}
+}
+
+static void bxt_ddi_pre_pll_enable(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_i915_private *dev_priv = to_i915(dport->base.base.dev);
+	enum port port = dport->port;
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	int lane;
+
+	for (lane = 0; lane < 4; lane++) {
+		u32 val = I915_READ(BXT_PORT_TX_DW14_LN(port, lane));
+
+		/*
+		 * Note that on CHV this flag is called UPAR, but has
+		 * the same function.
+		 */
+		val &= ~LATENCY_OPTIM;
+		if (intel_crtc->config->lane_lat_optim_mask & BIT(lane))
+			val |= LATENCY_OPTIM;
+
+		I915_WRITE(BXT_PORT_TX_DW14_LN(port, lane), val);
+	}
+}
+
+static uint8_t
+bxt_ddi_phy_get_lane_lat_optim_mask(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_i915_private *dev_priv = to_i915(dport->base.base.dev);
+	enum port port = dport->port;
+	int lane;
+	uint8_t mask;
+
+	mask = 0;
+	for (lane = 0; lane < 4; lane++) {
+		u32 val = I915_READ(BXT_PORT_TX_DW14_LN(port, lane));
+
+		if (val & LATENCY_OPTIM)
+			mask |= BIT(lane);
+	}
+
+	return mask;
 }
 
 void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
@@ -2113,7 +2124,7 @@ void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 
 void intel_ddi_fdi_disable(struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc);
 	uint32_t val;
 
@@ -2146,7 +2157,7 @@ void intel_ddi_fdi_disable(struct drm_crtc *crtc)
 void intel_ddi_get_config(struct intel_encoder *encoder,
 			  struct intel_crtc_state *pipe_config)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
 	struct intel_hdmi *intel_hdmi;
@@ -2200,7 +2211,6 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 		break;
 	case TRANS_DDI_MODE_SELECT_DP_SST:
 	case TRANS_DDI_MODE_SELECT_DP_MST:
-		pipe_config->has_dp_encoder = true;
 		pipe_config->lane_count =
 			((temp & DDI_PORT_WIDTH_MASK) >> DDI_PORT_WIDTH_SHIFT) + 1;
 		intel_dp_get_m_n(intel_crtc, pipe_config);
@@ -2236,13 +2246,19 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 	}
 
 	intel_ddi_clock_get(encoder, pipe_config);
+
+	if (IS_BROXTON(dev_priv))
+		pipe_config->lane_lat_optim_mask =
+			bxt_ddi_phy_get_lane_lat_optim_mask(encoder);
 }
 
 static bool intel_ddi_compute_config(struct intel_encoder *encoder,
 				     struct intel_crtc_state *pipe_config)
 {
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	int type = encoder->type;
 	int port = intel_ddi_get_encoder_port(encoder);
+	int ret;
 
 	WARN(type == INTEL_OUTPUT_UNKNOWN, "compute_config() on unknown output!\n");
 
@@ -2250,9 +2266,17 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder,
 		pipe_config->cpu_transcoder = TRANSCODER_EDP;
 
 	if (type == INTEL_OUTPUT_HDMI)
-		return intel_hdmi_compute_config(encoder, pipe_config);
+		ret = intel_hdmi_compute_config(encoder, pipe_config);
 	else
-		return intel_dp_compute_config(encoder, pipe_config);
+		ret = intel_dp_compute_config(encoder, pipe_config);
+
+	if (IS_BROXTON(dev_priv) && ret)
+		pipe_config->lane_lat_optim_mask =
+			bxt_ddi_phy_calc_lane_lat_optim_mask(encoder,
+							     pipe_config);
+
+	return ret;
+
 }
 
 static const struct drm_encoder_funcs intel_ddi_funcs = {
@@ -2297,7 +2321,7 @@ intel_ddi_init_hdmi_connector(struct intel_digital_port *intel_dig_port)
 
 void intel_ddi_init(struct drm_device *dev, enum port port)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_digital_port *intel_dig_port;
 	struct intel_encoder *intel_encoder;
 	struct drm_encoder *encoder;
@@ -2347,10 +2371,12 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 	encoder = &intel_encoder->base;
 
 	drm_encoder_init(dev, encoder, &intel_ddi_funcs,
-			 DRM_MODE_ENCODER_TMDS, NULL);
+			 DRM_MODE_ENCODER_TMDS, "DDI %c", port_name(port));
 
 	intel_encoder->compute_config = intel_ddi_compute_config;
 	intel_encoder->enable = intel_enable_ddi;
+	if (IS_BROXTON(dev_priv))
+		intel_encoder->pre_pll_enable = bxt_ddi_pre_pll_enable;
 	intel_encoder->pre_enable = intel_ddi_pre_enable;
 	intel_encoder->disable = intel_disable_ddi;
 	intel_encoder->post_disable = intel_ddi_post_disable;
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
new file mode 100644
index 000000000000..cba137f9ad3e
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -0,0 +1,388 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#include "i915_drv.h"
+
+void intel_device_info_dump(struct drm_i915_private *dev_priv)
+{
+	const struct intel_device_info *info = &dev_priv->info;
+
+#define PRINT_S(name) "%s"
+#define SEP_EMPTY
+#define PRINT_FLAG(name) info->name ? #name "," : ""
+#define SEP_COMMA ,
+	DRM_DEBUG_DRIVER("i915 device info: gen=%i, pciid=0x%04x rev=0x%02x flags="
+			 DEV_INFO_FOR_EACH_FLAG(PRINT_S, SEP_EMPTY),
+			 info->gen,
+			 dev_priv->drm.pdev->device,
+			 dev_priv->drm.pdev->revision,
+			 DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG, SEP_COMMA));
+#undef PRINT_S
+#undef SEP_EMPTY
+#undef PRINT_FLAG
+#undef SEP_COMMA
+}
+
+static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
+{
+	struct intel_device_info *info = mkwrite_device_info(dev_priv);
+	u32 fuse, eu_dis;
+
+	fuse = I915_READ(CHV_FUSE_GT);
+
+	info->slice_total = 1;
+
+	if (!(fuse & CHV_FGT_DISABLE_SS0)) {
+		info->subslice_per_slice++;
+		eu_dis = fuse & (CHV_FGT_EU_DIS_SS0_R0_MASK |
+				 CHV_FGT_EU_DIS_SS0_R1_MASK);
+		info->eu_total += 8 - hweight32(eu_dis);
+	}
+
+	if (!(fuse & CHV_FGT_DISABLE_SS1)) {
+		info->subslice_per_slice++;
+		eu_dis = fuse & (CHV_FGT_EU_DIS_SS1_R0_MASK |
+				 CHV_FGT_EU_DIS_SS1_R1_MASK);
+		info->eu_total += 8 - hweight32(eu_dis);
+	}
+
+	info->subslice_total = info->subslice_per_slice;
+	/*
+	 * CHV expected to always have a uniform distribution of EU
+	 * across subslices.
+	*/
+	info->eu_per_subslice = info->subslice_total ?
+				info->eu_total / info->subslice_total :
+				0;
+	/*
+	 * CHV supports subslice power gating on devices with more than
+	 * one subslice, and supports EU power gating on devices with
+	 * more than one EU pair per subslice.
+	*/
+	info->has_slice_pg = 0;
+	info->has_subslice_pg = (info->subslice_total > 1);
+	info->has_eu_pg = (info->eu_per_subslice > 2);
+}
+
+static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
+{
+	struct intel_device_info *info = mkwrite_device_info(dev_priv);
+	int s_max = 3, ss_max = 4, eu_max = 8;
+	int s, ss;
+	u32 fuse2, s_enable, ss_disable, eu_disable;
+	u8 eu_mask = 0xff;
+
+	fuse2 = I915_READ(GEN8_FUSE2);
+	s_enable = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
+	ss_disable = (fuse2 & GEN9_F2_SS_DIS_MASK) >> GEN9_F2_SS_DIS_SHIFT;
+
+	info->slice_total = hweight32(s_enable);
+	/*
+	 * The subslice disable field is global, i.e. it applies
+	 * to each of the enabled slices.
+	*/
+	info->subslice_per_slice = ss_max - hweight32(ss_disable);
+	info->subslice_total = info->slice_total * info->subslice_per_slice;
+
+	/*
+	 * Iterate through enabled slices and subslices to
+	 * count the total enabled EU.
+	*/
+	for (s = 0; s < s_max; s++) {
+		if (!(s_enable & BIT(s)))
+			/* skip disabled slice */
+			continue;
+
+		eu_disable = I915_READ(GEN9_EU_DISABLE(s));
+		for (ss = 0; ss < ss_max; ss++) {
+			int eu_per_ss;
+
+			if (ss_disable & BIT(ss))
+				/* skip disabled subslice */
+				continue;
+
+			eu_per_ss = eu_max - hweight8((eu_disable >> (ss*8)) &
+						      eu_mask);
+
+			/*
+			 * Record which subslice(s) has(have) 7 EUs. we
+			 * can tune the hash used to spread work among
+			 * subslices if they are unbalanced.
+			 */
+			if (eu_per_ss == 7)
+				info->subslice_7eu[s] |= BIT(ss);
+
+			info->eu_total += eu_per_ss;
+		}
+	}
+
+	/*
+	 * SKL is expected to always have a uniform distribution
+	 * of EU across subslices with the exception that any one
+	 * EU in any one subslice may be fused off for die
+	 * recovery. BXT is expected to be perfectly uniform in EU
+	 * distribution.
+	*/
+	info->eu_per_subslice = info->subslice_total ?
+				DIV_ROUND_UP(info->eu_total,
+					     info->subslice_total) : 0;
+	/*
+	 * SKL supports slice power gating on devices with more than
+	 * one slice, and supports EU power gating on devices with
+	 * more than one EU pair per subslice. BXT supports subslice
+	 * power gating on devices with more than one subslice, and
+	 * supports EU power gating on devices with more than one EU
+	 * pair per subslice.
+	*/
+	info->has_slice_pg =
+		(IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) &&
+		info->slice_total > 1;
+	info->has_subslice_pg =
+		IS_BROXTON(dev_priv) && info->subslice_total > 1;
+	info->has_eu_pg = info->eu_per_subslice > 2;
+
+	if (IS_BROXTON(dev_priv)) {
+#define IS_SS_DISABLED(_ss_disable, ss)    (_ss_disable & BIT(ss))
+		/*
+		 * There is a HW issue in 2x6 fused down parts that requires
+		 * Pooled EU to be enabled as a WA. The pool configuration
+		 * changes depending upon which subslice is fused down. This
+		 * doesn't affect if the device has all 3 subslices enabled.
+		 */
+		/* WaEnablePooledEuFor2x6:bxt */
+		info->has_pooled_eu = ((info->subslice_per_slice == 3) ||
+				       (info->subslice_per_slice == 2 &&
+					INTEL_REVID(dev_priv) < BXT_REVID_C0));
+
+		info->min_eu_in_pool = 0;
+		if (info->has_pooled_eu) {
+			if (IS_SS_DISABLED(ss_disable, 0) ||
+			    IS_SS_DISABLED(ss_disable, 2))
+				info->min_eu_in_pool = 3;
+			else if (IS_SS_DISABLED(ss_disable, 1))
+				info->min_eu_in_pool = 6;
+			else
+				info->min_eu_in_pool = 9;
+		}
+#undef IS_SS_DISABLED
+	}
+}
+
+static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
+{
+	struct intel_device_info *info = mkwrite_device_info(dev_priv);
+	const int s_max = 3, ss_max = 3, eu_max = 8;
+	int s, ss;
+	u32 fuse2, eu_disable[s_max], s_enable, ss_disable;
+
+	fuse2 = I915_READ(GEN8_FUSE2);
+	s_enable = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
+	ss_disable = (fuse2 & GEN8_F2_SS_DIS_MASK) >> GEN8_F2_SS_DIS_SHIFT;
+
+	eu_disable[0] = I915_READ(GEN8_EU_DISABLE0) & GEN8_EU_DIS0_S0_MASK;
+	eu_disable[1] = (I915_READ(GEN8_EU_DISABLE0) >> GEN8_EU_DIS0_S1_SHIFT) |
+			((I915_READ(GEN8_EU_DISABLE1) & GEN8_EU_DIS1_S1_MASK) <<
+			 (32 - GEN8_EU_DIS0_S1_SHIFT));
+	eu_disable[2] = (I915_READ(GEN8_EU_DISABLE1) >> GEN8_EU_DIS1_S2_SHIFT) |
+			((I915_READ(GEN8_EU_DISABLE2) & GEN8_EU_DIS2_S2_MASK) <<
+			 (32 - GEN8_EU_DIS1_S2_SHIFT));
+
+	info->slice_total = hweight32(s_enable);
+
+	/*
+	 * The subslice disable field is global, i.e. it applies
+	 * to each of the enabled slices.
+	 */
+	info->subslice_per_slice = ss_max - hweight32(ss_disable);
+	info->subslice_total = info->slice_total * info->subslice_per_slice;
+
+	/*
+	 * Iterate through enabled slices and subslices to
+	 * count the total enabled EU.
+	 */
+	for (s = 0; s < s_max; s++) {
+		if (!(s_enable & (0x1 << s)))
+			/* skip disabled slice */
+			continue;
+
+		for (ss = 0; ss < ss_max; ss++) {
+			u32 n_disabled;
+
+			if (ss_disable & (0x1 << ss))
+				/* skip disabled subslice */
+				continue;
+
+			n_disabled = hweight8(eu_disable[s] >> (ss * eu_max));
+
+			/*
+			 * Record which subslices have 7 EUs.
+			 */
+			if (eu_max - n_disabled == 7)
+				info->subslice_7eu[s] |= 1 << ss;
+
+			info->eu_total += eu_max - n_disabled;
+		}
+	}
+
+	/*
+	 * BDW is expected to always have a uniform distribution of EU across
+	 * subslices with the exception that any one EU in any one subslice may
+	 * be fused off for die recovery.
+	 */
+	info->eu_per_subslice = info->subslice_total ?
+		DIV_ROUND_UP(info->eu_total, info->subslice_total) : 0;
+
+	/*
+	 * BDW supports slice power gating on devices with more than
+	 * one slice.
+	 */
+	info->has_slice_pg = (info->slice_total > 1);
+	info->has_subslice_pg = 0;
+	info->has_eu_pg = 0;
+}
+
+/*
+ * Determine various intel_device_info fields at runtime.
+ *
+ * Use it when either:
+ *   - it's judged too laborious to fill n static structures with the limit
+ *     when a simple if statement does the job,
+ *   - run-time checks (eg read fuse/strap registers) are needed.
+ *
+ * This function needs to be called:
+ *   - after the MMIO has been setup as we are reading registers,
+ *   - after the PCH has been detected,
+ *   - before the first usage of the fields it can tweak.
+ */
+void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
+{
+	struct intel_device_info *info = mkwrite_device_info(dev_priv);
+	enum pipe pipe;
+
+	/*
+	 * Skylake and Broxton currently don't expose the topmost plane as its
+	 * use is exclusive with the legacy cursor and we only want to expose
+	 * one of those, not both. Until we can safely expose the topmost plane
+	 * as a DRM_PLANE_TYPE_CURSOR with all the features exposed/supported,
+	 * we don't expose the topmost plane at all to prevent ABI breakage
+	 * down the line.
+	 */
+	if (IS_BROXTON(dev_priv)) {
+		info->num_sprites[PIPE_A] = 2;
+		info->num_sprites[PIPE_B] = 2;
+		info->num_sprites[PIPE_C] = 1;
+	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		for_each_pipe(dev_priv, pipe)
+			info->num_sprites[pipe] = 2;
+	else
+		for_each_pipe(dev_priv, pipe)
+			info->num_sprites[pipe] = 1;
+
+	if (i915.disable_display) {
+		DRM_INFO("Display disabled (module parameter)\n");
+		info->num_pipes = 0;
+	} else if (info->num_pipes > 0 &&
+		   (IS_GEN7(dev_priv) || IS_GEN8(dev_priv)) &&
+		   HAS_PCH_SPLIT(dev_priv)) {
+		u32 fuse_strap = I915_READ(FUSE_STRAP);
+		u32 sfuse_strap = I915_READ(SFUSE_STRAP);
+
+		/*
+		 * SFUSE_STRAP is supposed to have a bit signalling the display
+		 * is fused off. Unfortunately it seems that, at least in
+		 * certain cases, fused off display means that PCH display
+		 * reads don't land anywhere. In that case, we read 0s.
+		 *
+		 * On CPT/PPT, we can detect this case as SFUSE_STRAP_FUSE_LOCK
+		 * should be set when taking over after the firmware.
+		 */
+		if (fuse_strap & ILK_INTERNAL_DISPLAY_DISABLE ||
+		    sfuse_strap & SFUSE_STRAP_DISPLAY_DISABLED ||
+		    (dev_priv->pch_type == PCH_CPT &&
+		     !(sfuse_strap & SFUSE_STRAP_FUSE_LOCK))) {
+			DRM_INFO("Display fused off, disabling\n");
+			info->num_pipes = 0;
+		} else if (fuse_strap & IVB_PIPE_C_DISABLE) {
+			DRM_INFO("PipeC fused off\n");
+			info->num_pipes -= 1;
+		}
+	} else if (info->num_pipes > 0 && IS_GEN9(dev_priv)) {
+		u32 dfsm = I915_READ(SKL_DFSM);
+		u8 disabled_mask = 0;
+		bool invalid;
+		int num_bits;
+
+		if (dfsm & SKL_DFSM_PIPE_A_DISABLE)
+			disabled_mask |= BIT(PIPE_A);
+		if (dfsm & SKL_DFSM_PIPE_B_DISABLE)
+			disabled_mask |= BIT(PIPE_B);
+		if (dfsm & SKL_DFSM_PIPE_C_DISABLE)
+			disabled_mask |= BIT(PIPE_C);
+
+		num_bits = hweight8(disabled_mask);
+
+		switch (disabled_mask) {
+		case BIT(PIPE_A):
+		case BIT(PIPE_B):
+		case BIT(PIPE_A) | BIT(PIPE_B):
+		case BIT(PIPE_A) | BIT(PIPE_C):
+			invalid = true;
+			break;
+		default:
+			invalid = false;
+		}
+
+		if (num_bits > info->num_pipes || invalid)
+			DRM_ERROR("invalid pipe fuse configuration: 0x%x\n",
+				  disabled_mask);
+		else
+			info->num_pipes -= num_bits;
+	}
+
+	/* Initialize slice/subslice/EU info */
+	if (IS_CHERRYVIEW(dev_priv))
+		cherryview_sseu_info_init(dev_priv);
+	else if (IS_BROADWELL(dev_priv))
+		broadwell_sseu_info_init(dev_priv);
+	else if (INTEL_INFO(dev_priv)->gen >= 9)
+		gen9_sseu_info_init(dev_priv);
+
+	info->has_snoop = !info->has_llc;
+
+	/* Snooping is broken on BXT A stepping. */
+	if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1))
+		info->has_snoop = false;
+
+	DRM_DEBUG_DRIVER("slice total: %u\n", info->slice_total);
+	DRM_DEBUG_DRIVER("subslice total: %u\n", info->subslice_total);
+	DRM_DEBUG_DRIVER("subslice per slice: %u\n", info->subslice_per_slice);
+	DRM_DEBUG_DRIVER("EU total: %u\n", info->eu_total);
+	DRM_DEBUG_DRIVER("EU per subslice: %u\n", info->eu_per_subslice);
+	DRM_DEBUG_DRIVER("has slice power gating: %s\n",
+			 info->has_slice_pg ? "y" : "n");
+	DRM_DEBUG_DRIVER("has subslice power gating: %s\n",
+			 info->has_subslice_pg ? "y" : "n");
+	DRM_DEBUG_DRIVER("has EU power gating: %s\n",
+			 info->has_eu_pg ? "y" : "n");
+}
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3074c56a643d..c457eed76f1f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -36,6 +36,7 @@
 #include "intel_drv.h"
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
+#include "i915_gem_dmabuf.h"
 #include "intel_dsi.h"
 #include "i915_trace.h"
 #include <drm/drm_atomic.h>
@@ -46,7 +47,11 @@
 #include <drm/drm_rect.h>
 #include <linux/dma_remapping.h>
 #include <linux/reservation.h>
-#include <linux/dma-buf.h>
+
+static bool is_mmio_work(struct intel_flip_work *work)
+{
+	return work->mmio_work.func;
+}
 
 /* Primary plane formats for gen <= 3 */
 static const uint32_t i8xx_primary_formats[] = {
@@ -117,20 +122,18 @@ static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force);
 static void ironlake_pfit_enable(struct intel_crtc *crtc);
 static void intel_modeset_setup_hw_state(struct drm_device *dev);
 static void intel_pre_disable_primary_noatomic(struct drm_crtc *crtc);
+static int ilk_max_pixel_rate(struct drm_atomic_state *state);
+static int bxt_calc_cdclk(int max_pixclk);
 
-typedef struct {
-	int	min, max;
-} intel_range_t;
-
-typedef struct {
-	int	dot_limit;
-	int	p2_slow, p2_fast;
-} intel_p2_t;
-
-typedef struct intel_limit intel_limit_t;
 struct intel_limit {
-	intel_range_t   dot, vco, n, m, m1, m2, p, p1;
-	intel_p2_t	    p2;
+	struct {
+		int min, max;
+	} dot, vco, n, m, m1, m2, p, p1;
+
+	struct {
+		int dot_limit;
+		int p2_slow, p2_fast;
+	} p2;
 };
 
 /* returns HPLL frequency in kHz */
@@ -185,6 +188,7 @@ intel_pch_rawclk(struct drm_i915_private *dev_priv)
 static int
 intel_vlv_hrawclk(struct drm_i915_private *dev_priv)
 {
+	/* RAWCLK_FREQ_VLV register updated from power well code */
 	return vlv_get_cck_clock_hpll(dev_priv, "hrawclk",
 				      CCK_DISPLAY_REF_CLOCK_CONTROL);
 }
@@ -218,7 +222,7 @@ intel_g4x_hrawclk(struct drm_i915_private *dev_priv)
 	}
 }
 
-static void intel_update_rawclk(struct drm_i915_private *dev_priv)
+void intel_update_rawclk(struct drm_i915_private *dev_priv)
 {
 	if (HAS_PCH_SPLIT(dev_priv))
 		dev_priv->rawclk_freq = intel_pch_rawclk(dev_priv);
@@ -255,7 +259,7 @@ intel_fdi_link_freq(struct drm_i915_private *dev_priv,
 		return 270000;
 }
 
-static const intel_limit_t intel_limits_i8xx_dac = {
+static const struct intel_limit intel_limits_i8xx_dac = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 908000, .max = 1512000 },
 	.n = { .min = 2, .max = 16 },
@@ -268,7 +272,7 @@ static const intel_limit_t intel_limits_i8xx_dac = {
 		.p2_slow = 4, .p2_fast = 2 },
 };
 
-static const intel_limit_t intel_limits_i8xx_dvo = {
+static const struct intel_limit intel_limits_i8xx_dvo = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 908000, .max = 1512000 },
 	.n = { .min = 2, .max = 16 },
@@ -281,7 +285,7 @@ static const intel_limit_t intel_limits_i8xx_dvo = {
 		.p2_slow = 4, .p2_fast = 4 },
 };
 
-static const intel_limit_t intel_limits_i8xx_lvds = {
+static const struct intel_limit intel_limits_i8xx_lvds = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 908000, .max = 1512000 },
 	.n = { .min = 2, .max = 16 },
@@ -294,7 +298,7 @@ static const intel_limit_t intel_limits_i8xx_lvds = {
 		.p2_slow = 14, .p2_fast = 7 },
 };
 
-static const intel_limit_t intel_limits_i9xx_sdvo = {
+static const struct intel_limit intel_limits_i9xx_sdvo = {
 	.dot = { .min = 20000, .max = 400000 },
 	.vco = { .min = 1400000, .max = 2800000 },
 	.n = { .min = 1, .max = 6 },
@@ -307,7 +311,7 @@ static const intel_limit_t intel_limits_i9xx_sdvo = {
 		.p2_slow = 10, .p2_fast = 5 },
 };
 
-static const intel_limit_t intel_limits_i9xx_lvds = {
+static const struct intel_limit intel_limits_i9xx_lvds = {
 	.dot = { .min = 20000, .max = 400000 },
 	.vco = { .min = 1400000, .max = 2800000 },
 	.n = { .min = 1, .max = 6 },
@@ -321,7 +325,7 @@ static const intel_limit_t intel_limits_i9xx_lvds = {
 };
 
 
-static const intel_limit_t intel_limits_g4x_sdvo = {
+static const struct intel_limit intel_limits_g4x_sdvo = {
 	.dot = { .min = 25000, .max = 270000 },
 	.vco = { .min = 1750000, .max = 3500000},
 	.n = { .min = 1, .max = 4 },
@@ -336,7 +340,7 @@ static const intel_limit_t intel_limits_g4x_sdvo = {
 	},
 };
 
-static const intel_limit_t intel_limits_g4x_hdmi = {
+static const struct intel_limit intel_limits_g4x_hdmi = {
 	.dot = { .min = 22000, .max = 400000 },
 	.vco = { .min = 1750000, .max = 3500000},
 	.n = { .min = 1, .max = 4 },
@@ -349,7 +353,7 @@ static const intel_limit_t intel_limits_g4x_hdmi = {
 		.p2_slow = 10, .p2_fast = 5 },
 };
 
-static const intel_limit_t intel_limits_g4x_single_channel_lvds = {
+static const struct intel_limit intel_limits_g4x_single_channel_lvds = {
 	.dot = { .min = 20000, .max = 115000 },
 	.vco = { .min = 1750000, .max = 3500000 },
 	.n = { .min = 1, .max = 3 },
@@ -363,7 +367,7 @@ static const intel_limit_t intel_limits_g4x_single_channel_lvds = {
 	},
 };
 
-static const intel_limit_t intel_limits_g4x_dual_channel_lvds = {
+static const struct intel_limit intel_limits_g4x_dual_channel_lvds = {
 	.dot = { .min = 80000, .max = 224000 },
 	.vco = { .min = 1750000, .max = 3500000 },
 	.n = { .min = 1, .max = 3 },
@@ -377,7 +381,7 @@ static const intel_limit_t intel_limits_g4x_dual_channel_lvds = {
 	},
 };
 
-static const intel_limit_t intel_limits_pineview_sdvo = {
+static const struct intel_limit intel_limits_pineview_sdvo = {
 	.dot = { .min = 20000, .max = 400000},
 	.vco = { .min = 1700000, .max = 3500000 },
 	/* Pineview's Ncounter is a ring counter */
@@ -392,7 +396,7 @@ static const intel_limit_t intel_limits_pineview_sdvo = {
 		.p2_slow = 10, .p2_fast = 5 },
 };
 
-static const intel_limit_t intel_limits_pineview_lvds = {
+static const struct intel_limit intel_limits_pineview_lvds = {
 	.dot = { .min = 20000, .max = 400000 },
 	.vco = { .min = 1700000, .max = 3500000 },
 	.n = { .min = 3, .max = 6 },
@@ -410,7 +414,7 @@ static const intel_limit_t intel_limits_pineview_lvds = {
  * We calculate clock using (register_value + 2) for N/M1/M2, so here
  * the range value for them is (actual_value - 2).
  */
-static const intel_limit_t intel_limits_ironlake_dac = {
+static const struct intel_limit intel_limits_ironlake_dac = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 5 },
@@ -423,7 +427,7 @@ static const intel_limit_t intel_limits_ironlake_dac = {
 		.p2_slow = 10, .p2_fast = 5 },
 };
 
-static const intel_limit_t intel_limits_ironlake_single_lvds = {
+static const struct intel_limit intel_limits_ironlake_single_lvds = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 3 },
@@ -436,7 +440,7 @@ static const intel_limit_t intel_limits_ironlake_single_lvds = {
 		.p2_slow = 14, .p2_fast = 14 },
 };
 
-static const intel_limit_t intel_limits_ironlake_dual_lvds = {
+static const struct intel_limit intel_limits_ironlake_dual_lvds = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 3 },
@@ -450,7 +454,7 @@ static const intel_limit_t intel_limits_ironlake_dual_lvds = {
 };
 
 /* LVDS 100mhz refclk limits. */
-static const intel_limit_t intel_limits_ironlake_single_lvds_100m = {
+static const struct intel_limit intel_limits_ironlake_single_lvds_100m = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 2 },
@@ -463,7 +467,7 @@ static const intel_limit_t intel_limits_ironlake_single_lvds_100m = {
 		.p2_slow = 14, .p2_fast = 14 },
 };
 
-static const intel_limit_t intel_limits_ironlake_dual_lvds_100m = {
+static const struct intel_limit intel_limits_ironlake_dual_lvds_100m = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 3 },
@@ -476,7 +480,7 @@ static const intel_limit_t intel_limits_ironlake_dual_lvds_100m = {
 		.p2_slow = 7, .p2_fast = 7 },
 };
 
-static const intel_limit_t intel_limits_vlv = {
+static const struct intel_limit intel_limits_vlv = {
 	 /*
 	  * These are the data rate limits (measured in fast clocks)
 	  * since those are the strictest limits we have. The fast
@@ -492,7 +496,7 @@ static const intel_limit_t intel_limits_vlv = {
 	.p2 = { .p2_slow = 2, .p2_fast = 20 }, /* slow=min, fast=max */
 };
 
-static const intel_limit_t intel_limits_chv = {
+static const struct intel_limit intel_limits_chv = {
 	/*
 	 * These are the data rate limits (measured in fast clocks)
 	 * since those are the strictest limits we have.  The fast
@@ -508,7 +512,7 @@ static const intel_limit_t intel_limits_chv = {
 	.p2 = {	.p2_slow = 1, .p2_fast = 14 },
 };
 
-static const intel_limit_t intel_limits_bxt = {
+static const struct intel_limit intel_limits_bxt = {
 	/* FIXME: find real dot limits */
 	.dot = { .min = 0, .max = INT_MAX },
 	.vco = { .min = 4800000, .max = 6700000 },
@@ -526,52 +530,6 @@ needs_modeset(struct drm_crtc_state *state)
 	return drm_atomic_crtc_needs_modeset(state);
 }
 
-/**
- * Returns whether any output on the specified pipe is of the specified type
- */
-bool intel_pipe_has_type(struct intel_crtc *crtc, enum intel_output_type type)
-{
-	struct drm_device *dev = crtc->base.dev;
-	struct intel_encoder *encoder;
-
-	for_each_encoder_on_crtc(dev, &crtc->base, encoder)
-		if (encoder->type == type)
-			return true;
-
-	return false;
-}
-
-/**
- * Returns whether any output on the specified pipe will have the specified
- * type after a staged modeset is complete, i.e., the same as
- * intel_pipe_has_type() but looking at encoder->new_crtc instead of
- * encoder->crtc.
- */
-static bool intel_pipe_will_have_type(const struct intel_crtc_state *crtc_state,
-				      int type)
-{
-	struct drm_atomic_state *state = crtc_state->base.state;
-	struct drm_connector *connector;
-	struct drm_connector_state *connector_state;
-	struct intel_encoder *encoder;
-	int i, num_connectors = 0;
-
-	for_each_connector_in_state(state, connector, connector_state, i) {
-		if (connector_state->crtc != crtc_state->base.crtc)
-			continue;
-
-		num_connectors++;
-
-		encoder = to_intel_encoder(connector_state->best_encoder);
-		if (encoder->type == type)
-			return true;
-	}
-
-	WARN_ON(num_connectors == 0);
-
-	return false;
-}
-
 /*
  * Platform specific helpers to calculate the port PLL loopback- (clock.m),
  * and post-divider (clock.p) values, pre- (clock.vco) and post-divided fast
@@ -581,7 +539,7 @@ static bool intel_pipe_will_have_type(const struct intel_crtc_state *crtc_state,
  * divided-down version of it.
  */
 /* m1 is reserved as 0 in Pineview, n is a ring counter */
-static int pnv_calc_dpll_params(int refclk, intel_clock_t *clock)
+static int pnv_calc_dpll_params(int refclk, struct dpll *clock)
 {
 	clock->m = clock->m2 + 2;
 	clock->p = clock->p1 * clock->p2;
@@ -598,7 +556,7 @@ static uint32_t i9xx_dpll_compute_m(struct dpll *dpll)
 	return 5 * (dpll->m1 + 2) + (dpll->m2 + 2);
 }
 
-static int i9xx_calc_dpll_params(int refclk, intel_clock_t *clock)
+static int i9xx_calc_dpll_params(int refclk, struct dpll *clock)
 {
 	clock->m = i9xx_dpll_compute_m(clock);
 	clock->p = clock->p1 * clock->p2;
@@ -610,7 +568,7 @@ static int i9xx_calc_dpll_params(int refclk, intel_clock_t *clock)
 	return clock->dot;
 }
 
-static int vlv_calc_dpll_params(int refclk, intel_clock_t *clock)
+static int vlv_calc_dpll_params(int refclk, struct dpll *clock)
 {
 	clock->m = clock->m1 * clock->m2;
 	clock->p = clock->p1 * clock->p2;
@@ -622,7 +580,7 @@ static int vlv_calc_dpll_params(int refclk, intel_clock_t *clock)
 	return clock->dot / 5;
 }
 
-int chv_calc_dpll_params(int refclk, intel_clock_t *clock)
+int chv_calc_dpll_params(int refclk, struct dpll *clock)
 {
 	clock->m = clock->m1 * clock->m2;
 	clock->p = clock->p1 * clock->p2;
@@ -642,8 +600,8 @@ int chv_calc_dpll_params(int refclk, intel_clock_t *clock)
  */
 
 static bool intel_PLL_is_valid(struct drm_device *dev,
-			       const intel_limit_t *limit,
-			       const intel_clock_t *clock)
+			       const struct intel_limit *limit,
+			       const struct dpll *clock)
 {
 	if (clock->n   < limit->n.min   || limit->n.max   < clock->n)
 		INTELPllInvalid("n out of range\n");
@@ -678,13 +636,13 @@ static bool intel_PLL_is_valid(struct drm_device *dev,
 }
 
 static int
-i9xx_select_p2_div(const intel_limit_t *limit,
+i9xx_select_p2_div(const struct intel_limit *limit,
 		   const struct intel_crtc_state *crtc_state,
 		   int target)
 {
 	struct drm_device *dev = crtc_state->base.crtc->dev;
 
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		/*
 		 * For LVDS just rely on its current settings for dual-channel.
 		 * We haven't figured out how to reliably set up different
@@ -713,13 +671,13 @@ i9xx_select_p2_div(const intel_limit_t *limit,
  * divider from @match_clock used for LVDS downclocking.
  */
 static bool
-i9xx_find_best_dpll(const intel_limit_t *limit,
+i9xx_find_best_dpll(const struct intel_limit *limit,
 		    struct intel_crtc_state *crtc_state,
-		    int target, int refclk, intel_clock_t *match_clock,
-		    intel_clock_t *best_clock)
+		    int target, int refclk, struct dpll *match_clock,
+		    struct dpll *best_clock)
 {
 	struct drm_device *dev = crtc_state->base.crtc->dev;
-	intel_clock_t clock;
+	struct dpll clock;
 	int err = target;
 
 	memset(best_clock, 0, sizeof(*best_clock));
@@ -770,13 +728,13 @@ i9xx_find_best_dpll(const intel_limit_t *limit,
  * divider from @match_clock used for LVDS downclocking.
  */
 static bool
-pnv_find_best_dpll(const intel_limit_t *limit,
+pnv_find_best_dpll(const struct intel_limit *limit,
 		   struct intel_crtc_state *crtc_state,
-		   int target, int refclk, intel_clock_t *match_clock,
-		   intel_clock_t *best_clock)
+		   int target, int refclk, struct dpll *match_clock,
+		   struct dpll *best_clock)
 {
 	struct drm_device *dev = crtc_state->base.crtc->dev;
-	intel_clock_t clock;
+	struct dpll clock;
 	int err = target;
 
 	memset(best_clock, 0, sizeof(*best_clock));
@@ -825,13 +783,13 @@ pnv_find_best_dpll(const intel_limit_t *limit,
  * divider from @match_clock used for LVDS downclocking.
  */
 static bool
-g4x_find_best_dpll(const intel_limit_t *limit,
+g4x_find_best_dpll(const struct intel_limit *limit,
 		   struct intel_crtc_state *crtc_state,
-		   int target, int refclk, intel_clock_t *match_clock,
-		   intel_clock_t *best_clock)
+		   int target, int refclk, struct dpll *match_clock,
+		   struct dpll *best_clock)
 {
 	struct drm_device *dev = crtc_state->base.crtc->dev;
-	intel_clock_t clock;
+	struct dpll clock;
 	int max_n;
 	bool found = false;
 	/* approximately equals target * 0.00585 */
@@ -877,8 +835,8 @@ g4x_find_best_dpll(const intel_limit_t *limit,
  * best configuration and error found so far. Return the calculated error.
  */
 static bool vlv_PLL_is_optimal(struct drm_device *dev, int target_freq,
-			       const intel_clock_t *calculated_clock,
-			       const intel_clock_t *best_clock,
+			       const struct dpll *calculated_clock,
+			       const struct dpll *best_clock,
 			       unsigned int best_error_ppm,
 			       unsigned int *error_ppm)
 {
@@ -918,14 +876,14 @@ static bool vlv_PLL_is_optimal(struct drm_device *dev, int target_freq,
  * reflck * (5 * (m1 + 2) + (m2 + 2)) / (n + 2) / p1 / p2.
  */
 static bool
-vlv_find_best_dpll(const intel_limit_t *limit,
+vlv_find_best_dpll(const struct intel_limit *limit,
 		   struct intel_crtc_state *crtc_state,
-		   int target, int refclk, intel_clock_t *match_clock,
-		   intel_clock_t *best_clock)
+		   int target, int refclk, struct dpll *match_clock,
+		   struct dpll *best_clock)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
-	intel_clock_t clock;
+	struct dpll clock;
 	unsigned int bestppm = 1000000;
 	/* min update 19.2 MHz */
 	int max_n = min(limit->n.max, refclk / 19200);
@@ -977,15 +935,15 @@ vlv_find_best_dpll(const intel_limit_t *limit,
  * reflck * (5 * (m1 + 2) + (m2 + 2)) / (n + 2) / p1 / p2.
  */
 static bool
-chv_find_best_dpll(const intel_limit_t *limit,
+chv_find_best_dpll(const struct intel_limit *limit,
 		   struct intel_crtc_state *crtc_state,
-		   int target, int refclk, intel_clock_t *match_clock,
-		   intel_clock_t *best_clock)
+		   int target, int refclk, struct dpll *match_clock,
+		   struct dpll *best_clock)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	unsigned int best_error_ppm;
-	intel_clock_t clock;
+	struct dpll clock;
 	uint64_t m2;
 	int found = false;
 
@@ -1035,10 +993,10 @@ chv_find_best_dpll(const intel_limit_t *limit,
 }
 
 bool bxt_find_best_dpll(struct intel_crtc_state *crtc_state, int target_clock,
-			intel_clock_t *best_clock)
+			struct dpll *best_clock)
 {
 	int refclk = 100000;
-	const intel_limit_t *limit = &intel_limits_bxt;
+	const struct intel_limit *limit = &intel_limits_bxt;
 
 	return chv_find_best_dpll(limit, crtc_state,
 				  target_clock, refclk, NULL, best_clock);
@@ -1076,7 +1034,7 @@ enum transcoder intel_pipe_to_cpu_transcoder(struct drm_i915_private *dev_priv,
 
 static bool pipe_dsl_stopped(struct drm_device *dev, enum pipe pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t reg = PIPEDSL(pipe);
 	u32 line1, line2;
 	u32 line_mask;
@@ -1112,7 +1070,7 @@ static bool pipe_dsl_stopped(struct drm_device *dev, enum pipe pipe)
 static void intel_wait_for_pipe_off(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = crtc->config->cpu_transcoder;
 	enum pipe pipe = crtc->pipe;
 
@@ -1120,8 +1078,9 @@ static void intel_wait_for_pipe_off(struct intel_crtc *crtc)
 		i915_reg_t reg = PIPECONF(cpu_transcoder);
 
 		/* Wait for the Pipe State to go off */
-		if (wait_for((I915_READ(reg) & I965_PIPECONF_ACTIVE) == 0,
-			     100))
+		if (intel_wait_for_register(dev_priv,
+					    reg, I965_PIPECONF_ACTIVE, 0,
+					    100))
 			WARN(1, "pipe_off wait timed out\n");
 	} else {
 		/* Wait for the display line to settle */
@@ -1203,7 +1162,7 @@ static void assert_fdi_tx_pll_enabled(struct drm_i915_private *dev_priv,
 	u32 val;
 
 	/* ILK FDI PLL is always enabled */
-	if (INTEL_INFO(dev_priv)->gen == 5)
+	if (IS_GEN5(dev_priv))
 		return;
 
 	/* On Haswell, DDI ports are responsible for the FDI PLL setup */
@@ -1230,7 +1189,7 @@ void assert_fdi_rx_pll(struct drm_i915_private *dev_priv,
 void assert_panel_unlocked(struct drm_i915_private *dev_priv,
 			   enum pipe pipe)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	i915_reg_t pp_reg;
 	u32 val;
 	enum pipe panel_pipe = PIPE_A;
@@ -1272,7 +1231,7 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv,
 static void assert_cursor(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, bool state)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	bool cur_state;
 
 	if (IS_845G(dev) || IS_I865G(dev))
@@ -1334,7 +1293,7 @@ static void assert_plane(struct drm_i915_private *dev_priv,
 static void assert_planes_disabled(struct drm_i915_private *dev_priv,
 				   enum pipe pipe)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	int i;
 
 	/* Primary planes are fixed to pipes on gen4+ */
@@ -1360,7 +1319,7 @@ static void assert_planes_disabled(struct drm_i915_private *dev_priv,
 static void assert_sprites_disabled(struct drm_i915_private *dev_priv,
 				    enum pipe pipe)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	int sprite;
 
 	if (INTEL_INFO(dev)->gen >= 9) {
@@ -1540,7 +1499,11 @@ static void _vlv_enable_pll(struct intel_crtc *crtc,
 	POSTING_READ(DPLL(pipe));
 	udelay(150);
 
-	if (wait_for(((I915_READ(DPLL(pipe)) & DPLL_LOCK_VLV) == DPLL_LOCK_VLV), 1))
+	if (intel_wait_for_register(dev_priv,
+				    DPLL(pipe),
+				    DPLL_LOCK_VLV,
+				    DPLL_LOCK_VLV,
+				    1))
 		DRM_ERROR("DPLL %d failed to lock\n", pipe);
 }
 
@@ -1589,7 +1552,9 @@ static void _chv_enable_pll(struct intel_crtc *crtc,
 	I915_WRITE(DPLL(pipe), pipe_config->dpll_hw_state.dpll);
 
 	/* Check PLL is locked */
-	if (wait_for(((I915_READ(DPLL(pipe)) & DPLL_LOCK_VLV) == DPLL_LOCK_VLV), 1))
+	if (intel_wait_for_register(dev_priv,
+				    DPLL(pipe), DPLL_LOCK_VLV, DPLL_LOCK_VLV,
+				    1))
 		DRM_ERROR("PLL %d failed to lock\n", pipe);
 }
 
@@ -1635,9 +1600,10 @@ static int intel_num_dvo_pipes(struct drm_device *dev)
 	struct intel_crtc *crtc;
 	int count = 0;
 
-	for_each_intel_crtc(dev, crtc)
+	for_each_intel_crtc(dev, crtc) {
 		count += crtc->base.state->active &&
-			intel_pipe_has_type(crtc, INTEL_OUTPUT_DVO);
+			intel_crtc_has_type(crtc->config, INTEL_OUTPUT_DVO);
+	}
 
 	return count;
 }
@@ -1645,7 +1611,7 @@ static int intel_num_dvo_pipes(struct drm_device *dev)
 static void i9xx_enable_pll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t reg = DPLL(crtc->pipe);
 	u32 dpll = crtc->config->dpll_hw_state.dpll;
 
@@ -1717,12 +1683,12 @@ static void i9xx_enable_pll(struct intel_crtc *crtc)
 static void i9xx_disable_pll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = crtc->pipe;
 
 	/* Disable DVO 2x clock on both PLLs if necessary */
 	if (IS_I830(dev) &&
-	    intel_pipe_has_type(crtc, INTEL_OUTPUT_DVO) &&
+	    intel_crtc_has_type(crtc->config, INTEL_OUTPUT_DVO) &&
 	    !intel_num_dvo_pipes(dev)) {
 		I915_WRITE(DPLL(PIPE_B),
 			   I915_READ(DPLL(PIPE_B)) & ~DPLL_DVO_2X_MODE);
@@ -1809,7 +1775,9 @@ void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 		BUG();
 	}
 
-	if (wait_for((I915_READ(dpll_reg) & port_mask) == expected_mask, 1000))
+	if (intel_wait_for_register(dev_priv,
+				    dpll_reg, port_mask, expected_mask,
+				    1000))
 		WARN(1, "timed out waiting for port %c ready: got 0x%x, expected 0x%x\n",
 		     port_name(dport->port), I915_READ(dpll_reg) & port_mask, expected_mask);
 }
@@ -1817,7 +1785,7 @@ void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 static void ironlake_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 					   enum pipe pipe)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	i915_reg_t reg;
@@ -1850,7 +1818,7 @@ static void ironlake_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 		 * here for both 8bpc and 12bpc.
 		 */
 		val &= ~PIPECONF_BPC_MASK;
-		if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_HDMI))
+		if (intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_HDMI))
 			val |= PIPECONF_8BPC;
 		else
 			val |= pipeconf_val & PIPECONF_BPC_MASK;
@@ -1859,7 +1827,7 @@ static void ironlake_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 	val &= ~TRANS_INTERLACE_MASK;
 	if ((pipeconf_val & PIPECONF_INTERLACE_MASK) == PIPECONF_INTERLACED_ILK)
 		if (HAS_PCH_IBX(dev_priv) &&
-		    intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_SDVO))
+		    intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_SDVO))
 			val |= TRANS_LEGACY_INTERLACED_ILK;
 		else
 			val |= TRANS_INTERLACED;
@@ -1867,7 +1835,9 @@ static void ironlake_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 		val |= TRANS_PROGRESSIVE;
 
 	I915_WRITE(reg, val | TRANS_ENABLE);
-	if (wait_for(I915_READ(reg) & TRANS_STATE_ENABLE, 100))
+	if (intel_wait_for_register(dev_priv,
+				    reg, TRANS_STATE_ENABLE, TRANS_STATE_ENABLE,
+				    100))
 		DRM_ERROR("failed to enable transcoder %c\n", pipe_name(pipe));
 }
 
@@ -1895,14 +1865,18 @@ static void lpt_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 		val |= TRANS_PROGRESSIVE;
 
 	I915_WRITE(LPT_TRANSCONF, val);
-	if (wait_for(I915_READ(LPT_TRANSCONF) & TRANS_STATE_ENABLE, 100))
+	if (intel_wait_for_register(dev_priv,
+				    LPT_TRANSCONF,
+				    TRANS_STATE_ENABLE,
+				    TRANS_STATE_ENABLE,
+				    100))
 		DRM_ERROR("Failed to enable PCH transcoder\n");
 }
 
 static void ironlake_disable_pch_transcoder(struct drm_i915_private *dev_priv,
 					    enum pipe pipe)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	i915_reg_t reg;
 	uint32_t val;
 
@@ -1918,7 +1892,9 @@ static void ironlake_disable_pch_transcoder(struct drm_i915_private *dev_priv,
 	val &= ~TRANS_ENABLE;
 	I915_WRITE(reg, val);
 	/* wait for PCH transcoder off, transcoder state */
-	if (wait_for((I915_READ(reg) & TRANS_STATE_ENABLE) == 0, 50))
+	if (intel_wait_for_register(dev_priv,
+				    reg, TRANS_STATE_ENABLE, 0,
+				    50))
 		DRM_ERROR("failed to disable transcoder %c\n", pipe_name(pipe));
 
 	if (HAS_PCH_CPT(dev)) {
@@ -1938,7 +1914,9 @@ static void lpt_disable_pch_transcoder(struct drm_i915_private *dev_priv)
 	val &= ~TRANS_ENABLE;
 	I915_WRITE(LPT_TRANSCONF, val);
 	/* wait for PCH transcoder off, transcoder state */
-	if (wait_for((I915_READ(LPT_TRANSCONF) & TRANS_STATE_ENABLE) == 0, 50))
+	if (intel_wait_for_register(dev_priv,
+				    LPT_TRANSCONF, TRANS_STATE_ENABLE, 0,
+				    50))
 		DRM_ERROR("Failed to disable PCH transcoder\n");
 
 	/* Workaround: clear timing override bit. */
@@ -1957,7 +1935,7 @@ static void lpt_disable_pch_transcoder(struct drm_i915_private *dev_priv)
 static void intel_enable_pipe(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = crtc->pipe;
 	enum transcoder cpu_transcoder = crtc->config->cpu_transcoder;
 	enum pipe pch_transcoder;
@@ -1981,7 +1959,7 @@ static void intel_enable_pipe(struct intel_crtc *crtc)
 	 * need the check.
 	 */
 	if (HAS_GMCH_DISPLAY(dev_priv))
-		if (crtc->config->has_dsi_encoder)
+		if (intel_crtc_has_type(crtc->config, INTEL_OUTPUT_DSI))
 			assert_dsi_pll_enabled(dev_priv);
 		else
 			assert_pll_enabled(dev_priv, pipe);
@@ -2030,7 +2008,7 @@ static void intel_enable_pipe(struct intel_crtc *crtc)
  */
 static void intel_disable_pipe(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc->config->cpu_transcoder;
 	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
@@ -2068,15 +2046,6 @@ static void intel_disable_pipe(struct intel_crtc *crtc)
 		intel_wait_for_pipe_off(crtc);
 }
 
-static bool need_vtd_wa(struct drm_device *dev)
-{
-#ifdef CONFIG_INTEL_IOMMU
-	if (INTEL_INFO(dev)->gen >= 6 && intel_iommu_gfx_mapped)
-		return true;
-#endif
-	return false;
-}
-
 static unsigned int intel_tile_size(const struct drm_i915_private *dev_priv)
 {
 	return IS_GEN2(dev_priv) ? 2048 : 4096;
@@ -2241,7 +2210,7 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 			   unsigned int rotation)
 {
 	struct drm_device *dev = fb->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct i915_ggtt_view view;
 	u32 alignment;
@@ -2258,7 +2227,7 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	 * we should always have valid PTE following the scanout preventing
 	 * the VT-d warning.
 	 */
-	if (need_vtd_wa(dev) && alignment < 256 * 1024)
+	if (intel_scanout_needs_vtd_wa(dev_priv) && alignment < 256 * 1024)
 		alignment = 256 * 1024;
 
 	/*
@@ -2309,7 +2278,7 @@ err_pm:
 	return ret;
 }
 
-static void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation)
+void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation)
 {
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct i915_ggtt_view view;
@@ -2543,7 +2512,7 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 			     struct intel_initial_plane_config *plane_config)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *c;
 	struct intel_crtc *i;
 	struct drm_i915_gem_object *obj;
@@ -2639,7 +2608,7 @@ static void i9xx_update_primary_plane(struct drm_plane *primary,
 				      const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = primary->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
@@ -2752,7 +2721,7 @@ static void i9xx_disable_primary_plane(struct drm_plane *primary,
 				       struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int plane = intel_crtc->plane;
 
@@ -2769,7 +2738,7 @@ static void ironlake_update_primary_plane(struct drm_plane *primary,
 					  const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = primary->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
@@ -2897,7 +2866,7 @@ u32 intel_plane_obj_offset(struct intel_plane *intel_plane,
 static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(SKL_PS_CTRL(intel_crtc->pipe, id), 0);
 	I915_WRITE(SKL_PS_WIN_POS(intel_crtc->pipe, id), 0);
@@ -3007,7 +2976,7 @@ static void skylake_update_primary_plane(struct drm_plane *plane,
 					 const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
@@ -3091,7 +3060,7 @@ static void skylake_disable_primary_plane(struct drm_plane *primary,
 					  struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = to_intel_crtc(crtc)->pipe;
 
 	I915_WRITE(PLANE_CTL(pipe, 0), 0);
@@ -3110,17 +3079,12 @@ intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	return -ENODEV;
 }
 
-static void intel_complete_page_flips(struct drm_device *dev)
+static void intel_complete_page_flips(struct drm_i915_private *dev_priv)
 {
-	struct drm_crtc *crtc;
-
-	for_each_crtc(dev, crtc) {
-		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-		enum plane plane = intel_crtc->plane;
+	struct intel_crtc *crtc;
 
-		intel_prepare_page_flip(dev, plane);
-		intel_finish_page_flip_plane(dev, plane);
-	}
+	for_each_intel_crtc(&dev_priv->drm, crtc)
+		intel_finish_page_flip_cs(dev_priv, crtc->pipe);
 }
 
 static void intel_update_primary_planes(struct drm_device *dev)
@@ -3143,41 +3107,39 @@ static void intel_update_primary_planes(struct drm_device *dev)
 	}
 }
 
-void intel_prepare_reset(struct drm_device *dev)
+void intel_prepare_reset(struct drm_i915_private *dev_priv)
 {
 	/* no reset support for gen2 */
-	if (IS_GEN2(dev))
+	if (IS_GEN2(dev_priv))
 		return;
 
 	/* reset doesn't touch the display */
-	if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev))
+	if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
 		return;
 
-	drm_modeset_lock_all(dev);
+	drm_modeset_lock_all(&dev_priv->drm);
 	/*
 	 * Disabling the crtcs gracefully seems nicer. Also the
 	 * g33 docs say we should at least disable all the planes.
 	 */
-	intel_display_suspend(dev);
+	intel_display_suspend(&dev_priv->drm);
 }
 
-void intel_finish_reset(struct drm_device *dev)
+void intel_finish_reset(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
 	/*
 	 * Flips in the rings will be nuked by the reset,
 	 * so complete all pending flips so that user space
 	 * will get its events and not get stuck.
 	 */
-	intel_complete_page_flips(dev);
+	intel_complete_page_flips(dev_priv);
 
 	/* no reset support for gen2 */
-	if (IS_GEN2(dev))
+	if (IS_GEN2(dev_priv))
 		return;
 
 	/* reset doesn't touch the display */
-	if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev)) {
+	if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) {
 		/*
 		 * Flips in the rings have been nuked by the reset,
 		 * so update the base address of all primary
@@ -3187,7 +3149,7 @@ void intel_finish_reset(struct drm_device *dev)
 		 * FIXME: Atomic will make this obsolete since we won't schedule
 		 * CS-based flips (which might get lost in gpu resets) any more.
 		 */
-		intel_update_primary_planes(dev);
+		intel_update_primary_planes(&dev_priv->drm);
 		return;
 	}
 
@@ -3198,18 +3160,18 @@ void intel_finish_reset(struct drm_device *dev)
 	intel_runtime_pm_disable_interrupts(dev_priv);
 	intel_runtime_pm_enable_interrupts(dev_priv);
 
-	intel_modeset_init_hw(dev);
+	intel_modeset_init_hw(&dev_priv->drm);
 
 	spin_lock_irq(&dev_priv->irq_lock);
 	if (dev_priv->display.hpd_irq_setup)
-		dev_priv->display.hpd_irq_setup(dev);
+		dev_priv->display.hpd_irq_setup(dev_priv);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	intel_display_resume(dev);
+	intel_display_resume(&dev_priv->drm);
 
 	intel_hpd_init(dev_priv);
 
-	drm_modeset_unlock_all(dev);
+	drm_modeset_unlock_all(&dev_priv->drm);
 }
 
 static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc)
@@ -3224,7 +3186,7 @@ static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc)
 		return false;
 
 	spin_lock_irq(&dev->event_lock);
-	pending = to_intel_crtc(crtc)->unpin_work != NULL;
+	pending = to_intel_crtc(crtc)->flip_work != NULL;
 	spin_unlock_irq(&dev->event_lock);
 
 	return pending;
@@ -3234,7 +3196,7 @@ static void intel_update_pipe_config(struct intel_crtc *crtc,
 				     struct intel_crtc_state *old_crtc_state)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc_state *pipe_config =
 		to_intel_crtc_state(crtc->base.state);
 
@@ -3275,7 +3237,7 @@ static void intel_update_pipe_config(struct intel_crtc *crtc,
 static void intel_fdi_normal_train(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 	i915_reg_t reg;
@@ -3318,7 +3280,7 @@ static void intel_fdi_normal_train(struct drm_crtc *crtc)
 static void ironlake_fdi_link_train(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 	i915_reg_t reg;
@@ -3419,7 +3381,7 @@ static const int snb_b_fdi_train_param[] = {
 static void gen6_fdi_link_train(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 	i915_reg_t reg;
@@ -3552,7 +3514,7 @@ static void gen6_fdi_link_train(struct drm_crtc *crtc)
 static void ivb_manual_fdi_link_train(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 	i915_reg_t reg;
@@ -3671,7 +3633,7 @@ train_done:
 static void ironlake_fdi_pll_enable(struct intel_crtc *intel_crtc)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = intel_crtc->pipe;
 	i915_reg_t reg;
 	u32 temp;
@@ -3708,7 +3670,7 @@ static void ironlake_fdi_pll_enable(struct intel_crtc *intel_crtc)
 static void ironlake_fdi_pll_disable(struct intel_crtc *intel_crtc)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = intel_crtc->pipe;
 	i915_reg_t reg;
 	u32 temp;
@@ -3738,7 +3700,7 @@ static void ironlake_fdi_pll_disable(struct intel_crtc *intel_crtc)
 static void ironlake_fdi_disable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 	i915_reg_t reg;
@@ -3803,7 +3765,7 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev)
 		if (atomic_read(&crtc->unpin_work_count) == 0)
 			continue;
 
-		if (crtc->unpin_work)
+		if (crtc->flip_work)
 			intel_wait_for_vblank(dev, crtc->pipe);
 
 		return true;
@@ -3815,11 +3777,9 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev)
 static void page_flip_completed(struct intel_crtc *intel_crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
-	struct intel_unpin_work *work = intel_crtc->unpin_work;
+	struct intel_flip_work *work = intel_crtc->flip_work;
 
-	/* ensure that the unpin work is consistent wrt ->pending. */
-	smp_rmb();
-	intel_crtc->unpin_work = NULL;
+	intel_crtc->flip_work = NULL;
 
 	if (work->event)
 		drm_crtc_send_vblank_event(&intel_crtc->base, work->event);
@@ -3827,7 +3787,7 @@ static void page_flip_completed(struct intel_crtc *intel_crtc)
 	drm_crtc_vblank_put(&intel_crtc->base);
 
 	wake_up_all(&dev_priv->pending_flip_queue);
-	queue_work(dev_priv->wq, &work->work);
+	queue_work(dev_priv->wq, &work->unpin_work);
 
 	trace_i915_flip_complete(intel_crtc->plane,
 				 work->pending_flip_obj);
@@ -3836,7 +3796,7 @@ static void page_flip_completed(struct intel_crtc *intel_crtc)
 static int intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	long ret;
 
 	WARN_ON(waitqueue_active(&dev_priv->pending_flip_queue));
@@ -3851,9 +3811,11 @@ static int intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
 
 	if (ret == 0) {
 		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+		struct intel_flip_work *work;
 
 		spin_lock_irq(&dev->event_lock);
-		if (intel_crtc->unpin_work) {
+		work = intel_crtc->flip_work;
+		if (work && !is_mmio_work(work)) {
 			WARN_ONCE(1, "Removing stuck page flip\n");
 			page_flip_completed(intel_crtc);
 		}
@@ -3997,7 +3959,7 @@ static void ironlake_pch_transcoder_set_timings(struct intel_crtc *crtc,
 						enum pipe pch_transcoder)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = crtc->config->cpu_transcoder;
 
 	I915_WRITE(PCH_TRANS_HTOTAL(pch_transcoder),
@@ -4019,7 +3981,7 @@ static void ironlake_pch_transcoder_set_timings(struct intel_crtc *crtc,
 
 static void cpt_set_fdi_bc_bifurcation(struct drm_device *dev, bool enable)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t temp;
 
 	temp = I915_READ(SOUTH_CHICKEN1);
@@ -4069,7 +4031,7 @@ intel_trans_dp_port_sel(struct drm_crtc *crtc)
 	struct intel_encoder *encoder;
 
 	for_each_encoder_on_crtc(dev, crtc, encoder) {
-		if (encoder->type == INTEL_OUTPUT_DISPLAYPORT ||
+		if (encoder->type == INTEL_OUTPUT_DP ||
 		    encoder->type == INTEL_OUTPUT_EDP)
 			return enc_to_dig_port(&encoder->base)->port;
 	}
@@ -4088,7 +4050,7 @@ intel_trans_dp_port_sel(struct drm_crtc *crtc)
 static void ironlake_pch_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 	u32 temp;
@@ -4138,7 +4100,7 @@ static void ironlake_pch_enable(struct drm_crtc *crtc)
 	intel_fdi_normal_train(crtc);
 
 	/* For PCH DP, enable TRANS_DP_CTL */
-	if (HAS_PCH_CPT(dev) && intel_crtc->config->has_dp_encoder) {
+	if (HAS_PCH_CPT(dev) && intel_crtc_has_dp_encoder(intel_crtc->config)) {
 		const struct drm_display_mode *adjusted_mode =
 			&intel_crtc->config->base.adjusted_mode;
 		u32 bpc = (I915_READ(PIPECONF(pipe)) & PIPECONF_BPC_MASK) >> 5;
@@ -4178,7 +4140,7 @@ static void ironlake_pch_enable(struct drm_crtc *crtc)
 static void lpt_pch_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
 
@@ -4194,7 +4156,7 @@ static void lpt_pch_enable(struct drm_crtc *crtc)
 
 static void cpt_verify_modeset(struct drm_device *dev, int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t dslreg = PIPEDSL(pipe);
 	u32 temp;
 
@@ -4281,8 +4243,9 @@ int skl_update_scaler_crtc(struct intel_crtc_state *state)
 	struct intel_crtc *intel_crtc = to_intel_crtc(state->base.crtc);
 	const struct drm_display_mode *adjusted_mode = &state->base.adjusted_mode;
 
-	DRM_DEBUG_KMS("Updating scaler for [CRTC:%i] scaler_user index %u.%u\n",
-		      intel_crtc->base.base.id, intel_crtc->pipe, SKL_CRTC_INDEX);
+	DRM_DEBUG_KMS("Updating scaler for [CRTC:%d:%s] scaler_user index %u.%u\n",
+		      intel_crtc->base.base.id, intel_crtc->base.name,
+		      intel_crtc->pipe, SKL_CRTC_INDEX);
 
 	return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX,
 		&state->scaler_state.scaler_id, BIT(DRM_ROTATE_0),
@@ -4312,9 +4275,9 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 
 	bool force_detach = !fb || !plane_state->visible;
 
-	DRM_DEBUG_KMS("Updating scaler for [PLANE:%d] scaler_user index %u.%u\n",
-		      intel_plane->base.base.id, intel_crtc->pipe,
-		      drm_plane_index(&intel_plane->base));
+	DRM_DEBUG_KMS("Updating scaler for [PLANE:%d:%s] scaler_user index %u.%u\n",
+		      intel_plane->base.base.id, intel_plane->base.name,
+		      intel_crtc->pipe, drm_plane_index(&intel_plane->base));
 
 	ret = skl_update_scaler(crtc_state, force_detach,
 				drm_plane_index(&intel_plane->base),
@@ -4330,8 +4293,9 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 
 	/* check colorkey */
 	if (plane_state->ckey.flags != I915_SET_COLORKEY_NONE) {
-		DRM_DEBUG_KMS("[PLANE:%d] scaling with color key not allowed",
-			      intel_plane->base.base.id);
+		DRM_DEBUG_KMS("[PLANE:%d:%s] scaling with color key not allowed",
+			      intel_plane->base.base.id,
+			      intel_plane->base.name);
 		return -EINVAL;
 	}
 
@@ -4350,8 +4314,9 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_VYUY:
 		break;
 	default:
-		DRM_DEBUG_KMS("[PLANE:%d] FB:%d unsupported scaling format 0x%x\n",
-			intel_plane->base.base.id, fb->base.id, fb->pixel_format);
+		DRM_DEBUG_KMS("[PLANE:%d:%s] FB:%d unsupported scaling format 0x%x\n",
+			      intel_plane->base.base.id, intel_plane->base.name,
+			      fb->base.id, fb->pixel_format);
 		return -EINVAL;
 	}
 
@@ -4369,7 +4334,7 @@ static void skylake_scaler_disable(struct intel_crtc *crtc)
 static void skylake_pfit_enable(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = crtc->pipe;
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc->config->scaler_state;
@@ -4397,7 +4362,7 @@ static void skylake_pfit_enable(struct intel_crtc *crtc)
 static void ironlake_pfit_enable(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = crtc->pipe;
 
 	if (crtc->config->pch_pfit.enabled) {
@@ -4418,7 +4383,7 @@ static void ironlake_pfit_enable(struct intel_crtc *crtc)
 void hsw_enable_ips(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!crtc->config->ips_enabled)
 		return;
@@ -4446,7 +4411,9 @@ void hsw_enable_ips(struct intel_crtc *crtc)
 		 * and don't wait for vblanks until the end of crtc_enable, then
 		 * the HW state readout code will complain that the expected
 		 * IPS_CTL value is not the one we read. */
-		if (wait_for(I915_READ_NOTRACE(IPS_CTL) & IPS_ENABLE, 50))
+		if (intel_wait_for_register(dev_priv,
+					    IPS_CTL, IPS_ENABLE, IPS_ENABLE,
+					    50))
 			DRM_ERROR("Timed out waiting for IPS enable\n");
 	}
 }
@@ -4454,7 +4421,7 @@ void hsw_enable_ips(struct intel_crtc *crtc)
 void hsw_disable_ips(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!crtc->config->ips_enabled)
 		return;
@@ -4465,7 +4432,9 @@ void hsw_disable_ips(struct intel_crtc *crtc)
 		WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0));
 		mutex_unlock(&dev_priv->rps.hw_lock);
 		/* wait for pcode to finish disabling IPS, which may take up to 42ms */
-		if (wait_for((I915_READ(IPS_CTL) & IPS_ENABLE) == 0, 42))
+		if (intel_wait_for_register(dev_priv,
+					    IPS_CTL, IPS_ENABLE, 0,
+					    42))
 			DRM_ERROR("Timed out waiting for IPS disable\n");
 	} else {
 		I915_WRITE(IPS_CTL, 0);
@@ -4480,7 +4449,7 @@ static void intel_crtc_dpms_overlay_disable(struct intel_crtc *intel_crtc)
 {
 	if (intel_crtc->overlay) {
 		struct drm_device *dev = intel_crtc->base.dev;
-		struct drm_i915_private *dev_priv = dev->dev_private;
+		struct drm_i915_private *dev_priv = to_i915(dev);
 
 		mutex_lock(&dev->struct_mutex);
 		dev_priv->mm.interruptible = false;
@@ -4508,7 +4477,7 @@ static void
 intel_post_enable_primary(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 
@@ -4540,7 +4509,7 @@ static void
 intel_pre_disable_primary(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 
@@ -4567,7 +4536,7 @@ static void
 intel_pre_disable_primary_noatomic(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 
@@ -4626,7 +4595,7 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc_state *pipe_config =
 		to_intel_crtc_state(crtc->base.state);
 	struct drm_atomic_state *old_state = old_crtc_state->base.state;
@@ -4641,14 +4610,14 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state)
 		struct intel_plane_state *old_primary_state =
 			to_intel_plane_state(old_pri_state);
 
-		intel_fbc_pre_update(crtc);
+		intel_fbc_pre_update(crtc, pipe_config, primary_state);
 
 		if (old_primary_state->visible &&
 		    (modeset || !primary_state->visible))
 			intel_pre_disable_primary(&crtc->base);
 	}
 
-	if (pipe_config->disable_cxsr) {
+	if (pipe_config->disable_cxsr && HAS_GMCH_DISPLAY(dev)) {
 		crtc->wm.cxsr_allowed = false;
 
 		/*
@@ -4729,7 +4698,7 @@ static void intel_crtc_disable_planes(struct drm_crtc *crtc, unsigned plane_mask
 static void ironlake_crtc_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
@@ -4757,7 +4726,7 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 	if (intel_crtc->config->has_pch_encoder)
 		intel_prepare_shared_dpll(intel_crtc);
 
-	if (intel_crtc->config->has_dp_encoder)
+	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		intel_dp_set_m_n(intel_crtc, M1_N1);
 
 	intel_set_pipe_timings(intel_crtc);
@@ -4826,7 +4795,7 @@ static bool hsw_crtc_supports_ips(struct intel_crtc *crtc)
 static void haswell_crtc_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe, hsw_workaround_pipe;
@@ -4841,13 +4810,17 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 		intel_set_pch_fifo_underrun_reporting(dev_priv, TRANSCODER_A,
 						      false);
 
+	for_each_encoder_on_crtc(dev, crtc, encoder)
+		if (encoder->pre_pll_enable)
+			encoder->pre_pll_enable(encoder);
+
 	if (intel_crtc->config->shared_dpll)
 		intel_enable_shared_dpll(intel_crtc);
 
-	if (intel_crtc->config->has_dp_encoder)
+	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		intel_dp_set_m_n(intel_crtc, M1_N1);
 
-	if (!intel_crtc->config->has_dsi_encoder)
+	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_set_pipe_timings(intel_crtc);
 
 	intel_set_pipe_src_size(intel_crtc);
@@ -4863,7 +4836,7 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 				     &intel_crtc->config->fdi_m_n, NULL);
 	}
 
-	if (!intel_crtc->config->has_dsi_encoder)
+	if (!transcoder_is_dsi(cpu_transcoder))
 		haswell_set_pipeconf(crtc);
 
 	haswell_set_pipemisc(crtc);
@@ -4885,7 +4858,7 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 	if (intel_crtc->config->has_pch_encoder)
 		dev_priv->display.fdi_link_train(crtc);
 
-	if (!intel_crtc->config->has_dsi_encoder)
+	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_enable_pipe_clock(intel_crtc);
 
 	if (INTEL_INFO(dev)->gen >= 9)
@@ -4900,7 +4873,7 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 	intel_color_load_luts(&pipe_config->base);
 
 	intel_ddi_set_pipe_settings(crtc);
-	if (!intel_crtc->config->has_dsi_encoder)
+	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_enable_transcoder_func(crtc);
 
 	if (dev_priv->display.initial_watermarks != NULL)
@@ -4909,7 +4882,7 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 		intel_update_watermarks(crtc);
 
 	/* XXX: Do the pipe assertions at the right place for BXT DSI. */
-	if (!intel_crtc->config->has_dsi_encoder)
+	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_enable_pipe(intel_crtc);
 
 	if (intel_crtc->config->has_pch_encoder)
@@ -4946,7 +4919,7 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = crtc->pipe;
 
 	/* To avoid upsetting the power well on haswell only disable the pfit if
@@ -4961,7 +4934,7 @@ static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force)
 static void ironlake_crtc_disable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
@@ -5024,7 +4997,7 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc)
 static void haswell_crtc_disable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
@@ -5042,13 +5015,13 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 	assert_vblank_disabled(crtc);
 
 	/* XXX: Do the pipe assertions at the right place for BXT DSI. */
-	if (!intel_crtc->config->has_dsi_encoder)
+	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_disable_pipe(intel_crtc);
 
 	if (intel_crtc->config->dp_encoder_is_mst)
 		intel_ddi_set_vc_payload_alloc(crtc, false);
 
-	if (!intel_crtc->config->has_dsi_encoder)
+	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder);
 
 	if (INTEL_INFO(dev)->gen >= 9)
@@ -5056,7 +5029,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 	else
 		ironlake_pfit_disable(intel_crtc, false);
 
-	if (!intel_crtc->config->has_dsi_encoder)
+	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_disable_pipe_clock(intel_crtc);
 
 	for_each_encoder_on_crtc(dev, crtc, encoder)
@@ -5076,7 +5049,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 static void i9xx_pfit_enable(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc_state *pipe_config = crtc->config;
 
 	if (!pipe_config->gmch_pfit.control)
@@ -5146,7 +5119,7 @@ intel_display_port_power_domain(struct intel_encoder *intel_encoder)
 	case INTEL_OUTPUT_UNKNOWN:
 		/* Only DDI platforms should ever use this output type */
 		WARN_ON_ONCE(!HAS_DDI(dev));
-	case INTEL_OUTPUT_DISPLAYPORT:
+	case INTEL_OUTPUT_DP:
 	case INTEL_OUTPUT_HDMI:
 	case INTEL_OUTPUT_EDP:
 		intel_dig_port = enc_to_dig_port(&intel_encoder->base);
@@ -5180,7 +5153,7 @@ intel_display_port_aux_power_domain(struct intel_encoder *intel_encoder)
 		 * run the DP detection too.
 		 */
 		WARN_ON_ONCE(!HAS_DDI(dev));
-	case INTEL_OUTPUT_DISPLAYPORT:
+	case INTEL_OUTPUT_DP:
 	case INTEL_OUTPUT_EDP:
 		intel_dig_port = enc_to_dig_port(&intel_encoder->base);
 		return port_to_aux_power_domain(intel_dig_port->port);
@@ -5228,7 +5201,7 @@ static unsigned long
 modeset_get_crtc_power_domains(struct drm_crtc *crtc,
 			       struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum intel_display_power_domain domain;
 	unsigned long domains, new_domains, old_domains;
@@ -5269,21 +5242,34 @@ static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv)
 		return max_cdclk_freq*90/100;
 }
 
+static int skl_calc_cdclk(int max_pixclk, int vco);
+
 static void intel_update_max_cdclk(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) {
 		u32 limit = I915_READ(SKL_DFSM) & SKL_DFSM_CDCLK_LIMIT_MASK;
+		int max_cdclk, vco;
+
+		vco = dev_priv->skl_preferred_vco_freq;
+		WARN_ON(vco != 8100000 && vco != 8640000);
 
+		/*
+		 * Use the lower (vco 8640) cdclk values as a
+		 * first guess. skl_calc_cdclk() will correct it
+		 * if the preferred vco is 8100 instead.
+		 */
 		if (limit == SKL_DFSM_CDCLK_LIMIT_675)
-			dev_priv->max_cdclk_freq = 675000;
+			max_cdclk = 617143;
 		else if (limit == SKL_DFSM_CDCLK_LIMIT_540)
-			dev_priv->max_cdclk_freq = 540000;
+			max_cdclk = 540000;
 		else if (limit == SKL_DFSM_CDCLK_LIMIT_450)
-			dev_priv->max_cdclk_freq = 450000;
+			max_cdclk = 432000;
 		else
-			dev_priv->max_cdclk_freq = 337500;
+			max_cdclk = 308571;
+
+		dev_priv->max_cdclk_freq = skl_calc_cdclk(max_cdclk, vco);
 	} else if (IS_BROXTON(dev)) {
 		dev_priv->max_cdclk_freq = 624000;
 	} else if (IS_BROADWELL(dev))  {
@@ -5321,267 +5307,322 @@ static void intel_update_max_cdclk(struct drm_device *dev)
 
 static void intel_update_cdclk(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	dev_priv->cdclk_freq = dev_priv->display.get_display_clock_speed(dev);
-	DRM_DEBUG_DRIVER("Current CD clock rate: %d kHz\n",
-			 dev_priv->cdclk_freq);
+
+	if (INTEL_GEN(dev_priv) >= 9)
+		DRM_DEBUG_DRIVER("Current CD clock rate: %d kHz, VCO: %d kHz, ref: %d kHz\n",
+				 dev_priv->cdclk_freq, dev_priv->cdclk_pll.vco,
+				 dev_priv->cdclk_pll.ref);
+	else
+		DRM_DEBUG_DRIVER("Current CD clock rate: %d kHz\n",
+				 dev_priv->cdclk_freq);
 
 	/*
-	 * Program the gmbus_freq based on the cdclk frequency.
-	 * BSpec erroneously claims we should aim for 4MHz, but
-	 * in fact 1MHz is the correct frequency.
+	 * 9:0 CMBUS [sic] CDCLK frequency (cdfreq):
+	 * Programmng [sic] note: bit[9:2] should be programmed to the number
+	 * of cdclk that generates 4MHz reference clock freq which is used to
+	 * generate GMBus clock. This will vary with the cdclk freq.
 	 */
-	if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
-		/*
-		 * Program the gmbus_freq based on the cdclk frequency.
-		 * BSpec erroneously claims we should aim for 4MHz, but
-		 * in fact 1MHz is the correct frequency.
-		 */
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		I915_WRITE(GMBUSFREQ_VLV, DIV_ROUND_UP(dev_priv->cdclk_freq, 1000));
-	}
+}
 
-	if (dev_priv->max_cdclk_freq == 0)
-		intel_update_max_cdclk(dev);
+/* convert from kHz to .1 fixpoint MHz with -1MHz offset */
+static int skl_cdclk_decimal(int cdclk)
+{
+	return DIV_ROUND_CLOSEST(cdclk - 1000, 500);
 }
 
-static void broxton_set_cdclk(struct drm_i915_private *dev_priv, int frequency)
+static int bxt_de_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 {
-	uint32_t divider;
-	uint32_t ratio;
-	uint32_t current_freq;
-	int ret;
+	int ratio;
 
-	/* frequency = 19.2MHz * ratio / 2 / div{1,1.5,2,4} */
-	switch (frequency) {
+	if (cdclk == dev_priv->cdclk_pll.ref)
+		return 0;
+
+	switch (cdclk) {
+	default:
+		MISSING_CASE(cdclk);
 	case 144000:
+	case 288000:
+	case 384000:
+	case 576000:
+		ratio = 60;
+		break;
+	case 624000:
+		ratio = 65;
+		break;
+	}
+
+	return dev_priv->cdclk_pll.ref * ratio;
+}
+
+static void bxt_de_pll_disable(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE(BXT_DE_PLL_ENABLE, 0);
+
+	/* Timeout 200us */
+	if (intel_wait_for_register(dev_priv,
+				    BXT_DE_PLL_ENABLE, BXT_DE_PLL_LOCK, 0,
+				    1))
+		DRM_ERROR("timeout waiting for DE PLL unlock\n");
+
+	dev_priv->cdclk_pll.vco = 0;
+}
+
+static void bxt_de_pll_enable(struct drm_i915_private *dev_priv, int vco)
+{
+	int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->cdclk_pll.ref);
+	u32 val;
+
+	val = I915_READ(BXT_DE_PLL_CTL);
+	val &= ~BXT_DE_PLL_RATIO_MASK;
+	val |= BXT_DE_PLL_RATIO(ratio);
+	I915_WRITE(BXT_DE_PLL_CTL, val);
+
+	I915_WRITE(BXT_DE_PLL_ENABLE, BXT_DE_PLL_PLL_ENABLE);
+
+	/* Timeout 200us */
+	if (intel_wait_for_register(dev_priv,
+				    BXT_DE_PLL_ENABLE,
+				    BXT_DE_PLL_LOCK,
+				    BXT_DE_PLL_LOCK,
+				    1))
+		DRM_ERROR("timeout waiting for DE PLL lock\n");
+
+	dev_priv->cdclk_pll.vco = vco;
+}
+
+static void bxt_set_cdclk(struct drm_i915_private *dev_priv, int cdclk)
+{
+	u32 val, divider;
+	int vco, ret;
+
+	vco = bxt_de_pll_vco(dev_priv, cdclk);
+
+	DRM_DEBUG_DRIVER("Changing CDCLK to %d kHz (VCO %d kHz)\n", cdclk, vco);
+
+	/* cdclk = vco / 2 / div{1,1.5,2,4} */
+	switch (DIV_ROUND_CLOSEST(vco, cdclk)) {
+	case 8:
 		divider = BXT_CDCLK_CD2X_DIV_SEL_4;
-		ratio = BXT_DE_PLL_RATIO(60);
 		break;
-	case 288000:
+	case 4:
 		divider = BXT_CDCLK_CD2X_DIV_SEL_2;
-		ratio = BXT_DE_PLL_RATIO(60);
 		break;
-	case 384000:
+	case 3:
 		divider = BXT_CDCLK_CD2X_DIV_SEL_1_5;
-		ratio = BXT_DE_PLL_RATIO(60);
-		break;
-	case 576000:
-		divider = BXT_CDCLK_CD2X_DIV_SEL_1;
-		ratio = BXT_DE_PLL_RATIO(60);
 		break;
-	case 624000:
+	case 2:
 		divider = BXT_CDCLK_CD2X_DIV_SEL_1;
-		ratio = BXT_DE_PLL_RATIO(65);
-		break;
-	case 19200:
-		/*
-		 * Bypass frequency with DE PLL disabled. Init ratio, divider
-		 * to suppress GCC warning.
-		 */
-		ratio = 0;
-		divider = 0;
 		break;
 	default:
-		DRM_ERROR("unsupported CDCLK freq %d", frequency);
+		WARN_ON(cdclk != dev_priv->cdclk_pll.ref);
+		WARN_ON(vco != 0);
 
-		return;
+		divider = BXT_CDCLK_CD2X_DIV_SEL_1;
+		break;
 	}
 
-	mutex_lock(&dev_priv->rps.hw_lock);
 	/* Inform power controller of upcoming frequency change */
+	mutex_lock(&dev_priv->rps.hw_lock);
 	ret = sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ,
 				      0x80000000);
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	if (ret) {
 		DRM_ERROR("PCode CDCLK freq change notify failed (err %d, freq %d)\n",
-			  ret, frequency);
+			  ret, cdclk);
 		return;
 	}
 
-	current_freq = I915_READ(CDCLK_CTL) & CDCLK_FREQ_DECIMAL_MASK;
-	/* convert from .1 fixpoint MHz with -1MHz offset to kHz */
-	current_freq = current_freq * 500 + 1000;
+	if (dev_priv->cdclk_pll.vco != 0 &&
+	    dev_priv->cdclk_pll.vco != vco)
+		bxt_de_pll_disable(dev_priv);
 
-	/*
-	 * DE PLL has to be disabled when
-	 * - setting to 19.2MHz (bypass, PLL isn't used)
-	 * - before setting to 624MHz (PLL needs toggling)
-	 * - before setting to any frequency from 624MHz (PLL needs toggling)
-	 */
-	if (frequency == 19200 || frequency == 624000 ||
-	    current_freq == 624000) {
-		I915_WRITE(BXT_DE_PLL_ENABLE, ~BXT_DE_PLL_PLL_ENABLE);
-		/* Timeout 200us */
-		if (wait_for(!(I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_LOCK),
-			     1))
-			DRM_ERROR("timout waiting for DE PLL unlock\n");
-	}
-
-	if (frequency != 19200) {
-		uint32_t val;
-
-		val = I915_READ(BXT_DE_PLL_CTL);
-		val &= ~BXT_DE_PLL_RATIO_MASK;
-		val |= ratio;
-		I915_WRITE(BXT_DE_PLL_CTL, val);
-
-		I915_WRITE(BXT_DE_PLL_ENABLE, BXT_DE_PLL_PLL_ENABLE);
-		/* Timeout 200us */
-		if (wait_for(I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_LOCK, 1))
-			DRM_ERROR("timeout waiting for DE PLL lock\n");
-
-		val = I915_READ(CDCLK_CTL);
-		val &= ~BXT_CDCLK_CD2X_DIV_SEL_MASK;
-		val |= divider;
-		/*
-		 * Disable SSA Precharge when CD clock frequency < 500 MHz,
-		 * enable otherwise.
-		 */
-		val &= ~BXT_CDCLK_SSA_PRECHARGE_ENABLE;
-		if (frequency >= 500000)
-			val |= BXT_CDCLK_SSA_PRECHARGE_ENABLE;
+	if (dev_priv->cdclk_pll.vco != vco)
+		bxt_de_pll_enable(dev_priv, vco);
 
-		val &= ~CDCLK_FREQ_DECIMAL_MASK;
-		/* convert from kHz to .1 fixpoint MHz with -1MHz offset */
-		val |= (frequency - 1000) / 500;
-		I915_WRITE(CDCLK_CTL, val);
-	}
+	val = divider | skl_cdclk_decimal(cdclk);
+	/*
+	 * FIXME if only the cd2x divider needs changing, it could be done
+	 * without shutting off the pipe (if only one pipe is active).
+	 */
+	val |= BXT_CDCLK_CD2X_PIPE_NONE;
+	/*
+	 * Disable SSA Precharge when CD clock frequency < 500 MHz,
+	 * enable otherwise.
+	 */
+	if (cdclk >= 500000)
+		val |= BXT_CDCLK_SSA_PRECHARGE_ENABLE;
+	I915_WRITE(CDCLK_CTL, val);
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 	ret = sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ,
-				      DIV_ROUND_UP(frequency, 25000));
+				      DIV_ROUND_UP(cdclk, 25000));
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	if (ret) {
 		DRM_ERROR("PCode CDCLK freq set failed, (err %d, freq %d)\n",
-			  ret, frequency);
+			  ret, cdclk);
 		return;
 	}
 
-	intel_update_cdclk(dev_priv->dev);
+	intel_update_cdclk(&dev_priv->drm);
 }
 
-static bool broxton_cdclk_is_enabled(struct drm_i915_private *dev_priv)
+static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv)
 {
-	if (!(I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_PLL_ENABLE))
-		return false;
+	u32 cdctl, expected;
 
-	/* TODO: Check for a valid CDCLK rate */
+	intel_update_cdclk(&dev_priv->drm);
 
-	if (!(I915_READ(DBUF_CTL) & DBUF_POWER_REQUEST)) {
-		DRM_DEBUG_DRIVER("CDCLK enabled, but DBUF power not requested\n");
+	if (dev_priv->cdclk_pll.vco == 0 ||
+	    dev_priv->cdclk_freq == dev_priv->cdclk_pll.ref)
+		goto sanitize;
 
-		return false;
-	}
+	/* DPLL okay; verify the cdclock
+	 *
+	 * Some BIOS versions leave an incorrect decimal frequency value and
+	 * set reserved MBZ bits in CDCLK_CTL at least during exiting from S4,
+	 * so sanitize this register.
+	 */
+	cdctl = I915_READ(CDCLK_CTL);
+	/*
+	 * Let's ignore the pipe field, since BIOS could have configured the
+	 * dividers both synching to an active pipe, or asynchronously
+	 * (PIPE_NONE).
+	 */
+	cdctl &= ~BXT_CDCLK_CD2X_PIPE_NONE;
 
-	if (!(I915_READ(DBUF_CTL) & DBUF_POWER_STATE)) {
-		DRM_DEBUG_DRIVER("CDCLK enabled, but DBUF power hasn't settled\n");
+	expected = (cdctl & BXT_CDCLK_CD2X_DIV_SEL_MASK) |
+		   skl_cdclk_decimal(dev_priv->cdclk_freq);
+	/*
+	 * Disable SSA Precharge when CD clock frequency < 500 MHz,
+	 * enable otherwise.
+	 */
+	if (dev_priv->cdclk_freq >= 500000)
+		expected |= BXT_CDCLK_SSA_PRECHARGE_ENABLE;
 
-		return false;
-	}
+	if (cdctl == expected)
+		/* All well; nothing to sanitize */
+		return;
 
-	return true;
-}
+sanitize:
+	DRM_DEBUG_KMS("Sanitizing cdclk programmed by pre-os\n");
 
-bool broxton_cdclk_verify_state(struct drm_i915_private *dev_priv)
-{
-	return broxton_cdclk_is_enabled(dev_priv);
+	/* force cdclk programming */
+	dev_priv->cdclk_freq = 0;
+
+	/* force full PLL disable + enable */
+	dev_priv->cdclk_pll.vco = -1;
 }
 
-void broxton_init_cdclk(struct drm_i915_private *dev_priv)
+void bxt_init_cdclk(struct drm_i915_private *dev_priv)
 {
-	/* check if cd clock is enabled */
-	if (broxton_cdclk_is_enabled(dev_priv)) {
-		DRM_DEBUG_KMS("CDCLK already enabled, won't reprogram it\n");
-		return;
-	}
+	bxt_sanitize_cdclk(dev_priv);
 
-	DRM_DEBUG_KMS("CDCLK not enabled, enabling it\n");
+	if (dev_priv->cdclk_freq != 0 && dev_priv->cdclk_pll.vco != 0)
+		return;
 
 	/*
 	 * FIXME:
 	 * - The initial CDCLK needs to be read from VBT.
 	 *   Need to make this change after VBT has changes for BXT.
-	 * - check if setting the max (or any) cdclk freq is really necessary
-	 *   here, it belongs to modeset time
 	 */
-	broxton_set_cdclk(dev_priv, 624000);
-
-	I915_WRITE(DBUF_CTL, I915_READ(DBUF_CTL) | DBUF_POWER_REQUEST);
-	POSTING_READ(DBUF_CTL);
+	bxt_set_cdclk(dev_priv, bxt_calc_cdclk(0));
+}
 
-	udelay(10);
+void bxt_uninit_cdclk(struct drm_i915_private *dev_priv)
+{
+	bxt_set_cdclk(dev_priv, dev_priv->cdclk_pll.ref);
+}
 
-	if (!(I915_READ(DBUF_CTL) & DBUF_POWER_STATE))
-		DRM_ERROR("DBuf power enable timeout!\n");
+static int skl_calc_cdclk(int max_pixclk, int vco)
+{
+	if (vco == 8640000) {
+		if (max_pixclk > 540000)
+			return 617143;
+		else if (max_pixclk > 432000)
+			return 540000;
+		else if (max_pixclk > 308571)
+			return 432000;
+		else
+			return 308571;
+	} else {
+		if (max_pixclk > 540000)
+			return 675000;
+		else if (max_pixclk > 450000)
+			return 540000;
+		else if (max_pixclk > 337500)
+			return 450000;
+		else
+			return 337500;
+	}
 }
 
-void broxton_uninit_cdclk(struct drm_i915_private *dev_priv)
+static void
+skl_dpll0_update(struct drm_i915_private *dev_priv)
 {
-	I915_WRITE(DBUF_CTL, I915_READ(DBUF_CTL) & ~DBUF_POWER_REQUEST);
-	POSTING_READ(DBUF_CTL);
+	u32 val;
 
-	udelay(10);
+	dev_priv->cdclk_pll.ref = 24000;
+	dev_priv->cdclk_pll.vco = 0;
 
-	if (I915_READ(DBUF_CTL) & DBUF_POWER_STATE)
-		DRM_ERROR("DBuf power disable timeout!\n");
+	val = I915_READ(LCPLL1_CTL);
+	if ((val & LCPLL_PLL_ENABLE) == 0)
+		return;
 
-	/* Set minimum (bypass) frequency, in effect turning off the DE PLL */
-	broxton_set_cdclk(dev_priv, 19200);
-}
+	if (WARN_ON((val & LCPLL_PLL_LOCK) == 0))
+		return;
 
-static const struct skl_cdclk_entry {
-	unsigned int freq;
-	unsigned int vco;
-} skl_cdclk_frequencies[] = {
-	{ .freq = 308570, .vco = 8640 },
-	{ .freq = 337500, .vco = 8100 },
-	{ .freq = 432000, .vco = 8640 },
-	{ .freq = 450000, .vco = 8100 },
-	{ .freq = 540000, .vco = 8100 },
-	{ .freq = 617140, .vco = 8640 },
-	{ .freq = 675000, .vco = 8100 },
-};
+	val = I915_READ(DPLL_CTRL1);
 
-static unsigned int skl_cdclk_decimal(unsigned int freq)
-{
-	return (freq - 1000) / 500;
+	if (WARN_ON((val & (DPLL_CTRL1_HDMI_MODE(SKL_DPLL0) |
+			    DPLL_CTRL1_SSC(SKL_DPLL0) |
+			    DPLL_CTRL1_OVERRIDE(SKL_DPLL0))) !=
+		    DPLL_CTRL1_OVERRIDE(SKL_DPLL0)))
+		return;
+
+	switch (val & DPLL_CTRL1_LINK_RATE_MASK(SKL_DPLL0)) {
+	case DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_810, SKL_DPLL0):
+	case DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1350, SKL_DPLL0):
+	case DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1620, SKL_DPLL0):
+	case DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_2700, SKL_DPLL0):
+		dev_priv->cdclk_pll.vco = 8100000;
+		break;
+	case DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1080, SKL_DPLL0):
+	case DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_2160, SKL_DPLL0):
+		dev_priv->cdclk_pll.vco = 8640000;
+		break;
+	default:
+		MISSING_CASE(val & DPLL_CTRL1_LINK_RATE_MASK(SKL_DPLL0));
+		break;
+	}
 }
 
-static unsigned int skl_cdclk_get_vco(unsigned int freq)
+void skl_set_preferred_cdclk_vco(struct drm_i915_private *dev_priv, int vco)
 {
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(skl_cdclk_frequencies); i++) {
-		const struct skl_cdclk_entry *e = &skl_cdclk_frequencies[i];
+	bool changed = dev_priv->skl_preferred_vco_freq != vco;
 
-		if (e->freq == freq)
-			return e->vco;
-	}
+	dev_priv->skl_preferred_vco_freq = vco;
 
-	return 8100;
+	if (changed)
+		intel_update_max_cdclk(&dev_priv->drm);
 }
 
 static void
-skl_dpll0_enable(struct drm_i915_private *dev_priv, unsigned int required_vco)
+skl_dpll0_enable(struct drm_i915_private *dev_priv, int vco)
 {
-	unsigned int min_freq;
+	int min_cdclk = skl_calc_cdclk(0, vco);
 	u32 val;
 
-	/* select the minimum CDCLK before enabling DPLL 0 */
-	val = I915_READ(CDCLK_CTL);
-	val &= ~CDCLK_FREQ_SEL_MASK | ~CDCLK_FREQ_DECIMAL_MASK;
-	val |= CDCLK_FREQ_337_308;
-
-	if (required_vco == 8640)
-		min_freq = 308570;
-	else
-		min_freq = 337500;
-
-	val = CDCLK_FREQ_337_308 | skl_cdclk_decimal(min_freq);
+	WARN_ON(vco != 8100000 && vco != 8640000);
 
+	/* select the minimum CDCLK before enabling DPLL 0 */
+	val = CDCLK_FREQ_337_308 | skl_cdclk_decimal(min_cdclk);
 	I915_WRITE(CDCLK_CTL, val);
 	POSTING_READ(CDCLK_CTL);
 
@@ -5592,14 +5633,14 @@ skl_dpll0_enable(struct drm_i915_private *dev_priv, unsigned int required_vco)
 	 * 8100 while the eDP 1.4 alternate link rates need a VCO of 8640.
 	 * The modeset code is responsible for the selection of the exact link
 	 * rate later on, with the constraint of choosing a frequency that
-	 * works with required_vco.
+	 * works with vco.
 	 */
 	val = I915_READ(DPLL_CTRL1);
 
 	val &= ~(DPLL_CTRL1_HDMI_MODE(SKL_DPLL0) | DPLL_CTRL1_SSC(SKL_DPLL0) |
 		 DPLL_CTRL1_LINK_RATE_MASK(SKL_DPLL0));
 	val |= DPLL_CTRL1_OVERRIDE(SKL_DPLL0);
-	if (required_vco == 8640)
+	if (vco == 8640000)
 		val |= DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1080,
 					    SKL_DPLL0);
 	else
@@ -5611,8 +5652,27 @@ skl_dpll0_enable(struct drm_i915_private *dev_priv, unsigned int required_vco)
 
 	I915_WRITE(LCPLL1_CTL, I915_READ(LCPLL1_CTL) | LCPLL_PLL_ENABLE);
 
-	if (wait_for(I915_READ(LCPLL1_CTL) & LCPLL_PLL_LOCK, 5))
+	if (intel_wait_for_register(dev_priv,
+				    LCPLL1_CTL, LCPLL_PLL_LOCK, LCPLL_PLL_LOCK,
+				    5))
 		DRM_ERROR("DPLL0 not locked\n");
+
+	dev_priv->cdclk_pll.vco = vco;
+
+	/* We'll want to keep using the current vco from now on. */
+	skl_set_preferred_cdclk_vco(dev_priv, vco);
+}
+
+static void
+skl_dpll0_disable(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE(LCPLL1_CTL, I915_READ(LCPLL1_CTL) & ~LCPLL_PLL_ENABLE);
+	if (intel_wait_for_register(dev_priv,
+				   LCPLL1_CTL, LCPLL_PLL_LOCK, 0,
+				   1))
+		DRM_ERROR("Couldn't disable DPLL0\n");
+
+	dev_priv->cdclk_pll.vco = 0;
 }
 
 static bool skl_cdclk_pcu_ready(struct drm_i915_private *dev_priv)
@@ -5642,12 +5702,14 @@ static bool skl_cdclk_wait_for_pcu_ready(struct drm_i915_private *dev_priv)
 	return false;
 }
 
-static void skl_set_cdclk(struct drm_i915_private *dev_priv, unsigned int freq)
+static void skl_set_cdclk(struct drm_i915_private *dev_priv, int cdclk, int vco)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	u32 freq_select, pcu_ack;
 
-	DRM_DEBUG_DRIVER("Changing CDCLK to %dKHz\n", freq);
+	WARN_ON((cdclk == 24000) != (vco == 0));
+
+	DRM_DEBUG_DRIVER("Changing CDCLK to %d kHz (VCO %d kHz)\n", cdclk, vco);
 
 	if (!skl_cdclk_wait_for_pcu_ready(dev_priv)) {
 		DRM_ERROR("failed to inform PCU about cdclk change\n");
@@ -5655,7 +5717,7 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv, unsigned int freq)
 	}
 
 	/* set CDCLK_CTL */
-	switch(freq) {
+	switch (cdclk) {
 	case 450000:
 	case 432000:
 		freq_select = CDCLK_FREQ_450_432;
@@ -5665,20 +5727,27 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv, unsigned int freq)
 		freq_select = CDCLK_FREQ_540;
 		pcu_ack = 2;
 		break;
-	case 308570:
+	case 308571:
 	case 337500:
 	default:
 		freq_select = CDCLK_FREQ_337_308;
 		pcu_ack = 0;
 		break;
-	case 617140:
+	case 617143:
 	case 675000:
 		freq_select = CDCLK_FREQ_675_617;
 		pcu_ack = 3;
 		break;
 	}
 
-	I915_WRITE(CDCLK_CTL, freq_select | skl_cdclk_decimal(freq));
+	if (dev_priv->cdclk_pll.vco != 0 &&
+	    dev_priv->cdclk_pll.vco != vco)
+		skl_dpll0_disable(dev_priv);
+
+	if (dev_priv->cdclk_pll.vco != vco)
+		skl_dpll0_enable(dev_priv, vco);
+
+	I915_WRITE(CDCLK_CTL, freq_select | skl_cdclk_decimal(cdclk));
 	POSTING_READ(CDCLK_CTL);
 
 	/* inform PCU of the change */
@@ -5689,52 +5758,41 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv, unsigned int freq)
 	intel_update_cdclk(dev);
 }
 
+static void skl_sanitize_cdclk(struct drm_i915_private *dev_priv);
+
 void skl_uninit_cdclk(struct drm_i915_private *dev_priv)
 {
-	/* disable DBUF power */
-	I915_WRITE(DBUF_CTL, I915_READ(DBUF_CTL) & ~DBUF_POWER_REQUEST);
-	POSTING_READ(DBUF_CTL);
-
-	udelay(10);
-
-	if (I915_READ(DBUF_CTL) & DBUF_POWER_STATE)
-		DRM_ERROR("DBuf power disable timeout\n");
-
-	/* disable DPLL0 */
-	I915_WRITE(LCPLL1_CTL, I915_READ(LCPLL1_CTL) & ~LCPLL_PLL_ENABLE);
-	if (wait_for(!(I915_READ(LCPLL1_CTL) & LCPLL_PLL_LOCK), 1))
-		DRM_ERROR("Couldn't disable DPLL0\n");
+	skl_set_cdclk(dev_priv, dev_priv->cdclk_pll.ref, 0);
 }
 
 void skl_init_cdclk(struct drm_i915_private *dev_priv)
 {
-	unsigned int required_vco;
+	int cdclk, vco;
 
-	/* DPLL0 not enabled (happens on early BIOS versions) */
-	if (!(I915_READ(LCPLL1_CTL) & LCPLL_PLL_ENABLE)) {
-		/* enable DPLL0 */
-		required_vco = skl_cdclk_get_vco(dev_priv->skl_boot_cdclk);
-		skl_dpll0_enable(dev_priv, required_vco);
-	}
+	skl_sanitize_cdclk(dev_priv);
 
-	/* set CDCLK to the frequency the BIOS chose */
-	skl_set_cdclk(dev_priv, dev_priv->skl_boot_cdclk);
-
-	/* enable DBUF power */
-	I915_WRITE(DBUF_CTL, I915_READ(DBUF_CTL) | DBUF_POWER_REQUEST);
-	POSTING_READ(DBUF_CTL);
+	if (dev_priv->cdclk_freq != 0 && dev_priv->cdclk_pll.vco != 0) {
+		/*
+		 * Use the current vco as our initial
+		 * guess as to what the preferred vco is.
+		 */
+		if (dev_priv->skl_preferred_vco_freq == 0)
+			skl_set_preferred_cdclk_vco(dev_priv,
+						    dev_priv->cdclk_pll.vco);
+		return;
+	}
 
-	udelay(10);
+	vco = dev_priv->skl_preferred_vco_freq;
+	if (vco == 0)
+		vco = 8100000;
+	cdclk = skl_calc_cdclk(0, vco);
 
-	if (!(I915_READ(DBUF_CTL) & DBUF_POWER_STATE))
-		DRM_ERROR("DBuf power enable timeout\n");
+	skl_set_cdclk(dev_priv, cdclk, vco);
 }
 
-int skl_sanitize_cdclk(struct drm_i915_private *dev_priv)
+static void skl_sanitize_cdclk(struct drm_i915_private *dev_priv)
 {
-	uint32_t lcpll1 = I915_READ(LCPLL1_CTL);
-	uint32_t cdctl = I915_READ(CDCLK_CTL);
-	int freq = dev_priv->skl_boot_cdclk;
+	uint32_t cdctl, expected;
 
 	/*
 	 * check if the pre-os intialized the display
@@ -5744,8 +5802,10 @@ int skl_sanitize_cdclk(struct drm_i915_private *dev_priv)
 	if ((I915_READ(SWF_ILK(0x18)) & 0x00FFFFFF) == 0)
 		goto sanitize;
 
+	intel_update_cdclk(&dev_priv->drm);
 	/* Is PLL enabled and locked ? */
-	if (!((lcpll1 & LCPLL_PLL_ENABLE) && (lcpll1 & LCPLL_PLL_LOCK)))
+	if (dev_priv->cdclk_pll.vco == 0 ||
+	    dev_priv->cdclk_freq == dev_priv->cdclk_pll.ref)
 		goto sanitize;
 
 	/* DPLL okay; verify the cdclock
@@ -5754,25 +5814,26 @@ int skl_sanitize_cdclk(struct drm_i915_private *dev_priv)
 	 * decimal part is programmed wrong from BIOS where pre-os does not
 	 * enable display. Verify the same as well.
 	 */
-	if (cdctl == ((cdctl & CDCLK_FREQ_SEL_MASK) | skl_cdclk_decimal(freq)))
+	cdctl = I915_READ(CDCLK_CTL);
+	expected = (cdctl & CDCLK_FREQ_SEL_MASK) |
+		skl_cdclk_decimal(dev_priv->cdclk_freq);
+	if (cdctl == expected)
 		/* All well; nothing to sanitize */
-		return false;
+		return;
+
 sanitize:
-	/*
-	 * As of now initialize with max cdclk till
-	 * we get dynamic cdclk support
-	 * */
-	dev_priv->skl_boot_cdclk = dev_priv->max_cdclk_freq;
-	skl_init_cdclk(dev_priv);
+	DRM_DEBUG_KMS("Sanitizing cdclk programmed by pre-os\n");
 
-	/* we did have to sanitize */
-	return true;
+	/* force cdclk programming */
+	dev_priv->cdclk_freq = 0;
+	/* force full PLL disable + enable */
+	dev_priv->cdclk_pll.vco = -1;
 }
 
 /* Adjust CDclk dividers to allow high res or save power if possible */
 static void valleyview_set_cdclk(struct drm_device *dev, int cdclk)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val, cmd;
 
 	WARN_ON(dev_priv->display.get_display_clock_speed(dev)
@@ -5837,7 +5898,7 @@ static void valleyview_set_cdclk(struct drm_device *dev, int cdclk)
 
 static void cherryview_set_cdclk(struct drm_device *dev, int cdclk)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val, cmd;
 
 	WARN_ON(dev_priv->display.get_display_clock_speed(dev)
@@ -5906,21 +5967,15 @@ static int valleyview_calc_cdclk(struct drm_i915_private *dev_priv,
 		return 200000;
 }
 
-static int broxton_calc_cdclk(struct drm_i915_private *dev_priv,
-			      int max_pixclk)
+static int bxt_calc_cdclk(int max_pixclk)
 {
-	/*
-	 * FIXME:
-	 * - remove the guardband, it's not needed on BXT
-	 * - set 19.2MHz bypass frequency if there are no active pipes
-	 */
-	if (max_pixclk > 576000*9/10)
+	if (max_pixclk > 576000)
 		return 624000;
-	else if (max_pixclk > 384000*9/10)
+	else if (max_pixclk > 384000)
 		return 576000;
-	else if (max_pixclk > 288000*9/10)
+	else if (max_pixclk > 288000)
 		return 384000;
-	else if (max_pixclk > 144000*9/10)
+	else if (max_pixclk > 144000)
 		return 288000;
 	else
 		return 144000;
@@ -5931,7 +5986,7 @@ static int intel_mode_max_pixclk(struct drm_device *dev,
 				 struct drm_atomic_state *state)
 {
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
 	unsigned max_pixclk = 0, i;
@@ -5958,14 +6013,11 @@ static int intel_mode_max_pixclk(struct drm_device *dev,
 static int valleyview_modeset_calc_cdclk(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int max_pixclk = intel_mode_max_pixclk(dev, state);
 	struct intel_atomic_state *intel_state =
 		to_intel_atomic_state(state);
 
-	if (max_pixclk < 0)
-		return max_pixclk;
-
 	intel_state->cdclk = intel_state->dev_cdclk =
 		valleyview_calc_cdclk(dev_priv, max_pixclk);
 
@@ -5975,22 +6027,17 @@ static int valleyview_modeset_calc_cdclk(struct drm_atomic_state *state)
 	return 0;
 }
 
-static int broxton_modeset_calc_cdclk(struct drm_atomic_state *state)
+static int bxt_modeset_calc_cdclk(struct drm_atomic_state *state)
 {
-	struct drm_device *dev = state->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int max_pixclk = intel_mode_max_pixclk(dev, state);
+	int max_pixclk = ilk_max_pixel_rate(state);
 	struct intel_atomic_state *intel_state =
 		to_intel_atomic_state(state);
 
-	if (max_pixclk < 0)
-		return max_pixclk;
-
 	intel_state->cdclk = intel_state->dev_cdclk =
-		broxton_calc_cdclk(dev_priv, max_pixclk);
+		bxt_calc_cdclk(max_pixclk);
 
 	if (!intel_state->active_crtcs)
-		intel_state->dev_cdclk = broxton_calc_cdclk(dev_priv, 0);
+		intel_state->dev_cdclk = bxt_calc_cdclk(0);
 
 	return 0;
 }
@@ -6034,7 +6081,7 @@ static void vlv_program_pfi_credits(struct drm_i915_private *dev_priv)
 static void valleyview_modeset_commit_cdclk(struct drm_atomic_state *old_state)
 {
 	struct drm_device *dev = old_state->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_atomic_state *old_intel_state =
 		to_intel_atomic_state(old_state);
 	unsigned req_cdclk = old_intel_state->dev_cdclk;
@@ -6073,14 +6120,14 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc)
 	if (WARN_ON(intel_crtc->active))
 		return;
 
-	if (intel_crtc->config->has_dp_encoder)
+	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		intel_dp_set_m_n(intel_crtc, M1_N1);
 
 	intel_set_pipe_timings(intel_crtc);
 	intel_set_pipe_src_size(intel_crtc);
 
 	if (IS_CHERRYVIEW(dev) && pipe == PIPE_B) {
-		struct drm_i915_private *dev_priv = dev->dev_private;
+		struct drm_i915_private *dev_priv = to_i915(dev);
 
 		I915_WRITE(CHV_BLEND(pipe), CHV_BLEND_LEGACY);
 		I915_WRITE(CHV_CANVAS(pipe), 0);
@@ -6125,7 +6172,7 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc)
 static void i9xx_set_pll_dividers(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(FP0(crtc->pipe), crtc->config->dpll_hw_state.fp0);
 	I915_WRITE(FP1(crtc->pipe), crtc->config->dpll_hw_state.fp1);
@@ -6146,7 +6193,7 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc)
 
 	i9xx_set_pll_dividers(intel_crtc);
 
-	if (intel_crtc->config->has_dp_encoder)
+	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		intel_dp_set_m_n(intel_crtc, M1_N1);
 
 	intel_set_pipe_timings(intel_crtc);
@@ -6182,7 +6229,7 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc)
 static void i9xx_pfit_disable(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!crtc->config->gmch_pfit.control)
 		return;
@@ -6197,7 +6244,7 @@ static void i9xx_pfit_disable(struct intel_crtc *crtc)
 static void i9xx_crtc_disable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
@@ -6223,7 +6270,7 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 		if (encoder->post_disable)
 			encoder->post_disable(encoder);
 
-	if (!intel_crtc->config->has_dsi_encoder) {
+	if (!intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_DSI)) {
 		if (IS_CHERRYVIEW(dev))
 			chv_disable_pll(dev_priv, pipe);
 		else if (IS_VALLEYVIEW(dev))
@@ -6252,7 +6299,7 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc)
 		return;
 
 	if (to_intel_plane_state(crtc->primary->state)->visible) {
-		WARN_ON(intel_crtc->unpin_work);
+		WARN_ON(intel_crtc->flip_work);
 
 		intel_pre_disable_primary_noatomic(crtc);
 
@@ -6262,8 +6309,8 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc)
 
 	dev_priv->display.crtc_disable(crtc);
 
-	DRM_DEBUG_KMS("[CRTC:%d] hw state adjusted, was enabled, now disabled\n",
-		      crtc->base.id);
+	DRM_DEBUG_KMS("[CRTC:%d:%s] hw state adjusted, was enabled, now disabled\n",
+		      crtc->base.id, crtc->name);
 
 	WARN_ON(drm_atomic_set_mode_for_crtc(crtc->state, NULL) < 0);
 	crtc->state->active = false;
@@ -6541,7 +6588,7 @@ static void hsw_compute_ips_config(struct intel_crtc *crtc,
 				   struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	pipe_config->ips_enabled = i915.enable_ips &&
 		hsw_crtc_supports_ips(crtc) &&
@@ -6561,12 +6608,12 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 				     struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	int clock_limit = dev_priv->max_dotclk_freq;
 
-	/* FIXME should check pixel clock limits on all platforms */
 	if (INTEL_INFO(dev)->gen < 4) {
-		int clock_limit = dev_priv->max_cdclk_freq * 9 / 10;
+		clock_limit = dev_priv->max_cdclk_freq * 9 / 10;
 
 		/*
 		 * Enable double wide mode when the dot clock
@@ -6574,16 +6621,16 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 		 */
 		if (intel_crtc_supports_double_wide(crtc) &&
 		    adjusted_mode->crtc_clock > clock_limit) {
-			clock_limit *= 2;
+			clock_limit = dev_priv->max_dotclk_freq;
 			pipe_config->double_wide = true;
 		}
+	}
 
-		if (adjusted_mode->crtc_clock > clock_limit) {
-			DRM_DEBUG_KMS("requested pixel clock (%d kHz) too high (max: %d kHz, double wide: %s)\n",
-				      adjusted_mode->crtc_clock, clock_limit,
-				      yesno(pipe_config->double_wide));
-			return -EINVAL;
-		}
+	if (adjusted_mode->crtc_clock > clock_limit) {
+		DRM_DEBUG_KMS("requested pixel clock (%d kHz) too high (max: %d kHz, double wide: %s)\n",
+			      adjusted_mode->crtc_clock, clock_limit,
+			      yesno(pipe_config->double_wide));
+		return -EINVAL;
 	}
 
 	/*
@@ -6592,7 +6639,7 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 	 * - LVDS dual channel mode
 	 * - Double wide pipe
 	 */
-	if ((intel_pipe_will_have_type(pipe_config, INTEL_OUTPUT_LVDS) &&
+	if ((intel_crtc_has_type(pipe_config, INTEL_OUTPUT_LVDS) &&
 	     intel_is_dual_link_lvds(dev)) || pipe_config->double_wide)
 		pipe_config->pipe_src_w &= ~1;
 
@@ -6615,81 +6662,103 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 static int skylake_get_display_clock_speed(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	uint32_t lcpll1 = I915_READ(LCPLL1_CTL);
-	uint32_t cdctl = I915_READ(CDCLK_CTL);
-	uint32_t linkrate;
+	uint32_t cdctl;
 
-	if (!(lcpll1 & LCPLL_PLL_ENABLE))
-		return 24000; /* 24MHz is the cd freq with NSSC ref */
+	skl_dpll0_update(dev_priv);
 
-	if ((cdctl & CDCLK_FREQ_SEL_MASK) == CDCLK_FREQ_540)
-		return 540000;
+	if (dev_priv->cdclk_pll.vco == 0)
+		return dev_priv->cdclk_pll.ref;
 
-	linkrate = (I915_READ(DPLL_CTRL1) &
-		    DPLL_CTRL1_LINK_RATE_MASK(SKL_DPLL0)) >> 1;
+	cdctl = I915_READ(CDCLK_CTL);
 
-	if (linkrate == DPLL_CTRL1_LINK_RATE_2160 ||
-	    linkrate == DPLL_CTRL1_LINK_RATE_1080) {
-		/* vco 8640 */
+	if (dev_priv->cdclk_pll.vco == 8640000) {
 		switch (cdctl & CDCLK_FREQ_SEL_MASK) {
 		case CDCLK_FREQ_450_432:
 			return 432000;
 		case CDCLK_FREQ_337_308:
-			return 308570;
+			return 308571;
+		case CDCLK_FREQ_540:
+			return 540000;
 		case CDCLK_FREQ_675_617:
-			return 617140;
+			return 617143;
 		default:
-			WARN(1, "Unknown cd freq selection\n");
+			MISSING_CASE(cdctl & CDCLK_FREQ_SEL_MASK);
 		}
 	} else {
-		/* vco 8100 */
 		switch (cdctl & CDCLK_FREQ_SEL_MASK) {
 		case CDCLK_FREQ_450_432:
 			return 450000;
 		case CDCLK_FREQ_337_308:
 			return 337500;
+		case CDCLK_FREQ_540:
+			return 540000;
 		case CDCLK_FREQ_675_617:
 			return 675000;
 		default:
-			WARN(1, "Unknown cd freq selection\n");
+			MISSING_CASE(cdctl & CDCLK_FREQ_SEL_MASK);
 		}
 	}
 
-	/* error case, do as if DPLL0 isn't enabled */
-	return 24000;
+	return dev_priv->cdclk_pll.ref;
+}
+
+static void bxt_de_pll_update(struct drm_i915_private *dev_priv)
+{
+	u32 val;
+
+	dev_priv->cdclk_pll.ref = 19200;
+	dev_priv->cdclk_pll.vco = 0;
+
+	val = I915_READ(BXT_DE_PLL_ENABLE);
+	if ((val & BXT_DE_PLL_PLL_ENABLE) == 0)
+		return;
+
+	if (WARN_ON((val & BXT_DE_PLL_LOCK) == 0))
+		return;
+
+	val = I915_READ(BXT_DE_PLL_CTL);
+	dev_priv->cdclk_pll.vco = (val & BXT_DE_PLL_RATIO_MASK) *
+		dev_priv->cdclk_pll.ref;
 }
 
 static int broxton_get_display_clock_speed(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	uint32_t cdctl = I915_READ(CDCLK_CTL);
-	uint32_t pll_ratio = I915_READ(BXT_DE_PLL_CTL) & BXT_DE_PLL_RATIO_MASK;
-	uint32_t pll_enab = I915_READ(BXT_DE_PLL_ENABLE);
-	int cdclk;
+	u32 divider;
+	int div, vco;
+
+	bxt_de_pll_update(dev_priv);
 
-	if (!(pll_enab & BXT_DE_PLL_PLL_ENABLE))
-		return 19200;
+	vco = dev_priv->cdclk_pll.vco;
+	if (vco == 0)
+		return dev_priv->cdclk_pll.ref;
 
-	cdclk = 19200 * pll_ratio / 2;
+	divider = I915_READ(CDCLK_CTL) & BXT_CDCLK_CD2X_DIV_SEL_MASK;
 
-	switch (cdctl & BXT_CDCLK_CD2X_DIV_SEL_MASK) {
+	switch (divider) {
 	case BXT_CDCLK_CD2X_DIV_SEL_1:
-		return cdclk;  /* 576MHz or 624MHz */
+		div = 2;
+		break;
 	case BXT_CDCLK_CD2X_DIV_SEL_1_5:
-		return cdclk * 2 / 3; /* 384MHz */
+		div = 3;
+		break;
 	case BXT_CDCLK_CD2X_DIV_SEL_2:
-		return cdclk / 2; /* 288MHz */
+		div = 4;
+		break;
 	case BXT_CDCLK_CD2X_DIV_SEL_4:
-		return cdclk / 4; /* 144MHz */
+		div = 8;
+		break;
+	default:
+		MISSING_CASE(divider);
+		return dev_priv->cdclk_pll.ref;
 	}
 
-	/* error case, do as if DE PLL isn't enabled */
-	return 19200;
+	return DIV_ROUND_CLOSEST(vco, div);
 }
 
 static int broadwell_get_display_clock_speed(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t lcpll = I915_READ(LCPLL_CTL);
 	uint32_t freq = lcpll & LCPLL_CLK_FREQ_MASK;
 
@@ -6709,7 +6778,7 @@ static int broadwell_get_display_clock_speed(struct drm_device *dev)
 
 static int haswell_get_display_clock_speed(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t lcpll = I915_READ(LCPLL_CTL);
 	uint32_t freq = lcpll & LCPLL_CLK_FREQ_MASK;
 
@@ -6843,7 +6912,7 @@ static int i830_get_display_clock_speed(struct drm_device *dev)
 
 static unsigned int intel_hpll_vco(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	static const unsigned int blb_vco[8] = {
 		[0] = 3200000,
 		[1] = 4000000,
@@ -7063,7 +7132,7 @@ static uint32_t i9xx_dpll_compute_fp(struct dpll *dpll)
 
 static void i9xx_update_pll_dividers(struct intel_crtc *crtc,
 				     struct intel_crtc_state *crtc_state,
-				     intel_clock_t *reduced_clock)
+				     struct dpll *reduced_clock)
 {
 	struct drm_device *dev = crtc->base.dev;
 	u32 fp, fp2 = 0;
@@ -7081,7 +7150,7 @@ static void i9xx_update_pll_dividers(struct intel_crtc *crtc,
 	crtc_state->dpll_hw_state.fp0 = fp;
 
 	crtc->lowfreq_avail = false;
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS) &&
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS) &&
 	    reduced_clock) {
 		crtc_state->dpll_hw_state.fp1 = fp2;
 		crtc->lowfreq_avail = true;
@@ -7123,7 +7192,7 @@ static void intel_pch_transcoder_set_m_n(struct intel_crtc *crtc,
 					 struct intel_link_m_n *m_n)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = crtc->pipe;
 
 	I915_WRITE(PCH_TRANS_DATA_M1(pipe), TU_SIZE(m_n->tu) | m_n->gmch_m);
@@ -7137,7 +7206,7 @@ static void intel_cpu_transcoder_set_m_n(struct intel_crtc *crtc,
 					 struct intel_link_m_n *m2_n2)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = crtc->pipe;
 	enum transcoder transcoder = crtc->config->cpu_transcoder;
 
@@ -7200,7 +7269,7 @@ static void vlv_compute_dpll(struct intel_crtc *crtc,
 		pipe_config->dpll_hw_state.dpll |= DPLL_INTEGRATED_CRI_CLK_VLV;
 
 	/* DPLL not used with DSI, but still need the rest set up */
-	if (!pipe_config->has_dsi_encoder)
+	if (!intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DSI))
 		pipe_config->dpll_hw_state.dpll |= DPLL_VCO_ENABLE |
 			DPLL_EXT_BUFFER_ENABLE_VLV;
 
@@ -7217,7 +7286,7 @@ static void chv_compute_dpll(struct intel_crtc *crtc,
 		pipe_config->dpll_hw_state.dpll |= DPLL_INTEGRATED_CRI_CLK_VLV;
 
 	/* DPLL not used with DSI, but still need the rest set up */
-	if (!pipe_config->has_dsi_encoder)
+	if (!intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DSI))
 		pipe_config->dpll_hw_state.dpll |= DPLL_VCO_ENABLE;
 
 	pipe_config->dpll_hw_state.dpll_md =
@@ -7228,7 +7297,7 @@ static void vlv_prepare_pll(struct intel_crtc *crtc,
 			    const struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = crtc->pipe;
 	u32 mdiv;
 	u32 bestn, bestm1, bestm2, bestp1, bestp2;
@@ -7287,15 +7356,15 @@ static void vlv_prepare_pll(struct intel_crtc *crtc,
 
 	/* Set HBR and RBR LPF coefficients */
 	if (pipe_config->port_clock == 162000 ||
-	    intel_pipe_has_type(crtc, INTEL_OUTPUT_ANALOG) ||
-	    intel_pipe_has_type(crtc, INTEL_OUTPUT_HDMI))
+	    intel_crtc_has_type(crtc->config, INTEL_OUTPUT_ANALOG) ||
+	    intel_crtc_has_type(crtc->config, INTEL_OUTPUT_HDMI))
 		vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW10(pipe),
 				 0x009f0003);
 	else
 		vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW10(pipe),
 				 0x00d0000f);
 
-	if (pipe_config->has_dp_encoder) {
+	if (intel_crtc_has_dp_encoder(pipe_config)) {
 		/* Use SSC source */
 		if (pipe == PIPE_A)
 			vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe),
@@ -7315,8 +7384,7 @@ static void vlv_prepare_pll(struct intel_crtc *crtc,
 
 	coreclk = vlv_dpio_read(dev_priv, pipe, VLV_PLL_DW7(pipe));
 	coreclk = (coreclk & 0x0000ff00) | 0x01c00000;
-	if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT) ||
-	    intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))
+	if (intel_crtc_has_dp_encoder(crtc->config))
 		coreclk |= 0x01000000;
 	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW7(pipe), coreclk);
 
@@ -7328,7 +7396,7 @@ static void chv_prepare_pll(struct intel_crtc *crtc,
 			    const struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = crtc->pipe;
 	enum dpio_channel port = vlv_pipe_to_channel(pipe);
 	u32 loopfilter, tribuf_calcntr;
@@ -7487,22 +7555,18 @@ void vlv_force_pll_off(struct drm_device *dev, enum pipe pipe)
 
 static void i9xx_compute_dpll(struct intel_crtc *crtc,
 			      struct intel_crtc_state *crtc_state,
-			      intel_clock_t *reduced_clock)
+			      struct dpll *reduced_clock)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 dpll;
-	bool is_sdvo;
 	struct dpll *clock = &crtc_state->dpll;
 
 	i9xx_update_pll_dividers(crtc, crtc_state, reduced_clock);
 
-	is_sdvo = intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_SDVO) ||
-		intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_HDMI);
-
 	dpll = DPLL_VGA_MODE_DIS;
 
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS))
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS))
 		dpll |= DPLLB_MODE_LVDS;
 	else
 		dpll |= DPLLB_MODE_DAC_SERIAL;
@@ -7512,10 +7576,11 @@ static void i9xx_compute_dpll(struct intel_crtc *crtc,
 			<< SDVO_MULTIPLIER_SHIFT_HIRES;
 	}
 
-	if (is_sdvo)
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_SDVO) ||
+	    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
 		dpll |= DPLL_SDVO_HIGH_SPEED;
 
-	if (crtc_state->has_dp_encoder)
+	if (intel_crtc_has_dp_encoder(crtc_state))
 		dpll |= DPLL_SDVO_HIGH_SPEED;
 
 	/* compute bitmask from p1 value */
@@ -7545,7 +7610,7 @@ static void i9xx_compute_dpll(struct intel_crtc *crtc,
 
 	if (crtc_state->sdvo_tv_clock)
 		dpll |= PLL_REF_INPUT_TVCLKINBC;
-	else if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS) &&
+	else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS) &&
 		 intel_panel_use_ssc(dev_priv))
 		dpll |= PLLB_REF_INPUT_SPREADSPECTRUMIN;
 	else
@@ -7563,10 +7628,10 @@ static void i9xx_compute_dpll(struct intel_crtc *crtc,
 
 static void i8xx_compute_dpll(struct intel_crtc *crtc,
 			      struct intel_crtc_state *crtc_state,
-			      intel_clock_t *reduced_clock)
+			      struct dpll *reduced_clock)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 dpll;
 	struct dpll *clock = &crtc_state->dpll;
 
@@ -7574,7 +7639,7 @@ static void i8xx_compute_dpll(struct intel_crtc *crtc,
 
 	dpll = DPLL_VGA_MODE_DIS;
 
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		dpll |= (1 << (clock->p1 - 1)) << DPLL_FPA01_P1_POST_DIV_SHIFT;
 	} else {
 		if (clock->p1 == 2)
@@ -7585,10 +7650,10 @@ static void i8xx_compute_dpll(struct intel_crtc *crtc,
 			dpll |= PLL_P2_DIVIDE_BY_4;
 	}
 
-	if (!IS_I830(dev) && intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_DVO))
+	if (!IS_I830(dev) && intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DVO))
 		dpll |= DPLL_DVO_2X_MODE;
 
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS) &&
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS) &&
 	    intel_panel_use_ssc(dev_priv))
 		dpll |= PLLB_REF_INPUT_SPREADSPECTRUMIN;
 	else
@@ -7601,7 +7666,7 @@ static void i8xx_compute_dpll(struct intel_crtc *crtc,
 static void intel_set_pipe_timings(struct intel_crtc *intel_crtc)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = intel_crtc->pipe;
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
 	const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode;
@@ -7618,7 +7683,7 @@ static void intel_set_pipe_timings(struct intel_crtc *intel_crtc)
 		crtc_vtotal -= 1;
 		crtc_vblank_end -= 1;
 
-		if (intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_SDVO))
+		if (intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_SDVO))
 			vsyncshift = (adjusted_mode->crtc_htotal - 1) / 2;
 		else
 			vsyncshift = adjusted_mode->crtc_hsync_start -
@@ -7663,7 +7728,7 @@ static void intel_set_pipe_timings(struct intel_crtc *intel_crtc)
 static void intel_set_pipe_src_size(struct intel_crtc *intel_crtc)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = intel_crtc->pipe;
 
 	/* pipesrc controls the size that is scaled from, which should
@@ -7678,7 +7743,7 @@ static void intel_get_pipe_timings(struct intel_crtc *crtc,
 				   struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
 	uint32_t tmp;
 
@@ -7713,7 +7778,7 @@ static void intel_get_pipe_src_size(struct intel_crtc *crtc,
 				    struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 tmp;
 
 	tmp = I915_READ(PIPESRC(crtc->pipe));
@@ -7751,7 +7816,7 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t pipeconf;
 
 	pipeconf = 0;
@@ -7797,7 +7862,7 @@ static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc)
 
 	if (intel_crtc->config->base.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) {
 		if (INTEL_INFO(dev)->gen < 4 ||
-		    intel_pipe_has_type(intel_crtc, INTEL_OUTPUT_SDVO))
+		    intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_SDVO))
 			pipeconf |= PIPECONF_INTERLACE_W_FIELD_INDICATION;
 		else
 			pipeconf |= PIPECONF_INTERLACE_W_SYNC_SHIFT;
@@ -7816,21 +7881,21 @@ static int i8xx_crtc_compute_clock(struct intel_crtc *crtc,
 				   struct intel_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const intel_limit_t *limit;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	const struct intel_limit *limit;
 	int refclk = 48000;
 
 	memset(&crtc_state->dpll_hw_state, 0,
 	       sizeof(crtc_state->dpll_hw_state));
 
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		if (intel_panel_use_ssc(dev_priv)) {
 			refclk = dev_priv->vbt.lvds_ssc_freq;
 			DRM_DEBUG_KMS("using SSC reference clock of %d kHz\n", refclk);
 		}
 
 		limit = &intel_limits_i8xx_lvds;
-	} else if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_DVO)) {
+	} else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DVO)) {
 		limit = &intel_limits_i8xx_dvo;
 	} else {
 		limit = &intel_limits_i8xx_dac;
@@ -7852,14 +7917,14 @@ static int g4x_crtc_compute_clock(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const intel_limit_t *limit;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	const struct intel_limit *limit;
 	int refclk = 96000;
 
 	memset(&crtc_state->dpll_hw_state, 0,
 	       sizeof(crtc_state->dpll_hw_state));
 
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		if (intel_panel_use_ssc(dev_priv)) {
 			refclk = dev_priv->vbt.lvds_ssc_freq;
 			DRM_DEBUG_KMS("using SSC reference clock of %d kHz\n", refclk);
@@ -7869,10 +7934,10 @@ static int g4x_crtc_compute_clock(struct intel_crtc *crtc,
 			limit = &intel_limits_g4x_dual_channel_lvds;
 		else
 			limit = &intel_limits_g4x_single_channel_lvds;
-	} else if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_HDMI) ||
-		   intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_ANALOG)) {
+	} else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI) ||
+		   intel_crtc_has_type(crtc_state, INTEL_OUTPUT_ANALOG)) {
 		limit = &intel_limits_g4x_hdmi;
-	} else if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_SDVO)) {
+	} else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_SDVO)) {
 		limit = &intel_limits_g4x_sdvo;
 	} else {
 		/* The option is for other outputs */
@@ -7895,14 +7960,14 @@ static int pnv_crtc_compute_clock(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const intel_limit_t *limit;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	const struct intel_limit *limit;
 	int refclk = 96000;
 
 	memset(&crtc_state->dpll_hw_state, 0,
 	       sizeof(crtc_state->dpll_hw_state));
 
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		if (intel_panel_use_ssc(dev_priv)) {
 			refclk = dev_priv->vbt.lvds_ssc_freq;
 			DRM_DEBUG_KMS("using SSC reference clock of %d kHz\n", refclk);
@@ -7929,14 +7994,14 @@ static int i9xx_crtc_compute_clock(struct intel_crtc *crtc,
 				   struct intel_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const intel_limit_t *limit;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	const struct intel_limit *limit;
 	int refclk = 96000;
 
 	memset(&crtc_state->dpll_hw_state, 0,
 	       sizeof(crtc_state->dpll_hw_state));
 
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		if (intel_panel_use_ssc(dev_priv)) {
 			refclk = dev_priv->vbt.lvds_ssc_freq;
 			DRM_DEBUG_KMS("using SSC reference clock of %d kHz\n", refclk);
@@ -7963,7 +8028,7 @@ static int chv_crtc_compute_clock(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state)
 {
 	int refclk = 100000;
-	const intel_limit_t *limit = &intel_limits_chv;
+	const struct intel_limit *limit = &intel_limits_chv;
 
 	memset(&crtc_state->dpll_hw_state, 0,
 	       sizeof(crtc_state->dpll_hw_state));
@@ -7984,7 +8049,7 @@ static int vlv_crtc_compute_clock(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state)
 {
 	int refclk = 100000;
-	const intel_limit_t *limit = &intel_limits_vlv;
+	const struct intel_limit *limit = &intel_limits_vlv;
 
 	memset(&crtc_state->dpll_hw_state, 0,
 	       sizeof(crtc_state->dpll_hw_state));
@@ -8005,7 +8070,7 @@ static void i9xx_get_pfit_config(struct intel_crtc *crtc,
 				 struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t tmp;
 
 	if (INTEL_INFO(dev)->gen <= 3 && (IS_I830(dev) || !IS_MOBILE(dev)))
@@ -8032,9 +8097,9 @@ static void vlv_crtc_clock_get(struct intel_crtc *crtc,
 			       struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = pipe_config->cpu_transcoder;
-	intel_clock_t clock;
+	struct dpll clock;
 	u32 mdiv;
 	int refclk = 100000;
 
@@ -8060,7 +8125,7 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc,
 			      struct intel_initial_plane_config *plane_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val, base, offset;
 	int pipe = crtc->pipe, plane = crtc->plane;
 	int fourcc, pixel_format;
@@ -8128,10 +8193,10 @@ static void chv_crtc_clock_get(struct intel_crtc *crtc,
 			       struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = pipe_config->cpu_transcoder;
 	enum dpio_channel port = vlv_pipe_to_channel(pipe);
-	intel_clock_t clock;
+	struct dpll clock;
 	u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2, pll_dw3;
 	int refclk = 100000;
 
@@ -8162,7 +8227,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 				 struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 	uint32_t tmp;
 	bool ret;
@@ -8273,7 +8338,7 @@ out:
 
 static void ironlake_init_pch_refclk(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *encoder;
 	int i;
 	u32 val, final;
@@ -8544,7 +8609,7 @@ static void lpt_program_fdi_mphy(struct drm_i915_private *dev_priv)
 static void lpt_enable_clkout_dp(struct drm_device *dev, bool with_spread,
 				 bool with_fdi)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t reg, tmp;
 
 	if (WARN(with_fdi && !with_spread, "FDI requires downspread\n"))
@@ -8583,7 +8648,7 @@ static void lpt_enable_clkout_dp(struct drm_device *dev, bool with_spread,
 /* Sequence to disable CLKOUT_DP */
 static void lpt_disable_clkout_dp(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t reg, tmp;
 
 	mutex_lock(&dev_priv->sb_lock);
@@ -8704,7 +8769,7 @@ void intel_init_pch_refclk(struct drm_device *dev)
 
 static void ironlake_set_pipeconf(struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 	uint32_t val;
@@ -8746,7 +8811,7 @@ static void ironlake_set_pipeconf(struct drm_crtc *crtc)
 
 static void haswell_set_pipeconf(struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
 	u32 val = 0;
@@ -8765,7 +8830,7 @@ static void haswell_set_pipeconf(struct drm_crtc *crtc)
 
 static void haswell_set_pipemisc(struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
 	if (IS_BROADWELL(dev_priv) || INTEL_INFO(dev_priv)->gen >= 9) {
@@ -8814,41 +8879,17 @@ static bool ironlake_needs_fb_cb_tune(struct dpll *dpll, int factor)
 
 static void ironlake_compute_dpll(struct intel_crtc *intel_crtc,
 				  struct intel_crtc_state *crtc_state,
-				  intel_clock_t *reduced_clock)
+				  struct dpll *reduced_clock)
 {
 	struct drm_crtc *crtc = &intel_crtc->base;
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_atomic_state *state = crtc_state->base.state;
-	struct drm_connector *connector;
-	struct drm_connector_state *connector_state;
-	struct intel_encoder *encoder;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 dpll, fp, fp2;
-	int factor, i;
-	bool is_lvds = false, is_sdvo = false;
-
-	for_each_connector_in_state(state, connector, connector_state, i) {
-		if (connector_state->crtc != crtc_state->base.crtc)
-			continue;
-
-		encoder = to_intel_encoder(connector_state->best_encoder);
-
-		switch (encoder->type) {
-		case INTEL_OUTPUT_LVDS:
-			is_lvds = true;
-			break;
-		case INTEL_OUTPUT_SDVO:
-		case INTEL_OUTPUT_HDMI:
-			is_sdvo = true;
-			break;
-		default:
-			break;
-		}
-	}
+	int factor;
 
 	/* Enable autotuning of the PLL clock (if permissible) */
 	factor = 21;
-	if (is_lvds) {
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		if ((intel_panel_use_ssc(dev_priv) &&
 		     dev_priv->vbt.lvds_ssc_freq == 100000) ||
 		    (HAS_PCH_IBX(dev) && intel_is_dual_link_lvds(dev)))
@@ -8872,7 +8913,7 @@ static void ironlake_compute_dpll(struct intel_crtc *intel_crtc,
 
 	dpll = 0;
 
-	if (is_lvds)
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS))
 		dpll |= DPLLB_MODE_LVDS;
 	else
 		dpll |= DPLLB_MODE_DAC_SERIAL;
@@ -8880,9 +8921,11 @@ static void ironlake_compute_dpll(struct intel_crtc *intel_crtc,
 	dpll |= (crtc_state->pixel_multiplier - 1)
 		<< PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT;
 
-	if (is_sdvo)
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_SDVO) ||
+	    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI))
 		dpll |= DPLL_SDVO_HIGH_SPEED;
-	if (crtc_state->has_dp_encoder)
+
+	if (intel_crtc_has_dp_encoder(crtc_state))
 		dpll |= DPLL_SDVO_HIGH_SPEED;
 
 	/* compute bitmask from p1 value */
@@ -8905,7 +8948,8 @@ static void ironlake_compute_dpll(struct intel_crtc *intel_crtc,
 		break;
 	}
 
-	if (is_lvds && intel_panel_use_ssc(dev_priv))
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS) &&
+	    intel_panel_use_ssc(dev_priv))
 		dpll |= PLLB_REF_INPUT_SPREADSPECTRUMIN;
 	else
 		dpll |= PLL_REF_INPUT_DREFCLK;
@@ -8921,11 +8965,11 @@ static int ironlake_crtc_compute_clock(struct intel_crtc *crtc,
 				       struct intel_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	intel_clock_t reduced_clock;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct dpll reduced_clock;
 	bool has_reduced_clock = false;
 	struct intel_shared_dpll *pll;
-	const intel_limit_t *limit;
+	const struct intel_limit *limit;
 	int refclk = 120000;
 
 	memset(&crtc_state->dpll_hw_state, 0,
@@ -8937,7 +8981,7 @@ static int ironlake_crtc_compute_clock(struct intel_crtc *crtc,
 	if (!crtc_state->has_pch_encoder)
 		return 0;
 
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		if (intel_panel_use_ssc(dev_priv)) {
 			DRM_DEBUG_KMS("using SSC reference clock of %d kHz\n",
 				      dev_priv->vbt.lvds_ssc_freq);
@@ -8976,7 +9020,7 @@ static int ironlake_crtc_compute_clock(struct intel_crtc *crtc,
 		return -EINVAL;
 	}
 
-	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS) &&
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS) &&
 	    has_reduced_clock)
 		crtc->lowfreq_avail = true;
 
@@ -8987,7 +9031,7 @@ static void intel_pch_transcoder_get_m_n(struct intel_crtc *crtc,
 					 struct intel_link_m_n *m_n)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = crtc->pipe;
 
 	m_n->link_m = I915_READ(PCH_TRANS_LINK_M1(pipe));
@@ -9005,7 +9049,7 @@ static void intel_cpu_transcoder_get_m_n(struct intel_crtc *crtc,
 					 struct intel_link_m_n *m2_n2)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = crtc->pipe;
 
 	if (INTEL_INFO(dev)->gen >= 5) {
@@ -9063,7 +9107,7 @@ static void skylake_get_pfit_config(struct intel_crtc *crtc,
 				    struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc_scaler_state *scaler_state = &pipe_config->scaler_state;
 	uint32_t ps_ctrl = 0;
 	int id = -1;
@@ -9094,7 +9138,7 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 				 struct intel_initial_plane_config *plane_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val, base, offset, stride_mult, tiling;
 	int pipe = crtc->pipe;
 	int fourcc, pixel_format;
@@ -9177,7 +9221,7 @@ static void ironlake_get_pfit_config(struct intel_crtc *crtc,
 				     struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t tmp;
 
 	tmp = I915_READ(PF_CTL(crtc->pipe));
@@ -9202,7 +9246,7 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc,
 				  struct intel_initial_plane_config *plane_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val, base, offset;
 	int pipe = crtc->pipe;
 	int fourcc, pixel_format;
@@ -9270,7 +9314,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 				     struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 	uint32_t tmp;
 	bool ret;
@@ -9320,6 +9364,10 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 		ironlake_get_fdi_m_n_config(crtc, pipe_config);
 
 		if (HAS_PCH_IBX(dev_priv)) {
+			/*
+			 * The pipe->pch transcoder and pch transcoder->pll
+			 * mapping is fixed.
+			 */
 			pll_id = (enum intel_dpll_id) crtc->pipe;
 		} else {
 			tmp = I915_READ(PCH_DPLL_SEL);
@@ -9361,7 +9409,7 @@ out:
 
 static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct intel_crtc *crtc;
 
 	for_each_intel_crtc(dev, crtc)
@@ -9395,7 +9443,7 @@ static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
 
 static uint32_t hsw_read_dcomp(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 
 	if (IS_HASWELL(dev))
 		return I915_READ(D_COMP_HSW);
@@ -9405,7 +9453,7 @@ static uint32_t hsw_read_dcomp(struct drm_i915_private *dev_priv)
 
 static void hsw_write_dcomp(struct drm_i915_private *dev_priv, uint32_t val)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 
 	if (IS_HASWELL(dev)) {
 		mutex_lock(&dev_priv->rps.hw_lock);
@@ -9451,7 +9499,7 @@ static void hsw_disable_lcpll(struct drm_i915_private *dev_priv,
 	I915_WRITE(LCPLL_CTL, val);
 	POSTING_READ(LCPLL_CTL);
 
-	if (wait_for((I915_READ(LCPLL_CTL) & LCPLL_PLL_LOCK) == 0, 1))
+	if (intel_wait_for_register(dev_priv, LCPLL_CTL, LCPLL_PLL_LOCK, 0, 1))
 		DRM_ERROR("LCPLL still locked\n");
 
 	val = hsw_read_dcomp(dev_priv);
@@ -9506,7 +9554,9 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 	val &= ~LCPLL_PLL_DISABLE;
 	I915_WRITE(LCPLL_CTL, val);
 
-	if (wait_for(I915_READ(LCPLL_CTL) & LCPLL_PLL_LOCK, 5))
+	if (intel_wait_for_register(dev_priv,
+				    LCPLL_CTL, LCPLL_PLL_LOCK, LCPLL_PLL_LOCK,
+				    5))
 		DRM_ERROR("LCPLL not locked yet\n");
 
 	if (val & LCPLL_CD_SOURCE_FCLK) {
@@ -9520,7 +9570,7 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 	}
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	intel_update_cdclk(dev_priv->dev);
+	intel_update_cdclk(&dev_priv->drm);
 }
 
 /*
@@ -9548,7 +9598,7 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
  */
 void hsw_enable_pc8(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	uint32_t val;
 
 	DRM_DEBUG_KMS("Enabling package C8+\n");
@@ -9565,7 +9615,7 @@ void hsw_enable_pc8(struct drm_i915_private *dev_priv)
 
 void hsw_disable_pc8(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	uint32_t val;
 
 	DRM_DEBUG_KMS("Disabling package C8+\n");
@@ -9580,21 +9630,21 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv)
 	}
 }
 
-static void broxton_modeset_commit_cdclk(struct drm_atomic_state *old_state)
+static void bxt_modeset_commit_cdclk(struct drm_atomic_state *old_state)
 {
 	struct drm_device *dev = old_state->dev;
 	struct intel_atomic_state *old_intel_state =
 		to_intel_atomic_state(old_state);
 	unsigned int req_cdclk = old_intel_state->dev_cdclk;
 
-	broxton_set_cdclk(to_i915(dev), req_cdclk);
+	bxt_set_cdclk(to_i915(dev), req_cdclk);
 }
 
 /* compute the max rate for new configuration */
 static int ilk_max_pixel_rate(struct drm_atomic_state *state)
 {
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
-	struct drm_i915_private *dev_priv = state->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(state->dev);
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *cstate;
 	struct intel_crtc_state *crtc_state;
@@ -9630,7 +9680,7 @@ static int ilk_max_pixel_rate(struct drm_atomic_state *state)
 
 static void broadwell_set_cdclk(struct drm_device *dev, int cdclk)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t val, data;
 	int ret;
 
@@ -9707,6 +9757,18 @@ static void broadwell_set_cdclk(struct drm_device *dev, int cdclk)
 	     cdclk, dev_priv->cdclk_freq);
 }
 
+static int broadwell_calc_cdclk(int max_pixclk)
+{
+	if (max_pixclk > 540000)
+		return 675000;
+	else if (max_pixclk > 450000)
+		return 540000;
+	else if (max_pixclk > 337500)
+		return 450000;
+	else
+		return 337500;
+}
+
 static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->dev);
@@ -9718,14 +9780,7 @@ static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state)
 	 * FIXME should also account for plane ratio
 	 * once 64bpp pixel formats are supported.
 	 */
-	if (max_pixclk > 540000)
-		cdclk = 675000;
-	else if (max_pixclk > 450000)
-		cdclk = 540000;
-	else if (max_pixclk > 337500)
-		cdclk = 450000;
-	else
-		cdclk = 337500;
+	cdclk = broadwell_calc_cdclk(max_pixclk);
 
 	if (cdclk > dev_priv->max_cdclk_freq) {
 		DRM_DEBUG_KMS("requested cdclk (%d kHz) exceeds max (%d kHz)\n",
@@ -9735,7 +9790,7 @@ static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state)
 
 	intel_state->cdclk = intel_state->dev_cdclk = cdclk;
 	if (!intel_state->active_crtcs)
-		intel_state->dev_cdclk = 337500;
+		intel_state->dev_cdclk = broadwell_calc_cdclk(0);
 
 	return 0;
 }
@@ -9750,13 +9805,51 @@ static void broadwell_modeset_commit_cdclk(struct drm_atomic_state *old_state)
 	broadwell_set_cdclk(dev, req_cdclk);
 }
 
+static int skl_modeset_calc_cdclk(struct drm_atomic_state *state)
+{
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	struct drm_i915_private *dev_priv = to_i915(state->dev);
+	const int max_pixclk = ilk_max_pixel_rate(state);
+	int vco = intel_state->cdclk_pll_vco;
+	int cdclk;
+
+	/*
+	 * FIXME should also account for plane ratio
+	 * once 64bpp pixel formats are supported.
+	 */
+	cdclk = skl_calc_cdclk(max_pixclk, vco);
+
+	/*
+	 * FIXME move the cdclk caclulation to
+	 * compute_config() so we can fail gracegully.
+	 */
+	if (cdclk > dev_priv->max_cdclk_freq) {
+		DRM_ERROR("requested cdclk (%d kHz) exceeds max (%d kHz)\n",
+			  cdclk, dev_priv->max_cdclk_freq);
+		cdclk = dev_priv->max_cdclk_freq;
+	}
+
+	intel_state->cdclk = intel_state->dev_cdclk = cdclk;
+	if (!intel_state->active_crtcs)
+		intel_state->dev_cdclk = skl_calc_cdclk(0, vco);
+
+	return 0;
+}
+
+static void skl_modeset_commit_cdclk(struct drm_atomic_state *old_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(old_state->dev);
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(old_state);
+	unsigned int req_cdclk = intel_state->dev_cdclk;
+	unsigned int req_vco = intel_state->cdclk_pll_vco;
+
+	skl_set_cdclk(dev_priv, req_cdclk, req_vco);
+}
+
 static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
 				      struct intel_crtc_state *crtc_state)
 {
-	struct intel_encoder *intel_encoder =
-		intel_ddi_get_crtc_new_encoder(crtc_state);
-
-	if (intel_encoder->type != INTEL_OUTPUT_DSI) {
+	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) {
 		if (!intel_ddi_pll_select(crtc, crtc_state))
 			return -EINVAL;
 	}
@@ -9866,10 +9959,14 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc,
 				     unsigned long *power_domain_mask)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
 
+	/*
+	 * The pipe->transcoder mapping is fixed with the exception of the eDP
+	 * transcoder handled below.
+	 */
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 
 	/*
@@ -9913,14 +10010,12 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc,
 					 unsigned long *power_domain_mask)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 	enum port port;
 	enum transcoder cpu_transcoder;
 	u32 tmp;
 
-	pipe_config->has_dsi_encoder = false;
-
 	for_each_port_masked(port, BIT(PORT_A) | BIT(PORT_C)) {
 		if (port == PORT_A)
 			cpu_transcoder = TRANSCODER_DSI_A;
@@ -9952,18 +10047,17 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc,
 			continue;
 
 		pipe_config->cpu_transcoder = cpu_transcoder;
-		pipe_config->has_dsi_encoder = true;
 		break;
 	}
 
-	return pipe_config->has_dsi_encoder;
+	return transcoder_is_dsi(pipe_config->cpu_transcoder);
 }
 
 static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
 				       struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_shared_dpll *pll;
 	enum port port;
 	uint32_t tmp;
@@ -10006,7 +10100,7 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 				    struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 	unsigned long power_domain_mask;
 	bool active;
@@ -10020,18 +10114,16 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 
 	active = hsw_get_transcoder_state(crtc, pipe_config, &power_domain_mask);
 
-	if (IS_BROXTON(dev_priv)) {
-		bxt_get_dsi_transcoder_state(crtc, pipe_config,
-					     &power_domain_mask);
-		WARN_ON(active && pipe_config->has_dsi_encoder);
-		if (pipe_config->has_dsi_encoder)
-			active = true;
+	if (IS_BROXTON(dev_priv) &&
+	    bxt_get_dsi_transcoder_state(crtc, pipe_config, &power_domain_mask)) {
+		WARN_ON(active);
+		active = true;
 	}
 
 	if (!active)
 		goto out;
 
-	if (!pipe_config->has_dsi_encoder) {
+	if (!transcoder_is_dsi(pipe_config->cpu_transcoder)) {
 		haswell_get_ddi_port_state(crtc, pipe_config);
 		intel_get_pipe_timings(crtc, pipe_config);
 	}
@@ -10082,7 +10174,7 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base,
 			       const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	uint32_t cntl = 0, size = 0;
 
@@ -10145,7 +10237,7 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base,
 			       const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 	uint32_t cntl = 0;
@@ -10193,7 +10285,7 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc,
 				     const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
 	u32 base = intel_crtc->cursor_addr;
@@ -10337,10 +10429,10 @@ intel_framebuffer_create_for_mode(struct drm_device *dev,
 	struct drm_i915_gem_object *obj;
 	struct drm_mode_fb_cmd2 mode_cmd = { 0 };
 
-	obj = i915_gem_alloc_object(dev,
+	obj = i915_gem_object_create(dev,
 				    intel_framebuffer_size_for_mode(mode, bpp));
-	if (obj == NULL)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
 
 	mode_cmd.width = mode->hdisplay;
 	mode_cmd.height = mode->vdisplay;
@@ -10360,7 +10452,7 @@ mode_fits_in_fbdev(struct drm_device *dev,
 		   struct drm_display_mode *mode)
 {
 #ifdef CONFIG_DRM_FBDEV_EMULATION
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
 	struct drm_framebuffer *fb;
 
@@ -10630,7 +10722,7 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 static int i9xx_pll_refclk(struct drm_device *dev,
 			   const struct intel_crtc_state *pipe_config)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 dpll = pipe_config->dpll_hw_state.dpll;
 
 	if ((dpll & PLL_REF_INPUT_MASK) == PLLB_REF_INPUT_SPREADSPECTRUMIN)
@@ -10648,11 +10740,11 @@ static void i9xx_crtc_clock_get(struct intel_crtc *crtc,
 				struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe = pipe_config->cpu_transcoder;
 	u32 dpll = pipe_config->dpll_hw_state.dpll;
 	u32 fp;
-	intel_clock_t clock;
+	struct dpll clock;
 	int port_clock;
 	int refclk = i9xx_pll_refclk(dev, pipe_config);
 
@@ -10774,7 +10866,7 @@ static void ironlake_pch_clock_get(struct intel_crtc *crtc,
 struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 					     struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
 	struct drm_display_mode *mode;
@@ -10826,48 +10918,20 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 	return mode;
 }
 
-void intel_mark_busy(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (dev_priv->mm.busy)
-		return;
-
-	intel_runtime_pm_get(dev_priv);
-	i915_update_gfx_val(dev_priv);
-	if (INTEL_INFO(dev)->gen >= 6)
-		gen6_rps_busy(dev_priv);
-	dev_priv->mm.busy = true;
-}
-
-void intel_mark_idle(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (!dev_priv->mm.busy)
-		return;
-
-	dev_priv->mm.busy = false;
-
-	if (INTEL_INFO(dev)->gen >= 6)
-		gen6_rps_idle(dev->dev_private);
-
-	intel_runtime_pm_put(dev_priv);
-}
-
 static void intel_crtc_destroy(struct drm_crtc *crtc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct intel_unpin_work *work;
+	struct intel_flip_work *work;
 
 	spin_lock_irq(&dev->event_lock);
-	work = intel_crtc->unpin_work;
-	intel_crtc->unpin_work = NULL;
+	work = intel_crtc->flip_work;
+	intel_crtc->flip_work = NULL;
 	spin_unlock_irq(&dev->event_lock);
 
 	if (work) {
-		cancel_work_sync(&work->work);
+		cancel_work_sync(&work->mmio_work);
+		cancel_work_sync(&work->unpin_work);
 		kfree(work);
 	}
 
@@ -10878,12 +10942,15 @@ static void intel_crtc_destroy(struct drm_crtc *crtc)
 
 static void intel_unpin_work_fn(struct work_struct *__work)
 {
-	struct intel_unpin_work *work =
-		container_of(__work, struct intel_unpin_work, work);
+	struct intel_flip_work *work =
+		container_of(__work, struct intel_flip_work, unpin_work);
 	struct intel_crtc *crtc = to_intel_crtc(work->crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_plane *primary = crtc->base.primary;
 
+	if (is_mmio_work(work))
+		flush_work(&work->mmio_work);
+
 	mutex_lock(&dev->struct_mutex);
 	intel_unpin_fb_obj(work->old_fb, primary->state->rotation);
 	drm_gem_object_unreference(&work->pending_flip_obj->base);
@@ -10902,63 +10969,17 @@ static void intel_unpin_work_fn(struct work_struct *__work)
 	kfree(work);
 }
 
-static void do_intel_finish_page_flip(struct drm_device *dev,
-				      struct drm_crtc *crtc)
-{
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_unpin_work *work;
-	unsigned long flags;
-
-	/* Ignore early vblank irqs */
-	if (intel_crtc == NULL)
-		return;
-
-	/*
-	 * This is called both by irq handlers and the reset code (to complete
-	 * lost pageflips) so needs the full irqsave spinlocks.
-	 */
-	spin_lock_irqsave(&dev->event_lock, flags);
-	work = intel_crtc->unpin_work;
-
-	/* Ensure we don't miss a work->pending update ... */
-	smp_rmb();
-
-	if (work == NULL || atomic_read(&work->pending) < INTEL_FLIP_COMPLETE) {
-		spin_unlock_irqrestore(&dev->event_lock, flags);
-		return;
-	}
-
-	page_flip_completed(intel_crtc);
-
-	spin_unlock_irqrestore(&dev->event_lock, flags);
-}
-
-void intel_finish_page_flip(struct drm_device *dev, int pipe)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
-
-	do_intel_finish_page_flip(dev, crtc);
-}
-
-void intel_finish_page_flip_plane(struct drm_device *dev, int plane)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_crtc *crtc = dev_priv->plane_to_crtc_mapping[plane];
-
-	do_intel_finish_page_flip(dev, crtc);
-}
-
 /* Is 'a' after or equal to 'b'? */
 static bool g4x_flip_count_after_eq(u32 a, u32 b)
 {
 	return !((a - b) & 0x80000000);
 }
 
-static bool page_flip_finished(struct intel_crtc *crtc)
+static bool __pageflip_finished_cs(struct intel_crtc *crtc,
+				   struct intel_flip_work *work)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned reset_counter;
 
 	reset_counter = i915_reset_counter(&dev_priv->gpu_error);
@@ -10997,40 +11018,103 @@ static bool page_flip_finished(struct intel_crtc *crtc)
 	 * anyway, we don't really care.
 	 */
 	return (I915_READ(DSPSURFLIVE(crtc->plane)) & ~0xfff) ==
-		crtc->unpin_work->gtt_offset &&
+		crtc->flip_work->gtt_offset &&
 		g4x_flip_count_after_eq(I915_READ(PIPE_FLIPCOUNT_G4X(crtc->pipe)),
-				    crtc->unpin_work->flip_count);
+				    crtc->flip_work->flip_count);
 }
 
-void intel_prepare_page_flip(struct drm_device *dev, int plane)
+static bool
+__pageflip_finished_mmio(struct intel_crtc *crtc,
+			       struct intel_flip_work *work)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(dev_priv->plane_to_crtc_mapping[plane]);
+	/*
+	 * MMIO work completes when vblank is different from
+	 * flip_queued_vblank.
+	 *
+	 * Reset counter value doesn't matter, this is handled by
+	 * i915_wait_request finishing early, so no need to handle
+	 * reset here.
+	 */
+	return intel_crtc_get_vblank_counter(crtc) != work->flip_queued_vblank;
+}
+
+
+static bool pageflip_finished(struct intel_crtc *crtc,
+			      struct intel_flip_work *work)
+{
+	if (!atomic_read(&work->pending))
+		return false;
+
+	smp_rmb();
+
+	if (is_mmio_work(work))
+		return __pageflip_finished_mmio(crtc, work);
+	else
+		return __pageflip_finished_cs(crtc, work);
+}
+
+void intel_finish_page_flip_cs(struct drm_i915_private *dev_priv, int pipe)
+{
+	struct drm_device *dev = &dev_priv->drm;
+	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_flip_work *work;
 	unsigned long flags;
 
+	/* Ignore early vblank irqs */
+	if (!crtc)
+		return;
 
 	/*
 	 * This is called both by irq handlers and the reset code (to complete
 	 * lost pageflips) so needs the full irqsave spinlocks.
-	 *
-	 * NB: An MMIO update of the plane base pointer will also
-	 * generate a page-flip completion irq, i.e. every modeset
-	 * is also accompanied by a spurious intel_prepare_page_flip().
 	 */
 	spin_lock_irqsave(&dev->event_lock, flags);
-	if (intel_crtc->unpin_work && page_flip_finished(intel_crtc))
-		atomic_inc_not_zero(&intel_crtc->unpin_work->pending);
+	work = intel_crtc->flip_work;
+
+	if (work != NULL &&
+	    !is_mmio_work(work) &&
+	    pageflip_finished(intel_crtc, work))
+		page_flip_completed(intel_crtc);
+
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
 
-static inline void intel_mark_page_flip_active(struct intel_unpin_work *work)
+void intel_finish_page_flip_mmio(struct drm_i915_private *dev_priv, int pipe)
 {
+	struct drm_device *dev = &dev_priv->drm;
+	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_flip_work *work;
+	unsigned long flags;
+
+	/* Ignore early vblank irqs */
+	if (!crtc)
+		return;
+
+	/*
+	 * This is called both by irq handlers and the reset code (to complete
+	 * lost pageflips) so needs the full irqsave spinlocks.
+	 */
+	spin_lock_irqsave(&dev->event_lock, flags);
+	work = intel_crtc->flip_work;
+
+	if (work != NULL &&
+	    is_mmio_work(work) &&
+	    pageflip_finished(intel_crtc, work))
+		page_flip_completed(intel_crtc);
+
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
+static inline void intel_mark_page_flip_active(struct intel_crtc *crtc,
+					       struct intel_flip_work *work)
+{
+	work->flip_queued_vblank = intel_crtc_get_vblank_counter(crtc);
+
 	/* Ensure that the work item is consistent when activating it ... */
-	smp_wmb();
-	atomic_set(&work->pending, INTEL_FLIP_PENDING);
-	/* and that it is marked active as soon as the irq could fire. */
-	smp_wmb();
+	smp_mb__before_atomic();
+	atomic_set(&work->pending, 1);
 }
 
 static int intel_gen2_queue_flip(struct drm_device *dev,
@@ -11061,10 +11145,9 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 	intel_ring_emit(engine, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(engine, fb->pitches[0]);
-	intel_ring_emit(engine, intel_crtc->unpin_work->gtt_offset);
+	intel_ring_emit(engine, intel_crtc->flip_work->gtt_offset);
 	intel_ring_emit(engine, 0); /* aux display base address, unused */
 
-	intel_mark_page_flip_active(intel_crtc->unpin_work);
 	return 0;
 }
 
@@ -11093,10 +11176,9 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
 	intel_ring_emit(engine, MI_DISPLAY_FLIP_I915 |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(engine, fb->pitches[0]);
-	intel_ring_emit(engine, intel_crtc->unpin_work->gtt_offset);
+	intel_ring_emit(engine, intel_crtc->flip_work->gtt_offset);
 	intel_ring_emit(engine, MI_NOOP);
 
-	intel_mark_page_flip_active(intel_crtc->unpin_work);
 	return 0;
 }
 
@@ -11108,7 +11190,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 				 uint32_t flags)
 {
 	struct intel_engine_cs *engine = req->engine;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	uint32_t pf, pipesrc;
 	int ret;
@@ -11124,7 +11206,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 	intel_ring_emit(engine, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(engine, fb->pitches[0]);
-	intel_ring_emit(engine, intel_crtc->unpin_work->gtt_offset |
+	intel_ring_emit(engine, intel_crtc->flip_work->gtt_offset |
 			obj->tiling_mode);
 
 	/* XXX Enabling the panel-fitter across page-flip is so far
@@ -11135,7 +11217,6 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 	pipesrc = I915_READ(PIPESRC(intel_crtc->pipe)) & 0x0fff0fff;
 	intel_ring_emit(engine, pf | pipesrc);
 
-	intel_mark_page_flip_active(intel_crtc->unpin_work);
 	return 0;
 }
 
@@ -11147,7 +11228,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 				 uint32_t flags)
 {
 	struct intel_engine_cs *engine = req->engine;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	uint32_t pf, pipesrc;
 	int ret;
@@ -11159,7 +11240,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 	intel_ring_emit(engine, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(engine, fb->pitches[0] | obj->tiling_mode);
-	intel_ring_emit(engine, intel_crtc->unpin_work->gtt_offset);
+	intel_ring_emit(engine, intel_crtc->flip_work->gtt_offset);
 
 	/* Contrary to the suggestions in the documentation,
 	 * "Enable Panel Fitter" does not seem to be required when page
@@ -11171,7 +11252,6 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 	pipesrc = I915_READ(PIPESRC(intel_crtc->pipe)) & 0x0fff0fff;
 	intel_ring_emit(engine, pf | pipesrc);
 
-	intel_mark_page_flip_active(intel_crtc->unpin_work);
 	return 0;
 }
 
@@ -11263,16 +11343,17 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 
 	intel_ring_emit(engine, MI_DISPLAY_FLIP_I915 | plane_bit);
 	intel_ring_emit(engine, (fb->pitches[0] | obj->tiling_mode));
-	intel_ring_emit(engine, intel_crtc->unpin_work->gtt_offset);
+	intel_ring_emit(engine, intel_crtc->flip_work->gtt_offset);
 	intel_ring_emit(engine, (MI_NOOP));
 
-	intel_mark_page_flip_active(intel_crtc->unpin_work);
 	return 0;
 }
 
 static bool use_mmio_flip(struct intel_engine_cs *engine,
 			  struct drm_i915_gem_object *obj)
 {
+	struct reservation_object *resv;
+
 	/*
 	 * This is not being used for older platforms, because
 	 * non-availability of flip done interrupt forces us to use
@@ -11284,7 +11365,7 @@ static bool use_mmio_flip(struct intel_engine_cs *engine,
 	if (engine == NULL)
 		return true;
 
-	if (INTEL_INFO(engine->dev)->gen < 5)
+	if (INTEL_GEN(engine->i915) < 5)
 		return false;
 
 	if (i915.use_mmio_flip < 0)
@@ -11293,20 +11374,20 @@ static bool use_mmio_flip(struct intel_engine_cs *engine,
 		return true;
 	else if (i915.enable_execlists)
 		return true;
-	else if (obj->base.dma_buf &&
-		 !reservation_object_test_signaled_rcu(obj->base.dma_buf->resv,
-						       false))
+
+	resv = i915_gem_object_get_dmabuf_resv(obj);
+	if (resv && !reservation_object_test_signaled_rcu(resv, false))
 		return true;
-	else
-		return engine != i915_gem_request_get_engine(obj->last_write_req);
+
+	return engine != i915_gem_request_get_engine(obj->last_write_req);
 }
 
 static void skl_do_mmio_flip(struct intel_crtc *intel_crtc,
 			     unsigned int rotation,
-			     struct intel_unpin_work *work)
+			     struct intel_flip_work *work)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_framebuffer *fb = intel_crtc->base.primary->fb;
 	const enum pipe pipe = intel_crtc->pipe;
 	u32 ctl, stride, tile_height;
@@ -11355,10 +11436,10 @@ static void skl_do_mmio_flip(struct intel_crtc *intel_crtc,
 }
 
 static void ilk_do_mmio_flip(struct intel_crtc *intel_crtc,
-			     struct intel_unpin_work *work)
+			     struct intel_flip_work *work)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_framebuffer *intel_fb =
 		to_intel_framebuffer(intel_crtc->base.primary->fb);
 	struct drm_i915_gem_object *obj = intel_fb->obj;
@@ -11378,78 +11459,37 @@ static void ilk_do_mmio_flip(struct intel_crtc *intel_crtc,
 	POSTING_READ(DSPSURF(intel_crtc->plane));
 }
 
-/*
- * XXX: This is the temporary way to update the plane registers until we get
- * around to using the usual plane update functions for MMIO flips
- */
-static void intel_do_mmio_flip(struct intel_mmio_flip *mmio_flip)
-{
-	struct intel_crtc *crtc = mmio_flip->crtc;
-	struct intel_unpin_work *work;
-
-	spin_lock_irq(&crtc->base.dev->event_lock);
-	work = crtc->unpin_work;
-	spin_unlock_irq(&crtc->base.dev->event_lock);
-	if (work == NULL)
-		return;
-
-	intel_mark_page_flip_active(work);
-
-	intel_pipe_update_start(crtc);
-
-	if (INTEL_INFO(mmio_flip->i915)->gen >= 9)
-		skl_do_mmio_flip(crtc, mmio_flip->rotation, work);
-	else
-		/* use_mmio_flip() retricts MMIO flips to ilk+ */
-		ilk_do_mmio_flip(crtc, work);
-
-	intel_pipe_update_end(crtc);
-}
-
-static void intel_mmio_flip_work_func(struct work_struct *work)
+static void intel_mmio_flip_work_func(struct work_struct *w)
 {
-	struct intel_mmio_flip *mmio_flip =
-		container_of(work, struct intel_mmio_flip, work);
+	struct intel_flip_work *work =
+		container_of(w, struct intel_flip_work, mmio_work);
+	struct intel_crtc *crtc = to_intel_crtc(work->crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_framebuffer *intel_fb =
-		to_intel_framebuffer(mmio_flip->crtc->base.primary->fb);
+		to_intel_framebuffer(crtc->base.primary->fb);
 	struct drm_i915_gem_object *obj = intel_fb->obj;
+	struct reservation_object *resv;
 
-	if (mmio_flip->req) {
-		WARN_ON(__i915_wait_request(mmio_flip->req,
+	if (work->flip_queued_req)
+		WARN_ON(__i915_wait_request(work->flip_queued_req,
 					    false, NULL,
-					    &mmio_flip->i915->rps.mmioflips));
-		i915_gem_request_unreference__unlocked(mmio_flip->req);
-	}
+					    &dev_priv->rps.mmioflips));
 
 	/* For framebuffer backed by dmabuf, wait for fence */
-	if (obj->base.dma_buf)
-		WARN_ON(reservation_object_wait_timeout_rcu(obj->base.dma_buf->resv,
-							    false, false,
+	resv = i915_gem_object_get_dmabuf_resv(obj);
+	if (resv)
+		WARN_ON(reservation_object_wait_timeout_rcu(resv, false, false,
 							    MAX_SCHEDULE_TIMEOUT) < 0);
 
-	intel_do_mmio_flip(mmio_flip);
-	kfree(mmio_flip);
-}
-
-static int intel_queue_mmio_flip(struct drm_device *dev,
-				 struct drm_crtc *crtc,
-				 struct drm_i915_gem_object *obj)
-{
-	struct intel_mmio_flip *mmio_flip;
-
-	mmio_flip = kmalloc(sizeof(*mmio_flip), GFP_KERNEL);
-	if (mmio_flip == NULL)
-		return -ENOMEM;
-
-	mmio_flip->i915 = to_i915(dev);
-	mmio_flip->req = i915_gem_request_reference(obj->last_write_req);
-	mmio_flip->crtc = to_intel_crtc(crtc);
-	mmio_flip->rotation = crtc->primary->state->rotation;
+	intel_pipe_update_start(crtc);
 
-	INIT_WORK(&mmio_flip->work, intel_mmio_flip_work_func);
-	schedule_work(&mmio_flip->work);
+	if (INTEL_GEN(dev_priv) >= 9)
+		skl_do_mmio_flip(crtc, work->rotation, work);
+	else
+		/* use_mmio_flip() retricts MMIO flips to ilk+ */
+		ilk_do_mmio_flip(crtc, work);
 
-	return 0;
+	intel_pipe_update_end(crtc, work);
 }
 
 static int intel_default_queue_flip(struct drm_device *dev,
@@ -11462,37 +11502,32 @@ static int intel_default_queue_flip(struct drm_device *dev,
 	return -ENODEV;
 }
 
-static bool __intel_pageflip_stall_check(struct drm_device *dev,
-					 struct drm_crtc *crtc)
+static bool __pageflip_stall_check_cs(struct drm_i915_private *dev_priv,
+				      struct intel_crtc *intel_crtc,
+				      struct intel_flip_work *work)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_unpin_work *work = intel_crtc->unpin_work;
-	u32 addr;
-
-	if (atomic_read(&work->pending) >= INTEL_FLIP_COMPLETE)
-		return true;
+	u32 addr, vblank;
 
-	if (atomic_read(&work->pending) < INTEL_FLIP_PENDING)
+	if (!atomic_read(&work->pending))
 		return false;
 
-	if (!work->enable_stall_check)
-		return false;
+	smp_rmb();
 
+	vblank = intel_crtc_get_vblank_counter(intel_crtc);
 	if (work->flip_ready_vblank == 0) {
 		if (work->flip_queued_req &&
-		    !i915_gem_request_completed(work->flip_queued_req, true))
+		    !i915_gem_request_completed(work->flip_queued_req))
 			return false;
 
-		work->flip_ready_vblank = drm_crtc_vblank_count(crtc);
+		work->flip_ready_vblank = vblank;
 	}
 
-	if (drm_crtc_vblank_count(crtc) - work->flip_ready_vblank < 3)
+	if (vblank - work->flip_ready_vblank < 3)
 		return false;
 
 	/* Potential stall - if we see that the flip has happened,
 	 * assume a missed interrupt. */
-	if (INTEL_INFO(dev)->gen >= 4)
+	if (INTEL_GEN(dev_priv) >= 4)
 		addr = I915_HI_DISPBASE(I915_READ(DSPSURF(intel_crtc->plane)));
 	else
 		addr = I915_READ(DSPADDR(intel_crtc->plane));
@@ -11504,12 +11539,12 @@ static bool __intel_pageflip_stall_check(struct drm_device *dev,
 	return addr == work->gtt_offset;
 }
 
-void intel_check_page_flip(struct drm_device *dev, int pipe)
+void intel_check_page_flip(struct drm_i915_private *dev_priv, int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_device *dev = &dev_priv->drm;
 	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_unpin_work *work;
+	struct intel_flip_work *work;
 
 	WARN_ON(!in_interrupt());
 
@@ -11517,16 +11552,20 @@ void intel_check_page_flip(struct drm_device *dev, int pipe)
 		return;
 
 	spin_lock(&dev->event_lock);
-	work = intel_crtc->unpin_work;
-	if (work != NULL && __intel_pageflip_stall_check(dev, crtc)) {
-		WARN_ONCE(1, "Kicking stuck page flip: queued at %d, now %d\n",
-			 work->flip_queued_vblank, drm_vblank_count(dev, pipe));
+	work = intel_crtc->flip_work;
+
+	if (work != NULL && !is_mmio_work(work) &&
+	    __pageflip_stall_check_cs(dev_priv, intel_crtc, work)) {
+		WARN_ONCE(1,
+			  "Kicking stuck page flip: queued at %d, now %d\n",
+			work->flip_queued_vblank, intel_crtc_get_vblank_counter(intel_crtc));
 		page_flip_completed(intel_crtc);
 		work = NULL;
 	}
-	if (work != NULL &&
-	    drm_vblank_count(dev, pipe) - work->flip_queued_vblank > 1)
-		intel_queue_rps_boost_for_request(dev, work->flip_queued_req);
+
+	if (work != NULL && !is_mmio_work(work) &&
+	    intel_crtc_get_vblank_counter(intel_crtc) - work->flip_queued_vblank > 1)
+		intel_queue_rps_boost_for_request(work->flip_queued_req);
 	spin_unlock(&dev->event_lock);
 }
 
@@ -11536,13 +11575,13 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 				uint32_t page_flip_flags)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_framebuffer *old_fb = crtc->primary->fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_plane *primary = crtc->primary;
 	enum pipe pipe = intel_crtc->pipe;
-	struct intel_unpin_work *work;
+	struct intel_flip_work *work;
 	struct intel_engine_cs *engine;
 	bool mmio_flip;
 	struct drm_i915_gem_request *request = NULL;
@@ -11579,19 +11618,19 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	work->event = event;
 	work->crtc = crtc;
 	work->old_fb = old_fb;
-	INIT_WORK(&work->work, intel_unpin_work_fn);
+	INIT_WORK(&work->unpin_work, intel_unpin_work_fn);
 
 	ret = drm_crtc_vblank_get(crtc);
 	if (ret)
 		goto free_work;
 
-	/* We borrow the event spin lock for protecting unpin_work */
+	/* We borrow the event spin lock for protecting flip_work */
 	spin_lock_irq(&dev->event_lock);
-	if (intel_crtc->unpin_work) {
+	if (intel_crtc->flip_work) {
 		/* Before declaring the flip queue wedged, check if
 		 * the hardware completed the operation behind our backs.
 		 */
-		if (__intel_pageflip_stall_check(dev, crtc)) {
+		if (pageflip_finished(intel_crtc, intel_crtc->flip_work)) {
 			DRM_DEBUG_DRIVER("flip queue: previous flip completed, continuing\n");
 			page_flip_completed(intel_crtc);
 		} else {
@@ -11603,7 +11642,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 			return -EBUSY;
 		}
 	}
-	intel_crtc->unpin_work = work;
+	intel_crtc->flip_work = work;
 	spin_unlock_irq(&dev->event_lock);
 
 	if (atomic_read(&intel_crtc->unpin_work_count) >= 2)
@@ -11615,7 +11654,9 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 
 	crtc->primary->fb = fb;
 	update_state_fb(crtc->primary);
-	intel_fbc_pre_update(intel_crtc);
+
+	intel_fbc_pre_update(intel_crtc, intel_crtc->config,
+			     to_intel_plane_state(primary->state));
 
 	work->pending_flip_obj = obj;
 
@@ -11658,6 +11699,11 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	 */
 	if (!mmio_flip) {
 		ret = i915_gem_object_sync(obj, engine, &request);
+		if (!ret && !request) {
+			request = i915_gem_request_alloc(engine, NULL);
+			ret = PTR_ERR_OR_ZERO(request);
+		}
+
 		if (ret)
 			goto cleanup_pending;
 	}
@@ -11669,38 +11715,28 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	work->gtt_offset = intel_plane_obj_offset(to_intel_plane(primary),
 						  obj, 0);
 	work->gtt_offset += intel_crtc->dspaddr_offset;
+	work->rotation = crtc->primary->state->rotation;
 
 	if (mmio_flip) {
-		ret = intel_queue_mmio_flip(dev, crtc, obj);
-		if (ret)
-			goto cleanup_unpin;
+		INIT_WORK(&work->mmio_work, intel_mmio_flip_work_func);
 
 		i915_gem_request_assign(&work->flip_queued_req,
 					obj->last_write_req);
-	} else {
-		if (!request) {
-			request = i915_gem_request_alloc(engine, NULL);
-			if (IS_ERR(request)) {
-				ret = PTR_ERR(request);
-				goto cleanup_unpin;
-			}
-		}
 
+		schedule_work(&work->mmio_work);
+	} else {
+		i915_gem_request_assign(&work->flip_queued_req, request);
 		ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, request,
 						   page_flip_flags);
 		if (ret)
 			goto cleanup_unpin;
 
-		i915_gem_request_assign(&work->flip_queued_req, request);
-	}
+		intel_mark_page_flip_active(intel_crtc, work);
 
-	if (request)
 		i915_add_request_no_flush(request);
+	}
 
-	work->flip_queued_vblank = drm_crtc_vblank_count(crtc);
-	work->enable_stall_check = true;
-
-	i915_gem_track_fb(intel_fb_obj(work->old_fb), obj,
+	i915_gem_track_fb(intel_fb_obj(old_fb), obj,
 			  to_intel_plane(primary)->frontbuffer_bit);
 	mutex_unlock(&dev->struct_mutex);
 
@@ -11726,7 +11762,7 @@ cleanup:
 	drm_framebuffer_unreference(work->old_fb);
 
 	spin_lock_irq(&dev->event_lock);
-	intel_crtc->unpin_work = NULL;
+	intel_crtc->flip_work = NULL;
 	spin_unlock_irq(&dev->event_lock);
 
 	drm_crtc_vblank_put(crtc);
@@ -11828,15 +11864,14 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane_state *old_plane_state =
 		to_intel_plane_state(plane->state);
-	int idx = intel_crtc->base.base.id, ret;
 	bool mode_changed = needs_modeset(crtc_state);
 	bool was_crtc_enabled = crtc->state->active;
 	bool is_crtc_enabled = crtc_state->active;
 	bool turn_off, turn_on, visible, was_visible;
 	struct drm_framebuffer *fb = plane_state->fb;
+	int ret;
 
-	if (crtc_state && INTEL_INFO(dev)->gen >= 9 &&
-	    plane->type != DRM_PLANE_TYPE_CURSOR) {
+	if (INTEL_GEN(dev) >= 9 && plane->type != DRM_PLANE_TYPE_CURSOR) {
 		ret = skl_update_scaler_plane(
 			to_intel_crtc_state(crtc_state),
 			to_intel_plane_state(plane_state));
@@ -11854,6 +11889,11 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 	 * Visibility is calculated as if the crtc was on, but
 	 * after scaler setup everything depends on it being off
 	 * when the crtc isn't active.
+	 *
+	 * FIXME this is wrong for watermarks. Watermarks should also
+	 * be computed as if the pipe would be active. Perhaps move
+	 * per-plane wm computation to the .check_plane() hook, and
+	 * only combine the results from all planes in the current place?
 	 */
 	if (!is_crtc_enabled)
 		to_intel_plane_state(plane_state)->visible = visible = false;
@@ -11867,11 +11907,15 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state,
 	turn_off = was_visible && (!visible || mode_changed);
 	turn_on = visible && (!was_visible || mode_changed);
 
-	DRM_DEBUG_ATOMIC("[CRTC:%i] has [PLANE:%i] with fb %i\n", idx,
-			 plane->base.id, fb ? fb->base.id : -1);
+	DRM_DEBUG_ATOMIC("[CRTC:%d:%s] has [PLANE:%d:%s] with fb %i\n",
+			 intel_crtc->base.base.id,
+			 intel_crtc->base.name,
+			 plane->base.id, plane->name,
+			 fb ? fb->base.id : -1);
 
-	DRM_DEBUG_ATOMIC("[PLANE:%i] visible %i -> %i, off %i, on %i, ms %i\n",
-			 plane->base.id, was_visible, visible,
+	DRM_DEBUG_ATOMIC("[PLANE:%d:%s] visible %i -> %i, off %i, on %i, ms %i\n",
+			 plane->base.id, plane->name,
+			 was_visible, visible,
 			 turn_off, turn_on, mode_changed);
 
 	if (turn_on) {
@@ -11944,31 +11988,11 @@ static bool check_single_encoder_cloning(struct drm_atomic_state *state,
 	return true;
 }
 
-static bool check_encoder_cloning(struct drm_atomic_state *state,
-				  struct intel_crtc *crtc)
-{
-	struct intel_encoder *encoder;
-	struct drm_connector *connector;
-	struct drm_connector_state *connector_state;
-	int i;
-
-	for_each_connector_in_state(state, connector, connector_state, i) {
-		if (connector_state->crtc != &crtc->base)
-			continue;
-
-		encoder = to_intel_encoder(connector_state->best_encoder);
-		if (!check_single_encoder_cloning(state, crtc, encoder))
-			return false;
-	}
-
-	return true;
-}
-
 static int intel_crtc_atomic_check(struct drm_crtc *crtc,
 				   struct drm_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_crtc_state *pipe_config =
 		to_intel_crtc_state(crtc_state);
@@ -11976,11 +12000,6 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc,
 	int ret;
 	bool mode_changed = needs_modeset(crtc_state);
 
-	if (mode_changed && !check_encoder_cloning(state, intel_crtc)) {
-		DRM_DEBUG_KMS("rejecting invalid cloning configuration\n");
-		return -EINVAL;
-	}
-
 	if (mode_changed && !crtc_state->active)
 		pipe_config->update_wm_post = true;
 
@@ -12033,7 +12052,7 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc,
 		}
 	} else if (dev_priv->display.compute_intermediate_wm) {
 		if (HAS_PCH_SPLIT(dev_priv) && INTEL_GEN(dev_priv) < 9)
-			pipe_config->wm.intermediate = pipe_config->wm.optimal.ilk;
+			pipe_config->wm.ilk.intermediate = pipe_config->wm.ilk.optimal;
 	}
 
 	if (INTEL_INFO(dev)->gen >= 9) {
@@ -12168,7 +12187,8 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc,
 	struct intel_plane_state *state;
 	struct drm_framebuffer *fb;
 
-	DRM_DEBUG_KMS("[CRTC:%d]%s config %p for pipe %c\n", crtc->base.base.id,
+	DRM_DEBUG_KMS("[CRTC:%d:%s]%s config %p for pipe %c\n",
+		      crtc->base.base.id, crtc->base.name,
 		      context, pipe_config, pipe_name(crtc->pipe));
 
 	DRM_DEBUG_KMS("cpu_transcoder: %s\n", transcoder_name(pipe_config->cpu_transcoder));
@@ -12181,14 +12201,14 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc,
 		      pipe_config->fdi_m_n.link_m, pipe_config->fdi_m_n.link_n,
 		      pipe_config->fdi_m_n.tu);
 	DRM_DEBUG_KMS("dp: %i, lanes: %i, gmch_m: %u, gmch_n: %u, link_m: %u, link_n: %u, tu: %u\n",
-		      pipe_config->has_dp_encoder,
+		      intel_crtc_has_dp_encoder(pipe_config),
 		      pipe_config->lane_count,
 		      pipe_config->dp_m_n.gmch_m, pipe_config->dp_m_n.gmch_n,
 		      pipe_config->dp_m_n.link_m, pipe_config->dp_m_n.link_n,
 		      pipe_config->dp_m_n.tu);
 
 	DRM_DEBUG_KMS("dp: %i, lanes: %i, gmch_m2: %u, gmch_n2: %u, link_m2: %u, link_n2: %u, tu2: %u\n",
-		      pipe_config->has_dp_encoder,
+		      intel_crtc_has_dp_encoder(pipe_config),
 		      pipe_config->lane_count,
 		      pipe_config->dp_m2_n2.gmch_m,
 		      pipe_config->dp_m2_n2.gmch_n,
@@ -12269,29 +12289,24 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc,
 		state = to_intel_plane_state(plane->state);
 		fb = state->base.fb;
 		if (!fb) {
-			DRM_DEBUG_KMS("%s PLANE:%d plane: %u.%u idx: %d "
-				"disabled, scaler_id = %d\n",
-				plane->type == DRM_PLANE_TYPE_CURSOR ? "CURSOR" : "STANDARD",
-				plane->base.id, intel_plane->pipe,
-				(crtc->base.primary == plane) ? 0 : intel_plane->plane + 1,
-				drm_plane_index(plane), state->scaler_id);
+			DRM_DEBUG_KMS("[PLANE:%d:%s] disabled, scaler_id = %d\n",
+				      plane->base.id, plane->name, state->scaler_id);
 			continue;
 		}
 
-		DRM_DEBUG_KMS("%s PLANE:%d plane: %u.%u idx: %d enabled",
-			plane->type == DRM_PLANE_TYPE_CURSOR ? "CURSOR" : "STANDARD",
-			plane->base.id, intel_plane->pipe,
-			crtc->base.primary == plane ? 0 : intel_plane->plane + 1,
-			drm_plane_index(plane));
-		DRM_DEBUG_KMS("\tFB:%d, fb = %ux%u format = 0x%x",
-			fb->base.id, fb->width, fb->height, fb->pixel_format);
-		DRM_DEBUG_KMS("\tscaler:%d src (%u, %u) %ux%u dst (%u, %u) %ux%u\n",
-			state->scaler_id,
-			state->src.x1 >> 16, state->src.y1 >> 16,
-			drm_rect_width(&state->src) >> 16,
-			drm_rect_height(&state->src) >> 16,
-			state->dst.x1, state->dst.y1,
-			drm_rect_width(&state->dst), drm_rect_height(&state->dst));
+		DRM_DEBUG_KMS("[PLANE:%d:%s] enabled",
+			      plane->base.id, plane->name);
+		DRM_DEBUG_KMS("\tFB:%d, fb = %ux%u format = %s",
+			      fb->base.id, fb->width, fb->height,
+			      drm_get_format_name(fb->pixel_format));
+		DRM_DEBUG_KMS("\tscaler:%d src %dx%d+%d+%d dst %dx%d+%d+%d\n",
+			      state->scaler_id,
+			      state->src.x1 >> 16, state->src.y1 >> 16,
+			      drm_rect_width(&state->src) >> 16,
+			      drm_rect_height(&state->src) >> 16,
+			      state->dst.x1, state->dst.y1,
+			      drm_rect_width(&state->dst),
+			      drm_rect_height(&state->dst));
 	}
 }
 
@@ -12326,7 +12341,7 @@ static bool check_digital_port_conflicts(struct drm_atomic_state *state)
 		case INTEL_OUTPUT_UNKNOWN:
 			if (WARN_ON(!HAS_DDI(dev)))
 				break;
-		case INTEL_OUTPUT_DISPLAYPORT:
+		case INTEL_OUTPUT_DP:
 		case INTEL_OUTPUT_HDMI:
 		case INTEL_OUTPUT_EDP:
 			port_mask = 1 << enc_to_dig_port(&encoder->base)->port;
@@ -12423,6 +12438,24 @@ intel_modeset_pipe_config(struct drm_crtc *crtc,
 			       &pipe_config->pipe_src_w,
 			       &pipe_config->pipe_src_h);
 
+	for_each_connector_in_state(state, connector, connector_state, i) {
+		if (connector_state->crtc != crtc)
+			continue;
+
+		encoder = to_intel_encoder(connector_state->best_encoder);
+
+		if (!check_single_encoder_cloning(state, to_intel_crtc(crtc), encoder)) {
+			DRM_DEBUG_KMS("rejecting invalid cloning configuration\n");
+			goto fail;
+		}
+
+		/*
+		 * Determine output_types before calling the .compute_config()
+		 * hooks so that the hooks can use this information safely.
+		 */
+		pipe_config->output_types |= 1 << encoder->type;
+	}
+
 encoder_retry:
 	/* Ensure the port clock defaults are reset when retrying. */
 	pipe_config->port_clock = 0;
@@ -12708,8 +12741,8 @@ intel_pipe_config_compare(struct drm_device *dev,
 	PIPE_CONF_CHECK_I(fdi_lanes);
 	PIPE_CONF_CHECK_M_N(fdi_m_n);
 
-	PIPE_CONF_CHECK_I(has_dp_encoder);
 	PIPE_CONF_CHECK_I(lane_count);
+	PIPE_CONF_CHECK_X(lane_lat_optim_mask);
 
 	if (INTEL_INFO(dev)->gen < 8) {
 		PIPE_CONF_CHECK_M_N(dp_m_n);
@@ -12719,7 +12752,7 @@ intel_pipe_config_compare(struct drm_device *dev,
 	} else
 		PIPE_CONF_CHECK_M_N_ALT(dp_m_n, dp_m2_n2);
 
-	PIPE_CONF_CHECK_I(has_dsi_encoder);
+	PIPE_CONF_CHECK_X(output_types);
 
 	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hdisplay);
 	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_htotal);
@@ -12838,7 +12871,7 @@ static void verify_wm_state(struct drm_crtc *crtc,
 			    struct drm_crtc_state *new_state)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct skl_ddb_allocation hw_ddb, *sw_ddb;
 	struct skl_ddb_entry *hw_entry, *sw_entry;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -12944,7 +12977,7 @@ verify_crtc_state(struct drm_crtc *crtc,
 		  struct drm_crtc_state *new_crtc_state)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *encoder;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_crtc_state *pipe_config, *sw_config;
@@ -12958,7 +12991,7 @@ verify_crtc_state(struct drm_crtc *crtc,
 	pipe_config->base.crtc = crtc;
 	pipe_config->base.state = old_state;
 
-	DRM_DEBUG_KMS("[CRTC:%d]\n", crtc->base.id);
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
 	active = dev_priv->display.get_pipe_config(intel_crtc, pipe_config);
 
@@ -12987,8 +13020,10 @@ verify_crtc_state(struct drm_crtc *crtc,
 				"Encoder connected to wrong pipe %c\n",
 				pipe_name(pipe));
 
-		if (active)
+		if (active) {
+			pipe_config->output_types |= 1 << encoder->type;
 			encoder->get_config(encoder, pipe_config);
+		}
 	}
 
 	if (!new_crtc_state->active)
@@ -13067,7 +13102,7 @@ verify_shared_dpll_state(struct drm_device *dev, struct drm_crtc *crtc,
 			 struct drm_crtc_state *old_crtc_state,
 			 struct drm_crtc_state *new_crtc_state)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc_state *old_state = to_intel_crtc_state(old_crtc_state);
 	struct intel_crtc_state *new_state = to_intel_crtc_state(new_crtc_state);
 
@@ -13106,7 +13141,7 @@ intel_modeset_verify_crtc(struct drm_crtc *crtc,
 static void
 verify_disabled_dpll_state(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
 	for (i = 0; i < dev_priv->num_shared_dpll; i++)
@@ -13153,7 +13188,7 @@ static void update_scanline_offset(struct intel_crtc *crtc)
 
 		crtc->scanline_offset = vtotal - 1;
 	} else if (HAS_DDI(dev) &&
-		   intel_pipe_has_type(crtc, INTEL_OUTPUT_HDMI)) {
+		   intel_crtc_has_type(crtc->config, INTEL_OUTPUT_HDMI)) {
 		crtc->scanline_offset = 2;
 	} else
 		crtc->scanline_offset = 1;
@@ -13288,7 +13323,7 @@ static int intel_modeset_all_pipes(struct drm_atomic_state *state)
 static int intel_modeset_checks(struct drm_atomic_state *state)
 {
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
-	struct drm_i915_private *dev_priv = state->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(state->dev);
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
 	int ret = 0, i;
@@ -13306,6 +13341,9 @@ static int intel_modeset_checks(struct drm_atomic_state *state)
 			intel_state->active_crtcs |= 1 << i;
 		else
 			intel_state->active_crtcs &= ~(1 << i);
+
+		if (crtc_state->active != crtc->state->active)
+			intel_state->active_pipe_changes |= drm_crtc_mask(crtc);
 	}
 
 	/*
@@ -13316,9 +13354,17 @@ static int intel_modeset_checks(struct drm_atomic_state *state)
 	 * adjusted_mode bits in the crtc directly.
 	 */
 	if (dev_priv->display.modeset_calc_cdclk) {
+		if (!intel_state->cdclk_pll_vco)
+			intel_state->cdclk_pll_vco = dev_priv->cdclk_pll.vco;
+		if (!intel_state->cdclk_pll_vco)
+			intel_state->cdclk_pll_vco = dev_priv->skl_preferred_vco_freq;
+
 		ret = dev_priv->display.modeset_calc_cdclk(state);
+		if (ret < 0)
+			return ret;
 
-		if (!ret && intel_state->dev_cdclk != dev_priv->cdclk_freq)
+		if (intel_state->dev_cdclk != dev_priv->cdclk_freq ||
+		    intel_state->cdclk_pll_vco != dev_priv->cdclk_pll.vco)
 			ret = intel_modeset_all_pipes(state);
 
 		if (ret < 0)
@@ -13342,38 +13388,16 @@ static int intel_modeset_checks(struct drm_atomic_state *state)
  * phase.  The code here should be run after the per-crtc and per-plane 'check'
  * handlers to ensure that all derived state has been updated.
  */
-static void calc_watermark_data(struct drm_atomic_state *state)
+static int calc_watermark_data(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
-	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
-	struct drm_crtc *crtc;
-	struct drm_crtc_state *cstate;
-	struct drm_plane *plane;
-	struct drm_plane_state *pstate;
-
-	/*
-	 * Calculate watermark configuration details now that derived
-	 * plane/crtc state is all properly updated.
-	 */
-	drm_for_each_crtc(crtc, dev) {
-		cstate = drm_atomic_get_existing_crtc_state(state, crtc) ?:
-			crtc->state;
-
-		if (cstate->active)
-			intel_state->wm_config.num_pipes_active++;
-	}
-	drm_for_each_legacy_plane(plane, dev) {
-		pstate = drm_atomic_get_existing_plane_state(state, plane) ?:
-			plane->state;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
-		if (!to_intel_plane_state(pstate)->visible)
-			continue;
+	/* Is there platform-specific watermark information to calculate? */
+	if (dev_priv->display.compute_global_watermarks)
+		return dev_priv->display.compute_global_watermarks(state);
 
-		intel_state->wm_config.sprites_enabled = true;
-		if (pstate->crtc_w != pstate->src_w >> 16 ||
-		    pstate->crtc_h != pstate->src_h >> 16)
-			intel_state->wm_config.sprites_scaled = true;
-	}
+	return 0;
 }
 
 /**
@@ -13403,14 +13427,13 @@ static int intel_atomic_check(struct drm_device *dev,
 		if (crtc_state->mode.private_flags != crtc->state->mode.private_flags)
 			crtc_state->mode_changed = true;
 
-		if (!crtc_state->enable) {
-			if (needs_modeset(crtc_state))
-				any_ms = true;
+		if (!needs_modeset(crtc_state))
 			continue;
-		}
 
-		if (!needs_modeset(crtc_state))
+		if (!crtc_state->enable) {
+			any_ms = true;
 			continue;
+		}
 
 		/* FIXME: For only active_changed we shouldn't need to do any
 		 * state recomputation at all. */
@@ -13420,8 +13443,11 @@ static int intel_atomic_check(struct drm_device *dev,
 			return ret;
 
 		ret = intel_modeset_pipe_config(crtc, pipe_config);
-		if (ret)
+		if (ret) {
+			intel_dump_pipe_config(to_intel_crtc(crtc),
+					       pipe_config, "[failed]");
 			return ret;
+		}
 
 		if (i915.fastboot &&
 		    intel_pipe_config_compare(dev,
@@ -13431,13 +13457,12 @@ static int intel_atomic_check(struct drm_device *dev,
 			to_intel_crtc_state(crtc_state)->update_pipe = true;
 		}
 
-		if (needs_modeset(crtc_state)) {
+		if (needs_modeset(crtc_state))
 			any_ms = true;
 
-			ret = drm_atomic_add_affected_planes(state, crtc);
-			if (ret)
-				return ret;
-		}
+		ret = drm_atomic_add_affected_planes(state, crtc);
+		if (ret)
+			return ret;
 
 		intel_dump_pipe_config(to_intel_crtc(crtc), pipe_config,
 				       needs_modeset(crtc_state) ?
@@ -13457,27 +13482,20 @@ static int intel_atomic_check(struct drm_device *dev,
 		return ret;
 
 	intel_fbc_choose_crtc(dev_priv, state);
-	calc_watermark_data(state);
-
-	return 0;
+	return calc_watermark_data(state);
 }
 
 static int intel_atomic_prepare_commit(struct drm_device *dev,
 				       struct drm_atomic_state *state,
 				       bool nonblock)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_plane_state *plane_state;
 	struct drm_crtc_state *crtc_state;
 	struct drm_plane *plane;
 	struct drm_crtc *crtc;
 	int i, ret;
 
-	if (nonblock) {
-		DRM_DEBUG_KMS("i915 does not yet support nonblocking commit\n");
-		return -EINVAL;
-	}
-
 	for_each_crtc_in_state(state, crtc, crtc_state, i) {
 		if (state->legacy_cursor_update)
 			continue;
@@ -13521,6 +13539,16 @@ static int intel_atomic_prepare_commit(struct drm_device *dev,
 	return ret;
 }
 
+u32 intel_crtc_get_vblank_counter(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+
+	if (!dev->max_vblank_count)
+		return drm_accurate_vblank_count(&crtc->base);
+
+	return dev->driver->get_vblank_counter(dev, crtc->pipe);
+}
+
 static void intel_atomic_wait_for_vblanks(struct drm_device *dev,
 					  struct drm_i915_private *dev_priv,
 					  unsigned crtc_mask)
@@ -13586,45 +13614,36 @@ static bool needs_vblank_wait(struct intel_crtc_state *crtc_state)
 	return false;
 }
 
-/**
- * intel_atomic_commit - commit validated state object
- * @dev: DRM device
- * @state: the top-level driver state object
- * @nonblock: nonblocking commit
- *
- * This function commits a top-level state object that has been validated
- * with drm_atomic_helper_check().
- *
- * FIXME:  Atomic modeset support for i915 is not yet complete.  At the moment
- * we can only handle plane-related operations and do not yet support
- * nonblocking commit.
- *
- * RETURNS
- * Zero for success or -errno.
- */
-static int intel_atomic_commit(struct drm_device *dev,
-			       struct drm_atomic_state *state,
-			       bool nonblock)
+static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 {
+	struct drm_device *dev = state->dev;
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc_state *old_crtc_state;
 	struct drm_crtc *crtc;
 	struct intel_crtc_state *intel_cstate;
-	int ret = 0, i;
+	struct drm_plane *plane;
+	struct drm_plane_state *plane_state;
 	bool hw_check = intel_state->modeset;
 	unsigned long put_domains[I915_MAX_PIPES] = {};
 	unsigned crtc_vblank_mask = 0;
+	int i, ret;
 
-	ret = intel_atomic_prepare_commit(dev, state, nonblock);
-	if (ret) {
-		DRM_DEBUG_ATOMIC("Preparing state failed with %i\n", ret);
-		return ret;
+	for_each_plane_in_state(state, plane, plane_state, i) {
+		struct intel_plane_state *intel_plane_state =
+			to_intel_plane_state(plane_state);
+
+		if (!intel_plane_state->wait_req)
+			continue;
+
+		ret = __i915_wait_request(intel_plane_state->wait_req,
+					  true, NULL, NULL);
+		/* EIO should be eaten, and we can't get interrupted in the
+		 * worker, and blocking commits have waited already. */
+		WARN_ON(ret);
 	}
 
-	drm_atomic_helper_swap_state(dev, state);
-	dev_priv->wm.config = intel_state->wm_config;
-	intel_shared_dpll_commit(state);
+	drm_atomic_helper_wait_for_dependencies(state);
 
 	if (intel_state->modeset) {
 		memcpy(dev_priv->min_pixclk, intel_state->min_pixclk,
@@ -13679,7 +13698,8 @@ static int intel_atomic_commit(struct drm_device *dev,
 		drm_atomic_helper_update_legacy_modeset_state(state->dev, state);
 
 		if (dev_priv->display.modeset_commit_cdclk &&
-		    intel_state->dev_cdclk != dev_priv->cdclk_freq)
+		    (intel_state->dev_cdclk != dev_priv->cdclk_freq ||
+		     intel_state->cdclk_pll_vco != dev_priv->cdclk_pll.vco))
 			dev_priv->display.modeset_commit_cdclk(state);
 
 		intel_modeset_verify_disabled(dev);
@@ -13691,30 +13711,44 @@ static int intel_atomic_commit(struct drm_device *dev,
 		bool modeset = needs_modeset(crtc->state);
 		struct intel_crtc_state *pipe_config =
 			to_intel_crtc_state(crtc->state);
-		bool update_pipe = !modeset && pipe_config->update_pipe;
 
 		if (modeset && crtc->state->active) {
 			update_scanline_offset(to_intel_crtc(crtc));
 			dev_priv->display.crtc_enable(crtc);
 		}
 
+		/* Complete events for now disable pipes here. */
+		if (modeset && !crtc->state->active && crtc->state->event) {
+			spin_lock_irq(&dev->event_lock);
+			drm_crtc_send_vblank_event(crtc, crtc->state->event);
+			spin_unlock_irq(&dev->event_lock);
+
+			crtc->state->event = NULL;
+		}
+
 		if (!modeset)
 			intel_pre_plane_update(to_intel_crtc_state(old_crtc_state));
 
 		if (crtc->state->active &&
 		    drm_atomic_get_existing_plane_state(state, crtc->primary))
-			intel_fbc_enable(intel_crtc);
+			intel_fbc_enable(intel_crtc, pipe_config, to_intel_plane_state(crtc->primary->state));
 
-		if (crtc->state->active &&
-		    (crtc->state->planes_changed || update_pipe))
+		if (crtc->state->active)
 			drm_atomic_helper_commit_planes_on_crtc(old_crtc_state);
 
 		if (pipe_config->base.active && needs_vblank_wait(pipe_config))
 			crtc_vblank_mask |= 1 << i;
 	}
 
-	/* FIXME: add subpixel order */
-
+	/* FIXME: We should call drm_atomic_helper_commit_hw_done() here
+	 * already, but still need the state for the delayed optimization. To
+	 * fix this:
+	 * - wrap the optimization/post_plane_update stuff into a per-crtc work.
+	 * - schedule that vblank worker _before_ calling hw_done
+	 * - at the start of commit_tail, cancel it _synchrously
+	 * - switch over to the vblank wait helper in the core after that since
+	 *   we don't need out special handling any more.
+	 */
 	if (!state->legacy_cursor_update)
 		intel_atomic_wait_for_vblanks(dev, dev_priv, crtc_vblank_mask);
 
@@ -13741,6 +13775,8 @@ static int intel_atomic_commit(struct drm_device *dev,
 		intel_modeset_verify_crtc(crtc, old_crtc_state, crtc->state);
 	}
 
+	drm_atomic_helper_commit_hw_done(state);
+
 	if (intel_state->modeset)
 		intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET);
 
@@ -13748,6 +13784,8 @@ static int intel_atomic_commit(struct drm_device *dev,
 	drm_atomic_helper_cleanup_planes(dev, state);
 	mutex_unlock(&dev->struct_mutex);
 
+	drm_atomic_helper_commit_cleanup_done(state);
+
 	drm_atomic_state_free(state);
 
 	/* As one of the primary mmio accessors, KMS has a high likelihood
@@ -13762,6 +13800,86 @@ static int intel_atomic_commit(struct drm_device *dev,
 	 * can happen also when the device is completely off.
 	 */
 	intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
+}
+
+static void intel_atomic_commit_work(struct work_struct *work)
+{
+	struct drm_atomic_state *state = container_of(work,
+						      struct drm_atomic_state,
+						      commit_work);
+	intel_atomic_commit_tail(state);
+}
+
+static void intel_atomic_track_fbs(struct drm_atomic_state *state)
+{
+	struct drm_plane_state *old_plane_state;
+	struct drm_plane *plane;
+	struct drm_i915_gem_object *obj, *old_obj;
+	struct intel_plane *intel_plane;
+	int i;
+
+	mutex_lock(&state->dev->struct_mutex);
+	for_each_plane_in_state(state, plane, old_plane_state, i) {
+		obj = intel_fb_obj(plane->state->fb);
+		old_obj = intel_fb_obj(old_plane_state->fb);
+		intel_plane = to_intel_plane(plane);
+
+		i915_gem_track_fb(old_obj, obj, intel_plane->frontbuffer_bit);
+	}
+	mutex_unlock(&state->dev->struct_mutex);
+}
+
+/**
+ * intel_atomic_commit - commit validated state object
+ * @dev: DRM device
+ * @state: the top-level driver state object
+ * @nonblock: nonblocking commit
+ *
+ * This function commits a top-level state object that has been validated
+ * with drm_atomic_helper_check().
+ *
+ * FIXME:  Atomic modeset support for i915 is not yet complete.  At the moment
+ * nonblocking commits are only safe for pure plane updates. Everything else
+ * should work though.
+ *
+ * RETURNS
+ * Zero for success or -errno.
+ */
+static int intel_atomic_commit(struct drm_device *dev,
+			       struct drm_atomic_state *state,
+			       bool nonblock)
+{
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int ret = 0;
+
+	if (intel_state->modeset && nonblock) {
+		DRM_DEBUG_KMS("nonblocking commit for modeset not yet implemented.\n");
+		return -EINVAL;
+	}
+
+	ret = drm_atomic_helper_setup_commit(state, nonblock);
+	if (ret)
+		return ret;
+
+	INIT_WORK(&state->commit_work, intel_atomic_commit_work);
+
+	ret = intel_atomic_prepare_commit(dev, state, nonblock);
+	if (ret) {
+		DRM_DEBUG_ATOMIC("Preparing state failed with %i\n", ret);
+		return ret;
+	}
+
+	drm_atomic_helper_swap_state(state, true);
+	dev_priv->wm.distrust_bios_wm = false;
+	dev_priv->wm.skl_results = intel_state->wm_results;
+	intel_shared_dpll_commit(state);
+	intel_atomic_track_fbs(state);
+
+	if (nonblock)
+		queue_work(system_unbound_wq, &state->commit_work);
+	else
+		intel_atomic_commit_tail(state);
 
 	return 0;
 }
@@ -13775,8 +13893,8 @@ void intel_crtc_restore_mode(struct drm_crtc *crtc)
 
 	state = drm_atomic_state_alloc(dev);
 	if (!state) {
-		DRM_DEBUG_KMS("[CRTC:%d] crtc restore failed, out of memory",
-			      crtc->base.id);
+		DRM_DEBUG_KMS("[CRTC:%d:%s] crtc restore failed, out of memory",
+			      crtc->base.id, crtc->name);
 		return;
 	}
 
@@ -13806,8 +13924,50 @@ out:
 
 #undef for_each_intel_crtc_masked
 
+/*
+ * FIXME: Remove this once i915 is fully DRIVER_ATOMIC by calling
+ *        drm_atomic_helper_legacy_gamma_set() directly.
+ */
+static int intel_atomic_legacy_gamma_set(struct drm_crtc *crtc,
+					 u16 *red, u16 *green, u16 *blue,
+					 uint32_t size)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_crtc_state *state;
+	int ret;
+
+	ret = drm_atomic_helper_legacy_gamma_set(crtc, red, green, blue, size);
+	if (ret)
+		return ret;
+
+	/*
+	 * Make sure we update the legacy properties so this works when
+	 * atomic is not enabled.
+	 */
+
+	state = crtc->state;
+
+	drm_object_property_set_value(&crtc->base,
+				      config->degamma_lut_property,
+				      (state->degamma_lut) ?
+				      state->degamma_lut->base.id : 0);
+
+	drm_object_property_set_value(&crtc->base,
+				      config->ctm_property,
+				      (state->ctm) ?
+				      state->ctm->base.id : 0);
+
+	drm_object_property_set_value(&crtc->base,
+				      config->gamma_lut_property,
+				      (state->gamma_lut) ?
+				      state->gamma_lut->base.id : 0);
+
+	return 0;
+}
+
 static const struct drm_crtc_funcs intel_crtc_funcs = {
-	.gamma_set = drm_atomic_helper_legacy_gamma_set,
+	.gamma_set = intel_atomic_legacy_gamma_set,
 	.set_config = drm_atomic_helper_set_config,
 	.set_property = drm_atomic_helper_crtc_set_property,
 	.destroy = intel_crtc_destroy,
@@ -13836,9 +13996,9 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 {
 	struct drm_device *dev = plane->dev;
 	struct drm_framebuffer *fb = new_state->fb;
-	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct drm_i915_gem_object *old_obj = intel_fb_obj(plane->state->fb);
+	struct reservation_object *resv;
 	int ret = 0;
 
 	if (!obj && !old_obj)
@@ -13868,12 +14028,15 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 		}
 	}
 
+	if (!obj)
+		return 0;
+
 	/* For framebuffer backed by dmabuf, wait for fence */
-	if (obj && obj->base.dma_buf) {
+	resv = i915_gem_object_get_dmabuf_resv(obj);
+	if (resv) {
 		long lret;
 
-		lret = reservation_object_wait_timeout_rcu(obj->base.dma_buf->resv,
-							   false, true,
+		lret = reservation_object_wait_timeout_rcu(resv, false, true,
 							   MAX_SCHEDULE_TIMEOUT);
 		if (lret == -ERESTARTSYS)
 			return lret;
@@ -13881,9 +14044,7 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 		WARN(lret < 0, "waiting returns %li\n", lret);
 	}
 
-	if (!obj) {
-		ret = 0;
-	} else if (plane->type == DRM_PLANE_TYPE_CURSOR &&
+	if (plane->type == DRM_PLANE_TYPE_CURSOR &&
 	    INTEL_INFO(dev)->cursor_needs_physical) {
 		int align = IS_I830(dev) ? 16 * 1024 : 256;
 		ret = i915_gem_object_attach_phys(obj, align);
@@ -13894,15 +14055,11 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 	}
 
 	if (ret == 0) {
-		if (obj) {
-			struct intel_plane_state *plane_state =
-				to_intel_plane_state(new_state);
+		struct intel_plane_state *plane_state =
+			to_intel_plane_state(new_state);
 
-			i915_gem_request_assign(&plane_state->wait_req,
-						obj->last_write_req);
-		}
-
-		i915_gem_track_fb(old_obj, obj, intel_plane->frontbuffer_bit);
+		i915_gem_request_assign(&plane_state->wait_req,
+					obj->last_write_req);
 	}
 
 	return ret;
@@ -13922,7 +14079,6 @@ intel_cleanup_plane_fb(struct drm_plane *plane,
 		       const struct drm_plane_state *old_state)
 {
 	struct drm_device *dev = plane->dev;
-	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct intel_plane_state *old_intel_state;
 	struct drm_i915_gem_object *old_obj = intel_fb_obj(old_state->fb);
 	struct drm_i915_gem_object *obj = intel_fb_obj(plane->state->fb);
@@ -13936,11 +14092,6 @@ intel_cleanup_plane_fb(struct drm_plane *plane,
 	    !INTEL_INFO(dev)->cursor_needs_physical))
 		intel_unpin_fb_obj(old_state->fb, old_state->rotation);
 
-	/* prepare_fb aborted? */
-	if ((old_obj && (old_obj->frontbuffer_bits & intel_plane->frontbuffer_bit)) ||
-	    (obj && !(obj->frontbuffer_bits & intel_plane->frontbuffer_bit)))
-		i915_gem_track_fb(old_obj, obj, intel_plane->frontbuffer_bit);
-
 	i915_gem_request_assign(&old_intel_state->wait_req, NULL);
 }
 
@@ -13948,15 +14099,11 @@ int
 skl_max_scale(struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state)
 {
 	int max_scale;
-	struct drm_device *dev;
-	struct drm_i915_private *dev_priv;
 	int crtc_clock, cdclk;
 
 	if (!intel_crtc || !crtc_state->base.enable)
 		return DRM_PLANE_HELPER_NO_SCALING;
 
-	dev = intel_crtc->base.dev;
-	dev_priv = dev->dev_private;
 	crtc_clock = crtc_state->base.adjusted_mode.crtc_clock;
 	cdclk = to_intel_atomic_state(crtc_state->base.state)->cdclk;
 
@@ -13996,6 +14143,7 @@ intel_check_primary_plane(struct drm_plane *plane,
 
 	return drm_plane_helper_check_update(plane, crtc, fb, &state->src,
 					     &state->dst, &state->clip,
+					     state->base.rotation,
 					     min_scale, max_scale,
 					     can_position, true,
 					     &state->visible);
@@ -14032,7 +14180,7 @@ static void intel_finish_crtc_commit(struct drm_crtc *crtc,
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
-	intel_pipe_update_end(intel_crtc);
+	intel_pipe_update_end(intel_crtc, NULL);
 }
 
 /**
@@ -14044,9 +14192,11 @@ static void intel_finish_crtc_commit(struct drm_crtc *crtc,
  */
 void intel_plane_destroy(struct drm_plane *plane)
 {
-	struct intel_plane *intel_plane = to_intel_plane(plane);
+	if (!plane)
+		return;
+
 	drm_plane_cleanup(plane);
-	kfree(intel_plane);
+	kfree(to_intel_plane(plane));
 }
 
 const struct drm_plane_funcs intel_plane_funcs = {
@@ -14118,10 +14268,24 @@ static struct drm_plane *intel_primary_plane_create(struct drm_device *dev,
 		primary->disable_plane = i9xx_disable_primary_plane;
 	}
 
-	ret = drm_universal_plane_init(dev, &primary->base, 0,
-				       &intel_plane_funcs,
-				       intel_primary_formats, num_formats,
-				       DRM_PLANE_TYPE_PRIMARY, NULL);
+	if (INTEL_INFO(dev)->gen >= 9)
+		ret = drm_universal_plane_init(dev, &primary->base, 0,
+					       &intel_plane_funcs,
+					       intel_primary_formats, num_formats,
+					       DRM_PLANE_TYPE_PRIMARY,
+					       "plane 1%c", pipe_name(pipe));
+	else if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev))
+		ret = drm_universal_plane_init(dev, &primary->base, 0,
+					       &intel_plane_funcs,
+					       intel_primary_formats, num_formats,
+					       DRM_PLANE_TYPE_PRIMARY,
+					       "primary %c", pipe_name(pipe));
+	else
+		ret = drm_universal_plane_init(dev, &primary->base, 0,
+					       &intel_plane_funcs,
+					       intel_primary_formats, num_formats,
+					       DRM_PLANE_TYPE_PRIMARY,
+					       "plane %c", plane_name(primary->plane));
 	if (ret)
 		goto fail;
 
@@ -14171,6 +14335,7 @@ intel_check_cursor_plane(struct drm_plane *plane,
 
 	ret = drm_plane_helper_check_update(plane, crtc, fb, &state->src,
 					    &state->dst, &state->clip,
+					    state->base.rotation,
 					    DRM_PLANE_HELPER_NO_SCALING,
 					    DRM_PLANE_HELPER_NO_SCALING,
 					    true, true, &state->visible);
@@ -14279,7 +14444,8 @@ static struct drm_plane *intel_cursor_plane_create(struct drm_device *dev,
 				       &intel_plane_funcs,
 				       intel_cursor_formats,
 				       ARRAY_SIZE(intel_cursor_formats),
-				       DRM_PLANE_TYPE_CURSOR, NULL);
+				       DRM_PLANE_TYPE_CURSOR,
+				       "cursor %c", pipe_name(pipe));
 	if (ret)
 		goto fail;
 
@@ -14327,7 +14493,7 @@ static void skl_init_scalers(struct drm_device *dev, struct intel_crtc *intel_cr
 
 static void intel_crtc_init(struct drm_device *dev, int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc;
 	struct intel_crtc_state *crtc_state = NULL;
 	struct drm_plane *primary = NULL;
@@ -14364,7 +14530,8 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 		goto fail;
 
 	ret = drm_crtc_init_with_planes(dev, &intel_crtc->base, primary,
-					cursor, &intel_crtc_funcs, NULL);
+					cursor, &intel_crtc_funcs,
+					"pipe %c", pipe_name(pipe));
 	if (ret)
 		goto fail;
 
@@ -14398,10 +14565,8 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 	return;
 
 fail:
-	if (primary)
-		drm_plane_cleanup(primary);
-	if (cursor)
-		drm_plane_cleanup(cursor);
+	intel_plane_destroy(primary);
+	intel_plane_destroy(cursor);
 	kfree(crtc_state);
 	kfree(intel_crtc);
 }
@@ -14427,11 +14592,8 @@ int intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data,
 	struct intel_crtc *crtc;
 
 	drmmode_crtc = drm_crtc_find(dev, pipe_from_crtc_id->crtc_id);
-
-	if (!drmmode_crtc) {
-		DRM_ERROR("no such CRTC id\n");
+	if (!drmmode_crtc)
 		return -ENOENT;
-	}
 
 	crtc = to_intel_crtc(drmmode_crtc);
 	pipe_from_crtc_id->pipe = crtc->pipe;
@@ -14458,7 +14620,7 @@ static int intel_encoder_clones(struct intel_encoder *encoder)
 
 static bool has_edp_a(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!IS_MOBILE(dev))
 		return false;
@@ -14474,7 +14636,7 @@ static bool has_edp_a(struct drm_device *dev)
 
 static bool intel_crt_present(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (INTEL_INFO(dev)->gen >= 9)
 		return false;
@@ -14500,10 +14662,15 @@ static bool intel_crt_present(struct drm_device *dev)
 
 static void intel_setup_outputs(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *encoder;
 	bool dpd_is_edp = false;
 
+	/*
+	 * intel_edp_init_connector() depends on this completing first, to
+	 * prevent the registeration of both eDP and LVDS and the incorrect
+	 * sharing of the PPS.
+	 */
 	intel_lvds_init(dev);
 
 	if (intel_crt_present(dev))
@@ -15088,12 +15255,13 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 		dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train;
 	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
 		dev_priv->display.fdi_link_train = hsw_fdi_link_train;
-		if (IS_BROADWELL(dev_priv)) {
-			dev_priv->display.modeset_commit_cdclk =
-				broadwell_modeset_commit_cdclk;
-			dev_priv->display.modeset_calc_cdclk =
-				broadwell_modeset_calc_cdclk;
-		}
+	}
+
+	if (IS_BROADWELL(dev_priv)) {
+		dev_priv->display.modeset_commit_cdclk =
+			broadwell_modeset_commit_cdclk;
+		dev_priv->display.modeset_calc_cdclk =
+			broadwell_modeset_calc_cdclk;
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		dev_priv->display.modeset_commit_cdclk =
 			valleyview_modeset_commit_cdclk;
@@ -15101,9 +15269,14 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 			valleyview_modeset_calc_cdclk;
 	} else if (IS_BROXTON(dev_priv)) {
 		dev_priv->display.modeset_commit_cdclk =
-			broxton_modeset_commit_cdclk;
+			bxt_modeset_commit_cdclk;
 		dev_priv->display.modeset_calc_cdclk =
-			broxton_modeset_calc_cdclk;
+			bxt_modeset_calc_cdclk;
+	} else if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+		dev_priv->display.modeset_commit_cdclk =
+			skl_modeset_commit_cdclk;
+		dev_priv->display.modeset_calc_cdclk =
+			skl_modeset_calc_cdclk;
 	}
 
 	switch (INTEL_INFO(dev_priv)->gen) {
@@ -15142,7 +15315,7 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
  */
 static void quirk_pipea_force(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	dev_priv->quirks |= QUIRK_PIPEA_FORCE;
 	DRM_INFO("applying pipe a force quirk\n");
@@ -15150,7 +15323,7 @@ static void quirk_pipea_force(struct drm_device *dev)
 
 static void quirk_pipeb_force(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	dev_priv->quirks |= QUIRK_PIPEB_FORCE;
 	DRM_INFO("applying pipe b force quirk\n");
@@ -15161,7 +15334,7 @@ static void quirk_pipeb_force(struct drm_device *dev)
  */
 static void quirk_ssc_force_disable(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	dev_priv->quirks |= QUIRK_LVDS_SSC_DISABLE;
 	DRM_INFO("applying lvds SSC disable quirk\n");
 }
@@ -15172,7 +15345,7 @@ static void quirk_ssc_force_disable(struct drm_device *dev)
  */
 static void quirk_invert_brightness(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	dev_priv->quirks |= QUIRK_INVERT_BRIGHTNESS;
 	DRM_INFO("applying inverted panel brightness quirk\n");
 }
@@ -15180,7 +15353,7 @@ static void quirk_invert_brightness(struct drm_device *dev)
 /* Some VBT's incorrectly indicate no backlight is present */
 static void quirk_backlight_present(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	dev_priv->quirks |= QUIRK_BACKLIGHT_PRESENT;
 	DRM_INFO("applying backlight present quirk\n");
 }
@@ -15306,7 +15479,7 @@ static void intel_init_quirks(struct drm_device *dev)
 /* Disable the VGA plane that we never use */
 static void i915_disable_vga(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u8 sr1;
 	i915_reg_t vga_reg = i915_vgacntrl_reg(dev);
 
@@ -15324,14 +15497,14 @@ static void i915_disable_vga(struct drm_device *dev)
 
 void intel_modeset_init_hw(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	intel_update_cdclk(dev);
 
 	dev_priv->atomic_cdclk_freq = dev_priv->cdclk_freq;
 
 	intel_init_clock_gating(dev);
-	intel_enable_gt_powersave(dev);
+	intel_enable_gt_powersave(dev_priv);
 }
 
 /*
@@ -15401,7 +15574,6 @@ retry:
 	}
 
 	/* Write calculated watermark values back */
-	to_i915(dev)->wm.config = to_intel_atomic_state(state)->wm_config;
 	for_each_crtc_in_state(state, crtc, cstate, i) {
 		struct intel_crtc_state *cs = to_intel_crtc_state(cstate);
 
@@ -15499,11 +15671,13 @@ void intel_modeset_init(struct drm_device *dev)
 	}
 
 	intel_update_czclk(dev_priv);
-	intel_update_rawclk(dev_priv);
 	intel_update_cdclk(dev);
 
 	intel_shared_dpll_init(dev);
 
+	if (dev_priv->max_cdclk_freq == 0)
+		intel_update_max_cdclk(dev);
+
 	/* Just disable it once at startup */
 	i915_disable_vga(dev);
 	intel_setup_outputs(dev);
@@ -15571,7 +15745,7 @@ static bool
 intel_check_plane_mapping(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val;
 
 	if (INTEL_INFO(dev)->num_pipes == 1)
@@ -15611,7 +15785,7 @@ static bool intel_encoder_has_connectors(struct intel_encoder *encoder)
 static void intel_sanitize_crtc(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = crtc->config->cpu_transcoder;
 
 	/* Clear any frame start delays used for debugging left by the BIOS */
@@ -15644,8 +15818,8 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 	if (INTEL_INFO(dev)->gen < 4 && !intel_check_plane_mapping(crtc)) {
 		bool plane;
 
-		DRM_DEBUG_KMS("[CRTC:%d] wrong plane connection detected!\n",
-			      crtc->base.base.id);
+		DRM_DEBUG_KMS("[CRTC:%d:%s] wrong plane connection detected!\n",
+			      crtc->base.base.id, crtc->base.name);
 
 		/* Pipe has the wrong plane attached and the plane is active.
 		 * Temporarily change the plane mapping and disable everything
@@ -15736,7 +15910,7 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 
 void i915_redisable_vga_power_on(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t vga_reg = i915_vgacntrl_reg(dev);
 
 	if (!(I915_READ(vga_reg) & VGA_DISP_DISABLE)) {
@@ -15747,7 +15921,7 @@ void i915_redisable_vga_power_on(struct drm_device *dev)
 
 void i915_redisable_vga(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* This function can be called both from intel_modeset_setup_hw_state or
 	 * at a very early point in our resume sequence, where the power well
@@ -15787,7 +15961,7 @@ static void readout_plane_state(struct intel_crtc *crtc)
 
 static void intel_modeset_readout_hw_state(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe;
 	struct intel_crtc *crtc;
 	struct intel_encoder *encoder;
@@ -15813,26 +15987,24 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		if (crtc_state->base.active) {
 			dev_priv->active_crtcs |= 1 << crtc->pipe;
 
-			if (IS_BROADWELL(dev_priv)) {
+			if (INTEL_GEN(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
 				pixclk = ilk_pipe_pixel_rate(crtc_state);
-
-				/* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
-				if (crtc_state->ips_enabled)
-					pixclk = DIV_ROUND_UP(pixclk * 100, 95);
-			} else if (IS_VALLEYVIEW(dev_priv) ||
-				   IS_CHERRYVIEW(dev_priv) ||
-				   IS_BROXTON(dev_priv))
+			else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 				pixclk = crtc_state->base.adjusted_mode.crtc_clock;
 			else
 				WARN_ON(dev_priv->display.modeset_calc_cdclk);
+
+			/* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
+			if (IS_BROADWELL(dev_priv) && crtc_state->ips_enabled)
+				pixclk = DIV_ROUND_UP(pixclk * 100, 95);
 		}
 
 		dev_priv->min_pixclk[crtc->pipe] = pixclk;
 
 		readout_plane_state(crtc);
 
-		DRM_DEBUG_KMS("[CRTC:%d] hw state readout: %s\n",
-			      crtc->base.base.id,
+		DRM_DEBUG_KMS("[CRTC:%d:%s] hw state readout: %s\n",
+			      crtc->base.base.id, crtc->base.name,
 			      crtc->active ? "enabled" : "disabled");
 	}
 
@@ -15858,6 +16030,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		if (encoder->get_hw_state(encoder, &pipe)) {
 			crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 			encoder->base.crtc = &crtc->base;
+			crtc->config->output_types |= 1 << encoder->type;
 			encoder->get_config(encoder, crtc->config);
 		} else {
 			encoder->base.crtc = NULL;
@@ -15942,7 +16115,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 static void
 intel_modeset_setup_hw_state(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe;
 	struct intel_crtc *crtc;
 	struct intel_encoder *encoder;
@@ -16063,15 +16236,16 @@ retry:
 
 void intel_modeset_gem_init(struct drm_device *dev)
 {
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *c;
 	struct drm_i915_gem_object *obj;
 	int ret;
 
-	intel_init_gt_powersave(dev);
+	intel_init_gt_powersave(dev_priv);
 
 	intel_modeset_init_hw(dev);
 
-	intel_setup_overlay(dev);
+	intel_setup_overlay(dev_priv);
 
 	/*
 	 * Make sure any fbs we allocated at startup are properly
@@ -16097,26 +16271,36 @@ void intel_modeset_gem_init(struct drm_device *dev)
 			c->state->plane_mask &= ~(1 << drm_plane_index(c->primary));
 		}
 	}
+}
+
+int intel_connector_register(struct drm_connector *connector)
+{
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	int ret;
+
+	ret = intel_backlight_device_register(intel_connector);
+	if (ret)
+		goto err;
 
-	intel_backlight_register(dev);
+	return 0;
+
+err:
+	return ret;
 }
 
-void intel_connector_unregister(struct intel_connector *intel_connector)
+void intel_connector_unregister(struct drm_connector *connector)
 {
-	struct drm_connector *connector = &intel_connector->base;
+	struct intel_connector *intel_connector = to_intel_connector(connector);
 
+	intel_backlight_device_unregister(intel_connector);
 	intel_panel_destroy_backlight(connector);
-	drm_connector_unregister(connector);
 }
 
 void intel_modeset_cleanup(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_connector *connector;
-
-	intel_disable_gt_powersave(dev);
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
-	intel_backlight_unregister(dev);
+	intel_disable_gt_powersave(dev_priv);
 
 	/*
 	 * Interrupts and polling as the first thing to avoid creating havoc.
@@ -16138,27 +16322,15 @@ void intel_modeset_cleanup(struct drm_device *dev)
 	/* flush any delayed tasks or pending work */
 	flush_scheduled_work();
 
-	/* destroy the backlight and sysfs files before encoders/connectors */
-	for_each_intel_connector(dev, connector)
-		connector->unregister(connector);
-
 	drm_mode_config_cleanup(dev);
 
-	intel_cleanup_overlay(dev);
+	intel_cleanup_overlay(dev_priv);
 
-	intel_cleanup_gt_powersave(dev);
+	intel_cleanup_gt_powersave(dev_priv);
 
 	intel_teardown_gmbus(dev);
 }
 
-/*
- * Return which encoder is currently attached for connector.
- */
-struct drm_encoder *intel_best_encoder(struct drm_connector *connector)
-{
-	return &intel_attached_encoder(connector)->base;
-}
-
 void intel_connector_attach_encoder(struct intel_connector *connector,
 				    struct intel_encoder *encoder)
 {
@@ -16172,7 +16344,7 @@ void intel_connector_attach_encoder(struct intel_connector *connector,
  */
 int intel_modeset_vga_set_state(struct drm_device *dev, bool state)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	unsigned reg = INTEL_INFO(dev)->gen >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL;
 	u16 gmch_ctrl;
 
@@ -16242,9 +16414,8 @@ struct intel_display_error_state {
 };
 
 struct intel_display_error_state *
-intel_display_capture_error_state(struct drm_device *dev)
+intel_display_capture_error_state(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_display_error_state *error;
 	int transcoders[] = {
 		TRANSCODER_A,
@@ -16254,14 +16425,14 @@ intel_display_capture_error_state(struct drm_device *dev)
 	};
 	int i;
 
-	if (INTEL_INFO(dev)->num_pipes == 0)
+	if (INTEL_INFO(dev_priv)->num_pipes == 0)
 		return NULL;
 
 	error = kzalloc(sizeof(*error), GFP_ATOMIC);
 	if (error == NULL)
 		return NULL;
 
-	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		error->power_well_driver = I915_READ(HSW_PWR_WELL_DRIVER);
 
 	for_each_pipe(dev_priv, i) {
@@ -16277,25 +16448,25 @@ intel_display_capture_error_state(struct drm_device *dev)
 
 		error->plane[i].control = I915_READ(DSPCNTR(i));
 		error->plane[i].stride = I915_READ(DSPSTRIDE(i));
-		if (INTEL_INFO(dev)->gen <= 3) {
+		if (INTEL_GEN(dev_priv) <= 3) {
 			error->plane[i].size = I915_READ(DSPSIZE(i));
 			error->plane[i].pos = I915_READ(DSPPOS(i));
 		}
-		if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev))
+		if (INTEL_GEN(dev_priv) <= 7 && !IS_HASWELL(dev_priv))
 			error->plane[i].addr = I915_READ(DSPADDR(i));
-		if (INTEL_INFO(dev)->gen >= 4) {
+		if (INTEL_GEN(dev_priv) >= 4) {
 			error->plane[i].surface = I915_READ(DSPSURF(i));
 			error->plane[i].tile_offset = I915_READ(DSPTILEOFF(i));
 		}
 
 		error->pipe[i].source = I915_READ(PIPESRC(i));
 
-		if (HAS_GMCH_DISPLAY(dev))
+		if (HAS_GMCH_DISPLAY(dev_priv))
 			error->pipe[i].stat = I915_READ(PIPESTAT(i));
 	}
 
 	/* Note: this does not include DSI transcoders. */
-	error->num_transcoders = INTEL_INFO(dev)->num_pipes;
+	error->num_transcoders = INTEL_INFO(dev_priv)->num_pipes;
 	if (HAS_DDI(dev_priv))
 		error->num_transcoders++; /* Account for eDP. */
 
@@ -16329,7 +16500,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 				struct drm_device *dev,
 				struct intel_display_error_state *error)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
 	if (!error)
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 891107f92d9f..21b04c3eda41 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -131,11 +131,6 @@ static void vlv_steal_power_sequencer(struct drm_device *dev,
 				      enum pipe pipe);
 static void intel_dp_unset_edid(struct intel_dp *intel_dp);
 
-static unsigned int intel_dp_unused_lane_mask(int lane_count)
-{
-	return ~((1 << lane_count) - 1) & 0xf;
-}
-
 static int
 intel_dp_max_link_bw(struct intel_dp  *intel_dp)
 {
@@ -267,7 +262,7 @@ static void pps_lock(struct intel_dp *intel_dp)
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *encoder = &intel_dig_port->base;
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 
 	/*
@@ -285,7 +280,7 @@ static void pps_unlock(struct intel_dp *intel_dp)
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *encoder = &intel_dig_port->base;
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 
 	mutex_unlock(&dev_priv->pps_mutex);
@@ -299,7 +294,7 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = intel_dp->pps_pipe;
 	bool pll_enabled, release_cl_override = false;
 	enum dpio_phy phy = DPIO_PHY(pipe);
@@ -373,7 +368,7 @@ vlv_power_sequencer_pipe(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *encoder;
 	unsigned int pipes = (1 << PIPE_A) | (1 << PIPE_B);
 	enum pipe pipe;
@@ -431,6 +426,37 @@ vlv_power_sequencer_pipe(struct intel_dp *intel_dp)
 	return intel_dp->pps_pipe;
 }
 
+static int
+bxt_power_sequencer_idx(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
+	/* We should never land here with regular DP ports */
+	WARN_ON(!is_edp(intel_dp));
+
+	/*
+	 * TODO: BXT has 2 PPS instances. The correct port->PPS instance
+	 * mapping needs to be retrieved from VBT, for now just hard-code to
+	 * use instance #0 always.
+	 */
+	if (!intel_dp->pps_reset)
+		return 0;
+
+	intel_dp->pps_reset = false;
+
+	/*
+	 * Only the HW needs to be reprogrammed, the SW state is fixed and
+	 * has been setup during connector init.
+	 */
+	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp);
+
+	return 0;
+}
+
 typedef bool (*vlv_pipe_check)(struct drm_i915_private *dev_priv,
 			       enum pipe pipe);
 
@@ -480,7 +506,7 @@ vlv_initial_power_sequencer_setup(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_dig_port->port;
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
@@ -512,12 +538,13 @@ vlv_initial_power_sequencer_setup(struct intel_dp *intel_dp)
 	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp);
 }
 
-void vlv_power_sequencer_reset(struct drm_i915_private *dev_priv)
+void intel_power_sequencer_reset(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct intel_encoder *encoder;
 
-	if (WARN_ON(!IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev)))
+	if (WARN_ON(!IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev) &&
+		    !IS_BROXTON(dev)))
 		return;
 
 	/*
@@ -537,34 +564,71 @@ void vlv_power_sequencer_reset(struct drm_i915_private *dev_priv)
 			continue;
 
 		intel_dp = enc_to_intel_dp(&encoder->base);
-		intel_dp->pps_pipe = INVALID_PIPE;
+		if (IS_BROXTON(dev))
+			intel_dp->pps_reset = true;
+		else
+			intel_dp->pps_pipe = INVALID_PIPE;
+	}
+}
+
+struct pps_registers {
+	i915_reg_t pp_ctrl;
+	i915_reg_t pp_stat;
+	i915_reg_t pp_on;
+	i915_reg_t pp_off;
+	i915_reg_t pp_div;
+};
+
+static void intel_pps_get_registers(struct drm_i915_private *dev_priv,
+				    struct intel_dp *intel_dp,
+				    struct pps_registers *regs)
+{
+	memset(regs, 0, sizeof(*regs));
+
+	if (IS_BROXTON(dev_priv)) {
+		int idx = bxt_power_sequencer_idx(intel_dp);
+
+		regs->pp_ctrl = BXT_PP_CONTROL(idx);
+		regs->pp_stat = BXT_PP_STATUS(idx);
+		regs->pp_on = BXT_PP_ON_DELAYS(idx);
+		regs->pp_off = BXT_PP_OFF_DELAYS(idx);
+	} else if (HAS_PCH_SPLIT(dev_priv)) {
+		regs->pp_ctrl = PCH_PP_CONTROL;
+		regs->pp_stat = PCH_PP_STATUS;
+		regs->pp_on = PCH_PP_ON_DELAYS;
+		regs->pp_off = PCH_PP_OFF_DELAYS;
+		regs->pp_div = PCH_PP_DIVISOR;
+	} else {
+		enum pipe pipe = vlv_power_sequencer_pipe(intel_dp);
+
+		regs->pp_ctrl = VLV_PIPE_PP_CONTROL(pipe);
+		regs->pp_stat = VLV_PIPE_PP_STATUS(pipe);
+		regs->pp_on = VLV_PIPE_PP_ON_DELAYS(pipe);
+		regs->pp_off = VLV_PIPE_PP_OFF_DELAYS(pipe);
+		regs->pp_div = VLV_PIPE_PP_DIVISOR(pipe);
 	}
 }
 
 static i915_reg_t
 _pp_ctrl_reg(struct intel_dp *intel_dp)
 {
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct pps_registers regs;
 
-	if (IS_BROXTON(dev))
-		return BXT_PP_CONTROL(0);
-	else if (HAS_PCH_SPLIT(dev))
-		return PCH_PP_CONTROL;
-	else
-		return VLV_PIPE_PP_CONTROL(vlv_power_sequencer_pipe(intel_dp));
+	intel_pps_get_registers(to_i915(intel_dp_to_dev(intel_dp)), intel_dp,
+				&regs);
+
+	return regs.pp_ctrl;
 }
 
 static i915_reg_t
 _pp_stat_reg(struct intel_dp *intel_dp)
 {
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct pps_registers regs;
 
-	if (IS_BROXTON(dev))
-		return BXT_PP_STATUS(0);
-	else if (HAS_PCH_SPLIT(dev))
-		return PCH_PP_STATUS;
-	else
-		return VLV_PIPE_PP_STATUS(vlv_power_sequencer_pipe(intel_dp));
+	intel_pps_get_registers(to_i915(intel_dp_to_dev(intel_dp)), intel_dp,
+				&regs);
+
+	return regs.pp_stat;
 }
 
 /* Reboot notifier handler to shutdown panel power to guarantee T12 timing
@@ -575,7 +639,7 @@ static int edp_notify_handler(struct notifier_block *this, unsigned long code,
 	struct intel_dp *intel_dp = container_of(this, typeof(* intel_dp),
 						 edp_notifier);
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!is_edp(intel_dp) || code != SYS_RESTART)
 		return 0;
@@ -606,7 +670,7 @@ static int edp_notify_handler(struct notifier_block *this, unsigned long code,
 static bool edp_have_panel_power(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
@@ -620,7 +684,7 @@ static bool edp_have_panel_power(struct intel_dp *intel_dp)
 static bool edp_have_panel_vdd(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
@@ -635,7 +699,7 @@ static void
 intel_dp_check_edp(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (!is_edp(intel_dp))
 		return;
@@ -653,7 +717,7 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t ch_ctl = intel_dp->aux_ch_ctl_reg;
 	uint32_t status;
 	bool done;
@@ -775,6 +839,7 @@ static uint32_t skl_get_aux_send_ctl(struct intel_dp *intel_dp,
 	       DP_AUX_CH_CTL_TIME_OUT_1600us |
 	       DP_AUX_CH_CTL_RECEIVE_ERROR |
 	       (send_bytes << DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT) |
+	       DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(32) |
 	       DP_AUX_CH_CTL_SYNC_PULSE_SKL(32);
 }
 
@@ -785,7 +850,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t ch_ctl = intel_dp->aux_ch_ctl_reg;
 	uint32_t aux_clock_divider;
 	int i, ret, recv_bytes;
@@ -1181,48 +1246,21 @@ static void intel_aux_reg_init(struct intel_dp *intel_dp)
 static void
 intel_dp_aux_fini(struct intel_dp *intel_dp)
 {
-	drm_dp_aux_unregister(&intel_dp->aux);
 	kfree(intel_dp->aux.name);
 }
 
-static int
+static void
 intel_dp_aux_init(struct intel_dp *intel_dp, struct intel_connector *connector)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	enum port port = intel_dig_port->port;
-	int ret;
 
 	intel_aux_reg_init(intel_dp);
+	drm_dp_aux_init(&intel_dp->aux);
 
+	/* Failure to allocate our preferred name is not critical */
 	intel_dp->aux.name = kasprintf(GFP_KERNEL, "DPDDC-%c", port_name(port));
-	if (!intel_dp->aux.name)
-		return -ENOMEM;
-
-	intel_dp->aux.dev = connector->base.kdev;
 	intel_dp->aux.transfer = intel_dp_aux_transfer;
-
-	DRM_DEBUG_KMS("registering %s bus for %s\n",
-		      intel_dp->aux.name,
-		      connector->base.kdev->kobj.name);
-
-	ret = drm_dp_aux_register(&intel_dp->aux);
-	if (ret < 0) {
-		DRM_ERROR("drm_dp_aux_register() for %s failed (%d)\n",
-			  intel_dp->aux.name, ret);
-		kfree(intel_dp->aux.name);
-		return ret;
-	}
-
-	return 0;
-}
-
-static void
-intel_dp_connector_unregister(struct intel_connector *intel_connector)
-{
-	struct intel_dp *intel_dp = intel_attached_dp(&intel_connector->base);
-
-	intel_dp_aux_fini(intel_dp);
-	intel_connector_unregister(intel_connector);
 }
 
 static int
@@ -1435,7 +1473,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 			struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	enum port port = dp_to_dig_port(intel_dp)->port;
@@ -1463,7 +1501,6 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev) && port != PORT_A)
 		pipe_config->has_pch_encoder = true;
 
-	pipe_config->has_dp_encoder = true;
 	pipe_config->has_drrs = false;
 	pipe_config->has_audio = intel_dp->has_audio && port != PORT_A;
 
@@ -1582,6 +1619,27 @@ found:
 				&pipe_config->dp_m2_n2);
 	}
 
+	/*
+	 * DPLL0 VCO may need to be adjusted to get the correct
+	 * clock for eDP. This will affect cdclk as well.
+	 */
+	if (is_edp(intel_dp) &&
+	    (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))) {
+		int vco;
+
+		switch (pipe_config->port_clock / 2) {
+		case 108000:
+		case 216000:
+			vco = 8640000;
+			break;
+		default:
+			vco = 8100000;
+			break;
+		}
+
+		to_intel_atomic_state(pipe_config->base.state)->cdclk_pll_vco = vco;
+	}
+
 	if (!HAS_DDI(dev))
 		intel_dp_set_clock(encoder, pipe_config);
 
@@ -1598,7 +1656,7 @@ void intel_dp_set_link_params(struct intel_dp *intel_dp,
 static void intel_dp_prepare(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	enum port port = dp_to_dig_port(intel_dp)->port;
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
@@ -1686,16 +1744,21 @@ static void intel_dp_prepare(struct intel_encoder *encoder)
 #define IDLE_CYCLE_MASK		(PP_ON | PP_SEQUENCE_MASK | PP_CYCLE_DELAY_ACTIVE | PP_SEQUENCE_STATE_MASK)
 #define IDLE_CYCLE_VALUE	(0     | PP_SEQUENCE_NONE | 0                     | PP_SEQUENCE_STATE_OFF_IDLE)
 
+static void intel_pps_verify_state(struct drm_i915_private *dev_priv,
+				   struct intel_dp *intel_dp);
+
 static void wait_panel_status(struct intel_dp *intel_dp,
 				       u32 mask,
 				       u32 value)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t pp_stat_reg, pp_ctrl_reg;
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
+	intel_pps_verify_state(dev_priv, intel_dp);
+
 	pp_stat_reg = _pp_stat_reg(intel_dp);
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 
@@ -1704,8 +1767,9 @@ static void wait_panel_status(struct intel_dp *intel_dp,
 			I915_READ(pp_stat_reg),
 			I915_READ(pp_ctrl_reg));
 
-	if (_wait_for((I915_READ(pp_stat_reg) & mask) == value,
-		      5 * USEC_PER_SEC, 10 * USEC_PER_MSEC))
+	if (intel_wait_for_register(dev_priv,
+				    pp_stat_reg, mask, value,
+				    5000))
 		DRM_ERROR("Panel status timeout: status %08x control %08x\n",
 				I915_READ(pp_stat_reg),
 				I915_READ(pp_ctrl_reg));
@@ -1765,7 +1829,7 @@ static void edp_wait_backlight_off(struct intel_dp *intel_dp)
 static  u32 ironlake_get_pp_control(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 control;
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
@@ -1788,7 +1852,7 @@ static bool edp_panel_vdd_on(struct intel_dp *intel_dp)
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 	u32 pp;
 	i915_reg_t pp_stat_reg, pp_ctrl_reg;
@@ -1861,7 +1925,7 @@ void intel_edp_panel_vdd_on(struct intel_dp *intel_dp)
 static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_digital_port *intel_dig_port =
 		dp_to_dig_port(intel_dp);
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
@@ -1930,8 +1994,7 @@ static void edp_panel_vdd_schedule_off(struct intel_dp *intel_dp)
  */
 static void edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
 {
-	struct drm_i915_private *dev_priv =
-		intel_dp_to_dev(intel_dp)->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
@@ -1952,7 +2015,7 @@ static void edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
 static void edp_panel_on(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 pp;
 	i915_reg_t pp_ctrl_reg;
 
@@ -2013,7 +2076,7 @@ static void edp_panel_off(struct intel_dp *intel_dp)
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 	u32 pp;
 	i915_reg_t pp_ctrl_reg;
@@ -2065,7 +2128,7 @@ static void _intel_edp_backlight_on(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 pp;
 	i915_reg_t pp_ctrl_reg;
 
@@ -2106,7 +2169,7 @@ void intel_edp_backlight_on(struct intel_dp *intel_dp)
 static void _intel_edp_backlight_off(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 pp;
 	i915_reg_t pp_ctrl_reg;
 
@@ -2222,7 +2285,7 @@ static void ironlake_edp_pll_on(struct intel_dp *intel_dp)
 	 * 2. Program DP PLL enable
 	 */
 	if (IS_GEN5(dev_priv))
-		intel_wait_for_vblank_if_active(dev_priv->dev, !crtc->pipe);
+		intel_wait_for_vblank_if_active(&dev_priv->drm, !crtc->pipe);
 
 	intel_dp->DP |= DP_PLL_ENABLE;
 
@@ -2287,7 +2350,7 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	enum port port = dp_to_dig_port(intel_dp)->port;
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
 	bool ret;
@@ -2340,7 +2403,7 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	u32 tmp, flags = 0;
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = dp_to_dig_port(intel_dp)->port;
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 
@@ -2378,8 +2441,6 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 	    !IS_CHERRYVIEW(dev) && tmp & DP_COLOR_RANGE_16_235)
 		pipe_config->limited_color_range = true;
 
-	pipe_config->has_dp_encoder = true;
-
 	pipe_config->lane_count =
 		((tmp & DP_PORT_WIDTH_MASK) >> DP_PORT_WIDTH_SHIFT) + 1;
 
@@ -2460,55 +2521,11 @@ static void vlv_post_disable_dp(struct intel_encoder *encoder)
 	intel_dp_link_down(intel_dp);
 }
 
-static void chv_data_lane_soft_reset(struct intel_encoder *encoder,
-				     bool reset)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base));
-	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
-	enum pipe pipe = crtc->pipe;
-	uint32_t val;
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
-	if (reset)
-		val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
-	else
-		val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
-
-	if (crtc->config->lane_count > 2) {
-		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
-		if (reset)
-			val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
-		else
-			val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET;
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
-	}
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
-	val |= CHV_PCS_REQ_SOFTRESET_EN;
-	if (reset)
-		val &= ~DPIO_PCS_CLK_SOFT_RESET;
-	else
-		val |= DPIO_PCS_CLK_SOFT_RESET;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
-
-	if (crtc->config->lane_count > 2) {
-		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
-		val |= CHV_PCS_REQ_SOFTRESET_EN;
-		if (reset)
-			val &= ~DPIO_PCS_CLK_SOFT_RESET;
-		else
-			val |= DPIO_PCS_CLK_SOFT_RESET;
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
-	}
-}
-
 static void chv_post_disable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	intel_dp_link_down(intel_dp);
 
@@ -2527,7 +2544,7 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_dig_port->port;
 
 	if (HAS_DDI(dev)) {
@@ -2607,7 +2624,7 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 static void intel_dp_enable_port(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc =
 		to_intel_crtc(dp_to_dig_port(intel_dp)->base.base.crtc);
 
@@ -2636,7 +2653,7 @@ static void intel_enable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	uint32_t dp_reg = I915_READ(intel_dp->output_reg);
 	enum pipe pipe = crtc->pipe;
@@ -2709,7 +2726,7 @@ static void g4x_pre_enable_dp(struct intel_encoder *encoder)
 static void vlv_detach_power_sequencer(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = intel_dig_port->base.base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
 	enum pipe pipe = intel_dp->pps_pipe;
 	i915_reg_t pp_on_reg = VLV_PIPE_PP_ON_DELAYS(pipe);
 
@@ -2735,7 +2752,7 @@ static void vlv_detach_power_sequencer(struct intel_dp *intel_dp)
 static void vlv_steal_power_sequencer(struct drm_device *dev,
 				      enum pipe pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *encoder;
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
@@ -2773,7 +2790,7 @@ static void vlv_init_panel_power_sequencer(struct intel_dp *intel_dp)
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *encoder = &intel_dig_port->base;
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
@@ -2811,266 +2828,38 @@ static void vlv_init_panel_power_sequencer(struct intel_dp *intel_dp)
 
 static void vlv_pre_enable_dp(struct intel_encoder *encoder)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
-	enum dpio_channel port = vlv_dport_to_channel(dport);
-	int pipe = intel_crtc->pipe;
-	u32 val;
-
-	mutex_lock(&dev_priv->sb_lock);
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(port));
-	val = 0;
-	if (pipe)
-		val |= (1<<21);
-	else
-		val &= ~(1<<21);
-	val |= 0x001000c4;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW8(port), val);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW14(port), 0x00760018);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW23(port), 0x00400888);
-
-	mutex_unlock(&dev_priv->sb_lock);
+	vlv_phy_pre_encoder_enable(encoder);
 
 	intel_enable_dp(encoder);
 }
 
 static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(encoder->base.crtc);
-	enum dpio_channel port = vlv_dport_to_channel(dport);
-	int pipe = intel_crtc->pipe;
-
 	intel_dp_prepare(encoder);
 
-	/* Program Tx lane resets to default */
-	mutex_lock(&dev_priv->sb_lock);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port),
-			 DPIO_PCS_TX_LANE2_RESET |
-			 DPIO_PCS_TX_LANE1_RESET);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW1(port),
-			 DPIO_PCS_CLK_CRI_RXEB_EIOS_EN |
-			 DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN |
-			 (1<<DPIO_PCS_CLK_DATAWIDTH_SHIFT) |
-				 DPIO_PCS_CLK_SOFT_RESET);
-
-	/* Fix up inter-pair skew failure */
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW12(port), 0x00750f00);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW11(port), 0x00001500);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW14(port), 0x40400000);
-	mutex_unlock(&dev_priv->sb_lock);
+	vlv_phy_pre_pll_enable(encoder);
 }
 
 static void chv_pre_enable_dp(struct intel_encoder *encoder)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(encoder->base.crtc);
-	enum dpio_channel ch = vlv_dport_to_channel(dport);
-	int pipe = intel_crtc->pipe;
-	int data, i, stagger;
-	u32 val;
-
-	mutex_lock(&dev_priv->sb_lock);
-
-	/* allow hardware to manage TX FIFO reset source */
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW11(ch));
-	val &= ~DPIO_LANEDESKEW_STRAP_OVRD;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW11(ch), val);
-
-	if (intel_crtc->config->lane_count > 2) {
-		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch));
-		val &= ~DPIO_LANEDESKEW_STRAP_OVRD;
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
-	}
-
-	/* Program Tx lane latency optimal setting*/
-	for (i = 0; i < intel_crtc->config->lane_count; i++) {
-		/* Set the upar bit */
-		if (intel_crtc->config->lane_count == 1)
-			data = 0x0;
-		else
-			data = (i == 1) ? 0x0 : 0x1;
-		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i),
-				data << DPIO_UPAR_SHIFT);
-	}
-
-	/* Data lane stagger programming */
-	if (intel_crtc->config->port_clock > 270000)
-		stagger = 0x18;
-	else if (intel_crtc->config->port_clock > 135000)
-		stagger = 0xd;
-	else if (intel_crtc->config->port_clock > 67500)
-		stagger = 0x7;
-	else if (intel_crtc->config->port_clock > 33750)
-		stagger = 0x4;
-	else
-		stagger = 0x2;
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW11(ch));
-	val |= DPIO_TX2_STAGGER_MASK(0x1f);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW11(ch), val);
-
-	if (intel_crtc->config->lane_count > 2) {
-		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch));
-		val |= DPIO_TX2_STAGGER_MASK(0x1f);
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
-	}
-
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW12(ch),
-		       DPIO_LANESTAGGER_STRAP(stagger) |
-		       DPIO_LANESTAGGER_STRAP_OVRD |
-		       DPIO_TX1_STAGGER_MASK(0x1f) |
-		       DPIO_TX1_STAGGER_MULT(6) |
-		       DPIO_TX2_STAGGER_MULT(0));
-
-	if (intel_crtc->config->lane_count > 2) {
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW12(ch),
-			       DPIO_LANESTAGGER_STRAP(stagger) |
-			       DPIO_LANESTAGGER_STRAP_OVRD |
-			       DPIO_TX1_STAGGER_MASK(0x1f) |
-			       DPIO_TX1_STAGGER_MULT(7) |
-			       DPIO_TX2_STAGGER_MULT(5));
-	}
-
-	/* Deassert data lane reset */
-	chv_data_lane_soft_reset(encoder, false);
-
-	mutex_unlock(&dev_priv->sb_lock);
+	chv_phy_pre_encoder_enable(encoder);
 
 	intel_enable_dp(encoder);
 
 	/* Second common lane will stay alive on its own now */
-	if (dport->release_cl2_override) {
-		chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, false);
-		dport->release_cl2_override = false;
-	}
+	chv_phy_release_cl2_override(encoder);
 }
 
 static void chv_dp_pre_pll_enable(struct intel_encoder *encoder)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(encoder->base.crtc);
-	enum dpio_channel ch = vlv_dport_to_channel(dport);
-	enum pipe pipe = intel_crtc->pipe;
-	unsigned int lane_mask =
-		intel_dp_unused_lane_mask(intel_crtc->config->lane_count);
-	u32 val;
-
 	intel_dp_prepare(encoder);
 
-	/*
-	 * Must trick the second common lane into life.
-	 * Otherwise we can't even access the PLL.
-	 */
-	if (ch == DPIO_CH0 && pipe == PIPE_B)
-		dport->release_cl2_override =
-			!chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, true);
-
-	chv_phy_powergate_lanes(encoder, true, lane_mask);
-
-	mutex_lock(&dev_priv->sb_lock);
-
-	/* Assert data lane reset */
-	chv_data_lane_soft_reset(encoder, true);
-
-	/* program left/right clock distribution */
-	if (pipe != PIPE_B) {
-		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
-		val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
-		if (ch == DPIO_CH0)
-			val |= CHV_BUFLEFTENA1_FORCE;
-		if (ch == DPIO_CH1)
-			val |= CHV_BUFRIGHTENA1_FORCE;
-		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
-	} else {
-		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
-		val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
-		if (ch == DPIO_CH0)
-			val |= CHV_BUFLEFTENA2_FORCE;
-		if (ch == DPIO_CH1)
-			val |= CHV_BUFRIGHTENA2_FORCE;
-		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
-	}
-
-	/* program clock channel usage */
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(ch));
-	val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
-	if (pipe != PIPE_B)
-		val &= ~CHV_PCS_USEDCLKCHANNEL;
-	else
-		val |= CHV_PCS_USEDCLKCHANNEL;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW8(ch), val);
-
-	if (intel_crtc->config->lane_count > 2) {
-		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW8(ch));
-		val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
-		if (pipe != PIPE_B)
-			val &= ~CHV_PCS_USEDCLKCHANNEL;
-		else
-			val |= CHV_PCS_USEDCLKCHANNEL;
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW8(ch), val);
-	}
-
-	/*
-	 * This a a bit weird since generally CL
-	 * matches the pipe, but here we need to
-	 * pick the CL based on the port.
-	 */
-	val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW19(ch));
-	if (pipe != PIPE_B)
-		val &= ~CHV_CMN_USEDCLKCHANNEL;
-	else
-		val |= CHV_CMN_USEDCLKCHANNEL;
-	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW19(ch), val);
-
-	mutex_unlock(&dev_priv->sb_lock);
+	chv_phy_pre_pll_enable(encoder);
 }
 
 static void chv_dp_post_pll_disable(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum pipe pipe = to_intel_crtc(encoder->base.crtc)->pipe;
-	u32 val;
-
-	mutex_lock(&dev_priv->sb_lock);
-
-	/* disable left/right clock distribution */
-	if (pipe != PIPE_B) {
-		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
-		val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
-		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
-	} else {
-		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
-		val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
-		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
-	}
-
-	mutex_unlock(&dev_priv->sb_lock);
-
-	/*
-	 * Leave the power down bit cleared for at least one
-	 * lane so that chv_powergate_phy_ch() will power
-	 * on something when the channel is otherwise unused.
-	 * When the port is off and the override is removed
-	 * the lanes power down anyway, so otherwise it doesn't
-	 * really matter what the state of power down bits is
-	 * after this.
-	 */
-	chv_phy_powergate_lanes(encoder, false, 0x0);
+	chv_phy_post_pll_disable(encoder);
 }
 
 /*
@@ -3089,7 +2878,7 @@ uint8_t
 intel_dp_voltage_max(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = dp_to_dig_port(intel_dp)->port;
 
 	if (IS_BROXTON(dev))
@@ -3178,16 +2967,10 @@ intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
 
 static uint32_t vlv_signal_levels(struct intel_dp *intel_dp)
 {
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(dport->base.base.crtc);
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
 	unsigned long demph_reg_value, preemph_reg_value,
 		uniqtranscale_reg_value;
 	uint8_t train_set = intel_dp->train_set[0];
-	enum dpio_channel port = vlv_dport_to_channel(dport);
-	int pipe = intel_crtc->pipe;
 
 	switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) {
 	case DP_TRAIN_PRE_EMPH_LEVEL_0:
@@ -3262,37 +3045,18 @@ static uint32_t vlv_signal_levels(struct intel_dp *intel_dp)
 		return 0;
 	}
 
-	mutex_lock(&dev_priv->sb_lock);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), 0x00000000);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW4(port), demph_reg_value);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW2(port),
-			 uniqtranscale_reg_value);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW3(port), 0x0C782040);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW11(port), 0x00030000);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW9(port), preemph_reg_value);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), 0x80000000);
-	mutex_unlock(&dev_priv->sb_lock);
+	vlv_set_phy_signal_level(encoder, demph_reg_value, preemph_reg_value,
+				 uniqtranscale_reg_value, 0);
 
 	return 0;
 }
 
-static bool chv_need_uniq_trans_scale(uint8_t train_set)
-{
-	return (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) == DP_TRAIN_PRE_EMPH_LEVEL_0 &&
-		(train_set & DP_TRAIN_VOLTAGE_SWING_MASK) == DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
-}
-
 static uint32_t chv_signal_levels(struct intel_dp *intel_dp)
 {
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
-	struct intel_crtc *intel_crtc = to_intel_crtc(dport->base.base.crtc);
-	u32 deemph_reg_value, margin_reg_value, val;
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	u32 deemph_reg_value, margin_reg_value;
+	bool uniq_trans_scale = false;
 	uint8_t train_set = intel_dp->train_set[0];
-	enum dpio_channel ch = vlv_dport_to_channel(dport);
-	enum pipe pipe = intel_crtc->pipe;
-	int i;
 
 	switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) {
 	case DP_TRAIN_PRE_EMPH_LEVEL_0:
@@ -3312,7 +3076,7 @@ static uint32_t chv_signal_levels(struct intel_dp *intel_dp)
 		case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
 			deemph_reg_value = 128;
 			margin_reg_value = 154;
-			/* FIXME extra to set for 1200 */
+			uniq_trans_scale = true;
 			break;
 		default:
 			return 0;
@@ -3364,88 +3128,8 @@ static uint32_t chv_signal_levels(struct intel_dp *intel_dp)
 		return 0;
 	}
 
-	mutex_lock(&dev_priv->sb_lock);
-
-	/* Clear calc init */
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
-	val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
-	val &= ~(DPIO_PCS_TX1DEEMP_MASK | DPIO_PCS_TX2DEEMP_MASK);
-	val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
-
-	if (intel_crtc->config->lane_count > 2) {
-		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
-		val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
-		val &= ~(DPIO_PCS_TX1DEEMP_MASK | DPIO_PCS_TX2DEEMP_MASK);
-		val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5;
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
-	}
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW9(ch));
-	val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK);
-	val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW9(ch), val);
-
-	if (intel_crtc->config->lane_count > 2) {
-		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW9(ch));
-		val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK);
-		val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000;
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW9(ch), val);
-	}
-
-	/* Program swing deemph */
-	for (i = 0; i < intel_crtc->config->lane_count; i++) {
-		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i));
-		val &= ~DPIO_SWING_DEEMPH9P5_MASK;
-		val |= deemph_reg_value << DPIO_SWING_DEEMPH9P5_SHIFT;
-		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW4(ch, i), val);
-	}
-
-	/* Program swing margin */
-	for (i = 0; i < intel_crtc->config->lane_count; i++) {
-		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
-
-		val &= ~DPIO_SWING_MARGIN000_MASK;
-		val |= margin_reg_value << DPIO_SWING_MARGIN000_SHIFT;
-
-		/*
-		 * Supposedly this value shouldn't matter when unique transition
-		 * scale is disabled, but in fact it does matter. Let's just
-		 * always program the same value and hope it's OK.
-		 */
-		val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT);
-		val |= 0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT;
-
-		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
-	}
-
-	/*
-	 * The document said it needs to set bit 27 for ch0 and bit 26
-	 * for ch1. Might be a typo in the doc.
-	 * For now, for this unique transition scale selection, set bit
-	 * 27 for ch0 and ch1.
-	 */
-	for (i = 0; i < intel_crtc->config->lane_count; i++) {
-		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i));
-		if (chv_need_uniq_trans_scale(train_set))
-			val |= DPIO_TX_UNIQ_TRANS_SCALE_EN;
-		else
-			val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN;
-		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val);
-	}
-
-	/* Start swing calculation */
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
-	val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
-
-	if (intel_crtc->config->lane_count > 2) {
-		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
-		val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
-	}
-
-	mutex_unlock(&dev_priv->sb_lock);
+	chv_set_phy_signal_level(encoder, deemph_reg_value,
+				 margin_reg_value, uniq_trans_scale);
 
 	return 0;
 }
@@ -3612,7 +3296,7 @@ void intel_dp_set_idle_link_train(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_dig_port->port;
 	uint32_t val;
 
@@ -3634,8 +3318,10 @@ void intel_dp_set_idle_link_train(struct intel_dp *intel_dp)
 	if (port == PORT_A)
 		return;
 
-	if (wait_for((I915_READ(DP_TP_STATUS(port)) & DP_TP_STATUS_IDLE_DONE),
-		     1))
+	if (intel_wait_for_register(dev_priv,DP_TP_STATUS(port),
+				    DP_TP_STATUS_IDLE_DONE,
+				    DP_TP_STATUS_IDLE_DONE,
+				    1))
 		DRM_ERROR("Timed out waiting for DP idle patterns\n");
 }
 
@@ -3646,7 +3332,7 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 	struct intel_crtc *crtc = to_intel_crtc(intel_dig_port->base.base.crtc);
 	enum port port = intel_dig_port->port;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t DP = intel_dp->DP;
 
 	if (WARN_ON(HAS_DDI(dev)))
@@ -3698,7 +3384,7 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 		I915_WRITE(intel_dp->output_reg, DP);
 		POSTING_READ(intel_dp->output_reg);
 
-		intel_wait_for_vblank_if_active(dev_priv->dev, PIPE_A);
+		intel_wait_for_vblank_if_active(&dev_priv->drm, PIPE_A);
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, PIPE_A, true);
 		intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, true);
 	}
@@ -3713,8 +3399,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint8_t rev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (drm_dp_dpcd_read(&intel_dp->aux, 0x000, intel_dp->dpcd,
 			     sizeof(intel_dp->dpcd)) < 0)
@@ -3771,6 +3456,15 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 			DRM_DEBUG_KMS("PSR2 %s on sink",
 				dev_priv->psr.psr2_support ? "supported" : "not supported");
 		}
+
+		/* Read the eDP Display control capabilities registers */
+		memset(intel_dp->edp_dpcd, 0, sizeof(intel_dp->edp_dpcd));
+		if ((intel_dp->dpcd[DP_EDP_CONFIGURATION_CAP] & DP_DPCD_DISPLAY_CONTROL_CAPABLE) &&
+				(drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_DPCD_REV,
+						intel_dp->edp_dpcd, sizeof(intel_dp->edp_dpcd)) ==
+								sizeof(intel_dp->edp_dpcd)))
+			DRM_DEBUG_KMS("EDP DPCD : %*ph\n", (int) sizeof(intel_dp->edp_dpcd),
+					intel_dp->edp_dpcd);
 	}
 
 	DRM_DEBUG_KMS("Display Port TPS3 support: source %s, sink %s\n",
@@ -3778,10 +3472,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 		      yesno(drm_dp_tps3_supported(intel_dp->dpcd)));
 
 	/* Intermediate frequency support */
-	if (is_edp(intel_dp) &&
-	    (intel_dp->dpcd[DP_EDP_CONFIGURATION_CAP] &	DP_DPCD_DISPLAY_CONTROL_CAPABLE) &&
-	    (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_DPCD_REV, &rev, 1) == 1) &&
-	    (rev >= 0x03)) { /* eDp v1.4 or higher */
+	if (is_edp(intel_dp) && (intel_dp->edp_dpcd[0] >= 0x03)) { /* eDp v1.4 or higher */
 		__le16 sink_rates[DP_MAX_SUPPORTED_RATES];
 		int i;
 
@@ -4559,7 +4250,7 @@ intel_dp_long_pulse(struct intel_connector *intel_connector)
 	}
 
 	if (intel_encoder->type != INTEL_OUTPUT_EDP)
-		intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
+		intel_encoder->type = INTEL_OUTPUT_DP;
 
 	intel_dp_probe_oui(intel_dp);
 
@@ -4635,7 +4326,7 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 		/* MST devices are disconnected from a monitor POV */
 		intel_dp_unset_edid(intel_dp);
 		if (intel_encoder->type != INTEL_OUTPUT_EDP)
-			intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
+			intel_encoder->type = INTEL_OUTPUT_DP;
 		return connector_status_disconnected;
 	}
 
@@ -4674,7 +4365,7 @@ intel_dp_force(struct drm_connector *connector)
 	intel_display_power_put(dev_priv, power_domain);
 
 	if (intel_encoder->type != INTEL_OUTPUT_EDP)
-		intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
+		intel_encoder->type = INTEL_OUTPUT_DP;
 }
 
 static int intel_dp_get_modes(struct drm_connector *connector)
@@ -4723,7 +4414,7 @@ intel_dp_set_property(struct drm_connector *connector,
 		      struct drm_property *property,
 		      uint64_t val)
 {
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct intel_encoder *intel_encoder = intel_attached_encoder(connector);
 	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base);
@@ -4811,6 +4502,32 @@ done:
 	return 0;
 }
 
+static int
+intel_dp_connector_register(struct drm_connector *connector)
+{
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	int ret;
+
+	ret = intel_connector_register(connector);
+	if (ret)
+		return ret;
+
+	i915_debugfs_connector_add(connector);
+
+	DRM_DEBUG_KMS("registering %s bus for %s\n",
+		      intel_dp->aux.name, connector->kdev->kobj.name);
+
+	intel_dp->aux.dev = connector->kdev;
+	return drm_dp_aux_register(&intel_dp->aux);
+}
+
+static void
+intel_dp_connector_unregister(struct drm_connector *connector)
+{
+	drm_dp_aux_unregister(&intel_attached_dp(connector)->aux);
+	intel_connector_unregister(connector);
+}
+
 static void
 intel_dp_connector_destroy(struct drm_connector *connector)
 {
@@ -4851,6 +4568,9 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 			intel_dp->edp_notifier.notifier_call = NULL;
 		}
 	}
+
+	intel_dp_aux_fini(intel_dp);
+
 	drm_encoder_cleanup(encoder);
 	kfree(intel_dig_port);
 }
@@ -4876,7 +4596,7 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
@@ -4929,6 +4649,8 @@ static const struct drm_connector_funcs intel_dp_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = intel_dp_set_property,
 	.atomic_get_property = intel_connector_atomic_get_property,
+	.late_register = intel_dp_connector_register,
+	.early_unregister = intel_dp_connector_unregister,
 	.destroy = intel_dp_connector_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
@@ -4937,7 +4659,6 @@ static const struct drm_connector_funcs intel_dp_connector_funcs = {
 static const struct drm_connector_helper_funcs intel_dp_connector_helper_funcs = {
 	.get_modes = intel_dp_get_modes,
 	.mode_valid = intel_dp_mode_valid,
-	.best_encoder = intel_best_encoder,
 };
 
 static const struct drm_encoder_funcs intel_dp_enc_funcs = {
@@ -4951,13 +4672,13 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
 	enum irqreturn ret = IRQ_NONE;
 
 	if (intel_dig_port->base.type != INTEL_OUTPUT_EDP &&
 	    intel_dig_port->base.type != INTEL_OUTPUT_HDMI)
-		intel_dig_port->base.type = INTEL_OUTPUT_DISPLAYPORT;
+		intel_dig_port->base.type = INTEL_OUTPUT_DP;
 
 	if (long_hpd && intel_dig_port->base.type == INTEL_OUTPUT_EDP) {
 		/*
@@ -5019,7 +4740,7 @@ put_power:
 /* check the VBT to see whether the eDP is on another port */
 bool intel_dp_is_edp(struct drm_device *dev, enum port port)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/*
 	 * eDP not supported on g4x. so bail out early just
@@ -5061,82 +4782,93 @@ static void intel_dp_init_panel_power_timestamps(struct intel_dp *intel_dp)
 }
 
 static void
-intel_dp_init_panel_power_sequencer(struct drm_device *dev,
-				    struct intel_dp *intel_dp)
+intel_pps_readout_hw_state(struct drm_i915_private *dev_priv,
+			   struct intel_dp *intel_dp, struct edp_power_seq *seq)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct edp_power_seq cur, vbt, spec,
-		*final = &intel_dp->pps_delays;
 	u32 pp_on, pp_off, pp_div = 0, pp_ctl = 0;
-	i915_reg_t pp_ctrl_reg, pp_on_reg, pp_off_reg, pp_div_reg;
-
-	lockdep_assert_held(&dev_priv->pps_mutex);
-
-	/* already initialized? */
-	if (final->t11_t12 != 0)
-		return;
-
-	if (IS_BROXTON(dev)) {
-		/*
-		 * TODO: BXT has 2 sets of PPS registers.
-		 * Correct Register for Broxton need to be identified
-		 * using VBT. hardcoding for now
-		 */
-		pp_ctrl_reg = BXT_PP_CONTROL(0);
-		pp_on_reg = BXT_PP_ON_DELAYS(0);
-		pp_off_reg = BXT_PP_OFF_DELAYS(0);
-	} else if (HAS_PCH_SPLIT(dev)) {
-		pp_ctrl_reg = PCH_PP_CONTROL;
-		pp_on_reg = PCH_PP_ON_DELAYS;
-		pp_off_reg = PCH_PP_OFF_DELAYS;
-		pp_div_reg = PCH_PP_DIVISOR;
-	} else {
-		enum pipe pipe = vlv_power_sequencer_pipe(intel_dp);
+	struct pps_registers regs;
 
-		pp_ctrl_reg = VLV_PIPE_PP_CONTROL(pipe);
-		pp_on_reg = VLV_PIPE_PP_ON_DELAYS(pipe);
-		pp_off_reg = VLV_PIPE_PP_OFF_DELAYS(pipe);
-		pp_div_reg = VLV_PIPE_PP_DIVISOR(pipe);
-	}
+	intel_pps_get_registers(dev_priv, intel_dp, &regs);
 
 	/* Workaround: Need to write PP_CONTROL with the unlock key as
 	 * the very first thing. */
 	pp_ctl = ironlake_get_pp_control(intel_dp);
 
-	pp_on = I915_READ(pp_on_reg);
-	pp_off = I915_READ(pp_off_reg);
-	if (!IS_BROXTON(dev)) {
-		I915_WRITE(pp_ctrl_reg, pp_ctl);
-		pp_div = I915_READ(pp_div_reg);
+	pp_on = I915_READ(regs.pp_on);
+	pp_off = I915_READ(regs.pp_off);
+	if (!IS_BROXTON(dev_priv)) {
+		I915_WRITE(regs.pp_ctrl, pp_ctl);
+		pp_div = I915_READ(regs.pp_div);
 	}
 
 	/* Pull timing values out of registers */
-	cur.t1_t3 = (pp_on & PANEL_POWER_UP_DELAY_MASK) >>
-		PANEL_POWER_UP_DELAY_SHIFT;
+	seq->t1_t3 = (pp_on & PANEL_POWER_UP_DELAY_MASK) >>
+		     PANEL_POWER_UP_DELAY_SHIFT;
 
-	cur.t8 = (pp_on & PANEL_LIGHT_ON_DELAY_MASK) >>
-		PANEL_LIGHT_ON_DELAY_SHIFT;
+	seq->t8 = (pp_on & PANEL_LIGHT_ON_DELAY_MASK) >>
+		  PANEL_LIGHT_ON_DELAY_SHIFT;
 
-	cur.t9 = (pp_off & PANEL_LIGHT_OFF_DELAY_MASK) >>
-		PANEL_LIGHT_OFF_DELAY_SHIFT;
+	seq->t9 = (pp_off & PANEL_LIGHT_OFF_DELAY_MASK) >>
+		  PANEL_LIGHT_OFF_DELAY_SHIFT;
 
-	cur.t10 = (pp_off & PANEL_POWER_DOWN_DELAY_MASK) >>
-		PANEL_POWER_DOWN_DELAY_SHIFT;
+	seq->t10 = (pp_off & PANEL_POWER_DOWN_DELAY_MASK) >>
+		   PANEL_POWER_DOWN_DELAY_SHIFT;
 
-	if (IS_BROXTON(dev)) {
+	if (IS_BROXTON(dev_priv)) {
 		u16 tmp = (pp_ctl & BXT_POWER_CYCLE_DELAY_MASK) >>
 			BXT_POWER_CYCLE_DELAY_SHIFT;
 		if (tmp > 0)
-			cur.t11_t12 = (tmp - 1) * 1000;
+			seq->t11_t12 = (tmp - 1) * 1000;
 		else
-			cur.t11_t12 = 0;
+			seq->t11_t12 = 0;
 	} else {
-		cur.t11_t12 = ((pp_div & PANEL_POWER_CYCLE_DELAY_MASK) >>
+		seq->t11_t12 = ((pp_div & PANEL_POWER_CYCLE_DELAY_MASK) >>
 		       PANEL_POWER_CYCLE_DELAY_SHIFT) * 1000;
 	}
+}
+
+static void
+intel_pps_dump_state(const char *state_name, const struct edp_power_seq *seq)
+{
+	DRM_DEBUG_KMS("%s t1_t3 %d t8 %d t9 %d t10 %d t11_t12 %d\n",
+		      state_name,
+		      seq->t1_t3, seq->t8, seq->t9, seq->t10, seq->t11_t12);
+}
+
+static void
+intel_pps_verify_state(struct drm_i915_private *dev_priv,
+		       struct intel_dp *intel_dp)
+{
+	struct edp_power_seq hw;
+	struct edp_power_seq *sw = &intel_dp->pps_delays;
+
+	intel_pps_readout_hw_state(dev_priv, intel_dp, &hw);
+
+	if (hw.t1_t3 != sw->t1_t3 || hw.t8 != sw->t8 || hw.t9 != sw->t9 ||
+	    hw.t10 != sw->t10 || hw.t11_t12 != sw->t11_t12) {
+		DRM_ERROR("PPS state mismatch\n");
+		intel_pps_dump_state("sw", sw);
+		intel_pps_dump_state("hw", &hw);
+	}
+}
+
+static void
+intel_dp_init_panel_power_sequencer(struct drm_device *dev,
+				    struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct edp_power_seq cur, vbt, spec,
+		*final = &intel_dp->pps_delays;
+
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
+	/* already initialized? */
+	if (final->t11_t12 != 0)
+		return;
 
-	DRM_DEBUG_KMS("cur t1_t3 %d t8 %d t9 %d t10 %d t11_t12 %d\n",
-		      cur.t1_t3, cur.t8, cur.t9, cur.t10, cur.t11_t12);
+	intel_pps_readout_hw_state(dev_priv, intel_dp, &cur);
+
+	intel_pps_dump_state("cur", &cur);
 
 	vbt = dev_priv->vbt.edp.pps;
 
@@ -5152,8 +4884,7 @@ intel_dp_init_panel_power_sequencer(struct drm_device *dev,
 	 * too. */
 	spec.t11_t12 = (510 + 100) * 10;
 
-	DRM_DEBUG_KMS("vbt t1_t3 %d t8 %d t9 %d t10 %d t11_t12 %d\n",
-		      vbt.t1_t3, vbt.t8, vbt.t9, vbt.t10, vbt.t11_t12);
+	intel_pps_dump_state("vbt", &vbt);
 
 	/* Use the max of the register settings and vbt. If both are
 	 * unset, fall back to the spec limits. */
@@ -5181,59 +4912,41 @@ intel_dp_init_panel_power_sequencer(struct drm_device *dev,
 
 	DRM_DEBUG_KMS("backlight on delay %d, off delay %d\n",
 		      intel_dp->backlight_on_delay, intel_dp->backlight_off_delay);
+
+	/*
+	 * We override the HW backlight delays to 1 because we do manual waits
+	 * on them. For T8, even BSpec recommends doing it. For T9, if we
+	 * don't do this, we'll end up waiting for the backlight off delay
+	 * twice: once when we do the manual sleep, and once when we disable
+	 * the panel and wait for the PP_STATUS bit to become zero.
+	 */
+	final->t8 = 1;
+	final->t9 = 1;
 }
 
 static void
 intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
 					      struct intel_dp *intel_dp)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 pp_on, pp_off, pp_div, port_sel = 0;
 	int div = dev_priv->rawclk_freq / 1000;
-	i915_reg_t pp_on_reg, pp_off_reg, pp_div_reg, pp_ctrl_reg;
+	struct pps_registers regs;
 	enum port port = dp_to_dig_port(intel_dp)->port;
 	const struct edp_power_seq *seq = &intel_dp->pps_delays;
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
-	if (IS_BROXTON(dev)) {
-		/*
-		 * TODO: BXT has 2 sets of PPS registers.
-		 * Correct Register for Broxton need to be identified
-		 * using VBT. hardcoding for now
-		 */
-		pp_ctrl_reg = BXT_PP_CONTROL(0);
-		pp_on_reg = BXT_PP_ON_DELAYS(0);
-		pp_off_reg = BXT_PP_OFF_DELAYS(0);
-
-	} else if (HAS_PCH_SPLIT(dev)) {
-		pp_on_reg = PCH_PP_ON_DELAYS;
-		pp_off_reg = PCH_PP_OFF_DELAYS;
-		pp_div_reg = PCH_PP_DIVISOR;
-	} else {
-		enum pipe pipe = vlv_power_sequencer_pipe(intel_dp);
+	intel_pps_get_registers(dev_priv, intel_dp, &regs);
 
-		pp_on_reg = VLV_PIPE_PP_ON_DELAYS(pipe);
-		pp_off_reg = VLV_PIPE_PP_OFF_DELAYS(pipe);
-		pp_div_reg = VLV_PIPE_PP_DIVISOR(pipe);
-	}
-
-	/*
-	 * And finally store the new values in the power sequencer. The
-	 * backlight delays are set to 1 because we do manual waits on them. For
-	 * T8, even BSpec recommends doing it. For T9, if we don't do this,
-	 * we'll end up waiting for the backlight off delay twice: once when we
-	 * do the manual sleep, and once when we disable the panel and wait for
-	 * the PP_STATUS bit to become zero.
-	 */
 	pp_on = (seq->t1_t3 << PANEL_POWER_UP_DELAY_SHIFT) |
-		(1 << PANEL_LIGHT_ON_DELAY_SHIFT);
-	pp_off = (1 << PANEL_LIGHT_OFF_DELAY_SHIFT) |
+		(seq->t8 << PANEL_LIGHT_ON_DELAY_SHIFT);
+	pp_off = (seq->t9 << PANEL_LIGHT_OFF_DELAY_SHIFT) |
 		 (seq->t10 << PANEL_POWER_DOWN_DELAY_SHIFT);
 	/* Compute the divisor for the pp clock, simply match the Bspec
 	 * formula. */
 	if (IS_BROXTON(dev)) {
-		pp_div = I915_READ(pp_ctrl_reg);
+		pp_div = I915_READ(regs.pp_ctrl);
 		pp_div &= ~BXT_POWER_CYCLE_DELAY_MASK;
 		pp_div |= (DIV_ROUND_UP((seq->t11_t12 + 1), 1000)
 				<< BXT_POWER_CYCLE_DELAY_SHIFT);
@@ -5256,19 +4969,19 @@ intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
 
 	pp_on |= port_sel;
 
-	I915_WRITE(pp_on_reg, pp_on);
-	I915_WRITE(pp_off_reg, pp_off);
+	I915_WRITE(regs.pp_on, pp_on);
+	I915_WRITE(regs.pp_off, pp_off);
 	if (IS_BROXTON(dev))
-		I915_WRITE(pp_ctrl_reg, pp_div);
+		I915_WRITE(regs.pp_ctrl, pp_div);
 	else
-		I915_WRITE(pp_div_reg, pp_div);
+		I915_WRITE(regs.pp_div, pp_div);
 
 	DRM_DEBUG_KMS("panel power sequencer register settings: PP_ON %#x, PP_OFF %#x, PP_DIV %#x\n",
-		      I915_READ(pp_on_reg),
-		      I915_READ(pp_off_reg),
+		      I915_READ(regs.pp_on),
+		      I915_READ(regs.pp_off),
 		      IS_BROXTON(dev) ?
-		      (I915_READ(pp_ctrl_reg) & BXT_POWER_CYCLE_DELAY_MASK) :
-		      I915_READ(pp_div_reg));
+		      (I915_READ(regs.pp_ctrl) & BXT_POWER_CYCLE_DELAY_MASK) :
+		      I915_READ(regs.pp_div));
 }
 
 /**
@@ -5285,7 +4998,7 @@ intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
  */
 static void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *encoder;
 	struct intel_digital_port *dig_port = NULL;
 	struct intel_dp *intel_dp = dev_priv->drrs.dp;
@@ -5384,7 +5097,7 @@ static void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate)
 void intel_edp_drrs_enable(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_crtc *crtc = dig_port->base.base.crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -5416,7 +5129,7 @@ unlock:
 void intel_edp_drrs_disable(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_crtc *crtc = dig_port->base.base.crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -5431,9 +5144,9 @@ void intel_edp_drrs_disable(struct intel_dp *intel_dp)
 	}
 
 	if (dev_priv->drrs.refresh_rate_type == DRRS_LOW_RR)
-		intel_dp_set_drrs_state(dev_priv->dev,
-			intel_dp->attached_connector->panel.
-			fixed_mode->vrefresh);
+		intel_dp_set_drrs_state(&dev_priv->drm,
+					intel_dp->attached_connector->panel.
+					fixed_mode->vrefresh);
 
 	dev_priv->drrs.dp = NULL;
 	mutex_unlock(&dev_priv->drrs.mutex);
@@ -5463,9 +5176,9 @@ static void intel_edp_drrs_downclock_work(struct work_struct *work)
 		goto unlock;
 
 	if (dev_priv->drrs.refresh_rate_type != DRRS_LOW_RR)
-		intel_dp_set_drrs_state(dev_priv->dev,
-			intel_dp->attached_connector->panel.
-			downclock_mode->vrefresh);
+		intel_dp_set_drrs_state(&dev_priv->drm,
+					intel_dp->attached_connector->panel.
+					downclock_mode->vrefresh);
 
 unlock:
 	mutex_unlock(&dev_priv->drrs.mutex);
@@ -5484,7 +5197,7 @@ unlock:
 void intel_edp_drrs_invalidate(struct drm_device *dev,
 		unsigned frontbuffer_bits)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc;
 	enum pipe pipe;
 
@@ -5507,9 +5220,9 @@ void intel_edp_drrs_invalidate(struct drm_device *dev,
 
 	/* invalidate means busy screen hence upclock */
 	if (frontbuffer_bits && dev_priv->drrs.refresh_rate_type == DRRS_LOW_RR)
-		intel_dp_set_drrs_state(dev_priv->dev,
-				dev_priv->drrs.dp->attached_connector->panel.
-				fixed_mode->vrefresh);
+		intel_dp_set_drrs_state(&dev_priv->drm,
+					dev_priv->drrs.dp->attached_connector->panel.
+					fixed_mode->vrefresh);
 
 	mutex_unlock(&dev_priv->drrs.mutex);
 }
@@ -5529,7 +5242,7 @@ void intel_edp_drrs_invalidate(struct drm_device *dev,
 void intel_edp_drrs_flush(struct drm_device *dev,
 		unsigned frontbuffer_bits)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc;
 	enum pipe pipe;
 
@@ -5552,9 +5265,9 @@ void intel_edp_drrs_flush(struct drm_device *dev,
 
 	/* flush means busy screen hence upclock */
 	if (frontbuffer_bits && dev_priv->drrs.refresh_rate_type == DRRS_LOW_RR)
-		intel_dp_set_drrs_state(dev_priv->dev,
-				dev_priv->drrs.dp->attached_connector->panel.
-				fixed_mode->vrefresh);
+		intel_dp_set_drrs_state(&dev_priv->drm,
+					dev_priv->drrs.dp->attached_connector->panel.
+					fixed_mode->vrefresh);
 
 	/*
 	 * flush also means no more activity hence schedule downclock, if all
@@ -5589,14 +5302,14 @@ void intel_edp_drrs_flush(struct drm_device *dev,
  *
  * DRRS saves power by switching to low RR based on usage scenarios.
  *
- * eDP DRRS:-
- *        The implementation is based on frontbuffer tracking implementation.
- * When there is a disturbance on the screen triggered by user activity or a
- * periodic system activity, DRRS is disabled (RR is changed to high RR).
- * When there is no movement on screen, after a timeout of 1 second, a switch
- * to low RR is made.
- *        For integration with frontbuffer tracking code,
- * intel_edp_drrs_invalidate() and intel_edp_drrs_flush() are called.
+ * The implementation is based on frontbuffer tracking implementation.  When
+ * there is a disturbance on the screen triggered by user activity or a periodic
+ * system activity, DRRS is disabled (RR is changed to high RR).  When there is
+ * no movement on screen, after a timeout of 1 second, a switch to low RR is
+ * made.
+ *
+ * For integration with frontbuffer tracking code, intel_edp_drrs_invalidate()
+ * and intel_edp_drrs_flush() are called.
  *
  * DRRS can be further extended to support other internal panels and also
  * the scenario of video playback wherein RR is set based on the rate
@@ -5622,7 +5335,7 @@ intel_dp_drrs_init(struct intel_connector *intel_connector,
 {
 	struct drm_connector *connector = &intel_connector->base;
 	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_display_mode *downclock_mode = NULL;
 
 	INIT_DELAYED_WORK(&dev_priv->drrs.work, intel_edp_drrs_downclock_work);
@@ -5660,7 +5373,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_device *dev = intel_encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_display_mode *fixed_mode = NULL;
 	struct drm_display_mode *downclock_mode = NULL;
 	bool has_dpcd;
@@ -5671,8 +5384,32 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	if (!is_edp(intel_dp))
 		return true;
 
+	/*
+	 * On IBX/CPT we may get here with LVDS already registered. Since the
+	 * driver uses the only internal power sequencer available for both
+	 * eDP and LVDS bail out early in this case to prevent interfering
+	 * with an already powered-on LVDS power sequencer.
+	 */
+	if (intel_get_lvds_encoder(dev)) {
+		WARN_ON(!(HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv)));
+		DRM_INFO("LVDS was detected, not registering eDP\n");
+
+		return false;
+	}
+
 	pps_lock(intel_dp);
+
+	intel_dp_init_panel_power_timestamps(intel_dp);
+
+	if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
+		vlv_initial_power_sequencer_setup(intel_dp);
+	} else {
+		intel_dp_init_panel_power_sequencer(dev, intel_dp);
+		intel_dp_init_panel_power_sequencer_registers(dev, intel_dp);
+	}
+
 	intel_edp_panel_vdd_sanitize(intel_dp);
+
 	pps_unlock(intel_dp);
 
 	/* Cache DPCD and EDID for edp. */
@@ -5686,14 +5423,9 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	} else {
 		/* if this fails, presume the device is a ghost */
 		DRM_INFO("failed to retrieve link info, disabling eDP\n");
-		return false;
+		goto out_vdd_off;
 	}
 
-	/* We now know it's not a ghost, init power sequence regs. */
-	pps_lock(intel_dp);
-	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp);
-	pps_unlock(intel_dp);
-
 	mutex_lock(&dev->mode_config.mutex);
 	edid = drm_get_edid(connector, &intel_dp->aux.ddc);
 	if (edid) {
@@ -5761,6 +5493,18 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	intel_panel_setup_backlight(connector, pipe);
 
 	return true;
+
+out_vdd_off:
+	cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
+	/*
+	 * vdd might still be enabled do to the delayed vdd off.
+	 * Make sure vdd is actually turned off here.
+	 */
+	pps_lock(intel_dp);
+	edp_panel_vdd_off_sync(intel_dp);
+	pps_unlock(intel_dp);
+
+	return false;
 }
 
 bool
@@ -5771,9 +5515,9 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_device *dev = intel_encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_dig_port->port;
-	int type, ret;
+	int type;
 
 	if (WARN(intel_dig_port->max_lanes < 1,
 		 "Not enough lanes (%d) for DP on port %c\n",
@@ -5832,17 +5576,17 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	connector->interlace_allowed = true;
 	connector->doublescan_allowed = 0;
 
+	intel_dp_aux_init(intel_dp, intel_connector);
+
 	INIT_DELAYED_WORK(&intel_dp->panel_vdd_work,
 			  edp_panel_vdd_work);
 
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
-	drm_connector_register(connector);
 
 	if (HAS_DDI(dev))
 		intel_connector->get_hw_state = intel_ddi_connector_get_hw_state;
 	else
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
-	intel_connector->unregister = intel_dp_connector_unregister;
 
 	/* Set up the hotplug pin. */
 	switch (port) {
@@ -5867,22 +5611,8 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 		BUG();
 	}
 
-	if (is_edp(intel_dp)) {
-		pps_lock(intel_dp);
-		intel_dp_init_panel_power_timestamps(intel_dp);
-		if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))
-			vlv_initial_power_sequencer_setup(intel_dp);
-		else
-			intel_dp_init_panel_power_sequencer(dev, intel_dp);
-		pps_unlock(intel_dp);
-	}
-
-	ret = intel_dp_aux_init(intel_dp, intel_connector);
-	if (ret)
-		goto fail;
-
 	/* init MST on ports that can support it */
-	if (HAS_DP_MST(dev) &&
+	if (HAS_DP_MST(dev) && !is_edp(intel_dp) &&
 	    (port == PORT_B || port == PORT_C || port == PORT_D))
 		intel_dp_mst_encoder_init(intel_dig_port,
 					  intel_connector->base.base.id);
@@ -5904,22 +5634,9 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 		I915_WRITE(PEG_BAND_GAP_DATA, (temp & ~0xf) | 0xd);
 	}
 
-	i915_debugfs_connector_add(connector);
-
 	return true;
 
 fail:
-	if (is_edp(intel_dp)) {
-		cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
-		/*
-		 * vdd might still be enabled do to the delayed vdd off.
-		 * Make sure vdd is actually turned off here.
-		 */
-		pps_lock(intel_dp);
-		edp_panel_vdd_off_sync(intel_dp);
-		pps_unlock(intel_dp);
-	}
-	drm_connector_unregister(connector);
 	drm_connector_cleanup(connector);
 
 	return false;
@@ -5929,7 +5646,7 @@ bool intel_dp_init(struct drm_device *dev,
 		   i915_reg_t output_reg,
 		   enum port port)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_digital_port *intel_dig_port;
 	struct intel_encoder *intel_encoder;
 	struct drm_encoder *encoder;
@@ -5947,7 +5664,7 @@ bool intel_dp_init(struct drm_device *dev,
 	encoder = &intel_encoder->base;
 
 	if (drm_encoder_init(dev, &intel_encoder->base, &intel_dp_enc_funcs,
-			     DRM_MODE_ENCODER_TMDS, NULL))
+			     DRM_MODE_ENCODER_TMDS, "DP %c", port_name(port)))
 		goto err_encoder_init;
 
 	intel_encoder->compute_config = intel_dp_compute_config;
@@ -5977,7 +5694,7 @@ bool intel_dp_init(struct drm_device *dev,
 	intel_dig_port->dp.output_reg = output_reg;
 	intel_dig_port->max_lanes = 4;
 
-	intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
+	intel_encoder->type = INTEL_OUTPUT_DP;
 	if (IS_CHERRYVIEW(dev)) {
 		if (port == PORT_D)
 			intel_encoder->crtc_mask = 1 << 2;
@@ -6007,43 +5724,35 @@ err_connector_alloc:
 
 void intel_dp_mst_suspend(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
 	/* disable MST */
 	for (i = 0; i < I915_MAX_PORTS; i++) {
 		struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i];
-		if (!intel_dig_port)
+
+		if (!intel_dig_port || !intel_dig_port->dp.can_mst)
 			continue;
 
-		if (intel_dig_port->base.type == INTEL_OUTPUT_DISPLAYPORT) {
-			if (!intel_dig_port->dp.can_mst)
-				continue;
-			if (intel_dig_port->dp.is_mst)
-				drm_dp_mst_topology_mgr_suspend(&intel_dig_port->dp.mst_mgr);
-		}
+		if (intel_dig_port->dp.is_mst)
+			drm_dp_mst_topology_mgr_suspend(&intel_dig_port->dp.mst_mgr);
 	}
 }
 
 void intel_dp_mst_resume(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
 	for (i = 0; i < I915_MAX_PORTS; i++) {
 		struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i];
-		if (!intel_dig_port)
-			continue;
-		if (intel_dig_port->base.type == INTEL_OUTPUT_DISPLAYPORT) {
-			int ret;
+		int ret;
 
-			if (!intel_dig_port->dp.can_mst)
-				continue;
+		if (!intel_dig_port || !intel_dig_port->dp.can_mst)
+			continue;
 
-			ret = drm_dp_mst_topology_mgr_resume(&intel_dig_port->dp.mst_mgr);
-			if (ret != 0) {
-				intel_dp_check_mst_status(&intel_dig_port->dp);
-			}
-		}
+		ret = drm_dp_mst_topology_mgr_resume(&intel_dig_port->dp.mst_mgr);
+		if (ret)
+			intel_dp_check_mst_status(&intel_dig_port->dp);
 	}
 }
diff --git a/drivers/gpu/drm/i915/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/intel_dp_aux_backlight.c
new file mode 100644
index 000000000000..6532e226db29
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_dp_aux_backlight.c
@@ -0,0 +1,172 @@
+/*
+ * Copyright © 2015 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#include "intel_drv.h"
+
+static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
+{
+	uint8_t reg_val = 0;
+
+	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER,
+			      &reg_val) < 0) {
+		DRM_DEBUG_KMS("Failed to read DPCD register 0x%x\n",
+			      DP_EDP_DISPLAY_CONTROL_REGISTER);
+		return;
+	}
+	if (enable)
+		reg_val |= DP_EDP_BACKLIGHT_ENABLE;
+	else
+		reg_val &= ~(DP_EDP_BACKLIGHT_ENABLE);
+
+	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER,
+			       reg_val) != 1) {
+		DRM_DEBUG_KMS("Failed to %s aux backlight\n",
+			      enable ? "enable" : "disable");
+	}
+}
+
+/*
+ * Read the current backlight value from DPCD register(s) based
+ * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported
+ */
+static uint32_t intel_dp_aux_get_backlight(struct intel_connector *connector)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	uint8_t read_val[2] = { 0x0 };
+	uint16_t level = 0;
+
+	if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB,
+			     &read_val, sizeof(read_val)) < 0) {
+		DRM_DEBUG_KMS("Failed to read DPCD register 0x%x\n",
+			      DP_EDP_BACKLIGHT_BRIGHTNESS_MSB);
+		return 0;
+	}
+	level = read_val[0];
+	if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT)
+		level = (read_val[0] << 8 | read_val[1]);
+
+	return level;
+}
+
+/*
+ * Sends the current backlight level over the aux channel, checking if its using
+ * 8-bit or 16 bit value (MSB and LSB)
+ */
+static void
+intel_dp_aux_set_backlight(struct intel_connector *connector, u32 level)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	uint8_t vals[2] = { 0x0 };
+
+	vals[0] = level;
+
+	/* Write the MSB and/or LSB */
+	if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT) {
+		vals[0] = (level & 0xFF00) >> 8;
+		vals[1] = (level & 0xFF);
+	}
+	if (drm_dp_dpcd_write(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB,
+			      vals, sizeof(vals)) < 0) {
+		DRM_DEBUG_KMS("Failed to write aux backlight level\n");
+		return;
+	}
+}
+
+static void intel_dp_aux_enable_backlight(struct intel_connector *connector)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	uint8_t dpcd_buf = 0;
+
+	set_aux_backlight_enable(intel_dp, true);
+
+	if ((drm_dp_dpcd_readb(&intel_dp->aux,
+			       DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf) == 1) &&
+	    ((dpcd_buf & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) ==
+	     DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET))
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER,
+				   (dpcd_buf | DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD));
+}
+
+static void intel_dp_aux_disable_backlight(struct intel_connector *connector)
+{
+	set_aux_backlight_enable(enc_to_intel_dp(&connector->encoder->base), false);
+}
+
+static int intel_dp_aux_setup_backlight(struct intel_connector *connector,
+					enum pipe pipe)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_panel *panel = &connector->panel;
+
+	intel_dp_aux_enable_backlight(connector);
+
+	if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT)
+		panel->backlight.max = 0xFFFF;
+	else
+		panel->backlight.max = 0xFF;
+
+	panel->backlight.min = 0;
+	panel->backlight.level = intel_dp_aux_get_backlight(connector);
+
+	panel->backlight.enabled = panel->backlight.level != 0;
+
+	return 0;
+}
+
+static bool
+intel_dp_aux_display_control_capable(struct intel_connector *connector)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+
+	/* Check the  eDP Display control capabilities registers to determine if
+	 * the panel can support backlight control over the aux channel
+	 */
+	if (intel_dp->edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP &&
+	    (intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP) &&
+	    !((intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_PIN_ENABLE_CAP) ||
+	      (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP))) {
+		DRM_DEBUG_KMS("AUX Backlight Control Supported!\n");
+		return true;
+	}
+	return false;
+}
+
+int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector)
+{
+	struct intel_panel *panel = &intel_connector->panel;
+
+	if (!i915.enable_dpcd_backlight)
+		return -ENODEV;
+
+	if (!intel_dp_aux_display_control_capable(intel_connector))
+		return -ENODEV;
+
+	panel->backlight.setup = intel_dp_aux_setup_backlight;
+	panel->backlight.enable = intel_dp_aux_enable_backlight;
+	panel->backlight.disable = intel_dp_aux_disable_backlight;
+	panel->backlight.set = intel_dp_aux_set_backlight;
+	panel->backlight.get = intel_dp_aux_get_backlight;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 7a34090cef34..68a005d729e9 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -47,7 +47,6 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder,
 
 	pipe_config->dp_encoder_is_mst = true;
 	pipe_config->has_pch_encoder = false;
-	pipe_config->has_dp_encoder = true;
 	bpp = 24;
 	/*
 	 * for MST we always configure max link bw - the spec doesn't
@@ -140,7 +139,7 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder)
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_dig_port->port;
 	int ret;
 	uint32_t temp;
@@ -207,14 +206,17 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder)
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_dig_port->port;
 	int ret;
 
 	DRM_DEBUG_KMS("%d\n", intel_dp->active_mst_links);
 
-	if (wait_for((I915_READ(DP_TP_STATUS(port)) & DP_TP_STATUS_ACT_SENT),
-		     1))
+	if (intel_wait_for_register(dev_priv,
+				    DP_TP_STATUS(port),
+				    DP_TP_STATUS_ACT_SENT,
+				    DP_TP_STATUS_ACT_SENT,
+				    1))
 		DRM_ERROR("Timed out waiting for ACT sent\n");
 
 	ret = drm_dp_check_act_status(&intel_dp->mst_mgr);
@@ -239,12 +241,10 @@ static void intel_dp_mst_enc_get_config(struct intel_encoder *encoder,
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
 	u32 temp, flags = 0;
 
-	pipe_config->has_dp_encoder = true;
-
 	temp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
 	if (temp & TRANS_DDI_PHSYNC)
 		flags |= DRM_MODE_FLAG_PHSYNC;
@@ -336,6 +336,8 @@ static const struct drm_connector_funcs intel_dp_mst_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = intel_dp_mst_set_property,
 	.atomic_get_property = intel_connector_atomic_get_property,
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
 	.destroy = intel_dp_mst_connector_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
@@ -455,7 +457,6 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 	drm_connector_init(dev, connector, &intel_dp_mst_connector_funcs, DRM_MODE_CONNECTOR_DisplayPort);
 	drm_connector_helper_add(connector, &intel_dp_mst_connector_helper_funcs);
 
-	intel_connector->unregister = intel_connector_unregister;
 	intel_connector->get_hw_state = intel_dp_mst_get_hw_state;
 	intel_connector->mst_port = intel_dp;
 	intel_connector->port = port;
@@ -477,9 +478,11 @@ static void intel_dp_register_mst_connector(struct drm_connector *connector)
 {
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct drm_device *dev = connector->dev;
+
 	drm_modeset_lock_all(dev);
 	intel_connector_add_to_fbdev(intel_connector);
 	drm_modeset_unlock_all(dev);
+
 	drm_connector_register(&intel_connector->base);
 }
 
@@ -489,7 +492,7 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct drm_device *dev = connector->dev;
 
-	intel_connector->unregister(intel_connector);
+	drm_connector_unregister(connector);
 
 	/* need to nuke the connector */
 	drm_modeset_lock_all(dev);
@@ -534,7 +537,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	intel_mst->primary = intel_dig_port;
 
 	drm_encoder_init(dev, &intel_encoder->base, &intel_dp_mst_enc_funcs,
-			 DRM_MODE_ENCODER_DPMST, NULL);
+			 DRM_MODE_ENCODER_DPMST, "DP-MST %c", pipe_name(pipe));
 
 	intel_encoder->type = INTEL_OUTPUT_DP_MST;
 	intel_encoder->crtc_mask = 0x7;
diff --git a/drivers/gpu/drm/i915/intel_dpio_phy.c b/drivers/gpu/drm/i915/intel_dpio_phy.c
new file mode 100644
index 000000000000..047f48748944
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_dpio_phy.c
@@ -0,0 +1,470 @@
+/*
+ * Copyright © 2014-2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#include "intel_drv.h"
+
+void chv_set_phy_signal_level(struct intel_encoder *encoder,
+			      u32 deemph_reg_value, u32 margin_reg_value,
+			      bool uniq_trans_scale)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_crtc *intel_crtc = to_intel_crtc(dport->base.base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	enum pipe pipe = intel_crtc->pipe;
+	u32 val;
+	int i;
+
+	mutex_lock(&dev_priv->sb_lock);
+
+	/* Clear calc init */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
+	val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
+	val &= ~(DPIO_PCS_TX1DEEMP_MASK | DPIO_PCS_TX2DEEMP_MASK);
+	val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
+
+	if (intel_crtc->config->lane_count > 2) {
+		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
+		val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
+		val &= ~(DPIO_PCS_TX1DEEMP_MASK | DPIO_PCS_TX2DEEMP_MASK);
+		val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5;
+		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
+	}
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW9(ch));
+	val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK);
+	val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW9(ch), val);
+
+	if (intel_crtc->config->lane_count > 2) {
+		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW9(ch));
+		val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK);
+		val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000;
+		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW9(ch), val);
+	}
+
+	/* Program swing deemph */
+	for (i = 0; i < intel_crtc->config->lane_count; i++) {
+		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i));
+		val &= ~DPIO_SWING_DEEMPH9P5_MASK;
+		val |= deemph_reg_value << DPIO_SWING_DEEMPH9P5_SHIFT;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW4(ch, i), val);
+	}
+
+	/* Program swing margin */
+	for (i = 0; i < intel_crtc->config->lane_count; i++) {
+		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
+
+		val &= ~DPIO_SWING_MARGIN000_MASK;
+		val |= margin_reg_value << DPIO_SWING_MARGIN000_SHIFT;
+
+		/*
+		 * Supposedly this value shouldn't matter when unique transition
+		 * scale is disabled, but in fact it does matter. Let's just
+		 * always program the same value and hope it's OK.
+		 */
+		val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT);
+		val |= 0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT;
+
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
+	}
+
+	/*
+	 * The document said it needs to set bit 27 for ch0 and bit 26
+	 * for ch1. Might be a typo in the doc.
+	 * For now, for this unique transition scale selection, set bit
+	 * 27 for ch0 and ch1.
+	 */
+	for (i = 0; i < intel_crtc->config->lane_count; i++) {
+		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i));
+		if (uniq_trans_scale)
+			val |= DPIO_TX_UNIQ_TRANS_SCALE_EN;
+		else
+			val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val);
+	}
+
+	/* Start swing calculation */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
+	val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
+
+	if (intel_crtc->config->lane_count > 2) {
+		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
+		val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
+		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
+	}
+
+	mutex_unlock(&dev_priv->sb_lock);
+
+}
+
+void chv_data_lane_soft_reset(struct intel_encoder *encoder,
+			      bool reset)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base));
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	enum pipe pipe = crtc->pipe;
+	uint32_t val;
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
+	if (reset)
+		val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+	else
+		val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
+
+	if (crtc->config->lane_count > 2) {
+		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
+		if (reset)
+			val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+		else
+			val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET;
+		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
+	}
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
+	val |= CHV_PCS_REQ_SOFTRESET_EN;
+	if (reset)
+		val &= ~DPIO_PCS_CLK_SOFT_RESET;
+	else
+		val |= DPIO_PCS_CLK_SOFT_RESET;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
+
+	if (crtc->config->lane_count > 2) {
+		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
+		val |= CHV_PCS_REQ_SOFTRESET_EN;
+		if (reset)
+			val &= ~DPIO_PCS_CLK_SOFT_RESET;
+		else
+			val |= DPIO_PCS_CLK_SOFT_RESET;
+		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
+	}
+}
+
+void chv_phy_pre_pll_enable(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	enum pipe pipe = intel_crtc->pipe;
+	unsigned int lane_mask =
+		intel_dp_unused_lane_mask(intel_crtc->config->lane_count);
+	u32 val;
+
+	/*
+	 * Must trick the second common lane into life.
+	 * Otherwise we can't even access the PLL.
+	 */
+	if (ch == DPIO_CH0 && pipe == PIPE_B)
+		dport->release_cl2_override =
+			!chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, true);
+
+	chv_phy_powergate_lanes(encoder, true, lane_mask);
+
+	mutex_lock(&dev_priv->sb_lock);
+
+	/* Assert data lane reset */
+	chv_data_lane_soft_reset(encoder, true);
+
+	/* program left/right clock distribution */
+	if (pipe != PIPE_B) {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
+		val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
+		if (ch == DPIO_CH0)
+			val |= CHV_BUFLEFTENA1_FORCE;
+		if (ch == DPIO_CH1)
+			val |= CHV_BUFRIGHTENA1_FORCE;
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
+	} else {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
+		val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
+		if (ch == DPIO_CH0)
+			val |= CHV_BUFLEFTENA2_FORCE;
+		if (ch == DPIO_CH1)
+			val |= CHV_BUFRIGHTENA2_FORCE;
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
+	}
+
+	/* program clock channel usage */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(ch));
+	val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
+	if (pipe != PIPE_B)
+		val &= ~CHV_PCS_USEDCLKCHANNEL;
+	else
+		val |= CHV_PCS_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW8(ch), val);
+
+	if (intel_crtc->config->lane_count > 2) {
+		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW8(ch));
+		val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
+		if (pipe != PIPE_B)
+			val &= ~CHV_PCS_USEDCLKCHANNEL;
+		else
+			val |= CHV_PCS_USEDCLKCHANNEL;
+		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW8(ch), val);
+	}
+
+	/*
+	 * This a a bit weird since generally CL
+	 * matches the pipe, but here we need to
+	 * pick the CL based on the port.
+	 */
+	val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW19(ch));
+	if (pipe != PIPE_B)
+		val &= ~CHV_CMN_USEDCLKCHANNEL;
+	else
+		val |= CHV_CMN_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW19(ch), val);
+
+	mutex_unlock(&dev_priv->sb_lock);
+}
+
+void chv_phy_pre_encoder_enable(struct intel_encoder *encoder)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	int pipe = intel_crtc->pipe;
+	int data, i, stagger;
+	u32 val;
+
+	mutex_lock(&dev_priv->sb_lock);
+
+	/* allow hardware to manage TX FIFO reset source */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW11(ch));
+	val &= ~DPIO_LANEDESKEW_STRAP_OVRD;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW11(ch), val);
+
+	if (intel_crtc->config->lane_count > 2) {
+		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch));
+		val &= ~DPIO_LANEDESKEW_STRAP_OVRD;
+		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
+	}
+
+	/* Program Tx lane latency optimal setting*/
+	for (i = 0; i < intel_crtc->config->lane_count; i++) {
+		/* Set the upar bit */
+		if (intel_crtc->config->lane_count == 1)
+			data = 0x0;
+		else
+			data = (i == 1) ? 0x0 : 0x1;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i),
+				data << DPIO_UPAR_SHIFT);
+	}
+
+	/* Data lane stagger programming */
+	if (intel_crtc->config->port_clock > 270000)
+		stagger = 0x18;
+	else if (intel_crtc->config->port_clock > 135000)
+		stagger = 0xd;
+	else if (intel_crtc->config->port_clock > 67500)
+		stagger = 0x7;
+	else if (intel_crtc->config->port_clock > 33750)
+		stagger = 0x4;
+	else
+		stagger = 0x2;
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW11(ch));
+	val |= DPIO_TX2_STAGGER_MASK(0x1f);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW11(ch), val);
+
+	if (intel_crtc->config->lane_count > 2) {
+		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch));
+		val |= DPIO_TX2_STAGGER_MASK(0x1f);
+		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
+	}
+
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW12(ch),
+		       DPIO_LANESTAGGER_STRAP(stagger) |
+		       DPIO_LANESTAGGER_STRAP_OVRD |
+		       DPIO_TX1_STAGGER_MASK(0x1f) |
+		       DPIO_TX1_STAGGER_MULT(6) |
+		       DPIO_TX2_STAGGER_MULT(0));
+
+	if (intel_crtc->config->lane_count > 2) {
+		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW12(ch),
+			       DPIO_LANESTAGGER_STRAP(stagger) |
+			       DPIO_LANESTAGGER_STRAP_OVRD |
+			       DPIO_TX1_STAGGER_MASK(0x1f) |
+			       DPIO_TX1_STAGGER_MULT(7) |
+			       DPIO_TX2_STAGGER_MULT(5));
+	}
+
+	/* Deassert data lane reset */
+	chv_data_lane_soft_reset(encoder, false);
+
+	mutex_unlock(&dev_priv->sb_lock);
+}
+
+void chv_phy_release_cl2_override(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (dport->release_cl2_override) {
+		chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, false);
+		dport->release_cl2_override = false;
+	}
+}
+
+void chv_phy_post_pll_disable(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum pipe pipe = to_intel_crtc(encoder->base.crtc)->pipe;
+	u32 val;
+
+	mutex_lock(&dev_priv->sb_lock);
+
+	/* disable left/right clock distribution */
+	if (pipe != PIPE_B) {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
+		val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
+	} else {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
+		val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
+	}
+
+	mutex_unlock(&dev_priv->sb_lock);
+
+	/*
+	 * Leave the power down bit cleared for at least one
+	 * lane so that chv_powergate_phy_ch() will power
+	 * on something when the channel is otherwise unused.
+	 * When the port is off and the override is removed
+	 * the lanes power down anyway, so otherwise it doesn't
+	 * really matter what the state of power down bits is
+	 * after this.
+	 */
+	chv_phy_powergate_lanes(encoder, false, 0x0);
+}
+
+void vlv_set_phy_signal_level(struct intel_encoder *encoder,
+			      u32 demph_reg_value, u32 preemph_reg_value,
+			      u32 uniqtranscale_reg_value, u32 tx3_demph)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	enum dpio_channel port = vlv_dport_to_channel(dport);
+	int pipe = intel_crtc->pipe;
+
+	mutex_lock(&dev_priv->sb_lock);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), 0x00000000);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW4(port), demph_reg_value);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW2(port),
+			 uniqtranscale_reg_value);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW3(port), 0x0C782040);
+
+	if (tx3_demph)
+		vlv_dpio_write(dev_priv, pipe, VLV_TX3_DW4(port), tx3_demph);
+
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW11(port), 0x00030000);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW9(port), preemph_reg_value);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), DPIO_TX_OCALINIT_EN);
+	mutex_unlock(&dev_priv->sb_lock);
+}
+
+void vlv_phy_pre_pll_enable(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel port = vlv_dport_to_channel(dport);
+	int pipe = intel_crtc->pipe;
+
+	/* Program Tx lane resets to default */
+	mutex_lock(&dev_priv->sb_lock);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port),
+			 DPIO_PCS_TX_LANE2_RESET |
+			 DPIO_PCS_TX_LANE1_RESET);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW1(port),
+			 DPIO_PCS_CLK_CRI_RXEB_EIOS_EN |
+			 DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN |
+			 (1<<DPIO_PCS_CLK_DATAWIDTH_SHIFT) |
+				 DPIO_PCS_CLK_SOFT_RESET);
+
+	/* Fix up inter-pair skew failure */
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW12(port), 0x00750f00);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW11(port), 0x00001500);
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW14(port), 0x40400000);
+	mutex_unlock(&dev_priv->sb_lock);
+}
+
+void vlv_phy_pre_encoder_enable(struct intel_encoder *encoder)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel port = vlv_dport_to_channel(dport);
+	int pipe = intel_crtc->pipe;
+	u32 val;
+
+	mutex_lock(&dev_priv->sb_lock);
+
+	/* Enable clock channels for this port */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(port));
+	val = 0;
+	if (pipe)
+		val |= (1<<21);
+	else
+		val &= ~(1<<21);
+	val |= 0x001000c4;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW8(port), val);
+
+	/* Program lane clock */
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW14(port), 0x00760018);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW23(port), 0x00400888);
+
+	mutex_unlock(&dev_priv->sb_lock);
+}
+
+void vlv_phy_reset_lanes(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel port = vlv_dport_to_channel(dport);
+	int pipe = intel_crtc->pipe;
+
+	mutex_lock(&dev_priv->sb_lock);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port), 0x00000000);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW1(port), 0x00e00060);
+	mutex_unlock(&dev_priv->sb_lock);
+}
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 58f60b27837e..5c1f2d235ffa 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -83,7 +83,7 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv,
 void intel_prepare_shared_dpll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_shared_dpll *pll = crtc->config->shared_dpll;
 
 	if (WARN_ON(pll == NULL))
@@ -112,7 +112,7 @@ void intel_prepare_shared_dpll(struct intel_crtc *crtc)
 void intel_enable_shared_dpll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_shared_dpll *pll = crtc->config->shared_dpll;
 	unsigned crtc_mask = 1 << drm_crtc_index(&crtc->base);
 	unsigned old_mask;
@@ -151,7 +151,7 @@ out:
 void intel_disable_shared_dpll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_shared_dpll *pll = crtc->config->shared_dpll;
 	unsigned crtc_mask = 1 << drm_crtc_index(&crtc->base);
 
@@ -191,7 +191,7 @@ intel_find_shared_dpll(struct intel_crtc *crtc,
 		       enum intel_dpll_id range_min,
 		       enum intel_dpll_id range_max)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_shared_dpll *pll;
 	struct intel_shared_dpll_config *shared_dpll;
 	enum intel_dpll_id i;
@@ -208,8 +208,8 @@ intel_find_shared_dpll(struct intel_crtc *crtc,
 		if (memcmp(&crtc_state->dpll_hw_state,
 			   &shared_dpll[i].hw_state,
 			   sizeof(crtc_state->dpll_hw_state)) == 0) {
-			DRM_DEBUG_KMS("CRTC:%d sharing existing %s (crtc mask 0x%08x, active %x)\n",
-				      crtc->base.base.id, pll->name,
+			DRM_DEBUG_KMS("[CRTC:%d:%s] sharing existing %s (crtc mask 0x%08x, active %x)\n",
+				      crtc->base.base.id, crtc->base.name, pll->name,
 				      shared_dpll[i].crtc_mask,
 				      pll->active_mask);
 			return pll;
@@ -220,8 +220,8 @@ intel_find_shared_dpll(struct intel_crtc *crtc,
 	for (i = range_min; i <= range_max; i++) {
 		pll = &dev_priv->shared_dplls[i];
 		if (shared_dpll[i].crtc_mask == 0) {
-			DRM_DEBUG_KMS("CRTC:%d allocated %s\n",
-				      crtc->base.base.id, pll->name);
+			DRM_DEBUG_KMS("[CRTC:%d:%s] allocated %s\n",
+				      crtc->base.base.id, crtc->base.name, pll->name);
 			return pll;
 		}
 	}
@@ -331,7 +331,7 @@ static void ibx_pch_dpll_enable(struct drm_i915_private *dev_priv,
 static void ibx_pch_dpll_disable(struct drm_i915_private *dev_priv,
 				 struct intel_shared_dpll *pll)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct intel_crtc *crtc;
 
 	/* Make sure no transcoder isn't still depending on us. */
@@ -358,8 +358,8 @@ ibx_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 		i = (enum intel_dpll_id) crtc->pipe;
 		pll = &dev_priv->shared_dplls[i];
 
-		DRM_DEBUG_KMS("CRTC:%d using pre-allocated %s\n",
-			      crtc->base.base.id, pll->name);
+		DRM_DEBUG_KMS("[CRTC:%d:%s] using pre-allocated %s\n",
+			      crtc->base.base.id, crtc->base.name, pll->name);
 	} else {
 		pll = intel_find_shared_dpll(crtc, crtc_state,
 					     DPLL_ID_PCH_PLL_A,
@@ -713,7 +713,7 @@ hsw_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 		pll = intel_find_shared_dpll(crtc, crtc_state,
 					     DPLL_ID_WRPLL1, DPLL_ID_WRPLL2);
 
-	} else if (encoder->type == INTEL_OUTPUT_DISPLAYPORT ||
+	} else if (encoder->type == INTEL_OUTPUT_DP ||
 		   encoder->type == INTEL_OUTPUT_DP_MST ||
 		   encoder->type == INTEL_OUTPUT_EDP) {
 		enum intel_dpll_id pll_id;
@@ -856,7 +856,11 @@ static void skl_ddi_pll_enable(struct drm_i915_private *dev_priv,
 	I915_WRITE(regs[pll->id].ctl,
 		   I915_READ(regs[pll->id].ctl) | LCPLL_PLL_ENABLE);
 
-	if (wait_for(I915_READ(DPLL_STATUS) & DPLL_LOCK(pll->id), 5))
+	if (intel_wait_for_register(dev_priv,
+				    DPLL_STATUS,
+				    DPLL_LOCK(pll->id),
+				    DPLL_LOCK(pll->id),
+				    5))
 		DRM_ERROR("DPLL %d not locked\n", pll->id);
 }
 
@@ -1222,7 +1226,7 @@ skl_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 			 DPLL_CFGCR2_KDIV(wrpll_params.kdiv) |
 			 DPLL_CFGCR2_PDIV(wrpll_params.pdiv) |
 			 wrpll_params.central_freq;
-	} else if (encoder->type == INTEL_OUTPUT_DISPLAYPORT ||
+	} else if (encoder->type == INTEL_OUTPUT_DP ||
 		   encoder->type == INTEL_OUTPUT_DP_MST ||
 		   encoder->type == INTEL_OUTPUT_EDP) {
 		switch (crtc_state->port_clock / 2) {
@@ -1239,9 +1243,6 @@ skl_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 		case 162000:
 			ctrl1 |= DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1620, 0);
 			break;
-		/* TBD: For DP link rates 2.16 GHz and 4.32 GHz, VCO is 8640 which
-		results in CDCLK change. Need to handle the change of CDCLK by
-		disabling pipes and re-enabling them */
 		case 108000:
 			ctrl1 |= DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1080, 0);
 			break;
@@ -1511,7 +1512,7 @@ bxt_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 	int clock = crtc_state->port_clock;
 
 	if (encoder->type == INTEL_OUTPUT_HDMI) {
-		intel_clock_t best_clock;
+		struct dpll best_clock;
 
 		/* Calculate HDMI div */
 		/*
@@ -1533,7 +1534,7 @@ bxt_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 		clk_div.m2_frac_en = clk_div.m2_frac != 0;
 
 		vco = best_clock.vco;
-	} else if (encoder->type == INTEL_OUTPUT_DISPLAYPORT ||
+	} else if (encoder->type == INTEL_OUTPUT_DP ||
 		   encoder->type == INTEL_OUTPUT_EDP) {
 		int i;
 
@@ -1616,8 +1617,8 @@ bxt_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 	i = (enum intel_dpll_id) intel_dig_port->port;
 	pll = intel_get_shared_dpll_by_id(dev_priv, i);
 
-	DRM_DEBUG_KMS("CRTC:%d using pre-allocated %s\n",
-		crtc->base.base.id, pll->name);
+	DRM_DEBUG_KMS("[CRTC:%d:%s] using pre-allocated %s\n",
+		      crtc->base.base.id, crtc->base.name, pll->name);
 
 	intel_reference_shared_dpll(pll, crtc_state);
 
@@ -1635,19 +1636,11 @@ static const struct intel_shared_dpll_funcs bxt_ddi_pll_funcs = {
 
 static void intel_ddi_pll_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t val = I915_READ(LCPLL_CTL);
-
-	if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) {
-		int cdclk_freq;
-
-		cdclk_freq = dev_priv->display.get_display_clock_speed(dev);
-		dev_priv->skl_boot_cdclk = cdclk_freq;
-		if (skl_sanitize_cdclk(dev_priv))
-			DRM_DEBUG_KMS("Sanitized cdclk programmed by pre-os\n");
-		if (!(I915_READ(LCPLL1_CTL) & LCPLL_PLL_ENABLE))
-			DRM_ERROR("LCPLL1 is disabled\n");
-	} else if (!IS_BROXTON(dev_priv)) {
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	if (INTEL_GEN(dev_priv) < 9) {
+		uint32_t val = I915_READ(LCPLL_CTL);
+
 		/*
 		 * The LCPLL register should be turned on by the BIOS. For now
 		 * let's just check its state and print errors in case
@@ -1730,7 +1723,7 @@ static const struct intel_dpll_mgr bxt_pll_mgr = {
 
 void intel_shared_dpll_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	const struct intel_dpll_mgr *dpll_mgr = NULL;
 	const struct dpll_info *dpll_info;
 	int i;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index f7f0f01814f6..cc937a19b1ba 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -69,39 +69,63 @@
 })
 
 #define wait_for(COND, MS)	  	_wait_for((COND), (MS) * 1000, 1000)
-#define wait_for_us(COND, US)	  	_wait_for((COND), (US), 1)
 
 /* If CONFIG_PREEMPT_COUNT is disabled, in_atomic() always reports false. */
 #if defined(CONFIG_DRM_I915_DEBUG) && defined(CONFIG_PREEMPT_COUNT)
-# define _WAIT_FOR_ATOMIC_CHECK WARN_ON_ONCE(!in_atomic())
+# define _WAIT_FOR_ATOMIC_CHECK(ATOMIC) WARN_ON_ONCE((ATOMIC) && !in_atomic())
 #else
-# define _WAIT_FOR_ATOMIC_CHECK do { } while (0)
+# define _WAIT_FOR_ATOMIC_CHECK(ATOMIC) do { } while (0)
 #endif
 
-#define _wait_for_atomic(COND, US) ({ \
-	unsigned long end__; \
-	int ret__ = 0; \
-	_WAIT_FOR_ATOMIC_CHECK; \
+#define _wait_for_atomic(COND, US, ATOMIC) \
+({ \
+	int cpu, ret, timeout = (US) * 1000; \
+	u64 base; \
+	_WAIT_FOR_ATOMIC_CHECK(ATOMIC); \
 	BUILD_BUG_ON((US) > 50000); \
-	end__ = (local_clock() >> 10) + (US) + 1; \
-	while (!(COND)) { \
-		if (time_after((unsigned long)(local_clock() >> 10), end__)) { \
-			/* Unlike the regular wait_for(), this atomic variant \
-			 * cannot be preempted (and we'll just ignore the issue\
-			 * of irq interruptions) and so we know that no time \
-			 * has passed since the last check of COND and can \
-			 * immediately report the timeout. \
-			 */ \
-			ret__ = -ETIMEDOUT; \
+	if (!(ATOMIC)) { \
+		preempt_disable(); \
+		cpu = smp_processor_id(); \
+	} \
+	base = local_clock(); \
+	for (;;) { \
+		u64 now = local_clock(); \
+		if (!(ATOMIC)) \
+			preempt_enable(); \
+		if (COND) { \
+			ret = 0; \
+			break; \
+		} \
+		if (now - base >= timeout) { \
+			ret = -ETIMEDOUT; \
 			break; \
 		} \
 		cpu_relax(); \
+		if (!(ATOMIC)) { \
+			preempt_disable(); \
+			if (unlikely(cpu != smp_processor_id())) { \
+				timeout -= now - base; \
+				cpu = smp_processor_id(); \
+				base = local_clock(); \
+			} \
+		} \
 	} \
+	ret; \
+})
+
+#define wait_for_us(COND, US) \
+({ \
+	int ret__; \
+	BUILD_BUG_ON(!__builtin_constant_p(US)); \
+	if ((US) > 10) \
+		ret__ = _wait_for((COND), (US), 10); \
+	else \
+		ret__ = _wait_for_atomic((COND), (US), 0); \
 	ret__; \
 })
 
-#define wait_for_atomic(COND, MS)	_wait_for_atomic((COND), (MS) * 1000)
-#define wait_for_atomic_us(COND, US)	_wait_for_atomic((COND), (US))
+#define wait_for_atomic(COND, MS)	_wait_for_atomic((COND), (MS) * 1000, 1)
+#define wait_for_atomic_us(COND, US)	_wait_for_atomic((COND), (US), 1)
 
 #define KHz(x) (1000 * (x))
 #define MHz(x) KHz(1000 * (x))
@@ -135,7 +159,7 @@ enum intel_output_type {
 	INTEL_OUTPUT_LVDS = 4,
 	INTEL_OUTPUT_TVOUT = 5,
 	INTEL_OUTPUT_HDMI = 6,
-	INTEL_OUTPUT_DISPLAYPORT = 7,
+	INTEL_OUTPUT_DP = 7,
 	INTEL_OUTPUT_EDP = 8,
 	INTEL_OUTPUT_DSI = 9,
 	INTEL_OUTPUT_UNKNOWN = 10,
@@ -159,6 +183,7 @@ struct intel_framebuffer {
 struct intel_fbdev {
 	struct drm_fb_helper helper;
 	struct intel_framebuffer *fb;
+	async_cookie_t cookie;
 	int preferred_bpp;
 };
 
@@ -242,14 +267,6 @@ struct intel_connector {
 	 * and active (i.e. dpms ON state). */
 	bool (*get_hw_state)(struct intel_connector *);
 
-	/*
-	 * Removes all interfaces through which the connector is accessible
-	 * - like sysfs, debugfs entries -, so that no new operations can be
-	 * started on the connector. Also makes sure all currently pending
-	 * operations finish before returing.
-	 */
-	void (*unregister)(struct intel_connector *);
-
 	/* Panel info for eDP and LVDS */
 	struct intel_panel panel;
 
@@ -266,7 +283,7 @@ struct intel_connector {
 	struct intel_dp *mst_port;
 };
 
-typedef struct dpll {
+struct dpll {
 	/* given values */
 	int n;
 	int m1, m2;
@@ -276,7 +293,7 @@ typedef struct dpll {
 	int	vco;
 	int	m;
 	int	p;
-} intel_clock_t;
+};
 
 struct intel_atomic_state {
 	struct drm_atomic_state base;
@@ -291,17 +308,32 @@ struct intel_atomic_state {
 
 	bool dpll_set, modeset;
 
+	/*
+	 * Does this transaction change the pipes that are active?  This mask
+	 * tracks which CRTC's have changed their active state at the end of
+	 * the transaction (not counting the temporary disable during modesets).
+	 * This mask should only be non-zero when intel_state->modeset is true,
+	 * but the converse is not necessarily true; simply changing a mode may
+	 * not flip the final active status of any CRTC's
+	 */
+	unsigned int active_pipe_changes;
+
 	unsigned int active_crtcs;
 	unsigned int min_pixclk[I915_MAX_PIPES];
 
+	/* SKL/KBL Only */
+	unsigned int cdclk_pll_vco;
+
 	struct intel_shared_dpll_config shared_dpll[I915_NUM_PLLS];
-	struct intel_wm_config wm_config;
 
 	/*
 	 * Current watermarks can't be trusted during hardware readout, so
 	 * don't bother calculating intermediate watermarks.
 	 */
 	bool skip_intermediate_wm;
+
+	/* Gen9+ only */
+	struct skl_wm_values wm_results;
 };
 
 struct intel_plane_state {
@@ -405,6 +437,48 @@ struct skl_pipe_wm {
 	uint32_t linetime;
 };
 
+struct intel_crtc_wm_state {
+	union {
+		struct {
+			/*
+			 * Intermediate watermarks; these can be
+			 * programmed immediately since they satisfy
+			 * both the current configuration we're
+			 * switching away from and the new
+			 * configuration we're switching to.
+			 */
+			struct intel_pipe_wm intermediate;
+
+			/*
+			 * Optimal watermarks, programmed post-vblank
+			 * when this state is committed.
+			 */
+			struct intel_pipe_wm optimal;
+		} ilk;
+
+		struct {
+			/* gen9+ only needs 1-step wm programming */
+			struct skl_pipe_wm optimal;
+
+			/* cached plane data rate */
+			unsigned plane_data_rate[I915_MAX_PLANES];
+			unsigned plane_y_data_rate[I915_MAX_PLANES];
+
+			/* minimum block allocation */
+			uint16_t minimum_blocks[I915_MAX_PLANES];
+			uint16_t minimum_y_blocks[I915_MAX_PLANES];
+		} skl;
+	};
+
+	/*
+	 * Platforms with two-step watermark programming will need to
+	 * update watermark programming post-vblank to switch from the
+	 * safe intermediate watermarks to the optimal final
+	 * watermarks.
+	 */
+	bool need_postvbl_update;
+};
+
 struct intel_crtc_state {
 	struct drm_crtc_state base;
 
@@ -448,12 +522,10 @@ struct intel_crtc_state {
 	 */
 	bool limited_color_range;
 
-	/* DP has a bunch of special case unfortunately, so mark the pipe
-	 * accordingly. */
-	bool has_dp_encoder;
-
-	/* DSI has special cases */
-	bool has_dsi_encoder;
+	/* Bitmask of encoder types (enum intel_output_type)
+	 * driven by the pipe.
+	 */
+	unsigned int output_types;
 
 	/* Whether we should send NULL infoframes. Required for audio. */
 	bool has_hdmi_sink;
@@ -522,6 +594,12 @@ struct intel_crtc_state {
 
 	uint8_t lane_count;
 
+	/*
+	 * Used by platforms having DP/HDMI PHY with programmable lane
+	 * latency optimization.
+	 */
+	uint8_t lane_lat_optim_mask;
+
 	/* Panel fitter controls for gen2-gen4 + VLV */
 	struct {
 		u32 control;
@@ -558,32 +636,7 @@ struct intel_crtc_state {
 	/* IVB sprite scaling w/a (WaCxSRDisabledForSpriteScaling:ivb) */
 	bool disable_lp_wm;
 
-	struct {
-		/*
-		 * Optimal watermarks, programmed post-vblank when this state
-		 * is committed.
-		 */
-		union {
-			struct intel_pipe_wm ilk;
-			struct skl_pipe_wm skl;
-		} optimal;
-
-		/*
-		 * Intermediate watermarks; these can be programmed immediately
-		 * since they satisfy both the current configuration we're
-		 * switching away from and the new configuration we're switching
-		 * to.
-		 */
-		struct intel_pipe_wm intermediate;
-
-		/*
-		 * Platforms with two-step watermark programming will need to
-		 * update watermark programming post-vblank to switch from the
-		 * safe intermediate watermarks to the optimal final
-		 * watermarks.
-		 */
-		bool need_postvbl_update;
-	} wm;
+	struct intel_crtc_wm_state wm;
 
 	/* Gamma mode programmed on the pipe */
 	uint32_t gamma_mode;
@@ -598,14 +651,6 @@ struct vlv_wm_state {
 	bool cxsr;
 };
 
-struct intel_mmio_flip {
-	struct work_struct work;
-	struct drm_i915_private *i915;
-	struct drm_i915_gem_request *req;
-	struct intel_crtc *crtc;
-	unsigned int rotation;
-};
-
 struct intel_crtc {
 	struct drm_crtc base;
 	enum pipe pipe;
@@ -620,7 +665,7 @@ struct intel_crtc {
 	unsigned long enabled_power_domains;
 	bool lowfreq_avail;
 	struct intel_overlay *overlay;
-	struct intel_unpin_work *unpin_work;
+	struct intel_flip_work *flip_work;
 
 	atomic_t unpin_work_count;
 
@@ -815,6 +860,7 @@ struct intel_dp {
 	uint8_t dpcd[DP_RECEIVER_CAP_SIZE];
 	uint8_t psr_dpcd[EDP_PSR_RECEIVER_CAP_SIZE];
 	uint8_t downstream_ports[DP_MAX_DOWNSTREAM_PORTS];
+	uint8_t edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE];
 	/* sink rates as reported by DP_SUPPORTED_LINK_RATES */
 	uint8_t num_sink_rates;
 	int sink_rates[DP_MAX_SUPPORTED_RATES];
@@ -838,6 +884,11 @@ struct intel_dp {
 	 * this port. Only relevant on VLV/CHV.
 	 */
 	enum pipe pps_pipe;
+	/*
+	 * Set if the sequencer may be reset due to a power transition,
+	 * requiring a reinitialization. Only relevant on BXT.
+	 */
+	bool pps_reset;
 	struct edp_power_seq pps_delays;
 
 	bool can_mst; /* this port supports mst */
@@ -934,33 +985,32 @@ vlv_pipe_to_channel(enum pipe pipe)
 static inline struct drm_crtc *
 intel_get_crtc_for_pipe(struct drm_device *dev, int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	return dev_priv->pipe_to_crtc_mapping[pipe];
 }
 
 static inline struct drm_crtc *
 intel_get_crtc_for_plane(struct drm_device *dev, int plane)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	return dev_priv->plane_to_crtc_mapping[plane];
 }
 
-struct intel_unpin_work {
-	struct work_struct work;
+struct intel_flip_work {
+	struct work_struct unpin_work;
+	struct work_struct mmio_work;
+
 	struct drm_crtc *crtc;
 	struct drm_framebuffer *old_fb;
 	struct drm_i915_gem_object *pending_flip_obj;
 	struct drm_pending_vblank_event *event;
 	atomic_t pending;
-#define INTEL_FLIP_INACTIVE	0
-#define INTEL_FLIP_PENDING	1
-#define INTEL_FLIP_COMPLETE	2
 	u32 flip_count;
 	u32 gtt_offset;
 	struct drm_i915_gem_request *flip_queued_req;
 	u32 flip_queued_vblank;
 	u32 flip_ready_vblank;
-	bool enable_stall_check;
+	unsigned int rotation;
 };
 
 struct intel_load_detect_pipe {
@@ -1029,9 +1079,9 @@ void gen5_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen5_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen6_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen6_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
-void gen6_reset_rps_interrupts(struct drm_device *dev);
-void gen6_enable_rps_interrupts(struct drm_device *dev);
-void gen6_disable_rps_interrupts(struct drm_device *dev);
+void gen6_reset_rps_interrupts(struct drm_i915_private *dev_priv);
+void gen6_enable_rps_interrupts(struct drm_i915_private *dev_priv);
+void gen6_disable_rps_interrupts(struct drm_i915_private *dev_priv);
 u32 gen6_sanitize_rps_pm_mask(struct drm_i915_private *dev_priv, u32 mask);
 void intel_runtime_pm_disable_interrupts(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_enable_interrupts(struct drm_i915_private *dev_priv);
@@ -1052,7 +1102,7 @@ void gen8_irq_power_well_pre_disable(struct drm_i915_private *dev_priv,
 
 /* intel_crt.c */
 void intel_crt_init(struct drm_device *dev);
-
+void intel_crt_reset(struct drm_encoder *encoder);
 
 /* intel_ddi.c */
 void intel_ddi_clk_select(struct intel_encoder *encoder,
@@ -1110,14 +1160,16 @@ void i915_audio_component_init(struct drm_i915_private *dev_priv);
 void i915_audio_component_cleanup(struct drm_i915_private *dev_priv);
 
 /* intel_display.c */
+void skl_set_preferred_cdclk_vco(struct drm_i915_private *dev_priv, int vco);
+void intel_update_rawclk(struct drm_i915_private *dev_priv);
 int vlv_get_cck_clock(struct drm_i915_private *dev_priv,
 		      const char *name, u32 reg, int ref_freq);
 extern const struct drm_plane_funcs intel_plane_funcs;
 void intel_init_display_hooks(struct drm_i915_private *dev_priv);
 unsigned int intel_rotation_info_size(const struct intel_rotation_info *rot_info);
 bool intel_has_pending_fb_unpin(struct drm_device *dev);
-void intel_mark_busy(struct drm_device *dev);
-void intel_mark_idle(struct drm_device *dev);
+void intel_mark_busy(struct drm_i915_private *dev_priv);
+void intel_mark_idle(struct drm_i915_private *dev_priv);
 void intel_crtc_restore_mode(struct drm_crtc *crtc);
 int intel_display_suspend(struct drm_device *dev);
 void intel_encoder_destroy(struct drm_encoder *encoder);
@@ -1126,7 +1178,6 @@ struct intel_connector *intel_connector_alloc(void);
 bool intel_connector_get_hw_state(struct intel_connector *connector);
 void intel_connector_attach_encoder(struct intel_connector *connector,
 				    struct intel_encoder *encoder);
-struct drm_encoder *intel_best_encoder(struct drm_connector *connector);
 struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 					     struct drm_crtc *crtc);
 enum pipe intel_get_pipe_from_connector(struct intel_connector *connector);
@@ -1134,7 +1185,20 @@ int intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data,
 				struct drm_file *file_priv);
 enum transcoder intel_pipe_to_cpu_transcoder(struct drm_i915_private *dev_priv,
 					     enum pipe pipe);
-bool intel_pipe_has_type(struct intel_crtc *crtc, enum intel_output_type type);
+static inline bool
+intel_crtc_has_type(const struct intel_crtc_state *crtc_state,
+		    enum intel_output_type type)
+{
+	return crtc_state->output_types & (1 << type);
+}
+static inline bool
+intel_crtc_has_dp_encoder(const struct intel_crtc_state *crtc_state)
+{
+	return crtc_state->output_types &
+		((1 << INTEL_OUTPUT_DP) |
+		 (1 << INTEL_OUTPUT_DP_MST) |
+		 (1 << INTEL_OUTPUT_EDP));
+}
 static inline void
 intel_wait_for_vblank(struct drm_device *dev, int pipe)
 {
@@ -1149,6 +1213,9 @@ intel_wait_for_vblank_if_active(struct drm_device *dev, int pipe)
 	if (crtc->active)
 		intel_wait_for_vblank(dev, pipe);
 }
+
+u32 intel_crtc_get_vblank_counter(struct intel_crtc *crtc);
+
 int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp);
 void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 			 struct intel_digital_port *dport,
@@ -1162,14 +1229,14 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 				    struct drm_modeset_acquire_ctx *ctx);
 int intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 			       unsigned int rotation);
+void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation);
 struct drm_framebuffer *
 __intel_framebuffer_create(struct drm_device *dev,
 			   struct drm_mode_fb_cmd2 *mode_cmd,
 			   struct drm_i915_gem_object *obj);
-void intel_prepare_page_flip(struct drm_device *dev, int plane);
-void intel_finish_page_flip(struct drm_device *dev, int pipe);
-void intel_finish_page_flip_plane(struct drm_device *dev, int plane);
-void intel_check_page_flip(struct drm_device *dev, int pipe);
+void intel_finish_page_flip_cs(struct drm_i915_private *dev_priv, int pipe);
+void intel_finish_page_flip_mmio(struct drm_i915_private *dev_priv, int pipe);
+void intel_check_page_flip(struct drm_i915_private *dev_priv, int pipe);
 int intel_prepare_plane_fb(struct drm_plane *plane,
 			   const struct drm_plane_state *new_state);
 void intel_cleanup_plane_fb(struct drm_plane *plane,
@@ -1226,23 +1293,25 @@ u32 intel_compute_tile_offset(int *x, int *y,
 			      const struct drm_framebuffer *fb, int plane,
 			      unsigned int pitch,
 			      unsigned int rotation);
-void intel_prepare_reset(struct drm_device *dev);
-void intel_finish_reset(struct drm_device *dev);
+void intel_prepare_reset(struct drm_i915_private *dev_priv);
+void intel_finish_reset(struct drm_i915_private *dev_priv);
 void hsw_enable_pc8(struct drm_i915_private *dev_priv);
 void hsw_disable_pc8(struct drm_i915_private *dev_priv);
-void broxton_init_cdclk(struct drm_i915_private *dev_priv);
-void broxton_uninit_cdclk(struct drm_i915_private *dev_priv);
-bool broxton_cdclk_verify_state(struct drm_i915_private *dev_priv);
-void broxton_ddi_phy_init(struct drm_i915_private *dev_priv);
-void broxton_ddi_phy_uninit(struct drm_i915_private *dev_priv);
-void broxton_ddi_phy_verify_state(struct drm_i915_private *dev_priv);
+void bxt_init_cdclk(struct drm_i915_private *dev_priv);
+void bxt_uninit_cdclk(struct drm_i915_private *dev_priv);
+void bxt_ddi_phy_init(struct drm_i915_private *dev_priv, enum dpio_phy phy);
+void bxt_ddi_phy_uninit(struct drm_i915_private *dev_priv, enum dpio_phy phy);
+bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv,
+			    enum dpio_phy phy);
+bool bxt_ddi_phy_verify_state(struct drm_i915_private *dev_priv,
+			      enum dpio_phy phy);
 void gen9_sanitize_dc_state(struct drm_i915_private *dev_priv);
 void bxt_enable_dc9(struct drm_i915_private *dev_priv);
 void bxt_disable_dc9(struct drm_i915_private *dev_priv);
 void gen9_enable_dc5(struct drm_i915_private *dev_priv);
 void skl_init_cdclk(struct drm_i915_private *dev_priv);
-int skl_sanitize_cdclk(struct drm_i915_private *dev_priv);
 void skl_uninit_cdclk(struct drm_i915_private *dev_priv);
+unsigned int skl_cdclk_get_vco(unsigned int freq);
 void skl_enable_dc6(struct drm_i915_private *dev_priv);
 void skl_disable_dc6(struct drm_i915_private *dev_priv);
 void intel_dp_get_m_n(struct intel_crtc *crtc,
@@ -1250,8 +1319,8 @@ void intel_dp_get_m_n(struct intel_crtc *crtc,
 void intel_dp_set_m_n(struct intel_crtc *crtc, enum link_m_n_set m_n);
 int intel_dotclock_calculate(int link_freq, const struct intel_link_m_n *m_n);
 bool bxt_find_best_dpll(struct intel_crtc_state *crtc_state, int target_clock,
-			intel_clock_t *best_clock);
-int chv_calc_dpll_params(int refclk, intel_clock_t *pll_clock);
+			struct dpll *best_clock);
+int chv_calc_dpll_params(int refclk, struct dpll *pll_clock);
 
 bool intel_crtc_active(struct drm_crtc *crtc);
 void hsw_enable_ips(struct intel_crtc *crtc);
@@ -1310,7 +1379,7 @@ void intel_dp_mst_resume(struct drm_device *dev);
 int intel_dp_max_link_rate(struct intel_dp *intel_dp);
 int intel_dp_rate_select(struct intel_dp *intel_dp, int rate);
 void intel_dp_hot_plug(struct intel_encoder *intel_encoder);
-void vlv_power_sequencer_reset(struct drm_i915_private *dev_priv);
+void intel_power_sequencer_reset(struct drm_i915_private *dev_priv);
 uint32_t intel_dp_pack_aux(const uint8_t *src, int src_bytes);
 void intel_plane_destroy(struct drm_plane *plane);
 void intel_edp_drrs_enable(struct intel_dp *intel_dp);
@@ -1337,15 +1406,27 @@ bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp);
 bool
 intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE]);
 
+static inline unsigned int intel_dp_unused_lane_mask(int lane_count)
+{
+	return ~((1 << lane_count) - 1) & 0xf;
+}
+
+/* intel_dp_aux_backlight.c */
+int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector);
+
 /* intel_dp_mst.c */
 int intel_dp_mst_encoder_init(struct intel_digital_port *intel_dig_port, int conn_id);
 void intel_dp_mst_encoder_cleanup(struct intel_digital_port *intel_dig_port);
 /* intel_dsi.c */
 void intel_dsi_init(struct drm_device *dev);
 
+/* intel_dsi_dcs_backlight.c */
+int intel_dsi_dcs_init_backlight_funcs(struct intel_connector *intel_connector);
 
 /* intel_dvo.c */
 void intel_dvo_init(struct drm_device *dev);
+/* intel_hotplug.c */
+void intel_hpd_poll_init(struct drm_i915_private *dev_priv);
 
 
 /* legacy fbdev emulation in intel_fbdev.c */
@@ -1383,11 +1464,15 @@ static inline void intel_fbdev_restore_mode(struct drm_device *dev)
 void intel_fbc_choose_crtc(struct drm_i915_private *dev_priv,
 			   struct drm_atomic_state *state);
 bool intel_fbc_is_active(struct drm_i915_private *dev_priv);
-void intel_fbc_pre_update(struct intel_crtc *crtc);
+void intel_fbc_pre_update(struct intel_crtc *crtc,
+			  struct intel_crtc_state *crtc_state,
+			  struct intel_plane_state *plane_state);
 void intel_fbc_post_update(struct intel_crtc *crtc);
 void intel_fbc_init(struct drm_i915_private *dev_priv);
 void intel_fbc_init_pipe_state(struct drm_i915_private *dev_priv);
-void intel_fbc_enable(struct intel_crtc *crtc);
+void intel_fbc_enable(struct intel_crtc *crtc,
+		      struct intel_crtc_state *crtc_state,
+		      struct intel_plane_state *plane_state);
 void intel_fbc_disable(struct intel_crtc *crtc);
 void intel_fbc_global_disable(struct drm_i915_private *dev_priv);
 void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
@@ -1409,6 +1494,7 @@ void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable);
 
 /* intel_lvds.c */
 void intel_lvds_init(struct drm_device *dev);
+struct intel_encoder *intel_get_lvds_encoder(struct drm_device *dev);
 bool intel_is_dual_link_lvds(struct drm_device *dev);
 
 
@@ -1422,13 +1508,13 @@ void intel_attach_aspect_ratio_property(struct drm_connector *connector);
 
 
 /* intel_overlay.c */
-void intel_setup_overlay(struct drm_device *dev);
-void intel_cleanup_overlay(struct drm_device *dev);
+void intel_setup_overlay(struct drm_i915_private *dev_priv);
+void intel_cleanup_overlay(struct drm_i915_private *dev_priv);
 int intel_overlay_switch_off(struct intel_overlay *overlay);
-int intel_overlay_put_image(struct drm_device *dev, void *data,
-			    struct drm_file *file_priv);
-int intel_overlay_attrs(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
+int intel_overlay_put_image_ioctl(struct drm_device *dev, void *data,
+				  struct drm_file *file_priv);
+int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
 void intel_overlay_reset(struct drm_i915_private *dev_priv);
 
 
@@ -1447,7 +1533,8 @@ void intel_gmch_panel_fitting(struct intel_crtc *crtc,
 			      int fitting_mode);
 void intel_panel_set_backlight_acpi(struct intel_connector *connector,
 				    u32 level, u32 max);
-int intel_panel_setup_backlight(struct drm_connector *connector, enum pipe pipe);
+int intel_panel_setup_backlight(struct drm_connector *connector,
+				enum pipe pipe);
 void intel_panel_enable_backlight(struct intel_connector *connector);
 void intel_panel_disable_backlight(struct intel_connector *connector);
 void intel_panel_destroy_backlight(struct drm_connector *connector);
@@ -1456,8 +1543,19 @@ extern struct drm_display_mode *intel_find_panel_downclock(
 				struct drm_device *dev,
 				struct drm_display_mode *fixed_mode,
 				struct drm_connector *connector);
-void intel_backlight_register(struct drm_device *dev);
-void intel_backlight_unregister(struct drm_device *dev);
+
+#if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE)
+int intel_backlight_device_register(struct intel_connector *connector);
+void intel_backlight_device_unregister(struct intel_connector *connector);
+#else /* CONFIG_BACKLIGHT_CLASS_DEVICE */
+static int intel_backlight_device_register(struct intel_connector *connector)
+{
+	return 0;
+}
+static inline void intel_backlight_device_unregister(struct intel_connector *connector)
+{
+}
+#endif /* CONFIG_BACKLIGHT_CLASS_DEVICE */
 
 
 /* intel_psr.c */
@@ -1599,21 +1697,20 @@ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv);
 void intel_pm_setup(struct drm_device *dev);
 void intel_gpu_ips_init(struct drm_i915_private *dev_priv);
 void intel_gpu_ips_teardown(void);
-void intel_init_gt_powersave(struct drm_device *dev);
-void intel_cleanup_gt_powersave(struct drm_device *dev);
-void intel_enable_gt_powersave(struct drm_device *dev);
-void intel_disable_gt_powersave(struct drm_device *dev);
-void intel_suspend_gt_powersave(struct drm_device *dev);
-void intel_reset_gt_powersave(struct drm_device *dev);
-void gen6_update_ring_freq(struct drm_device *dev);
+void intel_init_gt_powersave(struct drm_i915_private *dev_priv);
+void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv);
+void intel_enable_gt_powersave(struct drm_i915_private *dev_priv);
+void intel_disable_gt_powersave(struct drm_i915_private *dev_priv);
+void intel_suspend_gt_powersave(struct drm_i915_private *dev_priv);
+void intel_reset_gt_powersave(struct drm_i915_private *dev_priv);
+void gen6_update_ring_freq(struct drm_i915_private *dev_priv);
 void gen6_rps_busy(struct drm_i915_private *dev_priv);
 void gen6_rps_reset_ei(struct drm_i915_private *dev_priv);
 void gen6_rps_idle(struct drm_i915_private *dev_priv);
 void gen6_rps_boost(struct drm_i915_private *dev_priv,
 		    struct intel_rps_client *rps,
 		    unsigned long submitted);
-void intel_queue_rps_boost_for_request(struct drm_device *dev,
-				       struct drm_i915_gem_request *req);
+void intel_queue_rps_boost_for_request(struct drm_i915_gem_request *req);
 void vlv_wm_get_hw_state(struct drm_device *dev);
 void ilk_wm_get_hw_state(struct drm_device *dev);
 void skl_wm_get_hw_state(struct drm_device *dev);
@@ -1621,7 +1718,11 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 			  struct skl_ddb_allocation *ddb /* out */);
 uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config);
 bool ilk_disable_lp_wm(struct drm_device *dev);
-int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6);
+int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6);
+static inline int intel_enable_rc6(void)
+{
+	return i915.enable_rc6;
+}
 
 /* intel_sdvo.c */
 bool intel_sdvo_init(struct drm_device *dev,
@@ -1629,11 +1730,13 @@ bool intel_sdvo_init(struct drm_device *dev,
 
 
 /* intel_sprite.c */
+int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
+			     int usecs);
 int intel_plane_init(struct drm_device *dev, enum pipe pipe, int plane);
 int intel_sprite_set_colorkey(struct drm_device *dev, void *data,
 			      struct drm_file *file_priv);
 void intel_pipe_update_start(struct intel_crtc *crtc);
-void intel_pipe_update_end(struct intel_crtc *crtc);
+void intel_pipe_update_end(struct intel_crtc *crtc, struct intel_flip_work *work);
 
 /* intel_tv.c */
 void intel_tv_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index 4756ef639648..de8e9fb51595 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -84,13 +84,15 @@ static void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port)
 {
 	struct drm_encoder *encoder = &intel_dsi->base.base;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 mask;
 
 	mask = LP_CTRL_FIFO_EMPTY | HS_CTRL_FIFO_EMPTY |
 		LP_DATA_FIFO_EMPTY | HS_DATA_FIFO_EMPTY;
 
-	if (wait_for((I915_READ(MIPI_GEN_FIFO_STAT(port)) & mask) == mask, 100))
+	if (intel_wait_for_register(dev_priv,
+				    MIPI_GEN_FIFO_STAT(port), mask, mask,
+				    100))
 		DRM_ERROR("DPI FIFOs are not empty\n");
 }
 
@@ -129,7 +131,7 @@ static ssize_t intel_dsi_host_transfer(struct mipi_dsi_host *host,
 {
 	struct intel_dsi_host *intel_dsi_host = to_intel_dsi_host(host);
 	struct drm_device *dev = intel_dsi_host->intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_dsi_host->port;
 	struct mipi_dsi_packet packet;
 	ssize_t ret;
@@ -158,8 +160,10 @@ static ssize_t intel_dsi_host_transfer(struct mipi_dsi_host *host,
 
 	/* note: this is never true for reads */
 	if (packet.payload_length) {
-
-		if (wait_for((I915_READ(MIPI_GEN_FIFO_STAT(port)) & data_mask) == 0, 50))
+		if (intel_wait_for_register(dev_priv,
+					    MIPI_GEN_FIFO_STAT(port),
+					    data_mask, 0,
+					    50))
 			DRM_ERROR("Timeout waiting for HS/LP DATA FIFO !full\n");
 
 		write_data(dev_priv, data_reg, packet.payload,
@@ -170,7 +174,10 @@ static ssize_t intel_dsi_host_transfer(struct mipi_dsi_host *host,
 		I915_WRITE(MIPI_INTR_STAT(port), GEN_READ_DATA_AVAIL);
 	}
 
-	if (wait_for((I915_READ(MIPI_GEN_FIFO_STAT(port)) & ctrl_mask) == 0, 50)) {
+	if (intel_wait_for_register(dev_priv,
+				    MIPI_GEN_FIFO_STAT(port),
+				    ctrl_mask, 0,
+				    50)) {
 		DRM_ERROR("Timeout waiting for HS/LP CTRL FIFO !full\n");
 	}
 
@@ -179,7 +186,10 @@ static ssize_t intel_dsi_host_transfer(struct mipi_dsi_host *host,
 	/* ->rx_len is set only for reads */
 	if (msg->rx_len) {
 		data_mask = GEN_READ_DATA_AVAIL;
-		if (wait_for((I915_READ(MIPI_INTR_STAT(port)) & data_mask) == data_mask, 50))
+		if (intel_wait_for_register(dev_priv,
+					    MIPI_INTR_STAT(port),
+					    data_mask, data_mask,
+					    50))
 			DRM_ERROR("Timeout waiting for read data.\n");
 
 		read_data(dev_priv, data_reg, msg->rx_buf, msg->rx_len);
@@ -250,7 +260,7 @@ static int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd, bool hs,
 {
 	struct drm_encoder *encoder = &intel_dsi->base.base;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 mask;
 
 	/* XXX: pipe, hs */
@@ -269,7 +279,9 @@ static int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd, bool hs,
 	I915_WRITE(MIPI_DPI_CONTROL(port), cmd);
 
 	mask = SPL_PKT_SENT_INTERRUPT;
-	if (wait_for((I915_READ(MIPI_INTR_STAT(port)) & mask) == mask, 100))
+	if (intel_wait_for_register(dev_priv,
+				    MIPI_INTR_STAT(port), mask, mask,
+				    100))
 		DRM_ERROR("Video mode command 0x%08x send failed.\n", cmd);
 
 	return 0;
@@ -302,7 +314,7 @@ static inline bool is_cmd_mode(struct intel_dsi *intel_dsi)
 static bool intel_dsi_compute_config(struct intel_encoder *encoder,
 				     struct intel_crtc_state *pipe_config)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi,
 						   base);
 	struct intel_connector *intel_connector = intel_dsi->attached_connector;
@@ -313,8 +325,6 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder,
 
 	DRM_DEBUG_KMS("\n");
 
-	pipe_config->has_dsi_encoder = true;
-
 	if (fixed_mode) {
 		intel_fixed_panel_mode(fixed_mode, adjusted_mode);
 
@@ -348,7 +358,7 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder,
 
 static void bxt_dsi_device_ready(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
 	u32 val;
@@ -387,7 +397,7 @@ static void bxt_dsi_device_ready(struct intel_encoder *encoder)
 
 static void vlv_dsi_device_ready(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
 	u32 val;
@@ -437,7 +447,7 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder)
 static void intel_dsi_port_enable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
@@ -478,7 +488,7 @@ static void intel_dsi_port_enable(struct intel_encoder *encoder)
 static void intel_dsi_port_disable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
 
@@ -497,7 +507,7 @@ static void intel_dsi_port_disable(struct intel_encoder *encoder)
 static void intel_dsi_enable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
 
@@ -528,11 +538,10 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder);
 static void intel_dsi_pre_enable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	enum port port;
-	u32 tmp;
 
 	DRM_DEBUG_KMS("\n");
 
@@ -551,11 +560,13 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder)
 
 	msleep(intel_dsi->panel_on_delay);
 
-	if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+		u32 val;
+
 		/* Disable DPOunit clock gating, can stall pipe */
-		tmp = I915_READ(DSPCLK_GATE_D);
-		tmp |= DPOUNIT_CLOCK_GATE_DISABLE;
-		I915_WRITE(DSPCLK_GATE_D, tmp);
+		val = I915_READ(DSPCLK_GATE_D);
+		val |= DPOUNIT_CLOCK_GATE_DISABLE;
+		I915_WRITE(DSPCLK_GATE_D, val);
 	}
 
 	/* put device in ready state */
@@ -601,7 +612,7 @@ static void intel_dsi_pre_disable(struct intel_encoder *encoder)
 static void intel_dsi_disable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
 	u32 temp;
@@ -640,7 +651,7 @@ static void intel_dsi_disable(struct intel_encoder *encoder)
 static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
 
@@ -666,8 +677,9 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 		/* Wait till Clock lanes are in LP-00 state for MIPI Port A
 		 * only. MIPI Port C has no similar bit for checking
 		 */
-		if (wait_for(((I915_READ(port_ctrl) & AFE_LATCHOUT)
-						== 0x00000), 30))
+		if (intel_wait_for_register(dev_priv,
+					    port_ctrl, AFE_LATCHOUT, 0,
+					    30))
 			DRM_ERROR("DSI LP not going Low\n");
 
 		/* Disable MIPI PHY transparent latch */
@@ -684,7 +696,7 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 
 static void intel_dsi_post_disable(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 
 	DRM_DEBUG_KMS("\n");
@@ -693,7 +705,7 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder)
 
 	intel_dsi_clear_device_ready(encoder);
 
-	if (!IS_BROXTON(dev_priv)) {
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		u32 val;
 
 		val = I915_READ(DSPCLK_GATE_D);
@@ -719,7 +731,7 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder)
 static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	struct drm_device *dev = encoder->base.dev;
 	enum intel_display_power_domain power_domain;
@@ -793,7 +805,7 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
 				 struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_display_mode *adjusted_mode =
 					&pipe_config->base.adjusted_mode;
 	struct drm_display_mode *adjusted_mode_sw;
@@ -953,8 +965,6 @@ static void intel_dsi_get_config(struct intel_encoder *encoder,
 	u32 pclk;
 	DRM_DEBUG_KMS("\n");
 
-	pipe_config->has_dsi_encoder = true;
-
 	if (IS_BROXTON(dev))
 		bxt_dsi_get_pipe_config(encoder, pipe_config);
 
@@ -1012,7 +1022,7 @@ static void set_dsi_timings(struct drm_encoder *encoder,
 			    const struct drm_display_mode *adjusted_mode)
 {
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	unsigned int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
@@ -1098,7 +1108,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 {
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode;
@@ -1171,6 +1181,12 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 	if (intel_dsi->clock_stop)
 		tmp |= CLOCKSTOP;
 
+	if (IS_BROXTON(dev_priv)) {
+		tmp |= BXT_DPHY_DEFEATURE_EN;
+		if (!is_cmd_mode(intel_dsi))
+			tmp |= BXT_DEFEATURE_DPI_FIFO_CTR;
+	}
+
 	for_each_dsi_port(port, intel_dsi->ports) {
 		I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
 
@@ -1378,12 +1394,13 @@ static const struct drm_encoder_funcs intel_dsi_funcs = {
 static const struct drm_connector_helper_funcs intel_dsi_connector_helper_funcs = {
 	.get_modes = intel_dsi_get_modes,
 	.mode_valid = intel_dsi_mode_valid,
-	.best_encoder = intel_best_encoder,
 };
 
 static const struct drm_connector_funcs intel_dsi_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.detect = intel_dsi_detect,
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
 	.destroy = intel_dsi_connector_destroy,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = intel_dsi_set_property,
@@ -1413,7 +1430,7 @@ void intel_dsi_init(struct drm_device *dev)
 	struct intel_connector *intel_connector;
 	struct drm_connector *connector;
 	struct drm_display_mode *scan, *fixed_mode = NULL;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port;
 	unsigned int i;
 
@@ -1449,7 +1466,7 @@ void intel_dsi_init(struct drm_device *dev)
 	connector = &intel_connector->base;
 
 	drm_encoder_init(dev, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI,
-			 NULL);
+			 "DSI %c", port_name(port));
 
 	intel_encoder->compute_config = intel_dsi_compute_config;
 	intel_encoder->pre_enable = intel_dsi_pre_enable;
@@ -1460,7 +1477,6 @@ void intel_dsi_init(struct drm_device *dev)
 	intel_encoder->get_config = intel_dsi_get_config;
 
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
-	intel_connector->unregister = intel_connector_unregister;
 
 	/*
 	 * On BYT/CHV, pipe A maps to MIPI DSI port A, pipe B maps to MIPI DSI
@@ -1473,10 +1489,42 @@ void intel_dsi_init(struct drm_device *dev)
 	else
 		intel_encoder->crtc_mask = BIT(PIPE_B);
 
-	if (dev_priv->vbt.dsi.config->dual_link)
+	if (dev_priv->vbt.dsi.config->dual_link) {
 		intel_dsi->ports = BIT(PORT_A) | BIT(PORT_C);
-	else
+
+		switch (dev_priv->vbt.dsi.config->dl_dcs_backlight_ports) {
+		case DL_DCS_PORT_A:
+			intel_dsi->dcs_backlight_ports = BIT(PORT_A);
+			break;
+		case DL_DCS_PORT_C:
+			intel_dsi->dcs_backlight_ports = BIT(PORT_C);
+			break;
+		default:
+		case DL_DCS_PORT_A_AND_C:
+			intel_dsi->dcs_backlight_ports = BIT(PORT_A) | BIT(PORT_C);
+			break;
+		}
+
+		switch (dev_priv->vbt.dsi.config->dl_dcs_cabc_ports) {
+		case DL_DCS_PORT_A:
+			intel_dsi->dcs_cabc_ports = BIT(PORT_A);
+			break;
+		case DL_DCS_PORT_C:
+			intel_dsi->dcs_cabc_ports = BIT(PORT_C);
+			break;
+		default:
+		case DL_DCS_PORT_A_AND_C:
+			intel_dsi->dcs_cabc_ports = BIT(PORT_A) | BIT(PORT_C);
+			break;
+		}
+	} else {
 		intel_dsi->ports = BIT(port);
+		intel_dsi->dcs_backlight_ports = BIT(port);
+		intel_dsi->dcs_cabc_ports = BIT(port);
+	}
+
+	if (!dev_priv->vbt.dsi.config->cabc_supported)
+		intel_dsi->dcs_cabc_ports = 0;
 
 	/* Create a DSI host (and a device) for each port. */
 	for_each_dsi_port(port, intel_dsi->ports) {
@@ -1549,13 +1597,10 @@ void intel_dsi_init(struct drm_device *dev)
 	connector->display_info.height_mm = fixed_mode->height_mm;
 
 	intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
+	intel_panel_setup_backlight(connector, INVALID_PIPE);
 
 	intel_dsi_add_properties(intel_connector);
 
-	drm_connector_register(connector);
-
-	intel_panel_setup_backlight(connector, INVALID_PIPE);
-
 	return;
 
 err:
diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h
index 61a6957fc6c2..5967ea6d6045 100644
--- a/drivers/gpu/drm/i915/intel_dsi.h
+++ b/drivers/gpu/drm/i915/intel_dsi.h
@@ -78,6 +78,10 @@ struct intel_dsi {
 
 	u8 escape_clk_div;
 	u8 dual_link;
+
+	u16 dcs_backlight_ports;
+	u16 dcs_cabc_ports;
+
 	u8 pixel_overlap;
 	u32 port_bits;
 	u32 bw_timer;
diff --git a/drivers/gpu/drm/i915/intel_dsi_dcs_backlight.c b/drivers/gpu/drm/i915/intel_dsi_dcs_backlight.c
new file mode 100644
index 000000000000..ac7c6020c443
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_dsi_dcs_backlight.c
@@ -0,0 +1,179 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Author: Deepak M <m.deepak at intel.com>
+ */
+
+#include "intel_drv.h"
+#include "intel_dsi.h"
+#include "i915_drv.h"
+#include <video/mipi_display.h>
+#include <drm/drm_mipi_dsi.h>
+
+#define CONTROL_DISPLAY_BCTRL		(1 << 5)
+#define CONTROL_DISPLAY_DD		(1 << 3)
+#define CONTROL_DISPLAY_BL		(1 << 2)
+
+#define POWER_SAVE_OFF			(0 << 0)
+#define POWER_SAVE_LOW			(1 << 0)
+#define POWER_SAVE_MEDIUM		(2 << 0)
+#define POWER_SAVE_HIGH			(3 << 0)
+#define POWER_SAVE_OUTDOOR_MODE		(4 << 0)
+
+#define PANEL_PWM_MAX_VALUE		0xFF
+
+static u32 dcs_get_backlight(struct intel_connector *connector)
+{
+	struct intel_encoder *encoder = connector->encoder;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct mipi_dsi_device *dsi_device;
+	u8 data;
+	enum port port;
+
+	/* FIXME: Need to take care of 16 bit brightness level */
+	for_each_dsi_port(port, intel_dsi->dcs_backlight_ports) {
+		dsi_device = intel_dsi->dsi_hosts[port]->device;
+		mipi_dsi_dcs_read(dsi_device, MIPI_DCS_GET_DISPLAY_BRIGHTNESS,
+				  &data, sizeof(data));
+		break;
+	}
+
+	return data;
+}
+
+static void dcs_set_backlight(struct intel_connector *connector, u32 level)
+{
+	struct intel_encoder *encoder = connector->encoder;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct mipi_dsi_device *dsi_device;
+	u8 data = level;
+	enum port port;
+
+	/* FIXME: Need to take care of 16 bit brightness level */
+	for_each_dsi_port(port, intel_dsi->dcs_backlight_ports) {
+		dsi_device = intel_dsi->dsi_hosts[port]->device;
+		mipi_dsi_dcs_write(dsi_device, MIPI_DCS_SET_DISPLAY_BRIGHTNESS,
+				   &data, sizeof(data));
+	}
+}
+
+static void dcs_disable_backlight(struct intel_connector *connector)
+{
+	struct intel_encoder *encoder = connector->encoder;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct mipi_dsi_device *dsi_device;
+	enum port port;
+
+	dcs_set_backlight(connector, 0);
+
+	for_each_dsi_port(port, intel_dsi->dcs_cabc_ports) {
+		u8 cabc = POWER_SAVE_OFF;
+
+		dsi_device = intel_dsi->dsi_hosts[port]->device;
+		mipi_dsi_dcs_write(dsi_device, MIPI_DCS_WRITE_POWER_SAVE,
+				   &cabc, sizeof(cabc));
+	}
+
+	for_each_dsi_port(port, intel_dsi->dcs_backlight_ports) {
+		u8 ctrl = 0;
+
+		dsi_device = intel_dsi->dsi_hosts[port]->device;
+
+		mipi_dsi_dcs_read(dsi_device, MIPI_DCS_GET_CONTROL_DISPLAY,
+				  &ctrl, sizeof(ctrl));
+
+		ctrl &= ~CONTROL_DISPLAY_BL;
+		ctrl &= ~CONTROL_DISPLAY_DD;
+		ctrl &= ~CONTROL_DISPLAY_BCTRL;
+
+		mipi_dsi_dcs_write(dsi_device, MIPI_DCS_WRITE_CONTROL_DISPLAY,
+				   &ctrl, sizeof(ctrl));
+	}
+}
+
+static void dcs_enable_backlight(struct intel_connector *connector)
+{
+	struct intel_encoder *encoder = connector->encoder;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_panel *panel = &connector->panel;
+	struct mipi_dsi_device *dsi_device;
+	enum port port;
+
+	for_each_dsi_port(port, intel_dsi->dcs_backlight_ports) {
+		u8 ctrl = 0;
+
+		dsi_device = intel_dsi->dsi_hosts[port]->device;
+
+		mipi_dsi_dcs_read(dsi_device, MIPI_DCS_GET_CONTROL_DISPLAY,
+				  &ctrl, sizeof(ctrl));
+
+		ctrl |= CONTROL_DISPLAY_BL;
+		ctrl |= CONTROL_DISPLAY_DD;
+		ctrl |= CONTROL_DISPLAY_BCTRL;
+
+		mipi_dsi_dcs_write(dsi_device, MIPI_DCS_WRITE_CONTROL_DISPLAY,
+				   &ctrl, sizeof(ctrl));
+	}
+
+	for_each_dsi_port(port, intel_dsi->dcs_cabc_ports) {
+		u8 cabc = POWER_SAVE_MEDIUM;
+
+		dsi_device = intel_dsi->dsi_hosts[port]->device;
+		mipi_dsi_dcs_write(dsi_device, MIPI_DCS_WRITE_POWER_SAVE,
+				   &cabc, sizeof(cabc));
+	}
+
+	dcs_set_backlight(connector, panel->backlight.level);
+}
+
+static int dcs_setup_backlight(struct intel_connector *connector,
+			       enum pipe unused)
+{
+	struct intel_panel *panel = &connector->panel;
+
+	panel->backlight.max = PANEL_PWM_MAX_VALUE;
+	panel->backlight.level = PANEL_PWM_MAX_VALUE;
+
+	return 0;
+}
+
+int intel_dsi_dcs_init_backlight_funcs(struct intel_connector *intel_connector)
+{
+	struct drm_device *dev = intel_connector->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_encoder *encoder = intel_connector->encoder;
+	struct intel_panel *panel = &intel_connector->panel;
+
+	if (dev_priv->vbt.backlight.type != INTEL_BACKLIGHT_DSI_DCS)
+		return -ENODEV;
+
+	if (WARN_ON(encoder->type != INTEL_OUTPUT_DSI))
+		return -EINVAL;
+
+	panel->backlight.setup = dcs_setup_backlight;
+	panel->backlight.enable = dcs_enable_backlight;
+	panel->backlight.disable = dcs_disable_backlight;
+	panel->backlight.set = dcs_set_backlight;
+	panel->backlight.get = dcs_get_backlight;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
index e498f1c3221e..cd154ce6b6c1 100644
--- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
@@ -95,6 +95,24 @@ static struct gpio_map vlv_gpio_table[] = {
 	{ VLV_GPIO_NC_11_PANEL1_BKLTCTL },
 };
 
+#define CHV_GPIO_IDX_START_N		0
+#define CHV_GPIO_IDX_START_E		73
+#define CHV_GPIO_IDX_START_SW		100
+#define CHV_GPIO_IDX_START_SE		198
+
+#define CHV_VBT_MAX_PINS_PER_FMLY	15
+
+#define CHV_GPIO_PAD_CFG0(f, i)		(0x4400 + (f) * 0x400 + (i) * 8)
+#define  CHV_GPIO_GPIOEN		(1 << 15)
+#define  CHV_GPIO_GPIOCFG_GPIO		(0 << 8)
+#define  CHV_GPIO_GPIOCFG_GPO		(1 << 8)
+#define  CHV_GPIO_GPIOCFG_GPI		(2 << 8)
+#define  CHV_GPIO_GPIOCFG_HIZ		(3 << 8)
+#define  CHV_GPIO_GPIOTXSTATE(state)	((!!(state)) << 1)
+
+#define CHV_GPIO_PAD_CFG1(f, i)		(0x4400 + (f) * 0x400 + (i) * 8 + 4)
+#define  CHV_GPIO_CFGLOCK		(1 << 31)
+
 static inline enum port intel_dsi_seq_port_to_port(u8 port)
 {
 	return port ? PORT_C : PORT_A;
@@ -203,13 +221,14 @@ static void vlv_exec_gpio(struct drm_i915_private *dev_priv,
 	map = &vlv_gpio_table[gpio_index];
 
 	if (dev_priv->vbt.dsi.seq_version >= 3) {
-		DRM_DEBUG_KMS("GPIO element v3 not supported\n");
-		return;
+		/* XXX: this assumes vlv_gpio_table only has NC GPIOs. */
+		port = IOSF_PORT_GPIO_NC;
 	} else {
 		if (gpio_source == 0) {
 			port = IOSF_PORT_GPIO_NC;
 		} else if (gpio_source == 1) {
-			port = IOSF_PORT_GPIO_SC;
+			DRM_DEBUG_KMS("SC gpio not supported\n");
+			return;
 		} else {
 			DRM_DEBUG_KMS("unknown gpio source %u\n", gpio_source);
 			return;
@@ -231,10 +250,60 @@ static void vlv_exec_gpio(struct drm_i915_private *dev_priv,
 	mutex_unlock(&dev_priv->sb_lock);
 }
 
+static void chv_exec_gpio(struct drm_i915_private *dev_priv,
+			  u8 gpio_source, u8 gpio_index, bool value)
+{
+	u16 cfg0, cfg1;
+	u16 family_num;
+	u8 port;
+
+	if (dev_priv->vbt.dsi.seq_version >= 3) {
+		if (gpio_index >= CHV_GPIO_IDX_START_SE) {
+			/* XXX: it's unclear whether 255->57 is part of SE. */
+			gpio_index -= CHV_GPIO_IDX_START_SE;
+			port = CHV_IOSF_PORT_GPIO_SE;
+		} else if (gpio_index >= CHV_GPIO_IDX_START_SW) {
+			gpio_index -= CHV_GPIO_IDX_START_SW;
+			port = CHV_IOSF_PORT_GPIO_SW;
+		} else if (gpio_index >= CHV_GPIO_IDX_START_E) {
+			gpio_index -= CHV_GPIO_IDX_START_E;
+			port = CHV_IOSF_PORT_GPIO_E;
+		} else {
+			port = CHV_IOSF_PORT_GPIO_N;
+		}
+	} else {
+		/* XXX: The spec is unclear about CHV GPIO on seq v2 */
+		if (gpio_source != 0) {
+			DRM_DEBUG_KMS("unknown gpio source %u\n", gpio_source);
+			return;
+		}
+
+		if (gpio_index >= CHV_GPIO_IDX_START_E) {
+			DRM_DEBUG_KMS("invalid gpio index %u for GPIO N\n",
+				      gpio_index);
+			return;
+		}
+
+		port = CHV_IOSF_PORT_GPIO_N;
+	}
+
+	family_num = gpio_index / CHV_VBT_MAX_PINS_PER_FMLY;
+	gpio_index = gpio_index % CHV_VBT_MAX_PINS_PER_FMLY;
+
+	cfg0 = CHV_GPIO_PAD_CFG0(family_num, gpio_index);
+	cfg1 = CHV_GPIO_PAD_CFG1(family_num, gpio_index);
+
+	mutex_lock(&dev_priv->sb_lock);
+	vlv_iosf_sb_write(dev_priv, port, cfg1, 0);
+	vlv_iosf_sb_write(dev_priv, port, cfg0,
+			  CHV_GPIO_GPIOCFG_GPO | CHV_GPIO_GPIOTXSTATE(value));
+	mutex_unlock(&dev_priv->sb_lock);
+}
+
 static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 {
 	struct drm_device *dev = intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u8 gpio_source, gpio_index;
 	bool value;
 
@@ -254,6 +323,8 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 
 	if (IS_VALLEYVIEW(dev_priv))
 		vlv_exec_gpio(dev_priv, gpio_source, gpio_index, value);
+	else if (IS_CHERRYVIEW(dev_priv))
+		chv_exec_gpio(dev_priv, gpio_source, gpio_index, value);
 	else
 		DRM_DEBUG_KMS("GPIO element not supported on this platform\n");
 
@@ -398,7 +469,7 @@ static int vbt_panel_get_modes(struct drm_panel *panel)
 	struct vbt_panel *vbt_panel = to_vbt_panel(panel);
 	struct intel_dsi *intel_dsi = vbt_panel->intel_dsi;
 	struct drm_device *dev = intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_display_mode *mode;
 
 	if (!panel->connector)
@@ -426,7 +497,7 @@ static const struct drm_panel_funcs vbt_panel_funcs = {
 struct drm_panel *vbt_panel_init(struct intel_dsi *intel_dsi, u16 panel_id)
 {
 	struct drm_device *dev = intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct mipi_config *mipi_config = dev_priv->vbt.dsi.config;
 	struct mipi_pps_data *pps = dev_priv->vbt.dsi.pps;
 	struct drm_display_mode *mode = dev_priv->vbt.lfp_lvds_vbt_mode;
@@ -578,14 +649,13 @@ struct drm_panel *vbt_panel_init(struct intel_dsi *intel_dsi, u16 panel_id)
 				);
 
 	/*
-	 * Exit zero  is unified val ths_zero and ths_exit
+	 * Exit zero is unified val ths_zero and ths_exit
 	 * minimum value for ths_exit = 110ns
 	 * min (exit_zero_cnt * 2) = 110/UI
 	 * exit_zero_cnt = 55/UI
 	 */
-	 if (exit_zero_cnt < (55 * ui_den / ui_num))
-		if ((55 * ui_den) % ui_num)
-			exit_zero_cnt += 1;
+	if (exit_zero_cnt < (55 * ui_den / ui_num) && (55 * ui_den) % ui_num)
+		exit_zero_cnt += 1;
 
 	/* clk zero count */
 	clk_zero_cnt = DIV_ROUND_UP(
diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/intel_dsi_pll.c
index 1765e6e18f2c..6ab58a01b18e 100644
--- a/drivers/gpu/drm/i915/intel_dsi_pll.c
+++ b/drivers/gpu/drm/i915/intel_dsi_pll.c
@@ -55,12 +55,10 @@ static int dsi_calc_mnp(struct drm_i915_private *dev_priv,
 			struct intel_crtc_state *config,
 			int target_dsi_clk)
 {
-	unsigned int calc_m = 0, calc_p = 0;
 	unsigned int m_min, m_max, p_min = 2, p_max = 6;
 	unsigned int m, n, p;
-	int ref_clk;
-	int delta = target_dsi_clk;
-	u32 m_seed;
+	unsigned int calc_m, calc_p;
+	int delta, ref_clk;
 
 	/* target_dsi_clk is expected in kHz */
 	if (target_dsi_clk < 300000 || target_dsi_clk > 1150000) {
@@ -80,6 +78,10 @@ static int dsi_calc_mnp(struct drm_i915_private *dev_priv,
 		m_max = 92;
 	}
 
+	calc_p = p_min;
+	calc_m = m_min;
+	delta = abs(target_dsi_clk - (m_min * ref_clk) / (p_min * n));
+
 	for (m = m_min; m <= m_max && delta; m++) {
 		for (p = p_min; p <= p_max && delta; p++) {
 			/*
@@ -97,11 +99,10 @@ static int dsi_calc_mnp(struct drm_i915_private *dev_priv,
 	}
 
 	/* register has log2(N1), this works fine for powers of two */
-	n = ffs(n) - 1;
-	m_seed = lfsr_converts[calc_m - 62];
 	config->dsi_pll.ctrl = 1 << (DSI_PLL_P1_POST_DIV_SHIFT + calc_p - 2);
-	config->dsi_pll.div = n << DSI_PLL_N1_DIV_SHIFT |
-		m_seed << DSI_PLL_M1_DIV_SHIFT;
+	config->dsi_pll.div =
+		(ffs(n) - 1) << DSI_PLL_N1_DIV_SHIFT |
+		(u32)lfsr_converts[calc_m - 62] << DSI_PLL_M1_DIV_SHIFT;
 
 	return 0;
 }
@@ -113,7 +114,7 @@ static int dsi_calc_mnp(struct drm_i915_private *dev_priv,
 static int vlv_compute_dsi_pll(struct intel_encoder *encoder,
 			       struct intel_crtc_state *config)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	int ret;
 	u32 dsi_clk;
@@ -234,8 +235,11 @@ static void bxt_disable_dsi_pll(struct intel_encoder *encoder)
 	 * PLL lock should deassert within 200us.
 	 * Wait up to 1ms before timing out.
 	 */
-	if (wait_for((I915_READ(BXT_DSI_PLL_ENABLE)
-					& BXT_DSI_PLL_LOCKED) == 0, 1))
+	if (intel_wait_for_register(dev_priv,
+				    BXT_DSI_PLL_ENABLE,
+				    BXT_DSI_PLL_LOCKED,
+				    0,
+				    1))
 		DRM_ERROR("Timeout waiting for PLL lock deassertion\n");
 }
 
@@ -321,7 +325,7 @@ static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
 	u32 dsi_clk;
 	u32 dsi_ratio;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
 	/* Divide by zero */
 	if (!pipe_bpp) {
@@ -356,7 +360,7 @@ u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
 static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 {
 	u32 temp;
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 
 	temp = I915_READ(MIPI_CTRL(port));
@@ -370,7 +374,7 @@ static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 static void bxt_dsi_program_clocks(struct drm_device *dev, enum port port,
 				   const struct intel_crtc_state *config)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 tmp;
 	u32 dsi_rate = 0;
 	u32 pll_ratio = 0;
@@ -465,7 +469,7 @@ static int bxt_compute_dsi_pll(struct intel_encoder *encoder,
 static void bxt_enable_dsi_pll(struct intel_encoder *encoder,
 			       const struct intel_crtc_state *config)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	enum port port;
 	u32 val;
@@ -486,7 +490,11 @@ static void bxt_enable_dsi_pll(struct intel_encoder *encoder,
 	I915_WRITE(BXT_DSI_PLL_ENABLE, val);
 
 	/* Timeout and fail if PLL not locked */
-	if (wait_for(I915_READ(BXT_DSI_PLL_ENABLE) & BXT_DSI_PLL_LOCKED, 1)) {
+	if (intel_wait_for_register(dev_priv,
+				    BXT_DSI_PLL_ENABLE,
+				    BXT_DSI_PLL_LOCKED,
+				    BXT_DSI_PLL_LOCKED,
+				    1)) {
 		DRM_ERROR("Timed out waiting for DSI PLL to lock\n");
 		return;
 	}
@@ -542,7 +550,7 @@ static void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 {
 	u32 tmp;
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* Clear old configurations */
 	tmp = I915_READ(BXT_MIPI_CLOCK_CTL);
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 286baec979c8..47bdf9dad0d3 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -122,7 +122,7 @@ static struct intel_dvo *intel_attached_dvo(struct drm_connector *connector)
 static bool intel_dvo_connector_get_hw_state(struct intel_connector *connector)
 {
 	struct drm_device *dev = connector->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_dvo *intel_dvo = intel_attached_dvo(&connector->base);
 	u32 tmp;
 
@@ -138,7 +138,7 @@ static bool intel_dvo_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	u32 tmp;
 
@@ -155,7 +155,7 @@ static bool intel_dvo_get_hw_state(struct intel_encoder *encoder,
 static void intel_dvo_get_config(struct intel_encoder *encoder,
 				 struct intel_crtc_state *pipe_config)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	u32 tmp, flags = 0;
 
@@ -176,7 +176,7 @@ static void intel_dvo_get_config(struct intel_encoder *encoder,
 
 static void intel_disable_dvo(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	i915_reg_t dvo_reg = intel_dvo->dev.dvo_reg;
 	u32 temp = I915_READ(dvo_reg);
@@ -188,7 +188,7 @@ static void intel_disable_dvo(struct intel_encoder *encoder)
 
 static void intel_enable_dvo(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	i915_reg_t dvo_reg = intel_dvo->dev.dvo_reg;
@@ -256,7 +256,7 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder,
 static void intel_dvo_pre_enable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
@@ -305,7 +305,7 @@ intel_dvo_detect(struct drm_connector *connector, bool force)
 
 static int intel_dvo_get_modes(struct drm_connector *connector)
 {
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	const struct drm_display_mode *fixed_mode =
 		to_intel_connector(connector)->panel.fixed_mode;
 
@@ -341,6 +341,8 @@ static void intel_dvo_destroy(struct drm_connector *connector)
 static const struct drm_connector_funcs intel_dvo_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.detect = intel_dvo_detect,
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
 	.destroy = intel_dvo_destroy,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.atomic_get_property = intel_connector_atomic_get_property,
@@ -351,7 +353,6 @@ static const struct drm_connector_funcs intel_dvo_connector_funcs = {
 static const struct drm_connector_helper_funcs intel_dvo_connector_helper_funcs = {
 	.mode_valid = intel_dvo_mode_valid,
 	.get_modes = intel_dvo_get_modes,
-	.best_encoder = intel_best_encoder,
 };
 
 static void intel_dvo_enc_destroy(struct drm_encoder *encoder)
@@ -378,7 +379,7 @@ static struct drm_display_mode *
 intel_dvo_get_current_mode(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
 	uint32_t dvo_val = I915_READ(intel_dvo->dev.dvo_reg);
 	struct drm_display_mode *mode = NULL;
@@ -406,9 +407,21 @@ intel_dvo_get_current_mode(struct drm_connector *connector)
 	return mode;
 }
 
+static char intel_dvo_port_name(i915_reg_t dvo_reg)
+{
+	if (i915_mmio_reg_equal(dvo_reg, DVOA))
+		return 'A';
+	else if (i915_mmio_reg_equal(dvo_reg, DVOB))
+		return 'B';
+	else if (i915_mmio_reg_equal(dvo_reg, DVOC))
+		return 'C';
+	else
+		return '?';
+}
+
 void intel_dvo_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *intel_encoder;
 	struct intel_dvo *intel_dvo;
 	struct intel_connector *intel_connector;
@@ -428,8 +441,6 @@ void intel_dvo_init(struct drm_device *dev)
 	intel_dvo->attached_connector = intel_connector;
 
 	intel_encoder = &intel_dvo->base;
-	drm_encoder_init(dev, &intel_encoder->base,
-			 &intel_dvo_enc_funcs, encoder_type, NULL);
 
 	intel_encoder->disable = intel_disable_dvo;
 	intel_encoder->enable = intel_enable_dvo;
@@ -438,7 +449,6 @@ void intel_dvo_init(struct drm_device *dev)
 	intel_encoder->compute_config = intel_dvo_compute_config;
 	intel_encoder->pre_enable = intel_dvo_pre_enable;
 	intel_connector->get_hw_state = intel_dvo_connector_get_hw_state;
-	intel_connector->unregister = intel_connector_unregister;
 
 	/* Now, try to find a controller */
 	for (i = 0; i < ARRAY_SIZE(intel_dvo_devices); i++) {
@@ -496,6 +506,10 @@ void intel_dvo_init(struct drm_device *dev)
 		if (!dvoinit)
 			continue;
 
+		drm_encoder_init(dev, &intel_encoder->base,
+				 &intel_dvo_enc_funcs, encoder_type,
+				 "DVO %c", intel_dvo_port_name(dvo->dvo_reg));
+
 		intel_encoder->type = INTEL_OUTPUT_DVO;
 		intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
 		switch (dvo->type) {
@@ -537,7 +551,6 @@ void intel_dvo_init(struct drm_device *dev)
 			intel_dvo->panel_wants_dither = true;
 		}
 
-		drm_connector_register(connector);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index 647127f3aaff..6a7ad3ed1463 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -124,7 +124,9 @@ static void i8xx_fbc_deactivate(struct drm_i915_private *dev_priv)
 	I915_WRITE(FBC_CONTROL, fbc_ctl);
 
 	/* Wait for compressing bit to clear */
-	if (wait_for((I915_READ(FBC_STATUS) & FBC_STAT_COMPRESSING) == 0, 10)) {
+	if (intel_wait_for_register(dev_priv,
+				    FBC_STATUS, FBC_STAT_COMPRESSING, 0,
+				    10)) {
 		DRM_DEBUG_KMS("FBC idle timed out\n");
 		return;
 	}
@@ -374,8 +376,9 @@ static void intel_fbc_hw_deactivate(struct drm_i915_private *dev_priv)
  * @dev_priv: i915 device instance
  *
  * This function is used to verify the current state of FBC.
+ *
  * FIXME: This should be tracked in the plane config eventually
- *        instead of queried at runtime for most callers.
+ * instead of queried at runtime for most callers.
  */
 bool intel_fbc_is_active(struct drm_i915_private *dev_priv)
 {
@@ -389,7 +392,7 @@ static void intel_fbc_work_fn(struct work_struct *__work)
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_work *work = &fbc->work;
 	struct intel_crtc *crtc = fbc->crtc;
-	struct drm_vblank_crtc *vblank = &dev_priv->dev->vblank[crtc->pipe];
+	struct drm_vblank_crtc *vblank = &dev_priv->drm.vblank[crtc->pipe];
 
 	if (drm_crtc_vblank_get(&crtc->base)) {
 		DRM_ERROR("vblank not available for FBC on pipe %c\n",
@@ -442,7 +445,7 @@ out:
 
 static void intel_fbc_schedule_activation(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_work *work = &fbc->work;
 
@@ -480,10 +483,10 @@ static void intel_fbc_deactivate(struct drm_i915_private *dev_priv)
 		intel_fbc_hw_deactivate(dev_priv);
 }
 
-static bool multiple_pipes_ok(struct intel_crtc *crtc)
+static bool multiple_pipes_ok(struct intel_crtc *crtc,
+			      struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
-	struct drm_plane *primary = crtc->base.primary;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	enum pipe pipe = crtc->pipe;
 
@@ -491,9 +494,7 @@ static bool multiple_pipes_ok(struct intel_crtc *crtc)
 	if (!no_fbc_on_multiple_pipes(dev_priv))
 		return true;
 
-	WARN_ON(!drm_modeset_is_locked(&primary->mutex));
-
-	if (to_intel_plane_state(primary->state)->visible)
+	if (plane_state->visible)
 		fbc->visible_pipes_mask |= (1 << pipe);
 	else
 		fbc->visible_pipes_mask &= ~(1 << pipe);
@@ -554,7 +555,7 @@ again:
 
 static int intel_fbc_alloc_cfb(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct drm_mm_node *uninitialized_var(compressed_llb);
 	int size, fb_cpp, ret;
@@ -685,7 +686,7 @@ static bool pixel_format_is_valid(struct drm_i915_private *dev_priv,
  */
 static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	unsigned int effective_w, effective_h, max_w, max_h;
 
@@ -708,21 +709,16 @@ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
 	return effective_w <= max_w && effective_h <= max_h;
 }
 
-static void intel_fbc_update_state_cache(struct intel_crtc *crtc)
+static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
+					 struct intel_crtc_state *crtc_state,
+					 struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_state_cache *cache = &fbc->state_cache;
-	struct intel_crtc_state *crtc_state =
-		to_intel_crtc_state(crtc->base.state);
-	struct intel_plane_state *plane_state =
-		to_intel_plane_state(crtc->base.primary->state);
 	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj;
 
-	WARN_ON(!drm_modeset_is_locked(&crtc->base.mutex));
-	WARN_ON(!drm_modeset_is_locked(&crtc->base.primary->mutex));
-
 	cache->crtc.mode_flags = crtc_state->base.adjusted_mode.flags;
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		cache->crtc.hsw_bdw_pixel_rate =
@@ -740,7 +736,7 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc)
 
 	/* FIXME: We lack the proper locking here, so only run this on the
 	 * platforms that need. */
-	if (INTEL_INFO(dev_priv)->gen >= 5 && INTEL_INFO(dev_priv)->gen < 7)
+	if (IS_GEN(dev_priv, 5, 6))
 		cache->fb.ilk_ggtt_offset = i915_gem_obj_ggtt_offset(obj);
 	cache->fb.pixel_format = fb->pixel_format;
 	cache->fb.stride = fb->pitches[0];
@@ -750,7 +746,7 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc)
 
 static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_state_cache *cache = &fbc->state_cache;
 
@@ -822,22 +818,16 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 
 static bool intel_fbc_can_choose(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
-	bool enable_by_default = IS_BROADWELL(dev_priv);
 
-	if (intel_vgpu_active(dev_priv->dev)) {
+	if (intel_vgpu_active(dev_priv)) {
 		fbc->no_fbc_reason = "VGPU is active";
 		return false;
 	}
 
-	if (i915.enable_fbc < 0 && !enable_by_default) {
-		fbc->no_fbc_reason = "disabled per chip default";
-		return false;
-	}
-
 	if (!i915.enable_fbc) {
-		fbc->no_fbc_reason = "disabled per module param";
+		fbc->no_fbc_reason = "disabled per module param or by default";
 		return false;
 	}
 
@@ -857,7 +847,7 @@ static bool intel_fbc_can_choose(struct intel_crtc *crtc)
 static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 				     struct intel_fbc_reg_params *params)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_state_cache *cache = &fbc->state_cache;
 
@@ -886,9 +876,11 @@ static bool intel_fbc_reg_params_equal(struct intel_fbc_reg_params *params1,
 	return memcmp(params1, params2, sizeof(*params1)) == 0;
 }
 
-void intel_fbc_pre_update(struct intel_crtc *crtc)
+void intel_fbc_pre_update(struct intel_crtc *crtc,
+			  struct intel_crtc_state *crtc_state,
+			  struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	if (!fbc_supported(dev_priv))
@@ -896,7 +888,7 @@ void intel_fbc_pre_update(struct intel_crtc *crtc)
 
 	mutex_lock(&fbc->lock);
 
-	if (!multiple_pipes_ok(crtc)) {
+	if (!multiple_pipes_ok(crtc, plane_state)) {
 		fbc->no_fbc_reason = "more than one pipe active";
 		goto deactivate;
 	}
@@ -904,7 +896,7 @@ void intel_fbc_pre_update(struct intel_crtc *crtc)
 	if (!fbc->enabled || fbc->crtc != crtc)
 		goto unlock;
 
-	intel_fbc_update_state_cache(crtc);
+	intel_fbc_update_state_cache(crtc, crtc_state, plane_state);
 
 deactivate:
 	intel_fbc_deactivate(dev_priv);
@@ -914,7 +906,7 @@ unlock:
 
 static void __intel_fbc_post_update(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_reg_params old_params;
 
@@ -947,7 +939,7 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 
 void intel_fbc_post_update(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	if (!fbc_supported(dev_priv))
@@ -996,13 +988,13 @@ void intel_fbc_flush(struct drm_i915_private *dev_priv,
 	if (!fbc_supported(dev_priv))
 		return;
 
-	if (origin == ORIGIN_GTT || origin == ORIGIN_FLIP)
-		return;
-
 	mutex_lock(&fbc->lock);
 
 	fbc->busy_bits &= ~frontbuffer_bits;
 
+	if (origin == ORIGIN_GTT || origin == ORIGIN_FLIP)
+		goto out;
+
 	if (!fbc->busy_bits && fbc->enabled &&
 	    (frontbuffer_bits & intel_fbc_get_frontbuffer_bit(fbc))) {
 		if (fbc->active)
@@ -1011,6 +1003,7 @@ void intel_fbc_flush(struct drm_i915_private *dev_priv,
 			__intel_fbc_post_update(fbc->crtc);
 	}
 
+out:
 	mutex_unlock(&fbc->lock);
 }
 
@@ -1088,9 +1081,11 @@ out:
  * intel_fbc_enable multiple times for the same pipe without an
  * intel_fbc_disable in the middle, as long as it is deactivated.
  */
-void intel_fbc_enable(struct intel_crtc *crtc)
+void intel_fbc_enable(struct intel_crtc *crtc,
+		      struct intel_crtc_state *crtc_state,
+		      struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	if (!fbc_supported(dev_priv))
@@ -1101,19 +1096,19 @@ void intel_fbc_enable(struct intel_crtc *crtc)
 	if (fbc->enabled) {
 		WARN_ON(fbc->crtc == NULL);
 		if (fbc->crtc == crtc) {
-			WARN_ON(!crtc->config->enable_fbc);
+			WARN_ON(!crtc_state->enable_fbc);
 			WARN_ON(fbc->active);
 		}
 		goto out;
 	}
 
-	if (!crtc->config->enable_fbc)
+	if (!crtc_state->enable_fbc)
 		goto out;
 
 	WARN_ON(fbc->active);
 	WARN_ON(fbc->crtc != NULL);
 
-	intel_fbc_update_state_cache(crtc);
+	intel_fbc_update_state_cache(crtc, crtc_state, plane_state);
 	if (intel_fbc_alloc_cfb(crtc)) {
 		fbc->no_fbc_reason = "not enough stolen memory";
 		goto out;
@@ -1161,7 +1156,7 @@ static void __intel_fbc_disable(struct drm_i915_private *dev_priv)
  */
 void intel_fbc_disable(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	if (!fbc_supported(dev_priv))
@@ -1215,12 +1210,32 @@ void intel_fbc_init_pipe_state(struct drm_i915_private *dev_priv)
 	if (!no_fbc_on_multiple_pipes(dev_priv))
 		return;
 
-	for_each_intel_crtc(dev_priv->dev, crtc)
+	for_each_intel_crtc(&dev_priv->drm, crtc)
 		if (intel_crtc_active(&crtc->base) &&
 		    to_intel_plane_state(crtc->base.primary->state)->visible)
 			dev_priv->fbc.visible_pipes_mask |= (1 << crtc->pipe);
 }
 
+/*
+ * The DDX driver changes its behavior depending on the value it reads from
+ * i915.enable_fbc, so sanitize it by translating the default value into either
+ * 0 or 1 in order to allow it to know what's going on.
+ *
+ * Notice that this is done at driver initialization and we still allow user
+ * space to change the value during runtime without sanitizing it again. IGT
+ * relies on being able to change i915.enable_fbc at runtime.
+ */
+static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv)
+{
+	if (i915.enable_fbc >= 0)
+		return !!i915.enable_fbc;
+
+	if (IS_BROADWELL(dev_priv))
+		return 1;
+
+	return 0;
+}
+
 /**
  * intel_fbc_init - Initialize FBC
  * @dev_priv: the i915 device
@@ -1238,6 +1253,9 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
 	fbc->active = false;
 	fbc->work.scheduled = false;
 
+	i915.enable_fbc = intel_sanitize_fbc_option(dev_priv);
+	DRM_DEBUG_KMS("Sanitized enable_fbc value: %d\n", i915.enable_fbc);
+
 	if (!HAS_FBC(dev_priv)) {
 		fbc->no_fbc_reason = "unsupported by this chipset";
 		return;
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index ab8d09a81f14..86b00c6db1a6 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -150,10 +150,10 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 	if (size * 2 < ggtt->stolen_usable_size)
 		obj = i915_gem_object_create_stolen(dev, size);
 	if (obj == NULL)
-		obj = i915_gem_alloc_object(dev, size);
-	if (!obj) {
+		obj = i915_gem_object_create(dev, size);
+	if (IS_ERR(obj)) {
 		DRM_ERROR("failed to allocate framebuffer\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(obj);
 		goto out;
 	}
 
@@ -186,9 +186,11 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	struct fb_info *info;
 	struct drm_framebuffer *fb;
+	struct i915_vma *vma;
 	struct drm_i915_gem_object *obj;
-	int size, ret;
 	bool prealloc = false;
+	void *vaddr;
+	int ret;
 
 	if (intel_fb &&
 	    (sizes->fb_width > intel_fb->base.width ||
@@ -214,7 +216,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	}
 
 	obj = intel_fb->obj;
-	size = obj->base.size;
 
 	mutex_lock(&dev->struct_mutex);
 
@@ -244,22 +245,23 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->flags = FBINFO_DEFAULT | FBINFO_CAN_FORCE_OUTPUT;
 	info->fbops = &intelfb_ops;
 
+	vma = i915_gem_obj_to_ggtt(obj);
+
 	/* setup aperture base/size for vesafb takeover */
 	info->apertures->ranges[0].base = dev->mode_config.fb_base;
 	info->apertures->ranges[0].size = ggtt->mappable_end;
 
-	info->fix.smem_start = dev->mode_config.fb_base + i915_gem_obj_ggtt_offset(obj);
-	info->fix.smem_len = size;
+	info->fix.smem_start = dev->mode_config.fb_base + vma->node.start;
+	info->fix.smem_len = vma->node.size;
 
-	info->screen_base =
-		ioremap_wc(ggtt->mappable_base + i915_gem_obj_ggtt_offset(obj),
-			   size);
-	if (!info->screen_base) {
+	vaddr = i915_vma_pin_iomap(vma);
+	if (IS_ERR(vaddr)) {
 		DRM_ERROR("Failed to remap framebuffer into virtual memory\n");
-		ret = -ENOSPC;
+		ret = PTR_ERR(vaddr);
 		goto out_destroy_fbi;
 	}
-	info->screen_size = size;
+	info->screen_base = vaddr;
+	info->screen_size = vma->node.size;
 
 	/* This driver doesn't need a VT switch to restore the mode on resume */
 	info->skip_vt_switch = true;
@@ -287,7 +289,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 out_destroy_fbi:
 	drm_fb_helper_release_fbi(helper);
 out_unpin:
-	i915_gem_object_ggtt_unpin(obj);
+	intel_unpin_fb_obj(&ifbdev->fb->base, BIT(DRM_ROTATE_0));
 out_unlock:
 	mutex_unlock(&dev->struct_mutex);
 	return ret;
@@ -360,23 +362,24 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 				    bool *enabled, int width, int height)
 {
 	struct drm_device *dev = fb_helper->dev;
+	unsigned long conn_configured, mask;
+	unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG);
 	int i, j;
 	bool *save_enabled;
 	bool fallback = true;
 	int num_connectors_enabled = 0;
 	int num_connectors_detected = 0;
-	uint64_t conn_configured = 0, mask;
 	int pass = 0;
 
-	save_enabled = kcalloc(fb_helper->connector_count, sizeof(bool),
-			       GFP_KERNEL);
+	save_enabled = kcalloc(count, sizeof(bool), GFP_KERNEL);
 	if (!save_enabled)
 		return false;
 
-	memcpy(save_enabled, enabled, fb_helper->connector_count);
-	mask = (1 << fb_helper->connector_count) - 1;
+	memcpy(save_enabled, enabled, count);
+	mask = BIT(count) - 1;
+	conn_configured = 0;
 retry:
-	for (i = 0; i < fb_helper->connector_count; i++) {
+	for (i = 0; i < count; i++) {
 		struct drm_fb_helper_connector *fb_conn;
 		struct drm_connector *connector;
 		struct drm_encoder *encoder;
@@ -386,7 +389,7 @@ retry:
 		fb_conn = fb_helper->connector_info[i];
 		connector = fb_conn->connector;
 
-		if (conn_configured & (1 << i))
+		if (conn_configured & BIT(i))
 			continue;
 
 		if (pass == 0 && !connector->has_tile)
@@ -398,7 +401,7 @@ retry:
 		if (!enabled[i]) {
 			DRM_DEBUG_KMS("connector %s not enabled, skipping\n",
 				      connector->name);
-			conn_configured |= (1 << i);
+			conn_configured |= BIT(i);
 			continue;
 		}
 
@@ -417,7 +420,7 @@ retry:
 			DRM_DEBUG_KMS("connector %s has no encoder or crtc, skipping\n",
 				      connector->name);
 			enabled[i] = false;
-			conn_configured |= (1 << i);
+			conn_configured |= BIT(i);
 			continue;
 		}
 
@@ -430,14 +433,15 @@ retry:
 			intel_crtc->lut_b[j] = j;
 		}
 
-		new_crtc = intel_fb_helper_crtc(fb_helper, connector->state->crtc);
+		new_crtc = intel_fb_helper_crtc(fb_helper,
+						connector->state->crtc);
 
 		/*
 		 * Make sure we're not trying to drive multiple connectors
 		 * with a single CRTC, since our cloning support may not
 		 * match the BIOS.
 		 */
-		for (j = 0; j < fb_helper->connector_count; j++) {
+		for (j = 0; j < count; j++) {
 			if (crtcs[j] == new_crtc) {
 				DRM_DEBUG_KMS("fallback: cloned configuration\n");
 				goto bail;
@@ -488,15 +492,15 @@ retry:
 		}
 		crtcs[i] = new_crtc;
 
-		DRM_DEBUG_KMS("connector %s on pipe %c [CRTC:%d]: %dx%d%s\n",
+		DRM_DEBUG_KMS("connector %s on [CRTC:%d:%s]: %dx%d%s\n",
 			      connector->name,
-			      pipe_name(to_intel_crtc(connector->state->crtc)->pipe),
 			      connector->state->crtc->base.id,
+			      connector->state->crtc->name,
 			      modes[i]->hdisplay, modes[i]->vdisplay,
 			      modes[i]->flags & DRM_MODE_FLAG_INTERLACE ? "i" :"");
 
 		fallback = false;
-		conn_configured |= (1 << i);
+		conn_configured |= BIT(i);
 	}
 
 	if ((conn_configured & mask) != mask) {
@@ -520,7 +524,7 @@ retry:
 	if (fallback) {
 bail:
 		DRM_DEBUG_KMS("Not using firmware configuration\n");
-		memcpy(enabled, save_enabled, fb_helper->connector_count);
+		memcpy(enabled, save_enabled, count);
 		kfree(save_enabled);
 		return false;
 	}
@@ -536,8 +540,7 @@ static const struct drm_fb_helper_funcs intel_fb_helper_funcs = {
 	.fb_probe = intelfb_create,
 };
 
-static void intel_fbdev_destroy(struct drm_device *dev,
-				struct intel_fbdev *ifbdev)
+static void intel_fbdev_destroy(struct intel_fbdev *ifbdev)
 {
 	/* We rely on the object-free to release the VMA pinning for
 	 * the info->screen_base mmaping. Leaking the VMA is simpler than
@@ -550,9 +553,14 @@ static void intel_fbdev_destroy(struct drm_device *dev,
 	drm_fb_helper_fini(&ifbdev->helper);
 
 	if (ifbdev->fb) {
-		drm_framebuffer_unregister_private(&ifbdev->fb->base);
+		mutex_lock(&ifbdev->helper.dev->struct_mutex);
+		intel_unpin_fb_obj(&ifbdev->fb->base, BIT(DRM_ROTATE_0));
+		mutex_unlock(&ifbdev->helper.dev->struct_mutex);
+
 		drm_framebuffer_remove(&ifbdev->fb->base);
 	}
+
+	kfree(ifbdev);
 }
 
 /*
@@ -685,9 +693,9 @@ out:
 
 static void intel_fbdev_suspend_worker(struct work_struct *work)
 {
-	intel_fbdev_set_suspend(container_of(work,
-					     struct drm_i915_private,
-					     fbdev_suspend_work)->dev,
+	intel_fbdev_set_suspend(&container_of(work,
+					      struct drm_i915_private,
+					      fbdev_suspend_work)->drm,
 				FBINFO_STATE_RUNNING,
 				true);
 }
@@ -695,7 +703,7 @@ static void intel_fbdev_suspend_worker(struct work_struct *work)
 int intel_fbdev_init(struct drm_device *dev)
 {
 	struct intel_fbdev *ifbdev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int ret;
 
 	if (WARN_ON(INTEL_INFO(dev)->num_pipes == 0))
@@ -717,8 +725,6 @@ int intel_fbdev_init(struct drm_device *dev)
 		return ret;
 	}
 
-	ifbdev->helper.atomic = true;
-
 	dev_priv->fbdev = ifbdev;
 	INIT_WORK(&dev_priv->fbdev_suspend_work, intel_fbdev_suspend_worker);
 
@@ -729,38 +735,50 @@ int intel_fbdev_init(struct drm_device *dev)
 
 static void intel_fbdev_initial_config(void *data, async_cookie_t cookie)
 {
-	struct drm_i915_private *dev_priv = data;
-	struct intel_fbdev *ifbdev = dev_priv->fbdev;
+	struct intel_fbdev *ifbdev = data;
 
 	/* Due to peculiar init order wrt to hpd handling this is separate. */
 	if (drm_fb_helper_initial_config(&ifbdev->helper,
 					 ifbdev->preferred_bpp))
-		intel_fbdev_fini(dev_priv->dev);
+		intel_fbdev_fini(ifbdev->helper.dev);
 }
 
 void intel_fbdev_initial_config_async(struct drm_device *dev)
 {
-	async_schedule(intel_fbdev_initial_config, to_i915(dev));
+	struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
+
+	ifbdev->cookie = async_schedule(intel_fbdev_initial_config, ifbdev);
+}
+
+static void intel_fbdev_sync(struct intel_fbdev *ifbdev)
+{
+	if (!ifbdev->cookie)
+		return;
+
+	/* Only serialises with all preceding async calls, hence +1 */
+	async_synchronize_cookie(ifbdev->cookie + 1);
+	ifbdev->cookie = 0;
 }
 
 void intel_fbdev_fini(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	if (!dev_priv->fbdev)
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_fbdev *ifbdev = dev_priv->fbdev;
+
+	if (!ifbdev)
 		return;
 
 	flush_work(&dev_priv->fbdev_suspend_work);
-
 	if (!current_is_async())
-		async_synchronize_full();
-	intel_fbdev_destroy(dev, dev_priv->fbdev);
-	kfree(dev_priv->fbdev);
+		intel_fbdev_sync(ifbdev);
+
+	intel_fbdev_destroy(ifbdev);
 	dev_priv->fbdev = NULL;
 }
 
 void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_fbdev *ifbdev = dev_priv->fbdev;
 	struct fb_info *info;
 
@@ -809,7 +827,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous
 
 void intel_fbdev_output_poll_changed(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	if (dev_priv->fbdev)
 		drm_fb_helper_hotplug_event(&dev_priv->fbdev->helper);
 }
@@ -817,13 +835,15 @@ void intel_fbdev_output_poll_changed(struct drm_device *dev)
 void intel_fbdev_restore_mode(struct drm_device *dev)
 {
 	int ret;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_fbdev *ifbdev = dev_priv->fbdev;
 	struct drm_fb_helper *fb_helper;
 
 	if (!ifbdev)
 		return;
 
+	intel_fbdev_sync(ifbdev);
+
 	fb_helper = &ifbdev->helper;
 
 	ret = drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
diff --git a/drivers/gpu/drm/i915/intel_fifo_underrun.c b/drivers/gpu/drm/i915/intel_fifo_underrun.c
index 9be839a242f9..2aa744081f09 100644
--- a/drivers/gpu/drm/i915/intel_fifo_underrun.c
+++ b/drivers/gpu/drm/i915/intel_fifo_underrun.c
@@ -50,7 +50,7 @@
 
 static bool ivb_can_enable_err_int(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc;
 	enum pipe pipe;
 
@@ -68,7 +68,7 @@ static bool ivb_can_enable_err_int(struct drm_device *dev)
 
 static bool cpt_can_enable_serr_int(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe;
 	struct intel_crtc *crtc;
 
@@ -105,7 +105,7 @@ static void i9xx_set_fifo_underrun_reporting(struct drm_device *dev,
 					     enum pipe pipe,
 					     bool enable, bool old)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t reg = PIPESTAT(pipe);
 	u32 pipestat = I915_READ(reg) & 0xffff0000;
 
@@ -123,7 +123,7 @@ static void i9xx_set_fifo_underrun_reporting(struct drm_device *dev,
 static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev,
 						 enum pipe pipe, bool enable)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t bit = (pipe == PIPE_A) ? DE_PIPEA_FIFO_UNDERRUN :
 					  DE_PIPEB_FIFO_UNDERRUN;
 
@@ -154,7 +154,7 @@ static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev,
 						  enum pipe pipe,
 						  bool enable, bool old)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	if (enable) {
 		I915_WRITE(GEN7_ERR_INT, ERR_INT_FIFO_UNDERRUN(pipe));
 
@@ -176,7 +176,7 @@ static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev,
 static void broadwell_set_fifo_underrun_reporting(struct drm_device *dev,
 						  enum pipe pipe, bool enable)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (enable)
 		bdw_enable_pipe_irq(dev_priv, pipe, GEN8_PIPE_FIFO_UNDERRUN);
@@ -188,7 +188,7 @@ static void ibx_set_fifo_underrun_reporting(struct drm_device *dev,
 					    enum transcoder pch_transcoder,
 					    bool enable)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t bit = (pch_transcoder == TRANSCODER_A) ?
 		       SDE_TRANSA_FIFO_UNDER : SDE_TRANSB_FIFO_UNDER;
 
@@ -220,7 +220,7 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev,
 					    enum transcoder pch_transcoder,
 					    bool enable, bool old)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (enable) {
 		I915_WRITE(SERR_INT,
@@ -244,7 +244,7 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev,
 static bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
 						    enum pipe pipe, bool enable)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	bool old;
@@ -289,7 +289,7 @@ bool intel_set_cpu_fifo_underrun_reporting(struct drm_i915_private *dev_priv,
 	bool ret;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	ret = __intel_set_cpu_fifo_underrun_reporting(dev_priv->dev, pipe,
+	ret = __intel_set_cpu_fifo_underrun_reporting(&dev_priv->drm, pipe,
 						      enable);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
@@ -334,10 +334,12 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_i915_private *dev_priv,
 	intel_crtc->pch_fifo_underrun_disabled = !enable;
 
 	if (HAS_PCH_IBX(dev_priv))
-		ibx_set_fifo_underrun_reporting(dev_priv->dev, pch_transcoder,
+		ibx_set_fifo_underrun_reporting(&dev_priv->drm,
+						pch_transcoder,
 						enable);
 	else
-		cpt_set_fifo_underrun_reporting(dev_priv->dev, pch_transcoder,
+		cpt_set_fifo_underrun_reporting(&dev_priv->drm,
+						pch_transcoder,
 						enable, old);
 
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
@@ -405,7 +407,7 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv)
 
 	spin_lock_irq(&dev_priv->irq_lock);
 
-	for_each_intel_crtc(dev_priv->dev, crtc) {
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
 		if (crtc->cpu_fifo_underrun_disabled)
 			continue;
 
@@ -432,7 +434,7 @@ void intel_check_pch_fifo_underruns(struct drm_i915_private *dev_priv)
 
 	spin_lock_irq(&dev_priv->irq_lock);
 
-	for_each_intel_crtc(dev_priv->dev, crtc) {
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
 		if (crtc->pch_fifo_underrun_disabled)
 			continue;
 
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index 9d79c4c3e256..3e3e743740c0 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -26,6 +26,7 @@
 
 #include "intel_guc_fwif.h"
 #include "i915_guc_reg.h"
+#include "intel_ringbuffer.h"
 
 struct drm_i915_gem_request;
 
@@ -48,14 +49,23 @@ struct drm_i915_gem_request;
  * queue (a circular array of work items), again described in the process
  * descriptor. Work queue pages are mapped momentarily as required.
  *
- * Finally, we also keep a few statistics here, including the number of
- * submissions to each engine, and a record of the last submission failure
- * (if any).
+ * We also keep a few statistics on failures. Ideally, these should all
+ * be zero!
+ *   no_wq_space: times that the submission pre-check found no space was
+ *                available in the work queue (note, the queue is shared,
+ *                not per-engine). It is OK for this to be nonzero, but
+ *                it should not be huge!
+ *   q_fail: failed to enqueue a work item. This should never happen,
+ *           because we check for space beforehand.
+ *   b_fail: failed to ring the doorbell. This should never happen, unless
+ *           somehow the hardware misbehaves, or maybe if the GuC firmware
+ *           crashes? We probably need to reset the GPU to recover.
+ *   retcode: errno from last guc_submit()
  */
 struct i915_guc_client {
 	struct drm_i915_gem_object *client_obj;
 	void *client_base;		/* first page (only) of above	*/
-	struct intel_context *owner;
+	struct i915_gem_context *owner;
 	struct intel_guc *guc;
 	uint32_t priority;
 	uint32_t ctx_index;
@@ -71,12 +81,13 @@ struct i915_guc_client {
 	uint32_t wq_tail;
 	uint32_t unused;		/* Was 'wq_head'		*/
 
-	/* GuC submission statistics & status */
-	uint64_t submissions[GUC_MAX_ENGINES_NUM];
-	uint32_t q_fail;
+	uint32_t no_wq_space;
+	uint32_t q_fail;		/* No longer used		*/
 	uint32_t b_fail;
 	int retcode;
-	int spare;			/* pad to 32 DWords		*/
+
+	/* Per-engine counts of GuC submissions */
+	uint64_t submissions[I915_NUM_ENGINES];
 };
 
 enum intel_guc_fw_status {
@@ -133,25 +144,24 @@ struct intel_guc {
 	uint32_t action_fail;		/* Total number of failures	*/
 	int32_t action_err;		/* Last error code		*/
 
-	uint64_t submissions[GUC_MAX_ENGINES_NUM];
-	uint32_t last_seqno[GUC_MAX_ENGINES_NUM];
+	uint64_t submissions[I915_NUM_ENGINES];
+	uint32_t last_seqno[I915_NUM_ENGINES];
 };
 
 /* intel_guc_loader.c */
-extern void intel_guc_ucode_init(struct drm_device *dev);
-extern int intel_guc_ucode_load(struct drm_device *dev);
-extern void intel_guc_ucode_fini(struct drm_device *dev);
+extern void intel_guc_init(struct drm_device *dev);
+extern int intel_guc_setup(struct drm_device *dev);
+extern void intel_guc_fini(struct drm_device *dev);
 extern const char *intel_guc_fw_status_repr(enum intel_guc_fw_status status);
 extern int intel_guc_suspend(struct drm_device *dev);
 extern int intel_guc_resume(struct drm_device *dev);
 
 /* i915_guc_submission.c */
-int i915_guc_submission_init(struct drm_device *dev);
-int i915_guc_submission_enable(struct drm_device *dev);
-int i915_guc_submit(struct i915_guc_client *client,
-		    struct drm_i915_gem_request *rq);
-void i915_guc_submission_disable(struct drm_device *dev);
-void i915_guc_submission_fini(struct drm_device *dev);
-int i915_guc_wq_check_space(struct i915_guc_client *client);
+int i915_guc_submission_init(struct drm_i915_private *dev_priv);
+int i915_guc_submission_enable(struct drm_i915_private *dev_priv);
+int i915_guc_wq_check_space(struct drm_i915_gem_request *rq);
+int i915_guc_submit(struct drm_i915_gem_request *rq);
+void i915_guc_submission_disable(struct drm_i915_private *dev_priv);
+void i915_guc_submission_fini(struct drm_i915_private *dev_priv);
 
 #endif
diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h
index 2de57ffe5e18..944786d7075b 100644
--- a/drivers/gpu/drm/i915/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/intel_guc_fwif.h
@@ -71,7 +71,8 @@
 #define   WQ_WORKLOAD_TOUCH		(2 << WQ_WORKLOAD_SHIFT)
 
 #define WQ_RING_TAIL_SHIFT		20
-#define WQ_RING_TAIL_MASK		(0x7FF << WQ_RING_TAIL_SHIFT)
+#define WQ_RING_TAIL_MAX		0x7FF	/* 2^11 QWords */
+#define WQ_RING_TAIL_MASK		(WQ_RING_TAIL_MAX << WQ_RING_TAIL_SHIFT)
 
 #define GUC_DOORBELL_ENABLED		1
 #define GUC_DOORBELL_DISABLED		0
diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c
index 876e5da44c4e..605c69658d2c 100644
--- a/drivers/gpu/drm/i915/intel_guc_loader.c
+++ b/drivers/gpu/drm/i915/intel_guc_loader.c
@@ -59,9 +59,15 @@
  *
  */
 
-#define I915_SKL_GUC_UCODE "i915/skl_guc_ver6.bin"
+#define I915_SKL_GUC_UCODE "i915/skl_guc_ver6_1.bin"
 MODULE_FIRMWARE(I915_SKL_GUC_UCODE);
 
+#define I915_BXT_GUC_UCODE "i915/bxt_guc_ver8_7.bin"
+MODULE_FIRMWARE(I915_BXT_GUC_UCODE);
+
+#define I915_KBL_GUC_UCODE "i915/kbl_guc_ver9_14.bin"
+MODULE_FIRMWARE(I915_KBL_GUC_UCODE);
+
 /* User-friendly representation of an enum */
 const char *intel_guc_fw_status_repr(enum intel_guc_fw_status status)
 {
@@ -84,7 +90,7 @@ static void direct_interrupts_to_host(struct drm_i915_private *dev_priv)
 	struct intel_engine_cs *engine;
 	int irqs;
 
-	/* tell all command streamers NOT to forward interrupts and vblank to GuC */
+	/* tell all command streamers NOT to forward interrupts or vblank to GuC */
 	irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_NEVER);
 	irqs |= _MASKED_BIT_DISABLE(GFX_INTERRUPT_STEERING);
 	for_each_engine(engine, dev_priv)
@@ -100,10 +106,10 @@ static void direct_interrupts_to_guc(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
 	int irqs;
+	u32 tmp;
 
-	/* tell all command streamers to forward interrupts and vblank to GuC */
-	irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_ALWAYS);
-	irqs |= _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING);
+	/* tell all command streamers to forward interrupts (but not vblank) to GuC */
+	irqs = _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING);
 	for_each_engine(engine, dev_priv)
 		I915_WRITE(RING_MODE_GEN7(engine), irqs);
 
@@ -114,6 +120,16 @@ static void direct_interrupts_to_guc(struct drm_i915_private *dev_priv)
 	I915_WRITE(GUC_BCS_RCS_IER, ~irqs);
 	I915_WRITE(GUC_VCS2_VCS1_IER, ~irqs);
 	I915_WRITE(GUC_WD_VECS_IER, ~irqs);
+
+	/*
+	 * If GuC has routed PM interrupts to itself, don't keep it.
+	 * and keep other interrupts those are unmasked by GuC.
+	*/
+	tmp = I915_READ(GEN6_PMINTRMSK);
+	if (tmp & GEN8_PMINTR_REDIRECT_TO_NON_DISP) {
+		dev_priv->rps.pm_intr_keep |= ~(tmp & ~GEN8_PMINTR_REDIRECT_TO_NON_DISP);
+		dev_priv->rps.pm_intr_keep &= ~GEN8_PMINTR_REDIRECT_TO_NON_DISP;
+	}
 }
 
 static u32 get_gttype(struct drm_i915_private *dev_priv)
@@ -281,13 +297,24 @@ static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
+static u32 guc_wopcm_size(struct drm_i915_private *dev_priv)
+{
+	u32 wopcm_size = GUC_WOPCM_TOP;
+
+	/* On BXT, the top of WOPCM is reserved for RC6 context */
+	if (IS_BROXTON(dev_priv))
+		wopcm_size -= BXT_GUC_WOPCM_RC6_RESERVED;
+
+	return wopcm_size;
+}
+
 /*
  * Load the GuC firmware blob into the MinuteIA.
  */
 static int guc_ucode_xfer(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	int ret;
 
 	ret = i915_gem_object_set_to_gtt_domain(guc_fw->guc_fw_obj, false);
@@ -308,7 +335,7 @@ static int guc_ucode_xfer(struct drm_i915_private *dev_priv)
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
 	/* init WOPCM */
-	I915_WRITE(GUC_WOPCM_SIZE, GUC_WOPCM_SIZE_VALUE);
+	I915_WRITE(GUC_WOPCM_SIZE, guc_wopcm_size(dev_priv));
 	I915_WRITE(DMA_GUC_WOPCM_OFFSET, GUC_WOPCM_OFFSET_VALUE);
 
 	/* Enable MIA caching. GuC clock gating is disabled. */
@@ -372,66 +399,63 @@ static int i915_reset_guc(struct drm_i915_private *dev_priv)
 }
 
 /**
- * intel_guc_ucode_load() - load GuC uCode into the device
+ * intel_guc_setup() - finish preparing the GuC for activity
  * @dev:	drm device
  *
  * Called from gem_init_hw() during driver loading and also after a GPU reset.
  *
+ * The main action required here it to load the GuC uCode into the device.
  * The firmware image should have already been fetched into memory by the
- * earlier call to intel_guc_ucode_init(), so here we need only check that
- * is succeeded, and then transfer the image to the h/w.
+ * earlier call to intel_guc_init(), so here we need only check that worked,
+ * and then transfer the image to the h/w.
  *
  * Return:	non-zero code on error
  */
-int intel_guc_ucode_load(struct drm_device *dev)
+int intel_guc_setup(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
-	int retries, err = 0;
+	const char *fw_path = guc_fw->guc_fw_path;
+	int retries, ret, err;
 
-	if (!i915.enable_guc_submission)
-		return 0;
-
-	DRM_DEBUG_DRIVER("GuC fw status: fetch %s, load %s\n",
+	DRM_DEBUG_DRIVER("GuC fw status: path %s, fetch %s, load %s\n",
+		fw_path,
 		intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
 		intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
 
-	direct_interrupts_to_host(dev_priv);
-
-	if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_NONE)
-		return 0;
-
-	if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_SUCCESS &&
-	    guc_fw->guc_fw_load_status == GUC_FIRMWARE_FAIL)
-		return -ENOEXEC;
-
-	guc_fw->guc_fw_load_status = GUC_FIRMWARE_PENDING;
-
-	DRM_DEBUG_DRIVER("GuC fw fetch status %s\n",
-		intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status));
-
-	switch (guc_fw->guc_fw_fetch_status) {
-	case GUC_FIRMWARE_FAIL:
-		/* something went wrong :( */
-		err = -EIO;
+	/* Loading forbidden, or no firmware to load? */
+	if (!i915.enable_guc_loading) {
+		err = 0;
 		goto fail;
-
-	case GUC_FIRMWARE_NONE:
-	case GUC_FIRMWARE_PENDING:
-	default:
-		/* "can't happen" */
-		WARN_ONCE(1, "GuC fw %s invalid guc_fw_fetch_status %s [%d]\n",
-			guc_fw->guc_fw_path,
-			intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
-			guc_fw->guc_fw_fetch_status);
+	} else if (fw_path == NULL) {
+		/* Device is known to have no uCode (e.g. no GuC) */
 		err = -ENXIO;
 		goto fail;
+	} else if (*fw_path == '\0') {
+		/* Device has a GuC but we don't know what f/w to load? */
+		DRM_INFO("No GuC firmware known for this platform\n");
+		err = -ENODEV;
+		goto fail;
+	}
 
-	case GUC_FIRMWARE_SUCCESS:
-		break;
+	/* Fetch failed, or already fetched but failed to load? */
+	if (guc_fw->guc_fw_fetch_status != GUC_FIRMWARE_SUCCESS) {
+		err = -EIO;
+		goto fail;
+	} else if (guc_fw->guc_fw_load_status == GUC_FIRMWARE_FAIL) {
+		err = -ENOEXEC;
+		goto fail;
 	}
 
-	err = i915_guc_submission_init(dev);
+	direct_interrupts_to_host(dev_priv);
+
+	guc_fw->guc_fw_load_status = GUC_FIRMWARE_PENDING;
+
+	DRM_DEBUG_DRIVER("GuC fw status: fetch %s, load %s\n",
+		intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
+		intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
+
+	err = i915_guc_submission_init(dev_priv);
 	if (err)
 		goto fail;
 
@@ -448,7 +472,7 @@ int intel_guc_ucode_load(struct drm_device *dev)
 		 */
 		err = i915_reset_guc(dev_priv);
 		if (err) {
-			DRM_ERROR("GuC reset failed, err %d\n", err);
+			DRM_ERROR("GuC reset failed: %d\n", err);
 			goto fail;
 		}
 
@@ -459,8 +483,8 @@ int intel_guc_ucode_load(struct drm_device *dev)
 		if (--retries == 0)
 			goto fail;
 
-		DRM_INFO("GuC fw load failed, err %d; will reset and "
-			"retry %d more time(s)\n", err, retries);
+		DRM_INFO("GuC fw load failed: %d; will reset and "
+			 "retry %d more time(s)\n", err, retries);
 	}
 
 	guc_fw->guc_fw_load_status = GUC_FIRMWARE_SUCCESS;
@@ -470,10 +494,7 @@ int intel_guc_ucode_load(struct drm_device *dev)
 		intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
 
 	if (i915.enable_guc_submission) {
-		/* The execbuf_client will be recreated. Release it first. */
-		i915_guc_submission_disable(dev);
-
-		err = i915_guc_submission_enable(dev);
+		err = i915_guc_submission_enable(dev_priv);
 		if (err)
 			goto fail;
 		direct_interrupts_to_guc(dev_priv);
@@ -482,15 +503,50 @@ int intel_guc_ucode_load(struct drm_device *dev)
 	return 0;
 
 fail:
-	DRM_ERROR("GuC firmware load failed, err %d\n", err);
 	if (guc_fw->guc_fw_load_status == GUC_FIRMWARE_PENDING)
 		guc_fw->guc_fw_load_status = GUC_FIRMWARE_FAIL;
 
 	direct_interrupts_to_host(dev_priv);
-	i915_guc_submission_disable(dev);
-	i915_guc_submission_fini(dev);
+	i915_guc_submission_disable(dev_priv);
+	i915_guc_submission_fini(dev_priv);
 
-	return err;
+	/*
+	 * We've failed to load the firmware :(
+	 *
+	 * Decide whether to disable GuC submission and fall back to
+	 * execlist mode, and whether to hide the error by returning
+	 * zero or to return -EIO, which the caller will treat as a
+	 * nonfatal error (i.e. it doesn't prevent driver load, but
+	 * marks the GPU as wedged until reset).
+	 */
+	if (i915.enable_guc_loading > 1) {
+		ret = -EIO;
+	} else if (i915.enable_guc_submission > 1) {
+		ret = -EIO;
+	} else {
+		ret = 0;
+	}
+
+	if (err == 0 && !HAS_GUC_UCODE(dev))
+		;	/* Don't mention the GuC! */
+	else if (err == 0)
+		DRM_INFO("GuC firmware load skipped\n");
+	else if (ret != -EIO)
+		DRM_INFO("GuC firmware load failed: %d\n", err);
+	else
+		DRM_ERROR("GuC firmware load failed: %d\n", err);
+
+	if (i915.enable_guc_submission) {
+		if (fw_path == NULL)
+			DRM_INFO("GuC submission without firmware not supported\n");
+		if (ret == 0)
+			DRM_INFO("Falling back from GuC submission to execlist mode\n");
+		else
+			DRM_ERROR("GuC init failed: %d\n", ret);
+	}
+	i915.enable_guc_submission = 0;
+
+	return ret;
 }
 
 static void guc_fw_fetch(struct drm_device *dev, struct intel_guc_fw *guc_fw)
@@ -552,9 +608,7 @@ static void guc_fw_fetch(struct drm_device *dev, struct intel_guc_fw *guc_fw)
 
 	/* Header and uCode will be loaded to WOPCM. Size of the two. */
 	size = guc_fw->header_size + guc_fw->ucode_size;
-
-	/* Top 32k of WOPCM is reserved (8K stack + 24k RC6 context). */
-	if (size > GUC_WOPCM_SIZE_VALUE - 0x8000) {
+	if (size > guc_wopcm_size(to_i915(dev))) {
 		DRM_ERROR("Firmware is too large to fit in WOPCM\n");
 		goto fail;
 	}
@@ -617,22 +671,25 @@ fail:
 }
 
 /**
- * intel_guc_ucode_init() - define parameters and fetch firmware
+ * intel_guc_init() - define parameters and fetch firmware
  * @dev:	drm device
  *
  * Called early during driver load, but after GEM is initialised.
  *
  * The firmware will be transferred to the GuC's memory later,
- * when intel_guc_ucode_load() is called.
+ * when intel_guc_setup() is called.
  */
-void intel_guc_ucode_init(struct drm_device *dev)
+void intel_guc_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
 	const char *fw_path;
 
-	if (!HAS_GUC_SCHED(dev))
-		i915.enable_guc_submission = false;
+	/* A negative value means "use platform default" */
+	if (i915.enable_guc_loading < 0)
+		i915.enable_guc_loading = HAS_GUC_UCODE(dev);
+	if (i915.enable_guc_submission < 0)
+		i915.enable_guc_submission = HAS_GUC_SCHED(dev);
 
 	if (!HAS_GUC_UCODE(dev)) {
 		fw_path = NULL;
@@ -640,27 +697,30 @@ void intel_guc_ucode_init(struct drm_device *dev)
 		fw_path = I915_SKL_GUC_UCODE;
 		guc_fw->guc_fw_major_wanted = 6;
 		guc_fw->guc_fw_minor_wanted = 1;
+	} else if (IS_BROXTON(dev)) {
+		fw_path = I915_BXT_GUC_UCODE;
+		guc_fw->guc_fw_major_wanted = 8;
+		guc_fw->guc_fw_minor_wanted = 7;
+	} else if (IS_KABYLAKE(dev)) {
+		fw_path = I915_KBL_GUC_UCODE;
+		guc_fw->guc_fw_major_wanted = 9;
+		guc_fw->guc_fw_minor_wanted = 14;
 	} else {
-		i915.enable_guc_submission = false;
 		fw_path = "";	/* unknown device */
 	}
 
-	if (!i915.enable_guc_submission)
-		return;
-
 	guc_fw->guc_dev = dev;
 	guc_fw->guc_fw_path = fw_path;
 	guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_NONE;
 	guc_fw->guc_fw_load_status = GUC_FIRMWARE_NONE;
 
+	/* Early (and silent) return if GuC loading is disabled */
+	if (!i915.enable_guc_loading)
+		return;
 	if (fw_path == NULL)
 		return;
-
-	if (*fw_path == '\0') {
-		DRM_ERROR("No GuC firmware known for this platform\n");
-		guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_FAIL;
+	if (*fw_path == '\0')
 		return;
-	}
 
 	guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_PENDING;
 	DRM_DEBUG_DRIVER("GuC firmware pending, path %s\n", fw_path);
@@ -669,18 +729,18 @@ void intel_guc_ucode_init(struct drm_device *dev)
 }
 
 /**
- * intel_guc_ucode_fini() - clean up all allocated resources
+ * intel_guc_fini() - clean up all allocated resources
  * @dev:	drm device
  */
-void intel_guc_ucode_fini(struct drm_device *dev)
+void intel_guc_fini(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
 
 	mutex_lock(&dev->struct_mutex);
 	direct_interrupts_to_host(dev_priv);
-	i915_guc_submission_disable(dev);
-	i915_guc_submission_fini(dev);
+	i915_guc_submission_disable(dev_priv);
+	i915_guc_submission_fini(dev_priv);
 
 	if (guc_fw->guc_fw_obj)
 		drm_gem_object_unreference(&guc_fw->guc_fw_obj->base);
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
new file mode 100644
index 000000000000..434f4d5c553d
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -0,0 +1,104 @@
+/*
+ * Copyright(c) 2011-2016 Intel Corporation. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "i915_drv.h"
+#include "intel_gvt.h"
+
+/**
+ * DOC: Intel GVT-g host support
+ *
+ * Intel GVT-g is a graphics virtualization technology which shares the
+ * GPU among multiple virtual machines on a time-sharing basis. Each
+ * virtual machine is presented a virtual GPU (vGPU), which has equivalent
+ * features as the underlying physical GPU (pGPU), so i915 driver can run
+ * seamlessly in a virtual machine. This file provides the englightments
+ * of GVT and the necessary components used by GVT in i915 driver.
+ */
+
+static bool is_supported_device(struct drm_i915_private *dev_priv)
+{
+	if (IS_BROADWELL(dev_priv))
+		return true;
+	return false;
+}
+
+/**
+ * intel_gvt_init - initialize GVT components
+ * @dev_priv: drm i915 private data
+ *
+ * This function is called at the initialization stage to create a GVT device.
+ *
+ * Returns:
+ * Zero on success, negative error code if failed.
+ *
+ */
+int intel_gvt_init(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	if (!i915.enable_gvt) {
+		DRM_DEBUG_DRIVER("GVT-g is disabled by kernel params\n");
+		return 0;
+	}
+
+	if (!is_supported_device(dev_priv)) {
+		DRM_DEBUG_DRIVER("Unsupported device. GVT-g is disabled\n");
+		goto bail;
+	}
+
+	/*
+	 * We're not in host or fail to find a MPT module, disable GVT-g
+	 */
+	ret = intel_gvt_init_host();
+	if (ret) {
+		DRM_DEBUG_DRIVER("Not in host or MPT modules not found\n");
+		goto bail;
+	}
+
+	ret = intel_gvt_init_device(dev_priv);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Fail to init GVT device\n");
+		goto bail;
+	}
+
+	return 0;
+
+bail:
+	i915.enable_gvt = 0;
+	return 0;
+}
+
+/**
+ * intel_gvt_cleanup - cleanup GVT components when i915 driver is unloading
+ * @dev_priv: drm i915 private *
+ *
+ * This function is called at the i915 driver unloading stage, to shutdown
+ * GVT components and release the related resources.
+ */
+void intel_gvt_cleanup(struct drm_i915_private *dev_priv)
+{
+	if (!intel_gvt_active(dev_priv))
+		return;
+
+	intel_gvt_clean_device(dev_priv);
+}
diff --git a/drivers/gpu/drm/i915/intel_gvt.h b/drivers/gpu/drm/i915/intel_gvt.h
new file mode 100644
index 000000000000..960211df74db
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_gvt.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright(c) 2011-2016 Intel Corporation. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _INTEL_GVT_H_
+#define _INTEL_GVT_H_
+
+#include "gvt/gvt.h"
+
+#ifdef CONFIG_DRM_I915_GVT
+int intel_gvt_init(struct drm_i915_private *dev_priv);
+void intel_gvt_cleanup(struct drm_i915_private *dev_priv);
+int intel_gvt_init_device(struct drm_i915_private *dev_priv);
+void intel_gvt_clean_device(struct drm_i915_private *dev_priv);
+int intel_gvt_init_host(void);
+#else
+static inline int intel_gvt_init(struct drm_i915_private *dev_priv)
+{
+	return 0;
+}
+static inline void intel_gvt_cleanup(struct drm_i915_private *dev_priv)
+{
+}
+#endif
+
+#endif /* _INTEL_GVT_H_ */
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index a8844702d11b..4df9f384910c 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -47,7 +47,7 @@ static void
 assert_hdmi_port_disabled(struct intel_hdmi *intel_hdmi)
 {
 	struct drm_device *dev = intel_hdmi_to_dev(intel_hdmi);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t enabled_bits;
 
 	enabled_bits = HAS_DDI(dev) ? DDI_BUF_CTL_ENABLE : SDVO_ENABLE;
@@ -138,7 +138,7 @@ static void g4x_write_infoframe(struct drm_encoder *encoder,
 {
 	const uint32_t *data = frame;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val = I915_READ(VIDEO_DIP_CTL);
 	int i;
 
@@ -192,7 +192,7 @@ static void ibx_write_infoframe(struct drm_encoder *encoder,
 {
 	const uint32_t *data = frame;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
@@ -251,7 +251,7 @@ static void cpt_write_infoframe(struct drm_encoder *encoder,
 {
 	const uint32_t *data = frame;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
@@ -308,7 +308,7 @@ static void vlv_write_infoframe(struct drm_encoder *encoder,
 {
 	const uint32_t *data = frame;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	i915_reg_t reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
@@ -366,7 +366,7 @@ static void hsw_write_infoframe(struct drm_encoder *encoder,
 {
 	const uint32_t *data = frame;
 	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
 	i915_reg_t ctl_reg = HSW_TVIDEO_DIP_CTL(cpu_transcoder);
@@ -508,7 +508,7 @@ static void g4x_set_infoframes(struct drm_encoder *encoder,
 			       bool enable,
 			       const struct drm_display_mode *adjusted_mode)
 {
-	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
 	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
 	i915_reg_t reg = VIDEO_DIP_CTL;
@@ -629,7 +629,7 @@ static bool gcp_default_phase_possible(int pipe_bpp,
 
 static bool intel_hdmi_set_gcp_infoframe(struct drm_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->crtc);
 	i915_reg_t reg;
 	u32 val = 0;
@@ -661,7 +661,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder,
 			       bool enable,
 			       const struct drm_display_mode *adjusted_mode)
 {
-	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
@@ -713,7 +713,7 @@ static void cpt_set_infoframes(struct drm_encoder *encoder,
 			       bool enable,
 			       const struct drm_display_mode *adjusted_mode)
 {
-	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
@@ -755,7 +755,7 @@ static void vlv_set_infoframes(struct drm_encoder *encoder,
 			       bool enable,
 			       const struct drm_display_mode *adjusted_mode)
 {
-	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
 	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
@@ -807,7 +807,7 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
 			       bool enable,
 			       const struct drm_display_mode *adjusted_mode)
 {
-	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	i915_reg_t reg = HSW_TVIDEO_DIP_CTL(intel_crtc->config->cpu_transcoder);
@@ -855,7 +855,7 @@ void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable)
 static void intel_hdmi_prepare(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
@@ -894,7 +894,7 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
@@ -931,7 +931,7 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder,
 {
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 tmp, flags = 0;
 	int dotclock;
 
@@ -988,7 +988,7 @@ static void intel_enable_hdmi_audio(struct intel_encoder *encoder)
 static void g4x_enable_hdmi(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
 	u32 temp;
@@ -1009,7 +1009,7 @@ static void g4x_enable_hdmi(struct intel_encoder *encoder)
 static void ibx_enable_hdmi(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
 	u32 temp;
@@ -1058,7 +1058,7 @@ static void ibx_enable_hdmi(struct intel_encoder *encoder)
 static void cpt_enable_hdmi(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
 	enum pipe pipe = crtc->pipe;
@@ -1115,7 +1115,7 @@ static void vlv_enable_hdmi(struct intel_encoder *encoder)
 static void intel_disable_hdmi(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	u32 temp;
@@ -1154,7 +1154,7 @@ static void intel_disable_hdmi(struct intel_encoder *encoder)
 		I915_WRITE(intel_hdmi->hdmi_reg, temp);
 		POSTING_READ(intel_hdmi->hdmi_reg);
 
-		intel_wait_for_vblank_if_active(dev_priv->dev, PIPE_A);
+		intel_wait_for_vblank_if_active(&dev_priv->drm, PIPE_A);
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, PIPE_A, true);
 		intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, true);
 	}
@@ -1273,33 +1273,15 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 static bool hdmi_12bpc_possible(struct intel_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc_state->base.crtc->dev;
-	struct drm_atomic_state *state;
-	struct intel_encoder *encoder;
-	struct drm_connector *connector;
-	struct drm_connector_state *connector_state;
-	int count = 0, count_hdmi = 0;
-	int i;
 
 	if (HAS_GMCH_DISPLAY(dev))
 		return false;
 
-	state = crtc_state->base.state;
-
-	for_each_connector_in_state(state, connector, connector_state, i) {
-		if (connector_state->crtc != crtc_state->base.crtc)
-			continue;
-
-		encoder = to_intel_encoder(connector_state->best_encoder);
-
-		count_hdmi += encoder->type == INTEL_OUTPUT_HDMI;
-		count++;
-	}
-
 	/*
 	 * HDMI 12bpc affects the clocks, so it's only possible
 	 * when not cloning with other encoder types.
 	 */
-	return count_hdmi > 0 && count_hdmi == count;
+	return crtc_state->output_types == 1 << INTEL_OUTPUT_HDMI;
 }
 
 bool intel_hdmi_compute_config(struct intel_encoder *encoder,
@@ -1575,7 +1557,7 @@ intel_hdmi_set_property(struct drm_connector *connector,
 	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
 	struct intel_digital_port *intel_dig_port =
 		hdmi_to_dig_port(intel_hdmi);
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	int ret;
 
 	ret = drm_object_property_set_value(&connector->base, property, val);
@@ -1674,39 +1656,16 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder)
 	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
 	struct intel_hdmi *intel_hdmi = &dport->hdmi;
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(encoder->base.crtc);
 	const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode;
-	enum dpio_channel port = vlv_dport_to_channel(dport);
-	int pipe = intel_crtc->pipe;
-	u32 val;
 
-	/* Enable clock channels for this port */
-	mutex_lock(&dev_priv->sb_lock);
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(port));
-	val = 0;
-	if (pipe)
-		val |= (1<<21);
-	else
-		val &= ~(1<<21);
-	val |= 0x001000c4;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW8(port), val);
+	vlv_phy_pre_encoder_enable(encoder);
 
 	/* HDMI 1.0V-2dB */
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), 0);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW4(port), 0x2b245f5f);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW2(port), 0x5578b83a);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW3(port), 0x0c782040);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX3_DW4(port), 0x2b247878);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW11(port), 0x00030000);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW9(port), 0x00002000);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), DPIO_TX_OCALINIT_EN);
-
-	/* Program lane clock */
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW14(port), 0x00760018);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW23(port), 0x00400888);
-	mutex_unlock(&dev_priv->sb_lock);
+	vlv_set_phy_signal_level(encoder, 0x2b245f5f, 0x00002000, 0x5578b83a,
+				 0x2b247878);
 
 	intel_hdmi->set_infoframes(&encoder->base,
 				   intel_crtc->config->has_hdmi_sink,
@@ -1719,213 +1678,33 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder)
 
 static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(encoder->base.crtc);
-	enum dpio_channel port = vlv_dport_to_channel(dport);
-	int pipe = intel_crtc->pipe;
-
 	intel_hdmi_prepare(encoder);
 
-	/* Program Tx lane resets to default */
-	mutex_lock(&dev_priv->sb_lock);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port),
-			 DPIO_PCS_TX_LANE2_RESET |
-			 DPIO_PCS_TX_LANE1_RESET);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW1(port),
-			 DPIO_PCS_CLK_CRI_RXEB_EIOS_EN |
-			 DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN |
-			 (1<<DPIO_PCS_CLK_DATAWIDTH_SHIFT) |
-			 DPIO_PCS_CLK_SOFT_RESET);
-
-	/* Fix up inter-pair skew failure */
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW12(port), 0x00750f00);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW11(port), 0x00001500);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW14(port), 0x40400000);
-
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW9(port), 0x00002000);
-	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW5(port), DPIO_TX_OCALINIT_EN);
-	mutex_unlock(&dev_priv->sb_lock);
-}
-
-static void chv_data_lane_soft_reset(struct intel_encoder *encoder,
-				     bool reset)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base));
-	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
-	enum pipe pipe = crtc->pipe;
-	uint32_t val;
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
-	if (reset)
-		val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
-	else
-		val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
-
-	if (crtc->config->lane_count > 2) {
-		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
-		if (reset)
-			val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
-		else
-			val |= DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET;
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
-	}
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
-	val |= CHV_PCS_REQ_SOFTRESET_EN;
-	if (reset)
-		val &= ~DPIO_PCS_CLK_SOFT_RESET;
-	else
-		val |= DPIO_PCS_CLK_SOFT_RESET;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
-
-	if (crtc->config->lane_count > 2) {
-		val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
-		val |= CHV_PCS_REQ_SOFTRESET_EN;
-		if (reset)
-			val &= ~DPIO_PCS_CLK_SOFT_RESET;
-		else
-			val |= DPIO_PCS_CLK_SOFT_RESET;
-		vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
-	}
+	vlv_phy_pre_pll_enable(encoder);
 }
 
 static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(encoder->base.crtc);
-	enum dpio_channel ch = vlv_dport_to_channel(dport);
-	enum pipe pipe = intel_crtc->pipe;
-	u32 val;
-
 	intel_hdmi_prepare(encoder);
 
-	/*
-	 * Must trick the second common lane into life.
-	 * Otherwise we can't even access the PLL.
-	 */
-	if (ch == DPIO_CH0 && pipe == PIPE_B)
-		dport->release_cl2_override =
-			!chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, true);
-
-	chv_phy_powergate_lanes(encoder, true, 0x0);
-
-	mutex_lock(&dev_priv->sb_lock);
-
-	/* Assert data lane reset */
-	chv_data_lane_soft_reset(encoder, true);
-
-	/* program left/right clock distribution */
-	if (pipe != PIPE_B) {
-		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
-		val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
-		if (ch == DPIO_CH0)
-			val |= CHV_BUFLEFTENA1_FORCE;
-		if (ch == DPIO_CH1)
-			val |= CHV_BUFRIGHTENA1_FORCE;
-		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
-	} else {
-		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
-		val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
-		if (ch == DPIO_CH0)
-			val |= CHV_BUFLEFTENA2_FORCE;
-		if (ch == DPIO_CH1)
-			val |= CHV_BUFRIGHTENA2_FORCE;
-		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
-	}
-
-	/* program clock channel usage */
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(ch));
-	val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
-	if (pipe != PIPE_B)
-		val &= ~CHV_PCS_USEDCLKCHANNEL;
-	else
-		val |= CHV_PCS_USEDCLKCHANNEL;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW8(ch), val);
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW8(ch));
-	val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
-	if (pipe != PIPE_B)
-		val &= ~CHV_PCS_USEDCLKCHANNEL;
-	else
-		val |= CHV_PCS_USEDCLKCHANNEL;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW8(ch), val);
-
-	/*
-	 * This a a bit weird since generally CL
-	 * matches the pipe, but here we need to
-	 * pick the CL based on the port.
-	 */
-	val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW19(ch));
-	if (pipe != PIPE_B)
-		val &= ~CHV_CMN_USEDCLKCHANNEL;
-	else
-		val |= CHV_CMN_USEDCLKCHANNEL;
-	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW19(ch), val);
-
-	mutex_unlock(&dev_priv->sb_lock);
+	chv_phy_pre_pll_enable(encoder);
 }
 
 static void chv_hdmi_post_pll_disable(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum pipe pipe = to_intel_crtc(encoder->base.crtc)->pipe;
-	u32 val;
-
-	mutex_lock(&dev_priv->sb_lock);
-
-	/* disable left/right clock distribution */
-	if (pipe != PIPE_B) {
-		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
-		val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
-		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
-	} else {
-		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
-		val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
-		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
-	}
-
-	mutex_unlock(&dev_priv->sb_lock);
-
-	/*
-	 * Leave the power down bit cleared for at least one
-	 * lane so that chv_powergate_phy_ch() will power
-	 * on something when the channel is otherwise unused.
-	 * When the port is off and the override is removed
-	 * the lanes power down anyway, so otherwise it doesn't
-	 * really matter what the state of power down bits is
-	 * after this.
-	 */
-	chv_phy_powergate_lanes(encoder, false, 0x0);
+	chv_phy_post_pll_disable(encoder);
 }
 
 static void vlv_hdmi_post_disable(struct intel_encoder *encoder)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(encoder->base.crtc);
-	enum dpio_channel port = vlv_dport_to_channel(dport);
-	int pipe = intel_crtc->pipe;
-
 	/* Reset lanes to avoid HDMI flicker (VLV w/a) */
-	mutex_lock(&dev_priv->sb_lock);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port), 0x00000000);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW1(port), 0x00e00060);
-	mutex_unlock(&dev_priv->sb_lock);
+	vlv_phy_reset_lanes(encoder);
 }
 
 static void chv_hdmi_post_disable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	mutex_lock(&dev_priv->sb_lock);
 
@@ -1940,142 +1719,16 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder)
 	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
 	struct intel_hdmi *intel_hdmi = &dport->hdmi;
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(encoder->base.crtc);
 	const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode;
-	enum dpio_channel ch = vlv_dport_to_channel(dport);
-	int pipe = intel_crtc->pipe;
-	int data, i, stagger;
-	u32 val;
 
-	mutex_lock(&dev_priv->sb_lock);
-
-	/* allow hardware to manage TX FIFO reset source */
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW11(ch));
-	val &= ~DPIO_LANEDESKEW_STRAP_OVRD;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW11(ch), val);
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch));
-	val &= ~DPIO_LANEDESKEW_STRAP_OVRD;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
-
-	/* Program Tx latency optimal setting */
-	for (i = 0; i < 4; i++) {
-		/* Set the upar bit */
-		data = (i == 1) ? 0x0 : 0x1;
-		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i),
-				data << DPIO_UPAR_SHIFT);
-	}
-
-	/* Data lane stagger programming */
-	if (intel_crtc->config->port_clock > 270000)
-		stagger = 0x18;
-	else if (intel_crtc->config->port_clock > 135000)
-		stagger = 0xd;
-	else if (intel_crtc->config->port_clock > 67500)
-		stagger = 0x7;
-	else if (intel_crtc->config->port_clock > 33750)
-		stagger = 0x4;
-	else
-		stagger = 0x2;
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW11(ch));
-	val |= DPIO_TX2_STAGGER_MASK(0x1f);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW11(ch), val);
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW11(ch));
-	val |= DPIO_TX2_STAGGER_MASK(0x1f);
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW11(ch), val);
-
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW12(ch),
-		       DPIO_LANESTAGGER_STRAP(stagger) |
-		       DPIO_LANESTAGGER_STRAP_OVRD |
-		       DPIO_TX1_STAGGER_MASK(0x1f) |
-		       DPIO_TX1_STAGGER_MULT(6) |
-		       DPIO_TX2_STAGGER_MULT(0));
-
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW12(ch),
-		       DPIO_LANESTAGGER_STRAP(stagger) |
-		       DPIO_LANESTAGGER_STRAP_OVRD |
-		       DPIO_TX1_STAGGER_MASK(0x1f) |
-		       DPIO_TX1_STAGGER_MULT(7) |
-		       DPIO_TX2_STAGGER_MULT(5));
-
-	/* Deassert data lane reset */
-	chv_data_lane_soft_reset(encoder, false);
-
-	/* Clear calc init */
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
-	val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
-	val &= ~(DPIO_PCS_TX1DEEMP_MASK | DPIO_PCS_TX2DEEMP_MASK);
-	val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
-	val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
-	val &= ~(DPIO_PCS_TX1DEEMP_MASK | DPIO_PCS_TX2DEEMP_MASK);
-	val |= DPIO_PCS_TX1DEEMP_9P5 | DPIO_PCS_TX2DEEMP_9P5;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW9(ch));
-	val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK);
-	val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW9(ch), val);
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW9(ch));
-	val &= ~(DPIO_PCS_TX1MARGIN_MASK | DPIO_PCS_TX2MARGIN_MASK);
-	val |= DPIO_PCS_TX1MARGIN_000 | DPIO_PCS_TX2MARGIN_000;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW9(ch), val);
+	chv_phy_pre_encoder_enable(encoder);
 
 	/* FIXME: Program the support xxx V-dB */
 	/* Use 800mV-0dB */
-	for (i = 0; i < 4; i++) {
-		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i));
-		val &= ~DPIO_SWING_DEEMPH9P5_MASK;
-		val |= 128 << DPIO_SWING_DEEMPH9P5_SHIFT;
-		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW4(ch, i), val);
-	}
-
-	for (i = 0; i < 4; i++) {
-		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
-
-		val &= ~DPIO_SWING_MARGIN000_MASK;
-		val |= 102 << DPIO_SWING_MARGIN000_SHIFT;
-
-		/*
-		 * Supposedly this value shouldn't matter when unique transition
-		 * scale is disabled, but in fact it does matter. Let's just
-		 * always program the same value and hope it's OK.
-		 */
-		val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT);
-		val |= 0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT;
-
-		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
-	}
-
-	/*
-	 * The document said it needs to set bit 27 for ch0 and bit 26
-	 * for ch1. Might be a typo in the doc.
-	 * For now, for this unique transition scale selection, set bit
-	 * 27 for ch0 and ch1.
-	 */
-	for (i = 0; i < 4; i++) {
-		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i));
-		val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN;
-		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val);
-	}
-
-	/* Start swing calculation */
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
-	val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
-
-	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
-	val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
-	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
-
-	mutex_unlock(&dev_priv->sb_lock);
+	chv_set_phy_signal_level(encoder, 128, 102, false);
 
 	intel_hdmi->set_infoframes(&encoder->base,
 				   intel_crtc->config->has_hdmi_sink,
@@ -2086,10 +1739,7 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder)
 	vlv_wait_port_ready(dev_priv, dport, 0x0);
 
 	/* Second common lane will stay alive on its own now */
-	if (dport->release_cl2_override) {
-		chv_phy_powergate_ch(dev_priv, DPIO_PHY0, DPIO_CH1, false);
-		dport->release_cl2_override = false;
-	}
+	chv_phy_release_cl2_override(encoder);
 }
 
 static void intel_hdmi_destroy(struct drm_connector *connector)
@@ -2106,6 +1756,8 @@ static const struct drm_connector_funcs intel_hdmi_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = intel_hdmi_set_property,
 	.atomic_get_property = intel_connector_atomic_get_property,
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
 	.destroy = intel_hdmi_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
@@ -2114,7 +1766,6 @@ static const struct drm_connector_funcs intel_hdmi_connector_funcs = {
 static const struct drm_connector_helper_funcs intel_hdmi_connector_helper_funcs = {
 	.get_modes = intel_hdmi_get_modes,
 	.mode_valid = intel_hdmi_mode_valid,
-	.best_encoder = intel_best_encoder,
 };
 
 static const struct drm_encoder_funcs intel_hdmi_enc_funcs = {
@@ -2138,7 +1789,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_device *dev = intel_encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_dig_port->port;
 	uint8_t alternate_ddc_pin;
 
@@ -2242,12 +1893,10 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 		intel_connector->get_hw_state = intel_ddi_connector_get_hw_state;
 	else
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
-	intel_connector->unregister = intel_connector_unregister;
 
 	intel_hdmi_add_properties(intel_hdmi, connector);
 
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
-	drm_connector_register(connector);
 	intel_hdmi->attached_connector = intel_connector;
 
 	/* For G4X desktop chip, PEG_BAND_GAP_DATA 3:0 must first be written
@@ -2280,7 +1929,7 @@ void intel_hdmi_init(struct drm_device *dev,
 	intel_encoder = &intel_dig_port->base;
 
 	drm_encoder_init(dev, &intel_encoder->base, &intel_hdmi_enc_funcs,
-			 DRM_MODE_ENCODER_TMDS, NULL);
+			 DRM_MODE_ENCODER_TMDS, "HDMI %c", port_name(port));
 
 	intel_encoder->compute_config = intel_hdmi_compute_config;
 	if (HAS_PCH_SPLIT(dev)) {
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index bee673005d48..f48957ea100d 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -144,7 +144,7 @@ static bool intel_hpd_irq_storm_detect(struct drm_i915_private *dev_priv,
 
 static void intel_hpd_irq_storm_disable(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct intel_connector *intel_connector;
 	struct intel_encoder *intel_encoder;
@@ -191,7 +191,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 	struct drm_i915_private *dev_priv =
 		container_of(work, typeof(*dev_priv),
 			     hotplug.reenable_work.work);
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	int i;
 
@@ -220,7 +220,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 		}
 	}
 	if (dev_priv->display.hpd_irq_setup)
-		dev_priv->display.hpd_irq_setup(dev);
+		dev_priv->display.hpd_irq_setup(dev_priv);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
 	intel_runtime_pm_put(dev_priv);
@@ -302,7 +302,7 @@ static void i915_hotplug_work_func(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(work, struct drm_i915_private, hotplug.hotplug_work);
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct intel_connector *intel_connector;
 	struct intel_encoder *intel_encoder;
@@ -346,7 +346,7 @@ static void i915_hotplug_work_func(struct work_struct *work)
 
 /**
  * intel_hpd_irq_handler - main hotplug irq handler
- * @dev: drm device
+ * @dev_priv: drm_i915_private
  * @pin_mask: a mask of hpd pins that have triggered the irq
  * @long_mask: a mask of hpd pins that may be long hpd pulses
  *
@@ -360,10 +360,9 @@ static void i915_hotplug_work_func(struct work_struct *work)
  * Here, we do hotplug irq storm detection and mitigation, and pass further
  * processing to appropriate bottom halves.
  */
-void intel_hpd_irq_handler(struct drm_device *dev,
+void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			   u32 pin_mask, u32 long_mask)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
 	enum port port;
 	bool storm_detected = false;
@@ -407,7 +406,7 @@ void intel_hpd_irq_handler(struct drm_device *dev,
 			 * hotplug bits itself. So only WARN about unexpected
 			 * interrupts on saner platforms.
 			 */
-			WARN_ONCE(!HAS_GMCH_DISPLAY(dev),
+			WARN_ONCE(!HAS_GMCH_DISPLAY(dev_priv),
 				  "Received HPD interrupt on pin %d although disabled\n", i);
 			continue;
 		}
@@ -427,7 +426,7 @@ void intel_hpd_irq_handler(struct drm_device *dev,
 	}
 
 	if (storm_detected)
-		dev_priv->display.hpd_irq_setup(dev);
+		dev_priv->display.hpd_irq_setup(dev_priv);
 	spin_unlock(&dev_priv->irq_lock);
 
 	/*
@@ -453,20 +452,47 @@ void intel_hpd_irq_handler(struct drm_device *dev,
  *
  * This is a separate step from interrupt enabling to simplify the locking rules
  * in the driver load and resume code.
+ *
+ * Also see: intel_hpd_poll_init(), which enables connector polling
  */
 void intel_hpd_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
-	struct drm_mode_config *mode_config = &dev->mode_config;
-	struct drm_connector *connector;
 	int i;
 
 	for_each_hpd_pin(i) {
 		dev_priv->hotplug.stats[i].count = 0;
 		dev_priv->hotplug.stats[i].state = HPD_ENABLED;
 	}
+
+	WRITE_ONCE(dev_priv->hotplug.poll_enabled, false);
+	schedule_work(&dev_priv->hotplug.poll_init_work);
+
+	/*
+	 * Interrupt setup is already guaranteed to be single-threaded, this is
+	 * just to make the assert_spin_locked checks happy.
+	 */
+	spin_lock_irq(&dev_priv->irq_lock);
+	if (dev_priv->display.hpd_irq_setup)
+		dev_priv->display.hpd_irq_setup(dev_priv);
+	spin_unlock_irq(&dev_priv->irq_lock);
+}
+
+void i915_hpd_poll_init_work(struct work_struct *work) {
+	struct drm_i915_private *dev_priv =
+		container_of(work, struct drm_i915_private,
+			     hotplug.poll_init_work);
+	struct drm_device *dev = &dev_priv->drm;
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	struct drm_connector *connector;
+	bool enabled;
+
+	mutex_lock(&dev->mode_config.mutex);
+
+	enabled = READ_ONCE(dev_priv->hotplug.poll_enabled);
+
 	list_for_each_entry(connector, &mode_config->connector_list, head) {
-		struct intel_connector *intel_connector = to_intel_connector(connector);
+		struct intel_connector *intel_connector =
+			to_intel_connector(connector);
 		connector->polled = intel_connector->polled;
 
 		/* MST has a dynamic intel_connector->encoder and it's reprobing
@@ -475,24 +501,62 @@ void intel_hpd_init(struct drm_i915_private *dev_priv)
 			continue;
 
 		if (!connector->polled && I915_HAS_HOTPLUG(dev) &&
-		    intel_connector->encoder->hpd_pin > HPD_NONE)
-			connector->polled = DRM_CONNECTOR_POLL_HPD;
+		    intel_connector->encoder->hpd_pin > HPD_NONE) {
+			connector->polled = enabled ?
+				DRM_CONNECTOR_POLL_CONNECT |
+				DRM_CONNECTOR_POLL_DISCONNECT :
+				DRM_CONNECTOR_POLL_HPD;
+		}
 	}
 
+	if (enabled)
+		drm_kms_helper_poll_enable_locked(dev);
+
+	mutex_unlock(&dev->mode_config.mutex);
+
 	/*
-	 * Interrupt setup is already guaranteed to be single-threaded, this is
-	 * just to make the assert_spin_locked checks happy.
+	 * We might have missed any hotplugs that happened while we were
+	 * in the middle of disabling polling
 	 */
-	spin_lock_irq(&dev_priv->irq_lock);
-	if (dev_priv->display.hpd_irq_setup)
-		dev_priv->display.hpd_irq_setup(dev);
-	spin_unlock_irq(&dev_priv->irq_lock);
+	if (!enabled)
+		drm_helper_hpd_irq_event(dev);
+}
+
+/**
+ * intel_hpd_poll_init - enables/disables polling for connectors with hpd
+ * @dev_priv: i915 device instance
+ * @enabled: Whether to enable or disable polling
+ *
+ * This function enables polling for all connectors, regardless of whether or
+ * not they support hotplug detection. Under certain conditions HPD may not be
+ * functional. On most Intel GPUs, this happens when we enter runtime suspend.
+ * On Valleyview and Cherryview systems, this also happens when we shut off all
+ * of the powerwells.
+ *
+ * Since this function can get called in contexts where we're already holding
+ * dev->mode_config.mutex, we do the actual hotplug enabling in a seperate
+ * worker.
+ *
+ * Also see: intel_hpd_init(), which restores hpd handling.
+ */
+void intel_hpd_poll_init(struct drm_i915_private *dev_priv)
+{
+	WRITE_ONCE(dev_priv->hotplug.poll_enabled, true);
+
+	/*
+	 * We might already be holding dev->mode_config.mutex, so do this in a
+	 * seperate worker
+	 * As well, there's no issue if we race here since we always reschedule
+	 * this worker anyway
+	 */
+	schedule_work(&dev_priv->hotplug.poll_init_work);
 }
 
 void intel_hpd_init_work(struct drm_i915_private *dev_priv)
 {
 	INIT_WORK(&dev_priv->hotplug.hotplug_work, i915_hotplug_work_func);
 	INIT_WORK(&dev_priv->hotplug.dig_port_work, i915_digport_work_func);
+	INIT_WORK(&dev_priv->hotplug.poll_init_work, i915_hpd_poll_init_work);
 	INIT_DELAYED_WORK(&dev_priv->hotplug.reenable_work,
 			  intel_hpd_irq_storm_reenable_work);
 }
@@ -509,5 +573,33 @@ void intel_hpd_cancel_work(struct drm_i915_private *dev_priv)
 
 	cancel_work_sync(&dev_priv->hotplug.dig_port_work);
 	cancel_work_sync(&dev_priv->hotplug.hotplug_work);
+	cancel_work_sync(&dev_priv->hotplug.poll_init_work);
 	cancel_delayed_work_sync(&dev_priv->hotplug.reenable_work);
 }
+
+bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin)
+{
+	bool ret = false;
+
+	if (pin == HPD_NONE)
+		return false;
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	if (dev_priv->hotplug.stats[pin].state == HPD_ENABLED) {
+		dev_priv->hotplug.stats[pin].state = HPD_DISABLED;
+		ret = true;
+	}
+	spin_unlock_irq(&dev_priv->irq_lock);
+
+	return ret;
+}
+
+void intel_hpd_enable(struct drm_i915_private *dev_priv, enum hpd_pin pin)
+{
+	if (pin == HPD_NONE)
+		return;
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	dev_priv->hotplug.stats[pin].state = HPD_ENABLED;
+	spin_unlock_irq(&dev_priv->irq_lock);
+}
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 81de23098be7..1f266d7df2ec 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -113,7 +113,7 @@ to_intel_gmbus(struct i2c_adapter *i2c)
 void
 intel_i2c_reset(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(GMBUS0, 0);
 	I915_WRITE(GMBUS4, 0);
@@ -138,7 +138,7 @@ static void intel_i2c_quirk_set(struct drm_i915_private *dev_priv, bool enable)
 static u32 get_reserved(struct intel_gmbus *bus)
 {
 	struct drm_i915_private *dev_priv = bus->dev_priv;
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	u32 reserved = 0;
 
 	/* On most chips, these bits must be preserved in software. */
@@ -212,7 +212,7 @@ intel_gpio_pre_xfer(struct i2c_adapter *adapter)
 					       adapter);
 	struct drm_i915_private *dev_priv = bus->dev_priv;
 
-	intel_i2c_reset(dev_priv->dev);
+	intel_i2c_reset(&dev_priv->drm);
 	intel_i2c_quirk_set(dev_priv, true);
 	set_data(bus, 1);
 	set_clock(bus, 1);
@@ -298,15 +298,16 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv)
 {
 	int ret;
 
-#define C ((I915_READ_NOTRACE(GMBUS2) & GMBUS_ACTIVE) == 0)
-
 	if (!HAS_GMBUS_IRQ(dev_priv))
-		return wait_for(C, 10);
+		return intel_wait_for_register(dev_priv,
+					       GMBUS2, GMBUS_ACTIVE, 0,
+					       10);
 
 	/* Important: The hw handles only the first bit, so set only one! */
 	I915_WRITE(GMBUS4, GMBUS_IDLE_EN);
 
-	ret = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
+	ret = wait_event_timeout(dev_priv->gmbus_wait_queue,
+				 (I915_READ_NOTRACE(GMBUS2) & GMBUS_ACTIVE) == 0,
 				 msecs_to_jiffies_timeout(10));
 
 	I915_WRITE(GMBUS4, 0);
@@ -315,7 +316,6 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv)
 		return 0;
 	else
 		return -ETIMEDOUT;
-#undef C
 }
 
 static int
@@ -632,7 +632,7 @@ static const struct i2c_algorithm gmbus_algorithm = {
  */
 int intel_setup_gmbus(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_gmbus *bus;
 	unsigned int pin;
 	int ret;
@@ -688,7 +688,7 @@ int intel_setup_gmbus(struct drm_device *dev)
 			goto err;
 	}
 
-	intel_i2c_reset(dev_priv->dev);
+	intel_i2c_reset(&dev_priv->drm);
 
 	return 0;
 
@@ -736,7 +736,7 @@ void intel_gmbus_force_bit(struct i2c_adapter *adapter, bool force_bit)
 
 void intel_teardown_gmbus(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_gmbus *bus;
 	unsigned int pin;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 7f2d8415ed8b..414ddda43922 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -208,31 +208,27 @@
 } while (0)
 
 enum {
-	ADVANCED_CONTEXT = 0,
-	LEGACY_32B_CONTEXT,
-	ADVANCED_AD_CONTEXT,
-	LEGACY_64B_CONTEXT
-};
-#define GEN8_CTX_ADDRESSING_MODE_SHIFT 3
-#define GEN8_CTX_ADDRESSING_MODE(dev)  (USES_FULL_48BIT_PPGTT(dev) ?\
-		LEGACY_64B_CONTEXT :\
-		LEGACY_32B_CONTEXT)
-enum {
 	FAULT_AND_HANG = 0,
 	FAULT_AND_HALT, /* Debug only */
 	FAULT_AND_STREAM,
 	FAULT_AND_CONTINUE /* Unsupported */
 };
 #define GEN8_CTX_ID_SHIFT 32
+#define GEN8_CTX_ID_WIDTH 21
 #define GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x17
 #define GEN9_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x26
 
-static int intel_lr_context_pin(struct intel_context *ctx,
+/* Typical size of the average request (2 pipecontrols and a MI_BB) */
+#define EXECLISTS_REQUEST_SIZE 64 /* bytes */
+
+static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
+					    struct intel_engine_cs *engine);
+static int intel_lr_context_pin(struct i915_gem_context *ctx,
 				struct intel_engine_cs *engine);
 
 /**
  * intel_sanitize_enable_execlists() - sanitize i915.enable_execlists
- * @dev: DRM device.
+ * @dev_priv: i915 device private
  * @enable_execlists: value of i915.enable_execlists module parameter.
  *
  * Only certain platforms support Execlists (the prerequisites being
@@ -240,23 +236,22 @@ static int intel_lr_context_pin(struct intel_context *ctx,
  *
  * Return: 1 if Execlists is supported and has to be enabled.
  */
-int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists)
+int intel_sanitize_enable_execlists(struct drm_i915_private *dev_priv, int enable_execlists)
 {
-	WARN_ON(i915.enable_ppgtt == -1);
-
 	/* On platforms with execlist available, vGPU will only
 	 * support execlist mode, no ring buffer mode.
 	 */
-	if (HAS_LOGICAL_RING_CONTEXTS(dev) && intel_vgpu_active(dev))
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv) && intel_vgpu_active(dev_priv))
 		return 1;
 
-	if (INTEL_INFO(dev)->gen >= 9)
+	if (INTEL_GEN(dev_priv) >= 9)
 		return 1;
 
 	if (enable_execlists == 0)
 		return 0;
 
-	if (HAS_LOGICAL_RING_CONTEXTS(dev) && USES_PPGTT(dev) &&
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv) &&
+	    USES_PPGTT(dev_priv) &&
 	    i915.use_mmio_flip >= 0)
 		return 1;
 
@@ -266,19 +261,17 @@ int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists
 static void
 logical_ring_init_platform_invariants(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	if (IS_GEN8(dev) || IS_GEN9(dev))
+	if (IS_GEN8(dev_priv) || IS_GEN9(dev_priv))
 		engine->idle_lite_restore_wa = ~0;
 
-	engine->disable_lite_restore_wa = (IS_SKL_REVID(dev, 0, SKL_REVID_B0) ||
-					IS_BXT_REVID(dev, 0, BXT_REVID_A1)) &&
+	engine->disable_lite_restore_wa = (IS_SKL_REVID(dev_priv, 0, SKL_REVID_B0) ||
+					IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) &&
 					(engine->id == VCS || engine->id == VCS2);
 
 	engine->ctx_desc_template = GEN8_CTX_VALID;
-	engine->ctx_desc_template |= GEN8_CTX_ADDRESSING_MODE(dev) <<
-				   GEN8_CTX_ADDRESSING_MODE_SHIFT;
-	if (IS_GEN8(dev))
+	if (IS_GEN8(dev_priv))
 		engine->ctx_desc_template |= GEN8_CTX_L3LLC_COHERENT;
 	engine->ctx_desc_template |= GEN8_CTX_PRIVILEGE;
 
@@ -297,7 +290,7 @@ logical_ring_init_platform_invariants(struct intel_engine_cs *engine)
  * 					  descriptor for a pinned context
  *
  * @ctx: Context to work on
- * @ring: Engine the descriptor will be used with
+ * @engine: Engine the descriptor will be used with
  *
  * The context descriptor encodes various attributes of a context,
  * including its GTT address and some flags. Because it's fairly
@@ -305,62 +298,42 @@ logical_ring_init_platform_invariants(struct intel_engine_cs *engine)
  * which remains valid until the context is unpinned.
  *
  * This is what a descriptor looks like, from LSB to MSB:
- *    bits 0-11:    flags, GEN8_CTX_* (cached in ctx_desc_template)
+ *    bits  0-11:    flags, GEN8_CTX_* (cached in ctx_desc_template)
  *    bits 12-31:    LRCA, GTT address of (the HWSP of) this context
- *    bits 32-51:    ctx ID, a globally unique tag (the LRCA again!)
- *    bits 52-63:    reserved, may encode the engine ID (for GuC)
+ *    bits 32-52:    ctx ID, a globally unique tag
+ *    bits 53-54:    mbz, reserved for use by hardware
+ *    bits 55-63:    group ID, currently unused and set to 0
  */
 static void
-intel_lr_context_descriptor_update(struct intel_context *ctx,
+intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
 				   struct intel_engine_cs *engine)
 {
-	uint64_t lrca, desc;
+	struct intel_context *ce = &ctx->engine[engine->id];
+	u64 desc;
 
-	lrca = ctx->engine[engine->id].lrc_vma->node.start +
-	       LRC_PPHWSP_PN * PAGE_SIZE;
+	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (1<<GEN8_CTX_ID_WIDTH));
 
-	desc = engine->ctx_desc_template;			   /* bits  0-11 */
-	desc |= lrca;					   /* bits 12-31 */
-	desc |= (lrca >> PAGE_SHIFT) << GEN8_CTX_ID_SHIFT; /* bits 32-51 */
+	desc = ctx->desc_template;				/* bits  3-4  */
+	desc |= engine->ctx_desc_template;			/* bits  0-11 */
+	desc |= ce->lrc_vma->node.start + LRC_PPHWSP_PN * PAGE_SIZE;
+								/* bits 12-31 */
+	desc |= (u64)ctx->hw_id << GEN8_CTX_ID_SHIFT;		/* bits 32-52 */
 
-	ctx->engine[engine->id].lrc_desc = desc;
+	ce->lrc_desc = desc;
 }
 
-uint64_t intel_lr_context_descriptor(struct intel_context *ctx,
+uint64_t intel_lr_context_descriptor(struct i915_gem_context *ctx,
 				     struct intel_engine_cs *engine)
 {
 	return ctx->engine[engine->id].lrc_desc;
 }
 
-/**
- * intel_execlists_ctx_id() - get the Execlists Context ID
- * @ctx: Context to get the ID for
- * @ring: Engine to get the ID for
- *
- * Do not confuse with ctx->id! Unfortunately we have a name overload
- * here: the old context ID we pass to userspace as a handler so that
- * they can refer to a context, and the new context ID we pass to the
- * ELSP so that the GPU can inform us of the context status via
- * interrupts.
- *
- * The context ID is a portion of the context descriptor, so we can
- * just extract the required part from the cached descriptor.
- *
- * Return: 20-bits globally unique context ID.
- */
-u32 intel_execlists_ctx_id(struct intel_context *ctx,
-			   struct intel_engine_cs *engine)
-{
-	return intel_lr_context_descriptor(ctx, engine) >> GEN8_CTX_ID_SHIFT;
-}
-
 static void execlists_elsp_write(struct drm_i915_gem_request *rq0,
 				 struct drm_i915_gem_request *rq1)
 {
 
 	struct intel_engine_cs *engine = rq0->engine;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = rq0->i915;
 	uint64_t desc[2];
 
 	if (rq1) {
@@ -431,6 +404,20 @@ static void execlists_submit_requests(struct drm_i915_gem_request *rq0,
 	spin_unlock_irq(&dev_priv->uncore.lock);
 }
 
+static inline void execlists_context_status_change(
+		struct drm_i915_gem_request *rq,
+		unsigned long status)
+{
+	/*
+	 * Only used when GVT-g is enabled now. When GVT-g is disabled,
+	 * The compiler should eliminate this function as dead-code.
+	 */
+	if (!IS_ENABLED(CONFIG_DRM_I915_GVT))
+		return;
+
+	atomic_notifier_call_chain(&rq->ctx->status_notifier, status, rq);
+}
+
 static void execlists_context_unqueue(struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_request *req0 = NULL, *req1 = NULL;
@@ -442,7 +429,7 @@ static void execlists_context_unqueue(struct intel_engine_cs *engine)
 	 * If irqs are not active generate a warning as batches that finish
 	 * without the irqs may get lost and a GPU Hang may occur.
 	 */
-	WARN_ON(!intel_irqs_enabled(engine->dev->dev_private));
+	WARN_ON(!intel_irqs_enabled(engine->i915));
 
 	/* Try to read in pairs */
 	list_for_each_entry_safe(cursor, tmp, &engine->execlist_queue,
@@ -453,10 +440,24 @@ static void execlists_context_unqueue(struct intel_engine_cs *engine)
 			/* Same ctx: ignore first request, as second request
 			 * will update tail past first request's workload */
 			cursor->elsp_submitted = req0->elsp_submitted;
-			list_move_tail(&req0->execlist_link,
-				       &engine->execlist_retired_req_list);
+			list_del(&req0->execlist_link);
+			i915_gem_request_unreference(req0);
 			req0 = cursor;
 		} else {
+			if (IS_ENABLED(CONFIG_DRM_I915_GVT)) {
+				/*
+				 * req0 (after merged) ctx requires single
+				 * submission, stop picking
+				 */
+				if (req0->ctx->execlists_force_single_submission)
+					break;
+				/*
+				 * req0 ctx doesn't require single submission,
+				 * but next req ctx requires, stop picking
+				 */
+				if (cursor->ctx->execlists_force_single_submission)
+					break;
+			}
 			req1 = cursor;
 			WARN_ON(req1->elsp_submitted);
 			break;
@@ -466,6 +467,12 @@ static void execlists_context_unqueue(struct intel_engine_cs *engine)
 	if (unlikely(!req0))
 		return;
 
+	execlists_context_status_change(req0, INTEL_CONTEXT_SCHEDULE_IN);
+
+	if (req1)
+		execlists_context_status_change(req1,
+						INTEL_CONTEXT_SCHEDULE_IN);
+
 	if (req0->elsp_submitted & engine->idle_lite_restore_wa) {
 		/*
 		 * WaIdleLiteRestore: make sure we never cause a lite restore
@@ -486,7 +493,7 @@ static void execlists_context_unqueue(struct intel_engine_cs *engine)
 }
 
 static unsigned int
-execlists_check_remove_request(struct intel_engine_cs *engine, u32 request_id)
+execlists_check_remove_request(struct intel_engine_cs *engine, u32 ctx_id)
 {
 	struct drm_i915_gem_request *head_req;
 
@@ -496,19 +503,18 @@ execlists_check_remove_request(struct intel_engine_cs *engine, u32 request_id)
 					    struct drm_i915_gem_request,
 					    execlist_link);
 
-	if (!head_req)
-		return 0;
-
-	if (unlikely(intel_execlists_ctx_id(head_req->ctx, engine) != request_id))
-		return 0;
+	if (WARN_ON(!head_req || (head_req->ctx_hw_id != ctx_id)))
+               return 0;
 
 	WARN(head_req->elsp_submitted == 0, "Never submitted head request\n");
 
 	if (--head_req->elsp_submitted > 0)
 		return 0;
 
-	list_move_tail(&head_req->execlist_link,
-		       &engine->execlist_retired_req_list);
+	execlists_context_status_change(head_req, INTEL_CONTEXT_SCHEDULE_OUT);
+
+	list_del(&head_req->execlist_link);
+	i915_gem_request_unreference(head_req);
 
 	return 1;
 }
@@ -517,7 +523,7 @@ static u32
 get_context_status(struct intel_engine_cs *engine, unsigned int read_pointer,
 		   u32 *context_id)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	u32 status;
 
 	read_pointer %= GEN8_CSB_ENTRIES;
@@ -535,7 +541,7 @@ get_context_status(struct intel_engine_cs *engine, unsigned int read_pointer,
 
 /**
  * intel_lrc_irq_handler() - handle Context Switch interrupts
- * @engine: Engine Command Streamer to handle.
+ * @data: tasklet handler passed in unsigned long
  *
  * Check the unread Context Status Buffers and manage the submission of new
  * contexts to the ELSP accordingly.
@@ -543,7 +549,7 @@ get_context_status(struct intel_engine_cs *engine, unsigned int read_pointer,
 static void intel_lrc_irq_handler(unsigned long data)
 {
 	struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	u32 status_pointer;
 	unsigned int read_pointer, write_pointer;
 	u32 csb[GEN8_CSB_ENTRIES][2];
@@ -612,11 +618,6 @@ static void execlists_context_queue(struct drm_i915_gem_request *request)
 	struct drm_i915_gem_request *cursor;
 	int num_elements = 0;
 
-	if (request->ctx != request->i915->kernel_context)
-		intel_lr_context_pin(request->ctx, engine);
-
-	i915_gem_request_reference(request);
-
 	spin_lock_bh(&engine->execlist_lock);
 
 	list_for_each_entry(cursor, &engine->execlist_queue, execlist_link)
@@ -633,12 +634,14 @@ static void execlists_context_queue(struct drm_i915_gem_request *request)
 		if (request->ctx == tail_req->ctx) {
 			WARN(tail_req->elsp_submitted != 0,
 				"More than 2 already-submitted reqs queued\n");
-			list_move_tail(&tail_req->execlist_link,
-				       &engine->execlist_retired_req_list);
+			list_del(&tail_req->execlist_link);
+			i915_gem_request_unreference(tail_req);
 		}
 	}
 
+	i915_gem_request_reference(request);
 	list_add_tail(&request->execlist_link, &engine->execlist_queue);
+	request->ctx_hw_id = request->ctx->hw_id;
 	if (num_elements == 0)
 		execlists_context_unqueue(engine);
 
@@ -698,9 +701,23 @@ static int execlists_move_to_gpu(struct drm_i915_gem_request *req,
 
 int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request)
 {
-	int ret = 0;
+	struct intel_engine_cs *engine = request->engine;
+	struct intel_context *ce = &request->ctx->engine[engine->id];
+	int ret;
 
-	request->ringbuf = request->ctx->engine[request->engine->id].ringbuf;
+	/* Flush enough space to reduce the likelihood of waiting after
+	 * we start building the request - in which case we will just
+	 * have to repeat work.
+	 */
+	request->reserved_space += EXECLISTS_REQUEST_SIZE;
+
+	if (!ce->state) {
+		ret = execlists_context_deferred_alloc(request->ctx, engine);
+		if (ret)
+			return ret;
+	}
+
+	request->ringbuf = ce->ringbuf;
 
 	if (i915.enable_guc_submission) {
 		/*
@@ -708,16 +725,39 @@ int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request
 		 * going any further, as the i915_add_request() call
 		 * later on mustn't fail ...
 		 */
-		struct intel_guc *guc = &request->i915->guc;
-
-		ret = i915_guc_wq_check_space(guc->execbuf_client);
+		ret = i915_guc_wq_check_space(request);
 		if (ret)
 			return ret;
 	}
 
-	if (request->ctx != request->i915->kernel_context)
-		ret = intel_lr_context_pin(request->ctx, request->engine);
+	ret = intel_lr_context_pin(request->ctx, engine);
+	if (ret)
+		return ret;
+
+	ret = intel_ring_begin(request, 0);
+	if (ret)
+		goto err_unpin;
+
+	if (!ce->initialised) {
+		ret = engine->init_context(request);
+		if (ret)
+			goto err_unpin;
+
+		ce->initialised = true;
+	}
+
+	/* Note that after this point, we have committed to using
+	 * this request as it is being used to both track the
+	 * state of engine initialisation and liveness of the
+	 * golden renderstate above. Think twice before you try
+	 * to cancel/unwind this request now.
+	 */
 
+	request->reserved_space -= EXECLISTS_REQUEST_SIZE;
+	return 0;
+
+err_unpin:
+	intel_lr_context_unpin(request->ctx, engine);
 	return ret;
 }
 
@@ -734,7 +774,6 @@ static int
 intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request)
 {
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
-	struct drm_i915_private *dev_priv = request->i915;
 	struct intel_engine_cs *engine = request->engine;
 
 	intel_logical_ring_advance(ringbuf);
@@ -750,54 +789,28 @@ intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request)
 	intel_logical_ring_emit(ringbuf, MI_NOOP);
 	intel_logical_ring_advance(ringbuf);
 
-	if (intel_engine_stopped(engine))
-		return 0;
-
-	if (engine->last_context != request->ctx) {
-		if (engine->last_context)
-			intel_lr_context_unpin(engine->last_context, engine);
-		if (request->ctx != request->i915->kernel_context) {
-			intel_lr_context_pin(request->ctx, engine);
-			engine->last_context = request->ctx;
-		} else {
-			engine->last_context = NULL;
-		}
-	}
+	/* We keep the previous context alive until we retire the following
+	 * request. This ensures that any the context object is still pinned
+	 * for any residual writes the HW makes into it on the context switch
+	 * into the next object following the breadcrumb. Otherwise, we may
+	 * retire the context too early.
+	 */
+	request->previous_context = engine->last_context;
+	engine->last_context = request->ctx;
 
-	if (dev_priv->guc.execbuf_client)
-		i915_guc_submit(dev_priv->guc.execbuf_client, request);
+	if (i915.enable_guc_submission)
+		i915_guc_submit(request);
 	else
 		execlists_context_queue(request);
 
 	return 0;
 }
 
-int intel_logical_ring_reserve_space(struct drm_i915_gem_request *request)
-{
-	/*
-	 * The first call merely notes the reserve request and is common for
-	 * all back ends. The subsequent localised _begin() call actually
-	 * ensures that the reservation is available. Without the begin, if
-	 * the request creator immediately submitted the request without
-	 * adding any commands to it then there might not actually be
-	 * sufficient room for the submission commands.
-	 */
-	intel_ring_reserved_space_reserve(request->ringbuf, MIN_SPACE_FOR_ADD_REQUEST);
-
-	return intel_ring_begin(request, 0);
-}
-
 /**
  * execlists_submission() - submit a batchbuffer for execution, Execlists style
- * @dev: DRM device.
- * @file: DRM file.
- * @ring: Engine Command Streamer to submit to.
- * @ctx: Context to employ for this submission.
+ * @params: execbuffer call parameters.
  * @args: execbuffer call arguments.
  * @vmas: list of vmas.
- * @batch_obj: the batchbuffer to submit.
- * @exec_start: batchbuffer start virtual address pointer.
- * @dispatch_flags: translated execbuffer call flags.
  *
  * This is the evil twin version of i915_gem_ringbuffer_submission. It abstracts
  * away the submission details of the execbuffer ioctl call.
@@ -810,7 +823,7 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
 {
 	struct drm_device       *dev = params->dev;
 	struct intel_engine_cs *engine = params->engine;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_ringbuffer *ringbuf = params->ctx->engine[engine->id].ringbuf;
 	u64 exec_start;
 	int instp_mode;
@@ -881,28 +894,18 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
 	return 0;
 }
 
-void intel_execlists_retire_requests(struct intel_engine_cs *engine)
+void intel_execlists_cancel_requests(struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_request *req, *tmp;
-	struct list_head retired_list;
+	LIST_HEAD(cancel_list);
 
-	WARN_ON(!mutex_is_locked(&engine->dev->struct_mutex));
-	if (list_empty(&engine->execlist_retired_req_list))
-		return;
+	WARN_ON(!mutex_is_locked(&engine->i915->drm.struct_mutex));
 
-	INIT_LIST_HEAD(&retired_list);
 	spin_lock_bh(&engine->execlist_lock);
-	list_replace_init(&engine->execlist_retired_req_list, &retired_list);
+	list_replace_init(&engine->execlist_queue, &cancel_list);
 	spin_unlock_bh(&engine->execlist_lock);
 
-	list_for_each_entry_safe(req, tmp, &retired_list, execlist_link) {
-		struct intel_context *ctx = req->ctx;
-		struct drm_i915_gem_object *ctx_obj =
-				ctx->engine[engine->id].state;
-
-		if (ctx_obj && (ctx != req->i915->kernel_context))
-			intel_lr_context_unpin(ctx, engine);
-
+	list_for_each_entry_safe(req, tmp, &cancel_list, execlist_link) {
 		list_del(&req->execlist_link);
 		i915_gem_request_unreference(req);
 	}
@@ -910,7 +913,7 @@ void intel_execlists_retire_requests(struct intel_engine_cs *engine)
 
 void intel_logical_ring_stop(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret;
 
 	if (!intel_engine_initialized(engine))
@@ -923,7 +926,10 @@ void intel_logical_ring_stop(struct intel_engine_cs *engine)
 
 	/* TODO: Is this correct with Execlists enabled? */
 	I915_WRITE_MODE(engine, _MASKED_BIT_ENABLE(STOP_RING));
-	if (wait_for((I915_READ_MODE(engine) & MODE_IDLE) != 0, 1000)) {
+	if (intel_wait_for_register(dev_priv,
+				    RING_MI_MODE(engine->mmio_base),
+				    MODE_IDLE, MODE_IDLE,
+				    1000)) {
 		DRM_ERROR("%s :timed out trying to stop ring\n", engine->name);
 		return;
 	}
@@ -946,25 +952,26 @@ int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
 	return 0;
 }
 
-static int intel_lr_context_do_pin(struct intel_context *ctx,
-				   struct intel_engine_cs *engine)
+static int intel_lr_context_pin(struct i915_gem_context *ctx,
+				struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *ctx_obj = ctx->engine[engine->id].state;
-	struct intel_ringbuffer *ringbuf = ctx->engine[engine->id].ringbuf;
+	struct drm_i915_private *dev_priv = ctx->i915;
+	struct intel_context *ce = &ctx->engine[engine->id];
 	void *vaddr;
 	u32 *lrc_reg_state;
 	int ret;
 
-	WARN_ON(!mutex_is_locked(&engine->dev->struct_mutex));
+	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
 
-	ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN,
-			PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
+	if (ce->pin_count++)
+		return 0;
+
+	ret = i915_gem_obj_ggtt_pin(ce->state, GEN8_LR_CONTEXT_ALIGN,
+				    PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
 	if (ret)
-		return ret;
+		goto err;
 
-	vaddr = i915_gem_object_pin_map(ctx_obj);
+	vaddr = i915_gem_object_pin_map(ce->state);
 	if (IS_ERR(vaddr)) {
 		ret = PTR_ERR(vaddr);
 		goto unpin_ctx_obj;
@@ -972,65 +979,54 @@ static int intel_lr_context_do_pin(struct intel_context *ctx,
 
 	lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 
-	ret = intel_pin_and_map_ringbuffer_obj(engine->dev, ringbuf);
+	ret = intel_pin_and_map_ringbuffer_obj(dev_priv, ce->ringbuf);
 	if (ret)
 		goto unpin_map;
 
-	ctx->engine[engine->id].lrc_vma = i915_gem_obj_to_ggtt(ctx_obj);
+	i915_gem_context_reference(ctx);
+	ce->lrc_vma = i915_gem_obj_to_ggtt(ce->state);
 	intel_lr_context_descriptor_update(ctx, engine);
-	lrc_reg_state[CTX_RING_BUFFER_START+1] = ringbuf->vma->node.start;
-	ctx->engine[engine->id].lrc_reg_state = lrc_reg_state;
-	ctx_obj->dirty = true;
+
+	lrc_reg_state[CTX_RING_BUFFER_START+1] = ce->ringbuf->vma->node.start;
+	ce->lrc_reg_state = lrc_reg_state;
+	ce->state->dirty = true;
 
 	/* Invalidate GuC TLB. */
 	if (i915.enable_guc_submission)
 		I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE);
 
-	return ret;
+	return 0;
 
 unpin_map:
-	i915_gem_object_unpin_map(ctx_obj);
+	i915_gem_object_unpin_map(ce->state);
 unpin_ctx_obj:
-	i915_gem_object_ggtt_unpin(ctx_obj);
-
+	i915_gem_object_ggtt_unpin(ce->state);
+err:
+	ce->pin_count = 0;
 	return ret;
 }
 
-static int intel_lr_context_pin(struct intel_context *ctx,
-				struct intel_engine_cs *engine)
+void intel_lr_context_unpin(struct i915_gem_context *ctx,
+			    struct intel_engine_cs *engine)
 {
-	int ret = 0;
+	struct intel_context *ce = &ctx->engine[engine->id];
 
-	if (ctx->engine[engine->id].pin_count++ == 0) {
-		ret = intel_lr_context_do_pin(ctx, engine);
-		if (ret)
-			goto reset_pin_count;
+	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
+	GEM_BUG_ON(ce->pin_count == 0);
 
-		i915_gem_context_reference(ctx);
-	}
-	return ret;
+	if (--ce->pin_count)
+		return;
 
-reset_pin_count:
-	ctx->engine[engine->id].pin_count = 0;
-	return ret;
-}
+	intel_unpin_ringbuffer_obj(ce->ringbuf);
 
-void intel_lr_context_unpin(struct intel_context *ctx,
-			    struct intel_engine_cs *engine)
-{
-	struct drm_i915_gem_object *ctx_obj = ctx->engine[engine->id].state;
+	i915_gem_object_unpin_map(ce->state);
+	i915_gem_object_ggtt_unpin(ce->state);
 
-	WARN_ON(!mutex_is_locked(&ctx->i915->dev->struct_mutex));
-	if (--ctx->engine[engine->id].pin_count == 0) {
-		i915_gem_object_unpin_map(ctx_obj);
-		intel_unpin_ringbuffer_obj(ctx->engine[engine->id].ringbuf);
-		i915_gem_object_ggtt_unpin(ctx_obj);
-		ctx->engine[engine->id].lrc_vma = NULL;
-		ctx->engine[engine->id].lrc_desc = 0;
-		ctx->engine[engine->id].lrc_reg_state = NULL;
+	ce->lrc_vma = NULL;
+	ce->lrc_desc = 0;
+	ce->lrc_reg_state = NULL;
 
-		i915_gem_context_unreference(ctx);
-	}
+	i915_gem_context_unreference(ctx);
 }
 
 static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
@@ -1038,9 +1034,7 @@ static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req)
 	int ret, i;
 	struct intel_engine_cs *engine = req->engine;
 	struct intel_ringbuffer *ringbuf = req->ringbuf;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_workarounds *w = &dev_priv->workarounds;
+	struct i915_workarounds *w = &req->i915->workarounds;
 
 	if (w->count == 0)
 		return 0;
@@ -1103,7 +1097,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
 						uint32_t *const batch,
 						uint32_t index)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES);
 
 	/*
@@ -1165,7 +1159,7 @@ static inline int wa_ctx_end(struct i915_wa_ctx_bb *wa_ctx,
 /**
  * gen8_init_indirectctx_bb() - initialize indirect ctx batch with WA
  *
- * @ring: only applicable for RCS
+ * @engine: only applicable for RCS
  * @wa_ctx: structure representing wa_ctx
  *  offset: specifies start of the batch, should be cache-aligned. This is updated
  *    with the offset value received as input.
@@ -1202,7 +1196,7 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *engine,
 	wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_DISABLE);
 
 	/* WaFlushCoherentL3CacheLinesAtContextSwitch:bdw */
-	if (IS_BROADWELL(engine->dev)) {
+	if (IS_BROADWELL(engine->i915)) {
 		int rc = gen8_emit_flush_coherentl3_wa(engine, batch, index);
 		if (rc < 0)
 			return rc;
@@ -1239,7 +1233,7 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *engine,
 /**
  * gen8_init_perctx_bb() - initialize per ctx batch with WA
  *
- * @ring: only applicable for RCS
+ * @engine: only applicable for RCS
  * @wa_ctx: structure representing wa_ctx
  *  offset: specifies start of the batch, should be cache-aligned.
  *  size: size of the batch in DWORDS but HW expects in terms of cachelines
@@ -1274,13 +1268,12 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine,
 				    uint32_t *offset)
 {
 	int ret;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
 
 	/* WaDisableCtxRestoreArbitration:skl,bxt */
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_D0) ||
-	    IS_BXT_REVID(dev, 0, BXT_REVID_A1))
+	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_D0) ||
+	    IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1))
 		wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_DISABLE);
 
 	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt */
@@ -1305,6 +1298,31 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine,
 		wa_ctx_emit(batch, index, 0);
 		wa_ctx_emit(batch, index, 0);
 	}
+
+	/* WaMediaPoolStateCmdInWABB:bxt */
+	if (HAS_POOLED_EU(engine->i915)) {
+		/*
+		 * EU pool configuration is setup along with golden context
+		 * during context initialization. This value depends on
+		 * device type (2x6 or 3x6) and needs to be updated based
+		 * on which subslice is disabled especially for 2x6
+		 * devices, however it is safe to load default
+		 * configuration of 3x6 device instead of masking off
+		 * corresponding bits because HW ignores bits of a disabled
+		 * subslice and drops down to appropriate config. Please
+		 * see render_state_setup() in i915_gem_render_state.c for
+		 * possible configurations, to avoid duplication they are
+		 * not shown here again.
+		 */
+		u32 eu_pool_config = 0x00777000;
+		wa_ctx_emit(batch, index, GEN9_MEDIA_POOL_STATE);
+		wa_ctx_emit(batch, index, GEN9_MEDIA_POOL_ENABLE);
+		wa_ctx_emit(batch, index, eu_pool_config);
+		wa_ctx_emit(batch, index, 0);
+		wa_ctx_emit(batch, index, 0);
+		wa_ctx_emit(batch, index, 0);
+	}
+
 	/* Pad to end of cacheline */
 	while (index % CACHELINE_DWORDS)
 		wa_ctx_emit(batch, index, MI_NOOP);
@@ -1317,12 +1335,11 @@ static int gen9_init_perctx_bb(struct intel_engine_cs *engine,
 			       uint32_t *const batch,
 			       uint32_t *offset)
 {
-	struct drm_device *dev = engine->dev;
 	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
 
 	/* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl,bxt */
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_B0) ||
-	    IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+	if (IS_SKL_REVID(engine->i915, 0, SKL_REVID_B0) ||
+	    IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1)) {
 		wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
 		wa_ctx_emit_reg(batch, index, GEN9_SLICE_COMMON_ECO_CHICKEN0);
 		wa_ctx_emit(batch, index,
@@ -1331,7 +1348,7 @@ static int gen9_init_perctx_bb(struct intel_engine_cs *engine,
 	}
 
 	/* WaClearTdlStateAckDirtyBits:bxt */
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_B0)) {
+	if (IS_BXT_REVID(engine->i915, 0, BXT_REVID_B0)) {
 		wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(4));
 
 		wa_ctx_emit_reg(batch, index, GEN8_STATE_ACK);
@@ -1350,8 +1367,8 @@ static int gen9_init_perctx_bb(struct intel_engine_cs *engine,
 	}
 
 	/* WaDisableCtxRestoreArbitration:skl,bxt */
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_D0) ||
-	    IS_BXT_REVID(dev, 0, BXT_REVID_A1))
+	if (IS_SKL_REVID(engine->i915, 0, SKL_REVID_D0) ||
+	    IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1))
 		wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_ENABLE);
 
 	wa_ctx_emit(batch, index, MI_BATCH_BUFFER_END);
@@ -1363,11 +1380,13 @@ static int lrc_setup_wa_ctx_obj(struct intel_engine_cs *engine, u32 size)
 {
 	int ret;
 
-	engine->wa_ctx.obj = i915_gem_alloc_object(engine->dev,
-						   PAGE_ALIGN(size));
-	if (!engine->wa_ctx.obj) {
+	engine->wa_ctx.obj = i915_gem_object_create(&engine->i915->drm,
+						    PAGE_ALIGN(size));
+	if (IS_ERR(engine->wa_ctx.obj)) {
 		DRM_DEBUG_DRIVER("alloc LRC WA ctx backing obj failed.\n");
-		return -ENOMEM;
+		ret = PTR_ERR(engine->wa_ctx.obj);
+		engine->wa_ctx.obj = NULL;
+		return ret;
 	}
 
 	ret = i915_gem_obj_ggtt_pin(engine->wa_ctx.obj, PAGE_SIZE, 0);
@@ -1401,9 +1420,9 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 	WARN_ON(engine->id != RCS);
 
 	/* update this when WA for higher Gen are added */
-	if (INTEL_INFO(engine->dev)->gen > 9) {
+	if (INTEL_GEN(engine->i915) > 9) {
 		DRM_ERROR("WA batch buffer is not initialized for Gen%d\n",
-			  INTEL_INFO(engine->dev)->gen);
+			  INTEL_GEN(engine->i915));
 		return 0;
 	}
 
@@ -1423,7 +1442,7 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 	batch = kmap_atomic(page);
 	offset = 0;
 
-	if (INTEL_INFO(engine->dev)->gen == 8) {
+	if (IS_GEN8(engine->i915)) {
 		ret = gen8_init_indirectctx_bb(engine,
 					       &wa_ctx->indirect_ctx,
 					       batch,
@@ -1437,7 +1456,7 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 					  &offset);
 		if (ret)
 			goto out;
-	} else if (INTEL_INFO(engine->dev)->gen == 9) {
+	} else if (IS_GEN9(engine->i915)) {
 		ret = gen9_init_indirectctx_bb(engine,
 					       &wa_ctx->indirect_ctx,
 					       batch,
@@ -1463,7 +1482,7 @@ out:
 
 static void lrc_init_hws(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 
 	I915_WRITE(RING_HWS_PGA(engine->mmio_base),
 		   (u32)engine->status_page.gfx_addr);
@@ -1472,8 +1491,7 @@ static void lrc_init_hws(struct intel_engine_cs *engine)
 
 static int gen8_init_common_ring(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	unsigned int next_context_status_buffer_hw;
 
 	lrc_init_hws(engine);
@@ -1520,8 +1538,7 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine)
 
 static int gen8_init_render_ring(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret;
 
 	ret = gen8_init_common_ring(engine);
@@ -1598,7 +1615,7 @@ static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
 	if (req->ctx->ppgtt &&
 	    (intel_engine_flag(req->engine) & req->ctx->ppgtt->pd_dirty_rings)) {
 		if (!USES_FULL_48BIT_PPGTT(req->i915) &&
-		    !intel_vgpu_active(req->i915->dev)) {
+		    !intel_vgpu_active(req->i915)) {
 			ret = intel_logical_ring_emit_pdps(req);
 			if (ret)
 				return ret;
@@ -1624,38 +1641,18 @@ static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
 	return 0;
 }
 
-static bool gen8_logical_ring_get_irq(struct intel_engine_cs *engine)
+static void gen8_logical_ring_enable_irq(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
-
-	if (WARN_ON(!intel_irqs_enabled(dev_priv)))
-		return false;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (engine->irq_refcount++ == 0) {
-		I915_WRITE_IMR(engine,
-			       ~(engine->irq_enable_mask | engine->irq_keep_mask));
-		POSTING_READ(RING_IMR(engine->mmio_base));
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
-
-	return true;
+	struct drm_i915_private *dev_priv = engine->i915;
+	I915_WRITE_IMR(engine,
+		       ~(engine->irq_enable_mask | engine->irq_keep_mask));
+	POSTING_READ_FW(RING_IMR(engine->mmio_base));
 }
 
-static void gen8_logical_ring_put_irq(struct intel_engine_cs *engine)
+static void gen8_logical_ring_disable_irq(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--engine->irq_refcount == 0) {
-		I915_WRITE_IMR(engine, ~engine->irq_keep_mask);
-		POSTING_READ(RING_IMR(engine->mmio_base));
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+	struct drm_i915_private *dev_priv = engine->i915;
+	I915_WRITE_IMR(engine, ~engine->irq_keep_mask);
 }
 
 static int gen8_emit_flush(struct drm_i915_gem_request *request,
@@ -1664,8 +1661,7 @@ static int gen8_emit_flush(struct drm_i915_gem_request *request,
 {
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
 	struct intel_engine_cs *engine = ringbuf->engine;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = request->i915;
 	uint32_t cmd;
 	int ret;
 
@@ -1734,7 +1730,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 		 * On GEN9: before VF_CACHE_INVALIDATE we need to emit a NULL
 		 * pipe control.
 		 */
-		if (IS_GEN9(engine->dev))
+		if (IS_GEN9(request->i915))
 			vf_flush_wa = true;
 
 		/* WaForGAMHang:kbl */
@@ -1793,16 +1789,6 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 	return 0;
 }
 
-static u32 gen8_get_seqno(struct intel_engine_cs *engine)
-{
-	return intel_read_status_page(engine, I915_GEM_HWS_INDEX);
-}
-
-static void gen8_set_seqno(struct intel_engine_cs *engine, u32 seqno)
-{
-	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
-}
-
 static void bxt_a_seqno_barrier(struct intel_engine_cs *engine)
 {
 	/*
@@ -1818,14 +1804,6 @@ static void bxt_a_seqno_barrier(struct intel_engine_cs *engine)
 	intel_flush_status_page(engine, I915_GEM_HWS_INDEX);
 }
 
-static void bxt_a_set_seqno(struct intel_engine_cs *engine, u32 seqno)
-{
-	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
-
-	/* See bxt_a_get_seqno() explaining the reason for the clflush. */
-	intel_flush_status_page(engine, I915_GEM_HWS_INDEX);
-}
-
 /*
  * Reserve space for 2 NOOPs at the end of each request to be
  * used as a workaround for not being allowed to do lite
@@ -1833,11 +1811,6 @@ static void bxt_a_set_seqno(struct intel_engine_cs *engine, u32 seqno)
  */
 #define WA_TAIL_DWORDS 2
 
-static inline u32 hws_seqno_address(struct intel_engine_cs *engine)
-{
-	return engine->status_page.gfx_addr + I915_GEM_HWS_INDEX_ADDR;
-}
-
 static int gen8_emit_request(struct drm_i915_gem_request *request)
 {
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
@@ -1853,10 +1826,10 @@ static int gen8_emit_request(struct drm_i915_gem_request *request)
 	intel_logical_ring_emit(ringbuf,
 				(MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW);
 	intel_logical_ring_emit(ringbuf,
-				hws_seqno_address(request->engine) |
+				intel_hws_seqno_address(request->engine) |
 				MI_FLUSH_DW_USE_GTT);
 	intel_logical_ring_emit(ringbuf, 0);
-	intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
+	intel_logical_ring_emit(ringbuf, request->seqno);
 	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
 	intel_logical_ring_emit(ringbuf, MI_NOOP);
 	return intel_logical_ring_advance_and_submit(request);
@@ -1883,7 +1856,8 @@ static int gen8_emit_request_render(struct drm_i915_gem_request *request)
 				(PIPE_CONTROL_GLOBAL_GTT_IVB |
 				 PIPE_CONTROL_CS_STALL |
 				 PIPE_CONTROL_QW_WRITE));
-	intel_logical_ring_emit(ringbuf, hws_seqno_address(request->engine));
+	intel_logical_ring_emit(ringbuf,
+				intel_hws_seqno_address(request->engine));
 	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
 	/* We're thrashing one dword of HWS. */
@@ -1945,7 +1919,7 @@ static int gen8_init_rcs_context(struct drm_i915_gem_request *req)
 /**
  * intel_logical_ring_cleanup() - deallocate the Engine Command Streamer
  *
- * @ring: Engine Command Streamer.
+ * @engine: Engine Command Streamer.
  *
  */
 void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
@@ -1962,7 +1936,7 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 	if (WARN_ON(test_bit(TASKLET_STATE_SCHED, &engine->irq_tasklet.state)))
 		tasklet_kill(&engine->irq_tasklet);
 
-	dev_priv = engine->dev->dev_private;
+	dev_priv = engine->i915;
 
 	if (engine->buffer) {
 		intel_logical_ring_stop(engine);
@@ -1975,36 +1949,34 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 	i915_cmd_parser_fini_ring(engine);
 	i915_gem_batch_pool_fini(&engine->batch_pool);
 
+	intel_engine_fini_breadcrumbs(engine);
+
 	if (engine->status_page.obj) {
 		i915_gem_object_unpin_map(engine->status_page.obj);
 		engine->status_page.obj = NULL;
 	}
+	intel_lr_context_unpin(dev_priv->kernel_context, engine);
 
 	engine->idle_lite_restore_wa = 0;
 	engine->disable_lite_restore_wa = false;
 	engine->ctx_desc_template = 0;
 
 	lrc_destroy_wa_ctx_obj(engine);
-	engine->dev = NULL;
+	engine->i915 = NULL;
 }
 
 static void
-logical_ring_default_vfuncs(struct drm_device *dev,
-			    struct intel_engine_cs *engine)
+logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 {
 	/* Default vfuncs which can be overriden by each engine. */
 	engine->init_hw = gen8_init_common_ring;
 	engine->emit_request = gen8_emit_request;
 	engine->emit_flush = gen8_emit_flush;
-	engine->irq_get = gen8_logical_ring_get_irq;
-	engine->irq_put = gen8_logical_ring_put_irq;
+	engine->irq_enable = gen8_logical_ring_enable_irq;
+	engine->irq_disable = gen8_logical_ring_disable_irq;
 	engine->emit_bb_start = gen8_emit_bb_start;
-	engine->get_seqno = gen8_get_seqno;
-	engine->set_seqno = gen8_set_seqno;
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+	if (IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1))
 		engine->irq_seqno_barrier = bxt_a_seqno_barrier;
-		engine->set_seqno = bxt_a_set_seqno;
-	}
 }
 
 static inline void
@@ -2033,60 +2005,28 @@ lrc_setup_hws(struct intel_engine_cs *engine,
 }
 
 static int
-logical_ring_init(struct drm_device *dev, struct intel_engine_cs *engine)
+logical_ring_init(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_context *dctx = dev_priv->kernel_context;
-	enum forcewake_domains fw_domains;
+	struct i915_gem_context *dctx = engine->i915->kernel_context;
 	int ret;
 
-	/* Intentionally left blank. */
-	engine->buffer = NULL;
-
-	engine->dev = dev;
-	INIT_LIST_HEAD(&engine->active_list);
-	INIT_LIST_HEAD(&engine->request_list);
-	i915_gem_batch_pool_init(dev, &engine->batch_pool);
-	init_waitqueue_head(&engine->irq_queue);
-
-	INIT_LIST_HEAD(&engine->buffers);
-	INIT_LIST_HEAD(&engine->execlist_queue);
-	INIT_LIST_HEAD(&engine->execlist_retired_req_list);
-	spin_lock_init(&engine->execlist_lock);
-
-	tasklet_init(&engine->irq_tasklet,
-		     intel_lrc_irq_handler, (unsigned long)engine);
-
-	logical_ring_init_platform_invariants(engine);
-
-	fw_domains = intel_uncore_forcewake_for_reg(dev_priv,
-						    RING_ELSP(engine),
-						    FW_REG_WRITE);
-
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
-						     RING_CONTEXT_STATUS_PTR(engine),
-						     FW_REG_READ | FW_REG_WRITE);
-
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
-						     RING_CONTEXT_STATUS_BUF_BASE(engine),
-						     FW_REG_READ);
-
-	engine->fw_domains = fw_domains;
+	ret = intel_engine_init_breadcrumbs(engine);
+	if (ret)
+		goto error;
 
 	ret = i915_cmd_parser_init_ring(engine);
 	if (ret)
 		goto error;
 
-	ret = intel_lr_context_deferred_alloc(dctx, engine);
+	ret = execlists_context_deferred_alloc(dctx, engine);
 	if (ret)
 		goto error;
 
 	/* As this is the default context, always pin it */
-	ret = intel_lr_context_do_pin(dctx, engine);
+	ret = intel_lr_context_pin(dctx, engine);
 	if (ret) {
-		DRM_ERROR(
-			"Failed to pin and map ringbuffer %s: %d\n",
-			engine->name, ret);
+		DRM_ERROR("Failed to pin context for %s: %d\n",
+			  engine->name, ret);
 		goto error;
 	}
 
@@ -2104,26 +2044,16 @@ error:
 	return ret;
 }
 
-static int logical_render_ring_init(struct drm_device *dev)
+static int logical_render_ring_init(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *engine = &dev_priv->engine[RCS];
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret;
 
-	engine->name = "render ring";
-	engine->id = RCS;
-	engine->exec_id = I915_EXEC_RENDER;
-	engine->guc_id = GUC_RENDER_ENGINE;
-	engine->mmio_base = RENDER_RING_BASE;
-
-	logical_ring_default_irqs(engine, GEN8_RCS_IRQ_SHIFT);
-	if (HAS_L3_DPF(dev))
+	if (HAS_L3_DPF(dev_priv))
 		engine->irq_keep_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
 
-	logical_ring_default_vfuncs(dev, engine);
-
 	/* Override some for render ring. */
-	if (INTEL_INFO(dev)->gen >= 9)
+	if (INTEL_GEN(dev_priv) >= 9)
 		engine->init_hw = gen9_init_render_ring;
 	else
 		engine->init_hw = gen8_init_render_ring;
@@ -2132,9 +2062,7 @@ static int logical_render_ring_init(struct drm_device *dev)
 	engine->emit_flush = gen8_emit_flush_render;
 	engine->emit_request = gen8_emit_request_render;
 
-	engine->dev = dev;
-
-	ret = intel_init_pipe_control(engine);
+	ret = intel_init_pipe_control(engine, 4096);
 	if (ret)
 		return ret;
 
@@ -2149,7 +2077,7 @@ static int logical_render_ring_init(struct drm_device *dev)
 			  ret);
 	}
 
-	ret = logical_ring_init(dev, engine);
+	ret = logical_ring_init(engine);
 	if (ret) {
 		lrc_destroy_wa_ctx_obj(engine);
 	}
@@ -2157,133 +2085,164 @@ static int logical_render_ring_init(struct drm_device *dev)
 	return ret;
 }
 
-static int logical_bsd_ring_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *engine = &dev_priv->engine[VCS];
-
-	engine->name = "bsd ring";
-	engine->id = VCS;
-	engine->exec_id = I915_EXEC_BSD;
-	engine->guc_id = GUC_VIDEO_ENGINE;
-	engine->mmio_base = GEN6_BSD_RING_BASE;
-
-	logical_ring_default_irqs(engine, GEN8_VCS1_IRQ_SHIFT);
-	logical_ring_default_vfuncs(dev, engine);
-
-	return logical_ring_init(dev, engine);
-}
+static const struct logical_ring_info {
+	const char *name;
+	unsigned exec_id;
+	unsigned guc_id;
+	u32 mmio_base;
+	unsigned irq_shift;
+	int (*init)(struct intel_engine_cs *engine);
+} logical_rings[] = {
+	[RCS] = {
+		.name = "render ring",
+		.exec_id = I915_EXEC_RENDER,
+		.guc_id = GUC_RENDER_ENGINE,
+		.mmio_base = RENDER_RING_BASE,
+		.irq_shift = GEN8_RCS_IRQ_SHIFT,
+		.init = logical_render_ring_init,
+	},
+	[BCS] = {
+		.name = "blitter ring",
+		.exec_id = I915_EXEC_BLT,
+		.guc_id = GUC_BLITTER_ENGINE,
+		.mmio_base = BLT_RING_BASE,
+		.irq_shift = GEN8_BCS_IRQ_SHIFT,
+		.init = logical_ring_init,
+	},
+	[VCS] = {
+		.name = "bsd ring",
+		.exec_id = I915_EXEC_BSD,
+		.guc_id = GUC_VIDEO_ENGINE,
+		.mmio_base = GEN6_BSD_RING_BASE,
+		.irq_shift = GEN8_VCS1_IRQ_SHIFT,
+		.init = logical_ring_init,
+	},
+	[VCS2] = {
+		.name = "bsd2 ring",
+		.exec_id = I915_EXEC_BSD,
+		.guc_id = GUC_VIDEO_ENGINE2,
+		.mmio_base = GEN8_BSD2_RING_BASE,
+		.irq_shift = GEN8_VCS2_IRQ_SHIFT,
+		.init = logical_ring_init,
+	},
+	[VECS] = {
+		.name = "video enhancement ring",
+		.exec_id = I915_EXEC_VEBOX,
+		.guc_id = GUC_VIDEOENHANCE_ENGINE,
+		.mmio_base = VEBOX_RING_BASE,
+		.irq_shift = GEN8_VECS_IRQ_SHIFT,
+		.init = logical_ring_init,
+	},
+};
 
-static int logical_bsd2_ring_init(struct drm_device *dev)
+static struct intel_engine_cs *
+logical_ring_setup(struct drm_i915_private *dev_priv, enum intel_engine_id id)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *engine = &dev_priv->engine[VCS2];
+	const struct logical_ring_info *info = &logical_rings[id];
+	struct intel_engine_cs *engine = &dev_priv->engine[id];
+	enum forcewake_domains fw_domains;
 
-	engine->name = "bsd2 ring";
-	engine->id = VCS2;
-	engine->exec_id = I915_EXEC_BSD;
-	engine->guc_id = GUC_VIDEO_ENGINE2;
-	engine->mmio_base = GEN8_BSD2_RING_BASE;
+	engine->id = id;
+	engine->name = info->name;
+	engine->exec_id = info->exec_id;
+	engine->guc_id = info->guc_id;
+	engine->mmio_base = info->mmio_base;
 
-	logical_ring_default_irqs(engine, GEN8_VCS2_IRQ_SHIFT);
-	logical_ring_default_vfuncs(dev, engine);
+	engine->i915 = dev_priv;
 
-	return logical_ring_init(dev, engine);
-}
+	/* Intentionally left blank. */
+	engine->buffer = NULL;
 
-static int logical_blt_ring_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *engine = &dev_priv->engine[BCS];
+	fw_domains = intel_uncore_forcewake_for_reg(dev_priv,
+						    RING_ELSP(engine),
+						    FW_REG_WRITE);
 
-	engine->name = "blitter ring";
-	engine->id = BCS;
-	engine->exec_id = I915_EXEC_BLT;
-	engine->guc_id = GUC_BLITTER_ENGINE;
-	engine->mmio_base = BLT_RING_BASE;
+	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
+						     RING_CONTEXT_STATUS_PTR(engine),
+						     FW_REG_READ | FW_REG_WRITE);
 
-	logical_ring_default_irqs(engine, GEN8_BCS_IRQ_SHIFT);
-	logical_ring_default_vfuncs(dev, engine);
+	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
+						     RING_CONTEXT_STATUS_BUF_BASE(engine),
+						     FW_REG_READ);
 
-	return logical_ring_init(dev, engine);
-}
+	engine->fw_domains = fw_domains;
 
-static int logical_vebox_ring_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *engine = &dev_priv->engine[VECS];
+	INIT_LIST_HEAD(&engine->active_list);
+	INIT_LIST_HEAD(&engine->request_list);
+	INIT_LIST_HEAD(&engine->buffers);
+	INIT_LIST_HEAD(&engine->execlist_queue);
+	spin_lock_init(&engine->execlist_lock);
 
-	engine->name = "video enhancement ring";
-	engine->id = VECS;
-	engine->exec_id = I915_EXEC_VEBOX;
-	engine->guc_id = GUC_VIDEOENHANCE_ENGINE;
-	engine->mmio_base = VEBOX_RING_BASE;
+	tasklet_init(&engine->irq_tasklet,
+		     intel_lrc_irq_handler, (unsigned long)engine);
 
-	logical_ring_default_irqs(engine, GEN8_VECS_IRQ_SHIFT);
-	logical_ring_default_vfuncs(dev, engine);
+	logical_ring_init_platform_invariants(engine);
+	logical_ring_default_vfuncs(engine);
+	logical_ring_default_irqs(engine, info->irq_shift);
+
+	intel_engine_init_hangcheck(engine);
+	i915_gem_batch_pool_init(&dev_priv->drm, &engine->batch_pool);
 
-	return logical_ring_init(dev, engine);
+	return engine;
 }
 
 /**
  * intel_logical_rings_init() - allocate, populate and init the Engine Command Streamers
  * @dev: DRM device.
  *
- * This function inits the engines for an Execlists submission style (the equivalent in the
- * legacy ringbuffer submission world would be i915_gem_init_engines). It does it only for
- * those engines that are present in the hardware.
+ * This function inits the engines for an Execlists submission style (the
+ * equivalent in the legacy ringbuffer submission world would be
+ * i915_gem_init_engines). It does it only for those engines that are present in
+ * the hardware.
  *
  * Return: non-zero if the initialization failed.
  */
 int intel_logical_rings_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	unsigned int mask = 0;
+	unsigned int i;
 	int ret;
 
-	ret = logical_render_ring_init(dev);
-	if (ret)
-		return ret;
+	WARN_ON(INTEL_INFO(dev_priv)->ring_mask &
+		GENMASK(sizeof(mask) * BITS_PER_BYTE - 1, I915_NUM_ENGINES));
 
-	if (HAS_BSD(dev)) {
-		ret = logical_bsd_ring_init(dev);
-		if (ret)
-			goto cleanup_render_ring;
-	}
+	for (i = 0; i < ARRAY_SIZE(logical_rings); i++) {
+		if (!HAS_ENGINE(dev_priv, i))
+			continue;
 
-	if (HAS_BLT(dev)) {
-		ret = logical_blt_ring_init(dev);
-		if (ret)
-			goto cleanup_bsd_ring;
-	}
+		if (!logical_rings[i].init)
+			continue;
 
-	if (HAS_VEBOX(dev)) {
-		ret = logical_vebox_ring_init(dev);
+		ret = logical_rings[i].init(logical_ring_setup(dev_priv, i));
 		if (ret)
-			goto cleanup_blt_ring;
+			goto cleanup;
+
+		mask |= ENGINE_MASK(i);
 	}
 
-	if (HAS_BSD2(dev)) {
-		ret = logical_bsd2_ring_init(dev);
-		if (ret)
-			goto cleanup_vebox_ring;
+	/*
+	 * Catch failures to update logical_rings table when the new engines
+	 * are added to the driver by a warning and disabling the forgotten
+	 * engines.
+	 */
+	if (WARN_ON(mask != INTEL_INFO(dev_priv)->ring_mask)) {
+		struct intel_device_info *info =
+			(struct intel_device_info *)&dev_priv->info;
+		info->ring_mask = mask;
 	}
 
 	return 0;
 
-cleanup_vebox_ring:
-	intel_logical_ring_cleanup(&dev_priv->engine[VECS]);
-cleanup_blt_ring:
-	intel_logical_ring_cleanup(&dev_priv->engine[BCS]);
-cleanup_bsd_ring:
-	intel_logical_ring_cleanup(&dev_priv->engine[VCS]);
-cleanup_render_ring:
-	intel_logical_ring_cleanup(&dev_priv->engine[RCS]);
+cleanup:
+	for (i = 0; i < I915_NUM_ENGINES; i++)
+		intel_logical_ring_cleanup(&dev_priv->engine[i]);
 
 	return ret;
 }
 
 static u32
-make_rpcs(struct drm_device *dev)
+make_rpcs(struct drm_i915_private *dev_priv)
 {
 	u32 rpcs = 0;
 
@@ -2291,7 +2250,7 @@ make_rpcs(struct drm_device *dev)
 	 * No explicit RPCS request is needed to ensure full
 	 * slice/subslice/EU enablement prior to Gen9.
 	*/
-	if (INTEL_INFO(dev)->gen < 9)
+	if (INTEL_GEN(dev_priv) < 9)
 		return 0;
 
 	/*
@@ -2300,24 +2259,24 @@ make_rpcs(struct drm_device *dev)
 	 * must make an explicit request through RPCS for full
 	 * enablement.
 	*/
-	if (INTEL_INFO(dev)->has_slice_pg) {
+	if (INTEL_INFO(dev_priv)->has_slice_pg) {
 		rpcs |= GEN8_RPCS_S_CNT_ENABLE;
-		rpcs |= INTEL_INFO(dev)->slice_total <<
+		rpcs |= INTEL_INFO(dev_priv)->slice_total <<
 			GEN8_RPCS_S_CNT_SHIFT;
 		rpcs |= GEN8_RPCS_ENABLE;
 	}
 
-	if (INTEL_INFO(dev)->has_subslice_pg) {
+	if (INTEL_INFO(dev_priv)->has_subslice_pg) {
 		rpcs |= GEN8_RPCS_SS_CNT_ENABLE;
-		rpcs |= INTEL_INFO(dev)->subslice_per_slice <<
+		rpcs |= INTEL_INFO(dev_priv)->subslice_per_slice <<
 			GEN8_RPCS_SS_CNT_SHIFT;
 		rpcs |= GEN8_RPCS_ENABLE;
 	}
 
-	if (INTEL_INFO(dev)->has_eu_pg) {
-		rpcs |= INTEL_INFO(dev)->eu_per_subslice <<
+	if (INTEL_INFO(dev_priv)->has_eu_pg) {
+		rpcs |= INTEL_INFO(dev_priv)->eu_per_subslice <<
 			GEN8_RPCS_EU_MIN_SHIFT;
-		rpcs |= INTEL_INFO(dev)->eu_per_subslice <<
+		rpcs |= INTEL_INFO(dev_priv)->eu_per_subslice <<
 			GEN8_RPCS_EU_MAX_SHIFT;
 		rpcs |= GEN8_RPCS_ENABLE;
 	}
@@ -2329,9 +2288,9 @@ static u32 intel_lr_indirect_ctx_offset(struct intel_engine_cs *engine)
 {
 	u32 indirect_ctx_offset;
 
-	switch (INTEL_INFO(engine->dev)->gen) {
+	switch (INTEL_GEN(engine->i915)) {
 	default:
-		MISSING_CASE(INTEL_INFO(engine->dev)->gen);
+		MISSING_CASE(INTEL_GEN(engine->i915));
 		/* fall through */
 	case 9:
 		indirect_ctx_offset =
@@ -2347,13 +2306,12 @@ static u32 intel_lr_indirect_ctx_offset(struct intel_engine_cs *engine)
 }
 
 static int
-populate_lr_context(struct intel_context *ctx,
+populate_lr_context(struct i915_gem_context *ctx,
 		    struct drm_i915_gem_object *ctx_obj,
 		    struct intel_engine_cs *engine,
 		    struct intel_ringbuffer *ringbuf)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = ctx->i915;
 	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;
 	void *vaddr;
 	u32 *reg_state;
@@ -2391,7 +2349,7 @@ populate_lr_context(struct intel_context *ctx,
 		       RING_CONTEXT_CONTROL(engine),
 		       _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH |
 					  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT |
-					  (HAS_RESOURCE_STREAMER(dev) ?
+					  (HAS_RESOURCE_STREAMER(dev_priv) ?
 					    CTX_CTRL_RS_CTX_ENABLE : 0)));
 	ASSIGN_CTX_REG(reg_state, CTX_RING_HEAD, RING_HEAD(engine->mmio_base),
 		       0);
@@ -2480,7 +2438,7 @@ populate_lr_context(struct intel_context *ctx,
 	if (engine->id == RCS) {
 		reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
 		ASSIGN_CTX_REG(reg_state, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
-			       make_rpcs(dev));
+			       make_rpcs(dev_priv));
 	}
 
 	i915_gem_object_unpin_map(ctx_obj);
@@ -2489,39 +2447,8 @@ populate_lr_context(struct intel_context *ctx,
 }
 
 /**
- * intel_lr_context_free() - free the LRC specific bits of a context
- * @ctx: the LR context to free.
- *
- * The real context freeing is done in i915_gem_context_free: this only
- * takes care of the bits that are LRC related: the per-engine backing
- * objects and the logical ringbuffer.
- */
-void intel_lr_context_free(struct intel_context *ctx)
-{
-	int i;
-
-	for (i = I915_NUM_ENGINES; --i >= 0; ) {
-		struct intel_ringbuffer *ringbuf = ctx->engine[i].ringbuf;
-		struct drm_i915_gem_object *ctx_obj = ctx->engine[i].state;
-
-		if (!ctx_obj)
-			continue;
-
-		if (ctx == ctx->i915->kernel_context) {
-			intel_unpin_ringbuffer_obj(ringbuf);
-			i915_gem_object_ggtt_unpin(ctx_obj);
-			i915_gem_object_unpin_map(ctx_obj);
-		}
-
-		WARN_ON(ctx->engine[i].pin_count);
-		intel_ringbuffer_free(ringbuf);
-		drm_gem_object_unreference(&ctx_obj->base);
-	}
-}
-
-/**
  * intel_lr_context_size() - return the size of the context for an engine
- * @ring: which engine to find the context size for
+ * @engine: which engine to find the context size for
  *
  * Each engine may require a different amount of space for a context image,
  * so when allocating (or copying) an image, this function can be used to
@@ -2537,11 +2464,11 @@ uint32_t intel_lr_context_size(struct intel_engine_cs *engine)
 {
 	int ret = 0;
 
-	WARN_ON(INTEL_INFO(engine->dev)->gen < 8);
+	WARN_ON(INTEL_GEN(engine->i915) < 8);
 
 	switch (engine->id) {
 	case RCS:
-		if (INTEL_INFO(engine->dev)->gen >= 9)
+		if (INTEL_GEN(engine->i915) >= 9)
 			ret = GEN9_LR_CONTEXT_RENDER_SIZE;
 		else
 			ret = GEN8_LR_CONTEXT_RENDER_SIZE;
@@ -2558,9 +2485,9 @@ uint32_t intel_lr_context_size(struct intel_engine_cs *engine)
 }
 
 /**
- * intel_lr_context_deferred_alloc() - create the LRC specific bits of a context
+ * execlists_context_deferred_alloc() - create the LRC specific bits of a context
  * @ctx: LR context to create.
- * @ring: engine to be used with the context.
+ * @engine: engine to be used with the context.
  *
  * This function can be called more than once, with different engines, if we plan
  * to use the context with them. The context backing objects and the ringbuffers
@@ -2570,31 +2497,29 @@ uint32_t intel_lr_context_size(struct intel_engine_cs *engine)
  *
  * Return: non-zero on error.
  */
-
-int intel_lr_context_deferred_alloc(struct intel_context *ctx,
-				    struct intel_engine_cs *engine)
+static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
+					    struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
 	struct drm_i915_gem_object *ctx_obj;
+	struct intel_context *ce = &ctx->engine[engine->id];
 	uint32_t context_size;
 	struct intel_ringbuffer *ringbuf;
 	int ret;
 
-	WARN_ON(ctx->legacy_hw_ctx.rcs_state != NULL);
-	WARN_ON(ctx->engine[engine->id].state);
+	WARN_ON(ce->state);
 
 	context_size = round_up(intel_lr_context_size(engine), 4096);
 
 	/* One extra page as the sharing data between driver and GuC */
 	context_size += PAGE_SIZE * LRC_PPHWSP_PN;
 
-	ctx_obj = i915_gem_alloc_object(dev, context_size);
-	if (!ctx_obj) {
+	ctx_obj = i915_gem_object_create(&ctx->i915->drm, context_size);
+	if (IS_ERR(ctx_obj)) {
 		DRM_DEBUG_DRIVER("Alloc LRC backing obj failed.\n");
-		return -ENOMEM;
+		return PTR_ERR(ctx_obj);
 	}
 
-	ringbuf = intel_engine_create_ringbuffer(engine, 4 * PAGE_SIZE);
+	ringbuf = intel_engine_create_ringbuffer(engine, ctx->ring_size);
 	if (IS_ERR(ringbuf)) {
 		ret = PTR_ERR(ringbuf);
 		goto error_deref_obj;
@@ -2606,48 +2531,29 @@ int intel_lr_context_deferred_alloc(struct intel_context *ctx,
 		goto error_ringbuf;
 	}
 
-	ctx->engine[engine->id].ringbuf = ringbuf;
-	ctx->engine[engine->id].state = ctx_obj;
+	ce->ringbuf = ringbuf;
+	ce->state = ctx_obj;
+	ce->initialised = engine->init_context == NULL;
 
-	if (ctx != ctx->i915->kernel_context && engine->init_context) {
-		struct drm_i915_gem_request *req;
-
-		req = i915_gem_request_alloc(engine, ctx);
-		if (IS_ERR(req)) {
-			ret = PTR_ERR(req);
-			DRM_ERROR("ring create req: %d\n", ret);
-			goto error_ringbuf;
-		}
-
-		ret = engine->init_context(req);
-		i915_add_request_no_flush(req);
-		if (ret) {
-			DRM_ERROR("ring init context: %d\n",
-				ret);
-			goto error_ringbuf;
-		}
-	}
 	return 0;
 
 error_ringbuf:
 	intel_ringbuffer_free(ringbuf);
 error_deref_obj:
 	drm_gem_object_unreference(&ctx_obj->base);
-	ctx->engine[engine->id].ringbuf = NULL;
-	ctx->engine[engine->id].state = NULL;
+	ce->ringbuf = NULL;
+	ce->state = NULL;
 	return ret;
 }
 
 void intel_lr_context_reset(struct drm_i915_private *dev_priv,
-			    struct intel_context *ctx)
+			    struct i915_gem_context *ctx)
 {
 	struct intel_engine_cs *engine;
 
 	for_each_engine(engine, dev_priv) {
-		struct drm_i915_gem_object *ctx_obj =
-				ctx->engine[engine->id].state;
-		struct intel_ringbuffer *ringbuf =
-				ctx->engine[engine->id].ringbuf;
+		struct intel_context *ce = &ctx->engine[engine->id];
+		struct drm_i915_gem_object *ctx_obj = ce->state;
 		void *vaddr;
 		uint32_t *reg_state;
 
@@ -2666,7 +2572,7 @@ void intel_lr_context_reset(struct drm_i915_private *dev_priv,
 
 		i915_gem_object_unpin_map(ctx_obj);
 
-		ringbuf->head = 0;
-		ringbuf->tail = 0;
+		ce->ringbuf->head = 0;
+		ce->ringbuf->tail = 0;
 	}
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 60a7385bc531..2b8255c19dcc 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -57,6 +57,11 @@
 #define GEN8_CSB_READ_PTR(csb_status) \
 	(((csb_status) & GEN8_CSB_READ_PTR_MASK) >> 8)
 
+enum {
+	INTEL_CONTEXT_SCHEDULE_IN = 0,
+	INTEL_CONTEXT_SCHEDULE_OUT,
+};
+
 /* Logical Rings */
 int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request);
 int intel_logical_ring_reserve_space(struct drm_i915_gem_request *request);
@@ -99,30 +104,27 @@ static inline void intel_logical_ring_emit_reg(struct intel_ringbuffer *ringbuf,
 #define LRC_PPHWSP_PN	(LRC_GUCSHR_PN + 1)
 #define LRC_STATE_PN	(LRC_PPHWSP_PN + 1)
 
-void intel_lr_context_free(struct intel_context *ctx);
+struct i915_gem_context;
+
 uint32_t intel_lr_context_size(struct intel_engine_cs *engine);
-int intel_lr_context_deferred_alloc(struct intel_context *ctx,
-				    struct intel_engine_cs *engine);
-void intel_lr_context_unpin(struct intel_context *ctx,
+void intel_lr_context_unpin(struct i915_gem_context *ctx,
 			    struct intel_engine_cs *engine);
 
 struct drm_i915_private;
 
 void intel_lr_context_reset(struct drm_i915_private *dev_priv,
-			    struct intel_context *ctx);
-uint64_t intel_lr_context_descriptor(struct intel_context *ctx,
+			    struct i915_gem_context *ctx);
+uint64_t intel_lr_context_descriptor(struct i915_gem_context *ctx,
 				     struct intel_engine_cs *engine);
 
-u32 intel_execlists_ctx_id(struct intel_context *ctx,
-			   struct intel_engine_cs *engine);
-
 /* Execlists */
-int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);
+int intel_sanitize_enable_execlists(struct drm_i915_private *dev_priv,
+				    int enable_execlists);
 struct i915_execbuffer_params;
 int intel_execlists_submission(struct i915_execbuffer_params *params,
 			       struct drm_i915_gem_execbuffer2 *args,
 			       struct list_head *vmas);
 
-void intel_execlists_retire_requests(struct intel_engine_cs *engine);
+void intel_execlists_cancel_requests(struct intel_engine_cs *engine);
 
 #endif /* _INTEL_LRC_H_ */
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 96281e628d2a..49550470483e 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -72,7 +72,7 @@ static bool intel_lvds_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
@@ -106,7 +106,7 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
 				  struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
 	u32 tmp, flags = 0;
 
@@ -140,7 +140,7 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder)
 {
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	int pipe = crtc->pipe;
@@ -184,13 +184,13 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder)
 	 * panels behave in the two modes. For now, let's just maintain the
 	 * value we got from the BIOS.
 	 */
-	 temp &= ~LVDS_A3_POWER_MASK;
-	 temp |= lvds_encoder->a3_power;
+	temp &= ~LVDS_A3_POWER_MASK;
+	temp |= lvds_encoder->a3_power;
 
 	/* Set the dithering flag on LVDS as needed, note that there is no
 	 * special lvds dither control bit on pch-split platforms, dithering is
 	 * only controlled through the PIPECONF reg. */
-	if (INTEL_INFO(dev)->gen == 4) {
+	if (IS_GEN4(dev_priv)) {
 		/* Bspec wording suggests that LVDS port dithering only exists
 		 * for 18bpp panels. */
 		if (crtc->config->dither && crtc->config->pipe_bpp == 18)
@@ -216,7 +216,7 @@ static void intel_enable_lvds(struct intel_encoder *encoder)
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
 	struct intel_connector *intel_connector =
 		&lvds_encoder->attached_connector->base;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t ctl_reg, stat_reg;
 
 	if (HAS_PCH_SPLIT(dev)) {
@@ -231,7 +231,7 @@ static void intel_enable_lvds(struct intel_encoder *encoder)
 
 	I915_WRITE(ctl_reg, I915_READ(ctl_reg) | POWER_TARGET_ON);
 	POSTING_READ(lvds_encoder->reg);
-	if (wait_for((I915_READ(stat_reg) & PP_ON) != 0, 1000))
+	if (intel_wait_for_register(dev_priv, stat_reg, PP_ON, PP_ON, 1000))
 		DRM_ERROR("timed out waiting for panel to power on\n");
 
 	intel_panel_enable_backlight(intel_connector);
@@ -241,7 +241,7 @@ static void intel_disable_lvds(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t ctl_reg, stat_reg;
 
 	if (HAS_PCH_SPLIT(dev)) {
@@ -253,7 +253,7 @@ static void intel_disable_lvds(struct intel_encoder *encoder)
 	}
 
 	I915_WRITE(ctl_reg, I915_READ(ctl_reg) & ~POWER_TARGET_ON);
-	if (wait_for((I915_READ(stat_reg) & PP_ON) == 0, 1000))
+	if (intel_wait_for_register(dev_priv, stat_reg, PP_ON, 0, 1000))
 		DRM_ERROR("timed out waiting for panel to power off\n");
 
 	I915_WRITE(lvds_encoder->reg, I915_READ(lvds_encoder->reg) & ~LVDS_PORT_EN);
@@ -442,7 +442,7 @@ static int intel_lid_notify(struct notifier_block *nb, unsigned long val,
 		container_of(nb, struct intel_lvds_connector, lid_notifier);
 	struct drm_connector *connector = &lvds_connector->base.base;
 	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (dev->switch_power_state != DRM_SWITCH_POWER_ON)
 		return NOTIFY_OK;
@@ -547,7 +547,6 @@ static int intel_lvds_set_property(struct drm_connector *connector,
 static const struct drm_connector_helper_funcs intel_lvds_connector_helper_funcs = {
 	.get_modes = intel_lvds_get_modes,
 	.mode_valid = intel_lvds_mode_valid,
-	.best_encoder = intel_best_encoder,
 };
 
 static const struct drm_connector_funcs intel_lvds_connector_funcs = {
@@ -556,6 +555,8 @@ static const struct drm_connector_funcs intel_lvds_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = intel_lvds_set_property,
 	.atomic_get_property = intel_connector_atomic_get_property,
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
 	.destroy = intel_lvds_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
@@ -810,27 +811,29 @@ static const struct dmi_system_id intel_dual_link_lvds[] = {
 	{ }	/* terminating entry */
 };
 
-bool intel_is_dual_link_lvds(struct drm_device *dev)
+struct intel_encoder *intel_get_lvds_encoder(struct drm_device *dev)
 {
-	struct intel_encoder *encoder;
-	struct intel_lvds_encoder *lvds_encoder;
+	struct intel_encoder *intel_encoder;
 
-	for_each_intel_encoder(dev, encoder) {
-		if (encoder->type == INTEL_OUTPUT_LVDS) {
-			lvds_encoder = to_lvds_encoder(&encoder->base);
+	for_each_intel_encoder(dev, intel_encoder)
+		if (intel_encoder->type == INTEL_OUTPUT_LVDS)
+			return intel_encoder;
 
-			return lvds_encoder->is_dual_link;
-		}
-	}
+	return NULL;
+}
 
-	return false;
+bool intel_is_dual_link_lvds(struct drm_device *dev)
+{
+	struct intel_encoder *encoder = intel_get_lvds_encoder(dev);
+
+	return encoder && to_lvds_encoder(&encoder->base)->is_dual_link;
 }
 
 static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder)
 {
 	struct drm_device *dev = lvds_encoder->base.base.dev;
 	unsigned int val;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* use the module option value if specified */
 	if (i915.lvds_channel_mode > 0)
@@ -880,7 +883,7 @@ static bool intel_lvds_supported(struct drm_device *dev)
  */
 void intel_lvds_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_lvds_encoder *lvds_encoder;
 	struct intel_encoder *intel_encoder;
 	struct intel_lvds_connector *lvds_connector;
@@ -978,7 +981,7 @@ void intel_lvds_init(struct drm_device *dev)
 			   DRM_MODE_CONNECTOR_LVDS);
 
 	drm_encoder_init(dev, &intel_encoder->base, &intel_lvds_enc_funcs,
-			 DRM_MODE_ENCODER_LVDS, NULL);
+			 DRM_MODE_ENCODER_LVDS, "LVDS");
 
 	intel_encoder->enable = intel_enable_lvds;
 	intel_encoder->pre_enable = intel_pre_enable_lvds;
@@ -992,7 +995,6 @@ void intel_lvds_init(struct drm_device *dev)
 	intel_encoder->get_hw_state = intel_lvds_get_hw_state;
 	intel_encoder->get_config = intel_lvds_get_config;
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
-	intel_connector->unregister = intel_connector_unregister;
 
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_encoder->type = INTEL_OUTPUT_LVDS;
@@ -1119,6 +1121,7 @@ out:
 	mutex_unlock(&dev->mode_config.mutex);
 
 	intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
+	intel_panel_setup_backlight(connector, INVALID_PIPE);
 
 	lvds_encoder->is_dual_link = compute_is_dual_link_lvds(lvds_encoder);
 	DRM_DEBUG_KMS("detected %s-link lvds configuration\n",
@@ -1131,9 +1134,6 @@ out:
 		DRM_DEBUG_KMS("lid notifier registration failed\n");
 		lvds_connector->lid_notifier.notifier_call = NULL;
 	}
-	drm_connector_register(connector);
-
-	intel_panel_setup_backlight(connector, INVALID_PIPE);
 
 	return;
 
diff --git a/drivers/gpu/drm/i915/intel_mocs.c b/drivers/gpu/drm/i915/intel_mocs.c
index 6ba4bf7f2a89..927825f5b284 100644
--- a/drivers/gpu/drm/i915/intel_mocs.c
+++ b/drivers/gpu/drm/i915/intel_mocs.c
@@ -66,9 +66,10 @@ struct drm_i915_mocs_table {
 #define L3_WB			3
 
 /* Target cache */
-#define ELLC			0
-#define LLC			1
-#define LLC_ELLC		2
+#define LE_TC_PAGETABLE		0
+#define LE_TC_LLC		1
+#define LE_TC_LLC_ELLC		2
+#define LE_TC_LLC_ELLC_ALT	3
 
 /*
  * MOCS tables
@@ -96,34 +97,67 @@ struct drm_i915_mocs_table {
  *       end.
  */
 static const struct drm_i915_mocs_entry skylake_mocs_table[] = {
-	/* { 0x00000009, 0x0010 } */
-	{ (LE_CACHEABILITY(LE_UC) | LE_TGT_CACHE(LLC_ELLC) | LE_LRUM(0) |
-	   LE_AOM(0) | LE_RSC(0) | LE_SCC(0) | LE_PFM(0) | LE_SCF(0)),
-	  (L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_UC)) },
-	/* { 0x00000038, 0x0030 } */
-	{ (LE_CACHEABILITY(LE_PAGETABLE) | LE_TGT_CACHE(LLC_ELLC) | LE_LRUM(3) |
-	   LE_AOM(0) | LE_RSC(0) | LE_SCC(0) | LE_PFM(0) | LE_SCF(0)),
-	  (L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_WB)) },
-	/* { 0x0000003b, 0x0030 } */
-	{ (LE_CACHEABILITY(LE_WB) | LE_TGT_CACHE(LLC_ELLC) | LE_LRUM(3) |
-	   LE_AOM(0) | LE_RSC(0) | LE_SCC(0) | LE_PFM(0) | LE_SCF(0)),
-	  (L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_WB)) }
+	{ /* 0x00000009 */
+	  .control_value = LE_CACHEABILITY(LE_UC) |
+			   LE_TGT_CACHE(LE_TC_LLC_ELLC) |
+			   LE_LRUM(0) | LE_AOM(0) | LE_RSC(0) | LE_SCC(0) |
+			   LE_PFM(0) | LE_SCF(0),
+
+	  /* 0x0010 */
+	  .l3cc_value =    L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_UC),
+	},
+	{
+	  /* 0x00000038 */
+	  .control_value = LE_CACHEABILITY(LE_PAGETABLE) |
+			   LE_TGT_CACHE(LE_TC_LLC_ELLC) |
+			   LE_LRUM(3) | LE_AOM(0) | LE_RSC(0) | LE_SCC(0) |
+			   LE_PFM(0) | LE_SCF(0),
+	  /* 0x0030 */
+	  .l3cc_value =    L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_WB),
+	},
+	{
+	  /* 0x0000003b */
+	  .control_value = LE_CACHEABILITY(LE_WB) |
+			   LE_TGT_CACHE(LE_TC_LLC_ELLC) |
+			   LE_LRUM(3) | LE_AOM(0) | LE_RSC(0) | LE_SCC(0) |
+			   LE_PFM(0) | LE_SCF(0),
+	  /* 0x0030 */
+	  .l3cc_value =   L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_WB),
+	},
 };
 
 /* NOTE: the LE_TGT_CACHE is not used on Broxton */
 static const struct drm_i915_mocs_entry broxton_mocs_table[] = {
-	/* { 0x00000009, 0x0010 } */
-	{ (LE_CACHEABILITY(LE_UC) | LE_TGT_CACHE(LLC_ELLC) | LE_LRUM(0) |
-	   LE_AOM(0) | LE_RSC(0) | LE_SCC(0) | LE_PFM(0) | LE_SCF(0)),
-	  (L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_UC)) },
-	/* { 0x00000038, 0x0030 } */
-	{ (LE_CACHEABILITY(LE_PAGETABLE) | LE_TGT_CACHE(LLC_ELLC) | LE_LRUM(3) |
-	   LE_AOM(0) | LE_RSC(0) | LE_SCC(0) | LE_PFM(0) | LE_SCF(0)),
-	  (L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_WB)) },
-	/* { 0x0000003b, 0x0030 } */
-	{ (LE_CACHEABILITY(LE_WB) | LE_TGT_CACHE(LLC_ELLC) | LE_LRUM(3) |
-	   LE_AOM(0) | LE_RSC(0) | LE_SCC(0) | LE_PFM(0) | LE_SCF(0)),
-	  (L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_WB)) }
+	{
+	  /* 0x00000009 */
+	  .control_value = LE_CACHEABILITY(LE_UC) |
+			   LE_TGT_CACHE(LE_TC_LLC_ELLC) |
+			   LE_LRUM(0) | LE_AOM(0) | LE_RSC(0) | LE_SCC(0) |
+			   LE_PFM(0) | LE_SCF(0),
+
+	  /* 0x0010 */
+	  .l3cc_value =    L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_UC),
+	},
+	{
+	  /* 0x00000038 */
+	  .control_value = LE_CACHEABILITY(LE_PAGETABLE) |
+			   LE_TGT_CACHE(LE_TC_LLC_ELLC) |
+			   LE_LRUM(3) | LE_AOM(0) | LE_RSC(0) | LE_SCC(0) |
+			   LE_PFM(0) | LE_SCF(0),
+
+	  /* 0x0030 */
+	  .l3cc_value =    L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_WB),
+	},
+	{
+	  /* 0x00000039 */
+	  .control_value = LE_CACHEABILITY(LE_UC) |
+			   LE_TGT_CACHE(LE_TC_LLC_ELLC) |
+			   LE_LRUM(3) | LE_AOM(0) | LE_RSC(0) | LE_SCC(0) |
+			   LE_PFM(0) | LE_SCF(0),
+
+	  /* 0x0030 */
+	  .l3cc_value =    L3_ESC(0) | L3_SCC(0) | L3_CACHEABILITY(L3_WB),
+	},
 };
 
 /**
@@ -156,6 +190,16 @@ static bool get_mocs_settings(struct drm_i915_private *dev_priv,
 			  "Platform that should have a MOCS table does not.\n");
 	}
 
+	/* WaDisableSkipCaching:skl,bxt,kbl */
+	if (IS_GEN9(dev_priv)) {
+		int i;
+
+		for (i = 0; i < table->size; i++)
+			if (WARN_ON(table->table[i].l3cc_value &
+				    (L3_ESC(1) | L3_SCC(0x7))))
+				return false;
+	}
+
 	return result;
 }
 
@@ -189,7 +233,7 @@ static i915_reg_t mocs_register(enum intel_engine_id ring, int index)
  */
 int intel_mocs_init_engine(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = to_i915(engine->dev);
+	struct drm_i915_private *dev_priv = engine->i915;
 	struct drm_i915_mocs_table table;
 	unsigned int index;
 
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index 38a4c8ce7e63..f2584d0a01ab 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -82,7 +82,7 @@ void
 intel_attach_force_audio_property(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_property *prop;
 
 	prop = dev_priv->force_audio_property;
@@ -109,7 +109,7 @@ void
 intel_attach_broadcast_rgb_property(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_property *prop;
 
 	prop = dev_priv->broadcast_rgb_property;
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 16e209d326b6..adca262d591a 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -232,18 +232,36 @@ struct opregion_asle_ext {
 #define SWSCI_SBCB_POST_VBE_PM		SWSCI_FUNCTION_CODE(SWSCI_SBCB, 19)
 #define SWSCI_SBCB_ENABLE_DISABLE_AUDIO	SWSCI_FUNCTION_CODE(SWSCI_SBCB, 21)
 
-#define ACPI_OTHER_OUTPUT (0<<8)
-#define ACPI_VGA_OUTPUT (1<<8)
-#define ACPI_TV_OUTPUT (2<<8)
-#define ACPI_DIGITAL_OUTPUT (3<<8)
-#define ACPI_LVDS_OUTPUT (4<<8)
+/*
+ * ACPI Specification, Revision 5.0, Appendix B.3.2 _DOD (Enumerate All Devices
+ * Attached to the Display Adapter).
+ */
+#define ACPI_DISPLAY_INDEX_SHIFT		0
+#define ACPI_DISPLAY_INDEX_MASK			(0xf << 0)
+#define ACPI_DISPLAY_PORT_ATTACHMENT_SHIFT	4
+#define ACPI_DISPLAY_PORT_ATTACHMENT_MASK	(0xf << 4)
+#define ACPI_DISPLAY_TYPE_SHIFT			8
+#define ACPI_DISPLAY_TYPE_MASK			(0xf << 8)
+#define ACPI_DISPLAY_TYPE_OTHER			(0 << 8)
+#define ACPI_DISPLAY_TYPE_VGA			(1 << 8)
+#define ACPI_DISPLAY_TYPE_TV			(2 << 8)
+#define ACPI_DISPLAY_TYPE_EXTERNAL_DIGITAL	(3 << 8)
+#define ACPI_DISPLAY_TYPE_INTERNAL_DIGITAL	(4 << 8)
+#define ACPI_VENDOR_SPECIFIC_SHIFT		12
+#define ACPI_VENDOR_SPECIFIC_MASK		(0xf << 12)
+#define ACPI_BIOS_CAN_DETECT			(1 << 16)
+#define ACPI_DEPENDS_ON_VGA			(1 << 17)
+#define ACPI_PIPE_ID_SHIFT			18
+#define ACPI_PIPE_ID_MASK			(7 << 18)
+#define ACPI_DEVICE_ID_SCHEME			(1 << 31)
 
 #define MAX_DSLP	1500
 
-static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
+static int swsci(struct drm_i915_private *dev_priv,
+		 u32 function, u32 parm, u32 *parm_out)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct opregion_swsci *swsci = dev_priv->opregion.swsci;
+	struct pci_dev *pdev = dev_priv->drm.pdev;
 	u32 main_function, sub_function, scic;
 	u16 swsci_val;
 	u32 dslp;
@@ -293,16 +311,16 @@ static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 	swsci->scic = scic;
 
 	/* Ensure SCI event is selected and event trigger is cleared. */
-	pci_read_config_word(dev->pdev, SWSCI, &swsci_val);
+	pci_read_config_word(pdev, SWSCI, &swsci_val);
 	if (!(swsci_val & SWSCI_SCISEL) || (swsci_val & SWSCI_GSSCIE)) {
 		swsci_val |= SWSCI_SCISEL;
 		swsci_val &= ~SWSCI_GSSCIE;
-		pci_write_config_word(dev->pdev, SWSCI, swsci_val);
+		pci_write_config_word(pdev, SWSCI, swsci_val);
 	}
 
 	/* Use event trigger to tell bios to check the mail. */
 	swsci_val |= SWSCI_GSSCIE;
-	pci_write_config_word(dev->pdev, SWSCI, swsci_val);
+	pci_write_config_word(pdev, SWSCI, swsci_val);
 
 	/* Poll for the result. */
 #define C (((scic = swsci->scic) & SWSCI_SCIC_INDICATOR) == 0)
@@ -336,13 +354,13 @@ static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
 int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder,
 				  bool enable)
 {
-	struct drm_device *dev = intel_encoder->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev);
 	u32 parm = 0;
 	u32 type = 0;
 	u32 port;
 
 	/* don't care about old stuff for now */
-	if (!HAS_DDI(dev))
+	if (!HAS_DDI(dev_priv))
 		return 0;
 
 	if (intel_encoder->type == INTEL_OUTPUT_DSI)
@@ -365,7 +383,7 @@ int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder,
 		type = DISPLAY_TYPE_CRT;
 		break;
 	case INTEL_OUTPUT_UNKNOWN:
-	case INTEL_OUTPUT_DISPLAYPORT:
+	case INTEL_OUTPUT_DP:
 	case INTEL_OUTPUT_HDMI:
 	case INTEL_OUTPUT_DP_MST:
 		type = DISPLAY_TYPE_EXTERNAL_FLAT_PANEL;
@@ -382,7 +400,7 @@ int intel_opregion_notify_encoder(struct intel_encoder *intel_encoder,
 
 	parm |= type << (16 + port * 3);
 
-	return swsci(dev, SWSCI_SBCB_DISPLAY_POWER_STATE, parm, NULL);
+	return swsci(dev_priv, SWSCI_SBCB_DISPLAY_POWER_STATE, parm, NULL);
 }
 
 static const struct {
@@ -396,27 +414,28 @@ static const struct {
 	{ PCI_D3cold,	0x04 },
 };
 
-int intel_opregion_notify_adapter(struct drm_device *dev, pci_power_t state)
+int intel_opregion_notify_adapter(struct drm_i915_private *dev_priv,
+				  pci_power_t state)
 {
 	int i;
 
-	if (!HAS_DDI(dev))
+	if (!HAS_DDI(dev_priv))
 		return 0;
 
 	for (i = 0; i < ARRAY_SIZE(power_state_map); i++) {
 		if (state == power_state_map[i].pci_power_state)
-			return swsci(dev, SWSCI_SBCB_ADAPTER_POWER_STATE,
+			return swsci(dev_priv, SWSCI_SBCB_ADAPTER_POWER_STATE,
 				     power_state_map[i].parm, NULL);
 	}
 
 	return -EINVAL;
 }
 
-static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
+static u32 asle_set_backlight(struct drm_i915_private *dev_priv, u32 bclp)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_connector *connector;
 	struct opregion_asle *asle = dev_priv->opregion.asle;
+	struct drm_device *dev = &dev_priv->drm;
 
 	DRM_DEBUG_DRIVER("bclp = 0x%08x\n", bclp);
 
@@ -449,7 +468,7 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 	return 0;
 }
 
-static u32 asle_set_als_illum(struct drm_device *dev, u32 alsi)
+static u32 asle_set_als_illum(struct drm_i915_private *dev_priv, u32 alsi)
 {
 	/* alsi is the current ALS reading in lux. 0 indicates below sensor
 	   range, 0xffff indicates above sensor range. 1-0xfffe are valid */
@@ -457,13 +476,13 @@ static u32 asle_set_als_illum(struct drm_device *dev, u32 alsi)
 	return ASLC_ALS_ILLUM_FAILED;
 }
 
-static u32 asle_set_pwm_freq(struct drm_device *dev, u32 pfmb)
+static u32 asle_set_pwm_freq(struct drm_i915_private *dev_priv, u32 pfmb)
 {
 	DRM_DEBUG_DRIVER("PWM freq is not supported\n");
 	return ASLC_PWM_FREQ_FAILED;
 }
 
-static u32 asle_set_pfit(struct drm_device *dev, u32 pfit)
+static u32 asle_set_pfit(struct drm_i915_private *dev_priv, u32 pfit)
 {
 	/* Panel fitting is currently controlled by the X code, so this is a
 	   noop until modesetting support works fully */
@@ -471,13 +490,13 @@ static u32 asle_set_pfit(struct drm_device *dev, u32 pfit)
 	return ASLC_PFIT_FAILED;
 }
 
-static u32 asle_set_supported_rotation_angles(struct drm_device *dev, u32 srot)
+static u32 asle_set_supported_rotation_angles(struct drm_i915_private *dev_priv, u32 srot)
 {
 	DRM_DEBUG_DRIVER("SROT is not supported\n");
 	return ASLC_ROTATION_ANGLES_FAILED;
 }
 
-static u32 asle_set_button_array(struct drm_device *dev, u32 iuer)
+static u32 asle_set_button_array(struct drm_i915_private *dev_priv, u32 iuer)
 {
 	if (!iuer)
 		DRM_DEBUG_DRIVER("Button array event is not supported (nothing)\n");
@@ -495,7 +514,7 @@ static u32 asle_set_button_array(struct drm_device *dev, u32 iuer)
 	return ASLC_BUTTON_ARRAY_FAILED;
 }
 
-static u32 asle_set_convertible(struct drm_device *dev, u32 iuer)
+static u32 asle_set_convertible(struct drm_i915_private *dev_priv, u32 iuer)
 {
 	if (iuer & ASLE_IUER_CONVERTIBLE)
 		DRM_DEBUG_DRIVER("Convertible is not supported (clamshell)\n");
@@ -505,7 +524,7 @@ static u32 asle_set_convertible(struct drm_device *dev, u32 iuer)
 	return ASLC_CONVERTIBLE_FAILED;
 }
 
-static u32 asle_set_docking(struct drm_device *dev, u32 iuer)
+static u32 asle_set_docking(struct drm_i915_private *dev_priv, u32 iuer)
 {
 	if (iuer & ASLE_IUER_DOCKING)
 		DRM_DEBUG_DRIVER("Docking is not supported (docked)\n");
@@ -515,7 +534,7 @@ static u32 asle_set_docking(struct drm_device *dev, u32 iuer)
 	return ASLC_DOCKING_FAILED;
 }
 
-static u32 asle_isct_state(struct drm_device *dev)
+static u32 asle_isct_state(struct drm_i915_private *dev_priv)
 {
 	DRM_DEBUG_DRIVER("ISCT is not supported\n");
 	return ASLC_ISCT_STATE_FAILED;
@@ -527,7 +546,6 @@ static void asle_work(struct work_struct *work)
 		container_of(work, struct intel_opregion, asle_work);
 	struct drm_i915_private *dev_priv =
 		container_of(opregion, struct drm_i915_private, opregion);
-	struct drm_device *dev = dev_priv->dev;
 	struct opregion_asle *asle = dev_priv->opregion.asle;
 	u32 aslc_stat = 0;
 	u32 aslc_req;
@@ -544,40 +562,38 @@ static void asle_work(struct work_struct *work)
 	}
 
 	if (aslc_req & ASLC_SET_ALS_ILLUM)
-		aslc_stat |= asle_set_als_illum(dev, asle->alsi);
+		aslc_stat |= asle_set_als_illum(dev_priv, asle->alsi);
 
 	if (aslc_req & ASLC_SET_BACKLIGHT)
-		aslc_stat |= asle_set_backlight(dev, asle->bclp);
+		aslc_stat |= asle_set_backlight(dev_priv, asle->bclp);
 
 	if (aslc_req & ASLC_SET_PFIT)
-		aslc_stat |= asle_set_pfit(dev, asle->pfit);
+		aslc_stat |= asle_set_pfit(dev_priv, asle->pfit);
 
 	if (aslc_req & ASLC_SET_PWM_FREQ)
-		aslc_stat |= asle_set_pwm_freq(dev, asle->pfmb);
+		aslc_stat |= asle_set_pwm_freq(dev_priv, asle->pfmb);
 
 	if (aslc_req & ASLC_SUPPORTED_ROTATION_ANGLES)
-		aslc_stat |= asle_set_supported_rotation_angles(dev,
+		aslc_stat |= asle_set_supported_rotation_angles(dev_priv,
 							asle->srot);
 
 	if (aslc_req & ASLC_BUTTON_ARRAY)
-		aslc_stat |= asle_set_button_array(dev, asle->iuer);
+		aslc_stat |= asle_set_button_array(dev_priv, asle->iuer);
 
 	if (aslc_req & ASLC_CONVERTIBLE_INDICATOR)
-		aslc_stat |= asle_set_convertible(dev, asle->iuer);
+		aslc_stat |= asle_set_convertible(dev_priv, asle->iuer);
 
 	if (aslc_req & ASLC_DOCKING_INDICATOR)
-		aslc_stat |= asle_set_docking(dev, asle->iuer);
+		aslc_stat |= asle_set_docking(dev_priv, asle->iuer);
 
 	if (aslc_req & ASLC_ISCT_STATE_CHANGE)
-		aslc_stat |= asle_isct_state(dev);
+		aslc_stat |= asle_isct_state(dev_priv);
 
 	asle->aslc = aslc_stat;
 }
 
-void intel_opregion_asle_intr(struct drm_device *dev)
+void intel_opregion_asle_intr(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	if (dev_priv->opregion.asle)
 		schedule_work(&dev_priv->opregion.asle_work);
 }
@@ -658,10 +674,51 @@ static void set_did(struct intel_opregion *opregion, int i, u32 val)
 	}
 }
 
-static void intel_didl_outputs(struct drm_device *dev)
+static u32 acpi_display_type(struct drm_connector *connector)
+{
+	u32 display_type;
+
+	switch (connector->connector_type) {
+	case DRM_MODE_CONNECTOR_VGA:
+	case DRM_MODE_CONNECTOR_DVIA:
+		display_type = ACPI_DISPLAY_TYPE_VGA;
+		break;
+	case DRM_MODE_CONNECTOR_Composite:
+	case DRM_MODE_CONNECTOR_SVIDEO:
+	case DRM_MODE_CONNECTOR_Component:
+	case DRM_MODE_CONNECTOR_9PinDIN:
+	case DRM_MODE_CONNECTOR_TV:
+		display_type = ACPI_DISPLAY_TYPE_TV;
+		break;
+	case DRM_MODE_CONNECTOR_DVII:
+	case DRM_MODE_CONNECTOR_DVID:
+	case DRM_MODE_CONNECTOR_DisplayPort:
+	case DRM_MODE_CONNECTOR_HDMIA:
+	case DRM_MODE_CONNECTOR_HDMIB:
+		display_type = ACPI_DISPLAY_TYPE_EXTERNAL_DIGITAL;
+		break;
+	case DRM_MODE_CONNECTOR_LVDS:
+	case DRM_MODE_CONNECTOR_eDP:
+	case DRM_MODE_CONNECTOR_DSI:
+		display_type = ACPI_DISPLAY_TYPE_INTERNAL_DIGITAL;
+		break;
+	case DRM_MODE_CONNECTOR_Unknown:
+	case DRM_MODE_CONNECTOR_VIRTUAL:
+		display_type = ACPI_DISPLAY_TYPE_OTHER;
+		break;
+	default:
+		MISSING_CASE(connector->connector_type);
+		display_type = ACPI_DISPLAY_TYPE_OTHER;
+		break;
+	}
+
+	return display_type;
+}
+
+static void intel_didl_outputs(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_opregion *opregion = &dev_priv->opregion;
+	struct pci_dev *pdev = dev_priv->drm.pdev;
 	struct drm_connector *connector;
 	acpi_handle handle;
 	struct acpi_device *acpi_dev, *acpi_cdev, *acpi_video_bus = NULL;
@@ -670,7 +727,7 @@ static void intel_didl_outputs(struct drm_device *dev)
 	u32 temp, max_outputs;
 	int i = 0;
 
-	handle = ACPI_HANDLE(&dev->pdev->dev);
+	handle = ACPI_HANDLE(&pdev->dev);
 	if (!handle || acpi_bus_get_device(handle, &acpi_dev))
 		return;
 
@@ -725,45 +782,25 @@ end:
 
 blind_set:
 	i = 0;
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		int output_type = ACPI_OTHER_OUTPUT;
+	list_for_each_entry(connector,
+			    &dev_priv->drm.mode_config.connector_list, head) {
+		int display_type = acpi_display_type(connector);
+
 		if (i >= max_outputs) {
 			DRM_DEBUG_KMS("More than %u outputs in connector list\n",
 				      max_outputs);
 			return;
 		}
-		switch (connector->connector_type) {
-		case DRM_MODE_CONNECTOR_VGA:
-		case DRM_MODE_CONNECTOR_DVIA:
-			output_type = ACPI_VGA_OUTPUT;
-			break;
-		case DRM_MODE_CONNECTOR_Composite:
-		case DRM_MODE_CONNECTOR_SVIDEO:
-		case DRM_MODE_CONNECTOR_Component:
-		case DRM_MODE_CONNECTOR_9PinDIN:
-			output_type = ACPI_TV_OUTPUT;
-			break;
-		case DRM_MODE_CONNECTOR_DVII:
-		case DRM_MODE_CONNECTOR_DVID:
-		case DRM_MODE_CONNECTOR_DisplayPort:
-		case DRM_MODE_CONNECTOR_HDMIA:
-		case DRM_MODE_CONNECTOR_HDMIB:
-			output_type = ACPI_DIGITAL_OUTPUT;
-			break;
-		case DRM_MODE_CONNECTOR_LVDS:
-			output_type = ACPI_LVDS_OUTPUT;
-			break;
-		}
+
 		temp = get_did(opregion, i);
-		set_did(opregion, i, temp | (1 << 31) | output_type | i);
+		set_did(opregion, i, temp | (1 << 31) | display_type | i);
 		i++;
 	}
 	goto end;
 }
 
-static void intel_setup_cadls(struct drm_device *dev)
+static void intel_setup_cadls(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_opregion *opregion = &dev_priv->opregion;
 	int i = 0;
 	u32 disp_id;
@@ -780,17 +817,16 @@ static void intel_setup_cadls(struct drm_device *dev)
 	} while (++i < 8 && disp_id != 0);
 }
 
-void intel_opregion_init(struct drm_device *dev)
+void intel_opregion_register(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_opregion *opregion = &dev_priv->opregion;
 
 	if (!opregion->header)
 		return;
 
 	if (opregion->acpi) {
-		intel_didl_outputs(dev);
-		intel_setup_cadls(dev);
+		intel_didl_outputs(dev_priv);
+		intel_setup_cadls(dev_priv);
 
 		/* Notify BIOS we are ready to handle ACPI video ext notifs.
 		 * Right now, all the events are handled by the ACPI video module.
@@ -808,9 +844,8 @@ void intel_opregion_init(struct drm_device *dev)
 	}
 }
 
-void intel_opregion_fini(struct drm_device *dev)
+void intel_opregion_unregister(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_opregion *opregion = &dev_priv->opregion;
 
 	if (!opregion->header)
@@ -842,9 +877,8 @@ void intel_opregion_fini(struct drm_device *dev)
 	opregion->lid_state = NULL;
 }
 
-static void swsci_setup(struct drm_device *dev)
+static void swsci_setup(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_opregion *opregion = &dev_priv->opregion;
 	bool requested_callbacks = false;
 	u32 tmp;
@@ -854,7 +888,7 @@ static void swsci_setup(struct drm_device *dev)
 	opregion->swsci_sbcb_sub_functions = 1;
 
 	/* We use GBDA to ask for supported GBDA calls. */
-	if (swsci(dev, SWSCI_GBDA_SUPPORTED_CALLS, 0, &tmp) == 0) {
+	if (swsci(dev_priv, SWSCI_GBDA_SUPPORTED_CALLS, 0, &tmp) == 0) {
 		/* make the bits match the sub-function codes */
 		tmp <<= 1;
 		opregion->swsci_gbda_sub_functions |= tmp;
@@ -865,7 +899,7 @@ static void swsci_setup(struct drm_device *dev)
 	 * must not call interfaces that are not specifically requested by the
 	 * bios.
 	 */
-	if (swsci(dev, SWSCI_GBDA_REQUESTED_CALLBACKS, 0, &tmp) == 0) {
+	if (swsci(dev_priv, SWSCI_GBDA_REQUESTED_CALLBACKS, 0, &tmp) == 0) {
 		/* here, the bits already match sub-function codes */
 		opregion->swsci_sbcb_sub_functions |= tmp;
 		requested_callbacks = true;
@@ -876,7 +910,7 @@ static void swsci_setup(struct drm_device *dev)
 	 * the callback is _requested_. But we still can't call interfaces that
 	 * are not requested.
 	 */
-	if (swsci(dev, SWSCI_SBCB_SUPPORTED_CALLBACKS, 0, &tmp) == 0) {
+	if (swsci(dev_priv, SWSCI_SBCB_SUPPORTED_CALLBACKS, 0, &tmp) == 0) {
 		/* make the bits match the sub-function codes */
 		u32 low = tmp & 0x7ff;
 		u32 high = tmp & ~0xfff; /* bit 11 is reserved */
@@ -918,10 +952,10 @@ static const struct dmi_system_id intel_no_opregion_vbt[] = {
 	{ }
 };
 
-int intel_opregion_setup(struct drm_device *dev)
+int intel_opregion_setup(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_opregion *opregion = &dev_priv->opregion;
+	struct pci_dev *pdev = dev_priv->drm.pdev;
 	u32 asls, mboxes;
 	char buf[sizeof(OPREGION_SIGNATURE)];
 	int err = 0;
@@ -933,7 +967,7 @@ int intel_opregion_setup(struct drm_device *dev)
 	BUILD_BUG_ON(sizeof(struct opregion_asle) != 0x100);
 	BUILD_BUG_ON(sizeof(struct opregion_asle_ext) != 0x400);
 
-	pci_read_config_dword(dev->pdev, ASLS, &asls);
+	pci_read_config_dword(pdev, ASLS, &asls);
 	DRM_DEBUG_DRIVER("graphic opregion physical addr: 0x%x\n", asls);
 	if (asls == 0) {
 		DRM_DEBUG_DRIVER("ACPI OpRegion not supported!\n");
@@ -965,7 +999,7 @@ int intel_opregion_setup(struct drm_device *dev)
 	if (mboxes & MBOX_SWSCI) {
 		DRM_DEBUG_DRIVER("SWSCI supported\n");
 		opregion->swsci = base + OPREGION_SWSCI_OFFSET;
-		swsci_setup(dev);
+		swsci_setup(dev_priv);
 	}
 
 	if (mboxes & MBOX_ASLE) {
@@ -1014,12 +1048,12 @@ err_out:
 }
 
 int
-intel_opregion_get_panel_type(struct drm_device *dev)
+intel_opregion_get_panel_type(struct drm_i915_private *dev_priv)
 {
 	u32 panel_details;
 	int ret;
 
-	ret = swsci(dev, SWSCI_GBDA_PANEL_DETAILS, 0x0, &panel_details);
+	ret = swsci(dev_priv, SWSCI_GBDA_PANEL_DETAILS, 0x0, &panel_details);
 	if (ret) {
 		DRM_DEBUG_KMS("Failed to get panel details from OpRegion (%d)\n",
 			      ret);
@@ -1044,7 +1078,7 @@ intel_opregion_get_panel_type(struct drm_device *dev)
 	 * vswing instead. Low vswing results in some display flickers, so
 	 * let's simply ignore the OpRegion panel type on SKL for now.
 	 */
-	if (IS_SKYLAKE(dev)) {
+	if (IS_SKYLAKE(dev_priv)) {
 		DRM_DEBUG_KMS("Ignoring OpRegion panel type (%d)\n", ret - 1);
 		return -ENODEV;
 	}
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index bd38e49f7334..3212d8806b5a 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -168,7 +168,7 @@ struct overlay_registers {
 };
 
 struct intel_overlay {
-	struct drm_device *dev;
+	struct drm_i915_private *i915;
 	struct intel_crtc *crtc;
 	struct drm_i915_gem_object *vid_bo;
 	struct drm_i915_gem_object *old_vid_bo;
@@ -190,15 +190,15 @@ struct intel_overlay {
 static struct overlay_registers __iomem *
 intel_overlay_map_regs(struct intel_overlay *overlay)
 {
-	struct drm_i915_private *dev_priv = to_i915(overlay->dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct drm_i915_private *dev_priv = overlay->i915;
 	struct overlay_registers __iomem *regs;
 
-	if (OVERLAY_NEEDS_PHYSICAL(overlay->dev))
+	if (OVERLAY_NEEDS_PHYSICAL(dev_priv))
 		regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_handle->vaddr;
 	else
-		regs = io_mapping_map_wc(ggtt->mappable,
-					 i915_gem_obj_ggtt_offset(overlay->reg_bo));
+		regs = io_mapping_map_wc(dev_priv->ggtt.mappable,
+					 overlay->flip_addr,
+					 PAGE_SIZE);
 
 	return regs;
 }
@@ -206,7 +206,7 @@ intel_overlay_map_regs(struct intel_overlay *overlay)
 static void intel_overlay_unmap_regs(struct intel_overlay *overlay,
 				     struct overlay_registers __iomem *regs)
 {
-	if (!OVERLAY_NEEDS_PHYSICAL(overlay->dev))
+	if (!OVERLAY_NEEDS_PHYSICAL(overlay->i915))
 		io_mapping_unmap(regs);
 }
 
@@ -232,14 +232,13 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
 /* overlay needs to be disable in OCMD reg */
 static int intel_overlay_on(struct intel_overlay *overlay)
 {
-	struct drm_device *dev = overlay->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = overlay->i915;
 	struct intel_engine_cs *engine = &dev_priv->engine[RCS];
 	struct drm_i915_gem_request *req;
 	int ret;
 
 	WARN_ON(overlay->active);
-	WARN_ON(IS_I830(dev) && !(dev_priv->quirks & QUIRK_PIPEA_FORCE));
+	WARN_ON(IS_I830(dev_priv) && !(dev_priv->quirks & QUIRK_PIPEA_FORCE));
 
 	req = i915_gem_request_alloc(engine, NULL);
 	if (IS_ERR(req))
@@ -266,8 +265,7 @@ static int intel_overlay_on(struct intel_overlay *overlay)
 static int intel_overlay_continue(struct intel_overlay *overlay,
 				  bool load_polyphase_filter)
 {
-	struct drm_device *dev = overlay->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = overlay->i915;
 	struct intel_engine_cs *engine = &dev_priv->engine[RCS];
 	struct drm_i915_gem_request *req;
 	u32 flip_addr = overlay->flip_addr;
@@ -335,8 +333,7 @@ static void intel_overlay_off_tail(struct intel_overlay *overlay)
 /* overlay needs to be disabled in OCMD reg */
 static int intel_overlay_off(struct intel_overlay *overlay)
 {
-	struct drm_device *dev = overlay->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = overlay->i915;
 	struct intel_engine_cs *engine = &dev_priv->engine[RCS];
 	struct drm_i915_gem_request *req;
 	u32 flip_addr = overlay->flip_addr;
@@ -365,7 +362,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
 	intel_ring_emit(engine, flip_addr);
 	intel_ring_emit(engine, MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
 	/* turn overlay off */
-	if (IS_I830(dev)) {
+	if (IS_I830(dev_priv)) {
 		/* Workaround: Don't disable the overlay fully, since otherwise
 		 * it dies on the next OVERLAY_ON cmd. */
 		intel_ring_emit(engine, MI_NOOP);
@@ -408,12 +405,11 @@ static int intel_overlay_recover_from_interrupt(struct intel_overlay *overlay)
  */
 static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
 {
-	struct drm_device *dev = overlay->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = overlay->i915;
 	struct intel_engine_cs *engine = &dev_priv->engine[RCS];
 	int ret;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
 	/* Only wait if there is actually an old frame to release to
 	 * guarantee forward progress.
@@ -537,10 +533,10 @@ static int uv_vsubsampling(u32 format)
 	}
 }
 
-static u32 calc_swidthsw(struct drm_device *dev, u32 offset, u32 width)
+static u32 calc_swidthsw(struct drm_i915_private *dev_priv, u32 offset, u32 width)
 {
 	u32 mask, shift, ret;
-	if (IS_GEN2(dev)) {
+	if (IS_GEN2(dev_priv)) {
 		mask = 0x1f;
 		shift = 5;
 	} else {
@@ -548,7 +544,7 @@ static u32 calc_swidthsw(struct drm_device *dev, u32 offset, u32 width)
 		shift = 6;
 	}
 	ret = ((offset + width + mask) >> shift) - (offset >> shift);
-	if (!IS_GEN2(dev))
+	if (!IS_GEN2(dev_priv))
 		ret <<= 1;
 	ret -= 1;
 	return ret << 2;
@@ -741,12 +737,12 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	int ret, tmp_width;
 	struct overlay_registers __iomem *regs;
 	bool scale_changed = false;
-	struct drm_device *dev = overlay->dev;
+	struct drm_i915_private *dev_priv = overlay->i915;
 	u32 swidth, swidthsw, sheight, ostride;
 	enum pipe pipe = overlay->crtc->pipe;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+	WARN_ON(!drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex));
 
 	ret = intel_overlay_release_old_vid(overlay);
 	if (ret != 0)
@@ -769,7 +765,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 			goto out_unpin;
 		}
 		oconfig = OCONF_CC_OUT_8BIT;
-		if (IS_GEN4(overlay->dev))
+		if (IS_GEN4(dev_priv))
 			oconfig |= OCONF_CSC_MODE_BT709;
 		oconfig |= pipe == 0 ?
 			OCONF_PIPE_A : OCONF_PIPE_B;
@@ -796,7 +792,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 		tmp_width = params->src_w;
 
 	swidth = params->src_w;
-	swidthsw = calc_swidthsw(overlay->dev, params->offset_Y, tmp_width);
+	swidthsw = calc_swidthsw(dev_priv, params->offset_Y, tmp_width);
 	sheight = params->src_h;
 	iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_Y, &regs->OBUF_0Y);
 	ostride = params->stride_Y;
@@ -806,9 +802,9 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 		int uv_vscale = uv_vsubsampling(params->format);
 		u32 tmp_U, tmp_V;
 		swidth |= (params->src_w/uv_hscale) << 16;
-		tmp_U = calc_swidthsw(overlay->dev, params->offset_U,
+		tmp_U = calc_swidthsw(dev_priv, params->offset_U,
 				      params->src_w/uv_hscale);
-		tmp_V = calc_swidthsw(overlay->dev, params->offset_V,
+		tmp_V = calc_swidthsw(dev_priv, params->offset_V,
 				      params->src_w/uv_hscale);
 		swidthsw |= max_t(u32, tmp_U, tmp_V) << 16;
 		sheight |= (params->src_h/uv_vscale) << 16;
@@ -840,7 +836,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	overlay->old_vid_bo = overlay->vid_bo;
 	overlay->vid_bo = new_bo;
 
-	intel_frontbuffer_flip(dev,
+	intel_frontbuffer_flip(&dev_priv->drm,
 			       INTEL_FRONTBUFFER_OVERLAY(pipe));
 
 	return 0;
@@ -852,12 +848,12 @@ out_unpin:
 
 int intel_overlay_switch_off(struct intel_overlay *overlay)
 {
+	struct drm_i915_private *dev_priv = overlay->i915;
 	struct overlay_registers __iomem *regs;
-	struct drm_device *dev = overlay->dev;
 	int ret;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+	WARN_ON(!drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex));
 
 	ret = intel_overlay_recover_from_interrupt(overlay);
 	if (ret != 0)
@@ -897,15 +893,14 @@ static int check_overlay_possible_on_crtc(struct intel_overlay *overlay,
 
 static void update_pfit_vscale_ratio(struct intel_overlay *overlay)
 {
-	struct drm_device *dev = overlay->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = overlay->i915;
 	u32 pfit_control = I915_READ(PFIT_CONTROL);
 	u32 ratio;
 
 	/* XXX: This is not the same logic as in the xorg driver, but more in
 	 * line with the intel documentation for the i965
 	 */
-	if (INTEL_INFO(dev)->gen >= 4) {
+	if (INTEL_GEN(dev_priv) >= 4) {
 		/* on i965 use the PGM reg to read out the autoscaler values */
 		ratio = I915_READ(PFIT_PGM_RATIOS) >> PFIT_VERT_SCALE_SHIFT_965;
 	} else {
@@ -948,7 +943,7 @@ static int check_overlay_scaling(struct put_image_params *rec)
 	return 0;
 }
 
-static int check_overlay_src(struct drm_device *dev,
+static int check_overlay_src(struct drm_i915_private *dev_priv,
 			     struct drm_intel_overlay_put_image *rec,
 			     struct drm_i915_gem_object *new_bo)
 {
@@ -959,7 +954,7 @@ static int check_overlay_src(struct drm_device *dev,
 	u32 tmp;
 
 	/* check src dimensions */
-	if (IS_845G(dev) || IS_I830(dev)) {
+	if (IS_845G(dev_priv) || IS_I830(dev_priv)) {
 		if (rec->src_height > IMAGE_MAX_HEIGHT_LEGACY ||
 		    rec->src_width  > IMAGE_MAX_WIDTH_LEGACY)
 			return -EINVAL;
@@ -1011,14 +1006,14 @@ static int check_overlay_src(struct drm_device *dev,
 		return -EINVAL;
 
 	/* stride checking */
-	if (IS_I830(dev) || IS_845G(dev))
+	if (IS_I830(dev_priv) || IS_845G(dev_priv))
 		stride_mask = 255;
 	else
 		stride_mask = 63;
 
 	if (rec->stride_Y & stride_mask || rec->stride_UV & stride_mask)
 		return -EINVAL;
-	if (IS_GEN4(dev) && rec->stride_Y < 512)
+	if (IS_GEN4(dev_priv) && rec->stride_Y < 512)
 		return -EINVAL;
 
 	tmp = (rec->flags & I915_OVERLAY_TYPE_MASK) == I915_OVERLAY_YUV_PLANAR ?
@@ -1063,13 +1058,13 @@ static int check_overlay_src(struct drm_device *dev,
  * Return the pipe currently connected to the panel fitter,
  * or -1 if the panel fitter is not present or not in use
  */
-static int intel_panel_fitter_pipe(struct drm_device *dev)
+static int intel_panel_fitter_pipe(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32  pfit_control;
 
 	/* i830 doesn't have a panel fitter */
-	if (INTEL_INFO(dev)->gen <= 3 && (IS_I830(dev) || !IS_MOBILE(dev)))
+	if (INTEL_GEN(dev_priv) <= 3 &&
+	    (IS_I830(dev_priv) || !IS_MOBILE(dev_priv)))
 		return -1;
 
 	pfit_control = I915_READ(PFIT_CONTROL);
@@ -1079,18 +1074,18 @@ static int intel_panel_fitter_pipe(struct drm_device *dev)
 		return -1;
 
 	/* 965 can place panel fitter on either pipe */
-	if (IS_GEN4(dev))
+	if (IS_GEN4(dev_priv))
 		return (pfit_control >> 29) & 0x3;
 
 	/* older chips can only use pipe 1 */
 	return 1;
 }
 
-int intel_overlay_put_image(struct drm_device *dev, void *data,
-			    struct drm_file *file_priv)
+int intel_overlay_put_image_ioctl(struct drm_device *dev, void *data,
+				  struct drm_file *file_priv)
 {
 	struct drm_intel_overlay_put_image *put_image_rec = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_overlay *overlay;
 	struct drm_crtc *drmmode_crtc;
 	struct intel_crtc *crtc;
@@ -1162,7 +1157,7 @@ int intel_overlay_put_image(struct drm_device *dev, void *data,
 
 		/* line too wide, i.e. one-line-mode */
 		if (mode->hdisplay > 1024 &&
-		    intel_panel_fitter_pipe(dev) == crtc->pipe) {
+		    intel_panel_fitter_pipe(dev_priv) == crtc->pipe) {
 			overlay->pfit_active = true;
 			update_pfit_vscale_ratio(overlay);
 		} else
@@ -1196,7 +1191,7 @@ int intel_overlay_put_image(struct drm_device *dev, void *data,
 		goto out_unlock;
 	}
 
-	ret = check_overlay_src(dev, put_image_rec, new_bo);
+	ret = check_overlay_src(dev_priv, put_image_rec, new_bo);
 	if (ret != 0)
 		goto out_unlock;
 	params->format = put_image_rec->flags & ~I915_OVERLAY_FLAGS_MASK;
@@ -1284,11 +1279,11 @@ static int check_gamma(struct drm_intel_overlay_attrs *attrs)
 	return 0;
 }
 
-int intel_overlay_attrs(struct drm_device *dev, void *data,
-			struct drm_file *file_priv)
+int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv)
 {
 	struct drm_intel_overlay_attrs *attrs = data;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_overlay *overlay;
 	struct overlay_registers __iomem *regs;
 	int ret;
@@ -1309,7 +1304,7 @@ int intel_overlay_attrs(struct drm_device *dev, void *data,
 		attrs->contrast   = overlay->contrast;
 		attrs->saturation = overlay->saturation;
 
-		if (!IS_GEN2(dev)) {
+		if (!IS_GEN2(dev_priv)) {
 			attrs->gamma0 = I915_READ(OGAMC0);
 			attrs->gamma1 = I915_READ(OGAMC1);
 			attrs->gamma2 = I915_READ(OGAMC2);
@@ -1341,7 +1336,7 @@ int intel_overlay_attrs(struct drm_device *dev, void *data,
 		intel_overlay_unmap_regs(overlay, regs);
 
 		if (attrs->flags & I915_OVERLAY_UPDATE_GAMMA) {
-			if (IS_GEN2(dev))
+			if (IS_GEN2(dev_priv))
 				goto out_unlock;
 
 			if (overlay->active) {
@@ -1371,37 +1366,37 @@ out_unlock:
 	return ret;
 }
 
-void intel_setup_overlay(struct drm_device *dev)
+void intel_setup_overlay(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_overlay *overlay;
 	struct drm_i915_gem_object *reg_bo;
 	struct overlay_registers __iomem *regs;
 	int ret;
 
-	if (!HAS_OVERLAY(dev))
+	if (!HAS_OVERLAY(dev_priv))
 		return;
 
 	overlay = kzalloc(sizeof(*overlay), GFP_KERNEL);
 	if (!overlay)
 		return;
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&dev_priv->drm.struct_mutex);
 	if (WARN_ON(dev_priv->overlay))
 		goto out_free;
 
-	overlay->dev = dev;
+	overlay->i915 = dev_priv;
 
 	reg_bo = NULL;
-	if (!OVERLAY_NEEDS_PHYSICAL(dev))
-		reg_bo = i915_gem_object_create_stolen(dev, PAGE_SIZE);
-	if (reg_bo == NULL)
-		reg_bo = i915_gem_alloc_object(dev, PAGE_SIZE);
+	if (!OVERLAY_NEEDS_PHYSICAL(dev_priv))
+		reg_bo = i915_gem_object_create_stolen(&dev_priv->drm,
+						       PAGE_SIZE);
 	if (reg_bo == NULL)
+		reg_bo = i915_gem_object_create(&dev_priv->drm, PAGE_SIZE);
+	if (IS_ERR(reg_bo))
 		goto out_free;
 	overlay->reg_bo = reg_bo;
 
-	if (OVERLAY_NEEDS_PHYSICAL(dev)) {
+	if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) {
 		ret = i915_gem_object_attach_phys(reg_bo, PAGE_SIZE);
 		if (ret) {
 			DRM_ERROR("failed to attach phys overlay regs\n");
@@ -1441,25 +1436,23 @@ void intel_setup_overlay(struct drm_device *dev)
 	intel_overlay_unmap_regs(overlay, regs);
 
 	dev_priv->overlay = overlay;
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
 	DRM_INFO("initialized overlay support\n");
 	return;
 
 out_unpin_bo:
-	if (!OVERLAY_NEEDS_PHYSICAL(dev))
+	if (!OVERLAY_NEEDS_PHYSICAL(dev_priv))
 		i915_gem_object_ggtt_unpin(reg_bo);
 out_free_bo:
 	drm_gem_object_unreference(&reg_bo->base);
 out_free:
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
 	kfree(overlay);
 	return;
 }
 
-void intel_cleanup_overlay(struct drm_device *dev)
+void intel_cleanup_overlay(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	if (!dev_priv->overlay)
 		return;
 
@@ -1482,18 +1475,17 @@ struct intel_overlay_error_state {
 static struct overlay_registers __iomem *
 intel_overlay_map_regs_atomic(struct intel_overlay *overlay)
 {
-	struct drm_i915_private *dev_priv = to_i915(overlay->dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct drm_i915_private *dev_priv = overlay->i915;
 	struct overlay_registers __iomem *regs;
 
-	if (OVERLAY_NEEDS_PHYSICAL(overlay->dev))
+	if (OVERLAY_NEEDS_PHYSICAL(dev_priv))
 		/* Cast to make sparse happy, but it's wc memory anyway, so
 		 * equivalent to the wc io mapping on X86. */
 		regs = (struct overlay_registers __iomem *)
 			overlay->reg_bo->phys_handle->vaddr;
 	else
-		regs = io_mapping_map_atomic_wc(ggtt->mappable,
-						i915_gem_obj_ggtt_offset(overlay->reg_bo));
+		regs = io_mapping_map_atomic_wc(dev_priv->ggtt.mappable,
+						overlay->flip_addr);
 
 	return regs;
 }
@@ -1501,15 +1493,13 @@ intel_overlay_map_regs_atomic(struct intel_overlay *overlay)
 static void intel_overlay_unmap_regs_atomic(struct intel_overlay *overlay,
 					struct overlay_registers __iomem *regs)
 {
-	if (!OVERLAY_NEEDS_PHYSICAL(overlay->dev))
+	if (!OVERLAY_NEEDS_PHYSICAL(overlay->i915))
 		io_mapping_unmap_atomic(regs);
 }
 
-
 struct intel_overlay_error_state *
-intel_overlay_capture_error_state(struct drm_device *dev)
+intel_overlay_capture_error_state(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_overlay *overlay = dev_priv->overlay;
 	struct intel_overlay_error_state *error;
 	struct overlay_registers __iomem *regs;
@@ -1523,10 +1513,7 @@ intel_overlay_capture_error_state(struct drm_device *dev)
 
 	error->dovsta = I915_READ(DOVSTA);
 	error->isr = I915_READ(ISR);
-	if (OVERLAY_NEEDS_PHYSICAL(overlay->dev))
-		error->base = (__force long)overlay->reg_bo->phys_handle->vaddr;
-	else
-		error->base = i915_gem_obj_ggtt_offset(overlay->reg_bo);
+	error->base = overlay->flip_addr;
 
 	regs = intel_overlay_map_regs_atomic(overlay);
 	if (!regs)
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index aba94099886b..96c65d77e886 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -377,7 +377,7 @@ out:
 enum drm_connector_status
 intel_panel_detect(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* Assume that the BIOS does not lie through the OpRegion... */
 	if (!i915.panel_ignore_lid && dev_priv->opregion.lid_state) {
@@ -504,7 +504,7 @@ static u32 i9xx_get_backlight(struct intel_connector *connector)
 	if (panel->backlight.combination_mode) {
 		u8 lbpc;
 
-		pci_read_config_byte(dev_priv->dev->pdev, LBPC, &lbpc);
+		pci_read_config_byte(dev_priv->drm.pdev, LBPC, &lbpc);
 		val *= lbpc;
 	}
 
@@ -592,7 +592,7 @@ static void i9xx_set_backlight(struct intel_connector *connector, u32 level)
 
 		lbpc = level * 0xfe / panel->backlight.max + 1;
 		level /= lbpc;
-		pci_write_config_byte(dev_priv->dev->pdev, LBPC, lbpc);
+		pci_write_config_byte(dev_priv->drm.pdev, LBPC, lbpc);
 	}
 
 	if (IS_GEN4(dev_priv)) {
@@ -822,7 +822,7 @@ void intel_panel_disable_backlight(struct intel_connector *connector)
 	 * backlight. This will leave the backlight on unnecessarily when
 	 * another client is not activated.
 	 */
-	if (dev_priv->dev->switch_power_state == DRM_SWITCH_POWER_CHANGING) {
+	if (dev_priv->drm.switch_power_state == DRM_SWITCH_POWER_CHANGING) {
 		DRM_DEBUG_DRIVER("Skipping backlight disable on vga switch\n");
 		return;
 	}
@@ -1142,7 +1142,7 @@ static int intel_backlight_device_get_brightness(struct backlight_device *bd)
 {
 	struct intel_connector *connector = bl_get_data(bd);
 	struct drm_device *dev = connector->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 hw_level;
 	int ret;
 
@@ -1163,7 +1163,7 @@ static const struct backlight_ops intel_backlight_device_ops = {
 	.get_brightness = intel_backlight_device_get_brightness,
 };
 
-static int intel_backlight_device_register(struct intel_connector *connector)
+int intel_backlight_device_register(struct intel_connector *connector)
 {
 	struct intel_panel *panel = &connector->panel;
 	struct backlight_properties props;
@@ -1216,7 +1216,7 @@ static int intel_backlight_device_register(struct intel_connector *connector)
 	return 0;
 }
 
-static void intel_backlight_device_unregister(struct intel_connector *connector)
+void intel_backlight_device_unregister(struct intel_connector *connector)
 {
 	struct intel_panel *panel = &connector->panel;
 
@@ -1225,14 +1225,6 @@ static void intel_backlight_device_unregister(struct intel_connector *connector)
 		panel->backlight.device = NULL;
 	}
 }
-#else /* CONFIG_BACKLIGHT_CLASS_DEVICE */
-static int intel_backlight_device_register(struct intel_connector *connector)
-{
-	return 0;
-}
-static void intel_backlight_device_unregister(struct intel_connector *connector)
-{
-}
 #endif /* CONFIG_BACKLIGHT_CLASS_DEVICE */
 
 /*
@@ -1324,7 +1316,7 @@ static u32 i9xx_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
 static u32 i965_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz)
 {
 	struct drm_device *dev = connector->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int clock;
 
 	if (IS_G4X(dev_priv))
@@ -1724,6 +1716,14 @@ intel_panel_init_backlight_funcs(struct intel_panel *panel)
 		container_of(panel, struct intel_connector, panel);
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 
+	if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP &&
+	    intel_dp_aux_init_backlight_funcs(connector) == 0)
+		return;
+
+	if (connector->base.connector_type == DRM_MODE_CONNECTOR_DSI &&
+	    intel_dsi_dcs_init_backlight_funcs(connector) == 0)
+		return;
+
 	if (IS_BROXTON(dev_priv)) {
 		panel->backlight.setup = bxt_setup_backlight;
 		panel->backlight.enable = bxt_enable_backlight;
@@ -1805,19 +1805,3 @@ void intel_panel_fini(struct intel_panel *panel)
 		drm_mode_destroy(intel_connector->base.dev,
 				panel->downclock_mode);
 }
-
-void intel_backlight_register(struct drm_device *dev)
-{
-	struct intel_connector *connector;
-
-	for_each_intel_connector(dev, connector)
-		intel_backlight_device_register(connector);
-}
-
-void intel_backlight_unregister(struct drm_device *dev)
-{
-	struct intel_connector *connector;
-
-	for_each_intel_connector(dev, connector)
-		intel_backlight_device_unregister(connector);
-}
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 2863b92c9da6..f4f3fcc8b3be 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -26,6 +26,7 @@
  */
 
 #include <linux/cpufreq.h>
+#include <drm/drm_plane_helper.h>
 #include "i915_drv.h"
 #include "intel_drv.h"
 #include "../../../platform/x86/intel_ips.h"
@@ -82,7 +83,7 @@ static void gen9_init_clock_gating(struct drm_device *dev)
 
 static void bxt_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	gen9_init_clock_gating(dev);
 
@@ -108,7 +109,7 @@ static void bxt_init_clock_gating(struct drm_device *dev)
 
 static void i915_pineview_get_mem_freq(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 tmp;
 
 	tmp = I915_READ(CLKCFG);
@@ -147,7 +148,7 @@ static void i915_pineview_get_mem_freq(struct drm_device *dev)
 
 static void i915_ironlake_get_mem_freq(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u16 ddrpll, csipll;
 
 	ddrpll = I915_READ16(DDRMPLL1);
@@ -318,7 +319,7 @@ static void chv_set_memory_pm5(struct drm_i915_private *dev_priv, bool enable)
 
 void intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	u32 val;
 
 	if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
@@ -374,7 +375,7 @@ static const int pessimal_latency_ns = 5000;
 static int vlv_get_fifo_size(struct drm_device *dev,
 			      enum pipe pipe, int plane)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int sprite0_start, sprite1_start, size;
 
 	switch (pipe) {
@@ -425,7 +426,7 @@ static int vlv_get_fifo_size(struct drm_device *dev,
 
 static int i9xx_get_fifo_size(struct drm_device *dev, int plane)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t dsparb = I915_READ(DSPARB);
 	int size;
 
@@ -441,7 +442,7 @@ static int i9xx_get_fifo_size(struct drm_device *dev, int plane)
 
 static int i830_get_fifo_size(struct drm_device *dev, int plane)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t dsparb = I915_READ(DSPARB);
 	int size;
 
@@ -458,7 +459,7 @@ static int i830_get_fifo_size(struct drm_device *dev, int plane)
 
 static int i845_get_fifo_size(struct drm_device *dev, int plane)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t dsparb = I915_READ(DSPARB);
 	int size;
 
@@ -636,7 +637,7 @@ static struct drm_crtc *single_enabled_crtc(struct drm_device *dev)
 static void pineview_update_wm(struct drm_crtc *unused_crtc)
 {
 	struct drm_device *dev = unused_crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc;
 	const struct cxsr_latency *latency;
 	u32 reg;
@@ -933,7 +934,7 @@ static unsigned int vlv_wm_method2(unsigned int pixel_rate,
 
 static void vlv_setup_wm_latency(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* all latencies in usec */
 	dev_priv->wm.pri_latency[VLV_WM_LEVEL_PM2] = 3;
@@ -1324,7 +1325,7 @@ static void vlv_merge_wm(struct drm_device *dev,
 static void vlv_update_wm(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum pipe pipe = intel_crtc->pipe;
 	struct vlv_wm_values wm = {};
@@ -1380,7 +1381,7 @@ static void g4x_update_wm(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	static const int sr_latency_ns = 12000;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int planea_wm, planeb_wm, cursora_wm, cursorb_wm;
 	int plane_sr, cursor_sr;
 	unsigned int enabled = 0;
@@ -1437,7 +1438,7 @@ static void g4x_update_wm(struct drm_crtc *crtc)
 static void i965_update_wm(struct drm_crtc *unused_crtc)
 {
 	struct drm_device *dev = unused_crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc;
 	int srwm = 1;
 	int cursor_sr = 16;
@@ -1511,7 +1512,7 @@ static void i965_update_wm(struct drm_crtc *unused_crtc)
 static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 {
 	struct drm_device *dev = unused_crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	const struct intel_watermark_params *wm_info;
 	uint32_t fwater_lo;
 	uint32_t fwater_hi;
@@ -1641,7 +1642,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 static void i845_update_wm(struct drm_crtc *unused_crtc)
 {
 	struct drm_device *dev = unused_crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc;
 	const struct drm_display_mode *adjusted_mode;
 	uint32_t fwater_lo;
@@ -2040,10 +2041,10 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv,
 }
 
 static uint32_t
-hsw_compute_linetime_wm(struct drm_device *dev,
-			struct intel_crtc_state *cstate)
+hsw_compute_linetime_wm(const struct intel_crtc_state *cstate)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	const struct intel_atomic_state *intel_state =
+		to_intel_atomic_state(cstate->base.state);
 	const struct drm_display_mode *adjusted_mode =
 		&cstate->base.adjusted_mode;
 	u32 linetime, ips_linetime;
@@ -2052,7 +2053,7 @@ hsw_compute_linetime_wm(struct drm_device *dev,
 		return 0;
 	if (WARN_ON(adjusted_mode->crtc_clock == 0))
 		return 0;
-	if (WARN_ON(dev_priv->cdclk_freq == 0))
+	if (WARN_ON(intel_state->cdclk == 0))
 		return 0;
 
 	/* The WM are computed with base on how long it takes to fill a single
@@ -2061,7 +2062,7 @@ hsw_compute_linetime_wm(struct drm_device *dev,
 	linetime = DIV_ROUND_CLOSEST(adjusted_mode->crtc_htotal * 1000 * 8,
 				     adjusted_mode->crtc_clock);
 	ips_linetime = DIV_ROUND_CLOSEST(adjusted_mode->crtc_htotal * 1000 * 8,
-					 dev_priv->cdclk_freq);
+					 intel_state->cdclk);
 
 	return PIPE_WM_LINETIME_IPS_LINETIME(ips_linetime) |
 	       PIPE_WM_LINETIME_TIME(linetime);
@@ -2069,7 +2070,7 @@ hsw_compute_linetime_wm(struct drm_device *dev,
 
 static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[8])
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (IS_GEN9(dev)) {
 		uint32_t val;
@@ -2174,14 +2175,14 @@ static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[8])
 static void intel_fixup_spr_wm_latency(struct drm_device *dev, uint16_t wm[5])
 {
 	/* ILK sprite LP0 latency is 1300 ns */
-	if (INTEL_INFO(dev)->gen == 5)
+	if (IS_GEN5(dev))
 		wm[0] = 13;
 }
 
 static void intel_fixup_cur_wm_latency(struct drm_device *dev, uint16_t wm[5])
 {
 	/* ILK cursor LP0 latency is 1300 ns */
-	if (INTEL_INFO(dev)->gen == 5)
+	if (IS_GEN5(dev))
 		wm[0] = 13;
 
 	/* WaDoubleCursorLP3Latency:ivb */
@@ -2235,7 +2236,7 @@ static void intel_print_wm_latency(struct drm_device *dev,
 static bool ilk_increase_wm_latency(struct drm_i915_private *dev_priv,
 				    uint16_t wm[5], uint16_t min)
 {
-	int level, max_level = ilk_wm_max_level(dev_priv->dev);
+	int level, max_level = ilk_wm_max_level(&dev_priv->drm);
 
 	if (wm[0] >= min)
 		return false;
@@ -2249,7 +2250,7 @@ static bool ilk_increase_wm_latency(struct drm_i915_private *dev_priv,
 
 static void snb_wm_latency_quirk(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	bool changed;
 
 	/*
@@ -2271,7 +2272,7 @@ static void snb_wm_latency_quirk(struct drm_device *dev)
 
 static void ilk_setup_wm_latency(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	intel_read_wm_latency(dev, dev_priv->wm.pri_latency);
 
@@ -2293,7 +2294,7 @@ static void ilk_setup_wm_latency(struct drm_device *dev)
 
 static void skl_setup_wm_latency(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	intel_read_wm_latency(dev, dev_priv->wm.skl_latency);
 	intel_print_wm_latency(dev, "Gen9 Plane", dev_priv->wm.skl_latency);
@@ -2329,7 +2330,7 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
 	struct intel_pipe_wm *pipe_wm;
 	struct drm_device *dev = state->dev;
-	const struct drm_i915_private *dev_priv = dev->dev_private;
+	const struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *intel_plane;
 	struct intel_plane_state *pristate = NULL;
 	struct intel_plane_state *sprstate = NULL;
@@ -2337,7 +2338,7 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 	int level, max_level = ilk_wm_max_level(dev), usable_level;
 	struct ilk_wm_maximums max;
 
-	pipe_wm = &cstate->wm.optimal.ilk;
+	pipe_wm = &cstate->wm.ilk.optimal;
 
 	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
 		struct intel_plane_state *ps;
@@ -2380,7 +2381,7 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
 	pipe_wm->wm[0] = pipe_wm->raw_wm[0];
 
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
-		pipe_wm->linetime = hsw_compute_linetime_wm(dev, cstate);
+		pipe_wm->linetime = hsw_compute_linetime_wm(cstate);
 
 	if (!ilk_validate_pipe_wm(dev, pipe_wm))
 		return -EINVAL;
@@ -2419,7 +2420,7 @@ static int ilk_compute_intermediate_wm(struct drm_device *dev,
 				       struct intel_crtc *intel_crtc,
 				       struct intel_crtc_state *newstate)
 {
-	struct intel_pipe_wm *a = &newstate->wm.intermediate;
+	struct intel_pipe_wm *a = &newstate->wm.ilk.intermediate;
 	struct intel_pipe_wm *b = &intel_crtc->wm.active.ilk;
 	int level, max_level = ilk_wm_max_level(dev);
 
@@ -2428,7 +2429,7 @@ static int ilk_compute_intermediate_wm(struct drm_device *dev,
 	 * currently active watermarks to get values that are safe both before
 	 * and after the vblank.
 	 */
-	*a = newstate->wm.optimal.ilk;
+	*a = newstate->wm.ilk.optimal;
 	a->pipe_enabled |= b->pipe_enabled;
 	a->sprites_enabled |= b->sprites_enabled;
 	a->sprites_scaled |= b->sprites_scaled;
@@ -2457,7 +2458,7 @@ static int ilk_compute_intermediate_wm(struct drm_device *dev,
 	 * If our intermediate WM are identical to the final WM, then we can
 	 * omit the post-vblank programming; only update if it's different.
 	 */
-	if (memcmp(a, &newstate->wm.optimal.ilk, sizeof(*a)) == 0)
+	if (memcmp(a, &newstate->wm.ilk.optimal, sizeof(*a)) == 0)
 		newstate->wm.need_postvbl_update = false;
 
 	return 0;
@@ -2504,7 +2505,7 @@ static void ilk_wm_merge(struct drm_device *dev,
 			 const struct ilk_wm_maximums *max,
 			 struct intel_pipe_wm *merged)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int level, max_level = ilk_wm_max_level(dev);
 	int last_enabled_level = max_level;
 
@@ -2564,7 +2565,7 @@ static int ilk_wm_lp_to_level(int wm_lp, const struct intel_pipe_wm *pipe_wm)
 /* The value we need to program into the WM_LPx latency field */
 static unsigned int ilk_wm_lp_latency(struct drm_device *dev, int level)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		return 2 * level;
@@ -2764,7 +2765,7 @@ static bool _ilk_disable_lp_wm(struct drm_i915_private *dev_priv,
 static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
 				struct ilk_wm_values *results)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct ilk_wm_values *previous = &dev_priv->wm.hw;
 	unsigned int dirty;
 	uint32_t val;
@@ -2839,7 +2840,7 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
 
 bool ilk_disable_lp_wm(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	return _ilk_disable_lp_wm(dev_priv, WM_DIRTY_LP_ALL);
 }
@@ -2877,20 +2878,29 @@ skl_wm_plane_id(const struct intel_plane *plane)
 static void
 skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
 				   const struct intel_crtc_state *cstate,
-				   const struct intel_wm_config *config,
-				   struct skl_ddb_entry *alloc /* out */)
+				   struct skl_ddb_entry *alloc, /* out */
+				   int *num_active /* out */)
 {
+	struct drm_atomic_state *state = cstate->base.state;
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *for_crtc = cstate->base.crtc;
-	struct drm_crtc *crtc;
 	unsigned int pipe_size, ddb_size;
 	int nth_active_pipe;
+	int pipe = to_intel_crtc(for_crtc)->pipe;
 
-	if (!cstate->base.active) {
+	if (WARN_ON(!state) || !cstate->base.active) {
 		alloc->start = 0;
 		alloc->end = 0;
+		*num_active = hweight32(dev_priv->active_crtcs);
 		return;
 	}
 
+	if (intel_state->active_pipe_changes)
+		*num_active = hweight32(intel_state->active_crtcs);
+	else
+		*num_active = hweight32(dev_priv->active_crtcs);
+
 	if (IS_BROXTON(dev))
 		ddb_size = BXT_DDB_SIZE;
 	else
@@ -2898,25 +2908,29 @@ skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
 
 	ddb_size -= 4; /* 4 blocks for bypass path allocation */
 
-	nth_active_pipe = 0;
-	for_each_crtc(dev, crtc) {
-		if (!to_intel_crtc(crtc)->active)
-			continue;
-
-		if (crtc == for_crtc)
-			break;
-
-		nth_active_pipe++;
+	/*
+	 * If the state doesn't change the active CRTC's, then there's
+	 * no need to recalculate; the existing pipe allocation limits
+	 * should remain unchanged.  Note that we're safe from racing
+	 * commits since any racing commit that changes the active CRTC
+	 * list would need to grab _all_ crtc locks, including the one
+	 * we currently hold.
+	 */
+	if (!intel_state->active_pipe_changes) {
+		*alloc = dev_priv->wm.skl_hw.ddb.pipe[pipe];
+		return;
 	}
 
-	pipe_size = ddb_size / config->num_pipes_active;
-	alloc->start = nth_active_pipe * ddb_size / config->num_pipes_active;
+	nth_active_pipe = hweight32(intel_state->active_crtcs &
+				    (drm_crtc_mask(for_crtc) - 1));
+	pipe_size = ddb_size / hweight32(intel_state->active_crtcs);
+	alloc->start = nth_active_pipe * ddb_size / *num_active;
 	alloc->end = alloc->start + pipe_size;
 }
 
-static unsigned int skl_cursor_allocation(const struct intel_wm_config *config)
+static unsigned int skl_cursor_allocation(int num_active)
 {
-	if (config->num_pipes_active == 1)
+	if (num_active == 1)
 		return 32;
 
 	return 8;
@@ -2960,6 +2974,46 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 	}
 }
 
+/*
+ * Determines the downscale amount of a plane for the purposes of watermark calculations.
+ * The bspec defines downscale amount as:
+ *
+ * """
+ * Horizontal down scale amount = maximum[1, Horizontal source size /
+ *                                           Horizontal destination size]
+ * Vertical down scale amount = maximum[1, Vertical source size /
+ *                                         Vertical destination size]
+ * Total down scale amount = Horizontal down scale amount *
+ *                           Vertical down scale amount
+ * """
+ *
+ * Return value is provided in 16.16 fixed point form to retain fractional part.
+ * Caller should take care of dividing & rounding off the value.
+ */
+static uint32_t
+skl_plane_downscale_amount(const struct intel_plane_state *pstate)
+{
+	uint32_t downscale_h, downscale_w;
+	uint32_t src_w, src_h, dst_w, dst_h;
+
+	if (WARN_ON(!pstate->visible))
+		return DRM_PLANE_HELPER_NO_SCALING;
+
+	/* n.b., src is 16.16 fixed point, dst is whole integer */
+	src_w = drm_rect_width(&pstate->src);
+	src_h = drm_rect_height(&pstate->src);
+	dst_w = drm_rect_width(&pstate->dst);
+	dst_h = drm_rect_height(&pstate->dst);
+	if (intel_rotation_90_or_270(pstate->base.rotation))
+		swap(dst_w, dst_h);
+
+	downscale_h = max(src_h / dst_h, (uint32_t)DRM_PLANE_HELPER_NO_SCALING);
+	downscale_w = max(src_w / dst_w, (uint32_t)DRM_PLANE_HELPER_NO_SCALING);
+
+	/* Provide result in 16.16 fixed point */
+	return (uint64_t)downscale_w * downscale_h >> 16;
+}
+
 static unsigned int
 skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 			     const struct drm_plane_state *pstate,
@@ -2967,7 +3021,16 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 {
 	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
 	struct drm_framebuffer *fb = pstate->fb;
+	uint32_t down_scale_amount, data_rate;
 	uint32_t width = 0, height = 0;
+	unsigned format = fb ? fb->pixel_format : DRM_FORMAT_XRGB8888;
+
+	if (!intel_pstate->visible)
+		return 0;
+	if (pstate->plane->type == DRM_PLANE_TYPE_CURSOR)
+		return 0;
+	if (y && format != DRM_FORMAT_NV12)
+		return 0;
 
 	width = drm_rect_width(&intel_pstate->src) >> 16;
 	height = drm_rect_height(&intel_pstate->src) >> 16;
@@ -2976,17 +3039,21 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 		swap(width, height);
 
 	/* for planar format */
-	if (fb->pixel_format == DRM_FORMAT_NV12) {
+	if (format == DRM_FORMAT_NV12) {
 		if (y)  /* y-plane data rate */
-			return width * height *
-				drm_format_plane_cpp(fb->pixel_format, 0);
+			data_rate = width * height *
+				drm_format_plane_cpp(format, 0);
 		else    /* uv-plane data rate */
-			return (width / 2) * (height / 2) *
-				drm_format_plane_cpp(fb->pixel_format, 1);
+			data_rate = (width / 2) * (height / 2) *
+				drm_format_plane_cpp(format, 1);
+	} else {
+		/* for packed formats */
+		data_rate = width * height * drm_format_plane_cpp(format, 0);
 	}
 
-	/* for packed formats */
-	return width * height * drm_format_plane_cpp(fb->pixel_format, 0);
+	down_scale_amount = skl_plane_downscale_amount(intel_pstate);
+
+	return (uint64_t)data_rate * down_scale_amount >> 16;
 }
 
 /*
@@ -2995,86 +3062,188 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
  *   3 * 4096 * 8192  * 4 < 2^32
  */
 static unsigned int
-skl_get_total_relative_data_rate(const struct intel_crtc_state *cstate)
+skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
-	struct drm_device *dev = intel_crtc->base.dev;
+	struct drm_crtc_state *cstate = &intel_cstate->base;
+	struct drm_atomic_state *state = cstate->state;
+	struct drm_crtc *crtc = cstate->crtc;
+	struct drm_device *dev = crtc->dev;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	const struct drm_plane *plane;
 	const struct intel_plane *intel_plane;
-	unsigned int total_data_rate = 0;
+	struct drm_plane_state *pstate;
+	unsigned int rate, total_data_rate = 0;
+	int id;
+	int i;
 
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		const struct drm_plane_state *pstate = intel_plane->base.state;
+	if (WARN_ON(!state))
+		return 0;
 
-		if (pstate->fb == NULL)
-			continue;
+	/* Calculate and cache data rate for each plane */
+	for_each_plane_in_state(state, plane, pstate, i) {
+		id = skl_wm_plane_id(to_intel_plane(plane));
+		intel_plane = to_intel_plane(plane);
 
-		if (intel_plane->base.type == DRM_PLANE_TYPE_CURSOR)
+		if (intel_plane->pipe != intel_crtc->pipe)
 			continue;
 
 		/* packed/uv */
-		total_data_rate += skl_plane_relative_data_rate(cstate,
-								pstate,
-								0);
+		rate = skl_plane_relative_data_rate(intel_cstate,
+						    pstate, 0);
+		intel_cstate->wm.skl.plane_data_rate[id] = rate;
+
+		/* y-plane */
+		rate = skl_plane_relative_data_rate(intel_cstate,
+						    pstate, 1);
+		intel_cstate->wm.skl.plane_y_data_rate[id] = rate;
+	}
+
+	/* Calculate CRTC's total data rate from cached values */
+	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
+		int id = skl_wm_plane_id(intel_plane);
 
-		if (pstate->fb->pixel_format == DRM_FORMAT_NV12)
-			/* y-plane */
-			total_data_rate += skl_plane_relative_data_rate(cstate,
-									pstate,
-									1);
+		/* packed/uv */
+		total_data_rate += intel_cstate->wm.skl.plane_data_rate[id];
+		total_data_rate += intel_cstate->wm.skl.plane_y_data_rate[id];
 	}
 
+	WARN_ON(cstate->plane_mask && total_data_rate == 0);
+
 	return total_data_rate;
 }
 
-static void
+static uint16_t
+skl_ddb_min_alloc(const struct drm_plane_state *pstate,
+		  const int y)
+{
+	struct drm_framebuffer *fb = pstate->fb;
+	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
+	uint32_t src_w, src_h;
+	uint32_t min_scanlines = 8;
+	uint8_t plane_bpp;
+
+	if (WARN_ON(!fb))
+		return 0;
+
+	/* For packed formats, no y-plane, return 0 */
+	if (y && fb->pixel_format != DRM_FORMAT_NV12)
+		return 0;
+
+	/* For Non Y-tile return 8-blocks */
+	if (fb->modifier[0] != I915_FORMAT_MOD_Y_TILED &&
+	    fb->modifier[0] != I915_FORMAT_MOD_Yf_TILED)
+		return 8;
+
+	src_w = drm_rect_width(&intel_pstate->src) >> 16;
+	src_h = drm_rect_height(&intel_pstate->src) >> 16;
+
+	if (intel_rotation_90_or_270(pstate->rotation))
+		swap(src_w, src_h);
+
+	/* Halve UV plane width and height for NV12 */
+	if (fb->pixel_format == DRM_FORMAT_NV12 && !y) {
+		src_w /= 2;
+		src_h /= 2;
+	}
+
+	if (fb->pixel_format == DRM_FORMAT_NV12 && !y)
+		plane_bpp = drm_format_plane_cpp(fb->pixel_format, 1);
+	else
+		plane_bpp = drm_format_plane_cpp(fb->pixel_format, 0);
+
+	if (intel_rotation_90_or_270(pstate->rotation)) {
+		switch (plane_bpp) {
+		case 1:
+			min_scanlines = 32;
+			break;
+		case 2:
+			min_scanlines = 16;
+			break;
+		case 4:
+			min_scanlines = 8;
+			break;
+		case 8:
+			min_scanlines = 4;
+			break;
+		default:
+			WARN(1, "Unsupported pixel depth %u for rotation",
+			     plane_bpp);
+			min_scanlines = 32;
+		}
+	}
+
+	return DIV_ROUND_UP((4 * src_w * plane_bpp), 512) * min_scanlines/4 + 3;
+}
+
+static int
 skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 		      struct skl_ddb_allocation *ddb /* out */)
 {
+	struct drm_atomic_state *state = cstate->base.state;
 	struct drm_crtc *crtc = cstate->base.crtc;
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_wm_config *config = &dev_priv->wm.config;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_plane *intel_plane;
+	struct drm_plane *plane;
+	struct drm_plane_state *pstate;
 	enum pipe pipe = intel_crtc->pipe;
 	struct skl_ddb_entry *alloc = &ddb->pipe[pipe];
 	uint16_t alloc_size, start, cursor_blocks;
-	uint16_t minimum[I915_MAX_PLANES];
-	uint16_t y_minimum[I915_MAX_PLANES];
+	uint16_t *minimum = cstate->wm.skl.minimum_blocks;
+	uint16_t *y_minimum = cstate->wm.skl.minimum_y_blocks;
 	unsigned int total_data_rate;
+	int num_active;
+	int id, i;
 
-	skl_ddb_get_pipe_allocation_limits(dev, cstate, config, alloc);
+	if (WARN_ON(!state))
+		return 0;
+
+	if (!cstate->base.active) {
+		ddb->pipe[pipe].start = ddb->pipe[pipe].end = 0;
+		memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
+		memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe]));
+		return 0;
+	}
+
+	skl_ddb_get_pipe_allocation_limits(dev, cstate, alloc, &num_active);
 	alloc_size = skl_ddb_entry_size(alloc);
 	if (alloc_size == 0) {
 		memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
-		memset(&ddb->plane[pipe][PLANE_CURSOR], 0,
-		       sizeof(ddb->plane[pipe][PLANE_CURSOR]));
-		return;
+		return 0;
 	}
 
-	cursor_blocks = skl_cursor_allocation(config);
+	cursor_blocks = skl_cursor_allocation(num_active);
 	ddb->plane[pipe][PLANE_CURSOR].start = alloc->end - cursor_blocks;
 	ddb->plane[pipe][PLANE_CURSOR].end = alloc->end;
 
 	alloc_size -= cursor_blocks;
-	alloc->end -= cursor_blocks;
 
 	/* 1. Allocate the mininum required blocks for each active plane */
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		struct drm_plane *plane = &intel_plane->base;
-		struct drm_framebuffer *fb = plane->state->fb;
-		int id = skl_wm_plane_id(intel_plane);
+	for_each_plane_in_state(state, plane, pstate, i) {
+		intel_plane = to_intel_plane(plane);
+		id = skl_wm_plane_id(intel_plane);
 
-		if (!to_intel_plane_state(plane->state)->visible)
+		if (intel_plane->pipe != pipe)
 			continue;
 
-		if (plane->type == DRM_PLANE_TYPE_CURSOR)
+		if (!to_intel_plane_state(pstate)->visible) {
+			minimum[id] = 0;
+			y_minimum[id] = 0;
+			continue;
+		}
+		if (plane->type == DRM_PLANE_TYPE_CURSOR) {
+			minimum[id] = 0;
+			y_minimum[id] = 0;
 			continue;
+		}
+
+		minimum[id] = skl_ddb_min_alloc(pstate, 0);
+		y_minimum[id] = skl_ddb_min_alloc(pstate, 1);
+	}
 
-		minimum[id] = 8;
-		alloc_size -= minimum[id];
-		y_minimum[id] = (fb->pixel_format == DRM_FORMAT_NV12) ? 8 : 0;
-		alloc_size -= y_minimum[id];
+	for (i = 0; i < PLANE_CURSOR; i++) {
+		alloc_size -= minimum[i];
+		alloc_size -= y_minimum[i];
 	}
 
 	/*
@@ -3084,21 +3253,16 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	 * FIXME: we may not allocate every single block here.
 	 */
 	total_data_rate = skl_get_total_relative_data_rate(cstate);
+	if (total_data_rate == 0)
+		return 0;
 
 	start = alloc->start;
 	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		struct drm_plane *plane = &intel_plane->base;
-		struct drm_plane_state *pstate = intel_plane->base.state;
 		unsigned int data_rate, y_data_rate;
 		uint16_t plane_blocks, y_plane_blocks = 0;
 		int id = skl_wm_plane_id(intel_plane);
 
-		if (!to_intel_plane_state(pstate)->visible)
-			continue;
-		if (plane->type == DRM_PLANE_TYPE_CURSOR)
-			continue;
-
-		data_rate = skl_plane_relative_data_rate(cstate, pstate, 0);
+		data_rate = cstate->wm.skl.plane_data_rate[id];
 
 		/*
 		 * allocation for (packed formats) or (uv-plane part of planar format):
@@ -3109,30 +3273,32 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 		plane_blocks += div_u64((uint64_t)alloc_size * data_rate,
 					total_data_rate);
 
-		ddb->plane[pipe][id].start = start;
-		ddb->plane[pipe][id].end = start + plane_blocks;
+		/* Leave disabled planes at (0,0) */
+		if (data_rate) {
+			ddb->plane[pipe][id].start = start;
+			ddb->plane[pipe][id].end = start + plane_blocks;
+		}
 
 		start += plane_blocks;
 
 		/*
 		 * allocation for y_plane part of planar format:
 		 */
-		if (pstate->fb->pixel_format == DRM_FORMAT_NV12) {
-			y_data_rate = skl_plane_relative_data_rate(cstate,
-								   pstate,
-								   1);
-			y_plane_blocks = y_minimum[id];
-			y_plane_blocks += div_u64((uint64_t)alloc_size * y_data_rate,
-						total_data_rate);
+		y_data_rate = cstate->wm.skl.plane_y_data_rate[id];
+
+		y_plane_blocks = y_minimum[id];
+		y_plane_blocks += div_u64((uint64_t)alloc_size * y_data_rate,
+					total_data_rate);
 
+		if (y_data_rate) {
 			ddb->y_plane[pipe][id].start = start;
 			ddb->y_plane[pipe][id].end = start + y_plane_blocks;
-
-			start += y_plane_blocks;
 		}
 
+		start += y_plane_blocks;
 	}
 
+	return 0;
 }
 
 static uint32_t skl_pipe_pixel_rate(const struct intel_crtc_state *config)
@@ -3189,35 +3355,41 @@ static uint32_t skl_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
 	return ret;
 }
 
-static bool skl_ddb_allocation_changed(const struct skl_ddb_allocation *new_ddb,
-				       const struct intel_crtc *intel_crtc)
+static uint32_t skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *cstate,
+					      struct intel_plane_state *pstate)
 {
-	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	const struct skl_ddb_allocation *cur_ddb = &dev_priv->wm.skl_hw.ddb;
+	uint64_t adjusted_pixel_rate;
+	uint64_t downscale_amount;
+	uint64_t pixel_rate;
+
+	/* Shouldn't reach here on disabled planes... */
+	if (WARN_ON(!pstate->visible))
+		return 0;
 
 	/*
-	 * If ddb allocation of pipes changed, it may require recalculation of
-	 * watermarks
+	 * Adjusted plane pixel rate is just the pipe's adjusted pixel rate
+	 * with additional adjustments for plane-specific scaling.
 	 */
-	if (memcmp(new_ddb->pipe, cur_ddb->pipe, sizeof(new_ddb->pipe)))
-		return true;
+	adjusted_pixel_rate = skl_pipe_pixel_rate(cstate);
+	downscale_amount = skl_plane_downscale_amount(pstate);
+
+	pixel_rate = adjusted_pixel_rate * downscale_amount >> 16;
+	WARN_ON(pixel_rate != clamp_t(uint32_t, pixel_rate, 0, ~0));
 
-	return false;
+	return pixel_rate;
 }
 
-static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
-				 struct intel_crtc_state *cstate,
-				 struct intel_plane *intel_plane,
-				 uint16_t ddb_allocation,
-				 int level,
-				 uint16_t *out_blocks, /* out */
-				 uint8_t *out_lines /* out */)
+static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
+				struct intel_crtc_state *cstate,
+				struct intel_plane_state *intel_pstate,
+				uint16_t ddb_allocation,
+				int level,
+				uint16_t *out_blocks, /* out */
+				uint8_t *out_lines, /* out */
+				bool *enabled /* out */)
 {
-	struct drm_plane *plane = &intel_plane->base;
-	struct drm_framebuffer *fb = plane->state->fb;
-	struct intel_plane_state *intel_pstate =
-					to_intel_plane_state(plane->state);
+	struct drm_plane_state *pstate = &intel_pstate->base;
+	struct drm_framebuffer *fb = pstate->fb;
 	uint32_t latency = dev_priv->wm.skl_latency[level];
 	uint32_t method1, method2;
 	uint32_t plane_bytes_per_line, plane_blocks_per_line;
@@ -3225,20 +3397,24 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	uint32_t selected_result;
 	uint8_t cpp;
 	uint32_t width = 0, height = 0;
+	uint32_t plane_pixel_rate;
 
-	if (latency == 0 || !cstate->base.active || !intel_pstate->visible)
-		return false;
+	if (latency == 0 || !cstate->base.active || !intel_pstate->visible) {
+		*enabled = false;
+		return 0;
+	}
 
 	width = drm_rect_width(&intel_pstate->src) >> 16;
 	height = drm_rect_height(&intel_pstate->src) >> 16;
 
-	if (intel_rotation_90_or_270(plane->state->rotation))
+	if (intel_rotation_90_or_270(pstate->rotation))
 		swap(width, height);
 
 	cpp = drm_format_plane_cpp(fb->pixel_format, 0);
-	method1 = skl_wm_method1(skl_pipe_pixel_rate(cstate),
-				 cpp, latency);
-	method2 = skl_wm_method2(skl_pipe_pixel_rate(cstate),
+	plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate, intel_pstate);
+
+	method1 = skl_wm_method1(plane_pixel_rate, cpp, latency);
+	method2 = skl_wm_method2(plane_pixel_rate,
 				 cstate->base.adjusted_mode.crtc_htotal,
 				 width,
 				 cpp,
@@ -3252,7 +3428,7 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 	    fb->modifier[0] == I915_FORMAT_MOD_Yf_TILED) {
 		uint32_t min_scanlines = 4;
 		uint32_t y_tile_minimum;
-		if (intel_rotation_90_or_270(plane->state->rotation)) {
+		if (intel_rotation_90_or_270(pstate->rotation)) {
 			int cpp = (fb->pixel_format == DRM_FORMAT_NV12) ?
 				drm_format_plane_cpp(fb->pixel_format, 1) :
 				drm_format_plane_cpp(fb->pixel_format, 0);
@@ -3288,40 +3464,100 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 			res_blocks++;
 	}
 
-	if (res_blocks >= ddb_allocation || res_lines > 31)
-		return false;
+	if (res_blocks >= ddb_allocation || res_lines > 31) {
+		*enabled = false;
+
+		/*
+		 * If there are no valid level 0 watermarks, then we can't
+		 * support this display configuration.
+		 */
+		if (level) {
+			return 0;
+		} else {
+			DRM_DEBUG_KMS("Requested display configuration exceeds system watermark limitations\n");
+			DRM_DEBUG_KMS("Plane %d.%d: blocks required = %u/%u, lines required = %u/31\n",
+				      to_intel_crtc(cstate->base.crtc)->pipe,
+				      skl_wm_plane_id(to_intel_plane(pstate->plane)),
+				      res_blocks, ddb_allocation, res_lines);
+
+			return -EINVAL;
+		}
+	}
 
 	*out_blocks = res_blocks;
 	*out_lines = res_lines;
+	*enabled = true;
 
-	return true;
+	return 0;
 }
 
-static void skl_compute_wm_level(const struct drm_i915_private *dev_priv,
-				 struct skl_ddb_allocation *ddb,
-				 struct intel_crtc_state *cstate,
-				 int level,
-				 struct skl_wm_level *result)
+static int
+skl_compute_wm_level(const struct drm_i915_private *dev_priv,
+		     struct skl_ddb_allocation *ddb,
+		     struct intel_crtc_state *cstate,
+		     int level,
+		     struct skl_wm_level *result)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_atomic_state *state = cstate->base.state;
 	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
+	struct drm_plane *plane;
 	struct intel_plane *intel_plane;
+	struct intel_plane_state *intel_pstate;
 	uint16_t ddb_blocks;
 	enum pipe pipe = intel_crtc->pipe;
+	int ret;
 
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
+	/*
+	 * We'll only calculate watermarks for planes that are actually
+	 * enabled, so make sure all other planes are set as disabled.
+	 */
+	memset(result, 0, sizeof(*result));
+
+	for_each_intel_plane_mask(&dev_priv->drm,
+				  intel_plane,
+				  cstate->base.plane_mask) {
 		int i = skl_wm_plane_id(intel_plane);
 
+		plane = &intel_plane->base;
+		intel_pstate = NULL;
+		if (state)
+			intel_pstate =
+				intel_atomic_get_existing_plane_state(state,
+								      intel_plane);
+
+		/*
+		 * Note: If we start supporting multiple pending atomic commits
+		 * against the same planes/CRTC's in the future, plane->state
+		 * will no longer be the correct pre-state to use for the
+		 * calculations here and we'll need to change where we get the
+		 * 'unchanged' plane data from.
+		 *
+		 * For now this is fine because we only allow one queued commit
+		 * against a CRTC.  Even if the plane isn't modified by this
+		 * transaction and we don't have a plane lock, we still have
+		 * the CRTC's lock, so we know that no other transactions are
+		 * racing with us to update it.
+		 */
+		if (!intel_pstate)
+			intel_pstate = to_intel_plane_state(plane->state);
+
+		WARN_ON(!intel_pstate->base.fb);
+
 		ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][i]);
 
-		result->plane_en[i] = skl_compute_plane_wm(dev_priv,
-						cstate,
-						intel_plane,
-						ddb_blocks,
-						level,
-						&result->plane_res_b[i],
-						&result->plane_res_l[i]);
+		ret = skl_compute_plane_wm(dev_priv,
+					   cstate,
+					   intel_pstate,
+					   ddb_blocks,
+					   level,
+					   &result->plane_res_b[i],
+					   &result->plane_res_l[i],
+					   &result->plane_en[i]);
+		if (ret)
+			return ret;
 	}
+
+	return 0;
 }
 
 static uint32_t
@@ -3355,21 +3591,26 @@ static void skl_compute_transition_wm(struct intel_crtc_state *cstate,
 	}
 }
 
-static void skl_compute_pipe_wm(struct intel_crtc_state *cstate,
-				struct skl_ddb_allocation *ddb,
-				struct skl_pipe_wm *pipe_wm)
+static int skl_build_pipe_wm(struct intel_crtc_state *cstate,
+			     struct skl_ddb_allocation *ddb,
+			     struct skl_pipe_wm *pipe_wm)
 {
 	struct drm_device *dev = cstate->base.crtc->dev;
-	const struct drm_i915_private *dev_priv = dev->dev_private;
+	const struct drm_i915_private *dev_priv = to_i915(dev);
 	int level, max_level = ilk_wm_max_level(dev);
+	int ret;
 
 	for (level = 0; level <= max_level; level++) {
-		skl_compute_wm_level(dev_priv, ddb, cstate,
-				     level, &pipe_wm->wm[level]);
+		ret = skl_compute_wm_level(dev_priv, ddb, cstate,
+					   level, &pipe_wm->wm[level]);
+		if (ret)
+			return ret;
 	}
 	pipe_wm->linetime = skl_compute_linetime_wm(cstate);
 
 	skl_compute_transition_wm(cstate, &pipe_wm->trans_wm);
+
+	return 0;
 }
 
 static void skl_compute_wm_results(struct drm_device *dev,
@@ -3442,14 +3683,16 @@ static void skl_ddb_entry_write(struct drm_i915_private *dev_priv,
 static void skl_write_wm_values(struct drm_i915_private *dev_priv,
 				const struct skl_wm_values *new)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct intel_crtc *crtc;
 
 	for_each_intel_crtc(dev, crtc) {
 		int i, level, max_level = ilk_wm_max_level(dev);
 		enum pipe pipe = crtc->pipe;
 
-		if (!new->dirty[pipe])
+		if ((new->dirty_pipes & drm_crtc_mask(&crtc->base)) == 0)
+			continue;
+		if (!crtc->active)
 			continue;
 
 		I915_WRITE(PIPE_WM_LINETIME(pipe), new->wm_linetime[pipe]);
@@ -3537,7 +3780,7 @@ skl_ddb_allocation_included(const struct skl_ddb_allocation *old,
 static void skl_flush_wm_values(struct drm_i915_private *dev_priv,
 				struct skl_wm_values *new_values)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct skl_ddb_allocation *cur_ddb, *new_ddb;
 	bool reallocated[I915_MAX_PIPES] = {};
 	struct intel_crtc *crtc;
@@ -3616,116 +3859,182 @@ static void skl_flush_wm_values(struct drm_i915_private *dev_priv,
 	}
 }
 
-static bool skl_update_pipe_wm(struct drm_crtc *crtc,
-			       struct skl_ddb_allocation *ddb, /* out */
-			       struct skl_pipe_wm *pipe_wm /* out */)
+static int skl_update_pipe_wm(struct drm_crtc_state *cstate,
+			      struct skl_ddb_allocation *ddb, /* out */
+			      struct skl_pipe_wm *pipe_wm, /* out */
+			      bool *changed /* out */)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
+	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->crtc);
+	struct intel_crtc_state *intel_cstate = to_intel_crtc_state(cstate);
+	int ret;
 
-	skl_allocate_pipe_ddb(cstate, ddb);
-	skl_compute_pipe_wm(cstate, ddb, pipe_wm);
+	ret = skl_build_pipe_wm(intel_cstate, ddb, pipe_wm);
+	if (ret)
+		return ret;
 
 	if (!memcmp(&intel_crtc->wm.active.skl, pipe_wm, sizeof(*pipe_wm)))
-		return false;
+		*changed = false;
+	else
+		*changed = true;
 
-	intel_crtc->wm.active.skl = *pipe_wm;
+	return 0;
+}
 
-	return true;
+static uint32_t
+pipes_modified(struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *cstate;
+	uint32_t i, ret = 0;
+
+	for_each_crtc_in_state(state, crtc, cstate, i)
+		ret |= drm_crtc_mask(crtc);
+
+	return ret;
 }
 
-static void skl_update_other_pipe_wm(struct drm_device *dev,
-				     struct drm_crtc *crtc,
-				     struct skl_wm_values *r)
+static int
+skl_compute_ddb(struct drm_atomic_state *state)
 {
+	struct drm_device *dev = state->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
 	struct intel_crtc *intel_crtc;
-	struct intel_crtc *this_crtc = to_intel_crtc(crtc);
+	struct skl_ddb_allocation *ddb = &intel_state->wm_results.ddb;
+	uint32_t realloc_pipes = pipes_modified(state);
+	int ret;
 
 	/*
-	 * If the WM update hasn't changed the allocation for this_crtc (the
-	 * crtc we are currently computing the new WM values for), other
-	 * enabled crtcs will keep the same allocation and we don't need to
-	 * recompute anything for them.
+	 * If this is our first atomic update following hardware readout,
+	 * we can't trust the DDB that the BIOS programmed for us.  Let's
+	 * pretend that all pipes switched active status so that we'll
+	 * ensure a full DDB recompute.
 	 */
-	if (!skl_ddb_allocation_changed(&r->ddb, this_crtc))
-		return;
+	if (dev_priv->wm.distrust_bios_wm)
+		intel_state->active_pipe_changes = ~0;
 
 	/*
-	 * Otherwise, because of this_crtc being freshly enabled/disabled, the
-	 * other active pipes need new DDB allocation and WM values.
+	 * If the modeset changes which CRTC's are active, we need to
+	 * recompute the DDB allocation for *all* active pipes, even
+	 * those that weren't otherwise being modified in any way by this
+	 * atomic commit.  Due to the shrinking of the per-pipe allocations
+	 * when new active CRTC's are added, it's possible for a pipe that
+	 * we were already using and aren't changing at all here to suddenly
+	 * become invalid if its DDB needs exceeds its new allocation.
+	 *
+	 * Note that if we wind up doing a full DDB recompute, we can't let
+	 * any other display updates race with this transaction, so we need
+	 * to grab the lock on *all* CRTC's.
 	 */
-	for_each_intel_crtc(dev, intel_crtc) {
-		struct skl_pipe_wm pipe_wm = {};
-		bool wm_changed;
-
-		if (this_crtc->pipe == intel_crtc->pipe)
-			continue;
+	if (intel_state->active_pipe_changes) {
+		realloc_pipes = ~0;
+		intel_state->wm_results.dirty_pipes = ~0;
+	}
 
-		if (!intel_crtc->active)
-			continue;
+	for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) {
+		struct intel_crtc_state *cstate;
 
-		wm_changed = skl_update_pipe_wm(&intel_crtc->base,
-						&r->ddb, &pipe_wm);
+		cstate = intel_atomic_get_crtc_state(state, intel_crtc);
+		if (IS_ERR(cstate))
+			return PTR_ERR(cstate);
 
-		/*
-		 * If we end up re-computing the other pipe WM values, it's
-		 * because it was really needed, so we expect the WM values to
-		 * be different.
-		 */
-		WARN_ON(!wm_changed);
-
-		skl_compute_wm_results(dev, &pipe_wm, r, intel_crtc);
-		r->dirty[intel_crtc->pipe] = true;
+		ret = skl_allocate_pipe_ddb(cstate, ddb);
+		if (ret)
+			return ret;
 	}
+
+	return 0;
 }
 
-static void skl_clear_wm(struct skl_wm_values *watermarks, enum pipe pipe)
+static int
+skl_compute_wm(struct drm_atomic_state *state)
 {
-	watermarks->wm_linetime[pipe] = 0;
-	memset(watermarks->plane[pipe], 0,
-	       sizeof(uint32_t) * 8 * I915_MAX_PLANES);
-	memset(watermarks->plane_trans[pipe],
-	       0, sizeof(uint32_t) * I915_MAX_PLANES);
-	watermarks->plane_trans[pipe][PLANE_CURSOR] = 0;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *cstate;
+	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+	struct skl_wm_values *results = &intel_state->wm_results;
+	struct skl_pipe_wm *pipe_wm;
+	bool changed = false;
+	int ret, i;
+
+	/*
+	 * If this transaction isn't actually touching any CRTC's, don't
+	 * bother with watermark calculation.  Note that if we pass this
+	 * test, we're guaranteed to hold at least one CRTC state mutex,
+	 * which means we can safely use values like dev_priv->active_crtcs
+	 * since any racing commits that want to update them would need to
+	 * hold _all_ CRTC state mutexes.
+	 */
+	for_each_crtc_in_state(state, crtc, cstate, i)
+		changed = true;
+	if (!changed)
+		return 0;
+
+	/* Clear all dirty flags */
+	results->dirty_pipes = 0;
+
+	ret = skl_compute_ddb(state);
+	if (ret)
+		return ret;
+
+	/*
+	 * Calculate WM's for all pipes that are part of this transaction.
+	 * Note that the DDB allocation above may have added more CRTC's that
+	 * weren't otherwise being modified (and set bits in dirty_pipes) if
+	 * pipe allocations had to change.
+	 *
+	 * FIXME:  Now that we're doing this in the atomic check phase, we
+	 * should allow skl_update_pipe_wm() to return failure in cases where
+	 * no suitable watermark values can be found.
+	 */
+	for_each_crtc_in_state(state, crtc, cstate, i) {
+		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+		struct intel_crtc_state *intel_cstate =
+			to_intel_crtc_state(cstate);
+
+		pipe_wm = &intel_cstate->wm.skl.optimal;
+		ret = skl_update_pipe_wm(cstate, &results->ddb, pipe_wm,
+					 &changed);
+		if (ret)
+			return ret;
 
-	/* Clear ddb entries for pipe */
-	memset(&watermarks->ddb.pipe[pipe], 0, sizeof(struct skl_ddb_entry));
-	memset(&watermarks->ddb.plane[pipe], 0,
-	       sizeof(struct skl_ddb_entry) * I915_MAX_PLANES);
-	memset(&watermarks->ddb.y_plane[pipe], 0,
-	       sizeof(struct skl_ddb_entry) * I915_MAX_PLANES);
-	memset(&watermarks->ddb.plane[pipe][PLANE_CURSOR], 0,
-	       sizeof(struct skl_ddb_entry));
+		if (changed)
+			results->dirty_pipes |= drm_crtc_mask(crtc);
 
+		if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0)
+			/* This pipe's WM's did not change */
+			continue;
+
+		intel_cstate->update_wm_pre = true;
+		skl_compute_wm_results(crtc->dev, pipe_wm, results, intel_crtc);
+	}
+
+	return 0;
 }
 
 static void skl_update_wm(struct drm_crtc *crtc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct skl_wm_values *results = &dev_priv->wm.skl_results;
 	struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
-	struct skl_pipe_wm *pipe_wm = &cstate->wm.optimal.skl;
+	struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal;
 
-
-	/* Clear all dirty flags */
-	memset(results->dirty, 0, sizeof(bool) * I915_MAX_PIPES);
-
-	skl_clear_wm(results, intel_crtc->pipe);
-
-	if (!skl_update_pipe_wm(crtc, &results->ddb, pipe_wm))
+	if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0)
 		return;
 
-	skl_compute_wm_results(dev, pipe_wm, results, intel_crtc);
-	results->dirty[intel_crtc->pipe] = true;
+	intel_crtc->wm.active.skl = *pipe_wm;
+
+	mutex_lock(&dev_priv->wm.wm_mutex);
 
-	skl_update_other_pipe_wm(dev, crtc, results);
 	skl_write_wm_values(dev_priv, results);
 	skl_flush_wm_values(dev_priv, results);
 
 	/* store the new configuration */
 	dev_priv->wm.skl_hw = *results;
+
+	mutex_unlock(&dev_priv->wm.wm_mutex);
 }
 
 static void ilk_compute_wm_config(struct drm_device *dev,
@@ -3748,7 +4057,7 @@ static void ilk_compute_wm_config(struct drm_device *dev,
 
 static void ilk_program_watermarks(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm;
 	struct ilk_wm_maximums max;
 	struct intel_wm_config config = {};
@@ -3785,7 +4094,7 @@ static void ilk_initial_watermarks(struct intel_crtc_state *cstate)
 	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
-	intel_crtc->wm.active.ilk = cstate->wm.intermediate;
+	intel_crtc->wm.active.ilk = cstate->wm.ilk.intermediate;
 	ilk_program_watermarks(dev_priv);
 	mutex_unlock(&dev_priv->wm.wm_mutex);
 }
@@ -3797,7 +4106,7 @@ static void ilk_optimize_watermarks(struct intel_crtc_state *cstate)
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 	if (cstate->wm.need_postvbl_update) {
-		intel_crtc->wm.active.ilk = cstate->wm.optimal.ilk;
+		intel_crtc->wm.active.ilk = cstate->wm.ilk.optimal;
 		ilk_program_watermarks(dev_priv);
 	}
 	mutex_unlock(&dev_priv->wm.wm_mutex);
@@ -3850,11 +4159,11 @@ static void skl_pipe_wm_active_state(uint32_t val,
 static void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct skl_wm_values *hw = &dev_priv->wm.skl_hw;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
-	struct skl_pipe_wm *active = &cstate->wm.optimal.skl;
+	struct skl_pipe_wm *active = &cstate->wm.skl.optimal;
 	enum pipe pipe = intel_crtc->pipe;
 	int level, i, max_level;
 	uint32_t temp;
@@ -3877,7 +4186,7 @@ static void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc)
 	if (!intel_crtc->active)
 		return;
 
-	hw->dirty[pipe] = true;
+	hw->dirty_pipes |= drm_crtc_mask(crtc);
 
 	active->linetime = hw->wm_linetime[pipe];
 
@@ -3904,23 +4213,31 @@ static void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc)
 
 void skl_wm_get_hw_state(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct skl_ddb_allocation *ddb = &dev_priv->wm.skl_hw.ddb;
 	struct drm_crtc *crtc;
 
 	skl_ddb_get_hw_state(dev_priv, ddb);
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
 		skl_pipe_wm_get_hw_state(crtc);
+
+	if (dev_priv->active_crtcs) {
+		/* Fully recompute DDB on first atomic commit */
+		dev_priv->wm.distrust_bios_wm = true;
+	} else {
+		/* Easy/common case; just sanitize DDB now if everything off */
+		memset(ddb, 0, sizeof(*ddb));
+	}
 }
 
 static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct ilk_wm_values *hw = &dev_priv->wm.hw;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
-	struct intel_pipe_wm *active = &cstate->wm.optimal.ilk;
+	struct intel_pipe_wm *active = &cstate->wm.ilk.optimal;
 	enum pipe pipe = intel_crtc->pipe;
 	static const i915_reg_t wm0_pipe_reg[] = {
 		[PIPE_A] = WM0_PIPEA_ILK,
@@ -4120,7 +4437,7 @@ void vlv_wm_get_hw_state(struct drm_device *dev)
 
 void ilk_wm_get_hw_state(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct ilk_wm_values *hw = &dev_priv->wm.hw;
 	struct drm_crtc *crtc;
 
@@ -4182,7 +4499,7 @@ void ilk_wm_get_hw_state(struct drm_device *dev)
  */
 void intel_update_watermarks(struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 
 	if (dev_priv->display.update_wm)
 		dev_priv->display.update_wm(crtc);
@@ -4197,9 +4514,8 @@ DEFINE_SPINLOCK(mchdev_lock);
  * mchdev_lock. */
 static struct drm_i915_private *i915_mch_dev;
 
-bool ironlake_set_drps(struct drm_device *dev, u8 val)
+bool ironlake_set_drps(struct drm_i915_private *dev_priv, u8 val)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u16 rgvswctl;
 
 	assert_spin_locked(&mchdev_lock);
@@ -4221,9 +4537,8 @@ bool ironlake_set_drps(struct drm_device *dev, u8 val)
 	return true;
 }
 
-static void ironlake_enable_drps(struct drm_device *dev)
+static void ironlake_enable_drps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 rgvmodectl;
 	u8 fmax, fmin, fstart, vstart;
 
@@ -4280,7 +4595,7 @@ static void ironlake_enable_drps(struct drm_device *dev)
 		DRM_ERROR("stuck trying to change perf mode\n");
 	mdelay(1);
 
-	ironlake_set_drps(dev, fstart);
+	ironlake_set_drps(dev_priv, fstart);
 
 	dev_priv->ips.last_count1 = I915_READ(DMIEC) +
 		I915_READ(DDREC) + I915_READ(CSIEC);
@@ -4291,9 +4606,8 @@ static void ironlake_enable_drps(struct drm_device *dev)
 	spin_unlock_irq(&mchdev_lock);
 }
 
-static void ironlake_disable_drps(struct drm_device *dev)
+static void ironlake_disable_drps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u16 rgvswctl;
 
 	spin_lock_irq(&mchdev_lock);
@@ -4308,7 +4622,7 @@ static void ironlake_disable_drps(struct drm_device *dev)
 	I915_WRITE(DEIMR, I915_READ(DEIMR) | DE_PCU_EVENT);
 
 	/* Go back to the starting frequency */
-	ironlake_set_drps(dev, dev_priv->ips.fstart);
+	ironlake_set_drps(dev_priv, dev_priv->ips.fstart);
 	mdelay(1);
 	rgvswctl |= MEMCTL_CMD_STS;
 	I915_WRITE(MEMSWCTL, rgvswctl);
@@ -4354,19 +4668,23 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 	new_power = dev_priv->rps.power;
 	switch (dev_priv->rps.power) {
 	case LOW_POWER:
-		if (val > dev_priv->rps.efficient_freq + 1 && val > dev_priv->rps.cur_freq)
+		if (val > dev_priv->rps.efficient_freq + 1 &&
+		    val > dev_priv->rps.cur_freq)
 			new_power = BETWEEN;
 		break;
 
 	case BETWEEN:
-		if (val <= dev_priv->rps.efficient_freq && val < dev_priv->rps.cur_freq)
+		if (val <= dev_priv->rps.efficient_freq &&
+		    val < dev_priv->rps.cur_freq)
 			new_power = LOW_POWER;
-		else if (val >= dev_priv->rps.rp0_freq && val > dev_priv->rps.cur_freq)
+		else if (val >= dev_priv->rps.rp0_freq &&
+			 val > dev_priv->rps.cur_freq)
 			new_power = HIGH_POWER;
 		break;
 
 	case HIGH_POWER:
-		if (val < (dev_priv->rps.rp1_freq + dev_priv->rps.rp0_freq) >> 1 && val < dev_priv->rps.cur_freq)
+		if (val < (dev_priv->rps.rp1_freq + dev_priv->rps.rp0_freq) >> 1 &&
+		    val < dev_priv->rps.cur_freq)
 			new_power = BETWEEN;
 		break;
 	}
@@ -4412,22 +4730,24 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 	}
 
 	I915_WRITE(GEN6_RP_UP_EI,
-		GT_INTERVAL_FROM_US(dev_priv, ei_up));
+		   GT_INTERVAL_FROM_US(dev_priv, ei_up));
 	I915_WRITE(GEN6_RP_UP_THRESHOLD,
-		GT_INTERVAL_FROM_US(dev_priv, (ei_up * threshold_up / 100)));
+		   GT_INTERVAL_FROM_US(dev_priv,
+				       ei_up * threshold_up / 100));
 
 	I915_WRITE(GEN6_RP_DOWN_EI,
-		GT_INTERVAL_FROM_US(dev_priv, ei_down));
+		   GT_INTERVAL_FROM_US(dev_priv, ei_down));
 	I915_WRITE(GEN6_RP_DOWN_THRESHOLD,
-		GT_INTERVAL_FROM_US(dev_priv, (ei_down * threshold_down / 100)));
+		   GT_INTERVAL_FROM_US(dev_priv,
+				       ei_down * threshold_down / 100));
 
-	 I915_WRITE(GEN6_RP_CONTROL,
-		    GEN6_RP_MEDIA_TURBO |
-		    GEN6_RP_MEDIA_HW_NORMAL_MODE |
-		    GEN6_RP_MEDIA_IS_GFX |
-		    GEN6_RP_ENABLE |
-		    GEN6_RP_UP_BUSY_AVG |
-		    GEN6_RP_DOWN_IDLE_AVG);
+	I915_WRITE(GEN6_RP_CONTROL,
+		   GEN6_RP_MEDIA_TURBO |
+		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
+		   GEN6_RP_MEDIA_IS_GFX |
+		   GEN6_RP_ENABLE |
+		   GEN6_RP_UP_BUSY_AVG |
+		   GEN6_RP_DOWN_IDLE_AVG);
 
 	dev_priv->rps.power = new_power;
 	dev_priv->rps.up_threshold = threshold_up;
@@ -4452,12 +4772,10 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
 /* gen6_set_rps is called to update the frequency request, but should also be
  * called when the range (min_delay and max_delay) is modified so that we can
  * update the GEN6_RP_INTERRUPT_LIMITS register accordingly. */
-static void gen6_set_rps(struct drm_device *dev, u8 val)
+static void gen6_set_rps(struct drm_i915_private *dev_priv, u8 val)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	/* WaGsvDisableTurbo: Workaround to disable turbo on BXT A* */
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1))
+	if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1))
 		return;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -4470,10 +4788,10 @@ static void gen6_set_rps(struct drm_device *dev, u8 val)
 	if (val != dev_priv->rps.cur_freq) {
 		gen6_set_rps_thresholds(dev_priv, val);
 
-		if (IS_GEN9(dev))
+		if (IS_GEN9(dev_priv))
 			I915_WRITE(GEN6_RPNSWREQ,
 				   GEN9_FREQUENCY(val));
-		else if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 			I915_WRITE(GEN6_RPNSWREQ,
 				   HSW_FREQUENCY(val));
 		else
@@ -4495,15 +4813,13 @@ static void gen6_set_rps(struct drm_device *dev, u8 val)
 	trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
 }
 
-static void valleyview_set_rps(struct drm_device *dev, u8 val)
+static void valleyview_set_rps(struct drm_i915_private *dev_priv, u8 val)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 	WARN_ON(val > dev_priv->rps.max_freq);
 	WARN_ON(val < dev_priv->rps.min_freq);
 
-	if (WARN_ONCE(IS_CHERRYVIEW(dev) && (val & 1),
+	if (WARN_ONCE(IS_CHERRYVIEW(dev_priv) && (val & 1),
 		      "Odd GPU freq value\n"))
 		val &= ~1;
 
@@ -4536,7 +4852,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 	/* Wake up the media well, as that takes a lot less
 	 * power than the Render well. */
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_MEDIA);
-	valleyview_set_rps(dev_priv->dev, val);
+	valleyview_set_rps(dev_priv, val);
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_MEDIA);
 }
 
@@ -4548,20 +4864,33 @@ void gen6_rps_busy(struct drm_i915_private *dev_priv)
 			gen6_rps_reset_ei(dev_priv);
 		I915_WRITE(GEN6_PMINTRMSK,
 			   gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq));
+
+		gen6_enable_rps_interrupts(dev_priv);
+
+		/* Ensure we start at the user's desired frequency */
+		intel_set_rps(dev_priv,
+			      clamp(dev_priv->rps.cur_freq,
+				    dev_priv->rps.min_freq_softlimit,
+				    dev_priv->rps.max_freq_softlimit));
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
 void gen6_rps_idle(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	/* Flush our bottom-half so that it does not race with us
+	 * setting the idle frequency and so that it is bounded by
+	 * our rpm wakeref. And then disable the interrupts to stop any
+	 * futher RPS reclocking whilst we are asleep.
+	 */
+	gen6_disable_rps_interrupts(dev_priv);
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (dev_priv->rps.enabled) {
-		if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))
+		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 			vlv_set_rps_idle(dev_priv);
 		else
-			gen6_set_rps(dev_priv->dev, dev_priv->rps.idle_freq);
+			gen6_set_rps(dev_priv, dev_priv->rps.idle_freq);
 		dev_priv->rps.last_adj = 0;
 		I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
 	}
@@ -4580,7 +4909,7 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv,
 	/* This is intentionally racy! We peek at the state here, then
 	 * validate inside the RPS worker.
 	 */
-	if (!(dev_priv->mm.busy &&
+	if (!(dev_priv->gt.awake &&
 	      dev_priv->rps.enabled &&
 	      dev_priv->rps.cur_freq < dev_priv->rps.max_freq_softlimit))
 		return;
@@ -4596,7 +4925,7 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv,
 		spin_lock_irq(&dev_priv->irq_lock);
 		if (dev_priv->rps.interrupts_enabled) {
 			dev_priv->rps.client_boost = true;
-			queue_work(dev_priv->wq, &dev_priv->rps.work);
+			schedule_work(&dev_priv->rps.work);
 		}
 		spin_unlock_irq(&dev_priv->irq_lock);
 
@@ -4609,49 +4938,39 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv,
 	spin_unlock(&dev_priv->rps.client_lock);
 }
 
-void intel_set_rps(struct drm_device *dev, u8 val)
+void intel_set_rps(struct drm_i915_private *dev_priv, u8 val)
 {
-	if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))
-		valleyview_set_rps(dev, val);
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		valleyview_set_rps(dev_priv, val);
 	else
-		gen6_set_rps(dev, val);
+		gen6_set_rps(dev_priv, val);
 }
 
-static void gen9_disable_rc6(struct drm_device *dev)
+static void gen9_disable_rc6(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 	I915_WRITE(GEN9_PG_ENABLE, 0);
 }
 
-static void gen9_disable_rps(struct drm_device *dev)
+static void gen9_disable_rps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	I915_WRITE(GEN6_RP_CONTROL, 0);
 }
 
-static void gen6_disable_rps(struct drm_device *dev)
+static void gen6_disable_rps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
 	I915_WRITE(GEN6_RP_CONTROL, 0);
 }
 
-static void cherryview_disable_rps(struct drm_device *dev)
+static void cherryview_disable_rps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 }
 
-static void valleyview_disable_rps(struct drm_device *dev)
+static void valleyview_disable_rps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	/* we're doing forcewake before Disabling RC6,
 	 * This what the BIOS expects when going into suspend */
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
@@ -4661,34 +4980,45 @@ static void valleyview_disable_rps(struct drm_device *dev)
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-static void intel_print_rc6_info(struct drm_device *dev, u32 mode)
+static void intel_print_rc6_info(struct drm_i915_private *dev_priv, u32 mode)
 {
-	if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		if (mode & (GEN7_RC_CTL_TO_MODE | GEN6_RC_CTL_EI_MODE(1)))
 			mode = GEN6_RC_CTL_RC6_ENABLE;
 		else
 			mode = 0;
 	}
-	if (HAS_RC6p(dev))
-		DRM_DEBUG_KMS("Enabling RC6 states: RC6 %s RC6p %s RC6pp %s\n",
-			      onoff(mode & GEN6_RC_CTL_RC6_ENABLE),
-			      onoff(mode & GEN6_RC_CTL_RC6p_ENABLE),
-			      onoff(mode & GEN6_RC_CTL_RC6pp_ENABLE));
+	if (HAS_RC6p(dev_priv))
+		DRM_DEBUG_DRIVER("Enabling RC6 states: "
+				 "RC6 %s RC6p %s RC6pp %s\n",
+				 onoff(mode & GEN6_RC_CTL_RC6_ENABLE),
+				 onoff(mode & GEN6_RC_CTL_RC6p_ENABLE),
+				 onoff(mode & GEN6_RC_CTL_RC6pp_ENABLE));
 
 	else
-		DRM_DEBUG_KMS("Enabling RC6 states: RC6 %s\n",
-			      onoff(mode & GEN6_RC_CTL_RC6_ENABLE));
+		DRM_DEBUG_DRIVER("Enabling RC6 states: RC6 %s\n",
+				 onoff(mode & GEN6_RC_CTL_RC6_ENABLE));
 }
 
-static bool bxt_check_bios_rc6_setup(const struct drm_device *dev)
+static bool bxt_check_bios_rc6_setup(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	bool enable_rc6 = true;
 	unsigned long rc6_ctx_base;
+	u32 rc_ctl;
+	int rc_sw_target;
+
+	rc_ctl = I915_READ(GEN6_RC_CONTROL);
+	rc_sw_target = (I915_READ(GEN6_RC_STATE) & RC_SW_TARGET_STATE_MASK) >>
+		       RC_SW_TARGET_STATE_SHIFT;
+	DRM_DEBUG_DRIVER("BIOS enabled RC states: "
+			 "HW_CTRL %s HW_RC6 %s SW_TARGET_STATE %x\n",
+			 onoff(rc_ctl & GEN6_RC_CTL_HW_ENABLE),
+			 onoff(rc_ctl & GEN6_RC_CTL_RC6_ENABLE),
+			 rc_sw_target);
 
 	if (!(I915_READ(RC6_LOCATION) & RC6_CTX_IN_DRAM)) {
-		DRM_DEBUG_KMS("RC6 Base location not set properly.\n");
+		DRM_DEBUG_DRIVER("RC6 Base location not set properly.\n");
 		enable_rc6 = false;
 	}
 
@@ -4700,7 +5030,7 @@ static bool bxt_check_bios_rc6_setup(const struct drm_device *dev)
 	if (!((rc6_ctx_base >= ggtt->stolen_reserved_base) &&
 	      (rc6_ctx_base + PAGE_SIZE <= ggtt->stolen_reserved_base +
 					ggtt->stolen_reserved_size))) {
-		DRM_DEBUG_KMS("RC6 Base address not as expected.\n");
+		DRM_DEBUG_DRIVER("RC6 Base address not as expected.\n");
 		enable_rc6 = false;
 	}
 
@@ -4708,31 +5038,40 @@ static bool bxt_check_bios_rc6_setup(const struct drm_device *dev)
 	      ((I915_READ(PWRCTX_MAXCNT_VCSUNIT0) & IDLE_TIME_MASK) > 1) &&
 	      ((I915_READ(PWRCTX_MAXCNT_BCSUNIT) & IDLE_TIME_MASK) > 1) &&
 	      ((I915_READ(PWRCTX_MAXCNT_VECSUNIT) & IDLE_TIME_MASK) > 1))) {
-		DRM_DEBUG_KMS("Engine Idle wait time not set properly.\n");
+		DRM_DEBUG_DRIVER("Engine Idle wait time not set properly.\n");
+		enable_rc6 = false;
+	}
+
+	if (!I915_READ(GEN8_PUSHBUS_CONTROL) ||
+	    !I915_READ(GEN8_PUSHBUS_ENABLE) ||
+	    !I915_READ(GEN8_PUSHBUS_SHIFT)) {
+		DRM_DEBUG_DRIVER("Pushbus not setup properly.\n");
+		enable_rc6 = false;
+	}
+
+	if (!I915_READ(GEN6_GFXPAUSE)) {
+		DRM_DEBUG_DRIVER("GFX pause not setup properly.\n");
 		enable_rc6 = false;
 	}
 
-	if (!(I915_READ(GEN6_RC_CONTROL) & (GEN6_RC_CTL_RC6_ENABLE |
-					    GEN6_RC_CTL_HW_ENABLE)) &&
-	    ((I915_READ(GEN6_RC_CONTROL) & GEN6_RC_CTL_HW_ENABLE) ||
-	     !(I915_READ(GEN6_RC_STATE) & RC6_STATE))) {
-		DRM_DEBUG_KMS("HW/SW RC6 is not enabled by BIOS.\n");
+	if (!I915_READ(GEN8_MISC_CTRL0)) {
+		DRM_DEBUG_DRIVER("GPM control not setup properly.\n");
 		enable_rc6 = false;
 	}
 
 	return enable_rc6;
 }
 
-int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6)
+int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6)
 {
 	/* No RC6 before Ironlake and code is gone for ilk. */
-	if (INTEL_INFO(dev)->gen < 6)
+	if (INTEL_INFO(dev_priv)->gen < 6)
 		return 0;
 
 	if (!enable_rc6)
 		return 0;
 
-	if (IS_BROXTON(dev) && !bxt_check_bios_rc6_setup(dev)) {
+	if (IS_BROXTON(dev_priv) && !bxt_check_bios_rc6_setup(dev_priv)) {
 		DRM_INFO("RC6 disabled by BIOS\n");
 		return 0;
 	}
@@ -4741,33 +5080,28 @@ int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6)
 	if (enable_rc6 >= 0) {
 		int mask;
 
-		if (HAS_RC6p(dev))
+		if (HAS_RC6p(dev_priv))
 			mask = INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE |
 			       INTEL_RC6pp_ENABLE;
 		else
 			mask = INTEL_RC6_ENABLE;
 
 		if ((enable_rc6 & mask) != enable_rc6)
-			DRM_DEBUG_KMS("Adjusting RC6 mask to %d (requested %d, valid %d)\n",
-				      enable_rc6 & mask, enable_rc6, mask);
+			DRM_DEBUG_DRIVER("Adjusting RC6 mask to %d "
+					 "(requested %d, valid %d)\n",
+					 enable_rc6 & mask, enable_rc6, mask);
 
 		return enable_rc6 & mask;
 	}
 
-	if (IS_IVYBRIDGE(dev))
+	if (IS_IVYBRIDGE(dev_priv))
 		return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE);
 
 	return INTEL_RC6_ENABLE;
 }
 
-int intel_enable_rc6(const struct drm_device *dev)
+static void gen6_init_rps_frequencies(struct drm_i915_private *dev_priv)
 {
-	return i915.enable_rc6;
-}
-
-static void gen6_init_rps_frequencies(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t rp_state_cap;
 	u32 ddcc_status = 0;
 	int ret;
@@ -4775,7 +5109,7 @@ static void gen6_init_rps_frequencies(struct drm_device *dev)
 	/* All of these values are in units of 50MHz */
 	dev_priv->rps.cur_freq		= 0;
 	/* static values from HW: RP0 > RP1 > RPn (min_freq) */
-	if (IS_BROXTON(dev)) {
+	if (IS_BROXTON(dev_priv)) {
 		rp_state_cap = I915_READ(BXT_RP_STATE_CAP);
 		dev_priv->rps.rp0_freq = (rp_state_cap >> 16) & 0xff;
 		dev_priv->rps.rp1_freq = (rp_state_cap >>  8) & 0xff;
@@ -4791,8 +5125,8 @@ static void gen6_init_rps_frequencies(struct drm_device *dev)
 	dev_priv->rps.max_freq		= dev_priv->rps.rp0_freq;
 
 	dev_priv->rps.efficient_freq = dev_priv->rps.rp1_freq;
-	if (IS_HASWELL(dev) || IS_BROADWELL(dev) ||
-	    IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) {
+	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv) ||
+	    IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
 		ret = sandybridge_pcode_read(dev_priv,
 					HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL,
 					&ddcc_status);
@@ -4804,7 +5138,7 @@ static void gen6_init_rps_frequencies(struct drm_device *dev)
 					dev_priv->rps.max_freq);
 	}
 
-	if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) {
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
 		/* Store the frequency values in 16.66 MHZ units, which is
 		   the natural hardware unit for SKL */
 		dev_priv->rps.rp0_freq *= GEN9_FREQ_SCALER;
@@ -4821,7 +5155,7 @@ static void gen6_init_rps_frequencies(struct drm_device *dev)
 		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
 
 	if (dev_priv->rps.min_freq_softlimit == 0) {
-		if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 			dev_priv->rps.min_freq_softlimit =
 				max_t(int, dev_priv->rps.efficient_freq,
 				      intel_freq_opcode(dev_priv, 450));
@@ -4832,16 +5166,14 @@ static void gen6_init_rps_frequencies(struct drm_device *dev)
 }
 
 /* See the Gen9_GT_PM_Programming_Guide doc for the below */
-static void gen9_enable_rps(struct drm_device *dev)
+static void gen9_enable_rps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
-	gen6_init_rps_frequencies(dev);
+	gen6_init_rps_frequencies(dev_priv);
 
 	/* WaGsvDisableTurbo: Workaround to disable turbo on BXT A* */
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+	if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) {
 		/*
 		 * BIOS could leave the Hw Turbo enabled, so need to explicitly
 		 * clear out the Control register just to avoid inconsitency
@@ -4851,7 +5183,7 @@ static void gen9_enable_rps(struct drm_device *dev)
 		 * if the Turbo is left enabled in the Control register, as the
 		 * Up/Down interrupts would remain masked.
 		 */
-		gen9_disable_rps(dev);
+		gen9_disable_rps(dev_priv);
 		intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 		return;
 	}
@@ -4870,14 +5202,13 @@ static void gen9_enable_rps(struct drm_device *dev)
 	 * Up/Down EI & threshold registers, as well as the RP_CONTROL,
 	 * RP_INTERRUPT_LIMITS & RPNSWREQ registers */
 	dev_priv->rps.power = HIGH_POWER; /* force a reset */
-	gen6_set_rps(dev_priv->dev, dev_priv->rps.idle_freq);
+	gen6_set_rps(dev_priv, dev_priv->rps.idle_freq);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-static void gen9_enable_rc6(struct drm_device *dev)
+static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
 	uint32_t rc6_mask = 0;
 
@@ -4894,7 +5225,7 @@ static void gen9_enable_rc6(struct drm_device *dev)
 	/* 2b: Program RC6 thresholds.*/
 
 	/* WaRsDoubleRc6WrlWithCoarsePowerGating: Doubling WRL only when CPG is enabled */
-	if (IS_SKYLAKE(dev))
+	if (IS_SKYLAKE(dev_priv))
 		I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 108 << 16);
 	else
 		I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
@@ -4903,7 +5234,7 @@ static void gen9_enable_rc6(struct drm_device *dev)
 	for_each_engine(engine, dev_priv)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 
-	if (HAS_GUC_UCODE(dev))
+	if (HAS_GUC(dev_priv))
 		I915_WRITE(GUC_MAX_IDLE_COUNT, 0xA);
 
 	I915_WRITE(GEN6_RC_SLEEP, 0);
@@ -4913,12 +5244,12 @@ static void gen9_enable_rc6(struct drm_device *dev)
 	I915_WRITE(GEN9_RENDER_PG_IDLE_HYSTERESIS, 25);
 
 	/* 3a: Enable RC6 */
-	if (intel_enable_rc6(dev) & INTEL_RC6_ENABLE)
+	if (intel_enable_rc6() & INTEL_RC6_ENABLE)
 		rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
 	DRM_INFO("RC6 %s\n", onoff(rc6_mask & GEN6_RC_CTL_RC6_ENABLE));
 	/* WaRsUseTimeoutMode */
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_D0) ||
-	    IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_D0) ||
+	    IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) {
 		I915_WRITE(GEN6_RC6_THRESHOLD, 625); /* 800us */
 		I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE |
 			   GEN7_RC_CTL_TO_MODE |
@@ -4934,19 +5265,17 @@ static void gen9_enable_rc6(struct drm_device *dev)
 	 * 3b: Enable Coarse Power Gating only when RC6 is enabled.
 	 * WaRsDisableCoarsePowerGating:skl,bxt - Render/Media PG need to be disabled with RC6.
 	 */
-	if (NEEDS_WaRsDisableCoarsePowerGating(dev))
+	if (NEEDS_WaRsDisableCoarsePowerGating(dev_priv))
 		I915_WRITE(GEN9_PG_ENABLE, 0);
 	else
 		I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ?
 				(GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE) : 0);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-
 }
 
-static void gen8_enable_rps(struct drm_device *dev)
+static void gen8_enable_rps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
 	uint32_t rc6_mask = 0;
 
@@ -4961,7 +5290,7 @@ static void gen8_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 
 	/* Initialize rps frequencies */
-	gen6_init_rps_frequencies(dev);
+	gen6_init_rps_frequencies(dev_priv);
 
 	/* 2b: Program RC6 thresholds.*/
 	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
@@ -4970,16 +5299,16 @@ static void gen8_enable_rps(struct drm_device *dev)
 	for_each_engine(engine, dev_priv)
 		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
 	I915_WRITE(GEN6_RC_SLEEP, 0);
-	if (IS_BROADWELL(dev))
+	if (IS_BROADWELL(dev_priv))
 		I915_WRITE(GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
 	else
 		I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
 
 	/* 3: Enable RC6 */
-	if (intel_enable_rc6(dev) & INTEL_RC6_ENABLE)
+	if (intel_enable_rc6() & INTEL_RC6_ENABLE)
 		rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
-	intel_print_rc6_info(dev, rc6_mask);
-	if (IS_BROADWELL(dev))
+	intel_print_rc6_info(dev_priv, rc6_mask);
+	if (IS_BROADWELL(dev_priv))
 		I915_WRITE(GEN6_RC_CONTROL, GEN6_RC_CTL_HW_ENABLE |
 				GEN7_RC_CTL_TO_MODE |
 				rc6_mask);
@@ -5020,14 +5349,13 @@ static void gen8_enable_rps(struct drm_device *dev)
 	/* 6: Ring frequency + overclocking (our driver does this later */
 
 	dev_priv->rps.power = HIGH_POWER; /* force a reset */
-	gen6_set_rps(dev_priv->dev, dev_priv->rps.idle_freq);
+	gen6_set_rps(dev_priv, dev_priv->rps.idle_freq);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-static void gen6_enable_rps(struct drm_device *dev)
+static void gen6_enable_rps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
 	u32 rc6vids, pcu_mbox = 0, rc6_mask = 0;
 	u32 gtfifodbg;
@@ -5054,7 +5382,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
 	/* Initialize rps frequencies */
-	gen6_init_rps_frequencies(dev);
+	gen6_init_rps_frequencies(dev_priv);
 
 	/* disable the counters and set deterministic thresholds */
 	I915_WRITE(GEN6_RC_CONTROL, 0);
@@ -5070,7 +5398,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 	I915_WRITE(GEN6_RC1e_THRESHOLD, 1000);
-	if (IS_IVYBRIDGE(dev))
+	if (IS_IVYBRIDGE(dev_priv))
 		I915_WRITE(GEN6_RC6_THRESHOLD, 125000);
 	else
 		I915_WRITE(GEN6_RC6_THRESHOLD, 50000);
@@ -5078,12 +5406,12 @@ static void gen6_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
 
 	/* Check if we are enabling RC6 */
-	rc6_mode = intel_enable_rc6(dev_priv->dev);
+	rc6_mode = intel_enable_rc6();
 	if (rc6_mode & INTEL_RC6_ENABLE)
 		rc6_mask |= GEN6_RC_CTL_RC6_ENABLE;
 
 	/* We don't use those on Haswell */
-	if (!IS_HASWELL(dev)) {
+	if (!IS_HASWELL(dev_priv)) {
 		if (rc6_mode & INTEL_RC6p_ENABLE)
 			rc6_mask |= GEN6_RC_CTL_RC6p_ENABLE;
 
@@ -5091,7 +5419,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 			rc6_mask |= GEN6_RC_CTL_RC6pp_ENABLE;
 	}
 
-	intel_print_rc6_info(dev, rc6_mask);
+	intel_print_rc6_info(dev_priv, rc6_mask);
 
 	I915_WRITE(GEN6_RC_CONTROL,
 		   rc6_mask |
@@ -5115,13 +5443,13 @@ static void gen6_enable_rps(struct drm_device *dev)
 	}
 
 	dev_priv->rps.power = HIGH_POWER; /* force a reset */
-	gen6_set_rps(dev_priv->dev, dev_priv->rps.idle_freq);
+	gen6_set_rps(dev_priv, dev_priv->rps.idle_freq);
 
 	rc6vids = 0;
 	ret = sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS, &rc6vids);
-	if (IS_GEN6(dev) && ret) {
+	if (IS_GEN6(dev_priv) && ret) {
 		DRM_DEBUG_DRIVER("Couldn't check for BIOS workaround\n");
-	} else if (IS_GEN6(dev) && (GEN6_DECODE_RC6_VID(rc6vids & 0xff) < 450)) {
+	} else if (IS_GEN6(dev_priv) && (GEN6_DECODE_RC6_VID(rc6vids & 0xff) < 450)) {
 		DRM_DEBUG_DRIVER("You should update your BIOS. Correcting minimum rc6 voltage (%dmV->%dmV)\n",
 			  GEN6_DECODE_RC6_VID(rc6vids & 0xff), 450);
 		rc6vids &= 0xffff00;
@@ -5134,9 +5462,8 @@ static void gen6_enable_rps(struct drm_device *dev)
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-static void __gen6_update_ring_freq(struct drm_device *dev)
+static void __gen6_update_ring_freq(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int min_freq = 15;
 	unsigned int gpu_freq;
 	unsigned int max_ia_freq, min_ring_freq;
@@ -5165,7 +5492,7 @@ static void __gen6_update_ring_freq(struct drm_device *dev)
 	/* convert DDR frequency from units of 266.6MHz to bandwidth */
 	min_ring_freq = mult_frac(min_ring_freq, 8, 3);
 
-	if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) {
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
 		/* Convert GT frequency to 50 HZ units */
 		min_gpu_freq = dev_priv->rps.min_freq / GEN9_FREQ_SCALER;
 		max_gpu_freq = dev_priv->rps.max_freq / GEN9_FREQ_SCALER;
@@ -5183,16 +5510,16 @@ static void __gen6_update_ring_freq(struct drm_device *dev)
 		int diff = max_gpu_freq - gpu_freq;
 		unsigned int ia_freq = 0, ring_freq = 0;
 
-		if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) {
+		if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
 			/*
 			 * ring_freq = 2 * GT. ring_freq is in 100MHz units
 			 * No floor required for ring frequency on SKL.
 			 */
 			ring_freq = gpu_freq;
-		} else if (INTEL_INFO(dev)->gen >= 8) {
+		} else if (INTEL_INFO(dev_priv)->gen >= 8) {
 			/* max(2 * GT, DDR). NB: GT is 50MHz units */
 			ring_freq = max(min_ring_freq, gpu_freq);
-		} else if (IS_HASWELL(dev)) {
+		} else if (IS_HASWELL(dev_priv)) {
 			ring_freq = mult_frac(gpu_freq, 5, 4);
 			ring_freq = max(min_ring_freq, ring_freq);
 			/* leave ia_freq as the default, chosen by cpufreq */
@@ -5219,26 +5546,23 @@ static void __gen6_update_ring_freq(struct drm_device *dev)
 	}
 }
 
-void gen6_update_ring_freq(struct drm_device *dev)
+void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (!HAS_CORE_RING_FREQ(dev))
+	if (!HAS_CORE_RING_FREQ(dev_priv))
 		return;
 
 	mutex_lock(&dev_priv->rps.hw_lock);
-	__gen6_update_ring_freq(dev);
+	__gen6_update_ring_freq(dev_priv);
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
 static int cherryview_rps_max_freq(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
 	u32 val, rp0;
 
 	val = vlv_punit_read(dev_priv, FB_GFX_FMAX_AT_VMAX_FUSE);
 
-	switch (INTEL_INFO(dev)->eu_total) {
+	switch (INTEL_INFO(dev_priv)->eu_total) {
 	case 8:
 		/* (2 * 4) config */
 		rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS4EU_FUSE_SHIFT);
@@ -5349,9 +5673,8 @@ static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
 	WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
 }
 
-static void cherryview_setup_pctx(struct drm_device *dev)
+static void cherryview_setup_pctx(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	unsigned long pctx_paddr, paddr;
 	u32 pcbr;
@@ -5370,15 +5693,14 @@ static void cherryview_setup_pctx(struct drm_device *dev)
 	DRM_DEBUG_DRIVER("PCBR: 0x%08x\n", I915_READ(VLV_PCBR));
 }
 
-static void valleyview_setup_pctx(struct drm_device *dev)
+static void valleyview_setup_pctx(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *pctx;
 	unsigned long pctx_paddr;
 	u32 pcbr;
 	int pctx_size = 24*1024;
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&dev_priv->drm.struct_mutex);
 
 	pcbr = I915_READ(VLV_PCBR);
 	if (pcbr) {
@@ -5386,7 +5708,7 @@ static void valleyview_setup_pctx(struct drm_device *dev)
 		int pcbr_offset;
 
 		pcbr_offset = (pcbr & (~4095)) - dev_priv->mm.stolen_base;
-		pctx = i915_gem_object_create_stolen_for_preallocated(dev_priv->dev,
+		pctx = i915_gem_object_create_stolen_for_preallocated(&dev_priv->drm,
 								      pcbr_offset,
 								      I915_GTT_OFFSET_NONE,
 								      pctx_size);
@@ -5403,7 +5725,7 @@ static void valleyview_setup_pctx(struct drm_device *dev)
 	 * overlap with other ranges, such as the frame buffer, protected
 	 * memory, or any other relevant ranges.
 	 */
-	pctx = i915_gem_object_create_stolen(dev, pctx_size);
+	pctx = i915_gem_object_create_stolen(&dev_priv->drm, pctx_size);
 	if (!pctx) {
 		DRM_DEBUG("not enough stolen space for PCTX, disabling\n");
 		goto out;
@@ -5415,13 +5737,11 @@ static void valleyview_setup_pctx(struct drm_device *dev)
 out:
 	DRM_DEBUG_DRIVER("PCBR: 0x%08x\n", I915_READ(VLV_PCBR));
 	dev_priv->vlv_pctx = pctx;
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
 }
 
-static void valleyview_cleanup_pctx(struct drm_device *dev)
+static void valleyview_cleanup_pctx(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	if (WARN_ON(!dev_priv->vlv_pctx))
 		return;
 
@@ -5440,12 +5760,11 @@ static void vlv_init_gpll_ref_freq(struct drm_i915_private *dev_priv)
 			 dev_priv->rps.gpll_ref_freq);
 }
 
-static void valleyview_init_gt_powersave(struct drm_device *dev)
+static void valleyview_init_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 val;
 
-	valleyview_setup_pctx(dev);
+	valleyview_setup_pctx(dev_priv);
 
 	vlv_init_gpll_ref_freq(dev_priv);
 
@@ -5499,12 +5818,11 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
-static void cherryview_init_gt_powersave(struct drm_device *dev)
+static void cherryview_init_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 val;
 
-	cherryview_setup_pctx(dev);
+	cherryview_setup_pctx(dev_priv);
 
 	vlv_init_gpll_ref_freq(dev_priv);
 
@@ -5564,14 +5882,13 @@ static void cherryview_init_gt_powersave(struct drm_device *dev)
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
-static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
+static void valleyview_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	valleyview_cleanup_pctx(dev);
+	valleyview_cleanup_pctx(dev_priv);
 }
 
-static void cherryview_enable_rps(struct drm_device *dev)
+static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
 	u32 gtfifodbg, val, rc6_mode = 0, pcbr;
 
@@ -5616,8 +5933,8 @@ static void cherryview_enable_rps(struct drm_device *dev)
 	pcbr = I915_READ(VLV_PCBR);
 
 	/* 3: Enable RC6 */
-	if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
-						(pcbr >> VLV_PCBR_ADDR_SHIFT))
+	if ((intel_enable_rc6() & INTEL_RC6_ENABLE) &&
+	    (pcbr >> VLV_PCBR_ADDR_SHIFT))
 		rc6_mode = GEN7_RC_CTL_TO_MODE;
 
 	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
@@ -5662,14 +5979,13 @@ static void cherryview_enable_rps(struct drm_device *dev)
 			 intel_gpu_freq(dev_priv, dev_priv->rps.idle_freq),
 			 dev_priv->rps.idle_freq);
 
-	valleyview_set_rps(dev_priv->dev, dev_priv->rps.idle_freq);
+	valleyview_set_rps(dev_priv, dev_priv->rps.idle_freq);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-static void valleyview_enable_rps(struct drm_device *dev)
+static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
 	u32 gtfifodbg, val, rc6_mode = 0;
 
@@ -5722,10 +6038,10 @@ static void valleyview_enable_rps(struct drm_device *dev)
 				      VLV_MEDIA_RC6_COUNT_EN |
 				      VLV_RENDER_RC6_COUNT_EN));
 
-	if (intel_enable_rc6(dev) & INTEL_RC6_ENABLE)
+	if (intel_enable_rc6() & INTEL_RC6_ENABLE)
 		rc6_mode = GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL;
 
-	intel_print_rc6_info(dev, rc6_mode);
+	intel_print_rc6_info(dev_priv, rc6_mode);
 
 	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
 
@@ -5752,7 +6068,7 @@ static void valleyview_enable_rps(struct drm_device *dev)
 			 intel_gpu_freq(dev_priv, dev_priv->rps.idle_freq),
 			 dev_priv->rps.idle_freq);
 
-	valleyview_set_rps(dev_priv->dev, dev_priv->rps.idle_freq);
+	valleyview_set_rps(dev_priv, dev_priv->rps.idle_freq);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
@@ -5842,10 +6158,9 @@ static unsigned long __i915_chipset_val(struct drm_i915_private *dev_priv)
 
 unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
 	unsigned long val;
 
-	if (INTEL_INFO(dev)->gen != 5)
+	if (INTEL_INFO(dev_priv)->gen != 5)
 		return 0;
 
 	spin_lock_irq(&mchdev_lock);
@@ -5885,11 +6200,10 @@ static int _pxvid_to_vd(u8 pxvid)
 
 static u32 pvid_to_extvid(struct drm_i915_private *dev_priv, u8 pxvid)
 {
-	struct drm_device *dev = dev_priv->dev;
 	const int vd = _pxvid_to_vd(pxvid);
 	const int vm = vd - 1125;
 
-	if (INTEL_INFO(dev)->is_mobile)
+	if (INTEL_INFO(dev_priv)->is_mobile)
 		return vm > 0 ? vm : 0;
 
 	return vd;
@@ -5930,9 +6244,7 @@ static void __i915_update_gfx_val(struct drm_i915_private *dev_priv)
 
 void i915_update_gfx_val(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
-
-	if (INTEL_INFO(dev)->gen != 5)
+	if (INTEL_INFO(dev_priv)->gen != 5)
 		return;
 
 	spin_lock_irq(&mchdev_lock);
@@ -5981,10 +6293,9 @@ static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv)
 
 unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
 	unsigned long val;
 
-	if (INTEL_INFO(dev)->gen != 5)
+	if (INTEL_INFO(dev_priv)->gen != 5)
 		return 0;
 
 	spin_lock_irq(&mchdev_lock);
@@ -6125,7 +6436,7 @@ bool i915_gpu_turbo_disable(void)
 
 	dev_priv->ips.max_delay = dev_priv->ips.fstart;
 
-	if (!ironlake_set_drps(dev_priv->dev, dev_priv->ips.fstart))
+	if (!ironlake_set_drps(dev_priv, dev_priv->ips.fstart))
 		ret = false;
 
 out_unlock:
@@ -6173,9 +6484,8 @@ void intel_gpu_ips_teardown(void)
 	spin_unlock_irq(&mchdev_lock);
 }
 
-static void intel_init_emon(struct drm_device *dev)
+static void intel_init_emon(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 lcfuse;
 	u8 pxw[16];
 	int i;
@@ -6244,10 +6554,8 @@ static void intel_init_emon(struct drm_device *dev)
 	dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK);
 }
 
-void intel_init_gt_powersave(struct drm_device *dev)
+void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	/*
 	 * RPM depends on RC6 to save restore the GT HW context, so make RC6 a
 	 * requirement.
@@ -6257,74 +6565,66 @@ void intel_init_gt_powersave(struct drm_device *dev)
 		intel_runtime_pm_get(dev_priv);
 	}
 
-	if (IS_CHERRYVIEW(dev))
-		cherryview_init_gt_powersave(dev);
-	else if (IS_VALLEYVIEW(dev))
-		valleyview_init_gt_powersave(dev);
+	if (IS_CHERRYVIEW(dev_priv))
+		cherryview_init_gt_powersave(dev_priv);
+	else if (IS_VALLEYVIEW(dev_priv))
+		valleyview_init_gt_powersave(dev_priv);
 }
 
-void intel_cleanup_gt_powersave(struct drm_device *dev)
+void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (IS_CHERRYVIEW(dev))
+	if (IS_CHERRYVIEW(dev_priv))
 		return;
-	else if (IS_VALLEYVIEW(dev))
-		valleyview_cleanup_gt_powersave(dev);
+	else if (IS_VALLEYVIEW(dev_priv))
+		valleyview_cleanup_gt_powersave(dev_priv);
 
 	if (!i915.enable_rc6)
 		intel_runtime_pm_put(dev_priv);
 }
 
-static void gen6_suspend_rps(struct drm_device *dev)
+static void gen6_suspend_rps(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
 
-	gen6_disable_rps_interrupts(dev);
+	gen6_disable_rps_interrupts(dev_priv);
 }
 
 /**
  * intel_suspend_gt_powersave - suspend PM work and helper threads
- * @dev: drm device
+ * @dev_priv: i915 device
  *
  * We don't want to disable RC6 or other features here, we just want
  * to make sure any work we've queued has finished and won't bother
  * us while we're suspended.
  */
-void intel_suspend_gt_powersave(struct drm_device *dev)
+void intel_suspend_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (INTEL_INFO(dev)->gen < 6)
+	if (INTEL_GEN(dev_priv) < 6)
 		return;
 
-	gen6_suspend_rps(dev);
+	gen6_suspend_rps(dev_priv);
 
 	/* Force GPU to min freq during suspend */
 	gen6_rps_idle(dev_priv);
 }
 
-void intel_disable_gt_powersave(struct drm_device *dev)
+void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (IS_IRONLAKE_M(dev)) {
-		ironlake_disable_drps(dev);
-	} else if (INTEL_INFO(dev)->gen >= 6) {
-		intel_suspend_gt_powersave(dev);
+	if (IS_IRONLAKE_M(dev_priv)) {
+		ironlake_disable_drps(dev_priv);
+	} else if (INTEL_INFO(dev_priv)->gen >= 6) {
+		intel_suspend_gt_powersave(dev_priv);
 
 		mutex_lock(&dev_priv->rps.hw_lock);
-		if (INTEL_INFO(dev)->gen >= 9) {
-			gen9_disable_rc6(dev);
-			gen9_disable_rps(dev);
-		} else if (IS_CHERRYVIEW(dev))
-			cherryview_disable_rps(dev);
-		else if (IS_VALLEYVIEW(dev))
-			valleyview_disable_rps(dev);
+		if (INTEL_INFO(dev_priv)->gen >= 9) {
+			gen9_disable_rc6(dev_priv);
+			gen9_disable_rps(dev_priv);
+		} else if (IS_CHERRYVIEW(dev_priv))
+			cherryview_disable_rps(dev_priv);
+		else if (IS_VALLEYVIEW(dev_priv))
+			valleyview_disable_rps(dev_priv);
 		else
-			gen6_disable_rps(dev);
+			gen6_disable_rps(dev_priv);
 
 		dev_priv->rps.enabled = false;
 		mutex_unlock(&dev_priv->rps.hw_lock);
@@ -6336,27 +6636,26 @@ static void intel_gen6_powersave_work(struct work_struct *work)
 	struct drm_i915_private *dev_priv =
 		container_of(work, struct drm_i915_private,
 			     rps.delayed_resume_work.work);
-	struct drm_device *dev = dev_priv->dev;
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
-	gen6_reset_rps_interrupts(dev);
+	gen6_reset_rps_interrupts(dev_priv);
 
-	if (IS_CHERRYVIEW(dev)) {
-		cherryview_enable_rps(dev);
-	} else if (IS_VALLEYVIEW(dev)) {
-		valleyview_enable_rps(dev);
-	} else if (INTEL_INFO(dev)->gen >= 9) {
-		gen9_enable_rc6(dev);
-		gen9_enable_rps(dev);
-		if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev))
-			__gen6_update_ring_freq(dev);
-	} else if (IS_BROADWELL(dev)) {
-		gen8_enable_rps(dev);
-		__gen6_update_ring_freq(dev);
+	if (IS_CHERRYVIEW(dev_priv)) {
+		cherryview_enable_rps(dev_priv);
+	} else if (IS_VALLEYVIEW(dev_priv)) {
+		valleyview_enable_rps(dev_priv);
+	} else if (INTEL_INFO(dev_priv)->gen >= 9) {
+		gen9_enable_rc6(dev_priv);
+		gen9_enable_rps(dev_priv);
+		if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+			__gen6_update_ring_freq(dev_priv);
+	} else if (IS_BROADWELL(dev_priv)) {
+		gen8_enable_rps(dev_priv);
+		__gen6_update_ring_freq(dev_priv);
 	} else {
-		gen6_enable_rps(dev);
-		__gen6_update_ring_freq(dev);
+		gen6_enable_rps(dev_priv);
+		__gen6_update_ring_freq(dev_priv);
 	}
 
 	WARN_ON(dev_priv->rps.max_freq < dev_priv->rps.min_freq);
@@ -6367,27 +6666,25 @@ static void intel_gen6_powersave_work(struct work_struct *work)
 
 	dev_priv->rps.enabled = true;
 
-	gen6_enable_rps_interrupts(dev);
+	gen6_enable_rps_interrupts(dev_priv);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
 	intel_runtime_pm_put(dev_priv);
 }
 
-void intel_enable_gt_powersave(struct drm_device *dev)
+void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	/* Powersaving is controlled by the host when inside a VM */
-	if (intel_vgpu_active(dev))
+	if (intel_vgpu_active(dev_priv))
 		return;
 
-	if (IS_IRONLAKE_M(dev)) {
-		ironlake_enable_drps(dev);
-		mutex_lock(&dev->struct_mutex);
-		intel_init_emon(dev);
-		mutex_unlock(&dev->struct_mutex);
-	} else if (INTEL_INFO(dev)->gen >= 6) {
+	if (IS_IRONLAKE_M(dev_priv)) {
+		ironlake_enable_drps(dev_priv);
+		mutex_lock(&dev_priv->drm.struct_mutex);
+		intel_init_emon(dev_priv);
+		mutex_unlock(&dev_priv->drm.struct_mutex);
+	} else if (INTEL_INFO(dev_priv)->gen >= 6) {
 		/*
 		 * PCU communication is slow and this doesn't need to be
 		 * done at any specific time, so do this out of our fast path
@@ -6406,20 +6703,18 @@ void intel_enable_gt_powersave(struct drm_device *dev)
 	}
 }
 
-void intel_reset_gt_powersave(struct drm_device *dev)
+void intel_reset_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (INTEL_INFO(dev)->gen < 6)
+	if (INTEL_INFO(dev_priv)->gen < 6)
 		return;
 
-	gen6_suspend_rps(dev);
+	gen6_suspend_rps(dev_priv);
 	dev_priv->rps.enabled = false;
 }
 
 static void ibx_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/*
 	 * On Ibex Peak and Cougar Point, we need to disable clock
@@ -6431,7 +6726,7 @@ static void ibx_init_clock_gating(struct drm_device *dev)
 
 static void g4x_disable_trickle_feed(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe;
 
 	for_each_pipe(dev_priv, pipe) {
@@ -6446,7 +6741,7 @@ static void g4x_disable_trickle_feed(struct drm_device *dev)
 
 static void ilk_init_lp_watermarks(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(WM3_LP_ILK, I915_READ(WM3_LP_ILK) & ~WM1_LP_SR_EN);
 	I915_WRITE(WM2_LP_ILK, I915_READ(WM2_LP_ILK) & ~WM1_LP_SR_EN);
@@ -6460,7 +6755,7 @@ static void ilk_init_lp_watermarks(struct drm_device *dev)
 
 static void ironlake_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE;
 
 	/*
@@ -6534,7 +6829,7 @@ static void ironlake_init_clock_gating(struct drm_device *dev)
 
 static void cpt_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	int pipe;
 	uint32_t val;
 
@@ -6571,7 +6866,7 @@ static void cpt_init_clock_gating(struct drm_device *dev)
 
 static void gen6_check_mch_setup(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t tmp;
 
 	tmp = I915_READ(MCH_SSKPD);
@@ -6582,7 +6877,7 @@ static void gen6_check_mch_setup(struct drm_device *dev)
 
 static void gen6_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE;
 
 	I915_WRITE(ILK_DSPCLK_GATE_D, dspclk_gate);
@@ -6697,7 +6992,7 @@ static void gen7_setup_fixed_func_scheduler(struct drm_i915_private *dev_priv)
 
 static void lpt_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/*
 	 * TODO: this bit should only be enabled when really needed, then
@@ -6716,7 +7011,7 @@ static void lpt_init_clock_gating(struct drm_device *dev)
 
 static void lpt_suspend_hw(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (HAS_PCH_LPT_LP(dev)) {
 		uint32_t val = I915_READ(SOUTH_DSPCLK_GATE_D);
@@ -6726,6 +7021,29 @@ static void lpt_suspend_hw(struct drm_device *dev)
 	}
 }
 
+static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv,
+				   int general_prio_credits,
+				   int high_prio_credits)
+{
+	u32 misccpctl;
+
+	/* WaTempDisableDOPClkGating:bdw */
+	misccpctl = I915_READ(GEN7_MISCCPCTL);
+	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
+
+	I915_WRITE(GEN8_L3SQCREG1,
+		   L3_GENERAL_PRIO_CREDITS(general_prio_credits) |
+		   L3_HIGH_PRIO_CREDITS(high_prio_credits));
+
+	/*
+	 * Wait at least 100 clocks before re-enabling clock gating.
+	 * See the definition of L3SQCREG1 in BSpec.
+	 */
+	POSTING_READ(GEN8_L3SQCREG1);
+	udelay(1);
+	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+}
+
 static void kabylake_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -6753,6 +7071,10 @@ static void skylake_init_clock_gating(struct drm_device *dev)
 
 	gen9_init_clock_gating(dev);
 
+	/* WAC6entrylatency:skl */
+	I915_WRITE(FBC_LLC_READ_CTRL, I915_READ(FBC_LLC_READ_CTRL) |
+		   FBC_LLC_FULLY_OPEN);
+
 	/* WaFbcNukeOnHostModify:skl */
 	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
 		   ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
@@ -6760,9 +7082,8 @@ static void skylake_init_clock_gating(struct drm_device *dev)
 
 static void broadwell_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe;
-	uint32_t misccpctl;
 
 	ilk_init_lp_watermarks(dev);
 
@@ -6793,20 +7114,8 @@ static void broadwell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
-	/*
-	 * WaProgramL3SqcReg1Default:bdw
-	 * WaTempDisableDOPClkGating:bdw
-	 */
-	misccpctl = I915_READ(GEN7_MISCCPCTL);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-	I915_WRITE(GEN8_L3SQCREG1, BDW_WA_L3SQCREG1_DEFAULT);
-	/*
-	 * Wait at least 100 clocks before re-enabling clock gating. See
-	 * the definition of L3SQCREG1 in BSpec.
-	 */
-	POSTING_READ(GEN8_L3SQCREG1);
-	udelay(1);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+	/* WaProgramL3SqcReg1Default:bdw */
+	gen8_set_l3sqc_credits(dev_priv, 30, 2);
 
 	/*
 	 * WaGttCachingOffByDefault:bdw
@@ -6815,12 +7124,16 @@ static void broadwell_init_clock_gating(struct drm_device *dev)
 	 */
 	I915_WRITE(HSW_GTT_CACHE_EN, GTT_CACHE_EN_ALL);
 
+	/* WaKVMNotificationOnConfigChange:bdw */
+	I915_WRITE(CHICKEN_PAR2_1, I915_READ(CHICKEN_PAR2_1)
+		   | KVM_CONFIG_CHANGE_NOTIFICATION_SELECT);
+
 	lpt_init_clock_gating(dev);
 }
 
 static void haswell_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	ilk_init_lp_watermarks(dev);
 
@@ -6876,7 +7189,7 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 
 static void ivybridge_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t snpcr;
 
 	ilk_init_lp_watermarks(dev);
@@ -6974,7 +7287,7 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 
 static void valleyview_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* WaDisableEarlyCull:vlv */
 	I915_WRITE(_3D_CHICKEN3,
@@ -7056,7 +7369,7 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 
 static void cherryview_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* WaVSRefCountFullforceMissDisable:chv */
 	/* WaDSRefCountFullforceMissDisable:chv */
@@ -7077,6 +7390,13 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
 	/*
+	 * WaProgramL3SqcReg1Default:chv
+	 * See gfxspecs/Related Documents/Performance Guide/
+	 * LSQC Setting Recommendations.
+	 */
+	gen8_set_l3sqc_credits(dev_priv, 38, 2);
+
+	/*
 	 * GTT cache may not work with big pages, so if those
 	 * are ever enabled GTT cache may need to be disabled.
 	 */
@@ -7085,7 +7405,7 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 
 static void g4x_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t dspclk_gate;
 
 	I915_WRITE(RENCLK_GATE_D1, 0);
@@ -7112,7 +7432,7 @@ static void g4x_init_clock_gating(struct drm_device *dev)
 
 static void crestline_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(RENCLK_GATE_D1, I965_RCC_CLOCK_GATE_DISABLE);
 	I915_WRITE(RENCLK_GATE_D2, 0);
@@ -7128,7 +7448,7 @@ static void crestline_init_clock_gating(struct drm_device *dev)
 
 static void broadwater_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(RENCLK_GATE_D1, I965_RCZ_CLOCK_GATE_DISABLE |
 		   I965_RCC_CLOCK_GATE_DISABLE |
@@ -7145,7 +7465,7 @@ static void broadwater_init_clock_gating(struct drm_device *dev)
 
 static void gen3_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 dstate = I915_READ(D_STATE);
 
 	dstate |= DSTATE_PLL_D3_OFF | DSTATE_GFX_CLOCK_GATING |
@@ -7170,7 +7490,7 @@ static void gen3_init_clock_gating(struct drm_device *dev)
 
 static void i85x_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(RENCLK_GATE_D1, SV_CLOCK_GATE_DISABLE);
 
@@ -7184,7 +7504,7 @@ static void i85x_init_clock_gating(struct drm_device *dev)
 
 static void i830_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(DSPCLK_GATE_D, OVRUNIT_CLOCK_GATE_DISABLE);
 
@@ -7195,7 +7515,7 @@ static void i830_init_clock_gating(struct drm_device *dev)
 
 void intel_init_clock_gating(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	dev_priv->display.init_clock_gating(dev);
 }
@@ -7263,7 +7583,7 @@ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
 /* Set up chip specific power management-related functions */
 void intel_init_pm(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	intel_fbc_init(dev_priv);
 
@@ -7277,6 +7597,7 @@ void intel_init_pm(struct drm_device *dev)
 	if (INTEL_INFO(dev)->gen >= 9) {
 		skl_setup_wm_latency(dev);
 		dev_priv->display.update_wm = skl_update_wm;
+		dev_priv->display.compute_global_watermarks = skl_compute_wm;
 	} else if (HAS_PCH_SPLIT(dev)) {
 		ilk_setup_wm_latency(dev);
 
@@ -7340,46 +7661,59 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val
 {
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
-	if (I915_READ(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) {
+	/* GEN6_PCODE_* are outside of the forcewake domain, we can
+	 * use te fw I915_READ variants to reduce the amount of work
+	 * required when reading/writing.
+	 */
+
+	if (I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) {
 		DRM_DEBUG_DRIVER("warning: pcode (read) mailbox access failed\n");
 		return -EAGAIN;
 	}
 
-	I915_WRITE(GEN6_PCODE_DATA, *val);
-	I915_WRITE(GEN6_PCODE_DATA1, 0);
-	I915_WRITE(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY | mbox);
+	I915_WRITE_FW(GEN6_PCODE_DATA, *val);
+	I915_WRITE_FW(GEN6_PCODE_DATA1, 0);
+	I915_WRITE_FW(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY | mbox);
 
-	if (wait_for((I915_READ(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) == 0,
-		     500)) {
+	if (intel_wait_for_register_fw(dev_priv,
+				       GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0,
+				       500)) {
 		DRM_ERROR("timeout waiting for pcode read (%d) to finish\n", mbox);
 		return -ETIMEDOUT;
 	}
 
-	*val = I915_READ(GEN6_PCODE_DATA);
-	I915_WRITE(GEN6_PCODE_DATA, 0);
+	*val = I915_READ_FW(GEN6_PCODE_DATA);
+	I915_WRITE_FW(GEN6_PCODE_DATA, 0);
 
 	return 0;
 }
 
-int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u32 mbox, u32 val)
+int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
+			       u32 mbox, u32 val)
 {
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
-	if (I915_READ(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) {
+	/* GEN6_PCODE_* are outside of the forcewake domain, we can
+	 * use te fw I915_READ variants to reduce the amount of work
+	 * required when reading/writing.
+	 */
+
+	if (I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) {
 		DRM_DEBUG_DRIVER("warning: pcode (write) mailbox access failed\n");
 		return -EAGAIN;
 	}
 
-	I915_WRITE(GEN6_PCODE_DATA, val);
-	I915_WRITE(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY | mbox);
+	I915_WRITE_FW(GEN6_PCODE_DATA, val);
+	I915_WRITE_FW(GEN6_PCODE_MAILBOX, GEN6_PCODE_READY | mbox);
 
-	if (wait_for((I915_READ(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) == 0,
-		     500)) {
+	if (intel_wait_for_register_fw(dev_priv,
+				       GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0,
+				       500)) {
 		DRM_ERROR("timeout waiting for pcode write (%d) to finish\n", mbox);
 		return -ETIMEDOUT;
 	}
 
-	I915_WRITE(GEN6_PCODE_DATA, 0);
+	I915_WRITE_FW(GEN6_PCODE_DATA, 0);
 
 	return 0;
 }
@@ -7449,23 +7783,21 @@ static void __intel_rps_boost_work(struct work_struct *work)
 	struct request_boost *boost = container_of(work, struct request_boost, work);
 	struct drm_i915_gem_request *req = boost->req;
 
-	if (!i915_gem_request_completed(req, true))
-		gen6_rps_boost(to_i915(req->engine->dev), NULL,
-			       req->emitted_jiffies);
+	if (!i915_gem_request_completed(req))
+		gen6_rps_boost(req->i915, NULL, req->emitted_jiffies);
 
-	i915_gem_request_unreference__unlocked(req);
+	i915_gem_request_unreference(req);
 	kfree(boost);
 }
 
-void intel_queue_rps_boost_for_request(struct drm_device *dev,
-				       struct drm_i915_gem_request *req)
+void intel_queue_rps_boost_for_request(struct drm_i915_gem_request *req)
 {
 	struct request_boost *boost;
 
-	if (req == NULL || INTEL_INFO(dev)->gen < 6)
+	if (req == NULL || INTEL_GEN(req->i915) < 6)
 		return;
 
-	if (i915_gem_request_completed(req, true))
+	if (i915_gem_request_completed(req))
 		return;
 
 	boost = kmalloc(sizeof(*boost), GFP_ATOMIC);
@@ -7476,12 +7808,12 @@ void intel_queue_rps_boost_for_request(struct drm_device *dev,
 	boost->req = req;
 
 	INIT_WORK(&boost->work, __intel_rps_boost_work);
-	queue_work(to_i915(dev)->wq, &boost->work);
+	queue_work(req->i915->wq, &boost->work);
 }
 
 void intel_pm_setup(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	mutex_init(&dev_priv->rps.hw_lock);
 	spin_lock_init(&dev_priv->rps.client_lock);
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index a788d1e9589b..2b0d1baf15b3 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -63,7 +63,7 @@ static bool is_edp_psr(struct intel_dp *intel_dp)
 
 static bool vlv_is_psr_active_on_pipe(struct drm_device *dev, int pipe)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t val;
 
 	val = I915_READ(VLV_PSRSTAT(pipe)) &
@@ -77,7 +77,7 @@ static void intel_psr_write_vsc(struct intel_dp *intel_dp,
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(dig_port->base.base.crtc);
 	enum transcoder cpu_transcoder = crtc->config->cpu_transcoder;
 	i915_reg_t ctl_reg = HSW_TVIDEO_DIP_CTL(cpu_transcoder);
@@ -107,7 +107,7 @@ static void vlv_psr_setup_vsc(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc = intel_dig_port->base.base.crtc;
 	enum pipe pipe = to_intel_crtc(crtc)->pipe;
 	uint32_t val;
@@ -173,10 +173,9 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	uint32_t aux_clock_divider;
 	i915_reg_t aux_ctl_reg;
-	int precharge = 0x3;
 	static const uint8_t aux_msg[] = {
 		[0] = DP_AUX_NATIVE_WRITE << 4,
 		[1] = DP_SET_POWER >> 8,
@@ -185,6 +184,7 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
 		[4] = DP_SET_POWER_D0,
 	};
 	enum port port = dig_port->port;
+	u32 aux_ctl;
 	int i;
 
 	BUILD_BUG_ON(sizeof(aux_msg) > 20);
@@ -197,6 +197,13 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
 				DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF,
 				DP_AUX_FRAME_SYNC_ENABLE);
 
+	if (dev_priv->psr.link_standby)
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
+				   DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE);
+	else
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
+				   DP_PSR_ENABLE);
+
 	aux_ctl_reg = psr_aux_ctl_reg(dev_priv, port);
 
 	/* Setup AUX registers */
@@ -204,40 +211,16 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
 		I915_WRITE(psr_aux_data_reg(dev_priv, port, i >> 2),
 			   intel_dp_pack_aux(&aux_msg[i], sizeof(aux_msg) - i));
 
-	if (INTEL_INFO(dev)->gen >= 9) {
-		uint32_t val;
-
-		val = I915_READ(aux_ctl_reg);
-		val &= ~DP_AUX_CH_CTL_TIME_OUT_MASK;
-		val |= DP_AUX_CH_CTL_TIME_OUT_1600us;
-		val &= ~DP_AUX_CH_CTL_MESSAGE_SIZE_MASK;
-		val |= (sizeof(aux_msg) << DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT);
-		/* Use hardcoded data values for PSR, frame sync and GTC */
-		val &= ~DP_AUX_CH_CTL_PSR_DATA_AUX_REG_SKL;
-		val &= ~DP_AUX_CH_CTL_FS_DATA_AUX_REG_SKL;
-		val &= ~DP_AUX_CH_CTL_GTC_DATA_AUX_REG_SKL;
-		I915_WRITE(aux_ctl_reg, val);
-	} else {
-		I915_WRITE(aux_ctl_reg,
-		   DP_AUX_CH_CTL_TIME_OUT_400us |
-		   (sizeof(aux_msg) << DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT) |
-		   (precharge << DP_AUX_CH_CTL_PRECHARGE_2US_SHIFT) |
-		   (aux_clock_divider << DP_AUX_CH_CTL_BIT_CLOCK_2X_SHIFT));
-	}
-
-	if (dev_priv->psr.link_standby)
-		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
-				   DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE);
-	else
-		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
-				   DP_PSR_ENABLE);
+	aux_ctl = intel_dp->get_aux_send_ctl(intel_dp, 0, sizeof(aux_msg),
+					     aux_clock_divider);
+	I915_WRITE(aux_ctl_reg, aux_ctl);
 }
 
 static void vlv_psr_enable_source(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc = dig_port->base.base.crtc;
 	enum pipe pipe = to_intel_crtc(crtc)->pipe;
 
@@ -252,7 +235,7 @@ static void vlv_psr_activate(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc = dig_port->base.base.crtc;
 	enum pipe pipe = to_intel_crtc(crtc)->pipe;
 
@@ -269,17 +252,17 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	uint32_t max_sleep_time = 0x1f;
-	/*
-	 * Let's respect VBT in case VBT asks a higher idle_frame value.
-	 * Let's use 6 as the minimum to cover all known cases including
-	 * the off-by-one issue that HW has in some cases. Also there are
-	 * cases where sink should be able to train
-	 * with the 5 or 6 idle patterns.
+	/* Lately it was identified that depending on panel idle frame count
+	 * calculated at HW can be off by 1. So let's use what came
+	 * from VBT + 1.
+	 * There are also other cases where panel demands at least 4
+	 * but VBT is not being set. To cover these 2 cases lets use
+	 * at least 5 when VBT isn't set to be on the safest side.
 	 */
-	uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
+	uint32_t idle_frames = dev_priv->vbt.psr.idle_frames + 1;
 	uint32_t val = EDP_PSR_ENABLE;
 
 	val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT;
@@ -341,9 +324,12 @@ static bool intel_psr_match_conditions(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc = dig_port->base.base.crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	const struct drm_display_mode *adjusted_mode =
+		&intel_crtc->config->base.adjusted_mode;
+	int psr_setup_time;
 
 	lockdep_assert_held(&dev_priv->psr.lock);
 	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
@@ -382,11 +368,25 @@ static bool intel_psr_match_conditions(struct intel_dp *intel_dp)
 	}
 
 	if (IS_HASWELL(dev) &&
-	    intel_crtc->config->base.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) {
+	    adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) {
 		DRM_DEBUG_KMS("PSR condition failed: Interlaced is Enabled\n");
 		return false;
 	}
 
+	psr_setup_time = drm_dp_psr_setup_time(intel_dp->psr_dpcd);
+	if (psr_setup_time < 0) {
+		DRM_DEBUG_KMS("PSR condition failed: Invalid PSR setup time (0x%02x)\n",
+			      intel_dp->psr_dpcd[1]);
+		return false;
+	}
+
+	if (intel_usecs_to_scanlines(adjusted_mode, psr_setup_time) >
+	    adjusted_mode->crtc_vtotal - adjusted_mode->crtc_vdisplay - 1) {
+		DRM_DEBUG_KMS("PSR condition failed: PSR setup time (%d us) too long\n",
+			      psr_setup_time);
+		return false;
+	}
+
 	dev_priv->psr.source_ok = true;
 	return true;
 }
@@ -395,7 +395,7 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
 	WARN_ON(dev_priv->psr.active);
@@ -424,7 +424,7 @@ void intel_psr_enable(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(intel_dig_port->base.base.crtc);
 
 	if (!HAS_PSR(dev)) {
@@ -511,15 +511,18 @@ static void vlv_psr_disable(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(intel_dig_port->base.base.crtc);
 	uint32_t val;
 
 	if (dev_priv->psr.active) {
 		/* Put VLV PSR back to PSR_state 0 that is PSR Disabled. */
-		if (wait_for((I915_READ(VLV_PSRSTAT(intel_crtc->pipe)) &
-			      VLV_EDP_PSR_IN_TRANS) == 0, 1))
+		if (intel_wait_for_register(dev_priv,
+					    VLV_PSRSTAT(intel_crtc->pipe),
+					    VLV_EDP_PSR_IN_TRANS,
+					    0,
+					    1))
 			WARN(1, "PSR transition took longer than expected\n");
 
 		val = I915_READ(VLV_PSRCTL(intel_crtc->pipe));
@@ -538,16 +541,18 @@ static void hsw_psr_disable(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	if (dev_priv->psr.active) {
 		I915_WRITE(EDP_PSR_CTL,
 			   I915_READ(EDP_PSR_CTL) & ~EDP_PSR_ENABLE);
 
 		/* Wait till PSR is idle */
-		if (_wait_for((I915_READ(EDP_PSR_STATUS_CTL) &
-			       EDP_PSR_STATUS_STATE_MASK) == 0,
-			       2 * USEC_PER_SEC, 10 * USEC_PER_MSEC))
+		if (intel_wait_for_register(dev_priv,
+					    EDP_PSR_STATUS_CTL,
+					    EDP_PSR_STATUS_STATE_MASK,
+					    0,
+					    2000))
 			DRM_ERROR("Timed out waiting for PSR Idle State\n");
 
 		dev_priv->psr.active = false;
@@ -566,7 +571,7 @@ void intel_psr_disable(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	mutex_lock(&dev_priv->psr.lock);
 	if (!dev_priv->psr.enabled) {
@@ -603,14 +608,20 @@ static void intel_psr_work(struct work_struct *work)
 	 * and be ready for re-enable.
 	 */
 	if (HAS_DDI(dev_priv)) {
-		if (wait_for((I915_READ(EDP_PSR_STATUS_CTL) &
-			      EDP_PSR_STATUS_STATE_MASK) == 0, 50)) {
+		if (intel_wait_for_register(dev_priv,
+					    EDP_PSR_STATUS_CTL,
+					    EDP_PSR_STATUS_STATE_MASK,
+					    0,
+					    50)) {
 			DRM_ERROR("Timed out waiting for PSR Idle for re-enable\n");
 			return;
 		}
 	} else {
-		if (wait_for((I915_READ(VLV_PSRSTAT(pipe)) &
-			      VLV_EDP_PSR_IN_TRANS) == 0, 1)) {
+		if (intel_wait_for_register(dev_priv,
+					    VLV_PSRSTAT(pipe),
+					    VLV_EDP_PSR_IN_TRANS,
+					    0,
+					    1)) {
 			DRM_ERROR("Timed out waiting for PSR Idle for re-enable\n");
 			return;
 		}
@@ -636,7 +647,7 @@ unlock:
 
 static void intel_psr_exit(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_dp *intel_dp = dev_priv->psr.enabled;
 	struct drm_crtc *crtc = dp_to_dig_port(intel_dp)->base.base.crtc;
 	enum pipe pipe = to_intel_crtc(crtc)->pipe;
@@ -691,7 +702,7 @@ static void intel_psr_exit(struct drm_device *dev)
 void intel_psr_single_frame_update(struct drm_device *dev,
 				   unsigned frontbuffer_bits)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc;
 	enum pipe pipe;
 	u32 val;
@@ -739,7 +750,7 @@ void intel_psr_single_frame_update(struct drm_device *dev,
 void intel_psr_invalidate(struct drm_device *dev,
 			  unsigned frontbuffer_bits)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc;
 	enum pipe pipe;
 
@@ -777,7 +788,7 @@ void intel_psr_invalidate(struct drm_device *dev,
 void intel_psr_flush(struct drm_device *dev,
 		     unsigned frontbuffer_bits, enum fb_op_origin origin)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *crtc;
 	enum pipe pipe;
 
@@ -813,7 +824,7 @@ void intel_psr_flush(struct drm_device *dev,
  */
 void intel_psr_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	dev_priv->psr_mmio_base = IS_HASWELL(dev_priv) ?
 		HSW_EDP_PSR_BASE : BDW_EDP_PSR_BASE;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 68c5af079ef8..cca7792f26d5 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -34,6 +34,11 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
+/* Rough estimate of the typical request size, performing a flush,
+ * set-context and then emitting the batch.
+ */
+#define LEGACY_REQUEST_SIZE 200
+
 int __intel_ring_space(int head, int tail, int size)
 {
 	int space = head - tail;
@@ -53,18 +58,10 @@ void intel_ring_update_space(struct intel_ringbuffer *ringbuf)
 					    ringbuf->tail, ringbuf->size);
 }
 
-bool intel_engine_stopped(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
-	return dev_priv->gpu_error.stop_rings & intel_engine_flag(engine);
-}
-
 static void __intel_ring_advance(struct intel_engine_cs *engine)
 {
 	struct intel_ringbuffer *ringbuf = engine->buffer;
 	ringbuf->tail &= ringbuf->size - 1;
-	if (intel_engine_stopped(engine))
-		return;
 	engine->write_tail(engine, ringbuf->tail);
 }
 
@@ -101,7 +98,6 @@ gen4_render_ring_flush(struct drm_i915_gem_request *req,
 		       u32	flush_domains)
 {
 	struct intel_engine_cs *engine = req->engine;
-	struct drm_device *dev = engine->dev;
 	u32 cmd;
 	int ret;
 
@@ -140,7 +136,7 @@ gen4_render_ring_flush(struct drm_i915_gem_request *req,
 		cmd |= MI_EXE_FLUSH;
 
 	if (invalidate_domains & I915_GEM_DOMAIN_COMMAND &&
-	    (IS_G4X(dev) || IS_GEN5(dev)))
+	    (IS_G4X(req->i915) || IS_GEN5(req->i915)))
 		cmd |= MI_INVALIDATE_ISP;
 
 	ret = intel_ring_begin(req, 2);
@@ -426,19 +422,19 @@ gen8_render_ring_flush(struct drm_i915_gem_request *req,
 static void ring_write_tail(struct intel_engine_cs *engine,
 			    u32 value)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	I915_WRITE_TAIL(engine, value);
 }
 
 u64 intel_ring_get_active_head(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	u64 acthd;
 
-	if (INTEL_INFO(engine->dev)->gen >= 8)
+	if (INTEL_GEN(dev_priv) >= 8)
 		acthd = I915_READ64_2x32(RING_ACTHD(engine->mmio_base),
 					 RING_ACTHD_UDW(engine->mmio_base));
-	else if (INTEL_INFO(engine->dev)->gen >= 4)
+	else if (INTEL_GEN(dev_priv) >= 4)
 		acthd = I915_READ(RING_ACTHD(engine->mmio_base));
 	else
 		acthd = I915_READ(ACTHD);
@@ -448,25 +444,24 @@ u64 intel_ring_get_active_head(struct intel_engine_cs *engine)
 
 static void ring_setup_phys_status_page(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	u32 addr;
 
 	addr = dev_priv->status_page_dmah->busaddr;
-	if (INTEL_INFO(engine->dev)->gen >= 4)
+	if (INTEL_GEN(dev_priv) >= 4)
 		addr |= (dev_priv->status_page_dmah->busaddr >> 28) & 0xf0;
 	I915_WRITE(HWS_PGA, addr);
 }
 
 static void intel_ring_setup_status_page(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	i915_reg_t mmio;
 
 	/* The ring status page addresses are no longer next to the rest of
 	 * the ring registers as of gen7.
 	 */
-	if (IS_GEN7(dev)) {
+	if (IS_GEN7(dev_priv)) {
 		switch (engine->id) {
 		case RCS:
 			mmio = RENDER_HWS_PGA_GEN7;
@@ -486,7 +481,7 @@ static void intel_ring_setup_status_page(struct intel_engine_cs *engine)
 			mmio = VEBOX_HWS_PGA_GEN7;
 			break;
 		}
-	} else if (IS_GEN6(engine->dev)) {
+	} else if (IS_GEN6(dev_priv)) {
 		mmio = RING_HWS_PGA_GEN6(engine->mmio_base);
 	} else {
 		/* XXX: gen8 returns to sanity */
@@ -503,7 +498,7 @@ static void intel_ring_setup_status_page(struct intel_engine_cs *engine)
 	 * arises: do we still need this and if so how should we go about
 	 * invalidating the TLB?
 	 */
-	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8) {
+	if (IS_GEN(dev_priv, 6, 7)) {
 		i915_reg_t reg = RING_INSTPM(engine->mmio_base);
 
 		/* ring should be idle before issuing a sync flush*/
@@ -512,8 +507,9 @@ static void intel_ring_setup_status_page(struct intel_engine_cs *engine)
 		I915_WRITE(reg,
 			   _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE |
 					      INSTPM_SYNC_FLUSH));
-		if (wait_for((I915_READ(reg) & INSTPM_SYNC_FLUSH) == 0,
-			     1000))
+		if (intel_wait_for_register(dev_priv,
+					    reg, INSTPM_SYNC_FLUSH, 0,
+					    1000))
 			DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n",
 				  engine->name);
 	}
@@ -521,11 +517,15 @@ static void intel_ring_setup_status_page(struct intel_engine_cs *engine)
 
 static bool stop_ring(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = to_i915(engine->dev);
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	if (!IS_GEN2(engine->dev)) {
+	if (!IS_GEN2(dev_priv)) {
 		I915_WRITE_MODE(engine, _MASKED_BIT_ENABLE(STOP_RING));
-		if (wait_for((I915_READ_MODE(engine) & MODE_IDLE) != 0, 1000)) {
+		if (intel_wait_for_register(dev_priv,
+					    RING_MI_MODE(engine->mmio_base),
+					    MODE_IDLE,
+					    MODE_IDLE,
+					    1000)) {
 			DRM_ERROR("%s : timed out trying to stop ring\n",
 				  engine->name);
 			/* Sometimes we observe that the idle flag is not
@@ -541,7 +541,7 @@ static bool stop_ring(struct intel_engine_cs *engine)
 	I915_WRITE_HEAD(engine, 0);
 	engine->write_tail(engine, 0);
 
-	if (!IS_GEN2(engine->dev)) {
+	if (!IS_GEN2(dev_priv)) {
 		(void)I915_READ_CTL(engine);
 		I915_WRITE_MODE(engine, _MASKED_BIT_DISABLE(STOP_RING));
 	}
@@ -556,8 +556,7 @@ void intel_engine_init_hangcheck(struct intel_engine_cs *engine)
 
 static int init_ring_common(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	struct intel_ringbuffer *ringbuf = engine->buffer;
 	struct drm_i915_gem_object *obj = ringbuf->obj;
 	int ret = 0;
@@ -587,7 +586,7 @@ static int init_ring_common(struct intel_engine_cs *engine)
 		}
 	}
 
-	if (I915_NEED_GFX_HWS(dev))
+	if (I915_NEED_GFX_HWS(dev_priv))
 		intel_ring_setup_status_page(engine);
 	else
 		ring_setup_phys_status_page(engine);
@@ -641,59 +640,42 @@ out:
 	return ret;
 }
 
-void
-intel_fini_pipe_control(struct intel_engine_cs *engine)
+void intel_fini_pipe_control(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-
 	if (engine->scratch.obj == NULL)
 		return;
 
-	if (INTEL_INFO(dev)->gen >= 5) {
-		kunmap(sg_page(engine->scratch.obj->pages->sgl));
-		i915_gem_object_ggtt_unpin(engine->scratch.obj);
-	}
-
+	i915_gem_object_ggtt_unpin(engine->scratch.obj);
 	drm_gem_object_unreference(&engine->scratch.obj->base);
 	engine->scratch.obj = NULL;
 }
 
-int
-intel_init_pipe_control(struct intel_engine_cs *engine)
+int intel_init_pipe_control(struct intel_engine_cs *engine, int size)
 {
+	struct drm_i915_gem_object *obj;
 	int ret;
 
 	WARN_ON(engine->scratch.obj);
 
-	engine->scratch.obj = i915_gem_alloc_object(engine->dev, 4096);
-	if (engine->scratch.obj == NULL) {
-		DRM_ERROR("Failed to allocate seqno page\n");
-		ret = -ENOMEM;
+	obj = i915_gem_object_create_stolen(&engine->i915->drm, size);
+	if (!obj)
+		obj = i915_gem_object_create(&engine->i915->drm, size);
+	if (IS_ERR(obj)) {
+		DRM_ERROR("Failed to allocate scratch page\n");
+		ret = PTR_ERR(obj);
 		goto err;
 	}
 
-	ret = i915_gem_object_set_cache_level(engine->scratch.obj,
-					      I915_CACHE_LLC);
-	if (ret)
-		goto err_unref;
-
-	ret = i915_gem_obj_ggtt_pin(engine->scratch.obj, 4096, 0);
+	ret = i915_gem_obj_ggtt_pin(obj, 4096, PIN_HIGH);
 	if (ret)
 		goto err_unref;
 
-	engine->scratch.gtt_offset = i915_gem_obj_ggtt_offset(engine->scratch.obj);
-	engine->scratch.cpu_page = kmap(sg_page(engine->scratch.obj->pages->sgl));
-	if (engine->scratch.cpu_page == NULL) {
-		ret = -ENOMEM;
-		goto err_unpin;
-	}
-
+	engine->scratch.obj = obj;
+	engine->scratch.gtt_offset = i915_gem_obj_ggtt_offset(obj);
 	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n",
 			 engine->name, engine->scratch.gtt_offset);
 	return 0;
 
-err_unpin:
-	i915_gem_object_ggtt_unpin(engine->scratch.obj);
 err_unref:
 	drm_gem_object_unreference(&engine->scratch.obj->base);
 err:
@@ -702,11 +684,9 @@ err:
 
 static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
 {
-	int ret, i;
 	struct intel_engine_cs *engine = req->engine;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_workarounds *w = &dev_priv->workarounds;
+	struct i915_workarounds *w = &req->i915->workarounds;
+	int ret, i;
 
 	if (w->count == 0)
 		return 0;
@@ -795,7 +775,7 @@ static int wa_add(struct drm_i915_private *dev_priv,
 static int wa_ring_whitelist_reg(struct intel_engine_cs *engine,
 				 i915_reg_t reg)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	struct i915_workarounds *wa = &dev_priv->workarounds;
 	const uint32_t index = wa->hw_whitelist_count[engine->id];
 
@@ -811,8 +791,7 @@ static int wa_ring_whitelist_reg(struct intel_engine_cs *engine,
 
 static int gen8_init_workarounds(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 
 	WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
 
@@ -863,9 +842,8 @@ static int gen8_init_workarounds(struct intel_engine_cs *engine)
 
 static int bdw_init_workarounds(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	ret = gen8_init_workarounds(engine);
 	if (ret)
@@ -885,16 +863,15 @@ static int bdw_init_workarounds(struct intel_engine_cs *engine)
 			  /* WaForceContextSaveRestoreNonCoherent:bdw */
 			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
 			  /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */
-			  (IS_BDW_GT3(dev) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
+			  (IS_BDW_GT3(dev_priv) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
 
 	return 0;
 }
 
 static int chv_init_workarounds(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	ret = gen8_init_workarounds(engine);
 	if (ret)
@@ -911,8 +888,7 @@ static int chv_init_workarounds(struct intel_engine_cs *engine)
 
 static int gen9_init_workarounds(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret;
 
 	/* WaConextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl */
@@ -937,14 +913,14 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine)
 			  GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
 
 	/* WaDisableDgMirrorFixInHalfSliceChicken5:skl,bxt */
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_B0) ||
-	    IS_BXT_REVID(dev, 0, BXT_REVID_A1))
+	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_B0) ||
+	    IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1))
 		WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
 				  GEN9_DG_MIRROR_FIX_ENABLE);
 
 	/* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl,bxt */
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_B0) ||
-	    IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_B0) ||
+	    IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) {
 		WA_SET_BIT_MASKED(GEN7_COMMON_SLICE_CHICKEN1,
 				  GEN9_RHWO_OPTIMIZATION_DISABLE);
 		/*
@@ -970,8 +946,8 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine)
 			  GEN9_CCS_TLB_PREFETCH_ENABLE);
 
 	/* WaDisableMaskBasedCammingInRCC:skl,bxt */
-	if (IS_SKL_REVID(dev, SKL_REVID_C0, SKL_REVID_C0) ||
-	    IS_BXT_REVID(dev, 0, BXT_REVID_A1))
+	if (IS_SKL_REVID(dev_priv, SKL_REVID_C0, SKL_REVID_C0) ||
+	    IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1))
 		WA_SET_BIT_MASKED(SLICE_ECO_CHICKEN0,
 				  PIXEL_MASK_CAMMING_DISABLE);
 
@@ -1035,8 +1011,7 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine)
 
 static int skl_tune_iz_hashing(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	u8 vals[3] = { 0, 0, 0 };
 	unsigned int i;
 
@@ -1077,9 +1052,8 @@ static int skl_tune_iz_hashing(struct intel_engine_cs *engine)
 
 static int skl_init_workarounds(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	ret = gen9_init_workarounds(engine);
 	if (ret)
@@ -1090,12 +1064,12 @@ static int skl_init_workarounds(struct intel_engine_cs *engine)
 	 * until D0 which is the default case so this is equivalent to
 	 * !WaDisablePerCtxtPreemptionGranularityControl:skl
 	 */
-	if (IS_SKL_REVID(dev, SKL_REVID_E0, REVID_FOREVER)) {
+	if (IS_SKL_REVID(dev_priv, SKL_REVID_E0, REVID_FOREVER)) {
 		I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
 			   _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
 	}
 
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_D0)) {
+	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0)) {
 		/* WaDisableChickenBitTSGBarrierAckForFFSliceCS:skl */
 		I915_WRITE(FF_SLICE_CS_CHICKEN2,
 			   _MASKED_BIT_ENABLE(GEN9_TSG_BARRIER_ACK_DISABLE));
@@ -1104,30 +1078,30 @@ static int skl_init_workarounds(struct intel_engine_cs *engine)
 	/* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes
 	 * involving this register should also be added to WA batch as required.
 	 */
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_E0))
+	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0))
 		/* WaDisableLSQCROPERFforOCL:skl */
 		I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
 			   GEN8_LQSC_RO_PERF_DIS);
 
 	/* WaEnableGapsTsvCreditFix:skl */
-	if (IS_SKL_REVID(dev, SKL_REVID_C0, REVID_FOREVER)) {
+	if (IS_SKL_REVID(dev_priv, SKL_REVID_C0, REVID_FOREVER)) {
 		I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
 					   GEN9_GAPS_TSV_CREDIT_DISABLE));
 	}
 
 	/* WaDisablePowerCompilerClockGating:skl */
-	if (IS_SKL_REVID(dev, SKL_REVID_B0, SKL_REVID_B0))
+	if (IS_SKL_REVID(dev_priv, SKL_REVID_B0, SKL_REVID_B0))
 		WA_SET_BIT_MASKED(HIZ_CHICKEN,
 				  BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
 
 	/* WaBarrierPerformanceFixDisable:skl */
-	if (IS_SKL_REVID(dev, SKL_REVID_C0, SKL_REVID_D0))
+	if (IS_SKL_REVID(dev_priv, SKL_REVID_C0, SKL_REVID_D0))
 		WA_SET_BIT_MASKED(HDC_CHICKEN0,
 				  HDC_FENCE_DEST_SLM_DISABLE |
 				  HDC_BARRIER_PERFORMANCE_DISABLE);
 
 	/* WaDisableSbeCacheDispatchPortSharing:skl */
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_F0))
+	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_F0))
 		WA_SET_BIT_MASKED(
 			GEN7_HALF_SLICE_CHICKEN1,
 			GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
@@ -1135,6 +1109,11 @@ static int skl_init_workarounds(struct intel_engine_cs *engine)
 	/* WaDisableGafsUnitClkGating:skl */
 	WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
 
+	/* WaInPlaceDecompressionHang:skl */
+	if (IS_SKL_REVID(dev_priv, SKL_REVID_H0, REVID_FOREVER))
+		WA_SET_BIT(GEN9_GAMT_ECO_REG_RW_IA,
+			   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+
 	/* WaDisableLSQCROPERFforOCL:skl */
 	ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4);
 	if (ret)
@@ -1145,9 +1124,8 @@ static int skl_init_workarounds(struct intel_engine_cs *engine)
 
 static int bxt_init_workarounds(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	ret = gen9_init_workarounds(engine);
 	if (ret)
@@ -1155,11 +1133,11 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine)
 
 	/* WaStoreMultiplePTEenable:bxt */
 	/* This is a requirement according to Hardware specification */
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1))
+	if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1))
 		I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_TLBPF);
 
 	/* WaSetClckGatingDisableMedia:bxt */
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+	if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) {
 		I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) &
 					    ~GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE));
 	}
@@ -1168,8 +1146,14 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine)
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
 			  STALL_DOP_GATING_DISABLE);
 
+	/* WaDisablePooledEuLoadBalancingFix:bxt */
+	if (IS_BXT_REVID(dev_priv, BXT_REVID_B0, REVID_FOREVER)) {
+		WA_SET_BIT_MASKED(FF_SLICE_CS_CHICKEN2,
+				  GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE);
+	}
+
 	/* WaDisableSbeCacheDispatchPortSharing:bxt */
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_B0)) {
+	if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) {
 		WA_SET_BIT_MASKED(
 			GEN7_HALF_SLICE_CHICKEN1,
 			GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
@@ -1179,7 +1163,7 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine)
 	/* WaDisableObjectLevelPreemptionForInstancedDraw:bxt */
 	/* WaDisableObjectLevelPreemtionForInstanceId:bxt */
 	/* WaDisableLSQCROPERFforOCL:bxt */
-	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+	if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) {
 		ret = wa_ring_whitelist_reg(engine, GEN9_CS_DEBUG_MODE1);
 		if (ret)
 			return ret;
@@ -1189,17 +1173,27 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine)
 			return ret;
 	}
 
+	/* WaProgramL3SqcReg1DefaultForPerf:bxt */
+	if (IS_BXT_REVID(dev_priv, BXT_REVID_B0, REVID_FOREVER))
+		I915_WRITE(GEN8_L3SQCREG1, L3_GENERAL_PRIO_CREDITS(62) |
+					   L3_HIGH_PRIO_CREDITS(2));
+
 	/* WaInsertDummyPushConstPs:bxt */
 	if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0))
 		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
 				  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
 
+	/* WaInPlaceDecompressionHang:bxt */
+	if (IS_BXT_REVID(dev_priv, BXT_REVID_C0, REVID_FOREVER))
+		WA_SET_BIT(GEN9_GAMT_ECO_REG_RW_IA,
+			   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+
 	return 0;
 }
 
 static int kbl_init_workarounds(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret;
 
 	ret = gen9_init_workarounds(engine);
@@ -1241,6 +1235,10 @@ static int kbl_init_workarounds(struct intel_engine_cs *engine)
 		GEN7_HALF_SLICE_CHICKEN1,
 		GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
 
+	/* WaInPlaceDecompressionHang:kbl */
+	WA_SET_BIT(GEN9_GAMT_ECO_REG_RW_IA,
+		   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+
 	/* WaDisableLSQCROPERFforOCL:kbl */
 	ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4);
 	if (ret)
@@ -1251,24 +1249,23 @@ static int kbl_init_workarounds(struct intel_engine_cs *engine)
 
 int init_workarounds_ring(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 
 	WARN_ON(engine->id != RCS);
 
 	dev_priv->workarounds.count = 0;
 	dev_priv->workarounds.hw_whitelist_count[RCS] = 0;
 
-	if (IS_BROADWELL(dev))
+	if (IS_BROADWELL(dev_priv))
 		return bdw_init_workarounds(engine);
 
-	if (IS_CHERRYVIEW(dev))
+	if (IS_CHERRYVIEW(dev_priv))
 		return chv_init_workarounds(engine);
 
-	if (IS_SKYLAKE(dev))
+	if (IS_SKYLAKE(dev_priv))
 		return skl_init_workarounds(engine);
 
-	if (IS_BROXTON(dev))
+	if (IS_BROXTON(dev_priv))
 		return bxt_init_workarounds(engine);
 
 	if (IS_KABYLAKE(dev_priv))
@@ -1279,14 +1276,13 @@ int init_workarounds_ring(struct intel_engine_cs *engine)
 
 static int init_render_ring(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret = init_ring_common(engine);
 	if (ret)
 		return ret;
 
 	/* WaTimedSingleVertexDispatch:cl,bw,ctg,elk,ilk,snb */
-	if (INTEL_INFO(dev)->gen >= 4 && INTEL_INFO(dev)->gen < 7)
+	if (IS_GEN(dev_priv, 4, 6))
 		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH));
 
 	/* We need to disable the AsyncFlip performance optimisations in order
@@ -1295,22 +1291,22 @@ static int init_render_ring(struct intel_engine_cs *engine)
 	 *
 	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
 	 */
-	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
+	if (IS_GEN(dev_priv, 6, 7))
 		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
 
 	/* Required for the hardware to program scanline values for waiting */
 	/* WaEnableFlushTlbInvalidationMode:snb */
-	if (INTEL_INFO(dev)->gen == 6)
+	if (IS_GEN6(dev_priv))
 		I915_WRITE(GFX_MODE,
 			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT));
 
 	/* WaBCSVCSTlbInvalidationMode:ivb,vlv,hsw */
-	if (IS_GEN7(dev))
+	if (IS_GEN7(dev_priv))
 		I915_WRITE(GFX_MODE_GEN7,
 			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT) |
 			   _MASKED_BIT_ENABLE(GFX_REPLAY_MODE));
 
-	if (IS_GEN6(dev)) {
+	if (IS_GEN6(dev_priv)) {
 		/* From the Sandybridge PRM, volume 1 part 3, page 24:
 		 * "If this bit is set, STCunit will have LRA as replacement
 		 *  policy. [...] This bit must be reset.  LRA replacement
@@ -1320,19 +1316,18 @@ static int init_render_ring(struct intel_engine_cs *engine)
 			   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
 	}
 
-	if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
+	if (IS_GEN(dev_priv, 6, 7))
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
-	if (HAS_L3_DPF(dev))
-		I915_WRITE_IMR(engine, ~GT_PARITY_ERROR(dev));
+	if (INTEL_INFO(dev_priv)->gen >= 6)
+		I915_WRITE_IMR(engine, ~engine->irq_keep_mask);
 
 	return init_workarounds_ring(engine);
 }
 
 static void render_ring_cleanup(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 
 	if (dev_priv->semaphore_obj) {
 		i915_gem_object_ggtt_unpin(dev_priv->semaphore_obj);
@@ -1348,13 +1343,12 @@ static int gen8_rcs_signal(struct drm_i915_gem_request *signaller_req,
 {
 #define MBOX_UPDATE_DWORDS 8
 	struct intel_engine_cs *signaller = signaller_req->engine;
-	struct drm_device *dev = signaller->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = signaller_req->i915;
 	struct intel_engine_cs *waiter;
 	enum intel_engine_id id;
 	int ret, num_rings;
 
-	num_rings = hweight32(INTEL_INFO(dev)->ring_mask);
+	num_rings = hweight32(INTEL_INFO(dev_priv)->ring_mask);
 	num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS;
 #undef MBOX_UPDATE_DWORDS
 
@@ -1363,19 +1357,17 @@ static int gen8_rcs_signal(struct drm_i915_gem_request *signaller_req,
 		return ret;
 
 	for_each_engine_id(waiter, dev_priv, id) {
-		u32 seqno;
 		u64 gtt_offset = signaller->semaphore.signal_ggtt[id];
 		if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
 			continue;
 
-		seqno = i915_gem_request_get_seqno(signaller_req);
 		intel_ring_emit(signaller, GFX_OP_PIPE_CONTROL(6));
 		intel_ring_emit(signaller, PIPE_CONTROL_GLOBAL_GTT_IVB |
 					   PIPE_CONTROL_QW_WRITE |
-					   PIPE_CONTROL_FLUSH_ENABLE);
+					   PIPE_CONTROL_CS_STALL);
 		intel_ring_emit(signaller, lower_32_bits(gtt_offset));
 		intel_ring_emit(signaller, upper_32_bits(gtt_offset));
-		intel_ring_emit(signaller, seqno);
+		intel_ring_emit(signaller, signaller_req->seqno);
 		intel_ring_emit(signaller, 0);
 		intel_ring_emit(signaller, MI_SEMAPHORE_SIGNAL |
 					   MI_SEMAPHORE_TARGET(waiter->hw_id));
@@ -1390,13 +1382,12 @@ static int gen8_xcs_signal(struct drm_i915_gem_request *signaller_req,
 {
 #define MBOX_UPDATE_DWORDS 6
 	struct intel_engine_cs *signaller = signaller_req->engine;
-	struct drm_device *dev = signaller->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = signaller_req->i915;
 	struct intel_engine_cs *waiter;
 	enum intel_engine_id id;
 	int ret, num_rings;
 
-	num_rings = hweight32(INTEL_INFO(dev)->ring_mask);
+	num_rings = hweight32(INTEL_INFO(dev_priv)->ring_mask);
 	num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS;
 #undef MBOX_UPDATE_DWORDS
 
@@ -1405,18 +1396,16 @@ static int gen8_xcs_signal(struct drm_i915_gem_request *signaller_req,
 		return ret;
 
 	for_each_engine_id(waiter, dev_priv, id) {
-		u32 seqno;
 		u64 gtt_offset = signaller->semaphore.signal_ggtt[id];
 		if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
 			continue;
 
-		seqno = i915_gem_request_get_seqno(signaller_req);
 		intel_ring_emit(signaller, (MI_FLUSH_DW + 1) |
 					   MI_FLUSH_DW_OP_STOREDW);
 		intel_ring_emit(signaller, lower_32_bits(gtt_offset) |
 					   MI_FLUSH_DW_USE_GTT);
 		intel_ring_emit(signaller, upper_32_bits(gtt_offset));
-		intel_ring_emit(signaller, seqno);
+		intel_ring_emit(signaller, signaller_req->seqno);
 		intel_ring_emit(signaller, MI_SEMAPHORE_SIGNAL |
 					   MI_SEMAPHORE_TARGET(waiter->hw_id));
 		intel_ring_emit(signaller, 0);
@@ -1429,14 +1418,13 @@ static int gen6_signal(struct drm_i915_gem_request *signaller_req,
 		       unsigned int num_dwords)
 {
 	struct intel_engine_cs *signaller = signaller_req->engine;
-	struct drm_device *dev = signaller->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = signaller_req->i915;
 	struct intel_engine_cs *useless;
 	enum intel_engine_id id;
 	int ret, num_rings;
 
 #define MBOX_UPDATE_DWORDS 3
-	num_rings = hweight32(INTEL_INFO(dev)->ring_mask);
+	num_rings = hweight32(INTEL_INFO(dev_priv)->ring_mask);
 	num_dwords += round_up((num_rings-1) * MBOX_UPDATE_DWORDS, 2);
 #undef MBOX_UPDATE_DWORDS
 
@@ -1448,11 +1436,9 @@ static int gen6_signal(struct drm_i915_gem_request *signaller_req,
 		i915_reg_t mbox_reg = signaller->semaphore.mbox.signal[id];
 
 		if (i915_mmio_reg_valid(mbox_reg)) {
-			u32 seqno = i915_gem_request_get_seqno(signaller_req);
-
 			intel_ring_emit(signaller, MI_LOAD_REGISTER_IMM(1));
 			intel_ring_emit_reg(signaller, mbox_reg);
-			intel_ring_emit(signaller, seqno);
+			intel_ring_emit(signaller, signaller_req->seqno);
 		}
 	}
 
@@ -1488,17 +1474,45 @@ gen6_add_request(struct drm_i915_gem_request *req)
 	intel_ring_emit(engine, MI_STORE_DWORD_INDEX);
 	intel_ring_emit(engine,
 			I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
+	intel_ring_emit(engine, req->seqno);
+	intel_ring_emit(engine, MI_USER_INTERRUPT);
+	__intel_ring_advance(engine);
+
+	return 0;
+}
+
+static int
+gen8_render_add_request(struct drm_i915_gem_request *req)
+{
+	struct intel_engine_cs *engine = req->engine;
+	int ret;
+
+	if (engine->semaphore.signal)
+		ret = engine->semaphore.signal(req, 8);
+	else
+		ret = intel_ring_begin(req, 8);
+	if (ret)
+		return ret;
+
+	intel_ring_emit(engine, GFX_OP_PIPE_CONTROL(6));
+	intel_ring_emit(engine, (PIPE_CONTROL_GLOBAL_GTT_IVB |
+				 PIPE_CONTROL_CS_STALL |
+				 PIPE_CONTROL_QW_WRITE));
+	intel_ring_emit(engine, intel_hws_seqno_address(req->engine));
+	intel_ring_emit(engine, 0);
 	intel_ring_emit(engine, i915_gem_request_get_seqno(req));
+	/* We're thrashing one dword of HWS. */
+	intel_ring_emit(engine, 0);
 	intel_ring_emit(engine, MI_USER_INTERRUPT);
+	intel_ring_emit(engine, MI_NOOP);
 	__intel_ring_advance(engine);
 
 	return 0;
 }
 
-static inline bool i915_gem_has_seqno_wrapped(struct drm_device *dev,
+static inline bool i915_gem_has_seqno_wrapped(struct drm_i915_private *dev_priv,
 					      u32 seqno)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	return dev_priv->last_seqno < seqno;
 }
 
@@ -1516,7 +1530,9 @@ gen8_ring_sync(struct drm_i915_gem_request *waiter_req,
 	       u32 seqno)
 {
 	struct intel_engine_cs *waiter = waiter_req->engine;
-	struct drm_i915_private *dev_priv = waiter->dev->dev_private;
+	struct drm_i915_private *dev_priv = waiter_req->i915;
+	u64 offset = GEN8_WAIT_OFFSET(waiter, signaller->id);
+	struct i915_hw_ppgtt *ppgtt;
 	int ret;
 
 	ret = intel_ring_begin(waiter_req, 4);
@@ -1525,14 +1541,20 @@ gen8_ring_sync(struct drm_i915_gem_request *waiter_req,
 
 	intel_ring_emit(waiter, MI_SEMAPHORE_WAIT |
 				MI_SEMAPHORE_GLOBAL_GTT |
-				MI_SEMAPHORE_POLL |
 				MI_SEMAPHORE_SAD_GTE_SDD);
 	intel_ring_emit(waiter, seqno);
-	intel_ring_emit(waiter,
-			lower_32_bits(GEN8_WAIT_OFFSET(waiter, signaller->id)));
-	intel_ring_emit(waiter,
-			upper_32_bits(GEN8_WAIT_OFFSET(waiter, signaller->id)));
+	intel_ring_emit(waiter, lower_32_bits(offset));
+	intel_ring_emit(waiter, upper_32_bits(offset));
 	intel_ring_advance(waiter);
+
+	/* When the !RCS engines idle waiting upon a semaphore, they lose their
+	 * pagetables and we must reload them before executing the batch.
+	 * We do this on the i915_switch_context() following the wait and
+	 * before the dispatch.
+	 */
+	ppgtt = waiter_req->ctx->ppgtt;
+	if (ppgtt && waiter_req->engine->id != RCS)
+		ppgtt->pd_dirty_rings |= intel_engine_flag(waiter_req->engine);
 	return 0;
 }
 
@@ -1561,7 +1583,7 @@ gen6_ring_sync(struct drm_i915_gem_request *waiter_req,
 		return ret;
 
 	/* If seqno wrap happened, omit the wait with no-ops */
-	if (likely(!i915_gem_has_seqno_wrapped(waiter->dev, seqno))) {
+	if (likely(!i915_gem_has_seqno_wrapped(waiter_req->i915, seqno))) {
 		intel_ring_emit(waiter, dw1 | wait_mbox);
 		intel_ring_emit(waiter, seqno);
 		intel_ring_emit(waiter, 0);
@@ -1577,72 +1599,28 @@ gen6_ring_sync(struct drm_i915_gem_request *waiter_req,
 	return 0;
 }
 
-#define PIPE_CONTROL_FLUSH(ring__, addr__)					\
-do {									\
-	intel_ring_emit(ring__, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE |		\
-		 PIPE_CONTROL_DEPTH_STALL);				\
-	intel_ring_emit(ring__, (addr__) | PIPE_CONTROL_GLOBAL_GTT);			\
-	intel_ring_emit(ring__, 0);							\
-	intel_ring_emit(ring__, 0);							\
-} while (0)
-
-static int
-pc_render_add_request(struct drm_i915_gem_request *req)
+static void
+gen5_seqno_barrier(struct intel_engine_cs *ring)
 {
-	struct intel_engine_cs *engine = req->engine;
-	u32 scratch_addr = engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
-	int ret;
-
-	/* For Ironlake, MI_USER_INTERRUPT was deprecated and apparently
-	 * incoherent with writes to memory, i.e. completely fubar,
-	 * so we need to use PIPE_NOTIFY instead.
+	/* MI_STORE are internally buffered by the GPU and not flushed
+	 * either by MI_FLUSH or SyncFlush or any other combination of
+	 * MI commands.
 	 *
-	 * However, we also need to workaround the qword write
-	 * incoherence by flushing the 6 PIPE_NOTIFY buffers out to
-	 * memory before requesting an interrupt.
+	 * "Only the submission of the store operation is guaranteed.
+	 * The write result will be complete (coherent) some time later
+	 * (this is practically a finite period but there is no guaranteed
+	 * latency)."
+	 *
+	 * Empirically, we observe that we need a delay of at least 75us to
+	 * be sure that the seqno write is visible by the CPU.
 	 */
-	ret = intel_ring_begin(req, 32);
-	if (ret)
-		return ret;
-
-	intel_ring_emit(engine,
-			GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE |
-			PIPE_CONTROL_WRITE_FLUSH |
-			PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
-	intel_ring_emit(engine,
-			engine->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
-	intel_ring_emit(engine, i915_gem_request_get_seqno(req));
-	intel_ring_emit(engine, 0);
-	PIPE_CONTROL_FLUSH(engine, scratch_addr);
-	scratch_addr += 2 * CACHELINE_BYTES; /* write to separate cachelines */
-	PIPE_CONTROL_FLUSH(engine, scratch_addr);
-	scratch_addr += 2 * CACHELINE_BYTES;
-	PIPE_CONTROL_FLUSH(engine, scratch_addr);
-	scratch_addr += 2 * CACHELINE_BYTES;
-	PIPE_CONTROL_FLUSH(engine, scratch_addr);
-	scratch_addr += 2 * CACHELINE_BYTES;
-	PIPE_CONTROL_FLUSH(engine, scratch_addr);
-	scratch_addr += 2 * CACHELINE_BYTES;
-	PIPE_CONTROL_FLUSH(engine, scratch_addr);
-
-	intel_ring_emit(engine,
-			GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE |
-			PIPE_CONTROL_WRITE_FLUSH |
-			PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
-			PIPE_CONTROL_NOTIFY);
-	intel_ring_emit(engine,
-			engine->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
-	intel_ring_emit(engine, i915_gem_request_get_seqno(req));
-	intel_ring_emit(engine, 0);
-	__intel_ring_advance(engine);
-
-	return 0;
+	usleep_range(125, 250);
 }
 
 static void
 gen6_seqno_barrier(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 
 	/* Workaround to force correct ordering between irq and seqno writes on
 	 * ivb (and maybe also on snb) by reading from a CS register (like
@@ -1664,133 +1642,54 @@ gen6_seqno_barrier(struct intel_engine_cs *engine)
 	spin_unlock_irq(&dev_priv->uncore.lock);
 }
 
-static u32
-ring_get_seqno(struct intel_engine_cs *engine)
-{
-	return intel_read_status_page(engine, I915_GEM_HWS_INDEX);
-}
-
 static void
-ring_set_seqno(struct intel_engine_cs *engine, u32 seqno)
-{
-	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
-}
-
-static u32
-pc_render_get_seqno(struct intel_engine_cs *engine)
+gen5_irq_enable(struct intel_engine_cs *engine)
 {
-	return engine->scratch.cpu_page[0];
+	gen5_enable_gt_irq(engine->i915, engine->irq_enable_mask);
 }
 
 static void
-pc_render_set_seqno(struct intel_engine_cs *engine, u32 seqno)
-{
-	engine->scratch.cpu_page[0] = seqno;
-}
-
-static bool
-gen5_ring_get_irq(struct intel_engine_cs *engine)
+gen5_irq_disable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
-
-	if (WARN_ON(!intel_irqs_enabled(dev_priv)))
-		return false;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (engine->irq_refcount++ == 0)
-		gen5_enable_gt_irq(dev_priv, engine->irq_enable_mask);
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
-
-	return true;
+	gen5_disable_gt_irq(engine->i915, engine->irq_enable_mask);
 }
 
 static void
-gen5_ring_put_irq(struct intel_engine_cs *engine)
+i9xx_irq_enable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--engine->irq_refcount == 0)
-		gen5_disable_gt_irq(dev_priv, engine->irq_enable_mask);
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
-}
-
-static bool
-i9xx_ring_get_irq(struct intel_engine_cs *engine)
-{
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
-
-	if (!intel_irqs_enabled(dev_priv))
-		return false;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (engine->irq_refcount++ == 0) {
-		dev_priv->irq_mask &= ~engine->irq_enable_mask;
-		I915_WRITE(IMR, dev_priv->irq_mask);
-		POSTING_READ(IMR);
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	return true;
+	dev_priv->irq_mask &= ~engine->irq_enable_mask;
+	I915_WRITE(IMR, dev_priv->irq_mask);
+	POSTING_READ_FW(RING_IMR(engine->mmio_base));
 }
 
 static void
-i9xx_ring_put_irq(struct intel_engine_cs *engine)
+i9xx_irq_disable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--engine->irq_refcount == 0) {
-		dev_priv->irq_mask |= engine->irq_enable_mask;
-		I915_WRITE(IMR, dev_priv->irq_mask);
-		POSTING_READ(IMR);
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+	dev_priv->irq_mask |= engine->irq_enable_mask;
+	I915_WRITE(IMR, dev_priv->irq_mask);
 }
 
-static bool
-i8xx_ring_get_irq(struct intel_engine_cs *engine)
+static void
+i8xx_irq_enable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
-
-	if (!intel_irqs_enabled(dev_priv))
-		return false;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (engine->irq_refcount++ == 0) {
-		dev_priv->irq_mask &= ~engine->irq_enable_mask;
-		I915_WRITE16(IMR, dev_priv->irq_mask);
-		POSTING_READ16(IMR);
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	return true;
+	dev_priv->irq_mask &= ~engine->irq_enable_mask;
+	I915_WRITE16(IMR, dev_priv->irq_mask);
+	POSTING_READ16(RING_IMR(engine->mmio_base));
 }
 
 static void
-i8xx_ring_put_irq(struct intel_engine_cs *engine)
+i8xx_irq_disable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--engine->irq_refcount == 0) {
-		dev_priv->irq_mask |= engine->irq_enable_mask;
-		I915_WRITE16(IMR, dev_priv->irq_mask);
-		POSTING_READ16(IMR);
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+	dev_priv->irq_mask |= engine->irq_enable_mask;
+	I915_WRITE16(IMR, dev_priv->irq_mask);
 }
 
 static int
@@ -1824,135 +1723,68 @@ i9xx_add_request(struct drm_i915_gem_request *req)
 	intel_ring_emit(engine, MI_STORE_DWORD_INDEX);
 	intel_ring_emit(engine,
 			I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
-	intel_ring_emit(engine, i915_gem_request_get_seqno(req));
+	intel_ring_emit(engine, req->seqno);
 	intel_ring_emit(engine, MI_USER_INTERRUPT);
 	__intel_ring_advance(engine);
 
 	return 0;
 }
 
-static bool
-gen6_ring_get_irq(struct intel_engine_cs *engine)
+static void
+gen6_irq_enable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
-
-	if (WARN_ON(!intel_irqs_enabled(dev_priv)))
-		return false;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (engine->irq_refcount++ == 0) {
-		if (HAS_L3_DPF(dev) && engine->id == RCS)
-			I915_WRITE_IMR(engine,
-				       ~(engine->irq_enable_mask |
-					 GT_PARITY_ERROR(dev)));
-		else
-			I915_WRITE_IMR(engine, ~engine->irq_enable_mask);
-		gen5_enable_gt_irq(dev_priv, engine->irq_enable_mask);
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	return true;
+	I915_WRITE_IMR(engine,
+		       ~(engine->irq_enable_mask |
+			 engine->irq_keep_mask));
+	gen5_enable_gt_irq(dev_priv, engine->irq_enable_mask);
 }
 
 static void
-gen6_ring_put_irq(struct intel_engine_cs *engine)
+gen6_irq_disable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--engine->irq_refcount == 0) {
-		if (HAS_L3_DPF(dev) && engine->id == RCS)
-			I915_WRITE_IMR(engine, ~GT_PARITY_ERROR(dev));
-		else
-			I915_WRITE_IMR(engine, ~0);
-		gen5_disable_gt_irq(dev_priv, engine->irq_enable_mask);
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+	I915_WRITE_IMR(engine, ~engine->irq_keep_mask);
+	gen5_disable_gt_irq(dev_priv, engine->irq_enable_mask);
 }
 
-static bool
-hsw_vebox_get_irq(struct intel_engine_cs *engine)
+static void
+hsw_vebox_irq_enable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
-
-	if (WARN_ON(!intel_irqs_enabled(dev_priv)))
-		return false;
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (engine->irq_refcount++ == 0) {
-		I915_WRITE_IMR(engine, ~engine->irq_enable_mask);
-		gen6_enable_pm_irq(dev_priv, engine->irq_enable_mask);
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
-
-	return true;
+	I915_WRITE_IMR(engine, ~engine->irq_enable_mask);
+	gen6_enable_pm_irq(dev_priv, engine->irq_enable_mask);
 }
 
 static void
-hsw_vebox_put_irq(struct intel_engine_cs *engine)
+hsw_vebox_irq_disable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--engine->irq_refcount == 0) {
-		I915_WRITE_IMR(engine, ~0);
-		gen6_disable_pm_irq(dev_priv, engine->irq_enable_mask);
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+	I915_WRITE_IMR(engine, ~0);
+	gen6_disable_pm_irq(dev_priv, engine->irq_enable_mask);
 }
 
-static bool
-gen8_ring_get_irq(struct intel_engine_cs *engine)
+static void
+gen8_irq_enable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
-
-	if (WARN_ON(!intel_irqs_enabled(dev_priv)))
-		return false;
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (engine->irq_refcount++ == 0) {
-		if (HAS_L3_DPF(dev) && engine->id == RCS) {
-			I915_WRITE_IMR(engine,
-				       ~(engine->irq_enable_mask |
-					 GT_RENDER_L3_PARITY_ERROR_INTERRUPT));
-		} else {
-			I915_WRITE_IMR(engine, ~engine->irq_enable_mask);
-		}
-		POSTING_READ(RING_IMR(engine->mmio_base));
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
-
-	return true;
+	I915_WRITE_IMR(engine,
+		       ~(engine->irq_enable_mask |
+			 engine->irq_keep_mask));
+	POSTING_READ_FW(RING_IMR(engine->mmio_base));
 }
 
 static void
-gen8_ring_put_irq(struct intel_engine_cs *engine)
+gen8_irq_disable(struct intel_engine_cs *engine)
 {
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long flags;
+	struct drm_i915_private *dev_priv = engine->i915;
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--engine->irq_refcount == 0) {
-		if (HAS_L3_DPF(dev) && engine->id == RCS) {
-			I915_WRITE_IMR(engine,
-				       ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
-		} else {
-			I915_WRITE_IMR(engine, ~0);
-		}
-		POSTING_READ(RING_IMR(engine->mmio_base));
-	}
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+	I915_WRITE_IMR(engine, ~engine->irq_keep_mask);
 }
 
 static int
@@ -2066,12 +1898,12 @@ i915_dispatch_execbuffer(struct drm_i915_gem_request *req,
 
 static void cleanup_phys_status_page(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = to_i915(engine->dev);
+	struct drm_i915_private *dev_priv = engine->i915;
 
 	if (!dev_priv->status_page_dmah)
 		return;
 
-	drm_pci_free(engine->dev, dev_priv->status_page_dmah);
+	drm_pci_free(&dev_priv->drm, dev_priv->status_page_dmah);
 	engine->status_page.page_addr = NULL;
 }
 
@@ -2097,10 +1929,10 @@ static int init_status_page(struct intel_engine_cs *engine)
 		unsigned flags;
 		int ret;
 
-		obj = i915_gem_alloc_object(engine->dev, 4096);
-		if (obj == NULL) {
+		obj = i915_gem_object_create(&engine->i915->drm, 4096);
+		if (IS_ERR(obj)) {
 			DRM_ERROR("Failed to allocate status page\n");
-			return -ENOMEM;
+			return PTR_ERR(obj);
 		}
 
 		ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
@@ -2108,7 +1940,7 @@ static int init_status_page(struct intel_engine_cs *engine)
 			goto err_unref;
 
 		flags = 0;
-		if (!HAS_LLC(engine->dev))
+		if (!HAS_LLC(engine->i915))
 			/* On g33, we cannot place HWS above 256MiB, so
 			 * restrict its pinning to the low mappable arena.
 			 * Though this restriction is not documented for
@@ -2142,11 +1974,11 @@ err_unref:
 
 static int init_phys_status_page(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 
 	if (!dev_priv->status_page_dmah) {
 		dev_priv->status_page_dmah =
-			drm_pci_alloc(engine->dev, PAGE_SIZE, PAGE_SIZE);
+			drm_pci_alloc(&dev_priv->drm, PAGE_SIZE, PAGE_SIZE);
 		if (!dev_priv->status_page_dmah)
 			return -ENOMEM;
 	}
@@ -2159,20 +1991,22 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
 
 void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
 {
+	GEM_BUG_ON(ringbuf->vma == NULL);
+	GEM_BUG_ON(ringbuf->virtual_start == NULL);
+
 	if (HAS_LLC(ringbuf->obj->base.dev) && !ringbuf->obj->stolen)
 		i915_gem_object_unpin_map(ringbuf->obj);
 	else
-		iounmap(ringbuf->virtual_start);
+		i915_vma_unpin_iomap(ringbuf->vma);
 	ringbuf->virtual_start = NULL;
-	ringbuf->vma = NULL;
+
 	i915_gem_object_ggtt_unpin(ringbuf->obj);
+	ringbuf->vma = NULL;
 }
 
-int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
+int intel_pin_and_map_ringbuffer_obj(struct drm_i915_private *dev_priv,
 				     struct intel_ringbuffer *ringbuf)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	struct drm_i915_gem_object *obj = ringbuf->obj;
 	/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
 	unsigned flags = PIN_OFFSET_BIAS | 4096;
@@ -2206,10 +2040,9 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 		/* Access through the GTT requires the device to be awake. */
 		assert_rpm_wakelock_held(dev_priv);
 
-		addr = ioremap_wc(ggtt->mappable_base +
-				  i915_gem_obj_ggtt_offset(obj), ringbuf->size);
-		if (addr == NULL) {
-			ret = -ENOMEM;
+		addr = i915_vma_pin_iomap(i915_gem_obj_to_ggtt(obj));
+		if (IS_ERR(addr)) {
+			ret = PTR_ERR(addr);
 			goto err_unpin;
 		}
 	}
@@ -2238,9 +2071,9 @@ static int intel_alloc_ringbuffer_obj(struct drm_device *dev,
 	if (!HAS_LLC(dev))
 		obj = i915_gem_object_create_stolen(dev, ringbuf->size);
 	if (obj == NULL)
-		obj = i915_gem_alloc_object(dev, ringbuf->size);
-	if (obj == NULL)
-		return -ENOMEM;
+		obj = i915_gem_object_create(dev, ringbuf->size);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
 	/* mark ring buffers as read-only from GPU side by default */
 	obj->gt_ro = 1;
@@ -2272,13 +2105,13 @@ intel_engine_create_ringbuffer(struct intel_engine_cs *engine, int size)
 	 * of the buffer.
 	 */
 	ring->effective_size = size;
-	if (IS_I830(engine->dev) || IS_845G(engine->dev))
+	if (IS_I830(engine->i915) || IS_845G(engine->i915))
 		ring->effective_size -= 2 * CACHELINE_BYTES;
 
 	ring->last_retired_head = -1;
 	intel_ring_update_space(ring);
 
-	ret = intel_alloc_ringbuffer_obj(engine->dev, ring);
+	ret = intel_alloc_ringbuffer_obj(&engine->i915->drm, ring);
 	if (ret) {
 		DRM_DEBUG_DRIVER("Failed to allocate ringbuffer %s: %d\n",
 				 engine->name, ret);
@@ -2298,15 +2131,67 @@ intel_ringbuffer_free(struct intel_ringbuffer *ring)
 	kfree(ring);
 }
 
+static int intel_ring_context_pin(struct i915_gem_context *ctx,
+				  struct intel_engine_cs *engine)
+{
+	struct intel_context *ce = &ctx->engine[engine->id];
+	int ret;
+
+	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
+
+	if (ce->pin_count++)
+		return 0;
+
+	if (ce->state) {
+		ret = i915_gem_obj_ggtt_pin(ce->state, ctx->ggtt_alignment, 0);
+		if (ret)
+			goto error;
+	}
+
+	/* The kernel context is only used as a placeholder for flushing the
+	 * active context. It is never used for submitting user rendering and
+	 * as such never requires the golden render context, and so we can skip
+	 * emitting it when we switch to the kernel context. This is required
+	 * as during eviction we cannot allocate and pin the renderstate in
+	 * order to initialise the context.
+	 */
+	if (ctx == ctx->i915->kernel_context)
+		ce->initialised = true;
+
+	i915_gem_context_reference(ctx);
+	return 0;
+
+error:
+	ce->pin_count = 0;
+	return ret;
+}
+
+static void intel_ring_context_unpin(struct i915_gem_context *ctx,
+				     struct intel_engine_cs *engine)
+{
+	struct intel_context *ce = &ctx->engine[engine->id];
+
+	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
+
+	if (--ce->pin_count)
+		return;
+
+	if (ce->state)
+		i915_gem_object_ggtt_unpin(ce->state);
+
+	i915_gem_context_unreference(ctx);
+}
+
 static int intel_init_ring_buffer(struct drm_device *dev,
 				  struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_ringbuffer *ringbuf;
 	int ret;
 
 	WARN_ON(engine->buffer);
 
-	engine->dev = dev;
+	engine->i915 = dev_priv;
 	INIT_LIST_HEAD(&engine->active_list);
 	INIT_LIST_HEAD(&engine->request_list);
 	INIT_LIST_HEAD(&engine->execlist_queue);
@@ -2315,7 +2200,20 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 	memset(engine->semaphore.sync_seqno, 0,
 	       sizeof(engine->semaphore.sync_seqno));
 
-	init_waitqueue_head(&engine->irq_queue);
+	ret = intel_engine_init_breadcrumbs(engine);
+	if (ret)
+		goto error;
+
+	/* We may need to do things with the shrinker which
+	 * require us to immediately switch back to the default
+	 * context. This can cause a problem as pinning the
+	 * default context also requires GTT space which may not
+	 * be available. To avoid this we always pin the default
+	 * context.
+	 */
+	ret = intel_ring_context_pin(dev_priv->kernel_context, engine);
+	if (ret)
+		goto error;
 
 	ringbuf = intel_engine_create_ringbuffer(engine, 32 * PAGE_SIZE);
 	if (IS_ERR(ringbuf)) {
@@ -2324,7 +2222,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 	}
 	engine->buffer = ringbuf;
 
-	if (I915_NEED_GFX_HWS(dev)) {
+	if (I915_NEED_GFX_HWS(dev_priv)) {
 		ret = init_status_page(engine);
 		if (ret)
 			goto error;
@@ -2335,7 +2233,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 			goto error;
 	}
 
-	ret = intel_pin_and_map_ringbuffer_obj(dev, ringbuf);
+	ret = intel_pin_and_map_ringbuffer_obj(dev_priv, ringbuf);
 	if (ret) {
 		DRM_ERROR("Failed to pin and map ringbuffer %s: %d\n",
 				engine->name, ret);
@@ -2361,11 +2259,11 @@ void intel_cleanup_engine(struct intel_engine_cs *engine)
 	if (!intel_engine_initialized(engine))
 		return;
 
-	dev_priv = to_i915(engine->dev);
+	dev_priv = engine->i915;
 
 	if (engine->buffer) {
 		intel_stop_engine(engine);
-		WARN_ON(!IS_GEN2(engine->dev) && (I915_READ_MODE(engine) & MODE_IDLE) == 0);
+		WARN_ON(!IS_GEN2(dev_priv) && (I915_READ_MODE(engine) & MODE_IDLE) == 0);
 
 		intel_unpin_ringbuffer_obj(engine->buffer);
 		intel_ringbuffer_free(engine->buffer);
@@ -2375,7 +2273,7 @@ void intel_cleanup_engine(struct intel_engine_cs *engine)
 	if (engine->cleanup)
 		engine->cleanup(engine);
 
-	if (I915_NEED_GFX_HWS(engine->dev)) {
+	if (I915_NEED_GFX_HWS(dev_priv)) {
 		cleanup_status_page(engine);
 	} else {
 		WARN_ON(engine->id != RCS);
@@ -2384,7 +2282,11 @@ void intel_cleanup_engine(struct intel_engine_cs *engine)
 
 	i915_cmd_parser_fini_ring(engine);
 	i915_gem_batch_pool_fini(&engine->batch_pool);
-	engine->dev = NULL;
+	intel_engine_fini_breadcrumbs(engine);
+
+	intel_ring_context_unpin(dev_priv->kernel_context, engine);
+
+	engine->i915 = NULL;
 }
 
 int intel_engine_idle(struct intel_engine_cs *engine)
@@ -2407,46 +2309,22 @@ int intel_engine_idle(struct intel_engine_cs *engine)
 
 int intel_ring_alloc_request_extras(struct drm_i915_gem_request *request)
 {
-	request->ringbuf = request->engine->buffer;
-	return 0;
-}
+	int ret;
 
-int intel_ring_reserve_space(struct drm_i915_gem_request *request)
-{
-	/*
-	 * The first call merely notes the reserve request and is common for
-	 * all back ends. The subsequent localised _begin() call actually
-	 * ensures that the reservation is available. Without the begin, if
-	 * the request creator immediately submitted the request without
-	 * adding any commands to it then there might not actually be
-	 * sufficient room for the submission commands.
+	/* Flush enough space to reduce the likelihood of waiting after
+	 * we start building the request - in which case we will just
+	 * have to repeat work.
 	 */
-	intel_ring_reserved_space_reserve(request->ringbuf, MIN_SPACE_FOR_ADD_REQUEST);
-
-	return intel_ring_begin(request, 0);
-}
+	request->reserved_space += LEGACY_REQUEST_SIZE;
 
-void intel_ring_reserved_space_reserve(struct intel_ringbuffer *ringbuf, int size)
-{
-	GEM_BUG_ON(ringbuf->reserved_size);
-	ringbuf->reserved_size = size;
-}
-
-void intel_ring_reserved_space_cancel(struct intel_ringbuffer *ringbuf)
-{
-	GEM_BUG_ON(!ringbuf->reserved_size);
-	ringbuf->reserved_size   = 0;
-}
+	request->ringbuf = request->engine->buffer;
 
-void intel_ring_reserved_space_use(struct intel_ringbuffer *ringbuf)
-{
-	GEM_BUG_ON(!ringbuf->reserved_size);
-	ringbuf->reserved_size   = 0;
-}
+	ret = intel_ring_begin(request, 0);
+	if (ret)
+		return ret;
 
-void intel_ring_reserved_space_end(struct intel_ringbuffer *ringbuf)
-{
-	GEM_BUG_ON(ringbuf->reserved_size);
+	request->reserved_space -= LEGACY_REQUEST_SIZE;
+	return 0;
 }
 
 static int wait_for_space(struct drm_i915_gem_request *req, int bytes)
@@ -2468,7 +2346,7 @@ static int wait_for_space(struct drm_i915_gem_request *req, int bytes)
 	 *
 	 * See also i915_gem_request_alloc() and i915_add_request().
 	 */
-	GEM_BUG_ON(!ringbuf->reserved_size);
+	GEM_BUG_ON(!req->reserved_space);
 
 	list_for_each_entry(target, &engine->request_list, list) {
 		unsigned space;
@@ -2503,7 +2381,7 @@ int intel_ring_begin(struct drm_i915_gem_request *req, int num_dwords)
 	int total_bytes, wait_bytes;
 	bool need_wrap = false;
 
-	total_bytes = bytes + ringbuf->reserved_size;
+	total_bytes = bytes + req->reserved_space;
 
 	if (unlikely(bytes > remain_usable)) {
 		/*
@@ -2519,7 +2397,7 @@ int intel_ring_begin(struct drm_i915_gem_request *req, int num_dwords)
 		 * and only need to effectively wait for the reserved
 		 * size space from the start of ringbuffer.
 		 */
-		wait_bytes = remain_actual + ringbuf->reserved_size;
+		wait_bytes = remain_actual + req->reserved_space;
 	} else {
 		/* No wrapping required, just waiting. */
 		wait_bytes = total_bytes;
@@ -2576,7 +2454,7 @@ int intel_ring_cacheline_align(struct drm_i915_gem_request *req)
 
 void intel_ring_init_seqno(struct intel_engine_cs *engine, u32 seqno)
 {
-	struct drm_i915_private *dev_priv = to_i915(engine->dev);
+	struct drm_i915_private *dev_priv = engine->i915;
 
 	/* Our semaphore implementation is strictly monotonic (i.e. we proceed
 	 * so long as the semaphore value in the register/page is greater
@@ -2586,7 +2464,7 @@ void intel_ring_init_seqno(struct intel_engine_cs *engine, u32 seqno)
 	 * the semaphore value, then when the seqno moves backwards all
 	 * future waits will complete instantly (causing rendering corruption).
 	 */
-	if (INTEL_INFO(dev_priv)->gen == 6 || INTEL_INFO(dev_priv)->gen == 7) {
+	if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) {
 		I915_WRITE(RING_SYNC_0(engine->mmio_base), 0);
 		I915_WRITE(RING_SYNC_1(engine->mmio_base), 0);
 		if (HAS_VEBOX(dev_priv))
@@ -2603,43 +2481,58 @@ void intel_ring_init_seqno(struct intel_engine_cs *engine, u32 seqno)
 	memset(engine->semaphore.sync_seqno, 0,
 	       sizeof(engine->semaphore.sync_seqno));
 
-	engine->set_seqno(engine, seqno);
+	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
+	if (engine->irq_seqno_barrier)
+		engine->irq_seqno_barrier(engine);
 	engine->last_submitted_seqno = seqno;
 
 	engine->hangcheck.seqno = seqno;
+
+	/* After manually advancing the seqno, fake the interrupt in case
+	 * there are any waiters for that seqno.
+	 */
+	rcu_read_lock();
+	intel_engine_wakeup(engine);
+	rcu_read_unlock();
 }
 
 static void gen6_bsd_ring_write_tail(struct intel_engine_cs *engine,
 				     u32 value)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
+
+	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
        /* Every tail move must follow the sequence below */
 
 	/* Disable notification that the ring is IDLE. The GT
 	 * will then assume that it is busy and bring it out of rc6.
 	 */
-	I915_WRITE(GEN6_BSD_SLEEP_PSMI_CONTROL,
-		   _MASKED_BIT_ENABLE(GEN6_BSD_SLEEP_MSG_DISABLE));
+	I915_WRITE_FW(GEN6_BSD_SLEEP_PSMI_CONTROL,
+		      _MASKED_BIT_ENABLE(GEN6_BSD_SLEEP_MSG_DISABLE));
 
 	/* Clear the context id. Here be magic! */
-	I915_WRITE64(GEN6_BSD_RNCID, 0x0);
+	I915_WRITE64_FW(GEN6_BSD_RNCID, 0x0);
 
 	/* Wait for the ring not to be idle, i.e. for it to wake up. */
-	if (wait_for((I915_READ(GEN6_BSD_SLEEP_PSMI_CONTROL) &
-		      GEN6_BSD_SLEEP_INDICATOR) == 0,
-		     50))
+	if (intel_wait_for_register_fw(dev_priv,
+				       GEN6_BSD_SLEEP_PSMI_CONTROL,
+				       GEN6_BSD_SLEEP_INDICATOR,
+				       0,
+				       50))
 		DRM_ERROR("timed out waiting for the BSD ring to wake up\n");
 
 	/* Now that the ring is fully powered up, update the tail */
-	I915_WRITE_TAIL(engine, value);
-	POSTING_READ(RING_TAIL(engine->mmio_base));
+	I915_WRITE_FW(RING_TAIL(engine->mmio_base), value);
+	POSTING_READ_FW(RING_TAIL(engine->mmio_base));
 
 	/* Let the ring send IDLE messages to the GT again,
 	 * and so let it sleep to conserve power when idle.
 	 */
-	I915_WRITE(GEN6_BSD_SLEEP_PSMI_CONTROL,
-		   _MASKED_BIT_DISABLE(GEN6_BSD_SLEEP_MSG_DISABLE));
+	I915_WRITE_FW(GEN6_BSD_SLEEP_PSMI_CONTROL,
+		      _MASKED_BIT_DISABLE(GEN6_BSD_SLEEP_MSG_DISABLE));
+
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
 
 static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
@@ -2654,7 +2547,7 @@ static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
 		return ret;
 
 	cmd = MI_FLUSH_DW;
-	if (INTEL_INFO(engine->dev)->gen >= 8)
+	if (INTEL_GEN(req->i915) >= 8)
 		cmd += 1;
 
 	/* We always require a command barrier so that subsequent
@@ -2676,7 +2569,7 @@ static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
 	intel_ring_emit(engine, cmd);
 	intel_ring_emit(engine,
 			I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
-	if (INTEL_INFO(engine->dev)->gen >= 8) {
+	if (INTEL_GEN(req->i915) >= 8) {
 		intel_ring_emit(engine, 0); /* upper addr */
 		intel_ring_emit(engine, 0); /* value */
 	} else  {
@@ -2767,7 +2660,6 @@ static int gen6_ring_flush(struct drm_i915_gem_request *req,
 			   u32 invalidate, u32 flush)
 {
 	struct intel_engine_cs *engine = req->engine;
-	struct drm_device *dev = engine->dev;
 	uint32_t cmd;
 	int ret;
 
@@ -2776,7 +2668,7 @@ static int gen6_ring_flush(struct drm_i915_gem_request *req,
 		return ret;
 
 	cmd = MI_FLUSH_DW;
-	if (INTEL_INFO(dev)->gen >= 8)
+	if (INTEL_GEN(req->i915) >= 8)
 		cmd += 1;
 
 	/* We always require a command barrier so that subsequent
@@ -2797,7 +2689,7 @@ static int gen6_ring_flush(struct drm_i915_gem_request *req,
 	intel_ring_emit(engine, cmd);
 	intel_ring_emit(engine,
 			I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
-	if (INTEL_INFO(dev)->gen >= 8) {
+	if (INTEL_GEN(req->i915) >= 8) {
 		intel_ring_emit(engine, 0); /* upper addr */
 		intel_ring_emit(engine, 0); /* value */
 	} else  {
@@ -2809,11 +2701,159 @@ static int gen6_ring_flush(struct drm_i915_gem_request *req,
 	return 0;
 }
 
+static void intel_ring_init_semaphores(struct drm_i915_private *dev_priv,
+				       struct intel_engine_cs *engine)
+{
+	struct drm_i915_gem_object *obj;
+	int ret, i;
+
+	if (!i915_semaphore_is_enabled(dev_priv))
+		return;
+
+	if (INTEL_GEN(dev_priv) >= 8 && !dev_priv->semaphore_obj) {
+		obj = i915_gem_object_create(&dev_priv->drm, 4096);
+		if (IS_ERR(obj)) {
+			DRM_ERROR("Failed to allocate semaphore bo. Disabling semaphores\n");
+			i915.semaphores = 0;
+		} else {
+			i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
+			ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_NONBLOCK);
+			if (ret != 0) {
+				drm_gem_object_unreference(&obj->base);
+				DRM_ERROR("Failed to pin semaphore bo. Disabling semaphores\n");
+				i915.semaphores = 0;
+			} else {
+				dev_priv->semaphore_obj = obj;
+			}
+		}
+	}
+
+	if (!i915_semaphore_is_enabled(dev_priv))
+		return;
+
+	if (INTEL_GEN(dev_priv) >= 8) {
+		u64 offset = i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj);
+
+		engine->semaphore.sync_to = gen8_ring_sync;
+		engine->semaphore.signal = gen8_xcs_signal;
+
+		for (i = 0; i < I915_NUM_ENGINES; i++) {
+			u64 ring_offset;
+
+			if (i != engine->id)
+				ring_offset = offset + GEN8_SEMAPHORE_OFFSET(engine->id, i);
+			else
+				ring_offset = MI_SEMAPHORE_SYNC_INVALID;
+
+			engine->semaphore.signal_ggtt[i] = ring_offset;
+		}
+	} else if (INTEL_GEN(dev_priv) >= 6) {
+		engine->semaphore.sync_to = gen6_ring_sync;
+		engine->semaphore.signal = gen6_signal;
+
+		/*
+		 * The current semaphore is only applied on pre-gen8
+		 * platform.  And there is no VCS2 ring on the pre-gen8
+		 * platform. So the semaphore between RCS and VCS2 is
+		 * initialized as INVALID.  Gen8 will initialize the
+		 * sema between VCS2 and RCS later.
+		 */
+		for (i = 0; i < I915_NUM_ENGINES; i++) {
+			static const struct {
+				u32 wait_mbox;
+				i915_reg_t mbox_reg;
+			} sem_data[I915_NUM_ENGINES][I915_NUM_ENGINES] = {
+				[RCS] = {
+					[VCS] =  { .wait_mbox = MI_SEMAPHORE_SYNC_RV,  .mbox_reg = GEN6_VRSYNC },
+					[BCS] =  { .wait_mbox = MI_SEMAPHORE_SYNC_RB,  .mbox_reg = GEN6_BRSYNC },
+					[VECS] = { .wait_mbox = MI_SEMAPHORE_SYNC_RVE, .mbox_reg = GEN6_VERSYNC },
+				},
+				[VCS] = {
+					[RCS] =  { .wait_mbox = MI_SEMAPHORE_SYNC_VR,  .mbox_reg = GEN6_RVSYNC },
+					[BCS] =  { .wait_mbox = MI_SEMAPHORE_SYNC_VB,  .mbox_reg = GEN6_BVSYNC },
+					[VECS] = { .wait_mbox = MI_SEMAPHORE_SYNC_VVE, .mbox_reg = GEN6_VEVSYNC },
+				},
+				[BCS] = {
+					[RCS] =  { .wait_mbox = MI_SEMAPHORE_SYNC_BR,  .mbox_reg = GEN6_RBSYNC },
+					[VCS] =  { .wait_mbox = MI_SEMAPHORE_SYNC_BV,  .mbox_reg = GEN6_VBSYNC },
+					[VECS] = { .wait_mbox = MI_SEMAPHORE_SYNC_BVE, .mbox_reg = GEN6_VEBSYNC },
+				},
+				[VECS] = {
+					[RCS] =  { .wait_mbox = MI_SEMAPHORE_SYNC_VER, .mbox_reg = GEN6_RVESYNC },
+					[VCS] =  { .wait_mbox = MI_SEMAPHORE_SYNC_VEV, .mbox_reg = GEN6_VVESYNC },
+					[BCS] =  { .wait_mbox = MI_SEMAPHORE_SYNC_VEB, .mbox_reg = GEN6_BVESYNC },
+				},
+			};
+			u32 wait_mbox;
+			i915_reg_t mbox_reg;
+
+			if (i == engine->id || i == VCS2) {
+				wait_mbox = MI_SEMAPHORE_SYNC_INVALID;
+				mbox_reg = GEN6_NOSYNC;
+			} else {
+				wait_mbox = sem_data[engine->id][i].wait_mbox;
+				mbox_reg = sem_data[engine->id][i].mbox_reg;
+			}
+
+			engine->semaphore.mbox.wait[i] = wait_mbox;
+			engine->semaphore.mbox.signal[i] = mbox_reg;
+		}
+	}
+}
+
+static void intel_ring_init_irq(struct drm_i915_private *dev_priv,
+				struct intel_engine_cs *engine)
+{
+	if (INTEL_GEN(dev_priv) >= 8) {
+		engine->irq_enable = gen8_irq_enable;
+		engine->irq_disable = gen8_irq_disable;
+		engine->irq_seqno_barrier = gen6_seqno_barrier;
+	} else if (INTEL_GEN(dev_priv) >= 6) {
+		engine->irq_enable = gen6_irq_enable;
+		engine->irq_disable = gen6_irq_disable;
+		engine->irq_seqno_barrier = gen6_seqno_barrier;
+	} else if (INTEL_GEN(dev_priv) >= 5) {
+		engine->irq_enable = gen5_irq_enable;
+		engine->irq_disable = gen5_irq_disable;
+		engine->irq_seqno_barrier = gen5_seqno_barrier;
+	} else if (INTEL_GEN(dev_priv) >= 3) {
+		engine->irq_enable = i9xx_irq_enable;
+		engine->irq_disable = i9xx_irq_disable;
+	} else {
+		engine->irq_enable = i8xx_irq_enable;
+		engine->irq_disable = i8xx_irq_disable;
+	}
+}
+
+static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv,
+				      struct intel_engine_cs *engine)
+{
+	engine->init_hw = init_ring_common;
+	engine->write_tail = ring_write_tail;
+
+	engine->add_request = i9xx_add_request;
+	if (INTEL_GEN(dev_priv) >= 6)
+		engine->add_request = gen6_add_request;
+
+	if (INTEL_GEN(dev_priv) >= 8)
+		engine->dispatch_execbuffer = gen8_ring_dispatch_execbuffer;
+	else if (INTEL_GEN(dev_priv) >= 6)
+		engine->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
+	else if (INTEL_GEN(dev_priv) >= 4)
+		engine->dispatch_execbuffer = i965_dispatch_execbuffer;
+	else if (IS_I830(dev_priv) || IS_845G(dev_priv))
+		engine->dispatch_execbuffer = i830_dispatch_execbuffer;
+	else
+		engine->dispatch_execbuffer = i915_dispatch_execbuffer;
+
+	intel_ring_init_irq(dev_priv, engine);
+	intel_ring_init_semaphores(dev_priv, engine);
+}
+
 int intel_init_render_ring_buffer(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine = &dev_priv->engine[RCS];
-	struct drm_i915_gem_object *obj;
 	int ret;
 
 	engine->name = "render ring";
@@ -2822,140 +2862,49 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 	engine->hw_id = 0;
 	engine->mmio_base = RENDER_RING_BASE;
 
-	if (INTEL_INFO(dev)->gen >= 8) {
-		if (i915_semaphore_is_enabled(dev)) {
-			obj = i915_gem_alloc_object(dev, 4096);
-			if (obj == NULL) {
-				DRM_ERROR("Failed to allocate semaphore bo. Disabling semaphores\n");
-				i915.semaphores = 0;
-			} else {
-				i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
-				ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_NONBLOCK);
-				if (ret != 0) {
-					drm_gem_object_unreference(&obj->base);
-					DRM_ERROR("Failed to pin semaphore bo. Disabling semaphores\n");
-					i915.semaphores = 0;
-				} else
-					dev_priv->semaphore_obj = obj;
-			}
-		}
+	intel_ring_default_vfuncs(dev_priv, engine);
 
+	engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT;
+	if (HAS_L3_DPF(dev_priv))
+		engine->irq_keep_mask = GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
+
+	if (INTEL_GEN(dev_priv) >= 8) {
 		engine->init_context = intel_rcs_ctx_init;
-		engine->add_request = gen6_add_request;
+		engine->add_request = gen8_render_add_request;
 		engine->flush = gen8_render_ring_flush;
-		engine->irq_get = gen8_ring_get_irq;
-		engine->irq_put = gen8_ring_put_irq;
-		engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT;
-		engine->irq_seqno_barrier = gen6_seqno_barrier;
-		engine->get_seqno = ring_get_seqno;
-		engine->set_seqno = ring_set_seqno;
-		if (i915_semaphore_is_enabled(dev)) {
-			WARN_ON(!dev_priv->semaphore_obj);
-			engine->semaphore.sync_to = gen8_ring_sync;
+		if (i915_semaphore_is_enabled(dev_priv))
 			engine->semaphore.signal = gen8_rcs_signal;
-			GEN8_RING_SEMAPHORE_INIT(engine);
-		}
-	} else if (INTEL_INFO(dev)->gen >= 6) {
+	} else if (INTEL_GEN(dev_priv) >= 6) {
 		engine->init_context = intel_rcs_ctx_init;
-		engine->add_request = gen6_add_request;
 		engine->flush = gen7_render_ring_flush;
-		if (INTEL_INFO(dev)->gen == 6)
+		if (IS_GEN6(dev_priv))
 			engine->flush = gen6_render_ring_flush;
-		engine->irq_get = gen6_ring_get_irq;
-		engine->irq_put = gen6_ring_put_irq;
-		engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT;
-		engine->irq_seqno_barrier = gen6_seqno_barrier;
-		engine->get_seqno = ring_get_seqno;
-		engine->set_seqno = ring_set_seqno;
-		if (i915_semaphore_is_enabled(dev)) {
-			engine->semaphore.sync_to = gen6_ring_sync;
-			engine->semaphore.signal = gen6_signal;
-			/*
-			 * The current semaphore is only applied on pre-gen8
-			 * platform.  And there is no VCS2 ring on the pre-gen8
-			 * platform. So the semaphore between RCS and VCS2 is
-			 * initialized as INVALID.  Gen8 will initialize the
-			 * sema between VCS2 and RCS later.
-			 */
-			engine->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_INVALID;
-			engine->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_RV;
-			engine->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_RB;
-			engine->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_RVE;
-			engine->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
-			engine->semaphore.mbox.signal[RCS] = GEN6_NOSYNC;
-			engine->semaphore.mbox.signal[VCS] = GEN6_VRSYNC;
-			engine->semaphore.mbox.signal[BCS] = GEN6_BRSYNC;
-			engine->semaphore.mbox.signal[VECS] = GEN6_VERSYNC;
-			engine->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
-		}
-	} else if (IS_GEN5(dev)) {
-		engine->add_request = pc_render_add_request;
+	} else if (IS_GEN5(dev_priv)) {
 		engine->flush = gen4_render_ring_flush;
-		engine->get_seqno = pc_render_get_seqno;
-		engine->set_seqno = pc_render_set_seqno;
-		engine->irq_get = gen5_ring_get_irq;
-		engine->irq_put = gen5_ring_put_irq;
-		engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT |
-					GT_RENDER_PIPECTL_NOTIFY_INTERRUPT;
 	} else {
-		engine->add_request = i9xx_add_request;
-		if (INTEL_INFO(dev)->gen < 4)
+		if (INTEL_GEN(dev_priv) < 4)
 			engine->flush = gen2_render_ring_flush;
 		else
 			engine->flush = gen4_render_ring_flush;
-		engine->get_seqno = ring_get_seqno;
-		engine->set_seqno = ring_set_seqno;
-		if (IS_GEN2(dev)) {
-			engine->irq_get = i8xx_ring_get_irq;
-			engine->irq_put = i8xx_ring_put_irq;
-		} else {
-			engine->irq_get = i9xx_ring_get_irq;
-			engine->irq_put = i9xx_ring_put_irq;
-		}
 		engine->irq_enable_mask = I915_USER_INTERRUPT;
 	}
-	engine->write_tail = ring_write_tail;
 
-	if (IS_HASWELL(dev))
+	if (IS_HASWELL(dev_priv))
 		engine->dispatch_execbuffer = hsw_ring_dispatch_execbuffer;
-	else if (IS_GEN8(dev))
-		engine->dispatch_execbuffer = gen8_ring_dispatch_execbuffer;
-	else if (INTEL_INFO(dev)->gen >= 6)
-		engine->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
-	else if (INTEL_INFO(dev)->gen >= 4)
-		engine->dispatch_execbuffer = i965_dispatch_execbuffer;
-	else if (IS_I830(dev) || IS_845G(dev))
-		engine->dispatch_execbuffer = i830_dispatch_execbuffer;
-	else
-		engine->dispatch_execbuffer = i915_dispatch_execbuffer;
+
 	engine->init_hw = init_render_ring;
 	engine->cleanup = render_ring_cleanup;
 
-	/* Workaround batchbuffer to combat CS tlb bug. */
-	if (HAS_BROKEN_CS_TLB(dev)) {
-		obj = i915_gem_alloc_object(dev, I830_WA_SIZE);
-		if (obj == NULL) {
-			DRM_ERROR("Failed to allocate batch bo\n");
-			return -ENOMEM;
-		}
-
-		ret = i915_gem_obj_ggtt_pin(obj, 0, 0);
-		if (ret != 0) {
-			drm_gem_object_unreference(&obj->base);
-			DRM_ERROR("Failed to ping batch bo\n");
-			return ret;
-		}
-
-		engine->scratch.obj = obj;
-		engine->scratch.gtt_offset = i915_gem_obj_ggtt_offset(obj);
-	}
-
 	ret = intel_init_ring_buffer(dev, engine);
 	if (ret)
 		return ret;
 
-	if (INTEL_INFO(dev)->gen >= 5) {
-		ret = intel_init_pipe_control(engine);
+	if (INTEL_GEN(dev_priv) >= 6) {
+		ret = intel_init_pipe_control(engine, 4096);
+		if (ret)
+			return ret;
+	} else if (HAS_BROKEN_CS_TLB(dev_priv)) {
+		ret = intel_init_pipe_control(engine, I830_WA_SIZE);
 		if (ret)
 			return ret;
 	}
@@ -2965,7 +2914,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 
 int intel_init_bsd_ring_buffer(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine = &dev_priv->engine[VCS];
 
 	engine->name = "bsd ring";
@@ -2973,68 +2922,27 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 	engine->exec_id = I915_EXEC_BSD;
 	engine->hw_id = 1;
 
-	engine->write_tail = ring_write_tail;
-	if (INTEL_INFO(dev)->gen >= 6) {
+	intel_ring_default_vfuncs(dev_priv, engine);
+
+	if (INTEL_GEN(dev_priv) >= 6) {
 		engine->mmio_base = GEN6_BSD_RING_BASE;
 		/* gen6 bsd needs a special wa for tail updates */
-		if (IS_GEN6(dev))
+		if (IS_GEN6(dev_priv))
 			engine->write_tail = gen6_bsd_ring_write_tail;
 		engine->flush = gen6_bsd_ring_flush;
-		engine->add_request = gen6_add_request;
-		engine->irq_seqno_barrier = gen6_seqno_barrier;
-		engine->get_seqno = ring_get_seqno;
-		engine->set_seqno = ring_set_seqno;
-		if (INTEL_INFO(dev)->gen >= 8) {
+		if (INTEL_GEN(dev_priv) >= 8)
 			engine->irq_enable_mask =
 				GT_RENDER_USER_INTERRUPT << GEN8_VCS1_IRQ_SHIFT;
-			engine->irq_get = gen8_ring_get_irq;
-			engine->irq_put = gen8_ring_put_irq;
-			engine->dispatch_execbuffer =
-				gen8_ring_dispatch_execbuffer;
-			if (i915_semaphore_is_enabled(dev)) {
-				engine->semaphore.sync_to = gen8_ring_sync;
-				engine->semaphore.signal = gen8_xcs_signal;
-				GEN8_RING_SEMAPHORE_INIT(engine);
-			}
-		} else {
+		else
 			engine->irq_enable_mask = GT_BSD_USER_INTERRUPT;
-			engine->irq_get = gen6_ring_get_irq;
-			engine->irq_put = gen6_ring_put_irq;
-			engine->dispatch_execbuffer =
-				gen6_ring_dispatch_execbuffer;
-			if (i915_semaphore_is_enabled(dev)) {
-				engine->semaphore.sync_to = gen6_ring_sync;
-				engine->semaphore.signal = gen6_signal;
-				engine->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_VR;
-				engine->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_INVALID;
-				engine->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_VB;
-				engine->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_VVE;
-				engine->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
-				engine->semaphore.mbox.signal[RCS] = GEN6_RVSYNC;
-				engine->semaphore.mbox.signal[VCS] = GEN6_NOSYNC;
-				engine->semaphore.mbox.signal[BCS] = GEN6_BVSYNC;
-				engine->semaphore.mbox.signal[VECS] = GEN6_VEVSYNC;
-				engine->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
-			}
-		}
 	} else {
 		engine->mmio_base = BSD_RING_BASE;
 		engine->flush = bsd_ring_flush;
-		engine->add_request = i9xx_add_request;
-		engine->get_seqno = ring_get_seqno;
-		engine->set_seqno = ring_set_seqno;
-		if (IS_GEN5(dev)) {
+		if (IS_GEN5(dev_priv))
 			engine->irq_enable_mask = ILK_BSD_USER_INTERRUPT;
-			engine->irq_get = gen5_ring_get_irq;
-			engine->irq_put = gen5_ring_put_irq;
-		} else {
+		else
 			engine->irq_enable_mask = I915_BSD_USER_INTERRUPT;
-			engine->irq_get = i9xx_ring_get_irq;
-			engine->irq_put = i9xx_ring_put_irq;
-		}
-		engine->dispatch_execbuffer = i965_dispatch_execbuffer;
 	}
-	engine->init_hw = init_ring_common;
 
 	return intel_init_ring_buffer(dev, engine);
 }
@@ -3044,147 +2952,70 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
  */
 int intel_init_bsd2_ring_buffer(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine = &dev_priv->engine[VCS2];
 
 	engine->name = "bsd2 ring";
 	engine->id = VCS2;
 	engine->exec_id = I915_EXEC_BSD;
 	engine->hw_id = 4;
-
-	engine->write_tail = ring_write_tail;
 	engine->mmio_base = GEN8_BSD2_RING_BASE;
+
+	intel_ring_default_vfuncs(dev_priv, engine);
+
 	engine->flush = gen6_bsd_ring_flush;
-	engine->add_request = gen6_add_request;
-	engine->irq_seqno_barrier = gen6_seqno_barrier;
-	engine->get_seqno = ring_get_seqno;
-	engine->set_seqno = ring_set_seqno;
 	engine->irq_enable_mask =
 			GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT;
-	engine->irq_get = gen8_ring_get_irq;
-	engine->irq_put = gen8_ring_put_irq;
-	engine->dispatch_execbuffer =
-			gen8_ring_dispatch_execbuffer;
-	if (i915_semaphore_is_enabled(dev)) {
-		engine->semaphore.sync_to = gen8_ring_sync;
-		engine->semaphore.signal = gen8_xcs_signal;
-		GEN8_RING_SEMAPHORE_INIT(engine);
-	}
-	engine->init_hw = init_ring_common;
 
 	return intel_init_ring_buffer(dev, engine);
 }
 
 int intel_init_blt_ring_buffer(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine = &dev_priv->engine[BCS];
 
 	engine->name = "blitter ring";
 	engine->id = BCS;
 	engine->exec_id = I915_EXEC_BLT;
 	engine->hw_id = 2;
-
 	engine->mmio_base = BLT_RING_BASE;
-	engine->write_tail = ring_write_tail;
+
+	intel_ring_default_vfuncs(dev_priv, engine);
+
 	engine->flush = gen6_ring_flush;
-	engine->add_request = gen6_add_request;
-	engine->irq_seqno_barrier = gen6_seqno_barrier;
-	engine->get_seqno = ring_get_seqno;
-	engine->set_seqno = ring_set_seqno;
-	if (INTEL_INFO(dev)->gen >= 8) {
+	if (INTEL_GEN(dev_priv) >= 8)
 		engine->irq_enable_mask =
 			GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
-		engine->irq_get = gen8_ring_get_irq;
-		engine->irq_put = gen8_ring_put_irq;
-		engine->dispatch_execbuffer = gen8_ring_dispatch_execbuffer;
-		if (i915_semaphore_is_enabled(dev)) {
-			engine->semaphore.sync_to = gen8_ring_sync;
-			engine->semaphore.signal = gen8_xcs_signal;
-			GEN8_RING_SEMAPHORE_INIT(engine);
-		}
-	} else {
+	else
 		engine->irq_enable_mask = GT_BLT_USER_INTERRUPT;
-		engine->irq_get = gen6_ring_get_irq;
-		engine->irq_put = gen6_ring_put_irq;
-		engine->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
-		if (i915_semaphore_is_enabled(dev)) {
-			engine->semaphore.signal = gen6_signal;
-			engine->semaphore.sync_to = gen6_ring_sync;
-			/*
-			 * The current semaphore is only applied on pre-gen8
-			 * platform.  And there is no VCS2 ring on the pre-gen8
-			 * platform. So the semaphore between BCS and VCS2 is
-			 * initialized as INVALID.  Gen8 will initialize the
-			 * sema between BCS and VCS2 later.
-			 */
-			engine->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_BR;
-			engine->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_BV;
-			engine->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_INVALID;
-			engine->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_BVE;
-			engine->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
-			engine->semaphore.mbox.signal[RCS] = GEN6_RBSYNC;
-			engine->semaphore.mbox.signal[VCS] = GEN6_VBSYNC;
-			engine->semaphore.mbox.signal[BCS] = GEN6_NOSYNC;
-			engine->semaphore.mbox.signal[VECS] = GEN6_VEBSYNC;
-			engine->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
-		}
-	}
-	engine->init_hw = init_ring_common;
 
 	return intel_init_ring_buffer(dev, engine);
 }
 
 int intel_init_vebox_ring_buffer(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_engine_cs *engine = &dev_priv->engine[VECS];
 
 	engine->name = "video enhancement ring";
 	engine->id = VECS;
 	engine->exec_id = I915_EXEC_VEBOX;
 	engine->hw_id = 3;
-
 	engine->mmio_base = VEBOX_RING_BASE;
-	engine->write_tail = ring_write_tail;
+
+	intel_ring_default_vfuncs(dev_priv, engine);
+
 	engine->flush = gen6_ring_flush;
-	engine->add_request = gen6_add_request;
-	engine->irq_seqno_barrier = gen6_seqno_barrier;
-	engine->get_seqno = ring_get_seqno;
-	engine->set_seqno = ring_set_seqno;
 
-	if (INTEL_INFO(dev)->gen >= 8) {
+	if (INTEL_GEN(dev_priv) >= 8) {
 		engine->irq_enable_mask =
 			GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT;
-		engine->irq_get = gen8_ring_get_irq;
-		engine->irq_put = gen8_ring_put_irq;
-		engine->dispatch_execbuffer = gen8_ring_dispatch_execbuffer;
-		if (i915_semaphore_is_enabled(dev)) {
-			engine->semaphore.sync_to = gen8_ring_sync;
-			engine->semaphore.signal = gen8_xcs_signal;
-			GEN8_RING_SEMAPHORE_INIT(engine);
-		}
 	} else {
 		engine->irq_enable_mask = PM_VEBOX_USER_INTERRUPT;
-		engine->irq_get = hsw_vebox_get_irq;
-		engine->irq_put = hsw_vebox_put_irq;
-		engine->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
-		if (i915_semaphore_is_enabled(dev)) {
-			engine->semaphore.sync_to = gen6_ring_sync;
-			engine->semaphore.signal = gen6_signal;
-			engine->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_VER;
-			engine->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_VEV;
-			engine->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_VEB;
-			engine->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_INVALID;
-			engine->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
-			engine->semaphore.mbox.signal[RCS] = GEN6_RVESYNC;
-			engine->semaphore.mbox.signal[VCS] = GEN6_VVESYNC;
-			engine->semaphore.mbox.signal[BCS] = GEN6_BVESYNC;
-			engine->semaphore.mbox.signal[VECS] = GEN6_NOSYNC;
-			engine->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
-		}
+		engine->irq_enable = hsw_vebox_irq_enable;
+		engine->irq_disable = hsw_vebox_irq_disable;
 	}
-	engine->init_hw = init_ring_common;
 
 	return intel_init_ring_buffer(dev, engine);
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index ff126485d398..12cb7ed90014 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -62,18 +62,6 @@ struct  intel_hw_status_page {
 	(i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj) + \
 	 GEN8_SEMAPHORE_OFFSET(from, (__ring)->id))
 
-#define GEN8_RING_SEMAPHORE_INIT(e) do { \
-	if (!dev_priv->semaphore_obj) { \
-		break; \
-	} \
-	(e)->semaphore.signal_ggtt[RCS] = GEN8_SIGNAL_OFFSET((e), RCS); \
-	(e)->semaphore.signal_ggtt[VCS] = GEN8_SIGNAL_OFFSET((e), VCS); \
-	(e)->semaphore.signal_ggtt[BCS] = GEN8_SIGNAL_OFFSET((e), BCS); \
-	(e)->semaphore.signal_ggtt[VECS] = GEN8_SIGNAL_OFFSET((e), VECS); \
-	(e)->semaphore.signal_ggtt[VCS2] = GEN8_SIGNAL_OFFSET((e), VCS2); \
-	(e)->semaphore.signal_ggtt[(e)->id] = MI_SEMAPHORE_SYNC_INVALID; \
-	} while(0)
-
 enum intel_ring_hangcheck_action {
 	HANGCHECK_IDLE = 0,
 	HANGCHECK_WAIT,
@@ -86,8 +74,8 @@ enum intel_ring_hangcheck_action {
 
 struct intel_ring_hangcheck {
 	u64 acthd;
+	unsigned long user_interrupts;
 	u32 seqno;
-	unsigned user_interrupts;
 	int score;
 	enum intel_ring_hangcheck_action action;
 	int deadlock;
@@ -107,7 +95,6 @@ struct intel_ringbuffer {
 	int space;
 	int size;
 	int effective_size;
-	int reserved_size;
 
 	/** We track the position of the requests in the ring buffer, and
 	 * when each is retired we increment last_retired_head as the GPU
@@ -120,7 +107,7 @@ struct intel_ringbuffer {
 	u32 last_retired_head;
 };
 
-struct	intel_context;
+struct i915_gem_context;
 struct drm_i915_reg_table;
 
 /*
@@ -142,7 +129,10 @@ struct  i915_ctx_workarounds {
 	struct drm_i915_gem_object *obj;
 };
 
-struct  intel_engine_cs {
+struct drm_i915_gem_request;
+
+struct intel_engine_cs {
+	struct drm_i915_private *i915;
 	const char	*name;
 	enum intel_engine_id {
 		RCS = 0,
@@ -157,10 +147,42 @@ struct  intel_engine_cs {
 	unsigned int hw_id;
 	unsigned int guc_id; /* XXX same as hw_id? */
 	u32		mmio_base;
-	struct		drm_device *dev;
 	struct intel_ringbuffer *buffer;
 	struct list_head buffers;
 
+	/* Rather than have every client wait upon all user interrupts,
+	 * with the herd waking after every interrupt and each doing the
+	 * heavyweight seqno dance, we delegate the task (of being the
+	 * bottom-half of the user interrupt) to the first client. After
+	 * every interrupt, we wake up one client, who does the heavyweight
+	 * coherent seqno read and either goes back to sleep (if incomplete),
+	 * or wakes up all the completed clients in parallel, before then
+	 * transferring the bottom-half status to the next client in the queue.
+	 *
+	 * Compared to walking the entire list of waiters in a single dedicated
+	 * bottom-half, we reduce the latency of the first waiter by avoiding
+	 * a context switch, but incur additional coherent seqno reads when
+	 * following the chain of request breadcrumbs. Since it is most likely
+	 * that we have a single client waiting on each seqno, then reducing
+	 * the overhead of waking that client is much preferred.
+	 */
+	struct intel_breadcrumbs {
+		struct task_struct *irq_seqno_bh; /* bh for user interrupts */
+		unsigned long irq_wakeups;
+		bool irq_posted;
+
+		spinlock_t lock; /* protects the lists of requests */
+		struct rb_root waiters; /* sorted by retirement, priority */
+		struct rb_root signals; /* sorted by retirement */
+		struct intel_wait *first_wait; /* oldest waiter by retirement */
+		struct task_struct *signaler; /* used for fence signalling */
+		struct drm_i915_gem_request *first_signal;
+		struct timer_list fake_irq; /* used after a missed interrupt */
+
+		bool irq_enabled : 1;
+		bool rpm_wakelock : 1;
+	} breadcrumbs;
+
 	/*
 	 * A pool of objects to use as shadow copies of client batch buffers
 	 * when the command parser is enabled. Prevents the client from
@@ -171,11 +193,10 @@ struct  intel_engine_cs {
 	struct intel_hw_status_page status_page;
 	struct i915_ctx_workarounds wa_ctx;
 
-	unsigned irq_refcount; /* protected by dev_priv->irq_lock */
-	u32		irq_enable_mask;	/* bitmask to enable ring interrupt */
-	struct drm_i915_gem_request *trace_irq_req;
-	bool __must_check (*irq_get)(struct intel_engine_cs *ring);
-	void		(*irq_put)(struct intel_engine_cs *ring);
+	u32             irq_keep_mask; /* always keep these interrupts */
+	u32		irq_enable_mask; /* bitmask to enable ring interrupt */
+	void		(*irq_enable)(struct intel_engine_cs *ring);
+	void		(*irq_disable)(struct intel_engine_cs *ring);
 
 	int		(*init_hw)(struct intel_engine_cs *ring);
 
@@ -194,9 +215,6 @@ struct  intel_engine_cs {
 	 * monotonic, even if not coherent.
 	 */
 	void		(*irq_seqno_barrier)(struct intel_engine_cs *ring);
-	u32		(*get_seqno)(struct intel_engine_cs *ring);
-	void		(*set_seqno)(struct intel_engine_cs *ring,
-				     u32 seqno);
 	int		(*dispatch_execbuffer)(struct drm_i915_gem_request *req,
 					       u64 offset, u32 length,
 					       unsigned dispatch_flags);
@@ -268,13 +286,11 @@ struct  intel_engine_cs {
 	struct tasklet_struct irq_tasklet;
 	spinlock_t execlist_lock; /* used inside tasklet, use spin_lock_bh */
 	struct list_head execlist_queue;
-	struct list_head execlist_retired_req_list;
 	unsigned int fw_domains;
 	unsigned int next_context_status_buffer;
 	unsigned int idle_lite_restore_wa;
 	bool disable_lite_restore_wa;
 	u32 ctx_desc_template;
-	u32             irq_keep_mask; /* bitmask for interrupts that should not be masked */
 	int		(*emit_request)(struct drm_i915_gem_request *request);
 	int		(*emit_flush)(struct drm_i915_gem_request *request,
 				      u32 invalidate_domains,
@@ -306,20 +322,16 @@ struct  intel_engine_cs {
 	 * inspecting request list.
 	 */
 	u32 last_submitted_seqno;
-	unsigned user_interrupts;
 
 	bool gpu_caches_dirty;
 
-	wait_queue_head_t irq_queue;
-
-	struct intel_context *last_context;
+	struct i915_gem_context *last_context;
 
 	struct intel_ring_hangcheck hangcheck;
 
 	struct {
 		struct drm_i915_gem_object *obj;
 		u32 gtt_offset;
-		volatile u32 *cpu_page;
 	} scratch;
 
 	bool needs_cmd_parser;
@@ -350,13 +362,13 @@ struct  intel_engine_cs {
 };
 
 static inline bool
-intel_engine_initialized(struct intel_engine_cs *engine)
+intel_engine_initialized(const struct intel_engine_cs *engine)
 {
-	return engine->dev != NULL;
+	return engine->i915 != NULL;
 }
 
 static inline unsigned
-intel_engine_flag(struct intel_engine_cs *engine)
+intel_engine_flag(const struct intel_engine_cs *engine)
 {
 	return 1 << engine->id;
 }
@@ -427,7 +439,7 @@ intel_write_status_page(struct intel_engine_cs *engine,
 
 struct intel_ringbuffer *
 intel_engine_create_ringbuffer(struct intel_engine_cs *engine, int size);
-int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
+int intel_pin_and_map_ringbuffer_obj(struct drm_i915_private *dev_priv,
 				     struct intel_ringbuffer *ringbuf);
 void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf);
 void intel_ringbuffer_free(struct intel_ringbuffer *ring);
@@ -458,15 +470,14 @@ static inline void intel_ring_advance(struct intel_engine_cs *engine)
 }
 int __intel_ring_space(int head, int tail, int size);
 void intel_ring_update_space(struct intel_ringbuffer *ringbuf);
-bool intel_engine_stopped(struct intel_engine_cs *engine);
 
 int __must_check intel_engine_idle(struct intel_engine_cs *engine);
 void intel_ring_init_seqno(struct intel_engine_cs *engine, u32 seqno);
 int intel_ring_flush_all_caches(struct drm_i915_gem_request *req);
 int intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req);
 
+int intel_init_pipe_control(struct intel_engine_cs *engine, int size);
 void intel_fini_pipe_control(struct intel_engine_cs *engine);
-int intel_init_pipe_control(struct intel_engine_cs *engine);
 
 int intel_init_render_ring_buffer(struct drm_device *dev);
 int intel_init_bsd_ring_buffer(struct drm_device *dev);
@@ -475,6 +486,10 @@ int intel_init_blt_ring_buffer(struct drm_device *dev);
 int intel_init_vebox_ring_buffer(struct drm_device *dev);
 
 u64 intel_ring_get_active_head(struct intel_engine_cs *engine);
+static inline u32 intel_engine_get_seqno(struct intel_engine_cs *engine)
+{
+	return intel_read_status_page(engine, I915_GEM_HWS_INDEX);
+}
 
 int init_workarounds_ring(struct intel_engine_cs *engine);
 
@@ -486,26 +501,73 @@ static inline u32 intel_ring_get_tail(struct intel_ringbuffer *ringbuf)
 /*
  * Arbitrary size for largest possible 'add request' sequence. The code paths
  * are complex and variable. Empirical measurement shows that the worst case
- * is ILK at 136 words. Reserving too much is better than reserving too little
- * as that allows for corner cases that might have been missed. So the figure
- * has been rounded up to 160 words.
+ * is BDW at 192 bytes (6 + 6 + 36 dwords), then ILK at 136 bytes. However,
+ * we need to allocate double the largest single packet within that emission
+ * to account for tail wraparound (so 6 + 6 + 72 dwords for BDW).
  */
-#define MIN_SPACE_FOR_ADD_REQUEST	160
+#define MIN_SPACE_FOR_ADD_REQUEST 336
 
-/*
- * Reserve space in the ring to guarantee that the i915_add_request() call
- * will always have sufficient room to do its stuff. The request creation
- * code calls this automatically.
- */
-void intel_ring_reserved_space_reserve(struct intel_ringbuffer *ringbuf, int size);
-/* Cancel the reservation, e.g. because the request is being discarded. */
-void intel_ring_reserved_space_cancel(struct intel_ringbuffer *ringbuf);
-/* Use the reserved space - for use by i915_add_request() only. */
-void intel_ring_reserved_space_use(struct intel_ringbuffer *ringbuf);
-/* Finish with the reserved space - for use by i915_add_request() only. */
-void intel_ring_reserved_space_end(struct intel_ringbuffer *ringbuf);
-
-/* Legacy ringbuffer specific portion of reservation code: */
-int intel_ring_reserve_space(struct drm_i915_gem_request *request);
+static inline u32 intel_hws_seqno_address(struct intel_engine_cs *engine)
+{
+	return engine->status_page.gfx_addr + I915_GEM_HWS_INDEX_ADDR;
+}
+
+/* intel_breadcrumbs.c -- user interrupt bottom-half for waiters */
+struct intel_wait {
+	struct rb_node node;
+	struct task_struct *tsk;
+	u32 seqno;
+};
+
+struct intel_signal_node {
+	struct rb_node node;
+	struct intel_wait wait;
+};
+
+int intel_engine_init_breadcrumbs(struct intel_engine_cs *engine);
+
+static inline void intel_wait_init(struct intel_wait *wait, u32 seqno)
+{
+	wait->tsk = current;
+	wait->seqno = seqno;
+}
+
+static inline bool intel_wait_complete(const struct intel_wait *wait)
+{
+	return RB_EMPTY_NODE(&wait->node);
+}
+
+bool intel_engine_add_wait(struct intel_engine_cs *engine,
+			   struct intel_wait *wait);
+void intel_engine_remove_wait(struct intel_engine_cs *engine,
+			      struct intel_wait *wait);
+void intel_engine_enable_signaling(struct drm_i915_gem_request *request);
+
+static inline bool intel_engine_has_waiter(struct intel_engine_cs *engine)
+{
+	return READ_ONCE(engine->breadcrumbs.irq_seqno_bh);
+}
+
+static inline bool intel_engine_wakeup(struct intel_engine_cs *engine)
+{
+	bool wakeup = false;
+	struct task_struct *tsk = READ_ONCE(engine->breadcrumbs.irq_seqno_bh);
+	/* Note that for this not to dangerously chase a dangling pointer,
+	 * the caller is responsible for ensure that the task remain valid for
+	 * wake_up_process() i.e. that the RCU grace period cannot expire.
+	 *
+	 * Also note that tsk is likely to be in !TASK_RUNNING state so an
+	 * early test for tsk->state != TASK_RUNNING before wake_up_process()
+	 * is unlikely to be beneficial.
+	 */
+	if (tsk)
+		wakeup = wake_up_process(tsk);
+	return wakeup;
+}
+
+void intel_engine_enable_fake_irq(struct intel_engine_cs *engine);
+void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
+unsigned int intel_kick_waiters(struct drm_i915_private *i915);
+unsigned int intel_kick_signalers(struct drm_i915_private *i915);
 
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 7fb1da4e7fc3..1c603bbe5784 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -65,6 +65,9 @@
 bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv,
 				    int power_well_id);
 
+static struct i915_power_well *
+lookup_power_well(struct drm_i915_private *dev_priv, int power_well_id);
+
 const char *
 intel_display_power_domain_str(enum intel_display_power_domain domain)
 {
@@ -151,6 +154,23 @@ static void intel_power_well_disable(struct drm_i915_private *dev_priv,
 	power_well->ops->disable(dev_priv, power_well);
 }
 
+static void intel_power_well_get(struct drm_i915_private *dev_priv,
+				 struct i915_power_well *power_well)
+{
+	if (!power_well->count++)
+		intel_power_well_enable(dev_priv, power_well);
+}
+
+static void intel_power_well_put(struct drm_i915_private *dev_priv,
+				 struct i915_power_well *power_well)
+{
+	WARN(!power_well->count, "Use count on power well %s is already zero",
+	     power_well->name);
+
+	if (!--power_well->count)
+		intel_power_well_disable(dev_priv, power_well);
+}
+
 /*
  * We should only use the power well if we explicitly asked the hardware to
  * enable it, so check if it's enabled and also check if we've requested it to
@@ -267,7 +287,7 @@ void intel_display_set_init_power(struct drm_i915_private *dev_priv,
  */
 static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 
 	/*
 	 * After we re-enable the power well, if we touch VGA register 0x3d5
@@ -298,7 +318,7 @@ static void hsw_power_well_pre_disable(struct drm_i915_private *dev_priv)
 static void skl_power_well_post_enable(struct drm_i915_private *dev_priv,
 				       struct i915_power_well *power_well)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 
 	/*
 	 * After we re-enable the power well, if we touch VGA register 0x3d5
@@ -345,8 +365,11 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv,
 
 		if (!is_enabled) {
 			DRM_DEBUG_KMS("Enabling power well\n");
-			if (wait_for((I915_READ(HSW_PWR_WELL_DRIVER) &
-				      HSW_PWR_WELL_STATE_ENABLED), 20))
+			if (intel_wait_for_register(dev_priv,
+						    HSW_PWR_WELL_DRIVER,
+						    HSW_PWR_WELL_STATE_ENABLED,
+						    HSW_PWR_WELL_STATE_ENABLED,
+						    20))
 				DRM_ERROR("Timeout enabling power well\n");
 			hsw_power_well_post_enable(dev_priv);
 		}
@@ -419,6 +442,16 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv,
 	BIT(POWER_DOMAIN_MODESET) |			\
 	BIT(POWER_DOMAIN_AUX_A) |			\
 	BIT(POWER_DOMAIN_INIT))
+#define BXT_DPIO_CMN_A_POWER_DOMAINS (			\
+	BIT(POWER_DOMAIN_PORT_DDI_A_LANES) |		\
+	BIT(POWER_DOMAIN_AUX_A) |			\
+	BIT(POWER_DOMAIN_INIT))
+#define BXT_DPIO_CMN_BC_POWER_DOMAINS (			\
+	BIT(POWER_DOMAIN_PORT_DDI_B_LANES) |		\
+	BIT(POWER_DOMAIN_PORT_DDI_C_LANES) |		\
+	BIT(POWER_DOMAIN_AUX_B) |			\
+	BIT(POWER_DOMAIN_AUX_C) |			\
+	BIT(POWER_DOMAIN_INIT))
 
 static void assert_can_enable_dc9(struct drm_i915_private *dev_priv)
 {
@@ -548,6 +581,7 @@ void bxt_enable_dc9(struct drm_i915_private *dev_priv)
 
 	DRM_DEBUG_KMS("Enabling DC9\n");
 
+	intel_power_sequencer_reset(dev_priv);
 	gen9_set_dc_state(dev_priv, DC_STATE_EN_DC9);
 }
 
@@ -669,8 +703,11 @@ static void skl_set_power_well(struct drm_i915_private *dev_priv,
 
 	switch (power_well->data) {
 	case SKL_DISP_PW_1:
-		if (wait_for((I915_READ(SKL_FUSE_STATUS) &
-			SKL_FUSE_PG0_DIST_STATUS), 1)) {
+		if (intel_wait_for_register(dev_priv,
+					    SKL_FUSE_STATUS,
+					    SKL_FUSE_PG0_DIST_STATUS,
+					    SKL_FUSE_PG0_DIST_STATUS,
+					    1)) {
 			DRM_ERROR("PG0 not enabled\n");
 			return;
 		}
@@ -731,12 +768,18 @@ static void skl_set_power_well(struct drm_i915_private *dev_priv,
 
 	if (check_fuse_status) {
 		if (power_well->data == SKL_DISP_PW_1) {
-			if (wait_for((I915_READ(SKL_FUSE_STATUS) &
-				SKL_FUSE_PG1_DIST_STATUS), 1))
+			if (intel_wait_for_register(dev_priv,
+						    SKL_FUSE_STATUS,
+						    SKL_FUSE_PG1_DIST_STATUS,
+						    SKL_FUSE_PG1_DIST_STATUS,
+						    1))
 				DRM_ERROR("PG1 distributing status timeout\n");
 		} else if (power_well->data == SKL_DISP_PW_2) {
-			if (wait_for((I915_READ(SKL_FUSE_STATUS) &
-				SKL_FUSE_PG2_DIST_STATUS), 1))
+			if (intel_wait_for_register(dev_priv,
+						    SKL_FUSE_STATUS,
+						    SKL_FUSE_PG2_DIST_STATUS,
+						    SKL_FUSE_PG2_DIST_STATUS,
+						    1))
 				DRM_ERROR("PG2 distributing status timeout\n");
 		}
 	}
@@ -800,21 +843,99 @@ static void skl_power_well_disable(struct drm_i915_private *dev_priv,
 	skl_set_power_well(dev_priv, power_well, false);
 }
 
+static enum dpio_phy bxt_power_well_to_phy(struct i915_power_well *power_well)
+{
+	enum skl_disp_power_wells power_well_id = power_well->data;
+
+	return power_well_id == BXT_DPIO_CMN_A ? DPIO_PHY1 : DPIO_PHY0;
+}
+
+static void bxt_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv,
+					   struct i915_power_well *power_well)
+{
+	enum skl_disp_power_wells power_well_id = power_well->data;
+	struct i915_power_well *cmn_a_well;
+
+	if (power_well_id == BXT_DPIO_CMN_BC) {
+		/*
+		 * We need to copy the GRC calibration value from the eDP PHY,
+		 * so make sure it's powered up.
+		 */
+		cmn_a_well = lookup_power_well(dev_priv, BXT_DPIO_CMN_A);
+		intel_power_well_get(dev_priv, cmn_a_well);
+	}
+
+	bxt_ddi_phy_init(dev_priv, bxt_power_well_to_phy(power_well));
+
+	if (power_well_id == BXT_DPIO_CMN_BC)
+		intel_power_well_put(dev_priv, cmn_a_well);
+}
+
+static void bxt_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv,
+					    struct i915_power_well *power_well)
+{
+	bxt_ddi_phy_uninit(dev_priv, bxt_power_well_to_phy(power_well));
+}
+
+static bool bxt_dpio_cmn_power_well_enabled(struct drm_i915_private *dev_priv,
+					    struct i915_power_well *power_well)
+{
+	return bxt_ddi_phy_is_enabled(dev_priv,
+				      bxt_power_well_to_phy(power_well));
+}
+
+static void bxt_dpio_cmn_power_well_sync_hw(struct drm_i915_private *dev_priv,
+					    struct i915_power_well *power_well)
+{
+	if (power_well->count > 0)
+		bxt_dpio_cmn_power_well_enable(dev_priv, power_well);
+	else
+		bxt_dpio_cmn_power_well_disable(dev_priv, power_well);
+}
+
+
+static void bxt_verify_ddi_phy_power_wells(struct drm_i915_private *dev_priv)
+{
+	struct i915_power_well *power_well;
+
+	power_well = lookup_power_well(dev_priv, BXT_DPIO_CMN_A);
+	if (power_well->count > 0)
+		bxt_ddi_phy_verify_state(dev_priv,
+					 bxt_power_well_to_phy(power_well));
+
+	power_well = lookup_power_well(dev_priv, BXT_DPIO_CMN_BC);
+	if (power_well->count > 0)
+		bxt_ddi_phy_verify_state(dev_priv,
+					 bxt_power_well_to_phy(power_well));
+}
+
 static bool gen9_dc_off_power_well_enabled(struct drm_i915_private *dev_priv,
 					   struct i915_power_well *power_well)
 {
 	return (I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC5_DC6_MASK) == 0;
 }
 
+static void gen9_assert_dbuf_enabled(struct drm_i915_private *dev_priv)
+{
+	u32 tmp = I915_READ(DBUF_CTL);
+
+	WARN((tmp & (DBUF_POWER_STATE | DBUF_POWER_REQUEST)) !=
+	     (DBUF_POWER_STATE | DBUF_POWER_REQUEST),
+	     "Unexpected DBuf power power state (0x%08x)\n", tmp);
+}
+
 static void gen9_dc_off_power_well_enable(struct drm_i915_private *dev_priv,
 					  struct i915_power_well *power_well)
 {
 	gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
 
-	if (IS_BROXTON(dev_priv)) {
-		broxton_cdclk_verify_state(dev_priv);
-		broxton_ddi_phy_verify_state(dev_priv);
-	}
+	WARN_ON(dev_priv->cdclk_freq !=
+		dev_priv->display.get_display_clock_speed(&dev_priv->drm));
+
+	gen9_assert_dbuf_enabled(dev_priv);
+
+	if (IS_BROXTON(dev_priv))
+		bxt_verify_ddi_phy_power_wells(dev_priv);
 }
 
 static void gen9_dc_off_power_well_disable(struct drm_i915_private *dev_priv,
@@ -948,10 +1069,16 @@ static void vlv_init_display_clock_gating(struct drm_i915_private *dev_priv)
 	 */
 	I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE);
 	I915_WRITE(CBR1_VLV, 0);
+
+	WARN_ON(dev_priv->rawclk_freq == 0);
+
+	I915_WRITE(RAWCLK_FREQ_VLV,
+		   DIV_ROUND_CLOSEST(dev_priv->rawclk_freq, 1000));
 }
 
 static void vlv_display_power_well_init(struct drm_i915_private *dev_priv)
 {
+	struct intel_encoder *encoder;
 	enum pipe pipe;
 
 	/*
@@ -962,7 +1089,7 @@ static void vlv_display_power_well_init(struct drm_i915_private *dev_priv)
 	 *
 	 * CHV DPLL B/C have some issues if VGA mode is enabled.
 	 */
-	for_each_pipe(dev_priv->dev, pipe) {
+	for_each_pipe(&dev_priv->drm, pipe) {
 		u32 val = I915_READ(DPLL(pipe));
 
 		val |= DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS;
@@ -987,7 +1114,13 @@ static void vlv_display_power_well_init(struct drm_i915_private *dev_priv)
 
 	intel_hpd_init(dev_priv);
 
-	i915_redisable_vga_power_on(dev_priv->dev);
+	/* Re-enable the ADPA, if we have one */
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		if (encoder->type == INTEL_OUTPUT_ANALOG)
+			intel_crt_reset(&encoder->base);
+	}
+
+	i915_redisable_vga_power_on(&dev_priv->drm);
 }
 
 static void vlv_display_power_well_deinit(struct drm_i915_private *dev_priv)
@@ -997,9 +1130,11 @@ static void vlv_display_power_well_deinit(struct drm_i915_private *dev_priv)
 	spin_unlock_irq(&dev_priv->irq_lock);
 
 	/* make sure we're done processing display irqs */
-	synchronize_irq(dev_priv->dev->irq);
+	synchronize_irq(dev_priv->drm.irq);
+
+	intel_power_sequencer_reset(dev_priv);
 
-	vlv_power_sequencer_reset(dev_priv);
+	intel_hpd_poll_init(dev_priv);
 }
 
 static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv,
@@ -1092,7 +1227,6 @@ static void assert_chv_phy_status(struct drm_i915_private *dev_priv)
 	u32 phy_control = dev_priv->chv_phy_control;
 	u32 phy_status = 0;
 	u32 phy_status_mask = 0xffffffff;
-	u32 tmp;
 
 	/*
 	 * The BIOS can leave the PHY is some weird state
@@ -1180,10 +1314,14 @@ static void assert_chv_phy_status(struct drm_i915_private *dev_priv)
 	 * The PHY may be busy with some initial calibration and whatnot,
 	 * so the power state can take a while to actually change.
 	 */
-	if (wait_for((tmp = I915_READ(DISPLAY_PHY_STATUS) & phy_status_mask) == phy_status, 10))
-		WARN(phy_status != tmp,
-		     "Unexpected PHY_STATUS 0x%08x, expected 0x%08x (PHY_CONTROL=0x%08x)\n",
-		     tmp, phy_status, dev_priv->chv_phy_control);
+	if (intel_wait_for_register(dev_priv,
+				    DISPLAY_PHY_STATUS,
+				    phy_status_mask,
+				    phy_status,
+				    10))
+		DRM_ERROR("Unexpected PHY_STATUS 0x%08x, expected 0x%08x (PHY_CONTROL=0x%08x)\n",
+			  I915_READ(DISPLAY_PHY_STATUS) & phy_status_mask,
+			   phy_status, dev_priv->chv_phy_control);
 }
 
 #undef BITS_SET
@@ -1211,7 +1349,11 @@ static void chv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv,
 	vlv_set_power_well(dev_priv, power_well, true);
 
 	/* Poll for phypwrgood signal */
-	if (wait_for(I915_READ(DISPLAY_PHY_STATUS) & PHY_POWERGOOD(phy), 1))
+	if (intel_wait_for_register(dev_priv,
+				    DISPLAY_PHY_STATUS,
+				    PHY_POWERGOOD(phy),
+				    PHY_POWERGOOD(phy),
+				    1))
 		DRM_ERROR("Display PHY %d is not power up\n", phy);
 
 	mutex_lock(&dev_priv->sb_lock);
@@ -1501,10 +1643,8 @@ __intel_display_power_get_domain(struct drm_i915_private *dev_priv,
 	struct i915_power_well *power_well;
 	int i;
 
-	for_each_power_well(i, power_well, BIT(domain), power_domains) {
-		if (!power_well->count++)
-			intel_power_well_enable(dev_priv, power_well);
-	}
+	for_each_power_well(i, power_well, BIT(domain), power_domains)
+		intel_power_well_get(dev_priv, power_well);
 
 	power_domains->domain_use_count[domain]++;
 }
@@ -1598,14 +1738,8 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	     intel_display_power_domain_str(domain));
 	power_domains->domain_use_count[domain]--;
 
-	for_each_power_well_rev(i, power_well, BIT(domain), power_domains) {
-		WARN(!power_well->count,
-		     "Use count on power well %s is already zero",
-		     power_well->name);
-
-		if (!--power_well->count)
-			intel_power_well_disable(dev_priv, power_well);
-	}
+	for_each_power_well_rev(i, power_well, BIT(domain), power_domains)
+		intel_power_well_put(dev_priv, power_well);
 
 	mutex_unlock(&power_domains->lock);
 
@@ -1776,6 +1910,13 @@ static const struct i915_power_well_ops gen9_dc_off_power_well_ops = {
 	.is_enabled = gen9_dc_off_power_well_enabled,
 };
 
+static const struct i915_power_well_ops bxt_dpio_cmn_power_well_ops = {
+	.sync_hw = bxt_dpio_cmn_power_well_sync_hw,
+	.enable = bxt_dpio_cmn_power_well_enable,
+	.disable = bxt_dpio_cmn_power_well_disable,
+	.is_enabled = bxt_dpio_cmn_power_well_enabled,
+};
+
 static struct i915_power_well hsw_power_wells[] = {
 	{
 		.name = "always-on",
@@ -2012,6 +2153,18 @@ static struct i915_power_well bxt_power_wells[] = {
 		.ops = &skl_power_well_ops,
 		.data = SKL_DISP_PW_2,
 	},
+	{
+		.name = "dpio-common-a",
+		.domains = BXT_DPIO_CMN_A_POWER_DOMAINS,
+		.ops = &bxt_dpio_cmn_power_well_ops,
+		.data = BXT_DPIO_CMN_A,
+	},
+	{
+		.name = "dpio-common-bc",
+		.domains = BXT_DPIO_CMN_BC_POWER_DOMAINS,
+		.ops = &bxt_dpio_cmn_power_well_ops,
+		.data = BXT_DPIO_CMN_BC,
+	},
 };
 
 static int
@@ -2131,7 +2284,7 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
  */
 void intel_power_domains_fini(struct drm_i915_private *dev_priv)
 {
-	struct device *device = &dev_priv->dev->pdev->dev;
+	struct device *device = &dev_priv->drm.pdev->dev;
 
 	/*
 	 * The i915.ko module is still not prepared to be loaded when
@@ -2171,6 +2324,28 @@ static void intel_power_domains_sync_hw(struct drm_i915_private *dev_priv)
 	mutex_unlock(&power_domains->lock);
 }
 
+static void gen9_dbuf_enable(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE(DBUF_CTL, I915_READ(DBUF_CTL) | DBUF_POWER_REQUEST);
+	POSTING_READ(DBUF_CTL);
+
+	udelay(10);
+
+	if (!(I915_READ(DBUF_CTL) & DBUF_POWER_STATE))
+		DRM_ERROR("DBuf power enable timeout\n");
+}
+
+static void gen9_dbuf_disable(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE(DBUF_CTL, I915_READ(DBUF_CTL) & ~DBUF_POWER_REQUEST);
+	POSTING_READ(DBUF_CTL);
+
+	udelay(10);
+
+	if (I915_READ(DBUF_CTL) & DBUF_POWER_STATE)
+		DRM_ERROR("DBuf power disable timeout!\n");
+}
+
 static void skl_display_core_init(struct drm_i915_private *dev_priv,
 				   bool resume)
 {
@@ -2195,12 +2370,11 @@ static void skl_display_core_init(struct drm_i915_private *dev_priv,
 
 	mutex_unlock(&power_domains->lock);
 
-	if (!resume)
-		return;
-
 	skl_init_cdclk(dev_priv);
 
-	if (dev_priv->csr.dmc_payload)
+	gen9_dbuf_enable(dev_priv);
+
+	if (resume && dev_priv->csr.dmc_payload)
 		intel_csr_load_program(dev_priv);
 }
 
@@ -2211,6 +2385,8 @@ static void skl_display_core_uninit(struct drm_i915_private *dev_priv)
 
 	gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
 
+	gen9_dbuf_disable(dev_priv);
+
 	skl_uninit_cdclk(dev_priv);
 
 	/* The spec doesn't call for removing the reset handshake flag */
@@ -2254,11 +2430,9 @@ void bxt_display_core_init(struct drm_i915_private *dev_priv,
 
 	mutex_unlock(&power_domains->lock);
 
-	broxton_init_cdclk(dev_priv);
-	broxton_ddi_phy_init(dev_priv);
+	bxt_init_cdclk(dev_priv);
 
-	broxton_cdclk_verify_state(dev_priv);
-	broxton_ddi_phy_verify_state(dev_priv);
+	gen9_dbuf_enable(dev_priv);
 
 	if (resume && dev_priv->csr.dmc_payload)
 		intel_csr_load_program(dev_priv);
@@ -2271,8 +2445,9 @@ void bxt_display_core_uninit(struct drm_i915_private *dev_priv)
 
 	gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
 
-	broxton_ddi_phy_uninit(dev_priv);
-	broxton_uninit_cdclk(dev_priv);
+	gen9_dbuf_disable(dev_priv);
+
+	bxt_uninit_cdclk(dev_priv);
 
 	/* The spec doesn't call for removing the reset handshake flag */
 
@@ -2403,13 +2578,14 @@ static void vlv_cmnlane_wa(struct drm_i915_private *dev_priv)
 /**
  * intel_power_domains_init_hw - initialize hardware power domain state
  * @dev_priv: i915 device instance
+ * @resume: Called from resume code paths or not
  *
  * This function initializes the hardware power domain state and enables all
  * power domains using intel_display_set_init_power().
  */
 void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
 
 	power_domains->initializing = true;
@@ -2471,7 +2647,7 @@ void intel_power_domains_suspend(struct drm_i915_private *dev_priv)
  */
 void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct device *device = &dev->pdev->dev;
 
 	pm_runtime_get_sync(device);
@@ -2492,7 +2668,7 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
  */
 bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct device *device = &dev->pdev->dev;
 
 	if (IS_ENABLED(CONFIG_PM)) {
@@ -2534,7 +2710,7 @@ bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv)
  */
 void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct device *device = &dev->pdev->dev;
 
 	assert_rpm_wakelock_held(dev_priv);
@@ -2553,7 +2729,7 @@ void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv)
  */
 void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct device *device = &dev->pdev->dev;
 
 	assert_rpm_wakelock_held(dev_priv);
@@ -2576,7 +2752,7 @@ void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
  */
 void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
+	struct drm_device *dev = &dev_priv->drm;
 	struct device *device = &dev->pdev->dev;
 
 	pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 2128fae5687d..e378f35365a2 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -240,7 +240,7 @@ intel_sdvo_create_enhance_property(struct intel_sdvo *intel_sdvo,
 static void intel_sdvo_write_sdvox(struct intel_sdvo *intel_sdvo, u32 val)
 {
 	struct drm_device *dev = intel_sdvo->base.base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 bval = val, cval = val;
 	int i;
 
@@ -1195,7 +1195,7 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder,
 static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder)
 {
 	struct drm_device *dev = intel_encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc = to_intel_crtc(intel_encoder->base.crtc);
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	struct drm_display_mode *mode = &crtc->config->base.mode;
@@ -1330,7 +1330,7 @@ static bool intel_sdvo_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	u16 active_outputs = 0;
 	u32 tmp;
@@ -1353,7 +1353,7 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 				  struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	struct intel_sdvo_dtd dtd;
 	int encoder_pixel_multiplier = 0;
@@ -1436,7 +1436,7 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 
 static void intel_disable_sdvo(struct intel_encoder *encoder)
 {
-	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	u32 temp;
@@ -1471,7 +1471,7 @@ static void intel_disable_sdvo(struct intel_encoder *encoder)
 		temp &= ~SDVO_ENABLE;
 		intel_sdvo_write_sdvox(intel_sdvo, temp);
 
-		intel_wait_for_vblank_if_active(dev_priv->dev, PIPE_A);
+		intel_wait_for_vblank_if_active(&dev_priv->drm, PIPE_A);
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, PIPE_A, true);
 		intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, true);
 	}
@@ -1489,7 +1489,7 @@ static void pch_post_disable_sdvo(struct intel_encoder *encoder)
 static void intel_enable_sdvo(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	u32 temp;
@@ -1633,7 +1633,7 @@ intel_sdvo_get_edid(struct drm_connector *connector)
 static struct edid *
 intel_sdvo_get_analog_edid(struct drm_connector *connector)
 {
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 
 	return drm_get_edid(connector,
 			    intel_gmbus_get_adapter(dev_priv,
@@ -1916,7 +1916,7 @@ static void intel_sdvo_get_tv_modes(struct drm_connector *connector)
 static void intel_sdvo_get_lvds_modes(struct drm_connector *connector)
 {
 	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct drm_display_mode *newmode;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
@@ -2001,7 +2001,7 @@ intel_sdvo_set_property(struct drm_connector *connector,
 {
 	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
 	struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector);
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	uint16_t temp_value;
 	uint8_t cmd;
 	int ret;
@@ -2177,12 +2177,39 @@ done:
 #undef CHECK_PROPERTY
 }
 
+static int
+intel_sdvo_connector_register(struct drm_connector *connector)
+{
+	struct intel_sdvo *sdvo = intel_attached_sdvo(connector);
+	int ret;
+
+	ret = intel_connector_register(connector);
+	if (ret)
+		return ret;
+
+	return sysfs_create_link(&connector->kdev->kobj,
+				 &sdvo->ddc.dev.kobj,
+				 sdvo->ddc.dev.kobj.name);
+}
+
+static void
+intel_sdvo_connector_unregister(struct drm_connector *connector)
+{
+	struct intel_sdvo *sdvo = intel_attached_sdvo(connector);
+
+	sysfs_remove_link(&connector->kdev->kobj,
+			  sdvo->ddc.dev.kobj.name);
+	intel_connector_unregister(connector);
+}
+
 static const struct drm_connector_funcs intel_sdvo_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.detect = intel_sdvo_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = intel_sdvo_set_property,
 	.atomic_get_property = intel_connector_atomic_get_property,
+	.late_register = intel_sdvo_connector_register,
+	.early_unregister = intel_sdvo_connector_unregister,
 	.destroy = intel_sdvo_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
@@ -2191,7 +2218,6 @@ static const struct drm_connector_funcs intel_sdvo_connector_funcs = {
 static const struct drm_connector_helper_funcs intel_sdvo_connector_helper_funcs = {
 	.get_modes = intel_sdvo_get_modes,
 	.mode_valid = intel_sdvo_mode_valid,
-	.best_encoder = intel_best_encoder,
 };
 
 static void intel_sdvo_enc_destroy(struct drm_encoder *encoder)
@@ -2312,7 +2338,7 @@ intel_sdvo_is_hdmi_connector(struct intel_sdvo *intel_sdvo, int device)
 static u8
 intel_sdvo_get_slave_addr(struct drm_device *dev, struct intel_sdvo *sdvo)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct sdvo_device_mapping *my_mapping, *other_mapping;
 
 	if (sdvo->port == PORT_B) {
@@ -2346,20 +2372,6 @@ intel_sdvo_get_slave_addr(struct drm_device *dev, struct intel_sdvo *sdvo)
 		return 0x72;
 }
 
-static void
-intel_sdvo_connector_unregister(struct intel_connector *intel_connector)
-{
-	struct drm_connector *drm_connector;
-	struct intel_sdvo *sdvo_encoder;
-
-	drm_connector = &intel_connector->base;
-	sdvo_encoder = intel_attached_sdvo(&intel_connector->base);
-
-	sysfs_remove_link(&drm_connector->kdev->kobj,
-			  sdvo_encoder->ddc.dev.kobj.name);
-	intel_connector_unregister(intel_connector);
-}
-
 static int
 intel_sdvo_connector_init(struct intel_sdvo_connector *connector,
 			  struct intel_sdvo *encoder)
@@ -2382,27 +2394,10 @@ intel_sdvo_connector_init(struct intel_sdvo_connector *connector,
 	connector->base.base.doublescan_allowed = 0;
 	connector->base.base.display_info.subpixel_order = SubPixelHorizontalRGB;
 	connector->base.get_hw_state = intel_sdvo_connector_get_hw_state;
-	connector->base.unregister = intel_sdvo_connector_unregister;
 
 	intel_connector_attach_encoder(&connector->base, &encoder->base);
-	ret = drm_connector_register(drm_connector);
-	if (ret < 0)
-		goto err1;
-
-	ret = sysfs_create_link(&drm_connector->kdev->kobj,
-				&encoder->ddc.dev.kobj,
-				encoder->ddc.dev.kobj.name);
-	if (ret < 0)
-		goto err2;
 
 	return 0;
-
-err2:
-	drm_connector_unregister(drm_connector);
-err1:
-	drm_connector_cleanup(drm_connector);
-
-	return ret;
 }
 
 static void
@@ -2529,7 +2524,6 @@ intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, int type)
 	return true;
 
 err:
-	drm_connector_unregister(connector);
 	intel_sdvo_destroy(connector);
 	return false;
 }
@@ -2608,7 +2602,6 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device)
 	return true;
 
 err:
-	drm_connector_unregister(connector);
 	intel_sdvo_destroy(connector);
 	return false;
 }
@@ -2959,7 +2952,7 @@ static void assert_sdvo_port_valid(const struct drm_i915_private *dev_priv,
 bool intel_sdvo_init(struct drm_device *dev,
 		     i915_reg_t sdvo_reg, enum port port)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *intel_encoder;
 	struct intel_sdvo *intel_sdvo;
 	int i;
@@ -2981,7 +2974,7 @@ bool intel_sdvo_init(struct drm_device *dev,
 	intel_encoder = &intel_sdvo->base;
 	intel_encoder->type = INTEL_OUTPUT_SDVO;
 	drm_encoder_init(dev, &intel_encoder->base, &intel_sdvo_enc_funcs, 0,
-			 NULL);
+			 "SDVO %c", port_name(port));
 
 	/* Read the regs to test if we can talk to the device */
 	for (i = 0; i < 0x40; i++) {
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index c3998188cf35..1a840bf92eea 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -51,7 +51,9 @@ static int vlv_sideband_rw(struct drm_i915_private *dev_priv, u32 devfn,
 
 	WARN_ON(!mutex_is_locked(&dev_priv->sb_lock));
 
-	if (wait_for((I915_READ(VLV_IOSF_DOORBELL_REQ) & IOSF_SB_BUSY) == 0, 5)) {
+	if (intel_wait_for_register(dev_priv,
+				    VLV_IOSF_DOORBELL_REQ, IOSF_SB_BUSY, 0,
+				    5)) {
 		DRM_DEBUG_DRIVER("IOSF sideband idle wait (%s) timed out\n",
 				 is_read ? "read" : "write");
 		return -EAGAIN;
@@ -62,7 +64,9 @@ static int vlv_sideband_rw(struct drm_i915_private *dev_priv, u32 devfn,
 		I915_WRITE(VLV_IOSF_DATA, *val);
 	I915_WRITE(VLV_IOSF_DOORBELL_REQ, cmd);
 
-	if (wait_for((I915_READ(VLV_IOSF_DOORBELL_REQ) & IOSF_SB_BUSY) == 0, 5)) {
+	if (intel_wait_for_register(dev_priv,
+				    VLV_IOSF_DOORBELL_REQ, IOSF_SB_BUSY, 0,
+				    5)) {
 		DRM_DEBUG_DRIVER("IOSF sideband finish wait (%s) timed out\n",
 				 is_read ? "read" : "write");
 		return -ETIMEDOUT;
@@ -202,8 +206,9 @@ u32 intel_sbi_read(struct drm_i915_private *dev_priv, u16 reg,
 	u32 value = 0;
 	WARN_ON(!mutex_is_locked(&dev_priv->sb_lock));
 
-	if (wait_for((I915_READ(SBI_CTL_STAT) & SBI_BUSY) == 0,
-				100)) {
+	if (intel_wait_for_register(dev_priv,
+				    SBI_CTL_STAT, SBI_BUSY, 0,
+				    100)) {
 		DRM_ERROR("timeout waiting for SBI to become ready\n");
 		return 0;
 	}
@@ -216,8 +221,11 @@ u32 intel_sbi_read(struct drm_i915_private *dev_priv, u16 reg,
 		value = SBI_CTL_DEST_MPHY | SBI_CTL_OP_IORD;
 	I915_WRITE(SBI_CTL_STAT, value | SBI_BUSY);
 
-	if (wait_for((I915_READ(SBI_CTL_STAT) & (SBI_BUSY | SBI_RESPONSE_FAIL)) == 0,
-				100)) {
+	if (intel_wait_for_register(dev_priv,
+				    SBI_CTL_STAT,
+				    SBI_BUSY | SBI_RESPONSE_FAIL,
+				    0,
+				    100)) {
 		DRM_ERROR("timeout waiting for SBI to complete read transaction\n");
 		return 0;
 	}
@@ -232,8 +240,9 @@ void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
 
 	WARN_ON(!mutex_is_locked(&dev_priv->sb_lock));
 
-	if (wait_for((I915_READ(SBI_CTL_STAT) & SBI_BUSY) == 0,
-				100)) {
+	if (intel_wait_for_register(dev_priv,
+				    SBI_CTL_STAT, SBI_BUSY, 0,
+				    100)) {
 		DRM_ERROR("timeout waiting for SBI to become ready\n");
 		return;
 	}
@@ -247,8 +256,11 @@ void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
 		tmp = SBI_CTL_DEST_MPHY | SBI_CTL_OP_IOWR;
 	I915_WRITE(SBI_CTL_STAT, SBI_BUSY | tmp);
 
-	if (wait_for((I915_READ(SBI_CTL_STAT) & (SBI_BUSY | SBI_RESPONSE_FAIL)) == 0,
-				100)) {
+	if (intel_wait_for_register(dev_priv,
+				    SBI_CTL_STAT,
+				    SBI_BUSY | SBI_RESPONSE_FAIL,
+				    0,
+				    100)) {
 		DRM_ERROR("timeout waiting for SBI to complete write transaction\n");
 		return;
 	}
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 0f3e2303e0e9..7c08e4f29032 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -53,8 +53,8 @@ format_is_yuv(uint32_t format)
 	}
 }
 
-static int usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
-			      int usecs)
+int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
+			     int usecs)
 {
 	/* paranoia */
 	if (!adjusted_mode->crtc_htotal)
@@ -80,9 +80,7 @@ static int usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
  */
 void intel_pipe_update_start(struct intel_crtc *crtc)
 {
-	struct drm_device *dev = crtc->base.dev;
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
-	enum pipe pipe = crtc->pipe;
 	long timeout = msecs_to_jiffies_timeout(1);
 	int scanline, min, max, vblank_start;
 	wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base);
@@ -93,7 +91,7 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
 		vblank_start = DIV_ROUND_UP(vblank_start, 2);
 
 	/* FIXME needs to be calibrated sensibly */
-	min = vblank_start - usecs_to_scanlines(adjusted_mode, 100);
+	min = vblank_start - intel_usecs_to_scanlines(adjusted_mode, 100);
 	max = vblank_start - 1;
 
 	local_irq_disable();
@@ -139,8 +137,7 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
 
 	crtc->debug.scanline_start = scanline;
 	crtc->debug.start_vbl_time = ktime_get();
-	crtc->debug.start_vbl_count =
-		dev->driver->get_vblank_counter(dev, pipe);
+	crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);
 
 	trace_i915_pipe_update_vblank_evaded(crtc);
 }
@@ -154,16 +151,35 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
  * re-enables interrupts and verifies the update was actually completed
  * before a vblank using the value of @start_vbl_count.
  */
-void intel_pipe_update_end(struct intel_crtc *crtc)
+void intel_pipe_update_end(struct intel_crtc *crtc, struct intel_flip_work *work)
 {
-	struct drm_device *dev = crtc->base.dev;
 	enum pipe pipe = crtc->pipe;
 	int scanline_end = intel_get_crtc_scanline(crtc);
-	u32 end_vbl_count = dev->driver->get_vblank_counter(dev, pipe);
+	u32 end_vbl_count = intel_crtc_get_vblank_counter(crtc);
 	ktime_t end_vbl_time = ktime_get();
 
+	if (work) {
+		work->flip_queued_vblank = end_vbl_count;
+		smp_mb__before_atomic();
+		atomic_set(&work->pending, 1);
+	}
+
 	trace_i915_pipe_update_end(crtc, end_vbl_count, scanline_end);
 
+	/* We're still in the vblank-evade critical section, this can't race.
+	 * Would be slightly nice to just grab the vblank count and arm the
+	 * event outside of the critical section - the spinlock might spin for a
+	 * while ... */
+	if (crtc->base.state->event) {
+		WARN_ON(drm_crtc_vblank_get(&crtc->base) != 0);
+
+		spin_lock(&crtc->base.dev->event_lock);
+		drm_crtc_arm_vblank_event(&crtc->base, crtc->base.state->event);
+		spin_unlock(&crtc->base.dev->event_lock);
+
+		crtc->base.state->event = NULL;
+	}
+
 	local_irq_enable();
 
 	if (crtc->debug.start_vbl_count &&
@@ -183,7 +199,7 @@ skl_update_plane(struct drm_plane *drm_plane,
 		 const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = drm_plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *intel_plane = to_intel_plane(drm_plane);
 	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
@@ -203,8 +219,6 @@ skl_update_plane(struct drm_plane *drm_plane,
 	uint32_t y = plane_state->src.y1 >> 16;
 	uint32_t src_w = drm_rect_width(&plane_state->src) >> 16;
 	uint32_t src_h = drm_rect_height(&plane_state->src) >> 16;
-	const struct intel_scaler *scaler =
-		&crtc_state->scaler_state.scalers[plane_state->scaler_id];
 
 	plane_ctl = PLANE_CTL_ENABLE |
 		PLANE_CTL_PIPE_GAMMA_ENABLE |
@@ -260,13 +274,16 @@ skl_update_plane(struct drm_plane *drm_plane,
 
 	/* program plane scaler */
 	if (plane_state->scaler_id >= 0) {
-		uint32_t ps_ctrl = 0;
 		int scaler_id = plane_state->scaler_id;
+		const struct intel_scaler *scaler;
 
 		DRM_DEBUG_KMS("plane = %d PS_PLANE_SEL(plane) = 0x%x\n", plane,
 			PS_PLANE_SEL(plane));
-		ps_ctrl = PS_SCALER_EN | PS_PLANE_SEL(plane) | scaler->mode;
-		I915_WRITE(SKL_PS_CTRL(pipe, scaler_id), ps_ctrl);
+
+		scaler = &crtc_state->scaler_state.scalers[scaler_id];
+
+		I915_WRITE(SKL_PS_CTRL(pipe, scaler_id),
+			   PS_SCALER_EN | PS_PLANE_SEL(plane) | scaler->mode);
 		I915_WRITE(SKL_PS_PWR_GATE(pipe, scaler_id), 0);
 		I915_WRITE(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y);
 		I915_WRITE(SKL_PS_WIN_SZ(pipe, scaler_id),
@@ -286,7 +303,7 @@ static void
 skl_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc)
 {
 	struct drm_device *dev = dplane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *intel_plane = to_intel_plane(dplane);
 	const int pipe = intel_plane->pipe;
 	const int plane = intel_plane->plane + 1;
@@ -300,7 +317,7 @@ skl_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc)
 static void
 chv_update_csc(struct intel_plane *intel_plane, uint32_t format)
 {
-	struct drm_i915_private *dev_priv = intel_plane->base.dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(intel_plane->base.dev);
 	int plane = intel_plane->plane;
 
 	/* Seems RGB data bypasses the CSC always */
@@ -342,7 +359,7 @@ vlv_update_plane(struct drm_plane *dplane,
 		 const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = dplane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *intel_plane = to_intel_plane(dplane);
 	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
@@ -468,7 +485,7 @@ static void
 vlv_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc)
 {
 	struct drm_device *dev = dplane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *intel_plane = to_intel_plane(dplane);
 	int pipe = intel_plane->pipe;
 	int plane = intel_plane->plane;
@@ -485,7 +502,7 @@ ivb_update_plane(struct drm_plane *plane,
 		 const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
@@ -607,7 +624,7 @@ static void
 ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 {
 	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	int pipe = intel_plane->pipe;
 
@@ -626,7 +643,7 @@ ilk_update_plane(struct drm_plane *plane,
 		 const struct intel_plane_state *plane_state)
 {
 	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct drm_framebuffer *fb = plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
@@ -736,7 +753,7 @@ static void
 ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 {
 	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	int pipe = intel_plane->pipe;
 
@@ -1111,10 +1128,18 @@ intel_plane_init(struct drm_device *dev, enum pipe pipe, int plane)
 
 	possible_crtcs = (1 << pipe);
 
-	ret = drm_universal_plane_init(dev, &intel_plane->base, possible_crtcs,
-				       &intel_plane_funcs,
-				       plane_formats, num_plane_formats,
-				       DRM_PLANE_TYPE_OVERLAY, NULL);
+	if (INTEL_INFO(dev)->gen >= 9)
+		ret = drm_universal_plane_init(dev, &intel_plane->base, possible_crtcs,
+					       &intel_plane_funcs,
+					       plane_formats, num_plane_formats,
+					       DRM_PLANE_TYPE_OVERLAY,
+					       "plane %d%c", plane + 2, pipe_name(pipe));
+	else
+		ret = drm_universal_plane_init(dev, &intel_plane->base, possible_crtcs,
+					       &intel_plane_funcs,
+					       plane_formats, num_plane_formats,
+					       DRM_PLANE_TYPE_OVERLAY,
+					       "sprite %c", sprite_name(pipe, plane));
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 223129d3c765..49136ad5473e 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -826,7 +826,7 @@ static bool
 intel_tv_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 tmp = I915_READ(TV_CTL);
 
 	if (!(tmp & TV_ENC_ENABLE))
@@ -841,7 +841,7 @@ static void
 intel_enable_tv(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	/* Prevents vblank waits from timing out in intel_tv_detect_type() */
 	intel_wait_for_vblank(encoder->base.dev,
@@ -854,7 +854,7 @@ static void
 intel_disable_tv(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 
 	I915_WRITE(TV_CTL, I915_READ(TV_CTL) & ~TV_ENC_ENABLE);
 }
@@ -1013,7 +1013,7 @@ static void set_color_conversion(struct drm_i915_private *dev_priv,
 static void intel_tv_pre_enable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	struct intel_tv *intel_tv = enc_to_tv(encoder);
 	const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv);
@@ -1173,7 +1173,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv,
 	struct drm_crtc *crtc = connector->state->crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 tv_ctl, save_tv_ctl;
 	u32 tv_dac, save_tv_dac;
 	int type;
@@ -1501,6 +1501,8 @@ out:
 static const struct drm_connector_funcs intel_tv_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.detect = intel_tv_detect,
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
 	.destroy = intel_tv_destroy,
 	.set_property = intel_tv_set_property,
 	.atomic_get_property = intel_connector_atomic_get_property,
@@ -1512,7 +1514,6 @@ static const struct drm_connector_funcs intel_tv_connector_funcs = {
 static const struct drm_connector_helper_funcs intel_tv_connector_helper_funcs = {
 	.mode_valid = intel_tv_mode_valid,
 	.get_modes = intel_tv_get_modes,
-	.best_encoder = intel_best_encoder,
 };
 
 static const struct drm_encoder_funcs intel_tv_enc_funcs = {
@@ -1522,7 +1523,7 @@ static const struct drm_encoder_funcs intel_tv_enc_funcs = {
 void
 intel_tv_init(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_connector *connector;
 	struct intel_tv *intel_tv;
 	struct intel_encoder *intel_encoder;
@@ -1591,7 +1592,7 @@ intel_tv_init(struct drm_device *dev)
 			   DRM_MODE_CONNECTOR_SVIDEO);
 
 	drm_encoder_init(dev, &intel_encoder->base, &intel_tv_enc_funcs,
-			 DRM_MODE_ENCODER_TVDAC, NULL);
+			 DRM_MODE_ENCODER_TVDAC, "TV");
 
 	intel_encoder->compute_config = intel_tv_compute_config;
 	intel_encoder->get_config = intel_tv_get_config;
@@ -1600,7 +1601,6 @@ intel_tv_init(struct drm_device *dev)
 	intel_encoder->disable = intel_disable_tv;
 	intel_encoder->get_hw_state = intel_tv_get_hw_state;
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
-	intel_connector->unregister = intel_connector_unregister;
 
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_encoder->type = INTEL_OUTPUT_TVOUT;
@@ -1642,5 +1642,4 @@ intel_tv_init(struct drm_device *dev)
 	drm_object_attach_property(&connector->base,
 				   dev->mode_config.tv_bottom_margin_property,
 				   intel_tv->margin[TV_MARGIN_BOTTOM]);
-	drm_connector_register(connector);
 }
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 4f1dfe616856..ff80a81b1a84 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -248,9 +248,9 @@ intel_uncore_fw_release_timer(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore)
+void intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv,
+				  bool restore)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
 	struct intel_uncore_forcewake_domain *domain;
 	int retry_count = 100;
@@ -304,7 +304,7 @@ void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore)
 		if (fw)
 			dev_priv->uncore.funcs.force_wake_get(dev_priv, fw);
 
-		if (IS_GEN6(dev) || IS_GEN7(dev))
+		if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv))
 			dev_priv->uncore.fifo_count =
 				fifo_free_entries(dev_priv);
 	}
@@ -400,43 +400,42 @@ check_for_unclaimed_mmio(struct drm_i915_private *dev_priv)
 	return false;
 }
 
-static void __intel_uncore_early_sanitize(struct drm_device *dev,
+static void __intel_uncore_early_sanitize(struct drm_i915_private *dev_priv,
 					  bool restore_forcewake)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	/* clear out unclaimed reg detection bit */
 	if (check_for_unclaimed_mmio(dev_priv))
 		DRM_DEBUG("unclaimed mmio detected on uncore init, clearing\n");
 
 	/* clear out old GT FIFO errors */
-	if (IS_GEN6(dev) || IS_GEN7(dev))
+	if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv))
 		__raw_i915_write32(dev_priv, GTFIFODBG,
 				   __raw_i915_read32(dev_priv, GTFIFODBG));
 
 	/* WaDisableShadowRegForCpd:chv */
-	if (IS_CHERRYVIEW(dev)) {
+	if (IS_CHERRYVIEW(dev_priv)) {
 		__raw_i915_write32(dev_priv, GTFIFOCTL,
 				   __raw_i915_read32(dev_priv, GTFIFOCTL) |
 				   GT_FIFO_CTL_BLOCK_ALL_POLICY_STALL |
 				   GT_FIFO_CTL_RC6_POLICY_STALL);
 	}
 
-	intel_uncore_forcewake_reset(dev, restore_forcewake);
+	intel_uncore_forcewake_reset(dev_priv, restore_forcewake);
 }
 
-void intel_uncore_early_sanitize(struct drm_device *dev, bool restore_forcewake)
+void intel_uncore_early_sanitize(struct drm_i915_private *dev_priv,
+				 bool restore_forcewake)
 {
-	__intel_uncore_early_sanitize(dev, restore_forcewake);
-	i915_check_and_clear_faults(dev);
+	__intel_uncore_early_sanitize(dev_priv, restore_forcewake);
+	i915_check_and_clear_faults(dev_priv);
 }
 
-void intel_uncore_sanitize(struct drm_device *dev)
+void intel_uncore_sanitize(struct drm_i915_private *dev_priv)
 {
-	i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
+	i915.enable_rc6 = sanitize_rc6_option(dev_priv, i915.enable_rc6);
 
 	/* BIOS often leaves RC6 enabled, but disable it for hw init */
-	intel_disable_gt_powersave(dev);
+	intel_disable_gt_powersave(dev_priv);
 }
 
 static void __intel_uncore_forcewake_get(struct drm_i915_private *dev_priv,
@@ -1233,14 +1232,12 @@ static void fw_domain_init(struct drm_i915_private *dev_priv,
 	fw_domain_reset(d);
 }
 
-static void intel_uncore_fw_domains_init(struct drm_device *dev)
+static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	if (INTEL_INFO(dev_priv)->gen <= 5)
 		return;
 
-	if (IS_GEN9(dev)) {
+	if (IS_GEN9(dev_priv)) {
 		dev_priv->uncore.funcs.force_wake_get = fw_domains_get;
 		dev_priv->uncore.funcs.force_wake_put = fw_domains_put;
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER,
@@ -1251,9 +1248,9 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev)
 			       FORCEWAKE_ACK_BLITTER_GEN9);
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_MEDIA,
 			       FORCEWAKE_MEDIA_GEN9, FORCEWAKE_ACK_MEDIA_GEN9);
-	} else if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
+	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		dev_priv->uncore.funcs.force_wake_get = fw_domains_get;
-		if (!IS_CHERRYVIEW(dev))
+		if (!IS_CHERRYVIEW(dev_priv))
 			dev_priv->uncore.funcs.force_wake_put =
 				fw_domains_put_with_fifo;
 		else
@@ -1262,17 +1259,17 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev)
 			       FORCEWAKE_VLV, FORCEWAKE_ACK_VLV);
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_MEDIA,
 			       FORCEWAKE_MEDIA_VLV, FORCEWAKE_ACK_MEDIA_VLV);
-	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
+	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
 		dev_priv->uncore.funcs.force_wake_get =
 			fw_domains_get_with_thread_status;
-		if (IS_HASWELL(dev))
+		if (IS_HASWELL(dev_priv))
 			dev_priv->uncore.funcs.force_wake_put =
 				fw_domains_put_with_fifo;
 		else
 			dev_priv->uncore.funcs.force_wake_put = fw_domains_put;
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER,
 			       FORCEWAKE_MT, FORCEWAKE_ACK_HSW);
-	} else if (IS_IVYBRIDGE(dev)) {
+	} else if (IS_IVYBRIDGE(dev_priv)) {
 		u32 ecobus;
 
 		/* IVB configs may use multi-threaded forcewake */
@@ -1302,11 +1299,11 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev)
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER,
 			       FORCEWAKE_MT, FORCEWAKE_MT_ACK);
 
-		mutex_lock(&dev->struct_mutex);
+		spin_lock_irq(&dev_priv->uncore.lock);
 		fw_domains_get_with_thread_status(dev_priv, FORCEWAKE_ALL);
 		ecobus = __raw_i915_read32(dev_priv, ECOBUS);
 		fw_domains_put_with_fifo(dev_priv, FORCEWAKE_ALL);
-		mutex_unlock(&dev->struct_mutex);
+		spin_unlock_irq(&dev_priv->uncore.lock);
 
 		if (!(ecobus & FORCEWAKE_MT_ENABLE)) {
 			DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n");
@@ -1314,7 +1311,7 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev)
 			fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER,
 				       FORCEWAKE, FORCEWAKE_ACK);
 		}
-	} else if (IS_GEN6(dev)) {
+	} else if (IS_GEN6(dev_priv)) {
 		dev_priv->uncore.funcs.force_wake_get =
 			fw_domains_get_with_thread_status;
 		dev_priv->uncore.funcs.force_wake_put =
@@ -1327,26 +1324,24 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev)
 	WARN_ON(dev_priv->uncore.fw_domains == 0);
 }
 
-void intel_uncore_init(struct drm_device *dev)
+void intel_uncore_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	i915_check_vgpu(dev);
+	i915_check_vgpu(dev_priv);
 
 	intel_uncore_edram_detect(dev_priv);
-	intel_uncore_fw_domains_init(dev);
-	__intel_uncore_early_sanitize(dev, false);
+	intel_uncore_fw_domains_init(dev_priv);
+	__intel_uncore_early_sanitize(dev_priv, false);
 
 	dev_priv->uncore.unclaimed_mmio_check = 1;
 
-	switch (INTEL_INFO(dev)->gen) {
+	switch (INTEL_INFO(dev_priv)->gen) {
 	default:
 	case 9:
 		ASSIGN_WRITE_MMIO_VFUNCS(gen9);
 		ASSIGN_READ_MMIO_VFUNCS(gen9);
 		break;
 	case 8:
-		if (IS_CHERRYVIEW(dev)) {
+		if (IS_CHERRYVIEW(dev_priv)) {
 			ASSIGN_WRITE_MMIO_VFUNCS(chv);
 			ASSIGN_READ_MMIO_VFUNCS(chv);
 
@@ -1357,13 +1352,13 @@ void intel_uncore_init(struct drm_device *dev)
 		break;
 	case 7:
 	case 6:
-		if (IS_HASWELL(dev)) {
+		if (IS_HASWELL(dev_priv)) {
 			ASSIGN_WRITE_MMIO_VFUNCS(hsw);
 		} else {
 			ASSIGN_WRITE_MMIO_VFUNCS(gen6);
 		}
 
-		if (IS_VALLEYVIEW(dev)) {
+		if (IS_VALLEYVIEW(dev_priv)) {
 			ASSIGN_READ_MMIO_VFUNCS(vlv);
 		} else {
 			ASSIGN_READ_MMIO_VFUNCS(gen6);
@@ -1381,24 +1376,24 @@ void intel_uncore_init(struct drm_device *dev)
 		break;
 	}
 
-	if (intel_vgpu_active(dev)) {
+	if (intel_vgpu_active(dev_priv)) {
 		ASSIGN_WRITE_MMIO_VFUNCS(vgpu);
 		ASSIGN_READ_MMIO_VFUNCS(vgpu);
 	}
 
-	i915_check_and_clear_faults(dev);
+	i915_check_and_clear_faults(dev_priv);
 }
 #undef ASSIGN_WRITE_MMIO_VFUNCS
 #undef ASSIGN_READ_MMIO_VFUNCS
 
-void intel_uncore_fini(struct drm_device *dev)
+void intel_uncore_fini(struct drm_i915_private *dev_priv)
 {
 	/* Paranoia: make sure we have disabled everything before we exit. */
-	intel_uncore_sanitize(dev);
-	intel_uncore_forcewake_reset(dev, false);
+	intel_uncore_sanitize(dev_priv);
+	intel_uncore_forcewake_reset(dev_priv, false);
 }
 
-#define GEN_RANGE(l, h) GENMASK(h, l)
+#define GEN_RANGE(l, h) GENMASK((h) - 1, (l) - 1)
 
 static const struct register_whitelist {
 	i915_reg_t offset_ldw, offset_udw;
@@ -1414,7 +1409,7 @@ static const struct register_whitelist {
 int i915_reg_read_ioctl(struct drm_device *dev,
 			void *data, struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_reg_read *reg = data;
 	struct register_whitelist const *entry = whitelist;
 	unsigned size;
@@ -1423,7 +1418,7 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 
 	for (i = 0; i < ARRAY_SIZE(whitelist); i++, entry++) {
 		if (i915_mmio_reg_offset(entry->offset_ldw) == (reg->offset & -entry->size) &&
-		    (1 << INTEL_INFO(dev)->gen & entry->gen_bitmask))
+		    (INTEL_INFO(dev)->gen_mask & entry->gen_bitmask))
 			break;
 	}
 
@@ -1467,83 +1462,47 @@ out:
 	return ret;
 }
 
-int i915_get_reset_stats_ioctl(struct drm_device *dev,
-			       void *data, struct drm_file *file)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_reset_stats *args = data;
-	struct i915_ctx_hang_stats *hs;
-	struct intel_context *ctx;
-	int ret;
-
-	if (args->flags || args->pad)
-		return -EINVAL;
-
-	if (args->ctx_id == DEFAULT_CONTEXT_HANDLE && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
-
-	ctx = i915_gem_context_get(file->driver_priv, args->ctx_id);
-	if (IS_ERR(ctx)) {
-		mutex_unlock(&dev->struct_mutex);
-		return PTR_ERR(ctx);
-	}
-	hs = &ctx->hang_stats;
-
-	if (capable(CAP_SYS_ADMIN))
-		args->reset_count = i915_reset_count(&dev_priv->gpu_error);
-	else
-		args->reset_count = 0;
-
-	args->batch_active = hs->batch_active;
-	args->batch_pending = hs->batch_pending;
-
-	mutex_unlock(&dev->struct_mutex);
-
-	return 0;
-}
-
-static int i915_reset_complete(struct drm_device *dev)
+static int i915_reset_complete(struct pci_dev *pdev)
 {
 	u8 gdrst;
-	pci_read_config_byte(dev->pdev, I915_GDRST, &gdrst);
+	pci_read_config_byte(pdev, I915_GDRST, &gdrst);
 	return (gdrst & GRDOM_RESET_STATUS) == 0;
 }
 
-static int i915_do_reset(struct drm_device *dev, unsigned engine_mask)
+static int i915_do_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 {
+	struct pci_dev *pdev = dev_priv->drm.pdev;
+
 	/* assert reset for at least 20 usec */
-	pci_write_config_byte(dev->pdev, I915_GDRST, GRDOM_RESET_ENABLE);
+	pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE);
 	udelay(20);
-	pci_write_config_byte(dev->pdev, I915_GDRST, 0);
+	pci_write_config_byte(pdev, I915_GDRST, 0);
 
-	return wait_for(i915_reset_complete(dev), 500);
+	return wait_for(i915_reset_complete(pdev), 500);
 }
 
-static int g4x_reset_complete(struct drm_device *dev)
+static int g4x_reset_complete(struct pci_dev *pdev)
 {
 	u8 gdrst;
-	pci_read_config_byte(dev->pdev, I915_GDRST, &gdrst);
+	pci_read_config_byte(pdev, I915_GDRST, &gdrst);
 	return (gdrst & GRDOM_RESET_ENABLE) == 0;
 }
 
-static int g33_do_reset(struct drm_device *dev, unsigned engine_mask)
+static int g33_do_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 {
-	pci_write_config_byte(dev->pdev, I915_GDRST, GRDOM_RESET_ENABLE);
-	return wait_for(g4x_reset_complete(dev), 500);
+	struct pci_dev *pdev = dev_priv->drm.pdev;
+	pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE);
+	return wait_for(g4x_reset_complete(pdev), 500);
 }
 
-static int g4x_do_reset(struct drm_device *dev, unsigned engine_mask)
+static int g4x_do_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct pci_dev *pdev = dev_priv->drm.pdev;
 	int ret;
 
-	pci_write_config_byte(dev->pdev, I915_GDRST,
+	pci_write_config_byte(pdev, I915_GDRST,
 			      GRDOM_RENDER | GRDOM_RESET_ENABLE);
-	ret =  wait_for(g4x_reset_complete(dev), 500);
+	ret =  wait_for(g4x_reset_complete(pdev), 500);
 	if (ret)
 		return ret;
 
@@ -1551,9 +1510,9 @@ static int g4x_do_reset(struct drm_device *dev, unsigned engine_mask)
 	I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) | VCP_UNIT_CLOCK_GATE_DISABLE);
 	POSTING_READ(VDECCLK_GATE_D);
 
-	pci_write_config_byte(dev->pdev, I915_GDRST,
+	pci_write_config_byte(pdev, I915_GDRST,
 			      GRDOM_MEDIA | GRDOM_RESET_ENABLE);
-	ret =  wait_for(g4x_reset_complete(dev), 500);
+	ret =  wait_for(g4x_reset_complete(pdev), 500);
 	if (ret)
 		return ret;
 
@@ -1561,27 +1520,29 @@ static int g4x_do_reset(struct drm_device *dev, unsigned engine_mask)
 	I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) & ~VCP_UNIT_CLOCK_GATE_DISABLE);
 	POSTING_READ(VDECCLK_GATE_D);
 
-	pci_write_config_byte(dev->pdev, I915_GDRST, 0);
+	pci_write_config_byte(pdev, I915_GDRST, 0);
 
 	return 0;
 }
 
-static int ironlake_do_reset(struct drm_device *dev, unsigned engine_mask)
+static int ironlake_do_reset(struct drm_i915_private *dev_priv,
+			     unsigned engine_mask)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
 	I915_WRITE(ILK_GDSR,
 		   ILK_GRDOM_RENDER | ILK_GRDOM_RESET_ENABLE);
-	ret = wait_for((I915_READ(ILK_GDSR) &
-			ILK_GRDOM_RESET_ENABLE) == 0, 500);
+	ret = intel_wait_for_register(dev_priv,
+				      ILK_GDSR, ILK_GRDOM_RESET_ENABLE, 0,
+				      500);
 	if (ret)
 		return ret;
 
 	I915_WRITE(ILK_GDSR,
 		   ILK_GRDOM_MEDIA | ILK_GRDOM_RESET_ENABLE);
-	ret = wait_for((I915_READ(ILK_GDSR) &
-			ILK_GRDOM_RESET_ENABLE) == 0, 500);
+	ret = intel_wait_for_register(dev_priv,
+				      ILK_GDSR, ILK_GRDOM_RESET_ENABLE, 0,
+				      500);
 	if (ret)
 		return ret;
 
@@ -1594,25 +1555,21 @@ static int ironlake_do_reset(struct drm_device *dev, unsigned engine_mask)
 static int gen6_hw_domain_reset(struct drm_i915_private *dev_priv,
 				u32 hw_domain_mask)
 {
-	int ret;
-
 	/* GEN6_GDRST is not in the gt power well, no need to check
 	 * for fifo space for the write or forcewake the chip for
 	 * the read
 	 */
 	__raw_i915_write32(dev_priv, GEN6_GDRST, hw_domain_mask);
 
-#define ACKED ((__raw_i915_read32(dev_priv, GEN6_GDRST) & hw_domain_mask) == 0)
 	/* Spin waiting for the device to ack the reset requests */
-	ret = wait_for(ACKED, 500);
-#undef ACKED
-
-	return ret;
+	return intel_wait_for_register_fw(dev_priv,
+					  GEN6_GDRST, hw_domain_mask, 0,
+					  500);
 }
 
 /**
  * gen6_reset_engines - reset individual engines
- * @dev: DRM device
+ * @dev_priv: i915 device
  * @engine_mask: mask of intel_ring_flag() engines or ALL_ENGINES for full reset
  *
  * This function will reset the individual engines that are set in engine_mask.
@@ -1623,9 +1580,9 @@ static int gen6_hw_domain_reset(struct drm_i915_private *dev_priv,
  *
  * Returns 0 on success, nonzero on error.
  */
-static int gen6_reset_engines(struct drm_device *dev, unsigned engine_mask)
+static int gen6_reset_engines(struct drm_i915_private *dev_priv,
+			      unsigned engine_mask)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
 	const u32 hw_engine_mask[I915_NUM_ENGINES] = {
 		[RCS] = GEN6_GRDOM_RENDER,
@@ -1647,33 +1604,94 @@ static int gen6_reset_engines(struct drm_device *dev, unsigned engine_mask)
 
 	ret = gen6_hw_domain_reset(dev_priv, hw_mask);
 
-	intel_uncore_forcewake_reset(dev, true);
+	intel_uncore_forcewake_reset(dev_priv, true);
 
 	return ret;
 }
 
-static int wait_for_register_fw(struct drm_i915_private *dev_priv,
-				i915_reg_t reg,
-				const u32 mask,
-				const u32 value,
-				const unsigned long timeout_ms)
+/**
+ * intel_wait_for_register_fw - wait until register matches expected state
+ * @dev_priv: the i915 device
+ * @reg: the register to read
+ * @mask: mask to apply to register value
+ * @value: expected value
+ * @timeout_ms: timeout in millisecond
+ *
+ * This routine waits until the target register @reg contains the expected
+ * @value after applying the @mask, i.e. it waits until
+ *   (I915_READ_FW(@reg) & @mask) == @value
+ * Otherwise, the wait will timeout after @timeout_ms milliseconds.
+ *
+ * Note that this routine assumes the caller holds forcewake asserted, it is
+ * not suitable for very long waits. See intel_wait_for_register() if you
+ * wish to wait without holding forcewake for the duration (i.e. you expect
+ * the wait to be slow).
+ *
+ * Returns 0 if the register matches the desired condition, or -ETIMEOUT.
+ */
+int intel_wait_for_register_fw(struct drm_i915_private *dev_priv,
+			       i915_reg_t reg,
+			       const u32 mask,
+			       const u32 value,
+			       const unsigned long timeout_ms)
+{
+#define done ((I915_READ_FW(reg) & mask) == value)
+	int ret = wait_for_us(done, 2);
+	if (ret)
+		ret = wait_for(done, timeout_ms);
+	return ret;
+#undef done
+}
+
+/**
+ * intel_wait_for_register - wait until register matches expected state
+ * @dev_priv: the i915 device
+ * @reg: the register to read
+ * @mask: mask to apply to register value
+ * @value: expected value
+ * @timeout_ms: timeout in millisecond
+ *
+ * This routine waits until the target register @reg contains the expected
+ * @value after applying the @mask, i.e. it waits until
+ *   (I915_READ(@reg) & @mask) == @value
+ * Otherwise, the wait will timeout after @timeout_ms milliseconds.
+ *
+ * Returns 0 if the register matches the desired condition, or -ETIMEOUT.
+ */
+int intel_wait_for_register(struct drm_i915_private *dev_priv,
+			    i915_reg_t reg,
+			    const u32 mask,
+			    const u32 value,
+			    const unsigned long timeout_ms)
 {
-	return wait_for((I915_READ_FW(reg) & mask) == value, timeout_ms);
+
+	unsigned fw =
+		intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ);
+	int ret;
+
+	intel_uncore_forcewake_get(dev_priv, fw);
+	ret = wait_for_us((I915_READ_FW(reg) & mask) == value, 2);
+	intel_uncore_forcewake_put(dev_priv, fw);
+	if (ret)
+		ret = wait_for((I915_READ_NOTRACE(reg) & mask) == value,
+			       timeout_ms);
+
+	return ret;
 }
 
 static int gen8_request_engine_reset(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *dev_priv = engine->i915;
 	int ret;
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
 
 	I915_WRITE_FW(RING_RESET_CTL(engine->mmio_base),
 		      _MASKED_BIT_ENABLE(RESET_CTL_REQUEST_RESET));
 
-	ret = wait_for_register_fw(dev_priv,
-				   RING_RESET_CTL(engine->mmio_base),
-				   RESET_CTL_READY_TO_RESET,
-				   RESET_CTL_READY_TO_RESET,
-				   700);
+	ret = intel_wait_for_register_fw(dev_priv,
+					 RING_RESET_CTL(engine->mmio_base),
+					 RESET_CTL_READY_TO_RESET,
+					 RESET_CTL_READY_TO_RESET,
+					 700);
 	if (ret)
 		DRM_ERROR("%s: reset request timeout\n", engine->name);
 
@@ -1682,22 +1700,22 @@ static int gen8_request_engine_reset(struct intel_engine_cs *engine)
 
 static void gen8_unrequest_engine_reset(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	struct drm_i915_private *dev_priv = engine->i915;
 
 	I915_WRITE_FW(RING_RESET_CTL(engine->mmio_base),
 		      _MASKED_BIT_DISABLE(RESET_CTL_REQUEST_RESET));
 }
 
-static int gen8_reset_engines(struct drm_device *dev, unsigned engine_mask)
+static int gen8_reset_engines(struct drm_i915_private *dev_priv,
+			      unsigned engine_mask)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *engine;
 
 	for_each_engine_masked(engine, dev_priv, engine_mask)
 		if (gen8_request_engine_reset(engine))
 			goto not_ready;
 
-	return gen6_reset_engines(dev, engine_mask);
+	return gen6_reset_engines(dev_priv, engine_mask);
 
 not_ready:
 	for_each_engine_masked(engine, dev_priv, engine_mask)
@@ -1706,35 +1724,35 @@ not_ready:
 	return -EIO;
 }
 
-static int (*intel_get_gpu_reset(struct drm_device *dev))(struct drm_device *,
-							  unsigned engine_mask)
+typedef int (*reset_func)(struct drm_i915_private *, unsigned engine_mask);
+
+static reset_func intel_get_gpu_reset(struct drm_i915_private *dev_priv)
 {
 	if (!i915.reset)
 		return NULL;
 
-	if (INTEL_INFO(dev)->gen >= 8)
+	if (INTEL_INFO(dev_priv)->gen >= 8)
 		return gen8_reset_engines;
-	else if (INTEL_INFO(dev)->gen >= 6)
+	else if (INTEL_INFO(dev_priv)->gen >= 6)
 		return gen6_reset_engines;
-	else if (IS_GEN5(dev))
+	else if (IS_GEN5(dev_priv))
 		return ironlake_do_reset;
-	else if (IS_G4X(dev))
+	else if (IS_G4X(dev_priv))
 		return g4x_do_reset;
-	else if (IS_G33(dev))
+	else if (IS_G33(dev_priv))
 		return g33_do_reset;
-	else if (INTEL_INFO(dev)->gen >= 3)
+	else if (INTEL_INFO(dev_priv)->gen >= 3)
 		return i915_do_reset;
 	else
 		return NULL;
 }
 
-int intel_gpu_reset(struct drm_device *dev, unsigned engine_mask)
+int intel_gpu_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	int (*reset)(struct drm_device *, unsigned);
+	reset_func reset;
 	int ret;
 
-	reset = intel_get_gpu_reset(dev);
+	reset = intel_get_gpu_reset(dev_priv);
 	if (reset == NULL)
 		return -ENODEV;
 
@@ -1742,15 +1760,15 @@ int intel_gpu_reset(struct drm_device *dev, unsigned engine_mask)
 	 * request may be dropped and never completes (causing -EIO).
 	 */
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
-	ret = reset(dev, engine_mask);
+	ret = reset(dev_priv, engine_mask);
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
 	return ret;
 }
 
-bool intel_has_gpu_reset(struct drm_device *dev)
+bool intel_has_gpu_reset(struct drm_i915_private *dev_priv)
 {
-	return intel_get_gpu_reset(dev) != NULL;
+	return intel_get_gpu_reset(dev_priv) != NULL;
 }
 
 int intel_guc_reset(struct drm_i915_private *dev_priv)
@@ -1758,7 +1776,7 @@ int intel_guc_reset(struct drm_i915_private *dev_priv)
 	int ret;
 	unsigned long irqflags;
 
-	if (!i915.enable_guc_submission)
+	if (!HAS_GUC(dev_priv))
 		return -EINVAL;
 
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
@@ -1802,10 +1820,10 @@ intel_uncore_forcewake_for_read(struct drm_i915_private *dev_priv,
 {
 	enum forcewake_domains fw_domains;
 
-	if (intel_vgpu_active(dev_priv->dev))
+	if (intel_vgpu_active(dev_priv))
 		return 0;
 
-	switch (INTEL_INFO(dev_priv)->gen) {
+	switch (INTEL_GEN(dev_priv)) {
 	case 9:
 		fw_domains = __gen9_reg_read_fw_domains(i915_mmio_reg_offset(reg));
 		break;
@@ -1842,10 +1860,10 @@ intel_uncore_forcewake_for_write(struct drm_i915_private *dev_priv,
 {
 	enum forcewake_domains fw_domains;
 
-	if (intel_vgpu_active(dev_priv->dev))
+	if (intel_vgpu_active(dev_priv))
 		return 0;
 
-	switch (INTEL_INFO(dev_priv)->gen) {
+	switch (INTEL_GEN(dev_priv)) {
 	case 9:
 		fw_domains = __gen9_reg_write_fw_domains(i915_mmio_reg_offset(reg));
 		break;
diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h
index 44fb0b35eed3..68db9621f1f0 100644
--- a/drivers/gpu/drm/i915/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/intel_vbt_defs.h
@@ -447,10 +447,16 @@ struct bdb_lfp_backlight_data_entry {
 	u8 obsolete3;
 } __packed;
 
+struct bdb_lfp_backlight_control_method {
+	u8 type:4;
+	u8 controller:4;
+} __packed;
+
 struct bdb_lfp_backlight_data {
 	u8 entry_size;
 	struct bdb_lfp_backlight_data_entry data[16];
 	u8 level[16];
+	struct bdb_lfp_backlight_control_method backlight_control[16];
 } __packed;
 
 struct aimdb_header {
diff --git a/drivers/gpu/drm/imx/Kconfig b/drivers/gpu/drm/imx/Kconfig
index a1844b50546c..f2c9ae822149 100644
--- a/drivers/gpu/drm/imx/Kconfig
+++ b/drivers/gpu/drm/imx/Kconfig
@@ -1,7 +1,6 @@
 config DRM_IMX
 	tristate "DRM Support for Freescale i.MX"
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select VIDEOMODE_HELPERS
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_CMA_HELPER
diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c
index a24631fdf4ad..359cd2765552 100644
--- a/drivers/gpu/drm/imx/dw_hdmi-imx.c
+++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c
@@ -28,6 +28,11 @@ struct imx_hdmi {
 	struct regmap *regmap;
 };
 
+static inline struct imx_hdmi *enc_to_imx_hdmi(struct drm_encoder *e)
+{
+	return container_of(e, struct imx_hdmi, encoder);
+}
+
 static const struct dw_hdmi_mpll_config imx_mpll_cfg[] = {
 	{
 		45250000, {
@@ -109,15 +114,9 @@ static void dw_hdmi_imx_encoder_disable(struct drm_encoder *encoder)
 {
 }
 
-static void dw_hdmi_imx_encoder_mode_set(struct drm_encoder *encoder,
-					 struct drm_display_mode *mode,
-					 struct drm_display_mode *adj_mode)
+static void dw_hdmi_imx_encoder_enable(struct drm_encoder *encoder)
 {
-}
-
-static void dw_hdmi_imx_encoder_commit(struct drm_encoder *encoder)
-{
-	struct imx_hdmi *hdmi = container_of(encoder, struct imx_hdmi, encoder);
+	struct imx_hdmi *hdmi = enc_to_imx_hdmi(encoder);
 	int mux = drm_of_encoder_active_port_id(hdmi->dev->of_node, encoder);
 
 	regmap_update_bits(hdmi->regmap, IOMUXC_GPR3,
@@ -125,16 +124,23 @@ static void dw_hdmi_imx_encoder_commit(struct drm_encoder *encoder)
 			   mux << IMX6Q_GPR3_HDMI_MUX_CTL_SHIFT);
 }
 
-static void dw_hdmi_imx_encoder_prepare(struct drm_encoder *encoder)
+static int dw_hdmi_imx_atomic_check(struct drm_encoder *encoder,
+				    struct drm_crtc_state *crtc_state,
+				    struct drm_connector_state *conn_state)
 {
-	imx_drm_set_bus_format(encoder, MEDIA_BUS_FMT_RGB888_1X24);
+	struct imx_crtc_state *imx_crtc_state = to_imx_crtc_state(crtc_state);
+
+	imx_crtc_state->bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+	imx_crtc_state->di_hsync_pin = 2;
+	imx_crtc_state->di_vsync_pin = 3;
+
+	return 0;
 }
 
 static const struct drm_encoder_helper_funcs dw_hdmi_imx_encoder_helper_funcs = {
-	.mode_set   = dw_hdmi_imx_encoder_mode_set,
-	.prepare    = dw_hdmi_imx_encoder_prepare,
-	.commit     = dw_hdmi_imx_encoder_commit,
+	.enable     = dw_hdmi_imx_encoder_enable,
 	.disable    = dw_hdmi_imx_encoder_disable,
+	.atomic_check = dw_hdmi_imx_atomic_check,
 };
 
 static const struct drm_encoder_funcs dw_hdmi_imx_encoder_funcs = {
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 82656654fb21..9f7dafce3a4c 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -15,10 +15,14 @@
  */
 #include <linux/component.h>
 #include <linux/device.h>
+#include <linux/dma-buf.h>
 #include <linux/fb.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/reservation.h>
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_gem_cma_helper.h>
@@ -41,6 +45,7 @@ struct imx_drm_device {
 	struct imx_drm_crtc			*crtc[MAX_CRTC];
 	unsigned int				pipes;
 	struct drm_fbdev_cma			*fbhelper;
+	struct drm_atomic_state			*state;
 };
 
 struct imx_drm_crtc {
@@ -85,45 +90,6 @@ static int imx_drm_driver_unload(struct drm_device *drm)
 	return 0;
 }
 
-static struct imx_drm_crtc *imx_drm_find_crtc(struct drm_crtc *crtc)
-{
-	struct imx_drm_device *imxdrm = crtc->dev->dev_private;
-	unsigned i;
-
-	for (i = 0; i < MAX_CRTC; i++)
-		if (imxdrm->crtc[i] && imxdrm->crtc[i]->crtc == crtc)
-			return imxdrm->crtc[i];
-
-	return NULL;
-}
-
-int imx_drm_set_bus_config(struct drm_encoder *encoder, u32 bus_format,
-		int hsync_pin, int vsync_pin, u32 bus_flags)
-{
-	struct imx_drm_crtc_helper_funcs *helper;
-	struct imx_drm_crtc *imx_crtc;
-
-	imx_crtc = imx_drm_find_crtc(encoder->crtc);
-	if (!imx_crtc)
-		return -EINVAL;
-
-	helper = &imx_crtc->imx_drm_helper_funcs;
-	if (helper->set_interface_pix_fmt)
-		return helper->set_interface_pix_fmt(encoder->crtc,
-					bus_format, hsync_pin, vsync_pin,
-					bus_flags);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(imx_drm_set_bus_config);
-
-int imx_drm_set_bus_format(struct drm_encoder *encoder, u32 bus_format)
-{
-	return imx_drm_set_bus_config(encoder, bus_format, 2, 3,
-				      DRM_BUS_FLAG_DE_HIGH |
-				      DRM_BUS_FLAG_PIXDATA_NEGEDGE);
-}
-EXPORT_SYMBOL_GPL(imx_drm_set_bus_format);
-
 int imx_drm_crtc_vblank_get(struct imx_drm_crtc *imx_drm_crtc)
 {
 	return drm_crtc_vblank_get(imx_drm_crtc->crtc);
@@ -208,6 +174,63 @@ static void imx_drm_output_poll_changed(struct drm_device *drm)
 static const struct drm_mode_config_funcs imx_drm_mode_config_funcs = {
 	.fb_create = drm_fb_cma_create,
 	.output_poll_changed = imx_drm_output_poll_changed,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
+static void imx_drm_atomic_commit_tail(struct drm_atomic_state *state)
+{
+	struct drm_device *dev = state->dev;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_plane_state *plane_state;
+	struct drm_gem_cma_object *cma_obj;
+	struct fence *excl;
+	unsigned shared_count;
+	struct fence **shared;
+	unsigned int i, j;
+	int ret;
+
+	/* Wait for fences. */
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		plane_state = crtc->primary->state;
+		if (plane_state->fb) {
+			cma_obj = drm_fb_cma_get_gem_obj(plane_state->fb, 0);
+			if (cma_obj->base.dma_buf) {
+				ret = reservation_object_get_fences_rcu(
+					cma_obj->base.dma_buf->resv, &excl,
+					&shared_count, &shared);
+				if (unlikely(ret))
+					DRM_ERROR("failed to get fences "
+						  "for buffer\n");
+
+				if (excl) {
+					fence_wait(excl, false);
+					fence_put(excl);
+				}
+				for (j = 0; j < shared_count; i++) {
+					fence_wait(shared[j], false);
+					fence_put(shared[j]);
+				}
+			}
+		}
+	}
+
+	drm_atomic_helper_commit_modeset_disables(dev, state);
+
+	drm_atomic_helper_commit_planes(dev, state, true);
+
+	drm_atomic_helper_commit_modeset_enables(dev, state);
+
+	drm_atomic_helper_commit_hw_done(state);
+
+	drm_atomic_helper_wait_for_vblanks(dev, state);
+
+	drm_atomic_helper_cleanup_planes(dev, state);
+}
+
+static struct drm_mode_config_helper_funcs imx_drm_mode_config_helpers = {
+	.atomic_commit_tail = imx_drm_atomic_commit_tail,
 };
 
 /*
@@ -249,6 +272,7 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags)
 	drm->mode_config.max_width = 4096;
 	drm->mode_config.max_height = 4096;
 	drm->mode_config.funcs = &imx_drm_mode_config_funcs;
+	drm->mode_config.helper_private = &imx_drm_mode_config_helpers;
 
 	drm_mode_config_init(drm);
 
@@ -279,6 +303,8 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags)
 		}
 	}
 
+	drm_mode_config_reset(drm);
+
 	/*
 	 * All components are now initialised, so setup the fb helper.
 	 * The fb helper takes copies of key hardware information, so the
@@ -289,7 +315,6 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags)
 		dev_warn(drm->dev, "Invalid legacyfb_depth.  Defaulting to 16bpp\n");
 		legacyfb_depth = 16;
 	}
-	drm_helper_disable_unused_functions(drm);
 	imxdrm->fbhelper = drm_fbdev_cma_init(drm, legacyfb_depth,
 				drm->mode_config.num_crtc, MAX_CRTC);
 	if (IS_ERR(imxdrm->fbhelper)) {
@@ -403,11 +428,11 @@ static const struct drm_ioctl_desc imx_drm_ioctls[] = {
 };
 
 static struct drm_driver imx_drm_driver = {
-	.driver_features	= DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME,
+	.driver_features	= DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME |
+				  DRIVER_ATOMIC,
 	.load			= imx_drm_driver_load,
 	.unload			= imx_drm_driver_unload,
 	.lastclose		= imx_drm_driver_lastclose,
-	.set_busid		= drm_platform_set_busid,
 	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops		= &drm_gem_cma_vm_ops,
 	.dumb_create		= drm_gem_cma_dumb_create,
@@ -492,6 +517,7 @@ static int imx_drm_platform_remove(struct platform_device *pdev)
 static int imx_drm_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct imx_drm_device *imxdrm;
 
 	/* The drm_dev is NULL before .load hook is called */
 	if (drm_dev == NULL)
@@ -499,17 +525,26 @@ static int imx_drm_suspend(struct device *dev)
 
 	drm_kms_helper_poll_disable(drm_dev);
 
+	imxdrm = drm_dev->dev_private;
+	imxdrm->state = drm_atomic_helper_suspend(drm_dev);
+	if (IS_ERR(imxdrm->state)) {
+		drm_kms_helper_poll_enable(drm_dev);
+		return PTR_ERR(imxdrm->state);
+	}
+
 	return 0;
 }
 
 static int imx_drm_resume(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct imx_drm_device *imx_drm;
 
 	if (drm_dev == NULL)
 		return 0;
 
-	drm_helper_resume_force_mode(drm_dev);
+	imx_drm = drm_dev->dev_private;
+	drm_atomic_helper_resume(drm_dev, imx_drm->state);
 	drm_kms_helper_poll_enable(drm_dev);
 
 	return 0;
diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h
index 74320a1723b7..07d33e45f90f 100644
--- a/drivers/gpu/drm/imx/imx-drm.h
+++ b/drivers/gpu/drm/imx/imx-drm.h
@@ -15,12 +15,22 @@ struct platform_device;
 
 unsigned int imx_drm_crtc_id(struct imx_drm_crtc *crtc);
 
+struct imx_crtc_state {
+	struct drm_crtc_state			base;
+	u32					bus_format;
+	u32					bus_flags;
+	int					di_hsync_pin;
+	int					di_vsync_pin;
+};
+
+static inline struct imx_crtc_state *to_imx_crtc_state(struct drm_crtc_state *s)
+{
+	return container_of(s, struct imx_crtc_state, base);
+}
+
 struct imx_drm_crtc_helper_funcs {
 	int (*enable_vblank)(struct drm_crtc *crtc);
 	void (*disable_vblank)(struct drm_crtc *crtc);
-	int (*set_interface_pix_fmt)(struct drm_crtc *crtc,
-			u32 bus_format, int hsync_pin, int vsync_pin,
-			u32 bus_flags);
 	const struct drm_crtc_helper_funcs *crtc_helper_funcs;
 	const struct drm_crtc_funcs *crtc_funcs;
 };
@@ -42,11 +52,6 @@ void imx_drm_mode_config_init(struct drm_device *drm);
 
 struct drm_gem_cma_object *imx_drm_fb_get_obj(struct drm_framebuffer *fb);
 
-int imx_drm_set_bus_config(struct drm_encoder *encoder, u32 bus_format,
-		int hsync_pin, int vsync_pin, u32 bus_flags);
-int imx_drm_set_bus_format(struct drm_encoder *encoder,
-		u32 bus_format);
-
 int imx_drm_encoder_parse_of(struct drm_device *drm,
 	struct drm_encoder *encoder, struct device_node *np);
 
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index beff793bb717..b03919ed60ba 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -17,6 +17,8 @@
 #include <linux/clk.h>
 #include <linux/component.h>
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_of.h>
@@ -49,9 +51,6 @@
 #define LDB_DI1_VS_POL_ACT_LOW		(1 << 10)
 #define LDB_BGREF_RMODE_INT		(1 << 15)
 
-#define con_to_imx_ldb_ch(x) container_of(x, struct imx_ldb_channel, connector)
-#define enc_to_imx_ldb_ch(x) container_of(x, struct imx_ldb_channel, encoder)
-
 struct imx_ldb;
 
 struct imx_ldb_channel {
@@ -66,9 +65,19 @@ struct imx_ldb_channel {
 	int edid_len;
 	struct drm_display_mode mode;
 	int mode_valid;
-	int bus_format;
+	u32 bus_format;
 };
 
+static inline struct imx_ldb_channel *con_to_imx_ldb_ch(struct drm_connector *c)
+{
+	return container_of(c, struct imx_ldb_channel, connector);
+}
+
+static inline struct imx_ldb_channel *enc_to_imx_ldb_ch(struct drm_encoder *e)
+{
+	return container_of(e, struct imx_ldb_channel, encoder);
+}
+
 struct bus_mux {
 	int reg;
 	int shift;
@@ -93,6 +102,32 @@ static enum drm_connector_status imx_ldb_connector_detect(
 	return connector_status_connected;
 }
 
+static void imx_ldb_ch_set_bus_format(struct imx_ldb_channel *imx_ldb_ch,
+				      u32 bus_format)
+{
+	struct imx_ldb *ldb = imx_ldb_ch->ldb;
+	int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN;
+
+	switch (bus_format) {
+	case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG:
+		break;
+	case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG:
+		if (imx_ldb_ch->chno == 0 || dual)
+			ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH0_24;
+		if (imx_ldb_ch->chno == 1 || dual)
+			ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH1_24;
+		break;
+	case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA:
+		if (imx_ldb_ch->chno == 0 || dual)
+			ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH0_24 |
+					 LDB_BIT_MAP_CH0_JEIDA;
+		if (imx_ldb_ch->chno == 1 || dual)
+			ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH1_24 |
+					 LDB_BIT_MAP_CH1_JEIDA;
+		break;
+	}
+}
+
 static int imx_ldb_connector_get_modes(struct drm_connector *connector)
 {
 	struct imx_ldb_channel *imx_ldb_ch = con_to_imx_ldb_ch(connector);
@@ -100,11 +135,7 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector)
 
 	if (imx_ldb_ch->panel && imx_ldb_ch->panel->funcs &&
 	    imx_ldb_ch->panel->funcs->get_modes) {
-		struct drm_display_info *di = &connector->display_info;
-
 		num_modes = imx_ldb_ch->panel->funcs->get_modes(imx_ldb_ch->panel);
-		if (!imx_ldb_ch->bus_format && di->num_bus_formats)
-			imx_ldb_ch->bus_format = di->bus_formats[0];
 		if (num_modes > 0)
 			return num_modes;
 	}
@@ -141,10 +172,6 @@ static struct drm_encoder *imx_ldb_connector_best_encoder(
 	return &imx_ldb_ch->encoder;
 }
 
-static void imx_ldb_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-}
-
 static void imx_ldb_set_clock(struct imx_ldb *ldb, int mux, int chno,
 		unsigned long serial_clk, unsigned long di_clk)
 {
@@ -173,43 +200,7 @@ static void imx_ldb_set_clock(struct imx_ldb *ldb, int mux, int chno,
 			chno);
 }
 
-static void imx_ldb_encoder_prepare(struct drm_encoder *encoder)
-{
-	struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder);
-	struct imx_ldb *ldb = imx_ldb_ch->ldb;
-	int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN;
-	u32 bus_format;
-
-	switch (imx_ldb_ch->bus_format) {
-	default:
-		dev_warn(ldb->dev,
-			 "could not determine data mapping, default to 18-bit \"spwg\"\n");
-		/* fallthrough */
-	case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG:
-		bus_format = MEDIA_BUS_FMT_RGB666_1X18;
-		break;
-	case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG:
-		bus_format = MEDIA_BUS_FMT_RGB888_1X24;
-		if (imx_ldb_ch->chno == 0 || dual)
-			ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH0_24;
-		if (imx_ldb_ch->chno == 1 || dual)
-			ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH1_24;
-		break;
-	case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA:
-		bus_format = MEDIA_BUS_FMT_RGB888_1X24;
-		if (imx_ldb_ch->chno == 0 || dual)
-			ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH0_24 |
-					 LDB_BIT_MAP_CH0_JEIDA;
-		if (imx_ldb_ch->chno == 1 || dual)
-			ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH1_24 |
-					 LDB_BIT_MAP_CH1_JEIDA;
-		break;
-	}
-
-	imx_drm_set_bus_format(encoder, bus_format);
-}
-
-static void imx_ldb_encoder_commit(struct drm_encoder *encoder)
+static void imx_ldb_encoder_enable(struct drm_encoder *encoder)
 {
 	struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder);
 	struct imx_ldb *ldb = imx_ldb_ch->ldb;
@@ -219,8 +210,13 @@ static void imx_ldb_encoder_commit(struct drm_encoder *encoder)
 	drm_panel_prepare(imx_ldb_ch->panel);
 
 	if (dual) {
+		clk_set_parent(ldb->clk_sel[mux], ldb->clk[0]);
+		clk_set_parent(ldb->clk_sel[mux], ldb->clk[1]);
+
 		clk_prepare_enable(ldb->clk[0]);
 		clk_prepare_enable(ldb->clk[1]);
+	} else {
+		clk_set_parent(ldb->clk_sel[mux], ldb->clk[imx_ldb_ch->chno]);
 	}
 
 	if (imx_ldb_ch == &ldb->channel[0] || dual) {
@@ -265,6 +261,7 @@ static void imx_ldb_encoder_mode_set(struct drm_encoder *encoder,
 	unsigned long serial_clk;
 	unsigned long di_clk = mode->clock * 1000;
 	int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder);
+	u32 bus_format = imx_ldb_ch->bus_format;
 
 	if (mode->clock > 170000) {
 		dev_warn(ldb->dev,
@@ -286,18 +283,33 @@ static void imx_ldb_encoder_mode_set(struct drm_encoder *encoder,
 	}
 
 	/* FIXME - assumes straight connections DI0 --> CH0, DI1 --> CH1 */
-	if (imx_ldb_ch == &ldb->channel[0]) {
+	if (imx_ldb_ch == &ldb->channel[0] || dual) {
 		if (mode->flags & DRM_MODE_FLAG_NVSYNC)
 			ldb->ldb_ctrl |= LDB_DI0_VS_POL_ACT_LOW;
 		else if (mode->flags & DRM_MODE_FLAG_PVSYNC)
 			ldb->ldb_ctrl &= ~LDB_DI0_VS_POL_ACT_LOW;
 	}
-	if (imx_ldb_ch == &ldb->channel[1]) {
+	if (imx_ldb_ch == &ldb->channel[1] || dual) {
 		if (mode->flags & DRM_MODE_FLAG_NVSYNC)
 			ldb->ldb_ctrl |= LDB_DI1_VS_POL_ACT_LOW;
 		else if (mode->flags & DRM_MODE_FLAG_PVSYNC)
 			ldb->ldb_ctrl &= ~LDB_DI1_VS_POL_ACT_LOW;
 	}
+
+	if (!bus_format) {
+		struct drm_connector *connector;
+
+		drm_for_each_connector(connector, encoder->dev) {
+			struct drm_display_info *di = &connector->display_info;
+
+			if (connector->encoder == encoder &&
+			    di->num_bus_formats) {
+				bus_format = di->bus_formats[0];
+				break;
+			}
+		}
+	}
+	imx_ldb_ch_set_bus_format(imx_ldb_ch, bus_format);
 }
 
 static void imx_ldb_encoder_disable(struct drm_encoder *encoder)
@@ -357,11 +369,45 @@ static void imx_ldb_encoder_disable(struct drm_encoder *encoder)
 	drm_panel_unprepare(imx_ldb_ch->panel);
 }
 
+static int imx_ldb_encoder_atomic_check(struct drm_encoder *encoder,
+					struct drm_crtc_state *crtc_state,
+					struct drm_connector_state *conn_state)
+{
+	struct imx_crtc_state *imx_crtc_state = to_imx_crtc_state(crtc_state);
+	struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder);
+	struct drm_display_info *di = &conn_state->connector->display_info;
+	u32 bus_format = imx_ldb_ch->bus_format;
+
+	/* Bus format description in DT overrides connector display info. */
+	if (!bus_format && di->num_bus_formats)
+		bus_format = di->bus_formats[0];
+	switch (bus_format) {
+	case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG:
+		imx_crtc_state->bus_format = MEDIA_BUS_FMT_RGB666_1X18;
+		break;
+	case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG:
+	case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA:
+		imx_crtc_state->bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	imx_crtc_state->di_hsync_pin = 2;
+	imx_crtc_state->di_vsync_pin = 3;
+
+	return 0;
+}
+
+
 static const struct drm_connector_funcs imx_ldb_connector_funcs = {
-	.dpms = drm_helper_connector_dpms,
+	.dpms = drm_atomic_helper_connector_dpms,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.detect = imx_ldb_connector_detect,
 	.destroy = imx_drm_connector_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
 static const struct drm_connector_helper_funcs imx_ldb_connector_helper_funcs = {
@@ -374,11 +420,10 @@ static const struct drm_encoder_funcs imx_ldb_encoder_funcs = {
 };
 
 static const struct drm_encoder_helper_funcs imx_ldb_encoder_helper_funcs = {
-	.dpms = imx_ldb_encoder_dpms,
-	.prepare = imx_ldb_encoder_prepare,
-	.commit = imx_ldb_encoder_commit,
 	.mode_set = imx_ldb_encoder_mode_set,
+	.enable = imx_ldb_encoder_enable,
 	.disable = imx_ldb_encoder_disable,
+	.atomic_check = imx_ldb_encoder_atomic_check,
 };
 
 static int imx_ldb_get_clk(struct imx_ldb *ldb, int chno)
@@ -400,10 +445,10 @@ static int imx_ldb_register(struct drm_device *drm,
 	struct imx_ldb_channel *imx_ldb_ch)
 {
 	struct imx_ldb *ldb = imx_ldb_ch->ldb;
+	struct drm_encoder *encoder = &imx_ldb_ch->encoder;
 	int ret;
 
-	ret = imx_drm_encoder_parse_of(drm, &imx_ldb_ch->encoder,
-				       imx_ldb_ch->child);
+	ret = imx_drm_encoder_parse_of(drm, encoder, imx_ldb_ch->child);
 	if (ret)
 		return ret;
 
@@ -417,9 +462,8 @@ static int imx_ldb_register(struct drm_device *drm,
 			return ret;
 	}
 
-	drm_encoder_helper_add(&imx_ldb_ch->encoder,
-			&imx_ldb_encoder_helper_funcs);
-	drm_encoder_init(drm, &imx_ldb_ch->encoder, &imx_ldb_encoder_funcs,
+	drm_encoder_helper_add(encoder, &imx_ldb_encoder_helper_funcs);
+	drm_encoder_init(drm, encoder, &imx_ldb_encoder_funcs,
 			 DRM_MODE_ENCODER_LVDS, NULL);
 
 	drm_connector_helper_add(&imx_ldb_ch->connector,
@@ -427,11 +471,14 @@ static int imx_ldb_register(struct drm_device *drm,
 	drm_connector_init(drm, &imx_ldb_ch->connector,
 			   &imx_ldb_connector_funcs, DRM_MODE_CONNECTOR_LVDS);
 
-	if (imx_ldb_ch->panel)
-		drm_panel_attach(imx_ldb_ch->panel, &imx_ldb_ch->connector);
+	if (imx_ldb_ch->panel) {
+		ret = drm_panel_attach(imx_ldb_ch->panel,
+				       &imx_ldb_ch->connector);
+		if (ret)
+			return ret;
+	}
 
-	drm_mode_connector_attach_encoder(&imx_ldb_ch->connector,
-			&imx_ldb_ch->encoder);
+	drm_mode_connector_attach_encoder(&imx_ldb_ch->connector, encoder);
 
 	return 0;
 }
@@ -560,6 +607,7 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 		struct imx_ldb_channel *channel;
 		struct device_node *ddc_node;
 		struct device_node *ep;
+		int bus_format;
 
 		ret = of_property_read_u32(child, "reg", &i);
 		if (ret || i < 0 || i > 1)
@@ -632,21 +680,22 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 			}
 		}
 
-		channel->bus_format = of_get_bus_format(dev, child);
-		if (channel->bus_format == -EINVAL) {
+		bus_format = of_get_bus_format(dev, child);
+		if (bus_format == -EINVAL) {
 			/*
 			 * If no bus format was specified in the device tree,
 			 * we can still get it from the connected panel later.
 			 */
 			if (channel->panel && channel->panel->funcs &&
 			    channel->panel->funcs->get_modes)
-				channel->bus_format = 0;
+				bus_format = 0;
 		}
-		if (channel->bus_format < 0) {
+		if (bus_format < 0) {
 			dev_err(dev, "could not determine data mapping: %d\n",
-				channel->bus_format);
-			return channel->bus_format;
+				bus_format);
+			return bus_format;
 		}
+		channel->bus_format = bus_format;
 
 		ret = imx_ldb_register(drm, channel);
 		if (ret)
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index baf788121287..5e875944ffa2 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -23,6 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/videodev2.h>
 #include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <video/imx-ipu-v3.h>
@@ -97,9 +98,6 @@
 /* TVE_TST_MODE_REG */
 #define TVE_TVDAC_TEST_MODE_MASK	(0x7 << 0)
 
-#define con_to_tve(x) container_of(x, struct imx_tve, connector)
-#define enc_to_tve(x) container_of(x, struct imx_tve, encoder)
-
 enum {
 	TVE_MODE_TVOUT,
 	TVE_MODE_VGA,
@@ -112,6 +110,8 @@ struct imx_tve {
 	spinlock_t lock;	/* register lock */
 	bool enabled;
 	int mode;
+	int di_hsync_pin;
+	int di_vsync_pin;
 
 	struct regmap *regmap;
 	struct regulator *dac_reg;
@@ -120,10 +120,18 @@ struct imx_tve {
 	struct clk *di_sel_clk;
 	struct clk_hw clk_hw_di;
 	struct clk *di_clk;
-	int vsync_pin;
-	int hsync_pin;
 };
 
+static inline struct imx_tve *con_to_tve(struct drm_connector *c)
+{
+	return container_of(c, struct imx_tve, connector);
+}
+
+static inline struct imx_tve *enc_to_tve(struct drm_encoder *e)
+{
+	return container_of(e, struct imx_tve, encoder);
+}
+
 static void tve_lock(void *__tve)
 __acquires(&tve->lock)
 {
@@ -148,8 +156,7 @@ static void tve_enable(struct imx_tve *tve)
 		tve->enabled = true;
 		clk_prepare_enable(tve->clk);
 		ret = regmap_update_bits(tve->regmap, TVE_COM_CONF_REG,
-					 TVE_IPU_CLK_EN | TVE_EN,
-					 TVE_IPU_CLK_EN | TVE_EN);
+					 TVE_EN, TVE_EN);
 	}
 
 	/* clear interrupt status register */
@@ -172,7 +179,7 @@ static void tve_disable(struct imx_tve *tve)
 	if (tve->enabled) {
 		tve->enabled = false;
 		ret = regmap_update_bits(tve->regmap, TVE_COM_CONF_REG,
-					 TVE_IPU_CLK_EN | TVE_EN, 0);
+					 TVE_EN, 0);
 		clk_disable_unprepare(tve->clk);
 	}
 }
@@ -275,36 +282,6 @@ static struct drm_encoder *imx_tve_connector_best_encoder(
 	return &tve->encoder;
 }
 
-static void imx_tve_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-	struct imx_tve *tve = enc_to_tve(encoder);
-	int ret;
-
-	ret = regmap_update_bits(tve->regmap, TVE_COM_CONF_REG,
-				 TVE_TV_OUT_MODE_MASK, TVE_TV_OUT_DISABLE);
-	if (ret < 0)
-		dev_err(tve->dev, "failed to disable TVOUT: %d\n", ret);
-}
-
-static void imx_tve_encoder_prepare(struct drm_encoder *encoder)
-{
-	struct imx_tve *tve = enc_to_tve(encoder);
-
-	tve_disable(tve);
-
-	switch (tve->mode) {
-	case TVE_MODE_VGA:
-		imx_drm_set_bus_config(encoder, MEDIA_BUS_FMT_GBR888_1X24,
-				       tve->hsync_pin, tve->vsync_pin,
-				       DRM_BUS_FLAG_DE_HIGH |
-				       DRM_BUS_FLAG_PIXDATA_NEGEDGE);
-		break;
-	case TVE_MODE_TVOUT:
-		imx_drm_set_bus_format(encoder, MEDIA_BUS_FMT_YUV8_1X24);
-		break;
-	}
-}
-
 static void imx_tve_encoder_mode_set(struct drm_encoder *encoder,
 				     struct drm_display_mode *orig_mode,
 				     struct drm_display_mode *mode)
@@ -333,6 +310,9 @@ static void imx_tve_encoder_mode_set(struct drm_encoder *encoder,
 			ret);
 	}
 
+	regmap_update_bits(tve->regmap, TVE_COM_CONF_REG,
+			   TVE_IPU_CLK_EN, TVE_IPU_CLK_EN);
+
 	if (tve->mode == TVE_MODE_VGA)
 		ret = tve_setup_vga(tve);
 	else
@@ -341,7 +321,7 @@ static void imx_tve_encoder_mode_set(struct drm_encoder *encoder,
 		dev_err(tve->dev, "failed to set configuration: %d\n", ret);
 }
 
-static void imx_tve_encoder_commit(struct drm_encoder *encoder)
+static void imx_tve_encoder_enable(struct drm_encoder *encoder)
 {
 	struct imx_tve *tve = enc_to_tve(encoder);
 
@@ -355,11 +335,28 @@ static void imx_tve_encoder_disable(struct drm_encoder *encoder)
 	tve_disable(tve);
 }
 
+static int imx_tve_atomic_check(struct drm_encoder *encoder,
+				struct drm_crtc_state *crtc_state,
+				struct drm_connector_state *conn_state)
+{
+	struct imx_crtc_state *imx_crtc_state = to_imx_crtc_state(crtc_state);
+	struct imx_tve *tve = enc_to_tve(encoder);
+
+	imx_crtc_state->bus_format = MEDIA_BUS_FMT_GBR888_1X24;
+	imx_crtc_state->di_hsync_pin = tve->di_hsync_pin;
+	imx_crtc_state->di_vsync_pin = tve->di_vsync_pin;
+
+	return 0;
+}
+
 static const struct drm_connector_funcs imx_tve_connector_funcs = {
-	.dpms = drm_helper_connector_dpms,
+	.dpms = drm_atomic_helper_connector_dpms,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.detect = imx_tve_connector_detect,
 	.destroy = imx_drm_connector_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
 static const struct drm_connector_helper_funcs imx_tve_connector_helper_funcs = {
@@ -373,11 +370,10 @@ static const struct drm_encoder_funcs imx_tve_encoder_funcs = {
 };
 
 static const struct drm_encoder_helper_funcs imx_tve_encoder_helper_funcs = {
-	.dpms = imx_tve_encoder_dpms,
-	.prepare = imx_tve_encoder_prepare,
 	.mode_set = imx_tve_encoder_mode_set,
-	.commit = imx_tve_encoder_commit,
+	.enable = imx_tve_encoder_enable,
 	.disable = imx_tve_encoder_disable,
+	.atomic_check = imx_tve_atomic_check,
 };
 
 static irqreturn_t imx_tve_irq_handler(int irq, void *data)
@@ -495,8 +491,7 @@ static int imx_tve_register(struct drm_device *drm, struct imx_tve *tve)
 	encoder_type = tve->mode == TVE_MODE_VGA ?
 				DRM_MODE_ENCODER_DAC : DRM_MODE_ENCODER_TVDAC;
 
-	ret = imx_drm_encoder_parse_of(drm, &tve->encoder,
-				       tve->dev->of_node);
+	ret = imx_drm_encoder_parse_of(drm, &tve->encoder, tve->dev->of_node);
 	if (ret)
 		return ret;
 
@@ -587,15 +582,15 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data)
 
 	if (tve->mode == TVE_MODE_VGA) {
 		ret = of_property_read_u32(np, "fsl,hsync-pin",
-					   &tve->hsync_pin);
+					   &tve->di_hsync_pin);
 
 		if (ret < 0) {
-			dev_err(dev, "failed to get vsync pin\n");
+			dev_err(dev, "failed to get hsync pin\n");
 			return ret;
 		}
 
-		ret |= of_property_read_u32(np, "fsl,vsync-pin",
-					    &tve->vsync_pin);
+		ret = of_property_read_u32(np, "fsl,vsync-pin",
+					   &tve->di_vsync_pin);
 
 		if (ret < 0) {
 			dev_err(dev, "failed to get vsync pin\n");
@@ -633,7 +628,9 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data)
 
 	tve->dac_reg = devm_regulator_get(dev, "dac");
 	if (!IS_ERR(tve->dac_reg)) {
-		regulator_set_voltage(tve->dac_reg, 2750000, 2750000);
+		ret = regulator_set_voltage(tve->dac_reg, 2750000, 2750000);
+		if (ret)
+			return ret;
 		ret = regulator_enable(tve->dac_reg);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index fc040417e1e8..08e188bc10fc 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -18,12 +18,12 @@
 #include <linux/device.h>
 #include <linux/platform_device.h>
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <linux/fb.h>
 #include <linux/clk.h>
 #include <linux/errno.h>
-#include <linux/reservation.h>
-#include <linux/dma-buf.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_fb_cma_helper.h>
 
@@ -33,23 +33,6 @@
 
 #define DRIVER_DESC		"i.MX IPUv3 Graphics"
 
-enum ipu_flip_status {
-	IPU_FLIP_NONE,
-	IPU_FLIP_PENDING,
-	IPU_FLIP_SUBMITTED,
-};
-
-struct ipu_flip_work {
-	struct work_struct		unref_work;
-	struct drm_gem_object		*bo;
-	struct drm_pending_vblank_event *page_flip_event;
-	struct work_struct		fence_work;
-	struct ipu_crtc			*crtc;
-	struct fence			*excl;
-	unsigned			shared_count;
-	struct fence			**shared;
-};
-
 struct ipu_crtc {
 	struct device		*dev;
 	struct drm_crtc		base;
@@ -60,201 +43,166 @@ struct ipu_crtc {
 
 	struct ipu_dc		*dc;
 	struct ipu_di		*di;
-	int			enabled;
-	enum ipu_flip_status	flip_state;
-	struct workqueue_struct *flip_queue;
-	struct ipu_flip_work	*flip_work;
 	int			irq;
-	u32			bus_format;
-	u32			bus_flags;
-	int			di_hsync_pin;
-	int			di_vsync_pin;
 };
 
-#define to_ipu_crtc(x) container_of(x, struct ipu_crtc, base)
+static inline struct ipu_crtc *to_ipu_crtc(struct drm_crtc *crtc)
+{
+	return container_of(crtc, struct ipu_crtc, base);
+}
 
-static void ipu_fb_enable(struct ipu_crtc *ipu_crtc)
+static void ipu_crtc_enable(struct drm_crtc *crtc)
 {
+	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
 	struct ipu_soc *ipu = dev_get_drvdata(ipu_crtc->dev->parent);
 
-	if (ipu_crtc->enabled)
-		return;
-
 	ipu_dc_enable(ipu);
-	ipu_plane_enable(ipu_crtc->plane[0]);
-	/* Start DC channel and DI after IDMAC */
 	ipu_dc_enable_channel(ipu_crtc->dc);
 	ipu_di_enable(ipu_crtc->di);
-	drm_crtc_vblank_on(&ipu_crtc->base);
-
-	ipu_crtc->enabled = 1;
 }
 
-static void ipu_fb_disable(struct ipu_crtc *ipu_crtc)
+static void ipu_crtc_disable(struct drm_crtc *crtc)
 {
+	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
 	struct ipu_soc *ipu = dev_get_drvdata(ipu_crtc->dev->parent);
 
-	if (!ipu_crtc->enabled)
-		return;
-
-	/* Stop DC channel and DI before IDMAC */
 	ipu_dc_disable_channel(ipu_crtc->dc);
 	ipu_di_disable(ipu_crtc->di);
-	ipu_plane_disable(ipu_crtc->plane[0]);
 	ipu_dc_disable(ipu);
-	drm_crtc_vblank_off(&ipu_crtc->base);
 
-	ipu_crtc->enabled = 0;
+	spin_lock_irq(&crtc->dev->event_lock);
+	if (crtc->state->event) {
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+	}
+	spin_unlock_irq(&crtc->dev->event_lock);
 }
 
-static void ipu_crtc_dpms(struct drm_crtc *crtc, int mode)
+static void imx_drm_crtc_reset(struct drm_crtc *crtc)
 {
-	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
+	struct imx_crtc_state *state;
 
-	dev_dbg(ipu_crtc->dev, "%s mode: %d\n", __func__, mode);
-
-	switch (mode) {
-	case DRM_MODE_DPMS_ON:
-		ipu_fb_enable(ipu_crtc);
-		break;
-	case DRM_MODE_DPMS_STANDBY:
-	case DRM_MODE_DPMS_SUSPEND:
-	case DRM_MODE_DPMS_OFF:
-		ipu_fb_disable(ipu_crtc);
-		break;
+	if (crtc->state) {
+		if (crtc->state->mode_blob)
+			drm_property_unreference_blob(crtc->state->mode_blob);
+
+		state = to_imx_crtc_state(crtc->state);
+		memset(state, 0, sizeof(*state));
+	} else {
+		state = kzalloc(sizeof(*state), GFP_KERNEL);
+		if (!state)
+			return;
+		crtc->state = &state->base;
 	}
+
+	state->base.crtc = crtc;
 }
 
-static void ipu_flip_unref_work_func(struct work_struct *__work)
+static struct drm_crtc_state *imx_drm_crtc_duplicate_state(struct drm_crtc *crtc)
 {
-	struct ipu_flip_work *work =
-			container_of(__work, struct ipu_flip_work, unref_work);
+	struct imx_crtc_state *state;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return NULL;
 
-	drm_gem_object_unreference_unlocked(work->bo);
-	kfree(work);
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &state->base);
+
+	WARN_ON(state->base.crtc != crtc);
+	state->base.crtc = crtc;
+
+	return &state->base;
 }
 
-static void ipu_flip_fence_work_func(struct work_struct *__work)
+static void imx_drm_crtc_destroy_state(struct drm_crtc *crtc,
+				       struct drm_crtc_state *state)
 {
-	struct ipu_flip_work *work =
-			container_of(__work, struct ipu_flip_work, fence_work);
-	int i;
-
-	/* wait for all fences attached to the FB obj to signal */
-	if (work->excl) {
-		fence_wait(work->excl, false);
-		fence_put(work->excl);
-	}
-	for (i = 0; i < work->shared_count; i++) {
-		fence_wait(work->shared[i], false);
-		fence_put(work->shared[i]);
-	}
+	__drm_atomic_helper_crtc_destroy_state(state);
+	kfree(to_imx_crtc_state(state));
+}
+
+static const struct drm_crtc_funcs ipu_crtc_funcs = {
+	.set_config = drm_atomic_helper_set_config,
+	.destroy = drm_crtc_cleanup,
+	.page_flip = drm_atomic_helper_page_flip,
+	.reset = imx_drm_crtc_reset,
+	.atomic_duplicate_state = imx_drm_crtc_duplicate_state,
+	.atomic_destroy_state = imx_drm_crtc_destroy_state,
+};
 
-	work->crtc->flip_state = IPU_FLIP_SUBMITTED;
+static irqreturn_t ipu_irq_handler(int irq, void *dev_id)
+{
+	struct ipu_crtc *ipu_crtc = dev_id;
+
+	imx_drm_handle_vblank(ipu_crtc->imx_crtc);
+
+	return IRQ_HANDLED;
 }
 
-static int ipu_page_flip(struct drm_crtc *crtc,
-		struct drm_framebuffer *fb,
-		struct drm_pending_vblank_event *event,
-		uint32_t page_flip_flags)
+static bool ipu_crtc_mode_fixup(struct drm_crtc *crtc,
+				  const struct drm_display_mode *mode,
+				  struct drm_display_mode *adjusted_mode)
 {
-	struct drm_gem_cma_object *cma_obj = drm_fb_cma_get_gem_obj(fb, 0);
 	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
-	struct ipu_flip_work *flip_work;
+	struct videomode vm;
 	int ret;
 
-	if (ipu_crtc->flip_state != IPU_FLIP_NONE)
-		return -EBUSY;
-
-	ret = imx_drm_crtc_vblank_get(ipu_crtc->imx_crtc);
-	if (ret) {
-		dev_dbg(ipu_crtc->dev, "failed to acquire vblank counter\n");
-		list_del(&event->base.link);
-
-		return ret;
-	}
+	drm_display_mode_to_videomode(adjusted_mode, &vm);
 
-	flip_work = kzalloc(sizeof *flip_work, GFP_KERNEL);
-	if (!flip_work) {
-		ret = -ENOMEM;
-		goto put_vblank;
-	}
-	INIT_WORK(&flip_work->unref_work, ipu_flip_unref_work_func);
-	flip_work->page_flip_event = event;
+	ret = ipu_di_adjust_videomode(ipu_crtc->di, &vm);
+	if (ret)
+		return false;
 
-	/* get BO backing the old framebuffer and take a reference */
-	flip_work->bo = &drm_fb_cma_get_gem_obj(crtc->primary->fb, 0)->base;
-	drm_gem_object_reference(flip_work->bo);
+	if ((vm.vsync_len == 0) || (vm.hsync_len == 0))
+		return false;
 
-	ipu_crtc->flip_work = flip_work;
-	/*
-	 * If the object has a DMABUF attached, we need to wait on its fences
-	 * if there are any.
-	 */
-	if (cma_obj->base.dma_buf) {
-		INIT_WORK(&flip_work->fence_work, ipu_flip_fence_work_func);
-		flip_work->crtc = ipu_crtc;
+	drm_display_mode_from_videomode(&vm, adjusted_mode);
 
-		ret = reservation_object_get_fences_rcu(
-				cma_obj->base.dma_buf->resv, &flip_work->excl,
-				&flip_work->shared_count, &flip_work->shared);
+	return true;
+}
 
-		if (unlikely(ret)) {
-			DRM_ERROR("failed to get fences for buffer\n");
-			goto free_flip_work;
-		}
+static int ipu_crtc_atomic_check(struct drm_crtc *crtc,
+				 struct drm_crtc_state *state)
+{
+	u32 primary_plane_mask = 1 << drm_plane_index(crtc->primary);
 
-		/* No need to queue the worker if the are no fences */
-		if (!flip_work->excl && !flip_work->shared_count) {
-			ipu_crtc->flip_state = IPU_FLIP_SUBMITTED;
-		} else {
-			ipu_crtc->flip_state = IPU_FLIP_PENDING;
-			queue_work(ipu_crtc->flip_queue,
-				   &flip_work->fence_work);
-		}
-	} else {
-		ipu_crtc->flip_state = IPU_FLIP_SUBMITTED;
-	}
+	if (state->active && (primary_plane_mask & state->plane_mask) == 0)
+		return -EINVAL;
 
 	return 0;
-
-free_flip_work:
-	drm_gem_object_unreference_unlocked(flip_work->bo);
-	kfree(flip_work);
-	ipu_crtc->flip_work = NULL;
-put_vblank:
-	imx_drm_crtc_vblank_put(ipu_crtc->imx_crtc);
-
-	return ret;
 }
 
-static const struct drm_crtc_funcs ipu_crtc_funcs = {
-	.set_config = drm_crtc_helper_set_config,
-	.destroy = drm_crtc_cleanup,
-	.page_flip = ipu_page_flip,
-};
+static void ipu_crtc_atomic_begin(struct drm_crtc *crtc,
+				  struct drm_crtc_state *old_crtc_state)
+{
+	spin_lock_irq(&crtc->dev->event_lock);
+	if (crtc->state->event) {
+		WARN_ON(drm_crtc_vblank_get(crtc));
+		drm_crtc_arm_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+	}
+	spin_unlock_irq(&crtc->dev->event_lock);
+}
 
-static int ipu_crtc_mode_set(struct drm_crtc *crtc,
-			       struct drm_display_mode *orig_mode,
-			       struct drm_display_mode *mode,
-			       int x, int y,
-			       struct drm_framebuffer *old_fb)
+static void ipu_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_encoder *encoder;
 	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
+	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
+	struct imx_crtc_state *imx_crtc_state = to_imx_crtc_state(crtc->state);
 	struct ipu_di_signal_cfg sig_cfg = {};
 	unsigned long encoder_types = 0;
-	int ret;
 
 	dev_dbg(ipu_crtc->dev, "%s: mode->hdisplay: %d\n", __func__,
 			mode->hdisplay);
 	dev_dbg(ipu_crtc->dev, "%s: mode->vdisplay: %d\n", __func__,
 			mode->vdisplay);
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head)
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 		if (encoder->crtc == crtc)
 			encoder_types |= BIT(encoder->encoder_type);
+	}
 
 	dev_dbg(ipu_crtc->dev, "%s: attached to encoder types 0x%lx\n",
 		__func__, encoder_types);
@@ -272,114 +220,30 @@ static int ipu_crtc_mode_set(struct drm_crtc *crtc,
 	else
 		sig_cfg.clkflags = 0;
 
-	sig_cfg.enable_pol = !(ipu_crtc->bus_flags & DRM_BUS_FLAG_DE_LOW);
+	sig_cfg.enable_pol = !(imx_crtc_state->bus_flags & DRM_BUS_FLAG_DE_LOW);
 	/* Default to driving pixel data on negative clock edges */
-	sig_cfg.clk_pol = !!(ipu_crtc->bus_flags &
+	sig_cfg.clk_pol = !!(imx_crtc_state->bus_flags &
 			     DRM_BUS_FLAG_PIXDATA_POSEDGE);
-	sig_cfg.bus_format = ipu_crtc->bus_format;
+	sig_cfg.bus_format = imx_crtc_state->bus_format;
 	sig_cfg.v_to_h_sync = 0;
-	sig_cfg.hsync_pin = ipu_crtc->di_hsync_pin;
-	sig_cfg.vsync_pin = ipu_crtc->di_vsync_pin;
+	sig_cfg.hsync_pin = imx_crtc_state->di_hsync_pin;
+	sig_cfg.vsync_pin = imx_crtc_state->di_vsync_pin;
 
 	drm_display_mode_to_videomode(mode, &sig_cfg.mode);
 
-	ret = ipu_dc_init_sync(ipu_crtc->dc, ipu_crtc->di,
-			       mode->flags & DRM_MODE_FLAG_INTERLACE,
-			       ipu_crtc->bus_format, mode->hdisplay);
-	if (ret) {
-		dev_err(ipu_crtc->dev,
-				"initializing display controller failed with %d\n",
-				ret);
-		return ret;
-	}
-
-	ret = ipu_di_init_sync_panel(ipu_crtc->di, &sig_cfg);
-	if (ret) {
-		dev_err(ipu_crtc->dev,
-				"initializing panel failed with %d\n", ret);
-		return ret;
-	}
-
-	return ipu_plane_mode_set(ipu_crtc->plane[0], crtc, mode,
-				  crtc->primary->fb,
-				  0, 0, mode->hdisplay, mode->vdisplay,
-				  x, y, mode->hdisplay, mode->vdisplay,
-				  mode->flags & DRM_MODE_FLAG_INTERLACE);
-}
-
-static void ipu_crtc_handle_pageflip(struct ipu_crtc *ipu_crtc)
-{
-	unsigned long flags;
-	struct drm_device *drm = ipu_crtc->base.dev;
-	struct ipu_flip_work *work = ipu_crtc->flip_work;
-
-	spin_lock_irqsave(&drm->event_lock, flags);
-	if (work->page_flip_event)
-		drm_crtc_send_vblank_event(&ipu_crtc->base,
-					   work->page_flip_event);
-	imx_drm_crtc_vblank_put(ipu_crtc->imx_crtc);
-	spin_unlock_irqrestore(&drm->event_lock, flags);
-}
-
-static irqreturn_t ipu_irq_handler(int irq, void *dev_id)
-{
-	struct ipu_crtc *ipu_crtc = dev_id;
-
-	imx_drm_handle_vblank(ipu_crtc->imx_crtc);
-
-	if (ipu_crtc->flip_state == IPU_FLIP_SUBMITTED) {
-		struct ipu_plane *plane = ipu_crtc->plane[0];
-
-		ipu_plane_set_base(plane, ipu_crtc->base.primary->fb,
-				   plane->x, plane->y);
-		ipu_crtc_handle_pageflip(ipu_crtc);
-		queue_work(ipu_crtc->flip_queue,
-			   &ipu_crtc->flip_work->unref_work);
-		ipu_crtc->flip_state = IPU_FLIP_NONE;
-	}
-
-	return IRQ_HANDLED;
-}
-
-static bool ipu_crtc_mode_fixup(struct drm_crtc *crtc,
-				  const struct drm_display_mode *mode,
-				  struct drm_display_mode *adjusted_mode)
-{
-	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
-	struct videomode vm;
-	int ret;
-
-	drm_display_mode_to_videomode(adjusted_mode, &vm);
-
-	ret = ipu_di_adjust_videomode(ipu_crtc->di, &vm);
-	if (ret)
-		return false;
-
-	drm_display_mode_from_videomode(&vm, adjusted_mode);
-
-	return true;
-}
-
-static void ipu_crtc_prepare(struct drm_crtc *crtc)
-{
-	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
-
-	ipu_fb_disable(ipu_crtc);
-}
-
-static void ipu_crtc_commit(struct drm_crtc *crtc)
-{
-	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
-
-	ipu_fb_enable(ipu_crtc);
+	ipu_dc_init_sync(ipu_crtc->dc, ipu_crtc->di,
+			 mode->flags & DRM_MODE_FLAG_INTERLACE,
+			 imx_crtc_state->bus_format, mode->hdisplay);
+	ipu_di_init_sync_panel(ipu_crtc->di, &sig_cfg);
 }
 
 static const struct drm_crtc_helper_funcs ipu_helper_funcs = {
-	.dpms = ipu_crtc_dpms,
 	.mode_fixup = ipu_crtc_mode_fixup,
-	.mode_set = ipu_crtc_mode_set,
-	.prepare = ipu_crtc_prepare,
-	.commit = ipu_crtc_commit,
+	.mode_set_nofb = ipu_crtc_mode_set_nofb,
+	.atomic_check = ipu_crtc_atomic_check,
+	.atomic_begin = ipu_crtc_atomic_begin,
+	.disable = ipu_crtc_disable,
+	.enable = ipu_crtc_enable,
 };
 
 static int ipu_enable_vblank(struct drm_crtc *crtc)
@@ -398,23 +262,9 @@ static void ipu_disable_vblank(struct drm_crtc *crtc)
 	disable_irq_nosync(ipu_crtc->irq);
 }
 
-static int ipu_set_interface_pix_fmt(struct drm_crtc *crtc,
-		u32 bus_format, int hsync_pin, int vsync_pin, u32 bus_flags)
-{
-	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
-
-	ipu_crtc->bus_format = bus_format;
-	ipu_crtc->bus_flags = bus_flags;
-	ipu_crtc->di_hsync_pin = hsync_pin;
-	ipu_crtc->di_vsync_pin = vsync_pin;
-
-	return 0;
-}
-
 static const struct imx_drm_crtc_helper_funcs ipu_crtc_helper_funcs = {
 	.enable_vblank = ipu_enable_vblank,
 	.disable_vblank = ipu_disable_vblank,
-	.set_interface_pix_fmt = ipu_set_interface_pix_fmt,
 	.crtc_funcs = &ipu_crtc_funcs,
 	.crtc_helper_funcs = &ipu_helper_funcs,
 };
@@ -496,8 +346,16 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc,
 						IPU_DP_FLOW_SYNC_FG,
 						drm_crtc_mask(&ipu_crtc->base),
 						DRM_PLANE_TYPE_OVERLAY);
-		if (IS_ERR(ipu_crtc->plane[1]))
+		if (IS_ERR(ipu_crtc->plane[1])) {
 			ipu_crtc->plane[1] = NULL;
+		} else {
+			ret = ipu_plane_get_resources(ipu_crtc->plane[1]);
+			if (ret) {
+				dev_err(ipu_crtc->dev, "getting plane 1 "
+					"resources failed with %d.\n", ret);
+				goto err_put_plane0_res;
+			}
+		}
 	}
 
 	ipu_crtc->irq = ipu_plane_irq(ipu_crtc->plane[0]);
@@ -505,16 +363,17 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc,
 			"imx_drm", ipu_crtc);
 	if (ret < 0) {
 		dev_err(ipu_crtc->dev, "irq request failed with %d.\n", ret);
-		goto err_put_plane_res;
+		goto err_put_plane1_res;
 	}
 	/* Only enable IRQ when we actually need it to trigger work. */
 	disable_irq(ipu_crtc->irq);
 
-	ipu_crtc->flip_queue = create_singlethread_workqueue("ipu-crtc-flip");
-
 	return 0;
 
-err_put_plane_res:
+err_put_plane1_res:
+	if (ipu_crtc->plane[1])
+		ipu_plane_put_resources(ipu_crtc->plane[1]);
+err_put_plane0_res:
 	ipu_plane_put_resources(ipu_crtc->plane[0]);
 err_remove_crtc:
 	imx_drm_remove_crtc(ipu_crtc->imx_crtc);
@@ -553,9 +412,10 @@ static void ipu_drm_unbind(struct device *dev, struct device *master,
 
 	imx_drm_remove_crtc(ipu_crtc->imx_crtc);
 
-	destroy_workqueue(ipu_crtc->flip_queue);
-	ipu_plane_put_resources(ipu_crtc->plane[0]);
 	ipu_put_resources(ipu_crtc);
+	if (ipu_crtc->plane[1])
+		ipu_plane_put_resources(ipu_crtc->plane[1]);
+	ipu_plane_put_resources(ipu_crtc->plane[0]);
 }
 
 static const struct component_ops ipu_crtc_ops = {
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index a4bb44118d33..4ad67d015ec7 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -14,13 +14,19 @@
  */
 
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_plane_helper.h>
 
 #include "video/imx-ipu-v3.h"
 #include "ipuv3-plane.h"
 
-#define to_ipu_plane(x)	container_of(x, struct ipu_plane, base)
+static inline struct ipu_plane *to_ipu_plane(struct drm_plane *p)
+{
+	return container_of(p, struct ipu_plane, base);
+}
 
 static const uint32_t ipu_plane_formats[] = {
 	DRM_FORMAT_ARGB1555,
@@ -53,62 +59,67 @@ int ipu_plane_irq(struct ipu_plane *ipu_plane)
 				     IPU_IRQ_EOF);
 }
 
-static int calc_vref(struct drm_display_mode *mode)
+static inline unsigned long
+drm_plane_state_to_eba(struct drm_plane_state *state)
 {
-	unsigned long htotal, vtotal;
+	struct drm_framebuffer *fb = state->fb;
+	struct drm_gem_cma_object *cma_obj;
 
-	htotal = mode->htotal;
-	vtotal = mode->vtotal;
+	cma_obj = drm_fb_cma_get_gem_obj(fb, 0);
+	BUG_ON(!cma_obj);
 
-	if (!htotal || !vtotal)
-		return 60;
-
-	return DIV_ROUND_UP(mode->clock * 1000, vtotal * htotal);
+	return cma_obj->paddr + fb->offsets[0] +
+	       fb->pitches[0] * (state->src_y >> 16) +
+	       (fb->bits_per_pixel >> 3) * (state->src_x >> 16);
 }
 
-static inline int calc_bandwidth(int width, int height, unsigned int vref)
+static inline unsigned long
+drm_plane_state_to_ubo(struct drm_plane_state *state)
 {
-	return width * height * vref;
-}
+	struct drm_framebuffer *fb = state->fb;
+	struct drm_gem_cma_object *cma_obj;
+	unsigned long eba = drm_plane_state_to_eba(state);
 
-int ipu_plane_set_base(struct ipu_plane *ipu_plane, struct drm_framebuffer *fb,
-		       int x, int y)
-{
-	struct drm_gem_cma_object *cma_obj[3];
-	unsigned long eba, ubo, vbo;
-	int active, i;
+	cma_obj = drm_fb_cma_get_gem_obj(fb, 1);
+	BUG_ON(!cma_obj);
 
-	for (i = 0; i < drm_format_num_planes(fb->pixel_format); i++) {
-		cma_obj[i] = drm_fb_cma_get_gem_obj(fb, i);
-		if (!cma_obj[i]) {
-			DRM_DEBUG_KMS("plane %d entry is null.\n", i);
-			return -EFAULT;
-		}
-	}
+	return cma_obj->paddr + fb->offsets[1] +
+	       fb->pitches[1] * (state->src_y >> 16) / 2 +
+	       (state->src_x >> 16) / 2 - eba;
+}
 
-	eba = cma_obj[0]->paddr + fb->offsets[0] +
-	      fb->pitches[0] * y + (fb->bits_per_pixel >> 3) * x;
+static inline unsigned long
+drm_plane_state_to_vbo(struct drm_plane_state *state)
+{
+	struct drm_framebuffer *fb = state->fb;
+	struct drm_gem_cma_object *cma_obj;
+	unsigned long eba = drm_plane_state_to_eba(state);
 
-	if (eba & 0x7) {
-		DRM_DEBUG_KMS("base address must be a multiple of 8.\n");
-		return -EINVAL;
-	}
+	cma_obj = drm_fb_cma_get_gem_obj(fb, 2);
+	BUG_ON(!cma_obj);
 
-	if (fb->pitches[0] < 1 || fb->pitches[0] > 16384) {
-		DRM_DEBUG_KMS("pitches out of range.\n");
-		return -EINVAL;
-	}
+	return cma_obj->paddr + fb->offsets[2] +
+	       fb->pitches[2] * (state->src_y >> 16) / 2 +
+	       (state->src_x >> 16) / 2 - eba;
+}
 
-	if (ipu_plane->enabled && fb->pitches[0] != ipu_plane->stride[0]) {
-		DRM_DEBUG_KMS("pitches must not change while plane is enabled.\n");
-		return -EINVAL;
-	}
+static void ipu_plane_atomic_set_base(struct ipu_plane *ipu_plane,
+				      struct drm_plane_state *old_state)
+{
+	struct drm_plane *plane = &ipu_plane->base;
+	struct drm_plane_state *state = plane->state;
+	struct drm_framebuffer *fb = state->fb;
+	unsigned long eba, ubo, vbo;
+	int active;
 
-	ipu_plane->stride[0] = fb->pitches[0];
+	eba = drm_plane_state_to_eba(state);
 
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_YUV420:
 	case DRM_FORMAT_YVU420:
+		if (old_state->fb)
+			break;
+
 		/*
 		 * Multiplanar formats have to meet the following restrictions:
 		 * - The (up to) three plane addresses are EBA, EBA+UBO, EBA+VBO
@@ -117,59 +128,28 @@ int ipu_plane_set_base(struct ipu_plane *ipu_plane, struct drm_framebuffer *fb,
 		 * - Only EBA may be changed while scanout is active
 		 * - The strides of U and V planes must be identical.
 		 */
-		ubo = cma_obj[1]->paddr + fb->offsets[1] +
-		      fb->pitches[1] * y / 2 + x / 2 - eba;
-		vbo = cma_obj[2]->paddr + fb->offsets[2] +
-		      fb->pitches[2] * y / 2 + x / 2 - eba;
+		ubo = drm_plane_state_to_ubo(state);
+		vbo = drm_plane_state_to_vbo(state);
 
-		if ((ubo & 0x7) || (vbo & 0x7)) {
-			DRM_DEBUG_KMS("U/V buffer offsets must be a multiple of 8.\n");
-			return -EINVAL;
-		}
-
-		if ((ubo > 0xfffff8) || (vbo > 0xfffff8)) {
-			DRM_DEBUG_KMS("U/V buffer offsets must be positive and not larger than 0xfffff8.\n");
-			return -EINVAL;
-		}
-
-		if (ipu_plane->enabled && ((ipu_plane->u_offset != ubo) ||
-					   (ipu_plane->v_offset != vbo))) {
-			DRM_DEBUG_KMS("U/V buffer offsets must not change while plane is enabled.\n");
-			return -EINVAL;
-		}
-
-		if (fb->pitches[1] != fb->pitches[2]) {
-			DRM_DEBUG_KMS("U/V pitches must be identical.\n");
-			return -EINVAL;
-		}
-
-		if (fb->pitches[1] < 1 || fb->pitches[1] > 16384) {
-			DRM_DEBUG_KMS("U/V pitches out of range.\n");
-			return -EINVAL;
-		}
-
-		if (ipu_plane->enabled &&
-		    (ipu_plane->stride[1] != fb->pitches[1])) {
-			DRM_DEBUG_KMS("U/V pitches must not change while plane is enabled.\n");
-			return -EINVAL;
-		}
-
-		ipu_plane->u_offset = ubo;
-		ipu_plane->v_offset = vbo;
-		ipu_plane->stride[1] = fb->pitches[1];
+		if (fb->pixel_format == DRM_FORMAT_YUV420)
+			ipu_cpmem_set_yuv_planar_full(ipu_plane->ipu_ch,
+						      fb->pitches[1], ubo, vbo);
+		else
+			ipu_cpmem_set_yuv_planar_full(ipu_plane->ipu_ch,
+						      fb->pitches[1], vbo, ubo);
 
 		dev_dbg(ipu_plane->base.dev->dev,
-			"phys = %pad %pad %pad, x = %d, y = %d",
-			&cma_obj[0]->paddr, &cma_obj[1]->paddr,
-			&cma_obj[2]->paddr, x, y);
+			"phy = %lu %lu %lu, x = %d, y = %d", eba, ubo, vbo,
+			state->src_x >> 16, state->src_y >> 16);
 		break;
 	default:
-		dev_dbg(ipu_plane->base.dev->dev, "phys = %pad, x = %d, y = %d",
-			&cma_obj[0]->paddr, x, y);
+		dev_dbg(ipu_plane->base.dev->dev, "phys = %lu, x = %d, y = %d",
+			eba, state->src_x >> 16, state->src_y >> 16);
+
 		break;
 	}
 
-	if (ipu_plane->enabled) {
+	if (old_state->fb) {
 		active = ipu_idmac_get_current_buffer(ipu_plane->ipu_ch);
 		ipu_cpmem_set_buffer(ipu_plane->ipu_ch, !active, eba);
 		ipu_idmac_select_buffer(ipu_plane->ipu_ch, !active);
@@ -177,155 +157,6 @@ int ipu_plane_set_base(struct ipu_plane *ipu_plane, struct drm_framebuffer *fb,
 		ipu_cpmem_set_buffer(ipu_plane->ipu_ch, 0, eba);
 		ipu_cpmem_set_buffer(ipu_plane->ipu_ch, 1, eba);
 	}
-
-	/* cache offsets for subsequent pageflips */
-	ipu_plane->x = x;
-	ipu_plane->y = y;
-
-	return 0;
-}
-
-int ipu_plane_mode_set(struct ipu_plane *ipu_plane, struct drm_crtc *crtc,
-		       struct drm_display_mode *mode,
-		       struct drm_framebuffer *fb, int crtc_x, int crtc_y,
-		       unsigned int crtc_w, unsigned int crtc_h,
-		       uint32_t src_x, uint32_t src_y,
-		       uint32_t src_w, uint32_t src_h, bool interlaced)
-{
-	struct device *dev = ipu_plane->base.dev->dev;
-	int ret;
-
-	/* no scaling */
-	if (src_w != crtc_w || src_h != crtc_h)
-		return -EINVAL;
-
-	/* clip to crtc bounds */
-	if (crtc_x < 0) {
-		if (-crtc_x > crtc_w)
-			return -EINVAL;
-		src_x += -crtc_x;
-		src_w -= -crtc_x;
-		crtc_w -= -crtc_x;
-		crtc_x = 0;
-	}
-	if (crtc_y < 0) {
-		if (-crtc_y > crtc_h)
-			return -EINVAL;
-		src_y += -crtc_y;
-		src_h -= -crtc_y;
-		crtc_h -= -crtc_y;
-		crtc_y = 0;
-	}
-	if (crtc_x + crtc_w > mode->hdisplay) {
-		if (crtc_x > mode->hdisplay)
-			return -EINVAL;
-		crtc_w = mode->hdisplay - crtc_x;
-		src_w = crtc_w;
-	}
-	if (crtc_y + crtc_h > mode->vdisplay) {
-		if (crtc_y > mode->vdisplay)
-			return -EINVAL;
-		crtc_h = mode->vdisplay - crtc_y;
-		src_h = crtc_h;
-	}
-	/* full plane minimum width is 13 pixels */
-	if (crtc_w < 13 && (ipu_plane->dp_flow != IPU_DP_FLOW_SYNC_FG))
-		return -EINVAL;
-	if (crtc_h < 2)
-		return -EINVAL;
-
-	/*
-	 * since we cannot touch active IDMAC channels, we do not support
-	 * resizing the enabled plane or changing its format
-	 */
-	if (ipu_plane->enabled) {
-		if (src_w != ipu_plane->w || src_h != ipu_plane->h ||
-		    fb->pixel_format != ipu_plane->base.fb->pixel_format)
-			return -EINVAL;
-
-		return ipu_plane_set_base(ipu_plane, fb, src_x, src_y);
-	}
-
-	switch (ipu_plane->dp_flow) {
-	case IPU_DP_FLOW_SYNC_BG:
-		ret = ipu_dp_setup_channel(ipu_plane->dp,
-				IPUV3_COLORSPACE_RGB,
-				IPUV3_COLORSPACE_RGB);
-		if (ret) {
-			dev_err(dev,
-				"initializing display processor failed with %d\n",
-				ret);
-			return ret;
-		}
-		ipu_dp_set_global_alpha(ipu_plane->dp, true, 0, true);
-		break;
-	case IPU_DP_FLOW_SYNC_FG:
-		ipu_dp_setup_channel(ipu_plane->dp,
-				ipu_drm_fourcc_to_colorspace(fb->pixel_format),
-				IPUV3_COLORSPACE_UNKNOWN);
-		ipu_dp_set_window_pos(ipu_plane->dp, crtc_x, crtc_y);
-		/* Enable local alpha on partial plane */
-		switch (fb->pixel_format) {
-		case DRM_FORMAT_ARGB1555:
-		case DRM_FORMAT_ABGR1555:
-		case DRM_FORMAT_RGBA5551:
-		case DRM_FORMAT_BGRA5551:
-		case DRM_FORMAT_ARGB4444:
-		case DRM_FORMAT_ARGB8888:
-		case DRM_FORMAT_ABGR8888:
-		case DRM_FORMAT_RGBA8888:
-		case DRM_FORMAT_BGRA8888:
-			ipu_dp_set_global_alpha(ipu_plane->dp, false, 0, false);
-			break;
-		default:
-			break;
-		}
-	}
-
-	ret = ipu_dmfc_alloc_bandwidth(ipu_plane->dmfc,
-			calc_bandwidth(crtc_w, crtc_h,
-				       calc_vref(mode)), 64);
-	if (ret) {
-		dev_err(dev, "allocating dmfc bandwidth failed with %d\n", ret);
-		return ret;
-	}
-
-	ipu_dmfc_config_wait4eot(ipu_plane->dmfc, crtc_w);
-
-	ipu_cpmem_zero(ipu_plane->ipu_ch);
-	ipu_cpmem_set_resolution(ipu_plane->ipu_ch, src_w, src_h);
-	ret = ipu_cpmem_set_fmt(ipu_plane->ipu_ch, fb->pixel_format);
-	if (ret < 0) {
-		dev_err(dev, "unsupported pixel format 0x%08x\n",
-			fb->pixel_format);
-		return ret;
-	}
-	ipu_cpmem_set_high_priority(ipu_plane->ipu_ch);
-	ipu_idmac_set_double_buffer(ipu_plane->ipu_ch, 1);
-	ipu_cpmem_set_stride(ipu_plane->ipu_ch, fb->pitches[0]);
-
-	ret = ipu_plane_set_base(ipu_plane, fb, src_x, src_y);
-	if (ret < 0)
-		return ret;
-	if (interlaced)
-		ipu_cpmem_interlaced_scan(ipu_plane->ipu_ch, fb->pitches[0]);
-
-	if (fb->pixel_format == DRM_FORMAT_YUV420) {
-		ipu_cpmem_set_yuv_planar_full(ipu_plane->ipu_ch,
-					      ipu_plane->stride[1],
-					      ipu_plane->u_offset,
-					      ipu_plane->v_offset);
-	} else if (fb->pixel_format == DRM_FORMAT_YVU420) {
-		ipu_cpmem_set_yuv_planar_full(ipu_plane->ipu_ch,
-					      ipu_plane->stride[1],
-					      ipu_plane->v_offset,
-					      ipu_plane->u_offset);
-	}
-
-	ipu_plane->w = src_w;
-	ipu_plane->h = src_h;
-
-	return 0;
 }
 
 void ipu_plane_put_resources(struct ipu_plane *ipu_plane)
@@ -372,7 +203,7 @@ err_out:
 	return ret;
 }
 
-void ipu_plane_enable(struct ipu_plane *ipu_plane)
+static void ipu_plane_enable(struct ipu_plane *ipu_plane)
 {
 	if (ipu_plane->dp)
 		ipu_dp_enable(ipu_plane->ipu);
@@ -380,14 +211,10 @@ void ipu_plane_enable(struct ipu_plane *ipu_plane)
 	ipu_idmac_enable_channel(ipu_plane->ipu_ch);
 	if (ipu_plane->dp)
 		ipu_dp_enable_channel(ipu_plane->dp);
-
-	ipu_plane->enabled = true;
 }
 
-void ipu_plane_disable(struct ipu_plane *ipu_plane)
+static void ipu_plane_disable(struct ipu_plane *ipu_plane)
 {
-	ipu_plane->enabled = false;
-
 	ipu_idmac_wait_busy(ipu_plane->ipu_ch, 50);
 
 	if (ipu_plane->dp)
@@ -398,74 +225,225 @@ void ipu_plane_disable(struct ipu_plane *ipu_plane)
 		ipu_dp_disable(ipu_plane->ipu);
 }
 
-/*
- * drm_plane API
- */
-
-static int ipu_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
-			    struct drm_framebuffer *fb, int crtc_x, int crtc_y,
-			    unsigned int crtc_w, unsigned int crtc_h,
-			    uint32_t src_x, uint32_t src_y,
-			    uint32_t src_w, uint32_t src_h)
+static int ipu_disable_plane(struct drm_plane *plane)
 {
 	struct ipu_plane *ipu_plane = to_ipu_plane(plane);
-	int ret = 0;
-
-	DRM_DEBUG_KMS("plane - %p\n", plane);
-
-	if (!ipu_plane->enabled)
-		ret = ipu_plane_get_resources(ipu_plane);
-	if (ret < 0)
-		return ret;
-
-	ret = ipu_plane_mode_set(ipu_plane, crtc, &crtc->hwmode, fb,
-			crtc_x, crtc_y, crtc_w, crtc_h,
-			src_x >> 16, src_y >> 16, src_w >> 16, src_h >> 16,
-			false);
-	if (ret < 0) {
-		ipu_plane_put_resources(ipu_plane);
-		return ret;
-	}
 
-	if (crtc != plane->crtc)
-		dev_dbg(plane->dev->dev, "crtc change: %p -> %p\n",
-				plane->crtc, crtc);
+	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
 
-	if (!ipu_plane->enabled)
-		ipu_plane_enable(ipu_plane);
+	ipu_plane_disable(ipu_plane);
 
 	return 0;
 }
 
-static int ipu_disable_plane(struct drm_plane *plane)
+static void ipu_plane_destroy(struct drm_plane *plane)
 {
 	struct ipu_plane *ipu_plane = to_ipu_plane(plane);
 
 	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
 
-	if (ipu_plane->enabled)
-		ipu_plane_disable(ipu_plane);
+	ipu_disable_plane(plane);
+	drm_plane_cleanup(plane);
+	kfree(ipu_plane);
+}
 
-	ipu_plane_put_resources(ipu_plane);
+static const struct drm_plane_funcs ipu_plane_funcs = {
+	.update_plane	= drm_atomic_helper_update_plane,
+	.disable_plane	= drm_atomic_helper_disable_plane,
+	.destroy	= ipu_plane_destroy,
+	.reset		= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state	= drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+};
+
+static int ipu_plane_atomic_check(struct drm_plane *plane,
+				  struct drm_plane_state *state)
+{
+	struct drm_plane_state *old_state = plane->state;
+	struct drm_crtc_state *crtc_state;
+	struct device *dev = plane->dev->dev;
+	struct drm_framebuffer *fb = state->fb;
+	struct drm_framebuffer *old_fb = old_state->fb;
+	unsigned long eba, ubo, vbo, old_ubo, old_vbo;
+
+	/* Ok to disable */
+	if (!fb)
+		return 0;
+
+	if (!state->crtc)
+		return -EINVAL;
+
+	crtc_state =
+		drm_atomic_get_existing_crtc_state(state->state, state->crtc);
+	if (WARN_ON(!crtc_state))
+		return -EINVAL;
+
+	/* CRTC should be enabled */
+	if (!crtc_state->enable)
+		return -EINVAL;
+
+	/* no scaling */
+	if (state->src_w >> 16 != state->crtc_w ||
+	    state->src_h >> 16 != state->crtc_h)
+		return -EINVAL;
+
+	switch (plane->type) {
+	case DRM_PLANE_TYPE_PRIMARY:
+		/* full plane doesn't support partial off screen */
+		if (state->crtc_x || state->crtc_y ||
+		    state->crtc_w != crtc_state->adjusted_mode.hdisplay ||
+		    state->crtc_h != crtc_state->adjusted_mode.vdisplay)
+			return -EINVAL;
+
+		/* full plane minimum width is 13 pixels */
+		if (state->crtc_w < 13)
+			return -EINVAL;
+		break;
+	case DRM_PLANE_TYPE_OVERLAY:
+		if (state->crtc_x < 0 || state->crtc_y < 0)
+			return -EINVAL;
+
+		if (state->crtc_x + state->crtc_w >
+		    crtc_state->adjusted_mode.hdisplay)
+			return -EINVAL;
+		if (state->crtc_y + state->crtc_h >
+		    crtc_state->adjusted_mode.vdisplay)
+			return -EINVAL;
+		break;
+	default:
+		dev_warn(dev, "Unsupported plane type\n");
+		return -EINVAL;
+	}
+
+	if (state->crtc_h < 2)
+		return -EINVAL;
+
+	/*
+	 * since we cannot touch active IDMAC channels, we do not support
+	 * resizing the enabled plane or changing its format
+	 */
+	if (old_fb && (state->src_w != old_state->src_w ||
+			      state->src_h != old_state->src_h ||
+			      fb->pixel_format != old_fb->pixel_format))
+		return -EINVAL;
+
+	eba = drm_plane_state_to_eba(state);
+
+	if (eba & 0x7)
+		return -EINVAL;
+
+	if (fb->pitches[0] < 1 || fb->pitches[0] > 16384)
+		return -EINVAL;
+
+	if (old_fb && fb->pitches[0] != old_fb->pitches[0])
+		return -EINVAL;
+
+	switch (fb->pixel_format) {
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+		/*
+		 * Multiplanar formats have to meet the following restrictions:
+		 * - The (up to) three plane addresses are EBA, EBA+UBO, EBA+VBO
+		 * - EBA, UBO and VBO are a multiple of 8
+		 * - UBO and VBO are unsigned and not larger than 0xfffff8
+		 * - Only EBA may be changed while scanout is active
+		 * - The strides of U and V planes must be identical.
+		 */
+		ubo = drm_plane_state_to_ubo(state);
+		vbo = drm_plane_state_to_vbo(state);
+
+		if ((ubo & 0x7) || (vbo & 0x7))
+			return -EINVAL;
+
+		if ((ubo > 0xfffff8) || (vbo > 0xfffff8))
+			return -EINVAL;
+
+		if (old_fb) {
+			old_ubo = drm_plane_state_to_ubo(old_state);
+			old_vbo = drm_plane_state_to_vbo(old_state);
+			if (ubo != old_ubo || vbo != old_vbo)
+				return -EINVAL;
+		}
+
+		if (fb->pitches[1] != fb->pitches[2])
+			return -EINVAL;
+
+		if (fb->pitches[1] < 1 || fb->pitches[1] > 16384)
+			return -EINVAL;
+
+		if (old_fb && old_fb->pitches[1] != fb->pitches[1])
+			return -EINVAL;
+	}
 
 	return 0;
 }
 
-static void ipu_plane_destroy(struct drm_plane *plane)
+static void ipu_plane_atomic_disable(struct drm_plane *plane,
+				     struct drm_plane_state *old_state)
+{
+	ipu_disable_plane(plane);
+}
+
+static void ipu_plane_atomic_update(struct drm_plane *plane,
+				    struct drm_plane_state *old_state)
 {
 	struct ipu_plane *ipu_plane = to_ipu_plane(plane);
+	struct drm_plane_state *state = plane->state;
+	enum ipu_color_space ics;
 
-	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
+	if (old_state->fb) {
+		ipu_plane_atomic_set_base(ipu_plane, old_state);
+		return;
+	}
 
-	ipu_disable_plane(plane);
-	drm_plane_cleanup(plane);
-	kfree(ipu_plane);
+	switch (ipu_plane->dp_flow) {
+	case IPU_DP_FLOW_SYNC_BG:
+		ipu_dp_setup_channel(ipu_plane->dp,
+					IPUV3_COLORSPACE_RGB,
+					IPUV3_COLORSPACE_RGB);
+		ipu_dp_set_global_alpha(ipu_plane->dp, true, 0, true);
+		break;
+	case IPU_DP_FLOW_SYNC_FG:
+		ics = ipu_drm_fourcc_to_colorspace(state->fb->pixel_format);
+		ipu_dp_setup_channel(ipu_plane->dp, ics,
+					IPUV3_COLORSPACE_UNKNOWN);
+		ipu_dp_set_window_pos(ipu_plane->dp, state->crtc_x,
+					state->crtc_y);
+		/* Enable local alpha on partial plane */
+		switch (state->fb->pixel_format) {
+		case DRM_FORMAT_ARGB1555:
+		case DRM_FORMAT_ABGR1555:
+		case DRM_FORMAT_RGBA5551:
+		case DRM_FORMAT_BGRA5551:
+		case DRM_FORMAT_ARGB4444:
+		case DRM_FORMAT_ARGB8888:
+		case DRM_FORMAT_ABGR8888:
+		case DRM_FORMAT_RGBA8888:
+		case DRM_FORMAT_BGRA8888:
+			ipu_dp_set_global_alpha(ipu_plane->dp, false, 0, false);
+			break;
+		default:
+			break;
+		}
+	}
+
+	ipu_dmfc_config_wait4eot(ipu_plane->dmfc, state->crtc_w);
+
+	ipu_cpmem_zero(ipu_plane->ipu_ch);
+	ipu_cpmem_set_resolution(ipu_plane->ipu_ch, state->src_w >> 16,
+					state->src_h >> 16);
+	ipu_cpmem_set_fmt(ipu_plane->ipu_ch, state->fb->pixel_format);
+	ipu_cpmem_set_high_priority(ipu_plane->ipu_ch);
+	ipu_idmac_set_double_buffer(ipu_plane->ipu_ch, 1);
+	ipu_cpmem_set_stride(ipu_plane->ipu_ch, state->fb->pitches[0]);
+	ipu_plane_atomic_set_base(ipu_plane, old_state);
+	ipu_plane_enable(ipu_plane);
 }
 
-static const struct drm_plane_funcs ipu_plane_funcs = {
-	.update_plane	= ipu_update_plane,
-	.disable_plane	= ipu_disable_plane,
-	.destroy	= ipu_plane_destroy,
+static const struct drm_plane_helper_funcs ipu_plane_helper_funcs = {
+	.atomic_check = ipu_plane_atomic_check,
+	.atomic_disable = ipu_plane_atomic_disable,
+	.atomic_update = ipu_plane_atomic_update,
 };
 
 struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu,
@@ -498,5 +476,7 @@ struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu,
 		return ERR_PTR(ret);
 	}
 
+	drm_plane_helper_add(&ipu_plane->base, &ipu_plane_helper_funcs);
+
 	return ipu_plane;
 }
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.h b/drivers/gpu/drm/imx/ipuv3-plane.h
index 4448fd4ad4eb..338b88a74eb6 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.h
+++ b/drivers/gpu/drm/imx/ipuv3-plane.h
@@ -23,17 +23,6 @@ struct ipu_plane {
 
 	int			dma;
 	int			dp_flow;
-
-	int			x;
-	int			y;
-	int			w;
-	int			h;
-
-	unsigned int		u_offset;
-	unsigned int		v_offset;
-	unsigned int		stride[2];
-
-	bool			enabled;
 };
 
 struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu,
@@ -48,11 +37,6 @@ int ipu_plane_mode_set(struct ipu_plane *plane, struct drm_crtc *crtc,
 		       uint32_t src_x, uint32_t src_y, uint32_t src_w,
 		       uint32_t src_h, bool interlaced);
 
-void ipu_plane_enable(struct ipu_plane *plane);
-void ipu_plane_disable(struct ipu_plane *plane);
-int ipu_plane_set_base(struct ipu_plane *plane, struct drm_framebuffer *fb,
-		       int x, int y);
-
 int ipu_plane_get_resources(struct ipu_plane *plane);
 void ipu_plane_put_resources(struct ipu_plane *plane);
 
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 2d1fd02cd3d6..1dad297b01fd 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -16,6 +16,7 @@
 #include <linux/component.h>
 #include <linux/module.h>
 #include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_panel.h>
@@ -25,9 +26,6 @@
 
 #include "imx-drm.h"
 
-#define con_to_imxpd(x) container_of(x, struct imx_parallel_display, connector)
-#define enc_to_imxpd(x) container_of(x, struct imx_parallel_display, encoder)
-
 struct imx_parallel_display {
 	struct drm_connector connector;
 	struct drm_encoder encoder;
@@ -37,8 +35,19 @@ struct imx_parallel_display {
 	u32 bus_format;
 	struct drm_display_mode mode;
 	struct drm_panel *panel;
+	struct drm_bridge *bridge;
 };
 
+static inline struct imx_parallel_display *con_to_imxpd(struct drm_connector *c)
+{
+	return container_of(c, struct imx_parallel_display, connector);
+}
+
+static inline struct imx_parallel_display *enc_to_imxpd(struct drm_encoder *e)
+{
+	return container_of(e, struct imx_parallel_display, encoder);
+}
+
 static enum drm_connector_status imx_pd_connector_detect(
 		struct drm_connector *connector, bool force)
 {
@@ -53,11 +62,7 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 
 	if (imxpd->panel && imxpd->panel->funcs &&
 	    imxpd->panel->funcs->get_modes) {
-		struct drm_display_info *di = &connector->display_info;
-
 		num_modes = imxpd->panel->funcs->get_modes(imxpd->panel);
-		if (!imxpd->bus_format && di->num_bus_formats)
-			imxpd->bus_format = di->bus_formats[0];
 		if (num_modes > 0)
 			return num_modes;
 	}
@@ -69,10 +74,16 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 
 	if (np) {
 		struct drm_display_mode *mode = drm_mode_create(connector->dev);
+		int ret;
 
 		if (!mode)
 			return -EINVAL;
-		of_get_drm_display_mode(np, &imxpd->mode, OF_USE_NATIVE_MODE);
+
+		ret = of_get_drm_display_mode(np, &imxpd->mode,
+					      OF_USE_NATIVE_MODE);
+		if (ret)
+			return ret;
+
 		drm_mode_copy(mode, &imxpd->mode);
 		mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED,
 		drm_mode_probed_add(connector, mode);
@@ -90,24 +101,7 @@ static struct drm_encoder *imx_pd_connector_best_encoder(
 	return &imxpd->encoder;
 }
 
-static void imx_pd_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-	struct imx_parallel_display *imxpd = enc_to_imxpd(encoder);
-
-	if (mode != DRM_MODE_DPMS_ON)
-		drm_panel_disable(imxpd->panel);
-	else
-		drm_panel_enable(imxpd->panel);
-}
-
-static void imx_pd_encoder_prepare(struct drm_encoder *encoder)
-{
-	struct imx_parallel_display *imxpd = enc_to_imxpd(encoder);
-	imx_drm_set_bus_config(encoder, imxpd->bus_format, 2, 3,
-			       imxpd->connector.display_info.bus_flags);
-}
-
-static void imx_pd_encoder_commit(struct drm_encoder *encoder)
+static void imx_pd_encoder_enable(struct drm_encoder *encoder)
 {
 	struct imx_parallel_display *imxpd = enc_to_imxpd(encoder);
 
@@ -115,12 +109,6 @@ static void imx_pd_encoder_commit(struct drm_encoder *encoder)
 	drm_panel_enable(imxpd->panel);
 }
 
-static void imx_pd_encoder_mode_set(struct drm_encoder *encoder,
-			 struct drm_display_mode *orig_mode,
-			 struct drm_display_mode *mode)
-{
-}
-
 static void imx_pd_encoder_disable(struct drm_encoder *encoder)
 {
 	struct imx_parallel_display *imxpd = enc_to_imxpd(encoder);
@@ -129,11 +117,33 @@ static void imx_pd_encoder_disable(struct drm_encoder *encoder)
 	drm_panel_unprepare(imxpd->panel);
 }
 
+static int imx_pd_encoder_atomic_check(struct drm_encoder *encoder,
+				       struct drm_crtc_state *crtc_state,
+				       struct drm_connector_state *conn_state)
+{
+	struct imx_crtc_state *imx_crtc_state = to_imx_crtc_state(crtc_state);
+	struct drm_display_info *di = &conn_state->connector->display_info;
+	struct imx_parallel_display *imxpd = enc_to_imxpd(encoder);
+
+	imx_crtc_state->bus_flags = di->bus_flags;
+	if (!imxpd->bus_format && di->num_bus_formats)
+		imx_crtc_state->bus_format = di->bus_formats[0];
+	else
+		imx_crtc_state->bus_format = imxpd->bus_format;
+	imx_crtc_state->di_hsync_pin = 2;
+	imx_crtc_state->di_vsync_pin = 3;
+
+	return 0;
+}
+
 static const struct drm_connector_funcs imx_pd_connector_funcs = {
-	.dpms = drm_helper_connector_dpms,
+	.dpms = drm_atomic_helper_connector_dpms,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.detect = imx_pd_connector_detect,
 	.destroy = imx_drm_connector_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
 static const struct drm_connector_helper_funcs imx_pd_connector_helper_funcs = {
@@ -146,20 +156,18 @@ static const struct drm_encoder_funcs imx_pd_encoder_funcs = {
 };
 
 static const struct drm_encoder_helper_funcs imx_pd_encoder_helper_funcs = {
-	.dpms = imx_pd_encoder_dpms,
-	.prepare = imx_pd_encoder_prepare,
-	.commit = imx_pd_encoder_commit,
-	.mode_set = imx_pd_encoder_mode_set,
+	.enable = imx_pd_encoder_enable,
 	.disable = imx_pd_encoder_disable,
+	.atomic_check = imx_pd_encoder_atomic_check,
 };
 
 static int imx_pd_register(struct drm_device *drm,
 	struct imx_parallel_display *imxpd)
 {
+	struct drm_encoder *encoder = &imxpd->encoder;
 	int ret;
 
-	ret = imx_drm_encoder_parse_of(drm, &imxpd->encoder,
-				       imxpd->dev->of_node);
+	ret = imx_drm_encoder_parse_of(drm, encoder, imxpd->dev->of_node);
 	if (ret)
 		return ret;
 
@@ -170,19 +178,33 @@ static int imx_pd_register(struct drm_device *drm,
 	 */
 	imxpd->connector.dpms = DRM_MODE_DPMS_OFF;
 
-	drm_encoder_helper_add(&imxpd->encoder, &imx_pd_encoder_helper_funcs);
-	drm_encoder_init(drm, &imxpd->encoder, &imx_pd_encoder_funcs,
+	drm_encoder_helper_add(encoder, &imx_pd_encoder_helper_funcs);
+	drm_encoder_init(drm, encoder, &imx_pd_encoder_funcs,
 			 DRM_MODE_ENCODER_NONE, NULL);
 
-	drm_connector_helper_add(&imxpd->connector,
-			&imx_pd_connector_helper_funcs);
-	drm_connector_init(drm, &imxpd->connector, &imx_pd_connector_funcs,
-			   DRM_MODE_CONNECTOR_VGA);
+	if (!imxpd->bridge) {
+		drm_connector_helper_add(&imxpd->connector,
+				&imx_pd_connector_helper_funcs);
+		drm_connector_init(drm, &imxpd->connector,
+				   &imx_pd_connector_funcs,
+				   DRM_MODE_CONNECTOR_VGA);
+	}
 
 	if (imxpd->panel)
 		drm_panel_attach(imxpd->panel, &imxpd->connector);
 
-	drm_mode_connector_attach_encoder(&imxpd->connector, &imxpd->encoder);
+	if (imxpd->bridge) {
+		imxpd->bridge->encoder = encoder;
+		encoder->bridge = imxpd->bridge;
+		ret = drm_bridge_attach(drm, imxpd->bridge);
+		if (ret < 0) {
+			dev_err(imxpd->dev, "failed to attach bridge: %d\n",
+				ret);
+			return ret;
+		}
+	} else {
+		drm_mode_connector_attach_encoder(&imxpd->connector, encoder);
+	}
 
 	return 0;
 }
@@ -195,6 +217,7 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 	const u8 *edidp;
 	struct imx_parallel_display *imxpd;
 	int ret;
+	u32 bus_format = 0;
 	const char *fmt;
 
 	imxpd = devm_kzalloc(dev, sizeof(*imxpd), GFP_KERNEL);
@@ -208,14 +231,15 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 	ret = of_property_read_string(np, "interface-pix-fmt", &fmt);
 	if (!ret) {
 		if (!strcmp(fmt, "rgb24"))
-			imxpd->bus_format = MEDIA_BUS_FMT_RGB888_1X24;
+			bus_format = MEDIA_BUS_FMT_RGB888_1X24;
 		else if (!strcmp(fmt, "rgb565"))
-			imxpd->bus_format = MEDIA_BUS_FMT_RGB565_1X16;
+			bus_format = MEDIA_BUS_FMT_RGB565_1X16;
 		else if (!strcmp(fmt, "bgr666"))
-			imxpd->bus_format = MEDIA_BUS_FMT_RGB666_1X18;
+			bus_format = MEDIA_BUS_FMT_RGB666_1X18;
 		else if (!strcmp(fmt, "lvds666"))
-			imxpd->bus_format = MEDIA_BUS_FMT_RGB666_1X24_CPADHI;
+			bus_format = MEDIA_BUS_FMT_RGB666_1X24_CPADHI;
 	}
+	imxpd->bus_format = bus_format;
 
 	/* port@1 is the output port */
 	ep = of_graph_get_endpoint_by_regs(np, 1, -1);
@@ -223,13 +247,30 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 		struct device_node *remote;
 
 		remote = of_graph_get_remote_port_parent(ep);
+		if (!remote) {
+			dev_warn(dev, "endpoint %s not connected\n",
+				 ep->full_name);
+			of_node_put(ep);
+			return -ENODEV;
+		}
 		of_node_put(ep);
-		if (remote) {
-			imxpd->panel = of_drm_find_panel(remote);
-			of_node_put(remote);
+
+		imxpd->panel = of_drm_find_panel(remote);
+		if (imxpd->panel) {
+			dev_dbg(dev, "found panel %s\n", remote->full_name);
+		} else {
+			imxpd->bridge = of_drm_find_bridge(remote);
+			if (imxpd->bridge)
+				dev_dbg(dev, "found bridge %s\n",
+					remote->full_name);
 		}
-		if (!imxpd->panel)
+		if (!imxpd->panel && !imxpd->bridge) {
+			dev_dbg(dev, "waiting for panel or bridge %s\n",
+				remote->full_name);
+			of_node_put(remote);
 			return -EPROBE_DEFER;
+		}
+		of_node_put(remote);
 	}
 
 	imxpd->dev = dev;
diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig
index eeefc971801a..23ac8041c562 100644
--- a/drivers/gpu/drm/mediatek/Kconfig
+++ b/drivers/gpu/drm/mediatek/Kconfig
@@ -6,7 +6,6 @@ config DRM_MEDIATEK
 	select DRM_KMS_HELPER
 	select DRM_MIPI_DSI
 	select DRM_PANEL
-	select IOMMU_DMA
 	select MEMORY
 	select MTK_SMI
 	help
@@ -14,3 +13,11 @@ config DRM_MEDIATEK
 	  The module will be called mediatek-drm
 	  This driver provides kernel mode setting and
 	  buffer management to userspace.
+
+config DRM_MEDIATEK_HDMI
+	tristate "DRM HDMI Support for Mediatek SoCs"
+	depends on DRM_MEDIATEK
+	select SND_SOC_HDMI_CODEC if SND_SOC
+	select GENERIC_PHY
+	help
+	  DRM/KMS HDMI driver for Mediatek SoCs
diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile
index 5fcf58e87786..bf2e5be1ab30 100644
--- a/drivers/gpu/drm/mediatek/Makefile
+++ b/drivers/gpu/drm/mediatek/Makefile
@@ -12,3 +12,10 @@ mediatek-drm-y := mtk_disp_ovl.o \
 		  mtk_dpi.o
 
 obj-$(CONFIG_DRM_MEDIATEK) += mediatek-drm.o
+
+mediatek-drm-hdmi-objs := mtk_cec.o \
+			  mtk_hdmi.o \
+			  mtk_hdmi_ddc.o \
+			  mtk_mt8173_hdmi_phy.o
+
+obj-$(CONFIG_DRM_MEDIATEK_HDMI) += mediatek-drm-hdmi.o
diff --git a/drivers/gpu/drm/mediatek/mtk_cec.c b/drivers/gpu/drm/mediatek/mtk_cec.c
new file mode 100644
index 000000000000..7a3eb8c17ef9
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_cec.c
@@ -0,0 +1,265 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Jie Qiu <jie.qiu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+
+#include "mtk_cec.h"
+
+#define TR_CONFIG		0x00
+#define CLEAR_CEC_IRQ			BIT(15)
+
+#define CEC_CKGEN		0x04
+#define CEC_32K_PDN			BIT(19)
+#define PDN				BIT(16)
+
+#define RX_EVENT		0x54
+#define HDMI_PORD			BIT(25)
+#define HDMI_HTPLG			BIT(24)
+#define HDMI_PORD_INT_EN		BIT(9)
+#define HDMI_HTPLG_INT_EN		BIT(8)
+
+#define RX_GEN_WD		0x58
+#define HDMI_PORD_INT_32K_STATUS	BIT(26)
+#define RX_RISC_INT_32K_STATUS		BIT(25)
+#define HDMI_HTPLG_INT_32K_STATUS	BIT(24)
+#define HDMI_PORD_INT_32K_CLR		BIT(18)
+#define RX_INT_32K_CLR			BIT(17)
+#define HDMI_HTPLG_INT_32K_CLR		BIT(16)
+#define HDMI_PORD_INT_32K_STA_MASK	BIT(10)
+#define RX_RISC_INT_32K_STA_MASK	BIT(9)
+#define HDMI_HTPLG_INT_32K_STA_MASK	BIT(8)
+#define HDMI_PORD_INT_32K_EN		BIT(2)
+#define RX_INT_32K_EN			BIT(1)
+#define HDMI_HTPLG_INT_32K_EN		BIT(0)
+
+#define NORMAL_INT_CTRL		0x5C
+#define HDMI_HTPLG_INT_STA		BIT(0)
+#define HDMI_PORD_INT_STA		BIT(1)
+#define HDMI_HTPLG_INT_CLR		BIT(16)
+#define HDMI_PORD_INT_CLR		BIT(17)
+#define HDMI_FULL_INT_CLR		BIT(20)
+
+struct mtk_cec {
+	void __iomem *regs;
+	struct clk *clk;
+	int irq;
+	bool hpd;
+	void (*hpd_event)(bool hpd, struct device *dev);
+	struct device *hdmi_dev;
+	spinlock_t lock;
+};
+
+static void mtk_cec_clear_bits(struct mtk_cec *cec, unsigned int offset,
+			       unsigned int bits)
+{
+	void __iomem *reg = cec->regs + offset;
+	u32 tmp;
+
+	tmp = readl(reg);
+	tmp &= ~bits;
+	writel(tmp, reg);
+}
+
+static void mtk_cec_set_bits(struct mtk_cec *cec, unsigned int offset,
+			     unsigned int bits)
+{
+	void __iomem *reg = cec->regs + offset;
+	u32 tmp;
+
+	tmp = readl(reg);
+	tmp |= bits;
+	writel(tmp, reg);
+}
+
+static void mtk_cec_mask(struct mtk_cec *cec, unsigned int offset,
+			 unsigned int val, unsigned int mask)
+{
+	u32 tmp = readl(cec->regs + offset) & ~mask;
+
+	tmp |= val & mask;
+	writel(val, cec->regs + offset);
+}
+
+void mtk_cec_set_hpd_event(struct device *dev,
+			   void (*hpd_event)(bool hpd, struct device *dev),
+			   struct device *hdmi_dev)
+{
+	struct mtk_cec *cec = dev_get_drvdata(dev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&cec->lock, flags);
+	cec->hdmi_dev = hdmi_dev;
+	cec->hpd_event = hpd_event;
+	spin_unlock_irqrestore(&cec->lock, flags);
+}
+
+bool mtk_cec_hpd_high(struct device *dev)
+{
+	struct mtk_cec *cec = dev_get_drvdata(dev);
+	unsigned int status;
+
+	status = readl(cec->regs + RX_EVENT);
+
+	return (status & (HDMI_PORD | HDMI_HTPLG)) == (HDMI_PORD | HDMI_HTPLG);
+}
+
+static void mtk_cec_htplg_irq_init(struct mtk_cec *cec)
+{
+	mtk_cec_mask(cec, CEC_CKGEN, 0 | CEC_32K_PDN, PDN | CEC_32K_PDN);
+	mtk_cec_set_bits(cec, RX_GEN_WD, HDMI_PORD_INT_32K_CLR |
+			 RX_INT_32K_CLR | HDMI_HTPLG_INT_32K_CLR);
+	mtk_cec_mask(cec, RX_GEN_WD, 0, HDMI_PORD_INT_32K_CLR | RX_INT_32K_CLR |
+		     HDMI_HTPLG_INT_32K_CLR | HDMI_PORD_INT_32K_EN |
+		     RX_INT_32K_EN | HDMI_HTPLG_INT_32K_EN);
+}
+
+static void mtk_cec_htplg_irq_enable(struct mtk_cec *cec)
+{
+	mtk_cec_set_bits(cec, RX_EVENT, HDMI_PORD_INT_EN | HDMI_HTPLG_INT_EN);
+}
+
+static void mtk_cec_htplg_irq_disable(struct mtk_cec *cec)
+{
+	mtk_cec_clear_bits(cec, RX_EVENT, HDMI_PORD_INT_EN | HDMI_HTPLG_INT_EN);
+}
+
+static void mtk_cec_clear_htplg_irq(struct mtk_cec *cec)
+{
+	mtk_cec_set_bits(cec, TR_CONFIG, CLEAR_CEC_IRQ);
+	mtk_cec_set_bits(cec, NORMAL_INT_CTRL, HDMI_HTPLG_INT_CLR |
+			 HDMI_PORD_INT_CLR | HDMI_FULL_INT_CLR);
+	mtk_cec_set_bits(cec, RX_GEN_WD, HDMI_PORD_INT_32K_CLR |
+			 RX_INT_32K_CLR | HDMI_HTPLG_INT_32K_CLR);
+	usleep_range(5, 10);
+	mtk_cec_clear_bits(cec, NORMAL_INT_CTRL, HDMI_HTPLG_INT_CLR |
+			   HDMI_PORD_INT_CLR | HDMI_FULL_INT_CLR);
+	mtk_cec_clear_bits(cec, TR_CONFIG, CLEAR_CEC_IRQ);
+	mtk_cec_clear_bits(cec, RX_GEN_WD, HDMI_PORD_INT_32K_CLR |
+			   RX_INT_32K_CLR | HDMI_HTPLG_INT_32K_CLR);
+}
+
+static void mtk_cec_hpd_event(struct mtk_cec *cec, bool hpd)
+{
+	void (*hpd_event)(bool hpd, struct device *dev);
+	struct device *hdmi_dev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cec->lock, flags);
+	hpd_event = cec->hpd_event;
+	hdmi_dev = cec->hdmi_dev;
+	spin_unlock_irqrestore(&cec->lock, flags);
+
+	if (hpd_event)
+		hpd_event(hpd, hdmi_dev);
+}
+
+static irqreturn_t mtk_cec_htplg_isr_thread(int irq, void *arg)
+{
+	struct device *dev = arg;
+	struct mtk_cec *cec = dev_get_drvdata(dev);
+	bool hpd;
+
+	mtk_cec_clear_htplg_irq(cec);
+	hpd = mtk_cec_hpd_high(dev);
+
+	if (cec->hpd != hpd) {
+		dev_dbg(dev, "hotplug event! cur hpd = %d, hpd = %d\n",
+			cec->hpd, hpd);
+		cec->hpd = hpd;
+		mtk_cec_hpd_event(cec, hpd);
+	}
+	return IRQ_HANDLED;
+}
+
+static int mtk_cec_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mtk_cec *cec;
+	struct resource *res;
+	int ret;
+
+	cec = devm_kzalloc(dev, sizeof(*cec), GFP_KERNEL);
+	if (!cec)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, cec);
+	spin_lock_init(&cec->lock);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	cec->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cec->regs)) {
+		ret = PTR_ERR(cec->regs);
+		dev_err(dev, "Failed to ioremap cec: %d\n", ret);
+		return ret;
+	}
+
+	cec->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(cec->clk)) {
+		ret = PTR_ERR(cec->clk);
+		dev_err(dev, "Failed to get cec clock: %d\n", ret);
+		return ret;
+	}
+
+	cec->irq = platform_get_irq(pdev, 0);
+	if (cec->irq < 0) {
+		dev_err(dev, "Failed to get cec irq: %d\n", cec->irq);
+		return cec->irq;
+	}
+
+	ret = devm_request_threaded_irq(dev, cec->irq, NULL,
+					mtk_cec_htplg_isr_thread,
+					IRQF_SHARED | IRQF_TRIGGER_LOW |
+					IRQF_ONESHOT, "hdmi hpd", dev);
+	if (ret) {
+		dev_err(dev, "Failed to register cec irq: %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_prepare_enable(cec->clk);
+	if (ret) {
+		dev_err(dev, "Failed to enable cec clock: %d\n", ret);
+		return ret;
+	}
+
+	mtk_cec_htplg_irq_init(cec);
+	mtk_cec_htplg_irq_enable(cec);
+
+	return 0;
+}
+
+static int mtk_cec_remove(struct platform_device *pdev)
+{
+	struct mtk_cec *cec = platform_get_drvdata(pdev);
+
+	mtk_cec_htplg_irq_disable(cec);
+	clk_disable_unprepare(cec->clk);
+	return 0;
+}
+
+static const struct of_device_id mtk_cec_of_ids[] = {
+	{ .compatible = "mediatek,mt8173-cec", },
+	{}
+};
+
+struct platform_driver mtk_cec_driver = {
+	.probe = mtk_cec_probe,
+	.remove = mtk_cec_remove,
+	.driver = {
+		.name = "mediatek-cec",
+		.of_match_table = mtk_cec_of_ids,
+	},
+};
diff --git a/drivers/gpu/drm/mediatek/mtk_cec.h b/drivers/gpu/drm/mediatek/mtk_cec.h
new file mode 100644
index 000000000000..10057b7eabec
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_cec.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Jie Qiu <jie.qiu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef _MTK_CEC_H
+#define _MTK_CEC_H
+
+#include <linux/types.h>
+
+struct device;
+
+void mtk_cec_set_hpd_event(struct device *dev,
+			   void (*hotplug_event)(bool hpd, struct device *dev),
+			   struct device *hdmi_dev);
+bool mtk_cec_hpd_high(struct device *dev);
+
+#endif /* _MTK_CEC_H */
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index b1223d54d0ab..eebb7d881c2b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -91,7 +91,7 @@ static int mtk_atomic_commit(struct drm_device *drm,
 	mutex_lock(&private->commit.lock);
 	flush_work(&private->commit.work);
 
-	drm_atomic_helper_swap_state(drm, state);
+	drm_atomic_helper_swap_state(state, true);
 
 	if (async)
 		mtk_atomic_schedule(private, state);
@@ -243,7 +243,7 @@ static struct drm_driver mtk_drm_driver = {
 	.enable_vblank = mtk_drm_crtc_enable_vblank,
 	.disable_vblank = mtk_drm_crtc_disable_vblank,
 
-	.gem_free_object = mtk_drm_gem_free_object,
+	.gem_free_object_unlocked = mtk_drm_gem_free_object,
 	.gem_vm_ops = &drm_gem_cma_vm_ops,
 	.dumb_create = mtk_drm_gem_dumb_create,
 	.dumb_map_offset = mtk_drm_gem_dumb_map_offset,
@@ -280,8 +280,6 @@ static int mtk_drm_bind(struct device *dev)
 	if (!drm)
 		return -ENOMEM;
 
-	drm_dev_set_unique(drm, dev_name(dev));
-
 	drm->dev_private = private;
 	private->drm = drm;
 
@@ -293,14 +291,8 @@ static int mtk_drm_bind(struct device *dev)
 	if (ret < 0)
 		goto err_deinit;
 
-	ret = drm_connector_register_all(drm);
-	if (ret < 0)
-		goto err_unregister;
-
 	return 0;
 
-err_unregister:
-	drm_dev_unregister(drm);
 err_deinit:
 	mtk_drm_kms_deinit(drm);
 err_free:
@@ -455,7 +447,6 @@ static int mtk_drm_remove(struct platform_device *pdev)
 	struct drm_device *drm = private->drm;
 	int i;
 
-	drm_connector_unregister_all(drm);
 	drm_dev_unregister(drm);
 	mtk_drm_kms_deinit(drm);
 	drm_dev_unref(drm);
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 51bc8988fc26..3995765a90dc 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -170,6 +170,7 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 
 	return drm_plane_helper_check_update(plane, state->crtc, fb,
 					     &src, &dest, &clip,
+					     state->rotation,
 					     DRM_PLANE_HELPER_NO_SCALING,
 					     DRM_PLANE_HELPER_NO_SCALING,
 					     true, true, &visible);
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 769559124562..28b2044ed9f2 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -575,14 +575,6 @@ static int mtk_dsi_connector_get_modes(struct drm_connector *connector)
 	return drm_panel_get_modes(dsi->panel);
 }
 
-static struct drm_encoder *mtk_dsi_connector_best_encoder(
-		struct drm_connector *connector)
-{
-	struct mtk_dsi *dsi = connector_to_dsi(connector);
-
-	return &dsi->encoder;
-}
-
 static const struct drm_encoder_helper_funcs mtk_dsi_encoder_helper_funcs = {
 	.mode_fixup = mtk_dsi_encoder_mode_fixup,
 	.mode_set = mtk_dsi_encoder_mode_set,
@@ -603,7 +595,6 @@ static const struct drm_connector_funcs mtk_dsi_connector_funcs = {
 static const struct drm_connector_helper_funcs
 	mtk_dsi_connector_helper_funcs = {
 	.get_modes = mtk_dsi_connector_get_modes,
-	.best_encoder = mtk_dsi_connector_best_encoder,
 };
 
 static int mtk_drm_attach_bridge(struct drm_bridge *bridge,
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
new file mode 100644
index 000000000000..334562d06731
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -0,0 +1,1828 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Jie Qiu <jie.qiu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_edid.h>
+#include <linux/arm-smccc.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/hdmi.h>
+#include <linux/i2c.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of_platform.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/of_graph.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <sound/hdmi-codec.h>
+#include "mtk_cec.h"
+#include "mtk_hdmi.h"
+#include "mtk_hdmi_regs.h"
+
+#define NCTS_BYTES	7
+
+enum mtk_hdmi_clk_id {
+	MTK_HDMI_CLK_HDMI_PIXEL,
+	MTK_HDMI_CLK_HDMI_PLL,
+	MTK_HDMI_CLK_AUD_BCLK,
+	MTK_HDMI_CLK_AUD_SPDIF,
+	MTK_HDMI_CLK_COUNT
+};
+
+enum hdmi_aud_input_type {
+	HDMI_AUD_INPUT_I2S = 0,
+	HDMI_AUD_INPUT_SPDIF,
+};
+
+enum hdmi_aud_i2s_fmt {
+	HDMI_I2S_MODE_RJT_24BIT = 0,
+	HDMI_I2S_MODE_RJT_16BIT,
+	HDMI_I2S_MODE_LJT_24BIT,
+	HDMI_I2S_MODE_LJT_16BIT,
+	HDMI_I2S_MODE_I2S_24BIT,
+	HDMI_I2S_MODE_I2S_16BIT
+};
+
+enum hdmi_aud_mclk {
+	HDMI_AUD_MCLK_128FS,
+	HDMI_AUD_MCLK_192FS,
+	HDMI_AUD_MCLK_256FS,
+	HDMI_AUD_MCLK_384FS,
+	HDMI_AUD_MCLK_512FS,
+	HDMI_AUD_MCLK_768FS,
+	HDMI_AUD_MCLK_1152FS,
+};
+
+enum hdmi_aud_channel_type {
+	HDMI_AUD_CHAN_TYPE_1_0 = 0,
+	HDMI_AUD_CHAN_TYPE_1_1,
+	HDMI_AUD_CHAN_TYPE_2_0,
+	HDMI_AUD_CHAN_TYPE_2_1,
+	HDMI_AUD_CHAN_TYPE_3_0,
+	HDMI_AUD_CHAN_TYPE_3_1,
+	HDMI_AUD_CHAN_TYPE_4_0,
+	HDMI_AUD_CHAN_TYPE_4_1,
+	HDMI_AUD_CHAN_TYPE_5_0,
+	HDMI_AUD_CHAN_TYPE_5_1,
+	HDMI_AUD_CHAN_TYPE_6_0,
+	HDMI_AUD_CHAN_TYPE_6_1,
+	HDMI_AUD_CHAN_TYPE_7_0,
+	HDMI_AUD_CHAN_TYPE_7_1,
+	HDMI_AUD_CHAN_TYPE_3_0_LRS,
+	HDMI_AUD_CHAN_TYPE_3_1_LRS,
+	HDMI_AUD_CHAN_TYPE_4_0_CLRS,
+	HDMI_AUD_CHAN_TYPE_4_1_CLRS,
+	HDMI_AUD_CHAN_TYPE_6_1_CS,
+	HDMI_AUD_CHAN_TYPE_6_1_CH,
+	HDMI_AUD_CHAN_TYPE_6_1_OH,
+	HDMI_AUD_CHAN_TYPE_6_1_CHR,
+	HDMI_AUD_CHAN_TYPE_7_1_LH_RH,
+	HDMI_AUD_CHAN_TYPE_7_1_LSR_RSR,
+	HDMI_AUD_CHAN_TYPE_7_1_LC_RC,
+	HDMI_AUD_CHAN_TYPE_7_1_LW_RW,
+	HDMI_AUD_CHAN_TYPE_7_1_LSD_RSD,
+	HDMI_AUD_CHAN_TYPE_7_1_LSS_RSS,
+	HDMI_AUD_CHAN_TYPE_7_1_LHS_RHS,
+	HDMI_AUD_CHAN_TYPE_7_1_CS_CH,
+	HDMI_AUD_CHAN_TYPE_7_1_CS_OH,
+	HDMI_AUD_CHAN_TYPE_7_1_CS_CHR,
+	HDMI_AUD_CHAN_TYPE_7_1_CH_OH,
+	HDMI_AUD_CHAN_TYPE_7_1_CH_CHR,
+	HDMI_AUD_CHAN_TYPE_7_1_OH_CHR,
+	HDMI_AUD_CHAN_TYPE_7_1_LSS_RSS_LSR_RSR,
+	HDMI_AUD_CHAN_TYPE_6_0_CS,
+	HDMI_AUD_CHAN_TYPE_6_0_CH,
+	HDMI_AUD_CHAN_TYPE_6_0_OH,
+	HDMI_AUD_CHAN_TYPE_6_0_CHR,
+	HDMI_AUD_CHAN_TYPE_7_0_LH_RH,
+	HDMI_AUD_CHAN_TYPE_7_0_LSR_RSR,
+	HDMI_AUD_CHAN_TYPE_7_0_LC_RC,
+	HDMI_AUD_CHAN_TYPE_7_0_LW_RW,
+	HDMI_AUD_CHAN_TYPE_7_0_LSD_RSD,
+	HDMI_AUD_CHAN_TYPE_7_0_LSS_RSS,
+	HDMI_AUD_CHAN_TYPE_7_0_LHS_RHS,
+	HDMI_AUD_CHAN_TYPE_7_0_CS_CH,
+	HDMI_AUD_CHAN_TYPE_7_0_CS_OH,
+	HDMI_AUD_CHAN_TYPE_7_0_CS_CHR,
+	HDMI_AUD_CHAN_TYPE_7_0_CH_OH,
+	HDMI_AUD_CHAN_TYPE_7_0_CH_CHR,
+	HDMI_AUD_CHAN_TYPE_7_0_OH_CHR,
+	HDMI_AUD_CHAN_TYPE_7_0_LSS_RSS_LSR_RSR,
+	HDMI_AUD_CHAN_TYPE_8_0_LH_RH_CS,
+	HDMI_AUD_CHAN_TYPE_UNKNOWN = 0xFF
+};
+
+enum hdmi_aud_channel_swap_type {
+	HDMI_AUD_SWAP_LR,
+	HDMI_AUD_SWAP_LFE_CC,
+	HDMI_AUD_SWAP_LSRS,
+	HDMI_AUD_SWAP_RLS_RRS,
+	HDMI_AUD_SWAP_LR_STATUS,
+};
+
+struct hdmi_audio_param {
+	enum hdmi_audio_coding_type aud_codec;
+	enum hdmi_audio_sample_size aud_sampe_size;
+	enum hdmi_aud_input_type aud_input_type;
+	enum hdmi_aud_i2s_fmt aud_i2s_fmt;
+	enum hdmi_aud_mclk aud_mclk;
+	enum hdmi_aud_channel_type aud_input_chan_type;
+	struct hdmi_codec_params codec_params;
+};
+
+struct mtk_hdmi {
+	struct drm_bridge bridge;
+	struct drm_connector conn;
+	struct device *dev;
+	struct phy *phy;
+	struct device *cec_dev;
+	struct i2c_adapter *ddc_adpt;
+	struct clk *clk[MTK_HDMI_CLK_COUNT];
+	struct drm_display_mode mode;
+	bool dvi_mode;
+	u32 min_clock;
+	u32 max_clock;
+	u32 max_hdisplay;
+	u32 max_vdisplay;
+	u32 ibias;
+	u32 ibias_up;
+	struct regmap *sys_regmap;
+	unsigned int sys_offset;
+	void __iomem *regs;
+	enum hdmi_colorspace csp;
+	struct hdmi_audio_param aud_param;
+	bool audio_enable;
+	bool powered;
+	bool enabled;
+};
+
+static inline struct mtk_hdmi *hdmi_ctx_from_bridge(struct drm_bridge *b)
+{
+	return container_of(b, struct mtk_hdmi, bridge);
+}
+
+static inline struct mtk_hdmi *hdmi_ctx_from_conn(struct drm_connector *c)
+{
+	return container_of(c, struct mtk_hdmi, conn);
+}
+
+static u32 mtk_hdmi_read(struct mtk_hdmi *hdmi, u32 offset)
+{
+	return readl(hdmi->regs + offset);
+}
+
+static void mtk_hdmi_write(struct mtk_hdmi *hdmi, u32 offset, u32 val)
+{
+	writel(val, hdmi->regs + offset);
+}
+
+static void mtk_hdmi_clear_bits(struct mtk_hdmi *hdmi, u32 offset, u32 bits)
+{
+	void __iomem *reg = hdmi->regs + offset;
+	u32 tmp;
+
+	tmp = readl(reg);
+	tmp &= ~bits;
+	writel(tmp, reg);
+}
+
+static void mtk_hdmi_set_bits(struct mtk_hdmi *hdmi, u32 offset, u32 bits)
+{
+	void __iomem *reg = hdmi->regs + offset;
+	u32 tmp;
+
+	tmp = readl(reg);
+	tmp |= bits;
+	writel(tmp, reg);
+}
+
+static void mtk_hdmi_mask(struct mtk_hdmi *hdmi, u32 offset, u32 val, u32 mask)
+{
+	void __iomem *reg = hdmi->regs + offset;
+	u32 tmp;
+
+	tmp = readl(reg);
+	tmp = (tmp & ~mask) | (val & mask);
+	writel(tmp, reg);
+}
+
+static void mtk_hdmi_hw_vid_black(struct mtk_hdmi *hdmi, bool black)
+{
+	mtk_hdmi_mask(hdmi, VIDEO_CFG_4, black ? GEN_RGB : NORMAL_PATH,
+		      VIDEO_SOURCE_SEL);
+}
+
+static void mtk_hdmi_hw_make_reg_writable(struct mtk_hdmi *hdmi, bool enable)
+{
+	struct arm_smccc_res res;
+
+	/*
+	 * MT8173 HDMI hardware has an output control bit to enable/disable HDMI
+	 * output. This bit can only be controlled in ARM supervisor mode.
+	 * The ARM trusted firmware provides an API for the HDMI driver to set
+	 * this control bit to enable HDMI output in supervisor mode.
+	 */
+	arm_smccc_smc(MTK_SIP_SET_AUTHORIZED_SECURE_REG, 0x14000904, 0x80000000,
+		      0, 0, 0, 0, 0, &res);
+
+	regmap_update_bits(hdmi->sys_regmap, hdmi->sys_offset + HDMI_SYS_CFG20,
+			   HDMI_PCLK_FREE_RUN, enable ? HDMI_PCLK_FREE_RUN : 0);
+	regmap_update_bits(hdmi->sys_regmap, hdmi->sys_offset + HDMI_SYS_CFG1C,
+			   HDMI_ON | ANLG_ON, enable ? (HDMI_ON | ANLG_ON) : 0);
+}
+
+static void mtk_hdmi_hw_1p4_version_enable(struct mtk_hdmi *hdmi, bool enable)
+{
+	regmap_update_bits(hdmi->sys_regmap, hdmi->sys_offset + HDMI_SYS_CFG20,
+			   HDMI2P0_EN, enable ? 0 : HDMI2P0_EN);
+}
+
+static void mtk_hdmi_hw_aud_mute(struct mtk_hdmi *hdmi)
+{
+	mtk_hdmi_set_bits(hdmi, GRL_AUDIO_CFG, AUDIO_ZERO);
+}
+
+static void mtk_hdmi_hw_aud_unmute(struct mtk_hdmi *hdmi)
+{
+	mtk_hdmi_clear_bits(hdmi, GRL_AUDIO_CFG, AUDIO_ZERO);
+}
+
+static void mtk_hdmi_hw_reset(struct mtk_hdmi *hdmi)
+{
+	regmap_update_bits(hdmi->sys_regmap, hdmi->sys_offset + HDMI_SYS_CFG1C,
+			   HDMI_RST, HDMI_RST);
+	regmap_update_bits(hdmi->sys_regmap, hdmi->sys_offset + HDMI_SYS_CFG1C,
+			   HDMI_RST, 0);
+	mtk_hdmi_clear_bits(hdmi, GRL_CFG3, CFG3_CONTROL_PACKET_DELAY);
+	regmap_update_bits(hdmi->sys_regmap, hdmi->sys_offset + HDMI_SYS_CFG1C,
+			   ANLG_ON, ANLG_ON);
+}
+
+static void mtk_hdmi_hw_enable_notice(struct mtk_hdmi *hdmi, bool enable_notice)
+{
+	mtk_hdmi_mask(hdmi, GRL_CFG2, enable_notice ? CFG2_NOTICE_EN : 0,
+		      CFG2_NOTICE_EN);
+}
+
+static void mtk_hdmi_hw_write_int_mask(struct mtk_hdmi *hdmi, u32 int_mask)
+{
+	mtk_hdmi_write(hdmi, GRL_INT_MASK, int_mask);
+}
+
+static void mtk_hdmi_hw_enable_dvi_mode(struct mtk_hdmi *hdmi, bool enable)
+{
+	mtk_hdmi_mask(hdmi, GRL_CFG1, enable ? CFG1_DVI : 0, CFG1_DVI);
+}
+
+static void mtk_hdmi_hw_send_info_frame(struct mtk_hdmi *hdmi, u8 *buffer,
+					u8 len)
+{
+	u32 ctrl_reg = GRL_CTRL;
+	int i;
+	u8 *frame_data;
+	enum hdmi_infoframe_type frame_type;
+	u8 frame_ver;
+	u8 frame_len;
+	u8 checksum;
+	int ctrl_frame_en = 0;
+
+	frame_type = *buffer;
+	buffer += 1;
+	frame_ver = *buffer;
+	buffer += 1;
+	frame_len = *buffer;
+	buffer += 1;
+	checksum = *buffer;
+	buffer += 1;
+	frame_data = buffer;
+
+	dev_dbg(hdmi->dev,
+		"frame_type:0x%x,frame_ver:0x%x,frame_len:0x%x,checksum:0x%x\n",
+		frame_type, frame_ver, frame_len, checksum);
+
+	switch (frame_type) {
+	case HDMI_INFOFRAME_TYPE_AVI:
+		ctrl_frame_en = CTRL_AVI_EN;
+		ctrl_reg = GRL_CTRL;
+		break;
+	case HDMI_INFOFRAME_TYPE_SPD:
+		ctrl_frame_en = CTRL_SPD_EN;
+		ctrl_reg = GRL_CTRL;
+		break;
+	case HDMI_INFOFRAME_TYPE_AUDIO:
+		ctrl_frame_en = CTRL_AUDIO_EN;
+		ctrl_reg = GRL_CTRL;
+		break;
+	case HDMI_INFOFRAME_TYPE_VENDOR:
+		ctrl_frame_en = VS_EN;
+		ctrl_reg = GRL_ACP_ISRC_CTRL;
+		break;
+	}
+	mtk_hdmi_clear_bits(hdmi, ctrl_reg, ctrl_frame_en);
+	mtk_hdmi_write(hdmi, GRL_INFOFRM_TYPE, frame_type);
+	mtk_hdmi_write(hdmi, GRL_INFOFRM_VER, frame_ver);
+	mtk_hdmi_write(hdmi, GRL_INFOFRM_LNG, frame_len);
+
+	mtk_hdmi_write(hdmi, GRL_IFM_PORT, checksum);
+	for (i = 0; i < frame_len; i++)
+		mtk_hdmi_write(hdmi, GRL_IFM_PORT, frame_data[i]);
+
+	mtk_hdmi_set_bits(hdmi, ctrl_reg, ctrl_frame_en);
+}
+
+static void mtk_hdmi_hw_send_aud_packet(struct mtk_hdmi *hdmi, bool enable)
+{
+	mtk_hdmi_mask(hdmi, GRL_SHIFT_R2, enable ? 0 : AUDIO_PACKET_OFF,
+		      AUDIO_PACKET_OFF);
+}
+
+static void mtk_hdmi_hw_config_sys(struct mtk_hdmi *hdmi)
+{
+	regmap_update_bits(hdmi->sys_regmap, hdmi->sys_offset + HDMI_SYS_CFG20,
+			   HDMI_OUT_FIFO_EN | MHL_MODE_ON, 0);
+	usleep_range(2000, 4000);
+	regmap_update_bits(hdmi->sys_regmap, hdmi->sys_offset + HDMI_SYS_CFG20,
+			   HDMI_OUT_FIFO_EN | MHL_MODE_ON, HDMI_OUT_FIFO_EN);
+}
+
+static void mtk_hdmi_hw_set_deep_color_mode(struct mtk_hdmi *hdmi)
+{
+	regmap_update_bits(hdmi->sys_regmap, hdmi->sys_offset + HDMI_SYS_CFG20,
+			   DEEP_COLOR_MODE_MASK | DEEP_COLOR_EN,
+			   COLOR_8BIT_MODE);
+}
+
+static void mtk_hdmi_hw_send_av_mute(struct mtk_hdmi *hdmi)
+{
+	mtk_hdmi_clear_bits(hdmi, GRL_CFG4, CTRL_AVMUTE);
+	usleep_range(2000, 4000);
+	mtk_hdmi_set_bits(hdmi, GRL_CFG4, CTRL_AVMUTE);
+}
+
+static void mtk_hdmi_hw_send_av_unmute(struct mtk_hdmi *hdmi)
+{
+	mtk_hdmi_mask(hdmi, GRL_CFG4, CFG4_AV_UNMUTE_EN,
+		      CFG4_AV_UNMUTE_EN | CFG4_AV_UNMUTE_SET);
+	usleep_range(2000, 4000);
+	mtk_hdmi_mask(hdmi, GRL_CFG4, CFG4_AV_UNMUTE_SET,
+		      CFG4_AV_UNMUTE_EN | CFG4_AV_UNMUTE_SET);
+}
+
+static void mtk_hdmi_hw_ncts_enable(struct mtk_hdmi *hdmi, bool on)
+{
+	mtk_hdmi_mask(hdmi, GRL_CTS_CTRL, on ? 0 : CTS_CTRL_SOFT,
+		      CTS_CTRL_SOFT);
+}
+
+static void mtk_hdmi_hw_ncts_auto_write_enable(struct mtk_hdmi *hdmi,
+					       bool enable)
+{
+	mtk_hdmi_mask(hdmi, GRL_CTS_CTRL, enable ? NCTS_WRI_ANYTIME : 0,
+		      NCTS_WRI_ANYTIME);
+}
+
+static void mtk_hdmi_hw_msic_setting(struct mtk_hdmi *hdmi,
+				     struct drm_display_mode *mode)
+{
+	mtk_hdmi_clear_bits(hdmi, GRL_CFG4, CFG4_MHL_MODE);
+
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE &&
+	    mode->clock == 74250 &&
+	    mode->vdisplay == 1080)
+		mtk_hdmi_clear_bits(hdmi, GRL_CFG2, CFG2_MHL_DE_SEL);
+	else
+		mtk_hdmi_set_bits(hdmi, GRL_CFG2, CFG2_MHL_DE_SEL);
+}
+
+static void mtk_hdmi_hw_aud_set_channel_swap(struct mtk_hdmi *hdmi,
+					enum hdmi_aud_channel_swap_type swap)
+{
+	u8 swap_bit;
+
+	switch (swap) {
+	case HDMI_AUD_SWAP_LR:
+		swap_bit = LR_SWAP;
+		break;
+	case HDMI_AUD_SWAP_LFE_CC:
+		swap_bit = LFE_CC_SWAP;
+		break;
+	case HDMI_AUD_SWAP_LSRS:
+		swap_bit = LSRS_SWAP;
+		break;
+	case HDMI_AUD_SWAP_RLS_RRS:
+		swap_bit = RLS_RRS_SWAP;
+		break;
+	case HDMI_AUD_SWAP_LR_STATUS:
+		swap_bit = LR_STATUS_SWAP;
+		break;
+	default:
+		swap_bit = LFE_CC_SWAP;
+		break;
+	}
+	mtk_hdmi_mask(hdmi, GRL_CH_SWAP, swap_bit, 0xff);
+}
+
+static void mtk_hdmi_hw_aud_set_bit_num(struct mtk_hdmi *hdmi,
+					enum hdmi_audio_sample_size bit_num)
+{
+	u32 val;
+
+	switch (bit_num) {
+	case HDMI_AUDIO_SAMPLE_SIZE_16:
+		val = AOUT_16BIT;
+		break;
+	case HDMI_AUDIO_SAMPLE_SIZE_20:
+		val = AOUT_20BIT;
+		break;
+	case HDMI_AUDIO_SAMPLE_SIZE_24:
+	case HDMI_AUDIO_SAMPLE_SIZE_STREAM:
+		val = AOUT_24BIT;
+		break;
+	}
+
+	mtk_hdmi_mask(hdmi, GRL_AOUT_CFG, val, AOUT_BNUM_SEL_MASK);
+}
+
+static void mtk_hdmi_hw_aud_set_i2s_fmt(struct mtk_hdmi *hdmi,
+					enum hdmi_aud_i2s_fmt i2s_fmt)
+{
+	u32 val;
+
+	val = mtk_hdmi_read(hdmi, GRL_CFG0);
+	val &= ~(CFG0_W_LENGTH_MASK | CFG0_I2S_MODE_MASK);
+
+	switch (i2s_fmt) {
+	case HDMI_I2S_MODE_RJT_24BIT:
+		val |= CFG0_I2S_MODE_RTJ | CFG0_W_LENGTH_24BIT;
+		break;
+	case HDMI_I2S_MODE_RJT_16BIT:
+		val |= CFG0_I2S_MODE_RTJ | CFG0_W_LENGTH_16BIT;
+		break;
+	case HDMI_I2S_MODE_LJT_24BIT:
+	default:
+		val |= CFG0_I2S_MODE_LTJ | CFG0_W_LENGTH_24BIT;
+		break;
+	case HDMI_I2S_MODE_LJT_16BIT:
+		val |= CFG0_I2S_MODE_LTJ | CFG0_W_LENGTH_16BIT;
+		break;
+	case HDMI_I2S_MODE_I2S_24BIT:
+		val |= CFG0_I2S_MODE_I2S | CFG0_W_LENGTH_24BIT;
+		break;
+	case HDMI_I2S_MODE_I2S_16BIT:
+		val |= CFG0_I2S_MODE_I2S | CFG0_W_LENGTH_16BIT;
+		break;
+	}
+	mtk_hdmi_write(hdmi, GRL_CFG0, val);
+}
+
+static void mtk_hdmi_hw_audio_config(struct mtk_hdmi *hdmi, bool dst)
+{
+	const u8 mask = HIGH_BIT_RATE | DST_NORMAL_DOUBLE | SACD_DST | DSD_SEL;
+	u8 val;
+
+	/* Disable high bitrate, set DST packet normal/double */
+	mtk_hdmi_clear_bits(hdmi, GRL_AOUT_CFG, HIGH_BIT_RATE_PACKET_ALIGN);
+
+	if (dst)
+		val = DST_NORMAL_DOUBLE | SACD_DST;
+	else
+		val = 0;
+
+	mtk_hdmi_mask(hdmi, GRL_AUDIO_CFG, val, mask);
+}
+
+static void mtk_hdmi_hw_aud_set_i2s_chan_num(struct mtk_hdmi *hdmi,
+					enum hdmi_aud_channel_type channel_type,
+					u8 channel_count)
+{
+	unsigned int ch_switch;
+	u8 i2s_uv;
+
+	ch_switch = CH_SWITCH(7, 7) | CH_SWITCH(6, 6) |
+		    CH_SWITCH(5, 5) | CH_SWITCH(4, 4) |
+		    CH_SWITCH(3, 3) | CH_SWITCH(1, 2) |
+		    CH_SWITCH(2, 1) | CH_SWITCH(0, 0);
+
+	if (channel_count == 2) {
+		i2s_uv = I2S_UV_CH_EN(0);
+	} else if (channel_count == 3 || channel_count == 4) {
+		if (channel_count == 4 &&
+		    (channel_type == HDMI_AUD_CHAN_TYPE_3_0_LRS ||
+		    channel_type == HDMI_AUD_CHAN_TYPE_4_0))
+			i2s_uv = I2S_UV_CH_EN(2) | I2S_UV_CH_EN(0);
+		else
+			i2s_uv = I2S_UV_CH_EN(3) | I2S_UV_CH_EN(2);
+	} else if (channel_count == 6 || channel_count == 5) {
+		if (channel_count == 6 &&
+		    channel_type != HDMI_AUD_CHAN_TYPE_5_1 &&
+		    channel_type != HDMI_AUD_CHAN_TYPE_4_1_CLRS) {
+			i2s_uv = I2S_UV_CH_EN(3) | I2S_UV_CH_EN(2) |
+				 I2S_UV_CH_EN(1) | I2S_UV_CH_EN(0);
+		} else {
+			i2s_uv = I2S_UV_CH_EN(2) | I2S_UV_CH_EN(1) |
+				 I2S_UV_CH_EN(0);
+		}
+	} else if (channel_count == 8 || channel_count == 7) {
+		i2s_uv = I2S_UV_CH_EN(3) | I2S_UV_CH_EN(2) |
+			 I2S_UV_CH_EN(1) | I2S_UV_CH_EN(0);
+	} else {
+		i2s_uv = I2S_UV_CH_EN(0);
+	}
+
+	mtk_hdmi_write(hdmi, GRL_CH_SW0, ch_switch & 0xff);
+	mtk_hdmi_write(hdmi, GRL_CH_SW1, (ch_switch >> 8) & 0xff);
+	mtk_hdmi_write(hdmi, GRL_CH_SW2, (ch_switch >> 16) & 0xff);
+	mtk_hdmi_write(hdmi, GRL_I2S_UV, i2s_uv);
+}
+
+static void mtk_hdmi_hw_aud_set_input_type(struct mtk_hdmi *hdmi,
+					   enum hdmi_aud_input_type input_type)
+{
+	u32 val;
+
+	val = mtk_hdmi_read(hdmi, GRL_CFG1);
+	if (input_type == HDMI_AUD_INPUT_I2S &&
+	    (val & CFG1_SPDIF) == CFG1_SPDIF) {
+		val &= ~CFG1_SPDIF;
+	} else if (input_type == HDMI_AUD_INPUT_SPDIF &&
+		(val & CFG1_SPDIF) == 0) {
+		val |= CFG1_SPDIF;
+	}
+	mtk_hdmi_write(hdmi, GRL_CFG1, val);
+}
+
+static void mtk_hdmi_hw_aud_set_channel_status(struct mtk_hdmi *hdmi,
+					       u8 *channel_status)
+{
+	int i;
+
+	for (i = 0; i < 5; i++) {
+		mtk_hdmi_write(hdmi, GRL_I2S_C_STA0 + i * 4, channel_status[i]);
+		mtk_hdmi_write(hdmi, GRL_L_STATUS_0 + i * 4, channel_status[i]);
+		mtk_hdmi_write(hdmi, GRL_R_STATUS_0 + i * 4, channel_status[i]);
+	}
+	for (; i < 24; i++) {
+		mtk_hdmi_write(hdmi, GRL_L_STATUS_0 + i * 4, 0);
+		mtk_hdmi_write(hdmi, GRL_R_STATUS_0 + i * 4, 0);
+	}
+}
+
+static void mtk_hdmi_hw_aud_src_reenable(struct mtk_hdmi *hdmi)
+{
+	u32 val;
+
+	val = mtk_hdmi_read(hdmi, GRL_MIX_CTRL);
+	if (val & MIX_CTRL_SRC_EN) {
+		val &= ~MIX_CTRL_SRC_EN;
+		mtk_hdmi_write(hdmi, GRL_MIX_CTRL, val);
+		usleep_range(255, 512);
+		val |= MIX_CTRL_SRC_EN;
+		mtk_hdmi_write(hdmi, GRL_MIX_CTRL, val);
+	}
+}
+
+static void mtk_hdmi_hw_aud_src_disable(struct mtk_hdmi *hdmi)
+{
+	u32 val;
+
+	val = mtk_hdmi_read(hdmi, GRL_MIX_CTRL);
+	val &= ~MIX_CTRL_SRC_EN;
+	mtk_hdmi_write(hdmi, GRL_MIX_CTRL, val);
+	mtk_hdmi_write(hdmi, GRL_SHIFT_L1, 0x00);
+}
+
+static void mtk_hdmi_hw_aud_set_mclk(struct mtk_hdmi *hdmi,
+				     enum hdmi_aud_mclk mclk)
+{
+	u32 val;
+
+	val = mtk_hdmi_read(hdmi, GRL_CFG5);
+	val &= CFG5_CD_RATIO_MASK;
+
+	switch (mclk) {
+	case HDMI_AUD_MCLK_128FS:
+		val |= CFG5_FS128;
+		break;
+	case HDMI_AUD_MCLK_256FS:
+		val |= CFG5_FS256;
+		break;
+	case HDMI_AUD_MCLK_384FS:
+		val |= CFG5_FS384;
+		break;
+	case HDMI_AUD_MCLK_512FS:
+		val |= CFG5_FS512;
+		break;
+	case HDMI_AUD_MCLK_768FS:
+		val |= CFG5_FS768;
+		break;
+	default:
+		val |= CFG5_FS256;
+		break;
+	}
+	mtk_hdmi_write(hdmi, GRL_CFG5, val);
+}
+
+struct hdmi_acr_n {
+	unsigned int clock;
+	unsigned int n[3];
+};
+
+/* Recommended N values from HDMI specification, tables 7-1 to 7-3 */
+static const struct hdmi_acr_n hdmi_rec_n_table[] = {
+	/* Clock, N: 32kHz 44.1kHz 48kHz */
+	{  25175, {  4576,  7007,  6864 } },
+	{  74176, { 11648, 17836, 11648 } },
+	{ 148352, { 11648,  8918,  5824 } },
+	{ 296703, {  5824,  4459,  5824 } },
+	{ 297000, {  3072,  4704,  5120 } },
+	{      0, {  4096,  6272,  6144 } }, /* all other TMDS clocks */
+};
+
+/**
+ * hdmi_recommended_n() - Return N value recommended by HDMI specification
+ * @freq: audio sample rate in Hz
+ * @clock: rounded TMDS clock in kHz
+ */
+static unsigned int hdmi_recommended_n(unsigned int freq, unsigned int clock)
+{
+	const struct hdmi_acr_n *recommended;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(hdmi_rec_n_table) - 1; i++) {
+		if (clock == hdmi_rec_n_table[i].clock)
+			break;
+	}
+	recommended = hdmi_rec_n_table + i;
+
+	switch (freq) {
+	case 32000:
+		return recommended->n[0];
+	case 44100:
+		return recommended->n[1];
+	case 48000:
+		return recommended->n[2];
+	case 88200:
+		return recommended->n[1] * 2;
+	case 96000:
+		return recommended->n[2] * 2;
+	case 176400:
+		return recommended->n[1] * 4;
+	case 192000:
+		return recommended->n[2] * 4;
+	default:
+		return (128 * freq) / 1000;
+	}
+}
+
+static unsigned int hdmi_mode_clock_to_hz(unsigned int clock)
+{
+	switch (clock) {
+	case 25175:
+		return 25174825;	/* 25.2/1.001 MHz */
+	case 74176:
+		return 74175824;	/* 74.25/1.001 MHz */
+	case 148352:
+		return 148351648;	/* 148.5/1.001 MHz */
+	case 296703:
+		return 296703297;	/* 297/1.001 MHz */
+	default:
+		return clock * 1000;
+	}
+}
+
+static unsigned int hdmi_expected_cts(unsigned int audio_sample_rate,
+				      unsigned int tmds_clock, unsigned int n)
+{
+	return DIV_ROUND_CLOSEST_ULL((u64)hdmi_mode_clock_to_hz(tmds_clock) * n,
+				     128 * audio_sample_rate);
+}
+
+static void do_hdmi_hw_aud_set_ncts(struct mtk_hdmi *hdmi, unsigned int n,
+				    unsigned int cts)
+{
+	unsigned char val[NCTS_BYTES];
+	int i;
+
+	mtk_hdmi_write(hdmi, GRL_NCTS, 0);
+	mtk_hdmi_write(hdmi, GRL_NCTS, 0);
+	mtk_hdmi_write(hdmi, GRL_NCTS, 0);
+	memset(val, 0, sizeof(val));
+
+	val[0] = (cts >> 24) & 0xff;
+	val[1] = (cts >> 16) & 0xff;
+	val[2] = (cts >> 8) & 0xff;
+	val[3] = cts & 0xff;
+
+	val[4] = (n >> 16) & 0xff;
+	val[5] = (n >> 8) & 0xff;
+	val[6] = n & 0xff;
+
+	for (i = 0; i < NCTS_BYTES; i++)
+		mtk_hdmi_write(hdmi, GRL_NCTS, val[i]);
+}
+
+static void mtk_hdmi_hw_aud_set_ncts(struct mtk_hdmi *hdmi,
+				     unsigned int sample_rate,
+				     unsigned int clock)
+{
+	unsigned int n, cts;
+
+	n = hdmi_recommended_n(sample_rate, clock);
+	cts = hdmi_expected_cts(sample_rate, clock, n);
+
+	dev_dbg(hdmi->dev, "%s: sample_rate=%u, clock=%d, cts=%u, n=%u\n",
+		__func__, sample_rate, clock, n, cts);
+
+	mtk_hdmi_mask(hdmi, DUMMY_304, AUDIO_I2S_NCTS_SEL_64,
+		      AUDIO_I2S_NCTS_SEL);
+	do_hdmi_hw_aud_set_ncts(hdmi, n, cts);
+}
+
+static u8 mtk_hdmi_aud_get_chnl_count(enum hdmi_aud_channel_type channel_type)
+{
+	switch (channel_type) {
+	case HDMI_AUD_CHAN_TYPE_1_0:
+	case HDMI_AUD_CHAN_TYPE_1_1:
+	case HDMI_AUD_CHAN_TYPE_2_0:
+		return 2;
+	case HDMI_AUD_CHAN_TYPE_2_1:
+	case HDMI_AUD_CHAN_TYPE_3_0:
+		return 3;
+	case HDMI_AUD_CHAN_TYPE_3_1:
+	case HDMI_AUD_CHAN_TYPE_4_0:
+	case HDMI_AUD_CHAN_TYPE_3_0_LRS:
+		return 4;
+	case HDMI_AUD_CHAN_TYPE_4_1:
+	case HDMI_AUD_CHAN_TYPE_5_0:
+	case HDMI_AUD_CHAN_TYPE_3_1_LRS:
+	case HDMI_AUD_CHAN_TYPE_4_0_CLRS:
+		return 5;
+	case HDMI_AUD_CHAN_TYPE_5_1:
+	case HDMI_AUD_CHAN_TYPE_6_0:
+	case HDMI_AUD_CHAN_TYPE_4_1_CLRS:
+	case HDMI_AUD_CHAN_TYPE_6_0_CS:
+	case HDMI_AUD_CHAN_TYPE_6_0_CH:
+	case HDMI_AUD_CHAN_TYPE_6_0_OH:
+	case HDMI_AUD_CHAN_TYPE_6_0_CHR:
+		return 6;
+	case HDMI_AUD_CHAN_TYPE_6_1:
+	case HDMI_AUD_CHAN_TYPE_6_1_CS:
+	case HDMI_AUD_CHAN_TYPE_6_1_CH:
+	case HDMI_AUD_CHAN_TYPE_6_1_OH:
+	case HDMI_AUD_CHAN_TYPE_6_1_CHR:
+	case HDMI_AUD_CHAN_TYPE_7_0:
+	case HDMI_AUD_CHAN_TYPE_7_0_LH_RH:
+	case HDMI_AUD_CHAN_TYPE_7_0_LSR_RSR:
+	case HDMI_AUD_CHAN_TYPE_7_0_LC_RC:
+	case HDMI_AUD_CHAN_TYPE_7_0_LW_RW:
+	case HDMI_AUD_CHAN_TYPE_7_0_LSD_RSD:
+	case HDMI_AUD_CHAN_TYPE_7_0_LSS_RSS:
+	case HDMI_AUD_CHAN_TYPE_7_0_LHS_RHS:
+	case HDMI_AUD_CHAN_TYPE_7_0_CS_CH:
+	case HDMI_AUD_CHAN_TYPE_7_0_CS_OH:
+	case HDMI_AUD_CHAN_TYPE_7_0_CS_CHR:
+	case HDMI_AUD_CHAN_TYPE_7_0_CH_OH:
+	case HDMI_AUD_CHAN_TYPE_7_0_CH_CHR:
+	case HDMI_AUD_CHAN_TYPE_7_0_OH_CHR:
+	case HDMI_AUD_CHAN_TYPE_7_0_LSS_RSS_LSR_RSR:
+	case HDMI_AUD_CHAN_TYPE_8_0_LH_RH_CS:
+		return 7;
+	case HDMI_AUD_CHAN_TYPE_7_1:
+	case HDMI_AUD_CHAN_TYPE_7_1_LH_RH:
+	case HDMI_AUD_CHAN_TYPE_7_1_LSR_RSR:
+	case HDMI_AUD_CHAN_TYPE_7_1_LC_RC:
+	case HDMI_AUD_CHAN_TYPE_7_1_LW_RW:
+	case HDMI_AUD_CHAN_TYPE_7_1_LSD_RSD:
+	case HDMI_AUD_CHAN_TYPE_7_1_LSS_RSS:
+	case HDMI_AUD_CHAN_TYPE_7_1_LHS_RHS:
+	case HDMI_AUD_CHAN_TYPE_7_1_CS_CH:
+	case HDMI_AUD_CHAN_TYPE_7_1_CS_OH:
+	case HDMI_AUD_CHAN_TYPE_7_1_CS_CHR:
+	case HDMI_AUD_CHAN_TYPE_7_1_CH_OH:
+	case HDMI_AUD_CHAN_TYPE_7_1_CH_CHR:
+	case HDMI_AUD_CHAN_TYPE_7_1_OH_CHR:
+	case HDMI_AUD_CHAN_TYPE_7_1_LSS_RSS_LSR_RSR:
+		return 8;
+	default:
+		return 2;
+	}
+}
+
+static int mtk_hdmi_video_change_vpll(struct mtk_hdmi *hdmi, u32 clock)
+{
+	unsigned long rate;
+	int ret;
+
+	/* The DPI driver already should have set TVDPLL to the correct rate */
+	ret = clk_set_rate(hdmi->clk[MTK_HDMI_CLK_HDMI_PLL], clock);
+	if (ret) {
+		dev_err(hdmi->dev, "Failed to set PLL to %u Hz: %d\n", clock,
+			ret);
+		return ret;
+	}
+
+	rate = clk_get_rate(hdmi->clk[MTK_HDMI_CLK_HDMI_PLL]);
+
+	if (DIV_ROUND_CLOSEST(rate, 1000) != DIV_ROUND_CLOSEST(clock, 1000))
+		dev_warn(hdmi->dev, "Want PLL %u Hz, got %lu Hz\n", clock,
+			 rate);
+	else
+		dev_dbg(hdmi->dev, "Want PLL %u Hz, got %lu Hz\n", clock, rate);
+
+	mtk_hdmi_hw_config_sys(hdmi);
+	mtk_hdmi_hw_set_deep_color_mode(hdmi);
+	return 0;
+}
+
+static void mtk_hdmi_video_set_display_mode(struct mtk_hdmi *hdmi,
+					    struct drm_display_mode *mode)
+{
+	mtk_hdmi_hw_reset(hdmi);
+	mtk_hdmi_hw_enable_notice(hdmi, true);
+	mtk_hdmi_hw_write_int_mask(hdmi, 0xff);
+	mtk_hdmi_hw_enable_dvi_mode(hdmi, hdmi->dvi_mode);
+	mtk_hdmi_hw_ncts_auto_write_enable(hdmi, true);
+
+	mtk_hdmi_hw_msic_setting(hdmi, mode);
+}
+
+static int mtk_hdmi_aud_enable_packet(struct mtk_hdmi *hdmi, bool enable)
+{
+	mtk_hdmi_hw_send_aud_packet(hdmi, enable);
+	return 0;
+}
+
+static int mtk_hdmi_aud_on_off_hw_ncts(struct mtk_hdmi *hdmi, bool on)
+{
+	mtk_hdmi_hw_ncts_enable(hdmi, on);
+	return 0;
+}
+
+static int mtk_hdmi_aud_set_input(struct mtk_hdmi *hdmi)
+{
+	enum hdmi_aud_channel_type chan_type;
+	u8 chan_count;
+	bool dst;
+
+	mtk_hdmi_hw_aud_set_channel_swap(hdmi, HDMI_AUD_SWAP_LFE_CC);
+	mtk_hdmi_set_bits(hdmi, GRL_MIX_CTRL, MIX_CTRL_FLAT);
+
+	if (hdmi->aud_param.aud_input_type == HDMI_AUD_INPUT_SPDIF &&
+	    hdmi->aud_param.aud_codec == HDMI_AUDIO_CODING_TYPE_DST) {
+		mtk_hdmi_hw_aud_set_bit_num(hdmi, HDMI_AUDIO_SAMPLE_SIZE_24);
+	} else if (hdmi->aud_param.aud_i2s_fmt == HDMI_I2S_MODE_LJT_24BIT) {
+		hdmi->aud_param.aud_i2s_fmt = HDMI_I2S_MODE_LJT_16BIT;
+	}
+
+	mtk_hdmi_hw_aud_set_i2s_fmt(hdmi, hdmi->aud_param.aud_i2s_fmt);
+	mtk_hdmi_hw_aud_set_bit_num(hdmi, HDMI_AUDIO_SAMPLE_SIZE_24);
+
+	dst = ((hdmi->aud_param.aud_input_type == HDMI_AUD_INPUT_SPDIF) &&
+	       (hdmi->aud_param.aud_codec == HDMI_AUDIO_CODING_TYPE_DST));
+	mtk_hdmi_hw_audio_config(hdmi, dst);
+
+	if (hdmi->aud_param.aud_input_type == HDMI_AUD_INPUT_SPDIF)
+		chan_type = HDMI_AUD_CHAN_TYPE_2_0;
+	else
+		chan_type = hdmi->aud_param.aud_input_chan_type;
+	chan_count = mtk_hdmi_aud_get_chnl_count(chan_type);
+	mtk_hdmi_hw_aud_set_i2s_chan_num(hdmi, chan_type, chan_count);
+	mtk_hdmi_hw_aud_set_input_type(hdmi, hdmi->aud_param.aud_input_type);
+
+	return 0;
+}
+
+static int mtk_hdmi_aud_set_src(struct mtk_hdmi *hdmi,
+				struct drm_display_mode *display_mode)
+{
+	unsigned int sample_rate = hdmi->aud_param.codec_params.sample_rate;
+
+	mtk_hdmi_aud_on_off_hw_ncts(hdmi, false);
+	mtk_hdmi_hw_aud_src_disable(hdmi);
+	mtk_hdmi_clear_bits(hdmi, GRL_CFG2, CFG2_ACLK_INV);
+
+	if (hdmi->aud_param.aud_input_type == HDMI_AUD_INPUT_I2S) {
+		switch (sample_rate) {
+		case 32000:
+		case 44100:
+		case 48000:
+		case 88200:
+		case 96000:
+			break;
+		default:
+			return -EINVAL;
+		}
+		mtk_hdmi_hw_aud_set_mclk(hdmi, hdmi->aud_param.aud_mclk);
+	} else {
+		switch (sample_rate) {
+		case 32000:
+		case 44100:
+		case 48000:
+			break;
+		default:
+			return -EINVAL;
+		}
+		mtk_hdmi_hw_aud_set_mclk(hdmi, HDMI_AUD_MCLK_128FS);
+	}
+
+	mtk_hdmi_hw_aud_set_ncts(hdmi, sample_rate, display_mode->clock);
+
+	mtk_hdmi_hw_aud_src_reenable(hdmi);
+	return 0;
+}
+
+static int mtk_hdmi_aud_output_config(struct mtk_hdmi *hdmi,
+				      struct drm_display_mode *display_mode)
+{
+	mtk_hdmi_hw_aud_mute(hdmi);
+	mtk_hdmi_aud_enable_packet(hdmi, false);
+
+	mtk_hdmi_aud_set_input(hdmi);
+	mtk_hdmi_aud_set_src(hdmi, display_mode);
+	mtk_hdmi_hw_aud_set_channel_status(hdmi,
+			hdmi->aud_param.codec_params.iec.status);
+
+	usleep_range(50, 100);
+
+	mtk_hdmi_aud_on_off_hw_ncts(hdmi, true);
+	mtk_hdmi_aud_enable_packet(hdmi, true);
+	mtk_hdmi_hw_aud_unmute(hdmi);
+	return 0;
+}
+
+static int mtk_hdmi_setup_avi_infoframe(struct mtk_hdmi *hdmi,
+					struct drm_display_mode *mode)
+{
+	struct hdmi_avi_infoframe frame;
+	u8 buffer[17];
+	ssize_t err;
+
+	err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
+	if (err < 0) {
+		dev_err(hdmi->dev,
+			"Failed to get AVI infoframe from mode: %zd\n", err);
+		return err;
+	}
+
+	err = hdmi_avi_infoframe_pack(&frame, buffer, sizeof(buffer));
+	if (err < 0) {
+		dev_err(hdmi->dev, "Failed to pack AVI infoframe: %zd\n", err);
+		return err;
+	}
+
+	mtk_hdmi_hw_send_info_frame(hdmi, buffer, sizeof(buffer));
+	return 0;
+}
+
+static int mtk_hdmi_setup_spd_infoframe(struct mtk_hdmi *hdmi,
+					const char *vendor,
+					const char *product)
+{
+	struct hdmi_spd_infoframe frame;
+	u8 buffer[29];
+	ssize_t err;
+
+	err = hdmi_spd_infoframe_init(&frame, vendor, product);
+	if (err < 0) {
+		dev_err(hdmi->dev, "Failed to initialize SPD infoframe: %zd\n",
+			err);
+		return err;
+	}
+
+	err = hdmi_spd_infoframe_pack(&frame, buffer, sizeof(buffer));
+	if (err < 0) {
+		dev_err(hdmi->dev, "Failed to pack SDP infoframe: %zd\n", err);
+		return err;
+	}
+
+	mtk_hdmi_hw_send_info_frame(hdmi, buffer, sizeof(buffer));
+	return 0;
+}
+
+static int mtk_hdmi_setup_audio_infoframe(struct mtk_hdmi *hdmi)
+{
+	struct hdmi_audio_infoframe frame;
+	u8 buffer[14];
+	ssize_t err;
+
+	err = hdmi_audio_infoframe_init(&frame);
+	if (err < 0) {
+		dev_err(hdmi->dev, "Failed to setup audio infoframe: %zd\n",
+			err);
+		return err;
+	}
+
+	frame.coding_type = HDMI_AUDIO_CODING_TYPE_STREAM;
+	frame.sample_frequency = HDMI_AUDIO_SAMPLE_FREQUENCY_STREAM;
+	frame.sample_size = HDMI_AUDIO_SAMPLE_SIZE_STREAM;
+	frame.channels = mtk_hdmi_aud_get_chnl_count(
+					hdmi->aud_param.aud_input_chan_type);
+
+	err = hdmi_audio_infoframe_pack(&frame, buffer, sizeof(buffer));
+	if (err < 0) {
+		dev_err(hdmi->dev, "Failed to pack audio infoframe: %zd\n",
+			err);
+		return err;
+	}
+
+	mtk_hdmi_hw_send_info_frame(hdmi, buffer, sizeof(buffer));
+	return 0;
+}
+
+static int mtk_hdmi_setup_vendor_specific_infoframe(struct mtk_hdmi *hdmi,
+						struct drm_display_mode *mode)
+{
+	struct hdmi_vendor_infoframe frame;
+	u8 buffer[10];
+	ssize_t err;
+
+	err = drm_hdmi_vendor_infoframe_from_display_mode(&frame, mode);
+	if (err) {
+		dev_err(hdmi->dev,
+			"Failed to get vendor infoframe from mode: %zd\n", err);
+		return err;
+	}
+
+	err = hdmi_vendor_infoframe_pack(&frame, buffer, sizeof(buffer));
+	if (err) {
+		dev_err(hdmi->dev, "Failed to pack vendor infoframe: %zd\n",
+			err);
+		return err;
+	}
+
+	mtk_hdmi_hw_send_info_frame(hdmi, buffer, sizeof(buffer));
+	return 0;
+}
+
+static int mtk_hdmi_output_init(struct mtk_hdmi *hdmi)
+{
+	struct hdmi_audio_param *aud_param = &hdmi->aud_param;
+
+	hdmi->csp = HDMI_COLORSPACE_RGB;
+	aud_param->aud_codec = HDMI_AUDIO_CODING_TYPE_PCM;
+	aud_param->aud_sampe_size = HDMI_AUDIO_SAMPLE_SIZE_16;
+	aud_param->aud_input_type = HDMI_AUD_INPUT_I2S;
+	aud_param->aud_i2s_fmt = HDMI_I2S_MODE_I2S_24BIT;
+	aud_param->aud_mclk = HDMI_AUD_MCLK_128FS;
+	aud_param->aud_input_chan_type = HDMI_AUD_CHAN_TYPE_2_0;
+
+	return 0;
+}
+
+void mtk_hdmi_audio_enable(struct mtk_hdmi *hdmi)
+{
+	mtk_hdmi_aud_enable_packet(hdmi, true);
+	hdmi->audio_enable = true;
+}
+
+void mtk_hdmi_audio_disable(struct mtk_hdmi *hdmi)
+{
+	mtk_hdmi_aud_enable_packet(hdmi, false);
+	hdmi->audio_enable = false;
+}
+
+int mtk_hdmi_audio_set_param(struct mtk_hdmi *hdmi,
+			     struct hdmi_audio_param *param)
+{
+	if (!hdmi->audio_enable) {
+		dev_err(hdmi->dev, "hdmi audio is in disable state!\n");
+		return -EINVAL;
+	}
+	dev_dbg(hdmi->dev, "codec:%d, input:%d, channel:%d, fs:%d\n",
+		param->aud_codec, param->aud_input_type,
+		param->aud_input_chan_type, param->codec_params.sample_rate);
+	memcpy(&hdmi->aud_param, param, sizeof(*param));
+	return mtk_hdmi_aud_output_config(hdmi, &hdmi->mode);
+}
+
+static int mtk_hdmi_output_set_display_mode(struct mtk_hdmi *hdmi,
+					    struct drm_display_mode *mode)
+{
+	int ret;
+
+	mtk_hdmi_hw_vid_black(hdmi, true);
+	mtk_hdmi_hw_aud_mute(hdmi);
+	mtk_hdmi_hw_send_av_mute(hdmi);
+	phy_power_off(hdmi->phy);
+
+	ret = mtk_hdmi_video_change_vpll(hdmi,
+					 mode->clock * 1000);
+	if (ret) {
+		dev_err(hdmi->dev, "Failed to set vpll: %d\n", ret);
+		return ret;
+	}
+	mtk_hdmi_video_set_display_mode(hdmi, mode);
+
+	phy_power_on(hdmi->phy);
+	mtk_hdmi_aud_output_config(hdmi, mode);
+
+	mtk_hdmi_setup_audio_infoframe(hdmi);
+	mtk_hdmi_setup_avi_infoframe(hdmi, mode);
+	mtk_hdmi_setup_spd_infoframe(hdmi, "mediatek", "On-chip HDMI");
+	if (mode->flags & DRM_MODE_FLAG_3D_MASK)
+		mtk_hdmi_setup_vendor_specific_infoframe(hdmi, mode);
+
+	mtk_hdmi_hw_vid_black(hdmi, false);
+	mtk_hdmi_hw_aud_unmute(hdmi);
+	mtk_hdmi_hw_send_av_unmute(hdmi);
+
+	return 0;
+}
+
+static const char * const mtk_hdmi_clk_names[MTK_HDMI_CLK_COUNT] = {
+	[MTK_HDMI_CLK_HDMI_PIXEL] = "pixel",
+	[MTK_HDMI_CLK_HDMI_PLL] = "pll",
+	[MTK_HDMI_CLK_AUD_BCLK] = "bclk",
+	[MTK_HDMI_CLK_AUD_SPDIF] = "spdif",
+};
+
+static int mtk_hdmi_get_all_clk(struct mtk_hdmi *hdmi,
+				struct device_node *np)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mtk_hdmi_clk_names); i++) {
+		hdmi->clk[i] = of_clk_get_by_name(np,
+						  mtk_hdmi_clk_names[i]);
+		if (IS_ERR(hdmi->clk[i]))
+			return PTR_ERR(hdmi->clk[i]);
+	}
+	return 0;
+}
+
+static int mtk_hdmi_clk_enable_audio(struct mtk_hdmi *hdmi)
+{
+	int ret;
+
+	ret = clk_prepare_enable(hdmi->clk[MTK_HDMI_CLK_AUD_BCLK]);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(hdmi->clk[MTK_HDMI_CLK_AUD_SPDIF]);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	clk_disable_unprepare(hdmi->clk[MTK_HDMI_CLK_AUD_BCLK]);
+	return ret;
+}
+
+static void mtk_hdmi_clk_disable_audio(struct mtk_hdmi *hdmi)
+{
+	clk_disable_unprepare(hdmi->clk[MTK_HDMI_CLK_AUD_BCLK]);
+	clk_disable_unprepare(hdmi->clk[MTK_HDMI_CLK_AUD_SPDIF]);
+}
+
+static enum drm_connector_status hdmi_conn_detect(struct drm_connector *conn,
+						  bool force)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_conn(conn);
+
+	return mtk_cec_hpd_high(hdmi->cec_dev) ?
+	       connector_status_connected : connector_status_disconnected;
+}
+
+static void hdmi_conn_destroy(struct drm_connector *conn)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_conn(conn);
+
+	mtk_cec_set_hpd_event(hdmi->cec_dev, NULL, NULL);
+
+	drm_connector_cleanup(conn);
+}
+
+static int mtk_hdmi_conn_get_modes(struct drm_connector *conn)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_conn(conn);
+	struct edid *edid;
+	int ret;
+
+	if (!hdmi->ddc_adpt)
+		return -ENODEV;
+
+	edid = drm_get_edid(conn, hdmi->ddc_adpt);
+	if (!edid)
+		return -ENODEV;
+
+	hdmi->dvi_mode = !drm_detect_monitor_audio(edid);
+
+	drm_mode_connector_update_edid_property(conn, edid);
+
+	ret = drm_add_edid_modes(conn, edid);
+	drm_edid_to_eld(conn, edid);
+	kfree(edid);
+	return ret;
+}
+
+static int mtk_hdmi_conn_mode_valid(struct drm_connector *conn,
+				    struct drm_display_mode *mode)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_conn(conn);
+
+	dev_dbg(hdmi->dev, "xres=%d, yres=%d, refresh=%d, intl=%d clock=%d\n",
+		mode->hdisplay, mode->vdisplay, mode->vrefresh,
+		!!(mode->flags & DRM_MODE_FLAG_INTERLACE), mode->clock * 1000);
+
+	if (hdmi->bridge.next) {
+		struct drm_display_mode adjusted_mode;
+
+		drm_mode_copy(&adjusted_mode, mode);
+		if (!drm_bridge_mode_fixup(hdmi->bridge.next, mode,
+					   &adjusted_mode))
+			return MODE_BAD;
+	}
+
+	if (mode->clock < 27000)
+		return MODE_CLOCK_LOW;
+	if (mode->clock > 297000)
+		return MODE_CLOCK_HIGH;
+
+	return drm_mode_validate_size(mode, 0x1fff, 0x1fff);
+}
+
+static struct drm_encoder *mtk_hdmi_conn_best_enc(struct drm_connector *conn)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_conn(conn);
+
+	return hdmi->bridge.encoder;
+}
+
+static const struct drm_connector_funcs mtk_hdmi_connector_funcs = {
+	.dpms = drm_atomic_helper_connector_dpms,
+	.detect = hdmi_conn_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = hdmi_conn_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static const struct drm_connector_helper_funcs
+		mtk_hdmi_connector_helper_funcs = {
+	.get_modes = mtk_hdmi_conn_get_modes,
+	.mode_valid = mtk_hdmi_conn_mode_valid,
+	.best_encoder = mtk_hdmi_conn_best_enc,
+};
+
+static void mtk_hdmi_hpd_event(bool hpd, struct device *dev)
+{
+	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
+
+	if (hdmi && hdmi->bridge.encoder && hdmi->bridge.encoder->dev)
+		drm_helper_hpd_irq_event(hdmi->bridge.encoder->dev);
+}
+
+/*
+ * Bridge callbacks
+ */
+
+static int mtk_hdmi_bridge_attach(struct drm_bridge *bridge)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge);
+	int ret;
+
+	ret = drm_connector_init(bridge->encoder->dev, &hdmi->conn,
+				 &mtk_hdmi_connector_funcs,
+				 DRM_MODE_CONNECTOR_HDMIA);
+	if (ret) {
+		dev_err(hdmi->dev, "Failed to initialize connector: %d\n", ret);
+		return ret;
+	}
+	drm_connector_helper_add(&hdmi->conn, &mtk_hdmi_connector_helper_funcs);
+
+	hdmi->conn.polled = DRM_CONNECTOR_POLL_HPD;
+	hdmi->conn.interlace_allowed = true;
+	hdmi->conn.doublescan_allowed = false;
+
+	ret = drm_mode_connector_attach_encoder(&hdmi->conn,
+						bridge->encoder);
+	if (ret) {
+		dev_err(hdmi->dev,
+			"Failed to attach connector to encoder: %d\n", ret);
+		return ret;
+	}
+
+	if (bridge->next) {
+		bridge->next->encoder = bridge->encoder;
+		ret = drm_bridge_attach(bridge->encoder->dev, bridge->next);
+		if (ret) {
+			dev_err(hdmi->dev,
+				"Failed to attach external bridge: %d\n", ret);
+			return ret;
+		}
+	}
+
+	mtk_cec_set_hpd_event(hdmi->cec_dev, mtk_hdmi_hpd_event, hdmi->dev);
+
+	return 0;
+}
+
+static bool mtk_hdmi_bridge_mode_fixup(struct drm_bridge *bridge,
+				       const struct drm_display_mode *mode,
+				       struct drm_display_mode *adjusted_mode)
+{
+	return true;
+}
+
+static void mtk_hdmi_bridge_disable(struct drm_bridge *bridge)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge);
+
+	if (!hdmi->enabled)
+		return;
+
+	phy_power_off(hdmi->phy);
+	clk_disable_unprepare(hdmi->clk[MTK_HDMI_CLK_HDMI_PIXEL]);
+	clk_disable_unprepare(hdmi->clk[MTK_HDMI_CLK_HDMI_PLL]);
+
+	hdmi->enabled = false;
+}
+
+static void mtk_hdmi_bridge_post_disable(struct drm_bridge *bridge)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge);
+
+	if (!hdmi->powered)
+		return;
+
+	mtk_hdmi_hw_1p4_version_enable(hdmi, true);
+	mtk_hdmi_hw_make_reg_writable(hdmi, false);
+
+	hdmi->powered = false;
+}
+
+static void mtk_hdmi_bridge_mode_set(struct drm_bridge *bridge,
+				     struct drm_display_mode *mode,
+				     struct drm_display_mode *adjusted_mode)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge);
+
+	dev_dbg(hdmi->dev, "cur info: name:%s, hdisplay:%d\n",
+		adjusted_mode->name, adjusted_mode->hdisplay);
+	dev_dbg(hdmi->dev, "hsync_start:%d,hsync_end:%d, htotal:%d",
+		adjusted_mode->hsync_start, adjusted_mode->hsync_end,
+		adjusted_mode->htotal);
+	dev_dbg(hdmi->dev, "hskew:%d, vdisplay:%d\n",
+		adjusted_mode->hskew, adjusted_mode->vdisplay);
+	dev_dbg(hdmi->dev, "vsync_start:%d, vsync_end:%d, vtotal:%d",
+		adjusted_mode->vsync_start, adjusted_mode->vsync_end,
+		adjusted_mode->vtotal);
+	dev_dbg(hdmi->dev, "vscan:%d, flag:%d\n",
+		adjusted_mode->vscan, adjusted_mode->flags);
+
+	drm_mode_copy(&hdmi->mode, adjusted_mode);
+}
+
+static void mtk_hdmi_bridge_pre_enable(struct drm_bridge *bridge)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge);
+
+	mtk_hdmi_hw_make_reg_writable(hdmi, true);
+	mtk_hdmi_hw_1p4_version_enable(hdmi, true);
+
+	hdmi->powered = true;
+}
+
+static void mtk_hdmi_bridge_enable(struct drm_bridge *bridge)
+{
+	struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge);
+
+	mtk_hdmi_output_set_display_mode(hdmi, &hdmi->mode);
+	clk_prepare_enable(hdmi->clk[MTK_HDMI_CLK_HDMI_PLL]);
+	clk_prepare_enable(hdmi->clk[MTK_HDMI_CLK_HDMI_PIXEL]);
+	phy_power_on(hdmi->phy);
+
+	hdmi->enabled = true;
+}
+
+static const struct drm_bridge_funcs mtk_hdmi_bridge_funcs = {
+	.attach = mtk_hdmi_bridge_attach,
+	.mode_fixup = mtk_hdmi_bridge_mode_fixup,
+	.disable = mtk_hdmi_bridge_disable,
+	.post_disable = mtk_hdmi_bridge_post_disable,
+	.mode_set = mtk_hdmi_bridge_mode_set,
+	.pre_enable = mtk_hdmi_bridge_pre_enable,
+	.enable = mtk_hdmi_bridge_enable,
+};
+
+static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
+				   struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct device_node *cec_np, *port, *ep, *remote, *i2c_np;
+	struct platform_device *cec_pdev;
+	struct regmap *regmap;
+	struct resource *mem;
+	int ret;
+
+	ret = mtk_hdmi_get_all_clk(hdmi, np);
+	if (ret) {
+		dev_err(dev, "Failed to get clocks: %d\n", ret);
+		return ret;
+	}
+
+	/* The CEC module handles HDMI hotplug detection */
+	cec_np = of_find_compatible_node(np->parent, NULL,
+					 "mediatek,mt8173-cec");
+	if (!cec_np) {
+		dev_err(dev, "Failed to find CEC node\n");
+		return -EINVAL;
+	}
+
+	cec_pdev = of_find_device_by_node(cec_np);
+	if (!cec_pdev) {
+		dev_err(hdmi->dev, "Waiting for CEC device %s\n",
+			cec_np->full_name);
+		return -EPROBE_DEFER;
+	}
+	hdmi->cec_dev = &cec_pdev->dev;
+
+	/*
+	 * The mediatek,syscon-hdmi property contains a phandle link to the
+	 * MMSYS_CONFIG device and the register offset of the HDMI_SYS_CFG
+	 * registers it contains.
+	 */
+	regmap = syscon_regmap_lookup_by_phandle(np, "mediatek,syscon-hdmi");
+	ret = of_property_read_u32_index(np, "mediatek,syscon-hdmi", 1,
+					 &hdmi->sys_offset);
+	if (IS_ERR(regmap))
+		ret = PTR_ERR(regmap);
+	if (ret) {
+		ret = PTR_ERR(regmap);
+		dev_err(dev,
+			"Failed to get system configuration registers: %d\n",
+			ret);
+		return ret;
+	}
+	hdmi->sys_regmap = regmap;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	hdmi->regs = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(hdmi->regs))
+		return PTR_ERR(hdmi->regs);
+
+	port = of_graph_get_port_by_id(np, 1);
+	if (!port) {
+		dev_err(dev, "Missing output port node\n");
+		return -EINVAL;
+	}
+
+	ep = of_get_child_by_name(port, "endpoint");
+	if (!ep) {
+		dev_err(dev, "Missing endpoint node in port %s\n",
+			port->full_name);
+		of_node_put(port);
+		return -EINVAL;
+	}
+	of_node_put(port);
+
+	remote = of_graph_get_remote_port_parent(ep);
+	if (!remote) {
+		dev_err(dev, "Missing connector/bridge node for endpoint %s\n",
+			ep->full_name);
+		of_node_put(ep);
+		return -EINVAL;
+	}
+	of_node_put(ep);
+
+	if (!of_device_is_compatible(remote, "hdmi-connector")) {
+		hdmi->bridge.next = of_drm_find_bridge(remote);
+		if (!hdmi->bridge.next) {
+			dev_err(dev, "Waiting for external bridge\n");
+			of_node_put(remote);
+			return -EPROBE_DEFER;
+		}
+	}
+
+	i2c_np = of_parse_phandle(remote, "ddc-i2c-bus", 0);
+	if (!i2c_np) {
+		dev_err(dev, "Failed to find ddc-i2c-bus node in %s\n",
+			remote->full_name);
+		of_node_put(remote);
+		return -EINVAL;
+	}
+	of_node_put(remote);
+
+	hdmi->ddc_adpt = of_find_i2c_adapter_by_node(i2c_np);
+	if (!hdmi->ddc_adpt) {
+		dev_err(dev, "Failed to get ddc i2c adapter by node\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * HDMI audio codec callbacks
+ */
+
+static int mtk_hdmi_audio_hw_params(struct device *dev, void *data,
+				    struct hdmi_codec_daifmt *daifmt,
+				    struct hdmi_codec_params *params)
+{
+	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
+	struct hdmi_audio_param hdmi_params;
+	unsigned int chan = params->cea.channels;
+
+	dev_dbg(hdmi->dev, "%s: %u Hz, %d bit, %d channels\n", __func__,
+		params->sample_rate, params->sample_width, chan);
+
+	if (!hdmi->bridge.encoder)
+		return -ENODEV;
+
+	switch (chan) {
+	case 2:
+		hdmi_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_2_0;
+		break;
+	case 4:
+		hdmi_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_4_0;
+		break;
+	case 6:
+		hdmi_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_5_1;
+		break;
+	case 8:
+		hdmi_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_7_1;
+		break;
+	default:
+		dev_err(hdmi->dev, "channel[%d] not supported!\n", chan);
+		return -EINVAL;
+	}
+
+	switch (params->sample_rate) {
+	case 32000:
+	case 44100:
+	case 48000:
+	case 88200:
+	case 96000:
+	case 176400:
+	case 192000:
+		break;
+	default:
+		dev_err(hdmi->dev, "rate[%d] not supported!\n",
+			params->sample_rate);
+		return -EINVAL;
+	}
+
+	switch (daifmt->fmt) {
+	case HDMI_I2S:
+		hdmi_params.aud_codec = HDMI_AUDIO_CODING_TYPE_PCM;
+		hdmi_params.aud_sampe_size = HDMI_AUDIO_SAMPLE_SIZE_16;
+		hdmi_params.aud_input_type = HDMI_AUD_INPUT_I2S;
+		hdmi_params.aud_i2s_fmt = HDMI_I2S_MODE_I2S_24BIT;
+		hdmi_params.aud_mclk = HDMI_AUD_MCLK_128FS;
+		break;
+	default:
+		dev_err(hdmi->dev, "%s: Invalid DAI format %d\n", __func__,
+			daifmt->fmt);
+		return -EINVAL;
+	}
+
+	memcpy(&hdmi_params.codec_params, params,
+	       sizeof(hdmi_params.codec_params));
+
+	mtk_hdmi_audio_set_param(hdmi, &hdmi_params);
+
+	return 0;
+}
+
+static int mtk_hdmi_audio_startup(struct device *dev, void *data)
+{
+	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	mtk_hdmi_audio_enable(hdmi);
+
+	return 0;
+}
+
+static void mtk_hdmi_audio_shutdown(struct device *dev, void *data)
+{
+	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	mtk_hdmi_audio_disable(hdmi);
+}
+
+int mtk_hdmi_audio_digital_mute(struct device *dev, void *data, bool enable)
+{
+	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "%s(%d)\n", __func__, enable);
+
+	if (enable)
+		mtk_hdmi_hw_aud_mute(hdmi);
+	else
+		mtk_hdmi_hw_aud_unmute(hdmi);
+
+	return 0;
+}
+
+static int mtk_hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf, size_t len)
+{
+	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	memcpy(buf, hdmi->conn.eld, min(sizeof(hdmi->conn.eld), len));
+
+	return 0;
+}
+
+static const struct hdmi_codec_ops mtk_hdmi_audio_codec_ops = {
+	.hw_params = mtk_hdmi_audio_hw_params,
+	.audio_startup = mtk_hdmi_audio_startup,
+	.audio_shutdown = mtk_hdmi_audio_shutdown,
+	.digital_mute = mtk_hdmi_audio_digital_mute,
+	.get_eld = mtk_hdmi_audio_get_eld,
+};
+
+static void mtk_hdmi_register_audio_driver(struct device *dev)
+{
+	struct hdmi_codec_pdata codec_data = {
+		.ops = &mtk_hdmi_audio_codec_ops,
+		.max_i2s_channels = 2,
+		.i2s = 1,
+	};
+	struct platform_device *pdev;
+
+	pdev = platform_device_register_data(dev, HDMI_CODEC_DRV_NAME,
+					     PLATFORM_DEVID_AUTO, &codec_data,
+					     sizeof(codec_data));
+	if (IS_ERR(pdev))
+		return;
+
+	DRM_INFO("%s driver bound to HDMI\n", HDMI_CODEC_DRV_NAME);
+}
+
+static int mtk_drm_hdmi_probe(struct platform_device *pdev)
+{
+	struct mtk_hdmi *hdmi;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	hdmi = devm_kzalloc(dev, sizeof(*hdmi), GFP_KERNEL);
+	if (!hdmi)
+		return -ENOMEM;
+
+	hdmi->dev = dev;
+
+	ret = mtk_hdmi_dt_parse_pdata(hdmi, pdev);
+	if (ret)
+		return ret;
+
+	hdmi->phy = devm_phy_get(dev, "hdmi");
+	if (IS_ERR(hdmi->phy)) {
+		ret = PTR_ERR(hdmi->phy);
+		dev_err(dev, "Failed to get HDMI PHY: %d\n", ret);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, hdmi);
+
+	ret = mtk_hdmi_output_init(hdmi);
+	if (ret) {
+		dev_err(dev, "Failed to initialize hdmi output\n");
+		return ret;
+	}
+
+	mtk_hdmi_register_audio_driver(dev);
+
+	hdmi->bridge.funcs = &mtk_hdmi_bridge_funcs;
+	hdmi->bridge.of_node = pdev->dev.of_node;
+	ret = drm_bridge_add(&hdmi->bridge);
+	if (ret) {
+		dev_err(dev, "failed to add bridge, ret = %d\n", ret);
+		return ret;
+	}
+
+	ret = mtk_hdmi_clk_enable_audio(hdmi);
+	if (ret) {
+		dev_err(dev, "Failed to enable audio clocks: %d\n", ret);
+		goto err_bridge_remove;
+	}
+
+	dev_dbg(dev, "mediatek hdmi probe success\n");
+	return 0;
+
+err_bridge_remove:
+	drm_bridge_remove(&hdmi->bridge);
+	return ret;
+}
+
+static int mtk_drm_hdmi_remove(struct platform_device *pdev)
+{
+	struct mtk_hdmi *hdmi = platform_get_drvdata(pdev);
+
+	drm_bridge_remove(&hdmi->bridge);
+	mtk_hdmi_clk_disable_audio(hdmi);
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int mtk_hdmi_suspend(struct device *dev)
+{
+	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
+
+	mtk_hdmi_clk_disable_audio(hdmi);
+	dev_dbg(dev, "hdmi suspend success!\n");
+	return 0;
+}
+
+static int mtk_hdmi_resume(struct device *dev)
+{
+	struct mtk_hdmi *hdmi = dev_get_drvdata(dev);
+	int ret = 0;
+
+	ret = mtk_hdmi_clk_enable_audio(hdmi);
+	if (ret) {
+		dev_err(dev, "hdmi resume failed!\n");
+		return ret;
+	}
+
+	dev_dbg(dev, "hdmi resume success!\n");
+	return 0;
+}
+#endif
+static SIMPLE_DEV_PM_OPS(mtk_hdmi_pm_ops,
+			 mtk_hdmi_suspend, mtk_hdmi_resume);
+
+static const struct of_device_id mtk_drm_hdmi_of_ids[] = {
+	{ .compatible = "mediatek,mt8173-hdmi", },
+	{}
+};
+
+static struct platform_driver mtk_hdmi_driver = {
+	.probe = mtk_drm_hdmi_probe,
+	.remove = mtk_drm_hdmi_remove,
+	.driver = {
+		.name = "mediatek-drm-hdmi",
+		.of_match_table = mtk_drm_hdmi_of_ids,
+		.pm = &mtk_hdmi_pm_ops,
+	},
+};
+
+static struct platform_driver * const mtk_hdmi_drivers[] = {
+	&mtk_hdmi_phy_driver,
+	&mtk_hdmi_ddc_driver,
+	&mtk_cec_driver,
+	&mtk_hdmi_driver,
+};
+
+static int __init mtk_hdmitx_init(void)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mtk_hdmi_drivers); i++) {
+		ret = platform_driver_register(mtk_hdmi_drivers[i]);
+		if (ret < 0) {
+			pr_err("Failed to register %s driver: %d\n",
+			       mtk_hdmi_drivers[i]->driver.name, ret);
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	while (--i >= 0)
+		platform_driver_unregister(mtk_hdmi_drivers[i]);
+
+	return ret;
+}
+
+static void __exit mtk_hdmitx_exit(void)
+{
+	int i;
+
+	for (i = ARRAY_SIZE(mtk_hdmi_drivers) - 1; i >= 0; i--)
+		platform_driver_unregister(mtk_hdmi_drivers[i]);
+}
+
+module_init(mtk_hdmitx_init);
+module_exit(mtk_hdmitx_exit);
+
+MODULE_AUTHOR("Jie Qiu <jie.qiu@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek HDMI Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.h b/drivers/gpu/drm/mediatek/mtk_hdmi.h
new file mode 100644
index 000000000000..6371b3de1ff6
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Jie Qiu <jie.qiu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef _MTK_HDMI_CTRL_H
+#define _MTK_HDMI_CTRL_H
+
+struct platform_driver;
+
+extern struct platform_driver mtk_cec_driver;
+extern struct platform_driver mtk_hdmi_ddc_driver;
+extern struct platform_driver mtk_hdmi_phy_driver;
+
+#endif /* _MTK_HDMI_CTRL_H */
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
new file mode 100644
index 000000000000..33c9e1bdb114
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
@@ -0,0 +1,358 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Jie Qiu <jie.qiu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/time.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+
+#define SIF1_CLOK		(288)
+#define DDC_DDCMCTL0		(0x0)
+#define DDCM_ODRAIN			BIT(31)
+#define DDCM_CLK_DIV_OFFSET		(16)
+#define DDCM_CLK_DIV_MASK		(0xfff << 16)
+#define DDCM_CS_STATUS			BIT(4)
+#define DDCM_SCL_STATE			BIT(3)
+#define DDCM_SDA_STATE			BIT(2)
+#define DDCM_SM0EN			BIT(1)
+#define DDCM_SCL_STRECH			BIT(0)
+#define DDC_DDCMCTL1		(0x4)
+#define DDCM_ACK_OFFSET			(16)
+#define DDCM_ACK_MASK			(0xff << 16)
+#define DDCM_PGLEN_OFFSET		(8)
+#define DDCM_PGLEN_MASK			(0x7 << 8)
+#define DDCM_SIF_MODE_OFFSET		(4)
+#define DDCM_SIF_MODE_MASK		(0x7 << 4)
+#define DDCM_START			(0x1)
+#define DDCM_WRITE_DATA			(0x2)
+#define DDCM_STOP			(0x3)
+#define DDCM_READ_DATA_NO_ACK		(0x4)
+#define DDCM_READ_DATA_ACK		(0x5)
+#define DDCM_TRI			BIT(0)
+#define DDC_DDCMD0		(0x8)
+#define DDCM_DATA3			(0xff << 24)
+#define DDCM_DATA2			(0xff << 16)
+#define DDCM_DATA1			(0xff << 8)
+#define DDCM_DATA0			(0xff << 0)
+#define DDC_DDCMD1		(0xc)
+#define DDCM_DATA7			(0xff << 24)
+#define DDCM_DATA6			(0xff << 16)
+#define DDCM_DATA5			(0xff << 8)
+#define DDCM_DATA4			(0xff << 0)
+
+struct mtk_hdmi_ddc {
+	struct i2c_adapter adap;
+	struct clk *clk;
+	void __iomem *regs;
+};
+
+static inline void sif_set_bit(struct mtk_hdmi_ddc *ddc, unsigned int offset,
+			       unsigned int val)
+{
+	writel(readl(ddc->regs + offset) | val, ddc->regs + offset);
+}
+
+static inline void sif_clr_bit(struct mtk_hdmi_ddc *ddc, unsigned int offset,
+			       unsigned int val)
+{
+	writel(readl(ddc->regs + offset) & ~val, ddc->regs + offset);
+}
+
+static inline bool sif_bit_is_set(struct mtk_hdmi_ddc *ddc, unsigned int offset,
+				  unsigned int val)
+{
+	return (readl(ddc->regs + offset) & val) == val;
+}
+
+static inline void sif_write_mask(struct mtk_hdmi_ddc *ddc, unsigned int offset,
+				  unsigned int mask, unsigned int shift,
+				  unsigned int val)
+{
+	unsigned int tmp;
+
+	tmp = readl(ddc->regs + offset);
+	tmp &= ~mask;
+	tmp |= (val << shift) & mask;
+	writel(tmp, ddc->regs + offset);
+}
+
+static inline unsigned int sif_read_mask(struct mtk_hdmi_ddc *ddc,
+					 unsigned int offset, unsigned int mask,
+					 unsigned int shift)
+{
+	return (readl(ddc->regs + offset) & mask) >> shift;
+}
+
+static void ddcm_trigger_mode(struct mtk_hdmi_ddc *ddc, int mode)
+{
+	u32 val;
+
+	sif_write_mask(ddc, DDC_DDCMCTL1, DDCM_SIF_MODE_MASK,
+		       DDCM_SIF_MODE_OFFSET, mode);
+	sif_set_bit(ddc, DDC_DDCMCTL1, DDCM_TRI);
+	readl_poll_timeout(ddc->regs + DDC_DDCMCTL1, val,
+			   (val & DDCM_TRI) != DDCM_TRI, 4, 20000);
+}
+
+static int mtk_hdmi_ddc_read_msg(struct mtk_hdmi_ddc *ddc, struct i2c_msg *msg)
+{
+	struct device *dev = ddc->adap.dev.parent;
+	u32 remain_count, ack_count, ack_final, read_count, temp_count;
+	u32 index = 0;
+	u32 ack;
+	int i;
+
+	ddcm_trigger_mode(ddc, DDCM_START);
+	sif_write_mask(ddc, DDC_DDCMD0, 0xff, 0, (msg->addr << 1) | 0x01);
+	sif_write_mask(ddc, DDC_DDCMCTL1, DDCM_PGLEN_MASK, DDCM_PGLEN_OFFSET,
+		       0x00);
+	ddcm_trigger_mode(ddc, DDCM_WRITE_DATA);
+	ack = sif_read_mask(ddc, DDC_DDCMCTL1, DDCM_ACK_MASK, DDCM_ACK_OFFSET);
+	dev_dbg(dev, "ack = 0x%x\n", ack);
+	if (ack != 0x01) {
+		dev_err(dev, "i2c ack err!\n");
+		return -ENXIO;
+	}
+
+	remain_count = msg->len;
+	ack_count = (msg->len - 1) / 8;
+	ack_final = 0;
+
+	while (remain_count > 0) {
+		if (ack_count > 0) {
+			read_count = 8;
+			ack_final = 0;
+			ack_count--;
+		} else {
+			read_count = remain_count;
+			ack_final = 1;
+		}
+
+		sif_write_mask(ddc, DDC_DDCMCTL1, DDCM_PGLEN_MASK,
+			       DDCM_PGLEN_OFFSET, read_count - 1);
+		ddcm_trigger_mode(ddc, (ack_final == 1) ?
+				  DDCM_READ_DATA_NO_ACK :
+				  DDCM_READ_DATA_ACK);
+
+		ack = sif_read_mask(ddc, DDC_DDCMCTL1, DDCM_ACK_MASK,
+				    DDCM_ACK_OFFSET);
+		temp_count = 0;
+		while (((ack & (1 << temp_count)) != 0) && (temp_count < 8))
+			temp_count++;
+		if (((ack_final == 1) && (temp_count != (read_count - 1))) ||
+		    ((ack_final == 0) && (temp_count != read_count))) {
+			dev_err(dev, "Address NACK! ACK(0x%x)\n", ack);
+			break;
+		}
+
+		for (i = read_count; i >= 1; i--) {
+			int shift;
+			int offset;
+
+			if (i > 4) {
+				offset = DDC_DDCMD1;
+				shift = (i - 5) * 8;
+			} else {
+				offset = DDC_DDCMD0;
+				shift = (i - 1) * 8;
+			}
+
+			msg->buf[index + i - 1] = sif_read_mask(ddc, offset,
+								0xff << shift,
+								shift);
+		}
+
+		remain_count -= read_count;
+		index += read_count;
+	}
+
+	return 0;
+}
+
+static int mtk_hdmi_ddc_write_msg(struct mtk_hdmi_ddc *ddc, struct i2c_msg *msg)
+{
+	struct device *dev = ddc->adap.dev.parent;
+	u32 ack;
+
+	ddcm_trigger_mode(ddc, DDCM_START);
+	sif_write_mask(ddc, DDC_DDCMD0, DDCM_DATA0, 0, msg->addr << 1);
+	sif_write_mask(ddc, DDC_DDCMD0, DDCM_DATA1, 8, msg->buf[0]);
+	sif_write_mask(ddc, DDC_DDCMCTL1, DDCM_PGLEN_MASK, DDCM_PGLEN_OFFSET,
+		       0x1);
+	ddcm_trigger_mode(ddc, DDCM_WRITE_DATA);
+
+	ack = sif_read_mask(ddc, DDC_DDCMCTL1, DDCM_ACK_MASK, DDCM_ACK_OFFSET);
+	dev_dbg(dev, "ack = %d\n", ack);
+
+	if (ack != 0x03) {
+		dev_err(dev, "i2c ack err!\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int mtk_hdmi_ddc_xfer(struct i2c_adapter *adapter,
+			     struct i2c_msg *msgs, int num)
+{
+	struct mtk_hdmi_ddc *ddc = adapter->algo_data;
+	struct device *dev = adapter->dev.parent;
+	int ret;
+	int i;
+
+	if (!ddc) {
+		dev_err(dev, "invalid arguments\n");
+		return -EINVAL;
+	}
+
+	sif_set_bit(ddc, DDC_DDCMCTL0, DDCM_SCL_STRECH);
+	sif_set_bit(ddc, DDC_DDCMCTL0, DDCM_SM0EN);
+	sif_clr_bit(ddc, DDC_DDCMCTL0, DDCM_ODRAIN);
+
+	if (sif_bit_is_set(ddc, DDC_DDCMCTL1, DDCM_TRI)) {
+		dev_err(dev, "ddc line is busy!\n");
+		return -EBUSY;
+	}
+
+	sif_write_mask(ddc, DDC_DDCMCTL0, DDCM_CLK_DIV_MASK,
+		       DDCM_CLK_DIV_OFFSET, SIF1_CLOK);
+
+	for (i = 0; i < num; i++) {
+		struct i2c_msg *msg = &msgs[i];
+
+		dev_dbg(dev, "i2c msg, adr:0x%x, flags:%d, len :0x%x\n",
+			msg->addr, msg->flags, msg->len);
+
+		if (msg->flags & I2C_M_RD)
+			ret = mtk_hdmi_ddc_read_msg(ddc, msg);
+		else
+			ret = mtk_hdmi_ddc_write_msg(ddc, msg);
+		if (ret < 0)
+			goto xfer_end;
+	}
+
+	ddcm_trigger_mode(ddc, DDCM_STOP);
+
+	return i;
+
+xfer_end:
+	ddcm_trigger_mode(ddc, DDCM_STOP);
+	dev_err(dev, "ddc failed!\n");
+	return ret;
+}
+
+static u32 mtk_hdmi_ddc_func(struct i2c_adapter *adapter)
+{
+	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+}
+
+static const struct i2c_algorithm mtk_hdmi_ddc_algorithm = {
+	.master_xfer = mtk_hdmi_ddc_xfer,
+	.functionality = mtk_hdmi_ddc_func,
+};
+
+static int mtk_hdmi_ddc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mtk_hdmi_ddc *ddc;
+	struct resource *mem;
+	int ret;
+
+	ddc = devm_kzalloc(dev, sizeof(struct mtk_hdmi_ddc), GFP_KERNEL);
+	if (!ddc)
+		return -ENOMEM;
+
+	ddc->clk = devm_clk_get(dev, "ddc-i2c");
+	if (IS_ERR(ddc->clk)) {
+		dev_err(dev, "get ddc_clk failed: %p ,\n", ddc->clk);
+		return PTR_ERR(ddc->clk);
+	}
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ddc->regs = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(ddc->regs))
+		return PTR_ERR(ddc->regs);
+
+	ret = clk_prepare_enable(ddc->clk);
+	if (ret) {
+		dev_err(dev, "enable ddc clk failed!\n");
+		return ret;
+	}
+
+	strlcpy(ddc->adap.name, "mediatek-hdmi-ddc", sizeof(ddc->adap.name));
+	ddc->adap.owner = THIS_MODULE;
+	ddc->adap.class = I2C_CLASS_DDC;
+	ddc->adap.algo = &mtk_hdmi_ddc_algorithm;
+	ddc->adap.retries = 3;
+	ddc->adap.dev.of_node = dev->of_node;
+	ddc->adap.algo_data = ddc;
+	ddc->adap.dev.parent = &pdev->dev;
+
+	ret = i2c_add_adapter(&ddc->adap);
+	if (ret < 0) {
+		dev_err(dev, "failed to add bus to i2c core\n");
+		goto err_clk_disable;
+	}
+
+	platform_set_drvdata(pdev, ddc);
+
+	dev_dbg(dev, "ddc->adap: %p\n", &ddc->adap);
+	dev_dbg(dev, "ddc->clk: %p\n", ddc->clk);
+	dev_dbg(dev, "physical adr: %pa, end: %pa\n", &mem->start,
+		&mem->end);
+
+	return 0;
+
+err_clk_disable:
+	clk_disable_unprepare(ddc->clk);
+	return ret;
+}
+
+static int mtk_hdmi_ddc_remove(struct platform_device *pdev)
+{
+	struct mtk_hdmi_ddc *ddc = platform_get_drvdata(pdev);
+
+	i2c_del_adapter(&ddc->adap);
+	clk_disable_unprepare(ddc->clk);
+
+	return 0;
+}
+
+static const struct of_device_id mtk_hdmi_ddc_match[] = {
+	{ .compatible = "mediatek,mt8173-hdmi-ddc", },
+	{},
+};
+
+struct platform_driver mtk_hdmi_ddc_driver = {
+	.probe = mtk_hdmi_ddc_probe,
+	.remove = mtk_hdmi_ddc_remove,
+	.driver = {
+		.name = "mediatek-hdmi-ddc",
+		.of_match_table = mtk_hdmi_ddc_match,
+	},
+};
+
+MODULE_AUTHOR("Jie Qiu <jie.qiu@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek HDMI DDC Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_regs.h b/drivers/gpu/drm/mediatek/mtk_hdmi_regs.h
new file mode 100644
index 000000000000..a5cb07d12c9c
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi_regs.h
@@ -0,0 +1,238 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Jie Qiu <jie.qiu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef _MTK_HDMI_REGS_H
+#define _MTK_HDMI_REGS_H
+
+#define GRL_INT_MASK		0x18
+#define GRL_IFM_PORT		0x188
+#define GRL_CH_SWAP		0x198
+#define LR_SWAP				BIT(0)
+#define LFE_CC_SWAP			BIT(1)
+#define LSRS_SWAP			BIT(2)
+#define RLS_RRS_SWAP			BIT(3)
+#define LR_STATUS_SWAP			BIT(4)
+#define GRL_I2S_C_STA0		0x140
+#define GRL_I2S_C_STA1		0x144
+#define GRL_I2S_C_STA2		0x148
+#define GRL_I2S_C_STA3		0x14C
+#define GRL_I2S_C_STA4		0x150
+#define GRL_I2S_UV		0x154
+#define I2S_UV_V			BIT(0)
+#define I2S_UV_U			BIT(1)
+#define I2S_UV_CH_EN_MASK		0x3c
+#define I2S_UV_CH_EN(x)			BIT((x) + 2)
+#define I2S_UV_TMDS_DEBUG		BIT(6)
+#define I2S_UV_NORMAL_INFO_INV		BIT(7)
+#define GRL_ACP_ISRC_CTRL	0x158
+#define VS_EN				BIT(0)
+#define ACP_EN				BIT(1)
+#define ISRC1_EN			BIT(2)
+#define ISRC2_EN			BIT(3)
+#define GAMUT_EN			BIT(4)
+#define GRL_CTS_CTRL		0x160
+#define CTS_CTRL_SOFT			BIT(0)
+#define GRL_INT			0x14
+#define INT_MDI				BIT(0)
+#define INT_HDCP			BIT(1)
+#define INT_FIFO_O			BIT(2)
+#define INT_FIFO_U			BIT(3)
+#define INT_IFM_ERR			BIT(4)
+#define INT_INF_DONE			BIT(5)
+#define INT_NCTS_DONE			BIT(6)
+#define INT_CTRL_PKT_DONE		BIT(7)
+#define GRL_INT_MASK		0x18
+#define GRL_CTRL		0x1C
+#define CTRL_GEN_EN			BIT(2)
+#define CTRL_SPD_EN			BIT(3)
+#define CTRL_MPEG_EN			BIT(4)
+#define CTRL_AUDIO_EN			BIT(5)
+#define CTRL_AVI_EN			BIT(6)
+#define CTRL_AVMUTE			BIT(7)
+#define	GRL_STATUS		0x20
+#define STATUS_HTPLG			BIT(0)
+#define STATUS_PORD			BIT(1)
+#define GRL_DIVN		0x170
+#define NCTS_WRI_ANYTIME		BIT(6)
+#define GRL_AUDIO_CFG		0x17C
+#define AUDIO_ZERO			BIT(0)
+#define HIGH_BIT_RATE			BIT(1)
+#define SACD_DST			BIT(2)
+#define DST_NORMAL_DOUBLE		BIT(3)
+#define DSD_INV				BIT(4)
+#define LR_INV				BIT(5)
+#define LR_MIX				BIT(6)
+#define DSD_SEL				BIT(7)
+#define GRL_NCTS		0x184
+#define GRL_CH_SW0		0x18C
+#define GRL_CH_SW1		0x190
+#define GRL_CH_SW2		0x194
+#define CH_SWITCH(from, to)		((from) << ((to) * 3))
+#define GRL_INFOFRM_VER		0x19C
+#define GRL_INFOFRM_TYPE	0x1A0
+#define GRL_INFOFRM_LNG		0x1A4
+#define GRL_MIX_CTRL		0x1B4
+#define MIX_CTRL_SRC_EN			BIT(0)
+#define BYPASS_VOLUME			BIT(1)
+#define MIX_CTRL_FLAT			BIT(7)
+#define GRL_AOUT_CFG		0x1C4
+#define AOUT_BNUM_SEL_MASK		0x03
+#define AOUT_24BIT			0x00
+#define AOUT_20BIT			0x02
+#define AOUT_16BIT			0x03
+#define AOUT_FIFO_ADAP_CTRL		BIT(6)
+#define AOUT_BURST_PREAMBLE_EN		BIT(7)
+#define HIGH_BIT_RATE_PACKET_ALIGN	(AOUT_BURST_PREAMBLE_EN | \
+					 AOUT_FIFO_ADAP_CTRL)
+#define GRL_SHIFT_L1		0x1C0
+#define GRL_SHIFT_R2		0x1B0
+#define AUDIO_PACKET_OFF		BIT(6)
+#define GRL_CFG0		0x24
+#define CFG0_I2S_MODE_MASK		0x3
+#define CFG0_I2S_MODE_RTJ		0x1
+#define CFG0_I2S_MODE_LTJ		0x0
+#define CFG0_I2S_MODE_I2S		0x2
+#define CFG0_W_LENGTH_MASK		0x30
+#define CFG0_W_LENGTH_24BIT		0x00
+#define CFG0_W_LENGTH_16BIT		0x10
+#define GRL_CFG1		0x28
+#define CFG1_EDG_SEL			BIT(0)
+#define CFG1_SPDIF			BIT(1)
+#define CFG1_DVI			BIT(2)
+#define CFG1_HDCP_DEBUG			BIT(3)
+#define GRL_CFG2		0x2c
+#define CFG2_MHL_DE_SEL			BIT(3)
+#define CFG2_MHL_FAKE_DE_SEL		BIT(4)
+#define CFG2_MHL_DATA_REMAP		BIT(5)
+#define CFG2_NOTICE_EN			BIT(6)
+#define CFG2_ACLK_INV			BIT(7)
+#define GRL_CFG3		0x30
+#define CFG3_AES_KEY_INDEX_MASK		0x3f
+#define CFG3_CONTROL_PACKET_DELAY	BIT(6)
+#define CFG3_KSV_LOAD_START		BIT(7)
+#define GRL_CFG4		0x34
+#define CFG4_AES_KEY_LOAD		BIT(4)
+#define CFG4_AV_UNMUTE_EN		BIT(5)
+#define CFG4_AV_UNMUTE_SET		BIT(6)
+#define CFG4_MHL_MODE			BIT(7)
+#define GRL_CFG5		0x38
+#define CFG5_CD_RATIO_MASK	0x8F
+#define CFG5_FS128			(0x1 << 4)
+#define CFG5_FS256			(0x2 << 4)
+#define CFG5_FS384			(0x3 << 4)
+#define CFG5_FS512			(0x4 << 4)
+#define CFG5_FS768			(0x6 << 4)
+#define DUMMY_304		0x304
+#define CHMO_SEL			(0x3 << 2)
+#define CHM1_SEL			(0x3 << 4)
+#define CHM2_SEL			(0x3 << 6)
+#define AUDIO_I2S_NCTS_SEL		BIT(1)
+#define AUDIO_I2S_NCTS_SEL_64		(1 << 1)
+#define AUDIO_I2S_NCTS_SEL_128		(0 << 1)
+#define NEW_GCP_CTRL			BIT(0)
+#define NEW_GCP_CTRL_MERGE		BIT(0)
+#define GRL_L_STATUS_0		0x200
+#define GRL_L_STATUS_1		0x204
+#define GRL_L_STATUS_2		0x208
+#define GRL_L_STATUS_3		0x20c
+#define GRL_L_STATUS_4		0x210
+#define GRL_L_STATUS_5		0x214
+#define GRL_L_STATUS_6		0x218
+#define GRL_L_STATUS_7		0x21c
+#define GRL_L_STATUS_8		0x220
+#define GRL_L_STATUS_9		0x224
+#define GRL_L_STATUS_10		0x228
+#define GRL_L_STATUS_11		0x22c
+#define GRL_L_STATUS_12		0x230
+#define GRL_L_STATUS_13		0x234
+#define GRL_L_STATUS_14		0x238
+#define GRL_L_STATUS_15		0x23c
+#define GRL_L_STATUS_16		0x240
+#define GRL_L_STATUS_17		0x244
+#define GRL_L_STATUS_18		0x248
+#define GRL_L_STATUS_19		0x24c
+#define GRL_L_STATUS_20		0x250
+#define GRL_L_STATUS_21		0x254
+#define GRL_L_STATUS_22		0x258
+#define GRL_L_STATUS_23		0x25c
+#define GRL_R_STATUS_0		0x260
+#define GRL_R_STATUS_1		0x264
+#define GRL_R_STATUS_2		0x268
+#define GRL_R_STATUS_3		0x26c
+#define GRL_R_STATUS_4		0x270
+#define GRL_R_STATUS_5		0x274
+#define GRL_R_STATUS_6		0x278
+#define GRL_R_STATUS_7		0x27c
+#define GRL_R_STATUS_8		0x280
+#define GRL_R_STATUS_9		0x284
+#define GRL_R_STATUS_10		0x288
+#define GRL_R_STATUS_11		0x28c
+#define GRL_R_STATUS_12		0x290
+#define GRL_R_STATUS_13		0x294
+#define GRL_R_STATUS_14		0x298
+#define GRL_R_STATUS_15		0x29c
+#define GRL_R_STATUS_16		0x2a0
+#define GRL_R_STATUS_17		0x2a4
+#define GRL_R_STATUS_18		0x2a8
+#define GRL_R_STATUS_19		0x2ac
+#define GRL_R_STATUS_20		0x2b0
+#define GRL_R_STATUS_21		0x2b4
+#define GRL_R_STATUS_22		0x2b8
+#define GRL_R_STATUS_23		0x2bc
+#define GRL_ABIST_CTRL0		0x2D4
+#define GRL_ABIST_CTRL1		0x2D8
+#define ABIST_EN			BIT(7)
+#define ABIST_DATA_FMT			(0x7 << 0)
+#define VIDEO_CFG_0		0x380
+#define VIDEO_CFG_1		0x384
+#define VIDEO_CFG_2		0x388
+#define VIDEO_CFG_3		0x38c
+#define VIDEO_CFG_4		0x390
+#define VIDEO_SOURCE_SEL		BIT(7)
+#define NORMAL_PATH			(1 << 7)
+#define GEN_RGB				(0 << 7)
+
+#define HDMI_SYS_CFG1C		0x000
+#define HDMI_ON				BIT(0)
+#define HDMI_RST			BIT(1)
+#define ANLG_ON				BIT(2)
+#define CFG10_DVI			BIT(3)
+#define HDMI_TST			BIT(3)
+#define SYS_KEYMASK1			(0xff << 8)
+#define SYS_KEYMASK2			(0xff << 16)
+#define AUD_OUTSYNC_EN			BIT(24)
+#define AUD_OUTSYNC_PRE_EN		BIT(25)
+#define I2CM_ON				BIT(26)
+#define E2PROM_TYPE_8BIT		BIT(27)
+#define MCM_E2PROM_ON			BIT(28)
+#define EXT_E2PROM_ON			BIT(29)
+#define HTPLG_PIN_SEL_OFF		BIT(30)
+#define AES_EFUSE_ENABLE		BIT(31)
+#define HDMI_SYS_CFG20		0x004
+#define DEEP_COLOR_MODE_MASK		(3 << 1)
+#define COLOR_8BIT_MODE			(0 << 1)
+#define COLOR_10BIT_MODE		(1 << 1)
+#define COLOR_12BIT_MODE		(2 << 1)
+#define COLOR_16BIT_MODE		(3 << 1)
+#define DEEP_COLOR_EN			BIT(0)
+#define HDMI_AUDIO_TEST_SEL		BIT(8)
+#define HDMI2P0_EN			BIT(11)
+#define HDMI_OUT_FIFO_EN		BIT(16)
+#define HDMI_OUT_FIFO_CLK_INV		BIT(17)
+#define MHL_MODE_ON			BIT(28)
+#define MHL_PP_MODE			BIT(29)
+#define MHL_SYNC_AUTO_EN		BIT(30)
+#define HDMI_PCLK_FREE_RUN		BIT(31)
+
+#define MTK_SIP_SET_AUTHORIZED_SECURE_REG 0x82000001
+#endif
diff --git a/drivers/gpu/drm/mediatek/mtk_mipi_tx.c b/drivers/gpu/drm/mediatek/mtk_mipi_tx.c
index cf8f38d39e10..1c366f8cb2d0 100644
--- a/drivers/gpu/drm/mediatek/mtk_mipi_tx.c
+++ b/drivers/gpu/drm/mediatek/mtk_mipi_tx.c
@@ -431,7 +431,7 @@ static int mtk_mipi_tx_probe(struct platform_device *pdev)
 	phy_set_drvdata(phy, mipi_tx);
 
 	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
-	if (IS_ERR(phy)) {
+	if (IS_ERR(phy_provider)) {
 		ret = PTR_ERR(phy_provider);
 		return ret;
 	}
diff --git a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
new file mode 100644
index 000000000000..8a24754b440f
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
@@ -0,0 +1,515 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Jie Qiu <jie.qiu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+
+#define HDMI_CON0		0x00
+#define RG_HDMITX_PLL_EN		BIT(31)
+#define RG_HDMITX_PLL_FBKDIV		(0x7f << 24)
+#define PLL_FBKDIV_SHIFT		24
+#define RG_HDMITX_PLL_FBKSEL		(0x3 << 22)
+#define PLL_FBKSEL_SHIFT		22
+#define RG_HDMITX_PLL_PREDIV		(0x3 << 20)
+#define PREDIV_SHIFT			20
+#define RG_HDMITX_PLL_POSDIV		(0x3 << 18)
+#define POSDIV_SHIFT			18
+#define RG_HDMITX_PLL_RST_DLY		(0x3 << 16)
+#define RG_HDMITX_PLL_IR		(0xf << 12)
+#define PLL_IR_SHIFT			12
+#define RG_HDMITX_PLL_IC		(0xf << 8)
+#define PLL_IC_SHIFT			8
+#define RG_HDMITX_PLL_BP		(0xf << 4)
+#define PLL_BP_SHIFT			4
+#define RG_HDMITX_PLL_BR		(0x3 << 2)
+#define PLL_BR_SHIFT			2
+#define RG_HDMITX_PLL_BC		(0x3 << 0)
+#define PLL_BC_SHIFT			0
+#define HDMI_CON1		0x04
+#define RG_HDMITX_PLL_DIVEN		(0x7 << 29)
+#define PLL_DIVEN_SHIFT			29
+#define RG_HDMITX_PLL_AUTOK_EN		BIT(28)
+#define RG_HDMITX_PLL_AUTOK_KF		(0x3 << 26)
+#define RG_HDMITX_PLL_AUTOK_KS		(0x3 << 24)
+#define RG_HDMITX_PLL_AUTOK_LOAD	BIT(23)
+#define RG_HDMITX_PLL_BAND		(0x3f << 16)
+#define RG_HDMITX_PLL_REF_SEL		BIT(15)
+#define RG_HDMITX_PLL_BIAS_EN		BIT(14)
+#define RG_HDMITX_PLL_BIAS_LPF_EN	BIT(13)
+#define RG_HDMITX_PLL_TXDIV_EN		BIT(12)
+#define RG_HDMITX_PLL_TXDIV		(0x3 << 10)
+#define PLL_TXDIV_SHIFT			10
+#define RG_HDMITX_PLL_LVROD_EN		BIT(9)
+#define RG_HDMITX_PLL_MONVC_EN		BIT(8)
+#define RG_HDMITX_PLL_MONCK_EN		BIT(7)
+#define RG_HDMITX_PLL_MONREF_EN		BIT(6)
+#define RG_HDMITX_PLL_TST_EN		BIT(5)
+#define RG_HDMITX_PLL_TST_CK_EN		BIT(4)
+#define RG_HDMITX_PLL_TST_SEL		(0xf << 0)
+#define HDMI_CON2		0x08
+#define RGS_HDMITX_PLL_AUTOK_BAND	(0x7f << 8)
+#define RGS_HDMITX_PLL_AUTOK_FAIL	BIT(1)
+#define RG_HDMITX_EN_TX_CKLDO		BIT(0)
+#define HDMI_CON3		0x0c
+#define RG_HDMITX_SER_EN		(0xf << 28)
+#define RG_HDMITX_PRD_EN		(0xf << 24)
+#define RG_HDMITX_PRD_IMP_EN		(0xf << 20)
+#define RG_HDMITX_DRV_EN		(0xf << 16)
+#define RG_HDMITX_DRV_IMP_EN		(0xf << 12)
+#define DRV_IMP_EN_SHIFT		12
+#define RG_HDMITX_MHLCK_FORCE		BIT(10)
+#define RG_HDMITX_MHLCK_PPIX_EN		BIT(9)
+#define RG_HDMITX_MHLCK_EN		BIT(8)
+#define RG_HDMITX_SER_DIN_SEL		(0xf << 4)
+#define RG_HDMITX_SER_5T1_BIST_EN	BIT(3)
+#define RG_HDMITX_SER_BIST_TOG		BIT(2)
+#define RG_HDMITX_SER_DIN_TOG		BIT(1)
+#define RG_HDMITX_SER_CLKDIG_INV	BIT(0)
+#define HDMI_CON4		0x10
+#define RG_HDMITX_PRD_IBIAS_CLK		(0xf << 24)
+#define RG_HDMITX_PRD_IBIAS_D2		(0xf << 16)
+#define RG_HDMITX_PRD_IBIAS_D1		(0xf << 8)
+#define RG_HDMITX_PRD_IBIAS_D0		(0xf << 0)
+#define PRD_IBIAS_CLK_SHIFT		24
+#define PRD_IBIAS_D2_SHIFT		16
+#define PRD_IBIAS_D1_SHIFT		8
+#define PRD_IBIAS_D0_SHIFT		0
+#define HDMI_CON5		0x14
+#define RG_HDMITX_DRV_IBIAS_CLK		(0x3f << 24)
+#define RG_HDMITX_DRV_IBIAS_D2		(0x3f << 16)
+#define RG_HDMITX_DRV_IBIAS_D1		(0x3f << 8)
+#define RG_HDMITX_DRV_IBIAS_D0		(0x3f << 0)
+#define DRV_IBIAS_CLK_SHIFT		24
+#define DRV_IBIAS_D2_SHIFT		16
+#define DRV_IBIAS_D1_SHIFT		8
+#define DRV_IBIAS_D0_SHIFT		0
+#define HDMI_CON6		0x18
+#define RG_HDMITX_DRV_IMP_CLK		(0x3f << 24)
+#define RG_HDMITX_DRV_IMP_D2		(0x3f << 16)
+#define RG_HDMITX_DRV_IMP_D1		(0x3f << 8)
+#define RG_HDMITX_DRV_IMP_D0		(0x3f << 0)
+#define DRV_IMP_CLK_SHIFT		24
+#define DRV_IMP_D2_SHIFT		16
+#define DRV_IMP_D1_SHIFT		8
+#define DRV_IMP_D0_SHIFT		0
+#define HDMI_CON7		0x1c
+#define RG_HDMITX_MHLCK_DRV_IBIAS	(0x1f << 27)
+#define RG_HDMITX_SER_DIN		(0x3ff << 16)
+#define RG_HDMITX_CHLDC_TST		(0xf << 12)
+#define RG_HDMITX_CHLCK_TST		(0xf << 8)
+#define RG_HDMITX_RESERVE		(0xff << 0)
+#define HDMI_CON8		0x20
+#define RGS_HDMITX_2T1_LEV		(0xf << 16)
+#define RGS_HDMITX_2T1_EDG		(0xf << 12)
+#define RGS_HDMITX_5T1_LEV		(0xf << 8)
+#define RGS_HDMITX_5T1_EDG		(0xf << 4)
+#define RGS_HDMITX_PLUG_TST		BIT(0)
+
+struct mtk_hdmi_phy {
+	void __iomem *regs;
+	struct device *dev;
+	struct clk *pll;
+	struct clk_hw pll_hw;
+	unsigned long pll_rate;
+	u8 drv_imp_clk;
+	u8 drv_imp_d2;
+	u8 drv_imp_d1;
+	u8 drv_imp_d0;
+	u32 ibias;
+	u32 ibias_up;
+};
+
+static const u8 PREDIV[3][4] = {
+	{0x0, 0x0, 0x0, 0x0},	/* 27Mhz */
+	{0x1, 0x1, 0x1, 0x1},	/* 74Mhz */
+	{0x1, 0x1, 0x1, 0x1}	/* 148Mhz */
+};
+
+static const u8 TXDIV[3][4] = {
+	{0x3, 0x3, 0x3, 0x2},	/* 27Mhz */
+	{0x2, 0x1, 0x1, 0x1},	/* 74Mhz */
+	{0x1, 0x0, 0x0, 0x0}	/* 148Mhz */
+};
+
+static const u8 FBKSEL[3][4] = {
+	{0x1, 0x1, 0x1, 0x1},	/* 27Mhz */
+	{0x1, 0x0, 0x1, 0x1},	/* 74Mhz */
+	{0x1, 0x0, 0x1, 0x1}	/* 148Mhz */
+};
+
+static const u8 FBKDIV[3][4] = {
+	{19, 24, 29, 19},	/* 27Mhz */
+	{19, 24, 14, 19},	/* 74Mhz */
+	{19, 24, 14, 19}	/* 148Mhz */
+};
+
+static const u8 DIVEN[3][4] = {
+	{0x2, 0x1, 0x1, 0x2},	/* 27Mhz */
+	{0x2, 0x2, 0x2, 0x2},	/* 74Mhz */
+	{0x2, 0x2, 0x2, 0x2}	/* 148Mhz */
+};
+
+static const u8 HTPLLBP[3][4] = {
+	{0xc, 0xc, 0x8, 0xc},	/* 27Mhz */
+	{0xc, 0xf, 0xf, 0xc},	/* 74Mhz */
+	{0xc, 0xf, 0xf, 0xc}	/* 148Mhz */
+};
+
+static const u8 HTPLLBC[3][4] = {
+	{0x2, 0x3, 0x3, 0x2},	/* 27Mhz */
+	{0x2, 0x3, 0x3, 0x2},	/* 74Mhz */
+	{0x2, 0x3, 0x3, 0x2}	/* 148Mhz */
+};
+
+static const u8 HTPLLBR[3][4] = {
+	{0x1, 0x1, 0x0, 0x1},	/* 27Mhz */
+	{0x1, 0x2, 0x2, 0x1},	/* 74Mhz */
+	{0x1, 0x2, 0x2, 0x1}	/* 148Mhz */
+};
+
+static void mtk_hdmi_phy_clear_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
+				    u32 bits)
+{
+	void __iomem *reg = hdmi_phy->regs + offset;
+	u32 tmp;
+
+	tmp = readl(reg);
+	tmp &= ~bits;
+	writel(tmp, reg);
+}
+
+static void mtk_hdmi_phy_set_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
+				  u32 bits)
+{
+	void __iomem *reg = hdmi_phy->regs + offset;
+	u32 tmp;
+
+	tmp = readl(reg);
+	tmp |= bits;
+	writel(tmp, reg);
+}
+
+static void mtk_hdmi_phy_mask(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
+			      u32 val, u32 mask)
+{
+	void __iomem *reg = hdmi_phy->regs + offset;
+	u32 tmp;
+
+	tmp = readl(reg);
+	tmp = (tmp & ~mask) | (val & mask);
+	writel(tmp, reg);
+}
+
+static inline struct mtk_hdmi_phy *to_mtk_hdmi_phy(struct clk_hw *hw)
+{
+	return container_of(hw, struct mtk_hdmi_phy, pll_hw);
+}
+
+static int mtk_hdmi_pll_prepare(struct clk_hw *hw)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+
+	dev_dbg(hdmi_phy->dev, "%s\n", __func__);
+
+	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_AUTOK_EN);
+	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_POSDIV);
+	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3, RG_HDMITX_MHLCK_EN);
+	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_BIAS_EN);
+	usleep_range(100, 150);
+	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_EN);
+	usleep_range(100, 150);
+	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_BIAS_LPF_EN);
+	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_TXDIV_EN);
+
+	return 0;
+}
+
+static void mtk_hdmi_pll_unprepare(struct clk_hw *hw)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+
+	dev_dbg(hdmi_phy->dev, "%s\n", __func__);
+
+	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_TXDIV_EN);
+	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_BIAS_LPF_EN);
+	usleep_range(100, 150);
+	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_EN);
+	usleep_range(100, 150);
+	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_BIAS_EN);
+	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_POSDIV);
+	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON1, RG_HDMITX_PLL_AUTOK_EN);
+	usleep_range(100, 150);
+}
+
+static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+				 unsigned long parent_rate)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+	unsigned int pre_div;
+	unsigned int div;
+
+	dev_dbg(hdmi_phy->dev, "%s: %lu Hz, parent: %lu Hz\n", __func__,
+		rate, parent_rate);
+
+	if (rate <= 27000000) {
+		pre_div = 0;
+		div = 3;
+	} else if (rate <= 74250000) {
+		pre_div = 1;
+		div = 2;
+	} else {
+		pre_div = 1;
+		div = 1;
+	}
+
+	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON0,
+			  (pre_div << PREDIV_SHIFT), RG_HDMITX_PLL_PREDIV);
+	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_PLL_POSDIV);
+	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON0,
+			  (0x1 << PLL_IC_SHIFT) | (0x1 << PLL_IR_SHIFT),
+			  RG_HDMITX_PLL_IC | RG_HDMITX_PLL_IR);
+	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON1,
+			  (div << PLL_TXDIV_SHIFT), RG_HDMITX_PLL_TXDIV);
+	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON0,
+			  (0x1 << PLL_FBKSEL_SHIFT) | (19 << PLL_FBKDIV_SHIFT),
+			  RG_HDMITX_PLL_FBKSEL | RG_HDMITX_PLL_FBKDIV);
+	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON1,
+			  (0x2 << PLL_DIVEN_SHIFT), RG_HDMITX_PLL_DIVEN);
+	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON0,
+			  (0xc << PLL_BP_SHIFT) | (0x2 << PLL_BC_SHIFT) |
+			  (0x1 << PLL_BR_SHIFT),
+			  RG_HDMITX_PLL_BP | RG_HDMITX_PLL_BC |
+			  RG_HDMITX_PLL_BR);
+	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3, RG_HDMITX_PRD_IMP_EN);
+	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON4,
+			  (0x3 << PRD_IBIAS_CLK_SHIFT) |
+			  (0x3 << PRD_IBIAS_D2_SHIFT) |
+			  (0x3 << PRD_IBIAS_D1_SHIFT) |
+			  (0x3 << PRD_IBIAS_D0_SHIFT),
+			  RG_HDMITX_PRD_IBIAS_CLK |
+			  RG_HDMITX_PRD_IBIAS_D2 |
+			  RG_HDMITX_PRD_IBIAS_D1 |
+			  RG_HDMITX_PRD_IBIAS_D0);
+	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON3,
+			  (0x0 << DRV_IMP_EN_SHIFT), RG_HDMITX_DRV_IMP_EN);
+	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6,
+			  (hdmi_phy->drv_imp_clk << DRV_IMP_CLK_SHIFT) |
+			  (hdmi_phy->drv_imp_d2 << DRV_IMP_D2_SHIFT) |
+			  (hdmi_phy->drv_imp_d1 << DRV_IMP_D1_SHIFT) |
+			  (hdmi_phy->drv_imp_d0 << DRV_IMP_D0_SHIFT),
+			  RG_HDMITX_DRV_IMP_CLK | RG_HDMITX_DRV_IMP_D2 |
+			  RG_HDMITX_DRV_IMP_D1 | RG_HDMITX_DRV_IMP_D0);
+	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON5,
+			  (hdmi_phy->ibias << DRV_IBIAS_CLK_SHIFT) |
+			  (hdmi_phy->ibias << DRV_IBIAS_D2_SHIFT) |
+			  (hdmi_phy->ibias << DRV_IBIAS_D1_SHIFT) |
+			  (hdmi_phy->ibias << DRV_IBIAS_D0_SHIFT),
+			  RG_HDMITX_DRV_IBIAS_CLK | RG_HDMITX_DRV_IBIAS_D2 |
+			  RG_HDMITX_DRV_IBIAS_D1 | RG_HDMITX_DRV_IBIAS_D0);
+	return 0;
+}
+
+static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long *parent_rate)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+
+	hdmi_phy->pll_rate = rate;
+	if (rate <= 74250000)
+		*parent_rate = rate;
+	else
+		*parent_rate = rate / 2;
+
+	return rate;
+}
+
+static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
+					      unsigned long parent_rate)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+
+	return hdmi_phy->pll_rate;
+}
+
+static const struct clk_ops mtk_hdmi_pll_ops = {
+	.prepare = mtk_hdmi_pll_prepare,
+	.unprepare = mtk_hdmi_pll_unprepare,
+	.set_rate = mtk_hdmi_pll_set_rate,
+	.round_rate = mtk_hdmi_pll_round_rate,
+	.recalc_rate = mtk_hdmi_pll_recalc_rate,
+};
+
+static void mtk_hdmi_phy_enable_tmds(struct mtk_hdmi_phy *hdmi_phy)
+{
+	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON3,
+			      RG_HDMITX_SER_EN | RG_HDMITX_PRD_EN |
+			      RG_HDMITX_DRV_EN);
+	usleep_range(100, 150);
+}
+
+static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy)
+{
+	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3,
+				RG_HDMITX_DRV_EN | RG_HDMITX_PRD_EN |
+				RG_HDMITX_SER_EN);
+}
+
+static int mtk_hdmi_phy_power_on(struct phy *phy)
+{
+	struct mtk_hdmi_phy *hdmi_phy = phy_get_drvdata(phy);
+	int ret;
+
+	ret = clk_prepare_enable(hdmi_phy->pll);
+	if (ret < 0)
+		return ret;
+
+	mtk_hdmi_phy_enable_tmds(hdmi_phy);
+
+	return 0;
+}
+
+static int mtk_hdmi_phy_power_off(struct phy *phy)
+{
+	struct mtk_hdmi_phy *hdmi_phy = phy_get_drvdata(phy);
+
+	mtk_hdmi_phy_disable_tmds(hdmi_phy);
+	clk_disable_unprepare(hdmi_phy->pll);
+
+	return 0;
+}
+
+static const struct phy_ops mtk_hdmi_phy_ops = {
+	.power_on = mtk_hdmi_phy_power_on,
+	.power_off = mtk_hdmi_phy_power_off,
+	.owner = THIS_MODULE,
+};
+
+static int mtk_hdmi_phy_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mtk_hdmi_phy *hdmi_phy;
+	struct resource *mem;
+	struct clk *ref_clk;
+	const char *ref_clk_name;
+	struct clk_init_data clk_init = {
+		.ops = &mtk_hdmi_pll_ops,
+		.num_parents = 1,
+		.parent_names = (const char * const *)&ref_clk_name,
+		.flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE,
+	};
+	struct phy *phy;
+	struct phy_provider *phy_provider;
+	int ret;
+
+	hdmi_phy = devm_kzalloc(dev, sizeof(*hdmi_phy), GFP_KERNEL);
+	if (!hdmi_phy)
+		return -ENOMEM;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	hdmi_phy->regs = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(hdmi_phy->regs)) {
+		ret = PTR_ERR(hdmi_phy->regs);
+		dev_err(dev, "Failed to get memory resource: %d\n", ret);
+		return ret;
+	}
+
+	ref_clk = devm_clk_get(dev, "pll_ref");
+	if (IS_ERR(ref_clk)) {
+		ret = PTR_ERR(ref_clk);
+		dev_err(&pdev->dev, "Failed to get PLL reference clock: %d\n",
+			ret);
+		return ret;
+	}
+	ref_clk_name = __clk_get_name(ref_clk);
+
+	ret = of_property_read_string(dev->of_node, "clock-output-names",
+				      &clk_init.name);
+	if (ret < 0) {
+		dev_err(dev, "Failed to read clock-output-names: %d\n", ret);
+		return ret;
+	}
+
+	hdmi_phy->pll_hw.init = &clk_init;
+	hdmi_phy->pll = devm_clk_register(dev, &hdmi_phy->pll_hw);
+	if (IS_ERR(hdmi_phy->pll)) {
+		ret = PTR_ERR(hdmi_phy->pll);
+		dev_err(dev, "Failed to register PLL: %d\n", ret);
+		return ret;
+	}
+
+	ret = of_property_read_u32(dev->of_node, "mediatek,ibias",
+				   &hdmi_phy->ibias);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to get ibias: %d\n", ret);
+		return ret;
+	}
+
+	ret = of_property_read_u32(dev->of_node, "mediatek,ibias_up",
+				   &hdmi_phy->ibias_up);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to get ibias up: %d\n", ret);
+		return ret;
+	}
+
+	dev_info(dev, "Using default TX DRV impedance: 4.2k/36\n");
+	hdmi_phy->drv_imp_clk = 0x30;
+	hdmi_phy->drv_imp_d2 = 0x30;
+	hdmi_phy->drv_imp_d1 = 0x30;
+	hdmi_phy->drv_imp_d0 = 0x30;
+
+	phy = devm_phy_create(dev, NULL, &mtk_hdmi_phy_ops);
+	if (IS_ERR(phy)) {
+		dev_err(dev, "Failed to create HDMI PHY\n");
+		return PTR_ERR(phy);
+	}
+	phy_set_drvdata(phy, hdmi_phy);
+
+	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+	if (IS_ERR(phy_provider))
+		return PTR_ERR(phy_provider);
+
+	hdmi_phy->dev = dev;
+	return of_clk_add_provider(dev->of_node, of_clk_src_simple_get,
+				   hdmi_phy->pll);
+}
+
+static int mtk_hdmi_phy_remove(struct platform_device *pdev)
+{
+	return 0;
+}
+
+static const struct of_device_id mtk_hdmi_phy_match[] = {
+	{ .compatible = "mediatek,mt8173-hdmi-phy", },
+	{},
+};
+
+struct platform_driver mtk_hdmi_phy_driver = {
+	.probe = mtk_hdmi_phy_probe,
+	.remove = mtk_hdmi_phy_remove,
+	.driver = {
+		.name = "mediatek-hdmi-phy",
+		.of_match_table = mtk_hdmi_phy_match,
+	},
+};
+
+MODULE_AUTHOR("Jie Qiu <jie.qiu@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek MT8173 HDMI PHY Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/mgag200/Kconfig b/drivers/gpu/drm/mgag200/Kconfig
index 3a1c5fbae54a..520e5e668d6c 100644
--- a/drivers/gpu/drm/mgag200/Kconfig
+++ b/drivers/gpu/drm/mgag200/Kconfig
@@ -1,11 +1,7 @@
 config DRM_MGAG200
 	tristate "Kernel modesetting driver for MGA G200 server engines"
 	depends on DRM && PCI
-	select FB_SYS_FILLRECT
-	select FB_SYS_COPYAREA
-	select FB_SYS_IMAGEBLIT
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_TTM
 	help
 	 This is a KMS driver for the MGA G200 server chips, it
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index ebb470ff7200..2b4b125eebc3 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -101,7 +101,7 @@ static struct drm_driver driver = {
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
 
-	.gem_free_object = mgag200_gem_free_object,
+	.gem_free_object_unlocked = mgag200_gem_free_object,
 	.dumb_create = mgag200_dumb_create,
 	.dumb_map_offset = mgag200_dumb_mmap_offset,
 	.dumb_destroy = drm_gem_dumb_destroy,
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index 615cbb08ba29..13798b3e6beb 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -17,8 +17,8 @@
 static void mga_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct mga_framebuffer *mga_fb = to_mga_framebuffer(fb);
-	if (mga_fb->obj)
-		drm_gem_object_unreference_unlocked(mga_fb->obj);
+
+	drm_gem_object_unreference_unlocked(mga_fb->obj);
 	drm_framebuffer_cleanup(fb);
 	kfree(fb);
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index d347dca17267..6b21cb27e1cc 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1352,19 +1352,20 @@ static void mga_crtc_commit(struct drm_crtc *crtc)
  * use this for 8-bit mode so can't perform smooth fades on deeper modes,
  * but it's a requirement that we provide the function
  */
-static void mga_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-				  u16 *blue, uint32_t start, uint32_t size)
+static int mga_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
+			      u16 *blue, uint32_t size)
 {
 	struct mga_crtc *mga_crtc = to_mga_crtc(crtc);
-	int end = (start + size > MGAG200_LUT_SIZE) ? MGAG200_LUT_SIZE : start + size;
 	int i;
 
-	for (i = start; i < end; i++) {
+	for (i = 0; i < size; i++) {
 		mga_crtc->lut_r[i] = red[i] >> 8;
 		mga_crtc->lut_g[i] = green[i] >> 8;
 		mga_crtc->lut_b[i] = blue[i] >> 8;
 	}
 	mga_crtc_load_lut(crtc);
+
+	return 0;
 }
 
 /* Simple cleanup function */
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 9d5083d0f1ee..68268e55d595 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -186,17 +186,6 @@ static void mgag200_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_r
 {
 }
 
-static int mgag200_bo_move(struct ttm_buffer_object *bo,
-		       bool evict, bool interruptible,
-		       bool no_wait_gpu,
-		       struct ttm_mem_reg *new_mem)
-{
-	int r;
-	r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
-	return r;
-}
-
-
 static void mgag200_ttm_backend_destroy(struct ttm_tt *tt)
 {
 	ttm_tt_fini(tt);
@@ -241,7 +230,7 @@ struct ttm_bo_driver mgag200_bo_driver = {
 	.ttm_tt_unpopulate = mgag200_ttm_tt_unpopulate,
 	.init_mem_type = mgag200_bo_init_mem_type,
 	.evict_flags = mgag200_bo_evict_flags,
-	.move = mgag200_bo_move,
+	.move = NULL,
 	.verify_access = mgag200_bo_verify_access,
 	.io_mem_reserve = &mgag200_ttm_io_mem_reserve,
 	.io_mem_free = &mgag200_ttm_io_mem_free,
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 167a4971f47c..7c7a0314a756 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -10,6 +10,7 @@ config DRM_MSM
 	select SHMEM
 	select TMPFS
 	select QCOM_SCM
+	select SND_SOC_HDMI_CODEC if SND_SOC
 	default y
 	help
 	  DRM/KMS driver for MSM/snapdragon.
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 60cb02624dc0..4e2806cf778c 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -35,6 +35,7 @@ msm-y := \
 	mdp/mdp5/mdp5_crtc.o \
 	mdp/mdp5/mdp5_encoder.o \
 	mdp/mdp5/mdp5_irq.o \
+	mdp/mdp5/mdp5_mdss.o \
 	mdp/mdp5/mdp5_kms.o \
 	mdp/mdp5/mdp5_plane.o \
 	mdp/mdp5/mdp5_smp.o \
@@ -45,6 +46,7 @@ msm-y := \
 	msm_fence.o \
 	msm_gem.o \
 	msm_gem_prime.o \
+	msm_gem_shrinker.o \
 	msm_gem_submit.o \
 	msm_gpu.o \
 	msm_iommu.o \
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 2aec27dbb5bb..f386f463278d 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -139,7 +139,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct msm_drm_private *priv = gpu->dev->dev_private;
 	struct msm_ringbuffer *ring = gpu->rb;
-	unsigned i, ibs = 0;
+	unsigned i;
 
 	for (i = 0; i < submit->nr_cmds; i++) {
 		switch (submit->cmd[i].type) {
@@ -155,18 +155,11 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 				CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2);
 			OUT_RING(ring, submit->cmd[i].iova);
 			OUT_RING(ring, submit->cmd[i].size);
-			ibs++;
+			OUT_PKT2(ring);
 			break;
 		}
 	}
 
-	/* on a320, at least, we seem to need to pad things out to an
-	 * even number of qwords to avoid issue w/ CP hanging on wrap-
-	 * around:
-	 */
-	if (ibs % 2)
-		OUT_PKT2(ring);
-
 	OUT_PKT0(ring, REG_AXXX_CP_SCRATCH_REG2, 1);
 	OUT_RING(ring, submit->fence->seqno);
 
@@ -407,7 +400,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		return ret;
 	}
 
-	adreno_gpu->memptrs = msm_gem_vaddr(adreno_gpu->memptrs_bo);
+	adreno_gpu->memptrs = msm_gem_get_vaddr(adreno_gpu->memptrs_bo);
 	if (IS_ERR(adreno_gpu->memptrs)) {
 		dev_err(drm->dev, "could not vmap memptrs\n");
 		return -ENOMEM;
@@ -426,8 +419,12 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 void adreno_gpu_cleanup(struct adreno_gpu *gpu)
 {
 	if (gpu->memptrs_bo) {
+		if (gpu->memptrs)
+			msm_gem_put_vaddr(gpu->memptrs_bo);
+
 		if (gpu->memptrs_iova)
 			msm_gem_put_iova(gpu->memptrs_bo, gpu->base.id);
+
 		drm_gem_object_unreference_unlocked(gpu->memptrs_bo);
 	}
 	release_firmware(gpu->pm4);
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index 6edcd6f57e70..ec572f8389ed 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -29,7 +29,7 @@ static int dsi_get_phy(struct msm_dsi *msm_dsi)
 	struct platform_device *phy_pdev;
 	struct device_node *phy_node;
 
-	phy_node = of_parse_phandle(pdev->dev.of_node, "qcom,dsi-phy", 0);
+	phy_node = of_parse_phandle(pdev->dev.of_node, "phys", 0);
 	if (!phy_node) {
 		dev_err(&pdev->dev, "cannot find phy device\n");
 		return -ENXIO;
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index 93c1ee094eac..63436d8ee470 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -29,6 +29,8 @@ static const struct msm_dsi_config apq8064_dsi_cfg = {
 	},
 	.bus_clk_names = dsi_v2_bus_clk_names,
 	.num_bus_clks = ARRAY_SIZE(dsi_v2_bus_clk_names),
+	.io_start = { 0x4700000, 0x5800000 },
+	.num_dsi = 2,
 };
 
 static const char * const dsi_6g_bus_clk_names[] = {
@@ -48,6 +50,8 @@ static const struct msm_dsi_config msm8974_apq8084_dsi_cfg = {
 	},
 	.bus_clk_names = dsi_6g_bus_clk_names,
 	.num_bus_clks = ARRAY_SIZE(dsi_6g_bus_clk_names),
+	.io_start = { 0xfd922800, 0xfd922b00 },
+	.num_dsi = 2,
 };
 
 static const char * const dsi_8916_bus_clk_names[] = {
@@ -66,6 +70,8 @@ static const struct msm_dsi_config msm8916_dsi_cfg = {
 	},
 	.bus_clk_names = dsi_8916_bus_clk_names,
 	.num_bus_clks = ARRAY_SIZE(dsi_8916_bus_clk_names),
+	.io_start = { 0x1a98000 },
+	.num_dsi = 1,
 };
 
 static const struct msm_dsi_config msm8994_dsi_cfg = {
@@ -84,6 +90,8 @@ static const struct msm_dsi_config msm8994_dsi_cfg = {
 	},
 	.bus_clk_names = dsi_6g_bus_clk_names,
 	.num_bus_clks = ARRAY_SIZE(dsi_6g_bus_clk_names),
+	.io_start = { 0xfd998000, 0xfd9a0000 },
+	.num_dsi = 2,
 };
 
 static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index a68c836744a3..eeacc3232494 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -34,6 +34,8 @@ struct msm_dsi_config {
 	struct dsi_reg_config reg_cfg;
 	const char * const *bus_clk_names;
 	const int num_bus_clks;
+	const resource_size_t io_start[DSI_MAX];
+	const int num_dsi;
 };
 
 struct msm_dsi_cfg_handler {
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index a3e47ad83eb3..f05ed0e1f3d6 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1066,7 +1066,7 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host,
 	}
 
 	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		data = msm_gem_vaddr(msm_host->tx_gem_obj);
+		data = msm_gem_get_vaddr(msm_host->tx_gem_obj);
 		if (IS_ERR(data)) {
 			ret = PTR_ERR(data);
 			pr_err("%s: get vaddr failed, %d\n", __func__, ret);
@@ -1094,6 +1094,9 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host,
 	if (packet.size < len)
 		memset(data + packet.size, 0xff, len - packet.size);
 
+	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G)
+		msm_gem_put_vaddr(msm_host->tx_gem_obj);
+
 	return len;
 }
 
@@ -1543,7 +1546,7 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host,
 	u32 lane_map[4];
 	int ret, i, len, num_lanes;
 
-	prop = of_find_property(ep, "qcom,data-lane-map", &len);
+	prop = of_find_property(ep, "data-lanes", &len);
 	if (!prop) {
 		dev_dbg(dev, "failed to find data lane mapping\n");
 		return -EINVAL;
@@ -1558,7 +1561,7 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host,
 
 	msm_host->num_data_lanes = num_lanes;
 
-	ret = of_property_read_u32_array(ep, "qcom,data-lane-map", lane_map,
+	ret = of_property_read_u32_array(ep, "data-lanes", lane_map,
 					 num_lanes);
 	if (ret) {
 		dev_err(dev, "failed to read lane data\n");
@@ -1573,8 +1576,19 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host,
 		const int *swap = supported_data_lane_swaps[i];
 		int j;
 
+		/*
+		 * the data-lanes array we get from DT has a logical->physical
+		 * mapping. The "data lane swap" register field represents
+		 * supported configurations in a physical->logical mapping.
+		 * Translate the DT mapping to what we understand and find a
+		 * configuration that works.
+		 */
 		for (j = 0; j < num_lanes; j++) {
-			if (swap[j] != lane_map[j])
+			if (lane_map[j] < 0 || lane_map[j] > 3)
+				dev_err(dev, "bad physical lane entry %u\n",
+					lane_map[j]);
+
+			if (swap[lane_map[j]] != j)
 				break;
 		}
 
@@ -1594,20 +1608,13 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host)
 	struct device_node *endpoint, *device_node;
 	int ret;
 
-	ret = of_property_read_u32(np, "qcom,dsi-host-index", &msm_host->id);
-	if (ret) {
-		dev_err(dev, "%s: host index not specified, ret=%d\n",
-			__func__, ret);
-		return ret;
-	}
-
 	/*
-	 * Get the first endpoint node. In our case, dsi has one output port
-	 * to which the panel is connected. Don't return an error if a port
-	 * isn't defined. It's possible that there is nothing connected to
-	 * the dsi output.
+	 * Get the endpoint of the output port of the DSI host. In our case,
+	 * this is mapped to port number with reg = 1. Don't return an error if
+	 * the remote endpoint isn't defined. It's possible that there is
+	 * nothing connected to the dsi output.
 	 */
-	endpoint = of_graph_get_next_endpoint(np, NULL);
+	endpoint = of_graph_get_endpoint_by_regs(np, 1, -1);
 	if (!endpoint) {
 		dev_dbg(dev, "%s: no endpoint\n", __func__);
 		return 0;
@@ -1648,6 +1655,25 @@ err:
 	return ret;
 }
 
+static int dsi_host_get_id(struct msm_dsi_host *msm_host)
+{
+	struct platform_device *pdev = msm_host->pdev;
+	const struct msm_dsi_config *cfg = msm_host->cfg_hnd->cfg;
+	struct resource *res;
+	int i;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dsi_ctrl");
+	if (!res)
+		return -EINVAL;
+
+	for (i = 0; i < cfg->num_dsi; i++) {
+		if (cfg->io_start[i] == res->start)
+			return i;
+	}
+
+	return -EINVAL;
+}
+
 int msm_dsi_host_init(struct msm_dsi *msm_dsi)
 {
 	struct msm_dsi_host *msm_host = NULL;
@@ -1684,6 +1710,13 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi)
 		goto fail;
 	}
 
+	msm_host->id = dsi_host_get_id(msm_host);
+	if (msm_host->id < 0) {
+		ret = msm_host->id;
+		pr_err("%s: unable to identify DSI host index\n", __func__);
+		goto fail;
+	}
+
 	/* fixup base address by io offset */
 	msm_host->ctrl_base += msm_host->cfg_hnd->cfg->io_offset;
 
@@ -2245,9 +2278,9 @@ int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host,
 	}
 
 	msm_host->mode = drm_mode_duplicate(msm_host->dev, mode);
-	if (IS_ERR(msm_host->mode)) {
+	if (!msm_host->mode) {
 		pr_err("%s: cannot duplicate mode\n", __func__);
-		return PTR_ERR(msm_host->mode);
+		return -ENOMEM;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index e2f42d8ea294..f39386ed75e4 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -271,6 +271,30 @@ static const struct of_device_id dsi_phy_dt_match[] = {
 	{}
 };
 
+/*
+ * Currently, we only support one SoC for each PHY type. When we have multiple
+ * SoCs for the same PHY, we can try to make the index searching a bit more
+ * clever.
+ */
+static int dsi_phy_get_id(struct msm_dsi_phy *phy)
+{
+	struct platform_device *pdev = phy->pdev;
+	const struct msm_dsi_phy_cfg *cfg = phy->cfg;
+	struct resource *res;
+	int i;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dsi_phy");
+	if (!res)
+		return -EINVAL;
+
+	for (i = 0; i < cfg->num_dsi_phy; i++) {
+		if (cfg->io_start[i] == res->start)
+			return i;
+	}
+
+	return -EINVAL;
+}
+
 static int dsi_phy_driver_probe(struct platform_device *pdev)
 {
 	struct msm_dsi_phy *phy;
@@ -289,10 +313,10 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 	phy->cfg = match->data;
 	phy->pdev = pdev;
 
-	ret = of_property_read_u32(dev->of_node,
-				"qcom,dsi-phy-index", &phy->id);
-	if (ret) {
-		dev_err(dev, "%s: PHY index not specified, %d\n",
+	phy->id = dsi_phy_get_id(phy);
+	if (phy->id < 0) {
+		ret = phy->id;
+		dev_err(dev, "%s: couldn't identify PHY index, %d\n",
 			__func__, ret);
 		goto fail;
 	}
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index 0d54ed00386d..f24a85439b94 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -38,6 +38,8 @@ struct msm_dsi_phy_cfg {
 	 * Fill default H/W values in illegal cells, eg. cell {0, 1}.
 	 */
 	bool src_pll_truthtable[DSI_MAX][DSI_MAX];
+	const resource_size_t io_start[DSI_MAX];
+	const int num_dsi_phy;
 };
 
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
index f4bc11af849a..c757e2070cac 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
@@ -145,6 +145,8 @@ const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs = {
 	.ops = {
 		.enable = dsi_20nm_phy_enable,
 		.disable = dsi_20nm_phy_disable,
-	}
+	},
+	.io_start = { 0xfd998300, 0xfd9a0300 },
+	.num_dsi_phy = 2,
 };
 
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
index 96d1852af418..63d7fba31380 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
@@ -145,6 +145,8 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs = {
 		.enable = dsi_28nm_phy_enable,
 		.disable = dsi_28nm_phy_disable,
 	},
+	.io_start = { 0xfd922b00, 0xfd923100 },
+	.num_dsi_phy = 2,
 };
 
 const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs = {
@@ -160,5 +162,7 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs = {
 		.enable = dsi_28nm_phy_enable,
 		.disable = dsi_28nm_phy_disable,
 	},
+	.io_start = { 0x1a98500 },
+	.num_dsi_phy = 1,
 };
 
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
index 213355a3e767..7bdb9de54968 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
@@ -192,4 +192,6 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs = {
 		.enable = dsi_28nm_phy_enable,
 		.disable = dsi_28nm_phy_disable,
 	},
+	.io_start = { 0x4700300, 0x5800300 },
+	.num_dsi_phy = 2,
 };
diff --git a/drivers/gpu/drm/msm/edp/edp_connector.c b/drivers/gpu/drm/msm/edp/edp_connector.c
index 72360cd038c0..5960628ceb93 100644
--- a/drivers/gpu/drm/msm/edp/edp_connector.c
+++ b/drivers/gpu/drm/msm/edp/edp_connector.c
@@ -91,15 +91,6 @@ static int edp_connector_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-static struct drm_encoder *
-edp_connector_best_encoder(struct drm_connector *connector)
-{
-	struct edp_connector *edp_connector = to_edp_connector(connector);
-
-	DBG("");
-	return edp_connector->edp->encoder;
-}
-
 static const struct drm_connector_funcs edp_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.detect = edp_connector_detect,
@@ -113,7 +104,6 @@ static const struct drm_connector_funcs edp_connector_funcs = {
 static const struct drm_connector_helper_funcs edp_connector_helper_funcs = {
 	.get_modes = edp_connector_get_modes,
 	.mode_valid = edp_connector_mode_valid,
-	.best_encoder = edp_connector_best_encoder,
 };
 
 /* initialize connector */
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c
index 51b9ea552f97..973720792236 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.c
@@ -19,6 +19,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_gpio.h>
 
+#include <sound/hdmi-codec.h>
 #include "hdmi.h"
 
 void msm_hdmi_set_mode(struct hdmi *hdmi, bool power_on)
@@ -434,6 +435,111 @@ static int msm_hdmi_get_gpio(struct device_node *of_node, const char *name)
 	return gpio;
 }
 
+/*
+ * HDMI audio codec callbacks
+ */
+static int msm_hdmi_audio_hw_params(struct device *dev, void *data,
+				    struct hdmi_codec_daifmt *daifmt,
+				    struct hdmi_codec_params *params)
+{
+	struct hdmi *hdmi = dev_get_drvdata(dev);
+	unsigned int chan;
+	unsigned int channel_allocation = 0;
+	unsigned int rate;
+	unsigned int level_shift  = 0; /* 0dB */
+	bool down_mix = false;
+
+	dev_dbg(dev, "%u Hz, %d bit, %d channels\n", params->sample_rate,
+		 params->sample_width, params->cea.channels);
+
+	switch (params->cea.channels) {
+	case 2:
+		/* FR and FL speakers */
+		channel_allocation  = 0;
+		chan = MSM_HDMI_AUDIO_CHANNEL_2;
+		break;
+	case 4:
+		/* FC, LFE, FR and FL speakers */
+		channel_allocation  = 0x3;
+		chan = MSM_HDMI_AUDIO_CHANNEL_4;
+		break;
+	case 6:
+		/* RR, RL, FC, LFE, FR and FL speakers */
+		channel_allocation  = 0x0B;
+		chan = MSM_HDMI_AUDIO_CHANNEL_6;
+		break;
+	case 8:
+		/* FRC, FLC, RR, RL, FC, LFE, FR and FL speakers */
+		channel_allocation  = 0x1F;
+		chan = MSM_HDMI_AUDIO_CHANNEL_8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (params->sample_rate) {
+	case 32000:
+		rate = HDMI_SAMPLE_RATE_32KHZ;
+		break;
+	case 44100:
+		rate = HDMI_SAMPLE_RATE_44_1KHZ;
+		break;
+	case 48000:
+		rate = HDMI_SAMPLE_RATE_48KHZ;
+		break;
+	case 88200:
+		rate = HDMI_SAMPLE_RATE_88_2KHZ;
+		break;
+	case 96000:
+		rate = HDMI_SAMPLE_RATE_96KHZ;
+		break;
+	case 176400:
+		rate = HDMI_SAMPLE_RATE_176_4KHZ;
+		break;
+	case 192000:
+		rate = HDMI_SAMPLE_RATE_192KHZ;
+		break;
+	default:
+		dev_err(dev, "rate[%d] not supported!\n",
+			params->sample_rate);
+		return -EINVAL;
+	}
+
+	msm_hdmi_audio_set_sample_rate(hdmi, rate);
+	msm_hdmi_audio_info_setup(hdmi, 1, chan, channel_allocation,
+			      level_shift, down_mix);
+
+	return 0;
+}
+
+static void msm_hdmi_audio_shutdown(struct device *dev, void *data)
+{
+	struct hdmi *hdmi = dev_get_drvdata(dev);
+
+	msm_hdmi_audio_info_setup(hdmi, 0, 0, 0, 0, 0);
+}
+
+static const struct hdmi_codec_ops msm_hdmi_audio_codec_ops = {
+	.hw_params = msm_hdmi_audio_hw_params,
+	.audio_shutdown = msm_hdmi_audio_shutdown,
+};
+
+static struct hdmi_codec_pdata codec_data = {
+	.ops = &msm_hdmi_audio_codec_ops,
+	.max_i2s_channels = 8,
+	.i2s = 1,
+};
+
+static int msm_hdmi_register_audio_driver(struct hdmi *hdmi, struct device *dev)
+{
+	hdmi->audio_pdev = platform_device_register_data(dev,
+							 HDMI_CODEC_DRV_NAME,
+							 PLATFORM_DEVID_AUTO,
+							 &codec_data,
+							 sizeof(codec_data));
+	return PTR_ERR_OR_ZERO(hdmi->audio_pdev);
+}
+
 static int msm_hdmi_bind(struct device *dev, struct device *master, void *data)
 {
 	struct drm_device *drm = dev_get_drvdata(master);
@@ -441,7 +547,7 @@ static int msm_hdmi_bind(struct device *dev, struct device *master, void *data)
 	static struct hdmi_platform_config *hdmi_cfg;
 	struct hdmi *hdmi;
 	struct device_node *of_node = dev->of_node;
-	int i;
+	int i, err;
 
 	hdmi_cfg = (struct hdmi_platform_config *)
 			of_device_get_match_data(dev);
@@ -468,6 +574,12 @@ static int msm_hdmi_bind(struct device *dev, struct device *master, void *data)
 		return PTR_ERR(hdmi);
 	priv->hdmi = hdmi;
 
+	err = msm_hdmi_register_audio_driver(hdmi, dev);
+	if (err) {
+		DRM_ERROR("Failed to attach an audio codec %d\n", err);
+		hdmi->audio_pdev = NULL;
+	}
+
 	return 0;
 }
 
@@ -477,6 +589,9 @@ static void msm_hdmi_unbind(struct device *dev, struct device *master,
 	struct drm_device *drm = dev_get_drvdata(master);
 	struct msm_drm_private *priv = drm->dev_private;
 	if (priv->hdmi) {
+		if (priv->hdmi->audio_pdev)
+			platform_device_unregister(priv->hdmi->audio_pdev);
+
 		msm_hdmi_destroy(priv->hdmi);
 		priv->hdmi = NULL;
 	}
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h
index bc7ba0bdee07..accc9a61611d 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.h
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.h
@@ -50,6 +50,7 @@ struct hdmi_hdcp_ctrl;
 struct hdmi {
 	struct drm_device *dev;
 	struct platform_device *pdev;
+	struct platform_device *audio_pdev;
 
 	const struct hdmi_platform_config *config;
 
@@ -210,6 +211,19 @@ static inline int msm_hdmi_pll_8996_init(struct platform_device *pdev)
 /*
  * audio:
  */
+/* Supported HDMI Audio channels and rates */
+#define	MSM_HDMI_AUDIO_CHANNEL_2	0
+#define	MSM_HDMI_AUDIO_CHANNEL_4	1
+#define	MSM_HDMI_AUDIO_CHANNEL_6	2
+#define	MSM_HDMI_AUDIO_CHANNEL_8	3
+
+#define	HDMI_SAMPLE_RATE_32KHZ		0
+#define	HDMI_SAMPLE_RATE_44_1KHZ	1
+#define	HDMI_SAMPLE_RATE_48KHZ		2
+#define	HDMI_SAMPLE_RATE_88_2KHZ	3
+#define	HDMI_SAMPLE_RATE_96KHZ		4
+#define	HDMI_SAMPLE_RATE_176_4KHZ	5
+#define	HDMI_SAMPLE_RATE_192KHZ		6
 
 int msm_hdmi_audio_update(struct hdmi *hdmi);
 int msm_hdmi_audio_info_setup(struct hdmi *hdmi, bool enabled,
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
index b15d72683112..a2515b466ce5 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
@@ -406,13 +406,6 @@ static int msm_hdmi_connector_mode_valid(struct drm_connector *connector,
 	return 0;
 }
 
-static struct drm_encoder *
-msm_hdmi_connector_best_encoder(struct drm_connector *connector)
-{
-	struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector);
-	return hdmi_connector->hdmi->encoder;
-}
-
 static const struct drm_connector_funcs hdmi_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.detect = hdmi_connector_detect,
@@ -426,7 +419,6 @@ static const struct drm_connector_funcs hdmi_connector_funcs = {
 static const struct drm_connector_helper_funcs msm_hdmi_connector_helper_funcs = {
 	.get_modes = msm_hdmi_connector_get_modes,
 	.mode_valid = msm_hdmi_connector_mode_valid,
-	.best_encoder = msm_hdmi_connector_best_encoder,
 };
 
 /* initialize connector */
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c b/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c
index 0baaaaabd002..6e767979aab3 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_hdcp.c
@@ -1430,7 +1430,7 @@ struct hdmi_hdcp_ctrl *msm_hdmi_hdcp_init(struct hdmi *hdmi)
 
 void msm_hdmi_hdcp_destroy(struct hdmi *hdmi)
 {
-	if (hdmi && hdmi->hdcp_ctrl) {
+	if (hdmi) {
 		kfree(hdmi->hdcp_ctrl);
 		hdmi->hdcp_ctrl = NULL;
 	}
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c
index 35ad78a1dc1c..24258e3025e3 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c
@@ -23,7 +23,6 @@
 
 struct mdp4_dtv_encoder {
 	struct drm_encoder base;
-	struct clk *src_clk;
 	struct clk *hdmi_clk;
 	struct clk *mdp_clk;
 	unsigned long int pixclock;
@@ -179,7 +178,6 @@ static void mdp4_dtv_encoder_disable(struct drm_encoder *encoder)
 	 */
 	mdp_irq_wait(&mdp4_kms->base, MDP4_IRQ_EXTERNAL_VSYNC);
 
-	clk_disable_unprepare(mdp4_dtv_encoder->src_clk);
 	clk_disable_unprepare(mdp4_dtv_encoder->hdmi_clk);
 	clk_disable_unprepare(mdp4_dtv_encoder->mdp_clk);
 
@@ -208,19 +206,21 @@ static void mdp4_dtv_encoder_enable(struct drm_encoder *encoder)
 
 	bs_set(mdp4_dtv_encoder, 1);
 
-	DBG("setting src_clk=%lu", pc);
+	DBG("setting mdp_clk=%lu", pc);
 
-	ret = clk_set_rate(mdp4_dtv_encoder->src_clk, pc);
+	ret = clk_set_rate(mdp4_dtv_encoder->mdp_clk, pc);
 	if (ret)
-		dev_err(dev->dev, "failed to set src_clk to %lu: %d\n", pc, ret);
-	clk_prepare_enable(mdp4_dtv_encoder->src_clk);
-	ret = clk_prepare_enable(mdp4_dtv_encoder->hdmi_clk);
-	if (ret)
-		dev_err(dev->dev, "failed to enable hdmi_clk: %d\n", ret);
+		dev_err(dev->dev, "failed to set mdp_clk to %lu: %d\n",
+			pc, ret);
+
 	ret = clk_prepare_enable(mdp4_dtv_encoder->mdp_clk);
 	if (ret)
 		dev_err(dev->dev, "failed to enabled mdp_clk: %d\n", ret);
 
+	ret = clk_prepare_enable(mdp4_dtv_encoder->hdmi_clk);
+	if (ret)
+		dev_err(dev->dev, "failed to enable hdmi_clk: %d\n", ret);
+
 	mdp4_write(mdp4_kms, REG_MDP4_DTV_ENABLE, 1);
 
 	mdp4_dtv_encoder->enabled = true;
@@ -235,7 +235,7 @@ static const struct drm_encoder_helper_funcs mdp4_dtv_encoder_helper_funcs = {
 long mdp4_dtv_round_pixclk(struct drm_encoder *encoder, unsigned long rate)
 {
 	struct mdp4_dtv_encoder *mdp4_dtv_encoder = to_mdp4_dtv_encoder(encoder);
-	return clk_round_rate(mdp4_dtv_encoder->src_clk, rate);
+	return clk_round_rate(mdp4_dtv_encoder->mdp_clk, rate);
 }
 
 /* initialize encoder */
@@ -257,13 +257,6 @@ struct drm_encoder *mdp4_dtv_encoder_init(struct drm_device *dev)
 			 DRM_MODE_ENCODER_TMDS, NULL);
 	drm_encoder_helper_add(encoder, &mdp4_dtv_encoder_helper_funcs);
 
-	mdp4_dtv_encoder->src_clk = devm_clk_get(dev->dev, "src_clk");
-	if (IS_ERR(mdp4_dtv_encoder->src_clk)) {
-		dev_err(dev->dev, "failed to get src_clk\n");
-		ret = PTR_ERR(mdp4_dtv_encoder->src_clk);
-		goto fail;
-	}
-
 	mdp4_dtv_encoder->hdmi_clk = devm_clk_get(dev->dev, "hdmi_clk");
 	if (IS_ERR(mdp4_dtv_encoder->hdmi_clk)) {
 		dev_err(dev->dev, "failed to get hdmi_clk\n");
@@ -271,9 +264,9 @@ struct drm_encoder *mdp4_dtv_encoder_init(struct drm_device *dev)
 		goto fail;
 	}
 
-	mdp4_dtv_encoder->mdp_clk = devm_clk_get(dev->dev, "mdp_clk");
+	mdp4_dtv_encoder->mdp_clk = devm_clk_get(dev->dev, "tv_clk");
 	if (IS_ERR(mdp4_dtv_encoder->mdp_clk)) {
-		dev_err(dev->dev, "failed to get mdp_clk\n");
+		dev_err(dev->dev, "failed to get tv_clk\n");
 		ret = PTR_ERR(mdp4_dtv_encoder->mdp_clk);
 		goto fail;
 	}
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
index 67442d50a6c2..7b39e89fbc2b 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
@@ -106,31 +106,27 @@ out:
 static void mdp4_prepare_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
-	int i, ncrtcs = state->dev->mode_config.num_crtc;
+	int i;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
 
 	mdp4_enable(mdp4_kms);
 
 	/* see 119ecb7fd */
-	for (i = 0; i < ncrtcs; i++) {
-		struct drm_crtc *crtc = state->crtcs[i];
-		if (!crtc)
-			continue;
+	for_each_crtc_in_state(state, crtc, crtc_state, i)
 		drm_crtc_vblank_get(crtc);
-	}
 }
 
 static void mdp4_complete_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
-	int i, ncrtcs = state->dev->mode_config.num_crtc;
+	int i;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
 
 	/* see 119ecb7fd */
-	for (i = 0; i < ncrtcs; i++) {
-		struct drm_crtc *crtc = state->crtcs[i];
-		if (!crtc)
-			continue;
+	for_each_crtc_in_state(state, crtc, crtc_state, i)
 		drm_crtc_vblank_put(crtc);
-	}
 
 	mdp4_disable(mdp4_kms);
 }
@@ -162,6 +158,7 @@ static const char * const iommu_ports[] = {
 static void mdp4_destroy(struct msm_kms *kms)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
+	struct device *dev = mdp4_kms->dev->dev;
 	struct msm_mmu *mmu = mdp4_kms->mmu;
 
 	if (mmu) {
@@ -171,8 +168,11 @@ static void mdp4_destroy(struct msm_kms *kms)
 
 	if (mdp4_kms->blank_cursor_iova)
 		msm_gem_put_iova(mdp4_kms->blank_cursor_bo, mdp4_kms->id);
-	if (mdp4_kms->blank_cursor_bo)
-		drm_gem_object_unreference_unlocked(mdp4_kms->blank_cursor_bo);
+	drm_gem_object_unreference_unlocked(mdp4_kms->blank_cursor_bo);
+
+	if (mdp4_kms->rpm_enabled)
+		pm_runtime_disable(dev);
+
 	kfree(mdp4_kms);
 }
 
@@ -440,7 +440,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 	struct mdp4_kms *mdp4_kms;
 	struct msm_kms *kms = NULL;
 	struct msm_mmu *mmu;
-	int ret;
+	int irq, ret;
 
 	mdp4_kms = kzalloc(sizeof(*mdp4_kms), GFP_KERNEL);
 	if (!mdp4_kms) {
@@ -461,6 +461,15 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 		goto fail;
 	}
 
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		ret = irq;
+		dev_err(dev->dev, "failed to get irq: %d\n", ret);
+		goto fail;
+	}
+
+	kms->irq = irq;
+
 	/* NOTE: driver for this regulator still missing upstream.. use
 	 * _get_exclusive() and ignore the error if it does not exist
 	 * (and hope that the bootloader left it on for us)
@@ -496,7 +505,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 		goto fail;
 	}
 
-	mdp4_kms->axi_clk = devm_clk_get(&pdev->dev, "mdp_axi_clk");
+	mdp4_kms->axi_clk = devm_clk_get(&pdev->dev, "bus_clk");
 	if (IS_ERR(mdp4_kms->axi_clk)) {
 		dev_err(dev->dev, "failed to get axi_clk\n");
 		ret = PTR_ERR(mdp4_kms->axi_clk);
@@ -506,6 +515,9 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 	clk_set_rate(mdp4_kms->clk, config->max_clk);
 	clk_set_rate(mdp4_kms->lut_clk, config->max_clk);
 
+	pm_runtime_enable(dev->dev);
+	mdp4_kms->rpm_enabled = true;
+
 	/* make sure things are off before attaching iommu (bootloader could
 	 * have left things on, in which case we'll start getting faults if
 	 * we don't disable):
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
index c5d045d5680d..25fb83997119 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
@@ -47,6 +47,8 @@ struct mdp4_kms {
 
 	struct mdp_irq error_handler;
 
+	bool rpm_enabled;
+
 	/* empty/blank cursor bo to use when cursor is "disabled" */
 	struct drm_gem_object *blank_cursor_bo;
 	uint32_t blank_cursor_iova;
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lvds_connector.c
index 2648cd7631ef..353429b05733 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lvds_connector.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lvds_connector.c
@@ -90,14 +90,6 @@ static int mdp4_lvds_connector_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-static struct drm_encoder *
-mdp4_lvds_connector_best_encoder(struct drm_connector *connector)
-{
-	struct mdp4_lvds_connector *mdp4_lvds_connector =
-			to_mdp4_lvds_connector(connector);
-	return mdp4_lvds_connector->encoder;
-}
-
 static const struct drm_connector_funcs mdp4_lvds_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.detect = mdp4_lvds_connector_detect,
@@ -111,7 +103,6 @@ static const struct drm_connector_funcs mdp4_lvds_connector_funcs = {
 static const struct drm_connector_helper_funcs mdp4_lvds_connector_helper_funcs = {
 	.get_modes = mdp4_lvds_connector_get_modes,
 	.mode_valid = mdp4_lvds_connector_mode_valid,
-	.best_encoder = mdp4_lvds_connector_best_encoder,
 };
 
 /* initialize connector */
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h
index b275ce11b24b..ca6ca30650a0 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h
@@ -8,19 +8,11 @@ http://github.com/freedreno/envytools/
 git clone https://github.com/freedreno/envytools.git
 
 The rules-ng-ng source files this header was generated from are:
-- /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    676 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-02-10 17:07:21)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20915 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2015-09-18 12:07:28)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  37194 bytes, from 2015-09-18 12:07:28)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  27887 bytes, from 2015-10-22 16:34:52)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    602 bytes, from 2015-10-22 16:35:02)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2015-05-20 20:03:14)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2015-05-20 20:03:07)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  41472 bytes, from 2016-01-22 18:18:18)
-- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml             (  10416 bytes, from 2015-05-20 20:03:14)
-
-Copyright (C) 2013-2015 by the following authors:
+- /local/mnt/workspace/source_trees/envytools/rnndb/../rnndb/mdp/mdp5.xml   (  36965 bytes, from 2016-05-10 05:06:30)
+- /local/mnt/workspace/source_trees/envytools/rnndb/freedreno_copyright.xml (   1572 bytes, from 2016-05-09 06:32:54)
+- /local/mnt/workspace/source_trees/envytools/rnndb/mdp/mdp_common.xml      (   2849 bytes, from 2016-01-07 08:45:55)
+
+Copyright (C) 2013-2016 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -198,118 +190,109 @@ static inline uint32_t MDSS_HW_VERSION_MAJOR(uint32_t val)
 #define MDSS_HW_INTR_STATUS_INTR_HDMI				0x00000100
 #define MDSS_HW_INTR_STATUS_INTR_EDP				0x00001000
 
-static inline uint32_t __offset_MDP(uint32_t idx)
-{
-	switch (idx) {
-		case 0: return (mdp5_cfg->mdp.base[0]);
-		default: return INVALID_IDX(idx);
-	}
-}
-static inline uint32_t REG_MDP5_MDP(uint32_t i0) { return 0x00000000 + __offset_MDP(i0); }
-
-static inline uint32_t REG_MDP5_MDP_HW_VERSION(uint32_t i0) { return 0x00000000 + __offset_MDP(i0); }
-#define MDP5_MDP_HW_VERSION_STEP__MASK				0x0000ffff
-#define MDP5_MDP_HW_VERSION_STEP__SHIFT				0
-static inline uint32_t MDP5_MDP_HW_VERSION_STEP(uint32_t val)
+#define REG_MDP5_HW_VERSION					0x00000000
+#define MDP5_HW_VERSION_STEP__MASK				0x0000ffff
+#define MDP5_HW_VERSION_STEP__SHIFT				0
+static inline uint32_t MDP5_HW_VERSION_STEP(uint32_t val)
 {
-	return ((val) << MDP5_MDP_HW_VERSION_STEP__SHIFT) & MDP5_MDP_HW_VERSION_STEP__MASK;
+	return ((val) << MDP5_HW_VERSION_STEP__SHIFT) & MDP5_HW_VERSION_STEP__MASK;
 }
-#define MDP5_MDP_HW_VERSION_MINOR__MASK				0x0fff0000
-#define MDP5_MDP_HW_VERSION_MINOR__SHIFT			16
-static inline uint32_t MDP5_MDP_HW_VERSION_MINOR(uint32_t val)
+#define MDP5_HW_VERSION_MINOR__MASK				0x0fff0000
+#define MDP5_HW_VERSION_MINOR__SHIFT				16
+static inline uint32_t MDP5_HW_VERSION_MINOR(uint32_t val)
 {
-	return ((val) << MDP5_MDP_HW_VERSION_MINOR__SHIFT) & MDP5_MDP_HW_VERSION_MINOR__MASK;
+	return ((val) << MDP5_HW_VERSION_MINOR__SHIFT) & MDP5_HW_VERSION_MINOR__MASK;
 }
-#define MDP5_MDP_HW_VERSION_MAJOR__MASK				0xf0000000
-#define MDP5_MDP_HW_VERSION_MAJOR__SHIFT			28
-static inline uint32_t MDP5_MDP_HW_VERSION_MAJOR(uint32_t val)
+#define MDP5_HW_VERSION_MAJOR__MASK				0xf0000000
+#define MDP5_HW_VERSION_MAJOR__SHIFT				28
+static inline uint32_t MDP5_HW_VERSION_MAJOR(uint32_t val)
 {
-	return ((val) << MDP5_MDP_HW_VERSION_MAJOR__SHIFT) & MDP5_MDP_HW_VERSION_MAJOR__MASK;
+	return ((val) << MDP5_HW_VERSION_MAJOR__SHIFT) & MDP5_HW_VERSION_MAJOR__MASK;
 }
 
-static inline uint32_t REG_MDP5_MDP_DISP_INTF_SEL(uint32_t i0) { return 0x00000004 + __offset_MDP(i0); }
-#define MDP5_MDP_DISP_INTF_SEL_INTF0__MASK			0x000000ff
-#define MDP5_MDP_DISP_INTF_SEL_INTF0__SHIFT			0
-static inline uint32_t MDP5_MDP_DISP_INTF_SEL_INTF0(enum mdp5_intf_type val)
+#define REG_MDP5_DISP_INTF_SEL					0x00000004
+#define MDP5_DISP_INTF_SEL_INTF0__MASK				0x000000ff
+#define MDP5_DISP_INTF_SEL_INTF0__SHIFT				0
+static inline uint32_t MDP5_DISP_INTF_SEL_INTF0(enum mdp5_intf_type val)
 {
-	return ((val) << MDP5_MDP_DISP_INTF_SEL_INTF0__SHIFT) & MDP5_MDP_DISP_INTF_SEL_INTF0__MASK;
+	return ((val) << MDP5_DISP_INTF_SEL_INTF0__SHIFT) & MDP5_DISP_INTF_SEL_INTF0__MASK;
 }
-#define MDP5_MDP_DISP_INTF_SEL_INTF1__MASK			0x0000ff00
-#define MDP5_MDP_DISP_INTF_SEL_INTF1__SHIFT			8
-static inline uint32_t MDP5_MDP_DISP_INTF_SEL_INTF1(enum mdp5_intf_type val)
+#define MDP5_DISP_INTF_SEL_INTF1__MASK				0x0000ff00
+#define MDP5_DISP_INTF_SEL_INTF1__SHIFT				8
+static inline uint32_t MDP5_DISP_INTF_SEL_INTF1(enum mdp5_intf_type val)
 {
-	return ((val) << MDP5_MDP_DISP_INTF_SEL_INTF1__SHIFT) & MDP5_MDP_DISP_INTF_SEL_INTF1__MASK;
+	return ((val) << MDP5_DISP_INTF_SEL_INTF1__SHIFT) & MDP5_DISP_INTF_SEL_INTF1__MASK;
 }
-#define MDP5_MDP_DISP_INTF_SEL_INTF2__MASK			0x00ff0000
-#define MDP5_MDP_DISP_INTF_SEL_INTF2__SHIFT			16
-static inline uint32_t MDP5_MDP_DISP_INTF_SEL_INTF2(enum mdp5_intf_type val)
+#define MDP5_DISP_INTF_SEL_INTF2__MASK				0x00ff0000
+#define MDP5_DISP_INTF_SEL_INTF2__SHIFT				16
+static inline uint32_t MDP5_DISP_INTF_SEL_INTF2(enum mdp5_intf_type val)
 {
-	return ((val) << MDP5_MDP_DISP_INTF_SEL_INTF2__SHIFT) & MDP5_MDP_DISP_INTF_SEL_INTF2__MASK;
+	return ((val) << MDP5_DISP_INTF_SEL_INTF2__SHIFT) & MDP5_DISP_INTF_SEL_INTF2__MASK;
 }
-#define MDP5_MDP_DISP_INTF_SEL_INTF3__MASK			0xff000000
-#define MDP5_MDP_DISP_INTF_SEL_INTF3__SHIFT			24
-static inline uint32_t MDP5_MDP_DISP_INTF_SEL_INTF3(enum mdp5_intf_type val)
+#define MDP5_DISP_INTF_SEL_INTF3__MASK				0xff000000
+#define MDP5_DISP_INTF_SEL_INTF3__SHIFT				24
+static inline uint32_t MDP5_DISP_INTF_SEL_INTF3(enum mdp5_intf_type val)
 {
-	return ((val) << MDP5_MDP_DISP_INTF_SEL_INTF3__SHIFT) & MDP5_MDP_DISP_INTF_SEL_INTF3__MASK;
+	return ((val) << MDP5_DISP_INTF_SEL_INTF3__SHIFT) & MDP5_DISP_INTF_SEL_INTF3__MASK;
 }
 
-static inline uint32_t REG_MDP5_MDP_INTR_EN(uint32_t i0) { return 0x00000010 + __offset_MDP(i0); }
+#define REG_MDP5_INTR_EN					0x00000010
 
-static inline uint32_t REG_MDP5_MDP_INTR_STATUS(uint32_t i0) { return 0x00000014 + __offset_MDP(i0); }
+#define REG_MDP5_INTR_STATUS					0x00000014
 
-static inline uint32_t REG_MDP5_MDP_INTR_CLEAR(uint32_t i0) { return 0x00000018 + __offset_MDP(i0); }
+#define REG_MDP5_INTR_CLEAR					0x00000018
 
-static inline uint32_t REG_MDP5_MDP_HIST_INTR_EN(uint32_t i0) { return 0x0000001c + __offset_MDP(i0); }
+#define REG_MDP5_HIST_INTR_EN					0x0000001c
 
-static inline uint32_t REG_MDP5_MDP_HIST_INTR_STATUS(uint32_t i0) { return 0x00000020 + __offset_MDP(i0); }
+#define REG_MDP5_HIST_INTR_STATUS				0x00000020
 
-static inline uint32_t REG_MDP5_MDP_HIST_INTR_CLEAR(uint32_t i0) { return 0x00000024 + __offset_MDP(i0); }
+#define REG_MDP5_HIST_INTR_CLEAR				0x00000024
 
-static inline uint32_t REG_MDP5_MDP_SPARE_0(uint32_t i0) { return 0x00000028 + __offset_MDP(i0); }
-#define MDP5_MDP_SPARE_0_SPLIT_DPL_SINGLE_FLUSH_EN		0x00000001
+#define REG_MDP5_SPARE_0					0x00000028
+#define MDP5_SPARE_0_SPLIT_DPL_SINGLE_FLUSH_EN			0x00000001
 
-static inline uint32_t REG_MDP5_MDP_SMP_ALLOC_W(uint32_t i0, uint32_t i1) { return 0x00000080 + __offset_MDP(i0) + 0x4*i1; }
+static inline uint32_t REG_MDP5_SMP_ALLOC_W(uint32_t i0) { return 0x00000080 + 0x4*i0; }
 
-static inline uint32_t REG_MDP5_MDP_SMP_ALLOC_W_REG(uint32_t i0, uint32_t i1) { return 0x00000080 + __offset_MDP(i0) + 0x4*i1; }
-#define MDP5_MDP_SMP_ALLOC_W_REG_CLIENT0__MASK			0x000000ff
-#define MDP5_MDP_SMP_ALLOC_W_REG_CLIENT0__SHIFT			0
-static inline uint32_t MDP5_MDP_SMP_ALLOC_W_REG_CLIENT0(uint32_t val)
+static inline uint32_t REG_MDP5_SMP_ALLOC_W_REG(uint32_t i0) { return 0x00000080 + 0x4*i0; }
+#define MDP5_SMP_ALLOC_W_REG_CLIENT0__MASK			0x000000ff
+#define MDP5_SMP_ALLOC_W_REG_CLIENT0__SHIFT			0
+static inline uint32_t MDP5_SMP_ALLOC_W_REG_CLIENT0(uint32_t val)
 {
-	return ((val) << MDP5_MDP_SMP_ALLOC_W_REG_CLIENT0__SHIFT) & MDP5_MDP_SMP_ALLOC_W_REG_CLIENT0__MASK;
+	return ((val) << MDP5_SMP_ALLOC_W_REG_CLIENT0__SHIFT) & MDP5_SMP_ALLOC_W_REG_CLIENT0__MASK;
 }
-#define MDP5_MDP_SMP_ALLOC_W_REG_CLIENT1__MASK			0x0000ff00
-#define MDP5_MDP_SMP_ALLOC_W_REG_CLIENT1__SHIFT			8
-static inline uint32_t MDP5_MDP_SMP_ALLOC_W_REG_CLIENT1(uint32_t val)
+#define MDP5_SMP_ALLOC_W_REG_CLIENT1__MASK			0x0000ff00
+#define MDP5_SMP_ALLOC_W_REG_CLIENT1__SHIFT			8
+static inline uint32_t MDP5_SMP_ALLOC_W_REG_CLIENT1(uint32_t val)
 {
-	return ((val) << MDP5_MDP_SMP_ALLOC_W_REG_CLIENT1__SHIFT) & MDP5_MDP_SMP_ALLOC_W_REG_CLIENT1__MASK;
+	return ((val) << MDP5_SMP_ALLOC_W_REG_CLIENT1__SHIFT) & MDP5_SMP_ALLOC_W_REG_CLIENT1__MASK;
 }
-#define MDP5_MDP_SMP_ALLOC_W_REG_CLIENT2__MASK			0x00ff0000
-#define MDP5_MDP_SMP_ALLOC_W_REG_CLIENT2__SHIFT			16
-static inline uint32_t MDP5_MDP_SMP_ALLOC_W_REG_CLIENT2(uint32_t val)
+#define MDP5_SMP_ALLOC_W_REG_CLIENT2__MASK			0x00ff0000
+#define MDP5_SMP_ALLOC_W_REG_CLIENT2__SHIFT			16
+static inline uint32_t MDP5_SMP_ALLOC_W_REG_CLIENT2(uint32_t val)
 {
-	return ((val) << MDP5_MDP_SMP_ALLOC_W_REG_CLIENT2__SHIFT) & MDP5_MDP_SMP_ALLOC_W_REG_CLIENT2__MASK;
+	return ((val) << MDP5_SMP_ALLOC_W_REG_CLIENT2__SHIFT) & MDP5_SMP_ALLOC_W_REG_CLIENT2__MASK;
 }
 
-static inline uint32_t REG_MDP5_MDP_SMP_ALLOC_R(uint32_t i0, uint32_t i1) { return 0x00000130 + __offset_MDP(i0) + 0x4*i1; }
+static inline uint32_t REG_MDP5_SMP_ALLOC_R(uint32_t i0) { return 0x00000130 + 0x4*i0; }
 
-static inline uint32_t REG_MDP5_MDP_SMP_ALLOC_R_REG(uint32_t i0, uint32_t i1) { return 0x00000130 + __offset_MDP(i0) + 0x4*i1; }
-#define MDP5_MDP_SMP_ALLOC_R_REG_CLIENT0__MASK			0x000000ff
-#define MDP5_MDP_SMP_ALLOC_R_REG_CLIENT0__SHIFT			0
-static inline uint32_t MDP5_MDP_SMP_ALLOC_R_REG_CLIENT0(uint32_t val)
+static inline uint32_t REG_MDP5_SMP_ALLOC_R_REG(uint32_t i0) { return 0x00000130 + 0x4*i0; }
+#define MDP5_SMP_ALLOC_R_REG_CLIENT0__MASK			0x000000ff
+#define MDP5_SMP_ALLOC_R_REG_CLIENT0__SHIFT			0
+static inline uint32_t MDP5_SMP_ALLOC_R_REG_CLIENT0(uint32_t val)
 {
-	return ((val) << MDP5_MDP_SMP_ALLOC_R_REG_CLIENT0__SHIFT) & MDP5_MDP_SMP_ALLOC_R_REG_CLIENT0__MASK;
+	return ((val) << MDP5_SMP_ALLOC_R_REG_CLIENT0__SHIFT) & MDP5_SMP_ALLOC_R_REG_CLIENT0__MASK;
 }
-#define MDP5_MDP_SMP_ALLOC_R_REG_CLIENT1__MASK			0x0000ff00
-#define MDP5_MDP_SMP_ALLOC_R_REG_CLIENT1__SHIFT			8
-static inline uint32_t MDP5_MDP_SMP_ALLOC_R_REG_CLIENT1(uint32_t val)
+#define MDP5_SMP_ALLOC_R_REG_CLIENT1__MASK			0x0000ff00
+#define MDP5_SMP_ALLOC_R_REG_CLIENT1__SHIFT			8
+static inline uint32_t MDP5_SMP_ALLOC_R_REG_CLIENT1(uint32_t val)
 {
-	return ((val) << MDP5_MDP_SMP_ALLOC_R_REG_CLIENT1__SHIFT) & MDP5_MDP_SMP_ALLOC_R_REG_CLIENT1__MASK;
+	return ((val) << MDP5_SMP_ALLOC_R_REG_CLIENT1__SHIFT) & MDP5_SMP_ALLOC_R_REG_CLIENT1__MASK;
 }
-#define MDP5_MDP_SMP_ALLOC_R_REG_CLIENT2__MASK			0x00ff0000
-#define MDP5_MDP_SMP_ALLOC_R_REG_CLIENT2__SHIFT			16
-static inline uint32_t MDP5_MDP_SMP_ALLOC_R_REG_CLIENT2(uint32_t val)
+#define MDP5_SMP_ALLOC_R_REG_CLIENT2__MASK			0x00ff0000
+#define MDP5_SMP_ALLOC_R_REG_CLIENT2__SHIFT			16
+static inline uint32_t MDP5_SMP_ALLOC_R_REG_CLIENT2(uint32_t val)
 {
-	return ((val) << MDP5_MDP_SMP_ALLOC_R_REG_CLIENT2__SHIFT) & MDP5_MDP_SMP_ALLOC_R_REG_CLIENT2__MASK;
+	return ((val) << MDP5_SMP_ALLOC_R_REG_CLIENT2__SHIFT) & MDP5_SMP_ALLOC_R_REG_CLIENT2__MASK;
 }
 
 static inline uint32_t __offset_IGC(enum mdp5_igc_type idx)
@@ -322,35 +305,35 @@ static inline uint32_t __offset_IGC(enum mdp5_igc_type idx)
 		default: return INVALID_IDX(idx);
 	}
 }
-static inline uint32_t REG_MDP5_MDP_IGC(uint32_t i0, enum mdp5_igc_type i1) { return 0x00000000 + __offset_MDP(i0) + __offset_IGC(i1); }
+static inline uint32_t REG_MDP5_IGC(enum mdp5_igc_type i0) { return 0x00000000 + __offset_IGC(i0); }
 
-static inline uint32_t REG_MDP5_MDP_IGC_LUT(uint32_t i0, enum mdp5_igc_type i1, uint32_t i2) { return 0x00000000 + __offset_MDP(i0) + __offset_IGC(i1) + 0x4*i2; }
+static inline uint32_t REG_MDP5_IGC_LUT(enum mdp5_igc_type i0, uint32_t i1) { return 0x00000000 + __offset_IGC(i0) + 0x4*i1; }
 
-static inline uint32_t REG_MDP5_MDP_IGC_LUT_REG(uint32_t i0, enum mdp5_igc_type i1, uint32_t i2) { return 0x00000000 + __offset_MDP(i0) + __offset_IGC(i1) + 0x4*i2; }
-#define MDP5_MDP_IGC_LUT_REG_VAL__MASK				0x00000fff
-#define MDP5_MDP_IGC_LUT_REG_VAL__SHIFT				0
-static inline uint32_t MDP5_MDP_IGC_LUT_REG_VAL(uint32_t val)
+static inline uint32_t REG_MDP5_IGC_LUT_REG(enum mdp5_igc_type i0, uint32_t i1) { return 0x00000000 + __offset_IGC(i0) + 0x4*i1; }
+#define MDP5_IGC_LUT_REG_VAL__MASK				0x00000fff
+#define MDP5_IGC_LUT_REG_VAL__SHIFT				0
+static inline uint32_t MDP5_IGC_LUT_REG_VAL(uint32_t val)
 {
-	return ((val) << MDP5_MDP_IGC_LUT_REG_VAL__SHIFT) & MDP5_MDP_IGC_LUT_REG_VAL__MASK;
+	return ((val) << MDP5_IGC_LUT_REG_VAL__SHIFT) & MDP5_IGC_LUT_REG_VAL__MASK;
 }
-#define MDP5_MDP_IGC_LUT_REG_INDEX_UPDATE			0x02000000
-#define MDP5_MDP_IGC_LUT_REG_DISABLE_PIPE_0			0x10000000
-#define MDP5_MDP_IGC_LUT_REG_DISABLE_PIPE_1			0x20000000
-#define MDP5_MDP_IGC_LUT_REG_DISABLE_PIPE_2			0x40000000
+#define MDP5_IGC_LUT_REG_INDEX_UPDATE				0x02000000
+#define MDP5_IGC_LUT_REG_DISABLE_PIPE_0				0x10000000
+#define MDP5_IGC_LUT_REG_DISABLE_PIPE_1				0x20000000
+#define MDP5_IGC_LUT_REG_DISABLE_PIPE_2				0x40000000
 
-static inline uint32_t REG_MDP5_MDP_SPLIT_DPL_EN(uint32_t i0) { return 0x000002f4 + __offset_MDP(i0); }
+#define REG_MDP5_SPLIT_DPL_EN					0x000002f4
 
-static inline uint32_t REG_MDP5_MDP_SPLIT_DPL_UPPER(uint32_t i0) { return 0x000002f8 + __offset_MDP(i0); }
-#define MDP5_MDP_SPLIT_DPL_UPPER_SMART_PANEL			0x00000002
-#define MDP5_MDP_SPLIT_DPL_UPPER_SMART_PANEL_FREE_RUN		0x00000004
-#define MDP5_MDP_SPLIT_DPL_UPPER_INTF1_SW_TRG_MUX		0x00000010
-#define MDP5_MDP_SPLIT_DPL_UPPER_INTF2_SW_TRG_MUX		0x00000100
+#define REG_MDP5_SPLIT_DPL_UPPER				0x000002f8
+#define MDP5_SPLIT_DPL_UPPER_SMART_PANEL			0x00000002
+#define MDP5_SPLIT_DPL_UPPER_SMART_PANEL_FREE_RUN		0x00000004
+#define MDP5_SPLIT_DPL_UPPER_INTF1_SW_TRG_MUX			0x00000010
+#define MDP5_SPLIT_DPL_UPPER_INTF2_SW_TRG_MUX			0x00000100
 
-static inline uint32_t REG_MDP5_MDP_SPLIT_DPL_LOWER(uint32_t i0) { return 0x000003f0 + __offset_MDP(i0); }
-#define MDP5_MDP_SPLIT_DPL_LOWER_SMART_PANEL			0x00000002
-#define MDP5_MDP_SPLIT_DPL_LOWER_SMART_PANEL_FREE_RUN		0x00000004
-#define MDP5_MDP_SPLIT_DPL_LOWER_INTF1_TG_SYNC			0x00000010
-#define MDP5_MDP_SPLIT_DPL_LOWER_INTF2_TG_SYNC			0x00000100
+#define REG_MDP5_SPLIT_DPL_LOWER				0x000003f0
+#define MDP5_SPLIT_DPL_LOWER_SMART_PANEL			0x00000002
+#define MDP5_SPLIT_DPL_LOWER_SMART_PANEL_FREE_RUN		0x00000004
+#define MDP5_SPLIT_DPL_LOWER_INTF1_TG_SYNC			0x00000010
+#define MDP5_SPLIT_DPL_LOWER_INTF2_TG_SYNC			0x00000100
 
 static inline uint32_t __offset_CTL(uint32_t idx)
 {
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
index 57f73f0c120d..ac9e4cde1380 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
@@ -26,7 +26,6 @@ const struct mdp5_cfg_hw msm8x74v1_config = {
 	.name = "msm8x74v1",
 	.mdp = {
 		.count = 1,
-		.base = { 0x00100 },
 		.caps = MDP_CAP_SMP |
 			0,
 	},
@@ -41,12 +40,12 @@ const struct mdp5_cfg_hw msm8x74v1_config = {
 	},
 	.ctl = {
 		.count = 5,
-		.base = { 0x00600, 0x00700, 0x00800, 0x00900, 0x00a00 },
+		.base = { 0x00500, 0x00600, 0x00700, 0x00800, 0x00900 },
 		.flush_hw_mask = 0x0003ffff,
 	},
 	.pipe_vig = {
 		.count = 3,
-		.base = { 0x01200, 0x01600, 0x01a00 },
+		.base = { 0x01100, 0x01500, 0x01900 },
 		.caps = MDP_PIPE_CAP_HFLIP |
 			MDP_PIPE_CAP_VFLIP |
 			MDP_PIPE_CAP_SCALE |
@@ -55,7 +54,7 @@ const struct mdp5_cfg_hw msm8x74v1_config = {
 	},
 	.pipe_rgb = {
 		.count = 3,
-		.base = { 0x01e00, 0x02200, 0x02600 },
+		.base = { 0x01d00, 0x02100, 0x02500 },
 		.caps = MDP_PIPE_CAP_HFLIP |
 			MDP_PIPE_CAP_VFLIP |
 			MDP_PIPE_CAP_SCALE |
@@ -63,26 +62,26 @@ const struct mdp5_cfg_hw msm8x74v1_config = {
 	},
 	.pipe_dma = {
 		.count = 2,
-		.base = { 0x02a00, 0x02e00 },
+		.base = { 0x02900, 0x02d00 },
 		.caps = MDP_PIPE_CAP_HFLIP |
 			MDP_PIPE_CAP_VFLIP |
 			0,
 	},
 	.lm = {
 		.count = 5,
-		.base = { 0x03200, 0x03600, 0x03a00, 0x03e00, 0x04200 },
+		.base = { 0x03100, 0x03500, 0x03900, 0x03d00, 0x04100 },
 		.nb_stages = 5,
 	},
 	.dspp = {
 		.count = 3,
-		.base = { 0x04600, 0x04a00, 0x04e00 },
+		.base = { 0x04500, 0x04900, 0x04d00 },
 	},
 	.pp = {
 		.count = 3,
-		.base = { 0x21b00, 0x21c00, 0x21d00 },
+		.base = { 0x21a00, 0x21b00, 0x21c00 },
 	},
 	.intf = {
-		.base = { 0x21100, 0x21300, 0x21500, 0x21700 },
+		.base = { 0x21000, 0x21200, 0x21400, 0x21600 },
 		.connect = {
 			[0] = INTF_eDP,
 			[1] = INTF_DSI,
@@ -97,7 +96,6 @@ const struct mdp5_cfg_hw msm8x74v2_config = {
 	.name = "msm8x74",
 	.mdp = {
 		.count = 1,
-		.base = { 0x00100 },
 		.caps = MDP_CAP_SMP |
 			0,
 	},
@@ -112,48 +110,48 @@ const struct mdp5_cfg_hw msm8x74v2_config = {
 	},
 	.ctl = {
 		.count = 5,
-		.base = { 0x00600, 0x00700, 0x00800, 0x00900, 0x00a00 },
+		.base = { 0x00500, 0x00600, 0x00700, 0x00800, 0x00900 },
 		.flush_hw_mask = 0x0003ffff,
 	},
 	.pipe_vig = {
 		.count = 3,
-		.base = { 0x01200, 0x01600, 0x01a00 },
+		.base = { 0x01100, 0x01500, 0x01900 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP |
 				MDP_PIPE_CAP_SCALE | MDP_PIPE_CAP_CSC |
 				MDP_PIPE_CAP_DECIMATION,
 	},
 	.pipe_rgb = {
 		.count = 3,
-		.base = { 0x01e00, 0x02200, 0x02600 },
+		.base = { 0x01d00, 0x02100, 0x02500 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP |
 				MDP_PIPE_CAP_SCALE | MDP_PIPE_CAP_DECIMATION,
 	},
 	.pipe_dma = {
 		.count = 2,
-		.base = { 0x02a00, 0x02e00 },
+		.base = { 0x02900, 0x02d00 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP,
 	},
 	.lm = {
 		.count = 5,
-		.base = { 0x03200, 0x03600, 0x03a00, 0x03e00, 0x04200 },
+		.base = { 0x03100, 0x03500, 0x03900, 0x03d00, 0x04100 },
 		.nb_stages = 5,
 		.max_width = 2048,
 		.max_height = 0xFFFF,
 	},
 	.dspp = {
 		.count = 3,
-		.base = { 0x04600, 0x04a00, 0x04e00 },
+		.base = { 0x04500, 0x04900, 0x04d00 },
 	},
 	.ad = {
 		.count = 2,
-		.base = { 0x13100, 0x13300 },
+		.base = { 0x13000, 0x13200 },
 	},
 	.pp = {
 		.count = 3,
-		.base = { 0x12d00, 0x12e00, 0x12f00 },
+		.base = { 0x12c00, 0x12d00, 0x12e00 },
 	},
 	.intf = {
-		.base = { 0x12500, 0x12700, 0x12900, 0x12b00 },
+		.base = { 0x12400, 0x12600, 0x12800, 0x12a00 },
 		.connect = {
 			[0] = INTF_eDP,
 			[1] = INTF_DSI,
@@ -168,7 +166,6 @@ const struct mdp5_cfg_hw apq8084_config = {
 	.name = "apq8084",
 	.mdp = {
 		.count = 1,
-		.base = { 0x00100 },
 		.caps = MDP_CAP_SMP |
 			0,
 	},
@@ -190,49 +187,49 @@ const struct mdp5_cfg_hw apq8084_config = {
 	},
 	.ctl = {
 		.count = 5,
-		.base = { 0x00600, 0x00700, 0x00800, 0x00900, 0x00a00 },
+		.base = { 0x00500, 0x00600, 0x00700, 0x00800, 0x00900 },
 		.flush_hw_mask = 0x003fffff,
 	},
 	.pipe_vig = {
 		.count = 4,
-		.base = { 0x01200, 0x01600, 0x01a00, 0x01e00 },
+		.base = { 0x01100, 0x01500, 0x01900, 0x01d00 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP |
 				MDP_PIPE_CAP_SCALE | MDP_PIPE_CAP_CSC |
 				MDP_PIPE_CAP_DECIMATION,
 	},
 	.pipe_rgb = {
 		.count = 4,
-		.base = { 0x02200, 0x02600, 0x02a00, 0x02e00 },
+		.base = { 0x02100, 0x02500, 0x02900, 0x02d00 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP |
 				MDP_PIPE_CAP_SCALE | MDP_PIPE_CAP_DECIMATION,
 	},
 	.pipe_dma = {
 		.count = 2,
-		.base = { 0x03200, 0x03600 },
+		.base = { 0x03100, 0x03500 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP,
 	},
 	.lm = {
 		.count = 6,
-		.base = { 0x03a00, 0x03e00, 0x04200, 0x04600, 0x04a00, 0x04e00 },
+		.base = { 0x03900, 0x03d00, 0x04100, 0x04500, 0x04900, 0x04d00 },
 		.nb_stages = 5,
 		.max_width = 2048,
 		.max_height = 0xFFFF,
 	},
 	.dspp = {
 		.count = 4,
-		.base = { 0x05200, 0x05600, 0x05a00, 0x05e00 },
+		.base = { 0x05100, 0x05500, 0x05900, 0x05d00 },
 
 	},
 	.ad = {
 		.count = 3,
-		.base = { 0x13500, 0x13700, 0x13900 },
+		.base = { 0x13400, 0x13600, 0x13800 },
 	},
 	.pp = {
 		.count = 4,
-		.base = { 0x12f00, 0x13000, 0x13100, 0x13200 },
+		.base = { 0x12e00, 0x12f00, 0x13000, 0x13100 },
 	},
 	.intf = {
-		.base = { 0x12500, 0x12700, 0x12900, 0x12b00, 0x12d00 },
+		.base = { 0x12400, 0x12600, 0x12800, 0x12a00, 0x12c00 },
 		.connect = {
 			[0] = INTF_eDP,
 			[1] = INTF_DSI,
@@ -247,7 +244,7 @@ const struct mdp5_cfg_hw msm8x16_config = {
 	.name = "msm8x16",
 	.mdp = {
 		.count = 1,
-		.base = { 0x01000 },
+		.base = { 0x0 },
 		.caps = MDP_CAP_SMP |
 			0,
 	},
@@ -261,41 +258,41 @@ const struct mdp5_cfg_hw msm8x16_config = {
 	},
 	.ctl = {
 		.count = 5,
-		.base = { 0x02000, 0x02200, 0x02400, 0x02600, 0x02800 },
+		.base = { 0x01000, 0x01200, 0x01400, 0x01600, 0x01800 },
 		.flush_hw_mask = 0x4003ffff,
 	},
 	.pipe_vig = {
 		.count = 1,
-		.base = { 0x05000 },
+		.base = { 0x04000 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP |
 				MDP_PIPE_CAP_SCALE | MDP_PIPE_CAP_CSC |
 				MDP_PIPE_CAP_DECIMATION,
 	},
 	.pipe_rgb = {
 		.count = 2,
-		.base = { 0x15000, 0x17000 },
+		.base = { 0x14000, 0x16000 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP |
 				MDP_PIPE_CAP_SCALE | MDP_PIPE_CAP_DECIMATION,
 	},
 	.pipe_dma = {
 		.count = 1,
-		.base = { 0x25000 },
+		.base = { 0x24000 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP,
 	},
 	.lm = {
 		.count = 2, /* LM0 and LM3 */
-		.base = { 0x45000, 0x48000 },
+		.base = { 0x44000, 0x47000 },
 		.nb_stages = 5,
 		.max_width = 2048,
 		.max_height = 0xFFFF,
 	},
 	.dspp = {
 		.count = 1,
-		.base = { 0x55000 },
+		.base = { 0x54000 },
 
 	},
 	.intf = {
-		.base = { 0x00000, 0x6b800 },
+		.base = { 0x00000, 0x6a800 },
 		.connect = {
 			[0] = INTF_DISABLED,
 			[1] = INTF_DSI,
@@ -308,7 +305,6 @@ const struct mdp5_cfg_hw msm8x94_config = {
 	.name = "msm8x94",
 	.mdp = {
 		.count = 1,
-		.base = { 0x01000 },
 		.caps = MDP_CAP_SMP |
 			0,
 	},
@@ -330,49 +326,49 @@ const struct mdp5_cfg_hw msm8x94_config = {
 	},
 	.ctl = {
 		.count = 5,
-		.base = { 0x02000, 0x02200, 0x02400, 0x02600, 0x02800 },
+		.base = { 0x01000, 0x01200, 0x01400, 0x01600, 0x01800 },
 		.flush_hw_mask = 0xf0ffffff,
 	},
 	.pipe_vig = {
 		.count = 4,
-		.base = { 0x05000, 0x07000, 0x09000, 0x0b000 },
+		.base = { 0x04000, 0x06000, 0x08000, 0x0a000 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP |
 				MDP_PIPE_CAP_SCALE | MDP_PIPE_CAP_CSC |
 				MDP_PIPE_CAP_DECIMATION,
 	},
 	.pipe_rgb = {
 		.count = 4,
-		.base = { 0x15000, 0x17000, 0x19000, 0x1b000 },
+		.base = { 0x14000, 0x16000, 0x18000, 0x1a000 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP |
 				MDP_PIPE_CAP_SCALE | MDP_PIPE_CAP_DECIMATION,
 	},
 	.pipe_dma = {
 		.count = 2,
-		.base = { 0x25000, 0x27000 },
+		.base = { 0x24000, 0x26000 },
 		.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP,
 	},
 	.lm = {
 		.count = 6,
-		.base = { 0x45000, 0x46000, 0x47000, 0x48000, 0x49000, 0x4a000 },
+		.base = { 0x44000, 0x45000, 0x46000, 0x47000, 0x48000, 0x49000 },
 		.nb_stages = 8,
 		.max_width = 2048,
 		.max_height = 0xFFFF,
 	},
 	.dspp = {
 		.count = 4,
-		.base = { 0x55000, 0x57000, 0x59000, 0x5b000 },
+		.base = { 0x54000, 0x56000, 0x58000, 0x5a000 },
 
 	},
 	.ad = {
 		.count = 3,
-		.base = { 0x79000, 0x79800, 0x7a000 },
+		.base = { 0x78000, 0x78800, 0x79000 },
 	},
 	.pp = {
 		.count = 4,
-		.base = { 0x71000, 0x71800, 0x72000, 0x72800 },
+		.base = { 0x70000, 0x70800, 0x71000, 0x71800 },
 	},
 	.intf = {
-		.base = { 0x6b000, 0x6b800, 0x6c000, 0x6c800, 0x6d000 },
+		.base = { 0x6a000, 0x6a800, 0x6b000, 0x6b800, 0x6c000 },
 		.connect = {
 			[0] = INTF_DISABLED,
 			[1] = INTF_DSI,
@@ -387,19 +383,18 @@ const struct mdp5_cfg_hw msm8x96_config = {
 	.name = "msm8x96",
 	.mdp = {
 		.count = 1,
-		.base = { 0x01000 },
 		.caps = MDP_CAP_DSC |
 			MDP_CAP_CDM |
 			0,
 	},
 	.ctl = {
 		.count = 5,
-		.base = { 0x02000, 0x02200, 0x02400, 0x02600, 0x02800 },
+		.base = { 0x01000, 0x01200, 0x01400, 0x01600, 0x01800 },
 		.flush_hw_mask = 0xf4ffffff,
 	},
 	.pipe_vig = {
 		.count = 4,
-		.base = { 0x05000, 0x07000, 0x09000, 0x0b000 },
+		.base = { 0x04000, 0x06000, 0x08000, 0x0a000 },
 		.caps = MDP_PIPE_CAP_HFLIP	|
 			MDP_PIPE_CAP_VFLIP	|
 			MDP_PIPE_CAP_SCALE	|
@@ -410,7 +405,7 @@ const struct mdp5_cfg_hw msm8x96_config = {
 	},
 	.pipe_rgb = {
 		.count = 4,
-		.base = { 0x15000, 0x17000, 0x19000, 0x1b000 },
+		.base = { 0x14000, 0x16000, 0x18000, 0x1a000 },
 		.caps = MDP_PIPE_CAP_HFLIP	|
 			MDP_PIPE_CAP_VFLIP	|
 			MDP_PIPE_CAP_SCALE	|
@@ -420,7 +415,7 @@ const struct mdp5_cfg_hw msm8x96_config = {
 	},
 	.pipe_dma = {
 		.count = 2,
-		.base = { 0x25000, 0x27000 },
+		.base = { 0x24000, 0x26000 },
 		.caps = MDP_PIPE_CAP_HFLIP	|
 			MDP_PIPE_CAP_VFLIP	|
 			MDP_PIPE_CAP_SW_PIX_EXT	|
@@ -428,33 +423,33 @@ const struct mdp5_cfg_hw msm8x96_config = {
 	},
 	.lm = {
 		.count = 6,
-		.base = { 0x45000, 0x46000, 0x47000, 0x48000, 0x49000, 0x4a000 },
+		.base = { 0x44000, 0x45000, 0x46000, 0x47000, 0x48000, 0x49000 },
 		.nb_stages = 8,
 		.max_width = 2560,
 		.max_height = 0xFFFF,
 	},
 	.dspp = {
 		.count = 2,
-		.base = { 0x55000, 0x57000 },
+		.base = { 0x54000, 0x56000 },
 	},
 	.ad = {
 		.count = 3,
-		.base = { 0x79000, 0x79800, 0x7a000 },
+		.base = { 0x78000, 0x78800, 0x79000 },
 	},
 	.pp = {
 		.count = 4,
-		.base = { 0x71000, 0x71800, 0x72000, 0x72800 },
+		.base = { 0x70000, 0x70800, 0x71000, 0x71800 },
 	},
 	.cdm = {
 		.count = 1,
-		.base = { 0x7a200 },
+		.base = { 0x79200 },
 	},
 	.dsc = {
 		.count = 2,
-		.base = { 0x81000, 0x81400 },
+		.base = { 0x80000, 0x80400 },
 	},
 	.intf = {
-		.base = { 0x6b000, 0x6b800, 0x6c000, 0x6c800, 0x6d000 },
+		.base = { 0x6a000, 0x6a800, 0x6b000, 0x6b800, 0x6c000 },
 		.connect = {
 			[0] = INTF_DISABLED,
 			[1] = INTF_DSI,
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cmd_encoder.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cmd_encoder.c
index 69094cb28103..c627ab6d0061 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cmd_encoder.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cmd_encoder.c
@@ -272,22 +272,22 @@ int mdp5_cmd_encoder_set_split_display(struct drm_encoder *encoder,
 	 * start signal for the slave encoder
 	 */
 	if (intf_num == 1)
-		data |= MDP5_MDP_SPLIT_DPL_UPPER_INTF2_SW_TRG_MUX;
+		data |= MDP5_SPLIT_DPL_UPPER_INTF2_SW_TRG_MUX;
 	else if (intf_num == 2)
-		data |= MDP5_MDP_SPLIT_DPL_UPPER_INTF1_SW_TRG_MUX;
+		data |= MDP5_SPLIT_DPL_UPPER_INTF1_SW_TRG_MUX;
 	else
 		return -EINVAL;
 
 	/* Smart Panel, Sync mode */
-	data |= MDP5_MDP_SPLIT_DPL_UPPER_SMART_PANEL;
+	data |= MDP5_SPLIT_DPL_UPPER_SMART_PANEL;
 
 	/* Make sure clocks are on when connectors calling this function. */
 	mdp5_enable(mdp5_kms);
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_SPLIT_DPL_UPPER(0), data);
+	mdp5_write(mdp5_kms, REG_MDP5_SPLIT_DPL_UPPER, data);
 
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_SPLIT_DPL_LOWER(0),
-			MDP5_MDP_SPLIT_DPL_LOWER_SMART_PANEL);
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_SPLIT_DPL_EN(0), 1);
+	mdp5_write(mdp5_kms, REG_MDP5_SPLIT_DPL_LOWER,
+		   MDP5_SPLIT_DPL_LOWER_SMART_PANEL);
+	mdp5_write(mdp5_kms, REG_MDP5_SPLIT_DPL_EN, 1);
 	mdp5_disable(mdp5_kms);
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
index 88fe256c1931..fa2be7ce9468 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
@@ -374,6 +374,7 @@ static int mdp5_crtc_atomic_check(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct plane_state pstates[STAGE_MAX + 1];
 	const struct mdp5_cfg_hw *hw_cfg;
+	const struct drm_plane_state *pstate;
 	int cnt = 0, i;
 
 	DBG("%s: check", mdp5_crtc->name);
@@ -382,20 +383,13 @@ static int mdp5_crtc_atomic_check(struct drm_crtc *crtc,
 	 * and that we don't have conflicting mixer stages:
 	 */
 	hw_cfg = mdp5_cfg_get_hw_config(mdp5_kms->cfg);
-	drm_atomic_crtc_state_for_each_plane(plane, state) {
-		struct drm_plane_state *pstate;
+	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, state) {
 		if (cnt >= (hw_cfg->lm.nb_stages)) {
 			dev_err(dev->dev, "too many planes!\n");
 			return -EINVAL;
 		}
 
-		pstate = state->state->plane_states[drm_plane_index(plane)];
 
-		/* plane might not have changed, in which case take
-		 * current state:
-		 */
-		if (!pstate)
-			pstate = plane->state;
 		pstates[cnt].plane = plane;
 		pstates[cnt].state = to_mdp5_plane_state(pstate);
 
@@ -496,8 +490,7 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc,
 	struct mdp5_kms *mdp5_kms = get_kms(crtc);
 	struct drm_gem_object *cursor_bo, *old_bo = NULL;
 	uint32_t blendcfg, cursor_addr, stride;
-	int ret, bpp, lm;
-	unsigned int depth;
+	int ret, lm;
 	enum mdp5_cursor_alpha cur_alpha = CURSOR_ALPHA_PER_PIXEL;
 	uint32_t flush_mask = mdp_ctl_flush_mask_cursor(0);
 	uint32_t roi_w, roi_h;
@@ -527,8 +520,7 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc,
 		return -EINVAL;
 
 	lm = mdp5_crtc->lm;
-	drm_fb_get_bpp_depth(DRM_FORMAT_ARGB8888, &depth, &bpp);
-	stride = width * (bpp >> 3);
+	stride = width * drm_format_plane_cpp(DRM_FORMAT_ARGB8888, 0);
 
 	spin_lock_irqsave(&mdp5_crtc->cursor.lock, flags);
 	old_bo = mdp5_crtc->cursor.scanout_bo;
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_ctl.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_ctl.c
index 4e81ca4f964a..d021edc3b307 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_ctl.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_ctl.c
@@ -118,31 +118,31 @@ static void set_display_intf(struct mdp5_kms *mdp5_kms,
 	u32 intf_sel;
 
 	spin_lock_irqsave(&mdp5_kms->resource_lock, flags);
-	intf_sel = mdp5_read(mdp5_kms, REG_MDP5_MDP_DISP_INTF_SEL(0));
+	intf_sel = mdp5_read(mdp5_kms, REG_MDP5_DISP_INTF_SEL);
 
 	switch (intf->num) {
 	case 0:
-		intf_sel &= ~MDP5_MDP_DISP_INTF_SEL_INTF0__MASK;
-		intf_sel |= MDP5_MDP_DISP_INTF_SEL_INTF0(intf->type);
+		intf_sel &= ~MDP5_DISP_INTF_SEL_INTF0__MASK;
+		intf_sel |= MDP5_DISP_INTF_SEL_INTF0(intf->type);
 		break;
 	case 1:
-		intf_sel &= ~MDP5_MDP_DISP_INTF_SEL_INTF1__MASK;
-		intf_sel |= MDP5_MDP_DISP_INTF_SEL_INTF1(intf->type);
+		intf_sel &= ~MDP5_DISP_INTF_SEL_INTF1__MASK;
+		intf_sel |= MDP5_DISP_INTF_SEL_INTF1(intf->type);
 		break;
 	case 2:
-		intf_sel &= ~MDP5_MDP_DISP_INTF_SEL_INTF2__MASK;
-		intf_sel |= MDP5_MDP_DISP_INTF_SEL_INTF2(intf->type);
+		intf_sel &= ~MDP5_DISP_INTF_SEL_INTF2__MASK;
+		intf_sel |= MDP5_DISP_INTF_SEL_INTF2(intf->type);
 		break;
 	case 3:
-		intf_sel &= ~MDP5_MDP_DISP_INTF_SEL_INTF3__MASK;
-		intf_sel |= MDP5_MDP_DISP_INTF_SEL_INTF3(intf->type);
+		intf_sel &= ~MDP5_DISP_INTF_SEL_INTF3__MASK;
+		intf_sel |= MDP5_DISP_INTF_SEL_INTF3(intf->type);
 		break;
 	default:
 		BUG();
 		break;
 	}
 
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_DISP_INTF_SEL(0), intf_sel);
+	mdp5_write(mdp5_kms, REG_MDP5_DISP_INTF_SEL, intf_sel);
 	spin_unlock_irqrestore(&mdp5_kms->resource_lock, flags);
 }
 
@@ -557,7 +557,7 @@ int mdp5_ctl_pair(struct mdp5_ctl *ctlx, struct mdp5_ctl *ctly, bool enable)
 	if (!enable) {
 		ctlx->pair = NULL;
 		ctly->pair = NULL;
-		mdp5_write(mdp5_kms, REG_MDP5_MDP_SPARE_0(0), 0);
+		mdp5_write(mdp5_kms, REG_MDP5_SPARE_0, 0);
 		return 0;
 	} else if ((ctlx->pair != NULL) || (ctly->pair != NULL)) {
 		dev_err(ctl_mgr->dev->dev, "CTLs already paired\n");
@@ -570,8 +570,8 @@ int mdp5_ctl_pair(struct mdp5_ctl *ctlx, struct mdp5_ctl *ctly, bool enable)
 	ctlx->pair = ctly;
 	ctly->pair = ctlx;
 
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_SPARE_0(0),
-		MDP5_MDP_SPARE_0_SPLIT_DPL_SINGLE_FLUSH_EN);
+	mdp5_write(mdp5_kms, REG_MDP5_SPARE_0,
+		   MDP5_SPARE_0_SPLIT_DPL_SINGLE_FLUSH_EN);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c
index 1d95f9fd9dc7..fe0c22230883 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c
@@ -322,18 +322,18 @@ int mdp5_encoder_set_split_display(struct drm_encoder *encoder,
 	 * to use the master's enable signal for the slave encoder.
 	 */
 	if (intf_num == 1)
-		data |= MDP5_MDP_SPLIT_DPL_LOWER_INTF2_TG_SYNC;
+		data |= MDP5_SPLIT_DPL_LOWER_INTF2_TG_SYNC;
 	else if (intf_num == 2)
-		data |= MDP5_MDP_SPLIT_DPL_LOWER_INTF1_TG_SYNC;
+		data |= MDP5_SPLIT_DPL_LOWER_INTF1_TG_SYNC;
 	else
 		return -EINVAL;
 
 	/* Make sure clocks are on when connectors calling this function. */
 	mdp5_enable(mdp5_kms);
 	/* Dumb Panel, Sync mode */
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_SPLIT_DPL_UPPER(0), 0);
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_SPLIT_DPL_LOWER(0), data);
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_SPLIT_DPL_EN(0), 1);
+	mdp5_write(mdp5_kms, REG_MDP5_SPLIT_DPL_UPPER, 0);
+	mdp5_write(mdp5_kms, REG_MDP5_SPLIT_DPL_LOWER, data);
+	mdp5_write(mdp5_kms, REG_MDP5_SPLIT_DPL_EN, 1);
 
 	mdp5_ctl_pair(mdp5_encoder->ctl, mdp5_slave_enc->ctl, true);
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
index 73bc3e312fd4..d53e5510fd7c 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
@@ -15,7 +15,6 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <linux/irqdomain.h>
 #include <linux/irq.h>
 
 #include "msm_drv.h"
@@ -24,9 +23,9 @@
 void mdp5_set_irqmask(struct mdp_kms *mdp_kms, uint32_t irqmask,
 		uint32_t old_irqmask)
 {
-	mdp5_write(to_mdp5_kms(mdp_kms), REG_MDP5_MDP_INTR_CLEAR(0),
-		irqmask ^ (irqmask & old_irqmask));
-	mdp5_write(to_mdp5_kms(mdp_kms), REG_MDP5_MDP_INTR_EN(0), irqmask);
+	mdp5_write(to_mdp5_kms(mdp_kms), REG_MDP5_INTR_CLEAR,
+		   irqmask ^ (irqmask & old_irqmask));
+	mdp5_write(to_mdp5_kms(mdp_kms), REG_MDP5_INTR_EN, irqmask);
 }
 
 static void mdp5_irq_error_handler(struct mdp_irq *irq, uint32_t irqstatus)
@@ -38,8 +37,8 @@ void mdp5_irq_preinstall(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
 	mdp5_enable(mdp5_kms);
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_INTR_CLEAR(0), 0xffffffff);
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_INTR_EN(0), 0x00000000);
+	mdp5_write(mdp5_kms, REG_MDP5_INTR_CLEAR, 0xffffffff);
+	mdp5_write(mdp5_kms, REG_MDP5_INTR_EN, 0x00000000);
 	mdp5_disable(mdp5_kms);
 }
 
@@ -55,7 +54,9 @@ int mdp5_irq_postinstall(struct msm_kms *kms)
 			MDP5_IRQ_INTF2_UNDER_RUN |
 			MDP5_IRQ_INTF3_UNDER_RUN;
 
+	mdp5_enable(mdp5_kms);
 	mdp_irq_register(mdp_kms, error_handler);
+	mdp5_disable(mdp5_kms);
 
 	return 0;
 }
@@ -64,21 +65,22 @@ void mdp5_irq_uninstall(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
 	mdp5_enable(mdp5_kms);
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_INTR_EN(0), 0x00000000);
+	mdp5_write(mdp5_kms, REG_MDP5_INTR_EN, 0x00000000);
 	mdp5_disable(mdp5_kms);
 }
 
-static void mdp5_irq_mdp(struct mdp_kms *mdp_kms)
+irqreturn_t mdp5_irq(struct msm_kms *kms)
 {
+	struct mdp_kms *mdp_kms = to_mdp_kms(kms);
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(mdp_kms);
 	struct drm_device *dev = mdp5_kms->dev;
 	struct msm_drm_private *priv = dev->dev_private;
 	unsigned int id;
 	uint32_t status, enable;
 
-	enable = mdp5_read(mdp5_kms, REG_MDP5_MDP_INTR_EN(0));
-	status = mdp5_read(mdp5_kms, REG_MDP5_MDP_INTR_STATUS(0)) & enable;
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_INTR_CLEAR(0), status);
+	enable = mdp5_read(mdp5_kms, REG_MDP5_INTR_EN);
+	status = mdp5_read(mdp5_kms, REG_MDP5_INTR_STATUS) & enable;
+	mdp5_write(mdp5_kms, REG_MDP5_INTR_CLEAR, status);
 
 	VERB("status=%08x", status);
 
@@ -87,29 +89,6 @@ static void mdp5_irq_mdp(struct mdp_kms *mdp_kms)
 	for (id = 0; id < priv->num_crtcs; id++)
 		if (status & mdp5_crtc_vblank(priv->crtcs[id]))
 			drm_handle_vblank(dev, id);
-}
-
-irqreturn_t mdp5_irq(struct msm_kms *kms)
-{
-	struct mdp_kms *mdp_kms = to_mdp_kms(kms);
-	struct mdp5_kms *mdp5_kms = to_mdp5_kms(mdp_kms);
-	uint32_t intr;
-
-	intr = mdp5_read(mdp5_kms, REG_MDSS_HW_INTR_STATUS);
-
-	VERB("intr=%08x", intr);
-
-	if (intr & MDSS_HW_INTR_STATUS_INTR_MDP) {
-		mdp5_irq_mdp(mdp_kms);
-		intr &= ~MDSS_HW_INTR_STATUS_INTR_MDP;
-	}
-
-	while (intr) {
-		irq_hw_number_t hwirq = fls(intr) - 1;
-		generic_handle_irq(irq_find_mapping(
-				mdp5_kms->irqcontroller.domain, hwirq));
-		intr &= ~(1 << hwirq);
-	}
 
 	return IRQ_HANDLED;
 }
@@ -135,81 +114,3 @@ void mdp5_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
 			mdp5_crtc_vblank(crtc), false);
 	mdp5_disable(mdp5_kms);
 }
-
-/*
- * interrupt-controller implementation, so sub-blocks (hdmi/eDP/dsi/etc)
- * can register to get their irq's delivered
- */
-
-#define VALID_IRQS  (MDSS_HW_INTR_STATUS_INTR_DSI0 | \
-		MDSS_HW_INTR_STATUS_INTR_DSI1 | \
-		MDSS_HW_INTR_STATUS_INTR_HDMI | \
-		MDSS_HW_INTR_STATUS_INTR_EDP)
-
-static void mdp5_hw_mask_irq(struct irq_data *irqd)
-{
-	struct mdp5_kms *mdp5_kms = irq_data_get_irq_chip_data(irqd);
-	smp_mb__before_atomic();
-	clear_bit(irqd->hwirq, &mdp5_kms->irqcontroller.enabled_mask);
-	smp_mb__after_atomic();
-}
-
-static void mdp5_hw_unmask_irq(struct irq_data *irqd)
-{
-	struct mdp5_kms *mdp5_kms = irq_data_get_irq_chip_data(irqd);
-	smp_mb__before_atomic();
-	set_bit(irqd->hwirq, &mdp5_kms->irqcontroller.enabled_mask);
-	smp_mb__after_atomic();
-}
-
-static struct irq_chip mdp5_hw_irq_chip = {
-	.name		= "mdp5",
-	.irq_mask	= mdp5_hw_mask_irq,
-	.irq_unmask	= mdp5_hw_unmask_irq,
-};
-
-static int mdp5_hw_irqdomain_map(struct irq_domain *d,
-		unsigned int irq, irq_hw_number_t hwirq)
-{
-	struct mdp5_kms *mdp5_kms = d->host_data;
-
-	if (!(VALID_IRQS & (1 << hwirq)))
-		return -EPERM;
-
-	irq_set_chip_and_handler(irq, &mdp5_hw_irq_chip, handle_level_irq);
-	irq_set_chip_data(irq, mdp5_kms);
-
-	return 0;
-}
-
-static struct irq_domain_ops mdp5_hw_irqdomain_ops = {
-	.map = mdp5_hw_irqdomain_map,
-	.xlate = irq_domain_xlate_onecell,
-};
-
-
-int mdp5_irq_domain_init(struct mdp5_kms *mdp5_kms)
-{
-	struct device *dev = mdp5_kms->dev->dev;
-	struct irq_domain *d;
-
-	d = irq_domain_add_linear(dev->of_node, 32,
-			&mdp5_hw_irqdomain_ops, mdp5_kms);
-	if (!d) {
-		dev_err(dev, "mdp5 irq domain add failed\n");
-		return -ENXIO;
-	}
-
-	mdp5_kms->irqcontroller.enabled_mask = 0;
-	mdp5_kms->irqcontroller.domain = d;
-
-	return 0;
-}
-
-void mdp5_irq_domain_fini(struct mdp5_kms *mdp5_kms)
-{
-	if (mdp5_kms->irqcontroller.domain) {
-		irq_domain_remove(mdp5_kms->irqcontroller.domain);
-		mdp5_kms->irqcontroller.domain = NULL;
-	}
-}
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index 484b4d15e71d..ed7143d35b25 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -16,6 +16,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/of_irq.h>
 
 #include "msm_drv.h"
 #include "msm_mmu.h"
@@ -28,10 +29,11 @@ static const char *iommu_ports[] = {
 static int mdp5_hw_init(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
-	struct drm_device *dev = mdp5_kms->dev;
+	struct platform_device *pdev = mdp5_kms->pdev;
 	unsigned long flags;
 
-	pm_runtime_get_sync(dev->dev);
+	pm_runtime_get_sync(&pdev->dev);
+	mdp5_enable(mdp5_kms);
 
 	/* Magic unknown register writes:
 	 *
@@ -58,12 +60,13 @@ static int mdp5_hw_init(struct msm_kms *kms)
 	 */
 
 	spin_lock_irqsave(&mdp5_kms->resource_lock, flags);
-	mdp5_write(mdp5_kms, REG_MDP5_MDP_DISP_INTF_SEL(0), 0);
+	mdp5_write(mdp5_kms, REG_MDP5_DISP_INTF_SEL, 0);
 	spin_unlock_irqrestore(&mdp5_kms->resource_lock, flags);
 
 	mdp5_ctlm_hw_reset(mdp5_kms->ctlm);
 
-	pm_runtime_put_sync(dev->dev);
+	mdp5_disable(mdp5_kms);
+	pm_runtime_put_sync(&pdev->dev);
 
 	return 0;
 }
@@ -78,17 +81,11 @@ static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *s
 {
 	int i;
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
-	int nplanes = mdp5_kms->dev->mode_config.num_total_plane;
-
-	for (i = 0; i < nplanes; i++) {
-		struct drm_plane *plane = state->planes[i];
-		struct drm_plane_state *plane_state = state->plane_states[i];
-
-		if (!plane)
-			continue;
+	struct drm_plane *plane;
+	struct drm_plane_state *plane_state;
 
+	for_each_plane_in_state(state, plane, plane_state, i)
 		mdp5_plane_complete_commit(plane, plane_state);
-	}
 
 	mdp5_disable(mdp5_kms);
 }
@@ -117,26 +114,15 @@ static int mdp5_set_split_display(struct msm_kms *kms,
 		return mdp5_encoder_set_split_display(encoder, slave_encoder);
 }
 
-static void mdp5_destroy(struct msm_kms *kms)
+static void mdp5_kms_destroy(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
 	struct msm_mmu *mmu = mdp5_kms->mmu;
 
-	mdp5_irq_domain_fini(mdp5_kms);
-
 	if (mmu) {
 		mmu->funcs->detach(mmu, iommu_ports, ARRAY_SIZE(iommu_ports));
 		mmu->funcs->destroy(mmu);
 	}
-
-	if (mdp5_kms->ctlm)
-		mdp5_ctlm_destroy(mdp5_kms->ctlm);
-	if (mdp5_kms->smp)
-		mdp5_smp_destroy(mdp5_kms->smp);
-	if (mdp5_kms->cfg)
-		mdp5_cfg_destroy(mdp5_kms->cfg);
-
-	kfree(mdp5_kms);
 }
 
 static const struct mdp_kms_funcs kms_funcs = {
@@ -154,7 +140,7 @@ static const struct mdp_kms_funcs kms_funcs = {
 		.get_format      = mdp_get_format,
 		.round_pixclk    = mdp5_round_pixclk,
 		.set_split_display = mdp5_set_split_display,
-		.destroy         = mdp5_destroy,
+		.destroy         = mdp5_kms_destroy,
 	},
 	.set_irqmask         = mdp5_set_irqmask,
 };
@@ -351,13 +337,6 @@ static int modeset_init(struct mdp5_kms *mdp5_kms)
 
 	hw_cfg = mdp5_cfg_get_hw_config(mdp5_kms->cfg);
 
-	/* register our interrupt-controller for hdmi/eDP/dsi/etc
-	 * to use for irqs routed through mdp:
-	 */
-	ret = mdp5_irq_domain_init(mdp5_kms);
-	if (ret)
-		goto fail;
-
 	/* construct CRTCs and their private planes: */
 	for (i = 0; i < hw_cfg->pipe_rgb.count; i++) {
 		struct drm_plane *plane;
@@ -425,17 +404,17 @@ fail:
 	return ret;
 }
 
-static void read_hw_revision(struct mdp5_kms *mdp5_kms,
-		uint32_t *major, uint32_t *minor)
+static void read_mdp_hw_revision(struct mdp5_kms *mdp5_kms,
+				 u32 *major, u32 *minor)
 {
-	uint32_t version;
+	u32 version;
 
 	mdp5_enable(mdp5_kms);
-	version = mdp5_read(mdp5_kms, REG_MDSS_HW_VERSION);
+	version = mdp5_read(mdp5_kms, REG_MDP5_HW_VERSION);
 	mdp5_disable(mdp5_kms);
 
-	*major = FIELD(version, MDSS_HW_VERSION_MAJOR);
-	*minor = FIELD(version, MDSS_HW_VERSION_MINOR);
+	*major = FIELD(version, MDP5_HW_VERSION_MAJOR);
+	*minor = FIELD(version, MDP5_HW_VERSION_MINOR);
 
 	DBG("MDP5 version v%d.%d", *major, *minor);
 }
@@ -580,51 +559,146 @@ static u32 mdp5_get_vblank_counter(struct drm_device *dev, unsigned int pipe)
 
 struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 {
-	struct platform_device *pdev = dev->platformdev;
-	struct mdp5_cfg *config;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct platform_device *pdev;
 	struct mdp5_kms *mdp5_kms;
-	struct msm_kms *kms = NULL;
+	struct mdp5_cfg *config;
+	struct msm_kms *kms;
 	struct msm_mmu *mmu;
-	uint32_t major, minor;
-	int i, ret;
+	int irq, i, ret;
 
-	mdp5_kms = kzalloc(sizeof(*mdp5_kms), GFP_KERNEL);
-	if (!mdp5_kms) {
-		dev_err(dev->dev, "failed to allocate kms\n");
-		ret = -ENOMEM;
+	/* priv->kms would have been populated by the MDP5 driver */
+	kms = priv->kms;
+	if (!kms)
+		return NULL;
+
+	mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
+
+	mdp_kms_init(&mdp5_kms->base, &kms_funcs);
+
+	pdev = mdp5_kms->pdev;
+
+	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+	if (irq < 0) {
+		ret = irq;
+		dev_err(&pdev->dev, "failed to get irq: %d\n", ret);
 		goto fail;
 	}
 
-	spin_lock_init(&mdp5_kms->resource_lock);
+	kms->irq = irq;
 
-	mdp_kms_init(&mdp5_kms->base, &kms_funcs);
+	config = mdp5_cfg_get_config(mdp5_kms->cfg);
 
-	kms = &mdp5_kms->base.base;
+	/* make sure things are off before attaching iommu (bootloader could
+	 * have left things on, in which case we'll start getting faults if
+	 * we don't disable):
+	 */
+	mdp5_enable(mdp5_kms);
+	for (i = 0; i < MDP5_INTF_NUM_MAX; i++) {
+		if (mdp5_cfg_intf_is_virtual(config->hw->intf.connect[i]) ||
+		    !config->hw->intf.base[i])
+			continue;
+		mdp5_write(mdp5_kms, REG_MDP5_INTF_TIMING_ENGINE_EN(i), 0);
 
-	mdp5_kms->dev = dev;
+		mdp5_write(mdp5_kms, REG_MDP5_INTF_FRAME_LINE_COUNT_EN(i), 0x3);
+	}
+	mdp5_disable(mdp5_kms);
+	mdelay(16);
 
-	/* mdp5_kms->mmio actually represents the MDSS base address */
-	mdp5_kms->mmio = msm_ioremap(pdev, "mdp_phys", "MDP5");
-	if (IS_ERR(mdp5_kms->mmio)) {
-		ret = PTR_ERR(mdp5_kms->mmio);
+	if (config->platform.iommu) {
+		mmu = msm_iommu_new(&pdev->dev, config->platform.iommu);
+		if (IS_ERR(mmu)) {
+			ret = PTR_ERR(mmu);
+			dev_err(&pdev->dev, "failed to init iommu: %d\n", ret);
+			iommu_domain_free(config->platform.iommu);
+			goto fail;
+		}
+
+		ret = mmu->funcs->attach(mmu, iommu_ports,
+				ARRAY_SIZE(iommu_ports));
+		if (ret) {
+			dev_err(&pdev->dev, "failed to attach iommu: %d\n",
+				ret);
+			mmu->funcs->destroy(mmu);
+			goto fail;
+		}
+	} else {
+		dev_info(&pdev->dev,
+			 "no iommu, fallback to phys contig buffers for scanout\n");
+		mmu = NULL;
+	}
+	mdp5_kms->mmu = mmu;
+
+	mdp5_kms->id = msm_register_mmu(dev, mmu);
+	if (mdp5_kms->id < 0) {
+		ret = mdp5_kms->id;
+		dev_err(&pdev->dev, "failed to register mdp5 iommu: %d\n", ret);
 		goto fail;
 	}
 
-	mdp5_kms->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF");
-	if (IS_ERR(mdp5_kms->vbif)) {
-		ret = PTR_ERR(mdp5_kms->vbif);
+	ret = modeset_init(mdp5_kms);
+	if (ret) {
+		dev_err(&pdev->dev, "modeset_init failed: %d\n", ret);
 		goto fail;
 	}
 
-	mdp5_kms->vdd = devm_regulator_get(&pdev->dev, "vdd");
-	if (IS_ERR(mdp5_kms->vdd)) {
-		ret = PTR_ERR(mdp5_kms->vdd);
+	dev->mode_config.min_width = 0;
+	dev->mode_config.min_height = 0;
+	dev->mode_config.max_width = config->hw->lm.max_width;
+	dev->mode_config.max_height = config->hw->lm.max_height;
+
+	dev->driver->get_vblank_timestamp = mdp5_get_vblank_timestamp;
+	dev->driver->get_scanout_position = mdp5_get_scanoutpos;
+	dev->driver->get_vblank_counter = mdp5_get_vblank_counter;
+	dev->max_vblank_count = 0xffffffff;
+	dev->vblank_disable_immediate = true;
+
+	return kms;
+fail:
+	if (kms)
+		mdp5_kms_destroy(kms);
+	return ERR_PTR(ret);
+}
+
+static void mdp5_destroy(struct platform_device *pdev)
+{
+	struct mdp5_kms *mdp5_kms = platform_get_drvdata(pdev);
+
+	if (mdp5_kms->ctlm)
+		mdp5_ctlm_destroy(mdp5_kms->ctlm);
+	if (mdp5_kms->smp)
+		mdp5_smp_destroy(mdp5_kms->smp);
+	if (mdp5_kms->cfg)
+		mdp5_cfg_destroy(mdp5_kms->cfg);
+
+	if (mdp5_kms->rpm_enabled)
+		pm_runtime_disable(&pdev->dev);
+}
+
+static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct mdp5_kms *mdp5_kms;
+	struct mdp5_cfg *config;
+	u32 major, minor;
+	int ret;
+
+	mdp5_kms = devm_kzalloc(&pdev->dev, sizeof(*mdp5_kms), GFP_KERNEL);
+	if (!mdp5_kms) {
+		ret = -ENOMEM;
 		goto fail;
 	}
 
-	ret = regulator_enable(mdp5_kms->vdd);
-	if (ret) {
-		dev_err(dev->dev, "failed to enable regulator vdd: %d\n", ret);
+	platform_set_drvdata(pdev, mdp5_kms);
+
+	spin_lock_init(&mdp5_kms->resource_lock);
+
+	mdp5_kms->dev = dev;
+	mdp5_kms->pdev = pdev;
+
+	mdp5_kms->mmio = msm_ioremap(pdev, "mdp_phys", "MDP5");
+	if (IS_ERR(mdp5_kms->mmio)) {
+		ret = PTR_ERR(mdp5_kms->mmio);
 		goto fail;
 	}
 
@@ -635,9 +709,6 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 	ret = get_clk(pdev, &mdp5_kms->ahb_clk, "iface_clk", true);
 	if (ret)
 		goto fail;
-	ret = get_clk(pdev, &mdp5_kms->src_clk, "core_clk_src", true);
-	if (ret)
-		goto fail;
 	ret = get_clk(pdev, &mdp5_kms->core_clk, "core_clk", true);
 	if (ret)
 		goto fail;
@@ -652,9 +723,12 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 	 * rate first, then figure out hw revision, and then set a
 	 * more optimal rate:
 	 */
-	clk_set_rate(mdp5_kms->src_clk, 200000000);
+	clk_set_rate(mdp5_kms->core_clk, 200000000);
 
-	read_hw_revision(mdp5_kms, &major, &minor);
+	pm_runtime_enable(&pdev->dev);
+	mdp5_kms->rpm_enabled = true;
+
+	read_mdp_hw_revision(mdp5_kms, &major, &minor);
 
 	mdp5_kms->cfg = mdp5_cfg_init(mdp5_kms, major, minor);
 	if (IS_ERR(mdp5_kms->cfg)) {
@@ -667,7 +741,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 	mdp5_kms->caps = config->hw->mdp.caps;
 
 	/* TODO: compute core clock rate at runtime */
-	clk_set_rate(mdp5_kms->src_clk, config->hw->max_clk);
+	clk_set_rate(mdp5_kms->core_clk, config->hw->max_clk);
 
 	/*
 	 * Some chipsets have a Shared Memory Pool (SMP), while others
@@ -690,73 +764,76 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 		goto fail;
 	}
 
-	/* make sure things are off before attaching iommu (bootloader could
-	 * have left things on, in which case we'll start getting faults if
-	 * we don't disable):
-	 */
-	mdp5_enable(mdp5_kms);
-	for (i = 0; i < MDP5_INTF_NUM_MAX; i++) {
-		if (mdp5_cfg_intf_is_virtual(config->hw->intf.connect[i]) ||
-				!config->hw->intf.base[i])
-			continue;
-		mdp5_write(mdp5_kms, REG_MDP5_INTF_TIMING_ENGINE_EN(i), 0);
+	/* set uninit-ed kms */
+	priv->kms = &mdp5_kms->base.base;
 
-		mdp5_write(mdp5_kms, REG_MDP5_INTF_FRAME_LINE_COUNT_EN(i), 0x3);
-	}
-	mdp5_disable(mdp5_kms);
-	mdelay(16);
+	return 0;
+fail:
+	mdp5_destroy(pdev);
+	return ret;
+}
 
-	if (config->platform.iommu) {
-		mmu = msm_iommu_new(&pdev->dev, config->platform.iommu);
-		if (IS_ERR(mmu)) {
-			ret = PTR_ERR(mmu);
-			dev_err(dev->dev, "failed to init iommu: %d\n", ret);
-			iommu_domain_free(config->platform.iommu);
-			goto fail;
-		}
+static int mdp5_bind(struct device *dev, struct device *master, void *data)
+{
+	struct drm_device *ddev = dev_get_drvdata(master);
+	struct platform_device *pdev = to_platform_device(dev);
 
-		ret = mmu->funcs->attach(mmu, iommu_ports,
-				ARRAY_SIZE(iommu_ports));
-		if (ret) {
-			dev_err(dev->dev, "failed to attach iommu: %d\n", ret);
-			mmu->funcs->destroy(mmu);
-			goto fail;
-		}
-	} else {
-		dev_info(dev->dev, "no iommu, fallback to phys "
-				"contig buffers for scanout\n");
-		mmu = NULL;
-	}
-	mdp5_kms->mmu = mmu;
+	DBG("");
 
-	mdp5_kms->id = msm_register_mmu(dev, mmu);
-	if (mdp5_kms->id < 0) {
-		ret = mdp5_kms->id;
-		dev_err(dev->dev, "failed to register mdp5 iommu: %d\n", ret);
-		goto fail;
-	}
+	return mdp5_init(pdev, ddev);
+}
 
-	ret = modeset_init(mdp5_kms);
-	if (ret) {
-		dev_err(dev->dev, "modeset_init failed: %d\n", ret);
-		goto fail;
-	}
+static void mdp5_unbind(struct device *dev, struct device *master,
+			void *data)
+{
+	struct platform_device *pdev = to_platform_device(dev);
 
-	dev->mode_config.min_width = 0;
-	dev->mode_config.min_height = 0;
-	dev->mode_config.max_width = config->hw->lm.max_width;
-	dev->mode_config.max_height = config->hw->lm.max_height;
+	mdp5_destroy(pdev);
+}
 
-	dev->driver->get_vblank_timestamp = mdp5_get_vblank_timestamp;
-	dev->driver->get_scanout_position = mdp5_get_scanoutpos;
-	dev->driver->get_vblank_counter = mdp5_get_vblank_counter;
-	dev->max_vblank_count = 0xffffffff;
-	dev->vblank_disable_immediate = true;
+static const struct component_ops mdp5_ops = {
+	.bind   = mdp5_bind,
+	.unbind = mdp5_unbind,
+};
 
-	return kms;
+static int mdp5_dev_probe(struct platform_device *pdev)
+{
+	DBG("");
+	return component_add(&pdev->dev, &mdp5_ops);
+}
 
-fail:
-	if (kms)
-		mdp5_destroy(kms);
-	return ERR_PTR(ret);
+static int mdp5_dev_remove(struct platform_device *pdev)
+{
+	DBG("");
+	component_del(&pdev->dev, &mdp5_ops);
+	return 0;
+}
+
+static const struct of_device_id mdp5_dt_match[] = {
+	{ .compatible = "qcom,mdp5", },
+	/* to support downstream DT files */
+	{ .compatible = "qcom,mdss_mdp", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mdp5_dt_match);
+
+static struct platform_driver mdp5_driver = {
+	.probe = mdp5_dev_probe,
+	.remove = mdp5_dev_remove,
+	.driver = {
+		.name = "msm_mdp",
+		.of_match_table = mdp5_dt_match,
+	},
+};
+
+void __init msm_mdp_register(void)
+{
+	DBG("");
+	platform_driver_register(&mdp5_driver);
+}
+
+void __exit msm_mdp_unregister(void)
+{
+	DBG("");
+	platform_driver_unregister(&mdp5_driver);
 }
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
index 9a25898239d3..03738927be10 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
@@ -31,6 +31,8 @@ struct mdp5_kms {
 
 	struct drm_device *dev;
 
+	struct platform_device *pdev;
+
 	struct mdp5_cfg_handler *cfg;
 	uint32_t caps;	/* MDP capabilities (MDP_CAP_XXX bits) */
 
@@ -43,29 +45,23 @@ struct mdp5_kms {
 	struct mdp5_ctl_manager *ctlm;
 
 	/* io/register spaces: */
-	void __iomem *mmio, *vbif;
-
-	struct regulator *vdd;
+	void __iomem *mmio;
 
 	struct clk *axi_clk;
 	struct clk *ahb_clk;
-	struct clk *src_clk;
 	struct clk *core_clk;
 	struct clk *lut_clk;
 	struct clk *vsync_clk;
 
 	/*
 	 * lock to protect access to global resources: ie., following register:
-	 *	- REG_MDP5_MDP_DISP_INTF_SEL
+	 *	- REG_MDP5_DISP_INTF_SEL
 	 */
 	spinlock_t resource_lock;
 
-	struct mdp_irq error_handler;
+	bool rpm_enabled;
 
-	struct {
-		volatile unsigned long enabled_mask;
-		struct irq_domain *domain;
-	} irqcontroller;
+	struct mdp_irq error_handler;
 };
 #define to_mdp5_kms(x) container_of(x, struct mdp5_kms, base)
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_mdss.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_mdss.c
new file mode 100644
index 000000000000..d444a6901fff
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_mdss.c
@@ -0,0 +1,235 @@
+/*
+ * Copyright (c) 2016, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+
+#include "msm_drv.h"
+#include "mdp5_kms.h"
+
+/*
+ * If needed, this can become more specific: something like struct mdp5_mdss,
+ * which contains a 'struct msm_mdss base' member.
+ */
+struct msm_mdss {
+	struct drm_device *dev;
+
+	void __iomem *mmio, *vbif;
+
+	struct regulator *vdd;
+
+	struct {
+		volatile unsigned long enabled_mask;
+		struct irq_domain *domain;
+	} irqcontroller;
+};
+
+static inline void mdss_write(struct msm_mdss *mdss, u32 reg, u32 data)
+{
+	msm_writel(data, mdss->mmio + reg);
+}
+
+static inline u32 mdss_read(struct msm_mdss *mdss, u32 reg)
+{
+	return msm_readl(mdss->mmio + reg);
+}
+
+static irqreturn_t mdss_irq(int irq, void *arg)
+{
+	struct msm_mdss *mdss = arg;
+	u32 intr;
+
+	intr = mdss_read(mdss, REG_MDSS_HW_INTR_STATUS);
+
+	VERB("intr=%08x", intr);
+
+	while (intr) {
+		irq_hw_number_t hwirq = fls(intr) - 1;
+
+		generic_handle_irq(irq_find_mapping(
+				mdss->irqcontroller.domain, hwirq));
+		intr &= ~(1 << hwirq);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * interrupt-controller implementation, so sub-blocks (MDP/HDMI/eDP/DSI/etc)
+ * can register to get their irq's delivered
+ */
+
+#define VALID_IRQS  (MDSS_HW_INTR_STATUS_INTR_MDP | \
+		MDSS_HW_INTR_STATUS_INTR_DSI0 | \
+		MDSS_HW_INTR_STATUS_INTR_DSI1 | \
+		MDSS_HW_INTR_STATUS_INTR_HDMI | \
+		MDSS_HW_INTR_STATUS_INTR_EDP)
+
+static void mdss_hw_mask_irq(struct irq_data *irqd)
+{
+	struct msm_mdss *mdss = irq_data_get_irq_chip_data(irqd);
+
+	smp_mb__before_atomic();
+	clear_bit(irqd->hwirq, &mdss->irqcontroller.enabled_mask);
+	smp_mb__after_atomic();
+}
+
+static void mdss_hw_unmask_irq(struct irq_data *irqd)
+{
+	struct msm_mdss *mdss = irq_data_get_irq_chip_data(irqd);
+
+	smp_mb__before_atomic();
+	set_bit(irqd->hwirq, &mdss->irqcontroller.enabled_mask);
+	smp_mb__after_atomic();
+}
+
+static struct irq_chip mdss_hw_irq_chip = {
+	.name		= "mdss",
+	.irq_mask	= mdss_hw_mask_irq,
+	.irq_unmask	= mdss_hw_unmask_irq,
+};
+
+static int mdss_hw_irqdomain_map(struct irq_domain *d, unsigned int irq,
+				 irq_hw_number_t hwirq)
+{
+	struct msm_mdss *mdss = d->host_data;
+
+	if (!(VALID_IRQS & (1 << hwirq)))
+		return -EPERM;
+
+	irq_set_chip_and_handler(irq, &mdss_hw_irq_chip, handle_level_irq);
+	irq_set_chip_data(irq, mdss);
+
+	return 0;
+}
+
+static struct irq_domain_ops mdss_hw_irqdomain_ops = {
+	.map = mdss_hw_irqdomain_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+
+static int mdss_irq_domain_init(struct msm_mdss *mdss)
+{
+	struct device *dev = mdss->dev->dev;
+	struct irq_domain *d;
+
+	d = irq_domain_add_linear(dev->of_node, 32, &mdss_hw_irqdomain_ops,
+				  mdss);
+	if (!d) {
+		dev_err(dev, "mdss irq domain add failed\n");
+		return -ENXIO;
+	}
+
+	mdss->irqcontroller.enabled_mask = 0;
+	mdss->irqcontroller.domain = d;
+
+	return 0;
+}
+
+void msm_mdss_destroy(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_mdss *mdss = priv->mdss;
+
+	if (!mdss)
+		return;
+
+	irq_domain_remove(mdss->irqcontroller.domain);
+	mdss->irqcontroller.domain = NULL;
+
+	regulator_disable(mdss->vdd);
+
+	pm_runtime_put_sync(dev->dev);
+
+	pm_runtime_disable(dev->dev);
+}
+
+int msm_mdss_init(struct drm_device *dev)
+{
+	struct platform_device *pdev = dev->platformdev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_mdss *mdss;
+	int ret;
+
+	DBG("");
+
+	if (!of_device_is_compatible(dev->dev->of_node, "qcom,mdss"))
+		return 0;
+
+	mdss = devm_kzalloc(dev->dev, sizeof(*mdss), GFP_KERNEL);
+	if (!mdss) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	mdss->dev = dev;
+
+	mdss->mmio = msm_ioremap(pdev, "mdss_phys", "MDSS");
+	if (IS_ERR(mdss->mmio)) {
+		ret = PTR_ERR(mdss->mmio);
+		goto fail;
+	}
+
+	mdss->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF");
+	if (IS_ERR(mdss->vbif)) {
+		ret = PTR_ERR(mdss->vbif);
+		goto fail;
+	}
+
+	/* Regulator to enable GDSCs in downstream kernels */
+	mdss->vdd = devm_regulator_get(dev->dev, "vdd");
+	if (IS_ERR(mdss->vdd)) {
+		ret = PTR_ERR(mdss->vdd);
+		goto fail;
+	}
+
+	ret = regulator_enable(mdss->vdd);
+	if (ret) {
+		dev_err(dev->dev, "failed to enable regulator vdd: %d\n",
+			ret);
+		goto fail;
+	}
+
+	ret = devm_request_irq(dev->dev, platform_get_irq(pdev, 0),
+			       mdss_irq, 0, "mdss_isr", mdss);
+	if (ret) {
+		dev_err(dev->dev, "failed to init irq: %d\n", ret);
+		goto fail_irq;
+	}
+
+	ret = mdss_irq_domain_init(mdss);
+	if (ret) {
+		dev_err(dev->dev, "failed to init sub-block irqs: %d\n", ret);
+		goto fail_irq;
+	}
+
+	priv->mdss = mdss;
+
+	pm_runtime_enable(dev->dev);
+
+	/*
+	 * TODO: This is needed as the MDSS GDSC is only tied to MDSS's power
+	 * domain. Remove this once runtime PM is adapted for all the devices.
+	 */
+	pm_runtime_get_sync(dev->dev);
+
+	return 0;
+fail_irq:
+	regulator_disable(mdss->vdd);
+fail:
+	return ret;
+}
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
index 6f425c25d9fe..27d7b55b52c9 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
@@ -42,7 +42,7 @@
  *
  *     configured:
  *     The block is allocated to some client, and assigned to that
- *     client in MDP5_MDP_SMP_ALLOC registers.
+ *     client in MDP5_SMP_ALLOC registers.
  *
  *     inuse:
  *     The block is being actively used by a client.
@@ -59,7 +59,7 @@
  *     mdp5_smp_commit.
  *
  *  2) mdp5_smp_configure():
- *     As hw is programmed, before FLUSH, MDP5_MDP_SMP_ALLOC registers
+ *     As hw is programmed, before FLUSH, MDP5_SMP_ALLOC registers
  *     are configured for the union(pending, inuse)
  *     Current pending is copied to configured.
  *     It is assumed that mdp5_smp_request and mdp5_smp_configure not run
@@ -311,25 +311,25 @@ static void update_smp_state(struct mdp5_smp *smp,
 		int idx = blk / 3;
 		int fld = blk % 3;
 
-		val = mdp5_read(mdp5_kms, REG_MDP5_MDP_SMP_ALLOC_W_REG(0, idx));
+		val = mdp5_read(mdp5_kms, REG_MDP5_SMP_ALLOC_W_REG(idx));
 
 		switch (fld) {
 		case 0:
-			val &= ~MDP5_MDP_SMP_ALLOC_W_REG_CLIENT0__MASK;
-			val |= MDP5_MDP_SMP_ALLOC_W_REG_CLIENT0(cid);
+			val &= ~MDP5_SMP_ALLOC_W_REG_CLIENT0__MASK;
+			val |= MDP5_SMP_ALLOC_W_REG_CLIENT0(cid);
 			break;
 		case 1:
-			val &= ~MDP5_MDP_SMP_ALLOC_W_REG_CLIENT1__MASK;
-			val |= MDP5_MDP_SMP_ALLOC_W_REG_CLIENT1(cid);
+			val &= ~MDP5_SMP_ALLOC_W_REG_CLIENT1__MASK;
+			val |= MDP5_SMP_ALLOC_W_REG_CLIENT1(cid);
 			break;
 		case 2:
-			val &= ~MDP5_MDP_SMP_ALLOC_W_REG_CLIENT2__MASK;
-			val |= MDP5_MDP_SMP_ALLOC_W_REG_CLIENT2(cid);
+			val &= ~MDP5_SMP_ALLOC_W_REG_CLIENT2__MASK;
+			val |= MDP5_SMP_ALLOC_W_REG_CLIENT2(cid);
 			break;
 		}
 
-		mdp5_write(mdp5_kms, REG_MDP5_MDP_SMP_ALLOC_W_REG(0, idx), val);
-		mdp5_write(mdp5_kms, REG_MDP5_MDP_SMP_ALLOC_R_REG(0, idx), val);
+		mdp5_write(mdp5_kms, REG_MDP5_SMP_ALLOC_W_REG(idx), val);
+		mdp5_write(mdp5_kms, REG_MDP5_SMP_ALLOC_R_REG(idx), val);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index e3892c263f27..4a8a6f1f1151 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -84,17 +84,12 @@ static void msm_atomic_wait_for_commit_done(struct drm_device *dev,
 		struct drm_atomic_state *old_state)
 {
 	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
 	struct msm_drm_private *priv = old_state->dev->dev_private;
 	struct msm_kms *kms = priv->kms;
-	int ncrtcs = old_state->dev->mode_config.num_crtc;
 	int i;
 
-	for (i = 0; i < ncrtcs; i++) {
-		crtc = old_state->crtcs[i];
-
-		if (!crtc)
-			continue;
-
+	for_each_crtc_in_state(old_state, crtc, crtc_state, i) {
 		if (!crtc->state->enable)
 			continue;
 
@@ -192,9 +187,11 @@ int msm_atomic_commit(struct drm_device *dev,
 		struct drm_atomic_state *state, bool nonblock)
 {
 	struct msm_drm_private *priv = dev->dev_private;
-	int nplanes = dev->mode_config.num_total_plane;
-	int ncrtcs = dev->mode_config.num_crtc;
 	struct msm_commit *c;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	struct drm_plane *plane;
+	struct drm_plane_state *plane_state;
 	int i, ret;
 
 	ret = drm_atomic_helper_prepare_planes(dev, state);
@@ -210,28 +207,18 @@ int msm_atomic_commit(struct drm_device *dev,
 	/*
 	 * Figure out what crtcs we have:
 	 */
-	for (i = 0; i < ncrtcs; i++) {
-		struct drm_crtc *crtc = state->crtcs[i];
-		if (!crtc)
-			continue;
-		c->crtc_mask |= (1 << drm_crtc_index(crtc));
-	}
+	for_each_crtc_in_state(state, crtc, crtc_state, i)
+		c->crtc_mask |= drm_crtc_mask(crtc);
 
 	/*
 	 * Figure out what fence to wait for:
 	 */
-	for (i = 0; i < nplanes; i++) {
-		struct drm_plane *plane = state->planes[i];
-		struct drm_plane_state *new_state = state->plane_states[i];
-
-		if (!plane)
-			continue;
-
-		if ((plane->state->fb != new_state->fb) && new_state->fb) {
-			struct drm_gem_object *obj = msm_framebuffer_bo(new_state->fb, 0);
+	for_each_plane_in_state(state, plane, plane_state, i) {
+		if ((plane->state->fb != plane_state->fb) && plane_state->fb) {
+			struct drm_gem_object *obj = msm_framebuffer_bo(plane_state->fb, 0);
 			struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
-			new_state->fence = reservation_object_get_excl_rcu(msm_obj->resv);
+			plane_state->fence = reservation_object_get_excl_rcu(msm_obj->resv);
 		}
 	}
 
@@ -251,7 +238,7 @@ int msm_atomic_commit(struct drm_device *dev,
 	 * the software side now.
 	 */
 
-	drm_atomic_helper_swap_state(dev, state);
+	drm_atomic_helper_swap_state(state, true);
 
 	/*
 	 * Everything below can be run asynchronously without the need to grab
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 9c654092ef78..26f859ec24b3 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -21,6 +21,16 @@
 #include "msm_gpu.h"
 #include "msm_kms.h"
 
+
+/*
+ * MSM driver version:
+ * - 1.0.0 - initial interface
+ * - 1.1.0 - adds madvise, and support for submits with > 4 cmd buffers
+ */
+#define MSM_VERSION_MAJOR	1
+#define MSM_VERSION_MINOR	1
+#define MSM_VERSION_PATCHLEVEL	0
+
 static void msm_fb_output_poll_changed(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
@@ -195,9 +205,9 @@ static int msm_drm_uninit(struct device *dev)
 		kfree(vbl_ev);
 	}
 
-	drm_kms_helper_poll_fini(ddev);
+	msm_gem_shrinker_cleanup(ddev);
 
-	drm_connector_unregister_all(ddev);
+	drm_kms_helper_poll_fini(ddev);
 
 	drm_dev_unregister(ddev);
 
@@ -217,10 +227,8 @@ static int msm_drm_uninit(struct device *dev)
 	flush_workqueue(priv->atomic_wq);
 	destroy_workqueue(priv->atomic_wq);
 
-	if (kms) {
-		pm_runtime_disable(dev);
+	if (kms)
 		kms->funcs->destroy(kms);
-	}
 
 	if (gpu) {
 		mutex_lock(&ddev->struct_mutex);
@@ -239,6 +247,8 @@ static int msm_drm_uninit(struct device *dev)
 
 	component_unbind_all(dev, ddev);
 
+	msm_mdss_destroy(ddev);
+
 	ddev->dev_private = NULL;
 	drm_dev_unref(ddev);
 
@@ -284,6 +294,7 @@ static int msm_init_vram(struct drm_device *dev)
 	if (node) {
 		struct resource r;
 		ret = of_address_to_resource(node, 0, &r);
+		of_node_put(node);
 		if (ret)
 			return ret;
 		size = r.end - r.start;
@@ -352,6 +363,14 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	}
 
 	ddev->dev_private = priv;
+	priv->dev = ddev;
+
+	ret = msm_mdss_init(ddev);
+	if (ret) {
+		kfree(priv);
+		drm_dev_unref(ddev);
+		return ret;
+	}
 
 	priv->wq = alloc_ordered_workqueue("msm", 0);
 	priv->atomic_wq = alloc_ordered_workqueue("msm:atomic", 0);
@@ -367,6 +386,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	/* Bind all our sub-components: */
 	ret = component_bind_all(dev, ddev);
 	if (ret) {
+		msm_mdss_destroy(ddev);
 		kfree(priv);
 		drm_dev_unref(ddev);
 		return ret;
@@ -376,9 +396,12 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	if (ret)
 		goto fail;
 
+	msm_gem_shrinker_init(ddev);
+
 	switch (get_mdp_ver(pdev)) {
 	case 4:
 		kms = mdp4_kms_init(ddev);
+		priv->kms = kms;
 		break;
 	case 5:
 		kms = mdp5_kms_init(ddev);
@@ -400,10 +423,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		goto fail;
 	}
 
-	priv->kms = kms;
-
 	if (kms) {
-		pm_runtime_enable(dev);
 		ret = kms->funcs->hw_init(kms);
 		if (ret) {
 			dev_err(dev, "kms hw init failed: %d\n", ret);
@@ -419,24 +439,20 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		goto fail;
 	}
 
-	pm_runtime_get_sync(dev);
-	ret = drm_irq_install(ddev, platform_get_irq(pdev, 0));
-	pm_runtime_put_sync(dev);
-	if (ret < 0) {
-		dev_err(dev, "failed to install IRQ handler\n");
-		goto fail;
+	if (kms) {
+		pm_runtime_get_sync(dev);
+		ret = drm_irq_install(ddev, kms->irq);
+		pm_runtime_put_sync(dev);
+		if (ret < 0) {
+			dev_err(dev, "failed to install IRQ handler\n");
+			goto fail;
+		}
 	}
 
 	ret = drm_dev_register(ddev, 0);
 	if (ret)
 		goto fail;
 
-	ret = drm_connector_register_all(ddev);
-	if (ret) {
-		dev_err(dev, "failed to register connectors\n");
-		goto fail;
-	}
-
 	drm_mode_config_reset(ddev);
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
@@ -690,6 +706,44 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	return msm_wait_fence(priv->gpu->fctx, args->fence, &timeout, true);
 }
 
+static int msm_ioctl_gem_madvise(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_msm_gem_madvise *args = data;
+	struct drm_gem_object *obj;
+	int ret;
+
+	switch (args->madv) {
+	case MSM_MADV_DONTNEED:
+	case MSM_MADV_WILLNEED:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	obj = drm_gem_object_lookup(file, args->handle);
+	if (!obj) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	ret = msm_gem_madvise(obj, args->madv);
+	if (ret >= 0) {
+		args->retained = ret;
+		ret = 0;
+	}
+
+	drm_gem_object_unreference(obj);
+
+unlock:
+	mutex_unlock(&dev->struct_mutex);
+	return ret;
+}
+
 static const struct drm_ioctl_desc msm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(MSM_GET_PARAM,    msm_ioctl_get_param,    DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(MSM_GEM_NEW,      msm_ioctl_gem_new,      DRM_AUTH|DRM_RENDER_ALLOW),
@@ -698,6 +752,7 @@ static const struct drm_ioctl_desc msm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(MSM_GEM_CPU_FINI, msm_ioctl_gem_cpu_fini, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(MSM_GEM_SUBMIT,   msm_ioctl_gem_submit,   DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(MSM_WAIT_FENCE,   msm_ioctl_wait_fence,   DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(MSM_GEM_MADVISE,  msm_ioctl_gem_madvise,  DRM_AUTH|DRM_RENDER_ALLOW),
 };
 
 static const struct vm_operations_struct vm_ops = {
@@ -730,7 +785,6 @@ static struct drm_driver msm_driver = {
 	.open               = msm_open,
 	.preclose           = msm_preclose,
 	.lastclose          = msm_lastclose,
-	.set_busid          = drm_platform_set_busid,
 	.irq_handler        = msm_irq,
 	.irq_preinstall     = msm_irq_preinstall,
 	.irq_postinstall    = msm_irq_postinstall,
@@ -764,8 +818,9 @@ static struct drm_driver msm_driver = {
 	.name               = "msm",
 	.desc               = "MSM Snapdragon DRM",
 	.date               = "20130625",
-	.major              = 1,
-	.minor              = 0,
+	.major              = MSM_VERSION_MAJOR,
+	.minor              = MSM_VERSION_MINOR,
+	.patchlevel         = MSM_VERSION_PATCHLEVEL,
 };
 
 #ifdef CONFIG_PM_SLEEP
@@ -805,22 +860,146 @@ static int compare_of(struct device *dev, void *data)
 	return dev->of_node == data;
 }
 
-static int add_components(struct device *dev, struct component_match **matchptr,
-		const char *name)
+/*
+ * Identify what components need to be added by parsing what remote-endpoints
+ * our MDP output ports are connected to. In the case of LVDS on MDP4, there
+ * is no external component that we need to add since LVDS is within MDP4
+ * itself.
+ */
+static int add_components_mdp(struct device *mdp_dev,
+			      struct component_match **matchptr)
 {
-	struct device_node *np = dev->of_node;
-	unsigned i;
+	struct device_node *np = mdp_dev->of_node;
+	struct device_node *ep_node;
+	struct device *master_dev;
+
+	/*
+	 * on MDP4 based platforms, the MDP platform device is the component
+	 * master that adds other display interface components to itself.
+	 *
+	 * on MDP5 based platforms, the MDSS platform device is the component
+	 * master that adds MDP5 and other display interface components to
+	 * itself.
+	 */
+	if (of_device_is_compatible(np, "qcom,mdp4"))
+		master_dev = mdp_dev;
+	else
+		master_dev = mdp_dev->parent;
 
-	for (i = 0; ; i++) {
-		struct device_node *node;
+	for_each_endpoint_of_node(np, ep_node) {
+		struct device_node *intf;
+		struct of_endpoint ep;
+		int ret;
 
-		node = of_parse_phandle(np, name, i);
-		if (!node)
-			break;
+		ret = of_graph_parse_endpoint(ep_node, &ep);
+		if (ret) {
+			dev_err(mdp_dev, "unable to parse port endpoint\n");
+			of_node_put(ep_node);
+			return ret;
+		}
+
+		/*
+		 * The LCDC/LVDS port on MDP4 is a speacial case where the
+		 * remote-endpoint isn't a component that we need to add
+		 */
+		if (of_device_is_compatible(np, "qcom,mdp4") &&
+		    ep.port == 0) {
+			of_node_put(ep_node);
+			continue;
+		}
+
+		/*
+		 * It's okay if some of the ports don't have a remote endpoint
+		 * specified. It just means that the port isn't connected to
+		 * any external interface.
+		 */
+		intf = of_graph_get_remote_port_parent(ep_node);
+		if (!intf) {
+			of_node_put(ep_node);
+			continue;
+		}
+
+		component_match_add(master_dev, matchptr, compare_of, intf);
+
+		of_node_put(intf);
+		of_node_put(ep_node);
+	}
+
+	return 0;
+}
+
+static int compare_name_mdp(struct device *dev, void *data)
+{
+	return (strstr(dev_name(dev), "mdp") != NULL);
+}
+
+static int add_display_components(struct device *dev,
+				  struct component_match **matchptr)
+{
+	struct device *mdp_dev;
+	int ret;
+
+	/*
+	 * MDP5 based devices don't have a flat hierarchy. There is a top level
+	 * parent: MDSS, and children: MDP5, DSI, HDMI, eDP etc. Populate the
+	 * children devices, find the MDP5 node, and then add the interfaces
+	 * to our components list.
+	 */
+	if (of_device_is_compatible(dev->of_node, "qcom,mdss")) {
+		ret = of_platform_populate(dev->of_node, NULL, NULL, dev);
+		if (ret) {
+			dev_err(dev, "failed to populate children devices\n");
+			return ret;
+		}
+
+		mdp_dev = device_find_child(dev, NULL, compare_name_mdp);
+		if (!mdp_dev) {
+			dev_err(dev, "failed to find MDSS MDP node\n");
+			of_platform_depopulate(dev);
+			return -ENODEV;
+		}
+
+		put_device(mdp_dev);
 
-		component_match_add(dev, matchptr, compare_of, node);
+		/* add the MDP component itself */
+		component_match_add(dev, matchptr, compare_of,
+				    mdp_dev->of_node);
+	} else {
+		/* MDP4 */
+		mdp_dev = dev;
 	}
 
+	ret = add_components_mdp(mdp_dev, matchptr);
+	if (ret)
+		of_platform_depopulate(dev);
+
+	return ret;
+}
+
+/*
+ * We don't know what's the best binding to link the gpu with the drm device.
+ * Fow now, we just hunt for all the possible gpus that we support, and add them
+ * as components.
+ */
+static const struct of_device_id msm_gpu_match[] = {
+	{ .compatible = "qcom,adreno-3xx" },
+	{ .compatible = "qcom,kgsl-3d0" },
+	{ },
+};
+
+static int add_gpu_components(struct device *dev,
+			      struct component_match **matchptr)
+{
+	struct device_node *np;
+
+	np = of_find_matching_node(NULL, msm_gpu_match);
+	if (!np)
+		return 0;
+
+	component_match_add(dev, matchptr, compare_of, np);
+
+	of_node_put(np);
+
 	return 0;
 }
 
@@ -846,9 +1025,15 @@ static const struct component_master_ops msm_drm_ops = {
 static int msm_pdev_probe(struct platform_device *pdev)
 {
 	struct component_match *match = NULL;
+	int ret;
 
-	add_components(&pdev->dev, &match, "connectors");
-	add_components(&pdev->dev, &match, "gpus");
+	ret = add_display_components(&pdev->dev, &match);
+	if (ret)
+		return ret;
+
+	ret = add_gpu_components(&pdev->dev, &match);
+	if (ret)
+		return ret;
 
 	pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
 	return component_master_add_with_match(&pdev->dev, &msm_drm_ops, match);
@@ -857,20 +1042,14 @@ static int msm_pdev_probe(struct platform_device *pdev)
 static int msm_pdev_remove(struct platform_device *pdev)
 {
 	component_master_del(&pdev->dev, &msm_drm_ops);
+	of_platform_depopulate(&pdev->dev);
 
 	return 0;
 }
 
-static const struct platform_device_id msm_id[] = {
-	{ "mdp", 0 },
-	{ }
-};
-
 static const struct of_device_id dt_match[] = {
-	{ .compatible = "qcom,mdp4", .data = (void *) 4 },	/* mdp4 */
-	{ .compatible = "qcom,mdp5", .data = (void *) 5 },	/* mdp5 */
-	/* to support downstream DT files */
-	{ .compatible = "qcom,mdss_mdp", .data = (void *) 5 },  /* mdp5 */
+	{ .compatible = "qcom,mdp4", .data = (void *)4 },	/* MDP4 */
+	{ .compatible = "qcom,mdss", .data = (void *)5 },	/* MDP5 MDSS */
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
@@ -883,12 +1062,12 @@ static struct platform_driver msm_platform_driver = {
 		.of_match_table = dt_match,
 		.pm     = &msm_pm_ops,
 	},
-	.id_table   = msm_id,
 };
 
 static int __init msm_drm_register(void)
 {
 	DBG("init");
+	msm_mdp_register();
 	msm_dsi_register();
 	msm_edp_register();
 	msm_hdmi_register();
@@ -904,6 +1083,7 @@ static void __exit msm_drm_unregister(void)
 	adreno_unregister();
 	msm_edp_unregister();
 	msm_dsi_unregister();
+	msm_mdp_unregister();
 }
 
 module_init(msm_drm_register);
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 5b2963f32291..b4bc7f1ef717 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -46,6 +46,7 @@
 struct msm_kms;
 struct msm_gpu;
 struct msm_mmu;
+struct msm_mdss;
 struct msm_rd_state;
 struct msm_perf_state;
 struct msm_gem_submit;
@@ -77,11 +78,16 @@ struct msm_vblank_ctrl {
 
 struct msm_drm_private {
 
+	struct drm_device *dev;
+
 	struct msm_kms *kms;
 
 	/* subordinate devices, if present: */
 	struct platform_device *gpu_pdev;
 
+	/* top level MDSS wrapper device (for MDP5 only) */
+	struct msm_mdss *mdss;
+
 	/* possibly this should be in the kms component, but it is
 	 * shared by both mdp4 and mdp5..
 	 */
@@ -147,6 +153,9 @@ struct msm_drm_private {
 		struct drm_mm mm;
 	} vram;
 
+	struct notifier_block vmap_notifier;
+	struct shrinker shrinker;
+
 	struct msm_vblank_ctrl vblank_ctrl;
 };
 
@@ -165,6 +174,9 @@ void msm_gem_submit_free(struct msm_gem_submit *submit);
 int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		struct drm_file *file);
 
+void msm_gem_shrinker_init(struct drm_device *dev);
+void msm_gem_shrinker_cleanup(struct drm_device *dev);
+
 int msm_gem_mmap_obj(struct drm_gem_object *obj,
 			struct vm_area_struct *vma);
 int msm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
@@ -189,8 +201,13 @@ struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
 		struct dma_buf_attachment *attach, struct sg_table *sg);
 int msm_gem_prime_pin(struct drm_gem_object *obj);
 void msm_gem_prime_unpin(struct drm_gem_object *obj);
-void *msm_gem_vaddr_locked(struct drm_gem_object *obj);
-void *msm_gem_vaddr(struct drm_gem_object *obj);
+void *msm_gem_get_vaddr_locked(struct drm_gem_object *obj);
+void *msm_gem_get_vaddr(struct drm_gem_object *obj);
+void msm_gem_put_vaddr_locked(struct drm_gem_object *obj);
+void msm_gem_put_vaddr(struct drm_gem_object *obj);
+int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv);
+void msm_gem_purge(struct drm_gem_object *obj);
+void msm_gem_vunmap(struct drm_gem_object *obj);
 int msm_gem_sync_object(struct drm_gem_object *obj,
 		struct msm_fence_context *fctx, bool exclusive);
 void msm_gem_move_to_active(struct drm_gem_object *obj,
@@ -257,6 +274,9 @@ static inline int msm_dsi_modeset_init(struct msm_dsi *msm_dsi,
 }
 #endif
 
+void __init msm_mdp_register(void);
+void __exit msm_mdp_unregister(void);
+
 #ifdef CONFIG_DEBUG_FS
 void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m);
 void msm_gem_describe_objects(struct list_head *list, struct seq_file *m);
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index 461dc8b873f0..95cf8fe72ee5 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -49,24 +49,16 @@ static void msm_framebuffer_destroy(struct drm_framebuffer *fb)
 
 	for (i = 0; i < n; i++) {
 		struct drm_gem_object *bo = msm_fb->planes[i];
-		if (bo)
-			drm_gem_object_unreference_unlocked(bo);
+
+		drm_gem_object_unreference_unlocked(bo);
 	}
 
 	kfree(msm_fb);
 }
 
-static int msm_framebuffer_dirty(struct drm_framebuffer *fb,
-		struct drm_file *file_priv, unsigned flags, unsigned color,
-		struct drm_clip_rect *clips, unsigned num_clips)
-{
-	return 0;
-}
-
 static const struct drm_framebuffer_funcs msm_framebuffer_funcs = {
 	.create_handle = msm_framebuffer_create_handle,
 	.destroy = msm_framebuffer_destroy,
-	.dirty = msm_framebuffer_dirty,
 };
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index c6cf837c5193..ffd4a338ca12 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -158,7 +158,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 
 	dev->mode_config.fb_base = paddr;
 
-	fbi->screen_base = msm_gem_vaddr_locked(fbdev->bo);
+	fbi->screen_base = msm_gem_get_vaddr_locked(fbdev->bo);
 	if (IS_ERR(fbi->screen_base)) {
 		ret = PTR_ERR(fbi->screen_base);
 		goto fail_unlock;
@@ -188,21 +188,7 @@ fail:
 	return ret;
 }
 
-static void msm_crtc_fb_gamma_set(struct drm_crtc *crtc,
-		u16 red, u16 green, u16 blue, int regno)
-{
-	DBG("fbdev: set gamma");
-}
-
-static void msm_crtc_fb_gamma_get(struct drm_crtc *crtc,
-		u16 *red, u16 *green, u16 *blue, int regno)
-{
-	DBG("fbdev: get gamma");
-}
-
 static const struct drm_fb_helper_funcs msm_fb_helper_funcs = {
-	.gamma_set = msm_crtc_fb_gamma_set,
-	.gamma_get = msm_crtc_fb_gamma_get,
 	.fb_probe = msm_fbdev_create,
 };
 
@@ -265,6 +251,7 @@ void msm_fbdev_free(struct drm_device *dev)
 
 	/* this will free the backing object */
 	if (fbdev->fb) {
+		msm_gem_put_vaddr(fbdev->bo);
 		drm_framebuffer_unregister_private(fbdev->fb);
 		drm_framebuffer_remove(fbdev->fb);
 	}
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 69836f5685b1..6cd4af443139 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -276,6 +276,26 @@ uint64_t msm_gem_mmap_offset(struct drm_gem_object *obj)
 	return offset;
 }
 
+static void
+put_iova(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	struct msm_drm_private *priv = obj->dev->dev_private;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	int id;
+
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	for (id = 0; id < ARRAY_SIZE(msm_obj->domain); id++) {
+		struct msm_mmu *mmu = priv->mmus[id];
+		if (mmu && msm_obj->domain[id].iova) {
+			uint32_t offset = msm_obj->domain[id].iova;
+			mmu->funcs->unmap(mmu, offset, msm_obj->sgt, obj->size);
+			msm_obj->domain[id].iova = 0;
+		}
+	}
+}
+
 /* should be called under struct_mutex.. although it can be called
  * from atomic context without struct_mutex to acquire an extra
  * iova ref if you know one is already held.
@@ -388,7 +408,7 @@ fail:
 	return ret;
 }
 
-void *msm_gem_vaddr_locked(struct drm_gem_object *obj)
+void *msm_gem_get_vaddr_locked(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
@@ -401,18 +421,91 @@ void *msm_gem_vaddr_locked(struct drm_gem_object *obj)
 		if (msm_obj->vaddr == NULL)
 			return ERR_PTR(-ENOMEM);
 	}
+	msm_obj->vmap_count++;
 	return msm_obj->vaddr;
 }
 
-void *msm_gem_vaddr(struct drm_gem_object *obj)
+void *msm_gem_get_vaddr(struct drm_gem_object *obj)
 {
 	void *ret;
 	mutex_lock(&obj->dev->struct_mutex);
-	ret = msm_gem_vaddr_locked(obj);
+	ret = msm_gem_get_vaddr_locked(obj);
 	mutex_unlock(&obj->dev->struct_mutex);
 	return ret;
 }
 
+void msm_gem_put_vaddr_locked(struct drm_gem_object *obj)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
+	WARN_ON(msm_obj->vmap_count < 1);
+	msm_obj->vmap_count--;
+}
+
+void msm_gem_put_vaddr(struct drm_gem_object *obj)
+{
+	mutex_lock(&obj->dev->struct_mutex);
+	msm_gem_put_vaddr_locked(obj);
+	mutex_unlock(&obj->dev->struct_mutex);
+}
+
+/* Update madvise status, returns true if not purged, else
+ * false or -errno.
+ */
+int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
+
+	if (msm_obj->madv != __MSM_MADV_PURGED)
+		msm_obj->madv = madv;
+
+	return (msm_obj->madv != __MSM_MADV_PURGED);
+}
+
+void msm_gem_purge(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+	WARN_ON(!is_purgeable(msm_obj));
+	WARN_ON(obj->import_attach);
+
+	put_iova(obj);
+
+	msm_gem_vunmap(obj);
+
+	put_pages(obj);
+
+	msm_obj->madv = __MSM_MADV_PURGED;
+
+	drm_vma_node_unmap(&obj->vma_node, dev->anon_inode->i_mapping);
+	drm_gem_free_mmap_offset(obj);
+
+	/* Our goal here is to return as much of the memory as
+	 * is possible back to the system as we are called from OOM.
+	 * To do this we must instruct the shmfs to drop all of its
+	 * backing pages, *now*.
+	 */
+	shmem_truncate_range(file_inode(obj->filp), 0, (loff_t)-1);
+
+	invalidate_mapping_pages(file_inode(obj->filp)->i_mapping,
+			0, (loff_t)-1);
+}
+
+void msm_gem_vunmap(struct drm_gem_object *obj)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+
+	if (!msm_obj->vaddr || WARN_ON(!is_vunmapable(msm_obj)))
+		return;
+
+	vunmap(msm_obj->vaddr);
+	msm_obj->vaddr = NULL;
+}
+
 /* must be called before _move_to_active().. */
 int msm_gem_sync_object(struct drm_gem_object *obj,
 		struct msm_fence_context *fctx, bool exclusive)
@@ -464,6 +557,7 @@ void msm_gem_move_to_active(struct drm_gem_object *obj,
 		struct msm_gpu *gpu, bool exclusive, struct fence *fence)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED);
 	msm_obj->gpu = gpu;
 	if (exclusive)
 		reservation_object_add_excl_fence(msm_obj->resv, fence);
@@ -532,13 +626,27 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 	struct reservation_object_list *fobj;
 	struct fence *fence;
 	uint64_t off = drm_vma_node_start(&obj->vma_node);
+	const char *madv;
 
 	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
 
-	seq_printf(m, "%08x: %c %2d (%2d) %08llx %p %zu\n",
+	switch (msm_obj->madv) {
+	case __MSM_MADV_PURGED:
+		madv = " purged";
+		break;
+	case MSM_MADV_DONTNEED:
+		madv = " purgeable";
+		break;
+	case MSM_MADV_WILLNEED:
+	default:
+		madv = "";
+		break;
+	}
+
+	seq_printf(m, "%08x: %c %2d (%2d) %08llx %p %zu%s\n",
 			msm_obj->flags, is_active(msm_obj) ? 'A' : 'I',
 			obj->name, obj->refcount.refcount.counter,
-			off, msm_obj->vaddr, obj->size);
+			off, msm_obj->vaddr, obj->size, madv);
 
 	rcu_read_lock();
 	fobj = rcu_dereference(robj->fence);
@@ -578,9 +686,7 @@ void msm_gem_describe_objects(struct list_head *list, struct seq_file *m)
 void msm_gem_free_object(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
-	struct msm_drm_private *priv = obj->dev->dev_private;
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	int id;
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
@@ -589,13 +695,7 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 
 	list_del(&msm_obj->mm_list);
 
-	for (id = 0; id < ARRAY_SIZE(msm_obj->domain); id++) {
-		struct msm_mmu *mmu = priv->mmus[id];
-		if (mmu && msm_obj->domain[id].iova) {
-			uint32_t offset = msm_obj->domain[id].iova;
-			mmu->funcs->unmap(mmu, offset, msm_obj->sgt, obj->size);
-		}
-	}
+	put_iova(obj);
 
 	if (obj->import_attach) {
 		if (msm_obj->vaddr)
@@ -609,7 +709,7 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 
 		drm_prime_gem_destroy(obj, msm_obj->sgt);
 	} else {
-		vunmap(msm_obj->vaddr);
+		msm_gem_vunmap(obj);
 		put_pages(obj);
 	}
 
@@ -688,6 +788,7 @@ static int msm_gem_new_impl(struct drm_device *dev,
 		msm_obj->vram_node = (void *)&msm_obj[1];
 
 	msm_obj->flags = flags;
+	msm_obj->madv = MSM_MADV_WILLNEED;
 
 	if (resv) {
 		msm_obj->resv = resv;
@@ -729,9 +830,7 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev,
 	return obj;
 
 fail:
-	if (obj)
-		drm_gem_object_unreference(obj);
-
+	drm_gem_object_unreference(obj);
 	return ERR_PTR(ret);
 }
 
@@ -774,8 +873,6 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 	return obj;
 
 fail:
-	if (obj)
-		drm_gem_object_unreference_unlocked(obj);
-
+	drm_gem_object_unreference_unlocked(obj);
 	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 9facd4b6ffd9..b2f13cfe945e 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -29,6 +29,16 @@ struct msm_gem_object {
 
 	uint32_t flags;
 
+	/**
+	 * Advice: are the backing pages purgeable?
+	 */
+	uint8_t madv;
+
+	/**
+	 * count of active vmap'ing
+	 */
+	uint8_t vmap_count;
+
 	/* And object is either:
 	 *  inactive - on priv->inactive_list
 	 *  active   - on one one of the gpu's active_list..  well, at
@@ -72,7 +82,16 @@ static inline bool is_active(struct msm_gem_object *msm_obj)
 	return msm_obj->gpu != NULL;
 }
 
-#define MAX_CMDS 4
+static inline bool is_purgeable(struct msm_gem_object *msm_obj)
+{
+	return (msm_obj->madv == MSM_MADV_DONTNEED) && msm_obj->sgt &&
+			!msm_obj->base.dma_buf && !msm_obj->base.import_attach;
+}
+
+static inline bool is_vunmapable(struct msm_gem_object *msm_obj)
+{
+	return (msm_obj->vmap_count == 0) && msm_obj->vaddr;
+}
 
 /* Created per submit-ioctl, to track bo's and cmdstream bufs, etc,
  * associated with the cmdstream submission for synchronization (and
@@ -95,7 +114,7 @@ struct msm_gem_submit {
 		uint32_t size;  /* in dwords */
 		uint32_t iova;
 		uint32_t idx;   /* cmdstream buffer idx in bos[] */
-	} cmd[MAX_CMDS];
+	} *cmd;  /* array of size nr_cmds */
 	struct {
 		uint32_t flags;
 		struct msm_gem_object *obj;
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 6b90890faffe..60bb290700ce 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -33,12 +33,12 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj)
 
 void *msm_gem_prime_vmap(struct drm_gem_object *obj)
 {
-	return msm_gem_vaddr(obj);
+	return msm_gem_get_vaddr(obj);
 }
 
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 {
-	/* TODO msm_gem_vunmap() */
+	msm_gem_put_vaddr(obj);
 }
 
 int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c
new file mode 100644
index 000000000000..283d2841ba58
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -0,0 +1,168 @@
+/*
+ * Copyright (C) 2016 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "msm_drv.h"
+#include "msm_gem.h"
+
+static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
+{
+	if (!mutex_is_locked(mutex))
+		return false;
+
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
+	return mutex->owner == task;
+#else
+	/* Since UP may be pre-empted, we cannot assume that we own the lock */
+	return false;
+#endif
+}
+
+static bool msm_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
+{
+	if (!mutex_trylock(&dev->struct_mutex)) {
+		if (!mutex_is_locked_by(&dev->struct_mutex, current))
+			return false;
+		*unlock = false;
+	} else {
+		*unlock = true;
+	}
+
+	return true;
+}
+
+
+static unsigned long
+msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
+{
+	struct msm_drm_private *priv =
+		container_of(shrinker, struct msm_drm_private, shrinker);
+	struct drm_device *dev = priv->dev;
+	struct msm_gem_object *msm_obj;
+	unsigned long count = 0;
+	bool unlock;
+
+	if (!msm_gem_shrinker_lock(dev, &unlock))
+		return 0;
+
+	list_for_each_entry(msm_obj, &priv->inactive_list, mm_list) {
+		if (is_purgeable(msm_obj))
+			count += msm_obj->base.size >> PAGE_SHIFT;
+	}
+
+	if (unlock)
+		mutex_unlock(&dev->struct_mutex);
+
+	return count;
+}
+
+static unsigned long
+msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
+{
+	struct msm_drm_private *priv =
+		container_of(shrinker, struct msm_drm_private, shrinker);
+	struct drm_device *dev = priv->dev;
+	struct msm_gem_object *msm_obj;
+	unsigned long freed = 0;
+	bool unlock;
+
+	if (!msm_gem_shrinker_lock(dev, &unlock))
+		return SHRINK_STOP;
+
+	list_for_each_entry(msm_obj, &priv->inactive_list, mm_list) {
+		if (freed >= sc->nr_to_scan)
+			break;
+		if (is_purgeable(msm_obj)) {
+			msm_gem_purge(&msm_obj->base);
+			freed += msm_obj->base.size >> PAGE_SHIFT;
+		}
+	}
+
+	if (unlock)
+		mutex_unlock(&dev->struct_mutex);
+
+	if (freed > 0)
+		pr_info_ratelimited("Purging %lu bytes\n", freed << PAGE_SHIFT);
+
+	return freed;
+}
+
+static int
+msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr)
+{
+	struct msm_drm_private *priv =
+		container_of(nb, struct msm_drm_private, vmap_notifier);
+	struct drm_device *dev = priv->dev;
+	struct msm_gem_object *msm_obj;
+	unsigned unmapped = 0;
+	bool unlock;
+
+	if (!msm_gem_shrinker_lock(dev, &unlock))
+		return NOTIFY_DONE;
+
+	list_for_each_entry(msm_obj, &priv->inactive_list, mm_list) {
+		if (is_vunmapable(msm_obj)) {
+			msm_gem_vunmap(&msm_obj->base);
+			/* since we don't know any better, lets bail after a few
+			 * and if necessary the shrinker will be invoked again.
+			 * Seems better than unmapping *everything*
+			 */
+			if (++unmapped >= 15)
+				break;
+		}
+	}
+
+	if (unlock)
+		mutex_unlock(&dev->struct_mutex);
+
+	*(unsigned long *)ptr += unmapped;
+
+	if (unmapped > 0)
+		pr_info_ratelimited("Purging %u vmaps\n", unmapped);
+
+	return NOTIFY_DONE;
+}
+
+/**
+ * msm_gem_shrinker_init - Initialize msm shrinker
+ * @dev_priv: msm device
+ *
+ * This function registers and sets up the msm shrinker.
+ */
+void msm_gem_shrinker_init(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	priv->shrinker.count_objects = msm_gem_shrinker_count;
+	priv->shrinker.scan_objects = msm_gem_shrinker_scan;
+	priv->shrinker.seeks = DEFAULT_SEEKS;
+	WARN_ON(register_shrinker(&priv->shrinker));
+
+	priv->vmap_notifier.notifier_call = msm_gem_shrinker_vmap;
+	WARN_ON(register_vmap_purge_notifier(&priv->vmap_notifier));
+}
+
+/**
+ * msm_gem_shrinker_cleanup - Clean up msm shrinker
+ * @dev_priv: msm device
+ *
+ * This function unregisters the msm shrinker.
+ */
+void msm_gem_shrinker_cleanup(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	WARN_ON(unregister_vmap_purge_notifier(&priv->vmap_notifier));
+	unregister_shrinker(&priv->shrinker);
+}
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index eb4bb8b2f3a5..9766f9ae4b7d 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -29,10 +29,11 @@
 #define BO_PINNED   0x2000
 
 static struct msm_gem_submit *submit_create(struct drm_device *dev,
-		struct msm_gpu *gpu, int nr)
+		struct msm_gpu *gpu, int nr_bos, int nr_cmds)
 {
 	struct msm_gem_submit *submit;
-	int sz = sizeof(*submit) + (nr * sizeof(submit->bos[0]));
+	int sz = sizeof(*submit) + (nr_bos * sizeof(submit->bos[0])) +
+			(nr_cmds * sizeof(*submit->cmd));
 
 	submit = kmalloc(sz, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
 	if (!submit)
@@ -42,6 +43,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 	submit->gpu = gpu;
 	submit->fence = NULL;
 	submit->pid = get_pid(task_pid(current));
+	submit->cmd = (void *)&submit->bos[nr_bos];
 
 	/* initially, until copy_from_user() and bo lookup succeeds: */
 	submit->nr_bos = 0;
@@ -279,7 +281,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob
 	/* For now, just map the entire thing.  Eventually we probably
 	 * to do it page-by-page, w/ kmap() if not vmap()d..
 	 */
-	ptr = msm_gem_vaddr_locked(&obj->base);
+	ptr = msm_gem_get_vaddr_locked(&obj->base);
 
 	if (IS_ERR(ptr)) {
 		ret = PTR_ERR(ptr);
@@ -332,6 +334,8 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob
 		last_offset = off;
 	}
 
+	msm_gem_put_vaddr_locked(&obj->base);
+
 	return 0;
 }
 
@@ -369,14 +373,15 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (args->pipe != MSM_PIPE_3D0)
 		return -EINVAL;
 
-	if (args->nr_cmds > MAX_CMDS)
-		return -EINVAL;
-
-	submit = submit_create(dev, gpu, args->nr_bos);
-	if (!submit)
-		return -ENOMEM;
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
-	mutex_lock(&dev->struct_mutex);
+	submit = submit_create(dev, gpu, args->nr_bos, args->nr_cmds);
+	if (!submit) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
 
 	ret = submit_lookup_objects(submit, args, file);
 	if (ret)
@@ -462,6 +467,7 @@ out:
 	submit_cleanup(submit);
 	if (ret)
 		msm_gem_submit_free(submit);
+out_unlock:
 	mutex_unlock(&dev->struct_mutex);
 	return ret;
 }
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index a7a0b6d9b057..3a294d0da3a0 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -59,10 +59,10 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint32_t iova,
 		return -EINVAL;
 
 	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
-		u32 pa = sg_phys(sg) - sg->offset;
+		dma_addr_t pa = sg_phys(sg) - sg->offset;
 		size_t bytes = sg->length + sg->offset;
 
-		VERB("map[%d]: %08x %08x(%zx)", i, iova, pa, bytes);
+		VERB("map[%d]: %08x %08lx(%zx)", i, da, (unsigned long)pa, bytes);
 
 		ret = iommu_map(domain, da, pa, bytes, prot);
 		if (ret)
@@ -101,7 +101,7 @@ static int msm_iommu_unmap(struct msm_mmu *mmu, uint32_t iova,
 		if (unmapped < bytes)
 			return unmapped;
 
-		VERB("unmap[%d]: %08x(%zx)", i, iova, bytes);
+		VERB("unmap[%d]: %08x(%zx)", i, da, bytes);
 
 		BUG_ON(!PAGE_ALIGNED(bytes));
 
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index e32222c3d44f..40e41e5cdbc6 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -61,10 +61,8 @@ struct msm_kms_funcs {
 struct msm_kms {
 	const struct msm_kms_funcs *funcs;
 
-	/* irq handling: */
-	bool in_irq;
-	struct list_head irq_list;    /* list of mdp4_irq */
-	uint32_t vblank_mask;         /* irq bits set for userspace vblank */
+	/* irq number to be passed on to drm_irq_install */
+	int irq;
 };
 
 static inline void msm_kms_init(struct msm_kms *kms,
@@ -75,5 +73,7 @@ static inline void msm_kms_init(struct msm_kms *kms,
 
 struct msm_kms *mdp4_kms_init(struct drm_device *dev);
 struct msm_kms *mdp5_kms_init(struct drm_device *dev);
+int msm_mdss_init(struct drm_device *dev);
+void msm_mdss_destroy(struct drm_device *dev);
 
 #endif /* __MSM_KMS_H__ */
diff --git a/drivers/gpu/drm/msm/msm_perf.c b/drivers/gpu/drm/msm/msm_perf.c
index 830857c47c86..17fe4e53e0d1 100644
--- a/drivers/gpu/drm/msm/msm_perf.c
+++ b/drivers/gpu/drm/msm/msm_perf.c
@@ -132,7 +132,7 @@ static ssize_t perf_read(struct file *file, char __user *buf,
 		size_t sz, loff_t *ppos)
 {
 	struct msm_perf_state *perf = file->private_data;
-	int n = 0, ret;
+	int n = 0, ret = 0;
 
 	mutex_lock(&perf->read_lock);
 
@@ -143,9 +143,10 @@ static ssize_t perf_read(struct file *file, char __user *buf,
 	}
 
 	n = min((int)sz, perf->buftot - perf->bufpos);
-	ret = copy_to_user(buf, &perf->buf[perf->bufpos], n);
-	if (ret)
+	if (copy_to_user(buf, &perf->buf[perf->bufpos], n)) {
+		ret = -EFAULT;
 		goto out;
+	}
 
 	perf->bufpos += n;
 	*ppos += n;
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index 0857710c2ff2..3a5fdfcd67ae 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -27,6 +27,11 @@
  * This bypasses drm_debugfs_create_files() mainly because we need to use
  * our own fops for a bit more control.  In particular, we don't want to
  * do anything if userspace doesn't have the debugfs file open.
+ *
+ * The module-param "rd_full", which defaults to false, enables snapshotting
+ * all (non-written) buffers in the submit, rather than just cmdstream bo's.
+ * This is useful to capture the contents of (for example) vbo's or textures,
+ * or shader programs (if not emitted inline in cmdstream).
  */
 
 #ifdef CONFIG_DEBUG_FS
@@ -40,6 +45,10 @@
 #include "msm_gpu.h"
 #include "msm_gem.h"
 
+static bool rd_full = false;
+MODULE_PARM_DESC(rd_full, "If true, $debugfs/.../rd will snapshot all buffer contents");
+module_param_named(rd_full, rd_full, bool, 0600);
+
 enum rd_sect_type {
 	RD_NONE,
 	RD_TEST,       /* ascii text */
@@ -140,9 +149,10 @@ static ssize_t rd_read(struct file *file, char __user *buf,
 		goto out;
 
 	n = min_t(int, sz, circ_count_to_end(&rd->fifo));
-	ret = copy_to_user(buf, fptr, n);
-	if (ret)
+	if (copy_to_user(buf, fptr, n)) {
+		ret = -EFAULT;
 		goto out;
+	}
 
 	fifo->tail = (fifo->tail + n) & (BUF_SZ - 1);
 	*ppos += n;
@@ -277,6 +287,31 @@ void msm_rd_debugfs_cleanup(struct drm_minor *minor)
 	kfree(rd);
 }
 
+static void snapshot_buf(struct msm_rd_state *rd,
+		struct msm_gem_submit *submit, int idx,
+		uint32_t iova, uint32_t size)
+{
+	struct msm_gem_object *obj = submit->bos[idx].obj;
+	const char *buf;
+
+	buf = msm_gem_get_vaddr_locked(&obj->base);
+	if (IS_ERR(buf))
+		return;
+
+	if (iova) {
+		buf += iova - submit->bos[idx].iova;
+	} else {
+		iova = submit->bos[idx].iova;
+		size = obj->base.size;
+	}
+
+	rd_write_section(rd, RD_GPUADDR,
+			(uint32_t[2]){ iova, size }, 8);
+	rd_write_section(rd, RD_BUFFER_CONTENTS, buf, size);
+
+	msm_gem_put_vaddr_locked(&obj->base);
+}
+
 /* called under struct_mutex */
 void msm_rd_dump_submit(struct msm_gem_submit *submit)
 {
@@ -300,27 +335,27 @@ void msm_rd_dump_submit(struct msm_gem_submit *submit)
 
 	rd_write_section(rd, RD_CMD, msg, ALIGN(n, 4));
 
-	/* could be nice to have an option (module-param?) to snapshot
-	 * all the bo's associated with the submit.  Handy to see vtx
-	 * buffers, etc.  For now just the cmdstream bo's is enough.
-	 */
+	if (rd_full) {
+		for (i = 0; i < submit->nr_bos; i++) {
+			/* buffers that are written to probably don't start out
+			 * with anything interesting:
+			 */
+			if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
+				continue;
+
+			snapshot_buf(rd, submit, i, 0, 0);
+		}
+	}
 
 	for (i = 0; i < submit->nr_cmds; i++) {
-		uint32_t idx  = submit->cmd[i].idx;
 		uint32_t iova = submit->cmd[i].iova;
 		uint32_t szd  = submit->cmd[i].size; /* in dwords */
-		struct msm_gem_object *obj = submit->bos[idx].obj;
-		const char *buf = msm_gem_vaddr_locked(&obj->base);
-
-		if (IS_ERR(buf))
-			continue;
 
-		buf += iova - submit->bos[idx].iova;
-
-		rd_write_section(rd, RD_GPUADDR,
-				(uint32_t[2]){ iova, szd * 4 }, 8);
-		rd_write_section(rd, RD_BUFFER_CONTENTS,
-				buf, szd * 4);
+		/* snapshot cmdstream bo's (if we haven't already): */
+		if (!rd_full) {
+			snapshot_buf(rd, submit, submit->cmd[i].idx,
+					submit->cmd[i].iova, szd * 4);
+		}
 
 		switch (submit->cmd[i].type) {
 		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 42f5359cf988..f326cf6a32e6 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -39,7 +39,7 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int size)
 		goto fail;
 	}
 
-	ring->start = msm_gem_vaddr_locked(ring->bo);
+	ring->start = msm_gem_get_vaddr_locked(ring->bo);
 	if (IS_ERR(ring->start)) {
 		ret = PTR_ERR(ring->start);
 		goto fail;
@@ -59,7 +59,9 @@ fail:
 
 void msm_ringbuffer_destroy(struct msm_ringbuffer *ring)
 {
-	if (ring->bo)
+	if (ring->bo) {
+		msm_gem_put_vaddr(ring->bo);
 		drm_gem_object_unreference_unlocked(ring->bo);
+	}
 	kfree(ring);
 }
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index 5ab13e7939db..2922a82cba8e 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -3,13 +3,7 @@ config DRM_NOUVEAU
 	depends on DRM && PCI
         select FW_LOADER
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_TTM
-	select FB_CFB_FILLRECT
-	select FB_CFB_COPYAREA
-	select FB_CFB_IMAGEBLIT
-	select FB
-	select FRAMEBUFFER_CONSOLE if !EXPERT
 	select FB_BACKLIGHT if DRM_NOUVEAU_BACKLIGHT
 	select ACPI_VIDEO if ACPI && X86 && BACKLIGHT_CLASS_DEVICE && INPUT
 	select X86_PLATFORM_DEVICES if ACPI && X86
diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
index 6f318c54da33..0cb7a18cde26 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
@@ -785,14 +785,14 @@ nv_crtc_disable(struct drm_crtc *crtc)
 	nouveau_bo_ref(NULL, &disp->image[nv_crtc->index]);
 }
 
-static void
-nv_crtc_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b, uint32_t start,
+static int
+nv_crtc_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
 		  uint32_t size)
 {
-	int end = (start + size > 256) ? 256 : start + size, i;
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
+	int i;
 
-	for (i = start; i < end; i++) {
+	for (i = 0; i < size; i++) {
 		nv_crtc->lut.r[i] = r[i];
 		nv_crtc->lut.g[i] = g[i];
 		nv_crtc->lut.b[i] = b[i];
@@ -805,10 +805,12 @@ nv_crtc_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b, uint32_t start,
 	 */
 	if (!nv_crtc->base.primary->fb) {
 		nv_crtc->lut.depth = 0;
-		return;
+		return 0;
 	}
 
 	nv_crtc_gamma_load(crtc);
+
+	return 0;
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c
index aea81a547e85..34c0f2f67548 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c
@@ -125,18 +125,8 @@ nv04_display_destroy(struct drm_device *dev)
 	struct nv04_display *disp = nv04_display(dev);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_encoder *encoder;
-	struct drm_crtc *crtc;
 	struct nouveau_crtc *nv_crtc;
 
-	/* Turn every CRTC off. */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		struct drm_mode_set modeset = {
-			.crtc = crtc,
-		};
-
-		drm_mode_set_config_internal(&modeset);
-	}
-
 	/* Restore state */
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.base.head)
 		encoder->enc_restore(&encoder->base.base);
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
index a665b78b2af5..434d1e29f279 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
@@ -749,13 +749,8 @@ static int nv17_tv_set_property(struct drm_encoder *encoder,
 
 		/* Disable the crtc to ensure a full modeset is
 		 * performed whenever it's turned on again. */
-		if (crtc) {
-			struct drm_mode_set modeset = {
-				.crtc = crtc,
-			};
-
-			drm_mode_set_config_internal(&modeset);
-		}
+		if (crtc)
+			drm_crtc_force_disable(crtc);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
index 331620a52afa..287a7d6fa480 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
@@ -29,6 +29,7 @@ struct nv_device_info_v0 {
 #define NV_DEVICE_INFO_V0_FERMI                                            0x07
 #define NV_DEVICE_INFO_V0_KEPLER                                           0x08
 #define NV_DEVICE_INFO_V0_MAXWELL                                          0x09
+#define NV_DEVICE_INFO_V0_PASCAL                                           0x0a
 	__u8  family;
 	__u8  pad06[2];
 	__u64 ram_size;
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index 982aad8fa645..e6e9537537cf 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -39,6 +39,7 @@
 #define KEPLER_CHANNEL_GPFIFO_A                       /* cla06f.h */ 0x0000a06f
 #define KEPLER_CHANNEL_GPFIFO_B                       /* cla06f.h */ 0x0000a16f
 #define MAXWELL_CHANNEL_GPFIFO_A                      /* cla06f.h */ 0x0000b06f
+#define PASCAL_CHANNEL_GPFIFO_A                       /* cla06f.h */ 0x0000c06f
 
 #define NV50_DISP                                     /* cl5070.h */ 0x00005070
 #define G82_DISP                                      /* cl5070.h */ 0x00008270
@@ -50,6 +51,8 @@
 #define GK110_DISP                                    /* cl5070.h */ 0x00009270
 #define GM107_DISP                                    /* cl5070.h */ 0x00009470
 #define GM200_DISP                                    /* cl5070.h */ 0x00009570
+#define GP100_DISP                                    /* cl5070.h */ 0x00009770
+#define GP104_DISP                                    /* cl5070.h */ 0x00009870
 
 #define NV31_MPEG                                                    0x00003174
 #define G82_MPEG                                                     0x00008274
@@ -86,6 +89,8 @@
 #define GK110_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000927d
 #define GM107_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000947d
 #define GM200_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000957d
+#define GP100_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000977d
+#define GP104_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000987d
 
 #define NV50_DISP_OVERLAY_CHANNEL_DMA                 /* cl507e.h */ 0x0000507e
 #define G82_DISP_OVERLAY_CHANNEL_DMA                  /* cl507e.h */ 0x0000827e
@@ -105,6 +110,8 @@
 #define MAXWELL_A                                     /* cl9097.h */ 0x0000b097
 #define MAXWELL_B                                     /* cl9097.h */ 0x0000b197
 
+#define PASCAL_A                                      /* cl9097.h */ 0x0000c097
+
 #define NV74_BSP                                                     0x000074b0
 
 #define GT212_MSVLD                                                  0x000085b1
@@ -128,6 +135,8 @@
 #define FERMI_DMA                                                    0x000090b5
 #define KEPLER_DMA_COPY_A                                            0x0000a0b5
 #define MAXWELL_DMA_COPY_A                                           0x0000b0b5
+#define PASCAL_DMA_COPY_A                                            0x0000c0b5
+#define PASCAL_DMA_COPY_B                                            0x0000c1b5
 
 #define FERMI_DECOMPRESS                                             0x000090b8
 
@@ -137,6 +146,7 @@
 #define KEPLER_COMPUTE_B                                             0x0000a1c0
 #define MAXWELL_COMPUTE_A                                            0x0000b0c0
 #define MAXWELL_COMPUTE_B                                            0x0000b1c0
+#define PASCAL_COMPUTE_A                                             0x0000c0c0
 
 #define NV74_CIPHER                                                  0x000074c1
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index 126a85cc81bc..7ea8aa7ca408 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -33,7 +33,10 @@ enum nvkm_devidx {
 	NVKM_ENGINE_CE0,
 	NVKM_ENGINE_CE1,
 	NVKM_ENGINE_CE2,
-	NVKM_ENGINE_CE_LAST = NVKM_ENGINE_CE2,
+	NVKM_ENGINE_CE3,
+	NVKM_ENGINE_CE4,
+	NVKM_ENGINE_CE5,
+	NVKM_ENGINE_CE_LAST = NVKM_ENGINE_CE5,
 
 	NVKM_ENGINE_CIPHER,
 	NVKM_ENGINE_DISP,
@@ -50,7 +53,8 @@ enum nvkm_devidx {
 
 	NVKM_ENGINE_NVENC0,
 	NVKM_ENGINE_NVENC1,
-	NVKM_ENGINE_NVENC_LAST = NVKM_ENGINE_NVENC1,
+	NVKM_ENGINE_NVENC2,
+	NVKM_ENGINE_NVENC_LAST = NVKM_ENGINE_NVENC2,
 
 	NVKM_ENGINE_NVDEC,
 	NVKM_ENGINE_PM,
@@ -102,6 +106,7 @@ struct nvkm_device {
 		NV_C0    = 0xc0,
 		NV_E0    = 0xe0,
 		GM100    = 0x110,
+		GP100    = 0x130,
 	} card_type;
 	u32 chipset;
 	u8  chiprev;
@@ -136,7 +141,7 @@ struct nvkm_device {
 	struct nvkm_volt *volt;
 
 	struct nvkm_engine *bsp;
-	struct nvkm_engine *ce[3];
+	struct nvkm_engine *ce[6];
 	struct nvkm_engine *cipher;
 	struct nvkm_disp *disp;
 	struct nvkm_dma *dma;
@@ -149,7 +154,7 @@ struct nvkm_device {
 	struct nvkm_engine *mspdec;
 	struct nvkm_engine *msppp;
 	struct nvkm_engine *msvld;
-	struct nvkm_engine *nvenc[2];
+	struct nvkm_engine *nvenc[3];
 	struct nvkm_engine *nvdec;
 	struct nvkm_pm *pm;
 	struct nvkm_engine *sec;
@@ -170,7 +175,6 @@ struct nvkm_device_func {
 	void (*fini)(struct nvkm_device *, bool suspend);
 	resource_size_t (*resource_addr)(struct nvkm_device *, unsigned bar);
 	resource_size_t (*resource_size)(struct nvkm_device *, unsigned bar);
-	bool cpu_coherent;
 };
 
 struct nvkm_device_quirk {
@@ -206,7 +210,7 @@ struct nvkm_device_chip {
 	int (*volt    )(struct nvkm_device *, int idx, struct nvkm_volt **);
 
 	int (*bsp     )(struct nvkm_device *, int idx, struct nvkm_engine **);
-	int (*ce[3]   )(struct nvkm_device *, int idx, struct nvkm_engine **);
+	int (*ce[6]   )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*cipher  )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*disp    )(struct nvkm_device *, int idx, struct nvkm_disp **);
 	int (*dma     )(struct nvkm_device *, int idx, struct nvkm_dma **);
@@ -219,7 +223,7 @@ struct nvkm_device_chip {
 	int (*mspdec  )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*msppp   )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*msvld   )(struct nvkm_device *, int idx, struct nvkm_engine **);
-	int (*nvenc[2])(struct nvkm_device *, int idx, struct nvkm_engine **);
+	int (*nvenc[3])(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*nvdec   )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*pm      )(struct nvkm_device *, int idx, struct nvkm_pm **);
 	int (*sec     )(struct nvkm_device *, int idx, struct nvkm_engine **);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/tegra.h b/drivers/gpu/drm/nouveau/include/nvkm/core/tegra.h
index b5370cb56e3c..e5c9b6268dcc 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/tegra.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/tegra.h
@@ -28,6 +28,7 @@ struct nvkm_device_tegra {
 	} iommu;
 
 	int gpu_speedo;
+	int gpu_speedo_id;
 };
 
 struct nvkm_device_tegra_func {
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/ce.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/ce.h
index 594d719ba41e..d3d26a1e215d 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/ce.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/ce.h
@@ -7,4 +7,6 @@ int gf100_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
 int gk104_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
 int gm107_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
 int gm200_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
+int gp100_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
+int gp104_ce_new(struct nvkm_device *, int, struct nvkm_engine **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
index d4fdce27b297..e82049667ce4 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
@@ -32,4 +32,6 @@ int gk104_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int gk110_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int gm107_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int gm200_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
+int gp100_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
+int gp104_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h
index 15ddfcf5e8db..ed92fec5292c 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h
@@ -66,4 +66,5 @@ int gk20a_fifo_new(struct nvkm_device *, int, struct nvkm_fifo **);
 int gm107_fifo_new(struct nvkm_device *, int, struct nvkm_fifo **);
 int gm200_fifo_new(struct nvkm_device *, int, struct nvkm_fifo **);
 int gm20b_fifo_new(struct nvkm_device *, int, struct nvkm_fifo **);
+int gp100_fifo_new(struct nvkm_device *, int, struct nvkm_fifo **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
index 6515f5810a26..89cf99307828 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
@@ -42,4 +42,5 @@ int gk20a_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gm107_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gm200_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gm20b_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
+int gp100_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios.h
index e39a1fea930b..a72f3290528a 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios.h
@@ -7,6 +7,9 @@ struct nvkm_bios {
 	u32 size;
 	u8 *data;
 
+	u32 image0_size;
+	u32 imaged_addr;
+
 	u32 bmp_offset;
 	u32 bit_offset;
 
@@ -22,10 +25,9 @@ struct nvkm_bios {
 u8  nvbios_checksum(const u8 *data, int size);
 u16 nvbios_findstr(const u8 *data, int size, const char *str, int len);
 int nvbios_memcmp(struct nvkm_bios *, u32 addr, const char *, u32 len);
-
-#define nvbios_rd08(b,o) (b)->data[(o)]
-#define nvbios_rd16(b,o) get_unaligned_le16(&(b)->data[(o)])
-#define nvbios_rd32(b,o) get_unaligned_le32(&(b)->data[(o)])
+u8  nvbios_rd08(struct nvkm_bios *, u32 addr);
+u16 nvbios_rd16(struct nvkm_bios *, u32 addr);
+u32 nvbios_rd32(struct nvkm_bios *, u32 addr);
 
 int nvkm_bios_new(struct nvkm_device *, int, struct nvkm_bios **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
index 0a734fd06acf..3a410275fa71 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
@@ -56,6 +56,8 @@ struct nvkm_fb {
 		int regions;
 	} tile;
 
+	u8 page;
+
 	struct nvkm_memory *mmu_rd;
 	struct nvkm_memory *mmu_wr;
 };
@@ -91,6 +93,8 @@ int gk104_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gk20a_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gm107_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gm200_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int gp100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int gp104_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 
 #include <subdev/bios.h>
 #include <subdev/bios/ramcfg.h>
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
index c6b90b6543b3..cd755baf9cab 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
@@ -38,4 +38,5 @@ int gk104_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gk20a_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gm107_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gm200_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
+int gp100_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
index 2e80682b2da1..27d25b18d85c 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
@@ -7,11 +7,14 @@ struct nvkm_mc {
 	struct nvkm_subdev subdev;
 };
 
-void nvkm_mc_intr(struct nvkm_mc *, bool *handled);
-void nvkm_mc_intr_unarm(struct nvkm_mc *);
-void nvkm_mc_intr_rearm(struct nvkm_mc *);
-void nvkm_mc_reset(struct nvkm_mc *, enum nvkm_devidx);
-void nvkm_mc_unk260(struct nvkm_mc *, u32 data);
+void nvkm_mc_enable(struct nvkm_device *, enum nvkm_devidx);
+void nvkm_mc_disable(struct nvkm_device *, enum nvkm_devidx);
+void nvkm_mc_reset(struct nvkm_device *, enum nvkm_devidx);
+void nvkm_mc_intr(struct nvkm_device *, bool *handled);
+void nvkm_mc_intr_unarm(struct nvkm_device *);
+void nvkm_mc_intr_rearm(struct nvkm_device *);
+void nvkm_mc_intr_mask(struct nvkm_device *, enum nvkm_devidx, bool enable);
+void nvkm_mc_unk260(struct nvkm_device *, u32 data);
 
 int nv04_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 int nv11_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
@@ -24,4 +27,5 @@ int gt215_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 int gf100_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 int gk104_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 int gk20a_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
+int gp100_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/pci.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/pci.h
index ddb913889d7e..e6523e2cea9f 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/pci.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/pci.h
@@ -47,6 +47,7 @@ int g94_pci_new(struct nvkm_device *, int, struct nvkm_pci **);
 int gf100_pci_new(struct nvkm_device *, int, struct nvkm_pci **);
 int gf106_pci_new(struct nvkm_device *, int, struct nvkm_pci **);
 int gk104_pci_new(struct nvkm_device *, int, struct nvkm_pci **);
+int gp100_pci_new(struct nvkm_device *, int, struct nvkm_pci **);
 
 /* pcie functions */
 int nvkm_pcie_set_link(struct nvkm_pci *, enum nvkm_pcie_speed, u8 width);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h
index c6edd95a5b69..b04c38c07761 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h
@@ -43,9 +43,8 @@ struct nvkm_secboot {
 	const struct nvkm_secboot_func *func;
 	struct nvkm_subdev subdev;
 
+	enum nvkm_devidx devidx;
 	u32 base;
-	u32 irq_mask;
-	u32 enable_mask;
 };
 #define nvkm_secboot(p) container_of((p), struct nvkm_secboot, subdev)
 
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/top.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/top.h
index 8fb575a92c48..71ebbfd4484f 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/top.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/top.h
@@ -8,10 +8,11 @@ struct nvkm_top {
 	struct list_head device;
 };
 
-u32 nvkm_top_reset(struct nvkm_top *, enum nvkm_devidx);
-u32 nvkm_top_intr(struct nvkm_top *, u32 intr, u64 *subdevs);
-enum nvkm_devidx nvkm_top_fault(struct nvkm_top *, int fault);
-enum nvkm_devidx nvkm_top_engine(struct nvkm_top *, int, int *runl, int *engn);
+u32 nvkm_top_reset(struct nvkm_device *, enum nvkm_devidx);
+u32 nvkm_top_intr(struct nvkm_device *, u32 intr, u64 *subdevs);
+u32 nvkm_top_intr_mask(struct nvkm_device *, enum nvkm_devidx);
+enum nvkm_devidx nvkm_top_fault(struct nvkm_device *, int fault);
+enum nvkm_devidx nvkm_top_engine(struct nvkm_device *, int, int *runl, int *engn);
 
 int gk104_top_new(struct nvkm_device *, int, struct nvkm_top **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/volt.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/volt.h
index feff55cff05b..b765f4ffcde6 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/volt.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/volt.h
@@ -12,6 +12,9 @@ struct nvkm_volt {
 		u32 uv;
 		u8 vid;
 	} vid[256];
+
+	u32 max_uv;
+	u32 min_uv;
 };
 
 int nvkm_volt_get(struct nvkm_volt *);
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index eb7de487a2b3..7bd4683216d0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -100,6 +100,7 @@ nouveau_abi16_swclass(struct nouveau_drm *drm)
 	case NV_DEVICE_INFO_V0_FERMI:
 	case NV_DEVICE_INFO_V0_KEPLER:
 	case NV_DEVICE_INFO_V0_MAXWELL:
+	case NV_DEVICE_INFO_V0_PASCAL:
 		return NVIF_CLASS_SW_GF100;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index db76b94e6e26..f2ad17aa33f0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -45,6 +45,8 @@
 static struct nouveau_dsm_priv {
 	bool dsm_detected;
 	bool optimus_detected;
+	bool optimus_flags_detected;
+	bool optimus_skip_dsm;
 	acpi_handle dhandle;
 	acpi_handle rom_handle;
 } nouveau_dsm_priv;
@@ -57,9 +59,6 @@ bool nouveau_is_v1_dsm(void) {
 	return nouveau_dsm_priv.dsm_detected;
 }
 
-#define NOUVEAU_DSM_HAS_MUX 0x1
-#define NOUVEAU_DSM_HAS_OPT 0x2
-
 #ifdef CONFIG_VGA_SWITCHEROO
 static const char nouveau_dsm_muid[] = {
 	0xA0, 0xA0, 0x95, 0x9D, 0x60, 0x00, 0x48, 0x4D,
@@ -110,7 +109,7 @@ static int nouveau_optimus_dsm(acpi_handle handle, int func, int arg, uint32_t *
  * requirements on the fourth parameter, so a private implementation
  * instead of using acpi_check_dsm().
  */
-static int nouveau_check_optimus_dsm(acpi_handle handle)
+static int nouveau_dsm_get_optimus_functions(acpi_handle handle)
 {
 	int result;
 
@@ -125,7 +124,9 @@ static int nouveau_check_optimus_dsm(acpi_handle handle)
 	 * ACPI Spec v4 9.14.1: if bit 0 is zero, no function is supported.
 	 * If the n-th bit is enabled, function n is supported
 	 */
-	return result & 1 && result & (1 << NOUVEAU_DSM_OPTIMUS_CAPS);
+	if (result & 1 && result & (1 << NOUVEAU_DSM_OPTIMUS_CAPS))
+		return result;
+	return 0;
 }
 
 static int nouveau_dsm(acpi_handle handle, int func, int arg)
@@ -212,26 +213,55 @@ static const struct vga_switcheroo_handler nouveau_dsm_handler = {
 	.get_client_id = nouveau_dsm_get_client_id,
 };
 
-static int nouveau_dsm_pci_probe(struct pci_dev *pdev)
+/*
+ * Firmware supporting Windows 8 or later do not use _DSM to put the device into
+ * D3cold, they instead rely on disabling power resources on the parent.
+ */
+static bool nouveau_pr3_present(struct pci_dev *pdev)
+{
+	struct pci_dev *parent_pdev = pci_upstream_bridge(pdev);
+	struct acpi_device *parent_adev;
+
+	if (!parent_pdev)
+		return false;
+
+	parent_adev = ACPI_COMPANION(&parent_pdev->dev);
+	if (!parent_adev)
+		return false;
+
+	return acpi_has_method(parent_adev->handle, "_PR3");
+}
+
+static void nouveau_dsm_pci_probe(struct pci_dev *pdev, acpi_handle *dhandle_out,
+				  bool *has_mux, bool *has_opt,
+				  bool *has_opt_flags, bool *has_pr3)
 {
 	acpi_handle dhandle;
-	int retval = 0;
+	bool supports_mux;
+	int optimus_funcs;
 
 	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
-		return false;
+		return;
 
 	if (!acpi_has_method(dhandle, "_DSM"))
-		return false;
+		return;
+
+	supports_mux = acpi_check_dsm(dhandle, nouveau_dsm_muid, 0x00000102,
+				      1 << NOUVEAU_DSM_POWER);
+	optimus_funcs = nouveau_dsm_get_optimus_functions(dhandle);
 
-	if (acpi_check_dsm(dhandle, nouveau_dsm_muid, 0x00000102,
-			   1 << NOUVEAU_DSM_POWER))
-		retval |= NOUVEAU_DSM_HAS_MUX;
+	/* Does not look like a Nvidia device. */
+	if (!supports_mux && !optimus_funcs)
+		return;
 
-	if (nouveau_check_optimus_dsm(dhandle))
-		retval |= NOUVEAU_DSM_HAS_OPT;
+	*dhandle_out = dhandle;
+	*has_mux = supports_mux;
+	*has_opt = !!optimus_funcs;
+	*has_opt_flags = optimus_funcs & (1 << NOUVEAU_DSM_OPTIMUS_FLAGS);
+	*has_pr3 = false;
 
-	if (retval & NOUVEAU_DSM_HAS_OPT) {
+	if (optimus_funcs) {
 		uint32_t result;
 		nouveau_optimus_dsm(dhandle, NOUVEAU_DSM_OPTIMUS_CAPS, 0,
 				    &result);
@@ -239,11 +269,9 @@ static int nouveau_dsm_pci_probe(struct pci_dev *pdev)
 			 (result & OPTIMUS_ENABLED) ? "enabled" : "disabled",
 			 (result & OPTIMUS_DYNAMIC_PWR_CAP) ? "dynamic power, " : "",
 			 (result & OPTIMUS_HDA_CODEC_MASK) ? "hda bios codec supported" : "");
-	}
-	if (retval)
-		nouveau_dsm_priv.dhandle = dhandle;
 
-	return retval;
+		*has_pr3 = nouveau_pr3_present(pdev);
+	}
 }
 
 static bool nouveau_dsm_detect(void)
@@ -251,11 +279,13 @@ static bool nouveau_dsm_detect(void)
 	char acpi_method_name[255] = { 0 };
 	struct acpi_buffer buffer = {sizeof(acpi_method_name), acpi_method_name};
 	struct pci_dev *pdev = NULL;
-	int has_dsm = 0;
-	int has_optimus = 0;
+	acpi_handle dhandle = NULL;
+	bool has_mux = false;
+	bool has_optimus = false;
+	bool has_optimus_flags = false;
+	bool has_power_resources = false;
 	int vga_count = 0;
 	bool guid_valid;
-	int retval;
 	bool ret = false;
 
 	/* lookup the MXM GUID */
@@ -268,32 +298,32 @@ static bool nouveau_dsm_detect(void)
 	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
 		vga_count++;
 
-		retval = nouveau_dsm_pci_probe(pdev);
-		if (retval & NOUVEAU_DSM_HAS_MUX)
-			has_dsm |= 1;
-		if (retval & NOUVEAU_DSM_HAS_OPT)
-			has_optimus = 1;
+		nouveau_dsm_pci_probe(pdev, &dhandle, &has_mux, &has_optimus,
+				      &has_optimus_flags, &has_power_resources);
 	}
 
 	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_3D << 8, pdev)) != NULL) {
 		vga_count++;
 
-		retval = nouveau_dsm_pci_probe(pdev);
-		if (retval & NOUVEAU_DSM_HAS_MUX)
-			has_dsm |= 1;
-		if (retval & NOUVEAU_DSM_HAS_OPT)
-			has_optimus = 1;
+		nouveau_dsm_pci_probe(pdev, &dhandle, &has_mux, &has_optimus,
+				      &has_optimus_flags, &has_power_resources);
 	}
 
 	/* find the optimus DSM or the old v1 DSM */
-	if (has_optimus == 1) {
+	if (has_optimus) {
+		nouveau_dsm_priv.dhandle = dhandle;
 		acpi_get_name(nouveau_dsm_priv.dhandle, ACPI_FULL_PATHNAME,
 			&buffer);
 		printk(KERN_INFO "VGA switcheroo: detected Optimus DSM method %s handle\n",
 			acpi_method_name);
+		if (has_power_resources)
+			pr_info("nouveau: detected PR support, will not use DSM\n");
 		nouveau_dsm_priv.optimus_detected = true;
+		nouveau_dsm_priv.optimus_flags_detected = has_optimus_flags;
+		nouveau_dsm_priv.optimus_skip_dsm = has_power_resources;
 		ret = true;
-	} else if (vga_count == 2 && has_dsm && guid_valid) {
+	} else if (vga_count == 2 && has_mux && guid_valid) {
+		nouveau_dsm_priv.dhandle = dhandle;
 		acpi_get_name(nouveau_dsm_priv.dhandle, ACPI_FULL_PATHNAME,
 			&buffer);
 		printk(KERN_INFO "VGA switcheroo: detected DSM switching method %s handle\n",
@@ -321,11 +351,12 @@ void nouveau_register_dsm_handler(void)
 void nouveau_switcheroo_optimus_dsm(void)
 {
 	u32 result = 0;
-	if (!nouveau_dsm_priv.optimus_detected)
+	if (!nouveau_dsm_priv.optimus_detected || nouveau_dsm_priv.optimus_skip_dsm)
 		return;
 
-	nouveau_optimus_dsm(nouveau_dsm_priv.dhandle, NOUVEAU_DSM_OPTIMUS_FLAGS,
-			    0x3, &result);
+	if (nouveau_dsm_priv.optimus_flags_detected)
+		nouveau_optimus_dsm(nouveau_dsm_priv.dhandle, NOUVEAU_DSM_OPTIMUS_FLAGS,
+				    0x3, &result);
 
 	nouveau_optimus_dsm(nouveau_dsm_priv.dhandle, NOUVEAU_DSM_OPTIMUS_CAPS,
 		NOUVEAU_DSM_OPTIMUS_SET_POWERDOWN, &result);
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 5e3f3e826476..528bdeffb339 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -209,8 +209,7 @@ nouveau_bo_new(struct drm_device *dev, int size, int align,
 	nvbo->tile_flags = tile_flags;
 	nvbo->bo.bdev = &drm->ttm.bdev;
 
-	if (!nvxx_device(&drm->device)->func->cpu_coherent)
-		nvbo->force_coherent = flags & TTM_PL_FLAG_UNCACHED;
+	nvbo->force_coherent = flags & TTM_PL_FLAG_UNCACHED;
 
 	nvbo->page_shift = 12;
 	if (drm->client.vm) {
@@ -424,13 +423,7 @@ nouveau_bo_map(struct nouveau_bo *nvbo)
 	if (ret)
 		return ret;
 
-	/*
-	 * TTM buffers allocated using the DMA API already have a mapping, let's
-	 * use it instead.
-	 */
-	if (!nvbo->force_coherent)
-		ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.mem.num_pages,
-				  &nvbo->kmap);
+	ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.mem.num_pages, &nvbo->kmap);
 
 	ttm_bo_unreserve(&nvbo->bo);
 	return ret;
@@ -442,12 +435,7 @@ nouveau_bo_unmap(struct nouveau_bo *nvbo)
 	if (!nvbo)
 		return;
 
-	/*
-	 * TTM buffers allocated using the DMA API already had a coherent
-	 * mapping which we used, no need to unmap.
-	 */
-	if (!nvbo->force_coherent)
-		ttm_bo_kunmap(&nvbo->kmap);
+	ttm_bo_kunmap(&nvbo->kmap);
 }
 
 void
@@ -506,35 +494,13 @@ nouveau_bo_validate(struct nouveau_bo *nvbo, bool interruptible,
 	return 0;
 }
 
-static inline void *
-_nouveau_bo_mem_index(struct nouveau_bo *nvbo, unsigned index, void *mem, u8 sz)
-{
-	struct ttm_dma_tt *dma_tt;
-	u8 *m = mem;
-
-	index *= sz;
-
-	if (m) {
-		/* kmap'd address, return the corresponding offset */
-		m += index;
-	} else {
-		/* DMA-API mapping, lookup the right address */
-		dma_tt = (struct ttm_dma_tt *)nvbo->bo.ttm;
-		m = dma_tt->cpu_address[index / PAGE_SIZE];
-		m += index % PAGE_SIZE;
-	}
-
-	return m;
-}
-#define nouveau_bo_mem_index(o, i, m) _nouveau_bo_mem_index(o, i, m, sizeof(*m))
-
 void
 nouveau_bo_wr16(struct nouveau_bo *nvbo, unsigned index, u16 val)
 {
 	bool is_iomem;
 	u16 *mem = ttm_kmap_obj_virtual(&nvbo->kmap, &is_iomem);
 
-	mem = nouveau_bo_mem_index(nvbo, index, mem);
+	mem += index;
 
 	if (is_iomem)
 		iowrite16_native(val, (void __force __iomem *)mem);
@@ -548,7 +514,7 @@ nouveau_bo_rd32(struct nouveau_bo *nvbo, unsigned index)
 	bool is_iomem;
 	u32 *mem = ttm_kmap_obj_virtual(&nvbo->kmap, &is_iomem);
 
-	mem = nouveau_bo_mem_index(nvbo, index, mem);
+	mem += index;
 
 	if (is_iomem)
 		return ioread32_native((void __force __iomem *)mem);
@@ -562,7 +528,7 @@ nouveau_bo_wr32(struct nouveau_bo *nvbo, unsigned index, u32 val)
 	bool is_iomem;
 	u32 *mem = ttm_kmap_obj_virtual(&nvbo->kmap, &is_iomem);
 
-	mem = nouveau_bo_mem_index(nvbo, index, mem);
+	mem += index;
 
 	if (is_iomem)
 		iowrite32_native(val, (void __force __iomem *)mem);
@@ -1082,7 +1048,6 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
 				ret = ttm_bo_move_accel_cleanup(bo,
 								&fence->base,
 								evict,
-								no_wait_gpu,
 								new_mem);
 				nouveau_fence_unref(&fence);
 			}
@@ -1104,6 +1069,10 @@ nouveau_bo_move_init(struct nouveau_drm *drm)
 			    struct ttm_mem_reg *, struct ttm_mem_reg *);
 		int (*init)(struct nouveau_channel *, u32 handle);
 	} _methods[] = {
+		{  "COPY", 4, 0xc1b5, nve0_bo_move_copy, nve0_bo_move_init },
+		{  "GRCE", 0, 0xc1b5, nve0_bo_move_copy, nvc0_bo_move_init },
+		{  "COPY", 4, 0xc0b5, nve0_bo_move_copy, nve0_bo_move_init },
+		{  "GRCE", 0, 0xc0b5, nve0_bo_move_copy, nvc0_bo_move_init },
 		{  "COPY", 4, 0xb0b5, nve0_bo_move_copy, nve0_bo_move_init },
 		{  "GRCE", 0, 0xb0b5, nve0_bo_move_copy, nvc0_bo_move_init },
 		{  "COPY", 4, 0xa0b5, nve0_bo_move_copy, nve0_bo_move_init },
@@ -1289,6 +1258,10 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, bool intr,
 	struct nouveau_drm_tile *new_tile = NULL;
 	int ret = 0;
 
+	ret = ttm_bo_wait(bo, intr, no_wait_gpu);
+	if (ret)
+		return ret;
+
 	if (nvbo->pin_refcnt)
 		NV_WARN(drm, "Moving pinned object %p!\n", nvbo);
 
@@ -1324,7 +1297,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, bool intr,
 	/* Fallback to software copy. */
 	ret = ttm_bo_wait(bo, intr, no_wait_gpu);
 	if (ret == 0)
-		ret = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
+		ret = ttm_bo_move_memcpy(bo, evict, intr, no_wait_gpu, new_mem);
 
 out:
 	if (drm->device.info.family < NV_DEVICE_INFO_V0_TESLA) {
@@ -1488,14 +1461,6 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm)
 	dev = drm->dev;
 	pdev = device->dev;
 
-	/*
-	 * Objects matching this condition have been marked as force_coherent,
-	 * so use the DMA API for them.
-	 */
-	if (!nvxx_device(&drm->device)->func->cpu_coherent &&
-	    ttm->caching_state == tt_uncached)
-		return ttm_dma_populate(ttm_dma, dev->dev);
-
 #if IS_ENABLED(CONFIG_AGP)
 	if (drm->agp.bridge) {
 		return ttm_agp_tt_populate(ttm);
@@ -1553,16 +1518,6 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	dev = drm->dev;
 	pdev = device->dev;
 
-	/*
-	 * Objects matching this condition have been marked as force_coherent,
-	 * so use the DMA API for them.
-	 */
-	if (!nvxx_device(&drm->device)->func->cpu_coherent &&
-	    ttm->caching_state == tt_uncached) {
-		ttm_dma_unpopulate(ttm_dma, dev->dev);
-		return;
-	}
-
 #if IS_ENABLED(CONFIG_AGP)
 	if (drm->agp.bridge) {
 		ttm_agp_tt_unpopulate(ttm);
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c
index b1d2527c5625..f9b3c811187e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.c
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.c
@@ -191,7 +191,8 @@ static int
 nouveau_channel_ind(struct nouveau_drm *drm, struct nvif_device *device,
 		    u32 engine, struct nouveau_channel **pchan)
 {
-	static const u16 oclasses[] = { MAXWELL_CHANNEL_GPFIFO_A,
+	static const u16 oclasses[] = { PASCAL_CHANNEL_GPFIFO_A,
+					MAXWELL_CHANNEL_GPFIFO_A,
 					KEPLER_CHANNEL_GPFIFO_B,
 					KEPLER_CHANNEL_GPFIFO_A,
 					FERMI_CHANNEL_GPFIFO,
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 7c77f960c8b8..afbf557b23d4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -47,7 +47,7 @@ nouveau_display_vblank_handler(struct nvif_notify *notify)
 {
 	struct nouveau_crtc *nv_crtc =
 		container_of(notify, typeof(*nv_crtc), vblank);
-	drm_handle_vblank(nv_crtc->base.dev, nv_crtc->index);
+	drm_crtc_handle_vblank(&nv_crtc->base);
 	return NVIF_NOTIFY_KEEP;
 }
 
@@ -495,6 +495,8 @@ nouveau_display_create(struct drm_device *dev)
 
 	if (nouveau_modeset != 2 && drm->vbios.dcb.entries) {
 		static const u16 oclass[] = {
+			GP104_DISP,
+			GP100_DISP,
 			GM200_DISP,
 			GM107_DISP,
 			GK110_DISP,
@@ -554,6 +556,7 @@ nouveau_display_destroy(struct drm_device *dev)
 	nouveau_display_vblank_fini(dev);
 
 	drm_kms_helper_poll_fini(dev);
+	drm_crtc_force_disable_all(dev);
 	drm_mode_config_cleanup(dev);
 
 	if (disp->dtor)
@@ -760,12 +763,11 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 
 	/* Initialize a page flip struct */
 	*s = (struct nouveau_page_flip_state)
-		{ { }, event, nouveau_crtc(crtc)->index,
-		  fb->bits_per_pixel, fb->pitches[0], crtc->x, crtc->y,
+		{ { }, event, crtc, fb->bits_per_pixel, fb->pitches[0],
 		  new_bo->bo.offset };
 
 	/* Keep vblanks on during flip, for the target crtc of this flip */
-	drm_vblank_get(dev, nouveau_crtc(crtc)->index);
+	drm_crtc_vblank_get(crtc);
 
 	/* Emit a page flip */
 	if (drm->device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
@@ -810,7 +812,7 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	return 0;
 
 fail_unreserve:
-	drm_vblank_put(dev, nouveau_crtc(crtc)->index);
+	drm_crtc_vblank_put(crtc);
 	ttm_bo_unreserve(&old_bo->bo);
 fail_unpin:
 	mutex_unlock(&cli->mutex);
@@ -842,17 +844,17 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 	s = list_first_entry(&fctx->flip, struct nouveau_page_flip_state, head);
 	if (s->event) {
 		if (drm->device.info.family < NV_DEVICE_INFO_V0_TESLA) {
-			drm_arm_vblank_event(dev, s->crtc, s->event);
+			drm_crtc_arm_vblank_event(s->crtc, s->event);
 		} else {
-			drm_send_vblank_event(dev, s->crtc, s->event);
+			drm_crtc_send_vblank_event(s->crtc, s->event);
 
 			/* Give up ownership of vblank for page-flipped crtc */
-			drm_vblank_put(dev, s->crtc);
+			drm_crtc_vblank_put(s->crtc);
 		}
 	}
 	else {
 		/* Give up ownership of vblank for page-flipped crtc */
-		drm_vblank_put(dev, s->crtc);
+		drm_crtc_vblank_put(s->crtc);
 	}
 
 	list_del(&s->head);
@@ -873,9 +875,10 @@ nouveau_flip_complete(struct nvif_notify *notify)
 
 	if (!nouveau_finish_page_flip(chan, &state)) {
 		if (drm->device.info.family < NV_DEVICE_INFO_V0_TESLA) {
-			nv_set_crtc_base(drm->dev, state.crtc, state.offset +
-					 state.y * state.pitch +
-					 state.x * state.bpp / 8);
+			nv_set_crtc_base(drm->dev, drm_crtc_index(state.crtc),
+					 state.offset + state.crtc->y *
+					 state.pitch + state.crtc->x *
+					 state.bpp / 8);
 		}
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.h b/drivers/gpu/drm/nouveau/nouveau_display.h
index 24273bacd885..0420ee861ea4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.h
+++ b/drivers/gpu/drm/nouveau/nouveau_display.h
@@ -28,7 +28,8 @@ int nouveau_framebuffer_init(struct drm_device *, struct nouveau_framebuffer *,
 struct nouveau_page_flip_state {
 	struct list_head head;
 	struct drm_pending_vblank_event *event;
-	int crtc, bpp, pitch, x, y;
+	struct drm_crtc *crtc;
+	int bpp, pitch;
 	u64 offset;
 };
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 11f8dd9c0edb..66c1280c0f1f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -22,13 +22,11 @@
  * Authors: Ben Skeggs
  */
 
-#include <linux/apple-gmux.h>
 #include <linux/console.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
-#include <linux/vgaarb.h>
 #include <linux/vga_switcheroo.h>
 
 #include "drmP.h"
@@ -200,6 +198,7 @@ nouveau_accel_init(struct nouveau_drm *drm)
 		case KEPLER_CHANNEL_GPFIFO_A:
 		case KEPLER_CHANNEL_GPFIFO_B:
 		case MAXWELL_CHANNEL_GPFIFO_A:
+		case PASCAL_CHANNEL_GPFIFO_A:
 			ret = nvc0_fence_create(drm);
 			break;
 		default:
@@ -315,16 +314,19 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 	bool boot = false;
 	int ret;
 
-	/*
-	 * apple-gmux is needed on dual GPU MacBook Pro
-	 * to probe the panel if we're the inactive GPU.
-	 */
-	if (IS_ENABLED(CONFIG_VGA_ARB) && IS_ENABLED(CONFIG_VGA_SWITCHEROO) &&
-	    apple_gmux_present() && pdev != vga_default_device() &&
-	    !vga_switcheroo_handler_flags())
+	if (vga_switcheroo_client_probe_defer(pdev))
 		return -EPROBE_DEFER;
 
-	/* remove conflicting drivers (vesafb, efifb etc) */
+	/* We need to check that the chipset is supported before booting
+	 * fbdev off the hardware, as there's no way to put it back.
+	 */
+	ret = nvkm_device_pci_new(pdev, NULL, "error", true, false, 0, &device);
+	if (ret)
+		return ret;
+
+	nvkm_device_del(&device);
+
+	/* Remove conflicting drivers (vesafb, efifb etc). */
 	aper = alloc_apertures(3);
 	if (!aper)
 		return -ENOMEM;
@@ -438,6 +440,11 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 	nouveau_vga_init(drm);
 
 	if (drm->device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
+		if (!nvxx_device(&drm->device)->mmu) {
+			ret = -ENOSYS;
+			goto fail_device;
+		}
+
 		ret = nvkm_vm_new(nvxx_device(&drm->device), 0, (1ULL << 40),
 				  0x1000, NULL, &drm->client.vm);
 		if (ret)
@@ -498,7 +505,11 @@ nouveau_drm_unload(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
-	pm_runtime_get_sync(dev->dev);
+	if (nouveau_runtime_pm != 0) {
+		pm_runtime_get_sync(dev->dev);
+		pm_runtime_forbid(dev->dev);
+	}
+
 	nouveau_fbcon_fini(dev);
 	nouveau_accel_fini(drm);
 	nouveau_hwmon_fini(dev);
@@ -970,7 +981,7 @@ driver_stub = {
 	.gem_prime_vmap = nouveau_gem_prime_vmap,
 	.gem_prime_vunmap = nouveau_gem_prime_vunmap,
 
-	.gem_free_object = nouveau_gem_object_del,
+	.gem_free_object_unlocked = nouveau_gem_object_del,
 	.gem_open_object = nouveau_gem_object_open,
 	.gem_close_object = nouveau_gem_object_close,
 
@@ -1078,7 +1089,6 @@ nouveau_drm_init(void)
 	driver_pci = driver_stub;
 	driver_pci.set_busid = drm_pci_set_busid;
 	driver_platform = driver_stub;
-	driver_platform.set_busid = drm_platform_set_busid;
 
 	nouveau_display_options();
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 2e3a62d38fe9..64c4ce7115ad 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -57,7 +57,8 @@ struct nouveau_fence_priv {
 	int  (*context_new)(struct nouveau_channel *);
 	void (*context_del)(struct nouveau_channel *);
 
-	u32 contexts, context_base;
+	u32 contexts;
+	u64 context_base;
 	bool uevent;
 };
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_hwmon.c b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
index 1ff4166af26e..71f764bf4cc6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hwmon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
@@ -535,6 +535,40 @@ static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO,
 			  nouveau_hwmon_get_in0_input, NULL, 0);
 
 static ssize_t
+nouveau_hwmon_get_in0_min(struct device *d,
+			    struct device_attribute *a, char *buf)
+{
+	struct drm_device *dev = dev_get_drvdata(d);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_volt *volt = nvxx_volt(&drm->device);
+
+	if (!volt || !volt->min_uv)
+		return -ENODEV;
+
+	return sprintf(buf, "%i\n", volt->min_uv / 1000);
+}
+
+static SENSOR_DEVICE_ATTR(in0_min, S_IRUGO,
+			  nouveau_hwmon_get_in0_min, NULL, 0);
+
+static ssize_t
+nouveau_hwmon_get_in0_max(struct device *d,
+			    struct device_attribute *a, char *buf)
+{
+	struct drm_device *dev = dev_get_drvdata(d);
+	struct nouveau_drm *drm = nouveau_drm(dev);
+	struct nvkm_volt *volt = nvxx_volt(&drm->device);
+
+	if (!volt || !volt->max_uv)
+		return -ENODEV;
+
+	return sprintf(buf, "%i\n", volt->max_uv / 1000);
+}
+
+static SENSOR_DEVICE_ATTR(in0_max, S_IRUGO,
+			  nouveau_hwmon_get_in0_max, NULL, 0);
+
+static ssize_t
 nouveau_hwmon_get_in0_label(struct device *d,
 			    struct device_attribute *a, char *buf)
 {
@@ -594,6 +628,8 @@ static struct attribute *hwmon_pwm_fan_attributes[] = {
 
 static struct attribute *hwmon_in0_attributes[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
+	&sensor_dev_attr_in0_min.dev_attr.attr,
+	&sensor_dev_attr_in0_max.dev_attr.attr,
 	&sensor_dev_attr_in0_label.dev_attr.attr,
 	NULL
 };
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index bcee91497eb9..1825dbc33192 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -164,6 +164,7 @@ nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
 	case NV_DEVICE_INFO_V0_FERMI:
 	case NV_DEVICE_INFO_V0_KEPLER:
 	case NV_DEVICE_INFO_V0_MAXWELL:
+	case NV_DEVICE_INFO_V0_PASCAL:
 		node->memtype = (nvbo->tile_flags & 0xff00) >> 8;
 		break;
 	default:
diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c
index 675e9e077a95..08f9c6fa0f7f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_usif.c
+++ b/drivers/gpu/drm/nouveau/nouveau_usif.c
@@ -212,7 +212,6 @@ usif_notify_get(struct drm_file *f, void *data, u32 size, void *argv, u32 argc)
 	ntfy->p->base.event = &ntfy->p->e.base;
 	ntfy->p->base.file_priv = f;
 	ntfy->p->base.pid = current->pid;
-	ntfy->p->base.destroy =(void(*)(struct drm_pending_event *))kfree;
 	ntfy->p->e.base.type = DRM_NOUVEAU_EVENT_NVIF;
 	ntfy->p->e.base.length = sizeof(ntfy->p->e.base) + ntfy->reply;
 
diff --git a/drivers/gpu/drm/nouveau/nv04_fbcon.c b/drivers/gpu/drm/nouveau/nv04_fbcon.c
index 7d9248b8c664..da8fd5ff9d0f 100644
--- a/drivers/gpu/drm/nouveau/nv04_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv04_fbcon.c
@@ -107,11 +107,11 @@ nv04_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 			 ((image->dx + image->width) & 0xffff));
 	OUT_RING(chan, bg);
 	OUT_RING(chan, fg);
-	OUT_RING(chan, (image->height << 16) | image->width);
+	OUT_RING(chan, (image->height << 16) | ALIGN(image->width, 8));
 	OUT_RING(chan, (image->height << 16) | image->width);
 	OUT_RING(chan, (image->dy << 16) | (image->dx & 0xffff));
 
-	dsize = ALIGN(image->width * image->height, 32) >> 5;
+	dsize = ALIGN(ALIGN(image->width, 8) * image->height, 32) >> 5;
 	while (dsize) {
 		int iter_len = dsize > 128 ? 128 : dsize;
 
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 3ffc2b0057bf..7d0edcbcfca7 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -297,6 +297,8 @@ nv50_core_create(struct nvif_device *device, struct nvif_object *disp,
 		.pushbuf = 0xb0007d00,
 	};
 	static const s32 oclass[] = {
+		GP104_DISP_CORE_CHANNEL_DMA,
+		GP100_DISP_CORE_CHANNEL_DMA,
 		GM200_DISP_CORE_CHANNEL_DMA,
 		GM107_DISP_CORE_CHANNEL_DMA,
 		GK110_DISP_CORE_CHANNEL_DMA,
@@ -1346,21 +1348,22 @@ nv50_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 	return 0;
 }
 
-static void
+static int
 nv50_crtc_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
-		    uint32_t start, uint32_t size)
+		    uint32_t size)
 {
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
-	u32 end = min_t(u32, start + size, 256);
 	u32 i;
 
-	for (i = start; i < end; i++) {
+	for (i = 0; i < size; i++) {
 		nv_crtc->lut.r[i] = r[i];
 		nv_crtc->lut.g[i] = g[i];
 		nv_crtc->lut.b[i] = b[i];
 	}
 
 	nv50_crtc_lut_load(crtc);
+
+	return 0;
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/nv50_fbcon.c b/drivers/gpu/drm/nouveau/nv50_fbcon.c
index 1aeb698e9707..af3d3c49411a 100644
--- a/drivers/gpu/drm/nouveau/nv50_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv50_fbcon.c
@@ -125,7 +125,7 @@ nv50_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	OUT_RING(chan, 0);
 	OUT_RING(chan, image->dy);
 
-	dwords = ALIGN(image->width * image->height, 32) >> 5;
+	dwords = ALIGN(ALIGN(image->width, 8) * image->height, 32) >> 5;
 	while (dwords) {
 		int push = dwords > 2047 ? 2047 : dwords;
 
diff --git a/drivers/gpu/drm/nouveau/nvc0_fbcon.c b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
index 839f4c8c1805..054b6a056d99 100644
--- a/drivers/gpu/drm/nouveau/nvc0_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
@@ -125,7 +125,7 @@ nvc0_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
 	OUT_RING  (chan, 0);
 	OUT_RING  (chan, image->dy);
 
-	dwords = ALIGN(image->width * image->height, 32) >> 5;
+	dwords = ALIGN(ALIGN(image->width, 8) * image->height, 32) >> 5;
 	while (dwords) {
 		int push = dwords > 2047 ? 2047 : dwords;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/subdev.c b/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
index b18557858f19..19044aba265e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
@@ -57,6 +57,9 @@ nvkm_subdev_name[NVKM_SUBDEV_NR] = {
 	[NVKM_ENGINE_CE0     ] = "ce0",
 	[NVKM_ENGINE_CE1     ] = "ce1",
 	[NVKM_ENGINE_CE2     ] = "ce2",
+	[NVKM_ENGINE_CE3     ] = "ce3",
+	[NVKM_ENGINE_CE4     ] = "ce4",
+	[NVKM_ENGINE_CE5     ] = "ce5",
 	[NVKM_ENGINE_CIPHER  ] = "cipher",
 	[NVKM_ENGINE_DISP    ] = "disp",
 	[NVKM_ENGINE_DMAOBJ  ] = "dma",
@@ -71,6 +74,7 @@ nvkm_subdev_name[NVKM_SUBDEV_NR] = {
 	[NVKM_ENGINE_MSVLD   ] = "msvld",
 	[NVKM_ENGINE_NVENC0  ] = "nvenc0",
 	[NVKM_ENGINE_NVENC1  ] = "nvenc1",
+	[NVKM_ENGINE_NVENC2  ] = "nvenc2",
 	[NVKM_ENGINE_NVDEC   ] = "nvdec",
 	[NVKM_ENGINE_PM      ] = "pm",
 	[NVKM_ENGINE_SEC     ] = "sec",
@@ -105,7 +109,7 @@ nvkm_subdev_fini(struct nvkm_subdev *subdev, bool suspend)
 		}
 	}
 
-	nvkm_mc_reset(device->mc, subdev->index);
+	nvkm_mc_reset(device, subdev->index);
 
 	time = ktime_to_us(ktime_get()) - time;
 	nvkm_trace(subdev, "%s completed in %lldus\n", action, time);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild
index 9c19d59b47df..a4458a8eb30a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/Kbuild
@@ -3,3 +3,5 @@ nvkm-y += nvkm/engine/ce/gf100.o
 nvkm-y += nvkm/engine/ce/gk104.o
 nvkm-y += nvkm/engine/ce/gm107.o
 nvkm-y += nvkm/engine/ce/gm200.o
+nvkm-y += nvkm/engine/ce/gp100.o
+nvkm-y += nvkm/engine/ce/gp104.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/ce/gp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/ce/gp100.c
new file mode 100644
index 000000000000..c7710456bc30
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/gp100.c
@@ -0,0 +1,102 @@
+/*
+ * Copyright 2015 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#include "priv.h"
+#include <core/enum.h>
+
+#include <nvif/class.h>
+
+static const struct nvkm_enum
+gp100_ce_launcherr_report[] = {
+	{ 0x0, "NO_ERR" },
+	{ 0x1, "2D_LAYER_EXCEEDS_DEPTH" },
+	{ 0x2, "INVALID_ALIGNMENT" },
+	{ 0x3, "MEM2MEM_RECT_OUT_OF_BOUNDS" },
+	{ 0x4, "SRC_LINE_EXCEEDS_PITCH" },
+	{ 0x5, "SRC_LINE_EXCEEDS_NEG_PITCH" },
+	{ 0x6, "DST_LINE_EXCEEDS_PITCH" },
+	{ 0x7, "DST_LINE_EXCEEDS_NEG_PITCH" },
+	{ 0x8, "BAD_SRC_PIXEL_COMP_REF" },
+	{ 0x9, "INVALID_VALUE" },
+	{ 0xa, "UNUSED_FIELD" },
+	{ 0xb, "INVALID_OPERATION" },
+	{ 0xc, "NO_RESOURCES" },
+	{ 0xd, "INVALID_CONFIG" },
+	{}
+};
+
+static void
+gp100_ce_intr_launcherr(struct nvkm_engine *ce, const u32 base)
+{
+	struct nvkm_subdev *subdev = &ce->subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 stat = nvkm_rd32(device, 0x104418 + base);
+	const struct nvkm_enum *en =
+		nvkm_enum_find(gp100_ce_launcherr_report, stat & 0x0000000f);
+	nvkm_warn(subdev, "LAUNCHERR %08x [%s]\n", stat, en ? en->name : "");
+}
+
+void
+gp100_ce_intr(struct nvkm_engine *ce)
+{
+	const u32 base = (ce->subdev.index - NVKM_ENGINE_CE0) * 0x80;
+	struct nvkm_subdev *subdev = &ce->subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 mask = nvkm_rd32(device, 0x10440c + base);
+	u32 intr = nvkm_rd32(device, 0x104410 + base) & mask;
+	if (intr & 0x00000001) { //XXX: guess
+		nvkm_warn(subdev, "BLOCKPIPE\n");
+		nvkm_wr32(device, 0x104410 + base, 0x00000001);
+		intr &= ~0x00000001;
+	}
+	if (intr & 0x00000002) { //XXX: guess
+		nvkm_warn(subdev, "NONBLOCKPIPE\n");
+		nvkm_wr32(device, 0x104410 + base, 0x00000002);
+		intr &= ~0x00000002;
+	}
+	if (intr & 0x00000004) {
+		gp100_ce_intr_launcherr(ce, base);
+		nvkm_wr32(device, 0x104410 + base, 0x00000004);
+		intr &= ~0x00000004;
+	}
+	if (intr) {
+		nvkm_warn(subdev, "intr %08x\n", intr);
+		nvkm_wr32(device, 0x104410 + base, intr);
+	}
+}
+
+static const struct nvkm_engine_func
+gp100_ce = {
+	.intr = gp100_ce_intr,
+	.sclass = {
+		{ -1, -1, PASCAL_DMA_COPY_A },
+		{}
+	}
+};
+
+int
+gp100_ce_new(struct nvkm_device *device, int index,
+	     struct nvkm_engine **pengine)
+{
+	return nvkm_engine_new_(&gp100_ce, device, index, true, pengine);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/ce/gp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/ce/gp104.c
new file mode 100644
index 000000000000..20e019788a53
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/gp104.c
@@ -0,0 +1,44 @@
+/*
+ * Copyright 2015 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#include "priv.h"
+#include <core/enum.h>
+
+#include <nvif/class.h>
+
+static const struct nvkm_engine_func
+gp104_ce = {
+	.intr = gp100_ce_intr,
+	.sclass = {
+		{ -1, -1, PASCAL_DMA_COPY_B },
+		{ -1, -1, PASCAL_DMA_COPY_A },
+		{}
+	}
+};
+
+int
+gp104_ce_new(struct nvkm_device *device, int index,
+	     struct nvkm_engine **pengine)
+{
+	return nvkm_engine_new_(&gp104_ce, device, index, true, pengine);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/ce/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/ce/priv.h
index e2fa8b161943..2dce405976ad 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/ce/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/ce/priv.h
@@ -4,4 +4,5 @@
 
 void gt215_ce_intr(struct nvkm_falcon *, struct nvkm_fifo_chan *);
 void gk104_ce_intr(struct nvkm_engine *);
+void gp100_ce_intr(struct nvkm_engine *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 4572debcb0c9..7218a067a6c5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2148,6 +2148,67 @@ nv12b_chipset = {
 	.sw = gf100_sw_new,
 };
 
+static const struct nvkm_device_chip
+nv130_chipset = {
+	.name = "GP100",
+	.bar = gf100_bar_new,
+	.bios = nvkm_bios_new,
+	.bus = gf100_bus_new,
+	.devinit = gm200_devinit_new,
+	.fb = gp100_fb_new,
+	.fuse = gm107_fuse_new,
+	.gpio = gk104_gpio_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.ltc = gp100_ltc_new,
+	.mc = gp100_mc_new,
+	.mmu = gf100_mmu_new,
+	.secboot = gm200_secboot_new,
+	.pci = gp100_pci_new,
+	.timer = gk20a_timer_new,
+	.top = gk104_top_new,
+	.ce[0] = gp100_ce_new,
+	.ce[1] = gp100_ce_new,
+	.ce[2] = gp100_ce_new,
+	.ce[3] = gp100_ce_new,
+	.ce[4] = gp100_ce_new,
+	.ce[5] = gp100_ce_new,
+	.dma = gf119_dma_new,
+	.disp = gp100_disp_new,
+	.fifo = gp100_fifo_new,
+	.gr = gp100_gr_new,
+	.sw = gf100_sw_new,
+};
+
+static const struct nvkm_device_chip
+nv134_chipset = {
+	.name = "GP104",
+	.bar = gf100_bar_new,
+	.bios = nvkm_bios_new,
+	.bus = gf100_bus_new,
+	.devinit = gm200_devinit_new,
+	.fb = gp104_fb_new,
+	.fuse = gm107_fuse_new,
+	.gpio = gk104_gpio_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.ltc = gp100_ltc_new,
+	.mc = gp100_mc_new,
+	.mmu = gf100_mmu_new,
+	.pci = gp100_pci_new,
+	.timer = gk20a_timer_new,
+	.top = gk104_top_new,
+	.ce[0] = gp104_ce_new,
+	.ce[1] = gp104_ce_new,
+	.ce[2] = gp104_ce_new,
+	.ce[3] = gp104_ce_new,
+	.disp = gp104_disp_new,
+	.dma = gf119_dma_new,
+	.fifo = gp100_fifo_new,
+};
+
 static int
 nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size,
 		       struct nvkm_notify *notify)
@@ -2221,6 +2282,9 @@ nvkm_device_engine(struct nvkm_device *device, int index)
 	_(CE0    , device->ce[0]   ,  device->ce[0]);
 	_(CE1    , device->ce[1]   ,  device->ce[1]);
 	_(CE2    , device->ce[2]   ,  device->ce[2]);
+	_(CE3    , device->ce[3]   ,  device->ce[3]);
+	_(CE4    , device->ce[4]   ,  device->ce[4]);
+	_(CE5    , device->ce[5]   ,  device->ce[5]);
 	_(CIPHER , device->cipher  ,  device->cipher);
 	_(DISP   , device->disp    , &device->disp->engine);
 	_(DMAOBJ , device->dma     , &device->dma->engine);
@@ -2235,6 +2299,7 @@ nvkm_device_engine(struct nvkm_device *device, int index)
 	_(MSVLD  , device->msvld   ,  device->msvld);
 	_(NVENC0 , device->nvenc[0],  device->nvenc[0]);
 	_(NVENC1 , device->nvenc[1],  device->nvenc[1]);
+	_(NVENC2 , device->nvenc[2],  device->nvenc[2]);
 	_(NVDEC  , device->nvdec   ,  device->nvdec);
 	_(PM     , device->pm      , &device->pm->engine);
 	_(SEC    , device->sec     ,  device->sec);
@@ -2492,6 +2557,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 			case 0x100: device->card_type = NV_E0; break;
 			case 0x110:
 			case 0x120: device->card_type = GM100; break;
+			case 0x130: device->card_type = GP100; break;
 			default:
 				break;
 			}
@@ -2576,6 +2642,8 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		case 0x124: device->chip = &nv124_chipset; break;
 		case 0x126: device->chip = &nv126_chipset; break;
 		case 0x12b: device->chip = &nv12b_chipset; break;
+		case 0x130: device->chip = &nv130_chipset; break;
+		case 0x134: device->chip = &nv134_chipset; break;
 		default:
 			nvdev_error(device, "unknown chipset (%08x)\n", boot0);
 			goto done;
@@ -2659,6 +2727,9 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		_(NVKM_ENGINE_CE0     ,    ce[0]);
 		_(NVKM_ENGINE_CE1     ,    ce[1]);
 		_(NVKM_ENGINE_CE2     ,    ce[2]);
+		_(NVKM_ENGINE_CE3     ,    ce[3]);
+		_(NVKM_ENGINE_CE4     ,    ce[4]);
+		_(NVKM_ENGINE_CE5     ,    ce[5]);
 		_(NVKM_ENGINE_CIPHER  ,   cipher);
 		_(NVKM_ENGINE_DISP    ,     disp);
 		_(NVKM_ENGINE_DMAOBJ  ,      dma);
@@ -2673,6 +2744,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		_(NVKM_ENGINE_MSVLD   ,    msvld);
 		_(NVKM_ENGINE_NVENC0  , nvenc[0]);
 		_(NVKM_ENGINE_NVENC1  , nvenc[1]);
+		_(NVKM_ENGINE_NVENC2  , nvenc[2]);
 		_(NVKM_ENGINE_NVDEC   ,    nvdec);
 		_(NVKM_ENGINE_PM      ,       pm);
 		_(NVKM_ENGINE_SEC     ,      sec);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
index 62ad0300cfa5..b1b693219db3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
@@ -1614,7 +1614,6 @@ nvkm_device_pci_func = {
 	.fini = nvkm_device_pci_fini,
 	.resource_addr = nvkm_device_pci_resource_addr,
 	.resource_size = nvkm_device_pci_resource_size,
-	.cpu_coherent = !IS_ENABLED(CONFIG_ARM),
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
index ec12efb4689a..939682f18788 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
@@ -191,13 +191,11 @@ static irqreturn_t
 nvkm_device_tegra_intr(int irq, void *arg)
 {
 	struct nvkm_device_tegra *tdev = arg;
-	struct nvkm_mc *mc = tdev->device.mc;
+	struct nvkm_device *device = &tdev->device;
 	bool handled = false;
-	if (likely(mc)) {
-		nvkm_mc_intr_unarm(mc);
-		nvkm_mc_intr(mc, &handled);
-		nvkm_mc_intr_rearm(mc);
-	}
+	nvkm_mc_intr_unarm(device);
+	nvkm_mc_intr(device, &handled);
+	nvkm_mc_intr_rearm(device);
 	return handled ? IRQ_HANDLED : IRQ_NONE;
 }
 
@@ -247,7 +245,6 @@ nvkm_device_tegra_func = {
 	.fini = nvkm_device_tegra_fini,
 	.resource_addr = nvkm_device_tegra_resource_addr,
 	.resource_size = nvkm_device_tegra_resource_size,
-	.cpu_coherent = false,
 };
 
 int
@@ -313,6 +310,7 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func,
 		goto remove;
 
 	tdev->gpu_speedo = tegra_sku_info.gpu_speedo_value;
+	tdev->gpu_speedo_id = tegra_sku_info.gpu_speedo_id;
 	ret = nvkm_device_ctor(&nvkm_device_tegra_func, NULL, &pdev->dev,
 			       NVKM_DEVICE_TEGRA, pdev->id, NULL,
 			       cfg, dbg, detect, mmio, subdev_mask,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
index 137066426ed7..79a8f71cf788 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
@@ -102,6 +102,7 @@ nvkm_udevice_info(struct nvkm_udevice *udev, void *data, u32 size)
 	case NV_C0: args->v0.family = NV_DEVICE_INFO_V0_FERMI; break;
 	case NV_E0: args->v0.family = NV_DEVICE_INFO_V0_KEPLER; break;
 	case GM100: args->v0.family = NV_DEVICE_INFO_V0_MAXWELL; break;
+	case GP100: args->v0.family = NV_DEVICE_INFO_V0_PASCAL; break;
 	default:
 		args->v0.family = 0;
 		break;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
index e2a64ed14b22..77a52b54a31e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
@@ -10,6 +10,8 @@ nvkm-y += nvkm/engine/disp/gk104.o
 nvkm-y += nvkm/engine/disp/gk110.o
 nvkm-y += nvkm/engine/disp/gm107.o
 nvkm-y += nvkm/engine/disp/gm200.o
+nvkm-y += nvkm/engine/disp/gp100.o
+nvkm-y += nvkm/engine/disp/gp104.o
 
 nvkm-y += nvkm/engine/disp/outp.o
 nvkm-y += nvkm/engine/disp/outpdp.o
@@ -45,12 +47,15 @@ nvkm-y += nvkm/engine/disp/rootgk104.o
 nvkm-y += nvkm/engine/disp/rootgk110.o
 nvkm-y += nvkm/engine/disp/rootgm107.o
 nvkm-y += nvkm/engine/disp/rootgm200.o
+nvkm-y += nvkm/engine/disp/rootgp100.o
+nvkm-y += nvkm/engine/disp/rootgp104.o
 
 nvkm-y += nvkm/engine/disp/channv50.o
 nvkm-y += nvkm/engine/disp/changf119.o
 
 nvkm-y += nvkm/engine/disp/dmacnv50.o
 nvkm-y += nvkm/engine/disp/dmacgf119.o
+nvkm-y += nvkm/engine/disp/dmacgp104.o
 
 nvkm-y += nvkm/engine/disp/basenv50.o
 nvkm-y += nvkm/engine/disp/baseg84.o
@@ -59,6 +64,7 @@ nvkm-y += nvkm/engine/disp/basegt215.o
 nvkm-y += nvkm/engine/disp/basegf119.o
 nvkm-y += nvkm/engine/disp/basegk104.o
 nvkm-y += nvkm/engine/disp/basegk110.o
+nvkm-y += nvkm/engine/disp/basegp104.o
 
 nvkm-y += nvkm/engine/disp/corenv50.o
 nvkm-y += nvkm/engine/disp/coreg84.o
@@ -70,6 +76,8 @@ nvkm-y += nvkm/engine/disp/coregk104.o
 nvkm-y += nvkm/engine/disp/coregk110.o
 nvkm-y += nvkm/engine/disp/coregm107.o
 nvkm-y += nvkm/engine/disp/coregm200.o
+nvkm-y += nvkm/engine/disp/coregp100.o
+nvkm-y += nvkm/engine/disp/coregp104.o
 
 nvkm-y += nvkm/engine/disp/ovlynv50.o
 nvkm-y += nvkm/engine/disp/ovlyg84.o
@@ -77,6 +85,7 @@ nvkm-y += nvkm/engine/disp/ovlygt200.o
 nvkm-y += nvkm/engine/disp/ovlygt215.o
 nvkm-y += nvkm/engine/disp/ovlygf119.o
 nvkm-y += nvkm/engine/disp/ovlygk104.o
+nvkm-y += nvkm/engine/disp/ovlygp104.o
 
 nvkm-y += nvkm/engine/disp/piocnv50.o
 nvkm-y += nvkm/engine/disp/piocgf119.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegp104.c
new file mode 100644
index 000000000000..51688e37c54e
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/basegp104.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "dmacnv50.h"
+#include "rootnv50.h"
+
+#include <nvif/class.h>
+
+const struct nv50_disp_dmac_oclass
+gp104_disp_base_oclass = {
+	.base.oclass = GK110_DISP_BASE_CHANNEL_DMA,
+	.base.minver = 0,
+	.base.maxver = 0,
+	.ctor = nv50_disp_base_new,
+	.func = &gp104_disp_dmac_func,
+	.mthd = &gf119_disp_base_chan_mthd,
+	.chid = 1,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
index aee374884c96..f5f683d9fd20 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
@@ -85,6 +85,7 @@ extern const struct nv50_disp_mthd_list gf119_disp_core_mthd_pior;
 extern const struct nv50_disp_chan_mthd gf119_disp_base_chan_mthd;
 
 extern const struct nv50_disp_chan_mthd gk104_disp_core_chan_mthd;
+extern const struct nv50_disp_chan_mthd gk104_disp_ovly_chan_mthd;
 
 struct nv50_disp_pioc_oclass {
 	int (*ctor)(const struct nv50_disp_chan_func *,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregf119.c
index 6b1dc703dac7..21fbf89b6319 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregf119.c
@@ -171,7 +171,7 @@ gf119_disp_core_chan_mthd = {
 	}
 };
 
-static void
+void
 gf119_disp_core_fini(struct nv50_disp_dmac *chan)
 {
 	struct nv50_disp *disp = chan->base.root->disp;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp100.c
new file mode 100644
index 000000000000..d5dff6619d4d
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp100.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright 2015 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "dmacnv50.h"
+#include "rootnv50.h"
+
+#include <nvif/class.h>
+
+const struct nv50_disp_dmac_oclass
+gp100_disp_core_oclass = {
+	.base.oclass = GP100_DISP_CORE_CHANNEL_DMA,
+	.base.minver = 0,
+	.base.maxver = 0,
+	.ctor = nv50_disp_core_new,
+	.func = &gf119_disp_core_func,
+	.mthd = &gk104_disp_core_chan_mthd,
+	.chid = 0,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp104.c
new file mode 100644
index 000000000000..6922f4007b61
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/coregp104.c
@@ -0,0 +1,78 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "dmacnv50.h"
+#include "rootnv50.h"
+
+#include <subdev/timer.h>
+
+#include <nvif/class.h>
+
+static int
+gp104_disp_core_init(struct nv50_disp_dmac *chan)
+{
+	struct nv50_disp *disp = chan->base.root->disp;
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+
+	/* enable error reporting */
+	nvkm_mask(device, 0x6100a0, 0x00000001, 0x00000001);
+
+	/* initialise channel for dma command submission */
+	nvkm_wr32(device, 0x611494, chan->push);
+	nvkm_wr32(device, 0x611498, 0x00010000);
+	nvkm_wr32(device, 0x61149c, 0x00000001);
+	nvkm_mask(device, 0x610490, 0x00000010, 0x00000010);
+	nvkm_wr32(device, 0x640000, 0x00000000);
+	nvkm_wr32(device, 0x610490, 0x01000013);
+
+	/* wait for it to go inactive */
+	if (nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x610490) & 0x80000000))
+			break;
+	) < 0) {
+		nvkm_error(subdev, "core init: %08x\n",
+			   nvkm_rd32(device, 0x610490));
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+const struct nv50_disp_dmac_func
+gp104_disp_core_func = {
+	.init = gp104_disp_core_init,
+	.fini = gf119_disp_core_fini,
+	.bind = gf119_disp_dmac_bind,
+};
+
+const struct nv50_disp_dmac_oclass
+gp104_disp_core_oclass = {
+	.base.oclass = GP104_DISP_CORE_CHANNEL_DMA,
+	.base.minver = 0,
+	.base.maxver = 0,
+	.ctor = nv50_disp_core_new,
+	.func = &gp104_disp_core_func,
+	.mthd = &gk104_disp_core_chan_mthd,
+	.chid = 0,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c
index 876b14549a58..a57f7cef307a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c
@@ -36,7 +36,7 @@ gf119_disp_dmac_bind(struct nv50_disp_dmac *chan,
 				 chan->base.chid << 27 | 0x00000001);
 }
 
-static void
+void
 gf119_disp_dmac_fini(struct nv50_disp_dmac *chan)
 {
 	struct nv50_disp *disp = chan->base.root->disp;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp104.c
new file mode 100644
index 000000000000..ad24c2c57696
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp104.c
@@ -0,0 +1,66 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "dmacnv50.h"
+#include "rootnv50.h"
+
+#include <subdev/timer.h>
+
+static int
+gp104_disp_dmac_init(struct nv50_disp_dmac *chan)
+{
+	struct nv50_disp *disp = chan->base.root->disp;
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	int chid = chan->base.chid;
+
+	/* enable error reporting */
+	nvkm_mask(device, 0x6100a0, 0x00000001 << chid, 0x00000001 << chid);
+
+	/* initialise channel for dma command submission */
+	nvkm_wr32(device, 0x611494 + (chid * 0x0010), chan->push);
+	nvkm_wr32(device, 0x611498 + (chid * 0x0010), 0x00010000);
+	nvkm_wr32(device, 0x61149c + (chid * 0x0010), 0x00000001);
+	nvkm_mask(device, 0x610490 + (chid * 0x0010), 0x00000010, 0x00000010);
+	nvkm_wr32(device, 0x640000 + (chid * 0x1000), 0x00000000);
+	nvkm_wr32(device, 0x610490 + (chid * 0x0010), 0x00000013);
+
+	/* wait for it to go inactive */
+	if (nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x610490 + (chid * 0x10)) & 0x80000000))
+			break;
+	) < 0) {
+		nvkm_error(subdev, "ch %d init: %08x\n", chid,
+			   nvkm_rd32(device, 0x610490 + (chid * 0x10)));
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+const struct nv50_disp_dmac_func
+gp104_disp_dmac_func = {
+	.init = gp104_disp_dmac_init,
+	.fini = gf119_disp_dmac_fini,
+	.bind = gf119_disp_dmac_bind,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.h
index fc84eb8b5c45..43ac05857853 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.h
@@ -25,8 +25,12 @@ int nv50_disp_dmac_bind(struct nv50_disp_dmac *, struct nvkm_object *, u32);
 extern const struct nv50_disp_dmac_func nv50_disp_core_func;
 
 extern const struct nv50_disp_dmac_func gf119_disp_dmac_func;
+void gf119_disp_dmac_fini(struct nv50_disp_dmac *);
 int gf119_disp_dmac_bind(struct nv50_disp_dmac *, struct nvkm_object *, u32);
 extern const struct nv50_disp_dmac_func gf119_disp_core_func;
+void gf119_disp_core_fini(struct nv50_disp_dmac *);
+
+extern const struct nv50_disp_dmac_func gp104_disp_dmac_func;
 
 struct nv50_disp_dmac_oclass {
 	int (*ctor)(const struct nv50_disp_dmac_func *,
@@ -88,4 +92,10 @@ extern const struct nv50_disp_dmac_oclass gk110_disp_base_oclass;
 extern const struct nv50_disp_dmac_oclass gm107_disp_core_oclass;
 
 extern const struct nv50_disp_dmac_oclass gm200_disp_core_oclass;
+
+extern const struct nv50_disp_dmac_oclass gp100_disp_core_oclass;
+
+extern const struct nv50_disp_dmac_oclass gp104_disp_core_oclass;
+extern const struct nv50_disp_dmac_oclass gp104_disp_base_oclass;
+extern const struct nv50_disp_dmac_oclass gp104_disp_ovly_oclass;
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
index 5dd34382f55a..29e84b241cca 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
@@ -76,12 +76,10 @@ exec_lookup(struct nv50_disp *disp, int head, int or, u32 ctrl,
 	mask |= 0x0001 << or;
 	mask |= 0x0100 << head;
 
-
 	list_for_each_entry(outp, &disp->base.outp, head) {
 		if ((outp->info.hasht & 0xff) == type &&
 		    (outp->info.hashm & mask) == mask) {
-			*data = nvbios_outp_match(bios, outp->info.hasht,
-							outp->info.hashm,
+			*data = nvbios_outp_match(bios, outp->info.hasht, mask,
 						  ver, hdr, cnt, len, info);
 			if (!*data)
 				return NULL;
@@ -415,7 +413,7 @@ gf119_disp_intr_supervisor(struct work_struct *work)
 	nvkm_wr32(device, 0x6101d0, 0x80000000);
 }
 
-static void
+void
 gf119_disp_intr_error(struct nv50_disp *disp, int chid)
 {
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
@@ -463,7 +461,7 @@ gf119_disp_intr(struct nv50_disp *disp)
 		u32 stat = nvkm_rd32(device, 0x61009c);
 		int chid = ffs(stat) - 1;
 		if (chid >= 0)
-			gf119_disp_intr_error(disp, chid);
+			disp->func->intr_error(disp, chid);
 		intr &= ~0x00000002;
 	}
 
@@ -507,6 +505,7 @@ gf119_disp_new_(const struct nv50_disp_func *func, struct nvkm_device *device,
 static const struct nv50_disp_func
 gf119_disp = {
 	.intr = gf119_disp_intr,
+	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_intr_supervisor,
 	.root = &gf119_disp_root_oclass,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk104.c
index a86384b8e388..37f145cf30d7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk104.c
@@ -27,6 +27,7 @@
 static const struct nv50_disp_func
 gk104_disp = {
 	.intr = gf119_disp_intr,
+	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_intr_supervisor,
 	.root = &gk104_disp_root_oclass,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk110.c
index 0d574c7e594a..e14ac946608c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gk110.c
@@ -27,6 +27,7 @@
 static const struct nv50_disp_func
 gk110_disp = {
 	.intr = gf119_disp_intr,
+	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_intr_supervisor,
 	.root = &gk110_disp_root_oclass,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
index f4b9cf8574be..2f2437cc5891 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
@@ -27,6 +27,7 @@
 static const struct nv50_disp_func
 gm107_disp = {
 	.intr = gf119_disp_intr,
+	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_intr_supervisor,
 	.root = &gm107_disp_root_oclass,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm200.c
index 67eec8620719..9f368d4ee61e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm200.c
@@ -27,6 +27,7 @@
 static const struct nv50_disp_func
 gm200_disp = {
 	.intr = gf119_disp_intr,
+	.intr_error = gf119_disp_intr_error,
 	.uevent = &gf119_disp_chan_uevent,
 	.super = gf119_disp_intr_supervisor,
 	.root = &gm200_disp_root_oclass,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp100.c
new file mode 100644
index 000000000000..4f81bf31435e
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp100.c
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2015 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "nv50.h"
+#include "rootnv50.h"
+
+static const struct nv50_disp_func
+gp100_disp = {
+	.intr = gf119_disp_intr,
+	.intr_error = gf119_disp_intr_error,
+	.uevent = &gf119_disp_chan_uevent,
+	.super = gf119_disp_intr_supervisor,
+	.root = &gp100_disp_root_oclass,
+	.head.vblank_init = gf119_disp_vblank_init,
+	.head.vblank_fini = gf119_disp_vblank_fini,
+	.head.scanoutpos = gf119_disp_root_scanoutpos,
+	.outp.internal.crt = nv50_dac_output_new,
+	.outp.internal.tmds = nv50_sor_output_new,
+	.outp.internal.lvds = nv50_sor_output_new,
+	.outp.internal.dp = gm200_sor_dp_new,
+	.dac.nr = 3,
+	.dac.power = nv50_dac_power,
+	.dac.sense = nv50_dac_sense,
+	.sor.nr = 4,
+	.sor.power = nv50_sor_power,
+	.sor.hda_eld = gf119_hda_eld,
+	.sor.hdmi = gk104_hdmi_ctrl,
+	.sor.magic = gm200_sor_magic,
+};
+
+int
+gp100_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
+{
+	return gf119_disp_new_(&gp100_disp, device, index, pdisp);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp104.c
new file mode 100644
index 000000000000..3bf3380336e4
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gp104.c
@@ -0,0 +1,81 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "nv50.h"
+#include "rootnv50.h"
+
+static void
+gp104_disp_intr_error(struct nv50_disp *disp, int chid)
+{
+	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 mthd = nvkm_rd32(device, 0x6111f0 + (chid * 12));
+	u32 data = nvkm_rd32(device, 0x6111f4 + (chid * 12));
+	u32 unkn = nvkm_rd32(device, 0x6111f8 + (chid * 12));
+
+	nvkm_error(subdev, "chid %d mthd %04x data %08x %08x %08x\n",
+		   chid, (mthd & 0x0000ffc), data, mthd, unkn);
+
+	if (chid < ARRAY_SIZE(disp->chan)) {
+		switch (mthd & 0xffc) {
+		case 0x0080:
+			nv50_disp_chan_mthd(disp->chan[chid], NV_DBG_ERROR);
+			break;
+		default:
+			break;
+		}
+	}
+
+	nvkm_wr32(device, 0x61009c, (1 << chid));
+	nvkm_wr32(device, 0x6111f0 + (chid * 12), 0x90000000);
+}
+
+static const struct nv50_disp_func
+gp104_disp = {
+	.intr = gf119_disp_intr,
+	.intr_error = gp104_disp_intr_error,
+	.uevent = &gf119_disp_chan_uevent,
+	.super = gf119_disp_intr_supervisor,
+	.root = &gp104_disp_root_oclass,
+	.head.vblank_init = gf119_disp_vblank_init,
+	.head.vblank_fini = gf119_disp_vblank_fini,
+	.head.scanoutpos = gf119_disp_root_scanoutpos,
+	.outp.internal.crt = nv50_dac_output_new,
+	.outp.internal.tmds = nv50_sor_output_new,
+	.outp.internal.lvds = nv50_sor_output_new,
+	.outp.internal.dp = gm200_sor_dp_new,
+	.dac.nr = 3,
+	.dac.power = nv50_dac_power,
+	.dac.sense = nv50_dac_sense,
+	.sor.nr = 4,
+	.sor.power = nv50_sor_power,
+	.sor.hda_eld = gf119_hda_eld,
+	.sor.hdmi = gk104_hdmi_ctrl,
+	.sor.magic = gm200_sor_magic,
+};
+
+int
+gp104_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
+{
+	return gf119_disp_new_(&gp104_disp, device, index, pdisp);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
index fcb1b0c46d64..fbb8c7dc18fd 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
@@ -32,6 +32,7 @@
 #include <subdev/bios/init.h>
 #include <subdev/bios/pll.h>
 #include <subdev/devinit.h>
+#include <subdev/timer.h>
 
 static const struct nvkm_disp_oclass *
 nv50_disp_root_(struct nvkm_disp *base)
@@ -269,8 +270,7 @@ exec_lookup(struct nv50_disp *disp, int head, int or, u32 ctrl,
 	list_for_each_entry(outp, &disp->base.outp, head) {
 		if ((outp->info.hasht & 0xff) == type &&
 		    (outp->info.hashm & mask) == mask) {
-			*data = nvbios_outp_match(bios, outp->info.hasht,
-							outp->info.hashm,
+			*data = nvbios_outp_match(bios, outp->info.hasht, mask,
 						  ver, hdr, cnt, len, info);
 			if (!*data)
 				return NULL;
@@ -426,6 +426,134 @@ exec_clkcmp(struct nv50_disp *disp, int head, int id, u32 pclk, u32 *conf)
 	return outp;
 }
 
+static bool
+nv50_disp_dptmds_war(struct nvkm_device *device)
+{
+	switch (device->chipset) {
+	case 0x94:
+	case 0x96:
+	case 0x98:
+	case 0xaa:
+	case 0xac:
+		return true;
+	default:
+		break;
+	}
+	return false;
+}
+
+static bool
+nv50_disp_dptmds_war_needed(struct nv50_disp *disp, struct dcb_output *outp)
+{
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	const u32 soff = __ffs(outp->or) * 0x800;
+	if (nv50_disp_dptmds_war(device) && outp->type == DCB_OUTPUT_TMDS) {
+		switch (nvkm_rd32(device, 0x614300 + soff) & 0x00030000) {
+		case 0x00000000:
+		case 0x00030000:
+			return true;
+		default:
+			break;
+		}
+	}
+	return false;
+
+}
+
+static void
+nv50_disp_dptmds_war_2(struct nv50_disp *disp, struct dcb_output *outp)
+{
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	const u32 soff = __ffs(outp->or) * 0x800;
+
+	if (!nv50_disp_dptmds_war_needed(disp, outp))
+		return;
+
+	nvkm_mask(device, 0x00e840, 0x80000000, 0x80000000);
+	nvkm_mask(device, 0x614300 + soff, 0x03000000, 0x03000000);
+	nvkm_mask(device, 0x61c10c + soff, 0x00000001, 0x00000001);
+
+	nvkm_mask(device, 0x61c00c + soff, 0x0f000000, 0x00000000);
+	nvkm_mask(device, 0x61c008 + soff, 0xff000000, 0x14000000);
+	nvkm_usec(device, 400, NVKM_DELAY);
+	nvkm_mask(device, 0x61c008 + soff, 0xff000000, 0x00000000);
+	nvkm_mask(device, 0x61c00c + soff, 0x0f000000, 0x01000000);
+
+	if (nvkm_rd32(device, 0x61c004 + soff) & 0x00000001) {
+		u32 seqctl = nvkm_rd32(device, 0x61c030 + soff);
+		u32  pu_pc = seqctl & 0x0000000f;
+		nvkm_wr32(device, 0x61c040 + soff + pu_pc * 4, 0x1f008000);
+	}
+}
+
+static void
+nv50_disp_dptmds_war_3(struct nv50_disp *disp, struct dcb_output *outp)
+{
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	const u32 soff = __ffs(outp->or) * 0x800;
+	u32 sorpwr;
+
+	if (!nv50_disp_dptmds_war_needed(disp, outp))
+		return;
+
+	sorpwr = nvkm_rd32(device, 0x61c004 + soff);
+	if (sorpwr & 0x00000001) {
+		u32 seqctl = nvkm_rd32(device, 0x61c030 + soff);
+		u32  pd_pc = (seqctl & 0x00000f00) >> 8;
+		u32  pu_pc =  seqctl & 0x0000000f;
+
+		nvkm_wr32(device, 0x61c040 + soff + pd_pc * 4, 0x1f008000);
+
+		nvkm_msec(device, 2000,
+			if (!(nvkm_rd32(device, 0x61c030 + soff) & 0x10000000))
+				break;
+		);
+		nvkm_mask(device, 0x61c004 + soff, 0x80000001, 0x80000000);
+		nvkm_msec(device, 2000,
+			if (!(nvkm_rd32(device, 0x61c030 + soff) & 0x10000000))
+				break;
+		);
+
+		nvkm_wr32(device, 0x61c040 + soff + pd_pc * 4, 0x00002000);
+		nvkm_wr32(device, 0x61c040 + soff + pu_pc * 4, 0x1f000000);
+	}
+
+	nvkm_mask(device, 0x61c10c + soff, 0x00000001, 0x00000000);
+	nvkm_mask(device, 0x614300 + soff, 0x03000000, 0x00000000);
+
+	if (sorpwr & 0x00000001) {
+		nvkm_mask(device, 0x61c004 + soff, 0x80000001, 0x80000001);
+	}
+}
+
+static void
+nv50_disp_update_sppll1(struct nv50_disp *disp)
+{
+	struct nvkm_device *device = disp->base.engine.subdev.device;
+	bool used = false;
+	int sor;
+
+	if (!nv50_disp_dptmds_war(device))
+		return;
+
+	for (sor = 0; sor < disp->func->sor.nr; sor++) {
+		u32 clksor = nvkm_rd32(device, 0x614300 + (sor * 0x800));
+		switch (clksor & 0x03000000) {
+		case 0x02000000:
+		case 0x03000000:
+			used = true;
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (used)
+		return;
+
+	nvkm_mask(device, 0x00e840, 0x80000000, 0x00000000);
+}
+
 static void
 nv50_disp_intr_unk10_0(struct nv50_disp *disp, int head)
 {
@@ -679,6 +807,8 @@ nv50_disp_intr_unk20_2(struct nv50_disp *disp, int head)
 
 	nvkm_mask(device, hreg, 0x0000000f, hval);
 	nvkm_mask(device, oreg, mask, oval);
+
+	nv50_disp_dptmds_war_2(disp, &outp->info);
 }
 
 /* If programming a TMDS output on a SOR that can also be configured for
@@ -720,6 +850,7 @@ nv50_disp_intr_unk40_0(struct nv50_disp *disp, int head)
 
 	if (outp->info.location == 0 && outp->info.type == DCB_OUTPUT_TMDS)
 		nv50_disp_intr_unk40_0_tmds(disp, &outp->info);
+	nv50_disp_dptmds_war_3(disp, &outp->info);
 }
 
 void
@@ -767,6 +898,7 @@ nv50_disp_intr_supervisor(struct work_struct *work)
 				continue;
 			nv50_disp_intr_unk40_0(disp, head);
 		}
+		nv50_disp_update_sppll1(disp);
 	}
 
 	nvkm_wr32(device, 0x610030, 0x80000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
index aecebd8717e5..1e1de6bfe85a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
@@ -68,6 +68,7 @@ struct nv50_disp_func_outp {
 
 struct nv50_disp_func {
 	void (*intr)(struct nv50_disp *);
+	void (*intr_error)(struct nv50_disp *, int chid);
 
 	const struct nvkm_event_func *uevent;
 	void (*super)(struct work_struct *);
@@ -114,4 +115,5 @@ void gf119_disp_vblank_init(struct nv50_disp *, int);
 void gf119_disp_vblank_fini(struct nv50_disp *, int);
 void gf119_disp_intr(struct nv50_disp *);
 void gf119_disp_intr_supervisor(struct work_struct *);
+void gf119_disp_intr_error(struct nv50_disp *, int);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygk104.c
index 2e2dc0641ef2..2f0220b39f34 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygk104.c
@@ -80,7 +80,7 @@ gk104_disp_ovly_mthd_base = {
 	}
 };
 
-static const struct nv50_disp_chan_mthd
+const struct nv50_disp_chan_mthd
 gk104_disp_ovly_chan_mthd = {
 	.name = "Overlay",
 	.addr = 0x001000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygp104.c
new file mode 100644
index 000000000000..97e2dd2d908e
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ovlygp104.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright 2012 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#include "dmacnv50.h"
+#include "rootnv50.h"
+
+#include <nvif/class.h>
+
+const struct nv50_disp_dmac_oclass
+gp104_disp_ovly_oclass = {
+	.base.oclass = GK104_DISP_OVERLAY_CONTROL_DMA,
+	.base.minver = 0,
+	.base.maxver = 0,
+	.ctor = nv50_disp_ovly_new,
+	.func = &gp104_disp_dmac_func,
+	.mthd = &gk104_disp_ovly_chan_mthd,
+	.chid = 5,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp100.c
new file mode 100644
index 000000000000..ac8fdd728ec6
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp100.c
@@ -0,0 +1,58 @@
+/*
+ * Copyright 2015 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "rootnv50.h"
+#include "dmacnv50.h"
+
+#include <nvif/class.h>
+
+static const struct nv50_disp_root_func
+gp100_disp_root = {
+	.init = gf119_disp_root_init,
+	.fini = gf119_disp_root_fini,
+	.dmac = {
+		&gp100_disp_core_oclass,
+		&gk110_disp_base_oclass,
+		&gk104_disp_ovly_oclass,
+	},
+	.pioc = {
+		&gk104_disp_oimm_oclass,
+		&gk104_disp_curs_oclass,
+	},
+};
+
+static int
+gp100_disp_root_new(struct nvkm_disp *disp, const struct nvkm_oclass *oclass,
+		    void *data, u32 size, struct nvkm_object **pobject)
+{
+	return nv50_disp_root_new_(&gp100_disp_root, disp, oclass,
+				   data, size, pobject);
+}
+
+const struct nvkm_disp_oclass
+gp100_disp_root_oclass = {
+	.base.oclass = GP100_DISP,
+	.base.minver = -1,
+	.base.maxver = -1,
+	.ctor = gp100_disp_root_new,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp104.c
new file mode 100644
index 000000000000..8443e04dc626
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp104.c
@@ -0,0 +1,58 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "rootnv50.h"
+#include "dmacnv50.h"
+
+#include <nvif/class.h>
+
+static const struct nv50_disp_root_func
+gp104_disp_root = {
+	.init = gf119_disp_root_init,
+	.fini = gf119_disp_root_fini,
+	.dmac = {
+		&gp104_disp_core_oclass,
+		&gp104_disp_base_oclass,
+		&gp104_disp_ovly_oclass,
+	},
+	.pioc = {
+		&gk104_disp_oimm_oclass,
+		&gk104_disp_curs_oclass,
+	},
+};
+
+static int
+gp104_disp_root_new(struct nvkm_disp *disp, const struct nvkm_oclass *oclass,
+		    void *data, u32 size, struct nvkm_object **pobject)
+{
+	return nv50_disp_root_new_(&gp104_disp_root, disp, oclass,
+				   data, size, pobject);
+}
+
+const struct nvkm_disp_oclass
+gp104_disp_root_oclass = {
+	.base.oclass = GP104_DISP,
+	.base.minver = -1,
+	.base.maxver = -1,
+	.ctor = gp104_disp_root_new,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
index cb449ed8d92c..ad00f1724b72 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
@@ -40,4 +40,6 @@ extern const struct nvkm_disp_oclass gk104_disp_root_oclass;
 extern const struct nvkm_disp_oclass gk110_disp_root_oclass;
 extern const struct nvkm_disp_oclass gm107_disp_root_oclass;
 extern const struct nvkm_disp_oclass gm200_disp_root_oclass;
+extern const struct nvkm_disp_oclass gp100_disp_root_oclass;
+extern const struct nvkm_disp_oclass gp104_disp_root_oclass;
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
index 65e5d291ecda..98651a43bc12 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild
@@ -13,6 +13,7 @@ nvkm-y += nvkm/engine/fifo/gk20a.o
 nvkm-y += nvkm/engine/fifo/gm107.o
 nvkm-y += nvkm/engine/fifo/gm200.o
 nvkm-y += nvkm/engine/fifo/gm20b.o
+nvkm-y += nvkm/engine/fifo/gp100.o
 
 nvkm-y += nvkm/engine/fifo/chan.o
 nvkm-y += nvkm/engine/fifo/channv50.o
@@ -31,3 +32,4 @@ nvkm-y += nvkm/engine/fifo/gpfifogf100.o
 nvkm-y += nvkm/engine/fifo/gpfifogk104.o
 nvkm-y += nvkm/engine/fifo/gpfifogk110.o
 nvkm-y += nvkm/engine/fifo/gpfifogm200.o
+nvkm-y += nvkm/engine/fifo/gpfifogp100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/changk104.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/changk104.h
index e06f4d46f802..230f64e5f731 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/changk104.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/changk104.h
@@ -27,4 +27,5 @@ int gk104_fifo_gpfifo_new(struct nvkm_fifo *, const struct nvkm_oclass *,
 extern const struct nvkm_fifo_chan_oclass gk104_fifo_gpfifo_oclass;
 extern const struct nvkm_fifo_chan_oclass gk110_fifo_gpfifo_oclass;
 extern const struct nvkm_fifo_chan_oclass gm200_fifo_gpfifo_oclass;
+extern const struct nvkm_fifo_chan_oclass gp100_fifo_gpfifo_oclass;
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
index 743f3a189f28..103c0afaaa6d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
@@ -329,7 +329,7 @@ gk104_fifo_intr_fault(struct gk104_fifo *fifo, int unit)
 	}
 
 	if (eu == NULL) {
-		enum nvkm_devidx engidx = nvkm_top_fault(device->top, unit);
+		enum nvkm_devidx engidx = nvkm_top_fault(device, unit);
 		if (engidx < NVKM_SUBDEV_NR) {
 			const char *src = nvkm_subdev_name[engidx];
 			char *dst = en;
@@ -589,7 +589,6 @@ gk104_fifo_oneinit(struct nvkm_fifo *base)
 	struct gk104_fifo *fifo = gk104_fifo(base);
 	struct nvkm_subdev *subdev = &fifo->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	struct nvkm_top *top = device->top;
 	int engn, runl, pbid, ret, i, j;
 	enum nvkm_devidx engidx;
 	u32 *map;
@@ -608,7 +607,7 @@ gk104_fifo_oneinit(struct nvkm_fifo *base)
 
 	/* Determine runlist configuration from topology device info. */
 	i = 0;
-	while ((int)(engidx = nvkm_top_engine(top, i++, &runl, &engn)) >= 0) {
+	while ((int)(engidx = nvkm_top_engine(device, i++, &runl, &engn)) >= 0) {
 		/* Determine which PBDMA handles requests for this engine. */
 		for (j = 0, pbid = -1; j < fifo->pbdma_nr; j++) {
 			if (map[j] & (1 << runl)) {
@@ -617,8 +616,8 @@ gk104_fifo_oneinit(struct nvkm_fifo *base)
 			}
 		}
 
-		nvkm_debug(subdev, "engine %2d: runlist %2d pbdma %2d\n",
-			   engn, runl, pbid);
+		nvkm_debug(subdev, "engine %2d: runlist %2d pbdma %2d (%s)\n",
+			   engn, runl, pbid, nvkm_subdev_name[engidx]);
 
 		fifo->engine[engn].engine = nvkm_device_engine(device, engidx);
 		fifo->engine[engn].runl = runl;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp100.c
new file mode 100644
index 000000000000..eff83f7fb705
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gp100.c
@@ -0,0 +1,67 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#include "gk104.h"
+#include "changk104.h"
+
+static const struct nvkm_enum
+gp100_fifo_fault_engine[] = {
+	{ 0x01, "DISPLAY" },
+	{ 0x03, "IFB", NULL, NVKM_ENGINE_IFB },
+	{ 0x04, "BAR1", NULL, NVKM_SUBDEV_BAR },
+	{ 0x05, "BAR2", NULL, NVKM_SUBDEV_INSTMEM },
+	{ 0x06, "HOST0" },
+	{ 0x07, "HOST1" },
+	{ 0x08, "HOST2" },
+	{ 0x09, "HOST3" },
+	{ 0x0a, "HOST4" },
+	{ 0x0b, "HOST5" },
+	{ 0x0c, "HOST6" },
+	{ 0x0d, "HOST7" },
+	{ 0x0e, "HOST8" },
+	{ 0x0f, "HOST9" },
+	{ 0x10, "HOST10" },
+	{ 0x13, "PERF" },
+	{ 0x17, "PMU" },
+	{ 0x18, "PTP" },
+	{ 0x1f, "PHYSICAL" },
+	{}
+};
+
+static const struct gk104_fifo_func
+gp100_fifo = {
+	.fault.engine = gp100_fifo_fault_engine,
+	.fault.reason = gk104_fifo_fault_reason,
+	.fault.hubclient = gk104_fifo_fault_hubclient,
+	.fault.gpcclient = gk104_fifo_fault_gpcclient,
+	.chan = {
+		&gp100_fifo_gpfifo_oclass,
+		NULL
+	},
+};
+
+int
+gp100_fifo_new(struct nvkm_device *device, int index, struct nvkm_fifo **pfifo)
+{
+	return gk104_fifo_new_(&gp100_fifo, device, index, 4096, pfifo);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogp100.c
new file mode 100644
index 000000000000..1530a9217aea
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gpfifogp100.c
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#include "changk104.h"
+
+#include <nvif/class.h>
+
+const struct nvkm_fifo_chan_oclass
+gp100_fifo_gpfifo_oclass = {
+	.base.oclass = PASCAL_CHANNEL_GPFIFO_A,
+	.base.minver = 0,
+	.base.maxver = 0,
+	.ctor = gk104_fifo_gpfifo_new,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
index 290ed0db8047..f1c494182248 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
@@ -31,6 +31,7 @@ nvkm-y += nvkm/engine/gr/gk20a.o
 nvkm-y += nvkm/engine/gr/gm107.o
 nvkm-y += nvkm/engine/gr/gm200.o
 nvkm-y += nvkm/engine/gr/gm20b.o
+nvkm-y += nvkm/engine/gr/gp100.o
 
 nvkm-y += nvkm/engine/gr/ctxnv40.o
 nvkm-y += nvkm/engine/gr/ctxnv50.o
@@ -48,3 +49,4 @@ nvkm-y += nvkm/engine/gr/ctxgk20a.o
 nvkm-y += nvkm/engine/gr/ctxgm107.o
 nvkm-y += nvkm/engine/gr/ctxgm200.o
 nvkm-y += nvkm/engine/gr/ctxgm20b.o
+nvkm-y += nvkm/engine/gr/ctxgp100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
index b02d8f50ea6a..bc77eea351a5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
@@ -1240,7 +1240,7 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	const struct gf100_grctx_func *grctx = gr->func->grctx;
 	u32 idle_timeout;
 
-	nvkm_mc_unk260(device->mc, 0);
+	nvkm_mc_unk260(device, 0);
 
 	gf100_gr_mmio(gr, grctx->hub);
 	gf100_gr_mmio(gr, grctx->gpc);
@@ -1264,7 +1264,7 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	gf100_gr_icmd(gr, grctx->icmd);
 	nvkm_wr32(device, 0x404154, idle_timeout);
 	gf100_gr_mthd(gr, grctx->mthd);
-	nvkm_mc_unk260(device->mc, 1);
+	nvkm_mc_unk260(device, 1);
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
index ac895edce164..52048b5a5274 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
@@ -101,6 +101,8 @@ void gm200_grctx_generate_405b60(struct gf100_gr *);
 
 extern const struct gf100_grctx_func gm20b_grctx;
 
+extern const struct gf100_grctx_func gp100_grctx;
+
 /* context init value lists */
 
 extern const struct gf100_gr_pack gf100_grctx_pack_icmd[];
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
index f521de11a299..c925ade5880e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
@@ -226,7 +226,7 @@ gf117_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	u32 idle_timeout;
 	int i;
 
-	nvkm_mc_unk260(device->mc, 0);
+	nvkm_mc_unk260(device, 0);
 
 	gf100_gr_mmio(gr, grctx->hub);
 	gf100_gr_mmio(gr, grctx->gpc);
@@ -253,7 +253,7 @@ gf117_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	gf100_gr_icmd(gr, grctx->icmd);
 	nvkm_wr32(device, 0x404154, idle_timeout);
 	gf100_gr_mthd(gr, grctx->mthd);
-	nvkm_mc_unk260(device->mc, 1);
+	nvkm_mc_unk260(device, 1);
 }
 
 const struct gf100_grctx_func
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
index 9ba337778ef5..c46b3fdf7203 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
@@ -950,7 +950,7 @@ gk104_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	u32 idle_timeout;
 	int i;
 
-	nvkm_mc_unk260(device->mc, 0);
+	nvkm_mc_unk260(device, 0);
 
 	gf100_gr_mmio(gr, grctx->hub);
 	gf100_gr_mmio(gr, grctx->gpc);
@@ -979,7 +979,7 @@ gk104_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	gf100_gr_icmd(gr, grctx->icmd);
 	nvkm_wr32(device, 0x404154, idle_timeout);
 	gf100_gr_mthd(gr, grctx->mthd);
-	nvkm_mc_unk260(device->mc, 1);
+	nvkm_mc_unk260(device, 1);
 
 	nvkm_mask(device, 0x418800, 0x00200000, 0x00200000);
 	nvkm_mask(device, 0x41be10, 0x00800000, 0x00800000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp100.c
new file mode 100644
index 000000000000..3d1ae7ddf7dd
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgp100.c
@@ -0,0 +1,179 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "ctxgf100.h"
+
+#include <subdev/fb.h>
+
+/*******************************************************************************
+ * PGRAPH context implementation
+ ******************************************************************************/
+
+static void
+gp100_grctx_generate_pagepool(struct gf100_grctx *info)
+{
+	const struct gf100_grctx_func *grctx = info->gr->func->grctx;
+	const u32 access = NV_MEM_ACCESS_RW | NV_MEM_ACCESS_SYS;
+	const int s = 8;
+	const int b = mmio_vram(info, grctx->pagepool_size, (1 << s), access);
+	mmio_refn(info, 0x40800c, 0x00000000, s, b);
+	mmio_wr32(info, 0x408010, 0x80000000);
+	mmio_refn(info, 0x419004, 0x00000000, s, b);
+	mmio_wr32(info, 0x419008, 0x00000000);
+}
+
+static void
+gp100_grctx_generate_attrib(struct gf100_grctx *info)
+{
+	struct gf100_gr *gr = info->gr;
+	const struct gf100_grctx_func *grctx = gr->func->grctx;
+	const u32  alpha = grctx->alpha_nr;
+	const u32 attrib = grctx->attrib_nr;
+	const u32 pertpc = 0x20 * (grctx->attrib_nr_max + grctx->alpha_nr_max);
+	const u32   size = roundup(gr->tpc_total * pertpc, 0x80);
+	const u32 access = NV_MEM_ACCESS_RW;
+	const int s = 12;
+	const int b = mmio_vram(info, size, (1 << s), access);
+	const int max_batches = 0xffff;
+	u32 ao = 0;
+	u32 bo = ao + grctx->alpha_nr_max * gr->tpc_total;
+	int gpc, ppc, n = 0;
+
+	mmio_refn(info, 0x418810, 0x80000000, s, b);
+	mmio_refn(info, 0x419848, 0x10000000, s, b);
+	mmio_refn(info, 0x419c2c, 0x10000000, s, b);
+	mmio_refn(info, 0x419b00, 0x00000000, s, b);
+	mmio_wr32(info, 0x419b04, 0x80000000 | size >> 7);
+	mmio_wr32(info, 0x405830, attrib);
+	mmio_wr32(info, 0x40585c, alpha);
+	mmio_wr32(info, 0x4064c4, ((alpha / 4) << 16) | max_batches);
+
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+		for (ppc = 0; ppc < gr->ppc_nr[gpc]; ppc++, n++) {
+			const u32 as =  alpha * gr->ppc_tpc_nr[gpc][ppc];
+			const u32 bs = attrib * gr->ppc_tpc_nr[gpc][ppc];
+			const u32 u = 0x418ea0 + (n * 0x04);
+			const u32 o = PPC_UNIT(gpc, ppc, 0);
+			if (!(gr->ppc_mask[gpc] & (1 << ppc)))
+				continue;
+			mmio_wr32(info, o + 0xc0, bs);
+			mmio_wr32(info, o + 0xf4, bo);
+			mmio_wr32(info, o + 0xf0, bs);
+			bo += grctx->attrib_nr_max * gr->ppc_tpc_nr[gpc][ppc];
+			mmio_wr32(info, o + 0xe4, as);
+			mmio_wr32(info, o + 0xf8, ao);
+			ao += grctx->alpha_nr_max * gr->ppc_tpc_nr[gpc][ppc];
+			mmio_wr32(info, u, bs);
+		}
+	}
+
+	mmio_wr32(info, 0x418eec, 0x00000000);
+	mmio_wr32(info, 0x41befc, 0x00000000);
+}
+
+static void
+gp100_grctx_generate_405b60(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	const u32 dist_nr = DIV_ROUND_UP(gr->tpc_total, 4);
+	u32 dist[TPC_MAX / 4] = {};
+	u32 gpcs[GPC_MAX * 2] = {};
+	u8  tpcnr[GPC_MAX];
+	int tpc, gpc, i;
+
+	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
+
+	/* won't result in the same distribution as the binary driver where
+	 * some of the gpcs have more tpcs than others, but this shall do
+	 * for the moment.  the code for earlier gpus has this issue too.
+	 */
+	for (gpc = -1, i = 0; i < gr->tpc_total; i++) {
+		do {
+			gpc = (gpc + 1) % gr->gpc_nr;
+		} while(!tpcnr[gpc]);
+		tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
+
+		dist[i / 4] |= ((gpc << 4) | tpc) << ((i % 4) * 8);
+		gpcs[gpc + (gr->gpc_nr * (tpc / 4))] |= i << (tpc * 8);
+	}
+
+	for (i = 0; i < dist_nr; i++)
+		nvkm_wr32(device, 0x405b60 + (i * 4), dist[i]);
+	for (i = 0; i < gr->gpc_nr * 2; i++)
+		nvkm_wr32(device, 0x405ba0 + (i * 4), gpcs[i]);
+}
+
+static void
+gp100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	const struct gf100_grctx_func *grctx = gr->func->grctx;
+	u32 idle_timeout, tmp;
+	int i;
+
+	gf100_gr_mmio(gr, gr->fuc_sw_ctx);
+
+	idle_timeout = nvkm_mask(device, 0x404154, 0xffffffff, 0x00000000);
+
+	grctx->pagepool(info);
+	grctx->bundle(info);
+	grctx->attrib(info);
+	grctx->unkn(gr);
+
+	gm200_grctx_generate_tpcid(gr);
+	gf100_grctx_generate_r406028(gr);
+	gk104_grctx_generate_r418bb8(gr);
+
+	for (i = 0; i < 8; i++)
+		nvkm_wr32(device, 0x4064d0 + (i * 0x04), 0x00000000);
+	nvkm_wr32(device, 0x406500, 0x00000000);
+
+	nvkm_wr32(device, 0x405b00, (gr->tpc_total << 8) | gr->gpc_nr);
+
+	for (tmp = 0, i = 0; i < gr->gpc_nr; i++)
+		tmp |= ((1 << gr->tpc_nr[i]) - 1) << (i * 5);
+	nvkm_wr32(device, 0x4041c4, tmp);
+
+	gp100_grctx_generate_405b60(gr);
+
+	gf100_gr_icmd(gr, gr->fuc_bundle);
+	nvkm_wr32(device, 0x404154, idle_timeout);
+	gf100_gr_mthd(gr, gr->fuc_method);
+}
+
+const struct gf100_grctx_func
+gp100_grctx = {
+	.main  = gp100_grctx_generate_main,
+	.unkn  = gk104_grctx_generate_unkn,
+	.bundle = gm107_grctx_generate_bundle,
+	.bundle_size = 0x3000,
+	.bundle_min_gpm_fifo_depth = 0x180,
+	.bundle_token_limit = 0x1080,
+	.pagepool = gp100_grctx_generate_pagepool,
+	.pagepool_size = 0x20000,
+	.attrib = gp100_grctx_generate_attrib,
+	.attrib_nr_max = 0x660,
+	.attrib_nr = 0x440,
+	.alpha_nr_max = 0xc00,
+	.alpha_nr = 0x800,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index ae9ab5b1ab97..157919c788e6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -1457,24 +1457,30 @@ gf100_gr_init_ctxctl(struct gf100_gr *gr)
 	struct nvkm_device *device = subdev->device;
 	struct nvkm_secboot *sb = device->secboot;
 	int i;
+	int ret = 0;
 
 	if (gr->firmware) {
 		/* load fuc microcode */
-		nvkm_mc_unk260(device->mc, 0);
+		nvkm_mc_unk260(device, 0);
 
 		/* securely-managed falcons must be reset using secure boot */
 		if (nvkm_secboot_is_managed(sb, NVKM_SECBOOT_FALCON_FECS))
-			nvkm_secboot_reset(sb, NVKM_SECBOOT_FALCON_FECS);
+			ret = nvkm_secboot_reset(sb, NVKM_SECBOOT_FALCON_FECS);
 		else
 			gf100_gr_init_fw(gr, 0x409000, &gr->fuc409c,
 					 &gr->fuc409d);
+		if (ret)
+			return ret;
+
 		if (nvkm_secboot_is_managed(sb, NVKM_SECBOOT_FALCON_GPCCS))
-			nvkm_secboot_reset(sb, NVKM_SECBOOT_FALCON_GPCCS);
+			ret = nvkm_secboot_reset(sb, NVKM_SECBOOT_FALCON_GPCCS);
 		else
 			gf100_gr_init_fw(gr, 0x41a000, &gr->fuc41ac,
 					 &gr->fuc41ad);
+		if (ret)
+			return ret;
 
-		nvkm_mc_unk260(device->mc, 1);
+		nvkm_mc_unk260(device, 1);
 
 		/* start both of them running */
 		nvkm_wr32(device, 0x409840, 0xffffffff);
@@ -1576,7 +1582,7 @@ gf100_gr_init_ctxctl(struct gf100_gr *gr)
 	}
 
 	/* load HUB microcode */
-	nvkm_mc_unk260(device->mc, 0);
+	nvkm_mc_unk260(device, 0);
 	nvkm_wr32(device, 0x4091c0, 0x01000000);
 	for (i = 0; i < gr->func->fecs.ucode->data.size / 4; i++)
 		nvkm_wr32(device, 0x4091c4, gr->func->fecs.ucode->data.data[i]);
@@ -1599,7 +1605,7 @@ gf100_gr_init_ctxctl(struct gf100_gr *gr)
 			nvkm_wr32(device, 0x41a188, i >> 6);
 		nvkm_wr32(device, 0x41a184, gr->func->gpccs.ucode->code.data[i]);
 	}
-	nvkm_mc_unk260(device->mc, 1);
+	nvkm_mc_unk260(device, 1);
 
 	/* load register lists */
 	gf100_gr_init_csdata(gr, grctx->hub, 0x409000, 0x000, 0x000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index 2b98abdb9270..268b8d60ff73 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -292,4 +292,6 @@ extern const struct gf100_gr_init gm107_gr_init_l1c_0[];
 extern const struct gf100_gr_init gm107_gr_init_wwdx_0[];
 extern const struct gf100_gr_init gm107_gr_init_cbm_0[];
 void gm107_gr_init_bios(struct gf100_gr *);
+
+void gm200_gr_init_gpc_mmu(struct gf100_gr *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
index 4ca8ed15191c..de8b806b88fd 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
@@ -361,6 +361,5 @@ gk20a_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 	if (ret)
 		return ret;
 
-
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c
index 4dfa4513bb6c..6435f1257572 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c
@@ -38,7 +38,7 @@ gm200_gr_rops(struct gf100_gr *gr)
 	return nvkm_rd32(gr->base.engine.subdev.device, 0x12006c);
 }
 
-static void
+void
 gm200_gr_init_gpc_mmu(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c
new file mode 100644
index 000000000000..26ad79def0ff
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c
@@ -0,0 +1,171 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "gf100.h"
+#include "ctxgf100.h"
+
+#include <nvif/class.h>
+
+/*******************************************************************************
+ * PGRAPH engine/subdev functions
+ ******************************************************************************/
+
+static void
+gp100_gr_init_rop_active_fbps(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	/*XXX: otherwise identical to gm200 aside from mask.. do everywhere? */
+	const u32 fbp_count = nvkm_rd32(device, 0x12006c) & 0x0000000f;
+	nvkm_mask(device, 0x408850, 0x0000000f, fbp_count); /* zrop */
+	nvkm_mask(device, 0x408958, 0x0000000f, fbp_count); /* crop */
+}
+
+static int
+gp100_gr_init(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	const u32 magicgpc918 = DIV_ROUND_UP(0x00800000, gr->tpc_total);
+	u32 data[TPC_MAX / 8] = {};
+	u8  tpcnr[GPC_MAX];
+	int gpc, tpc, rop;
+	int i;
+
+	gr->func->init_gpc_mmu(gr);
+
+	gf100_gr_mmio(gr, gr->fuc_sw_nonctx);
+
+	nvkm_wr32(device, GPC_UNIT(0, 0x3018), 0x00000001);
+
+	memset(data, 0x00, sizeof(data));
+	memcpy(tpcnr, gr->tpc_nr, sizeof(gr->tpc_nr));
+	for (i = 0, gpc = -1; i < gr->tpc_total; i++) {
+		do {
+			gpc = (gpc + 1) % gr->gpc_nr;
+		} while (!tpcnr[gpc]);
+		tpc = gr->tpc_nr[gpc] - tpcnr[gpc]--;
+
+		data[i / 8] |= tpc << ((i % 8) * 4);
+	}
+
+	nvkm_wr32(device, GPC_BCAST(0x0980), data[0]);
+	nvkm_wr32(device, GPC_BCAST(0x0984), data[1]);
+	nvkm_wr32(device, GPC_BCAST(0x0988), data[2]);
+	nvkm_wr32(device, GPC_BCAST(0x098c), data[3]);
+
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0914),
+			  gr->screen_tile_row_offset << 8 | gr->tpc_nr[gpc]);
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0910), 0x00040000 |
+							 gr->tpc_total);
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0918), magicgpc918);
+	}
+
+	nvkm_wr32(device, GPC_BCAST(0x3fd4), magicgpc918);
+	nvkm_wr32(device, GPC_BCAST(0x08ac), nvkm_rd32(device, 0x100800));
+	nvkm_wr32(device, GPC_BCAST(0x033c), nvkm_rd32(device, 0x100804));
+
+	gr->func->init_rop_active_fbps(gr);
+
+	nvkm_wr32(device, 0x400500, 0x00010001);
+	nvkm_wr32(device, 0x400100, 0xffffffff);
+	nvkm_wr32(device, 0x40013c, 0xffffffff);
+	nvkm_wr32(device, 0x400124, 0x00000002);
+	nvkm_wr32(device, 0x409c24, 0x000f0002);
+	nvkm_wr32(device, 0x405848, 0xc0000000);
+	nvkm_mask(device, 0x40584c, 0x00000000, 0x00000001);
+	nvkm_wr32(device, 0x404000, 0xc0000000);
+	nvkm_wr32(device, 0x404600, 0xc0000000);
+	nvkm_wr32(device, 0x408030, 0xc0000000);
+	nvkm_wr32(device, 0x404490, 0xc0000000);
+	nvkm_wr32(device, 0x406018, 0xc0000000);
+	nvkm_wr32(device, 0x407020, 0x40000000);
+	nvkm_wr32(device, 0x405840, 0xc0000000);
+	nvkm_wr32(device, 0x405844, 0x00ffffff);
+	nvkm_mask(device, 0x419cc0, 0x00000008, 0x00000008);
+
+	nvkm_mask(device, 0x419c9c, 0x00010000, 0x00010000);
+	nvkm_mask(device, 0x419c9c, 0x00020000, 0x00020000);
+
+	gr->func->init_ppc_exceptions(gr);
+
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0420), 0xc0000000);
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0900), 0xc0000000);
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x1028), 0xc0000000);
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0824), 0xc0000000);
+		for (tpc = 0; tpc < gr->tpc_nr[gpc]; tpc++) {
+			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x508), 0xffffffff);
+			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x50c), 0xffffffff);
+			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x224), 0xc0000000);
+			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x48c), 0xc0000000);
+			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x084), 0xc0000000);
+			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x430), 0xc0000000);
+			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x644), 0x00dffffe);
+			nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x64c), 0x00000105);
+		}
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c90), 0xffffffff);
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x2c94), 0xffffffff);
+	}
+
+	for (rop = 0; rop < gr->rop_nr; rop++) {
+		nvkm_wr32(device, ROP_UNIT(rop, 0x144), 0x40000000);
+		nvkm_wr32(device, ROP_UNIT(rop, 0x070), 0x40000000);
+		nvkm_wr32(device, ROP_UNIT(rop, 0x204), 0xffffffff);
+		nvkm_wr32(device, ROP_UNIT(rop, 0x208), 0xffffffff);
+	}
+
+	nvkm_wr32(device, 0x400108, 0xffffffff);
+	nvkm_wr32(device, 0x400138, 0xffffffff);
+	nvkm_wr32(device, 0x400118, 0xffffffff);
+	nvkm_wr32(device, 0x400130, 0xffffffff);
+	nvkm_wr32(device, 0x40011c, 0xffffffff);
+	nvkm_wr32(device, 0x400134, 0xffffffff);
+
+	gf100_gr_zbc_init(gr);
+
+	return gf100_gr_init_ctxctl(gr);
+}
+
+static const struct gf100_gr_func
+gp100_gr = {
+	.init = gp100_gr_init,
+	.init_gpc_mmu = gm200_gr_init_gpc_mmu,
+	.init_rop_active_fbps = gp100_gr_init_rop_active_fbps,
+	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.rops = gm200_gr_rops,
+	.ppc_nr = 2,
+	.grctx = &gp100_grctx,
+	.sclass = {
+		{ -1, -1, FERMI_TWOD_A },
+		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
+		{ -1, -1, PASCAL_A, &gf100_fermi },
+		{ -1, -1, PASCAL_COMPUTE_A },
+		{}
+	}
+};
+
+int
+gp100_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
+{
+	return gm200_gr_new_(&gp100_gr, device, index, pgr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c
index 69de8c6259fe..f1e15a4d4f64 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv30.c
@@ -76,8 +76,8 @@ nv30_gr_chan_new(struct nvkm_gr *base, struct nvkm_fifo_chan *fifoch,
 		nvkm_wo32(chan->inst, i, 0x00040004);
 	for (i = 0x1f18; i <= 0x3088 ; i += 16) {
 		nvkm_wo32(chan->inst, i + 0, 0x10700ff9);
-		nvkm_wo32(chan->inst, i + 1, 0x0436086c);
-		nvkm_wo32(chan->inst, i + 2, 0x000c001b);
+		nvkm_wo32(chan->inst, i + 4, 0x0436086c);
+		nvkm_wo32(chan->inst, i + 8, 0x000c001b);
 	}
 	for (i = 0x30b8; i < 0x30c8; i += 4)
 		nvkm_wo32(chan->inst, i, 0x0000ffff);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c
index 2207dac23981..300f5ed5de0b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv34.c
@@ -75,8 +75,8 @@ nv34_gr_chan_new(struct nvkm_gr *base, struct nvkm_fifo_chan *fifoch,
 		nvkm_wo32(chan->inst, i, 0x00040004);
 	for (i = 0x15ac; i <= 0x271c ; i += 16) {
 		nvkm_wo32(chan->inst, i + 0, 0x10700ff9);
-		nvkm_wo32(chan->inst, i + 1, 0x0436086c);
-		nvkm_wo32(chan->inst, i + 2, 0x000c001b);
+		nvkm_wo32(chan->inst, i + 4, 0x0436086c);
+		nvkm_wo32(chan->inst, i + 8, 0x000c001b);
 	}
 	for (i = 0x274c; i < 0x275c; i += 4)
 		nvkm_wo32(chan->inst, i, 0x0000ffff);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c
index e15b9627b07e..f3c30b2a788e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c
@@ -26,6 +26,49 @@
 #include <subdev/bios.h>
 #include <subdev/bios/bmp.h>
 #include <subdev/bios/bit.h>
+#include <subdev/bios/image.h>
+
+static bool
+nvbios_addr(struct nvkm_bios *bios, u32 *addr, u8 size)
+{
+	u32 p = *addr;
+
+	if (*addr > bios->image0_size && bios->imaged_addr) {
+		*addr -= bios->image0_size;
+		*addr += bios->imaged_addr;
+	}
+
+	if (unlikely(*addr + size >= bios->size)) {
+		nvkm_error(&bios->subdev, "OOB %d %08x %08x\n", size, p, *addr);
+		return false;
+	}
+
+	return true;
+}
+
+u8
+nvbios_rd08(struct nvkm_bios *bios, u32 addr)
+{
+	if (likely(nvbios_addr(bios, &addr, 1)))
+		return bios->data[addr];
+	return 0x00;
+}
+
+u16
+nvbios_rd16(struct nvkm_bios *bios, u32 addr)
+{
+	if (likely(nvbios_addr(bios, &addr, 2)))
+		return get_unaligned_le16(&bios->data[addr]);
+	return 0x0000;
+}
+
+u32
+nvbios_rd32(struct nvkm_bios *bios, u32 addr)
+{
+	if (likely(nvbios_addr(bios, &addr, 4)))
+		return get_unaligned_le32(&bios->data[addr]);
+	return 0x00000000;
+}
 
 u8
 nvbios_checksum(const u8 *data, int size)
@@ -100,8 +143,9 @@ int
 nvkm_bios_new(struct nvkm_device *device, int index, struct nvkm_bios **pbios)
 {
 	struct nvkm_bios *bios;
+	struct nvbios_image image;
 	struct bit_entry bit_i;
-	int ret;
+	int ret, idx = 0;
 
 	if (!(bios = *pbios = kzalloc(sizeof(*bios), GFP_KERNEL)))
 		return -ENOMEM;
@@ -111,6 +155,19 @@ nvkm_bios_new(struct nvkm_device *device, int index, struct nvkm_bios **pbios)
 	if (ret)
 		return ret;
 
+	/* Some tables have weird pointers that need adjustment before
+	 * they're dereferenced.  I'm not entirely sure why...
+	 */
+	if (nvbios_image(bios, idx++, &image)) {
+		bios->image0_size = image.size;
+		while (nvbios_image(bios, idx++, &image)) {
+			if (image.type == 0xe0) {
+				bios->imaged_addr = image.base;
+				break;
+			}
+		}
+	}
+
 	/* detect type of vbios we're dealing with */
 	bios->bmp_offset = nvbios_findstr(bios->data, bios->size,
 					  "\xff\x7f""NV\0", 5);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c
index 05332476354a..d89e78c4e689 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c
@@ -40,6 +40,7 @@ nvbios_dp_table(struct nvkm_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
 				case 0x30:
 				case 0x40:
 				case 0x41:
+				case 0x42:
 					*hdr = nvbios_rd08(bios, data + 0x01);
 					*len = nvbios_rd08(bios, data + 0x02);
 					*cnt = nvbios_rd08(bios, data + 0x03);
@@ -70,6 +71,7 @@ nvbios_dpout_entry(struct nvkm_bios *bios, u8 idx,
 			break;
 		case 0x40:
 		case 0x41:
+		case 0x42:
 			*hdr = nvbios_rd08(bios, data + 0x04);
 			*cnt = 0;
 			*len = 0;
@@ -109,6 +111,7 @@ nvbios_dpout_parse(struct nvkm_bios *bios, u8 idx,
 			break;
 		case 0x40:
 		case 0x41:
+		case 0x42:
 			info->flags     = nvbios_rd08(bios, data + 0x04);
 			info->script[0] = nvbios_rd16(bios, data + 0x05);
 			info->script[1] = nvbios_rd16(bios, data + 0x07);
@@ -180,6 +183,11 @@ nvbios_dpcfg_parse(struct nvkm_bios *bios, u16 outp, u8 idx,
 			info->pe    = nvbios_rd08(bios, data + 0x02);
 			info->tx_pu = nvbios_rd08(bios, data + 0x03);
 			break;
+		case 0x42:
+			info->dc    = nvbios_rd08(bios, data + 0x00);
+			info->pe    = nvbios_rd08(bios, data + 0x01);
+			info->tx_pu = nvbios_rd08(bios, data + 0x02);
+			break;
 		default:
 			data = 0x0000;
 			break;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/image.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/image.c
index 74b14cf09308..1dbff7aeafec 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/image.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/image.c
@@ -68,11 +68,16 @@ nvbios_imagen(struct nvkm_bios *bios, struct nvbios_image *image)
 bool
 nvbios_image(struct nvkm_bios *bios, int idx, struct nvbios_image *image)
 {
+	u32 imaged_addr = bios->imaged_addr;
 	memset(image, 0x00, sizeof(*image));
+	bios->imaged_addr = 0;
 	do {
 		image->base += image->size;
-		if (image->last || !nvbios_imagen(bios, image))
+		if (image->last || !nvbios_imagen(bios, image)) {
+			bios->imaged_addr = imaged_addr;
 			return false;
+		}
 	} while(idx--);
+	bios->imaged_addr = imaged_addr;
 	return true;
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c
index 91a7dc56e406..2ca23a9157ab 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c
@@ -77,15 +77,17 @@ g84_pll_mapping[] = {
 	{}
 };
 
-static u16
+static u32
 pll_limits_table(struct nvkm_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
 {
 	struct bit_entry bit_C;
-	u16 data = 0x0000;
+	u32 data = 0x0000;
 
 	if (!bit_entry(bios, 'C', &bit_C)) {
 		if (bit_C.version == 1 && bit_C.length >= 10)
 			data = nvbios_rd16(bios, bit_C.offset + 8);
+		if (bit_C.version == 2 && bit_C.length >= 4)
+			data = nvbios_rd32(bios, bit_C.offset + 0);
 		if (data) {
 			*ver = nvbios_rd08(bios, data + 0);
 			*hdr = nvbios_rd08(bios, data + 1);
@@ -137,12 +139,12 @@ pll_map(struct nvkm_bios *bios)
 	}
 }
 
-static u16
+static u32
 pll_map_reg(struct nvkm_bios *bios, u32 reg, u32 *type, u8 *ver, u8 *len)
 {
 	struct pll_mapping *map;
 	u8  hdr, cnt;
-	u16 data;
+	u32 data;
 
 	data = pll_limits_table(bios, ver, &hdr, &cnt, len);
 	if (data && *ver >= 0x30) {
@@ -160,7 +162,7 @@ pll_map_reg(struct nvkm_bios *bios, u32 reg, u32 *type, u8 *ver, u8 *len)
 	map = pll_map(bios);
 	while (map && map->reg) {
 		if (map->reg == reg && *ver >= 0x20) {
-			u16 addr = (data += hdr);
+			u32 addr = (data += hdr);
 			*type = map->type;
 			while (cnt--) {
 				if (nvbios_rd32(bios, data) == map->reg)
@@ -179,12 +181,12 @@ pll_map_reg(struct nvkm_bios *bios, u32 reg, u32 *type, u8 *ver, u8 *len)
 	return 0x0000;
 }
 
-static u16
+static u32
 pll_map_type(struct nvkm_bios *bios, u8 type, u32 *reg, u8 *ver, u8 *len)
 {
 	struct pll_mapping *map;
 	u8  hdr, cnt;
-	u16 data;
+	u32 data;
 
 	data = pll_limits_table(bios, ver, &hdr, &cnt, len);
 	if (data && *ver >= 0x30) {
@@ -202,7 +204,7 @@ pll_map_type(struct nvkm_bios *bios, u8 type, u32 *reg, u8 *ver, u8 *len)
 	map = pll_map(bios);
 	while (map && map->reg) {
 		if (map->type == type && *ver >= 0x20) {
-			u16 addr = (data += hdr);
+			u32 addr = (data += hdr);
 			*reg = map->reg;
 			while (cnt--) {
 				if (nvbios_rd32(bios, data) == map->reg)
@@ -228,7 +230,7 @@ nvbios_pll_parse(struct nvkm_bios *bios, u32 type, struct nvbios_pll *info)
 	struct nvkm_device *device = subdev->device;
 	u8  ver, len;
 	u32 reg = type;
-	u16 data;
+	u32 data;
 
 	if (type > PLL_MAX) {
 		reg  = type;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pmu.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pmu.c
index c268e5afe852..b4a308f3cf7b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pmu.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pmu.c
@@ -26,21 +26,6 @@
 #include <subdev/bios/image.h>
 #include <subdev/bios/pmu.h>
 
-static u32
-weirdo_pointer(struct nvkm_bios *bios, u32 data)
-{
-	struct nvbios_image image;
-	int idx = 0;
-	if (nvbios_image(bios, idx++, &image)) {
-		data -= image.size;
-		while (nvbios_image(bios, idx++, &image)) {
-			if (image.type == 0xe0)
-				return image.base + data;
-		}
-	}
-	return 0;
-}
-
 u32
 nvbios_pmuTe(struct nvkm_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
 {
@@ -50,7 +35,7 @@ nvbios_pmuTe(struct nvkm_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
 	if (!bit_entry(bios, 'p', &bit_p)) {
 		if (bit_p.version == 2 && bit_p.length >= 4)
 			data = nvbios_rd32(bios, bit_p.offset + 0x00);
-		if ((data = weirdo_pointer(bios, data))) {
+		if (data) {
 			*ver = nvbios_rd08(bios, data + 0x00); /* maybe? */
 			*hdr = nvbios_rd08(bios, data + 0x01);
 			*len = nvbios_rd08(bios, data + 0x02);
@@ -97,8 +82,7 @@ nvbios_pmuRm(struct nvkm_bios *bios, u8 type, struct nvbios_pmuR *info)
 	u32 data;
 	memset(info, 0x00, sizeof(*info));
 	while ((data = nvbios_pmuEp(bios, idx++, &ver, &hdr, &pmuE))) {
-		if ( pmuE.type == type &&
-		    (data = weirdo_pointer(bios, pmuE.data))) {
+		if (pmuE.type == type && (data = pmuE.data)) {
 			info->init_addr_pmu = nvbios_rd32(bios, data + 0x08);
 			info->args_addr_pmu = nvbios_rd32(bios, data + 0x0c);
 			info->boot_addr     = data + 0x30;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/rammap.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/rammap.c
index d0ae7454764e..b57c370c725d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/rammap.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/rammap.c
@@ -30,11 +30,11 @@ nvbios_rammapTe(struct nvkm_bios *bios, u8 *ver, u8 *hdr,
 		u8 *cnt, u8 *len, u8 *snr, u8 *ssz)
 {
 	struct bit_entry bit_P;
-	u16 rammap = 0x0000;
+	u32 rammap = 0x0000;
 
 	if (!bit_entry(bios, 'P', &bit_P)) {
 		if (bit_P.version == 2)
-			rammap = nvbios_rd16(bios, bit_P.offset + 4);
+			rammap = nvbios_rd32(bios, bit_P.offset + 4);
 
 		if (rammap) {
 			*ver = nvbios_rd08(bios, rammap + 0);
@@ -61,7 +61,7 @@ nvbios_rammapEe(struct nvkm_bios *bios, int idx,
 		u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
 {
 	u8  snr, ssz;
-	u16 rammap = nvbios_rammapTe(bios, ver, hdr, cnt, len, &snr, &ssz);
+	u32 rammap = nvbios_rammapTe(bios, ver, hdr, cnt, len, &snr, &ssz);
 	if (rammap && idx < *cnt) {
 		rammap = rammap + *hdr + (idx * (*len + (snr * ssz)));
 		*hdr = *len;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gf100.c
index 78c449b417b7..89d5543118cf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gf100.c
@@ -99,7 +99,7 @@ read_div(struct gf100_clk *clk, int doff, u32 dsrc, u32 dctl)
 {
 	struct nvkm_device *device = clk->base.subdev.device;
 	u32 ssrc = nvkm_rd32(device, dsrc + (doff * 4));
-	u32 sctl = nvkm_rd32(device, dctl + (doff * 4));
+	u32 sclk, sctl, sdiv = 2;
 
 	switch (ssrc & 0x00000003) {
 	case 0:
@@ -109,13 +109,21 @@ read_div(struct gf100_clk *clk, int doff, u32 dsrc, u32 dctl)
 	case 2:
 		return 100000;
 	case 3:
-		if (sctl & 0x80000000) {
-			u32 sclk = read_vco(clk, dsrc + (doff * 4));
-			u32 sdiv = (sctl & 0x0000003f) + 2;
-			return (sclk * 2) / sdiv;
+		sclk = read_vco(clk, dsrc + (doff * 4));
+
+		/* Memclk has doff of 0 despite its alt. location */
+		if (doff <= 2) {
+			sctl = nvkm_rd32(device, dctl + (doff * 4));
+
+			if (sctl & 0x80000000) {
+				if (ssrc & 0x100)
+					sctl >>= 8;
+
+				sdiv = (sctl & 0x3f) + 2;
+			}
 		}
 
-		return read_vco(clk, dsrc + (doff * 4));
+		return (sclk * 2) / sdiv;
 	default:
 		return 0;
 	}
@@ -366,11 +374,17 @@ gf100_clk_prog_2(struct gf100_clk *clk, int idx)
 		if (info->coef) {
 			nvkm_wr32(device, addr + 0x04, info->coef);
 			nvkm_mask(device, addr + 0x00, 0x00000001, 0x00000001);
+
+			/* Test PLL lock */
+			nvkm_mask(device, addr + 0x00, 0x00000010, 0x00000000);
 			nvkm_msec(device, 2000,
 				if (nvkm_rd32(device, addr + 0x00) & 0x00020000)
 					break;
 			);
-			nvkm_mask(device, addr + 0x00, 0x00020004, 0x00000004);
+			nvkm_mask(device, addr + 0x00, 0x00000010, 0x00000010);
+
+			/* Enable sync mode */
+			nvkm_mask(device, addr + 0x00, 0x00000004, 0x00000004);
 		}
 	}
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk104.c
index 975c401bccab..06bc0d2d6ae1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk104.c
@@ -393,11 +393,17 @@ gk104_clk_prog_2(struct gk104_clk *clk, int idx)
 	if (info->coef) {
 		nvkm_wr32(device, addr + 0x04, info->coef);
 		nvkm_mask(device, addr + 0x00, 0x00000001, 0x00000001);
+
+		/* Test PLL lock */
+		nvkm_mask(device, addr + 0x00, 0x00000010, 0x00000000);
 		nvkm_msec(device, 2000,
 			if (nvkm_rd32(device, addr + 0x00) & 0x00020000)
 				break;
 		);
-		nvkm_mask(device, addr + 0x00, 0x00020004, 0x00000004);
+		nvkm_mask(device, addr + 0x00, 0x00000010, 0x00000010);
+
+		/* Enable sync mode */
+		nvkm_mask(device, addr + 0x00, 0x00000004, 0x00000004);
 	}
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk20a.c
index 5f0ee24e31b8..218893e3e5f9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk20a.c
@@ -28,69 +28,6 @@
 #include <core/tegra.h>
 #include <subdev/timer.h>
 
-#define KHZ (1000)
-#define MHZ (KHZ * 1000)
-
-#define MASK(w)	((1 << w) - 1)
-
-#define GPCPLL_CFG		(SYS_GPCPLL_CFG_BASE + 0)
-#define GPCPLL_CFG_ENABLE	BIT(0)
-#define GPCPLL_CFG_IDDQ		BIT(1)
-#define GPCPLL_CFG_LOCK_DET_OFF	BIT(4)
-#define GPCPLL_CFG_LOCK		BIT(17)
-
-#define GPCPLL_COEFF		(SYS_GPCPLL_CFG_BASE + 4)
-#define GPCPLL_COEFF_M_SHIFT	0
-#define GPCPLL_COEFF_M_WIDTH	8
-#define GPCPLL_COEFF_N_SHIFT	8
-#define GPCPLL_COEFF_N_WIDTH	8
-#define GPCPLL_COEFF_P_SHIFT	16
-#define GPCPLL_COEFF_P_WIDTH	6
-
-#define GPCPLL_CFG2			(SYS_GPCPLL_CFG_BASE + 0xc)
-#define GPCPLL_CFG2_SETUP2_SHIFT	16
-#define GPCPLL_CFG2_PLL_STEPA_SHIFT	24
-
-#define GPCPLL_CFG3			(SYS_GPCPLL_CFG_BASE + 0x18)
-#define GPCPLL_CFG3_PLL_STEPB_SHIFT	16
-
-#define GPC_BCASE_GPCPLL_CFG_BASE		0x00132800
-#define GPCPLL_NDIV_SLOWDOWN			(SYS_GPCPLL_CFG_BASE + 0x1c)
-#define GPCPLL_NDIV_SLOWDOWN_NDIV_LO_SHIFT	0
-#define GPCPLL_NDIV_SLOWDOWN_NDIV_MID_SHIFT	8
-#define GPCPLL_NDIV_SLOWDOWN_STEP_SIZE_LO2MID_SHIFT	16
-#define GPCPLL_NDIV_SLOWDOWN_SLOWDOWN_USING_PLL_SHIFT	22
-#define GPCPLL_NDIV_SLOWDOWN_EN_DYNRAMP_SHIFT	31
-
-#define SEL_VCO				(SYS_GPCPLL_CFG_BASE + 0x100)
-#define SEL_VCO_GPC2CLK_OUT_SHIFT	0
-
-#define GPC2CLK_OUT			(SYS_GPCPLL_CFG_BASE + 0x250)
-#define GPC2CLK_OUT_SDIV14_INDIV4_WIDTH	1
-#define GPC2CLK_OUT_SDIV14_INDIV4_SHIFT	31
-#define GPC2CLK_OUT_SDIV14_INDIV4_MODE	1
-#define GPC2CLK_OUT_VCODIV_WIDTH	6
-#define GPC2CLK_OUT_VCODIV_SHIFT	8
-#define GPC2CLK_OUT_VCODIV1		0
-#define GPC2CLK_OUT_VCODIV_MASK		(MASK(GPC2CLK_OUT_VCODIV_WIDTH) << \
-					GPC2CLK_OUT_VCODIV_SHIFT)
-#define GPC2CLK_OUT_BYPDIV_WIDTH	6
-#define GPC2CLK_OUT_BYPDIV_SHIFT	0
-#define GPC2CLK_OUT_BYPDIV31		0x3c
-#define GPC2CLK_OUT_INIT_MASK	((MASK(GPC2CLK_OUT_SDIV14_INDIV4_WIDTH) << \
-		GPC2CLK_OUT_SDIV14_INDIV4_SHIFT)\
-		| (MASK(GPC2CLK_OUT_VCODIV_WIDTH) << GPC2CLK_OUT_VCODIV_SHIFT)\
-		| (MASK(GPC2CLK_OUT_BYPDIV_WIDTH) << GPC2CLK_OUT_BYPDIV_SHIFT))
-#define GPC2CLK_OUT_INIT_VAL	((GPC2CLK_OUT_SDIV14_INDIV4_MODE << \
-		GPC2CLK_OUT_SDIV14_INDIV4_SHIFT) \
-		| (GPC2CLK_OUT_VCODIV1 << GPC2CLK_OUT_VCODIV_SHIFT) \
-		| (GPC2CLK_OUT_BYPDIV31 << GPC2CLK_OUT_BYPDIV_SHIFT))
-
-#define GPC_BCAST_NDIV_SLOWDOWN_DEBUG	(GPC_BCASE_GPCPLL_CFG_BASE + 0xa0)
-#define GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_SHIFT	24
-#define GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_MASK \
-	    (0x1 << GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_SHIFT)
-
 static const u8 _pl_to_div[] = {
 /* PL:   0, 1, 2, 3, 4, 5, 6,  7,  8,  9, 10, 11, 12, 13, 14 */
 /* p: */ 1, 2, 3, 4, 5, 6, 8, 10, 12, 16, 12, 16, 20, 24, 32,
@@ -124,7 +61,7 @@ static const struct gk20a_clk_pllg_params gk20a_pllg_params = {
 	.min_pl = 1, .max_pl = 32,
 };
 
-static void
+void
 gk20a_pllg_read_mnp(struct gk20a_clk *clk, struct gk20a_pll *pll)
 {
 	struct nvkm_device *device = clk->base.subdev.device;
@@ -136,20 +73,33 @@ gk20a_pllg_read_mnp(struct gk20a_clk *clk, struct gk20a_pll *pll)
 	pll->pl = (val >> GPCPLL_COEFF_P_SHIFT) & MASK(GPCPLL_COEFF_P_WIDTH);
 }
 
-static u32
-gk20a_pllg_calc_rate(struct gk20a_clk *clk)
+void
+gk20a_pllg_write_mnp(struct gk20a_clk *clk, const struct gk20a_pll *pll)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 val;
+
+	val = (pll->m & MASK(GPCPLL_COEFF_M_WIDTH)) << GPCPLL_COEFF_M_SHIFT;
+	val |= (pll->n & MASK(GPCPLL_COEFF_N_WIDTH)) << GPCPLL_COEFF_N_SHIFT;
+	val |= (pll->pl & MASK(GPCPLL_COEFF_P_WIDTH)) << GPCPLL_COEFF_P_SHIFT;
+	nvkm_wr32(device, GPCPLL_COEFF, val);
+}
+
+u32
+gk20a_pllg_calc_rate(struct gk20a_clk *clk, struct gk20a_pll *pll)
 {
 	u32 rate;
 	u32 divider;
 
-	rate = clk->parent_rate * clk->pll.n;
-	divider = clk->pll.m * clk->pl_to_div(clk->pll.pl);
+	rate = clk->parent_rate * pll->n;
+	divider = pll->m * clk->pl_to_div(pll->pl);
 
 	return rate / divider / 2;
 }
 
-static int
-gk20a_pllg_calc_mnp(struct gk20a_clk *clk, unsigned long rate)
+int
+gk20a_pllg_calc_mnp(struct gk20a_clk *clk, unsigned long rate,
+		    struct gk20a_pll *pll)
 {
 	struct nvkm_subdev *subdev = &clk->base.subdev;
 	u32 target_clk_f, ref_clk_f, target_freq;
@@ -163,16 +113,13 @@ gk20a_pllg_calc_mnp(struct gk20a_clk *clk, unsigned long rate)
 	target_clk_f = rate * 2 / KHZ;
 	ref_clk_f = clk->parent_rate / KHZ;
 
-	max_vco_f = clk->params->max_vco;
+	target_vco_f = target_clk_f + target_clk_f / 50;
+	max_vco_f = max(clk->params->max_vco, target_vco_f);
 	min_vco_f = clk->params->min_vco;
 	best_m = clk->params->max_m;
 	best_n = clk->params->min_n;
 	best_pl = clk->params->min_pl;
 
-	target_vco_f = target_clk_f + target_clk_f / 50;
-	if (max_vco_f < target_vco_f)
-		max_vco_f = target_vco_f;
-
 	/* min_pl <= high_pl <= max_pl */
 	high_pl = (max_vco_f + target_vco_f - 1) / target_vco_f;
 	high_pl = min(high_pl, clk->params->max_pl);
@@ -195,9 +142,7 @@ gk20a_pllg_calc_mnp(struct gk20a_clk *clk, unsigned long rate)
 		target_vco_f = target_clk_f * clk->pl_to_div(pl);
 
 		for (m = clk->params->min_m; m <= clk->params->max_m; m++) {
-			u32 u_f, vco_f;
-
-			u_f = ref_clk_f / m;
+			u32 u_f = ref_clk_f / m;
 
 			if (u_f < clk->params->min_u)
 				break;
@@ -211,6 +156,8 @@ gk20a_pllg_calc_mnp(struct gk20a_clk *clk, unsigned long rate)
 				break;
 
 			for (; n <= n2; n++) {
+				u32 vco_f;
+
 				if (n < clk->params->min_n)
 					continue;
 				if (n > clk->params->max_n)
@@ -247,16 +194,16 @@ found_match:
 			   "no best match for target @ %dMHz on gpc_pll",
 			   target_clk_f / KHZ);
 
-	clk->pll.m = best_m;
-	clk->pll.n = best_n;
-	clk->pll.pl = best_pl;
+	pll->m = best_m;
+	pll->n = best_n;
+	pll->pl = best_pl;
 
-	target_freq = gk20a_pllg_calc_rate(clk);
+	target_freq = gk20a_pllg_calc_rate(clk, pll);
 
 	nvkm_debug(subdev,
-		   "actual target freq %d MHz, M %d, N %d, PL %d(div%d)\n",
-		   target_freq / MHZ, clk->pll.m, clk->pll.n, clk->pll.pl,
-		   clk->pl_to_div(clk->pll.pl));
+		   "actual target freq %d KHz, M %d, N %d, PL %d(div%d)\n",
+		   target_freq / KHZ, pll->m, pll->n, pll->pl,
+		   clk->pl_to_div(pll->pl));
 	return 0;
 }
 
@@ -265,45 +212,36 @@ gk20a_pllg_slide(struct gk20a_clk *clk, u32 n)
 {
 	struct nvkm_subdev *subdev = &clk->base.subdev;
 	struct nvkm_device *device = subdev->device;
-	u32 val;
-	int ramp_timeout;
+	struct gk20a_pll pll;
+	int ret = 0;
 
 	/* get old coefficients */
-	val = nvkm_rd32(device, GPCPLL_COEFF);
+	gk20a_pllg_read_mnp(clk, &pll);
 	/* do nothing if NDIV is the same */
-	if (n == ((val >> GPCPLL_COEFF_N_SHIFT) & MASK(GPCPLL_COEFF_N_WIDTH)))
+	if (n == pll.n)
 		return 0;
 
-	/* setup */
-	nvkm_mask(device, GPCPLL_CFG2, 0xff << GPCPLL_CFG2_PLL_STEPA_SHIFT,
-		0x2b << GPCPLL_CFG2_PLL_STEPA_SHIFT);
-	nvkm_mask(device, GPCPLL_CFG3, 0xff << GPCPLL_CFG3_PLL_STEPB_SHIFT,
-		0xb << GPCPLL_CFG3_PLL_STEPB_SHIFT);
-
 	/* pll slowdown mode */
 	nvkm_mask(device, GPCPLL_NDIV_SLOWDOWN,
 		BIT(GPCPLL_NDIV_SLOWDOWN_SLOWDOWN_USING_PLL_SHIFT),
 		BIT(GPCPLL_NDIV_SLOWDOWN_SLOWDOWN_USING_PLL_SHIFT));
 
 	/* new ndiv ready for ramp */
-	val = nvkm_rd32(device, GPCPLL_COEFF);
-	val &= ~(MASK(GPCPLL_COEFF_N_WIDTH) << GPCPLL_COEFF_N_SHIFT);
-	val |= (n & MASK(GPCPLL_COEFF_N_WIDTH)) << GPCPLL_COEFF_N_SHIFT;
+	pll.n = n;
 	udelay(1);
-	nvkm_wr32(device, GPCPLL_COEFF, val);
+	gk20a_pllg_write_mnp(clk, &pll);
 
 	/* dynamic ramp to new ndiv */
-	val = nvkm_rd32(device, GPCPLL_NDIV_SLOWDOWN);
-	val |= 0x1 << GPCPLL_NDIV_SLOWDOWN_EN_DYNRAMP_SHIFT;
 	udelay(1);
-	nvkm_wr32(device, GPCPLL_NDIV_SLOWDOWN, val);
+	nvkm_mask(device, GPCPLL_NDIV_SLOWDOWN,
+		  BIT(GPCPLL_NDIV_SLOWDOWN_EN_DYNRAMP_SHIFT),
+		  BIT(GPCPLL_NDIV_SLOWDOWN_EN_DYNRAMP_SHIFT));
 
-	for (ramp_timeout = 500; ramp_timeout > 0; ramp_timeout--) {
-		udelay(1);
-		val = nvkm_rd32(device, GPC_BCAST_NDIV_SLOWDOWN_DEBUG);
-		if (val & GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_MASK)
-			break;
-	}
+	/* wait for ramping to complete */
+	if (nvkm_wait_usec(device, 500, GPC_BCAST_NDIV_SLOWDOWN_DEBUG,
+		GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_MASK,
+		GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_MASK) < 0)
+		ret = -ETIMEDOUT;
 
 	/* exit slowdown mode */
 	nvkm_mask(device, GPCPLL_NDIV_SLOWDOWN,
@@ -311,21 +249,35 @@ gk20a_pllg_slide(struct gk20a_clk *clk, u32 n)
 		BIT(GPCPLL_NDIV_SLOWDOWN_EN_DYNRAMP_SHIFT), 0);
 	nvkm_rd32(device, GPCPLL_NDIV_SLOWDOWN);
 
-	if (ramp_timeout <= 0) {
-		nvkm_error(subdev, "gpcpll dynamic ramp timeout\n");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
+	return ret;
 }
 
-static void
+static int
 gk20a_pllg_enable(struct gk20a_clk *clk)
 {
 	struct nvkm_device *device = clk->base.subdev.device;
+	u32 val;
 
 	nvkm_mask(device, GPCPLL_CFG, GPCPLL_CFG_ENABLE, GPCPLL_CFG_ENABLE);
 	nvkm_rd32(device, GPCPLL_CFG);
+
+	/* enable lock detection */
+	val = nvkm_rd32(device, GPCPLL_CFG);
+	if (val & GPCPLL_CFG_LOCK_DET_OFF) {
+		val &= ~GPCPLL_CFG_LOCK_DET_OFF;
+		nvkm_wr32(device, GPCPLL_CFG, val);
+	}
+
+	/* wait for lock */
+	if (nvkm_wait_usec(device, 300, GPCPLL_CFG, GPCPLL_CFG_LOCK,
+			   GPCPLL_CFG_LOCK) < 0)
+		return -ETIMEDOUT;
+
+	/* switch to VCO mode */
+	nvkm_mask(device, SEL_VCO, BIT(SEL_VCO_GPC2CLK_OUT_SHIFT),
+		BIT(SEL_VCO_GPC2CLK_OUT_SHIFT));
+
+	return 0;
 }
 
 static void
@@ -333,117 +285,81 @@ gk20a_pllg_disable(struct gk20a_clk *clk)
 {
 	struct nvkm_device *device = clk->base.subdev.device;
 
+	/* put PLL in bypass before disabling it */
+	nvkm_mask(device, SEL_VCO, BIT(SEL_VCO_GPC2CLK_OUT_SHIFT), 0);
+
 	nvkm_mask(device, GPCPLL_CFG, GPCPLL_CFG_ENABLE, 0);
 	nvkm_rd32(device, GPCPLL_CFG);
 }
 
 static int
-_gk20a_pllg_program_mnp(struct gk20a_clk *clk, bool allow_slide)
+gk20a_pllg_program_mnp(struct gk20a_clk *clk, const struct gk20a_pll *pll)
 {
 	struct nvkm_subdev *subdev = &clk->base.subdev;
 	struct nvkm_device *device = subdev->device;
-	u32 val, cfg;
-	struct gk20a_pll old_pll;
-	u32 n_lo;
-
-	/* get old coefficients */
-	gk20a_pllg_read_mnp(clk, &old_pll);
-
-	/* do NDIV slide if there is no change in M and PL */
-	cfg = nvkm_rd32(device, GPCPLL_CFG);
-	if (allow_slide && clk->pll.m == old_pll.m &&
-	    clk->pll.pl == old_pll.pl && (cfg & GPCPLL_CFG_ENABLE)) {
-		return gk20a_pllg_slide(clk, clk->pll.n);
-	}
-
-	/* slide down to NDIV_LO */
-	if (allow_slide && (cfg & GPCPLL_CFG_ENABLE)) {
-		int ret;
-
-		n_lo = DIV_ROUND_UP(old_pll.m * clk->params->min_vco,
-				    clk->parent_rate / KHZ);
-		ret = gk20a_pllg_slide(clk, n_lo);
+	struct gk20a_pll cur_pll;
+	int ret;
 
-		if (ret)
-			return ret;
-	}
+	gk20a_pllg_read_mnp(clk, &cur_pll);
 
-	/* split FO-to-bypass jump in halfs by setting out divider 1:2 */
+	/* split VCO-to-bypass jump in half by setting out divider 1:2 */
 	nvkm_mask(device, GPC2CLK_OUT, GPC2CLK_OUT_VCODIV_MASK,
-		0x2 << GPC2CLK_OUT_VCODIV_SHIFT);
-
-	/* put PLL in bypass before programming it */
-	val = nvkm_rd32(device, SEL_VCO);
-	val &= ~(BIT(SEL_VCO_GPC2CLK_OUT_SHIFT));
+		  GPC2CLK_OUT_VCODIV2 << GPC2CLK_OUT_VCODIV_SHIFT);
+	/* Intentional 2nd write to assure linear divider operation */
+	nvkm_mask(device, GPC2CLK_OUT, GPC2CLK_OUT_VCODIV_MASK,
+		  GPC2CLK_OUT_VCODIV2 << GPC2CLK_OUT_VCODIV_SHIFT);
+	nvkm_rd32(device, GPC2CLK_OUT);
 	udelay(2);
-	nvkm_wr32(device, SEL_VCO, val);
-
-	/* get out from IDDQ */
-	val = nvkm_rd32(device, GPCPLL_CFG);
-	if (val & GPCPLL_CFG_IDDQ) {
-		val &= ~GPCPLL_CFG_IDDQ;
-		nvkm_wr32(device, GPCPLL_CFG, val);
-		nvkm_rd32(device, GPCPLL_CFG);
-		udelay(2);
-	}
 
 	gk20a_pllg_disable(clk);
 
-	nvkm_debug(subdev, "%s: m=%d n=%d pl=%d\n", __func__,
-		   clk->pll.m, clk->pll.n, clk->pll.pl);
-
-	n_lo = DIV_ROUND_UP(clk->pll.m * clk->params->min_vco,
-			    clk->parent_rate / KHZ);
-	val = clk->pll.m << GPCPLL_COEFF_M_SHIFT;
-	val |= (allow_slide ? n_lo : clk->pll.n) << GPCPLL_COEFF_N_SHIFT;
-	val |= clk->pll.pl << GPCPLL_COEFF_P_SHIFT;
-	nvkm_wr32(device, GPCPLL_COEFF, val);
+	gk20a_pllg_write_mnp(clk, pll);
 
-	gk20a_pllg_enable(clk);
-
-	val = nvkm_rd32(device, GPCPLL_CFG);
-	if (val & GPCPLL_CFG_LOCK_DET_OFF) {
-		val &= ~GPCPLL_CFG_LOCK_DET_OFF;
-		nvkm_wr32(device, GPCPLL_CFG, val);
-	}
-
-	if (nvkm_usec(device, 300,
-		if (nvkm_rd32(device, GPCPLL_CFG) & GPCPLL_CFG_LOCK)
-			break;
-	) < 0)
-		return -ETIMEDOUT;
-
-	/* switch to VCO mode */
-	nvkm_mask(device, SEL_VCO, BIT(SEL_VCO_GPC2CLK_OUT_SHIFT),
-		  BIT(SEL_VCO_GPC2CLK_OUT_SHIFT));
+	ret = gk20a_pllg_enable(clk);
+	if (ret)
+		return ret;
 
 	/* restore out divider 1:1 */
-	val = nvkm_rd32(device, GPC2CLK_OUT);
-	if ((val & GPC2CLK_OUT_VCODIV_MASK) !=
-	    (GPC2CLK_OUT_VCODIV1 << GPC2CLK_OUT_VCODIV_SHIFT)) {
-		val &= ~GPC2CLK_OUT_VCODIV_MASK;
-		val |= GPC2CLK_OUT_VCODIV1 << GPC2CLK_OUT_VCODIV_SHIFT;
-		udelay(2);
-		nvkm_wr32(device, GPC2CLK_OUT, val);
-		/* Intentional 2nd write to assure linear divider operation */
-		nvkm_wr32(device, GPC2CLK_OUT, val);
-		nvkm_rd32(device, GPC2CLK_OUT);
-	}
+	udelay(2);
+	nvkm_mask(device, GPC2CLK_OUT, GPC2CLK_OUT_VCODIV_MASK,
+		  GPC2CLK_OUT_VCODIV1 << GPC2CLK_OUT_VCODIV_SHIFT);
+	/* Intentional 2nd write to assure linear divider operation */
+	nvkm_mask(device, GPC2CLK_OUT, GPC2CLK_OUT_VCODIV_MASK,
+		  GPC2CLK_OUT_VCODIV1 << GPC2CLK_OUT_VCODIV_SHIFT);
+	nvkm_rd32(device, GPC2CLK_OUT);
 
-	/* slide up to new NDIV */
-	return allow_slide ? gk20a_pllg_slide(clk, clk->pll.n) : 0;
+	return 0;
 }
 
 static int
-gk20a_pllg_program_mnp(struct gk20a_clk *clk)
+gk20a_pllg_program_mnp_slide(struct gk20a_clk *clk, const struct gk20a_pll *pll)
 {
-	int err;
+	struct gk20a_pll cur_pll;
+	int ret;
 
-	err = _gk20a_pllg_program_mnp(clk, true);
-	if (err)
-		err = _gk20a_pllg_program_mnp(clk, false);
+	if (gk20a_pllg_is_enabled(clk)) {
+		gk20a_pllg_read_mnp(clk, &cur_pll);
+
+		/* just do NDIV slide if there is no change to M and PL */
+		if (pll->m == cur_pll.m && pll->pl == cur_pll.pl)
+			return gk20a_pllg_slide(clk, pll->n);
+
+		/* slide down to current NDIV_LO */
+		cur_pll.n = gk20a_pllg_n_lo(clk, &cur_pll);
+		ret = gk20a_pllg_slide(clk, cur_pll.n);
+		if (ret)
+			return ret;
+	}
+
+	/* program MNP with the new clock parameters and new NDIV_LO */
+	cur_pll = *pll;
+	cur_pll.n = gk20a_pllg_n_lo(clk, &cur_pll);
+	ret = gk20a_pllg_program_mnp(clk, &cur_pll);
+	if (ret)
+		return ret;
 
-	return err;
+	/* slide up to new NDIV */
+	return gk20a_pllg_slide(clk, pll->n);
 }
 
 static struct nvkm_pstate
@@ -546,13 +462,14 @@ gk20a_clk_read(struct nvkm_clk *base, enum nv_clk_src src)
 	struct gk20a_clk *clk = gk20a_clk(base);
 	struct nvkm_subdev *subdev = &clk->base.subdev;
 	struct nvkm_device *device = subdev->device;
+	struct gk20a_pll pll;
 
 	switch (src) {
 	case nv_clk_src_crystal:
 		return device->crystal;
 	case nv_clk_src_gpc:
-		gk20a_pllg_read_mnp(clk, &clk->pll);
-		return gk20a_pllg_calc_rate(clk) / GK20A_CLK_GPC_MDIV;
+		gk20a_pllg_read_mnp(clk, &pll);
+		return gk20a_pllg_calc_rate(clk, &pll) / GK20A_CLK_GPC_MDIV;
 	default:
 		nvkm_error(subdev, "invalid clock source %d\n", src);
 		return -EINVAL;
@@ -565,15 +482,20 @@ gk20a_clk_calc(struct nvkm_clk *base, struct nvkm_cstate *cstate)
 	struct gk20a_clk *clk = gk20a_clk(base);
 
 	return gk20a_pllg_calc_mnp(clk, cstate->domain[nv_clk_src_gpc] *
-					 GK20A_CLK_GPC_MDIV);
+					 GK20A_CLK_GPC_MDIV, &clk->pll);
 }
 
 int
 gk20a_clk_prog(struct nvkm_clk *base)
 {
 	struct gk20a_clk *clk = gk20a_clk(base);
+	int ret;
+
+	ret = gk20a_pllg_program_mnp_slide(clk, &clk->pll);
+	if (ret)
+		ret = gk20a_pllg_program_mnp(clk, &clk->pll);
 
-	return gk20a_pllg_program_mnp(clk);
+	return ret;
 }
 
 void
@@ -581,29 +503,62 @@ gk20a_clk_tidy(struct nvkm_clk *base)
 {
 }
 
+int
+gk20a_clk_setup_slide(struct gk20a_clk *clk)
+{
+	struct nvkm_subdev *subdev = &clk->base.subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 step_a, step_b;
+
+	switch (clk->parent_rate) {
+	case 12000000:
+	case 12800000:
+	case 13000000:
+		step_a = 0x2b;
+		step_b = 0x0b;
+		break;
+	case 19200000:
+		step_a = 0x12;
+		step_b = 0x08;
+		break;
+	case 38400000:
+		step_a = 0x04;
+		step_b = 0x05;
+		break;
+	default:
+		nvkm_error(subdev, "invalid parent clock rate %u KHz",
+			   clk->parent_rate / KHZ);
+		return -EINVAL;
+	}
+
+	nvkm_mask(device, GPCPLL_CFG2, 0xff << GPCPLL_CFG2_PLL_STEPA_SHIFT,
+		step_a << GPCPLL_CFG2_PLL_STEPA_SHIFT);
+	nvkm_mask(device, GPCPLL_CFG3, 0xff << GPCPLL_CFG3_PLL_STEPB_SHIFT,
+		step_b << GPCPLL_CFG3_PLL_STEPB_SHIFT);
+
+	return 0;
+}
+
 void
 gk20a_clk_fini(struct nvkm_clk *base)
 {
 	struct nvkm_device *device = base->subdev.device;
 	struct gk20a_clk *clk = gk20a_clk(base);
-	u32 val;
 
 	/* slide to VCO min */
-	val = nvkm_rd32(device, GPCPLL_CFG);
-	if (val & GPCPLL_CFG_ENABLE) {
+	if (gk20a_pllg_is_enabled(clk)) {
 		struct gk20a_pll pll;
 		u32 n_lo;
 
 		gk20a_pllg_read_mnp(clk, &pll);
-		n_lo = DIV_ROUND_UP(pll.m * clk->params->min_vco,
-				    clk->parent_rate / KHZ);
+		n_lo = gk20a_pllg_n_lo(clk, &pll);
 		gk20a_pllg_slide(clk, n_lo);
 	}
 
-	/* put PLL in bypass before disabling it */
-	nvkm_mask(device, SEL_VCO, BIT(SEL_VCO_GPC2CLK_OUT_SHIFT), 0);
-
 	gk20a_pllg_disable(clk);
+
+	/* set IDDQ */
+	nvkm_mask(device, GPCPLL_CFG, GPCPLL_CFG_IDDQ, 1);
 }
 
 static int
@@ -614,9 +569,18 @@ gk20a_clk_init(struct nvkm_clk *base)
 	struct nvkm_device *device = subdev->device;
 	int ret;
 
+	/* get out from IDDQ */
+	nvkm_mask(device, GPCPLL_CFG, GPCPLL_CFG_IDDQ, 0);
+	nvkm_rd32(device, GPCPLL_CFG);
+	udelay(5);
+
 	nvkm_mask(device, GPC2CLK_OUT, GPC2CLK_OUT_INIT_MASK,
 		  GPC2CLK_OUT_INIT_VAL);
 
+	ret = gk20a_clk_setup_slide(clk);
+	if (ret)
+		return ret;
+
 	/* Start with lowest frequency */
 	base->func->calc(base, &base->func->pstates[0].base);
 	ret = base->func->prog(&clk->base);
@@ -646,7 +610,7 @@ gk20a_clk = {
 };
 
 int
-_gk20a_clk_ctor(struct nvkm_device *device, int index,
+gk20a_clk_ctor(struct nvkm_device *device, int index,
 		const struct nvkm_clk_func *func,
 		const struct gk20a_clk_pllg_params *params,
 		struct gk20a_clk *clk)
@@ -685,7 +649,7 @@ gk20a_clk_new(struct nvkm_device *device, int index, struct nvkm_clk **pclk)
 		return -ENOMEM;
 	*pclk = &clk->base;
 
-	ret = _gk20a_clk_ctor(device, index, &gk20a_clk, &gk20a_pllg_params,
+	ret = gk20a_clk_ctor(device, index, &gk20a_clk, &gk20a_pllg_params,
 			      clk);
 
 	clk->pl_to_div = pl_to_div;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk20a.h b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk20a.h
index 13c46740197d..0d1450972162 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk20a.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk20a.h
@@ -24,9 +24,79 @@
 #ifndef __NVKM_CLK_GK20A_H__
 #define __NVKM_CLK_GK20A_H__
 
+#define KHZ (1000)
+#define MHZ (KHZ * 1000)
+
+#define MASK(w)	((1 << (w)) - 1)
+
 #define GK20A_CLK_GPC_MDIV 1000
 
 #define SYS_GPCPLL_CFG_BASE	0x00137000
+#define GPCPLL_CFG		(SYS_GPCPLL_CFG_BASE + 0)
+#define GPCPLL_CFG_ENABLE	BIT(0)
+#define GPCPLL_CFG_IDDQ		BIT(1)
+#define GPCPLL_CFG_LOCK_DET_OFF	BIT(4)
+#define GPCPLL_CFG_LOCK		BIT(17)
+
+#define GPCPLL_CFG2		(SYS_GPCPLL_CFG_BASE + 0xc)
+#define GPCPLL_CFG2_SETUP2_SHIFT	16
+#define GPCPLL_CFG2_PLL_STEPA_SHIFT	24
+
+#define GPCPLL_CFG3			(SYS_GPCPLL_CFG_BASE + 0x18)
+#define GPCPLL_CFG3_VCO_CTRL_SHIFT		0
+#define GPCPLL_CFG3_VCO_CTRL_WIDTH		9
+#define GPCPLL_CFG3_VCO_CTRL_MASK		\
+	(MASK(GPCPLL_CFG3_VCO_CTRL_WIDTH) << GPCPLL_CFG3_VCO_CTRL_SHIFT)
+#define GPCPLL_CFG3_PLL_STEPB_SHIFT		16
+#define GPCPLL_CFG3_PLL_STEPB_WIDTH		8
+
+#define GPCPLL_COEFF		(SYS_GPCPLL_CFG_BASE + 4)
+#define GPCPLL_COEFF_M_SHIFT	0
+#define GPCPLL_COEFF_M_WIDTH	8
+#define GPCPLL_COEFF_N_SHIFT	8
+#define GPCPLL_COEFF_N_WIDTH	8
+#define GPCPLL_COEFF_N_MASK	\
+	(MASK(GPCPLL_COEFF_N_WIDTH) << GPCPLL_COEFF_N_SHIFT)
+#define GPCPLL_COEFF_P_SHIFT	16
+#define GPCPLL_COEFF_P_WIDTH	6
+
+#define GPCPLL_NDIV_SLOWDOWN			(SYS_GPCPLL_CFG_BASE + 0x1c)
+#define GPCPLL_NDIV_SLOWDOWN_NDIV_LO_SHIFT	0
+#define GPCPLL_NDIV_SLOWDOWN_NDIV_MID_SHIFT	8
+#define GPCPLL_NDIV_SLOWDOWN_STEP_SIZE_LO2MID_SHIFT	16
+#define GPCPLL_NDIV_SLOWDOWN_SLOWDOWN_USING_PLL_SHIFT	22
+#define GPCPLL_NDIV_SLOWDOWN_EN_DYNRAMP_SHIFT	31
+
+#define GPC_BCAST_GPCPLL_CFG_BASE		0x00132800
+#define GPC_BCAST_NDIV_SLOWDOWN_DEBUG	(GPC_BCAST_GPCPLL_CFG_BASE + 0xa0)
+#define GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_SHIFT	24
+#define GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_MASK \
+	(0x1 << GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_SHIFT)
+
+#define SEL_VCO				(SYS_GPCPLL_CFG_BASE + 0x100)
+#define SEL_VCO_GPC2CLK_OUT_SHIFT	0
+
+#define GPC2CLK_OUT			(SYS_GPCPLL_CFG_BASE + 0x250)
+#define GPC2CLK_OUT_SDIV14_INDIV4_WIDTH	1
+#define GPC2CLK_OUT_SDIV14_INDIV4_SHIFT	31
+#define GPC2CLK_OUT_SDIV14_INDIV4_MODE	1
+#define GPC2CLK_OUT_VCODIV_WIDTH	6
+#define GPC2CLK_OUT_VCODIV_SHIFT	8
+#define GPC2CLK_OUT_VCODIV1		0
+#define GPC2CLK_OUT_VCODIV2		2
+#define GPC2CLK_OUT_VCODIV_MASK		(MASK(GPC2CLK_OUT_VCODIV_WIDTH) << \
+					GPC2CLK_OUT_VCODIV_SHIFT)
+#define GPC2CLK_OUT_BYPDIV_WIDTH	6
+#define GPC2CLK_OUT_BYPDIV_SHIFT	0
+#define GPC2CLK_OUT_BYPDIV31		0x3c
+#define GPC2CLK_OUT_INIT_MASK	((MASK(GPC2CLK_OUT_SDIV14_INDIV4_WIDTH) << \
+		GPC2CLK_OUT_SDIV14_INDIV4_SHIFT)\
+		| (MASK(GPC2CLK_OUT_VCODIV_WIDTH) << GPC2CLK_OUT_VCODIV_SHIFT)\
+		| (MASK(GPC2CLK_OUT_BYPDIV_WIDTH) << GPC2CLK_OUT_BYPDIV_SHIFT))
+#define GPC2CLK_OUT_INIT_VAL	((GPC2CLK_OUT_SDIV14_INDIV4_MODE << \
+		GPC2CLK_OUT_SDIV14_INDIV4_SHIFT) \
+		| (GPC2CLK_OUT_VCODIV1 << GPC2CLK_OUT_VCODIV_SHIFT) \
+		| (GPC2CLK_OUT_BYPDIV31 << GPC2CLK_OUT_BYPDIV_SHIFT))
 
 /* All frequencies in Khz */
 struct gk20a_clk_pllg_params {
@@ -54,7 +124,29 @@ struct gk20a_clk {
 };
 #define gk20a_clk(p) container_of((p), struct gk20a_clk, base)
 
-int _gk20a_clk_ctor(struct nvkm_device *, int, const struct nvkm_clk_func *,
+u32 gk20a_pllg_calc_rate(struct gk20a_clk *, struct gk20a_pll *);
+int gk20a_pllg_calc_mnp(struct gk20a_clk *, unsigned long, struct gk20a_pll *);
+void gk20a_pllg_read_mnp(struct gk20a_clk *, struct gk20a_pll *);
+void gk20a_pllg_write_mnp(struct gk20a_clk *, const struct gk20a_pll *);
+
+static inline bool
+gk20a_pllg_is_enabled(struct gk20a_clk *clk)
+{
+	struct nvkm_device *device = clk->base.subdev.device;
+	u32 val;
+
+	val = nvkm_rd32(device, GPCPLL_CFG);
+	return val & GPCPLL_CFG_ENABLE;
+}
+
+static inline u32
+gk20a_pllg_n_lo(struct gk20a_clk *clk, struct gk20a_pll *pll)
+{
+	return DIV_ROUND_UP(pll->m * clk->params->min_vco,
+			    clk->parent_rate / KHZ);
+}
+
+int gk20a_clk_ctor(struct nvkm_device *, int, const struct nvkm_clk_func *,
 		    const struct gk20a_clk_pllg_params *, struct gk20a_clk *);
 void gk20a_clk_fini(struct nvkm_clk *);
 int gk20a_clk_read(struct nvkm_clk *, enum nv_clk_src);
@@ -62,4 +154,6 @@ int gk20a_clk_calc(struct nvkm_clk *, struct nvkm_cstate *);
 int gk20a_clk_prog(struct nvkm_clk *);
 void gk20a_clk_tidy(struct nvkm_clk *);
 
+int gk20a_clk_setup_slide(struct gk20a_clk *);
+
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gm20b.c
index 71b2bbb61973..b284e949f732 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gm20b.c
@@ -21,20 +21,123 @@
  */
 
 #include <subdev/clk.h>
+#include <subdev/volt.h>
+#include <subdev/timer.h>
 #include <core/device.h>
+#include <core/tegra.h>
 
 #include "priv.h"
 #include "gk20a.h"
 
-#define KHZ (1000)
-#define MHZ (KHZ * 1000)
-
-#define MASK(w)	((1 << w) - 1)
+#define GPCPLL_CFG_SYNC_MODE	BIT(2)
 
 #define BYPASSCTRL_SYS	(SYS_GPCPLL_CFG_BASE + 0x340)
 #define BYPASSCTRL_SYS_GPCPLL_SHIFT	0
 #define BYPASSCTRL_SYS_GPCPLL_WIDTH	1
 
+#define GPCPLL_CFG2_SDM_DIN_SHIFT	0
+#define GPCPLL_CFG2_SDM_DIN_WIDTH	8
+#define GPCPLL_CFG2_SDM_DIN_MASK	\
+	(MASK(GPCPLL_CFG2_SDM_DIN_WIDTH) << GPCPLL_CFG2_SDM_DIN_SHIFT)
+#define GPCPLL_CFG2_SDM_DIN_NEW_SHIFT	8
+#define GPCPLL_CFG2_SDM_DIN_NEW_WIDTH	15
+#define GPCPLL_CFG2_SDM_DIN_NEW_MASK	\
+	(MASK(GPCPLL_CFG2_SDM_DIN_NEW_WIDTH) << GPCPLL_CFG2_SDM_DIN_NEW_SHIFT)
+#define GPCPLL_CFG2_SETUP2_SHIFT	16
+#define GPCPLL_CFG2_PLL_STEPA_SHIFT	24
+
+#define GPCPLL_DVFS0	(SYS_GPCPLL_CFG_BASE + 0x10)
+#define GPCPLL_DVFS0_DFS_COEFF_SHIFT	0
+#define GPCPLL_DVFS0_DFS_COEFF_WIDTH	7
+#define GPCPLL_DVFS0_DFS_COEFF_MASK	\
+	(MASK(GPCPLL_DVFS0_DFS_COEFF_WIDTH) << GPCPLL_DVFS0_DFS_COEFF_SHIFT)
+#define GPCPLL_DVFS0_DFS_DET_MAX_SHIFT	8
+#define GPCPLL_DVFS0_DFS_DET_MAX_WIDTH	7
+#define GPCPLL_DVFS0_DFS_DET_MAX_MASK	\
+	(MASK(GPCPLL_DVFS0_DFS_DET_MAX_WIDTH) << GPCPLL_DVFS0_DFS_DET_MAX_SHIFT)
+
+#define GPCPLL_DVFS1		(SYS_GPCPLL_CFG_BASE + 0x14)
+#define GPCPLL_DVFS1_DFS_EXT_DET_SHIFT		0
+#define GPCPLL_DVFS1_DFS_EXT_DET_WIDTH		7
+#define GPCPLL_DVFS1_DFS_EXT_STRB_SHIFT		7
+#define GPCPLL_DVFS1_DFS_EXT_STRB_WIDTH		1
+#define GPCPLL_DVFS1_DFS_EXT_CAL_SHIFT		8
+#define GPCPLL_DVFS1_DFS_EXT_CAL_WIDTH		7
+#define GPCPLL_DVFS1_DFS_EXT_SEL_SHIFT		15
+#define GPCPLL_DVFS1_DFS_EXT_SEL_WIDTH		1
+#define GPCPLL_DVFS1_DFS_CTRL_SHIFT		16
+#define GPCPLL_DVFS1_DFS_CTRL_WIDTH		12
+#define GPCPLL_DVFS1_EN_SDM_SHIFT		28
+#define GPCPLL_DVFS1_EN_SDM_WIDTH		1
+#define GPCPLL_DVFS1_EN_SDM_BIT			BIT(28)
+#define GPCPLL_DVFS1_EN_DFS_SHIFT		29
+#define GPCPLL_DVFS1_EN_DFS_WIDTH		1
+#define GPCPLL_DVFS1_EN_DFS_BIT			BIT(29)
+#define GPCPLL_DVFS1_EN_DFS_CAL_SHIFT		30
+#define GPCPLL_DVFS1_EN_DFS_CAL_WIDTH		1
+#define GPCPLL_DVFS1_EN_DFS_CAL_BIT		BIT(30)
+#define GPCPLL_DVFS1_DFS_CAL_DONE_SHIFT		31
+#define GPCPLL_DVFS1_DFS_CAL_DONE_WIDTH		1
+#define GPCPLL_DVFS1_DFS_CAL_DONE_BIT		BIT(31)
+
+#define GPC_BCAST_GPCPLL_DVFS2	(GPC_BCAST_GPCPLL_CFG_BASE + 0x20)
+#define GPC_BCAST_GPCPLL_DVFS2_DFS_EXT_STROBE_BIT	BIT(16)
+
+#define GPCPLL_CFG3_PLL_DFS_TESTOUT_SHIFT	24
+#define GPCPLL_CFG3_PLL_DFS_TESTOUT_WIDTH	7
+
+#define DFS_DET_RANGE	6	/* -2^6 ... 2^6-1 */
+#define SDM_DIN_RANGE	12	/* -2^12 ... 2^12-1 */
+
+struct gm20b_clk_dvfs_params {
+	s32 coeff_slope;
+	s32 coeff_offs;
+	u32 vco_ctrl;
+};
+
+static const struct gm20b_clk_dvfs_params gm20b_dvfs_params = {
+	.coeff_slope = -165230,
+	.coeff_offs = 214007,
+	.vco_ctrl = 0x7 << 3,
+};
+
+/*
+ * base.n is now the *integer* part of the N factor.
+ * sdm_din contains n's decimal part.
+ */
+struct gm20b_pll {
+	struct gk20a_pll base;
+	u32 sdm_din;
+};
+
+struct gm20b_clk_dvfs {
+	u32 dfs_coeff;
+	s32 dfs_det_max;
+	s32 dfs_ext_cal;
+};
+
+struct gm20b_clk {
+	/* currently applied parameters */
+	struct gk20a_clk base;
+	struct gm20b_clk_dvfs dvfs;
+	u32 uv;
+
+	/* new parameters to apply */
+	struct gk20a_pll new_pll;
+	struct gm20b_clk_dvfs new_dvfs;
+	u32 new_uv;
+
+	const struct gm20b_clk_dvfs_params *dvfs_params;
+
+	/* fused parameters */
+	s32 uvdet_slope;
+	s32 uvdet_offs;
+
+	/* safe frequency we can use at minimum voltage */
+	u32 safe_fmax_vmin;
+};
+#define gm20b_clk(p) container_of((gk20a_clk(p)), struct gm20b_clk, base)
+
 static u32 pl_to_div(u32 pl)
 {
 	return pl;
@@ -53,6 +156,484 @@ static const struct gk20a_clk_pllg_params gm20b_pllg_params = {
 	.min_pl = 1, .max_pl = 31,
 };
 
+static void
+gm20b_pllg_read_mnp(struct gm20b_clk *clk, struct gm20b_pll *pll)
+{
+	struct nvkm_subdev *subdev = &clk->base.base.subdev;
+	struct nvkm_device *device = subdev->device;
+	u32 val;
+
+	gk20a_pllg_read_mnp(&clk->base, &pll->base);
+	val = nvkm_rd32(device, GPCPLL_CFG2);
+	pll->sdm_din = (val >> GPCPLL_CFG2_SDM_DIN_SHIFT) &
+		       MASK(GPCPLL_CFG2_SDM_DIN_WIDTH);
+}
+
+static void
+gm20b_pllg_write_mnp(struct gm20b_clk *clk, const struct gm20b_pll *pll)
+{
+	struct nvkm_device *device = clk->base.base.subdev.device;
+
+	nvkm_mask(device, GPCPLL_CFG2, GPCPLL_CFG2_SDM_DIN_MASK,
+		  pll->sdm_din << GPCPLL_CFG2_SDM_DIN_SHIFT);
+	gk20a_pllg_write_mnp(&clk->base, &pll->base);
+}
+
+/*
+ * Determine DFS_COEFF for the requested voltage. Always select external
+ * calibration override equal to the voltage, and set maximum detection
+ * limit "0" (to make sure that PLL output remains under F/V curve when
+ * voltage increases).
+ */
+static void
+gm20b_dvfs_calc_det_coeff(struct gm20b_clk *clk, s32 uv,
+			  struct gm20b_clk_dvfs *dvfs)
+{
+	struct nvkm_subdev *subdev = &clk->base.base.subdev;
+	const struct gm20b_clk_dvfs_params *p = clk->dvfs_params;
+	u32 coeff;
+	/* Work with mv as uv would likely trigger an overflow */
+	s32 mv = DIV_ROUND_CLOSEST(uv, 1000);
+
+	/* coeff = slope * voltage + offset */
+	coeff = DIV_ROUND_CLOSEST(mv * p->coeff_slope, 1000) + p->coeff_offs;
+	coeff = DIV_ROUND_CLOSEST(coeff, 1000);
+	dvfs->dfs_coeff = min_t(u32, coeff, MASK(GPCPLL_DVFS0_DFS_COEFF_WIDTH));
+
+	dvfs->dfs_ext_cal = DIV_ROUND_CLOSEST(uv - clk->uvdet_offs,
+					     clk->uvdet_slope);
+	/* should never happen */
+	if (abs(dvfs->dfs_ext_cal) >= BIT(DFS_DET_RANGE))
+		nvkm_error(subdev, "dfs_ext_cal overflow!\n");
+
+	dvfs->dfs_det_max = 0;
+
+	nvkm_debug(subdev, "%s uv: %d coeff: %x, ext_cal: %d, det_max: %d\n",
+		   __func__, uv, dvfs->dfs_coeff, dvfs->dfs_ext_cal,
+		   dvfs->dfs_det_max);
+}
+
+/*
+ * Solve equation for integer and fractional part of the effective NDIV:
+ *
+ * n_eff = n_int + 1/2 + (SDM_DIN / 2^(SDM_DIN_RANGE + 1)) +
+ *         (DVFS_COEFF * DVFS_DET_DELTA) / 2^DFS_DET_RANGE
+ *
+ * The SDM_DIN LSB is finally shifted out, since it is not accessible by sw.
+ */
+static void
+gm20b_dvfs_calc_ndiv(struct gm20b_clk *clk, u32 n_eff, u32 *n_int, u32 *sdm_din)
+{
+	struct nvkm_subdev *subdev = &clk->base.base.subdev;
+	const struct gk20a_clk_pllg_params *p = clk->base.params;
+	u32 n;
+	s32 det_delta;
+	u32 rem, rem_range;
+
+	/* calculate current ext_cal and subtract previous one */
+	det_delta = DIV_ROUND_CLOSEST(((s32)clk->uv) - clk->uvdet_offs,
+				      clk->uvdet_slope);
+	det_delta -= clk->dvfs.dfs_ext_cal;
+	det_delta = min(det_delta, clk->dvfs.dfs_det_max);
+	det_delta *= clk->dvfs.dfs_coeff;
+
+	/* integer part of n */
+	n = (n_eff << DFS_DET_RANGE) - det_delta;
+	/* should never happen! */
+	if (n <= 0) {
+		nvkm_error(subdev, "ndiv <= 0 - setting to 1...\n");
+		n = 1 << DFS_DET_RANGE;
+	}
+	if (n >> DFS_DET_RANGE > p->max_n) {
+		nvkm_error(subdev, "ndiv > max_n - setting to max_n...\n");
+		n = p->max_n << DFS_DET_RANGE;
+	}
+	*n_int = n >> DFS_DET_RANGE;
+
+	/* fractional part of n */
+	rem = ((u32)n) & MASK(DFS_DET_RANGE);
+	rem_range = SDM_DIN_RANGE + 1 - DFS_DET_RANGE;
+	/* subtract 2^SDM_DIN_RANGE to account for the 1/2 of the equation */
+	rem = (rem << rem_range) - BIT(SDM_DIN_RANGE);
+	/* lose 8 LSB and clip - sdm_din only keeps the most significant byte */
+	*sdm_din = (rem >> BITS_PER_BYTE) & MASK(GPCPLL_CFG2_SDM_DIN_WIDTH);
+
+	nvkm_debug(subdev, "%s n_eff: %d, n_int: %d, sdm_din: %d\n", __func__,
+		   n_eff, *n_int, *sdm_din);
+}
+
+static int
+gm20b_pllg_slide(struct gm20b_clk *clk, u32 n)
+{
+	struct nvkm_subdev *subdev = &clk->base.base.subdev;
+	struct nvkm_device *device = subdev->device;
+	struct gm20b_pll pll;
+	u32 n_int, sdm_din;
+	int ret = 0;
+
+	/* calculate the new n_int/sdm_din for this n/uv */
+	gm20b_dvfs_calc_ndiv(clk, n, &n_int, &sdm_din);
+
+	/* get old coefficients */
+	gm20b_pllg_read_mnp(clk, &pll);
+	/* do nothing if NDIV is the same */
+	if (n_int == pll.base.n && sdm_din == pll.sdm_din)
+		return 0;
+
+	/* pll slowdown mode */
+	nvkm_mask(device, GPCPLL_NDIV_SLOWDOWN,
+		BIT(GPCPLL_NDIV_SLOWDOWN_SLOWDOWN_USING_PLL_SHIFT),
+		BIT(GPCPLL_NDIV_SLOWDOWN_SLOWDOWN_USING_PLL_SHIFT));
+
+	/* new ndiv ready for ramp */
+	/* in DVFS mode SDM is updated via "new" field */
+	nvkm_mask(device, GPCPLL_CFG2, GPCPLL_CFG2_SDM_DIN_NEW_MASK,
+		  sdm_din << GPCPLL_CFG2_SDM_DIN_NEW_SHIFT);
+	pll.base.n = n_int;
+	udelay(1);
+	gk20a_pllg_write_mnp(&clk->base, &pll.base);
+
+	/* dynamic ramp to new ndiv */
+	udelay(1);
+	nvkm_mask(device, GPCPLL_NDIV_SLOWDOWN,
+		  BIT(GPCPLL_NDIV_SLOWDOWN_EN_DYNRAMP_SHIFT),
+		  BIT(GPCPLL_NDIV_SLOWDOWN_EN_DYNRAMP_SHIFT));
+
+	/* wait for ramping to complete */
+	if (nvkm_wait_usec(device, 500, GPC_BCAST_NDIV_SLOWDOWN_DEBUG,
+		GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_MASK,
+		GPC_BCAST_NDIV_SLOWDOWN_DEBUG_PLL_DYNRAMP_DONE_SYNCED_MASK) < 0)
+		ret = -ETIMEDOUT;
+
+	/* in DVFS mode complete SDM update */
+	nvkm_mask(device, GPCPLL_CFG2, GPCPLL_CFG2_SDM_DIN_MASK,
+		  sdm_din << GPCPLL_CFG2_SDM_DIN_SHIFT);
+
+	/* exit slowdown mode */
+	nvkm_mask(device, GPCPLL_NDIV_SLOWDOWN,
+		BIT(GPCPLL_NDIV_SLOWDOWN_SLOWDOWN_USING_PLL_SHIFT) |
+		BIT(GPCPLL_NDIV_SLOWDOWN_EN_DYNRAMP_SHIFT), 0);
+	nvkm_rd32(device, GPCPLL_NDIV_SLOWDOWN);
+
+	return ret;
+}
+
+static int
+gm20b_pllg_enable(struct gm20b_clk *clk)
+{
+	struct nvkm_device *device = clk->base.base.subdev.device;
+
+	nvkm_mask(device, GPCPLL_CFG, GPCPLL_CFG_ENABLE, GPCPLL_CFG_ENABLE);
+	nvkm_rd32(device, GPCPLL_CFG);
+
+	/* In DVFS mode lock cannot be used - so just delay */
+	udelay(40);
+
+	/* set SYNC_MODE for glitchless switch out of bypass */
+	nvkm_mask(device, GPCPLL_CFG, GPCPLL_CFG_SYNC_MODE,
+		       GPCPLL_CFG_SYNC_MODE);
+	nvkm_rd32(device, GPCPLL_CFG);
+
+	/* switch to VCO mode */
+	nvkm_mask(device, SEL_VCO, BIT(SEL_VCO_GPC2CLK_OUT_SHIFT),
+		  BIT(SEL_VCO_GPC2CLK_OUT_SHIFT));
+
+	return 0;
+}
+
+static void
+gm20b_pllg_disable(struct gm20b_clk *clk)
+{
+	struct nvkm_device *device = clk->base.base.subdev.device;
+
+	/* put PLL in bypass before disabling it */
+	nvkm_mask(device, SEL_VCO, BIT(SEL_VCO_GPC2CLK_OUT_SHIFT), 0);
+
+	/* clear SYNC_MODE before disabling PLL */
+	nvkm_mask(device, GPCPLL_CFG, GPCPLL_CFG_SYNC_MODE, 0);
+
+	nvkm_mask(device, GPCPLL_CFG, GPCPLL_CFG_ENABLE, 0);
+	nvkm_rd32(device, GPCPLL_CFG);
+}
+
+static int
+gm20b_pllg_program_mnp(struct gm20b_clk *clk, const struct gk20a_pll *pll)
+{
+	struct nvkm_subdev *subdev = &clk->base.base.subdev;
+	struct nvkm_device *device = subdev->device;
+	struct gm20b_pll cur_pll;
+	u32 n_int, sdm_din;
+	/* if we only change pdiv, we can do a glitchless transition */
+	bool pdiv_only;
+	int ret;
+
+	gm20b_dvfs_calc_ndiv(clk, pll->n, &n_int, &sdm_din);
+	gm20b_pllg_read_mnp(clk, &cur_pll);
+	pdiv_only = cur_pll.base.n == n_int && cur_pll.sdm_din == sdm_din &&
+		    cur_pll.base.m == pll->m;
+
+	/* need full sequence if clock not enabled yet */
+	if (!gk20a_pllg_is_enabled(&clk->base))
+		pdiv_only = false;
+
+	/* split VCO-to-bypass jump in half by setting out divider 1:2 */
+	nvkm_mask(device, GPC2CLK_OUT, GPC2CLK_OUT_VCODIV_MASK,
+		  GPC2CLK_OUT_VCODIV2 << GPC2CLK_OUT_VCODIV_SHIFT);
+	/* Intentional 2nd write to assure linear divider operation */
+	nvkm_mask(device, GPC2CLK_OUT, GPC2CLK_OUT_VCODIV_MASK,
+		  GPC2CLK_OUT_VCODIV2 << GPC2CLK_OUT_VCODIV_SHIFT);
+	nvkm_rd32(device, GPC2CLK_OUT);
+	udelay(2);
+
+	if (pdiv_only) {
+		u32 old = cur_pll.base.pl;
+		u32 new = pll->pl;
+
+		/*
+		 * we can do a glitchless transition only if the old and new PL
+		 * parameters share at least one bit set to 1. If this is not
+		 * the case, calculate and program an interim PL that will allow
+		 * us to respect that rule.
+		 */
+		if ((old & new) == 0) {
+			cur_pll.base.pl = min(old | BIT(ffs(new) - 1),
+					      new | BIT(ffs(old) - 1));
+			gk20a_pllg_write_mnp(&clk->base, &cur_pll.base);
+		}
+
+		cur_pll.base.pl = new;
+		gk20a_pllg_write_mnp(&clk->base, &cur_pll.base);
+	} else {
+		/* disable before programming if more than pdiv changes */
+		gm20b_pllg_disable(clk);
+
+		cur_pll.base = *pll;
+		cur_pll.base.n = n_int;
+		cur_pll.sdm_din = sdm_din;
+		gm20b_pllg_write_mnp(clk, &cur_pll);
+
+		ret = gm20b_pllg_enable(clk);
+		if (ret)
+			return ret;
+	}
+
+	/* restore out divider 1:1 */
+	udelay(2);
+	nvkm_mask(device, GPC2CLK_OUT, GPC2CLK_OUT_VCODIV_MASK,
+		  GPC2CLK_OUT_VCODIV1 << GPC2CLK_OUT_VCODIV_SHIFT);
+	/* Intentional 2nd write to assure linear divider operation */
+	nvkm_mask(device, GPC2CLK_OUT, GPC2CLK_OUT_VCODIV_MASK,
+		  GPC2CLK_OUT_VCODIV1 << GPC2CLK_OUT_VCODIV_SHIFT);
+	nvkm_rd32(device, GPC2CLK_OUT);
+
+	return 0;
+}
+
+static int
+gm20b_pllg_program_mnp_slide(struct gm20b_clk *clk, const struct gk20a_pll *pll)
+{
+	struct gk20a_pll cur_pll;
+	int ret;
+
+	if (gk20a_pllg_is_enabled(&clk->base)) {
+		gk20a_pllg_read_mnp(&clk->base, &cur_pll);
+
+		/* just do NDIV slide if there is no change to M and PL */
+		if (pll->m == cur_pll.m && pll->pl == cur_pll.pl)
+			return gm20b_pllg_slide(clk, pll->n);
+
+		/* slide down to current NDIV_LO */
+		cur_pll.n = gk20a_pllg_n_lo(&clk->base, &cur_pll);
+		ret = gm20b_pllg_slide(clk, cur_pll.n);
+		if (ret)
+			return ret;
+	}
+
+	/* program MNP with the new clock parameters and new NDIV_LO */
+	cur_pll = *pll;
+	cur_pll.n = gk20a_pllg_n_lo(&clk->base, &cur_pll);
+	ret = gm20b_pllg_program_mnp(clk, &cur_pll);
+	if (ret)
+		return ret;
+
+	/* slide up to new NDIV */
+	return gm20b_pllg_slide(clk, pll->n);
+}
+
+static int
+gm20b_clk_calc(struct nvkm_clk *base, struct nvkm_cstate *cstate)
+{
+	struct gm20b_clk *clk = gm20b_clk(base);
+	struct nvkm_subdev *subdev = &base->subdev;
+	struct nvkm_volt *volt = base->subdev.device->volt;
+	int ret;
+
+	ret = gk20a_pllg_calc_mnp(&clk->base, cstate->domain[nv_clk_src_gpc] *
+					     GK20A_CLK_GPC_MDIV, &clk->new_pll);
+	if (ret)
+		return ret;
+
+	clk->new_uv = volt->vid[cstate->voltage].uv;
+	gm20b_dvfs_calc_det_coeff(clk, clk->new_uv, &clk->new_dvfs);
+
+	nvkm_debug(subdev, "%s uv: %d uv\n", __func__, clk->new_uv);
+
+	return 0;
+}
+
+/*
+ * Compute PLL parameters that are always safe for the current voltage
+ */
+static void
+gm20b_dvfs_calc_safe_pll(struct gm20b_clk *clk, struct gk20a_pll *pll)
+{
+	u32 rate = gk20a_pllg_calc_rate(&clk->base, pll) / KHZ;
+	u32 parent_rate = clk->base.parent_rate / KHZ;
+	u32 nmin, nsafe;
+
+	/* remove a safe margin of 10% */
+	if (rate > clk->safe_fmax_vmin)
+		rate = rate * (100 - 10) / 100;
+
+	/* gpc2clk */
+	rate *= 2;
+
+	nmin = DIV_ROUND_UP(pll->m * clk->base.params->min_vco, parent_rate);
+	nsafe = pll->m * rate / (clk->base.parent_rate);
+
+	if (nsafe < nmin) {
+		pll->pl = DIV_ROUND_UP(nmin * parent_rate, pll->m * rate);
+		nsafe = nmin;
+	}
+
+	pll->n = nsafe;
+}
+
+static void
+gm20b_dvfs_program_coeff(struct gm20b_clk *clk, u32 coeff)
+{
+	struct nvkm_device *device = clk->base.base.subdev.device;
+
+	/* strobe to read external DFS coefficient */
+	nvkm_mask(device, GPC_BCAST_GPCPLL_DVFS2,
+		  GPC_BCAST_GPCPLL_DVFS2_DFS_EXT_STROBE_BIT,
+		  GPC_BCAST_GPCPLL_DVFS2_DFS_EXT_STROBE_BIT);
+
+	nvkm_mask(device, GPCPLL_DVFS0, GPCPLL_DVFS0_DFS_COEFF_MASK,
+		  coeff << GPCPLL_DVFS0_DFS_COEFF_SHIFT);
+
+	udelay(1);
+	nvkm_mask(device, GPC_BCAST_GPCPLL_DVFS2,
+		  GPC_BCAST_GPCPLL_DVFS2_DFS_EXT_STROBE_BIT, 0);
+}
+
+static void
+gm20b_dvfs_program_ext_cal(struct gm20b_clk *clk, u32 dfs_det_cal)
+{
+	struct nvkm_device *device = clk->base.base.subdev.device;
+	u32 val;
+
+	nvkm_mask(device, GPC_BCAST_GPCPLL_DVFS2, MASK(DFS_DET_RANGE + 1),
+		  dfs_det_cal);
+	udelay(1);
+
+	val = nvkm_rd32(device, GPCPLL_DVFS1);
+	if (!(val & BIT(25))) {
+		/* Use external value to overwrite calibration value */
+		val |= BIT(25) | BIT(16);
+		nvkm_wr32(device, GPCPLL_DVFS1, val);
+	}
+}
+
+static void
+gm20b_dvfs_program_dfs_detection(struct gm20b_clk *clk,
+				 struct gm20b_clk_dvfs *dvfs)
+{
+	struct nvkm_device *device = clk->base.base.subdev.device;
+
+	/* strobe to read external DFS coefficient */
+	nvkm_mask(device, GPC_BCAST_GPCPLL_DVFS2,
+		  GPC_BCAST_GPCPLL_DVFS2_DFS_EXT_STROBE_BIT,
+		  GPC_BCAST_GPCPLL_DVFS2_DFS_EXT_STROBE_BIT);
+
+	nvkm_mask(device, GPCPLL_DVFS0,
+		  GPCPLL_DVFS0_DFS_COEFF_MASK | GPCPLL_DVFS0_DFS_DET_MAX_MASK,
+		  dvfs->dfs_coeff << GPCPLL_DVFS0_DFS_COEFF_SHIFT |
+		  dvfs->dfs_det_max << GPCPLL_DVFS0_DFS_DET_MAX_SHIFT);
+
+	udelay(1);
+	nvkm_mask(device, GPC_BCAST_GPCPLL_DVFS2,
+		  GPC_BCAST_GPCPLL_DVFS2_DFS_EXT_STROBE_BIT, 0);
+
+	gm20b_dvfs_program_ext_cal(clk, dvfs->dfs_ext_cal);
+}
+
+static int
+gm20b_clk_prog(struct nvkm_clk *base)
+{
+	struct gm20b_clk *clk = gm20b_clk(base);
+	u32 cur_freq;
+	int ret;
+
+	/* No change in DVFS settings? */
+	if (clk->uv == clk->new_uv)
+		goto prog;
+
+	/*
+	 * Interim step for changing DVFS detection settings: low enough
+	 * frequency to be safe at at DVFS coeff = 0.
+	 *
+	 * 1. If voltage is increasing:
+	 * - safe frequency target matches the lowest - old - frequency
+	 * - DVFS settings are still old
+	 * - Voltage already increased to new level by volt, but maximum
+	 *   detection limit assures PLL output remains under F/V curve
+	 *
+	 * 2. If voltage is decreasing:
+	 * - safe frequency target matches the lowest - new - frequency
+	 * - DVFS settings are still old
+	 * - Voltage is also old, it will be lowered by volt afterwards
+	 *
+	 * Interim step can be skipped if old frequency is below safe minimum,
+	 * i.e., it is low enough to be safe at any voltage in operating range
+	 * with zero DVFS coefficient.
+	 */
+	cur_freq = nvkm_clk_read(&clk->base.base, nv_clk_src_gpc);
+	if (cur_freq > clk->safe_fmax_vmin) {
+		struct gk20a_pll pll_safe;
+
+		if (clk->uv < clk->new_uv)
+			/* voltage will raise: safe frequency is current one */
+			pll_safe = clk->base.pll;
+		else
+			/* voltage will drop: safe frequency is new one */
+			pll_safe = clk->new_pll;
+
+		gm20b_dvfs_calc_safe_pll(clk, &pll_safe);
+		ret = gm20b_pllg_program_mnp_slide(clk, &pll_safe);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * DVFS detection settings transition:
+	 * - Set DVFS coefficient zero
+	 * - Set calibration level to new voltage
+	 * - Set DVFS coefficient to match new voltage
+	 */
+	gm20b_dvfs_program_coeff(clk, 0);
+	gm20b_dvfs_program_ext_cal(clk, clk->new_dvfs.dfs_ext_cal);
+	gm20b_dvfs_program_coeff(clk, clk->new_dvfs.dfs_coeff);
+	gm20b_dvfs_program_dfs_detection(clk, &clk->new_dvfs);
+
+prog:
+	clk->uv = clk->new_uv;
+	clk->dvfs = clk->new_dvfs;
+	clk->base.pll = clk->new_pll;
+
+	return gm20b_pllg_program_mnp_slide(clk, &clk->base.pll);
+}
+
 static struct nvkm_pstate
 gm20b_pstates[] = {
 	{
@@ -133,9 +714,99 @@ gm20b_pstates[] = {
 			.voltage = 12,
 		},
 	},
-
 };
 
+static void
+gm20b_clk_fini(struct nvkm_clk *base)
+{
+	struct nvkm_device *device = base->subdev.device;
+	struct gm20b_clk *clk = gm20b_clk(base);
+
+	/* slide to VCO min */
+	if (gk20a_pllg_is_enabled(&clk->base)) {
+		struct gk20a_pll pll;
+		u32 n_lo;
+
+		gk20a_pllg_read_mnp(&clk->base, &pll);
+		n_lo = gk20a_pllg_n_lo(&clk->base, &pll);
+		gm20b_pllg_slide(clk, n_lo);
+	}
+
+	gm20b_pllg_disable(clk);
+
+	/* set IDDQ */
+	nvkm_mask(device, GPCPLL_CFG, GPCPLL_CFG_IDDQ, 1);
+}
+
+static int
+gm20b_clk_init_dvfs(struct gm20b_clk *clk)
+{
+	struct nvkm_subdev *subdev = &clk->base.base.subdev;
+	struct nvkm_device *device = subdev->device;
+	bool fused = clk->uvdet_offs && clk->uvdet_slope;
+	static const s32 ADC_SLOPE_UV = 10000; /* default ADC detection slope */
+	u32 data;
+	int ret;
+
+	/* Enable NA DVFS */
+	nvkm_mask(device, GPCPLL_DVFS1, GPCPLL_DVFS1_EN_DFS_BIT,
+		  GPCPLL_DVFS1_EN_DFS_BIT);
+
+	/* Set VCO_CTRL */
+	if (clk->dvfs_params->vco_ctrl)
+		nvkm_mask(device, GPCPLL_CFG3, GPCPLL_CFG3_VCO_CTRL_MASK,
+		      clk->dvfs_params->vco_ctrl << GPCPLL_CFG3_VCO_CTRL_SHIFT);
+
+	if (fused) {
+		/* Start internal calibration, but ignore results */
+		nvkm_mask(device, GPCPLL_DVFS1, GPCPLL_DVFS1_EN_DFS_CAL_BIT,
+			  GPCPLL_DVFS1_EN_DFS_CAL_BIT);
+
+		/* got uvdev parameters from fuse, skip calibration */
+		goto calibrated;
+	}
+
+	/*
+	 * If calibration parameters are not fused, start internal calibration,
+	 * wait for completion, and use results along with default slope to
+	 * calculate ADC offset during boot.
+	 */
+	nvkm_mask(device, GPCPLL_DVFS1, GPCPLL_DVFS1_EN_DFS_CAL_BIT,
+			  GPCPLL_DVFS1_EN_DFS_CAL_BIT);
+
+	/* Wait for internal calibration done (spec < 2us). */
+	ret = nvkm_wait_usec(device, 10, GPCPLL_DVFS1,
+			     GPCPLL_DVFS1_DFS_CAL_DONE_BIT,
+			     GPCPLL_DVFS1_DFS_CAL_DONE_BIT);
+	if (ret < 0) {
+		nvkm_error(subdev, "GPCPLL calibration timeout\n");
+		return -ETIMEDOUT;
+	}
+
+	data = nvkm_rd32(device, GPCPLL_CFG3) >>
+			 GPCPLL_CFG3_PLL_DFS_TESTOUT_SHIFT;
+	data &= MASK(GPCPLL_CFG3_PLL_DFS_TESTOUT_WIDTH);
+
+	clk->uvdet_slope = ADC_SLOPE_UV;
+	clk->uvdet_offs = ((s32)clk->uv) - data * ADC_SLOPE_UV;
+
+	nvkm_debug(subdev, "calibrated DVFS parameters: offs %d, slope %d\n",
+		   clk->uvdet_offs, clk->uvdet_slope);
+
+calibrated:
+	/* Compute and apply initial DVFS parameters */
+	gm20b_dvfs_calc_det_coeff(clk, clk->uv, &clk->dvfs);
+	gm20b_dvfs_program_coeff(clk, 0);
+	gm20b_dvfs_program_ext_cal(clk, clk->dvfs.dfs_ext_cal);
+	gm20b_dvfs_program_coeff(clk, clk->dvfs.dfs_coeff);
+	gm20b_dvfs_program_dfs_detection(clk, &clk->new_dvfs);
+
+	return 0;
+}
+
+/* Forward declaration to detect speedo >=1 in gm20b_clk_init() */
+static const struct nvkm_clk_func gm20b_clk;
+
 static int
 gm20b_clk_init(struct nvkm_clk *base)
 {
@@ -143,15 +814,56 @@ gm20b_clk_init(struct nvkm_clk *base)
 	struct nvkm_subdev *subdev = &clk->base.subdev;
 	struct nvkm_device *device = subdev->device;
 	int ret;
+	u32 data;
+
+	/* get out from IDDQ */
+	nvkm_mask(device, GPCPLL_CFG, GPCPLL_CFG_IDDQ, 0);
+	nvkm_rd32(device, GPCPLL_CFG);
+	udelay(5);
+
+	nvkm_mask(device, GPC2CLK_OUT, GPC2CLK_OUT_INIT_MASK,
+		  GPC2CLK_OUT_INIT_VAL);
 
 	/* Set the global bypass control to VCO */
 	nvkm_mask(device, BYPASSCTRL_SYS,
 	       MASK(BYPASSCTRL_SYS_GPCPLL_WIDTH) << BYPASSCTRL_SYS_GPCPLL_SHIFT,
 	       0);
 
+	ret = gk20a_clk_setup_slide(clk);
+	if (ret)
+		return ret;
+
+	/* If not fused, set RAM SVOP PDP data 0x2, and enable fuse override */
+	data = nvkm_rd32(device, 0x021944);
+	if (!(data & 0x3)) {
+		data |= 0x2;
+		nvkm_wr32(device, 0x021944, data);
+
+		data = nvkm_rd32(device, 0x021948);
+		data |=  0x1;
+		nvkm_wr32(device, 0x021948, data);
+	}
+
+	/* Disable idle slow down  */
+	nvkm_mask(device, 0x20160, 0x003f0000, 0x0);
+
+	/* speedo >= 1? */
+	if (clk->base.func == &gm20b_clk) {
+		struct gm20b_clk *_clk = gm20b_clk(base);
+		struct nvkm_volt *volt = device->volt;
+
+		/* Get current voltage */
+		_clk->uv = nvkm_volt_get(volt);
+
+		/* Initialize DVFS */
+		ret = gm20b_clk_init_dvfs(_clk);
+		if (ret)
+			return ret;
+	}
+
 	/* Start with lowest frequency */
 	base->func->calc(base, &base->func->pstates[0].base);
-	ret = base->func->prog(&clk->base);
+	ret = base->func->prog(base);
 	if (ret) {
 		nvkm_error(subdev, "cannot initialize clock\n");
 		return ret;
@@ -169,6 +881,7 @@ gm20b_clk_speedo0 = {
 	.prog = gk20a_clk_prog,
 	.tidy = gk20a_clk_tidy,
 	.pstates = gm20b_pstates,
+	/* Speedo 0 only supports 12 voltages */
 	.nr_pstates = ARRAY_SIZE(gm20b_pstates) - 1,
 	.domains = {
 		{ nv_clk_src_crystal, 0xff },
@@ -177,8 +890,26 @@ gm20b_clk_speedo0 = {
 	},
 };
 
-int
-gm20b_clk_new(struct nvkm_device *device, int index, struct nvkm_clk **pclk)
+static const struct nvkm_clk_func
+gm20b_clk = {
+	.init = gm20b_clk_init,
+	.fini = gm20b_clk_fini,
+	.read = gk20a_clk_read,
+	.calc = gm20b_clk_calc,
+	.prog = gm20b_clk_prog,
+	.tidy = gk20a_clk_tidy,
+	.pstates = gm20b_pstates,
+	.nr_pstates = ARRAY_SIZE(gm20b_pstates),
+	.domains = {
+		{ nv_clk_src_crystal, 0xff },
+		{ nv_clk_src_gpc, 0xff, 0, "core", GK20A_CLK_GPC_MDIV },
+		{ nv_clk_src_max },
+	},
+};
+
+static int
+gm20b_clk_new_speedo0(struct nvkm_device *device, int index,
+		      struct nvkm_clk **pclk)
 {
 	struct gk20a_clk *clk;
 	int ret;
@@ -188,11 +919,156 @@ gm20b_clk_new(struct nvkm_device *device, int index, struct nvkm_clk **pclk)
 		return -ENOMEM;
 	*pclk = &clk->base;
 
-	ret = _gk20a_clk_ctor(device, index, &gm20b_clk_speedo0,
-			      &gm20b_pllg_params, clk);
+	ret = gk20a_clk_ctor(device, index, &gm20b_clk_speedo0,
+			     &gm20b_pllg_params, clk);
 
 	clk->pl_to_div = pl_to_div;
 	clk->div_to_pl = div_to_pl;
 
 	return ret;
 }
+
+/* FUSE register */
+#define FUSE_RESERVED_CALIB0	0x204
+#define FUSE_RESERVED_CALIB0_INTERCEPT_FRAC_SHIFT	0
+#define FUSE_RESERVED_CALIB0_INTERCEPT_FRAC_WIDTH	4
+#define FUSE_RESERVED_CALIB0_INTERCEPT_INT_SHIFT	4
+#define FUSE_RESERVED_CALIB0_INTERCEPT_INT_WIDTH	10
+#define FUSE_RESERVED_CALIB0_SLOPE_FRAC_SHIFT		14
+#define FUSE_RESERVED_CALIB0_SLOPE_FRAC_WIDTH		10
+#define FUSE_RESERVED_CALIB0_SLOPE_INT_SHIFT		24
+#define FUSE_RESERVED_CALIB0_SLOPE_INT_WIDTH		6
+#define FUSE_RESERVED_CALIB0_FUSE_REV_SHIFT		30
+#define FUSE_RESERVED_CALIB0_FUSE_REV_WIDTH		2
+
+static int
+gm20b_clk_init_fused_params(struct gm20b_clk *clk)
+{
+	struct nvkm_subdev *subdev = &clk->base.base.subdev;
+	u32 val = 0;
+	u32 rev = 0;
+
+#if IS_ENABLED(CONFIG_ARCH_TEGRA)
+	tegra_fuse_readl(FUSE_RESERVED_CALIB0, &val);
+	rev = (val >> FUSE_RESERVED_CALIB0_FUSE_REV_SHIFT) &
+	      MASK(FUSE_RESERVED_CALIB0_FUSE_REV_WIDTH);
+#endif
+
+	/* No fused parameters, we will calibrate later */
+	if (rev == 0)
+		return -EINVAL;
+
+	/* Integer part in mV + fractional part in uV */
+	clk->uvdet_slope = ((val >> FUSE_RESERVED_CALIB0_SLOPE_INT_SHIFT) &
+			MASK(FUSE_RESERVED_CALIB0_SLOPE_INT_WIDTH)) * 1000 +
+			((val >> FUSE_RESERVED_CALIB0_SLOPE_FRAC_SHIFT) &
+			MASK(FUSE_RESERVED_CALIB0_SLOPE_FRAC_WIDTH));
+
+	/* Integer part in mV + fractional part in 100uV */
+	clk->uvdet_offs = ((val >> FUSE_RESERVED_CALIB0_INTERCEPT_INT_SHIFT) &
+			MASK(FUSE_RESERVED_CALIB0_INTERCEPT_INT_WIDTH)) * 1000 +
+			((val >> FUSE_RESERVED_CALIB0_INTERCEPT_FRAC_SHIFT) &
+			 MASK(FUSE_RESERVED_CALIB0_INTERCEPT_FRAC_WIDTH)) * 100;
+
+	nvkm_debug(subdev, "fused calibration data: slope %d, offs %d\n",
+		   clk->uvdet_slope, clk->uvdet_offs);
+	return 0;
+}
+
+static int
+gm20b_clk_init_safe_fmax(struct gm20b_clk *clk)
+{
+	struct nvkm_subdev *subdev = &clk->base.base.subdev;
+	struct nvkm_volt *volt = subdev->device->volt;
+	struct nvkm_pstate *pstates = clk->base.base.func->pstates;
+	int nr_pstates = clk->base.base.func->nr_pstates;
+	int vmin, id = 0;
+	u32 fmax = 0;
+	int i;
+
+	/* find lowest voltage we can use */
+	vmin = volt->vid[0].uv;
+	for (i = 1; i < volt->vid_nr; i++) {
+		if (volt->vid[i].uv <= vmin) {
+			vmin = volt->vid[i].uv;
+			id = volt->vid[i].vid;
+		}
+	}
+
+	/* find max frequency at this voltage */
+	for (i = 0; i < nr_pstates; i++)
+		if (pstates[i].base.voltage == id)
+			fmax = max(fmax,
+				   pstates[i].base.domain[nv_clk_src_gpc]);
+
+	if (!fmax) {
+		nvkm_error(subdev, "failed to evaluate safe fmax\n");
+		return -EINVAL;
+	}
+
+	/* we are safe at 90% of the max frequency */
+	clk->safe_fmax_vmin = fmax * (100 - 10) / 100;
+	nvkm_debug(subdev, "safe fmax @ vmin = %u Khz\n", clk->safe_fmax_vmin);
+
+	return 0;
+}
+
+int
+gm20b_clk_new(struct nvkm_device *device, int index, struct nvkm_clk **pclk)
+{
+	struct nvkm_device_tegra *tdev = device->func->tegra(device);
+	struct gm20b_clk *clk;
+	struct nvkm_subdev *subdev;
+	struct gk20a_clk_pllg_params *clk_params;
+	int ret;
+
+	/* Speedo 0 GPUs cannot use noise-aware PLL */
+	if (tdev->gpu_speedo_id == 0)
+		return gm20b_clk_new_speedo0(device, index, pclk);
+
+	/* Speedo >= 1, use NAPLL */
+	clk = kzalloc(sizeof(*clk) + sizeof(*clk_params), GFP_KERNEL);
+	if (!clk)
+		return -ENOMEM;
+	*pclk = &clk->base.base;
+	subdev = &clk->base.base.subdev;
+
+	/* duplicate the clock parameters since we will patch them below */
+	clk_params = (void *) (clk + 1);
+	*clk_params = gm20b_pllg_params;
+	ret = gk20a_clk_ctor(device, index, &gm20b_clk, clk_params,
+			     &clk->base);
+	if (ret)
+		return ret;
+
+	/*
+	 * NAPLL can only work with max_u, clamp the m range so
+	 * gk20a_pllg_calc_mnp always uses it
+	 */
+	clk_params->max_m = clk_params->min_m = DIV_ROUND_UP(clk_params->max_u,
+						(clk->base.parent_rate / KHZ));
+	if (clk_params->max_m == 0) {
+		nvkm_warn(subdev, "cannot use NAPLL, using legacy clock...\n");
+		kfree(clk);
+		return gm20b_clk_new_speedo0(device, index, pclk);
+	}
+
+	clk->base.pl_to_div = pl_to_div;
+	clk->base.div_to_pl = div_to_pl;
+
+	clk->dvfs_params = &gm20b_dvfs_params;
+
+	ret = gm20b_clk_init_fused_params(clk);
+	/*
+	 * we will calibrate during init - should never happen on
+	 * prod parts
+	 */
+	if (ret)
+		nvkm_warn(subdev, "no fused calibration parameters\n");
+
+	ret = gm20b_clk_init_safe_fmax(clk);
+	if (ret)
+		return ret;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
index 842d5de96d73..edcc157e6ac8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
@@ -24,6 +24,8 @@ nvkm-y += nvkm/subdev/fb/gk104.o
 nvkm-y += nvkm/subdev/fb/gk20a.o
 nvkm-y += nvkm/subdev/fb/gm107.o
 nvkm-y += nvkm/subdev/fb/gm200.o
+nvkm-y += nvkm/subdev/fb/gp100.o
+nvkm-y += nvkm/subdev/fb/gp104.o
 
 nvkm-y += nvkm/subdev/fb/ram.o
 nvkm-y += nvkm/subdev/fb/ramnv04.o
@@ -41,6 +43,7 @@ nvkm-y += nvkm/subdev/fb/rammcp77.o
 nvkm-y += nvkm/subdev/fb/ramgf100.o
 nvkm-y += nvkm/subdev/fb/ramgk104.o
 nvkm-y += nvkm/subdev/fb/ramgm107.o
+nvkm-y += nvkm/subdev/fb/ramgp100.o
 nvkm-y += nvkm/subdev/fb/sddr2.o
 nvkm-y += nvkm/subdev/fb/sddr3.o
 nvkm-y += nvkm/subdev/fb/gddr3.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
index ce90242b8cce..a7049c041594 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
@@ -25,6 +25,7 @@
 #include "ram.h"
 
 #include <core/memory.h>
+#include <core/option.h>
 #include <subdev/bios.h>
 #include <subdev/bios/M0203.h>
 #include <engine/gr.h>
@@ -134,6 +135,10 @@ nvkm_fb_init(struct nvkm_subdev *subdev)
 
 	if (fb->func->init)
 		fb->func->init(fb);
+	if (fb->func->init_page)
+		fb->func->init_page(fb);
+	if (fb->func->init_unkn)
+		fb->func->init_unkn(fb);
 	return 0;
 }
 
@@ -171,6 +176,7 @@ nvkm_fb_ctor(const struct nvkm_fb_func *func, struct nvkm_device *device,
 	nvkm_subdev_ctor(&nvkm_fb, device, index, &fb->subdev);
 	fb->func = func;
 	fb->tile.regions = fb->func->tile.regions;
+	fb->page = nvkm_longopt(device->cfgopt, "NvFbBigPage", 0);
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c
index e649ead5ccfc..76433cc66fff 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c
@@ -72,6 +72,22 @@ gf100_fb_oneinit(struct nvkm_fb *fb)
 }
 
 void
+gf100_fb_init_page(struct nvkm_fb *fb)
+{
+	struct nvkm_device *device = fb->subdev.device;
+	switch (fb->page) {
+	case 16:
+		nvkm_mask(device, 0x100c80, 0x00000001, 0x00000001);
+		break;
+	case 17:
+	default:
+		nvkm_mask(device, 0x100c80, 0x00000001, 0x00000000);
+		fb->page = 17;
+		break;
+	}
+}
+
+void
 gf100_fb_init(struct nvkm_fb *base)
 {
 	struct gf100_fb *fb = gf100_fb(base);
@@ -79,8 +95,6 @@ gf100_fb_init(struct nvkm_fb *base)
 
 	if (fb->r100c10_page)
 		nvkm_wr32(device, 0x100c10, fb->r100c10 >> 8);
-
-	nvkm_mask(device, 0x100c80, 0x00000001, 0x00000000); /* 128KiB lpg */
 }
 
 void *
@@ -125,6 +139,7 @@ gf100_fb = {
 	.dtor = gf100_fb_dtor,
 	.oneinit = gf100_fb_oneinit,
 	.init = gf100_fb_init,
+	.init_page = gf100_fb_init_page,
 	.intr = gf100_fb_intr,
 	.ram_new = gf100_ram_new,
 	.memtype_valid = gf100_fb_memtype_valid,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.h
index 2160e5a39c9a..449f431644b3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.h
@@ -14,4 +14,6 @@ int gf100_fb_new_(const struct nvkm_fb_func *, struct nvkm_device *,
 void *gf100_fb_dtor(struct nvkm_fb *);
 void gf100_fb_init(struct nvkm_fb *);
 void gf100_fb_intr(struct nvkm_fb *);
+
+void gp100_fb_init(struct nvkm_fb *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
index b41f0f70038c..4245e2e6e604 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
@@ -29,6 +29,7 @@ gk104_fb = {
 	.dtor = gf100_fb_dtor,
 	.oneinit = gf100_fb_oneinit,
 	.init = gf100_fb_init,
+	.init_page = gf100_fb_init_page,
 	.intr = gf100_fb_intr,
 	.ram_new = gk104_ram_new,
 	.memtype_valid = gf100_fb_memtype_valid,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk20a.c
index 7306f7dfc3b9..f815fe2bbf08 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk20a.c
@@ -27,7 +27,6 @@ static void
 gk20a_fb_init(struct nvkm_fb *fb)
 {
 	struct nvkm_device *device = fb->subdev.device;
-	nvkm_mask(device, 0x100c80, 0x00000001, 0x00000000); /* 128KiB lpg */
 	nvkm_wr32(device, 0x100cc8, nvkm_memory_addr(fb->mmu_wr) >> 8);
 	nvkm_wr32(device, 0x100ccc, nvkm_memory_addr(fb->mmu_rd) >> 8);
 }
@@ -36,6 +35,7 @@ static const struct nvkm_fb_func
 gk20a_fb = {
 	.oneinit = gf100_fb_oneinit,
 	.init = gk20a_fb_init,
+	.init_page = gf100_fb_init_page,
 	.memtype_valid = gf100_fb_memtype_valid,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c
index 4869fdb753c9..db699025f546 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c
@@ -29,6 +29,7 @@ gm107_fb = {
 	.dtor = gf100_fb_dtor,
 	.oneinit = gf100_fb_oneinit,
 	.init = gf100_fb_init,
+	.init_page = gf100_fb_init_page,
 	.intr = gf100_fb_intr,
 	.ram_new = gm107_ram_new,
 	.memtype_valid = gf100_fb_memtype_valid,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm200.c
index 44f5716f64d8..62f653240be3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm200.c
@@ -26,6 +26,24 @@
 
 #include <core/memory.h>
 
+void
+gm200_fb_init_page(struct nvkm_fb *fb)
+{
+	struct nvkm_device *device = fb->subdev.device;
+	switch (fb->page) {
+	case 16:
+		nvkm_mask(device, 0x100c80, 0x00000801, 0x00000001);
+		break;
+	case 17:
+		nvkm_mask(device, 0x100c80, 0x00000801, 0x00000000);
+		break;
+	default:
+		nvkm_mask(device, 0x100c80, 0x00000800, 0x00000800);
+		fb->page = 0;
+		break;
+	}
+}
+
 static void
 gm200_fb_init(struct nvkm_fb *base)
 {
@@ -48,6 +66,7 @@ gm200_fb = {
 	.dtor = gf100_fb_dtor,
 	.oneinit = gf100_fb_oneinit,
 	.init = gm200_fb_init,
+	.init_page = gm200_fb_init_page,
 	.intr = gf100_fb_intr,
 	.ram_new = gm107_ram_new,
 	.memtype_valid = gf100_fb_memtype_valid,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
new file mode 100644
index 000000000000..98474aec1921
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
@@ -0,0 +1,69 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "gf100.h"
+#include "ram.h"
+
+#include <core/memory.h>
+
+static void
+gp100_fb_init_unkn(struct nvkm_fb *base)
+{
+	struct nvkm_device *device = gf100_fb(base)->base.subdev.device;
+	nvkm_wr32(device, 0x1fac80, nvkm_rd32(device, 0x100c80));
+	nvkm_wr32(device, 0x1facc4, nvkm_rd32(device, 0x100cc4));
+	nvkm_wr32(device, 0x1facc8, nvkm_rd32(device, 0x100cc8));
+	nvkm_wr32(device, 0x1faccc, nvkm_rd32(device, 0x100ccc));
+}
+
+void
+gp100_fb_init(struct nvkm_fb *base)
+{
+	struct gf100_fb *fb = gf100_fb(base);
+	struct nvkm_device *device = fb->base.subdev.device;
+
+	if (fb->r100c10_page)
+		nvkm_wr32(device, 0x100c10, fb->r100c10 >> 8);
+
+	nvkm_wr32(device, 0x100cc8, nvkm_memory_addr(fb->base.mmu_wr) >> 8);
+	nvkm_wr32(device, 0x100ccc, nvkm_memory_addr(fb->base.mmu_rd) >> 8);
+	nvkm_mask(device, 0x100cc4, 0x00060000,
+		  max(nvkm_memory_size(fb->base.mmu_rd) >> 16, (u64)2) << 17);
+}
+
+static const struct nvkm_fb_func
+gp100_fb = {
+	.dtor = gf100_fb_dtor,
+	.oneinit = gf100_fb_oneinit,
+	.init = gp100_fb_init,
+	.init_page = gm200_fb_init_page,
+	.init_unkn = gp100_fb_init_unkn,
+	.ram_new = gp100_ram_new,
+	.memtype_valid = gf100_fb_memtype_valid,
+};
+
+int
+gp100_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+	return gf100_fb_new_(&gp100_fb, device, index, pfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp104.c
new file mode 100644
index 000000000000..92cb71861bec
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp104.c
@@ -0,0 +1,43 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "gf100.h"
+#include "ram.h"
+
+#include <core/memory.h>
+
+static const struct nvkm_fb_func
+gp104_fb = {
+	.dtor = gf100_fb_dtor,
+	.oneinit = gf100_fb_oneinit,
+	.init = gp100_fb_init,
+	.init_page = gm200_fb_init_page,
+	.ram_new = gp100_ram_new,
+	.memtype_valid = gf100_fb_memtype_valid,
+};
+
+int
+gp104_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+	return gf100_fb_new_(&gp104_fb, device, index, pfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
index d97d640e60a0..e905d44fa1d5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
@@ -8,6 +8,8 @@ struct nvkm_fb_func {
 	void *(*dtor)(struct nvkm_fb *);
 	int (*oneinit)(struct nvkm_fb *);
 	void (*init)(struct nvkm_fb *);
+	void (*init_page)(struct nvkm_fb *);
+	void (*init_unkn)(struct nvkm_fb *);
 	void (*intr)(struct nvkm_fb *);
 
 	struct {
@@ -60,5 +62,8 @@ void nv46_fb_tile_init(struct nvkm_fb *, int i, u32 addr, u32 size,
 		       u32 pitch, u32 flags, struct nvkm_fb_tile *);
 
 int gf100_fb_oneinit(struct nvkm_fb *);
+void gf100_fb_init_page(struct nvkm_fb *);
 bool gf100_fb_memtype_valid(struct nvkm_fb *, u32);
+
+void gm200_fb_init_page(struct nvkm_fb *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
index f816cbf2ced3..b9ec0ae6723a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
@@ -47,4 +47,5 @@ int mcp77_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 int gf100_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 int gk104_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 int gm107_ram_new(struct nvkm_fb *, struct nvkm_ram **);
+int gp100_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c
new file mode 100644
index 000000000000..f3be408b5e5e
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c
@@ -0,0 +1,146 @@
+/*
+ * Copyright 2013 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#include "ram.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/init.h>
+#include <subdev/bios/rammap.h>
+
+static int
+gp100_ram_init(struct nvkm_ram *ram)
+{
+	struct nvkm_subdev *subdev = &ram->fb->subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_bios *bios = device->bios;
+	u8  ver, hdr, cnt, len, snr, ssz;
+	u32 data;
+	int i;
+
+	/* run a bunch of tables from rammap table.  there's actually
+	 * individual pointers for each rammap entry too, but, nvidia
+	 * seem to just run the last two entries' scripts early on in
+	 * their init, and never again.. we'll just run 'em all once
+	 * for now.
+	 *
+	 * i strongly suspect that each script is for a separate mode
+	 * (likely selected by 0x9a065c's lower bits?), and the
+	 * binary driver skips the one that's already been setup by
+	 * the init tables.
+	 */
+	data = nvbios_rammapTe(bios, &ver, &hdr, &cnt, &len, &snr, &ssz);
+	if (!data || hdr < 0x15)
+		return -EINVAL;
+
+	cnt  = nvbios_rd08(bios, data + 0x14); /* guess at count */
+	data = nvbios_rd32(bios, data + 0x10); /* guess u32... */
+	if (cnt) {
+		u32 save = nvkm_rd32(device, 0x9a065c) & 0x000000f0;
+		for (i = 0; i < cnt; i++, data += 4) {
+			if (i != save >> 4) {
+				nvkm_mask(device, 0x9a065c, 0x000000f0, i << 4);
+				nvbios_exec(&(struct nvbios_init) {
+						.subdev = subdev,
+						.bios = bios,
+						.offset = nvbios_rd32(bios, data),
+						.execute = 1,
+					    });
+			}
+		}
+		nvkm_mask(device, 0x9a065c, 0x000000f0, save);
+	}
+
+	nvkm_mask(device, 0x9a0584, 0x11000000, 0x00000000);
+	nvkm_wr32(device, 0x10ecc0, 0xffffffff);
+	nvkm_mask(device, 0x9a0160, 0x00000010, 0x00000010);
+	return 0;
+}
+
+static const struct nvkm_ram_func
+gp100_ram_func = {
+	.init = gp100_ram_init,
+	.get = gf100_ram_get,
+	.put = gf100_ram_put,
+};
+
+int
+gp100_ram_new(struct nvkm_fb *fb, struct nvkm_ram **pram)
+{
+	struct nvkm_ram *ram;
+	struct nvkm_subdev *subdev = &fb->subdev;
+	struct nvkm_device *device = subdev->device;
+	enum nvkm_ram_type type = nvkm_fb_bios_memtype(device->bios);
+	const u32 rsvd_head = ( 256 * 1024); /* vga memory */
+	const u32 rsvd_tail = (1024 * 1024); /* vbios etc */
+	u32 fbpa_num = nvkm_rd32(device, 0x022438), fbpa;
+	u32 fbio_opt = nvkm_rd32(device, 0x021c14);
+	u64 part, size = 0, comm = ~0ULL;
+	bool mixed = false;
+	int ret;
+
+	nvkm_debug(subdev, "022438: %08x\n", fbpa_num);
+	nvkm_debug(subdev, "021c14: %08x\n", fbio_opt);
+	for (fbpa = 0; fbpa < fbpa_num; fbpa++) {
+		if (!(fbio_opt & (1 << fbpa))) {
+			part = nvkm_rd32(device, 0x90020c + (fbpa * 0x4000));
+			nvkm_debug(subdev, "fbpa %02x: %lld MiB\n", fbpa, part);
+			part = part << 20;
+			if (part != comm) {
+				if (comm != ~0ULL)
+					mixed = true;
+				comm = min(comm, part);
+			}
+			size = size + part;
+		}
+	}
+
+	ret = nvkm_ram_new_(&gp100_ram_func, fb, type, size, 0, &ram);
+	*pram = ram;
+	if (ret)
+		return ret;
+
+	nvkm_mm_fini(&ram->vram);
+
+	if (mixed) {
+		ret = nvkm_mm_init(&ram->vram, rsvd_head >> NVKM_RAM_MM_SHIFT,
+				   ((comm * fbpa_num) - rsvd_head) >>
+				   NVKM_RAM_MM_SHIFT, 1);
+		if (ret)
+			return ret;
+
+		ret = nvkm_mm_init(&ram->vram, (0x1000000000ULL + comm) >>
+				   NVKM_RAM_MM_SHIFT,
+				   (size - (comm * fbpa_num) - rsvd_tail) >>
+				   NVKM_RAM_MM_SHIFT, 1);
+		if (ret)
+			return ret;
+	} else {
+		ret = nvkm_mm_init(&ram->vram, rsvd_head >> NVKM_RAM_MM_SHIFT,
+				   (size - rsvd_head - rsvd_tail) >>
+				   NVKM_RAM_MM_SHIFT, 1);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
index 932b366598aa..12d6f4f102cb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
@@ -3,3 +3,4 @@ nvkm-y += nvkm/subdev/ltc/gf100.o
 nvkm-y += nvkm/subdev/ltc/gk104.o
 nvkm-y += nvkm/subdev/ltc/gm107.o
 nvkm-y += nvkm/subdev/ltc/gm200.o
+nvkm-y += nvkm/subdev/ltc/gp100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gf100.c
index c9eb677967a8..4a0fa0a9b802 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gf100.c
@@ -23,7 +23,6 @@
  */
 #include "priv.h"
 
-#include <core/enum.h>
 #include <subdev/fb.h>
 #include <subdev/timer.h>
 
@@ -71,7 +70,7 @@ gf100_ltc_zbc_clear_depth(struct nvkm_ltc *ltc, int i, const u32 depth)
 	nvkm_wr32(device, 0x17ea58, depth);
 }
 
-static const struct nvkm_bitfield
+const struct nvkm_bitfield
 gf100_ltc_lts_intr_name[] = {
 	{ 0x00000001, "IDLE_ERROR_IQ" },
 	{ 0x00000002, "IDLE_ERROR_CBC" },
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c
index 389fb13a1998..ec0a3844b2d1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c
@@ -68,18 +68,22 @@ gm107_ltc_zbc_clear_depth(struct nvkm_ltc *ltc, int i, const u32 depth)
 	nvkm_wr32(device, 0x17e34c, depth);
 }
 
-static void
+void
 gm107_ltc_intr_lts(struct nvkm_ltc *ltc, int c, int s)
 {
 	struct nvkm_subdev *subdev = &ltc->subdev;
 	struct nvkm_device *device = subdev->device;
 	u32 base = 0x140400 + (c * 0x2000) + (s * 0x200);
-	u32 stat = nvkm_rd32(device, base + 0x00c);
+	u32 intr = nvkm_rd32(device, base + 0x00c);
+	u16 stat = intr & 0x0000ffff;
+	char msg[128];
 
 	if (stat) {
-		nvkm_error(subdev, "LTC%d_LTS%d: %08x\n", c, s, stat);
-		nvkm_wr32(device, base + 0x00c, stat);
+		nvkm_snprintbf(msg, sizeof(msg), gf100_ltc_lts_intr_name, stat);
+		nvkm_error(subdev, "LTC%d_LTS%d: %08x [%s]\n", c, s, intr, msg);
 	}
+
+	nvkm_wr32(device, base + 0x00c, intr);
 }
 
 void
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp100.c
new file mode 100644
index 000000000000..0bdfb2f40266
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp100.c
@@ -0,0 +1,75 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#include "priv.h"
+
+static void
+gp100_ltc_intr(struct nvkm_ltc *ltc)
+{
+	struct nvkm_device *device = ltc->subdev.device;
+	u32 mask;
+
+	mask = nvkm_rd32(device, 0x0001c0);
+	while (mask) {
+		u32 s, c = __ffs(mask);
+		for (s = 0; s < ltc->lts_nr; s++)
+			gm107_ltc_intr_lts(ltc, c, s);
+		mask &= ~(1 << c);
+	}
+}
+
+static int
+gp100_ltc_oneinit(struct nvkm_ltc *ltc)
+{
+	struct nvkm_device *device = ltc->subdev.device;
+	ltc->ltc_nr = nvkm_rd32(device, 0x12006c);
+	ltc->lts_nr = nvkm_rd32(device, 0x17e280) >> 28;
+	/*XXX: tagram allocation - TBD */
+	return nvkm_mm_init(&ltc->tags, 0, 0, 1);
+}
+
+static void
+gp100_ltc_init(struct nvkm_ltc *ltc)
+{
+	/*XXX: PMU LS call to setup tagram address */
+}
+
+static const struct nvkm_ltc_func
+gp100_ltc = {
+	.oneinit = gp100_ltc_oneinit,
+	.init = gp100_ltc_init,
+	.intr = gp100_ltc_intr,
+	.cbc_clear = gm107_ltc_cbc_clear,
+	.cbc_wait = gm107_ltc_cbc_wait,
+	.zbc = 16,
+	.zbc_clear_color = gm107_ltc_zbc_clear_color,
+	.zbc_clear_depth = gm107_ltc_zbc_clear_depth,
+	.invalidate = gf100_ltc_invalidate,
+	.flush = gf100_ltc_flush,
+};
+
+int
+gp100_ltc_new(struct nvkm_device *device, int index, struct nvkm_ltc **pltc)
+{
+	return nvkm_ltc_new_(&gp100_ltc, device, index, pltc);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h
index 6d81c695ed0d..8b95f96e3ffa 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h
@@ -2,6 +2,7 @@
 #define __NVKM_LTC_PRIV_H__
 #define nvkm_ltc(p) container_of((p), struct nvkm_ltc, subdev)
 #include <subdev/ltc.h>
+#include <core/enum.h>
 
 int nvkm_ltc_new_(const struct nvkm_ltc_func *, struct nvkm_device *,
 		  int index, struct nvkm_ltc **);
@@ -31,8 +32,10 @@ void gf100_ltc_zbc_clear_color(struct nvkm_ltc *, int, const u32[4]);
 void gf100_ltc_zbc_clear_depth(struct nvkm_ltc *, int, const u32);
 void gf100_ltc_invalidate(struct nvkm_ltc *);
 void gf100_ltc_flush(struct nvkm_ltc *);
+extern const struct nvkm_bitfield gf100_ltc_lts_intr_name[];
 
 void gm107_ltc_intr(struct nvkm_ltc *);
+void gm107_ltc_intr_lts(struct nvkm_ltc *, int ltc, int lts);
 void gm107_ltc_cbc_clear(struct nvkm_ltc *, u32, u32);
 void gm107_ltc_cbc_wait(struct nvkm_ltc *);
 void gm107_ltc_zbc_clear_color(struct nvkm_ltc *, int, const u32[4]);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
index 49695ac7be2e..12943f92c206 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
@@ -10,3 +10,4 @@ nvkm-y += nvkm/subdev/mc/gt215.o
 nvkm-y += nvkm/subdev/mc/gf100.o
 nvkm-y += nvkm/subdev/mc/gk104.o
 nvkm-y += nvkm/subdev/mc/gk20a.o
+nvkm-y += nvkm/subdev/mc/gp100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/base.c
index 350a8caa84c8..6b25e25f9eba 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/base.c
@@ -27,43 +27,67 @@
 #include <subdev/top.h>
 
 void
-nvkm_mc_unk260(struct nvkm_mc *mc, u32 data)
+nvkm_mc_unk260(struct nvkm_device *device, u32 data)
 {
-	if (mc->func->unk260)
+	struct nvkm_mc *mc = device->mc;
+	if (likely(mc) && mc->func->unk260)
 		mc->func->unk260(mc, data);
 }
 
 void
-nvkm_mc_intr_unarm(struct nvkm_mc *mc)
+nvkm_mc_intr_mask(struct nvkm_device *device, enum nvkm_devidx devidx, bool en)
 {
-	return mc->func->intr_unarm(mc);
+	struct nvkm_mc *mc = device->mc;
+	const struct nvkm_mc_map *map;
+	if (likely(mc) && mc->func->intr_mask) {
+		u32 mask = nvkm_top_intr_mask(device, devidx);
+		for (map = mc->func->intr; !mask && map->stat; map++) {
+			if (map->unit == devidx)
+				mask = map->stat;
+		}
+		mc->func->intr_mask(mc, mask, en ? mask : 0);
+	}
+}
+
+void
+nvkm_mc_intr_unarm(struct nvkm_device *device)
+{
+	struct nvkm_mc *mc = device->mc;
+	if (likely(mc))
+		mc->func->intr_unarm(mc);
 }
 
 void
-nvkm_mc_intr_rearm(struct nvkm_mc *mc)
+nvkm_mc_intr_rearm(struct nvkm_device *device)
 {
-	return mc->func->intr_rearm(mc);
+	struct nvkm_mc *mc = device->mc;
+	if (likely(mc))
+		mc->func->intr_rearm(mc);
 }
 
 static u32
-nvkm_mc_intr_mask(struct nvkm_mc *mc)
+nvkm_mc_intr_stat(struct nvkm_mc *mc)
 {
-	u32 intr = mc->func->intr_mask(mc);
+	u32 intr = mc->func->intr_stat(mc);
 	if (WARN_ON_ONCE(intr == 0xffffffff))
 		intr = 0; /* likely fallen off the bus */
 	return intr;
 }
 
 void
-nvkm_mc_intr(struct nvkm_mc *mc, bool *handled)
+nvkm_mc_intr(struct nvkm_device *device, bool *handled)
 {
-	struct nvkm_device *device = mc->subdev.device;
+	struct nvkm_mc *mc = device->mc;
 	struct nvkm_subdev *subdev;
-	const struct nvkm_mc_map *map = mc->func->intr;
-	u32 stat, intr = nvkm_mc_intr_mask(mc);
+	const struct nvkm_mc_map *map;
+	u32 stat, intr;
 	u64 subdevs;
 
-	stat = nvkm_top_intr(device->top, intr, &subdevs);
+	if (unlikely(!mc))
+		return;
+
+	intr = nvkm_mc_intr_stat(mc);
+	stat = nvkm_top_intr(device, intr, &subdevs);
 	while (subdevs) {
 		enum nvkm_devidx subidx = __ffs64(subdevs);
 		subdev = nvkm_device_subdev(device, subidx);
@@ -72,14 +96,13 @@ nvkm_mc_intr(struct nvkm_mc *mc, bool *handled)
 		subdevs &= ~BIT_ULL(subidx);
 	}
 
-	while (map->stat) {
+	for (map = mc->func->intr; map->stat; map++) {
 		if (intr & map->stat) {
 			subdev = nvkm_device_subdev(device, map->unit);
 			if (subdev)
 				nvkm_subdev_intr(subdev);
 			stat &= ~map->stat;
 		}
-		map++;
 	}
 
 	if (stat)
@@ -87,22 +110,32 @@ nvkm_mc_intr(struct nvkm_mc *mc, bool *handled)
 	*handled = intr != 0;
 }
 
-static void
-nvkm_mc_reset_(struct nvkm_mc *mc, enum nvkm_devidx devidx)
+static u32
+nvkm_mc_reset_mask(struct nvkm_device *device, bool isauto,
+		   enum nvkm_devidx devidx)
 {
-	struct nvkm_device *device = mc->subdev.device;
+	struct nvkm_mc *mc = device->mc;
 	const struct nvkm_mc_map *map;
-	u64 pmc_enable;
-
-	if (!(pmc_enable = nvkm_top_reset(device->top, devidx))) {
-		for (map = mc->func->reset; map && map->stat; map++) {
-			if (map->unit == devidx) {
-				pmc_enable = map->stat;
-				break;
+	u64 pmc_enable = 0;
+	if (likely(mc)) {
+		if (!(pmc_enable = nvkm_top_reset(device, devidx))) {
+			for (map = mc->func->reset; map && map->stat; map++) {
+				if (!isauto || !map->noauto) {
+					if (map->unit == devidx) {
+						pmc_enable = map->stat;
+						break;
+					}
+				}
 			}
 		}
 	}
+	return pmc_enable;
+}
 
+void
+nvkm_mc_reset(struct nvkm_device *device, enum nvkm_devidx devidx)
+{
+	u64 pmc_enable = nvkm_mc_reset_mask(device, true, devidx);
 	if (pmc_enable) {
 		nvkm_mask(device, 0x000200, pmc_enable, 0x00000000);
 		nvkm_mask(device, 0x000200, pmc_enable, pmc_enable);
@@ -111,17 +144,27 @@ nvkm_mc_reset_(struct nvkm_mc *mc, enum nvkm_devidx devidx)
 }
 
 void
-nvkm_mc_reset(struct nvkm_mc *mc, enum nvkm_devidx devidx)
+nvkm_mc_disable(struct nvkm_device *device, enum nvkm_devidx devidx)
 {
-	if (likely(mc))
-		nvkm_mc_reset_(mc, devidx);
+	u64 pmc_enable = nvkm_mc_reset_mask(device, false, devidx);
+	if (pmc_enable)
+		nvkm_mask(device, 0x000200, pmc_enable, 0x00000000);
+}
+
+void
+nvkm_mc_enable(struct nvkm_device *device, enum nvkm_devidx devidx)
+{
+	u64 pmc_enable = nvkm_mc_reset_mask(device, false, devidx);
+	if (pmc_enable) {
+		nvkm_mask(device, 0x000200, pmc_enable, pmc_enable);
+		nvkm_rd32(device, 0x000200);
+	}
 }
 
 static int
 nvkm_mc_fini(struct nvkm_subdev *subdev, bool suspend)
 {
-	struct nvkm_mc *mc = nvkm_mc(subdev);
-	nvkm_mc_intr_unarm(mc);
+	nvkm_mc_intr_unarm(subdev->device);
 	return 0;
 }
 
@@ -131,7 +174,7 @@ nvkm_mc_init(struct nvkm_subdev *subdev)
 	struct nvkm_mc *mc = nvkm_mc(subdev);
 	if (mc->func->init)
 		mc->func->init(mc);
-	nvkm_mc_intr_rearm(mc);
+	nvkm_mc_intr_rearm(subdev->device);
 	return 0;
 }
 
@@ -148,16 +191,21 @@ nvkm_mc = {
 	.fini = nvkm_mc_fini,
 };
 
+void
+nvkm_mc_ctor(const struct nvkm_mc_func *func, struct nvkm_device *device,
+	     int index, struct nvkm_mc *mc)
+{
+	nvkm_subdev_ctor(&nvkm_mc, device, index, &mc->subdev);
+	mc->func = func;
+}
+
 int
 nvkm_mc_new_(const struct nvkm_mc_func *func, struct nvkm_device *device,
 	     int index, struct nvkm_mc **pmc)
 {
 	struct nvkm_mc *mc;
-
 	if (!(mc = *pmc = kzalloc(sizeof(*mc), GFP_KERNEL)))
 		return -ENOMEM;
-
-	nvkm_subdev_ctor(&nvkm_mc, device, index, &mc->subdev);
-	mc->func = func;
+	nvkm_mc_ctor(func, device, index, *pmc);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/g84.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/g84.c
index 5c85b47f071d..c3d66ef5dc12 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/g84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/g84.c
@@ -57,7 +57,7 @@ g84_mc = {
 	.intr = g84_mc_intr,
 	.intr_unarm = nv04_mc_intr_unarm,
 	.intr_rearm = nv04_mc_intr_rearm,
-	.intr_mask = nv04_mc_intr_mask,
+	.intr_stat = nv04_mc_intr_stat,
 	.reset = g84_mc_reset,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/g98.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/g98.c
index 0280b43cc10c..93ad4982ce5f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/g98.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/g98.c
@@ -57,7 +57,7 @@ g98_mc = {
 	.intr = g98_mc_intr,
 	.intr_unarm = nv04_mc_intr_unarm,
 	.intr_rearm = nv04_mc_intr_rearm,
-	.intr_mask = nv04_mc_intr_mask,
+	.intr_stat = nv04_mc_intr_stat,
 	.reset = g98_mc_reset,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gf100.c
index 8397e223bd43..d2c4d6033abb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gf100.c
@@ -76,7 +76,7 @@ gf100_mc_intr_rearm(struct nvkm_mc *mc)
 }
 
 u32
-gf100_mc_intr_mask(struct nvkm_mc *mc)
+gf100_mc_intr_stat(struct nvkm_mc *mc)
 {
 	struct nvkm_device *device = mc->subdev.device;
 	u32 intr0 = nvkm_rd32(device, 0x000100);
@@ -85,6 +85,14 @@ gf100_mc_intr_mask(struct nvkm_mc *mc)
 }
 
 void
+gf100_mc_intr_mask(struct nvkm_mc *mc, u32 mask, u32 stat)
+{
+	struct nvkm_device *device = mc->subdev.device;
+	nvkm_mask(device, 0x000640, mask, stat);
+	nvkm_mask(device, 0x000644, mask, stat);
+}
+
+void
 gf100_mc_unk260(struct nvkm_mc *mc, u32 data)
 {
 	nvkm_wr32(mc->subdev.device, 0x000260, data);
@@ -97,6 +105,7 @@ gf100_mc = {
 	.intr_unarm = gf100_mc_intr_unarm,
 	.intr_rearm = gf100_mc_intr_rearm,
 	.intr_mask = gf100_mc_intr_mask,
+	.intr_stat = gf100_mc_intr_stat,
 	.reset = gf100_mc_reset,
 	.unk260 = gf100_mc_unk260,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gk104.c
index 317464212c7d..7b8c6ecad1a5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gk104.c
@@ -26,6 +26,7 @@
 const struct nvkm_mc_map
 gk104_mc_reset[] = {
 	{ 0x00000100, NVKM_ENGINE_FIFO },
+	{ 0x00002000, NVKM_SUBDEV_PMU, true },
 	{}
 };
 
@@ -53,6 +54,7 @@ gk104_mc = {
 	.intr_unarm = gf100_mc_intr_unarm,
 	.intr_rearm = gf100_mc_intr_rearm,
 	.intr_mask = gf100_mc_intr_mask,
+	.intr_stat = gf100_mc_intr_stat,
 	.reset = gk104_mc_reset,
 	.unk260 = gf100_mc_unk260,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gk20a.c
index 60b044f517ed..ca1bf3279dbe 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gk20a.c
@@ -30,6 +30,7 @@ gk20a_mc = {
 	.intr_unarm = gf100_mc_intr_unarm,
 	.intr_rearm = gf100_mc_intr_rearm,
 	.intr_mask = gf100_mc_intr_mask,
+	.intr_stat = gf100_mc_intr_stat,
 	.reset = gk104_mc_reset,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp100.c
new file mode 100644
index 000000000000..4d22f4abd6de
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gp100.c
@@ -0,0 +1,103 @@
+/*
+ * Copyright 2012 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+#define gp100_mc(p) container_of((p), struct gp100_mc, base)
+#include "priv.h"
+
+struct gp100_mc {
+	struct nvkm_mc base;
+	spinlock_t lock;
+	bool intr;
+	u32 mask;
+};
+
+static void
+gp100_mc_intr_update(struct gp100_mc *mc)
+{
+	struct nvkm_device *device = mc->base.subdev.device;
+	u32 mask = mc->intr ? mc->mask : 0, i;
+	for (i = 0; i < 2; i++) {
+		nvkm_wr32(device, 0x000180 + (i * 0x04), ~mask);
+		nvkm_wr32(device, 0x000160 + (i * 0x04),  mask);
+	}
+}
+
+static void
+gp100_mc_intr_unarm(struct nvkm_mc *base)
+{
+	struct gp100_mc *mc = gp100_mc(base);
+	unsigned long flags;
+	spin_lock_irqsave(&mc->lock, flags);
+	mc->intr = false;
+	gp100_mc_intr_update(mc);
+	spin_unlock_irqrestore(&mc->lock, flags);
+}
+
+static void
+gp100_mc_intr_rearm(struct nvkm_mc *base)
+{
+	struct gp100_mc *mc = gp100_mc(base);
+	unsigned long flags;
+	spin_lock_irqsave(&mc->lock, flags);
+	mc->intr = true;
+	gp100_mc_intr_update(mc);
+	spin_unlock_irqrestore(&mc->lock, flags);
+}
+
+static void
+gp100_mc_intr_mask(struct nvkm_mc *base, u32 mask, u32 intr)
+{
+	struct gp100_mc *mc = gp100_mc(base);
+	unsigned long flags;
+	spin_lock_irqsave(&mc->lock, flags);
+	mc->mask = (mc->mask & ~mask) | intr;
+	gp100_mc_intr_update(mc);
+	spin_unlock_irqrestore(&mc->lock, flags);
+}
+
+static const struct nvkm_mc_func
+gp100_mc = {
+	.init = nv50_mc_init,
+	.intr = gk104_mc_intr,
+	.intr_unarm = gp100_mc_intr_unarm,
+	.intr_rearm = gp100_mc_intr_rearm,
+	.intr_mask = gp100_mc_intr_mask,
+	.intr_stat = gf100_mc_intr_stat,
+	.reset = gk104_mc_reset,
+};
+
+int
+gp100_mc_new(struct nvkm_device *device, int index, struct nvkm_mc **pmc)
+{
+	struct gp100_mc *mc;
+
+	if (!(mc = kzalloc(sizeof(*mc), GFP_KERNEL)))
+		return -ENOMEM;
+	nvkm_mc_ctor(&gp100_mc, device, index, &mc->base);
+	*pmc = &mc->base;
+
+	spin_lock_init(&mc->lock);
+	mc->intr = false;
+	mc->mask = 0x7fffffff;
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gt215.c
index aad0ba95bf18..99d50a3d956f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/gt215.c
@@ -53,13 +53,20 @@ gt215_mc_intr[] = {
 	{},
 };
 
+static void
+gt215_mc_intr_mask(struct nvkm_mc *mc, u32 mask, u32 stat)
+{
+	nvkm_mask(mc->subdev.device, 0x000640, mask, stat);
+}
+
 static const struct nvkm_mc_func
 gt215_mc = {
 	.init = nv50_mc_init,
 	.intr = gt215_mc_intr,
 	.intr_unarm = nv04_mc_intr_unarm,
 	.intr_rearm = nv04_mc_intr_rearm,
-	.intr_mask = nv04_mc_intr_mask,
+	.intr_mask = gt215_mc_intr_mask,
+	.intr_stat = nv04_mc_intr_stat,
 	.reset = gt215_mc_reset,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv04.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv04.c
index a062624e906b..6509defd1460 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv04.c
@@ -56,7 +56,7 @@ nv04_mc_intr_rearm(struct nvkm_mc *mc)
 }
 
 u32
-nv04_mc_intr_mask(struct nvkm_mc *mc)
+nv04_mc_intr_stat(struct nvkm_mc *mc)
 {
 	return nvkm_rd32(mc->subdev.device, 0x000100);
 }
@@ -75,7 +75,7 @@ nv04_mc = {
 	.intr = nv04_mc_intr,
 	.intr_unarm = nv04_mc_intr_unarm,
 	.intr_rearm = nv04_mc_intr_rearm,
-	.intr_mask = nv04_mc_intr_mask,
+	.intr_stat = nv04_mc_intr_stat,
 	.reset = nv04_mc_reset,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv11.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv11.c
index 55f0b9166b52..9213107901e6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv11.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv11.c
@@ -39,7 +39,7 @@ nv11_mc = {
 	.intr = nv11_mc_intr,
 	.intr_unarm = nv04_mc_intr_unarm,
 	.intr_rearm = nv04_mc_intr_rearm,
-	.intr_mask = nv04_mc_intr_mask,
+	.intr_stat = nv04_mc_intr_stat,
 	.reset = nv04_mc_reset,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv17.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv17.c
index c40fa67f79a5..64bf5bbf8146 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv17.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv17.c
@@ -48,7 +48,7 @@ nv17_mc = {
 	.intr = nv17_mc_intr,
 	.intr_unarm = nv04_mc_intr_unarm,
 	.intr_rearm = nv04_mc_intr_rearm,
-	.intr_mask = nv04_mc_intr_mask,
+	.intr_stat = nv04_mc_intr_stat,
 	.reset = nv17_mc_reset,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv44.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv44.c
index cc56271db564..65fa44a64b98 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv44.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv44.c
@@ -43,7 +43,7 @@ nv44_mc = {
 	.intr = nv17_mc_intr,
 	.intr_unarm = nv04_mc_intr_unarm,
 	.intr_rearm = nv04_mc_intr_rearm,
-	.intr_mask = nv04_mc_intr_mask,
+	.intr_stat = nv04_mc_intr_stat,
 	.reset = nv17_mc_reset,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv50.c
index 343b6078580d..fe93b4fd7100 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/nv50.c
@@ -50,7 +50,7 @@ nv50_mc = {
 	.intr = nv50_mc_intr,
 	.intr_unarm = nv04_mc_intr_unarm,
 	.intr_rearm = nv04_mc_intr_rearm,
-	.intr_mask = nv04_mc_intr_mask,
+	.intr_stat = nv04_mc_intr_stat,
 	.reset = nv17_mc_reset,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/priv.h
index a12038118512..4f0576a06d24 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/priv.h
@@ -3,12 +3,15 @@
 #define nvkm_mc(p) container_of((p), struct nvkm_mc, subdev)
 #include <subdev/mc.h>
 
+void nvkm_mc_ctor(const struct nvkm_mc_func *, struct nvkm_device *,
+		  int index, struct nvkm_mc *);
 int nvkm_mc_new_(const struct nvkm_mc_func *, struct nvkm_device *,
 		 int index, struct nvkm_mc **);
 
 struct nvkm_mc_map {
 	u32 stat;
 	u32 unit;
+	bool noauto;
 };
 
 struct nvkm_mc_func {
@@ -18,8 +21,10 @@ struct nvkm_mc_func {
 	void (*intr_unarm)(struct nvkm_mc *);
 	/* enable reporting of interrupts to host */
 	void (*intr_rearm)(struct nvkm_mc *);
+	/* (un)mask delivery of specific interrupts */
+	void (*intr_mask)(struct nvkm_mc *, u32 mask, u32 stat);
 	/* retrieve pending interrupt mask (NV_PMC_INTR) */
-	u32 (*intr_mask)(struct nvkm_mc *);
+	u32 (*intr_stat)(struct nvkm_mc *);
 	const struct nvkm_mc_map *reset;
 	void (*unk260)(struct nvkm_mc *, u32);
 };
@@ -27,7 +32,7 @@ struct nvkm_mc_func {
 void nv04_mc_init(struct nvkm_mc *);
 void nv04_mc_intr_unarm(struct nvkm_mc *);
 void nv04_mc_intr_rearm(struct nvkm_mc *);
-u32 nv04_mc_intr_mask(struct nvkm_mc *);
+u32 nv04_mc_intr_stat(struct nvkm_mc *);
 extern const struct nvkm_mc_map nv04_mc_reset[];
 
 extern const struct nvkm_mc_map nv17_mc_intr[];
@@ -39,7 +44,8 @@ void nv50_mc_init(struct nvkm_mc *);
 
 void gf100_mc_intr_unarm(struct nvkm_mc *);
 void gf100_mc_intr_rearm(struct nvkm_mc *);
-u32 gf100_mc_intr_mask(struct nvkm_mc *);
+void gf100_mc_intr_mask(struct nvkm_mc *, u32, u32);
+u32 gf100_mc_intr_stat(struct nvkm_mc *);
 void gf100_mc_unk260(struct nvkm_mc *, u32);
 
 extern const struct nvkm_mc_map gk104_mc_intr[];
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/Kbuild
index 3c2519fdeb81..2a31b7d66a6d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/Kbuild
@@ -10,3 +10,4 @@ nvkm-y += nvkm/subdev/pci/g94.o
 nvkm-y += nvkm/subdev/pci/gf100.o
 nvkm-y += nvkm/subdev/pci/gf106.o
 nvkm-y += nvkm/subdev/pci/gk104.o
+nvkm-y += nvkm/subdev/pci/gp100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
index 6b0328bd7eed..eb9b278198b2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
@@ -69,15 +69,13 @@ static irqreturn_t
 nvkm_pci_intr(int irq, void *arg)
 {
 	struct nvkm_pci *pci = arg;
-	struct nvkm_mc *mc = pci->subdev.device->mc;
+	struct nvkm_device *device = pci->subdev.device;
 	bool handled = false;
-	if (likely(mc)) {
-		nvkm_mc_intr_unarm(mc);
-		if (pci->msi)
-			pci->func->msi_rearm(pci);
-		nvkm_mc_intr(mc, &handled);
-		nvkm_mc_intr_rearm(mc);
-	}
+	nvkm_mc_intr_unarm(device);
+	if (pci->msi)
+		pci->func->msi_rearm(pci);
+	nvkm_mc_intr(device, &handled);
+	nvkm_mc_intr_rearm(device);
 	return handled ? IRQ_HANDLED : IRQ_NONE;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/gp100.c
new file mode 100644
index 000000000000..82c5234a06ff
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/gp100.c
@@ -0,0 +1,44 @@
+/*
+ * Copyright 2015 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "priv.h"
+
+static void
+gp100_pci_msi_rearm(struct nvkm_pci *pci)
+{
+	nvkm_pci_wr32(pci, 0x0704, 0x00000000);
+}
+
+static const struct nvkm_pci_func
+gp100_pci_func = {
+	.rd32 = nv40_pci_rd32,
+	.wr08 = nv40_pci_wr08,
+	.wr32 = nv40_pci_wr32,
+	.msi_rearm = gp100_pci_msi_rearm,
+};
+
+int
+gp100_pci_new(struct nvkm_device *device, int index, struct nvkm_pci **ppci)
+{
+	return nvkm_pci_new_(&gp100_pci_func, device, index, ppci);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/base.c
index 213fdba6cfa0..314be2192b7d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/base.c
@@ -19,8 +19,9 @@
  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  * DEALINGS IN THE SOFTWARE.
  */
-
 #include "priv.h"
+
+#include <subdev/mc.h>
 #include <subdev/timer.h>
 
 static const char *
@@ -70,12 +71,11 @@ nvkm_secboot_falcon_enable(struct nvkm_secboot *sb)
 	int ret;
 
 	/* enable engine */
-	nvkm_mask(device, 0x200, sb->enable_mask, sb->enable_mask);
-	nvkm_rd32(device, 0x200);
+	nvkm_mc_enable(device, sb->devidx);
 	ret = nvkm_wait_msec(device, 10, sb->base + 0x10c, 0x6, 0x0);
 	if (ret < 0) {
-		nvkm_mask(device, 0x200, sb->enable_mask, 0x0);
 		nvkm_error(&sb->subdev, "Falcon mem scrubbing timeout\n");
+		nvkm_mc_disable(device, sb->devidx);
 		return ret;
 	}
 
@@ -85,8 +85,7 @@ nvkm_secboot_falcon_enable(struct nvkm_secboot *sb)
 
 	/* enable IRQs */
 	nvkm_wr32(device, sb->base + 0x010, 0xff);
-	nvkm_mask(device, 0x640, sb->irq_mask, sb->irq_mask);
-	nvkm_mask(device, 0x644, sb->irq_mask, sb->irq_mask);
+	nvkm_mc_intr_mask(device, sb->devidx, true);
 
 	return 0;
 }
@@ -97,14 +96,13 @@ nvkm_secboot_falcon_disable(struct nvkm_secboot *sb)
 	struct nvkm_device *device = sb->subdev.device;
 
 	/* disable IRQs and wait for any previous code to complete */
-	nvkm_mask(device, 0x644, sb->irq_mask, 0x0);
-	nvkm_mask(device, 0x640, sb->irq_mask, 0x0);
+	nvkm_mc_intr_mask(device, sb->devidx, false);
 	nvkm_wr32(device, sb->base + 0x014, 0xff);
 
 	falcon_wait_idle(device, sb->base);
 
 	/* disable engine */
-	nvkm_mask(device, 0x200, sb->enable_mask, 0x0);
+	nvkm_mc_disable(device, sb->devidx);
 
 	return 0;
 }
@@ -216,14 +214,7 @@ nvkm_secboot_oneinit(struct nvkm_subdev *subdev)
 		return ret;
 	}
 
-	/*
-	 * Build all blobs - the same blobs can be used to perform secure boot
-	 * multiple times
-	 */
-	if (sb->func->prepare_blobs)
-		ret = sb->func->prepare_blobs(sb);
-
-	return ret;
+	return 0;
 }
 
 static int
@@ -270,9 +261,8 @@ nvkm_secboot_ctor(const struct nvkm_secboot_func *func,
 	/* setup the performing falcon's base address and masks */
 	switch (func->boot_falcon) {
 	case NVKM_SECBOOT_FALCON_PMU:
+		sb->devidx = NVKM_SUBDEV_PMU;
 		sb->base = 0x10a000;
-		sb->irq_mask = 0x1000000;
-		sb->enable_mask = 0x2000;
 		break;
 	default:
 		nvkm_error(&sb->subdev, "invalid secure boot falcon\n");
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.c
index cc100dc940ea..f1e2dc914366 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.c
@@ -860,6 +860,8 @@ gm200_secboot_prepare_ls_blob(struct gm200_secboot *gsb)
 
 	/* Write LS blob */
 	ret = ls_ucode_mgr_write_wpr(gsb, &mgr, gsb->ls_blob);
+	if (ret)
+		nvkm_gpuobj_del(&gsb->ls_blob);
 
 cleanup:
 	ls_ucode_mgr_cleanup(&mgr);
@@ -1023,29 +1025,34 @@ gm20x_secboot_prepare_blobs(struct gm200_secboot *gsb)
 	int ret;
 
 	/* Load and prepare the managed falcon's firmwares */
-	ret = gm200_secboot_prepare_ls_blob(gsb);
-	if (ret)
-		return ret;
+	if (!gsb->ls_blob) {
+		ret = gm200_secboot_prepare_ls_blob(gsb);
+		if (ret)
+			return ret;
+	}
 
 	/* Load the HS firmware that will load the LS firmwares */
-	ret = gm200_secboot_prepare_hs_blob(gsb, "acr/ucode_load",
-					    &gsb->acr_load_blob,
-					    &gsb->acr_load_bl_desc, true);
-	if (ret)
-		return ret;
+	if (!gsb->acr_load_blob) {
+		ret = gm200_secboot_prepare_hs_blob(gsb, "acr/ucode_load",
+						&gsb->acr_load_blob,
+						&gsb->acr_load_bl_desc, true);
+		if (ret)
+			return ret;
+	}
 
 	/* Load the HS firmware bootloader */
-	ret = gm200_secboot_prepare_hsbl_blob(gsb);
-	if (ret)
-		return ret;
+	if (!gsb->hsbl_blob) {
+		ret = gm200_secboot_prepare_hsbl_blob(gsb);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
 
 static int
-gm200_secboot_prepare_blobs(struct nvkm_secboot *sb)
+gm200_secboot_prepare_blobs(struct gm200_secboot *gsb)
 {
-	struct gm200_secboot *gsb = gm200_secboot(sb);
 	int ret;
 
 	ret = gm20x_secboot_prepare_blobs(gsb);
@@ -1053,15 +1060,37 @@ gm200_secboot_prepare_blobs(struct nvkm_secboot *sb)
 		return ret;
 
 	/* dGPU only: load the HS firmware that unprotects the WPR region */
-	ret = gm200_secboot_prepare_hs_blob(gsb, "acr/ucode_unload",
-					    &gsb->acr_unload_blob,
-					    &gsb->acr_unload_bl_desc, false);
-	if (ret)
-		return ret;
+	if (!gsb->acr_unload_blob) {
+		ret = gm200_secboot_prepare_hs_blob(gsb, "acr/ucode_unload",
+					       &gsb->acr_unload_blob,
+					       &gsb->acr_unload_bl_desc, false);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
 
+static int
+gm200_secboot_blobs_ready(struct gm200_secboot *gsb)
+{
+	struct nvkm_subdev *subdev = &gsb->base.subdev;
+	int ret;
+
+	/* firmware already loaded, nothing to do... */
+	if (gsb->firmware_ok)
+		return 0;
+
+	ret = gsb->func->prepare_blobs(gsb);
+	if (ret) {
+		nvkm_error(subdev, "failed to load secure firmware\n");
+		return ret;
+	}
+
+	gsb->firmware_ok = true;
+
+	return 0;
+}
 
 
 /*
@@ -1234,6 +1263,11 @@ gm200_secboot_reset(struct nvkm_secboot *sb, enum nvkm_secboot_falcon falcon)
 	struct gm200_secboot *gsb = gm200_secboot(sb);
 	int ret;
 
+	/* Make sure all blobs are ready */
+	ret = gm200_secboot_blobs_ready(gsb);
+	if (ret)
+		return ret;
+
 	/*
 	 * Dummy GM200 implementation: perform secure boot each time we are
 	 * called on FECS. Since only FECS and GPCCS are managed and started
@@ -1373,7 +1407,6 @@ gm200_secboot = {
 	.dtor = gm200_secboot_dtor,
 	.init = gm200_secboot_init,
 	.fini = gm200_secboot_fini,
-	.prepare_blobs = gm200_secboot_prepare_blobs,
 	.reset = gm200_secboot_reset,
 	.start = gm200_secboot_start,
 	.managed_falcons = BIT(NVKM_SECBOOT_FALCON_FECS) |
@@ -1415,6 +1448,7 @@ gm200_secboot_func = {
 	.bl_desc_size = sizeof(struct gm200_flcn_bl_desc),
 	.fixup_bl_desc = gm200_secboot_fixup_bl_desc,
 	.fixup_hs_desc = gm200_secboot_fixup_hs_desc,
+	.prepare_blobs = gm200_secboot_prepare_blobs,
 };
 
 int
@@ -1487,3 +1521,19 @@ MODULE_FIRMWARE("nvidia/gm206/gr/sw_ctx.bin");
 MODULE_FIRMWARE("nvidia/gm206/gr/sw_nonctx.bin");
 MODULE_FIRMWARE("nvidia/gm206/gr/sw_bundle_init.bin");
 MODULE_FIRMWARE("nvidia/gm206/gr/sw_method_init.bin");
+
+MODULE_FIRMWARE("nvidia/gp100/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gp100/acr/ucode_load.bin");
+MODULE_FIRMWARE("nvidia/gp100/acr/ucode_unload.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/sw_method_init.bin");
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
index 684320484b70..d5395ebfe8d3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
@@ -42,6 +42,32 @@ struct gm20b_flcn_bl_desc {
 	u32 data_size;
 };
 
+static int
+gm20b_secboot_prepare_blobs(struct gm200_secboot *gsb)
+{
+	struct nvkm_subdev *subdev = &gsb->base.subdev;
+	int acr_size;
+	int ret;
+
+	ret = gm20x_secboot_prepare_blobs(gsb);
+	if (ret)
+		return ret;
+
+	acr_size = gsb->acr_load_blob->size;
+	/*
+	 * On Tegra the WPR region is set by the bootloader. It is illegal for
+	 * the HS blob to be larger than this region.
+	 */
+	if (acr_size > gsb->wpr_size) {
+		nvkm_error(subdev, "WPR region too small for FW blob!\n");
+		nvkm_error(subdev, "required: %dB\n", acr_size);
+		nvkm_error(subdev, "WPR size: %dB\n", gsb->wpr_size);
+		return -ENOSPC;
+	}
+
+	return 0;
+}
+
 /**
  * gm20b_secboot_fixup_bl_desc - adapt BL descriptor to format used by GM20B FW
  *
@@ -88,6 +114,7 @@ gm20b_secboot_func = {
 	.bl_desc_size = sizeof(struct gm20b_flcn_bl_desc),
 	.fixup_bl_desc = gm20b_secboot_fixup_bl_desc,
 	.fixup_hs_desc = gm20b_secboot_fixup_hs_desc,
+	.prepare_blobs = gm20b_secboot_prepare_blobs,
 };
 
 
@@ -147,32 +174,6 @@ gm20b_tegra_read_wpr(struct gm200_secboot *gsb)
 #endif
 
 static int
-gm20b_secboot_prepare_blobs(struct nvkm_secboot *sb)
-{
-	struct gm200_secboot *gsb = gm200_secboot(sb);
-	int acr_size;
-	int ret;
-
-	ret = gm20x_secboot_prepare_blobs(gsb);
-	if (ret)
-		return ret;
-
-	acr_size = gsb->acr_load_blob->size;
-	/*
-	 * On Tegra the WPR region is set by the bootloader. It is illegal for
-	 * the HS blob to be larger than this region.
-	 */
-	if (acr_size > gsb->wpr_size) {
-		nvkm_error(&sb->subdev, "WPR region too small for FW blob!\n");
-		nvkm_error(&sb->subdev, "required: %dB\n", acr_size);
-		nvkm_error(&sb->subdev, "WPR size: %dB\n", gsb->wpr_size);
-		return -ENOSPC;
-	}
-
-	return 0;
-}
-
-static int
 gm20b_secboot_init(struct nvkm_secboot *sb)
 {
 	struct gm200_secboot *gsb = gm200_secboot(sb);
@@ -189,7 +190,6 @@ static const struct nvkm_secboot_func
 gm20b_secboot = {
 	.dtor = gm200_secboot_dtor,
 	.init = gm20b_secboot_init,
-	.prepare_blobs = gm20b_secboot_prepare_blobs,
 	.reset = gm200_secboot_reset,
 	.start = gm200_secboot_start,
 	.managed_falcons = BIT(NVKM_SECBOOT_FALCON_FECS),
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h
index f2b09dee7c5d..a9a8a0e1017e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h
@@ -30,7 +30,6 @@ struct nvkm_secboot_func {
 	int (*init)(struct nvkm_secboot *);
 	int (*fini)(struct nvkm_secboot *, bool suspend);
 	void *(*dtor)(struct nvkm_secboot *);
-	int (*prepare_blobs)(struct nvkm_secboot *);
 	int (*reset)(struct nvkm_secboot *, enum nvkm_secboot_falcon);
 	int (*start)(struct nvkm_secboot *, enum nvkm_secboot_falcon);
 
@@ -147,10 +146,8 @@ struct hsflcn_acr_desc {
  * @inst:		instance block for HS falcon
  * @pgd:		page directory for the HS falcon
  * @vm:			address space used by the HS falcon
- * @bl_desc_size:	size of the BL descriptor used by this chip.
- * @fixup_bl_desc:	hook that generates the proper BL descriptor format from
- *			the generic GM200 format into a data array of size
- *			bl_desc_size
+ * @falcon_state:	current state of the managed falcons
+ * @firmware_ok:	whether the firmware blobs have been created
  */
 struct gm200_secboot {
 	struct nvkm_secboot base;
@@ -196,9 +193,19 @@ struct gm200_secboot {
 		RUNNING,
 	} falcon_state[NVKM_SECBOOT_FALCON_END];
 
+	bool firmware_ok;
 };
 #define gm200_secboot(sb) container_of(sb, struct gm200_secboot, base)
 
+/**
+ * Contains functions we wish to abstract between GM200-like implementations
+ * @bl_desc_size:	size of the BL descriptor used by this chip.
+ * @fixup_bl_desc:	hook that generates the proper BL descriptor format from
+ *			the generic GM200 format into a data array of size
+ *			bl_desc_size
+ * @fixup_hs_desc:	hook that twiddles the HS descriptor before it is used
+ * @prepare_blobs:	prepares the various blobs needed for secure booting
+ */
 struct gm200_secboot_func {
 	/*
 	 * Size of the bootloader descriptor for this chip. A block of this
@@ -214,6 +221,7 @@ struct gm200_secboot_func {
 	 * we want the HS FW to set up.
 	 */
 	void (*fixup_hs_desc)(struct gm200_secboot *, struct hsflcn_acr_desc *);
+	int (*prepare_blobs)(struct gm200_secboot *);
 };
 
 int gm200_secboot_init(struct nvkm_secboot *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/top/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/top/base.c
index a1b264664aad..fe063d5728e2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/top/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/top/base.c
@@ -41,8 +41,9 @@ nvkm_top_device_new(struct nvkm_top *top)
 }
 
 u32
-nvkm_top_reset(struct nvkm_top *top, enum nvkm_devidx index)
+nvkm_top_reset(struct nvkm_device *device, enum nvkm_devidx index)
 {
+	struct nvkm_top *top = device->top;
 	struct nvkm_top_device *info;
 
 	if (top) {
@@ -56,8 +57,25 @@ nvkm_top_reset(struct nvkm_top *top, enum nvkm_devidx index)
 }
 
 u32
-nvkm_top_intr(struct nvkm_top *top, u32 intr, u64 *psubdevs)
+nvkm_top_intr_mask(struct nvkm_device *device, enum nvkm_devidx devidx)
 {
+	struct nvkm_top *top = device->top;
+	struct nvkm_top_device *info;
+
+	if (top) {
+		list_for_each_entry(info, &top->device, head) {
+			if (info->index == devidx && info->intr >= 0)
+				return BIT(info->intr);
+		}
+	}
+
+	return 0;
+}
+
+u32
+nvkm_top_intr(struct nvkm_device *device, u32 intr, u64 *psubdevs)
+{
+	struct nvkm_top *top = device->top;
 	struct nvkm_top_device *info;
 	u64 subdevs = 0;
 	u32 handled = 0;
@@ -78,8 +96,9 @@ nvkm_top_intr(struct nvkm_top *top, u32 intr, u64 *psubdevs)
 }
 
 enum nvkm_devidx
-nvkm_top_fault(struct nvkm_top *top, int fault)
+nvkm_top_fault(struct nvkm_device *device, int fault)
 {
+	struct nvkm_top *top = device->top;
 	struct nvkm_top_device *info;
 
 	list_for_each_entry(info, &top->device, head) {
@@ -91,8 +110,9 @@ nvkm_top_fault(struct nvkm_top *top, int fault)
 }
 
 enum nvkm_devidx
-nvkm_top_engine(struct nvkm_top *top, int index, int *runl, int *engn)
+nvkm_top_engine(struct nvkm_device *device, int index, int *runl, int *engn)
 {
+	struct nvkm_top *top = device->top;
 	struct nvkm_top_device *info;
 	int n = 0;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/top/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/top/gk104.c
index e06acc340e99..efac3402f9dd 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/top/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/top/gk104.c
@@ -29,7 +29,7 @@ gk104_top_oneinit(struct nvkm_top *top)
 	struct nvkm_subdev *subdev = &top->subdev;
 	struct nvkm_device *device = subdev->device;
 	struct nvkm_top_device *info = NULL;
-	u32 data, type;
+	u32 data, type, inst;
 	int i;
 
 	for (i = 0; i < 64; i++) {
@@ -37,6 +37,7 @@ gk104_top_oneinit(struct nvkm_top *top)
 			if (!(info = nvkm_top_device_new(top)))
 				return -ENOMEM;
 			type = ~0;
+			inst = 0;
 		}
 
 		data = nvkm_rd32(device, 0x022700 + (i * 0x04));
@@ -45,6 +46,7 @@ gk104_top_oneinit(struct nvkm_top *top)
 		case 0x00000000: /* NOT_VALID */
 			continue;
 		case 0x00000001: /* DATA */
+			inst        = (data & 0x3c000000) >> 26;
 			info->addr  = (data & 0x00fff000);
 			info->fault = (data & 0x000000f8) >> 3;
 			break;
@@ -67,27 +69,32 @@ gk104_top_oneinit(struct nvkm_top *top)
 			continue;
 
 		/* Translate engine type to NVKM engine identifier. */
+#define A_(A) if (inst == 0) info->index = NVKM_ENGINE_##A
+#define B_(A) if (inst + NVKM_ENGINE_##A##0 < NVKM_ENGINE_##A##_LAST + 1)      \
+		info->index = NVKM_ENGINE_##A##0 + inst
 		switch (type) {
-		case 0x00000000: info->index = NVKM_ENGINE_GR; break;
-		case 0x00000001: info->index = NVKM_ENGINE_CE0; break;
-		case 0x00000002: info->index = NVKM_ENGINE_CE1; break;
-		case 0x00000003: info->index = NVKM_ENGINE_CE2; break;
-		case 0x00000008: info->index = NVKM_ENGINE_MSPDEC; break;
-		case 0x00000009: info->index = NVKM_ENGINE_MSPPP; break;
-		case 0x0000000a: info->index = NVKM_ENGINE_MSVLD; break;
-		case 0x0000000b: info->index = NVKM_ENGINE_MSENC; break;
-		case 0x0000000c: info->index = NVKM_ENGINE_VIC; break;
-		case 0x0000000d: info->index = NVKM_ENGINE_SEC; break;
-		case 0x0000000e: info->index = NVKM_ENGINE_NVENC0; break;
-		case 0x0000000f: info->index = NVKM_ENGINE_NVENC1; break;
-		case 0x00000010: info->index = NVKM_ENGINE_NVDEC; break;
+		case 0x00000000: A_(GR    ); break;
+		case 0x00000001: A_(CE0   ); break;
+		case 0x00000002: A_(CE1   ); break;
+		case 0x00000003: A_(CE2   ); break;
+		case 0x00000008: A_(MSPDEC); break;
+		case 0x00000009: A_(MSPPP ); break;
+		case 0x0000000a: A_(MSVLD ); break;
+		case 0x0000000b: A_(MSENC ); break;
+		case 0x0000000c: A_(VIC   ); break;
+		case 0x0000000d: A_(SEC   ); break;
+		case 0x0000000e: B_(NVENC ); break;
+		case 0x0000000f: A_(NVENC1); break;
+		case 0x00000010: A_(NVDEC ); break;
+		case 0x00000013: B_(CE    ); break;
 			break;
 		default:
 			break;
 		}
 
-		nvkm_debug(subdev, "%02x (%8s): addr %06x fault %2d engine %2d "
-				   "runlist %2d intr %2d reset %2d\n", type,
+		nvkm_debug(subdev, "%02x.%d (%8s): addr %06x fault %2d "
+				   "engine %2d runlist %2d intr %2d "
+				   "reset %2d\n", type, inst,
 			   info->index == NVKM_SUBDEV_NR ? NULL :
 					  nvkm_subdev_name[info->index],
 			   info->addr, info->fault, info->engine, info->runlist,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/base.c
index 6b2d7531a7ff..1c3d23b0e84a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/base.c
@@ -120,6 +120,8 @@ nvkm_volt_parse_bios(struct nvkm_bios *bios, struct nvkm_volt *volt)
 
 	data = nvbios_volt_parse(bios, &ver, &hdr, &cnt, &len, &info);
 	if (data && info.vidmask && info.base && info.step) {
+		volt->min_uv = info.min;
+		volt->max_uv = info.max;
 		for (i = 0; i < info.vidmask + 1; i++) {
 			if (info.base >= info.min &&
 				info.base <= info.max) {
@@ -131,6 +133,8 @@ nvkm_volt_parse_bios(struct nvkm_bios *bios, struct nvkm_volt *volt)
 		}
 		volt->vid_mask = info.vidmask;
 	} else if (data && info.vidmask) {
+		volt->min_uv = 0xffffffff;
+		volt->max_uv = 0;
 		for (i = 0; i < cnt; i++) {
 			data = nvbios_volt_entry_parse(bios, i, &ver, &hdr,
 						       &ivid);
@@ -138,9 +142,14 @@ nvkm_volt_parse_bios(struct nvkm_bios *bios, struct nvkm_volt *volt)
 				volt->vid[volt->vid_nr].uv = ivid.voltage;
 				volt->vid[volt->vid_nr].vid = ivid.vid;
 				volt->vid_nr++;
+				volt->min_uv = min(volt->min_uv, ivid.voltage);
+				volt->max_uv = max(volt->max_uv, ivid.voltage);
 			}
 		}
 		volt->vid_mask = info.vidmask;
+	} else if (data && info.type == NVBIOS_VOLT_PWM) {
+		volt->min_uv = info.base;
+		volt->max_uv = info.base + info.pwm_range;
 	}
 }
 
@@ -181,8 +190,11 @@ nvkm_volt_ctor(const struct nvkm_volt_func *func, struct nvkm_device *device,
 	volt->func = func;
 
 	/* Assuming the non-bios device should build the voltage table later */
-	if (bios)
+	if (bios) {
 		nvkm_volt_parse_bios(bios, volt);
+		nvkm_debug(&volt->subdev, "min: %iuv max: %iuv\n",
+			   volt->min_uv, volt->max_uv);
+	}
 
 	if (volt->vid_nr) {
 		for (i = 0; i < volt->vid_nr; i++) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.c
index d554455326da..ce5d83cdc7cf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.c
@@ -77,18 +77,19 @@ gk20a_volt_get_cvb_t_voltage(int speedo, int temp, int s_scale, int t_scale,
 	return mv;
 }
 
-int
+static int
 gk20a_volt_calc_voltage(const struct cvb_coef *coef, int speedo)
 {
+	static const int v_scale = 1000;
 	int mv;
 
 	mv = gk20a_volt_get_cvb_t_voltage(speedo, -10, 100, 10, coef);
-	mv = DIV_ROUND_UP(mv, 1000);
+	mv = DIV_ROUND_UP(mv, v_scale);
 
 	return mv * 1000;
 }
 
-int
+static int
 gk20a_volt_vid_get(struct nvkm_volt *base)
 {
 	struct gk20a_volt *volt = gk20a_volt(base);
@@ -103,7 +104,7 @@ gk20a_volt_vid_get(struct nvkm_volt *base)
 	return -EINVAL;
 }
 
-int
+static int
 gk20a_volt_vid_set(struct nvkm_volt *base, u8 vid)
 {
 	struct gk20a_volt *volt = gk20a_volt(base);
@@ -113,7 +114,7 @@ gk20a_volt_vid_set(struct nvkm_volt *base, u8 vid)
 	return regulator_set_voltage(volt->vdd, volt->base.vid[vid].uv, 1200000);
 }
 
-int
+static int
 gk20a_volt_set_id(struct nvkm_volt *base, u8 id, int condition)
 {
 	struct gk20a_volt *volt = gk20a_volt(base);
@@ -143,9 +144,9 @@ gk20a_volt = {
 };
 
 int
-_gk20a_volt_ctor(struct nvkm_device *device, int index,
-		 const struct cvb_coef *coefs, int nb_coefs,
-		 struct gk20a_volt *volt)
+gk20a_volt_ctor(struct nvkm_device *device, int index,
+		const struct cvb_coef *coefs, int nb_coefs,
+		int vmin, struct gk20a_volt *volt)
 {
 	struct nvkm_device_tegra *tdev = device->func->tegra(device);
 	int i, uv;
@@ -160,9 +161,9 @@ _gk20a_volt_ctor(struct nvkm_device *device, int index,
 	volt->base.vid_nr = nb_coefs;
 	for (i = 0; i < volt->base.vid_nr; i++) {
 		volt->base.vid[i].vid = i;
-		volt->base.vid[i].uv =
-			gk20a_volt_calc_voltage(&coefs[i],
-						tdev->gpu_speedo);
+		volt->base.vid[i].uv = max(
+			gk20a_volt_calc_voltage(&coefs[i], tdev->gpu_speedo),
+			vmin);
 		nvkm_debug(&volt->base.subdev, "%2d: vid=%d, uv=%d\n", i,
 			   volt->base.vid[i].vid, volt->base.vid[i].uv);
 	}
@@ -180,6 +181,6 @@ gk20a_volt_new(struct nvkm_device *device, int index, struct nvkm_volt **pvolt)
 		return -ENOMEM;
 	*pvolt = &volt->base;
 
-	return _gk20a_volt_ctor(device, index, gk20a_cvb_coef,
-				ARRAY_SIZE(gk20a_cvb_coef), volt);
+	return gk20a_volt_ctor(device, index, gk20a_cvb_coef,
+			       ARRAY_SIZE(gk20a_cvb_coef), 0, volt);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.h b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.h
index 0fa3b502bcf8..6a6c97f9684e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk20a.h
@@ -37,13 +37,8 @@ struct gk20a_volt {
 	struct regulator *vdd;
 };
 
-int _gk20a_volt_ctor(struct nvkm_device *device, int index,
-		     const struct cvb_coef *coefs, int nb_coefs,
-		     struct gk20a_volt *volt);
-
-int gk20a_volt_calc_voltage(const struct cvb_coef *coef, int speedo);
-int gk20a_volt_vid_get(struct nvkm_volt *volt);
-int gk20a_volt_vid_set(struct nvkm_volt *volt, u8 vid);
-int gk20a_volt_set_id(struct nvkm_volt *volt, u8 id, int condition);
+int gk20a_volt_ctor(struct nvkm_device *device, int index,
+		    const struct cvb_coef *coefs, int nb_coefs,
+		    int vmin, struct gk20a_volt *volt);
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gm20b.c
index 49b5ecb701e4..74db4d28930f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gm20b.c
@@ -41,16 +41,52 @@ const struct cvb_coef gm20b_cvb_coef[] = {
 	/* 921600 */ { 2647676, -106455, 1632 },
 };
 
+static const struct cvb_coef gm20b_na_cvb_coef[] = {
+	/* KHz,         c0,     c1,   c2,    c3,     c4,   c5 */
+	/*  76800 */ {  814294, 8144, -940, 808, -21583, 226 },
+	/* 153600 */ {  856185, 8144, -940, 808, -21583, 226 },
+	/* 230400 */ {  898077, 8144, -940, 808, -21583, 226 },
+	/* 307200 */ {  939968, 8144, -940, 808, -21583, 226 },
+	/* 384000 */ {  981860, 8144, -940, 808, -21583, 226 },
+	/* 460800 */ { 1023751, 8144, -940, 808, -21583, 226 },
+	/* 537600 */ { 1065642, 8144, -940, 808, -21583, 226 },
+	/* 614400 */ { 1107534, 8144, -940, 808, -21583, 226 },
+	/* 691200 */ { 1149425, 8144, -940, 808, -21583, 226 },
+	/* 768000 */ { 1191317, 8144, -940, 808, -21583, 226 },
+	/* 844800 */ { 1233208, 8144, -940, 808, -21583, 226 },
+	/* 921600 */ { 1275100, 8144, -940, 808, -21583, 226 },
+	/* 998400 */ { 1316991, 8144, -940, 808, -21583, 226 },
+};
+
+const u32 speedo_to_vmin[] = {
+	/*   0,      1,      2,      3,      4, */
+	950000, 840000, 818750, 840000, 810000,
+};
+
 int
 gm20b_volt_new(struct nvkm_device *device, int index, struct nvkm_volt **pvolt)
 {
+	struct nvkm_device_tegra *tdev = device->func->tegra(device);
 	struct gk20a_volt *volt;
+	u32 vmin;
+
+	if (tdev->gpu_speedo_id >= ARRAY_SIZE(speedo_to_vmin)) {
+		nvdev_error(device, "unsupported speedo %d\n",
+			    tdev->gpu_speedo_id);
+		return -EINVAL;
+	}
 
 	volt = kzalloc(sizeof(*volt), GFP_KERNEL);
 	if (!volt)
 		return -ENOMEM;
 	*pvolt = &volt->base;
 
-	return _gk20a_volt_ctor(device, index, gm20b_cvb_coef,
-				ARRAY_SIZE(gm20b_cvb_coef), volt);
+	vmin = speedo_to_vmin[tdev->gpu_speedo_id];
+
+	if (tdev->gpu_speedo_id >= 1)
+		return gk20a_volt_ctor(device, index, gm20b_na_cvb_coef,
+				     ARRAY_SIZE(gm20b_na_cvb_coef), vmin, volt);
+	else
+		return gk20a_volt_ctor(device, index, gm20b_cvb_coef,
+					ARRAY_SIZE(gm20b_cvb_coef), vmin, volt);
 }
diff --git a/drivers/gpu/drm/omapdrm/Kconfig b/drivers/gpu/drm/omapdrm/Kconfig
index 336ad4de9981..556f81f6b2c7 100644
--- a/drivers/gpu/drm/omapdrm/Kconfig
+++ b/drivers/gpu/drm/omapdrm/Kconfig
@@ -4,11 +4,6 @@ config DRM_OMAP
 	depends on ARCH_OMAP2PLUS || ARCH_MULTIPLATFORM
 	select OMAP2_DSS
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
-	select FB_SYS_FILLRECT
-	select FB_SYS_COPYAREA
-	select FB_SYS_IMAGEBLIT
-	select FB_SYS_FOPS
 	default n
 	help
 	  DRM display driver for OMAP2/3/4 based boards.
diff --git a/drivers/gpu/drm/omapdrm/displays/Kconfig b/drivers/gpu/drm/omapdrm/displays/Kconfig
index 2a618afe0f53..c226da145fb3 100644
--- a/drivers/gpu/drm/omapdrm/displays/Kconfig
+++ b/drivers/gpu/drm/omapdrm/displays/Kconfig
@@ -1,80 +1,80 @@
 menu "OMAPDRM External Display Device Drivers"
 
-config DISPLAY_ENCODER_OPA362
+config DRM_OMAP_ENCODER_OPA362
 	tristate "OPA362 external analog amplifier"
 	help
 	  Driver for OPA362 external analog TV amplifier controlled
 	  through a GPIO.
 
-config DISPLAY_ENCODER_TFP410
+config DRM_OMAP_ENCODER_TFP410
         tristate "TFP410 DPI to DVI Encoder"
 	help
 	  Driver for TFP410 DPI to DVI encoder.
 
-config DISPLAY_ENCODER_TPD12S015
+config DRM_OMAP_ENCODER_TPD12S015
         tristate "TPD12S015 HDMI ESD protection and level shifter"
 	help
 	  Driver for TPD12S015, which offers HDMI ESD protection and level
 	  shifting.
 
-config DISPLAY_CONNECTOR_DVI
+config DRM_OMAP_CONNECTOR_DVI
         tristate "DVI Connector"
 	depends on I2C
 	help
 	  Driver for a generic DVI connector.
 
-config DISPLAY_CONNECTOR_HDMI
+config DRM_OMAP_CONNECTOR_HDMI
         tristate "HDMI Connector"
 	help
 	  Driver for a generic HDMI connector.
 
-config DISPLAY_CONNECTOR_ANALOG_TV
+config DRM_OMAP_CONNECTOR_ANALOG_TV
         tristate "Analog TV Connector"
 	help
 	  Driver for a generic analog TV connector.
 
-config DISPLAY_PANEL_DPI
+config DRM_OMAP_PANEL_DPI
 	tristate "Generic DPI panel"
 	help
 	  Driver for generic DPI panels.
 
-config DISPLAY_PANEL_DSI_CM
+config DRM_OMAP_PANEL_DSI_CM
 	tristate "Generic DSI Command Mode Panel"
 	depends on BACKLIGHT_CLASS_DEVICE
 	help
 	  Driver for generic DSI command mode panels.
 
-config DISPLAY_PANEL_SONY_ACX565AKM
+config DRM_OMAP_PANEL_SONY_ACX565AKM
 	tristate "ACX565AKM Panel"
 	depends on SPI && BACKLIGHT_CLASS_DEVICE
 	help
 	  This is the LCD panel used on Nokia N900
 
-config DISPLAY_PANEL_LGPHILIPS_LB035Q02
+config DRM_OMAP_PANEL_LGPHILIPS_LB035Q02
 	tristate "LG.Philips LB035Q02 LCD Panel"
 	depends on SPI
 	help
 	  LCD Panel used on the Gumstix Overo Palo35
 
-config DISPLAY_PANEL_SHARP_LS037V7DW01
+config DRM_OMAP_PANEL_SHARP_LS037V7DW01
         tristate "Sharp LS037V7DW01 LCD Panel"
         depends on BACKLIGHT_CLASS_DEVICE
         help
           LCD Panel used in TI's SDP3430 and EVM boards
 
-config DISPLAY_PANEL_TPO_TD028TTEC1
+config DRM_OMAP_PANEL_TPO_TD028TTEC1
         tristate "TPO TD028TTEC1 LCD Panel"
         depends on SPI
         help
           LCD panel used in Openmoko.
 
-config DISPLAY_PANEL_TPO_TD043MTEA1
+config DRM_OMAP_PANEL_TPO_TD043MTEA1
         tristate "TPO TD043MTEA1 LCD Panel"
         depends on SPI
         help
           LCD Panel used in OMAP3 Pandora
 
-config DISPLAY_PANEL_NEC_NL8048HL11
+config DRM_OMAP_PANEL_NEC_NL8048HL11
 	tristate "NEC NL8048HL11 Panel"
 	depends on SPI
 	depends on BACKLIGHT_CLASS_DEVICE
diff --git a/drivers/gpu/drm/omapdrm/displays/Makefile b/drivers/gpu/drm/omapdrm/displays/Makefile
index 9aa176bfbf2e..46baafb1a83e 100644
--- a/drivers/gpu/drm/omapdrm/displays/Makefile
+++ b/drivers/gpu/drm/omapdrm/displays/Makefile
@@ -1,14 +1,14 @@
-obj-$(CONFIG_DISPLAY_ENCODER_OPA362) += encoder-opa362.o
-obj-$(CONFIG_DISPLAY_ENCODER_TFP410) += encoder-tfp410.o
-obj-$(CONFIG_DISPLAY_ENCODER_TPD12S015) += encoder-tpd12s015.o
-obj-$(CONFIG_DISPLAY_CONNECTOR_DVI) += connector-dvi.o
-obj-$(CONFIG_DISPLAY_CONNECTOR_HDMI) += connector-hdmi.o
-obj-$(CONFIG_DISPLAY_CONNECTOR_ANALOG_TV) += connector-analog-tv.o
-obj-$(CONFIG_DISPLAY_PANEL_DPI) += panel-dpi.o
-obj-$(CONFIG_DISPLAY_PANEL_DSI_CM) += panel-dsi-cm.o
-obj-$(CONFIG_DISPLAY_PANEL_SONY_ACX565AKM) += panel-sony-acx565akm.o
-obj-$(CONFIG_DISPLAY_PANEL_LGPHILIPS_LB035Q02) += panel-lgphilips-lb035q02.o
-obj-$(CONFIG_DISPLAY_PANEL_SHARP_LS037V7DW01) += panel-sharp-ls037v7dw01.o
-obj-$(CONFIG_DISPLAY_PANEL_TPO_TD028TTEC1) += panel-tpo-td028ttec1.o
-obj-$(CONFIG_DISPLAY_PANEL_TPO_TD043MTEA1) += panel-tpo-td043mtea1.o
-obj-$(CONFIG_DISPLAY_PANEL_NEC_NL8048HL11) += panel-nec-nl8048hl11.o
+obj-$(CONFIG_DRM_OMAP_ENCODER_OPA362) += encoder-opa362.o
+obj-$(CONFIG_DRM_OMAP_ENCODER_TFP410) += encoder-tfp410.o
+obj-$(CONFIG_DRM_OMAP_ENCODER_TPD12S015) += encoder-tpd12s015.o
+obj-$(CONFIG_DRM_OMAP_CONNECTOR_DVI) += connector-dvi.o
+obj-$(CONFIG_DRM_OMAP_CONNECTOR_HDMI) += connector-hdmi.o
+obj-$(CONFIG_DRM_OMAP_CONNECTOR_ANALOG_TV) += connector-analog-tv.o
+obj-$(CONFIG_DRM_OMAP_PANEL_DPI) += panel-dpi.o
+obj-$(CONFIG_DRM_OMAP_PANEL_DSI_CM) += panel-dsi-cm.o
+obj-$(CONFIG_DRM_OMAP_PANEL_SONY_ACX565AKM) += panel-sony-acx565akm.o
+obj-$(CONFIG_DRM_OMAP_PANEL_LGPHILIPS_LB035Q02) += panel-lgphilips-lb035q02.o
+obj-$(CONFIG_DRM_OMAP_PANEL_SHARP_LS037V7DW01) += panel-sharp-ls037v7dw01.o
+obj-$(CONFIG_DRM_OMAP_PANEL_TPO_TD028TTEC1) += panel-tpo-td028ttec1.o
+obj-$(CONFIG_DRM_OMAP_PANEL_TPO_TD043MTEA1) += panel-tpo-td043mtea1.o
+obj-$(CONFIG_DRM_OMAP_PANEL_NEC_NL8048HL11) += panel-nec-nl8048hl11.o
diff --git a/drivers/gpu/drm/omapdrm/displays/connector-analog-tv.c b/drivers/gpu/drm/omapdrm/displays/connector-analog-tv.c
index 8511c648a15c..3485d1ecd655 100644
--- a/drivers/gpu/drm/omapdrm/displays/connector-analog-tv.c
+++ b/drivers/gpu/drm/omapdrm/displays/connector-analog-tv.c
@@ -14,9 +14,10 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 
-#include <video/omapdss.h>
 #include <video/omap-panel-data.h>
 
+#include "../dss/omapdss.h"
+
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
 	struct omap_dss_device *in;
@@ -25,7 +26,6 @@ struct panel_drv_data {
 
 	struct omap_video_timings timings;
 
-	enum omap_dss_venc_type connector_type;
 	bool invert_polarity;
 };
 
@@ -45,10 +45,6 @@ static const struct omap_video_timings tvc_pal_timings = {
 
 static const struct of_device_id tvc_of_match[];
 
-struct tvc_of_data {
-	enum omap_dss_venc_type connector_type;
-};
-
 #define to_panel_data(x) container_of(x, struct panel_drv_data, dssdev)
 
 static int tvc_connect(struct omap_dss_device *dssdev)
@@ -99,7 +95,7 @@ static int tvc_enable(struct omap_dss_device *dssdev)
 	in->ops.atv->set_timings(in, &ddata->timings);
 
 	if (!ddata->dev->of_node) {
-		in->ops.atv->set_type(in, ddata->connector_type);
+		in->ops.atv->set_type(in, OMAP_DSS_VENC_TYPE_COMPOSITE);
 
 		in->ops.atv->invert_vid_out_polarity(in,
 			ddata->invert_polarity);
@@ -207,7 +203,6 @@ static int tvc_probe_pdata(struct platform_device *pdev)
 
 	ddata->in = in;
 
-	ddata->connector_type = pdata->connector_type;
 	ddata->invert_polarity = pdata->invert_polarity;
 
 	dssdev = &ddata->dssdev;
diff --git a/drivers/gpu/drm/omapdrm/displays/connector-dvi.c b/drivers/gpu/drm/omapdrm/displays/connector-dvi.c
index 747f26a55e43..684b7aeda411 100644
--- a/drivers/gpu/drm/omapdrm/displays/connector-dvi.c
+++ b/drivers/gpu/drm/omapdrm/displays/connector-dvi.c
@@ -15,10 +15,10 @@
 #include <linux/slab.h>
 
 #include <drm/drm_edid.h>
-
-#include <video/omapdss.h>
 #include <video/omap-panel-data.h>
 
+#include "../dss/omapdss.h"
+
 static const struct omap_video_timings dvic_default_timings = {
 	.x_res		= 640,
 	.y_res		= 480,
@@ -255,6 +255,7 @@ static int dvic_probe_of(struct platform_device *pdev)
 	adapter_node = of_parse_phandle(node, "ddc-i2c-bus", 0);
 	if (adapter_node) {
 		adapter = of_get_i2c_adapter_by_node(adapter_node);
+		of_node_put(adapter_node);
 		if (adapter == NULL) {
 			dev_err(&pdev->dev, "failed to parse ddc-i2c-bus\n");
 			omap_dss_put_device(ddata->in);
diff --git a/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c b/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
index 667ca4a24ece..7bdf83af9797 100644
--- a/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
+++ b/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
@@ -17,10 +17,10 @@
 #include <linux/of_gpio.h>
 
 #include <drm/drm_edid.h>
-
-#include <video/omapdss.h>
 #include <video/omap-panel-data.h>
 
+#include "../dss/omapdss.h"
+
 static const struct omap_video_timings hdmic_default_timings = {
 	.x_res		= 640,
 	.y_res		= 480,
diff --git a/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c b/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
index 9594ff7a2b0c..fe4e7ec3bab0 100644
--- a/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
+++ b/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
@@ -18,9 +18,8 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
+#include "../dss/omapdss.h"
 
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
diff --git a/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c b/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
index 671806ca7d6a..d768217cefe0 100644
--- a/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
+++ b/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
@@ -15,8 +15,7 @@
 #include <linux/slab.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include "../dss/omapdss.h"
 
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
diff --git a/drivers/gpu/drm/omapdrm/displays/encoder-tpd12s015.c b/drivers/gpu/drm/omapdrm/displays/encoder-tpd12s015.c
index 916a89978387..46855c8f5cbf 100644
--- a/drivers/gpu/drm/omapdrm/displays/encoder-tpd12s015.c
+++ b/drivers/gpu/drm/omapdrm/displays/encoder-tpd12s015.c
@@ -16,8 +16,7 @@
 #include <linux/platform_device.h>
 #include <linux/gpio/consumer.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include "../dss/omapdss.h"
 
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-dpi.c b/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
index 7c2331be8d15..7f16f985ab22 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
@@ -15,11 +15,13 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
+#include <linux/regulator/consumer.h>
 
-#include <video/omapdss.h>
 #include <video/omap-panel-data.h>
 #include <video/of_display_timing.h>
 
+#include "../dss/omapdss.h"
+
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
 	struct omap_dss_device *in;
@@ -32,6 +34,7 @@ struct panel_drv_data {
 	int backlight_gpio;
 
 	struct gpio_desc *enable_gpio;
+	struct regulator *vcc_supply;
 };
 
 #define to_panel_data(p) container_of(p, struct panel_drv_data, dssdev)
@@ -83,6 +86,12 @@ static int panel_dpi_enable(struct omap_dss_device *dssdev)
 	if (r)
 		return r;
 
+	r = regulator_enable(ddata->vcc_supply);
+	if (r) {
+		in->ops.dpi->disable(in);
+		return r;
+	}
+
 	gpiod_set_value_cansleep(ddata->enable_gpio, 1);
 
 	if (gpio_is_valid(ddata->backlight_gpio))
@@ -105,6 +114,7 @@ static void panel_dpi_disable(struct omap_dss_device *dssdev)
 		gpio_set_value_cansleep(ddata->backlight_gpio, 0);
 
 	gpiod_set_value_cansleep(ddata->enable_gpio, 0);
+	regulator_disable(ddata->vcc_supply);
 
 	in->ops.dpi->disable(in);
 
@@ -213,6 +223,20 @@ static int panel_dpi_probe_of(struct platform_device *pdev)
 
 	ddata->enable_gpio = gpio;
 
+	/*
+	 * Many different panels are supported by this driver and there are
+	 * probably very different needs for their reset pins in regards to
+	 * timing and order relative to the enable gpio. So for now it's just
+	 * ensured that the reset line isn't active.
+	 */
+	gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(gpio))
+		return PTR_ERR(gpio);
+
+	ddata->vcc_supply = devm_regulator_get(&pdev->dev, "vcc");
+	if (IS_ERR(ddata->vcc_supply))
+		return PTR_ERR(ddata->vcc_supply);
+
 	ddata->backlight_gpio = -ENOENT;
 
 	r = of_get_display_timing(node, "panel-timing", &timing);
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c b/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
index 2b118071b5a1..0eae8afaed90 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
@@ -25,10 +25,10 @@
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
 #include <video/mipi_display.h>
 
+#include "../dss/omapdss.h"
+
 /* DSI Virtual channel. Hardcoded for now. */
 #define TCH 0
 
@@ -1284,8 +1284,7 @@ static int dsicm_probe(struct platform_device *pdev)
 	return 0;
 
 err_sysfs_create:
-	if (bldev != NULL)
-		backlight_device_unregister(bldev);
+	backlight_device_unregister(bldev);
 err_bl:
 	destroy_workqueue(ddata->workqueue);
 err_reg:
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c b/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
index ac680e1de603..6dfb96cea293 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
@@ -17,8 +17,7 @@
 #include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include "../dss/omapdss.h"
 
 static struct omap_video_timings lb035q02_timings = {
 	.x_res = 320,
@@ -51,9 +50,6 @@ struct panel_drv_data {
 
 	struct omap_video_timings videomode;
 
-	/* used for non-DT boot, to be removed */
-	int backlight_gpio;
-
 	struct gpio_desc *enable_gpio;
 };
 
@@ -171,9 +167,6 @@ static int lb035q02_enable(struct omap_dss_device *dssdev)
 	if (ddata->enable_gpio)
 		gpiod_set_value_cansleep(ddata->enable_gpio, 1);
 
-	if (gpio_is_valid(ddata->backlight_gpio))
-		gpio_set_value_cansleep(ddata->backlight_gpio, 1);
-
 	dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
 
 	return 0;
@@ -190,9 +183,6 @@ static void lb035q02_disable(struct omap_dss_device *dssdev)
 	if (ddata->enable_gpio)
 		gpiod_set_value_cansleep(ddata->enable_gpio, 0);
 
-	if (gpio_is_valid(ddata->backlight_gpio))
-		gpio_set_value_cansleep(ddata->backlight_gpio, 0);
-
 	in->ops.dpi->disable(in);
 
 	dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
@@ -256,8 +246,6 @@ static int lb035q02_probe_of(struct spi_device *spi)
 
 	ddata->enable_gpio = gpio;
 
-	ddata->backlight_gpio = -ENOENT;
-
 	in = omapdss_of_find_source_for_first_ep(node);
 	if (IS_ERR(in)) {
 		dev_err(&spi->dev, "failed to find video source\n");
@@ -290,13 +278,6 @@ static int lb035q02_panel_spi_probe(struct spi_device *spi)
 	if (r)
 		return r;
 
-	if (gpio_is_valid(ddata->backlight_gpio)) {
-		r = devm_gpio_request_one(&spi->dev, ddata->backlight_gpio,
-				GPIOF_OUT_INIT_LOW, "panel backlight");
-		if (r)
-			goto err_gpio;
-	}
-
 	ddata->videomode = lb035q02_timings;
 
 	dssdev = &ddata->dssdev;
@@ -316,7 +297,6 @@ static int lb035q02_panel_spi_probe(struct spi_device *spi)
 	return 0;
 
 err_reg:
-err_gpio:
 	omap_dss_put_device(ddata->in);
 	return r;
 }
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c b/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
index 38d2920a95e6..fc4c238c9583 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
@@ -18,7 +18,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
+#include "../dss/omapdss.h"
 
 struct panel_drv_data {
 	struct omap_dss_device	dssdev;
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c b/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
index 4363fffc87e3..3d3efc561ea9 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
@@ -13,11 +13,11 @@
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/regulator/consumer.h>
-#include <video/omapdss.h>
+
+#include "../dss/omapdss.h"
 
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
index deb416736aad..157c512205d1 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
@@ -33,9 +33,10 @@
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
 #include <video/omap-panel-data.h>
 
+#include "../dss/omapdss.h"
+
 #define MIPID_CMD_READ_DISP_ID		0x04
 #define MIPID_CMD_READ_RED		0x06
 #define MIPID_CMD_READ_GREEN		0x07
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c
index bd8d85041926..e859b3f893f7 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c
@@ -28,7 +28,8 @@
 #include <linux/delay.h>
 #include <linux/spi/spi.h>
 #include <linux/gpio.h>
-#include <video/omapdss.h>
+
+#include "../dss/omapdss.h"
 
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
index d93175b03a12..66c6bbe6472b 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
@@ -19,7 +19,7 @@
 #include <linux/slab.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
+#include "../dss/omapdss.h"
 
 #define TPO_R02_MODE(x)		((x) & 7)
 #define TPO_R02_MODE_800x480	7
diff --git a/drivers/gpu/drm/omapdrm/dss/core.c b/drivers/gpu/drm/omapdrm/dss/core.c
index 7e4e5bebabbe..6a3ebfcd7223 100644
--- a/drivers/gpu/drm/omapdrm/dss/core.c
+++ b/drivers/gpu/drm/omapdrm/dss/core.c
@@ -35,8 +35,7 @@
 #include <linux/suspend.h>
 #include <linux/slab.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 #include "dss_features.h"
 
@@ -196,8 +195,6 @@ static int __init omap_dss_probe(struct platform_device *pdev)
 		core.default_display_name = def_disp_name;
 	else if (pdata->default_display_name)
 		core.default_display_name = pdata->default_display_name;
-	else if (pdata->default_device)
-		core.default_display_name = pdata->default_device->name;
 
 	return 0;
 
diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.c b/drivers/gpu/drm/omapdrm/dss/dispc.c
index f83608b69e68..535240fba671 100644
--- a/drivers/gpu/drm/omapdrm/dss/dispc.c
+++ b/drivers/gpu/drm/omapdrm/dss/dispc.c
@@ -41,8 +41,7 @@
 #include <linux/of.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 #include "dss_features.h"
 #include "dispc.h"
@@ -113,9 +112,14 @@ struct dispc_features {
 	 * never both, we can just use this flag for now.
 	 */
 	bool reverse_ilace_field_order:1;
+
+	bool has_gamma_table:1;
+
+	bool has_gamma_i734_bug:1;
 };
 
 #define DISPC_MAX_NR_FIFOS 5
+#define DISPC_MAX_CHANNEL_GAMMA 4
 
 static struct {
 	struct platform_device *pdev;
@@ -135,6 +139,8 @@ static struct {
 	bool		ctx_valid;
 	u32		ctx[DISPC_SZ_REGS / sizeof(u32)];
 
+	u32 *gamma_table[DISPC_MAX_CHANNEL_GAMMA];
+
 	const struct dispc_features *feat;
 
 	bool is_enabled;
@@ -178,11 +184,19 @@ struct dispc_reg_field {
 	u8 low;
 };
 
+struct dispc_gamma_desc {
+	u32 len;
+	u32 bits;
+	u16 reg;
+	bool has_index;
+};
+
 static const struct {
 	const char *name;
 	u32 vsync_irq;
 	u32 framedone_irq;
 	u32 sync_lost_irq;
+	struct dispc_gamma_desc gamma;
 	struct dispc_reg_field reg_desc[DISPC_MGR_FLD_NUM];
 } mgr_desc[] = {
 	[OMAP_DSS_CHANNEL_LCD] = {
@@ -190,6 +204,12 @@ static const struct {
 		.vsync_irq	= DISPC_IRQ_VSYNC,
 		.framedone_irq	= DISPC_IRQ_FRAMEDONE,
 		.sync_lost_irq	= DISPC_IRQ_SYNC_LOST,
+		.gamma		= {
+			.len	= 256,
+			.bits	= 8,
+			.reg	= DISPC_GAMMA_TABLE0,
+			.has_index = true,
+		},
 		.reg_desc	= {
 			[DISPC_MGR_FLD_ENABLE]		= { DISPC_CONTROL,  0,  0 },
 			[DISPC_MGR_FLD_STNTFT]		= { DISPC_CONTROL,  3,  3 },
@@ -207,6 +227,12 @@ static const struct {
 		.vsync_irq	= DISPC_IRQ_EVSYNC_ODD | DISPC_IRQ_EVSYNC_EVEN,
 		.framedone_irq	= DISPC_IRQ_FRAMEDONETV,
 		.sync_lost_irq	= DISPC_IRQ_SYNC_LOST_DIGIT,
+		.gamma		= {
+			.len	= 1024,
+			.bits	= 10,
+			.reg	= DISPC_GAMMA_TABLE2,
+			.has_index = false,
+		},
 		.reg_desc	= {
 			[DISPC_MGR_FLD_ENABLE]		= { DISPC_CONTROL,  1,  1 },
 			[DISPC_MGR_FLD_STNTFT]		= { },
@@ -224,6 +250,12 @@ static const struct {
 		.vsync_irq	= DISPC_IRQ_VSYNC2,
 		.framedone_irq	= DISPC_IRQ_FRAMEDONE2,
 		.sync_lost_irq	= DISPC_IRQ_SYNC_LOST2,
+		.gamma		= {
+			.len	= 256,
+			.bits	= 8,
+			.reg	= DISPC_GAMMA_TABLE1,
+			.has_index = true,
+		},
 		.reg_desc	= {
 			[DISPC_MGR_FLD_ENABLE]		= { DISPC_CONTROL2,  0,  0 },
 			[DISPC_MGR_FLD_STNTFT]		= { DISPC_CONTROL2,  3,  3 },
@@ -241,6 +273,12 @@ static const struct {
 		.vsync_irq	= DISPC_IRQ_VSYNC3,
 		.framedone_irq	= DISPC_IRQ_FRAMEDONE3,
 		.sync_lost_irq	= DISPC_IRQ_SYNC_LOST3,
+		.gamma		= {
+			.len	= 256,
+			.bits	= 8,
+			.reg	= DISPC_GAMMA_TABLE3,
+			.has_index = true,
+		},
 		.reg_desc	= {
 			[DISPC_MGR_FLD_ENABLE]		= { DISPC_CONTROL3,  0,  0 },
 			[DISPC_MGR_FLD_STNTFT]		= { DISPC_CONTROL3,  3,  3 },
@@ -1084,20 +1122,6 @@ static u32 dispc_ovl_get_burst_size(enum omap_plane plane)
 	return unit * 8;
 }
 
-void dispc_enable_gamma_table(bool enable)
-{
-	/*
-	 * This is partially implemented to support only disabling of
-	 * the gamma table.
-	 */
-	if (enable) {
-		DSSWARN("Gamma table enabling for TV not yet supported");
-		return;
-	}
-
-	REG_FLD_MOD(DISPC_CONFIG, enable, 9, 9);
-}
-
 static void dispc_mgr_enable_cpr(enum omap_channel channel, bool enable)
 {
 	if (channel == OMAP_DSS_CHANNEL_DIGIT)
@@ -3299,30 +3323,21 @@ static void dispc_mgr_get_lcd_divisor(enum omap_channel channel, int *lck_div,
 
 static unsigned long dispc_fclk_rate(void)
 {
-	struct dss_pll *pll;
-	unsigned long r = 0;
+	unsigned long r;
+	enum dss_clk_source src;
+
+	src = dss_get_dispc_clk_source();
 
-	switch (dss_get_dispc_clk_source()) {
-	case OMAP_DSS_CLK_SRC_FCK:
+	if (src == DSS_CLK_SRC_FCK) {
 		r = dss_get_dispc_clk_rate();
-		break;
-	case OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
-		pll = dss_pll_find("dsi0");
-		if (!pll)
-			pll = dss_pll_find("video0");
+	} else {
+		struct dss_pll *pll;
+		unsigned clkout_idx;
 
-		r = pll->cinfo.clkout[0];
-		break;
-	case OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC:
-		pll = dss_pll_find("dsi1");
-		if (!pll)
-			pll = dss_pll_find("video1");
+		pll = dss_pll_find_by_src(src);
+		clkout_idx = dss_pll_get_clkout_idx_for_src(src);
 
-		r = pll->cinfo.clkout[0];
-		break;
-	default:
-		BUG();
-		return 0;
+		r = pll->cinfo.clkout[clkout_idx];
 	}
 
 	return r;
@@ -3330,43 +3345,31 @@ static unsigned long dispc_fclk_rate(void)
 
 static unsigned long dispc_mgr_lclk_rate(enum omap_channel channel)
 {
-	struct dss_pll *pll;
 	int lcd;
 	unsigned long r;
-	u32 l;
-
-	if (dss_mgr_is_lcd(channel)) {
-		l = dispc_read_reg(DISPC_DIVISORo(channel));
+	enum dss_clk_source src;
 
-		lcd = FLD_GET(l, 23, 16);
+	/* for TV, LCLK rate is the FCLK rate */
+	if (!dss_mgr_is_lcd(channel))
+		return dispc_fclk_rate();
 
-		switch (dss_get_lcd_clk_source(channel)) {
-		case OMAP_DSS_CLK_SRC_FCK:
-			r = dss_get_dispc_clk_rate();
-			break;
-		case OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
-			pll = dss_pll_find("dsi0");
-			if (!pll)
-				pll = dss_pll_find("video0");
+	src = dss_get_lcd_clk_source(channel);
 
-			r = pll->cinfo.clkout[0];
-			break;
-		case OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC:
-			pll = dss_pll_find("dsi1");
-			if (!pll)
-				pll = dss_pll_find("video1");
+	if (src == DSS_CLK_SRC_FCK) {
+		r = dss_get_dispc_clk_rate();
+	} else {
+		struct dss_pll *pll;
+		unsigned clkout_idx;
 
-			r = pll->cinfo.clkout[0];
-			break;
-		default:
-			BUG();
-			return 0;
-		}
+		pll = dss_pll_find_by_src(src);
+		clkout_idx = dss_pll_get_clkout_idx_for_src(src);
 
-		return r / lcd;
-	} else {
-		return dispc_fclk_rate();
+		r = pll->cinfo.clkout[clkout_idx];
 	}
+
+	lcd = REG_GET(DISPC_DIVISORo(channel), 23, 16);
+
+	return r / lcd;
 }
 
 static unsigned long dispc_mgr_pclk_rate(enum omap_channel channel)
@@ -3426,15 +3429,14 @@ static unsigned long dispc_plane_lclk_rate(enum omap_plane plane)
 static void dispc_dump_clocks_channel(struct seq_file *s, enum omap_channel channel)
 {
 	int lcd, pcd;
-	enum omap_dss_clk_source lcd_clk_src;
+	enum dss_clk_source lcd_clk_src;
 
 	seq_printf(s, "- %s -\n", mgr_desc[channel].name);
 
 	lcd_clk_src = dss_get_lcd_clk_source(channel);
 
-	seq_printf(s, "%s clk source = %s (%s)\n", mgr_desc[channel].name,
-		dss_get_generic_clk_source_name(lcd_clk_src),
-		dss_feat_get_clk_source_name(lcd_clk_src));
+	seq_printf(s, "%s clk source = %s\n", mgr_desc[channel].name,
+		dss_get_clk_source_name(lcd_clk_src));
 
 	dispc_mgr_get_lcd_divisor(channel, &lcd, &pcd);
 
@@ -3448,16 +3450,15 @@ void dispc_dump_clocks(struct seq_file *s)
 {
 	int lcd;
 	u32 l;
-	enum omap_dss_clk_source dispc_clk_src = dss_get_dispc_clk_source();
+	enum dss_clk_source dispc_clk_src = dss_get_dispc_clk_source();
 
 	if (dispc_runtime_get())
 		return;
 
 	seq_printf(s, "- DISPC -\n");
 
-	seq_printf(s, "dispc fclk source = %s (%s)\n",
-			dss_get_generic_clk_source_name(dispc_clk_src),
-			dss_feat_get_clk_source_name(dispc_clk_src));
+	seq_printf(s, "dispc fclk source = %s\n",
+			dss_get_clk_source_name(dispc_clk_src));
 
 	seq_printf(s, "fck\t\t%-16lu\n", dispc_fclk_rate());
 
@@ -3814,6 +3815,139 @@ void dispc_disable_sidle(void)
 	REG_FLD_MOD(DISPC_SYSCONFIG, 1, 4, 3);	/* SIDLEMODE: no idle */
 }
 
+u32 dispc_mgr_gamma_size(enum omap_channel channel)
+{
+	const struct dispc_gamma_desc *gdesc = &mgr_desc[channel].gamma;
+
+	if (!dispc.feat->has_gamma_table)
+		return 0;
+
+	return gdesc->len;
+}
+EXPORT_SYMBOL(dispc_mgr_gamma_size);
+
+static void dispc_mgr_write_gamma_table(enum omap_channel channel)
+{
+	const struct dispc_gamma_desc *gdesc = &mgr_desc[channel].gamma;
+	u32 *table = dispc.gamma_table[channel];
+	unsigned int i;
+
+	DSSDBG("%s: channel %d\n", __func__, channel);
+
+	for (i = 0; i < gdesc->len; ++i) {
+		u32 v = table[i];
+
+		if (gdesc->has_index)
+			v |= i << 24;
+		else if (i == 0)
+			v |= 1 << 31;
+
+		dispc_write_reg(gdesc->reg, v);
+	}
+}
+
+static void dispc_restore_gamma_tables(void)
+{
+	DSSDBG("%s()\n", __func__);
+
+	if (!dispc.feat->has_gamma_table)
+		return;
+
+	dispc_mgr_write_gamma_table(OMAP_DSS_CHANNEL_LCD);
+
+	dispc_mgr_write_gamma_table(OMAP_DSS_CHANNEL_DIGIT);
+
+	if (dss_has_feature(FEAT_MGR_LCD2))
+		dispc_mgr_write_gamma_table(OMAP_DSS_CHANNEL_LCD2);
+
+	if (dss_has_feature(FEAT_MGR_LCD3))
+		dispc_mgr_write_gamma_table(OMAP_DSS_CHANNEL_LCD3);
+}
+
+static const struct drm_color_lut dispc_mgr_gamma_default_lut[] = {
+	{ .red = 0, .green = 0, .blue = 0, },
+	{ .red = U16_MAX, .green = U16_MAX, .blue = U16_MAX, },
+};
+
+void dispc_mgr_set_gamma(enum omap_channel channel,
+			 const struct drm_color_lut *lut,
+			 unsigned int length)
+{
+	const struct dispc_gamma_desc *gdesc = &mgr_desc[channel].gamma;
+	u32 *table = dispc.gamma_table[channel];
+	uint i;
+
+	DSSDBG("%s: channel %d, lut len %u, hw len %u\n", __func__,
+	       channel, length, gdesc->len);
+
+	if (!dispc.feat->has_gamma_table)
+		return;
+
+	if (lut == NULL || length < 2) {
+		lut = dispc_mgr_gamma_default_lut;
+		length = ARRAY_SIZE(dispc_mgr_gamma_default_lut);
+	}
+
+	for (i = 0; i < length - 1; ++i) {
+		uint first = i * (gdesc->len - 1) / (length - 1);
+		uint last = (i + 1) * (gdesc->len - 1) / (length - 1);
+		uint w = last - first;
+		u16 r, g, b;
+		uint j;
+
+		if (w == 0)
+			continue;
+
+		for (j = 0; j <= w; j++) {
+			r = (lut[i].red * (w - j) + lut[i+1].red * j) / w;
+			g = (lut[i].green * (w - j) + lut[i+1].green * j) / w;
+			b = (lut[i].blue * (w - j) + lut[i+1].blue * j) / w;
+
+			r >>= 16 - gdesc->bits;
+			g >>= 16 - gdesc->bits;
+			b >>= 16 - gdesc->bits;
+
+			table[first + j] = (r << (gdesc->bits * 2)) |
+				(g << gdesc->bits) | b;
+		}
+	}
+
+	if (dispc.is_enabled)
+		dispc_mgr_write_gamma_table(channel);
+}
+EXPORT_SYMBOL(dispc_mgr_set_gamma);
+
+static int dispc_init_gamma_tables(void)
+{
+	int channel;
+
+	if (!dispc.feat->has_gamma_table)
+		return 0;
+
+	for (channel = 0; channel < ARRAY_SIZE(dispc.gamma_table); channel++) {
+		const struct dispc_gamma_desc *gdesc = &mgr_desc[channel].gamma;
+		u32 *gt;
+
+		if (channel == OMAP_DSS_CHANNEL_LCD2 &&
+		    !dss_has_feature(FEAT_MGR_LCD2))
+			continue;
+
+		if (channel == OMAP_DSS_CHANNEL_LCD3 &&
+		    !dss_has_feature(FEAT_MGR_LCD3))
+			continue;
+
+		gt = devm_kmalloc_array(&dispc.pdev->dev, gdesc->len,
+					   sizeof(u32), GFP_KERNEL);
+		if (!gt)
+			return -ENOMEM;
+
+		dispc.gamma_table[channel] = gt;
+
+		dispc_mgr_set_gamma(channel, NULL, 0);
+	}
+	return 0;
+}
+
 static void _omap_dispc_initial_config(void)
 {
 	u32 l;
@@ -3829,8 +3963,15 @@ static void _omap_dispc_initial_config(void)
 		dispc.core_clk_rate = dispc_fclk_rate();
 	}
 
-	/* FUNCGATED */
-	if (dss_has_feature(FEAT_FUNCGATED))
+	/* Use gamma table mode, instead of palette mode */
+	if (dispc.feat->has_gamma_table)
+		REG_FLD_MOD(DISPC_CONFIG, 1, 3, 3);
+
+	/* For older DSS versions (FEAT_FUNCGATED) this enables
+	 * func-clock auto-gating. For newer versions
+	 * (dispc.feat->has_gamma_table) this enables tv-out gamma tables.
+	 */
+	if (dss_has_feature(FEAT_FUNCGATED) || dispc.feat->has_gamma_table)
 		REG_FLD_MOD(DISPC_CONFIG, 1, 9, 9);
 
 	dispc_setup_color_conv_coef();
@@ -3934,6 +4075,8 @@ static const struct dispc_features omap44xx_dispc_feats = {
 	.has_writeback		=	true,
 	.supports_double_pixel	=	true,
 	.reverse_ilace_field_order =	true,
+	.has_gamma_table	=	true,
+	.has_gamma_i734_bug	=	true,
 };
 
 static const struct dispc_features omap54xx_dispc_feats = {
@@ -3959,6 +4102,8 @@ static const struct dispc_features omap54xx_dispc_feats = {
 	.has_writeback		=	true,
 	.supports_double_pixel	=	true,
 	.reverse_ilace_field_order =	true,
+	.has_gamma_table	=	true,
+	.has_gamma_i734_bug	=	true,
 };
 
 static int dispc_init_features(struct platform_device *pdev)
@@ -4050,6 +4195,168 @@ void dispc_free_irq(void *dev_id)
 }
 EXPORT_SYMBOL(dispc_free_irq);
 
+/*
+ * Workaround for errata i734 in DSS dispc
+ *  - LCD1 Gamma Correction Is Not Working When GFX Pipe Is Disabled
+ *
+ * For gamma tables to work on LCD1 the GFX plane has to be used at
+ * least once after DSS HW has come out of reset. The workaround
+ * sets up a minimal LCD setup with GFX plane and waits for one
+ * vertical sync irq before disabling the setup and continuing with
+ * the context restore. The physical outputs are gated during the
+ * operation. This workaround requires that gamma table's LOADMODE
+ * is set to 0x2 in DISPC_CONTROL1 register.
+ *
+ * For details see:
+ * OMAP543x Multimedia Device Silicon Revision 2.0 Silicon Errata
+ * Literature Number: SWPZ037E
+ * Or some other relevant errata document for the DSS IP version.
+ */
+
+static const struct dispc_errata_i734_data {
+	struct omap_video_timings timings;
+	struct omap_overlay_info ovli;
+	struct omap_overlay_manager_info mgri;
+	struct dss_lcd_mgr_config lcd_conf;
+} i734 = {
+	.timings = {
+		.x_res = 8, .y_res = 1,
+		.pixelclock = 16000000,
+		.hsw = 8, .hfp = 4, .hbp = 4,
+		.vsw = 1, .vfp = 1, .vbp = 1,
+		.vsync_level = OMAPDSS_SIG_ACTIVE_LOW,
+		.hsync_level = OMAPDSS_SIG_ACTIVE_LOW,
+		.interlace = false,
+		.data_pclk_edge = OMAPDSS_DRIVE_SIG_RISING_EDGE,
+		.de_level = OMAPDSS_SIG_ACTIVE_HIGH,
+		.sync_pclk_edge = OMAPDSS_DRIVE_SIG_RISING_EDGE,
+		.double_pixel = false,
+	},
+	.ovli = {
+		.screen_width = 1,
+		.width = 1, .height = 1,
+		.color_mode = OMAP_DSS_COLOR_RGB24U,
+		.rotation = OMAP_DSS_ROT_0,
+		.rotation_type = OMAP_DSS_ROT_DMA,
+		.mirror = 0,
+		.pos_x = 0, .pos_y = 0,
+		.out_width = 0, .out_height = 0,
+		.global_alpha = 0xff,
+		.pre_mult_alpha = 0,
+		.zorder = 0,
+	},
+	.mgri = {
+		.default_color = 0,
+		.trans_enabled = false,
+		.partial_alpha_enabled = false,
+		.cpr_enable = false,
+	},
+	.lcd_conf = {
+		.io_pad_mode = DSS_IO_PAD_MODE_BYPASS,
+		.stallmode = false,
+		.fifohandcheck = false,
+		.clock_info = {
+			.lck_div = 1,
+			.pck_div = 2,
+		},
+		.video_port_width = 24,
+		.lcden_sig_polarity = 0,
+	},
+};
+
+static struct i734_buf {
+	size_t size;
+	dma_addr_t paddr;
+	void *vaddr;
+} i734_buf;
+
+static int dispc_errata_i734_wa_init(void)
+{
+	if (!dispc.feat->has_gamma_i734_bug)
+		return 0;
+
+	i734_buf.size = i734.ovli.width * i734.ovli.height *
+		color_mode_to_bpp(i734.ovli.color_mode) / 8;
+
+	i734_buf.vaddr = dma_alloc_writecombine(&dispc.pdev->dev, i734_buf.size,
+						&i734_buf.paddr, GFP_KERNEL);
+	if (!i734_buf.vaddr) {
+		dev_err(&dispc.pdev->dev, "%s: dma_alloc_writecombine failed",
+			__func__);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void dispc_errata_i734_wa_fini(void)
+{
+	if (!dispc.feat->has_gamma_i734_bug)
+		return;
+
+	dma_free_writecombine(&dispc.pdev->dev, i734_buf.size, i734_buf.vaddr,
+			      i734_buf.paddr);
+}
+
+static void dispc_errata_i734_wa(void)
+{
+	u32 framedone_irq = dispc_mgr_get_framedone_irq(OMAP_DSS_CHANNEL_LCD);
+	struct omap_overlay_info ovli;
+	struct dss_lcd_mgr_config lcd_conf;
+	u32 gatestate;
+	unsigned int count;
+
+	if (!dispc.feat->has_gamma_i734_bug)
+		return;
+
+	gatestate = REG_GET(DISPC_CONFIG, 8, 4);
+
+	ovli = i734.ovli;
+	ovli.paddr = i734_buf.paddr;
+	lcd_conf = i734.lcd_conf;
+
+	/* Gate all LCD1 outputs */
+	REG_FLD_MOD(DISPC_CONFIG, 0x1f, 8, 4);
+
+	/* Setup and enable GFX plane */
+	dispc_ovl_set_channel_out(OMAP_DSS_GFX, OMAP_DSS_CHANNEL_LCD);
+	dispc_ovl_setup(OMAP_DSS_GFX, &ovli, false, &i734.timings, false);
+	dispc_ovl_enable(OMAP_DSS_GFX, true);
+
+	/* Set up and enable display manager for LCD1 */
+	dispc_mgr_setup(OMAP_DSS_CHANNEL_LCD, &i734.mgri);
+	dispc_calc_clock_rates(dss_get_dispc_clk_rate(),
+			       &lcd_conf.clock_info);
+	dispc_mgr_set_lcd_config(OMAP_DSS_CHANNEL_LCD, &lcd_conf);
+	dispc_mgr_set_timings(OMAP_DSS_CHANNEL_LCD, &i734.timings);
+
+	dispc_clear_irqstatus(framedone_irq);
+
+	/* Enable and shut the channel to produce just one frame */
+	dispc_mgr_enable(OMAP_DSS_CHANNEL_LCD, true);
+	dispc_mgr_enable(OMAP_DSS_CHANNEL_LCD, false);
+
+	/* Busy wait for framedone. We can't fiddle with irq handlers
+	 * in PM resume. Typically the loop runs less than 5 times and
+	 * waits less than a micro second.
+	 */
+	count = 0;
+	while (!(dispc_read_irqstatus() & framedone_irq)) {
+		if (count++ > 10000) {
+			dev_err(&dispc.pdev->dev, "%s: framedone timeout\n",
+				__func__);
+			break;
+		}
+	}
+	dispc_ovl_enable(OMAP_DSS_GFX, false);
+
+	/* Clear all irq bits before continuing */
+	dispc_clear_irqstatus(0xffffffff);
+
+	/* Restore the original state to LCD1 output gates */
+	REG_FLD_MOD(DISPC_CONFIG, gatestate, 8, 4);
+}
+
 /* DISPC HW IP initialisation */
 static int dispc_bind(struct device *dev, struct device *master, void *data)
 {
@@ -4067,6 +4374,10 @@ static int dispc_bind(struct device *dev, struct device *master, void *data)
 	if (r)
 		return r;
 
+	r = dispc_errata_i734_wa_init();
+	if (r)
+		return r;
+
 	dispc_mem = platform_get_resource(dispc.pdev, IORESOURCE_MEM, 0);
 	if (!dispc_mem) {
 		DSSERR("can't get IORESOURCE_MEM DISPC\n");
@@ -4100,6 +4411,10 @@ static int dispc_bind(struct device *dev, struct device *master, void *data)
 		}
 	}
 
+	r = dispc_init_gamma_tables();
+	if (r)
+		return r;
+
 	pm_runtime_enable(&pdev->dev);
 
 	r = dispc_runtime_get();
@@ -4127,6 +4442,8 @@ static void dispc_unbind(struct device *dev, struct device *master,
 			       void *data)
 {
 	pm_runtime_disable(dev);
+
+	dispc_errata_i734_wa_fini();
 }
 
 static const struct component_ops dispc_component_ops = {
@@ -4169,7 +4486,11 @@ static int dispc_runtime_resume(struct device *dev)
 	if (REG_GET(DISPC_CONFIG, 2, 1) != OMAP_DSS_LOAD_FRAME_ONLY) {
 		_omap_dispc_initial_config();
 
+		dispc_errata_i734_wa();
+
 		dispc_restore_context();
+
+		dispc_restore_gamma_tables();
 	}
 
 	dispc.is_enabled = true;
diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.h b/drivers/gpu/drm/omapdrm/dss/dispc.h
index 483744223dd1..bc1d8126ee87 100644
--- a/drivers/gpu/drm/omapdrm/dss/dispc.h
+++ b/drivers/gpu/drm/omapdrm/dss/dispc.h
@@ -42,6 +42,11 @@
 #define DISPC_MSTANDBY_CTRL		0x0858
 #define DISPC_GLOBAL_MFLAG_ATTRIBUTE	0x085C
 
+#define DISPC_GAMMA_TABLE0		0x0630
+#define DISPC_GAMMA_TABLE1		0x0634
+#define DISPC_GAMMA_TABLE2		0x0638
+#define DISPC_GAMMA_TABLE3		0x0850
+
 /* DISPC overlay registers */
 #define DISPC_OVL_BA0(n)		(DISPC_OVL_BASE(n) + \
 					DISPC_BA0_OFFSET(n))
diff --git a/drivers/gpu/drm/omapdrm/dss/dispc_coefs.c b/drivers/gpu/drm/omapdrm/dss/dispc_coefs.c
index 038c15b04215..34fad2376f8d 100644
--- a/drivers/gpu/drm/omapdrm/dss/dispc_coefs.c
+++ b/drivers/gpu/drm/omapdrm/dss/dispc_coefs.c
@@ -18,8 +18,8 @@
  */
 
 #include <linux/kernel.h>
-#include <video/omapdss.h>
 
+#include "omapdss.h"
 #include "dispc.h"
 
 static const struct dispc_coef coef3_M8[8] = {
diff --git a/drivers/gpu/drm/omapdrm/dss/display.c b/drivers/gpu/drm/omapdrm/dss/display.c
index 9f3dd09b0a6c..8dcdd7cf9937 100644
--- a/drivers/gpu/drm/omapdrm/dss/display.c
+++ b/drivers/gpu/drm/omapdrm/dss/display.c
@@ -28,7 +28,7 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 
-#include <video/omapdss.h>
+#include "omapdss.h"
 #include "dss.h"
 #include "dss_features.h"
 
diff --git a/drivers/gpu/drm/omapdrm/dss/dpi.c b/drivers/gpu/drm/omapdrm/dss/dpi.c
index 97ea60257884..b268295b76cf 100644
--- a/drivers/gpu/drm/omapdrm/dss/dpi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dpi.c
@@ -34,17 +34,15 @@
 #include <linux/clk.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 #include "dss_features.h"
 
-#define HSDIV_DISPC	0
-
 struct dpi_data {
 	struct platform_device *pdev;
 
 	struct regulator *vdds_dsi_reg;
+	enum dss_clk_source clk_src;
 	struct dss_pll *pll;
 
 	struct mutex lock;
@@ -69,7 +67,7 @@ static struct dpi_data *dpi_get_data_from_pdev(struct platform_device *pdev)
 	return dev_get_drvdata(&pdev->dev);
 }
 
-static struct dss_pll *dpi_get_pll(enum omap_channel channel)
+static enum dss_clk_source dpi_get_clk_src(enum omap_channel channel)
 {
 	/*
 	 * XXX we can't currently use DSI PLL for DPI with OMAP3, as the DSI PLL
@@ -83,64 +81,51 @@ static struct dss_pll *dpi_get_pll(enum omap_channel channel)
 	case OMAPDSS_VER_OMAP3630:
 	case OMAPDSS_VER_AM35xx:
 	case OMAPDSS_VER_AM43xx:
-		return NULL;
+		return DSS_CLK_SRC_FCK;
 
 	case OMAPDSS_VER_OMAP4430_ES1:
 	case OMAPDSS_VER_OMAP4430_ES2:
 	case OMAPDSS_VER_OMAP4:
 		switch (channel) {
 		case OMAP_DSS_CHANNEL_LCD:
-			return dss_pll_find("dsi0");
+			return DSS_CLK_SRC_PLL1_1;
 		case OMAP_DSS_CHANNEL_LCD2:
-			return dss_pll_find("dsi1");
+			return DSS_CLK_SRC_PLL2_1;
 		default:
-			return NULL;
+			return DSS_CLK_SRC_FCK;
 		}
 
 	case OMAPDSS_VER_OMAP5:
 		switch (channel) {
 		case OMAP_DSS_CHANNEL_LCD:
-			return dss_pll_find("dsi0");
+			return DSS_CLK_SRC_PLL1_1;
 		case OMAP_DSS_CHANNEL_LCD3:
-			return dss_pll_find("dsi1");
+			return DSS_CLK_SRC_PLL2_1;
+		case OMAP_DSS_CHANNEL_LCD2:
 		default:
-			return NULL;
+			return DSS_CLK_SRC_FCK;
 		}
 
 	case OMAPDSS_VER_DRA7xx:
 		switch (channel) {
 		case OMAP_DSS_CHANNEL_LCD:
+			return DSS_CLK_SRC_PLL1_1;
 		case OMAP_DSS_CHANNEL_LCD2:
-			return dss_pll_find("video0");
+			return DSS_CLK_SRC_PLL1_3;
 		case OMAP_DSS_CHANNEL_LCD3:
-			return dss_pll_find("video1");
+			return DSS_CLK_SRC_PLL2_1;
 		default:
-			return NULL;
+			return DSS_CLK_SRC_FCK;
 		}
 
 	default:
-		return NULL;
-	}
-}
-
-static enum omap_dss_clk_source dpi_get_alt_clk_src(enum omap_channel channel)
-{
-	switch (channel) {
-	case OMAP_DSS_CHANNEL_LCD:
-		return OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC;
-	case OMAP_DSS_CHANNEL_LCD2:
-		return OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC;
-	case OMAP_DSS_CHANNEL_LCD3:
-		return OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC;
-	default:
-		/* this shouldn't happen */
-		WARN_ON(1);
-		return OMAP_DSS_CLK_SRC_FCK;
+		return DSS_CLK_SRC_FCK;
 	}
 }
 
 struct dpi_clk_calc_ctx {
 	struct dss_pll *pll;
+	unsigned clkout_idx;
 
 	/* inputs */
 
@@ -148,7 +133,7 @@ struct dpi_clk_calc_ctx {
 
 	/* outputs */
 
-	struct dss_pll_clock_info dsi_cinfo;
+	struct dss_pll_clock_info pll_cinfo;
 	unsigned long fck;
 	struct dispc_clock_info dispc_cinfo;
 };
@@ -193,8 +178,8 @@ static bool dpi_calc_hsdiv_cb(int m_dispc, unsigned long dispc,
 	if (m_dispc > 1 && m_dispc % 2 != 0 && ctx->pck_min >= 100000000)
 		return false;
 
-	ctx->dsi_cinfo.mX[HSDIV_DISPC] = m_dispc;
-	ctx->dsi_cinfo.clkout[HSDIV_DISPC] = dispc;
+	ctx->pll_cinfo.mX[ctx->clkout_idx] = m_dispc;
+	ctx->pll_cinfo.clkout[ctx->clkout_idx] = dispc;
 
 	return dispc_div_calc(dispc, ctx->pck_min, ctx->pck_max,
 			dpi_calc_dispc_cb, ctx);
@@ -207,12 +192,12 @@ static bool dpi_calc_pll_cb(int n, int m, unsigned long fint,
 {
 	struct dpi_clk_calc_ctx *ctx = data;
 
-	ctx->dsi_cinfo.n = n;
-	ctx->dsi_cinfo.m = m;
-	ctx->dsi_cinfo.fint = fint;
-	ctx->dsi_cinfo.clkdco = clkdco;
+	ctx->pll_cinfo.n = n;
+	ctx->pll_cinfo.m = m;
+	ctx->pll_cinfo.fint = fint;
+	ctx->pll_cinfo.clkdco = clkdco;
 
-	return dss_pll_hsdiv_calc(ctx->pll, clkdco,
+	return dss_pll_hsdiv_calc_a(ctx->pll, clkdco,
 		ctx->pck_min, dss_feat_get_param_max(FEAT_PARAM_DSS_FCK),
 		dpi_calc_hsdiv_cb, ctx);
 }
@@ -227,25 +212,39 @@ static bool dpi_calc_dss_cb(unsigned long fck, void *data)
 			dpi_calc_dispc_cb, ctx);
 }
 
-static bool dpi_dsi_clk_calc(struct dpi_data *dpi, unsigned long pck,
+static bool dpi_pll_clk_calc(struct dpi_data *dpi, unsigned long pck,
 		struct dpi_clk_calc_ctx *ctx)
 {
 	unsigned long clkin;
-	unsigned long pll_min, pll_max;
 
 	memset(ctx, 0, sizeof(*ctx));
 	ctx->pll = dpi->pll;
-	ctx->pck_min = pck - 1000;
-	ctx->pck_max = pck + 1000;
+	ctx->clkout_idx = dss_pll_get_clkout_idx_for_src(dpi->clk_src);
 
-	pll_min = 0;
-	pll_max = 0;
+	clkin = clk_get_rate(dpi->pll->clkin);
 
-	clkin = clk_get_rate(ctx->pll->clkin);
+	if (dpi->pll->hw->type == DSS_PLL_TYPE_A) {
+		unsigned long pll_min, pll_max;
 
-	return dss_pll_calc(ctx->pll, clkin,
-			pll_min, pll_max,
-			dpi_calc_pll_cb, ctx);
+		ctx->pck_min = pck - 1000;
+		ctx->pck_max = pck + 1000;
+
+		pll_min = 0;
+		pll_max = 0;
+
+		return dss_pll_calc_a(ctx->pll, clkin,
+				pll_min, pll_max,
+				dpi_calc_pll_cb, ctx);
+	} else { /* DSS_PLL_TYPE_B */
+		dss_pll_calc_b(dpi->pll, clkin, pck, &ctx->pll_cinfo);
+
+		ctx->dispc_cinfo.lck_div = 1;
+		ctx->dispc_cinfo.pck_div = 1;
+		ctx->dispc_cinfo.lck = ctx->pll_cinfo.clkout[0];
+		ctx->dispc_cinfo.pck = ctx->dispc_cinfo.lck;
+
+		return true;
+	}
 }
 
 static bool dpi_dss_clk_calc(unsigned long pck, struct dpi_clk_calc_ctx *ctx)
@@ -279,7 +278,7 @@ static bool dpi_dss_clk_calc(unsigned long pck, struct dpi_clk_calc_ctx *ctx)
 
 
 
-static int dpi_set_dsi_clk(struct dpi_data *dpi, enum omap_channel channel,
+static int dpi_set_pll_clk(struct dpi_data *dpi, enum omap_channel channel,
 		unsigned long pck_req, unsigned long *fck, int *lck_div,
 		int *pck_div)
 {
@@ -287,20 +286,19 @@ static int dpi_set_dsi_clk(struct dpi_data *dpi, enum omap_channel channel,
 	int r;
 	bool ok;
 
-	ok = dpi_dsi_clk_calc(dpi, pck_req, &ctx);
+	ok = dpi_pll_clk_calc(dpi, pck_req, &ctx);
 	if (!ok)
 		return -EINVAL;
 
-	r = dss_pll_set_config(dpi->pll, &ctx.dsi_cinfo);
+	r = dss_pll_set_config(dpi->pll, &ctx.pll_cinfo);
 	if (r)
 		return r;
 
-	dss_select_lcd_clk_source(channel,
-			dpi_get_alt_clk_src(channel));
+	dss_select_lcd_clk_source(channel, dpi->clk_src);
 
 	dpi->mgr_config.clock_info = ctx.dispc_cinfo;
 
-	*fck = ctx.dsi_cinfo.clkout[HSDIV_DISPC];
+	*fck = ctx.pll_cinfo.clkout[ctx.clkout_idx];
 	*lck_div = ctx.dispc_cinfo.lck_div;
 	*pck_div = ctx.dispc_cinfo.pck_div;
 
@@ -342,7 +340,7 @@ static int dpi_set_mode(struct dpi_data *dpi)
 	int r = 0;
 
 	if (dpi->pll)
-		r = dpi_set_dsi_clk(dpi, channel, t->pixelclock, &fck,
+		r = dpi_set_pll_clk(dpi, channel, t->pixelclock, &fck,
 				&lck_div, &pck_div);
 	else
 		r = dpi_set_dispc_clk(dpi, t->pixelclock, &fck,
@@ -419,7 +417,7 @@ static int dpi_display_enable(struct omap_dss_device *dssdev)
 	if (dpi->pll) {
 		r = dss_pll_enable(dpi->pll);
 		if (r)
-			goto err_dsi_pll_init;
+			goto err_pll_init;
 	}
 
 	r = dpi_set_mode(dpi);
@@ -442,7 +440,7 @@ err_mgr_enable:
 err_set_mode:
 	if (dpi->pll)
 		dss_pll_disable(dpi->pll);
-err_dsi_pll_init:
+err_pll_init:
 err_src_sel:
 	dispc_runtime_put();
 err_get_dispc:
@@ -465,7 +463,7 @@ static void dpi_display_disable(struct omap_dss_device *dssdev)
 	dss_mgr_disable(channel);
 
 	if (dpi->pll) {
-		dss_select_lcd_clk_source(channel, OMAP_DSS_CLK_SRC_FCK);
+		dss_select_lcd_clk_source(channel, DSS_CLK_SRC_FCK);
 		dss_pll_disable(dpi->pll);
 	}
 
@@ -524,11 +522,11 @@ static int dpi_check_timings(struct omap_dss_device *dssdev,
 		return -EINVAL;
 
 	if (dpi->pll) {
-		ok = dpi_dsi_clk_calc(dpi, timings->pixelclock, &ctx);
+		ok = dpi_pll_clk_calc(dpi, timings->pixelclock, &ctx);
 		if (!ok)
 			return -EINVAL;
 
-		fck = ctx.dsi_cinfo.clkout[HSDIV_DISPC];
+		fck = ctx.pll_cinfo.clkout[ctx.clkout_idx];
 	} else {
 		ok = dpi_dss_clk_calc(timings->pixelclock, &ctx);
 		if (!ok)
@@ -558,7 +556,7 @@ static void dpi_set_data_lines(struct omap_dss_device *dssdev, int data_lines)
 	mutex_unlock(&dpi->lock);
 }
 
-static int dpi_verify_dsi_pll(struct dss_pll *pll)
+static int dpi_verify_pll(struct dss_pll *pll)
 {
 	int r;
 
@@ -602,16 +600,14 @@ static void dpi_init_pll(struct dpi_data *dpi)
 	if (dpi->pll)
 		return;
 
-	pll = dpi_get_pll(dpi->output.dispc_channel);
+	dpi->clk_src = dpi_get_clk_src(dpi->output.dispc_channel);
+
+	pll = dss_pll_find_by_src(dpi->clk_src);
 	if (!pll)
 		return;
 
-	/* On DRA7 we need to set a mux to use the PLL */
-	if (omapdss_get_version() == OMAPDSS_VER_DRA7xx)
-		dss_ctrl_pll_set_control_mux(pll->id, dpi->output.dispc_channel);
-
-	if (dpi_verify_dsi_pll(pll)) {
-		DSSWARN("DSI PLL not operational\n");
+	if (dpi_verify_pll(pll)) {
+		DSSWARN("PLL not operational\n");
 		return;
 	}
 
diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c
index 56c43f355ce3..e1be5e795cd8 100644
--- a/drivers/gpu/drm/omapdrm/dss/dsi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dsi.c
@@ -42,9 +42,9 @@
 #include <linux/of_platform.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
 #include <video/mipi_display.h>
 
+#include "omapdss.h"
 #include "dss.h"
 #include "dss_features.h"
 
@@ -1261,7 +1261,7 @@ static unsigned long dsi_fclk_rate(struct platform_device *dsidev)
 	unsigned long r;
 	struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
 
-	if (dss_get_dsi_clk_source(dsi->module_id) == OMAP_DSS_CLK_SRC_FCK) {
+	if (dss_get_dsi_clk_source(dsi->module_id) == DSS_CLK_SRC_FCK) {
 		/* DSI FCLK source is DSS_CLK_FCK */
 		r = clk_get_rate(dsi->dss_clk);
 	} else {
@@ -1474,7 +1474,7 @@ static void dsi_dump_dsidev_clocks(struct platform_device *dsidev,
 {
 	struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
 	struct dss_pll_clock_info *cinfo = &dsi->pll.cinfo;
-	enum omap_dss_clk_source dispc_clk_src, dsi_clk_src;
+	enum dss_clk_source dispc_clk_src, dsi_clk_src;
 	int dsi_module = dsi->module_id;
 	struct dss_pll *pll = &dsi->pll;
 
@@ -1494,28 +1494,27 @@ static void dsi_dump_dsidev_clocks(struct platform_device *dsidev,
 			cinfo->clkdco, cinfo->m);
 
 	seq_printf(s,	"DSI_PLL_HSDIV_DISPC (%s)\t%-16lum_dispc %u\t(%s)\n",
-			dss_feat_get_clk_source_name(dsi_module == 0 ?
-				OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC :
-				OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC),
+			dss_get_clk_source_name(dsi_module == 0 ?
+				DSS_CLK_SRC_PLL1_1 :
+				DSS_CLK_SRC_PLL2_1),
 			cinfo->clkout[HSDIV_DISPC],
 			cinfo->mX[HSDIV_DISPC],
-			dispc_clk_src == OMAP_DSS_CLK_SRC_FCK ?
+			dispc_clk_src == DSS_CLK_SRC_FCK ?
 			"off" : "on");
 
 	seq_printf(s,	"DSI_PLL_HSDIV_DSI (%s)\t%-16lum_dsi %u\t(%s)\n",
-			dss_feat_get_clk_source_name(dsi_module == 0 ?
-				OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI :
-				OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI),
+			dss_get_clk_source_name(dsi_module == 0 ?
+				DSS_CLK_SRC_PLL1_2 :
+				DSS_CLK_SRC_PLL2_2),
 			cinfo->clkout[HSDIV_DSI],
 			cinfo->mX[HSDIV_DSI],
-			dsi_clk_src == OMAP_DSS_CLK_SRC_FCK ?
+			dsi_clk_src == DSS_CLK_SRC_FCK ?
 			"off" : "on");
 
 	seq_printf(s,	"- DSI%d -\n", dsi_module + 1);
 
-	seq_printf(s,	"dsi fclk source = %s (%s)\n",
-			dss_get_generic_clk_source_name(dsi_clk_src),
-			dss_feat_get_clk_source_name(dsi_clk_src));
+	seq_printf(s,	"dsi fclk source = %s\n",
+			dss_get_clk_source_name(dsi_clk_src));
 
 	seq_printf(s,	"DSI_FCLK\t%lu\n", dsi_fclk_rate(dsidev));
 
@@ -4101,8 +4100,8 @@ static int dsi_display_init_dispc(struct platform_device *dsidev,
 	int r;
 
 	dss_select_lcd_clk_source(channel, dsi->module_id == 0 ?
-			OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC :
-			OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC);
+			DSS_CLK_SRC_PLL1_1 :
+			DSS_CLK_SRC_PLL2_1);
 
 	if (dsi->mode == OMAP_DSS_DSI_CMD_MODE) {
 		r = dss_mgr_register_framedone_handler(channel,
@@ -4149,7 +4148,7 @@ err1:
 		dss_mgr_unregister_framedone_handler(channel,
 				dsi_framedone_irq_callback, dsidev);
 err:
-	dss_select_lcd_clk_source(channel, OMAP_DSS_CLK_SRC_FCK);
+	dss_select_lcd_clk_source(channel, DSS_CLK_SRC_FCK);
 	return r;
 }
 
@@ -4162,7 +4161,7 @@ static void dsi_display_uninit_dispc(struct platform_device *dsidev,
 		dss_mgr_unregister_framedone_handler(channel,
 				dsi_framedone_irq_callback, dsidev);
 
-	dss_select_lcd_clk_source(channel, OMAP_DSS_CLK_SRC_FCK);
+	dss_select_lcd_clk_source(channel, DSS_CLK_SRC_FCK);
 }
 
 static int dsi_configure_dsi_clocks(struct platform_device *dsidev)
@@ -4196,8 +4195,8 @@ static int dsi_display_init_dsi(struct platform_device *dsidev)
 		goto err1;
 
 	dss_select_dsi_clk_source(dsi->module_id, dsi->module_id == 0 ?
-			OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI :
-			OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI);
+			DSS_CLK_SRC_PLL1_2 :
+			DSS_CLK_SRC_PLL2_2);
 
 	DSSDBG("PLL OK\n");
 
@@ -4229,7 +4228,7 @@ static int dsi_display_init_dsi(struct platform_device *dsidev)
 err3:
 	dsi_cio_uninit(dsidev);
 err2:
-	dss_select_dsi_clk_source(dsi->module_id, OMAP_DSS_CLK_SRC_FCK);
+	dss_select_dsi_clk_source(dsi->module_id, DSS_CLK_SRC_FCK);
 err1:
 	dss_pll_disable(&dsi->pll);
 err0:
@@ -4251,7 +4250,7 @@ static void dsi_display_uninit_dsi(struct platform_device *dsidev,
 	dsi_vc_enable(dsidev, 2, 0);
 	dsi_vc_enable(dsidev, 3, 0);
 
-	dss_select_dsi_clk_source(dsi->module_id, OMAP_DSS_CLK_SRC_FCK);
+	dss_select_dsi_clk_source(dsi->module_id, DSS_CLK_SRC_FCK);
 	dsi_cio_uninit(dsidev);
 	dsi_pll_uninit(dsidev, disconnect_lanes);
 }
@@ -4452,7 +4451,7 @@ static bool dsi_cm_calc_pll_cb(int n, int m, unsigned long fint,
 	ctx->dsi_cinfo.fint = fint;
 	ctx->dsi_cinfo.clkdco = clkdco;
 
-	return dss_pll_hsdiv_calc(ctx->pll, clkdco, ctx->req_pck_min,
+	return dss_pll_hsdiv_calc_a(ctx->pll, clkdco, ctx->req_pck_min,
 			dss_feat_get_param_max(FEAT_PARAM_DSS_FCK),
 			dsi_cm_calc_hsdiv_cb, ctx);
 }
@@ -4491,7 +4490,7 @@ static bool dsi_cm_calc(struct dsi_data *dsi,
 	pll_min = max(cfg->hs_clk_min * 4, txbyteclk * 4 * 4);
 	pll_max = cfg->hs_clk_max * 4;
 
-	return dss_pll_calc(ctx->pll, clkin,
+	return dss_pll_calc_a(ctx->pll, clkin,
 			pll_min, pll_max,
 			dsi_cm_calc_pll_cb, ctx);
 }
@@ -4750,7 +4749,7 @@ static bool dsi_vm_calc_pll_cb(int n, int m, unsigned long fint,
 	ctx->dsi_cinfo.fint = fint;
 	ctx->dsi_cinfo.clkdco = clkdco;
 
-	return dss_pll_hsdiv_calc(ctx->pll, clkdco, ctx->req_pck_min,
+	return dss_pll_hsdiv_calc_a(ctx->pll, clkdco, ctx->req_pck_min,
 			dss_feat_get_param_max(FEAT_PARAM_DSS_FCK),
 			dsi_vm_calc_hsdiv_cb, ctx);
 }
@@ -4792,7 +4791,7 @@ static bool dsi_vm_calc(struct dsi_data *dsi,
 		pll_max = byteclk_max * 4 * 4;
 	}
 
-	return dss_pll_calc(ctx->pll, clkin,
+	return dss_pll_calc_a(ctx->pll, clkin,
 			pll_min, pll_max,
 			dsi_vm_calc_pll_cb, ctx);
 }
@@ -5138,6 +5137,8 @@ static const struct dss_pll_ops dsi_pll_ops = {
 };
 
 static const struct dss_pll_hw dss_omap3_dsi_pll_hw = {
+	.type = DSS_PLL_TYPE_A,
+
 	.n_max = (1 << 7) - 1,
 	.m_max = (1 << 11) - 1,
 	.mX_max = (1 << 4) - 1,
@@ -5163,6 +5164,8 @@ static const struct dss_pll_hw dss_omap3_dsi_pll_hw = {
 };
 
 static const struct dss_pll_hw dss_omap4_dsi_pll_hw = {
+	.type = DSS_PLL_TYPE_A,
+
 	.n_max = (1 << 8) - 1,
 	.m_max = (1 << 12) - 1,
 	.mX_max = (1 << 5) - 1,
@@ -5188,6 +5191,8 @@ static const struct dss_pll_hw dss_omap4_dsi_pll_hw = {
 };
 
 static const struct dss_pll_hw dss_omap5_dsi_pll_hw = {
+	.type = DSS_PLL_TYPE_A,
+
 	.n_max = (1 << 8) - 1,
 	.m_max = (1 << 12) - 1,
 	.mX_max = (1 << 5) - 1,
diff --git a/drivers/gpu/drm/omapdrm/dss/dss-of.c b/drivers/gpu/drm/omapdrm/dss/dss-of.c
index bf407b6ba15c..e256d879b25c 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss-of.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss-of.c
@@ -18,8 +18,7 @@
 #include <linux/of.h>
 #include <linux/seq_file.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 
 struct device_node *
@@ -126,15 +125,16 @@ u32 dss_of_port_get_port_number(struct device_node *port)
 
 static struct device_node *omapdss_of_get_remote_port(const struct device_node *node)
 {
-	struct device_node *np;
+	struct device_node *np, *np_parent;
 
 	np = of_parse_phandle(node, "remote-endpoint", 0);
 	if (!np)
 		return NULL;
 
-	np = of_get_next_parent(np);
+	np_parent = of_get_next_parent(np);
+	of_node_put(np);
 
-	return np;
+	return np_parent;
 }
 
 struct device_node *
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index 3303cfad4838..14887d5b02e5 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -42,8 +42,7 @@
 #include <linux/suspend.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 #include "dss_features.h"
 
@@ -76,6 +75,8 @@ struct dss_features {
 	const enum omap_display_type *ports;
 	int num_ports;
 	int (*dpi_select_source)(int port, enum omap_channel channel);
+	int (*select_lcd_source)(enum omap_channel channel,
+		enum dss_clk_source clk_src);
 };
 
 static struct {
@@ -92,9 +93,9 @@ static struct {
 	unsigned long	cache_prate;
 	struct dispc_clock_info cache_dispc_cinfo;
 
-	enum omap_dss_clk_source dsi_clk_source[MAX_NUM_DSI];
-	enum omap_dss_clk_source dispc_clk_source;
-	enum omap_dss_clk_source lcd_clk_source[MAX_DSS_LCD_MANAGERS];
+	enum dss_clk_source dsi_clk_source[MAX_NUM_DSI];
+	enum dss_clk_source dispc_clk_source;
+	enum dss_clk_source lcd_clk_source[MAX_DSS_LCD_MANAGERS];
 
 	bool		ctx_valid;
 	u32		ctx[DSS_SZ_REGS / sizeof(u32)];
@@ -106,11 +107,14 @@ static struct {
 } dss;
 
 static const char * const dss_generic_clk_source_names[] = {
-	[OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]	= "DSI_PLL_HSDIV_DISPC",
-	[OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]	= "DSI_PLL_HSDIV_DSI",
-	[OMAP_DSS_CLK_SRC_FCK]			= "DSS_FCK",
-	[OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC]	= "DSI_PLL2_HSDIV_DISPC",
-	[OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI]	= "DSI_PLL2_HSDIV_DSI",
+	[DSS_CLK_SRC_FCK]	= "FCK",
+	[DSS_CLK_SRC_PLL1_1]	= "PLL1:1",
+	[DSS_CLK_SRC_PLL1_2]	= "PLL1:2",
+	[DSS_CLK_SRC_PLL1_3]	= "PLL1:3",
+	[DSS_CLK_SRC_PLL2_1]	= "PLL2:1",
+	[DSS_CLK_SRC_PLL2_2]	= "PLL2:2",
+	[DSS_CLK_SRC_PLL2_3]	= "PLL2:3",
+	[DSS_CLK_SRC_HDMI_PLL]	= "HDMI PLL",
 };
 
 static bool dss_initialized;
@@ -203,68 +207,70 @@ void dss_ctrl_pll_enable(enum dss_pll_id pll_id, bool enable)
 		1 << shift, val << shift);
 }
 
-void dss_ctrl_pll_set_control_mux(enum dss_pll_id pll_id,
+static int dss_ctrl_pll_set_control_mux(enum dss_clk_source clk_src,
 	enum omap_channel channel)
 {
 	unsigned shift, val;
 
 	if (!dss.syscon_pll_ctrl)
-		return;
+		return -EINVAL;
 
 	switch (channel) {
 	case OMAP_DSS_CHANNEL_LCD:
 		shift = 3;
 
-		switch (pll_id) {
-		case DSS_PLL_VIDEO1:
+		switch (clk_src) {
+		case DSS_CLK_SRC_PLL1_1:
 			val = 0; break;
-		case DSS_PLL_HDMI:
+		case DSS_CLK_SRC_HDMI_PLL:
 			val = 1; break;
 		default:
 			DSSERR("error in PLL mux config for LCD\n");
-			return;
+			return -EINVAL;
 		}
 
 		break;
 	case OMAP_DSS_CHANNEL_LCD2:
 		shift = 5;
 
-		switch (pll_id) {
-		case DSS_PLL_VIDEO1:
+		switch (clk_src) {
+		case DSS_CLK_SRC_PLL1_3:
 			val = 0; break;
-		case DSS_PLL_VIDEO2:
+		case DSS_CLK_SRC_PLL2_3:
 			val = 1; break;
-		case DSS_PLL_HDMI:
+		case DSS_CLK_SRC_HDMI_PLL:
 			val = 2; break;
 		default:
 			DSSERR("error in PLL mux config for LCD2\n");
-			return;
+			return -EINVAL;
 		}
 
 		break;
 	case OMAP_DSS_CHANNEL_LCD3:
 		shift = 7;
 
-		switch (pll_id) {
-		case DSS_PLL_VIDEO1:
-			val = 1; break;
-		case DSS_PLL_VIDEO2:
+		switch (clk_src) {
+		case DSS_CLK_SRC_PLL2_1:
 			val = 0; break;
-		case DSS_PLL_HDMI:
+		case DSS_CLK_SRC_PLL1_3:
+			val = 1; break;
+		case DSS_CLK_SRC_HDMI_PLL:
 			val = 2; break;
 		default:
 			DSSERR("error in PLL mux config for LCD3\n");
-			return;
+			return -EINVAL;
 		}
 
 		break;
 	default:
 		DSSERR("error in PLL mux config\n");
-		return;
+		return -EINVAL;
 	}
 
 	regmap_update_bits(dss.syscon_pll_ctrl, dss.syscon_pll_ctrl_offset,
 		0x3 << shift, val << shift);
+
+	return 0;
 }
 
 void dss_sdi_init(int datapairs)
@@ -354,14 +360,14 @@ void dss_sdi_disable(void)
 	REG_FLD_MOD(DSS_PLL_CONTROL, 0, 18, 18); /* SDI_PLL_SYSRESET */
 }
 
-const char *dss_get_generic_clk_source_name(enum omap_dss_clk_source clk_src)
+const char *dss_get_clk_source_name(enum dss_clk_source clk_src)
 {
 	return dss_generic_clk_source_names[clk_src];
 }
 
 void dss_dump_clocks(struct seq_file *s)
 {
-	const char *fclk_name, *fclk_real_name;
+	const char *fclk_name;
 	unsigned long fclk_rate;
 
 	if (dss_runtime_get())
@@ -369,12 +375,11 @@ void dss_dump_clocks(struct seq_file *s)
 
 	seq_printf(s, "- DSS -\n");
 
-	fclk_name = dss_get_generic_clk_source_name(OMAP_DSS_CLK_SRC_FCK);
-	fclk_real_name = dss_feat_get_clk_source_name(OMAP_DSS_CLK_SRC_FCK);
+	fclk_name = dss_get_clk_source_name(DSS_CLK_SRC_FCK);
 	fclk_rate = clk_get_rate(dss.dss_clk);
 
-	seq_printf(s, "%s (%s) = %lu\n",
-			fclk_name, fclk_real_name,
+	seq_printf(s, "%s = %lu\n",
+			fclk_name,
 			fclk_rate);
 
 	dss_runtime_put();
@@ -403,19 +408,42 @@ static void dss_dump_regs(struct seq_file *s)
 #undef DUMPREG
 }
 
-static void dss_select_dispc_clk_source(enum omap_dss_clk_source clk_src)
+static int dss_get_channel_index(enum omap_channel channel)
+{
+	switch (channel) {
+	case OMAP_DSS_CHANNEL_LCD:
+		return 0;
+	case OMAP_DSS_CHANNEL_LCD2:
+		return 1;
+	case OMAP_DSS_CHANNEL_LCD3:
+		return 2;
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
+static void dss_select_dispc_clk_source(enum dss_clk_source clk_src)
 {
 	int b;
 	u8 start, end;
 
+	/*
+	 * We always use PRCM clock as the DISPC func clock, except on DSS3,
+	 * where we don't have separate DISPC and LCD clock sources.
+	 */
+	if (WARN_ON(dss_has_feature(FEAT_LCD_CLK_SRC) &&
+		clk_src != DSS_CLK_SRC_FCK))
+		return;
+
 	switch (clk_src) {
-	case OMAP_DSS_CLK_SRC_FCK:
+	case DSS_CLK_SRC_FCK:
 		b = 0;
 		break;
-	case OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
+	case DSS_CLK_SRC_PLL1_1:
 		b = 1;
 		break;
-	case OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC:
+	case DSS_CLK_SRC_PLL2_1:
 		b = 2;
 		break;
 	default:
@@ -431,19 +459,19 @@ static void dss_select_dispc_clk_source(enum omap_dss_clk_source clk_src)
 }
 
 void dss_select_dsi_clk_source(int dsi_module,
-		enum omap_dss_clk_source clk_src)
+		enum dss_clk_source clk_src)
 {
 	int b, pos;
 
 	switch (clk_src) {
-	case OMAP_DSS_CLK_SRC_FCK:
+	case DSS_CLK_SRC_FCK:
 		b = 0;
 		break;
-	case OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI:
+	case DSS_CLK_SRC_PLL1_2:
 		BUG_ON(dsi_module != 0);
 		b = 1;
 		break;
-	case OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI:
+	case DSS_CLK_SRC_PLL2_2:
 		BUG_ON(dsi_module != 1);
 		b = 1;
 		break;
@@ -458,59 +486,125 @@ void dss_select_dsi_clk_source(int dsi_module,
 	dss.dsi_clk_source[dsi_module] = clk_src;
 }
 
+static int dss_lcd_clk_mux_dra7(enum omap_channel channel,
+	enum dss_clk_source clk_src)
+{
+	const u8 ctrl_bits[] = {
+		[OMAP_DSS_CHANNEL_LCD] = 0,
+		[OMAP_DSS_CHANNEL_LCD2] = 12,
+		[OMAP_DSS_CHANNEL_LCD3] = 19,
+	};
+
+	u8 ctrl_bit = ctrl_bits[channel];
+	int r;
+
+	if (clk_src == DSS_CLK_SRC_FCK) {
+		/* LCDx_CLK_SWITCH */
+		REG_FLD_MOD(DSS_CONTROL, 0, ctrl_bit, ctrl_bit);
+		return -EINVAL;
+	}
+
+	r = dss_ctrl_pll_set_control_mux(clk_src, channel);
+	if (r)
+		return r;
+
+	REG_FLD_MOD(DSS_CONTROL, 1, ctrl_bit, ctrl_bit);
+
+	return 0;
+}
+
+static int dss_lcd_clk_mux_omap5(enum omap_channel channel,
+	enum dss_clk_source clk_src)
+{
+	const u8 ctrl_bits[] = {
+		[OMAP_DSS_CHANNEL_LCD] = 0,
+		[OMAP_DSS_CHANNEL_LCD2] = 12,
+		[OMAP_DSS_CHANNEL_LCD3] = 19,
+	};
+	const enum dss_clk_source allowed_plls[] = {
+		[OMAP_DSS_CHANNEL_LCD] = DSS_CLK_SRC_PLL1_1,
+		[OMAP_DSS_CHANNEL_LCD2] = DSS_CLK_SRC_FCK,
+		[OMAP_DSS_CHANNEL_LCD3] = DSS_CLK_SRC_PLL2_1,
+	};
+
+	u8 ctrl_bit = ctrl_bits[channel];
+
+	if (clk_src == DSS_CLK_SRC_FCK) {
+		/* LCDx_CLK_SWITCH */
+		REG_FLD_MOD(DSS_CONTROL, 0, ctrl_bit, ctrl_bit);
+		return -EINVAL;
+	}
+
+	if (WARN_ON(allowed_plls[channel] != clk_src))
+		return -EINVAL;
+
+	REG_FLD_MOD(DSS_CONTROL, 1, ctrl_bit, ctrl_bit);
+
+	return 0;
+}
+
+static int dss_lcd_clk_mux_omap4(enum omap_channel channel,
+	enum dss_clk_source clk_src)
+{
+	const u8 ctrl_bits[] = {
+		[OMAP_DSS_CHANNEL_LCD] = 0,
+		[OMAP_DSS_CHANNEL_LCD2] = 12,
+	};
+	const enum dss_clk_source allowed_plls[] = {
+		[OMAP_DSS_CHANNEL_LCD] = DSS_CLK_SRC_PLL1_1,
+		[OMAP_DSS_CHANNEL_LCD2] = DSS_CLK_SRC_PLL2_1,
+	};
+
+	u8 ctrl_bit = ctrl_bits[channel];
+
+	if (clk_src == DSS_CLK_SRC_FCK) {
+		/* LCDx_CLK_SWITCH */
+		REG_FLD_MOD(DSS_CONTROL, 0, ctrl_bit, ctrl_bit);
+		return 0;
+	}
+
+	if (WARN_ON(allowed_plls[channel] != clk_src))
+		return -EINVAL;
+
+	REG_FLD_MOD(DSS_CONTROL, 1, ctrl_bit, ctrl_bit);
+
+	return 0;
+}
+
 void dss_select_lcd_clk_source(enum omap_channel channel,
-		enum omap_dss_clk_source clk_src)
+		enum dss_clk_source clk_src)
 {
-	int b, ix, pos;
+	int idx = dss_get_channel_index(channel);
+	int r;
 
 	if (!dss_has_feature(FEAT_LCD_CLK_SRC)) {
 		dss_select_dispc_clk_source(clk_src);
+		dss.lcd_clk_source[idx] = clk_src;
 		return;
 	}
 
-	switch (clk_src) {
-	case OMAP_DSS_CLK_SRC_FCK:
-		b = 0;
-		break;
-	case OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC:
-		BUG_ON(channel != OMAP_DSS_CHANNEL_LCD);
-		b = 1;
-		break;
-	case OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC:
-		BUG_ON(channel != OMAP_DSS_CHANNEL_LCD2 &&
-		       channel != OMAP_DSS_CHANNEL_LCD3);
-		b = 1;
-		break;
-	default:
-		BUG();
+	r = dss.feat->select_lcd_source(channel, clk_src);
+	if (r)
 		return;
-	}
-
-	pos = channel == OMAP_DSS_CHANNEL_LCD ? 0 :
-	     (channel == OMAP_DSS_CHANNEL_LCD2 ? 12 : 19);
-	REG_FLD_MOD(DSS_CONTROL, b, pos, pos);	/* LCDx_CLK_SWITCH */
 
-	ix = channel == OMAP_DSS_CHANNEL_LCD ? 0 :
-	    (channel == OMAP_DSS_CHANNEL_LCD2 ? 1 : 2);
-	dss.lcd_clk_source[ix] = clk_src;
+	dss.lcd_clk_source[idx] = clk_src;
 }
 
-enum omap_dss_clk_source dss_get_dispc_clk_source(void)
+enum dss_clk_source dss_get_dispc_clk_source(void)
 {
 	return dss.dispc_clk_source;
 }
 
-enum omap_dss_clk_source dss_get_dsi_clk_source(int dsi_module)
+enum dss_clk_source dss_get_dsi_clk_source(int dsi_module)
 {
 	return dss.dsi_clk_source[dsi_module];
 }
 
-enum omap_dss_clk_source dss_get_lcd_clk_source(enum omap_channel channel)
+enum dss_clk_source dss_get_lcd_clk_source(enum omap_channel channel)
 {
 	if (dss_has_feature(FEAT_LCD_CLK_SRC)) {
-		int ix = channel == OMAP_DSS_CHANNEL_LCD ? 0 :
-			(channel == OMAP_DSS_CHANNEL_LCD2 ? 1 : 2);
-		return dss.lcd_clk_source[ix];
+		int idx = dss_get_channel_index(channel);
+		return dss.lcd_clk_source[idx];
 	} else {
 		/* LCD_CLK source is the same as DISPC_FCLK source for
 		 * OMAP2 and OMAP3 */
@@ -859,6 +953,7 @@ static const struct dss_features omap44xx_dss_feats = {
 	.dpi_select_source	=	&dss_dpi_select_source_omap4,
 	.ports			=	omap2plus_ports,
 	.num_ports		=	ARRAY_SIZE(omap2plus_ports),
+	.select_lcd_source	=	&dss_lcd_clk_mux_omap4,
 };
 
 static const struct dss_features omap54xx_dss_feats = {
@@ -868,6 +963,7 @@ static const struct dss_features omap54xx_dss_feats = {
 	.dpi_select_source	=	&dss_dpi_select_source_omap5,
 	.ports			=	omap2plus_ports,
 	.num_ports		=	ARRAY_SIZE(omap2plus_ports),
+	.select_lcd_source	=	&dss_lcd_clk_mux_omap5,
 };
 
 static const struct dss_features am43xx_dss_feats = {
@@ -886,6 +982,7 @@ static const struct dss_features dra7xx_dss_feats = {
 	.dpi_select_source	=	&dss_dpi_select_source_dra7xx,
 	.ports			=	dra7xx_ports,
 	.num_ports		=	ARRAY_SIZE(dra7xx_ports),
+	.select_lcd_source	=	&dss_lcd_clk_mux_dra7,
 };
 
 static int dss_init_features(struct platform_device *pdev)
@@ -1143,18 +1240,18 @@ static int dss_bind(struct device *dev)
 	/* Select DPLL */
 	REG_FLD_MOD(DSS_CONTROL, 0, 0, 0);
 
-	dss_select_dispc_clk_source(OMAP_DSS_CLK_SRC_FCK);
+	dss_select_dispc_clk_source(DSS_CLK_SRC_FCK);
 
 #ifdef CONFIG_OMAP2_DSS_VENC
 	REG_FLD_MOD(DSS_CONTROL, 1, 4, 4);	/* venc dac demen */
 	REG_FLD_MOD(DSS_CONTROL, 1, 3, 3);	/* venc clock 4x enable */
 	REG_FLD_MOD(DSS_CONTROL, 0, 2, 2);	/* venc clock mode = normal */
 #endif
-	dss.dsi_clk_source[0] = OMAP_DSS_CLK_SRC_FCK;
-	dss.dsi_clk_source[1] = OMAP_DSS_CLK_SRC_FCK;
-	dss.dispc_clk_source = OMAP_DSS_CLK_SRC_FCK;
-	dss.lcd_clk_source[0] = OMAP_DSS_CLK_SRC_FCK;
-	dss.lcd_clk_source[1] = OMAP_DSS_CLK_SRC_FCK;
+	dss.dsi_clk_source[0] = DSS_CLK_SRC_FCK;
+	dss.dsi_clk_source[1] = DSS_CLK_SRC_FCK;
+	dss.dispc_clk_source = DSS_CLK_SRC_FCK;
+	dss.lcd_clk_source[0] = DSS_CLK_SRC_FCK;
+	dss.lcd_clk_source[1] = DSS_CLK_SRC_FCK;
 
 	rev = dss_read_reg(DSS_REVISION);
 	printk(KERN_INFO "OMAP DSS rev %d.%d\n",
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.h b/drivers/gpu/drm/omapdrm/dss/dss.h
index 38e6ab50142d..4fd06dc41cb3 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.h
+++ b/drivers/gpu/drm/omapdrm/dss/dss.h
@@ -102,6 +102,20 @@ enum dss_writeback_channel {
 	DSS_WB_LCD3_MGR =	7,
 };
 
+enum dss_clk_source {
+	DSS_CLK_SRC_FCK = 0,
+
+	DSS_CLK_SRC_PLL1_1,
+	DSS_CLK_SRC_PLL1_2,
+	DSS_CLK_SRC_PLL1_3,
+
+	DSS_CLK_SRC_PLL2_1,
+	DSS_CLK_SRC_PLL2_2,
+	DSS_CLK_SRC_PLL2_3,
+
+	DSS_CLK_SRC_HDMI_PLL,
+};
+
 enum dss_pll_id {
 	DSS_PLL_DSI1,
 	DSS_PLL_DSI2,
@@ -114,6 +128,11 @@ struct dss_pll;
 
 #define DSS_PLL_MAX_HSDIVS 4
 
+enum dss_pll_type {
+	DSS_PLL_TYPE_A,
+	DSS_PLL_TYPE_B,
+};
+
 /*
  * Type-A PLLs: clkout[]/mX[] refer to hsdiv outputs m4, m5, m6, m7.
  * Type-B PLLs: clkout[0] refers to m2.
@@ -140,6 +159,8 @@ struct dss_pll_ops {
 };
 
 struct dss_pll_hw {
+	enum dss_pll_type type;
+
 	unsigned n_max;
 	unsigned m_min;
 	unsigned m_max;
@@ -227,7 +248,7 @@ unsigned long dss_get_dispc_clk_rate(void);
 int dss_dpi_select_source(int port, enum omap_channel channel);
 void dss_select_hdmi_venc_clk_source(enum dss_hdmi_venc_clk_source_select);
 enum dss_hdmi_venc_clk_source_select dss_get_hdmi_venc_clk_source(void);
-const char *dss_get_generic_clk_source_name(enum omap_dss_clk_source clk_src);
+const char *dss_get_clk_source_name(enum dss_clk_source clk_src);
 void dss_dump_clocks(struct seq_file *s);
 
 /* DSS VIDEO PLL */
@@ -244,20 +265,18 @@ void dss_debug_dump_clocks(struct seq_file *s);
 #endif
 
 void dss_ctrl_pll_enable(enum dss_pll_id pll_id, bool enable);
-void dss_ctrl_pll_set_control_mux(enum dss_pll_id pll_id,
-	enum omap_channel channel);
 
 void dss_sdi_init(int datapairs);
 int dss_sdi_enable(void);
 void dss_sdi_disable(void);
 
 void dss_select_dsi_clk_source(int dsi_module,
-		enum omap_dss_clk_source clk_src);
+		enum dss_clk_source clk_src);
 void dss_select_lcd_clk_source(enum omap_channel channel,
-		enum omap_dss_clk_source clk_src);
-enum omap_dss_clk_source dss_get_dispc_clk_source(void);
-enum omap_dss_clk_source dss_get_dsi_clk_source(int dsi_module);
-enum omap_dss_clk_source dss_get_lcd_clk_source(enum omap_channel channel);
+		enum dss_clk_source clk_src);
+enum dss_clk_source dss_get_dispc_clk_source(void);
+enum dss_clk_source dss_get_dsi_clk_source(int dsi_module);
+enum dss_clk_source dss_get_lcd_clk_source(enum omap_channel channel);
 
 void dss_set_venc_output(enum omap_dss_venc_type type);
 void dss_set_dac_pwrdn_bgz(bool enable);
@@ -409,17 +428,23 @@ typedef bool (*dss_hsdiv_calc_func)(int m_dispc, unsigned long dispc,
 int dss_pll_register(struct dss_pll *pll);
 void dss_pll_unregister(struct dss_pll *pll);
 struct dss_pll *dss_pll_find(const char *name);
+struct dss_pll *dss_pll_find_by_src(enum dss_clk_source src);
+unsigned dss_pll_get_clkout_idx_for_src(enum dss_clk_source src);
 int dss_pll_enable(struct dss_pll *pll);
 void dss_pll_disable(struct dss_pll *pll);
 int dss_pll_set_config(struct dss_pll *pll,
 		const struct dss_pll_clock_info *cinfo);
 
-bool dss_pll_hsdiv_calc(const struct dss_pll *pll, unsigned long clkdco,
+bool dss_pll_hsdiv_calc_a(const struct dss_pll *pll, unsigned long clkdco,
 		unsigned long out_min, unsigned long out_max,
 		dss_hsdiv_calc_func func, void *data);
-bool dss_pll_calc(const struct dss_pll *pll, unsigned long clkin,
+bool dss_pll_calc_a(const struct dss_pll *pll, unsigned long clkin,
 		unsigned long pll_min, unsigned long pll_max,
 		dss_pll_calc_func func, void *data);
+
+bool dss_pll_calc_b(const struct dss_pll *pll, unsigned long clkin,
+	unsigned long target_clkout, struct dss_pll_clock_info *cinfo);
+
 int dss_pll_write_config_type_a(struct dss_pll *pll,
 		const struct dss_pll_clock_info *cinfo);
 int dss_pll_write_config_type_b(struct dss_pll *pll,
diff --git a/drivers/gpu/drm/omapdrm/dss/dss_features.c b/drivers/gpu/drm/omapdrm/dss/dss_features.c
index c886a2927f73..ee5b93ce2763 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss_features.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss_features.c
@@ -23,8 +23,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 #include "dss_features.h"
 
@@ -50,7 +49,6 @@ struct omap_dss_features {
 	const enum omap_dss_output_id *supported_outputs;
 	const enum omap_color_mode *supported_color_modes;
 	const enum omap_overlay_caps *overlay_caps;
-	const char * const *clksrc_names;
 	const struct dss_param_range *dss_params;
 
 	const enum omap_dss_rotation_type supported_rotation_types;
@@ -389,34 +387,6 @@ static const enum omap_overlay_caps omap4_dss_overlay_caps[] = {
 		OMAP_DSS_OVL_CAP_POS | OMAP_DSS_OVL_CAP_REPLICATION,
 };
 
-static const char * const omap2_dss_clk_source_names[] = {
-	[OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]	= "N/A",
-	[OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]	= "N/A",
-	[OMAP_DSS_CLK_SRC_FCK]			= "DSS_FCLK1",
-};
-
-static const char * const omap3_dss_clk_source_names[] = {
-	[OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]	= "DSI1_PLL_FCLK",
-	[OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]	= "DSI2_PLL_FCLK",
-	[OMAP_DSS_CLK_SRC_FCK]			= "DSS1_ALWON_FCLK",
-};
-
-static const char * const omap4_dss_clk_source_names[] = {
-	[OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]	= "PLL1_CLK1",
-	[OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]	= "PLL1_CLK2",
-	[OMAP_DSS_CLK_SRC_FCK]			= "DSS_FCLK",
-	[OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC]	= "PLL2_CLK1",
-	[OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI]	= "PLL2_CLK2",
-};
-
-static const char * const omap5_dss_clk_source_names[] = {
-	[OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC]	= "DPLL_DSI1_A_CLK1",
-	[OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI]	= "DPLL_DSI1_A_CLK2",
-	[OMAP_DSS_CLK_SRC_FCK]			= "DSS_CLK",
-	[OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC]	= "DPLL_DSI1_C_CLK1",
-	[OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI]	= "DPLL_DSI1_C_CLK2",
-};
-
 static const struct dss_param_range omap2_dss_param_range[] = {
 	[FEAT_PARAM_DSS_FCK]			= { 0, 133000000 },
 	[FEAT_PARAM_DSS_PCD]			= { 2, 255 },
@@ -631,7 +601,6 @@ static const struct omap_dss_features omap2_dss_features = {
 	.supported_outputs = omap2_dss_supported_outputs,
 	.supported_color_modes = omap2_dss_supported_color_modes,
 	.overlay_caps = omap2_dss_overlay_caps,
-	.clksrc_names = omap2_dss_clk_source_names,
 	.dss_params = omap2_dss_param_range,
 	.supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_VRFB,
 	.buffer_size_unit = 1,
@@ -652,7 +621,6 @@ static const struct omap_dss_features omap3430_dss_features = {
 	.supported_outputs = omap3430_dss_supported_outputs,
 	.supported_color_modes = omap3_dss_supported_color_modes,
 	.overlay_caps = omap3430_dss_overlay_caps,
-	.clksrc_names = omap3_dss_clk_source_names,
 	.dss_params = omap3_dss_param_range,
 	.supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_VRFB,
 	.buffer_size_unit = 1,
@@ -676,7 +644,6 @@ static const struct omap_dss_features am35xx_dss_features = {
 	.supported_outputs = omap3430_dss_supported_outputs,
 	.supported_color_modes = omap3_dss_supported_color_modes,
 	.overlay_caps = omap3430_dss_overlay_caps,
-	.clksrc_names = omap3_dss_clk_source_names,
 	.dss_params = omap3_dss_param_range,
 	.supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_VRFB,
 	.buffer_size_unit = 1,
@@ -696,7 +663,6 @@ static const struct omap_dss_features am43xx_dss_features = {
 	.supported_outputs = am43xx_dss_supported_outputs,
 	.supported_color_modes = omap3_dss_supported_color_modes,
 	.overlay_caps = omap3430_dss_overlay_caps,
-	.clksrc_names = omap2_dss_clk_source_names,
 	.dss_params = am43xx_dss_param_range,
 	.supported_rotation_types = OMAP_DSS_ROT_DMA,
 	.buffer_size_unit = 1,
@@ -716,7 +682,6 @@ static const struct omap_dss_features omap3630_dss_features = {
 	.supported_outputs = omap3630_dss_supported_outputs,
 	.supported_color_modes = omap3_dss_supported_color_modes,
 	.overlay_caps = omap3630_dss_overlay_caps,
-	.clksrc_names = omap3_dss_clk_source_names,
 	.dss_params = omap3_dss_param_range,
 	.supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_VRFB,
 	.buffer_size_unit = 1,
@@ -738,7 +703,6 @@ static const struct omap_dss_features omap4430_es1_0_dss_features  = {
 	.supported_outputs = omap4_dss_supported_outputs,
 	.supported_color_modes = omap4_dss_supported_color_modes,
 	.overlay_caps = omap4_dss_overlay_caps,
-	.clksrc_names = omap4_dss_clk_source_names,
 	.dss_params = omap4_dss_param_range,
 	.supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_TILER,
 	.buffer_size_unit = 16,
@@ -759,7 +723,6 @@ static const struct omap_dss_features omap4430_es2_0_1_2_dss_features = {
 	.supported_outputs = omap4_dss_supported_outputs,
 	.supported_color_modes = omap4_dss_supported_color_modes,
 	.overlay_caps = omap4_dss_overlay_caps,
-	.clksrc_names = omap4_dss_clk_source_names,
 	.dss_params = omap4_dss_param_range,
 	.supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_TILER,
 	.buffer_size_unit = 16,
@@ -780,7 +743,6 @@ static const struct omap_dss_features omap4_dss_features = {
 	.supported_outputs = omap4_dss_supported_outputs,
 	.supported_color_modes = omap4_dss_supported_color_modes,
 	.overlay_caps = omap4_dss_overlay_caps,
-	.clksrc_names = omap4_dss_clk_source_names,
 	.dss_params = omap4_dss_param_range,
 	.supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_TILER,
 	.buffer_size_unit = 16,
@@ -801,7 +763,6 @@ static const struct omap_dss_features omap5_dss_features = {
 	.supported_outputs = omap5_dss_supported_outputs,
 	.supported_color_modes = omap4_dss_supported_color_modes,
 	.overlay_caps = omap4_dss_overlay_caps,
-	.clksrc_names = omap5_dss_clk_source_names,
 	.dss_params = omap5_dss_param_range,
 	.supported_rotation_types = OMAP_DSS_ROT_DMA | OMAP_DSS_ROT_TILER,
 	.buffer_size_unit = 16,
@@ -859,11 +820,6 @@ bool dss_feat_color_mode_supported(enum omap_plane plane,
 			color_mode;
 }
 
-const char *dss_feat_get_clk_source_name(enum omap_dss_clk_source id)
-{
-	return omap_current_dss_features->clksrc_names[id];
-}
-
 u32 dss_feat_get_buffer_size_unit(void)
 {
 	return omap_current_dss_features->buffer_size_unit;
diff --git a/drivers/gpu/drm/omapdrm/dss/dss_features.h b/drivers/gpu/drm/omapdrm/dss/dss_features.h
index 3d67d39f192f..bb4b7f0e642b 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss_features.h
+++ b/drivers/gpu/drm/omapdrm/dss/dss_features.h
@@ -91,7 +91,6 @@ unsigned long dss_feat_get_param_max(enum dss_range_param param);
 enum omap_overlay_caps dss_feat_get_overlay_caps(enum omap_plane plane);
 bool dss_feat_color_mode_supported(enum omap_plane plane,
 		enum omap_color_mode color_mode);
-const char *dss_feat_get_clk_source_name(enum omap_dss_clk_source id);
 
 u32 dss_feat_get_buffer_size_unit(void);	/* in bytes */
 u32 dss_feat_get_burst_size_unit(void);		/* in bytes */
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi.h b/drivers/gpu/drm/omapdrm/dss/hdmi.h
index 53616b02b613..63e711545865 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi.h
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi.h
@@ -23,8 +23,9 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/hdmi.h>
-#include <video/omapdss.h>
+#include <sound/omap-hdmi-audio.h>
 
+#include "omapdss.h"
 #include "dss.h"
 
 /* HDMI Wrapper */
@@ -240,6 +241,7 @@ struct hdmi_pll_data {
 
 	void __iomem *base;
 
+	struct platform_device *pdev;
 	struct hdmi_wp_data *wp;
 };
 
@@ -306,8 +308,6 @@ phys_addr_t hdmi_wp_get_audio_dma_addr(struct hdmi_wp_data *wp);
 
 /* HDMI PLL funcs */
 void hdmi_pll_dump(struct hdmi_pll_data *pll, struct seq_file *s);
-void hdmi_pll_compute(struct hdmi_pll_data *pll,
-	unsigned long target_tmds, struct dss_pll_clock_info *pi);
 int hdmi_pll_init(struct platform_device *pdev, struct hdmi_pll_data *pll,
 	struct hdmi_wp_data *wp);
 void hdmi_pll_uninit(struct hdmi_pll_data *hpll);
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4.c b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
index 4d46cdf7a037..cbd28dfdb86a 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
@@ -34,9 +34,9 @@
 #include <linux/regulator/consumer.h>
 #include <linux/component.h>
 #include <linux/of.h>
-#include <video/omapdss.h>
 #include <sound/omap-hdmi-audio.h>
 
+#include "omapdss.h"
 #include "hdmi4_core.h"
 #include "dss.h"
 #include "dss_features.h"
@@ -177,7 +177,11 @@ static int hdmi_power_on_full(struct omap_dss_device *dssdev)
 	if (p->double_pixel)
 		pc *= 2;
 
-	hdmi_pll_compute(&hdmi.pll, pc, &hdmi_cinfo);
+	/* DSS_HDMI_TCLK is bitclk / 10 */
+	pc *= 10;
+
+	dss_pll_calc_b(&hdmi.pll.pll, clk_get_rate(hdmi.pll.pll.clkin),
+		pc, &hdmi_cinfo);
 
 	r = dss_pll_enable(&hdmi.pll.pll);
 	if (r) {
@@ -204,9 +208,6 @@ static int hdmi_power_on_full(struct omap_dss_device *dssdev)
 
 	hdmi4_configure(&hdmi.core, &hdmi.wp, &hdmi.cfg);
 
-	/* bypass TV gamma table */
-	dispc_enable_gamma_table(0);
-
 	/* tv size */
 	dss_mgr_set_timings(channel, p);
 
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5.c b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
index 9255c0e1e4a7..0c0a5139a301 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi5.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
@@ -39,9 +39,9 @@
 #include <linux/regulator/consumer.h>
 #include <linux/component.h>
 #include <linux/of.h>
-#include <video/omapdss.h>
 #include <sound/omap-hdmi-audio.h>
 
+#include "omapdss.h"
 #include "hdmi5_core.h"
 #include "dss.h"
 #include "dss_features.h"
@@ -189,7 +189,11 @@ static int hdmi_power_on_full(struct omap_dss_device *dssdev)
 	if (p->double_pixel)
 		pc *= 2;
 
-	hdmi_pll_compute(&hdmi.pll, pc, &hdmi_cinfo);
+	/* DSS_HDMI_TCLK is bitclk / 10 */
+	pc *= 10;
+
+	dss_pll_calc_b(&hdmi.pll.pll, clk_get_rate(hdmi.pll.pll.clkin),
+		pc, &hdmi_cinfo);
 
 	/* disable and clear irqs */
 	hdmi_wp_clear_irqenable(&hdmi.wp, 0xffffffff);
@@ -221,9 +225,6 @@ static int hdmi_power_on_full(struct omap_dss_device *dssdev)
 
 	hdmi5_configure(&hdmi.core, &hdmi.wp, &hdmi.cfg);
 
-	/* bypass TV gamma table */
-	dispc_enable_gamma_table(0);
-
 	/* tv size */
 	dss_mgr_set_timings(channel, p);
 
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_common.c b/drivers/gpu/drm/omapdrm/dss/hdmi_common.c
index 1b8fcc6c4ba1..4dfb67fe5f6d 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_common.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_common.c
@@ -4,8 +4,8 @@
 #include <linux/kernel.h>
 #include <linux/err.h>
 #include <linux/of.h>
-#include <video/omapdss.h>
 
+#include "omapdss.h"
 #include "hdmi.h"
 
 int hdmi_parse_lanes_of(struct platform_device *pdev, struct device_node *ep,
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c b/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
index f98b750fc499..3ead47cccac5 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
@@ -14,8 +14,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
-#include <video/omapdss.h>
 
+#include "omapdss.h"
 #include "dss.h"
 #include "hdmi.h"
 
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c b/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
index f1015e8b8267..b8bf6a9e5557 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
@@ -17,9 +17,9 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/seq_file.h>
+#include <linux/pm_runtime.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 #include "hdmi.h"
 
@@ -39,71 +39,14 @@ void hdmi_pll_dump(struct hdmi_pll_data *pll, struct seq_file *s)
 	DUMPPLL(PLLCTRL_CFG4);
 }
 
-void hdmi_pll_compute(struct hdmi_pll_data *pll,
-	unsigned long target_tmds, struct dss_pll_clock_info *pi)
-{
-	unsigned long fint, clkdco, clkout;
-	unsigned long target_bitclk, target_clkdco;
-	unsigned long min_dco;
-	unsigned n, m, mf, m2, sd;
-	unsigned long clkin;
-	const struct dss_pll_hw *hw = pll->pll.hw;
-
-	clkin = clk_get_rate(pll->pll.clkin);
-
-	DSSDBG("clkin %lu, target tmds %lu\n", clkin, target_tmds);
-
-	target_bitclk = target_tmds * 10;
-
-	/* Fint */
-	n = DIV_ROUND_UP(clkin, hw->fint_max);
-	fint = clkin / n;
-
-	/* adjust m2 so that the clkdco will be high enough */
-	min_dco = roundup(hw->clkdco_min, fint);
-	m2 = DIV_ROUND_UP(min_dco, target_bitclk);
-	if (m2 == 0)
-		m2 = 1;
-
-	target_clkdco = target_bitclk * m2;
-	m = target_clkdco / fint;
-
-	clkdco = fint * m;
-
-	/* adjust clkdco with fractional mf */
-	if (WARN_ON(target_clkdco - clkdco > fint))
-		mf = 0;
-	else
-		mf = (u32)div_u64(262144ull * (target_clkdco - clkdco), fint);
-
-	if (mf > 0)
-		clkdco += (u32)div_u64((u64)mf * fint, 262144);
-
-	clkout = clkdco / m2;
-
-	/* sigma-delta */
-	sd = DIV_ROUND_UP(fint * m, 250000000);
-
-	DSSDBG("N = %u, M = %u, M.f = %u, M2 = %u, SD = %u\n",
-		n, m, mf, m2, sd);
-	DSSDBG("Fint %lu, clkdco %lu, clkout %lu\n", fint, clkdco, clkout);
-
-	pi->n = n;
-	pi->m = m;
-	pi->mf = mf;
-	pi->mX[0] = m2;
-	pi->sd = sd;
-
-	pi->fint = fint;
-	pi->clkdco = clkdco;
-	pi->clkout[0] = clkout;
-}
-
 static int hdmi_pll_enable(struct dss_pll *dsspll)
 {
 	struct hdmi_pll_data *pll = container_of(dsspll, struct hdmi_pll_data, pll);
 	struct hdmi_wp_data *wp = pll->wp;
-	u16 r = 0;
+	int r;
+
+	r = pm_runtime_get_sync(&pll->pdev->dev);
+	WARN_ON(r < 0);
 
 	dss_ctrl_pll_enable(DSS_PLL_HDMI, true);
 
@@ -118,10 +61,14 @@ static void hdmi_pll_disable(struct dss_pll *dsspll)
 {
 	struct hdmi_pll_data *pll = container_of(dsspll, struct hdmi_pll_data, pll);
 	struct hdmi_wp_data *wp = pll->wp;
+	int r;
 
 	hdmi_wp_set_pll_pwr(wp, HDMI_PLLPWRCMD_ALLOFF);
 
 	dss_ctrl_pll_enable(DSS_PLL_HDMI, false);
+
+	r = pm_runtime_put_sync(&pll->pdev->dev);
+	WARN_ON(r < 0 && r != -ENOSYS);
 }
 
 static const struct dss_pll_ops dsi_pll_ops = {
@@ -131,6 +78,8 @@ static const struct dss_pll_ops dsi_pll_ops = {
 };
 
 static const struct dss_pll_hw dss_omap4_hdmi_pll_hw = {
+	.type = DSS_PLL_TYPE_B,
+
 	.n_max = 255,
 	.m_min = 20,
 	.m_max = 4095,
@@ -154,6 +103,8 @@ static const struct dss_pll_hw dss_omap4_hdmi_pll_hw = {
 };
 
 static const struct dss_pll_hw dss_omap5_hdmi_pll_hw = {
+	.type = DSS_PLL_TYPE_B,
+
 	.n_max = 255,
 	.m_min = 20,
 	.m_max = 2045,
@@ -225,6 +176,7 @@ int hdmi_pll_init(struct platform_device *pdev, struct hdmi_pll_data *pll,
 	int r;
 	struct resource *res;
 
+	pll->pdev = pdev;
 	pll->wp = wp;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pll");
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c b/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
index 055f62fca5dc..203694a52d18 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
@@ -15,8 +15,8 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/seq_file.h>
-#include <video/omapdss.h>
 
+#include "omapdss.h"
 #include "dss.h"
 #include "hdmi.h"
 
diff --git a/drivers/gpu/drm/omapdrm/dss/omapdss.h b/drivers/gpu/drm/omapdrm/dss/omapdss.h
index d7e7c909bbc2..6eaf1adbd606 100644
--- a/drivers/gpu/drm/omapdrm/dss/omapdss.h
+++ b/drivers/gpu/drm/omapdrm/dss/omapdss.h
@@ -18,7 +18,872 @@
 #ifndef __OMAP_DRM_DSS_H
 #define __OMAP_DRM_DSS_H
 
-#include <video/omapdss.h>
+#include <linux/list.h>
+#include <linux/kobject.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <video/videomode.h>
+#include <linux/platform_data/omapdss.h>
+#include <uapi/drm/drm_mode.h>
+
+#define DISPC_IRQ_FRAMEDONE		(1 << 0)
+#define DISPC_IRQ_VSYNC			(1 << 1)
+#define DISPC_IRQ_EVSYNC_EVEN		(1 << 2)
+#define DISPC_IRQ_EVSYNC_ODD		(1 << 3)
+#define DISPC_IRQ_ACBIAS_COUNT_STAT	(1 << 4)
+#define DISPC_IRQ_PROG_LINE_NUM		(1 << 5)
+#define DISPC_IRQ_GFX_FIFO_UNDERFLOW	(1 << 6)
+#define DISPC_IRQ_GFX_END_WIN		(1 << 7)
+#define DISPC_IRQ_PAL_GAMMA_MASK	(1 << 8)
+#define DISPC_IRQ_OCP_ERR		(1 << 9)
+#define DISPC_IRQ_VID1_FIFO_UNDERFLOW	(1 << 10)
+#define DISPC_IRQ_VID1_END_WIN		(1 << 11)
+#define DISPC_IRQ_VID2_FIFO_UNDERFLOW	(1 << 12)
+#define DISPC_IRQ_VID2_END_WIN		(1 << 13)
+#define DISPC_IRQ_SYNC_LOST		(1 << 14)
+#define DISPC_IRQ_SYNC_LOST_DIGIT	(1 << 15)
+#define DISPC_IRQ_WAKEUP		(1 << 16)
+#define DISPC_IRQ_SYNC_LOST2		(1 << 17)
+#define DISPC_IRQ_VSYNC2		(1 << 18)
+#define DISPC_IRQ_VID3_END_WIN		(1 << 19)
+#define DISPC_IRQ_VID3_FIFO_UNDERFLOW	(1 << 20)
+#define DISPC_IRQ_ACBIAS_COUNT_STAT2	(1 << 21)
+#define DISPC_IRQ_FRAMEDONE2		(1 << 22)
+#define DISPC_IRQ_FRAMEDONEWB		(1 << 23)
+#define DISPC_IRQ_FRAMEDONETV		(1 << 24)
+#define DISPC_IRQ_WBBUFFEROVERFLOW	(1 << 25)
+#define DISPC_IRQ_WBUNCOMPLETEERROR	(1 << 26)
+#define DISPC_IRQ_SYNC_LOST3		(1 << 27)
+#define DISPC_IRQ_VSYNC3		(1 << 28)
+#define DISPC_IRQ_ACBIAS_COUNT_STAT3	(1 << 29)
+#define DISPC_IRQ_FRAMEDONE3		(1 << 30)
+
+struct omap_dss_device;
+struct omap_overlay_manager;
+struct dss_lcd_mgr_config;
+struct snd_aes_iec958;
+struct snd_cea_861_aud_if;
+struct hdmi_avi_infoframe;
+
+enum omap_display_type {
+	OMAP_DISPLAY_TYPE_NONE		= 0,
+	OMAP_DISPLAY_TYPE_DPI		= 1 << 0,
+	OMAP_DISPLAY_TYPE_DBI		= 1 << 1,
+	OMAP_DISPLAY_TYPE_SDI		= 1 << 2,
+	OMAP_DISPLAY_TYPE_DSI		= 1 << 3,
+	OMAP_DISPLAY_TYPE_VENC		= 1 << 4,
+	OMAP_DISPLAY_TYPE_HDMI		= 1 << 5,
+	OMAP_DISPLAY_TYPE_DVI		= 1 << 6,
+};
+
+enum omap_plane {
+	OMAP_DSS_GFX	= 0,
+	OMAP_DSS_VIDEO1	= 1,
+	OMAP_DSS_VIDEO2	= 2,
+	OMAP_DSS_VIDEO3	= 3,
+	OMAP_DSS_WB	= 4,
+};
+
+enum omap_channel {
+	OMAP_DSS_CHANNEL_LCD	= 0,
+	OMAP_DSS_CHANNEL_DIGIT	= 1,
+	OMAP_DSS_CHANNEL_LCD2	= 2,
+	OMAP_DSS_CHANNEL_LCD3	= 3,
+	OMAP_DSS_CHANNEL_WB	= 4,
+};
+
+enum omap_color_mode {
+	OMAP_DSS_COLOR_CLUT1	= 1 << 0,  /* BITMAP 1 */
+	OMAP_DSS_COLOR_CLUT2	= 1 << 1,  /* BITMAP 2 */
+	OMAP_DSS_COLOR_CLUT4	= 1 << 2,  /* BITMAP 4 */
+	OMAP_DSS_COLOR_CLUT8	= 1 << 3,  /* BITMAP 8 */
+	OMAP_DSS_COLOR_RGB12U	= 1 << 4,  /* RGB12, 16-bit container */
+	OMAP_DSS_COLOR_ARGB16	= 1 << 5,  /* ARGB16 */
+	OMAP_DSS_COLOR_RGB16	= 1 << 6,  /* RGB16 */
+	OMAP_DSS_COLOR_RGB24U	= 1 << 7,  /* RGB24, 32-bit container */
+	OMAP_DSS_COLOR_RGB24P	= 1 << 8,  /* RGB24, 24-bit container */
+	OMAP_DSS_COLOR_YUV2	= 1 << 9,  /* YUV2 4:2:2 co-sited */
+	OMAP_DSS_COLOR_UYVY	= 1 << 10, /* UYVY 4:2:2 co-sited */
+	OMAP_DSS_COLOR_ARGB32	= 1 << 11, /* ARGB32 */
+	OMAP_DSS_COLOR_RGBA32	= 1 << 12, /* RGBA32 */
+	OMAP_DSS_COLOR_RGBX32	= 1 << 13, /* RGBx32 */
+	OMAP_DSS_COLOR_NV12		= 1 << 14, /* NV12 format: YUV 4:2:0 */
+	OMAP_DSS_COLOR_RGBA16		= 1 << 15, /* RGBA16 - 4444 */
+	OMAP_DSS_COLOR_RGBX16		= 1 << 16, /* RGBx16 - 4444 */
+	OMAP_DSS_COLOR_ARGB16_1555	= 1 << 17, /* ARGB16 - 1555 */
+	OMAP_DSS_COLOR_XRGB16_1555	= 1 << 18, /* xRGB16 - 1555 */
+};
+
+enum omap_dss_load_mode {
+	OMAP_DSS_LOAD_CLUT_AND_FRAME	= 0,
+	OMAP_DSS_LOAD_CLUT_ONLY		= 1,
+	OMAP_DSS_LOAD_FRAME_ONLY	= 2,
+	OMAP_DSS_LOAD_CLUT_ONCE_FRAME	= 3,
+};
+
+enum omap_dss_trans_key_type {
+	OMAP_DSS_COLOR_KEY_GFX_DST = 0,
+	OMAP_DSS_COLOR_KEY_VID_SRC = 1,
+};
+
+enum omap_rfbi_te_mode {
+	OMAP_DSS_RFBI_TE_MODE_1 = 1,
+	OMAP_DSS_RFBI_TE_MODE_2 = 2,
+};
+
+enum omap_dss_signal_level {
+	OMAPDSS_SIG_ACTIVE_LOW,
+	OMAPDSS_SIG_ACTIVE_HIGH,
+};
+
+enum omap_dss_signal_edge {
+	OMAPDSS_DRIVE_SIG_FALLING_EDGE,
+	OMAPDSS_DRIVE_SIG_RISING_EDGE,
+};
+
+enum omap_dss_venc_type {
+	OMAP_DSS_VENC_TYPE_COMPOSITE,
+	OMAP_DSS_VENC_TYPE_SVIDEO,
+};
+
+enum omap_dss_dsi_pixel_format {
+	OMAP_DSS_DSI_FMT_RGB888,
+	OMAP_DSS_DSI_FMT_RGB666,
+	OMAP_DSS_DSI_FMT_RGB666_PACKED,
+	OMAP_DSS_DSI_FMT_RGB565,
+};
+
+enum omap_dss_dsi_mode {
+	OMAP_DSS_DSI_CMD_MODE = 0,
+	OMAP_DSS_DSI_VIDEO_MODE,
+};
+
+enum omap_display_caps {
+	OMAP_DSS_DISPLAY_CAP_MANUAL_UPDATE	= 1 << 0,
+	OMAP_DSS_DISPLAY_CAP_TEAR_ELIM		= 1 << 1,
+};
+
+enum omap_dss_display_state {
+	OMAP_DSS_DISPLAY_DISABLED = 0,
+	OMAP_DSS_DISPLAY_ACTIVE,
+};
+
+enum omap_dss_rotation_type {
+	OMAP_DSS_ROT_DMA	= 1 << 0,
+	OMAP_DSS_ROT_VRFB	= 1 << 1,
+	OMAP_DSS_ROT_TILER	= 1 << 2,
+};
+
+/* clockwise rotation angle */
+enum omap_dss_rotation_angle {
+	OMAP_DSS_ROT_0   = 0,
+	OMAP_DSS_ROT_90  = 1,
+	OMAP_DSS_ROT_180 = 2,
+	OMAP_DSS_ROT_270 = 3,
+};
+
+enum omap_overlay_caps {
+	OMAP_DSS_OVL_CAP_SCALE = 1 << 0,
+	OMAP_DSS_OVL_CAP_GLOBAL_ALPHA = 1 << 1,
+	OMAP_DSS_OVL_CAP_PRE_MULT_ALPHA = 1 << 2,
+	OMAP_DSS_OVL_CAP_ZORDER = 1 << 3,
+	OMAP_DSS_OVL_CAP_POS = 1 << 4,
+	OMAP_DSS_OVL_CAP_REPLICATION = 1 << 5,
+};
+
+enum omap_overlay_manager_caps {
+	OMAP_DSS_DUMMY_VALUE, /* add a dummy value to prevent compiler error */
+};
+
+enum omap_dss_clk_source {
+	OMAP_DSS_CLK_SRC_FCK = 0,		/* OMAP2/3: DSS1_ALWON_FCLK
+						 * OMAP4: DSS_FCLK */
+	OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC,	/* OMAP3: DSI1_PLL_FCLK
+						 * OMAP4: PLL1_CLK1 */
+	OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI,	/* OMAP3: DSI2_PLL_FCLK
+						 * OMAP4: PLL1_CLK2 */
+	OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC,	/* OMAP4: PLL2_CLK1 */
+	OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI,	/* OMAP4: PLL2_CLK2 */
+};
+
+enum omap_hdmi_flags {
+	OMAP_HDMI_SDA_SCL_EXTERNAL_PULLUP = 1 << 0,
+};
+
+enum omap_dss_output_id {
+	OMAP_DSS_OUTPUT_DPI	= 1 << 0,
+	OMAP_DSS_OUTPUT_DBI	= 1 << 1,
+	OMAP_DSS_OUTPUT_SDI	= 1 << 2,
+	OMAP_DSS_OUTPUT_DSI1	= 1 << 3,
+	OMAP_DSS_OUTPUT_DSI2	= 1 << 4,
+	OMAP_DSS_OUTPUT_VENC	= 1 << 5,
+	OMAP_DSS_OUTPUT_HDMI	= 1 << 6,
+};
+
+/* RFBI */
+
+struct rfbi_timings {
+	int cs_on_time;
+	int cs_off_time;
+	int we_on_time;
+	int we_off_time;
+	int re_on_time;
+	int re_off_time;
+	int we_cycle_time;
+	int re_cycle_time;
+	int cs_pulse_width;
+	int access_time;
+
+	int clk_div;
+
+	u32 tim[5];             /* set by rfbi_convert_timings() */
+
+	int converted;
+};
+
+/* DSI */
+
+enum omap_dss_dsi_trans_mode {
+	/* Sync Pulses: both sync start and end packets sent */
+	OMAP_DSS_DSI_PULSE_MODE,
+	/* Sync Events: only sync start packets sent */
+	OMAP_DSS_DSI_EVENT_MODE,
+	/* Burst: only sync start packets sent, pixels are time compressed */
+	OMAP_DSS_DSI_BURST_MODE,
+};
+
+struct omap_dss_dsi_videomode_timings {
+	unsigned long hsclk;
+
+	unsigned ndl;
+	unsigned bitspp;
+
+	/* pixels */
+	u16 hact;
+	/* lines */
+	u16 vact;
+
+	/* DSI video mode blanking data */
+	/* Unit: byte clock cycles */
+	u16 hss;
+	u16 hsa;
+	u16 hse;
+	u16 hfp;
+	u16 hbp;
+	/* Unit: line clocks */
+	u16 vsa;
+	u16 vfp;
+	u16 vbp;
+
+	/* DSI blanking modes */
+	int blanking_mode;
+	int hsa_blanking_mode;
+	int hbp_blanking_mode;
+	int hfp_blanking_mode;
+
+	enum omap_dss_dsi_trans_mode trans_mode;
+
+	bool ddr_clk_always_on;
+	int window_sync;
+};
+
+struct omap_dss_dsi_config {
+	enum omap_dss_dsi_mode mode;
+	enum omap_dss_dsi_pixel_format pixel_format;
+	const struct omap_video_timings *timings;
+
+	unsigned long hs_clk_min, hs_clk_max;
+	unsigned long lp_clk_min, lp_clk_max;
+
+	bool ddr_clk_always_on;
+	enum omap_dss_dsi_trans_mode trans_mode;
+};
+
+struct omap_video_timings {
+	/* Unit: pixels */
+	u16 x_res;
+	/* Unit: pixels */
+	u16 y_res;
+	/* Unit: Hz */
+	u32 pixelclock;
+	/* Unit: pixel clocks */
+	u16 hsw;	/* Horizontal synchronization pulse width */
+	/* Unit: pixel clocks */
+	u16 hfp;	/* Horizontal front porch */
+	/* Unit: pixel clocks */
+	u16 hbp;	/* Horizontal back porch */
+	/* Unit: line clocks */
+	u16 vsw;	/* Vertical synchronization pulse width */
+	/* Unit: line clocks */
+	u16 vfp;	/* Vertical front porch */
+	/* Unit: line clocks */
+	u16 vbp;	/* Vertical back porch */
+
+	/* Vsync logic level */
+	enum omap_dss_signal_level vsync_level;
+	/* Hsync logic level */
+	enum omap_dss_signal_level hsync_level;
+	/* Interlaced or Progressive timings */
+	bool interlace;
+	/* Pixel clock edge to drive LCD data */
+	enum omap_dss_signal_edge data_pclk_edge;
+	/* Data enable logic level */
+	enum omap_dss_signal_level de_level;
+	/* Pixel clock edges to drive HSYNC and VSYNC signals */
+	enum omap_dss_signal_edge sync_pclk_edge;
+
+	bool double_pixel;
+};
+
+/* Hardcoded timings for tv modes. Venc only uses these to
+ * identify the mode, and does not actually use the configs
+ * itself. However, the configs should be something that
+ * a normal monitor can also show */
+extern const struct omap_video_timings omap_dss_pal_timings;
+extern const struct omap_video_timings omap_dss_ntsc_timings;
+
+struct omap_dss_cpr_coefs {
+	s16 rr, rg, rb;
+	s16 gr, gg, gb;
+	s16 br, bg, bb;
+};
+
+struct omap_overlay_info {
+	dma_addr_t paddr;
+	dma_addr_t p_uv_addr;  /* for NV12 format */
+	u16 screen_width;
+	u16 width;
+	u16 height;
+	enum omap_color_mode color_mode;
+	u8 rotation;
+	enum omap_dss_rotation_type rotation_type;
+	bool mirror;
+
+	u16 pos_x;
+	u16 pos_y;
+	u16 out_width;	/* if 0, out_width == width */
+	u16 out_height;	/* if 0, out_height == height */
+	u8 global_alpha;
+	u8 pre_mult_alpha;
+	u8 zorder;
+};
+
+struct omap_overlay {
+	struct kobject kobj;
+	struct list_head list;
+
+	/* static fields */
+	const char *name;
+	enum omap_plane id;
+	enum omap_color_mode supported_modes;
+	enum omap_overlay_caps caps;
+
+	/* dynamic fields */
+	struct omap_overlay_manager *manager;
+
+	/*
+	 * The following functions do not block:
+	 *
+	 * is_enabled
+	 * set_overlay_info
+	 * get_overlay_info
+	 *
+	 * The rest of the functions may block and cannot be called from
+	 * interrupt context
+	 */
+
+	int (*enable)(struct omap_overlay *ovl);
+	int (*disable)(struct omap_overlay *ovl);
+	bool (*is_enabled)(struct omap_overlay *ovl);
+
+	int (*set_manager)(struct omap_overlay *ovl,
+		struct omap_overlay_manager *mgr);
+	int (*unset_manager)(struct omap_overlay *ovl);
+
+	int (*set_overlay_info)(struct omap_overlay *ovl,
+			struct omap_overlay_info *info);
+	void (*get_overlay_info)(struct omap_overlay *ovl,
+			struct omap_overlay_info *info);
+
+	int (*wait_for_go)(struct omap_overlay *ovl);
+
+	struct omap_dss_device *(*get_device)(struct omap_overlay *ovl);
+};
+
+struct omap_overlay_manager_info {
+	u32 default_color;
+
+	enum omap_dss_trans_key_type trans_key_type;
+	u32 trans_key;
+	bool trans_enabled;
+
+	bool partial_alpha_enabled;
+
+	bool cpr_enable;
+	struct omap_dss_cpr_coefs cpr_coefs;
+};
+
+struct omap_overlay_manager {
+	struct kobject kobj;
+
+	/* static fields */
+	const char *name;
+	enum omap_channel id;
+	enum omap_overlay_manager_caps caps;
+	struct list_head overlays;
+	enum omap_display_type supported_displays;
+	enum omap_dss_output_id supported_outputs;
+
+	/* dynamic fields */
+	struct omap_dss_device *output;
+
+	/*
+	 * The following functions do not block:
+	 *
+	 * set_manager_info
+	 * get_manager_info
+	 * apply
+	 *
+	 * The rest of the functions may block and cannot be called from
+	 * interrupt context
+	 */
+
+	int (*set_output)(struct omap_overlay_manager *mgr,
+		struct omap_dss_device *output);
+	int (*unset_output)(struct omap_overlay_manager *mgr);
+
+	int (*set_manager_info)(struct omap_overlay_manager *mgr,
+			struct omap_overlay_manager_info *info);
+	void (*get_manager_info)(struct omap_overlay_manager *mgr,
+			struct omap_overlay_manager_info *info);
+
+	int (*apply)(struct omap_overlay_manager *mgr);
+	int (*wait_for_go)(struct omap_overlay_manager *mgr);
+	int (*wait_for_vsync)(struct omap_overlay_manager *mgr);
+
+	struct omap_dss_device *(*get_device)(struct omap_overlay_manager *mgr);
+};
+
+/* 22 pins means 1 clk lane and 10 data lanes */
+#define OMAP_DSS_MAX_DSI_PINS 22
+
+struct omap_dsi_pin_config {
+	int num_pins;
+	/*
+	 * pin numbers in the following order:
+	 * clk+, clk-
+	 * data1+, data1-
+	 * data2+, data2-
+	 * ...
+	 */
+	int pins[OMAP_DSS_MAX_DSI_PINS];
+};
+
+struct omap_dss_writeback_info {
+	u32 paddr;
+	u32 p_uv_addr;
+	u16 buf_width;
+	u16 width;
+	u16 height;
+	enum omap_color_mode color_mode;
+	u8 rotation;
+	enum omap_dss_rotation_type rotation_type;
+	bool mirror;
+	u8 pre_mult_alpha;
+};
+
+struct omapdss_dpi_ops {
+	int (*connect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+	void (*disconnect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+
+	int (*enable)(struct omap_dss_device *dssdev);
+	void (*disable)(struct omap_dss_device *dssdev);
+
+	int (*check_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*set_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*get_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+
+	void (*set_data_lines)(struct omap_dss_device *dssdev, int data_lines);
+};
+
+struct omapdss_sdi_ops {
+	int (*connect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+	void (*disconnect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+
+	int (*enable)(struct omap_dss_device *dssdev);
+	void (*disable)(struct omap_dss_device *dssdev);
+
+	int (*check_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*set_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*get_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+
+	void (*set_datapairs)(struct omap_dss_device *dssdev, int datapairs);
+};
+
+struct omapdss_dvi_ops {
+	int (*connect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+	void (*disconnect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+
+	int (*enable)(struct omap_dss_device *dssdev);
+	void (*disable)(struct omap_dss_device *dssdev);
+
+	int (*check_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*set_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*get_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+};
+
+struct omapdss_atv_ops {
+	int (*connect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+	void (*disconnect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+
+	int (*enable)(struct omap_dss_device *dssdev);
+	void (*disable)(struct omap_dss_device *dssdev);
+
+	int (*check_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*set_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*get_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+
+	void (*set_type)(struct omap_dss_device *dssdev,
+		enum omap_dss_venc_type type);
+	void (*invert_vid_out_polarity)(struct omap_dss_device *dssdev,
+		bool invert_polarity);
+
+	int (*set_wss)(struct omap_dss_device *dssdev, u32 wss);
+	u32 (*get_wss)(struct omap_dss_device *dssdev);
+};
+
+struct omapdss_hdmi_ops {
+	int (*connect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+	void (*disconnect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+
+	int (*enable)(struct omap_dss_device *dssdev);
+	void (*disable)(struct omap_dss_device *dssdev);
+
+	int (*check_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*set_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*get_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+
+	int (*read_edid)(struct omap_dss_device *dssdev, u8 *buf, int len);
+	bool (*detect)(struct omap_dss_device *dssdev);
+
+	int (*set_hdmi_mode)(struct omap_dss_device *dssdev, bool hdmi_mode);
+	int (*set_infoframe)(struct omap_dss_device *dssdev,
+		const struct hdmi_avi_infoframe *avi);
+};
+
+struct omapdss_dsi_ops {
+	int (*connect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+	void (*disconnect)(struct omap_dss_device *dssdev,
+			struct omap_dss_device *dst);
+
+	int (*enable)(struct omap_dss_device *dssdev);
+	void (*disable)(struct omap_dss_device *dssdev, bool disconnect_lanes,
+			bool enter_ulps);
+
+	/* bus configuration */
+	int (*set_config)(struct omap_dss_device *dssdev,
+			const struct omap_dss_dsi_config *cfg);
+	int (*configure_pins)(struct omap_dss_device *dssdev,
+			const struct omap_dsi_pin_config *pin_cfg);
+
+	void (*enable_hs)(struct omap_dss_device *dssdev, int channel,
+			bool enable);
+	int (*enable_te)(struct omap_dss_device *dssdev, bool enable);
+
+	int (*update)(struct omap_dss_device *dssdev, int channel,
+			void (*callback)(int, void *), void *data);
+
+	void (*bus_lock)(struct omap_dss_device *dssdev);
+	void (*bus_unlock)(struct omap_dss_device *dssdev);
+
+	int (*enable_video_output)(struct omap_dss_device *dssdev, int channel);
+	void (*disable_video_output)(struct omap_dss_device *dssdev,
+			int channel);
+
+	int (*request_vc)(struct omap_dss_device *dssdev, int *channel);
+	int (*set_vc_id)(struct omap_dss_device *dssdev, int channel,
+			int vc_id);
+	void (*release_vc)(struct omap_dss_device *dssdev, int channel);
+
+	/* data transfer */
+	int (*dcs_write)(struct omap_dss_device *dssdev, int channel,
+			u8 *data, int len);
+	int (*dcs_write_nosync)(struct omap_dss_device *dssdev, int channel,
+			u8 *data, int len);
+	int (*dcs_read)(struct omap_dss_device *dssdev, int channel, u8 dcs_cmd,
+			u8 *data, int len);
+
+	int (*gen_write)(struct omap_dss_device *dssdev, int channel,
+			u8 *data, int len);
+	int (*gen_write_nosync)(struct omap_dss_device *dssdev, int channel,
+			u8 *data, int len);
+	int (*gen_read)(struct omap_dss_device *dssdev, int channel,
+			u8 *reqdata, int reqlen,
+			u8 *data, int len);
+
+	int (*bta_sync)(struct omap_dss_device *dssdev, int channel);
+
+	int (*set_max_rx_packet_size)(struct omap_dss_device *dssdev,
+			int channel, u16 plen);
+};
+
+struct omap_dss_device {
+	struct kobject kobj;
+	struct device *dev;
+
+	struct module *owner;
+
+	struct list_head panel_list;
+
+	/* alias in the form of "display%d" */
+	char alias[16];
+
+	enum omap_display_type type;
+	enum omap_display_type output_type;
+
+	union {
+		struct {
+			u8 data_lines;
+		} dpi;
+
+		struct {
+			u8 channel;
+			u8 data_lines;
+		} rfbi;
+
+		struct {
+			u8 datapairs;
+		} sdi;
+
+		struct {
+			int module;
+		} dsi;
+
+		struct {
+			enum omap_dss_venc_type type;
+			bool invert_polarity;
+		} venc;
+	} phy;
+
+	struct {
+		struct omap_video_timings timings;
+
+		enum omap_dss_dsi_pixel_format dsi_pix_fmt;
+		enum omap_dss_dsi_mode dsi_mode;
+	} panel;
+
+	struct {
+		u8 pixel_size;
+		struct rfbi_timings rfbi_timings;
+	} ctrl;
+
+	const char *name;
+
+	/* used to match device to driver */
+	const char *driver_name;
+
+	void *data;
+
+	struct omap_dss_driver *driver;
+
+	union {
+		const struct omapdss_dpi_ops *dpi;
+		const struct omapdss_sdi_ops *sdi;
+		const struct omapdss_dvi_ops *dvi;
+		const struct omapdss_hdmi_ops *hdmi;
+		const struct omapdss_atv_ops *atv;
+		const struct omapdss_dsi_ops *dsi;
+	} ops;
+
+	/* helper variable for driver suspend/resume */
+	bool activate_after_resume;
+
+	enum omap_display_caps caps;
+
+	struct omap_dss_device *src;
+
+	enum omap_dss_display_state state;
+
+	/* OMAP DSS output specific fields */
+
+	struct list_head list;
+
+	/* DISPC channel for this output */
+	enum omap_channel dispc_channel;
+	bool dispc_channel_connected;
+
+	/* output instance */
+	enum omap_dss_output_id id;
+
+	/* the port number in the DT node */
+	int port_num;
+
+	/* dynamic fields */
+	struct omap_overlay_manager *manager;
+
+	struct omap_dss_device *dst;
+};
+
+struct omap_dss_driver {
+	int (*probe)(struct omap_dss_device *);
+	void (*remove)(struct omap_dss_device *);
+
+	int (*connect)(struct omap_dss_device *dssdev);
+	void (*disconnect)(struct omap_dss_device *dssdev);
+
+	int (*enable)(struct omap_dss_device *display);
+	void (*disable)(struct omap_dss_device *display);
+	int (*run_test)(struct omap_dss_device *display, int test);
+
+	int (*update)(struct omap_dss_device *dssdev,
+			       u16 x, u16 y, u16 w, u16 h);
+	int (*sync)(struct omap_dss_device *dssdev);
+
+	int (*enable_te)(struct omap_dss_device *dssdev, bool enable);
+	int (*get_te)(struct omap_dss_device *dssdev);
+
+	u8 (*get_rotate)(struct omap_dss_device *dssdev);
+	int (*set_rotate)(struct omap_dss_device *dssdev, u8 rotate);
+
+	bool (*get_mirror)(struct omap_dss_device *dssdev);
+	int (*set_mirror)(struct omap_dss_device *dssdev, bool enable);
+
+	int (*memory_read)(struct omap_dss_device *dssdev,
+			void *buf, size_t size,
+			u16 x, u16 y, u16 w, u16 h);
+
+	void (*get_resolution)(struct omap_dss_device *dssdev,
+			u16 *xres, u16 *yres);
+	void (*get_dimensions)(struct omap_dss_device *dssdev,
+			u32 *width, u32 *height);
+	int (*get_recommended_bpp)(struct omap_dss_device *dssdev);
+
+	int (*check_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*set_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+	void (*get_timings)(struct omap_dss_device *dssdev,
+			struct omap_video_timings *timings);
+
+	int (*set_wss)(struct omap_dss_device *dssdev, u32 wss);
+	u32 (*get_wss)(struct omap_dss_device *dssdev);
+
+	int (*read_edid)(struct omap_dss_device *dssdev, u8 *buf, int len);
+	bool (*detect)(struct omap_dss_device *dssdev);
+
+	int (*set_hdmi_mode)(struct omap_dss_device *dssdev, bool hdmi_mode);
+	int (*set_hdmi_infoframe)(struct omap_dss_device *dssdev,
+		const struct hdmi_avi_infoframe *avi);
+};
+
+enum omapdss_version omapdss_get_version(void);
+bool omapdss_is_initialized(void);
+
+int omap_dss_register_driver(struct omap_dss_driver *);
+void omap_dss_unregister_driver(struct omap_dss_driver *);
+
+int omapdss_register_display(struct omap_dss_device *dssdev);
+void omapdss_unregister_display(struct omap_dss_device *dssdev);
+
+struct omap_dss_device *omap_dss_get_device(struct omap_dss_device *dssdev);
+void omap_dss_put_device(struct omap_dss_device *dssdev);
+#define for_each_dss_dev(d) while ((d = omap_dss_get_next_device(d)) != NULL)
+struct omap_dss_device *omap_dss_get_next_device(struct omap_dss_device *from);
+struct omap_dss_device *omap_dss_find_device(void *data,
+		int (*match)(struct omap_dss_device *dssdev, void *data));
+const char *omapdss_get_default_display_name(void);
+
+void videomode_to_omap_video_timings(const struct videomode *vm,
+		struct omap_video_timings *ovt);
+void omap_video_timings_to_videomode(const struct omap_video_timings *ovt,
+		struct videomode *vm);
+
+int dss_feat_get_num_mgrs(void);
+int dss_feat_get_num_ovls(void);
+enum omap_color_mode dss_feat_get_supported_color_modes(enum omap_plane plane);
+
+
+
+int omap_dss_get_num_overlay_managers(void);
+struct omap_overlay_manager *omap_dss_get_overlay_manager(int num);
+
+int omap_dss_get_num_overlays(void);
+struct omap_overlay *omap_dss_get_overlay(int num);
+
+int omapdss_register_output(struct omap_dss_device *output);
+void omapdss_unregister_output(struct omap_dss_device *output);
+struct omap_dss_device *omap_dss_get_output(enum omap_dss_output_id id);
+struct omap_dss_device *omap_dss_find_output(const char *name);
+struct omap_dss_device *omap_dss_find_output_by_port_node(struct device_node *port);
+int omapdss_output_set_device(struct omap_dss_device *out,
+		struct omap_dss_device *dssdev);
+int omapdss_output_unset_device(struct omap_dss_device *out);
+
+struct omap_dss_device *omapdss_find_output_from_display(struct omap_dss_device *dssdev);
+struct omap_overlay_manager *omapdss_find_mgr_from_display(struct omap_dss_device *dssdev);
+
+void omapdss_default_get_resolution(struct omap_dss_device *dssdev,
+		u16 *xres, u16 *yres);
+int omapdss_default_get_recommended_bpp(struct omap_dss_device *dssdev);
+void omapdss_default_get_timings(struct omap_dss_device *dssdev,
+		struct omap_video_timings *timings);
+
+typedef void (*omap_dispc_isr_t) (void *arg, u32 mask);
+int omap_dispc_register_isr(omap_dispc_isr_t isr, void *arg, u32 mask);
+int omap_dispc_unregister_isr(omap_dispc_isr_t isr, void *arg, u32 mask);
+
+int omapdss_compat_init(void);
+void omapdss_compat_uninit(void);
+
+static inline bool omapdss_device_is_connected(struct omap_dss_device *dssdev)
+{
+	return dssdev->src;
+}
+
+static inline bool omapdss_device_is_enabled(struct omap_dss_device *dssdev)
+{
+	return dssdev->state == OMAP_DSS_DISPLAY_ACTIVE;
+}
+
+struct device_node *
+omapdss_of_get_next_port(const struct device_node *parent,
+			 struct device_node *prev);
+
+struct device_node *
+omapdss_of_get_next_endpoint(const struct device_node *parent,
+			     struct device_node *prev);
+
+struct device_node *
+omapdss_of_get_first_endpoint(const struct device_node *parent);
+
+struct omap_dss_device *
+omapdss_of_find_source_for_first_ep(struct device_node *node);
 
 u32 dispc_read_irqstatus(void);
 void dispc_clear_irqstatus(u32 mask);
@@ -44,6 +909,10 @@ void dispc_mgr_set_timings(enum omap_channel channel,
 		const struct omap_video_timings *timings);
 void dispc_mgr_setup(enum omap_channel channel,
 		const struct omap_overlay_manager_info *info);
+u32 dispc_mgr_gamma_size(enum omap_channel channel);
+void dispc_mgr_set_gamma(enum omap_channel channel,
+			 const struct drm_color_lut *lut,
+			 unsigned int length);
 
 int dispc_ovl_enable(enum omap_plane plane, bool enable);
 bool dispc_ovl_enabled(enum omap_plane plane);
diff --git a/drivers/gpu/drm/omapdrm/dss/output.c b/drivers/gpu/drm/omapdrm/dss/output.c
index 829232ad8c81..24f859488201 100644
--- a/drivers/gpu/drm/omapdrm/dss/output.c
+++ b/drivers/gpu/drm/omapdrm/dss/output.c
@@ -21,8 +21,7 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 
 static LIST_HEAD(output_list);
diff --git a/drivers/gpu/drm/omapdrm/dss/pll.c b/drivers/gpu/drm/omapdrm/dss/pll.c
index f974ddcd3b6e..0a76c89cdc2e 100644
--- a/drivers/gpu/drm/omapdrm/dss/pll.c
+++ b/drivers/gpu/drm/omapdrm/dss/pll.c
@@ -22,8 +22,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/sched.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 
 #define PLL_CONTROL			0x0000
@@ -76,6 +75,59 @@ struct dss_pll *dss_pll_find(const char *name)
 	return NULL;
 }
 
+struct dss_pll *dss_pll_find_by_src(enum dss_clk_source src)
+{
+	struct dss_pll *pll;
+
+	switch (src) {
+	default:
+	case DSS_CLK_SRC_FCK:
+		return NULL;
+
+	case DSS_CLK_SRC_HDMI_PLL:
+		return dss_pll_find("hdmi");
+
+	case DSS_CLK_SRC_PLL1_1:
+	case DSS_CLK_SRC_PLL1_2:
+	case DSS_CLK_SRC_PLL1_3:
+		pll = dss_pll_find("dsi0");
+		if (!pll)
+			pll = dss_pll_find("video0");
+		return pll;
+
+	case DSS_CLK_SRC_PLL2_1:
+	case DSS_CLK_SRC_PLL2_2:
+	case DSS_CLK_SRC_PLL2_3:
+		pll = dss_pll_find("dsi1");
+		if (!pll)
+			pll = dss_pll_find("video1");
+		return pll;
+	}
+}
+
+unsigned dss_pll_get_clkout_idx_for_src(enum dss_clk_source src)
+{
+	switch (src) {
+	case DSS_CLK_SRC_HDMI_PLL:
+		return 0;
+
+	case DSS_CLK_SRC_PLL1_1:
+	case DSS_CLK_SRC_PLL2_1:
+		return 0;
+
+	case DSS_CLK_SRC_PLL1_2:
+	case DSS_CLK_SRC_PLL2_2:
+		return 1;
+
+	case DSS_CLK_SRC_PLL1_3:
+	case DSS_CLK_SRC_PLL2_3:
+		return 2;
+
+	default:
+		return 0;
+	}
+}
+
 int dss_pll_enable(struct dss_pll *pll)
 {
 	int r;
@@ -129,7 +181,7 @@ int dss_pll_set_config(struct dss_pll *pll, const struct dss_pll_clock_info *cin
 	return 0;
 }
 
-bool dss_pll_hsdiv_calc(const struct dss_pll *pll, unsigned long clkdco,
+bool dss_pll_hsdiv_calc_a(const struct dss_pll *pll, unsigned long clkdco,
 		unsigned long out_min, unsigned long out_max,
 		dss_hsdiv_calc_func func, void *data)
 {
@@ -154,7 +206,11 @@ bool dss_pll_hsdiv_calc(const struct dss_pll *pll, unsigned long clkdco,
 	return false;
 }
 
-bool dss_pll_calc(const struct dss_pll *pll, unsigned long clkin,
+/*
+ * clkdco = clkin / n * m * 2
+ * clkoutX = clkdco / mX
+ */
+bool dss_pll_calc_a(const struct dss_pll *pll, unsigned long clkin,
 		unsigned long pll_min, unsigned long pll_max,
 		dss_pll_calc_func func, void *data)
 {
@@ -195,6 +251,71 @@ bool dss_pll_calc(const struct dss_pll *pll, unsigned long clkin,
 	return false;
 }
 
+/*
+ * This calculates a PLL config that will provide the target_clkout rate
+ * for clkout. Additionally clkdco rate will be the same as clkout rate
+ * when clkout rate is >= min_clkdco.
+ *
+ * clkdco = clkin / n * m + clkin / n * mf / 262144
+ * clkout = clkdco / m2
+ */
+bool dss_pll_calc_b(const struct dss_pll *pll, unsigned long clkin,
+	unsigned long target_clkout, struct dss_pll_clock_info *cinfo)
+{
+	unsigned long fint, clkdco, clkout;
+	unsigned long target_clkdco;
+	unsigned long min_dco;
+	unsigned n, m, mf, m2, sd;
+	const struct dss_pll_hw *hw = pll->hw;
+
+	DSSDBG("clkin %lu, target clkout %lu\n", clkin, target_clkout);
+
+	/* Fint */
+	n = DIV_ROUND_UP(clkin, hw->fint_max);
+	fint = clkin / n;
+
+	/* adjust m2 so that the clkdco will be high enough */
+	min_dco = roundup(hw->clkdco_min, fint);
+	m2 = DIV_ROUND_UP(min_dco, target_clkout);
+	if (m2 == 0)
+		m2 = 1;
+
+	target_clkdco = target_clkout * m2;
+	m = target_clkdco / fint;
+
+	clkdco = fint * m;
+
+	/* adjust clkdco with fractional mf */
+	if (WARN_ON(target_clkdco - clkdco > fint))
+		mf = 0;
+	else
+		mf = (u32)div_u64(262144ull * (target_clkdco - clkdco), fint);
+
+	if (mf > 0)
+		clkdco += (u32)div_u64((u64)mf * fint, 262144);
+
+	clkout = clkdco / m2;
+
+	/* sigma-delta */
+	sd = DIV_ROUND_UP(fint * m, 250000000);
+
+	DSSDBG("N = %u, M = %u, M.f = %u, M2 = %u, SD = %u\n",
+		n, m, mf, m2, sd);
+	DSSDBG("Fint %lu, clkdco %lu, clkout %lu\n", fint, clkdco, clkout);
+
+	cinfo->n = n;
+	cinfo->m = m;
+	cinfo->mf = mf;
+	cinfo->mX[0] = m2;
+	cinfo->sd = sd;
+
+	cinfo->fint = fint;
+	cinfo->clkdco = clkdco;
+	cinfo->clkout[0] = clkout;
+
+	return true;
+}
+
 static int wait_for_bit_change(void __iomem *reg, int bitnum, int value)
 {
 	unsigned long timeout;
diff --git a/drivers/gpu/drm/omapdrm/dss/rfbi.c b/drivers/gpu/drm/omapdrm/dss/rfbi.c
index 3796576dfadf..cd53566d75eb 100644
--- a/drivers/gpu/drm/omapdrm/dss/rfbi.c
+++ b/drivers/gpu/drm/omapdrm/dss/rfbi.c
@@ -38,7 +38,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
+#include "omapdss.h"
 #include "dss.h"
 
 struct rfbi_reg { u16 idx; };
diff --git a/drivers/gpu/drm/omapdrm/dss/sdi.c b/drivers/gpu/drm/omapdrm/dss/sdi.c
index cd6d3bfb041d..0a96c321ce62 100644
--- a/drivers/gpu/drm/omapdrm/dss/sdi.c
+++ b/drivers/gpu/drm/omapdrm/dss/sdi.c
@@ -29,7 +29,7 @@
 #include <linux/of.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
+#include "omapdss.h"
 #include "dss.h"
 
 static struct {
diff --git a/drivers/gpu/drm/omapdrm/dss/venc.c b/drivers/gpu/drm/omapdrm/dss/venc.c
index 08a2cc778ba9..6eedf2118708 100644
--- a/drivers/gpu/drm/omapdrm/dss/venc.c
+++ b/drivers/gpu/drm/omapdrm/dss/venc.c
@@ -37,8 +37,7 @@
 #include <linux/of.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 #include "dss_features.h"
 
diff --git a/drivers/gpu/drm/omapdrm/dss/video-pll.c b/drivers/gpu/drm/omapdrm/dss/video-pll.c
index b1ec59e42940..7429de928d4e 100644
--- a/drivers/gpu/drm/omapdrm/dss/video-pll.c
+++ b/drivers/gpu/drm/omapdrm/dss/video-pll.c
@@ -17,8 +17,7 @@
 #include <linux/platform_device.h>
 #include <linux/sched.h>
 
-#include <video/omapdss.h>
-
+#include "omapdss.h"
 #include "dss.h"
 #include "dss_features.h"
 
@@ -108,6 +107,8 @@ static const struct dss_pll_ops dss_pll_ops = {
 };
 
 static const struct dss_pll_hw dss_dra7_video_pll_hw = {
+	.type = DSS_PLL_TYPE_A,
+
 	.n_max = (1 << 8) - 1,
 	.m_max = (1 << 12) - 1,
 	.mX_max = (1 << 5) - 1,
@@ -124,6 +125,10 @@ static const struct dss_pll_hw dss_dra7_video_pll_hw = {
 	.mX_lsb[0] = 21,
 	.mX_msb[1] = 30,
 	.mX_lsb[1] = 26,
+	.mX_msb[2] = 4,
+	.mX_lsb[2] = 0,
+	.mX_msb[3] = 9,
+	.mX_lsb[3] = 5,
 
 	.has_refsel = true,
 };
diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c
index ce2d67b6a8c7..137fe690a0da 100644
--- a/drivers/gpu/drm/omapdrm/omap_connector.c
+++ b/drivers/gpu/drm/omapdrm/omap_connector.c
@@ -32,7 +32,6 @@
 struct omap_connector {
 	struct drm_connector base;
 	struct omap_dss_device *dssdev;
-	struct drm_encoder *encoder;
 	bool hdmi_mode;
 };
 
@@ -256,13 +255,6 @@ static int omap_connector_mode_valid(struct drm_connector *connector,
 	return ret;
 }
 
-struct drm_encoder *omap_connector_attached_encoder(
-		struct drm_connector *connector)
-{
-	struct omap_connector *omap_connector = to_omap_connector(connector);
-	return omap_connector->encoder;
-}
-
 static const struct drm_connector_funcs omap_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.reset = drm_atomic_helper_connector_reset,
@@ -276,7 +268,6 @@ static const struct drm_connector_funcs omap_connector_funcs = {
 static const struct drm_connector_helper_funcs omap_connector_helper_funcs = {
 	.get_modes = omap_connector_get_modes,
 	.mode_valid = omap_connector_mode_valid,
-	.best_encoder = omap_connector_attached_encoder,
 };
 
 /* initialize connector */
@@ -296,7 +287,6 @@ struct drm_connector *omap_connector_init(struct drm_device *dev,
 		goto fail;
 
 	omap_connector->dssdev = dssdev;
-	omap_connector->encoder = encoder;
 
 	connector = &omap_connector->base;
 
diff --git a/drivers/gpu/drm/omapdrm/omap_crtc.c b/drivers/gpu/drm/omapdrm/omap_crtc.c
index 075f2bb44867..180f644e861e 100644
--- a/drivers/gpu/drm/omapdrm/omap_crtc.c
+++ b/drivers/gpu/drm/omapdrm/omap_crtc.c
@@ -372,6 +372,20 @@ static void omap_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	copy_timings_drm_to_omap(&omap_crtc->timings, mode);
 }
 
+static int omap_crtc_atomic_check(struct drm_crtc *crtc,
+				struct drm_crtc_state *state)
+{
+	if (state->color_mgmt_changed && state->gamma_lut) {
+		uint length = state->gamma_lut->length /
+			sizeof(struct drm_color_lut);
+
+		if (length < 2)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void omap_crtc_atomic_begin(struct drm_crtc *crtc,
                                   struct drm_crtc_state *old_crtc_state)
 {
@@ -384,6 +398,32 @@ static void omap_crtc_atomic_flush(struct drm_crtc *crtc,
 
 	WARN_ON(omap_crtc->vblank_irq.registered);
 
+	if (crtc->state->color_mgmt_changed) {
+		struct drm_color_lut *lut = NULL;
+		uint length = 0;
+
+		if (crtc->state->gamma_lut) {
+			lut = (struct drm_color_lut *)
+				crtc->state->gamma_lut->data;
+			length = crtc->state->gamma_lut->length /
+				sizeof(*lut);
+		}
+		dispc_mgr_set_gamma(omap_crtc->channel, lut, length);
+	}
+
+	if (crtc->state->color_mgmt_changed) {
+		struct drm_color_lut *lut = NULL;
+		uint length = 0;
+
+		if (crtc->state->gamma_lut) {
+			lut = (struct drm_color_lut *)
+				crtc->state->gamma_lut->data;
+			length = crtc->state->gamma_lut->length /
+				sizeof(*lut);
+		}
+		dispc_mgr_set_gamma(omap_crtc->channel, lut, length);
+	}
+
 	if (dispc_mgr_is_enabled(omap_crtc->channel)) {
 
 		DBG("%s: GO", omap_crtc->name);
@@ -460,6 +500,7 @@ static const struct drm_crtc_funcs omap_crtc_funcs = {
 	.set_config = drm_atomic_helper_set_config,
 	.destroy = omap_crtc_destroy,
 	.page_flip = drm_atomic_helper_page_flip,
+	.gamma_set = drm_atomic_helper_legacy_gamma_set,
 	.set_property = drm_atomic_helper_crtc_set_property,
 	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
@@ -471,6 +512,7 @@ static const struct drm_crtc_helper_funcs omap_crtc_helper_funcs = {
 	.mode_set_nofb = omap_crtc_mode_set_nofb,
 	.disable = omap_crtc_disable,
 	.enable = omap_crtc_enable,
+	.atomic_check = omap_crtc_atomic_check,
 	.atomic_begin = omap_crtc_atomic_begin,
 	.atomic_flush = omap_crtc_atomic_flush,
 };
@@ -534,6 +576,20 @@ struct drm_crtc *omap_crtc_init(struct drm_device *dev,
 
 	drm_crtc_helper_add(crtc, &omap_crtc_helper_funcs);
 
+	/* The dispc API adapts to what ever size, but the HW supports
+	 * 256 element gamma table for LCDs and 1024 element table for
+	 * OMAP_DSS_CHANNEL_DIGIT. X server assumes 256 element gamma
+	 * tables so lets use that. Size of HW gamma table can be
+	 * extracted with dispc_mgr_gamma_size(). If it returns 0
+	 * gamma table is not supprted.
+	 */
+	if (dispc_mgr_gamma_size(channel)) {
+		uint gamma_lut_size = 256;
+
+		drm_crtc_enable_color_mgmt(crtc, 0, false, gamma_lut_size);
+		drm_mode_crtc_set_gamma_size(crtc, gamma_lut_size);
+	}
+
 	omap_plane_install_properties(crtc->primary, &crtc->base);
 
 	omap_crtcs[channel] = omap_crtc;
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index d86f5479345b..26c6134eb744 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -142,8 +142,9 @@ static int omap_atomic_commit(struct drm_device *dev,
 {
 	struct omap_drm_private *priv = dev->dev_private;
 	struct omap_atomic_state_commit *commit;
-	unsigned int i;
-	int ret;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	int i, ret;
 
 	ret = drm_atomic_helper_prepare_planes(dev, state);
 	if (ret)
@@ -163,10 +164,8 @@ static int omap_atomic_commit(struct drm_device *dev,
 	/* Wait until all affected CRTCs have completed previous commits and
 	 * mark them as pending.
 	 */
-	for (i = 0; i < dev->mode_config.num_crtc; ++i) {
-		if (state->crtcs[i])
-			commit->crtcs |= 1 << drm_crtc_index(state->crtcs[i]);
-	}
+	for_each_crtc_in_state(state, crtc, crtc_state, i)
+		commit->crtcs |= drm_crtc_mask(crtc);
 
 	wait_event(priv->commit.wait, !omap_atomic_is_pending(priv, commit));
 
@@ -175,7 +174,7 @@ static int omap_atomic_commit(struct drm_device *dev,
 	spin_unlock(&priv->commit.lock);
 
 	/* Swap the state, this is the point of no return. */
-	drm_atomic_helper_swap_state(dev, state);
+	drm_atomic_helper_swap_state(state, true);
 
 	if (nonblock)
 		schedule_work(&commit->work);
@@ -203,6 +202,8 @@ static int get_connector_type(struct omap_dss_device *dssdev)
 		return DRM_MODE_CONNECTOR_HDMIA;
 	case OMAP_DISPLAY_TYPE_DVI:
 		return DRM_MODE_CONNECTOR_DVID;
+	case OMAP_DISPLAY_TYPE_DSI:
+		return DRM_MODE_CONNECTOR_DSI;
 	default:
 		return DRM_MODE_CONNECTOR_Unknown;
 	}
@@ -800,7 +801,6 @@ static struct drm_driver omap_drm_driver = {
 	.unload = dev_unload,
 	.open = dev_open,
 	.lastclose = dev_lastclose,
-	.set_busid = drm_platform_set_busid,
 	.get_vblank_counter = drm_vblank_no_hw_counter,
 	.enable_vblank = omap_irq_enable_vblank,
 	.disable_vblank = omap_irq_disable_vblank,
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h
index 3f823c368912..dcc30a98b9d4 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.h
+++ b/drivers/gpu/drm/omapdrm/omap_drv.h
@@ -24,7 +24,6 @@
 #include <linux/platform_data/omap_drm.h>
 #include <linux/types.h>
 #include <linux/wait.h>
-#include <video/omapdss.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
@@ -183,7 +182,6 @@ struct drm_framebuffer *omap_framebuffer_create(struct drm_device *dev,
 		struct drm_file *file, const struct drm_mode_fb_cmd2 *mode_cmd);
 struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev,
 		const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos);
-struct drm_gem_object *omap_framebuffer_bo(struct drm_framebuffer *fb, int p);
 int omap_framebuffer_pin(struct drm_framebuffer *fb);
 void omap_framebuffer_unpin(struct drm_framebuffer *fb);
 void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
@@ -231,7 +229,6 @@ int omap_gem_rotated_paddr(struct drm_gem_object *obj, uint32_t orient,
 		int x, int y, dma_addr_t *paddr);
 uint64_t omap_gem_mmap_offset(struct drm_gem_object *obj);
 size_t omap_gem_mmap_size(struct drm_gem_object *obj);
-int omap_gem_tiled_size(struct drm_gem_object *obj, uint16_t *w, uint16_t *h);
 int omap_gem_tiled_stride(struct drm_gem_object *obj, uint32_t orient);
 
 struct dma_buf *omap_gem_prime_export(struct drm_device *dev,
@@ -239,17 +236,6 @@ struct dma_buf *omap_gem_prime_export(struct drm_device *dev,
 struct drm_gem_object *omap_gem_prime_import(struct drm_device *dev,
 		struct dma_buf *buffer);
 
-static inline int align_pitch(int pitch, int width, int bpp)
-{
-	int bytespp = (bpp + 7) / 8;
-	/* in case someone tries to feed us a completely bogus stride: */
-	pitch = max(pitch, width * bytespp);
-	/* PVR needs alignment to 8 pixels.. right now that is the most
-	 * restrictive stride requirement..
-	 */
-	return roundup(pitch, 8 * bytespp);
-}
-
 /* map crtc to vblank mask */
 uint32_t pipe2vbl(struct drm_crtc *crtc);
 struct omap_dss_device *omap_encoder_get_dssdev(struct drm_encoder *encoder);
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index f84570d1636c..31f5178c22c7 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -115,24 +115,16 @@ static void omap_framebuffer_destroy(struct drm_framebuffer *fb)
 
 	for (i = 0; i < n; i++) {
 		struct plane *plane = &omap_fb->planes[i];
-		if (plane->bo)
-			drm_gem_object_unreference_unlocked(plane->bo);
+
+		drm_gem_object_unreference_unlocked(plane->bo);
 	}
 
 	kfree(omap_fb);
 }
 
-static int omap_framebuffer_dirty(struct drm_framebuffer *fb,
-		struct drm_file *file_priv, unsigned flags, unsigned color,
-		struct drm_clip_rect *clips, unsigned num_clips)
-{
-	return 0;
-}
-
 static const struct drm_framebuffer_funcs omap_framebuffer_funcs = {
 	.create_handle = omap_framebuffer_create_handle,
 	.destroy = omap_framebuffer_destroy,
-	.dirty = omap_framebuffer_dirty,
 };
 
 static uint32_t get_linear_addr(struct plane *plane,
@@ -320,14 +312,6 @@ void omap_framebuffer_unpin(struct drm_framebuffer *fb)
 	mutex_unlock(&omap_fb->lock);
 }
 
-struct drm_gem_object *omap_framebuffer_bo(struct drm_framebuffer *fb, int p)
-{
-	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
-	if (p >= drm_format_num_planes(fb->pixel_format))
-		return NULL;
-	return omap_fb->planes[p].bo;
-}
-
 /* iterate thru all the connectors, returning ones that are attached
  * to the same fb..
  */
diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c
index 89da41ac64d2..adb10fbe918d 100644
--- a/drivers/gpu/drm/omapdrm/omap_fbdev.c
+++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c
@@ -125,9 +125,8 @@ static int omap_fbdev_create(struct drm_fb_helper *helper,
 	mode_cmd.width = sizes->surface_width;
 	mode_cmd.height = sizes->surface_height;
 
-	mode_cmd.pitches[0] = align_pitch(
-			mode_cmd.width * ((sizes->surface_bpp + 7) / 8),
-			mode_cmd.width, sizes->surface_bpp);
+	mode_cmd.pitches[0] =
+			DIV_ROUND_UP(mode_cmd.width * sizes->surface_bpp, 8);
 
 	fbdev->ywrap_enabled = priv->has_dmm && ywrap_enabled;
 	if (fbdev->ywrap_enabled) {
@@ -280,9 +279,6 @@ struct drm_fb_helper *omap_fbdev_init(struct drm_device *dev)
 	if (ret)
 		goto fini;
 
-	/* disable all the possible outputs/crtcs before entering KMS mode */
-	drm_helper_disable_unused_functions(dev);
-
 	ret = drm_fb_helper_initial_config(helper, 32);
 	if (ret)
 		goto fini;
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 0dbd0f03f9bd..505dee0db973 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -383,18 +383,6 @@ size_t omap_gem_mmap_size(struct drm_gem_object *obj)
 	return size;
 }
 
-/* get tiled size, returns -EINVAL if not tiled buffer */
-int omap_gem_tiled_size(struct drm_gem_object *obj, uint16_t *w, uint16_t *h)
-{
-	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	if (omap_obj->flags & OMAP_BO_TILED) {
-		*w = omap_obj->width;
-		*h = omap_obj->height;
-		return 0;
-	}
-	return -EINVAL;
-}
-
 /* -----------------------------------------------------------------------------
  * Fault Handling
  */
@@ -661,7 +649,8 @@ int omap_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 {
 	union omap_gem_size gsize;
 
-	args->pitch = align_pitch(0, args->width, args->bpp);
+	args->pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
+
 	args->size = PAGE_ALIGN(args->pitch * args->height);
 
 	gsize = (union omap_gem_size){
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 3a7bdf1c842b..85143d1b9b31 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -168,6 +168,7 @@ static int panel_simple_disable(struct drm_panel *panel)
 
 	if (p->backlight) {
 		p->backlight->props.power = FB_BLANK_POWERDOWN;
+		p->backlight->props.state |= BL_CORE_FBBLANK;
 		backlight_update_status(p->backlight);
 	}
 
@@ -235,6 +236,7 @@ static int panel_simple_enable(struct drm_panel *panel)
 		msleep(p->desc->delay.enable);
 
 	if (p->backlight) {
+		p->backlight->props.state &= ~BL_CORE_FBBLANK;
 		p->backlight->props.power = FB_BLANK_UNBLANK;
 		backlight_update_status(p->backlight);
 	}
@@ -964,8 +966,8 @@ static const struct panel_desc innolux_zj070na_01p = {
 	.num_modes = 1,
 	.bpc = 6,
 	.size = {
-		.width = 1024,
-		.height = 600,
+		.width = 154,
+		.height = 90,
 	},
 };
 
@@ -1017,6 +1019,51 @@ static const struct panel_desc lg_lb070wv8 = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
 };
 
+static const struct drm_display_mode lg_lp079qx1_sp0v_mode = {
+	.clock = 200000,
+	.hdisplay = 1536,
+	.hsync_start = 1536 + 12,
+	.hsync_end = 1536 + 12 + 16,
+	.htotal = 1536 + 12 + 16 + 48,
+	.vdisplay = 2048,
+	.vsync_start = 2048 + 8,
+	.vsync_end = 2048 + 8 + 4,
+	.vtotal = 2048 + 8 + 4 + 8,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc lg_lp079qx1_sp0v = {
+	.modes = &lg_lp079qx1_sp0v_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 129,
+		.height = 171,
+	},
+};
+
+static const struct drm_display_mode lg_lp097qx1_spa1_mode = {
+	.clock = 205210,
+	.hdisplay = 2048,
+	.hsync_start = 2048 + 150,
+	.hsync_end = 2048 + 150 + 5,
+	.htotal = 2048 + 150 + 5 + 5,
+	.vdisplay = 1536,
+	.vsync_start = 1536 + 3,
+	.vsync_end = 1536 + 3 + 1,
+	.vtotal = 1536 + 3 + 1 + 9,
+	.vrefresh = 60,
+};
+
+static const struct panel_desc lg_lp097qx1_spa1 = {
+	.modes = &lg_lp097qx1_spa1_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 208,
+		.height = 147,
+	},
+};
+
 static const struct drm_display_mode lg_lp120up1_mode = {
 	.clock = 162300,
 	.hdisplay = 1920,
@@ -1224,6 +1271,28 @@ static const struct panel_desc qd43003c0_40 = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
 };
 
+static const struct drm_display_mode samsung_lsn122dl01_c01_mode = {
+	.clock = 271560,
+	.hdisplay = 2560,
+	.hsync_start = 2560 + 48,
+	.hsync_end = 2560 + 48 + 32,
+	.htotal = 2560 + 48 + 32 + 80,
+	.vdisplay = 1600,
+	.vsync_start = 1600 + 2,
+	.vsync_end = 1600 + 2 + 5,
+	.vtotal = 1600 + 2 + 5 + 57,
+	.vrefresh = 60,
+};
+
+static const struct panel_desc samsung_lsn122dl01_c01 = {
+	.modes = &samsung_lsn122dl01_c01_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 263,
+		.height = 164,
+	},
+};
+
 static const struct drm_display_mode samsung_ltn101nt05_mode = {
 	.clock = 54030,
 	.hdisplay = 1024,
@@ -1242,8 +1311,8 @@ static const struct panel_desc samsung_ltn101nt05 = {
 	.num_modes = 1,
 	.bpc = 6,
 	.size = {
-		.width = 1024,
-		.height = 600,
+		.width = 223,
+		.height = 125,
 	},
 };
 
@@ -1270,6 +1339,53 @@ static const struct panel_desc samsung_ltn140at29_301 = {
 	},
 };
 
+static const struct display_timing sharp_lq101k1ly04_timing = {
+	.pixelclock = { 60000000, 65000000, 80000000 },
+	.hactive = { 1280, 1280, 1280 },
+	.hfront_porch = { 20, 20, 20 },
+	.hback_porch = { 20, 20, 20 },
+	.hsync_len = { 10, 10, 10 },
+	.vactive = { 800, 800, 800 },
+	.vfront_porch = { 4, 4, 4 },
+	.vback_porch = { 4, 4, 4 },
+	.vsync_len = { 4, 4, 4 },
+	.flags = DISPLAY_FLAGS_PIXDATA_POSEDGE,
+};
+
+static const struct panel_desc sharp_lq101k1ly04 = {
+	.timings = &sharp_lq101k1ly04_timing,
+	.num_timings = 1,
+	.bpc = 8,
+	.size = {
+		.width = 217,
+		.height = 136,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA,
+};
+
+static const struct drm_display_mode sharp_lq123p1jx31_mode = {
+	.clock = 252750,
+	.hdisplay = 2400,
+	.hsync_start = 2400 + 48,
+	.hsync_end = 2400 + 48 + 32,
+	.htotal = 2400 + 48 + 32 + 80,
+	.vdisplay = 1600,
+	.vsync_start = 1600 + 3,
+	.vsync_end = 1600 + 3 + 10,
+	.vtotal = 1600 + 3 + 10 + 33,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc sharp_lq123p1jx31 = {
+	.modes = &sharp_lq123p1jx31_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 259,
+		.height = 173,
+	},
+};
+
 static const struct drm_display_mode shelly_sca07010_bfn_lnn_mode = {
 	.clock = 33300,
 	.hdisplay = 800,
@@ -1293,6 +1409,29 @@ static const struct panel_desc shelly_sca07010_bfn_lnn = {
 	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
 };
 
+static const struct drm_display_mode starry_kr122ea0sra_mode = {
+	.clock = 147000,
+	.hdisplay = 1920,
+	.hsync_start = 1920 + 16,
+	.hsync_end = 1920 + 16 + 16,
+	.htotal = 1920 + 16 + 16 + 32,
+	.vdisplay = 1200,
+	.vsync_start = 1200 + 15,
+	.vsync_end = 1200 + 15 + 2,
+	.vtotal = 1200 + 15 + 2 + 18,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc starry_kr122ea0sra = {
+	.modes = &starry_kr122ea0sra_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 263,
+		.height = 164,
+	},
+};
+
 static const struct drm_display_mode tpk_f07a_0102_mode = {
 	.clock = 33260,
 	.hdisplay = 800,
@@ -1457,6 +1596,12 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "lg,lb070wv8",
 		.data = &lg_lb070wv8,
 	}, {
+		.compatible = "lg,lp079qx1-sp0v",
+		.data = &lg_lp079qx1_sp0v,
+	}, {
+		.compatible = "lg,lp097qx1-spa1",
+		.data = &lg_lp097qx1_spa1,
+	}, {
 		.compatible = "lg,lp120up1",
 		.data = &lg_lp120up1,
 	}, {
@@ -1481,15 +1626,27 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "qiaodian,qd43003c0-40",
 		.data = &qd43003c0_40,
 	}, {
+		.compatible = "samsung,lsn122dl01-c01",
+		.data = &samsung_lsn122dl01_c01,
+	}, {
 		.compatible = "samsung,ltn101nt05",
 		.data = &samsung_ltn101nt05,
 	}, {
 		.compatible = "samsung,ltn140at29-301",
 		.data = &samsung_ltn140at29_301,
 	}, {
+		.compatible = "sharp,lq101k1ly04",
+		.data = &sharp_lq101k1ly04,
+	}, {
+		.compatible = "sharp,lq123p1jx31",
+		.data = &sharp_lq123p1jx31,
+	}, {
 		.compatible = "shelly,sca07010-bfn-lnn",
 		.data = &shelly_sca07010_bfn_lnn,
 	}, {
+		.compatible = "starry,kr122ea0sra",
+		.data = &starry_kr122ea0sra,
+	}, {
 		.compatible = "tpk,f07a-0102",
 		.data = &tpk_f07a_0102,
 	}, {
@@ -1701,7 +1858,6 @@ static const struct panel_desc_dsi panasonic_vvx10f004b00 = {
 	.lanes = 4,
 };
 
-
 static const struct of_device_id dsi_of_match[] = {
 	{
 		.compatible = "auo,b080uan01",
diff --git a/drivers/gpu/drm/qxl/Kconfig b/drivers/gpu/drm/qxl/Kconfig
index 38c2bb72e456..da45b11b66b8 100644
--- a/drivers/gpu/drm/qxl/Kconfig
+++ b/drivers/gpu/drm/qxl/Kconfig
@@ -1,12 +1,7 @@
 config DRM_QXL
 	tristate "QXL virtual GPU"
 	depends on DRM && PCI
-	select FB_SYS_FILLRECT
-	select FB_SYS_COPYAREA
-	select FB_SYS_IMAGEBLIT
-	select FB_DEFERRED_IO
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_TTM
 	select CRC32
 	help
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index b5d4b41361bd..04270f5d110c 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -203,7 +203,7 @@ qxl_push_cursor_ring_release(struct qxl_device *qdev, struct qxl_release *releas
 bool qxl_queue_garbage_collect(struct qxl_device *qdev, bool flush)
 {
 	if (!qxl_check_idle(qdev->release_ring)) {
-		queue_work(qdev->gc_queue, &qdev->gc_work);
+		schedule_work(&qdev->gc_work);
 		if (flush)
 			flush_work(&qdev->gc_work);
 		return true;
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 8b5d54385892..3aef12742a53 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -221,7 +221,6 @@ static int qxl_crtc_page_flip(struct drm_crtc *crtc,
 {
 	struct drm_device *dev = crtc->dev;
 	struct qxl_device *qdev = dev->dev_private;
-	struct qxl_crtc *qcrtc = to_qxl_crtc(crtc);
 	struct qxl_framebuffer *qfb_src = to_qxl_framebuffer(fb);
 	struct qxl_framebuffer *qfb_old = to_qxl_framebuffer(crtc->primary->fb);
 	struct qxl_bo *bo_old = gem_to_qxl_bo(qfb_old->obj);
@@ -252,14 +251,14 @@ static int qxl_crtc_page_flip(struct drm_crtc *crtc,
 	qxl_draw_dirty_fb(qdev, qfb_src, bo, 0, 0,
 			  &norect, one_clip_rect, inc);
 
-	drm_vblank_get(dev, qcrtc->index);
+	drm_crtc_vblank_get(crtc);
 
 	if (event) {
 		spin_lock_irqsave(&dev->event_lock, flags);
-		drm_send_vblank_event(dev, qcrtc->index, event);
+		drm_crtc_send_vblank_event(crtc, event);
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 	}
-	drm_vblank_put(dev, qcrtc->index);
+	drm_crtc_vblank_put(crtc);
 
 	ret = qxl_bo_reserve(bo, false);
 	if (!ret) {
@@ -469,8 +468,7 @@ void qxl_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct qxl_framebuffer *qxl_fb = to_qxl_framebuffer(fb);
 
-	if (qxl_fb->obj)
-		drm_gem_object_unreference_unlocked(qxl_fb->obj);
+	drm_gem_object_unreference_unlocked(qxl_fb->obj);
 	drm_framebuffer_cleanup(fb);
 	kfree(qxl_fb);
 }
@@ -730,7 +728,6 @@ static int qdev_crtc_init(struct drm_device *dev, int crtc_id)
 
 	drm_crtc_init(dev, &qxl_crtc->base, &qxl_crtc_funcs);
 	qxl_crtc->index = crtc_id;
-	drm_mode_crtc_set_gamma_size(&qxl_crtc->base, 256);
 	drm_crtc_helper_add(&qxl_crtc->base, &qxl_crtc_helper_funcs);
 	return 0;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_draw.c b/drivers/gpu/drm/qxl/qxl_draw.c
index 56e1d633875e..ffe885395145 100644
--- a/drivers/gpu/drm/qxl/qxl_draw.c
+++ b/drivers/gpu/drm/qxl/qxl_draw.c
@@ -37,7 +37,6 @@ static int alloc_clips(struct qxl_device *qdev,
  * the qxl_clip_rects. This is *not* the same as the memory allocated
  * on the device, it is offset to qxl_clip_rects.chunk.data */
 static struct qxl_rect *drawable_set_clipping(struct qxl_device *qdev,
-					      struct qxl_drawable *drawable,
 					      unsigned num_clips,
 					      struct qxl_bo *clips_bo)
 {
@@ -136,6 +135,8 @@ static int qxl_palette_create_1bit(struct qxl_bo *palette_bo,
 				 * correctly globaly, since that would require
 				 * tracking all of our palettes. */
 	ret = qxl_bo_kmap(palette_bo, (void **)&pal);
+	if (ret)
+		return ret;
 	pal->num_ents = 2;
 	pal->unique = unique++;
 	if (visual == FB_VISUAL_TRUECOLOR || visual == FB_VISUAL_DIRECTCOLOR) {
@@ -349,7 +350,7 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev,
 	if (ret)
 		goto out_release_backoff;
 
-	rects = drawable_set_clipping(qdev, drawable, num_clips, clips_bo);
+	rects = drawable_set_clipping(qdev, num_clips, clips_bo);
 	if (!rects)
 		goto out_release_backoff;
 
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index dc9df5fe50ba..460bbceae297 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -256,7 +256,7 @@ static struct drm_driver qxl_driver = {
 	.gem_prime_vmap = qxl_gem_prime_vmap,
 	.gem_prime_vunmap = qxl_gem_prime_vunmap,
 	.gem_prime_mmap = qxl_gem_prime_mmap,
-	.gem_free_object = qxl_gem_object_free,
+	.gem_free_object_unlocked = qxl_gem_object_free,
 	.gem_open_object = qxl_gem_object_open,
 	.gem_close_object = qxl_gem_object_close,
 	.fops = &qxl_fops,
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 3ad6604b34ce..8e633caa4078 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -321,7 +321,6 @@ struct qxl_device {
 	struct qxl_bo *current_release_bo[3];
 	int current_release_bo_offset[3];
 
-	struct workqueue_struct *gc_queue;
 	struct work_struct gc_work;
 
 	struct drm_property *hotplug_mode_update_property;
diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c
index 5ea57f6320b8..df2657051afd 100644
--- a/drivers/gpu/drm/qxl/qxl_fb.c
+++ b/drivers/gpu/drm/qxl/qxl_fb.c
@@ -131,10 +131,6 @@ static int qxlfb_create_pinned_object(struct qxl_fbdev *qfbdev,
 	int ret;
 	int aligned_size, size;
 	int height = mode_cmd->height;
-	int bpp;
-	int depth;
-
-	drm_fb_get_bpp_depth(mode_cmd->pixel_format, &bpp, &depth);
 
 	size = mode_cmd->pitches[0] * height;
 	aligned_size = ALIGN(size, PAGE_SIZE);
diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c
index 2319800b7add..e642242728c0 100644
--- a/drivers/gpu/drm/qxl/qxl_kms.c
+++ b/drivers/gpu/drm/qxl/qxl_kms.c
@@ -258,7 +258,6 @@ static int qxl_device_init(struct qxl_device *qdev,
 		 (unsigned long)qdev->surfaceram_size);
 
 
-	qdev->gc_queue = create_singlethread_workqueue("qxl_gc");
 	INIT_WORK(&qdev->gc_work, qxl_gc_work);
 
 	return 0;
@@ -270,10 +269,7 @@ static void qxl_device_fini(struct qxl_device *qdev)
 		qxl_bo_unref(&qdev->current_release_bo[0]);
 	if (qdev->current_release_bo[1])
 		qxl_bo_unref(&qdev->current_release_bo[1]);
-	flush_workqueue(qdev->gc_queue);
-	destroy_workqueue(qdev->gc_queue);
-	qdev->gc_queue = NULL;
-
+	flush_work(&qdev->gc_work);
 	qxl_ring_free(qdev->command_ring);
 	qxl_ring_free(qdev->cursor_ring);
 	qxl_ring_free(qdev->release_ring);
@@ -310,10 +306,6 @@ int qxl_driver_load(struct drm_device *dev, unsigned long flags)
 	struct qxl_device *qdev;
 	int r;
 
-	/* require kms */
-	if (!drm_core_check_feature(dev, DRIVER_MODESET))
-		return -ENODEV;
-
 	qdev = kzalloc(sizeof(struct qxl_device), GFP_KERNEL);
 	if (qdev == NULL)
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 4efa8e261baf..f599cd073b72 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -96,7 +96,7 @@ retry:
 			return 0;
 
 		if (have_drawable_releases && sc > 300) {
-			FENCE_WARN(fence, "failed to wait on release %d "
+			FENCE_WARN(fence, "failed to wait on release %llu "
 					  "after spincount %d\n",
 					  fence->context & ~0xf0000000, sc);
 			goto signaled;
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 0738d74c8d04..d50c9679e631 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -350,11 +350,19 @@ static int qxl_bo_move(struct ttm_buffer_object *bo,
 		       struct ttm_mem_reg *new_mem)
 {
 	struct ttm_mem_reg *old_mem = &bo->mem;
+	int ret;
+
+	ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
+	if (ret)
+		return ret;
+
+
 	if (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL) {
 		qxl_move_null(bo, new_mem);
 		return 0;
 	}
-	return ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
+	return ttm_bo_move_memcpy(bo, evict, interruptible,
+				  no_wait_gpu, new_mem);
 }
 
 static void qxl_bo_move_notify(struct ttm_buffer_object *bo,
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 259cd6e6d71c..a97abc8af657 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -276,14 +276,14 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 			atombios_enable_crtc_memreq(crtc, ATOM_ENABLE);
 		atombios_blank_crtc(crtc, ATOM_DISABLE);
 		if (dev->num_crtcs > radeon_crtc->crtc_id)
-			drm_vblank_on(dev, radeon_crtc->crtc_id);
+			drm_crtc_vblank_on(crtc);
 		radeon_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
 		if (dev->num_crtcs > radeon_crtc->crtc_id)
-			drm_vblank_off(dev, radeon_crtc->crtc_id);
+			drm_crtc_vblank_off(crtc);
 		if (radeon_crtc->enabled)
 			atombios_blank_crtc(crtc, ATOM_ENABLE);
 		if (ASIC_IS_DCE3(rdev) && !ASIC_IS_DCE6(rdev))
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 587cae4e73c9..56bb758f4e33 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -120,6 +120,7 @@ atombios_set_backlight_level(struct radeon_encoder *radeon_encoder, u8 level)
 		case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
 		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
 		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
+		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3:
 			if (dig->backlight_level == 0)
 				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_LCD_BLOFF, 0, 0);
 			else {
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 35e0fc3ae8a7..7ba450832e6b 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -3843,7 +3843,10 @@ static void ci_find_dpm_states_clocks_in_dpm_table(struct radeon_device *rdev,
 	if (i >= sclk_table->count) {
 		pi->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK;
 	} else {
-		/* XXX check display min clock requirements */
+		/* XXX The current code always reprogrammed the sclk levels,
+		 * but we don't currently handle disp sclk requirements
+		 * so just skip it.
+		 */
 		if (CISLAND_MINIMUM_ENGINE_CLOCK != CISLAND_MINIMUM_ENGINE_CLOCK)
 			pi->need_update_smu7_dpm_table |= DPMTABLE_UPDATE_SCLK;
 	}
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index ba192a35c607..0c1b9ff433af 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -53,6 +53,7 @@ MODULE_FIRMWARE("radeon/bonaire_mc.bin");
 MODULE_FIRMWARE("radeon/bonaire_rlc.bin");
 MODULE_FIRMWARE("radeon/bonaire_sdma.bin");
 MODULE_FIRMWARE("radeon/bonaire_smc.bin");
+MODULE_FIRMWARE("radeon/bonaire_k_smc.bin");
 
 MODULE_FIRMWARE("radeon/HAWAII_pfp.bin");
 MODULE_FIRMWARE("radeon/HAWAII_me.bin");
@@ -72,6 +73,7 @@ MODULE_FIRMWARE("radeon/hawaii_mc.bin");
 MODULE_FIRMWARE("radeon/hawaii_rlc.bin");
 MODULE_FIRMWARE("radeon/hawaii_sdma.bin");
 MODULE_FIRMWARE("radeon/hawaii_smc.bin");
+MODULE_FIRMWARE("radeon/hawaii_k_smc.bin");
 
 MODULE_FIRMWARE("radeon/KAVERI_pfp.bin");
 MODULE_FIRMWARE("radeon/KAVERI_me.bin");
@@ -1990,12 +1992,17 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	int new_fw = 0;
 	int err;
 	int num_fw;
+	bool new_smc = false;
 
 	DRM_DEBUG("\n");
 
 	switch (rdev->family) {
 	case CHIP_BONAIRE:
 		chip_name = "BONAIRE";
+		if ((rdev->pdev->revision == 0x80) ||
+		    (rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->device == 0x665f))
+			new_smc = true;
 		new_chip_name = "bonaire";
 		pfp_req_size = CIK_PFP_UCODE_SIZE * 4;
 		me_req_size = CIK_ME_UCODE_SIZE * 4;
@@ -2010,6 +2017,8 @@ static int cik_init_microcode(struct radeon_device *rdev)
 		break;
 	case CHIP_HAWAII:
 		chip_name = "HAWAII";
+		if (rdev->pdev->revision == 0x80)
+			new_smc = true;
 		new_chip_name = "hawaii";
 		pfp_req_size = CIK_PFP_UCODE_SIZE * 4;
 		me_req_size = CIK_ME_UCODE_SIZE * 4;
@@ -2259,7 +2268,10 @@ static int cik_init_microcode(struct radeon_device *rdev)
 			}
 		}
 
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", new_chip_name);
+		if (new_smc)
+			snprintf(fw_name, sizeof(fw_name), "radeon/%s_k_smc.bin", new_chip_name);
+		else
+			snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", new_chip_name);
 		err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
 		if (err) {
 			snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
@@ -8354,7 +8366,8 @@ static int cik_startup(struct radeon_device *rdev)
 		}
 	}
 	rdev->rlc.cs_data = ci_cs_data;
-	rdev->rlc.cp_table_size = CP_ME_TABLE_SIZE * 5 * 4;
+	rdev->rlc.cp_table_size = ALIGN(CP_ME_TABLE_SIZE * 5 * 4, 2048); /* CP JT */
+	rdev->rlc.cp_table_size += 64 * 1024; /* GDS */
 	r = sumo_rlc_init(rdev);
 	if (r) {
 		DRM_ERROR("Failed to init rlc BOs!\n");
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 0d3f744de35a..d960d3915408 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -2209,6 +2209,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		}
 		break;
 	}
+	case PACKET3_PFP_SYNC_ME:
+		if (pkt->count) {
+			DRM_ERROR("bad PFP_SYNC_ME\n");
+			return -EINVAL;
+		}
+		break;
 	case PACKET3_SURFACE_SYNC:
 		if (pkt->count != 3) {
 			DRM_ERROR("bad SURFACE_SYNC\n");
@@ -3381,6 +3387,7 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev,
 	case PACKET3_MPEG_INDEX:
 	case PACKET3_WAIT_REG_MEM:
 	case PACKET3_MEM_WRITE:
+	case PACKET3_PFP_SYNC_ME:
 	case PACKET3_SURFACE_SYNC:
 	case PACKET3_EVENT_WRITE:
 	case PACKET3_EVENT_WRITE_EOP:
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 0b174e14e9a6..c8e3d394cde7 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -1624,6 +1624,7 @@
 		 */
 #              define PACKET3_CP_DMA_CMD_SAIC      (1 << 28)
 #              define PACKET3_CP_DMA_CMD_DAIC      (1 << 29)
+#define	PACKET3_PFP_SYNC_ME				0x42
 #define	PACKET3_SURFACE_SYNC				0x43
 #              define PACKET3_CB0_DEST_BASE_ENA    (1 << 6)
 #              define PACKET3_CB1_DEST_BASE_ENA    (1 << 7)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 80b24a495d6c..5633ee3eb46e 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2386,7 +2386,7 @@ struct radeon_device {
 	struct radeon_mman		mman;
 	struct radeon_fence_driver	fence_drv[RADEON_NUM_RINGS];
 	wait_queue_head_t		fence_queue;
-	unsigned			fence_context;
+	u64				fence_context;
 	struct mutex			ring_lock;
 	struct radeon_ring		ring[RADEON_NUM_RINGS];
 	bool				ib_pool_ready;
diff --git a/drivers/gpu/drm/radeon/radeon_acpi.c b/drivers/gpu/drm/radeon/radeon_acpi.c
index 59acd0e5c2c6..31c9a92d6a1b 100644
--- a/drivers/gpu/drm/radeon/radeon_acpi.c
+++ b/drivers/gpu/drm/radeon/radeon_acpi.c
@@ -741,13 +741,6 @@ int radeon_acpi_init(struct radeon_device *rdev)
 		}
 
 		atif->encoder_for_bl = target;
-		if (!target) {
-			/* Brightness change notification is enabled, but we
-			 * didn't find a backlight controller, this should
-			 * never happen.
-			 */
-			DRM_ERROR("Cannot find a backlight controller\n");
-		}
 	}
 
 	if (atif->functions.sbios_requests && !atif->functions.system_params) {
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index f8097a0e7a79..5df3ec73021b 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1155,7 +1155,7 @@ bool radeon_atom_get_clock_info(struct drm_device *dev)
 		    le16_to_cpu(firmware_info->info.usReferenceClock);
 		p1pll->reference_div = 0;
 
-		if (crev < 2)
+		if ((frev < 2) && (crev < 2))
 			p1pll->pll_out_min =
 				le16_to_cpu(firmware_info->info.usMinPixelClockPLL_Output);
 		else
@@ -1164,7 +1164,7 @@ bool radeon_atom_get_clock_info(struct drm_device *dev)
 		p1pll->pll_out_max =
 		    le32_to_cpu(firmware_info->info.ulMaxPixelClockPLL_Output);
 
-		if (crev >= 4) {
+		if (((frev < 2) && (crev >= 4)) || (frev >= 2)) {
 			p1pll->lcd_pll_out_min =
 				le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100;
 			if (p1pll->lcd_pll_out_min == 0)
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 95f4fea89302..6de342861202 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/acpi.h>
 #include <linux/pci.h>
+#include <linux/delay.h>
 
 #include "radeon_acpi.h"
 
@@ -27,6 +28,7 @@ struct radeon_atpx_functions {
 struct radeon_atpx {
 	acpi_handle handle;
 	struct radeon_atpx_functions functions;
+	bool is_hybrid;
 };
 
 static struct radeon_atpx_priv {
@@ -62,6 +64,14 @@ bool radeon_has_atpx(void) {
 	return radeon_atpx_priv.atpx_detected;
 }
 
+bool radeon_has_atpx_dgpu_power_cntl(void) {
+	return radeon_atpx_priv.atpx.functions.power_cntl;
+}
+
+bool radeon_is_atpx_hybrid(void) {
+	return radeon_atpx_priv.atpx.is_hybrid;
+}
+
 /**
  * radeon_atpx_call - call an ATPX method
  *
@@ -141,18 +151,12 @@ static void radeon_atpx_parse_functions(struct radeon_atpx_functions *f, u32 mas
  */
 static int radeon_atpx_validate(struct radeon_atpx *atpx)
 {
-	/* make sure required functions are enabled */
-	/* dGPU power control is required */
-	if (atpx->functions.power_cntl == false) {
-		printk("ATPX dGPU power cntl not present, forcing\n");
-		atpx->functions.power_cntl = true;
-	}
+	u32 valid_bits = 0;
 
 	if (atpx->functions.px_params) {
 		union acpi_object *info;
 		struct atpx_px_params output;
 		size_t size;
-		u32 valid_bits;
 
 		info = radeon_atpx_call(atpx->handle, ATPX_FUNCTION_GET_PX_PARAMETERS, NULL);
 		if (!info)
@@ -171,19 +175,42 @@ static int radeon_atpx_validate(struct radeon_atpx *atpx)
 		memcpy(&output, info->buffer.pointer, size);
 
 		valid_bits = output.flags & output.valid_flags;
-		/* if separate mux flag is set, mux controls are required */
-		if (valid_bits & ATPX_SEPARATE_MUX_FOR_I2C) {
-			atpx->functions.i2c_mux_cntl = true;
-			atpx->functions.disp_mux_cntl = true;
-		}
-		/* if any outputs are muxed, mux controls are required */
-		if (valid_bits & (ATPX_CRT1_RGB_SIGNAL_MUXED |
-				  ATPX_TV_SIGNAL_MUXED |
-				  ATPX_DFP_SIGNAL_MUXED))
-			atpx->functions.disp_mux_cntl = true;
 
 		kfree(info);
 	}
+
+	/* if separate mux flag is set, mux controls are required */
+	if (valid_bits & ATPX_SEPARATE_MUX_FOR_I2C) {
+		atpx->functions.i2c_mux_cntl = true;
+		atpx->functions.disp_mux_cntl = true;
+	}
+	/* if any outputs are muxed, mux controls are required */
+	if (valid_bits & (ATPX_CRT1_RGB_SIGNAL_MUXED |
+			  ATPX_TV_SIGNAL_MUXED |
+			  ATPX_DFP_SIGNAL_MUXED))
+		atpx->functions.disp_mux_cntl = true;
+
+	/* some bioses set these bits rather than flagging power_cntl as supported */
+	if (valid_bits & (ATPX_DYNAMIC_PX_SUPPORTED |
+			  ATPX_DYNAMIC_DGPU_POWER_OFF_SUPPORTED))
+		atpx->functions.power_cntl = true;
+
+	atpx->is_hybrid = false;
+	if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) {
+		printk("ATPX Hybrid Graphics\n");
+#if 1
+		/* This is a temporary hack until the D3 cold support
+		 * makes it upstream.  The ATPX power_control method seems
+		 * to still work on even if the system should be using
+		 * the new standardized hybrid D3 cold ACPI interface.
+		 */
+		atpx->functions.power_cntl = true;
+#else
+		atpx->functions.power_cntl = false;
+#endif
+		atpx->is_hybrid = true;
+	}
+
 	return 0;
 }
 
@@ -258,6 +285,10 @@ static int radeon_atpx_set_discrete_state(struct radeon_atpx *atpx, u8 state)
 		if (!info)
 			return -EIO;
 		kfree(info);
+
+		/* 200ms delay is required after off */
+		if (state == 0)
+			msleep(200);
 	}
 	return 0;
 }
@@ -505,7 +536,6 @@ static int radeon_atpx_get_client_id(struct pci_dev *pdev)
 static const struct vga_switcheroo_handler radeon_atpx_handler = {
 	.switchto = radeon_atpx_switchto,
 	.power_state = radeon_atpx_power_state,
-	.init = radeon_atpx_init,
 	.get_client_id = radeon_atpx_get_client_id,
 };
 
@@ -541,6 +571,7 @@ static bool radeon_atpx_detect(void)
 		printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n",
 		       acpi_method_name);
 		radeon_atpx_priv.atpx_detected = true;
+		radeon_atpx_init();
 		return true;
 	}
 	return false;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 81a63d7f5cd9..b79f3b002471 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -2064,7 +2064,6 @@ radeon_add_atom_connector(struct drm_device *dev,
 							   RADEON_OUTPUT_CSC_BYPASS);
 			/* no HPD on analog connectors */
 			radeon_connector->hpd.hpd = RADEON_HPD_NONE;
-			connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 			connector->interlace_allowed = true;
 			connector->doublescan_allowed = true;
 			break;
@@ -2314,8 +2313,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 	}
 
 	if (radeon_connector->hpd.hpd == RADEON_HPD_NONE) {
-		if (i2c_bus->valid)
-			connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+		if (i2c_bus->valid) {
+			connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+			                    DRM_CONNECTOR_POLL_DISCONNECT;
+		}
 	} else
 		connector->polled = DRM_CONNECTOR_POLL_HPD;
 
@@ -2391,7 +2392,6 @@ radeon_add_legacy_connector(struct drm_device *dev,
 					      1);
 		/* no HPD on analog connectors */
 		radeon_connector->hpd.hpd = RADEON_HPD_NONE;
-		connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 		connector->interlace_allowed = true;
 		connector->doublescan_allowed = true;
 		break;
@@ -2476,10 +2476,13 @@ radeon_add_legacy_connector(struct drm_device *dev,
 	}
 
 	if (radeon_connector->hpd.hpd == RADEON_HPD_NONE) {
-		if (i2c_bus->valid)
-			connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+		if (i2c_bus->valid) {
+			connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+			                    DRM_CONNECTOR_POLL_DISCONNECT;
+		}
 	} else
 		connector->polled = DRM_CONNECTOR_POLL_HPD;
+
 	connector->display_info.subpixel_order = subpixel_order;
 	drm_connector_register(connector);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 21c44b2293bc..a00dd2f74527 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -30,6 +30,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/radeon_drm.h>
+#include <linux/pm_runtime.h>
 #include <linux/vgaarb.h>
 #include <linux/vga_switcheroo.h>
 #include <linux/efi.h>
@@ -1526,6 +1527,9 @@ int radeon_device_init(struct radeon_device *rdev,
 	return 0;
 
 failed:
+	/* balance pm_runtime_get_sync() in radeon_driver_unload_kms() */
+	if (radeon_is_px(ddev))
+		pm_runtime_put_noidle(ddev->dev);
 	if (runtime)
 		vga_switcheroo_fini_domain_pm_ops(rdev->dev);
 	return r;
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 6a41b4982647..c3206fb8f4cf 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -231,19 +231,21 @@ void radeon_crtc_fb_gamma_get(struct drm_crtc *crtc, u16 *red, u16 *green,
 	*blue = radeon_crtc->lut_b[regno] << 6;
 }
 
-static void radeon_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-				  u16 *blue, uint32_t start, uint32_t size)
+static int radeon_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
+				 u16 *blue, uint32_t size)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
-	int end = (start + size > 256) ? 256 : start + size, i;
+	int i;
 
 	/* userspace palettes are always correct as is */
-	for (i = start; i < end; i++) {
+	for (i = 0; i < size; i++) {
 		radeon_crtc->lut_r[i] = red[i] >> 6;
 		radeon_crtc->lut_g[i] = green[i] >> 6;
 		radeon_crtc->lut_b[i] = blue[i] >> 6;
 	}
 	radeon_crtc_load_lut(crtc);
+
+	return 0;
 }
 
 static void radeon_crtc_destroy(struct drm_crtc *crtc)
@@ -381,7 +383,7 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
 
 	spin_unlock_irqrestore(&rdev->ddev->event_lock, flags);
 
-	drm_vblank_put(rdev->ddev, radeon_crtc->crtc_id);
+	drm_crtc_vblank_put(&radeon_crtc->base);
 	radeon_irq_kms_pflip_irq_put(rdev, work->crtc_id);
 	queue_work(radeon_crtc->flip_queue, &work->unpin_work);
 }
@@ -598,7 +600,7 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 	}
 	work->base = base;
 
-	r = drm_vblank_get(crtc->dev, radeon_crtc->crtc_id);
+	r = drm_crtc_vblank_get(crtc);
 	if (r) {
 		DRM_ERROR("failed to get vblank before flip\n");
 		goto pflip_cleanup;
@@ -625,7 +627,7 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 	return 0;
 
 vblank_cleanup:
-	drm_vblank_put(crtc->dev, radeon_crtc->crtc_id);
+	drm_crtc_vblank_put(crtc);
 
 pflip_cleanup:
 	if (unlikely(radeon_bo_reserve(new_rbo, false) != 0)) {
@@ -688,6 +690,7 @@ radeon_crtc_set_config(struct drm_mode_set *set)
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;
 }
+
 static const struct drm_crtc_funcs radeon_crtc_funcs = {
 	.cursor_set2 = radeon_crtc_cursor_set2,
 	.cursor_move = radeon_crtc_cursor_move,
@@ -711,7 +714,7 @@ static void radeon_crtc_init(struct drm_device *dev, int index)
 
 	drm_mode_crtc_set_gamma_size(&radeon_crtc->base, 256);
 	radeon_crtc->crtc_id = index;
-	radeon_crtc->flip_queue = create_singlethread_workqueue("radeon-crtc");
+	radeon_crtc->flip_queue = alloc_workqueue("radeon-crtc", WQ_HIGHPRI, 0);
 	rdev->mode_info.crtcs[index] = radeon_crtc;
 
 	if (rdev->family >= CHIP_BONAIRE) {
@@ -1321,9 +1324,7 @@ static void radeon_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct radeon_framebuffer *radeon_fb = to_radeon_framebuffer(fb);
 
-	if (radeon_fb->obj) {
-		drm_gem_object_unreference_unlocked(radeon_fb->obj);
-	}
+	drm_gem_object_unreference_unlocked(radeon_fb->obj);
 	drm_framebuffer_cleanup(fb);
 	kfree(radeon_fb);
 }
@@ -1708,6 +1709,7 @@ void radeon_modeset_fini(struct radeon_device *rdev)
 		radeon_afmt_fini(rdev);
 		drm_kms_helper_poll_fini(rdev->ddev);
 		radeon_hpd_fini(rdev);
+		drm_crtc_force_disable_all(rdev->ddev);
 		drm_mode_config_cleanup(rdev->ddev);
 		rdev->mode_info.mode_config_initialized = false;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index b55aa740171f..c01a7c6abb49 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -34,11 +34,9 @@
 #include "radeon_drv.h"
 
 #include <drm/drm_pciids.h>
-#include <linux/apple-gmux.h>
 #include <linux/console.h>
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
-#include <linux/vgaarb.h>
 #include <linux/vga_switcheroo.h>
 #include <drm/drm_gem.h>
 
@@ -95,9 +93,10 @@
  *   2.43.0 - RADEON_INFO_GPU_RESET_COUNTER
  *   2.44.0 - SET_APPEND_CNT packet3 support
  *   2.45.0 - Allow setting shader registers using DMA/COPY packet3 on SI
+ *   2.46.0 - Add PFP_SYNC_ME support on evergreen
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	45
+#define KMS_DRIVER_MINOR	46
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
@@ -164,9 +163,13 @@ void radeon_debugfs_cleanup(struct drm_minor *minor);
 #if defined(CONFIG_VGA_SWITCHEROO)
 void radeon_register_atpx_handler(void);
 void radeon_unregister_atpx_handler(void);
+bool radeon_has_atpx_dgpu_power_cntl(void);
+bool radeon_is_atpx_hybrid(void);
 #else
 static inline void radeon_register_atpx_handler(void) {}
 static inline void radeon_unregister_atpx_handler(void) {}
+static inline bool radeon_has_atpx_dgpu_power_cntl(void) { return false; }
+static inline bool radeon_is_atpx_hybrid(void) { return false; }
 #endif
 
 int radeon_no_wb;
@@ -340,13 +343,7 @@ static int radeon_pci_probe(struct pci_dev *pdev,
 	if (ret == -EPROBE_DEFER)
 		return ret;
 
-	/*
-	 * apple-gmux is needed on dual GPU MacBook Pro
-	 * to probe the panel if we're the inactive GPU.
-	 */
-	if (IS_ENABLED(CONFIG_VGA_ARB) && IS_ENABLED(CONFIG_VGA_SWITCHEROO) &&
-	    apple_gmux_present() && pdev != vga_default_device() &&
-	    !vga_switcheroo_handler_flags())
+	if (vga_switcheroo_client_probe_defer(pdev))
 		return -EPROBE_DEFER;
 
 	/* Get rid of things like offb */
@@ -412,7 +409,10 @@ static int radeon_pmops_runtime_suspend(struct device *dev)
 	pci_save_state(pdev);
 	pci_disable_device(pdev);
 	pci_ignore_hotplug(pdev);
-	pci_set_power_state(pdev, PCI_D3cold);
+	if (radeon_is_atpx_hybrid())
+		pci_set_power_state(pdev, PCI_D3cold);
+	else if (!radeon_has_atpx_dgpu_power_cntl())
+		pci_set_power_state(pdev, PCI_D3hot);
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
 
 	return 0;
@@ -429,7 +429,9 @@ static int radeon_pmops_runtime_resume(struct device *dev)
 
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 
-	pci_set_power_state(pdev, PCI_D0);
+	if (radeon_is_atpx_hybrid() ||
+	    !radeon_has_atpx_dgpu_power_cntl())
+		pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
 	ret = pci_enable_device(pdev);
 	if (ret)
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 414953c46a38..835563c1f0ed 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -63,7 +63,10 @@ int radeon_driver_unload_kms(struct drm_device *dev)
 	if (rdev->rmmio == NULL)
 		goto done_free;
 
-	pm_runtime_get_sync(dev->dev);
+	if (radeon_is_px(dev)) {
+		pm_runtime_get_sync(dev->dev);
+		pm_runtime_forbid(dev->dev);
+	}
 
 	radeon_kfd_device_fini(rdev);
 
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index 478d4099b0d0..d0de4022fff9 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -332,14 +332,14 @@ static void radeon_crtc_dpms(struct drm_crtc *crtc, int mode)
 			WREG32_P(RADEON_CRTC_EXT_CNTL, crtc_ext_cntl, ~(mask | crtc_ext_cntl));
 		}
 		if (dev->num_crtcs > radeon_crtc->crtc_id)
-			drm_vblank_on(dev, radeon_crtc->crtc_id);
+			drm_crtc_vblank_on(crtc);
 		radeon_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
 		if (dev->num_crtcs > radeon_crtc->crtc_id)
-			drm_vblank_off(dev, radeon_crtc->crtc_id);
+			drm_crtc_vblank_off(crtc);
 		if (radeon_crtc->crtc_id)
 			WREG32_P(RADEON_CRTC2_GEN_CNTL, mask, ~(RADEON_CRTC2_EN | mask));
 		else {
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 38226d925a5b..4b6542538ff9 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -246,6 +246,7 @@ static void radeon_set_power_state(struct radeon_device *rdev)
 
 static void radeon_pm_set_clocks(struct radeon_device *rdev)
 {
+	struct drm_crtc *crtc;
 	int i, r;
 
 	/* no need to take locks, etc. if nothing's going to change */
@@ -274,26 +275,30 @@ static void radeon_pm_set_clocks(struct radeon_device *rdev)
 	radeon_unmap_vram_bos(rdev);
 
 	if (rdev->irq.installed) {
-		for (i = 0; i < rdev->num_crtc; i++) {
+		i = 0;
+		drm_for_each_crtc(crtc, rdev->ddev) {
 			if (rdev->pm.active_crtcs & (1 << i)) {
 				/* This can fail if a modeset is in progress */
-				if (drm_vblank_get(rdev->ddev, i) == 0)
+				if (drm_crtc_vblank_get(crtc) == 0)
 					rdev->pm.req_vblank |= (1 << i);
 				else
 					DRM_DEBUG_DRIVER("crtc %d no vblank, can glitch\n",
 							 i);
 			}
+			i++;
 		}
 	}
 
 	radeon_set_power_state(rdev);
 
 	if (rdev->irq.installed) {
-		for (i = 0; i < rdev->num_crtc; i++) {
+		i = 0;
+		drm_for_each_crtc(crtc, rdev->ddev) {
 			if (rdev->pm.req_vblank & (1 << i)) {
 				rdev->pm.req_vblank &= ~(1 << i);
-				drm_vblank_put(rdev->ddev, i);
+				drm_crtc_vblank_put(crtc);
 			}
+			i++;
 		}
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 590b0377fbe2..ffdad81ef964 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -300,8 +300,7 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 	if (IS_ERR(fence))
 		return PTR_ERR(fence);
 
-	r = ttm_bo_move_accel_cleanup(bo, &fence->base,
-				      evict, no_wait_gpu, new_mem);
+	r = ttm_bo_move_accel_cleanup(bo, &fence->base, evict, new_mem);
 	radeon_fence_unref(&fence);
 	return r;
 }
@@ -403,6 +402,10 @@ static int radeon_bo_move(struct ttm_buffer_object *bo,
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	int r;
 
+	r = ttm_bo_wait(bo, interruptible, no_wait_gpu);
+	if (r)
+		return r;
+
 	/* Can't move a pinned BO */
 	rbo = container_of(bo, struct radeon_bo, tbo);
 	if (WARN_ON_ONCE(rbo->pin_count > 0))
@@ -441,7 +444,8 @@ static int radeon_bo_move(struct ttm_buffer_object *bo,
 
 	if (r) {
 memcpy:
-		r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
+		r = ttm_bo_move_memcpy(bo, evict, interruptible,
+				       no_wait_gpu, new_mem);
 		if (r) {
 			return r;
 		}
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index b30e719dd56d..2523ca96c6c7 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -50,6 +50,7 @@ MODULE_FIRMWARE("radeon/tahiti_ce.bin");
 MODULE_FIRMWARE("radeon/tahiti_mc.bin");
 MODULE_FIRMWARE("radeon/tahiti_rlc.bin");
 MODULE_FIRMWARE("radeon/tahiti_smc.bin");
+MODULE_FIRMWARE("radeon/tahiti_k_smc.bin");
 
 MODULE_FIRMWARE("radeon/PITCAIRN_pfp.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_me.bin");
@@ -65,6 +66,7 @@ MODULE_FIRMWARE("radeon/pitcairn_ce.bin");
 MODULE_FIRMWARE("radeon/pitcairn_mc.bin");
 MODULE_FIRMWARE("radeon/pitcairn_rlc.bin");
 MODULE_FIRMWARE("radeon/pitcairn_smc.bin");
+MODULE_FIRMWARE("radeon/pitcairn_k_smc.bin");
 
 MODULE_FIRMWARE("radeon/VERDE_pfp.bin");
 MODULE_FIRMWARE("radeon/VERDE_me.bin");
@@ -80,6 +82,7 @@ MODULE_FIRMWARE("radeon/verde_ce.bin");
 MODULE_FIRMWARE("radeon/verde_mc.bin");
 MODULE_FIRMWARE("radeon/verde_rlc.bin");
 MODULE_FIRMWARE("radeon/verde_smc.bin");
+MODULE_FIRMWARE("radeon/verde_k_smc.bin");
 
 MODULE_FIRMWARE("radeon/OLAND_pfp.bin");
 MODULE_FIRMWARE("radeon/OLAND_me.bin");
@@ -95,6 +98,7 @@ MODULE_FIRMWARE("radeon/oland_ce.bin");
 MODULE_FIRMWARE("radeon/oland_mc.bin");
 MODULE_FIRMWARE("radeon/oland_rlc.bin");
 MODULE_FIRMWARE("radeon/oland_smc.bin");
+MODULE_FIRMWARE("radeon/oland_k_smc.bin");
 
 MODULE_FIRMWARE("radeon/HAINAN_pfp.bin");
 MODULE_FIRMWARE("radeon/HAINAN_me.bin");
@@ -110,6 +114,7 @@ MODULE_FIRMWARE("radeon/hainan_ce.bin");
 MODULE_FIRMWARE("radeon/hainan_mc.bin");
 MODULE_FIRMWARE("radeon/hainan_rlc.bin");
 MODULE_FIRMWARE("radeon/hainan_smc.bin");
+MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
 
 static u32 si_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh);
 static void si_pcie_gen3_enable(struct radeon_device *rdev);
@@ -1653,12 +1658,16 @@ static int si_init_microcode(struct radeon_device *rdev)
 	char fw_name[30];
 	int err;
 	int new_fw = 0;
+	bool new_smc = false;
 
 	DRM_DEBUG("\n");
 
 	switch (rdev->family) {
 	case CHIP_TAHITI:
 		chip_name = "TAHITI";
+		/* XXX: figure out which Tahitis need the new ucode */
+		if (0)
+			new_smc = true;
 		new_chip_name = "tahiti";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
@@ -1670,6 +1679,13 @@ static int si_init_microcode(struct radeon_device *rdev)
 		break;
 	case CHIP_PITCAIRN:
 		chip_name = "PITCAIRN";
+		if ((rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->device == 0x6810) ||
+		    (rdev->pdev->device == 0x6811) ||
+		    (rdev->pdev->device == 0x6816) ||
+		    (rdev->pdev->device == 0x6817) ||
+		    (rdev->pdev->device == 0x6806))
+			new_smc = true;
 		new_chip_name = "pitcairn";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
@@ -1681,6 +1697,16 @@ static int si_init_microcode(struct radeon_device *rdev)
 		break;
 	case CHIP_VERDE:
 		chip_name = "VERDE";
+		if ((rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->revision == 0x83) ||
+		    (rdev->pdev->revision == 0x87) ||
+		    (rdev->pdev->device == 0x6820) ||
+		    (rdev->pdev->device == 0x6821) ||
+		    (rdev->pdev->device == 0x6822) ||
+		    (rdev->pdev->device == 0x6823) ||
+		    (rdev->pdev->device == 0x682A) ||
+		    (rdev->pdev->device == 0x682B))
+			new_smc = true;
 		new_chip_name = "verde";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
@@ -1692,6 +1718,13 @@ static int si_init_microcode(struct radeon_device *rdev)
 		break;
 	case CHIP_OLAND:
 		chip_name = "OLAND";
+		if ((rdev->pdev->revision == 0xC7) ||
+		    (rdev->pdev->revision == 0x80) ||
+		    (rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->revision == 0x83) ||
+		    (rdev->pdev->device == 0x6604) ||
+		    (rdev->pdev->device == 0x6605))
+			new_smc = true;
 		new_chip_name = "oland";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
@@ -1702,6 +1735,13 @@ static int si_init_microcode(struct radeon_device *rdev)
 		break;
 	case CHIP_HAINAN:
 		chip_name = "HAINAN";
+		if ((rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->revision == 0x83) ||
+		    (rdev->pdev->revision == 0xC3) ||
+		    (rdev->pdev->device == 0x6664) ||
+		    (rdev->pdev->device == 0x6665) ||
+		    (rdev->pdev->device == 0x6667))
+			new_smc = true;
 		new_chip_name = "hainan";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
@@ -1847,7 +1887,10 @@ static int si_init_microcode(struct radeon_device *rdev)
 		}
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", new_chip_name);
+	if (new_smc)
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_k_smc.bin", new_chip_name);
+	else
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", new_chip_name);
 	err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
 	if (err) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index 7fc3ca5ce6c7..4c2fd056dd6d 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -6,7 +6,6 @@ config DRM_RCAR_DU
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_GEM_CMA_HELPER
-	select DRM_KMS_FB_HELPER
 	select VIDEOMODE_HELPERS
 	help
 	  Choose this option if you have an R-Car chipset.
diff --git a/drivers/gpu/drm/rcar-du/Makefile b/drivers/gpu/drm/rcar-du/Makefile
index 827711e28226..d3b44651061a 100644
--- a/drivers/gpu/drm/rcar-du/Makefile
+++ b/drivers/gpu/drm/rcar-du/Makefile
@@ -7,8 +7,8 @@ rcar-du-drm-y := rcar_du_crtc.o \
 		 rcar_du_plane.o \
 		 rcar_du_vgacon.o
 
-rcar-du-drm-$(CONFIG_DRM_RCAR_HDMI)	+= rcar_du_hdmicon.o \
-					   rcar_du_hdmienc.o
+rcar-du-drm-$(CONFIG_DRM_RCAR_HDMI)	+= rcar_du_hdmienc.o
+
 rcar-du-drm-$(CONFIG_DRM_RCAR_LVDS)	+= rcar_du_lvdsenc.o
 
 rcar-du-drm-$(CONFIG_DRM_RCAR_VSP)	+= rcar_du_vsp.o
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
index 0d8bdda736f9..e39fcef2e033 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
@@ -552,7 +552,7 @@ static irqreturn_t rcar_du_crtc_irq(int irq, void *arg)
 	rcar_du_crtc_write(rcrtc, DSRCR, status & DSRCR_MASK);
 
 	if (status & DSSR_FRM) {
-		drm_handle_vblank(rcrtc->crtc.dev, rcrtc->index);
+		drm_crtc_handle_vblank(&rcrtc->crtc);
 		rcar_du_crtc_finish_page_flip(rcrtc);
 		ret = IRQ_HANDLED;
 	}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index fb9242d27883..899ef7a2a7b4 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -217,7 +217,7 @@ static struct drm_driver rcar_du_driver = {
 	.get_vblank_counter	= drm_vblank_no_hw_counter,
 	.enable_vblank		= rcar_du_enable_vblank,
 	.disable_vblank		= rcar_du_disable_vblank,
-	.gem_free_object	= drm_gem_cma_free_object,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops		= &drm_gem_cma_vm_ops,
 	.prime_handle_to_fd	= drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle	= drm_gem_prime_fd_to_handle,
@@ -278,7 +278,6 @@ static int rcar_du_remove(struct platform_device *pdev)
 	struct rcar_du_device *rcdu = platform_get_drvdata(pdev);
 	struct drm_device *ddev = rcdu->ddev;
 
-	drm_connector_unregister_all(ddev);
 	drm_dev_unregister(ddev);
 
 	if (rcdu->fbdev)
@@ -320,8 +319,6 @@ static int rcar_du_probe(struct platform_device *pdev)
 	if (!ddev)
 		return -ENOMEM;
 
-	drm_dev_set_unique(ddev, dev_name(&pdev->dev));
-
 	rcdu->ddev = ddev;
 	ddev->dev_private = rcdu;
 
@@ -339,15 +336,15 @@ static int rcar_du_probe(struct platform_device *pdev)
 	 * disabled for all CRTCs.
 	 */
 	ret = drm_vblank_init(ddev, (1 << rcdu->info->num_crtcs) - 1);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to initialize vblank\n");
+	if (ret < 0)
 		goto error;
-	}
 
 	/* DRM/KMS objects */
 	ret = rcar_du_modeset_init(rcdu);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to initialize DRM/KMS (%d)\n", ret);
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev,
+				"failed to initialize DRM/KMS (%d)\n", ret);
 		goto error;
 	}
 
@@ -360,10 +357,6 @@ static int rcar_du_probe(struct platform_device *pdev)
 	if (ret)
 		goto error;
 
-	ret = drm_connector_register_all(ddev);
-	if (ret < 0)
-		goto error;
-
 	DRM_INFO("Device %s probed\n", dev_name(&pdev->dev));
 
 	return 0;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
index 4e939e41f030..ab8645c57e2d 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
@@ -19,7 +19,6 @@
 
 #include "rcar_du_drv.h"
 #include "rcar_du_encoder.h"
-#include "rcar_du_hdmicon.h"
 #include "rcar_du_hdmienc.h"
 #include "rcar_du_kms.h"
 #include "rcar_du_lvdscon.h"
@@ -27,18 +26,6 @@
 #include "rcar_du_vgacon.h"
 
 /* -----------------------------------------------------------------------------
- * Common connector functions
- */
-
-struct drm_encoder *
-rcar_du_connector_best_encoder(struct drm_connector *connector)
-{
-	struct rcar_du_connector *rcon = to_rcar_connector(connector);
-
-	return rcar_encoder_to_drm_encoder(rcon->encoder);
-}
-
-/* -----------------------------------------------------------------------------
  * Encoder
  */
 
@@ -186,7 +173,7 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu,
 		break;
 
 	case DRM_MODE_ENCODER_TMDS:
-		ret = rcar_du_hdmi_connector_init(rcdu, renc);
+		/* connector managed by the bridge driver */
 		break;
 
 	default:
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.h b/drivers/gpu/drm/rcar-du/rcar_du_encoder.h
index 719b6f2a031c..7fc10a9c34c3 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.h
@@ -15,7 +15,6 @@
 #define __RCAR_DU_ENCODER_H__
 
 #include <drm/drm_crtc.h>
-#include <drm/drm_encoder_slave.h>
 
 struct rcar_du_device;
 struct rcar_du_hdmienc;
@@ -30,16 +29,16 @@ enum rcar_du_encoder_type {
 };
 
 struct rcar_du_encoder {
-	struct drm_encoder_slave slave;
+	struct drm_encoder base;
 	enum rcar_du_output output;
 	struct rcar_du_hdmienc *hdmi;
 	struct rcar_du_lvdsenc *lvds;
 };
 
 #define to_rcar_encoder(e) \
-	container_of(e, struct rcar_du_encoder, slave.base)
+	container_of(e, struct rcar_du_encoder, base)
 
-#define rcar_encoder_to_drm_encoder(e)	(&(e)->slave.base)
+#define rcar_encoder_to_drm_encoder(e)	(&(e)->base)
 
 struct rcar_du_connector {
 	struct drm_connector connector;
@@ -49,9 +48,6 @@ struct rcar_du_connector {
 #define to_rcar_connector(c) \
 	container_of(c, struct rcar_du_connector, connector)
 
-struct drm_encoder *
-rcar_du_connector_best_encoder(struct drm_connector *connector);
-
 int rcar_du_encoder_init(struct rcar_du_device *rcdu,
 			 enum rcar_du_encoder_type type,
 			 enum rcar_du_output output,
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c b/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c
deleted file mode 100644
index 6c927144b5c9..000000000000
--- a/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.c
+++ /dev/null
@@ -1,117 +0,0 @@
-/*
- * R-Car Display Unit HDMI Connector
- *
- * Copyright (C) 2014 Renesas Electronics Corporation
- *
- * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <drm/drmP.h>
-#include <drm/drm_atomic_helper.h>
-#include <drm/drm_crtc.h>
-#include <drm/drm_crtc_helper.h>
-#include <drm/drm_encoder_slave.h>
-
-#include "rcar_du_drv.h"
-#include "rcar_du_encoder.h"
-#include "rcar_du_hdmicon.h"
-#include "rcar_du_kms.h"
-
-#define to_slave_funcs(e)	(to_rcar_encoder(e)->slave.slave_funcs)
-
-static int rcar_du_hdmi_connector_get_modes(struct drm_connector *connector)
-{
-	struct rcar_du_connector *con = to_rcar_connector(connector);
-	struct drm_encoder *encoder = rcar_encoder_to_drm_encoder(con->encoder);
-	const struct drm_encoder_slave_funcs *sfuncs = to_slave_funcs(encoder);
-
-	if (sfuncs->get_modes == NULL)
-		return 0;
-
-	return sfuncs->get_modes(encoder, connector);
-}
-
-static int rcar_du_hdmi_connector_mode_valid(struct drm_connector *connector,
-					     struct drm_display_mode *mode)
-{
-	struct rcar_du_connector *con = to_rcar_connector(connector);
-	struct drm_encoder *encoder = rcar_encoder_to_drm_encoder(con->encoder);
-	const struct drm_encoder_slave_funcs *sfuncs = to_slave_funcs(encoder);
-
-	if (sfuncs->mode_valid == NULL)
-		return MODE_OK;
-
-	return sfuncs->mode_valid(encoder, mode);
-}
-
-static const struct drm_connector_helper_funcs connector_helper_funcs = {
-	.get_modes = rcar_du_hdmi_connector_get_modes,
-	.mode_valid = rcar_du_hdmi_connector_mode_valid,
-	.best_encoder = rcar_du_connector_best_encoder,
-};
-
-static enum drm_connector_status
-rcar_du_hdmi_connector_detect(struct drm_connector *connector, bool force)
-{
-	struct rcar_du_connector *con = to_rcar_connector(connector);
-	struct drm_encoder *encoder = rcar_encoder_to_drm_encoder(con->encoder);
-	const struct drm_encoder_slave_funcs *sfuncs = to_slave_funcs(encoder);
-
-	if (sfuncs->detect == NULL)
-		return connector_status_unknown;
-
-	return sfuncs->detect(encoder, connector);
-}
-
-static const struct drm_connector_funcs connector_funcs = {
-	.dpms = drm_atomic_helper_connector_dpms,
-	.reset = drm_atomic_helper_connector_reset,
-	.detect = rcar_du_hdmi_connector_detect,
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = drm_connector_cleanup,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
-};
-
-int rcar_du_hdmi_connector_init(struct rcar_du_device *rcdu,
-				struct rcar_du_encoder *renc)
-{
-	struct drm_encoder *encoder = rcar_encoder_to_drm_encoder(renc);
-	struct rcar_du_connector *rcon;
-	struct drm_connector *connector;
-	int ret;
-
-	rcon = devm_kzalloc(rcdu->dev, sizeof(*rcon), GFP_KERNEL);
-	if (rcon == NULL)
-		return -ENOMEM;
-
-	connector = &rcon->connector;
-	connector->display_info.width_mm = 0;
-	connector->display_info.height_mm = 0;
-	connector->interlace_allowed = true;
-	connector->polled = DRM_CONNECTOR_POLL_HPD;
-
-	ret = drm_connector_init(rcdu->ddev, connector, &connector_funcs,
-				 DRM_MODE_CONNECTOR_HDMIA);
-	if (ret < 0)
-		return ret;
-
-	drm_connector_helper_add(connector, &connector_helper_funcs);
-
-	connector->dpms = DRM_MODE_DPMS_OFF;
-	drm_object_property_set_value(&connector->base,
-		rcdu->ddev->mode_config.dpms_property, DRM_MODE_DPMS_OFF);
-
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
-	if (ret < 0)
-		return ret;
-
-	rcon->encoder = renc;
-
-	return 0;
-}
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.h b/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.h
deleted file mode 100644
index 87daa949227f..000000000000
--- a/drivers/gpu/drm/rcar-du/rcar_du_hdmicon.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * R-Car Display Unit HDMI Connector
- *
- * Copyright (C) 2014 Renesas Electronics Corporation
- *
- * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef __RCAR_DU_HDMICON_H__
-#define __RCAR_DU_HDMICON_H__
-
-struct rcar_du_device;
-struct rcar_du_encoder;
-
-#if IS_ENABLED(CONFIG_DRM_RCAR_HDMI)
-int rcar_du_hdmi_connector_init(struct rcar_du_device *rcdu,
-				struct rcar_du_encoder *renc);
-#else
-static inline int rcar_du_hdmi_connector_init(struct rcar_du_device *rcdu,
-					      struct rcar_du_encoder *renc)
-{
-	return -ENOSYS;
-}
-#endif
-
-#endif /* __RCAR_DU_HDMICON_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_hdmienc.c b/drivers/gpu/drm/rcar-du/rcar_du_hdmienc.c
index 461662d231e2..4de3ff0dbebd 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_hdmienc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_hdmienc.c
@@ -16,7 +16,6 @@
 #include <drm/drmP.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
-#include <drm/drm_encoder_slave.h>
 
 #include "rcar_du_drv.h"
 #include "rcar_du_encoder.h"
@@ -25,20 +24,14 @@
 
 struct rcar_du_hdmienc {
 	struct rcar_du_encoder *renc;
-	struct device *dev;
 	bool enabled;
 };
 
 #define to_rcar_hdmienc(e)	(to_rcar_encoder(e)->hdmi)
-#define to_slave_funcs(e)	(to_rcar_encoder(e)->slave.slave_funcs)
 
 static void rcar_du_hdmienc_disable(struct drm_encoder *encoder)
 {
 	struct rcar_du_hdmienc *hdmienc = to_rcar_hdmienc(encoder);
-	const struct drm_encoder_slave_funcs *sfuncs = to_slave_funcs(encoder);
-
-	if (sfuncs->dpms)
-		sfuncs->dpms(encoder, DRM_MODE_DPMS_OFF);
 
 	if (hdmienc->renc->lvds)
 		rcar_du_lvdsenc_enable(hdmienc->renc->lvds, encoder->crtc,
@@ -50,15 +43,11 @@ static void rcar_du_hdmienc_disable(struct drm_encoder *encoder)
 static void rcar_du_hdmienc_enable(struct drm_encoder *encoder)
 {
 	struct rcar_du_hdmienc *hdmienc = to_rcar_hdmienc(encoder);
-	const struct drm_encoder_slave_funcs *sfuncs = to_slave_funcs(encoder);
 
 	if (hdmienc->renc->lvds)
 		rcar_du_lvdsenc_enable(hdmienc->renc->lvds, encoder->crtc,
 				       true);
 
-	if (sfuncs->dpms)
-		sfuncs->dpms(encoder, DRM_MODE_DPMS_ON);
-
 	hdmienc->enabled = true;
 }
 
@@ -67,29 +56,21 @@ static int rcar_du_hdmienc_atomic_check(struct drm_encoder *encoder,
 					struct drm_connector_state *conn_state)
 {
 	struct rcar_du_hdmienc *hdmienc = to_rcar_hdmienc(encoder);
-	const struct drm_encoder_slave_funcs *sfuncs = to_slave_funcs(encoder);
 	struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode;
-	const struct drm_display_mode *mode = &crtc_state->mode;
 
 	if (hdmienc->renc->lvds)
 		rcar_du_lvdsenc_atomic_check(hdmienc->renc->lvds,
 					     adjusted_mode);
 
-	if (sfuncs->mode_fixup == NULL)
-		return 0;
-
-	return sfuncs->mode_fixup(encoder, mode, adjusted_mode) ? 0 : -EINVAL;
+	return 0;
 }
 
+
 static void rcar_du_hdmienc_mode_set(struct drm_encoder *encoder,
 				     struct drm_display_mode *mode,
 				     struct drm_display_mode *adjusted_mode)
 {
 	struct rcar_du_hdmienc *hdmienc = to_rcar_hdmienc(encoder);
-	const struct drm_encoder_slave_funcs *sfuncs = to_slave_funcs(encoder);
-
-	if (sfuncs->mode_set)
-		sfuncs->mode_set(encoder, mode, adjusted_mode);
 
 	rcar_du_crtc_route_output(encoder->crtc, hdmienc->renc->output);
 }
@@ -109,7 +90,6 @@ static void rcar_du_hdmienc_cleanup(struct drm_encoder *encoder)
 		rcar_du_hdmienc_disable(encoder);
 
 	drm_encoder_cleanup(encoder);
-	put_device(hdmienc->dev);
 }
 
 static const struct drm_encoder_funcs encoder_funcs = {
@@ -120,8 +100,7 @@ int rcar_du_hdmienc_init(struct rcar_du_device *rcdu,
 			 struct rcar_du_encoder *renc, struct device_node *np)
 {
 	struct drm_encoder *encoder = rcar_encoder_to_drm_encoder(renc);
-	struct drm_i2c_encoder_driver *driver;
-	struct i2c_client *i2c_slave;
+	struct drm_bridge *bridge;
 	struct rcar_du_hdmienc *hdmienc;
 	int ret;
 
@@ -129,44 +108,29 @@ int rcar_du_hdmienc_init(struct rcar_du_device *rcdu,
 	if (hdmienc == NULL)
 		return -ENOMEM;
 
-	/* Locate the slave I2C device and driver. */
-	i2c_slave = of_find_i2c_device_by_node(np);
-	if (!i2c_slave || !i2c_get_clientdata(i2c_slave)) {
-		dev_dbg(rcdu->dev,
-			"can't get I2C slave for %s, deferring probe\n",
-			of_node_full_name(np));
+	/* Locate drm bridge from the hdmi encoder DT node */
+	bridge = of_drm_find_bridge(np);
+	if (!bridge)
 		return -EPROBE_DEFER;
-	}
-
-	hdmienc->dev = &i2c_slave->dev;
-
-	if (hdmienc->dev->driver == NULL) {
-		dev_dbg(rcdu->dev,
-			"I2C slave %s not probed yet, deferring probe\n",
-			dev_name(hdmienc->dev));
-		ret = -EPROBE_DEFER;
-		goto error;
-	}
-
-	/* Initialize the slave encoder. */
-	driver = to_drm_i2c_encoder_driver(to_i2c_driver(hdmienc->dev->driver));
-	ret = driver->encoder_init(i2c_slave, rcdu->ddev, &renc->slave);
-	if (ret < 0)
-		goto error;
 
 	ret = drm_encoder_init(rcdu->ddev, encoder, &encoder_funcs,
 			       DRM_MODE_ENCODER_TMDS, NULL);
 	if (ret < 0)
-		goto error;
+		return ret;
 
 	drm_encoder_helper_add(encoder, &encoder_helper_funcs);
 
 	renc->hdmi = hdmienc;
 	hdmienc->renc = renc;
 
-	return 0;
+	/* Link drm_bridge to encoder */
+	bridge->encoder = encoder;
+
+	ret = drm_bridge_attach(rcdu->ddev, bridge);
+	if (ret) {
+		drm_encoder_cleanup(encoder);
+		return ret;
+	}
 
-error:
-	put_device(hdmienc->dev);
-	return ret;
+	return 0;
 }
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index e70a4f33d970..6bb032d8ac6b 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -288,6 +288,8 @@ static int rcar_du_atomic_commit(struct drm_device *dev,
 {
 	struct rcar_du_device *rcdu = dev->dev_private;
 	struct rcar_du_commit *commit;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
 	unsigned int i;
 	int ret;
 
@@ -309,10 +311,8 @@ static int rcar_du_atomic_commit(struct drm_device *dev,
 	/* Wait until all affected CRTCs have completed previous commits and
 	 * mark them as pending.
 	 */
-	for (i = 0; i < dev->mode_config.num_crtc; ++i) {
-		if (state->crtcs[i])
-			commit->crtcs |= 1 << drm_crtc_index(state->crtcs[i]);
-	}
+	for_each_crtc_in_state(state, crtc, crtc_state, i)
+		commit->crtcs |= drm_crtc_mask(crtc);
 
 	spin_lock(&rcdu->commit.wait.lock);
 	ret = wait_event_interruptible_locked(rcdu->commit.wait,
@@ -327,7 +327,7 @@ static int rcar_du_atomic_commit(struct drm_device *dev,
 	}
 
 	/* Swap the state, this is the point of no return. */
-	drm_atomic_helper_swap_state(dev, state);
+	drm_atomic_helper_swap_state(state, true);
 
 	if (nonblock)
 		schedule_work(&commit->work);
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
index e905f5da7aaa..6afd0af312ba 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
@@ -59,7 +59,6 @@ static int rcar_du_lvds_connector_get_modes(struct drm_connector *connector)
 
 static const struct drm_connector_helper_funcs connector_helper_funcs = {
 	.get_modes = rcar_du_lvds_connector_get_modes,
-	.best_encoder = rcar_du_connector_best_encoder,
 };
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
index d445e67f78e1..bfe31ca870cc 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
@@ -140,18 +140,17 @@ int rcar_du_atomic_check_planes(struct drm_device *dev,
 	bool needs_realloc = false;
 	unsigned int groups = 0;
 	unsigned int i;
+	struct drm_plane *drm_plane;
+	struct drm_plane_state *drm_plane_state;
 
 	/* Check if hardware planes need to be reallocated. */
-	for (i = 0; i < dev->mode_config.num_total_plane; ++i) {
+	for_each_plane_in_state(state, drm_plane, drm_plane_state, i) {
 		struct rcar_du_plane_state *plane_state;
 		struct rcar_du_plane *plane;
 		unsigned int index;
 
-		if (!state->planes[i])
-			continue;
-
-		plane = to_rcar_plane(state->planes[i]);
-		plane_state = to_rcar_plane_state(state->plane_states[i]);
+		plane = to_rcar_plane(drm_plane);
+		plane_state = to_rcar_plane_state(drm_plane_state);
 
 		dev_dbg(rcdu->dev, "%s: checking plane (%u,%tu)\n", __func__,
 			plane->group->index, plane - plane->group->planes);
@@ -247,18 +246,15 @@ int rcar_du_atomic_check_planes(struct drm_device *dev,
 	}
 
 	/* Reallocate hardware planes for each plane that needs it. */
-	for (i = 0; i < dev->mode_config.num_total_plane; ++i) {
+	for_each_plane_in_state(state, drm_plane, drm_plane_state, i) {
 		struct rcar_du_plane_state *plane_state;
 		struct rcar_du_plane *plane;
 		unsigned int crtc_planes;
 		unsigned int free;
 		int idx;
 
-		if (!state->planes[i])
-			continue;
-
-		plane = to_rcar_plane(state->planes[i]);
-		plane_state = to_rcar_plane_state(state->plane_states[i]);
+		plane = to_rcar_plane(drm_plane);
+		plane_state = to_rcar_plane_state(drm_plane_state);
 
 		dev_dbg(rcdu->dev, "%s: allocating plane (%u,%tu)\n", __func__,
 			plane->group->index, plane - plane->group->planes);
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_regs.h b/drivers/gpu/drm/rcar-du/rcar_du_regs.h
index d2f66068e52c..fedb0161e234 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_regs.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_regs.h
@@ -195,9 +195,10 @@
 #define DEFR6_ODPM12_DISP	(2 << 8)
 #define DEFR6_ODPM12_CDE	(3 << 8)
 #define DEFR6_ODPM12_MASK	(3 << 8)
-#define DEFR6_TCNE2		(1 << 6)
+#define DEFR6_TCNE1		(1 << 6)
+#define DEFR6_TCNE0		(1 << 4)
 #define DEFR6_MLOS1		(1 << 2)
-#define DEFR6_DEFAULT		(DEFR6_CODE | DEFR6_TCNE2)
+#define DEFR6_DEFAULT		(DEFR6_CODE | DEFR6_TCNE1)
 
 /* -----------------------------------------------------------------------------
  * R8A7790-only Control Registers
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
index 9d7e5c99caf6..8d6125c1c0f9 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
@@ -28,7 +28,6 @@ static int rcar_du_vga_connector_get_modes(struct drm_connector *connector)
 
 static const struct drm_connector_helper_funcs connector_helper_funcs = {
 	.get_modes = rcar_du_vga_connector_get_modes,
-	.best_encoder = rcar_du_connector_best_encoder,
 };
 
 static enum drm_connector_status
@@ -79,7 +78,5 @@ int rcar_du_vga_connector_init(struct rcar_du_device *rcdu,
 	if (ret < 0)
 		return ret;
 
-	rcon->encoder = renc;
-
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig
index d30bdc38a760..3c58669a06ce 100644
--- a/drivers/gpu/drm/rockchip/Kconfig
+++ b/drivers/gpu/drm/rockchip/Kconfig
@@ -2,12 +2,9 @@ config DRM_ROCKCHIP
 	tristate "DRM Support for Rockchip"
 	depends on DRM && ROCKCHIP_IOMMU
 	depends on RESET_CONTROLLER
+	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_PANEL
-	select FB_CFB_FILLRECT
-	select FB_CFB_COPYAREA
-	select FB_CFB_IMAGEBLIT
 	select VIDEOMODE_HELPERS
 	help
 	  Choose this option if you have a Rockchip soc chipset.
diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
index 7f6a55cae27a..89aadbf465f8 100644
--- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
@@ -14,6 +14,7 @@
 
 #include <linux/component.h>
 #include <linux/mfd/syscon.h>
+#include <linux/of_device.h>
 #include <linux/of_graph.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
@@ -33,13 +34,28 @@
 #include "rockchip_drm_drv.h"
 #include "rockchip_drm_vop.h"
 
+#define RK3288_GRF_SOC_CON6		0x25c
+#define RK3288_EDP_LCDC_SEL		BIT(5)
+#define RK3399_GRF_SOC_CON20		0x6250
+#define RK3399_EDP_LCDC_SEL		BIT(5)
+
+#define HIWORD_UPDATE(val, mask)	(val | (mask) << 16)
+
 #define to_dp(nm)	container_of(nm, struct rockchip_dp_device, nm)
 
-/* dp grf register offset */
-#define GRF_SOC_CON6                            0x025c
-#define GRF_EDP_LCD_SEL_MASK                    BIT(5)
-#define GRF_EDP_SEL_VOP_LIT                     BIT(5)
-#define GRF_EDP_SEL_VOP_BIG                     0
+/**
+ * struct rockchip_dp_chip_data - splite the grf setting of kind of chips
+ * @lcdsel_grf_reg: grf register offset of lcdc select
+ * @lcdsel_big: reg value of selecting vop big for eDP
+ * @lcdsel_lit: reg value of selecting vop little for eDP
+ * @chip_type: specific chip type
+ */
+struct rockchip_dp_chip_data {
+	u32	lcdsel_grf_reg;
+	u32	lcdsel_big;
+	u32	lcdsel_lit;
+	u32	chip_type;
+};
 
 struct rockchip_dp_device {
 	struct drm_device        *drm_dev;
@@ -48,9 +64,12 @@ struct rockchip_dp_device {
 	struct drm_display_mode  mode;
 
 	struct clk               *pclk;
+	struct clk               *grfclk;
 	struct regmap            *grf;
 	struct reset_control     *rst;
 
+	const struct rockchip_dp_chip_data *data;
+
 	struct analogix_dp_plat_data plat_data;
 };
 
@@ -77,6 +96,7 @@ static int rockchip_dp_poweron(struct analogix_dp_plat_data *plat_data)
 	ret = rockchip_dp_pre_init(dp);
 	if (ret < 0) {
 		dev_err(dp->dev, "failed to dp pre init %d\n", ret);
+		clk_disable_unprepare(dp->pclk);
 		return ret;
 	}
 
@@ -92,6 +112,23 @@ static int rockchip_dp_powerdown(struct analogix_dp_plat_data *plat_data)
 	return 0;
 }
 
+static int rockchip_dp_get_modes(struct analogix_dp_plat_data *plat_data,
+				 struct drm_connector *connector)
+{
+	struct drm_display_info *di = &connector->display_info;
+	/* VOP couldn't output YUV video format for eDP rightly */
+	u32 mask = DRM_COLOR_FORMAT_YCRCB444 | DRM_COLOR_FORMAT_YCRCB422;
+
+	if ((di->color_formats & mask)) {
+		DRM_DEBUG_KMS("Swapping display color format from YUV to RGB\n");
+		di->color_formats &= ~mask;
+		di->color_formats |= DRM_COLOR_FORMAT_RGB444;
+		di->bpc = 8;
+	}
+
+	return 0;
+}
+
 static bool
 rockchip_dp_drm_encoder_mode_fixup(struct drm_encoder *encoder,
 				   const struct drm_display_mode *mode,
@@ -119,17 +156,23 @@ static void rockchip_dp_drm_encoder_enable(struct drm_encoder *encoder)
 		return;
 
 	if (ret)
-		val = GRF_EDP_SEL_VOP_LIT | (GRF_EDP_LCD_SEL_MASK << 16);
+		val = dp->data->lcdsel_lit;
 	else
-		val = GRF_EDP_SEL_VOP_BIG | (GRF_EDP_LCD_SEL_MASK << 16);
+		val = dp->data->lcdsel_big;
 
 	dev_dbg(dp->dev, "vop %s output to dp\n", (ret) ? "LIT" : "BIG");
 
-	ret = regmap_write(dp->grf, GRF_SOC_CON6, val);
-	if (ret != 0) {
-		dev_err(dp->dev, "Could not write to GRF: %d\n", ret);
+	ret = clk_prepare_enable(dp->grfclk);
+	if (ret < 0) {
+		dev_err(dp->dev, "failed to enable grfclk %d\n", ret);
 		return;
 	}
+
+	ret = regmap_write(dp->grf, dp->data->lcdsel_grf_reg, val);
+	if (ret != 0)
+		dev_err(dp->dev, "Could not write to GRF: %d\n", ret);
+
+	clk_disable_unprepare(dp->grfclk);
 }
 
 static void rockchip_dp_drm_encoder_nop(struct drm_encoder *encoder)
@@ -143,22 +186,29 @@ rockchip_dp_drm_encoder_atomic_check(struct drm_encoder *encoder,
 				      struct drm_connector_state *conn_state)
 {
 	struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state);
+	struct rockchip_dp_device *dp = to_dp(encoder);
+	int ret;
 
 	/*
-	 * FIXME(Yakir): driver should configure the CRTC output video
-	 * mode with the display information which indicated the monitor
-	 * support colorimetry.
-	 *
-	 * But don't know why the CRTC driver seems could only output the
-	 * RGBaaa rightly. For example, if connect the "innolux,n116bge"
-	 * eDP screen, EDID would indicated that screen only accepted the
-	 * 6bpc mode. But if I configure CRTC to RGB666 output, then eDP
-	 * screen would show a blue picture (RGB888 show a green picture).
-	 * But if I configure CTRC to RGBaaa, and eDP driver still keep
-	 * RGB666 input video mode, then screen would works prefect.
+	 * The hardware IC designed that VOP must output the RGB10 video
+	 * format to eDP controller, and if eDP panel only support RGB8,
+	 * then eDP controller should cut down the video data, not via VOP
+	 * controller, that's why we need to hardcode the VOP output mode
+	 * to RGA10 here.
 	 */
+
 	s->output_mode = ROCKCHIP_OUT_MODE_AAAA;
 	s->output_type = DRM_MODE_CONNECTOR_eDP;
+	if (dp->data->chip_type == RK3399_EDP) {
+		/*
+		 * For RK3399, VOP Lit must code the out mode to RGB888,
+		 * VOP Big must code the out mode to RGB10.
+		 */
+		ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node,
+							encoder);
+		if (ret > 0)
+			s->output_mode = ROCKCHIP_OUT_MODE_P888;
+	}
 
 	return 0;
 }
@@ -192,6 +242,16 @@ static int rockchip_dp_init(struct rockchip_dp_device *dp)
 		return PTR_ERR(dp->grf);
 	}
 
+	dp->grfclk = devm_clk_get(dev, "grf");
+	if (PTR_ERR(dp->grfclk) == -ENOENT) {
+		dp->grfclk = NULL;
+	} else if (PTR_ERR(dp->grfclk) == -EPROBE_DEFER) {
+		return -EPROBE_DEFER;
+	} else if (IS_ERR(dp->grfclk)) {
+		dev_err(dev, "failed to get grf clock\n");
+		return PTR_ERR(dp->grfclk);
+	}
+
 	dp->pclk = devm_clk_get(dev, "pclk");
 	if (IS_ERR(dp->pclk)) {
 		dev_err(dev, "failed to get pclk property\n");
@@ -213,6 +273,7 @@ static int rockchip_dp_init(struct rockchip_dp_device *dp)
 	ret = rockchip_dp_pre_init(dp);
 	if (ret < 0) {
 		dev_err(dp->dev, "failed to pre init %d\n", ret);
+		clk_disable_unprepare(dp->pclk);
 		return ret;
 	}
 
@@ -246,6 +307,7 @@ static int rockchip_dp_bind(struct device *dev, struct device *master,
 			    void *data)
 {
 	struct rockchip_dp_device *dp = dev_get_drvdata(dev);
+	const struct rockchip_dp_chip_data *dp_data;
 	struct drm_device *drm_dev = data;
 	int ret;
 
@@ -256,10 +318,15 @@ static int rockchip_dp_bind(struct device *dev, struct device *master,
 	 */
 	dev_set_drvdata(dev, NULL);
 
+	dp_data = of_device_get_match_data(dev);
+	if (!dp_data)
+		return -ENODEV;
+
 	ret = rockchip_dp_init(dp);
 	if (ret < 0)
 		return ret;
 
+	dp->data = dp_data;
 	dp->drm_dev = drm_dev;
 
 	ret = rockchip_dp_drm_create_encoder(dp);
@@ -270,9 +337,10 @@ static int rockchip_dp_bind(struct device *dev, struct device *master,
 
 	dp->plat_data.encoder = &dp->encoder;
 
-	dp->plat_data.dev_type = RK3288_DP;
+	dp->plat_data.dev_type = dp->data->chip_type;
 	dp->plat_data.power_on = rockchip_dp_poweron;
 	dp->plat_data.power_off = rockchip_dp_powerdown;
+	dp->plat_data.get_modes = rockchip_dp_get_modes;
 
 	return analogix_dp_bind(dev, dp->drm_dev, &dp->plat_data);
 }
@@ -292,38 +360,33 @@ static int rockchip_dp_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *panel_node, *port, *endpoint;
+	struct drm_panel *panel = NULL;
 	struct rockchip_dp_device *dp;
-	struct drm_panel *panel;
 
 	port = of_graph_get_port_by_id(dev->of_node, 1);
-	if (!port) {
-		dev_err(dev, "can't find output port\n");
-		return -EINVAL;
-	}
-
-	endpoint = of_get_child_by_name(port, "endpoint");
-	of_node_put(port);
-	if (!endpoint) {
-		dev_err(dev, "no output endpoint found\n");
-		return -EINVAL;
-	}
-
-	panel_node = of_graph_get_remote_port_parent(endpoint);
-	of_node_put(endpoint);
-	if (!panel_node) {
-		dev_err(dev, "no output node found\n");
-		return -EINVAL;
-	}
-
-	panel = of_drm_find_panel(panel_node);
-	if (!panel) {
-		DRM_ERROR("failed to find panel\n");
+	if (port) {
+		endpoint = of_get_child_by_name(port, "endpoint");
+		of_node_put(port);
+		if (!endpoint) {
+			dev_err(dev, "no output endpoint found\n");
+			return -EINVAL;
+		}
+
+		panel_node = of_graph_get_remote_port_parent(endpoint);
+		of_node_put(endpoint);
+		if (!panel_node) {
+			dev_err(dev, "no output node found\n");
+			return -EINVAL;
+		}
+
+		panel = of_drm_find_panel(panel_node);
 		of_node_put(panel_node);
-		return -EPROBE_DEFER;
+		if (!panel) {
+			DRM_ERROR("failed to find panel\n");
+			return -EPROBE_DEFER;
+		}
 	}
 
-	of_node_put(panel_node);
-
 	dp = devm_kzalloc(dev, sizeof(*dp), GFP_KERNEL);
 	if (!dp)
 		return -ENOMEM;
@@ -349,24 +412,30 @@ static int rockchip_dp_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct dev_pm_ops rockchip_dp_pm_ops = {
 #ifdef CONFIG_PM_SLEEP
-static int rockchip_dp_suspend(struct device *dev)
-{
-	return analogix_dp_suspend(dev);
-}
-
-static int rockchip_dp_resume(struct device *dev)
-{
-	return analogix_dp_resume(dev);
-}
+	.suspend = analogix_dp_suspend,
+	.resume_early = analogix_dp_resume,
 #endif
+};
 
-static const struct dev_pm_ops rockchip_dp_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(rockchip_dp_suspend, rockchip_dp_resume)
+static const struct rockchip_dp_chip_data rk3399_edp = {
+	.lcdsel_grf_reg = RK3399_GRF_SOC_CON20,
+	.lcdsel_big = HIWORD_UPDATE(0, RK3399_EDP_LCDC_SEL),
+	.lcdsel_lit = HIWORD_UPDATE(RK3399_EDP_LCDC_SEL, RK3399_EDP_LCDC_SEL),
+	.chip_type = RK3399_EDP,
+};
+
+static const struct rockchip_dp_chip_data rk3288_dp = {
+	.lcdsel_grf_reg = RK3288_GRF_SOC_CON6,
+	.lcdsel_big = HIWORD_UPDATE(0, RK3288_EDP_LCDC_SEL),
+	.lcdsel_lit = HIWORD_UPDATE(RK3288_EDP_LCDC_SEL, RK3288_EDP_LCDC_SEL),
+	.chip_type = RK3288_DP,
 };
 
 static const struct of_device_id rockchip_dp_dt_ids[] = {
-	{.compatible = "rockchip,rk3288-dp",},
+	{.compatible = "rockchip,rk3288-dp", .data = &rk3288_dp },
+	{.compatible = "rockchip,rk3399-edp", .data = &rk3399_edp },
 	{}
 };
 MODULE_DEVICE_TABLE(of, rockchip_dp_dt_ids);
diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
index dedc65b40f36..ca22e5ee89ca 100644
--- a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
@@ -964,18 +964,9 @@ static enum drm_mode_status dw_mipi_dsi_mode_valid(
 	return mode_status;
 }
 
-static struct drm_encoder *dw_mipi_dsi_connector_best_encoder(
-					struct drm_connector *connector)
-{
-	struct dw_mipi_dsi *dsi = con_to_dsi(connector);
-
-	return &dsi->encoder;
-}
-
 static struct drm_connector_helper_funcs dw_mipi_dsi_connector_helper_funcs = {
 	.get_modes = dw_mipi_dsi_connector_get_modes,
 	.mode_valid = dw_mipi_dsi_mode_valid,
-	.best_encoder = dw_mipi_dsi_connector_best_encoder,
 };
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
index 801110f65a63..0665fb915579 100644
--- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
@@ -15,7 +15,6 @@
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_edid.h>
-#include <drm/drm_encoder_slave.h>
 #include <drm/bridge/dw_hdmi.h>
 
 #include "rockchip_drm_drv.h"
diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c
index f8b4feb60b25..006260de9dbd 100644
--- a/drivers/gpu/drm/rockchip/inno_hdmi.c
+++ b/drivers/gpu/drm/rockchip/inno_hdmi.c
@@ -579,14 +579,6 @@ inno_hdmi_connector_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-static struct drm_encoder *
-inno_hdmi_connector_best_encoder(struct drm_connector *connector)
-{
-	struct inno_hdmi *hdmi = to_inno_hdmi(connector);
-
-	return &hdmi->encoder;
-}
-
 static int
 inno_hdmi_probe_single_connector_modes(struct drm_connector *connector,
 				       uint32_t maxX, uint32_t maxY)
@@ -613,7 +605,6 @@ static struct drm_connector_funcs inno_hdmi_connector_funcs = {
 static struct drm_connector_helper_funcs inno_hdmi_connector_helper_funcs = {
 	.get_modes = inno_hdmi_connector_get_modes,
 	.mode_valid = inno_hdmi_connector_mode_valid,
-	.best_encoder = inno_hdmi_connector_best_encoder,
 };
 
 static int inno_hdmi_register(struct drm_device *drm, struct inno_hdmi *hdmi)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
index a409d1f703cb..a822d49a255a 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
@@ -19,11 +19,13 @@
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_gem_cma_helper.h>
 #include <linux/dma-mapping.h>
 #include <linux/pm_runtime.h>
 #include <linux/module.h>
 #include <linux/of_graph.h>
 #include <linux/component.h>
+#include <linux/console.h>
 
 #include "rockchip_drm_drv.h"
 #include "rockchip_drm_fb.h"
@@ -37,6 +39,7 @@
 #define DRIVER_MINOR	0
 
 static bool is_support_iommu = true;
+static struct drm_driver rockchip_drm_driver;
 
 /*
  * Attach a (component) device to the shared drm dma mapping from master drm
@@ -76,7 +79,7 @@ int rockchip_register_crtc_funcs(struct drm_crtc *crtc,
 	int pipe = drm_crtc_index(crtc);
 	struct rockchip_drm_private *priv = crtc->dev->dev_private;
 
-	if (pipe > ROCKCHIP_MAX_CRTC)
+	if (pipe >= ROCKCHIP_MAX_CRTC)
 		return -EINVAL;
 
 	priv->crtc_funcs[pipe] = crtc_funcs;
@@ -89,7 +92,7 @@ void rockchip_unregister_crtc_funcs(struct drm_crtc *crtc)
 	int pipe = drm_crtc_index(crtc);
 	struct rockchip_drm_private *priv = crtc->dev->dev_private;
 
-	if (pipe > ROCKCHIP_MAX_CRTC)
+	if (pipe >= ROCKCHIP_MAX_CRTC)
 		return;
 
 	priv->crtc_funcs[pipe] = NULL;
@@ -132,20 +135,24 @@ static void rockchip_drm_crtc_disable_vblank(struct drm_device *dev,
 		priv->crtc_funcs[pipe]->disable_vblank(crtc);
 }
 
-static int rockchip_drm_load(struct drm_device *drm_dev, unsigned long flags)
+static int rockchip_drm_bind(struct device *dev)
 {
+	struct drm_device *drm_dev;
 	struct rockchip_drm_private *private;
 	struct dma_iommu_mapping *mapping = NULL;
-	struct device *dev = drm_dev->dev;
-	struct drm_connector *connector;
 	int ret;
 
-	private = devm_kzalloc(drm_dev->dev, sizeof(*private), GFP_KERNEL);
-	if (!private)
+	drm_dev = drm_dev_alloc(&rockchip_drm_driver, dev);
+	if (!drm_dev)
 		return -ENOMEM;
 
-	mutex_init(&private->commit.lock);
-	INIT_WORK(&private->commit.work, rockchip_drm_atomic_work);
+	dev_set_drvdata(dev, drm_dev);
+
+	private = devm_kzalloc(drm_dev->dev, sizeof(*private), GFP_KERNEL);
+	if (!private) {
+		ret = -ENOMEM;
+		goto err_free;
+	}
 
 	drm_dev->dev_private = private;
 
@@ -186,23 +193,6 @@ static int rockchip_drm_load(struct drm_device *drm_dev, unsigned long flags)
 	if (ret)
 		goto err_detach_device;
 
-	/*
-	 * All components are now added, we can publish the connector sysfs
-	 * entries to userspace.  This will generate hotplug events and so
-	 * userspace will expect to be able to access DRM at this point.
-	 */
-	list_for_each_entry(connector, &drm_dev->mode_config.connector_list,
-			head) {
-		ret = drm_connector_register(connector);
-		if (ret) {
-			dev_err(drm_dev->dev,
-				"[CONNECTOR:%d:%s] drm_connector_register failed: %d\n",
-				connector->base.id,
-				connector->name, ret);
-			goto err_unbind;
-		}
-	}
-
 	/* init kms poll for handling hpd */
 	drm_kms_helper_poll_init(drm_dev);
 
@@ -222,14 +212,19 @@ static int rockchip_drm_load(struct drm_device *drm_dev, unsigned long flags)
 	if (ret)
 		goto err_vblank_cleanup;
 
+	ret = drm_dev_register(drm_dev, 0);
+	if (ret)
+		goto err_fbdev_fini;
+
 	if (is_support_iommu)
 		arm_iommu_release_mapping(mapping);
 	return 0;
+err_fbdev_fini:
+	rockchip_drm_fbdev_fini(drm_dev);
 err_vblank_cleanup:
 	drm_vblank_cleanup(drm_dev);
 err_kms_helper_poll_fini:
 	drm_kms_helper_poll_fini(drm_dev);
-err_unbind:
 	component_unbind_all(dev, drm_dev);
 err_detach_device:
 	if (is_support_iommu)
@@ -240,12 +235,14 @@ err_release_mapping:
 err_config_cleanup:
 	drm_mode_config_cleanup(drm_dev);
 	drm_dev->dev_private = NULL;
+err_free:
+	drm_dev_unref(drm_dev);
 	return ret;
 }
 
-static int rockchip_drm_unload(struct drm_device *drm_dev)
+static void rockchip_drm_unbind(struct device *dev)
 {
-	struct device *dev = drm_dev->dev;
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
 	rockchip_drm_fbdev_fini(drm_dev);
 	drm_vblank_cleanup(drm_dev);
@@ -255,32 +252,12 @@ static int rockchip_drm_unload(struct drm_device *drm_dev)
 		arm_iommu_detach_device(dev);
 	drm_mode_config_cleanup(drm_dev);
 	drm_dev->dev_private = NULL;
-
-	return 0;
-}
-
-static void rockchip_drm_crtc_cancel_pending_vblank(struct drm_crtc *crtc,
-						    struct drm_file *file_priv)
-{
-	struct rockchip_drm_private *priv = crtc->dev->dev_private;
-	int pipe = drm_crtc_index(crtc);
-
-	if (pipe < ROCKCHIP_MAX_CRTC &&
-	    priv->crtc_funcs[pipe] &&
-	    priv->crtc_funcs[pipe]->cancel_pending_vblank)
-		priv->crtc_funcs[pipe]->cancel_pending_vblank(crtc, file_priv);
-}
-
-static void rockchip_drm_preclose(struct drm_device *dev,
-				  struct drm_file *file_priv)
-{
-	struct drm_crtc *crtc;
-
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
-		rockchip_drm_crtc_cancel_pending_vblank(crtc, file_priv);
+	drm_dev_unregister(drm_dev);
+	drm_dev_unref(drm_dev);
+	dev_set_drvdata(dev, NULL);
 }
 
-void rockchip_drm_lastclose(struct drm_device *dev)
+static void rockchip_drm_lastclose(struct drm_device *dev)
 {
 	struct rockchip_drm_private *priv = dev->dev_private;
 
@@ -300,23 +277,15 @@ static const struct file_operations rockchip_drm_driver_fops = {
 	.release = drm_release,
 };
 
-const struct vm_operations_struct rockchip_drm_vm_ops = {
-	.open = drm_gem_vm_open,
-	.close = drm_gem_vm_close,
-};
-
 static struct drm_driver rockchip_drm_driver = {
 	.driver_features	= DRIVER_MODESET | DRIVER_GEM |
 				  DRIVER_PRIME | DRIVER_ATOMIC,
-	.load			= rockchip_drm_load,
-	.unload			= rockchip_drm_unload,
-	.preclose		= rockchip_drm_preclose,
 	.lastclose		= rockchip_drm_lastclose,
 	.get_vblank_counter	= drm_vblank_no_hw_counter,
 	.enable_vblank		= rockchip_drm_crtc_enable_vblank,
 	.disable_vblank		= rockchip_drm_crtc_disable_vblank,
-	.gem_vm_ops		= &rockchip_drm_vm_ops,
-	.gem_free_object	= rockchip_gem_free_object,
+	.gem_vm_ops		= &drm_gem_cma_vm_ops,
+	.gem_free_object_unlocked = rockchip_gem_free_object,
 	.dumb_create		= rockchip_gem_dumb_create,
 	.dumb_map_offset	= rockchip_gem_dumb_map_offset,
 	.dumb_destroy		= drm_gem_dumb_destroy,
@@ -337,25 +306,38 @@ static struct drm_driver rockchip_drm_driver = {
 };
 
 #ifdef CONFIG_PM_SLEEP
-static int rockchip_drm_sys_suspend(struct device *dev)
+void rockchip_drm_fb_suspend(struct drm_device *drm)
 {
-	struct drm_device *drm = dev_get_drvdata(dev);
-	struct drm_connector *connector;
+	struct rockchip_drm_private *priv = drm->dev_private;
 
-	if (!drm)
-		return 0;
+	console_lock();
+	drm_fb_helper_set_suspend(&priv->fbdev_helper, 1);
+	console_unlock();
+}
 
-	drm_modeset_lock_all(drm);
-	list_for_each_entry(connector, &drm->mode_config.connector_list, head) {
-		int old_dpms = connector->dpms;
+void rockchip_drm_fb_resume(struct drm_device *drm)
+{
+	struct rockchip_drm_private *priv = drm->dev_private;
 
-		if (connector->funcs->dpms)
-			connector->funcs->dpms(connector, DRM_MODE_DPMS_OFF);
+	console_lock();
+	drm_fb_helper_set_suspend(&priv->fbdev_helper, 0);
+	console_unlock();
+}
 
-		/* Set the old mode back to the connector for resume */
-		connector->dpms = old_dpms;
+static int rockchip_drm_sys_suspend(struct device *dev)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct rockchip_drm_private *priv = drm->dev_private;
+
+	drm_kms_helper_poll_disable(drm);
+	rockchip_drm_fb_suspend(drm);
+
+	priv->state = drm_atomic_helper_suspend(drm);
+	if (IS_ERR(priv->state)) {
+		rockchip_drm_fb_resume(drm);
+		drm_kms_helper_poll_enable(drm);
+		return PTR_ERR(priv->state);
 	}
-	drm_modeset_unlock_all(drm);
 
 	return 0;
 }
@@ -363,47 +345,11 @@ static int rockchip_drm_sys_suspend(struct device *dev)
 static int rockchip_drm_sys_resume(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct drm_connector *connector;
-	enum drm_connector_status status;
-	bool changed = false;
-
-	if (!drm)
-		return 0;
+	struct rockchip_drm_private *priv = drm->dev_private;
 
-	drm_modeset_lock_all(drm);
-	list_for_each_entry(connector, &drm->mode_config.connector_list, head) {
-		int desired_mode = connector->dpms;
-
-		/*
-		 * at suspend time, we save dpms to connector->dpms,
-		 * restore the old_dpms, and at current time, the connector
-		 * dpms status must be DRM_MODE_DPMS_OFF.
-		 */
-		connector->dpms = DRM_MODE_DPMS_OFF;
-
-		/*
-		 * If the connector has been disconnected during suspend,
-		 * disconnect it from the encoder and leave it off. We'll notify
-		 * userspace at the end.
-		 */
-		if (desired_mode == DRM_MODE_DPMS_ON) {
-			status = connector->funcs->detect(connector, true);
-			if (status == connector_status_disconnected) {
-				connector->encoder = NULL;
-				connector->status = status;
-				changed = true;
-				continue;
-			}
-		}
-		if (connector->funcs->dpms)
-			connector->funcs->dpms(connector, desired_mode);
-	}
-	drm_modeset_unlock_all(drm);
-
-	drm_helper_resume_force_mode(drm);
-
-	if (changed)
-		drm_kms_helper_hotplug_event(drm);
+	drm_atomic_helper_resume(drm, priv->state);
+	rockchip_drm_fb_resume(drm);
+	drm_kms_helper_poll_enable(drm);
 
 	return 0;
 }
@@ -444,37 +390,6 @@ static void rockchip_add_endpoints(struct device *dev,
 	}
 }
 
-static int rockchip_drm_bind(struct device *dev)
-{
-	struct drm_device *drm;
-	int ret;
-
-	drm = drm_dev_alloc(&rockchip_drm_driver, dev);
-	if (!drm)
-		return -ENOMEM;
-
-	ret = drm_dev_register(drm, 0);
-	if (ret)
-		goto err_free;
-
-	dev_set_drvdata(dev, drm);
-
-	return 0;
-
-err_free:
-	drm_dev_unref(drm);
-	return ret;
-}
-
-static void rockchip_drm_unbind(struct device *dev)
-{
-	struct drm_device *drm = dev_get_drvdata(dev);
-
-	drm_dev_unregister(drm);
-	drm_dev_unref(drm);
-	dev_set_drvdata(dev, NULL);
-}
-
 static const struct component_master_ops rockchip_drm_ops = {
 	.bind = rockchip_drm_bind,
 	.unbind = rockchip_drm_unbind,
@@ -518,6 +433,7 @@ static int rockchip_drm_platform_probe(struct platform_device *pdev)
 			is_support_iommu = false;
 		}
 
+		of_node_put(iommu);
 		component_match_add(dev, &match, compare_of, port->parent);
 		of_node_put(port);
 	}
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h
index 56f43a364c7f..ea3932940061 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h
@@ -40,14 +40,6 @@ struct rockchip_crtc_funcs {
 	int (*enable_vblank)(struct drm_crtc *crtc);
 	void (*disable_vblank)(struct drm_crtc *crtc);
 	void (*wait_for_update)(struct drm_crtc *crtc);
-	void (*cancel_pending_vblank)(struct drm_crtc *crtc, struct drm_file *file_priv);
-};
-
-struct rockchip_atomic_commit {
-	struct work_struct	work;
-	struct drm_atomic_state *state;
-	struct drm_device *dev;
-	struct mutex lock;
 };
 
 struct rockchip_crtc_state {
@@ -68,11 +60,9 @@ struct rockchip_drm_private {
 	struct drm_fb_helper fbdev_helper;
 	struct drm_gem_object *fbdev_bo;
 	const struct rockchip_crtc_funcs *crtc_funcs[ROCKCHIP_MAX_CRTC];
-
-	struct rockchip_atomic_commit commit;
+	struct drm_atomic_state *state;
 };
 
-void rockchip_drm_atomic_work(struct work_struct *work);
 int rockchip_register_crtc_funcs(struct drm_crtc *crtc,
 				 const struct rockchip_crtc_funcs *crtc_funcs);
 void rockchip_unregister_crtc_funcs(struct drm_crtc *crtc);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
index 755cfdba61cd..55c52734c52d 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
@@ -20,6 +20,7 @@
 #include <drm/drm_crtc_helper.h>
 
 #include "rockchip_drm_drv.h"
+#include "rockchip_drm_fb.h"
 #include "rockchip_drm_gem.h"
 
 #define to_rockchip_fb(x) container_of(x, struct rockchip_drm_fb, fb)
@@ -43,14 +44,10 @@ struct drm_gem_object *rockchip_fb_get_gem_obj(struct drm_framebuffer *fb,
 static void rockchip_drm_fb_destroy(struct drm_framebuffer *fb)
 {
 	struct rockchip_drm_fb *rockchip_fb = to_rockchip_fb(fb);
-	struct drm_gem_object *obj;
 	int i;
 
-	for (i = 0; i < ROCKCHIP_MAX_FB_BUFFER; i++) {
-		obj = rockchip_fb->obj[i];
-		if (obj)
-			drm_gem_object_unreference_unlocked(obj);
-	}
+	for (i = 0; i < ROCKCHIP_MAX_FB_BUFFER; i++)
+		drm_gem_object_unreference_unlocked(rockchip_fb->obj[i]);
 
 	drm_framebuffer_cleanup(fb);
 	kfree(rockchip_fb);
@@ -228,87 +225,32 @@ rockchip_atomic_wait_for_complete(struct drm_device *dev, struct drm_atomic_stat
 }
 
 static void
-rockchip_atomic_commit_complete(struct rockchip_atomic_commit *commit)
+rockchip_atomic_commit_tail(struct drm_atomic_state *state)
 {
-	struct drm_atomic_state *state = commit->state;
-	struct drm_device *dev = commit->dev;
+	struct drm_device *dev = state->dev;
 
-	/*
-	 * TODO: do fence wait here.
-	 */
-
-	/*
-	 * Rockchip crtc support runtime PM, can't update display planes
-	 * when crtc is disabled.
-	 *
-	 * drm_atomic_helper_commit comments detail that:
-	 *     For drivers supporting runtime PM the recommended sequence is
-	 *
-	 *     drm_atomic_helper_commit_modeset_disables(dev, state);
-	 *
-	 *     drm_atomic_helper_commit_modeset_enables(dev, state);
-	 *
-	 *     drm_atomic_helper_commit_planes(dev, state, true);
-	 *
-	 * See the kerneldoc entries for these three functions for more details.
-	 */
 	drm_atomic_helper_commit_modeset_disables(dev, state);
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
 
 	drm_atomic_helper_commit_planes(dev, state, true);
 
+	drm_atomic_helper_commit_hw_done(state);
+
 	rockchip_atomic_wait_for_complete(dev, state);
 
 	drm_atomic_helper_cleanup_planes(dev, state);
-
-	drm_atomic_state_free(state);
-}
-
-void rockchip_drm_atomic_work(struct work_struct *work)
-{
-	struct rockchip_atomic_commit *commit = container_of(work,
-					struct rockchip_atomic_commit, work);
-
-	rockchip_atomic_commit_complete(commit);
 }
 
-int rockchip_drm_atomic_commit(struct drm_device *dev,
-			       struct drm_atomic_state *state,
-			       bool nonblock)
-{
-	struct rockchip_drm_private *private = dev->dev_private;
-	struct rockchip_atomic_commit *commit = &private->commit;
-	int ret;
-
-	ret = drm_atomic_helper_prepare_planes(dev, state);
-	if (ret)
-		return ret;
-
-	/* serialize outstanding nonblocking commits */
-	mutex_lock(&commit->lock);
-	flush_work(&commit->work);
-
-	drm_atomic_helper_swap_state(dev, state);
-
-	commit->dev = dev;
-	commit->state = state;
-
-	if (nonblock)
-		schedule_work(&commit->work);
-	else
-		rockchip_atomic_commit_complete(commit);
-
-	mutex_unlock(&commit->lock);
-
-	return 0;
-}
+static struct drm_mode_config_helper_funcs rockchip_mode_config_helpers = {
+	.atomic_commit_tail = rockchip_atomic_commit_tail,
+};
 
 static const struct drm_mode_config_funcs rockchip_drm_mode_config_funcs = {
 	.fb_create = rockchip_user_fb_create,
 	.output_poll_changed = rockchip_drm_output_poll_changed,
 	.atomic_check = drm_atomic_helper_check,
-	.atomic_commit = rockchip_drm_atomic_commit,
+	.atomic_commit = drm_atomic_helper_commit,
 };
 
 struct drm_framebuffer *
@@ -339,4 +281,5 @@ void rockchip_drm_mode_config_init(struct drm_device *dev)
 	dev->mode_config.max_height = 4096;
 
 	dev->mode_config.funcs = &rockchip_drm_mode_config_funcs;
+	dev->mode_config.helper_private = &rockchip_mode_config_helpers;
 }
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c
index f261512bb4a0..207e01de6e32 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c
@@ -108,7 +108,7 @@ static int rockchip_drm_fbdev_create(struct drm_fb_helper *helper,
 	fbi->screen_size = rk_obj->base.size;
 	fbi->fix.smem_len = rk_obj->base.size;
 
-	DRM_DEBUG_KMS("FB [%dx%d]-%d kvaddr=%p offset=%ld size=%d\n",
+	DRM_DEBUG_KMS("FB [%dx%d]-%d kvaddr=%p offset=%ld size=%zu\n",
 		      fb->width, fb->height, fb->depth, rk_obj->kvaddr,
 		      offset, size);
 
@@ -156,9 +156,6 @@ int rockchip_drm_fbdev_init(struct drm_device *dev)
 		goto err_drm_fb_helper_fini;
 	}
 
-	/* disable all the possible outputs/crtcs before entering KMS mode */
-	drm_helper_disable_unused_functions(dev);
-
 	ret = drm_fb_helper_initial_config(helper, PREFERRED_BPP);
 	if (ret < 0) {
 		dev_err(dev->dev, "Failed to set initial hw config - %d.\n",
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
index 9c2d8a894093..059e902f872d 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
@@ -38,7 +38,7 @@ static int rockchip_gem_alloc_buf(struct rockchip_gem_object *rk_obj,
 					 &rk_obj->dma_addr, GFP_KERNEL,
 					 &rk_obj->dma_attrs);
 	if (!rk_obj->kvaddr) {
-		DRM_ERROR("failed to allocate %#x byte dma buffer", obj->size);
+		DRM_ERROR("failed to allocate %zu byte dma buffer", obj->size);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 1c4d5b5a70a2..91305eb7d312 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -98,7 +98,9 @@ struct vop_win {
 	const struct vop_win_data *data;
 	struct vop *vop;
 
-	struct vop_plane_state state;
+	/* protected by dev->event_lock */
+	bool enable;
+	dma_addr_t yrgb_mst;
 };
 
 struct vop {
@@ -112,6 +114,8 @@ struct vop {
 	bool vsync_work_pending;
 	struct completion dsp_hold_completion;
 	struct completion wait_update_complete;
+
+	/* protected by dev->event_lock */
 	struct drm_pending_vblank_event *event;
 
 	const struct vop_data *data;
@@ -324,9 +328,9 @@ static void scl_vop_cal_scl_fac(struct vop *vop, const struct vop_win_data *win,
 			    scl_cal_scale2(src_h, dst_h));
 		if (is_yuv) {
 			VOP_SCL_SET(vop, win, scale_cbcr_x,
-				    scl_cal_scale2(src_w, dst_w));
+				    scl_cal_scale2(cbcr_src_w, dst_w));
 			VOP_SCL_SET(vop, win, scale_cbcr_y,
-				    scl_cal_scale2(src_h, dst_h));
+				    scl_cal_scale2(cbcr_src_h, dst_h));
 		}
 		return;
 	}
@@ -431,9 +435,6 @@ static void vop_enable(struct drm_crtc *crtc)
 	struct vop *vop = to_vop(crtc);
 	int ret;
 
-	if (vop->is_enabled)
-		return;
-
 	ret = pm_runtime_get_sync(vop->dev);
 	if (ret < 0) {
 		dev_err(vop->dev, "failed to get pm runtime: %d\n", ret);
@@ -501,8 +502,7 @@ static void vop_crtc_disable(struct drm_crtc *crtc)
 	struct vop *vop = to_vop(crtc);
 	int i;
 
-	if (!vop->is_enabled)
-		return;
+	WARN_ON(vop->event);
 
 	/*
 	 * We need to make sure that all windows are disabled before we
@@ -553,6 +553,14 @@ static void vop_crtc_disable(struct drm_crtc *crtc)
 	clk_disable(vop->aclk);
 	clk_disable(vop->hclk);
 	pm_runtime_put(vop->dev);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+
+		crtc->state->event = NULL;
+	}
 }
 
 static void vop_plane_destroy(struct drm_plane *plane)
@@ -618,6 +626,7 @@ static int vop_plane_atomic_check(struct drm_plane *plane,
 
 	ret = drm_plane_helper_check_update(plane, crtc, state->fb,
 					    src, dest, &clip,
+					    state->rotation,
 					    min_scale,
 					    max_scale,
 					    true, true, &visible);
@@ -658,6 +667,11 @@ static void vop_plane_atomic_disable(struct drm_plane *plane,
 	if (!old_state->crtc)
 		return;
 
+	spin_lock_irq(&plane->dev->event_lock);
+	vop_win->enable = false;
+	vop_win->yrgb_mst = 0;
+	spin_unlock_irq(&plane->dev->event_lock);
+
 	spin_lock(&vop->reg_lock);
 
 	VOP_WIN_SET(vop, win, enable, 0);
@@ -692,7 +706,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	/*
 	 * can't update plane when vop is disabled.
 	 */
-	if (!crtc)
+	if (WARN_ON(!crtc))
 		return;
 
 	if (WARN_ON(!vop->is_enabled))
@@ -721,6 +735,11 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	offset += (src->y1 >> 16) * fb->pitches[0];
 	vop_plane_state->yrgb_mst = rk_obj->dma_addr + offset + fb->offsets[0];
 
+	spin_lock_irq(&plane->dev->event_lock);
+	vop_win->enable = true;
+	vop_win->yrgb_mst = vop_plane_state->yrgb_mst;
+	spin_unlock_irq(&plane->dev->event_lock);
+
 	spin_lock(&vop->reg_lock);
 
 	VOP_WIN_SET(vop, win, format, vop_plane_state->format);
@@ -779,7 +798,7 @@ static const struct drm_plane_helper_funcs plane_helper_funcs = {
 	.atomic_disable = vop_plane_atomic_disable,
 };
 
-void vop_atomic_plane_reset(struct drm_plane *plane)
+static void vop_atomic_plane_reset(struct drm_plane *plane)
 {
 	struct vop_plane_state *vop_plane_state =
 					to_vop_plane_state(plane->state);
@@ -796,7 +815,7 @@ void vop_atomic_plane_reset(struct drm_plane *plane)
 	plane->state->plane = plane;
 }
 
-struct drm_plane_state *
+static struct drm_plane_state *
 vop_atomic_plane_duplicate_state(struct drm_plane *plane)
 {
 	struct vop_plane_state *old_vop_plane_state;
@@ -876,30 +895,10 @@ static void vop_crtc_wait_for_update(struct drm_crtc *crtc)
 	WARN_ON(!wait_for_completion_timeout(&vop->wait_update_complete, 100));
 }
 
-static void vop_crtc_cancel_pending_vblank(struct drm_crtc *crtc,
-					   struct drm_file *file_priv)
-{
-	struct drm_device *drm = crtc->dev;
-	struct vop *vop = to_vop(crtc);
-	struct drm_pending_vblank_event *e;
-	unsigned long flags;
-
-	spin_lock_irqsave(&drm->event_lock, flags);
-	e = vop->event;
-	if (e && e->base.file_priv == file_priv) {
-		vop->event = NULL;
-
-		e->base.destroy(&e->base);
-		file_priv->event_space += sizeof(e->event);
-	}
-	spin_unlock_irqrestore(&drm->event_lock, flags);
-}
-
 static const struct rockchip_crtc_funcs private_crtc_funcs = {
 	.enable_vblank = vop_crtc_enable_vblank,
 	.disable_vblank = vop_crtc_disable_vblank,
 	.wait_for_update = vop_crtc_wait_for_update,
-	.cancel_pending_vblank = vop_crtc_cancel_pending_vblank,
 };
 
 static bool vop_crtc_mode_fixup(struct drm_crtc *crtc,
@@ -931,6 +930,8 @@ static void vop_crtc_enable(struct drm_crtc *crtc)
 	u16 vact_end = vact_st + vdisplay;
 	uint32_t val;
 
+	WARN_ON(vop->event);
+
 	vop_enable(crtc);
 	/*
 	 * If dclk rate is zero, mean that scanout is stop,
@@ -1027,12 +1028,15 @@ static void vop_crtc_atomic_begin(struct drm_crtc *crtc,
 {
 	struct vop *vop = to_vop(crtc);
 
+	spin_lock_irq(&crtc->dev->event_lock);
 	if (crtc->state->event) {
 		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+		WARN_ON(vop->event);
 
 		vop->event = crtc->state->event;
 		crtc->state->event = NULL;
 	}
+	spin_unlock_irq(&crtc->dev->event_lock);
 }
 
 static const struct drm_crtc_helper_funcs vop_crtc_helper_funcs = {
@@ -1048,6 +1052,17 @@ static void vop_crtc_destroy(struct drm_crtc *crtc)
 	drm_crtc_cleanup(crtc);
 }
 
+static void vop_crtc_reset(struct drm_crtc *crtc)
+{
+	if (crtc->state)
+		__drm_atomic_helper_crtc_destroy_state(crtc->state);
+	kfree(crtc->state);
+
+	crtc->state = kzalloc(sizeof(struct rockchip_crtc_state), GFP_KERNEL);
+	if (crtc->state)
+		crtc->state->crtc = crtc;
+}
+
 static struct drm_crtc_state *vop_crtc_duplicate_state(struct drm_crtc *crtc)
 {
 	struct rockchip_crtc_state *rockchip_state;
@@ -1073,23 +1088,21 @@ static const struct drm_crtc_funcs vop_crtc_funcs = {
 	.set_config = drm_atomic_helper_set_config,
 	.page_flip = drm_atomic_helper_page_flip,
 	.destroy = vop_crtc_destroy,
-	.reset = drm_atomic_helper_crtc_reset,
+	.reset = vop_crtc_reset,
 	.atomic_duplicate_state = vop_crtc_duplicate_state,
 	.atomic_destroy_state = vop_crtc_destroy_state,
 };
 
 static bool vop_win_pending_is_complete(struct vop_win *vop_win)
 {
-	struct drm_plane *plane = &vop_win->base;
-	struct vop_plane_state *state = to_vop_plane_state(plane->state);
 	dma_addr_t yrgb_mst;
 
-	if (!state->enable)
+	if (!vop_win->enable)
 		return VOP_WIN_GET(vop_win->vop, vop_win->data, enable) == 0;
 
 	yrgb_mst = VOP_WIN_GET_YRGBADDR(vop_win->vop, vop_win->data);
 
-	return yrgb_mst == state->yrgb_mst;
+	return yrgb_mst == vop_win->yrgb_mst;
 }
 
 static void vop_handle_vblank(struct vop *vop)
@@ -1104,15 +1117,16 @@ static void vop_handle_vblank(struct vop *vop)
 			return;
 	}
 
+	spin_lock_irqsave(&drm->event_lock, flags);
 	if (vop->event) {
-		spin_lock_irqsave(&drm->event_lock, flags);
 
 		drm_crtc_send_vblank_event(crtc, vop->event);
 		drm_crtc_vblank_put(crtc);
 		vop->event = NULL;
 
-		spin_unlock_irqrestore(&drm->event_lock, flags);
 	}
+	spin_unlock_irqrestore(&drm->event_lock, flags);
+
 	if (!completion_done(&vop->wait_update_complete))
 		complete(&vop->wait_update_complete);
 }
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
index 3166b46a5893..919992cdc97e 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
@@ -190,7 +190,7 @@ static const struct vop_data rk3288_vop = {
 	.win_size = ARRAY_SIZE(rk3288_vop_win_data),
 };
 
-static const struct vop_scl_regs rk3066_win_scl = {
+static const struct vop_scl_regs rk3036_win_scl = {
 	.scale_yrgb_x = VOP_REG(RK3036_WIN0_SCL_FACTOR_YRGB, 0xffff, 0x0),
 	.scale_yrgb_y = VOP_REG(RK3036_WIN0_SCL_FACTOR_YRGB, 0xffff, 16),
 	.scale_cbcr_x = VOP_REG(RK3036_WIN0_SCL_FACTOR_CBR, 0xffff, 0x0),
@@ -198,7 +198,7 @@ static const struct vop_scl_regs rk3066_win_scl = {
 };
 
 static const struct vop_win_phy rk3036_win0_data = {
-	.scl = &rk3066_win_scl,
+	.scl = &rk3036_win_scl,
 	.data_formats = formats_win_full,
 	.nformats = ARRAY_SIZE(formats_win_full),
 	.enable = VOP_REG(RK3036_SYS_CTRL, 0x1, 0),
@@ -210,6 +210,7 @@ static const struct vop_win_phy rk3036_win0_data = {
 	.yrgb_mst = VOP_REG(RK3036_WIN0_YRGB_MST, 0xffffffff, 0),
 	.uv_mst = VOP_REG(RK3036_WIN0_CBR_MST, 0xffffffff, 0),
 	.yrgb_vir = VOP_REG(RK3036_WIN0_VIR, 0xffff, 0),
+	.uv_vir = VOP_REG(RK3036_WIN0_VIR, 0x1fff, 16),
 };
 
 static const struct vop_win_phy rk3036_win1_data = {
@@ -299,7 +300,7 @@ static int vop_remove(struct platform_device *pdev)
 	return 0;
 }
 
-struct platform_driver vop_platform_driver = {
+static struct platform_driver vop_platform_driver = {
 	.probe = vop_probe,
 	.remove = vop_remove,
 	.driver = {
diff --git a/drivers/gpu/drm/shmobile/Kconfig b/drivers/gpu/drm/shmobile/Kconfig
index 8d17d00ddb4b..c987c826daa3 100644
--- a/drivers/gpu/drm/shmobile/Kconfig
+++ b/drivers/gpu/drm/shmobile/Kconfig
@@ -6,7 +6,6 @@ config DRM_SHMOBILE
 	select BACKLIGHT_CLASS_DEVICE
 	select BACKLIGHT_LCD_SUPPORT
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_GEM_CMA_HELPER
 	help
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
index 1e154fc779d5..6547b1db460a 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
@@ -441,7 +441,7 @@ void shmob_drm_crtc_finish_page_flip(struct shmob_drm_crtc *scrtc)
 	scrtc->event = NULL;
 	if (event) {
 		drm_crtc_send_vblank_event(&scrtc->crtc, event);
-		drm_vblank_put(dev, 0);
+		drm_crtc_vblank_put(&scrtc->crtc);
 	}
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
@@ -467,7 +467,7 @@ static int shmob_drm_crtc_page_flip(struct drm_crtc *crtc,
 
 	if (event) {
 		event->pipe = 0;
-		drm_vblank_get(dev, 0);
+		drm_crtc_vblank_get(&scrtc->crtc);
 		spin_lock_irqsave(&dev->event_lock, flags);
 		scrtc->event = event;
 		spin_unlock_irqrestore(&dev->event_lock, flags);
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
index 7700ff172079..f0492603ea88 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_drv.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
@@ -259,12 +259,11 @@ static struct drm_driver shmob_drm_driver = {
 				| DRIVER_PRIME,
 	.load			= shmob_drm_load,
 	.unload			= shmob_drm_unload,
-	.set_busid		= drm_platform_set_busid,
 	.irq_handler		= shmob_drm_irq,
 	.get_vblank_counter	= drm_vblank_no_hw_counter,
 	.enable_vblank		= shmob_drm_enable_vblank,
 	.disable_vblank		= shmob_drm_disable_vblank,
-	.gem_free_object	= drm_gem_cma_free_object,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops		= &drm_gem_cma_vm_ops,
 	.prime_handle_to_fd	= drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle	= drm_gem_prime_fd_to_handle,
diff --git a/drivers/gpu/drm/sis/sis_mm.c b/drivers/gpu/drm/sis/sis_mm.c
index 93ad8a5704d1..03defda77766 100644
--- a/drivers/gpu/drm/sis/sis_mm.c
+++ b/drivers/gpu/drm/sis/sis_mm.c
@@ -316,7 +316,7 @@ void sis_reclaim_buffers_locked(struct drm_device *dev,
 	struct sis_file_private *file_priv = file->driver_priv;
 	struct sis_memblock *entry, *next;
 
-	if (!(file->minor->master && file->master->lock.hw_lock))
+	if (!(dev->master && file->master->lock.hw_lock))
 		return;
 
 	drm_legacy_idlelock_take(&file->master->lock);
diff --git a/drivers/gpu/drm/sti/Kconfig b/drivers/gpu/drm/sti/Kconfig
index 5ad43a1bb260..494ab257f77c 100644
--- a/drivers/gpu/drm/sti/Kconfig
+++ b/drivers/gpu/drm/sti/Kconfig
@@ -7,5 +7,6 @@ config DRM_STI
 	select DRM_KMS_CMA_HELPER
 	select DRM_PANEL
 	select FW_LOADER
+	select SND_SOC_HDMI_CODEC if SND_SOC
 	help
 	  Choose this option to enable DRM on STM stiH41x chipset
diff --git a/drivers/gpu/drm/sti/sti_awg_utils.c b/drivers/gpu/drm/sti/sti_awg_utils.c
index a516eb869f6f..2da7d6866d5d 100644
--- a/drivers/gpu/drm/sti/sti_awg_utils.c
+++ b/drivers/gpu/drm/sti/sti_awg_utils.c
@@ -6,6 +6,8 @@
 
 #include "sti_awg_utils.h"
 
+#define AWG_DELAY (-5)
+
 #define AWG_OPCODE_OFFSET 10
 #define AWG_MAX_ARG       0x3ff
 
@@ -125,7 +127,7 @@ static int awg_generate_line_signal(
 		val = timing->blanking_level;
 		ret |= awg_generate_instr(RPLSET, val, 0, 0, fwparams);
 
-		val = timing->trailing_pixels - 1;
+		val = timing->trailing_pixels - 1 + AWG_DELAY;
 		ret |= awg_generate_instr(SKIP, val, 0, 0, fwparams);
 	}
 
diff --git a/drivers/gpu/drm/sti/sti_compositor.c b/drivers/gpu/drm/sti/sti_compositor.c
index 3d2fa3ab33df..134201ecc6fd 100644
--- a/drivers/gpu/drm/sti/sti_compositor.c
+++ b/drivers/gpu/drm/sti/sti_compositor.c
@@ -55,6 +55,26 @@ struct sti_compositor_data stih416_compositor_data = {
 	},
 };
 
+int sti_compositor_debufs_init(struct sti_compositor *compo,
+			       struct drm_minor *minor)
+{
+	int ret = 0, i;
+
+	for (i = 0; compo->vid[i]; i++) {
+		ret = vid_debugfs_init(compo->vid[i], minor);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; compo->mixer[i]; i++) {
+		ret = sti_mixer_debugfs_init(compo->mixer[i], minor);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int sti_compositor_bind(struct device *dev,
 			       struct device *master,
 			       void *data)
@@ -234,12 +254,12 @@ static int sti_compositor_probe(struct platform_device *pdev)
 	}
 
 	/* Get reset resources */
-	compo->rst_main = devm_reset_control_get(dev, "compo-main");
+	compo->rst_main = devm_reset_control_get_shared(dev, "compo-main");
 	/* Take compo main out of reset */
 	if (!IS_ERR(compo->rst_main))
 		reset_control_deassert(compo->rst_main);
 
-	compo->rst_aux = devm_reset_control_get(dev, "compo-aux");
+	compo->rst_aux = devm_reset_control_get_shared(dev, "compo-aux");
 	/* Take compo aux out of reset */
 	if (!IS_ERR(compo->rst_aux))
 		reset_control_deassert(compo->rst_aux);
@@ -247,10 +267,12 @@ static int sti_compositor_probe(struct platform_device *pdev)
 	vtg_np = of_parse_phandle(pdev->dev.of_node, "st,vtg", 0);
 	if (vtg_np)
 		compo->vtg_main = of_vtg_find(vtg_np);
+	of_node_put(vtg_np);
 
 	vtg_np = of_parse_phandle(pdev->dev.of_node, "st,vtg", 1);
 	if (vtg_np)
 		compo->vtg_aux = of_vtg_find(vtg_np);
+	of_node_put(vtg_np);
 
 	platform_set_drvdata(pdev, compo);
 
diff --git a/drivers/gpu/drm/sti/sti_compositor.h b/drivers/gpu/drm/sti/sti_compositor.h
index 1a4a73dab11e..24444ef42a98 100644
--- a/drivers/gpu/drm/sti/sti_compositor.h
+++ b/drivers/gpu/drm/sti/sti_compositor.h
@@ -81,4 +81,7 @@ struct sti_compositor {
 	struct notifier_block vtg_vblank_nb;
 };
 
+int sti_compositor_debufs_init(struct sti_compositor *compo,
+			       struct drm_minor *minor);
+
 #endif
diff --git a/drivers/gpu/drm/sti/sti_crtc.c b/drivers/gpu/drm/sti/sti_crtc.c
index e04deedabd4a..c7d734dc3cf4 100644
--- a/drivers/gpu/drm/sti/sti_crtc.c
+++ b/drivers/gpu/drm/sti/sti_crtc.c
@@ -23,22 +23,11 @@
 static void sti_crtc_enable(struct drm_crtc *crtc)
 {
 	struct sti_mixer *mixer = to_sti_mixer(crtc);
-	struct device *dev = mixer->dev;
-	struct sti_compositor *compo = dev_get_drvdata(dev);
 
 	DRM_DEBUG_DRIVER("\n");
 
 	mixer->status = STI_MIXER_READY;
 
-	/* Prepare and enable the compo IP clock */
-	if (mixer->id == STI_MIXER_MAIN) {
-		if (clk_prepare_enable(compo->clk_compo_main))
-			DRM_INFO("Failed to prepare/enable compo_main clk\n");
-	} else {
-		if (clk_prepare_enable(compo->clk_compo_aux))
-			DRM_INFO("Failed to prepare/enable compo_aux clk\n");
-	}
-
 	drm_crtc_vblank_on(crtc);
 }
 
@@ -57,9 +46,8 @@ sti_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode)
 	struct sti_mixer *mixer = to_sti_mixer(crtc);
 	struct device *dev = mixer->dev;
 	struct sti_compositor *compo = dev_get_drvdata(dev);
-	struct clk *clk;
+	struct clk *compo_clk, *pix_clk;
 	int rate = mode->clock * 1000;
-	int res;
 
 	DRM_DEBUG_KMS("CRTC:%d (%s) mode:%d (%s)\n",
 		      crtc->base.id, sti_mixer_to_str(mixer),
@@ -74,32 +62,46 @@ sti_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode)
 		      mode->vsync_start, mode->vsync_end,
 		      mode->vtotal, mode->type, mode->flags);
 
-	/* Set rate and prepare/enable pixel clock */
-	if (mixer->id == STI_MIXER_MAIN)
-		clk = compo->clk_pix_main;
-	else
-		clk = compo->clk_pix_aux;
+	if (mixer->id == STI_MIXER_MAIN) {
+		compo_clk = compo->clk_compo_main;
+		pix_clk = compo->clk_pix_main;
+	} else {
+		compo_clk = compo->clk_compo_aux;
+		pix_clk = compo->clk_pix_aux;
+	}
+
+	/* Prepare and enable the compo IP clock */
+	if (clk_prepare_enable(compo_clk)) {
+		DRM_INFO("Failed to prepare/enable compositor clk\n");
+		goto compo_error;
+	}
 
-	res = clk_set_rate(clk, rate);
-	if (res < 0) {
+	/* Set rate and prepare/enable pixel clock */
+	if (clk_set_rate(pix_clk, rate) < 0) {
 		DRM_ERROR("Cannot set rate (%dHz) for pix clk\n", rate);
-		return -EINVAL;
+		goto pix_error;
 	}
-	if (clk_prepare_enable(clk)) {
+	if (clk_prepare_enable(pix_clk)) {
 		DRM_ERROR("Failed to prepare/enable pix clk\n");
-		return -EINVAL;
+		goto pix_error;
 	}
 
 	sti_vtg_set_config(mixer->id == STI_MIXER_MAIN ?
 			compo->vtg_main : compo->vtg_aux, &crtc->mode);
 
-	res = sti_mixer_active_video_area(mixer, &crtc->mode);
-	if (res) {
+	if (sti_mixer_active_video_area(mixer, &crtc->mode)) {
 		DRM_ERROR("Can't set active video area\n");
-		return -EINVAL;
+		goto mixer_error;
 	}
 
-	return res;
+	return 0;
+
+mixer_error:
+	clk_disable_unprepare(pix_clk);
+pix_error:
+	clk_disable_unprepare(compo_clk);
+compo_error:
+	return -EINVAL;
 }
 
 static void sti_crtc_disable(struct drm_crtc *crtc)
@@ -130,7 +132,6 @@ static void sti_crtc_disable(struct drm_crtc *crtc)
 static void
 sti_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
-	sti_crtc_enable(crtc);
 	sti_crtc_mode_set(crtc, &crtc->state->adjusted_mode);
 }
 
@@ -221,9 +222,7 @@ static void sti_crtc_atomic_flush(struct drm_crtc *crtc,
 static const struct drm_crtc_helper_funcs sti_crtc_helper_funcs = {
 	.enable = sti_crtc_enable,
 	.disable = sti_crtc_disabling,
-	.mode_set = drm_helper_crtc_mode_set,
 	.mode_set_nofb = sti_crtc_mode_set_nofb,
-	.mode_set_base = drm_helper_crtc_mode_set_base,
 	.atomic_begin = sti_crtc_atomic_begin,
 	.atomic_flush = sti_crtc_atomic_flush,
 };
@@ -331,6 +330,17 @@ void sti_crtc_disable_vblank(struct drm_device *drm_dev, unsigned int pipe)
 	}
 }
 
+static int sti_crtc_late_register(struct drm_crtc *crtc)
+{
+	struct sti_mixer *mixer = to_sti_mixer(crtc);
+	struct sti_compositor *compo = dev_get_drvdata(mixer->dev);
+
+	if (drm_crtc_index(crtc) == 0)
+		return sti_compositor_debufs_init(compo, crtc->dev->primary);
+
+	return 0;
+}
+
 static const struct drm_crtc_funcs sti_crtc_funcs = {
 	.set_config = drm_atomic_helper_set_config,
 	.page_flip = drm_atomic_helper_page_flip,
@@ -339,6 +349,7 @@ static const struct drm_crtc_funcs sti_crtc_funcs = {
 	.reset = drm_atomic_helper_crtc_reset,
 	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
+	.late_register = sti_crtc_late_register,
 };
 
 bool sti_crtc_is_main(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c
index 4e990299735c..a263bbba4119 100644
--- a/drivers/gpu/drm/sti/sti_cursor.c
+++ b/drivers/gpu/drm/sti/sti_cursor.c
@@ -105,12 +105,6 @@ static int cursor_dbg_show(struct seq_file *s, void *data)
 {
 	struct drm_info_node *node = s->private;
 	struct sti_cursor *cursor = (struct sti_cursor *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(s, "%s: (vaddr = 0x%p)",
 		   sti_plane_to_str(&cursor->plane), cursor->regs);
@@ -129,7 +123,6 @@ static int cursor_dbg_show(struct seq_file *s, void *data)
 	DBGFS_DUMP(CUR_AWE);
 	seq_puts(s, "\n");
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -336,6 +329,33 @@ static const struct drm_plane_helper_funcs sti_cursor_helpers_funcs = {
 	.atomic_disable = sti_cursor_atomic_disable,
 };
 
+static void sti_cursor_destroy(struct drm_plane *drm_plane)
+{
+	DRM_DEBUG_DRIVER("\n");
+
+	drm_plane_helper_disable(drm_plane);
+	drm_plane_cleanup(drm_plane);
+}
+
+static int sti_cursor_late_register(struct drm_plane *drm_plane)
+{
+	struct sti_plane *plane = to_sti_plane(drm_plane);
+	struct sti_cursor *cursor = to_sti_cursor(plane);
+
+	return cursor_debugfs_init(cursor, drm_plane->dev->primary);
+}
+
+struct drm_plane_funcs sti_cursor_plane_helpers_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = sti_cursor_destroy,
+	.set_property = sti_plane_set_property,
+	.reset = drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+	.late_register = sti_cursor_late_register,
+};
+
 struct drm_plane *sti_cursor_create(struct drm_device *drm_dev,
 				    struct device *dev, int desc,
 				    void __iomem *baseaddr,
@@ -370,7 +390,7 @@ struct drm_plane *sti_cursor_create(struct drm_device *drm_dev,
 
 	res = drm_universal_plane_init(drm_dev, &cursor->plane.drm_plane,
 				       possible_crtcs,
-				       &sti_plane_helpers_funcs,
+				       &sti_cursor_plane_helpers_funcs,
 				       cursor_supported_formats,
 				       ARRAY_SIZE(cursor_supported_formats),
 				       DRM_PLANE_TYPE_CURSOR, NULL);
@@ -384,9 +404,6 @@ struct drm_plane *sti_cursor_create(struct drm_device *drm_dev,
 
 	sti_plane_init_property(&cursor->plane, DRM_PLANE_TYPE_CURSOR);
 
-	if (cursor_debugfs_init(cursor, drm_dev->primary))
-		DRM_ERROR("CURSOR debugfs setup failed\n");
-
 	return &cursor->plane.drm_plane;
 
 err_plane:
diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c
index 872495e72294..96bd3d08b2d4 100644
--- a/drivers/gpu/drm/sti/sti_drv.c
+++ b/drivers/gpu/drm/sti/sti_drv.c
@@ -72,11 +72,6 @@ static int sti_drm_fps_dbg_show(struct seq_file *s, void *data)
 	struct drm_info_node *node = s->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_plane *p;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	list_for_each_entry(p, &dev->mode_config.plane_list, head) {
 		struct sti_plane *plane = to_sti_plane(p);
@@ -86,7 +81,6 @@ static int sti_drm_fps_dbg_show(struct seq_file *s, void *data)
 			   plane->fps_info.fips_str);
 	}
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -221,7 +215,7 @@ static int sti_atomic_commit(struct drm_device *drm,
 	 * the software side now.
 	 */
 
-	drm_atomic_helper_swap_state(drm, state);
+	drm_atomic_helper_swap_state(state, true);
 
 	if (nonblock)
 		sti_atomic_schedule(private, state);
@@ -232,8 +226,28 @@ static int sti_atomic_commit(struct drm_device *drm,
 	return 0;
 }
 
+static void sti_output_poll_changed(struct drm_device *ddev)
+{
+	struct sti_private *private = ddev->dev_private;
+
+	if (!ddev->mode_config.num_connector)
+		return;
+
+	if (private->fbdev) {
+		drm_fbdev_cma_hotplug_event(private->fbdev);
+		return;
+	}
+
+	private->fbdev = drm_fbdev_cma_init(ddev, 32,
+					    ddev->mode_config.num_crtc,
+					    ddev->mode_config.num_connector);
+	if (IS_ERR(private->fbdev))
+		private->fbdev = NULL;
+}
+
 static const struct drm_mode_config_funcs sti_mode_config_funcs = {
 	.fb_create = drm_fb_cma_create,
+	.output_poll_changed = sti_output_poll_changed,
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = sti_atomic_commit,
 };
@@ -254,45 +268,6 @@ static void sti_mode_config_init(struct drm_device *dev)
 	dev->mode_config.funcs = &sti_mode_config_funcs;
 }
 
-static int sti_load(struct drm_device *dev, unsigned long flags)
-{
-	struct sti_private *private;
-	int ret;
-
-	private = kzalloc(sizeof(*private), GFP_KERNEL);
-	if (!private) {
-		DRM_ERROR("Failed to allocate private\n");
-		return -ENOMEM;
-	}
-	dev->dev_private = (void *)private;
-	private->drm_dev = dev;
-
-	mutex_init(&private->commit.lock);
-	INIT_WORK(&private->commit.work, sti_atomic_work);
-
-	drm_mode_config_init(dev);
-	drm_kms_helper_poll_init(dev);
-
-	sti_mode_config_init(dev);
-
-	ret = component_bind_all(dev->dev, dev);
-	if (ret) {
-		drm_kms_helper_poll_fini(dev);
-		drm_mode_config_cleanup(dev);
-		kfree(private);
-		return ret;
-	}
-
-	drm_mode_config_reset(dev);
-
-	drm_helper_disable_unused_functions(dev);
-	drm_fbdev_cma_init(dev, 32,
-			   dev->mode_config.num_crtc,
-			   dev->mode_config.num_connector);
-
-	return 0;
-}
-
 static const struct file_operations sti_driver_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
@@ -309,8 +284,7 @@ static const struct file_operations sti_driver_fops = {
 static struct drm_driver sti_driver = {
 	.driver_features = DRIVER_HAVE_IRQ | DRIVER_MODESET |
 	    DRIVER_GEM | DRIVER_PRIME | DRIVER_ATOMIC,
-	.load = sti_load,
-	.gem_free_object = drm_gem_cma_free_object,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops = &drm_gem_cma_vm_ops,
 	.dumb_create = drm_gem_cma_dumb_create,
 	.dumb_map_offset = drm_gem_cma_dumb_map_offset,
@@ -346,14 +320,88 @@ static int compare_of(struct device *dev, void *data)
 	return dev->of_node == data;
 }
 
+static int sti_init(struct drm_device *ddev)
+{
+	struct sti_private *private;
+
+	private = kzalloc(sizeof(*private), GFP_KERNEL);
+	if (!private)
+		return -ENOMEM;
+
+	ddev->dev_private = (void *)private;
+	dev_set_drvdata(ddev->dev, ddev);
+	private->drm_dev = ddev;
+
+	mutex_init(&private->commit.lock);
+	INIT_WORK(&private->commit.work, sti_atomic_work);
+
+	drm_mode_config_init(ddev);
+
+	sti_mode_config_init(ddev);
+
+	drm_kms_helper_poll_init(ddev);
+
+	return 0;
+}
+
+static void sti_cleanup(struct drm_device *ddev)
+{
+	struct sti_private *private = ddev->dev_private;
+
+	if (private->fbdev) {
+		drm_fbdev_cma_fini(private->fbdev);
+		private->fbdev = NULL;
+	}
+
+	drm_kms_helper_poll_fini(ddev);
+	drm_vblank_cleanup(ddev);
+	kfree(private);
+	ddev->dev_private = NULL;
+}
+
 static int sti_bind(struct device *dev)
 {
-	return drm_platform_init(&sti_driver, to_platform_device(dev));
+	struct drm_device *ddev;
+	int ret;
+
+	ddev = drm_dev_alloc(&sti_driver, dev);
+	if (!ddev)
+		return -ENOMEM;
+
+	ddev->platformdev = to_platform_device(dev);
+
+	ret = sti_init(ddev);
+	if (ret)
+		goto err_drm_dev_unref;
+
+	ret = component_bind_all(ddev->dev, ddev);
+	if (ret)
+		goto err_cleanup;
+
+	ret = drm_dev_register(ddev, 0);
+	if (ret)
+		goto err_register;
+
+	drm_mode_config_reset(ddev);
+
+	return 0;
+
+err_register:
+	drm_mode_config_cleanup(ddev);
+err_cleanup:
+	sti_cleanup(ddev);
+err_drm_dev_unref:
+	drm_dev_unref(ddev);
+	return ret;
 }
 
 static void sti_unbind(struct device *dev)
 {
-	drm_put_dev(dev_get_drvdata(dev));
+	struct drm_device *ddev = dev_get_drvdata(dev);
+
+	drm_dev_unregister(ddev);
+	sti_cleanup(ddev);
+	drm_dev_unref(ddev);
 }
 
 static const struct component_master_ops sti_ops = {
diff --git a/drivers/gpu/drm/sti/sti_drv.h b/drivers/gpu/drm/sti/sti_drv.h
index 30ddc20841c3..78ebe5e30f53 100644
--- a/drivers/gpu/drm/sti/sti_drv.h
+++ b/drivers/gpu/drm/sti/sti_drv.h
@@ -24,6 +24,7 @@ struct sti_private {
 	struct sti_compositor *compo;
 	struct drm_property *plane_zorder_property;
 	struct drm_device *drm_dev;
+	struct drm_fbdev_cma *fbdev;
 
 	struct {
 		struct drm_atomic_state *state;
diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c
index 25f76632002c..00881eb4536e 100644
--- a/drivers/gpu/drm/sti/sti_dvo.c
+++ b/drivers/gpu/drm/sti/sti_dvo.c
@@ -177,12 +177,6 @@ static int dvo_dbg_show(struct seq_file *s, void *data)
 {
 	struct drm_info_node *node = s->private;
 	struct sti_dvo *dvo = (struct sti_dvo *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(s, "DVO: (vaddr = 0x%p)", dvo->regs);
 	DBGFS_DUMP(DVO_AWG_DIGSYNC_CTRL);
@@ -193,7 +187,6 @@ static int dvo_dbg_show(struct seq_file *s, void *data)
 	dvo_dbg_awg_microcode(s, dvo->regs + DVO_DIGSYNC_INSTR_I);
 	seq_puts(s, "\n");
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -384,20 +377,10 @@ static int sti_dvo_connector_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-struct drm_encoder *sti_dvo_best_encoder(struct drm_connector *connector)
-{
-	struct sti_dvo_connector *dvo_connector
-		= to_sti_dvo_connector(connector);
-
-	/* Best encoder is the one associated during connector creation */
-	return dvo_connector->encoder;
-}
-
 static const
 struct drm_connector_helper_funcs sti_dvo_connector_helper_funcs = {
 	.get_modes = sti_dvo_connector_get_modes,
 	.mode_valid = sti_dvo_connector_mode_valid,
-	.best_encoder = sti_dvo_best_encoder,
 };
 
 static enum drm_connector_status
@@ -421,24 +404,29 @@ sti_dvo_connector_detect(struct drm_connector *connector, bool force)
 	return connector_status_disconnected;
 }
 
-static void sti_dvo_connector_destroy(struct drm_connector *connector)
+static int sti_dvo_late_register(struct drm_connector *connector)
 {
 	struct sti_dvo_connector *dvo_connector
 		= to_sti_dvo_connector(connector);
+	struct sti_dvo *dvo = dvo_connector->dvo;
 
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-	kfree(dvo_connector);
+	if (dvo_debugfs_init(dvo, dvo->drm_dev->primary)) {
+		DRM_ERROR("DVO debugfs setup failed\n");
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 static const struct drm_connector_funcs sti_dvo_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.detect = sti_dvo_connector_detect,
-	.destroy = sti_dvo_connector_destroy,
+	.destroy = drm_connector_cleanup,
 	.reset = drm_atomic_helper_connector_reset,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.late_register = sti_dvo_late_register,
 };
 
 static struct drm_encoder *sti_dvo_find_encoder(struct drm_device *dev)
@@ -509,26 +497,16 @@ static int sti_dvo_bind(struct device *dev, struct device *master, void *data)
 	drm_connector_helper_add(drm_connector,
 				 &sti_dvo_connector_helper_funcs);
 
-	err = drm_connector_register(drm_connector);
-	if (err)
-		goto err_connector;
-
 	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
 		goto err_sysfs;
 	}
 
-	if (dvo_debugfs_init(dvo, drm_dev->primary))
-		DRM_ERROR("DVO debugfs setup failed\n");
-
 	return 0;
 
 err_sysfs:
-	drm_connector_unregister(drm_connector);
-err_connector:
 	drm_bridge_remove(bridge);
-	drm_connector_cleanup(drm_connector);
 	return -EINVAL;
 }
 
@@ -602,6 +580,7 @@ static int sti_dvo_probe(struct platform_device *pdev)
 	dvo->panel_node = of_parse_phandle(np, "sti,panel", 0);
 	if (!dvo->panel_node)
 		DRM_ERROR("No panel associated to the dvo output\n");
+	of_node_put(dvo->panel_node);
 
 	platform_set_drvdata(pdev, dvo);
 
diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c
index ff33c38da197..bf63086a3dc8 100644
--- a/drivers/gpu/drm/sti/sti_gdp.c
+++ b/drivers/gpu/drm/sti/sti_gdp.c
@@ -208,14 +208,8 @@ static int gdp_dbg_show(struct seq_file *s, void *data)
 {
 	struct drm_info_node *node = s->private;
 	struct sti_gdp *gdp = (struct sti_gdp *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
 	struct drm_plane *drm_plane = &gdp->plane.drm_plane;
 	struct drm_crtc *crtc = drm_plane->crtc;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(s, "%s: (vaddr = 0x%p)",
 		   sti_plane_to_str(&gdp->plane), gdp->regs);
@@ -248,7 +242,6 @@ static int gdp_dbg_show(struct seq_file *s, void *data)
 		seq_printf(s, "  Connected to DRM CRTC #%d (%s)\n",
 			   crtc->base.id, sti_mixer_to_str(to_sti_mixer(crtc)));
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -279,13 +272,7 @@ static int gdp_node_dbg_show(struct seq_file *s, void *arg)
 {
 	struct drm_info_node *node = s->private;
 	struct sti_gdp *gdp = (struct sti_gdp *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
 	unsigned int b;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	for (b = 0; b < GDP_NODE_NB_BANK; b++) {
 		seq_printf(s, "\n%s[%d].top", sti_plane_to_str(&gdp->plane), b);
@@ -294,7 +281,6 @@ static int gdp_node_dbg_show(struct seq_file *s, void *arg)
 		gdp_node_dump_node(s, gdp->node_list[b].btm_field);
 	}
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -880,6 +866,33 @@ static const struct drm_plane_helper_funcs sti_gdp_helpers_funcs = {
 	.atomic_disable = sti_gdp_atomic_disable,
 };
 
+static void sti_gdp_destroy(struct drm_plane *drm_plane)
+{
+	DRM_DEBUG_DRIVER("\n");
+
+	drm_plane_helper_disable(drm_plane);
+	drm_plane_cleanup(drm_plane);
+}
+
+static int sti_gdp_late_register(struct drm_plane *drm_plane)
+{
+	struct sti_plane *plane = to_sti_plane(drm_plane);
+	struct sti_gdp *gdp = to_sti_gdp(plane);
+
+	return gdp_debugfs_init(gdp, drm_plane->dev->primary);
+}
+
+struct drm_plane_funcs sti_gdp_plane_helpers_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = sti_gdp_destroy,
+	.set_property = sti_plane_set_property,
+	.reset = drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+	.late_register = sti_gdp_late_register,
+};
+
 struct drm_plane *sti_gdp_create(struct drm_device *drm_dev,
 				 struct device *dev, int desc,
 				 void __iomem *baseaddr,
@@ -906,7 +919,7 @@ struct drm_plane *sti_gdp_create(struct drm_device *drm_dev,
 
 	res = drm_universal_plane_init(drm_dev, &gdp->plane.drm_plane,
 				       possible_crtcs,
-				       &sti_plane_helpers_funcs,
+				       &sti_gdp_plane_helpers_funcs,
 				       gdp_supported_formats,
 				       ARRAY_SIZE(gdp_supported_formats),
 				       type, NULL);
@@ -919,9 +932,6 @@ struct drm_plane *sti_gdp_create(struct drm_device *drm_dev,
 
 	sti_plane_init_property(&gdp->plane, type);
 
-	if (gdp_debugfs_init(gdp, drm_dev->primary))
-		DRM_ERROR("GDP debugfs setup failed\n");
-
 	return &gdp->plane.drm_plane;
 
 err:
diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c
index f7d3464cdf09..8505569f75de 100644
--- a/drivers/gpu/drm/sti/sti_hda.c
+++ b/drivers/gpu/drm/sti/sti_hda.c
@@ -376,12 +376,6 @@ static int hda_dbg_show(struct seq_file *s, void *data)
 {
 	struct drm_info_node *node = s->private;
 	struct sti_hda *hda = (struct sti_hda *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(s, "HD Analog: (vaddr = 0x%p)", hda->regs);
 	DBGFS_DUMP(HDA_ANA_CFG);
@@ -397,7 +391,6 @@ static int hda_dbg_show(struct seq_file *s, void *data)
 		hda_dbg_video_dacs_ctrl(s, hda->video_dacs_ctrl);
 	seq_puts(s, "\n");
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -676,20 +669,10 @@ static int sti_hda_connector_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-struct drm_encoder *sti_hda_best_encoder(struct drm_connector *connector)
-{
-	struct sti_hda_connector *hda_connector
-		= to_sti_hda_connector(connector);
-
-	/* Best encoder is the one associated during connector creation */
-	return hda_connector->encoder;
-}
-
 static const
 struct drm_connector_helper_funcs sti_hda_connector_helper_funcs = {
 	.get_modes = sti_hda_connector_get_modes,
 	.mode_valid = sti_hda_connector_mode_valid,
-	.best_encoder = sti_hda_best_encoder,
 };
 
 static enum drm_connector_status
@@ -698,24 +681,29 @@ sti_hda_connector_detect(struct drm_connector *connector, bool force)
 	return connector_status_connected;
 }
 
-static void sti_hda_connector_destroy(struct drm_connector *connector)
+static int sti_hda_late_register(struct drm_connector *connector)
 {
 	struct sti_hda_connector *hda_connector
 		= to_sti_hda_connector(connector);
+	struct sti_hda *hda = hda_connector->hda;
+
+	if (hda_debugfs_init(hda, hda->drm_dev->primary)) {
+		DRM_ERROR("HDA debugfs setup failed\n");
+		return -EINVAL;
+	}
 
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-	kfree(hda_connector);
+	return 0;
 }
 
 static const struct drm_connector_funcs sti_hda_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.detect = sti_hda_connector_detect,
-	.destroy = sti_hda_connector_destroy,
+	.destroy = drm_connector_cleanup,
 	.reset = drm_atomic_helper_connector_reset,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.late_register = sti_hda_late_register,
 };
 
 static struct drm_encoder *sti_hda_find_encoder(struct drm_device *dev)
@@ -773,10 +761,6 @@ static int sti_hda_bind(struct device *dev, struct device *master, void *data)
 	drm_connector_helper_add(drm_connector,
 			&sti_hda_connector_helper_funcs);
 
-	err = drm_connector_register(drm_connector);
-	if (err)
-		goto err_connector;
-
 	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
@@ -786,15 +770,10 @@ static int sti_hda_bind(struct device *dev, struct device *master, void *data)
 	/* force to disable hd dacs at startup */
 	hda_enable_hd_dacs(hda, false);
 
-	if (hda_debugfs_init(hda, drm_dev->primary))
-		DRM_ERROR("HDA debugfs setup failed\n");
-
 	return 0;
 
 err_sysfs:
-	drm_connector_unregister(drm_connector);
-err_connector:
-	drm_connector_cleanup(drm_connector);
+	drm_bridge_remove(bridge);
 	return -EINVAL;
 }
 
diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c
index 6ef0715bd5b9..fedc17f98d9b 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.c
+++ b/drivers/gpu/drm/sti/sti_hdmi.c
@@ -18,6 +18,8 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_edid.h>
 
+#include <sound/hdmi-codec.h>
+
 #include "sti_hdmi.h"
 #include "sti_hdmi_tx3g4c28phy.h"
 #include "sti_hdmi_tx3g0c55phy.h"
@@ -35,6 +37,8 @@
 #define HDMI_DFLT_CHL0_DAT              0x0110
 #define HDMI_DFLT_CHL1_DAT              0x0114
 #define HDMI_DFLT_CHL2_DAT              0x0118
+#define HDMI_AUDIO_CFG                  0x0200
+#define HDMI_SPDIF_FIFO_STATUS          0x0204
 #define HDMI_SW_DI_1_HEAD_WORD          0x0210
 #define HDMI_SW_DI_1_PKT_WORD0          0x0214
 #define HDMI_SW_DI_1_PKT_WORD1          0x0218
@@ -44,6 +48,9 @@
 #define HDMI_SW_DI_1_PKT_WORD5          0x0228
 #define HDMI_SW_DI_1_PKT_WORD6          0x022C
 #define HDMI_SW_DI_CFG                  0x0230
+#define HDMI_SAMPLE_FLAT_MASK           0x0244
+#define HDMI_AUDN                       0x0400
+#define HDMI_AUD_CTS                    0x0404
 #define HDMI_SW_DI_2_HEAD_WORD          0x0600
 #define HDMI_SW_DI_2_PKT_WORD0          0x0604
 #define HDMI_SW_DI_2_PKT_WORD1          0x0608
@@ -103,6 +110,7 @@
 #define HDMI_INT_DLL_LCK                BIT(5)
 #define HDMI_INT_NEW_FRAME              BIT(6)
 #define HDMI_INT_GENCTRL_PKT            BIT(7)
+#define HDMI_INT_AUDIO_FIFO_XRUN        BIT(8)
 #define HDMI_INT_SINK_TERM_PRESENT      BIT(11)
 
 #define HDMI_DEFAULT_INT (HDMI_INT_SINK_TERM_PRESENT \
@@ -111,6 +119,7 @@
 			| HDMI_INT_GLOBAL)
 
 #define HDMI_WORKING_INT (HDMI_INT_SINK_TERM_PRESENT \
+			| HDMI_INT_AUDIO_FIFO_XRUN \
 			| HDMI_INT_GENCTRL_PKT \
 			| HDMI_INT_NEW_FRAME \
 			| HDMI_INT_DLL_LCK \
@@ -121,6 +130,27 @@
 
 #define HDMI_STA_SW_RST                 BIT(1)
 
+#define HDMI_AUD_CFG_8CH		BIT(0)
+#define HDMI_AUD_CFG_SPDIF_DIV_2	BIT(1)
+#define HDMI_AUD_CFG_SPDIF_DIV_3	BIT(2)
+#define HDMI_AUD_CFG_SPDIF_CLK_DIV_4	(BIT(1) | BIT(2))
+#define HDMI_AUD_CFG_CTS_CLK_256FS	BIT(12)
+#define HDMI_AUD_CFG_DTS_INVALID	BIT(16)
+#define HDMI_AUD_CFG_ONE_BIT_INVALID	(BIT(18) | BIT(19) | BIT(20) |  BIT(21))
+#define HDMI_AUD_CFG_CH12_VALID	BIT(28)
+#define HDMI_AUD_CFG_CH34_VALID	BIT(29)
+#define HDMI_AUD_CFG_CH56_VALID	BIT(30)
+#define HDMI_AUD_CFG_CH78_VALID	BIT(31)
+
+/* sample flat mask */
+#define HDMI_SAMPLE_FLAT_NO	 0
+#define HDMI_SAMPLE_FLAT_SP0 BIT(0)
+#define HDMI_SAMPLE_FLAT_SP1 BIT(1)
+#define HDMI_SAMPLE_FLAT_SP2 BIT(2)
+#define HDMI_SAMPLE_FLAT_SP3 BIT(3)
+#define HDMI_SAMPLE_FLAT_ALL (HDMI_SAMPLE_FLAT_SP0 | HDMI_SAMPLE_FLAT_SP1 |\
+			      HDMI_SAMPLE_FLAT_SP2 | HDMI_SAMPLE_FLAT_SP3)
+
 #define HDMI_INFOFRAME_HEADER_TYPE(x)    (((x) & 0xff) <<  0)
 #define HDMI_INFOFRAME_HEADER_VERSION(x) (((x) & 0xff) <<  8)
 #define HDMI_INFOFRAME_HEADER_LEN(x)     (((x) & 0x0f) << 16)
@@ -171,6 +201,10 @@ static irqreturn_t hdmi_irq_thread(int irq, void *arg)
 		wake_up_interruptible(&hdmi->wait_event);
 	}
 
+	/* Audio FIFO underrun IRQ */
+	if (hdmi->irq_status & HDMI_INT_AUDIO_FIFO_XRUN)
+		DRM_INFO("Warning: audio FIFO underrun occurs!");
+
 	return IRQ_HANDLED;
 }
 
@@ -441,26 +475,29 @@ static int hdmi_avi_infoframe_config(struct sti_hdmi *hdmi)
  */
 static int hdmi_audio_infoframe_config(struct sti_hdmi *hdmi)
 {
-	struct hdmi_audio_infoframe infofame;
+	struct hdmi_audio_params *audio = &hdmi->audio;
 	u8 buffer[HDMI_INFOFRAME_SIZE(AUDIO)];
-	int ret;
-
-	ret = hdmi_audio_infoframe_init(&infofame);
-	if (ret < 0) {
-		DRM_ERROR("failed to setup audio infoframe: %d\n", ret);
-		return ret;
-	}
-
-	infofame.channels = 2;
-
-	ret = hdmi_audio_infoframe_pack(&infofame, buffer, sizeof(buffer));
-	if (ret < 0) {
-		DRM_ERROR("failed to pack audio infoframe: %d\n", ret);
-		return ret;
+	int ret, val;
+
+	DRM_DEBUG_DRIVER("enter %s, AIF %s\n", __func__,
+			 audio->enabled ? "enable" : "disable");
+	if (audio->enabled) {
+		/* set audio parameters stored*/
+		ret = hdmi_audio_infoframe_pack(&audio->cea, buffer,
+						sizeof(buffer));
+		if (ret < 0) {
+			DRM_ERROR("failed to pack audio infoframe: %d\n", ret);
+			return ret;
+		}
+		hdmi_infoframe_write_infopack(hdmi, buffer, ret);
+	} else {
+		/*disable audio info frame transmission */
+		val = hdmi_read(hdmi, HDMI_SW_DI_CFG);
+		val &= ~HDMI_IFRAME_CFG_DI_N(HDMI_IFRAME_MASK,
+					     HDMI_IFRAME_SLOT_AUDIO);
+		hdmi_write(hdmi, val, HDMI_SW_DI_CFG);
 	}
 
-	hdmi_infoframe_write_infopack(hdmi, buffer, ret);
-
 	return 0;
 }
 
@@ -628,12 +665,6 @@ static int hdmi_dbg_show(struct seq_file *s, void *data)
 {
 	struct drm_info_node *node = s->private;
 	struct sti_hdmi *hdmi = (struct sti_hdmi *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(s, "HDMI: (vaddr = 0x%p)", hdmi->regs);
 	DBGFS_DUMP("\n", HDMI_CFG);
@@ -656,6 +687,10 @@ static int hdmi_dbg_show(struct seq_file *s, void *data)
 	DBGFS_DUMP("", HDMI_SW_DI_CFG);
 	hdmi_dbg_sw_di_cfg(s, hdmi_read(hdmi, HDMI_SW_DI_CFG));
 
+	DBGFS_DUMP("\n", HDMI_AUDIO_CFG);
+	DBGFS_DUMP("\n", HDMI_SPDIF_FIFO_STATUS);
+	DBGFS_DUMP("\n", HDMI_AUDN);
+
 	seq_printf(s, "\n AVI Infoframe (Data Island slot N=%d):",
 		   HDMI_IFRAME_SLOT_AVI);
 	DBGFS_DUMP_DI(HDMI_SW_DI_N_HEAD_WORD, HDMI_IFRAME_SLOT_AVI);
@@ -690,7 +725,6 @@ static int hdmi_dbg_show(struct seq_file *s, void *data)
 	DBGFS_DUMP_DI(HDMI_SW_DI_N_PKT_WORD6, HDMI_IFRAME_SLOT_VENDOR);
 	seq_puts(s, "\n");
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -861,6 +895,7 @@ static int sti_hdmi_connector_get_modes(struct drm_connector *connector)
 
 	count = drm_add_edid_modes(connector, edid);
 	drm_mode_connector_update_edid_property(connector, edid);
+	drm_edid_to_eld(connector, edid);
 
 	kfree(edid);
 	return count;
@@ -897,20 +932,10 @@ static int sti_hdmi_connector_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-struct drm_encoder *sti_hdmi_best_encoder(struct drm_connector *connector)
-{
-	struct sti_hdmi_connector *hdmi_connector
-		= to_sti_hdmi_connector(connector);
-
-	/* Best encoder is the one associated during connector creation */
-	return hdmi_connector->encoder;
-}
-
 static const
 struct drm_connector_helper_funcs sti_hdmi_connector_helper_funcs = {
 	.get_modes = sti_hdmi_connector_get_modes,
 	.mode_valid = sti_hdmi_connector_mode_valid,
-	.best_encoder = sti_hdmi_best_encoder,
 };
 
 /* get detection status of display device */
@@ -932,16 +957,6 @@ sti_hdmi_connector_detect(struct drm_connector *connector, bool force)
 	return connector_status_disconnected;
 }
 
-static void sti_hdmi_connector_destroy(struct drm_connector *connector)
-{
-	struct sti_hdmi_connector *hdmi_connector
-		= to_sti_hdmi_connector(connector);
-
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-	kfree(hdmi_connector);
-}
-
 static void sti_hdmi_connector_init_property(struct drm_device *drm_dev,
 					     struct drm_connector *connector)
 {
@@ -1024,17 +1039,31 @@ sti_hdmi_connector_get_property(struct drm_connector *connector,
 	return -EINVAL;
 }
 
+static int sti_hdmi_late_register(struct drm_connector *connector)
+{
+	struct sti_hdmi_connector *hdmi_connector
+		= to_sti_hdmi_connector(connector);
+	struct sti_hdmi *hdmi = hdmi_connector->hdmi;
+
+	if (hdmi_debugfs_init(hdmi, hdmi->drm_dev->primary)) {
+		DRM_ERROR("HDMI debugfs setup failed\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct drm_connector_funcs sti_hdmi_connector_funcs = {
-	.dpms = drm_atomic_helper_connector_dpms,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.detect = sti_hdmi_connector_detect,
-	.destroy = sti_hdmi_connector_destroy,
+	.destroy = drm_connector_cleanup,
 	.reset = drm_atomic_helper_connector_reset,
 	.set_property = drm_atomic_helper_connector_set_property,
 	.atomic_set_property = sti_hdmi_connector_set_property,
 	.atomic_get_property = sti_hdmi_connector_get_property,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.late_register = sti_hdmi_late_register,
 };
 
 static struct drm_encoder *sti_hdmi_find_encoder(struct drm_device *dev)
@@ -1049,6 +1078,207 @@ static struct drm_encoder *sti_hdmi_find_encoder(struct drm_device *dev)
 	return NULL;
 }
 
+/**
+ * sti_hdmi_audio_get_non_coherent_n() - get N parameter for non-coherent
+ * clocks. None-coherent clocks means that audio and TMDS clocks have not the
+ * same source (drifts between clocks). In this case assumption is that CTS is
+ * automatically calculated by hardware.
+ *
+ * @audio_fs: audio frame clock frequency in Hz
+ *
+ * Values computed are based on table described in HDMI specification 1.4b
+ *
+ * Returns n value.
+ */
+static int sti_hdmi_audio_get_non_coherent_n(unsigned int audio_fs)
+{
+	unsigned int n;
+
+	switch (audio_fs) {
+	case 32000:
+		n = 4096;
+		break;
+	case 44100:
+		n = 6272;
+		break;
+	case 48000:
+		n = 6144;
+		break;
+	case 88200:
+		n = 6272 * 2;
+		break;
+	case 96000:
+		n = 6144 * 2;
+		break;
+	case 176400:
+		n = 6272 * 4;
+		break;
+	case 192000:
+		n = 6144 * 4;
+		break;
+	default:
+		/* Not pre-defined, recommended value: 128 * fs / 1000 */
+		n = (audio_fs * 128) / 1000;
+	}
+
+	return n;
+}
+
+static int hdmi_audio_configure(struct sti_hdmi *hdmi,
+				struct hdmi_audio_params *params)
+{
+	int audio_cfg, n;
+	struct hdmi_audio_infoframe *info = &params->cea;
+
+	DRM_DEBUG_DRIVER("\n");
+
+	if (!hdmi->enabled)
+		return 0;
+
+	/* update N parameter */
+	n = sti_hdmi_audio_get_non_coherent_n(params->sample_rate);
+
+	DRM_DEBUG_DRIVER("Audio rate = %d Hz, TMDS clock = %d Hz, n = %d\n",
+			 params->sample_rate, hdmi->mode.clock * 1000, n);
+	hdmi_write(hdmi, n, HDMI_AUDN);
+
+	/* update HDMI registers according to configuration */
+	audio_cfg = HDMI_AUD_CFG_SPDIF_DIV_2 | HDMI_AUD_CFG_DTS_INVALID |
+		    HDMI_AUD_CFG_ONE_BIT_INVALID;
+
+	switch (info->channels) {
+	case 8:
+		audio_cfg |= HDMI_AUD_CFG_CH78_VALID;
+	case 6:
+		audio_cfg |= HDMI_AUD_CFG_CH56_VALID;
+	case 4:
+		audio_cfg |= HDMI_AUD_CFG_CH34_VALID | HDMI_AUD_CFG_8CH;
+	case 2:
+		audio_cfg |= HDMI_AUD_CFG_CH12_VALID;
+		break;
+	default:
+		DRM_ERROR("ERROR: Unsupported number of channels (%d)!\n",
+			  info->channels);
+		return -EINVAL;
+	}
+
+	hdmi_write(hdmi, audio_cfg, HDMI_AUDIO_CFG);
+
+	hdmi->audio = *params;
+
+	return hdmi_audio_infoframe_config(hdmi);
+}
+
+static void hdmi_audio_shutdown(struct device *dev, void *data)
+{
+	struct sti_hdmi *hdmi = dev_get_drvdata(dev);
+	int audio_cfg;
+
+	DRM_DEBUG_DRIVER("\n");
+
+	/* disable audio */
+	audio_cfg = HDMI_AUD_CFG_SPDIF_DIV_2 | HDMI_AUD_CFG_DTS_INVALID |
+		    HDMI_AUD_CFG_ONE_BIT_INVALID;
+	hdmi_write(hdmi, audio_cfg, HDMI_AUDIO_CFG);
+
+	hdmi->audio.enabled = 0;
+	hdmi_audio_infoframe_config(hdmi);
+}
+
+static int hdmi_audio_hw_params(struct device *dev,
+				void *data,
+				struct hdmi_codec_daifmt *daifmt,
+				struct hdmi_codec_params *params)
+{
+	struct sti_hdmi *hdmi = dev_get_drvdata(dev);
+	int ret;
+	struct hdmi_audio_params audio = {
+		.sample_width = params->sample_width,
+		.sample_rate = params->sample_rate,
+		.cea = params->cea,
+	};
+
+	DRM_DEBUG_DRIVER("\n");
+
+	if (!hdmi->enabled)
+		return 0;
+
+	if ((daifmt->fmt != HDMI_I2S) || daifmt->bit_clk_inv ||
+	    daifmt->frame_clk_inv || daifmt->bit_clk_master ||
+	    daifmt->frame_clk_master) {
+		dev_err(dev, "%s: Bad flags %d %d %d %d\n", __func__,
+			daifmt->bit_clk_inv, daifmt->frame_clk_inv,
+			daifmt->bit_clk_master,
+			daifmt->frame_clk_master);
+		return -EINVAL;
+	}
+
+	audio.enabled = 1;
+
+	ret = hdmi_audio_configure(hdmi, &audio);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int hdmi_audio_digital_mute(struct device *dev, void *data, bool enable)
+{
+	struct sti_hdmi *hdmi = dev_get_drvdata(dev);
+
+	DRM_DEBUG_DRIVER("%s\n", enable ? "enable" : "disable");
+
+	if (enable)
+		hdmi_write(hdmi, HDMI_SAMPLE_FLAT_ALL, HDMI_SAMPLE_FLAT_MASK);
+	else
+		hdmi_write(hdmi, HDMI_SAMPLE_FLAT_NO, HDMI_SAMPLE_FLAT_MASK);
+
+	return 0;
+}
+
+static int hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf, size_t len)
+{
+	struct sti_hdmi *hdmi = dev_get_drvdata(dev);
+	struct drm_connector *connector = hdmi->drm_connector;
+
+	DRM_DEBUG_DRIVER("\n");
+	memcpy(buf, connector->eld, min(sizeof(connector->eld), len));
+
+	return 0;
+}
+
+static const struct hdmi_codec_ops audio_codec_ops = {
+	.hw_params = hdmi_audio_hw_params,
+	.audio_shutdown = hdmi_audio_shutdown,
+	.digital_mute = hdmi_audio_digital_mute,
+	.get_eld = hdmi_audio_get_eld,
+};
+
+static int sti_hdmi_register_audio_driver(struct device *dev,
+					  struct sti_hdmi *hdmi)
+{
+	struct hdmi_codec_pdata codec_data = {
+		.ops = &audio_codec_ops,
+		.max_i2s_channels = 8,
+		.i2s = 1,
+	};
+
+	DRM_DEBUG_DRIVER("\n");
+
+	hdmi->audio.enabled = 0;
+
+	hdmi->audio_pdev = platform_device_register_data(
+		dev, HDMI_CODEC_DRV_NAME, PLATFORM_DEVID_AUTO,
+		&codec_data, sizeof(codec_data));
+
+	if (IS_ERR(hdmi->audio_pdev))
+		return PTR_ERR(hdmi->audio_pdev);
+
+	DRM_INFO("%s Driver bound %s\n", HDMI_CODEC_DRV_NAME, dev_name(dev));
+
+	return 0;
+}
+
 static int sti_hdmi_bind(struct device *dev, struct device *master, void *data)
 {
 	struct sti_hdmi *hdmi = dev_get_drvdata(dev);
@@ -1095,9 +1325,7 @@ static int sti_hdmi_bind(struct device *dev, struct device *master, void *data)
 	/* initialise property */
 	sti_hdmi_connector_init_property(drm_dev, drm_connector);
 
-	err = drm_connector_register(drm_connector);
-	if (err)
-		goto err_connector;
+	hdmi->drm_connector = drm_connector;
 
 	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
@@ -1105,19 +1333,27 @@ static int sti_hdmi_bind(struct device *dev, struct device *master, void *data)
 		goto err_sysfs;
 	}
 
+	err = sti_hdmi_register_audio_driver(dev, hdmi);
+	if (err) {
+		DRM_ERROR("Failed to attach an audio codec\n");
+		goto err_sysfs;
+	}
+
+	/* Initialize audio infoframe */
+	err = hdmi_audio_infoframe_init(&hdmi->audio.cea);
+	if (err) {
+		DRM_ERROR("Failed to init audio infoframe\n");
+		goto err_sysfs;
+	}
+
 	/* Enable default interrupts */
 	hdmi_write(hdmi, HDMI_DEFAULT_INT, HDMI_INT_EN);
 
-	if (hdmi_debugfs_init(hdmi, drm_dev->primary))
-		DRM_ERROR("HDMI debugfs setup failed\n");
-
 	return 0;
 
 err_sysfs:
-	drm_connector_unregister(drm_connector);
-err_connector:
-	drm_connector_cleanup(drm_connector);
-
+	drm_bridge_remove(bridge);
+	hdmi->drm_connector = NULL;
 	return -EINVAL;
 }
 
@@ -1267,6 +1503,8 @@ static int sti_hdmi_remove(struct platform_device *pdev)
 	struct sti_hdmi *hdmi = dev_get_drvdata(&pdev->dev);
 
 	i2c_put_adapter(hdmi->ddc_adapt);
+	if (hdmi->audio_pdev)
+		platform_device_unregister(hdmi->audio_pdev);
 	component_del(&pdev->dev, &sti_hdmi_ops);
 
 	return 0;
diff --git a/drivers/gpu/drm/sti/sti_hdmi.h b/drivers/gpu/drm/sti/sti_hdmi.h
index ef3a94583bbd..119bc3582ac7 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.h
+++ b/drivers/gpu/drm/sti/sti_hdmi.h
@@ -23,6 +23,13 @@ struct hdmi_phy_ops {
 	void (*stop)(struct sti_hdmi *hdmi);
 };
 
+struct hdmi_audio_params {
+	bool enabled;
+	unsigned int sample_width;
+	unsigned int sample_rate;
+	struct hdmi_audio_infoframe cea;
+};
+
 /* values for the framing mode property */
 enum sti_hdmi_modes {
 	HDMI_MODE_HDMI,
@@ -67,6 +74,9 @@ static const struct drm_prop_enum_list colorspace_mode_names[] = {
  * @ddc_adapt: i2c ddc adapter
  * @colorspace: current colorspace selected
  * @hdmi_mode: select framing for HDMI or DVI
+ * @audio_pdev: ASoC hdmi-codec platform device
+ * @audio: hdmi audio parameters.
+ * @drm_connector: hdmi connector
  */
 struct sti_hdmi {
 	struct device dev;
@@ -89,6 +99,9 @@ struct sti_hdmi {
 	struct i2c_adapter *ddc_adapt;
 	enum hdmi_colorspace colorspace;
 	enum sti_hdmi_modes hdmi_mode;
+	struct platform_device *audio_pdev;
+	struct hdmi_audio_params audio;
+	struct drm_connector *drm_connector;
 };
 
 u32 hdmi_read(struct sti_hdmi *hdmi, int offset);
diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c
index 1edec29b9e45..b03232247966 100644
--- a/drivers/gpu/drm/sti/sti_hqvdp.c
+++ b/drivers/gpu/drm/sti/sti_hqvdp.c
@@ -555,14 +555,8 @@ static int hqvdp_dbg_show(struct seq_file *s, void *data)
 {
 	struct drm_info_node *node = s->private;
 	struct sti_hqvdp *hqvdp = (struct sti_hqvdp *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
 	int cmd, cmd_offset, infoxp70;
 	void *virt;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(s, "%s: (vaddr = 0x%p)",
 		   sti_plane_to_str(&hqvdp->plane), hqvdp->regs);
@@ -630,7 +624,6 @@ static int hqvdp_dbg_show(struct seq_file *s, void *data)
 
 	seq_puts(s, "\n");
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -1241,6 +1234,33 @@ static const struct drm_plane_helper_funcs sti_hqvdp_helpers_funcs = {
 	.atomic_disable = sti_hqvdp_atomic_disable,
 };
 
+static void sti_hqvdp_destroy(struct drm_plane *drm_plane)
+{
+	DRM_DEBUG_DRIVER("\n");
+
+	drm_plane_helper_disable(drm_plane);
+	drm_plane_cleanup(drm_plane);
+}
+
+static int sti_hqvdp_late_register(struct drm_plane *drm_plane)
+{
+	struct sti_plane *plane = to_sti_plane(drm_plane);
+	struct sti_hqvdp *hqvdp = to_sti_hqvdp(plane);
+
+	return hqvdp_debugfs_init(hqvdp, drm_plane->dev->primary);
+}
+
+struct drm_plane_funcs sti_hqvdp_plane_helpers_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = sti_hqvdp_destroy,
+	.set_property = sti_plane_set_property,
+	.reset = drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+	.late_register = sti_hqvdp_late_register,
+};
+
 static struct drm_plane *sti_hqvdp_create(struct drm_device *drm_dev,
 					  struct device *dev, int desc)
 {
@@ -1253,7 +1273,7 @@ static struct drm_plane *sti_hqvdp_create(struct drm_device *drm_dev,
 	sti_hqvdp_init(hqvdp);
 
 	res = drm_universal_plane_init(drm_dev, &hqvdp->plane.drm_plane, 1,
-				       &sti_plane_helpers_funcs,
+				       &sti_hqvdp_plane_helpers_funcs,
 				       hqvdp_supported_formats,
 				       ARRAY_SIZE(hqvdp_supported_formats),
 				       DRM_PLANE_TYPE_OVERLAY, NULL);
@@ -1266,9 +1286,6 @@ static struct drm_plane *sti_hqvdp_create(struct drm_device *drm_dev,
 
 	sti_plane_init_property(&hqvdp->plane, DRM_PLANE_TYPE_OVERLAY);
 
-	if (hqvdp_debugfs_init(hqvdp, drm_dev->primary))
-		DRM_ERROR("HQVDP debugfs setup failed\n");
-
 	return &hqvdp->plane.drm_plane;
 }
 
@@ -1346,6 +1363,7 @@ static int sti_hqvdp_probe(struct platform_device *pdev)
 	vtg_np = of_parse_phandle(pdev->dev.of_node, "st,vtg", 0);
 	if (vtg_np)
 		hqvdp->vtg = of_vtg_find(vtg_np);
+	of_node_put(vtg_np);
 
 	platform_set_drvdata(pdev, hqvdp);
 
diff --git a/drivers/gpu/drm/sti/sti_mixer.c b/drivers/gpu/drm/sti/sti_mixer.c
index aed7801b51f7..1885c7ab5a8b 100644
--- a/drivers/gpu/drm/sti/sti_mixer.c
+++ b/drivers/gpu/drm/sti/sti_mixer.c
@@ -151,12 +151,6 @@ static int mixer_dbg_show(struct seq_file *s, void *arg)
 {
 	struct drm_info_node *node = s->private;
 	struct sti_mixer *mixer = (struct sti_mixer *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(s, "%s: (vaddr = 0x%p)",
 		   sti_mixer_to_str(mixer), mixer->regs);
@@ -176,7 +170,6 @@ static int mixer_dbg_show(struct seq_file *s, void *arg)
 	mixer_dbg_mxn(s, mixer->regs + GAM_MIXER_MX0);
 	seq_puts(s, "\n");
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -188,7 +181,7 @@ static struct drm_info_list mixer1_debugfs_files[] = {
 	{ "mixer_aux", mixer_dbg_show, 0, NULL },
 };
 
-static int mixer_debugfs_init(struct sti_mixer *mixer, struct drm_minor *minor)
+int sti_mixer_debugfs_init(struct sti_mixer *mixer, struct drm_minor *minor)
 {
 	unsigned int i;
 	struct drm_info_list *mixer_debugfs_files;
@@ -400,8 +393,5 @@ struct sti_mixer *sti_mixer_create(struct device *dev,
 	DRM_DEBUG_DRIVER("%s created. Regs=%p\n",
 			 sti_mixer_to_str(mixer), mixer->regs);
 
-	if (mixer_debugfs_init(mixer, drm_dev->primary))
-		DRM_ERROR("MIXER debugfs setup failed\n");
-
 	return mixer;
 }
diff --git a/drivers/gpu/drm/sti/sti_mixer.h b/drivers/gpu/drm/sti/sti_mixer.h
index 6f35fc086873..830a3c42d886 100644
--- a/drivers/gpu/drm/sti/sti_mixer.h
+++ b/drivers/gpu/drm/sti/sti_mixer.h
@@ -55,6 +55,8 @@ int sti_mixer_active_video_area(struct sti_mixer *mixer,
 
 void sti_mixer_set_background_status(struct sti_mixer *mixer, bool enable);
 
+int sti_mixer_debugfs_init(struct sti_mixer *mixer, struct drm_minor *minor);
+
 /* depth in Cross-bar control = z order */
 #define GAM_MIXER_NB_DEPTH_LEVEL 6
 
diff --git a/drivers/gpu/drm/sti/sti_plane.c b/drivers/gpu/drm/sti/sti_plane.c
index f10c98d3f012..0cf3335ef37c 100644
--- a/drivers/gpu/drm/sti/sti_plane.c
+++ b/drivers/gpu/drm/sti/sti_plane.c
@@ -45,25 +45,15 @@ const char *sti_plane_to_str(struct sti_plane *plane)
 
 #define STI_FPS_INTERVAL_MS     3000
 
-static int sti_plane_timespec_ms_diff(struct timespec lhs, struct timespec rhs)
-{
-	struct timespec tmp_ts = timespec_sub(lhs, rhs);
-	u64 tmp_ns = (u64)timespec_to_ns(&tmp_ts);
-
-	do_div(tmp_ns, NSEC_PER_MSEC);
-
-	return (u32)tmp_ns;
-}
-
 void sti_plane_update_fps(struct sti_plane *plane,
 			  bool new_frame,
 			  bool new_field)
 {
-	struct timespec now;
+	ktime_t now;
 	struct sti_fps_info *fps;
 	int fpks, fipks, ms_since_last, num_frames, num_fields;
 
-	getrawmonotonic(&now);
+	now = ktime_get();
 
 	/* Compute number of frame updates */
 	fps = &plane->fps_info;
@@ -76,7 +66,7 @@ void sti_plane_update_fps(struct sti_plane *plane,
 		return;
 
 	fps->curr_frame_counter++;
-	ms_since_last = sti_plane_timespec_ms_diff(now, fps->last_timestamp);
+	ms_since_last = ktime_to_ms(ktime_sub(now, fps->last_timestamp));
 	num_frames = fps->curr_frame_counter - fps->last_frame_counter;
 
 	if (num_frames <= 0  || ms_since_last < STI_FPS_INTERVAL_MS)
@@ -106,17 +96,9 @@ void sti_plane_update_fps(struct sti_plane *plane,
 			 plane->fps_info.fips_str);
 }
 
-static void sti_plane_destroy(struct drm_plane *drm_plane)
-{
-	DRM_DEBUG_DRIVER("\n");
-
-	drm_plane_helper_disable(drm_plane);
-	drm_plane_cleanup(drm_plane);
-}
-
-static int sti_plane_set_property(struct drm_plane *drm_plane,
-				  struct drm_property *property,
-				  uint64_t val)
+int sti_plane_set_property(struct drm_plane *drm_plane,
+			   struct drm_property *property,
+			   uint64_t val)
 {
 	struct drm_device *dev = drm_plane->dev;
 	struct sti_private *private = dev->dev_private;
@@ -170,13 +152,3 @@ void sti_plane_init_property(struct sti_plane *plane,
 			 plane->drm_plane.base.id,
 			 sti_plane_to_str(plane), plane->zorder);
 }
-
-struct drm_plane_funcs sti_plane_helpers_funcs = {
-	.update_plane = drm_atomic_helper_update_plane,
-	.disable_plane = drm_atomic_helper_disable_plane,
-	.destroy = sti_plane_destroy,
-	.set_property = sti_plane_set_property,
-	.reset = drm_atomic_helper_plane_reset,
-	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
-};
diff --git a/drivers/gpu/drm/sti/sti_plane.h b/drivers/gpu/drm/sti/sti_plane.h
index c50a3b9f5d37..e0ea1dd3bb88 100644
--- a/drivers/gpu/drm/sti/sti_plane.h
+++ b/drivers/gpu/drm/sti/sti_plane.h
@@ -11,8 +11,6 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_plane_helper.h>
 
-extern struct drm_plane_funcs sti_plane_helpers_funcs;
-
 #define to_sti_plane(x) container_of(x, struct sti_plane, drm_plane)
 
 #define STI_PLANE_TYPE_SHIFT 8
@@ -57,7 +55,7 @@ struct sti_fps_info {
 	unsigned int last_frame_counter;
 	unsigned int curr_field_counter;
 	unsigned int last_field_counter;
-	struct timespec last_timestamp;
+	ktime_t	     last_timestamp;
 	char fps_str[FPS_LENGTH];
 	char fips_str[FPS_LENGTH];
 };
@@ -83,6 +81,11 @@ const char *sti_plane_to_str(struct sti_plane *plane);
 void sti_plane_update_fps(struct sti_plane *plane,
 			  bool new_frame,
 			  bool new_field);
+
+int sti_plane_set_property(struct drm_plane *drm_plane,
+			   struct drm_property *property,
+			   uint64_t val);
+
 void sti_plane_init_property(struct sti_plane *plane,
 			     enum drm_plane_type type);
 #endif
diff --git a/drivers/gpu/drm/sti/sti_tvout.c b/drivers/gpu/drm/sti/sti_tvout.c
index f983db5a59da..e25995b35715 100644
--- a/drivers/gpu/drm/sti/sti_tvout.c
+++ b/drivers/gpu/drm/sti/sti_tvout.c
@@ -112,6 +112,7 @@ struct sti_tvout {
 	struct drm_encoder *hdmi;
 	struct drm_encoder *hda;
 	struct drm_encoder *dvo;
+	bool debugfs_registered;
 };
 
 struct sti_tvout_encoder {
@@ -515,13 +516,7 @@ static int tvout_dbg_show(struct seq_file *s, void *data)
 {
 	struct drm_info_node *node = s->private;
 	struct sti_tvout *tvout = (struct sti_tvout *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
 	struct drm_crtc *crtc;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(s, "TVOUT: (vaddr = 0x%p)", tvout->regs);
 
@@ -587,7 +582,6 @@ static int tvout_dbg_show(struct seq_file *s, void *data)
 	DBGFS_DUMP(TVO_AUX_IN_VID_FORMAT);
 	seq_puts(s, "\n");
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -632,8 +626,37 @@ static void sti_tvout_encoder_destroy(struct drm_encoder *encoder)
 	kfree(sti_encoder);
 }
 
+static int sti_tvout_late_register(struct drm_encoder *encoder)
+{
+	struct sti_tvout *tvout = to_sti_tvout(encoder);
+	int ret;
+
+	if (tvout->debugfs_registered)
+		return 0;
+
+	ret = tvout_debugfs_init(tvout, encoder->dev->primary);
+	if (ret)
+		return ret;
+
+	tvout->debugfs_registered = true;
+	return 0;
+}
+
+static void sti_tvout_early_unregister(struct drm_encoder *encoder)
+{
+	struct sti_tvout *tvout = to_sti_tvout(encoder);
+
+	if (!tvout->debugfs_registered)
+		return;
+
+	tvout_debugfs_exit(tvout, encoder->dev->primary);
+	tvout->debugfs_registered = false;
+}
+
 static const struct drm_encoder_funcs sti_tvout_encoder_funcs = {
 	.destroy = sti_tvout_encoder_destroy,
+	.late_register = sti_tvout_late_register,
+	.early_unregister = sti_tvout_early_unregister,
 };
 
 static void sti_dvo_encoder_enable(struct drm_encoder *encoder)
@@ -820,9 +843,6 @@ static int sti_tvout_bind(struct device *dev, struct device *master, void *data)
 
 	sti_tvout_create_encoders(drm_dev, tvout);
 
-	if (tvout_debugfs_init(tvout, drm_dev->primary))
-		DRM_ERROR("TVOUT debugfs setup failed\n");
-
 	return 0;
 }
 
@@ -830,11 +850,8 @@ static void sti_tvout_unbind(struct device *dev, struct device *master,
 	void *data)
 {
 	struct sti_tvout *tvout = dev_get_drvdata(dev);
-	struct drm_device *drm_dev = data;
 
 	sti_tvout_destroy_encoders(tvout);
-
-	tvout_debugfs_exit(tvout, drm_dev->primary);
 }
 
 static const struct component_ops sti_tvout_ops = {
diff --git a/drivers/gpu/drm/sti/sti_vid.c b/drivers/gpu/drm/sti/sti_vid.c
index 523ed19f5ac6..47634a0251fc 100644
--- a/drivers/gpu/drm/sti/sti_vid.c
+++ b/drivers/gpu/drm/sti/sti_vid.c
@@ -92,12 +92,6 @@ static int vid_dbg_show(struct seq_file *s, void *arg)
 {
 	struct drm_info_node *node = s->private;
 	struct sti_vid *vid = (struct sti_vid *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(s, "VID: (vaddr= 0x%p)", vid->regs);
 
@@ -122,7 +116,6 @@ static int vid_dbg_show(struct seq_file *s, void *arg)
 	DBGFS_DUMP(VID_CSAT);
 	seq_puts(s, "\n");
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 
@@ -130,7 +123,7 @@ static struct drm_info_list vid_debugfs_files[] = {
 	{ "vid", vid_dbg_show, 0, NULL },
 };
 
-static int vid_debugfs_init(struct sti_vid *vid, struct drm_minor *minor)
+int vid_debugfs_init(struct sti_vid *vid, struct drm_minor *minor)
 {
 	unsigned int i;
 
@@ -227,8 +220,5 @@ struct sti_vid *sti_vid_create(struct device *dev, struct drm_device *drm_dev,
 
 	sti_vid_init(vid);
 
-	if (vid_debugfs_init(vid, drm_dev->primary))
-		DRM_ERROR("VID debugfs setup failed\n");
-
 	return vid;
 }
diff --git a/drivers/gpu/drm/sti/sti_vid.h b/drivers/gpu/drm/sti/sti_vid.h
index 6c842344f3d8..fdc90f922a05 100644
--- a/drivers/gpu/drm/sti/sti_vid.h
+++ b/drivers/gpu/drm/sti/sti_vid.h
@@ -26,4 +26,6 @@ void sti_vid_disable(struct sti_vid *vid);
 struct sti_vid *sti_vid_create(struct device *dev, struct drm_device *drm_dev,
 			       int id, void __iomem *baseaddr);
 
+int vid_debugfs_init(struct sti_vid *vid, struct drm_minor *minor);
+
 #endif
diff --git a/drivers/gpu/drm/sti/sti_vtg.c b/drivers/gpu/drm/sti/sti_vtg.c
index 6bf4ce466d20..0bdc385eec17 100644
--- a/drivers/gpu/drm/sti/sti_vtg.c
+++ b/drivers/gpu/drm/sti/sti_vtg.c
@@ -65,7 +65,7 @@
 #define HDMI_DELAY          (5)
 
 /* Delay introduced by the DVO in nb of pixel */
-#define DVO_DELAY           (2)
+#define DVO_DELAY           (7)
 
 /* delay introduced by the Arbitrary Waveform Generator in nb of pixels */
 #define AWG_DELAY_HD        (-9)
@@ -432,6 +432,7 @@ static int vtg_probe(struct platform_device *pdev)
 	np = of_parse_phandle(pdev->dev.of_node, "st,slave", 0);
 	if (np) {
 		vtg->slave = of_vtg_find(np);
+		of_node_put(np);
 
 		if (!vtg->slave)
 			return -EPROBE_DEFER;
diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c
index 41cacecbea9a..4a192210574f 100644
--- a/drivers/gpu/drm/sun4i/sun4i_crtc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c
@@ -51,10 +51,22 @@ static void sun4i_crtc_atomic_flush(struct drm_crtc *crtc,
 {
 	struct sun4i_crtc *scrtc = drm_crtc_to_sun4i_crtc(crtc);
 	struct sun4i_drv *drv = scrtc->drv;
+	struct drm_pending_vblank_event *event = crtc->state->event;
 
 	DRM_DEBUG_DRIVER("Committing plane changes\n");
 
 	sun4i_backend_commit(drv->backend);
+
+	if (event) {
+		crtc->state->event = NULL;
+
+		spin_lock_irq(&crtc->dev->event_lock);
+		if (drm_crtc_vblank_get(crtc) == 0)
+			drm_crtc_arm_vblank_event(crtc, event);
+		else
+			drm_crtc_send_vblank_event(crtc, event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
 }
 
 static void sun4i_crtc_disable(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 937394cbc241..7092daaf6c43 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -75,7 +75,7 @@ static struct drm_driver sun4i_drv_driver = {
 	.dumb_create		= drm_gem_cma_dumb_create,
 	.dumb_destroy		= drm_gem_dumb_destroy,
 	.dumb_map_offset	= drm_gem_cma_dumb_map_offset,
-	.gem_free_object	= drm_gem_cma_free_object,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops		= &drm_gem_cma_vm_ops,
 
 	/* PRIME Operations */
@@ -123,10 +123,6 @@ static int sun4i_drv_bind(struct device *dev)
 	if (!drm)
 		return -ENOMEM;
 
-	ret = drm_dev_set_unique(drm, dev_name(drm->dev));
-	if (ret)
-		goto free_drm;
-
 	drv = devm_kzalloc(dev, sizeof(*drv), GFP_KERNEL);
 	if (!drv) {
 		ret = -ENOMEM;
@@ -178,14 +174,8 @@ static int sun4i_drv_bind(struct device *dev)
 	if (ret)
 		goto free_drm;
 
-	ret = drm_connector_register_all(drm);
-	if (ret)
-		goto unregister_drm;
-
 	return 0;
 
-unregister_drm:
-	drm_dev_unregister(drm);
 free_drm:
 	drm_dev_unref(drm);
 	return ret;
@@ -195,7 +185,6 @@ static void sun4i_drv_unbind(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
 
-	drm_connector_unregister_all(drm);
 	drm_dev_unregister(drm);
 	drm_kms_helper_poll_fini(drm);
 	sun4i_framebuffer_free(drm);
diff --git a/drivers/gpu/drm/sun4i/sun4i_framebuffer.c b/drivers/gpu/drm/sun4i/sun4i_framebuffer.c
index a0b30c216a5b..70688febd7ac 100644
--- a/drivers/gpu/drm/sun4i/sun4i_framebuffer.c
+++ b/drivers/gpu/drm/sun4i/sun4i_framebuffer.c
@@ -20,8 +20,7 @@ static void sun4i_de_output_poll_changed(struct drm_device *drm)
 {
 	struct sun4i_drv *drv = drm->dev_private;
 
-	if (drv->fbdev)
-		drm_fbdev_cma_hotplug_event(drv->fbdev);
+	drm_fbdev_cma_hotplug_event(drv->fbdev);
 }
 
 static const struct drm_mode_config_funcs sun4i_de_mode_config_funcs = {
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index aaffe9e64ffb..f5bbac6efb4c 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -104,19 +104,9 @@ static int sun4i_rgb_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-static struct drm_encoder *
-sun4i_rgb_best_encoder(struct drm_connector *connector)
-{
-	struct sun4i_rgb *rgb =
-		drm_connector_to_sun4i_rgb(connector);
-
-	return &rgb->encoder;
-}
-
 static struct drm_connector_helper_funcs sun4i_rgb_con_helper_funcs = {
 	.get_modes	= sun4i_rgb_get_modes,
 	.mode_valid	= sun4i_rgb_mode_valid,
-	.best_encoder	= sun4i_rgb_best_encoder,
 };
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/sun4i/sun4i_tv.c b/drivers/gpu/drm/sun4i/sun4i_tv.c
index bc047f923508..b84147896294 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tv.c
@@ -526,18 +526,9 @@ static int sun4i_tv_comp_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
-static struct drm_encoder *
-sun4i_tv_comp_best_encoder(struct drm_connector *connector)
-{
-	struct sun4i_tv *tv = drm_connector_to_sun4i_tv(connector);
-
-	return &tv->encoder;
-}
-
 static struct drm_connector_helper_funcs sun4i_tv_comp_connector_helper_funcs = {
 	.get_modes	= sun4i_tv_comp_get_modes,
 	.mode_valid	= sun4i_tv_comp_mode_valid,
-	.best_encoder	= sun4i_tv_comp_best_encoder,
 };
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 39940f5b7c91..8495bd01b544 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -10,6 +10,7 @@
 #include <linux/clk.h>
 #include <linux/debugfs.h>
 #include <linux/iommu.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
 #include <soc/tegra/pmc.h>
@@ -1216,6 +1217,8 @@ static void tegra_crtc_disable(struct drm_crtc *crtc)
 
 	tegra_dc_stats_reset(&dc->stats);
 	drm_crtc_vblank_off(crtc);
+
+	pm_runtime_put_sync(dc->dev);
 }
 
 static void tegra_crtc_enable(struct drm_crtc *crtc)
@@ -1225,6 +1228,48 @@ static void tegra_crtc_enable(struct drm_crtc *crtc)
 	struct tegra_dc *dc = to_tegra_dc(crtc);
 	u32 value;
 
+	pm_runtime_get_sync(dc->dev);
+
+	/* initialize display controller */
+	if (dc->syncpt) {
+		u32 syncpt = host1x_syncpt_id(dc->syncpt);
+
+		value = SYNCPT_CNTRL_NO_STALL;
+		tegra_dc_writel(dc, value, DC_CMD_GENERAL_INCR_SYNCPT_CNTRL);
+
+		value = SYNCPT_VSYNC_ENABLE | syncpt;
+		tegra_dc_writel(dc, value, DC_CMD_CONT_SYNCPT_VSYNC);
+	}
+
+	value = WIN_A_UF_INT | WIN_B_UF_INT | WIN_C_UF_INT |
+		WIN_A_OF_INT | WIN_B_OF_INT | WIN_C_OF_INT;
+	tegra_dc_writel(dc, value, DC_CMD_INT_TYPE);
+
+	value = WIN_A_UF_INT | WIN_B_UF_INT | WIN_C_UF_INT |
+		WIN_A_OF_INT | WIN_B_OF_INT | WIN_C_OF_INT;
+	tegra_dc_writel(dc, value, DC_CMD_INT_POLARITY);
+
+	/* initialize timer */
+	value = CURSOR_THRESHOLD(0) | WINDOW_A_THRESHOLD(0x20) |
+		WINDOW_B_THRESHOLD(0x20) | WINDOW_C_THRESHOLD(0x20);
+	tegra_dc_writel(dc, value, DC_DISP_DISP_MEM_HIGH_PRIORITY);
+
+	value = CURSOR_THRESHOLD(0) | WINDOW_A_THRESHOLD(1) |
+		WINDOW_B_THRESHOLD(1) | WINDOW_C_THRESHOLD(1);
+	tegra_dc_writel(dc, value, DC_DISP_DISP_MEM_HIGH_PRIORITY_TIMER);
+
+	value = VBLANK_INT | WIN_A_UF_INT | WIN_B_UF_INT | WIN_C_UF_INT |
+		WIN_A_OF_INT | WIN_B_OF_INT | WIN_C_OF_INT;
+	tegra_dc_writel(dc, value, DC_CMD_INT_ENABLE);
+
+	value = WIN_A_UF_INT | WIN_B_UF_INT | WIN_C_UF_INT |
+		WIN_A_OF_INT | WIN_B_OF_INT | WIN_C_OF_INT;
+	tegra_dc_writel(dc, value, DC_CMD_INT_MASK);
+
+	if (dc->soc->supports_border_color)
+		tegra_dc_writel(dc, 0, DC_DISP_BORDER_COLOR);
+
+	/* apply PLL and pixel clock changes */
 	tegra_dc_commit_state(dc, state);
 
 	/* program display mode */
@@ -1685,7 +1730,6 @@ static int tegra_dc_init(struct host1x_client *client)
 	struct tegra_drm *tegra = drm->dev_private;
 	struct drm_plane *primary = NULL;
 	struct drm_plane *cursor = NULL;
-	u32 value;
 	int err;
 
 	dc->syncpt = host1x_syncpt_request(dc->dev, flags);
@@ -1755,47 +1799,6 @@ static int tegra_dc_init(struct host1x_client *client)
 		goto cleanup;
 	}
 
-	/* initialize display controller */
-	if (dc->syncpt) {
-		u32 syncpt = host1x_syncpt_id(dc->syncpt);
-
-		value = SYNCPT_CNTRL_NO_STALL;
-		tegra_dc_writel(dc, value, DC_CMD_GENERAL_INCR_SYNCPT_CNTRL);
-
-		value = SYNCPT_VSYNC_ENABLE | syncpt;
-		tegra_dc_writel(dc, value, DC_CMD_CONT_SYNCPT_VSYNC);
-	}
-
-	value = WIN_A_UF_INT | WIN_B_UF_INT | WIN_C_UF_INT |
-		WIN_A_OF_INT | WIN_B_OF_INT | WIN_C_OF_INT;
-	tegra_dc_writel(dc, value, DC_CMD_INT_TYPE);
-
-	value = WIN_A_UF_INT | WIN_B_UF_INT | WIN_C_UF_INT |
-		WIN_A_OF_INT | WIN_B_OF_INT | WIN_C_OF_INT;
-	tegra_dc_writel(dc, value, DC_CMD_INT_POLARITY);
-
-	/* initialize timer */
-	value = CURSOR_THRESHOLD(0) | WINDOW_A_THRESHOLD(0x20) |
-		WINDOW_B_THRESHOLD(0x20) | WINDOW_C_THRESHOLD(0x20);
-	tegra_dc_writel(dc, value, DC_DISP_DISP_MEM_HIGH_PRIORITY);
-
-	value = CURSOR_THRESHOLD(0) | WINDOW_A_THRESHOLD(1) |
-		WINDOW_B_THRESHOLD(1) | WINDOW_C_THRESHOLD(1);
-	tegra_dc_writel(dc, value, DC_DISP_DISP_MEM_HIGH_PRIORITY_TIMER);
-
-	value = VBLANK_INT | WIN_A_UF_INT | WIN_B_UF_INT | WIN_C_UF_INT |
-		WIN_A_OF_INT | WIN_B_OF_INT | WIN_C_OF_INT;
-	tegra_dc_writel(dc, value, DC_CMD_INT_ENABLE);
-
-	value = WIN_A_UF_INT | WIN_B_UF_INT | WIN_C_UF_INT |
-		WIN_A_OF_INT | WIN_B_OF_INT | WIN_C_OF_INT;
-	tegra_dc_writel(dc, value, DC_CMD_INT_MASK);
-
-	if (dc->soc->supports_border_color)
-		tegra_dc_writel(dc, 0, DC_DISP_BORDER_COLOR);
-
-	tegra_dc_stats_reset(&dc->stats);
-
 	return 0;
 
 cleanup:
@@ -1987,33 +1990,15 @@ static int tegra_dc_probe(struct platform_device *pdev)
 		return PTR_ERR(dc->rst);
 	}
 
+	reset_control_assert(dc->rst);
+
 	if (dc->soc->has_powergate) {
 		if (dc->pipe == 0)
 			dc->powergate = TEGRA_POWERGATE_DIS;
 		else
 			dc->powergate = TEGRA_POWERGATE_DISB;
 
-		err = tegra_powergate_sequence_power_up(dc->powergate, dc->clk,
-							dc->rst);
-		if (err < 0) {
-			dev_err(&pdev->dev, "failed to power partition: %d\n",
-				err);
-			return err;
-		}
-	} else {
-		err = clk_prepare_enable(dc->clk);
-		if (err < 0) {
-			dev_err(&pdev->dev, "failed to enable clock: %d\n",
-				err);
-			return err;
-		}
-
-		err = reset_control_deassert(dc->rst);
-		if (err < 0) {
-			dev_err(&pdev->dev, "failed to deassert reset: %d\n",
-				err);
-			return err;
-		}
+		tegra_powergate_power_off(dc->powergate);
 	}
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -2027,16 +2012,19 @@ static int tegra_dc_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	INIT_LIST_HEAD(&dc->client.list);
-	dc->client.ops = &dc_client_ops;
-	dc->client.dev = &pdev->dev;
-
 	err = tegra_dc_rgb_probe(dc);
 	if (err < 0 && err != -ENODEV) {
 		dev_err(&pdev->dev, "failed to probe RGB output: %d\n", err);
 		return err;
 	}
 
+	platform_set_drvdata(pdev, dc);
+	pm_runtime_enable(&pdev->dev);
+
+	INIT_LIST_HEAD(&dc->client.list);
+	dc->client.ops = &dc_client_ops;
+	dc->client.dev = &pdev->dev;
+
 	err = host1x_client_register(&dc->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
@@ -2044,8 +2032,6 @@ static int tegra_dc_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	platform_set_drvdata(pdev, dc);
-
 	return 0;
 }
 
@@ -2067,7 +2053,22 @@ static int tegra_dc_remove(struct platform_device *pdev)
 		return err;
 	}
 
-	reset_control_assert(dc->rst);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int tegra_dc_suspend(struct device *dev)
+{
+	struct tegra_dc *dc = dev_get_drvdata(dev);
+	int err;
+
+	err = reset_control_assert(dc->rst);
+	if (err < 0) {
+		dev_err(dev, "failed to assert reset: %d\n", err);
+		return err;
+	}
 
 	if (dc->soc->has_powergate)
 		tegra_powergate_power_off(dc->powergate);
@@ -2077,10 +2078,45 @@ static int tegra_dc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int tegra_dc_resume(struct device *dev)
+{
+	struct tegra_dc *dc = dev_get_drvdata(dev);
+	int err;
+
+	if (dc->soc->has_powergate) {
+		err = tegra_powergate_sequence_power_up(dc->powergate, dc->clk,
+							dc->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to power partition: %d\n", err);
+			return err;
+		}
+	} else {
+		err = clk_prepare_enable(dc->clk);
+		if (err < 0) {
+			dev_err(dev, "failed to enable clock: %d\n", err);
+			return err;
+		}
+
+		err = reset_control_deassert(dc->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to deassert reset: %d\n", err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops tegra_dc_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_dc_suspend, tegra_dc_resume, NULL)
+};
+
 struct platform_driver tegra_dc_driver = {
 	.driver = {
 		.name = "tegra-dc",
 		.of_match_table = tegra_dc_of_match,
+		.pm = &tegra_dc_pm_ops,
 	},
 	.probe = tegra_dc_probe,
 	.remove = tegra_dc_remove,
diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c
index b24a0f14821a..059f409556d5 100644
--- a/drivers/gpu/drm/tegra/dpaux.c
+++ b/drivers/gpu/drm/tegra/dpaux.c
@@ -12,6 +12,9 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/of_gpio.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/regulator/consumer.h>
@@ -44,6 +47,11 @@ struct tegra_dpaux {
 	struct completion complete;
 	struct work_struct work;
 	struct list_head list;
+
+#ifdef CONFIG_GENERIC_PINCONF
+	struct pinctrl_dev *pinctrl;
+	struct pinctrl_desc desc;
+#endif
 };
 
 static inline struct tegra_dpaux *to_dpaux(struct drm_dp_aux *aux)
@@ -267,6 +275,148 @@ static irqreturn_t tegra_dpaux_irq(int irq, void *data)
 	return ret;
 }
 
+enum tegra_dpaux_functions {
+	DPAUX_PADCTL_FUNC_AUX,
+	DPAUX_PADCTL_FUNC_I2C,
+	DPAUX_PADCTL_FUNC_OFF,
+};
+
+static void tegra_dpaux_pad_power_down(struct tegra_dpaux *dpaux)
+{
+	u32 value = tegra_dpaux_readl(dpaux, DPAUX_HYBRID_SPARE);
+
+	value |= DPAUX_HYBRID_SPARE_PAD_POWER_DOWN;
+
+	tegra_dpaux_writel(dpaux, value, DPAUX_HYBRID_SPARE);
+}
+
+static void tegra_dpaux_pad_power_up(struct tegra_dpaux *dpaux)
+{
+	u32 value = tegra_dpaux_readl(dpaux, DPAUX_HYBRID_SPARE);
+
+	value &= ~DPAUX_HYBRID_SPARE_PAD_POWER_DOWN;
+
+	tegra_dpaux_writel(dpaux, value, DPAUX_HYBRID_SPARE);
+}
+
+static int tegra_dpaux_pad_config(struct tegra_dpaux *dpaux, unsigned function)
+{
+	u32 value;
+
+	switch (function) {
+	case DPAUX_PADCTL_FUNC_AUX:
+		value = DPAUX_HYBRID_PADCTL_AUX_CMH(2) |
+			DPAUX_HYBRID_PADCTL_AUX_DRVZ(4) |
+			DPAUX_HYBRID_PADCTL_AUX_DRVI(0x18) |
+			DPAUX_HYBRID_PADCTL_AUX_INPUT_RCV |
+			DPAUX_HYBRID_PADCTL_MODE_AUX;
+		break;
+
+	case DPAUX_PADCTL_FUNC_I2C:
+		value = DPAUX_HYBRID_PADCTL_I2C_SDA_INPUT_RCV |
+			DPAUX_HYBRID_PADCTL_I2C_SCL_INPUT_RCV |
+			DPAUX_HYBRID_PADCTL_MODE_I2C;
+		break;
+
+	case DPAUX_PADCTL_FUNC_OFF:
+		tegra_dpaux_pad_power_down(dpaux);
+		return 0;
+
+	default:
+		return -ENOTSUPP;
+	}
+
+	tegra_dpaux_writel(dpaux, value, DPAUX_HYBRID_PADCTL);
+	tegra_dpaux_pad_power_up(dpaux);
+
+	return 0;
+}
+
+#ifdef CONFIG_GENERIC_PINCONF
+static const struct pinctrl_pin_desc tegra_dpaux_pins[] = {
+	PINCTRL_PIN(0, "DP_AUX_CHx_P"),
+	PINCTRL_PIN(1, "DP_AUX_CHx_N"),
+};
+
+static const unsigned tegra_dpaux_pin_numbers[] = { 0, 1 };
+
+static const char * const tegra_dpaux_groups[] = {
+	"dpaux-io",
+};
+
+static const char * const tegra_dpaux_functions[] = {
+	"aux",
+	"i2c",
+	"off",
+};
+
+static int tegra_dpaux_get_groups_count(struct pinctrl_dev *pinctrl)
+{
+	return ARRAY_SIZE(tegra_dpaux_groups);
+}
+
+static const char *tegra_dpaux_get_group_name(struct pinctrl_dev *pinctrl,
+					      unsigned int group)
+{
+	return tegra_dpaux_groups[group];
+}
+
+static int tegra_dpaux_get_group_pins(struct pinctrl_dev *pinctrl,
+				      unsigned group, const unsigned **pins,
+				      unsigned *num_pins)
+{
+	*pins = tegra_dpaux_pin_numbers;
+	*num_pins = ARRAY_SIZE(tegra_dpaux_pin_numbers);
+
+	return 0;
+}
+
+static const struct pinctrl_ops tegra_dpaux_pinctrl_ops = {
+	.get_groups_count = tegra_dpaux_get_groups_count,
+	.get_group_name = tegra_dpaux_get_group_name,
+	.get_group_pins = tegra_dpaux_get_group_pins,
+	.dt_node_to_map = pinconf_generic_dt_node_to_map_group,
+	.dt_free_map = pinconf_generic_dt_free_map,
+};
+
+static int tegra_dpaux_get_functions_count(struct pinctrl_dev *pinctrl)
+{
+	return ARRAY_SIZE(tegra_dpaux_functions);
+}
+
+static const char *tegra_dpaux_get_function_name(struct pinctrl_dev *pinctrl,
+						 unsigned int function)
+{
+	return tegra_dpaux_functions[function];
+}
+
+static int tegra_dpaux_get_function_groups(struct pinctrl_dev *pinctrl,
+					   unsigned int function,
+					   const char * const **groups,
+					   unsigned * const num_groups)
+{
+	*num_groups = ARRAY_SIZE(tegra_dpaux_groups);
+	*groups = tegra_dpaux_groups;
+
+	return 0;
+}
+
+static int tegra_dpaux_set_mux(struct pinctrl_dev *pinctrl,
+			       unsigned int function, unsigned int group)
+{
+	struct tegra_dpaux *dpaux = pinctrl_dev_get_drvdata(pinctrl);
+
+	return tegra_dpaux_pad_config(dpaux, function);
+}
+
+static const struct pinmux_ops tegra_dpaux_pinmux_ops = {
+	.get_functions_count = tegra_dpaux_get_functions_count,
+	.get_function_name = tegra_dpaux_get_function_name,
+	.get_function_groups = tegra_dpaux_get_function_groups,
+	.set_mux = tegra_dpaux_set_mux,
+};
+#endif
+
 static int tegra_dpaux_probe(struct platform_device *pdev)
 {
 	struct tegra_dpaux *dpaux;
@@ -294,11 +444,14 @@ static int tegra_dpaux_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	dpaux->rst = devm_reset_control_get(&pdev->dev, "dpaux");
-	if (IS_ERR(dpaux->rst)) {
-		dev_err(&pdev->dev, "failed to get reset control: %ld\n",
-			PTR_ERR(dpaux->rst));
-		return PTR_ERR(dpaux->rst);
+	if (!pdev->dev.pm_domain) {
+		dpaux->rst = devm_reset_control_get(&pdev->dev, "dpaux");
+		if (IS_ERR(dpaux->rst)) {
+			dev_err(&pdev->dev,
+				"failed to get reset control: %ld\n",
+				PTR_ERR(dpaux->rst));
+			return PTR_ERR(dpaux->rst);
+		}
 	}
 
 	dpaux->clk = devm_clk_get(&pdev->dev, NULL);
@@ -315,34 +468,37 @@ static int tegra_dpaux_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	reset_control_deassert(dpaux->rst);
+	if (dpaux->rst)
+		reset_control_deassert(dpaux->rst);
 
 	dpaux->clk_parent = devm_clk_get(&pdev->dev, "parent");
 	if (IS_ERR(dpaux->clk_parent)) {
 		dev_err(&pdev->dev, "failed to get parent clock: %ld\n",
 			PTR_ERR(dpaux->clk_parent));
-		return PTR_ERR(dpaux->clk_parent);
+		err = PTR_ERR(dpaux->clk_parent);
+		goto assert_reset;
 	}
 
 	err = clk_prepare_enable(dpaux->clk_parent);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to enable parent clock: %d\n",
 			err);
-		return err;
+		goto assert_reset;
 	}
 
 	err = clk_set_rate(dpaux->clk_parent, 270000000);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to set clock to 270 MHz: %d\n",
 			err);
-		return err;
+		goto disable_parent_clk;
 	}
 
 	dpaux->vdd = devm_regulator_get(&pdev->dev, "vdd");
 	if (IS_ERR(dpaux->vdd)) {
 		dev_err(&pdev->dev, "failed to get VDD supply: %ld\n",
 			PTR_ERR(dpaux->vdd));
-		return PTR_ERR(dpaux->vdd);
+		err = PTR_ERR(dpaux->vdd);
+		goto disable_parent_clk;
 	}
 
 	err = devm_request_irq(dpaux->dev, dpaux->irq, tegra_dpaux_irq, 0,
@@ -350,7 +506,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev)
 	if (err < 0) {
 		dev_err(dpaux->dev, "failed to request IRQ#%u: %d\n",
 			dpaux->irq, err);
-		return err;
+		goto disable_parent_clk;
 	}
 
 	disable_irq(dpaux->irq);
@@ -360,7 +516,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev)
 
 	err = drm_dp_aux_register(&dpaux->aux);
 	if (err < 0)
-		return err;
+		goto disable_parent_clk;
 
 	/*
 	 * Assume that by default the DPAUX/I2C pads will be used for HDMI,
@@ -370,16 +526,24 @@ static int tegra_dpaux_probe(struct platform_device *pdev)
 	 * is no possibility to perform the I2C mode configuration in the
 	 * HDMI path.
 	 */
-	value = tegra_dpaux_readl(dpaux, DPAUX_HYBRID_SPARE);
-	value &= ~DPAUX_HYBRID_SPARE_PAD_POWER_DOWN;
-	tegra_dpaux_writel(dpaux, value, DPAUX_HYBRID_SPARE);
-
-	value = tegra_dpaux_readl(dpaux, DPAUX_HYBRID_PADCTL);
-	value = DPAUX_HYBRID_PADCTL_I2C_SDA_INPUT_RCV |
-		DPAUX_HYBRID_PADCTL_I2C_SCL_INPUT_RCV |
-		DPAUX_HYBRID_PADCTL_MODE_I2C;
-	tegra_dpaux_writel(dpaux, value, DPAUX_HYBRID_PADCTL);
+	err = tegra_dpaux_pad_config(dpaux, DPAUX_HYBRID_PADCTL_MODE_I2C);
+	if (err < 0)
+		return err;
 
+#ifdef CONFIG_GENERIC_PINCONF
+	dpaux->desc.name = dev_name(&pdev->dev);
+	dpaux->desc.pins = tegra_dpaux_pins;
+	dpaux->desc.npins = ARRAY_SIZE(tegra_dpaux_pins);
+	dpaux->desc.pctlops = &tegra_dpaux_pinctrl_ops;
+	dpaux->desc.pmxops = &tegra_dpaux_pinmux_ops;
+	dpaux->desc.owner = THIS_MODULE;
+
+	dpaux->pinctrl = devm_pinctrl_register(&pdev->dev, &dpaux->desc, dpaux);
+	if (!dpaux->pinctrl) {
+		dev_err(&pdev->dev, "failed to register pincontrol\n");
+		return -ENODEV;
+	}
+#endif
 	/* enable and clear all interrupts */
 	value = DPAUX_INTR_AUX_DONE | DPAUX_INTR_IRQ_EVENT |
 		DPAUX_INTR_UNPLUG_EVENT | DPAUX_INTR_PLUG_EVENT;
@@ -393,17 +557,24 @@ static int tegra_dpaux_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, dpaux);
 
 	return 0;
+
+disable_parent_clk:
+	clk_disable_unprepare(dpaux->clk_parent);
+assert_reset:
+	if (dpaux->rst)
+		reset_control_assert(dpaux->rst);
+
+	clk_disable_unprepare(dpaux->clk);
+
+	return err;
 }
 
 static int tegra_dpaux_remove(struct platform_device *pdev)
 {
 	struct tegra_dpaux *dpaux = platform_get_drvdata(pdev);
-	u32 value;
 
 	/* make sure pads are powered down when not in use */
-	value = tegra_dpaux_readl(dpaux, DPAUX_HYBRID_SPARE);
-	value |= DPAUX_HYBRID_SPARE_PAD_POWER_DOWN;
-	tegra_dpaux_writel(dpaux, value, DPAUX_HYBRID_SPARE);
+	tegra_dpaux_pad_power_down(dpaux);
 
 	drm_dp_aux_unregister(&dpaux->aux);
 
@@ -414,7 +585,10 @@ static int tegra_dpaux_remove(struct platform_device *pdev)
 	cancel_work_sync(&dpaux->work);
 
 	clk_disable_unprepare(dpaux->clk_parent);
-	reset_control_assert(dpaux->rst);
+
+	if (dpaux->rst)
+		reset_control_assert(dpaux->rst);
+
 	clk_disable_unprepare(dpaux->clk);
 
 	return 0;
@@ -528,30 +702,15 @@ enum drm_connector_status drm_dp_aux_detect(struct drm_dp_aux *aux)
 int drm_dp_aux_enable(struct drm_dp_aux *aux)
 {
 	struct tegra_dpaux *dpaux = to_dpaux(aux);
-	u32 value;
-
-	value = DPAUX_HYBRID_PADCTL_AUX_CMH(2) |
-		DPAUX_HYBRID_PADCTL_AUX_DRVZ(4) |
-		DPAUX_HYBRID_PADCTL_AUX_DRVI(0x18) |
-		DPAUX_HYBRID_PADCTL_AUX_INPUT_RCV |
-		DPAUX_HYBRID_PADCTL_MODE_AUX;
-	tegra_dpaux_writel(dpaux, value, DPAUX_HYBRID_PADCTL);
-
-	value = tegra_dpaux_readl(dpaux, DPAUX_HYBRID_SPARE);
-	value &= ~DPAUX_HYBRID_SPARE_PAD_POWER_DOWN;
-	tegra_dpaux_writel(dpaux, value, DPAUX_HYBRID_SPARE);
 
-	return 0;
+	return tegra_dpaux_pad_config(dpaux, DPAUX_PADCTL_FUNC_AUX);
 }
 
 int drm_dp_aux_disable(struct drm_dp_aux *aux)
 {
 	struct tegra_dpaux *dpaux = to_dpaux(aux);
-	u32 value;
 
-	value = tegra_dpaux_readl(dpaux, DPAUX_HYBRID_SPARE);
-	value |= DPAUX_HYBRID_SPARE_PAD_POWER_DOWN;
-	tegra_dpaux_writel(dpaux, value, DPAUX_HYBRID_SPARE);
+	tegra_dpaux_pad_power_down(dpaux);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index b59c3bf0df44..755264d9db22 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -56,8 +56,8 @@ static void tegra_atomic_complete(struct tegra_drm *tegra,
 	 */
 
 	drm_atomic_helper_commit_modeset_disables(drm, state);
-	drm_atomic_helper_commit_planes(drm, state, false);
 	drm_atomic_helper_commit_modeset_enables(drm, state);
+	drm_atomic_helper_commit_planes(drm, state, true);
 
 	drm_atomic_helper_wait_for_vblanks(drm, state);
 
@@ -93,7 +93,7 @@ static int tegra_atomic_commit(struct drm_device *drm,
 	 * the software side now.
 	 */
 
-	drm_atomic_helper_swap_state(drm, state);
+	drm_atomic_helper_swap_state(state, true);
 
 	if (nonblock)
 		tegra_atomic_schedule(tegra, state);
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h
index f52d6cb24ff5..0ddcce1b420d 100644
--- a/drivers/gpu/drm/tegra/drm.h
+++ b/drivers/gpu/drm/tegra/drm.h
@@ -239,8 +239,6 @@ int tegra_output_init(struct drm_device *drm, struct tegra_output *output);
 void tegra_output_exit(struct tegra_output *output);
 
 int tegra_output_connector_get_modes(struct drm_connector *connector);
-struct drm_encoder *
-tegra_output_connector_best_encoder(struct drm_connector *connector);
 enum drm_connector_status
 tegra_output_connector_detect(struct drm_connector *connector, bool force);
 void tegra_output_connector_destroy(struct drm_connector *connector);
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index d1239ebc190f..3d228ad90e0f 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -13,6 +13,7 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
 #include <linux/regulator/consumer.h>
@@ -677,6 +678,45 @@ static void tegra_dsi_ganged_disable(struct tegra_dsi *dsi)
 	tegra_dsi_writel(dsi, 0, DSI_GANGED_MODE_CONTROL);
 }
 
+static int tegra_dsi_pad_enable(struct tegra_dsi *dsi)
+{
+	u32 value;
+
+	value = DSI_PAD_CONTROL_VS1_PULLDN(0) | DSI_PAD_CONTROL_VS1_PDIO(0);
+	tegra_dsi_writel(dsi, value, DSI_PAD_CONTROL_0);
+
+	return 0;
+}
+
+static int tegra_dsi_pad_calibrate(struct tegra_dsi *dsi)
+{
+	u32 value;
+
+	/*
+	 * XXX Is this still needed? The module reset is deasserted right
+	 * before this function is called.
+	 */
+	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_0);
+	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_1);
+	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_2);
+	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_3);
+	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_4);
+
+	/* start calibration */
+	tegra_dsi_pad_enable(dsi);
+
+	value = DSI_PAD_SLEW_UP(0x7) | DSI_PAD_SLEW_DN(0x7) |
+		DSI_PAD_LP_UP(0x1) | DSI_PAD_LP_DN(0x1) |
+		DSI_PAD_OUT_CLK(0x0);
+	tegra_dsi_writel(dsi, value, DSI_PAD_CONTROL_2);
+
+	value = DSI_PAD_PREEMP_PD_CLK(0x3) | DSI_PAD_PREEMP_PU_CLK(0x3) |
+		DSI_PAD_PREEMP_PD(0x03) | DSI_PAD_PREEMP_PU(0x3);
+	tegra_dsi_writel(dsi, value, DSI_PAD_CONTROL_3);
+
+	return tegra_mipi_calibrate(dsi->mipi);
+}
+
 static void tegra_dsi_set_timeout(struct tegra_dsi *dsi, unsigned long bclk,
 				  unsigned int vrefresh)
 {
@@ -794,7 +834,6 @@ tegra_dsi_connector_mode_valid(struct drm_connector *connector,
 static const struct drm_connector_helper_funcs tegra_dsi_connector_helper_funcs = {
 	.get_modes = tegra_output_connector_get_modes,
 	.mode_valid = tegra_dsi_connector_mode_valid,
-	.best_encoder = tegra_output_connector_best_encoder,
 };
 
 static const struct drm_encoder_funcs tegra_dsi_encoder_funcs = {
@@ -837,7 +876,7 @@ static void tegra_dsi_encoder_disable(struct drm_encoder *encoder)
 
 	tegra_dsi_disable(dsi);
 
-	return;
+	pm_runtime_put(dsi->dev);
 }
 
 static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
@@ -848,6 +887,13 @@ static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
 	struct tegra_dsi *dsi = to_dsi(output);
 	struct tegra_dsi_state *state;
 	u32 value;
+	int err;
+
+	pm_runtime_get_sync(dsi->dev);
+
+	err = tegra_dsi_pad_calibrate(dsi);
+	if (err < 0)
+		dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
 
 	state = tegra_dsi_get_state(dsi);
 
@@ -876,8 +922,6 @@ static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
 
 	if (output->panel)
 		drm_panel_enable(output->panel);
-
-	return;
 }
 
 static int
@@ -967,55 +1011,12 @@ static const struct drm_encoder_helper_funcs tegra_dsi_encoder_helper_funcs = {
 	.atomic_check = tegra_dsi_encoder_atomic_check,
 };
 
-static int tegra_dsi_pad_enable(struct tegra_dsi *dsi)
-{
-	u32 value;
-
-	value = DSI_PAD_CONTROL_VS1_PULLDN(0) | DSI_PAD_CONTROL_VS1_PDIO(0);
-	tegra_dsi_writel(dsi, value, DSI_PAD_CONTROL_0);
-
-	return 0;
-}
-
-static int tegra_dsi_pad_calibrate(struct tegra_dsi *dsi)
-{
-	u32 value;
-
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_0);
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_1);
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_2);
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_3);
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_4);
-
-	/* start calibration */
-	tegra_dsi_pad_enable(dsi);
-
-	value = DSI_PAD_SLEW_UP(0x7) | DSI_PAD_SLEW_DN(0x7) |
-		DSI_PAD_LP_UP(0x1) | DSI_PAD_LP_DN(0x1) |
-		DSI_PAD_OUT_CLK(0x0);
-	tegra_dsi_writel(dsi, value, DSI_PAD_CONTROL_2);
-
-	value = DSI_PAD_PREEMP_PD_CLK(0x3) | DSI_PAD_PREEMP_PU_CLK(0x3) |
-		DSI_PAD_PREEMP_PD(0x03) | DSI_PAD_PREEMP_PU(0x3);
-	tegra_dsi_writel(dsi, value, DSI_PAD_CONTROL_3);
-
-	return tegra_mipi_calibrate(dsi->mipi);
-}
-
 static int tegra_dsi_init(struct host1x_client *client)
 {
 	struct drm_device *drm = dev_get_drvdata(client->parent);
 	struct tegra_dsi *dsi = host1x_client_to_dsi(client);
 	int err;
 
-	reset_control_deassert(dsi->rst);
-
-	err = tegra_dsi_pad_calibrate(dsi);
-	if (err < 0) {
-		dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
-		goto reset;
-	}
-
 	/* Gangsters must not register their own outputs. */
 	if (!dsi->master) {
 		dsi->output.dev = client->dev;
@@ -1038,12 +1039,9 @@ static int tegra_dsi_init(struct host1x_client *client)
 		drm_connector_register(&dsi->output.connector);
 
 		err = tegra_output_init(drm, &dsi->output);
-		if (err < 0) {
-			dev_err(client->dev,
-				"failed to initialize output: %d\n",
+		if (err < 0)
+			dev_err(dsi->dev, "failed to initialize output: %d\n",
 				err);
-			goto reset;
-		}
 
 		dsi->output.encoder.possible_crtcs = 0x3;
 	}
@@ -1055,10 +1053,6 @@ static int tegra_dsi_init(struct host1x_client *client)
 	}
 
 	return 0;
-
-reset:
-	reset_control_assert(dsi->rst);
-	return err;
 }
 
 static int tegra_dsi_exit(struct host1x_client *client)
@@ -1070,7 +1064,7 @@ static int tegra_dsi_exit(struct host1x_client *client)
 	if (IS_ENABLED(CONFIG_DEBUG_FS))
 		tegra_dsi_debugfs_exit(dsi);
 
-	reset_control_assert(dsi->rst);
+	regulator_disable(dsi->vdd);
 
 	return 0;
 }
@@ -1494,74 +1488,50 @@ static int tegra_dsi_probe(struct platform_device *pdev)
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->lanes = 4;
 
-	dsi->rst = devm_reset_control_get(&pdev->dev, "dsi");
-	if (IS_ERR(dsi->rst))
-		return PTR_ERR(dsi->rst);
+	if (!pdev->dev.pm_domain) {
+		dsi->rst = devm_reset_control_get(&pdev->dev, "dsi");
+		if (IS_ERR(dsi->rst))
+			return PTR_ERR(dsi->rst);
+	}
 
 	dsi->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(dsi->clk)) {
 		dev_err(&pdev->dev, "cannot get DSI clock\n");
-		err = PTR_ERR(dsi->clk);
-		goto reset;
-	}
-
-	err = clk_prepare_enable(dsi->clk);
-	if (err < 0) {
-		dev_err(&pdev->dev, "cannot enable DSI clock\n");
-		goto reset;
+		return PTR_ERR(dsi->clk);
 	}
 
 	dsi->clk_lp = devm_clk_get(&pdev->dev, "lp");
 	if (IS_ERR(dsi->clk_lp)) {
 		dev_err(&pdev->dev, "cannot get low-power clock\n");
-		err = PTR_ERR(dsi->clk_lp);
-		goto disable_clk;
-	}
-
-	err = clk_prepare_enable(dsi->clk_lp);
-	if (err < 0) {
-		dev_err(&pdev->dev, "cannot enable low-power clock\n");
-		goto disable_clk;
+		return PTR_ERR(dsi->clk_lp);
 	}
 
 	dsi->clk_parent = devm_clk_get(&pdev->dev, "parent");
 	if (IS_ERR(dsi->clk_parent)) {
 		dev_err(&pdev->dev, "cannot get parent clock\n");
-		err = PTR_ERR(dsi->clk_parent);
-		goto disable_clk_lp;
+		return PTR_ERR(dsi->clk_parent);
 	}
 
 	dsi->vdd = devm_regulator_get(&pdev->dev, "avdd-dsi-csi");
 	if (IS_ERR(dsi->vdd)) {
 		dev_err(&pdev->dev, "cannot get VDD supply\n");
-		err = PTR_ERR(dsi->vdd);
-		goto disable_clk_lp;
-	}
-
-	err = regulator_enable(dsi->vdd);
-	if (err < 0) {
-		dev_err(&pdev->dev, "cannot enable VDD supply\n");
-		goto disable_clk_lp;
+		return PTR_ERR(dsi->vdd);
 	}
 
 	err = tegra_dsi_setup_clocks(dsi);
 	if (err < 0) {
 		dev_err(&pdev->dev, "cannot setup clocks\n");
-		goto disable_vdd;
+		return err;
 	}
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	dsi->regs = devm_ioremap_resource(&pdev->dev, regs);
-	if (IS_ERR(dsi->regs)) {
-		err = PTR_ERR(dsi->regs);
-		goto disable_vdd;
-	}
+	if (IS_ERR(dsi->regs))
+		return PTR_ERR(dsi->regs);
 
 	dsi->mipi = tegra_mipi_request(&pdev->dev);
-	if (IS_ERR(dsi->mipi)) {
-		err = PTR_ERR(dsi->mipi);
-		goto disable_vdd;
-	}
+	if (IS_ERR(dsi->mipi))
+		return PTR_ERR(dsi->mipi);
 
 	dsi->host.ops = &tegra_dsi_host_ops;
 	dsi->host.dev = &pdev->dev;
@@ -1572,6 +1542,9 @@ static int tegra_dsi_probe(struct platform_device *pdev)
 		goto mipi_free;
 	}
 
+	platform_set_drvdata(pdev, dsi);
+	pm_runtime_enable(&pdev->dev);
+
 	INIT_LIST_HEAD(&dsi->client.list);
 	dsi->client.ops = &dsi_client_ops;
 	dsi->client.dev = &pdev->dev;
@@ -1583,22 +1556,12 @@ static int tegra_dsi_probe(struct platform_device *pdev)
 		goto unregister;
 	}
 
-	platform_set_drvdata(pdev, dsi);
-
 	return 0;
 
 unregister:
 	mipi_dsi_host_unregister(&dsi->host);
 mipi_free:
 	tegra_mipi_free(dsi->mipi);
-disable_vdd:
-	regulator_disable(dsi->vdd);
-disable_clk_lp:
-	clk_disable_unprepare(dsi->clk_lp);
-disable_clk:
-	clk_disable_unprepare(dsi->clk);
-reset:
-	reset_control_assert(dsi->rst);
 	return err;
 }
 
@@ -1607,6 +1570,8 @@ static int tegra_dsi_remove(struct platform_device *pdev)
 	struct tegra_dsi *dsi = platform_get_drvdata(pdev);
 	int err;
 
+	pm_runtime_disable(&pdev->dev);
+
 	err = host1x_client_unregister(&dsi->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
@@ -1619,14 +1584,82 @@ static int tegra_dsi_remove(struct platform_device *pdev)
 	mipi_dsi_host_unregister(&dsi->host);
 	tegra_mipi_free(dsi->mipi);
 
-	regulator_disable(dsi->vdd);
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int tegra_dsi_suspend(struct device *dev)
+{
+	struct tegra_dsi *dsi = dev_get_drvdata(dev);
+	int err;
+
+	if (dsi->rst) {
+		err = reset_control_assert(dsi->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to assert reset: %d\n", err);
+			return err;
+		}
+	}
+
+	usleep_range(1000, 2000);
+
 	clk_disable_unprepare(dsi->clk_lp);
 	clk_disable_unprepare(dsi->clk);
-	reset_control_assert(dsi->rst);
+
+	regulator_disable(dsi->vdd);
 
 	return 0;
 }
 
+static int tegra_dsi_resume(struct device *dev)
+{
+	struct tegra_dsi *dsi = dev_get_drvdata(dev);
+	int err;
+
+	err = regulator_enable(dsi->vdd);
+	if (err < 0) {
+		dev_err(dsi->dev, "failed to enable VDD supply: %d\n", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(dsi->clk);
+	if (err < 0) {
+		dev_err(dev, "cannot enable DSI clock: %d\n", err);
+		goto disable_vdd;
+	}
+
+	err = clk_prepare_enable(dsi->clk_lp);
+	if (err < 0) {
+		dev_err(dev, "cannot enable low-power clock: %d\n", err);
+		goto disable_clk;
+	}
+
+	usleep_range(1000, 2000);
+
+	if (dsi->rst) {
+		err = reset_control_deassert(dsi->rst);
+		if (err < 0) {
+			dev_err(dev, "cannot assert reset: %d\n", err);
+			goto disable_clk_lp;
+		}
+	}
+
+	return 0;
+
+disable_clk_lp:
+	clk_disable_unprepare(dsi->clk_lp);
+disable_clk:
+	clk_disable_unprepare(dsi->clk);
+disable_vdd:
+	regulator_disable(dsi->vdd);
+	return err;
+}
+#endif
+
+static const struct dev_pm_ops tegra_dsi_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_dsi_suspend, tegra_dsi_resume, NULL)
+};
+
 static const struct of_device_id tegra_dsi_of_match[] = {
 	{ .compatible = "nvidia,tegra210-dsi", },
 	{ .compatible = "nvidia,tegra132-dsi", },
@@ -1640,6 +1673,7 @@ struct platform_driver tegra_dsi_driver = {
 	.driver = {
 		.name = "tegra-dsi",
 		.of_match_table = tegra_dsi_of_match,
+		.pm = &tegra_dsi_pm_ops,
 	},
 	.probe = tegra_dsi_probe,
 	.remove = tegra_dsi_remove,
diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c
index 1b12aa7a715e..e6d71fa4028e 100644
--- a/drivers/gpu/drm/tegra/fb.c
+++ b/drivers/gpu/drm/tegra/fb.c
@@ -68,7 +68,7 @@ static void tegra_fb_destroy(struct drm_framebuffer *framebuffer)
 		struct tegra_bo *bo = fb->planes[i];
 
 		if (bo) {
-			if (bo->pages && bo->vaddr)
+			if (bo->pages)
 				vunmap(bo->vaddr);
 
 			drm_gem_object_unreference_unlocked(&bo->gem);
diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c
index b7ef4929e347..cda0491ed6bf 100644
--- a/drivers/gpu/drm/tegra/hdmi.c
+++ b/drivers/gpu/drm/tegra/hdmi.c
@@ -11,6 +11,7 @@
 #include <linux/debugfs.h>
 #include <linux/gpio.h>
 #include <linux/hdmi.h>
+#include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 
@@ -18,10 +19,14 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
 
+#include <sound/hda_verbs.h>
+
 #include "hdmi.h"
 #include "drm.h"
 #include "dc.h"
 
+#define HDMI_ELD_BUFFER_SIZE 96
+
 struct tmds_config {
 	unsigned int pclk;
 	u32 pll0;
@@ -39,6 +44,8 @@ struct tegra_hdmi_config {
 	u32 fuse_override_value;
 
 	bool has_sor_io_peak_current;
+	bool has_hda;
+	bool has_hbr;
 };
 
 struct tegra_hdmi {
@@ -60,7 +67,10 @@ struct tegra_hdmi {
 	const struct tegra_hdmi_config *config;
 
 	unsigned int audio_source;
-	unsigned int audio_freq;
+	unsigned int audio_sample_rate;
+	unsigned int audio_channels;
+
+	unsigned int pixel_clock;
 	bool stereo;
 	bool dvi;
 
@@ -402,11 +412,11 @@ static const struct tmds_config tegra124_tmds_config[] = {
 };
 
 static const struct tegra_hdmi_audio_config *
-tegra_hdmi_get_audio_config(unsigned int audio_freq, unsigned int pclk)
+tegra_hdmi_get_audio_config(unsigned int sample_rate, unsigned int pclk)
 {
 	const struct tegra_hdmi_audio_config *table;
 
-	switch (audio_freq) {
+	switch (sample_rate) {
 	case 32000:
 		table = tegra_hdmi_audio_32k;
 		break;
@@ -476,44 +486,114 @@ static void tegra_hdmi_setup_audio_fs_tables(struct tegra_hdmi *hdmi)
 	}
 }
 
-static int tegra_hdmi_setup_audio(struct tegra_hdmi *hdmi, unsigned int pclk)
+static void tegra_hdmi_write_aval(struct tegra_hdmi *hdmi, u32 value)
+{
+	static const struct {
+		unsigned int sample_rate;
+		unsigned int offset;
+	} regs[] = {
+		{  32000, HDMI_NV_PDISP_SOR_AUDIO_AVAL_0320 },
+		{  44100, HDMI_NV_PDISP_SOR_AUDIO_AVAL_0441 },
+		{  48000, HDMI_NV_PDISP_SOR_AUDIO_AVAL_0480 },
+		{  88200, HDMI_NV_PDISP_SOR_AUDIO_AVAL_0882 },
+		{  96000, HDMI_NV_PDISP_SOR_AUDIO_AVAL_0960 },
+		{ 176400, HDMI_NV_PDISP_SOR_AUDIO_AVAL_1764 },
+		{ 192000, HDMI_NV_PDISP_SOR_AUDIO_AVAL_1920 },
+	};
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(regs); i++) {
+		if (regs[i].sample_rate == hdmi->audio_sample_rate) {
+			tegra_hdmi_writel(hdmi, value, regs[i].offset);
+			break;
+		}
+	}
+}
+
+static int tegra_hdmi_setup_audio(struct tegra_hdmi *hdmi)
 {
-	struct device_node *node = hdmi->dev->of_node;
 	const struct tegra_hdmi_audio_config *config;
-	unsigned int offset = 0;
-	u32 value;
+	u32 source, value;
 
 	switch (hdmi->audio_source) {
 	case HDA:
-		value = AUDIO_CNTRL0_SOURCE_SELECT_HDAL;
+		if (hdmi->config->has_hda)
+			source = SOR_AUDIO_CNTRL0_SOURCE_SELECT_HDAL;
+		else
+			return -EINVAL;
+
 		break;
 
 	case SPDIF:
-		value = AUDIO_CNTRL0_SOURCE_SELECT_SPDIF;
+		if (hdmi->config->has_hda)
+			source = SOR_AUDIO_CNTRL0_SOURCE_SELECT_SPDIF;
+		else
+			source = AUDIO_CNTRL0_SOURCE_SELECT_SPDIF;
 		break;
 
 	default:
-		value = AUDIO_CNTRL0_SOURCE_SELECT_AUTO;
+		if (hdmi->config->has_hda)
+			source = SOR_AUDIO_CNTRL0_SOURCE_SELECT_AUTO;
+		else
+			source = AUDIO_CNTRL0_SOURCE_SELECT_AUTO;
 		break;
 	}
 
-	if (of_device_is_compatible(node, "nvidia,tegra30-hdmi")) {
-		value |= AUDIO_CNTRL0_ERROR_TOLERANCE(6) |
-			 AUDIO_CNTRL0_FRAMES_PER_BLOCK(0xc0);
-		tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_AUDIO_CNTRL0);
-	} else {
-		value |= AUDIO_CNTRL0_INJECT_NULLSMPL;
+	/*
+	 * Tegra30 and later use a slightly modified version of the register
+	 * layout to accomodate for changes related to supporting HDA as the
+	 * audio input source for HDMI. The source select field has moved to
+	 * the SOR_AUDIO_CNTRL0 register, but the error tolerance and frames
+	 * per block fields remain in the AUDIO_CNTRL0 register.
+	 */
+	if (hdmi->config->has_hda) {
+		/*
+		 * Inject null samples into the audio FIFO for every frame in
+		 * which the codec did not receive any samples. This applies
+		 * to stereo LPCM only.
+		 *
+		 * XXX: This seems to be a remnant of MCP days when this was
+		 * used to work around issues with monitors not being able to
+		 * play back system startup sounds early. It is possibly not
+		 * needed on Linux at all.
+		 */
+		if (hdmi->audio_channels == 2)
+			value = SOR_AUDIO_CNTRL0_INJECT_NULLSMPL;
+		else
+			value = 0;
+
+		value |= source;
+
 		tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_SOR_AUDIO_CNTRL0);
+	}
 
-		value = AUDIO_CNTRL0_ERROR_TOLERANCE(6) |
-			AUDIO_CNTRL0_FRAMES_PER_BLOCK(0xc0);
-		tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_AUDIO_CNTRL0);
+	/*
+	 * On Tegra20, HDA is not a supported audio source and the source
+	 * select field is part of the AUDIO_CNTRL0 register.
+	 */
+	value = AUDIO_CNTRL0_FRAMES_PER_BLOCK(0xc0) |
+		AUDIO_CNTRL0_ERROR_TOLERANCE(6);
+
+	if (!hdmi->config->has_hda)
+		value |= source;
+
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_AUDIO_CNTRL0);
+
+	/*
+	 * Advertise support for High Bit-Rate on Tegra114 and later.
+	 */
+	if (hdmi->config->has_hbr) {
+		value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_SOR_AUDIO_SPARE0);
+		value |= SOR_AUDIO_SPARE0_HBR_ENABLE;
+		tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_SOR_AUDIO_SPARE0);
 	}
 
-	config = tegra_hdmi_get_audio_config(hdmi->audio_freq, pclk);
+	config = tegra_hdmi_get_audio_config(hdmi->audio_sample_rate,
+					     hdmi->pixel_clock);
 	if (!config) {
-		dev_err(hdmi->dev, "cannot set audio to %u at %u pclk\n",
-			hdmi->audio_freq, pclk);
+		dev_err(hdmi->dev,
+			"cannot set audio to %u Hz at %u Hz pixel clock\n",
+			hdmi->audio_sample_rate, hdmi->pixel_clock);
 		return -EINVAL;
 	}
 
@@ -526,8 +606,8 @@ static int tegra_hdmi_setup_audio(struct tegra_hdmi *hdmi, unsigned int pclk)
 	tegra_hdmi_writel(hdmi, ACR_SUBPACK_N(config->n) | ACR_ENABLE,
 			  HDMI_NV_PDISP_HDMI_ACR_0441_SUBPACK_HIGH);
 
-	value = ACR_SUBPACK_CTS(config->cts);
-	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_ACR_0441_SUBPACK_LOW);
+	tegra_hdmi_writel(hdmi, ACR_SUBPACK_CTS(config->cts),
+			  HDMI_NV_PDISP_HDMI_ACR_0441_SUBPACK_LOW);
 
 	value = SPARE_HW_CTS | SPARE_FORCE_SW_CTS | SPARE_CTS_RESET_VAL(1);
 	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_SPARE);
@@ -536,43 +616,53 @@ static int tegra_hdmi_setup_audio(struct tegra_hdmi *hdmi, unsigned int pclk)
 	value &= ~AUDIO_N_RESETF;
 	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_AUDIO_N);
 
-	if (of_device_is_compatible(node, "nvidia,tegra30-hdmi")) {
-		switch (hdmi->audio_freq) {
-		case 32000:
-			offset = HDMI_NV_PDISP_SOR_AUDIO_AVAL_0320;
-			break;
+	if (hdmi->config->has_hda)
+		tegra_hdmi_write_aval(hdmi, config->aval);
 
-		case 44100:
-			offset = HDMI_NV_PDISP_SOR_AUDIO_AVAL_0441;
-			break;
+	tegra_hdmi_setup_audio_fs_tables(hdmi);
 
-		case 48000:
-			offset = HDMI_NV_PDISP_SOR_AUDIO_AVAL_0480;
-			break;
+	return 0;
+}
 
-		case 88200:
-			offset = HDMI_NV_PDISP_SOR_AUDIO_AVAL_0882;
-			break;
+static void tegra_hdmi_disable_audio(struct tegra_hdmi *hdmi)
+{
+	u32 value;
 
-		case 96000:
-			offset = HDMI_NV_PDISP_SOR_AUDIO_AVAL_0960;
-			break;
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
+	value &= ~GENERIC_CTRL_AUDIO;
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
+}
 
-		case 176400:
-			offset = HDMI_NV_PDISP_SOR_AUDIO_AVAL_1764;
-			break;
+static void tegra_hdmi_enable_audio(struct tegra_hdmi *hdmi)
+{
+	u32 value;
 
-		case 192000:
-			offset = HDMI_NV_PDISP_SOR_AUDIO_AVAL_1920;
-			break;
-		}
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
+	value |= GENERIC_CTRL_AUDIO;
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
+}
 
-		tegra_hdmi_writel(hdmi, config->aval, offset);
-	}
+static void tegra_hdmi_write_eld(struct tegra_hdmi *hdmi)
+{
+	size_t length = drm_eld_size(hdmi->output.connector.eld), i;
+	u32 value;
 
-	tegra_hdmi_setup_audio_fs_tables(hdmi);
+	for (i = 0; i < length; i++)
+		tegra_hdmi_writel(hdmi, i << 8 | hdmi->output.connector.eld[i],
+				  HDMI_NV_PDISP_SOR_AUDIO_HDA_ELD_BUFWR);
 
-	return 0;
+	/*
+	 * The HDA codec will always report an ELD buffer size of 96 bytes and
+	 * the HDA codec driver will check that each byte read from the buffer
+	 * is valid. Therefore every byte must be written, even if no 96 bytes
+	 * were parsed from EDID.
+	 */
+	for (i = length; i < HDMI_ELD_BUFFER_SIZE; i++)
+		tegra_hdmi_writel(hdmi, i << 8 | 0,
+				  HDMI_NV_PDISP_SOR_AUDIO_HDA_ELD_BUFWR);
+
+	value = SOR_AUDIO_HDA_PRESENSE_VALID | SOR_AUDIO_HDA_PRESENSE_PRESENT;
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_SOR_AUDIO_HDA_PRESENSE);
 }
 
 static inline u32 tegra_hdmi_subpack(const u8 *ptr, size_t size)
@@ -644,12 +734,6 @@ static void tegra_hdmi_setup_avi_infoframe(struct tegra_hdmi *hdmi,
 	u8 buffer[17];
 	ssize_t err;
 
-	if (hdmi->dvi) {
-		tegra_hdmi_writel(hdmi, 0,
-				  HDMI_NV_PDISP_HDMI_AVI_INFOFRAME_CTRL);
-		return;
-	}
-
 	err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
 	if (err < 0) {
 		dev_err(hdmi->dev, "failed to setup AVI infoframe: %zd\n", err);
@@ -663,9 +747,24 @@ static void tegra_hdmi_setup_avi_infoframe(struct tegra_hdmi *hdmi,
 	}
 
 	tegra_hdmi_write_infopack(hdmi, buffer, err);
+}
+
+static void tegra_hdmi_disable_avi_infoframe(struct tegra_hdmi *hdmi)
+{
+	u32 value;
 
-	tegra_hdmi_writel(hdmi, INFOFRAME_CTRL_ENABLE,
-			  HDMI_NV_PDISP_HDMI_AVI_INFOFRAME_CTRL);
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_HDMI_AVI_INFOFRAME_CTRL);
+	value &= ~INFOFRAME_CTRL_ENABLE;
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_AVI_INFOFRAME_CTRL);
+}
+
+static void tegra_hdmi_enable_avi_infoframe(struct tegra_hdmi *hdmi)
+{
+	u32 value;
+
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_HDMI_AVI_INFOFRAME_CTRL);
+	value |= INFOFRAME_CTRL_ENABLE;
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_AVI_INFOFRAME_CTRL);
 }
 
 static void tegra_hdmi_setup_audio_infoframe(struct tegra_hdmi *hdmi)
@@ -674,12 +773,6 @@ static void tegra_hdmi_setup_audio_infoframe(struct tegra_hdmi *hdmi)
 	u8 buffer[14];
 	ssize_t err;
 
-	if (hdmi->dvi) {
-		tegra_hdmi_writel(hdmi, 0,
-				  HDMI_NV_PDISP_HDMI_AUDIO_INFOFRAME_CTRL);
-		return;
-	}
-
 	err = hdmi_audio_infoframe_init(&frame);
 	if (err < 0) {
 		dev_err(hdmi->dev, "failed to setup audio infoframe: %zd\n",
@@ -687,7 +780,7 @@ static void tegra_hdmi_setup_audio_infoframe(struct tegra_hdmi *hdmi)
 		return;
 	}
 
-	frame.channels = 2;
+	frame.channels = hdmi->audio_channels;
 
 	err = hdmi_audio_infoframe_pack(&frame, buffer, sizeof(buffer));
 	if (err < 0) {
@@ -703,9 +796,24 @@ static void tegra_hdmi_setup_audio_infoframe(struct tegra_hdmi *hdmi)
 	 * bytes can be programmed.
 	 */
 	tegra_hdmi_write_infopack(hdmi, buffer, min_t(size_t, 10, err));
+}
 
-	tegra_hdmi_writel(hdmi, INFOFRAME_CTRL_ENABLE,
-			  HDMI_NV_PDISP_HDMI_AUDIO_INFOFRAME_CTRL);
+static void tegra_hdmi_disable_audio_infoframe(struct tegra_hdmi *hdmi)
+{
+	u32 value;
+
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_HDMI_AUDIO_INFOFRAME_CTRL);
+	value &= ~INFOFRAME_CTRL_ENABLE;
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_AUDIO_INFOFRAME_CTRL);
+}
+
+static void tegra_hdmi_enable_audio_infoframe(struct tegra_hdmi *hdmi)
+{
+	u32 value;
+
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_HDMI_AUDIO_INFOFRAME_CTRL);
+	value |= INFOFRAME_CTRL_ENABLE;
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_AUDIO_INFOFRAME_CTRL);
 }
 
 static void tegra_hdmi_setup_stereo_infoframe(struct tegra_hdmi *hdmi)
@@ -713,14 +821,6 @@ static void tegra_hdmi_setup_stereo_infoframe(struct tegra_hdmi *hdmi)
 	struct hdmi_vendor_infoframe frame;
 	u8 buffer[10];
 	ssize_t err;
-	u32 value;
-
-	if (!hdmi->stereo) {
-		value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
-		value &= ~GENERIC_CTRL_ENABLE;
-		tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
-		return;
-	}
 
 	hdmi_vendor_infoframe_init(&frame);
 	frame.s3d_struct = HDMI_3D_STRUCTURE_FRAME_PACKING;
@@ -733,6 +833,20 @@ static void tegra_hdmi_setup_stereo_infoframe(struct tegra_hdmi *hdmi)
 	}
 
 	tegra_hdmi_write_infopack(hdmi, buffer, err);
+}
+
+static void tegra_hdmi_disable_stereo_infoframe(struct tegra_hdmi *hdmi)
+{
+	u32 value;
+
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
+	value &= ~GENERIC_CTRL_ENABLE;
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
+}
+
+static void tegra_hdmi_enable_stereo_infoframe(struct tegra_hdmi *hdmi)
+{
+	u32 value;
 
 	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
 	value |= GENERIC_CTRL_ENABLE;
@@ -772,10 +886,25 @@ static bool tegra_output_is_hdmi(struct tegra_output *output)
 	return drm_detect_hdmi_monitor(edid);
 }
 
+static enum drm_connector_status
+tegra_hdmi_connector_detect(struct drm_connector *connector, bool force)
+{
+	struct tegra_output *output = connector_to_output(connector);
+	struct tegra_hdmi *hdmi = to_hdmi(output);
+	enum drm_connector_status status;
+
+	status = tegra_output_connector_detect(connector, force);
+	if (status == connector_status_connected)
+		return status;
+
+	tegra_hdmi_writel(hdmi, 0, HDMI_NV_PDISP_SOR_AUDIO_HDA_PRESENSE);
+	return status;
+}
+
 static const struct drm_connector_funcs tegra_hdmi_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.reset = drm_atomic_helper_connector_reset,
-	.detect = tegra_output_connector_detect,
+	.detect = tegra_hdmi_connector_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.destroy = tegra_output_connector_destroy,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
@@ -806,7 +935,6 @@ static const struct drm_connector_helper_funcs
 tegra_hdmi_connector_helper_funcs = {
 	.get_modes = tegra_output_connector_get_modes,
 	.mode_valid = tegra_hdmi_connector_mode_valid,
-	.best_encoder = tegra_output_connector_best_encoder,
 };
 
 static const struct drm_encoder_funcs tegra_hdmi_encoder_funcs = {
@@ -815,7 +943,9 @@ static const struct drm_encoder_funcs tegra_hdmi_encoder_funcs = {
 
 static void tegra_hdmi_encoder_disable(struct drm_encoder *encoder)
 {
+	struct tegra_output *output = encoder_to_output(encoder);
 	struct tegra_dc *dc = to_tegra_dc(encoder->crtc);
+	struct tegra_hdmi *hdmi = to_hdmi(output);
 	u32 value;
 
 	/*
@@ -829,6 +959,20 @@ static void tegra_hdmi_encoder_disable(struct drm_encoder *encoder)
 
 		tegra_dc_commit(dc);
 	}
+
+	if (!hdmi->dvi) {
+		if (hdmi->stereo)
+			tegra_hdmi_disable_stereo_infoframe(hdmi);
+
+		tegra_hdmi_disable_audio_infoframe(hdmi);
+		tegra_hdmi_disable_avi_infoframe(hdmi);
+		tegra_hdmi_disable_audio(hdmi);
+	}
+
+	tegra_hdmi_writel(hdmi, 0, HDMI_NV_PDISP_INT_ENABLE);
+	tegra_hdmi_writel(hdmi, 0, HDMI_NV_PDISP_INT_MASK);
+
+	pm_runtime_put(hdmi->dev);
 }
 
 static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder)
@@ -837,21 +981,28 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder)
 	unsigned int h_sync_width, h_front_porch, h_back_porch, i, rekey;
 	struct tegra_output *output = encoder_to_output(encoder);
 	struct tegra_dc *dc = to_tegra_dc(encoder->crtc);
-	struct device_node *node = output->dev->of_node;
 	struct tegra_hdmi *hdmi = to_hdmi(output);
-	unsigned int pulse_start, div82, pclk;
+	unsigned int pulse_start, div82;
 	int retries = 1000;
 	u32 value;
 	int err;
 
-	hdmi->dvi = !tegra_output_is_hdmi(output);
+	pm_runtime_get_sync(hdmi->dev);
 
-	pclk = mode->clock * 1000;
+	/*
+	 * Enable and unmask the HDA codec SCRATCH0 register interrupt. This
+	 * is used for interoperability between the HDA codec driver and the
+	 * HDMI driver.
+	 */
+	tegra_hdmi_writel(hdmi, INT_CODEC_SCRATCH0, HDMI_NV_PDISP_INT_ENABLE);
+	tegra_hdmi_writel(hdmi, INT_CODEC_SCRATCH0, HDMI_NV_PDISP_INT_MASK);
+
+	hdmi->pixel_clock = mode->clock * 1000;
 	h_sync_width = mode->hsync_end - mode->hsync_start;
 	h_back_porch = mode->htotal - mode->hsync_end;
 	h_front_porch = mode->hsync_start - mode->hdisplay;
 
-	err = clk_set_rate(hdmi->clk, pclk);
+	err = clk_set_rate(hdmi->clk, hdmi->pixel_clock);
 	if (err < 0) {
 		dev_err(hdmi->dev, "failed to set HDMI clock frequency: %d\n",
 			err);
@@ -910,17 +1061,15 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder)
 	value = SOR_REFCLK_DIV_INT(div82 >> 2) | SOR_REFCLK_DIV_FRAC(div82);
 	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_SOR_REFCLK);
 
+	hdmi->dvi = !tegra_output_is_hdmi(output);
 	if (!hdmi->dvi) {
-		err = tegra_hdmi_setup_audio(hdmi, pclk);
+		err = tegra_hdmi_setup_audio(hdmi);
 		if (err < 0)
 			hdmi->dvi = true;
 	}
 
-	if (of_device_is_compatible(node, "nvidia,tegra20-hdmi")) {
-		/*
-		 * TODO: add ELD support
-		 */
-	}
+	if (hdmi->config->has_hda)
+		tegra_hdmi_write_eld(hdmi);
 
 	rekey = HDMI_REKEY_DEFAULT;
 	value = HDMI_CTRL_REKEY(rekey);
@@ -932,20 +1081,17 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder)
 
 	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_HDMI_CTRL);
 
-	if (hdmi->dvi)
-		tegra_hdmi_writel(hdmi, 0x0,
-				  HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
-	else
-		tegra_hdmi_writel(hdmi, GENERIC_CTRL_AUDIO,
-				  HDMI_NV_PDISP_HDMI_GENERIC_CTRL);
+	if (!hdmi->dvi) {
+		tegra_hdmi_setup_avi_infoframe(hdmi, mode);
+		tegra_hdmi_setup_audio_infoframe(hdmi);
 
-	tegra_hdmi_setup_avi_infoframe(hdmi, mode);
-	tegra_hdmi_setup_audio_infoframe(hdmi);
-	tegra_hdmi_setup_stereo_infoframe(hdmi);
+		if (hdmi->stereo)
+			tegra_hdmi_setup_stereo_infoframe(hdmi);
+	}
 
 	/* TMDS CONFIG */
 	for (i = 0; i < hdmi->config->num_tmds; i++) {
-		if (pclk <= hdmi->config->tmds[i].pclk) {
+		if (hdmi->pixel_clock <= hdmi->config->tmds[i].pclk) {
 			tegra_hdmi_setup_tmds(hdmi, &hdmi->config->tmds[i]);
 			break;
 		}
@@ -1032,6 +1178,15 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder)
 
 	tegra_dc_commit(dc);
 
+	if (!hdmi->dvi) {
+		tegra_hdmi_enable_avi_infoframe(hdmi);
+		tegra_hdmi_enable_audio_infoframe(hdmi);
+		tegra_hdmi_enable_audio(hdmi);
+
+		if (hdmi->stereo)
+			tegra_hdmi_enable_stereo_infoframe(hdmi);
+	}
+
 	/* TODO: add HDCP support */
 }
 
@@ -1236,8 +1391,14 @@ static int tegra_hdmi_show_regs(struct seq_file *s, void *data)
 	DUMP_REG(HDMI_NV_PDISP_KEY_HDCP_KEY_TRIG);
 	DUMP_REG(HDMI_NV_PDISP_KEY_SKEY_INDEX);
 	DUMP_REG(HDMI_NV_PDISP_SOR_AUDIO_CNTRL0);
+	DUMP_REG(HDMI_NV_PDISP_SOR_AUDIO_SPARE0);
+	DUMP_REG(HDMI_NV_PDISP_SOR_AUDIO_HDA_CODEC_SCRATCH0);
+	DUMP_REG(HDMI_NV_PDISP_SOR_AUDIO_HDA_CODEC_SCRATCH1);
 	DUMP_REG(HDMI_NV_PDISP_SOR_AUDIO_HDA_ELD_BUFWR);
 	DUMP_REG(HDMI_NV_PDISP_SOR_AUDIO_HDA_PRESENSE);
+	DUMP_REG(HDMI_NV_PDISP_INT_STATUS);
+	DUMP_REG(HDMI_NV_PDISP_INT_MASK);
+	DUMP_REG(HDMI_NV_PDISP_INT_ENABLE);
 	DUMP_REG(HDMI_NV_PDISP_SOR_IO_PEAK_CURRENT);
 
 #undef DUMP_REG
@@ -1361,14 +1522,6 @@ static int tegra_hdmi_init(struct host1x_client *client)
 		return err;
 	}
 
-	err = clk_prepare_enable(hdmi->clk);
-	if (err < 0) {
-		dev_err(hdmi->dev, "failed to enable clock: %d\n", err);
-		return err;
-	}
-
-	reset_control_deassert(hdmi->rst);
-
 	return 0;
 }
 
@@ -1378,9 +1531,6 @@ static int tegra_hdmi_exit(struct host1x_client *client)
 
 	tegra_output_exit(&hdmi->output);
 
-	reset_control_assert(hdmi->rst);
-	clk_disable_unprepare(hdmi->clk);
-
 	regulator_disable(hdmi->vdd);
 	regulator_disable(hdmi->pll);
 	regulator_disable(hdmi->hdmi);
@@ -1402,6 +1552,8 @@ static const struct tegra_hdmi_config tegra20_hdmi_config = {
 	.fuse_override_offset = HDMI_NV_PDISP_SOR_LANE_DRIVE_CURRENT,
 	.fuse_override_value = 1 << 31,
 	.has_sor_io_peak_current = false,
+	.has_hda = false,
+	.has_hbr = false,
 };
 
 static const struct tegra_hdmi_config tegra30_hdmi_config = {
@@ -1410,6 +1562,8 @@ static const struct tegra_hdmi_config tegra30_hdmi_config = {
 	.fuse_override_offset = HDMI_NV_PDISP_SOR_LANE_DRIVE_CURRENT,
 	.fuse_override_value = 1 << 31,
 	.has_sor_io_peak_current = false,
+	.has_hda = true,
+	.has_hbr = false,
 };
 
 static const struct tegra_hdmi_config tegra114_hdmi_config = {
@@ -1418,6 +1572,8 @@ static const struct tegra_hdmi_config tegra114_hdmi_config = {
 	.fuse_override_offset = HDMI_NV_PDISP_SOR_PAD_CTLS0,
 	.fuse_override_value = 1 << 31,
 	.has_sor_io_peak_current = true,
+	.has_hda = true,
+	.has_hbr = true,
 };
 
 static const struct tegra_hdmi_config tegra124_hdmi_config = {
@@ -1426,6 +1582,8 @@ static const struct tegra_hdmi_config tegra124_hdmi_config = {
 	.fuse_override_offset = HDMI_NV_PDISP_SOR_PAD_CTLS0,
 	.fuse_override_value = 1 << 31,
 	.has_sor_io_peak_current = true,
+	.has_hda = true,
+	.has_hbr = true,
 };
 
 static const struct of_device_id tegra_hdmi_of_match[] = {
@@ -1437,6 +1595,67 @@ static const struct of_device_id tegra_hdmi_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, tegra_hdmi_of_match);
 
+static void hda_format_parse(unsigned int format, unsigned int *rate,
+			     unsigned int *channels)
+{
+	unsigned int mul, div;
+
+	if (format & AC_FMT_BASE_44K)
+		*rate = 44100;
+	else
+		*rate = 48000;
+
+	mul = (format & AC_FMT_MULT_MASK) >> AC_FMT_MULT_SHIFT;
+	div = (format & AC_FMT_DIV_MASK) >> AC_FMT_DIV_SHIFT;
+
+	*rate = *rate * (mul + 1) / (div + 1);
+
+	*channels = (format & AC_FMT_CHAN_MASK) >> AC_FMT_CHAN_SHIFT;
+}
+
+static irqreturn_t tegra_hdmi_irq(int irq, void *data)
+{
+	struct tegra_hdmi *hdmi = data;
+	u32 value;
+	int err;
+
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_INT_STATUS);
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_INT_STATUS);
+
+	if (value & INT_CODEC_SCRATCH0) {
+		unsigned int format;
+		u32 value;
+
+		value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_SOR_AUDIO_HDA_CODEC_SCRATCH0);
+
+		if (value & SOR_AUDIO_HDA_CODEC_SCRATCH0_VALID) {
+			unsigned int sample_rate, channels;
+
+			format = value & SOR_AUDIO_HDA_CODEC_SCRATCH0_FMT_MASK;
+
+			hda_format_parse(format, &sample_rate, &channels);
+
+			hdmi->audio_sample_rate = sample_rate;
+			hdmi->audio_channels = channels;
+
+			err = tegra_hdmi_setup_audio(hdmi);
+			if (err < 0) {
+				tegra_hdmi_disable_audio_infoframe(hdmi);
+				tegra_hdmi_disable_audio(hdmi);
+			} else {
+				tegra_hdmi_setup_audio_infoframe(hdmi);
+				tegra_hdmi_enable_audio_infoframe(hdmi);
+				tegra_hdmi_enable_audio(hdmi);
+			}
+		} else {
+			tegra_hdmi_disable_audio_infoframe(hdmi);
+			tegra_hdmi_disable_audio(hdmi);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
 static int tegra_hdmi_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match;
@@ -1454,8 +1673,10 @@ static int tegra_hdmi_probe(struct platform_device *pdev)
 
 	hdmi->config = match->data;
 	hdmi->dev = &pdev->dev;
+
 	hdmi->audio_source = AUTO;
-	hdmi->audio_freq = 44100;
+	hdmi->audio_sample_rate = 48000;
+	hdmi->audio_channels = 2;
 	hdmi->stereo = false;
 	hdmi->dvi = false;
 
@@ -1516,6 +1737,17 @@ static int tegra_hdmi_probe(struct platform_device *pdev)
 
 	hdmi->irq = err;
 
+	err = devm_request_irq(hdmi->dev, hdmi->irq, tegra_hdmi_irq, 0,
+			       dev_name(hdmi->dev), hdmi);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to request IRQ#%u: %d\n",
+			hdmi->irq, err);
+		return err;
+	}
+
+	platform_set_drvdata(pdev, hdmi);
+	pm_runtime_enable(&pdev->dev);
+
 	INIT_LIST_HEAD(&hdmi->client.list);
 	hdmi->client.ops = &hdmi_client_ops;
 	hdmi->client.dev = &pdev->dev;
@@ -1527,8 +1759,6 @@ static int tegra_hdmi_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	platform_set_drvdata(pdev, hdmi);
-
 	return 0;
 }
 
@@ -1537,6 +1767,8 @@ static int tegra_hdmi_remove(struct platform_device *pdev)
 	struct tegra_hdmi *hdmi = platform_get_drvdata(pdev);
 	int err;
 
+	pm_runtime_disable(&pdev->dev);
+
 	err = host1x_client_unregister(&hdmi->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
@@ -1546,17 +1778,61 @@ static int tegra_hdmi_remove(struct platform_device *pdev)
 
 	tegra_output_remove(&hdmi->output);
 
-	clk_disable_unprepare(hdmi->clk_parent);
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int tegra_hdmi_suspend(struct device *dev)
+{
+	struct tegra_hdmi *hdmi = dev_get_drvdata(dev);
+	int err;
+
+	err = reset_control_assert(hdmi->rst);
+	if (err < 0) {
+		dev_err(dev, "failed to assert reset: %d\n", err);
+		return err;
+	}
+
+	usleep_range(1000, 2000);
+
 	clk_disable_unprepare(hdmi->clk);
 
 	return 0;
 }
 
+static int tegra_hdmi_resume(struct device *dev)
+{
+	struct tegra_hdmi *hdmi = dev_get_drvdata(dev);
+	int err;
+
+	err = clk_prepare_enable(hdmi->clk);
+	if (err < 0) {
+		dev_err(dev, "failed to enable clock: %d\n", err);
+		return err;
+	}
+
+	usleep_range(1000, 2000);
+
+	err = reset_control_deassert(hdmi->rst);
+	if (err < 0) {
+		dev_err(dev, "failed to deassert reset: %d\n", err);
+		clk_disable_unprepare(hdmi->clk);
+		return err;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops tegra_hdmi_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_hdmi_suspend, tegra_hdmi_resume, NULL)
+};
+
 struct platform_driver tegra_hdmi_driver = {
 	.driver = {
 		.name = "tegra-hdmi",
-		.owner = THIS_MODULE,
 		.of_match_table = tegra_hdmi_of_match,
+		.pm = &tegra_hdmi_pm_ops,
 	},
 	.probe = tegra_hdmi_probe,
 	.remove = tegra_hdmi_remove,
diff --git a/drivers/gpu/drm/tegra/hdmi.h b/drivers/gpu/drm/tegra/hdmi.h
index a882514389cd..2339f134a09a 100644
--- a/drivers/gpu/drm/tegra/hdmi.h
+++ b/drivers/gpu/drm/tegra/hdmi.h
@@ -468,9 +468,20 @@
 #define HDMI_NV_PDISP_KEY_SKEY_INDEX				0xa3
 
 #define HDMI_NV_PDISP_SOR_AUDIO_CNTRL0				0xac
-#define AUDIO_CNTRL0_INJECT_NULLSMPL (1 << 29)
+#define  SOR_AUDIO_CNTRL0_SOURCE_SELECT_AUTO	(0 << 20)
+#define  SOR_AUDIO_CNTRL0_SOURCE_SELECT_SPDIF	(1 << 20)
+#define  SOR_AUDIO_CNTRL0_SOURCE_SELECT_HDAL	(2 << 20)
+#define  SOR_AUDIO_CNTRL0_INJECT_NULLSMPL	(1 << 29)
+#define HDMI_NV_PDISP_SOR_AUDIO_SPARE0				0xae
+#define  SOR_AUDIO_SPARE0_HBR_ENABLE		(1 << 27)
+#define HDMI_NV_PDISP_SOR_AUDIO_HDA_CODEC_SCRATCH0		0xba
+#define  SOR_AUDIO_HDA_CODEC_SCRATCH0_VALID	(1 << 30)
+#define  SOR_AUDIO_HDA_CODEC_SCRATCH0_FMT_MASK	0xffff
+#define HDMI_NV_PDISP_SOR_AUDIO_HDA_CODEC_SCRATCH1		0xbb
 #define HDMI_NV_PDISP_SOR_AUDIO_HDA_ELD_BUFWR			0xbc
 #define HDMI_NV_PDISP_SOR_AUDIO_HDA_PRESENSE			0xbd
+#define  SOR_AUDIO_HDA_PRESENSE_VALID		(1 << 1)
+#define  SOR_AUDIO_HDA_PRESENSE_PRESENT		(1 << 0)
 
 #define HDMI_NV_PDISP_SOR_AUDIO_AVAL_0320    0xbf
 #define HDMI_NV_PDISP_SOR_AUDIO_AVAL_0441    0xc0
@@ -481,6 +492,14 @@
 #define HDMI_NV_PDISP_SOR_AUDIO_AVAL_1920    0xc5
 #define HDMI_NV_PDISP_SOR_AUDIO_AVAL_DEFAULT 0xc5
 
+#define HDMI_NV_PDISP_INT_STATUS			0xcc
+#define  INT_SCRATCH		(1 << 3)
+#define  INT_CP_REQUEST		(1 << 2)
+#define  INT_CODEC_SCRATCH1	(1 << 1)
+#define  INT_CODEC_SCRATCH0	(1 << 0)
+#define HDMI_NV_PDISP_INT_MASK				0xcd
+#define HDMI_NV_PDISP_INT_ENABLE			0xce
+
 #define HDMI_NV_PDISP_SOR_IO_PEAK_CURRENT		0xd1
 #define PEAK_CURRENT_LANE0(x) (((x) & 0x7f) <<  0)
 #define PEAK_CURRENT_LANE1(x) (((x) & 0x7f) <<  8)
diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c
index 46664b622270..595d1ec3e02e 100644
--- a/drivers/gpu/drm/tegra/output.c
+++ b/drivers/gpu/drm/tegra/output.c
@@ -36,20 +36,13 @@ int tegra_output_connector_get_modes(struct drm_connector *connector)
 
 	if (edid) {
 		err = drm_add_edid_modes(connector, edid);
+		drm_edid_to_eld(connector, edid);
 		kfree(edid);
 	}
 
 	return err;
 }
 
-struct drm_encoder *
-tegra_output_connector_best_encoder(struct drm_connector *connector)
-{
-	struct tegra_output *output = connector_to_output(connector);
-
-	return &output->encoder;
-}
-
 enum drm_connector_status
 tegra_output_connector_detect(struct drm_connector *connector, bool force)
 {
diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c
index e246334e0252..a131b44e2d6f 100644
--- a/drivers/gpu/drm/tegra/rgb.c
+++ b/drivers/gpu/drm/tegra/rgb.c
@@ -112,7 +112,6 @@ tegra_rgb_connector_mode_valid(struct drm_connector *connector,
 static const struct drm_connector_helper_funcs tegra_rgb_connector_helper_funcs = {
 	.get_modes = tegra_output_connector_get_modes,
 	.mode_valid = tegra_rgb_connector_mode_valid,
-	.best_encoder = tegra_output_connector_best_encoder,
 };
 
 static const struct drm_encoder_funcs tegra_rgb_encoder_funcs = {
diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c
index 757c6e8603af..74d0540b8d4c 100644
--- a/drivers/gpu/drm/tegra/sor.c
+++ b/drivers/gpu/drm/tegra/sor.c
@@ -7,11 +7,13 @@
  */
 
 #include <linux/clk.h>
+#include <linux/clk-provider.h>
 #include <linux/debugfs.h>
 #include <linux/gpio.h>
 #include <linux/io.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 
@@ -149,6 +151,8 @@ struct tegra_sor_soc {
 
 	const struct tegra_sor_hdmi_settings *settings;
 	unsigned int num_settings;
+
+	const u8 *xbar_cfg;
 };
 
 struct tegra_sor;
@@ -169,7 +173,9 @@ struct tegra_sor {
 
 	struct reset_control *rst;
 	struct clk *clk_parent;
+	struct clk *clk_brick;
 	struct clk *clk_safe;
+	struct clk *clk_src;
 	struct clk *clk_dp;
 	struct clk *clk;
 
@@ -190,6 +196,18 @@ struct tegra_sor {
 	struct regulator *hdmi_supply;
 };
 
+struct tegra_sor_state {
+	struct drm_connector_state base;
+
+	unsigned int bpc;
+};
+
+static inline struct tegra_sor_state *
+to_sor_state(struct drm_connector_state *state)
+{
+	return container_of(state, struct tegra_sor_state, base);
+}
+
 struct tegra_sor_config {
 	u32 bits_per_pixel;
 
@@ -225,6 +243,118 @@ static inline void tegra_sor_writel(struct tegra_sor *sor, u32 value,
 	writel(value, sor->regs + (offset << 2));
 }
 
+static int tegra_sor_set_parent_clock(struct tegra_sor *sor, struct clk *parent)
+{
+	int err;
+
+	clk_disable_unprepare(sor->clk);
+
+	err = clk_set_parent(sor->clk, parent);
+	if (err < 0)
+		return err;
+
+	err = clk_prepare_enable(sor->clk);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+struct tegra_clk_sor_brick {
+	struct clk_hw hw;
+	struct tegra_sor *sor;
+};
+
+static inline struct tegra_clk_sor_brick *to_brick(struct clk_hw *hw)
+{
+	return container_of(hw, struct tegra_clk_sor_brick, hw);
+}
+
+static const char * const tegra_clk_sor_brick_parents[] = {
+	"pll_d2_out0", "pll_dp"
+};
+
+static int tegra_clk_sor_brick_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct tegra_clk_sor_brick *brick = to_brick(hw);
+	struct tegra_sor *sor = brick->sor;
+	u32 value;
+
+	value = tegra_sor_readl(sor, SOR_CLK_CNTRL);
+	value &= ~SOR_CLK_CNTRL_DP_CLK_SEL_MASK;
+
+	switch (index) {
+	case 0:
+		value |= SOR_CLK_CNTRL_DP_CLK_SEL_SINGLE_PCLK;
+		break;
+
+	case 1:
+		value |= SOR_CLK_CNTRL_DP_CLK_SEL_SINGLE_DPCLK;
+		break;
+	}
+
+	tegra_sor_writel(sor, value, SOR_CLK_CNTRL);
+
+	return 0;
+}
+
+static u8 tegra_clk_sor_brick_get_parent(struct clk_hw *hw)
+{
+	struct tegra_clk_sor_brick *brick = to_brick(hw);
+	struct tegra_sor *sor = brick->sor;
+	u8 parent = U8_MAX;
+	u32 value;
+
+	value = tegra_sor_readl(sor, SOR_CLK_CNTRL);
+
+	switch (value & SOR_CLK_CNTRL_DP_CLK_SEL_MASK) {
+	case SOR_CLK_CNTRL_DP_CLK_SEL_SINGLE_PCLK:
+	case SOR_CLK_CNTRL_DP_CLK_SEL_DIFF_PCLK:
+		parent = 0;
+		break;
+
+	case SOR_CLK_CNTRL_DP_CLK_SEL_SINGLE_DPCLK:
+	case SOR_CLK_CNTRL_DP_CLK_SEL_DIFF_DPCLK:
+		parent = 1;
+		break;
+	}
+
+	return parent;
+}
+
+static const struct clk_ops tegra_clk_sor_brick_ops = {
+	.set_parent = tegra_clk_sor_brick_set_parent,
+	.get_parent = tegra_clk_sor_brick_get_parent,
+};
+
+static struct clk *tegra_clk_sor_brick_register(struct tegra_sor *sor,
+						const char *name)
+{
+	struct tegra_clk_sor_brick *brick;
+	struct clk_init_data init;
+	struct clk *clk;
+
+	brick = devm_kzalloc(sor->dev, sizeof(*brick), GFP_KERNEL);
+	if (!brick)
+		return ERR_PTR(-ENOMEM);
+
+	brick->sor = sor;
+
+	init.name = name;
+	init.flags = 0;
+	init.parent_names = tegra_clk_sor_brick_parents;
+	init.num_parents = ARRAY_SIZE(tegra_clk_sor_brick_parents);
+	init.ops = &tegra_clk_sor_brick_ops;
+
+	brick->hw.init = &init;
+
+	clk = devm_clk_register(sor->dev, &brick->hw);
+	if (IS_ERR(clk))
+		kfree(brick);
+
+	return clk;
+}
+
 static int tegra_sor_dp_train_fast(struct tegra_sor *sor,
 				   struct drm_dp_link *link)
 {
@@ -569,10 +699,10 @@ static int tegra_sor_compute_params(struct tegra_sor *sor,
 	return false;
 }
 
-static int tegra_sor_calc_config(struct tegra_sor *sor,
-				 const struct drm_display_mode *mode,
-				 struct tegra_sor_config *config,
-				 struct drm_dp_link *link)
+static int tegra_sor_compute_config(struct tegra_sor *sor,
+				    const struct drm_display_mode *mode,
+				    struct tegra_sor_config *config,
+				    struct drm_dp_link *link)
 {
 	const u64 f = 100000, link_rate = link->rate * 1000;
 	const u64 pclk = mode->clock * 1000;
@@ -661,6 +791,135 @@ static int tegra_sor_calc_config(struct tegra_sor *sor,
 	return 0;
 }
 
+static void tegra_sor_apply_config(struct tegra_sor *sor,
+				   const struct tegra_sor_config *config)
+{
+	u32 value;
+
+	value = tegra_sor_readl(sor, SOR_DP_LINKCTL0);
+	value &= ~SOR_DP_LINKCTL_TU_SIZE_MASK;
+	value |= SOR_DP_LINKCTL_TU_SIZE(config->tu_size);
+	tegra_sor_writel(sor, value, SOR_DP_LINKCTL0);
+
+	value = tegra_sor_readl(sor, SOR_DP_CONFIG0);
+	value &= ~SOR_DP_CONFIG_WATERMARK_MASK;
+	value |= SOR_DP_CONFIG_WATERMARK(config->watermark);
+
+	value &= ~SOR_DP_CONFIG_ACTIVE_SYM_COUNT_MASK;
+	value |= SOR_DP_CONFIG_ACTIVE_SYM_COUNT(config->active_count);
+
+	value &= ~SOR_DP_CONFIG_ACTIVE_SYM_FRAC_MASK;
+	value |= SOR_DP_CONFIG_ACTIVE_SYM_FRAC(config->active_frac);
+
+	if (config->active_polarity)
+		value |= SOR_DP_CONFIG_ACTIVE_SYM_POLARITY;
+	else
+		value &= ~SOR_DP_CONFIG_ACTIVE_SYM_POLARITY;
+
+	value |= SOR_DP_CONFIG_ACTIVE_SYM_ENABLE;
+	value |= SOR_DP_CONFIG_DISPARITY_NEGATIVE;
+	tegra_sor_writel(sor, value, SOR_DP_CONFIG0);
+
+	value = tegra_sor_readl(sor, SOR_DP_AUDIO_HBLANK_SYMBOLS);
+	value &= ~SOR_DP_AUDIO_HBLANK_SYMBOLS_MASK;
+	value |= config->hblank_symbols & 0xffff;
+	tegra_sor_writel(sor, value, SOR_DP_AUDIO_HBLANK_SYMBOLS);
+
+	value = tegra_sor_readl(sor, SOR_DP_AUDIO_VBLANK_SYMBOLS);
+	value &= ~SOR_DP_AUDIO_VBLANK_SYMBOLS_MASK;
+	value |= config->vblank_symbols & 0xffff;
+	tegra_sor_writel(sor, value, SOR_DP_AUDIO_VBLANK_SYMBOLS);
+}
+
+static void tegra_sor_mode_set(struct tegra_sor *sor,
+			       const struct drm_display_mode *mode,
+			       struct tegra_sor_state *state)
+{
+	struct tegra_dc *dc = to_tegra_dc(sor->output.encoder.crtc);
+	unsigned int vbe, vse, hbe, hse, vbs, hbs;
+	u32 value;
+
+	value = tegra_sor_readl(sor, SOR_STATE1);
+	value &= ~SOR_STATE_ASY_PIXELDEPTH_MASK;
+	value &= ~SOR_STATE_ASY_CRC_MODE_MASK;
+	value &= ~SOR_STATE_ASY_OWNER_MASK;
+
+	value |= SOR_STATE_ASY_CRC_MODE_COMPLETE |
+		 SOR_STATE_ASY_OWNER(dc->pipe + 1);
+
+	if (mode->flags & DRM_MODE_FLAG_PHSYNC)
+		value &= ~SOR_STATE_ASY_HSYNCPOL;
+
+	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
+		value |= SOR_STATE_ASY_HSYNCPOL;
+
+	if (mode->flags & DRM_MODE_FLAG_PVSYNC)
+		value &= ~SOR_STATE_ASY_VSYNCPOL;
+
+	if (mode->flags & DRM_MODE_FLAG_NVSYNC)
+		value |= SOR_STATE_ASY_VSYNCPOL;
+
+	switch (state->bpc) {
+	case 16:
+		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_48_444;
+		break;
+
+	case 12:
+		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_36_444;
+		break;
+
+	case 10:
+		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_30_444;
+		break;
+
+	case 8:
+		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_24_444;
+		break;
+
+	case 6:
+		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_18_444;
+		break;
+
+	default:
+		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_24_444;
+		break;
+	}
+
+	tegra_sor_writel(sor, value, SOR_STATE1);
+
+	/*
+	 * TODO: The video timing programming below doesn't seem to match the
+	 * register definitions.
+	 */
+
+	value = ((mode->vtotal & 0x7fff) << 16) | (mode->htotal & 0x7fff);
+	tegra_sor_writel(sor, value, SOR_HEAD_STATE1(dc->pipe));
+
+	/* sync end = sync width - 1 */
+	vse = mode->vsync_end - mode->vsync_start - 1;
+	hse = mode->hsync_end - mode->hsync_start - 1;
+
+	value = ((vse & 0x7fff) << 16) | (hse & 0x7fff);
+	tegra_sor_writel(sor, value, SOR_HEAD_STATE2(dc->pipe));
+
+	/* blank end = sync end + back porch */
+	vbe = vse + (mode->vtotal - mode->vsync_end);
+	hbe = hse + (mode->htotal - mode->hsync_end);
+
+	value = ((vbe & 0x7fff) << 16) | (hbe & 0x7fff);
+	tegra_sor_writel(sor, value, SOR_HEAD_STATE3(dc->pipe));
+
+	/* blank start = blank end + active */
+	vbs = vbe + mode->vdisplay;
+	hbs = hbe + mode->hdisplay;
+
+	value = ((vbs & 0x7fff) << 16) | (hbs & 0x7fff);
+	tegra_sor_writel(sor, value, SOR_HEAD_STATE4(dc->pipe));
+
+	/* XXX interlacing support */
+	tegra_sor_writel(sor, 0x001, SOR_HEAD_STATE5(dc->pipe));
+}
+
 static int tegra_sor_detach(struct tegra_sor *sor)
 {
 	unsigned long value, timeout;
@@ -733,7 +992,8 @@ static int tegra_sor_power_down(struct tegra_sor *sor)
 	if ((value & SOR_PWR_TRIGGER) != 0)
 		return -ETIMEDOUT;
 
-	err = clk_set_parent(sor->clk, sor->clk_safe);
+	/* switch to safe parent clock */
+	err = tegra_sor_set_parent_clock(sor, sor->clk_safe);
 	if (err < 0)
 		dev_err(sor->dev, "failed to set safe parent clock: %d\n", err);
 
@@ -1038,6 +1298,22 @@ static void tegra_sor_debugfs_exit(struct tegra_sor *sor)
 	sor->debugfs = NULL;
 }
 
+static void tegra_sor_connector_reset(struct drm_connector *connector)
+{
+	struct tegra_sor_state *state;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return;
+
+	if (connector->state) {
+		__drm_atomic_helper_connector_destroy_state(connector->state);
+		kfree(connector->state);
+	}
+
+	__drm_atomic_helper_connector_reset(connector, &state->base);
+}
+
 static enum drm_connector_status
 tegra_sor_connector_detect(struct drm_connector *connector, bool force)
 {
@@ -1050,13 +1326,28 @@ tegra_sor_connector_detect(struct drm_connector *connector, bool force)
 	return tegra_output_connector_detect(connector, force);
 }
 
+static struct drm_connector_state *
+tegra_sor_connector_duplicate_state(struct drm_connector *connector)
+{
+	struct tegra_sor_state *state = to_sor_state(connector->state);
+	struct tegra_sor_state *copy;
+
+	copy = kmemdup(state, sizeof(*state), GFP_KERNEL);
+	if (!copy)
+		return NULL;
+
+	__drm_atomic_helper_connector_duplicate_state(connector, &copy->base);
+
+	return &copy->base;
+}
+
 static const struct drm_connector_funcs tegra_sor_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
-	.reset = drm_atomic_helper_connector_reset,
+	.reset = tegra_sor_connector_reset,
 	.detect = tegra_sor_connector_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.destroy = tegra_output_connector_destroy,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_duplicate_state = tegra_sor_connector_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
@@ -1081,13 +1372,16 @@ static enum drm_mode_status
 tegra_sor_connector_mode_valid(struct drm_connector *connector,
 			       struct drm_display_mode *mode)
 {
+	/* HDMI 2.0 modes are not yet supported */
+	if (mode->clock > 340000)
+		return MODE_NOCLOCK;
+
 	return MODE_OK;
 }
 
 static const struct drm_connector_helper_funcs tegra_sor_connector_helper_funcs = {
 	.get_modes = tegra_sor_connector_get_modes,
 	.mode_valid = tegra_sor_connector_mode_valid,
-	.best_encoder = tegra_output_connector_best_encoder,
 };
 
 static const struct drm_encoder_funcs tegra_sor_encoder_funcs = {
@@ -1141,8 +1435,7 @@ static void tegra_sor_edp_disable(struct drm_encoder *encoder)
 	if (output->panel)
 		drm_panel_unprepare(output->panel);
 
-	reset_control_assert(sor->rst);
-	clk_disable_unprepare(sor->clk);
+	pm_runtime_put(sor->dev);
 }
 
 #if 0
@@ -1192,19 +1485,18 @@ static void tegra_sor_edp_enable(struct drm_encoder *encoder)
 	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
 	struct tegra_output *output = encoder_to_output(encoder);
 	struct tegra_dc *dc = to_tegra_dc(encoder->crtc);
-	unsigned int vbe, vse, hbe, hse, vbs, hbs, i;
 	struct tegra_sor *sor = to_sor(output);
 	struct tegra_sor_config config;
+	struct tegra_sor_state *state;
 	struct drm_dp_link link;
 	u8 rate, lanes;
+	unsigned int i;
 	int err = 0;
 	u32 value;
 
-	err = clk_prepare_enable(sor->clk);
-	if (err < 0)
-		dev_err(sor->dev, "failed to enable clock: %d\n", err);
+	state = to_sor_state(output->connector.state);
 
-	reset_control_deassert(sor->rst);
+	pm_runtime_get_sync(sor->dev);
 
 	if (output->panel)
 		drm_panel_prepare(output->panel);
@@ -1219,17 +1511,17 @@ static void tegra_sor_edp_enable(struct drm_encoder *encoder)
 		return;
 	}
 
-	err = clk_set_parent(sor->clk, sor->clk_safe);
+	/* switch to safe parent clock */
+	err = tegra_sor_set_parent_clock(sor, sor->clk_safe);
 	if (err < 0)
 		dev_err(sor->dev, "failed to set safe parent clock: %d\n", err);
 
 	memset(&config, 0, sizeof(config));
-	config.bits_per_pixel = output->connector.display_info.bpc * 3;
+	config.bits_per_pixel = state->bpc * 3;
 
-	err = tegra_sor_calc_config(sor, mode, &config, &link);
+	err = tegra_sor_compute_config(sor, mode, &config, &link);
 	if (err < 0)
-		dev_err(sor->dev, "failed to compute link configuration: %d\n",
-			err);
+		dev_err(sor->dev, "failed to compute configuration: %d\n", err);
 
 	value = tegra_sor_readl(sor, SOR_CLK_CNTRL);
 	value &= ~SOR_CLK_CNTRL_DP_CLK_SEL_MASK;
@@ -1326,10 +1618,18 @@ static void tegra_sor_edp_enable(struct drm_encoder *encoder)
 	value &= ~SOR_PLL2_PORT_POWERDOWN;
 	tegra_sor_writel(sor, value, SOR_PLL2);
 
-	/* switch to DP clock */
-	err = clk_set_parent(sor->clk, sor->clk_dp);
+	/* XXX not in TRM */
+	for (value = 0, i = 0; i < 5; i++)
+		value |= SOR_XBAR_CTRL_LINK0_XSEL(i, sor->soc->xbar_cfg[i]) |
+			 SOR_XBAR_CTRL_LINK1_XSEL(i, i);
+
+	tegra_sor_writel(sor, 0x00000000, SOR_XBAR_POL);
+	tegra_sor_writel(sor, value, SOR_XBAR_CTRL);
+
+	/* switch to DP parent clock */
+	err = tegra_sor_set_parent_clock(sor, sor->clk_dp);
 	if (err < 0)
-		dev_err(sor->dev, "failed to set DP parent clock: %d\n", err);
+		dev_err(sor->dev, "failed to set parent clock: %d\n", err);
 
 	/* power DP lanes */
 	value = tegra_sor_readl(sor, SOR_DP_PADCTL0);
@@ -1375,13 +1675,11 @@ static void tegra_sor_edp_enable(struct drm_encoder *encoder)
 	value |= drm_dp_link_rate_to_bw_code(link.rate) << 2;
 	tegra_sor_writel(sor, value, SOR_CLK_CNTRL);
 
-	/* set linkctl */
+	tegra_sor_apply_config(sor, &config);
+
+	/* enable link */
 	value = tegra_sor_readl(sor, SOR_DP_LINKCTL0);
 	value |= SOR_DP_LINKCTL_ENABLE;
-
-	value &= ~SOR_DP_LINKCTL_TU_SIZE_MASK;
-	value |= SOR_DP_LINKCTL_TU_SIZE(config.tu_size);
-
 	value |= SOR_DP_LINKCTL_ENHANCED_FRAME;
 	tegra_sor_writel(sor, value, SOR_DP_LINKCTL0);
 
@@ -1394,35 +1692,6 @@ static void tegra_sor_edp_enable(struct drm_encoder *encoder)
 
 	tegra_sor_writel(sor, value, SOR_DP_TPG);
 
-	value = tegra_sor_readl(sor, SOR_DP_CONFIG0);
-	value &= ~SOR_DP_CONFIG_WATERMARK_MASK;
-	value |= SOR_DP_CONFIG_WATERMARK(config.watermark);
-
-	value &= ~SOR_DP_CONFIG_ACTIVE_SYM_COUNT_MASK;
-	value |= SOR_DP_CONFIG_ACTIVE_SYM_COUNT(config.active_count);
-
-	value &= ~SOR_DP_CONFIG_ACTIVE_SYM_FRAC_MASK;
-	value |= SOR_DP_CONFIG_ACTIVE_SYM_FRAC(config.active_frac);
-
-	if (config.active_polarity)
-		value |= SOR_DP_CONFIG_ACTIVE_SYM_POLARITY;
-	else
-		value &= ~SOR_DP_CONFIG_ACTIVE_SYM_POLARITY;
-
-	value |= SOR_DP_CONFIG_ACTIVE_SYM_ENABLE;
-	value |= SOR_DP_CONFIG_DISPARITY_NEGATIVE;
-	tegra_sor_writel(sor, value, SOR_DP_CONFIG0);
-
-	value = tegra_sor_readl(sor, SOR_DP_AUDIO_HBLANK_SYMBOLS);
-	value &= ~SOR_DP_AUDIO_HBLANK_SYMBOLS_MASK;
-	value |= config.hblank_symbols & 0xffff;
-	tegra_sor_writel(sor, value, SOR_DP_AUDIO_HBLANK_SYMBOLS);
-
-	value = tegra_sor_readl(sor, SOR_DP_AUDIO_VBLANK_SYMBOLS);
-	value &= ~SOR_DP_AUDIO_VBLANK_SYMBOLS_MASK;
-	value |= config.vblank_symbols & 0xffff;
-	tegra_sor_writel(sor, value, SOR_DP_AUDIO_VBLANK_SYMBOLS);
-
 	/* enable pad calibration logic */
 	value = tegra_sor_readl(sor, SOR_DP_PADCTL0);
 	value |= SOR_DP_PADCTL_PAD_CAL_PD;
@@ -1478,75 +1747,19 @@ static void tegra_sor_edp_enable(struct drm_encoder *encoder)
 	if (err < 0)
 		dev_err(sor->dev, "failed to power up SOR: %d\n", err);
 
-	/*
-	 * configure panel (24bpp, vsync-, hsync-, DP-A protocol, complete
-	 * raster, associate with display controller)
-	 */
-	value = SOR_STATE_ASY_PROTOCOL_DP_A |
-		SOR_STATE_ASY_CRC_MODE_COMPLETE |
-		SOR_STATE_ASY_OWNER(dc->pipe + 1);
-
-	if (mode->flags & DRM_MODE_FLAG_PHSYNC)
-		value &= ~SOR_STATE_ASY_HSYNCPOL;
-
-	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
-		value |= SOR_STATE_ASY_HSYNCPOL;
-
-	if (mode->flags & DRM_MODE_FLAG_PVSYNC)
-		value &= ~SOR_STATE_ASY_VSYNCPOL;
-
-	if (mode->flags & DRM_MODE_FLAG_NVSYNC)
-		value |= SOR_STATE_ASY_VSYNCPOL;
-
-	switch (config.bits_per_pixel) {
-	case 24:
-		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_24_444;
-		break;
-
-	case 18:
-		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_18_444;
-		break;
-
-	default:
-		BUG();
-		break;
-	}
-
-	tegra_sor_writel(sor, value, SOR_STATE1);
-
-	/*
-	 * TODO: The video timing programming below doesn't seem to match the
-	 * register definitions.
-	 */
-
-	value = ((mode->vtotal & 0x7fff) << 16) | (mode->htotal & 0x7fff);
-	tegra_sor_writel(sor, value, SOR_HEAD_STATE1(dc->pipe));
-
-	vse = mode->vsync_end - mode->vsync_start - 1;
-	hse = mode->hsync_end - mode->hsync_start - 1;
-
-	value = ((vse & 0x7fff) << 16) | (hse & 0x7fff);
-	tegra_sor_writel(sor, value, SOR_HEAD_STATE2(dc->pipe));
-
-	vbe = vse + (mode->vsync_start - mode->vdisplay);
-	hbe = hse + (mode->hsync_start - mode->hdisplay);
-
-	value = ((vbe & 0x7fff) << 16) | (hbe & 0x7fff);
-	tegra_sor_writel(sor, value, SOR_HEAD_STATE3(dc->pipe));
-
-	vbs = vbe + mode->vdisplay;
-	hbs = hbe + mode->hdisplay;
-
-	value = ((vbs & 0x7fff) << 16) | (hbs & 0x7fff);
-	tegra_sor_writel(sor, value, SOR_HEAD_STATE4(dc->pipe));
-
-	tegra_sor_writel(sor, 0x1, SOR_HEAD_STATE5(dc->pipe));
-
 	/* CSTM (LVDS, link A/B, upper) */
 	value = SOR_CSTM_LVDS | SOR_CSTM_LINK_ACT_A | SOR_CSTM_LINK_ACT_B |
 		SOR_CSTM_UPPER;
 	tegra_sor_writel(sor, value, SOR_CSTM);
 
+	/* use DP-A protocol */
+	value = tegra_sor_readl(sor, SOR_STATE1);
+	value &= ~SOR_STATE_ASY_PROTOCOL_MASK;
+	value |= SOR_STATE_ASY_PROTOCOL_DP_A;
+	tegra_sor_writel(sor, value, SOR_STATE1);
+
+	tegra_sor_mode_set(sor, mode, state);
+
 	/* PWM setup */
 	err = tegra_sor_setup_pwm(sor, 250);
 	if (err < 0)
@@ -1578,11 +1791,15 @@ tegra_sor_encoder_atomic_check(struct drm_encoder *encoder,
 			       struct drm_connector_state *conn_state)
 {
 	struct tegra_output *output = encoder_to_output(encoder);
+	struct tegra_sor_state *state = to_sor_state(conn_state);
 	struct tegra_dc *dc = to_tegra_dc(conn_state->crtc);
 	unsigned long pclk = crtc_state->mode.clock * 1000;
 	struct tegra_sor *sor = to_sor(output);
+	struct drm_display_info *info;
 	int err;
 
+	info = &output->connector.display_info;
+
 	err = tegra_dc_state_setup_clock(dc, crtc_state, sor->clk_parent,
 					 pclk, 0);
 	if (err < 0) {
@@ -1590,6 +1807,18 @@ tegra_sor_encoder_atomic_check(struct drm_encoder *encoder,
 		return err;
 	}
 
+	switch (info->bpc) {
+	case 8:
+	case 6:
+		state->bpc = info->bpc;
+		break;
+
+	default:
+		DRM_DEBUG_KMS("%u bits-per-color not supported\n", info->bpc);
+		state->bpc = 8;
+		break;
+	}
+
 	return 0;
 }
 
@@ -1752,9 +1981,7 @@ static void tegra_sor_hdmi_disable(struct drm_encoder *encoder)
 	if (err < 0)
 		dev_err(sor->dev, "failed to power off HDMI rail: %d\n", err);
 
-	reset_control_assert(sor->rst);
-	usleep_range(1000, 2000);
-	clk_disable_unprepare(sor->clk);
+	pm_runtime_put(sor->dev);
 }
 
 static void tegra_sor_hdmi_enable(struct drm_encoder *encoder)
@@ -1762,26 +1989,21 @@ static void tegra_sor_hdmi_enable(struct drm_encoder *encoder)
 	struct tegra_output *output = encoder_to_output(encoder);
 	unsigned int h_ref_to_sync = 1, pulse_start, max_ac;
 	struct tegra_dc *dc = to_tegra_dc(encoder->crtc);
-	unsigned int vbe, vse, hbe, hse, vbs, hbs, div;
 	struct tegra_sor_hdmi_settings *settings;
 	struct tegra_sor *sor = to_sor(output);
+	struct tegra_sor_state *state;
 	struct drm_display_mode *mode;
-	struct drm_display_info *info;
+	unsigned int div, i;
 	u32 value;
 	int err;
 
+	state = to_sor_state(output->connector.state);
 	mode = &encoder->crtc->state->adjusted_mode;
-	info = &output->connector.display_info;
 
-	err = clk_prepare_enable(sor->clk);
-	if (err < 0)
-		dev_err(sor->dev, "failed to enable clock: %d\n", err);
+	pm_runtime_get_sync(sor->dev);
 
-	usleep_range(1000, 2000);
-
-	reset_control_deassert(sor->rst);
-
-	err = clk_set_parent(sor->clk, sor->clk_safe);
+	/* switch to safe parent clock */
+	err = tegra_sor_set_parent_clock(sor, sor->clk_safe);
 	if (err < 0)
 		dev_err(sor->dev, "failed to set safe parent clock: %d\n", err);
 
@@ -1877,22 +2099,20 @@ static void tegra_sor_hdmi_enable(struct drm_encoder *encoder)
 	value = SOR_REFCLK_DIV_INT(div) | SOR_REFCLK_DIV_FRAC(div);
 	tegra_sor_writel(sor, value, SOR_REFCLK);
 
-	/* XXX don't hardcode */
-	value = SOR_XBAR_CTRL_LINK1_XSEL(4, 4) |
-		SOR_XBAR_CTRL_LINK1_XSEL(3, 3) |
-		SOR_XBAR_CTRL_LINK1_XSEL(2, 2) |
-		SOR_XBAR_CTRL_LINK1_XSEL(1, 1) |
-		SOR_XBAR_CTRL_LINK1_XSEL(0, 0) |
-		SOR_XBAR_CTRL_LINK0_XSEL(4, 4) |
-		SOR_XBAR_CTRL_LINK0_XSEL(3, 3) |
-		SOR_XBAR_CTRL_LINK0_XSEL(2, 0) |
-		SOR_XBAR_CTRL_LINK0_XSEL(1, 1) |
-		SOR_XBAR_CTRL_LINK0_XSEL(0, 2);
-	tegra_sor_writel(sor, value, SOR_XBAR_CTRL);
+	/* XXX not in TRM */
+	for (value = 0, i = 0; i < 5; i++)
+		value |= SOR_XBAR_CTRL_LINK0_XSEL(i, sor->soc->xbar_cfg[i]) |
+			 SOR_XBAR_CTRL_LINK1_XSEL(i, i);
 
 	tegra_sor_writel(sor, 0x00000000, SOR_XBAR_POL);
+	tegra_sor_writel(sor, value, SOR_XBAR_CTRL);
 
-	err = clk_set_parent(sor->clk, sor->clk_parent);
+	/* switch to parent clock */
+	err = clk_set_parent(sor->clk_src, sor->clk_parent);
+	if (err < 0)
+		dev_err(sor->dev, "failed to set source clock: %d\n", err);
+
+	err = tegra_sor_set_parent_clock(sor, sor->clk_src);
 	if (err < 0)
 		dev_err(sor->dev, "failed to set parent clock: %d\n", err);
 
@@ -2002,7 +2222,7 @@ static void tegra_sor_hdmi_enable(struct drm_encoder *encoder)
 	value &= ~DITHER_CONTROL_MASK;
 	value &= ~BASE_COLOR_SIZE_MASK;
 
-	switch (info->bpc) {
+	switch (state->bpc) {
 	case 6:
 		value |= BASE_COLOR_SIZE_666;
 		break;
@@ -2012,7 +2232,8 @@ static void tegra_sor_hdmi_enable(struct drm_encoder *encoder)
 		break;
 
 	default:
-		WARN(1, "%u bits-per-color not supported\n", info->bpc);
+		WARN(1, "%u bits-per-color not supported\n", state->bpc);
+		value |= BASE_COLOR_SIZE_888;
 		break;
 	}
 
@@ -2022,83 +2243,19 @@ static void tegra_sor_hdmi_enable(struct drm_encoder *encoder)
 	if (err < 0)
 		dev_err(sor->dev, "failed to power up SOR: %d\n", err);
 
-	/* configure mode */
-	value = tegra_sor_readl(sor, SOR_STATE1);
-	value &= ~SOR_STATE_ASY_PIXELDEPTH_MASK;
-	value &= ~SOR_STATE_ASY_CRC_MODE_MASK;
-	value &= ~SOR_STATE_ASY_OWNER_MASK;
-
-	value |= SOR_STATE_ASY_CRC_MODE_COMPLETE |
-		 SOR_STATE_ASY_OWNER(dc->pipe + 1);
-
-	if (mode->flags & DRM_MODE_FLAG_PHSYNC)
-		value &= ~SOR_STATE_ASY_HSYNCPOL;
-
-	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
-		value |= SOR_STATE_ASY_HSYNCPOL;
-
-	if (mode->flags & DRM_MODE_FLAG_PVSYNC)
-		value &= ~SOR_STATE_ASY_VSYNCPOL;
-
-	if (mode->flags & DRM_MODE_FLAG_NVSYNC)
-		value |= SOR_STATE_ASY_VSYNCPOL;
-
-	switch (info->bpc) {
-	case 8:
-		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_24_444;
-		break;
-
-	case 6:
-		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_18_444;
-		break;
-
-	default:
-		BUG();
-		break;
-	}
-
-	tegra_sor_writel(sor, value, SOR_STATE1);
-
+	/* configure dynamic range of output */
 	value = tegra_sor_readl(sor, SOR_HEAD_STATE0(dc->pipe));
 	value &= ~SOR_HEAD_STATE_RANGECOMPRESS_MASK;
 	value &= ~SOR_HEAD_STATE_DYNRANGE_MASK;
 	tegra_sor_writel(sor, value, SOR_HEAD_STATE0(dc->pipe));
 
+	/* configure colorspace */
 	value = tegra_sor_readl(sor, SOR_HEAD_STATE0(dc->pipe));
 	value &= ~SOR_HEAD_STATE_COLORSPACE_MASK;
 	value |= SOR_HEAD_STATE_COLORSPACE_RGB;
 	tegra_sor_writel(sor, value, SOR_HEAD_STATE0(dc->pipe));
 
-	/*
-	 * TODO: The video timing programming below doesn't seem to match the
-	 * register definitions.
-	 */
-
-	value = ((mode->vtotal & 0x7fff) << 16) | (mode->htotal & 0x7fff);
-	tegra_sor_writel(sor, value, SOR_HEAD_STATE1(dc->pipe));
-
-	/* sync end = sync width - 1 */
-	vse = mode->vsync_end - mode->vsync_start - 1;
-	hse = mode->hsync_end - mode->hsync_start - 1;
-
-	value = ((vse & 0x7fff) << 16) | (hse & 0x7fff);
-	tegra_sor_writel(sor, value, SOR_HEAD_STATE2(dc->pipe));
-
-	/* blank end = sync end + back porch */
-	vbe = vse + (mode->vtotal - mode->vsync_end);
-	hbe = hse + (mode->htotal - mode->hsync_end);
-
-	value = ((vbe & 0x7fff) << 16) | (hbe & 0x7fff);
-	tegra_sor_writel(sor, value, SOR_HEAD_STATE3(dc->pipe));
-
-	/* blank start = blank end + active */
-	vbs = vbe + mode->vdisplay;
-	hbs = hbe + mode->hdisplay;
-
-	value = ((vbs & 0x7fff) << 16) | (hbs & 0x7fff);
-	tegra_sor_writel(sor, value, SOR_HEAD_STATE4(dc->pipe));
-
-	tegra_sor_writel(sor, 0x1, SOR_HEAD_STATE5(dc->pipe));
+	tegra_sor_mode_set(sor, mode, state);
 
 	tegra_sor_update(sor);
 
@@ -2196,10 +2353,13 @@ static int tegra_sor_init(struct host1x_client *client)
 	 * XXX: Remove this reset once proper hand-over from firmware to
 	 * kernel is possible.
 	 */
-	err = reset_control_assert(sor->rst);
-	if (err < 0) {
-		dev_err(sor->dev, "failed to assert SOR reset: %d\n", err);
-		return err;
+	if (sor->rst) {
+		err = reset_control_assert(sor->rst);
+		if (err < 0) {
+			dev_err(sor->dev, "failed to assert SOR reset: %d\n",
+				err);
+			return err;
+		}
 	}
 
 	err = clk_prepare_enable(sor->clk);
@@ -2210,10 +2370,13 @@ static int tegra_sor_init(struct host1x_client *client)
 
 	usleep_range(1000, 3000);
 
-	err = reset_control_deassert(sor->rst);
-	if (err < 0) {
-		dev_err(sor->dev, "failed to deassert SOR reset: %d\n", err);
-		return err;
+	if (sor->rst) {
+		err = reset_control_deassert(sor->rst);
+		if (err < 0) {
+			dev_err(sor->dev, "failed to deassert SOR reset: %d\n",
+				err);
+			return err;
+		}
 	}
 
 	err = clk_prepare_enable(sor->clk_safe);
@@ -2324,11 +2487,16 @@ static const struct tegra_sor_ops tegra_sor_hdmi_ops = {
 	.remove = tegra_sor_hdmi_remove,
 };
 
+static const u8 tegra124_sor_xbar_cfg[5] = {
+	0, 1, 2, 3, 4
+};
+
 static const struct tegra_sor_soc tegra124_sor = {
 	.supports_edp = true,
 	.supports_lvds = true,
 	.supports_hdmi = false,
 	.supports_dp = false,
+	.xbar_cfg = tegra124_sor_xbar_cfg,
 };
 
 static const struct tegra_sor_soc tegra210_sor = {
@@ -2336,6 +2504,11 @@ static const struct tegra_sor_soc tegra210_sor = {
 	.supports_lvds = false,
 	.supports_hdmi = false,
 	.supports_dp = false,
+	.xbar_cfg = tegra124_sor_xbar_cfg,
+};
+
+static const u8 tegra210_sor_xbar_cfg[5] = {
+	2, 1, 0, 3, 4
 };
 
 static const struct tegra_sor_soc tegra210_sor1 = {
@@ -2346,6 +2519,8 @@ static const struct tegra_sor_soc tegra210_sor1 = {
 
 	.num_settings = ARRAY_SIZE(tegra210_sor_hdmi_defaults),
 	.settings = tegra210_sor_hdmi_defaults,
+
+	.xbar_cfg = tegra210_sor_xbar_cfg,
 };
 
 static const struct of_device_id tegra_sor_of_match[] = {
@@ -2435,11 +2610,14 @@ static int tegra_sor_probe(struct platform_device *pdev)
 		goto remove;
 	}
 
-	sor->rst = devm_reset_control_get(&pdev->dev, "sor");
-	if (IS_ERR(sor->rst)) {
-		err = PTR_ERR(sor->rst);
-		dev_err(&pdev->dev, "failed to get reset control: %d\n", err);
-		goto remove;
+	if (!pdev->dev.pm_domain) {
+		sor->rst = devm_reset_control_get(&pdev->dev, "sor");
+		if (IS_ERR(sor->rst)) {
+			err = PTR_ERR(sor->rst);
+			dev_err(&pdev->dev, "failed to get reset control: %d\n",
+				err);
+			goto remove;
+		}
 	}
 
 	sor->clk = devm_clk_get(&pdev->dev, NULL);
@@ -2449,6 +2627,16 @@ static int tegra_sor_probe(struct platform_device *pdev)
 		goto remove;
 	}
 
+	if (sor->soc->supports_hdmi || sor->soc->supports_dp) {
+		sor->clk_src = devm_clk_get(&pdev->dev, "source");
+		if (IS_ERR(sor->clk_src)) {
+			err = PTR_ERR(sor->clk_src);
+			dev_err(sor->dev, "failed to get source clock: %d\n",
+				err);
+			goto remove;
+		}
+	}
+
 	sor->clk_parent = devm_clk_get(&pdev->dev, "parent");
 	if (IS_ERR(sor->clk_parent)) {
 		err = PTR_ERR(sor->clk_parent);
@@ -2470,6 +2658,19 @@ static int tegra_sor_probe(struct platform_device *pdev)
 		goto remove;
 	}
 
+	platform_set_drvdata(pdev, sor);
+	pm_runtime_enable(&pdev->dev);
+
+	pm_runtime_get_sync(&pdev->dev);
+	sor->clk_brick = tegra_clk_sor_brick_register(sor, "sor1_brick");
+	pm_runtime_put(&pdev->dev);
+
+	if (IS_ERR(sor->clk_brick)) {
+		err = PTR_ERR(sor->clk_brick);
+		dev_err(&pdev->dev, "failed to register SOR clock: %d\n", err);
+		goto remove;
+	}
+
 	INIT_LIST_HEAD(&sor->client.list);
 	sor->client.ops = &sor_client_ops;
 	sor->client.dev = &pdev->dev;
@@ -2481,8 +2682,6 @@ static int tegra_sor_probe(struct platform_device *pdev)
 		goto remove;
 	}
 
-	platform_set_drvdata(pdev, sor);
-
 	return 0;
 
 remove:
@@ -2498,6 +2697,8 @@ static int tegra_sor_remove(struct platform_device *pdev)
 	struct tegra_sor *sor = platform_get_drvdata(pdev);
 	int err;
 
+	pm_runtime_disable(&pdev->dev);
+
 	err = host1x_client_unregister(&sor->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
@@ -2516,10 +2717,62 @@ static int tegra_sor_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int tegra_sor_suspend(struct device *dev)
+{
+	struct tegra_sor *sor = dev_get_drvdata(dev);
+	int err;
+
+	if (sor->rst) {
+		err = reset_control_assert(sor->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to assert reset: %d\n", err);
+			return err;
+		}
+	}
+
+	usleep_range(1000, 2000);
+
+	clk_disable_unprepare(sor->clk);
+
+	return 0;
+}
+
+static int tegra_sor_resume(struct device *dev)
+{
+	struct tegra_sor *sor = dev_get_drvdata(dev);
+	int err;
+
+	err = clk_prepare_enable(sor->clk);
+	if (err < 0) {
+		dev_err(dev, "failed to enable clock: %d\n", err);
+		return err;
+	}
+
+	usleep_range(1000, 2000);
+
+	if (sor->rst) {
+		err = reset_control_deassert(sor->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to deassert reset: %d\n", err);
+			clk_disable_unprepare(sor->clk);
+			return err;
+		}
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops tegra_sor_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_sor_suspend, tegra_sor_resume, NULL)
+};
+
 struct platform_driver tegra_sor_driver = {
 	.driver = {
 		.name = "tegra-sor",
 		.of_match_table = tegra_sor_of_match,
+		.pm = &tegra_sor_pm_ops,
 	},
 	.probe = tegra_sor_probe,
 	.remove = tegra_sor_remove,
diff --git a/drivers/gpu/drm/tegra/sor.h b/drivers/gpu/drm/tegra/sor.h
index 2d31d027e3f6..865c73b48968 100644
--- a/drivers/gpu/drm/tegra/sor.h
+++ b/drivers/gpu/drm/tegra/sor.h
@@ -27,6 +27,9 @@
 #define  SOR_STATE_ASY_PIXELDEPTH_MASK		(0xf << 17)
 #define  SOR_STATE_ASY_PIXELDEPTH_BPP_18_444	(0x2 << 17)
 #define  SOR_STATE_ASY_PIXELDEPTH_BPP_24_444	(0x5 << 17)
+#define  SOR_STATE_ASY_PIXELDEPTH_BPP_30_444	(0x6 << 17)
+#define  SOR_STATE_ASY_PIXELDEPTH_BPP_36_444	(0x8 << 17)
+#define  SOR_STATE_ASY_PIXELDEPTH_BPP_48_444	(0x9 << 17)
 #define  SOR_STATE_ASY_VSYNCPOL			(1 << 13)
 #define  SOR_STATE_ASY_HSYNCPOL			(1 << 12)
 #define  SOR_STATE_ASY_PROTOCOL_MASK		(0xf << 8)
diff --git a/drivers/gpu/drm/tilcdc/Kconfig b/drivers/gpu/drm/tilcdc/Kconfig
index f60a1ec84fa4..28fed7e206d0 100644
--- a/drivers/gpu/drm/tilcdc/Kconfig
+++ b/drivers/gpu/drm/tilcdc/Kconfig
@@ -2,7 +2,6 @@ config DRM_TILCDC
 	tristate "DRM Support for TI LCDC Display Controller"
 	depends on DRM && OF && ARM
 	select DRM_KMS_HELPER
-	select DRM_KMS_FB_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_GEM_CMA_HELPER
 	select VIDEOMODE_HELPERS
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
index 79027b1c64d3..107c8bd04f6d 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
@@ -697,7 +697,7 @@ irqreturn_t tilcdc_crtc_irq(struct drm_crtc *crtc)
 
 		spin_unlock_irqrestore(&tilcdc_crtc->irq_lock, flags);
 
-		drm_handle_vblank(dev, 0);
+		drm_crtc_handle_vblank(crtc);
 
 		if (!skip_event) {
 			struct drm_pending_vblank_event *event;
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index 709bc903524d..d27809372d54 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -541,7 +541,6 @@ static struct drm_driver tilcdc_driver = {
 	.load               = tilcdc_load,
 	.unload             = tilcdc_unload,
 	.lastclose          = tilcdc_lastclose,
-	.set_busid          = drm_platform_set_busid,
 	.irq_handler        = tilcdc_irq,
 	.irq_preinstall     = tilcdc_irq_preinstall,
 	.irq_postinstall    = tilcdc_irq_postinstall,
@@ -549,7 +548,7 @@ static struct drm_driver tilcdc_driver = {
 	.get_vblank_counter = drm_vblank_no_hw_counter,
 	.enable_vblank      = tilcdc_enable_vblank,
 	.disable_vblank     = tilcdc_disable_vblank,
-	.gem_free_object    = drm_gem_cma_free_object,
+	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops         = &drm_gem_cma_vm_ops,
 	.dumb_create        = drm_gem_cma_dumb_create,
 	.dumb_map_offset    = drm_gem_cma_dumb_map_offset,
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index a71cf98c655f..4054d804fe06 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -146,10 +146,9 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	BUG_ON(bo->mem.mm_node != NULL);
 	BUG_ON(!list_empty(&bo->lru));
 	BUG_ON(!list_empty(&bo->ddestroy));
-
-	if (bo->ttm)
-		ttm_tt_destroy(bo->ttm);
+	ttm_tt_destroy(bo->ttm);
 	atomic_dec(&bo->glob->bo_count);
+	fence_put(bo->moving);
 	if (bo->resv == &bo->ttm_resv)
 		reservation_object_fini(&bo->ttm_resv);
 	mutex_destroy(&bo->wu_mutex);
@@ -360,7 +359,8 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 		ret = bdev->driver->move(bo, evict, interruptible,
 					 no_wait_gpu, mem);
 	else
-		ret = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, mem);
+		ret = ttm_bo_move_memcpy(bo, evict, interruptible,
+					 no_wait_gpu, mem);
 
 	if (ret) {
 		if (bdev->driver->move_notify) {
@@ -396,8 +396,7 @@ moved:
 
 out_err:
 	new_man = &bdev->man[bo->mem.mem_type];
-	if ((new_man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm) {
-		ttm_tt_unbind(bo->ttm);
+	if (new_man->flags & TTM_MEMTYPE_FLAG_FIXED) {
 		ttm_tt_destroy(bo->ttm);
 		bo->ttm = NULL;
 	}
@@ -418,11 +417,8 @@ static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo)
 	if (bo->bdev->driver->move_notify)
 		bo->bdev->driver->move_notify(bo, NULL);
 
-	if (bo->ttm) {
-		ttm_tt_unbind(bo->ttm);
-		ttm_tt_destroy(bo->ttm);
-		bo->ttm = NULL;
-	}
+	ttm_tt_destroy(bo->ttm);
+	bo->ttm = NULL;
 	ttm_bo_mem_put(bo, &bo->mem);
 
 	ww_mutex_unlock (&bo->resv->lock);
@@ -688,15 +684,6 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	struct ttm_placement placement;
 	int ret = 0;
 
-	ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
-
-	if (unlikely(ret != 0)) {
-		if (ret != -ERESTARTSYS) {
-			pr_err("Failed to expire sync object before buffer eviction\n");
-		}
-		goto out;
-	}
-
 	lockdep_assert_held(&bo->resv->lock.base);
 
 	evict_mem = bo->mem;
@@ -720,7 +707,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 
 	ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, interruptible,
 				     no_wait_gpu);
-	if (ret) {
+	if (unlikely(ret)) {
 		if (ret != -ERESTARTSYS)
 			pr_err("Buffer eviction failed\n");
 		ttm_bo_mem_put(bo, &evict_mem);
@@ -800,6 +787,34 @@ void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem)
 EXPORT_SYMBOL(ttm_bo_mem_put);
 
 /**
+ * Add the last move fence to the BO and reserve a new shared slot.
+ */
+static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
+				 struct ttm_mem_type_manager *man,
+				 struct ttm_mem_reg *mem)
+{
+	struct fence *fence;
+	int ret;
+
+	spin_lock(&man->move_lock);
+	fence = fence_get(man->move);
+	spin_unlock(&man->move_lock);
+
+	if (fence) {
+		reservation_object_add_shared_fence(bo->resv, fence);
+
+		ret = reservation_object_reserve_shared(bo->resv);
+		if (unlikely(ret))
+			return ret;
+
+		fence_put(bo->moving);
+		bo->moving = fence;
+	}
+
+	return 0;
+}
+
+/**
  * Repeatedly evict memory from the LRU for @mem_type until we create enough
  * space, or we've evicted everything and there isn't enough space.
  */
@@ -825,10 +840,8 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 		if (unlikely(ret != 0))
 			return ret;
 	} while (1);
-	if (mem->mm_node == NULL)
-		return -ENOMEM;
 	mem->mem_type = mem_type;
-	return 0;
+	return ttm_bo_add_move_fence(bo, man, mem);
 }
 
 static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man,
@@ -898,6 +911,10 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 	bool has_erestartsys = false;
 	int i, ret;
 
+	ret = reservation_object_reserve_shared(bo->resv);
+	if (unlikely(ret))
+		return ret;
+
 	mem->mm_node = NULL;
 	for (i = 0; i < placement->num_placement; ++i) {
 		const struct ttm_place *place = &placement->placement[i];
@@ -931,9 +948,15 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		ret = (*man->func->get_node)(man, bo, place, mem);
 		if (unlikely(ret))
 			return ret;
-		
-		if (mem->mm_node)
+
+		if (mem->mm_node) {
+			ret = ttm_bo_add_move_fence(bo, man, mem);
+			if (unlikely(ret)) {
+				(*man->func->put_node)(man, mem);
+				return ret;
+			}
 			break;
+		}
 	}
 
 	if ((type_ok && (mem_type == TTM_PL_SYSTEM)) || mem->mm_node) {
@@ -1000,20 +1023,6 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 
 	lockdep_assert_held(&bo->resv->lock.base);
 
-	/*
-	 * Don't wait for the BO on initial allocation. This is important when
-	 * the BO has an imported reservation object.
-	 */
-	if (bo->mem.mem_type != TTM_PL_SYSTEM || bo->ttm != NULL) {
-		/*
-		 * FIXME: It's possible to pipeline buffer moves.
-		 * Have the driver move function wait for idle when necessary,
-		 * instead of doing it here.
-		 */
-		ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
-		if (ret)
-			return ret;
-	}
 	mem.num_pages = bo->num_pages;
 	mem.size = mem.num_pages << PAGE_SHIFT;
 	mem.page_alignment = bo->mem.page_alignment;
@@ -1166,7 +1175,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	bo->mem.page_alignment = page_alignment;
 	bo->mem.bus.io_reserved_vm = false;
 	bo->mem.bus.io_reserved_count = 0;
-	bo->priv_flags = 0;
+	bo->moving = NULL;
 	bo->mem.placement = (TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED);
 	bo->persistent_swap_storage = persistent_swap_storage;
 	bo->acc_size = acc_size;
@@ -1278,6 +1287,7 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
 {
 	struct ttm_mem_type_manager *man = &bdev->man[mem_type];
 	struct ttm_bo_global *glob = bdev->glob;
+	struct fence *fence;
 	int ret;
 
 	/*
@@ -1298,6 +1308,23 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
 		spin_lock(&glob->lru_lock);
 	}
 	spin_unlock(&glob->lru_lock);
+
+	spin_lock(&man->move_lock);
+	fence = fence_get(man->move);
+	spin_unlock(&man->move_lock);
+
+	if (fence) {
+		ret = fence_wait(fence, false);
+		fence_put(fence);
+		if (ret) {
+			if (allow_errors) {
+				return ret;
+			} else {
+				pr_err("Cleanup eviction failed\n");
+			}
+		}
+	}
+
 	return 0;
 }
 
@@ -1317,6 +1344,7 @@ int ttm_bo_clean_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 		       mem_type);
 		return ret;
 	}
+	fence_put(man->move);
 
 	man->use_type = false;
 	man->has_type = false;
@@ -1362,6 +1390,7 @@ int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type,
 	man->io_reserve_fastpath = true;
 	man->use_io_reserve_lru = false;
 	mutex_init(&man->io_reserve_mutex);
+	spin_lock_init(&man->move_lock);
 	INIT_LIST_HEAD(&man->io_reserve_lru);
 
 	ret = bdev->driver->init_mem_type(bdev, type, man);
@@ -1380,6 +1409,7 @@ int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type,
 	man->size = p_size;
 
 	INIT_LIST_HEAD(&man->lru);
+	man->move = NULL;
 
 	return 0;
 }
@@ -1573,47 +1603,17 @@ EXPORT_SYMBOL(ttm_bo_unmap_virtual);
 int ttm_bo_wait(struct ttm_buffer_object *bo,
 		bool interruptible, bool no_wait)
 {
-	struct reservation_object_list *fobj;
-	struct reservation_object *resv;
-	struct fence *excl;
-	long timeout = 15 * HZ;
-	int i;
-
-	resv = bo->resv;
-	fobj = reservation_object_get_list(resv);
-	excl = reservation_object_get_excl(resv);
-	if (excl) {
-		if (!fence_is_signaled(excl)) {
-			if (no_wait)
-				return -EBUSY;
-
-			timeout = fence_wait_timeout(excl,
-						     interruptible, timeout);
-		}
-	}
-
-	for (i = 0; fobj && timeout > 0 && i < fobj->shared_count; ++i) {
-		struct fence *fence;
-		fence = rcu_dereference_protected(fobj->shared[i],
-						reservation_object_held(resv));
-
-		if (!fence_is_signaled(fence)) {
-			if (no_wait)
-				return -EBUSY;
-
-			timeout = fence_wait_timeout(fence,
-						     interruptible, timeout);
-		}
-	}
+	long timeout = no_wait ? 0 : 15 * HZ;
 
+	timeout = reservation_object_wait_timeout_rcu(bo->resv, true,
+						      interruptible, timeout);
 	if (timeout < 0)
 		return timeout;
 
 	if (timeout == 0)
 		return -EBUSY;
 
-	reservation_object_add_excl_fence(resv, NULL);
-	clear_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
+	reservation_object_add_excl_fence(bo->resv, NULL);
 	return 0;
 }
 EXPORT_SYMBOL(ttm_bo_wait);
@@ -1683,14 +1683,9 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 	ttm_bo_list_ref_sub(bo, put_count, true);
 
 	/**
-	 * Wait for GPU, then move to system cached.
+	 * Move to system cached
 	 */
 
-	ret = ttm_bo_wait(bo, false, false);
-
-	if (unlikely(ret != 0))
-		goto out;
-
 	if ((bo->mem.placement & swap_placement) != swap_placement) {
 		struct ttm_mem_reg evict_mem;
 
@@ -1705,6 +1700,14 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 			goto out;
 	}
 
+	/**
+	 * Make sure BO is idle.
+	 */
+
+	ret = ttm_bo_wait(bo, false, false);
+	if (unlikely(ret != 0))
+		goto out;
+
 	ttm_bo_unmap_virtual(bo);
 
 	/**
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index d9831559706e..2df602a35f92 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -321,7 +321,8 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst,
 }
 
 int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
-		       bool evict, bool no_wait_gpu,
+		       bool evict, bool interruptible,
+		       bool no_wait_gpu,
 		       struct ttm_mem_reg *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
@@ -337,6 +338,10 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 	unsigned long add = 0;
 	int dir;
 
+	ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
+	if (ret)
+		return ret;
+
 	ret = ttm_mem_reg_ioremap(bdev, old_mem, &old_iomap);
 	if (ret)
 		return ret;
@@ -401,8 +406,7 @@ out2:
 	*old_mem = *new_mem;
 	new_mem->mm_node = NULL;
 
-	if ((man->flags & TTM_MEMTYPE_FLAG_FIXED) && (ttm != NULL)) {
-		ttm_tt_unbind(ttm);
+	if (man->flags & TTM_MEMTYPE_FLAG_FIXED) {
 		ttm_tt_destroy(ttm);
 		bo->ttm = NULL;
 	}
@@ -462,6 +466,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	INIT_LIST_HEAD(&fbo->lru);
 	INIT_LIST_HEAD(&fbo->swap);
 	INIT_LIST_HEAD(&fbo->io_reserve_lru);
+	fbo->moving = NULL;
 	drm_vma_node_reset(&fbo->vma_node);
 	atomic_set(&fbo->cpu_writers, 0);
 
@@ -634,7 +639,6 @@ EXPORT_SYMBOL(ttm_bo_kunmap);
 int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			      struct fence *fence,
 			      bool evict,
-			      bool no_wait_gpu,
 			      struct ttm_mem_reg *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
@@ -649,9 +653,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		if ((man->flags & TTM_MEMTYPE_FLAG_FIXED) &&
-		    (bo->ttm != NULL)) {
-			ttm_tt_unbind(bo->ttm);
+		if (man->flags & TTM_MEMTYPE_FLAG_FIXED) {
 			ttm_tt_destroy(bo->ttm);
 			bo->ttm = NULL;
 		}
@@ -665,7 +667,8 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		 * operation has completed.
 		 */
 
-		set_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
+		fence_put(bo->moving);
+		bo->moving = fence_get(fence);
 
 		ret = ttm_buffer_object_transfer(bo, &ghost_obj);
 		if (ret)
@@ -694,3 +697,95 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 	return 0;
 }
 EXPORT_SYMBOL(ttm_bo_move_accel_cleanup);
+
+int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
+			 struct fence *fence, bool evict,
+			 struct ttm_mem_reg *new_mem)
+{
+	struct ttm_bo_device *bdev = bo->bdev;
+	struct ttm_mem_reg *old_mem = &bo->mem;
+
+	struct ttm_mem_type_manager *from = &bdev->man[old_mem->mem_type];
+	struct ttm_mem_type_manager *to = &bdev->man[new_mem->mem_type];
+
+	int ret;
+
+	reservation_object_add_excl_fence(bo->resv, fence);
+
+	if (!evict) {
+		struct ttm_buffer_object *ghost_obj;
+
+		/**
+		 * This should help pipeline ordinary buffer moves.
+		 *
+		 * Hang old buffer memory on a new buffer object,
+		 * and leave it to be released when the GPU
+		 * operation has completed.
+		 */
+
+		fence_put(bo->moving);
+		bo->moving = fence_get(fence);
+
+		ret = ttm_buffer_object_transfer(bo, &ghost_obj);
+		if (ret)
+			return ret;
+
+		reservation_object_add_excl_fence(ghost_obj->resv, fence);
+
+		/**
+		 * If we're not moving to fixed memory, the TTM object
+		 * needs to stay alive. Otherwhise hang it on the ghost
+		 * bo to be unbound and destroyed.
+		 */
+
+		if (!(to->flags & TTM_MEMTYPE_FLAG_FIXED))
+			ghost_obj->ttm = NULL;
+		else
+			bo->ttm = NULL;
+
+		ttm_bo_unreserve(ghost_obj);
+		ttm_bo_unref(&ghost_obj);
+
+	} else if (from->flags & TTM_MEMTYPE_FLAG_FIXED) {
+
+		/**
+		 * BO doesn't have a TTM we need to bind/unbind. Just remember
+		 * this eviction and free up the allocation
+		 */
+
+		spin_lock(&from->move_lock);
+		if (!from->move || fence_is_later(fence, from->move)) {
+			fence_put(from->move);
+			from->move = fence_get(fence);
+		}
+		spin_unlock(&from->move_lock);
+
+		ttm_bo_free_old_node(bo);
+
+		fence_put(bo->moving);
+		bo->moving = fence_get(fence);
+
+	} else {
+		/**
+		 * Last resort, wait for the move to be completed.
+		 *
+		 * Should never happen in pratice.
+		 */
+
+		ret = ttm_bo_wait(bo, false, false);
+		if (ret)
+			return ret;
+
+		if (to->flags & TTM_MEMTYPE_FLAG_FIXED) {
+			ttm_tt_destroy(bo->ttm);
+			bo->ttm = NULL;
+		}
+		ttm_bo_free_old_node(bo);
+	}
+
+	*old_mem = *new_mem;
+	new_mem->mm_node = NULL;
+
+	return 0;
+}
+EXPORT_SYMBOL(ttm_bo_pipeline_move);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 3216878bced3..a6ed9d5e5167 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -48,15 +48,14 @@ static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 {
 	int ret = 0;
 
-	if (likely(!test_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags)))
+	if (likely(!bo->moving))
 		goto out_unlock;
 
 	/*
 	 * Quick non-stalling check for idle.
 	 */
-	ret = ttm_bo_wait(bo, false, true);
-	if (likely(ret == 0))
-		goto out_unlock;
+	if (fence_is_signaled(bo->moving))
+		goto out_clear;
 
 	/*
 	 * If possible, avoid waiting for GPU with mmap_sem
@@ -68,17 +67,23 @@ static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 			goto out_unlock;
 
 		up_read(&vma->vm_mm->mmap_sem);
-		(void) ttm_bo_wait(bo, true, false);
+		(void) fence_wait(bo->moving, true);
 		goto out_unlock;
 	}
 
 	/*
 	 * Ordinary wait.
 	 */
-	ret = ttm_bo_wait(bo, true, false);
-	if (unlikely(ret != 0))
+	ret = fence_wait(bo->moving, true);
+	if (unlikely(ret != 0)) {
 		ret = (ret != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
 			VM_FAULT_NOPAGE;
+		goto out_unlock;
+	}
+
+out_clear:
+	fence_put(bo->moving);
+	bo->moving = NULL;
 
 out_unlock:
 	return ret;
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 97542c35d6ef..bc5aa573f466 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -166,12 +166,10 @@ EXPORT_SYMBOL(ttm_tt_set_placement_caching);
 
 void ttm_tt_destroy(struct ttm_tt *ttm)
 {
-	if (unlikely(ttm == NULL))
+	if (ttm == NULL)
 		return;
 
-	if (ttm->state == tt_bound) {
-		ttm_tt_unbind(ttm);
-	}
+	ttm_tt_unbind(ttm);
 
 	if (ttm->state == tt_unbound)
 		ttm_tt_unpopulate(ttm);
diff --git a/drivers/gpu/drm/udl/Kconfig b/drivers/gpu/drm/udl/Kconfig
index 613ab0622d6e..1616ec4f4d84 100644
--- a/drivers/gpu/drm/udl/Kconfig
+++ b/drivers/gpu/drm/udl/Kconfig
@@ -4,12 +4,7 @@ config DRM_UDL
 	depends on USB_SUPPORT
 	depends on USB_ARCH_HAS_HCD
 	select USB
-	select FB_SYS_FILLRECT
-	select FB_SYS_COPYAREA
-	select FB_SYS_IMAGEBLIT
-	select FB_DEFERRED_IO
 	select DRM_KMS_HELPER
-        select DRM_KMS_FB_HELPER
 	help
 	  This is a KMS driver for the USB displaylink video adapters.
           Say M/Y to add support for these devices via drm/kms interfaces.
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index c20408940cd0..17d34e0edbdd 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -94,7 +94,6 @@ static void udl_usb_disconnect(struct usb_interface *interface)
 	struct drm_device *dev = usb_get_intfdata(interface);
 
 	drm_kms_helper_poll_disable(dev);
-	drm_connector_unregister_all(dev);
 	udl_fbdev_unplug(dev);
 	udl_drop_usb(dev);
 	drm_unplug_dev(dev);
diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c
index b87afee44995..f92ea9579674 100644
--- a/drivers/gpu/drm/udl/udl_modeset.c
+++ b/drivers/gpu/drm/udl/udl_modeset.c
@@ -376,7 +376,7 @@ static int udl_crtc_page_flip(struct drm_crtc *crtc,
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 	if (event)
-		drm_send_vblank_event(dev, 0, event);
+		drm_crtc_send_vblank_event(crtc, event);
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 	crtc->primary->fb = fb;
 
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index e5a9d3aaf45f..59adcf8532dd 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -291,8 +291,6 @@ static void vc4_bo_cache_free_old(struct drm_device *dev)
 
 /* Called on the last userspace/kernel unreference of the BO.  Returns
  * it to the BO cache if possible, otherwise frees it.
- *
- * Note that this is called with the struct_mutex held.
  */
 void vc4_free_object(struct drm_gem_object *gem_bo)
 {
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 0f18b76c7906..8fc2b731b59a 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -46,12 +46,17 @@ struct vc4_crtc {
 	const struct vc4_crtc_data *data;
 	void __iomem *regs;
 
+	/* Timestamp at start of vblank irq - unaffected by lock delays. */
+	ktime_t t_vblank;
+
 	/* Which HVS channel we're using for our CRTC. */
 	int channel;
 
 	u8 lut_r[256];
 	u8 lut_g[256];
 	u8 lut_b[256];
+	/* Size in pixels of the COB memory allocated to this CRTC. */
+	u32 cob_size;
 
 	struct drm_pending_vblank_event *event;
 };
@@ -146,6 +151,144 @@ int vc4_crtc_debugfs_regs(struct seq_file *m, void *unused)
 }
 #endif
 
+int vc4_crtc_get_scanoutpos(struct drm_device *dev, unsigned int crtc_id,
+			    unsigned int flags, int *vpos, int *hpos,
+			    ktime_t *stime, ktime_t *etime,
+			    const struct drm_display_mode *mode)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_crtc *vc4_crtc = vc4->crtc[crtc_id];
+	u32 val;
+	int fifo_lines;
+	int vblank_lines;
+	int ret = 0;
+
+	/*
+	 * XXX Doesn't work well in interlaced mode yet, partially due
+	 * to problems in vc4 kms or drm core interlaced mode handling,
+	 * so disable for now in interlaced mode.
+	 */
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		return ret;
+
+	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+
+	/* Get optional system timestamp before query. */
+	if (stime)
+		*stime = ktime_get();
+
+	/*
+	 * Read vertical scanline which is currently composed for our
+	 * pixelvalve by the HVS, and also the scaler status.
+	 */
+	val = HVS_READ(SCALER_DISPSTATX(vc4_crtc->channel));
+
+	/* Get optional system timestamp after query. */
+	if (etime)
+		*etime = ktime_get();
+
+	/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+
+	/* Vertical position of hvs composed scanline. */
+	*vpos = VC4_GET_FIELD(val, SCALER_DISPSTATX_LINE);
+
+	/* No hpos info available. */
+	if (hpos)
+		*hpos = 0;
+
+	/* This is the offset we need for translating hvs -> pv scanout pos. */
+	fifo_lines = vc4_crtc->cob_size / mode->crtc_hdisplay;
+
+	if (fifo_lines > 0)
+		ret |= DRM_SCANOUTPOS_VALID;
+
+	/* HVS more than fifo_lines into frame for compositing? */
+	if (*vpos > fifo_lines) {
+		/*
+		 * We are in active scanout and can get some meaningful results
+		 * from HVS. The actual PV scanout can not trail behind more
+		 * than fifo_lines as that is the fifo's capacity. Assume that
+		 * in active scanout the HVS and PV work in lockstep wrt. HVS
+		 * refilling the fifo and PV consuming from the fifo, ie.
+		 * whenever the PV consumes and frees up a scanline in the
+		 * fifo, the HVS will immediately refill it, therefore
+		 * incrementing vpos. Therefore we choose HVS read position -
+		 * fifo size in scanlines as a estimate of the real scanout
+		 * position of the PV.
+		 */
+		*vpos -= fifo_lines + 1;
+		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+			*vpos /= 2;
+
+		ret |= DRM_SCANOUTPOS_ACCURATE;
+		return ret;
+	}
+
+	/*
+	 * Less: This happens when we are in vblank and the HVS, after getting
+	 * the VSTART restart signal from the PV, just started refilling its
+	 * fifo with new lines from the top-most lines of the new framebuffers.
+	 * The PV does not scan out in vblank, so does not remove lines from
+	 * the fifo, so the fifo will be full quickly and the HVS has to pause.
+	 * We can't get meaningful readings wrt. scanline position of the PV
+	 * and need to make things up in a approximative but consistent way.
+	 */
+	ret |= DRM_SCANOUTPOS_IN_VBLANK;
+	vblank_lines = mode->crtc_vtotal - mode->crtc_vdisplay;
+
+	if (flags & DRM_CALLED_FROM_VBLIRQ) {
+		/*
+		 * Assume the irq handler got called close to first
+		 * line of vblank, so PV has about a full vblank
+		 * scanlines to go, and as a base timestamp use the
+		 * one taken at entry into vblank irq handler, so it
+		 * is not affected by random delays due to lock
+		 * contention on event_lock or vblank_time lock in
+		 * the core.
+		 */
+		*vpos = -vblank_lines;
+
+		if (stime)
+			*stime = vc4_crtc->t_vblank;
+		if (etime)
+			*etime = vc4_crtc->t_vblank;
+
+		/*
+		 * If the HVS fifo is not yet full then we know for certain
+		 * we are at the very beginning of vblank, as the hvs just
+		 * started refilling, and the stime and etime timestamps
+		 * truly correspond to start of vblank.
+		 */
+		if ((val & SCALER_DISPSTATX_FULL) != SCALER_DISPSTATX_FULL)
+			ret |= DRM_SCANOUTPOS_ACCURATE;
+	} else {
+		/*
+		 * No clue where we are inside vblank. Return a vpos of zero,
+		 * which will cause calling code to just return the etime
+		 * timestamp uncorrected. At least this is no worse than the
+		 * standard fallback.
+		 */
+		*vpos = 0;
+	}
+
+	return ret;
+}
+
+int vc4_crtc_get_vblank_timestamp(struct drm_device *dev, unsigned int crtc_id,
+				  int *max_error, struct timeval *vblank_time,
+				  unsigned flags)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_crtc *vc4_crtc = vc4->crtc[crtc_id];
+	struct drm_crtc *crtc = &vc4_crtc->base;
+	struct drm_crtc_state *state = crtc->state;
+
+	/* Helper routine in DRM core does all the work: */
+	return drm_calc_vbltimestamp_from_scanoutpos(dev, crtc_id, max_error,
+						     vblank_time, flags,
+						     &state->adjusted_mode);
+}
+
 static void vc4_crtc_destroy(struct drm_crtc *crtc)
 {
 	drm_crtc_cleanup(crtc);
@@ -175,20 +318,22 @@ vc4_crtc_lut_load(struct drm_crtc *crtc)
 		HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_b[i]);
 }
 
-static void
+static int
 vc4_crtc_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
-		   uint32_t start, uint32_t size)
+		   uint32_t size)
 {
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
 	u32 i;
 
-	for (i = start; i < start + size; i++) {
+	for (i = 0; i < size; i++) {
 		vc4_crtc->lut_r[i] = r[i] >> 8;
 		vc4_crtc->lut_g[i] = g[i] >> 8;
 		vc4_crtc->lut_b[i] = b[i] >> 8;
 	}
 
 	vc4_crtc_lut_load(crtc);
+
+	return 0;
 }
 
 static u32 vc4_get_fifo_full_level(u32 format)
@@ -395,6 +540,7 @@ static int vc4_crtc_atomic_check(struct drm_crtc *crtc,
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_plane *plane;
 	unsigned long flags;
+	const struct drm_plane_state *plane_state;
 	u32 dlist_count = 0;
 	int ret;
 
@@ -404,18 +550,8 @@ static int vc4_crtc_atomic_check(struct drm_crtc *crtc,
 	if (hweight32(state->connector_mask) > 1)
 		return -EINVAL;
 
-	drm_atomic_crtc_state_for_each_plane(plane, state) {
-		struct drm_plane_state *plane_state =
-			state->state->plane_states[drm_plane_index(plane)];
-
-		/* plane might not have changed, in which case take
-		 * current state:
-		 */
-		if (!plane_state)
-			plane_state = plane->state;
-
+	drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, state)
 		dlist_count += vc4_plane_dlist_size(plane_state);
-	}
 
 	dlist_count++; /* Account for SCALER_CTL0_END. */
 
@@ -526,6 +662,7 @@ static irqreturn_t vc4_crtc_irq_handler(int irq, void *data)
 	irqreturn_t ret = IRQ_NONE;
 
 	if (stat & PV_INT_VFP_START) {
+		vc4_crtc->t_vblank = ktime_get();
 		CRTC_WRITE(PV_INTSTAT, PV_INT_VFP_START);
 		drm_crtc_handle_vblank(&vc4_crtc->base);
 		vc4_crtc_handle_page_flip(vc4_crtc);
@@ -730,6 +867,22 @@ static void vc4_set_crtc_possible_masks(struct drm_device *drm,
 	}
 }
 
+static void
+vc4_crtc_get_cob_allocation(struct vc4_crtc *vc4_crtc)
+{
+	struct drm_device *drm = vc4_crtc->base.dev;
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	u32 dispbase = HVS_READ(SCALER_DISPBASEX(vc4_crtc->channel));
+	/* Top/base are supposed to be 4-pixel aligned, but the
+	 * Raspberry Pi firmware fills the low bits (which are
+	 * presumably ignored).
+	 */
+	u32 top = VC4_GET_FIELD(dispbase, SCALER_DISPBASEX_TOP) & ~3;
+	u32 base = VC4_GET_FIELD(dispbase, SCALER_DISPBASEX_BASE) & ~3;
+
+	vc4_crtc->cob_size = top - base + 4;
+}
+
 static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -806,6 +959,8 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 		crtc->cursor = cursor_plane;
 	}
 
+	vc4_crtc_get_cob_allocation(vc4_crtc);
+
 	CRTC_WRITE(PV_INTEN, 0);
 	CRTC_WRITE(PV_INTSTAT, PV_INT_VFP_START);
 	ret = devm_request_irq(dev, platform_get_irq(pdev, 0),
diff --git a/drivers/gpu/drm/vc4/vc4_dpi.c b/drivers/gpu/drm/vc4/vc4_dpi.c
index 9817dbfa4ac3..275fedbdbd9e 100644
--- a/drivers/gpu/drm/vc4/vc4_dpi.c
+++ b/drivers/gpu/drm/vc4/vc4_dpi.c
@@ -208,14 +208,6 @@ static int vc4_dpi_connector_get_modes(struct drm_connector *connector)
 	return 0;
 }
 
-static struct drm_encoder *
-vc4_dpi_connector_best_encoder(struct drm_connector *connector)
-{
-	struct vc4_dpi_connector *dpi_connector =
-		to_vc4_dpi_connector(connector);
-	return dpi_connector->encoder;
-}
-
 static const struct drm_connector_funcs vc4_dpi_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.detect = vc4_dpi_connector_detect,
@@ -228,7 +220,6 @@ static const struct drm_connector_funcs vc4_dpi_connector_funcs = {
 
 static const struct drm_connector_helper_funcs vc4_dpi_connector_helper_funcs = {
 	.get_modes = vc4_dpi_connector_get_modes,
-	.best_encoder = vc4_dpi_connector_best_encoder,
 };
 
 static struct drm_connector *vc4_dpi_connector_init(struct drm_device *dev,
@@ -236,14 +227,12 @@ static struct drm_connector *vc4_dpi_connector_init(struct drm_device *dev,
 {
 	struct drm_connector *connector = NULL;
 	struct vc4_dpi_connector *dpi_connector;
-	int ret = 0;
 
 	dpi_connector = devm_kzalloc(dev->dev, sizeof(*dpi_connector),
 				     GFP_KERNEL);
-	if (!dpi_connector) {
-		ret = -ENOMEM;
-		goto fail;
-	}
+	if (!dpi_connector)
+		return ERR_PTR(-ENOMEM);
+
 	connector = &dpi_connector->base;
 
 	dpi_connector->encoder = dpi->encoder;
@@ -260,12 +249,6 @@ static struct drm_connector *vc4_dpi_connector_init(struct drm_device *dev,
 	drm_mode_connector_attach_encoder(connector, dpi->encoder);
 
 	return connector;
-
- fail:
-	if (connector)
-		vc4_dpi_connector_destroy(connector);
-
-	return ERR_PTR(ret);
 }
 
 static const struct drm_encoder_funcs vc4_dpi_encoder_funcs = {
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 250ed7e3754c..8b42d31a7f0e 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include "drm_fb_cma_helper.h"
 
 #include "uapi/drm/vc4_drm.h"
@@ -43,12 +44,54 @@ void __iomem *vc4_ioremap_regs(struct platform_device *dev, int index)
 	return map;
 }
 
+static int vc4_get_param_ioctl(struct drm_device *dev, void *data,
+			       struct drm_file *file_priv)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct drm_vc4_get_param *args = data;
+	int ret;
+
+	if (args->pad != 0)
+		return -EINVAL;
+
+	switch (args->param) {
+	case DRM_VC4_PARAM_V3D_IDENT0:
+		ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
+		if (ret)
+			return ret;
+		args->value = V3D_READ(V3D_IDENT0);
+		pm_runtime_put(&vc4->v3d->pdev->dev);
+		break;
+	case DRM_VC4_PARAM_V3D_IDENT1:
+		ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
+		if (ret)
+			return ret;
+		args->value = V3D_READ(V3D_IDENT1);
+		pm_runtime_put(&vc4->v3d->pdev->dev);
+		break;
+	case DRM_VC4_PARAM_V3D_IDENT2:
+		ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
+		if (ret)
+			return ret;
+		args->value = V3D_READ(V3D_IDENT2);
+		pm_runtime_put(&vc4->v3d->pdev->dev);
+		break;
+	case DRM_VC4_PARAM_SUPPORTS_BRANCHES:
+		args->value = true;
+		break;
+	default:
+		DRM_DEBUG("Unknown parameter %d\n", args->param);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void vc4_lastclose(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
-	if (vc4->fbdev)
-		drm_fbdev_cma_restore_mode(vc4->fbdev);
+	drm_fbdev_cma_restore_mode(vc4->fbdev);
 }
 
 static const struct file_operations vc4_drm_fops = {
@@ -74,6 +117,7 @@ static const struct drm_ioctl_desc vc4_drm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(VC4_CREATE_SHADER_BO, vc4_create_shader_bo_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(VC4_GET_HANG_STATE, vc4_get_hang_state_ioctl,
 			  DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(VC4_GET_PARAM, vc4_get_param_ioctl, DRM_RENDER_ALLOW),
 };
 
 static struct drm_driver vc4_drm_driver = {
@@ -92,6 +136,8 @@ static struct drm_driver vc4_drm_driver = {
 	.enable_vblank = vc4_enable_vblank,
 	.disable_vblank = vc4_disable_vblank,
 	.get_vblank_counter = drm_vblank_no_hw_counter,
+	.get_scanout_position = vc4_crtc_get_scanoutpos,
+	.get_vblank_timestamp = vc4_crtc_get_vblank_timestamp,
 
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = vc4_debugfs_init,
@@ -99,7 +145,7 @@ static struct drm_driver vc4_drm_driver = {
 #endif
 
 	.gem_create_object = vc4_create_object,
-	.gem_free_object = vc4_free_object,
+	.gem_free_object_unlocked = vc4_free_object,
 	.gem_vm_ops = &drm_gem_cma_vm_ops,
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
@@ -176,7 +222,6 @@ static int vc4_drm_bind(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct drm_device *drm;
-	struct drm_connector *connector;
 	struct vc4_dev *vc4;
 	int ret = 0;
 
@@ -196,8 +241,6 @@ static int vc4_drm_bind(struct device *dev)
 	vc4_bo_cache_init(drm);
 
 	drm_mode_config_init(drm);
-	if (ret)
-		goto unref;
 
 	vc4_gem_init(drm);
 
@@ -211,27 +254,14 @@ static int vc4_drm_bind(struct device *dev)
 	if (ret < 0)
 		goto unbind_all;
 
-	/* Connector registration has to occur after DRM device
-	 * registration, because it creates sysfs entries based on the
-	 * DRM device.
-	 */
-	list_for_each_entry(connector, &drm->mode_config.connector_list, head) {
-		ret = drm_connector_register(connector);
-		if (ret)
-			goto unregister;
-	}
-
 	vc4_kms_load(drm);
 
 	return 0;
 
-unregister:
-	drm_dev_unregister(drm);
 unbind_all:
 	component_unbind_all(dev, drm);
 gem_destroy:
 	vc4_gem_destroy(drm);
-unref:
 	drm_dev_unref(drm);
 	vc4_bo_cache_destroy(drm);
 	return ret;
@@ -259,8 +289,8 @@ static const struct component_master_ops vc4_drm_ops = {
 static struct platform_driver *const component_drivers[] = {
 	&vc4_hdmi_driver,
 	&vc4_dpi_driver,
-	&vc4_crtc_driver,
 	&vc4_hvs_driver,
+	&vc4_crtc_driver,
 	&vc4_v3d_driver,
 };
 
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 37cac59401d7..489e3de0c050 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -355,6 +355,9 @@ struct vc4_validated_shader_info {
 	uint32_t uniforms_src_size;
 	uint32_t num_texture_samples;
 	struct vc4_texture_sample_info *texture_samples;
+
+	uint32_t num_uniform_addr_offsets;
+	uint32_t *uniform_addr_offsets;
 };
 
 /**
@@ -415,6 +418,13 @@ extern struct platform_driver vc4_crtc_driver;
 int vc4_enable_vblank(struct drm_device *dev, unsigned int crtc_id);
 void vc4_disable_vblank(struct drm_device *dev, unsigned int crtc_id);
 int vc4_crtc_debugfs_regs(struct seq_file *m, void *arg);
+int vc4_crtc_get_scanoutpos(struct drm_device *dev, unsigned int crtc_id,
+			    unsigned int flags, int *vpos, int *hpos,
+			    ktime_t *stime, ktime_t *etime,
+			    const struct drm_display_mode *mode);
+int vc4_crtc_get_vblank_timestamp(struct drm_device *dev, unsigned int crtc_id,
+				  int *max_error, struct timeval *vblank_time,
+				  unsigned flags);
 
 /* vc4_debugfs.c */
 int vc4_debugfs_init(struct drm_minor *minor);
@@ -469,7 +479,7 @@ int vc4_kms_load(struct drm_device *dev);
 struct drm_plane *vc4_plane_init(struct drm_device *dev,
 				 enum drm_plane_type type);
 u32 vc4_plane_write_dlist(struct drm_plane *plane, u32 __iomem *dlist);
-u32 vc4_plane_dlist_size(struct drm_plane_state *state);
+u32 vc4_plane_dlist_size(const struct drm_plane_state *state);
 void vc4_plane_async_set_fb(struct drm_plane *plane,
 			    struct drm_framebuffer *fb);
 
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 46899d6de675..6155e8aca1c6 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -53,10 +53,8 @@ vc4_free_hang_state(struct drm_device *dev, struct vc4_hang_state *state)
 {
 	unsigned int i;
 
-	mutex_lock(&dev->struct_mutex);
 	for (i = 0; i < state->user_state.bo_count; i++)
-		drm_gem_object_unreference(state->bo[i]);
-	mutex_unlock(&dev->struct_mutex);
+		drm_gem_object_unreference_unlocked(state->bo[i]);
 
 	kfree(state);
 }
@@ -687,11 +685,9 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	unsigned i;
 
-	/* Need the struct lock for drm_gem_object_unreference(). */
-	mutex_lock(&dev->struct_mutex);
 	if (exec->bo) {
 		for (i = 0; i < exec->bo_count; i++)
-			drm_gem_object_unreference(&exec->bo[i]->base);
+			drm_gem_object_unreference_unlocked(&exec->bo[i]->base);
 		kfree(exec->bo);
 	}
 
@@ -699,9 +695,8 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 		struct vc4_bo *bo = list_first_entry(&exec->unref_list,
 						     struct vc4_bo, unref_head);
 		list_del(&bo->unref_head);
-		drm_gem_object_unreference(&bo->base.base);
+		drm_gem_object_unreference_unlocked(&bo->base.base);
 	}
-	mutex_unlock(&dev->struct_mutex);
 
 	mutex_lock(&vc4->power_lock);
 	if (--vc4->power_refcount == 0)
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index fd2644d231ff..4452f3631cac 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -208,14 +208,6 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector)
 	return ret;
 }
 
-static struct drm_encoder *
-vc4_hdmi_connector_best_encoder(struct drm_connector *connector)
-{
-	struct vc4_hdmi_connector *hdmi_connector =
-		to_vc4_hdmi_connector(connector);
-	return hdmi_connector->encoder;
-}
-
 static const struct drm_connector_funcs vc4_hdmi_connector_funcs = {
 	.dpms = drm_atomic_helper_connector_dpms,
 	.detect = vc4_hdmi_connector_detect,
@@ -228,7 +220,6 @@ static const struct drm_connector_funcs vc4_hdmi_connector_funcs = {
 
 static const struct drm_connector_helper_funcs vc4_hdmi_connector_helper_funcs = {
 	.get_modes = vc4_hdmi_connector_get_modes,
-	.best_encoder = vc4_hdmi_connector_best_encoder,
 };
 
 static struct drm_connector *vc4_hdmi_connector_init(struct drm_device *dev,
@@ -465,12 +456,6 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 	if (IS_ERR(hdmi->hd_regs))
 		return PTR_ERR(hdmi->hd_regs);
 
-	ddc_node = of_parse_phandle(dev->of_node, "ddc", 0);
-	if (!ddc_node) {
-		DRM_ERROR("Failed to find ddc node in device tree\n");
-		return -ENODEV;
-	}
-
 	hdmi->pixel_clock = devm_clk_get(dev, "pixel");
 	if (IS_ERR(hdmi->pixel_clock)) {
 		DRM_ERROR("Failed to get pixel clock\n");
@@ -482,7 +467,14 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 		return PTR_ERR(hdmi->hsm_clock);
 	}
 
+	ddc_node = of_parse_phandle(dev->of_node, "ddc", 0);
+	if (!ddc_node) {
+		DRM_ERROR("Failed to find ddc node in device tree\n");
+		return -ENODEV;
+	}
+
 	hdmi->ddc = of_find_i2c_adapter_by_node(ddc_node);
+	of_node_put(ddc_node);
 	if (!hdmi->ddc) {
 		DRM_DEBUG("Failed to get ddc i2c adapter by node\n");
 		return -EPROBE_DEFER;
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index 861a623bc185..4ac894d993cd 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -26,8 +26,7 @@ static void vc4_output_poll_changed(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
-	if (vc4->fbdev)
-		drm_fbdev_cma_hotplug_event(vc4->fbdev);
+	drm_fbdev_cma_hotplug_event(vc4->fbdev);
 }
 
 struct vc4_commit {
@@ -111,6 +110,8 @@ static int vc4_atomic_commit(struct drm_device *dev,
 	int i;
 	uint64_t wait_seqno = 0;
 	struct vc4_commit *c;
+	struct drm_plane *plane;
+	struct drm_plane_state *new_state;
 
 	c = commit_init(state);
 	if (!c)
@@ -138,13 +139,7 @@ static int vc4_atomic_commit(struct drm_device *dev,
 		return ret;
 	}
 
-	for (i = 0; i < dev->mode_config.num_total_plane; i++) {
-		struct drm_plane *plane = state->planes[i];
-		struct drm_plane_state *new_state = state->plane_states[i];
-
-		if (!plane)
-			continue;
-
+	for_each_plane_in_state(state, plane, new_state, i) {
 		if ((plane->state->fb != new_state->fb) && new_state->fb) {
 			struct drm_gem_cma_object *cma_bo =
 				drm_fb_cma_get_gem_obj(new_state->fb, 0);
@@ -160,7 +155,7 @@ static int vc4_atomic_commit(struct drm_device *dev,
 	 * the software side now.
 	 */
 
-	drm_atomic_helper_swap_state(dev, state);
+	drm_atomic_helper_swap_state(state, true);
 
 	/*
 	 * Everything below can be run asynchronously without the need to grab
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 4037b52fde31..29e4b400e25e 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -94,6 +94,14 @@ static const struct hvs_format {
 		.pixel_order = HVS_PIXEL_ORDER_ABGR, .has_alpha = true,
 	},
 	{
+		.drm = DRM_FORMAT_ABGR8888, .hvs = HVS_PIXEL_FORMAT_RGBA8888,
+		.pixel_order = HVS_PIXEL_ORDER_ARGB, .has_alpha = true,
+	},
+	{
+		.drm = DRM_FORMAT_XBGR8888, .hvs = HVS_PIXEL_FORMAT_RGBA8888,
+		.pixel_order = HVS_PIXEL_ORDER_ARGB, .has_alpha = false,
+	},
+	{
 		.drm = DRM_FORMAT_RGB565, .hvs = HVS_PIXEL_FORMAT_RGB565,
 		.pixel_order = HVS_PIXEL_ORDER_XRGB, .has_alpha = false,
 	},
@@ -690,9 +698,10 @@ u32 vc4_plane_write_dlist(struct drm_plane *plane, u32 __iomem *dlist)
 	return vc4_state->dlist_count;
 }
 
-u32 vc4_plane_dlist_size(struct drm_plane_state *state)
+u32 vc4_plane_dlist_size(const struct drm_plane_state *state)
 {
-	struct vc4_plane_state *vc4_state = to_vc4_plane_state(state);
+	const struct vc4_plane_state *vc4_state =
+		container_of(state, typeof(*vc4_state), base);
 
 	return vc4_state->dlist_count;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_qpu_defines.h b/drivers/gpu/drm/vc4/vc4_qpu_defines.h
index d5c2f3c85ebb..f4e795a0d3f6 100644
--- a/drivers/gpu/drm/vc4/vc4_qpu_defines.h
+++ b/drivers/gpu/drm/vc4/vc4_qpu_defines.h
@@ -70,7 +70,7 @@ enum qpu_raddr {
 	QPU_R_ELEM_QPU = 38,
 	QPU_R_NOP,
 	QPU_R_XY_PIXEL_COORD = 41,
-	QPU_R_MS_REV_FLAGS = 41,
+	QPU_R_MS_REV_FLAGS = 42,
 	QPU_R_VPM = 48,
 	QPU_R_VPM_LD_BUSY,
 	QPU_R_VPM_LD_WAIT,
@@ -230,6 +230,15 @@ enum qpu_unpack_r4 {
 #define QPU_COND_MUL_SHIFT              46
 #define QPU_COND_MUL_MASK               QPU_MASK(48, 46)
 
+#define QPU_BRANCH_COND_SHIFT           52
+#define QPU_BRANCH_COND_MASK            QPU_MASK(55, 52)
+
+#define QPU_BRANCH_REL                  ((uint64_t)1 << 51)
+#define QPU_BRANCH_REG                  ((uint64_t)1 << 50)
+
+#define QPU_BRANCH_RADDR_A_SHIFT        45
+#define QPU_BRANCH_RADDR_A_MASK         QPU_MASK(49, 45)
+
 #define QPU_SF                          ((uint64_t)1 << 45)
 
 #define QPU_WADDR_ADD_SHIFT             38
@@ -261,4 +270,10 @@ enum qpu_unpack_r4 {
 #define QPU_OP_ADD_SHIFT                24
 #define QPU_OP_ADD_MASK                 QPU_MASK(28, 24)
 
+#define QPU_LOAD_IMM_SHIFT              0
+#define QPU_LOAD_IMM_MASK               QPU_MASK(31, 0)
+
+#define QPU_BRANCH_TARGET_SHIFT         0
+#define QPU_BRANCH_TARGET_MASK          QPU_MASK(31, 0)
+
 #endif /* VC4_QPU_DEFINES_H */
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index f99eece4cc97..160942a9180e 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -366,7 +366,6 @@
 # define SCALER_DISPBKGND_FILL			BIT(24)
 
 #define SCALER_DISPSTAT0                        0x00000048
-#define SCALER_DISPBASE0                        0x0000004c
 # define SCALER_DISPSTATX_MODE_MASK		VC4_MASK(31, 30)
 # define SCALER_DISPSTATX_MODE_SHIFT		30
 # define SCALER_DISPSTATX_MODE_DISABLED		0
@@ -375,6 +374,24 @@
 # define SCALER_DISPSTATX_MODE_EOF		3
 # define SCALER_DISPSTATX_FULL			BIT(29)
 # define SCALER_DISPSTATX_EMPTY			BIT(28)
+# define SCALER_DISPSTATX_FRAME_COUNT_MASK	VC4_MASK(17, 12)
+# define SCALER_DISPSTATX_FRAME_COUNT_SHIFT	12
+# define SCALER_DISPSTATX_LINE_MASK		VC4_MASK(11, 0)
+# define SCALER_DISPSTATX_LINE_SHIFT		0
+
+#define SCALER_DISPBASE0                        0x0000004c
+/* Last pixel in the COB (display FIFO memory) allocated to this HVS
+ * channel.  Must be 4-pixel aligned (and thus 4 pixels less than the
+ * next COB base).
+ */
+# define SCALER_DISPBASEX_TOP_MASK		VC4_MASK(31, 16)
+# define SCALER_DISPBASEX_TOP_SHIFT		16
+/* First pixel in the COB (display FIFO memory) allocated to this HVS
+ * channel.  Must be 4-pixel aligned.
+ */
+# define SCALER_DISPBASEX_BASE_MASK		VC4_MASK(15, 0)
+# define SCALER_DISPBASEX_BASE_SHIFT		0
+
 #define SCALER_DISPCTRL1                        0x00000050
 #define SCALER_DISPBKGND1                       0x00000054
 #define SCALER_DISPBKGNDX(x)			(SCALER_DISPBKGND0 +        \
@@ -385,6 +402,9 @@
 						 (x) * (SCALER_DISPSTAT1 - \
 							SCALER_DISPSTAT0))
 #define SCALER_DISPBASE1                        0x0000005c
+#define SCALER_DISPBASEX(x)			(SCALER_DISPBASE0 +        \
+						 (x) * (SCALER_DISPBASE1 - \
+							SCALER_DISPBASE0))
 #define SCALER_DISPCTRL2                        0x00000060
 #define SCALER_DISPCTRLX(x)			(SCALER_DISPCTRL0 +        \
 						 (x) * (SCALER_DISPCTRL1 - \
diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c
index 24c2c746e8f3..9ce1d0adf882 100644
--- a/drivers/gpu/drm/vc4/vc4_validate.c
+++ b/drivers/gpu/drm/vc4/vc4_validate.c
@@ -802,7 +802,7 @@ validate_gl_shader_rec(struct drm_device *dev,
 		uint32_t src_offset = *(uint32_t *)(pkt_u + o);
 		uint32_t *texture_handles_u;
 		void *uniform_data_u;
-		uint32_t tex;
+		uint32_t tex, uni;
 
 		*(uint32_t *)(pkt_v + o) = bo[i]->paddr + src_offset;
 
@@ -840,6 +840,17 @@ validate_gl_shader_rec(struct drm_device *dev,
 			}
 		}
 
+		/* Fill in the uniform slots that need this shader's
+		 * start-of-uniforms address (used for resetting the uniform
+		 * stream in the presence of control flow).
+		 */
+		for (uni = 0;
+		     uni < validated_shader->num_uniform_addr_offsets;
+		     uni++) {
+			uint32_t o = validated_shader->uniform_addr_offsets[uni];
+			((uint32_t *)exec->uniforms_v)[o] = exec->uniforms_p;
+		}
+
 		*(uint32_t *)(pkt_v + o + 4) = exec->uniforms_p;
 
 		exec->uniforms_u += validated_shader->uniforms_src_size;
diff --git a/drivers/gpu/drm/vc4/vc4_validate_shaders.c b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
index f67124b4c534..46527e989ce3 100644
--- a/drivers/gpu/drm/vc4/vc4_validate_shaders.c
+++ b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
@@ -39,7 +39,17 @@
 #include "vc4_drv.h"
 #include "vc4_qpu_defines.h"
 
+#define LIVE_REG_COUNT (32 + 32 + 4)
+
 struct vc4_shader_validation_state {
+	/* Current IP being validated. */
+	uint32_t ip;
+
+	/* IP at the end of the BO, do not read shader[max_ip] */
+	uint32_t max_ip;
+
+	uint64_t *shader;
+
 	struct vc4_texture_sample_info tmu_setup[2];
 	int tmu_write_count[2];
 
@@ -49,8 +59,30 @@ struct vc4_shader_validation_state {
 	 *
 	 * This is used for the validation of direct address memory reads.
 	 */
-	uint32_t live_min_clamp_offsets[32 + 32 + 4];
-	bool live_max_clamp_regs[32 + 32 + 4];
+	uint32_t live_min_clamp_offsets[LIVE_REG_COUNT];
+	bool live_max_clamp_regs[LIVE_REG_COUNT];
+	uint32_t live_immediates[LIVE_REG_COUNT];
+
+	/* Bitfield of which IPs are used as branch targets.
+	 *
+	 * Used for validation that the uniform stream is updated at the right
+	 * points and clearing the texturing/clamping state.
+	 */
+	unsigned long *branch_targets;
+
+	/* Set when entering a basic block, and cleared when the uniform
+	 * address update is found.  This is used to make sure that we don't
+	 * read uniforms when the address is undefined.
+	 */
+	bool needs_uniform_address_update;
+
+	/* Set when we find a backwards branch.  If the branch is backwards,
+	 * the taraget is probably doing an address reset to read uniforms,
+	 * and so we need to be sure that a uniforms address is present in the
+	 * stream, even if the shader didn't need to read uniforms in later
+	 * basic blocks.
+	 */
+	bool needs_uniform_address_for_loop;
 };
 
 static uint32_t
@@ -129,11 +161,11 @@ record_texture_sample(struct vc4_validated_shader_info *validated_shader,
 }
 
 static bool
-check_tmu_write(uint64_t inst,
-		struct vc4_validated_shader_info *validated_shader,
+check_tmu_write(struct vc4_validated_shader_info *validated_shader,
 		struct vc4_shader_validation_state *validation_state,
 		bool is_mul)
 {
+	uint64_t inst = validation_state->shader[validation_state->ip];
 	uint32_t waddr = (is_mul ?
 			  QPU_GET_FIELD(inst, QPU_WADDR_MUL) :
 			  QPU_GET_FIELD(inst, QPU_WADDR_ADD));
@@ -162,7 +194,7 @@ check_tmu_write(uint64_t inst,
 			return false;
 		}
 
-		/* We assert that the the clamped address is the first
+		/* We assert that the clamped address is the first
 		 * argument, and the UBO base address is the second argument.
 		 * This is arbitrary, but simpler than supporting flipping the
 		 * two either way.
@@ -212,8 +244,14 @@ check_tmu_write(uint64_t inst,
 	/* Since direct uses a RADDR uniform reference, it will get counted in
 	 * check_instruction_reads()
 	 */
-	if (!is_direct)
+	if (!is_direct) {
+		if (validation_state->needs_uniform_address_update) {
+			DRM_ERROR("Texturing with undefined uniform address\n");
+			return false;
+		}
+
 		validated_shader->uniforms_size += 4;
+	}
 
 	if (submit) {
 		if (!record_texture_sample(validated_shader,
@@ -227,23 +265,138 @@ check_tmu_write(uint64_t inst,
 	return true;
 }
 
+static bool require_uniform_address_uniform(struct vc4_validated_shader_info *validated_shader)
+{
+	uint32_t o = validated_shader->num_uniform_addr_offsets;
+	uint32_t num_uniforms = validated_shader->uniforms_size / 4;
+
+	validated_shader->uniform_addr_offsets =
+		krealloc(validated_shader->uniform_addr_offsets,
+			 (o + 1) *
+			 sizeof(*validated_shader->uniform_addr_offsets),
+			 GFP_KERNEL);
+	if (!validated_shader->uniform_addr_offsets)
+		return false;
+
+	validated_shader->uniform_addr_offsets[o] = num_uniforms;
+	validated_shader->num_uniform_addr_offsets++;
+
+	return true;
+}
+
 static bool
-check_reg_write(uint64_t inst,
-		struct vc4_validated_shader_info *validated_shader,
+validate_uniform_address_write(struct vc4_validated_shader_info *validated_shader,
+			       struct vc4_shader_validation_state *validation_state,
+			       bool is_mul)
+{
+	uint64_t inst = validation_state->shader[validation_state->ip];
+	u32 add_b = QPU_GET_FIELD(inst, QPU_ADD_B);
+	u32 raddr_a = QPU_GET_FIELD(inst, QPU_RADDR_A);
+	u32 raddr_b = QPU_GET_FIELD(inst, QPU_RADDR_B);
+	u32 add_lri = raddr_add_a_to_live_reg_index(inst);
+	/* We want our reset to be pointing at whatever uniform follows the
+	 * uniforms base address.
+	 */
+	u32 expected_offset = validated_shader->uniforms_size + 4;
+
+	/* We only support absolute uniform address changes, and we
+	 * require that they be in the current basic block before any
+	 * of its uniform reads.
+	 *
+	 * One could potentially emit more efficient QPU code, by
+	 * noticing that (say) an if statement does uniform control
+	 * flow for all threads and that the if reads the same number
+	 * of uniforms on each side.  However, this scheme is easy to
+	 * validate so it's all we allow for now.
+	 */
+
+	if (QPU_GET_FIELD(inst, QPU_SIG) != QPU_SIG_NONE) {
+		DRM_ERROR("uniforms address change must be "
+			  "normal math\n");
+		return false;
+	}
+
+	if (is_mul || QPU_GET_FIELD(inst, QPU_OP_ADD) != QPU_A_ADD) {
+		DRM_ERROR("Uniform address reset must be an ADD.\n");
+		return false;
+	}
+
+	if (QPU_GET_FIELD(inst, QPU_COND_ADD) != QPU_COND_ALWAYS) {
+		DRM_ERROR("Uniform address reset must be unconditional.\n");
+		return false;
+	}
+
+	if (QPU_GET_FIELD(inst, QPU_PACK) != QPU_PACK_A_NOP &&
+	    !(inst & QPU_PM)) {
+		DRM_ERROR("No packing allowed on uniforms reset\n");
+		return false;
+	}
+
+	if (add_lri == -1) {
+		DRM_ERROR("First argument of uniform address write must be "
+			  "an immediate value.\n");
+		return false;
+	}
+
+	if (validation_state->live_immediates[add_lri] != expected_offset) {
+		DRM_ERROR("Resetting uniforms with offset %db instead of %db\n",
+			  validation_state->live_immediates[add_lri],
+			  expected_offset);
+		return false;
+	}
+
+	if (!(add_b == QPU_MUX_A && raddr_a == QPU_R_UNIF) &&
+	    !(add_b == QPU_MUX_B && raddr_b == QPU_R_UNIF)) {
+		DRM_ERROR("Second argument of uniform address write must be "
+			  "a uniform.\n");
+		return false;
+	}
+
+	validation_state->needs_uniform_address_update = false;
+	validation_state->needs_uniform_address_for_loop = false;
+	return require_uniform_address_uniform(validated_shader);
+}
+
+static bool
+check_reg_write(struct vc4_validated_shader_info *validated_shader,
 		struct vc4_shader_validation_state *validation_state,
 		bool is_mul)
 {
+	uint64_t inst = validation_state->shader[validation_state->ip];
 	uint32_t waddr = (is_mul ?
 			  QPU_GET_FIELD(inst, QPU_WADDR_MUL) :
 			  QPU_GET_FIELD(inst, QPU_WADDR_ADD));
+	uint32_t sig = QPU_GET_FIELD(inst, QPU_SIG);
+	bool ws = inst & QPU_WS;
+	bool is_b = is_mul ^ ws;
+	u32 lri = waddr_to_live_reg_index(waddr, is_b);
+
+	if (lri != -1) {
+		uint32_t cond_add = QPU_GET_FIELD(inst, QPU_COND_ADD);
+		uint32_t cond_mul = QPU_GET_FIELD(inst, QPU_COND_MUL);
+
+		if (sig == QPU_SIG_LOAD_IMM &&
+		    QPU_GET_FIELD(inst, QPU_PACK) == QPU_PACK_A_NOP &&
+		    ((is_mul && cond_mul == QPU_COND_ALWAYS) ||
+		     (!is_mul && cond_add == QPU_COND_ALWAYS))) {
+			validation_state->live_immediates[lri] =
+				QPU_GET_FIELD(inst, QPU_LOAD_IMM);
+		} else {
+			validation_state->live_immediates[lri] = ~0;
+		}
+	}
 
 	switch (waddr) {
 	case QPU_W_UNIFORMS_ADDRESS:
-		/* XXX: We'll probably need to support this for reladdr, but
-		 * it's definitely a security-related one.
-		 */
-		DRM_ERROR("uniforms address load unsupported\n");
-		return false;
+		if (is_b) {
+			DRM_ERROR("relative uniforms address change "
+				  "unsupported\n");
+			return false;
+		}
+
+		return validate_uniform_address_write(validated_shader,
+						      validation_state,
+						      is_mul);
 
 	case QPU_W_TLB_COLOR_MS:
 	case QPU_W_TLB_COLOR_ALL:
@@ -261,7 +414,7 @@ check_reg_write(uint64_t inst,
 	case QPU_W_TMU1_T:
 	case QPU_W_TMU1_R:
 	case QPU_W_TMU1_B:
-		return check_tmu_write(inst, validated_shader, validation_state,
+		return check_tmu_write(validated_shader, validation_state,
 				       is_mul);
 
 	case QPU_W_HOST_INT:
@@ -294,10 +447,10 @@ check_reg_write(uint64_t inst,
 }
 
 static void
-track_live_clamps(uint64_t inst,
-		  struct vc4_validated_shader_info *validated_shader,
+track_live_clamps(struct vc4_validated_shader_info *validated_shader,
 		  struct vc4_shader_validation_state *validation_state)
 {
+	uint64_t inst = validation_state->shader[validation_state->ip];
 	uint32_t op_add = QPU_GET_FIELD(inst, QPU_OP_ADD);
 	uint32_t waddr_add = QPU_GET_FIELD(inst, QPU_WADDR_ADD);
 	uint32_t waddr_mul = QPU_GET_FIELD(inst, QPU_WADDR_MUL);
@@ -369,10 +522,10 @@ track_live_clamps(uint64_t inst,
 }
 
 static bool
-check_instruction_writes(uint64_t inst,
-			 struct vc4_validated_shader_info *validated_shader,
+check_instruction_writes(struct vc4_validated_shader_info *validated_shader,
 			 struct vc4_shader_validation_state *validation_state)
 {
+	uint64_t inst = validation_state->shader[validation_state->ip];
 	uint32_t waddr_add = QPU_GET_FIELD(inst, QPU_WADDR_ADD);
 	uint32_t waddr_mul = QPU_GET_FIELD(inst, QPU_WADDR_MUL);
 	bool ok;
@@ -382,20 +535,44 @@ check_instruction_writes(uint64_t inst,
 		return false;
 	}
 
-	ok = (check_reg_write(inst, validated_shader, validation_state,
-			      false) &&
-	      check_reg_write(inst, validated_shader, validation_state,
-			      true));
+	ok = (check_reg_write(validated_shader, validation_state, false) &&
+	      check_reg_write(validated_shader, validation_state, true));
 
-	track_live_clamps(inst, validated_shader, validation_state);
+	track_live_clamps(validated_shader, validation_state);
 
 	return ok;
 }
 
 static bool
-check_instruction_reads(uint64_t inst,
-			struct vc4_validated_shader_info *validated_shader)
+check_branch(uint64_t inst,
+	     struct vc4_validated_shader_info *validated_shader,
+	     struct vc4_shader_validation_state *validation_state,
+	     int ip)
+{
+	int32_t branch_imm = QPU_GET_FIELD(inst, QPU_BRANCH_TARGET);
+	uint32_t waddr_add = QPU_GET_FIELD(inst, QPU_WADDR_ADD);
+	uint32_t waddr_mul = QPU_GET_FIELD(inst, QPU_WADDR_MUL);
+
+	if ((int)branch_imm < 0)
+		validation_state->needs_uniform_address_for_loop = true;
+
+	/* We don't want to have to worry about validation of this, and
+	 * there's no need for it.
+	 */
+	if (waddr_add != QPU_W_NOP || waddr_mul != QPU_W_NOP) {
+		DRM_ERROR("branch instruction at %d wrote a register.\n",
+			  validation_state->ip);
+		return false;
+	}
+
+	return true;
+}
+
+static bool
+check_instruction_reads(struct vc4_validated_shader_info *validated_shader,
+			struct vc4_shader_validation_state *validation_state)
 {
+	uint64_t inst = validation_state->shader[validation_state->ip];
 	uint32_t raddr_a = QPU_GET_FIELD(inst, QPU_RADDR_A);
 	uint32_t raddr_b = QPU_GET_FIELD(inst, QPU_RADDR_B);
 	uint32_t sig = QPU_GET_FIELD(inst, QPU_SIG);
@@ -407,40 +584,204 @@ check_instruction_reads(uint64_t inst,
 		 * already be OOM.
 		 */
 		validated_shader->uniforms_size += 4;
+
+		if (validation_state->needs_uniform_address_update) {
+			DRM_ERROR("Uniform read with undefined uniform "
+				  "address\n");
+			return false;
+		}
+	}
+
+	return true;
+}
+
+/* Make sure that all branches are absolute and point within the shader, and
+ * note their targets for later.
+ */
+static bool
+vc4_validate_branches(struct vc4_shader_validation_state *validation_state)
+{
+	uint32_t max_branch_target = 0;
+	bool found_shader_end = false;
+	int ip;
+	int shader_end_ip = 0;
+	int last_branch = -2;
+
+	for (ip = 0; ip < validation_state->max_ip; ip++) {
+		uint64_t inst = validation_state->shader[ip];
+		int32_t branch_imm = QPU_GET_FIELD(inst, QPU_BRANCH_TARGET);
+		uint32_t sig = QPU_GET_FIELD(inst, QPU_SIG);
+		uint32_t after_delay_ip = ip + 4;
+		uint32_t branch_target_ip;
+
+		if (sig == QPU_SIG_PROG_END) {
+			shader_end_ip = ip;
+			found_shader_end = true;
+			continue;
+		}
+
+		if (sig != QPU_SIG_BRANCH)
+			continue;
+
+		if (ip - last_branch < 4) {
+			DRM_ERROR("Branch at %d during delay slots\n", ip);
+			return false;
+		}
+		last_branch = ip;
+
+		if (inst & QPU_BRANCH_REG) {
+			DRM_ERROR("branching from register relative "
+				  "not supported\n");
+			return false;
+		}
+
+		if (!(inst & QPU_BRANCH_REL)) {
+			DRM_ERROR("relative branching required\n");
+			return false;
+		}
+
+		/* The actual branch target is the instruction after the delay
+		 * slots, plus whatever byte offset is in the low 32 bits of
+		 * the instruction.  Make sure we're not branching beyond the
+		 * end of the shader object.
+		 */
+		if (branch_imm % sizeof(inst) != 0) {
+			DRM_ERROR("branch target not aligned\n");
+			return false;
+		}
+
+		branch_target_ip = after_delay_ip + (branch_imm >> 3);
+		if (branch_target_ip >= validation_state->max_ip) {
+			DRM_ERROR("Branch at %d outside of shader (ip %d/%d)\n",
+				  ip, branch_target_ip,
+				  validation_state->max_ip);
+			return false;
+		}
+		set_bit(branch_target_ip, validation_state->branch_targets);
+
+		/* Make sure that the non-branching path is also not outside
+		 * the shader.
+		 */
+		if (after_delay_ip >= validation_state->max_ip) {
+			DRM_ERROR("Branch at %d continues past shader end "
+				  "(%d/%d)\n",
+				  ip, after_delay_ip, validation_state->max_ip);
+			return false;
+		}
+		set_bit(after_delay_ip, validation_state->branch_targets);
+		max_branch_target = max(max_branch_target, after_delay_ip);
+
+		/* There are two delay slots after program end is signaled
+		 * that are still executed, then we're finished.
+		 */
+		if (found_shader_end && ip == shader_end_ip + 2)
+			break;
+	}
+
+	if (max_branch_target > shader_end_ip) {
+		DRM_ERROR("Branch landed after QPU_SIG_PROG_END");
+		return false;
 	}
 
 	return true;
 }
 
+/* Resets any known state for the shader, used when we may be branched to from
+ * multiple locations in the program (or at shader start).
+ */
+static void
+reset_validation_state(struct vc4_shader_validation_state *validation_state)
+{
+	int i;
+
+	for (i = 0; i < 8; i++)
+		validation_state->tmu_setup[i / 4].p_offset[i % 4] = ~0;
+
+	for (i = 0; i < LIVE_REG_COUNT; i++) {
+		validation_state->live_min_clamp_offsets[i] = ~0;
+		validation_state->live_max_clamp_regs[i] = false;
+		validation_state->live_immediates[i] = ~0;
+	}
+}
+
+static bool
+texturing_in_progress(struct vc4_shader_validation_state *validation_state)
+{
+	return (validation_state->tmu_write_count[0] != 0 ||
+		validation_state->tmu_write_count[1] != 0);
+}
+
+static bool
+vc4_handle_branch_target(struct vc4_shader_validation_state *validation_state)
+{
+	uint32_t ip = validation_state->ip;
+
+	if (!test_bit(ip, validation_state->branch_targets))
+		return true;
+
+	if (texturing_in_progress(validation_state)) {
+		DRM_ERROR("Branch target landed during TMU setup\n");
+		return false;
+	}
+
+	/* Reset our live values tracking, since this instruction may have
+	 * multiple predecessors.
+	 *
+	 * One could potentially do analysis to determine that, for
+	 * example, all predecessors have a live max clamp in the same
+	 * register, but we don't bother with that.
+	 */
+	reset_validation_state(validation_state);
+
+	/* Since we've entered a basic block from potentially multiple
+	 * predecessors, we need the uniforms address to be updated before any
+	 * unforms are read.  We require that after any branch point, the next
+	 * uniform to be loaded is a uniform address offset.  That uniform's
+	 * offset will be marked by the uniform address register write
+	 * validation, or a one-off the end-of-program check.
+	 */
+	validation_state->needs_uniform_address_update = true;
+
+	return true;
+}
+
 struct vc4_validated_shader_info *
 vc4_validate_shader(struct drm_gem_cma_object *shader_obj)
 {
 	bool found_shader_end = false;
 	int shader_end_ip = 0;
-	uint32_t ip, max_ip;
-	uint64_t *shader;
-	struct vc4_validated_shader_info *validated_shader;
+	uint32_t ip;
+	struct vc4_validated_shader_info *validated_shader = NULL;
 	struct vc4_shader_validation_state validation_state;
-	int i;
 
 	memset(&validation_state, 0, sizeof(validation_state));
+	validation_state.shader = shader_obj->vaddr;
+	validation_state.max_ip = shader_obj->base.size / sizeof(uint64_t);
 
-	for (i = 0; i < 8; i++)
-		validation_state.tmu_setup[i / 4].p_offset[i % 4] = ~0;
-	for (i = 0; i < ARRAY_SIZE(validation_state.live_min_clamp_offsets); i++)
-		validation_state.live_min_clamp_offsets[i] = ~0;
+	reset_validation_state(&validation_state);
 
-	shader = shader_obj->vaddr;
-	max_ip = shader_obj->base.size / sizeof(uint64_t);
+	validation_state.branch_targets =
+		kcalloc(BITS_TO_LONGS(validation_state.max_ip),
+			sizeof(unsigned long), GFP_KERNEL);
+	if (!validation_state.branch_targets)
+		goto fail;
 
 	validated_shader = kcalloc(1, sizeof(*validated_shader), GFP_KERNEL);
 	if (!validated_shader)
-		return NULL;
+		goto fail;
+
+	if (!vc4_validate_branches(&validation_state))
+		goto fail;
 
-	for (ip = 0; ip < max_ip; ip++) {
-		uint64_t inst = shader[ip];
+	for (ip = 0; ip < validation_state.max_ip; ip++) {
+		uint64_t inst = validation_state.shader[ip];
 		uint32_t sig = QPU_GET_FIELD(inst, QPU_SIG);
 
+		validation_state.ip = ip;
+
+		if (!vc4_handle_branch_target(&validation_state))
+			goto fail;
+
 		switch (sig) {
 		case QPU_SIG_NONE:
 		case QPU_SIG_WAIT_FOR_SCOREBOARD:
@@ -450,13 +791,14 @@ vc4_validate_shader(struct drm_gem_cma_object *shader_obj)
 		case QPU_SIG_LOAD_TMU1:
 		case QPU_SIG_PROG_END:
 		case QPU_SIG_SMALL_IMM:
-			if (!check_instruction_writes(inst, validated_shader,
+			if (!check_instruction_writes(validated_shader,
 						      &validation_state)) {
 				DRM_ERROR("Bad write at ip %d\n", ip);
 				goto fail;
 			}
 
-			if (!check_instruction_reads(inst, validated_shader))
+			if (!check_instruction_reads(validated_shader,
+						     &validation_state))
 				goto fail;
 
 			if (sig == QPU_SIG_PROG_END) {
@@ -467,13 +809,18 @@ vc4_validate_shader(struct drm_gem_cma_object *shader_obj)
 			break;
 
 		case QPU_SIG_LOAD_IMM:
-			if (!check_instruction_writes(inst, validated_shader,
+			if (!check_instruction_writes(validated_shader,
 						      &validation_state)) {
 				DRM_ERROR("Bad LOAD_IMM write at ip %d\n", ip);
 				goto fail;
 			}
 			break;
 
+		case QPU_SIG_BRANCH:
+			if (!check_branch(inst, validated_shader,
+					  &validation_state, ip))
+				goto fail;
+			break;
 		default:
 			DRM_ERROR("Unsupported QPU signal %d at "
 				  "instruction %d\n", sig, ip);
@@ -487,13 +834,28 @@ vc4_validate_shader(struct drm_gem_cma_object *shader_obj)
 			break;
 	}
 
-	if (ip == max_ip) {
+	if (ip == validation_state.max_ip) {
 		DRM_ERROR("shader failed to terminate before "
 			  "shader BO end at %zd\n",
 			  shader_obj->base.size);
 		goto fail;
 	}
 
+	/* If we did a backwards branch and we haven't emitted a uniforms
+	 * reset since then, we still need the uniforms stream to have the
+	 * uniforms address available so that the backwards branch can do its
+	 * uniforms reset.
+	 *
+	 * We could potentially prove that the backwards branch doesn't
+	 * contain any uses of uniforms until program exit, but that doesn't
+	 * seem to be worth the trouble.
+	 */
+	if (validation_state.needs_uniform_address_for_loop) {
+		if (!require_uniform_address_uniform(validated_shader))
+			goto fail;
+		validated_shader->uniforms_size += 4;
+	}
+
 	/* Again, no chance of integer overflow here because the worst case
 	 * scenario is 8 bytes of uniforms plus handles per 8-byte
 	 * instruction.
@@ -502,9 +864,12 @@ vc4_validate_shader(struct drm_gem_cma_object *shader_obj)
 		(validated_shader->uniforms_size +
 		 4 * validated_shader->num_texture_samples);
 
+	kfree(validation_state.branch_targets);
+
 	return validated_shader;
 
 fail:
+	kfree(validation_state.branch_targets);
 	if (validated_shader) {
 		kfree(validated_shader->texture_samples);
 		kfree(validated_shader);
diff --git a/drivers/gpu/drm/vgem/Makefile b/drivers/gpu/drm/vgem/Makefile
index 3f4c7b842028..bfcdea1330e6 100644
--- a/drivers/gpu/drm/vgem/Makefile
+++ b/drivers/gpu/drm/vgem/Makefile
@@ -1,4 +1,4 @@
 ccflags-y := -Iinclude/drm
-vgem-y := vgem_drv.o
+vgem-y := vgem_drv.o vgem_fence.o
 
 obj-$(CONFIG_DRM_VGEM)	+= vgem.o
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index 341f9be3dde6..c15bafb06665 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -42,81 +42,38 @@
 #define DRIVER_MAJOR	1
 #define DRIVER_MINOR	0
 
-void vgem_gem_put_pages(struct drm_vgem_gem_object *obj)
-{
-	drm_gem_put_pages(&obj->base, obj->pages, false, false);
-	obj->pages = NULL;
-}
-
 static void vgem_gem_free_object(struct drm_gem_object *obj)
 {
 	struct drm_vgem_gem_object *vgem_obj = to_vgem_bo(obj);
 
-	drm_gem_free_mmap_offset(obj);
-
-	if (vgem_obj->use_dma_buf && obj->dma_buf) {
-		dma_buf_put(obj->dma_buf);
-		obj->dma_buf = NULL;
-	}
-
 	drm_gem_object_release(obj);
-
-	if (vgem_obj->pages)
-		vgem_gem_put_pages(vgem_obj);
-
-	vgem_obj->pages = NULL;
-
 	kfree(vgem_obj);
 }
 
-int vgem_gem_get_pages(struct drm_vgem_gem_object *obj)
-{
-	struct page **pages;
-
-	if (obj->pages || obj->use_dma_buf)
-		return 0;
-
-	pages = drm_gem_get_pages(&obj->base);
-	if (IS_ERR(pages)) {
-		return PTR_ERR(pages);
-	}
-
-	obj->pages = pages;
-
-	return 0;
-}
-
 static int vgem_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct drm_vgem_gem_object *obj = vma->vm_private_data;
-	loff_t num_pages;
-	pgoff_t page_offset;
-	int ret;
-
 	/* We don't use vmf->pgoff since that has the fake offset */
-	page_offset = ((unsigned long)vmf->virtual_address - vma->vm_start) >>
-		PAGE_SHIFT;
-
-	num_pages = DIV_ROUND_UP(obj->base.size, PAGE_SIZE);
-
-	if (page_offset > num_pages)
-		return VM_FAULT_SIGBUS;
-
-	ret = vm_insert_page(vma, (unsigned long)vmf->virtual_address,
-			     obj->pages[page_offset]);
-	switch (ret) {
-	case 0:
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	case -EBUSY:
-		return VM_FAULT_RETRY;
-	case -EFAULT:
-	case -EINVAL:
-		return VM_FAULT_SIGBUS;
-	default:
-		WARN_ON(1);
-		return VM_FAULT_SIGBUS;
+	unsigned long vaddr = (unsigned long)vmf->virtual_address;
+	struct page *page;
+
+	page = shmem_read_mapping_page(file_inode(obj->base.filp)->i_mapping,
+				       (vaddr - vma->vm_start) >> PAGE_SHIFT);
+	if (!IS_ERR(page)) {
+		vmf->page = page;
+		return 0;
+	} else switch (PTR_ERR(page)) {
+		case -ENOSPC:
+		case -ENOMEM:
+			return VM_FAULT_OOM;
+		case -EBUSY:
+			return VM_FAULT_RETRY;
+		case -EFAULT:
+		case -EINVAL:
+			return VM_FAULT_SIGBUS;
+		default:
+			WARN_ON_ONCE(PTR_ERR(page));
+			return VM_FAULT_SIGBUS;
 	}
 }
 
@@ -126,6 +83,34 @@ static const struct vm_operations_struct vgem_gem_vm_ops = {
 	.close = drm_gem_vm_close,
 };
 
+static int vgem_open(struct drm_device *dev, struct drm_file *file)
+{
+	struct vgem_file *vfile;
+	int ret;
+
+	vfile = kzalloc(sizeof(*vfile), GFP_KERNEL);
+	if (!vfile)
+		return -ENOMEM;
+
+	file->driver_priv = vfile;
+
+	ret = vgem_fence_open(vfile);
+	if (ret) {
+		kfree(vfile);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void vgem_preclose(struct drm_device *dev, struct drm_file *file)
+{
+	struct vgem_file *vfile = file->driver_priv;
+
+	vgem_fence_close(vfile);
+	kfree(vfile);
+}
+
 /* ioctls */
 
 static struct drm_gem_object *vgem_gem_create(struct drm_device *dev,
@@ -134,57 +119,43 @@ static struct drm_gem_object *vgem_gem_create(struct drm_device *dev,
 					      unsigned long size)
 {
 	struct drm_vgem_gem_object *obj;
-	struct drm_gem_object *gem_object;
-	int err;
-
-	size = roundup(size, PAGE_SIZE);
+	int ret;
 
 	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
 	if (!obj)
 		return ERR_PTR(-ENOMEM);
 
-	gem_object = &obj->base;
-
-	err = drm_gem_object_init(dev, gem_object, size);
-	if (err)
-		goto out;
-
-	err = vgem_gem_get_pages(obj);
-	if (err)
-		goto out;
-
-	err = drm_gem_handle_create(file, gem_object, handle);
-	if (err)
-		goto handle_out;
+	ret = drm_gem_object_init(dev, &obj->base, roundup(size, PAGE_SIZE));
+	if (ret)
+		goto err_free;
 
-	drm_gem_object_unreference_unlocked(gem_object);
+	ret = drm_gem_handle_create(file, &obj->base, handle);
+	drm_gem_object_unreference_unlocked(&obj->base);
+	if (ret)
+		goto err;
 
-	return gem_object;
+	return &obj->base;
 
-handle_out:
-	drm_gem_object_release(gem_object);
-out:
+err_free:
 	kfree(obj);
-	return ERR_PTR(err);
+err:
+	return ERR_PTR(ret);
 }
 
 static int vgem_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 				struct drm_mode_create_dumb *args)
 {
 	struct drm_gem_object *gem_object;
-	uint64_t size;
-	uint64_t pitch = args->width * DIV_ROUND_UP(args->bpp, 8);
+	u64 pitch, size;
 
+	pitch = args->width * DIV_ROUND_UP(args->bpp, 8);
 	size = args->height * pitch;
 	if (size == 0)
 		return -EINVAL;
 
 	gem_object = vgem_gem_create(dev, file, &args->handle, size);
-
-	if (IS_ERR(gem_object)) {
-		DRM_DEBUG_DRIVER("object creation failed\n");
+	if (IS_ERR(gem_object))
 		return PTR_ERR(gem_object);
-	}
 
 	args->size = gem_object->size;
 	args->pitch = pitch;
@@ -194,26 +165,26 @@ static int vgem_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 	return 0;
 }
 
-int vgem_gem_dumb_map(struct drm_file *file, struct drm_device *dev,
-		      uint32_t handle, uint64_t *offset)
+static int vgem_gem_dumb_map(struct drm_file *file, struct drm_device *dev,
+			     uint32_t handle, uint64_t *offset)
 {
-	int ret = 0;
 	struct drm_gem_object *obj;
+	int ret;
 
 	obj = drm_gem_object_lookup(file, handle);
 	if (!obj)
 		return -ENOENT;
 
+	if (!obj->filp) {
+		ret = -EINVAL;
+		goto unref;
+	}
+
 	ret = drm_gem_create_mmap_offset(obj);
 	if (ret)
 		goto unref;
 
-	BUG_ON(!obj->filp);
-
-	obj->filp->private_data = obj;
-
 	*offset = drm_vma_node_offset_addr(&obj->vma_node);
-
 unref:
 	drm_gem_object_unreference_unlocked(obj);
 
@@ -221,26 +192,134 @@ unref:
 }
 
 static struct drm_ioctl_desc vgem_ioctls[] = {
+	DRM_IOCTL_DEF_DRV(VGEM_FENCE_ATTACH, vgem_fence_attach_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VGEM_FENCE_SIGNAL, vgem_fence_signal_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 };
 
+static int vgem_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	unsigned long flags = vma->vm_flags;
+	int ret;
+
+	ret = drm_gem_mmap(filp, vma);
+	if (ret)
+		return ret;
+
+	/* Keep the WC mmaping set by drm_gem_mmap() but our pages
+	 * are ordinary and not special.
+	 */
+	vma->vm_flags = flags | VM_DONTEXPAND | VM_DONTDUMP;
+	return 0;
+}
+
 static const struct file_operations vgem_driver_fops = {
 	.owner		= THIS_MODULE,
 	.open		= drm_open,
-	.mmap		= drm_gem_mmap,
+	.mmap		= vgem_mmap,
 	.poll		= drm_poll,
 	.read		= drm_read,
 	.unlocked_ioctl = drm_ioctl,
 	.release	= drm_release,
 };
 
+static int vgem_prime_pin(struct drm_gem_object *obj)
+{
+	long n_pages = obj->size >> PAGE_SHIFT;
+	struct page **pages;
+
+	/* Flush the object from the CPU cache so that importers can rely
+	 * on coherent indirect access via the exported dma-address.
+	 */
+	pages = drm_gem_get_pages(obj);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+
+	drm_clflush_pages(pages, n_pages);
+	drm_gem_put_pages(obj, pages, true, false);
+
+	return 0;
+}
+
+static struct sg_table *vgem_prime_get_sg_table(struct drm_gem_object *obj)
+{
+	struct sg_table *st;
+	struct page **pages;
+
+	pages = drm_gem_get_pages(obj);
+	if (IS_ERR(pages))
+		return ERR_CAST(pages);
+
+	st = drm_prime_pages_to_sg(pages, obj->size >> PAGE_SHIFT);
+	drm_gem_put_pages(obj, pages, false, false);
+
+	return st;
+}
+
+static void *vgem_prime_vmap(struct drm_gem_object *obj)
+{
+	long n_pages = obj->size >> PAGE_SHIFT;
+	struct page **pages;
+	void *addr;
+
+	pages = drm_gem_get_pages(obj);
+	if (IS_ERR(pages))
+		return NULL;
+
+	addr = vmap(pages, n_pages, 0, pgprot_writecombine(PAGE_KERNEL));
+	drm_gem_put_pages(obj, pages, false, false);
+
+	return addr;
+}
+
+static void vgem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
+{
+	vunmap(vaddr);
+}
+
+static int vgem_prime_mmap(struct drm_gem_object *obj,
+			   struct vm_area_struct *vma)
+{
+	int ret;
+
+	if (obj->size < vma->vm_end - vma->vm_start)
+		return -EINVAL;
+
+	if (!obj->filp)
+		return -ENODEV;
+
+	ret = obj->filp->f_op->mmap(obj->filp, vma);
+	if (ret)
+		return ret;
+
+	fput(vma->vm_file);
+	vma->vm_file = get_file(obj->filp);
+	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+
+	return 0;
+}
+
 static struct drm_driver vgem_driver = {
-	.driver_features		= DRIVER_GEM,
-	.gem_free_object		= vgem_gem_free_object,
+	.driver_features		= DRIVER_GEM | DRIVER_PRIME,
+	.open				= vgem_open,
+	.preclose			= vgem_preclose,
+	.gem_free_object_unlocked	= vgem_gem_free_object,
 	.gem_vm_ops			= &vgem_gem_vm_ops,
 	.ioctls				= vgem_ioctls,
+	.num_ioctls 			= ARRAY_SIZE(vgem_ioctls),
 	.fops				= &vgem_driver_fops,
+
 	.dumb_create			= vgem_gem_dumb_create,
 	.dumb_map_offset		= vgem_gem_dumb_map,
+
+	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+	.gem_prime_pin = vgem_prime_pin,
+	.gem_prime_export = drm_gem_prime_export,
+	.gem_prime_get_sg_table = vgem_prime_get_sg_table,
+	.gem_prime_vmap = vgem_prime_vmap,
+	.gem_prime_vunmap = vgem_prime_vunmap,
+	.gem_prime_mmap = vgem_prime_mmap,
+
 	.name	= DRIVER_NAME,
 	.desc	= DRIVER_DESC,
 	.date	= DRIVER_DATE,
@@ -248,7 +327,7 @@ static struct drm_driver vgem_driver = {
 	.minor	= DRIVER_MINOR,
 };
 
-struct drm_device *vgem_device;
+static struct drm_device *vgem_device;
 
 static int __init vgem_init(void)
 {
@@ -260,10 +339,7 @@ static int __init vgem_init(void)
 		goto out;
 	}
 
-	drm_dev_set_unique(vgem_device, "vgem");
-
 	ret  = drm_dev_register(vgem_device, 0);
-
 	if (ret)
 		goto out_unref;
 
@@ -285,5 +361,6 @@ module_init(vgem_init);
 module_exit(vgem_exit);
 
 MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_AUTHOR("Intel Corporation");
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/vgem/vgem_drv.h b/drivers/gpu/drm/vgem/vgem_drv.h
index e9f92f7ee275..1f8798ad329c 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.h
+++ b/drivers/gpu/drm/vgem/vgem_drv.h
@@ -32,15 +32,25 @@
 #include <drm/drmP.h>
 #include <drm/drm_gem.h>
 
+#include <uapi/drm/vgem_drm.h>
+
+struct vgem_file {
+	struct idr fence_idr;
+	struct mutex fence_mutex;
+};
+
 #define to_vgem_bo(x) container_of(x, struct drm_vgem_gem_object, base)
 struct drm_vgem_gem_object {
 	struct drm_gem_object base;
-	struct page **pages;
-	bool use_dma_buf;
 };
 
-/* vgem_drv.c */
-extern void vgem_gem_put_pages(struct drm_vgem_gem_object *obj);
-extern int vgem_gem_get_pages(struct drm_vgem_gem_object *obj);
+int vgem_fence_open(struct vgem_file *file);
+int vgem_fence_attach_ioctl(struct drm_device *dev,
+			    void *data,
+			    struct drm_file *file);
+int vgem_fence_signal_ioctl(struct drm_device *dev,
+			    void *data,
+			    struct drm_file *file);
+void vgem_fence_close(struct vgem_file *file);
 
 #endif
diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c
new file mode 100644
index 000000000000..5c57c1ffa1f9
--- /dev/null
+++ b/drivers/gpu/drm/vgem/vgem_fence.c
@@ -0,0 +1,283 @@
+/*
+ * Copyright 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software")
+ * to deal in the software without restriction, including without limitation
+ * on the rights to use, copy, modify, merge, publish, distribute, sub
+ * license, and/or sell copies of the Software, and to permit persons to whom
+ * them Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTIBILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER
+ * IN AN ACTION OF CONTRACT, TORT, OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/reservation.h>
+
+#include "vgem_drv.h"
+
+#define VGEM_FENCE_TIMEOUT (10*HZ)
+
+struct vgem_fence {
+	struct fence base;
+	struct spinlock lock;
+	struct timer_list timer;
+};
+
+static const char *vgem_fence_get_driver_name(struct fence *fence)
+{
+	return "vgem";
+}
+
+static const char *vgem_fence_get_timeline_name(struct fence *fence)
+{
+	return "unbound";
+}
+
+static bool vgem_fence_signaled(struct fence *fence)
+{
+	return false;
+}
+
+static bool vgem_fence_enable_signaling(struct fence *fence)
+{
+	return true;
+}
+
+static void vgem_fence_release(struct fence *base)
+{
+	struct vgem_fence *fence = container_of(base, typeof(*fence), base);
+
+	del_timer_sync(&fence->timer);
+	fence_free(&fence->base);
+}
+
+static void vgem_fence_value_str(struct fence *fence, char *str, int size)
+{
+	snprintf(str, size, "%u", fence->seqno);
+}
+
+static void vgem_fence_timeline_value_str(struct fence *fence, char *str,
+					  int size)
+{
+	snprintf(str, size, "%u", fence_is_signaled(fence) ? fence->seqno : 0);
+}
+
+static const struct fence_ops vgem_fence_ops = {
+	.get_driver_name = vgem_fence_get_driver_name,
+	.get_timeline_name = vgem_fence_get_timeline_name,
+	.enable_signaling = vgem_fence_enable_signaling,
+	.signaled = vgem_fence_signaled,
+	.wait = fence_default_wait,
+	.release = vgem_fence_release,
+
+	.fence_value_str = vgem_fence_value_str,
+	.timeline_value_str = vgem_fence_timeline_value_str,
+};
+
+static void vgem_fence_timeout(unsigned long data)
+{
+	struct vgem_fence *fence = (struct vgem_fence *)data;
+
+	fence_signal(&fence->base);
+}
+
+static struct fence *vgem_fence_create(struct vgem_file *vfile,
+				       unsigned int flags)
+{
+	struct vgem_fence *fence;
+
+	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
+	if (!fence)
+		return NULL;
+
+	spin_lock_init(&fence->lock);
+	fence_init(&fence->base, &vgem_fence_ops, &fence->lock,
+		   fence_context_alloc(1), 1);
+
+	setup_timer(&fence->timer, vgem_fence_timeout, (unsigned long)fence);
+
+	/* We force the fence to expire within 10s to prevent driver hangs */
+	mod_timer(&fence->timer, jiffies + VGEM_FENCE_TIMEOUT);
+
+	return &fence->base;
+}
+
+static int attach_dmabuf(struct drm_device *dev,
+			 struct drm_gem_object *obj)
+{
+	struct dma_buf *dmabuf;
+
+	if (obj->dma_buf)
+		return 0;
+
+	dmabuf = dev->driver->gem_prime_export(dev, obj, 0);
+	if (IS_ERR(dmabuf))
+		return PTR_ERR(dmabuf);
+
+	obj->dma_buf = dmabuf;
+	drm_gem_object_reference(obj);
+	return 0;
+}
+
+/*
+ * vgem_fence_attach_ioctl (DRM_IOCTL_VGEM_FENCE_ATTACH):
+ *
+ * Create and attach a fence to the vGEM handle. This fence is then exposed
+ * via the dma-buf reservation object and visible to consumers of the exported
+ * dma-buf. If the flags contain VGEM_FENCE_WRITE, the fence indicates the
+ * vGEM buffer is being written to by the client and is exposed as an exclusive
+ * fence, otherwise the fence indicates the client is current reading from the
+ * buffer and all future writes should wait for the client to signal its
+ * completion. Note that if a conflicting fence is already on the dma-buf (i.e.
+ * an exclusive fence when adding a read, or any fence when adding a write),
+ * -EBUSY is reported. Serialisation between operations should be handled
+ * by waiting upon the dma-buf.
+ *
+ * This returns the handle for the new fence that must be signaled within 10
+ * seconds (or otherwise it will automatically expire). See
+ * vgem_fence_signal_ioctl (DRM_IOCTL_VGEM_FENCE_SIGNAL).
+ *
+ * If the vGEM handle does not exist, vgem_fence_attach_ioctl returns -ENOENT.
+ */
+int vgem_fence_attach_ioctl(struct drm_device *dev,
+			    void *data,
+			    struct drm_file *file)
+{
+	struct drm_vgem_fence_attach *arg = data;
+	struct vgem_file *vfile = file->driver_priv;
+	struct reservation_object *resv;
+	struct drm_gem_object *obj;
+	struct fence *fence;
+	int ret;
+
+	if (arg->flags & ~VGEM_FENCE_WRITE)
+		return -EINVAL;
+
+	if (arg->pad)
+		return -EINVAL;
+
+	obj = drm_gem_object_lookup(file, arg->handle);
+	if (!obj)
+		return -ENOENT;
+
+	ret = attach_dmabuf(dev, obj);
+	if (ret)
+		goto err;
+
+	fence = vgem_fence_create(vfile, arg->flags);
+	if (!fence) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	/* Check for a conflicting fence */
+	resv = obj->dma_buf->resv;
+	if (!reservation_object_test_signaled_rcu(resv,
+						  arg->flags & VGEM_FENCE_WRITE)) {
+		ret = -EBUSY;
+		goto err_fence;
+	}
+
+	/* Expose the fence via the dma-buf */
+	ret = 0;
+	mutex_lock(&resv->lock.base);
+	if (arg->flags & VGEM_FENCE_WRITE)
+		reservation_object_add_excl_fence(resv, fence);
+	else if ((ret = reservation_object_reserve_shared(resv)) == 0)
+		reservation_object_add_shared_fence(resv, fence);
+	mutex_unlock(&resv->lock.base);
+
+	/* Record the fence in our idr for later signaling */
+	if (ret == 0) {
+		mutex_lock(&vfile->fence_mutex);
+		ret = idr_alloc(&vfile->fence_idr, fence, 1, 0, GFP_KERNEL);
+		mutex_unlock(&vfile->fence_mutex);
+		if (ret > 0) {
+			arg->out_fence = ret;
+			ret = 0;
+		}
+	}
+err_fence:
+	if (ret) {
+		fence_signal(fence);
+		fence_put(fence);
+	}
+err:
+	drm_gem_object_unreference_unlocked(obj);
+	return ret;
+}
+
+/*
+ * vgem_fence_signal_ioctl (DRM_IOCTL_VGEM_FENCE_SIGNAL):
+ *
+ * Signal and consume a fence ealier attached to a vGEM handle using
+ * vgem_fence_attach_ioctl (DRM_IOCTL_VGEM_FENCE_ATTACH).
+ *
+ * All fences must be signaled within 10s of attachment or otherwise they
+ * will automatically expire (and a vgem_fence_signal_ioctl returns -ETIMEDOUT).
+ *
+ * Signaling a fence indicates to all consumers of the dma-buf that the
+ * client has completed the operation associated with the fence, and that the
+ * buffer is then ready for consumption.
+ *
+ * If the fence does not exist (or has already been signaled by the client),
+ * vgem_fence_signal_ioctl returns -ENOENT.
+ */
+int vgem_fence_signal_ioctl(struct drm_device *dev,
+			    void *data,
+			    struct drm_file *file)
+{
+	struct vgem_file *vfile = file->driver_priv;
+	struct drm_vgem_fence_signal *arg = data;
+	struct fence *fence;
+	int ret = 0;
+
+	if (arg->flags)
+		return -EINVAL;
+
+	mutex_lock(&vfile->fence_mutex);
+	fence = idr_replace(&vfile->fence_idr, NULL, arg->fence);
+	mutex_unlock(&vfile->fence_mutex);
+	if (!fence)
+		return -ENOENT;
+	if (IS_ERR(fence))
+		return PTR_ERR(fence);
+
+	if (fence_is_signaled(fence))
+		ret = -ETIMEDOUT;
+
+	fence_signal(fence);
+	fence_put(fence);
+	return ret;
+}
+
+int vgem_fence_open(struct vgem_file *vfile)
+{
+	mutex_init(&vfile->fence_mutex);
+	idr_init(&vfile->fence_idr);
+
+	return 0;
+}
+
+static int __vgem_fence_idr_fini(int id, void *p, void *data)
+{
+	fence_signal(p);
+	fence_put(p);
+	return 0;
+}
+
+void vgem_fence_close(struct vgem_file *vfile)
+{
+	idr_for_each(&vfile->fence_idr, __vgem_fence_idr_fini, vfile);
+	idr_destroy(&vfile->fence_idr);
+}
diff --git a/drivers/gpu/drm/via/via_mm.c b/drivers/gpu/drm/via/via_mm.c
index 4f20742e7788..a04ef1c992d9 100644
--- a/drivers/gpu/drm/via/via_mm.c
+++ b/drivers/gpu/drm/via/via_mm.c
@@ -208,7 +208,7 @@ void via_reclaim_buffers_locked(struct drm_device *dev,
 	struct via_file_private *file_priv = file->driver_priv;
 	struct via_memblock *entry, *next;
 
-	if (!(file->minor->master && file->master->lock.hw_lock))
+	if (!(dev->master && file->master->lock.hw_lock))
 		return;
 
 	drm_legacy_idlelock_take(&file->master->lock);
diff --git a/drivers/gpu/drm/virtio/Kconfig b/drivers/gpu/drm/virtio/Kconfig
index 9983eadb81b6..e1afc3d3f8d9 100644
--- a/drivers/gpu/drm/virtio/Kconfig
+++ b/drivers/gpu/drm/virtio/Kconfig
@@ -1,11 +1,7 @@
 config DRM_VIRTIO_GPU
 	tristate "Virtio GPU driver"
 	depends on DRM && VIRTIO
-	select FB_SYS_FILLRECT
-	select FB_SYS_COPYAREA
-	select FB_SYS_IMAGEBLIT
         select DRM_KMS_HELPER
-        select DRM_KMS_FB_HELPER
         select DRM_TTM
 	help
 	   This is the virtual GPU driver for virtio.  It can be used with
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index d4305da88f44..4e192aa2d021 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -29,8 +29,8 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_atomic_helper.h>
 
-#define XRES_MIN   320
-#define YRES_MIN   200
+#define XRES_MIN    32
+#define YRES_MIN    32
 
 #define XRES_DEF  1024
 #define YRES_DEF   768
@@ -38,138 +38,11 @@
 #define XRES_MAX  8192
 #define YRES_MAX  8192
 
-static void
-virtio_gpu_hide_cursor(struct virtio_gpu_device *vgdev,
-		       struct virtio_gpu_output *output)
-{
-	output->cursor.hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_UPDATE_CURSOR);
-	output->cursor.resource_id = 0;
-	virtio_gpu_cursor_ping(vgdev, output);
-}
-
-static int virtio_gpu_crtc_cursor_set(struct drm_crtc *crtc,
-				      struct drm_file *file_priv,
-				      uint32_t handle,
-				      uint32_t width,
-				      uint32_t height,
-				      int32_t hot_x, int32_t hot_y)
-{
-	struct virtio_gpu_device *vgdev = crtc->dev->dev_private;
-	struct virtio_gpu_output *output =
-		container_of(crtc, struct virtio_gpu_output, crtc);
-	struct drm_gem_object *gobj = NULL;
-	struct virtio_gpu_object *qobj = NULL;
-	struct virtio_gpu_fence *fence = NULL;
-	int ret = 0;
-
-	if (handle == 0) {
-		virtio_gpu_hide_cursor(vgdev, output);
-		return 0;
-	}
-
-	/* lookup the cursor */
-	gobj = drm_gem_object_lookup(file_priv, handle);
-	if (gobj == NULL)
-		return -ENOENT;
-
-	qobj = gem_to_virtio_gpu_obj(gobj);
-
-	if (!qobj->hw_res_handle) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	virtio_gpu_cmd_transfer_to_host_2d(vgdev, qobj->hw_res_handle, 0,
-					   cpu_to_le32(64),
-					   cpu_to_le32(64),
-					   0, 0, &fence);
-	ret = virtio_gpu_object_reserve(qobj, false);
-	if (!ret) {
-		reservation_object_add_excl_fence(qobj->tbo.resv,
-						  &fence->f);
-		fence_put(&fence->f);
-		virtio_gpu_object_unreserve(qobj);
-		virtio_gpu_object_wait(qobj, false);
-	}
-
-	output->cursor.hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_UPDATE_CURSOR);
-	output->cursor.resource_id = cpu_to_le32(qobj->hw_res_handle);
-	output->cursor.hot_x = cpu_to_le32(hot_x);
-	output->cursor.hot_y = cpu_to_le32(hot_y);
-	virtio_gpu_cursor_ping(vgdev, output);
-	ret = 0;
-
-out:
-	drm_gem_object_unreference_unlocked(gobj);
-	return ret;
-}
-
-static int virtio_gpu_crtc_cursor_move(struct drm_crtc *crtc,
-				    int x, int y)
-{
-	struct virtio_gpu_device *vgdev = crtc->dev->dev_private;
-	struct virtio_gpu_output *output =
-		container_of(crtc, struct virtio_gpu_output, crtc);
-
-	output->cursor.hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_MOVE_CURSOR);
-	output->cursor.pos.x = cpu_to_le32(x);
-	output->cursor.pos.y = cpu_to_le32(y);
-	virtio_gpu_cursor_ping(vgdev, output);
-	return 0;
-}
-
-static int virtio_gpu_page_flip(struct drm_crtc *crtc,
-				struct drm_framebuffer *fb,
-				struct drm_pending_vblank_event *event,
-				uint32_t flags)
-{
-	struct virtio_gpu_device *vgdev = crtc->dev->dev_private;
-	struct virtio_gpu_output *output =
-		container_of(crtc, struct virtio_gpu_output, crtc);
-	struct drm_plane *plane = crtc->primary;
-	struct virtio_gpu_framebuffer *vgfb;
-	struct virtio_gpu_object *bo;
-	unsigned long irqflags;
-	uint32_t handle;
-
-	plane->fb = fb;
-	vgfb = to_virtio_gpu_framebuffer(plane->fb);
-	bo = gem_to_virtio_gpu_obj(vgfb->obj);
-	handle = bo->hw_res_handle;
-
-	DRM_DEBUG("handle 0x%x%s, crtc %dx%d\n", handle,
-		  bo->dumb ? ", dumb" : "",
-		  crtc->mode.hdisplay, crtc->mode.vdisplay);
-	if (bo->dumb) {
-		virtio_gpu_cmd_transfer_to_host_2d
-			(vgdev, handle, 0,
-			 cpu_to_le32(crtc->mode.hdisplay),
-			 cpu_to_le32(crtc->mode.vdisplay),
-			 0, 0, NULL);
-	}
-	virtio_gpu_cmd_set_scanout(vgdev, output->index, handle,
-				   crtc->mode.hdisplay,
-				   crtc->mode.vdisplay, 0, 0);
-	virtio_gpu_cmd_resource_flush(vgdev, handle, 0, 0,
-				      crtc->mode.hdisplay,
-				      crtc->mode.vdisplay);
-
-	if (event) {
-		spin_lock_irqsave(&crtc->dev->event_lock, irqflags);
-		drm_send_vblank_event(crtc->dev, -1, event);
-		spin_unlock_irqrestore(&crtc->dev->event_lock, irqflags);
-	}
-
-	return 0;
-}
-
 static const struct drm_crtc_funcs virtio_gpu_crtc_funcs = {
-	.cursor_set2            = virtio_gpu_crtc_cursor_set,
-	.cursor_move            = virtio_gpu_crtc_cursor_move,
 	.set_config             = drm_atomic_helper_set_config,
 	.destroy                = drm_crtc_cleanup,
 
-	.page_flip              = virtio_gpu_page_flip,
+	.page_flip              = drm_atomic_helper_page_flip,
 	.reset                  = drm_atomic_helper_crtc_reset,
 	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
 	.atomic_destroy_state   = drm_atomic_helper_crtc_destroy_state,
@@ -180,8 +53,7 @@ static void virtio_gpu_user_framebuffer_destroy(struct drm_framebuffer *fb)
 	struct virtio_gpu_framebuffer *virtio_gpu_fb
 		= to_virtio_gpu_framebuffer(fb);
 
-	if (virtio_gpu_fb->obj)
-		drm_gem_object_unreference_unlocked(virtio_gpu_fb->obj);
+	drm_gem_object_unreference_unlocked(virtio_gpu_fb->obj);
 	drm_framebuffer_cleanup(fb);
 	kfree(virtio_gpu_fb);
 }
@@ -267,6 +139,7 @@ static void virtio_gpu_crtc_atomic_flush(struct drm_crtc *crtc,
 	spin_lock_irqsave(&crtc->dev->event_lock, flags);
 	if (crtc->state->event)
 		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+	crtc->state->event = NULL;
 	spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 }
 
@@ -341,15 +214,6 @@ static int virtio_gpu_conn_mode_valid(struct drm_connector *connector,
 	return MODE_BAD;
 }
 
-static struct drm_encoder*
-virtio_gpu_best_encoder(struct drm_connector *connector)
-{
-	struct virtio_gpu_output *virtio_gpu_output =
-		drm_connector_to_virtio_gpu_output(connector);
-
-	return &virtio_gpu_output->enc;
-}
-
 static const struct drm_encoder_helper_funcs virtio_gpu_enc_helper_funcs = {
 	.mode_set   = virtio_gpu_enc_mode_set,
 	.enable     = virtio_gpu_enc_enable,
@@ -359,7 +223,6 @@ static const struct drm_encoder_helper_funcs virtio_gpu_enc_helper_funcs = {
 static const struct drm_connector_helper_funcs virtio_gpu_conn_helper_funcs = {
 	.get_modes    = virtio_gpu_conn_get_modes,
 	.mode_valid   = virtio_gpu_conn_mode_valid,
-	.best_encoder = virtio_gpu_best_encoder,
 };
 
 static enum drm_connector_status virtio_gpu_conn_detect(
@@ -406,7 +269,7 @@ static int vgdev_output_init(struct virtio_gpu_device *vgdev, int index)
 	struct drm_connector *connector = &output->conn;
 	struct drm_encoder *encoder = &output->enc;
 	struct drm_crtc *crtc = &output->crtc;
-	struct drm_plane *plane;
+	struct drm_plane *primary, *cursor;
 
 	output->index = index;
 	if (index == 0) {
@@ -415,13 +278,17 @@ static int vgdev_output_init(struct virtio_gpu_device *vgdev, int index)
 		output->info.r.height = cpu_to_le32(YRES_DEF);
 	}
 
-	plane = virtio_gpu_plane_init(vgdev, index);
-	if (IS_ERR(plane))
-		return PTR_ERR(plane);
-	drm_crtc_init_with_planes(dev, crtc, plane, NULL,
+	primary = virtio_gpu_plane_init(vgdev, DRM_PLANE_TYPE_PRIMARY, index);
+	if (IS_ERR(primary))
+		return PTR_ERR(primary);
+	cursor = virtio_gpu_plane_init(vgdev, DRM_PLANE_TYPE_CURSOR, index);
+	if (IS_ERR(cursor))
+		return PTR_ERR(cursor);
+	drm_crtc_init_with_planes(dev, crtc, primary, cursor,
 				  &virtio_gpu_crtc_funcs, NULL);
 	drm_crtc_helper_add(crtc, &virtio_gpu_crtc_helper_funcs);
-	plane->crtc = crtc;
+	primary->crtc = crtc;
+	cursor->crtc = crtc;
 
 	drm_connector_init(dev, connector, &virtio_gpu_connector_funcs,
 			   DRM_MODE_CONNECTOR_VIRTUAL);
@@ -458,14 +325,31 @@ virtio_gpu_user_framebuffer_create(struct drm_device *dev,
 	ret = virtio_gpu_framebuffer_init(dev, virtio_gpu_fb, mode_cmd, obj);
 	if (ret) {
 		kfree(virtio_gpu_fb);
-		if (obj)
-			drm_gem_object_unreference_unlocked(obj);
+		drm_gem_object_unreference_unlocked(obj);
 		return NULL;
 	}
 
 	return &virtio_gpu_fb->base;
 }
 
+static void vgdev_atomic_commit_tail(struct drm_atomic_state *state)
+{
+	struct drm_device *dev = state->dev;
+
+	drm_atomic_helper_commit_modeset_disables(dev, state);
+	drm_atomic_helper_commit_modeset_enables(dev, state);
+	drm_atomic_helper_commit_planes(dev, state, true);
+
+	drm_atomic_helper_commit_hw_done(state);
+
+	drm_atomic_helper_wait_for_vblanks(dev, state);
+	drm_atomic_helper_cleanup_planes(dev, state);
+}
+
+static struct drm_mode_config_helper_funcs virtio_mode_config_helpers = {
+	.atomic_commit_tail = vgdev_atomic_commit_tail,
+};
+
 static const struct drm_mode_config_funcs virtio_gpu_mode_funcs = {
 	.fb_create = virtio_gpu_user_framebuffer_create,
 	.atomic_check = drm_atomic_helper_check,
@@ -477,7 +361,8 @@ int virtio_gpu_modeset_init(struct virtio_gpu_device *vgdev)
 	int i;
 
 	drm_mode_config_init(vgdev->ddev);
-	vgdev->ddev->mode_config.funcs = (void *)&virtio_gpu_mode_funcs;
+	vgdev->ddev->mode_config.funcs = &virtio_gpu_mode_funcs;
+	vgdev->ddev->mode_config.helper_private = &virtio_mode_config_helpers;
 
 	/* modes will be validated against the framebuffer size */
 	vgdev->ddev->mode_config.min_width = XRES_MIN;
diff --git a/drivers/gpu/drm/virtio/virtgpu_drm_bus.c b/drivers/gpu/drm/virtio/virtgpu_drm_bus.c
index 88a39165edd5..7f0e93f87a55 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drm_bus.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drm_bus.c
@@ -27,16 +27,6 @@
 
 #include "virtgpu_drv.h"
 
-int drm_virtio_set_busid(struct drm_device *dev, struct drm_master *master)
-{
-	struct pci_dev *pdev = dev->pdev;
-
-	if (pdev) {
-		return drm_pci_set_busid(dev, master);
-	}
-	return 0;
-}
-
 static void virtio_pci_kick_out_firmware_fb(struct pci_dev *pci_dev)
 {
 	struct apertures_struct *ap;
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index 3cc7afa77a35..c13f70cfc461 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -117,7 +117,6 @@ static const struct file_operations virtio_gpu_driver_fops = {
 
 static struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME | DRIVER_RENDER | DRIVER_ATOMIC,
-	.set_busid = drm_virtio_set_busid,
 	.load = virtio_gpu_driver_load,
 	.unload = virtio_gpu_driver_unload,
 	.open = virtio_gpu_driver_open,
@@ -143,7 +142,7 @@ static struct drm_driver driver = {
 	.gem_prime_vunmap = virtgpu_gem_prime_vunmap,
 	.gem_prime_mmap = virtgpu_gem_prime_mmap,
 
-	.gem_free_object = virtio_gpu_gem_free_object,
+	.gem_free_object_unlocked = virtio_gpu_gem_free_object,
 	.gem_open_object = virtio_gpu_gem_object_open,
 	.gem_close_object = virtio_gpu_gem_object_close,
 	.fops = &virtio_gpu_driver_fops,
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index 0a54f43f846a..b18ef3111f0c 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -33,6 +33,7 @@
 
 #include <drm/drmP.h>
 #include <drm/drm_gem.h>
+#include <drm/drm_atomic.h>
 #include <drm/drm_crtc_helper.h>
 #include <ttm/ttm_bo_api.h>
 #include <ttm/ttm_bo_driver.h>
@@ -48,7 +49,6 @@
 #define DRIVER_PATCHLEVEL 1
 
 /* virtgpu_drm_bus.c */
-int drm_virtio_set_busid(struct drm_device *dev, struct drm_master *master);
 int drm_virtio_init(struct drm_driver *driver, struct virtio_device *vdev);
 
 struct virtio_gpu_object {
@@ -335,6 +335,7 @@ void virtio_gpu_modeset_fini(struct virtio_gpu_device *vgdev);
 
 /* virtio_gpu_plane.c */
 struct drm_plane *virtio_gpu_plane_init(struct virtio_gpu_device *vgdev,
+					enum drm_plane_type type,
 					int index);
 
 /* virtio_gpu_ttm.c */
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index 70b44a2345ab..925ca25209df 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -38,6 +38,10 @@ static const uint32_t virtio_gpu_formats[] = {
 	DRM_FORMAT_ABGR8888,
 };
 
+static const uint32_t virtio_gpu_cursor_formats[] = {
+	DRM_FORMAT_ARGB8888,
+};
+
 static void virtio_gpu_plane_destroy(struct drm_plane *plane)
 {
 	kfree(plane);
@@ -58,16 +62,22 @@ static int virtio_gpu_plane_atomic_check(struct drm_plane *plane,
 	return 0;
 }
 
-static void virtio_gpu_plane_atomic_update(struct drm_plane *plane,
-					   struct drm_plane_state *old_state)
+static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
+					    struct drm_plane_state *old_state)
 {
 	struct drm_device *dev = plane->dev;
 	struct virtio_gpu_device *vgdev = dev->dev_private;
-	struct virtio_gpu_output *output = drm_crtc_to_virtio_gpu_output(plane->crtc);
+	struct virtio_gpu_output *output = NULL;
 	struct virtio_gpu_framebuffer *vgfb;
 	struct virtio_gpu_object *bo;
 	uint32_t handle;
 
+	if (plane->state->crtc)
+		output = drm_crtc_to_virtio_gpu_output(plane->state->crtc);
+	if (old_state->crtc)
+		output = drm_crtc_to_virtio_gpu_output(old_state->crtc);
+	WARN_ON(!output);
+
 	if (plane->state->fb) {
 		vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
 		bo = gem_to_virtio_gpu_obj(vgfb->obj);
@@ -75,55 +85,149 @@ static void virtio_gpu_plane_atomic_update(struct drm_plane *plane,
 		if (bo->dumb) {
 			virtio_gpu_cmd_transfer_to_host_2d
 				(vgdev, handle, 0,
-				 cpu_to_le32(plane->state->crtc_w),
-				 cpu_to_le32(plane->state->crtc_h),
-				 plane->state->crtc_x, plane->state->crtc_y, NULL);
+				 cpu_to_le32(plane->state->src_w >> 16),
+				 cpu_to_le32(plane->state->src_h >> 16),
+				 plane->state->src_x >> 16,
+				 plane->state->src_y >> 16, NULL);
 		}
 	} else {
 		handle = 0;
 	}
 
-	DRM_DEBUG("handle 0x%x, crtc %dx%d+%d+%d\n", handle,
+	DRM_DEBUG("handle 0x%x, crtc %dx%d+%d+%d, src %dx%d+%d+%d\n", handle,
 		  plane->state->crtc_w, plane->state->crtc_h,
-		  plane->state->crtc_x, plane->state->crtc_y);
+		  plane->state->crtc_x, plane->state->crtc_y,
+		  plane->state->src_w >> 16,
+		  plane->state->src_h >> 16,
+		  plane->state->src_x >> 16,
+		  plane->state->src_y >> 16);
 	virtio_gpu_cmd_set_scanout(vgdev, output->index, handle,
-				   plane->state->crtc_w,
-				   plane->state->crtc_h,
-				   plane->state->crtc_x,
-				   plane->state->crtc_y);
+				   plane->state->src_w >> 16,
+				   plane->state->src_h >> 16,
+				   plane->state->src_x >> 16,
+				   plane->state->src_y >> 16);
 	virtio_gpu_cmd_resource_flush(vgdev, handle,
-				      plane->state->crtc_x,
-				      plane->state->crtc_y,
-				      plane->state->crtc_w,
-				      plane->state->crtc_h);
+				      plane->state->src_x >> 16,
+				      plane->state->src_y >> 16,
+				      plane->state->src_w >> 16,
+				      plane->state->src_h >> 16);
 }
 
+static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
+					   struct drm_plane_state *old_state)
+{
+	struct drm_device *dev = plane->dev;
+	struct virtio_gpu_device *vgdev = dev->dev_private;
+	struct virtio_gpu_output *output = NULL;
+	struct virtio_gpu_framebuffer *vgfb;
+	struct virtio_gpu_fence *fence = NULL;
+	struct virtio_gpu_object *bo = NULL;
+	uint32_t handle;
+	int ret = 0;
 
-static const struct drm_plane_helper_funcs virtio_gpu_plane_helper_funcs = {
+	if (plane->state->crtc)
+		output = drm_crtc_to_virtio_gpu_output(plane->state->crtc);
+	if (old_state->crtc)
+		output = drm_crtc_to_virtio_gpu_output(old_state->crtc);
+	WARN_ON(!output);
+
+	if (plane->state->fb) {
+		vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
+		bo = gem_to_virtio_gpu_obj(vgfb->obj);
+		handle = bo->hw_res_handle;
+	} else {
+		handle = 0;
+	}
+
+	if (bo && bo->dumb && (plane->state->fb != old_state->fb)) {
+		/* new cursor -- update & wait */
+		virtio_gpu_cmd_transfer_to_host_2d
+			(vgdev, handle, 0,
+			 cpu_to_le32(plane->state->crtc_w),
+			 cpu_to_le32(plane->state->crtc_h),
+			 0, 0, &fence);
+		ret = virtio_gpu_object_reserve(bo, false);
+		if (!ret) {
+			reservation_object_add_excl_fence(bo->tbo.resv,
+							  &fence->f);
+			fence_put(&fence->f);
+			fence = NULL;
+			virtio_gpu_object_unreserve(bo);
+			virtio_gpu_object_wait(bo, false);
+		}
+	}
+
+	if (plane->state->fb != old_state->fb) {
+		DRM_DEBUG("update, handle %d, pos +%d+%d, hot %d,%d\n", handle,
+			  plane->state->crtc_x,
+			  plane->state->crtc_y,
+			  plane->state->fb ? plane->state->fb->hot_x : 0,
+			  plane->state->fb ? plane->state->fb->hot_y : 0);
+		output->cursor.hdr.type =
+			cpu_to_le32(VIRTIO_GPU_CMD_UPDATE_CURSOR);
+		output->cursor.resource_id = cpu_to_le32(handle);
+		if (plane->state->fb) {
+			output->cursor.hot_x =
+				cpu_to_le32(plane->state->fb->hot_x);
+			output->cursor.hot_y =
+				cpu_to_le32(plane->state->fb->hot_y);
+		} else {
+			output->cursor.hot_x = cpu_to_le32(0);
+			output->cursor.hot_y = cpu_to_le32(0);
+		}
+	} else {
+		DRM_DEBUG("move +%d+%d\n",
+			  plane->state->crtc_x,
+			  plane->state->crtc_y);
+		output->cursor.hdr.type =
+			cpu_to_le32(VIRTIO_GPU_CMD_MOVE_CURSOR);
+	}
+	output->cursor.pos.x = cpu_to_le32(plane->state->crtc_x);
+	output->cursor.pos.y = cpu_to_le32(plane->state->crtc_y);
+	virtio_gpu_cursor_ping(vgdev, output);
+}
+
+static const struct drm_plane_helper_funcs virtio_gpu_primary_helper_funcs = {
+	.atomic_check		= virtio_gpu_plane_atomic_check,
+	.atomic_update		= virtio_gpu_primary_plane_update,
+};
+
+static const struct drm_plane_helper_funcs virtio_gpu_cursor_helper_funcs = {
 	.atomic_check		= virtio_gpu_plane_atomic_check,
-	.atomic_update		= virtio_gpu_plane_atomic_update,
+	.atomic_update		= virtio_gpu_cursor_plane_update,
 };
 
 struct drm_plane *virtio_gpu_plane_init(struct virtio_gpu_device *vgdev,
+					enum drm_plane_type type,
 					int index)
 {
 	struct drm_device *dev = vgdev->ddev;
+	const struct drm_plane_helper_funcs *funcs;
 	struct drm_plane *plane;
-	int ret;
+	const uint32_t *formats;
+	int ret, nformats;
 
 	plane = kzalloc(sizeof(*plane), GFP_KERNEL);
 	if (!plane)
 		return ERR_PTR(-ENOMEM);
 
+	if (type == DRM_PLANE_TYPE_CURSOR) {
+		formats = virtio_gpu_cursor_formats;
+		nformats = ARRAY_SIZE(virtio_gpu_cursor_formats);
+		funcs = &virtio_gpu_cursor_helper_funcs;
+	} else {
+		formats = virtio_gpu_formats;
+		nformats = ARRAY_SIZE(virtio_gpu_formats);
+		funcs = &virtio_gpu_primary_helper_funcs;
+	}
 	ret = drm_universal_plane_init(dev, plane, 1 << index,
 				       &virtio_gpu_plane_funcs,
-				       virtio_gpu_formats,
-				       ARRAY_SIZE(virtio_gpu_formats),
-				       DRM_PLANE_TYPE_PRIMARY, NULL);
+				       formats, nformats,
+				       type, NULL);
 	if (ret)
 		goto err_plane_init;
 
-	drm_plane_helper_add(plane, &virtio_gpu_plane_helper_funcs);
+	drm_plane_helper_add(plane, funcs);
 	return plane;
 
 err_plane_init:
diff --git a/drivers/gpu/drm/virtio/virtgpu_ttm.c b/drivers/gpu/drm/virtio/virtgpu_ttm.c
index a0580815629f..80482ac5f95d 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ttm.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ttm.c
@@ -375,6 +375,12 @@ static int virtio_gpu_bo_move(struct ttm_buffer_object *bo,
 			      bool no_wait_gpu,
 			      struct ttm_mem_reg *new_mem)
 {
+	int ret;
+
+	ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
+	if (ret)
+		return ret;
+
 	virtio_gpu_move_null(bo, new_mem);
 	return 0;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
index 67cebb23c940..aa04fb0159a7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
@@ -293,13 +293,10 @@ static int vmw_cmdbuf_header_submit(struct vmw_cmdbuf_header *header)
 	struct vmw_cmdbuf_man *man = header->man;
 	u32 val;
 
-	if (sizeof(header->handle) > 4)
-		val = (header->handle >> 32);
-	else
-		val = 0;
+	val = upper_32_bits(header->handle);
 	vmw_write(man->dev_priv, SVGA_REG_COMMAND_HIGH, val);
 
-	val = (header->handle & 0xFFFFFFFFULL);
+	val = lower_32_bits(header->handle);
 	val |= header->cb_context & SVGA_CB_CONTEXT_MASK;
 	vmw_write(man->dev_priv, SVGA_REG_COMMAND_LOW, val);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 8d528fcf6e96..e8ae3dc476d1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1053,15 +1053,14 @@ static struct vmw_master *vmw_master_check(struct drm_device *dev,
 	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
 	struct vmw_master *vmaster;
 
-	if (file_priv->minor->type != DRM_MINOR_LEGACY ||
-	    !(flags & DRM_AUTH))
+	if (!drm_is_primary_client(file_priv) || !(flags & DRM_AUTH))
 		return NULL;
 
 	ret = mutex_lock_interruptible(&dev->master_mutex);
 	if (unlikely(ret != 0))
 		return ERR_PTR(-ERESTARTSYS);
 
-	if (file_priv->is_master) {
+	if (drm_is_current_master(file_priv)) {
 		mutex_unlock(&dev->master_mutex);
 		return NULL;
 	}
@@ -1240,8 +1239,7 @@ static int vmw_master_set(struct drm_device *dev,
 }
 
 static void vmw_master_drop(struct drm_device *dev,
-			    struct drm_file *file_priv,
-			    bool from_release)
+			    struct drm_file *file_priv)
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
 	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 89fb19443a3f..74304b03f9d4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -32,6 +32,7 @@
 #include <drm/drmP.h>
 #include <drm/vmwgfx_drm.h>
 #include <drm/drm_hashtab.h>
+#include <drm/drm_auth.h>
 #include <linux/suspend.h>
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_object.h>
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 1a1a87cbf109..dc5beff2b4aa 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -3625,9 +3625,7 @@ static int vmw_resize_cmd_bounce(struct vmw_sw_context *sw_context,
 				   (sw_context->cmd_bounce_size >> 1));
 	}
 
-	if (sw_context->cmd_bounce != NULL)
-		vfree(sw_context->cmd_bounce);
-
+	vfree(sw_context->cmd_bounce);
 	sw_context->cmd_bounce = vmalloc(sw_context->cmd_bounce_size);
 
 	if (sw_context->cmd_bounce == NULL) {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index e959df6ede83..26ac8e80a478 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -46,7 +46,7 @@ struct vmw_fence_manager {
 	bool goal_irq_on; /* Protected by @goal_irq_mutex */
 	bool seqno_valid; /* Protected by @lock, and may not be set to true
 			     without the @goal_irq_mutex held. */
-	unsigned ctx;
+	u64 ctx;
 };
 
 struct vmw_user_fence {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index e29da45a2847..bf28ccc150df 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1404,9 +1404,9 @@ static int vmw_du_update_layout(struct vmw_private *dev_priv, unsigned num,
 	return 0;
 }
 
-void vmw_du_crtc_gamma_set(struct drm_crtc *crtc,
-			   u16 *r, u16 *g, u16 *b,
-			   uint32_t start, uint32_t size)
+int vmw_du_crtc_gamma_set(struct drm_crtc *crtc,
+			  u16 *r, u16 *g, u16 *b,
+			  uint32_t size)
 {
 	struct vmw_private *dev_priv = vmw_priv(crtc->dev);
 	int i;
@@ -1418,6 +1418,8 @@ void vmw_du_crtc_gamma_set(struct drm_crtc *crtc,
 		vmw_write(dev_priv, SVGA_PALETTE_BASE + i * 3 + 1, g[i] >> 8);
 		vmw_write(dev_priv, SVGA_PALETTE_BASE + i * 3 + 2, b[i] >> 8);
 	}
+
+	return 0;
 }
 
 int vmw_du_connector_dpms(struct drm_connector *connector, int mode)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 57203212c501..ff4803c107bc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -195,9 +195,9 @@ struct vmw_display_unit {
 void vmw_du_cleanup(struct vmw_display_unit *du);
 void vmw_du_crtc_save(struct drm_crtc *crtc);
 void vmw_du_crtc_restore(struct drm_crtc *crtc);
-void vmw_du_crtc_gamma_set(struct drm_crtc *crtc,
+int vmw_du_crtc_gamma_set(struct drm_crtc *crtc,
 			   u16 *r, u16 *g, u16 *b,
-			   uint32_t start, uint32_t size);
+			   uint32_t size);
 int vmw_du_crtc_cursor_set2(struct drm_crtc *crtc, struct drm_file *file_priv,
 			    uint32_t handle, uint32_t width, uint32_t height,
 			    int32_t hot_x, int32_t hot_y);
diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
index a18db4d5347c..c5d82a8a2ec9 100644
--- a/drivers/gpu/host1x/cdma.c
+++ b/drivers/gpu/host1x/cdma.c
@@ -96,12 +96,12 @@ fail:
  */
 static void host1x_pushbuffer_push(struct push_buffer *pb, u32 op1, u32 op2)
 {
-	u32 pos = pb->pos;
-	u32 *p = (u32 *)((void *)pb->mapped + pos);
-	WARN_ON(pos == pb->fence);
+	u32 *p = (u32 *)((void *)pb->mapped + pb->pos);
+
+	WARN_ON(pb->pos == pb->fence);
 	*(p++) = op1;
 	*(p++) = op2;
-	pb->pos = (pos + 8) & (pb->size_bytes - 1);
+	pb->pos = (pb->pos + 8) & (pb->size_bytes - 1);
 }
 
 /*
@@ -134,14 +134,19 @@ unsigned int host1x_cdma_wait_locked(struct host1x_cdma *cdma,
 				     enum cdma_event event)
 {
 	for (;;) {
+		struct push_buffer *pb = &cdma->push_buffer;
 		unsigned int space;
 
-		if (event == CDMA_EVENT_SYNC_QUEUE_EMPTY)
+		switch (event) {
+		case CDMA_EVENT_SYNC_QUEUE_EMPTY:
 			space = list_empty(&cdma->sync_queue) ? 1 : 0;
-		else if (event == CDMA_EVENT_PUSH_BUFFER_SPACE) {
-			struct push_buffer *pb = &cdma->push_buffer;
+			break;
+
+		case CDMA_EVENT_PUSH_BUFFER_SPACE:
 			space = host1x_pushbuffer_space(pb);
-		} else {
+			break;
+
+		default:
 			WARN_ON(1);
 			return -EINVAL;
 		}
@@ -159,12 +164,14 @@ unsigned int host1x_cdma_wait_locked(struct host1x_cdma *cdma,
 			mutex_lock(&cdma->lock);
 			continue;
 		}
+
 		cdma->event = event;
 
 		mutex_unlock(&cdma->lock);
 		down(&cdma->sem);
 		mutex_lock(&cdma->lock);
 	}
+
 	return 0;
 }
 
@@ -234,6 +241,7 @@ static void update_cdma_locked(struct host1x_cdma *cdma)
 			/* Start timer on next pending syncpt */
 			if (job->timeout)
 				cdma_start_timer_locked(cdma, job);
+
 			break;
 		}
 
@@ -247,7 +255,9 @@ static void update_cdma_locked(struct host1x_cdma *cdma)
 		/* Pop push buffer slots */
 		if (job->num_slots) {
 			struct push_buffer *pb = &cdma->push_buffer;
+
 			host1x_pushbuffer_pop(pb, job->num_slots);
+
 			if (cdma->event == CDMA_EVENT_PUSH_BUFFER_SPACE)
 				signal = true;
 		}
@@ -269,11 +279,9 @@ static void update_cdma_locked(struct host1x_cdma *cdma)
 void host1x_cdma_update_sync_queue(struct host1x_cdma *cdma,
 				   struct device *dev)
 {
-	u32 restart_addr;
-	u32 syncpt_incrs;
-	struct host1x_job *job = NULL;
-	u32 syncpt_val;
 	struct host1x *host1x = cdma_to_host1x(cdma);
+	u32 restart_addr, syncpt_incrs, syncpt_val;
+	struct host1x_job *job = NULL;
 
 	syncpt_val = host1x_syncpt_load(cdma->timeout.syncpt);
 
@@ -342,9 +350,11 @@ void host1x_cdma_update_sync_queue(struct host1x_cdma *cdma,
 		syncpt_val += syncpt_incrs;
 	}
 
-	/* The following sumbits from the same client may be dependent on the
+	/*
+	 * The following sumbits from the same client may be dependent on the
 	 * failed submit and therefore they may fail. Force a small timeout
-	 * to make the queue cleanup faster */
+	 * to make the queue cleanup faster.
+	 */
 
 	list_for_each_entry_from(job, &cdma->sync_queue, list)
 		if (job->client == cdma->timeout.client)
@@ -375,6 +385,7 @@ int host1x_cdma_init(struct host1x_cdma *cdma)
 	err = host1x_pushbuffer_init(&cdma->push_buffer);
 	if (err)
 		return err;
+
 	return 0;
 }
 
@@ -410,6 +421,7 @@ int host1x_cdma_begin(struct host1x_cdma *cdma, struct host1x_job *job)
 		/* init state on first submit with timeout value */
 		if (!cdma->timeout.initialized) {
 			int err;
+
 			err = host1x_hw_cdma_timeout_init(host1x, cdma,
 							  job->syncpt_id);
 			if (err) {
@@ -418,6 +430,7 @@ int host1x_cdma_begin(struct host1x_cdma *cdma, struct host1x_job *job)
 			}
 		}
 	}
+
 	if (!cdma->running)
 		host1x_hw_cdma_start(host1x, cdma);
 
@@ -448,6 +461,7 @@ void host1x_cdma_push(struct host1x_cdma *cdma, u32 op1, u32 op2)
 		slots_free = host1x_cdma_wait_locked(cdma,
 						CDMA_EVENT_PUSH_BUFFER_SPACE);
 	}
+
 	cdma->slots_free = slots_free - 1;
 	cdma->slots_used++;
 	host1x_pushbuffer_push(pb, op1, op2);
diff --git a/drivers/gpu/host1x/channel.c b/drivers/gpu/host1x/channel.c
index b4ae3affb987..8f437d924c10 100644
--- a/drivers/gpu/host1x/channel.c
+++ b/drivers/gpu/host1x/channel.c
@@ -83,9 +83,10 @@ EXPORT_SYMBOL(host1x_channel_put);
 struct host1x_channel *host1x_channel_request(struct device *dev)
 {
 	struct host1x *host = dev_get_drvdata(dev->parent);
-	int max_channels = host->info->nb_channels;
+	unsigned int max_channels = host->info->nb_channels;
 	struct host1x_channel *channel = NULL;
-	int index, err;
+	unsigned long index;
+	int err;
 
 	mutex_lock(&host->chlist_mutex);
 
diff --git a/drivers/gpu/host1x/debug.c b/drivers/gpu/host1x/debug.c
index ee3d12b51c50..d9330fcc62ad 100644
--- a/drivers/gpu/host1x/debug.c
+++ b/drivers/gpu/host1x/debug.c
@@ -39,6 +39,7 @@ void host1x_debug_output(struct output *o, const char *fmt, ...)
 	va_start(args, fmt);
 	len = vsnprintf(o->buf, sizeof(o->buf), fmt, args);
 	va_end(args);
+
 	o->fn(o->ctx, o->buf, len);
 }
 
@@ -48,13 +49,17 @@ static int show_channels(struct host1x_channel *ch, void *data, bool show_fifo)
 	struct output *o = data;
 
 	mutex_lock(&ch->reflock);
+
 	if (ch->refcount) {
 		mutex_lock(&ch->cdma.lock);
+
 		if (show_fifo)
 			host1x_hw_show_channel_fifo(m, ch, o);
+
 		host1x_hw_show_channel_cdma(m, ch, o);
 		mutex_unlock(&ch->cdma.lock);
 	}
+
 	mutex_unlock(&ch->reflock);
 
 	return 0;
@@ -62,22 +67,27 @@ static int show_channels(struct host1x_channel *ch, void *data, bool show_fifo)
 
 static void show_syncpts(struct host1x *m, struct output *o)
 {
-	int i;
+	unsigned int i;
+
 	host1x_debug_output(o, "---- syncpts ----\n");
+
 	for (i = 0; i < host1x_syncpt_nb_pts(m); i++) {
 		u32 max = host1x_syncpt_read_max(m->syncpt + i);
 		u32 min = host1x_syncpt_load(m->syncpt + i);
+
 		if (!min && !max)
 			continue;
-		host1x_debug_output(o, "id %d (%s) min %d max %d\n",
+
+		host1x_debug_output(o, "id %u (%s) min %d max %d\n",
 				    i, m->syncpt[i].name, min, max);
 	}
 
 	for (i = 0; i < host1x_syncpt_nb_bases(m); i++) {
 		u32 base_val;
+
 		base_val = host1x_syncpt_load_wait_base(m->syncpt + i);
 		if (base_val)
-			host1x_debug_output(o, "waitbase id %d val %d\n", i,
+			host1x_debug_output(o, "waitbase id %u val %d\n", i,
 					    base_val);
 	}
 
@@ -114,7 +124,9 @@ static int host1x_debug_show_all(struct seq_file *s, void *unused)
 		.fn = write_to_seqfile,
 		.ctx = s
 	};
+
 	show_all(s->private, &o);
+
 	return 0;
 }
 
@@ -124,7 +136,9 @@ static int host1x_debug_show(struct seq_file *s, void *unused)
 		.fn = write_to_seqfile,
 		.ctx = s
 	};
+
 	show_all_no_fifo(s->private, &o);
+
 	return 0;
 }
 
@@ -134,10 +148,10 @@ static int host1x_debug_open_all(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations host1x_debug_all_fops = {
-	.open		= host1x_debug_open_all,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
+	.open = host1x_debug_open_all,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
 };
 
 static int host1x_debug_open(struct inode *inode, struct file *file)
@@ -146,10 +160,10 @@ static int host1x_debug_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations host1x_debug_fops = {
-	.open		= host1x_debug_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
+	.open = host1x_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
 };
 
 static void host1x_debugfs_init(struct host1x *host1x)
@@ -201,6 +215,7 @@ void host1x_debug_dump(struct host1x *host1x)
 	struct output o = {
 		.fn = write_to_printk
 	};
+
 	show_all(host1x, &o);
 }
 
@@ -209,5 +224,6 @@ void host1x_debug_dump_syncpts(struct host1x *host1x)
 	struct output o = {
 		.fn = write_to_printk
 	};
+
 	show_syncpts(host1x, &o);
 }
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index ff348690df94..a62317af76ad 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -63,13 +63,13 @@ u32 host1x_ch_readl(struct host1x_channel *ch, u32 r)
 }
 
 static const struct host1x_info host1x01_info = {
-	.nb_channels	= 8,
-	.nb_pts		= 32,
-	.nb_mlocks	= 16,
-	.nb_bases	= 8,
-	.init		= host1x01_init,
-	.sync_offset	= 0x3000,
-	.dma_mask	= DMA_BIT_MASK(32),
+	.nb_channels = 8,
+	.nb_pts = 32,
+	.nb_mlocks = 16,
+	.nb_bases = 8,
+	.init = host1x01_init,
+	.sync_offset = 0x3000,
+	.dma_mask = DMA_BIT_MASK(32),
 };
 
 static const struct host1x_info host1x02_info = {
@@ -102,7 +102,7 @@ static const struct host1x_info host1x05_info = {
 	.dma_mask = DMA_BIT_MASK(34),
 };
 
-static struct of_device_id host1x_of_match[] = {
+static const struct of_device_id host1x_of_match[] = {
 	{ .compatible = "nvidia,tegra210-host1x", .data = &host1x05_info, },
 	{ .compatible = "nvidia,tegra124-host1x", .data = &host1x04_info, },
 	{ .compatible = "nvidia,tegra114-host1x", .data = &host1x02_info, },
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index dace124994bb..5220510f39da 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/drivers/gpu/host1x/dev.h
@@ -45,7 +45,7 @@ struct host1x_cdma_ops {
 	void (*start)(struct host1x_cdma *cdma);
 	void (*stop)(struct host1x_cdma *cdma);
 	void (*flush)(struct  host1x_cdma *cdma);
-	int (*timeout_init)(struct host1x_cdma *cdma, u32 syncpt_id);
+	int (*timeout_init)(struct host1x_cdma *cdma, unsigned int syncpt);
 	void (*timeout_destroy)(struct host1x_cdma *cdma);
 	void (*freeze)(struct host1x_cdma *cdma);
 	void (*resume)(struct host1x_cdma *cdma, u32 getptr);
@@ -82,21 +82,21 @@ struct host1x_intr_ops {
 	int (*init_host_sync)(struct host1x *host, u32 cpm,
 		void (*syncpt_thresh_work)(struct work_struct *work));
 	void (*set_syncpt_threshold)(
-		struct host1x *host, u32 id, u32 thresh);
-	void (*enable_syncpt_intr)(struct host1x *host, u32 id);
-	void (*disable_syncpt_intr)(struct host1x *host, u32 id);
+		struct host1x *host, unsigned int id, u32 thresh);
+	void (*enable_syncpt_intr)(struct host1x *host, unsigned int id);
+	void (*disable_syncpt_intr)(struct host1x *host, unsigned int id);
 	void (*disable_all_syncpt_intrs)(struct host1x *host);
 	int (*free_syncpt_irq)(struct host1x *host);
 };
 
 struct host1x_info {
-	int	nb_channels;		/* host1x: num channels supported */
-	int	nb_pts;			/* host1x: num syncpoints supported */
-	int	nb_bases;		/* host1x: num syncpoints supported */
-	int	nb_mlocks;		/* host1x: number of mlocks */
-	int	(*init)(struct host1x *); /* initialize per SoC ops */
-	int	sync_offset;
-	u64	dma_mask;		/* mask of addressable memory */
+	unsigned int nb_channels; /* host1x: number of channels supported */
+	unsigned int nb_pts; /* host1x: number of syncpoints supported */
+	unsigned int nb_bases; /* host1x: number of syncpoint bases supported */
+	unsigned int nb_mlocks; /* host1x: number of mlocks supported */
+	int (*init)(struct host1x *host1x); /* initialize per SoC ops */
+	unsigned int sync_offset; /* offset of syncpoint registers */
+	u64 dma_mask; /* mask of addressable memory */
 };
 
 struct host1x {
@@ -109,7 +109,6 @@ struct host1x {
 	struct clk *clk;
 
 	struct mutex intr_mutex;
-	struct workqueue_struct *intr_wq;
 	int intr_syncpt_irq;
 
 	const struct host1x_syncpt_ops *syncpt_op;
@@ -183,19 +182,20 @@ static inline int host1x_hw_intr_init_host_sync(struct host1x *host, u32 cpm,
 }
 
 static inline void host1x_hw_intr_set_syncpt_threshold(struct host1x *host,
-						       u32 id, u32 thresh)
+						       unsigned int id,
+						       u32 thresh)
 {
 	host->intr_op->set_syncpt_threshold(host, id, thresh);
 }
 
 static inline void host1x_hw_intr_enable_syncpt_intr(struct host1x *host,
-						     u32 id)
+						     unsigned int id)
 {
 	host->intr_op->enable_syncpt_intr(host, id);
 }
 
 static inline void host1x_hw_intr_disable_syncpt_intr(struct host1x *host,
-						      u32 id)
+						      unsigned int id)
 {
 	host->intr_op->disable_syncpt_intr(host, id);
 }
@@ -212,9 +212,9 @@ static inline int host1x_hw_intr_free_syncpt_irq(struct host1x *host)
 
 static inline int host1x_hw_channel_init(struct host1x *host,
 					 struct host1x_channel *channel,
-					 int chid)
+					 unsigned int id)
 {
-	return host->channel_op->init(channel, host, chid);
+	return host->channel_op->init(channel, host, id);
 }
 
 static inline int host1x_hw_channel_submit(struct host1x *host,
@@ -243,9 +243,9 @@ static inline void host1x_hw_cdma_flush(struct host1x *host,
 
 static inline int host1x_hw_cdma_timeout_init(struct host1x *host,
 					      struct host1x_cdma *cdma,
-					      u32 syncpt_id)
+					      unsigned int syncpt)
 {
-	return host->cdma_op->timeout_init(cdma, syncpt_id);
+	return host->cdma_op->timeout_init(cdma, syncpt);
 }
 
 static inline void host1x_hw_cdma_timeout_destroy(struct host1x *host,
diff --git a/drivers/gpu/host1x/hw/cdma_hw.c b/drivers/gpu/host1x/hw/cdma_hw.c
index 305ea8f3382d..659c1bbfeeba 100644
--- a/drivers/gpu/host1x/hw/cdma_hw.c
+++ b/drivers/gpu/host1x/hw/cdma_hw.c
@@ -41,7 +41,7 @@ static void cdma_timeout_cpu_incr(struct host1x_cdma *cdma, u32 getptr,
 {
 	struct host1x *host1x = cdma_to_host1x(cdma);
 	struct push_buffer *pb = &cdma->push_buffer;
-	u32 i;
+	unsigned int i;
 
 	for (i = 0; i < syncpt_incrs; i++)
 		host1x_syncpt_incr(cdma->timeout.syncpt);
@@ -58,6 +58,7 @@ static void cdma_timeout_cpu_incr(struct host1x_cdma *cdma, u32 getptr,
 			&pb->phys, getptr);
 		getptr = (getptr + 8) & (pb->size_bytes - 1);
 	}
+
 	wmb();
 }
 
@@ -162,12 +163,14 @@ static void cdma_stop(struct host1x_cdma *cdma)
 	struct host1x_channel *ch = cdma_to_channel(cdma);
 
 	mutex_lock(&cdma->lock);
+
 	if (cdma->running) {
 		host1x_cdma_wait_locked(cdma, CDMA_EVENT_SYNC_QUEUE_EMPTY);
 		host1x_ch_writel(ch, HOST1X_CHANNEL_DMACTRL_DMASTOP,
 				 HOST1X_CHANNEL_DMACTRL);
 		cdma->running = false;
 	}
+
 	mutex_unlock(&cdma->lock);
 }
 
@@ -213,11 +216,11 @@ static void cdma_resume(struct host1x_cdma *cdma, u32 getptr)
 	u32 cmdproc_stop;
 
 	dev_dbg(host1x->dev,
-		"resuming channel (id %d, DMAGET restart = 0x%x)\n",
+		"resuming channel (id %u, DMAGET restart = 0x%x)\n",
 		ch->id, getptr);
 
 	cmdproc_stop = host1x_sync_readl(host1x, HOST1X_SYNC_CMDPROC_STOP);
-	cmdproc_stop &= ~(BIT(ch->id));
+	cmdproc_stop &= ~BIT(ch->id);
 	host1x_sync_writel(host1x, cmdproc_stop, HOST1X_SYNC_CMDPROC_STOP);
 
 	cdma->torndown = false;
@@ -231,14 +234,11 @@ static void cdma_resume(struct host1x_cdma *cdma, u32 getptr)
  */
 static void cdma_timeout_handler(struct work_struct *work)
 {
+	u32 prev_cmdproc, cmdproc_stop, syncpt_val;
 	struct host1x_cdma *cdma;
 	struct host1x *host1x;
 	struct host1x_channel *ch;
 
-	u32 syncpt_val;
-
-	u32 prev_cmdproc, cmdproc_stop;
-
 	cdma = container_of(to_delayed_work(work), struct host1x_cdma,
 			    timeout.wq);
 	host1x = cdma_to_host1x(cdma);
@@ -277,9 +277,9 @@ static void cdma_timeout_handler(struct work_struct *work)
 		return;
 	}
 
-	dev_warn(host1x->dev, "%s: timeout: %d (%s), HW thresh %d, done %d\n",
-		__func__, cdma->timeout.syncpt->id, cdma->timeout.syncpt->name,
-		syncpt_val, cdma->timeout.syncpt_val);
+	dev_warn(host1x->dev, "%s: timeout: %u (%s), HW thresh %d, done %d\n",
+		 __func__, cdma->timeout.syncpt->id, cdma->timeout.syncpt->name,
+		 syncpt_val, cdma->timeout.syncpt_val);
 
 	/* stop HW, resetting channel/module */
 	host1x_hw_cdma_freeze(host1x, cdma);
@@ -291,7 +291,7 @@ static void cdma_timeout_handler(struct work_struct *work)
 /*
  * Init timeout resources
  */
-static int cdma_timeout_init(struct host1x_cdma *cdma, u32 syncpt_id)
+static int cdma_timeout_init(struct host1x_cdma *cdma, unsigned int syncpt)
 {
 	INIT_DELAYED_WORK(&cdma->timeout.wq, cdma_timeout_handler);
 	cdma->timeout.initialized = true;
@@ -306,6 +306,7 @@ static void cdma_timeout_destroy(struct host1x_cdma *cdma)
 {
 	if (cdma->timeout.initialized)
 		cancel_delayed_work(&cdma->timeout.wq);
+
 	cdma->timeout.initialized = false;
 }
 
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index 946c332c3906..5e8df78b7acd 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -46,6 +46,7 @@ static void trace_write_gather(struct host1x_cdma *cdma, struct host1x_bo *bo,
 		 */
 		for (i = 0; i < words; i += TRACE_MAX_LENGTH) {
 			u32 num_words = min(words - i, TRACE_MAX_LENGTH);
+
 			offset += i * sizeof(u32);
 
 			trace_host1x_cdma_push_gather(dev_name(dev), bo,
@@ -66,6 +67,7 @@ static void submit_gathers(struct host1x_job *job)
 		struct host1x_job_gather *g = &job->gathers[i];
 		u32 op1 = host1x_opcode_gather(g->words);
 		u32 op2 = g->base + g->offset;
+
 		trace_write_gather(cdma, g->bo, g->offset, op1 & 0xffff);
 		host1x_cdma_push(cdma, op1, op2);
 	}
@@ -75,7 +77,8 @@ static inline void synchronize_syncpt_base(struct host1x_job *job)
 {
 	struct host1x *host = dev_get_drvdata(job->channel->dev->parent);
 	struct host1x_syncpt *sp = host->syncpt + job->syncpt_id;
-	u32 id, value;
+	unsigned int id;
+	u32 value;
 
 	value = host1x_syncpt_read_max(sp);
 	id = sp->base->id;
diff --git a/drivers/gpu/host1x/hw/debug_hw.c b/drivers/gpu/host1x/hw/debug_hw.c
index cc3f1825c735..7a4a3286e4a7 100644
--- a/drivers/gpu/host1x/hw/debug_hw.c
+++ b/drivers/gpu/host1x/hw/debug_hw.c
@@ -40,8 +40,7 @@ enum {
 
 static unsigned int show_channel_command(struct output *o, u32 val)
 {
-	unsigned mask;
-	unsigned subop;
+	unsigned int mask, subop;
 
 	switch (val >> 28) {
 	case HOST1X_OPCODE_SETCLASS:
@@ -51,12 +50,11 @@ static unsigned int show_channel_command(struct output *o, u32 val)
 					    val >> 6 & 0x3ff,
 					    val >> 16 & 0xfff, mask);
 			return hweight8(mask);
-		} else {
-			host1x_debug_output(o, "SETCL(class=%03x)\n",
-					    val >> 6 & 0x3ff);
-			return 0;
 		}
 
+		host1x_debug_output(o, "SETCL(class=%03x)\n", val >> 6 & 0x3ff);
+		return 0;
+
 	case HOST1X_OPCODE_INCR:
 		host1x_debug_output(o, "INCR(offset=%03x, [",
 				    val >> 16 & 0xfff);
@@ -143,7 +141,8 @@ static void show_channel_gathers(struct output *o, struct host1x_cdma *cdma)
 	struct host1x_job *job;
 
 	list_for_each_entry(job, &cdma->sync_queue, list) {
-		int i;
+		unsigned int i;
+
 		host1x_debug_output(o, "\n%p: JOB, syncpt_id=%d, syncpt_val=%d, first_get=%08x, timeout=%d num_slots=%d, num_handles=%d\n",
 				    job, job->syncpt_id, job->syncpt_end,
 				    job->first_get, job->timeout,
@@ -190,7 +189,7 @@ static void host1x_debug_show_channel_cdma(struct host1x *host,
 	cbread = host1x_sync_readl(host, HOST1X_SYNC_CBREAD(ch->id));
 	cbstat = host1x_sync_readl(host, HOST1X_SYNC_CBSTAT(ch->id));
 
-	host1x_debug_output(o, "%d-%s: ", ch->id, dev_name(ch->dev));
+	host1x_debug_output(o, "%u-%s: ", ch->id, dev_name(ch->dev));
 
 	if (HOST1X_CHANNEL_DMACTRL_DMASTOP_V(dmactrl) ||
 	    !ch->cdma.push_buffer.mapped) {
@@ -200,14 +199,13 @@ static void host1x_debug_show_channel_cdma(struct host1x *host,
 
 	if (HOST1X_SYNC_CBSTAT_CBCLASS_V(cbstat) == HOST1X_CLASS_HOST1X &&
 	    HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat) ==
-	    HOST1X_UCLASS_WAIT_SYNCPT)
+			HOST1X_UCLASS_WAIT_SYNCPT)
 		host1x_debug_output(o, "waiting on syncpt %d val %d\n",
 				    cbread >> 24, cbread & 0xffffff);
 	else if (HOST1X_SYNC_CBSTAT_CBCLASS_V(cbstat) ==
-	   HOST1X_CLASS_HOST1X &&
-	   HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat) ==
-	   HOST1X_UCLASS_WAIT_SYNCPT_BASE) {
-
+				HOST1X_CLASS_HOST1X &&
+		 HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat) ==
+				HOST1X_UCLASS_WAIT_SYNCPT_BASE) {
 		base = (cbread >> 16) & 0xff;
 		baseval =
 			host1x_sync_readl(host, HOST1X_SYNC_SYNCPT_BASE(base));
@@ -236,7 +234,7 @@ static void host1x_debug_show_channel_fifo(struct host1x *host,
 	u32 val, rd_ptr, wr_ptr, start, end;
 	unsigned int data_count = 0;
 
-	host1x_debug_output(o, "%d: fifo:\n", ch->id);
+	host1x_debug_output(o, "%u: fifo:\n", ch->id);
 
 	val = host1x_ch_readl(ch, HOST1X_CHANNEL_FIFOSTAT);
 	host1x_debug_output(o, "FIFOSTAT %08x\n", val);
@@ -290,20 +288,22 @@ static void host1x_debug_show_channel_fifo(struct host1x *host,
 
 static void host1x_debug_show_mlocks(struct host1x *host, struct output *o)
 {
-	int i;
+	unsigned int i;
 
 	host1x_debug_output(o, "---- mlocks ----\n");
+
 	for (i = 0; i < host1x_syncpt_nb_mlocks(host); i++) {
 		u32 owner =
 			host1x_sync_readl(host, HOST1X_SYNC_MLOCK_OWNER(i));
 		if (HOST1X_SYNC_MLOCK_OWNER_CH_OWNS_V(owner))
-			host1x_debug_output(o, "%d: locked by channel %d\n",
+			host1x_debug_output(o, "%u: locked by channel %u\n",
 				i, HOST1X_SYNC_MLOCK_OWNER_CHID_V(owner));
 		else if (HOST1X_SYNC_MLOCK_OWNER_CPU_OWNS_V(owner))
-			host1x_debug_output(o, "%d: locked by cpu\n", i);
+			host1x_debug_output(o, "%u: locked by cpu\n", i);
 		else
-			host1x_debug_output(o, "%d: unlocked\n", i);
+			host1x_debug_output(o, "%u: unlocked\n", i);
 	}
+
 	host1x_debug_output(o, "\n");
 }
 
diff --git a/drivers/gpu/host1x/hw/intr_hw.c b/drivers/gpu/host1x/hw/intr_hw.c
index e1e31e9e67cd..dacb8009a605 100644
--- a/drivers/gpu/host1x/hw/intr_hw.c
+++ b/drivers/gpu/host1x/hw/intr_hw.c
@@ -38,14 +38,14 @@ static void host1x_intr_syncpt_handle(struct host1x_syncpt *syncpt)
 	host1x_sync_writel(host, BIT_MASK(id),
 		HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(BIT_WORD(id)));
 
-	queue_work(host->intr_wq, &syncpt->intr.work);
+	schedule_work(&syncpt->intr.work);
 }
 
 static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id)
 {
 	struct host1x *host = dev_id;
 	unsigned long reg;
-	int i, id;
+	unsigned int i, id;
 
 	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); i++) {
 		reg = host1x_sync_readl(host,
@@ -62,7 +62,7 @@ static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id)
 
 static void _host1x_intr_disable_all_syncpt_intrs(struct host1x *host)
 {
-	u32 i;
+	unsigned int i;
 
 	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); ++i) {
 		host1x_sync_writel(host, 0xffffffffu,
@@ -72,10 +72,12 @@ static void _host1x_intr_disable_all_syncpt_intrs(struct host1x *host)
 	}
 }
 
-static int _host1x_intr_init_host_sync(struct host1x *host, u32 cpm,
-	void (*syncpt_thresh_work)(struct work_struct *))
+static int
+_host1x_intr_init_host_sync(struct host1x *host, u32 cpm,
+			    void (*syncpt_thresh_work)(struct work_struct *))
 {
-	int i, err;
+	unsigned int i;
+	int err;
 
 	host1x_hw_intr_disable_all_syncpt_intrs(host);
 
@@ -106,18 +108,21 @@ static int _host1x_intr_init_host_sync(struct host1x *host, u32 cpm,
 }
 
 static void _host1x_intr_set_syncpt_threshold(struct host1x *host,
-	u32 id, u32 thresh)
+					      unsigned int id,
+					      u32 thresh)
 {
 	host1x_sync_writel(host, thresh, HOST1X_SYNC_SYNCPT_INT_THRESH(id));
 }
 
-static void _host1x_intr_enable_syncpt_intr(struct host1x *host, u32 id)
+static void _host1x_intr_enable_syncpt_intr(struct host1x *host,
+					    unsigned int id)
 {
 	host1x_sync_writel(host, BIT_MASK(id),
 		HOST1X_SYNC_SYNCPT_THRESH_INT_ENABLE_CPU0(BIT_WORD(id)));
 }
 
-static void _host1x_intr_disable_syncpt_intr(struct host1x *host, u32 id)
+static void _host1x_intr_disable_syncpt_intr(struct host1x *host,
+					     unsigned int id)
 {
 	host1x_sync_writel(host, BIT_MASK(id),
 		HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(BIT_WORD(id)));
@@ -127,8 +132,13 @@ static void _host1x_intr_disable_syncpt_intr(struct host1x *host, u32 id)
 
 static int _host1x_free_syncpt_irq(struct host1x *host)
 {
+	unsigned int i;
+
 	devm_free_irq(host->dev, host->intr_syncpt_irq, host);
-	flush_workqueue(host->intr_wq);
+
+	for (i = 0; i < host->info->nb_pts; i++)
+		cancel_work_sync(&host->syncpt[i].intr.work);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/host1x/hw/syncpt_hw.c b/drivers/gpu/host1x/hw/syncpt_hw.c
index 56e85395ac24..c93f74fcce72 100644
--- a/drivers/gpu/host1x/hw/syncpt_hw.c
+++ b/drivers/gpu/host1x/hw/syncpt_hw.c
@@ -26,8 +26,9 @@
  */
 static void syncpt_restore(struct host1x_syncpt *sp)
 {
+	u32 min = host1x_syncpt_read_min(sp);
 	struct host1x *host = sp->host;
-	int min = host1x_syncpt_read_min(sp);
+
 	host1x_sync_writel(host, min, HOST1X_SYNC_SYNCPT(sp->id));
 }
 
@@ -37,6 +38,7 @@ static void syncpt_restore(struct host1x_syncpt *sp)
 static void syncpt_restore_wait_base(struct host1x_syncpt *sp)
 {
 	struct host1x *host = sp->host;
+
 	host1x_sync_writel(host, sp->base_val,
 			   HOST1X_SYNC_SYNCPT_BASE(sp->id));
 }
@@ -47,6 +49,7 @@ static void syncpt_restore_wait_base(struct host1x_syncpt *sp)
 static void syncpt_read_wait_base(struct host1x_syncpt *sp)
 {
 	struct host1x *host = sp->host;
+
 	sp->base_val =
 		host1x_sync_readl(host, HOST1X_SYNC_SYNCPT_BASE(sp->id));
 }
@@ -85,6 +88,7 @@ static int syncpt_cpu_incr(struct host1x_syncpt *sp)
 	if (!host1x_syncpt_client_managed(sp) &&
 	    host1x_syncpt_idle(sp))
 		return -EINVAL;
+
 	host1x_sync_writel(host, BIT_MASK(sp->id),
 			   HOST1X_SYNC_SYNCPT_CPU_INCR(reg_offset));
 	wmb();
@@ -95,10 +99,10 @@ static int syncpt_cpu_incr(struct host1x_syncpt *sp)
 /* remove a wait pointed to by patch_addr */
 static int syncpt_patch_wait(struct host1x_syncpt *sp, void *patch_addr)
 {
-	u32 override = host1x_class_host_wait_syncpt(
-		HOST1X_SYNCPT_RESERVED, 0);
+	u32 override = host1x_class_host_wait_syncpt(HOST1X_SYNCPT_RESERVED, 0);
 
 	*((u32 *)patch_addr) = override;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/host1x/intr.c b/drivers/gpu/host1x/intr.c
index 2491bf82e30c..8b4fad0ab35d 100644
--- a/drivers/gpu/host1x/intr.c
+++ b/drivers/gpu/host1x/intr.c
@@ -122,18 +122,20 @@ static void action_submit_complete(struct host1x_waitlist *waiter)
 static void action_wakeup(struct host1x_waitlist *waiter)
 {
 	wait_queue_head_t *wq = waiter->data;
+
 	wake_up(wq);
 }
 
 static void action_wakeup_interruptible(struct host1x_waitlist *waiter)
 {
 	wait_queue_head_t *wq = waiter->data;
+
 	wake_up_interruptible(wq);
 }
 
 typedef void (*action_handler)(struct host1x_waitlist *waiter);
 
-static action_handler action_handlers[HOST1X_INTR_ACTION_COUNT] = {
+static const action_handler action_handlers[HOST1X_INTR_ACTION_COUNT] = {
 	action_submit_complete,
 	action_wakeup,
 	action_wakeup_interruptible,
@@ -209,7 +211,7 @@ static void syncpt_thresh_work(struct work_struct *work)
 				host1x_syncpt_load(host->syncpt + id));
 }
 
-int host1x_intr_add_action(struct host1x *host, u32 id, u32 thresh,
+int host1x_intr_add_action(struct host1x *host, unsigned int id, u32 thresh,
 			   enum host1x_intr_action action, void *data,
 			   struct host1x_waitlist *waiter, void **ref)
 {
@@ -254,7 +256,7 @@ int host1x_intr_add_action(struct host1x *host, u32 id, u32 thresh,
 	return 0;
 }
 
-void host1x_intr_put_ref(struct host1x *host, u32 id, void *ref)
+void host1x_intr_put_ref(struct host1x *host, unsigned int id, void *ref)
 {
 	struct host1x_waitlist *waiter = ref;
 	struct host1x_syncpt *syncpt;
@@ -277,9 +279,6 @@ int host1x_intr_init(struct host1x *host, unsigned int irq_sync)
 
 	mutex_init(&host->intr_mutex);
 	host->intr_syncpt_irq = irq_sync;
-	host->intr_wq = create_workqueue("host_syncpt");
-	if (!host->intr_wq)
-		return -ENOMEM;
 
 	for (id = 0; id < nb_pts; ++id) {
 		struct host1x_syncpt *syncpt = host->syncpt + id;
@@ -288,7 +287,7 @@ int host1x_intr_init(struct host1x *host, unsigned int irq_sync)
 		INIT_LIST_HEAD(&syncpt->intr.wait_head);
 		snprintf(syncpt->intr.thresh_irq_name,
 			 sizeof(syncpt->intr.thresh_irq_name),
-			 "host1x_sp_%02d", id);
+			 "host1x_sp_%02u", id);
 	}
 
 	host1x_intr_start(host);
@@ -299,7 +298,6 @@ int host1x_intr_init(struct host1x *host, unsigned int irq_sync)
 void host1x_intr_deinit(struct host1x *host)
 {
 	host1x_intr_stop(host);
-	destroy_workqueue(host->intr_wq);
 }
 
 void host1x_intr_start(struct host1x *host)
@@ -342,7 +340,7 @@ void host1x_intr_stop(struct host1x *host)
 		if (!list_empty(&syncpt[id].intr.wait_head)) {
 			/* output diagnostics */
 			mutex_unlock(&host->intr_mutex);
-			pr_warn("%s cannot stop syncpt intr id=%d\n",
+			pr_warn("%s cannot stop syncpt intr id=%u\n",
 				__func__, id);
 			return;
 		}
diff --git a/drivers/gpu/host1x/intr.h b/drivers/gpu/host1x/intr.h
index 2b8adf016a05..1370c2bb75b8 100644
--- a/drivers/gpu/host1x/intr.h
+++ b/drivers/gpu/host1x/intr.h
@@ -75,7 +75,7 @@ struct host1x_waitlist {
  *
  * This is a non-blocking api.
  */
-int host1x_intr_add_action(struct host1x *host, u32 id, u32 thresh,
+int host1x_intr_add_action(struct host1x *host, unsigned int id, u32 thresh,
 	enum host1x_intr_action action, void *data,
 	struct host1x_waitlist *waiter, void **ref);
 
@@ -84,7 +84,7 @@ int host1x_intr_add_action(struct host1x *host, u32 id, u32 thresh,
  * You must call this if you passed non-NULL as ref.
  * @ref the ref returned from host1x_intr_add_action()
  */
-void host1x_intr_put_ref(struct host1x *host, u32 id, void *ref);
+void host1x_intr_put_ref(struct host1x *host, unsigned int id, void *ref);
 
 /* Initialize host1x sync point interrupt */
 int host1x_intr_init(struct host1x *host, unsigned int irq_sync);
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index b4515d544039..a91b7c4a6110 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -161,7 +161,7 @@ static int do_waitchks(struct host1x_job *job, struct host1x *host,
 
 		if (host1x_syncpt_is_expired(sp, wait->thresh)) {
 			dev_dbg(host->dev,
-				"drop WAIT id %d (%s) thresh 0x%x, min 0x%x\n",
+				"drop WAIT id %u (%s) thresh 0x%x, min 0x%x\n",
 				wait->syncpt_id, sp->name, wait->thresh,
 				host1x_syncpt_read_min(sp));
 
@@ -464,6 +464,7 @@ static inline int copy_gathers(struct host1x_job *job, struct device *dev)
 
 	for (i = 0; i < job->num_gathers; i++) {
 		struct host1x_job_gather *g = &job->gathers[i];
+
 		size += g->words * sizeof(u32);
 	}
 
@@ -514,6 +515,7 @@ int host1x_job_pin(struct host1x_job *job, struct device *dev)
 	bitmap_zero(waitchk_mask, host1x_syncpt_nb_pts(host));
 	for (i = 0; i < job->num_waitchk; i++) {
 		u32 syncpt_id = job->waitchk[i].syncpt_id;
+
 		if (syncpt_id < host1x_syncpt_nb_pts(host))
 			set_bit(syncpt_id, waitchk_mask);
 	}
@@ -571,14 +573,16 @@ void host1x_job_unpin(struct host1x_job *job)
 
 	for (i = 0; i < job->num_unpins; i++) {
 		struct host1x_job_unpin_data *unpin = &job->unpins[i];
+
 		host1x_bo_unpin(unpin->bo, unpin->sgt);
 		host1x_bo_put(unpin->bo);
 	}
+
 	job->num_unpins = 0;
 
 	if (job->gather_copy_size)
 		dma_free_wc(job->channel->dev, job->gather_copy_size,
-		            job->gather_copy_mapped, job->gather_copy);
+			    job->gather_copy_mapped, job->gather_copy);
 }
 EXPORT_SYMBOL(host1x_job_unpin);
 
diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c
index 6b7fdc1e2ed0..95589328ad52 100644
--- a/drivers/gpu/host1x/syncpt.c
+++ b/drivers/gpu/host1x/syncpt.c
@@ -73,7 +73,7 @@ static struct host1x_syncpt *host1x_syncpt_alloc(struct host1x *host,
 			return NULL;
 	}
 
-	name = kasprintf(GFP_KERNEL, "%02d-%s", sp->id,
+	name = kasprintf(GFP_KERNEL, "%02u-%s", sp->id,
 			dev ? dev_name(dev) : NULL);
 	if (!name)
 		return NULL;
@@ -110,12 +110,14 @@ EXPORT_SYMBOL(host1x_syncpt_incr_max);
 void host1x_syncpt_restore(struct host1x *host)
 {
 	struct host1x_syncpt *sp_base = host->syncpt;
-	u32 i;
+	unsigned int i;
 
 	for (i = 0; i < host1x_syncpt_nb_pts(host); i++)
 		host1x_hw_syncpt_restore(host, sp_base + i);
+
 	for (i = 0; i < host1x_syncpt_nb_bases(host); i++)
 		host1x_hw_syncpt_restore_wait_base(host, sp_base + i);
+
 	wmb();
 }
 
@@ -126,7 +128,7 @@ void host1x_syncpt_restore(struct host1x *host)
 void host1x_syncpt_save(struct host1x *host)
 {
 	struct host1x_syncpt *sp_base = host->syncpt;
-	u32 i;
+	unsigned int i;
 
 	for (i = 0; i < host1x_syncpt_nb_pts(host); i++) {
 		if (host1x_syncpt_client_managed(sp_base + i))
@@ -146,6 +148,7 @@ void host1x_syncpt_save(struct host1x *host)
 u32 host1x_syncpt_load(struct host1x_syncpt *sp)
 {
 	u32 val;
+
 	val = host1x_hw_syncpt_load(sp->host, sp);
 	trace_host1x_syncpt_load_min(sp->id, val);
 
@@ -157,10 +160,9 @@ u32 host1x_syncpt_load(struct host1x_syncpt *sp)
  */
 u32 host1x_syncpt_load_wait_base(struct host1x_syncpt *sp)
 {
-	u32 val;
 	host1x_hw_syncpt_load_wait_base(sp->host, sp);
-	val = sp->base_val;
-	return val;
+
+	return sp->base_val;
 }
 
 /*
@@ -179,6 +181,7 @@ EXPORT_SYMBOL(host1x_syncpt_incr);
 static bool syncpt_load_min_is_expired(struct host1x_syncpt *sp, u32 thresh)
 {
 	host1x_hw_syncpt_load(sp->host, sp);
+
 	return host1x_syncpt_is_expired(sp, thresh);
 }
 
@@ -186,7 +189,7 @@ static bool syncpt_load_min_is_expired(struct host1x_syncpt *sp, u32 thresh)
  * Main entrypoint for syncpoint value waits.
  */
 int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
-			u32 *value)
+		       u32 *value)
 {
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
 	void *ref;
@@ -201,6 +204,7 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
 	if (host1x_syncpt_is_expired(sp, thresh)) {
 		if (value)
 			*value = host1x_syncpt_load(sp);
+
 		return 0;
 	}
 
@@ -209,6 +213,7 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
 	if (host1x_syncpt_is_expired(sp, thresh)) {
 		if (value)
 			*value = val;
+
 		goto done;
 	}
 
@@ -239,32 +244,42 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
 	/* wait for the syncpoint, or timeout, or signal */
 	while (timeout) {
 		long check = min_t(long, SYNCPT_CHECK_PERIOD, timeout);
-		int remain = wait_event_interruptible_timeout(wq,
+		int remain;
+
+		remain = wait_event_interruptible_timeout(wq,
 				syncpt_load_min_is_expired(sp, thresh),
 				check);
 		if (remain > 0 || host1x_syncpt_is_expired(sp, thresh)) {
 			if (value)
 				*value = host1x_syncpt_load(sp);
+
 			err = 0;
+
 			break;
 		}
+
 		if (remain < 0) {
 			err = remain;
 			break;
 		}
+
 		timeout -= check;
+
 		if (timeout && check_count <= MAX_STUCK_CHECK_COUNT) {
 			dev_warn(sp->host->dev,
-				"%s: syncpoint id %d (%s) stuck waiting %d, timeout=%ld\n",
+				"%s: syncpoint id %u (%s) stuck waiting %d, timeout=%ld\n",
 				 current->comm, sp->id, sp->name,
 				 thresh, timeout);
 
 			host1x_debug_dump_syncpts(sp->host);
+
 			if (check_count == MAX_STUCK_CHECK_COUNT)
 				host1x_debug_dump(sp->host);
+
 			check_count++;
 		}
 	}
+
 	host1x_intr_put_ref(sp->host, sp->id, ref);
 
 done:
@@ -279,7 +294,9 @@ bool host1x_syncpt_is_expired(struct host1x_syncpt *sp, u32 thresh)
 {
 	u32 current_val;
 	u32 future_val;
+
 	smp_rmb();
+
 	current_val = (u32)atomic_read(&sp->min_val);
 	future_val = (u32)atomic_read(&sp->max_val);
 
@@ -341,14 +358,14 @@ int host1x_syncpt_init(struct host1x *host)
 {
 	struct host1x_syncpt_base *bases;
 	struct host1x_syncpt *syncpt;
-	int i;
+	unsigned int i;
 
-	syncpt = devm_kzalloc(host->dev, sizeof(*syncpt) * host->info->nb_pts,
+	syncpt = devm_kcalloc(host->dev, host->info->nb_pts, sizeof(*syncpt),
 			      GFP_KERNEL);
 	if (!syncpt)
 		return -ENOMEM;
 
-	bases = devm_kzalloc(host->dev, sizeof(*bases) * host->info->nb_bases,
+	bases = devm_kcalloc(host->dev, host->info->nb_bases, sizeof(*bases),
 			     GFP_KERNEL);
 	if (!bases)
 		return -ENOMEM;
@@ -378,6 +395,7 @@ struct host1x_syncpt *host1x_syncpt_request(struct device *dev,
 					    unsigned long flags)
 {
 	struct host1x *host = dev_get_drvdata(dev->parent);
+
 	return host1x_syncpt_alloc(host, dev, flags);
 }
 EXPORT_SYMBOL(host1x_syncpt_request);
@@ -398,8 +416,9 @@ EXPORT_SYMBOL(host1x_syncpt_free);
 
 void host1x_syncpt_deinit(struct host1x *host)
 {
-	int i;
 	struct host1x_syncpt *sp = host->syncpt;
+	unsigned int i;
+
 	for (i = 0; i < host->info->nb_pts; i++, sp++)
 		kfree(sp->name);
 }
@@ -407,10 +426,11 @@ void host1x_syncpt_deinit(struct host1x *host)
 /*
  * Read max. It indicates how many operations there are in queue, either in
  * channel or in a software thread.
- * */
+ */
 u32 host1x_syncpt_read_max(struct host1x_syncpt *sp)
 {
 	smp_rmb();
+
 	return (u32)atomic_read(&sp->max_val);
 }
 EXPORT_SYMBOL(host1x_syncpt_read_max);
@@ -421,6 +441,7 @@ EXPORT_SYMBOL(host1x_syncpt_read_max);
 u32 host1x_syncpt_read_min(struct host1x_syncpt *sp)
 {
 	smp_rmb();
+
 	return (u32)atomic_read(&sp->min_val);
 }
 EXPORT_SYMBOL(host1x_syncpt_read_min);
@@ -431,25 +452,26 @@ u32 host1x_syncpt_read(struct host1x_syncpt *sp)
 }
 EXPORT_SYMBOL(host1x_syncpt_read);
 
-int host1x_syncpt_nb_pts(struct host1x *host)
+unsigned int host1x_syncpt_nb_pts(struct host1x *host)
 {
 	return host->info->nb_pts;
 }
 
-int host1x_syncpt_nb_bases(struct host1x *host)
+unsigned int host1x_syncpt_nb_bases(struct host1x *host)
 {
 	return host->info->nb_bases;
 }
 
-int host1x_syncpt_nb_mlocks(struct host1x *host)
+unsigned int host1x_syncpt_nb_mlocks(struct host1x *host)
 {
 	return host->info->nb_mlocks;
 }
 
-struct host1x_syncpt *host1x_syncpt_get(struct host1x *host, u32 id)
+struct host1x_syncpt *host1x_syncpt_get(struct host1x *host, unsigned int id)
 {
 	if (host->info->nb_pts < id)
 		return NULL;
+
 	return host->syncpt + id;
 }
 EXPORT_SYMBOL(host1x_syncpt_get);
diff --git a/drivers/gpu/host1x/syncpt.h b/drivers/gpu/host1x/syncpt.h
index 9056465ecd3f..f719205105ac 100644
--- a/drivers/gpu/host1x/syncpt.h
+++ b/drivers/gpu/host1x/syncpt.h
@@ -37,7 +37,7 @@ struct host1x_syncpt_base {
 };
 
 struct host1x_syncpt {
-	int id;
+	unsigned int id;
 	atomic_t min_val;
 	atomic_t max_val;
 	u32 base_val;
@@ -58,13 +58,13 @@ int host1x_syncpt_init(struct host1x *host);
 void host1x_syncpt_deinit(struct host1x *host);
 
 /* Return number of sync point supported. */
-int host1x_syncpt_nb_pts(struct host1x *host);
+unsigned int host1x_syncpt_nb_pts(struct host1x *host);
 
 /* Return number of wait bases supported. */
-int host1x_syncpt_nb_bases(struct host1x *host);
+unsigned int host1x_syncpt_nb_bases(struct host1x *host);
 
 /* Return number of mlocks supported. */
-int host1x_syncpt_nb_mlocks(struct host1x *host);
+unsigned int host1x_syncpt_nb_mlocks(struct host1x *host);
 
 /*
  * Check sync point sanity. If max is larger than min, there have too many
diff --git a/drivers/gpu/ipu-v3/ipu-dc.c b/drivers/gpu/ipu-v3/ipu-dc.c
index 2f29780e7c68..659475c1e44a 100644
--- a/drivers/gpu/ipu-v3/ipu-dc.c
+++ b/drivers/gpu/ipu-v3/ipu-dc.c
@@ -150,6 +150,9 @@ static void dc_write_tmpl(struct ipu_dc *dc, int word, u32 opcode, u32 operand,
 static int ipu_bus_format_to_map(u32 fmt)
 {
 	switch (fmt) {
+	default:
+		WARN_ON(1);
+		/* fall-through */
 	case MEDIA_BUS_FMT_RGB888_1X24:
 		return IPU_DC_MAP_RGB24;
 	case MEDIA_BUS_FMT_RGB565_1X16:
@@ -162,8 +165,6 @@ static int ipu_bus_format_to_map(u32 fmt)
 		return IPU_DC_MAP_LVDS666;
 	case MEDIA_BUS_FMT_BGR888_1X24:
 		return IPU_DC_MAP_BGR24;
-	default:
-		return -EINVAL;
 	}
 }
 
@@ -178,10 +179,6 @@ int ipu_dc_init_sync(struct ipu_dc *dc, struct ipu_di *di, bool interlaced,
 	dc->di = ipu_di_get_num(di);
 
 	map = ipu_bus_format_to_map(bus_format);
-	if (map < 0) {
-		dev_dbg(priv->dev, "IPU_DISP: No MAP\n");
-		return map;
-	}
 
 	/*
 	 * In interlaced mode we need more counters to create the asymmetric
diff --git a/drivers/gpu/ipu-v3/ipu-di.c b/drivers/gpu/ipu-v3/ipu-di.c
index 359268e3a166..a8d87ddd8a17 100644
--- a/drivers/gpu/ipu-v3/ipu-di.c
+++ b/drivers/gpu/ipu-v3/ipu-di.c
@@ -572,9 +572,6 @@ int ipu_di_init_sync_panel(struct ipu_di *di, struct ipu_di_signal_cfg *sig)
 	dev_dbg(di->ipu->dev, "disp %d: panel size = %d x %d\n",
 		di->id, sig->mode.hactive, sig->mode.vactive);
 
-	if ((sig->mode.vsync_len == 0) || (sig->mode.hsync_len == 0))
-		return -EINVAL;
-
 	dev_dbg(di->ipu->dev, "Clocks: IPU %luHz DI %luHz Needed %luHz\n",
 		clk_get_rate(di->clk_ipu),
 		clk_get_rate(di->clk_di),
diff --git a/drivers/gpu/ipu-v3/ipu-dmfc.c b/drivers/gpu/ipu-v3/ipu-dmfc.c
index 837b1ec22800..42705bb5aaa3 100644
--- a/drivers/gpu/ipu-v3/ipu-dmfc.c
+++ b/drivers/gpu/ipu-v3/ipu-dmfc.c
@@ -45,17 +45,6 @@
 #define DMFC_DP_CHAN_6B_24		16
 #define DMFC_DP_CHAN_6F_29		24
 
-#define DMFC_FIFO_SIZE_64		(3 << 3)
-#define DMFC_FIFO_SIZE_128		(2 << 3)
-#define DMFC_FIFO_SIZE_256		(1 << 3)
-#define DMFC_FIFO_SIZE_512		(0 << 3)
-
-#define DMFC_SEGMENT(x)			((x & 0x7) << 0)
-#define DMFC_BURSTSIZE_128		(0 << 6)
-#define DMFC_BURSTSIZE_64		(1 << 6)
-#define DMFC_BURSTSIZE_32		(2 << 6)
-#define DMFC_BURSTSIZE_16		(3 << 6)
-
 struct dmfc_channel_data {
 	int		ipu_channel;
 	unsigned long	channel_reg;
@@ -104,9 +93,6 @@ struct ipu_dmfc_priv;
 
 struct dmfc_channel {
 	unsigned			slots;
-	unsigned			slotmask;
-	unsigned			segment;
-	int				burstsize;
 	struct ipu_soc			*ipu;
 	struct ipu_dmfc_priv		*priv;
 	const struct dmfc_channel_data	*data;
@@ -117,7 +103,6 @@ struct ipu_dmfc_priv {
 	struct device *dev;
 	struct dmfc_channel channels[DMFC_NUM_CHANNELS];
 	struct mutex mutex;
-	unsigned long bandwidth_per_slot;
 	void __iomem *base;
 	int use_count;
 };
@@ -172,184 +157,6 @@ void ipu_dmfc_disable_channel(struct dmfc_channel *dmfc)
 }
 EXPORT_SYMBOL_GPL(ipu_dmfc_disable_channel);
 
-static int ipu_dmfc_setup_channel(struct dmfc_channel *dmfc, int slots,
-		int segment, int burstsize)
-{
-	struct ipu_dmfc_priv *priv = dmfc->priv;
-	u32 val, field;
-
-	dev_dbg(priv->dev,
-			"dmfc: using %d slots starting from segment %d for IPU channel %d\n",
-			slots, segment, dmfc->data->ipu_channel);
-
-	switch (slots) {
-	case 1:
-		field = DMFC_FIFO_SIZE_64;
-		break;
-	case 2:
-		field = DMFC_FIFO_SIZE_128;
-		break;
-	case 4:
-		field = DMFC_FIFO_SIZE_256;
-		break;
-	case 8:
-		field = DMFC_FIFO_SIZE_512;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	switch (burstsize) {
-	case 16:
-		field |= DMFC_BURSTSIZE_16;
-		break;
-	case 32:
-		field |= DMFC_BURSTSIZE_32;
-		break;
-	case 64:
-		field |= DMFC_BURSTSIZE_64;
-		break;
-	case 128:
-		field |= DMFC_BURSTSIZE_128;
-		break;
-	}
-
-	field |= DMFC_SEGMENT(segment);
-
-	val = readl(priv->base + dmfc->data->channel_reg);
-
-	val &= ~(0xff << dmfc->data->shift);
-	val |= field << dmfc->data->shift;
-
-	writel(val, priv->base + dmfc->data->channel_reg);
-
-	dmfc->slots = slots;
-	dmfc->segment = segment;
-	dmfc->burstsize = burstsize;
-	dmfc->slotmask = ((1 << slots) - 1) << segment;
-
-	return 0;
-}
-
-static int dmfc_bandwidth_to_slots(struct ipu_dmfc_priv *priv,
-		unsigned long bandwidth)
-{
-	int slots = 1;
-
-	while (slots * priv->bandwidth_per_slot < bandwidth)
-		slots *= 2;
-
-	return slots;
-}
-
-static int dmfc_find_slots(struct ipu_dmfc_priv *priv, int slots)
-{
-	unsigned slotmask_need, slotmask_used = 0;
-	int i, segment = 0;
-
-	slotmask_need = (1 << slots) - 1;
-
-	for (i = 0; i < DMFC_NUM_CHANNELS; i++)
-		slotmask_used |= priv->channels[i].slotmask;
-
-	while (slotmask_need <= 0xff) {
-		if (!(slotmask_used & slotmask_need))
-			return segment;
-
-		slotmask_need <<= 1;
-		segment++;
-	}
-
-	return -EBUSY;
-}
-
-void ipu_dmfc_free_bandwidth(struct dmfc_channel *dmfc)
-{
-	struct ipu_dmfc_priv *priv = dmfc->priv;
-	int i;
-
-	dev_dbg(priv->dev, "dmfc: freeing %d slots starting from segment %d\n",
-			dmfc->slots, dmfc->segment);
-
-	mutex_lock(&priv->mutex);
-
-	if (!dmfc->slots)
-		goto out;
-
-	dmfc->slotmask = 0;
-	dmfc->slots = 0;
-	dmfc->segment = 0;
-
-	for (i = 0; i < DMFC_NUM_CHANNELS; i++)
-		priv->channels[i].slotmask = 0;
-
-	for (i = 0; i < DMFC_NUM_CHANNELS; i++) {
-		if (priv->channels[i].slots > 0) {
-			priv->channels[i].segment =
-				dmfc_find_slots(priv, priv->channels[i].slots);
-			priv->channels[i].slotmask =
-				((1 << priv->channels[i].slots) - 1) <<
-				priv->channels[i].segment;
-		}
-	}
-
-	for (i = 0; i < DMFC_NUM_CHANNELS; i++) {
-		if (priv->channels[i].slots > 0)
-			ipu_dmfc_setup_channel(&priv->channels[i],
-					priv->channels[i].slots,
-					priv->channels[i].segment,
-					priv->channels[i].burstsize);
-	}
-out:
-	mutex_unlock(&priv->mutex);
-}
-EXPORT_SYMBOL_GPL(ipu_dmfc_free_bandwidth);
-
-int ipu_dmfc_alloc_bandwidth(struct dmfc_channel *dmfc,
-		unsigned long bandwidth_pixel_per_second, int burstsize)
-{
-	struct ipu_dmfc_priv *priv = dmfc->priv;
-	int slots = dmfc_bandwidth_to_slots(priv, bandwidth_pixel_per_second);
-	int segment = -1, ret = 0;
-
-	dev_dbg(priv->dev, "dmfc: trying to allocate %ldMpixel/s for IPU channel %d\n",
-			bandwidth_pixel_per_second / 1000000,
-			dmfc->data->ipu_channel);
-
-	ipu_dmfc_free_bandwidth(dmfc);
-
-	mutex_lock(&priv->mutex);
-
-	if (slots > 8) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	/* For the MEM_BG channel, first try to allocate twice the slots */
-	if (dmfc->data->ipu_channel == IPUV3_CHANNEL_MEM_BG_SYNC)
-		segment = dmfc_find_slots(priv, slots * 2);
-	else if (slots < 2)
-		/* Always allocate at least 128*4 bytes (2 slots) */
-		slots = 2;
-
-	if (segment >= 0)
-		slots *= 2;
-	else
-		segment = dmfc_find_slots(priv, slots);
-	if (segment < 0) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	ipu_dmfc_setup_channel(dmfc, slots, segment, burstsize);
-
-out:
-	mutex_unlock(&priv->mutex);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(ipu_dmfc_alloc_bandwidth);
-
 void ipu_dmfc_config_wait4eot(struct dmfc_channel *dmfc, int width)
 {
 	struct ipu_dmfc_priv *priv = dmfc->priv;
@@ -384,7 +191,6 @@ EXPORT_SYMBOL_GPL(ipu_dmfc_get);
 
 void ipu_dmfc_put(struct dmfc_channel *dmfc)
 {
-	ipu_dmfc_free_bandwidth(dmfc);
 }
 EXPORT_SYMBOL_GPL(ipu_dmfc_put);
 
@@ -412,20 +218,15 @@ int ipu_dmfc_init(struct ipu_soc *ipu, struct device *dev, unsigned long base,
 		priv->channels[i].priv = priv;
 		priv->channels[i].ipu = ipu;
 		priv->channels[i].data = &dmfcdata[i];
-	}
-
-	writel(0x0, priv->base + DMFC_WR_CHAN);
-	writel(0x0, priv->base + DMFC_DP_CHAN);
 
-	/*
-	 * We have a total bandwidth of clkrate * 4pixel divided
-	 * into 8 slots.
-	 */
-	priv->bandwidth_per_slot = clk_get_rate(ipu_clk) * 4 / 8;
-
-	dev_dbg(dev, "dmfc: 8 slots with %ldMpixel/s bandwidth each\n",
-			priv->bandwidth_per_slot / 1000000);
+		if (dmfcdata[i].ipu_channel == IPUV3_CHANNEL_MEM_BG_SYNC ||
+		    dmfcdata[i].ipu_channel == IPUV3_CHANNEL_MEM_FG_SYNC ||
+		    dmfcdata[i].ipu_channel == IPUV3_CHANNEL_MEM_DC_SYNC)
+			priv->channels[i].slots = 2;
+	}
 
+	writel(0x00000050, priv->base + DMFC_WR_CHAN);
+	writel(0x00005654, priv->base + DMFC_DP_CHAN);
 	writel(0x202020f6, priv->base + DMFC_WR_CHAN_DEF);
 	writel(0x2020f6f6, priv->base + DMFC_DP_CHAN_DEF);
 	writel(0x00000003, priv->base + DMFC_GENERAL1);
diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index cbd7c986d926..5f962bfcb43c 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -30,6 +30,7 @@
 
 #define pr_fmt(fmt) "vga_switcheroo: " fmt
 
+#include <linux/apple-gmux.h>
 #include <linux/console.h>
 #include <linux/debugfs.h>
 #include <linux/fb.h>
@@ -51,9 +52,9 @@
  *
  * * muxed: Dual GPUs with a multiplexer chip to switch outputs between GPUs.
  * * muxless: Dual GPUs but only one of them is connected to outputs.
- * 	The other one is merely used to offload rendering, its results
- * 	are copied over PCIe into the framebuffer. On Linux this is
- * 	supported with DRI PRIME.
+ *   The other one is merely used to offload rendering, its results
+ *   are copied over PCIe into the framebuffer. On Linux this is
+ *   supported with DRI PRIME.
  *
  * Hybrid graphics started to appear in the late Naughties and were initially
  * all muxed. Newer laptops moved to a muxless architecture for cost reasons.
@@ -308,7 +309,8 @@ static int register_client(struct pci_dev *pdev,
  *
  * Register vga client (GPU). Enable vga_switcheroo if another GPU and a
  * handler have already registered. The power state of the client is assumed
- * to be ON.
+ * to be ON. Beforehand, vga_switcheroo_client_probe_defer() shall be called
+ * to ensure that all prerequisites are met.
  *
  * Return: 0 on success, -ENOMEM on memory allocation error.
  */
@@ -329,7 +331,8 @@ EXPORT_SYMBOL(vga_switcheroo_register_client);
  * @id: client identifier
  *
  * Register audio client (audio device on a GPU). The power state of the
- * client is assumed to be ON.
+ * client is assumed to be ON. Beforehand, vga_switcheroo_client_probe_defer()
+ * shall be called to ensure that all prerequisites are met.
  *
  * Return: 0 on success, -ENOMEM on memory allocation error.
  */
@@ -376,6 +379,33 @@ find_active_client(struct list_head *head)
 }
 
 /**
+ * vga_switcheroo_client_probe_defer() - whether to defer probing a given client
+ * @pdev: client pci device
+ *
+ * Determine whether any prerequisites are not fulfilled to probe a given
+ * client. Drivers shall invoke this early on in their ->probe callback
+ * and return %-EPROBE_DEFER if it evaluates to %true. Thou shalt not
+ * register the client ere thou hast called this.
+ *
+ * Return: %true if probing should be deferred, otherwise %false.
+ */
+bool vga_switcheroo_client_probe_defer(struct pci_dev *pdev)
+{
+	if ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
+		/*
+		 * apple-gmux is needed on pre-retina MacBook Pro
+		 * to probe the panel if pdev is the inactive GPU.
+		 */
+		if (apple_gmux_present() && pdev != vga_default_device() &&
+		    !vgasr_priv.handler_flags)
+			return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(vga_switcheroo_client_probe_defer);
+
+/**
  * vga_switcheroo_get_client_state() - obtain power state of a given client
  * @pdev: client pci device
  *
@@ -530,21 +560,21 @@ EXPORT_SYMBOL(vga_switcheroo_unlock_ddc);
  * * OFF: Power off the device not in use.
  * * ON: Power on the device not in use.
  * * IGD: Switch to the integrated graphics device.
- * 	Power on the integrated GPU if necessary, power off the discrete GPU.
- * 	Prerequisite is that no user space processes (e.g. Xorg, alsactl)
- * 	have opened device files of the GPUs or the audio client. If the
- * 	switch fails, the user may invoke lsof(8) or fuser(1) on /dev/dri/
- * 	and /dev/snd/controlC1 to identify processes blocking the switch.
+ *   Power on the integrated GPU if necessary, power off the discrete GPU.
+ *   Prerequisite is that no user space processes (e.g. Xorg, alsactl)
+ *   have opened device files of the GPUs or the audio client. If the
+ *   switch fails, the user may invoke lsof(8) or fuser(1) on /dev/dri/
+ *   and /dev/snd/controlC1 to identify processes blocking the switch.
  * * DIS: Switch to the discrete graphics device.
  * * DIGD: Delayed switch to the integrated graphics device.
- * 	This will perform the switch once the last user space process has
- * 	closed the device files of the GPUs and the audio client.
+ *   This will perform the switch once the last user space process has
+ *   closed the device files of the GPUs and the audio client.
  * * DDIS: Delayed switch to the discrete graphics device.
  * * MIGD: Mux-only switch to the integrated graphics device.
- * 	Does not remap console or change the power state of either gpu.
- * 	If the integrated GPU is currently off, the screen will turn black.
- * 	If it is on, the screen will show whatever happens to be in VRAM.
- * 	Either way, the user has to blindly enter the command to switch back.
+ *   Does not remap console or change the power state of either gpu.
+ *   If the integrated GPU is currently off, the screen will turn black.
+ *   If it is on, the screen will show whatever happens to be in VRAM.
+ *   Either way, the user has to blindly enter the command to switch back.
  * * MDIS: Mux-only switch to the discrete graphics device.
  *
  * For GPUs whose power state is controlled by the driver's runtime pm,
diff --git a/drivers/hwmon/adt7411.c b/drivers/hwmon/adt7411.c
index a7f886961830..fc1e65a263a4 100644
--- a/drivers/hwmon/adt7411.c
+++ b/drivers/hwmon/adt7411.c
@@ -30,6 +30,7 @@
 
 #define ADT7411_REG_CFG1			0x18
 #define ADT7411_CFG1_START_MONITOR		(1 << 0)
+#define ADT7411_CFG1_RESERVED_BIT1		(1 << 1)
 #define ADT7411_CFG1_RESERVED_BIT3		(1 << 3)
 
 #define ADT7411_REG_CFG2			0x19
@@ -37,6 +38,9 @@
 
 #define ADT7411_REG_CFG3			0x1a
 #define ADT7411_CFG3_ADC_CLK_225		(1 << 0)
+#define ADT7411_CFG3_RESERVED_BIT1		(1 << 1)
+#define ADT7411_CFG3_RESERVED_BIT2		(1 << 2)
+#define ADT7411_CFG3_RESERVED_BIT3		(1 << 3)
 #define ADT7411_CFG3_REF_VDD			(1 << 4)
 
 #define ADT7411_REG_DEVICE_ID			0x4d
@@ -280,6 +284,45 @@ static int adt7411_detect(struct i2c_client *client,
 	return 0;
 }
 
+static int adt7411_init_device(struct adt7411_data *data)
+{
+	int ret;
+	u8 val;
+
+	ret = i2c_smbus_read_byte_data(data->client, ADT7411_REG_CFG3);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * We must only write zero to bit 1 and bit 2 and only one to bit 3
+	 * according to the datasheet.
+	 */
+	val = ret;
+	val &= ~(ADT7411_CFG3_RESERVED_BIT1 | ADT7411_CFG3_RESERVED_BIT2);
+	val |= ADT7411_CFG3_RESERVED_BIT3;
+
+	ret = i2c_smbus_write_byte_data(data->client, ADT7411_REG_CFG3, val);
+	if (ret < 0)
+		return ret;
+
+	ret = i2c_smbus_read_byte_data(data->client, ADT7411_REG_CFG1);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * We must only write zero to bit 1 and only one to bit 3 according to
+	 * the datasheet.
+	 */
+	val = ret;
+	val &= ~ADT7411_CFG1_RESERVED_BIT1;
+	val |= ADT7411_CFG1_RESERVED_BIT3;
+
+	/* enable monitoring */
+	val |= ADT7411_CFG1_START_MONITOR;
+
+	return i2c_smbus_write_byte_data(data->client, ADT7411_REG_CFG1, val);
+}
+
 static int adt7411_probe(struct i2c_client *client,
 				   const struct i2c_device_id *id)
 {
@@ -297,10 +340,7 @@ static int adt7411_probe(struct i2c_client *client,
 	mutex_init(&data->device_lock);
 	mutex_init(&data->update_lock);
 
-	/* According to the datasheet, we must only write 1 to bit 3 */
-	ret = adt7411_modify_bit(client, ADT7411_REG_CFG1,
-				 ADT7411_CFG1_RESERVED_BIT3
-				 | ADT7411_CFG1_START_MONITOR, 1);
+	ret = adt7411_init_device(data);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/hwmon/ftsteutates.c b/drivers/hwmon/ftsteutates.c
index 2b2ff67026be..48633e541dc3 100644
--- a/drivers/hwmon/ftsteutates.c
+++ b/drivers/hwmon/ftsteutates.c
@@ -242,7 +242,7 @@ static int fts_wd_set_resolution(struct fts_data *data,
 	}
 
 	if (resolution == seconds)
-		set_bit(1, (unsigned long *)&ret);
+		ret |= BIT(1);
 	else
 		ret &= ~BIT(1);
 
diff --git a/drivers/hwmon/iio_hwmon.c b/drivers/hwmon/iio_hwmon.c
index b550ba5fa58a..89449871bca7 100644
--- a/drivers/hwmon/iio_hwmon.c
+++ b/drivers/hwmon/iio_hwmon.c
@@ -110,24 +110,24 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 
 		switch (type) {
 		case IIO_VOLTAGE:
-			a->dev_attr.attr.name = kasprintf(GFP_KERNEL,
-							  "in%d_input",
-							  in_i++);
+			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
+							       "in%d_input",
+							       in_i++);
 			break;
 		case IIO_TEMP:
-			a->dev_attr.attr.name = kasprintf(GFP_KERNEL,
-							  "temp%d_input",
-							  temp_i++);
+			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
+							       "temp%d_input",
+							       temp_i++);
 			break;
 		case IIO_CURRENT:
-			a->dev_attr.attr.name = kasprintf(GFP_KERNEL,
-							  "curr%d_input",
-							  curr_i++);
+			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
+							       "curr%d_input",
+							       curr_i++);
 			break;
 		case IIO_HUMIDITYRELATIVE:
-			a->dev_attr.attr.name = kasprintf(GFP_KERNEL,
-							  "humidity%d_input",
-							  humidity_i++);
+			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
+							       "humidity%d_input",
+							       humidity_i++);
 			break;
 		default:
 			ret = -EINVAL;
diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index 547a9c87c68c..92f9d4bbf597 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -220,7 +220,7 @@ lm75_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	struct device *dev = &client->dev;
 	struct device *hwmon_dev;
 	struct lm75_data *data;
-	int status;
+	int status, err;
 	u8 set_mask, clr_mask;
 	int new;
 	enum lm75_type kind = id->driver_data;
@@ -331,7 +331,9 @@ lm75_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (status != new)
 		i2c_smbus_write_byte_data(client, LM75_REG_CONF, new);
 
-	devm_add_action(dev, lm75_remove, data);
+	err = devm_add_action_or_reset(dev, lm75_remove, data);
+	if (err)
+		return err;
 
 	dev_dbg(dev, "Config %02x\n", new);
 
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index 1e8237478b2f..496e771b363f 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -529,7 +529,7 @@ static int lm90_update_limits(struct device *dev)
 		return val;
 	data->temp_hyst = val;
 
-	lm90_read_reg(client, LM90_REG_R_REMOTE_LOWH);
+	val = lm90_read_reg(client, LM90_REG_R_REMOTE_LOWH);
 	if (val < 0)
 		return val;
 	data->temp11[REMOTE_LOW] = val << 8;
@@ -1551,9 +1551,7 @@ static int lm90_init_client(struct i2c_client *client, struct lm90_data *data)
 	if (config != data->config_orig) /* Only write if changed */
 		i2c_smbus_write_byte_data(client, LM90_REG_W_CONFIG1, config);
 
-	devm_add_action(&client->dev, lm90_restore_conf, data);
-
-	return 0;
+	return devm_add_action_or_reset(&client->dev, lm90_restore_conf, data);
 }
 
 static bool lm90_is_tripped(struct i2c_client *client, u16 *status)
@@ -1640,7 +1638,9 @@ static int lm90_probe(struct i2c_client *client,
 		return err;
 	}
 
-	devm_add_action(dev, lm90_regulator_disable, regulator);
+	err = devm_add_action_or_reset(dev, lm90_regulator_disable, regulator);
+	if (err)
+		return err;
 
 	data = devm_kzalloc(dev, sizeof(struct lm90_data), GFP_KERNEL);
 	if (!data)
@@ -1696,7 +1696,9 @@ static int lm90_probe(struct i2c_client *client,
 		err = device_create_file(dev, &dev_attr_pec);
 		if (err)
 			return err;
-		devm_add_action(dev, lm90_remove_pec, dev);
+		err = devm_add_action_or_reset(dev, lm90_remove_pec, dev);
+		if (err)
+			return err;
 	}
 
 	hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name,
diff --git a/drivers/hwmon/sht3x.c b/drivers/hwmon/sht3x.c
index b73a48832732..6ea99cd6ae79 100644
--- a/drivers/hwmon/sht3x.c
+++ b/drivers/hwmon/sht3x.c
@@ -720,7 +720,7 @@ static int sht3x_probe(struct i2c_client *client,
 	data->setup.blocking_io = false;
 	data->setup.high_precision = true;
 	data->mode = 0;
-	data->last_update = 0;
+	data->last_update = jiffies - msecs_to_jiffies(3000);
 	data->client = client;
 	crc8_populate_msb(sht3x_crc8_table, SHT3X_CRC8_POLYNOMIAL);
 
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index a942a2574a4d..8479ac5eb853 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -227,7 +227,9 @@ static int tmp102_probe(struct i2c_client *client,
 
 	tmp102->config_orig = regval;
 
-	devm_add_action(dev, tmp102_restore_config, tmp102);
+	err = devm_add_action_or_reset(dev, tmp102_restore_config, tmp102);
+	if (err)
+		return err;
 
 	regval &= ~TMP102_CONFIG_CLEAR;
 	regval |= TMP102_CONFIG_SET;
diff --git a/drivers/i2c/busses/i2c-opal.c b/drivers/i2c/busses/i2c-opal.c
index 75dd6d041241..11e2a1fc10e9 100644
--- a/drivers/i2c/busses/i2c-opal.c
+++ b/drivers/i2c/busses/i2c-opal.c
@@ -71,7 +71,7 @@ static int i2c_opal_send_request(u32 bus_id, struct opal_i2c_request *req)
 	if (rc)
 		goto exit;
 
-	rc = be64_to_cpu(msg.params[1]);
+	rc = opal_get_async_rc(msg);
 	if (rc != OPAL_SUCCESS) {
 		rc = i2c_opal_translate_error(rc);
 		goto exit;
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 9b2ef248788d..67ec58f9ef99 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1055,7 +1055,7 @@ static const struct idle_cpu idle_cpu_dnv = {
 static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	ICPU(INTEL_FAM6_NEHALEM_EP,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_NEHALEM,		idle_cpu_nehalem),
-	ICPU(INTEL_FAM6_WESTMERE2,		idle_cpu_nehalem),
+	ICPU(INTEL_FAM6_NEHALEM_G,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_WESTMERE,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_WESTMERE_EP,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_NEHALEM_EX,		idle_cpu_nehalem),
diff --git a/drivers/input/keyboard/clps711x-keypad.c b/drivers/input/keyboard/clps711x-keypad.c
index b637f1af842e..997e3e97f573 100644
--- a/drivers/input/keyboard/clps711x-keypad.c
+++ b/drivers/input/keyboard/clps711x-keypad.c
@@ -101,7 +101,7 @@ static int clps711x_keypad_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	priv->syscon =
-		syscon_regmap_lookup_by_compatible("cirrus,clps711x-syscon1");
+		syscon_regmap_lookup_by_compatible("cirrus,ep7209-syscon1");
 	if (IS_ERR(priv->syscon))
 		return PTR_ERR(priv->syscon);
 
@@ -181,7 +181,7 @@ static int clps711x_keypad_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id clps711x_keypad_of_match[] = {
-	{ .compatible = "cirrus,clps711x-keypad", },
+	{ .compatible = "cirrus,ep7209-keypad", },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, clps711x_keypad_of_match);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index ad0860383cb3..d432ca828472 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -89,8 +89,8 @@ config MSM_IOMMU
 	bool "MSM IOMMU Support"
 	depends on ARM
 	depends on ARCH_MSM8X60 || ARCH_MSM8960 || COMPILE_TEST
-	depends on BROKEN
 	select IOMMU_API
+	select IOMMU_IO_PGTABLE_ARMV7S
 	help
 	  Support for the IOMMUs found on certain Qualcomm SOCs.
 	  These IOMMUs allow virtualization of the address space used by most
@@ -111,6 +111,7 @@ config AMD_IOMMU
 	select PCI_PRI
 	select PCI_PASID
 	select IOMMU_API
+	select IOMMU_IOVA
 	depends on X86_64 && PCI && ACPI
 	---help---
 	  With this option you can enable support for AMD IOMMU hardware in
@@ -343,4 +344,22 @@ config MTK_IOMMU
 
 	  If unsure, say N here.
 
+config MTK_IOMMU_V1
+	bool "MTK IOMMU Version 1 (M4U gen1) Support"
+	depends on ARM
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	select ARM_DMA_USE_IOMMU
+	select IOMMU_API
+	select MEMORY
+	select MTK_SMI
+	select COMMON_CLK_MT2701_MMSYS
+	select COMMON_CLK_MT2701_IMGSYS
+	select COMMON_CLK_MT2701_VDECSYS
+	help
+	  Support for the M4U on certain Mediatek SoCs. M4U generation 1 HW is
+	  Multimedia Memory Managememt Unit. This option enables remapping of
+	  DMA memory accesses for the multimedia subsystem.
+
+	  if unsure, say N here.
+
 endif # IOMMU_SUPPORT
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index c6edb31bf8c6..195f7b997d8e 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o
 obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
 obj-$(CONFIG_IOMMU_IOVA) += iova.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
-obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
+obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
 obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
@@ -18,6 +18,7 @@ obj-$(CONFIG_INTEL_IOMMU_SVM) += intel-svm.o
 obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
 obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o
 obj-$(CONFIG_MTK_IOMMU) += mtk_iommu.o
+obj-$(CONFIG_MTK_IOMMU_V1) += mtk_iommu_v1.o
 obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o
 obj-$(CONFIG_OMAP_IOMMU_DEBUG) += omap-iommu-debug.o
 obj-$(CONFIG_ROCKCHIP_IOMMU) += rockchip-iommu.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 634f636393d5..33c177ba93be 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -21,6 +21,7 @@
 #include <linux/pci.h>
 #include <linux/acpi.h>
 #include <linux/amba/bus.h>
+#include <linux/platform_device.h>
 #include <linux/pci-ats.h>
 #include <linux/bitmap.h>
 #include <linux/slab.h>
@@ -38,6 +39,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/irqdomain.h>
 #include <linux/percpu.h>
+#include <linux/iova.h>
 #include <asm/irq_remapping.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
@@ -56,6 +58,17 @@
 
 #define LOOP_TIMEOUT	100000
 
+/* IO virtual address start page frame number */
+#define IOVA_START_PFN		(1)
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
+#define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
+
+/* Reserved IOVA ranges */
+#define MSI_RANGE_START		(0xfee00000)
+#define MSI_RANGE_END		(0xfeefffff)
+#define HT_RANGE_START		(0xfd00000000ULL)
+#define HT_RANGE_END		(0xffffffffffULL)
+
 /*
  * This bitmap is used to advertise the page sizes our hardware support
  * to the IOMMU core, which will then use this information to split
@@ -76,6 +89,25 @@ LIST_HEAD(ioapic_map);
 LIST_HEAD(hpet_map);
 LIST_HEAD(acpihid_map);
 
+#define FLUSH_QUEUE_SIZE 256
+
+struct flush_queue_entry {
+	unsigned long iova_pfn;
+	unsigned long pages;
+	struct dma_ops_domain *dma_dom;
+};
+
+struct flush_queue {
+	spinlock_t lock;
+	unsigned next;
+	struct flush_queue_entry *entries;
+};
+
+DEFINE_PER_CPU(struct flush_queue, flush_queue);
+
+static atomic_t queue_timer_on;
+static struct timer_list queue_timer;
+
 /*
  * Domain for untranslated devices - only allocated
  * if iommu=pt passed on kernel cmd line.
@@ -121,44 +153,19 @@ static int protection_domain_init(struct protection_domain *domain);
 static void detach_device(struct device *dev);
 
 /*
- * For dynamic growth the aperture size is split into ranges of 128MB of
- * DMA address space each. This struct represents one such range.
- */
-struct aperture_range {
-
-	spinlock_t bitmap_lock;
-
-	/* address allocation bitmap */
-	unsigned long *bitmap;
-	unsigned long offset;
-	unsigned long next_bit;
-
-	/*
-	 * Array of PTE pages for the aperture. In this array we save all the
-	 * leaf pages of the domain page table used for the aperture. This way
-	 * we don't need to walk the page table to find a specific PTE. We can
-	 * just calculate its address in constant time.
-	 */
-	u64 *pte_pages[64];
-};
-
-/*
  * Data container for a dma_ops specific protection domain
  */
 struct dma_ops_domain {
 	/* generic protection domain information */
 	struct protection_domain domain;
 
-	/* size of the aperture for the mappings */
-	unsigned long aperture_size;
-
-	/* aperture index we start searching for free addresses */
-	u32 __percpu *next_index;
-
-	/* address space relevant data */
-	struct aperture_range *aperture[APERTURE_MAX_RANGES];
+	/* IOVA RB-Tree */
+	struct iova_domain iovad;
 };
 
+static struct iova_domain reserved_iova_ranges;
+static struct lock_class_key reserved_rbtree_key;
+
 /****************************************************************************
  *
  * Helper functions
@@ -224,6 +231,12 @@ static struct protection_domain *to_pdomain(struct iommu_domain *dom)
 	return container_of(dom, struct protection_domain, domain);
 }
 
+static struct dma_ops_domain* to_dma_ops_domain(struct protection_domain *domain)
+{
+	BUG_ON(domain->flags != PD_DMA_OPS_MASK);
+	return container_of(domain, struct dma_ops_domain, domain);
+}
+
 static struct iommu_dev_data *alloc_dev_data(u16 devid)
 {
 	struct iommu_dev_data *dev_data;
@@ -391,43 +404,6 @@ static bool pdev_pri_erratum(struct pci_dev *pdev, u32 erratum)
 }
 
 /*
- * This function actually applies the mapping to the page table of the
- * dma_ops domain.
- */
-static void alloc_unity_mapping(struct dma_ops_domain *dma_dom,
-				struct unity_map_entry *e)
-{
-	u64 addr;
-
-	for (addr = e->address_start; addr < e->address_end;
-	     addr += PAGE_SIZE) {
-		if (addr < dma_dom->aperture_size)
-			__set_bit(addr >> PAGE_SHIFT,
-				  dma_dom->aperture[0]->bitmap);
-	}
-}
-
-/*
- * Inits the unity mappings required for a specific device
- */
-static void init_unity_mappings_for_device(struct device *dev,
-					   struct dma_ops_domain *dma_dom)
-{
-	struct unity_map_entry *e;
-	int devid;
-
-	devid = get_device_id(dev);
-	if (devid < 0)
-		return;
-
-	list_for_each_entry(e, &amd_iommu_unity_map, list) {
-		if (!(devid >= e->devid_start && devid <= e->devid_end))
-			continue;
-		alloc_unity_mapping(dma_dom, e);
-	}
-}
-
-/*
  * This function checks if the driver got a valid device from the caller to
  * avoid dereferencing invalid pointers.
  */
@@ -454,22 +430,12 @@ static bool check_device(struct device *dev)
 
 static void init_iommu_group(struct device *dev)
 {
-	struct dma_ops_domain *dma_domain;
-	struct iommu_domain *domain;
 	struct iommu_group *group;
 
 	group = iommu_group_get_for_dev(dev);
 	if (IS_ERR(group))
 		return;
 
-	domain = iommu_group_default_domain(group);
-	if (!domain)
-		goto out;
-
-	dma_domain = to_pdomain(domain)->priv;
-
-	init_unity_mappings_for_device(dev, dma_domain);
-out:
 	iommu_group_put(group);
 }
 
@@ -1220,7 +1186,7 @@ static void domain_flush_complete(struct protection_domain *domain)
 	int i;
 
 	for (i = 0; i < amd_iommus_present; ++i) {
-		if (!domain->dev_iommu[i])
+		if (domain && !domain->dev_iommu[i])
 			continue;
 
 		/*
@@ -1397,8 +1363,9 @@ static u64 *fetch_pte(struct protection_domain *domain,
 static int iommu_map_page(struct protection_domain *dom,
 			  unsigned long bus_addr,
 			  unsigned long phys_addr,
+			  unsigned long page_size,
 			  int prot,
-			  unsigned long page_size)
+			  gfp_t gfp)
 {
 	u64 __pte, *pte;
 	int i, count;
@@ -1410,7 +1377,7 @@ static int iommu_map_page(struct protection_domain *dom,
 		return -EINVAL;
 
 	count = PAGE_SIZE_PTE_COUNT(page_size);
-	pte   = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL);
+	pte   = alloc_pte(dom, bus_addr, page_size, NULL, gfp);
 
 	if (!pte)
 		return -ENOMEM;
@@ -1474,320 +1441,37 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
 /****************************************************************************
  *
  * The next functions belong to the address allocator for the dma_ops
- * interface functions. They work like the allocators in the other IOMMU
- * drivers. Its basically a bitmap which marks the allocated pages in
- * the aperture. Maybe it could be enhanced in the future to a more
- * efficient allocator.
+ * interface functions.
  *
  ****************************************************************************/
 
-/*
- * The address allocator core functions.
- *
- * called with domain->lock held
- */
 
-/*
- * Used to reserve address ranges in the aperture (e.g. for exclusion
- * ranges.
- */
-static void dma_ops_reserve_addresses(struct dma_ops_domain *dom,
-				      unsigned long start_page,
-				      unsigned int pages)
+static unsigned long dma_ops_alloc_iova(struct device *dev,
+					struct dma_ops_domain *dma_dom,
+					unsigned int pages, u64 dma_mask)
 {
-	unsigned int i, last_page = dom->aperture_size >> PAGE_SHIFT;
-
-	if (start_page + pages > last_page)
-		pages = last_page - start_page;
-
-	for (i = start_page; i < start_page + pages; ++i) {
-		int index = i / APERTURE_RANGE_PAGES;
-		int page  = i % APERTURE_RANGE_PAGES;
-		__set_bit(page, dom->aperture[index]->bitmap);
-	}
-}
+	unsigned long pfn = 0;
 
-/*
- * This function is used to add a new aperture range to an existing
- * aperture in case of dma_ops domain allocation or address allocation
- * failure.
- */
-static int alloc_new_range(struct dma_ops_domain *dma_dom,
-			   bool populate, gfp_t gfp)
-{
-	int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
-	unsigned long i, old_size, pte_pgsize;
-	struct aperture_range *range;
-	struct amd_iommu *iommu;
-	unsigned long flags;
+	pages = __roundup_pow_of_two(pages);
 
-#ifdef CONFIG_IOMMU_STRESS
-	populate = false;
-#endif
+	if (dma_mask > DMA_BIT_MASK(32))
+		pfn = alloc_iova_fast(&dma_dom->iovad, pages,
+				      IOVA_PFN(DMA_BIT_MASK(32)));
 
-	if (index >= APERTURE_MAX_RANGES)
-		return -ENOMEM;
-
-	range = kzalloc(sizeof(struct aperture_range), gfp);
-	if (!range)
-		return -ENOMEM;
-
-	range->bitmap = (void *)get_zeroed_page(gfp);
-	if (!range->bitmap)
-		goto out_free;
-
-	range->offset = dma_dom->aperture_size;
-
-	spin_lock_init(&range->bitmap_lock);
-
-	if (populate) {
-		unsigned long address = dma_dom->aperture_size;
-		int i, num_ptes = APERTURE_RANGE_PAGES / 512;
-		u64 *pte, *pte_page;
-
-		for (i = 0; i < num_ptes; ++i) {
-			pte = alloc_pte(&dma_dom->domain, address, PAGE_SIZE,
-					&pte_page, gfp);
-			if (!pte)
-				goto out_free;
-
-			range->pte_pages[i] = pte_page;
-
-			address += APERTURE_RANGE_SIZE / 64;
-		}
-	}
+	if (!pfn)
+		pfn = alloc_iova_fast(&dma_dom->iovad, pages, IOVA_PFN(dma_mask));
 
-	spin_lock_irqsave(&dma_dom->domain.lock, flags);
-
-	/* First take the bitmap_lock and then publish the range */
-	spin_lock(&range->bitmap_lock);
-
-	old_size                 = dma_dom->aperture_size;
-	dma_dom->aperture[index] = range;
-	dma_dom->aperture_size  += APERTURE_RANGE_SIZE;
-
-	/* Reserve address range used for MSI messages */
-	if (old_size < MSI_ADDR_BASE_LO &&
-	    dma_dom->aperture_size > MSI_ADDR_BASE_LO) {
-		unsigned long spage;
-		int pages;
-
-		pages = iommu_num_pages(MSI_ADDR_BASE_LO, 0x10000, PAGE_SIZE);
-		spage = MSI_ADDR_BASE_LO >> PAGE_SHIFT;
-
-		dma_ops_reserve_addresses(dma_dom, spage, pages);
-	}
-
-	/* Initialize the exclusion range if necessary */
-	for_each_iommu(iommu) {
-		if (iommu->exclusion_start &&
-		    iommu->exclusion_start >= dma_dom->aperture[index]->offset
-		    && iommu->exclusion_start < dma_dom->aperture_size) {
-			unsigned long startpage;
-			int pages = iommu_num_pages(iommu->exclusion_start,
-						    iommu->exclusion_length,
-						    PAGE_SIZE);
-			startpage = iommu->exclusion_start >> PAGE_SHIFT;
-			dma_ops_reserve_addresses(dma_dom, startpage, pages);
-		}
-	}
-
-	/*
-	 * Check for areas already mapped as present in the new aperture
-	 * range and mark those pages as reserved in the allocator. Such
-	 * mappings may already exist as a result of requested unity
-	 * mappings for devices.
-	 */
-	for (i = dma_dom->aperture[index]->offset;
-	     i < dma_dom->aperture_size;
-	     i += pte_pgsize) {
-		u64 *pte = fetch_pte(&dma_dom->domain, i, &pte_pgsize);
-		if (!pte || !IOMMU_PTE_PRESENT(*pte))
-			continue;
-
-		dma_ops_reserve_addresses(dma_dom, i >> PAGE_SHIFT,
-					  pte_pgsize >> 12);
-	}
-
-	update_domain(&dma_dom->domain);
-
-	spin_unlock(&range->bitmap_lock);
-
-	spin_unlock_irqrestore(&dma_dom->domain.lock, flags);
-
-	return 0;
-
-out_free:
-	update_domain(&dma_dom->domain);
-
-	free_page((unsigned long)range->bitmap);
-
-	kfree(range);
-
-	return -ENOMEM;
+	return (pfn << PAGE_SHIFT);
 }
 
-static dma_addr_t dma_ops_aperture_alloc(struct dma_ops_domain *dom,
-					 struct aperture_range *range,
-					 unsigned long pages,
-					 unsigned long dma_mask,
-					 unsigned long boundary_size,
-					 unsigned long align_mask,
-					 bool trylock)
+static void dma_ops_free_iova(struct dma_ops_domain *dma_dom,
+			      unsigned long address,
+			      unsigned int pages)
 {
-	unsigned long offset, limit, flags;
-	dma_addr_t address;
-	bool flush = false;
-
-	offset = range->offset >> PAGE_SHIFT;
-	limit  = iommu_device_max_index(APERTURE_RANGE_PAGES, offset,
-					dma_mask >> PAGE_SHIFT);
-
-	if (trylock) {
-		if (!spin_trylock_irqsave(&range->bitmap_lock, flags))
-			return -1;
-	} else {
-		spin_lock_irqsave(&range->bitmap_lock, flags);
-	}
-
-	address = iommu_area_alloc(range->bitmap, limit, range->next_bit,
-				   pages, offset, boundary_size, align_mask);
-	if (address == -1) {
-		/* Nothing found, retry one time */
-		address = iommu_area_alloc(range->bitmap, limit,
-					   0, pages, offset, boundary_size,
-					   align_mask);
-		flush = true;
-	}
-
-	if (address != -1)
-		range->next_bit = address + pages;
-
-	spin_unlock_irqrestore(&range->bitmap_lock, flags);
-
-	if (flush) {
-		domain_flush_tlb(&dom->domain);
-		domain_flush_complete(&dom->domain);
-	}
-
-	return address;
-}
-
-static unsigned long dma_ops_area_alloc(struct device *dev,
-					struct dma_ops_domain *dom,
-					unsigned int pages,
-					unsigned long align_mask,
-					u64 dma_mask)
-{
-	unsigned long boundary_size, mask;
-	unsigned long address = -1;
-	bool first = true;
-	u32 start, i;
-
-	preempt_disable();
-
-	mask = dma_get_seg_boundary(dev);
-
-again:
-	start = this_cpu_read(*dom->next_index);
-
-	/* Sanity check - is it really necessary? */
-	if (unlikely(start > APERTURE_MAX_RANGES)) {
-		start = 0;
-		this_cpu_write(*dom->next_index, 0);
-	}
-
-	boundary_size = mask + 1 ? ALIGN(mask + 1, PAGE_SIZE) >> PAGE_SHIFT :
-				   1UL << (BITS_PER_LONG - PAGE_SHIFT);
-
-	for (i = 0; i < APERTURE_MAX_RANGES; ++i) {
-		struct aperture_range *range;
-		int index;
-
-		index = (start + i) % APERTURE_MAX_RANGES;
-
-		range = dom->aperture[index];
-
-		if (!range || range->offset >= dma_mask)
-			continue;
-
-		address = dma_ops_aperture_alloc(dom, range, pages,
-						 dma_mask, boundary_size,
-						 align_mask, first);
-		if (address != -1) {
-			address = range->offset + (address << PAGE_SHIFT);
-			this_cpu_write(*dom->next_index, index);
-			break;
-		}
-	}
-
-	if (address == -1 && first) {
-		first = false;
-		goto again;
-	}
-
-	preempt_enable();
-
-	return address;
-}
-
-static unsigned long dma_ops_alloc_addresses(struct device *dev,
-					     struct dma_ops_domain *dom,
-					     unsigned int pages,
-					     unsigned long align_mask,
-					     u64 dma_mask)
-{
-	unsigned long address = -1;
-
-	while (address == -1) {
-		address = dma_ops_area_alloc(dev, dom, pages,
-					     align_mask, dma_mask);
-
-		if (address == -1 && alloc_new_range(dom, false, GFP_ATOMIC))
-			break;
-	}
-
-	if (unlikely(address == -1))
-		address = DMA_ERROR_CODE;
-
-	WARN_ON((address + (PAGE_SIZE*pages)) > dom->aperture_size);
-
-	return address;
-}
-
-/*
- * The address free function.
- *
- * called with domain->lock held
- */
-static void dma_ops_free_addresses(struct dma_ops_domain *dom,
-				   unsigned long address,
-				   unsigned int pages)
-{
-	unsigned i = address >> APERTURE_RANGE_SHIFT;
-	struct aperture_range *range = dom->aperture[i];
-	unsigned long flags;
-
-	BUG_ON(i >= APERTURE_MAX_RANGES || range == NULL);
-
-#ifdef CONFIG_IOMMU_STRESS
-	if (i < 4)
-		return;
-#endif
-
-	if (amd_iommu_unmap_flush) {
-		domain_flush_tlb(&dom->domain);
-		domain_flush_complete(&dom->domain);
-	}
-
-	address = (address % APERTURE_RANGE_SIZE) >> PAGE_SHIFT;
-
-	spin_lock_irqsave(&range->bitmap_lock, flags);
-	if (address + pages > range->next_bit)
-		range->next_bit = address + pages;
-	bitmap_clear(range->bitmap, address, pages);
-	spin_unlock_irqrestore(&range->bitmap_lock, flags);
+	pages = __roundup_pow_of_two(pages);
+	address >>= PAGE_SHIFT;
 
+	free_iova_fast(&dma_dom->iovad, address, pages);
 }
 
 /****************************************************************************
@@ -1961,44 +1645,18 @@ static void free_gcr3_table(struct protection_domain *domain)
  */
 static void dma_ops_domain_free(struct dma_ops_domain *dom)
 {
-	int i;
-
 	if (!dom)
 		return;
 
-	free_percpu(dom->next_index);
-
 	del_domain_from_list(&dom->domain);
 
-	free_pagetable(&dom->domain);
+	put_iova_domain(&dom->iovad);
 
-	for (i = 0; i < APERTURE_MAX_RANGES; ++i) {
-		if (!dom->aperture[i])
-			continue;
-		free_page((unsigned long)dom->aperture[i]->bitmap);
-		kfree(dom->aperture[i]);
-	}
+	free_pagetable(&dom->domain);
 
 	kfree(dom);
 }
 
-static int dma_ops_domain_alloc_apertures(struct dma_ops_domain *dma_dom,
-					  int max_apertures)
-{
-	int ret, i, apertures;
-
-	apertures = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
-	ret       = 0;
-
-	for (i = apertures; i < max_apertures; ++i) {
-		ret = alloc_new_range(dma_dom, false, GFP_KERNEL);
-		if (ret)
-			break;
-	}
-
-	return ret;
-}
-
 /*
  * Allocates a new protection domain usable for the dma_ops functions.
  * It also initializes the page table and the address allocator data
@@ -2007,7 +1665,6 @@ static int dma_ops_domain_alloc_apertures(struct dma_ops_domain *dma_dom,
 static struct dma_ops_domain *dma_ops_domain_alloc(void)
 {
 	struct dma_ops_domain *dma_dom;
-	int cpu;
 
 	dma_dom = kzalloc(sizeof(struct dma_ops_domain), GFP_KERNEL);
 	if (!dma_dom)
@@ -2016,30 +1673,19 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
 	if (protection_domain_init(&dma_dom->domain))
 		goto free_dma_dom;
 
-	dma_dom->next_index = alloc_percpu(u32);
-	if (!dma_dom->next_index)
-		goto free_dma_dom;
-
-	dma_dom->domain.mode = PAGE_MODE_2_LEVEL;
+	dma_dom->domain.mode = PAGE_MODE_3_LEVEL;
 	dma_dom->domain.pt_root = (void *)get_zeroed_page(GFP_KERNEL);
 	dma_dom->domain.flags = PD_DMA_OPS_MASK;
-	dma_dom->domain.priv = dma_dom;
 	if (!dma_dom->domain.pt_root)
 		goto free_dma_dom;
 
-	add_domain_to_list(&dma_dom->domain);
+	init_iova_domain(&dma_dom->iovad, PAGE_SIZE,
+			 IOVA_START_PFN, DMA_32BIT_PFN);
 
-	if (alloc_new_range(dma_dom, true, GFP_KERNEL))
-		goto free_dma_dom;
-
-	/*
-	 * mark the first page as allocated so we never return 0 as
-	 * a valid dma-address. So we can use 0 as error value
-	 */
-	dma_dom->aperture[0]->bitmap[0] = 1;
+	/* Initialize reserved ranges */
+	copy_reserved_iova(&reserved_iova_ranges, &dma_dom->iovad);
 
-	for_each_possible_cpu(cpu)
-		*per_cpu_ptr(dma_dom->next_index, cpu) = 0;
+	add_domain_to_list(&dma_dom->domain);
 
 	return dma_dom;
 
@@ -2482,6 +2128,92 @@ static struct iommu_group *amd_iommu_device_group(struct device *dev)
  *
  *****************************************************************************/
 
+static void __queue_flush(struct flush_queue *queue)
+{
+	struct protection_domain *domain;
+	unsigned long flags;
+	int idx;
+
+	/* First flush TLB of all known domains */
+	spin_lock_irqsave(&amd_iommu_pd_lock, flags);
+	list_for_each_entry(domain, &amd_iommu_pd_list, list)
+		domain_flush_tlb(domain);
+	spin_unlock_irqrestore(&amd_iommu_pd_lock, flags);
+
+	/* Wait until flushes have completed */
+	domain_flush_complete(NULL);
+
+	for (idx = 0; idx < queue->next; ++idx) {
+		struct flush_queue_entry *entry;
+
+		entry = queue->entries + idx;
+
+		free_iova_fast(&entry->dma_dom->iovad,
+				entry->iova_pfn,
+				entry->pages);
+
+		/* Not really necessary, just to make sure we catch any bugs */
+		entry->dma_dom = NULL;
+	}
+
+	queue->next = 0;
+}
+
+static void queue_flush_all(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct flush_queue *queue;
+		unsigned long flags;
+
+		queue = per_cpu_ptr(&flush_queue, cpu);
+		spin_lock_irqsave(&queue->lock, flags);
+		if (queue->next > 0)
+			__queue_flush(queue);
+		spin_unlock_irqrestore(&queue->lock, flags);
+	}
+}
+
+static void queue_flush_timeout(unsigned long unsused)
+{
+	atomic_set(&queue_timer_on, 0);
+	queue_flush_all();
+}
+
+static void queue_add(struct dma_ops_domain *dma_dom,
+		      unsigned long address, unsigned long pages)
+{
+	struct flush_queue_entry *entry;
+	struct flush_queue *queue;
+	unsigned long flags;
+	int idx;
+
+	pages     = __roundup_pow_of_two(pages);
+	address >>= PAGE_SHIFT;
+
+	queue = get_cpu_ptr(&flush_queue);
+	spin_lock_irqsave(&queue->lock, flags);
+
+	if (queue->next == FLUSH_QUEUE_SIZE)
+		__queue_flush(queue);
+
+	idx   = queue->next++;
+	entry = queue->entries + idx;
+
+	entry->iova_pfn = address;
+	entry->pages    = pages;
+	entry->dma_dom  = dma_dom;
+
+	spin_unlock_irqrestore(&queue->lock, flags);
+
+	if (atomic_cmpxchg(&queue_timer_on, 0, 1) == 0)
+		mod_timer(&queue_timer, jiffies + msecs_to_jiffies(10));
+
+	put_cpu_ptr(&flush_queue);
+}
+
+
 /*
  * In the dma_ops path we only have the struct device. This function
  * finds the corresponding IOMMU, the protection domain and the
@@ -2492,16 +2224,11 @@ static struct iommu_group *amd_iommu_device_group(struct device *dev)
 static struct protection_domain *get_domain(struct device *dev)
 {
 	struct protection_domain *domain;
-	struct iommu_domain *io_domain;
 
 	if (!check_device(dev))
 		return ERR_PTR(-EINVAL);
 
-	io_domain = iommu_get_domain_for_dev(dev);
-	if (!io_domain)
-		return NULL;
-
-	domain = to_pdomain(io_domain);
+	domain = get_dev_data(dev)->domain;
 	if (!dma_ops_domain(domain))
 		return ERR_PTR(-EBUSY);
 
@@ -2512,8 +2239,15 @@ static void update_device_table(struct protection_domain *domain)
 {
 	struct iommu_dev_data *dev_data;
 
-	list_for_each_entry(dev_data, &domain->dev_list, list)
+	list_for_each_entry(dev_data, &domain->dev_list, list) {
 		set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled);
+
+		if (dev_data->devid == dev_data->alias)
+			continue;
+
+		/* There is an alias, update device table entry for it */
+		set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled);
+	}
 }
 
 static void update_domain(struct protection_domain *domain)
@@ -2529,94 +2263,17 @@ static void update_domain(struct protection_domain *domain)
 	domain->updated = false;
 }
 
-/*
- * This function fetches the PTE for a given address in the aperture
- */
-static u64* dma_ops_get_pte(struct dma_ops_domain *dom,
-			    unsigned long address)
-{
-	struct aperture_range *aperture;
-	u64 *pte, *pte_page;
-
-	aperture = dom->aperture[APERTURE_RANGE_INDEX(address)];
-	if (!aperture)
-		return NULL;
-
-	pte = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
-	if (!pte) {
-		pte = alloc_pte(&dom->domain, address, PAGE_SIZE, &pte_page,
-				GFP_ATOMIC);
-		aperture->pte_pages[APERTURE_PAGE_INDEX(address)] = pte_page;
-	} else
-		pte += PM_LEVEL_INDEX(0, address);
-
-	update_domain(&dom->domain);
-
-	return pte;
-}
-
-/*
- * This is the generic map function. It maps one 4kb page at paddr to
- * the given address in the DMA address space for the domain.
- */
-static dma_addr_t dma_ops_domain_map(struct dma_ops_domain *dom,
-				     unsigned long address,
-				     phys_addr_t paddr,
-				     int direction)
+static int dir2prot(enum dma_data_direction direction)
 {
-	u64 *pte, __pte;
-
-	WARN_ON(address > dom->aperture_size);
-
-	paddr &= PAGE_MASK;
-
-	pte  = dma_ops_get_pte(dom, address);
-	if (!pte)
-		return DMA_ERROR_CODE;
-
-	__pte = paddr | IOMMU_PTE_P | IOMMU_PTE_FC;
-
 	if (direction == DMA_TO_DEVICE)
-		__pte |= IOMMU_PTE_IR;
+		return IOMMU_PROT_IR;
 	else if (direction == DMA_FROM_DEVICE)
-		__pte |= IOMMU_PTE_IW;
+		return IOMMU_PROT_IW;
 	else if (direction == DMA_BIDIRECTIONAL)
-		__pte |= IOMMU_PTE_IR | IOMMU_PTE_IW;
-
-	WARN_ON_ONCE(*pte);
-
-	*pte = __pte;
-
-	return (dma_addr_t)address;
-}
-
-/*
- * The generic unmapping function for on page in the DMA address space.
- */
-static void dma_ops_domain_unmap(struct dma_ops_domain *dom,
-				 unsigned long address)
-{
-	struct aperture_range *aperture;
-	u64 *pte;
-
-	if (address >= dom->aperture_size)
-		return;
-
-	aperture = dom->aperture[APERTURE_RANGE_INDEX(address)];
-	if (!aperture)
-		return;
-
-	pte  = aperture->pte_pages[APERTURE_PAGE_INDEX(address)];
-	if (!pte)
-		return;
-
-	pte += PM_LEVEL_INDEX(0, address);
-
-	WARN_ON_ONCE(!*pte);
-
-	*pte = 0ULL;
+		return IOMMU_PROT_IW | IOMMU_PROT_IR;
+	else
+		return 0;
 }
-
 /*
  * This function contains common code for mapping of a physically
  * contiguous memory region into DMA address space. It is used by all
@@ -2627,32 +2284,29 @@ static dma_addr_t __map_single(struct device *dev,
 			       struct dma_ops_domain *dma_dom,
 			       phys_addr_t paddr,
 			       size_t size,
-			       int dir,
-			       bool align,
+			       enum dma_data_direction direction,
 			       u64 dma_mask)
 {
 	dma_addr_t offset = paddr & ~PAGE_MASK;
 	dma_addr_t address, start, ret;
 	unsigned int pages;
-	unsigned long align_mask = 0;
+	int prot = 0;
 	int i;
 
 	pages = iommu_num_pages(paddr, size, PAGE_SIZE);
 	paddr &= PAGE_MASK;
 
-	if (align)
-		align_mask = (1UL << get_order(size)) - 1;
-
-	address = dma_ops_alloc_addresses(dev, dma_dom, pages, align_mask,
-					  dma_mask);
-
+	address = dma_ops_alloc_iova(dev, dma_dom, pages, dma_mask);
 	if (address == DMA_ERROR_CODE)
 		goto out;
 
+	prot = dir2prot(direction);
+
 	start = address;
 	for (i = 0; i < pages; ++i) {
-		ret = dma_ops_domain_map(dma_dom, start, paddr, dir);
-		if (ret == DMA_ERROR_CODE)
+		ret = iommu_map_page(&dma_dom->domain, start, paddr,
+				     PAGE_SIZE, prot, GFP_ATOMIC);
+		if (ret)
 			goto out_unmap;
 
 		paddr += PAGE_SIZE;
@@ -2672,10 +2326,13 @@ out_unmap:
 
 	for (--i; i >= 0; --i) {
 		start -= PAGE_SIZE;
-		dma_ops_domain_unmap(dma_dom, start);
+		iommu_unmap_page(&dma_dom->domain, start, PAGE_SIZE);
 	}
 
-	dma_ops_free_addresses(dma_dom, address, pages);
+	domain_flush_tlb(&dma_dom->domain);
+	domain_flush_complete(&dma_dom->domain);
+
+	dma_ops_free_iova(dma_dom, address, pages);
 
 	return DMA_ERROR_CODE;
 }
@@ -2693,21 +2350,23 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 	dma_addr_t i, start;
 	unsigned int pages;
 
-	if ((dma_addr == DMA_ERROR_CODE) ||
-	    (dma_addr + size > dma_dom->aperture_size))
-		return;
-
 	flush_addr = dma_addr;
 	pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
 	dma_addr &= PAGE_MASK;
 	start = dma_addr;
 
 	for (i = 0; i < pages; ++i) {
-		dma_ops_domain_unmap(dma_dom, start);
+		iommu_unmap_page(&dma_dom->domain, start, PAGE_SIZE);
 		start += PAGE_SIZE;
 	}
 
-	dma_ops_free_addresses(dma_dom, dma_addr, pages);
+	if (amd_iommu_unmap_flush) {
+		dma_ops_free_iova(dma_dom, dma_addr, pages);
+		domain_flush_tlb(&dma_dom->domain);
+		domain_flush_complete(&dma_dom->domain);
+	} else {
+		queue_add(dma_dom, dma_addr, pages);
+	}
 }
 
 /*
@@ -2720,6 +2379,7 @@ static dma_addr_t map_page(struct device *dev, struct page *page,
 {
 	phys_addr_t paddr = page_to_phys(page) + offset;
 	struct protection_domain *domain;
+	struct dma_ops_domain *dma_dom;
 	u64 dma_mask;
 
 	domain = get_domain(dev);
@@ -2729,9 +2389,9 @@ static dma_addr_t map_page(struct device *dev, struct page *page,
 		return DMA_ERROR_CODE;
 
 	dma_mask = *dev->dma_mask;
+	dma_dom = to_dma_ops_domain(domain);
 
-	return __map_single(dev, domain->priv, paddr, size, dir, false,
-			    dma_mask);
+	return __map_single(dev, dma_dom, paddr, size, dir, dma_mask);
 }
 
 /*
@@ -2741,12 +2401,41 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
 		       enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	struct protection_domain *domain;
+	struct dma_ops_domain *dma_dom;
 
 	domain = get_domain(dev);
 	if (IS_ERR(domain))
 		return;
 
-	__unmap_single(domain->priv, dma_addr, size, dir);
+	dma_dom = to_dma_ops_domain(domain);
+
+	__unmap_single(dma_dom, dma_addr, size, dir);
+}
+
+static int sg_num_pages(struct device *dev,
+			struct scatterlist *sglist,
+			int nelems)
+{
+	unsigned long mask, boundary_size;
+	struct scatterlist *s;
+	int i, npages = 0;
+
+	mask          = dma_get_seg_boundary(dev);
+	boundary_size = mask + 1 ? ALIGN(mask + 1, PAGE_SIZE) >> PAGE_SHIFT :
+				   1UL << (BITS_PER_LONG - PAGE_SHIFT);
+
+	for_each_sg(sglist, s, nelems, i) {
+		int p, n;
+
+		s->dma_address = npages << PAGE_SHIFT;
+		p = npages % boundary_size;
+		n = iommu_num_pages(sg_phys(s), s->length, PAGE_SIZE);
+		if (p + n > boundary_size)
+			npages += boundary_size - p;
+		npages += n;
+	}
+
+	return npages;
 }
 
 /*
@@ -2754,46 +2443,79 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
  * lists).
  */
 static int map_sg(struct device *dev, struct scatterlist *sglist,
-		  int nelems, enum dma_data_direction dir,
+		  int nelems, enum dma_data_direction direction,
 		  struct dma_attrs *attrs)
 {
+	int mapped_pages = 0, npages = 0, prot = 0, i;
 	struct protection_domain *domain;
-	int i;
+	struct dma_ops_domain *dma_dom;
 	struct scatterlist *s;
-	phys_addr_t paddr;
-	int mapped_elems = 0;
+	unsigned long address;
 	u64 dma_mask;
 
 	domain = get_domain(dev);
 	if (IS_ERR(domain))
 		return 0;
 
+	dma_dom  = to_dma_ops_domain(domain);
 	dma_mask = *dev->dma_mask;
 
+	npages = sg_num_pages(dev, sglist, nelems);
+
+	address = dma_ops_alloc_iova(dev, dma_dom, npages, dma_mask);
+	if (address == DMA_ERROR_CODE)
+		goto out_err;
+
+	prot = dir2prot(direction);
+
+	/* Map all sg entries */
 	for_each_sg(sglist, s, nelems, i) {
-		paddr = sg_phys(s);
+		int j, pages = iommu_num_pages(sg_phys(s), s->length, PAGE_SIZE);
 
-		s->dma_address = __map_single(dev, domain->priv,
-					      paddr, s->length, dir, false,
-					      dma_mask);
+		for (j = 0; j < pages; ++j) {
+			unsigned long bus_addr, phys_addr;
+			int ret;
 
-		if (s->dma_address) {
-			s->dma_length = s->length;
-			mapped_elems++;
-		} else
-			goto unmap;
+			bus_addr  = address + s->dma_address + (j << PAGE_SHIFT);
+			phys_addr = (sg_phys(s) & PAGE_MASK) + (j << PAGE_SHIFT);
+			ret = iommu_map_page(domain, bus_addr, phys_addr, PAGE_SIZE, prot, GFP_ATOMIC);
+			if (ret)
+				goto out_unmap;
+
+			mapped_pages += 1;
+		}
 	}
 
-	return mapped_elems;
+	/* Everything is mapped - write the right values into s->dma_address */
+	for_each_sg(sglist, s, nelems, i) {
+		s->dma_address += address + s->offset;
+		s->dma_length   = s->length;
+	}
+
+	return nelems;
+
+out_unmap:
+	pr_err("%s: IOMMU mapping error in map_sg (io-pages: %d)\n",
+	       dev_name(dev), npages);
 
-unmap:
-	for_each_sg(sglist, s, mapped_elems, i) {
-		if (s->dma_address)
-			__unmap_single(domain->priv, s->dma_address,
-				       s->dma_length, dir);
-		s->dma_address = s->dma_length = 0;
+	for_each_sg(sglist, s, nelems, i) {
+		int j, pages = iommu_num_pages(sg_phys(s), s->length, PAGE_SIZE);
+
+		for (j = 0; j < pages; ++j) {
+			unsigned long bus_addr;
+
+			bus_addr  = address + s->dma_address + (j << PAGE_SHIFT);
+			iommu_unmap_page(domain, bus_addr, PAGE_SIZE);
+
+			if (--mapped_pages)
+				goto out_free_iova;
+		}
 	}
 
+out_free_iova:
+	free_iova_fast(&dma_dom->iovad, address, npages);
+
+out_err:
 	return 0;
 }
 
@@ -2806,18 +2528,19 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
 		     struct dma_attrs *attrs)
 {
 	struct protection_domain *domain;
-	struct scatterlist *s;
-	int i;
+	struct dma_ops_domain *dma_dom;
+	unsigned long startaddr;
+	int npages = 2;
 
 	domain = get_domain(dev);
 	if (IS_ERR(domain))
 		return;
 
-	for_each_sg(sglist, s, nelems, i) {
-		__unmap_single(domain->priv, s->dma_address,
-			       s->dma_length, dir);
-		s->dma_address = s->dma_length = 0;
-	}
+	startaddr = sg_dma_address(sglist) & PAGE_MASK;
+	dma_dom   = to_dma_ops_domain(domain);
+	npages    = sg_num_pages(dev, sglist, nelems);
+
+	__unmap_single(dma_dom, startaddr, npages << PAGE_SHIFT, dir);
 }
 
 /*
@@ -2829,6 +2552,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
 {
 	u64 dma_mask = dev->coherent_dma_mask;
 	struct protection_domain *domain;
+	struct dma_ops_domain *dma_dom;
 	struct page *page;
 
 	domain = get_domain(dev);
@@ -2839,6 +2563,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
 	} else if (IS_ERR(domain))
 		return NULL;
 
+	dma_dom   = to_dma_ops_domain(domain);
 	size	  = PAGE_ALIGN(size);
 	dma_mask  = dev->coherent_dma_mask;
 	flag     &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
@@ -2858,8 +2583,8 @@ static void *alloc_coherent(struct device *dev, size_t size,
 	if (!dma_mask)
 		dma_mask = *dev->dma_mask;
 
-	*dma_addr = __map_single(dev, domain->priv, page_to_phys(page),
-				 size, DMA_BIDIRECTIONAL, true, dma_mask);
+	*dma_addr = __map_single(dev, dma_dom, page_to_phys(page),
+				 size, DMA_BIDIRECTIONAL, dma_mask);
 
 	if (*dma_addr == DMA_ERROR_CODE)
 		goto out_free;
@@ -2882,6 +2607,7 @@ static void free_coherent(struct device *dev, size_t size,
 			  struct dma_attrs *attrs)
 {
 	struct protection_domain *domain;
+	struct dma_ops_domain *dma_dom;
 	struct page *page;
 
 	page = virt_to_page(virt_addr);
@@ -2891,7 +2617,9 @@ static void free_coherent(struct device *dev, size_t size,
 	if (IS_ERR(domain))
 		goto free_mem;
 
-	__unmap_single(domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
+	dma_dom = to_dma_ops_domain(domain);
+
+	__unmap_single(dma_dom, dma_addr, size, DMA_BIDIRECTIONAL);
 
 free_mem:
 	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
@@ -2907,48 +2635,92 @@ static int amd_iommu_dma_supported(struct device *dev, u64 mask)
 	return check_device(dev);
 }
 
-static int set_dma_mask(struct device *dev, u64 mask)
+static struct dma_map_ops amd_iommu_dma_ops = {
+	.alloc		= alloc_coherent,
+	.free		= free_coherent,
+	.map_page	= map_page,
+	.unmap_page	= unmap_page,
+	.map_sg		= map_sg,
+	.unmap_sg	= unmap_sg,
+	.dma_supported	= amd_iommu_dma_supported,
+};
+
+static int init_reserved_iova_ranges(void)
 {
-	struct protection_domain *domain;
-	int max_apertures = 1;
+	struct pci_dev *pdev = NULL;
+	struct iova *val;
 
-	domain = get_domain(dev);
-	if (IS_ERR(domain))
-		return PTR_ERR(domain);
+	init_iova_domain(&reserved_iova_ranges, PAGE_SIZE,
+			 IOVA_START_PFN, DMA_32BIT_PFN);
 
-	if (mask == DMA_BIT_MASK(64))
-		max_apertures = 8;
-	else if (mask > DMA_BIT_MASK(32))
-		max_apertures = 4;
+	lockdep_set_class(&reserved_iova_ranges.iova_rbtree_lock,
+			  &reserved_rbtree_key);
+
+	/* MSI memory range */
+	val = reserve_iova(&reserved_iova_ranges,
+			   IOVA_PFN(MSI_RANGE_START), IOVA_PFN(MSI_RANGE_END));
+	if (!val) {
+		pr_err("Reserving MSI range failed\n");
+		return -ENOMEM;
+	}
+
+	/* HT memory range */
+	val = reserve_iova(&reserved_iova_ranges,
+			   IOVA_PFN(HT_RANGE_START), IOVA_PFN(HT_RANGE_END));
+	if (!val) {
+		pr_err("Reserving HT range failed\n");
+		return -ENOMEM;
+	}
 
 	/*
-	 * To prevent lock contention it doesn't make sense to allocate more
-	 * apertures than online cpus
+	 * Memory used for PCI resources
+	 * FIXME: Check whether we can reserve the PCI-hole completly
 	 */
-	if (max_apertures > num_online_cpus())
-		max_apertures = num_online_cpus();
+	for_each_pci_dev(pdev) {
+		int i;
+
+		for (i = 0; i < PCI_NUM_RESOURCES; ++i) {
+			struct resource *r = &pdev->resource[i];
+
+			if (!(r->flags & IORESOURCE_MEM))
+				continue;
 
-	if (dma_ops_domain_alloc_apertures(domain->priv, max_apertures))
-		dev_err(dev, "Can't allocate %d iommu apertures\n",
-			max_apertures);
+			val = reserve_iova(&reserved_iova_ranges,
+					   IOVA_PFN(r->start),
+					   IOVA_PFN(r->end));
+			if (!val) {
+				pr_err("Reserve pci-resource range failed\n");
+				return -ENOMEM;
+			}
+		}
+	}
 
 	return 0;
 }
 
-static struct dma_map_ops amd_iommu_dma_ops = {
-	.alloc		= alloc_coherent,
-	.free		= free_coherent,
-	.map_page	= map_page,
-	.unmap_page	= unmap_page,
-	.map_sg		= map_sg,
-	.unmap_sg	= unmap_sg,
-	.dma_supported	= amd_iommu_dma_supported,
-	.set_dma_mask	= set_dma_mask,
-};
-
 int __init amd_iommu_init_api(void)
 {
-	int err = 0;
+	int ret, cpu, err = 0;
+
+	ret = iova_cache_get();
+	if (ret)
+		return ret;
+
+	ret = init_reserved_iova_ranges();
+	if (ret)
+		return ret;
+
+	for_each_possible_cpu(cpu) {
+		struct flush_queue *queue = per_cpu_ptr(&flush_queue, cpu);
+
+		queue->entries = kzalloc(FLUSH_QUEUE_SIZE *
+					 sizeof(*queue->entries),
+					 GFP_KERNEL);
+		if (!queue->entries)
+			goto out_put_iova;
+
+		spin_lock_init(&queue->lock);
+	}
 
 	err = bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
 	if (err)
@@ -2958,11 +2730,26 @@ int __init amd_iommu_init_api(void)
 	if (err)
 		return err;
 #endif
+	err = bus_set_iommu(&platform_bus_type, &amd_iommu_ops);
+	if (err)
+		return err;
 	return 0;
+
+out_put_iova:
+	for_each_possible_cpu(cpu) {
+		struct flush_queue *queue = per_cpu_ptr(&flush_queue, cpu);
+
+		kfree(queue->entries);
+	}
+
+	return -ENOMEM;
 }
 
 int __init amd_iommu_init_dma_ops(void)
 {
+	setup_timer(&queue_timer, queue_flush_timeout, 0);
+	atomic_set(&queue_timer_on, 0);
+
 	swiotlb        = iommu_pass_through ? 1 : 0;
 	iommu_detected = 1;
 
@@ -2981,6 +2768,7 @@ int __init amd_iommu_init_dma_ops(void)
 		pr_info("AMD-Vi: Lazy IO/TLB flushing enabled\n");
 
 	return 0;
+
 }
 
 /*****************************************************************************
@@ -3103,9 +2891,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 static void amd_iommu_domain_free(struct iommu_domain *dom)
 {
 	struct protection_domain *domain;
-
-	if (!dom)
-		return;
+	struct dma_ops_domain *dma_dom;
 
 	domain = to_pdomain(dom);
 
@@ -3114,13 +2900,31 @@ static void amd_iommu_domain_free(struct iommu_domain *dom)
 
 	BUG_ON(domain->dev_cnt != 0);
 
-	if (domain->mode != PAGE_MODE_NONE)
-		free_pagetable(domain);
+	if (!dom)
+		return;
+
+	switch (dom->type) {
+	case IOMMU_DOMAIN_DMA:
+		/*
+		 * First make sure the domain is no longer referenced from the
+		 * flush queue
+		 */
+		queue_flush_all();
 
-	if (domain->flags & PD_IOMMUV2_MASK)
-		free_gcr3_table(domain);
+		/* Now release the domain */
+		dma_dom = to_dma_ops_domain(domain);
+		dma_ops_domain_free(dma_dom);
+		break;
+	default:
+		if (domain->mode != PAGE_MODE_NONE)
+			free_pagetable(domain);
+
+		if (domain->flags & PD_IOMMUV2_MASK)
+			free_gcr3_table(domain);
 
-	protection_domain_free(domain);
+		protection_domain_free(domain);
+		break;
+	}
 }
 
 static void amd_iommu_detach_device(struct iommu_domain *dom,
@@ -3190,7 +2994,7 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
 		prot |= IOMMU_PROT_IW;
 
 	mutex_lock(&domain->api_lock);
-	ret = iommu_map_page(domain, iova, paddr, prot, page_size);
+	ret = iommu_map_page(domain, iova, paddr, page_size, prot, GFP_KERNEL);
 	mutex_unlock(&domain->api_lock);
 
 	return ret;
@@ -3292,6 +3096,19 @@ static void amd_iommu_put_dm_regions(struct device *dev,
 		kfree(entry);
 }
 
+static void amd_iommu_apply_dm_region(struct device *dev,
+				      struct iommu_domain *domain,
+				      struct iommu_dm_region *region)
+{
+	struct dma_ops_domain *dma_dom = to_dma_ops_domain(to_pdomain(domain));
+	unsigned long start, end;
+
+	start = IOVA_PFN(region->start);
+	end   = IOVA_PFN(region->start + region->length);
+
+	WARN_ON_ONCE(reserve_iova(&dma_dom->iovad, start, end) == NULL);
+}
+
 static const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
@@ -3307,6 +3124,7 @@ static const struct iommu_ops amd_iommu_ops = {
 	.device_group = amd_iommu_device_group,
 	.get_dm_regions = amd_iommu_get_dm_regions,
 	.put_dm_regions = amd_iommu_put_dm_regions,
+	.apply_dm_region = amd_iommu_apply_dm_region,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 };
 
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 590956ac704e..caf5e3822715 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -421,7 +421,6 @@ struct protection_domain {
 	bool updated;		/* complete domain flush required */
 	unsigned dev_cnt;	/* devices assigned to this domain */
 	unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */
-	void *priv;             /* private data */
 };
 
 /*
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index fbdaf81ae925..594849a3a9be 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -960,7 +960,7 @@ static int __init amd_iommu_v2_init(void)
 	spin_lock_init(&state_lock);
 
 	ret = -ENOMEM;
-	iommu_wq = create_workqueue("amd_iommu_v2");
+	iommu_wq = alloc_workqueue("amd_iommu_v2", WQ_MEM_RECLAIM, 0);
 	if (iommu_wq == NULL)
 		goto out;
 
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 5f6b3bcab078..ce801170d5f2 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2687,6 +2687,8 @@ static int __init arm_smmu_init(void)
 	if (ret)
 		return ret;
 
+	pci_request_acs();
+
 	return bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
 }
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 9345a3fcb706..4f49fe29f202 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -987,8 +987,8 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	 * handler seeing a half-initialised domain state.
 	 */
 	irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
-	ret = request_irq(irq, arm_smmu_context_fault, IRQF_SHARED,
-			  "arm-smmu-context-fault", domain);
+	ret = devm_request_irq(smmu->dev, irq, arm_smmu_context_fault,
+			       IRQF_SHARED, "arm-smmu-context-fault", domain);
 	if (ret < 0) {
 		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
 			cfg->irptndx, irq);
@@ -1028,7 +1028,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 
 	if (cfg->irptndx != INVALID_IRPTNDX) {
 		irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
-		free_irq(irq, domain);
+		devm_free_irq(smmu->dev, irq, domain);
 	}
 
 	free_io_pgtable_ops(smmu_domain->pgtbl_ops);
@@ -1986,15 +1986,15 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	}
 
 	for (i = 0; i < smmu->num_global_irqs; ++i) {
-		err = request_irq(smmu->irqs[i],
-				  arm_smmu_global_fault,
-				  IRQF_SHARED,
-				  "arm-smmu global fault",
-				  smmu);
+		err = devm_request_irq(smmu->dev, smmu->irqs[i],
+				       arm_smmu_global_fault,
+				       IRQF_SHARED,
+				       "arm-smmu global fault",
+				       smmu);
 		if (err) {
 			dev_err(dev, "failed to request global IRQ %d (%u)\n",
 				i, smmu->irqs[i]);
-			goto out_free_irqs;
+			goto out_put_masters;
 		}
 	}
 
@@ -2006,10 +2006,6 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	arm_smmu_device_reset(smmu);
 	return 0;
 
-out_free_irqs:
-	while (i--)
-		free_irq(smmu->irqs[i], smmu);
-
 out_put_masters:
 	for (node = rb_first(&smmu->masters); node; node = rb_next(node)) {
 		struct arm_smmu_master *master
@@ -2050,7 +2046,7 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
 		dev_err(dev, "removing device with active domains!\n");
 
 	for (i = 0; i < smmu->num_global_irqs; ++i)
-		free_irq(smmu->irqs[i], smmu);
+		devm_free_irq(smmu->dev, smmu->irqs[i], smmu);
 
 	/* Turn the thing off */
 	writel(sCR0_CLIENTPD, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
@@ -2096,8 +2092,10 @@ static int __init arm_smmu_init(void)
 #endif
 
 #ifdef CONFIG_PCI
-	if (!iommu_present(&pci_bus_type))
+	if (!iommu_present(&pci_bus_type)) {
+		pci_request_acs();
 		bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
+	}
 #endif
 
 	return 0;
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 7330a66e2b7e..58470f5ced04 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -241,8 +241,20 @@ int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
 		if (!dmar_match_pci_path(info, scope->bus, path, level))
 			continue;
 
-		if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT) ^
-		    (info->dev->hdr_type == PCI_HEADER_TYPE_NORMAL)) {
+		/*
+		 * We expect devices with endpoint scope to have normal PCI
+		 * headers, and devices with bridge scope to have bridge PCI
+		 * headers.  However PCI NTB devices may be listed in the
+		 * DMAR table with bridge scope, even though they have a
+		 * normal PCI header.  NTB devices are identified by class
+		 * "BRIDGE_OTHER" (0680h) - we don't declare a socpe mismatch
+		 * for this special case.
+		 */
+		if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT &&
+		     info->dev->hdr_type != PCI_HEADER_TYPE_NORMAL) ||
+		    (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE &&
+		     (info->dev->hdr_type == PCI_HEADER_TYPE_NORMAL &&
+		      info->dev->class >> 8 != PCI_CLASS_BRIDGE_OTHER))) {
 			pr_warn("Device scope type does not match for %s\n",
 				pci_name(info->dev));
 			return -EINVAL;
@@ -1155,8 +1167,6 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
 				(unsigned long long)qi->desc[index].high);
 			memcpy(&qi->desc[index], &qi->desc[wait_index],
 					sizeof(struct qi_desc));
-			__iommu_flush_cache(iommu, &qi->desc[index],
-					sizeof(struct qi_desc));
 			writel(DMA_FSTS_IQE, iommu->reg + DMAR_FSTS_REG);
 			return -EINVAL;
 		}
@@ -1231,9 +1241,6 @@ restart:
 
 	hw[wait_index] = wait_desc;
 
-	__iommu_flush_cache(iommu, &hw[index], sizeof(struct qi_desc));
-	__iommu_flush_cache(iommu, &hw[wait_index], sizeof(struct qi_desc));
-
 	qi->free_head = (qi->free_head + 2) % QI_LENGTH;
 	qi->free_cnt -= 2;
 
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 5ecc86cb74c8..33dcc29ec200 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -54,6 +54,10 @@ typedef u32 sysmmu_pte_t;
 #define lv2ent_small(pent) ((*(pent) & 2) == 2)
 #define lv2ent_large(pent) ((*(pent) & 3) == 1)
 
+#ifdef CONFIG_BIG_ENDIAN
+#warning "revisit driver if we can enable big-endian ptes"
+#endif
+
 /*
  * v1.x - v3.x SYSMMU supports 32bit physical and 32bit virtual address spaces
  * v5.0 introduced support for 36bit physical address space by shifting
@@ -322,14 +326,27 @@ static void __sysmmu_set_ptbase(struct sysmmu_drvdata *data, phys_addr_t pgd)
 	__sysmmu_tlb_invalidate(data);
 }
 
+static void __sysmmu_enable_clocks(struct sysmmu_drvdata *data)
+{
+	BUG_ON(clk_prepare_enable(data->clk_master));
+	BUG_ON(clk_prepare_enable(data->clk));
+	BUG_ON(clk_prepare_enable(data->pclk));
+	BUG_ON(clk_prepare_enable(data->aclk));
+}
+
+static void __sysmmu_disable_clocks(struct sysmmu_drvdata *data)
+{
+	clk_disable_unprepare(data->aclk);
+	clk_disable_unprepare(data->pclk);
+	clk_disable_unprepare(data->clk);
+	clk_disable_unprepare(data->clk_master);
+}
+
 static void __sysmmu_get_version(struct sysmmu_drvdata *data)
 {
 	u32 ver;
 
-	clk_enable(data->clk_master);
-	clk_enable(data->clk);
-	clk_enable(data->pclk);
-	clk_enable(data->aclk);
+	__sysmmu_enable_clocks(data);
 
 	ver = readl(data->sfrbase + REG_MMU_VERSION);
 
@@ -342,10 +359,7 @@ static void __sysmmu_get_version(struct sysmmu_drvdata *data)
 	dev_dbg(data->sysmmu, "hardware version: %d.%d\n",
 		MMU_MAJ_VER(data->version), MMU_MIN_VER(data->version));
 
-	clk_disable(data->aclk);
-	clk_disable(data->pclk);
-	clk_disable(data->clk);
-	clk_disable(data->clk_master);
+	__sysmmu_disable_clocks(data);
 }
 
 static void show_fault_information(struct sysmmu_drvdata *data,
@@ -427,10 +441,7 @@ static void __sysmmu_disable_nocount(struct sysmmu_drvdata *data)
 	writel(CTRL_DISABLE, data->sfrbase + REG_MMU_CTRL);
 	writel(0, data->sfrbase + REG_MMU_CFG);
 
-	clk_disable(data->aclk);
-	clk_disable(data->pclk);
-	clk_disable(data->clk);
-	clk_disable(data->clk_master);
+	__sysmmu_disable_clocks(data);
 }
 
 static bool __sysmmu_disable(struct sysmmu_drvdata *data)
@@ -475,10 +486,7 @@ static void __sysmmu_init_config(struct sysmmu_drvdata *data)
 
 static void __sysmmu_enable_nocount(struct sysmmu_drvdata *data)
 {
-	clk_enable(data->clk_master);
-	clk_enable(data->clk);
-	clk_enable(data->pclk);
-	clk_enable(data->aclk);
+	__sysmmu_enable_clocks(data);
 
 	writel(CTRL_BLOCK, data->sfrbase + REG_MMU_CTRL);
 
@@ -488,6 +496,12 @@ static void __sysmmu_enable_nocount(struct sysmmu_drvdata *data)
 
 	writel(CTRL_ENABLE, data->sfrbase + REG_MMU_CTRL);
 
+	/*
+	 * SYSMMU driver keeps master's clock enabled only for the short
+	 * time, while accessing the registers. For performing address
+	 * translation during DMA transaction it relies on the client
+	 * driver to enable it.
+	 */
 	clk_disable(data->clk_master);
 }
 
@@ -524,16 +538,15 @@ static void sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
 {
 	unsigned long flags;
 
-	clk_enable(data->clk_master);
 
 	spin_lock_irqsave(&data->lock, flags);
-	if (is_sysmmu_active(data)) {
-		if (data->version >= MAKE_MMU_VER(3, 3))
-			__sysmmu_tlb_invalidate_entry(data, iova, 1);
+	if (is_sysmmu_active(data) && data->version >= MAKE_MMU_VER(3, 3)) {
+		clk_enable(data->clk_master);
+		__sysmmu_tlb_invalidate_entry(data, iova, 1);
+		clk_disable(data->clk_master);
 	}
 	spin_unlock_irqrestore(&data->lock, flags);
 
-	clk_disable(data->clk_master);
 }
 
 static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
@@ -572,6 +585,8 @@ static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
 	spin_unlock_irqrestore(&data->lock, flags);
 }
 
+static struct iommu_ops exynos_iommu_ops;
+
 static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 {
 	int irq, ret;
@@ -602,37 +617,22 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 	}
 
 	data->clk = devm_clk_get(dev, "sysmmu");
-	if (!IS_ERR(data->clk)) {
-		ret = clk_prepare(data->clk);
-		if (ret) {
-			dev_err(dev, "Failed to prepare clk\n");
-			return ret;
-		}
-	} else {
+	if (PTR_ERR(data->clk) == -ENOENT)
 		data->clk = NULL;
-	}
+	else if (IS_ERR(data->clk))
+		return PTR_ERR(data->clk);
 
 	data->aclk = devm_clk_get(dev, "aclk");
-	if (!IS_ERR(data->aclk)) {
-		ret = clk_prepare(data->aclk);
-		if (ret) {
-			dev_err(dev, "Failed to prepare aclk\n");
-			return ret;
-		}
-	} else {
+	if (PTR_ERR(data->aclk) == -ENOENT)
 		data->aclk = NULL;
-	}
+	else if (IS_ERR(data->aclk))
+		return PTR_ERR(data->aclk);
 
 	data->pclk = devm_clk_get(dev, "pclk");
-	if (!IS_ERR(data->pclk)) {
-		ret = clk_prepare(data->pclk);
-		if (ret) {
-			dev_err(dev, "Failed to prepare pclk\n");
-			return ret;
-		}
-	} else {
+	if (PTR_ERR(data->pclk) == -ENOENT)
 		data->pclk = NULL;
-	}
+	else if (IS_ERR(data->pclk))
+		return PTR_ERR(data->pclk);
 
 	if (!data->clk && (!data->aclk || !data->pclk)) {
 		dev_err(dev, "Failed to get device clock(s)!\n");
@@ -640,15 +640,10 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 	}
 
 	data->clk_master = devm_clk_get(dev, "master");
-	if (!IS_ERR(data->clk_master)) {
-		ret = clk_prepare(data->clk_master);
-		if (ret) {
-			dev_err(dev, "Failed to prepare master's clk\n");
-			return ret;
-		}
-	} else {
+	if (PTR_ERR(data->clk_master) == -ENOENT)
 		data->clk_master = NULL;
-	}
+	else if (IS_ERR(data->clk_master))
+		return PTR_ERR(data->clk_master);
 
 	data->sysmmu = dev;
 	spin_lock_init(&data->lock);
@@ -665,6 +660,8 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 
+	of_iommu_set_ops(dev->of_node, &exynos_iommu_ops);
+
 	return 0;
 }
 
@@ -709,6 +706,7 @@ static struct platform_driver exynos_sysmmu_driver __refdata = {
 		.name		= "exynos-sysmmu",
 		.of_match_table	= sysmmu_of_match,
 		.pm		= &sysmmu_pm_ops,
+		.suppress_bind_attrs = true,
 	}
 };
 
@@ -716,7 +714,7 @@ static inline void update_pte(sysmmu_pte_t *ent, sysmmu_pte_t val)
 {
 	dma_sync_single_for_cpu(dma_dev, virt_to_phys(ent), sizeof(*ent),
 				DMA_TO_DEVICE);
-	*ent = val;
+	*ent = cpu_to_le32(val);
 	dma_sync_single_for_device(dma_dev, virt_to_phys(ent), sizeof(*ent),
 				   DMA_TO_DEVICE);
 }
@@ -1357,7 +1355,6 @@ static int __init exynos_iommu_of_setup(struct device_node *np)
 	if (!dma_dev)
 		dma_dev = &pdev->dev;
 
-	of_iommu_set_ops(np, &exynos_iommu_ops);
 	return 0;
 }
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 4b9040bb2f1c..afbaa2c69a59 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1672,7 +1672,7 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 		return -ENOMEM;
 	}
 
-	size = ((ndomains >> 8) + 1) * sizeof(struct dmar_domain **);
+	size = (ALIGN(ndomains, 256) >> 8) * sizeof(struct dmar_domain **);
 	iommu->domains = kzalloc(size, GFP_KERNEL);
 
 	if (iommu->domains) {
@@ -1737,7 +1737,7 @@ static void disable_dmar_iommu(struct intel_iommu *iommu)
 static void free_dmar_iommu(struct intel_iommu *iommu)
 {
 	if ((iommu->domains) && (iommu->domain_ids)) {
-		int elems = (cap_ndoms(iommu->cap) >> 8) + 1;
+		int elems = ALIGN(cap_ndoms(iommu->cap), 256) >> 8;
 		int i;
 
 		for (i = 0; i < elems; i++)
@@ -2076,7 +2076,7 @@ out_unlock:
 	spin_unlock(&iommu->lock);
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
-	return 0;
+	return ret;
 }
 
 struct domain_context_mapping_data {
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index a1ed1b73fed4..f5c90e1366ce 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -576,7 +576,7 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
 	return 0;
 
 found_translation:
-	iova &= (ARM_LPAE_GRANULE(data) - 1);
+	iova &= (ARM_LPAE_BLOCK_SIZE(lvl, data) - 1);
 	return ((phys_addr_t)iopte_to_pfn(pte,data) << data->pg_shift) | iova;
 }
 
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 3000051f48b4..b06d93594436 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -34,8 +34,7 @@
 #include <trace/events/iommu.h>
 
 static struct kset *iommu_group_kset;
-static struct ida iommu_group_ida;
-static struct mutex iommu_group_mutex;
+static DEFINE_IDA(iommu_group_ida);
 
 struct iommu_callback_data {
 	const struct iommu_ops *ops;
@@ -144,9 +143,7 @@ static void iommu_group_release(struct kobject *kobj)
 	if (group->iommu_data_release)
 		group->iommu_data_release(group->iommu_data);
 
-	mutex_lock(&iommu_group_mutex);
-	ida_remove(&iommu_group_ida, group->id);
-	mutex_unlock(&iommu_group_mutex);
+	ida_simple_remove(&iommu_group_ida, group->id);
 
 	if (group->default_domain)
 		iommu_domain_free(group->default_domain);
@@ -186,26 +183,17 @@ struct iommu_group *iommu_group_alloc(void)
 	INIT_LIST_HEAD(&group->devices);
 	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
 
-	mutex_lock(&iommu_group_mutex);
-
-again:
-	if (unlikely(0 == ida_pre_get(&iommu_group_ida, GFP_KERNEL))) {
+	ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL);
+	if (ret < 0) {
 		kfree(group);
-		mutex_unlock(&iommu_group_mutex);
-		return ERR_PTR(-ENOMEM);
+		return ERR_PTR(ret);
 	}
-
-	if (-EAGAIN == ida_get_new(&iommu_group_ida, &group->id))
-		goto again;
-
-	mutex_unlock(&iommu_group_mutex);
+	group->id = ret;
 
 	ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype,
 				   NULL, "%d", group->id);
 	if (ret) {
-		mutex_lock(&iommu_group_mutex);
-		ida_remove(&iommu_group_ida, group->id);
-		mutex_unlock(&iommu_group_mutex);
+		ida_simple_remove(&iommu_group_ida, group->id);
 		kfree(group);
 		return ERR_PTR(ret);
 	}
@@ -348,6 +336,9 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
 	list_for_each_entry(entry, &mappings, list) {
 		dma_addr_t start, end, addr;
 
+		if (domain->ops->apply_dm_region)
+			domain->ops->apply_dm_region(dev, domain, entry);
+
 		start = ALIGN(entry->start, pg_size);
 		end   = ALIGN(entry->start + entry->length, pg_size);
 
@@ -1483,9 +1474,6 @@ static int __init iommu_init(void)
 {
 	iommu_group_kset = kset_create_and_add("iommu_groups",
 					       NULL, kernel_kobj);
-	ida_init(&iommu_group_ida);
-	mutex_init(&iommu_group_mutex);
-
 	BUG_ON(!iommu_group_kset);
 
 	return 0;
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index e321fa517a45..b09692bb5b0a 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -27,32 +27,35 @@
 #include <linux/slab.h>
 #include <linux/iommu.h>
 #include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/of_iommu.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sizes.h>
 
 #include "msm_iommu_hw-8xxx.h"
 #include "msm_iommu.h"
+#include "io-pgtable.h"
 
 #define MRC(reg, processor, op1, crn, crm, op2)				\
 __asm__ __volatile__ (							\
 "   mrc   "   #processor "," #op1 ", %0,"  #crn "," #crm "," #op2 "\n"  \
 : "=r" (reg))
 
-#define RCP15_PRRR(reg)		MRC(reg, p15, 0, c10, c2, 0)
-#define RCP15_NMRR(reg)		MRC(reg, p15, 0, c10, c2, 1)
-
 /* bitmap of the page sizes currently supported */
 #define MSM_IOMMU_PGSIZES	(SZ_4K | SZ_64K | SZ_1M | SZ_16M)
 
-static int msm_iommu_tex_class[4];
-
 DEFINE_SPINLOCK(msm_iommu_lock);
+static LIST_HEAD(qcom_iommu_devices);
+static struct iommu_ops msm_iommu_ops;
 
 struct msm_priv {
-	unsigned long *pgtable;
 	struct list_head list_attached;
 	struct iommu_domain domain;
+	struct io_pgtable_cfg	cfg;
+	struct io_pgtable_ops	*iop;
+	struct device		*dev;
+	spinlock_t		pgtlock; /* pagetable lock */
 };
 
 static struct msm_priv *to_msm_priv(struct iommu_domain *dom)
@@ -60,67 +63,183 @@ static struct msm_priv *to_msm_priv(struct iommu_domain *dom)
 	return container_of(dom, struct msm_priv, domain);
 }
 
-static int __enable_clocks(struct msm_iommu_drvdata *drvdata)
+static int __enable_clocks(struct msm_iommu_dev *iommu)
 {
 	int ret;
 
-	ret = clk_enable(drvdata->pclk);
+	ret = clk_enable(iommu->pclk);
 	if (ret)
 		goto fail;
 
-	if (drvdata->clk) {
-		ret = clk_enable(drvdata->clk);
+	if (iommu->clk) {
+		ret = clk_enable(iommu->clk);
 		if (ret)
-			clk_disable(drvdata->pclk);
+			clk_disable(iommu->pclk);
 	}
 fail:
 	return ret;
 }
 
-static void __disable_clocks(struct msm_iommu_drvdata *drvdata)
+static void __disable_clocks(struct msm_iommu_dev *iommu)
 {
-	clk_disable(drvdata->clk);
-	clk_disable(drvdata->pclk);
+	if (iommu->clk)
+		clk_disable(iommu->clk);
+	clk_disable(iommu->pclk);
 }
 
-static int __flush_iotlb(struct iommu_domain *domain)
+static void msm_iommu_reset(void __iomem *base, int ncb)
 {
-	struct msm_priv *priv = to_msm_priv(domain);
-	struct msm_iommu_drvdata *iommu_drvdata;
-	struct msm_iommu_ctx_drvdata *ctx_drvdata;
-	int ret = 0;
-#ifndef CONFIG_IOMMU_PGTABLES_L2
-	unsigned long *fl_table = priv->pgtable;
-	int i;
-
-	if (!list_empty(&priv->list_attached)) {
-		dmac_flush_range(fl_table, fl_table + SZ_16K);
-
-		for (i = 0; i < NUM_FL_PTE; i++)
-			if ((fl_table[i] & 0x03) == FL_TYPE_TABLE) {
-				void *sl_table = __va(fl_table[i] &
-								FL_BASE_MASK);
-				dmac_flush_range(sl_table, sl_table + SZ_4K);
-			}
+	int ctx;
+
+	SET_RPUE(base, 0);
+	SET_RPUEIE(base, 0);
+	SET_ESRRESTORE(base, 0);
+	SET_TBE(base, 0);
+	SET_CR(base, 0);
+	SET_SPDMBE(base, 0);
+	SET_TESTBUSCR(base, 0);
+	SET_TLBRSW(base, 0);
+	SET_GLOBAL_TLBIALL(base, 0);
+	SET_RPU_ACR(base, 0);
+	SET_TLBLKCRWE(base, 1);
+
+	for (ctx = 0; ctx < ncb; ctx++) {
+		SET_BPRCOSH(base, ctx, 0);
+		SET_BPRCISH(base, ctx, 0);
+		SET_BPRCNSH(base, ctx, 0);
+		SET_BPSHCFG(base, ctx, 0);
+		SET_BPMTCFG(base, ctx, 0);
+		SET_ACTLR(base, ctx, 0);
+		SET_SCTLR(base, ctx, 0);
+		SET_FSRRESTORE(base, ctx, 0);
+		SET_TTBR0(base, ctx, 0);
+		SET_TTBR1(base, ctx, 0);
+		SET_TTBCR(base, ctx, 0);
+		SET_BFBCR(base, ctx, 0);
+		SET_PAR(base, ctx, 0);
+		SET_FAR(base, ctx, 0);
+		SET_CTX_TLBIALL(base, ctx, 0);
+		SET_TLBFLPTER(base, ctx, 0);
+		SET_TLBSLPTER(base, ctx, 0);
+		SET_TLBLKCR(base, ctx, 0);
+		SET_CONTEXTIDR(base, ctx, 0);
 	}
-#endif
+}
 
-	list_for_each_entry(ctx_drvdata, &priv->list_attached, attached_elm) {
+static void __flush_iotlb(void *cookie)
+{
+	struct msm_priv *priv = cookie;
+	struct msm_iommu_dev *iommu = NULL;
+	struct msm_iommu_ctx_dev *master;
+	int ret = 0;
+
+	list_for_each_entry(iommu, &priv->list_attached, dom_node) {
+		ret = __enable_clocks(iommu);
+		if (ret)
+			goto fail;
 
-		BUG_ON(!ctx_drvdata->pdev || !ctx_drvdata->pdev->dev.parent);
+		list_for_each_entry(master, &iommu->ctx_list, list)
+			SET_CTX_TLBIALL(iommu->base, master->num, 0);
 
-		iommu_drvdata = dev_get_drvdata(ctx_drvdata->pdev->dev.parent);
-		BUG_ON(!iommu_drvdata);
+		__disable_clocks(iommu);
+	}
+fail:
+	return;
+}
 
-		ret = __enable_clocks(iommu_drvdata);
+static void __flush_iotlb_range(unsigned long iova, size_t size,
+				size_t granule, bool leaf, void *cookie)
+{
+	struct msm_priv *priv = cookie;
+	struct msm_iommu_dev *iommu = NULL;
+	struct msm_iommu_ctx_dev *master;
+	int ret = 0;
+	int temp_size;
+
+	list_for_each_entry(iommu, &priv->list_attached, dom_node) {
+		ret = __enable_clocks(iommu);
 		if (ret)
 			goto fail;
 
-		SET_CTX_TLBIALL(iommu_drvdata->base, ctx_drvdata->num, 0);
-		__disable_clocks(iommu_drvdata);
+		list_for_each_entry(master, &iommu->ctx_list, list) {
+			temp_size = size;
+			do {
+				iova &= TLBIVA_VA;
+				iova |= GET_CONTEXTIDR_ASID(iommu->base,
+							    master->num);
+				SET_TLBIVA(iommu->base, master->num, iova);
+				iova += granule;
+			} while (temp_size -= granule);
+		}
+
+		__disable_clocks(iommu);
 	}
+
 fail:
-	return ret;
+	return;
+}
+
+static void __flush_iotlb_sync(void *cookie)
+{
+	/*
+	 * Nothing is needed here, the barrier to guarantee
+	 * completion of the tlb sync operation is implicitly
+	 * taken care when the iommu client does a writel before
+	 * kick starting the other master.
+	 */
+}
+
+static const struct iommu_gather_ops msm_iommu_gather_ops = {
+	.tlb_flush_all = __flush_iotlb,
+	.tlb_add_flush = __flush_iotlb_range,
+	.tlb_sync = __flush_iotlb_sync,
+};
+
+static int msm_iommu_alloc_ctx(unsigned long *map, int start, int end)
+{
+	int idx;
+
+	do {
+		idx = find_next_zero_bit(map, end, start);
+		if (idx == end)
+			return -ENOSPC;
+	} while (test_and_set_bit(idx, map));
+
+	return idx;
+}
+
+static void msm_iommu_free_ctx(unsigned long *map, int idx)
+{
+	clear_bit(idx, map);
+}
+
+static void config_mids(struct msm_iommu_dev *iommu,
+			struct msm_iommu_ctx_dev *master)
+{
+	int mid, ctx, i;
+
+	for (i = 0; i < master->num_mids; i++) {
+		mid = master->mids[i];
+		ctx = master->num;
+
+		SET_M2VCBR_N(iommu->base, mid, 0);
+		SET_CBACR_N(iommu->base, ctx, 0);
+
+		/* Set VMID = 0 */
+		SET_VMID(iommu->base, mid, 0);
+
+		/* Set the context number for that MID to this context */
+		SET_CBNDX(iommu->base, mid, ctx);
+
+		/* Set MID associated with this context bank to 0*/
+		SET_CBVMID(iommu->base, ctx, 0);
+
+		/* Set the ASID for TLB tagging for this context */
+		SET_CONTEXTIDR_ASID(iommu->base, ctx, ctx);
+
+		/* Set security bit override to be Non-secure */
+		SET_NSCFG(iommu->base, mid, 3);
+	}
 }
 
 static void __reset_context(void __iomem *base, int ctx)
@@ -143,15 +262,17 @@ static void __reset_context(void __iomem *base, int ctx)
 	SET_TLBFLPTER(base, ctx, 0);
 	SET_TLBSLPTER(base, ctx, 0);
 	SET_TLBLKCR(base, ctx, 0);
-	SET_PRRR(base, ctx, 0);
-	SET_NMRR(base, ctx, 0);
 }
 
-static void __program_context(void __iomem *base, int ctx, phys_addr_t pgtable)
+static void __program_context(void __iomem *base, int ctx,
+			      struct msm_priv *priv)
 {
-	unsigned int prrr, nmrr;
 	__reset_context(base, ctx);
 
+	/* Turn on TEX Remap */
+	SET_TRE(base, ctx, 1);
+	SET_AFE(base, ctx, 1);
+
 	/* Set up HTW mode */
 	/* TLB miss configuration: perform HTW on miss */
 	SET_TLBMCFG(base, ctx, 0x3);
@@ -159,8 +280,13 @@ static void __program_context(void __iomem *base, int ctx, phys_addr_t pgtable)
 	/* V2P configuration: HTW for access */
 	SET_V2PCFG(base, ctx, 0x3);
 
-	SET_TTBCR(base, ctx, 0);
-	SET_TTBR0_PA(base, ctx, (pgtable >> 14));
+	SET_TTBCR(base, ctx, priv->cfg.arm_v7s_cfg.tcr);
+	SET_TTBR0(base, ctx, priv->cfg.arm_v7s_cfg.ttbr[0]);
+	SET_TTBR1(base, ctx, priv->cfg.arm_v7s_cfg.ttbr[1]);
+
+	/* Set prrr and nmrr */
+	SET_PRRR(base, ctx, priv->cfg.arm_v7s_cfg.prrr);
+	SET_NMRR(base, ctx, priv->cfg.arm_v7s_cfg.nmrr);
 
 	/* Invalidate the TLB for this context */
 	SET_CTX_TLBIALL(base, ctx, 0);
@@ -179,38 +305,9 @@ static void __program_context(void __iomem *base, int ctx, phys_addr_t pgtable)
 	SET_RCOSH(base, ctx, 1);
 	SET_RCNSH(base, ctx, 1);
 
-	/* Turn on TEX Remap */
-	SET_TRE(base, ctx, 1);
-
-	/* Set TEX remap attributes */
-	RCP15_PRRR(prrr);
-	RCP15_NMRR(nmrr);
-	SET_PRRR(base, ctx, prrr);
-	SET_NMRR(base, ctx, nmrr);
-
 	/* Turn on BFB prefetch */
 	SET_BFBDFE(base, ctx, 1);
 
-#ifdef CONFIG_IOMMU_PGTABLES_L2
-	/* Configure page tables as inner-cacheable and shareable to reduce
-	 * the TLB miss penalty.
-	 */
-	SET_TTBR0_SH(base, ctx, 1);
-	SET_TTBR1_SH(base, ctx, 1);
-
-	SET_TTBR0_NOS(base, ctx, 1);
-	SET_TTBR1_NOS(base, ctx, 1);
-
-	SET_TTBR0_IRGNH(base, ctx, 0); /* WB, WA */
-	SET_TTBR0_IRGNL(base, ctx, 1);
-
-	SET_TTBR1_IRGNH(base, ctx, 0); /* WB, WA */
-	SET_TTBR1_IRGNL(base, ctx, 1);
-
-	SET_TTBR0_ORGN(base, ctx, 1); /* WB, WA */
-	SET_TTBR1_ORGN(base, ctx, 1); /* WB, WA */
-#endif
-
 	/* Enable the MMU */
 	SET_M(base, ctx, 1);
 }
@@ -227,13 +324,6 @@ static struct iommu_domain *msm_iommu_domain_alloc(unsigned type)
 		goto fail_nomem;
 
 	INIT_LIST_HEAD(&priv->list_attached);
-	priv->pgtable = (unsigned long *)__get_free_pages(GFP_KERNEL,
-							  get_order(SZ_16K));
-
-	if (!priv->pgtable)
-		goto fail_nomem;
-
-	memset(priv->pgtable, 0, SZ_16K);
 
 	priv->domain.geometry.aperture_start = 0;
 	priv->domain.geometry.aperture_end   = (1ULL << 32) - 1;
@@ -250,304 +340,137 @@ static void msm_iommu_domain_free(struct iommu_domain *domain)
 {
 	struct msm_priv *priv;
 	unsigned long flags;
-	unsigned long *fl_table;
-	int i;
 
 	spin_lock_irqsave(&msm_iommu_lock, flags);
 	priv = to_msm_priv(domain);
+	kfree(priv);
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+}
 
-	fl_table = priv->pgtable;
-
-	for (i = 0; i < NUM_FL_PTE; i++)
-		if ((fl_table[i] & 0x03) == FL_TYPE_TABLE)
-			free_page((unsigned long) __va(((fl_table[i]) &
-							FL_BASE_MASK)));
+static int msm_iommu_domain_config(struct msm_priv *priv)
+{
+	spin_lock_init(&priv->pgtlock);
+
+	priv->cfg = (struct io_pgtable_cfg) {
+		.quirks = IO_PGTABLE_QUIRK_TLBI_ON_MAP,
+		.pgsize_bitmap = msm_iommu_ops.pgsize_bitmap,
+		.ias = 32,
+		.oas = 32,
+		.tlb = &msm_iommu_gather_ops,
+		.iommu_dev = priv->dev,
+	};
+
+	priv->iop = alloc_io_pgtable_ops(ARM_V7S, &priv->cfg, priv);
+	if (!priv->iop) {
+		dev_err(priv->dev, "Failed to allocate pgtable\n");
+		return -EINVAL;
+	}
 
-	free_pages((unsigned long)priv->pgtable, get_order(SZ_16K));
-	priv->pgtable = NULL;
+	msm_iommu_ops.pgsize_bitmap = priv->cfg.pgsize_bitmap;
 
-	kfree(priv);
-	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+	return 0;
 }
 
 static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
-	struct msm_priv *priv;
-	struct msm_iommu_ctx_dev *ctx_dev;
-	struct msm_iommu_drvdata *iommu_drvdata;
-	struct msm_iommu_ctx_drvdata *ctx_drvdata;
-	struct msm_iommu_ctx_drvdata *tmp_drvdata;
 	int ret = 0;
 	unsigned long flags;
+	struct msm_iommu_dev *iommu;
+	struct msm_priv *priv = to_msm_priv(domain);
+	struct msm_iommu_ctx_dev *master;
 
-	spin_lock_irqsave(&msm_iommu_lock, flags);
-
-	priv = to_msm_priv(domain);
-
-	if (!dev) {
-		ret = -EINVAL;
-		goto fail;
-	}
-
-	iommu_drvdata = dev_get_drvdata(dev->parent);
-	ctx_drvdata = dev_get_drvdata(dev);
-	ctx_dev = dev->platform_data;
-
-	if (!iommu_drvdata || !ctx_drvdata || !ctx_dev) {
-		ret = -EINVAL;
-		goto fail;
-	}
-
-	if (!list_empty(&ctx_drvdata->attached_elm)) {
-		ret = -EBUSY;
-		goto fail;
-	}
+	priv->dev = dev;
+	msm_iommu_domain_config(priv);
 
-	list_for_each_entry(tmp_drvdata, &priv->list_attached, attached_elm)
-		if (tmp_drvdata == ctx_drvdata) {
-			ret = -EBUSY;
-			goto fail;
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	list_for_each_entry(iommu, &qcom_iommu_devices, dev_node) {
+		master = list_first_entry(&iommu->ctx_list,
+					  struct msm_iommu_ctx_dev,
+					  list);
+		if (master->of_node == dev->of_node) {
+			ret = __enable_clocks(iommu);
+			if (ret)
+				goto fail;
+
+			list_for_each_entry(master, &iommu->ctx_list, list) {
+				if (master->num) {
+					dev_err(dev, "domain already attached");
+					ret = -EEXIST;
+					goto fail;
+				}
+				master->num =
+					msm_iommu_alloc_ctx(iommu->context_map,
+							    0, iommu->ncb);
+					if (IS_ERR_VALUE(master->num)) {
+						ret = -ENODEV;
+						goto fail;
+					}
+				config_mids(iommu, master);
+				__program_context(iommu->base, master->num,
+						  priv);
+			}
+			__disable_clocks(iommu);
+			list_add(&iommu->dom_node, &priv->list_attached);
 		}
-
-	ret = __enable_clocks(iommu_drvdata);
-	if (ret)
-		goto fail;
-
-	__program_context(iommu_drvdata->base, ctx_dev->num,
-			  __pa(priv->pgtable));
-
-	__disable_clocks(iommu_drvdata);
-	list_add(&(ctx_drvdata->attached_elm), &priv->list_attached);
-	ret = __flush_iotlb(domain);
+	}
 
 fail:
 	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+
 	return ret;
 }
 
 static void msm_iommu_detach_dev(struct iommu_domain *domain,
 				 struct device *dev)
 {
-	struct msm_priv *priv;
-	struct msm_iommu_ctx_dev *ctx_dev;
-	struct msm_iommu_drvdata *iommu_drvdata;
-	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+	struct msm_priv *priv = to_msm_priv(domain);
 	unsigned long flags;
+	struct msm_iommu_dev *iommu;
+	struct msm_iommu_ctx_dev *master;
 	int ret;
 
-	spin_lock_irqsave(&msm_iommu_lock, flags);
-	priv = to_msm_priv(domain);
-
-	if (!dev)
-		goto fail;
-
-	iommu_drvdata = dev_get_drvdata(dev->parent);
-	ctx_drvdata = dev_get_drvdata(dev);
-	ctx_dev = dev->platform_data;
-
-	if (!iommu_drvdata || !ctx_drvdata || !ctx_dev)
-		goto fail;
-
-	ret = __flush_iotlb(domain);
-	if (ret)
-		goto fail;
-
-	ret = __enable_clocks(iommu_drvdata);
-	if (ret)
-		goto fail;
+	free_io_pgtable_ops(priv->iop);
 
-	__reset_context(iommu_drvdata->base, ctx_dev->num);
-	__disable_clocks(iommu_drvdata);
-	list_del_init(&ctx_drvdata->attached_elm);
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	list_for_each_entry(iommu, &priv->list_attached, dom_node) {
+		ret = __enable_clocks(iommu);
+		if (ret)
+			goto fail;
 
+		list_for_each_entry(master, &iommu->ctx_list, list) {
+			msm_iommu_free_ctx(iommu->context_map, master->num);
+			__reset_context(iommu->base, master->num);
+		}
+		__disable_clocks(iommu);
+	}
 fail:
 	spin_unlock_irqrestore(&msm_iommu_lock, flags);
 }
 
-static int msm_iommu_map(struct iommu_domain *domain, unsigned long va,
+static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
 			 phys_addr_t pa, size_t len, int prot)
 {
-	struct msm_priv *priv;
+	struct msm_priv *priv = to_msm_priv(domain);
 	unsigned long flags;
-	unsigned long *fl_table;
-	unsigned long *fl_pte;
-	unsigned long fl_offset;
-	unsigned long *sl_table;
-	unsigned long *sl_pte;
-	unsigned long sl_offset;
-	unsigned int pgprot;
-	int ret = 0, tex, sh;
-
-	spin_lock_irqsave(&msm_iommu_lock, flags);
-
-	sh = (prot & MSM_IOMMU_ATTR_SH) ? 1 : 0;
-	tex = msm_iommu_tex_class[prot & MSM_IOMMU_CP_MASK];
-
-	if (tex < 0 || tex > NUM_TEX_CLASS - 1) {
-		ret = -EINVAL;
-		goto fail;
-	}
-
-	priv = to_msm_priv(domain);
-
-	fl_table = priv->pgtable;
-
-	if (len != SZ_16M && len != SZ_1M &&
-	    len != SZ_64K && len != SZ_4K) {
-		pr_debug("Bad size: %d\n", len);
-		ret = -EINVAL;
-		goto fail;
-	}
-
-	if (!fl_table) {
-		pr_debug("Null page table\n");
-		ret = -EINVAL;
-		goto fail;
-	}
-
-	if (len == SZ_16M || len == SZ_1M) {
-		pgprot = sh ? FL_SHARED : 0;
-		pgprot |= tex & 0x01 ? FL_BUFFERABLE : 0;
-		pgprot |= tex & 0x02 ? FL_CACHEABLE : 0;
-		pgprot |= tex & 0x04 ? FL_TEX0 : 0;
-	} else	{
-		pgprot = sh ? SL_SHARED : 0;
-		pgprot |= tex & 0x01 ? SL_BUFFERABLE : 0;
-		pgprot |= tex & 0x02 ? SL_CACHEABLE : 0;
-		pgprot |= tex & 0x04 ? SL_TEX0 : 0;
-	}
-
-	fl_offset = FL_OFFSET(va);	/* Upper 12 bits */
-	fl_pte = fl_table + fl_offset;	/* int pointers, 4 bytes */
-
-	if (len == SZ_16M) {
-		int i = 0;
-		for (i = 0; i < 16; i++)
-			*(fl_pte+i) = (pa & 0xFF000000) | FL_SUPERSECTION |
-				  FL_AP_READ | FL_AP_WRITE | FL_TYPE_SECT |
-				  FL_SHARED | FL_NG | pgprot;
-	}
-
-	if (len == SZ_1M)
-		*fl_pte = (pa & 0xFFF00000) | FL_AP_READ | FL_AP_WRITE | FL_NG |
-					    FL_TYPE_SECT | FL_SHARED | pgprot;
-
-	/* Need a 2nd level table */
-	if ((len == SZ_4K || len == SZ_64K) && (*fl_pte) == 0) {
-		unsigned long *sl;
-		sl = (unsigned long *) __get_free_pages(GFP_ATOMIC,
-							get_order(SZ_4K));
-
-		if (!sl) {
-			pr_debug("Could not allocate second level table\n");
-			ret = -ENOMEM;
-			goto fail;
-		}
-
-		memset(sl, 0, SZ_4K);
-		*fl_pte = ((((int)__pa(sl)) & FL_BASE_MASK) | FL_TYPE_TABLE);
-	}
-
-	sl_table = (unsigned long *) __va(((*fl_pte) & FL_BASE_MASK));
-	sl_offset = SL_OFFSET(va);
-	sl_pte = sl_table + sl_offset;
-
-
-	if (len == SZ_4K)
-		*sl_pte = (pa & SL_BASE_MASK_SMALL) | SL_AP0 | SL_AP1 | SL_NG |
-					  SL_SHARED | SL_TYPE_SMALL | pgprot;
-
-	if (len == SZ_64K) {
-		int i;
+	int ret;
 
-		for (i = 0; i < 16; i++)
-			*(sl_pte+i) = (pa & SL_BASE_MASK_LARGE) | SL_AP0 |
-			    SL_NG | SL_AP1 | SL_SHARED | SL_TYPE_LARGE | pgprot;
-	}
+	spin_lock_irqsave(&priv->pgtlock, flags);
+	ret = priv->iop->map(priv->iop, iova, pa, len, prot);
+	spin_unlock_irqrestore(&priv->pgtlock, flags);
 
-	ret = __flush_iotlb(domain);
-fail:
-	spin_unlock_irqrestore(&msm_iommu_lock, flags);
 	return ret;
 }
 
-static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long va,
-			    size_t len)
+static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+			      size_t len)
 {
-	struct msm_priv *priv;
+	struct msm_priv *priv = to_msm_priv(domain);
 	unsigned long flags;
-	unsigned long *fl_table;
-	unsigned long *fl_pte;
-	unsigned long fl_offset;
-	unsigned long *sl_table;
-	unsigned long *sl_pte;
-	unsigned long sl_offset;
-	int i, ret = 0;
-
-	spin_lock_irqsave(&msm_iommu_lock, flags);
-
-	priv = to_msm_priv(domain);
 
-	fl_table = priv->pgtable;
+	spin_lock_irqsave(&priv->pgtlock, flags);
+	len = priv->iop->unmap(priv->iop, iova, len);
+	spin_unlock_irqrestore(&priv->pgtlock, flags);
 
-	if (len != SZ_16M && len != SZ_1M &&
-	    len != SZ_64K && len != SZ_4K) {
-		pr_debug("Bad length: %d\n", len);
-		goto fail;
-	}
-
-	if (!fl_table) {
-		pr_debug("Null page table\n");
-		goto fail;
-	}
-
-	fl_offset = FL_OFFSET(va);	/* Upper 12 bits */
-	fl_pte = fl_table + fl_offset;	/* int pointers, 4 bytes */
-
-	if (*fl_pte == 0) {
-		pr_debug("First level PTE is 0\n");
-		goto fail;
-	}
-
-	/* Unmap supersection */
-	if (len == SZ_16M)
-		for (i = 0; i < 16; i++)
-			*(fl_pte+i) = 0;
-
-	if (len == SZ_1M)
-		*fl_pte = 0;
-
-	sl_table = (unsigned long *) __va(((*fl_pte) & FL_BASE_MASK));
-	sl_offset = SL_OFFSET(va);
-	sl_pte = sl_table + sl_offset;
-
-	if (len == SZ_64K) {
-		for (i = 0; i < 16; i++)
-			*(sl_pte+i) = 0;
-	}
-
-	if (len == SZ_4K)
-		*sl_pte = 0;
-
-	if (len == SZ_4K || len == SZ_64K) {
-		int used = 0;
-
-		for (i = 0; i < NUM_SL_PTE; i++)
-			if (sl_table[i])
-				used = 1;
-		if (!used) {
-			free_page((unsigned long)sl_table);
-			*fl_pte = 0;
-		}
-	}
-
-	ret = __flush_iotlb(domain);
-
-fail:
-	spin_unlock_irqrestore(&msm_iommu_lock, flags);
-
-	/* the IOMMU API requires us to return how many bytes were unmapped */
-	len = ret ? 0 : len;
 	return len;
 }
 
@@ -555,47 +478,46 @@ static phys_addr_t msm_iommu_iova_to_phys(struct iommu_domain *domain,
 					  dma_addr_t va)
 {
 	struct msm_priv *priv;
-	struct msm_iommu_drvdata *iommu_drvdata;
-	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+	struct msm_iommu_dev *iommu;
+	struct msm_iommu_ctx_dev *master;
 	unsigned int par;
 	unsigned long flags;
-	void __iomem *base;
 	phys_addr_t ret = 0;
-	int ctx;
 
 	spin_lock_irqsave(&msm_iommu_lock, flags);
 
 	priv = to_msm_priv(domain);
-	if (list_empty(&priv->list_attached))
-		goto fail;
+	iommu = list_first_entry(&priv->list_attached,
+				 struct msm_iommu_dev, dom_node);
 
-	ctx_drvdata = list_entry(priv->list_attached.next,
-				 struct msm_iommu_ctx_drvdata, attached_elm);
-	iommu_drvdata = dev_get_drvdata(ctx_drvdata->pdev->dev.parent);
+	if (list_empty(&iommu->ctx_list))
+		goto fail;
 
-	base = iommu_drvdata->base;
-	ctx = ctx_drvdata->num;
+	master = list_first_entry(&iommu->ctx_list,
+				  struct msm_iommu_ctx_dev, list);
+	if (!master)
+		goto fail;
 
-	ret = __enable_clocks(iommu_drvdata);
+	ret = __enable_clocks(iommu);
 	if (ret)
 		goto fail;
 
 	/* Invalidate context TLB */
-	SET_CTX_TLBIALL(base, ctx, 0);
-	SET_V2PPR(base, ctx, va & V2Pxx_VA);
+	SET_CTX_TLBIALL(iommu->base, master->num, 0);
+	SET_V2PPR(iommu->base, master->num, va & V2Pxx_VA);
 
-	par = GET_PAR(base, ctx);
+	par = GET_PAR(iommu->base, master->num);
 
 	/* We are dealing with a supersection */
-	if (GET_NOFAULT_SS(base, ctx))
+	if (GET_NOFAULT_SS(iommu->base, master->num))
 		ret = (par & 0xFF000000) | (va & 0x00FFFFFF);
 	else	/* Upper 20 bits from PAR, lower 12 from VA */
 		ret = (par & 0xFFFFF000) | (va & 0x00000FFF);
 
-	if (GET_FAULT(base, ctx))
+	if (GET_FAULT(iommu->base, master->num))
 		ret = 0;
 
-	__disable_clocks(iommu_drvdata);
+	__disable_clocks(iommu);
 fail:
 	spin_unlock_irqrestore(&msm_iommu_lock, flags);
 	return ret;
@@ -629,49 +551,92 @@ static void print_ctx_regs(void __iomem *base, int ctx)
 	       GET_TTBR0(base, ctx), GET_TTBR1(base, ctx));
 	pr_err("SCTLR  = %08x    ACTLR  = %08x\n",
 	       GET_SCTLR(base, ctx), GET_ACTLR(base, ctx));
-	pr_err("PRRR   = %08x    NMRR   = %08x\n",
-	       GET_PRRR(base, ctx), GET_NMRR(base, ctx));
+}
+
+static void insert_iommu_master(struct device *dev,
+				struct msm_iommu_dev **iommu,
+				struct of_phandle_args *spec)
+{
+	struct msm_iommu_ctx_dev *master = dev->archdata.iommu;
+	int sid;
+
+	if (list_empty(&(*iommu)->ctx_list)) {
+		master = kzalloc(sizeof(*master), GFP_ATOMIC);
+		master->of_node = dev->of_node;
+		list_add(&master->list, &(*iommu)->ctx_list);
+		dev->archdata.iommu = master;
+	}
+
+	for (sid = 0; sid < master->num_mids; sid++)
+		if (master->mids[sid] == spec->args[0]) {
+			dev_warn(dev, "Stream ID 0x%hx repeated; ignoring\n",
+				 sid);
+			return;
+		}
+
+	master->mids[master->num_mids++] = spec->args[0];
+}
+
+static int qcom_iommu_of_xlate(struct device *dev,
+			       struct of_phandle_args *spec)
+{
+	struct msm_iommu_dev *iommu;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	list_for_each_entry(iommu, &qcom_iommu_devices, dev_node)
+		if (iommu->dev->of_node == spec->np)
+			break;
+
+	if (!iommu || iommu->dev->of_node != spec->np) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	insert_iommu_master(dev, &iommu, spec);
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+
+	return ret;
 }
 
 irqreturn_t msm_iommu_fault_handler(int irq, void *dev_id)
 {
-	struct msm_iommu_drvdata *drvdata = dev_id;
-	void __iomem *base;
+	struct msm_iommu_dev *iommu = dev_id;
 	unsigned int fsr;
 	int i, ret;
 
 	spin_lock(&msm_iommu_lock);
 
-	if (!drvdata) {
+	if (!iommu) {
 		pr_err("Invalid device ID in context interrupt handler\n");
 		goto fail;
 	}
 
-	base = drvdata->base;
-
 	pr_err("Unexpected IOMMU page fault!\n");
-	pr_err("base = %08x\n", (unsigned int) base);
+	pr_err("base = %08x\n", (unsigned int)iommu->base);
 
-	ret = __enable_clocks(drvdata);
+	ret = __enable_clocks(iommu);
 	if (ret)
 		goto fail;
 
-	for (i = 0; i < drvdata->ncb; i++) {
-		fsr = GET_FSR(base, i);
+	for (i = 0; i < iommu->ncb; i++) {
+		fsr = GET_FSR(iommu->base, i);
 		if (fsr) {
 			pr_err("Fault occurred in context %d.\n", i);
 			pr_err("Interesting registers:\n");
-			print_ctx_regs(base, i);
-			SET_FSR(base, i, 0x4000000F);
+			print_ctx_regs(iommu->base, i);
+			SET_FSR(iommu->base, i, 0x4000000F);
 		}
 	}
-	__disable_clocks(drvdata);
+	__disable_clocks(iommu);
 fail:
 	spin_unlock(&msm_iommu_lock);
 	return 0;
 }
 
-static const struct iommu_ops msm_iommu_ops = {
+static struct iommu_ops msm_iommu_ops = {
 	.capable = msm_iommu_capable,
 	.domain_alloc = msm_iommu_domain_alloc,
 	.domain_free = msm_iommu_domain_free,
@@ -682,54 +647,163 @@ static const struct iommu_ops msm_iommu_ops = {
 	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = msm_iommu_iova_to_phys,
 	.pgsize_bitmap = MSM_IOMMU_PGSIZES,
+	.of_xlate = qcom_iommu_of_xlate,
 };
 
-static int __init get_tex_class(int icp, int ocp, int mt, int nos)
+static int msm_iommu_probe(struct platform_device *pdev)
 {
-	int i = 0;
-	unsigned int prrr = 0;
-	unsigned int nmrr = 0;
-	int c_icp, c_ocp, c_mt, c_nos;
-
-	RCP15_PRRR(prrr);
-	RCP15_NMRR(nmrr);
-
-	for (i = 0; i < NUM_TEX_CLASS; i++) {
-		c_nos = PRRR_NOS(prrr, i);
-		c_mt = PRRR_MT(prrr, i);
-		c_icp = NMRR_ICP(nmrr, i);
-		c_ocp = NMRR_OCP(nmrr, i);
-
-		if (icp == c_icp && ocp == c_ocp && c_mt == mt && c_nos == nos)
-			return i;
+	struct resource *r;
+	struct msm_iommu_dev *iommu;
+	int ret, par, val;
+
+	iommu = devm_kzalloc(&pdev->dev, sizeof(*iommu), GFP_KERNEL);
+	if (!iommu)
+		return -ENODEV;
+
+	iommu->dev = &pdev->dev;
+	INIT_LIST_HEAD(&iommu->ctx_list);
+
+	iommu->pclk = devm_clk_get(iommu->dev, "smmu_pclk");
+	if (IS_ERR(iommu->pclk)) {
+		dev_err(iommu->dev, "could not get smmu_pclk\n");
+		return PTR_ERR(iommu->pclk);
+	}
+
+	ret = clk_prepare(iommu->pclk);
+	if (ret) {
+		dev_err(iommu->dev, "could not prepare smmu_pclk\n");
+		return ret;
+	}
+
+	iommu->clk = devm_clk_get(iommu->dev, "iommu_clk");
+	if (IS_ERR(iommu->clk)) {
+		dev_err(iommu->dev, "could not get iommu_clk\n");
+		clk_unprepare(iommu->pclk);
+		return PTR_ERR(iommu->clk);
+	}
+
+	ret = clk_prepare(iommu->clk);
+	if (ret) {
+		dev_err(iommu->dev, "could not prepare iommu_clk\n");
+		clk_unprepare(iommu->pclk);
+		return ret;
+	}
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	iommu->base = devm_ioremap_resource(iommu->dev, r);
+	if (IS_ERR(iommu->base)) {
+		dev_err(iommu->dev, "could not get iommu base\n");
+		ret = PTR_ERR(iommu->base);
+		goto fail;
 	}
 
-	return -ENODEV;
+	iommu->irq = platform_get_irq(pdev, 0);
+	if (iommu->irq < 0) {
+		dev_err(iommu->dev, "could not get iommu irq\n");
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	ret = of_property_read_u32(iommu->dev->of_node, "qcom,ncb", &val);
+	if (ret) {
+		dev_err(iommu->dev, "could not get ncb\n");
+		goto fail;
+	}
+	iommu->ncb = val;
+
+	msm_iommu_reset(iommu->base, iommu->ncb);
+	SET_M(iommu->base, 0, 1);
+	SET_PAR(iommu->base, 0, 0);
+	SET_V2PCFG(iommu->base, 0, 1);
+	SET_V2PPR(iommu->base, 0, 0);
+	par = GET_PAR(iommu->base, 0);
+	SET_V2PCFG(iommu->base, 0, 0);
+	SET_M(iommu->base, 0, 0);
+
+	if (!par) {
+		pr_err("Invalid PAR value detected\n");
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	ret = devm_request_threaded_irq(iommu->dev, iommu->irq, NULL,
+					msm_iommu_fault_handler,
+					IRQF_ONESHOT | IRQF_SHARED,
+					"msm_iommu_secure_irpt_handler",
+					iommu);
+	if (ret) {
+		pr_err("Request IRQ %d failed with ret=%d\n", iommu->irq, ret);
+		goto fail;
+	}
+
+	list_add(&iommu->dev_node, &qcom_iommu_devices);
+	of_iommu_set_ops(pdev->dev.of_node, &msm_iommu_ops);
+
+	pr_info("device mapped at %p, irq %d with %d ctx banks\n",
+		iommu->base, iommu->irq, iommu->ncb);
+
+	return ret;
+fail:
+	clk_unprepare(iommu->clk);
+	clk_unprepare(iommu->pclk);
+	return ret;
+}
+
+static const struct of_device_id msm_iommu_dt_match[] = {
+	{ .compatible = "qcom,apq8064-iommu" },
+	{}
+};
+
+static int msm_iommu_remove(struct platform_device *pdev)
+{
+	struct msm_iommu_dev *iommu = platform_get_drvdata(pdev);
+
+	clk_unprepare(iommu->clk);
+	clk_unprepare(iommu->pclk);
+	return 0;
 }
 
-static void __init setup_iommu_tex_classes(void)
+static struct platform_driver msm_iommu_driver = {
+	.driver = {
+		.name	= "msm_iommu",
+		.of_match_table = msm_iommu_dt_match,
+	},
+	.probe		= msm_iommu_probe,
+	.remove		= msm_iommu_remove,
+};
+
+static int __init msm_iommu_driver_init(void)
 {
-	msm_iommu_tex_class[MSM_IOMMU_ATTR_NONCACHED] =
-			get_tex_class(CP_NONCACHED, CP_NONCACHED, MT_NORMAL, 1);
+	int ret;
 
-	msm_iommu_tex_class[MSM_IOMMU_ATTR_CACHED_WB_WA] =
-			get_tex_class(CP_WB_WA, CP_WB_WA, MT_NORMAL, 1);
+	ret = platform_driver_register(&msm_iommu_driver);
+	if (ret != 0)
+		pr_err("Failed to register IOMMU driver\n");
 
-	msm_iommu_tex_class[MSM_IOMMU_ATTR_CACHED_WB_NWA] =
-			get_tex_class(CP_WB_NWA, CP_WB_NWA, MT_NORMAL, 1);
+	return ret;
+}
 
-	msm_iommu_tex_class[MSM_IOMMU_ATTR_CACHED_WT] =
-			get_tex_class(CP_WT, CP_WT, MT_NORMAL, 1);
+static void __exit msm_iommu_driver_exit(void)
+{
+	platform_driver_unregister(&msm_iommu_driver);
 }
 
+subsys_initcall(msm_iommu_driver_init);
+module_exit(msm_iommu_driver_exit);
+
 static int __init msm_iommu_init(void)
 {
-	setup_iommu_tex_classes();
 	bus_set_iommu(&platform_bus_type, &msm_iommu_ops);
 	return 0;
 }
 
-subsys_initcall(msm_iommu_init);
+static int __init msm_iommu_of_setup(struct device_node *np)
+{
+	msm_iommu_init();
+	return 0;
+}
+
+IOMMU_OF_DECLARE(msm_iommu_of, "qcom,apq8064-iommu", msm_iommu_of_setup);
 
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>");
diff --git a/drivers/iommu/msm_iommu.h b/drivers/iommu/msm_iommu.h
index 5c7c955e6d25..4ca25d50d679 100644
--- a/drivers/iommu/msm_iommu.h
+++ b/drivers/iommu/msm_iommu.h
@@ -42,74 +42,53 @@
  */
 #define MAX_NUM_MIDS	32
 
+/* Maximum number of context banks that can be present in IOMMU */
+#define IOMMU_MAX_CBS	128
+
 /**
  * struct msm_iommu_dev - a single IOMMU hardware instance
- * name		Human-readable name given to this IOMMU HW instance
  * ncb		Number of context banks present on this IOMMU HW instance
+ * dev:		IOMMU device
+ * irq:		Interrupt number
+ * clk:		The bus clock for this IOMMU hardware instance
+ * pclk:	The clock for the IOMMU bus interconnect
+ * dev_node:	list head in qcom_iommu_device_list
+ * dom_node:	list head for domain
+ * ctx_list:	list of 'struct msm_iommu_ctx_dev'
+ * context_map: Bitmap to track allocated context banks
  */
 struct msm_iommu_dev {
-	const char *name;
+	void __iomem *base;
 	int ncb;
+	struct device *dev;
+	int irq;
+	struct clk *clk;
+	struct clk *pclk;
+	struct list_head dev_node;
+	struct list_head dom_node;
+	struct list_head ctx_list;
+	DECLARE_BITMAP(context_map, IOMMU_MAX_CBS);
 };
 
 /**
  * struct msm_iommu_ctx_dev - an IOMMU context bank instance
- * name		Human-readable name given to this context bank
+ * of_node	node ptr of client device
  * num		Index of this context bank within the hardware
  * mids		List of Machine IDs that are to be mapped into this context
  *		bank, terminated by -1. The MID is a set of signals on the
  *		AXI bus that identifies the function associated with a specific
  *		memory request. (See ARM spec).
+ * num_mids	Total number of mids
+ * node		list head in ctx_list
  */
 struct msm_iommu_ctx_dev {
-	const char *name;
+	struct device_node *of_node;
 	int num;
 	int mids[MAX_NUM_MIDS];
+	int num_mids;
+	struct list_head list;
 };
 
-
-/**
- * struct msm_iommu_drvdata - A single IOMMU hardware instance
- * @base:	IOMMU config port base address (VA)
- * @ncb		The number of contexts on this IOMMU
- * @irq:	Interrupt number
- * @clk:	The bus clock for this IOMMU hardware instance
- * @pclk:	The clock for the IOMMU bus interconnect
- *
- * A msm_iommu_drvdata holds the global driver data about a single piece
- * of an IOMMU hardware instance.
- */
-struct msm_iommu_drvdata {
-	void __iomem *base;
-	int irq;
-	int ncb;
-	struct clk *clk;
-	struct clk *pclk;
-};
-
-/**
- * struct msm_iommu_ctx_drvdata - an IOMMU context bank instance
- * @num:		Hardware context number of this context
- * @pdev:		Platform device associated wit this HW instance
- * @attached_elm:	List element for domains to track which devices are
- *			attached to them
- *
- * A msm_iommu_ctx_drvdata holds the driver data for a single context bank
- * within each IOMMU hardware instance
- */
-struct msm_iommu_ctx_drvdata {
-	int num;
-	struct platform_device *pdev;
-	struct list_head attached_elm;
-};
-
-/*
- * Look up an IOMMU context device by its context name. NULL if none found.
- * Useful for testing and drivers that do not yet fully have IOMMU stuff in
- * their platform devices.
- */
-struct device *msm_iommu_get_ctx(const char *ctx_name);
-
 /*
  * Interrupt handler for the IOMMU context fault interrupt. Hooking the
  * interrupt is not supported in the API yet, but this will print an error
diff --git a/drivers/iommu/msm_iommu_dev.c b/drivers/iommu/msm_iommu_dev.c
deleted file mode 100644
index 4b09e815accf..000000000000
--- a/drivers/iommu/msm_iommu_dev.c
+++ /dev/null
@@ -1,381 +0,0 @@
-/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA.
- */
-
-#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/io.h>
-#include <linux/clk.h>
-#include <linux/iommu.h>
-#include <linux/interrupt.h>
-#include <linux/err.h>
-#include <linux/slab.h>
-
-#include "msm_iommu_hw-8xxx.h"
-#include "msm_iommu.h"
-
-struct iommu_ctx_iter_data {
-	/* input */
-	const char *name;
-
-	/* output */
-	struct device *dev;
-};
-
-static struct platform_device *msm_iommu_root_dev;
-
-static int each_iommu_ctx(struct device *dev, void *data)
-{
-	struct iommu_ctx_iter_data *res = data;
-	struct msm_iommu_ctx_dev *c = dev->platform_data;
-
-	if (!res || !c || !c->name || !res->name)
-		return -EINVAL;
-
-	if (!strcmp(res->name, c->name)) {
-		res->dev = dev;
-		return 1;
-	}
-	return 0;
-}
-
-static int each_iommu(struct device *dev, void *data)
-{
-	return device_for_each_child(dev, data, each_iommu_ctx);
-}
-
-struct device *msm_iommu_get_ctx(const char *ctx_name)
-{
-	struct iommu_ctx_iter_data r;
-	int found;
-
-	if (!msm_iommu_root_dev) {
-		pr_err("No root IOMMU device.\n");
-		goto fail;
-	}
-
-	r.name = ctx_name;
-	found = device_for_each_child(&msm_iommu_root_dev->dev, &r, each_iommu);
-
-	if (!found) {
-		pr_err("Could not find context <%s>\n", ctx_name);
-		goto fail;
-	}
-
-	return r.dev;
-fail:
-	return NULL;
-}
-EXPORT_SYMBOL(msm_iommu_get_ctx);
-
-static void msm_iommu_reset(void __iomem *base, int ncb)
-{
-	int ctx;
-
-	SET_RPUE(base, 0);
-	SET_RPUEIE(base, 0);
-	SET_ESRRESTORE(base, 0);
-	SET_TBE(base, 0);
-	SET_CR(base, 0);
-	SET_SPDMBE(base, 0);
-	SET_TESTBUSCR(base, 0);
-	SET_TLBRSW(base, 0);
-	SET_GLOBAL_TLBIALL(base, 0);
-	SET_RPU_ACR(base, 0);
-	SET_TLBLKCRWE(base, 1);
-
-	for (ctx = 0; ctx < ncb; ctx++) {
-		SET_BPRCOSH(base, ctx, 0);
-		SET_BPRCISH(base, ctx, 0);
-		SET_BPRCNSH(base, ctx, 0);
-		SET_BPSHCFG(base, ctx, 0);
-		SET_BPMTCFG(base, ctx, 0);
-		SET_ACTLR(base, ctx, 0);
-		SET_SCTLR(base, ctx, 0);
-		SET_FSRRESTORE(base, ctx, 0);
-		SET_TTBR0(base, ctx, 0);
-		SET_TTBR1(base, ctx, 0);
-		SET_TTBCR(base, ctx, 0);
-		SET_BFBCR(base, ctx, 0);
-		SET_PAR(base, ctx, 0);
-		SET_FAR(base, ctx, 0);
-		SET_CTX_TLBIALL(base, ctx, 0);
-		SET_TLBFLPTER(base, ctx, 0);
-		SET_TLBSLPTER(base, ctx, 0);
-		SET_TLBLKCR(base, ctx, 0);
-		SET_PRRR(base, ctx, 0);
-		SET_NMRR(base, ctx, 0);
-		SET_CONTEXTIDR(base, ctx, 0);
-	}
-}
-
-static int msm_iommu_probe(struct platform_device *pdev)
-{
-	struct resource *r;
-	struct clk *iommu_clk;
-	struct clk *iommu_pclk;
-	struct msm_iommu_drvdata *drvdata;
-	struct msm_iommu_dev *iommu_dev = dev_get_platdata(&pdev->dev);
-	void __iomem *regs_base;
-	int ret, irq, par;
-
-	if (pdev->id == -1) {
-		msm_iommu_root_dev = pdev;
-		return 0;
-	}
-
-	drvdata = kzalloc(sizeof(*drvdata), GFP_KERNEL);
-
-	if (!drvdata) {
-		ret = -ENOMEM;
-		goto fail;
-	}
-
-	if (!iommu_dev) {
-		ret = -ENODEV;
-		goto fail;
-	}
-
-	iommu_pclk = clk_get(NULL, "smmu_pclk");
-	if (IS_ERR(iommu_pclk)) {
-		ret = -ENODEV;
-		goto fail;
-	}
-
-	ret = clk_prepare_enable(iommu_pclk);
-	if (ret)
-		goto fail_enable;
-
-	iommu_clk = clk_get(&pdev->dev, "iommu_clk");
-
-	if (!IS_ERR(iommu_clk))	{
-		if (clk_get_rate(iommu_clk) == 0)
-			clk_set_rate(iommu_clk, 1);
-
-		ret = clk_prepare_enable(iommu_clk);
-		if (ret) {
-			clk_put(iommu_clk);
-			goto fail_pclk;
-		}
-	} else
-		iommu_clk = NULL;
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "physbase");
-	regs_base = devm_ioremap_resource(&pdev->dev, r);
-	if (IS_ERR(regs_base)) {
-		ret = PTR_ERR(regs_base);
-		goto fail_clk;
-	}
-
-	irq = platform_get_irq_byname(pdev, "secure_irq");
-	if (irq < 0) {
-		ret = -ENODEV;
-		goto fail_clk;
-	}
-
-	msm_iommu_reset(regs_base, iommu_dev->ncb);
-
-	SET_M(regs_base, 0, 1);
-	SET_PAR(regs_base, 0, 0);
-	SET_V2PCFG(regs_base, 0, 1);
-	SET_V2PPR(regs_base, 0, 0);
-	par = GET_PAR(regs_base, 0);
-	SET_V2PCFG(regs_base, 0, 0);
-	SET_M(regs_base, 0, 0);
-
-	if (!par) {
-		pr_err("%s: Invalid PAR value detected\n", iommu_dev->name);
-		ret = -ENODEV;
-		goto fail_clk;
-	}
-
-	ret = request_irq(irq, msm_iommu_fault_handler, 0,
-			"msm_iommu_secure_irpt_handler", drvdata);
-	if (ret) {
-		pr_err("Request IRQ %d failed with ret=%d\n", irq, ret);
-		goto fail_clk;
-	}
-
-
-	drvdata->pclk = iommu_pclk;
-	drvdata->clk = iommu_clk;
-	drvdata->base = regs_base;
-	drvdata->irq = irq;
-	drvdata->ncb = iommu_dev->ncb;
-
-	pr_info("device %s mapped at %p, irq %d with %d ctx banks\n",
-		iommu_dev->name, regs_base, irq, iommu_dev->ncb);
-
-	platform_set_drvdata(pdev, drvdata);
-
-	clk_disable(iommu_clk);
-
-	clk_disable(iommu_pclk);
-
-	return 0;
-fail_clk:
-	if (iommu_clk) {
-		clk_disable(iommu_clk);
-		clk_put(iommu_clk);
-	}
-fail_pclk:
-	clk_disable_unprepare(iommu_pclk);
-fail_enable:
-	clk_put(iommu_pclk);
-fail:
-	kfree(drvdata);
-	return ret;
-}
-
-static int msm_iommu_remove(struct platform_device *pdev)
-{
-	struct msm_iommu_drvdata *drv = NULL;
-
-	drv = platform_get_drvdata(pdev);
-	if (drv) {
-		if (drv->clk) {
-			clk_unprepare(drv->clk);
-			clk_put(drv->clk);
-		}
-		clk_unprepare(drv->pclk);
-		clk_put(drv->pclk);
-		memset(drv, 0, sizeof(*drv));
-		kfree(drv);
-	}
-	return 0;
-}
-
-static int msm_iommu_ctx_probe(struct platform_device *pdev)
-{
-	struct msm_iommu_ctx_dev *c = dev_get_platdata(&pdev->dev);
-	struct msm_iommu_drvdata *drvdata;
-	struct msm_iommu_ctx_drvdata *ctx_drvdata;
-	int i, ret;
-
-	if (!c || !pdev->dev.parent)
-		return -EINVAL;
-
-	drvdata = dev_get_drvdata(pdev->dev.parent);
-	if (!drvdata)
-		return -ENODEV;
-
-	ctx_drvdata = kzalloc(sizeof(*ctx_drvdata), GFP_KERNEL);
-	if (!ctx_drvdata)
-		return -ENOMEM;
-
-	ctx_drvdata->num = c->num;
-	ctx_drvdata->pdev = pdev;
-
-	INIT_LIST_HEAD(&ctx_drvdata->attached_elm);
-	platform_set_drvdata(pdev, ctx_drvdata);
-
-	ret = clk_prepare_enable(drvdata->pclk);
-	if (ret)
-		goto fail;
-
-	if (drvdata->clk) {
-		ret = clk_prepare_enable(drvdata->clk);
-		if (ret) {
-			clk_disable_unprepare(drvdata->pclk);
-			goto fail;
-		}
-	}
-
-	/* Program the M2V tables for this context */
-	for (i = 0; i < MAX_NUM_MIDS; i++) {
-		int mid = c->mids[i];
-		if (mid == -1)
-			break;
-
-		SET_M2VCBR_N(drvdata->base, mid, 0);
-		SET_CBACR_N(drvdata->base, c->num, 0);
-
-		/* Set VMID = 0 */
-		SET_VMID(drvdata->base, mid, 0);
-
-		/* Set the context number for that MID to this context */
-		SET_CBNDX(drvdata->base, mid, c->num);
-
-		/* Set MID associated with this context bank to 0*/
-		SET_CBVMID(drvdata->base, c->num, 0);
-
-		/* Set the ASID for TLB tagging for this context */
-		SET_CONTEXTIDR_ASID(drvdata->base, c->num, c->num);
-
-		/* Set security bit override to be Non-secure */
-		SET_NSCFG(drvdata->base, mid, 3);
-	}
-
-	clk_disable(drvdata->clk);
-	clk_disable(drvdata->pclk);
-
-	dev_info(&pdev->dev, "context %s using bank %d\n", c->name, c->num);
-	return 0;
-fail:
-	kfree(ctx_drvdata);
-	return ret;
-}
-
-static int msm_iommu_ctx_remove(struct platform_device *pdev)
-{
-	struct msm_iommu_ctx_drvdata *drv = NULL;
-	drv = platform_get_drvdata(pdev);
-	if (drv) {
-		memset(drv, 0, sizeof(struct msm_iommu_ctx_drvdata));
-		kfree(drv);
-	}
-	return 0;
-}
-
-static struct platform_driver msm_iommu_driver = {
-	.driver = {
-		.name	= "msm_iommu",
-	},
-	.probe		= msm_iommu_probe,
-	.remove		= msm_iommu_remove,
-};
-
-static struct platform_driver msm_iommu_ctx_driver = {
-	.driver = {
-		.name	= "msm_iommu_ctx",
-	},
-	.probe		= msm_iommu_ctx_probe,
-	.remove		= msm_iommu_ctx_remove,
-};
-
-static struct platform_driver * const drivers[] = {
-	&msm_iommu_driver,
-	&msm_iommu_ctx_driver,
-};
-
-static int __init msm_iommu_driver_init(void)
-{
-	return platform_register_drivers(drivers, ARRAY_SIZE(drivers));
-}
-
-static void __exit msm_iommu_driver_exit(void)
-{
-	platform_unregister_drivers(drivers, ARRAY_SIZE(drivers));
-}
-
-subsys_initcall(msm_iommu_driver_init);
-module_exit(msm_iommu_driver_exit);
-
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>");
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index c3043d8754e3..b12c12d74c33 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -34,7 +34,7 @@
 #include <dt-bindings/memory/mt8173-larb-port.h>
 #include <soc/mediatek/smi.h>
 
-#include "io-pgtable.h"
+#include "mtk_iommu.h"
 
 #define REG_MMU_PT_BASE_ADDR			0x000
 
@@ -93,20 +93,6 @@
 
 #define MTK_PROTECT_PA_ALIGN			128
 
-struct mtk_iommu_suspend_reg {
-	u32				standard_axi_mode;
-	u32				dcm_dis;
-	u32				ctrl_reg;
-	u32				int_control0;
-	u32				int_main_control;
-};
-
-struct mtk_iommu_client_priv {
-	struct list_head		client;
-	unsigned int			mtk_m4u_id;
-	struct device			*m4udev;
-};
-
 struct mtk_iommu_domain {
 	spinlock_t			pgtlock; /* lock for page table */
 
@@ -116,19 +102,6 @@ struct mtk_iommu_domain {
 	struct iommu_domain		domain;
 };
 
-struct mtk_iommu_data {
-	void __iomem			*base;
-	int				irq;
-	struct device			*dev;
-	struct clk			*bclk;
-	phys_addr_t			protect_base; /* protect memory base */
-	struct mtk_iommu_suspend_reg	reg;
-	struct mtk_iommu_domain		*m4u_dom;
-	struct iommu_group		*m4u_group;
-	struct mtk_smi_iommu		smi_imu;      /* SMI larb iommu info */
-	bool                            enable_4GB;
-};
-
 static struct iommu_ops mtk_iommu_ops;
 
 static struct mtk_iommu_domain *to_mtk_domain(struct iommu_domain *dom)
@@ -455,7 +428,6 @@ static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	if (!dev->archdata.iommu) {
 		/* Get the m4u device */
 		m4updev = of_find_device_by_node(args->np);
-		of_node_put(args->np);
 		if (WARN_ON(!m4updev))
 			return -EINVAL;
 
@@ -552,25 +524,6 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 	return 0;
 }
 
-static int compare_of(struct device *dev, void *data)
-{
-	return dev->of_node == data;
-}
-
-static int mtk_iommu_bind(struct device *dev)
-{
-	struct mtk_iommu_data *data = dev_get_drvdata(dev);
-
-	return component_bind_all(dev, &data->smi_imu);
-}
-
-static void mtk_iommu_unbind(struct device *dev)
-{
-	struct mtk_iommu_data *data = dev_get_drvdata(dev);
-
-	component_unbind_all(dev, &data->smi_imu);
-}
-
 static const struct component_master_ops mtk_iommu_com_ops = {
 	.bind		= mtk_iommu_bind,
 	.unbind		= mtk_iommu_unbind,
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
new file mode 100644
index 000000000000..9ed0a8462ccf
--- /dev/null
+++ b/drivers/iommu/mtk_iommu.h
@@ -0,0 +1,77 @@
+/*
+ * Copyright (c) 2015-2016 MediaTek Inc.
+ * Author: Honghui Zhang <honghui.zhang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _MTK_IOMMU_H_
+#define _MTK_IOMMU_H_
+
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <soc/mediatek/smi.h>
+
+#include "io-pgtable.h"
+
+struct mtk_iommu_suspend_reg {
+	u32				standard_axi_mode;
+	u32				dcm_dis;
+	u32				ctrl_reg;
+	u32				int_control0;
+	u32				int_main_control;
+};
+
+struct mtk_iommu_client_priv {
+	struct list_head		client;
+	unsigned int			mtk_m4u_id;
+	struct device			*m4udev;
+};
+
+struct mtk_iommu_domain;
+
+struct mtk_iommu_data {
+	void __iomem			*base;
+	int				irq;
+	struct device			*dev;
+	struct clk			*bclk;
+	phys_addr_t			protect_base; /* protect memory base */
+	struct mtk_iommu_suspend_reg	reg;
+	struct mtk_iommu_domain		*m4u_dom;
+	struct iommu_group		*m4u_group;
+	struct mtk_smi_iommu		smi_imu;      /* SMI larb iommu info */
+	bool                            enable_4GB;
+};
+
+static int compare_of(struct device *dev, void *data)
+{
+	return dev->of_node == data;
+}
+
+static int mtk_iommu_bind(struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_get_drvdata(dev);
+
+	return component_bind_all(dev, &data->smi_imu);
+}
+
+static void mtk_iommu_unbind(struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_get_drvdata(dev);
+
+	component_unbind_all(dev, &data->smi_imu);
+}
+
+#endif
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
new file mode 100644
index 000000000000..b8aeb0768483
--- /dev/null
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -0,0 +1,727 @@
+/*
+ * Copyright (c) 2015-2016 MediaTek Inc.
+ * Author: Honghui Zhang <honghui.zhang@mediatek.com>
+ *
+ * Based on driver/iommu/mtk_iommu.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/bootmem.h>
+#include <linux/bug.h>
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/device.h>
+#include <linux/dma-iommu.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/kmemleak.h>
+#include <linux/list.h>
+#include <linux/of_address.h>
+#include <linux/of_iommu.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <asm/barrier.h>
+#include <asm/dma-iommu.h>
+#include <linux/module.h>
+#include <dt-bindings/memory/mt2701-larb-port.h>
+#include <soc/mediatek/smi.h>
+#include "mtk_iommu.h"
+
+#define REG_MMU_PT_BASE_ADDR			0x000
+
+#define F_ALL_INVLD				0x2
+#define F_MMU_INV_RANGE				0x1
+#define F_INVLD_EN0				BIT(0)
+#define F_INVLD_EN1				BIT(1)
+
+#define F_MMU_FAULT_VA_MSK			0xfffff000
+#define MTK_PROTECT_PA_ALIGN			128
+
+#define REG_MMU_CTRL_REG			0x210
+#define F_MMU_CTRL_COHERENT_EN			BIT(8)
+#define REG_MMU_IVRP_PADDR			0x214
+#define REG_MMU_INT_CONTROL			0x220
+#define F_INT_TRANSLATION_FAULT			BIT(0)
+#define F_INT_MAIN_MULTI_HIT_FAULT		BIT(1)
+#define F_INT_INVALID_PA_FAULT			BIT(2)
+#define F_INT_ENTRY_REPLACEMENT_FAULT		BIT(3)
+#define F_INT_TABLE_WALK_FAULT			BIT(4)
+#define F_INT_TLB_MISS_FAULT			BIT(5)
+#define F_INT_PFH_DMA_FIFO_OVERFLOW		BIT(6)
+#define F_INT_MISS_DMA_FIFO_OVERFLOW		BIT(7)
+
+#define F_MMU_TF_PROTECT_SEL(prot)		(((prot) & 0x3) << 5)
+#define F_INT_CLR_BIT				BIT(12)
+
+#define REG_MMU_FAULT_ST			0x224
+#define REG_MMU_FAULT_VA			0x228
+#define REG_MMU_INVLD_PA			0x22C
+#define REG_MMU_INT_ID				0x388
+#define REG_MMU_INVALIDATE			0x5c0
+#define REG_MMU_INVLD_START_A			0x5c4
+#define REG_MMU_INVLD_END_A			0x5c8
+
+#define REG_MMU_INV_SEL				0x5d8
+#define REG_MMU_STANDARD_AXI_MODE		0x5e8
+
+#define REG_MMU_DCM				0x5f0
+#define F_MMU_DCM_ON				BIT(1)
+#define REG_MMU_CPE_DONE			0x60c
+#define F_DESC_VALID				0x2
+#define F_DESC_NONSEC				BIT(3)
+#define MT2701_M4U_TF_LARB(TF)			(6 - (((TF) >> 13) & 0x7))
+#define MT2701_M4U_TF_PORT(TF)			(((TF) >> 8) & 0xF)
+/* MTK generation one iommu HW only support 4K size mapping */
+#define MT2701_IOMMU_PAGE_SHIFT			12
+#define MT2701_IOMMU_PAGE_SIZE			(1UL << MT2701_IOMMU_PAGE_SHIFT)
+
+/*
+ * MTK m4u support 4GB iova address space, and only support 4K page
+ * mapping. So the pagetable size should be exactly as 4M.
+ */
+#define M2701_IOMMU_PGT_SIZE			SZ_4M
+
+struct mtk_iommu_domain {
+	spinlock_t			pgtlock; /* lock for page table */
+	struct iommu_domain		domain;
+	u32				*pgt_va;
+	dma_addr_t			pgt_pa;
+	struct mtk_iommu_data		*data;
+};
+
+static struct mtk_iommu_domain *to_mtk_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct mtk_iommu_domain, domain);
+}
+
+static const int mt2701_m4u_in_larb[] = {
+	LARB0_PORT_OFFSET, LARB1_PORT_OFFSET,
+	LARB2_PORT_OFFSET, LARB3_PORT_OFFSET
+};
+
+static inline int mt2701_m4u_to_larb(int id)
+{
+	int i;
+
+	for (i = ARRAY_SIZE(mt2701_m4u_in_larb) - 1; i >= 0; i--)
+		if ((id) >= mt2701_m4u_in_larb[i])
+			return i;
+
+	return 0;
+}
+
+static inline int mt2701_m4u_to_port(int id)
+{
+	int larb = mt2701_m4u_to_larb(id);
+
+	return id - mt2701_m4u_in_larb[larb];
+}
+
+static void mtk_iommu_tlb_flush_all(struct mtk_iommu_data *data)
+{
+	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
+			data->base + REG_MMU_INV_SEL);
+	writel_relaxed(F_ALL_INVLD, data->base + REG_MMU_INVALIDATE);
+	wmb(); /* Make sure the tlb flush all done */
+}
+
+static void mtk_iommu_tlb_flush_range(struct mtk_iommu_data *data,
+				unsigned long iova, size_t size)
+{
+	int ret;
+	u32 tmp;
+
+	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
+		data->base + REG_MMU_INV_SEL);
+	writel_relaxed(iova & F_MMU_FAULT_VA_MSK,
+		data->base + REG_MMU_INVLD_START_A);
+	writel_relaxed((iova + size - 1) & F_MMU_FAULT_VA_MSK,
+		data->base + REG_MMU_INVLD_END_A);
+	writel_relaxed(F_MMU_INV_RANGE, data->base + REG_MMU_INVALIDATE);
+
+	ret = readl_poll_timeout_atomic(data->base + REG_MMU_CPE_DONE,
+				tmp, tmp != 0, 10, 100000);
+	if (ret) {
+		dev_warn(data->dev,
+			 "Partial TLB flush timed out, falling back to full flush\n");
+		mtk_iommu_tlb_flush_all(data);
+	}
+	/* Clear the CPE status */
+	writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
+}
+
+static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
+{
+	struct mtk_iommu_data *data = dev_id;
+	struct mtk_iommu_domain *dom = data->m4u_dom;
+	u32 int_state, regval, fault_iova, fault_pa;
+	unsigned int fault_larb, fault_port;
+
+	/* Read error information from registers */
+	int_state = readl_relaxed(data->base + REG_MMU_FAULT_ST);
+	fault_iova = readl_relaxed(data->base + REG_MMU_FAULT_VA);
+
+	fault_iova &= F_MMU_FAULT_VA_MSK;
+	fault_pa = readl_relaxed(data->base + REG_MMU_INVLD_PA);
+	regval = readl_relaxed(data->base + REG_MMU_INT_ID);
+	fault_larb = MT2701_M4U_TF_LARB(regval);
+	fault_port = MT2701_M4U_TF_PORT(regval);
+
+	/*
+	 * MTK v1 iommu HW could not determine whether the fault is read or
+	 * write fault, report as read fault.
+	 */
+	if (report_iommu_fault(&dom->domain, data->dev, fault_iova,
+			IOMMU_FAULT_READ))
+		dev_err_ratelimited(data->dev,
+			"fault type=0x%x iova=0x%x pa=0x%x larb=%d port=%d\n",
+			int_state, fault_iova, fault_pa,
+			fault_larb, fault_port);
+
+	/* Interrupt clear */
+	regval = readl_relaxed(data->base + REG_MMU_INT_CONTROL);
+	regval |= F_INT_CLR_BIT;
+	writel_relaxed(regval, data->base + REG_MMU_INT_CONTROL);
+
+	mtk_iommu_tlb_flush_all(data);
+
+	return IRQ_HANDLED;
+}
+
+static void mtk_iommu_config(struct mtk_iommu_data *data,
+			     struct device *dev, bool enable)
+{
+	struct mtk_iommu_client_priv *head, *cur, *next;
+	struct mtk_smi_larb_iommu    *larb_mmu;
+	unsigned int                 larbid, portid;
+
+	head = dev->archdata.iommu;
+	list_for_each_entry_safe(cur, next, &head->client, client) {
+		larbid = mt2701_m4u_to_larb(cur->mtk_m4u_id);
+		portid = mt2701_m4u_to_port(cur->mtk_m4u_id);
+		larb_mmu = &data->smi_imu.larb_imu[larbid];
+
+		dev_dbg(dev, "%s iommu port: %d\n",
+			enable ? "enable" : "disable", portid);
+
+		if (enable)
+			larb_mmu->mmu |= MTK_SMI_MMU_EN(portid);
+		else
+			larb_mmu->mmu &= ~MTK_SMI_MMU_EN(portid);
+	}
+}
+
+static int mtk_iommu_domain_finalise(struct mtk_iommu_data *data)
+{
+	struct mtk_iommu_domain *dom = data->m4u_dom;
+
+	spin_lock_init(&dom->pgtlock);
+
+	dom->pgt_va = dma_zalloc_coherent(data->dev,
+				M2701_IOMMU_PGT_SIZE,
+				&dom->pgt_pa, GFP_KERNEL);
+	if (!dom->pgt_va)
+		return -ENOMEM;
+
+	writel(dom->pgt_pa, data->base + REG_MMU_PT_BASE_ADDR);
+
+	dom->data = data;
+
+	return 0;
+}
+
+static struct iommu_domain *mtk_iommu_domain_alloc(unsigned type)
+{
+	struct mtk_iommu_domain *dom;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
+	if (!dom)
+		return NULL;
+
+	return &dom->domain;
+}
+
+static void mtk_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	struct mtk_iommu_data *data = dom->data;
+
+	dma_free_coherent(data->dev, M2701_IOMMU_PGT_SIZE,
+			dom->pgt_va, dom->pgt_pa);
+	kfree(to_mtk_domain(domain));
+}
+
+static int mtk_iommu_attach_device(struct iommu_domain *domain,
+				   struct device *dev)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	struct mtk_iommu_client_priv *priv = dev->archdata.iommu;
+	struct mtk_iommu_data *data;
+	int ret;
+
+	if (!priv)
+		return -ENODEV;
+
+	data = dev_get_drvdata(priv->m4udev);
+	if (!data->m4u_dom) {
+		data->m4u_dom = dom;
+		ret = mtk_iommu_domain_finalise(data);
+		if (ret) {
+			data->m4u_dom = NULL;
+			return ret;
+		}
+	}
+
+	mtk_iommu_config(data, dev, true);
+	return 0;
+}
+
+static void mtk_iommu_detach_device(struct iommu_domain *domain,
+				    struct device *dev)
+{
+	struct mtk_iommu_client_priv *priv = dev->archdata.iommu;
+	struct mtk_iommu_data *data;
+
+	if (!priv)
+		return;
+
+	data = dev_get_drvdata(priv->m4udev);
+	mtk_iommu_config(data, dev, false);
+}
+
+static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
+			 phys_addr_t paddr, size_t size, int prot)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT;
+	unsigned long flags;
+	unsigned int i;
+	u32 *pgt_base_iova = dom->pgt_va + (iova  >> MT2701_IOMMU_PAGE_SHIFT);
+	u32 pabase = (u32)paddr;
+	int map_size = 0;
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	for (i = 0; i < page_num; i++) {
+		if (pgt_base_iova[i]) {
+			memset(pgt_base_iova, 0, i * sizeof(u32));
+			break;
+		}
+		pgt_base_iova[i] = pabase | F_DESC_VALID | F_DESC_NONSEC;
+		pabase += MT2701_IOMMU_PAGE_SIZE;
+		map_size += MT2701_IOMMU_PAGE_SIZE;
+	}
+
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	mtk_iommu_tlb_flush_range(dom->data, iova, size);
+
+	return map_size == size ? 0 : -EEXIST;
+}
+
+static size_t mtk_iommu_unmap(struct iommu_domain *domain,
+			      unsigned long iova, size_t size)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	unsigned long flags;
+	u32 *pgt_base_iova = dom->pgt_va + (iova  >> MT2701_IOMMU_PAGE_SHIFT);
+	unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT;
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	memset(pgt_base_iova, 0, page_num * sizeof(u32));
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	mtk_iommu_tlb_flush_range(dom->data, iova, size);
+
+	return size;
+}
+
+static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
+					  dma_addr_t iova)
+{
+	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
+	unsigned long flags;
+	phys_addr_t pa;
+
+	spin_lock_irqsave(&dom->pgtlock, flags);
+	pa = *(dom->pgt_va + (iova >> MT2701_IOMMU_PAGE_SHIFT));
+	pa = pa & (~(MT2701_IOMMU_PAGE_SIZE - 1));
+	spin_unlock_irqrestore(&dom->pgtlock, flags);
+
+	return pa;
+}
+
+/*
+ * MTK generation one iommu HW only support one iommu domain, and all the client
+ * sharing the same iova address space.
+ */
+static int mtk_iommu_create_mapping(struct device *dev,
+				    struct of_phandle_args *args)
+{
+	struct mtk_iommu_client_priv *head, *priv, *next;
+	struct platform_device *m4updev;
+	struct dma_iommu_mapping *mtk_mapping;
+	struct device *m4udev;
+	int ret;
+
+	if (args->args_count != 1) {
+		dev_err(dev, "invalid #iommu-cells(%d) property for IOMMU\n",
+			args->args_count);
+		return -EINVAL;
+	}
+
+	if (!dev->archdata.iommu) {
+		/* Get the m4u device */
+		m4updev = of_find_device_by_node(args->np);
+		if (WARN_ON(!m4updev))
+			return -EINVAL;
+
+		head = kzalloc(sizeof(*head), GFP_KERNEL);
+		if (!head)
+			return -ENOMEM;
+
+		dev->archdata.iommu = head;
+		INIT_LIST_HEAD(&head->client);
+		head->m4udev = &m4updev->dev;
+	} else {
+		head = dev->archdata.iommu;
+	}
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		ret = -ENOMEM;
+		goto err_free_mem;
+	}
+	priv->mtk_m4u_id = args->args[0];
+	list_add_tail(&priv->client, &head->client);
+
+	m4udev = head->m4udev;
+	mtk_mapping = m4udev->archdata.iommu;
+	if (!mtk_mapping) {
+		/* MTK iommu support 4GB iova address space. */
+		mtk_mapping = arm_iommu_create_mapping(&platform_bus_type,
+						0, 1ULL << 32);
+		if (IS_ERR(mtk_mapping)) {
+			ret = PTR_ERR(mtk_mapping);
+			goto err_free_mem;
+		}
+		m4udev->archdata.iommu = mtk_mapping;
+	}
+
+	ret = arm_iommu_attach_device(dev, mtk_mapping);
+	if (ret)
+		goto err_release_mapping;
+
+	return 0;
+
+err_release_mapping:
+	arm_iommu_release_mapping(mtk_mapping);
+	m4udev->archdata.iommu = NULL;
+err_free_mem:
+	list_for_each_entry_safe(priv, next, &head->client, client)
+		kfree(priv);
+	kfree(head);
+	dev->archdata.iommu = NULL;
+	return ret;
+}
+
+static int mtk_iommu_add_device(struct device *dev)
+{
+	struct iommu_group *group;
+	struct of_phandle_args iommu_spec;
+	struct of_phandle_iterator it;
+	int err;
+
+	of_for_each_phandle(&it, err, dev->of_node, "iommus",
+			"#iommu-cells", 0) {
+		int count = of_phandle_iterator_args(&it, iommu_spec.args,
+					MAX_PHANDLE_ARGS);
+		iommu_spec.np = of_node_get(it.node);
+		iommu_spec.args_count = count;
+
+		mtk_iommu_create_mapping(dev, &iommu_spec);
+		of_node_put(iommu_spec.np);
+	}
+
+	if (!dev->archdata.iommu) /* Not a iommu client device */
+		return -ENODEV;
+
+	group = iommu_group_get_for_dev(dev);
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	iommu_group_put(group);
+	return 0;
+}
+
+static void mtk_iommu_remove_device(struct device *dev)
+{
+	struct mtk_iommu_client_priv *head, *cur, *next;
+
+	head = dev->archdata.iommu;
+	if (!head)
+		return;
+
+	list_for_each_entry_safe(cur, next, &head->client, client) {
+		list_del(&cur->client);
+		kfree(cur);
+	}
+	kfree(head);
+	dev->archdata.iommu = NULL;
+
+	iommu_group_remove_device(dev);
+}
+
+static struct iommu_group *mtk_iommu_device_group(struct device *dev)
+{
+	struct mtk_iommu_data *data;
+	struct mtk_iommu_client_priv *priv;
+
+	priv = dev->archdata.iommu;
+	if (!priv)
+		return ERR_PTR(-ENODEV);
+
+	/* All the client devices are in the same m4u iommu-group */
+	data = dev_get_drvdata(priv->m4udev);
+	if (!data->m4u_group) {
+		data->m4u_group = iommu_group_alloc();
+		if (IS_ERR(data->m4u_group))
+			dev_err(dev, "Failed to allocate M4U IOMMU group\n");
+	}
+	return data->m4u_group;
+}
+
+static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
+{
+	u32 regval;
+	int ret;
+
+	ret = clk_prepare_enable(data->bclk);
+	if (ret) {
+		dev_err(data->dev, "Failed to enable iommu bclk(%d)\n", ret);
+		return ret;
+	}
+
+	regval = F_MMU_CTRL_COHERENT_EN | F_MMU_TF_PROTECT_SEL(2);
+	writel_relaxed(regval, data->base + REG_MMU_CTRL_REG);
+
+	regval = F_INT_TRANSLATION_FAULT |
+		F_INT_MAIN_MULTI_HIT_FAULT |
+		F_INT_INVALID_PA_FAULT |
+		F_INT_ENTRY_REPLACEMENT_FAULT |
+		F_INT_TABLE_WALK_FAULT |
+		F_INT_TLB_MISS_FAULT |
+		F_INT_PFH_DMA_FIFO_OVERFLOW |
+		F_INT_MISS_DMA_FIFO_OVERFLOW;
+	writel_relaxed(regval, data->base + REG_MMU_INT_CONTROL);
+
+	/* protect memory,hw will write here while translation fault */
+	writel_relaxed(data->protect_base,
+			data->base + REG_MMU_IVRP_PADDR);
+
+	writel_relaxed(F_MMU_DCM_ON, data->base + REG_MMU_DCM);
+
+	if (devm_request_irq(data->dev, data->irq, mtk_iommu_isr, 0,
+			     dev_name(data->dev), (void *)data)) {
+		writel_relaxed(0, data->base + REG_MMU_PT_BASE_ADDR);
+		clk_disable_unprepare(data->bclk);
+		dev_err(data->dev, "Failed @ IRQ-%d Request\n", data->irq);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static struct iommu_ops mtk_iommu_ops = {
+	.domain_alloc	= mtk_iommu_domain_alloc,
+	.domain_free	= mtk_iommu_domain_free,
+	.attach_dev	= mtk_iommu_attach_device,
+	.detach_dev	= mtk_iommu_detach_device,
+	.map		= mtk_iommu_map,
+	.unmap		= mtk_iommu_unmap,
+	.map_sg		= default_iommu_map_sg,
+	.iova_to_phys	= mtk_iommu_iova_to_phys,
+	.add_device	= mtk_iommu_add_device,
+	.remove_device	= mtk_iommu_remove_device,
+	.device_group	= mtk_iommu_device_group,
+	.pgsize_bitmap	= ~0UL << MT2701_IOMMU_PAGE_SHIFT,
+};
+
+static const struct of_device_id mtk_iommu_of_ids[] = {
+	{ .compatible = "mediatek,mt2701-m4u", },
+	{}
+};
+
+static const struct component_master_ops mtk_iommu_com_ops = {
+	.bind		= mtk_iommu_bind,
+	.unbind		= mtk_iommu_unbind,
+};
+
+static int mtk_iommu_probe(struct platform_device *pdev)
+{
+	struct mtk_iommu_data		*data;
+	struct device			*dev = &pdev->dev;
+	struct resource			*res;
+	struct component_match		*match = NULL;
+	struct of_phandle_args		larb_spec;
+	struct of_phandle_iterator	it;
+	void				*protect;
+	int				larb_nr, ret, err;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->dev = dev;
+
+	/* Protect memory. HW will access here while translation fault.*/
+	protect = devm_kzalloc(dev, MTK_PROTECT_PA_ALIGN * 2,
+			GFP_KERNEL | GFP_DMA);
+	if (!protect)
+		return -ENOMEM;
+	data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(data->base))
+		return PTR_ERR(data->base);
+
+	data->irq = platform_get_irq(pdev, 0);
+	if (data->irq < 0)
+		return data->irq;
+
+	data->bclk = devm_clk_get(dev, "bclk");
+	if (IS_ERR(data->bclk))
+		return PTR_ERR(data->bclk);
+
+	larb_nr = 0;
+	of_for_each_phandle(&it, err, dev->of_node,
+			"mediatek,larbs", NULL, 0) {
+		struct platform_device *plarbdev;
+		int count = of_phandle_iterator_args(&it, larb_spec.args,
+					MAX_PHANDLE_ARGS);
+
+		if (count)
+			continue;
+
+		larb_spec.np = of_node_get(it.node);
+		if (!of_device_is_available(larb_spec.np))
+			continue;
+
+		plarbdev = of_find_device_by_node(larb_spec.np);
+		of_node_put(larb_spec.np);
+		if (!plarbdev) {
+			plarbdev = of_platform_device_create(
+						larb_spec.np, NULL,
+						platform_bus_type.dev_root);
+			if (!plarbdev)
+				return -EPROBE_DEFER;
+		}
+
+		data->smi_imu.larb_imu[larb_nr].dev = &plarbdev->dev;
+		component_match_add(dev, &match, compare_of, larb_spec.np);
+		larb_nr++;
+	}
+
+	data->smi_imu.larb_nr = larb_nr;
+
+	platform_set_drvdata(pdev, data);
+
+	ret = mtk_iommu_hw_init(data);
+	if (ret)
+		return ret;
+
+	if (!iommu_present(&platform_bus_type))
+		bus_set_iommu(&platform_bus_type,  &mtk_iommu_ops);
+
+	return component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
+}
+
+static int mtk_iommu_remove(struct platform_device *pdev)
+{
+	struct mtk_iommu_data *data = platform_get_drvdata(pdev);
+
+	if (iommu_present(&platform_bus_type))
+		bus_set_iommu(&platform_bus_type, NULL);
+
+	clk_disable_unprepare(data->bclk);
+	devm_free_irq(&pdev->dev, data->irq, data);
+	component_master_del(&pdev->dev, &mtk_iommu_com_ops);
+	return 0;
+}
+
+static int __maybe_unused mtk_iommu_suspend(struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_get_drvdata(dev);
+	struct mtk_iommu_suspend_reg *reg = &data->reg;
+	void __iomem *base = data->base;
+
+	reg->standard_axi_mode = readl_relaxed(base +
+					       REG_MMU_STANDARD_AXI_MODE);
+	reg->dcm_dis = readl_relaxed(base + REG_MMU_DCM);
+	reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG);
+	reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL);
+	return 0;
+}
+
+static int __maybe_unused mtk_iommu_resume(struct device *dev)
+{
+	struct mtk_iommu_data *data = dev_get_drvdata(dev);
+	struct mtk_iommu_suspend_reg *reg = &data->reg;
+	void __iomem *base = data->base;
+
+	writel_relaxed(data->m4u_dom->pgt_pa, base + REG_MMU_PT_BASE_ADDR);
+	writel_relaxed(reg->standard_axi_mode,
+		       base + REG_MMU_STANDARD_AXI_MODE);
+	writel_relaxed(reg->dcm_dis, base + REG_MMU_DCM);
+	writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG);
+	writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL);
+	writel_relaxed(data->protect_base, base + REG_MMU_IVRP_PADDR);
+	return 0;
+}
+
+static const struct dev_pm_ops mtk_iommu_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(mtk_iommu_suspend, mtk_iommu_resume)
+};
+
+static struct platform_driver mtk_iommu_driver = {
+	.probe	= mtk_iommu_probe,
+	.remove	= mtk_iommu_remove,
+	.driver	= {
+		.name = "mtk-iommu",
+		.of_match_table = mtk_iommu_of_ids,
+		.pm = &mtk_iommu_pm_ops,
+	}
+};
+
+static int __init m4u_init(void)
+{
+	return platform_driver_register(&mtk_iommu_driver);
+}
+
+static void __exit m4u_exit(void)
+{
+	return platform_driver_unregister(&mtk_iommu_driver);
+}
+
+subsys_initcall(m4u_init);
+module_exit(m4u_exit);
+
+MODULE_DESCRIPTION("IOMMU API for MTK architected m4u v1 implementations");
+MODULE_AUTHOR("Honghui Zhang <honghui.zhang@mediatek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index af499aea0a1a..57f23eaaa2f9 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -174,7 +174,7 @@ err_put_node:
 	return NULL;
 }
 
-void __init of_iommu_init(void)
+static int __init of_iommu_init(void)
 {
 	struct device_node *np;
 	const struct of_device_id *match, *matches = &__iommu_of_table;
@@ -186,4 +186,7 @@ void __init of_iommu_init(void)
 			pr_err("Failed to initialise IOMMU %s\n",
 				of_node_full_name(np));
 	}
+
+	return 0;
 }
+postcore_initcall_sync(of_iommu_init);
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 25b4627cb57f..9afcbf79f0b0 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -4,11 +4,10 @@
  * published by the Free Software Foundation.
  */
 
-#include <asm/cacheflush.h>
-#include <asm/pgtable.h>
 #include <linux/compiler.h>
 #include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/dma-iommu.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -77,7 +76,9 @@
 
 struct rk_iommu_domain {
 	struct list_head iommus;
+	struct platform_device *pdev;
 	u32 *dt; /* page directory table */
+	dma_addr_t dt_dma;
 	spinlock_t iommus_lock; /* lock for iommus list */
 	spinlock_t dt_lock; /* lock for modifying page directory table */
 
@@ -93,14 +94,12 @@ struct rk_iommu {
 	struct iommu_domain *domain; /* domain to which iommu is attached */
 };
 
-static inline void rk_table_flush(u32 *va, unsigned int count)
+static inline void rk_table_flush(struct rk_iommu_domain *dom, dma_addr_t dma,
+				  unsigned int count)
 {
-	phys_addr_t pa_start = virt_to_phys(va);
-	phys_addr_t pa_end = virt_to_phys(va + count);
-	size_t size = pa_end - pa_start;
+	size_t size = count * sizeof(u32); /* count of u32 entry */
 
-	__cpuc_flush_dcache_area(va, size);
-	outer_flush_range(pa_start, pa_end);
+	dma_sync_single_for_device(&dom->pdev->dev, dma, size, DMA_TO_DEVICE);
 }
 
 static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom)
@@ -183,10 +182,9 @@ static inline bool rk_dte_is_pt_valid(u32 dte)
 	return dte & RK_DTE_PT_VALID;
 }
 
-static u32 rk_mk_dte(u32 *pt)
+static inline u32 rk_mk_dte(dma_addr_t pt_dma)
 {
-	phys_addr_t pt_phys = virt_to_phys(pt);
-	return (pt_phys & RK_DTE_PT_ADDRESS_MASK) | RK_DTE_PT_VALID;
+	return (pt_dma & RK_DTE_PT_ADDRESS_MASK) | RK_DTE_PT_VALID;
 }
 
 /*
@@ -603,13 +601,16 @@ static void rk_iommu_zap_iova_first_last(struct rk_iommu_domain *rk_domain,
 static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
 				  dma_addr_t iova)
 {
+	struct device *dev = &rk_domain->pdev->dev;
 	u32 *page_table, *dte_addr;
-	u32 dte;
+	u32 dte_index, dte;
 	phys_addr_t pt_phys;
+	dma_addr_t pt_dma;
 
 	assert_spin_locked(&rk_domain->dt_lock);
 
-	dte_addr = &rk_domain->dt[rk_iova_dte_index(iova)];
+	dte_index = rk_iova_dte_index(iova);
+	dte_addr = &rk_domain->dt[dte_index];
 	dte = *dte_addr;
 	if (rk_dte_is_pt_valid(dte))
 		goto done;
@@ -618,19 +619,27 @@ static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
 	if (!page_table)
 		return ERR_PTR(-ENOMEM);
 
-	dte = rk_mk_dte(page_table);
-	*dte_addr = dte;
+	pt_dma = dma_map_single(dev, page_table, SPAGE_SIZE, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, pt_dma)) {
+		dev_err(dev, "DMA mapping error while allocating page table\n");
+		free_page((unsigned long)page_table);
+		return ERR_PTR(-ENOMEM);
+	}
 
-	rk_table_flush(page_table, NUM_PT_ENTRIES);
-	rk_table_flush(dte_addr, 1);
+	dte = rk_mk_dte(pt_dma);
+	*dte_addr = dte;
 
+	rk_table_flush(rk_domain, pt_dma, NUM_PT_ENTRIES);
+	rk_table_flush(rk_domain,
+		       rk_domain->dt_dma + dte_index * sizeof(u32), 1);
 done:
 	pt_phys = rk_dte_pt_address(dte);
 	return (u32 *)phys_to_virt(pt_phys);
 }
 
 static size_t rk_iommu_unmap_iova(struct rk_iommu_domain *rk_domain,
-				  u32 *pte_addr, dma_addr_t iova, size_t size)
+				  u32 *pte_addr, dma_addr_t pte_dma,
+				  size_t size)
 {
 	unsigned int pte_count;
 	unsigned int pte_total = size / SPAGE_SIZE;
@@ -645,14 +654,14 @@ static size_t rk_iommu_unmap_iova(struct rk_iommu_domain *rk_domain,
 		pte_addr[pte_count] = rk_mk_pte_invalid(pte);
 	}
 
-	rk_table_flush(pte_addr, pte_count);
+	rk_table_flush(rk_domain, pte_dma, pte_count);
 
 	return pte_count * SPAGE_SIZE;
 }
 
 static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr,
-			     dma_addr_t iova, phys_addr_t paddr, size_t size,
-			     int prot)
+			     dma_addr_t pte_dma, dma_addr_t iova,
+			     phys_addr_t paddr, size_t size, int prot)
 {
 	unsigned int pte_count;
 	unsigned int pte_total = size / SPAGE_SIZE;
@@ -671,7 +680,7 @@ static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr,
 		paddr += SPAGE_SIZE;
 	}
 
-	rk_table_flush(pte_addr, pte_count);
+	rk_table_flush(rk_domain, pte_dma, pte_total);
 
 	/*
 	 * Zap the first and last iova to evict from iotlb any previously
@@ -684,7 +693,8 @@ static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr,
 	return 0;
 unwind:
 	/* Unmap the range of iovas that we just mapped */
-	rk_iommu_unmap_iova(rk_domain, pte_addr, iova, pte_count * SPAGE_SIZE);
+	rk_iommu_unmap_iova(rk_domain, pte_addr, pte_dma,
+			    pte_count * SPAGE_SIZE);
 
 	iova += pte_count * SPAGE_SIZE;
 	page_phys = rk_pte_page_address(pte_addr[pte_count]);
@@ -699,8 +709,9 @@ static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
 {
 	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
-	dma_addr_t iova = (dma_addr_t)_iova;
+	dma_addr_t pte_dma, iova = (dma_addr_t)_iova;
 	u32 *page_table, *pte_addr;
+	u32 dte_index, pte_index;
 	int ret;
 
 	spin_lock_irqsave(&rk_domain->dt_lock, flags);
@@ -718,8 +729,13 @@ static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
 		return PTR_ERR(page_table);
 	}
 
-	pte_addr = &page_table[rk_iova_pte_index(iova)];
-	ret = rk_iommu_map_iova(rk_domain, pte_addr, iova, paddr, size, prot);
+	dte_index = rk_domain->dt[rk_iova_dte_index(iova)];
+	pte_index = rk_iova_pte_index(iova);
+	pte_addr = &page_table[pte_index];
+	pte_dma = rk_dte_pt_address(dte_index) + pte_index * sizeof(u32);
+	ret = rk_iommu_map_iova(rk_domain, pte_addr, pte_dma, iova,
+				paddr, size, prot);
+
 	spin_unlock_irqrestore(&rk_domain->dt_lock, flags);
 
 	return ret;
@@ -730,7 +746,7 @@ static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova,
 {
 	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
-	dma_addr_t iova = (dma_addr_t)_iova;
+	dma_addr_t pte_dma, iova = (dma_addr_t)_iova;
 	phys_addr_t pt_phys;
 	u32 dte;
 	u32 *pte_addr;
@@ -754,7 +770,8 @@ static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova,
 
 	pt_phys = rk_dte_pt_address(dte);
 	pte_addr = (u32 *)phys_to_virt(pt_phys) + rk_iova_pte_index(iova);
-	unmap_size = rk_iommu_unmap_iova(rk_domain, pte_addr, iova, size);
+	pte_dma = pt_phys + rk_iova_pte_index(iova) * sizeof(u32);
+	unmap_size = rk_iommu_unmap_iova(rk_domain, pte_addr, pte_dma, size);
 
 	spin_unlock_irqrestore(&rk_domain->dt_lock, flags);
 
@@ -787,7 +804,6 @@ static int rk_iommu_attach_device(struct iommu_domain *domain,
 	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
 	int ret, i;
-	phys_addr_t dte_addr;
 
 	/*
 	 * Allow 'virtual devices' (e.g., drm) to attach to domain.
@@ -807,14 +823,14 @@ static int rk_iommu_attach_device(struct iommu_domain *domain,
 
 	iommu->domain = domain;
 
-	ret = devm_request_irq(dev, iommu->irq, rk_iommu_irq,
+	ret = devm_request_irq(iommu->dev, iommu->irq, rk_iommu_irq,
 			       IRQF_SHARED, dev_name(dev), iommu);
 	if (ret)
 		return ret;
 
-	dte_addr = virt_to_phys(rk_domain->dt);
 	for (i = 0; i < iommu->num_mmu; i++) {
-		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, dte_addr);
+		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR,
+			       rk_domain->dt_dma);
 		rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
 		rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, RK_MMU_IRQ_MASK);
 	}
@@ -860,7 +876,7 @@ static void rk_iommu_detach_device(struct iommu_domain *domain,
 	}
 	rk_iommu_disable_stall(iommu);
 
-	devm_free_irq(dev, iommu->irq, iommu);
+	devm_free_irq(iommu->dev, iommu->irq, iommu);
 
 	iommu->domain = NULL;
 
@@ -870,14 +886,30 @@ static void rk_iommu_detach_device(struct iommu_domain *domain,
 static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
 {
 	struct rk_iommu_domain *rk_domain;
+	struct platform_device *pdev;
+	struct device *iommu_dev;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED)
+	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
 		return NULL;
 
-	rk_domain = kzalloc(sizeof(*rk_domain), GFP_KERNEL);
-	if (!rk_domain)
+	/* Register a pdev per domain, so DMA API can base on this *dev
+	 * even some virtual master doesn't have an iommu slave
+	 */
+	pdev = platform_device_register_simple("rk_iommu_domain",
+					       PLATFORM_DEVID_AUTO, NULL, 0);
+	if (IS_ERR(pdev))
 		return NULL;
 
+	rk_domain = devm_kzalloc(&pdev->dev, sizeof(*rk_domain), GFP_KERNEL);
+	if (!rk_domain)
+		goto err_unreg_pdev;
+
+	rk_domain->pdev = pdev;
+
+	if (type == IOMMU_DOMAIN_DMA &&
+	    iommu_get_dma_cookie(&rk_domain->domain))
+		goto err_unreg_pdev;
+
 	/*
 	 * rk32xx iommus use a 2 level pagetable.
 	 * Each level1 (dt) and level2 (pt) table has 1024 4-byte entries.
@@ -885,18 +917,36 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
 	 */
 	rk_domain->dt = (u32 *)get_zeroed_page(GFP_KERNEL | GFP_DMA32);
 	if (!rk_domain->dt)
-		goto err_dt;
+		goto err_put_cookie;
+
+	iommu_dev = &pdev->dev;
+	rk_domain->dt_dma = dma_map_single(iommu_dev, rk_domain->dt,
+					   SPAGE_SIZE, DMA_TO_DEVICE);
+	if (dma_mapping_error(iommu_dev, rk_domain->dt_dma)) {
+		dev_err(iommu_dev, "DMA map error for DT\n");
+		goto err_free_dt;
+	}
 
-	rk_table_flush(rk_domain->dt, NUM_DT_ENTRIES);
+	rk_table_flush(rk_domain, rk_domain->dt_dma, NUM_DT_ENTRIES);
 
 	spin_lock_init(&rk_domain->iommus_lock);
 	spin_lock_init(&rk_domain->dt_lock);
 	INIT_LIST_HEAD(&rk_domain->iommus);
 
+	rk_domain->domain.geometry.aperture_start = 0;
+	rk_domain->domain.geometry.aperture_end   = DMA_BIT_MASK(32);
+	rk_domain->domain.geometry.force_aperture = true;
+
 	return &rk_domain->domain;
 
-err_dt:
-	kfree(rk_domain);
+err_free_dt:
+	free_page((unsigned long)rk_domain->dt);
+err_put_cookie:
+	if (type == IOMMU_DOMAIN_DMA)
+		iommu_put_dma_cookie(&rk_domain->domain);
+err_unreg_pdev:
+	platform_device_unregister(pdev);
+
 	return NULL;
 }
 
@@ -912,12 +962,20 @@ static void rk_iommu_domain_free(struct iommu_domain *domain)
 		if (rk_dte_is_pt_valid(dte)) {
 			phys_addr_t pt_phys = rk_dte_pt_address(dte);
 			u32 *page_table = phys_to_virt(pt_phys);
+			dma_unmap_single(&rk_domain->pdev->dev, pt_phys,
+					 SPAGE_SIZE, DMA_TO_DEVICE);
 			free_page((unsigned long)page_table);
 		}
 	}
 
+	dma_unmap_single(&rk_domain->pdev->dev, rk_domain->dt_dma,
+			 SPAGE_SIZE, DMA_TO_DEVICE);
 	free_page((unsigned long)rk_domain->dt);
-	kfree(rk_domain);
+
+	if (domain->type == IOMMU_DOMAIN_DMA)
+		iommu_put_dma_cookie(&rk_domain->domain);
+
+	platform_device_unregister(rk_domain->pdev);
 }
 
 static bool rk_iommu_is_dev_iommu_master(struct device *dev)
@@ -1022,17 +1080,43 @@ static const struct iommu_ops rk_iommu_ops = {
 	.detach_dev = rk_iommu_detach_device,
 	.map = rk_iommu_map,
 	.unmap = rk_iommu_unmap,
+	.map_sg = default_iommu_map_sg,
 	.add_device = rk_iommu_add_device,
 	.remove_device = rk_iommu_remove_device,
 	.iova_to_phys = rk_iommu_iova_to_phys,
 	.pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP,
 };
 
+static int rk_iommu_domain_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+
+	dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), GFP_KERNEL);
+	if (!dev->dma_parms)
+		return -ENOMEM;
+
+	/* Set dma_ops for dev, otherwise it would be dummy_dma_ops */
+	arch_setup_dma_ops(dev, 0, DMA_BIT_MASK(32), NULL, false);
+
+	dma_set_max_seg_size(dev, DMA_BIT_MASK(32));
+	dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
+
+	return 0;
+}
+
+static struct platform_driver rk_iommu_domain_driver = {
+	.probe = rk_iommu_domain_probe,
+	.driver = {
+		   .name = "rk_iommu_domain",
+	},
+};
+
 static int rk_iommu_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct rk_iommu *iommu;
 	struct resource *res;
+	int num_res = pdev->num_resources;
 	int i;
 
 	iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
@@ -1042,12 +1126,13 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, iommu);
 	iommu->dev = dev;
 	iommu->num_mmu = 0;
-	iommu->bases = devm_kzalloc(dev, sizeof(*iommu->bases) * iommu->num_mmu,
+
+	iommu->bases = devm_kzalloc(dev, sizeof(*iommu->bases) * num_res,
 				    GFP_KERNEL);
 	if (!iommu->bases)
 		return -ENOMEM;
 
-	for (i = 0; i < pdev->num_resources; i++) {
+	for (i = 0; i < num_res; i++) {
 		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
 		if (!res)
 			continue;
@@ -1103,11 +1188,19 @@ static int __init rk_iommu_init(void)
 	if (ret)
 		return ret;
 
-	return platform_driver_register(&rk_iommu_driver);
+	ret = platform_driver_register(&rk_iommu_domain_driver);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&rk_iommu_driver);
+	if (ret)
+		platform_driver_unregister(&rk_iommu_domain_driver);
+	return ret;
 }
 static void __exit rk_iommu_exit(void)
 {
 	platform_driver_unregister(&rk_iommu_driver);
+	platform_driver_unregister(&rk_iommu_domain_driver);
 }
 
 subsys_initcall(rk_iommu_init);
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 5495a5ba8039..7f8728984f44 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -21,9 +21,9 @@ config ARM_GIC_MAX_NR
 
 config ARM_GIC_V2M
 	bool
-	depends on ARM_GIC
-	depends on PCI && PCI_MSI
-	select PCI_MSI_IRQ_DOMAIN
+	depends on PCI
+	select ARM_GIC
+	select PCI_MSI
 
 config GIC_NON_BANKED
 	bool
@@ -37,7 +37,8 @@ config ARM_GIC_V3
 
 config ARM_GIC_V3_ITS
 	bool
-	select PCI_MSI_IRQ_DOMAIN
+	depends on PCI
+	depends on PCI_MSI
 
 config ARM_NVIC
 	bool
@@ -62,13 +63,13 @@ config ARM_VIC_NR
 config ARMADA_370_XP_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
-	select PCI_MSI_IRQ_DOMAIN if PCI_MSI
+	select PCI_MSI if PCI
 
 config ALPINE_MSI
 	bool
-	depends on PCI && PCI_MSI
+	depends on PCI
+	select PCI_MSI
 	select GENERIC_IRQ_CHIP
-	select PCI_MSI_IRQ_DOMAIN
 
 config ATMEL_AIC_IRQ
 	bool
@@ -117,7 +118,6 @@ config HISILICON_IRQ_MBIGEN
 	bool
 	select ARM_GIC_V3
 	select ARM_GIC_V3_ITS
-	select GENERIC_MSI_IRQ_DOMAIN
 
 config IMGPDC_IRQ
 	bool
@@ -250,12 +250,10 @@ config IRQ_MXS
 
 config MVEBU_ODMI
 	bool
-	select GENERIC_MSI_IRQ_DOMAIN
 
 config LS_SCFG_MSI
 	def_bool y if SOC_LS1021A || ARCH_LAYERSCAPE
 	depends on PCI && PCI_MSI
-	select PCI_MSI_IRQ_DOMAIN
 
 config PARTITION_PERCPU
 	bool
diff --git a/drivers/irqchip/irq-clps711x.c b/drivers/irqchip/irq-clps711x.c
index 2223b3f15d68..f913f4db7ae1 100644
--- a/drivers/irqchip/irq-clps711x.c
+++ b/drivers/irqchip/irq-clps711x.c
@@ -234,5 +234,5 @@ static int __init clps711x_intc_init_dt(struct device_node *np,
 
 	return _clps711x_intc_init(np, res.start, resource_size(&res));
 }
-IRQCHIP_DECLARE(clps711x, "cirrus,clps711x-intc", clps711x_intc_init_dt);
+IRQCHIP_DECLARE(clps711x, "cirrus,ep7209-intc", clps711x_intc_init_dt);
 #endif
diff --git a/drivers/leds/leds-powernv.c b/drivers/leds/leds-powernv.c
index dfb8bd390125..b2a98c7b521b 100644
--- a/drivers/leds/leds-powernv.c
+++ b/drivers/leds/leds-powernv.c
@@ -118,7 +118,7 @@ static int powernv_led_set(struct powernv_led_data *powernv_led,
 		goto out_token;
 	}
 
-	rc = be64_to_cpu(msg.params[1]);
+	rc = opal_get_async_rc(msg);
 	if (rc != OPAL_SUCCESS)
 		dev_err(dev, "%s : OAPL async call returned failed [rc=%d]\n",
 			__func__, rc);
diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index d531f804455d..d6f72c826c1c 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -38,6 +38,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/slab.h>
+#include <linux/memblock.h>
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
@@ -99,6 +100,7 @@ static DEFINE_MUTEX(smu_mutex);
 static struct smu_device	*smu;
 static DEFINE_MUTEX(smu_part_access);
 static int smu_irq_inited;
+static unsigned long smu_cmdbuf_abs;
 
 static void smu_i2c_retry(unsigned long data);
 
@@ -479,8 +481,13 @@ int __init smu_init (void)
 
 	printk(KERN_INFO "SMU: Driver %s %s\n", VERSION, AUTHOR);
 
+	/*
+	 * SMU based G5s need some memory below 2Gb. Thankfully this is
+	 * called at a time where memblock is still available.
+	 */
+	smu_cmdbuf_abs = memblock_alloc_base(4096, 4096, 0x80000000UL);
 	if (smu_cmdbuf_abs == 0) {
-		printk(KERN_ERR "SMU: Command buffer not allocated !\n");
+		printk(KERN_ERR "SMU: Command buffer allocation failed !\n");
 		ret = -EINVAL;
 		goto fail_np;
 	}
diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index 5305923752d2..97c372908e78 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -123,4 +123,13 @@ config XGENE_SLIMPRO_MBOX
 	  It is used to send short messages between ARM64-bit cores and
 	  the SLIMpro Management Engine, primarily for PM. Say Y here if you
 	  want to use the APM X-Gene SLIMpro IPCM support.
+
+config BCM_PDC_MBOX
+	tristate "Broadcom PDC Mailbox"
+	depends on ARM64 || COMPILE_TEST
+	default ARCH_BCM_IPROC
+	help
+	  Mailbox implementation for the Broadcom PDC ring manager,
+	  which provides access to various offload engines on Broadcom
+	  SoCs. Say Y here if you want to use the Broadcom PDC.
 endif
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index 0be3e742bb7d..66c38e300dfc 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -25,3 +25,5 @@ obj-$(CONFIG_TI_MESSAGE_MANAGER) += ti-msgmgr.o
 obj-$(CONFIG_XGENE_SLIMPRO_MBOX) += mailbox-xgene-slimpro.o
 
 obj-$(CONFIG_HI6220_MBOX)	+= hi6220-mailbox.o
+
+obj-$(CONFIG_BCM_PDC_MBOX)	+= bcm-pdc-mailbox.o
diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c
new file mode 100644
index 000000000000..cbe0c1ee4ba9
--- /dev/null
+++ b/drivers/mailbox/bcm-pdc-mailbox.c
@@ -0,0 +1,1531 @@
+/*
+ * Copyright 2016 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation (the "GPL").
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License version 2 (GPLv2) for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 (GPLv2) along with this source code.
+ */
+
+/*
+ * Broadcom PDC Mailbox Driver
+ * The PDC provides a ring based programming interface to one or more hardware
+ * offload engines. For example, the PDC driver works with both SPU-M and SPU2
+ * cryptographic offload hardware. In some chips the PDC is referred to as MDE.
+ *
+ * The PDC driver registers with the Linux mailbox framework as a mailbox
+ * controller, once for each PDC instance. Ring 0 for each PDC is registered as
+ * a mailbox channel. The PDC driver uses interrupts to determine when data
+ * transfers to and from an offload engine are complete. The PDC driver uses
+ * threaded IRQs so that response messages are handled outside of interrupt
+ * context.
+ *
+ * The PDC driver allows multiple messages to be pending in the descriptor
+ * rings. The tx_msg_start descriptor index indicates where the last message
+ * starts. The txin_numd value at this index indicates how many descriptor
+ * indexes make up the message. Similar state is kept on the receive side. When
+ * an rx interrupt indicates a response is ready, the PDC driver processes numd
+ * descriptors from the tx and rx ring, thus processing one response at a time.
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/debugfs.h>
+#include <linux/interrupt.h>
+#include <linux/wait.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/mailbox_controller.h>
+#include <linux/mailbox/brcm-message.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-direction.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+
+#define PDC_SUCCESS  0
+
+#define RING_ENTRY_SIZE   sizeof(struct dma64dd)
+
+/* # entries in PDC dma ring */
+#define PDC_RING_ENTRIES  128
+#define PDC_RING_SIZE    (PDC_RING_ENTRIES * RING_ENTRY_SIZE)
+/* Rings are 8k aligned */
+#define RING_ALIGN_ORDER  13
+#define RING_ALIGN        BIT(RING_ALIGN_ORDER)
+
+#define RX_BUF_ALIGN_ORDER  5
+#define RX_BUF_ALIGN	    BIT(RX_BUF_ALIGN_ORDER)
+
+/* descriptor bumping macros */
+#define XXD(x, max_mask)              ((x) & (max_mask))
+#define TXD(x, max_mask)              XXD((x), (max_mask))
+#define RXD(x, max_mask)              XXD((x), (max_mask))
+#define NEXTTXD(i, max_mask)          TXD((i) + 1, (max_mask))
+#define PREVTXD(i, max_mask)          TXD((i) - 1, (max_mask))
+#define NEXTRXD(i, max_mask)          RXD((i) + 1, (max_mask))
+#define PREVRXD(i, max_mask)          RXD((i) - 1, (max_mask))
+#define NTXDACTIVE(h, t, max_mask)    TXD((t) - (h), (max_mask))
+#define NRXDACTIVE(h, t, max_mask)    RXD((t) - (h), (max_mask))
+
+/* Length of BCM header at start of SPU msg, in bytes */
+#define BCM_HDR_LEN  8
+
+/*
+ * PDC driver reserves ringset 0 on each SPU for its own use. The driver does
+ * not currently support use of multiple ringsets on a single PDC engine.
+ */
+#define PDC_RINGSET  0
+
+/*
+ * Interrupt mask and status definitions. Enable interrupts for tx and rx on
+ * ring 0
+ */
+#define PDC_XMTINT_0         (24 + PDC_RINGSET)
+#define PDC_RCVINT_0         (16 + PDC_RINGSET)
+#define PDC_XMTINTEN_0       BIT(PDC_XMTINT_0)
+#define PDC_RCVINTEN_0       BIT(PDC_RCVINT_0)
+#define PDC_INTMASK  (PDC_XMTINTEN_0 | PDC_RCVINTEN_0)
+#define PDC_LAZY_FRAMECOUNT  1
+#define PDC_LAZY_TIMEOUT     10000
+#define PDC_LAZY_INT  (PDC_LAZY_TIMEOUT | (PDC_LAZY_FRAMECOUNT << 24))
+#define PDC_INTMASK_OFFSET   0x24
+#define PDC_INTSTATUS_OFFSET 0x20
+#define PDC_RCVLAZY0_OFFSET  (0x30 + 4 * PDC_RINGSET)
+
+/*
+ * For SPU2, configure MDE_CKSUM_CONTROL to write 17 bytes of metadata
+ * before frame
+ */
+#define PDC_SPU2_RESP_HDR_LEN  17
+#define PDC_CKSUM_CTRL         BIT(27)
+#define PDC_CKSUM_CTRL_OFFSET  0x400
+
+#define PDC_SPUM_RESP_HDR_LEN  32
+
+/*
+ * Sets the following bits for write to transmit control reg:
+ *  0    - XmtEn - enable activity on the tx channel
+ * 11    - PtyChkDisable - parity check is disabled
+ * 20:18 - BurstLen = 3 -> 2^7 = 128 byte data reads from memory
+ */
+#define PDC_TX_CTL              0x000C0801
+
+/*
+ * Sets the following bits for write to receive control reg:
+ * 0     - RcvEn - enable activity on the rx channel
+ * 7:1   - RcvOffset - size in bytes of status region at start of rx frame buf
+ * 9     - SepRxHdrDescEn - place start of new frames only in descriptors
+ *                          that have StartOfFrame set
+ * 10    - OflowContinue - on rx FIFO overflow, clear rx fifo, discard all
+ *                         remaining bytes in current frame, report error
+ *                         in rx frame status for current frame
+ * 11    - PtyChkDisable - parity check is disabled
+ * 20:18 - BurstLen = 3 -> 2^7 = 128 byte data reads from memory
+ */
+#define PDC_RX_CTL              0x000C0E01
+
+#define CRYPTO_D64_RS0_CD_MASK   ((PDC_RING_ENTRIES * RING_ENTRY_SIZE) - 1)
+
+/* descriptor flags */
+#define D64_CTRL1_EOT   BIT(28)	/* end of descriptor table */
+#define D64_CTRL1_IOC   BIT(29)	/* interrupt on complete */
+#define D64_CTRL1_EOF   BIT(30)	/* end of frame */
+#define D64_CTRL1_SOF   BIT(31)	/* start of frame */
+
+#define RX_STATUS_OVERFLOW       0x00800000
+#define RX_STATUS_LEN            0x0000FFFF
+
+#define PDC_TXREGS_OFFSET  0x200
+#define PDC_RXREGS_OFFSET  0x220
+
+/* Maximum size buffer the DMA engine can handle */
+#define PDC_DMA_BUF_MAX 16384
+
+struct pdc_dma_map {
+	void *ctx;          /* opaque context associated with frame */
+};
+
+/* dma descriptor */
+struct dma64dd {
+	u32 ctrl1;      /* misc control bits */
+	u32 ctrl2;      /* buffer count and address extension */
+	u32 addrlow;    /* memory address of the date buffer, bits 31:0 */
+	u32 addrhigh;   /* memory address of the date buffer, bits 63:32 */
+};
+
+/* dma registers per channel(xmt or rcv) */
+struct dma64_regs {
+	u32  control;   /* enable, et al */
+	u32  ptr;       /* last descriptor posted to chip */
+	u32  addrlow;   /* descriptor ring base address low 32-bits */
+	u32  addrhigh;  /* descriptor ring base address bits 63:32 */
+	u32  status0;   /* last rx descriptor written by hw */
+	u32  status1;   /* driver does not use */
+};
+
+/* cpp contortions to concatenate w/arg prescan */
+#ifndef PAD
+#define _PADLINE(line)  pad ## line
+#define _XSTR(line)     _PADLINE(line)
+#define PAD             _XSTR(__LINE__)
+#endif  /* PAD */
+
+/* dma registers. matches hw layout. */
+struct dma64 {
+	struct dma64_regs dmaxmt;  /* dma tx */
+	u32          PAD[2];
+	struct dma64_regs dmarcv;  /* dma rx */
+	u32          PAD[2];
+};
+
+/* PDC registers */
+struct pdc_regs {
+	u32  devcontrol;             /* 0x000 */
+	u32  devstatus;              /* 0x004 */
+	u32  PAD;
+	u32  biststatus;             /* 0x00c */
+	u32  PAD[4];
+	u32  intstatus;              /* 0x020 */
+	u32  intmask;                /* 0x024 */
+	u32  gptimer;                /* 0x028 */
+
+	u32  PAD;
+	u32  intrcvlazy_0;           /* 0x030 */
+	u32  intrcvlazy_1;           /* 0x034 */
+	u32  intrcvlazy_2;           /* 0x038 */
+	u32  intrcvlazy_3;           /* 0x03c */
+
+	u32  PAD[48];
+	u32  removed_intrecvlazy;    /* 0x100 */
+	u32  flowctlthresh;          /* 0x104 */
+	u32  wrrthresh;              /* 0x108 */
+	u32  gmac_idle_cnt_thresh;   /* 0x10c */
+
+	u32  PAD[4];
+	u32  ifioaccessaddr;         /* 0x120 */
+	u32  ifioaccessbyte;         /* 0x124 */
+	u32  ifioaccessdata;         /* 0x128 */
+
+	u32  PAD[21];
+	u32  phyaccess;              /* 0x180 */
+	u32  PAD;
+	u32  phycontrol;             /* 0x188 */
+	u32  txqctl;                 /* 0x18c */
+	u32  rxqctl;                 /* 0x190 */
+	u32  gpioselect;             /* 0x194 */
+	u32  gpio_output_en;         /* 0x198 */
+	u32  PAD;                    /* 0x19c */
+	u32  txq_rxq_mem_ctl;        /* 0x1a0 */
+	u32  memory_ecc_status;      /* 0x1a4 */
+	u32  serdes_ctl;             /* 0x1a8 */
+	u32  serdes_status0;         /* 0x1ac */
+	u32  serdes_status1;         /* 0x1b0 */
+	u32  PAD[11];                /* 0x1b4-1dc */
+	u32  clk_ctl_st;             /* 0x1e0 */
+	u32  hw_war;                 /* 0x1e4 */
+	u32  pwrctl;                 /* 0x1e8 */
+	u32  PAD[5];
+
+#define PDC_NUM_DMA_RINGS   4
+	struct dma64 dmaregs[PDC_NUM_DMA_RINGS];  /* 0x0200 - 0x2fc */
+
+	/* more registers follow, but we don't use them */
+};
+
+/* structure for allocating/freeing DMA rings */
+struct pdc_ring_alloc {
+	dma_addr_t  dmabase; /* DMA address of start of ring */
+	void	   *vbase;   /* base kernel virtual address of ring */
+	u32	    size;    /* ring allocation size in bytes */
+};
+
+/* PDC state structure */
+struct pdc_state {
+	/* synchronize access to this PDC state structure */
+	spinlock_t pdc_lock;
+
+	/* Index of the PDC whose state is in this structure instance */
+	u8 pdc_idx;
+
+	/* Platform device for this PDC instance */
+	struct platform_device *pdev;
+
+	/*
+	 * Each PDC instance has a mailbox controller. PDC receives request
+	 * messages through mailboxes, and sends response messages through the
+	 * mailbox framework.
+	 */
+	struct mbox_controller mbc;
+
+	unsigned int pdc_irq;
+
+	/*
+	 * Last interrupt status read from PDC device. Saved in interrupt
+	 * handler so the handler can clear the interrupt in the device,
+	 * and the interrupt thread called later can know which interrupt
+	 * bits are active.
+	 */
+	unsigned long intstatus;
+
+	/* Number of bytes of receive status prior to each rx frame */
+	u32 rx_status_len;
+	/* Whether a BCM header is prepended to each frame */
+	bool use_bcm_hdr;
+	/* Sum of length of BCM header and rx status header */
+	u32 pdc_resp_hdr_len;
+
+	/* The base virtual address of DMA hw registers */
+	void __iomem *pdc_reg_vbase;
+
+	/* Pool for allocation of DMA rings */
+	struct dma_pool *ring_pool;
+
+	/* Pool for allocation of metadata buffers for response messages */
+	struct dma_pool *rx_buf_pool;
+
+	/*
+	 * The base virtual address of DMA tx/rx descriptor rings. Corresponding
+	 * DMA address and size of ring allocation.
+	 */
+	struct pdc_ring_alloc tx_ring_alloc;
+	struct pdc_ring_alloc rx_ring_alloc;
+
+	struct pdc_regs *regs;    /* start of PDC registers */
+
+	struct dma64_regs *txregs_64; /* dma tx engine registers */
+	struct dma64_regs *rxregs_64; /* dma rx engine registers */
+
+	/*
+	 * Arrays of PDC_RING_ENTRIES descriptors
+	 * To use multiple ringsets, this needs to be extended
+	 */
+	struct dma64dd   *txd_64;  /* tx descriptor ring */
+	struct dma64dd   *rxd_64;  /* rx descriptor ring */
+
+	/* descriptor ring sizes */
+	u32      ntxd;       /* # tx descriptors */
+	u32      nrxd;       /* # rx descriptors */
+	u32      nrxpost;    /* # rx buffers to keep posted */
+	u32      ntxpost;    /* max number of tx buffers that can be posted */
+
+	/*
+	 * Index of next tx descriptor to reclaim. That is, the descriptor
+	 * index of the oldest tx buffer for which the host has yet to process
+	 * the corresponding response.
+	 */
+	u32  txin;
+
+	/*
+	 * Index of the first receive descriptor for the sequence of
+	 * message fragments currently under construction. Used to build up
+	 * the rxin_numd count for a message. Updated to rxout when the host
+	 * starts a new sequence of rx buffers for a new message.
+	 */
+	u32  tx_msg_start;
+
+	/* Index of next tx descriptor to post. */
+	u32  txout;
+
+	/*
+	 * Number of tx descriptors associated with the message that starts
+	 * at this tx descriptor index.
+	 */
+	u32      txin_numd[PDC_RING_ENTRIES];
+
+	/*
+	 * Index of next rx descriptor to reclaim. This is the index of
+	 * the next descriptor whose data has yet to be processed by the host.
+	 */
+	u32  rxin;
+
+	/*
+	 * Index of the first receive descriptor for the sequence of
+	 * message fragments currently under construction. Used to build up
+	 * the rxin_numd count for a message. Updated to rxout when the host
+	 * starts a new sequence of rx buffers for a new message.
+	 */
+	u32  rx_msg_start;
+
+	/*
+	 * Saved value of current hardware rx descriptor index.
+	 * The last rx buffer written by the hw is the index previous to
+	 * this one.
+	 */
+	u32  last_rx_curr;
+
+	/* Index of next rx descriptor to post. */
+	u32  rxout;
+
+	/*
+	 * opaque context associated with frame that starts at each
+	 * rx ring index.
+	 */
+	void *rxp_ctx[PDC_RING_ENTRIES];
+
+	/*
+	 * Scatterlists used to form request and reply frames beginning at a
+	 * given ring index. Retained in order to unmap each sg after reply
+	 * is processed
+	 */
+	struct scatterlist *src_sg[PDC_RING_ENTRIES];
+	struct scatterlist *dst_sg[PDC_RING_ENTRIES];
+
+	/*
+	 * Number of rx descriptors associated with the message that starts
+	 * at this descriptor index. Not set for every index. For example,
+	 * if descriptor index i points to a scatterlist with 4 entries, then
+	 * the next three descriptor indexes don't have a value set.
+	 */
+	u32  rxin_numd[PDC_RING_ENTRIES];
+
+	void *resp_hdr[PDC_RING_ENTRIES];
+	dma_addr_t resp_hdr_daddr[PDC_RING_ENTRIES];
+
+	struct dentry *debugfs_stats;  /* debug FS stats file for this PDC */
+
+	/* counters */
+	u32  pdc_requests;    /* number of request messages submitted */
+	u32  pdc_replies;     /* number of reply messages received */
+	u32  txnobuf;         /* count of tx ring full */
+	u32  rxnobuf;         /* count of rx ring full */
+	u32  rx_oflow;        /* count of rx overflows */
+};
+
+/* Global variables */
+
+struct pdc_globals {
+	/* Actual number of SPUs in hardware, as reported by device tree */
+	u32 num_spu;
+};
+
+static struct pdc_globals pdcg;
+
+/* top level debug FS directory for PDC driver */
+static struct dentry *debugfs_dir;
+
+static ssize_t pdc_debugfs_read(struct file *filp, char __user *ubuf,
+				size_t count, loff_t *offp)
+{
+	struct pdc_state *pdcs;
+	char *buf;
+	ssize_t ret, out_offset, out_count;
+
+	out_count = 512;
+
+	buf = kmalloc(out_count, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	pdcs = filp->private_data;
+	out_offset = 0;
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "SPU %u stats:\n", pdcs->pdc_idx);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "PDC requests............%u\n",
+			       pdcs->pdc_requests);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "PDC responses...........%u\n",
+			       pdcs->pdc_replies);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "Tx err ring full........%u\n",
+			       pdcs->txnobuf);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "Rx err ring full........%u\n",
+			       pdcs->rxnobuf);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "Receive overflow........%u\n",
+			       pdcs->rx_oflow);
+
+	if (out_offset > out_count)
+		out_offset = out_count;
+
+	ret = simple_read_from_buffer(ubuf, count, offp, buf, out_offset);
+	kfree(buf);
+	return ret;
+}
+
+static const struct file_operations pdc_debugfs_stats = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = pdc_debugfs_read,
+};
+
+/**
+ * pdc_setup_debugfs() - Create the debug FS directories. If the top-level
+ * directory has not yet been created, create it now. Create a stats file in
+ * this directory for a SPU.
+ * @pdcs: PDC state structure
+ */
+void pdc_setup_debugfs(struct pdc_state *pdcs)
+{
+	char spu_stats_name[16];
+
+	if (!debugfs_initialized())
+		return;
+
+	snprintf(spu_stats_name, 16, "pdc%d_stats", pdcs->pdc_idx);
+	if (!debugfs_dir)
+		debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
+
+	pdcs->debugfs_stats = debugfs_create_file(spu_stats_name, S_IRUSR,
+						  debugfs_dir, pdcs,
+						  &pdc_debugfs_stats);
+}
+
+void pdc_free_debugfs(void)
+{
+	if (debugfs_dir && simple_empty(debugfs_dir)) {
+		debugfs_remove_recursive(debugfs_dir);
+		debugfs_dir = NULL;
+	}
+}
+
+/**
+ * pdc_build_rxd() - Build DMA descriptor to receive SPU result.
+ * @pdcs:      PDC state for SPU that will generate result
+ * @dma_addr:  DMA address of buffer that descriptor is being built for
+ * @buf_len:   Length of the receive buffer, in bytes
+ * @flags:     Flags to be stored in descriptor
+ */
+static inline void
+pdc_build_rxd(struct pdc_state *pdcs, dma_addr_t dma_addr,
+	      u32 buf_len, u32 flags)
+{
+	struct device *dev = &pdcs->pdev->dev;
+
+	dev_dbg(dev,
+		"Writing rx descriptor for PDC %u at index %u with length %u. flags %#x\n",
+		pdcs->pdc_idx, pdcs->rxout, buf_len, flags);
+
+	iowrite32(lower_32_bits(dma_addr),
+		  (void *)&pdcs->rxd_64[pdcs->rxout].addrlow);
+	iowrite32(upper_32_bits(dma_addr),
+		  (void *)&pdcs->rxd_64[pdcs->rxout].addrhigh);
+	iowrite32(flags, (void *)&pdcs->rxd_64[pdcs->rxout].ctrl1);
+	iowrite32(buf_len, (void *)&pdcs->rxd_64[pdcs->rxout].ctrl2);
+	/* bump ring index and return */
+	pdcs->rxout = NEXTRXD(pdcs->rxout, pdcs->nrxpost);
+}
+
+/**
+ * pdc_build_txd() - Build a DMA descriptor to transmit a SPU request to
+ * hardware.
+ * @pdcs:        PDC state for the SPU that will process this request
+ * @dma_addr:    DMA address of packet to be transmitted
+ * @buf_len:     Length of tx buffer, in bytes
+ * @flags:       Flags to be stored in descriptor
+ */
+static inline void
+pdc_build_txd(struct pdc_state *pdcs, dma_addr_t dma_addr, u32 buf_len,
+	      u32 flags)
+{
+	struct device *dev = &pdcs->pdev->dev;
+
+	dev_dbg(dev,
+		"Writing tx descriptor for PDC %u at index %u with length %u, flags %#x\n",
+		pdcs->pdc_idx, pdcs->txout, buf_len, flags);
+
+	iowrite32(lower_32_bits(dma_addr),
+		  (void *)&pdcs->txd_64[pdcs->txout].addrlow);
+	iowrite32(upper_32_bits(dma_addr),
+		  (void *)&pdcs->txd_64[pdcs->txout].addrhigh);
+	iowrite32(flags, (void *)&pdcs->txd_64[pdcs->txout].ctrl1);
+	iowrite32(buf_len, (void *)&pdcs->txd_64[pdcs->txout].ctrl2);
+
+	/* bump ring index and return */
+	pdcs->txout = NEXTTXD(pdcs->txout, pdcs->ntxpost);
+}
+
+/**
+ * pdc_receive() - Receive a response message from a given SPU.
+ * @pdcs:    PDC state for the SPU to receive from
+ * @mssg:    mailbox message to be returned to client
+ *
+ * When the return code indicates success, the response message is available in
+ * the receive buffers provided prior to submission of the request.
+ *
+ * Input:
+ *   pdcs - PDC state structure for the SPU to be polled
+ *   mssg - mailbox message to be returned to client. This function sets the
+ *	    context pointer on the message to help the client associate the
+ *	    response with a request.
+ *
+ * Return:  PDC_SUCCESS if one or more receive descriptors was processed
+ *          -EAGAIN indicates that no response message is available
+ *          -EIO an error occurred
+ */
+static int
+pdc_receive(struct pdc_state *pdcs, struct brcm_message *mssg)
+{
+	struct device *dev = &pdcs->pdev->dev;
+	u32 len, rx_status;
+	u32 num_frags;
+	int i;
+	u8 *resp_hdr;    /* virtual addr of start of resp message DMA header */
+	u32 frags_rdy;   /* number of fragments ready to read */
+	u32 rx_idx;      /* ring index of start of receive frame */
+	dma_addr_t resp_hdr_daddr;
+
+	spin_lock(&pdcs->pdc_lock);
+
+	/*
+	 * return if a complete response message is not yet ready.
+	 * rxin_numd[rxin] is the number of fragments in the next msg
+	 * to read.
+	 */
+	frags_rdy = NRXDACTIVE(pdcs->rxin, pdcs->last_rx_curr, pdcs->nrxpost);
+	if ((frags_rdy == 0) || (frags_rdy < pdcs->rxin_numd[pdcs->rxin])) {
+		/* See if the hw has written more fragments than we know */
+		pdcs->last_rx_curr =
+		    (ioread32((void *)&pdcs->rxregs_64->status0) &
+		     CRYPTO_D64_RS0_CD_MASK) / RING_ENTRY_SIZE;
+		frags_rdy = NRXDACTIVE(pdcs->rxin, pdcs->last_rx_curr,
+				       pdcs->nrxpost);
+		if ((frags_rdy == 0) ||
+		    (frags_rdy < pdcs->rxin_numd[pdcs->rxin])) {
+			/* No response ready */
+			spin_unlock(&pdcs->pdc_lock);
+			return -EAGAIN;
+		}
+		/* can't read descriptors/data until write index is read */
+		rmb();
+	}
+
+	num_frags = pdcs->txin_numd[pdcs->txin];
+	dma_unmap_sg(dev, pdcs->src_sg[pdcs->txin],
+		     sg_nents(pdcs->src_sg[pdcs->txin]), DMA_TO_DEVICE);
+
+	for (i = 0; i < num_frags; i++)
+		pdcs->txin = NEXTTXD(pdcs->txin, pdcs->ntxpost);
+
+	dev_dbg(dev, "PDC %u reclaimed %d tx descriptors",
+		pdcs->pdc_idx, num_frags);
+
+	rx_idx = pdcs->rxin;
+	num_frags = pdcs->rxin_numd[rx_idx];
+	/* Return opaque context with result */
+	mssg->ctx = pdcs->rxp_ctx[rx_idx];
+	pdcs->rxp_ctx[rx_idx] = NULL;
+	resp_hdr = pdcs->resp_hdr[rx_idx];
+	resp_hdr_daddr = pdcs->resp_hdr_daddr[rx_idx];
+	dma_unmap_sg(dev, pdcs->dst_sg[rx_idx],
+		     sg_nents(pdcs->dst_sg[rx_idx]), DMA_FROM_DEVICE);
+
+	for (i = 0; i < num_frags; i++)
+		pdcs->rxin = NEXTRXD(pdcs->rxin, pdcs->nrxpost);
+
+	spin_unlock(&pdcs->pdc_lock);
+
+	dev_dbg(dev, "PDC %u reclaimed %d rx descriptors",
+		pdcs->pdc_idx, num_frags);
+
+	dev_dbg(dev,
+		"PDC %u txin %u, txout %u, rxin %u, rxout %u, last_rx_curr %u\n",
+		pdcs->pdc_idx, pdcs->txin, pdcs->txout, pdcs->rxin,
+		pdcs->rxout, pdcs->last_rx_curr);
+
+	if (pdcs->pdc_resp_hdr_len == PDC_SPUM_RESP_HDR_LEN) {
+		/*
+		 * For SPU-M, get length of response msg and rx overflow status.
+		 */
+		rx_status = *((u32 *)resp_hdr);
+		len = rx_status & RX_STATUS_LEN;
+		dev_dbg(dev,
+			"SPU response length %u bytes", len);
+		if (unlikely(((rx_status & RX_STATUS_OVERFLOW) || (!len)))) {
+			if (rx_status & RX_STATUS_OVERFLOW) {
+				dev_err_ratelimited(dev,
+						    "crypto receive overflow");
+				pdcs->rx_oflow++;
+			} else {
+				dev_info_ratelimited(dev, "crypto rx len = 0");
+			}
+			return -EIO;
+		}
+	}
+
+	dma_pool_free(pdcs->rx_buf_pool, resp_hdr, resp_hdr_daddr);
+
+	pdcs->pdc_replies++;
+	/* if we read one or more rx descriptors, claim success */
+	if (num_frags > 0)
+		return PDC_SUCCESS;
+	else
+		return -EIO;
+}
+
+/**
+ * pdc_tx_list_sg_add() - Add the buffers in a scatterlist to the transmit
+ * descriptors for a given SPU. The scatterlist buffers contain the data for a
+ * SPU request message.
+ * @spu_idx:   The index of the SPU to submit the request to, [0, max_spu)
+ * @sg:        Scatterlist whose buffers contain part of the SPU request
+ *
+ * If a scatterlist buffer is larger than PDC_DMA_BUF_MAX, multiple descriptors
+ * are written for that buffer, each <= PDC_DMA_BUF_MAX byte in length.
+ *
+ * Return: PDC_SUCCESS if successful
+ *         < 0 otherwise
+ */
+static int pdc_tx_list_sg_add(struct pdc_state *pdcs, struct scatterlist *sg)
+{
+	u32 flags = 0;
+	u32 eot;
+	u32 tx_avail;
+
+	/*
+	 * Num descriptors needed. Conservatively assume we need a descriptor
+	 * for every entry in sg.
+	 */
+	u32 num_desc;
+	u32 desc_w = 0;	/* Number of tx descriptors written */
+	u32 bufcnt;	/* Number of bytes of buffer pointed to by descriptor */
+	dma_addr_t databufptr;	/* DMA address to put in descriptor */
+
+	num_desc = (u32)sg_nents(sg);
+
+	/* check whether enough tx descriptors are available */
+	tx_avail = pdcs->ntxpost - NTXDACTIVE(pdcs->txin, pdcs->txout,
+					      pdcs->ntxpost);
+	if (unlikely(num_desc > tx_avail)) {
+		pdcs->txnobuf++;
+		return -ENOSPC;
+	}
+
+	/* build tx descriptors */
+	if (pdcs->tx_msg_start == pdcs->txout) {
+		/* Start of frame */
+		pdcs->txin_numd[pdcs->tx_msg_start] = 0;
+		pdcs->src_sg[pdcs->txout] = sg;
+		flags = D64_CTRL1_SOF;
+	}
+
+	while (sg) {
+		if (unlikely(pdcs->txout == (pdcs->ntxd - 1)))
+			eot = D64_CTRL1_EOT;
+		else
+			eot = 0;
+
+		/*
+		 * If sg buffer larger than PDC limit, split across
+		 * multiple descriptors
+		 */
+		bufcnt = sg_dma_len(sg);
+		databufptr = sg_dma_address(sg);
+		while (bufcnt > PDC_DMA_BUF_MAX) {
+			pdc_build_txd(pdcs, databufptr, PDC_DMA_BUF_MAX,
+				      flags | eot);
+			desc_w++;
+			bufcnt -= PDC_DMA_BUF_MAX;
+			databufptr += PDC_DMA_BUF_MAX;
+			if (unlikely(pdcs->txout == (pdcs->ntxd - 1)))
+				eot = D64_CTRL1_EOT;
+			else
+				eot = 0;
+		}
+		sg = sg_next(sg);
+		if (!sg)
+			/* Writing last descriptor for frame */
+			flags |= (D64_CTRL1_EOF | D64_CTRL1_IOC);
+		pdc_build_txd(pdcs, databufptr, bufcnt, flags | eot);
+		desc_w++;
+		/* Clear start of frame after first descriptor */
+		flags &= ~D64_CTRL1_SOF;
+	}
+	pdcs->txin_numd[pdcs->tx_msg_start] += desc_w;
+
+	return PDC_SUCCESS;
+}
+
+/**
+ * pdc_tx_list_final() - Initiate DMA transfer of last frame written to tx
+ * ring.
+ * @pdcs:  PDC state for SPU to process the request
+ *
+ * Sets the index of the last descriptor written in both the rx and tx ring.
+ *
+ * Return: PDC_SUCCESS
+ */
+static int pdc_tx_list_final(struct pdc_state *pdcs)
+{
+	/*
+	 * write barrier to ensure all register writes are complete
+	 * before chip starts to process new request
+	 */
+	wmb();
+	iowrite32(pdcs->rxout << 4, (void *)&pdcs->rxregs_64->ptr);
+	iowrite32(pdcs->txout << 4, (void *)&pdcs->txregs_64->ptr);
+	pdcs->pdc_requests++;
+
+	return PDC_SUCCESS;
+}
+
+/**
+ * pdc_rx_list_init() - Start a new receive descriptor list for a given PDC.
+ * @pdcs:   PDC state for SPU handling request
+ * @dst_sg: scatterlist providing rx buffers for response to be returned to
+ *	    mailbox client
+ * @ctx:    Opaque context for this request
+ *
+ * Posts a single receive descriptor to hold the metadata that precedes a
+ * response. For example, with SPU-M, the metadata is a 32-byte DMA header and
+ * an 8-byte BCM header. Moves the msg_start descriptor indexes for both tx and
+ * rx to indicate the start of a new message.
+ *
+ * Return:  PDC_SUCCESS if successful
+ *          < 0 if an error (e.g., rx ring is full)
+ */
+static int pdc_rx_list_init(struct pdc_state *pdcs, struct scatterlist *dst_sg,
+			    void *ctx)
+{
+	u32 flags = 0;
+	u32 rx_avail;
+	u32 rx_pkt_cnt = 1;	/* Adding a single rx buffer */
+	dma_addr_t daddr;
+	void *vaddr;
+
+	rx_avail = pdcs->nrxpost - NRXDACTIVE(pdcs->rxin, pdcs->rxout,
+					      pdcs->nrxpost);
+	if (unlikely(rx_pkt_cnt > rx_avail)) {
+		pdcs->rxnobuf++;
+		return -ENOSPC;
+	}
+
+	/* allocate a buffer for the dma rx status */
+	vaddr = dma_pool_zalloc(pdcs->rx_buf_pool, GFP_ATOMIC, &daddr);
+	if (!vaddr)
+		return -ENOMEM;
+
+	/*
+	 * Update msg_start indexes for both tx and rx to indicate the start
+	 * of a new sequence of descriptor indexes that contain the fragments
+	 * of the same message.
+	 */
+	pdcs->rx_msg_start = pdcs->rxout;
+	pdcs->tx_msg_start = pdcs->txout;
+
+	/* This is always the first descriptor in the receive sequence */
+	flags = D64_CTRL1_SOF;
+	pdcs->rxin_numd[pdcs->rx_msg_start] = 1;
+
+	if (unlikely(pdcs->rxout == (pdcs->nrxd - 1)))
+		flags |= D64_CTRL1_EOT;
+
+	pdcs->rxp_ctx[pdcs->rxout] = ctx;
+	pdcs->dst_sg[pdcs->rxout] = dst_sg;
+	pdcs->resp_hdr[pdcs->rxout] = vaddr;
+	pdcs->resp_hdr_daddr[pdcs->rxout] = daddr;
+	pdc_build_rxd(pdcs, daddr, pdcs->pdc_resp_hdr_len, flags);
+	return PDC_SUCCESS;
+}
+
+/**
+ * pdc_rx_list_sg_add() - Add the buffers in a scatterlist to the receive
+ * descriptors for a given SPU. The caller must have already DMA mapped the
+ * scatterlist.
+ * @spu_idx:    Indicates which SPU the buffers are for
+ * @sg:         Scatterlist whose buffers are added to the receive ring
+ *
+ * If a receive buffer in the scatterlist is larger than PDC_DMA_BUF_MAX,
+ * multiple receive descriptors are written, each with a buffer <=
+ * PDC_DMA_BUF_MAX.
+ *
+ * Return: PDC_SUCCESS if successful
+ *         < 0 otherwise (e.g., receive ring is full)
+ */
+static int pdc_rx_list_sg_add(struct pdc_state *pdcs, struct scatterlist *sg)
+{
+	u32 flags = 0;
+	u32 rx_avail;
+
+	/*
+	 * Num descriptors needed. Conservatively assume we need a descriptor
+	 * for every entry from our starting point in the scatterlist.
+	 */
+	u32 num_desc;
+	u32 desc_w = 0;	/* Number of tx descriptors written */
+	u32 bufcnt;	/* Number of bytes of buffer pointed to by descriptor */
+	dma_addr_t databufptr;	/* DMA address to put in descriptor */
+
+	num_desc = (u32)sg_nents(sg);
+
+	rx_avail = pdcs->nrxpost - NRXDACTIVE(pdcs->rxin, pdcs->rxout,
+					      pdcs->nrxpost);
+	if (unlikely(num_desc > rx_avail)) {
+		pdcs->rxnobuf++;
+		return -ENOSPC;
+	}
+
+	while (sg) {
+		if (unlikely(pdcs->rxout == (pdcs->nrxd - 1)))
+			flags = D64_CTRL1_EOT;
+		else
+			flags = 0;
+
+		/*
+		 * If sg buffer larger than PDC limit, split across
+		 * multiple descriptors
+		 */
+		bufcnt = sg_dma_len(sg);
+		databufptr = sg_dma_address(sg);
+		while (bufcnt > PDC_DMA_BUF_MAX) {
+			pdc_build_rxd(pdcs, databufptr, PDC_DMA_BUF_MAX, flags);
+			desc_w++;
+			bufcnt -= PDC_DMA_BUF_MAX;
+			databufptr += PDC_DMA_BUF_MAX;
+			if (unlikely(pdcs->rxout == (pdcs->nrxd - 1)))
+				flags = D64_CTRL1_EOT;
+			else
+				flags = 0;
+		}
+		pdc_build_rxd(pdcs, databufptr, bufcnt, flags);
+		desc_w++;
+		sg = sg_next(sg);
+	}
+	pdcs->rxin_numd[pdcs->rx_msg_start] += desc_w;
+
+	return PDC_SUCCESS;
+}
+
+/**
+ * pdc_irq_handler() - Interrupt handler called in interrupt context.
+ * @irq:      Interrupt number that has fired
+ * @cookie:   PDC state for DMA engine that generated the interrupt
+ *
+ * We have to clear the device interrupt status flags here. So cache the
+ * status for later use in the thread function. Other than that, just return
+ * WAKE_THREAD to invoke the thread function.
+ *
+ * Return: IRQ_WAKE_THREAD if interrupt is ours
+ *         IRQ_NONE otherwise
+ */
+static irqreturn_t pdc_irq_handler(int irq, void *cookie)
+{
+	struct pdc_state *pdcs = cookie;
+	u32 intstatus = ioread32(pdcs->pdc_reg_vbase + PDC_INTSTATUS_OFFSET);
+
+	if (intstatus & PDC_XMTINTEN_0)
+		set_bit(PDC_XMTINT_0, &pdcs->intstatus);
+	if (intstatus & PDC_RCVINTEN_0)
+		set_bit(PDC_RCVINT_0, &pdcs->intstatus);
+
+	/* Clear interrupt flags in device */
+	iowrite32(intstatus, pdcs->pdc_reg_vbase + PDC_INTSTATUS_OFFSET);
+
+	/* Wakeup IRQ thread */
+	if (pdcs && (irq == pdcs->pdc_irq) && (intstatus & PDC_INTMASK))
+		return IRQ_WAKE_THREAD;
+
+	return IRQ_NONE;
+}
+
+/**
+ * pdc_irq_thread() - Function invoked on deferred thread when a DMA tx has
+ * completed or data is available to receive.
+ * @irq:    Interrupt number
+ * @cookie: PDC state for PDC that generated the interrupt
+ *
+ * On DMA tx complete, notify the mailbox client. On DMA rx complete, process
+ * as many SPU response messages as are available and send each to the mailbox
+ * client.
+ *
+ * Return: IRQ_HANDLED if we recognized and handled the interrupt
+ *         IRQ_NONE otherwise
+ */
+static irqreturn_t pdc_irq_thread(int irq, void *cookie)
+{
+	struct pdc_state *pdcs = cookie;
+	struct mbox_controller *mbc;
+	struct mbox_chan *chan;
+	bool tx_int;
+	bool rx_int;
+	int rx_status;
+	struct brcm_message mssg;
+
+	tx_int = test_and_clear_bit(PDC_XMTINT_0, &pdcs->intstatus);
+	rx_int = test_and_clear_bit(PDC_RCVINT_0, &pdcs->intstatus);
+
+	if (pdcs && (tx_int || rx_int)) {
+		dev_dbg(&pdcs->pdev->dev,
+			"%s() got irq %d with tx_int %s, rx_int %s",
+			__func__, irq,
+			tx_int ? "set" : "clear", rx_int ? "set" : "clear");
+
+		mbc = &pdcs->mbc;
+		chan = &mbc->chans[0];
+
+		if (tx_int) {
+			dev_dbg(&pdcs->pdev->dev, "%s(): tx done", __func__);
+			/* only one frame in flight at a time */
+			mbox_chan_txdone(chan, PDC_SUCCESS);
+		}
+		if (rx_int) {
+			while (1) {
+				/* Could be many frames ready */
+				memset(&mssg, 0, sizeof(mssg));
+				mssg.type = BRCM_MESSAGE_SPU;
+				rx_status = pdc_receive(pdcs, &mssg);
+				if (rx_status >= 0) {
+					dev_dbg(&pdcs->pdev->dev,
+						"%s(): invoking client rx cb",
+						__func__);
+					mbox_chan_received_data(chan, &mssg);
+				} else {
+					dev_dbg(&pdcs->pdev->dev,
+						"%s(): no SPU response available",
+						__func__);
+					break;
+				}
+			}
+		}
+		return IRQ_HANDLED;
+	}
+	return IRQ_NONE;
+}
+
+/**
+ * pdc_ring_init() - Allocate DMA rings and initialize constant fields of
+ * descriptors in one ringset.
+ * @pdcs:    PDC instance state
+ * @ringset: index of ringset being used
+ *
+ * Return: PDC_SUCCESS if ring initialized
+ *         < 0 otherwise
+ */
+static int pdc_ring_init(struct pdc_state *pdcs, int ringset)
+{
+	int i;
+	int err = PDC_SUCCESS;
+	struct dma64 *dma_reg;
+	struct device *dev = &pdcs->pdev->dev;
+	struct pdc_ring_alloc tx;
+	struct pdc_ring_alloc rx;
+
+	/* Allocate tx ring */
+	tx.vbase = dma_pool_zalloc(pdcs->ring_pool, GFP_KERNEL, &tx.dmabase);
+	if (!tx.vbase) {
+		err = -ENOMEM;
+		goto done;
+	}
+
+	/* Allocate rx ring */
+	rx.vbase = dma_pool_zalloc(pdcs->ring_pool, GFP_KERNEL, &rx.dmabase);
+	if (!rx.vbase) {
+		err = -ENOMEM;
+		goto fail_dealloc;
+	}
+
+	dev_dbg(dev, " - base DMA addr of tx ring      %pad", &tx.dmabase);
+	dev_dbg(dev, " - base virtual addr of tx ring  %p", tx.vbase);
+	dev_dbg(dev, " - base DMA addr of rx ring      %pad", &rx.dmabase);
+	dev_dbg(dev, " - base virtual addr of rx ring  %p", rx.vbase);
+
+	/* lock after ring allocation to avoid scheduling while atomic */
+	spin_lock(&pdcs->pdc_lock);
+
+	memcpy(&pdcs->tx_ring_alloc, &tx, sizeof(tx));
+	memcpy(&pdcs->rx_ring_alloc, &rx, sizeof(rx));
+
+	pdcs->rxin = 0;
+	pdcs->rx_msg_start = 0;
+	pdcs->last_rx_curr = 0;
+	pdcs->rxout = 0;
+	pdcs->txin = 0;
+	pdcs->tx_msg_start = 0;
+	pdcs->txout = 0;
+
+	/* Set descriptor array base addresses */
+	pdcs->txd_64 = (struct dma64dd *)pdcs->tx_ring_alloc.vbase;
+	pdcs->rxd_64 = (struct dma64dd *)pdcs->rx_ring_alloc.vbase;
+
+	/* Tell device the base DMA address of each ring */
+	dma_reg = &pdcs->regs->dmaregs[ringset];
+	iowrite32(lower_32_bits(pdcs->tx_ring_alloc.dmabase),
+		  (void *)&dma_reg->dmaxmt.addrlow);
+	iowrite32(upper_32_bits(pdcs->tx_ring_alloc.dmabase),
+		  (void *)&dma_reg->dmaxmt.addrhigh);
+
+	iowrite32(lower_32_bits(pdcs->rx_ring_alloc.dmabase),
+		  (void *)&dma_reg->dmarcv.addrlow);
+	iowrite32(upper_32_bits(pdcs->rx_ring_alloc.dmabase),
+		  (void *)&dma_reg->dmarcv.addrhigh);
+
+	/* Initialize descriptors */
+	for (i = 0; i < PDC_RING_ENTRIES; i++) {
+		/* Every tx descriptor can be used for start of frame. */
+		if (i != pdcs->ntxpost) {
+			iowrite32(D64_CTRL1_SOF | D64_CTRL1_EOF,
+				  (void *)&pdcs->txd_64[i].ctrl1);
+		} else {
+			/* Last descriptor in ringset. Set End of Table. */
+			iowrite32(D64_CTRL1_SOF | D64_CTRL1_EOF |
+				  D64_CTRL1_EOT,
+				  (void *)&pdcs->txd_64[i].ctrl1);
+		}
+
+		/* Every rx descriptor can be used for start of frame */
+		if (i != pdcs->nrxpost) {
+			iowrite32(D64_CTRL1_SOF,
+				  (void *)&pdcs->rxd_64[i].ctrl1);
+		} else {
+			/* Last descriptor in ringset. Set End of Table. */
+			iowrite32(D64_CTRL1_SOF | D64_CTRL1_EOT,
+				  (void *)&pdcs->rxd_64[i].ctrl1);
+		}
+	}
+	spin_unlock(&pdcs->pdc_lock);
+	return PDC_SUCCESS;
+
+fail_dealloc:
+	dma_pool_free(pdcs->ring_pool, tx.vbase, tx.dmabase);
+done:
+	return err;
+}
+
+static void pdc_ring_free(struct pdc_state *pdcs)
+{
+	if (pdcs->tx_ring_alloc.vbase) {
+		dma_pool_free(pdcs->ring_pool, pdcs->tx_ring_alloc.vbase,
+			      pdcs->tx_ring_alloc.dmabase);
+		pdcs->tx_ring_alloc.vbase = NULL;
+	}
+
+	if (pdcs->rx_ring_alloc.vbase) {
+		dma_pool_free(pdcs->ring_pool, pdcs->rx_ring_alloc.vbase,
+			      pdcs->rx_ring_alloc.dmabase);
+		pdcs->rx_ring_alloc.vbase = NULL;
+	}
+}
+
+/**
+ * pdc_send_data() - mailbox send_data function
+ * @chan:	The mailbox channel on which the data is sent. The channel
+ *              corresponds to a DMA ringset.
+ * @data:	The mailbox message to be sent. The message must be a
+ *              brcm_message structure.
+ *
+ * This function is registered as the send_data function for the mailbox
+ * controller. From the destination scatterlist in the mailbox message, it
+ * creates a sequence of receive descriptors in the rx ring. From the source
+ * scatterlist, it creates a sequence of transmit descriptors in the tx ring.
+ * After creating the descriptors, it writes the rx ptr and tx ptr registers to
+ * initiate the DMA transfer.
+ *
+ * This function does the DMA map and unmap of the src and dst scatterlists in
+ * the mailbox message.
+ *
+ * Return: 0 if successful
+ *	   -ENOTSUPP if the mailbox message is a type this driver does not
+ *			support
+ *         < 0 if an error
+ */
+static int pdc_send_data(struct mbox_chan *chan, void *data)
+{
+	struct pdc_state *pdcs = chan->con_priv;
+	struct device *dev = &pdcs->pdev->dev;
+	struct brcm_message *mssg = data;
+	int err = PDC_SUCCESS;
+	int src_nent;
+	int dst_nent;
+	int nent;
+
+	if (mssg->type != BRCM_MESSAGE_SPU)
+		return -ENOTSUPP;
+
+	src_nent = sg_nents(mssg->spu.src);
+	if (src_nent) {
+		nent = dma_map_sg(dev, mssg->spu.src, src_nent, DMA_TO_DEVICE);
+		if (nent == 0)
+			return -EIO;
+	}
+
+	dst_nent = sg_nents(mssg->spu.dst);
+	if (dst_nent) {
+		nent = dma_map_sg(dev, mssg->spu.dst, dst_nent,
+				  DMA_FROM_DEVICE);
+		if (nent == 0) {
+			dma_unmap_sg(dev, mssg->spu.src, src_nent,
+				     DMA_TO_DEVICE);
+			return -EIO;
+		}
+	}
+
+	spin_lock(&pdcs->pdc_lock);
+
+	/* Create rx descriptors to SPU catch response */
+	err = pdc_rx_list_init(pdcs, mssg->spu.dst, mssg->ctx);
+	err |= pdc_rx_list_sg_add(pdcs, mssg->spu.dst);
+
+	/* Create tx descriptors to submit SPU request */
+	err |= pdc_tx_list_sg_add(pdcs, mssg->spu.src);
+	err |= pdc_tx_list_final(pdcs);	/* initiate transfer */
+
+	spin_unlock(&pdcs->pdc_lock);
+
+	if (err)
+		dev_err(&pdcs->pdev->dev,
+			"%s failed with error %d", __func__, err);
+
+	return err;
+}
+
+static int pdc_startup(struct mbox_chan *chan)
+{
+	return pdc_ring_init(chan->con_priv, PDC_RINGSET);
+}
+
+static void pdc_shutdown(struct mbox_chan *chan)
+{
+	struct pdc_state *pdcs = chan->con_priv;
+
+	if (pdcs)
+		dev_dbg(&pdcs->pdev->dev,
+			"Shutdown mailbox channel for PDC %u", pdcs->pdc_idx);
+
+	pdc_ring_free(pdcs);
+}
+
+/**
+ * pdc_hw_init() - Use the given initialization parameters to initialize the
+ * state for one of the PDCs.
+ * @pdcs:  state of the PDC
+ */
+static
+void pdc_hw_init(struct pdc_state *pdcs)
+{
+	struct platform_device *pdev;
+	struct device *dev;
+	struct dma64 *dma_reg;
+	int ringset = PDC_RINGSET;
+
+	pdev = pdcs->pdev;
+	dev = &pdev->dev;
+
+	dev_dbg(dev, "PDC %u initial values:", pdcs->pdc_idx);
+	dev_dbg(dev, "state structure:                   %p",
+		pdcs);
+	dev_dbg(dev, " - base virtual addr of hw regs    %p",
+		pdcs->pdc_reg_vbase);
+
+	/* initialize data structures */
+	pdcs->regs = (struct pdc_regs *)pdcs->pdc_reg_vbase;
+	pdcs->txregs_64 = (struct dma64_regs *)
+	    (void *)(((u8 *)pdcs->pdc_reg_vbase) +
+		     PDC_TXREGS_OFFSET + (sizeof(struct dma64) * ringset));
+	pdcs->rxregs_64 = (struct dma64_regs *)
+	    (void *)(((u8 *)pdcs->pdc_reg_vbase) +
+		     PDC_RXREGS_OFFSET + (sizeof(struct dma64) * ringset));
+
+	pdcs->ntxd = PDC_RING_ENTRIES;
+	pdcs->nrxd = PDC_RING_ENTRIES;
+	pdcs->ntxpost = PDC_RING_ENTRIES - 1;
+	pdcs->nrxpost = PDC_RING_ENTRIES - 1;
+	pdcs->regs->intmask = 0;
+
+	dma_reg = &pdcs->regs->dmaregs[ringset];
+	iowrite32(0, (void *)&dma_reg->dmaxmt.ptr);
+	iowrite32(0, (void *)&dma_reg->dmarcv.ptr);
+
+	iowrite32(PDC_TX_CTL, (void *)&dma_reg->dmaxmt.control);
+
+	iowrite32(PDC_RX_CTL + (pdcs->rx_status_len << 1),
+		  (void *)&dma_reg->dmarcv.control);
+
+	if (pdcs->pdc_resp_hdr_len == PDC_SPU2_RESP_HDR_LEN)
+		iowrite32(PDC_CKSUM_CTRL,
+			  pdcs->pdc_reg_vbase + PDC_CKSUM_CTRL_OFFSET);
+}
+
+/**
+ * pdc_rx_buf_pool_create() - Pool of receive buffers used to catch the metadata
+ * header returned with each response message.
+ * @pdcs: PDC state structure
+ *
+ * The metadata is not returned to the mailbox client. So the PDC driver
+ * manages these buffers.
+ *
+ * Return: PDC_SUCCESS
+ *         -ENOMEM if pool creation fails
+ */
+static int pdc_rx_buf_pool_create(struct pdc_state *pdcs)
+{
+	struct platform_device *pdev;
+	struct device *dev;
+
+	pdev = pdcs->pdev;
+	dev = &pdev->dev;
+
+	pdcs->pdc_resp_hdr_len = pdcs->rx_status_len;
+	if (pdcs->use_bcm_hdr)
+		pdcs->pdc_resp_hdr_len += BCM_HDR_LEN;
+
+	pdcs->rx_buf_pool = dma_pool_create("pdc rx bufs", dev,
+					    pdcs->pdc_resp_hdr_len,
+					    RX_BUF_ALIGN, 0);
+	if (!pdcs->rx_buf_pool)
+		return -ENOMEM;
+
+	return PDC_SUCCESS;
+}
+
+/**
+ * pdc_interrupts_init() - Initialize the interrupt configuration for a PDC and
+ * specify a threaded IRQ handler for deferred handling of interrupts outside of
+ * interrupt context.
+ * @pdcs:   PDC state
+ *
+ * Set the interrupt mask for transmit and receive done.
+ * Set the lazy interrupt frame count to generate an interrupt for just one pkt.
+ *
+ * Return:  PDC_SUCCESS
+ *          <0 if threaded irq request fails
+ */
+static int pdc_interrupts_init(struct pdc_state *pdcs)
+{
+	struct platform_device *pdev = pdcs->pdev;
+	struct device *dev = &pdev->dev;
+	struct device_node *dn = pdev->dev.of_node;
+	int err;
+
+	pdcs->intstatus = 0;
+
+	/* interrupt configuration */
+	iowrite32(PDC_INTMASK, pdcs->pdc_reg_vbase + PDC_INTMASK_OFFSET);
+	iowrite32(PDC_LAZY_INT, pdcs->pdc_reg_vbase + PDC_RCVLAZY0_OFFSET);
+
+	/* read irq from device tree */
+	pdcs->pdc_irq = irq_of_parse_and_map(dn, 0);
+	dev_dbg(dev, "pdc device %s irq %u for pdcs %p",
+		dev_name(dev), pdcs->pdc_irq, pdcs);
+	err = devm_request_threaded_irq(dev, pdcs->pdc_irq,
+					pdc_irq_handler,
+					pdc_irq_thread, 0, dev_name(dev), pdcs);
+	if (err) {
+		dev_err(dev, "threaded tx IRQ %u request failed with err %d\n",
+			pdcs->pdc_irq, err);
+		return err;
+	}
+	return PDC_SUCCESS;
+}
+
+static const struct mbox_chan_ops pdc_mbox_chan_ops = {
+	.send_data = pdc_send_data,
+	.startup = pdc_startup,
+	.shutdown = pdc_shutdown
+};
+
+/**
+ * pdc_mb_init() - Initialize the mailbox controller.
+ * @pdcs:  PDC state
+ *
+ * Each PDC is a mailbox controller. Each ringset is a mailbox channel. Kernel
+ * driver only uses one ringset and thus one mb channel. PDC uses the transmit
+ * complete interrupt to determine when a mailbox message has successfully been
+ * transmitted.
+ *
+ * Return: 0 on success
+ *         < 0 if there is an allocation or registration failure
+ */
+static int pdc_mb_init(struct pdc_state *pdcs)
+{
+	struct device *dev = &pdcs->pdev->dev;
+	struct mbox_controller *mbc;
+	int chan_index;
+	int err;
+
+	mbc = &pdcs->mbc;
+	mbc->dev = dev;
+	mbc->ops = &pdc_mbox_chan_ops;
+	mbc->num_chans = 1;
+	mbc->chans = devm_kcalloc(dev, mbc->num_chans, sizeof(*mbc->chans),
+				  GFP_KERNEL);
+	if (!mbc->chans)
+		return -ENOMEM;
+
+	mbc->txdone_irq = true;
+	mbc->txdone_poll = false;
+	for (chan_index = 0; chan_index < mbc->num_chans; chan_index++)
+		mbc->chans[chan_index].con_priv = pdcs;
+
+	/* Register mailbox controller */
+	err = mbox_controller_register(mbc);
+	if (err) {
+		dev_crit(dev,
+			 "Failed to register PDC mailbox controller. Error %d.",
+			 err);
+		return err;
+	}
+	return 0;
+}
+
+/**
+ * pdc_dt_read() - Read application-specific data from device tree.
+ * @pdev:  Platform device
+ * @pdcs:  PDC state
+ *
+ * Reads the number of bytes of receive status that precede each received frame.
+ * Reads whether transmit and received frames should be preceded by an 8-byte
+ * BCM header.
+ *
+ * Return: 0 if successful
+ *         -ENODEV if device not available
+ */
+static int pdc_dt_read(struct platform_device *pdev, struct pdc_state *pdcs)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *dn = pdev->dev.of_node;
+	int err;
+
+	err = of_property_read_u32(dn, "brcm,rx-status-len",
+				   &pdcs->rx_status_len);
+	if (err < 0)
+		dev_err(dev,
+			"%s failed to get DMA receive status length from device tree",
+			__func__);
+
+	pdcs->use_bcm_hdr = of_property_read_bool(dn, "brcm,use-bcm-hdr");
+
+	return 0;
+}
+
+/**
+ * pdc_probe() - Probe function for PDC driver.
+ * @pdev:   PDC platform device
+ *
+ * Reserve and map register regions defined in device tree.
+ * Allocate and initialize tx and rx DMA rings.
+ * Initialize a mailbox controller for each PDC.
+ *
+ * Return: 0 if successful
+ *         < 0 if an error
+ */
+static int pdc_probe(struct platform_device *pdev)
+{
+	int err = 0;
+	struct device *dev = &pdev->dev;
+	struct resource *pdc_regs;
+	struct pdc_state *pdcs;
+
+	/* PDC state for one SPU */
+	pdcs = devm_kzalloc(dev, sizeof(*pdcs), GFP_KERNEL);
+	if (!pdcs) {
+		err = -ENOMEM;
+		goto cleanup;
+	}
+
+	spin_lock_init(&pdcs->pdc_lock);
+	pdcs->pdev = pdev;
+	platform_set_drvdata(pdev, pdcs);
+	pdcs->pdc_idx = pdcg.num_spu;
+	pdcg.num_spu++;
+
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (err) {
+		dev_warn(dev, "PDC device cannot perform DMA. Error %d.", err);
+		goto cleanup;
+	}
+
+	/* Create DMA pool for tx ring */
+	pdcs->ring_pool = dma_pool_create("pdc rings", dev, PDC_RING_SIZE,
+					  RING_ALIGN, 0);
+	if (!pdcs->ring_pool) {
+		err = -ENOMEM;
+		goto cleanup;
+	}
+
+	err = pdc_dt_read(pdev, pdcs);
+	if (err)
+		goto cleanup_ring_pool;
+
+	pdc_regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!pdc_regs) {
+		err = -ENODEV;
+		goto cleanup_ring_pool;
+	}
+	dev_dbg(dev, "PDC register region res.start = %pa, res.end = %pa",
+		&pdc_regs->start, &pdc_regs->end);
+
+	pdcs->pdc_reg_vbase = devm_ioremap_resource(&pdev->dev, pdc_regs);
+	if (IS_ERR(pdcs->pdc_reg_vbase)) {
+		err = PTR_ERR(pdcs->pdc_reg_vbase);
+		dev_err(&pdev->dev, "Failed to map registers: %d\n", err);
+		goto cleanup_ring_pool;
+	}
+
+	/* create rx buffer pool after dt read to know how big buffers are */
+	err = pdc_rx_buf_pool_create(pdcs);
+	if (err)
+		goto cleanup_ring_pool;
+
+	pdc_hw_init(pdcs);
+
+	err = pdc_interrupts_init(pdcs);
+	if (err)
+		goto cleanup_buf_pool;
+
+	/* Initialize mailbox controller */
+	err = pdc_mb_init(pdcs);
+	if (err)
+		goto cleanup_buf_pool;
+
+	pdcs->debugfs_stats = NULL;
+	pdc_setup_debugfs(pdcs);
+
+	dev_dbg(dev, "pdc_probe() successful");
+	return PDC_SUCCESS;
+
+cleanup_buf_pool:
+	dma_pool_destroy(pdcs->rx_buf_pool);
+
+cleanup_ring_pool:
+	dma_pool_destroy(pdcs->ring_pool);
+
+cleanup:
+	return err;
+}
+
+static int pdc_remove(struct platform_device *pdev)
+{
+	struct pdc_state *pdcs = platform_get_drvdata(pdev);
+
+	pdc_free_debugfs();
+
+	mbox_controller_unregister(&pdcs->mbc);
+
+	dma_pool_destroy(pdcs->rx_buf_pool);
+	dma_pool_destroy(pdcs->ring_pool);
+	return 0;
+}
+
+static const struct of_device_id pdc_mbox_of_match[] = {
+	{.compatible = "brcm,iproc-pdc-mbox"},
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, pdc_mbox_of_match);
+
+static struct platform_driver pdc_mbox_driver = {
+	.probe = pdc_probe,
+	.remove = pdc_remove,
+	.driver = {
+		   .name = "brcm-iproc-pdc-mbox",
+		   .of_match_table = of_match_ptr(pdc_mbox_of_match),
+		   },
+};
+module_platform_driver(pdc_mbox_driver);
+
+MODULE_AUTHOR("Rob Rice <rob.rice@broadcom.com>");
+MODULE_DESCRIPTION("Broadcom PDC mailbox driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c
index 58d04726cdd7..9ca96e9db6bf 100644
--- a/drivers/mailbox/mailbox-test.c
+++ b/drivers/mailbox/mailbox-test.c
@@ -133,6 +133,7 @@ static ssize_t mbox_test_message_write(struct file *filp,
 out:
 	kfree(tdev->signal);
 	kfree(tdev->message);
+	tdev->signal = NULL;
 
 	return ret < 0 ? ret : count;
 }
diff --git a/drivers/mailbox/pl320-ipc.c b/drivers/mailbox/pl320-ipc.c
index f80acb36ff07..2dbed87094d7 100644
--- a/drivers/mailbox/pl320-ipc.c
+++ b/drivers/mailbox/pl320-ipc.c
@@ -58,29 +58,29 @@ static ATOMIC_NOTIFIER_HEAD(ipc_notifier);
 
 static inline void set_destination(int source, int mbox)
 {
-	__raw_writel(CHAN_MASK(source), ipc_base + IPCMxDSET(mbox));
-	__raw_writel(CHAN_MASK(source), ipc_base + IPCMxMSET(mbox));
+	writel_relaxed(CHAN_MASK(source), ipc_base + IPCMxDSET(mbox));
+	writel_relaxed(CHAN_MASK(source), ipc_base + IPCMxMSET(mbox));
 }
 
 static inline void clear_destination(int source, int mbox)
 {
-	__raw_writel(CHAN_MASK(source), ipc_base + IPCMxDCLEAR(mbox));
-	__raw_writel(CHAN_MASK(source), ipc_base + IPCMxMCLEAR(mbox));
+	writel_relaxed(CHAN_MASK(source), ipc_base + IPCMxDCLEAR(mbox));
+	writel_relaxed(CHAN_MASK(source), ipc_base + IPCMxMCLEAR(mbox));
 }
 
 static void __ipc_send(int mbox, u32 *data)
 {
 	int i;
 	for (i = 0; i < 7; i++)
-		__raw_writel(data[i], ipc_base + IPCMxDR(mbox, i));
-	__raw_writel(0x1, ipc_base + IPCMxSEND(mbox));
+		writel_relaxed(data[i], ipc_base + IPCMxDR(mbox, i));
+	writel_relaxed(0x1, ipc_base + IPCMxSEND(mbox));
 }
 
 static u32 __ipc_rcv(int mbox, u32 *data)
 {
 	int i;
 	for (i = 0; i < 7; i++)
-		data[i] = __raw_readl(ipc_base + IPCMxDR(mbox, i));
+		data[i] = readl_relaxed(ipc_base + IPCMxDR(mbox, i));
 	return data[1];
 }
 
@@ -112,15 +112,15 @@ static irqreturn_t ipc_handler(int irq, void *dev)
 	u32 irq_stat;
 	u32 data[7];
 
-	irq_stat = __raw_readl(ipc_base + IPCMMIS(1));
+	irq_stat = readl_relaxed(ipc_base + IPCMMIS(1));
 	if (irq_stat & MBOX_MASK(IPC_TX_MBOX)) {
-		__raw_writel(0, ipc_base + IPCMxSEND(IPC_TX_MBOX));
+		writel_relaxed(0, ipc_base + IPCMxSEND(IPC_TX_MBOX));
 		complete(&ipc_completion);
 	}
 	if (irq_stat & MBOX_MASK(IPC_RX_MBOX)) {
 		__ipc_rcv(IPC_RX_MBOX, data);
 		atomic_notifier_call_chain(&ipc_notifier, data[0], data + 1);
-		__raw_writel(2, ipc_base + IPCMxSEND(IPC_RX_MBOX));
+		writel_relaxed(2, ipc_base + IPCMxSEND(IPC_RX_MBOX));
 	}
 
 	return IRQ_HANDLED;
@@ -146,7 +146,7 @@ static int pl320_probe(struct amba_device *adev, const struct amba_id *id)
 	if (ipc_base == NULL)
 		return -ENOMEM;
 
-	__raw_writel(0, ipc_base + IPCMxSEND(IPC_TX_MBOX));
+	writel_relaxed(0, ipc_base + IPCMxSEND(IPC_TX_MBOX));
 
 	ipc_irq = adev->irq[0];
 	ret = request_irq(ipc_irq, ipc_handler, 0, dev_name(&adev->dev), NULL);
@@ -154,20 +154,20 @@ static int pl320_probe(struct amba_device *adev, const struct amba_id *id)
 		goto err;
 
 	/* Init slow mailbox */
-	__raw_writel(CHAN_MASK(A9_SOURCE),
-			ipc_base + IPCMxSOURCE(IPC_TX_MBOX));
-	__raw_writel(CHAN_MASK(M3_SOURCE),
-			ipc_base + IPCMxDSET(IPC_TX_MBOX));
-	__raw_writel(CHAN_MASK(M3_SOURCE) | CHAN_MASK(A9_SOURCE),
-		     ipc_base + IPCMxMSET(IPC_TX_MBOX));
+	writel_relaxed(CHAN_MASK(A9_SOURCE),
+		       ipc_base + IPCMxSOURCE(IPC_TX_MBOX));
+	writel_relaxed(CHAN_MASK(M3_SOURCE),
+		       ipc_base + IPCMxDSET(IPC_TX_MBOX));
+	writel_relaxed(CHAN_MASK(M3_SOURCE) | CHAN_MASK(A9_SOURCE),
+		       ipc_base + IPCMxMSET(IPC_TX_MBOX));
 
 	/* Init receive mailbox */
-	__raw_writel(CHAN_MASK(M3_SOURCE),
-			ipc_base + IPCMxSOURCE(IPC_RX_MBOX));
-	__raw_writel(CHAN_MASK(A9_SOURCE),
-			ipc_base + IPCMxDSET(IPC_RX_MBOX));
-	__raw_writel(CHAN_MASK(M3_SOURCE) | CHAN_MASK(A9_SOURCE),
-		     ipc_base + IPCMxMSET(IPC_RX_MBOX));
+	writel_relaxed(CHAN_MASK(M3_SOURCE),
+		       ipc_base + IPCMxSOURCE(IPC_RX_MBOX));
+	writel_relaxed(CHAN_MASK(A9_SOURCE),
+		       ipc_base + IPCMxDSET(IPC_RX_MBOX));
+	writel_relaxed(CHAN_MASK(M3_SOURCE) | CHAN_MASK(A9_SOURCE),
+		       ipc_base + IPCMxMSET(IPC_RX_MBOX));
 
 	return 0;
 err:
diff --git a/drivers/media/platform/omap/omap_vout.c b/drivers/media/platform/omap/omap_vout.c
index 4afc999c0780..6b01e126fe73 100644
--- a/drivers/media/platform/omap/omap_vout.c
+++ b/drivers/media/platform/omap/omap_vout.c
@@ -45,7 +45,7 @@
 #include <media/v4l2-ioctl.h>
 
 #include <video/omapvrfb.h>
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "omap_voutlib.h"
 #include "omap_voutdef.h"
diff --git a/drivers/media/platform/omap/omap_voutdef.h b/drivers/media/platform/omap/omap_voutdef.h
index 49de1475e473..80c79fabdf95 100644
--- a/drivers/media/platform/omap/omap_voutdef.h
+++ b/drivers/media/platform/omap/omap_voutdef.h
@@ -12,7 +12,7 @@
 #define OMAP_VOUTDEF_H
 
 #include <media/v4l2-ctrls.h>
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include <video/omapvrfb.h>
 
 #define YUYV_BPP        2
diff --git a/drivers/media/platform/omap/omap_voutlib.c b/drivers/media/platform/omap/omap_voutlib.c
index 80b0d88f125c..58a25fdf0cce 100644
--- a/drivers/media/platform/omap/omap_voutlib.c
+++ b/drivers/media/platform/omap/omap_voutlib.c
@@ -26,7 +26,7 @@
 
 #include <linux/dma-mapping.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "omap_voutlib.h"
 
diff --git a/drivers/media/rc/Kconfig b/drivers/media/rc/Kconfig
index bd4d68500085..370e16e07867 100644
--- a/drivers/media/rc/Kconfig
+++ b/drivers/media/rc/Kconfig
@@ -336,7 +336,7 @@ config IR_TTUSBIR
 
 config IR_RX51
 	tristate "Nokia N900 IR transmitter diode"
-	depends on OMAP_DM_TIMER && ARCH_OMAP2PLUS && LIRC && !ARCH_MULTIPLATFORM
+	depends on OMAP_DM_TIMER && PWM_OMAP_DMTIMER && ARCH_OMAP2PLUS && LIRC
 	---help---
 	   Say Y or M here if you want to enable support for the IR
 	   transmitter diode built in the Nokia N900 (RX51) device.
diff --git a/drivers/media/rc/ir-rx51.c b/drivers/media/rc/ir-rx51.c
index 4e1711a40466..82fb6f2ca011 100644
--- a/drivers/media/rc/ir-rx51.c
+++ b/drivers/media/rc/ir-rx51.c
@@ -12,22 +12,17 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
  */
-
+#include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/uaccess.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
-
-#include <plat/dmtimer.h>
-#include <plat/clock.h>
+#include <linux/pwm.h>
+#include <linux/of.h>
+#include <linux/hrtimer.h>
 
 #include <media/lirc.h>
 #include <media/lirc_dev.h>
@@ -41,100 +36,51 @@
 
 #define WBUF_LEN 256
 
-#define TIMER_MAX_VALUE 0xffffffff
-
 struct lirc_rx51 {
-	struct omap_dm_timer *pwm_timer;
-	struct omap_dm_timer *pulse_timer;
+	struct pwm_device *pwm;
+	struct hrtimer timer;
 	struct device	     *dev;
 	struct lirc_rx51_platform_data *pdata;
 	wait_queue_head_t     wqueue;
 
-	unsigned long	fclk_khz;
 	unsigned int	freq;		/* carrier frequency */
 	unsigned int	duty_cycle;	/* carrier duty cycle */
-	unsigned int	irq_num;
-	unsigned int	match;
 	int		wbuf[WBUF_LEN];
 	int		wbuf_index;
 	unsigned long	device_is_open;
-	int		pwm_timer_num;
 };
 
-static void lirc_rx51_on(struct lirc_rx51 *lirc_rx51)
+static inline void lirc_rx51_on(struct lirc_rx51 *lirc_rx51)
 {
-	omap_dm_timer_set_pwm(lirc_rx51->pwm_timer, 0, 1,
-			      OMAP_TIMER_TRIGGER_OVERFLOW_AND_COMPARE);
+	pwm_enable(lirc_rx51->pwm);
 }
 
-static void lirc_rx51_off(struct lirc_rx51 *lirc_rx51)
+static inline void lirc_rx51_off(struct lirc_rx51 *lirc_rx51)
 {
-	omap_dm_timer_set_pwm(lirc_rx51->pwm_timer, 0, 1,
-			      OMAP_TIMER_TRIGGER_NONE);
+	pwm_disable(lirc_rx51->pwm);
 }
 
 static int init_timing_params(struct lirc_rx51 *lirc_rx51)
 {
-	u32 load, match;
+	struct pwm_device *pwm = lirc_rx51->pwm;
+	int duty, period = DIV_ROUND_CLOSEST(NSEC_PER_SEC, lirc_rx51->freq);
 
-	load = -(lirc_rx51->fclk_khz * 1000 / lirc_rx51->freq);
-	match = -(lirc_rx51->duty_cycle * -load / 100);
-	omap_dm_timer_set_load(lirc_rx51->pwm_timer, 1, load);
-	omap_dm_timer_set_match(lirc_rx51->pwm_timer, 1, match);
-	omap_dm_timer_write_counter(lirc_rx51->pwm_timer, TIMER_MAX_VALUE - 2);
-	omap_dm_timer_start(lirc_rx51->pwm_timer);
-	omap_dm_timer_set_int_enable(lirc_rx51->pulse_timer, 0);
-	omap_dm_timer_start(lirc_rx51->pulse_timer);
+	duty = DIV_ROUND_CLOSEST(lirc_rx51->duty_cycle * period, 100);
 
-	lirc_rx51->match = 0;
+	pwm_config(pwm, duty, period);
 
 	return 0;
 }
 
-#define tics_after(a, b) ((long)(b) - (long)(a) < 0)
-
-static int pulse_timer_set_timeout(struct lirc_rx51 *lirc_rx51, int usec)
+static enum hrtimer_restart lirc_rx51_timer_cb(struct hrtimer *timer)
 {
-	int counter;
-
-	BUG_ON(usec < 0);
-
-	if (lirc_rx51->match == 0)
-		counter = omap_dm_timer_read_counter(lirc_rx51->pulse_timer);
-	else
-		counter = lirc_rx51->match;
-
-	counter += (u32)(lirc_rx51->fclk_khz * usec / (1000));
-	omap_dm_timer_set_match(lirc_rx51->pulse_timer, 1, counter);
-	omap_dm_timer_set_int_enable(lirc_rx51->pulse_timer,
-				     OMAP_TIMER_INT_MATCH);
-	if (tics_after(omap_dm_timer_read_counter(lirc_rx51->pulse_timer),
-		       counter)) {
-		return 1;
-	}
-	return 0;
-}
-
-static irqreturn_t lirc_rx51_interrupt_handler(int irq, void *ptr)
-{
-	unsigned int retval;
-	struct lirc_rx51 *lirc_rx51 = ptr;
-
-	retval = omap_dm_timer_read_status(lirc_rx51->pulse_timer);
-	if (!retval)
-		return IRQ_NONE;
+	struct lirc_rx51 *lirc_rx51 =
+			container_of(timer, struct lirc_rx51, timer);
+	ktime_t now;
 
-	if (retval & ~OMAP_TIMER_INT_MATCH)
-		dev_err_ratelimited(lirc_rx51->dev,
-				": Unexpected interrupt source: %x\n", retval);
-
-	omap_dm_timer_write_status(lirc_rx51->pulse_timer,
-				OMAP_TIMER_INT_MATCH	|
-				OMAP_TIMER_INT_OVERFLOW	|
-				OMAP_TIMER_INT_CAPTURE);
 	if (lirc_rx51->wbuf_index < 0) {
 		dev_err_ratelimited(lirc_rx51->dev,
-				": BUG wbuf_index has value of %i\n",
+				"BUG wbuf_index has value of %i\n",
 				lirc_rx51->wbuf_index);
 		goto end;
 	}
@@ -144,6 +90,8 @@ static irqreturn_t lirc_rx51_interrupt_handler(int irq, void *ptr)
 	 * pulses until we catch up.
 	 */
 	do {
+		u64 ns;
+
 		if (lirc_rx51->wbuf_index >= WBUF_LEN)
 			goto end;
 		if (lirc_rx51->wbuf[lirc_rx51->wbuf_index] == -1)
@@ -154,84 +102,24 @@ static irqreturn_t lirc_rx51_interrupt_handler(int irq, void *ptr)
 		else
 			lirc_rx51_on(lirc_rx51);
 
-		retval = pulse_timer_set_timeout(lirc_rx51,
-					lirc_rx51->wbuf[lirc_rx51->wbuf_index]);
+		ns = 1000 * lirc_rx51->wbuf[lirc_rx51->wbuf_index];
+		hrtimer_add_expires_ns(timer, ns);
+
 		lirc_rx51->wbuf_index++;
 
-	} while (retval);
+		now = timer->base->get_time();
+
+	} while (hrtimer_get_expires_tv64(timer) < now.tv64);
 
-	return IRQ_HANDLED;
+	return HRTIMER_RESTART;
 end:
 	/* Stop TX here */
 	lirc_rx51_off(lirc_rx51);
 	lirc_rx51->wbuf_index = -1;
-	omap_dm_timer_stop(lirc_rx51->pwm_timer);
-	omap_dm_timer_stop(lirc_rx51->pulse_timer);
-	omap_dm_timer_set_int_enable(lirc_rx51->pulse_timer, 0);
-	wake_up_interruptible(&lirc_rx51->wqueue);
-
-	return IRQ_HANDLED;
-}
-
-static int lirc_rx51_init_port(struct lirc_rx51 *lirc_rx51)
-{
-	struct clk *clk_fclk;
-	int retval, pwm_timer = lirc_rx51->pwm_timer_num;
-
-	lirc_rx51->pwm_timer = omap_dm_timer_request_specific(pwm_timer);
-	if (lirc_rx51->pwm_timer == NULL) {
-		dev_err(lirc_rx51->dev, ": Error requesting GPT%d timer\n",
-			pwm_timer);
-		return -EBUSY;
-	}
-
-	lirc_rx51->pulse_timer = omap_dm_timer_request();
-	if (lirc_rx51->pulse_timer == NULL) {
-		dev_err(lirc_rx51->dev, ": Error requesting pulse timer\n");
-		retval = -EBUSY;
-		goto err1;
-	}
-
-	omap_dm_timer_set_source(lirc_rx51->pwm_timer, OMAP_TIMER_SRC_SYS_CLK);
-	omap_dm_timer_set_source(lirc_rx51->pulse_timer,
-				OMAP_TIMER_SRC_SYS_CLK);
-
-	omap_dm_timer_enable(lirc_rx51->pwm_timer);
-	omap_dm_timer_enable(lirc_rx51->pulse_timer);
-
-	lirc_rx51->irq_num = omap_dm_timer_get_irq(lirc_rx51->pulse_timer);
-	retval = request_irq(lirc_rx51->irq_num, lirc_rx51_interrupt_handler,
-			     IRQF_SHARED, "lirc_pulse_timer", lirc_rx51);
-	if (retval) {
-		dev_err(lirc_rx51->dev, ": Failed to request interrupt line\n");
-		goto err2;
-	}
-
-	clk_fclk = omap_dm_timer_get_fclk(lirc_rx51->pwm_timer);
-	lirc_rx51->fclk_khz = clk_fclk->rate / 1000;
-
-	return 0;
 
-err2:
-	omap_dm_timer_free(lirc_rx51->pulse_timer);
-err1:
-	omap_dm_timer_free(lirc_rx51->pwm_timer);
-
-	return retval;
-}
-
-static int lirc_rx51_free_port(struct lirc_rx51 *lirc_rx51)
-{
-	omap_dm_timer_set_int_enable(lirc_rx51->pulse_timer, 0);
-	free_irq(lirc_rx51->irq_num, lirc_rx51);
-	lirc_rx51_off(lirc_rx51);
-	omap_dm_timer_disable(lirc_rx51->pwm_timer);
-	omap_dm_timer_disable(lirc_rx51->pulse_timer);
-	omap_dm_timer_free(lirc_rx51->pwm_timer);
-	omap_dm_timer_free(lirc_rx51->pulse_timer);
-	lirc_rx51->wbuf_index = -1;
+	wake_up_interruptible(&lirc_rx51->wqueue);
 
-	return 0;
+	return HRTIMER_NORESTART;
 }
 
 static ssize_t lirc_rx51_write(struct file *file, const char *buf,
@@ -270,8 +158,9 @@ static ssize_t lirc_rx51_write(struct file *file, const char *buf,
 
 	lirc_rx51_on(lirc_rx51);
 	lirc_rx51->wbuf_index = 1;
-	pulse_timer_set_timeout(lirc_rx51, lirc_rx51->wbuf[0]);
-
+	hrtimer_start(&lirc_rx51->timer,
+		      ns_to_ktime(1000 * lirc_rx51->wbuf[0]),
+		      HRTIMER_MODE_REL);
 	/*
 	 * Don't return back to the userspace until the transfer has
 	 * finished
@@ -371,14 +260,24 @@ static int lirc_rx51_open(struct inode *inode, struct file *file)
 	if (test_and_set_bit(1, &lirc_rx51->device_is_open))
 		return -EBUSY;
 
-	return lirc_rx51_init_port(lirc_rx51);
+	lirc_rx51->pwm = pwm_get(lirc_rx51->dev, NULL);
+	if (IS_ERR(lirc_rx51->pwm)) {
+		int res = PTR_ERR(lirc_rx51->pwm);
+
+		dev_err(lirc_rx51->dev, "pwm_get failed: %d\n", res);
+		return res;
+	}
+
+	return 0;
 }
 
 static int lirc_rx51_release(struct inode *inode, struct file *file)
 {
 	struct lirc_rx51 *lirc_rx51 = file->private_data;
 
-	lirc_rx51_free_port(lirc_rx51);
+	hrtimer_cancel(&lirc_rx51->timer);
+	lirc_rx51_off(lirc_rx51);
+	pwm_put(lirc_rx51->pwm);
 
 	clear_bit(1, &lirc_rx51->device_is_open);
 
@@ -386,7 +285,6 @@ static int lirc_rx51_release(struct inode *inode, struct file *file)
 }
 
 static struct lirc_rx51 lirc_rx51 = {
-	.freq		= 38000,
 	.duty_cycle	= 50,
 	.wbuf_index	= -1,
 };
@@ -444,9 +342,32 @@ static int lirc_rx51_resume(struct platform_device *dev)
 
 static int lirc_rx51_probe(struct platform_device *dev)
 {
+	struct pwm_device *pwm;
+
 	lirc_rx51_driver.features = LIRC_RX51_DRIVER_FEATURES;
 	lirc_rx51.pdata = dev->dev.platform_data;
-	lirc_rx51.pwm_timer_num = lirc_rx51.pdata->pwm_timer;
+
+	if (!lirc_rx51.pdata) {
+		dev_err(&dev->dev, "Platform Data is missing\n");
+		return -ENXIO;
+	}
+
+	pwm = pwm_get(&dev->dev, NULL);
+	if (IS_ERR(pwm)) {
+		int err = PTR_ERR(pwm);
+
+		if (err != -EPROBE_DEFER)
+			dev_err(&dev->dev, "pwm_get failed: %d\n", err);
+		return err;
+	}
+
+	/* Use default, in case userspace does not set the carrier */
+	lirc_rx51.freq = DIV_ROUND_CLOSEST(pwm_get_period(pwm), NSEC_PER_SEC);
+	pwm_put(pwm);
+
+	hrtimer_init(&lirc_rx51.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	lirc_rx51.timer.function = lirc_rx51_timer_cb;
+
 	lirc_rx51.dev = &dev->dev;
 	lirc_rx51_driver.dev = &dev->dev;
 	lirc_rx51_driver.minor = lirc_register_driver(&lirc_rx51_driver);
@@ -457,8 +378,6 @@ static int lirc_rx51_probe(struct platform_device *dev)
 		       lirc_rx51_driver.minor);
 		return lirc_rx51_driver.minor;
 	}
-	dev_info(lirc_rx51.dev, "registration ok, minor: %d, pwm: %d\n",
-		 lirc_rx51_driver.minor, lirc_rx51.pwm_timer_num);
 
 	return 0;
 }
@@ -468,6 +387,14 @@ static int lirc_rx51_remove(struct platform_device *dev)
 	return lirc_unregister_driver(lirc_rx51_driver.minor);
 }
 
+static const struct of_device_id lirc_rx51_match[] = {
+	{
+		.compatible = "nokia,n900-ir",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, lirc_rx51_match);
+
 struct platform_driver lirc_rx51_platform_driver = {
 	.probe		= lirc_rx51_probe,
 	.remove		= lirc_rx51_remove,
@@ -475,7 +402,7 @@ struct platform_driver lirc_rx51_platform_driver = {
 	.resume		= lirc_rx51_resume,
 	.driver		= {
 		.name	= DRIVER_NAME,
-		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(lirc_rx51_match),
 	},
 };
 module_platform_driver(lirc_rx51_platform_driver);
diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
index 81ddb17575a9..4b4c0c3c3d2f 100644
--- a/drivers/memory/Kconfig
+++ b/drivers/memory/Kconfig
@@ -25,6 +25,17 @@ config ATMEL_SDRAMC
 	  Starting with the at91sam9g45, this controller supports SDR, DDR and
 	  LP-DDR memories.
 
+config ATMEL_EBI
+	bool "Atmel EBI driver"
+	default y
+	depends on ARCH_AT91 && OF
+	select MFD_SYSCON
+	help
+	  Driver for Atmel EBI controller.
+	  Used to configure the EBI (external bus interface) when the device-
+	  tree is used. This bus supports NANDs, external ethernet controller,
+	  SRAMs, ATA devices, etc.
+
 config TI_AEMIF
 	tristate "Texas Instruments AEMIF driver"
 	depends on (ARCH_DAVINCI || ARCH_KEYSTONE) && OF
@@ -104,7 +115,7 @@ config FSL_CORENET_CF
 
 config FSL_IFC
 	bool
-	depends on FSL_SOC
+	depends on FSL_SOC || ARCH_LAYERSCAPE
 
 config JZ4780_NEMC
 	bool "Ingenic JZ4780 SoC NEMC driver"
diff --git a/drivers/memory/Makefile b/drivers/memory/Makefile
index cb0b7a1df11a..b20ae38b5bfb 100644
--- a/drivers/memory/Makefile
+++ b/drivers/memory/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_OF)		+= of_memory.o
 endif
 obj-$(CONFIG_ARM_PL172_MPMC)	+= pl172.o
 obj-$(CONFIG_ATMEL_SDRAMC)	+= atmel-sdramc.o
+obj-$(CONFIG_ATMEL_EBI)		+= atmel-ebi.o
 obj-$(CONFIG_TI_AEMIF)		+= ti-aemif.o
 obj-$(CONFIG_TI_EMIF)		+= emif.o
 obj-$(CONFIG_OMAP_GPMC)		+= omap-gpmc.o
diff --git a/drivers/memory/atmel-ebi.c b/drivers/memory/atmel-ebi.c
new file mode 100644
index 000000000000..f87ad6f5d2dc
--- /dev/null
+++ b/drivers/memory/atmel-ebi.c
@@ -0,0 +1,766 @@
+/*
+ * EBI driver for Atmel chips
+ * inspired by the fsl weim bus driver
+ *
+ * Copyright (C) 2013 Jean-Jacques Hiblot <jjhiblot@traphandler.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mfd/syscon/atmel-matrix.h>
+#include <linux/mfd/syscon/atmel-smc.h>
+#include <linux/init.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+
+struct at91sam9_smc_timings {
+	u32 ncs_rd_setup_ns;
+	u32 nrd_setup_ns;
+	u32 ncs_wr_setup_ns;
+	u32 nwe_setup_ns;
+	u32 ncs_rd_pulse_ns;
+	u32 nrd_pulse_ns;
+	u32 ncs_wr_pulse_ns;
+	u32 nwe_pulse_ns;
+	u32 nrd_cycle_ns;
+	u32 nwe_cycle_ns;
+	u32 tdf_ns;
+};
+
+struct at91sam9_smc_generic_fields {
+	struct regmap_field *setup;
+	struct regmap_field *pulse;
+	struct regmap_field *cycle;
+	struct regmap_field *mode;
+};
+
+struct at91sam9_ebi_dev_config {
+	struct at91sam9_smc_timings timings;
+	u32 mode;
+};
+
+struct at91_ebi_dev_config {
+	int cs;
+	union {
+		struct at91sam9_ebi_dev_config sam9;
+	};
+};
+
+struct at91_ebi;
+
+struct at91_ebi_dev {
+	struct list_head node;
+	struct at91_ebi *ebi;
+	u32 mode;
+	int numcs;
+	struct at91_ebi_dev_config configs[];
+};
+
+struct at91_ebi_caps {
+	unsigned int available_cs;
+	const struct reg_field *ebi_csa;
+	void (*get_config)(struct at91_ebi_dev *ebid,
+			   struct at91_ebi_dev_config *conf);
+	int (*xlate_config)(struct at91_ebi_dev *ebid,
+			    struct device_node *configs_np,
+			    struct at91_ebi_dev_config *conf);
+	int (*apply_config)(struct at91_ebi_dev *ebid,
+			    struct at91_ebi_dev_config *conf);
+	int (*init)(struct at91_ebi *ebi);
+};
+
+struct at91_ebi {
+	struct clk *clk;
+	struct regmap *smc;
+	struct regmap *matrix;
+
+	struct regmap_field *ebi_csa;
+
+	struct device *dev;
+	const struct at91_ebi_caps *caps;
+	struct list_head devs;
+	union {
+		struct at91sam9_smc_generic_fields sam9;
+	};
+};
+
+static void at91sam9_ebi_get_config(struct at91_ebi_dev *ebid,
+				    struct at91_ebi_dev_config *conf)
+{
+	struct at91sam9_smc_generic_fields *fields = &ebid->ebi->sam9;
+	unsigned int clk_rate = clk_get_rate(ebid->ebi->clk);
+	struct at91sam9_ebi_dev_config *config = &conf->sam9;
+	struct at91sam9_smc_timings *timings = &config->timings;
+	unsigned int val;
+
+	regmap_fields_read(fields->mode, conf->cs, &val);
+	config->mode = val & ~AT91_SMC_TDF;
+
+	val = (val & AT91_SMC_TDF) >> 16;
+	timings->tdf_ns = clk_rate * val;
+
+	regmap_fields_read(fields->setup, conf->cs, &val);
+	timings->ncs_rd_setup_ns = (val >> 24) & 0x1f;
+	timings->ncs_rd_setup_ns += ((val >> 29) & 0x1) * 128;
+	timings->ncs_rd_setup_ns *= clk_rate;
+	timings->nrd_setup_ns = (val >> 16) & 0x1f;
+	timings->nrd_setup_ns += ((val >> 21) & 0x1) * 128;
+	timings->nrd_setup_ns *= clk_rate;
+	timings->ncs_wr_setup_ns = (val >> 8) & 0x1f;
+	timings->ncs_wr_setup_ns += ((val >> 13) & 0x1) * 128;
+	timings->ncs_wr_setup_ns *= clk_rate;
+	timings->nwe_setup_ns = val & 0x1f;
+	timings->nwe_setup_ns += ((val >> 5) & 0x1) * 128;
+	timings->nwe_setup_ns *= clk_rate;
+
+	regmap_fields_read(fields->pulse, conf->cs, &val);
+	timings->ncs_rd_pulse_ns = (val >> 24) & 0x3f;
+	timings->ncs_rd_pulse_ns += ((val >> 30) & 0x1) * 256;
+	timings->ncs_rd_pulse_ns *= clk_rate;
+	timings->nrd_pulse_ns = (val >> 16) & 0x3f;
+	timings->nrd_pulse_ns += ((val >> 22) & 0x1) * 256;
+	timings->nrd_pulse_ns *= clk_rate;
+	timings->ncs_wr_pulse_ns = (val >> 8) & 0x3f;
+	timings->ncs_wr_pulse_ns += ((val >> 14) & 0x1) * 256;
+	timings->ncs_wr_pulse_ns *= clk_rate;
+	timings->nwe_pulse_ns = val & 0x3f;
+	timings->nwe_pulse_ns += ((val >> 6) & 0x1) * 256;
+	timings->nwe_pulse_ns *= clk_rate;
+
+	regmap_fields_read(fields->cycle, conf->cs, &val);
+	timings->nrd_cycle_ns = (val >> 16) & 0x7f;
+	timings->nrd_cycle_ns += ((val >> 23) & 0x3) * 256;
+	timings->nrd_cycle_ns *= clk_rate;
+	timings->nwe_cycle_ns = val & 0x7f;
+	timings->nwe_cycle_ns += ((val >> 7) & 0x3) * 256;
+	timings->nwe_cycle_ns *= clk_rate;
+}
+
+static int at91_xlate_timing(struct device_node *np, const char *prop,
+			     u32 *val, bool *required)
+{
+	if (!of_property_read_u32(np, prop, val)) {
+		*required = true;
+		return 0;
+	}
+
+	if (*required)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int at91sam9_smc_xslate_timings(struct at91_ebi_dev *ebid,
+				       struct device_node *np,
+				       struct at91sam9_smc_timings *timings,
+				       bool *required)
+{
+	int ret;
+
+	ret = at91_xlate_timing(np, "atmel,smc-ncs-rd-setup-ns",
+				&timings->ncs_rd_setup_ns, required);
+	if (ret)
+		goto out;
+
+	ret = at91_xlate_timing(np, "atmel,smc-nrd-setup-ns",
+				&timings->nrd_setup_ns, required);
+	if (ret)
+		goto out;
+
+	ret = at91_xlate_timing(np, "atmel,smc-ncs-wr-setup-ns",
+				&timings->ncs_wr_setup_ns, required);
+	if (ret)
+		goto out;
+
+	ret = at91_xlate_timing(np, "atmel,smc-nwe-setup-ns",
+				&timings->nwe_setup_ns, required);
+	if (ret)
+		goto out;
+
+	ret = at91_xlate_timing(np, "atmel,smc-ncs-rd-pulse-ns",
+				&timings->ncs_rd_pulse_ns, required);
+	if (ret)
+		goto out;
+
+	ret = at91_xlate_timing(np, "atmel,smc-nrd-pulse-ns",
+				&timings->nrd_pulse_ns, required);
+	if (ret)
+		goto out;
+
+	ret = at91_xlate_timing(np, "atmel,smc-ncs-wr-pulse-ns",
+				&timings->ncs_wr_pulse_ns, required);
+	if (ret)
+		goto out;
+
+	ret = at91_xlate_timing(np, "atmel,smc-nwe-pulse-ns",
+				&timings->nwe_pulse_ns, required);
+	if (ret)
+		goto out;
+
+	ret = at91_xlate_timing(np, "atmel,smc-nwe-cycle-ns",
+				&timings->nwe_cycle_ns, required);
+	if (ret)
+		goto out;
+
+	ret = at91_xlate_timing(np, "atmel,smc-nrd-cycle-ns",
+				&timings->nrd_cycle_ns, required);
+	if (ret)
+		goto out;
+
+	ret = at91_xlate_timing(np, "atmel,smc-tdf-ns",
+				&timings->tdf_ns, required);
+
+out:
+	if (ret)
+		dev_err(ebid->ebi->dev,
+			"missing or invalid timings definition in %s",
+			np->full_name);
+
+	return ret;
+}
+
+static int at91sam9_ebi_xslate_config(struct at91_ebi_dev *ebid,
+				      struct device_node *np,
+				      struct at91_ebi_dev_config *conf)
+{
+	struct at91sam9_ebi_dev_config *config = &conf->sam9;
+	bool required = false;
+	const char *tmp_str;
+	u32 tmp;
+	int ret;
+
+	ret = of_property_read_u32(np, "atmel,smc-bus-width", &tmp);
+	if (!ret) {
+		switch (tmp) {
+		case 8:
+			config->mode |= AT91_SMC_DBW_8;
+			break;
+
+		case 16:
+			config->mode |= AT91_SMC_DBW_16;
+			break;
+
+		case 32:
+			config->mode |= AT91_SMC_DBW_32;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+
+		required = true;
+	}
+
+	if (of_property_read_bool(np, "atmel,smc-tdf-optimized")) {
+		config->mode |= AT91_SMC_TDFMODE_OPTIMIZED;
+		required = true;
+	}
+
+	tmp_str = NULL;
+	of_property_read_string(np, "atmel,smc-byte-access-type", &tmp_str);
+	if (tmp_str && !strcmp(tmp_str, "write")) {
+		config->mode |= AT91_SMC_BAT_WRITE;
+		required = true;
+	}
+
+	tmp_str = NULL;
+	of_property_read_string(np, "atmel,smc-read-mode", &tmp_str);
+	if (tmp_str && !strcmp(tmp_str, "nrd")) {
+		config->mode |= AT91_SMC_READMODE_NRD;
+		required = true;
+	}
+
+	tmp_str = NULL;
+	of_property_read_string(np, "atmel,smc-write-mode", &tmp_str);
+	if (tmp_str && !strcmp(tmp_str, "nwe")) {
+		config->mode |= AT91_SMC_WRITEMODE_NWE;
+		required = true;
+	}
+
+	tmp_str = NULL;
+	of_property_read_string(np, "atmel,smc-exnw-mode", &tmp_str);
+	if (tmp_str) {
+		if (!strcmp(tmp_str, "frozen"))
+			config->mode |= AT91_SMC_EXNWMODE_FROZEN;
+		else if (!strcmp(tmp_str, "ready"))
+			config->mode |= AT91_SMC_EXNWMODE_READY;
+		else if (strcmp(tmp_str, "disabled"))
+			return -EINVAL;
+
+		required = true;
+	}
+
+	ret = of_property_read_u32(np, "atmel,smc-page-mode", &tmp);
+	if (!ret) {
+		switch (tmp) {
+		case 4:
+			config->mode |= AT91_SMC_PS_4;
+			break;
+
+		case 8:
+			config->mode |= AT91_SMC_PS_8;
+			break;
+
+		case 16:
+			config->mode |= AT91_SMC_PS_16;
+			break;
+
+		case 32:
+			config->mode |= AT91_SMC_PS_32;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+
+		config->mode |= AT91_SMC_PMEN;
+		required = true;
+	}
+
+	ret = at91sam9_smc_xslate_timings(ebid, np, &config->timings,
+					  &required);
+	if (ret)
+		return ret;
+
+	return required;
+}
+
+static int at91sam9_ebi_apply_config(struct at91_ebi_dev *ebid,
+				     struct at91_ebi_dev_config *conf)
+{
+	unsigned int clk_rate = clk_get_rate(ebid->ebi->clk);
+	struct at91sam9_ebi_dev_config *config = &conf->sam9;
+	struct at91sam9_smc_timings *timings = &config->timings;
+	struct at91sam9_smc_generic_fields *fields = &ebid->ebi->sam9;
+	u32 coded_val;
+	u32 val;
+
+	coded_val = at91sam9_smc_setup_ns_to_cycles(clk_rate,
+						    timings->ncs_rd_setup_ns);
+	val = AT91SAM9_SMC_NCS_NRDSETUP(coded_val);
+	coded_val = at91sam9_smc_setup_ns_to_cycles(clk_rate,
+						    timings->nrd_setup_ns);
+	val |= AT91SAM9_SMC_NRDSETUP(coded_val);
+	coded_val = at91sam9_smc_setup_ns_to_cycles(clk_rate,
+						    timings->ncs_wr_setup_ns);
+	val |= AT91SAM9_SMC_NCS_WRSETUP(coded_val);
+	coded_val = at91sam9_smc_setup_ns_to_cycles(clk_rate,
+						    timings->nwe_setup_ns);
+	val |= AT91SAM9_SMC_NWESETUP(coded_val);
+	regmap_fields_write(fields->setup, conf->cs, val);
+
+	coded_val = at91sam9_smc_pulse_ns_to_cycles(clk_rate,
+						    timings->ncs_rd_pulse_ns);
+	val = AT91SAM9_SMC_NCS_NRDPULSE(coded_val);
+	coded_val = at91sam9_smc_pulse_ns_to_cycles(clk_rate,
+						    timings->nrd_pulse_ns);
+	val |= AT91SAM9_SMC_NRDPULSE(coded_val);
+	coded_val = at91sam9_smc_pulse_ns_to_cycles(clk_rate,
+						    timings->ncs_wr_pulse_ns);
+	val |= AT91SAM9_SMC_NCS_WRPULSE(coded_val);
+	coded_val = at91sam9_smc_pulse_ns_to_cycles(clk_rate,
+						    timings->nwe_pulse_ns);
+	val |= AT91SAM9_SMC_NWEPULSE(coded_val);
+	regmap_fields_write(fields->pulse, conf->cs, val);
+
+	coded_val = at91sam9_smc_cycle_ns_to_cycles(clk_rate,
+						    timings->nrd_cycle_ns);
+	val = AT91SAM9_SMC_NRDCYCLE(coded_val);
+	coded_val = at91sam9_smc_cycle_ns_to_cycles(clk_rate,
+						    timings->nwe_cycle_ns);
+	val |= AT91SAM9_SMC_NWECYCLE(coded_val);
+	regmap_fields_write(fields->cycle, conf->cs, val);
+
+	val = DIV_ROUND_UP(timings->tdf_ns, clk_rate);
+	if (val > AT91_SMC_TDF_MAX)
+		val = AT91_SMC_TDF_MAX;
+	regmap_fields_write(fields->mode, conf->cs,
+			    config->mode | AT91_SMC_TDF_(val));
+
+	return 0;
+}
+
+static int at91sam9_ebi_init(struct at91_ebi *ebi)
+{
+	struct at91sam9_smc_generic_fields *fields = &ebi->sam9;
+	struct reg_field field = REG_FIELD(0, 0, 31);
+
+	field.id_size = fls(ebi->caps->available_cs);
+	field.id_offset = AT91SAM9_SMC_GENERIC_BLK_SZ;
+
+	field.reg = AT91SAM9_SMC_SETUP(AT91SAM9_SMC_GENERIC);
+	fields->setup = devm_regmap_field_alloc(ebi->dev, ebi->smc, field);
+	if (IS_ERR(fields->setup))
+		return PTR_ERR(fields->setup);
+
+	field.reg = AT91SAM9_SMC_PULSE(AT91SAM9_SMC_GENERIC);
+	fields->pulse = devm_regmap_field_alloc(ebi->dev, ebi->smc, field);
+	if (IS_ERR(fields->pulse))
+		return PTR_ERR(fields->pulse);
+
+	field.reg = AT91SAM9_SMC_CYCLE(AT91SAM9_SMC_GENERIC);
+	fields->cycle = devm_regmap_field_alloc(ebi->dev, ebi->smc, field);
+	if (IS_ERR(fields->cycle))
+		return PTR_ERR(fields->cycle);
+
+	field.reg = AT91SAM9_SMC_MODE(AT91SAM9_SMC_GENERIC);
+	fields->mode = devm_regmap_field_alloc(ebi->dev, ebi->smc, field);
+	if (IS_ERR(fields->mode))
+		return PTR_ERR(fields->mode);
+
+	return 0;
+}
+
+static int sama5d3_ebi_init(struct at91_ebi *ebi)
+{
+	struct at91sam9_smc_generic_fields *fields = &ebi->sam9;
+	struct reg_field field = REG_FIELD(0, 0, 31);
+
+	field.id_size = fls(ebi->caps->available_cs);
+	field.id_offset = SAMA5_SMC_GENERIC_BLK_SZ;
+
+	field.reg = AT91SAM9_SMC_SETUP(SAMA5_SMC_GENERIC);
+	fields->setup = devm_regmap_field_alloc(ebi->dev, ebi->smc, field);
+	if (IS_ERR(fields->setup))
+		return PTR_ERR(fields->setup);
+
+	field.reg = AT91SAM9_SMC_PULSE(SAMA5_SMC_GENERIC);
+	fields->pulse = devm_regmap_field_alloc(ebi->dev, ebi->smc, field);
+	if (IS_ERR(fields->pulse))
+		return PTR_ERR(fields->pulse);
+
+	field.reg = AT91SAM9_SMC_CYCLE(SAMA5_SMC_GENERIC);
+	fields->cycle = devm_regmap_field_alloc(ebi->dev, ebi->smc, field);
+	if (IS_ERR(fields->cycle))
+		return PTR_ERR(fields->cycle);
+
+	field.reg = SAMA5_SMC_MODE(SAMA5_SMC_GENERIC);
+	fields->mode = devm_regmap_field_alloc(ebi->dev, ebi->smc, field);
+	if (IS_ERR(fields->mode))
+		return PTR_ERR(fields->mode);
+
+	return 0;
+}
+
+static int at91_ebi_dev_setup(struct at91_ebi *ebi, struct device_node *np,
+			      int reg_cells)
+{
+	const struct at91_ebi_caps *caps = ebi->caps;
+	struct at91_ebi_dev_config conf = { };
+	struct device *dev = ebi->dev;
+	struct at91_ebi_dev *ebid;
+	int ret, numcs = 0, i;
+	bool apply = false;
+
+	numcs = of_property_count_elems_of_size(np, "reg",
+						reg_cells * sizeof(u32));
+	if (numcs <= 0) {
+		dev_err(dev, "invalid reg property in %s\n", np->full_name);
+		return -EINVAL;
+	}
+
+	ebid = devm_kzalloc(ebi->dev,
+			    sizeof(*ebid) + (numcs * sizeof(*ebid->configs)),
+			    GFP_KERNEL);
+	if (!ebid)
+		return -ENOMEM;
+
+	ebid->ebi = ebi;
+
+	ret = caps->xlate_config(ebid, np, &conf);
+	if (ret < 0)
+		return ret;
+	else if (ret)
+		apply = true;
+
+	for (i = 0; i < numcs; i++) {
+		u32 cs;
+
+		ret = of_property_read_u32_index(np, "reg", i * reg_cells,
+						 &cs);
+		if (ret)
+			return ret;
+
+		if (cs > AT91_MATRIX_EBI_NUM_CS ||
+		    !(ebi->caps->available_cs & BIT(cs))) {
+			dev_err(dev, "invalid reg property in %s\n",
+				np->full_name);
+			return -EINVAL;
+		}
+
+		ebid->configs[i].cs = cs;
+
+		if (apply) {
+			conf.cs = cs;
+			ret = caps->apply_config(ebid, &conf);
+			if (ret)
+				return ret;
+		}
+
+		caps->get_config(ebid, &ebid->configs[i]);
+
+		/*
+		 * Attach the EBI device to the generic SMC logic if at least
+		 * one "atmel,smc-" property is present.
+		 */
+		if (ebi->ebi_csa && ret)
+			regmap_field_update_bits(ebi->ebi_csa,
+						 BIT(cs), 0);
+	}
+
+	list_add_tail(&ebid->node, &ebi->devs);
+
+	return 0;
+}
+
+static const struct reg_field at91sam9260_ebi_csa =
+				REG_FIELD(AT91SAM9260_MATRIX_EBICSA, 0,
+					  AT91_MATRIX_EBI_NUM_CS - 1);
+
+static const struct at91_ebi_caps at91sam9260_ebi_caps = {
+	.available_cs = 0xff,
+	.ebi_csa = &at91sam9260_ebi_csa,
+	.get_config = at91sam9_ebi_get_config,
+	.xlate_config = at91sam9_ebi_xslate_config,
+	.apply_config = at91sam9_ebi_apply_config,
+	.init = at91sam9_ebi_init,
+};
+
+static const struct reg_field at91sam9261_ebi_csa =
+				REG_FIELD(AT91SAM9261_MATRIX_EBICSA, 0,
+					  AT91_MATRIX_EBI_NUM_CS - 1);
+
+static const struct at91_ebi_caps at91sam9261_ebi_caps = {
+	.available_cs = 0xff,
+	.ebi_csa = &at91sam9261_ebi_csa,
+	.get_config = at91sam9_ebi_get_config,
+	.xlate_config = at91sam9_ebi_xslate_config,
+	.apply_config = at91sam9_ebi_apply_config,
+	.init = at91sam9_ebi_init,
+};
+
+static const struct reg_field at91sam9263_ebi0_csa =
+				REG_FIELD(AT91SAM9263_MATRIX_EBI0CSA, 0,
+					  AT91_MATRIX_EBI_NUM_CS - 1);
+
+static const struct at91_ebi_caps at91sam9263_ebi0_caps = {
+	.available_cs = 0x3f,
+	.ebi_csa = &at91sam9263_ebi0_csa,
+	.get_config = at91sam9_ebi_get_config,
+	.xlate_config = at91sam9_ebi_xslate_config,
+	.apply_config = at91sam9_ebi_apply_config,
+	.init = at91sam9_ebi_init,
+};
+
+static const struct reg_field at91sam9263_ebi1_csa =
+				REG_FIELD(AT91SAM9263_MATRIX_EBI1CSA, 0,
+					  AT91_MATRIX_EBI_NUM_CS - 1);
+
+static const struct at91_ebi_caps at91sam9263_ebi1_caps = {
+	.available_cs = 0x7,
+	.ebi_csa = &at91sam9263_ebi1_csa,
+	.get_config = at91sam9_ebi_get_config,
+	.xlate_config = at91sam9_ebi_xslate_config,
+	.apply_config = at91sam9_ebi_apply_config,
+	.init = at91sam9_ebi_init,
+};
+
+static const struct reg_field at91sam9rl_ebi_csa =
+				REG_FIELD(AT91SAM9RL_MATRIX_EBICSA, 0,
+					  AT91_MATRIX_EBI_NUM_CS - 1);
+
+static const struct at91_ebi_caps at91sam9rl_ebi_caps = {
+	.available_cs = 0x3f,
+	.ebi_csa = &at91sam9rl_ebi_csa,
+	.get_config = at91sam9_ebi_get_config,
+	.xlate_config = at91sam9_ebi_xslate_config,
+	.apply_config = at91sam9_ebi_apply_config,
+	.init = at91sam9_ebi_init,
+};
+
+static const struct reg_field at91sam9g45_ebi_csa =
+				REG_FIELD(AT91SAM9G45_MATRIX_EBICSA, 0,
+					  AT91_MATRIX_EBI_NUM_CS - 1);
+
+static const struct at91_ebi_caps at91sam9g45_ebi_caps = {
+	.available_cs = 0x3f,
+	.ebi_csa = &at91sam9g45_ebi_csa,
+	.get_config = at91sam9_ebi_get_config,
+	.xlate_config = at91sam9_ebi_xslate_config,
+	.apply_config = at91sam9_ebi_apply_config,
+	.init = at91sam9_ebi_init,
+};
+
+static const struct at91_ebi_caps at91sam9x5_ebi_caps = {
+	.available_cs = 0x3f,
+	.ebi_csa = &at91sam9263_ebi0_csa,
+	.get_config = at91sam9_ebi_get_config,
+	.xlate_config = at91sam9_ebi_xslate_config,
+	.apply_config = at91sam9_ebi_apply_config,
+	.init = at91sam9_ebi_init,
+};
+
+static const struct at91_ebi_caps sama5d3_ebi_caps = {
+	.available_cs = 0xf,
+	.get_config = at91sam9_ebi_get_config,
+	.xlate_config = at91sam9_ebi_xslate_config,
+	.apply_config = at91sam9_ebi_apply_config,
+	.init = sama5d3_ebi_init,
+};
+
+static const struct of_device_id at91_ebi_id_table[] = {
+	{
+		.compatible = "atmel,at91sam9260-ebi",
+		.data = &at91sam9260_ebi_caps,
+	},
+	{
+		.compatible = "atmel,at91sam9261-ebi",
+		.data = &at91sam9261_ebi_caps,
+	},
+	{
+		.compatible = "atmel,at91sam9263-ebi0",
+		.data = &at91sam9263_ebi0_caps,
+	},
+	{
+		.compatible = "atmel,at91sam9263-ebi1",
+		.data = &at91sam9263_ebi1_caps,
+	},
+	{
+		.compatible = "atmel,at91sam9rl-ebi",
+		.data = &at91sam9rl_ebi_caps,
+	},
+	{
+		.compatible = "atmel,at91sam9g45-ebi",
+		.data = &at91sam9g45_ebi_caps,
+	},
+	{
+		.compatible = "atmel,at91sam9x5-ebi",
+		.data = &at91sam9x5_ebi_caps,
+	},
+	{
+		.compatible = "atmel,sama5d3-ebi",
+		.data = &sama5d3_ebi_caps,
+	},
+	{ /* sentinel */ }
+};
+
+static int at91_ebi_dev_disable(struct at91_ebi *ebi, struct device_node *np)
+{
+	struct device *dev = ebi->dev;
+	struct property *newprop;
+
+	newprop = devm_kzalloc(dev, sizeof(*newprop), GFP_KERNEL);
+	if (!newprop)
+		return -ENOMEM;
+
+	newprop->name = devm_kstrdup(dev, "status", GFP_KERNEL);
+	if (!newprop->name)
+		return -ENOMEM;
+
+	newprop->value = devm_kstrdup(dev, "disabled", GFP_KERNEL);
+	if (!newprop->name)
+		return -ENOMEM;
+
+	newprop->length = sizeof("disabled");
+
+	return of_update_property(np, newprop);
+}
+
+static int at91_ebi_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *child, *np = dev->of_node;
+	const struct of_device_id *match;
+	struct at91_ebi *ebi;
+	int ret, reg_cells;
+	struct clk *clk;
+	u32 val;
+
+	match = of_match_device(at91_ebi_id_table, dev);
+	if (!match || !match->data)
+		return -EINVAL;
+
+	ebi = devm_kzalloc(dev, sizeof(*ebi), GFP_KERNEL);
+	if (!ebi)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&ebi->devs);
+	ebi->caps = match->data;
+	ebi->dev = dev;
+
+	clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	ebi->clk = clk;
+
+	ebi->smc = syscon_regmap_lookup_by_phandle(np, "atmel,smc");
+	if (IS_ERR(ebi->smc))
+		return PTR_ERR(ebi->smc);
+
+	/*
+	 * The sama5d3 does not provide an EBICSA register and thus does need
+	 * to access the matrix registers.
+	 */
+	if (ebi->caps->ebi_csa) {
+		ebi->matrix =
+			syscon_regmap_lookup_by_phandle(np, "atmel,matrix");
+		if (IS_ERR(ebi->matrix))
+			return PTR_ERR(ebi->matrix);
+
+		ebi->ebi_csa = regmap_field_alloc(ebi->matrix,
+						  *ebi->caps->ebi_csa);
+		if (IS_ERR(ebi->ebi_csa))
+			return PTR_ERR(ebi->ebi_csa);
+	}
+
+	ret = ebi->caps->init(ebi);
+	if (ret)
+		return ret;
+
+	ret = of_property_read_u32(np, "#address-cells", &val);
+	if (ret) {
+		dev_err(dev, "missing #address-cells property\n");
+		return ret;
+	}
+
+	reg_cells = val;
+
+	ret = of_property_read_u32(np, "#size-cells", &val);
+	if (ret) {
+		dev_err(dev, "missing #address-cells property\n");
+		return ret;
+	}
+
+	reg_cells += val;
+
+	for_each_available_child_of_node(np, child) {
+		if (!of_find_property(child, "reg", NULL))
+			continue;
+
+		ret = at91_ebi_dev_setup(ebi, child, reg_cells);
+		if (ret) {
+			dev_err(dev, "failed to configure EBI bus for %s, disabling the device",
+				child->full_name);
+
+			ret = at91_ebi_dev_disable(ebi, child);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return of_platform_populate(np, NULL, NULL, dev);
+}
+
+static struct platform_driver at91_ebi_driver = {
+	.driver = {
+		.name = "atmel-ebi",
+		.of_match_table	= at91_ebi_id_table,
+	},
+};
+builtin_platform_driver_probe(at91_ebi_driver, at91_ebi_probe);
diff --git a/drivers/memory/atmel-sdramc.c b/drivers/memory/atmel-sdramc.c
index a3ebc8a87479..53a341f3b305 100644
--- a/drivers/memory/atmel-sdramc.c
+++ b/drivers/memory/atmel-sdramc.c
@@ -1,6 +1,8 @@
 /*
  * Atmel (Multi-port DDR-)SDRAM Controller driver
  *
+ * Author: Alexandre Belloni <alexandre.belloni@free-electrons.com>
+ *
  * Copyright (C) 2014 Atmel
  *
  * This program is free software: you can redistribute it and/or modify
@@ -20,7 +22,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 
@@ -48,7 +50,6 @@ static const struct of_device_id atmel_ramc_of_match[] = {
 	{ .compatible = "atmel,sama5d3-ddramc", .data = &sama5d3_caps, },
 	{},
 };
-MODULE_DEVICE_TABLE(of, atmel_ramc_of_match);
 
 static int atmel_ramc_probe(struct platform_device *pdev)
 {
@@ -90,8 +91,4 @@ static int __init atmel_ramc_init(void)
 {
 	return platform_driver_register(&atmel_ramc_driver);
 }
-module_init(atmel_ramc_init);
-
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Alexandre Belloni <alexandre.belloni@free-electrons.com>");
-MODULE_DESCRIPTION("Atmel (Multi-port DDR-)SDRAM Controller");
+device_initcall(atmel_ramc_init);
diff --git a/drivers/memory/fsl_ifc.c b/drivers/memory/fsl_ifc.c
index 904b4af5f142..1b182b117f9c 100644
--- a/drivers/memory/fsl_ifc.c
+++ b/drivers/memory/fsl_ifc.c
@@ -31,7 +31,9 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/fsl_ifc.h>
-#include <asm/prom.h>
+#include <linux/irqdomain.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
 
 struct fsl_ifc_ctrl *fsl_ifc_ctrl_dev;
 EXPORT_SYMBOL(fsl_ifc_ctrl_dev);
diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c
index f6b57579185a..4afbc412f959 100644
--- a/drivers/memory/mtk-smi.c
+++ b/drivers/memory/mtk-smi.c
@@ -21,19 +21,50 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <soc/mediatek/smi.h>
+#include <dt-bindings/memory/mt2701-larb-port.h>
 
 #define SMI_LARB_MMU_EN		0xf00
+#define REG_SMI_SECUR_CON_BASE		0x5c0
+
+/* every register control 8 port, register offset 0x4 */
+#define REG_SMI_SECUR_CON_OFFSET(id)	(((id) >> 3) << 2)
+#define REG_SMI_SECUR_CON_ADDR(id)	\
+	(REG_SMI_SECUR_CON_BASE + REG_SMI_SECUR_CON_OFFSET(id))
+
+/*
+ * every port have 4 bit to control, bit[port + 3] control virtual or physical,
+ * bit[port + 2 : port + 1] control the domain, bit[port] control the security
+ * or non-security.
+ */
+#define SMI_SECUR_CON_VAL_MSK(id)	(~(0xf << (((id) & 0x7) << 2)))
+#define SMI_SECUR_CON_VAL_VIRT(id)	BIT((((id) & 0x7) << 2) + 3)
+/* mt2701 domain should be set to 3 */
+#define SMI_SECUR_CON_VAL_DOMAIN(id)	(0x3 << ((((id) & 0x7) << 2) + 1))
+
+struct mtk_smi_larb_gen {
+	int port_in_larb[MTK_LARB_NR_MAX + 1];
+	void (*config_port)(struct device *);
+};
 
 struct mtk_smi {
-	struct device	*dev;
-	struct clk	*clk_apb, *clk_smi;
+	struct device			*dev;
+	struct clk			*clk_apb, *clk_smi;
+	struct clk			*clk_async; /*only needed by mt2701*/
+	void __iomem			*smi_ao_base;
 };
 
 struct mtk_smi_larb { /* larb: local arbiter */
-	struct mtk_smi  smi;
-	void __iomem	*base;
-	struct device	*smi_common_dev;
-	u32		*mmu;
+	struct mtk_smi			smi;
+	void __iomem			*base;
+	struct device			*smi_common_dev;
+	const struct mtk_smi_larb_gen	*larb_gen;
+	int				larbid;
+	u32				*mmu;
+};
+
+enum mtk_smi_gen {
+	MTK_SMI_GEN1,
+	MTK_SMI_GEN2
 };
 
 static int mtk_smi_enable(const struct mtk_smi *smi)
@@ -71,6 +102,7 @@ static void mtk_smi_disable(const struct mtk_smi *smi)
 int mtk_smi_larb_get(struct device *larbdev)
 {
 	struct mtk_smi_larb *larb = dev_get_drvdata(larbdev);
+	const struct mtk_smi_larb_gen *larb_gen = larb->larb_gen;
 	struct mtk_smi *common = dev_get_drvdata(larb->smi_common_dev);
 	int ret;
 
@@ -87,7 +119,7 @@ int mtk_smi_larb_get(struct device *larbdev)
 	}
 
 	/* Configure the iommu info for this larb */
-	writel(*larb->mmu, larb->base + SMI_LARB_MMU_EN);
+	larb_gen->config_port(larbdev);
 
 	return 0;
 }
@@ -126,6 +158,45 @@ mtk_smi_larb_bind(struct device *dev, struct device *master, void *data)
 	return -ENODEV;
 }
 
+static void mtk_smi_larb_config_port(struct device *dev)
+{
+	struct mtk_smi_larb *larb = dev_get_drvdata(dev);
+
+	writel(*larb->mmu, larb->base + SMI_LARB_MMU_EN);
+}
+
+
+static void mtk_smi_larb_config_port_gen1(struct device *dev)
+{
+	struct mtk_smi_larb *larb = dev_get_drvdata(dev);
+	const struct mtk_smi_larb_gen *larb_gen = larb->larb_gen;
+	struct mtk_smi *common = dev_get_drvdata(larb->smi_common_dev);
+	int i, m4u_port_id, larb_port_num;
+	u32 sec_con_val, reg_val;
+
+	m4u_port_id = larb_gen->port_in_larb[larb->larbid];
+	larb_port_num = larb_gen->port_in_larb[larb->larbid + 1]
+			- larb_gen->port_in_larb[larb->larbid];
+
+	for (i = 0; i < larb_port_num; i++, m4u_port_id++) {
+		if (*larb->mmu & BIT(i)) {
+			/* bit[port + 3] controls the virtual or physical */
+			sec_con_val = SMI_SECUR_CON_VAL_VIRT(m4u_port_id);
+		} else {
+			/* do not need to enable m4u for this port */
+			continue;
+		}
+		reg_val = readl(common->smi_ao_base
+			+ REG_SMI_SECUR_CON_ADDR(m4u_port_id));
+		reg_val &= SMI_SECUR_CON_VAL_MSK(m4u_port_id);
+		reg_val |= sec_con_val;
+		reg_val |= SMI_SECUR_CON_VAL_DOMAIN(m4u_port_id);
+		writel(reg_val,
+			common->smi_ao_base
+			+ REG_SMI_SECUR_CON_ADDR(m4u_port_id));
+	}
+}
+
 static void
 mtk_smi_larb_unbind(struct device *dev, struct device *master, void *data)
 {
@@ -137,6 +208,31 @@ static const struct component_ops mtk_smi_larb_component_ops = {
 	.unbind = mtk_smi_larb_unbind,
 };
 
+static const struct mtk_smi_larb_gen mtk_smi_larb_mt8173 = {
+	/* mt8173 do not need the port in larb */
+	.config_port = mtk_smi_larb_config_port,
+};
+
+static const struct mtk_smi_larb_gen mtk_smi_larb_mt2701 = {
+	.port_in_larb = {
+		LARB0_PORT_OFFSET, LARB1_PORT_OFFSET,
+		LARB2_PORT_OFFSET, LARB3_PORT_OFFSET
+	},
+	.config_port = mtk_smi_larb_config_port_gen1,
+};
+
+static const struct of_device_id mtk_smi_larb_of_ids[] = {
+	{
+		.compatible = "mediatek,mt8173-smi-larb",
+		.data = &mtk_smi_larb_mt8173
+	},
+	{
+		.compatible = "mediatek,mt2701-smi-larb",
+		.data = &mtk_smi_larb_mt2701
+	},
+	{}
+};
+
 static int mtk_smi_larb_probe(struct platform_device *pdev)
 {
 	struct mtk_smi_larb *larb;
@@ -144,14 +240,20 @@ static int mtk_smi_larb_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *smi_node;
 	struct platform_device *smi_pdev;
+	const struct of_device_id *of_id;
 
 	if (!dev->pm_domain)
 		return -EPROBE_DEFER;
 
+	of_id = of_match_node(mtk_smi_larb_of_ids, pdev->dev.of_node);
+	if (!of_id)
+		return -EINVAL;
+
 	larb = devm_kzalloc(dev, sizeof(*larb), GFP_KERNEL);
 	if (!larb)
 		return -ENOMEM;
 
+	larb->larb_gen = of_id->data;
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	larb->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(larb->base))
@@ -191,24 +293,34 @@ static int mtk_smi_larb_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id mtk_smi_larb_of_ids[] = {
-	{ .compatible = "mediatek,mt8173-smi-larb",},
-	{}
-};
-
 static struct platform_driver mtk_smi_larb_driver = {
 	.probe	= mtk_smi_larb_probe,
-	.remove = mtk_smi_larb_remove,
+	.remove	= mtk_smi_larb_remove,
 	.driver	= {
 		.name = "mtk-smi-larb",
 		.of_match_table = mtk_smi_larb_of_ids,
 	}
 };
 
+static const struct of_device_id mtk_smi_common_of_ids[] = {
+	{
+		.compatible = "mediatek,mt8173-smi-common",
+		.data = (void *)MTK_SMI_GEN2
+	},
+	{
+		.compatible = "mediatek,mt2701-smi-common",
+		.data = (void *)MTK_SMI_GEN1
+	},
+	{}
+};
+
 static int mtk_smi_common_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct mtk_smi *common;
+	struct resource *res;
+	const struct of_device_id *of_id;
+	enum mtk_smi_gen smi_gen;
 
 	if (!dev->pm_domain)
 		return -EPROBE_DEFER;
@@ -226,6 +338,29 @@ static int mtk_smi_common_probe(struct platform_device *pdev)
 	if (IS_ERR(common->clk_smi))
 		return PTR_ERR(common->clk_smi);
 
+	of_id = of_match_node(mtk_smi_common_of_ids, pdev->dev.of_node);
+	if (!of_id)
+		return -EINVAL;
+
+	/*
+	 * for mtk smi gen 1, we need to get the ao(always on) base to config
+	 * m4u port, and we need to enable the aync clock for transform the smi
+	 * clock into emi clock domain, but for mtk smi gen2, there's no smi ao
+	 * base.
+	 */
+	smi_gen = (enum mtk_smi_gen)of_id->data;
+	if (smi_gen == MTK_SMI_GEN1) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		common->smi_ao_base = devm_ioremap_resource(dev, res);
+		if (IS_ERR(common->smi_ao_base))
+			return PTR_ERR(common->smi_ao_base);
+
+		common->clk_async = devm_clk_get(dev, "async");
+		if (IS_ERR(common->clk_async))
+			return PTR_ERR(common->clk_async);
+
+		clk_prepare_enable(common->clk_async);
+	}
 	pm_runtime_enable(dev);
 	platform_set_drvdata(pdev, common);
 	return 0;
@@ -237,11 +372,6 @@ static int mtk_smi_common_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id mtk_smi_common_of_ids[] = {
-	{ .compatible = "mediatek,mt8173-smi-common", },
-	{}
-};
-
 static struct platform_driver mtk_smi_common_driver = {
 	.probe	= mtk_smi_common_probe,
 	.remove = mtk_smi_common_remove,
@@ -272,4 +402,5 @@ err_unreg_smi:
 	platform_driver_unregister(&mtk_smi_common_driver);
 	return ret;
 }
+
 subsys_initcall(mtk_smi_init);
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index 15508df24e5d..869c83fb3c5d 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -20,7 +20,6 @@
 #include <linux/ioport.h>
 #include <linux/spinlock.h>
 #include <linux/io.h>
-#include <linux/module.h>
 #include <linux/gpio/driver.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
@@ -1807,7 +1806,6 @@ static const struct of_device_id gpmc_dt_ids[] = {
 	{ .compatible = "ti,am3352-gpmc" },	/* am335x devices */
 	{ }
 };
-MODULE_DEVICE_TABLE(of, gpmc_dt_ids);
 
 /**
  * gpmc_read_settings_dt - read gpmc settings from device-tree
@@ -2134,8 +2132,7 @@ no_timings:
 	/* is child a common bus? */
 	if (of_match_node(of_default_bus_match_table, child))
 		/* create children and other common bus children */
-		if (of_platform_populate(child, of_default_bus_match_table,
-					 NULL, &pdev->dev))
+		if (of_platform_default_populate(child, NULL, &pdev->dev))
 			goto err_child_fail;
 
 	return 0;
@@ -2155,68 +2152,6 @@ err:
 	return ret;
 }
 
-static int gpmc_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
-{
-	return 1;	/* we're input only */
-}
-
-static int gpmc_gpio_direction_input(struct gpio_chip *chip,
-				     unsigned int offset)
-{
-	return 0;	/* we're input only */
-}
-
-static int gpmc_gpio_direction_output(struct gpio_chip *chip,
-				      unsigned int offset, int value)
-{
-	return -EINVAL;	/* we're input only */
-}
-
-static void gpmc_gpio_set(struct gpio_chip *chip, unsigned int offset,
-			  int value)
-{
-}
-
-static int gpmc_gpio_get(struct gpio_chip *chip, unsigned int offset)
-{
-	u32 reg;
-
-	offset += 8;
-
-	reg = gpmc_read_reg(GPMC_STATUS) & BIT(offset);
-
-	return !!reg;
-}
-
-static int gpmc_gpio_init(struct gpmc_device *gpmc)
-{
-	int ret;
-
-	gpmc->gpio_chip.parent = gpmc->dev;
-	gpmc->gpio_chip.owner = THIS_MODULE;
-	gpmc->gpio_chip.label = DEVICE_NAME;
-	gpmc->gpio_chip.ngpio = gpmc_nr_waitpins;
-	gpmc->gpio_chip.get_direction = gpmc_gpio_get_direction;
-	gpmc->gpio_chip.direction_input = gpmc_gpio_direction_input;
-	gpmc->gpio_chip.direction_output = gpmc_gpio_direction_output;
-	gpmc->gpio_chip.set = gpmc_gpio_set;
-	gpmc->gpio_chip.get = gpmc_gpio_get;
-	gpmc->gpio_chip.base = -1;
-
-	ret = gpiochip_add(&gpmc->gpio_chip);
-	if (ret < 0) {
-		dev_err(gpmc->dev, "could not register gpio chip: %d\n", ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-static void gpmc_gpio_exit(struct gpmc_device *gpmc)
-{
-	gpiochip_remove(&gpmc->gpio_chip);
-}
-
 static int gpmc_probe_dt(struct platform_device *pdev)
 {
 	int ret;
@@ -2281,7 +2216,69 @@ static int gpmc_probe_dt_children(struct platform_device *pdev)
 {
 	return 0;
 }
-#endif
+#endif /* CONFIG_OF */
+
+static int gpmc_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
+{
+	return 1;	/* we're input only */
+}
+
+static int gpmc_gpio_direction_input(struct gpio_chip *chip,
+				     unsigned int offset)
+{
+	return 0;	/* we're input only */
+}
+
+static int gpmc_gpio_direction_output(struct gpio_chip *chip,
+				      unsigned int offset, int value)
+{
+	return -EINVAL;	/* we're input only */
+}
+
+static void gpmc_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			  int value)
+{
+}
+
+static int gpmc_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	u32 reg;
+
+	offset += 8;
+
+	reg = gpmc_read_reg(GPMC_STATUS) & BIT(offset);
+
+	return !!reg;
+}
+
+static int gpmc_gpio_init(struct gpmc_device *gpmc)
+{
+	int ret;
+
+	gpmc->gpio_chip.parent = gpmc->dev;
+	gpmc->gpio_chip.owner = THIS_MODULE;
+	gpmc->gpio_chip.label = DEVICE_NAME;
+	gpmc->gpio_chip.ngpio = gpmc_nr_waitpins;
+	gpmc->gpio_chip.get_direction = gpmc_gpio_get_direction;
+	gpmc->gpio_chip.direction_input = gpmc_gpio_direction_input;
+	gpmc->gpio_chip.direction_output = gpmc_gpio_direction_output;
+	gpmc->gpio_chip.set = gpmc_gpio_set;
+	gpmc->gpio_chip.get = gpmc_gpio_get;
+	gpmc->gpio_chip.base = -1;
+
+	ret = gpiochip_add(&gpmc->gpio_chip);
+	if (ret < 0) {
+		dev_err(gpmc->dev, "could not register gpio chip: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void gpmc_gpio_exit(struct gpmc_device *gpmc)
+{
+	gpiochip_remove(&gpmc->gpio_chip);
+}
 
 static int gpmc_probe(struct platform_device *pdev)
 {
@@ -2437,15 +2434,7 @@ static __init int gpmc_init(void)
 {
 	return platform_driver_register(&gpmc_driver);
 }
-
-static __exit void gpmc_exit(void)
-{
-	platform_driver_unregister(&gpmc_driver);
-
-}
-
 postcore_initcall(gpmc_init);
-module_exit(gpmc_exit);
 
 static struct omap3_gpmc_regs gpmc_context;
 
diff --git a/drivers/memory/samsung/exynos-srom.c b/drivers/memory/samsung/exynos-srom.c
index 96756fb4d6bd..bf827a666694 100644
--- a/drivers/memory/samsung/exynos-srom.c
+++ b/drivers/memory/samsung/exynos-srom.c
@@ -11,7 +11,7 @@
  */
 
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
@@ -91,17 +91,17 @@ static int exynos_srom_configure_bank(struct exynos_srom *srom,
 	if (width == 2)
 		cs |= 1 << EXYNOS_SROM_BW__DATAWIDTH__SHIFT;
 
-	bw = __raw_readl(srom->reg_base + EXYNOS_SROM_BW);
+	bw = readl_relaxed(srom->reg_base + EXYNOS_SROM_BW);
 	bw = (bw & ~(EXYNOS_SROM_BW__CS_MASK << bank)) | (cs << bank);
-	__raw_writel(bw, srom->reg_base + EXYNOS_SROM_BW);
+	writel_relaxed(bw, srom->reg_base + EXYNOS_SROM_BW);
 
-	__raw_writel(pmc | (timing[0] << EXYNOS_SROM_BCX__TACP__SHIFT) |
-		    (timing[1] << EXYNOS_SROM_BCX__TCAH__SHIFT) |
-		    (timing[2] << EXYNOS_SROM_BCX__TCOH__SHIFT) |
-		    (timing[3] << EXYNOS_SROM_BCX__TACC__SHIFT) |
-		    (timing[4] << EXYNOS_SROM_BCX__TCOS__SHIFT) |
-		    (timing[5] << EXYNOS_SROM_BCX__TACS__SHIFT),
-		    srom->reg_base + EXYNOS_SROM_BC0 + bank);
+	writel_relaxed(pmc | (timing[0] << EXYNOS_SROM_BCX__TACP__SHIFT) |
+		       (timing[1] << EXYNOS_SROM_BCX__TCAH__SHIFT) |
+		       (timing[2] << EXYNOS_SROM_BCX__TCOH__SHIFT) |
+		       (timing[3] << EXYNOS_SROM_BCX__TACC__SHIFT) |
+		       (timing[4] << EXYNOS_SROM_BCX__TCOS__SHIFT) |
+		       (timing[5] << EXYNOS_SROM_BCX__TACS__SHIFT),
+		       srom->reg_base + EXYNOS_SROM_BC0 + bank);
 
 	return 0;
 }
@@ -134,7 +134,7 @@ static int exynos_srom_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, srom);
 
 	srom->reg_offset = exynos_srom_alloc_reg_dump(exynos_srom_offsets,
-			sizeof(exynos_srom_offsets));
+			ARRAY_SIZE(exynos_srom_offsets));
 	if (!srom->reg_offset) {
 		iounmap(srom->reg_base);
 		return -ENOMEM;
@@ -159,16 +159,6 @@ static int exynos_srom_probe(struct platform_device *pdev)
 	return of_platform_populate(np, NULL, NULL, dev);
 }
 
-static int exynos_srom_remove(struct platform_device *pdev)
-{
-	struct exynos_srom *srom = platform_get_drvdata(pdev);
-
-	kfree(srom->reg_offset);
-	iounmap(srom->reg_base);
-
-	return 0;
-}
-
 #ifdef CONFIG_PM_SLEEP
 static void exynos_srom_save(void __iomem *base,
 				    struct exynos_srom_reg_dump *rd,
@@ -211,21 +201,16 @@ static const struct of_device_id of_exynos_srom_ids[] = {
 	},
 	{},
 };
-MODULE_DEVICE_TABLE(of, of_exynos_srom_ids);
 
 static SIMPLE_DEV_PM_OPS(exynos_srom_pm_ops, exynos_srom_suspend, exynos_srom_resume);
 
 static struct platform_driver exynos_srom_driver = {
 	.probe = exynos_srom_probe,
-	.remove = exynos_srom_remove,
 	.driver = {
 		.name = "exynos-srom",
 		.of_match_table = of_exynos_srom_ids,
 		.pm = &exynos_srom_pm_ops,
+		.suppress_bind_attrs = true,
 	},
 };
-module_platform_driver(exynos_srom_driver);
-
-MODULE_AUTHOR("Pankaj Dubey <pankaj.dubey@samsung.com>");
-MODULE_DESCRIPTION("Exynos SROM Controller Driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(exynos_srom_driver);
diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c
index a1ae0cc2b86d..a4803ac192bb 100644
--- a/drivers/memory/tegra/mc.c
+++ b/drivers/memory/tegra/mc.c
@@ -186,8 +186,10 @@ static int load_timings(struct tegra_mc *mc, struct device_node *node)
 		timing = &mc->timings[i++];
 
 		err = load_one_timing(mc, timing, child);
-		if (err)
+		if (err) {
+			of_node_put(child);
 			return err;
+		}
 	}
 
 	return 0;
@@ -206,15 +208,13 @@ static int tegra_mc_setup_timings(struct tegra_mc *mc)
 	for_each_child_of_node(mc->dev->of_node, node) {
 		err = of_property_read_u32(node, "nvidia,ram-code",
 					   &node_ram_code);
-		if (err || (node_ram_code != ram_code)) {
-			of_node_put(node);
+		if (err || (node_ram_code != ram_code))
 			continue;
-		}
 
 		err = load_timings(mc, node);
+		of_node_put(node);
 		if (err)
 			return err;
-		of_node_put(node);
 		break;
 	}
 
diff --git a/drivers/memory/tegra/tegra124-emc.c b/drivers/memory/tegra/tegra124-emc.c
index 3dac7be39654..06cc781ebac1 100644
--- a/drivers/memory/tegra/tegra124-emc.c
+++ b/drivers/memory/tegra/tegra124-emc.c
@@ -970,8 +970,10 @@ static int tegra_emc_load_timings_from_dt(struct tegra_emc *emc,
 		timing = &emc->timings[i++];
 
 		err = load_one_timing_from_dt(emc, timing, child);
-		if (err)
+		if (err) {
+			of_node_put(child);
 			return err;
+		}
 	}
 
 	sort(emc->timings, emc->num_timings, sizeof(*timing), cmp_timings,
@@ -995,10 +997,8 @@ tegra_emc_find_node_by_ram_code(struct device_node *node, u32 ram_code)
 		u32 value;
 
 		err = of_property_read_u32(np, "nvidia,ram-code", &value);
-		if (err || (value != ram_code)) {
-			of_node_put(np);
+		if (err || (value != ram_code))
 			continue;
-		}
 
 		return np;
 	}
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index 40bb8ae5853c..aacf584f2a42 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -2338,23 +2338,11 @@ static struct memstick_driver msb_driver = {
 	.resume   = msb_resume
 };
 
-static int major;
-
 static int __init msb_init(void)
 {
-	int rc = register_blkdev(0, DRIVER_NAME);
-
-	if (rc < 0) {
-		pr_err("failed to register major (error %d)\n", rc);
-		return rc;
-	}
-
-	major = rc;
-	rc = memstick_register_driver(&msb_driver);
-	if (rc) {
-		unregister_blkdev(major, DRIVER_NAME);
+	int rc = memstick_register_driver(&msb_driver);
+	if (rc)
 		pr_err("failed to register memstick driver (error %d)\n", rc);
-	}
 
 	return rc;
 }
@@ -2362,7 +2350,6 @@ static int __init msb_init(void)
 static void __exit msb_exit(void)
 {
 	memstick_unregister_driver(&msb_driver);
-	unregister_blkdev(major, DRIVER_NAME);
 	idr_destroy(&msb_disk_idr);
 }
 
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index ff031a7735a5..2d1fb6420592 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -18,6 +18,17 @@ config MFD_CS5535
 	  This is the core driver for CS5535/CS5536 MFD functions.  This is
           necessary for using the board's GPIO and MFGPT functionality.
 
+config MFD_ALTERA_A10SR
+	bool "Altera Arria10 DevKit System Resource chip"
+	depends on ARCH_SOCFPGA && SPI_MASTER=y && OF
+	select REGMAP_SPI
+	select MFD_CORE
+	help
+	  Support for the Altera Arria10 DevKit MAX5 System Resource chip
+	  using the SPI interface. This driver provides common support for
+	  accessing the external gpio extender (LEDs & buttons) and
+	  power supply alarms (hwmon).
+
 config MFD_ACT8945A
 	tristate "Active-semi ACT8945A"
 	select MFD_CORE
@@ -480,6 +491,8 @@ config MFD_KEMPLD
 		* COMe-cDC2 (microETXexpress-DC)
 		* COMe-cHL6
 		* COMe-cPC2 (microETXexpress-PC)
+		* COMe-cSL6
+		* COMe-mAL10
 		* COMe-mBT10
 		* COMe-mCT10
 		* COMe-mTT10 (nanoETXexpress-TT)
@@ -524,8 +537,8 @@ config MFD_88PM860X
 	  battery-charger under the corresponding menus.
 
 config MFD_MAX14577
-	bool "Maxim Semiconductor MAX14577/77836 MUIC + Charger Support"
-	depends on I2C=y
+	tristate "Maxim Semiconductor MAX14577/77836 MUIC + Charger Support"
+	depends on I2C
 	select MFD_CORE
 	select REGMAP_I2C
 	select REGMAP_IRQ
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 42a66e19e191..2ba3ba35f745 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -205,3 +205,5 @@ intel-soc-pmic-objs		:= intel_soc_pmic_core.o intel_soc_pmic_crc.o
 intel-soc-pmic-$(CONFIG_INTEL_PMC_IPC)	+= intel_soc_pmic_bxtwc.o
 obj-$(CONFIG_INTEL_SOC_PMIC)	+= intel-soc-pmic.o
 obj-$(CONFIG_MFD_MT6397)	+= mt6397-core.o
+
+obj-$(CONFIG_MFD_ALTERA_A10SR)	+= altera-a10sr.o
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index f3d689176fc2..589eebfc13df 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -1087,7 +1087,6 @@ static int ab8500_probe(struct platform_device *pdev)
 		"Vbus Detect (USB)",
 		"USB ID Detect",
 		"UART Factory Mode Detect"};
-	struct ab8500_platform_data *plat = dev_get_platdata(&pdev->dev);
 	const struct platform_device_id *platid = platform_get_device_id(pdev);
 	enum ab8500_version version = AB8500_VERSION_UNDEFINED;
 	struct device_node *np = pdev->dev.of_node;
@@ -1219,9 +1218,6 @@ static int ab8500_probe(struct platform_device *pdev)
 		pr_cont("None\n");
 	}
 
-	if (plat && plat->init)
-		plat->init(ab8500);
-
 	if (is_ab9540(ab8500)) {
 		ret = get_register_interruptible(ab8500, AB8500_CHARGER,
 			AB8500_CH_USBCH_STAT1_REG, &value);
diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c
index b9f0010309f9..207cc497958a 100644
--- a/drivers/mfd/ab8500-sysctrl.c
+++ b/drivers/mfd/ab8500-sysctrl.c
@@ -127,45 +127,11 @@ EXPORT_SYMBOL(ab8500_sysctrl_write);
 
 static int ab8500_sysctrl_probe(struct platform_device *pdev)
 {
-	struct ab8500 *ab8500 = dev_get_drvdata(pdev->dev.parent);
-	struct ab8500_platform_data *plat;
-	struct ab8500_sysctrl_platform_data *pdata;
-
-	plat = dev_get_platdata(pdev->dev.parent);
-
-	if (!plat)
-		return -EINVAL;
-
 	sysctrl_dev = &pdev->dev;
 
 	if (!pm_power_off)
 		pm_power_off = ab8500_power_off;
 
-	pdata = plat->sysctrl;
-	if (pdata) {
-		int last, ret, i, j;
-
-		if (is_ab8505(ab8500))
-			last = AB8500_SYSCLKREQ4RFCLKBUF;
-		else
-			last = AB8500_SYSCLKREQ8RFCLKBUF;
-
-		for (i = AB8500_SYSCLKREQ1RFCLKBUF; i <= last; i++) {
-			j = i - AB8500_SYSCLKREQ1RFCLKBUF;
-			ret = ab8500_sysctrl_write(i, 0xff,
-					pdata->initial_req_buf_config[j]);
-			dev_dbg(&pdev->dev,
-					"Setting SysClkReq%dRfClkBuf 0x%X\n",
-					j + 1,
-					pdata->initial_req_buf_config[j]);
-			if (ret < 0) {
-				dev_err(&pdev->dev,
-					"Can't set sysClkReq%dRfClkBuf: %d\n",
-					j + 1, ret);
-			}
-		}
-	}
-
 	return 0;
 }
 
diff --git a/drivers/mfd/altera-a10sr.c b/drivers/mfd/altera-a10sr.c
new file mode 100644
index 000000000000..c05aa4ff57fd
--- /dev/null
+++ b/drivers/mfd/altera-a10sr.c
@@ -0,0 +1,169 @@
+/*
+ * Copyright Intel Corporation (C) 2014-2016. All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * SPI access for Altera Arria10 MAX5 System Resource Chip
+ *
+ * Adapted from DA9052
+ */
+
+#include <linux/mfd/altera-a10sr.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/spi/spi.h>
+
+static const struct mfd_cell altr_a10sr_subdev_info[] = {
+	{
+		.name = "altr_a10sr_gpio",
+		.of_compatible = "altr,a10sr-gpio",
+	},
+};
+
+static bool altr_a10sr_reg_readable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ALTR_A10SR_VERSION_READ:
+	case ALTR_A10SR_LED_REG:
+	case ALTR_A10SR_PBDSW_REG:
+	case ALTR_A10SR_PBDSW_IRQ_REG:
+	case ALTR_A10SR_PWR_GOOD1_REG:
+	case ALTR_A10SR_PWR_GOOD2_REG:
+	case ALTR_A10SR_PWR_GOOD3_REG:
+	case ALTR_A10SR_FMCAB_REG:
+	case ALTR_A10SR_HPS_RST_REG:
+	case ALTR_A10SR_USB_QSPI_REG:
+	case ALTR_A10SR_SFPA_REG:
+	case ALTR_A10SR_SFPB_REG:
+	case ALTR_A10SR_I2C_M_REG:
+	case ALTR_A10SR_WARM_RST_REG:
+	case ALTR_A10SR_WR_KEY_REG:
+	case ALTR_A10SR_PMBUS_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool altr_a10sr_reg_writeable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ALTR_A10SR_LED_REG:
+	case ALTR_A10SR_PBDSW_IRQ_REG:
+	case ALTR_A10SR_FMCAB_REG:
+	case ALTR_A10SR_HPS_RST_REG:
+	case ALTR_A10SR_USB_QSPI_REG:
+	case ALTR_A10SR_SFPA_REG:
+	case ALTR_A10SR_SFPB_REG:
+	case ALTR_A10SR_WARM_RST_REG:
+	case ALTR_A10SR_WR_KEY_REG:
+	case ALTR_A10SR_PMBUS_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool altr_a10sr_reg_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ALTR_A10SR_PBDSW_REG:
+	case ALTR_A10SR_PBDSW_IRQ_REG:
+	case ALTR_A10SR_PWR_GOOD1_REG:
+	case ALTR_A10SR_PWR_GOOD2_REG:
+	case ALTR_A10SR_PWR_GOOD3_REG:
+	case ALTR_A10SR_HPS_RST_REG:
+	case ALTR_A10SR_I2C_M_REG:
+	case ALTR_A10SR_WARM_RST_REG:
+	case ALTR_A10SR_WR_KEY_REG:
+	case ALTR_A10SR_PMBUS_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+const struct regmap_config altr_a10sr_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.cache_type = REGCACHE_NONE,
+
+	.use_single_rw = true,
+	.read_flag_mask = 1,
+	.write_flag_mask = 0,
+
+	.max_register = ALTR_A10SR_WR_KEY_REG,
+	.readable_reg = altr_a10sr_reg_readable,
+	.writeable_reg = altr_a10sr_reg_writeable,
+	.volatile_reg = altr_a10sr_reg_volatile,
+
+};
+
+static int altr_a10sr_spi_probe(struct spi_device *spi)
+{
+	int ret;
+	struct altr_a10sr *a10sr;
+
+	a10sr = devm_kzalloc(&spi->dev, sizeof(*a10sr),
+			     GFP_KERNEL);
+	if (!a10sr)
+		return -ENOMEM;
+
+	spi->mode = SPI_MODE_3;
+	spi->bits_per_word = 8;
+	spi_setup(spi);
+
+	a10sr->dev = &spi->dev;
+
+	spi_set_drvdata(spi, a10sr);
+
+	a10sr->regmap = devm_regmap_init_spi(spi, &altr_a10sr_regmap_config);
+	if (IS_ERR(a10sr->regmap)) {
+		ret = PTR_ERR(a10sr->regmap);
+		dev_err(&spi->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = devm_mfd_add_devices(a10sr->dev, PLATFORM_DEVID_AUTO,
+				   altr_a10sr_subdev_info,
+				   ARRAY_SIZE(altr_a10sr_subdev_info),
+				   NULL, 0, NULL);
+	if (ret)
+		dev_err(a10sr->dev, "Failed to register sub-devices: %d\n",
+			ret);
+
+	return ret;
+}
+
+static const struct of_device_id altr_a10sr_spi_of_match[] = {
+	{ .compatible = "altr,a10sr" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, altr_a10sr_spi_of_match);
+
+static struct spi_driver altr_a10sr_spi_driver = {
+	.probe = altr_a10sr_spi_probe,
+	.driver = {
+		.name = "altr_a10sr",
+		.of_match_table = of_match_ptr(altr_a10sr_spi_of_match),
+	},
+};
+
+module_spi_driver(altr_a10sr_spi_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Thor Thayer <tthayer@opensource.altera.com>");
+MODULE_DESCRIPTION("Altera Arria10 DevKit System Resource MFD Driver");
diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c
index bf2717967597..e4f97b3c824b 100644
--- a/drivers/mfd/arizona-core.c
+++ b/drivers/mfd/arizona-core.c
@@ -1462,7 +1462,7 @@ int arizona_dev_init(struct arizona *arizona)
 	/* Set up for interrupts */
 	ret = arizona_irq_init(arizona);
 	if (ret != 0)
-		goto err_reset;
+		goto err_pm;
 
 	pm_runtime_set_autosuspend_delay(arizona->dev, 100);
 	pm_runtime_use_autosuspend(arizona->dev);
@@ -1486,6 +1486,8 @@ int arizona_dev_init(struct arizona *arizona)
 
 err_irq:
 	arizona_irq_exit(arizona);
+err_pm:
+	pm_runtime_disable(arizona->dev);
 err_reset:
 	arizona_enable_reset(arizona);
 	regulator_disable(arizona->dcvdd);
diff --git a/drivers/mfd/arizona-irq.c b/drivers/mfd/arizona-irq.c
index edeb4951366a..5e18d3c77582 100644
--- a/drivers/mfd/arizona-irq.c
+++ b/drivers/mfd/arizona-irq.c
@@ -109,8 +109,20 @@ static irqreturn_t arizona_irq_thread(int irq, void *data)
 	do {
 		poll = false;
 
-		if (arizona->aod_irq_chip)
-			handle_nested_irq(irq_find_mapping(arizona->virq, 0));
+		if (arizona->aod_irq_chip) {
+			/*
+			 * Check the AOD status register to determine whether
+			 * the nested IRQ handler should be called.
+			 */
+			ret = regmap_read(arizona->regmap,
+					  ARIZONA_AOD_IRQ1, &val);
+			if (ret)
+				dev_warn(arizona->dev,
+					"Failed to read AOD IRQ1 %d\n", ret);
+			else if (val)
+				handle_nested_irq(
+					irq_find_mapping(arizona->virq, 0));
+		}
 
 		/*
 		 * Check if one of the main interrupts is asserted and only
diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c
index e4e32978c377..fd80b0981f0f 100644
--- a/drivers/mfd/axp20x.c
+++ b/drivers/mfd/axp20x.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/err.h>
+#include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -93,7 +94,10 @@ static const struct regmap_range axp22x_writeable_ranges[] = {
 };
 
 static const struct regmap_range axp22x_volatile_ranges[] = {
+	regmap_reg_range(AXP20X_PWR_INPUT_STATUS, AXP20X_PWR_OP_MODE),
 	regmap_reg_range(AXP20X_IRQ1_EN, AXP20X_IRQ5_STATE),
+	regmap_reg_range(AXP22X_GPIO_STATE, AXP22X_GPIO_STATE),
+	regmap_reg_range(AXP20X_FG_RES, AXP20X_FG_RES),
 };
 
 static const struct regmap_access_table axp22x_writeable_table = {
@@ -157,6 +161,11 @@ static struct resource axp20x_usb_power_supply_resources[] = {
 	DEFINE_RES_IRQ_NAMED(AXP20X_IRQ_VBUS_NOT_VALID, "VBUS_NOT_VALID"),
 };
 
+static struct resource axp22x_usb_power_supply_resources[] = {
+	DEFINE_RES_IRQ_NAMED(AXP22X_IRQ_VBUS_PLUGIN, "VBUS_PLUGIN"),
+	DEFINE_RES_IRQ_NAMED(AXP22X_IRQ_VBUS_REMOVAL, "VBUS_REMOVAL"),
+};
+
 static struct resource axp22x_pek_resources[] = {
 	{
 		.name   = "PEK_DBR",
@@ -524,6 +533,11 @@ static struct mfd_cell axp22x_cells[] = {
 		.resources		= axp22x_pek_resources,
 	}, {
 		.name			= "axp20x-regulator",
+	}, {
+		.name		= "axp20x-usb-power-supply",
+		.of_compatible	= "x-powers,axp221-usb-power-supply",
+		.num_resources	= ARRAY_SIZE(axp22x_usb_power_supply_resources),
+		.resources	= axp22x_usb_power_supply_resources,
 	},
 };
 
@@ -664,6 +678,9 @@ static void axp20x_power_off(void)
 
 	regmap_write(axp20x_pm_power_off->regmap, AXP20X_OFF_CTRL,
 		     AXP20X_OFF);
+
+	/* Give capacitors etc. time to drain to avoid kernel panic msg. */
+	msleep(500);
 }
 
 int axp20x_match_device(struct axp20x_dev *axp20x)
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index c0a86aeb1733..388e268b9bcf 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -3094,8 +3094,7 @@ static void db8500_prcmu_update_cpufreq(void)
 	}
 }
 
-static int db8500_prcmu_register_ab8500(struct device *parent,
-					struct ab8500_platform_data *pdata)
+static int db8500_prcmu_register_ab8500(struct device *parent)
 {
 	struct device_node *np;
 	struct resource ab8500_resource;
@@ -3103,8 +3102,6 @@ static int db8500_prcmu_register_ab8500(struct device *parent,
 		.name = "ab8500-core",
 		.of_compatible = "stericsson,ab8500",
 		.id = AB8500_VERSION_AB8500,
-		.platform_data = pdata,
-		.pdata_size = sizeof(struct ab8500_platform_data),
 		.resources = &ab8500_resource,
 		.num_resources = 1,
 	};
@@ -3133,7 +3130,6 @@ static int db8500_prcmu_register_ab8500(struct device *parent,
 static int db8500_prcmu_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	struct prcmu_pdata *pdata = dev_get_platdata(&pdev->dev);
 	int irq = 0, err = 0;
 	struct resource *res;
 
@@ -3149,7 +3145,7 @@ static int db8500_prcmu_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 	init_prcm_registers();
-	dbx500_fw_version_init(pdev, pdata->version_offset);
+	dbx500_fw_version_init(pdev, DB8500_PRCMU_FW_VERSION_OFFSET);
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "prcmu-tcdm");
 	if (!res) {
 		dev_err(&pdev->dev, "no prcmu tcdm region provided\n");
@@ -3204,7 +3200,7 @@ static int db8500_prcmu_probe(struct platform_device *pdev)
 		}
 	}
 
-	err = db8500_prcmu_register_ab8500(&pdev->dev, pdata->ab_platdata);
+	err = db8500_prcmu_register_ab8500(&pdev->dev);
 	if (err) {
 		mfd_remove_devices(&pdev->dev);
 		pr_err("prcmu: Failed to add ab8500 subdevice\n");
diff --git a/drivers/mfd/dm355evm_msp.c b/drivers/mfd/dm355evm_msp.c
index 14661ec5ef7f..270e19c0bba1 100644
--- a/drivers/mfd/dm355evm_msp.c
+++ b/drivers/mfd/dm355evm_msp.c
@@ -199,11 +199,8 @@ static struct device *add_child(struct i2c_client *client, const char *name,
 	int			status;
 
 	pdev = platform_device_alloc(name, -1);
-	if (!pdev) {
-		dev_dbg(&client->dev, "can't alloc dev\n");
-		status = -ENOMEM;
-		goto err;
-	}
+	if (!pdev)
+		return ERR_PTR(-ENOMEM);
 
 	device_init_wakeup(&pdev->dev, can_wakeup);
 	pdev->dev.parent = &client->dev;
diff --git a/drivers/mfd/hi655x-pmic.c b/drivers/mfd/hi655x-pmic.c
index 05ddc7882362..0fc62995695b 100644
--- a/drivers/mfd/hi655x-pmic.c
+++ b/drivers/mfd/hi655x-pmic.c
@@ -24,19 +24,15 @@
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 
-static const struct mfd_cell hi655x_pmic_devs[] = {
-	{ .name = "hi655x-regulator", },
-};
-
 static const struct regmap_irq hi655x_irqs[] = {
-	{ .reg_offset = 0, .mask = OTMP_D1R_INT },
-	{ .reg_offset = 0, .mask = VSYS_2P5_R_INT },
-	{ .reg_offset = 0, .mask = VSYS_UV_D3R_INT },
-	{ .reg_offset = 0, .mask = VSYS_6P0_D200UR_INT },
-	{ .reg_offset = 0, .mask = PWRON_D4SR_INT },
-	{ .reg_offset = 0, .mask = PWRON_D20F_INT },
-	{ .reg_offset = 0, .mask = PWRON_D20R_INT },
-	{ .reg_offset = 0, .mask = RESERVE_INT },
+	{ .reg_offset = 0, .mask = OTMP_D1R_INT_MASK },
+	{ .reg_offset = 0, .mask = VSYS_2P5_R_INT_MASK },
+	{ .reg_offset = 0, .mask = VSYS_UV_D3R_INT_MASK },
+	{ .reg_offset = 0, .mask = VSYS_6P0_D200UR_INT_MASK },
+	{ .reg_offset = 0, .mask = PWRON_D4SR_INT_MASK },
+	{ .reg_offset = 0, .mask = PWRON_D20F_INT_MASK },
+	{ .reg_offset = 0, .mask = PWRON_D20R_INT_MASK },
+	{ .reg_offset = 0, .mask = RESERVE_INT_MASK },
 };
 
 static const struct regmap_irq_chip hi655x_irq_chip = {
@@ -45,6 +41,7 @@ static const struct regmap_irq_chip hi655x_irq_chip = {
 	.num_regs = 1,
 	.num_irqs = ARRAY_SIZE(hi655x_irqs),
 	.status_base = HI655X_IRQ_STAT_BASE,
+	.ack_base = HI655X_IRQ_STAT_BASE,
 	.mask_base = HI655X_IRQ_MASK_BASE,
 };
 
@@ -55,6 +52,34 @@ static struct regmap_config hi655x_regmap_config = {
 	.max_register = HI655X_BUS_ADDR(0xFFF),
 };
 
+static struct resource pwrkey_resources[] = {
+	{
+		.name	= "down",
+		.start	= PWRON_D20R_INT,
+		.end	= PWRON_D20R_INT,
+		.flags	= IORESOURCE_IRQ,
+	}, {
+		.name	= "up",
+		.start	= PWRON_D20F_INT,
+		.end	= PWRON_D20F_INT,
+		.flags	= IORESOURCE_IRQ,
+	}, {
+		.name	= "hold 4s",
+		.start	= PWRON_D4SR_INT,
+		.end	= PWRON_D4SR_INT,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static const struct mfd_cell hi655x_pmic_devs[] = {
+	{
+		.name		= "hi65xx-powerkey",
+		.num_resources	= ARRAY_SIZE(pwrkey_resources),
+		.resources	= &pwrkey_resources[0],
+	},
+	{	.name		= "hi655x-regulator", },
+};
+
 static void hi655x_local_irq_clear(struct regmap *map)
 {
 	int i;
@@ -80,12 +105,9 @@ static int hi655x_pmic_probe(struct platform_device *pdev)
 	pmic->dev = dev;
 
 	pmic->res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!pmic->res)
-		return -ENOENT;
-
 	base = devm_ioremap_resource(dev, pmic->res);
-	if (!base)
-		return -ENOMEM;
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 
 	pmic->regmap = devm_regmap_init_mmio_clk(dev, NULL, base,
 						 &hi655x_regmap_config);
@@ -123,7 +145,8 @@ static int hi655x_pmic_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, pmic);
 
 	ret = mfd_add_devices(dev, PLATFORM_DEVID_AUTO, hi655x_pmic_devs,
-			      ARRAY_SIZE(hi655x_pmic_devs), NULL, 0, NULL);
+			      ARRAY_SIZE(hi655x_pmic_devs), NULL, 0,
+			      regmap_irq_get_domain(pmic->irq_data));
 	if (ret) {
 		dev_err(dev, "Failed to register device %d\n", ret);
 		regmap_del_irq_chip(gpio_to_irq(pmic->gpio), pmic->irq_data);
diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c
index 05b924542ee2..da5722d7c540 100644
--- a/drivers/mfd/kempld-core.c
+++ b/drivers/mfd/kempld-core.c
@@ -624,6 +624,14 @@ static struct dmi_system_id kempld_dmi_table[] __initdata = {
 		.driver_data = (void *)&kempld_platform_data_generic,
 		.callback = kempld_create_platform_device,
 	}, {
+		.ident = "CSL6",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Kontron"),
+			DMI_MATCH(DMI_BOARD_NAME, "COMe-cSL6"),
+		},
+		.driver_data = (void *)&kempld_platform_data_generic,
+		.callback = kempld_create_platform_device,
+	}, {
 		.ident = "CVV6",
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Kontron"),
@@ -647,6 +655,14 @@ static struct dmi_system_id kempld_dmi_table[] __initdata = {
 		.driver_data = (void *)&kempld_platform_data_generic,
 		.callback = kempld_create_platform_device,
 	}, {
+		.ident = "MAL1",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Kontron"),
+			DMI_MATCH(DMI_BOARD_NAME, "COMe-mAL10"),
+		},
+		.driver_data = (void *)&kempld_platform_data_generic,
+		.callback = kempld_create_platform_device,
+	}, {
 		.ident = "MBR1",
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Kontron"),
diff --git a/drivers/mfd/max14577.c b/drivers/mfd/max14577.c
index 2280b3fdcf68..6c245128ab2e 100644
--- a/drivers/mfd/max14577.c
+++ b/drivers/mfd/max14577.c
@@ -561,7 +561,7 @@ static int __init max14577_i2c_init(void)
 
 	return i2c_add_driver(&max14577_i2c_driver);
 }
-subsys_initcall(max14577_i2c_init);
+module_init(max14577_i2c_init);
 
 static void __exit max14577_i2c_exit(void)
 {
diff --git a/drivers/mfd/max77620.c b/drivers/mfd/max77620.c
index f32fbb8e8129..258757e216c4 100644
--- a/drivers/mfd/max77620.c
+++ b/drivers/mfd/max77620.c
@@ -31,25 +31,25 @@
 #include <linux/interrupt.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/max77620.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
 
-static struct resource gpio_resources[] = {
+static const struct resource gpio_resources[] = {
 	DEFINE_RES_IRQ(MAX77620_IRQ_TOP_GPIO),
 };
 
-static struct resource power_resources[] = {
+static const struct resource power_resources[] = {
 	DEFINE_RES_IRQ(MAX77620_IRQ_LBT_MBATLOW),
 };
 
-static struct resource rtc_resources[] = {
+static const struct resource rtc_resources[] = {
 	DEFINE_RES_IRQ(MAX77620_IRQ_TOP_RTC),
 };
 
-static struct resource thermal_resources[] = {
+static const struct resource thermal_resources[] = {
 	DEFINE_RES_IRQ(MAX77620_IRQ_LBT_TJALRM1),
 	DEFINE_RES_IRQ(MAX77620_IRQ_LBT_TJALRM2),
 };
@@ -111,15 +111,6 @@ static const struct mfd_cell max20024_children[] = {
 	},
 };
 
-static struct regmap_irq_chip max77620_top_irq_chip = {
-	.name = "max77620-top",
-	.irqs = max77620_top_irqs,
-	.num_irqs = ARRAY_SIZE(max77620_top_irqs),
-	.num_regs = 2,
-	.status_base = MAX77620_REG_IRQTOP,
-	.mask_base = MAX77620_REG_IRQTOPM,
-};
-
 static const struct regmap_range max77620_readable_ranges[] = {
 	regmap_reg_range(MAX77620_REG_CNFGGLBL1, MAX77620_REG_DVSSD4),
 };
@@ -180,6 +171,51 @@ static const struct regmap_config max20024_regmap_config = {
 	.volatile_table = &max77620_volatile_table,
 };
 
+/*
+ * MAX77620 and MAX20024 has the following steps of the interrupt handling
+ * for TOP interrupts:
+ * 1. When interrupt occurs from PMIC, mask the PMIC interrupt by setting GLBLM.
+ * 2. Read IRQTOP and service the interrupt.
+ * 3. Once all interrupts has been checked and serviced, the interrupt service
+ *    routine un-masks the hardware interrupt line by clearing GLBLM.
+ */
+static int max77620_irq_global_mask(void *irq_drv_data)
+{
+	struct max77620_chip *chip = irq_drv_data;
+	int ret;
+
+	ret = regmap_update_bits(chip->rmap, MAX77620_REG_INTENLBT,
+				 MAX77620_GLBLM_MASK, MAX77620_GLBLM_MASK);
+	if (ret < 0)
+		dev_err(chip->dev, "Failed to set GLBLM: %d\n", ret);
+
+	return ret;
+}
+
+static int max77620_irq_global_unmask(void *irq_drv_data)
+{
+	struct max77620_chip *chip = irq_drv_data;
+	int ret;
+
+	ret = regmap_update_bits(chip->rmap, MAX77620_REG_INTENLBT,
+				 MAX77620_GLBLM_MASK, 0);
+	if (ret < 0)
+		dev_err(chip->dev, "Failed to reset GLBLM: %d\n", ret);
+
+	return ret;
+}
+
+static struct regmap_irq_chip max77620_top_irq_chip = {
+	.name = "max77620-top",
+	.irqs = max77620_top_irqs,
+	.num_irqs = ARRAY_SIZE(max77620_top_irqs),
+	.num_regs = 2,
+	.status_base = MAX77620_REG_IRQTOP,
+	.mask_base = MAX77620_REG_IRQTOPM,
+	.handle_pre_irq = max77620_irq_global_mask,
+	.handle_post_irq = max77620_irq_global_unmask,
+};
+
 /* max77620_get_fps_period_reg_value:  Get FPS bit field value from
  *				       requested periods.
  * MAX77620 supports the FPS period of 40, 80, 160, 320, 540, 1280, 2560
@@ -433,6 +469,7 @@ static int max77620_probe(struct i2c_client *client,
 	if (ret < 0)
 		return ret;
 
+	max77620_top_irq_chip.irq_drv_data = chip;
 	ret = devm_regmap_add_irq_chip(chip->dev, chip->rmap, client->irq,
 				       IRQF_ONESHOT | IRQF_SHARED,
 				       chip->irq_base, &max77620_top_irq_chip,
@@ -568,7 +605,6 @@ static const struct i2c_device_id max77620_id[] = {
 	{"max20024", MAX20024},
 	{},
 };
-MODULE_DEVICE_TABLE(i2c, max77620_id);
 
 static const struct dev_pm_ops max77620_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(max77620_i2c_suspend, max77620_i2c_resume)
@@ -582,11 +618,4 @@ static struct i2c_driver max77620_driver = {
 	.probe = max77620_probe,
 	.id_table = max77620_id,
 };
-
-module_i2c_driver(max77620_driver);
-
-MODULE_DESCRIPTION("MAX77620/MAX20024 Multi Function Device Core Driver");
-MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
-MODULE_AUTHOR("Chaitanya Bandi <bandik@nvidia.com>");
-MODULE_AUTHOR("Mallikarjun Kasoju <mkasoju@nvidia.com>");
-MODULE_LICENSE("GPL v2");
+builtin_i2c_driver(max77620_driver);
diff --git a/drivers/mfd/max77843.c b/drivers/mfd/max77843.c
index 7cfc95b49c5d..dc5caeaaa6a1 100644
--- a/drivers/mfd/max77843.c
+++ b/drivers/mfd/max77843.c
@@ -15,7 +15,7 @@
 #include <linux/i2c.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/max77693-common.h>
 #include <linux/mfd/max77843-private.h>
@@ -171,19 +171,6 @@ err_pmic_id:
 	return ret;
 }
 
-static int max77843_remove(struct i2c_client *i2c)
-{
-	struct max77693_dev *max77843 = i2c_get_clientdata(i2c);
-
-	mfd_remove_devices(max77843->dev);
-
-	regmap_del_irq_chip(max77843->irq, max77843->irq_data_topsys);
-
-	i2c_unregister_device(max77843->i2c_chg);
-
-	return 0;
-}
-
 static const struct of_device_id max77843_dt_match[] = {
 	{ .compatible = "maxim,max77843", },
 	{ },
@@ -193,7 +180,6 @@ static const struct i2c_device_id max77843_id[] = {
 	{ "max77843", TYPE_MAX77843, },
 	{ },
 };
-MODULE_DEVICE_TABLE(i2c, max77843_id);
 
 static int __maybe_unused max77843_suspend(struct device *dev)
 {
@@ -226,9 +212,9 @@ static struct i2c_driver max77843_i2c_driver = {
 		.name = "max77843",
 		.pm = &max77843_pm,
 		.of_match_table = max77843_dt_match,
+		.suppress_bind_attrs = true,
 	},
 	.probe = max77843_probe,
-	.remove = max77843_remove,
 	.id_table = max77843_id,
 };
 
@@ -237,9 +223,3 @@ static int __init max77843_i2c_init(void)
 	return i2c_add_driver(&max77843_i2c_driver);
 }
 subsys_initcall(max77843_i2c_init);
-
-static void __exit max77843_i2c_exit(void)
-{
-	i2c_del_driver(&max77843_i2c_driver);
-}
-module_exit(max77843_i2c_exit);
diff --git a/drivers/mfd/max8925-i2c.c b/drivers/mfd/max8925-i2c.c
index 70443b161a5b..5c80aea3211f 100644
--- a/drivers/mfd/max8925-i2c.c
+++ b/drivers/mfd/max8925-i2c.c
@@ -9,7 +9,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
 #include <linux/mfd/max8925.h>
@@ -133,7 +133,6 @@ static const struct i2c_device_id max8925_id_table[] = {
 	{ "max8925", 0 },
 	{ },
 };
-MODULE_DEVICE_TABLE(i2c, max8925_id_table);
 
 static int max8925_dt_init(struct device_node *np, struct device *dev,
 			   struct max8925_platform_data *pdata)
@@ -240,7 +239,6 @@ static const struct of_device_id max8925_dt_ids[] = {
 	{ .compatible = "maxim,max8925", },
 	{},
 };
-MODULE_DEVICE_TABLE(of, max8925_dt_ids);
 
 static struct i2c_driver max8925_driver = {
 	.driver	= {
@@ -264,13 +262,3 @@ static int __init max8925_i2c_init(void)
 	return ret;
 }
 subsys_initcall(max8925_i2c_init);
-
-static void __exit max8925_i2c_exit(void)
-{
-	i2c_del_driver(&max8925_driver);
-}
-module_exit(max8925_i2c_exit);
-
-MODULE_DESCRIPTION("I2C Driver for Maxim 8925");
-MODULE_AUTHOR("Haojian Zhuang <haojian.zhuang@marvell.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c
index f316348e3d98..2d6e2c392786 100644
--- a/drivers/mfd/max8997.c
+++ b/drivers/mfd/max8997.c
@@ -2,7 +2,7 @@
  * max8997.c - mfd core driver for the Maxim 8966 and 8997
  *
  * Copyright (C) 2011 Samsung Electronics
- * MyungJoo Ham <myungjoo.ham@smasung.com>
+ * MyungJoo Ham <myungjoo.ham@samsung.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -28,7 +28,7 @@
 #include <linux/of_irq.h>
 #include <linux/interrupt.h>
 #include <linux/pm_runtime.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/max8997.h>
@@ -55,7 +55,6 @@ static const struct of_device_id max8997_pmic_dt_match[] = {
 	{ .compatible = "maxim,max8997-pmic", .data = (void *)TYPE_MAX8997 },
 	{},
 };
-MODULE_DEVICE_TABLE(of, max8997_pmic_dt_match);
 #endif
 
 int max8997_read_reg(struct i2c_client *i2c, u8 reg, u8 *dest)
@@ -263,24 +262,11 @@ err_i2c_haptic:
 	return ret;
 }
 
-static int max8997_i2c_remove(struct i2c_client *i2c)
-{
-	struct max8997_dev *max8997 = i2c_get_clientdata(i2c);
-
-	mfd_remove_devices(max8997->dev);
-	i2c_unregister_device(max8997->muic);
-	i2c_unregister_device(max8997->haptic);
-	i2c_unregister_device(max8997->rtc);
-
-	return 0;
-}
-
 static const struct i2c_device_id max8997_i2c_id[] = {
 	{ "max8997", TYPE_MAX8997 },
 	{ "max8966", TYPE_MAX8966 },
 	{ }
 };
-MODULE_DEVICE_TABLE(i2c, max8998_i2c_id);
 
 static u8 max8997_dumpaddr_pmic[] = {
 	MAX8997_REG_INT1MSK,
@@ -510,10 +496,10 @@ static struct i2c_driver max8997_i2c_driver = {
 	.driver = {
 		   .name = "max8997",
 		   .pm = &max8997_pm,
+		   .suppress_bind_attrs = true,
 		   .of_match_table = of_match_ptr(max8997_pmic_dt_match),
 	},
 	.probe = max8997_i2c_probe,
-	.remove = max8997_i2c_remove,
 	.id_table = max8997_i2c_id,
 };
 
@@ -523,13 +509,3 @@ static int __init max8997_i2c_init(void)
 }
 /* init early so consumer devices can complete system boot */
 subsys_initcall(max8997_i2c_init);
-
-static void __exit max8997_i2c_exit(void)
-{
-	i2c_del_driver(&max8997_i2c_driver);
-}
-module_exit(max8997_i2c_exit);
-
-MODULE_DESCRIPTION("MAXIM 8997 multi-function core driver");
-MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c
index ab28b29400f6..4c33b8063bc3 100644
--- a/drivers/mfd/max8998.c
+++ b/drivers/mfd/max8998.c
@@ -21,8 +21,6 @@
  */
 
 #include <linux/err.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
@@ -138,7 +136,6 @@ static const struct of_device_id max8998_dt_match[] = {
 	{ .compatible = "ti,lp3974", .data = (void *)TYPE_LP3974 },
 	{},
 };
-MODULE_DEVICE_TABLE(of, max8998_dt_match);
 #endif
 
 /*
@@ -254,23 +251,11 @@ err:
 	return ret;
 }
 
-static int max8998_i2c_remove(struct i2c_client *i2c)
-{
-	struct max8998_dev *max8998 = i2c_get_clientdata(i2c);
-
-	mfd_remove_devices(max8998->dev);
-	max8998_irq_exit(max8998);
-	i2c_unregister_device(max8998->rtc);
-
-	return 0;
-}
-
 static const struct i2c_device_id max8998_i2c_id[] = {
 	{ "max8998", TYPE_MAX8998 },
 	{ "lp3974", TYPE_LP3974},
 	{ }
 };
-MODULE_DEVICE_TABLE(i2c, max8998_i2c_id);
 
 static int max8998_suspend(struct device *dev)
 {
@@ -378,10 +363,10 @@ static struct i2c_driver max8998_i2c_driver = {
 	.driver = {
 		   .name = "max8998",
 		   .pm = &max8998_pm,
+		   .suppress_bind_attrs = true,
 		   .of_match_table = of_match_ptr(max8998_dt_match),
 	},
 	.probe = max8998_i2c_probe,
-	.remove = max8998_i2c_remove,
 	.id_table = max8998_i2c_id,
 };
 
@@ -391,13 +376,3 @@ static int __init max8998_i2c_init(void)
 }
 /* init early so consumer devices can complete system boot */
 subsys_initcall(max8998_i2c_init);
-
-static void __exit max8998_i2c_exit(void)
-{
-	i2c_del_driver(&max8998_i2c_driver);
-}
-module_exit(max8998_i2c_exit);
-
-MODULE_DESCRIPTION("MAXIM 8998 multi-function core driver");
-MODULE_AUTHOR("Kyungmin Park <kyungmin.park@samsung.com>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c
index c30290f33430..1aa74c4c3ced 100644
--- a/drivers/mfd/omap-usb-tll.c
+++ b/drivers/mfd/omap-usb-tll.c
@@ -30,6 +30,8 @@
 #include <linux/platform_data/usb-omap.h>
 #include <linux/of.h>
 
+#include "omap-usb.h"
+
 #define USBTLL_DRIVER_NAME	"usbhs_tll"
 
 /* TLL Register Set */
diff --git a/drivers/mfd/qcom_rpm.c b/drivers/mfd/qcom_rpm.c
index 1be47ad6441b..2e44323455dd 100644
--- a/drivers/mfd/qcom_rpm.c
+++ b/drivers/mfd/qcom_rpm.c
@@ -34,7 +34,13 @@ struct qcom_rpm_resource {
 struct qcom_rpm_data {
 	u32 version;
 	const struct qcom_rpm_resource *resource_table;
-	unsigned n_resources;
+	unsigned int n_resources;
+	unsigned int req_ctx_off;
+	unsigned int req_sel_off;
+	unsigned int ack_ctx_off;
+	unsigned int ack_sel_off;
+	unsigned int req_sel_size;
+	unsigned int ack_sel_size;
 };
 
 struct qcom_rpm {
@@ -61,17 +67,11 @@ struct qcom_rpm {
 
 #define RPM_REQUEST_TIMEOUT	(5 * HZ)
 
-#define RPM_REQUEST_CONTEXT	3
-#define RPM_REQ_SELECT		11
-#define RPM_ACK_CONTEXT		15
-#define RPM_ACK_SELECTOR	23
-#define RPM_SELECT_SIZE		7
+#define RPM_MAX_SEL_SIZE	7
 
 #define RPM_NOTIFICATION	BIT(30)
 #define RPM_REJECTED		BIT(31)
 
-#define RPM_SIGNAL		BIT(2)
-
 static const struct qcom_rpm_resource apq8064_rpm_resource_table[] = {
 	[QCOM_RPM_CXO_CLK] =			{ 25, 9, 5, 1 },
 	[QCOM_RPM_PXO_CLK] =			{ 26, 10, 6, 1 },
@@ -157,6 +157,12 @@ static const struct qcom_rpm_data apq8064_template = {
 	.version = 3,
 	.resource_table = apq8064_rpm_resource_table,
 	.n_resources = ARRAY_SIZE(apq8064_rpm_resource_table),
+	.req_ctx_off = 3,
+	.req_sel_off = 11,
+	.ack_ctx_off = 15,
+	.ack_sel_off = 23,
+	.req_sel_size = 4,
+	.ack_sel_size = 7,
 };
 
 static const struct qcom_rpm_resource msm8660_rpm_resource_table[] = {
@@ -240,6 +246,12 @@ static const struct qcom_rpm_data msm8660_template = {
 	.version = 2,
 	.resource_table = msm8660_rpm_resource_table,
 	.n_resources = ARRAY_SIZE(msm8660_rpm_resource_table),
+	.req_ctx_off = 3,
+	.req_sel_off = 11,
+	.ack_ctx_off = 19,
+	.ack_sel_off = 27,
+	.req_sel_size = 7,
+	.ack_sel_size = 7,
 };
 
 static const struct qcom_rpm_resource msm8960_rpm_resource_table[] = {
@@ -322,6 +334,12 @@ static const struct qcom_rpm_data msm8960_template = {
 	.version = 3,
 	.resource_table = msm8960_rpm_resource_table,
 	.n_resources = ARRAY_SIZE(msm8960_rpm_resource_table),
+	.req_ctx_off = 3,
+	.req_sel_off = 11,
+	.ack_ctx_off = 15,
+	.ack_sel_off = 23,
+	.req_sel_size = 4,
+	.ack_sel_size = 7,
 };
 
 static const struct qcom_rpm_resource ipq806x_rpm_resource_table[] = {
@@ -362,6 +380,12 @@ static const struct qcom_rpm_data ipq806x_template = {
 	.version = 3,
 	.resource_table = ipq806x_rpm_resource_table,
 	.n_resources = ARRAY_SIZE(ipq806x_rpm_resource_table),
+	.req_ctx_off = 3,
+	.req_sel_off = 11,
+	.ack_ctx_off = 15,
+	.ack_sel_off = 23,
+	.req_sel_size = 4,
+	.ack_sel_size = 7,
 };
 
 static const struct of_device_id qcom_rpm_of_match[] = {
@@ -380,7 +404,7 @@ int qcom_rpm_write(struct qcom_rpm *rpm,
 {
 	const struct qcom_rpm_resource *res;
 	const struct qcom_rpm_data *data = rpm->data;
-	u32 sel_mask[RPM_SELECT_SIZE] = { 0 };
+	u32 sel_mask[RPM_MAX_SEL_SIZE] = { 0 };
 	int left;
 	int ret = 0;
 	int i;
@@ -398,12 +422,12 @@ int qcom_rpm_write(struct qcom_rpm *rpm,
 		writel_relaxed(buf[i], RPM_REQ_REG(rpm, res->target_id + i));
 
 	bitmap_set((unsigned long *)sel_mask, res->select_id, 1);
-	for (i = 0; i < ARRAY_SIZE(sel_mask); i++) {
+	for (i = 0; i < rpm->data->req_sel_size; i++) {
 		writel_relaxed(sel_mask[i],
-			       RPM_CTRL_REG(rpm, RPM_REQ_SELECT + i));
+			       RPM_CTRL_REG(rpm, rpm->data->req_sel_off + i));
 	}
 
-	writel_relaxed(BIT(state), RPM_CTRL_REG(rpm, RPM_REQUEST_CONTEXT));
+	writel_relaxed(BIT(state), RPM_CTRL_REG(rpm, rpm->data->req_ctx_off));
 
 	reinit_completion(&rpm->ack);
 	regmap_write(rpm->ipc_regmap, rpm->ipc_offset, BIT(rpm->ipc_bit));
@@ -426,10 +450,11 @@ static irqreturn_t qcom_rpm_ack_interrupt(int irq, void *dev)
 	u32 ack;
 	int i;
 
-	ack = readl_relaxed(RPM_CTRL_REG(rpm, RPM_ACK_CONTEXT));
-	for (i = 0; i < RPM_SELECT_SIZE; i++)
-		writel_relaxed(0, RPM_CTRL_REG(rpm, RPM_ACK_SELECTOR + i));
-	writel(0, RPM_CTRL_REG(rpm, RPM_ACK_CONTEXT));
+	ack = readl_relaxed(RPM_CTRL_REG(rpm, rpm->data->ack_ctx_off));
+	for (i = 0; i < rpm->data->ack_sel_size; i++)
+		writel_relaxed(0,
+			RPM_CTRL_REG(rpm, rpm->data->ack_sel_off + i));
+	writel(0, RPM_CTRL_REG(rpm, rpm->data->ack_ctx_off));
 
 	if (ack & RPM_NOTIFICATION) {
 		dev_warn(rpm->dev, "ignoring notification!\n");
diff --git a/drivers/mfd/si476x-i2c.c b/drivers/mfd/si476x-i2c.c
index fb4ce6d04c30..c180b7533bba 100644
--- a/drivers/mfd/si476x-i2c.c
+++ b/drivers/mfd/si476x-i2c.c
@@ -600,7 +600,7 @@ static int si476x_core_fwver_to_revision(struct si476x_core *core,
 unknown_revision:
 	dev_err(&core->client->dev,
 		"Unsupported version of the firmware: %d.%d.%d, "
-		"reverting to A10 comptible functions\n",
+		"reverting to A10 compatible functions\n",
 		major, minor1, minor2);
 
 	return SI476X_REVISION_A10;
diff --git a/drivers/mfd/smsc-ece1099.c b/drivers/mfd/smsc-ece1099.c
index 7f89e89b8a5e..cd18c09827ef 100644
--- a/drivers/mfd/smsc-ece1099.c
+++ b/drivers/mfd/smsc-ece1099.c
@@ -36,7 +36,7 @@ static int smsc_i2c_probe(struct i2c_client *i2c,
 {
 	struct smsc *smsc;
 	int devid, rev, venid_l, venid_h;
-	int ret = 0;
+	int ret;
 
 	smsc = devm_kzalloc(&i2c->dev, sizeof(struct smsc),
 				GFP_KERNEL);
@@ -46,10 +46,8 @@ static int smsc_i2c_probe(struct i2c_client *i2c,
 	}
 
 	smsc->regmap = devm_regmap_init_i2c(i2c, &smsc_regmap_config);
-	if (IS_ERR(smsc->regmap)) {
-		ret = PTR_ERR(smsc->regmap);
-		goto err;
-	}
+	if (IS_ERR(smsc->regmap))
+		return PTR_ERR(smsc->regmap);
 
 	i2c_set_clientdata(i2c, smsc);
 	smsc->dev = &i2c->dev;
@@ -68,7 +66,7 @@ static int smsc_i2c_probe(struct i2c_client *i2c,
 
 	ret = regmap_write(smsc->regmap, SMSC_CLK_CTRL, smsc->clk);
 	if (ret)
-		goto err;
+		return ret;
 
 #ifdef CONFIG_OF
 	if (i2c->dev.of_node)
@@ -76,7 +74,6 @@ static int smsc_i2c_probe(struct i2c_client *i2c,
 					   NULL, NULL, &i2c->dev);
 #endif
 
-err:
 	return ret;
 }
 
diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c
index fb8f9e8b75df..94c7cc02fdab 100644
--- a/drivers/mfd/stmpe.c
+++ b/drivers/mfd/stmpe.c
@@ -23,6 +23,27 @@
 #include <linux/regulator/consumer.h>
 #include "stmpe.h"
 
+/**
+ * struct stmpe_platform_data - STMPE platform data
+ * @id: device id to distinguish between multiple STMPEs on the same board
+ * @blocks: bitmask of blocks to enable (use STMPE_BLOCK_*)
+ * @irq_trigger: IRQ trigger to use for the interrupt to the host
+ * @autosleep: bool to enable/disable stmpe autosleep
+ * @autosleep_timeout: inactivity timeout in milliseconds for autosleep
+ * @irq_over_gpio: true if gpio is used to get irq
+ * @irq_gpio: gpio number over which irq will be requested (significant only if
+ *	      irq_over_gpio is true)
+ */
+struct stmpe_platform_data {
+	int id;
+	unsigned int blocks;
+	unsigned int irq_trigger;
+	bool autosleep;
+	bool irq_over_gpio;
+	int irq_gpio;
+	int autosleep_timeout;
+};
+
 static int __stmpe_enable(struct stmpe *stmpe, unsigned int blocks)
 {
 	return stmpe->variant->enable(stmpe, blocks, true);
@@ -1187,24 +1208,19 @@ static void stmpe_of_probe(struct stmpe_platform_data *pdata,
 /* Called from client specific probe routines */
 int stmpe_probe(struct stmpe_client_info *ci, enum stmpe_partnum partnum)
 {
-	struct stmpe_platform_data *pdata = dev_get_platdata(ci->dev);
+	struct stmpe_platform_data *pdata;
 	struct device_node *np = ci->dev->of_node;
 	struct stmpe *stmpe;
 	int ret;
 
-	if (!pdata) {
-		if (!np)
-			return -EINVAL;
-
-		pdata = devm_kzalloc(ci->dev, sizeof(*pdata), GFP_KERNEL);
-		if (!pdata)
-			return -ENOMEM;
+	pdata = devm_kzalloc(ci->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
 
-		stmpe_of_probe(pdata, np);
+	stmpe_of_probe(pdata, np);
 
-		if (of_find_property(np, "interrupts", NULL) == NULL)
-			ci->irq = -1;
-	}
+	if (of_find_property(np, "interrupts", NULL) == NULL)
+		ci->irq = -1;
 
 	stmpe = devm_kzalloc(ci->dev, sizeof(struct stmpe), GFP_KERNEL);
 	if (!stmpe)
diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index e4e4b22eebc9..c8f027b4ea4c 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -27,20 +27,6 @@
 
 #include <linux/mfd/ti_am335x_tscadc.h>
 
-static unsigned int tscadc_readl(struct ti_tscadc_dev *tsadc, unsigned int reg)
-{
-	unsigned int val;
-
-	regmap_read(tsadc->regmap_tscadc, reg, &val);
-	return val;
-}
-
-static void tscadc_writel(struct ti_tscadc_dev *tsadc, unsigned int reg,
-					unsigned int val)
-{
-	regmap_write(tsadc->regmap_tscadc, reg, val);
-}
-
 static const struct regmap_config tscadc_regmap_config = {
 	.name = "ti_tscadc",
 	.reg_bits = 32,
@@ -48,89 +34,89 @@ static const struct regmap_config tscadc_regmap_config = {
 	.val_bits = 32,
 };
 
-void am335x_tsc_se_set_cache(struct ti_tscadc_dev *tsadc, u32 val)
+void am335x_tsc_se_set_cache(struct ti_tscadc_dev *tscadc, u32 val)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&tsadc->reg_lock, flags);
-	tsadc->reg_se_cache |= val;
-	if (tsadc->adc_waiting)
-		wake_up(&tsadc->reg_se_wait);
-	else if (!tsadc->adc_in_use)
-		tscadc_writel(tsadc, REG_SE, tsadc->reg_se_cache);
+	spin_lock_irqsave(&tscadc->reg_lock, flags);
+	tscadc->reg_se_cache |= val;
+	if (tscadc->adc_waiting)
+		wake_up(&tscadc->reg_se_wait);
+	else if (!tscadc->adc_in_use)
+		regmap_write(tscadc->regmap, REG_SE, tscadc->reg_se_cache);
 
-	spin_unlock_irqrestore(&tsadc->reg_lock, flags);
+	spin_unlock_irqrestore(&tscadc->reg_lock, flags);
 }
 EXPORT_SYMBOL_GPL(am335x_tsc_se_set_cache);
 
-static void am335x_tscadc_need_adc(struct ti_tscadc_dev *tsadc)
+static void am335x_tscadc_need_adc(struct ti_tscadc_dev *tscadc)
 {
 	DEFINE_WAIT(wait);
 	u32 reg;
 
-	reg = tscadc_readl(tsadc, REG_ADCFSM);
+	regmap_read(tscadc->regmap, REG_ADCFSM, &reg);
 	if (reg & SEQ_STATUS) {
-		tsadc->adc_waiting = true;
-		prepare_to_wait(&tsadc->reg_se_wait, &wait,
+		tscadc->adc_waiting = true;
+		prepare_to_wait(&tscadc->reg_se_wait, &wait,
 				TASK_UNINTERRUPTIBLE);
-		spin_unlock_irq(&tsadc->reg_lock);
+		spin_unlock_irq(&tscadc->reg_lock);
 
 		schedule();
 
-		spin_lock_irq(&tsadc->reg_lock);
-		finish_wait(&tsadc->reg_se_wait, &wait);
+		spin_lock_irq(&tscadc->reg_lock);
+		finish_wait(&tscadc->reg_se_wait, &wait);
 
 		/*
 		 * Sequencer should either be idle or
 		 * busy applying the charge step.
 		 */
-		reg = tscadc_readl(tsadc, REG_ADCFSM);
+		regmap_read(tscadc->regmap, REG_ADCFSM, &reg);
 		WARN_ON((reg & SEQ_STATUS) && !(reg & CHARGE_STEP));
-		tsadc->adc_waiting = false;
+		tscadc->adc_waiting = false;
 	}
-	tsadc->adc_in_use = true;
+	tscadc->adc_in_use = true;
 }
 
-void am335x_tsc_se_set_once(struct ti_tscadc_dev *tsadc, u32 val)
+void am335x_tsc_se_set_once(struct ti_tscadc_dev *tscadc, u32 val)
 {
-	spin_lock_irq(&tsadc->reg_lock);
-	am335x_tscadc_need_adc(tsadc);
+	spin_lock_irq(&tscadc->reg_lock);
+	am335x_tscadc_need_adc(tscadc);
 
-	tscadc_writel(tsadc, REG_SE, val);
-	spin_unlock_irq(&tsadc->reg_lock);
+	regmap_write(tscadc->regmap, REG_SE, val);
+	spin_unlock_irq(&tscadc->reg_lock);
 }
 EXPORT_SYMBOL_GPL(am335x_tsc_se_set_once);
 
-void am335x_tsc_se_adc_done(struct ti_tscadc_dev *tsadc)
+void am335x_tsc_se_adc_done(struct ti_tscadc_dev *tscadc)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&tsadc->reg_lock, flags);
-	tsadc->adc_in_use = false;
-	tscadc_writel(tsadc, REG_SE, tsadc->reg_se_cache);
-	spin_unlock_irqrestore(&tsadc->reg_lock, flags);
+	spin_lock_irqsave(&tscadc->reg_lock, flags);
+	tscadc->adc_in_use = false;
+	regmap_write(tscadc->regmap, REG_SE, tscadc->reg_se_cache);
+	spin_unlock_irqrestore(&tscadc->reg_lock, flags);
 }
 EXPORT_SYMBOL_GPL(am335x_tsc_se_adc_done);
 
-void am335x_tsc_se_clr(struct ti_tscadc_dev *tsadc, u32 val)
+void am335x_tsc_se_clr(struct ti_tscadc_dev *tscadc, u32 val)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&tsadc->reg_lock, flags);
-	tsadc->reg_se_cache &= ~val;
-	tscadc_writel(tsadc, REG_SE, tsadc->reg_se_cache);
-	spin_unlock_irqrestore(&tsadc->reg_lock, flags);
+	spin_lock_irqsave(&tscadc->reg_lock, flags);
+	tscadc->reg_se_cache &= ~val;
+	regmap_write(tscadc->regmap, REG_SE, tscadc->reg_se_cache);
+	spin_unlock_irqrestore(&tscadc->reg_lock, flags);
 }
 EXPORT_SYMBOL_GPL(am335x_tsc_se_clr);
 
-static void tscadc_idle_config(struct ti_tscadc_dev *config)
+static void tscadc_idle_config(struct ti_tscadc_dev *tscadc)
 {
 	unsigned int idleconfig;
 
 	idleconfig = STEPCONFIG_YNN | STEPCONFIG_INM_ADCREFM |
 			STEPCONFIG_INP_ADCREFM | STEPCONFIG_YPN;
 
-	tscadc_writel(config, REG_IDLECONFIG, idleconfig);
+	regmap_write(tscadc->regmap, REG_IDLECONFIG, idleconfig);
 }
 
 static	int ti_tscadc_probe(struct platform_device *pdev)
@@ -182,8 +168,7 @@ static	int ti_tscadc_probe(struct platform_device *pdev)
 	}
 
 	/* Allocate memory for device */
-	tscadc = devm_kzalloc(&pdev->dev,
-			sizeof(struct ti_tscadc_dev), GFP_KERNEL);
+	tscadc = devm_kzalloc(&pdev->dev, sizeof(*tscadc), GFP_KERNEL);
 	if (!tscadc) {
 		dev_err(&pdev->dev, "failed to allocate memory.\n");
 		return -ENOMEM;
@@ -202,11 +187,11 @@ static	int ti_tscadc_probe(struct platform_device *pdev)
 	if (IS_ERR(tscadc->tscadc_base))
 		return PTR_ERR(tscadc->tscadc_base);
 
-	tscadc->regmap_tscadc = devm_regmap_init_mmio(&pdev->dev,
+	tscadc->regmap = devm_regmap_init_mmio(&pdev->dev,
 			tscadc->tscadc_base, &tscadc_regmap_config);
-	if (IS_ERR(tscadc->regmap_tscadc)) {
+	if (IS_ERR(tscadc->regmap)) {
 		dev_err(&pdev->dev, "regmap init failed\n");
-		err = PTR_ERR(tscadc->regmap_tscadc);
+		err = PTR_ERR(tscadc->regmap);
 		goto ret;
 	}
 
@@ -236,11 +221,11 @@ static	int ti_tscadc_probe(struct platform_device *pdev)
 
 	/* TSCADC_CLKDIV needs to be configured to the value minus 1 */
 	tscadc->clk_div--;
-	tscadc_writel(tscadc, REG_CLKDIV, tscadc->clk_div);
+	regmap_write(tscadc->regmap, REG_CLKDIV, tscadc->clk_div);
 
 	/* Set the control register bits */
 	ctrl = CNTRLREG_STEPCONFIGWRT |	CNTRLREG_STEPID;
-	tscadc_writel(tscadc, REG_CTRL, ctrl);
+	regmap_write(tscadc->regmap, REG_CTRL, ctrl);
 
 	/* Set register bits for Idle Config Mode */
 	if (tsc_wires > 0) {
@@ -254,7 +239,7 @@ static	int ti_tscadc_probe(struct platform_device *pdev)
 
 	/* Enable the TSC module enable bit */
 	ctrl |= CNTRLREG_TSCSSENB;
-	tscadc_writel(tscadc, REG_CTRL, ctrl);
+	regmap_write(tscadc->regmap, REG_CTRL, ctrl);
 
 	tscadc->used_cells = 0;
 	tscadc->tsc_cell = -1;
@@ -300,7 +285,7 @@ static int ti_tscadc_remove(struct platform_device *pdev)
 {
 	struct ti_tscadc_dev	*tscadc = platform_get_drvdata(pdev);
 
-	tscadc_writel(tscadc, REG_SE, 0x00);
+	regmap_write(tscadc->regmap, REG_SE, 0x00);
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
@@ -310,51 +295,43 @@ static int ti_tscadc_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int tscadc_suspend(struct device *dev)
+static int __maybe_unused tscadc_suspend(struct device *dev)
 {
-	struct ti_tscadc_dev	*tscadc_dev = dev_get_drvdata(dev);
+	struct ti_tscadc_dev	*tscadc = dev_get_drvdata(dev);
 
-	tscadc_writel(tscadc_dev, REG_SE, 0x00);
+	regmap_write(tscadc->regmap, REG_SE, 0x00);
 	pm_runtime_put_sync(dev);
 
 	return 0;
 }
 
-static int tscadc_resume(struct device *dev)
+static int __maybe_unused tscadc_resume(struct device *dev)
 {
-	struct ti_tscadc_dev	*tscadc_dev = dev_get_drvdata(dev);
+	struct ti_tscadc_dev	*tscadc = dev_get_drvdata(dev);
 	u32 ctrl;
 
 	pm_runtime_get_sync(dev);
 
 	/* context restore */
 	ctrl = CNTRLREG_STEPCONFIGWRT |	CNTRLREG_STEPID;
-	tscadc_writel(tscadc_dev, REG_CTRL, ctrl);
+	regmap_write(tscadc->regmap, REG_CTRL, ctrl);
 
-	if (tscadc_dev->tsc_cell != -1) {
-		if (tscadc_dev->tsc_wires == 5)
+	if (tscadc->tsc_cell != -1) {
+		if (tscadc->tsc_wires == 5)
 			ctrl |= CNTRLREG_5WIRE | CNTRLREG_TSCENB;
 		else
 			ctrl |= CNTRLREG_4WIRE | CNTRLREG_TSCENB;
-		tscadc_idle_config(tscadc_dev);
+		tscadc_idle_config(tscadc);
 	}
 	ctrl |= CNTRLREG_TSCSSENB;
-	tscadc_writel(tscadc_dev, REG_CTRL, ctrl);
+	regmap_write(tscadc->regmap, REG_CTRL, ctrl);
 
-	tscadc_writel(tscadc_dev, REG_CLKDIV, tscadc_dev->clk_div);
+	regmap_write(tscadc->regmap, REG_CLKDIV, tscadc->clk_div);
 
 	return 0;
 }
 
-static const struct dev_pm_ops tscadc_pm_ops = {
-	.suspend = tscadc_suspend,
-	.resume = tscadc_resume,
-};
-#define TSCADC_PM_OPS (&tscadc_pm_ops)
-#else
-#define TSCADC_PM_OPS NULL
-#endif
+static SIMPLE_DEV_PM_OPS(tscadc_pm_ops, tscadc_suspend, tscadc_resume);
 
 static const struct of_device_id ti_tscadc_dt_ids[] = {
 	{ .compatible = "ti,am3359-tscadc", },
@@ -365,7 +342,7 @@ MODULE_DEVICE_TABLE(of, ti_tscadc_dt_ids);
 static struct platform_driver ti_tscadc_driver = {
 	.driver = {
 		.name   = "ti_am3359-tscadc",
-		.pm	= TSCADC_PM_OPS,
+		.pm	= &tscadc_pm_ops,
 		.of_match_table = ti_tscadc_dt_ids,
 	},
 	.probe	= ti_tscadc_probe,
diff --git a/drivers/mfd/tps6507x.c b/drivers/mfd/tps6507x.c
index 40beb2f4350c..1f308c4e3694 100644
--- a/drivers/mfd/tps6507x.c
+++ b/drivers/mfd/tps6507x.c
@@ -105,8 +105,8 @@ static int tps6507x_i2c_probe(struct i2c_client *i2c,
 }
 
 static const struct i2c_device_id tps6507x_i2c_id[] = {
-       { "tps6507x", 0 },
-       { }
+	{ "tps6507x", 0 },
+	{ }
 };
 MODULE_DEVICE_TABLE(i2c, tps6507x_i2c_id);
 
diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c
index 831696ee2472..a49d3db6d936 100644
--- a/drivers/mfd/twl-core.c
+++ b/drivers/mfd/twl-core.c
@@ -622,11 +622,8 @@ add_numbered_child(unsigned mod_no, const char *name, int num,
 	twl = &twl_priv->twl_modules[sid];
 
 	pdev = platform_device_alloc(name, num);
-	if (!pdev) {
-		dev_dbg(&twl->client->dev, "can't alloc dev\n");
-		status = -ENOMEM;
-		goto err;
-	}
+	if (!pdev)
+		return ERR_PTR(-ENOMEM);
 
 	pdev->dev.parent = &twl->client->dev;
 
@@ -634,7 +631,7 @@ add_numbered_child(unsigned mod_no, const char *name, int num,
 		status = platform_device_add_data(pdev, pdata, pdata_len);
 		if (status < 0) {
 			dev_dbg(&pdev->dev, "can't add platform_data\n");
-			goto err;
+			goto put_device;
 		}
 	}
 
@@ -647,21 +644,22 @@ add_numbered_child(unsigned mod_no, const char *name, int num,
 		status = platform_device_add_resources(pdev, r, irq1 ? 2 : 1);
 		if (status < 0) {
 			dev_dbg(&pdev->dev, "can't add irqs\n");
-			goto err;
+			goto put_device;
 		}
 	}
 
 	status = platform_device_add(pdev);
-	if (status == 0)
-		device_init_wakeup(&pdev->dev, can_wakeup);
+	if (status)
+		goto put_device;
+
+	device_init_wakeup(&pdev->dev, can_wakeup);
 
-err:
-	if (status < 0) {
-		platform_device_put(pdev);
-		dev_err(&twl->client->dev, "can't add %s dev\n", name);
-		return ERR_PTR(status);
-	}
 	return &pdev->dev;
+
+put_device:
+	platform_device_put(pdev);
+	dev_err(&twl->client->dev, "failed to add device %s\n", name);
+	return ERR_PTR(status);
 }
 
 static inline struct device *add_child(unsigned mod_no, const char *name,
diff --git a/drivers/mfd/twl6040.c b/drivers/mfd/twl6040.c
index 852d5874aabb..ab328ec49353 100644
--- a/drivers/mfd/twl6040.c
+++ b/drivers/mfd/twl6040.c
@@ -323,8 +323,7 @@ int twl6040_power(struct twl6040 *twl6040, int on)
 
 		/* Default PLL configuration after power up */
 		twl6040->pll = TWL6040_SYSCLK_SEL_LPPLL;
-		twl6040->sysclk = 19200000;
-		twl6040->mclk = 32768;
+		twl6040->sysclk_rate = 19200000;
 	} else {
 		/* already powered-down */
 		if (!twl6040->power_count) {
@@ -352,8 +351,12 @@ int twl6040_power(struct twl6040 *twl6040, int on)
 		regcache_cache_only(twl6040->regmap, true);
 		regcache_mark_dirty(twl6040->regmap);
 
-		twl6040->sysclk = 0;
-		twl6040->mclk = 0;
+		twl6040->sysclk_rate = 0;
+
+		if (twl6040->pll == TWL6040_SYSCLK_SEL_HPPLL) {
+			clk_disable_unprepare(twl6040->mclk);
+			twl6040->mclk_rate = 0;
+		}
 
 		clk_disable_unprepare(twl6040->clk32k);
 	}
@@ -377,15 +380,15 @@ int twl6040_set_pll(struct twl6040 *twl6040, int pll_id,
 
 	/* Force full reconfiguration when switching between PLL */
 	if (pll_id != twl6040->pll) {
-		twl6040->sysclk = 0;
-		twl6040->mclk = 0;
+		twl6040->sysclk_rate = 0;
+		twl6040->mclk_rate = 0;
 	}
 
 	switch (pll_id) {
 	case TWL6040_SYSCLK_SEL_LPPLL:
 		/* low-power PLL divider */
 		/* Change the sysclk configuration only if it has been canged */
-		if (twl6040->sysclk != freq_out) {
+		if (twl6040->sysclk_rate != freq_out) {
 			switch (freq_out) {
 			case 17640000:
 				lppllctl |= TWL6040_LPLLFIN;
@@ -427,6 +430,8 @@ int twl6040_set_pll(struct twl6040 *twl6040, int pll_id,
 			ret = -EINVAL;
 			goto pll_out;
 		}
+
+		clk_disable_unprepare(twl6040->mclk);
 		break;
 	case TWL6040_SYSCLK_SEL_HPPLL:
 		/* high-performance PLL can provide only 19.2 MHz */
@@ -437,7 +442,7 @@ int twl6040_set_pll(struct twl6040 *twl6040, int pll_id,
 			goto pll_out;
 		}
 
-		if (twl6040->mclk != freq_in) {
+		if (twl6040->mclk_rate != freq_in) {
 			hppllctl &= ~TWL6040_MCLK_MSK;
 
 			switch (freq_in) {
@@ -468,6 +473,9 @@ int twl6040_set_pll(struct twl6040 *twl6040, int pll_id,
 				goto pll_out;
 			}
 
+			/* When switching to HPPLL, enable the mclk first */
+			if (pll_id != twl6040->pll)
+				clk_prepare_enable(twl6040->mclk);
 			/*
 			 * enable clock slicer to ensure input waveform is
 			 * square
@@ -483,6 +491,8 @@ int twl6040_set_pll(struct twl6040 *twl6040, int pll_id,
 			lppllctl &= ~TWL6040_LPLLENA;
 			twl6040_reg_write(twl6040, TWL6040_REG_LPPLLCTL,
 					  lppllctl);
+
+			twl6040->mclk_rate = freq_in;
 		}
 		break;
 	default:
@@ -491,8 +501,7 @@ int twl6040_set_pll(struct twl6040 *twl6040, int pll_id,
 		goto pll_out;
 	}
 
-	twl6040->sysclk = freq_out;
-	twl6040->mclk = freq_in;
+	twl6040->sysclk_rate = freq_out;
 	twl6040->pll = pll_id;
 
 pll_out:
@@ -512,7 +521,7 @@ EXPORT_SYMBOL(twl6040_get_pll);
 
 unsigned int twl6040_get_sysclk(struct twl6040 *twl6040)
 {
-	return twl6040->sysclk;
+	return twl6040->sysclk_rate;
 }
 EXPORT_SYMBOL(twl6040_get_sysclk);
 
@@ -655,10 +664,18 @@ static int twl6040_probe(struct i2c_client *client,
 	if (IS_ERR(twl6040->clk32k)) {
 		if (PTR_ERR(twl6040->clk32k) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
-		dev_info(&client->dev, "clk32k is not handled\n");
+		dev_dbg(&client->dev, "clk32k is not handled\n");
 		twl6040->clk32k = NULL;
 	}
 
+	twl6040->mclk = devm_clk_get(&client->dev, "mclk");
+	if (IS_ERR(twl6040->mclk)) {
+		if (PTR_ERR(twl6040->mclk) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		dev_dbg(&client->dev, "mclk is not handled\n");
+		twl6040->mclk = NULL;
+	}
+
 	twl6040->supplies[0].supply = "vio";
 	twl6040->supplies[1].supply = "v2v1";
 	ret = devm_regulator_bulk_get(&client->dev, TWL6040_NUM_SUPPLIES,
diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig
index 8756d06e2bb8..b75cf830d08a 100644
--- a/drivers/misc/cxl/Kconfig
+++ b/drivers/misc/cxl/Kconfig
@@ -7,11 +7,7 @@ config CXL_BASE
 	default n
 	select PPC_COPRO_BASE
 
-config CXL_KERNEL_API
-	bool
-	default n
-
-config CXL_EEH
+config CXL_AFU_DRIVER_OPS
 	bool
 	default n
 
@@ -19,8 +15,7 @@ config CXL
 	tristate "Support for IBM Coherent Accelerators (CXL)"
 	depends on PPC_POWERNV && PCI_MSI && EEH
 	select CXL_BASE
-	select CXL_KERNEL_API
-	select CXL_EEH
+	select CXL_AFU_DRIVER_OPS
 	default m
 	help
 	  Select this option to enable driver support for IBM Coherent
@@ -33,3 +28,11 @@ config CXL
 	  CAPI adapters are found in POWER8 based systems.
 
 	  If unsure, say N.
+
+config CXL_BIMODAL
+	bool "Support for bi-modal CAPI cards"
+	depends on HOTPLUG_PCI_POWERNV = y && CXL || HOTPLUG_PCI_POWERNV = m && CXL = m
+	default y
+	help
+	  Select this option to enable support for bi-modal CAPI cards, such as
+	  the Mellanox CX-4.
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
index 8a55c1aa11aa..56e9a4732ef0 100644
--- a/drivers/misc/cxl/Makefile
+++ b/drivers/misc/cxl/Makefile
@@ -3,7 +3,7 @@ ccflags-$(CONFIG_PPC_WERROR)	+= -Werror
 
 cxl-y				+= main.o file.o irq.o fault.o native.o
 cxl-y				+= context.o sysfs.o debugfs.o pci.o trace.o
-cxl-y				+= vphb.o api.o
+cxl-y				+= vphb.o phb.o api.o
 cxl-$(CONFIG_PPC_PSERIES)	+= flash.o guest.o of.o hcalls.o
 obj-$(CONFIG_CXL)		+= cxl.o
 obj-$(CONFIG_CXL_BASE)		+= base.o
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 6d228ccd884d..f3d34b941f85 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -13,6 +13,8 @@
 #include <linux/file.h>
 #include <misc/cxl.h>
 #include <linux/fs.h>
+#include <asm/pnv-pci.h>
+#include <linux/msi.h>
 
 #include "cxl.h"
 
@@ -24,6 +26,8 @@ struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
 	int rc;
 
 	afu = cxl_pci_to_afu(dev);
+	if (IS_ERR(afu))
+		return ERR_CAST(afu);
 
 	ctx = cxl_context_alloc();
 	if (IS_ERR(ctx)) {
@@ -94,6 +98,42 @@ static irq_hw_number_t cxl_find_afu_irq(struct cxl_context *ctx, int num)
 	return 0;
 }
 
+int _cxl_next_msi_hwirq(struct pci_dev *pdev, struct cxl_context **ctx, int *afu_irq)
+{
+	if (*ctx == NULL || *afu_irq == 0) {
+		*afu_irq = 1;
+		*ctx = cxl_get_context(pdev);
+	} else {
+		(*afu_irq)++;
+		if (*afu_irq > cxl_get_max_irqs_per_process(pdev)) {
+			*ctx = list_next_entry(*ctx, extra_irq_contexts);
+			*afu_irq = 1;
+		}
+	}
+	return cxl_find_afu_irq(*ctx, *afu_irq);
+}
+/* Exported via cxl_base */
+
+int cxl_set_priv(struct cxl_context *ctx, void *priv)
+{
+	if (!ctx)
+		return -EINVAL;
+
+	ctx->priv = priv;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxl_set_priv);
+
+void *cxl_get_priv(struct cxl_context *ctx)
+{
+	if (!ctx)
+		return ERR_PTR(-EINVAL);
+
+	return ctx->priv;
+}
+EXPORT_SYMBOL_GPL(cxl_get_priv);
+
 int cxl_allocate_afu_irqs(struct cxl_context *ctx, int num)
 {
 	int res;
@@ -102,7 +142,10 @@ int cxl_allocate_afu_irqs(struct cxl_context *ctx, int num)
 	if (num == 0)
 		num = ctx->afu->pp_irqs;
 	res = afu_allocate_irqs(ctx, num);
-	if (!res && !cpu_has_feature(CPU_FTR_HVMODE)) {
+	if (res)
+		return res;
+
+	if (!cpu_has_feature(CPU_FTR_HVMODE)) {
 		/* In a guest, the PSL interrupt is not multiplexed. It was
 		 * allocated above, and we need to set its handler
 		 */
@@ -110,6 +153,13 @@ int cxl_allocate_afu_irqs(struct cxl_context *ctx, int num)
 		if (hwirq)
 			cxl_map_irq(ctx->afu->adapter, hwirq, cxl_ops->psl_interrupt, ctx, "psl");
 	}
+
+	if (ctx->status == STARTED) {
+		if (cxl_ops->update_ivtes)
+			cxl_ops->update_ivtes(ctx);
+		else WARN(1, "BUG: cxl_allocate_afu_irqs must be called prior to starting the context on this platform\n");
+	}
+
 	return res;
 }
 EXPORT_SYMBOL_GPL(cxl_allocate_afu_irqs);
@@ -323,6 +373,23 @@ struct cxl_context *cxl_fops_get_context(struct file *file)
 }
 EXPORT_SYMBOL_GPL(cxl_fops_get_context);
 
+void cxl_set_driver_ops(struct cxl_context *ctx,
+			struct cxl_afu_driver_ops *ops)
+{
+	WARN_ON(!ops->fetch_event || !ops->event_delivered);
+	atomic_set(&ctx->afu_driver_events, 0);
+	ctx->afu_driver_ops = ops;
+}
+EXPORT_SYMBOL_GPL(cxl_set_driver_ops);
+
+void cxl_context_events_pending(struct cxl_context *ctx,
+				unsigned int new_events)
+{
+	atomic_add(new_events, &ctx->afu_driver_events);
+	wake_up_all(&ctx->wq);
+}
+EXPORT_SYMBOL_GPL(cxl_context_events_pending);
+
 int cxl_start_work(struct cxl_context *ctx,
 		   struct cxl_ioctl_start_work *work)
 {
@@ -390,7 +457,106 @@ EXPORT_SYMBOL_GPL(cxl_perst_reloads_same_image);
 ssize_t cxl_read_adapter_vpd(struct pci_dev *dev, void *buf, size_t count)
 {
 	struct cxl_afu *afu = cxl_pci_to_afu(dev);
+	if (IS_ERR(afu))
+		return -ENODEV;
 
 	return cxl_ops->read_adapter_vpd(afu->adapter, buf, count);
 }
 EXPORT_SYMBOL_GPL(cxl_read_adapter_vpd);
+
+int cxl_set_max_irqs_per_process(struct pci_dev *dev, int irqs)
+{
+	struct cxl_afu *afu = cxl_pci_to_afu(dev);
+	if (IS_ERR(afu))
+		return -ENODEV;
+
+	if (irqs > afu->adapter->user_irqs)
+		return -EINVAL;
+
+	/* Limit user_irqs to prevent the user increasing this via sysfs */
+	afu->adapter->user_irqs = irqs;
+	afu->irqs_max = irqs;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxl_set_max_irqs_per_process);
+
+int cxl_get_max_irqs_per_process(struct pci_dev *dev)
+{
+	struct cxl_afu *afu = cxl_pci_to_afu(dev);
+	if (IS_ERR(afu))
+		return -ENODEV;
+
+	return afu->irqs_max;
+}
+EXPORT_SYMBOL_GPL(cxl_get_max_irqs_per_process);
+
+/*
+ * This is a special interrupt allocation routine called from the PHB's MSI
+ * setup function. When capi interrupts are allocated in this manner they must
+ * still be associated with a running context, but since the MSI APIs have no
+ * way to specify this we use the default context associated with the device.
+ *
+ * The Mellanox CX4 has a hardware limitation that restricts the maximum AFU
+ * interrupt number, so in order to overcome this their driver informs us of
+ * the restriction by setting the maximum interrupts per context, and we
+ * allocate additional contexts as necessary so that we can keep the AFU
+ * interrupt number within the supported range.
+ */
+int _cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	struct cxl_context *ctx, *new_ctx, *default_ctx;
+	int remaining;
+	int rc;
+
+	ctx = default_ctx = cxl_get_context(pdev);
+	if (WARN_ON(!default_ctx))
+		return -ENODEV;
+
+	remaining = nvec;
+	while (remaining > 0) {
+		rc = cxl_allocate_afu_irqs(ctx, min(remaining, ctx->afu->irqs_max));
+		if (rc) {
+			pr_warn("%s: Failed to find enough free MSIs\n", pci_name(pdev));
+			return rc;
+		}
+		remaining -= ctx->afu->irqs_max;
+
+		if (ctx != default_ctx && default_ctx->status == STARTED) {
+			WARN_ON(cxl_start_context(ctx,
+				be64_to_cpu(default_ctx->elem->common.wed),
+				NULL));
+		}
+
+		if (remaining > 0) {
+			new_ctx = cxl_dev_context_init(pdev);
+			if (!new_ctx) {
+				pr_warn("%s: Failed to allocate enough contexts for MSIs\n", pci_name(pdev));
+				return -ENOSPC;
+			}
+			list_add(&new_ctx->extra_irq_contexts, &ctx->extra_irq_contexts);
+			ctx = new_ctx;
+		}
+	}
+
+	return 0;
+}
+/* Exported via cxl_base */
+
+void _cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct cxl_context *ctx, *pos, *tmp;
+
+	ctx = cxl_get_context(pdev);
+	if (WARN_ON(!ctx))
+		return;
+
+	cxl_free_afu_irqs(ctx);
+	list_for_each_entry_safe(pos, tmp, &ctx->extra_irq_contexts, extra_irq_contexts) {
+		cxl_stop_context(pos);
+		cxl_free_afu_irqs(pos);
+		list_del(&pos->extra_irq_contexts);
+		cxl_release_context(pos);
+	}
+}
+/* Exported via cxl_base */
diff --git a/drivers/misc/cxl/base.c b/drivers/misc/cxl/base.c
index 9b90ec6c07cd..cd54ce6f6230 100644
--- a/drivers/misc/cxl/base.c
+++ b/drivers/misc/cxl/base.c
@@ -54,6 +54,19 @@ static inline void cxl_calls_put(struct cxl_calls *calls) { }
 
 #endif /* CONFIG_CXL_MODULE */
 
+/* AFU refcount management */
+struct cxl_afu *cxl_afu_get(struct cxl_afu *afu)
+{
+	return (get_device(&afu->dev) == NULL) ? NULL : afu;
+}
+EXPORT_SYMBOL_GPL(cxl_afu_get);
+
+void cxl_afu_put(struct cxl_afu *afu)
+{
+	put_device(&afu->dev);
+}
+EXPORT_SYMBOL_GPL(cxl_afu_put);
+
 void cxl_slbia(struct mm_struct *mm)
 {
 	struct cxl_calls *calls;
@@ -93,9 +106,92 @@ int cxl_update_properties(struct device_node *dn,
 }
 EXPORT_SYMBOL_GPL(cxl_update_properties);
 
+/*
+ * API calls into the driver that may be called from the PHB code and must be
+ * built in.
+ */
+bool cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu)
+{
+	bool ret;
+	struct cxl_calls *calls;
+
+	calls = cxl_calls_get();
+	if (!calls)
+		return false;
+
+	ret = calls->cxl_pci_associate_default_context(dev, afu);
+
+	cxl_calls_put(calls);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cxl_pci_associate_default_context);
+
+void cxl_pci_disable_device(struct pci_dev *dev)
+{
+	struct cxl_calls *calls;
+
+	calls = cxl_calls_get();
+	if (!calls)
+		return;
+
+	calls->cxl_pci_disable_device(dev);
+
+	cxl_calls_put(calls);
+}
+EXPORT_SYMBOL_GPL(cxl_pci_disable_device);
+
+int cxl_next_msi_hwirq(struct pci_dev *pdev, struct cxl_context **ctx, int *afu_irq)
+{
+	int ret;
+	struct cxl_calls *calls;
+
+	calls = cxl_calls_get();
+	if (!calls)
+		return -EBUSY;
+
+	ret = calls->cxl_next_msi_hwirq(pdev, ctx, afu_irq);
+
+	cxl_calls_put(calls);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cxl_next_msi_hwirq);
+
+int cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	int ret;
+	struct cxl_calls *calls;
+
+	calls = cxl_calls_get();
+	if (!calls)
+		return false;
+
+	ret = calls->cxl_cx4_setup_msi_irqs(pdev, nvec, type);
+
+	cxl_calls_put(calls);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cxl_cx4_setup_msi_irqs);
+
+void cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct cxl_calls *calls;
+
+	calls = cxl_calls_get();
+	if (!calls)
+		return;
+
+	calls->cxl_cx4_teardown_msi_irqs(pdev);
+
+	cxl_calls_put(calls);
+}
+EXPORT_SYMBOL_GPL(cxl_cx4_teardown_msi_irqs);
+
 static int __init cxl_base_init(void)
 {
-	struct device_node *np = NULL;
+	struct device_node *np;
 	struct platform_device *dev;
 	int count = 0;
 
@@ -105,8 +201,7 @@ static int __init cxl_base_init(void)
 	if (cpu_has_feature(CPU_FTR_HVMODE))
 		return 0;
 
-	while ((np = of_find_compatible_node(np, NULL,
-				     "ibm,coherent-platform-facility"))) {
+	for_each_compatible_node(np, NULL, "ibm,coherent-platform-facility") {
 		dev = of_platform_device_create(np, NULL, NULL);
 		if (dev)
 			count++;
@@ -114,5 +209,4 @@ static int __init cxl_base_init(void)
 	pr_devel("Found %d cxl device(s)\n", count);
 	return 0;
 }
-
-module_init(cxl_base_init);
+device_initcall(cxl_base_init);
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 26d206b1d08c..bdee9a01ef35 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -67,6 +67,9 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 	ctx->pending_fault = false;
 	ctx->pending_afu_err = false;
 
+	INIT_LIST_HEAD(&ctx->irq_names);
+	INIT_LIST_HEAD(&ctx->extra_irq_contexts);
+
 	/*
 	 * When we have to destroy all contexts in cxl_context_detach_all() we
 	 * end up with afu_release_irqs() called from inside a
@@ -87,7 +90,8 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 	 */
 	mutex_lock(&afu->contexts_lock);
 	idr_preload(GFP_KERNEL);
-	i = idr_alloc(&ctx->afu->contexts_idr, ctx, 0,
+	i = idr_alloc(&ctx->afu->contexts_idr, ctx,
+		      ctx->afu->adapter->native->sl_ops->min_pe,
 		      ctx->afu->num_procs, GFP_NOWAIT);
 	idr_preload_end();
 	mutex_unlock(&afu->contexts_lock);
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 4fe50788ff45..de090533f18c 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -24,6 +24,7 @@
 #include <asm/reg.h>
 #include <misc/cxl-base.h>
 
+#include <misc/cxl.h>
 #include <uapi/misc/cxl.h>
 
 extern uint cxl_verbose;
@@ -34,7 +35,7 @@ extern uint cxl_verbose;
  * Bump version each time a user API change is made, whether it is
  * backwards compatible ot not.
  */
-#define CXL_API_VERSION 2
+#define CXL_API_VERSION 3
 #define CXL_API_VERSION_COMPATIBLE 1
 
 /*
@@ -81,6 +82,7 @@ static const cxl_p1_reg_t CXL_PSL_TLBIA   = {0x00A8};
 static const cxl_p1_reg_t CXL_PSL_AFUSEL  = {0x00B0};
 
 /* 0x00C0:7EFF Implementation dependent area */
+/* PSL registers */
 static const cxl_p1_reg_t CXL_PSL_FIR1      = {0x0100};
 static const cxl_p1_reg_t CXL_PSL_FIR2      = {0x0108};
 static const cxl_p1_reg_t CXL_PSL_Timebase  = {0x0110};
@@ -91,6 +93,11 @@ static const cxl_p1_reg_t CXL_PSL_FIR_CNTL  = {0x0148};
 static const cxl_p1_reg_t CXL_PSL_DSNDCTL   = {0x0150};
 static const cxl_p1_reg_t CXL_PSL_SNWRALLOC = {0x0158};
 static const cxl_p1_reg_t CXL_PSL_TRACE     = {0x0170};
+/* XSL registers (Mellanox CX4) */
+static const cxl_p1_reg_t CXL_XSL_Timebase  = {0x0100};
+static const cxl_p1_reg_t CXL_XSL_TB_CTLSTAT = {0x0108};
+static const cxl_p1_reg_t CXL_XSL_FEC       = {0x0158};
+static const cxl_p1_reg_t CXL_XSL_DSNCTL    = {0x0168};
 /* 0x7F00:7FFF Reserved PCIe MSI-X Pending Bit Array area */
 /* 0x8000:FFFF Reserved PCIe MSI-X Table Area */
 
@@ -182,6 +189,18 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An     = {0x0A0};
 #define CXL_PSL_ID_An_F	(1ull << (63-31))
 #define CXL_PSL_ID_An_L	(1ull << (63-30))
 
+/****** CXL_PSL_SERR_An ****************************************************/
+#define CXL_PSL_SERR_An_afuto	(1ull << (63-0))
+#define CXL_PSL_SERR_An_afudis	(1ull << (63-1))
+#define CXL_PSL_SERR_An_afuov	(1ull << (63-2))
+#define CXL_PSL_SERR_An_badsrc	(1ull << (63-3))
+#define CXL_PSL_SERR_An_badctx	(1ull << (63-4))
+#define CXL_PSL_SERR_An_llcmdis	(1ull << (63-5))
+#define CXL_PSL_SERR_An_llcmdto	(1ull << (63-6))
+#define CXL_PSL_SERR_An_afupar	(1ull << (63-7))
+#define CXL_PSL_SERR_An_afudup	(1ull << (63-8))
+#define CXL_PSL_SERR_An_AE	(1ull << (63-30))
+
 /****** CXL_PSL_SCNTL_An ****************************************************/
 #define CXL_PSL_SCNTL_An_CR          (0x1ull << (63-15))
 /* Programming Modes: */
@@ -421,18 +440,6 @@ struct cxl_afu {
 	bool enabled;
 };
 
-/* AFU refcount management */
-static inline struct cxl_afu *cxl_afu_get(struct cxl_afu *afu)
-{
-
-	return (get_device(&afu->dev) == NULL) ? NULL : afu;
-}
-
-static inline void  cxl_afu_put(struct cxl_afu *afu)
-{
-	put_device(&afu->dev);
-}
-
 
 struct cxl_irq_name {
 	struct list_head list;
@@ -477,6 +484,9 @@ struct cxl_context {
 	/* Only used in PR mode */
 	u64 process_token;
 
+	/* driver private data */
+	void *priv;
+
 	unsigned long *irq_bitmap; /* Accessed from IRQ context */
 	struct cxl_irq_ranges irqs;
 	struct list_head irq_names;
@@ -522,7 +532,36 @@ struct cxl_context {
 	bool pending_fault;
 	bool pending_afu_err;
 
+	/* Used by AFU drivers for driver specific event delivery */
+	struct cxl_afu_driver_ops *afu_driver_ops;
+	atomic_t afu_driver_events;
+
 	struct rcu_head rcu;
+
+	/*
+	 * Only used when more interrupts are allocated via
+	 * pci_enable_msix_range than are supported in the default context, to
+	 * use additional contexts to overcome the limitation. i.e. Mellanox
+	 * CX4 only:
+	 */
+	struct list_head extra_irq_contexts;
+};
+
+struct cxl_service_layer_ops {
+	int (*adapter_regs_init)(struct cxl *adapter, struct pci_dev *dev);
+	int (*afu_regs_init)(struct cxl_afu *afu);
+	int (*register_serr_irq)(struct cxl_afu *afu);
+	void (*release_serr_irq)(struct cxl_afu *afu);
+	void (*debugfs_add_adapter_sl_regs)(struct cxl *adapter, struct dentry *dir);
+	void (*debugfs_add_afu_sl_regs)(struct cxl_afu *afu, struct dentry *dir);
+	void (*psl_irq_dump_registers)(struct cxl_context *ctx);
+	void (*err_irq_dump_registers)(struct cxl *adapter);
+	void (*debugfs_stop_trace)(struct cxl *adapter);
+	void (*write_timebase_ctrl)(struct cxl *adapter);
+	u64 (*timebase_read)(struct cxl *adapter);
+	int capi_mode;
+	bool needs_reset_before_disable;
+	int min_pe;
 };
 
 struct cxl_native {
@@ -533,6 +572,7 @@ struct cxl_native {
 	irq_hw_number_t err_hwirq;
 	unsigned int err_virq;
 	u64 ps_off;
+	const struct cxl_service_layer_ops *sl_ops;
 };
 
 struct cxl_guest {
@@ -688,9 +728,21 @@ static inline u64 cxl_p2n_read(struct cxl_afu *afu, cxl_p2n_reg_t reg)
 ssize_t cxl_pci_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
 				loff_t off, size_t count);
 
+/* Internal functions wrapped in cxl_base to allow PHB to call them */
+bool _cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu);
+void _cxl_pci_disable_device(struct pci_dev *dev);
+int _cxl_next_msi_hwirq(struct pci_dev *pdev, struct cxl_context **ctx, int *afu_irq);
+int _cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
+void _cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev);
 
 struct cxl_calls {
 	void (*cxl_slbia)(struct mm_struct *mm);
+	bool (*cxl_pci_associate_default_context)(struct pci_dev *dev, struct cxl_afu *afu);
+	void (*cxl_pci_disable_device)(struct pci_dev *dev);
+	int (*cxl_next_msi_hwirq)(struct pci_dev *pdev, struct cxl_context **ctx, int *afu_irq);
+	int (*cxl_cx4_setup_msi_irqs)(struct pci_dev *pdev, int nvec, int type);
+	void (*cxl_cx4_teardown_msi_irqs)(struct pci_dev *pdev);
+
 	struct module *owner;
 };
 int register_cxl_calls(struct cxl_calls *calls);
@@ -805,6 +857,11 @@ int cxl_tlb_slb_invalidate(struct cxl *adapter);
 int cxl_afu_disable(struct cxl_afu *afu);
 int cxl_psl_purge(struct cxl_afu *afu);
 
+void cxl_debugfs_add_adapter_psl_regs(struct cxl *adapter, struct dentry *dir);
+void cxl_debugfs_add_adapter_xsl_regs(struct cxl *adapter, struct dentry *dir);
+void cxl_debugfs_add_afu_psl_regs(struct cxl_afu *afu, struct dentry *dir);
+void cxl_native_psl_irq_dump_regs(struct cxl_context *ctx);
+void cxl_native_err_irq_dump_regs(struct cxl *adapter);
 void cxl_stop_trace(struct cxl *cxl);
 int cxl_pci_vphb_add(struct cxl_afu *afu);
 void cxl_pci_vphb_remove(struct cxl_afu *afu);
@@ -855,6 +912,7 @@ struct cxl_backend_ops {
 	int (*attach_process)(struct cxl_context *ctx, bool kernel,
 			u64 wed, u64 amr);
 	int (*detach_process)(struct cxl_context *ctx);
+	void (*update_ivtes)(struct cxl_context *ctx);
 	bool (*support_attributes)(const char *attr_name, enum cxl_attrs type);
 	bool (*link_ok)(struct cxl *cxl, struct cxl_afu *afu);
 	void (*release_afu)(struct device *dev);
@@ -879,4 +937,7 @@ extern const struct cxl_backend_ops *cxl_ops;
 
 /* check if the given pci_dev is on the the cxl vphb bus */
 bool cxl_pci_is_vphb_device(struct pci_dev *dev);
+
+/* decode AFU error bits in the PSL register PSL_SERR_An */
+void cxl_afu_decode_psl_serr(struct cxl_afu *afu, u64 serr);
 #endif
diff --git a/drivers/misc/cxl/debugfs.c b/drivers/misc/cxl/debugfs.c
index 5751899e0c17..ec7b8a017439 100644
--- a/drivers/misc/cxl/debugfs.c
+++ b/drivers/misc/cxl/debugfs.c
@@ -51,6 +51,19 @@ static struct dentry *debugfs_create_io_x64(const char *name, umode_t mode,
 	return debugfs_create_file(name, mode, parent, (void __force *)value, &fops_io_x64);
 }
 
+void cxl_debugfs_add_adapter_psl_regs(struct cxl *adapter, struct dentry *dir)
+{
+	debugfs_create_io_x64("fir1", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR1));
+	debugfs_create_io_x64("fir2", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR2));
+	debugfs_create_io_x64("fir_cntl", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR_CNTL));
+	debugfs_create_io_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_TRACE));
+}
+
+void cxl_debugfs_add_adapter_xsl_regs(struct cxl *adapter, struct dentry *dir)
+{
+	debugfs_create_io_x64("fec", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_XSL_FEC));
+}
+
 int cxl_debugfs_adapter_add(struct cxl *adapter)
 {
 	struct dentry *dir;
@@ -65,13 +78,10 @@ int cxl_debugfs_adapter_add(struct cxl *adapter)
 		return PTR_ERR(dir);
 	adapter->debugfs = dir;
 
-	debugfs_create_io_x64("fir1",     S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR1));
-	debugfs_create_io_x64("fir2",     S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR2));
-	debugfs_create_io_x64("fir_cntl", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR_CNTL));
 	debugfs_create_io_x64("err_ivte", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_ErrIVTE));
 
-	debugfs_create_io_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_TRACE));
-
+	if (adapter->native->sl_ops->debugfs_add_adapter_sl_regs)
+		adapter->native->sl_ops->debugfs_add_adapter_sl_regs(adapter, dir);
 	return 0;
 }
 
@@ -80,6 +90,14 @@ void cxl_debugfs_adapter_remove(struct cxl *adapter)
 	debugfs_remove_recursive(adapter->debugfs);
 }
 
+void cxl_debugfs_add_afu_psl_regs(struct cxl_afu *afu, struct dentry *dir)
+{
+	debugfs_create_io_x64("fir", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_FIR_SLICE_An));
+	debugfs_create_io_x64("serr", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SERR_An));
+	debugfs_create_io_x64("afu_debug", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_AFU_DEBUG_An));
+	debugfs_create_io_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SLICE_TRACE));
+}
+
 int cxl_debugfs_afu_add(struct cxl_afu *afu)
 {
 	struct dentry *dir;
@@ -94,18 +112,15 @@ int cxl_debugfs_afu_add(struct cxl_afu *afu)
 		return PTR_ERR(dir);
 	afu->debugfs = dir;
 
-	debugfs_create_io_x64("fir",        S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_FIR_SLICE_An));
-	debugfs_create_io_x64("serr",       S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SERR_An));
-	debugfs_create_io_x64("afu_debug",  S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_AFU_DEBUG_An));
 	debugfs_create_io_x64("sr",         S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SR_An));
-
 	debugfs_create_io_x64("dsisr",      S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_DSISR_An));
 	debugfs_create_io_x64("dar",        S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_DAR_An));
 	debugfs_create_io_x64("sstp0",      S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_SSTP0_An));
 	debugfs_create_io_x64("sstp1",      S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_SSTP1_An));
 	debugfs_create_io_x64("err_status", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_ErrStat_An));
 
-	debugfs_create_io_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SLICE_TRACE));
+	if (afu->adapter->native->sl_ops->debugfs_add_afu_sl_regs)
+		afu->adapter->native->sl_ops->debugfs_add_afu_sl_regs(afu, dir);
 
 	return 0;
 }
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index eec468f1612f..5fb9894b157f 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -293,6 +293,17 @@ int afu_mmap(struct file *file, struct vm_area_struct *vm)
 	return cxl_context_iomap(ctx, vm);
 }
 
+static inline bool ctx_event_pending(struct cxl_context *ctx)
+{
+	if (ctx->pending_irq || ctx->pending_fault || ctx->pending_afu_err)
+		return true;
+
+	if (ctx->afu_driver_ops && atomic_read(&ctx->afu_driver_events))
+		return true;
+
+	return false;
+}
+
 unsigned int afu_poll(struct file *file, struct poll_table_struct *poll)
 {
 	struct cxl_context *ctx = file->private_data;
@@ -305,8 +316,7 @@ unsigned int afu_poll(struct file *file, struct poll_table_struct *poll)
 	pr_devel("afu_poll wait done pe: %i\n", ctx->pe);
 
 	spin_lock_irqsave(&ctx->lock, flags);
-	if (ctx->pending_irq || ctx->pending_fault ||
-	    ctx->pending_afu_err)
+	if (ctx_event_pending(ctx))
 		mask |= POLLIN | POLLRDNORM;
 	else if (ctx->status == CLOSED)
 		/* Only error on closed when there are no futher events pending
@@ -319,16 +329,46 @@ unsigned int afu_poll(struct file *file, struct poll_table_struct *poll)
 	return mask;
 }
 
-static inline int ctx_event_pending(struct cxl_context *ctx)
+static ssize_t afu_driver_event_copy(struct cxl_context *ctx,
+				     char __user *buf,
+				     struct cxl_event *event,
+				     struct cxl_event_afu_driver_reserved *pl)
 {
-	return (ctx->pending_irq || ctx->pending_fault ||
-	    ctx->pending_afu_err || (ctx->status == CLOSED));
+	/* Check event */
+	if (!pl) {
+		ctx->afu_driver_ops->event_delivered(ctx, pl, -EINVAL);
+		return -EFAULT;
+	}
+
+	/* Check event size */
+	event->header.size += pl->data_size;
+	if (event->header.size > CXL_READ_MIN_SIZE) {
+		ctx->afu_driver_ops->event_delivered(ctx, pl, -EINVAL);
+		return -EFAULT;
+	}
+
+	/* Copy event header */
+	if (copy_to_user(buf, event, sizeof(struct cxl_event_header))) {
+		ctx->afu_driver_ops->event_delivered(ctx, pl, -EFAULT);
+		return -EFAULT;
+	}
+
+	/* Copy event data */
+	buf += sizeof(struct cxl_event_header);
+	if (copy_to_user(buf, &pl->data, pl->data_size)) {
+		ctx->afu_driver_ops->event_delivered(ctx, pl, -EFAULT);
+		return -EFAULT;
+	}
+
+	ctx->afu_driver_ops->event_delivered(ctx, pl, 0); /* Success */
+	return event->header.size;
 }
 
 ssize_t afu_read(struct file *file, char __user *buf, size_t count,
 			loff_t *off)
 {
 	struct cxl_context *ctx = file->private_data;
+	struct cxl_event_afu_driver_reserved *pl = NULL;
 	struct cxl_event event;
 	unsigned long flags;
 	int rc;
@@ -344,7 +384,7 @@ ssize_t afu_read(struct file *file, char __user *buf, size_t count,
 
 	for (;;) {
 		prepare_to_wait(&ctx->wq, &wait, TASK_INTERRUPTIBLE);
-		if (ctx_event_pending(ctx))
+		if (ctx_event_pending(ctx) || (ctx->status == CLOSED))
 			break;
 
 		if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu)) {
@@ -374,7 +414,12 @@ ssize_t afu_read(struct file *file, char __user *buf, size_t count,
 	memset(&event, 0, sizeof(event));
 	event.header.process_element = ctx->pe;
 	event.header.size = sizeof(struct cxl_event_header);
-	if (ctx->pending_irq) {
+	if (ctx->afu_driver_ops && atomic_read(&ctx->afu_driver_events)) {
+		pr_devel("afu_read delivering AFU driver specific event\n");
+		pl = ctx->afu_driver_ops->fetch_event(ctx);
+		atomic_dec(&ctx->afu_driver_events);
+		event.header.type = CXL_EVENT_AFU_DRIVER;
+	} else if (ctx->pending_irq) {
 		pr_devel("afu_read delivering AFU interrupt\n");
 		event.header.size += sizeof(struct cxl_event_afu_interrupt);
 		event.header.type = CXL_EVENT_AFU_INTERRUPT;
@@ -404,6 +449,9 @@ ssize_t afu_read(struct file *file, char __user *buf, size_t count,
 
 	spin_unlock_irqrestore(&ctx->lock, flags);
 
+	if (event.header.type == CXL_EVENT_AFU_DRIVER)
+		return afu_driver_event_copy(ctx, buf, &event, pl);
+
 	if (copy_to_user(buf, &event, event.header.size))
 		return -EFAULT;
 	return event.header.size;
@@ -558,7 +606,7 @@ int __init cxl_file_init(void)
 	 * If these change we really need to update API.  Either change some
 	 * flags or update API version number CXL_API_VERSION.
 	 */
-	BUILD_BUG_ON(CXL_API_VERSION != 2);
+	BUILD_BUG_ON(CXL_API_VERSION != 3);
 	BUILD_BUG_ON(sizeof(struct cxl_ioctl_start_work) != 64);
 	BUILD_BUG_ON(sizeof(struct cxl_event_header) != 8);
 	BUILD_BUG_ON(sizeof(struct cxl_event_afu_interrupt) != 8);
diff --git a/drivers/misc/cxl/flash.c b/drivers/misc/cxl/flash.c
index 68dd0b7da471..c63d61e17d56 100644
--- a/drivers/misc/cxl/flash.c
+++ b/drivers/misc/cxl/flash.c
@@ -24,8 +24,8 @@ struct ai_header {
 };
 
 static struct semaphore sem;
-unsigned long *buffer[CXL_AI_MAX_ENTRIES];
-struct sg_list *le;
+static unsigned long *buffer[CXL_AI_MAX_ENTRIES];
+static struct sg_list *le;
 static u64 continue_token;
 static unsigned int transfer;
 
diff --git a/drivers/misc/cxl/guest.c b/drivers/misc/cxl/guest.c
index bc8d0b9870eb..9aa58a77a24d 100644
--- a/drivers/misc/cxl/guest.c
+++ b/drivers/misc/cxl/guest.c
@@ -196,15 +196,18 @@ static irqreturn_t guest_slice_irq_err(int irq, void *data)
 {
 	struct cxl_afu *afu = data;
 	int rc;
-	u64 serr;
+	u64 serr, afu_error, dsisr;
 
-	WARN(irq, "CXL SLICE ERROR interrupt %i\n", irq);
 	rc = cxl_h_get_fn_error_interrupt(afu->guest->handle, &serr);
 	if (rc) {
 		dev_crit(&afu->dev, "Couldn't read PSL_SERR_An: %d\n", rc);
 		return IRQ_HANDLED;
 	}
-	dev_crit(&afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr);
+	afu_error = cxl_p2n_read(afu, CXL_AFU_ERR_An);
+	dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
+	cxl_afu_decode_psl_serr(afu, serr);
+	dev_crit(&afu->dev, "AFU_ERR_An: 0x%.16llx\n", afu_error);
+	dev_crit(&afu->dev, "PSL_DSISR_An: 0x%.16llx\n", dsisr);
 
 	rc = cxl_h_ack_fn_error_interrupt(afu->guest->handle, serr);
 	if (rc)
@@ -1052,16 +1055,18 @@ static void free_adapter(struct cxl *adapter)
 	struct irq_avail *cur;
 	int i;
 
-	if (adapter->guest->irq_avail) {
-		for (i = 0; i < adapter->guest->irq_nranges; i++) {
-			cur = &adapter->guest->irq_avail[i];
-			kfree(cur->bitmap);
+	if (adapter->guest) {
+		if (adapter->guest->irq_avail) {
+			for (i = 0; i < adapter->guest->irq_nranges; i++) {
+				cur = &adapter->guest->irq_avail[i];
+				kfree(cur->bitmap);
+			}
+			kfree(adapter->guest->irq_avail);
 		}
-		kfree(adapter->guest->irq_avail);
+		kfree(adapter->guest->status);
+		kfree(adapter->guest);
 	}
-	kfree(adapter->guest->status);
 	cxl_remove_adapter_nr(adapter);
-	kfree(adapter->guest);
 	kfree(adapter);
 }
 
@@ -1182,6 +1187,7 @@ const struct cxl_backend_ops cxl_guest_ops = {
 	.ack_irq = guest_ack_irq,
 	.attach_process = guest_attach_process,
 	.detach_process = guest_detach_process,
+	.update_ivtes = NULL,
 	.support_attributes = guest_support_attributes,
 	.link_ok = guest_link_ok,
 	.release_afu = guest_release_afu,
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
index 8def4553acba..dec60f58a767 100644
--- a/drivers/misc/cxl/irq.c
+++ b/drivers/misc/cxl/irq.c
@@ -260,9 +260,6 @@ int afu_allocate_irqs(struct cxl_context *ctx, u32 count)
 	else
 		alloc_count = count + 1;
 
-	/* Initialize the list head to hold irq names */
-	INIT_LIST_HEAD(&ctx->irq_names);
-
 	if ((rc = cxl_ops->alloc_irq_ranges(&ctx->irqs, ctx->afu->adapter,
 							alloc_count)))
 		return rc;
@@ -374,3 +371,32 @@ void afu_release_irqs(struct cxl_context *ctx, void *cookie)
 
 	ctx->irq_count = 0;
 }
+
+void cxl_afu_decode_psl_serr(struct cxl_afu *afu, u64 serr)
+{
+	dev_crit(&afu->dev,
+		 "PSL Slice error received. Check AFU for root cause.\n");
+	dev_crit(&afu->dev, "PSL_SERR_An: 0x%016llx\n", serr);
+	if (serr & CXL_PSL_SERR_An_afuto)
+		dev_crit(&afu->dev, "AFU MMIO Timeout\n");
+	if (serr & CXL_PSL_SERR_An_afudis)
+		dev_crit(&afu->dev,
+			 "MMIO targeted Accelerator that was not enabled\n");
+	if (serr & CXL_PSL_SERR_An_afuov)
+		dev_crit(&afu->dev, "AFU CTAG Overflow\n");
+	if (serr & CXL_PSL_SERR_An_badsrc)
+		dev_crit(&afu->dev, "Bad Interrupt Source\n");
+	if (serr & CXL_PSL_SERR_An_badctx)
+		dev_crit(&afu->dev, "Bad Context Handle\n");
+	if (serr & CXL_PSL_SERR_An_llcmdis)
+		dev_crit(&afu->dev, "LLCMD to Disabled AFU\n");
+	if (serr & CXL_PSL_SERR_An_llcmdto)
+		dev_crit(&afu->dev, "LLCMD Timeout to AFU\n");
+	if (serr & CXL_PSL_SERR_An_afupar)
+		dev_crit(&afu->dev, "AFU MMIO Parity Error\n");
+	if (serr & CXL_PSL_SERR_An_afudup)
+		dev_crit(&afu->dev, "AFU MMIO Duplicate CTAG Error\n");
+	if (serr & CXL_PSL_SERR_An_AE)
+		dev_crit(&afu->dev,
+			 "AFU asserted JDONE with JERROR in AFU Directed Mode\n");
+}
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index ae68c3201156..d9be23b24aa3 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -110,6 +110,11 @@ static inline void cxl_slbia_core(struct mm_struct *mm)
 
 static struct cxl_calls cxl_calls = {
 	.cxl_slbia = cxl_slbia_core,
+	.cxl_pci_associate_default_context = _cxl_pci_associate_default_context,
+	.cxl_pci_disable_device = _cxl_pci_disable_device,
+	.cxl_next_msi_hwirq = _cxl_next_msi_hwirq,
+	.cxl_cx4_setup_msi_irqs = _cxl_cx4_setup_msi_irqs,
+	.cxl_cx4_teardown_msi_irqs = _cxl_cx4_teardown_msi_irqs,
 	.owner = THIS_MODULE,
 };
 
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 55d8a1459f28..3bcdaee11ba1 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -21,10 +21,10 @@
 #include "cxl.h"
 #include "trace.h"
 
-static int afu_control(struct cxl_afu *afu, u64 command,
+static int afu_control(struct cxl_afu *afu, u64 command, u64 clear,
 		       u64 result, u64 mask, bool enabled)
 {
-	u64 AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+	u64 AFU_Cntl;
 	unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
 	int rc = 0;
 
@@ -33,7 +33,8 @@ static int afu_control(struct cxl_afu *afu, u64 command,
 
 	trace_cxl_afu_ctrl(afu, command);
 
-	cxl_p2n_write(afu, CXL_AFU_Cntl_An, AFU_Cntl | command);
+	AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+	cxl_p2n_write(afu, CXL_AFU_Cntl_An, (AFU_Cntl & ~clear) | command);
 
 	AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
 	while ((AFU_Cntl & mask) != result) {
@@ -54,6 +55,16 @@ static int afu_control(struct cxl_afu *afu, u64 command,
 		cpu_relax();
 		AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
 	};
+
+	if (AFU_Cntl & CXL_AFU_Cntl_An_RA) {
+		/*
+		 * Workaround for a bug in the XSL used in the Mellanox CX4
+		 * that fails to clear the RA bit after an AFU reset,
+		 * preventing subsequent AFU resets from working.
+		 */
+		cxl_p2n_write(afu, CXL_AFU_Cntl_An, AFU_Cntl & ~CXL_AFU_Cntl_An_RA);
+	}
+
 	pr_devel("AFU command complete: %llx\n", command);
 	afu->enabled = enabled;
 out:
@@ -67,7 +78,7 @@ static int afu_enable(struct cxl_afu *afu)
 {
 	pr_devel("AFU enable request\n");
 
-	return afu_control(afu, CXL_AFU_Cntl_An_E,
+	return afu_control(afu, CXL_AFU_Cntl_An_E, 0,
 			   CXL_AFU_Cntl_An_ES_Enabled,
 			   CXL_AFU_Cntl_An_ES_MASK, true);
 }
@@ -76,7 +87,8 @@ int cxl_afu_disable(struct cxl_afu *afu)
 {
 	pr_devel("AFU disable request\n");
 
-	return afu_control(afu, 0, CXL_AFU_Cntl_An_ES_Disabled,
+	return afu_control(afu, 0, CXL_AFU_Cntl_An_E,
+			   CXL_AFU_Cntl_An_ES_Disabled,
 			   CXL_AFU_Cntl_An_ES_MASK, false);
 }
 
@@ -85,7 +97,7 @@ static int native_afu_reset(struct cxl_afu *afu)
 {
 	pr_devel("AFU reset request\n");
 
-	return afu_control(afu, CXL_AFU_Cntl_An_RA,
+	return afu_control(afu, CXL_AFU_Cntl_An_RA, 0,
 			   CXL_AFU_Cntl_An_RS_Complete | CXL_AFU_Cntl_An_ES_Disabled,
 			   CXL_AFU_Cntl_An_RS_MASK | CXL_AFU_Cntl_An_ES_MASK,
 			   false);
@@ -189,7 +201,7 @@ int cxl_alloc_spa(struct cxl_afu *afu)
 	unsigned spa_size;
 
 	/* Work out how many pages to allocate */
-	afu->native->spa_order = 0;
+	afu->native->spa_order = -1;
 	do {
 		afu->native->spa_order++;
 		spa_size = (1 << afu->native->spa_order) * PAGE_SIZE;
@@ -430,7 +442,6 @@ static int remove_process_element(struct cxl_context *ctx)
 	return rc;
 }
 
-
 void cxl_assign_psn_space(struct cxl_context *ctx)
 {
 	if (!ctx->afu->pp_size || ctx->master) {
@@ -507,10 +518,39 @@ static u64 calculate_sr(struct cxl_context *ctx)
 	return sr;
 }
 
+static void update_ivtes_directed(struct cxl_context *ctx)
+{
+	bool need_update = (ctx->status == STARTED);
+	int r;
+
+	if (need_update) {
+		WARN_ON(terminate_process_element(ctx));
+		WARN_ON(remove_process_element(ctx));
+	}
+
+	for (r = 0; r < CXL_IRQ_RANGES; r++) {
+		ctx->elem->ivte_offsets[r] = cpu_to_be16(ctx->irqs.offset[r]);
+		ctx->elem->ivte_ranges[r] = cpu_to_be16(ctx->irqs.range[r]);
+	}
+
+	/*
+	 * Theoretically we could use the update llcmd, instead of a
+	 * terminate/remove/add (or if an atomic update was required we could
+	 * do a suspend/update/resume), however it seems there might be issues
+	 * with the update llcmd on some cards (including those using an XSL on
+	 * an ASIC) so for now it's safest to go with the commands that are
+	 * known to work. In the future if we come across a situation where the
+	 * card may be performing transactions using the same PE while we are
+	 * doing this update we might need to revisit this.
+	 */
+	if (need_update)
+		WARN_ON(add_process_element(ctx));
+}
+
 static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
 {
 	u32 pid;
-	int r, result;
+	int result;
 
 	cxl_assign_psn_space(ctx);
 
@@ -545,10 +585,7 @@ static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
 		ctx->irqs.range[0] = 1;
 	}
 
-	for (r = 0; r < CXL_IRQ_RANGES; r++) {
-		ctx->elem->ivte_offsets[r] = cpu_to_be16(ctx->irqs.offset[r]);
-		ctx->elem->ivte_ranges[r] = cpu_to_be16(ctx->irqs.range[r]);
-	}
+	update_ivtes_directed(ctx);
 
 	ctx->elem->common.amr = cpu_to_be64(amr);
 	ctx->elem->common.wed = cpu_to_be64(wed);
@@ -570,7 +607,33 @@ static int deactivate_afu_directed(struct cxl_afu *afu)
 	cxl_sysfs_afu_m_remove(afu);
 	cxl_chardev_afu_remove(afu);
 
-	cxl_ops->afu_reset(afu);
+	/*
+	 * The CAIA section 2.2.1 indicates that the procedure for starting and
+	 * stopping an AFU in AFU directed mode is AFU specific, which is not
+	 * ideal since this code is generic and with one exception has no
+	 * knowledge of the AFU. This is in contrast to the procedure for
+	 * disabling a dedicated process AFU, which is documented to just
+	 * require a reset. The architecture does indicate that both an AFU
+	 * reset and an AFU disable should result in the AFU being disabled and
+	 * we do both followed by a PSL purge for safety.
+	 *
+	 * Notably we used to have some issues with the disable sequence on PSL
+	 * cards, which is why we ended up using this heavy weight procedure in
+	 * the first place, however a bug was discovered that had rendered the
+	 * disable operation ineffective, so it is conceivable that was the
+	 * sole explanation for those difficulties. Careful regression testing
+	 * is recommended if anyone attempts to remove or reorder these
+	 * operations.
+	 *
+	 * The XSL on the Mellanox CX4 behaves a little differently from the
+	 * PSL based cards and will time out an AFU reset if the AFU is still
+	 * enabled. That card is special in that we do have a means to identify
+	 * it from this code, so in that case we skip the reset and just use a
+	 * disable/purge to avoid the timeout and corresponding noise in the
+	 * kernel log.
+	 */
+	if (afu->adapter->native->sl_ops->needs_reset_before_disable)
+		cxl_ops->afu_reset(afu);
 	cxl_afu_disable(afu);
 	cxl_psl_purge(afu);
 
@@ -600,6 +663,22 @@ static int activate_dedicated_process(struct cxl_afu *afu)
 	return cxl_chardev_d_afu_add(afu);
 }
 
+static void update_ivtes_dedicated(struct cxl_context *ctx)
+{
+	struct cxl_afu *afu = ctx->afu;
+
+	cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An,
+		       (((u64)ctx->irqs.offset[0] & 0xffff) << 48) |
+		       (((u64)ctx->irqs.offset[1] & 0xffff) << 32) |
+		       (((u64)ctx->irqs.offset[2] & 0xffff) << 16) |
+			((u64)ctx->irqs.offset[3] & 0xffff));
+	cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, (u64)
+		       (((u64)ctx->irqs.range[0] & 0xffff) << 48) |
+		       (((u64)ctx->irqs.range[1] & 0xffff) << 32) |
+		       (((u64)ctx->irqs.range[2] & 0xffff) << 16) |
+			((u64)ctx->irqs.range[3] & 0xffff));
+}
+
 static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr)
 {
 	struct cxl_afu *afu = ctx->afu;
@@ -618,16 +697,7 @@ static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr)
 
 	cxl_prefault(ctx, wed);
 
-	cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An,
-		       (((u64)ctx->irqs.offset[0] & 0xffff) << 48) |
-		       (((u64)ctx->irqs.offset[1] & 0xffff) << 32) |
-		       (((u64)ctx->irqs.offset[2] & 0xffff) << 16) |
-			((u64)ctx->irqs.offset[3] & 0xffff));
-	cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, (u64)
-		       (((u64)ctx->irqs.range[0] & 0xffff) << 48) |
-		       (((u64)ctx->irqs.range[1] & 0xffff) << 32) |
-		       (((u64)ctx->irqs.range[2] & 0xffff) << 16) |
-			((u64)ctx->irqs.range[3] & 0xffff));
+	update_ivtes_dedicated(ctx);
 
 	cxl_p2n_write(afu, CXL_PSL_AMR_An, amr);
 
@@ -703,12 +773,37 @@ static int native_attach_process(struct cxl_context *ctx, bool kernel,
 
 static inline int detach_process_native_dedicated(struct cxl_context *ctx)
 {
+	/*
+	 * The CAIA section 2.1.1 indicates that we need to do an AFU reset to
+	 * stop the AFU in dedicated mode (we therefore do not make that
+	 * optional like we do in the afu directed path). It does not indicate
+	 * that we need to do an explicit disable (which should occur
+	 * implicitly as part of the reset) or purge, but we do these as well
+	 * to be on the safe side.
+	 *
+	 * Notably we used to have some issues with the disable sequence
+	 * (before the sequence was spelled out in the architecture) which is
+	 * why we were so heavy weight in the first place, however a bug was
+	 * discovered that had rendered the disable operation ineffective, so
+	 * it is conceivable that was the sole explanation for those
+	 * difficulties. Point is, we should be careful and do some regression
+	 * testing if we ever attempt to remove any part of this procedure.
+	 */
 	cxl_ops->afu_reset(ctx->afu);
 	cxl_afu_disable(ctx->afu);
 	cxl_psl_purge(ctx->afu);
 	return 0;
 }
 
+static void native_update_ivtes(struct cxl_context *ctx)
+{
+	if (ctx->afu->current_mode == CXL_MODE_DIRECTED)
+		return update_ivtes_directed(ctx);
+	if (ctx->afu->current_mode == CXL_MODE_DEDICATED)
+		return update_ivtes_dedicated(ctx);
+	WARN(1, "native_update_ivtes: Bad mode\n");
+}
+
 static inline int detach_process_native_afu_directed(struct cxl_context *ctx)
 {
 	if (!ctx->pe_inserted)
@@ -754,26 +849,38 @@ static int native_get_irq_info(struct cxl_afu *afu, struct cxl_irq_info *info)
 	return 0;
 }
 
-static irqreturn_t native_handle_psl_slice_error(struct cxl_context *ctx,
-						u64 dsisr, u64 errstat)
+void cxl_native_psl_irq_dump_regs(struct cxl_context *ctx)
 {
 	u64 fir1, fir2, fir_slice, serr, afu_debug;
 
 	fir1 = cxl_p1_read(ctx->afu->adapter, CXL_PSL_FIR1);
 	fir2 = cxl_p1_read(ctx->afu->adapter, CXL_PSL_FIR2);
 	fir_slice = cxl_p1n_read(ctx->afu, CXL_PSL_FIR_SLICE_An);
-	serr = cxl_p1n_read(ctx->afu, CXL_PSL_SERR_An);
 	afu_debug = cxl_p1n_read(ctx->afu, CXL_AFU_DEBUG_An);
 
-	dev_crit(&ctx->afu->dev, "PSL ERROR STATUS: 0x%016llx\n", errstat);
 	dev_crit(&ctx->afu->dev, "PSL_FIR1: 0x%016llx\n", fir1);
 	dev_crit(&ctx->afu->dev, "PSL_FIR2: 0x%016llx\n", fir2);
-	dev_crit(&ctx->afu->dev, "PSL_SERR_An: 0x%016llx\n", serr);
+	if (ctx->afu->adapter->native->sl_ops->register_serr_irq) {
+		serr = cxl_p1n_read(ctx->afu, CXL_PSL_SERR_An);
+		cxl_afu_decode_psl_serr(ctx->afu, serr);
+	}
 	dev_crit(&ctx->afu->dev, "PSL_FIR_SLICE_An: 0x%016llx\n", fir_slice);
 	dev_crit(&ctx->afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%016llx\n", afu_debug);
+}
+
+static irqreturn_t native_handle_psl_slice_error(struct cxl_context *ctx,
+						u64 dsisr, u64 errstat)
+{
+
+	dev_crit(&ctx->afu->dev, "PSL ERROR STATUS: 0x%016llx\n", errstat);
 
-	dev_crit(&ctx->afu->dev, "STOPPING CXL TRACE\n");
-	cxl_stop_trace(ctx->afu->adapter);
+	if (ctx->afu->adapter->native->sl_ops->psl_irq_dump_registers)
+		ctx->afu->adapter->native->sl_ops->psl_irq_dump_registers(ctx);
+
+	if (ctx->afu->adapter->native->sl_ops->debugfs_stop_trace) {
+		dev_crit(&ctx->afu->dev, "STOPPING CXL TRACE\n");
+		ctx->afu->adapter->native->sl_ops->debugfs_stop_trace(ctx->afu->adapter);
+	}
 
 	return cxl_ops->ack_irq(ctx, 0, errstat);
 }
@@ -849,41 +956,56 @@ void native_irq_wait(struct cxl_context *ctx)
 static irqreturn_t native_slice_irq_err(int irq, void *data)
 {
 	struct cxl_afu *afu = data;
-	u64 fir_slice, errstat, serr, afu_debug;
-
-	WARN(irq, "CXL SLICE ERROR interrupt %i\n", irq);
+	u64 fir_slice, errstat, serr, afu_debug, afu_error, dsisr;
 
+	/*
+	 * slice err interrupt is only used with full PSL (no XSL)
+	 */
 	serr = cxl_p1n_read(afu, CXL_PSL_SERR_An);
 	fir_slice = cxl_p1n_read(afu, CXL_PSL_FIR_SLICE_An);
 	errstat = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
 	afu_debug = cxl_p1n_read(afu, CXL_AFU_DEBUG_An);
-	dev_crit(&afu->dev, "PSL_SERR_An: 0x%016llx\n", serr);
+	afu_error = cxl_p2n_read(afu, CXL_AFU_ERR_An);
+	dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
+	cxl_afu_decode_psl_serr(afu, serr);
 	dev_crit(&afu->dev, "PSL_FIR_SLICE_An: 0x%016llx\n", fir_slice);
 	dev_crit(&afu->dev, "CXL_PSL_ErrStat_An: 0x%016llx\n", errstat);
 	dev_crit(&afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%016llx\n", afu_debug);
+	dev_crit(&afu->dev, "AFU_ERR_An: 0x%.16llx\n", afu_error);
+	dev_crit(&afu->dev, "PSL_DSISR_An: 0x%.16llx\n", dsisr);
 
 	cxl_p1n_write(afu, CXL_PSL_SERR_An, serr);
 
 	return IRQ_HANDLED;
 }
 
+void cxl_native_err_irq_dump_regs(struct cxl *adapter)
+{
+	u64 fir1, fir2;
+
+	fir1 = cxl_p1_read(adapter, CXL_PSL_FIR1);
+	fir2 = cxl_p1_read(adapter, CXL_PSL_FIR2);
+
+	dev_crit(&adapter->dev, "PSL_FIR1: 0x%016llx\nPSL_FIR2: 0x%016llx\n", fir1, fir2);
+}
+
 static irqreturn_t native_irq_err(int irq, void *data)
 {
 	struct cxl *adapter = data;
-	u64 fir1, fir2, err_ivte;
+	u64 err_ivte;
 
 	WARN(1, "CXL ERROR interrupt %i\n", irq);
 
 	err_ivte = cxl_p1_read(adapter, CXL_PSL_ErrIVTE);
 	dev_crit(&adapter->dev, "PSL_ErrIVTE: 0x%016llx\n", err_ivte);
 
-	dev_crit(&adapter->dev, "STOPPING CXL TRACE\n");
-	cxl_stop_trace(adapter);
-
-	fir1 = cxl_p1_read(adapter, CXL_PSL_FIR1);
-	fir2 = cxl_p1_read(adapter, CXL_PSL_FIR2);
+	if (adapter->native->sl_ops->debugfs_stop_trace) {
+		dev_crit(&adapter->dev, "STOPPING CXL TRACE\n");
+		adapter->native->sl_ops->debugfs_stop_trace(adapter);
+	}
 
-	dev_crit(&adapter->dev, "PSL_FIR1: 0x%016llx\nPSL_FIR2: 0x%016llx\n", fir1, fir2);
+	if (adapter->native->sl_ops->err_irq_dump_registers)
+		adapter->native->sl_ops->err_irq_dump_registers(adapter);
 
 	return IRQ_HANDLED;
 }
@@ -1128,6 +1250,7 @@ const struct cxl_backend_ops cxl_native_ops = {
 	.irq_wait = native_irq_wait,
 	.attach_process = native_attach_process,
 	.detach_process = native_detach_process,
+	.update_ivtes = native_update_ivtes,
 	.support_attributes = native_support_attributes,
 	.link_ok = cxl_adapter_link_ok,
 	.release_afu = cxl_pci_release_afu,
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index a08fcc888a71..d152e2de8c93 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -55,6 +55,8 @@
 	pci_read_config_byte(dev, vsec + 0xa, dest)
 #define CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val) \
 	pci_write_config_byte(dev, vsec + 0xa, val)
+#define CXL_WRITE_VSEC_MODE_CONTROL_BUS(bus, devfn, vsec, val) \
+	pci_bus_write_config_byte(bus, devfn, vsec + 0xa, val)
 #define CXL_VSEC_PROTOCOL_MASK   0xe0
 #define CXL_VSEC_PROTOCOL_1024TB 0x80
 #define CXL_VSEC_PROTOCOL_512TB  0x40
@@ -352,13 +354,10 @@ static u64 get_capp_unit_id(struct device_node *np)
 	return 0;
 }
 
-static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev *dev)
+static int calc_capp_routing(struct pci_dev *dev, u64 *chipid, u64 *capp_unit_id)
 {
 	struct device_node *np;
 	const __be32 *prop;
-	u64 psl_dsnctl;
-	u64 chipid;
-	u64 capp_unit_id;
 
 	if (!(np = pnv_pci_get_phb_node(dev)))
 		return -ENODEV;
@@ -367,14 +366,28 @@ static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev
 		np = of_get_next_parent(np);
 	if (!np)
 		return -ENODEV;
-	chipid = be32_to_cpup(prop);
-	capp_unit_id = get_capp_unit_id(np);
+	*chipid = be32_to_cpup(prop);
+	*capp_unit_id = get_capp_unit_id(np);
 	of_node_put(np);
-	if (!capp_unit_id) {
+	if (!*capp_unit_id) {
 		pr_err("cxl: invalid capp unit id\n");
 		return -ENODEV;
 	}
 
+	return 0;
+}
+
+static int init_implementation_adapter_psl_regs(struct cxl *adapter, struct pci_dev *dev)
+{
+	u64 psl_dsnctl;
+	u64 chipid;
+	u64 capp_unit_id;
+	int rc;
+
+	rc = calc_capp_routing(dev, &chipid, &capp_unit_id);
+	if (rc)
+		return rc;
+
 	psl_dsnctl = 0x0000900000000000ULL; /* pteupd ttype, scdone */
 	psl_dsnctl |= (0x2ULL << (63-38)); /* MMIO hang pulse: 256 us */
 	/* Tell PSL where to route data to */
@@ -393,8 +406,61 @@ static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev
 	return 0;
 }
 
+static int init_implementation_adapter_xsl_regs(struct cxl *adapter, struct pci_dev *dev)
+{
+	u64 xsl_dsnctl;
+	u64 chipid;
+	u64 capp_unit_id;
+	int rc;
+
+	rc = calc_capp_routing(dev, &chipid, &capp_unit_id);
+	if (rc)
+		return rc;
+
+	/* Tell XSL where to route data to */
+	xsl_dsnctl = 0x0000600000000000ULL | (chipid << (63-5));
+	xsl_dsnctl |= (capp_unit_id << (63-13));
+	cxl_p1_write(adapter, CXL_XSL_DSNCTL, xsl_dsnctl);
+
+	return 0;
+}
+
+/* PSL & XSL */
+#define TBSYNC_CAL(n) (((u64)n & 0x7) << (63-3))
 #define TBSYNC_CNT(n) (((u64)n & 0x7) << (63-6))
-#define _2048_250MHZ_CYCLES 1
+/* For the PSL this is a multiple for 0 < n <= 7: */
+#define PSL_2048_250MHZ_CYCLES 1
+
+static void write_timebase_ctrl_psl(struct cxl *adapter)
+{
+	cxl_p1_write(adapter, CXL_PSL_TB_CTLSTAT,
+		     TBSYNC_CNT(2 * PSL_2048_250MHZ_CYCLES));
+}
+
+/* XSL */
+#define TBSYNC_ENA (1ULL << 63)
+/* For the XSL this is 2**n * 2000 clocks for 0 < n <= 6: */
+#define XSL_2000_CLOCKS 1
+#define XSL_4000_CLOCKS 2
+#define XSL_8000_CLOCKS 3
+
+static void write_timebase_ctrl_xsl(struct cxl *adapter)
+{
+	cxl_p1_write(adapter, CXL_XSL_TB_CTLSTAT,
+		     TBSYNC_ENA |
+		     TBSYNC_CAL(3) |
+		     TBSYNC_CNT(XSL_4000_CLOCKS));
+}
+
+static u64 timebase_read_psl(struct cxl *adapter)
+{
+	return cxl_p1_read(adapter, CXL_PSL_Timebase);
+}
+
+static u64 timebase_read_xsl(struct cxl *adapter)
+{
+	return cxl_p1_read(adapter, CXL_XSL_Timebase);
+}
 
 static void cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
 {
@@ -421,8 +487,7 @@ static void cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
 	 * Setup PSL Timebase Control and Status register
 	 * with the recommended Timebase Sync Count value
 	 */
-	cxl_p1_write(adapter, CXL_PSL_TB_CTLSTAT,
-		     TBSYNC_CNT(2 * _2048_250MHZ_CYCLES));
+	adapter->native->sl_ops->write_timebase_ctrl(adapter);
 
 	/* Enable PSL Timebase */
 	cxl_p1_write(adapter, CXL_PSL_Control, 0x0000000000000000);
@@ -435,7 +500,7 @@ static void cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
 			dev_info(&dev->dev, "PSL timebase can't synchronize\n");
 			return;
 		}
-		psl_tb = cxl_p1_read(adapter, CXL_PSL_Timebase);
+		psl_tb = adapter->native->sl_ops->timebase_read(adapter);
 		delta = mftb() - psl_tb;
 		if (delta < 0)
 			delta = -delta;
@@ -445,7 +510,7 @@ static void cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
 	return;
 }
 
-static int init_implementation_afu_regs(struct cxl_afu *afu)
+static int init_implementation_afu_psl_regs(struct cxl_afu *afu)
 {
 	/* read/write masks for this slice */
 	cxl_p1n_write(afu, CXL_PSL_APCALLOC_A, 0xFFFFFFFEFEFEFEFEULL);
@@ -551,36 +616,234 @@ static int setup_cxl_bars(struct pci_dev *dev)
 	return 0;
 }
 
-/* pciex node: ibm,opal-m64-window = <0x3d058 0x0 0x3d058 0x0 0x8 0x0>; */
-static int switch_card_to_cxl(struct pci_dev *dev)
-{
+#ifdef CONFIG_CXL_BIMODAL
+
+struct cxl_switch_work {
+	struct pci_dev *dev;
+	struct work_struct work;
 	int vsec;
+	int mode;
+};
+
+static void switch_card_to_cxl(struct work_struct *work)
+{
+	struct cxl_switch_work *switch_work =
+		container_of(work, struct cxl_switch_work, work);
+	struct pci_dev *dev = switch_work->dev;
+	struct pci_bus *bus = dev->bus;
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pci_dev *bridge;
+	struct pnv_php_slot *php_slot;
+	unsigned int devfn;
 	u8 val;
 	int rc;
 
-	dev_info(&dev->dev, "switch card to CXL\n");
+	dev_info(&bus->dev, "cxl: Preparing for mode switch...\n");
+	bridge = list_first_entry_or_null(&hose->bus->devices, struct pci_dev,
+					  bus_list);
+	if (!bridge) {
+		dev_WARN(&bus->dev, "cxl: Couldn't find root port!\n");
+		goto err_dev_put;
+	}
 
-	if (!(vsec = find_cxl_vsec(dev))) {
-		dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
+	php_slot = pnv_php_find_slot(pci_device_to_OF_node(bridge));
+	if (!php_slot) {
+		dev_err(&bus->dev, "cxl: Failed to find slot hotplug "
+			           "information. You may need to upgrade "
+			           "skiboot. Aborting.\n");
+		goto err_dev_put;
+	}
+
+	rc = CXL_READ_VSEC_MODE_CONTROL(dev, switch_work->vsec, &val);
+	if (rc) {
+		dev_err(&bus->dev, "cxl: Failed to read CAPI mode control: %i\n", rc);
+		goto err_dev_put;
+	}
+	devfn = dev->devfn;
+
+	/* Release the reference obtained in cxl_check_and_switch_mode() */
+	pci_dev_put(dev);
+
+	dev_dbg(&bus->dev, "cxl: Removing PCI devices from kernel\n");
+	pci_lock_rescan_remove();
+	pci_hp_remove_devices(bridge->subordinate);
+	pci_unlock_rescan_remove();
+
+	/* Switch the CXL protocol on the card */
+	if (switch_work->mode == CXL_BIMODE_CXL) {
+		dev_info(&bus->dev, "cxl: Switching card to CXL mode\n");
+		val &= ~CXL_VSEC_PROTOCOL_MASK;
+		val |= CXL_VSEC_PROTOCOL_256TB | CXL_VSEC_PROTOCOL_ENABLE;
+		rc = pnv_cxl_enable_phb_kernel_api(hose, true);
+		if (rc) {
+			dev_err(&bus->dev, "cxl: Failed to enable kernel API"
+				           " on real PHB, aborting\n");
+			goto err_free_work;
+		}
+	} else {
+		dev_WARN(&bus->dev, "cxl: Switching card to PCI mode not supported!\n");
+		goto err_free_work;
+	}
+
+	rc = CXL_WRITE_VSEC_MODE_CONTROL_BUS(bus, devfn, switch_work->vsec, val);
+	if (rc) {
+		dev_err(&bus->dev, "cxl: Failed to configure CXL protocol: %i\n", rc);
+		goto err_free_work;
+	}
+
+	/*
+	 * The CAIA spec (v1.1, Section 10.6 Bi-modal Device Support) states
+	 * we must wait 100ms after this mode switch before touching PCIe config
+	 * space.
+	 */
+	msleep(100);
+
+	/*
+	 * Hot reset to cause the card to come back in cxl mode. A
+	 * OPAL_RESET_PCI_LINK would be sufficient, but currently lacks support
+	 * in skiboot, so we use a hot reset instead.
+	 *
+	 * We call pci_set_pcie_reset_state() on the bridge, as a CAPI card is
+	 * guaranteed to sit directly under the root port, and setting the reset
+	 * state on a device directly under the root port is equivalent to doing
+	 * it on the root port iself.
+	 */
+	dev_info(&bus->dev, "cxl: Configuration write complete, resetting card\n");
+	pci_set_pcie_reset_state(bridge, pcie_hot_reset);
+	pci_set_pcie_reset_state(bridge, pcie_deassert_reset);
+
+	dev_dbg(&bus->dev, "cxl: Offlining slot\n");
+	rc = pnv_php_set_slot_power_state(&php_slot->slot, OPAL_PCI_SLOT_OFFLINE);
+	if (rc) {
+		dev_err(&bus->dev, "cxl: OPAL offlining call failed: %i\n", rc);
+		goto err_free_work;
+	}
+
+	dev_dbg(&bus->dev, "cxl: Onlining and probing slot\n");
+	rc = pnv_php_set_slot_power_state(&php_slot->slot, OPAL_PCI_SLOT_ONLINE);
+	if (rc) {
+		dev_err(&bus->dev, "cxl: OPAL onlining call failed: %i\n", rc);
+		goto err_free_work;
+	}
+
+	pci_lock_rescan_remove();
+	pci_hp_add_devices(bridge->subordinate);
+	pci_unlock_rescan_remove();
+
+	dev_info(&bus->dev, "cxl: CAPI mode switch completed\n");
+	kfree(switch_work);
+	return;
+
+err_dev_put:
+	/* Release the reference obtained in cxl_check_and_switch_mode() */
+	pci_dev_put(dev);
+err_free_work:
+	kfree(switch_work);
+}
+
+int cxl_check_and_switch_mode(struct pci_dev *dev, int mode, int vsec)
+{
+	struct cxl_switch_work *work;
+	u8 val;
+	int rc;
+
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
 		return -ENODEV;
+
+	if (!vsec) {
+		vsec = find_cxl_vsec(dev);
+		if (!vsec) {
+			dev_info(&dev->dev, "CXL VSEC not found\n");
+			return -ENODEV;
+		}
 	}
 
-	if ((rc = CXL_READ_VSEC_MODE_CONTROL(dev, vsec, &val))) {
-		dev_err(&dev->dev, "failed to read current mode control: %i", rc);
+	rc = CXL_READ_VSEC_MODE_CONTROL(dev, vsec, &val);
+	if (rc) {
+		dev_err(&dev->dev, "Failed to read current mode control: %i", rc);
 		return rc;
 	}
-	val &= ~CXL_VSEC_PROTOCOL_MASK;
-	val |= CXL_VSEC_PROTOCOL_256TB | CXL_VSEC_PROTOCOL_ENABLE;
-	if ((rc = CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val))) {
-		dev_err(&dev->dev, "failed to enable CXL protocol: %i", rc);
-		return rc;
+
+	if (mode == CXL_BIMODE_PCI) {
+		if (!(val & CXL_VSEC_PROTOCOL_ENABLE)) {
+			dev_info(&dev->dev, "Card is already in PCI mode\n");
+			return 0;
+		}
+		/*
+		 * TODO: Before it's safe to switch the card back to PCI mode
+		 * we need to disable the CAPP and make sure any cachelines the
+		 * card holds have been flushed out. Needs skiboot support.
+		 */
+		dev_WARN(&dev->dev, "CXL mode switch to PCI unsupported!\n");
+		return -EIO;
 	}
+
+	if (val & CXL_VSEC_PROTOCOL_ENABLE) {
+		dev_info(&dev->dev, "Card is already in CXL mode\n");
+		return 0;
+	}
+
+	dev_info(&dev->dev, "Card is in PCI mode, scheduling kernel thread "
+			    "to switch to CXL mode\n");
+
+	work = kmalloc(sizeof(struct cxl_switch_work), GFP_KERNEL);
+	if (!work)
+		return -ENOMEM;
+
+	pci_dev_get(dev);
+	work->dev = dev;
+	work->vsec = vsec;
+	work->mode = mode;
+	INIT_WORK(&work->work, switch_card_to_cxl);
+
+	schedule_work(&work->work);
+
 	/*
-	 * The CAIA spec (v0.12 11.6 Bi-modal Device Support) states
-	 * we must wait 100ms after this mode switch before touching
-	 * PCIe config space.
+	 * We return a failure now to abort the driver init. Once the
+	 * link has been cycled and the card is in cxl mode we will
+	 * come back (possibly using the generic cxl driver), but
+	 * return success as the card should then be in cxl mode.
+	 *
+	 * TODO: What if the card comes back in PCI mode even after
+	 *       the switch?  Don't want to spin endlessly.
 	 */
-	msleep(100);
+	return -EBUSY;
+}
+EXPORT_SYMBOL_GPL(cxl_check_and_switch_mode);
+
+#endif /* CONFIG_CXL_BIMODAL */
+
+static int setup_cxl_protocol_area(struct pci_dev *dev)
+{
+	u8 val;
+	int rc;
+	int vsec = find_cxl_vsec(dev);
+
+	if (!vsec) {
+		dev_info(&dev->dev, "CXL VSEC not found\n");
+		return -ENODEV;
+	}
+
+	rc = CXL_READ_VSEC_MODE_CONTROL(dev, vsec, &val);
+	if (rc) {
+		dev_err(&dev->dev, "Failed to read current mode control: %i\n", rc);
+		return rc;
+	}
+
+	if (!(val & CXL_VSEC_PROTOCOL_ENABLE)) {
+		dev_err(&dev->dev, "Card not in CAPI mode!\n");
+		return -EIO;
+	}
+
+	if ((val & CXL_VSEC_PROTOCOL_MASK) != CXL_VSEC_PROTOCOL_256TB) {
+		val &= ~CXL_VSEC_PROTOCOL_MASK;
+		val |= CXL_VSEC_PROTOCOL_256TB;
+		rc = CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val);
+		if (rc) {
+			dev_err(&dev->dev, "Failed to set CXL protocol area: %i\n", rc);
+			return rc;
+		}
+	}
 
 	return 0;
 }
@@ -712,6 +975,21 @@ static int cxl_afu_descriptor_looks_ok(struct cxl_afu *afu)
 		}
 	}
 
+	if ((afu->modes_supported & ~CXL_MODE_DEDICATED) && afu->max_procs_virtualised == 0) {
+		/*
+		 * We could also check this for the dedicated process model
+		 * since the architecture indicates it should be set to 1, but
+		 * in that case we ignore the value and I'd rather not risk
+		 * breaking any existing dedicated process AFUs that left it as
+		 * 0 (not that I'm aware of any). It is clearly an error for an
+		 * AFU directed AFU to set this to 0, and would have previously
+		 * triggered a bug resulting in the maximum not being enforced
+		 * at all since idr_alloc treats 0 as no maximum.
+		 */
+		dev_err(&afu->dev, "AFU does not support any processes\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -753,11 +1031,13 @@ static int sanitise_afu_regs(struct cxl_afu *afu)
 		else
 			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A);
 	}
-	reg = cxl_p1n_read(afu, CXL_PSL_SERR_An);
-	if (reg) {
-		if (reg & ~0xffff)
-			dev_warn(&afu->dev, "AFU had pending SERR: %#016llx\n", reg);
-		cxl_p1n_write(afu, CXL_PSL_SERR_An, reg & ~0xffff);
+	if (afu->adapter->native->sl_ops->register_serr_irq) {
+		reg = cxl_p1n_read(afu, CXL_PSL_SERR_An);
+		if (reg) {
+			if (reg & ~0xffff)
+				dev_warn(&afu->dev, "AFU had pending SERR: %#016llx\n", reg);
+			cxl_p1n_write(afu, CXL_PSL_SERR_An, reg & ~0xffff);
+		}
 	}
 	reg = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
 	if (reg) {
@@ -835,11 +1115,13 @@ static int pci_configure_afu(struct cxl_afu *afu, struct cxl *adapter, struct pc
 	if ((rc = cxl_afu_descriptor_looks_ok(afu)))
 		goto err1;
 
-	if ((rc = init_implementation_afu_regs(afu)))
-		goto err1;
+	if (adapter->native->sl_ops->afu_regs_init)
+		if ((rc = adapter->native->sl_ops->afu_regs_init(afu)))
+			goto err1;
 
-	if ((rc = cxl_native_register_serr_irq(afu)))
-		goto err1;
+	if (adapter->native->sl_ops->register_serr_irq)
+		if ((rc = adapter->native->sl_ops->register_serr_irq(afu)))
+			goto err1;
 
 	if ((rc = cxl_native_register_psl_irq(afu)))
 		goto err2;
@@ -847,7 +1129,8 @@ static int pci_configure_afu(struct cxl_afu *afu, struct cxl *adapter, struct pc
 	return 0;
 
 err2:
-	cxl_native_release_serr_irq(afu);
+	if (adapter->native->sl_ops->release_serr_irq)
+		adapter->native->sl_ops->release_serr_irq(afu);
 err1:
 	pci_unmap_slice_regs(afu);
 	return rc;
@@ -856,7 +1139,8 @@ err1:
 static void pci_deconfigure_afu(struct cxl_afu *afu)
 {
 	cxl_native_release_psl_irq(afu);
-	cxl_native_release_serr_irq(afu);
+	if (afu->adapter->native->sl_ops->release_serr_irq)
+		afu->adapter->native->sl_ops->release_serr_irq(afu);
 	pci_unmap_slice_regs(afu);
 }
 
@@ -1165,7 +1449,7 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
 	if ((rc = setup_cxl_bars(dev)))
 		return rc;
 
-	if ((rc = switch_card_to_cxl(dev)))
+	if ((rc = setup_cxl_protocol_area(dev)))
 		return rc;
 
 	if ((rc = cxl_update_image_control(adapter)))
@@ -1177,10 +1461,13 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
 	if ((rc = sanitise_adapter_regs(adapter)))
 		goto err;
 
-	if ((rc = init_implementation_adapter_regs(adapter, dev)))
+	if ((rc = adapter->native->sl_ops->adapter_regs_init(adapter, dev)))
 		goto err;
 
-	if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_CAPI)))
+	/* Required for devices using CAPP DMA mode, harmless for others */
+	pci_set_master(dev);
+
+	if ((rc = pnv_phb_to_cxl_mode(dev, adapter->native->sl_ops->capi_mode)))
 		goto err;
 
 	/* If recovery happened, the last step is to turn on snooping.
@@ -1212,6 +1499,43 @@ static void cxl_deconfigure_adapter(struct cxl *adapter)
 	pci_disable_device(pdev);
 }
 
+static const struct cxl_service_layer_ops psl_ops = {
+	.adapter_regs_init = init_implementation_adapter_psl_regs,
+	.afu_regs_init = init_implementation_afu_psl_regs,
+	.register_serr_irq = cxl_native_register_serr_irq,
+	.release_serr_irq = cxl_native_release_serr_irq,
+	.debugfs_add_adapter_sl_regs = cxl_debugfs_add_adapter_psl_regs,
+	.debugfs_add_afu_sl_regs = cxl_debugfs_add_afu_psl_regs,
+	.psl_irq_dump_registers = cxl_native_psl_irq_dump_regs,
+	.err_irq_dump_registers = cxl_native_err_irq_dump_regs,
+	.debugfs_stop_trace = cxl_stop_trace,
+	.write_timebase_ctrl = write_timebase_ctrl_psl,
+	.timebase_read = timebase_read_psl,
+	.capi_mode = OPAL_PHB_CAPI_MODE_CAPI,
+	.needs_reset_before_disable = true,
+};
+
+static const struct cxl_service_layer_ops xsl_ops = {
+	.adapter_regs_init = init_implementation_adapter_xsl_regs,
+	.debugfs_add_adapter_sl_regs = cxl_debugfs_add_adapter_xsl_regs,
+	.write_timebase_ctrl = write_timebase_ctrl_xsl,
+	.timebase_read = timebase_read_xsl,
+	.capi_mode = OPAL_PHB_CAPI_MODE_DMA,
+	.min_pe = 1, /* Workaround for Mellanox CX4 HW bug */
+};
+
+static void set_sl_ops(struct cxl *adapter, struct pci_dev *dev)
+{
+	if (dev->vendor == PCI_VENDOR_ID_MELLANOX && dev->device == 0x1013) {
+		dev_info(&adapter->dev, "Device uses an XSL\n");
+		adapter->native->sl_ops = &xsl_ops;
+	} else {
+		dev_info(&adapter->dev, "Device uses a PSL\n");
+		adapter->native->sl_ops = &psl_ops;
+	}
+}
+
+
 static struct cxl *cxl_pci_init_adapter(struct pci_dev *dev)
 {
 	struct cxl *adapter;
@@ -1227,6 +1551,8 @@ static struct cxl *cxl_pci_init_adapter(struct pci_dev *dev)
 		goto err_release;
 	}
 
+	set_sl_ops(adapter, dev);
+
 	/* Set defaults for parameters which need to persist over
 	 * configure/reconfigure
 	 */
@@ -1280,6 +1606,67 @@ static void cxl_pci_remove_adapter(struct cxl *adapter)
 	device_unregister(&adapter->dev);
 }
 
+#define CXL_MAX_PCIEX_PARENT 2
+
+static int cxl_slot_is_switched(struct pci_dev *dev)
+{
+	struct device_node *np;
+	int depth = 0;
+	const __be32 *prop;
+
+	if (!(np = pci_device_to_OF_node(dev))) {
+		pr_err("cxl: np = NULL\n");
+		return -ENODEV;
+	}
+	of_node_get(np);
+	while (np) {
+		np = of_get_next_parent(np);
+		prop = of_get_property(np, "device_type", NULL);
+		if (!prop || strcmp((char *)prop, "pciex"))
+			break;
+		depth++;
+	}
+	of_node_put(np);
+	return (depth > CXL_MAX_PCIEX_PARENT);
+}
+
+bool cxl_slot_is_supported(struct pci_dev *dev, int flags)
+{
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return false;
+
+	if ((flags & CXL_SLOT_FLAG_DMA) && (!pvr_version_is(PVR_POWER8NVL))) {
+		/*
+		 * CAPP DMA mode is technically supported on regular P8, but
+		 * will EEH if the card attempts to access memory < 4GB, which
+		 * we cannot realistically avoid. We might be able to work
+		 * around the issue, but until then return unsupported:
+		 */
+		return false;
+	}
+
+	if (cxl_slot_is_switched(dev))
+		return false;
+
+	/*
+	 * XXX: This gets a little tricky on regular P8 (not POWER8NVL) since
+	 * the CAPP can be connected to PHB 0, 1 or 2 on a first come first
+	 * served basis, which is racy to check from here. If we need to
+	 * support this in future we might need to consider having this
+	 * function effectively reserve it ahead of time.
+	 *
+	 * Currently, the only user of this API is the Mellanox CX4, which is
+	 * only supported on P8NVL due to the above mentioned limitation of
+	 * CAPP DMA mode and therefore does not need to worry about this. If the
+	 * issue with CAPP DMA mode is later worked around on P8 we might need
+	 * to revisit this.
+	 */
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(cxl_slot_is_supported);
+
+
 static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	struct cxl *adapter;
@@ -1291,6 +1678,11 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		return -ENODEV;
 	}
 
+	if (cxl_slot_is_switched(dev)) {
+		dev_info(&dev->dev, "Ignoring card on incompatible PCI slot\n");
+		return -ENODEV;
+	}
+
 	if (cxl_verbose)
 		dump_cxl_config_space(dev);
 
@@ -1311,6 +1703,9 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 			dev_err(&dev->dev, "AFU %i failed to start: %i\n", slice, rc);
 	}
 
+	if (pnv_pci_on_cxl_phb(dev) && adapter->slices >= 1)
+		pnv_cxl_phb_set_peer_afu(dev, adapter->afu[0]);
+
 	return 0;
 }
 
@@ -1381,6 +1776,9 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
 		 */
 		for (i = 0; i < adapter->slices; i++) {
 			afu = adapter->afu[i];
+			/* Only participate in EEH if we are on a virtual PHB */
+			if (afu->phb == NULL)
+				return PCI_ERS_RESULT_NONE;
 			cxl_vphb_error_detected(afu, state);
 		}
 		return PCI_ERS_RESULT_DISCONNECT;
diff --git a/drivers/misc/cxl/phb.c b/drivers/misc/cxl/phb.c
new file mode 100644
index 000000000000..0935d44c1770
--- /dev/null
+++ b/drivers/misc/cxl/phb.c
@@ -0,0 +1,44 @@
+/*
+ * Copyright 2014-2016 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/pci.h>
+#include "cxl.h"
+
+bool _cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu)
+{
+	struct cxl_context *ctx;
+
+	/*
+	 * Allocate a context to do cxl things to. This is used for interrupts
+	 * in the peer model using a real phb, and if we eventually do DMA ops
+	 * in the virtual phb, we'll need a default context to attach them to.
+	 */
+	ctx = cxl_dev_context_init(dev);
+	if (!ctx)
+		return false;
+	dev->dev.archdata.cxl_ctx = ctx;
+
+	return (cxl_ops->afu_check_and_enable(afu) == 0);
+}
+/* exported via cxl_base */
+
+void _cxl_pci_disable_device(struct pci_dev *dev)
+{
+	struct cxl_context *ctx = cxl_get_context(dev);
+
+	if (ctx) {
+		if (ctx->status == STARTED) {
+			dev_err(&dev->dev, "Default context started\n");
+			return;
+		}
+		dev->dev.archdata.cxl_ctx = NULL;
+		cxl_release_context(ctx);
+	}
+}
+/* exported via cxl_base */
diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c
index cdc7723b845d..dee8def1c193 100644
--- a/drivers/misc/cxl/vphb.c
+++ b/drivers/misc/cxl/vphb.c
@@ -9,6 +9,7 @@
 
 #include <linux/pci.h>
 #include <misc/cxl.h>
+#include <asm/pnv-pci.h>
 #include "cxl.h"
 
 static int cxl_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
@@ -44,7 +45,6 @@ static bool cxl_pci_enable_device_hook(struct pci_dev *dev)
 {
 	struct pci_controller *phb;
 	struct cxl_afu *afu;
-	struct cxl_context *ctx;
 
 	phb = pci_bus_to_host(dev->bus);
 	afu = (struct cxl_afu *)phb->private_data;
@@ -57,30 +57,7 @@ static bool cxl_pci_enable_device_hook(struct pci_dev *dev)
 	set_dma_ops(&dev->dev, &dma_direct_ops);
 	set_dma_offset(&dev->dev, PAGE_OFFSET);
 
-	/*
-	 * Allocate a context to do cxl things too.  If we eventually do real
-	 * DMA ops, we'll need a default context to attach them to
-	 */
-	ctx = cxl_dev_context_init(dev);
-	if (!ctx)
-		return false;
-	dev->dev.archdata.cxl_ctx = ctx;
-
-	return (cxl_ops->afu_check_and_enable(afu) == 0);
-}
-
-static void cxl_pci_disable_device(struct pci_dev *dev)
-{
-	struct cxl_context *ctx = cxl_get_context(dev);
-
-	if (ctx) {
-		if (ctx->status == STARTED) {
-			dev_err(&dev->dev, "Default context started\n");
-			return;
-		}
-		dev->dev.archdata.cxl_ctx = NULL;
-		cxl_release_context(ctx);
-	}
+	return _cxl_pci_associate_default_context(dev, afu);
 }
 
 static resource_size_t cxl_pci_window_alignment(struct pci_bus *bus,
@@ -197,8 +174,8 @@ static struct pci_controller_ops cxl_pci_controller_ops =
 {
 	.probe_mode = cxl_pci_probe_mode,
 	.enable_device_hook = cxl_pci_enable_device_hook,
-	.disable_device = cxl_pci_disable_device,
-	.release_device = cxl_pci_disable_device,
+	.disable_device = _cxl_pci_disable_device,
+	.release_device = _cxl_pci_disable_device,
 	.window_alignment = cxl_pci_window_alignment,
 	.reset_secondary_bus = cxl_pci_reset_secondary_bus,
 	.setup_msi_irqs = cxl_setup_msi_irqs,
@@ -208,20 +185,30 @@ static struct pci_controller_ops cxl_pci_controller_ops =
 
 int cxl_pci_vphb_add(struct cxl_afu *afu)
 {
-	struct pci_dev *phys_dev;
-	struct pci_controller *phb, *phys_phb;
+	struct pci_controller *phb;
 	struct device_node *vphb_dn;
 	struct device *parent;
 
-	if (cpu_has_feature(CPU_FTR_HVMODE)) {
-		phys_dev = to_pci_dev(afu->adapter->dev.parent);
-		phys_phb = pci_bus_to_host(phys_dev->bus);
-		vphb_dn = phys_phb->dn;
-		parent = &phys_dev->dev;
-	} else {
-		vphb_dn = afu->adapter->dev.parent->of_node;
-		parent = afu->adapter->dev.parent;
-	}
+	/*
+	 * If there are no AFU configuration records we won't have anything to
+	 * expose under the vPHB, so skip creating one, returning success since
+	 * this is still a valid case. This will also opt us out of EEH
+	 * handling since we won't have anything special to do if there are no
+	 * kernel drivers attached to the vPHB, and EEH handling is not yet
+	 * supported in the peer model.
+	 */
+	if (!afu->crs_num)
+		return 0;
+
+	/* The parent device is the adapter. Reuse the device node of
+	 * the adapter.
+	 * We don't seem to care what device node is used for the vPHB,
+	 * but tools such as lsvpd walk up the device parents looking
+	 * for a valid location code, so we might as well show devices
+	 * attached to the adapter as being located on that adapter.
+	 */
+	parent = afu->adapter->dev.parent;
+	vphb_dn = parent->of_node;
 
 	/* Alloc and setup PHB data structure */
 	phb = pcibios_alloc_controller(vphb_dn);
@@ -272,13 +259,18 @@ void cxl_pci_vphb_remove(struct cxl_afu *afu)
 	pcibios_free_controller(phb);
 }
 
+static bool _cxl_pci_is_vphb_device(struct pci_controller *phb)
+{
+	return (phb->ops == &cxl_pcie_pci_ops);
+}
+
 bool cxl_pci_is_vphb_device(struct pci_dev *dev)
 {
 	struct pci_controller *phb;
 
 	phb = pci_bus_to_host(dev->bus);
 
-	return (phb->ops == &cxl_pcie_pci_ops);
+	return _cxl_pci_is_vphb_device(phb);
 }
 
 struct cxl_afu *cxl_pci_to_afu(struct pci_dev *dev)
@@ -287,7 +279,13 @@ struct cxl_afu *cxl_pci_to_afu(struct pci_dev *dev)
 
 	phb = pci_bus_to_host(dev->bus);
 
-	return (struct cxl_afu *)phb->private_data;
+	if (_cxl_pci_is_vphb_device(phb))
+		return (struct cxl_afu *)phb->private_data;
+
+	if (pnv_pci_on_cxl_phb(dev))
+		return pnv_cxl_phb_to_afu(phb);
+
+	return ERR_PTR(-ENODEV);
 }
 EXPORT_SYMBOL_GPL(cxl_pci_to_afu);
 
diff --git a/drivers/misc/genwqe/card_base.c b/drivers/misc/genwqe/card_base.c
index 4cf8f82cfca2..a70b853fa2c9 100644
--- a/drivers/misc/genwqe/card_base.c
+++ b/drivers/misc/genwqe/card_base.c
@@ -182,7 +182,7 @@ static void genwqe_dev_free(struct genwqe_dev *cd)
  */
 static int genwqe_bus_reset(struct genwqe_dev *cd)
 {
-	int bars, rc = 0;
+	int rc = 0;
 	struct pci_dev *pci_dev = cd->pci_dev;
 	void __iomem *mmio;
 
@@ -193,8 +193,7 @@ static int genwqe_bus_reset(struct genwqe_dev *cd)
 	cd->mmio = NULL;
 	pci_iounmap(pci_dev, mmio);
 
-	bars = pci_select_bars(pci_dev, IORESOURCE_MEM);
-	pci_release_selected_regions(pci_dev, bars);
+	pci_release_mem_regions(pci_dev);
 
 	/*
 	 * Firmware/BIOS might change memory mapping during bus reset.
@@ -218,7 +217,7 @@ static int genwqe_bus_reset(struct genwqe_dev *cd)
 			    GENWQE_INJECT_GFIR_FATAL |
 			    GENWQE_INJECT_GFIR_INFO);
 
-	rc = pci_request_selected_regions(pci_dev, bars, genwqe_driver_name);
+	rc = pci_request_mem_regions(pci_dev, genwqe_driver_name);
 	if (rc) {
 		dev_err(&pci_dev->dev,
 			"[%s] err: request bars failed (%d)\n", __func__, rc);
@@ -1068,10 +1067,9 @@ static int genwqe_health_check_stop(struct genwqe_dev *cd)
  */
 static int genwqe_pci_setup(struct genwqe_dev *cd)
 {
-	int err, bars;
+	int err;
 	struct pci_dev *pci_dev = cd->pci_dev;
 
-	bars = pci_select_bars(pci_dev, IORESOURCE_MEM);
 	err = pci_enable_device_mem(pci_dev);
 	if (err) {
 		dev_err(&pci_dev->dev,
@@ -1080,7 +1078,7 @@ static int genwqe_pci_setup(struct genwqe_dev *cd)
 	}
 
 	/* Reserve PCI I/O and memory resources */
-	err = pci_request_selected_regions(pci_dev, bars, genwqe_driver_name);
+	err = pci_request_mem_regions(pci_dev, genwqe_driver_name);
 	if (err) {
 		dev_err(&pci_dev->dev,
 			"[%s] err: request bars failed (%d)\n", __func__, err);
@@ -1142,7 +1140,7 @@ static int genwqe_pci_setup(struct genwqe_dev *cd)
  out_iounmap:
 	pci_iounmap(pci_dev, cd->mmio);
  out_release_resources:
-	pci_release_selected_regions(pci_dev, bars);
+	pci_release_mem_regions(pci_dev);
  err_disable_device:
 	pci_disable_device(pci_dev);
  err_out:
@@ -1154,14 +1152,12 @@ static int genwqe_pci_setup(struct genwqe_dev *cd)
  */
 static void genwqe_pci_remove(struct genwqe_dev *cd)
 {
-	int bars;
 	struct pci_dev *pci_dev = cd->pci_dev;
 
 	if (cd->mmio)
 		pci_iounmap(pci_dev, cd->mmio);
 
-	bars = pci_select_bars(pci_dev, IORESOURCE_MEM);
-	pci_release_selected_regions(pci_dev, bars);
+	pci_release_mem_regions(pci_dev);
 	pci_disable_device(pci_dev);
 }
 
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 10b553765ee7..48a5dd740f3b 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1801,8 +1801,7 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq,
 		do_data_tag = (card->ext_csd.data_tag_unit_size) &&
 			(prq->cmd_flags & REQ_META) &&
 			(rq_data_dir(prq) == WRITE) &&
-			((brq->data.blocks * brq->data.blksz) >=
-			 card->ext_csd.data_tag_unit_size);
+			blk_rq_bytes(prq) >= card->ext_csd.data_tag_unit_size;
 		/* Argument of CMD23 */
 		packed_cmd_hdr[(i * 2)] = cpu_to_le32(
 			(do_rel_wr ? MMC_CMD23_ARG_REL_WR : 0) |
@@ -1977,8 +1976,8 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 			 * When 4KB native sector is enabled, only 8 blocks
 			 * multiple read or write is allowed
 			 */
-			if ((brq->data.blocks & 0x07) &&
-			    (card->ext_csd.data_sector_size == 4096)) {
+			if (mmc_large_sector(card) &&
+				!IS_ALIGNED(blk_rq_sectors(rqc), 8)) {
 				pr_err("%s: Transfer size is not 4KB sector size aligned\n",
 					req->rq_disk->disk_name);
 				mq_rq = mq->mqrq_cur;
@@ -2501,12 +2500,6 @@ force_ro_fail:
 	return ret;
 }
 
-#define CID_MANFID_SANDISK	0x2
-#define CID_MANFID_TOSHIBA	0x11
-#define CID_MANFID_MICRON	0x13
-#define CID_MANFID_SAMSUNG	0x15
-#define CID_MANFID_KINGSTON	0x70
-
 static const struct mmc_fixup blk_fixups[] =
 {
 	MMC_FIXUP("SEM02G", CID_MANFID_SANDISK, 0x100, add_quirk,
diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index 4bc48f10452f..c64266f5a399 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -332,12 +332,13 @@ int mmc_add_card(struct mmc_card *card)
 			mmc_card_ddr52(card) ? "DDR " : "",
 			type);
 	} else {
-		pr_info("%s: new %s%s%s%s%s card at address %04x\n",
+		pr_info("%s: new %s%s%s%s%s%s card at address %04x\n",
 			mmc_hostname(card->host),
 			mmc_card_uhs(card) ? "ultra high speed " :
 			(mmc_card_hs(card) ? "high speed " : ""),
 			mmc_card_hs400(card) ? "HS400 " :
 			(mmc_card_hs200(card) ? "HS200 " : ""),
+			mmc_card_hs400es(card) ? "Enhanced strobe " : "",
 			mmc_card_ddr52(card) ? "DDR " : "",
 			uhs_bus_speed_mode, type, card->rca);
 	}
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 8b4dfd45433b..e55cde6d436d 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -1127,6 +1127,15 @@ void mmc_set_initial_state(struct mmc_host *host)
 	host->ios.bus_width = MMC_BUS_WIDTH_1;
 	host->ios.timing = MMC_TIMING_LEGACY;
 	host->ios.drv_type = 0;
+	host->ios.enhanced_strobe = false;
+
+	/*
+	 * Make sure we are in non-enhanced strobe mode before we
+	 * actually enable it in ext_csd.
+	 */
+	if ((host->caps2 & MMC_CAP2_HS400_ES) &&
+	     host->ops->hs400_enhanced_strobe)
+		host->ops->hs400_enhanced_strobe(host, &host->ios);
 
 	mmc_set_ios(host);
 }
@@ -1925,17 +1934,15 @@ void mmc_init_erase(struct mmc_card *card)
 	 * to that size and alignment.
 	 *
 	 * For SD cards that define Allocation Unit size, limit erases to one
-	 * Allocation Unit at a time.  For MMC cards that define High Capacity
-	 * Erase Size, whether it is switched on or not, limit to that size.
-	 * Otherwise just have a stab at a good value.  For modern cards it
-	 * will end up being 4MiB.  Note that if the value is too small, it
-	 * can end up taking longer to erase.
+	 * Allocation Unit at a time.
+	 * For MMC, have a stab at ai good value and for modern cards it will
+	 * end up being 4MiB. Note that if the value is too small, it can end
+	 * up taking longer to erase. Also note, erase_size is already set to
+	 * High Capacity Erase Size if available when this function is called.
 	 */
 	if (mmc_card_sd(card) && card->ssr.au) {
 		card->pref_erase = card->ssr.au;
 		card->erase_shift = ffs(card->ssr.au) - 1;
-	} else if (card->ext_csd.hc_erase_size) {
-		card->pref_erase = card->ext_csd.hc_erase_size;
 	} else if (card->erase_size) {
 		sz = (card->csd.capacity << (card->csd.read_blkbits - 9)) >> 11;
 		if (sz < 128)
@@ -2060,7 +2067,8 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 			unsigned int to, unsigned int arg)
 {
 	struct mmc_command cmd = {0};
-	unsigned int qty = 0;
+	unsigned int qty = 0, busy_timeout = 0;
+	bool use_r1b_resp = false;
 	unsigned long timeout;
 	int err;
 
@@ -2128,8 +2136,22 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	memset(&cmd, 0, sizeof(struct mmc_command));
 	cmd.opcode = MMC_ERASE;
 	cmd.arg = arg;
-	cmd.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
-	cmd.busy_timeout = mmc_erase_timeout(card, arg, qty);
+	busy_timeout = mmc_erase_timeout(card, arg, qty);
+	/*
+	 * If the host controller supports busy signalling and the timeout for
+	 * the erase operation does not exceed the max_busy_timeout, we should
+	 * use R1B response. Or we need to prevent the host from doing hw busy
+	 * detection, which is done by converting to a R1 response instead.
+	 */
+	if (card->host->max_busy_timeout &&
+	    busy_timeout > card->host->max_busy_timeout) {
+		cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_AC;
+	} else {
+		cmd.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
+		cmd.busy_timeout = busy_timeout;
+		use_r1b_resp = true;
+	}
+
 	err = mmc_wait_for_cmd(card->host, &cmd, 0);
 	if (err) {
 		pr_err("mmc_erase: erase error %d, status %#x\n",
@@ -2141,7 +2163,14 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	if (mmc_host_is_spi(card->host))
 		goto out;
 
-	timeout = jiffies + msecs_to_jiffies(MMC_CORE_TIMEOUT_MS);
+	/*
+	 * In case of when R1B + MMC_CAP_WAIT_WHILE_BUSY is used, the polling
+	 * shall be avoided.
+	 */
+	if ((card->host->caps & MMC_CAP_WAIT_WHILE_BUSY) && use_r1b_resp)
+		goto out;
+
+	timeout = jiffies + msecs_to_jiffies(busy_timeout);
 	do {
 		memset(&cmd, 0, sizeof(struct mmc_command));
 		cmd.opcode = MMC_SEND_STATUS;
@@ -2321,23 +2350,41 @@ static unsigned int mmc_do_calc_max_discard(struct mmc_card *card,
 					    unsigned int arg)
 {
 	struct mmc_host *host = card->host;
-	unsigned int max_discard, x, y, qty = 0, max_qty, timeout;
+	unsigned int max_discard, x, y, qty = 0, max_qty, min_qty, timeout;
 	unsigned int last_timeout = 0;
 
-	if (card->erase_shift)
+	if (card->erase_shift) {
 		max_qty = UINT_MAX >> card->erase_shift;
-	else if (mmc_card_sd(card))
+		min_qty = card->pref_erase >> card->erase_shift;
+	} else if (mmc_card_sd(card)) {
 		max_qty = UINT_MAX;
-	else
+		min_qty = card->pref_erase;
+	} else {
 		max_qty = UINT_MAX / card->erase_size;
+		min_qty = card->pref_erase / card->erase_size;
+	}
 
-	/* Find the largest qty with an OK timeout */
+	/*
+	 * We should not only use 'host->max_busy_timeout' as the limitation
+	 * when deciding the max discard sectors. We should set a balance value
+	 * to improve the erase speed, and it can not get too long timeout at
+	 * the same time.
+	 *
+	 * Here we set 'card->pref_erase' as the minimal discard sectors no
+	 * matter what size of 'host->max_busy_timeout', but if the
+	 * 'host->max_busy_timeout' is large enough for more discard sectors,
+	 * then we can continue to increase the max discard sectors until we
+	 * get a balance value.
+	 */
 	do {
 		y = 0;
 		for (x = 1; x && x <= max_qty && max_qty - x >= qty; x <<= 1) {
 			timeout = mmc_erase_timeout(card, arg, qty + x);
-			if (timeout > host->max_busy_timeout)
+
+			if (qty + x > min_qty &&
+			    timeout > host->max_busy_timeout)
 				break;
+
 			if (timeout < last_timeout)
 				break;
 			last_timeout = timeout;
@@ -2491,17 +2538,21 @@ static int mmc_rescan_try_freq(struct mmc_host *host, unsigned freq)
 
 	mmc_go_idle(host);
 
-	mmc_send_if_cond(host, host->ocr_avail);
+	if (!(host->caps2 & MMC_CAP2_NO_SD))
+		mmc_send_if_cond(host, host->ocr_avail);
 
 	/* Order's important: probe SDIO, then SD, then MMC */
 	if (!(host->caps2 & MMC_CAP2_NO_SDIO))
 		if (!mmc_attach_sdio(host))
 			return 0;
 
-	if (!mmc_attach_sd(host))
-		return 0;
-	if (!mmc_attach_mmc(host))
-		return 0;
+	if (!(host->caps2 & MMC_CAP2_NO_SD))
+		if (!mmc_attach_sd(host))
+			return 0;
+
+	if (!(host->caps2 & MMC_CAP2_NO_MMC))
+		if (!mmc_attach_mmc(host))
+			return 0;
 
 	mmc_power_off(host);
 	return -EIO;
diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c
index 9382a57a5aa4..c8451ce557ae 100644
--- a/drivers/mmc/core/debugfs.c
+++ b/drivers/mmc/core/debugfs.c
@@ -148,7 +148,8 @@ static int mmc_ios_show(struct seq_file *s, void *data)
 		str = "mmc HS200";
 		break;
 	case MMC_TIMING_MMC_HS400:
-		str = "mmc HS400";
+		str = mmc_card_hs400es(host->card) ?
+			"mmc HS400 enhanced strobe" : "mmc HS400";
 		break;
 	default:
 		str = "invalid";
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 1be42fab1a30..98f25ffb4258 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -313,6 +313,14 @@ int mmc_of_parse(struct mmc_host *host)
 		host->caps2 |= MMC_CAP2_HS400_1_8V | MMC_CAP2_HS200_1_8V_SDR;
 	if (of_property_read_bool(np, "mmc-hs400-1_2v"))
 		host->caps2 |= MMC_CAP2_HS400_1_2V | MMC_CAP2_HS200_1_2V_SDR;
+	if (of_property_read_bool(np, "mmc-hs400-enhanced-strobe"))
+		host->caps2 |= MMC_CAP2_HS400_ES;
+	if (of_property_read_bool(np, "no-sdio"))
+		host->caps2 |= MMC_CAP2_NO_SDIO;
+	if (of_property_read_bool(np, "no-sd"))
+		host->caps2 |= MMC_CAP2_NO_SD;
+	if (of_property_read_bool(np, "no-mmc"))
+		host->caps2 |= MMC_CAP2_NO_MMC;
 
 	host->dsr_req = !of_property_read_u32(np, "dsr", &host->dsr);
 	if (host->dsr_req && (host->dsr & ~0xffff)) {
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 5d438ad3ee32..f2d185cf8a8b 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -45,6 +45,17 @@ static const unsigned int tacc_mant[] = {
 	35,	40,	45,	50,	55,	60,	70,	80,
 };
 
+static const struct mmc_fixup mmc_ext_csd_fixups[] = {
+	/*
+	 * Certain Hynix eMMC 4.41 cards might get broken when HPI feature
+	 * is used so disable the HPI feature for such buggy cards.
+	 */
+	MMC_FIXUP_EXT_CSD_REV(CID_NAME_ANY, CID_MANFID_HYNIX,
+			      0x014a, add_quirk, MMC_QUIRK_BROKEN_HPI, 5),
+
+	END_FIXUP
+};
+
 #define UNSTUFF_BITS(resp,start,size)					\
 	({								\
 		const int __size = size;				\
@@ -235,6 +246,11 @@ static void mmc_select_card_type(struct mmc_card *card)
 		avail_type |= EXT_CSD_CARD_TYPE_HS400_1_2V;
 	}
 
+	if ((caps2 & MMC_CAP2_HS400_ES) &&
+	    card->ext_csd.strobe_support &&
+	    (avail_type & EXT_CSD_CARD_TYPE_HS400))
+		avail_type |= EXT_CSD_CARD_TYPE_HS400ES;
+
 	card->ext_csd.hs_max_dtr = hs_max_dtr;
 	card->ext_csd.hs200_max_dtr = hs200_max_dtr;
 	card->mmc_avail_type = avail_type;
@@ -370,6 +386,9 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 	 */
 	card->ext_csd.rev = ext_csd[EXT_CSD_REV];
 
+	/* fixup device after ext_csd revision field is updated */
+	mmc_fixup_device(card, mmc_ext_csd_fixups);
+
 	card->ext_csd.raw_sectors[0] = ext_csd[EXT_CSD_SEC_CNT + 0];
 	card->ext_csd.raw_sectors[1] = ext_csd[EXT_CSD_SEC_CNT + 1];
 	card->ext_csd.raw_sectors[2] = ext_csd[EXT_CSD_SEC_CNT + 2];
@@ -386,6 +405,7 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 			mmc_card_set_blockaddr(card);
 	}
 
+	card->ext_csd.strobe_support = ext_csd[EXT_CSD_STROBE_SUPPORT];
 	card->ext_csd.raw_card_type = ext_csd[EXT_CSD_CARD_TYPE];
 	mmc_select_card_type(card);
 
@@ -500,7 +520,8 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 			card->cid.year += 16;
 
 		/* check whether the eMMC card supports BKOPS */
-		if (ext_csd[EXT_CSD_BKOPS_SUPPORT] & 0x1) {
+		if (!mmc_card_broken_hpi(card) &&
+		    ext_csd[EXT_CSD_BKOPS_SUPPORT] & 0x1) {
 			card->ext_csd.bkops = 1;
 			card->ext_csd.man_bkops_en =
 					(ext_csd[EXT_CSD_BKOPS_EN] &
@@ -513,7 +534,8 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		}
 
 		/* check whether the eMMC card supports HPI */
-		if (!broken_hpi && (ext_csd[EXT_CSD_HPI_FEATURES] & 0x1)) {
+		if (!mmc_card_broken_hpi(card) &&
+		    !broken_hpi && (ext_csd[EXT_CSD_HPI_FEATURES] & 0x1)) {
 			card->ext_csd.hpi = 1;
 			if (ext_csd[EXT_CSD_HPI_FEATURES] & 0x2)
 				card->ext_csd.hpi_cmd =	MMC_STOP_TRANSMISSION;
@@ -727,6 +749,7 @@ MMC_DEV_ATTR(enhanced_area_offset, "%llu\n",
 MMC_DEV_ATTR(enhanced_area_size, "%u\n", card->ext_csd.enhanced_area_size);
 MMC_DEV_ATTR(raw_rpmb_size_mult, "%#x\n", card->ext_csd.raw_rpmb_size_mult);
 MMC_DEV_ATTR(rel_sectors, "%#x\n", card->ext_csd.rel_sectors);
+MMC_DEV_ATTR(ocr, "%08x\n", card->ocr);
 
 static ssize_t mmc_fwrev_show(struct device *dev,
 			      struct device_attribute *attr,
@@ -744,6 +767,22 @@ static ssize_t mmc_fwrev_show(struct device *dev,
 
 static DEVICE_ATTR(fwrev, S_IRUGO, mmc_fwrev_show, NULL);
 
+static ssize_t mmc_dsr_show(struct device *dev,
+			    struct device_attribute *attr,
+			    char *buf)
+{
+	struct mmc_card *card = mmc_dev_to_card(dev);
+	struct mmc_host *host = card->host;
+
+	if (card->csd.dsr_imp && host->dsr_req)
+		return sprintf(buf, "0x%x\n", host->dsr);
+	else
+		/* return default DSR value */
+		return sprintf(buf, "0x%x\n", 0x404);
+}
+
+static DEVICE_ATTR(dsr, S_IRUGO, mmc_dsr_show, NULL);
+
 static struct attribute *mmc_std_attrs[] = {
 	&dev_attr_cid.attr,
 	&dev_attr_csd.attr,
@@ -762,6 +801,8 @@ static struct attribute *mmc_std_attrs[] = {
 	&dev_attr_enhanced_area_size.attr,
 	&dev_attr_raw_rpmb_size_mult.attr,
 	&dev_attr_rel_sectors.attr,
+	&dev_attr_ocr.attr,
+	&dev_attr_dsr.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(mmc_std);
@@ -959,6 +1000,19 @@ static int mmc_select_bus_width(struct mmc_card *card)
 	return err;
 }
 
+/* Caller must hold re-tuning */
+static int mmc_switch_status(struct mmc_card *card)
+{
+	u32 status;
+	int err;
+
+	err = mmc_send_status(card, &status);
+	if (err)
+		return err;
+
+	return mmc_switch_status_error(card->host, status);
+}
+
 /*
  * Switch to the high-speed mode
  */
@@ -969,9 +1023,11 @@ static int mmc_select_hs(struct mmc_card *card)
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS,
 			   card->ext_csd.generic_cmd6_time,
-			   true, true, true);
-	if (!err)
+			   true, false, true);
+	if (!err) {
 		mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
+		err = mmc_switch_status(card);
+	}
 
 	return err;
 }
@@ -1047,23 +1103,9 @@ static int mmc_select_hs_ddr(struct mmc_card *card)
 	return err;
 }
 
-/* Caller must hold re-tuning */
-static int mmc_switch_status(struct mmc_card *card)
-{
-	u32 status;
-	int err;
-
-	err = mmc_send_status(card, &status);
-	if (err)
-		return err;
-
-	return mmc_switch_status_error(card->host, status);
-}
-
 static int mmc_select_hs400(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
-	bool send_status = true;
 	unsigned int max_dtr;
 	int err = 0;
 	u8 val;
@@ -1075,19 +1117,12 @@ static int mmc_select_hs400(struct mmc_card *card)
 	      host->ios.bus_width == MMC_BUS_WIDTH_8))
 		return 0;
 
-	if (host->caps & MMC_CAP_WAIT_WHILE_BUSY)
-		send_status = false;
-
-	/* Reduce frequency to HS frequency */
-	max_dtr = card->ext_csd.hs_max_dtr;
-	mmc_set_clock(host, max_dtr);
-
 	/* Switch card to HS mode */
 	val = EXT_CSD_TIMING_HS;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			   EXT_CSD_HS_TIMING, val,
 			   card->ext_csd.generic_cmd6_time,
-			   true, send_status, true);
+			   true, false, true);
 	if (err) {
 		pr_err("%s: switch to high-speed from hs200 failed, err:%d\n",
 			mmc_hostname(host), err);
@@ -1097,11 +1132,13 @@ static int mmc_select_hs400(struct mmc_card *card)
 	/* Set host controller to HS timing */
 	mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
 
-	if (!send_status) {
-		err = mmc_switch_status(card);
-		if (err)
-			goto out_err;
-	}
+	/* Reduce frequency to HS frequency */
+	max_dtr = card->ext_csd.hs_max_dtr;
+	mmc_set_clock(host, max_dtr);
+
+	err = mmc_switch_status(card);
+	if (err)
+		goto out_err;
 
 	/* Switch card to DDR */
 	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
@@ -1120,7 +1157,7 @@ static int mmc_select_hs400(struct mmc_card *card)
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			   EXT_CSD_HS_TIMING, val,
 			   card->ext_csd.generic_cmd6_time,
-			   true, send_status, true);
+			   true, false, true);
 	if (err) {
 		pr_err("%s: switch to hs400 failed, err:%d\n",
 			 mmc_hostname(host), err);
@@ -1131,11 +1168,9 @@ static int mmc_select_hs400(struct mmc_card *card)
 	mmc_set_timing(host, MMC_TIMING_MMC_HS400);
 	mmc_set_bus_speed(card);
 
-	if (!send_status) {
-		err = mmc_switch_status(card);
-		if (err)
-			goto out_err;
-	}
+	err = mmc_switch_status(card);
+	if (err)
+		goto out_err;
 
 	return 0;
 
@@ -1153,14 +1188,10 @@ int mmc_hs200_to_hs400(struct mmc_card *card)
 int mmc_hs400_to_hs200(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
-	bool send_status = true;
 	unsigned int max_dtr;
 	int err;
 	u8 val;
 
-	if (host->caps & MMC_CAP_WAIT_WHILE_BUSY)
-		send_status = false;
-
 	/* Reduce frequency to HS */
 	max_dtr = card->ext_csd.hs_max_dtr;
 	mmc_set_clock(host, max_dtr);
@@ -1169,49 +1200,43 @@ int mmc_hs400_to_hs200(struct mmc_card *card)
 	val = EXT_CSD_TIMING_HS;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING,
 			   val, card->ext_csd.generic_cmd6_time,
-			   true, send_status, true);
+			   true, false, true);
 	if (err)
 		goto out_err;
 
 	mmc_set_timing(host, MMC_TIMING_MMC_DDR52);
 
-	if (!send_status) {
-		err = mmc_switch_status(card);
-		if (err)
-			goto out_err;
-	}
+	err = mmc_switch_status(card);
+	if (err)
+		goto out_err;
 
 	/* Switch HS DDR to HS */
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_BUS_WIDTH,
 			   EXT_CSD_BUS_WIDTH_8, card->ext_csd.generic_cmd6_time,
-			   true, send_status, true);
+			   true, false, true);
 	if (err)
 		goto out_err;
 
 	mmc_set_timing(host, MMC_TIMING_MMC_HS);
 
-	if (!send_status) {
-		err = mmc_switch_status(card);
-		if (err)
-			goto out_err;
-	}
+	err = mmc_switch_status(card);
+	if (err)
+		goto out_err;
 
 	/* Switch HS to HS200 */
 	val = EXT_CSD_TIMING_HS200 |
 	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING,
-			   val, card->ext_csd.generic_cmd6_time, true,
-			   send_status, true);
+			   val, card->ext_csd.generic_cmd6_time,
+			   true, false, true);
 	if (err)
 		goto out_err;
 
 	mmc_set_timing(host, MMC_TIMING_MMC_HS200);
 
-	if (!send_status) {
-		err = mmc_switch_status(card);
-		if (err)
-			goto out_err;
-	}
+	err = mmc_switch_status(card);
+	if (err)
+		goto out_err;
 
 	mmc_set_bus_speed(card);
 
@@ -1223,6 +1248,78 @@ out_err:
 	return err;
 }
 
+static int mmc_select_hs400es(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	int err = 0;
+	u8 val;
+
+	if (!(host->caps & MMC_CAP_8_BIT_DATA)) {
+		err = -ENOTSUPP;
+		goto out_err;
+	}
+
+	err = mmc_select_bus_width(card);
+	if (err < 0)
+		goto out_err;
+
+	/* Switch card to HS mode */
+	err = mmc_select_hs(card);
+	if (err) {
+		pr_err("%s: switch to high-speed failed, err:%d\n",
+			mmc_hostname(host), err);
+		goto out_err;
+	}
+
+	err = mmc_switch_status(card);
+	if (err)
+		goto out_err;
+
+	/* Switch card to DDR with strobe bit */
+	val = EXT_CSD_DDR_BUS_WIDTH_8 | EXT_CSD_BUS_WIDTH_STROBE;
+	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			 EXT_CSD_BUS_WIDTH,
+			 val,
+			 card->ext_csd.generic_cmd6_time);
+	if (err) {
+		pr_err("%s: switch to bus width for hs400es failed, err:%d\n",
+			mmc_hostname(host), err);
+		goto out_err;
+	}
+
+	/* Switch card to HS400 */
+	val = EXT_CSD_TIMING_HS400 |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			   EXT_CSD_HS_TIMING, val,
+			   card->ext_csd.generic_cmd6_time,
+			   true, false, true);
+	if (err) {
+		pr_err("%s: switch to hs400es failed, err:%d\n",
+			mmc_hostname(host), err);
+		goto out_err;
+	}
+
+	/* Set host controller to HS400 timing and frequency */
+	mmc_set_timing(host, MMC_TIMING_MMC_HS400);
+
+	/* Controller enable enhanced strobe function */
+	host->ios.enhanced_strobe = true;
+	if (host->ops->hs400_enhanced_strobe)
+		host->ops->hs400_enhanced_strobe(host, &host->ios);
+
+	err = mmc_switch_status(card);
+	if (err)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	pr_err("%s: %s failed, error %d\n", mmc_hostname(card->host),
+	       __func__, err);
+	return err;
+}
+
 static void mmc_select_driver_type(struct mmc_card *card)
 {
 	int card_drv_type, drive_strength, drv_type;
@@ -1250,7 +1347,6 @@ static void mmc_select_driver_type(struct mmc_card *card)
 static int mmc_select_hs200(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
-	bool send_status = true;
 	unsigned int old_timing, old_signal_voltage;
 	int err = -EINVAL;
 	u8 val;
@@ -1268,34 +1364,30 @@ static int mmc_select_hs200(struct mmc_card *card)
 
 	mmc_select_driver_type(card);
 
-	if (host->caps & MMC_CAP_WAIT_WHILE_BUSY)
-		send_status = false;
-
 	/*
 	 * Set the bus width(4 or 8) with host's support and
 	 * switch to HS200 mode if bus width is set successfully.
 	 */
 	err = mmc_select_bus_width(card);
-	if (err >= 0) {
+	if (err > 0) {
 		val = EXT_CSD_TIMING_HS200 |
 		      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 		err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 				   EXT_CSD_HS_TIMING, val,
 				   card->ext_csd.generic_cmd6_time,
-				   true, send_status, true);
+				   true, false, true);
 		if (err)
 			goto err;
 		old_timing = host->ios.timing;
 		mmc_set_timing(host, MMC_TIMING_MMC_HS200);
-		if (!send_status) {
-			err = mmc_switch_status(card);
-			/*
-			 * mmc_select_timing() assumes timing has not changed if
-			 * it is a switch error.
-			 */
-			if (err == -EBADMSG)
-				mmc_set_timing(host, old_timing);
-		}
+
+		err = mmc_switch_status(card);
+		/*
+		 * mmc_select_timing() assumes timing has not changed if
+		 * it is a switch error.
+		 */
+		if (err == -EBADMSG)
+			mmc_set_timing(host, old_timing);
 	}
 err:
 	if (err) {
@@ -1310,7 +1402,7 @@ err:
 }
 
 /*
- * Activate High Speed or HS200 mode if supported.
+ * Activate High Speed, HS200 or HS400ES mode if supported.
  */
 static int mmc_select_timing(struct mmc_card *card)
 {
@@ -1319,7 +1411,9 @@ static int mmc_select_timing(struct mmc_card *card)
 	if (!mmc_can_ext_csd(card))
 		goto bus_speed;
 
-	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS200)
+	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400ES)
+		err = mmc_select_hs400es(card);
+	else if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS200)
 		err = mmc_select_hs200(card);
 	else if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS)
 		err = mmc_select_hs(card);
@@ -1583,7 +1677,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	} else if (mmc_card_hs(card)) {
 		/* Select the desired bus width optionally */
 		err = mmc_select_bus_width(card);
-		if (err >= 0) {
+		if (err > 0) {
 			err = mmc_select_hs_ddr(card);
 			if (err)
 				goto free_card;
@@ -1616,7 +1710,8 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	 * If cache size is higher than 0, this indicates
 	 * the existence of cache and it can be turned on.
 	 */
-	if (card->ext_csd.cache_size > 0) {
+	if (!mmc_card_broken_hpi(card) &&
+	    card->ext_csd.cache_size > 0) {
 		err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 				EXT_CSD_CACHE_CTRL, 1,
 				card->ext_csd.generic_cmd6_time);
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 62355bda608f..ad6e9798e949 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -480,6 +480,7 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 	u32 status = 0;
 	bool use_r1b_resp = use_busy_signal;
 	bool expired = false;
+	bool busy = false;
 
 	mmc_retune_hold(host);
 
@@ -533,21 +534,26 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		timeout_ms = MMC_OPS_TIMEOUT_MS;
 
 	/* Must check status to be sure of no errors. */
-	timeout = jiffies + msecs_to_jiffies(timeout_ms);
+	timeout = jiffies + msecs_to_jiffies(timeout_ms) + 1;
 	do {
+		/*
+		 * Due to the possibility of being preempted after
+		 * sending the status command, check the expiration
+		 * time first.
+		 */
+		expired = time_after(jiffies, timeout);
 		if (send_status) {
-			/*
-			 * Due to the possibility of being preempted after
-			 * sending the status command, check the expiration
-			 * time first.
-			 */
-			expired = time_after(jiffies, timeout);
 			err = __mmc_send_status(card, &status, ignore_crc);
 			if (err)
 				goto out;
 		}
 		if ((host->caps & MMC_CAP_WAIT_WHILE_BUSY) && use_r1b_resp)
 			break;
+		if (host->ops->card_busy) {
+			if (!host->ops->card_busy(host))
+				break;
+			busy = true;
+		}
 		if (mmc_host_is_spi(host))
 			break;
 
@@ -556,19 +562,20 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		 * does'nt support MMC_CAP_WAIT_WHILE_BUSY, then we can only
 		 * rely on waiting for the stated timeout to be sufficient.
 		 */
-		if (!send_status) {
+		if (!send_status && !host->ops->card_busy) {
 			mmc_delay(timeout_ms);
 			goto out;
 		}
 
 		/* Timeout if the device never leaves the program state. */
-		if (expired && R1_CURRENT_STATE(status) == R1_STATE_PRG) {
+		if (expired &&
+		    (R1_CURRENT_STATE(status) == R1_STATE_PRG || busy)) {
 			pr_err("%s: Card stuck in programming state! %s\n",
 				mmc_hostname(host), __func__);
 			err = -ETIMEDOUT;
 			goto out;
 		}
-	} while (R1_CURRENT_STATE(status) == R1_STATE_PRG);
+	} while (R1_CURRENT_STATE(status) == R1_STATE_PRG || busy);
 
 	err = mmc_switch_status_error(host, status);
 out:
diff --git a/drivers/mmc/core/quirks.c b/drivers/mmc/core/quirks.c
index fad660b95809..ca9cade317c7 100644
--- a/drivers/mmc/core/quirks.c
+++ b/drivers/mmc/core/quirks.c
@@ -72,6 +72,8 @@ void mmc_fixup_device(struct mmc_card *card, const struct mmc_fixup *table)
 		     f->cis_vendor == (u16) SDIO_ANY_ID) &&
 		    (f->cis_device == card->cis.device ||
 		     f->cis_device == (u16) SDIO_ANY_ID) &&
+		    (f->ext_csd_rev == EXT_CSD_REV_ANY ||
+		     f->ext_csd_rev == card->ext_csd.rev) &&
 		    rev >= f->rev_start && rev <= f->rev_end) {
 			dev_dbg(&card->dev, "calling %pf\n", f->vendor_fixup);
 			f->vendor_fixup(card, f->data);
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index b95bd24d92f4..0123936241b0 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -675,8 +675,25 @@ MMC_DEV_ATTR(manfid, "0x%06x\n", card->cid.manfid);
 MMC_DEV_ATTR(name, "%s\n", card->cid.prod_name);
 MMC_DEV_ATTR(oemid, "0x%04x\n", card->cid.oemid);
 MMC_DEV_ATTR(serial, "0x%08x\n", card->cid.serial);
+MMC_DEV_ATTR(ocr, "%08x\n", card->ocr);
 
 
+static ssize_t mmc_dsr_show(struct device *dev,
+                           struct device_attribute *attr,
+                           char *buf)
+{
+       struct mmc_card *card = mmc_dev_to_card(dev);
+       struct mmc_host *host = card->host;
+
+       if (card->csd.dsr_imp && host->dsr_req)
+               return sprintf(buf, "0x%x\n", host->dsr);
+       else
+               /* return default DSR value */
+               return sprintf(buf, "0x%x\n", 0x404);
+}
+
+static DEVICE_ATTR(dsr, S_IRUGO, mmc_dsr_show, NULL);
+
 static struct attribute *sd_std_attrs[] = {
 	&dev_attr_cid.attr,
 	&dev_attr_csd.attr,
@@ -690,6 +707,8 @@ static struct attribute *sd_std_attrs[] = {
 	&dev_attr_name.attr,
 	&dev_attr_oemid.attr,
 	&dev_attr_serial.attr,
+	&dev_attr_ocr.attr,
+	&dev_attr_dsr.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(sd_std);
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 0aa484c10c0a..5274f503a39a 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -122,6 +122,7 @@ config MMC_SDHCI_OF_ARASAN
 	tristate "SDHCI OF support for the Arasan SDHCI controllers"
 	depends on MMC_SDHCI_PLTFM
 	depends on OF
+	depends on COMMON_CLK
 	help
 	  This selects the Arasan Secure Digital Host Controller Interface
 	  (SDHCI). This hardware is found e.g. in Xilinx' Zynq SoC.
@@ -296,17 +297,6 @@ config MMC_SDHCI_BCM_KONA
 
 	  If you have a controller with this interface, say Y or M here.
 
-config MMC_SDHCI_BCM2835
-	tristate "SDHCI platform support for the BCM2835 SD/MMC Controller"
-	depends on ARCH_BCM2835
-	depends on MMC_SDHCI_PLTFM
-	select MMC_SDHCI_IO_ACCESSORS
-	help
-	  This selects the BCM2835 SD/MMC controller. If you have a BCM2835
-	  platform with SD or MMC devices, say Y or M here.
-
-	  If unsure, say N.
-
 config MMC_SDHCI_F_SDH30
 	tristate "SDHCI support for Fujitsu Semiconductor F_SDH30"
 	depends on MMC_SDHCI_PLTFM
@@ -798,3 +788,13 @@ config MMC_SDHCI_MICROCHIP_PIC32
           If you have a controller with this interface, say Y or M here.
 
           If unsure, say N.
+config MMC_SDHCI_BRCMSTB
+	tristate "Broadcom SDIO/SD/MMC support"
+	depends on ARCH_BRCMSTB || BMIPS_GENERIC
+	depends on MMC_SDHCI_PLTFM
+	default y
+	help
+	  This selects support for the SDIO/SD/MMC Host Controller on
+	  Broadcom STB SoCs.
+
+	  If unsure, say Y.
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index af918d261ff9..e2bdaaf43184 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -71,11 +71,11 @@ obj-$(CONFIG_MMC_SDHCI_OF_AT91)		+= sdhci-of-at91.o
 obj-$(CONFIG_MMC_SDHCI_OF_ESDHC)	+= sdhci-of-esdhc.o
 obj-$(CONFIG_MMC_SDHCI_OF_HLWD)		+= sdhci-of-hlwd.o
 obj-$(CONFIG_MMC_SDHCI_BCM_KONA)	+= sdhci-bcm-kona.o
-obj-$(CONFIG_MMC_SDHCI_BCM2835)		+= sdhci-bcm2835.o
 obj-$(CONFIG_MMC_SDHCI_IPROC)		+= sdhci-iproc.o
 obj-$(CONFIG_MMC_SDHCI_MSM)		+= sdhci-msm.o
 obj-$(CONFIG_MMC_SDHCI_ST)		+= sdhci-st.o
 obj-$(CONFIG_MMC_SDHCI_MICROCHIP_PIC32)	+= sdhci-pic32.o
+obj-$(CONFIG_MMC_SDHCI_BRCMSTB)		+= sdhci-brcmstb.o
 
 ifeq ($(CONFIG_CB710_DEBUG),y)
 	CFLAGS-cb710-mmc	+= -DDEBUG
diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index 7e3a3247b852..da0ef1765735 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -157,7 +157,7 @@ static void dw_mci_exynos_set_clksel_timing(struct dw_mci *host, u32 timing)
 	 * HOLD register should be bypassed in case there is no phase shift
 	 * applied on CMD/DATA that is sent to the card.
 	 */
-	if (!SDMMC_CLKSEL_GET_DRV_WD3(clksel))
+	if (!SDMMC_CLKSEL_GET_DRV_WD3(clksel) && host->cur_slot)
 		set_bit(DW_MMC_CARD_NO_USE_HOLD, &host->cur_slot->flags);
 }
 
diff --git a/drivers/mmc/host/dw_mmc-k3.c b/drivers/mmc/host/dw_mmc-k3.c
index 63c2e2ed1288..8e9d886bfcda 100644
--- a/drivers/mmc/host/dw_mmc-k3.c
+++ b/drivers/mmc/host/dw_mmc-k3.c
@@ -32,6 +32,12 @@ struct k3_priv {
 	struct regmap	*reg;
 };
 
+static unsigned long dw_mci_hi6220_caps[] = {
+	MMC_CAP_CMD23,
+	MMC_CAP_CMD23,
+	0
+};
+
 static void dw_mci_k3_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 {
 	int ret;
@@ -126,6 +132,7 @@ static void dw_mci_hi6220_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 }
 
 static const struct dw_mci_drv_data hi6220_data = {
+	.caps			= dw_mci_hi6220_caps,
 	.switch_voltage		= dw_mci_hi6220_switch_voltage,
 	.set_ios		= dw_mci_hi6220_set_ios,
 	.parse_dt		= dw_mci_hi6220_parse_dt,
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index 358b0dc853b0..25eae359a5ea 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -285,9 +285,6 @@ static int dw_mci_rockchip_init(struct dw_mci *host)
 	/* It is slot 8 on Rockchip SoCs */
 	host->sdio_id0 = 8;
 
-	/* It needs this quirk on all Rockchip SoCs */
-	host->pdata->quirks |= DW_MCI_QUIRK_BROKEN_DTO;
-
 	if (of_device_is_compatible(host->dev->of_node,
 				    "rockchip,rk3288-dw-mshc"))
 		host->bus_hz /= RK3288_CLKGEN_DIV;
@@ -297,10 +294,10 @@ static int dw_mci_rockchip_init(struct dw_mci *host)
 
 /* Common capabilities of RK3288 SoC */
 static unsigned long dw_mci_rk3288_dwmmc_caps[4] = {
-	MMC_CAP_ERASE | MMC_CAP_CMD23,
-	MMC_CAP_ERASE | MMC_CAP_CMD23,
-	MMC_CAP_ERASE | MMC_CAP_CMD23,
-	MMC_CAP_ERASE | MMC_CAP_CMD23,
+	MMC_CAP_CMD23,
+	MMC_CAP_CMD23,
+	MMC_CAP_CMD23,
+	MMC_CAP_CMD23,
 };
 
 static const struct dw_mci_drv_data rk2928_drv_data = {
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 2cc6123b1df9..32380d5d4f6b 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -44,11 +44,11 @@
 /* Common flag combinations */
 #define DW_MCI_DATA_ERROR_FLAGS	(SDMMC_INT_DRTO | SDMMC_INT_DCRC | \
 				 SDMMC_INT_HTO | SDMMC_INT_SBE  | \
-				 SDMMC_INT_EBE)
+				 SDMMC_INT_EBE | SDMMC_INT_HLE)
 #define DW_MCI_CMD_ERROR_FLAGS	(SDMMC_INT_RTO | SDMMC_INT_RCRC | \
-				 SDMMC_INT_RESP_ERR)
+				 SDMMC_INT_RESP_ERR | SDMMC_INT_HLE)
 #define DW_MCI_ERROR_FLAGS	(DW_MCI_DATA_ERROR_FLAGS | \
-				 DW_MCI_CMD_ERROR_FLAGS  | SDMMC_INT_HLE)
+				 DW_MCI_CMD_ERROR_FLAGS)
 #define DW_MCI_SEND_STATUS	1
 #define DW_MCI_RECV_STATUS	2
 #define DW_MCI_DMA_THRESHOLD	16
@@ -92,7 +92,7 @@ struct idmac_desc {
 
 	__le32		des1;	/* Buffer sizes */
 #define IDMAC_SET_BUFFER1_SIZE(d, s) \
-	((d)->des1 = ((d)->des1 & 0x03ffe000) | ((s) & 0x1fff))
+	((d)->des1 = ((d)->des1 & cpu_to_le32(0x03ffe000)) | (cpu_to_le32((s) & 0x1fff)))
 
 	__le32		des2;	/* buffer 1 physical address */
 
@@ -105,6 +105,7 @@ struct idmac_desc {
 static bool dw_mci_reset(struct dw_mci *host);
 static bool dw_mci_ctrl_reset(struct dw_mci *host, u32 reset);
 static int dw_mci_card_busy(struct mmc_host *mmc);
+static int dw_mci_get_cd(struct mmc_host *mmc);
 
 #if defined(CONFIG_DEBUG_FS)
 static int dw_mci_req_show(struct seq_file *s, void *v)
@@ -898,23 +899,35 @@ done:
 	mci_writel(host, FIFOTH, fifoth_val);
 }
 
-static void dw_mci_ctrl_rd_thld(struct dw_mci *host, struct mmc_data *data)
+static void dw_mci_ctrl_thld(struct dw_mci *host, struct mmc_data *data)
 {
 	unsigned int blksz = data->blksz;
 	u32 blksz_depth, fifo_depth;
 	u16 thld_size;
-
-	WARN_ON(!(data->flags & MMC_DATA_READ));
+	u8 enable;
 
 	/*
 	 * CDTHRCTL doesn't exist prior to 240A (in fact that register offset is
 	 * in the FIFO region, so we really shouldn't access it).
 	 */
-	if (host->verid < DW_MMC_240A)
+	if (host->verid < DW_MMC_240A ||
+		(host->verid < DW_MMC_280A && data->flags & MMC_DATA_WRITE))
+		return;
+
+	/*
+	 * Card write Threshold is introduced since 2.80a
+	 * It's used when HS400 mode is enabled.
+	 */
+	if (data->flags & MMC_DATA_WRITE &&
+		!(host->timing != MMC_TIMING_MMC_HS400))
 		return;
 
+	if (data->flags & MMC_DATA_WRITE)
+		enable = SDMMC_CARD_WR_THR_EN;
+	else
+		enable = SDMMC_CARD_RD_THR_EN;
+
 	if (host->timing != MMC_TIMING_MMC_HS200 &&
-	    host->timing != MMC_TIMING_MMC_HS400 &&
 	    host->timing != MMC_TIMING_UHS_SDR104)
 		goto disable;
 
@@ -930,11 +943,11 @@ static void dw_mci_ctrl_rd_thld(struct dw_mci *host, struct mmc_data *data)
 	 * Currently just choose blksz.
 	 */
 	thld_size = blksz;
-	mci_writel(host, CDTHRCTL, SDMMC_SET_RD_THLD(thld_size, 1));
+	mci_writel(host, CDTHRCTL, SDMMC_SET_THLD(thld_size, enable));
 	return;
 
 disable:
-	mci_writel(host, CDTHRCTL, SDMMC_SET_RD_THLD(0, 0));
+	mci_writel(host, CDTHRCTL, 0);
 }
 
 static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
@@ -1005,12 +1018,12 @@ static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data)
 	host->sg = NULL;
 	host->data = data;
 
-	if (data->flags & MMC_DATA_READ) {
+	if (data->flags & MMC_DATA_READ)
 		host->dir_status = DW_MCI_RECV_STATUS;
-		dw_mci_ctrl_rd_thld(host, data);
-	} else {
+	else
 		host->dir_status = DW_MCI_SEND_STATUS;
-	}
+
+	dw_mci_ctrl_thld(host, data);
 
 	if (dw_mci_submit_data_dma(host, data)) {
 		if (host->data->flags & MMC_DATA_READ)
@@ -1099,12 +1112,11 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 
 		div = (host->bus_hz != clock) ? DIV_ROUND_UP(div, 2) : 0;
 
-		if ((clock << div) != slot->__clk_old || force_clkinit)
-			dev_info(&slot->mmc->class_dev,
-				 "Bus speed (slot %d) = %dHz (slot req %dHz, actual %dHZ div = %d)\n",
-				 slot->id, host->bus_hz, clock,
-				 div ? ((host->bus_hz / div) >> 1) :
-				 host->bus_hz, div);
+		dev_info(&slot->mmc->class_dev,
+			 "Bus speed (slot %d) = %dHz (slot req %dHz, actual %dHZ div = %d)\n",
+			 slot->id, host->bus_hz, clock,
+			 div ? ((host->bus_hz / div) >> 1) :
+			 host->bus_hz, div);
 
 		/* disable clock */
 		mci_writel(host, CLKENA, 0);
@@ -1127,9 +1139,6 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 
 		/* inform CIU */
 		mci_send_cmd(slot, sdmmc_cmd_bits, 0);
-
-		/* keep the clock with reflecting clock dividor */
-		slot->__clk_old = clock << div;
 	}
 
 	host->current_speed = clock;
@@ -1253,15 +1262,15 @@ static void dw_mci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	 * atomic, otherwise the card could be removed in between and the
 	 * request wouldn't fail until another card was inserted.
 	 */
-	spin_lock_bh(&host->lock);
 
-	if (!test_bit(DW_MMC_CARD_PRESENT, &slot->flags)) {
-		spin_unlock_bh(&host->lock);
+	if (!dw_mci_get_cd(mmc)) {
 		mrq->cmd->error = -ENOMEDIUM;
 		mmc_request_done(mmc, mrq);
 		return;
 	}
 
+	spin_lock_bh(&host->lock);
+
 	dw_mci_queue_request(host, slot, mrq);
 
 	spin_unlock_bh(&host->lock);
@@ -1451,8 +1460,7 @@ static int dw_mci_get_cd(struct mmc_host *mmc)
 	int gpio_cd = mmc_gpio_get_cd(mmc);
 
 	/* Use platform get_cd function, else try onboard card detect */
-	if ((mmc->caps & MMC_CAP_NEEDS_POLL) ||
-	    (mmc->caps & MMC_CAP_NONREMOVABLE))
+	if ((mmc->caps & MMC_CAP_NEEDS_POLL) || !mmc_card_is_removable(mmc))
 		present = 1;
 	else if (gpio_cd >= 0)
 		present = gpio_cd;
@@ -1761,6 +1769,33 @@ static void dw_mci_tasklet_func(unsigned long priv)
 			}
 
 			if (cmd->data && err) {
+				/*
+				 * During UHS tuning sequence, sending the stop
+				 * command after the response CRC error would
+				 * throw the system into a confused state
+				 * causing all future tuning phases to report
+				 * failure.
+				 *
+				 * In such case controller will move into a data
+				 * transfer state after a response error or
+				 * response CRC error. Let's let that finish
+				 * before trying to send a stop, so we'll go to
+				 * STATE_SENDING_DATA.
+				 *
+				 * Although letting the data transfer take place
+				 * will waste a bit of time (we already know
+				 * the command was bad), it can't cause any
+				 * errors since it's possible it would have
+				 * taken place anyway if this tasklet got
+				 * delayed. Allowing the transfer to take place
+				 * avoids races and keeps things simple.
+				 */
+				if ((err != -ETIMEDOUT) &&
+				    (cmd->opcode == MMC_SEND_TUNING_BLOCK)) {
+					state = STATE_SENDING_DATA;
+					continue;
+				}
+
 				dw_mci_stop_dma(host);
 				send_stop_abort(host, data);
 				state = STATE_SENDING_STOP;
@@ -1801,8 +1836,7 @@ static void dw_mci_tasklet_func(unsigned long priv)
 				 * If all data-related interrupts don't come
 				 * within the given time in reading data state.
 				 */
-				if ((host->quirks & DW_MCI_QUIRK_BROKEN_DTO) &&
-				    (host->dir_status == DW_MCI_RECV_STATUS))
+				if (host->dir_status == DW_MCI_RECV_STATUS)
 					dw_mci_set_drto(host);
 				break;
 			}
@@ -1844,8 +1878,7 @@ static void dw_mci_tasklet_func(unsigned long priv)
 				 * interrupt doesn't come within the given time.
 				 * in reading data state.
 				 */
-				if ((host->quirks & DW_MCI_QUIRK_BROKEN_DTO) &&
-				    (host->dir_status == DW_MCI_RECV_STATUS))
+				if (host->dir_status == DW_MCI_RECV_STATUS)
 					dw_mci_set_drto(host);
 				break;
 			}
@@ -2411,8 +2444,7 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 		}
 
 		if (pending & SDMMC_INT_DATA_OVER) {
-			if (host->quirks & DW_MCI_QUIRK_BROKEN_DTO)
-				del_timer(&host->dto_timer);
+			del_timer(&host->dto_timer);
 
 			mci_writel(host, RINTSTS, SDMMC_INT_DATA_OVER);
 			if (!host->data_status)
@@ -2474,7 +2506,8 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 			mci_writel(host, IDSTS64, SDMMC_IDMAC_INT_TI |
 							SDMMC_IDMAC_INT_RI);
 			mci_writel(host, IDSTS64, SDMMC_IDMAC_INT_NI);
-			host->dma_ops->complete((void *)host);
+			if (!test_bit(EVENT_DATA_ERROR, &host->pending_events))
+				host->dma_ops->complete((void *)host);
 		}
 	} else {
 		pending = mci_readl(host, IDSTS);
@@ -2482,7 +2515,8 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 			mci_writel(host, IDSTS, SDMMC_IDMAC_INT_TI |
 							SDMMC_IDMAC_INT_RI);
 			mci_writel(host, IDSTS, SDMMC_IDMAC_INT_NI);
-			host->dma_ops->complete((void *)host);
+			if (!test_bit(EVENT_DATA_ERROR, &host->pending_events))
+				host->dma_ops->complete((void *)host);
 		}
 	}
 
@@ -2570,6 +2604,12 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	if (host->pdata->caps)
 		mmc->caps = host->pdata->caps;
 
+	/*
+	 * Support MMC_CAP_ERASE by default.
+	 * It needs to use trim/discard/erase commands.
+	 */
+	mmc->caps |= MMC_CAP_ERASE;
+
 	if (host->pdata->pm_caps)
 		mmc->pm_caps = host->pdata->pm_caps;
 
@@ -2616,10 +2656,7 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 		mmc->max_seg_size = mmc->max_req_size;
 	}
 
-	if (dw_mci_get_cd(mmc))
-		set_bit(DW_MMC_CARD_PRESENT, &slot->flags);
-	else
-		clear_bit(DW_MMC_CARD_PRESENT, &slot->flags);
+	dw_mci_get_cd(mmc);
 
 	ret = mmc_add_host(mmc);
 	if (ret)
@@ -3006,11 +3043,8 @@ int dw_mci_probe(struct dw_mci *host)
 	setup_timer(&host->cmd11_timer,
 		    dw_mci_cmd11_timer, (unsigned long)host);
 
-	host->quirks = host->pdata->quirks;
-
-	if (host->quirks & DW_MCI_QUIRK_BROKEN_DTO)
-		setup_timer(&host->dto_timer,
-			    dw_mci_dto_timer, (unsigned long)host);
+	setup_timer(&host->dto_timer,
+		    dw_mci_dto_timer, (unsigned long)host);
 
 	spin_lock_init(&host->lock);
 	spin_lock_init(&host->irq_lock);
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index 1e8d8380f9cf..9e740bc232a8 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -15,6 +15,7 @@
 #define _DW_MMC_H_
 
 #define DW_MMC_240A		0x240a
+#define DW_MMC_280A		0x280a
 
 #define SDMMC_CTRL		0x000
 #define SDMMC_PWREN		0x004
@@ -175,7 +176,10 @@
 /* Version ID register define */
 #define SDMMC_GET_VERID(x)		((x) & 0xFFFF)
 /* Card read threshold */
-#define SDMMC_SET_RD_THLD(v, x)		(((v) & 0xFFF) << 16 | (x))
+#define SDMMC_SET_THLD(v, x)		(((v) & 0xFFF) << 16 | (x))
+#define SDMMC_CARD_WR_THR_EN		BIT(2)
+#define SDMMC_CARD_RD_THR_EN		BIT(0)
+/* UHS-1 register defines */
 #define SDMMC_UHS_18V			BIT(0)
 /* All ctrl reset bits */
 #define SDMMC_CTRL_ALL_RESET_FLAGS \
@@ -245,9 +249,6 @@ extern int dw_mci_resume(struct dw_mci *host);
  * @queue_node: List node for placing this node in the @queue list of
  *	&struct dw_mci.
  * @clock: Clock rate configured by set_ios(). Protected by host->lock.
- * @__clk_old: The last updated clock with reflecting clock divider.
- *	Keeping track of this helps us to avoid spamming the console
- *	with CONFIG_MMC_CLKGATE.
  * @flags: Random state bits associated with the slot.
  * @id: Number of this slot.
  * @sdio_id: Number of this slot in the SDIO interrupt registers.
@@ -262,7 +263,6 @@ struct dw_mci_slot {
 	struct list_head	queue_node;
 
 	unsigned int		clock;
-	unsigned int		__clk_old;
 
 	unsigned long		flags;
 #define DW_MMC_CARD_PRESENT	0
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 5642f71f8bf0..84e9afcb5c09 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -287,6 +287,11 @@ struct msdc_save_para {
 	u32 emmc50_cfg0;
 };
 
+struct msdc_tune_para {
+	u32 iocon;
+	u32 pad_tune;
+};
+
 struct msdc_delay_phase {
 	u8 maxlen;
 	u8 start;
@@ -326,7 +331,10 @@ struct msdc_host {
 	unsigned char timing;
 	bool vqmmc_enabled;
 	u32 hs400_ds_delay;
+	bool hs400_mode;	/* current eMMC will run at hs400 mode */
 	struct msdc_save_para save_para; /* used when gate HCLK */
+	struct msdc_tune_para def_tune_para; /* default tune setting */
+	struct msdc_tune_para saved_tune_para; /* tune result of CMD21/CMD19 */
 };
 
 static void sdr_set_bits(void __iomem *reg, u32 bs)
@@ -582,6 +590,18 @@ static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz)
 	msdc_set_timeout(host, host->timeout_ns, host->timeout_clks);
 	sdr_set_bits(host->base + MSDC_INTEN, flags);
 
+	/*
+	 * mmc_select_hs400() will drop to 50Mhz and High speed mode,
+	 * tune result of hs200/200Mhz is not suitable for 50Mhz
+	 */
+	if (host->sclk <= 52000000) {
+		writel(host->def_tune_para.iocon, host->base + MSDC_IOCON);
+		writel(host->def_tune_para.pad_tune, host->base + MSDC_PAD_TUNE);
+	} else {
+		writel(host->saved_tune_para.iocon, host->base + MSDC_IOCON);
+		writel(host->saved_tune_para.pad_tune, host->base + MSDC_PAD_TUNE);
+	}
+
 	dev_dbg(host->dev, "sclk: %d, timing: %d\n", host->sclk, timing);
 }
 
@@ -781,7 +801,13 @@ static bool msdc_cmd_done(struct msdc_host *host, int events,
 	}
 
 	if (!sbc_error && !(events & MSDC_INT_CMDRDY)) {
-		msdc_reset_hw(host);
+		if (cmd->opcode != MMC_SEND_TUNING_BLOCK &&
+		    cmd->opcode != MMC_SEND_TUNING_BLOCK_HS200)
+			/*
+			 * should not clear fifo/interrupt as the tune data
+			 * may have alreay come.
+			 */
+			msdc_reset_hw(host);
 		if (events & MSDC_INT_RSPCRCERR) {
 			cmd->error = -EILSEQ;
 			host->error |= REQ_CMD_EIO;
@@ -865,7 +891,11 @@ static void msdc_start_command(struct msdc_host *host,
 static void msdc_cmd_next(struct msdc_host *host,
 		struct mmc_request *mrq, struct mmc_command *cmd)
 {
-	if (cmd->error || (mrq->sbc && mrq->sbc->error))
+	if ((cmd->error &&
+	    !(cmd->error == -EILSEQ &&
+	      (cmd->opcode == MMC_SEND_TUNING_BLOCK ||
+	       cmd->opcode == MMC_SEND_TUNING_BLOCK_HS200))) ||
+	    (mrq->sbc && mrq->sbc->error))
 		msdc_request_done(host, mrq);
 	else if (cmd == mrq->sbc)
 		msdc_start_command(host, mrq, mrq->cmd);
@@ -1158,6 +1188,8 @@ static void msdc_init_hw(struct msdc_host *host)
 	/* Configure to default data timeout */
 	sdr_set_field(host->base + SDC_CFG, SDC_CFG_DTOC, 3);
 
+	host->def_tune_para.iocon = readl(host->base + MSDC_IOCON);
+	host->def_tune_para.pad_tune = readl(host->base + MSDC_PAD_TUNE);
 	dev_dbg(host->dev, "init hardware done!");
 }
 
@@ -1296,7 +1328,7 @@ static int msdc_tune_response(struct mmc_host *mmc, u32 opcode)
 {
 	struct msdc_host *host = mmc_priv(mmc);
 	u32 rise_delay = 0, fall_delay = 0;
-	struct msdc_delay_phase final_rise_delay, final_fall_delay;
+	struct msdc_delay_phase final_rise_delay, final_fall_delay = { 0,};
 	u8 final_delay, final_maxlen;
 	int cmd_err;
 	int i;
@@ -1309,6 +1341,11 @@ static int msdc_tune_response(struct mmc_host *mmc, u32 opcode)
 		if (!cmd_err)
 			rise_delay |= (1 << i);
 	}
+	final_rise_delay = get_best_delay(host, rise_delay);
+	/* if rising edge has enough margin, then do not scan falling edge */
+	if (final_rise_delay.maxlen >= 10 ||
+	    (final_rise_delay.start == 0 && final_rise_delay.maxlen >= 4))
+		goto skip_fall;
 
 	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
 	for (i = 0; i < PAD_DELAY_MAX; i++) {
@@ -1318,10 +1355,9 @@ static int msdc_tune_response(struct mmc_host *mmc, u32 opcode)
 		if (!cmd_err)
 			fall_delay |= (1 << i);
 	}
-
-	final_rise_delay = get_best_delay(host, rise_delay);
 	final_fall_delay = get_best_delay(host, fall_delay);
 
+skip_fall:
 	final_maxlen = max(final_rise_delay.maxlen, final_fall_delay.maxlen);
 	if (final_maxlen == final_rise_delay.maxlen) {
 		sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
@@ -1342,7 +1378,7 @@ static int msdc_tune_data(struct mmc_host *mmc, u32 opcode)
 {
 	struct msdc_host *host = mmc_priv(mmc);
 	u32 rise_delay = 0, fall_delay = 0;
-	struct msdc_delay_phase final_rise_delay, final_fall_delay;
+	struct msdc_delay_phase final_rise_delay, final_fall_delay = { 0,};
 	u8 final_delay, final_maxlen;
 	int i, ret;
 
@@ -1355,6 +1391,11 @@ static int msdc_tune_data(struct mmc_host *mmc, u32 opcode)
 		if (!ret)
 			rise_delay |= (1 << i);
 	}
+	final_rise_delay = get_best_delay(host, rise_delay);
+	/* if rising edge has enough margin, then do not scan falling edge */
+	if (final_rise_delay.maxlen >= 10 ||
+	    (final_rise_delay.start == 0 && final_rise_delay.maxlen >= 4))
+		goto skip_fall;
 
 	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_DSPL);
 	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_W_DSPL);
@@ -1365,14 +1406,10 @@ static int msdc_tune_data(struct mmc_host *mmc, u32 opcode)
 		if (!ret)
 			fall_delay |= (1 << i);
 	}
-
-	final_rise_delay = get_best_delay(host, rise_delay);
 	final_fall_delay = get_best_delay(host, fall_delay);
 
+skip_fall:
 	final_maxlen = max(final_rise_delay.maxlen, final_fall_delay.maxlen);
-	/* Rising edge is more stable, prefer to use it */
-	if (final_rise_delay.maxlen >= 10)
-		final_maxlen = final_rise_delay.maxlen;
 	if (final_maxlen == final_rise_delay.maxlen) {
 		sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_DSPL);
 		sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_W_DSPL);
@@ -1402,16 +1439,21 @@ static int msdc_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		dev_err(host->dev, "Tune response fail!\n");
 		return ret;
 	}
-	ret = msdc_tune_data(mmc, opcode);
-	if (ret == -EIO)
-		dev_err(host->dev, "Tune data fail!\n");
+	if (host->hs400_mode == false) {
+		ret = msdc_tune_data(mmc, opcode);
+		if (ret == -EIO)
+			dev_err(host->dev, "Tune data fail!\n");
+	}
 
+	host->saved_tune_para.iocon = readl(host->base + MSDC_IOCON);
+	host->saved_tune_para.pad_tune = readl(host->base + MSDC_PAD_TUNE);
 	return ret;
 }
 
 static int msdc_prepare_hs400_tuning(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct msdc_host *host = mmc_priv(mmc);
+	host->hs400_mode = true;
 
 	writel(host->hs400_ds_delay, host->base + PAD_DS_TUNE);
 	return 0;
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 3d1ea5e0e549..fb3ca8296273 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -1065,7 +1065,7 @@ static int mxcmci_probe(struct platform_device *pdev)
 
 	if (pdata)
 		dat3_card_detect = pdata->dat3_card_detect;
-	else if (!(mmc->caps & MMC_CAP_NONREMOVABLE)
+	else if (mmc_card_is_removable(mmc)
 			&& !of_property_read_bool(pdev->dev.of_node, "cd-gpios"))
 		dat3_card_detect = true;
 
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 93137483ecde..396c9b7e4121 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -38,7 +38,6 @@ struct realtek_pci_sdmmc {
 	struct rtsx_pcr		*pcr;
 	struct mmc_host		*mmc;
 	struct mmc_request	*mrq;
-	struct workqueue_struct *workq;
 #define SDMMC_WORKQ_NAME	"rtsx_pci_sdmmc_workq"
 
 	struct work_struct	work;
@@ -244,7 +243,7 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 	stat_idx = sd_status_index(rsp_type);
 
 	if (rsp_type == SD_RSP_TYPE_R1b)
-		timeout = 3000;
+		timeout = cmd->busy_timeout ? cmd->busy_timeout : 3000;
 
 	if (cmd->opcode == SD_SWITCH_VOLTAGE) {
 		err = rtsx_pci_write_register(pcr, SD_BUS_STAT,
@@ -885,7 +884,7 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	if (sd_rw_cmd(mrq->cmd) || sdio_extblock_cmd(mrq->cmd, data))
 		host->using_cookie = sd_pre_dma_transfer(host, data, false);
 
-	queue_work(host->workq, &host->work);
+	schedule_work(&host->work);
 }
 
 static int sd_set_bus_width(struct realtek_pci_sdmmc *host,
@@ -1360,7 +1359,7 @@ static void realtek_init_host(struct realtek_pci_sdmmc *host)
 	mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34 | MMC_VDD_165_195;
 	mmc->caps = MMC_CAP_4_BIT_DATA | MMC_CAP_SD_HIGHSPEED |
 		MMC_CAP_MMC_HIGHSPEED | MMC_CAP_BUS_WIDTH_TEST |
-		MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25;
+		MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 | MMC_CAP_ERASE;
 	mmc->caps2 = MMC_CAP2_NO_PRESCAN_POWERUP | MMC_CAP2_FULL_PWR_CYCLE;
 	mmc->max_current_330 = 400;
 	mmc->max_current_180 = 800;
@@ -1404,11 +1403,6 @@ static int rtsx_pci_sdmmc_drv_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	host = mmc_priv(mmc);
-	host->workq = create_singlethread_workqueue(SDMMC_WORKQ_NAME);
-	if (!host->workq) {
-		mmc_free_host(mmc);
-		return -ENOMEM;
-	}
 	host->pcr = pcr;
 	host->mmc = mmc;
 	host->pdev = pdev;
@@ -1462,9 +1456,7 @@ static int rtsx_pci_sdmmc_drv_remove(struct platform_device *pdev)
 	mmc_remove_host(mmc);
 	host->eject = true;
 
-	flush_workqueue(host->workq);
-	destroy_workqueue(host->workq);
-	host->workq = NULL;
+	flush_work(&host->work);
 
 	mmc_free_host(mmc);
 
diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c
index 39814f3dc96f..c531deef3258 100644
--- a/drivers/mmc/host/s3cmci.c
+++ b/drivers/mmc/host/s3cmci.c
@@ -1365,7 +1365,7 @@ static struct s3c24xx_mci_pdata s3cmci_def_pdata = {
 	 .no_detect = 1,
 };
 
-#ifdef CONFIG_CPU_FREQ
+#ifdef CONFIG_ARM_S3C24XX_CPUFREQ
 
 static int s3cmci_cpufreq_transition(struct notifier_block *nb,
 				     unsigned long val, void *data)
diff --git a/drivers/mmc/host/s3cmci.h b/drivers/mmc/host/s3cmci.h
index cc2e46cb5c64..30c2c0dd1bc8 100644
--- a/drivers/mmc/host/s3cmci.h
+++ b/drivers/mmc/host/s3cmci.h
@@ -74,7 +74,7 @@ struct s3cmci_host {
 	struct dentry		*debug_regs;
 #endif
 
-#ifdef CONFIG_CPU_FREQ
+#ifdef CONFIG_ARM_S3C24XX_CPUFREQ
 	struct notifier_block	freq_transition;
 #endif
 };
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 008709c5cb09..8fe0756c8e1e 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -532,11 +532,6 @@ static int sdhci_acpi_resume(struct device *dev)
 	return sdhci_resume_host(c->host);
 }
 
-#else
-
-#define sdhci_acpi_suspend	NULL
-#define sdhci_acpi_resume	NULL
-
 #endif
 
 #ifdef CONFIG_PM
@@ -560,8 +555,7 @@ static int sdhci_acpi_runtime_resume(struct device *dev)
 #endif
 
 static const struct dev_pm_ops sdhci_acpi_pm_ops = {
-	.suspend		= sdhci_acpi_suspend,
-	.resume			= sdhci_acpi_resume,
+	SET_SYSTEM_SLEEP_PM_OPS(sdhci_acpi_suspend, sdhci_acpi_resume)
 	SET_RUNTIME_PM_OPS(sdhci_acpi_runtime_suspend,
 			sdhci_acpi_runtime_resume, NULL)
 };
diff --git a/drivers/mmc/host/sdhci-bcm-kona.c b/drivers/mmc/host/sdhci-bcm-kona.c
index 00a8a40a3729..e5c634bdfdd9 100644
--- a/drivers/mmc/host/sdhci-bcm-kona.c
+++ b/drivers/mmc/host/sdhci-bcm-kona.c
@@ -264,12 +264,12 @@ static int sdhci_bcm_kona_probe(struct platform_device *pdev)
 	}
 
 	dev_dbg(dev, "non-removable=%c\n",
-		(host->mmc->caps & MMC_CAP_NONREMOVABLE) ? 'Y' : 'N');
+		mmc_card_is_removable(host->mmc) ? 'N' : 'Y');
 	dev_dbg(dev, "cd_gpio %c, wp_gpio %c\n",
 		(mmc_gpio_get_cd(host->mmc) != -ENOSYS) ? 'Y' : 'N',
 		(mmc_gpio_get_ro(host->mmc) != -ENOSYS) ? 'Y' : 'N');
 
-	if (host->mmc->caps & MMC_CAP_NONREMOVABLE)
+	if (!mmc_card_is_removable(host->mmc))
 		host->quirks |= SDHCI_QUIRK_BROKEN_CARD_DETECTION;
 
 	dev_dbg(dev, "is_8bit=%c\n",
@@ -288,7 +288,7 @@ static int sdhci_bcm_kona_probe(struct platform_device *pdev)
 	}
 
 	/* if device is eMMC, emulate card insert right here */
-	if (host->mmc->caps & MMC_CAP_NONREMOVABLE) {
+	if (!mmc_card_is_removable(host->mmc)) {
 		ret = sdhci_bcm_kona_sd_card_emulate(host, 1);
 		if (ret) {
 			dev_err(dev,
@@ -326,7 +326,7 @@ err_pltfm_free:
 static struct platform_driver sdhci_bcm_kona_driver = {
 	.driver		= {
 		.name	= "sdhci-kona",
-		.pm	= SDHCI_PLTFM_PMOPS,
+		.pm	= &sdhci_pltfm_pmops,
 		.of_match_table = sdhci_bcm_kona_of_match,
 	},
 	.probe		= sdhci_bcm_kona_probe,
diff --git a/drivers/mmc/host/sdhci-bcm2835.c b/drivers/mmc/host/sdhci-bcm2835.c
deleted file mode 100644
index 4a6a1d1386cb..000000000000
--- a/drivers/mmc/host/sdhci-bcm2835.c
+++ /dev/null
@@ -1,204 +0,0 @@
-/*
- * BCM2835 SDHCI
- * Copyright (C) 2012 Stephen Warren
- * Based on U-Boot's MMC driver for the BCM2835 by Oleksandr Tymoshenko & me
- * Portions of the code there were obviously based on the Linux kernel at:
- * git://github.com/raspberrypi/linux.git rpi-3.6.y
- * commit f5b930b "Main bcm2708 linux port" signed-off-by Dom Cobley.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/delay.h>
-#include <linux/module.h>
-#include <linux/mmc/host.h>
-#include "sdhci-pltfm.h"
-
-/*
- * 400KHz is max freq for card ID etc. Use that as min card clock. We need to
- * know the min to enable static calculation of max BCM2835_SDHCI_WRITE_DELAY.
- */
-#define MIN_FREQ 400000
-
-/*
- * The Arasan has a bugette whereby it may lose the content of successive
- * writes to registers that are within two SD-card clock cycles of each other
- * (a clock domain crossing problem). It seems, however, that the data
- * register does not have this problem, which is just as well - otherwise we'd
- * have to nobble the DMA engine too.
- *
- * This should probably be dynamically calculated based on the actual card
- * frequency. However, this is the longest we'll have to wait, and doesn't
- * seem to slow access down too much, so the added complexity doesn't seem
- * worth it for now.
- *
- * 1/MIN_FREQ is (max) time per tick of eMMC clock.
- * 2/MIN_FREQ is time for two ticks.
- * Multiply by 1000000 to get uS per two ticks.
- * *1000000 for uSecs.
- * +1 for hack rounding.
- */
-#define BCM2835_SDHCI_WRITE_DELAY	(((2 * 1000000) / MIN_FREQ) + 1)
-
-struct bcm2835_sdhci {
-	u32 shadow;
-};
-
-static void bcm2835_sdhci_writel(struct sdhci_host *host, u32 val, int reg)
-{
-	writel(val, host->ioaddr + reg);
-
-	udelay(BCM2835_SDHCI_WRITE_DELAY);
-}
-
-static inline u32 bcm2835_sdhci_readl(struct sdhci_host *host, int reg)
-{
-	u32 val = readl(host->ioaddr + reg);
-
-	if (reg == SDHCI_CAPABILITIES)
-		val |= SDHCI_CAN_VDD_330;
-
-	return val;
-}
-
-static void bcm2835_sdhci_writew(struct sdhci_host *host, u16 val, int reg)
-{
-	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-	struct bcm2835_sdhci *bcm2835_host = sdhci_pltfm_priv(pltfm_host);
-	u32 oldval = (reg == SDHCI_COMMAND) ? bcm2835_host->shadow :
-		bcm2835_sdhci_readl(host, reg & ~3);
-	u32 word_num = (reg >> 1) & 1;
-	u32 word_shift = word_num * 16;
-	u32 mask = 0xffff << word_shift;
-	u32 newval = (oldval & ~mask) | (val << word_shift);
-
-	if (reg == SDHCI_TRANSFER_MODE)
-		bcm2835_host->shadow = newval;
-	else
-		bcm2835_sdhci_writel(host, newval, reg & ~3);
-}
-
-static u16 bcm2835_sdhci_readw(struct sdhci_host *host, int reg)
-{
-	u32 val = bcm2835_sdhci_readl(host, (reg & ~3));
-	u32 word_num = (reg >> 1) & 1;
-	u32 word_shift = word_num * 16;
-	u32 word = (val >> word_shift) & 0xffff;
-
-	return word;
-}
-
-static void bcm2835_sdhci_writeb(struct sdhci_host *host, u8 val, int reg)
-{
-	u32 oldval = bcm2835_sdhci_readl(host, reg & ~3);
-	u32 byte_num = reg & 3;
-	u32 byte_shift = byte_num * 8;
-	u32 mask = 0xff << byte_shift;
-	u32 newval = (oldval & ~mask) | (val << byte_shift);
-
-	bcm2835_sdhci_writel(host, newval, reg & ~3);
-}
-
-static u8 bcm2835_sdhci_readb(struct sdhci_host *host, int reg)
-{
-	u32 val = bcm2835_sdhci_readl(host, (reg & ~3));
-	u32 byte_num = reg & 3;
-	u32 byte_shift = byte_num * 8;
-	u32 byte = (val >> byte_shift) & 0xff;
-
-	return byte;
-}
-
-static unsigned int bcm2835_sdhci_get_min_clock(struct sdhci_host *host)
-{
-	return MIN_FREQ;
-}
-
-static const struct sdhci_ops bcm2835_sdhci_ops = {
-	.write_l = bcm2835_sdhci_writel,
-	.write_w = bcm2835_sdhci_writew,
-	.write_b = bcm2835_sdhci_writeb,
-	.read_l = bcm2835_sdhci_readl,
-	.read_w = bcm2835_sdhci_readw,
-	.read_b = bcm2835_sdhci_readb,
-	.set_clock = sdhci_set_clock,
-	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
-	.get_min_clock = bcm2835_sdhci_get_min_clock,
-	.set_bus_width = sdhci_set_bus_width,
-	.reset = sdhci_reset,
-	.set_uhs_signaling = sdhci_set_uhs_signaling,
-};
-
-static const struct sdhci_pltfm_data bcm2835_sdhci_pdata = {
-	.quirks = SDHCI_QUIRK_BROKEN_CARD_DETECTION |
-		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK,
-	.ops = &bcm2835_sdhci_ops,
-};
-
-static int bcm2835_sdhci_probe(struct platform_device *pdev)
-{
-	struct sdhci_host *host;
-	struct bcm2835_sdhci *bcm2835_host;
-	struct sdhci_pltfm_host *pltfm_host;
-	int ret;
-
-	host = sdhci_pltfm_init(pdev, &bcm2835_sdhci_pdata,
-				sizeof(*bcm2835_host));
-	if (IS_ERR(host))
-		return PTR_ERR(host);
-
-	pltfm_host = sdhci_priv(host);
-
-	pltfm_host->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(pltfm_host->clk)) {
-		ret = PTR_ERR(pltfm_host->clk);
-		goto err;
-	}
-	ret = clk_prepare_enable(pltfm_host->clk);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to enable host clk\n");
-		goto err;
-	}
-
-	ret = sdhci_add_host(host);
-	if (ret)
-		goto err_clk;
-
-	return 0;
-err_clk:
-	clk_disable_unprepare(pltfm_host->clk);
-err:
-	sdhci_pltfm_free(pdev);
-	return ret;
-}
-
-static const struct of_device_id bcm2835_sdhci_of_match[] = {
-	{ .compatible = "brcm,bcm2835-sdhci" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, bcm2835_sdhci_of_match);
-
-static struct platform_driver bcm2835_sdhci_driver = {
-	.driver = {
-		.name = "sdhci-bcm2835",
-		.of_match_table = bcm2835_sdhci_of_match,
-		.pm = SDHCI_PLTFM_PMOPS,
-	},
-	.probe = bcm2835_sdhci_probe,
-	.remove = sdhci_pltfm_unregister,
-};
-module_platform_driver(bcm2835_sdhci_driver);
-
-MODULE_DESCRIPTION("BCM2835 SDHCI driver");
-MODULE_AUTHOR("Stephen Warren");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c
new file mode 100644
index 000000000000..cce10fe3e19e
--- /dev/null
+++ b/drivers/mmc/host/sdhci-brcmstb.c
@@ -0,0 +1,143 @@
+/*
+ * sdhci-brcmstb.c Support for SDHCI on Broadcom BRCMSTB SoC's
+ *
+ * Copyright (C) 2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/io.h>
+#include <linux/mmc/host.h>
+#include <linux/module.h>
+#include <linux/of.h>
+
+#include "sdhci-pltfm.h"
+
+#ifdef CONFIG_PM_SLEEP
+
+static int sdhci_brcmstb_suspend(struct device *dev)
+{
+	struct sdhci_host *host = dev_get_drvdata(dev);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	int res;
+
+	res = sdhci_suspend_host(host);
+	if (res)
+		return res;
+	clk_disable_unprepare(pltfm_host->clk);
+	return res;
+}
+
+static int sdhci_brcmstb_resume(struct device *dev)
+{
+	struct sdhci_host *host = dev_get_drvdata(dev);
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	int err;
+
+	err = clk_prepare_enable(pltfm_host->clk);
+	if (err)
+		return err;
+	return sdhci_resume_host(host);
+}
+
+#endif /* CONFIG_PM_SLEEP */
+
+static SIMPLE_DEV_PM_OPS(sdhci_brcmstb_pmops, sdhci_brcmstb_suspend,
+			sdhci_brcmstb_resume);
+
+static const struct sdhci_ops sdhci_brcmstb_ops = {
+	.set_clock = sdhci_set_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
+};
+
+static struct sdhci_pltfm_data sdhci_brcmstb_pdata = {
+	.ops = &sdhci_brcmstb_ops,
+};
+
+static int sdhci_brcmstb_probe(struct platform_device *pdev)
+{
+	struct sdhci_host *host;
+	struct sdhci_pltfm_host *pltfm_host;
+	struct clk *clk;
+	int res;
+
+	clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(clk)) {
+		dev_err(&pdev->dev, "Clock not found in Device Tree\n");
+		clk = NULL;
+	}
+	res = clk_prepare_enable(clk);
+	if (res)
+		return res;
+
+	host = sdhci_pltfm_init(pdev, &sdhci_brcmstb_pdata, 0);
+	if (IS_ERR(host)) {
+		res = PTR_ERR(host);
+		goto err_clk;
+	}
+
+	/* Enable MMC_CAP2_HC_ERASE_SZ for better max discard calculations */
+	host->mmc->caps2 |= MMC_CAP2_HC_ERASE_SZ;
+
+	sdhci_get_of_property(pdev);
+	mmc_of_parse(host->mmc);
+
+	/*
+	 * Supply the existing CAPS, but clear the UHS modes. This
+	 * will allow these modes to be specified by device tree
+	 * properties through mmc_of_parse().
+	 */
+	host->caps = sdhci_readl(host, SDHCI_CAPABILITIES);
+	host->caps1 = sdhci_readl(host, SDHCI_CAPABILITIES_1);
+	host->caps1 &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_SDR104 |
+			SDHCI_SUPPORT_DDR50);
+	host->quirks |= SDHCI_QUIRK_MISSING_CAPS |
+		SDHCI_QUIRK_BROKEN_TIMEOUT_VAL;
+
+	res = sdhci_add_host(host);
+	if (res)
+		goto err;
+
+	pltfm_host = sdhci_priv(host);
+	pltfm_host->clk = clk;
+	return res;
+
+err:
+	sdhci_pltfm_free(pdev);
+err_clk:
+	clk_disable_unprepare(clk);
+	return res;
+}
+
+static const struct of_device_id sdhci_brcm_of_match[] = {
+	{ .compatible = "brcm,bcm7425-sdhci" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, sdhci_brcm_of_match);
+
+static struct platform_driver sdhci_brcmstb_driver = {
+	.driver		= {
+		.name	= "sdhci-brcmstb",
+		.owner	= THIS_MODULE,
+		.pm	= &sdhci_brcmstb_pmops,
+		.of_match_table = of_match_ptr(sdhci_brcm_of_match),
+	},
+	.probe		= sdhci_brcmstb_probe,
+	.remove		= sdhci_pltfm_unregister,
+};
+
+module_platform_driver(sdhci_brcmstb_driver);
+
+MODULE_DESCRIPTION("SDHCI driver for Broadcom BRCMSTB SoCs");
+MODULE_AUTHOR("Broadcom");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/sdhci-cns3xxx.c b/drivers/mmc/host/sdhci-cns3xxx.c
index 59f2923f8054..bd286db7f9af 100644
--- a/drivers/mmc/host/sdhci-cns3xxx.c
+++ b/drivers/mmc/host/sdhci-cns3xxx.c
@@ -101,7 +101,7 @@ static int sdhci_cns3xxx_probe(struct platform_device *pdev)
 static struct platform_driver sdhci_cns3xxx_driver = {
 	.driver		= {
 		.name	= "sdhci-cns3xxx",
-		.pm	= SDHCI_PLTFM_PMOPS,
+		.pm	= &sdhci_pltfm_pmops,
 	},
 	.probe		= sdhci_cns3xxx_probe,
 	.remove		= sdhci_pltfm_unregister,
diff --git a/drivers/mmc/host/sdhci-dove.c b/drivers/mmc/host/sdhci-dove.c
index 407c21f152b2..de9f9603dbdc 100644
--- a/drivers/mmc/host/sdhci-dove.c
+++ b/drivers/mmc/host/sdhci-dove.c
@@ -117,7 +117,7 @@ MODULE_DEVICE_TABLE(of, sdhci_dove_of_match_table);
 static struct platform_driver sdhci_dove_driver = {
 	.driver		= {
 		.name	= "sdhci-dove",
-		.pm	= SDHCI_PLTFM_PMOPS,
+		.pm	= &sdhci_pltfm_pmops,
 		.of_match_table = sdhci_dove_of_match_table,
 	},
 	.probe		= sdhci_dove_probe,
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 9d3ae1f4bd3c..99e0b334f9df 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -39,11 +39,13 @@
 #define  ESDHC_VENDOR_SPEC_VSELECT	(1 << 1)
 #define  ESDHC_VENDOR_SPEC_FRC_SDCLK_ON	(1 << 8)
 #define ESDHC_WTMK_LVL			0x44
+#define  ESDHC_WTMK_DEFAULT_VAL		0x10401040
 #define ESDHC_MIX_CTRL			0x48
 #define  ESDHC_MIX_CTRL_DDREN		(1 << 3)
 #define  ESDHC_MIX_CTRL_AC23EN		(1 << 7)
 #define  ESDHC_MIX_CTRL_EXE_TUNE	(1 << 22)
 #define  ESDHC_MIX_CTRL_SMPCLK_SEL	(1 << 23)
+#define  ESDHC_MIX_CTRL_AUTO_TUNE_EN	(1 << 24)
 #define  ESDHC_MIX_CTRL_FBCLK_SEL	(1 << 25)
 #define  ESDHC_MIX_CTRL_HS400_EN	(1 << 26)
 /* Bits 3 and 6 are not SDHCI standard definitions */
@@ -75,7 +77,8 @@
 #define ESDHC_TUNING_CTRL		0xcc
 #define ESDHC_STD_TUNING_EN		(1 << 24)
 /* NOTE: the minimum valid tuning start tap for mx6sl is 1 */
-#define ESDHC_TUNING_START_TAP		0x1
+#define ESDHC_TUNING_START_TAP_DEFAULT	0x1
+#define ESDHC_TUNING_START_TAP_MASK	0xff
 #define ESDHC_TUNING_STEP_MASK		0x00070000
 #define ESDHC_TUNING_STEP_SHIFT		16
 
@@ -299,7 +302,8 @@ static u32 esdhc_readl_le(struct sdhci_host *host, int reg)
 				/* imx6q/dl does not have cap_1 register, fake one */
 				val = SDHCI_SUPPORT_DDR50 | SDHCI_SUPPORT_SDR104
 					| SDHCI_SUPPORT_SDR50
-					| SDHCI_USE_SDR50_TUNING;
+					| SDHCI_USE_SDR50_TUNING
+					| (SDHCI_TUNING_MODE_3 << SDHCI_RETUNING_MODE_SHIFT);
 
 			if (imx_data->socdata->flags & ESDHC_FLAG_HS400)
 				val |= SDHCI_SUPPORT_HS400;
@@ -469,32 +473,29 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg)
 		writel(new_val, host->ioaddr + ESDHC_VENDOR_SPEC);
 		if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING) {
 			new_val = readl(host->ioaddr + ESDHC_MIX_CTRL);
-			if (val & SDHCI_CTRL_TUNED_CLK)
+			if (val & SDHCI_CTRL_TUNED_CLK) {
 				new_val |= ESDHC_MIX_CTRL_SMPCLK_SEL;
-			else
+				new_val |= ESDHC_MIX_CTRL_AUTO_TUNE_EN;
+			} else {
 				new_val &= ~ESDHC_MIX_CTRL_SMPCLK_SEL;
+				new_val &= ~ESDHC_MIX_CTRL_AUTO_TUNE_EN;
+			}
 			writel(new_val , host->ioaddr + ESDHC_MIX_CTRL);
 		} else if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) {
 			u32 v = readl(host->ioaddr + SDHCI_ACMD12_ERR);
 			u32 m = readl(host->ioaddr + ESDHC_MIX_CTRL);
-			u32 tuning_ctrl;
 			if (val & SDHCI_CTRL_TUNED_CLK) {
 				v |= ESDHC_MIX_CTRL_SMPCLK_SEL;
 			} else {
 				v &= ~ESDHC_MIX_CTRL_SMPCLK_SEL;
 				m &= ~ESDHC_MIX_CTRL_FBCLK_SEL;
+				m &= ~ESDHC_MIX_CTRL_AUTO_TUNE_EN;
 			}
 
 			if (val & SDHCI_CTRL_EXEC_TUNING) {
 				v |= ESDHC_MIX_CTRL_EXE_TUNE;
 				m |= ESDHC_MIX_CTRL_FBCLK_SEL;
-				tuning_ctrl = readl(host->ioaddr + ESDHC_TUNING_CTRL);
-				tuning_ctrl |= ESDHC_STD_TUNING_EN | ESDHC_TUNING_START_TAP;
-				if (imx_data->boarddata.tuning_step) {
-					tuning_ctrl &= ~ESDHC_TUNING_STEP_MASK;
-					tuning_ctrl |= imx_data->boarddata.tuning_step << ESDHC_TUNING_STEP_SHIFT;
-				}
-				writel(tuning_ctrl, host->ioaddr + ESDHC_TUNING_CTRL);
+				m |= ESDHC_MIX_CTRL_AUTO_TUNE_EN;
 			} else {
 				v &= ~ESDHC_MIX_CTRL_EXE_TUNE;
 			}
@@ -751,6 +752,7 @@ static void esdhc_post_tuning(struct sdhci_host *host)
 
 	reg = readl(host->ioaddr + ESDHC_MIX_CTRL);
 	reg &= ~ESDHC_MIX_CTRL_EXE_TUNE;
+	reg |= ESDHC_MIX_CTRL_AUTO_TUNE_EN;
 	writel(reg, host->ioaddr + ESDHC_MIX_CTRL);
 }
 
@@ -838,6 +840,11 @@ static void esdhc_set_strobe_dll(struct sdhci_host *host)
 	u32 v;
 
 	if (host->mmc->actual_clock > ESDHC_STROBE_DLL_CLK_FREQ) {
+		/* disable clock before enabling strobe dll */
+		writel(readl(host->ioaddr + ESDHC_VENDOR_SPEC) &
+		       ~ESDHC_VENDOR_SPEC_FRC_SDCLK_ON,
+		       host->ioaddr + ESDHC_VENDOR_SPEC);
+
 		/* force a reset on strobe dll */
 		writel(ESDHC_STROBE_DLL_CTRL_RESET,
 			host->ioaddr + ESDHC_STROBE_DLL_CTRL);
@@ -899,6 +906,8 @@ static void esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned timing)
 		m |= ESDHC_MIX_CTRL_DDREN | ESDHC_MIX_CTRL_HS400_EN;
 		writel(m, host->ioaddr + ESDHC_MIX_CTRL);
 		imx_data->is_ddr = 1;
+		/* update clock after enable DDR for strobe DLL lock */
+		host->ops->set_clock(host, host->clock);
 		esdhc_set_strobe_dll(host);
 		break;
 	}
@@ -957,6 +966,62 @@ static const struct sdhci_pltfm_data sdhci_esdhc_imx_pdata = {
 	.ops = &sdhci_esdhc_ops,
 };
 
+static void sdhci_esdhc_imx_hwinit(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
+	int tmp;
+
+	if (esdhc_is_usdhc(imx_data)) {
+		/*
+		 * The imx6q ROM code will change the default watermark
+		 * level setting to something insane.  Change it back here.
+		 */
+		writel(ESDHC_WTMK_DEFAULT_VAL, host->ioaddr + ESDHC_WTMK_LVL);
+
+		/*
+		 * ROM code will change the bit burst_length_enable setting
+		 * to zero if this usdhc is choosed to boot system. Change
+		 * it back here, otherwise it will impact the performance a
+		 * lot. This bit is used to enable/disable the burst length
+		 * for the external AHB2AXI bridge, it's usefully especially
+		 * for INCR transfer because without burst length indicator,
+		 * the AHB2AXI bridge does not know the burst length in
+		 * advance. And without burst length indicator, AHB INCR
+		 * transfer can only be converted to singles on the AXI side.
+		 */
+		writel(readl(host->ioaddr + SDHCI_HOST_CONTROL)
+			| ESDHC_BURST_LEN_EN_INCR,
+			host->ioaddr + SDHCI_HOST_CONTROL);
+		/*
+		* errata ESDHC_FLAG_ERR004536 fix for MX6Q TO1.2 and MX6DL
+		* TO1.1, it's harmless for MX6SL
+		*/
+		writel(readl(host->ioaddr + 0x6c) | BIT(7),
+			host->ioaddr + 0x6c);
+
+		/* disable DLL_CTRL delay line settings */
+		writel(0x0, host->ioaddr + ESDHC_DLL_CTRL);
+
+		if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) {
+			tmp = readl(host->ioaddr + ESDHC_TUNING_CTRL);
+			tmp |= ESDHC_STD_TUNING_EN |
+				ESDHC_TUNING_START_TAP_DEFAULT;
+			if (imx_data->boarddata.tuning_start_tap) {
+				tmp &= ~ESDHC_TUNING_START_TAP_MASK;
+				tmp |= imx_data->boarddata.tuning_start_tap;
+			}
+
+			if (imx_data->boarddata.tuning_step) {
+				tmp &= ~ESDHC_TUNING_STEP_MASK;
+				tmp |= imx_data->boarddata.tuning_step
+					<< ESDHC_TUNING_STEP_SHIFT;
+			}
+			writel(tmp, host->ioaddr + ESDHC_TUNING_CTRL);
+		}
+	}
+}
+
 #ifdef CONFIG_OF
 static int
 sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
@@ -975,6 +1040,8 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
 		boarddata->wp_type = ESDHC_WP_GPIO;
 
 	of_property_read_u32(np, "fsl,tuning-step", &boarddata->tuning_step);
+	of_property_read_u32(np, "fsl,tuning-start-tap",
+			     &boarddata->tuning_start_tap);
 
 	if (of_find_property(np, "no-1-8-v", NULL))
 		boarddata->support_vsel = false;
@@ -1147,58 +1214,27 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 	if (IS_ERR(imx_data->pins_default))
 		dev_warn(mmc_dev(host->mmc), "could not get default state\n");
 
-	host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL;
-
 	if (imx_data->socdata->flags & ESDHC_FLAG_ENGCM07207)
 		/* Fix errata ENGcm07207 present on i.MX25 and i.MX35 */
 		host->quirks |= SDHCI_QUIRK_NO_MULTIBLOCK
 			| SDHCI_QUIRK_BROKEN_ADMA;
 
-	/*
-	 * The imx6q ROM code will change the default watermark level setting
-	 * to something insane.  Change it back here.
-	 */
 	if (esdhc_is_usdhc(imx_data)) {
-		writel(0x10401040, host->ioaddr + ESDHC_WTMK_LVL);
-
 		host->quirks2 |= SDHCI_QUIRK2_PRESET_VALUE_BROKEN;
 		host->mmc->caps |= MMC_CAP_1_8V_DDR;
-
-		/*
-		 * ROM code will change the bit burst_length_enable setting
-		 * to zero if this usdhc is choosed to boot system. Change
-		 * it back here, otherwise it will impact the performance a
-		 * lot. This bit is used to enable/disable the burst length
-		 * for the external AHB2AXI bridge, it's usefully especially
-		 * for INCR transfer because without burst length indicator,
-		 * the AHB2AXI bridge does not know the burst length in
-		 * advance. And without burst length indicator, AHB INCR
-		 * transfer can only be converted to singles on the AXI side.
-		 */
-		writel(readl(host->ioaddr + SDHCI_HOST_CONTROL)
-			| ESDHC_BURST_LEN_EN_INCR,
-			host->ioaddr + SDHCI_HOST_CONTROL);
-
 		if (!(imx_data->socdata->flags & ESDHC_FLAG_HS200))
 			host->quirks2 |= SDHCI_QUIRK2_BROKEN_HS200;
 
-		/*
-		* errata ESDHC_FLAG_ERR004536 fix for MX6Q TO1.2 and MX6DL
-		* TO1.1, it's harmless for MX6SL
-		*/
-		writel(readl(host->ioaddr + 0x6c) | BIT(7),
-			host->ioaddr + 0x6c);
+		/* clear tuning bits in case ROM has set it already */
+		writel(0x0, host->ioaddr + ESDHC_MIX_CTRL);
+		writel(0x0, host->ioaddr + SDHCI_ACMD12_ERR);
+		writel(0x0, host->ioaddr + ESDHC_TUNE_CTRL_STATUS);
 	}
 
 	if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING)
 		sdhci_esdhc_ops.platform_execute_tuning =
 					esdhc_executing_tuning;
 
-	if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING)
-		writel(readl(host->ioaddr + ESDHC_TUNING_CTRL) |
-			ESDHC_STD_TUNING_EN | ESDHC_TUNING_START_TAP,
-			host->ioaddr + ESDHC_TUNING_CTRL);
-
 	if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536)
 		host->quirks |= SDHCI_QUIRK_BROKEN_ADMA;
 
@@ -1212,6 +1248,8 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 	if (err)
 		goto disable_clk;
 
+	sdhci_esdhc_imx_hwinit(host);
+
 	err = sdhci_add_host(host);
 	if (err)
 		goto disable_clk;
@@ -1255,6 +1293,25 @@ static int sdhci_esdhc_imx_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int sdhci_esdhc_suspend(struct device *dev)
+{
+	struct sdhci_host *host = dev_get_drvdata(dev);
+
+	return sdhci_suspend_host(host);
+}
+
+static int sdhci_esdhc_resume(struct device *dev)
+{
+	struct sdhci_host *host = dev_get_drvdata(dev);
+
+	/* re-initialize hw state in case it's lost in low power mode */
+	sdhci_esdhc_imx_hwinit(host);
+
+	return sdhci_resume_host(host);
+}
+#endif
+
 #ifdef CONFIG_PM
 static int sdhci_esdhc_runtime_suspend(struct device *dev)
 {
@@ -1291,7 +1348,7 @@ static int sdhci_esdhc_runtime_resume(struct device *dev)
 #endif
 
 static const struct dev_pm_ops sdhci_esdhc_pmops = {
-	SET_SYSTEM_SLEEP_PM_OPS(sdhci_pltfm_suspend, sdhci_pltfm_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(sdhci_esdhc_suspend, sdhci_esdhc_resume)
 	SET_RUNTIME_PM_OPS(sdhci_esdhc_runtime_suspend,
 				sdhci_esdhc_runtime_resume, NULL)
 };
diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c
index 1110f73b08aa..726246665850 100644
--- a/drivers/mmc/host/sdhci-iproc.c
+++ b/drivers/mmc/host/sdhci-iproc.c
@@ -164,8 +164,17 @@ static const struct sdhci_pltfm_data sdhci_iproc_pltfm_data = {
 
 static const struct sdhci_iproc_data iproc_data = {
 	.pdata = &sdhci_iproc_pltfm_data,
-	.caps = 0x05E90000,
-	.caps1 = 0x00000064,
+	.caps = ((0x1 << SDHCI_MAX_BLOCK_SHIFT)
+			& SDHCI_MAX_BLOCK_MASK) |
+		SDHCI_CAN_VDD_330 |
+		SDHCI_CAN_VDD_180 |
+		SDHCI_CAN_DO_SUSPEND |
+		SDHCI_CAN_DO_HISPD |
+		SDHCI_CAN_DO_ADMA2 |
+		SDHCI_CAN_DO_SDMA,
+	.caps1 = SDHCI_DRIVER_TYPE_C |
+		 SDHCI_DRIVER_TYPE_D |
+		 SDHCI_SUPPORT_DDR50,
 	.mmc_caps = MMC_CAP_1_8V_DDR,
 };
 
@@ -251,7 +260,7 @@ static struct platform_driver sdhci_iproc_driver = {
 	.driver = {
 		.name = "sdhci-iproc",
 		.of_match_table = sdhci_iproc_of_match,
-		.pm = SDHCI_PLTFM_PMOPS,
+		.pm = &sdhci_pltfm_pmops,
 	},
 	.probe = sdhci_iproc_probe,
 	.remove = sdhci_pltfm_unregister,
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 0653fe730150..8ef44a2a2fd9 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -32,6 +32,21 @@
 #define CORE_POWER		0x0
 #define CORE_SW_RST		BIT(7)
 
+#define CORE_PWRCTL_STATUS	0xdc
+#define CORE_PWRCTL_MASK	0xe0
+#define CORE_PWRCTL_CLEAR	0xe4
+#define CORE_PWRCTL_CTL		0xe8
+#define CORE_PWRCTL_BUS_OFF	BIT(0)
+#define CORE_PWRCTL_BUS_ON	BIT(1)
+#define CORE_PWRCTL_IO_LOW	BIT(2)
+#define CORE_PWRCTL_IO_HIGH	BIT(3)
+#define CORE_PWRCTL_BUS_SUCCESS BIT(0)
+#define CORE_PWRCTL_IO_SUCCESS	BIT(2)
+#define REQ_BUS_OFF		BIT(0)
+#define REQ_BUS_ON		BIT(1)
+#define REQ_IO_LOW		BIT(2)
+#define REQ_IO_HIGH		BIT(3)
+#define INT_MASK		0xf
 #define MAX_PHASES		16
 #define CORE_DLL_LOCK		BIT(7)
 #define CORE_DLL_EN		BIT(16)
@@ -56,6 +71,7 @@
 struct sdhci_msm_host {
 	struct platform_device *pdev;
 	void __iomem *core_mem;	/* MSM SDCC mapped address */
+	int pwr_irq;		/* power irq */
 	struct clk *clk;	/* main SD/MMC bus clock */
 	struct clk *pclk;	/* SDHC peripheral bus clock */
 	struct clk *bus_clk;	/* SDHC bus voter clock */
@@ -410,6 +426,85 @@ retry:
 	return rc;
 }
 
+static void sdhci_msm_set_uhs_signaling(struct sdhci_host *host,
+					unsigned int uhs)
+{
+	struct mmc_host *mmc = host->mmc;
+	u16 ctrl_2;
+
+	ctrl_2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+	/* Select Bus Speed Mode for host */
+	ctrl_2 &= ~SDHCI_CTRL_UHS_MASK;
+	switch (uhs) {
+	case MMC_TIMING_UHS_SDR12:
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR12;
+		break;
+	case MMC_TIMING_UHS_SDR25:
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR25;
+		break;
+	case MMC_TIMING_UHS_SDR50:
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR50;
+		break;
+	case MMC_TIMING_MMC_HS200:
+	case MMC_TIMING_UHS_SDR104:
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR104;
+		break;
+	case MMC_TIMING_UHS_DDR50:
+	case MMC_TIMING_MMC_DDR52:
+		ctrl_2 |= SDHCI_CTRL_UHS_DDR50;
+		break;
+	}
+
+	/*
+	 * When clock frequency is less than 100MHz, the feedback clock must be
+	 * provided and DLL must not be used so that tuning can be skipped. To
+	 * provide feedback clock, the mode selection can be any value less
+	 * than 3'b011 in bits [2:0] of HOST CONTROL2 register.
+	 */
+	if (host->clock <= 100000000 &&
+	    (uhs == MMC_TIMING_MMC_HS400 ||
+	     uhs == MMC_TIMING_MMC_HS200 ||
+	     uhs == MMC_TIMING_UHS_SDR104))
+		ctrl_2 &= ~SDHCI_CTRL_UHS_MASK;
+
+	dev_dbg(mmc_dev(mmc), "%s: clock=%u uhs=%u ctrl_2=0x%x\n",
+		mmc_hostname(host->mmc), host->clock, uhs, ctrl_2);
+	sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
+}
+
+static void sdhci_msm_voltage_switch(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
+	u32 irq_status, irq_ack = 0;
+
+	irq_status = readl_relaxed(msm_host->core_mem + CORE_PWRCTL_STATUS);
+	irq_status &= INT_MASK;
+
+	writel_relaxed(irq_status, msm_host->core_mem + CORE_PWRCTL_CLEAR);
+
+	if (irq_status & (CORE_PWRCTL_BUS_ON | CORE_PWRCTL_BUS_OFF))
+		irq_ack |= CORE_PWRCTL_BUS_SUCCESS;
+	if (irq_status & (CORE_PWRCTL_IO_LOW | CORE_PWRCTL_IO_HIGH))
+		irq_ack |= CORE_PWRCTL_IO_SUCCESS;
+
+	/*
+	 * The driver has to acknowledge the interrupt, switch voltages and
+	 * report back if it succeded or not to this register. The voltage
+	 * switches are handled by the sdhci core, so just report success.
+	 */
+	writel_relaxed(irq_ack, msm_host->core_mem + CORE_PWRCTL_CTL);
+}
+
+static irqreturn_t sdhci_msm_pwr_irq(int irq, void *data)
+{
+	struct sdhci_host *host = (struct sdhci_host *)data;
+
+	sdhci_msm_voltage_switch(host);
+
+	return IRQ_HANDLED;
+}
+
 static const struct of_device_id sdhci_msm_dt_match[] = {
 	{ .compatible = "qcom,sdhci-msm-v4" },
 	{},
@@ -422,11 +517,13 @@ static const struct sdhci_ops sdhci_msm_ops = {
 	.reset = sdhci_reset,
 	.set_clock = sdhci_set_clock,
 	.set_bus_width = sdhci_set_bus_width,
-	.set_uhs_signaling = sdhci_set_uhs_signaling,
+	.set_uhs_signaling = sdhci_msm_set_uhs_signaling,
+	.voltage_switch = sdhci_msm_voltage_switch,
 };
 
 static const struct sdhci_pltfm_data sdhci_msm_pdata = {
 	.quirks = SDHCI_QUIRK_BROKEN_CARD_DETECTION |
+		  SDHCI_QUIRK_NO_CARD_NO_RESET |
 		  SDHCI_QUIRK_SINGLE_POWER_WRITE,
 	.ops = &sdhci_msm_ops,
 };
@@ -473,7 +570,7 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 	msm_host->pclk = devm_clk_get(&pdev->dev, "iface");
 	if (IS_ERR(msm_host->pclk)) {
 		ret = PTR_ERR(msm_host->pclk);
-		dev_err(&pdev->dev, "Perpheral clk setup failed (%d)\n", ret);
+		dev_err(&pdev->dev, "Peripheral clk setup failed (%d)\n", ret);
 		goto bus_clk_disable;
 	}
 
@@ -545,6 +642,22 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 			       CORE_VENDOR_SPEC_CAPABILITIES0);
 	}
 
+	/* Setup IRQ for handling power/voltage tasks with PMIC */
+	msm_host->pwr_irq = platform_get_irq_byname(pdev, "pwr_irq");
+	if (msm_host->pwr_irq < 0) {
+		dev_err(&pdev->dev, "Get pwr_irq failed (%d)\n",
+			msm_host->pwr_irq);
+		goto clk_disable;
+	}
+
+	ret = devm_request_threaded_irq(&pdev->dev, msm_host->pwr_irq, NULL,
+					sdhci_msm_pwr_irq, IRQF_ONESHOT,
+					dev_name(&pdev->dev), host);
+	if (ret) {
+		dev_err(&pdev->dev, "Request IRQ failed (%d)\n", ret);
+		goto clk_disable;
+	}
+
 	ret = sdhci_add_host(host);
 	if (ret)
 		goto clk_disable;
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index b6f4c1d41636..e0f193f7e3e5 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -19,27 +19,136 @@
  * your option) any later version.
  */
 
+#include <linux/clk-provider.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/phy/phy.h>
+#include <linux/regmap.h>
 #include "sdhci-pltfm.h"
 
 #define SDHCI_ARASAN_CLK_CTRL_OFFSET	0x2c
+#define SDHCI_ARASAN_VENDOR_REGISTER	0x78
 
+#define VENDOR_ENHANCED_STROBE		BIT(0)
 #define CLK_CTRL_TIMEOUT_SHIFT		16
 #define CLK_CTRL_TIMEOUT_MASK		(0xf << CLK_CTRL_TIMEOUT_SHIFT)
 #define CLK_CTRL_TIMEOUT_MIN_EXP	13
 
+/*
+ * On some SoCs the syscon area has a feature where the upper 16-bits of
+ * each 32-bit register act as a write mask for the lower 16-bits.  This allows
+ * atomic updates of the register without locking.  This macro is used on SoCs
+ * that have that feature.
+ */
+#define HIWORD_UPDATE(val, mask, shift) \
+		((val) << (shift) | (mask) << ((shift) + 16))
+
+/**
+ * struct sdhci_arasan_soc_ctl_field - Field used in sdhci_arasan_soc_ctl_map
+ *
+ * @reg:	Offset within the syscon of the register containing this field
+ * @width:	Number of bits for this field
+ * @shift:	Bit offset within @reg of this field (or -1 if not avail)
+ */
+struct sdhci_arasan_soc_ctl_field {
+	u32 reg;
+	u16 width;
+	s16 shift;
+};
+
+/**
+ * struct sdhci_arasan_soc_ctl_map - Map in syscon to corecfg registers
+ *
+ * It's up to the licensee of the Arsan IP block to make these available
+ * somewhere if needed.  Presumably these will be scattered somewhere that's
+ * accessible via the syscon API.
+ *
+ * @baseclkfreq:	Where to find corecfg_baseclkfreq
+ * @hiword_update:	If true, use HIWORD_UPDATE to access the syscon
+ */
+struct sdhci_arasan_soc_ctl_map {
+	struct sdhci_arasan_soc_ctl_field	baseclkfreq;
+	bool					hiword_update;
+};
+
 /**
  * struct sdhci_arasan_data
- * @clk_ahb:	Pointer to the AHB clock
- * @phy: Pointer to the generic phy
+ * @host:		Pointer to the main SDHCI host structure.
+ * @clk_ahb:		Pointer to the AHB clock
+ * @phy:		Pointer to the generic phy
+ * @sdcardclk_hw:	Struct for the clock we might provide to a PHY.
+ * @sdcardclk:		Pointer to normal 'struct clock' for sdcardclk_hw.
+ * @soc_ctl_base:	Pointer to regmap for syscon for soc_ctl registers.
+ * @soc_ctl_map:	Map to get offsets into soc_ctl registers.
  */
 struct sdhci_arasan_data {
+	struct sdhci_host *host;
 	struct clk	*clk_ahb;
 	struct phy	*phy;
+
+	struct clk_hw	sdcardclk_hw;
+	struct clk      *sdcardclk;
+
+	struct regmap	*soc_ctl_base;
+	const struct sdhci_arasan_soc_ctl_map *soc_ctl_map;
+};
+
+static const struct sdhci_arasan_soc_ctl_map rk3399_soc_ctl_map = {
+	.baseclkfreq = { .reg = 0xf000, .width = 8, .shift = 8 },
+	.hiword_update = true,
 };
 
+/**
+ * sdhci_arasan_syscon_write - Write to a field in soc_ctl registers
+ *
+ * This function allows writing to fields in sdhci_arasan_soc_ctl_map.
+ * Note that if a field is specified as not available (shift < 0) then
+ * this function will silently return an error code.  It will be noisy
+ * and print errors for any other (unexpected) errors.
+ *
+ * @host:	The sdhci_host
+ * @fld:	The field to write to
+ * @val:	The value to write
+ */
+static int sdhci_arasan_syscon_write(struct sdhci_host *host,
+				   const struct sdhci_arasan_soc_ctl_field *fld,
+				   u32 val)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host);
+	struct regmap *soc_ctl_base = sdhci_arasan->soc_ctl_base;
+	u32 reg = fld->reg;
+	u16 width = fld->width;
+	s16 shift = fld->shift;
+	int ret;
+
+	/*
+	 * Silently return errors for shift < 0 so caller doesn't have
+	 * to check for fields which are optional.  For fields that
+	 * are required then caller needs to do something special
+	 * anyway.
+	 */
+	if (shift < 0)
+		return -EINVAL;
+
+	if (sdhci_arasan->soc_ctl_map->hiword_update)
+		ret = regmap_write(soc_ctl_base, reg,
+				   HIWORD_UPDATE(val, GENMASK(width, 0),
+						 shift));
+	else
+		ret = regmap_update_bits(soc_ctl_base, reg,
+					 GENMASK(shift + width, shift),
+					 val << shift);
+
+	/* Yell about (unexpected) regmap errors */
+	if (ret)
+		pr_warn("%s: Regmap write fail: %d\n",
+			 mmc_hostname(host->mmc), ret);
+
+	return ret;
+}
+
 static unsigned int sdhci_arasan_get_timeout_clock(struct sdhci_host *host)
 {
 	u32 div;
@@ -79,6 +188,21 @@ static void sdhci_arasan_set_clock(struct sdhci_host *host, unsigned int clock)
 	}
 }
 
+static void sdhci_arasan_hs400_enhanced_strobe(struct mmc_host *mmc,
+					struct mmc_ios *ios)
+{
+	u32 vendor;
+	struct sdhci_host *host = mmc_priv(mmc);
+
+	vendor = readl(host->ioaddr + SDHCI_ARASAN_VENDOR_REGISTER);
+	if (ios->enhanced_strobe)
+		vendor |= VENDOR_ENHANCED_STROBE;
+	else
+		vendor &= ~VENDOR_ENHANCED_STROBE;
+
+	writel(vendor, host->ioaddr + SDHCI_ARASAN_VENDOR_REGISTER);
+}
+
 static struct sdhci_ops sdhci_arasan_ops = {
 	.set_clock = sdhci_arasan_set_clock,
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
@@ -172,9 +296,168 @@ static int sdhci_arasan_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(sdhci_arasan_dev_pm_ops, sdhci_arasan_suspend,
 			 sdhci_arasan_resume);
 
+static const struct of_device_id sdhci_arasan_of_match[] = {
+	/* SoC-specific compatible strings w/ soc_ctl_map */
+	{
+		.compatible = "rockchip,rk3399-sdhci-5.1",
+		.data = &rk3399_soc_ctl_map,
+	},
+
+	/* Generic compatible below here */
+	{ .compatible = "arasan,sdhci-8.9a" },
+	{ .compatible = "arasan,sdhci-5.1" },
+	{ .compatible = "arasan,sdhci-4.9a" },
+
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sdhci_arasan_of_match);
+
+/**
+ * sdhci_arasan_sdcardclk_recalc_rate - Return the card clock rate
+ *
+ * Return the current actual rate of the SD card clock.  This can be used
+ * to communicate with out PHY.
+ *
+ * @hw:			Pointer to the hardware clock structure.
+ * @parent_rate		The parent rate (should be rate of clk_xin).
+ * Returns the card clock rate.
+ */
+static unsigned long sdhci_arasan_sdcardclk_recalc_rate(struct clk_hw *hw,
+						      unsigned long parent_rate)
+
+{
+	struct sdhci_arasan_data *sdhci_arasan =
+		container_of(hw, struct sdhci_arasan_data, sdcardclk_hw);
+	struct sdhci_host *host = sdhci_arasan->host;
+
+	return host->mmc->actual_clock;
+}
+
+static const struct clk_ops arasan_sdcardclk_ops = {
+	.recalc_rate = sdhci_arasan_sdcardclk_recalc_rate,
+};
+
+/**
+ * sdhci_arasan_update_baseclkfreq - Set corecfg_baseclkfreq
+ *
+ * The corecfg_baseclkfreq is supposed to contain the MHz of clk_xin.  This
+ * function can be used to make that happen.
+ *
+ * NOTES:
+ * - Many existing devices don't seem to do this and work fine.  To keep
+ *   compatibility for old hardware where the device tree doesn't provide a
+ *   register map, this function is a noop if a soc_ctl_map hasn't been provided
+ *   for this platform.
+ * - It's assumed that clk_xin is not dynamic and that we use the SDHCI divider
+ *   to achieve lower clock rates.  That means that this function is called once
+ *   at probe time and never called again.
+ *
+ * @host:		The sdhci_host
+ */
+static void sdhci_arasan_update_baseclkfreq(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host);
+	const struct sdhci_arasan_soc_ctl_map *soc_ctl_map =
+		sdhci_arasan->soc_ctl_map;
+	u32 mhz = DIV_ROUND_CLOSEST(clk_get_rate(pltfm_host->clk), 1000000);
+
+	/* Having a map is optional */
+	if (!soc_ctl_map)
+		return;
+
+	/* If we have a map, we expect to have a syscon */
+	if (!sdhci_arasan->soc_ctl_base) {
+		pr_warn("%s: Have regmap, but no soc-ctl-syscon\n",
+			mmc_hostname(host->mmc));
+		return;
+	}
+
+	sdhci_arasan_syscon_write(host, &soc_ctl_map->baseclkfreq, mhz);
+}
+
+/**
+ * sdhci_arasan_register_sdclk - Register the sdclk for a PHY to use
+ *
+ * Some PHY devices need to know what the actual card clock is.  In order for
+ * them to find out, we'll provide a clock through the common clock framework
+ * for them to query.
+ *
+ * Note: without seriously re-architecting SDHCI's clock code and testing on
+ * all platforms, there's no way to create a totally beautiful clock here
+ * with all clock ops implemented.  Instead, we'll just create a clock that can
+ * be queried and set the CLK_GET_RATE_NOCACHE attribute to tell common clock
+ * framework that we're doing things behind its back.  This should be sufficient
+ * to create nice clean device tree bindings and later (if needed) we can try
+ * re-architecting SDHCI if we see some benefit to it.
+ *
+ * @sdhci_arasan:	Our private data structure.
+ * @clk_xin:		Pointer to the functional clock
+ * @dev:		Pointer to our struct device.
+ * Returns 0 on success and error value on error
+ */
+static int sdhci_arasan_register_sdclk(struct sdhci_arasan_data *sdhci_arasan,
+				       struct clk *clk_xin,
+				       struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	struct clk_init_data sdcardclk_init;
+	const char *parent_clk_name;
+	int ret;
+
+	/* Providing a clock to the PHY is optional; no error if missing */
+	if (!of_find_property(np, "#clock-cells", NULL))
+		return 0;
+
+	ret = of_property_read_string_index(np, "clock-output-names", 0,
+					    &sdcardclk_init.name);
+	if (ret) {
+		dev_err(dev, "DT has #clock-cells but no clock-output-names\n");
+		return ret;
+	}
+
+	parent_clk_name = __clk_get_name(clk_xin);
+	sdcardclk_init.parent_names = &parent_clk_name;
+	sdcardclk_init.num_parents = 1;
+	sdcardclk_init.flags = CLK_GET_RATE_NOCACHE;
+	sdcardclk_init.ops = &arasan_sdcardclk_ops;
+
+	sdhci_arasan->sdcardclk_hw.init = &sdcardclk_init;
+	sdhci_arasan->sdcardclk =
+		devm_clk_register(dev, &sdhci_arasan->sdcardclk_hw);
+	sdhci_arasan->sdcardclk_hw.init = NULL;
+
+	ret = of_clk_add_provider(np, of_clk_src_simple_get,
+				  sdhci_arasan->sdcardclk);
+	if (ret)
+		dev_err(dev, "Failed to add clock provider\n");
+
+	return ret;
+}
+
+/**
+ * sdhci_arasan_unregister_sdclk - Undoes sdhci_arasan_register_sdclk()
+ *
+ * Should be called any time we're exiting and sdhci_arasan_register_sdclk()
+ * returned success.
+ *
+ * @dev:		Pointer to our struct device.
+ */
+static void sdhci_arasan_unregister_sdclk(struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+
+	if (!of_find_property(np, "#clock-cells", NULL))
+		return;
+
+	of_clk_del_provider(dev->of_node);
+}
+
 static int sdhci_arasan_probe(struct platform_device *pdev)
 {
 	int ret;
+	const struct of_device_id *match;
+	struct device_node *node;
 	struct clk *clk_xin;
 	struct sdhci_host *host;
 	struct sdhci_pltfm_host *pltfm_host;
@@ -187,6 +470,24 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 
 	pltfm_host = sdhci_priv(host);
 	sdhci_arasan = sdhci_pltfm_priv(pltfm_host);
+	sdhci_arasan->host = host;
+
+	match = of_match_node(sdhci_arasan_of_match, pdev->dev.of_node);
+	sdhci_arasan->soc_ctl_map = match->data;
+
+	node = of_parse_phandle(pdev->dev.of_node, "arasan,soc-ctl-syscon", 0);
+	if (node) {
+		sdhci_arasan->soc_ctl_base = syscon_node_to_regmap(node);
+		of_node_put(node);
+
+		if (IS_ERR(sdhci_arasan->soc_ctl_base)) {
+			ret = PTR_ERR(sdhci_arasan->soc_ctl_base);
+			if (ret != -EPROBE_DEFER)
+				dev_err(&pdev->dev, "Can't get syscon: %d\n",
+					ret);
+			goto err_pltfm_free;
+		}
+	}
 
 	sdhci_arasan->clk_ahb = devm_clk_get(&pdev->dev, "clk_ahb");
 	if (IS_ERR(sdhci_arasan->clk_ahb)) {
@@ -217,10 +518,16 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 	sdhci_get_of_property(pdev);
 	pltfm_host->clk = clk_xin;
 
+	sdhci_arasan_update_baseclkfreq(host);
+
+	ret = sdhci_arasan_register_sdclk(sdhci_arasan, clk_xin, &pdev->dev);
+	if (ret)
+		goto clk_disable_all;
+
 	ret = mmc_of_parse(host->mmc);
 	if (ret) {
 		dev_err(&pdev->dev, "parsing dt failed (%u)\n", ret);
-		goto clk_disable_all;
+		goto unreg_clk;
 	}
 
 	sdhci_arasan->phy = ERR_PTR(-ENODEV);
@@ -231,13 +538,13 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 		if (IS_ERR(sdhci_arasan->phy)) {
 			ret = PTR_ERR(sdhci_arasan->phy);
 			dev_err(&pdev->dev, "No phy for arasan,sdhci-5.1.\n");
-			goto clk_disable_all;
+			goto unreg_clk;
 		}
 
 		ret = phy_init(sdhci_arasan->phy);
 		if (ret < 0) {
 			dev_err(&pdev->dev, "phy_init err.\n");
-			goto clk_disable_all;
+			goto unreg_clk;
 		}
 
 		ret = phy_power_on(sdhci_arasan->phy);
@@ -245,6 +552,9 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "phy_power_on err.\n");
 			goto err_phy_power;
 		}
+
+		host->mmc_host_ops.hs400_enhanced_strobe =
+					sdhci_arasan_hs400_enhanced_strobe;
 	}
 
 	ret = sdhci_add_host(host);
@@ -259,6 +569,8 @@ err_add_host:
 err_phy_power:
 	if (!IS_ERR(sdhci_arasan->phy))
 		phy_exit(sdhci_arasan->phy);
+unreg_clk:
+	sdhci_arasan_unregister_sdclk(&pdev->dev);
 clk_disable_all:
 	clk_disable_unprepare(clk_xin);
 clk_dis_ahb:
@@ -281,6 +593,8 @@ static int sdhci_arasan_remove(struct platform_device *pdev)
 		phy_exit(sdhci_arasan->phy);
 	}
 
+	sdhci_arasan_unregister_sdclk(&pdev->dev);
+
 	ret = sdhci_pltfm_unregister(pdev);
 
 	clk_disable_unprepare(clk_ahb);
@@ -288,14 +602,6 @@ static int sdhci_arasan_remove(struct platform_device *pdev)
 	return ret;
 }
 
-static const struct of_device_id sdhci_arasan_of_match[] = {
-	{ .compatible = "arasan,sdhci-8.9a" },
-	{ .compatible = "arasan,sdhci-5.1" },
-	{ .compatible = "arasan,sdhci-4.9a" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, sdhci_arasan_of_match);
-
 static struct platform_driver sdhci_arasan_driver = {
 	.driver = {
 		.name = "sdhci-arasan",
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index d4cef713d246..a9b7fc06c434 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -288,7 +288,7 @@ static int sdhci_at91_probe(struct platform_device *pdev)
 	 * Disable SDHCI_QUIRK_BROKEN_CARD_DETECTION to be sure nobody tries
 	 * to enable polling via device tree with broken-cd property.
 	 */
-	if (!(host->mmc->caps & MMC_CAP_NONREMOVABLE) &&
+	if (mmc_card_is_removable(host->mmc) &&
 	    mmc_gpio_get_cd(host->mmc) < 0) {
 		host->mmc->caps |= MMC_CAP_NEEDS_POLL;
 		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 3f34d354f1fc..239be2fde242 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -481,7 +481,7 @@ static void esdhc_reset(struct sdhci_host *host, u8 mask)
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static u32 esdhc_proctl;
 static int esdhc_of_suspend(struct device *dev)
 {
@@ -504,16 +504,12 @@ static int esdhc_of_resume(struct device *dev)
 	}
 	return ret;
 }
-
-static const struct dev_pm_ops esdhc_pmops = {
-	.suspend	= esdhc_of_suspend,
-	.resume		= esdhc_of_resume,
-};
-#define ESDHC_PMOPS (&esdhc_pmops)
-#else
-#define ESDHC_PMOPS NULL
 #endif
 
+static SIMPLE_DEV_PM_OPS(esdhc_of_dev_pm_ops,
+			esdhc_of_suspend,
+			esdhc_of_resume);
+
 static const struct sdhci_ops sdhci_esdhc_be_ops = {
 	.read_l = esdhc_be_readl,
 	.read_w = esdhc_be_readw,
@@ -657,7 +653,7 @@ static struct platform_driver sdhci_esdhc_driver = {
 	.driver = {
 		.name = "sdhci-esdhc",
 		.of_match_table = sdhci_esdhc_of_match,
-		.pm = ESDHC_PMOPS,
+		.pm = &esdhc_of_dev_pm_ops,
 	},
 	.probe = sdhci_esdhc_probe,
 	.remove = sdhci_pltfm_unregister,
diff --git a/drivers/mmc/host/sdhci-of-hlwd.c b/drivers/mmc/host/sdhci-of-hlwd.c
index 4079a96ad37e..ac00c5efb2a3 100644
--- a/drivers/mmc/host/sdhci-of-hlwd.c
+++ b/drivers/mmc/host/sdhci-of-hlwd.c
@@ -85,7 +85,7 @@ static struct platform_driver sdhci_hlwd_driver = {
 	.driver = {
 		.name = "sdhci-hlwd",
 		.of_match_table = sdhci_hlwd_of_match,
-		.pm = SDHCI_PLTFM_PMOPS,
+		.pm = &sdhci_pltfm_pmops,
 	},
 	.probe = sdhci_hlwd_probe,
 	.remove = sdhci_pltfm_unregister,
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index a4dbf7421edc..897cfd24ca2e 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -419,13 +419,13 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sd = {
 };
 
 /* Define Host controllers for Intel Merrifield platform */
-#define INTEL_MRFL_EMMC_0	0
-#define INTEL_MRFL_EMMC_1	1
+#define INTEL_MRFLD_EMMC_0	0
+#define INTEL_MRFLD_EMMC_1	1
 
-static int intel_mrfl_mmc_probe_slot(struct sdhci_pci_slot *slot)
+static int intel_mrfld_mmc_probe_slot(struct sdhci_pci_slot *slot)
 {
-	if ((PCI_FUNC(slot->chip->pdev->devfn) != INTEL_MRFL_EMMC_0) &&
-	    (PCI_FUNC(slot->chip->pdev->devfn) != INTEL_MRFL_EMMC_1))
+	if ((PCI_FUNC(slot->chip->pdev->devfn) != INTEL_MRFLD_EMMC_0) &&
+	    (PCI_FUNC(slot->chip->pdev->devfn) != INTEL_MRFLD_EMMC_1))
 		/* SD support is not ready yet */
 		return -ENODEV;
 
@@ -435,12 +435,12 @@ static int intel_mrfl_mmc_probe_slot(struct sdhci_pci_slot *slot)
 	return 0;
 }
 
-static const struct sdhci_pci_fixes sdhci_intel_mrfl_mmc = {
+static const struct sdhci_pci_fixes sdhci_intel_mrfld_mmc = {
 	.quirks		= SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.quirks2	= SDHCI_QUIRK2_BROKEN_HS200 |
 			SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 	.allow_runtime_pm = true,
-	.probe_slot	= intel_mrfl_mmc_probe_slot,
+	.probe_slot	= intel_mrfld_mmc_probe_slot,
 };
 
 /* O2Micro extra registers */
@@ -1104,10 +1104,10 @@ static const struct pci_device_id pci_ids[] = {
 
 	{
 		.vendor		= PCI_VENDOR_ID_INTEL,
-		.device		= PCI_DEVICE_ID_INTEL_MRFL_MMC,
+		.device		= PCI_DEVICE_ID_INTEL_MRFLD_MMC,
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
-		.driver_data	= (kernel_ulong_t)&sdhci_intel_mrfl_mmc,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_mrfld_mmc,
 	},
 
 	{
@@ -1413,8 +1413,7 @@ static const struct sdhci_ops sdhci_pci_ops = {
  *                                                                           *
 \*****************************************************************************/
 
-#ifdef CONFIG_PM
-
+#ifdef CONFIG_PM_SLEEP
 static int sdhci_pci_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -1496,7 +1495,9 @@ static int sdhci_pci_resume(struct device *dev)
 
 	return 0;
 }
+#endif
 
+#ifdef CONFIG_PM
 static int sdhci_pci_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -1562,17 +1563,10 @@ static int sdhci_pci_runtime_resume(struct device *dev)
 
 	return 0;
 }
-
-#else /* CONFIG_PM */
-
-#define sdhci_pci_suspend NULL
-#define sdhci_pci_resume NULL
-
-#endif /* CONFIG_PM */
+#endif
 
 static const struct dev_pm_ops sdhci_pci_pm_ops = {
-	.suspend = sdhci_pci_suspend,
-	.resume = sdhci_pci_resume,
+	SET_SYSTEM_SLEEP_PM_OPS(sdhci_pci_suspend, sdhci_pci_resume)
 	SET_RUNTIME_PM_OPS(sdhci_pci_runtime_suspend,
 			sdhci_pci_runtime_resume, NULL)
 };
@@ -1760,11 +1754,12 @@ static void sdhci_pci_remove_slot(struct sdhci_pci_slot *slot)
 
 static void sdhci_pci_runtime_pm_allow(struct device *dev)
 {
-	pm_runtime_put_noidle(dev);
-	pm_runtime_allow(dev);
+	pm_suspend_ignore_children(dev, 1);
 	pm_runtime_set_autosuspend_delay(dev, 50);
 	pm_runtime_use_autosuspend(dev);
-	pm_suspend_ignore_children(dev, 1);
+	pm_runtime_allow(dev);
+	/* Stay active until mmc core scans for a card */
+	pm_runtime_put_noidle(dev);
 }
 
 static void sdhci_pci_runtime_pm_forbid(struct device *dev)
@@ -1810,15 +1805,13 @@ static int sdhci_pci_probe(struct pci_dev *pdev,
 		return -ENODEV;
 	}
 
-	ret = pci_enable_device(pdev);
+	ret = pcim_enable_device(pdev);
 	if (ret)
 		return ret;
 
-	chip = kzalloc(sizeof(struct sdhci_pci_chip), GFP_KERNEL);
-	if (!chip) {
-		ret = -ENOMEM;
-		goto err;
-	}
+	chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
 
 	chip->pdev = pdev;
 	chip->fixes = (const struct sdhci_pci_fixes *)ent->driver_data;
@@ -1834,7 +1827,7 @@ static int sdhci_pci_probe(struct pci_dev *pdev,
 	if (chip->fixes && chip->fixes->probe) {
 		ret = chip->fixes->probe(chip);
 		if (ret)
-			goto free;
+			return ret;
 	}
 
 	slots = chip->num_slots;	/* Quirk may have changed this */
@@ -1844,8 +1837,7 @@ static int sdhci_pci_probe(struct pci_dev *pdev,
 		if (IS_ERR(slot)) {
 			for (i--; i >= 0; i--)
 				sdhci_pci_remove_slot(chip->slots[i]);
-			ret = PTR_ERR(slot);
-			goto free;
+			return PTR_ERR(slot);
 		}
 
 		chip->slots[i] = slot;
@@ -1855,35 +1847,18 @@ static int sdhci_pci_probe(struct pci_dev *pdev,
 		sdhci_pci_runtime_pm_allow(&pdev->dev);
 
 	return 0;
-
-free:
-	pci_set_drvdata(pdev, NULL);
-	kfree(chip);
-
-err:
-	pci_disable_device(pdev);
-	return ret;
 }
 
 static void sdhci_pci_remove(struct pci_dev *pdev)
 {
 	int i;
-	struct sdhci_pci_chip *chip;
+	struct sdhci_pci_chip *chip = pci_get_drvdata(pdev);
 
-	chip = pci_get_drvdata(pdev);
-
-	if (chip) {
-		if (chip->allow_runtime_pm)
-			sdhci_pci_runtime_pm_forbid(&pdev->dev);
-
-		for (i = 0; i < chip->num_slots; i++)
-			sdhci_pci_remove_slot(chip->slots[i]);
-
-		pci_set_drvdata(pdev, NULL);
-		kfree(chip);
-	}
+	if (chip->allow_runtime_pm)
+		sdhci_pci_runtime_pm_forbid(&pdev->dev);
 
-	pci_disable_device(pdev);
+	for (i = 0; i < chip->num_slots; i++)
+		sdhci_pci_remove_slot(chip->slots[i]);
 }
 
 static struct pci_driver sdhci_driver = {
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 89e7151684a1..7e0788712e1a 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -14,7 +14,7 @@
 #define PCI_DEVICE_ID_INTEL_BSW_EMMC	0x2294
 #define PCI_DEVICE_ID_INTEL_BSW_SDIO	0x2295
 #define PCI_DEVICE_ID_INTEL_BSW_SD	0x2296
-#define PCI_DEVICE_ID_INTEL_MRFL_MMC	0x1190
+#define PCI_DEVICE_ID_INTEL_MRFLD_MMC	0x1190
 #define PCI_DEVICE_ID_INTEL_CLV_SDIO0	0x08f9
 #define PCI_DEVICE_ID_INTEL_CLV_SDIO1	0x08fa
 #define PCI_DEVICE_ID_INTEL_CLV_SDIO2	0x08fb
diff --git a/drivers/mmc/host/sdhci-pltfm.c b/drivers/mmc/host/sdhci-pltfm.c
index 64f287a03cd3..1d17dcfc3ffb 100644
--- a/drivers/mmc/host/sdhci-pltfm.c
+++ b/drivers/mmc/host/sdhci-pltfm.c
@@ -215,29 +215,26 @@ int sdhci_pltfm_unregister(struct platform_device *pdev)
 }
 EXPORT_SYMBOL_GPL(sdhci_pltfm_unregister);
 
-#ifdef CONFIG_PM
-int sdhci_pltfm_suspend(struct device *dev)
+#ifdef CONFIG_PM_SLEEP
+static int sdhci_pltfm_suspend(struct device *dev)
 {
 	struct sdhci_host *host = dev_get_drvdata(dev);
 
 	return sdhci_suspend_host(host);
 }
-EXPORT_SYMBOL_GPL(sdhci_pltfm_suspend);
 
-int sdhci_pltfm_resume(struct device *dev)
+static int sdhci_pltfm_resume(struct device *dev)
 {
 	struct sdhci_host *host = dev_get_drvdata(dev);
 
 	return sdhci_resume_host(host);
 }
-EXPORT_SYMBOL_GPL(sdhci_pltfm_resume);
+#endif
 
 const struct dev_pm_ops sdhci_pltfm_pmops = {
-	.suspend	= sdhci_pltfm_suspend,
-	.resume		= sdhci_pltfm_resume,
+	SET_SYSTEM_SLEEP_PM_OPS(sdhci_pltfm_suspend, sdhci_pltfm_resume)
 };
 EXPORT_SYMBOL_GPL(sdhci_pltfm_pmops);
-#endif	/* CONFIG_PM */
 
 static int __init sdhci_pltfm_drv_init(void)
 {
diff --git a/drivers/mmc/host/sdhci-pltfm.h b/drivers/mmc/host/sdhci-pltfm.h
index d38053bf9e4d..3280f2077959 100644
--- a/drivers/mmc/host/sdhci-pltfm.h
+++ b/drivers/mmc/host/sdhci-pltfm.h
@@ -109,13 +109,6 @@ static inline void *sdhci_pltfm_priv(struct sdhci_pltfm_host *host)
 	return (void *)host->private;
 }
 
-#ifdef CONFIG_PM
-extern int sdhci_pltfm_suspend(struct device *dev);
-extern int sdhci_pltfm_resume(struct device *dev);
 extern const struct dev_pm_ops sdhci_pltfm_pmops;
-#define SDHCI_PLTFM_PMOPS (&sdhci_pltfm_pmops)
-#else
-#define SDHCI_PLTFM_PMOPS NULL
-#endif
 
 #endif /* _DRIVERS_MMC_SDHCI_PLTFM_H */
diff --git a/drivers/mmc/host/sdhci-pxav2.c b/drivers/mmc/host/sdhci-pxav2.c
index 1d8dd3540636..347eae2d7b6a 100644
--- a/drivers/mmc/host/sdhci-pxav2.c
+++ b/drivers/mmc/host/sdhci-pxav2.c
@@ -252,7 +252,7 @@ static struct platform_driver sdhci_pxav2_driver = {
 	.driver		= {
 		.name	= "sdhci-pxav2",
 		.of_match_table = of_match_ptr(sdhci_pxav2_of_match),
-		.pm	= SDHCI_PLTFM_PMOPS,
+		.pm	= &sdhci_pltfm_pmops,
 	},
 	.probe		= sdhci_pxav2_probe,
 	.remove		= sdhci_pxav2_remove,
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 30132500aa1c..dd1938d341f7 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -583,24 +583,17 @@ static int sdhci_pxav3_runtime_resume(struct device *dev)
 }
 #endif
 
-#ifdef CONFIG_PM
 static const struct dev_pm_ops sdhci_pxav3_pmops = {
 	SET_SYSTEM_SLEEP_PM_OPS(sdhci_pxav3_suspend, sdhci_pxav3_resume)
 	SET_RUNTIME_PM_OPS(sdhci_pxav3_runtime_suspend,
 		sdhci_pxav3_runtime_resume, NULL)
 };
 
-#define SDHCI_PXAV3_PMOPS (&sdhci_pxav3_pmops)
-
-#else
-#define SDHCI_PXAV3_PMOPS NULL
-#endif
-
 static struct platform_driver sdhci_pxav3_driver = {
 	.driver		= {
 		.name	= "sdhci-pxav3",
 		.of_match_table = of_match_ptr(sdhci_pxav3_of_match),
-		.pm	= SDHCI_PXAV3_PMOPS,
+		.pm	= &sdhci_pxav3_pmops,
 	},
 	.probe		= sdhci_pxav3_probe,
 	.remove		= sdhci_pxav3_remove,
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index 70c724bc6fc7..784c5a848fb4 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -714,19 +714,12 @@ static int sdhci_s3c_runtime_resume(struct device *dev)
 }
 #endif
 
-#ifdef CONFIG_PM
 static const struct dev_pm_ops sdhci_s3c_pmops = {
 	SET_SYSTEM_SLEEP_PM_OPS(sdhci_s3c_suspend, sdhci_s3c_resume)
 	SET_RUNTIME_PM_OPS(sdhci_s3c_runtime_suspend, sdhci_s3c_runtime_resume,
 			   NULL)
 };
 
-#define SDHCI_S3C_PMOPS (&sdhci_s3c_pmops)
-
-#else
-#define SDHCI_S3C_PMOPS NULL
-#endif
-
 #if defined(CONFIG_CPU_EXYNOS4210) || defined(CONFIG_SOC_EXYNOS4212)
 static struct sdhci_s3c_drv_data exynos4_sdhci_drv_data = {
 	.no_divider = true,
@@ -765,7 +758,7 @@ static struct platform_driver sdhci_s3c_driver = {
 	.driver		= {
 		.name	= "s3c-sdhci",
 		.of_match_table = of_match_ptr(sdhci_s3c_dt_match),
-		.pm	= SDHCI_S3C_PMOPS,
+		.pm	= &sdhci_s3c_pmops,
 	},
 };
 
diff --git a/drivers/mmc/host/sdhci-sirf.c b/drivers/mmc/host/sdhci-sirf.c
index 34866f668dd7..5d068639dd3f 100644
--- a/drivers/mmc/host/sdhci-sirf.c
+++ b/drivers/mmc/host/sdhci-sirf.c
@@ -260,9 +260,9 @@ static int sdhci_sirf_resume(struct device *dev)
 
 	return sdhci_resume_host(host);
 }
+#endif
 
 static SIMPLE_DEV_PM_OPS(sdhci_sirf_pm_ops, sdhci_sirf_suspend, sdhci_sirf_resume);
-#endif
 
 static const struct of_device_id sdhci_sirf_of_match[] = {
 	{ .compatible = "sirf,prima2-sdhc" },
@@ -274,9 +274,7 @@ static struct platform_driver sdhci_sirf_driver = {
 	.driver		= {
 		.name	= "sdhci-sirf",
 		.of_match_table = sdhci_sirf_of_match,
-#ifdef CONFIG_PM_SLEEP
 		.pm	= &sdhci_sirf_pm_ops,
-#endif
 	},
 	.probe		= sdhci_sirf_probe,
 	.remove		= sdhci_pltfm_unregister,
diff --git a/drivers/mmc/host/sdhci-st.c b/drivers/mmc/host/sdhci-st.c
index 320e1c2f8853..c95ba83366a0 100644
--- a/drivers/mmc/host/sdhci-st.c
+++ b/drivers/mmc/host/sdhci-st.c
@@ -183,7 +183,7 @@ static void st_mmcss_cconfig(struct device_node *np, struct sdhci_host *host)
 
 	writel_relaxed(cconf2, host->ioaddr + ST_MMC_CCONFIG_REG_2);
 
-	if (mhost->caps & MMC_CAP_NONREMOVABLE)
+	if (!mmc_card_is_removable(mhost))
 		cconf3 |= ST_MMC_CCONFIG_EMMC_SLOT_TYPE;
 	else
 		/* CARD _D ET_CTRL */
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index bcc0de47fe7e..1e93dc4e303e 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -148,28 +148,37 @@ static void tegra_sdhci_reset(struct sdhci_host *host, u8 mask)
 		return;
 
 	misc_ctrl = sdhci_readl(host, SDHCI_TEGRA_VENDOR_MISC_CTRL);
-	/* Erratum: Enable SDHCI spec v3.00 support */
-	if (soc_data->nvquirks & NVQUIRK_ENABLE_SDHCI_SPEC_300)
-		misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDHCI_SPEC_300;
-	/* Advertise UHS modes as supported by host */
-	if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR50)
-		misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR50;
-	else
-		misc_ctrl &= ~SDHCI_MISC_CTRL_ENABLE_SDR50;
-	if (soc_data->nvquirks & NVQUIRK_ENABLE_DDR50)
-		misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_DDR50;
-	else
-		misc_ctrl &= ~SDHCI_MISC_CTRL_ENABLE_DDR50;
-	if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR104)
-		misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR104;
-	else
-		misc_ctrl &= ~SDHCI_MISC_CTRL_ENABLE_SDR104;
-	sdhci_writel(host, misc_ctrl, SDHCI_TEGRA_VENDOR_MISC_CTRL);
-
 	clk_ctrl = sdhci_readl(host, SDHCI_TEGRA_VENDOR_CLOCK_CTRL);
+
+	misc_ctrl &= ~(SDHCI_MISC_CTRL_ENABLE_SDHCI_SPEC_300 |
+		       SDHCI_MISC_CTRL_ENABLE_SDR50 |
+		       SDHCI_MISC_CTRL_ENABLE_DDR50 |
+		       SDHCI_MISC_CTRL_ENABLE_SDR104);
+
 	clk_ctrl &= ~SDHCI_CLOCK_CTRL_SPI_MODE_CLKEN_OVERRIDE;
-	if (soc_data->nvquirks & SDHCI_MISC_CTRL_ENABLE_SDR50)
-		clk_ctrl |= SDHCI_CLOCK_CTRL_SDR50_TUNING_OVERRIDE;
+
+	/*
+	 * If the board does not define a regulator for the SDHCI
+	 * IO voltage, then don't advertise support for UHS modes
+	 * even if the device supports it because the IO voltage
+	 * cannot be configured.
+	 */
+	if (!IS_ERR(host->mmc->supply.vqmmc)) {
+		/* Erratum: Enable SDHCI spec v3.00 support */
+		if (soc_data->nvquirks & NVQUIRK_ENABLE_SDHCI_SPEC_300)
+			misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDHCI_SPEC_300;
+		/* Advertise UHS modes as supported by host */
+		if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR50)
+			misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR50;
+		if (soc_data->nvquirks & NVQUIRK_ENABLE_DDR50)
+			misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_DDR50;
+		if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR104)
+			misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR104;
+		if (soc_data->nvquirks & SDHCI_MISC_CTRL_ENABLE_SDR50)
+			clk_ctrl |= SDHCI_CLOCK_CTRL_SDR50_TUNING_OVERRIDE;
+	}
+
+	sdhci_writel(host, misc_ctrl, SDHCI_TEGRA_VENDOR_MISC_CTRL);
 	sdhci_writel(host, clk_ctrl, SDHCI_TEGRA_VENDOR_CLOCK_CTRL);
 
 	if (soc_data->nvquirks & NVQUIRK_HAS_PADCALIB)
@@ -474,7 +483,7 @@ static struct platform_driver sdhci_tegra_driver = {
 	.driver		= {
 		.name	= "sdhci-tegra",
 		.of_match_table = sdhci_tegra_dt_match,
-		.pm	= SDHCI_PLTFM_PMOPS,
+		.pm	= &sdhci_pltfm_pmops,
 	},
 	.probe		= sdhci_tegra_probe,
 	.remove		= sdhci_pltfm_unregister,
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 0e3d7c056cb1..cd65d474afa2 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -45,65 +45,62 @@ static unsigned int debug_quirks2;
 
 static void sdhci_finish_data(struct sdhci_host *);
 
-static void sdhci_finish_command(struct sdhci_host *);
-static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode);
 static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable);
-static int sdhci_get_cd(struct mmc_host *mmc);
 
 static void sdhci_dumpregs(struct sdhci_host *host)
 {
-	pr_debug(DRIVER_NAME ": =========== REGISTER DUMP (%s)===========\n",
-		mmc_hostname(host->mmc));
-
-	pr_debug(DRIVER_NAME ": Sys addr: 0x%08x | Version:  0x%08x\n",
-		sdhci_readl(host, SDHCI_DMA_ADDRESS),
-		sdhci_readw(host, SDHCI_HOST_VERSION));
-	pr_debug(DRIVER_NAME ": Blk size: 0x%08x | Blk cnt:  0x%08x\n",
-		sdhci_readw(host, SDHCI_BLOCK_SIZE),
-		sdhci_readw(host, SDHCI_BLOCK_COUNT));
-	pr_debug(DRIVER_NAME ": Argument: 0x%08x | Trn mode: 0x%08x\n",
-		sdhci_readl(host, SDHCI_ARGUMENT),
-		sdhci_readw(host, SDHCI_TRANSFER_MODE));
-	pr_debug(DRIVER_NAME ": Present:  0x%08x | Host ctl: 0x%08x\n",
-		sdhci_readl(host, SDHCI_PRESENT_STATE),
-		sdhci_readb(host, SDHCI_HOST_CONTROL));
-	pr_debug(DRIVER_NAME ": Power:    0x%08x | Blk gap:  0x%08x\n",
-		sdhci_readb(host, SDHCI_POWER_CONTROL),
-		sdhci_readb(host, SDHCI_BLOCK_GAP_CONTROL));
-	pr_debug(DRIVER_NAME ": Wake-up:  0x%08x | Clock:    0x%08x\n",
-		sdhci_readb(host, SDHCI_WAKE_UP_CONTROL),
-		sdhci_readw(host, SDHCI_CLOCK_CONTROL));
-	pr_debug(DRIVER_NAME ": Timeout:  0x%08x | Int stat: 0x%08x\n",
-		sdhci_readb(host, SDHCI_TIMEOUT_CONTROL),
-		sdhci_readl(host, SDHCI_INT_STATUS));
-	pr_debug(DRIVER_NAME ": Int enab: 0x%08x | Sig enab: 0x%08x\n",
-		sdhci_readl(host, SDHCI_INT_ENABLE),
-		sdhci_readl(host, SDHCI_SIGNAL_ENABLE));
-	pr_debug(DRIVER_NAME ": AC12 err: 0x%08x | Slot int: 0x%08x\n",
-		sdhci_readw(host, SDHCI_ACMD12_ERR),
-		sdhci_readw(host, SDHCI_SLOT_INT_STATUS));
-	pr_debug(DRIVER_NAME ": Caps:     0x%08x | Caps_1:   0x%08x\n",
-		sdhci_readl(host, SDHCI_CAPABILITIES),
-		sdhci_readl(host, SDHCI_CAPABILITIES_1));
-	pr_debug(DRIVER_NAME ": Cmd:      0x%08x | Max curr: 0x%08x\n",
-		sdhci_readw(host, SDHCI_COMMAND),
-		sdhci_readl(host, SDHCI_MAX_CURRENT));
-	pr_debug(DRIVER_NAME ": Host ctl2: 0x%08x\n",
-		sdhci_readw(host, SDHCI_HOST_CONTROL2));
+	pr_err(DRIVER_NAME ": =========== REGISTER DUMP (%s)===========\n",
+	       mmc_hostname(host->mmc));
+
+	pr_err(DRIVER_NAME ": Sys addr: 0x%08x | Version:  0x%08x\n",
+	       sdhci_readl(host, SDHCI_DMA_ADDRESS),
+	       sdhci_readw(host, SDHCI_HOST_VERSION));
+	pr_err(DRIVER_NAME ": Blk size: 0x%08x | Blk cnt:  0x%08x\n",
+	       sdhci_readw(host, SDHCI_BLOCK_SIZE),
+	       sdhci_readw(host, SDHCI_BLOCK_COUNT));
+	pr_err(DRIVER_NAME ": Argument: 0x%08x | Trn mode: 0x%08x\n",
+	       sdhci_readl(host, SDHCI_ARGUMENT),
+	       sdhci_readw(host, SDHCI_TRANSFER_MODE));
+	pr_err(DRIVER_NAME ": Present:  0x%08x | Host ctl: 0x%08x\n",
+	       sdhci_readl(host, SDHCI_PRESENT_STATE),
+	       sdhci_readb(host, SDHCI_HOST_CONTROL));
+	pr_err(DRIVER_NAME ": Power:    0x%08x | Blk gap:  0x%08x\n",
+	       sdhci_readb(host, SDHCI_POWER_CONTROL),
+	       sdhci_readb(host, SDHCI_BLOCK_GAP_CONTROL));
+	pr_err(DRIVER_NAME ": Wake-up:  0x%08x | Clock:    0x%08x\n",
+	       sdhci_readb(host, SDHCI_WAKE_UP_CONTROL),
+	       sdhci_readw(host, SDHCI_CLOCK_CONTROL));
+	pr_err(DRIVER_NAME ": Timeout:  0x%08x | Int stat: 0x%08x\n",
+	       sdhci_readb(host, SDHCI_TIMEOUT_CONTROL),
+	       sdhci_readl(host, SDHCI_INT_STATUS));
+	pr_err(DRIVER_NAME ": Int enab: 0x%08x | Sig enab: 0x%08x\n",
+	       sdhci_readl(host, SDHCI_INT_ENABLE),
+	       sdhci_readl(host, SDHCI_SIGNAL_ENABLE));
+	pr_err(DRIVER_NAME ": AC12 err: 0x%08x | Slot int: 0x%08x\n",
+	       sdhci_readw(host, SDHCI_ACMD12_ERR),
+	       sdhci_readw(host, SDHCI_SLOT_INT_STATUS));
+	pr_err(DRIVER_NAME ": Caps:     0x%08x | Caps_1:   0x%08x\n",
+	       sdhci_readl(host, SDHCI_CAPABILITIES),
+	       sdhci_readl(host, SDHCI_CAPABILITIES_1));
+	pr_err(DRIVER_NAME ": Cmd:      0x%08x | Max curr: 0x%08x\n",
+	       sdhci_readw(host, SDHCI_COMMAND),
+	       sdhci_readl(host, SDHCI_MAX_CURRENT));
+	pr_err(DRIVER_NAME ": Host ctl2: 0x%08x\n",
+	       sdhci_readw(host, SDHCI_HOST_CONTROL2));
 
 	if (host->flags & SDHCI_USE_ADMA) {
 		if (host->flags & SDHCI_USE_64_BIT_DMA)
-			pr_debug(DRIVER_NAME ": ADMA Err: 0x%08x | ADMA Ptr: 0x%08x%08x\n",
-				 readl(host->ioaddr + SDHCI_ADMA_ERROR),
-				 readl(host->ioaddr + SDHCI_ADMA_ADDRESS_HI),
-				 readl(host->ioaddr + SDHCI_ADMA_ADDRESS));
+			pr_err(DRIVER_NAME ": ADMA Err: 0x%08x | ADMA Ptr: 0x%08x%08x\n",
+			       readl(host->ioaddr + SDHCI_ADMA_ERROR),
+			       readl(host->ioaddr + SDHCI_ADMA_ADDRESS_HI),
+			       readl(host->ioaddr + SDHCI_ADMA_ADDRESS));
 		else
-			pr_debug(DRIVER_NAME ": ADMA Err: 0x%08x | ADMA Ptr: 0x%08x\n",
-				 readl(host->ioaddr + SDHCI_ADMA_ERROR),
-				 readl(host->ioaddr + SDHCI_ADMA_ADDRESS));
+			pr_err(DRIVER_NAME ": ADMA Err: 0x%08x | ADMA Ptr: 0x%08x\n",
+			       readl(host->ioaddr + SDHCI_ADMA_ERROR),
+			       readl(host->ioaddr + SDHCI_ADMA_ADDRESS));
 	}
 
-	pr_debug(DRIVER_NAME ": ===========================================\n");
+	pr_err(DRIVER_NAME ": ===========================================\n");
 }
 
 /*****************************************************************************\
@@ -112,12 +109,17 @@ static void sdhci_dumpregs(struct sdhci_host *host)
  *                                                                           *
 \*****************************************************************************/
 
+static inline bool sdhci_data_line_cmd(struct mmc_command *cmd)
+{
+	return cmd->data || cmd->flags & MMC_RSP_BUSY;
+}
+
 static void sdhci_set_card_detection(struct sdhci_host *host, bool enable)
 {
 	u32 present;
 
 	if ((host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) ||
-	    (host->mmc->caps & MMC_CAP_NONREMOVABLE))
+	    !mmc_card_is_removable(host->mmc))
 		return;
 
 	if (enable) {
@@ -193,7 +195,9 @@ EXPORT_SYMBOL_GPL(sdhci_reset);
 static void sdhci_do_reset(struct sdhci_host *host, u8 mask)
 {
 	if (host->quirks & SDHCI_QUIRK_NO_CARD_NO_RESET) {
-		if (!sdhci_get_cd(host->mmc))
+		struct mmc_host *mmc = host->mmc;
+
+		if (!mmc->ops->get_cd(mmc))
 			return;
 	}
 
@@ -210,10 +214,10 @@ static void sdhci_do_reset(struct sdhci_host *host, u8 mask)
 	}
 }
 
-static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios);
-
 static void sdhci_init(struct sdhci_host *host, int soft)
 {
+	struct mmc_host *mmc = host->mmc;
+
 	if (soft)
 		sdhci_do_reset(host, SDHCI_RESET_CMD|SDHCI_RESET_DATA);
 	else
@@ -225,13 +229,17 @@ static void sdhci_init(struct sdhci_host *host, int soft)
 		    SDHCI_INT_TIMEOUT | SDHCI_INT_DATA_END |
 		    SDHCI_INT_RESPONSE;
 
+	if (host->tuning_mode == SDHCI_TUNING_MODE_2 ||
+	    host->tuning_mode == SDHCI_TUNING_MODE_3)
+		host->ier |= SDHCI_INT_RETUNE;
+
 	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 
 	if (soft) {
 		/* force clock reconfiguration */
 		host->clock = 0;
-		sdhci_set_ios(host->mmc, &host->mmc->ios);
+		mmc->ops->set_ios(mmc, &mmc->ios);
 	}
 }
 
@@ -429,8 +437,6 @@ static void sdhci_transfer_pio(struct sdhci_host *host)
 {
 	u32 mask;
 
-	BUG_ON(!host->data);
-
 	if (host->blocks == 0)
 		return;
 
@@ -747,14 +753,14 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 	u8 ctrl;
 	struct mmc_data *data = cmd->data;
 
-	WARN_ON(host->data);
-
-	if (data || (cmd->flags & MMC_RSP_BUSY))
+	if (sdhci_data_line_cmd(cmd))
 		sdhci_set_timeout(host, cmd);
 
 	if (!data)
 		return;
 
+	WARN_ON(host->data);
+
 	/* Sanity checks */
 	BUG_ON(data->blksz * data->blocks > 524288);
 	BUG_ON(data->blksz > host->mmc->max_blk_size);
@@ -879,6 +885,12 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 	sdhci_writew(host, data->blocks, SDHCI_BLOCK_COUNT);
 }
 
+static inline bool sdhci_auto_cmd12(struct sdhci_host *host,
+				    struct mmc_request *mrq)
+{
+	return !mrq->sbc && (host->flags & SDHCI_AUTO_CMD12);
+}
+
 static void sdhci_set_transfer_mode(struct sdhci_host *host,
 	struct mmc_command *cmd)
 {
@@ -909,12 +921,12 @@ static void sdhci_set_transfer_mode(struct sdhci_host *host,
 		 * If we are sending CMD23, CMD12 never gets sent
 		 * on successful completion (so no Auto-CMD12).
 		 */
-		if (!host->mrq->sbc && (host->flags & SDHCI_AUTO_CMD12) &&
+		if (sdhci_auto_cmd12(host, cmd->mrq) &&
 		    (cmd->opcode != SD_IO_RW_EXTENDED))
 			mode |= SDHCI_TRNS_AUTO_CMD12;
-		else if (host->mrq->sbc && (host->flags & SDHCI_AUTO_CMD23)) {
+		else if (cmd->mrq->sbc && (host->flags & SDHCI_AUTO_CMD23)) {
 			mode |= SDHCI_TRNS_AUTO_CMD23;
-			sdhci_writel(host, host->mrq->sbc->arg, SDHCI_ARGUMENT2);
+			sdhci_writel(host, cmd->mrq->sbc->arg, SDHCI_ARGUMENT2);
 		}
 	}
 
@@ -926,14 +938,63 @@ static void sdhci_set_transfer_mode(struct sdhci_host *host,
 	sdhci_writew(host, mode, SDHCI_TRANSFER_MODE);
 }
 
-static void sdhci_finish_data(struct sdhci_host *host)
+static bool sdhci_needs_reset(struct sdhci_host *host, struct mmc_request *mrq)
+{
+	return (!(host->flags & SDHCI_DEVICE_DEAD) &&
+		((mrq->cmd && mrq->cmd->error) ||
+		 (mrq->sbc && mrq->sbc->error) ||
+		 (mrq->data && ((mrq->data->error && !mrq->data->stop) ||
+				(mrq->data->stop && mrq->data->stop->error))) ||
+		 (host->quirks & SDHCI_QUIRK_RESET_AFTER_REQUEST)));
+}
+
+static void __sdhci_finish_mrq(struct sdhci_host *host, struct mmc_request *mrq)
+{
+	int i;
+
+	for (i = 0; i < SDHCI_MAX_MRQS; i++) {
+		if (host->mrqs_done[i] == mrq) {
+			WARN_ON(1);
+			return;
+		}
+	}
+
+	for (i = 0; i < SDHCI_MAX_MRQS; i++) {
+		if (!host->mrqs_done[i]) {
+			host->mrqs_done[i] = mrq;
+			break;
+		}
+	}
+
+	WARN_ON(i >= SDHCI_MAX_MRQS);
+
+	tasklet_schedule(&host->finish_tasklet);
+}
+
+static void sdhci_finish_mrq(struct sdhci_host *host, struct mmc_request *mrq)
 {
-	struct mmc_data *data;
+	if (host->cmd && host->cmd->mrq == mrq)
+		host->cmd = NULL;
+
+	if (host->data_cmd && host->data_cmd->mrq == mrq)
+		host->data_cmd = NULL;
+
+	if (host->data && host->data->mrq == mrq)
+		host->data = NULL;
 
-	BUG_ON(!host->data);
+	if (sdhci_needs_reset(host, mrq))
+		host->pending_reset = true;
+
+	__sdhci_finish_mrq(host, mrq);
+}
+
+static void sdhci_finish_data(struct sdhci_host *host)
+{
+	struct mmc_command *data_cmd = host->data_cmd;
+	struct mmc_data *data = host->data;
 
-	data = host->data;
 	host->data = NULL;
+	host->data_cmd = NULL;
 
 	if ((host->flags & (SDHCI_REQ_USE_DMA | SDHCI_USE_ADMA)) ==
 	    (SDHCI_REQ_USE_DMA | SDHCI_USE_ADMA))
@@ -958,20 +1019,41 @@ static void sdhci_finish_data(struct sdhci_host *host)
 	 */
 	if (data->stop &&
 	    (data->error ||
-	     !host->mrq->sbc)) {
+	     !data->mrq->sbc)) {
 
 		/*
 		 * The controller needs a reset of internal state machines
 		 * upon error conditions.
 		 */
 		if (data->error) {
-			sdhci_do_reset(host, SDHCI_RESET_CMD);
+			if (!host->cmd || host->cmd == data_cmd)
+				sdhci_do_reset(host, SDHCI_RESET_CMD);
 			sdhci_do_reset(host, SDHCI_RESET_DATA);
 		}
 
+		/* Avoid triggering warning in sdhci_send_command() */
+		host->cmd = NULL;
 		sdhci_send_command(host, data->stop);
-	} else
-		tasklet_schedule(&host->finish_tasklet);
+	} else {
+		sdhci_finish_mrq(host, data->mrq);
+	}
+}
+
+static void sdhci_mod_timer(struct sdhci_host *host, struct mmc_request *mrq,
+			    unsigned long timeout)
+{
+	if (sdhci_data_line_cmd(mrq->cmd))
+		mod_timer(&host->data_timer, timeout);
+	else
+		mod_timer(&host->timer, timeout);
+}
+
+static void sdhci_del_timer(struct sdhci_host *host, struct mmc_request *mrq)
+{
+	if (sdhci_data_line_cmd(mrq->cmd))
+		del_timer(&host->data_timer);
+	else
+		del_timer(&host->timer);
 }
 
 void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
@@ -989,12 +1071,12 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 	timeout = 10;
 
 	mask = SDHCI_CMD_INHIBIT;
-	if ((cmd->data != NULL) || (cmd->flags & MMC_RSP_BUSY))
+	if (sdhci_data_line_cmd(cmd))
 		mask |= SDHCI_DATA_INHIBIT;
 
 	/* We shouldn't wait for data inihibit for stop commands, even
 	   though they might use busy signaling */
-	if (host->mrq->data && (cmd == host->mrq->data->stop))
+	if (cmd->mrq->data && (cmd == cmd->mrq->data->stop))
 		mask &= ~SDHCI_DATA_INHIBIT;
 
 	while (sdhci_readl(host, SDHCI_PRESENT_STATE) & mask) {
@@ -1003,7 +1085,7 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 			       mmc_hostname(host->mmc));
 			sdhci_dumpregs(host);
 			cmd->error = -EIO;
-			tasklet_schedule(&host->finish_tasklet);
+			sdhci_finish_mrq(host, cmd->mrq);
 			return;
 		}
 		timeout--;
@@ -1015,10 +1097,13 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 		timeout += DIV_ROUND_UP(cmd->busy_timeout, 1000) * HZ + HZ;
 	else
 		timeout += 10 * HZ;
-	mod_timer(&host->timer, timeout);
+	sdhci_mod_timer(host, cmd->mrq, timeout);
 
 	host->cmd = cmd;
-	host->busy_handle = 0;
+	if (sdhci_data_line_cmd(cmd)) {
+		WARN_ON(host->data_cmd);
+		host->data_cmd = cmd;
+	}
 
 	sdhci_prepare_data(host, cmd);
 
@@ -1030,7 +1115,7 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 		pr_err("%s: Unsupported response type!\n",
 			mmc_hostname(host->mmc));
 		cmd->error = -EINVAL;
-		tasklet_schedule(&host->finish_tasklet);
+		sdhci_finish_mrq(host, cmd->mrq);
 		return;
 	}
 
@@ -1059,40 +1144,58 @@ EXPORT_SYMBOL_GPL(sdhci_send_command);
 
 static void sdhci_finish_command(struct sdhci_host *host)
 {
+	struct mmc_command *cmd = host->cmd;
 	int i;
 
-	BUG_ON(host->cmd == NULL);
+	host->cmd = NULL;
 
-	if (host->cmd->flags & MMC_RSP_PRESENT) {
-		if (host->cmd->flags & MMC_RSP_136) {
+	if (cmd->flags & MMC_RSP_PRESENT) {
+		if (cmd->flags & MMC_RSP_136) {
 			/* CRC is stripped so we need to do some shifting. */
 			for (i = 0;i < 4;i++) {
-				host->cmd->resp[i] = sdhci_readl(host,
+				cmd->resp[i] = sdhci_readl(host,
 					SDHCI_RESPONSE + (3-i)*4) << 8;
 				if (i != 3)
-					host->cmd->resp[i] |=
+					cmd->resp[i] |=
 						sdhci_readb(host,
 						SDHCI_RESPONSE + (3-i)*4-1);
 			}
 		} else {
-			host->cmd->resp[0] = sdhci_readl(host, SDHCI_RESPONSE);
+			cmd->resp[0] = sdhci_readl(host, SDHCI_RESPONSE);
+		}
+	}
+
+	/*
+	 * The host can send and interrupt when the busy state has
+	 * ended, allowing us to wait without wasting CPU cycles.
+	 * The busy signal uses DAT0 so this is similar to waiting
+	 * for data to complete.
+	 *
+	 * Note: The 1.0 specification is a bit ambiguous about this
+	 *       feature so there might be some problems with older
+	 *       controllers.
+	 */
+	if (cmd->flags & MMC_RSP_BUSY) {
+		if (cmd->data) {
+			DBG("Cannot wait for busy signal when also doing a data transfer");
+		} else if (!(host->quirks & SDHCI_QUIRK_NO_BUSY_IRQ) &&
+			   cmd == host->data_cmd) {
+			/* Command complete before busy is ended */
+			return;
 		}
 	}
 
 	/* Finished CMD23, now send actual command. */
-	if (host->cmd == host->mrq->sbc) {
-		host->cmd = NULL;
-		sdhci_send_command(host, host->mrq->cmd);
+	if (cmd == cmd->mrq->sbc) {
+		sdhci_send_command(host, cmd->mrq->cmd);
 	} else {
 
 		/* Processed actual command. */
 		if (host->data && host->data_early)
 			sdhci_finish_data(host);
 
-		if (!host->cmd->data)
-			tasklet_schedule(&host->finish_tasklet);
-
-		host->cmd = NULL;
+		if (!cmd->data)
+			sdhci_finish_mrq(host, cmd->mrq);
 	}
 }
 
@@ -1373,26 +1476,22 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 	spin_lock_irqsave(&host->lock, flags);
 
-	WARN_ON(host->mrq != NULL);
-
 	sdhci_led_activate(host);
 
 	/*
 	 * Ensure we don't send the STOP for non-SET_BLOCK_COUNTED
 	 * requests if Auto-CMD12 is enabled.
 	 */
-	if (!mrq->sbc && (host->flags & SDHCI_AUTO_CMD12)) {
+	if (sdhci_auto_cmd12(host, mrq)) {
 		if (mrq->stop) {
 			mrq->data->stop = NULL;
 			mrq->stop = NULL;
 		}
 	}
 
-	host->mrq = mrq;
-
 	if (!present || host->flags & SDHCI_DEVICE_DEAD) {
-		host->mrq->cmd->error = -ENOMEDIUM;
-		tasklet_schedule(&host->finish_tasklet);
+		mrq->cmd->error = -ENOMEDIUM;
+		sdhci_finish_mrq(host, mrq);
 	} else {
 		if (mrq->sbc && !(host->flags & SDHCI_AUTO_CMD23))
 			sdhci_send_command(host, mrq->sbc);
@@ -1617,7 +1716,7 @@ static int sdhci_get_cd(struct mmc_host *mmc)
 		return 0;
 
 	/* If nonremovable, assume that the card is always present. */
-	if (host->mmc->caps & MMC_CAP_NONREMOVABLE)
+	if (!mmc_card_is_removable(host->mmc))
 		return 1;
 
 	/*
@@ -1733,13 +1832,14 @@ static int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
 
 	switch (ios->signal_voltage) {
 	case MMC_SIGNAL_VOLTAGE_330:
+		if (!(host->flags & SDHCI_SIGNALING_330))
+			return -EINVAL;
 		/* Set 1.8V Signal Enable in the Host Control2 register to 0 */
 		ctrl &= ~SDHCI_CTRL_VDD_180;
 		sdhci_writew(host, ctrl, SDHCI_HOST_CONTROL2);
 
 		if (!IS_ERR(mmc->supply.vqmmc)) {
-			ret = regulator_set_voltage(mmc->supply.vqmmc, 2700000,
-						    3600000);
+			ret = mmc_regulator_set_vqmmc(mmc, ios);
 			if (ret) {
 				pr_warn("%s: Switching to 3.3V signalling voltage failed\n",
 					mmc_hostname(mmc));
@@ -1759,9 +1859,10 @@ static int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
 
 		return -EAGAIN;
 	case MMC_SIGNAL_VOLTAGE_180:
+		if (!(host->flags & SDHCI_SIGNALING_180))
+			return -EINVAL;
 		if (!IS_ERR(mmc->supply.vqmmc)) {
-			ret = regulator_set_voltage(mmc->supply.vqmmc,
-					1700000, 1950000);
+			ret = mmc_regulator_set_vqmmc(mmc, ios);
 			if (ret) {
 				pr_warn("%s: Switching to 1.8V signalling voltage failed\n",
 					mmc_hostname(mmc));
@@ -1790,9 +1891,10 @@ static int sdhci_start_signal_voltage_switch(struct mmc_host *mmc,
 
 		return -EAGAIN;
 	case MMC_SIGNAL_VOLTAGE_120:
+		if (!(host->flags & SDHCI_SIGNALING_120))
+			return -EINVAL;
 		if (!IS_ERR(mmc->supply.vqmmc)) {
-			ret = regulator_set_voltage(mmc->supply.vqmmc, 1100000,
-						    1300000);
+			ret = mmc_regulator_set_vqmmc(mmc, ios);
 			if (ret) {
 				pr_warn("%s: Switching to 1.2V signalling voltage failed\n",
 					mmc_hostname(mmc));
@@ -1811,10 +1913,10 @@ static int sdhci_card_busy(struct mmc_host *mmc)
 	struct sdhci_host *host = mmc_priv(mmc);
 	u32 present_state;
 
-	/* Check whether DAT[3:0] is 0000 */
+	/* Check whether DAT[0] is 0 */
 	present_state = sdhci_readl(host, SDHCI_PRESENT_STATE);
 
-	return !(present_state & SDHCI_DATA_LVL_MASK);
+	return !(present_state & SDHCI_DATA_0_LVL_MASK);
 }
 
 static int sdhci_prepare_hs400_tuning(struct mmc_host *mmc, struct mmc_ios *ios)
@@ -1909,7 +2011,7 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 
 	/*
 	 * Issue CMD19 repeatedly till Execute Tuning is set to 0 or the number
-	 * of loops reaches 40 times or a timeout of 150ms occurs.
+	 * of loops reaches 40 times.
 	 */
 	do {
 		struct mmc_command cmd = {0};
@@ -1920,13 +2022,13 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		cmd.flags = MMC_RSP_R1 | MMC_CMD_ADTC;
 		cmd.retries = 0;
 		cmd.data = NULL;
+		cmd.mrq = &mrq;
 		cmd.error = 0;
 
 		if (tuning_loop_counter-- == 0)
 			break;
 
 		mrq.cmd = &cmd;
-		host->mrq = &mrq;
 
 		/*
 		 * In response to CMD19, the card sends 64 bytes of tuning
@@ -1956,7 +2058,7 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		sdhci_send_command(host, &cmd);
 
 		host->cmd = NULL;
-		host->mrq = NULL;
+		sdhci_del_timer(host, &mrq);
 
 		spin_unlock_irqrestore(&host->lock, flags);
 		/* Wait for Buffer Read Ready interrupt */
@@ -2086,6 +2188,24 @@ static void sdhci_pre_req(struct mmc_host *mmc, struct mmc_request *mrq,
 		sdhci_pre_dma_transfer(host, mrq->data, COOKIE_PRE_MAPPED);
 }
 
+static inline bool sdhci_has_requests(struct sdhci_host *host)
+{
+	return host->cmd || host->data_cmd;
+}
+
+static void sdhci_error_out_mrqs(struct sdhci_host *host, int err)
+{
+	if (host->data_cmd) {
+		host->data_cmd->error = err;
+		sdhci_finish_mrq(host, host->data_cmd->mrq);
+	}
+
+	if (host->cmd) {
+		host->cmd->error = err;
+		sdhci_finish_mrq(host, host->cmd->mrq);
+	}
+}
+
 static void sdhci_card_event(struct mmc_host *mmc)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
@@ -2096,12 +2216,12 @@ static void sdhci_card_event(struct mmc_host *mmc)
 	if (host->ops->card_event)
 		host->ops->card_event(host);
 
-	present = sdhci_get_cd(host->mmc);
+	present = mmc->ops->get_cd(mmc);
 
 	spin_lock_irqsave(&host->lock, flags);
 
-	/* Check host->mrq first in case we are runtime suspended */
-	if (host->mrq && !present) {
+	/* Check sdhci_has_requests() first in case we are runtime suspended */
+	if (sdhci_has_requests(host) && !present) {
 		pr_err("%s: Card removed during transfer!\n",
 			mmc_hostname(host->mmc));
 		pr_err("%s: Resetting controller.\n",
@@ -2110,8 +2230,7 @@ static void sdhci_card_event(struct mmc_host *mmc)
 		sdhci_do_reset(host, SDHCI_RESET_CMD);
 		sdhci_do_reset(host, SDHCI_RESET_DATA);
 
-		host->mrq->cmd->error = -ENOMEDIUM;
-		tasklet_schedule(&host->finish_tasklet);
+		sdhci_error_out_mrqs(host, -ENOMEDIUM);
 	}
 
 	spin_unlock_irqrestore(&host->lock, flags);
@@ -2140,28 +2259,28 @@ static const struct mmc_host_ops sdhci_ops = {
  *                                                                           *
 \*****************************************************************************/
 
-static void sdhci_tasklet_finish(unsigned long param)
+static bool sdhci_request_done(struct sdhci_host *host)
 {
-	struct sdhci_host *host;
 	unsigned long flags;
 	struct mmc_request *mrq;
-
-	host = (struct sdhci_host*)param;
+	int i;
 
 	spin_lock_irqsave(&host->lock, flags);
 
-        /*
-         * If this tasklet gets rescheduled while running, it will
-         * be run again afterwards but without any active request.
-         */
-	if (!host->mrq) {
-		spin_unlock_irqrestore(&host->lock, flags);
-		return;
+	for (i = 0; i < SDHCI_MAX_MRQS; i++) {
+		mrq = host->mrqs_done[i];
+		if (mrq) {
+			host->mrqs_done[i] = NULL;
+			break;
+		}
 	}
 
-	del_timer(&host->timer);
+	if (!mrq) {
+		spin_unlock_irqrestore(&host->lock, flags);
+		return true;
+	}
 
-	mrq = host->mrq;
+	sdhci_del_timer(host, mrq);
 
 	/*
 	 * Always unmap the data buffers if they were mapped by
@@ -2183,13 +2302,7 @@ static void sdhci_tasklet_finish(unsigned long param)
 	 * The controller needs a reset of internal state machines
 	 * upon error conditions.
 	 */
-	if (!(host->flags & SDHCI_DEVICE_DEAD) &&
-	    ((mrq->cmd && mrq->cmd->error) ||
-	     (mrq->sbc && mrq->sbc->error) ||
-	     (mrq->data && ((mrq->data->error && !mrq->data->stop) ||
-			    (mrq->data->stop && mrq->data->stop->error))) ||
-	     (host->quirks & SDHCI_QUIRK_RESET_AFTER_REQUEST))) {
-
+	if (sdhci_needs_reset(host, mrq)) {
 		/* Some controllers need this kick or reset won't work here */
 		if (host->quirks & SDHCI_QUIRK_CLOCK_BEFORE_RESET)
 			/* This is to force an update */
@@ -2197,20 +2310,31 @@ static void sdhci_tasklet_finish(unsigned long param)
 
 		/* Spec says we should do both at the same time, but Ricoh
 		   controllers do not like that. */
-		sdhci_do_reset(host, SDHCI_RESET_CMD);
-		sdhci_do_reset(host, SDHCI_RESET_DATA);
-	}
+		if (!host->cmd)
+			sdhci_do_reset(host, SDHCI_RESET_CMD);
+		if (!host->data_cmd)
+			sdhci_do_reset(host, SDHCI_RESET_DATA);
 
-	host->mrq = NULL;
-	host->cmd = NULL;
-	host->data = NULL;
+		host->pending_reset = false;
+	}
 
-	sdhci_led_deactivate(host);
+	if (!sdhci_has_requests(host))
+		sdhci_led_deactivate(host);
 
 	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	mmc_request_done(host->mmc, mrq);
+
+	return false;
+}
+
+static void sdhci_tasklet_finish(unsigned long param)
+{
+	struct sdhci_host *host = (struct sdhci_host *)param;
+
+	while (!sdhci_request_done(host))
+		;
 }
 
 static void sdhci_timeout_timer(unsigned long data)
@@ -2222,7 +2346,30 @@ static void sdhci_timeout_timer(unsigned long data)
 
 	spin_lock_irqsave(&host->lock, flags);
 
-	if (host->mrq) {
+	if (host->cmd && !sdhci_data_line_cmd(host->cmd)) {
+		pr_err("%s: Timeout waiting for hardware cmd interrupt.\n",
+		       mmc_hostname(host->mmc));
+		sdhci_dumpregs(host);
+
+		host->cmd->error = -ETIMEDOUT;
+		sdhci_finish_mrq(host, host->cmd->mrq);
+	}
+
+	mmiowb();
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+
+static void sdhci_timeout_data_timer(unsigned long data)
+{
+	struct sdhci_host *host;
+	unsigned long flags;
+
+	host = (struct sdhci_host *)data;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (host->data || host->data_cmd ||
+	    (host->cmd && sdhci_data_line_cmd(host->cmd))) {
 		pr_err("%s: Timeout waiting for hardware interrupt.\n",
 		       mmc_hostname(host->mmc));
 		sdhci_dumpregs(host);
@@ -2230,13 +2377,12 @@ static void sdhci_timeout_timer(unsigned long data)
 		if (host->data) {
 			host->data->error = -ETIMEDOUT;
 			sdhci_finish_data(host);
+		} else if (host->data_cmd) {
+			host->data_cmd->error = -ETIMEDOUT;
+			sdhci_finish_mrq(host, host->data_cmd->mrq);
 		} else {
-			if (host->cmd)
-				host->cmd->error = -ETIMEDOUT;
-			else
-				host->mrq->cmd->error = -ETIMEDOUT;
-
-			tasklet_schedule(&host->finish_tasklet);
+			host->cmd->error = -ETIMEDOUT;
+			sdhci_finish_mrq(host, host->cmd->mrq);
 		}
 	}
 
@@ -2252,9 +2398,14 @@ static void sdhci_timeout_timer(unsigned long data)
 
 static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *mask)
 {
-	BUG_ON(intmask == 0);
-
 	if (!host->cmd) {
+		/*
+		 * SDHCI recovers from errors by resetting the cmd and data
+		 * circuits.  Until that is done, there very well might be more
+		 * interrupts, so ignore them in that case.
+		 */
+		if (host->pending_reset)
+			return;
 		pr_err("%s: Got command interrupt 0x%08x even though no command operation was in progress.\n",
 		       mmc_hostname(host->mmc), (unsigned)intmask);
 		sdhci_dumpregs(host);
@@ -2285,37 +2436,14 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *mask)
 			return;
 		}
 
-		tasklet_schedule(&host->finish_tasklet);
+		sdhci_finish_mrq(host, host->cmd->mrq);
 		return;
 	}
 
-	/*
-	 * The host can send and interrupt when the busy state has
-	 * ended, allowing us to wait without wasting CPU cycles.
-	 * Unfortunately this is overloaded on the "data complete"
-	 * interrupt, so we need to take some care when handling
-	 * it.
-	 *
-	 * Note: The 1.0 specification is a bit ambiguous about this
-	 *       feature so there might be some problems with older
-	 *       controllers.
-	 */
-	if (host->cmd->flags & MMC_RSP_BUSY) {
-		if (host->cmd->data)
-			DBG("Cannot wait for busy signal when also doing a data transfer");
-		else if (!(host->quirks & SDHCI_QUIRK_NO_BUSY_IRQ)
-				&& !host->busy_handle) {
-			/* Mark that command complete before busy is ended */
-			host->busy_handle = 1;
-			return;
-		}
-
-		/* The controller does not support the end-of-busy IRQ,
-		 * fall through and take the SDHCI_INT_RESPONSE */
-	} else if ((host->quirks2 & SDHCI_QUIRK2_STOP_WITH_TC) &&
-		   host->cmd->opcode == MMC_STOP_TRANSMISSION && !host->data) {
+	if ((host->quirks2 & SDHCI_QUIRK2_STOP_WITH_TC) &&
+	    !(host->cmd->flags & MMC_RSP_BUSY) && !host->data &&
+	    host->cmd->opcode == MMC_STOP_TRANSMISSION)
 		*mask &= ~SDHCI_INT_DATA_END;
-	}
 
 	if (intmask & SDHCI_INT_RESPONSE)
 		sdhci_finish_command(host);
@@ -2357,7 +2485,6 @@ static void sdhci_adma_show_error(struct sdhci_host *host) { }
 static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 {
 	u32 command;
-	BUG_ON(intmask == 0);
 
 	/* CMD19 generates _only_ Buffer Read Ready interrupt */
 	if (intmask & SDHCI_INT_DATA_AVAIL) {
@@ -2371,15 +2498,20 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 	}
 
 	if (!host->data) {
+		struct mmc_command *data_cmd = host->data_cmd;
+
+		if (data_cmd)
+			host->data_cmd = NULL;
+
 		/*
 		 * The "data complete" interrupt is also used to
 		 * indicate that a busy state has ended. See comment
 		 * above in sdhci_cmd_irq().
 		 */
-		if (host->cmd && (host->cmd->flags & MMC_RSP_BUSY)) {
+		if (data_cmd && (data_cmd->flags & MMC_RSP_BUSY)) {
 			if (intmask & SDHCI_INT_DATA_TIMEOUT) {
-				host->cmd->error = -ETIMEDOUT;
-				tasklet_schedule(&host->finish_tasklet);
+				data_cmd->error = -ETIMEDOUT;
+				sdhci_finish_mrq(host, data_cmd->mrq);
 				return;
 			}
 			if (intmask & SDHCI_INT_DATA_END) {
@@ -2388,14 +2520,22 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 				 * before the command completed, so make
 				 * sure we do things in the proper order.
 				 */
-				if (host->busy_handle)
-					sdhci_finish_command(host);
-				else
-					host->busy_handle = 1;
+				if (host->cmd == data_cmd)
+					return;
+
+				sdhci_finish_mrq(host, data_cmd->mrq);
 				return;
 			}
 		}
 
+		/*
+		 * SDHCI recovers from errors by resetting the cmd and data
+		 * circuits. Until that is done, there very well might be more
+		 * interrupts, so ignore them in that case.
+		 */
+		if (host->pending_reset)
+			return;
+
 		pr_err("%s: Got data interrupt 0x%08x even though no data operation was in progress.\n",
 		       mmc_hostname(host->mmc), (unsigned)intmask);
 		sdhci_dumpregs(host);
@@ -2453,7 +2593,7 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 		}
 
 		if (intmask & SDHCI_INT_DATA_END) {
-			if (host->cmd) {
+			if (host->cmd == host->data_cmd) {
 				/*
 				 * Data managed to finish before the
 				 * command completed. Make sure we do
@@ -2537,6 +2677,9 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 			pr_err("%s: Card is consuming too much power!\n",
 				mmc_hostname(host->mmc));
 
+		if (intmask & SDHCI_INT_RETUNE)
+			mmc_retune_needed(host->mmc);
+
 		if (intmask & SDHCI_INT_CARD_INT) {
 			sdhci_enable_sdio_irq_nolock(host, false);
 			host->thread_isr |= SDHCI_INT_CARD_INT;
@@ -2546,7 +2689,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 		intmask &= ~(SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE |
 			     SDHCI_INT_CMD_MASK | SDHCI_INT_DATA_MASK |
 			     SDHCI_INT_ERROR | SDHCI_INT_BUS_POWER |
-			     SDHCI_INT_CARD_INT);
+			     SDHCI_INT_RETUNE | SDHCI_INT_CARD_INT);
 
 		if (intmask) {
 			unexpected |= intmask;
@@ -2582,8 +2725,10 @@ static irqreturn_t sdhci_thread_irq(int irq, void *dev_id)
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	if (isr & (SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE)) {
-		sdhci_card_event(host->mmc);
-		mmc_detect_change(host->mmc, msecs_to_jiffies(200));
+		struct mmc_host *mmc = host->mmc;
+
+		mmc->ops->card_event(mmc);
+		mmc_detect_change(mmc, msecs_to_jiffies(200));
 	}
 
 	if (isr & SDHCI_INT_CARD_INT) {
@@ -2605,18 +2750,31 @@ static irqreturn_t sdhci_thread_irq(int irq, void *dev_id)
 \*****************************************************************************/
 
 #ifdef CONFIG_PM
+/*
+ * To enable wakeup events, the corresponding events have to be enabled in
+ * the Interrupt Status Enable register too. See 'Table 1-6: Wakeup Signal
+ * Table' in the SD Host Controller Standard Specification.
+ * It is useless to restore SDHCI_INT_ENABLE state in
+ * sdhci_disable_irq_wakeups() since it will be set by
+ * sdhci_enable_card_detection() or sdhci_init().
+ */
 void sdhci_enable_irq_wakeups(struct sdhci_host *host)
 {
 	u8 val;
 	u8 mask = SDHCI_WAKE_ON_INSERT | SDHCI_WAKE_ON_REMOVE
 			| SDHCI_WAKE_ON_INT;
+	u32 irq_val = SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE |
+		      SDHCI_INT_CARD_INT;
 
 	val = sdhci_readb(host, SDHCI_WAKE_UP_CONTROL);
 	val |= mask ;
 	/* Avoid fake wake up */
-	if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION)
+	if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) {
 		val &= ~(SDHCI_WAKE_ON_INSERT | SDHCI_WAKE_ON_REMOVE);
+		irq_val &= ~(SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE);
+	}
 	sdhci_writeb(host, val, SDHCI_WAKE_UP_CONTROL);
+	sdhci_writel(host, irq_val, SDHCI_INT_ENABLE);
 }
 EXPORT_SYMBOL_GPL(sdhci_enable_irq_wakeups);
 
@@ -2636,7 +2794,8 @@ int sdhci_suspend_host(struct sdhci_host *host)
 	sdhci_disable_card_detection(host);
 
 	mmc_retune_timer_stop(host->mmc);
-	mmc_retune_needed(host->mmc);
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
 
 	if (!device_may_wakeup(mmc_dev(host->mmc))) {
 		host->ier = 0;
@@ -2654,6 +2813,7 @@ EXPORT_SYMBOL_GPL(sdhci_suspend_host);
 
 int sdhci_resume_host(struct sdhci_host *host)
 {
+	struct mmc_host *mmc = host->mmc;
 	int ret = 0;
 
 	if (host->flags & (SDHCI_USE_SDMA | SDHCI_USE_ADMA)) {
@@ -2667,7 +2827,7 @@ int sdhci_resume_host(struct sdhci_host *host)
 		sdhci_init(host, 0);
 		host->pwr = 0;
 		host->clock = 0;
-		sdhci_set_ios(host->mmc, &host->mmc->ios);
+		mmc->ops->set_ios(mmc, &mmc->ios);
 	} else {
 		sdhci_init(host, (host->mmc->pm_flags & MMC_PM_KEEP_POWER));
 		mmiowb();
@@ -2696,7 +2856,8 @@ int sdhci_runtime_suspend_host(struct sdhci_host *host)
 	unsigned long flags;
 
 	mmc_retune_timer_stop(host->mmc);
-	mmc_retune_needed(host->mmc);
+	if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+		mmc_retune_needed(host->mmc);
 
 	spin_lock_irqsave(&host->lock, flags);
 	host->ier &= SDHCI_INT_CARD_INT;
@@ -2716,6 +2877,7 @@ EXPORT_SYMBOL_GPL(sdhci_runtime_suspend_host);
 
 int sdhci_runtime_resume_host(struct sdhci_host *host)
 {
+	struct mmc_host *mmc = host->mmc;
 	unsigned long flags;
 	int host_flags = host->flags;
 
@@ -2729,8 +2891,8 @@ int sdhci_runtime_resume_host(struct sdhci_host *host)
 	/* Force clock and power re-program */
 	host->pwr = 0;
 	host->clock = 0;
-	sdhci_start_signal_voltage_switch(host->mmc, &host->mmc->ios);
-	sdhci_set_ios(host->mmc, &host->mmc->ios);
+	mmc->ops->start_signal_voltage_switch(mmc, &mmc->ios);
+	mmc->ops->set_ios(mmc, &mmc->ios);
 
 	if ((host_flags & SDHCI_PV_ENABLED) &&
 		!(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN)) {
@@ -2781,6 +2943,8 @@ struct sdhci_host *sdhci_alloc_host(struct device *dev,
 	host->mmc_host_ops = sdhci_ops;
 	mmc->ops = &host->mmc_host_ops;
 
+	host->flags = SDHCI_SIGNALING_330;
+
 	return host;
 }
 
@@ -2816,10 +2980,41 @@ static int sdhci_set_dma_mask(struct sdhci_host *host)
 	return ret;
 }
 
-int sdhci_add_host(struct sdhci_host *host)
+void __sdhci_read_caps(struct sdhci_host *host, u16 *ver, u32 *caps, u32 *caps1)
+{
+	u16 v;
+
+	if (host->read_caps)
+		return;
+
+	host->read_caps = true;
+
+	if (debug_quirks)
+		host->quirks = debug_quirks;
+
+	if (debug_quirks2)
+		host->quirks2 = debug_quirks2;
+
+	sdhci_do_reset(host, SDHCI_RESET_ALL);
+
+	v = ver ? *ver : sdhci_readw(host, SDHCI_HOST_VERSION);
+	host->version = (v & SDHCI_SPEC_VER_MASK) >> SDHCI_SPEC_VER_SHIFT;
+
+	if (host->quirks & SDHCI_QUIRK_MISSING_CAPS)
+		return;
+
+	host->caps = caps ? *caps : sdhci_readl(host, SDHCI_CAPABILITIES);
+
+	if (host->version < SDHCI_SPEC_300)
+		return;
+
+	host->caps1 = caps1 ? *caps1 : sdhci_readl(host, SDHCI_CAPABILITIES_1);
+}
+EXPORT_SYMBOL_GPL(__sdhci_read_caps);
+
+int sdhci_setup_host(struct sdhci_host *host)
 {
 	struct mmc_host *mmc;
-	u32 caps[2] = {0, 0};
 	u32 max_current_caps;
 	unsigned int ocr_avail;
 	unsigned int override_timeout_clk;
@@ -2832,34 +3027,28 @@ int sdhci_add_host(struct sdhci_host *host)
 
 	mmc = host->mmc;
 
-	if (debug_quirks)
-		host->quirks = debug_quirks;
-	if (debug_quirks2)
-		host->quirks2 = debug_quirks2;
+	/*
+	 * If there are external regulators, get them. Note this must be done
+	 * early before resetting the host and reading the capabilities so that
+	 * the host can take the appropriate action if regulators are not
+	 * available.
+	 */
+	ret = mmc_regulator_get_supply(mmc);
+	if (ret == -EPROBE_DEFER)
+		return ret;
 
-	override_timeout_clk = host->timeout_clk;
+	sdhci_read_caps(host);
 
-	sdhci_do_reset(host, SDHCI_RESET_ALL);
+	override_timeout_clk = host->timeout_clk;
 
-	host->version = sdhci_readw(host, SDHCI_HOST_VERSION);
-	host->version = (host->version & SDHCI_SPEC_VER_MASK)
-				>> SDHCI_SPEC_VER_SHIFT;
 	if (host->version > SDHCI_SPEC_300) {
 		pr_err("%s: Unknown controller version (%d). You may experience problems.\n",
 		       mmc_hostname(mmc), host->version);
 	}
 
-	caps[0] = (host->quirks & SDHCI_QUIRK_MISSING_CAPS) ? host->caps :
-		sdhci_readl(host, SDHCI_CAPABILITIES);
-
-	if (host->version >= SDHCI_SPEC_300)
-		caps[1] = (host->quirks & SDHCI_QUIRK_MISSING_CAPS) ?
-			host->caps1 :
-			sdhci_readl(host, SDHCI_CAPABILITIES_1);
-
 	if (host->quirks & SDHCI_QUIRK_FORCE_DMA)
 		host->flags |= SDHCI_USE_SDMA;
-	else if (!(caps[0] & SDHCI_CAN_DO_SDMA))
+	else if (!(host->caps & SDHCI_CAN_DO_SDMA))
 		DBG("Controller doesn't have SDMA capability\n");
 	else
 		host->flags |= SDHCI_USE_SDMA;
@@ -2871,7 +3060,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	}
 
 	if ((host->version >= SDHCI_SPEC_200) &&
-		(caps[0] & SDHCI_CAN_DO_ADMA2))
+		(host->caps & SDHCI_CAN_DO_ADMA2))
 		host->flags |= SDHCI_USE_ADMA;
 
 	if ((host->quirks & SDHCI_QUIRK_BROKEN_ADMA) &&
@@ -2887,7 +3076,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	 * SDHCI_QUIRK2_BROKEN_64_BIT_DMA must be left to the drivers to
 	 * implement.
 	 */
-	if (caps[0] & SDHCI_CAN_64BIT)
+	if (host->caps & SDHCI_CAN_64BIT)
 		host->flags |= SDHCI_USE_64_BIT_DMA;
 
 	if (host->flags & (SDHCI_USE_SDMA | SDHCI_USE_ADMA)) {
@@ -2963,10 +3152,10 @@ int sdhci_add_host(struct sdhci_host *host)
 	}
 
 	if (host->version >= SDHCI_SPEC_300)
-		host->max_clk = (caps[0] & SDHCI_CLOCK_V3_BASE_MASK)
+		host->max_clk = (host->caps & SDHCI_CLOCK_V3_BASE_MASK)
 			>> SDHCI_CLOCK_BASE_SHIFT;
 	else
-		host->max_clk = (caps[0] & SDHCI_CLOCK_BASE_MASK)
+		host->max_clk = (host->caps & SDHCI_CLOCK_BASE_MASK)
 			>> SDHCI_CLOCK_BASE_SHIFT;
 
 	host->max_clk *= 1000000;
@@ -2985,7 +3174,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	 * In case of Host Controller v3.00, find out whether clock
 	 * multiplier is supported.
 	 */
-	host->clk_mul = (caps[1] & SDHCI_CLOCK_MUL_MASK) >>
+	host->clk_mul = (host->caps1 & SDHCI_CLOCK_MUL_MASK) >>
 			SDHCI_CLOCK_MUL_SHIFT;
 
 	/*
@@ -3017,7 +3206,7 @@ int sdhci_add_host(struct sdhci_host *host)
 		mmc->f_max = max_clk;
 
 	if (!(host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK)) {
-		host->timeout_clk = (caps[0] & SDHCI_TIMEOUT_CLK_MASK) >>
+		host->timeout_clk = (host->caps & SDHCI_TIMEOUT_CLK_MASK) >>
 					SDHCI_TIMEOUT_CLK_SHIFT;
 		if (host->timeout_clk == 0) {
 			if (host->ops->get_timeout_clock) {
@@ -3031,7 +3220,7 @@ int sdhci_add_host(struct sdhci_host *host)
 			}
 		}
 
-		if (caps[0] & SDHCI_TIMEOUT_CLK_UNIT)
+		if (host->caps & SDHCI_TIMEOUT_CLK_UNIT)
 			host->timeout_clk *= 1000;
 
 		if (override_timeout_clk)
@@ -3072,27 +3261,22 @@ int sdhci_add_host(struct sdhci_host *host)
 	if (host->quirks2 & SDHCI_QUIRK2_HOST_NO_CMD23)
 		mmc->caps &= ~MMC_CAP_CMD23;
 
-	if (caps[0] & SDHCI_CAN_DO_HISPD)
+	if (host->caps & SDHCI_CAN_DO_HISPD)
 		mmc->caps |= MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED;
 
 	if ((host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) &&
-	    !(mmc->caps & MMC_CAP_NONREMOVABLE) &&
+	    mmc_card_is_removable(mmc) &&
 	    mmc_gpio_get_cd(host->mmc) < 0)
 		mmc->caps |= MMC_CAP_NEEDS_POLL;
 
-	/* If there are external regulators, get them */
-	ret = mmc_regulator_get_supply(mmc);
-	if (ret == -EPROBE_DEFER)
-		goto undma;
-
 	/* If vqmmc regulator and no 1.8V signalling, then there's no UHS */
 	if (!IS_ERR(mmc->supply.vqmmc)) {
 		ret = regulator_enable(mmc->supply.vqmmc);
 		if (!regulator_is_supported_voltage(mmc->supply.vqmmc, 1700000,
 						    1950000))
-			caps[1] &= ~(SDHCI_SUPPORT_SDR104 |
-					SDHCI_SUPPORT_SDR50 |
-					SDHCI_SUPPORT_DDR50);
+			host->caps1 &= ~(SDHCI_SUPPORT_SDR104 |
+					 SDHCI_SUPPORT_SDR50 |
+					 SDHCI_SUPPORT_DDR50);
 		if (ret) {
 			pr_warn("%s: Failed to enable vqmmc regulator: %d\n",
 				mmc_hostname(mmc), ret);
@@ -3100,28 +3284,30 @@ int sdhci_add_host(struct sdhci_host *host)
 		}
 	}
 
-	if (host->quirks2 & SDHCI_QUIRK2_NO_1_8_V)
-		caps[1] &= ~(SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_SDR50 |
-		       SDHCI_SUPPORT_DDR50);
+	if (host->quirks2 & SDHCI_QUIRK2_NO_1_8_V) {
+		host->caps1 &= ~(SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_SDR50 |
+				 SDHCI_SUPPORT_DDR50);
+	}
 
 	/* Any UHS-I mode in caps implies SDR12 and SDR25 support. */
-	if (caps[1] & (SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_SDR50 |
-		       SDHCI_SUPPORT_DDR50))
+	if (host->caps1 & (SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_SDR50 |
+			   SDHCI_SUPPORT_DDR50))
 		mmc->caps |= MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25;
 
 	/* SDR104 supports also implies SDR50 support */
-	if (caps[1] & SDHCI_SUPPORT_SDR104) {
+	if (host->caps1 & SDHCI_SUPPORT_SDR104) {
 		mmc->caps |= MMC_CAP_UHS_SDR104 | MMC_CAP_UHS_SDR50;
 		/* SD3.0: SDR104 is supported so (for eMMC) the caps2
 		 * field can be promoted to support HS200.
 		 */
 		if (!(host->quirks2 & SDHCI_QUIRK2_BROKEN_HS200))
 			mmc->caps2 |= MMC_CAP2_HS200;
-	} else if (caps[1] & SDHCI_SUPPORT_SDR50)
+	} else if (host->caps1 & SDHCI_SUPPORT_SDR50) {
 		mmc->caps |= MMC_CAP_UHS_SDR50;
+	}
 
 	if (host->quirks2 & SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 &&
-	    (caps[1] & SDHCI_SUPPORT_HS400))
+	    (host->caps1 & SDHCI_SUPPORT_HS400))
 		mmc->caps2 |= MMC_CAP2_HS400;
 
 	if ((mmc->caps2 & MMC_CAP2_HSX00_1_2V) &&
@@ -3130,25 +3316,25 @@ int sdhci_add_host(struct sdhci_host *host)
 					     1300000)))
 		mmc->caps2 &= ~MMC_CAP2_HSX00_1_2V;
 
-	if ((caps[1] & SDHCI_SUPPORT_DDR50) &&
-		!(host->quirks2 & SDHCI_QUIRK2_BROKEN_DDR50))
+	if ((host->caps1 & SDHCI_SUPPORT_DDR50) &&
+	    !(host->quirks2 & SDHCI_QUIRK2_BROKEN_DDR50))
 		mmc->caps |= MMC_CAP_UHS_DDR50;
 
 	/* Does the host need tuning for SDR50? */
-	if (caps[1] & SDHCI_USE_SDR50_TUNING)
+	if (host->caps1 & SDHCI_USE_SDR50_TUNING)
 		host->flags |= SDHCI_SDR50_NEEDS_TUNING;
 
 	/* Driver Type(s) (A, C, D) supported by the host */
-	if (caps[1] & SDHCI_DRIVER_TYPE_A)
+	if (host->caps1 & SDHCI_DRIVER_TYPE_A)
 		mmc->caps |= MMC_CAP_DRIVER_TYPE_A;
-	if (caps[1] & SDHCI_DRIVER_TYPE_C)
+	if (host->caps1 & SDHCI_DRIVER_TYPE_C)
 		mmc->caps |= MMC_CAP_DRIVER_TYPE_C;
-	if (caps[1] & SDHCI_DRIVER_TYPE_D)
+	if (host->caps1 & SDHCI_DRIVER_TYPE_D)
 		mmc->caps |= MMC_CAP_DRIVER_TYPE_D;
 
 	/* Initial value for re-tuning timer count */
-	host->tuning_count = (caps[1] & SDHCI_RETUNING_TIMER_COUNT_MASK) >>
-			      SDHCI_RETUNING_TIMER_COUNT_SHIFT;
+	host->tuning_count = (host->caps1 & SDHCI_RETUNING_TIMER_COUNT_MASK) >>
+			     SDHCI_RETUNING_TIMER_COUNT_SHIFT;
 
 	/*
 	 * In case Re-tuning Timer is not disabled, the actual value of
@@ -3158,7 +3344,7 @@ int sdhci_add_host(struct sdhci_host *host)
 		host->tuning_count = 1 << (host->tuning_count - 1);
 
 	/* Re-tuning mode supported by the Host Controller */
-	host->tuning_mode = (caps[1] & SDHCI_RETUNING_MODE_MASK) >>
+	host->tuning_mode = (host->caps1 & SDHCI_RETUNING_MODE_MASK) >>
 			     SDHCI_RETUNING_MODE_SHIFT;
 
 	ocr_avail = 0;
@@ -3187,7 +3373,7 @@ int sdhci_add_host(struct sdhci_host *host)
 		}
 	}
 
-	if (caps[0] & SDHCI_CAN_VDD_330) {
+	if (host->caps & SDHCI_CAN_VDD_330) {
 		ocr_avail |= MMC_VDD_32_33 | MMC_VDD_33_34;
 
 		mmc->max_current_330 = ((max_current_caps &
@@ -3195,7 +3381,7 @@ int sdhci_add_host(struct sdhci_host *host)
 				   SDHCI_MAX_CURRENT_330_SHIFT) *
 				   SDHCI_MAX_CURRENT_MULTIPLIER;
 	}
-	if (caps[0] & SDHCI_CAN_VDD_300) {
+	if (host->caps & SDHCI_CAN_VDD_300) {
 		ocr_avail |= MMC_VDD_29_30 | MMC_VDD_30_31;
 
 		mmc->max_current_300 = ((max_current_caps &
@@ -3203,7 +3389,7 @@ int sdhci_add_host(struct sdhci_host *host)
 				   SDHCI_MAX_CURRENT_300_SHIFT) *
 				   SDHCI_MAX_CURRENT_MULTIPLIER;
 	}
-	if (caps[0] & SDHCI_CAN_VDD_180) {
+	if (host->caps & SDHCI_CAN_VDD_180) {
 		ocr_avail |= MMC_VDD_165_195;
 
 		mmc->max_current_180 = ((max_current_caps &
@@ -3240,6 +3426,15 @@ int sdhci_add_host(struct sdhci_host *host)
 		goto unreg;
 	}
 
+	if ((mmc->caps & (MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 |
+			  MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 |
+			  MMC_CAP_UHS_DDR50 | MMC_CAP_1_8V_DDR)) ||
+	    (mmc->caps2 & (MMC_CAP2_HS200_1_8V_SDR | MMC_CAP2_HS400_1_8V)))
+		host->flags |= SDHCI_SIGNALING_180;
+
+	if (mmc->caps2 & MMC_CAP2_HSX00_1_2V)
+		host->flags |= SDHCI_SIGNALING_120;
+
 	spin_lock_init(&host->lock);
 
 	/*
@@ -3281,7 +3476,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	if (host->quirks & SDHCI_QUIRK_FORCE_BLK_SZ_2048) {
 		mmc->max_blk_size = 2;
 	} else {
-		mmc->max_blk_size = (caps[0] & SDHCI_MAX_BLOCK_MASK) >>
+		mmc->max_blk_size = (host->caps & SDHCI_MAX_BLOCK_MASK) >>
 				SDHCI_MAX_BLOCK_SHIFT;
 		if (mmc->max_blk_size >= 3) {
 			pr_warn("%s: Invalid maximum block size, assuming 512 bytes\n",
@@ -3297,6 +3492,28 @@ int sdhci_add_host(struct sdhci_host *host)
 	 */
 	mmc->max_blk_count = (host->quirks & SDHCI_QUIRK_NO_MULTIBLOCK) ? 1 : 65535;
 
+	return 0;
+
+unreg:
+	if (!IS_ERR(mmc->supply.vqmmc))
+		regulator_disable(mmc->supply.vqmmc);
+undma:
+	if (host->align_buffer)
+		dma_free_coherent(mmc_dev(mmc), host->align_buffer_sz +
+				  host->adma_table_sz, host->align_buffer,
+				  host->align_addr);
+	host->adma_table = NULL;
+	host->align_buffer = NULL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sdhci_setup_host);
+
+int __sdhci_add_host(struct sdhci_host *host)
+{
+	struct mmc_host *mmc = host->mmc;
+	int ret;
+
 	/*
 	 * Init tasklets.
 	 */
@@ -3304,6 +3521,8 @@ int sdhci_add_host(struct sdhci_host *host)
 		sdhci_tasklet_finish, (unsigned long)host);
 
 	setup_timer(&host->timer, sdhci_timeout_timer, (unsigned long)host);
+	setup_timer(&host->data_timer, sdhci_timeout_data_timer,
+		    (unsigned long)host);
 
 	init_waitqueue_head(&host->buf_ready_int);
 
@@ -3353,10 +3572,10 @@ unirq:
 	free_irq(host->irq, host);
 untasklet:
 	tasklet_kill(&host->finish_tasklet);
-unreg:
+
 	if (!IS_ERR(mmc->supply.vqmmc))
 		regulator_disable(mmc->supply.vqmmc);
-undma:
+
 	if (host->align_buffer)
 		dma_free_coherent(mmc_dev(mmc), host->align_buffer_sz +
 				  host->adma_table_sz, host->align_buffer,
@@ -3366,7 +3585,18 @@ undma:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(__sdhci_add_host);
+
+int sdhci_add_host(struct sdhci_host *host)
+{
+	int ret;
 
+	ret = sdhci_setup_host(host);
+	if (ret)
+		return ret;
+
+	return __sdhci_add_host(host);
+}
 EXPORT_SYMBOL_GPL(sdhci_add_host);
 
 void sdhci_remove_host(struct sdhci_host *host, int dead)
@@ -3379,12 +3609,10 @@ void sdhci_remove_host(struct sdhci_host *host, int dead)
 
 		host->flags |= SDHCI_DEVICE_DEAD;
 
-		if (host->mrq) {
+		if (sdhci_has_requests(host)) {
 			pr_err("%s: Controller removed during "
 				" transfer!\n", mmc_hostname(mmc));
-
-			host->mrq->cmd->error = -ENOMEDIUM;
-			tasklet_schedule(&host->finish_tasklet);
+			sdhci_error_out_mrqs(host, -ENOMEDIUM);
 		}
 
 		spin_unlock_irqrestore(&host->lock, flags);
@@ -3404,6 +3632,7 @@ void sdhci_remove_host(struct sdhci_host *host, int dead)
 	free_irq(host->irq, host);
 
 	del_timer_sync(&host->timer);
+	del_timer_sync(&host->data_timer);
 
 	tasklet_kill(&host->finish_tasklet);
 
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 609f87ca536b..0411c9f36461 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -128,6 +128,7 @@
 #define  SDHCI_INT_CARD_INSERT	0x00000040
 #define  SDHCI_INT_CARD_REMOVE	0x00000080
 #define  SDHCI_INT_CARD_INT	0x00000100
+#define  SDHCI_INT_RETUNE	0x00001000
 #define  SDHCI_INT_ERROR	0x00008000
 #define  SDHCI_INT_TIMEOUT	0x00010000
 #define  SDHCI_INT_CRC		0x00020000
@@ -186,6 +187,7 @@
 #define  SDHCI_CAN_DO_ADMA1	0x00100000
 #define  SDHCI_CAN_DO_HISPD	0x00200000
 #define  SDHCI_CAN_DO_SDMA	0x00400000
+#define  SDHCI_CAN_DO_SUSPEND	0x00800000
 #define  SDHCI_CAN_VDD_330	0x01000000
 #define  SDHCI_CAN_VDD_300	0x02000000
 #define  SDHCI_CAN_VDD_180	0x04000000
@@ -314,6 +316,9 @@ struct sdhci_adma2_64_desc {
  */
 #define SDHCI_MAX_SEGS		128
 
+/* Allow for a a command request and a data request at the same time */
+#define SDHCI_MAX_MRQS		2
+
 enum sdhci_cookie {
 	COOKIE_UNMAPPED,
 	COOKIE_PRE_MAPPED,	/* mapped by sdhci_pre_req() */
@@ -447,6 +452,9 @@ struct sdhci_host {
 #define SDHCI_SDIO_IRQ_ENABLED	(1<<9)	/* SDIO irq enabled */
 #define SDHCI_USE_64_BIT_DMA	(1<<12)	/* Use 64-bit DMA */
 #define SDHCI_HS400_TUNING	(1<<13)	/* Tuning for HS400 */
+#define SDHCI_SIGNALING_330	(1<<14)	/* Host is capable of 3.3V signaling */
+#define SDHCI_SIGNALING_180	(1<<15)	/* Host is capable of 1.8V signaling */
+#define SDHCI_SIGNALING_120	(1<<16)	/* Host is capable of 1.2V signaling */
 
 	unsigned int version;	/* SDHCI spec. version */
 
@@ -460,12 +468,13 @@ struct sdhci_host {
 	bool runtime_suspended;	/* Host is runtime suspended */
 	bool bus_on;		/* Bus power prevents runtime suspend */
 	bool preset_enabled;	/* Preset is enabled */
+	bool pending_reset;	/* Cmd/data reset is pending */
 
-	struct mmc_request *mrq;	/* Current request */
+	struct mmc_request *mrqs_done[SDHCI_MAX_MRQS];	/* Requests done */
 	struct mmc_command *cmd;	/* Current command */
+	struct mmc_command *data_cmd;	/* Current data command */
 	struct mmc_data *data;	/* Current data request */
 	unsigned int data_early:1;	/* Data finished before cmd */
-	unsigned int busy_handle:1;	/* Handling the order of Busy-end */
 
 	struct sg_mapping_iter sg_miter;	/* SG state for PIO */
 	unsigned int blocks;	/* remaining PIO blocks */
@@ -486,9 +495,11 @@ struct sdhci_host {
 	struct tasklet_struct finish_tasklet;	/* Tasklet structures */
 
 	struct timer_list timer;	/* Timer for timeouts */
+	struct timer_list data_timer;	/* Timer for data timeouts */
 
-	u32 caps;		/* Alternative CAPABILITY_0 */
-	u32 caps1;		/* Alternative CAPABILITY_1 */
+	u32 caps;		/* CAPABILITY_0 */
+	u32 caps1;		/* CAPABILITY_1 */
+	bool read_caps;		/* Capability flags have been read */
 
 	unsigned int            ocr_avail_sdio;	/* OCR bit masks */
 	unsigned int            ocr_avail_sd;
@@ -508,6 +519,8 @@ struct sdhci_host {
 	unsigned int		tuning_count;	/* Timer count for re-tuning */
 	unsigned int		tuning_mode;	/* Re-tuning mode supported by host */
 #define SDHCI_TUNING_MODE_1	0
+#define SDHCI_TUNING_MODE_2	1
+#define SDHCI_TUNING_MODE_3	2
 
 	unsigned long private[0] ____cacheline_aligned;
 };
@@ -645,11 +658,20 @@ static inline void *sdhci_priv(struct sdhci_host *host)
 }
 
 extern void sdhci_card_detect(struct sdhci_host *host);
+extern void __sdhci_read_caps(struct sdhci_host *host, u16 *ver, u32 *caps,
+			      u32 *caps1);
+extern int sdhci_setup_host(struct sdhci_host *host);
+extern int __sdhci_add_host(struct sdhci_host *host);
 extern int sdhci_add_host(struct sdhci_host *host);
 extern void sdhci_remove_host(struct sdhci_host *host, int dead);
 extern void sdhci_send_command(struct sdhci_host *host,
 				struct mmc_command *cmd);
 
+static inline void sdhci_read_caps(struct sdhci_host *host)
+{
+	__sdhci_read_caps(host, NULL, NULL, NULL);
+}
+
 static inline bool sdhci_sdio_irq_enabled(struct sdhci_host *host)
 {
 	return !!(host->flags & SDHCI_SDIO_IRQ_ENABLED);
diff --git a/drivers/mmc/host/sdhci_f_sdh30.c b/drivers/mmc/host/sdhci_f_sdh30.c
index 983b8b32ef96..111b66f5439b 100644
--- a/drivers/mmc/host/sdhci_f_sdh30.c
+++ b/drivers/mmc/host/sdhci_f_sdh30.c
@@ -222,7 +222,7 @@ static struct platform_driver sdhci_f_sdh30_driver = {
 	.driver = {
 		.name = "f_sdh30",
 		.of_match_table = f_sdh30_dt_ids,
-		.pm	= SDHCI_PLTFM_PMOPS,
+		.pm	= &sdhci_pltfm_pmops,
 	},
 	.probe	= sdhci_f_sdh30_probe,
 	.remove	= sdhci_f_sdh30_remove,
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index dd64b8663984..900778421be6 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -574,7 +574,7 @@ static int sh_mmcif_error_manage(struct sh_mmcif_host *host)
 	if (state1 & STS1_CMDSEQ) {
 		sh_mmcif_bitset(host, MMCIF_CE_CMD_CTRL, CMD_CTRL_BREAK);
 		sh_mmcif_bitset(host, MMCIF_CE_CMD_CTRL, ~CMD_CTRL_BREAK);
-		for (timeout = 10000000; timeout; timeout--) {
+		for (timeout = 10000; timeout; timeout--) {
 			if (!(sh_mmcif_readl(host->addr, MMCIF_CE_HOST_STS1)
 			      & STS1_CMDSEQ))
 				break;
@@ -819,10 +819,12 @@ static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 		tmp |= CMD_SET_RTYP_NO;
 		break;
 	case MMC_RSP_R1:
-	case MMC_RSP_R1B:
 	case MMC_RSP_R3:
 		tmp |= CMD_SET_RTYP_6B;
 		break;
+	case MMC_RSP_R1B:
+		tmp |= CMD_SET_RBSY | CMD_SET_RTYP_6B;
+		break;
 	case MMC_RSP_R2:
 		tmp |= CMD_SET_RTYP_17B;
 		break;
@@ -830,17 +832,7 @@ static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 		dev_err(dev, "Unsupported response type.\n");
 		break;
 	}
-	switch (opc) {
-	/* RBSY */
-	case MMC_SLEEP_AWAKE:
-	case MMC_SWITCH:
-	case MMC_STOP_TRANSMISSION:
-	case MMC_SET_WRITE_PROT:
-	case MMC_CLR_WRITE_PROT:
-	case MMC_ERASE:
-		tmp |= CMD_SET_RBSY;
-		break;
-	}
+
 	/* WDAT / DATW */
 	if (data) {
 		tmp |= CMD_SET_WDAT;
@@ -925,23 +917,13 @@ static void sh_mmcif_start_cmd(struct sh_mmcif_host *host,
 {
 	struct mmc_command *cmd = mrq->cmd;
 	u32 opc = cmd->opcode;
-	u32 mask;
+	u32 mask = 0;
 	unsigned long flags;
 
-	switch (opc) {
-	/* response busy check */
-	case MMC_SLEEP_AWAKE:
-	case MMC_SWITCH:
-	case MMC_STOP_TRANSMISSION:
-	case MMC_SET_WRITE_PROT:
-	case MMC_CLR_WRITE_PROT:
-	case MMC_ERASE:
+	if (cmd->flags & MMC_RSP_BUSY)
 		mask = MASK_START_CMD | MASK_MRBSYE;
-		break;
-	default:
+	else
 		mask = MASK_START_CMD | MASK_MCRSPE;
-		break;
-	}
 
 	if (host->ccs_enable)
 		mask |= MASK_MCCSTO;
@@ -1009,22 +991,6 @@ static void sh_mmcif_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	host->state = STATE_REQUEST;
 	spin_unlock_irqrestore(&host->lock, flags);
 
-	switch (mrq->cmd->opcode) {
-	/* MMCIF does not support SD/SDIO command */
-	case MMC_SLEEP_AWAKE: /* = SD_IO_SEND_OP_COND (5) */
-	case MMC_SEND_EXT_CSD: /* = SD_SEND_IF_COND (8) */
-		if ((mrq->cmd->flags & MMC_CMD_MASK) != MMC_CMD_BCR)
-			break;
-	case MMC_APP_CMD:
-	case SD_IO_RW_DIRECT:
-		host->state = STATE_IDLE;
-		mrq->cmd->error = -ETIMEDOUT;
-		mmc_request_done(mmc, mrq);
-		return;
-	default:
-		break;
-	}
-
 	host->mrq = mrq;
 
 	sh_mmcif_start_cmd(host, mrq);
@@ -1488,6 +1454,9 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	sh_mmcif_init_ocr(host);
 
 	mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_WAIT_WHILE_BUSY;
+	mmc->caps2 |= MMC_CAP2_NO_SD | MMC_CAP2_NO_SDIO;
+	mmc->max_busy_timeout = 10000;
+
 	if (pd && pd->caps)
 		mmc->caps |= pd->caps;
 	mmc->max_segs = 32;
diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index f750f9494410..c3b651bf89cb 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -39,6 +39,12 @@
 
 #define EXT_ACC           0xe4
 
+#define SDHI_VER_GEN2_SDR50	0x490c
+/* very old datasheets said 0x490c for SDR104, too. They are wrong! */
+#define SDHI_VER_GEN2_SDR104	0xcb0d
+#define SDHI_VER_GEN3_SD	0xcc10
+#define SDHI_VER_GEN3_SDMMC	0xcd10
+
 #define host_to_priv(host) container_of((host)->pdata, struct sh_mobile_sdhi, mmc_data)
 
 struct sh_mobile_sdhi_of_data {
@@ -109,14 +115,14 @@ static void sh_mobile_sdhi_sdbuf_width(struct tmio_mmc_host *host, int width)
 	 *	sh_mobile_sdhi_of_data :: dma_buswidth
 	 */
 	switch (sd_ctrl_read16(host, CTL_VERSION)) {
-	case 0x490C:
+	case SDHI_VER_GEN2_SDR50:
 		val = (width == 32) ? 0x0001 : 0x0000;
 		break;
-	case 0xCB0D:
+	case SDHI_VER_GEN2_SDR104:
 		val = (width == 32) ? 0x0000 : 0x0001;
 		break;
-	case 0xCC10: /* Gen3, SD only */
-	case 0xCD10: /* Gen3, SD + MMC */
+	case SDHI_VER_GEN3_SD:
+	case SDHI_VER_GEN3_SDMMC:
 		if (width == 64)
 			val = 0x0000;
 		else if (width == 32)
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 1aac2ad8edf2..7f63ec05bdf4 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -259,7 +259,7 @@ static inline void sd_ctrl_write16_rep(struct tmio_mmc_host *host, int addr,
 
 static inline void sd_ctrl_write32_as_16_and_16(struct tmio_mmc_host *host, int addr, u32 val)
 {
-	writew(val, host->ctl + (addr << host->bus_shift));
+	writew(val & 0xffff, host->ctl + (addr << host->bus_shift));
 	writew(val >> 16, host->ctl + ((addr + 2) << host->bus_shift));
 }
 
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index f44e2ab7aea2..92467efc4e2c 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -1086,7 +1086,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 
 	_host->native_hotplug = !(pdata->flags & TMIO_MMC_USE_GPIO_CD ||
 				  mmc->caps & MMC_CAP_NEEDS_POLL ||
-				  mmc->caps & MMC_CAP_NONREMOVABLE ||
+				  !mmc_card_is_removable(mmc) ||
 				  mmc->slot.cd_irq >= 0);
 
 	if (tmio_mmc_clk_enable(_host) < 0) {
diff --git a/drivers/mtd/chips/cfi_cmdset_0020.c b/drivers/mtd/chips/cfi_cmdset_0020.c
index 9a1a6ffd16b8..94d3eb42c4d5 100644
--- a/drivers/mtd/chips/cfi_cmdset_0020.c
+++ b/drivers/mtd/chips/cfi_cmdset_0020.c
@@ -416,7 +416,7 @@ static int cfi_staa_read (struct mtd_info *mtd, loff_t from, size_t len, size_t
 	return ret;
 }
 
-static inline int do_write_buffer(struct map_info *map, struct flchip *chip,
+static int do_write_buffer(struct map_info *map, struct flchip *chip,
 				  unsigned long adr, const u_char *buf, int len)
 {
 	struct cfi_private *cfi = map->fldrv_priv;
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 64a248556d29..58329d2dacd1 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -113,12 +113,12 @@ config MTD_SST25L
 	  if you want to specify device partitioning.
 
 config MTD_BCM47XXSFLASH
-	tristate "R/O support for serial flash on BCMA bus"
+	tristate "Support for serial flash on BCMA bus"
 	depends on BCMA_SFLASH && (MIPS || ARM)
 	help
 	  BCMA bus can have various flash memories attached, they are
 	  registered by bcma as platform devices. This enables driver for
-	  serial flash memories (only read-only mode is implemented).
+	  serial flash memories.
 
 config MTD_SLRAM
 	tristate "Uncached system RAM"
@@ -171,18 +171,6 @@ config MTDRAM_ERASE_SIZE
 	  as a module, it is also possible to specify this as a parameter when
 	  loading the module.
 
-#If not a module (I don't want to test it as a module)
-config MTDRAM_ABS_POS
-	hex "SRAM Hexadecimal Absolute position or 0"
-	depends on MTD_MTDRAM=y
-	default "0"
-	help
-	  If you have system RAM accessible by the CPU but not used by Linux
-	  in normal operation, you can give the physical address at which the
-	  available RAM starts, and the MTDRAM driver will use it instead of
-	  allocating space from Linux's available memory. Otherwise, leave
-	  this set to zero. Most people will want to leave this as zero.
-
 config MTD_BLOCK2MTD
 	tristate "MTD using block device"
 	depends on BLOCK
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 9d6854467651..9cf7fcd28034 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -73,14 +73,15 @@ static int m25p80_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return spi_write(spi, flash->command, len + 1);
 }
 
-static void m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
-			size_t *retlen, const u_char *buf)
+static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
+			    const u_char *buf)
 {
 	struct m25p *flash = nor->priv;
 	struct spi_device *spi = flash->spi;
 	struct spi_transfer t[2] = {};
 	struct spi_message m;
 	int cmd_sz = m25p_cmdsz(nor);
+	ssize_t ret;
 
 	spi_message_init(&m);
 
@@ -98,9 +99,14 @@ static void m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	t[1].len = len;
 	spi_message_add_tail(&t[1], &m);
 
-	spi_sync(spi, &m);
+	ret = spi_sync(spi, &m);
+	if (ret)
+		return ret;
 
-	*retlen += m.actual_length - cmd_sz;
+	ret = m.actual_length - cmd_sz;
+	if (ret < 0)
+		return -EIO;
+	return ret;
 }
 
 static inline unsigned int m25p80_rx_nbits(struct spi_nor *nor)
@@ -119,21 +125,21 @@ static inline unsigned int m25p80_rx_nbits(struct spi_nor *nor)
  * Read an address range from the nor chip.  The address range
  * may be any size provided it is within the physical boundaries.
  */
-static int m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
-			size_t *retlen, u_char *buf)
+static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
+			   u_char *buf)
 {
 	struct m25p *flash = nor->priv;
 	struct spi_device *spi = flash->spi;
 	struct spi_transfer t[2];
 	struct spi_message m;
 	unsigned int dummy = nor->read_dummy;
+	ssize_t ret;
 
 	/* convert the dummy cycles to the number of bytes */
 	dummy /= 8;
 
 	if (spi_flash_read_supported(spi)) {
 		struct spi_flash_read_message msg;
-		int ret;
 
 		memset(&msg, 0, sizeof(msg));
 
@@ -149,8 +155,9 @@ static int m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
 		msg.data_nbits = m25p80_rx_nbits(nor);
 
 		ret = spi_flash_read(spi, &msg);
-		*retlen = msg.retlen;
-		return ret;
+		if (ret < 0)
+			return ret;
+		return msg.retlen;
 	}
 
 	spi_message_init(&m);
@@ -165,13 +172,17 @@ static int m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
 
 	t[1].rx_buf = buf;
 	t[1].rx_nbits = m25p80_rx_nbits(nor);
-	t[1].len = len;
+	t[1].len = min(len, spi_max_transfer_size(spi));
 	spi_message_add_tail(&t[1], &m);
 
-	spi_sync(spi, &m);
+	ret = spi_sync(spi, &m);
+	if (ret)
+		return ret;
 
-	*retlen = m.actual_length - m25p_cmdsz(nor) - dummy;
-	return 0;
+	ret = m.actual_length - m25p_cmdsz(nor) - dummy;
+	if (ret < 0)
+		return -EIO;
+	return ret;
 }
 
 /*
diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c
index d5b870b3fd4e..f5396f26ddb4 100644
--- a/drivers/mtd/devices/powernv_flash.c
+++ b/drivers/mtd/devices/powernv_flash.c
@@ -95,7 +95,7 @@ static int powernv_flash_async_op(struct mtd_info *mtd, enum flash_op op,
 		return -EIO;
 	}
 
-	rc = be64_to_cpu(msg.params[1]);
+	rc = opal_get_async_rc(msg);
 	if (rc == OPAL_SUCCESS) {
 		rc = 0;
 		if (retlen)
diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c
index 22f3858c0364..3fad35942895 100644
--- a/drivers/mtd/maps/physmap_of.c
+++ b/drivers/mtd/maps/physmap_of.c
@@ -186,7 +186,7 @@ static int of_flash_probe(struct platform_device *dev)
 	 * consists internally of 2 non-identical NOR chips on one die.
 	 */
 	p = of_get_property(dp, "reg", &count);
-	if (count % reg_tuple_size != 0) {
+	if (!p || count % reg_tuple_size != 0) {
 		dev_err(&dev->dev, "Malformed reg property on %s\n",
 				dev->dev.of_node->full_name);
 		err = -EINVAL;
diff --git a/drivers/mtd/maps/pmcmsp-flash.c b/drivers/mtd/maps/pmcmsp-flash.c
index 744ca5cacc9b..f9fa3fad728e 100644
--- a/drivers/mtd/maps/pmcmsp-flash.c
+++ b/drivers/mtd/maps/pmcmsp-flash.c
@@ -75,15 +75,15 @@ static int __init init_msp_flash(void)
 
 	printk(KERN_NOTICE "Found %d PMC flash devices\n", fcnt);
 
-	msp_flash = kmalloc(fcnt * sizeof(struct map_info *), GFP_KERNEL);
+	msp_flash = kcalloc(fcnt, sizeof(*msp_flash), GFP_KERNEL);
 	if (!msp_flash)
 		return -ENOMEM;
 
-	msp_parts = kmalloc(fcnt * sizeof(struct mtd_partition *), GFP_KERNEL);
+	msp_parts = kcalloc(fcnt, sizeof(*msp_parts), GFP_KERNEL);
 	if (!msp_parts)
 		goto free_msp_flash;
 
-	msp_maps = kcalloc(fcnt, sizeof(struct mtd_info), GFP_KERNEL);
+	msp_maps = kcalloc(fcnt, sizeof(*msp_maps), GFP_KERNEL);
 	if (!msp_maps)
 		goto free_msp_parts;
 
diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c
index 142fc3d79463..784c6e1a0391 100644
--- a/drivers/mtd/maps/sa1100-flash.c
+++ b/drivers/mtd/maps/sa1100-flash.c
@@ -230,8 +230,10 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev,
 
 		info->mtd = mtd_concat_create(cdev, info->num_subdev,
 					      plat->name);
-		if (info->mtd == NULL)
+		if (info->mtd == NULL) {
 			ret = -ENXIO;
+			goto err;
+		}
 	}
 	info->mtd->dev.parent = &pdev->dev;
 
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index f05e0e9eb2f7..21ff58099f3b 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -438,7 +438,7 @@ config MTD_NAND_FSL_ELBC
 
 config MTD_NAND_FSL_IFC
 	tristate "NAND support for Freescale IFC controller"
-	depends on MTD_NAND && FSL_SOC
+	depends on MTD_NAND && (FSL_SOC || ARCH_LAYERSCAPE)
 	select FSL_IFC
 	select MEMORY
 	help
@@ -539,7 +539,6 @@ config MTD_NAND_FSMC
 config MTD_NAND_XWAY
 	tristate "Support for NAND on Lantiq XWAY SoC"
 	depends on LANTIQ && SOC_TYPE_XWAY
-	select MTD_NAND_PLATFORM
 	help
 	  Enables support for NAND Flash chips on Lantiq XWAY SoCs. NAND is attached
 	  to the External Bus Unit (EBU).
@@ -563,4 +562,11 @@ config MTD_NAND_QCOM
 	  Enables support for NAND flash chips on SoCs containing the EBI2 NAND
 	  controller. This controller is found on IPQ806x SoC.
 
+config MTD_NAND_MTK
+	tristate "Support for NAND controller on MTK SoCs"
+	depends on HAS_DMA
+	help
+	  Enables support for NAND controller on MTK SoCs.
+	  This controller is found on mt27xx, mt81xx, mt65xx SoCs.
+
 endif # MTD_NAND
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index f55335373f7c..cafde6f3d957 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -57,5 +57,6 @@ obj-$(CONFIG_MTD_NAND_SUNXI)		+= sunxi_nand.o
 obj-$(CONFIG_MTD_NAND_HISI504)	        += hisi504_nand.o
 obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= brcmnand/
 obj-$(CONFIG_MTD_NAND_QCOM)		+= qcom_nandc.o
+obj-$(CONFIG_MTD_NAND_MTK)		+= mtk_nand.o mtk_ecc.o
 
 nand-objs := nand_base.o nand_bbt.o nand_timings.o
diff --git a/drivers/mtd/nand/brcmnand/brcmnand.c b/drivers/mtd/nand/brcmnand/brcmnand.c
index b76ad7c0144f..8eb2c64df38c 100644
--- a/drivers/mtd/nand/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/brcmnand/brcmnand.c
@@ -340,6 +340,36 @@ static const u16 brcmnand_regs_v71[] = {
 	[BRCMNAND_FC_BASE]		= 0x400,
 };
 
+/* BRCMNAND v7.2 */
+static const u16 brcmnand_regs_v72[] = {
+	[BRCMNAND_CMD_START]		=  0x04,
+	[BRCMNAND_CMD_EXT_ADDRESS]	=  0x08,
+	[BRCMNAND_CMD_ADDRESS]		=  0x0c,
+	[BRCMNAND_INTFC_STATUS]		=  0x14,
+	[BRCMNAND_CS_SELECT]		=  0x18,
+	[BRCMNAND_CS_XOR]		=  0x1c,
+	[BRCMNAND_LL_OP]		=  0x20,
+	[BRCMNAND_CS0_BASE]		=  0x50,
+	[BRCMNAND_CS1_BASE]		=     0,
+	[BRCMNAND_CORR_THRESHOLD]	=  0xdc,
+	[BRCMNAND_CORR_THRESHOLD_EXT]	=  0xe0,
+	[BRCMNAND_UNCORR_COUNT]		=  0xfc,
+	[BRCMNAND_CORR_COUNT]		= 0x100,
+	[BRCMNAND_CORR_EXT_ADDR]	= 0x10c,
+	[BRCMNAND_CORR_ADDR]		= 0x110,
+	[BRCMNAND_UNCORR_EXT_ADDR]	= 0x114,
+	[BRCMNAND_UNCORR_ADDR]		= 0x118,
+	[BRCMNAND_SEMAPHORE]		= 0x150,
+	[BRCMNAND_ID]			= 0x194,
+	[BRCMNAND_ID_EXT]		= 0x198,
+	[BRCMNAND_LL_RDATA]		= 0x19c,
+	[BRCMNAND_OOB_READ_BASE]	= 0x200,
+	[BRCMNAND_OOB_READ_10_BASE]	=     0,
+	[BRCMNAND_OOB_WRITE_BASE]	= 0x400,
+	[BRCMNAND_OOB_WRITE_10_BASE]	=     0,
+	[BRCMNAND_FC_BASE]		= 0x600,
+};
+
 enum brcmnand_cs_reg {
 	BRCMNAND_CS_CFG_EXT = 0,
 	BRCMNAND_CS_CFG,
@@ -435,7 +465,9 @@ static int brcmnand_revision_init(struct brcmnand_controller *ctrl)
 	}
 
 	/* Register offsets */
-	if (ctrl->nand_version >= 0x0701)
+	if (ctrl->nand_version >= 0x0702)
+		ctrl->reg_offsets = brcmnand_regs_v72;
+	else if (ctrl->nand_version >= 0x0701)
 		ctrl->reg_offsets = brcmnand_regs_v71;
 	else if (ctrl->nand_version >= 0x0600)
 		ctrl->reg_offsets = brcmnand_regs_v60;
@@ -480,7 +512,9 @@ static int brcmnand_revision_init(struct brcmnand_controller *ctrl)
 	}
 
 	/* Maximum spare area sector size (per 512B) */
-	if (ctrl->nand_version >= 0x0600)
+	if (ctrl->nand_version >= 0x0702)
+		ctrl->max_oob = 128;
+	else if (ctrl->nand_version >= 0x0600)
 		ctrl->max_oob = 64;
 	else if (ctrl->nand_version >= 0x0500)
 		ctrl->max_oob = 32;
@@ -583,14 +617,20 @@ static void brcmnand_wr_corr_thresh(struct brcmnand_host *host, u8 val)
 	enum brcmnand_reg reg = BRCMNAND_CORR_THRESHOLD;
 	int cs = host->cs;
 
-	if (ctrl->nand_version >= 0x0600)
+	if (ctrl->nand_version >= 0x0702)
+		bits = 7;
+	else if (ctrl->nand_version >= 0x0600)
 		bits = 6;
 	else if (ctrl->nand_version >= 0x0500)
 		bits = 5;
 	else
 		bits = 4;
 
-	if (ctrl->nand_version >= 0x0600) {
+	if (ctrl->nand_version >= 0x0702) {
+		if (cs >= 4)
+			reg = BRCMNAND_CORR_THRESHOLD_EXT;
+		shift = (cs % 4) * bits;
+	} else if (ctrl->nand_version >= 0x0600) {
 		if (cs >= 5)
 			reg = BRCMNAND_CORR_THRESHOLD_EXT;
 		shift = (cs % 5) * bits;
@@ -631,19 +671,28 @@ enum {
 
 static inline u32 brcmnand_spare_area_mask(struct brcmnand_controller *ctrl)
 {
-	if (ctrl->nand_version >= 0x0600)
+	if (ctrl->nand_version >= 0x0702)
+		return GENMASK(7, 0);
+	else if (ctrl->nand_version >= 0x0600)
 		return GENMASK(6, 0);
 	else
 		return GENMASK(5, 0);
 }
 
 #define NAND_ACC_CONTROL_ECC_SHIFT	16
+#define NAND_ACC_CONTROL_ECC_EXT_SHIFT	13
 
 static inline u32 brcmnand_ecc_level_mask(struct brcmnand_controller *ctrl)
 {
 	u32 mask = (ctrl->nand_version >= 0x0600) ? 0x1f : 0x0f;
 
-	return mask << NAND_ACC_CONTROL_ECC_SHIFT;
+	mask <<= NAND_ACC_CONTROL_ECC_SHIFT;
+
+	/* v7.2 includes additional ECC levels */
+	if (ctrl->nand_version >= 0x0702)
+		mask |= 0x7 << NAND_ACC_CONTROL_ECC_EXT_SHIFT;
+
+	return mask;
 }
 
 static void brcmnand_set_ecc_enabled(struct brcmnand_host *host, int en)
@@ -667,7 +716,9 @@ static void brcmnand_set_ecc_enabled(struct brcmnand_host *host, int en)
 
 static inline int brcmnand_sector_1k_shift(struct brcmnand_controller *ctrl)
 {
-	if (ctrl->nand_version >= 0x0600)
+	if (ctrl->nand_version >= 0x0702)
+		return 9;
+	else if (ctrl->nand_version >= 0x0600)
 		return 7;
 	else if (ctrl->nand_version >= 0x0500)
 		return 6;
@@ -773,10 +824,16 @@ enum brcmnand_llop_type {
  * Internal support functions
  ***********************************************************************/
 
-static inline bool is_hamming_ecc(struct brcmnand_cfg *cfg)
+static inline bool is_hamming_ecc(struct brcmnand_controller *ctrl,
+				  struct brcmnand_cfg *cfg)
 {
-	return cfg->sector_size_1k == 0 && cfg->spare_area_size == 16 &&
-		cfg->ecc_level == 15;
+	if (ctrl->nand_version <= 0x0701)
+		return cfg->sector_size_1k == 0 && cfg->spare_area_size == 16 &&
+			cfg->ecc_level == 15;
+	else
+		return cfg->sector_size_1k == 0 && ((cfg->spare_area_size == 16 &&
+			cfg->ecc_level == 15) ||
+			(cfg->spare_area_size == 28 && cfg->ecc_level == 16));
 }
 
 /*
@@ -931,7 +988,7 @@ static int brcmstb_choose_ecc_layout(struct brcmnand_host *host)
 	if (p->sector_size_1k)
 		ecc_level <<= 1;
 
-	if (is_hamming_ecc(p)) {
+	if (is_hamming_ecc(host->ctrl, p)) {
 		ecc->bytes = 3 * sectors;
 		mtd_set_ooblayout(mtd, &brcmnand_hamming_ooblayout_ops);
 		return 0;
@@ -1108,7 +1165,7 @@ static void brcmnand_send_cmd(struct brcmnand_host *host, int cmd)
 	ctrl->cmd_pending = cmd;
 
 	intfc = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS);
-	BUG_ON(!(intfc & INTFC_CTLR_READY));
+	WARN_ON(!(intfc & INTFC_CTLR_READY));
 
 	mb(); /* flush previous writes */
 	brcmnand_write_reg(ctrl, BRCMNAND_CMD_START,
@@ -1545,6 +1602,56 @@ static int brcmnand_read_by_pio(struct mtd_info *mtd, struct nand_chip *chip,
 	return ret;
 }
 
+/*
+ * Check a page to see if it is erased (w/ bitflips) after an uncorrectable ECC
+ * error
+ *
+ * Because the HW ECC signals an ECC error if an erase paged has even a single
+ * bitflip, we must check each ECC error to see if it is actually an erased
+ * page with bitflips, not a truly corrupted page.
+ *
+ * On a real error, return a negative error code (-EBADMSG for ECC error), and
+ * buf will contain raw data.
+ * Otherwise, buf gets filled with 0xffs and return the maximum number of
+ * bitflips-per-ECC-sector to the caller.
+ *
+ */
+static int brcmstb_nand_verify_erased_page(struct mtd_info *mtd,
+		  struct nand_chip *chip, void *buf, u64 addr)
+{
+	int i, sas;
+	void *oob = chip->oob_poi;
+	int bitflips = 0;
+	int page = addr >> chip->page_shift;
+	int ret;
+
+	if (!buf) {
+		buf = chip->buffers->databuf;
+		/* Invalidate page cache */
+		chip->pagebuf = -1;
+	}
+
+	sas = mtd->oobsize / chip->ecc.steps;
+
+	/* read without ecc for verification */
+	chip->cmdfunc(mtd, NAND_CMD_READ0, 0x00, page);
+	ret = chip->ecc.read_page_raw(mtd, chip, buf, true, page);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < chip->ecc.steps; i++, oob += sas) {
+		ret = nand_check_erased_ecc_chunk(buf, chip->ecc.size,
+						  oob, sas, NULL, 0,
+						  chip->ecc.strength);
+		if (ret < 0)
+			return ret;
+
+		bitflips = max(bitflips, ret);
+	}
+
+	return bitflips;
+}
+
 static int brcmnand_read(struct mtd_info *mtd, struct nand_chip *chip,
 			 u64 addr, unsigned int trans, u32 *buf, u8 *oob)
 {
@@ -1552,9 +1659,11 @@ static int brcmnand_read(struct mtd_info *mtd, struct nand_chip *chip,
 	struct brcmnand_controller *ctrl = host->ctrl;
 	u64 err_addr = 0;
 	int err;
+	bool retry = true;
 
 	dev_dbg(ctrl->dev, "read %llx -> %p\n", (unsigned long long)addr, buf);
 
+try_dmaread:
 	brcmnand_write_reg(ctrl, BRCMNAND_UNCORR_COUNT, 0);
 
 	if (has_flash_dma(ctrl) && !oob && flash_dma_buf_ok(buf)) {
@@ -1575,6 +1684,34 @@ static int brcmnand_read(struct mtd_info *mtd, struct nand_chip *chip,
 	}
 
 	if (mtd_is_eccerr(err)) {
+		/*
+		 * On controller version and 7.0, 7.1 , DMA read after a
+		 * prior PIO read that reported uncorrectable error,
+		 * the DMA engine captures this error following DMA read
+		 * cleared only on subsequent DMA read, so just retry once
+		 * to clear a possible false error reported for current DMA
+		 * read
+		 */
+		if ((ctrl->nand_version == 0x0700) ||
+		    (ctrl->nand_version == 0x0701)) {
+			if (retry) {
+				retry = false;
+				goto try_dmaread;
+			}
+		}
+
+		/*
+		 * Controller version 7.2 has hw encoder to detect erased page
+		 * bitflips, apply sw verification for older controllers only
+		 */
+		if (ctrl->nand_version < 0x0702) {
+			err = brcmstb_nand_verify_erased_page(mtd, chip, buf,
+							      addr);
+			/* erased page bitflips corrected */
+			if (err > 0)
+				return err;
+		}
+
 		dev_dbg(ctrl->dev, "uncorrectable error at 0x%llx\n",
 			(unsigned long long)err_addr);
 		mtd->ecc_stats.failed++;
@@ -1857,7 +1994,8 @@ static int brcmnand_set_cfg(struct brcmnand_host *host,
 	return 0;
 }
 
-static void brcmnand_print_cfg(char *buf, struct brcmnand_cfg *cfg)
+static void brcmnand_print_cfg(struct brcmnand_host *host,
+			       char *buf, struct brcmnand_cfg *cfg)
 {
 	buf += sprintf(buf,
 		"%lluMiB total, %uKiB blocks, %u%s pages, %uB OOB, %u-bit",
@@ -1868,7 +2006,7 @@ static void brcmnand_print_cfg(char *buf, struct brcmnand_cfg *cfg)
 		cfg->spare_area_size, cfg->device_width);
 
 	/* Account for Hamming ECC and for BCH 512B vs 1KiB sectors */
-	if (is_hamming_ecc(cfg))
+	if (is_hamming_ecc(host->ctrl, cfg))
 		sprintf(buf, ", Hamming ECC");
 	else if (cfg->sector_size_1k)
 		sprintf(buf, ", BCH-%u (1KiB sector)", cfg->ecc_level << 1);
@@ -1987,7 +2125,7 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 
 	brcmnand_set_ecc_enabled(host, 1);
 
-	brcmnand_print_cfg(msg, cfg);
+	brcmnand_print_cfg(host, msg, cfg);
 	dev_info(ctrl->dev, "detected %s\n", msg);
 
 	/* Configure ACC_CONTROL */
@@ -1995,6 +2133,10 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 	tmp = nand_readreg(ctrl, offs);
 	tmp &= ~ACC_CONTROL_PARTIAL_PAGE;
 	tmp &= ~ACC_CONTROL_RD_ERASED;
+
+	/* We need to turn on Read from erased paged protected by ECC */
+	if (ctrl->nand_version >= 0x0702)
+		tmp |= ACC_CONTROL_RD_ERASED;
 	tmp &= ~ACC_CONTROL_FAST_PGM_RDIN;
 	if (ctrl->features & BRCMNAND_HAS_PREFETCH) {
 		/*
@@ -2195,6 +2337,7 @@ static const struct of_device_id brcmnand_of_match[] = {
 	{ .compatible = "brcm,brcmnand-v6.2" },
 	{ .compatible = "brcm,brcmnand-v7.0" },
 	{ .compatible = "brcm,brcmnand-v7.1" },
+	{ .compatible = "brcm,brcmnand-v7.2" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, brcmnand_of_match);
diff --git a/drivers/mtd/nand/jz4780_bch.c b/drivers/mtd/nand/jz4780_bch.c
index d74f4ba4a6f4..731c6051d91e 100644
--- a/drivers/mtd/nand/jz4780_bch.c
+++ b/drivers/mtd/nand/jz4780_bch.c
@@ -375,6 +375,6 @@ static struct platform_driver jz4780_bch_driver = {
 module_platform_driver(jz4780_bch_driver);
 
 MODULE_AUTHOR("Alex Smith <alex@alex-smith.me.uk>");
-MODULE_AUTHOR("Harvey Hunt <harvey.hunt@imgtec.com>");
+MODULE_AUTHOR("Harvey Hunt <harveyhuntnexus@gmail.com>");
 MODULE_DESCRIPTION("Ingenic JZ4780 BCH error correction driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/nand/jz4780_nand.c b/drivers/mtd/nand/jz4780_nand.c
index daf3c4217f4d..175f67da25af 100644
--- a/drivers/mtd/nand/jz4780_nand.c
+++ b/drivers/mtd/nand/jz4780_nand.c
@@ -412,6 +412,6 @@ static struct platform_driver jz4780_nand_driver = {
 module_platform_driver(jz4780_nand_driver);
 
 MODULE_AUTHOR("Alex Smith <alex@alex-smith.me.uk>");
-MODULE_AUTHOR("Harvey Hunt <harvey.hunt@imgtec.com>");
+MODULE_AUTHOR("Harvey Hunt <harveyhuntnexus@gmail.com>");
 MODULE_DESCRIPTION("Ingenic JZ4780 NAND driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/nand/mtk_ecc.c b/drivers/mtd/nand/mtk_ecc.c
new file mode 100644
index 000000000000..25a4fbd4d24a
--- /dev/null
+++ b/drivers/mtd/nand/mtk_ecc.c
@@ -0,0 +1,530 @@
+/*
+ * MTK ECC controller driver.
+ * Copyright (C) 2016  MediaTek Inc.
+ * Authors:	Xiaolei Li		<xiaolei.li@mediatek.com>
+ *		Jorge Ramirez-Ortiz	<jorge.ramirez-ortiz@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/iopoll.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/mutex.h>
+
+#include "mtk_ecc.h"
+
+#define ECC_IDLE_MASK		BIT(0)
+#define ECC_IRQ_EN		BIT(0)
+#define ECC_OP_ENABLE		(1)
+#define ECC_OP_DISABLE		(0)
+
+#define ECC_ENCCON		(0x00)
+#define ECC_ENCCNFG		(0x04)
+#define		ECC_CNFG_4BIT		(0)
+#define		ECC_CNFG_6BIT		(1)
+#define		ECC_CNFG_8BIT		(2)
+#define		ECC_CNFG_10BIT		(3)
+#define		ECC_CNFG_12BIT		(4)
+#define		ECC_CNFG_14BIT		(5)
+#define		ECC_CNFG_16BIT		(6)
+#define		ECC_CNFG_18BIT		(7)
+#define		ECC_CNFG_20BIT		(8)
+#define		ECC_CNFG_22BIT		(9)
+#define		ECC_CNFG_24BIT		(0xa)
+#define		ECC_CNFG_28BIT		(0xb)
+#define		ECC_CNFG_32BIT		(0xc)
+#define		ECC_CNFG_36BIT		(0xd)
+#define		ECC_CNFG_40BIT		(0xe)
+#define		ECC_CNFG_44BIT		(0xf)
+#define		ECC_CNFG_48BIT		(0x10)
+#define		ECC_CNFG_52BIT		(0x11)
+#define		ECC_CNFG_56BIT		(0x12)
+#define		ECC_CNFG_60BIT		(0x13)
+#define		ECC_MODE_SHIFT		(5)
+#define		ECC_MS_SHIFT		(16)
+#define ECC_ENCDIADDR		(0x08)
+#define ECC_ENCIDLE		(0x0C)
+#define ECC_ENCPAR(x)		(0x10 + (x) * sizeof(u32))
+#define ECC_ENCIRQ_EN		(0x80)
+#define ECC_ENCIRQ_STA		(0x84)
+#define ECC_DECCON		(0x100)
+#define ECC_DECCNFG		(0x104)
+#define		DEC_EMPTY_EN		BIT(31)
+#define		DEC_CNFG_CORRECT	(0x3 << 12)
+#define ECC_DECIDLE		(0x10C)
+#define ECC_DECENUM0		(0x114)
+#define		ERR_MASK		(0x3f)
+#define ECC_DECDONE		(0x124)
+#define ECC_DECIRQ_EN		(0x200)
+#define ECC_DECIRQ_STA		(0x204)
+
+#define ECC_TIMEOUT		(500000)
+
+#define ECC_IDLE_REG(op)	((op) == ECC_ENCODE ? ECC_ENCIDLE : ECC_DECIDLE)
+#define ECC_CTL_REG(op)		((op) == ECC_ENCODE ? ECC_ENCCON : ECC_DECCON)
+#define ECC_IRQ_REG(op)		((op) == ECC_ENCODE ? \
+					ECC_ENCIRQ_EN : ECC_DECIRQ_EN)
+
+struct mtk_ecc {
+	struct device *dev;
+	void __iomem *regs;
+	struct clk *clk;
+
+	struct completion done;
+	struct mutex lock;
+	u32 sectors;
+};
+
+static inline void mtk_ecc_wait_idle(struct mtk_ecc *ecc,
+				     enum mtk_ecc_operation op)
+{
+	struct device *dev = ecc->dev;
+	u32 val;
+	int ret;
+
+	ret = readl_poll_timeout_atomic(ecc->regs + ECC_IDLE_REG(op), val,
+					val & ECC_IDLE_MASK,
+					10, ECC_TIMEOUT);
+	if (ret)
+		dev_warn(dev, "%s NOT idle\n",
+			 op == ECC_ENCODE ? "encoder" : "decoder");
+}
+
+static irqreturn_t mtk_ecc_irq(int irq, void *id)
+{
+	struct mtk_ecc *ecc = id;
+	enum mtk_ecc_operation op;
+	u32 dec, enc;
+
+	dec = readw(ecc->regs + ECC_DECIRQ_STA) & ECC_IRQ_EN;
+	if (dec) {
+		op = ECC_DECODE;
+		dec = readw(ecc->regs + ECC_DECDONE);
+		if (dec & ecc->sectors) {
+			ecc->sectors = 0;
+			complete(&ecc->done);
+		} else {
+			return IRQ_HANDLED;
+		}
+	} else {
+		enc = readl(ecc->regs + ECC_ENCIRQ_STA) & ECC_IRQ_EN;
+		if (enc) {
+			op = ECC_ENCODE;
+			complete(&ecc->done);
+		} else {
+			return IRQ_NONE;
+		}
+	}
+
+	writel(0, ecc->regs + ECC_IRQ_REG(op));
+
+	return IRQ_HANDLED;
+}
+
+static void mtk_ecc_config(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
+{
+	u32 ecc_bit = ECC_CNFG_4BIT, dec_sz, enc_sz;
+	u32 reg;
+
+	switch (config->strength) {
+	case 4:
+		ecc_bit = ECC_CNFG_4BIT;
+		break;
+	case 6:
+		ecc_bit = ECC_CNFG_6BIT;
+		break;
+	case 8:
+		ecc_bit = ECC_CNFG_8BIT;
+		break;
+	case 10:
+		ecc_bit = ECC_CNFG_10BIT;
+		break;
+	case 12:
+		ecc_bit = ECC_CNFG_12BIT;
+		break;
+	case 14:
+		ecc_bit = ECC_CNFG_14BIT;
+		break;
+	case 16:
+		ecc_bit = ECC_CNFG_16BIT;
+		break;
+	case 18:
+		ecc_bit = ECC_CNFG_18BIT;
+		break;
+	case 20:
+		ecc_bit = ECC_CNFG_20BIT;
+		break;
+	case 22:
+		ecc_bit = ECC_CNFG_22BIT;
+		break;
+	case 24:
+		ecc_bit = ECC_CNFG_24BIT;
+		break;
+	case 28:
+		ecc_bit = ECC_CNFG_28BIT;
+		break;
+	case 32:
+		ecc_bit = ECC_CNFG_32BIT;
+		break;
+	case 36:
+		ecc_bit = ECC_CNFG_36BIT;
+		break;
+	case 40:
+		ecc_bit = ECC_CNFG_40BIT;
+		break;
+	case 44:
+		ecc_bit = ECC_CNFG_44BIT;
+		break;
+	case 48:
+		ecc_bit = ECC_CNFG_48BIT;
+		break;
+	case 52:
+		ecc_bit = ECC_CNFG_52BIT;
+		break;
+	case 56:
+		ecc_bit = ECC_CNFG_56BIT;
+		break;
+	case 60:
+		ecc_bit = ECC_CNFG_60BIT;
+		break;
+	default:
+		dev_err(ecc->dev, "invalid strength %d, default to 4 bits\n",
+			config->strength);
+	}
+
+	if (config->op == ECC_ENCODE) {
+		/* configure ECC encoder (in bits) */
+		enc_sz = config->len << 3;
+
+		reg = ecc_bit | (config->mode << ECC_MODE_SHIFT);
+		reg |= (enc_sz << ECC_MS_SHIFT);
+		writel(reg, ecc->regs + ECC_ENCCNFG);
+
+		if (config->mode != ECC_NFI_MODE)
+			writel(lower_32_bits(config->addr),
+			       ecc->regs + ECC_ENCDIADDR);
+
+	} else {
+		/* configure ECC decoder (in bits) */
+		dec_sz = (config->len << 3) +
+					config->strength * ECC_PARITY_BITS;
+
+		reg = ecc_bit | (config->mode << ECC_MODE_SHIFT);
+		reg |= (dec_sz << ECC_MS_SHIFT) | DEC_CNFG_CORRECT;
+		reg |= DEC_EMPTY_EN;
+		writel(reg, ecc->regs + ECC_DECCNFG);
+
+		if (config->sectors)
+			ecc->sectors = 1 << (config->sectors - 1);
+	}
+}
+
+void mtk_ecc_get_stats(struct mtk_ecc *ecc, struct mtk_ecc_stats *stats,
+		       int sectors)
+{
+	u32 offset, i, err;
+	u32 bitflips = 0;
+
+	stats->corrected = 0;
+	stats->failed = 0;
+
+	for (i = 0; i < sectors; i++) {
+		offset = (i >> 2) << 2;
+		err = readl(ecc->regs + ECC_DECENUM0 + offset);
+		err = err >> ((i % 4) * 8);
+		err &= ERR_MASK;
+		if (err == ERR_MASK) {
+			/* uncorrectable errors */
+			stats->failed++;
+			continue;
+		}
+
+		stats->corrected += err;
+		bitflips = max_t(u32, bitflips, err);
+	}
+
+	stats->bitflips = bitflips;
+}
+EXPORT_SYMBOL(mtk_ecc_get_stats);
+
+void mtk_ecc_release(struct mtk_ecc *ecc)
+{
+	clk_disable_unprepare(ecc->clk);
+	put_device(ecc->dev);
+}
+EXPORT_SYMBOL(mtk_ecc_release);
+
+static void mtk_ecc_hw_init(struct mtk_ecc *ecc)
+{
+	mtk_ecc_wait_idle(ecc, ECC_ENCODE);
+	writew(ECC_OP_DISABLE, ecc->regs + ECC_ENCCON);
+
+	mtk_ecc_wait_idle(ecc, ECC_DECODE);
+	writel(ECC_OP_DISABLE, ecc->regs + ECC_DECCON);
+}
+
+static struct mtk_ecc *mtk_ecc_get(struct device_node *np)
+{
+	struct platform_device *pdev;
+	struct mtk_ecc *ecc;
+
+	pdev = of_find_device_by_node(np);
+	if (!pdev || !platform_get_drvdata(pdev))
+		return ERR_PTR(-EPROBE_DEFER);
+
+	get_device(&pdev->dev);
+	ecc = platform_get_drvdata(pdev);
+	clk_prepare_enable(ecc->clk);
+	mtk_ecc_hw_init(ecc);
+
+	return ecc;
+}
+
+struct mtk_ecc *of_mtk_ecc_get(struct device_node *of_node)
+{
+	struct mtk_ecc *ecc = NULL;
+	struct device_node *np;
+
+	np = of_parse_phandle(of_node, "ecc-engine", 0);
+	if (np) {
+		ecc = mtk_ecc_get(np);
+		of_node_put(np);
+	}
+
+	return ecc;
+}
+EXPORT_SYMBOL(of_mtk_ecc_get);
+
+int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
+{
+	enum mtk_ecc_operation op = config->op;
+	int ret;
+
+	ret = mutex_lock_interruptible(&ecc->lock);
+	if (ret) {
+		dev_err(ecc->dev, "interrupted when attempting to lock\n");
+		return ret;
+	}
+
+	mtk_ecc_wait_idle(ecc, op);
+	mtk_ecc_config(ecc, config);
+	writew(ECC_OP_ENABLE, ecc->regs + ECC_CTL_REG(op));
+
+	init_completion(&ecc->done);
+	writew(ECC_IRQ_EN, ecc->regs + ECC_IRQ_REG(op));
+
+	return 0;
+}
+EXPORT_SYMBOL(mtk_ecc_enable);
+
+void mtk_ecc_disable(struct mtk_ecc *ecc)
+{
+	enum mtk_ecc_operation op = ECC_ENCODE;
+
+	/* find out the running operation */
+	if (readw(ecc->regs + ECC_CTL_REG(op)) != ECC_OP_ENABLE)
+		op = ECC_DECODE;
+
+	/* disable it */
+	mtk_ecc_wait_idle(ecc, op);
+	writew(0, ecc->regs + ECC_IRQ_REG(op));
+	writew(ECC_OP_DISABLE, ecc->regs + ECC_CTL_REG(op));
+
+	mutex_unlock(&ecc->lock);
+}
+EXPORT_SYMBOL(mtk_ecc_disable);
+
+int mtk_ecc_wait_done(struct mtk_ecc *ecc, enum mtk_ecc_operation op)
+{
+	int ret;
+
+	ret = wait_for_completion_timeout(&ecc->done, msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ecc->dev, "%s timeout - interrupt did not arrive)\n",
+			(op == ECC_ENCODE) ? "encoder" : "decoder");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mtk_ecc_wait_done);
+
+int mtk_ecc_encode(struct mtk_ecc *ecc, struct mtk_ecc_config *config,
+		   u8 *data, u32 bytes)
+{
+	dma_addr_t addr;
+	u32 *p, len, i;
+	int ret = 0;
+
+	addr = dma_map_single(ecc->dev, data, bytes, DMA_TO_DEVICE);
+	ret = dma_mapping_error(ecc->dev, addr);
+	if (ret) {
+		dev_err(ecc->dev, "dma mapping error\n");
+		return -EINVAL;
+	}
+
+	config->op = ECC_ENCODE;
+	config->addr = addr;
+	ret = mtk_ecc_enable(ecc, config);
+	if (ret) {
+		dma_unmap_single(ecc->dev, addr, bytes, DMA_TO_DEVICE);
+		return ret;
+	}
+
+	ret = mtk_ecc_wait_done(ecc, ECC_ENCODE);
+	if (ret)
+		goto timeout;
+
+	mtk_ecc_wait_idle(ecc, ECC_ENCODE);
+
+	/* Program ECC bytes to OOB: per sector oob = FDM + ECC + SPARE */
+	len = (config->strength * ECC_PARITY_BITS + 7) >> 3;
+	p = (u32 *)(data + bytes);
+
+	/* write the parity bytes generated by the ECC back to the OOB region */
+	for (i = 0; i < len; i++)
+		p[i] = readl(ecc->regs + ECC_ENCPAR(i));
+timeout:
+
+	dma_unmap_single(ecc->dev, addr, bytes, DMA_TO_DEVICE);
+	mtk_ecc_disable(ecc);
+
+	return ret;
+}
+EXPORT_SYMBOL(mtk_ecc_encode);
+
+void mtk_ecc_adjust_strength(u32 *p)
+{
+	u32 ecc[] = {4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36,
+			40, 44, 48, 52, 56, 60};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ecc); i++) {
+		if (*p <= ecc[i]) {
+			if (!i)
+				*p = ecc[i];
+			else if (*p != ecc[i])
+				*p = ecc[i - 1];
+			return;
+		}
+	}
+
+	*p = ecc[ARRAY_SIZE(ecc) - 1];
+}
+EXPORT_SYMBOL(mtk_ecc_adjust_strength);
+
+static int mtk_ecc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mtk_ecc *ecc;
+	struct resource *res;
+	int irq, ret;
+
+	ecc = devm_kzalloc(dev, sizeof(*ecc), GFP_KERNEL);
+	if (!ecc)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ecc->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(ecc->regs)) {
+		dev_err(dev, "failed to map regs: %ld\n", PTR_ERR(ecc->regs));
+		return PTR_ERR(ecc->regs);
+	}
+
+	ecc->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(ecc->clk)) {
+		dev_err(dev, "failed to get clock: %ld\n", PTR_ERR(ecc->clk));
+		return PTR_ERR(ecc->clk);
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "failed to get irq\n");
+		return -EINVAL;
+	}
+
+	ret = dma_set_mask(dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(dev, "failed to set DMA mask\n");
+		return ret;
+	}
+
+	ret = devm_request_irq(dev, irq, mtk_ecc_irq, 0x0, "mtk-ecc", ecc);
+	if (ret) {
+		dev_err(dev, "failed to request irq\n");
+		return -EINVAL;
+	}
+
+	ecc->dev = dev;
+	mutex_init(&ecc->lock);
+	platform_set_drvdata(pdev, ecc);
+	dev_info(dev, "probed\n");
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int mtk_ecc_suspend(struct device *dev)
+{
+	struct mtk_ecc *ecc = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(ecc->clk);
+
+	return 0;
+}
+
+static int mtk_ecc_resume(struct device *dev)
+{
+	struct mtk_ecc *ecc = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(ecc->clk);
+	if (ret) {
+		dev_err(dev, "failed to enable clk\n");
+		return ret;
+	}
+
+	mtk_ecc_hw_init(ecc);
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(mtk_ecc_pm_ops, mtk_ecc_suspend, mtk_ecc_resume);
+#endif
+
+static const struct of_device_id mtk_ecc_dt_match[] = {
+	{ .compatible = "mediatek,mt2701-ecc" },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, mtk_ecc_dt_match);
+
+static struct platform_driver mtk_ecc_driver = {
+	.probe  = mtk_ecc_probe,
+	.driver = {
+		.name  = "mtk-ecc",
+		.of_match_table = of_match_ptr(mtk_ecc_dt_match),
+#ifdef CONFIG_PM_SLEEP
+		.pm = &mtk_ecc_pm_ops,
+#endif
+	},
+};
+
+module_platform_driver(mtk_ecc_driver);
+
+MODULE_AUTHOR("Xiaolei Li <xiaolei.li@mediatek.com>");
+MODULE_DESCRIPTION("MTK Nand ECC Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mtd/nand/mtk_ecc.h b/drivers/mtd/nand/mtk_ecc.h
new file mode 100644
index 000000000000..cbeba5cd1c13
--- /dev/null
+++ b/drivers/mtd/nand/mtk_ecc.h
@@ -0,0 +1,50 @@
+/*
+ * MTK SDG1 ECC controller
+ *
+ * Copyright (c) 2016 Mediatek
+ * Authors:	Xiaolei Li		<xiaolei.li@mediatek.com>
+ *		Jorge Ramirez-Ortiz	<jorge.ramirez-ortiz@linaro.org>
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef __DRIVERS_MTD_NAND_MTK_ECC_H__
+#define __DRIVERS_MTD_NAND_MTK_ECC_H__
+
+#include <linux/types.h>
+
+#define ECC_PARITY_BITS		(14)
+
+enum mtk_ecc_mode {ECC_DMA_MODE = 0, ECC_NFI_MODE = 1};
+enum mtk_ecc_operation {ECC_ENCODE, ECC_DECODE};
+
+struct device_node;
+struct mtk_ecc;
+
+struct mtk_ecc_stats {
+	u32 corrected;
+	u32 bitflips;
+	u32 failed;
+};
+
+struct mtk_ecc_config {
+	enum mtk_ecc_operation op;
+	enum mtk_ecc_mode mode;
+	dma_addr_t addr;
+	u32 strength;
+	u32 sectors;
+	u32 len;
+};
+
+int mtk_ecc_encode(struct mtk_ecc *, struct mtk_ecc_config *, u8 *, u32);
+void mtk_ecc_get_stats(struct mtk_ecc *, struct mtk_ecc_stats *, int);
+int mtk_ecc_wait_done(struct mtk_ecc *, enum mtk_ecc_operation);
+int mtk_ecc_enable(struct mtk_ecc *, struct mtk_ecc_config *);
+void mtk_ecc_disable(struct mtk_ecc *);
+void mtk_ecc_adjust_strength(u32 *);
+
+struct mtk_ecc *of_mtk_ecc_get(struct device_node *);
+void mtk_ecc_release(struct mtk_ecc *);
+
+#endif
diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c
new file mode 100644
index 000000000000..ddaa2acb9dd7
--- /dev/null
+++ b/drivers/mtd/nand/mtk_nand.c
@@ -0,0 +1,1526 @@
+/*
+ * MTK NAND Flash controller driver.
+ * Copyright (C) 2016 MediaTek Inc.
+ * Authors:	Xiaolei Li		<xiaolei.li@mediatek.com>
+ *		Jorge Ramirez-Ortiz	<jorge.ramirez-ortiz@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/clk.h>
+#include <linux/mtd/nand.h>
+#include <linux/mtd/mtd.h>
+#include <linux/module.h>
+#include <linux/iopoll.h>
+#include <linux/of.h>
+#include "mtk_ecc.h"
+
+/* NAND controller register definition */
+#define NFI_CNFG		(0x00)
+#define		CNFG_AHB		BIT(0)
+#define		CNFG_READ_EN		BIT(1)
+#define		CNFG_DMA_BURST_EN	BIT(2)
+#define		CNFG_BYTE_RW		BIT(6)
+#define		CNFG_HW_ECC_EN		BIT(8)
+#define		CNFG_AUTO_FMT_EN	BIT(9)
+#define		CNFG_OP_CUST		(6 << 12)
+#define NFI_PAGEFMT		(0x04)
+#define		PAGEFMT_FDM_ECC_SHIFT	(12)
+#define		PAGEFMT_FDM_SHIFT	(8)
+#define		PAGEFMT_SPARE_16	(0)
+#define		PAGEFMT_SPARE_26	(1)
+#define		PAGEFMT_SPARE_27	(2)
+#define		PAGEFMT_SPARE_28	(3)
+#define		PAGEFMT_SPARE_32	(4)
+#define		PAGEFMT_SPARE_36	(5)
+#define		PAGEFMT_SPARE_40	(6)
+#define		PAGEFMT_SPARE_44	(7)
+#define		PAGEFMT_SPARE_48	(8)
+#define		PAGEFMT_SPARE_49	(9)
+#define		PAGEFMT_SPARE_50	(0xa)
+#define		PAGEFMT_SPARE_51	(0xb)
+#define		PAGEFMT_SPARE_52	(0xc)
+#define		PAGEFMT_SPARE_62	(0xd)
+#define		PAGEFMT_SPARE_63	(0xe)
+#define		PAGEFMT_SPARE_64	(0xf)
+#define		PAGEFMT_SPARE_SHIFT	(4)
+#define		PAGEFMT_SEC_SEL_512	BIT(2)
+#define		PAGEFMT_512_2K		(0)
+#define		PAGEFMT_2K_4K		(1)
+#define		PAGEFMT_4K_8K		(2)
+#define		PAGEFMT_8K_16K		(3)
+/* NFI control */
+#define NFI_CON			(0x08)
+#define		CON_FIFO_FLUSH		BIT(0)
+#define		CON_NFI_RST		BIT(1)
+#define		CON_BRD			BIT(8)  /* burst  read */
+#define		CON_BWR			BIT(9)	/* burst  write */
+#define		CON_SEC_SHIFT		(12)
+/* Timming control register */
+#define NFI_ACCCON		(0x0C)
+#define NFI_INTR_EN		(0x10)
+#define		INTR_AHB_DONE_EN	BIT(6)
+#define NFI_INTR_STA		(0x14)
+#define NFI_CMD			(0x20)
+#define NFI_ADDRNOB		(0x30)
+#define NFI_COLADDR		(0x34)
+#define NFI_ROWADDR		(0x38)
+#define NFI_STRDATA		(0x40)
+#define		STAR_EN			(1)
+#define		STAR_DE			(0)
+#define NFI_CNRNB		(0x44)
+#define NFI_DATAW		(0x50)
+#define NFI_DATAR		(0x54)
+#define NFI_PIO_DIRDY		(0x58)
+#define		PIO_DI_RDY		(0x01)
+#define NFI_STA			(0x60)
+#define		STA_CMD			BIT(0)
+#define		STA_ADDR		BIT(1)
+#define		STA_BUSY		BIT(8)
+#define		STA_EMP_PAGE		BIT(12)
+#define		NFI_FSM_CUSTDATA	(0xe << 16)
+#define		NFI_FSM_MASK		(0xf << 16)
+#define NFI_ADDRCNTR		(0x70)
+#define		CNTR_MASK		GENMASK(16, 12)
+#define NFI_STRADDR		(0x80)
+#define NFI_BYTELEN		(0x84)
+#define NFI_CSEL		(0x90)
+#define NFI_FDML(x)		(0xA0 + (x) * sizeof(u32) * 2)
+#define NFI_FDMM(x)		(0xA4 + (x) * sizeof(u32) * 2)
+#define NFI_FDM_MAX_SIZE	(8)
+#define NFI_FDM_MIN_SIZE	(1)
+#define NFI_MASTER_STA		(0x224)
+#define		MASTER_STA_MASK		(0x0FFF)
+#define NFI_EMPTY_THRESH	(0x23C)
+
+#define MTK_NAME		"mtk-nand"
+#define KB(x)			((x) * 1024UL)
+#define MB(x)			(KB(x) * 1024UL)
+
+#define MTK_TIMEOUT		(500000)
+#define MTK_RESET_TIMEOUT	(1000000)
+#define MTK_MAX_SECTOR		(16)
+#define MTK_NAND_MAX_NSELS	(2)
+
+struct mtk_nfc_bad_mark_ctl {
+	void (*bm_swap)(struct mtd_info *, u8 *buf, int raw);
+	u32 sec;
+	u32 pos;
+};
+
+/*
+ * FDM: region used to store free OOB data
+ */
+struct mtk_nfc_fdm {
+	u32 reg_size;
+	u32 ecc_size;
+};
+
+struct mtk_nfc_nand_chip {
+	struct list_head node;
+	struct nand_chip nand;
+
+	struct mtk_nfc_bad_mark_ctl bad_mark;
+	struct mtk_nfc_fdm fdm;
+	u32 spare_per_sector;
+
+	int nsels;
+	u8 sels[0];
+	/* nothing after this field */
+};
+
+struct mtk_nfc_clk {
+	struct clk *nfi_clk;
+	struct clk *pad_clk;
+};
+
+struct mtk_nfc {
+	struct nand_hw_control controller;
+	struct mtk_ecc_config ecc_cfg;
+	struct mtk_nfc_clk clk;
+	struct mtk_ecc *ecc;
+
+	struct device *dev;
+	void __iomem *regs;
+
+	struct completion done;
+	struct list_head chips;
+
+	u8 *buffer;
+};
+
+static inline struct mtk_nfc_nand_chip *to_mtk_nand(struct nand_chip *nand)
+{
+	return container_of(nand, struct mtk_nfc_nand_chip, nand);
+}
+
+static inline u8 *data_ptr(struct nand_chip *chip, const u8 *p, int i)
+{
+	return (u8 *)p + i * chip->ecc.size;
+}
+
+static inline u8 *oob_ptr(struct nand_chip *chip, int i)
+{
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	u8 *poi;
+
+	/* map the sector's FDM data to free oob:
+	 * the beginning of the oob area stores the FDM data of bad mark sectors
+	 */
+
+	if (i < mtk_nand->bad_mark.sec)
+		poi = chip->oob_poi + (i + 1) * mtk_nand->fdm.reg_size;
+	else if (i == mtk_nand->bad_mark.sec)
+		poi = chip->oob_poi;
+	else
+		poi = chip->oob_poi + i * mtk_nand->fdm.reg_size;
+
+	return poi;
+}
+
+static inline int mtk_data_len(struct nand_chip *chip)
+{
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+
+	return chip->ecc.size + mtk_nand->spare_per_sector;
+}
+
+static inline u8 *mtk_data_ptr(struct nand_chip *chip,  int i)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+
+	return nfc->buffer + i * mtk_data_len(chip);
+}
+
+static inline u8 *mtk_oob_ptr(struct nand_chip *chip, int i)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+
+	return nfc->buffer + i * mtk_data_len(chip) + chip->ecc.size;
+}
+
+static inline void nfi_writel(struct mtk_nfc *nfc, u32 val, u32 reg)
+{
+	writel(val, nfc->regs + reg);
+}
+
+static inline void nfi_writew(struct mtk_nfc *nfc, u16 val, u32 reg)
+{
+	writew(val, nfc->regs + reg);
+}
+
+static inline void nfi_writeb(struct mtk_nfc *nfc, u8 val, u32 reg)
+{
+	writeb(val, nfc->regs + reg);
+}
+
+static inline u32 nfi_readl(struct mtk_nfc *nfc, u32 reg)
+{
+	return readl_relaxed(nfc->regs + reg);
+}
+
+static inline u16 nfi_readw(struct mtk_nfc *nfc, u32 reg)
+{
+	return readw_relaxed(nfc->regs + reg);
+}
+
+static inline u8 nfi_readb(struct mtk_nfc *nfc, u32 reg)
+{
+	return readb_relaxed(nfc->regs + reg);
+}
+
+static void mtk_nfc_hw_reset(struct mtk_nfc *nfc)
+{
+	struct device *dev = nfc->dev;
+	u32 val;
+	int ret;
+
+	/* reset all registers and force the NFI master to terminate */
+	nfi_writel(nfc, CON_FIFO_FLUSH | CON_NFI_RST, NFI_CON);
+
+	/* wait for the master to finish the last transaction */
+	ret = readl_poll_timeout(nfc->regs + NFI_MASTER_STA, val,
+				 !(val & MASTER_STA_MASK), 50,
+				 MTK_RESET_TIMEOUT);
+	if (ret)
+		dev_warn(dev, "master active in reset [0x%x] = 0x%x\n",
+			 NFI_MASTER_STA, val);
+
+	/* ensure any status register affected by the NFI master is reset */
+	nfi_writel(nfc, CON_FIFO_FLUSH | CON_NFI_RST, NFI_CON);
+	nfi_writew(nfc, STAR_DE, NFI_STRDATA);
+}
+
+static int mtk_nfc_send_command(struct mtk_nfc *nfc, u8 command)
+{
+	struct device *dev = nfc->dev;
+	u32 val;
+	int ret;
+
+	nfi_writel(nfc, command, NFI_CMD);
+
+	ret = readl_poll_timeout_atomic(nfc->regs + NFI_STA, val,
+					!(val & STA_CMD), 10,  MTK_TIMEOUT);
+	if (ret) {
+		dev_warn(dev, "nfi core timed out entering command mode\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int mtk_nfc_send_address(struct mtk_nfc *nfc, int addr)
+{
+	struct device *dev = nfc->dev;
+	u32 val;
+	int ret;
+
+	nfi_writel(nfc, addr, NFI_COLADDR);
+	nfi_writel(nfc, 0, NFI_ROWADDR);
+	nfi_writew(nfc, 1, NFI_ADDRNOB);
+
+	ret = readl_poll_timeout_atomic(nfc->regs + NFI_STA, val,
+					!(val & STA_ADDR), 10, MTK_TIMEOUT);
+	if (ret) {
+		dev_warn(dev, "nfi core timed out entering address mode\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int mtk_nfc_hw_runtime_config(struct mtd_info *mtd)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	u32 fmt, spare;
+
+	if (!mtd->writesize)
+		return 0;
+
+	spare = mtk_nand->spare_per_sector;
+
+	switch (mtd->writesize) {
+	case 512:
+		fmt = PAGEFMT_512_2K | PAGEFMT_SEC_SEL_512;
+		break;
+	case KB(2):
+		if (chip->ecc.size == 512)
+			fmt = PAGEFMT_2K_4K | PAGEFMT_SEC_SEL_512;
+		else
+			fmt = PAGEFMT_512_2K;
+		break;
+	case KB(4):
+		if (chip->ecc.size == 512)
+			fmt = PAGEFMT_4K_8K | PAGEFMT_SEC_SEL_512;
+		else
+			fmt = PAGEFMT_2K_4K;
+		break;
+	case KB(8):
+		if (chip->ecc.size == 512)
+			fmt = PAGEFMT_8K_16K | PAGEFMT_SEC_SEL_512;
+		else
+			fmt = PAGEFMT_4K_8K;
+		break;
+	case KB(16):
+		fmt = PAGEFMT_8K_16K;
+		break;
+	default:
+		dev_err(nfc->dev, "invalid page len: %d\n", mtd->writesize);
+		return -EINVAL;
+	}
+
+	/*
+	 * the hardware will double the value for this eccsize, so we need to
+	 * halve it
+	 */
+	if (chip->ecc.size == 1024)
+		spare >>= 1;
+
+	switch (spare) {
+	case 16:
+		fmt |= (PAGEFMT_SPARE_16 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 26:
+		fmt |= (PAGEFMT_SPARE_26 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 27:
+		fmt |= (PAGEFMT_SPARE_27 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 28:
+		fmt |= (PAGEFMT_SPARE_28 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 32:
+		fmt |= (PAGEFMT_SPARE_32 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 36:
+		fmt |= (PAGEFMT_SPARE_36 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 40:
+		fmt |= (PAGEFMT_SPARE_40 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 44:
+		fmt |= (PAGEFMT_SPARE_44 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 48:
+		fmt |= (PAGEFMT_SPARE_48 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 49:
+		fmt |= (PAGEFMT_SPARE_49 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 50:
+		fmt |= (PAGEFMT_SPARE_50 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 51:
+		fmt |= (PAGEFMT_SPARE_51 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 52:
+		fmt |= (PAGEFMT_SPARE_52 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 62:
+		fmt |= (PAGEFMT_SPARE_62 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 63:
+		fmt |= (PAGEFMT_SPARE_63 << PAGEFMT_SPARE_SHIFT);
+		break;
+	case 64:
+		fmt |= (PAGEFMT_SPARE_64 << PAGEFMT_SPARE_SHIFT);
+		break;
+	default:
+		dev_err(nfc->dev, "invalid spare per sector %d\n", spare);
+		return -EINVAL;
+	}
+
+	fmt |= mtk_nand->fdm.reg_size << PAGEFMT_FDM_SHIFT;
+	fmt |= mtk_nand->fdm.ecc_size << PAGEFMT_FDM_ECC_SHIFT;
+	nfi_writew(nfc, fmt, NFI_PAGEFMT);
+
+	nfc->ecc_cfg.strength = chip->ecc.strength;
+	nfc->ecc_cfg.len = chip->ecc.size + mtk_nand->fdm.ecc_size;
+
+	return 0;
+}
+
+static void mtk_nfc_select_chip(struct mtd_info *mtd, int chip)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct mtk_nfc *nfc = nand_get_controller_data(nand);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(nand);
+
+	if (chip < 0)
+		return;
+
+	mtk_nfc_hw_runtime_config(mtd);
+
+	nfi_writel(nfc, mtk_nand->sels[chip], NFI_CSEL);
+}
+
+static int mtk_nfc_dev_ready(struct mtd_info *mtd)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(mtd_to_nand(mtd));
+
+	if (nfi_readl(nfc, NFI_STA) & STA_BUSY)
+		return 0;
+
+	return 1;
+}
+
+static void mtk_nfc_cmd_ctrl(struct mtd_info *mtd, int dat, unsigned int ctrl)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(mtd_to_nand(mtd));
+
+	if (ctrl & NAND_ALE) {
+		mtk_nfc_send_address(nfc, dat);
+	} else if (ctrl & NAND_CLE) {
+		mtk_nfc_hw_reset(nfc);
+
+		nfi_writew(nfc, CNFG_OP_CUST, NFI_CNFG);
+		mtk_nfc_send_command(nfc, dat);
+	}
+}
+
+static inline void mtk_nfc_wait_ioready(struct mtk_nfc *nfc)
+{
+	int rc;
+	u8 val;
+
+	rc = readb_poll_timeout_atomic(nfc->regs + NFI_PIO_DIRDY, val,
+				       val & PIO_DI_RDY, 10, MTK_TIMEOUT);
+	if (rc < 0)
+		dev_err(nfc->dev, "data not ready\n");
+}
+
+static inline u8 mtk_nfc_read_byte(struct mtd_info *mtd)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	u32 reg;
+
+	/* after each byte read, the NFI_STA reg is reset by the hardware */
+	reg = nfi_readl(nfc, NFI_STA) & NFI_FSM_MASK;
+	if (reg != NFI_FSM_CUSTDATA) {
+		reg = nfi_readw(nfc, NFI_CNFG);
+		reg |= CNFG_BYTE_RW | CNFG_READ_EN;
+		nfi_writew(nfc, reg, NFI_CNFG);
+
+		/*
+		 * set to max sector to allow the HW to continue reading over
+		 * unaligned accesses
+		 */
+		reg = (MTK_MAX_SECTOR << CON_SEC_SHIFT) | CON_BRD;
+		nfi_writel(nfc, reg, NFI_CON);
+
+		/* trigger to fetch data */
+		nfi_writew(nfc, STAR_EN, NFI_STRDATA);
+	}
+
+	mtk_nfc_wait_ioready(nfc);
+
+	return nfi_readb(nfc, NFI_DATAR);
+}
+
+static void mtk_nfc_read_buf(struct mtd_info *mtd, u8 *buf, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		buf[i] = mtk_nfc_read_byte(mtd);
+}
+
+static void mtk_nfc_write_byte(struct mtd_info *mtd, u8 byte)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(mtd_to_nand(mtd));
+	u32 reg;
+
+	reg = nfi_readl(nfc, NFI_STA) & NFI_FSM_MASK;
+
+	if (reg != NFI_FSM_CUSTDATA) {
+		reg = nfi_readw(nfc, NFI_CNFG) | CNFG_BYTE_RW;
+		nfi_writew(nfc, reg, NFI_CNFG);
+
+		reg = MTK_MAX_SECTOR << CON_SEC_SHIFT | CON_BWR;
+		nfi_writel(nfc, reg, NFI_CON);
+
+		nfi_writew(nfc, STAR_EN, NFI_STRDATA);
+	}
+
+	mtk_nfc_wait_ioready(nfc);
+	nfi_writeb(nfc, byte, NFI_DATAW);
+}
+
+static void mtk_nfc_write_buf(struct mtd_info *mtd, const u8 *buf, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		mtk_nfc_write_byte(mtd, buf[i]);
+}
+
+static int mtk_nfc_sector_encode(struct nand_chip *chip, u8 *data)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	int size = chip->ecc.size + mtk_nand->fdm.reg_size;
+
+	nfc->ecc_cfg.mode = ECC_DMA_MODE;
+	nfc->ecc_cfg.op = ECC_ENCODE;
+
+	return mtk_ecc_encode(nfc->ecc, &nfc->ecc_cfg, data, size);
+}
+
+static void mtk_nfc_no_bad_mark_swap(struct mtd_info *a, u8 *b, int c)
+{
+	/* nop */
+}
+
+static void mtk_nfc_bad_mark_swap(struct mtd_info *mtd, u8 *buf, int raw)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtk_nfc_nand_chip *nand = to_mtk_nand(chip);
+	u32 bad_pos = nand->bad_mark.pos;
+
+	if (raw)
+		bad_pos += nand->bad_mark.sec * mtk_data_len(chip);
+	else
+		bad_pos += nand->bad_mark.sec * chip->ecc.size;
+
+	swap(chip->oob_poi[0], buf[bad_pos]);
+}
+
+static int mtk_nfc_format_subpage(struct mtd_info *mtd, u32 offset,
+				  u32 len, const u8 *buf)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_fdm *fdm = &mtk_nand->fdm;
+	u32 start, end;
+	int i, ret;
+
+	start = offset / chip->ecc.size;
+	end = DIV_ROUND_UP(offset + len, chip->ecc.size);
+
+	memset(nfc->buffer, 0xff, mtd->writesize + mtd->oobsize);
+	for (i = 0; i < chip->ecc.steps; i++) {
+		memcpy(mtk_data_ptr(chip, i), data_ptr(chip, buf, i),
+		       chip->ecc.size);
+
+		if (start > i || i >= end)
+			continue;
+
+		if (i == mtk_nand->bad_mark.sec)
+			mtk_nand->bad_mark.bm_swap(mtd, nfc->buffer, 1);
+
+		memcpy(mtk_oob_ptr(chip, i), oob_ptr(chip, i), fdm->reg_size);
+
+		/* program the CRC back to the OOB */
+		ret = mtk_nfc_sector_encode(chip, mtk_data_ptr(chip, i));
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void mtk_nfc_format_page(struct mtd_info *mtd, const u8 *buf)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_fdm *fdm = &mtk_nand->fdm;
+	u32 i;
+
+	memset(nfc->buffer, 0xff, mtd->writesize + mtd->oobsize);
+	for (i = 0; i < chip->ecc.steps; i++) {
+		if (buf)
+			memcpy(mtk_data_ptr(chip, i), data_ptr(chip, buf, i),
+			       chip->ecc.size);
+
+		if (i == mtk_nand->bad_mark.sec)
+			mtk_nand->bad_mark.bm_swap(mtd, nfc->buffer, 1);
+
+		memcpy(mtk_oob_ptr(chip, i), oob_ptr(chip, i), fdm->reg_size);
+	}
+}
+
+static inline void mtk_nfc_read_fdm(struct nand_chip *chip, u32 start,
+				    u32 sectors)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	struct mtk_nfc_fdm *fdm = &mtk_nand->fdm;
+	u32 vall, valm;
+	u8 *oobptr;
+	int i, j;
+
+	for (i = 0; i < sectors; i++) {
+		oobptr = oob_ptr(chip, start + i);
+		vall = nfi_readl(nfc, NFI_FDML(i));
+		valm = nfi_readl(nfc, NFI_FDMM(i));
+
+		for (j = 0; j < fdm->reg_size; j++)
+			oobptr[j] = (j >= 4 ? valm : vall) >> ((j % 4) * 8);
+	}
+}
+
+static inline void mtk_nfc_write_fdm(struct nand_chip *chip)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	struct mtk_nfc_fdm *fdm = &mtk_nand->fdm;
+	u32 vall, valm;
+	u8 *oobptr;
+	int i, j;
+
+	for (i = 0; i < chip->ecc.steps; i++) {
+		oobptr = oob_ptr(chip, i);
+		vall = 0;
+		valm = 0;
+		for (j = 0; j < 8; j++) {
+			if (j < 4)
+				vall |= (j < fdm->reg_size ? oobptr[j] : 0xff)
+						<< (j * 8);
+			else
+				valm |= (j < fdm->reg_size ? oobptr[j] : 0xff)
+						<< ((j - 4) * 8);
+		}
+		nfi_writel(nfc, vall, NFI_FDML(i));
+		nfi_writel(nfc, valm, NFI_FDMM(i));
+	}
+}
+
+static int mtk_nfc_do_write_page(struct mtd_info *mtd, struct nand_chip *chip,
+				 const u8 *buf, int page, int len)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct device *dev = nfc->dev;
+	dma_addr_t addr;
+	u32 reg;
+	int ret;
+
+	addr = dma_map_single(dev, (void *)buf, len, DMA_TO_DEVICE);
+	ret = dma_mapping_error(nfc->dev, addr);
+	if (ret) {
+		dev_err(nfc->dev, "dma mapping error\n");
+		return -EINVAL;
+	}
+
+	reg = nfi_readw(nfc, NFI_CNFG) | CNFG_AHB | CNFG_DMA_BURST_EN;
+	nfi_writew(nfc, reg, NFI_CNFG);
+
+	nfi_writel(nfc, chip->ecc.steps << CON_SEC_SHIFT, NFI_CON);
+	nfi_writel(nfc, lower_32_bits(addr), NFI_STRADDR);
+	nfi_writew(nfc, INTR_AHB_DONE_EN, NFI_INTR_EN);
+
+	init_completion(&nfc->done);
+
+	reg = nfi_readl(nfc, NFI_CON) | CON_BWR;
+	nfi_writel(nfc, reg, NFI_CON);
+	nfi_writew(nfc, STAR_EN, NFI_STRDATA);
+
+	ret = wait_for_completion_timeout(&nfc->done, msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(dev, "program ahb done timeout\n");
+		nfi_writew(nfc, 0, NFI_INTR_EN);
+		ret = -ETIMEDOUT;
+		goto timeout;
+	}
+
+	ret = readl_poll_timeout_atomic(nfc->regs + NFI_ADDRCNTR, reg,
+					(reg & CNTR_MASK) >= chip->ecc.steps,
+					10, MTK_TIMEOUT);
+	if (ret)
+		dev_err(dev, "hwecc write timeout\n");
+
+timeout:
+
+	dma_unmap_single(nfc->dev, addr, len, DMA_TO_DEVICE);
+	nfi_writel(nfc, 0, NFI_CON);
+
+	return ret;
+}
+
+static int mtk_nfc_write_page(struct mtd_info *mtd, struct nand_chip *chip,
+			      const u8 *buf, int page, int raw)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	size_t len;
+	const u8 *bufpoi;
+	u32 reg;
+	int ret;
+
+	if (!raw) {
+		/* OOB => FDM: from register,  ECC: from HW */
+		reg = nfi_readw(nfc, NFI_CNFG) | CNFG_AUTO_FMT_EN;
+		nfi_writew(nfc, reg | CNFG_HW_ECC_EN, NFI_CNFG);
+
+		nfc->ecc_cfg.op = ECC_ENCODE;
+		nfc->ecc_cfg.mode = ECC_NFI_MODE;
+		ret = mtk_ecc_enable(nfc->ecc, &nfc->ecc_cfg);
+		if (ret) {
+			/* clear NFI config */
+			reg = nfi_readw(nfc, NFI_CNFG);
+			reg &= ~(CNFG_AUTO_FMT_EN | CNFG_HW_ECC_EN);
+			nfi_writew(nfc, reg, NFI_CNFG);
+
+			return ret;
+		}
+
+		memcpy(nfc->buffer, buf, mtd->writesize);
+		mtk_nand->bad_mark.bm_swap(mtd, nfc->buffer, raw);
+		bufpoi = nfc->buffer;
+
+		/* write OOB into the FDM registers (OOB area in MTK NAND) */
+		mtk_nfc_write_fdm(chip);
+	} else {
+		bufpoi = buf;
+	}
+
+	len = mtd->writesize + (raw ? mtd->oobsize : 0);
+	ret = mtk_nfc_do_write_page(mtd, chip, bufpoi, page, len);
+
+	if (!raw)
+		mtk_ecc_disable(nfc->ecc);
+
+	return ret;
+}
+
+static int mtk_nfc_write_page_hwecc(struct mtd_info *mtd,
+				    struct nand_chip *chip, const u8 *buf,
+				    int oob_on, int page)
+{
+	return mtk_nfc_write_page(mtd, chip, buf, page, 0);
+}
+
+static int mtk_nfc_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+				  const u8 *buf, int oob_on, int pg)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+
+	mtk_nfc_format_page(mtd, buf);
+	return mtk_nfc_write_page(mtd, chip, nfc->buffer, pg, 1);
+}
+
+static int mtk_nfc_write_subpage_hwecc(struct mtd_info *mtd,
+				       struct nand_chip *chip, u32 offset,
+				       u32 data_len, const u8 *buf,
+				       int oob_on, int page)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	int ret;
+
+	ret = mtk_nfc_format_subpage(mtd, offset, data_len, buf);
+	if (ret < 0)
+		return ret;
+
+	/* use the data in the private buffer (now with FDM and CRC) */
+	return mtk_nfc_write_page(mtd, chip, nfc->buffer, page, 1);
+}
+
+static int mtk_nfc_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip,
+				 int page)
+{
+	int ret;
+
+	chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page);
+
+	ret = mtk_nfc_write_page_raw(mtd, chip, NULL, 1, page);
+	if (ret < 0)
+		return -EIO;
+
+	chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
+	ret = chip->waitfunc(mtd, chip);
+
+	return ret & NAND_STATUS_FAIL ? -EIO : 0;
+}
+
+static int mtk_nfc_update_ecc_stats(struct mtd_info *mtd, u8 *buf, u32 sectors)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	struct mtk_ecc_stats stats;
+	int rc, i;
+
+	rc = nfi_readl(nfc, NFI_STA) & STA_EMP_PAGE;
+	if (rc) {
+		memset(buf, 0xff, sectors * chip->ecc.size);
+		for (i = 0; i < sectors; i++)
+			memset(oob_ptr(chip, i), 0xff, mtk_nand->fdm.reg_size);
+		return 0;
+	}
+
+	mtk_ecc_get_stats(nfc->ecc, &stats, sectors);
+	mtd->ecc_stats.corrected += stats.corrected;
+	mtd->ecc_stats.failed += stats.failed;
+
+	return stats.bitflips;
+}
+
+static int mtk_nfc_read_subpage(struct mtd_info *mtd, struct nand_chip *chip,
+				u32 data_offs, u32 readlen,
+				u8 *bufpoi, int page, int raw)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	u32 spare = mtk_nand->spare_per_sector;
+	u32 column, sectors, start, end, reg;
+	dma_addr_t addr;
+	int bitflips;
+	size_t len;
+	u8 *buf;
+	int rc;
+
+	start = data_offs / chip->ecc.size;
+	end = DIV_ROUND_UP(data_offs + readlen, chip->ecc.size);
+
+	sectors = end - start;
+	column = start * (chip->ecc.size + spare);
+
+	len = sectors * chip->ecc.size + (raw ? sectors * spare : 0);
+	buf = bufpoi + start * chip->ecc.size;
+
+	if (column != 0)
+		chip->cmdfunc(mtd, NAND_CMD_RNDOUT, column, -1);
+
+	addr = dma_map_single(nfc->dev, buf, len, DMA_FROM_DEVICE);
+	rc = dma_mapping_error(nfc->dev, addr);
+	if (rc) {
+		dev_err(nfc->dev, "dma mapping error\n");
+
+		return -EINVAL;
+	}
+
+	reg = nfi_readw(nfc, NFI_CNFG);
+	reg |= CNFG_READ_EN | CNFG_DMA_BURST_EN | CNFG_AHB;
+	if (!raw) {
+		reg |= CNFG_AUTO_FMT_EN | CNFG_HW_ECC_EN;
+		nfi_writew(nfc, reg, NFI_CNFG);
+
+		nfc->ecc_cfg.mode = ECC_NFI_MODE;
+		nfc->ecc_cfg.sectors = sectors;
+		nfc->ecc_cfg.op = ECC_DECODE;
+		rc = mtk_ecc_enable(nfc->ecc, &nfc->ecc_cfg);
+		if (rc) {
+			dev_err(nfc->dev, "ecc enable\n");
+			/* clear NFI_CNFG */
+			reg &= ~(CNFG_DMA_BURST_EN | CNFG_AHB | CNFG_READ_EN |
+				CNFG_AUTO_FMT_EN | CNFG_HW_ECC_EN);
+			nfi_writew(nfc, reg, NFI_CNFG);
+			dma_unmap_single(nfc->dev, addr, len, DMA_FROM_DEVICE);
+
+			return rc;
+		}
+	} else {
+		nfi_writew(nfc, reg, NFI_CNFG);
+	}
+
+	nfi_writel(nfc, sectors << CON_SEC_SHIFT, NFI_CON);
+	nfi_writew(nfc, INTR_AHB_DONE_EN, NFI_INTR_EN);
+	nfi_writel(nfc, lower_32_bits(addr), NFI_STRADDR);
+
+	init_completion(&nfc->done);
+	reg = nfi_readl(nfc, NFI_CON) | CON_BRD;
+	nfi_writel(nfc, reg, NFI_CON);
+	nfi_writew(nfc, STAR_EN, NFI_STRDATA);
+
+	rc = wait_for_completion_timeout(&nfc->done, msecs_to_jiffies(500));
+	if (!rc)
+		dev_warn(nfc->dev, "read ahb/dma done timeout\n");
+
+	rc = readl_poll_timeout_atomic(nfc->regs + NFI_BYTELEN, reg,
+				       (reg & CNTR_MASK) >= sectors, 10,
+				       MTK_TIMEOUT);
+	if (rc < 0) {
+		dev_err(nfc->dev, "subpage done timeout\n");
+		bitflips = -EIO;
+	} else {
+		bitflips = 0;
+		if (!raw) {
+			rc = mtk_ecc_wait_done(nfc->ecc, ECC_DECODE);
+			bitflips = rc < 0 ? -ETIMEDOUT :
+				mtk_nfc_update_ecc_stats(mtd, buf, sectors);
+			mtk_nfc_read_fdm(chip, start, sectors);
+		}
+	}
+
+	dma_unmap_single(nfc->dev, addr, len, DMA_FROM_DEVICE);
+
+	if (raw)
+		goto done;
+
+	mtk_ecc_disable(nfc->ecc);
+
+	if (clamp(mtk_nand->bad_mark.sec, start, end) == mtk_nand->bad_mark.sec)
+		mtk_nand->bad_mark.bm_swap(mtd, bufpoi, raw);
+done:
+	nfi_writel(nfc, 0, NFI_CON);
+
+	return bitflips;
+}
+
+static int mtk_nfc_read_subpage_hwecc(struct mtd_info *mtd,
+				      struct nand_chip *chip, u32 off,
+				      u32 len, u8 *p, int pg)
+{
+	return mtk_nfc_read_subpage(mtd, chip, off, len, p, pg, 0);
+}
+
+static int mtk_nfc_read_page_hwecc(struct mtd_info *mtd,
+				   struct nand_chip *chip, u8 *p,
+				   int oob_on, int pg)
+{
+	return mtk_nfc_read_subpage(mtd, chip, 0, mtd->writesize, p, pg, 0);
+}
+
+static int mtk_nfc_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+				 u8 *buf, int oob_on, int page)
+{
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_fdm *fdm = &mtk_nand->fdm;
+	int i, ret;
+
+	memset(nfc->buffer, 0xff, mtd->writesize + mtd->oobsize);
+	ret = mtk_nfc_read_subpage(mtd, chip, 0, mtd->writesize, nfc->buffer,
+				   page, 1);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < chip->ecc.steps; i++) {
+		memcpy(oob_ptr(chip, i), mtk_oob_ptr(chip, i), fdm->reg_size);
+
+		if (i == mtk_nand->bad_mark.sec)
+			mtk_nand->bad_mark.bm_swap(mtd, nfc->buffer, 1);
+
+		if (buf)
+			memcpy(data_ptr(chip, buf, i), mtk_data_ptr(chip, i),
+			       chip->ecc.size);
+	}
+
+	return ret;
+}
+
+static int mtk_nfc_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip,
+				int page)
+{
+	chip->cmdfunc(mtd, NAND_CMD_READ0, 0, page);
+
+	return mtk_nfc_read_page_raw(mtd, chip, NULL, 1, page);
+}
+
+static inline void mtk_nfc_hw_init(struct mtk_nfc *nfc)
+{
+	/*
+	 * ACCON: access timing control register
+	 * -------------------------------------
+	 * 31:28: minimum required time for CS post pulling down after accessing
+	 *	the device
+	 * 27:22: minimum required time for CS pre pulling down before accessing
+	 *	the device
+	 * 21:16: minimum required time from NCEB low to NREB low
+	 * 15:12: minimum required time from NWEB high to NREB low.
+	 * 11:08: write enable hold time
+	 * 07:04: write wait states
+	 * 03:00: read wait states
+	 */
+	nfi_writel(nfc, 0x10804211, NFI_ACCCON);
+
+	/*
+	 * CNRNB: nand ready/busy register
+	 * -------------------------------
+	 * 7:4: timeout register for polling the NAND busy/ready signal
+	 * 0  : poll the status of the busy/ready signal after [7:4]*16 cycles.
+	 */
+	nfi_writew(nfc, 0xf1, NFI_CNRNB);
+	nfi_writew(nfc, PAGEFMT_8K_16K, NFI_PAGEFMT);
+
+	mtk_nfc_hw_reset(nfc);
+
+	nfi_readl(nfc, NFI_INTR_STA);
+	nfi_writel(nfc, 0, NFI_INTR_EN);
+}
+
+static irqreturn_t mtk_nfc_irq(int irq, void *id)
+{
+	struct mtk_nfc *nfc = id;
+	u16 sta, ien;
+
+	sta = nfi_readw(nfc, NFI_INTR_STA);
+	ien = nfi_readw(nfc, NFI_INTR_EN);
+
+	if (!(sta & ien))
+		return IRQ_NONE;
+
+	nfi_writew(nfc, ~sta & ien, NFI_INTR_EN);
+	complete(&nfc->done);
+
+	return IRQ_HANDLED;
+}
+
+static int mtk_nfc_enable_clk(struct device *dev, struct mtk_nfc_clk *clk)
+{
+	int ret;
+
+	ret = clk_prepare_enable(clk->nfi_clk);
+	if (ret) {
+		dev_err(dev, "failed to enable nfi clk\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(clk->pad_clk);
+	if (ret) {
+		dev_err(dev, "failed to enable pad clk\n");
+		clk_disable_unprepare(clk->nfi_clk);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void mtk_nfc_disable_clk(struct mtk_nfc_clk *clk)
+{
+	clk_disable_unprepare(clk->nfi_clk);
+	clk_disable_unprepare(clk->pad_clk);
+}
+
+static int mtk_nfc_ooblayout_free(struct mtd_info *mtd, int section,
+				  struct mtd_oob_region *oob_region)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	struct mtk_nfc_fdm *fdm = &mtk_nand->fdm;
+	u32 eccsteps;
+
+	eccsteps = mtd->writesize / chip->ecc.size;
+
+	if (section >= eccsteps)
+		return -ERANGE;
+
+	oob_region->length = fdm->reg_size - fdm->ecc_size;
+	oob_region->offset = section * fdm->reg_size + fdm->ecc_size;
+
+	return 0;
+}
+
+static int mtk_nfc_ooblayout_ecc(struct mtd_info *mtd, int section,
+				 struct mtd_oob_region *oob_region)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	u32 eccsteps;
+
+	if (section)
+		return -ERANGE;
+
+	eccsteps = mtd->writesize / chip->ecc.size;
+	oob_region->offset = mtk_nand->fdm.reg_size * eccsteps;
+	oob_region->length = mtd->oobsize - oob_region->offset;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops mtk_nfc_ooblayout_ops = {
+	.free = mtk_nfc_ooblayout_free,
+	.ecc = mtk_nfc_ooblayout_ecc,
+};
+
+static void mtk_nfc_set_fdm(struct mtk_nfc_fdm *fdm, struct mtd_info *mtd)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct mtk_nfc_nand_chip *chip = to_mtk_nand(nand);
+	u32 ecc_bytes;
+
+	ecc_bytes = DIV_ROUND_UP(nand->ecc.strength * ECC_PARITY_BITS, 8);
+
+	fdm->reg_size = chip->spare_per_sector - ecc_bytes;
+	if (fdm->reg_size > NFI_FDM_MAX_SIZE)
+		fdm->reg_size = NFI_FDM_MAX_SIZE;
+
+	/* bad block mark storage */
+	fdm->ecc_size = 1;
+}
+
+static void mtk_nfc_set_bad_mark_ctl(struct mtk_nfc_bad_mark_ctl *bm_ctl,
+				     struct mtd_info *mtd)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+
+	if (mtd->writesize == 512) {
+		bm_ctl->bm_swap = mtk_nfc_no_bad_mark_swap;
+	} else {
+		bm_ctl->bm_swap = mtk_nfc_bad_mark_swap;
+		bm_ctl->sec = mtd->writesize / mtk_data_len(nand);
+		bm_ctl->pos = mtd->writesize % mtk_data_len(nand);
+	}
+}
+
+static void mtk_nfc_set_spare_per_sector(u32 *sps, struct mtd_info *mtd)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	u32 spare[] = {16, 26, 27, 28, 32, 36, 40, 44,
+			48, 49, 50, 51, 52, 62, 63, 64};
+	u32 eccsteps, i;
+
+	eccsteps = mtd->writesize / nand->ecc.size;
+	*sps = mtd->oobsize / eccsteps;
+
+	if (nand->ecc.size == 1024)
+		*sps >>= 1;
+
+	for (i = 0; i < ARRAY_SIZE(spare); i++) {
+		if (*sps <= spare[i]) {
+			if (!i)
+				*sps = spare[i];
+			else if (*sps != spare[i])
+				*sps = spare[i - 1];
+			break;
+		}
+	}
+
+	if (i >= ARRAY_SIZE(spare))
+		*sps = spare[ARRAY_SIZE(spare) - 1];
+
+	if (nand->ecc.size == 1024)
+		*sps <<= 1;
+}
+
+static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	u32 spare;
+	int free;
+
+	/* support only ecc hw mode */
+	if (nand->ecc.mode != NAND_ECC_HW) {
+		dev_err(dev, "ecc.mode not supported\n");
+		return -EINVAL;
+	}
+
+	/* if optional dt settings not present */
+	if (!nand->ecc.size || !nand->ecc.strength) {
+		/* use datasheet requirements */
+		nand->ecc.strength = nand->ecc_strength_ds;
+		nand->ecc.size = nand->ecc_step_ds;
+
+		/*
+		 * align eccstrength and eccsize
+		 * this controller only supports 512 and 1024 sizes
+		 */
+		if (nand->ecc.size < 1024) {
+			if (mtd->writesize > 512) {
+				nand->ecc.size = 1024;
+				nand->ecc.strength <<= 1;
+			} else {
+				nand->ecc.size = 512;
+			}
+		} else {
+			nand->ecc.size = 1024;
+		}
+
+		mtk_nfc_set_spare_per_sector(&spare, mtd);
+
+		/* calculate oob bytes except ecc parity data */
+		free = ((nand->ecc.strength * ECC_PARITY_BITS) + 7) >> 3;
+		free = spare - free;
+
+		/*
+		 * enhance ecc strength if oob left is bigger than max FDM size
+		 * or reduce ecc strength if oob size is not enough for ecc
+		 * parity data.
+		 */
+		if (free > NFI_FDM_MAX_SIZE) {
+			spare -= NFI_FDM_MAX_SIZE;
+			nand->ecc.strength = (spare << 3) / ECC_PARITY_BITS;
+		} else if (free < 0) {
+			spare -= NFI_FDM_MIN_SIZE;
+			nand->ecc.strength = (spare << 3) / ECC_PARITY_BITS;
+		}
+	}
+
+	mtk_ecc_adjust_strength(&nand->ecc.strength);
+
+	dev_info(dev, "eccsize %d eccstrength %d\n",
+		 nand->ecc.size, nand->ecc.strength);
+
+	return 0;
+}
+
+static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
+				  struct device_node *np)
+{
+	struct mtk_nfc_nand_chip *chip;
+	struct nand_chip *nand;
+	struct mtd_info *mtd;
+	int nsels, len;
+	u32 tmp;
+	int ret;
+	int i;
+
+	if (!of_get_property(np, "reg", &nsels))
+		return -ENODEV;
+
+	nsels /= sizeof(u32);
+	if (!nsels || nsels > MTK_NAND_MAX_NSELS) {
+		dev_err(dev, "invalid reg property size %d\n", nsels);
+		return -EINVAL;
+	}
+
+	chip = devm_kzalloc(dev, sizeof(*chip) + nsels * sizeof(u8),
+			    GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->nsels = nsels;
+	for (i = 0; i < nsels; i++) {
+		ret = of_property_read_u32_index(np, "reg", i, &tmp);
+		if (ret) {
+			dev_err(dev, "reg property failure : %d\n", ret);
+			return ret;
+		}
+		chip->sels[i] = tmp;
+	}
+
+	nand = &chip->nand;
+	nand->controller = &nfc->controller;
+
+	nand_set_flash_node(nand, np);
+	nand_set_controller_data(nand, nfc);
+
+	nand->options |= NAND_USE_BOUNCE_BUFFER | NAND_SUBPAGE_READ;
+	nand->dev_ready = mtk_nfc_dev_ready;
+	nand->select_chip = mtk_nfc_select_chip;
+	nand->write_byte = mtk_nfc_write_byte;
+	nand->write_buf = mtk_nfc_write_buf;
+	nand->read_byte = mtk_nfc_read_byte;
+	nand->read_buf = mtk_nfc_read_buf;
+	nand->cmd_ctrl = mtk_nfc_cmd_ctrl;
+
+	/* set default mode in case dt entry is missing */
+	nand->ecc.mode = NAND_ECC_HW;
+
+	nand->ecc.write_subpage = mtk_nfc_write_subpage_hwecc;
+	nand->ecc.write_page_raw = mtk_nfc_write_page_raw;
+	nand->ecc.write_page = mtk_nfc_write_page_hwecc;
+	nand->ecc.write_oob_raw = mtk_nfc_write_oob_std;
+	nand->ecc.write_oob = mtk_nfc_write_oob_std;
+
+	nand->ecc.read_subpage = mtk_nfc_read_subpage_hwecc;
+	nand->ecc.read_page_raw = mtk_nfc_read_page_raw;
+	nand->ecc.read_page = mtk_nfc_read_page_hwecc;
+	nand->ecc.read_oob_raw = mtk_nfc_read_oob_std;
+	nand->ecc.read_oob = mtk_nfc_read_oob_std;
+
+	mtd = nand_to_mtd(nand);
+	mtd->owner = THIS_MODULE;
+	mtd->dev.parent = dev;
+	mtd->name = MTK_NAME;
+	mtd_set_ooblayout(mtd, &mtk_nfc_ooblayout_ops);
+
+	mtk_nfc_hw_init(nfc);
+
+	ret = nand_scan_ident(mtd, nsels, NULL);
+	if (ret)
+		return -ENODEV;
+
+	/* store bbt magic in page, cause OOB is not protected */
+	if (nand->bbt_options & NAND_BBT_USE_FLASH)
+		nand->bbt_options |= NAND_BBT_NO_OOB;
+
+	ret = mtk_nfc_ecc_init(dev, mtd);
+	if (ret)
+		return -EINVAL;
+
+	if (nand->options & NAND_BUSWIDTH_16) {
+		dev_err(dev, "16bits buswidth not supported");
+		return -EINVAL;
+	}
+
+	mtk_nfc_set_spare_per_sector(&chip->spare_per_sector, mtd);
+	mtk_nfc_set_fdm(&chip->fdm, mtd);
+	mtk_nfc_set_bad_mark_ctl(&chip->bad_mark, mtd);
+
+	len = mtd->writesize + mtd->oobsize;
+	nfc->buffer = devm_kzalloc(dev, len, GFP_KERNEL);
+	if (!nfc->buffer)
+		return  -ENOMEM;
+
+	ret = nand_scan_tail(mtd);
+	if (ret)
+		return -ENODEV;
+
+	ret = mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+	if (ret) {
+		dev_err(dev, "mtd parse partition error\n");
+		nand_release(mtd);
+		return ret;
+	}
+
+	list_add_tail(&chip->node, &nfc->chips);
+
+	return 0;
+}
+
+static int mtk_nfc_nand_chips_init(struct device *dev, struct mtk_nfc *nfc)
+{
+	struct device_node *np = dev->of_node;
+	struct device_node *nand_np;
+	int ret;
+
+	for_each_child_of_node(np, nand_np) {
+		ret = mtk_nfc_nand_chip_init(dev, nfc, nand_np);
+		if (ret) {
+			of_node_put(nand_np);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int mtk_nfc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct mtk_nfc *nfc;
+	struct resource *res;
+	int ret, irq;
+
+	nfc = devm_kzalloc(dev, sizeof(*nfc), GFP_KERNEL);
+	if (!nfc)
+		return -ENOMEM;
+
+	spin_lock_init(&nfc->controller.lock);
+	init_waitqueue_head(&nfc->controller.wq);
+	INIT_LIST_HEAD(&nfc->chips);
+
+	/* probe defer if not ready */
+	nfc->ecc = of_mtk_ecc_get(np);
+	if (IS_ERR(nfc->ecc))
+		return PTR_ERR(nfc->ecc);
+	else if (!nfc->ecc)
+		return -ENODEV;
+
+	nfc->dev = dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	nfc->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(nfc->regs)) {
+		ret = PTR_ERR(nfc->regs);
+		dev_err(dev, "no nfi base\n");
+		goto release_ecc;
+	}
+
+	nfc->clk.nfi_clk = devm_clk_get(dev, "nfi_clk");
+	if (IS_ERR(nfc->clk.nfi_clk)) {
+		dev_err(dev, "no clk\n");
+		ret = PTR_ERR(nfc->clk.nfi_clk);
+		goto release_ecc;
+	}
+
+	nfc->clk.pad_clk = devm_clk_get(dev, "pad_clk");
+	if (IS_ERR(nfc->clk.pad_clk)) {
+		dev_err(dev, "no pad clk\n");
+		ret = PTR_ERR(nfc->clk.pad_clk);
+		goto release_ecc;
+	}
+
+	ret = mtk_nfc_enable_clk(dev, &nfc->clk);
+	if (ret)
+		goto release_ecc;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "no nfi irq resource\n");
+		ret = -EINVAL;
+		goto clk_disable;
+	}
+
+	ret = devm_request_irq(dev, irq, mtk_nfc_irq, 0x0, "mtk-nand", nfc);
+	if (ret) {
+		dev_err(dev, "failed to request nfi irq\n");
+		goto clk_disable;
+	}
+
+	ret = dma_set_mask(dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(dev, "failed to set dma mask\n");
+		goto clk_disable;
+	}
+
+	platform_set_drvdata(pdev, nfc);
+
+	ret = mtk_nfc_nand_chips_init(dev, nfc);
+	if (ret) {
+		dev_err(dev, "failed to init nand chips\n");
+		goto clk_disable;
+	}
+
+	return 0;
+
+clk_disable:
+	mtk_nfc_disable_clk(&nfc->clk);
+
+release_ecc:
+	mtk_ecc_release(nfc->ecc);
+
+	return ret;
+}
+
+static int mtk_nfc_remove(struct platform_device *pdev)
+{
+	struct mtk_nfc *nfc = platform_get_drvdata(pdev);
+	struct mtk_nfc_nand_chip *chip;
+
+	while (!list_empty(&nfc->chips)) {
+		chip = list_first_entry(&nfc->chips, struct mtk_nfc_nand_chip,
+					node);
+		nand_release(nand_to_mtd(&chip->nand));
+		list_del(&chip->node);
+	}
+
+	mtk_ecc_release(nfc->ecc);
+	mtk_nfc_disable_clk(&nfc->clk);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int mtk_nfc_suspend(struct device *dev)
+{
+	struct mtk_nfc *nfc = dev_get_drvdata(dev);
+
+	mtk_nfc_disable_clk(&nfc->clk);
+
+	return 0;
+}
+
+static int mtk_nfc_resume(struct device *dev)
+{
+	struct mtk_nfc *nfc = dev_get_drvdata(dev);
+	struct mtk_nfc_nand_chip *chip;
+	struct nand_chip *nand;
+	struct mtd_info *mtd;
+	int ret;
+	u32 i;
+
+	udelay(200);
+
+	ret = mtk_nfc_enable_clk(dev, &nfc->clk);
+	if (ret)
+		return ret;
+
+	mtk_nfc_hw_init(nfc);
+
+	/* reset NAND chip if VCC was powered off */
+	list_for_each_entry(chip, &nfc->chips, node) {
+		nand = &chip->nand;
+		mtd = nand_to_mtd(nand);
+		for (i = 0; i < chip->nsels; i++) {
+			nand->select_chip(mtd, i);
+			nand->cmdfunc(mtd, NAND_CMD_RESET, -1, -1);
+		}
+	}
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(mtk_nfc_pm_ops, mtk_nfc_suspend, mtk_nfc_resume);
+#endif
+
+static const struct of_device_id mtk_nfc_id_table[] = {
+	{ .compatible = "mediatek,mt2701-nfc" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mtk_nfc_id_table);
+
+static struct platform_driver mtk_nfc_driver = {
+	.probe  = mtk_nfc_probe,
+	.remove = mtk_nfc_remove,
+	.driver = {
+		.name  = MTK_NAME,
+		.of_match_table = mtk_nfc_id_table,
+#ifdef CONFIG_PM_SLEEP
+		.pm = &mtk_nfc_pm_ops,
+#endif
+	},
+};
+
+module_platform_driver(mtk_nfc_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Xiaolei Li <xiaolei.li@mediatek.com>");
+MODULE_DESCRIPTION("MTK Nand Flash Controller Driver");
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 0b0dc29d2af7..77533f7f2429 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2610,7 +2610,7 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 		int cached = writelen > bytes && page != blockmask;
 		uint8_t *wbuf = buf;
 		int use_bufpoi;
-		int part_pagewr = (column || writelen < (mtd->writesize - 1));
+		int part_pagewr = (column || writelen < mtd->writesize);
 
 		if (part_pagewr)
 			use_bufpoi = 1;
diff --git a/drivers/mtd/nand/nand_ids.c b/drivers/mtd/nand/nand_ids.c
index ccc05f5b2695..2af9869a115e 100644
--- a/drivers/mtd/nand/nand_ids.c
+++ b/drivers/mtd/nand/nand_ids.c
@@ -168,6 +168,7 @@ struct nand_flash_dev nand_flash_ids[] = {
 /* Manufacturer IDs */
 struct nand_manufacturers nand_manuf_ids[] = {
 	{NAND_MFR_TOSHIBA, "Toshiba"},
+	{NAND_MFR_ESMT, "ESMT"},
 	{NAND_MFR_SAMSUNG, "Samsung"},
 	{NAND_MFR_FUJITSU, "Fujitsu"},
 	{NAND_MFR_NATIONAL, "National"},
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index a136da8df6fe..a59361c36f40 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -118,8 +118,6 @@
 #define	PREFETCH_STATUS_FIFO_CNT(val)	((val >> 24) & 0x7F)
 #define	STATUS_BUFF_EMPTY		0x00000001
 
-#define OMAP24XX_DMA_GPMC		4
-
 #define SECTOR_BYTES		512
 /* 4 bit padding to make byte aligned, 56 = 52 + 4 */
 #define BCH4_BIT_PAD		4
@@ -1811,7 +1809,6 @@ static int omap_nand_probe(struct platform_device *pdev)
 	struct nand_chip		*nand_chip;
 	int				err;
 	dma_cap_mask_t			mask;
-	unsigned			sig;
 	struct resource			*res;
 	struct device			*dev = &pdev->dev;
 	int				min_oobbytes = BADBLOCK_MARKER_LENGTH;
@@ -1924,11 +1921,11 @@ static int omap_nand_probe(struct platform_device *pdev)
 	case NAND_OMAP_PREFETCH_DMA:
 		dma_cap_zero(mask);
 		dma_cap_set(DMA_SLAVE, mask);
-		sig = OMAP24XX_DMA_GPMC;
-		info->dma = dma_request_channel(mask, omap_dma_filter_fn, &sig);
-		if (!info->dma) {
+		info->dma = dma_request_chan(pdev->dev.parent, "rxtx");
+
+		if (IS_ERR(info->dma)) {
 			dev_err(&pdev->dev, "DMA engine request failed\n");
-			err = -ENXIO;
+			err = PTR_ERR(info->dma);
 			goto return_error;
 		} else {
 			struct dma_slave_config cfg;
diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c
index a83a690688b4..e414b31b71c1 100644
--- a/drivers/mtd/nand/sunxi_nand.c
+++ b/drivers/mtd/nand/sunxi_nand.c
@@ -39,6 +39,7 @@
 #include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
+#include <linux/reset.h>
 
 #define NFC_REG_CTL		0x0000
 #define NFC_REG_ST		0x0004
@@ -153,6 +154,7 @@
 
 /* define bit use in NFC_ECC_ST */
 #define NFC_ECC_ERR(x)		BIT(x)
+#define NFC_ECC_ERR_MSK		GENMASK(15, 0)
 #define NFC_ECC_PAT_FOUND(x)	BIT(x + 16)
 #define NFC_ECC_ERR_CNT(b, x)	(((x) >> (((b) % 4) * 8)) & 0xff)
 
@@ -269,10 +271,12 @@ struct sunxi_nfc {
 	void __iomem *regs;
 	struct clk *ahb_clk;
 	struct clk *mod_clk;
+	struct reset_control *reset;
 	unsigned long assigned_cs;
 	unsigned long clk_rate;
 	struct list_head chips;
 	struct completion complete;
+	struct dma_chan *dmac;
 };
 
 static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_hw_control *ctrl)
@@ -365,6 +369,67 @@ static int sunxi_nfc_rst(struct sunxi_nfc *nfc)
 	return ret;
 }
 
+static int sunxi_nfc_dma_op_prepare(struct mtd_info *mtd, const void *buf,
+				    int chunksize, int nchunks,
+				    enum dma_data_direction ddir,
+				    struct scatterlist *sg)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
+	struct dma_async_tx_descriptor *dmad;
+	enum dma_transfer_direction tdir;
+	dma_cookie_t dmat;
+	int ret;
+
+	if (ddir == DMA_FROM_DEVICE)
+		tdir = DMA_DEV_TO_MEM;
+	else
+		tdir = DMA_MEM_TO_DEV;
+
+	sg_init_one(sg, buf, nchunks * chunksize);
+	ret = dma_map_sg(nfc->dev, sg, 1, ddir);
+	if (!ret)
+		return -ENOMEM;
+
+	dmad = dmaengine_prep_slave_sg(nfc->dmac, sg, 1, tdir, DMA_CTRL_ACK);
+	if (!dmad) {
+		ret = -EINVAL;
+		goto err_unmap_buf;
+	}
+
+	writel(readl(nfc->regs + NFC_REG_CTL) | NFC_RAM_METHOD,
+	       nfc->regs + NFC_REG_CTL);
+	writel(nchunks, nfc->regs + NFC_REG_SECTOR_NUM);
+	writel(chunksize, nfc->regs + NFC_REG_CNT);
+	dmat = dmaengine_submit(dmad);
+
+	ret = dma_submit_error(dmat);
+	if (ret)
+		goto err_clr_dma_flag;
+
+	return 0;
+
+err_clr_dma_flag:
+	writel(readl(nfc->regs + NFC_REG_CTL) & ~NFC_RAM_METHOD,
+	       nfc->regs + NFC_REG_CTL);
+
+err_unmap_buf:
+	dma_unmap_sg(nfc->dev, sg, 1, ddir);
+	return ret;
+}
+
+static void sunxi_nfc_dma_op_cleanup(struct mtd_info *mtd,
+				     enum dma_data_direction ddir,
+				     struct scatterlist *sg)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
+
+	dma_unmap_sg(nfc->dev, sg, 1, ddir);
+	writel(readl(nfc->regs + NFC_REG_CTL) & ~NFC_RAM_METHOD,
+	       nfc->regs + NFC_REG_CTL);
+}
+
 static int sunxi_nfc_dev_ready(struct mtd_info *mtd)
 {
 	struct nand_chip *nand = mtd_to_nand(mtd);
@@ -822,17 +887,15 @@ static void sunxi_nfc_hw_ecc_update_stats(struct mtd_info *mtd,
 }
 
 static int sunxi_nfc_hw_ecc_correct(struct mtd_info *mtd, u8 *data, u8 *oob,
-				    int step, bool *erased)
+				    int step, u32 status, bool *erased)
 {
 	struct nand_chip *nand = mtd_to_nand(mtd);
 	struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
 	struct nand_ecc_ctrl *ecc = &nand->ecc;
-	u32 status, tmp;
+	u32 tmp;
 
 	*erased = false;
 
-	status = readl(nfc->regs + NFC_REG_ECC_ST);
-
 	if (status & NFC_ECC_ERR(step))
 		return -EBADMSG;
 
@@ -898,6 +961,7 @@ static int sunxi_nfc_hw_ecc_read_chunk(struct mtd_info *mtd,
 	*cur_off = oob_off + ecc->bytes + 4;
 
 	ret = sunxi_nfc_hw_ecc_correct(mtd, data, oob_required ? oob : NULL, 0,
+				       readl(nfc->regs + NFC_REG_ECC_ST),
 				       &erased);
 	if (erased)
 		return 1;
@@ -967,6 +1031,130 @@ static void sunxi_nfc_hw_ecc_read_extra_oob(struct mtd_info *mtd,
 		*cur_off = mtd->oobsize + mtd->writesize;
 }
 
+static int sunxi_nfc_hw_ecc_read_chunks_dma(struct mtd_info *mtd, uint8_t *buf,
+					    int oob_required, int page,
+					    int nchunks)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	bool randomized = nand->options & NAND_NEED_SCRAMBLING;
+	struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
+	struct nand_ecc_ctrl *ecc = &nand->ecc;
+	unsigned int max_bitflips = 0;
+	int ret, i, raw_mode = 0;
+	struct scatterlist sg;
+	u32 status;
+
+	ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
+	if (ret)
+		return ret;
+
+	ret = sunxi_nfc_dma_op_prepare(mtd, buf, ecc->size, nchunks,
+				       DMA_FROM_DEVICE, &sg);
+	if (ret)
+		return ret;
+
+	sunxi_nfc_hw_ecc_enable(mtd);
+	sunxi_nfc_randomizer_config(mtd, page, false);
+	sunxi_nfc_randomizer_enable(mtd);
+
+	writel((NAND_CMD_RNDOUTSTART << 16) | (NAND_CMD_RNDOUT << 8) |
+	       NAND_CMD_READSTART, nfc->regs + NFC_REG_RCMD_SET);
+
+	dma_async_issue_pending(nfc->dmac);
+
+	writel(NFC_PAGE_OP | NFC_DATA_SWAP_METHOD | NFC_DATA_TRANS,
+	       nfc->regs + NFC_REG_CMD);
+
+	ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+	if (ret)
+		dmaengine_terminate_all(nfc->dmac);
+
+	sunxi_nfc_randomizer_disable(mtd);
+	sunxi_nfc_hw_ecc_disable(mtd);
+
+	sunxi_nfc_dma_op_cleanup(mtd, DMA_FROM_DEVICE, &sg);
+
+	if (ret)
+		return ret;
+
+	status = readl(nfc->regs + NFC_REG_ECC_ST);
+
+	for (i = 0; i < nchunks; i++) {
+		int data_off = i * ecc->size;
+		int oob_off = i * (ecc->bytes + 4);
+		u8 *data = buf + data_off;
+		u8 *oob = nand->oob_poi + oob_off;
+		bool erased;
+
+		ret = sunxi_nfc_hw_ecc_correct(mtd, randomized ? data : NULL,
+					       oob_required ? oob : NULL,
+					       i, status, &erased);
+
+		/* ECC errors are handled in the second loop. */
+		if (ret < 0)
+			continue;
+
+		if (oob_required && !erased) {
+			/* TODO: use DMA to retrieve OOB */
+			nand->cmdfunc(mtd, NAND_CMD_RNDOUT,
+				      mtd->writesize + oob_off, -1);
+			nand->read_buf(mtd, oob, ecc->bytes + 4);
+
+			sunxi_nfc_hw_ecc_get_prot_oob_bytes(mtd, oob, i,
+							    !i, page);
+		}
+
+		if (erased)
+			raw_mode = 1;
+
+		sunxi_nfc_hw_ecc_update_stats(mtd, &max_bitflips, ret);
+	}
+
+	if (status & NFC_ECC_ERR_MSK) {
+		for (i = 0; i < nchunks; i++) {
+			int data_off = i * ecc->size;
+			int oob_off = i * (ecc->bytes + 4);
+			u8 *data = buf + data_off;
+			u8 *oob = nand->oob_poi + oob_off;
+
+			if (!(status & NFC_ECC_ERR(i)))
+				continue;
+
+			/*
+			 * Re-read the data with the randomizer disabled to
+			 * identify bitflips in erased pages.
+			 */
+			if (randomized) {
+				/* TODO: use DMA to read page in raw mode */
+				nand->cmdfunc(mtd, NAND_CMD_RNDOUT,
+					      data_off, -1);
+				nand->read_buf(mtd, data, ecc->size);
+			}
+
+			/* TODO: use DMA to retrieve OOB */
+			nand->cmdfunc(mtd, NAND_CMD_RNDOUT,
+				      mtd->writesize + oob_off, -1);
+			nand->read_buf(mtd, oob, ecc->bytes + 4);
+
+			ret = nand_check_erased_ecc_chunk(data,	ecc->size,
+							  oob, ecc->bytes + 4,
+							  NULL, 0,
+							  ecc->strength);
+			if (ret >= 0)
+				raw_mode = 1;
+
+			sunxi_nfc_hw_ecc_update_stats(mtd, &max_bitflips, ret);
+		}
+	}
+
+	if (oob_required)
+		sunxi_nfc_hw_ecc_read_extra_oob(mtd, nand->oob_poi,
+						NULL, !raw_mode,
+						page);
+
+	return max_bitflips;
+}
+
 static int sunxi_nfc_hw_ecc_write_chunk(struct mtd_info *mtd,
 					const u8 *data, int data_off,
 					const u8 *oob, int oob_off,
@@ -1065,6 +1253,23 @@ static int sunxi_nfc_hw_ecc_read_page(struct mtd_info *mtd,
 	return max_bitflips;
 }
 
+static int sunxi_nfc_hw_ecc_read_page_dma(struct mtd_info *mtd,
+					  struct nand_chip *chip, u8 *buf,
+					  int oob_required, int page)
+{
+	int ret;
+
+	ret = sunxi_nfc_hw_ecc_read_chunks_dma(mtd, buf, oob_required, page,
+					       chip->ecc.steps);
+	if (ret >= 0)
+		return ret;
+
+	/* Fallback to PIO mode */
+	chip->cmdfunc(mtd, NAND_CMD_RNDOUT, 0, -1);
+
+	return sunxi_nfc_hw_ecc_read_page(mtd, chip, buf, oob_required, page);
+}
+
 static int sunxi_nfc_hw_ecc_read_subpage(struct mtd_info *mtd,
 					 struct nand_chip *chip,
 					 u32 data_offs, u32 readlen,
@@ -1098,6 +1303,25 @@ static int sunxi_nfc_hw_ecc_read_subpage(struct mtd_info *mtd,
 	return max_bitflips;
 }
 
+static int sunxi_nfc_hw_ecc_read_subpage_dma(struct mtd_info *mtd,
+					     struct nand_chip *chip,
+					     u32 data_offs, u32 readlen,
+					     u8 *buf, int page)
+{
+	int nchunks = DIV_ROUND_UP(data_offs + readlen, chip->ecc.size);
+	int ret;
+
+	ret = sunxi_nfc_hw_ecc_read_chunks_dma(mtd, buf, false, page, nchunks);
+	if (ret >= 0)
+		return ret;
+
+	/* Fallback to PIO mode */
+	chip->cmdfunc(mtd, NAND_CMD_RNDOUT, 0, -1);
+
+	return sunxi_nfc_hw_ecc_read_subpage(mtd, chip, data_offs, readlen,
+					     buf, page);
+}
+
 static int sunxi_nfc_hw_ecc_write_page(struct mtd_info *mtd,
 				       struct nand_chip *chip,
 				       const uint8_t *buf, int oob_required,
@@ -1130,6 +1354,99 @@ static int sunxi_nfc_hw_ecc_write_page(struct mtd_info *mtd,
 	return 0;
 }
 
+static int sunxi_nfc_hw_ecc_write_subpage(struct mtd_info *mtd,
+					  struct nand_chip *chip,
+					  u32 data_offs, u32 data_len,
+					  const u8 *buf, int oob_required,
+					  int page)
+{
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	int ret, i, cur_off = 0;
+
+	sunxi_nfc_hw_ecc_enable(mtd);
+
+	for (i = data_offs / ecc->size;
+	     i < DIV_ROUND_UP(data_offs + data_len, ecc->size); i++) {
+		int data_off = i * ecc->size;
+		int oob_off = i * (ecc->bytes + 4);
+		const u8 *data = buf + data_off;
+		const u8 *oob = chip->oob_poi + oob_off;
+
+		ret = sunxi_nfc_hw_ecc_write_chunk(mtd, data, data_off, oob,
+						   oob_off + mtd->writesize,
+						   &cur_off, !i, page);
+		if (ret)
+			return ret;
+	}
+
+	sunxi_nfc_hw_ecc_disable(mtd);
+
+	return 0;
+}
+
+static int sunxi_nfc_hw_ecc_write_page_dma(struct mtd_info *mtd,
+					   struct nand_chip *chip,
+					   const u8 *buf,
+					   int oob_required,
+					   int page)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
+	struct nand_ecc_ctrl *ecc = &nand->ecc;
+	struct scatterlist sg;
+	int ret, i;
+
+	ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
+	if (ret)
+		return ret;
+
+	ret = sunxi_nfc_dma_op_prepare(mtd, buf, ecc->size, ecc->steps,
+				       DMA_TO_DEVICE, &sg);
+	if (ret)
+		goto pio_fallback;
+
+	for (i = 0; i < ecc->steps; i++) {
+		const u8 *oob = nand->oob_poi + (i * (ecc->bytes + 4));
+
+		sunxi_nfc_hw_ecc_set_prot_oob_bytes(mtd, oob, i, !i, page);
+	}
+
+	sunxi_nfc_hw_ecc_enable(mtd);
+	sunxi_nfc_randomizer_config(mtd, page, false);
+	sunxi_nfc_randomizer_enable(mtd);
+
+	writel((NAND_CMD_RNDIN << 8) | NAND_CMD_PAGEPROG,
+	       nfc->regs + NFC_REG_RCMD_SET);
+
+	dma_async_issue_pending(nfc->dmac);
+
+	writel(NFC_PAGE_OP | NFC_DATA_SWAP_METHOD |
+	       NFC_DATA_TRANS | NFC_ACCESS_DIR,
+	       nfc->regs + NFC_REG_CMD);
+
+	ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+	if (ret)
+		dmaengine_terminate_all(nfc->dmac);
+
+	sunxi_nfc_randomizer_disable(mtd);
+	sunxi_nfc_hw_ecc_disable(mtd);
+
+	sunxi_nfc_dma_op_cleanup(mtd, DMA_TO_DEVICE, &sg);
+
+	if (ret)
+		return ret;
+
+	if (oob_required || (chip->options & NAND_NEED_SCRAMBLING))
+		/* TODO: use DMA to transfer extra OOB bytes ? */
+		sunxi_nfc_hw_ecc_write_extra_oob(mtd, chip->oob_poi,
+						 NULL, page);
+
+	return 0;
+
+pio_fallback:
+	return sunxi_nfc_hw_ecc_write_page(mtd, chip, buf, oob_required, page);
+}
+
 static int sunxi_nfc_hw_syndrome_ecc_read_page(struct mtd_info *mtd,
 					       struct nand_chip *chip,
 					       uint8_t *buf, int oob_required,
@@ -1497,10 +1814,19 @@ static int sunxi_nand_hw_common_ecc_ctrl_init(struct mtd_info *mtd,
 	int ret;
 	int i;
 
+	if (ecc->size != 512 && ecc->size != 1024)
+		return -EINVAL;
+
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
+	/* Prefer 1k ECC chunk over 512 ones */
+	if (ecc->size == 512 && mtd->writesize > 512) {
+		ecc->size = 1024;
+		ecc->strength *= 2;
+	}
+
 	/* Add ECC info retrieval from DT */
 	for (i = 0; i < ARRAY_SIZE(strengths); i++) {
 		if (ecc->strength <= strengths[i])
@@ -1550,14 +1876,28 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct mtd_info *mtd,
 				       struct nand_ecc_ctrl *ecc,
 				       struct device_node *np)
 {
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct sunxi_nand_chip *sunxi_nand = to_sunxi_nand(nand);
+	struct sunxi_nfc *nfc = to_sunxi_nfc(sunxi_nand->nand.controller);
 	int ret;
 
 	ret = sunxi_nand_hw_common_ecc_ctrl_init(mtd, ecc, np);
 	if (ret)
 		return ret;
 
-	ecc->read_page = sunxi_nfc_hw_ecc_read_page;
-	ecc->write_page = sunxi_nfc_hw_ecc_write_page;
+	if (nfc->dmac) {
+		ecc->read_page = sunxi_nfc_hw_ecc_read_page_dma;
+		ecc->read_subpage = sunxi_nfc_hw_ecc_read_subpage_dma;
+		ecc->write_page = sunxi_nfc_hw_ecc_write_page_dma;
+		nand->options |= NAND_USE_BOUNCE_BUFFER;
+	} else {
+		ecc->read_page = sunxi_nfc_hw_ecc_read_page;
+		ecc->read_subpage = sunxi_nfc_hw_ecc_read_subpage;
+		ecc->write_page = sunxi_nfc_hw_ecc_write_page;
+	}
+
+	/* TODO: support DMA for raw accesses and subpage write */
+	ecc->write_subpage = sunxi_nfc_hw_ecc_write_subpage;
 	ecc->read_oob_raw = nand_read_oob_std;
 	ecc->write_oob_raw = nand_write_oob_std;
 	ecc->read_subpage = sunxi_nfc_hw_ecc_read_subpage;
@@ -1871,26 +2211,59 @@ static int sunxi_nfc_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_ahb_clk_unprepare;
 
+	nfc->reset = devm_reset_control_get_optional(dev, "ahb");
+	if (!IS_ERR(nfc->reset)) {
+		ret = reset_control_deassert(nfc->reset);
+		if (ret) {
+			dev_err(dev, "reset err %d\n", ret);
+			goto out_mod_clk_unprepare;
+		}
+	} else if (PTR_ERR(nfc->reset) != -ENOENT) {
+		ret = PTR_ERR(nfc->reset);
+		goto out_mod_clk_unprepare;
+	}
+
 	ret = sunxi_nfc_rst(nfc);
 	if (ret)
-		goto out_mod_clk_unprepare;
+		goto out_ahb_reset_reassert;
 
 	writel(0, nfc->regs + NFC_REG_INT);
 	ret = devm_request_irq(dev, irq, sunxi_nfc_interrupt,
 			       0, "sunxi-nand", nfc);
 	if (ret)
-		goto out_mod_clk_unprepare;
+		goto out_ahb_reset_reassert;
+
+	nfc->dmac = dma_request_slave_channel(dev, "rxtx");
+	if (nfc->dmac) {
+		struct dma_slave_config dmac_cfg = { };
+
+		dmac_cfg.src_addr = r->start + NFC_REG_IO_DATA;
+		dmac_cfg.dst_addr = dmac_cfg.src_addr;
+		dmac_cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dmac_cfg.dst_addr_width = dmac_cfg.src_addr_width;
+		dmac_cfg.src_maxburst = 4;
+		dmac_cfg.dst_maxburst = 4;
+		dmaengine_slave_config(nfc->dmac, &dmac_cfg);
+	} else {
+		dev_warn(dev, "failed to request rxtx DMA channel\n");
+	}
 
 	platform_set_drvdata(pdev, nfc);
 
 	ret = sunxi_nand_chips_init(dev, nfc);
 	if (ret) {
 		dev_err(dev, "failed to init nand chips\n");
-		goto out_mod_clk_unprepare;
+		goto out_release_dmac;
 	}
 
 	return 0;
 
+out_release_dmac:
+	if (nfc->dmac)
+		dma_release_channel(nfc->dmac);
+out_ahb_reset_reassert:
+	if (!IS_ERR(nfc->reset))
+		reset_control_assert(nfc->reset);
 out_mod_clk_unprepare:
 	clk_disable_unprepare(nfc->mod_clk);
 out_ahb_clk_unprepare:
@@ -1904,6 +2277,12 @@ static int sunxi_nfc_remove(struct platform_device *pdev)
 	struct sunxi_nfc *nfc = platform_get_drvdata(pdev);
 
 	sunxi_nand_chips_cleanup(nfc);
+
+	if (!IS_ERR(nfc->reset))
+		reset_control_assert(nfc->reset);
+
+	if (nfc->dmac)
+		dma_release_channel(nfc->dmac);
 	clk_disable_unprepare(nfc->mod_clk);
 	clk_disable_unprepare(nfc->ahb_clk);
 
diff --git a/drivers/mtd/nand/xway_nand.c b/drivers/mtd/nand/xway_nand.c
index 0cf0ac07a8c2..1f2948c0c458 100644
--- a/drivers/mtd/nand/xway_nand.c
+++ b/drivers/mtd/nand/xway_nand.c
@@ -4,6 +4,7 @@
  *  by the Free Software Foundation.
  *
  *  Copyright © 2012 John Crispin <blogic@openwrt.org>
+ *  Copyright © 2016 Hauke Mehrtens <hauke@hauke-m.de>
  */
 
 #include <linux/mtd/nand.h>
@@ -16,20 +17,28 @@
 #define EBU_ADDSEL1		0x24
 #define EBU_NAND_CON		0xB0
 #define EBU_NAND_WAIT		0xB4
+#define  NAND_WAIT_RD		BIT(0) /* NAND flash status output */
+#define  NAND_WAIT_WR_C		BIT(3) /* NAND Write/Read complete */
 #define EBU_NAND_ECC0		0xB8
 #define EBU_NAND_ECC_AC		0xBC
 
-/* nand commands */
-#define NAND_CMD_ALE		(1 << 2)
-#define NAND_CMD_CLE		(1 << 3)
-#define NAND_CMD_CS		(1 << 4)
-#define NAND_WRITE_CMD_RESET	0xff
+/*
+ * nand commands
+ * The pins of the NAND chip are selected based on the address bits of the
+ * "register" read and write. There are no special registers, but an
+ * address range and the lower address bits are used to activate the
+ * correct line. For example when the bit (1 << 2) is set in the address
+ * the ALE pin will be activated.
+ */
+#define NAND_CMD_ALE		BIT(2) /* address latch enable */
+#define NAND_CMD_CLE		BIT(3) /* command latch enable */
+#define NAND_CMD_CS		BIT(4) /* chip select */
+#define NAND_CMD_SE		BIT(5) /* spare area access latch */
+#define NAND_CMD_WP		BIT(6) /* write protect */
 #define NAND_WRITE_CMD		(NAND_CMD_CS | NAND_CMD_CLE)
 #define NAND_WRITE_ADDR		(NAND_CMD_CS | NAND_CMD_ALE)
 #define NAND_WRITE_DATA		(NAND_CMD_CS)
 #define NAND_READ_DATA		(NAND_CMD_CS)
-#define NAND_WAIT_WR_C		(1 << 3)
-#define NAND_WAIT_RD		(0x1)
 
 /* we need to tel the ebu which addr we mapped the nand to */
 #define ADDSEL1_MASK(x)		(x << 4)
@@ -54,31 +63,41 @@
 #define NAND_CON_CSMUX		(1 << 1)
 #define NAND_CON_NANDM		1
 
-static void xway_reset_chip(struct nand_chip *chip)
+struct xway_nand_data {
+	struct nand_chip	chip;
+	unsigned long		csflags;
+	void __iomem		*nandaddr;
+};
+
+static u8 xway_readb(struct mtd_info *mtd, int op)
 {
-	unsigned long nandaddr = (unsigned long) chip->IO_ADDR_W;
-	unsigned long flags;
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct xway_nand_data *data = nand_get_controller_data(chip);
 
-	nandaddr &= ~NAND_WRITE_ADDR;
-	nandaddr |= NAND_WRITE_CMD;
+	return readb(data->nandaddr + op);
+}
 
-	/* finish with a reset */
-	spin_lock_irqsave(&ebu_lock, flags);
-	writeb(NAND_WRITE_CMD_RESET, (void __iomem *) nandaddr);
-	while ((ltq_ebu_r32(EBU_NAND_WAIT) & NAND_WAIT_WR_C) == 0)
-		;
-	spin_unlock_irqrestore(&ebu_lock, flags);
+static void xway_writeb(struct mtd_info *mtd, int op, u8 value)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct xway_nand_data *data = nand_get_controller_data(chip);
+
+	writeb(value, data->nandaddr + op);
 }
 
-static void xway_select_chip(struct mtd_info *mtd, int chip)
+static void xway_select_chip(struct mtd_info *mtd, int select)
 {
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct xway_nand_data *data = nand_get_controller_data(chip);
 
-	switch (chip) {
+	switch (select) {
 	case -1:
 		ltq_ebu_w32_mask(NAND_CON_CE, 0, EBU_NAND_CON);
 		ltq_ebu_w32_mask(NAND_CON_NANDM, 0, EBU_NAND_CON);
+		spin_unlock_irqrestore(&ebu_lock, data->csflags);
 		break;
 	case 0:
+		spin_lock_irqsave(&ebu_lock, data->csflags);
 		ltq_ebu_w32_mask(0, NAND_CON_NANDM, EBU_NAND_CON);
 		ltq_ebu_w32_mask(0, NAND_CON_CE, EBU_NAND_CON);
 		break;
@@ -89,26 +108,16 @@ static void xway_select_chip(struct mtd_info *mtd, int chip)
 
 static void xway_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
 {
-	struct nand_chip *this = mtd_to_nand(mtd);
-	unsigned long nandaddr = (unsigned long) this->IO_ADDR_W;
-	unsigned long flags;
-
-	if (ctrl & NAND_CTRL_CHANGE) {
-		nandaddr &= ~(NAND_WRITE_CMD | NAND_WRITE_ADDR);
-		if (ctrl & NAND_CLE)
-			nandaddr |= NAND_WRITE_CMD;
-		else
-			nandaddr |= NAND_WRITE_ADDR;
-		this->IO_ADDR_W = (void __iomem *) nandaddr;
-	}
+	if (cmd == NAND_CMD_NONE)
+		return;
 
-	if (cmd != NAND_CMD_NONE) {
-		spin_lock_irqsave(&ebu_lock, flags);
-		writeb(cmd, this->IO_ADDR_W);
-		while ((ltq_ebu_r32(EBU_NAND_WAIT) & NAND_WAIT_WR_C) == 0)
-			;
-		spin_unlock_irqrestore(&ebu_lock, flags);
-	}
+	if (ctrl & NAND_CLE)
+		xway_writeb(mtd, NAND_WRITE_CMD, cmd);
+	else if (ctrl & NAND_ALE)
+		xway_writeb(mtd, NAND_WRITE_ADDR, cmd);
+
+	while ((ltq_ebu_r32(EBU_NAND_WAIT) & NAND_WAIT_WR_C) == 0)
+		;
 }
 
 static int xway_dev_ready(struct mtd_info *mtd)
@@ -118,80 +127,122 @@ static int xway_dev_ready(struct mtd_info *mtd)
 
 static unsigned char xway_read_byte(struct mtd_info *mtd)
 {
-	struct nand_chip *this = mtd_to_nand(mtd);
-	unsigned long nandaddr = (unsigned long) this->IO_ADDR_R;
-	unsigned long flags;
-	int ret;
+	return xway_readb(mtd, NAND_READ_DATA);
+}
+
+static void xway_read_buf(struct mtd_info *mtd, u_char *buf, int len)
+{
+	int i;
 
-	spin_lock_irqsave(&ebu_lock, flags);
-	ret = ltq_r8((void __iomem *)(nandaddr + NAND_READ_DATA));
-	spin_unlock_irqrestore(&ebu_lock, flags);
+	for (i = 0; i < len; i++)
+		buf[i] = xway_readb(mtd, NAND_WRITE_DATA);
+}
 
-	return ret;
+static void xway_write_buf(struct mtd_info *mtd, const u_char *buf, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		xway_writeb(mtd, NAND_WRITE_DATA, buf[i]);
 }
 
+/*
+ * Probe for the NAND device.
+ */
 static int xway_nand_probe(struct platform_device *pdev)
 {
-	struct nand_chip *this = platform_get_drvdata(pdev);
-	unsigned long nandaddr = (unsigned long) this->IO_ADDR_W;
-	const __be32 *cs = of_get_property(pdev->dev.of_node,
-					"lantiq,cs", NULL);
+	struct xway_nand_data *data;
+	struct mtd_info *mtd;
+	struct resource *res;
+	int err;
+	u32 cs;
 	u32 cs_flag = 0;
 
+	/* Allocate memory for the device structure (and zero it) */
+	data = devm_kzalloc(&pdev->dev, sizeof(struct xway_nand_data),
+			    GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->nandaddr = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(data->nandaddr))
+		return PTR_ERR(data->nandaddr);
+
+	nand_set_flash_node(&data->chip, pdev->dev.of_node);
+	mtd = nand_to_mtd(&data->chip);
+	mtd->dev.parent = &pdev->dev;
+
+	data->chip.cmd_ctrl = xway_cmd_ctrl;
+	data->chip.dev_ready = xway_dev_ready;
+	data->chip.select_chip = xway_select_chip;
+	data->chip.write_buf = xway_write_buf;
+	data->chip.read_buf = xway_read_buf;
+	data->chip.read_byte = xway_read_byte;
+	data->chip.chip_delay = 30;
+
+	data->chip.ecc.mode = NAND_ECC_SOFT;
+	data->chip.ecc.algo = NAND_ECC_HAMMING;
+
+	platform_set_drvdata(pdev, data);
+	nand_set_controller_data(&data->chip, data);
+
 	/* load our CS from the DT. Either we find a valid 1 or default to 0 */
-	if (cs && (*cs == 1))
+	err = of_property_read_u32(pdev->dev.of_node, "lantiq,cs", &cs);
+	if (!err && cs == 1)
 		cs_flag = NAND_CON_IN_CS1 | NAND_CON_OUT_CS1;
 
 	/* setup the EBU to run in NAND mode on our base addr */
-	ltq_ebu_w32(CPHYSADDR(nandaddr)
-		| ADDSEL1_MASK(3) | ADDSEL1_REGEN, EBU_ADDSEL1);
+	ltq_ebu_w32(CPHYSADDR(data->nandaddr)
+		    | ADDSEL1_MASK(3) | ADDSEL1_REGEN, EBU_ADDSEL1);
 
 	ltq_ebu_w32(BUSCON1_SETUP | BUSCON1_BCGEN_RES | BUSCON1_WAITWRC2
-		| BUSCON1_WAITRDC2 | BUSCON1_HOLDC1 | BUSCON1_RECOVC1
-		| BUSCON1_CMULT4, LTQ_EBU_BUSCON1);
+		    | BUSCON1_WAITRDC2 | BUSCON1_HOLDC1 | BUSCON1_RECOVC1
+		    | BUSCON1_CMULT4, LTQ_EBU_BUSCON1);
 
 	ltq_ebu_w32(NAND_CON_NANDM | NAND_CON_CSMUX | NAND_CON_CS_P
-		| NAND_CON_SE_P | NAND_CON_WP_P | NAND_CON_PRE_P
-		| cs_flag, EBU_NAND_CON);
+		    | NAND_CON_SE_P | NAND_CON_WP_P | NAND_CON_PRE_P
+		    | cs_flag, EBU_NAND_CON);
 
-	/* finish with a reset */
-	xway_reset_chip(this);
+	/* Scan to find existence of the device */
+	err = nand_scan(mtd, 1);
+	if (err)
+		return err;
 
-	return 0;
-}
+	err = mtd_device_register(mtd, NULL, 0);
+	if (err)
+		nand_release(mtd);
 
-static struct platform_nand_data xway_nand_data = {
-	.chip = {
-		.nr_chips		= 1,
-		.chip_delay		= 30,
-	},
-	.ctrl = {
-		.probe		= xway_nand_probe,
-		.cmd_ctrl	= xway_cmd_ctrl,
-		.dev_ready	= xway_dev_ready,
-		.select_chip	= xway_select_chip,
-		.read_byte	= xway_read_byte,
-	}
-};
+	return err;
+}
 
 /*
- * Try to find the node inside the DT. If it is available attach out
- * platform_nand_data
+ * Remove a NAND device.
  */
-static int __init xway_register_nand(void)
+static int xway_nand_remove(struct platform_device *pdev)
 {
-	struct device_node *node;
-	struct platform_device *pdev;
-
-	node = of_find_compatible_node(NULL, NULL, "lantiq,nand-xway");
-	if (!node)
-		return -ENOENT;
-	pdev = of_find_device_by_node(node);
-	if (!pdev)
-		return -EINVAL;
-	pdev->dev.platform_data = &xway_nand_data;
-	of_node_put(node);
+	struct xway_nand_data *data = platform_get_drvdata(pdev);
+
+	nand_release(nand_to_mtd(&data->chip));
+
 	return 0;
 }
 
-subsys_initcall(xway_register_nand);
+static const struct of_device_id xway_nand_match[] = {
+	{ .compatible = "lantiq,nand-xway" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, xway_nand_match);
+
+static struct platform_driver xway_nand_driver = {
+	.probe	= xway_nand_probe,
+	.remove	= xway_nand_remove,
+	.driver	= {
+		.name		= "lantiq,nand-xway",
+		.of_match_table = xway_nand_match,
+	},
+};
+
+module_platform_driver(xway_nand_driver);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c
index a4b029a417f0..1a6d0e367b89 100644
--- a/drivers/mtd/onenand/onenand_base.c
+++ b/drivers/mtd/onenand/onenand_base.c
@@ -3188,13 +3188,13 @@ static int onenand_otp_walk(struct mtd_info *mtd, loff_t from, size_t len,
 			size_t tmp_retlen;
 
 			ret = action(mtd, from, len, &tmp_retlen, buf);
+			if (ret)
+				break;
 
 			buf += tmp_retlen;
 			len -= tmp_retlen;
 			*retlen += tmp_retlen;
 
-			if (ret)
-				break;
 		}
 		otp_pages--;
 	}
diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig
index d42c98e1f581..4a682ee0f632 100644
--- a/drivers/mtd/spi-nor/Kconfig
+++ b/drivers/mtd/spi-nor/Kconfig
@@ -29,6 +29,26 @@ config MTD_SPI_NOR_USE_4K_SECTORS
 	  Please note that some tools/drivers/filesystems may not work with
 	  4096 B erase size (e.g. UBIFS requires 15 KiB as a minimum).
 
+config SPI_ATMEL_QUADSPI
+	tristate "Atmel Quad SPI Controller"
+	depends on ARCH_AT91 || (ARM && COMPILE_TEST)
+	depends on OF && HAS_IOMEM
+	help
+	  This enables support for the Quad SPI controller in master mode.
+	  This driver does not support generic SPI. The implementation only
+	  supports SPI NOR.
+
+config SPI_CADENCE_QUADSPI
+	tristate "Cadence Quad SPI controller"
+	depends on OF && ARM
+	help
+	  Enable support for the Cadence Quad SPI Flash controller.
+
+	  Cadence QSPI is a specialized controller for connecting an SPI
+	  Flash over 1/2/4-bit wide bus. Enable this option if you have a
+	  device with a Cadence QSPI controller and want to access the
+	  Flash as an MTD device.
+
 config SPI_FSL_QUADSPI
 	tristate "Freescale Quad SPI controller"
 	depends on ARCH_MXC || SOC_LS1021A || ARCH_LAYERSCAPE || COMPILE_TEST
@@ -38,6 +58,13 @@ config SPI_FSL_QUADSPI
 	  This controller does not support generic SPI. It only supports
 	  SPI NOR.
 
+config SPI_HISI_SFC
+	tristate "Hisilicon SPI-NOR Flash Controller(SFC)"
+	depends on ARCH_HISI || COMPILE_TEST
+	depends on HAS_IOMEM && HAS_DMA
+	help
+	  This enables support for hisilicon SPI-NOR flash controller.
+
 config SPI_NXP_SPIFI
 	tristate "NXP SPI Flash Interface (SPIFI)"
 	depends on OF && (ARCH_LPC18XX || COMPILE_TEST)
diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile
index 0bf3a7f81675..121695e83542 100644
--- a/drivers/mtd/spi-nor/Makefile
+++ b/drivers/mtd/spi-nor/Makefile
@@ -1,4 +1,7 @@
 obj-$(CONFIG_MTD_SPI_NOR)	+= spi-nor.o
+obj-$(CONFIG_SPI_ATMEL_QUADSPI)	+= atmel-quadspi.o
+obj-$(CONFIG_SPI_CADENCE_QUADSPI)	+= cadence-quadspi.o
 obj-$(CONFIG_SPI_FSL_QUADSPI)	+= fsl-quadspi.o
+obj-$(CONFIG_SPI_HISI_SFC)	+= hisi-sfc.o
 obj-$(CONFIG_MTD_MT81xx_NOR)    += mtk-quadspi.o
 obj-$(CONFIG_SPI_NXP_SPIFI)	+= nxp-spifi.o
diff --git a/drivers/mtd/spi-nor/atmel-quadspi.c b/drivers/mtd/spi-nor/atmel-quadspi.c
new file mode 100644
index 000000000000..47937d9beec6
--- /dev/null
+++ b/drivers/mtd/spi-nor/atmel-quadspi.c
@@ -0,0 +1,732 @@
+/*
+ * Driver for Atmel QSPI Controller
+ *
+ * Copyright (C) 2015 Atmel Corporation
+ *
+ * Author: Cyrille Pitchen <cyrille.pitchen@atmel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This driver is based on drivers/mtd/spi-nor/fsl-quadspi.c from Freescale.
+ */
+
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
+#include <linux/platform_data/atmel.h>
+#include <linux/of.h>
+
+#include <linux/io.h>
+#include <linux/gpio.h>
+#include <linux/pinctrl/consumer.h>
+
+/* QSPI register offsets */
+#define QSPI_CR      0x0000  /* Control Register */
+#define QSPI_MR      0x0004  /* Mode Register */
+#define QSPI_RD      0x0008  /* Receive Data Register */
+#define QSPI_TD      0x000c  /* Transmit Data Register */
+#define QSPI_SR      0x0010  /* Status Register */
+#define QSPI_IER     0x0014  /* Interrupt Enable Register */
+#define QSPI_IDR     0x0018  /* Interrupt Disable Register */
+#define QSPI_IMR     0x001c  /* Interrupt Mask Register */
+#define QSPI_SCR     0x0020  /* Serial Clock Register */
+
+#define QSPI_IAR     0x0030  /* Instruction Address Register */
+#define QSPI_ICR     0x0034  /* Instruction Code Register */
+#define QSPI_IFR     0x0038  /* Instruction Frame Register */
+
+#define QSPI_SMR     0x0040  /* Scrambling Mode Register */
+#define QSPI_SKR     0x0044  /* Scrambling Key Register */
+
+#define QSPI_WPMR    0x00E4  /* Write Protection Mode Register */
+#define QSPI_WPSR    0x00E8  /* Write Protection Status Register */
+
+#define QSPI_VERSION 0x00FC  /* Version Register */
+
+
+/* Bitfields in QSPI_CR (Control Register) */
+#define QSPI_CR_QSPIEN                  BIT(0)
+#define QSPI_CR_QSPIDIS                 BIT(1)
+#define QSPI_CR_SWRST                   BIT(7)
+#define QSPI_CR_LASTXFER                BIT(24)
+
+/* Bitfields in QSPI_MR (Mode Register) */
+#define QSPI_MR_SSM                     BIT(0)
+#define QSPI_MR_LLB                     BIT(1)
+#define QSPI_MR_WDRBT                   BIT(2)
+#define QSPI_MR_SMRM                    BIT(3)
+#define QSPI_MR_CSMODE_MASK             GENMASK(5, 4)
+#define QSPI_MR_CSMODE_NOT_RELOADED     (0 << 4)
+#define QSPI_MR_CSMODE_LASTXFER         (1 << 4)
+#define QSPI_MR_CSMODE_SYSTEMATICALLY   (2 << 4)
+#define QSPI_MR_NBBITS_MASK             GENMASK(11, 8)
+#define QSPI_MR_NBBITS(n)               ((((n) - 8) << 8) & QSPI_MR_NBBITS_MASK)
+#define QSPI_MR_DLYBCT_MASK             GENMASK(23, 16)
+#define QSPI_MR_DLYBCT(n)               (((n) << 16) & QSPI_MR_DLYBCT_MASK)
+#define QSPI_MR_DLYCS_MASK              GENMASK(31, 24)
+#define QSPI_MR_DLYCS(n)                (((n) << 24) & QSPI_MR_DLYCS_MASK)
+
+/* Bitfields in QSPI_SR/QSPI_IER/QSPI_IDR/QSPI_IMR  */
+#define QSPI_SR_RDRF                    BIT(0)
+#define QSPI_SR_TDRE                    BIT(1)
+#define QSPI_SR_TXEMPTY                 BIT(2)
+#define QSPI_SR_OVRES                   BIT(3)
+#define QSPI_SR_CSR                     BIT(8)
+#define QSPI_SR_CSS                     BIT(9)
+#define QSPI_SR_INSTRE                  BIT(10)
+#define QSPI_SR_QSPIENS                 BIT(24)
+
+#define QSPI_SR_CMD_COMPLETED	(QSPI_SR_INSTRE | QSPI_SR_CSR)
+
+/* Bitfields in QSPI_SCR (Serial Clock Register) */
+#define QSPI_SCR_CPOL                   BIT(0)
+#define QSPI_SCR_CPHA                   BIT(1)
+#define QSPI_SCR_SCBR_MASK              GENMASK(15, 8)
+#define QSPI_SCR_SCBR(n)                (((n) << 8) & QSPI_SCR_SCBR_MASK)
+#define QSPI_SCR_DLYBS_MASK             GENMASK(23, 16)
+#define QSPI_SCR_DLYBS(n)               (((n) << 16) & QSPI_SCR_DLYBS_MASK)
+
+/* Bitfields in QSPI_ICR (Instruction Code Register) */
+#define QSPI_ICR_INST_MASK              GENMASK(7, 0)
+#define QSPI_ICR_INST(inst)             (((inst) << 0) & QSPI_ICR_INST_MASK)
+#define QSPI_ICR_OPT_MASK               GENMASK(23, 16)
+#define QSPI_ICR_OPT(opt)               (((opt) << 16) & QSPI_ICR_OPT_MASK)
+
+/* Bitfields in QSPI_IFR (Instruction Frame Register) */
+#define QSPI_IFR_WIDTH_MASK             GENMASK(2, 0)
+#define QSPI_IFR_WIDTH_SINGLE_BIT_SPI   (0 << 0)
+#define QSPI_IFR_WIDTH_DUAL_OUTPUT      (1 << 0)
+#define QSPI_IFR_WIDTH_QUAD_OUTPUT      (2 << 0)
+#define QSPI_IFR_WIDTH_DUAL_IO          (3 << 0)
+#define QSPI_IFR_WIDTH_QUAD_IO          (4 << 0)
+#define QSPI_IFR_WIDTH_DUAL_CMD         (5 << 0)
+#define QSPI_IFR_WIDTH_QUAD_CMD         (6 << 0)
+#define QSPI_IFR_INSTEN                 BIT(4)
+#define QSPI_IFR_ADDREN                 BIT(5)
+#define QSPI_IFR_OPTEN                  BIT(6)
+#define QSPI_IFR_DATAEN                 BIT(7)
+#define QSPI_IFR_OPTL_MASK              GENMASK(9, 8)
+#define QSPI_IFR_OPTL_1BIT              (0 << 8)
+#define QSPI_IFR_OPTL_2BIT              (1 << 8)
+#define QSPI_IFR_OPTL_4BIT              (2 << 8)
+#define QSPI_IFR_OPTL_8BIT              (3 << 8)
+#define QSPI_IFR_ADDRL                  BIT(10)
+#define QSPI_IFR_TFRTYP_MASK            GENMASK(13, 12)
+#define QSPI_IFR_TFRTYP_TRSFR_READ      (0 << 12)
+#define QSPI_IFR_TFRTYP_TRSFR_READ_MEM  (1 << 12)
+#define QSPI_IFR_TFRTYP_TRSFR_WRITE     (2 << 12)
+#define QSPI_IFR_TFRTYP_TRSFR_WRITE_MEM (3 << 13)
+#define QSPI_IFR_CRM                    BIT(14)
+#define QSPI_IFR_NBDUM_MASK             GENMASK(20, 16)
+#define QSPI_IFR_NBDUM(n)               (((n) << 16) & QSPI_IFR_NBDUM_MASK)
+
+/* Bitfields in QSPI_SMR (Scrambling Mode Register) */
+#define QSPI_SMR_SCREN                  BIT(0)
+#define QSPI_SMR_RVDIS                  BIT(1)
+
+/* Bitfields in QSPI_WPMR (Write Protection Mode Register) */
+#define QSPI_WPMR_WPEN                  BIT(0)
+#define QSPI_WPMR_WPKEY_MASK            GENMASK(31, 8)
+#define QSPI_WPMR_WPKEY(wpkey)          (((wpkey) << 8) & QSPI_WPMR_WPKEY_MASK)
+
+/* Bitfields in QSPI_WPSR (Write Protection Status Register) */
+#define QSPI_WPSR_WPVS                  BIT(0)
+#define QSPI_WPSR_WPVSRC_MASK           GENMASK(15, 8)
+#define QSPI_WPSR_WPVSRC(src)           (((src) << 8) & QSPI_WPSR_WPVSRC)
+
+
+struct atmel_qspi {
+	void __iomem		*regs;
+	void __iomem		*mem;
+	struct clk		*clk;
+	struct platform_device	*pdev;
+	u32			pending;
+
+	struct spi_nor		nor;
+	u32			clk_rate;
+	struct completion	cmd_completion;
+};
+
+struct atmel_qspi_command {
+	union {
+		struct {
+			u32	instruction:1;
+			u32	address:3;
+			u32	mode:1;
+			u32	dummy:1;
+			u32	data:1;
+			u32	reserved:25;
+		}		bits;
+		u32	word;
+	}	enable;
+	u8	instruction;
+	u8	mode;
+	u8	num_mode_cycles;
+	u8	num_dummy_cycles;
+	u32	address;
+
+	size_t		buf_len;
+	const void	*tx_buf;
+	void		*rx_buf;
+};
+
+/* Register access functions */
+static inline u32 qspi_readl(struct atmel_qspi *aq, u32 reg)
+{
+	return readl_relaxed(aq->regs + reg);
+}
+
+static inline void qspi_writel(struct atmel_qspi *aq, u32 reg, u32 value)
+{
+	writel_relaxed(value, aq->regs + reg);
+}
+
+static int atmel_qspi_run_transfer(struct atmel_qspi *aq,
+				   const struct atmel_qspi_command *cmd)
+{
+	void __iomem *ahb_mem;
+
+	/* Then fallback to a PIO transfer (memcpy() DOES NOT work!) */
+	ahb_mem = aq->mem;
+	if (cmd->enable.bits.address)
+		ahb_mem += cmd->address;
+	if (cmd->tx_buf)
+		_memcpy_toio(ahb_mem, cmd->tx_buf, cmd->buf_len);
+	else
+		_memcpy_fromio(cmd->rx_buf, ahb_mem, cmd->buf_len);
+
+	return 0;
+}
+
+#ifdef DEBUG
+static void atmel_qspi_debug_command(struct atmel_qspi *aq,
+				     const struct atmel_qspi_command *cmd,
+				     u32 ifr)
+{
+	u8 cmd_buf[SPI_NOR_MAX_CMD_SIZE];
+	size_t len = 0;
+	int i;
+
+	if (cmd->enable.bits.instruction)
+		cmd_buf[len++] = cmd->instruction;
+
+	for (i = cmd->enable.bits.address-1; i >= 0; --i)
+		cmd_buf[len++] = (cmd->address >> (i << 3)) & 0xff;
+
+	if (cmd->enable.bits.mode)
+		cmd_buf[len++] = cmd->mode;
+
+	if (cmd->enable.bits.dummy) {
+		int num = cmd->num_dummy_cycles;
+
+		switch (ifr & QSPI_IFR_WIDTH_MASK) {
+		case QSPI_IFR_WIDTH_SINGLE_BIT_SPI:
+		case QSPI_IFR_WIDTH_DUAL_OUTPUT:
+		case QSPI_IFR_WIDTH_QUAD_OUTPUT:
+			num >>= 3;
+			break;
+		case QSPI_IFR_WIDTH_DUAL_IO:
+		case QSPI_IFR_WIDTH_DUAL_CMD:
+			num >>= 2;
+			break;
+		case QSPI_IFR_WIDTH_QUAD_IO:
+		case QSPI_IFR_WIDTH_QUAD_CMD:
+			num >>= 1;
+			break;
+		default:
+			return;
+		}
+
+		for (i = 0; i < num; ++i)
+			cmd_buf[len++] = 0;
+	}
+
+	/* Dump the SPI command */
+	print_hex_dump(KERN_DEBUG, "qspi cmd: ", DUMP_PREFIX_NONE,
+		       32, 1, cmd_buf, len, false);
+
+#ifdef VERBOSE_DEBUG
+	/* If verbose debug is enabled, also dump the TX data */
+	if (cmd->enable.bits.data && cmd->tx_buf)
+		print_hex_dump(KERN_DEBUG, "qspi tx : ", DUMP_PREFIX_NONE,
+			       32, 1, cmd->tx_buf, cmd->buf_len, false);
+#endif
+}
+#else
+#define atmel_qspi_debug_command(aq, cmd, ifr)
+#endif
+
+static int atmel_qspi_run_command(struct atmel_qspi *aq,
+				  const struct atmel_qspi_command *cmd,
+				  u32 ifr_tfrtyp, u32 ifr_width)
+{
+	u32 iar, icr, ifr, sr;
+	int err = 0;
+
+	iar = 0;
+	icr = 0;
+	ifr = ifr_tfrtyp | ifr_width;
+
+	/* Compute instruction parameters */
+	if (cmd->enable.bits.instruction) {
+		icr |= QSPI_ICR_INST(cmd->instruction);
+		ifr |= QSPI_IFR_INSTEN;
+	}
+
+	/* Compute address parameters */
+	switch (cmd->enable.bits.address) {
+	case 4:
+		ifr |= QSPI_IFR_ADDRL;
+		/* fall through to the 24bit (3 byte) address case. */
+	case 3:
+		iar = (cmd->enable.bits.data) ? 0 : cmd->address;
+		ifr |= QSPI_IFR_ADDREN;
+		break;
+	case 0:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Compute option parameters */
+	if (cmd->enable.bits.mode && cmd->num_mode_cycles) {
+		u32 mode_cycle_bits, mode_bits;
+
+		icr |= QSPI_ICR_OPT(cmd->mode);
+		ifr |= QSPI_IFR_OPTEN;
+
+		switch (ifr & QSPI_IFR_WIDTH_MASK) {
+		case QSPI_IFR_WIDTH_SINGLE_BIT_SPI:
+		case QSPI_IFR_WIDTH_DUAL_OUTPUT:
+		case QSPI_IFR_WIDTH_QUAD_OUTPUT:
+			mode_cycle_bits = 1;
+			break;
+		case QSPI_IFR_WIDTH_DUAL_IO:
+		case QSPI_IFR_WIDTH_DUAL_CMD:
+			mode_cycle_bits = 2;
+			break;
+		case QSPI_IFR_WIDTH_QUAD_IO:
+		case QSPI_IFR_WIDTH_QUAD_CMD:
+			mode_cycle_bits = 4;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		mode_bits = cmd->num_mode_cycles * mode_cycle_bits;
+		switch (mode_bits) {
+		case 1:
+			ifr |= QSPI_IFR_OPTL_1BIT;
+			break;
+
+		case 2:
+			ifr |= QSPI_IFR_OPTL_2BIT;
+			break;
+
+		case 4:
+			ifr |= QSPI_IFR_OPTL_4BIT;
+			break;
+
+		case 8:
+			ifr |= QSPI_IFR_OPTL_8BIT;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+	}
+
+	/* Set number of dummy cycles */
+	if (cmd->enable.bits.dummy)
+		ifr |= QSPI_IFR_NBDUM(cmd->num_dummy_cycles);
+
+	/* Set data enable */
+	if (cmd->enable.bits.data) {
+		ifr |= QSPI_IFR_DATAEN;
+
+		/* Special case for Continuous Read Mode */
+		if (!cmd->tx_buf && !cmd->rx_buf)
+			ifr |= QSPI_IFR_CRM;
+	}
+
+	/* Clear pending interrupts */
+	(void)qspi_readl(aq, QSPI_SR);
+
+	/* Set QSPI Instruction Frame registers */
+	atmel_qspi_debug_command(aq, cmd, ifr);
+	qspi_writel(aq, QSPI_IAR, iar);
+	qspi_writel(aq, QSPI_ICR, icr);
+	qspi_writel(aq, QSPI_IFR, ifr);
+
+	/* Skip to the final steps if there is no data */
+	if (!cmd->enable.bits.data)
+		goto no_data;
+
+	/* Dummy read of QSPI_IFR to synchronize APB and AHB accesses */
+	(void)qspi_readl(aq, QSPI_IFR);
+
+	/* Stop here for continuous read */
+	if (!cmd->tx_buf && !cmd->rx_buf)
+		return 0;
+	/* Send/Receive data */
+	err = atmel_qspi_run_transfer(aq, cmd);
+
+	/* Release the chip-select */
+	qspi_writel(aq, QSPI_CR, QSPI_CR_LASTXFER);
+
+	if (err)
+		return err;
+
+#if defined(DEBUG) && defined(VERBOSE_DEBUG)
+	/*
+	 * If verbose debug is enabled, also dump the RX data in addition to
+	 * the SPI command previously dumped by atmel_qspi_debug_command()
+	 */
+	if (cmd->rx_buf)
+		print_hex_dump(KERN_DEBUG, "qspi rx : ", DUMP_PREFIX_NONE,
+			       32, 1, cmd->rx_buf, cmd->buf_len, false);
+#endif
+no_data:
+	/* Poll INSTRuction End status */
+	sr = qspi_readl(aq, QSPI_SR);
+	if ((sr & QSPI_SR_CMD_COMPLETED) == QSPI_SR_CMD_COMPLETED)
+		return err;
+
+	/* Wait for INSTRuction End interrupt */
+	reinit_completion(&aq->cmd_completion);
+	aq->pending = sr & QSPI_SR_CMD_COMPLETED;
+	qspi_writel(aq, QSPI_IER, QSPI_SR_CMD_COMPLETED);
+	if (!wait_for_completion_timeout(&aq->cmd_completion,
+					 msecs_to_jiffies(1000)))
+		err = -ETIMEDOUT;
+	qspi_writel(aq, QSPI_IDR, QSPI_SR_CMD_COMPLETED);
+
+	return err;
+}
+
+static int atmel_qspi_read_reg(struct spi_nor *nor, u8 opcode,
+			       u8 *buf, int len)
+{
+	struct atmel_qspi *aq = nor->priv;
+	struct atmel_qspi_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.enable.bits.instruction = 1;
+	cmd.enable.bits.data = 1;
+	cmd.instruction = opcode;
+	cmd.rx_buf = buf;
+	cmd.buf_len = len;
+	return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_READ,
+				      QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+}
+
+static int atmel_qspi_write_reg(struct spi_nor *nor, u8 opcode,
+				u8 *buf, int len)
+{
+	struct atmel_qspi *aq = nor->priv;
+	struct atmel_qspi_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.enable.bits.instruction = 1;
+	cmd.enable.bits.data = (buf != NULL && len > 0);
+	cmd.instruction = opcode;
+	cmd.tx_buf = buf;
+	cmd.buf_len = len;
+	return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE,
+				      QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+}
+
+static ssize_t atmel_qspi_write(struct spi_nor *nor, loff_t to, size_t len,
+				const u_char *write_buf)
+{
+	struct atmel_qspi *aq = nor->priv;
+	struct atmel_qspi_command cmd;
+	ssize_t ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.enable.bits.instruction = 1;
+	cmd.enable.bits.address = nor->addr_width;
+	cmd.enable.bits.data = 1;
+	cmd.instruction = nor->program_opcode;
+	cmd.address = (u32)to;
+	cmd.tx_buf = write_buf;
+	cmd.buf_len = len;
+	ret = atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE_MEM,
+				     QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+	return (ret < 0) ? ret : len;
+}
+
+static int atmel_qspi_erase(struct spi_nor *nor, loff_t offs)
+{
+	struct atmel_qspi *aq = nor->priv;
+	struct atmel_qspi_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.enable.bits.instruction = 1;
+	cmd.enable.bits.address = nor->addr_width;
+	cmd.instruction = nor->erase_opcode;
+	cmd.address = (u32)offs;
+	return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE,
+				      QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+}
+
+static ssize_t atmel_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
+			       u_char *read_buf)
+{
+	struct atmel_qspi *aq = nor->priv;
+	struct atmel_qspi_command cmd;
+	u8 num_mode_cycles, num_dummy_cycles;
+	u32 ifr_width;
+	ssize_t ret;
+
+	switch (nor->flash_read) {
+	case SPI_NOR_NORMAL:
+	case SPI_NOR_FAST:
+		ifr_width = QSPI_IFR_WIDTH_SINGLE_BIT_SPI;
+		break;
+
+	case SPI_NOR_DUAL:
+		ifr_width = QSPI_IFR_WIDTH_DUAL_OUTPUT;
+		break;
+
+	case SPI_NOR_QUAD:
+		ifr_width = QSPI_IFR_WIDTH_QUAD_OUTPUT;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (nor->read_dummy >= 2) {
+		num_mode_cycles = 2;
+		num_dummy_cycles = nor->read_dummy - 2;
+	} else {
+		num_mode_cycles = nor->read_dummy;
+		num_dummy_cycles = 0;
+	}
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.enable.bits.instruction = 1;
+	cmd.enable.bits.address = nor->addr_width;
+	cmd.enable.bits.mode = (num_mode_cycles > 0);
+	cmd.enable.bits.dummy = (num_dummy_cycles > 0);
+	cmd.enable.bits.data = 1;
+	cmd.instruction = nor->read_opcode;
+	cmd.address = (u32)from;
+	cmd.mode = 0xff; /* This value prevents from entering the 0-4-4 mode */
+	cmd.num_mode_cycles = num_mode_cycles;
+	cmd.num_dummy_cycles = num_dummy_cycles;
+	cmd.rx_buf = read_buf;
+	cmd.buf_len = len;
+	ret = atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_READ_MEM,
+				     ifr_width);
+	return (ret < 0) ? ret : len;
+}
+
+static int atmel_qspi_init(struct atmel_qspi *aq)
+{
+	unsigned long src_rate;
+	u32 mr, scr, scbr;
+
+	/* Reset the QSPI controller */
+	qspi_writel(aq, QSPI_CR, QSPI_CR_SWRST);
+
+	/* Set the QSPI controller in Serial Memory Mode */
+	mr = QSPI_MR_NBBITS(8) | QSPI_MR_SSM;
+	qspi_writel(aq, QSPI_MR, mr);
+
+	src_rate = clk_get_rate(aq->clk);
+	if (!src_rate)
+		return -EINVAL;
+
+	/* Compute the QSPI baudrate */
+	scbr = DIV_ROUND_UP(src_rate, aq->clk_rate);
+	if (scbr > 0)
+		scbr--;
+	scr = QSPI_SCR_SCBR(scbr);
+	qspi_writel(aq, QSPI_SCR, scr);
+
+	/* Enable the QSPI controller */
+	qspi_writel(aq, QSPI_CR, QSPI_CR_QSPIEN);
+
+	return 0;
+}
+
+static irqreturn_t atmel_qspi_interrupt(int irq, void *dev_id)
+{
+	struct atmel_qspi *aq = (struct atmel_qspi *)dev_id;
+	u32 status, mask, pending;
+
+	status = qspi_readl(aq, QSPI_SR);
+	mask = qspi_readl(aq, QSPI_IMR);
+	pending = status & mask;
+
+	if (!pending)
+		return IRQ_NONE;
+
+	aq->pending |= pending;
+	if ((aq->pending & QSPI_SR_CMD_COMPLETED) == QSPI_SR_CMD_COMPLETED)
+		complete(&aq->cmd_completion);
+
+	return IRQ_HANDLED;
+}
+
+static int atmel_qspi_probe(struct platform_device *pdev)
+{
+	struct device_node *child, *np = pdev->dev.of_node;
+	struct atmel_qspi *aq;
+	struct resource *res;
+	struct spi_nor *nor;
+	struct mtd_info *mtd;
+	int irq, err = 0;
+
+	if (of_get_child_count(np) != 1)
+		return -ENODEV;
+	child = of_get_next_child(np, NULL);
+
+	aq = devm_kzalloc(&pdev->dev, sizeof(*aq), GFP_KERNEL);
+	if (!aq) {
+		err = -ENOMEM;
+		goto exit;
+	}
+
+	platform_set_drvdata(pdev, aq);
+	init_completion(&aq->cmd_completion);
+	aq->pdev = pdev;
+
+	/* Map the registers */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qspi_base");
+	aq->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(aq->regs)) {
+		dev_err(&pdev->dev, "missing registers\n");
+		err = PTR_ERR(aq->regs);
+		goto exit;
+	}
+
+	/* Map the AHB memory */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qspi_mmap");
+	aq->mem = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(aq->mem)) {
+		dev_err(&pdev->dev, "missing AHB memory\n");
+		err = PTR_ERR(aq->mem);
+		goto exit;
+	}
+
+	/* Get the peripheral clock */
+	aq->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(aq->clk)) {
+		dev_err(&pdev->dev, "missing peripheral clock\n");
+		err = PTR_ERR(aq->clk);
+		goto exit;
+	}
+
+	/* Enable the peripheral clock */
+	err = clk_prepare_enable(aq->clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable the peripheral clock\n");
+		goto exit;
+	}
+
+	/* Request the IRQ */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "missing IRQ\n");
+		err = irq;
+		goto disable_clk;
+	}
+	err = devm_request_irq(&pdev->dev, irq, atmel_qspi_interrupt,
+			       0, dev_name(&pdev->dev), aq);
+	if (err)
+		goto disable_clk;
+
+	/* Setup the spi-nor */
+	nor = &aq->nor;
+	mtd = &nor->mtd;
+
+	nor->dev = &pdev->dev;
+	spi_nor_set_flash_node(nor, child);
+	nor->priv = aq;
+	mtd->priv = nor;
+
+	nor->read_reg = atmel_qspi_read_reg;
+	nor->write_reg = atmel_qspi_write_reg;
+	nor->read = atmel_qspi_read;
+	nor->write = atmel_qspi_write;
+	nor->erase = atmel_qspi_erase;
+
+	err = of_property_read_u32(child, "spi-max-frequency", &aq->clk_rate);
+	if (err < 0)
+		goto disable_clk;
+
+	err = atmel_qspi_init(aq);
+	if (err)
+		goto disable_clk;
+
+	err = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+	if (err)
+		goto disable_clk;
+
+	err = mtd_device_register(mtd, NULL, 0);
+	if (err)
+		goto disable_clk;
+
+	of_node_put(child);
+
+	return 0;
+
+disable_clk:
+	clk_disable_unprepare(aq->clk);
+exit:
+	of_node_put(child);
+
+	return err;
+}
+
+static int atmel_qspi_remove(struct platform_device *pdev)
+{
+	struct atmel_qspi *aq = platform_get_drvdata(pdev);
+
+	mtd_device_unregister(&aq->nor.mtd);
+	qspi_writel(aq, QSPI_CR, QSPI_CR_QSPIDIS);
+	clk_disable_unprepare(aq->clk);
+	return 0;
+}
+
+
+static const struct of_device_id atmel_qspi_dt_ids[] = {
+	{ .compatible = "atmel,sama5d2-qspi" },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(of, atmel_qspi_dt_ids);
+
+static struct platform_driver atmel_qspi_driver = {
+	.driver = {
+		.name	= "atmel_qspi",
+		.of_match_table	= atmel_qspi_dt_ids,
+	},
+	.probe		= atmel_qspi_probe,
+	.remove		= atmel_qspi_remove,
+};
+module_platform_driver(atmel_qspi_driver);
+
+MODULE_AUTHOR("Cyrille Pitchen <cyrille.pitchen@atmel.com>");
+MODULE_DESCRIPTION("Atmel QSPI Controller driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
new file mode 100644
index 000000000000..d403ba7b8f43
--- /dev/null
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -0,0 +1,1299 @@
+/*
+ * Driver for Cadence QSPI Controller
+ *
+ * Copyright Altera Corporation (C) 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
+#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+#include <linux/spi/spi.h>
+#include <linux/timer.h>
+
+#define CQSPI_NAME			"cadence-qspi"
+#define CQSPI_MAX_CHIPSELECT		16
+
+struct cqspi_st;
+
+struct cqspi_flash_pdata {
+	struct spi_nor	nor;
+	struct cqspi_st	*cqspi;
+	u32		clk_rate;
+	u32		read_delay;
+	u32		tshsl_ns;
+	u32		tsd2d_ns;
+	u32		tchsh_ns;
+	u32		tslch_ns;
+	u8		inst_width;
+	u8		addr_width;
+	u8		data_width;
+	u8		cs;
+	bool		registered;
+};
+
+struct cqspi_st {
+	struct platform_device	*pdev;
+
+	struct clk		*clk;
+	unsigned int		sclk;
+
+	void __iomem		*iobase;
+	void __iomem		*ahb_base;
+	struct completion	transfer_complete;
+	struct mutex		bus_mutex;
+
+	int			current_cs;
+	int			current_page_size;
+	int			current_erase_size;
+	int			current_addr_width;
+	unsigned long		master_ref_clk_hz;
+	bool			is_decoded_cs;
+	u32			fifo_depth;
+	u32			fifo_width;
+	u32			trigger_address;
+	struct cqspi_flash_pdata f_pdata[CQSPI_MAX_CHIPSELECT];
+};
+
+/* Operation timeout value */
+#define CQSPI_TIMEOUT_MS			500
+#define CQSPI_READ_TIMEOUT_MS			10
+
+/* Instruction type */
+#define CQSPI_INST_TYPE_SINGLE			0
+#define CQSPI_INST_TYPE_DUAL			1
+#define CQSPI_INST_TYPE_QUAD			2
+
+#define CQSPI_DUMMY_CLKS_PER_BYTE		8
+#define CQSPI_DUMMY_BYTES_MAX			4
+#define CQSPI_DUMMY_CLKS_MAX			31
+
+#define CQSPI_STIG_DATA_LEN_MAX			8
+
+/* Register map */
+#define CQSPI_REG_CONFIG			0x00
+#define CQSPI_REG_CONFIG_ENABLE_MASK		BIT(0)
+#define CQSPI_REG_CONFIG_DECODE_MASK		BIT(9)
+#define CQSPI_REG_CONFIG_CHIPSELECT_LSB		10
+#define CQSPI_REG_CONFIG_DMA_MASK		BIT(15)
+#define CQSPI_REG_CONFIG_BAUD_LSB		19
+#define CQSPI_REG_CONFIG_IDLE_LSB		31
+#define CQSPI_REG_CONFIG_CHIPSELECT_MASK	0xF
+#define CQSPI_REG_CONFIG_BAUD_MASK		0xF
+
+#define CQSPI_REG_RD_INSTR			0x04
+#define CQSPI_REG_RD_INSTR_OPCODE_LSB		0
+#define CQSPI_REG_RD_INSTR_TYPE_INSTR_LSB	8
+#define CQSPI_REG_RD_INSTR_TYPE_ADDR_LSB	12
+#define CQSPI_REG_RD_INSTR_TYPE_DATA_LSB	16
+#define CQSPI_REG_RD_INSTR_MODE_EN_LSB		20
+#define CQSPI_REG_RD_INSTR_DUMMY_LSB		24
+#define CQSPI_REG_RD_INSTR_TYPE_INSTR_MASK	0x3
+#define CQSPI_REG_RD_INSTR_TYPE_ADDR_MASK	0x3
+#define CQSPI_REG_RD_INSTR_TYPE_DATA_MASK	0x3
+#define CQSPI_REG_RD_INSTR_DUMMY_MASK		0x1F
+
+#define CQSPI_REG_WR_INSTR			0x08
+#define CQSPI_REG_WR_INSTR_OPCODE_LSB		0
+#define CQSPI_REG_WR_INSTR_TYPE_ADDR_LSB	12
+#define CQSPI_REG_WR_INSTR_TYPE_DATA_LSB	16
+
+#define CQSPI_REG_DELAY				0x0C
+#define CQSPI_REG_DELAY_TSLCH_LSB		0
+#define CQSPI_REG_DELAY_TCHSH_LSB		8
+#define CQSPI_REG_DELAY_TSD2D_LSB		16
+#define CQSPI_REG_DELAY_TSHSL_LSB		24
+#define CQSPI_REG_DELAY_TSLCH_MASK		0xFF
+#define CQSPI_REG_DELAY_TCHSH_MASK		0xFF
+#define CQSPI_REG_DELAY_TSD2D_MASK		0xFF
+#define CQSPI_REG_DELAY_TSHSL_MASK		0xFF
+
+#define CQSPI_REG_READCAPTURE			0x10
+#define CQSPI_REG_READCAPTURE_BYPASS_LSB	0
+#define CQSPI_REG_READCAPTURE_DELAY_LSB		1
+#define CQSPI_REG_READCAPTURE_DELAY_MASK	0xF
+
+#define CQSPI_REG_SIZE				0x14
+#define CQSPI_REG_SIZE_ADDRESS_LSB		0
+#define CQSPI_REG_SIZE_PAGE_LSB			4
+#define CQSPI_REG_SIZE_BLOCK_LSB		16
+#define CQSPI_REG_SIZE_ADDRESS_MASK		0xF
+#define CQSPI_REG_SIZE_PAGE_MASK		0xFFF
+#define CQSPI_REG_SIZE_BLOCK_MASK		0x3F
+
+#define CQSPI_REG_SRAMPARTITION			0x18
+#define CQSPI_REG_INDIRECTTRIGGER		0x1C
+
+#define CQSPI_REG_DMA				0x20
+#define CQSPI_REG_DMA_SINGLE_LSB		0
+#define CQSPI_REG_DMA_BURST_LSB			8
+#define CQSPI_REG_DMA_SINGLE_MASK		0xFF
+#define CQSPI_REG_DMA_BURST_MASK		0xFF
+
+#define CQSPI_REG_REMAP				0x24
+#define CQSPI_REG_MODE_BIT			0x28
+
+#define CQSPI_REG_SDRAMLEVEL			0x2C
+#define CQSPI_REG_SDRAMLEVEL_RD_LSB		0
+#define CQSPI_REG_SDRAMLEVEL_WR_LSB		16
+#define CQSPI_REG_SDRAMLEVEL_RD_MASK		0xFFFF
+#define CQSPI_REG_SDRAMLEVEL_WR_MASK		0xFFFF
+
+#define CQSPI_REG_IRQSTATUS			0x40
+#define CQSPI_REG_IRQMASK			0x44
+
+#define CQSPI_REG_INDIRECTRD			0x60
+#define CQSPI_REG_INDIRECTRD_START_MASK		BIT(0)
+#define CQSPI_REG_INDIRECTRD_CANCEL_MASK	BIT(1)
+#define CQSPI_REG_INDIRECTRD_DONE_MASK		BIT(5)
+
+#define CQSPI_REG_INDIRECTRDWATERMARK		0x64
+#define CQSPI_REG_INDIRECTRDSTARTADDR		0x68
+#define CQSPI_REG_INDIRECTRDBYTES		0x6C
+
+#define CQSPI_REG_CMDCTRL			0x90
+#define CQSPI_REG_CMDCTRL_EXECUTE_MASK		BIT(0)
+#define CQSPI_REG_CMDCTRL_INPROGRESS_MASK	BIT(1)
+#define CQSPI_REG_CMDCTRL_WR_BYTES_LSB		12
+#define CQSPI_REG_CMDCTRL_WR_EN_LSB		15
+#define CQSPI_REG_CMDCTRL_ADD_BYTES_LSB		16
+#define CQSPI_REG_CMDCTRL_ADDR_EN_LSB		19
+#define CQSPI_REG_CMDCTRL_RD_BYTES_LSB		20
+#define CQSPI_REG_CMDCTRL_RD_EN_LSB		23
+#define CQSPI_REG_CMDCTRL_OPCODE_LSB		24
+#define CQSPI_REG_CMDCTRL_WR_BYTES_MASK		0x7
+#define CQSPI_REG_CMDCTRL_ADD_BYTES_MASK	0x3
+#define CQSPI_REG_CMDCTRL_RD_BYTES_MASK		0x7
+
+#define CQSPI_REG_INDIRECTWR			0x70
+#define CQSPI_REG_INDIRECTWR_START_MASK		BIT(0)
+#define CQSPI_REG_INDIRECTWR_CANCEL_MASK	BIT(1)
+#define CQSPI_REG_INDIRECTWR_DONE_MASK		BIT(5)
+
+#define CQSPI_REG_INDIRECTWRWATERMARK		0x74
+#define CQSPI_REG_INDIRECTWRSTARTADDR		0x78
+#define CQSPI_REG_INDIRECTWRBYTES		0x7C
+
+#define CQSPI_REG_CMDADDRESS			0x94
+#define CQSPI_REG_CMDREADDATALOWER		0xA0
+#define CQSPI_REG_CMDREADDATAUPPER		0xA4
+#define CQSPI_REG_CMDWRITEDATALOWER		0xA8
+#define CQSPI_REG_CMDWRITEDATAUPPER		0xAC
+
+/* Interrupt status bits */
+#define CQSPI_REG_IRQ_MODE_ERR			BIT(0)
+#define CQSPI_REG_IRQ_UNDERFLOW			BIT(1)
+#define CQSPI_REG_IRQ_IND_COMP			BIT(2)
+#define CQSPI_REG_IRQ_IND_RD_REJECT		BIT(3)
+#define CQSPI_REG_IRQ_WR_PROTECTED_ERR		BIT(4)
+#define CQSPI_REG_IRQ_ILLEGAL_AHB_ERR		BIT(5)
+#define CQSPI_REG_IRQ_WATERMARK			BIT(6)
+#define CQSPI_REG_IRQ_IND_SRAM_FULL		BIT(12)
+
+#define CQSPI_IRQ_MASK_RD		(CQSPI_REG_IRQ_WATERMARK	| \
+					 CQSPI_REG_IRQ_IND_SRAM_FULL	| \
+					 CQSPI_REG_IRQ_IND_COMP)
+
+#define CQSPI_IRQ_MASK_WR		(CQSPI_REG_IRQ_IND_COMP		| \
+					 CQSPI_REG_IRQ_WATERMARK	| \
+					 CQSPI_REG_IRQ_UNDERFLOW)
+
+#define CQSPI_IRQ_STATUS_MASK		0x1FFFF
+
+static int cqspi_wait_for_bit(void __iomem *reg, const u32 mask, bool clear)
+{
+	unsigned long end = jiffies + msecs_to_jiffies(CQSPI_TIMEOUT_MS);
+	u32 val;
+
+	while (1) {
+		val = readl(reg);
+		if (clear)
+			val = ~val;
+		val &= mask;
+
+		if (val == mask)
+			return 0;
+
+		if (time_after(jiffies, end))
+			return -ETIMEDOUT;
+	}
+}
+
+static bool cqspi_is_idle(struct cqspi_st *cqspi)
+{
+	u32 reg = readl(cqspi->iobase + CQSPI_REG_CONFIG);
+
+	return reg & (1 << CQSPI_REG_CONFIG_IDLE_LSB);
+}
+
+static u32 cqspi_get_rd_sram_level(struct cqspi_st *cqspi)
+{
+	u32 reg = readl(cqspi->iobase + CQSPI_REG_SDRAMLEVEL);
+
+	reg >>= CQSPI_REG_SDRAMLEVEL_RD_LSB;
+	return reg & CQSPI_REG_SDRAMLEVEL_RD_MASK;
+}
+
+static irqreturn_t cqspi_irq_handler(int this_irq, void *dev)
+{
+	struct cqspi_st *cqspi = dev;
+	unsigned int irq_status;
+
+	/* Read interrupt status */
+	irq_status = readl(cqspi->iobase + CQSPI_REG_IRQSTATUS);
+
+	/* Clear interrupt */
+	writel(irq_status, cqspi->iobase + CQSPI_REG_IRQSTATUS);
+
+	irq_status &= CQSPI_IRQ_MASK_RD | CQSPI_IRQ_MASK_WR;
+
+	if (irq_status)
+		complete(&cqspi->transfer_complete);
+
+	return IRQ_HANDLED;
+}
+
+static unsigned int cqspi_calc_rdreg(struct spi_nor *nor, const u8 opcode)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	u32 rdreg = 0;
+
+	rdreg |= f_pdata->inst_width << CQSPI_REG_RD_INSTR_TYPE_INSTR_LSB;
+	rdreg |= f_pdata->addr_width << CQSPI_REG_RD_INSTR_TYPE_ADDR_LSB;
+	rdreg |= f_pdata->data_width << CQSPI_REG_RD_INSTR_TYPE_DATA_LSB;
+
+	return rdreg;
+}
+
+static int cqspi_wait_idle(struct cqspi_st *cqspi)
+{
+	const unsigned int poll_idle_retry = 3;
+	unsigned int count = 0;
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(CQSPI_TIMEOUT_MS);
+	while (1) {
+		/*
+		 * Read few times in succession to ensure the controller
+		 * is indeed idle, that is, the bit does not transition
+		 * low again.
+		 */
+		if (cqspi_is_idle(cqspi))
+			count++;
+		else
+			count = 0;
+
+		if (count >= poll_idle_retry)
+			return 0;
+
+		if (time_after(jiffies, timeout)) {
+			/* Timeout, in busy mode. */
+			dev_err(&cqspi->pdev->dev,
+				"QSPI is still busy after %dms timeout.\n",
+				CQSPI_TIMEOUT_MS);
+			return -ETIMEDOUT;
+		}
+
+		cpu_relax();
+	}
+}
+
+static int cqspi_exec_flash_cmd(struct cqspi_st *cqspi, unsigned int reg)
+{
+	void __iomem *reg_base = cqspi->iobase;
+	int ret;
+
+	/* Write the CMDCTRL without start execution. */
+	writel(reg, reg_base + CQSPI_REG_CMDCTRL);
+	/* Start execute */
+	reg |= CQSPI_REG_CMDCTRL_EXECUTE_MASK;
+	writel(reg, reg_base + CQSPI_REG_CMDCTRL);
+
+	/* Polling for completion. */
+	ret = cqspi_wait_for_bit(reg_base + CQSPI_REG_CMDCTRL,
+				 CQSPI_REG_CMDCTRL_INPROGRESS_MASK, 1);
+	if (ret) {
+		dev_err(&cqspi->pdev->dev,
+			"Flash command execution timed out.\n");
+		return ret;
+	}
+
+	/* Polling QSPI idle status. */
+	return cqspi_wait_idle(cqspi);
+}
+
+static int cqspi_command_read(struct spi_nor *nor,
+			      const u8 *txbuf, const unsigned n_tx,
+			      u8 *rxbuf, const unsigned n_rx)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int rdreg;
+	unsigned int reg;
+	unsigned int read_len;
+	int status;
+
+	if (!n_rx || n_rx > CQSPI_STIG_DATA_LEN_MAX || !rxbuf) {
+		dev_err(nor->dev, "Invalid input argument, len %d rxbuf 0x%p\n",
+			n_rx, rxbuf);
+		return -EINVAL;
+	}
+
+	reg = txbuf[0] << CQSPI_REG_CMDCTRL_OPCODE_LSB;
+
+	rdreg = cqspi_calc_rdreg(nor, txbuf[0]);
+	writel(rdreg, reg_base + CQSPI_REG_RD_INSTR);
+
+	reg |= (0x1 << CQSPI_REG_CMDCTRL_RD_EN_LSB);
+
+	/* 0 means 1 byte. */
+	reg |= (((n_rx - 1) & CQSPI_REG_CMDCTRL_RD_BYTES_MASK)
+		<< CQSPI_REG_CMDCTRL_RD_BYTES_LSB);
+	status = cqspi_exec_flash_cmd(cqspi, reg);
+	if (status)
+		return status;
+
+	reg = readl(reg_base + CQSPI_REG_CMDREADDATALOWER);
+
+	/* Put the read value into rx_buf */
+	read_len = (n_rx > 4) ? 4 : n_rx;
+	memcpy(rxbuf, &reg, read_len);
+	rxbuf += read_len;
+
+	if (n_rx > 4) {
+		reg = readl(reg_base + CQSPI_REG_CMDREADDATAUPPER);
+
+		read_len = n_rx - read_len;
+		memcpy(rxbuf, &reg, read_len);
+	}
+
+	return 0;
+}
+
+static int cqspi_command_write(struct spi_nor *nor, const u8 opcode,
+			       const u8 *txbuf, const unsigned n_tx)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int reg;
+	unsigned int data;
+	int ret;
+
+	if (n_tx > 4 || (n_tx && !txbuf)) {
+		dev_err(nor->dev,
+			"Invalid input argument, cmdlen %d txbuf 0x%p\n",
+			n_tx, txbuf);
+		return -EINVAL;
+	}
+
+	reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
+	if (n_tx) {
+		reg |= (0x1 << CQSPI_REG_CMDCTRL_WR_EN_LSB);
+		reg |= ((n_tx - 1) & CQSPI_REG_CMDCTRL_WR_BYTES_MASK)
+			<< CQSPI_REG_CMDCTRL_WR_BYTES_LSB;
+		data = 0;
+		memcpy(&data, txbuf, n_tx);
+		writel(data, reg_base + CQSPI_REG_CMDWRITEDATALOWER);
+	}
+
+	ret = cqspi_exec_flash_cmd(cqspi, reg);
+	return ret;
+}
+
+static int cqspi_command_write_addr(struct spi_nor *nor,
+				    const u8 opcode, const unsigned int addr)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int reg;
+
+	reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
+	reg |= (0x1 << CQSPI_REG_CMDCTRL_ADDR_EN_LSB);
+	reg |= ((nor->addr_width - 1) & CQSPI_REG_CMDCTRL_ADD_BYTES_MASK)
+		<< CQSPI_REG_CMDCTRL_ADD_BYTES_LSB;
+
+	writel(addr, reg_base + CQSPI_REG_CMDADDRESS);
+
+	return cqspi_exec_flash_cmd(cqspi, reg);
+}
+
+static int cqspi_indirect_read_setup(struct spi_nor *nor,
+				     const unsigned int from_addr)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int dummy_clk = 0;
+	unsigned int reg;
+
+	writel(from_addr, reg_base + CQSPI_REG_INDIRECTRDSTARTADDR);
+
+	reg = nor->read_opcode << CQSPI_REG_RD_INSTR_OPCODE_LSB;
+	reg |= cqspi_calc_rdreg(nor, nor->read_opcode);
+
+	/* Setup dummy clock cycles */
+	dummy_clk = nor->read_dummy;
+	if (dummy_clk > CQSPI_DUMMY_CLKS_MAX)
+		dummy_clk = CQSPI_DUMMY_CLKS_MAX;
+
+	if (dummy_clk / 8) {
+		reg |= (1 << CQSPI_REG_RD_INSTR_MODE_EN_LSB);
+		/* Set mode bits high to ensure chip doesn't enter XIP */
+		writel(0xFF, reg_base + CQSPI_REG_MODE_BIT);
+
+		/* Need to subtract the mode byte (8 clocks). */
+		if (f_pdata->inst_width != CQSPI_INST_TYPE_QUAD)
+			dummy_clk -= 8;
+
+		if (dummy_clk)
+			reg |= (dummy_clk & CQSPI_REG_RD_INSTR_DUMMY_MASK)
+			       << CQSPI_REG_RD_INSTR_DUMMY_LSB;
+	}
+
+	writel(reg, reg_base + CQSPI_REG_RD_INSTR);
+
+	/* Set address width */
+	reg = readl(reg_base + CQSPI_REG_SIZE);
+	reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
+	reg |= (nor->addr_width - 1);
+	writel(reg, reg_base + CQSPI_REG_SIZE);
+	return 0;
+}
+
+static int cqspi_indirect_read_execute(struct spi_nor *nor,
+				       u8 *rxbuf, const unsigned n_rx)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	void __iomem *ahb_base = cqspi->ahb_base;
+	unsigned int remaining = n_rx;
+	unsigned int bytes_to_read = 0;
+	int ret = 0;
+
+	writel(remaining, reg_base + CQSPI_REG_INDIRECTRDBYTES);
+
+	/* Clear all interrupts. */
+	writel(CQSPI_IRQ_STATUS_MASK, reg_base + CQSPI_REG_IRQSTATUS);
+
+	writel(CQSPI_IRQ_MASK_RD, reg_base + CQSPI_REG_IRQMASK);
+
+	reinit_completion(&cqspi->transfer_complete);
+	writel(CQSPI_REG_INDIRECTRD_START_MASK,
+	       reg_base + CQSPI_REG_INDIRECTRD);
+
+	while (remaining > 0) {
+		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
+						  msecs_to_jiffies
+						  (CQSPI_READ_TIMEOUT_MS));
+
+		bytes_to_read = cqspi_get_rd_sram_level(cqspi);
+
+		if (!ret && bytes_to_read == 0) {
+			dev_err(nor->dev, "Indirect read timeout, no bytes\n");
+			ret = -ETIMEDOUT;
+			goto failrd;
+		}
+
+		while (bytes_to_read != 0) {
+			bytes_to_read *= cqspi->fifo_width;
+			bytes_to_read = bytes_to_read > remaining ?
+					remaining : bytes_to_read;
+			readsl(ahb_base, rxbuf, DIV_ROUND_UP(bytes_to_read, 4));
+			rxbuf += bytes_to_read;
+			remaining -= bytes_to_read;
+			bytes_to_read = cqspi_get_rd_sram_level(cqspi);
+		}
+
+		if (remaining > 0)
+			reinit_completion(&cqspi->transfer_complete);
+	}
+
+	/* Check indirect done status */
+	ret = cqspi_wait_for_bit(reg_base + CQSPI_REG_INDIRECTRD,
+				 CQSPI_REG_INDIRECTRD_DONE_MASK, 0);
+	if (ret) {
+		dev_err(nor->dev,
+			"Indirect read completion error (%i)\n", ret);
+		goto failrd;
+	}
+
+	/* Disable interrupt */
+	writel(0, reg_base + CQSPI_REG_IRQMASK);
+
+	/* Clear indirect completion status */
+	writel(CQSPI_REG_INDIRECTRD_DONE_MASK, reg_base + CQSPI_REG_INDIRECTRD);
+
+	return 0;
+
+failrd:
+	/* Disable interrupt */
+	writel(0, reg_base + CQSPI_REG_IRQMASK);
+
+	/* Cancel the indirect read */
+	writel(CQSPI_REG_INDIRECTWR_CANCEL_MASK,
+	       reg_base + CQSPI_REG_INDIRECTRD);
+	return ret;
+}
+
+static int cqspi_indirect_write_setup(struct spi_nor *nor,
+				      const unsigned int to_addr)
+{
+	unsigned int reg;
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+
+	/* Set opcode. */
+	reg = nor->program_opcode << CQSPI_REG_WR_INSTR_OPCODE_LSB;
+	writel(reg, reg_base + CQSPI_REG_WR_INSTR);
+	reg = cqspi_calc_rdreg(nor, nor->program_opcode);
+	writel(reg, reg_base + CQSPI_REG_RD_INSTR);
+
+	writel(to_addr, reg_base + CQSPI_REG_INDIRECTWRSTARTADDR);
+
+	reg = readl(reg_base + CQSPI_REG_SIZE);
+	reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
+	reg |= (nor->addr_width - 1);
+	writel(reg, reg_base + CQSPI_REG_SIZE);
+	return 0;
+}
+
+static int cqspi_indirect_write_execute(struct spi_nor *nor,
+					const u8 *txbuf, const unsigned n_tx)
+{
+	const unsigned int page_size = nor->page_size;
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int remaining = n_tx;
+	unsigned int write_bytes;
+	int ret;
+
+	writel(remaining, reg_base + CQSPI_REG_INDIRECTWRBYTES);
+
+	/* Clear all interrupts. */
+	writel(CQSPI_IRQ_STATUS_MASK, reg_base + CQSPI_REG_IRQSTATUS);
+
+	writel(CQSPI_IRQ_MASK_WR, reg_base + CQSPI_REG_IRQMASK);
+
+	reinit_completion(&cqspi->transfer_complete);
+	writel(CQSPI_REG_INDIRECTWR_START_MASK,
+	       reg_base + CQSPI_REG_INDIRECTWR);
+
+	while (remaining > 0) {
+		write_bytes = remaining > page_size ? page_size : remaining;
+		writesl(cqspi->ahb_base, txbuf, DIV_ROUND_UP(write_bytes, 4));
+
+		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
+						  msecs_to_jiffies
+						  (CQSPI_TIMEOUT_MS));
+		if (!ret) {
+			dev_err(nor->dev, "Indirect write timeout\n");
+			ret = -ETIMEDOUT;
+			goto failwr;
+		}
+
+		txbuf += write_bytes;
+		remaining -= write_bytes;
+
+		if (remaining > 0)
+			reinit_completion(&cqspi->transfer_complete);
+	}
+
+	/* Check indirect done status */
+	ret = cqspi_wait_for_bit(reg_base + CQSPI_REG_INDIRECTWR,
+				 CQSPI_REG_INDIRECTWR_DONE_MASK, 0);
+	if (ret) {
+		dev_err(nor->dev,
+			"Indirect write completion error (%i)\n", ret);
+		goto failwr;
+	}
+
+	/* Disable interrupt. */
+	writel(0, reg_base + CQSPI_REG_IRQMASK);
+
+	/* Clear indirect completion status */
+	writel(CQSPI_REG_INDIRECTWR_DONE_MASK, reg_base + CQSPI_REG_INDIRECTWR);
+
+	cqspi_wait_idle(cqspi);
+
+	return 0;
+
+failwr:
+	/* Disable interrupt. */
+	writel(0, reg_base + CQSPI_REG_IRQMASK);
+
+	/* Cancel the indirect write */
+	writel(CQSPI_REG_INDIRECTWR_CANCEL_MASK,
+	       reg_base + CQSPI_REG_INDIRECTWR);
+	return ret;
+}
+
+static void cqspi_chipselect(struct spi_nor *nor)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int chip_select = f_pdata->cs;
+	unsigned int reg;
+
+	reg = readl(reg_base + CQSPI_REG_CONFIG);
+	if (cqspi->is_decoded_cs) {
+		reg |= CQSPI_REG_CONFIG_DECODE_MASK;
+	} else {
+		reg &= ~CQSPI_REG_CONFIG_DECODE_MASK;
+
+		/* Convert CS if without decoder.
+		 * CS0 to 4b'1110
+		 * CS1 to 4b'1101
+		 * CS2 to 4b'1011
+		 * CS3 to 4b'0111
+		 */
+		chip_select = 0xF & ~(1 << chip_select);
+	}
+
+	reg &= ~(CQSPI_REG_CONFIG_CHIPSELECT_MASK
+		 << CQSPI_REG_CONFIG_CHIPSELECT_LSB);
+	reg |= (chip_select & CQSPI_REG_CONFIG_CHIPSELECT_MASK)
+	    << CQSPI_REG_CONFIG_CHIPSELECT_LSB;
+	writel(reg, reg_base + CQSPI_REG_CONFIG);
+}
+
+static void cqspi_configure_cs_and_sizes(struct spi_nor *nor)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *iobase = cqspi->iobase;
+	unsigned int reg;
+
+	/* configure page size and block size. */
+	reg = readl(iobase + CQSPI_REG_SIZE);
+	reg &= ~(CQSPI_REG_SIZE_PAGE_MASK << CQSPI_REG_SIZE_PAGE_LSB);
+	reg &= ~(CQSPI_REG_SIZE_BLOCK_MASK << CQSPI_REG_SIZE_BLOCK_LSB);
+	reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
+	reg |= (nor->page_size << CQSPI_REG_SIZE_PAGE_LSB);
+	reg |= (ilog2(nor->mtd.erasesize) << CQSPI_REG_SIZE_BLOCK_LSB);
+	reg |= (nor->addr_width - 1);
+	writel(reg, iobase + CQSPI_REG_SIZE);
+
+	/* configure the chip select */
+	cqspi_chipselect(nor);
+
+	/* Store the new configuration of the controller */
+	cqspi->current_page_size = nor->page_size;
+	cqspi->current_erase_size = nor->mtd.erasesize;
+	cqspi->current_addr_width = nor->addr_width;
+}
+
+static unsigned int calculate_ticks_for_ns(const unsigned int ref_clk_hz,
+					   const unsigned int ns_val)
+{
+	unsigned int ticks;
+
+	ticks = ref_clk_hz / 1000;	/* kHz */
+	ticks = DIV_ROUND_UP(ticks * ns_val, 1000000);
+
+	return ticks;
+}
+
+static void cqspi_delay(struct spi_nor *nor)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *iobase = cqspi->iobase;
+	const unsigned int ref_clk_hz = cqspi->master_ref_clk_hz;
+	unsigned int tshsl, tchsh, tslch, tsd2d;
+	unsigned int reg;
+	unsigned int tsclk;
+
+	/* calculate the number of ref ticks for one sclk tick */
+	tsclk = DIV_ROUND_UP(ref_clk_hz, cqspi->sclk);
+
+	tshsl = calculate_ticks_for_ns(ref_clk_hz, f_pdata->tshsl_ns);
+	/* this particular value must be at least one sclk */
+	if (tshsl < tsclk)
+		tshsl = tsclk;
+
+	tchsh = calculate_ticks_for_ns(ref_clk_hz, f_pdata->tchsh_ns);
+	tslch = calculate_ticks_for_ns(ref_clk_hz, f_pdata->tslch_ns);
+	tsd2d = calculate_ticks_for_ns(ref_clk_hz, f_pdata->tsd2d_ns);
+
+	reg = (tshsl & CQSPI_REG_DELAY_TSHSL_MASK)
+	       << CQSPI_REG_DELAY_TSHSL_LSB;
+	reg |= (tchsh & CQSPI_REG_DELAY_TCHSH_MASK)
+		<< CQSPI_REG_DELAY_TCHSH_LSB;
+	reg |= (tslch & CQSPI_REG_DELAY_TSLCH_MASK)
+		<< CQSPI_REG_DELAY_TSLCH_LSB;
+	reg |= (tsd2d & CQSPI_REG_DELAY_TSD2D_MASK)
+		<< CQSPI_REG_DELAY_TSD2D_LSB;
+	writel(reg, iobase + CQSPI_REG_DELAY);
+}
+
+static void cqspi_config_baudrate_div(struct cqspi_st *cqspi)
+{
+	const unsigned int ref_clk_hz = cqspi->master_ref_clk_hz;
+	void __iomem *reg_base = cqspi->iobase;
+	u32 reg, div;
+
+	/* Recalculate the baudrate divisor based on QSPI specification. */
+	div = DIV_ROUND_UP(ref_clk_hz, 2 * cqspi->sclk) - 1;
+
+	reg = readl(reg_base + CQSPI_REG_CONFIG);
+	reg &= ~(CQSPI_REG_CONFIG_BAUD_MASK << CQSPI_REG_CONFIG_BAUD_LSB);
+	reg |= (div & CQSPI_REG_CONFIG_BAUD_MASK) << CQSPI_REG_CONFIG_BAUD_LSB;
+	writel(reg, reg_base + CQSPI_REG_CONFIG);
+}
+
+static void cqspi_readdata_capture(struct cqspi_st *cqspi,
+				   const unsigned int bypass,
+				   const unsigned int delay)
+{
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int reg;
+
+	reg = readl(reg_base + CQSPI_REG_READCAPTURE);
+
+	if (bypass)
+		reg |= (1 << CQSPI_REG_READCAPTURE_BYPASS_LSB);
+	else
+		reg &= ~(1 << CQSPI_REG_READCAPTURE_BYPASS_LSB);
+
+	reg &= ~(CQSPI_REG_READCAPTURE_DELAY_MASK
+		 << CQSPI_REG_READCAPTURE_DELAY_LSB);
+
+	reg |= (delay & CQSPI_REG_READCAPTURE_DELAY_MASK)
+		<< CQSPI_REG_READCAPTURE_DELAY_LSB;
+
+	writel(reg, reg_base + CQSPI_REG_READCAPTURE);
+}
+
+static void cqspi_controller_enable(struct cqspi_st *cqspi, bool enable)
+{
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int reg;
+
+	reg = readl(reg_base + CQSPI_REG_CONFIG);
+
+	if (enable)
+		reg |= CQSPI_REG_CONFIG_ENABLE_MASK;
+	else
+		reg &= ~CQSPI_REG_CONFIG_ENABLE_MASK;
+
+	writel(reg, reg_base + CQSPI_REG_CONFIG);
+}
+
+static void cqspi_configure(struct spi_nor *nor)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	const unsigned int sclk = f_pdata->clk_rate;
+	int switch_cs = (cqspi->current_cs != f_pdata->cs);
+	int switch_ck = (cqspi->sclk != sclk);
+
+	if ((cqspi->current_page_size != nor->page_size) ||
+	    (cqspi->current_erase_size != nor->mtd.erasesize) ||
+	    (cqspi->current_addr_width != nor->addr_width))
+		switch_cs = 1;
+
+	if (switch_cs || switch_ck)
+		cqspi_controller_enable(cqspi, 0);
+
+	/* Switch chip select. */
+	if (switch_cs) {
+		cqspi->current_cs = f_pdata->cs;
+		cqspi_configure_cs_and_sizes(nor);
+	}
+
+	/* Setup baudrate divisor and delays */
+	if (switch_ck) {
+		cqspi->sclk = sclk;
+		cqspi_config_baudrate_div(cqspi);
+		cqspi_delay(nor);
+		cqspi_readdata_capture(cqspi, 1, f_pdata->read_delay);
+	}
+
+	if (switch_cs || switch_ck)
+		cqspi_controller_enable(cqspi, 1);
+}
+
+static int cqspi_set_protocol(struct spi_nor *nor, const int read)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+
+	f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE;
+	f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE;
+	f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
+
+	if (read) {
+		switch (nor->flash_read) {
+		case SPI_NOR_NORMAL:
+		case SPI_NOR_FAST:
+			f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
+			break;
+		case SPI_NOR_DUAL:
+			f_pdata->data_width = CQSPI_INST_TYPE_DUAL;
+			break;
+		case SPI_NOR_QUAD:
+			f_pdata->data_width = CQSPI_INST_TYPE_QUAD;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	cqspi_configure(nor);
+
+	return 0;
+}
+
+static ssize_t cqspi_write(struct spi_nor *nor, loff_t to,
+			   size_t len, const u_char *buf)
+{
+	int ret;
+
+	ret = cqspi_set_protocol(nor, 0);
+	if (ret)
+		return ret;
+
+	ret = cqspi_indirect_write_setup(nor, to);
+	if (ret)
+		return ret;
+
+	ret = cqspi_indirect_write_execute(nor, buf, len);
+	if (ret)
+		return ret;
+
+	return (ret < 0) ? ret : len;
+}
+
+static ssize_t cqspi_read(struct spi_nor *nor, loff_t from,
+			  size_t len, u_char *buf)
+{
+	int ret;
+
+	ret = cqspi_set_protocol(nor, 1);
+	if (ret)
+		return ret;
+
+	ret = cqspi_indirect_read_setup(nor, from);
+	if (ret)
+		return ret;
+
+	ret = cqspi_indirect_read_execute(nor, buf, len);
+	if (ret)
+		return ret;
+
+	return (ret < 0) ? ret : len;
+}
+
+static int cqspi_erase(struct spi_nor *nor, loff_t offs)
+{
+	int ret;
+
+	ret = cqspi_set_protocol(nor, 0);
+	if (ret)
+		return ret;
+
+	/* Send write enable, then erase commands. */
+	ret = nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0);
+	if (ret)
+		return ret;
+
+	/* Set up command buffer. */
+	ret = cqspi_command_write_addr(nor, nor->erase_opcode, offs);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int cqspi_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+
+	mutex_lock(&cqspi->bus_mutex);
+
+	return 0;
+}
+
+static void cqspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	struct cqspi_flash_pdata *f_pdata = nor->priv;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+
+	mutex_unlock(&cqspi->bus_mutex);
+}
+
+static int cqspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+	int ret;
+
+	ret = cqspi_set_protocol(nor, 0);
+	if (!ret)
+		ret = cqspi_command_read(nor, &opcode, 1, buf, len);
+
+	return ret;
+}
+
+static int cqspi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+	int ret;
+
+	ret = cqspi_set_protocol(nor, 0);
+	if (!ret)
+		ret = cqspi_command_write(nor, opcode, buf, len);
+
+	return ret;
+}
+
+static int cqspi_of_get_flash_pdata(struct platform_device *pdev,
+				    struct cqspi_flash_pdata *f_pdata,
+				    struct device_node *np)
+{
+	if (of_property_read_u32(np, "cdns,read-delay", &f_pdata->read_delay)) {
+		dev_err(&pdev->dev, "couldn't determine read-delay\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,tshsl-ns", &f_pdata->tshsl_ns)) {
+		dev_err(&pdev->dev, "couldn't determine tshsl-ns\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,tsd2d-ns", &f_pdata->tsd2d_ns)) {
+		dev_err(&pdev->dev, "couldn't determine tsd2d-ns\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,tchsh-ns", &f_pdata->tchsh_ns)) {
+		dev_err(&pdev->dev, "couldn't determine tchsh-ns\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,tslch-ns", &f_pdata->tslch_ns)) {
+		dev_err(&pdev->dev, "couldn't determine tslch-ns\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "spi-max-frequency", &f_pdata->clk_rate)) {
+		dev_err(&pdev->dev, "couldn't determine spi-max-frequency\n");
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int cqspi_of_get_pdata(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct cqspi_st *cqspi = platform_get_drvdata(pdev);
+
+	cqspi->is_decoded_cs = of_property_read_bool(np, "cdns,is-decoded-cs");
+
+	if (of_property_read_u32(np, "cdns,fifo-depth", &cqspi->fifo_depth)) {
+		dev_err(&pdev->dev, "couldn't determine fifo-depth\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,fifo-width", &cqspi->fifo_width)) {
+		dev_err(&pdev->dev, "couldn't determine fifo-width\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,trigger-address",
+				 &cqspi->trigger_address)) {
+		dev_err(&pdev->dev, "couldn't determine trigger-address\n");
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static void cqspi_controller_init(struct cqspi_st *cqspi)
+{
+	cqspi_controller_enable(cqspi, 0);
+
+	/* Configure the remap address register, no remap */
+	writel(0, cqspi->iobase + CQSPI_REG_REMAP);
+
+	/* Disable all interrupts. */
+	writel(0, cqspi->iobase + CQSPI_REG_IRQMASK);
+
+	/* Configure the SRAM split to 1:1 . */
+	writel(cqspi->fifo_depth / 2, cqspi->iobase + CQSPI_REG_SRAMPARTITION);
+
+	/* Load indirect trigger address. */
+	writel(cqspi->trigger_address,
+	       cqspi->iobase + CQSPI_REG_INDIRECTTRIGGER);
+
+	/* Program read watermark -- 1/2 of the FIFO. */
+	writel(cqspi->fifo_depth * cqspi->fifo_width / 2,
+	       cqspi->iobase + CQSPI_REG_INDIRECTRDWATERMARK);
+	/* Program write watermark -- 1/8 of the FIFO. */
+	writel(cqspi->fifo_depth * cqspi->fifo_width / 8,
+	       cqspi->iobase + CQSPI_REG_INDIRECTWRWATERMARK);
+
+	cqspi_controller_enable(cqspi, 1);
+}
+
+static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np)
+{
+	struct platform_device *pdev = cqspi->pdev;
+	struct device *dev = &pdev->dev;
+	struct cqspi_flash_pdata *f_pdata;
+	struct spi_nor *nor;
+	struct mtd_info *mtd;
+	unsigned int cs;
+	int i, ret;
+
+	/* Get flash device data */
+	for_each_available_child_of_node(dev->of_node, np) {
+		if (of_property_read_u32(np, "reg", &cs)) {
+			dev_err(dev, "Couldn't determine chip select.\n");
+			goto err;
+		}
+
+		if (cs > CQSPI_MAX_CHIPSELECT) {
+			dev_err(dev, "Chip select %d out of range.\n", cs);
+			goto err;
+		}
+
+		f_pdata = &cqspi->f_pdata[cs];
+		f_pdata->cqspi = cqspi;
+		f_pdata->cs = cs;
+
+		ret = cqspi_of_get_flash_pdata(pdev, f_pdata, np);
+		if (ret)
+			goto err;
+
+		nor = &f_pdata->nor;
+		mtd = &nor->mtd;
+
+		mtd->priv = nor;
+
+		nor->dev = dev;
+		spi_nor_set_flash_node(nor, np);
+		nor->priv = f_pdata;
+
+		nor->read_reg = cqspi_read_reg;
+		nor->write_reg = cqspi_write_reg;
+		nor->read = cqspi_read;
+		nor->write = cqspi_write;
+		nor->erase = cqspi_erase;
+		nor->prepare = cqspi_prep;
+		nor->unprepare = cqspi_unprep;
+
+		mtd->name = devm_kasprintf(dev, GFP_KERNEL, "%s.%d",
+					   dev_name(dev), cs);
+		if (!mtd->name) {
+			ret = -ENOMEM;
+			goto err;
+		}
+
+		ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+		if (ret)
+			goto err;
+
+		ret = mtd_device_register(mtd, NULL, 0);
+		if (ret)
+			goto err;
+
+		f_pdata->registered = true;
+	}
+
+	return 0;
+
+err:
+	for (i = 0; i < CQSPI_MAX_CHIPSELECT; i++)
+		if (cqspi->f_pdata[i].registered)
+			mtd_device_unregister(&cqspi->f_pdata[i].nor.mtd);
+	return ret;
+}
+
+static int cqspi_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct device *dev = &pdev->dev;
+	struct cqspi_st *cqspi;
+	struct resource *res;
+	struct resource *res_ahb;
+	int ret;
+	int irq;
+
+	cqspi = devm_kzalloc(dev, sizeof(*cqspi), GFP_KERNEL);
+	if (!cqspi)
+		return -ENOMEM;
+
+	mutex_init(&cqspi->bus_mutex);
+	cqspi->pdev = pdev;
+	platform_set_drvdata(pdev, cqspi);
+
+	/* Obtain configuration from OF. */
+	ret = cqspi_of_get_pdata(pdev);
+	if (ret) {
+		dev_err(dev, "Cannot get mandatory OF data.\n");
+		return -ENODEV;
+	}
+
+	/* Obtain QSPI clock. */
+	cqspi->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(cqspi->clk)) {
+		dev_err(dev, "Cannot claim QSPI clock.\n");
+		return PTR_ERR(cqspi->clk);
+	}
+
+	/* Obtain and remap controller address. */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	cqspi->iobase = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cqspi->iobase)) {
+		dev_err(dev, "Cannot remap controller address.\n");
+		return PTR_ERR(cqspi->iobase);
+	}
+
+	/* Obtain and remap AHB address. */
+	res_ahb = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	cqspi->ahb_base = devm_ioremap_resource(dev, res_ahb);
+	if (IS_ERR(cqspi->ahb_base)) {
+		dev_err(dev, "Cannot remap AHB address.\n");
+		return PTR_ERR(cqspi->ahb_base);
+	}
+
+	init_completion(&cqspi->transfer_complete);
+
+	/* Obtain IRQ line. */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "Cannot obtain IRQ.\n");
+		return -ENXIO;
+	}
+
+	ret = clk_prepare_enable(cqspi->clk);
+	if (ret) {
+		dev_err(dev, "Cannot enable QSPI clock.\n");
+		return ret;
+	}
+
+	cqspi->master_ref_clk_hz = clk_get_rate(cqspi->clk);
+
+	ret = devm_request_irq(dev, irq, cqspi_irq_handler, 0,
+			       pdev->name, cqspi);
+	if (ret) {
+		dev_err(dev, "Cannot request IRQ.\n");
+		goto probe_irq_failed;
+	}
+
+	cqspi_wait_idle(cqspi);
+	cqspi_controller_init(cqspi);
+	cqspi->current_cs = -1;
+	cqspi->sclk = 0;
+
+	ret = cqspi_setup_flash(cqspi, np);
+	if (ret) {
+		dev_err(dev, "Cadence QSPI NOR probe failed %d\n", ret);
+		goto probe_setup_failed;
+	}
+
+	return ret;
+probe_irq_failed:
+	cqspi_controller_enable(cqspi, 0);
+probe_setup_failed:
+	clk_disable_unprepare(cqspi->clk);
+	return ret;
+}
+
+static int cqspi_remove(struct platform_device *pdev)
+{
+	struct cqspi_st *cqspi = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < CQSPI_MAX_CHIPSELECT; i++)
+		if (cqspi->f_pdata[i].registered)
+			mtd_device_unregister(&cqspi->f_pdata[i].nor.mtd);
+
+	cqspi_controller_enable(cqspi, 0);
+
+	clk_disable_unprepare(cqspi->clk);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int cqspi_suspend(struct device *dev)
+{
+	struct cqspi_st *cqspi = dev_get_drvdata(dev);
+
+	cqspi_controller_enable(cqspi, 0);
+	return 0;
+}
+
+static int cqspi_resume(struct device *dev)
+{
+	struct cqspi_st *cqspi = dev_get_drvdata(dev);
+
+	cqspi_controller_enable(cqspi, 1);
+	return 0;
+}
+
+static const struct dev_pm_ops cqspi__dev_pm_ops = {
+	.suspend = cqspi_suspend,
+	.resume = cqspi_resume,
+};
+
+#define CQSPI_DEV_PM_OPS	(&cqspi__dev_pm_ops)
+#else
+#define CQSPI_DEV_PM_OPS	NULL
+#endif
+
+static struct of_device_id const cqspi_dt_ids[] = {
+	{.compatible = "cdns,qspi-nor",},
+	{ /* end of table */ }
+};
+
+MODULE_DEVICE_TABLE(of, cqspi_dt_ids);
+
+static struct platform_driver cqspi_platform_driver = {
+	.probe = cqspi_probe,
+	.remove = cqspi_remove,
+	.driver = {
+		.name = CQSPI_NAME,
+		.pm = CQSPI_DEV_PM_OPS,
+		.of_match_table = cqspi_dt_ids,
+	},
+};
+
+module_platform_driver(cqspi_platform_driver);
+
+MODULE_DESCRIPTION("Cadence QSPI Controller Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:" CQSPI_NAME);
+MODULE_AUTHOR("Ley Foon Tan <lftan@altera.com>");
+MODULE_AUTHOR("Graham Moore <grmoore@opensource.altera.com>");
diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c
index 9ab2b51d54b8..5c82e4ef1904 100644
--- a/drivers/mtd/spi-nor/fsl-quadspi.c
+++ b/drivers/mtd/spi-nor/fsl-quadspi.c
@@ -618,9 +618,9 @@ static inline void fsl_qspi_invalid(struct fsl_qspi *q)
 	qspi_writel(q, reg, q->iobase + QUADSPI_MCR);
 }
 
-static int fsl_qspi_nor_write(struct fsl_qspi *q, struct spi_nor *nor,
+static ssize_t fsl_qspi_nor_write(struct fsl_qspi *q, struct spi_nor *nor,
 				u8 opcode, unsigned int to, u32 *txbuf,
-				unsigned count, size_t *retlen)
+				unsigned count)
 {
 	int ret, i, j;
 	u32 tmp;
@@ -647,8 +647,8 @@ static int fsl_qspi_nor_write(struct fsl_qspi *q, struct spi_nor *nor,
 	/* Trigger it */
 	ret = fsl_qspi_runcmd(q, opcode, to, count);
 
-	if (ret == 0 && retlen)
-		*retlen += count;
+	if (ret == 0)
+		return count;
 
 	return ret;
 }
@@ -859,7 +859,9 @@ static int fsl_qspi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 
 	} else if (len > 0) {
 		ret = fsl_qspi_nor_write(q, nor, opcode, 0,
-					(u32 *)buf, len, NULL);
+					(u32 *)buf, len);
+		if (ret > 0)
+			return 0;
 	} else {
 		dev_err(q->dev, "invalid cmd %d\n", opcode);
 		ret = -EINVAL;
@@ -868,20 +870,20 @@ static int fsl_qspi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return ret;
 }
 
-static void fsl_qspi_write(struct spi_nor *nor, loff_t to,
-		size_t len, size_t *retlen, const u_char *buf)
+static ssize_t fsl_qspi_write(struct spi_nor *nor, loff_t to,
+			      size_t len, const u_char *buf)
 {
 	struct fsl_qspi *q = nor->priv;
-
-	fsl_qspi_nor_write(q, nor, nor->program_opcode, to,
-				(u32 *)buf, len, retlen);
+	ssize_t ret = fsl_qspi_nor_write(q, nor, nor->program_opcode, to,
+					 (u32 *)buf, len);
 
 	/* invalid the data in the AHB buffer. */
 	fsl_qspi_invalid(q);
+	return ret;
 }
 
-static int fsl_qspi_read(struct spi_nor *nor, loff_t from,
-		size_t len, size_t *retlen, u_char *buf)
+static ssize_t fsl_qspi_read(struct spi_nor *nor, loff_t from,
+			     size_t len, u_char *buf)
 {
 	struct fsl_qspi *q = nor->priv;
 	u8 cmd = nor->read_opcode;
@@ -923,8 +925,7 @@ static int fsl_qspi_read(struct spi_nor *nor, loff_t from,
 	memcpy(buf, q->ahb_addr + q->chip_base_addr + from - q->memmap_offs,
 		len);
 
-	*retlen += len;
-	return 0;
+	return len;
 }
 
 static int fsl_qspi_erase(struct spi_nor *nor, loff_t offs)
diff --git a/drivers/mtd/spi-nor/hisi-sfc.c b/drivers/mtd/spi-nor/hisi-sfc.c
new file mode 100644
index 000000000000..20378b0d55e9
--- /dev/null
+++ b/drivers/mtd/spi-nor/hisi-sfc.c
@@ -0,0 +1,489 @@
+/*
+ * HiSilicon SPI Nor Flash Controller Driver
+ *
+ * Copyright (c) 2015-2016 HiSilicon Technologies Co., Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/spi-nor.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+/* Hardware register offsets and field definitions */
+#define FMC_CFG				0x00
+#define FMC_CFG_OP_MODE_MASK		BIT_MASK(0)
+#define FMC_CFG_OP_MODE_BOOT		0
+#define FMC_CFG_OP_MODE_NORMAL		1
+#define FMC_CFG_FLASH_SEL(type)		(((type) & 0x3) << 1)
+#define FMC_CFG_FLASH_SEL_MASK		0x6
+#define FMC_ECC_TYPE(type)		(((type) & 0x7) << 5)
+#define FMC_ECC_TYPE_MASK		GENMASK(7, 5)
+#define SPI_NOR_ADDR_MODE_MASK		BIT_MASK(10)
+#define SPI_NOR_ADDR_MODE_3BYTES	(0x0 << 10)
+#define SPI_NOR_ADDR_MODE_4BYTES	(0x1 << 10)
+#define FMC_GLOBAL_CFG			0x04
+#define FMC_GLOBAL_CFG_WP_ENABLE	BIT(6)
+#define FMC_SPI_TIMING_CFG		0x08
+#define TIMING_CFG_TCSH(nr)		(((nr) & 0xf) << 8)
+#define TIMING_CFG_TCSS(nr)		(((nr) & 0xf) << 4)
+#define TIMING_CFG_TSHSL(nr)		((nr) & 0xf)
+#define CS_HOLD_TIME			0x6
+#define CS_SETUP_TIME			0x6
+#define CS_DESELECT_TIME		0xf
+#define FMC_INT				0x18
+#define FMC_INT_OP_DONE			BIT(0)
+#define FMC_INT_CLR			0x20
+#define FMC_CMD				0x24
+#define FMC_CMD_CMD1(cmd)		((cmd) & 0xff)
+#define FMC_ADDRL			0x2c
+#define FMC_OP_CFG			0x30
+#define OP_CFG_FM_CS(cs)		((cs) << 11)
+#define OP_CFG_MEM_IF_TYPE(type)	(((type) & 0x7) << 7)
+#define OP_CFG_ADDR_NUM(addr)		(((addr) & 0x7) << 4)
+#define OP_CFG_DUMMY_NUM(dummy)		((dummy) & 0xf)
+#define FMC_DATA_NUM			0x38
+#define FMC_DATA_NUM_CNT(cnt)		((cnt) & GENMASK(13, 0))
+#define FMC_OP				0x3c
+#define FMC_OP_DUMMY_EN			BIT(8)
+#define FMC_OP_CMD1_EN			BIT(7)
+#define FMC_OP_ADDR_EN			BIT(6)
+#define FMC_OP_WRITE_DATA_EN		BIT(5)
+#define FMC_OP_READ_DATA_EN		BIT(2)
+#define FMC_OP_READ_STATUS_EN		BIT(1)
+#define FMC_OP_REG_OP_START		BIT(0)
+#define FMC_DMA_LEN			0x40
+#define FMC_DMA_LEN_SET(len)		((len) & GENMASK(27, 0))
+#define FMC_DMA_SADDR_D0		0x4c
+#define HIFMC_DMA_MAX_LEN		(4096)
+#define HIFMC_DMA_MASK			(HIFMC_DMA_MAX_LEN - 1)
+#define FMC_OP_DMA			0x68
+#define OP_CTRL_RD_OPCODE(code)		(((code) & 0xff) << 16)
+#define OP_CTRL_WR_OPCODE(code)		(((code) & 0xff) << 8)
+#define OP_CTRL_RW_OP(op)		((op) << 1)
+#define OP_CTRL_DMA_OP_READY		BIT(0)
+#define FMC_OP_READ			0x0
+#define FMC_OP_WRITE			0x1
+#define FMC_WAIT_TIMEOUT		1000000
+
+enum hifmc_iftype {
+	IF_TYPE_STD,
+	IF_TYPE_DUAL,
+	IF_TYPE_DIO,
+	IF_TYPE_QUAD,
+	IF_TYPE_QIO,
+};
+
+struct hifmc_priv {
+	u32 chipselect;
+	u32 clkrate;
+	struct hifmc_host *host;
+};
+
+#define HIFMC_MAX_CHIP_NUM		2
+struct hifmc_host {
+	struct device *dev;
+	struct mutex lock;
+
+	void __iomem *regbase;
+	void __iomem *iobase;
+	struct clk *clk;
+	void *buffer;
+	dma_addr_t dma_buffer;
+
+	struct spi_nor	*nor[HIFMC_MAX_CHIP_NUM];
+	u32 num_chip;
+};
+
+static inline int wait_op_finish(struct hifmc_host *host)
+{
+	u32 reg;
+
+	return readl_poll_timeout(host->regbase + FMC_INT, reg,
+		(reg & FMC_INT_OP_DONE), 0, FMC_WAIT_TIMEOUT);
+}
+
+static int get_if_type(enum read_mode flash_read)
+{
+	enum hifmc_iftype if_type;
+
+	switch (flash_read) {
+	case SPI_NOR_DUAL:
+		if_type = IF_TYPE_DUAL;
+		break;
+	case SPI_NOR_QUAD:
+		if_type = IF_TYPE_QUAD;
+		break;
+	case SPI_NOR_NORMAL:
+	case SPI_NOR_FAST:
+	default:
+		if_type = IF_TYPE_STD;
+		break;
+	}
+
+	return if_type;
+}
+
+static void hisi_spi_nor_init(struct hifmc_host *host)
+{
+	u32 reg;
+
+	reg = TIMING_CFG_TCSH(CS_HOLD_TIME)
+		| TIMING_CFG_TCSS(CS_SETUP_TIME)
+		| TIMING_CFG_TSHSL(CS_DESELECT_TIME);
+	writel(reg, host->regbase + FMC_SPI_TIMING_CFG);
+}
+
+static int hisi_spi_nor_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	struct hifmc_priv *priv = nor->priv;
+	struct hifmc_host *host = priv->host;
+	int ret;
+
+	mutex_lock(&host->lock);
+
+	ret = clk_set_rate(host->clk, priv->clkrate);
+	if (ret)
+		goto out;
+
+	ret = clk_prepare_enable(host->clk);
+	if (ret)
+		goto out;
+
+	return 0;
+
+out:
+	mutex_unlock(&host->lock);
+	return ret;
+}
+
+static void hisi_spi_nor_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	struct hifmc_priv *priv = nor->priv;
+	struct hifmc_host *host = priv->host;
+
+	clk_disable_unprepare(host->clk);
+	mutex_unlock(&host->lock);
+}
+
+static int hisi_spi_nor_op_reg(struct spi_nor *nor,
+				u8 opcode, int len, u8 optype)
+{
+	struct hifmc_priv *priv = nor->priv;
+	struct hifmc_host *host = priv->host;
+	u32 reg;
+
+	reg = FMC_CMD_CMD1(opcode);
+	writel(reg, host->regbase + FMC_CMD);
+
+	reg = FMC_DATA_NUM_CNT(len);
+	writel(reg, host->regbase + FMC_DATA_NUM);
+
+	reg = OP_CFG_FM_CS(priv->chipselect);
+	writel(reg, host->regbase + FMC_OP_CFG);
+
+	writel(0xff, host->regbase + FMC_INT_CLR);
+	reg = FMC_OP_CMD1_EN | FMC_OP_REG_OP_START | optype;
+	writel(reg, host->regbase + FMC_OP);
+
+	return wait_op_finish(host);
+}
+
+static int hisi_spi_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
+		int len)
+{
+	struct hifmc_priv *priv = nor->priv;
+	struct hifmc_host *host = priv->host;
+	int ret;
+
+	ret = hisi_spi_nor_op_reg(nor, opcode, len, FMC_OP_READ_DATA_EN);
+	if (ret)
+		return ret;
+
+	memcpy_fromio(buf, host->iobase, len);
+	return 0;
+}
+
+static int hisi_spi_nor_write_reg(struct spi_nor *nor, u8 opcode,
+				u8 *buf, int len)
+{
+	struct hifmc_priv *priv = nor->priv;
+	struct hifmc_host *host = priv->host;
+
+	if (len)
+		memcpy_toio(host->iobase, buf, len);
+
+	return hisi_spi_nor_op_reg(nor, opcode, len, FMC_OP_WRITE_DATA_EN);
+}
+
+static int hisi_spi_nor_dma_transfer(struct spi_nor *nor, loff_t start_off,
+		dma_addr_t dma_buf, size_t len, u8 op_type)
+{
+	struct hifmc_priv *priv = nor->priv;
+	struct hifmc_host *host = priv->host;
+	u8 if_type = 0;
+	u32 reg;
+
+	reg = readl(host->regbase + FMC_CFG);
+	reg &= ~(FMC_CFG_OP_MODE_MASK | SPI_NOR_ADDR_MODE_MASK);
+	reg |= FMC_CFG_OP_MODE_NORMAL;
+	reg |= (nor->addr_width == 4) ? SPI_NOR_ADDR_MODE_4BYTES
+		: SPI_NOR_ADDR_MODE_3BYTES;
+	writel(reg, host->regbase + FMC_CFG);
+
+	writel(start_off, host->regbase + FMC_ADDRL);
+	writel(dma_buf, host->regbase + FMC_DMA_SADDR_D0);
+	writel(FMC_DMA_LEN_SET(len), host->regbase + FMC_DMA_LEN);
+
+	reg = OP_CFG_FM_CS(priv->chipselect);
+	if_type = get_if_type(nor->flash_read);
+	reg |= OP_CFG_MEM_IF_TYPE(if_type);
+	if (op_type == FMC_OP_READ)
+		reg |= OP_CFG_DUMMY_NUM(nor->read_dummy >> 3);
+	writel(reg, host->regbase + FMC_OP_CFG);
+
+	writel(0xff, host->regbase + FMC_INT_CLR);
+	reg = OP_CTRL_RW_OP(op_type) | OP_CTRL_DMA_OP_READY;
+	reg |= (op_type == FMC_OP_READ)
+		? OP_CTRL_RD_OPCODE(nor->read_opcode)
+		: OP_CTRL_WR_OPCODE(nor->program_opcode);
+	writel(reg, host->regbase + FMC_OP_DMA);
+
+	return wait_op_finish(host);
+}
+
+static ssize_t hisi_spi_nor_read(struct spi_nor *nor, loff_t from, size_t len,
+		u_char *read_buf)
+{
+	struct hifmc_priv *priv = nor->priv;
+	struct hifmc_host *host = priv->host;
+	size_t offset;
+	int ret;
+
+	for (offset = 0; offset < len; offset += HIFMC_DMA_MAX_LEN) {
+		size_t trans = min_t(size_t, HIFMC_DMA_MAX_LEN, len - offset);
+
+		ret = hisi_spi_nor_dma_transfer(nor,
+			from + offset, host->dma_buffer, trans, FMC_OP_READ);
+		if (ret) {
+			dev_warn(nor->dev, "DMA read timeout\n");
+			return ret;
+		}
+		memcpy(read_buf + offset, host->buffer, trans);
+	}
+
+	return len;
+}
+
+static ssize_t hisi_spi_nor_write(struct spi_nor *nor, loff_t to,
+			size_t len, const u_char *write_buf)
+{
+	struct hifmc_priv *priv = nor->priv;
+	struct hifmc_host *host = priv->host;
+	size_t offset;
+	int ret;
+
+	for (offset = 0; offset < len; offset += HIFMC_DMA_MAX_LEN) {
+		size_t trans = min_t(size_t, HIFMC_DMA_MAX_LEN, len - offset);
+
+		memcpy(host->buffer, write_buf + offset, trans);
+		ret = hisi_spi_nor_dma_transfer(nor,
+			to + offset, host->dma_buffer, trans, FMC_OP_WRITE);
+		if (ret) {
+			dev_warn(nor->dev, "DMA write timeout\n");
+			return ret;
+		}
+	}
+
+	return len;
+}
+
+/**
+ * Get spi flash device information and register it as a mtd device.
+ */
+static int hisi_spi_nor_register(struct device_node *np,
+				struct hifmc_host *host)
+{
+	struct device *dev = host->dev;
+	struct spi_nor *nor;
+	struct hifmc_priv *priv;
+	struct mtd_info *mtd;
+	int ret;
+
+	nor = devm_kzalloc(dev, sizeof(*nor), GFP_KERNEL);
+	if (!nor)
+		return -ENOMEM;
+
+	nor->dev = dev;
+	spi_nor_set_flash_node(nor, np);
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	ret = of_property_read_u32(np, "reg", &priv->chipselect);
+	if (ret) {
+		dev_err(dev, "There's no reg property for %s\n",
+			np->full_name);
+		return ret;
+	}
+
+	ret = of_property_read_u32(np, "spi-max-frequency",
+			&priv->clkrate);
+	if (ret) {
+		dev_err(dev, "There's no spi-max-frequency property for %s\n",
+			np->full_name);
+		return ret;
+	}
+	priv->host = host;
+	nor->priv = priv;
+
+	nor->prepare = hisi_spi_nor_prep;
+	nor->unprepare = hisi_spi_nor_unprep;
+	nor->read_reg = hisi_spi_nor_read_reg;
+	nor->write_reg = hisi_spi_nor_write_reg;
+	nor->read = hisi_spi_nor_read;
+	nor->write = hisi_spi_nor_write;
+	nor->erase = NULL;
+	ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+	if (ret)
+		return ret;
+
+	mtd = &nor->mtd;
+	mtd->name = np->name;
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret)
+		return ret;
+
+	host->nor[host->num_chip] = nor;
+	host->num_chip++;
+	return 0;
+}
+
+static void hisi_spi_nor_unregister_all(struct hifmc_host *host)
+{
+	int i;
+
+	for (i = 0; i < host->num_chip; i++)
+		mtd_device_unregister(&host->nor[i]->mtd);
+}
+
+static int hisi_spi_nor_register_all(struct hifmc_host *host)
+{
+	struct device *dev = host->dev;
+	struct device_node *np;
+	int ret;
+
+	for_each_available_child_of_node(dev->of_node, np) {
+		ret = hisi_spi_nor_register(np, host);
+		if (ret)
+			goto fail;
+
+		if (host->num_chip == HIFMC_MAX_CHIP_NUM) {
+			dev_warn(dev, "Flash device number exceeds the maximum chipselect number\n");
+			break;
+		}
+	}
+
+	return 0;
+
+fail:
+	hisi_spi_nor_unregister_all(host);
+	return ret;
+}
+
+static int hisi_spi_nor_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct hifmc_host *host;
+	int ret;
+
+	host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, host);
+	host->dev = dev;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "control");
+	host->regbase = devm_ioremap_resource(dev, res);
+	if (IS_ERR(host->regbase))
+		return PTR_ERR(host->regbase);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "memory");
+	host->iobase = devm_ioremap_resource(dev, res);
+	if (IS_ERR(host->iobase))
+		return PTR_ERR(host->iobase);
+
+	host->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(host->clk))
+		return PTR_ERR(host->clk);
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_warn(dev, "Unable to set dma mask\n");
+		return ret;
+	}
+
+	host->buffer = dmam_alloc_coherent(dev, HIFMC_DMA_MAX_LEN,
+			&host->dma_buffer, GFP_KERNEL);
+	if (!host->buffer)
+		return -ENOMEM;
+
+	mutex_init(&host->lock);
+	clk_prepare_enable(host->clk);
+	hisi_spi_nor_init(host);
+	ret = hisi_spi_nor_register_all(host);
+	if (ret)
+		mutex_destroy(&host->lock);
+
+	clk_disable_unprepare(host->clk);
+	return ret;
+}
+
+static int hisi_spi_nor_remove(struct platform_device *pdev)
+{
+	struct hifmc_host *host = platform_get_drvdata(pdev);
+
+	hisi_spi_nor_unregister_all(host);
+	mutex_destroy(&host->lock);
+	clk_disable_unprepare(host->clk);
+	return 0;
+}
+
+static const struct of_device_id hisi_spi_nor_dt_ids[] = {
+	{ .compatible = "hisilicon,fmc-spi-nor"},
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, hisi_spi_nor_dt_ids);
+
+static struct platform_driver hisi_spi_nor_driver = {
+	.driver = {
+		.name	= "hisi-sfc",
+		.of_match_table = hisi_spi_nor_dt_ids,
+	},
+	.probe	= hisi_spi_nor_probe,
+	.remove	= hisi_spi_nor_remove,
+};
+module_platform_driver(hisi_spi_nor_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("HiSilicon SPI Nor Flash Controller Driver");
diff --git a/drivers/mtd/spi-nor/mtk-quadspi.c b/drivers/mtd/spi-nor/mtk-quadspi.c
index 8bed1a4cb79c..e661877c23de 100644
--- a/drivers/mtd/spi-nor/mtk-quadspi.c
+++ b/drivers/mtd/spi-nor/mtk-quadspi.c
@@ -21,7 +21,6 @@
 #include <linux/ioport.h>
 #include <linux/math64.h>
 #include <linux/module.h>
-#include <linux/mtd/mtd.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -243,8 +242,8 @@ static void mt8173_nor_set_addr(struct mt8173_nor *mt8173_nor, u32 addr)
 	writeb(addr & 0xff, mt8173_nor->base + MTK_NOR_RADR3_REG);
 }
 
-static int mt8173_nor_read(struct spi_nor *nor, loff_t from, size_t length,
-			   size_t *retlen, u_char *buffer)
+static ssize_t mt8173_nor_read(struct spi_nor *nor, loff_t from, size_t length,
+			       u_char *buffer)
 {
 	int i, ret;
 	int addr = (int)from;
@@ -255,13 +254,13 @@ static int mt8173_nor_read(struct spi_nor *nor, loff_t from, size_t length,
 	mt8173_nor_set_read_mode(mt8173_nor);
 	mt8173_nor_set_addr(mt8173_nor, addr);
 
-	for (i = 0; i < length; i++, (*retlen)++) {
+	for (i = 0; i < length; i++) {
 		ret = mt8173_nor_execute_cmd(mt8173_nor, MTK_NOR_PIO_READ_CMD);
 		if (ret < 0)
 			return ret;
 		buf[i] = readb(mt8173_nor->base + MTK_NOR_RDATA_REG);
 	}
-	return 0;
+	return length;
 }
 
 static int mt8173_nor_write_single_byte(struct mt8173_nor *mt8173_nor,
@@ -297,36 +296,44 @@ static int mt8173_nor_write_buffer(struct mt8173_nor *mt8173_nor, int addr,
 	return mt8173_nor_execute_cmd(mt8173_nor, MTK_NOR_WR_CMD);
 }
 
-static void mt8173_nor_write(struct spi_nor *nor, loff_t to, size_t len,
-			     size_t *retlen, const u_char *buf)
+static ssize_t mt8173_nor_write(struct spi_nor *nor, loff_t to, size_t len,
+				const u_char *buf)
 {
 	int ret;
 	struct mt8173_nor *mt8173_nor = nor->priv;
+	size_t i;
 
 	ret = mt8173_nor_write_buffer_enable(mt8173_nor);
-	if (ret < 0)
+	if (ret < 0) {
 		dev_warn(mt8173_nor->dev, "write buffer enable failed!\n");
+		return ret;
+	}
 
-	while (len >= SFLASH_WRBUF_SIZE) {
+	for (i = 0; i + SFLASH_WRBUF_SIZE <= len; i += SFLASH_WRBUF_SIZE) {
 		ret = mt8173_nor_write_buffer(mt8173_nor, to, buf);
-		if (ret < 0)
+		if (ret < 0) {
 			dev_err(mt8173_nor->dev, "write buffer failed!\n");
-		len -= SFLASH_WRBUF_SIZE;
+			return ret;
+		}
 		to += SFLASH_WRBUF_SIZE;
 		buf += SFLASH_WRBUF_SIZE;
-		(*retlen) += SFLASH_WRBUF_SIZE;
 	}
 	ret = mt8173_nor_write_buffer_disable(mt8173_nor);
-	if (ret < 0)
+	if (ret < 0) {
 		dev_warn(mt8173_nor->dev, "write buffer disable failed!\n");
+		return ret;
+	}
 
-	if (len) {
-		ret = mt8173_nor_write_single_byte(mt8173_nor, to, (int)len,
-						   (u8 *)buf);
-		if (ret < 0)
+	if (i < len) {
+		ret = mt8173_nor_write_single_byte(mt8173_nor, to,
+						   (int)(len - i), (u8 *)buf);
+		if (ret < 0) {
 			dev_err(mt8173_nor->dev, "write single byte failed!\n");
-		(*retlen) += len;
+			return ret;
+		}
 	}
+
+	return len;
 }
 
 static int mt8173_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c
index ae428cb0e04b..73a14f40928b 100644
--- a/drivers/mtd/spi-nor/nxp-spifi.c
+++ b/drivers/mtd/spi-nor/nxp-spifi.c
@@ -172,8 +172,8 @@ static int nxp_spifi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	return nxp_spifi_wait_for_cmd(spifi);
 }
 
-static int nxp_spifi_read(struct spi_nor *nor, loff_t from, size_t len,
-			  size_t *retlen, u_char *buf)
+static ssize_t nxp_spifi_read(struct spi_nor *nor, loff_t from, size_t len,
+			      u_char *buf)
 {
 	struct nxp_spifi *spifi = nor->priv;
 	int ret;
@@ -183,24 +183,23 @@ static int nxp_spifi_read(struct spi_nor *nor, loff_t from, size_t len,
 		return ret;
 
 	memcpy_fromio(buf, spifi->flash_base + from, len);
-	*retlen += len;
 
-	return 0;
+	return len;
 }
 
-static void nxp_spifi_write(struct spi_nor *nor, loff_t to, size_t len,
-			    size_t *retlen, const u_char *buf)
+static ssize_t nxp_spifi_write(struct spi_nor *nor, loff_t to, size_t len,
+			       const u_char *buf)
 {
 	struct nxp_spifi *spifi = nor->priv;
 	u32 cmd;
 	int ret;
+	size_t i;
 
 	ret = nxp_spifi_set_memory_mode_off(spifi);
 	if (ret)
-		return;
+		return ret;
 
 	writel(to, spifi->io_base + SPIFI_ADDR);
-	*retlen += len;
 
 	cmd = SPIFI_CMD_DOUT |
 	      SPIFI_CMD_DATALEN(len) |
@@ -209,10 +208,14 @@ static void nxp_spifi_write(struct spi_nor *nor, loff_t to, size_t len,
 	      SPIFI_CMD_FRAMEFORM(spifi->nor.addr_width + 1);
 	writel(cmd, spifi->io_base + SPIFI_CMD);
 
-	while (len--)
-		writeb(*buf++, spifi->io_base + SPIFI_DATA);
+	for (i = 0; i < len; i++)
+		writeb(buf[i], spifi->io_base + SPIFI_DATA);
+
+	ret = nxp_spifi_wait_for_cmd(spifi);
+	if (ret)
+		return ret;
 
-	nxp_spifi_wait_for_cmd(spifi);
+	return len;
 }
 
 static int nxp_spifi_erase(struct spi_nor *nor, loff_t offs)
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index c52e45594bfd..d0fc165d7d66 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -661,7 +661,7 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	status_new = (status_old & ~mask & ~SR_TB) | val;
 
 	/* Don't protect status register if we're fully unlocked */
-	if (lock_len == mtd->size)
+	if (lock_len == 0)
 		status_new &= ~SR_SRWD;
 
 	if (!use_top)
@@ -830,10 +830,26 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "mb85rs1mt", INFO(0x047f27, 0, 128 * 1024, 1, SPI_NOR_NO_ERASE) },
 
 	/* GigaDevice */
-	{ "gd25q32", INFO(0xc84016, 0, 64 * 1024,  64, SECT_4K) },
-	{ "gd25q64", INFO(0xc84017, 0, 64 * 1024, 128, SECT_4K) },
-	{ "gd25lq64c", INFO(0xc86017, 0, 64 * 1024, 128, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
-	{ "gd25q128", INFO(0xc84018, 0, 64 * 1024, 256, SECT_4K) },
+	{
+		"gd25q32", INFO(0xc84016, 0, 64 * 1024,  64,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
+	{
+		"gd25q64", INFO(0xc84017, 0, 64 * 1024, 128,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
+	{
+		"gd25lq64c", INFO(0xc86017, 0, 64 * 1024, 128,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
+	{
+		"gd25q128", INFO(0xc84018, 0, 64 * 1024, 256,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
 
 	/* Intel/Numonyx -- xxxs33b */
 	{ "160s33b",  INFO(0x898911, 0, 64 * 1024,  32, 0) },
@@ -871,6 +887,7 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "n25q512a",    INFO(0x20bb20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
 	{ "n25q512ax3",  INFO(0x20ba20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
 	{ "n25q00",      INFO(0x20ba21, 0, 64 * 1024, 2048, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
+	{ "n25q00a",     INFO(0x20bb21, 0, 64 * 1024, 2048, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
 
 	/* PMC */
 	{ "pm25lv512",   INFO(0,        0, 32 * 1024,    2, SECT_4K_PMC) },
@@ -1031,8 +1048,25 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len,
 	if (ret)
 		return ret;
 
-	ret = nor->read(nor, from, len, retlen, buf);
+	while (len) {
+		ret = nor->read(nor, from, len, buf);
+		if (ret == 0) {
+			/* We shouldn't see 0-length reads */
+			ret = -EIO;
+			goto read_err;
+		}
+		if (ret < 0)
+			goto read_err;
+
+		WARN_ON(ret > len);
+		*retlen += ret;
+		buf += ret;
+		from += ret;
+		len -= ret;
+	}
+	ret = 0;
 
+read_err:
 	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_READ);
 	return ret;
 }
@@ -1060,10 +1094,14 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 		nor->program_opcode = SPINOR_OP_BP;
 
 		/* write one byte. */
-		nor->write(nor, to, 1, retlen, buf);
+		ret = nor->write(nor, to, 1, buf);
+		if (ret < 0)
+			goto sst_write_err;
+		WARN(ret != 1, "While writing 1 byte written %i bytes\n",
+		     (int)ret);
 		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
-			goto time_out;
+			goto sst_write_err;
 	}
 	to += actual;
 
@@ -1072,10 +1110,14 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 		nor->program_opcode = SPINOR_OP_AAI_WP;
 
 		/* write two bytes. */
-		nor->write(nor, to, 2, retlen, buf + actual);
+		ret = nor->write(nor, to, 2, buf + actual);
+		if (ret < 0)
+			goto sst_write_err;
+		WARN(ret != 2, "While writing 2 bytes written %i bytes\n",
+		     (int)ret);
 		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
-			goto time_out;
+			goto sst_write_err;
 		to += 2;
 		nor->sst_write_second = true;
 	}
@@ -1084,21 +1126,26 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 	write_disable(nor);
 	ret = spi_nor_wait_till_ready(nor);
 	if (ret)
-		goto time_out;
+		goto sst_write_err;
 
 	/* Write out trailing byte if it exists. */
 	if (actual != len) {
 		write_enable(nor);
 
 		nor->program_opcode = SPINOR_OP_BP;
-		nor->write(nor, to, 1, retlen, buf + actual);
-
+		ret = nor->write(nor, to, 1, buf + actual);
+		if (ret < 0)
+			goto sst_write_err;
+		WARN(ret != 1, "While writing 1 byte written %i bytes\n",
+		     (int)ret);
 		ret = spi_nor_wait_till_ready(nor);
 		if (ret)
-			goto time_out;
+			goto sst_write_err;
 		write_disable(nor);
+		actual += 1;
 	}
-time_out:
+sst_write_err:
+	*retlen += actual;
 	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE);
 	return ret;
 }
@@ -1112,8 +1159,8 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 	size_t *retlen, const u_char *buf)
 {
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
-	u32 page_offset, page_size, i;
-	int ret;
+	size_t page_offset, page_remain, i;
+	ssize_t ret;
 
 	dev_dbg(nor->dev, "to 0x%08x, len %zd\n", (u32)to, len);
 
@@ -1121,35 +1168,37 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 	if (ret)
 		return ret;
 
-	write_enable(nor);
-
-	page_offset = to & (nor->page_size - 1);
+	for (i = 0; i < len; ) {
+		ssize_t written;
 
-	/* do all the bytes fit onto one page? */
-	if (page_offset + len <= nor->page_size) {
-		nor->write(nor, to, len, retlen, buf);
-	} else {
+		page_offset = (to + i) & (nor->page_size - 1);
+		WARN_ONCE(page_offset,
+			  "Writing at offset %zu into a NOR page. Writing partial pages may decrease reliability and increase wear of NOR flash.",
+			  page_offset);
 		/* the size of data remaining on the first page */
-		page_size = nor->page_size - page_offset;
-		nor->write(nor, to, page_size, retlen, buf);
-
-		/* write everything in nor->page_size chunks */
-		for (i = page_size; i < len; i += page_size) {
-			page_size = len - i;
-			if (page_size > nor->page_size)
-				page_size = nor->page_size;
+		page_remain = min_t(size_t,
+				    nor->page_size - page_offset, len - i);
 
-			ret = spi_nor_wait_till_ready(nor);
-			if (ret)
-				goto write_err;
-
-			write_enable(nor);
+		write_enable(nor);
+		ret = nor->write(nor, to + i, page_remain, buf + i);
+		if (ret < 0)
+			goto write_err;
+		written = ret;
 
-			nor->write(nor, to + i, page_size, retlen, buf + i);
+		ret = spi_nor_wait_till_ready(nor);
+		if (ret)
+			goto write_err;
+		*retlen += written;
+		i += written;
+		if (written != page_remain) {
+			dev_err(nor->dev,
+				"While writing %zu bytes written %zd bytes\n",
+				page_remain, written);
+			ret = -EIO;
+			goto write_err;
 		}
 	}
 
-	ret = spi_nor_wait_till_ready(nor);
 write_err:
 	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE);
 	return ret;
diff --git a/drivers/mtd/ssfdc.c b/drivers/mtd/ssfdc.c
index daf82ba7aba0..41b13d1cdcc4 100644
--- a/drivers/mtd/ssfdc.c
+++ b/drivers/mtd/ssfdc.c
@@ -380,8 +380,7 @@ static int ssfdcr_readsect(struct mtd_blktrans_dev *dev,
 		" block_addr=%d\n", logic_sect_no, sectors_per_block, offset,
 		block_address);
 
-	if (block_address >= ssfdc->map_len)
-		BUG();
+	BUG_ON(block_address >= ssfdc->map_len);
 
 	block_address = ssfdc->logic_block_map[block_address];
 
diff --git a/drivers/mtd/tests/nandbiterrs.c b/drivers/mtd/tests/nandbiterrs.c
index 09a4ccac53a2..f26dec896afa 100644
--- a/drivers/mtd/tests/nandbiterrs.c
+++ b/drivers/mtd/tests/nandbiterrs.c
@@ -290,7 +290,7 @@ static int overwrite_test(void)
 
 	while (opno < max_overwrite) {
 
-		err = rewrite_page(0);
+		err = write_page(0);
 		if (err)
 			break;
 
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index e708e360a9e3..6453148d066a 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1251,7 +1251,7 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct alx_priv *alx;
 	struct alx_hw *hw;
 	bool phy_configured;
-	int bars, err;
+	int err;
 
 	err = pci_enable_device_mem(pdev);
 	if (err)
@@ -1271,11 +1271,10 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
-	err = pci_request_selected_regions(pdev, bars, alx_drv_name);
+	err = pci_request_mem_regions(pdev, alx_drv_name);
 	if (err) {
 		dev_err(&pdev->dev,
-			"pci_request_selected_regions failed(bars:%d)\n", bars);
+			"pci_request_mem_regions failed\n");
 		goto out_pci_disable;
 	}
 
@@ -1401,7 +1400,7 @@ out_unmap:
 out_free_netdev:
 	free_netdev(netdev);
 out_pci_release:
-	pci_release_selected_regions(pdev, bars);
+	pci_release_mem_regions(pdev);
 out_pci_disable:
 	pci_disable_device(pdev);
 	return err;
@@ -1420,8 +1419,7 @@ static void alx_remove(struct pci_dev *pdev)
 
 	unregister_netdev(alx->dev);
 	iounmap(hw->hw_addr);
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 
 	pci_disable_pcie_error_reporting(pdev);
 	pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 92fd5c0bf4df..c865135f3cb9 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -444,6 +444,8 @@ struct bufdesc_ex {
 #define FEC_QUIRK_HAS_RACC		(1 << 12)
 /* Controller supports interrupt coalesc */
 #define FEC_QUIRK_HAS_COALESCE		(1 << 13)
+/* Interrupt doesn't wake CPU from deep idle */
+#define FEC_QUIRK_ERR006687		(1 << 14)
 
 struct bufdesc_prop {
 	int qid;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 4040003a74f9..01f7e811739b 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -60,6 +60,7 @@
 #include <linux/if_vlan.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/prefetch.h>
+#include <soc/imx/cpuidle.h>
 
 #include <asm/cacheflush.h>
 
@@ -2825,6 +2826,9 @@ fec_enet_open(struct net_device *ndev)
 	if (ret)
 		goto err_enet_mii_probe;
 
+	if (fep->quirks & FEC_QUIRK_ERR006687)
+		imx6q_cpuidle_fec_irqs_used();
+
 	napi_enable(&fep->napi);
 	phy_start(ndev->phydev);
 	netif_tx_start_all_queues(ndev);
@@ -2860,6 +2864,9 @@ fec_enet_close(struct net_device *ndev)
 
 	phy_disconnect(ndev->phydev);
 
+	if (fep->quirks & FEC_QUIRK_ERR006687)
+		imx6q_cpuidle_fec_irqs_unused();
+
 	fec_enet_clk_enable(ndev, false);
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
 	pm_runtime_mark_last_busy(&fep->pdev->dev);
@@ -3304,6 +3311,11 @@ fec_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, ndev);
 
+	if ((of_machine_is_compatible("fsl,imx6q") ||
+	     of_machine_is_compatible("fsl,imx6dl")) &&
+	    !of_property_read_bool(np, "fsl,err006687-workaround-present"))
+		fep->quirks |= FEC_QUIRK_ERR006687;
+
 	if (of_get_property(np, "fsl,magic-packet", NULL))
 		fep->wol_flag |= FEC_WOL_HAS_MAGIC_PACKET;
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 41f32c0b341e..02f443958f31 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -7330,8 +7330,7 @@ err_flashmap:
 err_ioremap:
 	free_netdev(netdev);
 err_alloc_etherdev:
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 err_pci_reg:
 err_dma:
 	pci_disable_device(pdev);
@@ -7398,8 +7397,7 @@ static void e1000_remove(struct pci_dev *pdev)
 	if ((adapter->hw.flash_address) &&
 	    (adapter->hw.mac.type < e1000_pch_spt))
 		iounmap(adapter->hw.flash_address);
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 
 	free_netdev(netdev);
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index b8245c734c96..774a5654bf42 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -1963,10 +1963,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_dma;
 	}
 
-	err = pci_request_selected_regions(pdev,
-					   pci_select_bars(pdev,
-							   IORESOURCE_MEM),
-					   fm10k_driver_name);
+	err = pci_request_mem_regions(pdev, fm10k_driver_name);
 	if (err) {
 		dev_err(&pdev->dev,
 			"pci_request_selected_regions failed: %d\n", err);
@@ -2070,8 +2067,7 @@ err_sw_init:
 err_ioremap:
 	free_netdev(netdev);
 err_alloc_netdev:
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 err_pci_reg:
 err_dma:
 	pci_disable_device(pdev);
@@ -2119,8 +2115,7 @@ static void fm10k_remove(struct pci_dev *pdev)
 
 	free_netdev(netdev);
 
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 
 	pci_disable_pcie_error_reporting(pdev);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 339d99be4702..81c99e1be708 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -10710,8 +10710,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	/* set up pci connections */
-	err = pci_request_selected_regions(pdev, pci_select_bars(pdev,
-					   IORESOURCE_MEM), i40e_driver_name);
+	err = pci_request_mem_regions(pdev, i40e_driver_name);
 	if (err) {
 		dev_info(&pdev->dev,
 			 "pci_request_selected_regions failed %d\n", err);
@@ -11208,8 +11207,7 @@ err_ioremap:
 	kfree(pf);
 err_pf_alloc:
 	pci_disable_pcie_error_reporting(pdev);
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 err_pci_reg:
 err_dma:
 	pci_disable_device(pdev);
@@ -11320,8 +11318,7 @@ static void i40e_remove(struct pci_dev *pdev)
 
 	iounmap(hw->hw_addr);
 	kfree(pf);
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 
 	pci_disable_pcie_error_reporting(pdev);
 	pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 9bcba42abb91..942a89fb0090 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2324,9 +2324,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 
-	err = pci_request_selected_regions(pdev, pci_select_bars(pdev,
-					   IORESOURCE_MEM),
-					   igb_driver_name);
+	err = pci_request_mem_regions(pdev, igb_driver_name);
 	if (err)
 		goto err_pci_reg;
 
@@ -2750,8 +2748,7 @@ err_sw_init:
 err_ioremap:
 	free_netdev(netdev);
 err_alloc_etherdev:
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 err_pci_reg:
 err_dma:
 	pci_disable_device(pdev);
@@ -2916,8 +2913,7 @@ static void igb_remove(struct pci_dev *pdev)
 	pci_iounmap(pdev, adapter->io_addr);
 	if (hw->flash_address)
 		iounmap(hw->flash_address);
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 
 	kfree(adapter->shadow_vfta);
 	free_netdev(netdev);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 7871f538f0ad..5418c69a7463 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9353,8 +9353,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		pci_using_dac = 0;
 	}
 
-	err = pci_request_selected_regions(pdev, pci_select_bars(pdev,
-					   IORESOURCE_MEM), ixgbe_driver_name);
+	err = pci_request_mem_regions(pdev, ixgbe_driver_name);
 	if (err) {
 		dev_err(&pdev->dev,
 			"pci_request_selected_regions failed 0x%x\n", err);
@@ -9740,8 +9739,7 @@ err_ioremap:
 	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
 	free_netdev(netdev);
 err_alloc_etherdev:
-	pci_release_selected_regions(pdev,
-				     pci_select_bars(pdev, IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 err_pci_reg:
 err_dma:
 	if (!adapter || disable_dev)
@@ -9808,8 +9806,7 @@ static void ixgbe_remove(struct pci_dev *pdev)
 
 #endif
 	iounmap(adapter->io_addr);
-	pci_release_selected_regions(pdev, pci_select_bars(pdev,
-				     IORESOURCE_MEM));
+	pci_release_mem_regions(pdev);
 
 	e_dev_info("complete\n");
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c
index b3cc3ab63799..6fc156a3918d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/pd.c
@@ -205,7 +205,9 @@ int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf, int node)
 			goto free_uar;
 		}
 
-		uar->bf_map = io_mapping_map_wc(priv->bf_mapping, uar->index << PAGE_SHIFT);
+		uar->bf_map = io_mapping_map_wc(priv->bf_mapping,
+						uar->index << PAGE_SHIFT,
+						PAGE_SIZE);
 		if (!uar->bf_map) {
 			err = -ENOMEM;
 			goto unamp_uar;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4cb9b156cab7..d7c33f9361aa 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1661,14 +1661,9 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 static void nvme_dev_unmap(struct nvme_dev *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev->dev);
-	int bars;
-
 	if (dev->bar)
 		iounmap(dev->bar);
-
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
-	pci_release_selected_regions(pdev, bars);
+	pci_release_mem_regions(to_pci_dev(dev->dev));
 }
 
 static void nvme_pci_disable(struct nvme_dev *dev)
@@ -1897,13 +1892,9 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 
 static int nvme_dev_map(struct nvme_dev *dev)
 {
-	int bars;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
-	if (!bars)
-		return -ENODEV;
-	if (pci_request_selected_regions(pdev, bars, "nvme"))
+	if (pci_request_mem_regions(pdev, "nvme"))
 		return -ENODEV;
 
 	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
@@ -1912,7 +1903,7 @@ static int nvme_dev_map(struct nvme_dev *dev)
 
        return 0;
   release:
-       pci_release_selected_regions(pdev, bars);
+       pci_release_mem_regions(pdev);
        return -ENODEV;
 }
 
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 0a553c084a81..02b2903fe9d2 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -1,4 +1,6 @@
 
+#define pr_fmt(fmt)	"OF: " fmt
+
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
@@ -24,10 +26,10 @@ static int __of_address_to_resource(struct device_node *dev,
 #ifdef DEBUG
 static void of_dump_addr(const char *s, const __be32 *addr, int na)
 {
-	printk(KERN_DEBUG "%s", s);
+	pr_debug("%s", s);
 	while (na--)
-		printk(" %08x", be32_to_cpu(*(addr++)));
-	printk("\n");
+		pr_cont(" %08x", be32_to_cpu(*(addr++)));
+	pr_cont("\n");
 }
 #else
 static void of_dump_addr(const char *s, const __be32 *addr, int na) { }
@@ -68,7 +70,7 @@ static u64 of_bus_default_map(__be32 *addr, const __be32 *range,
 	s  = of_read_number(range + na + pna, ns);
 	da = of_read_number(addr, na);
 
-	pr_debug("OF: default map, cp=%llx, s=%llx, da=%llx\n",
+	pr_debug("default map, cp=%llx, s=%llx, da=%llx\n",
 		 (unsigned long long)cp, (unsigned long long)s,
 		 (unsigned long long)da);
 
@@ -156,7 +158,7 @@ static u64 of_bus_pci_map(__be32 *addr, const __be32 *range, int na, int ns,
 	s  = of_read_number(range + na + pna, ns);
 	da = of_read_number(addr + 1, na - 1);
 
-	pr_debug("OF: PCI map, cp=%llx, s=%llx, da=%llx\n",
+	pr_debug("PCI map, cp=%llx, s=%llx, da=%llx\n",
 		 (unsigned long long)cp, (unsigned long long)s,
 		 (unsigned long long)da);
 
@@ -381,7 +383,7 @@ static u64 of_bus_isa_map(__be32 *addr, const __be32 *range, int na, int ns,
 	s  = of_read_number(range + na + pna, ns);
 	da = of_read_number(addr + 1, na - 1);
 
-	pr_debug("OF: ISA map, cp=%llx, s=%llx, da=%llx\n",
+	pr_debug("ISA map, cp=%llx, s=%llx, da=%llx\n",
 		 (unsigned long long)cp, (unsigned long long)s,
 		 (unsigned long long)da);
 
@@ -504,17 +506,17 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus,
 	 */
 	ranges = of_get_property(parent, rprop, &rlen);
 	if (ranges == NULL && !of_empty_ranges_quirk(parent)) {
-		pr_debug("OF: no ranges; cannot translate\n");
+		pr_debug("no ranges; cannot translate\n");
 		return 1;
 	}
 	if (ranges == NULL || rlen == 0) {
 		offset = of_read_number(addr, na);
 		memset(addr, 0, pna * 4);
-		pr_debug("OF: empty ranges; 1:1 translation\n");
+		pr_debug("empty ranges; 1:1 translation\n");
 		goto finish;
 	}
 
-	pr_debug("OF: walking ranges...\n");
+	pr_debug("walking ranges...\n");
 
 	/* Now walk through the ranges */
 	rlen /= 4;
@@ -525,14 +527,14 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus,
 			break;
 	}
 	if (offset == OF_BAD_ADDR) {
-		pr_debug("OF: not found !\n");
+		pr_debug("not found !\n");
 		return 1;
 	}
 	memcpy(addr, ranges + na, 4 * pna);
 
  finish:
-	of_dump_addr("OF: parent translation for:", addr, pna);
-	pr_debug("OF: with offset: %llx\n", (unsigned long long)offset);
+	of_dump_addr("parent translation for:", addr, pna);
+	pr_debug("with offset: %llx\n", (unsigned long long)offset);
 
 	/* Translate it into parent bus space */
 	return pbus->translate(addr, offset, pna);
@@ -557,7 +559,7 @@ static u64 __of_translate_address(struct device_node *dev,
 	int na, ns, pna, pns;
 	u64 result = OF_BAD_ADDR;
 
-	pr_debug("OF: ** translation for device %s **\n", of_node_full_name(dev));
+	pr_debug("** translation for device %s **\n", of_node_full_name(dev));
 
 	/* Increase refcount at current level */
 	of_node_get(dev);
@@ -571,14 +573,14 @@ static u64 __of_translate_address(struct device_node *dev,
 	/* Count address cells & copy address locally */
 	bus->count_cells(dev, &na, &ns);
 	if (!OF_CHECK_COUNTS(na, ns)) {
-		pr_debug("OF: Bad cell count for %s\n", of_node_full_name(dev));
+		pr_debug("Bad cell count for %s\n", of_node_full_name(dev));
 		goto bail;
 	}
 	memcpy(addr, in_addr, na * 4);
 
-	pr_debug("OF: bus is %s (na=%d, ns=%d) on %s\n",
+	pr_debug("bus is %s (na=%d, ns=%d) on %s\n",
 	    bus->name, na, ns, of_node_full_name(parent));
-	of_dump_addr("OF: translating address:", addr, na);
+	of_dump_addr("translating address:", addr, na);
 
 	/* Translate */
 	for (;;) {
@@ -589,7 +591,7 @@ static u64 __of_translate_address(struct device_node *dev,
 
 		/* If root, we have finished */
 		if (parent == NULL) {
-			pr_debug("OF: reached root node\n");
+			pr_debug("reached root node\n");
 			result = of_read_number(addr, na);
 			break;
 		}
@@ -598,12 +600,12 @@ static u64 __of_translate_address(struct device_node *dev,
 		pbus = of_match_bus(parent);
 		pbus->count_cells(dev, &pna, &pns);
 		if (!OF_CHECK_COUNTS(pna, pns)) {
-			pr_err("prom_parse: Bad cell count for %s\n",
+			pr_err("Bad cell count for %s\n",
 			       of_node_full_name(dev));
 			break;
 		}
 
-		pr_debug("OF: parent bus is %s (na=%d, ns=%d) on %s\n",
+		pr_debug("parent bus is %s (na=%d, ns=%d) on %s\n",
 		    pbus->name, pna, pns, of_node_full_name(parent));
 
 		/* Apply bus translation */
@@ -615,7 +617,7 @@ static u64 __of_translate_address(struct device_node *dev,
 		ns = pns;
 		bus = pbus;
 
-		of_dump_addr("OF: one level translation:", addr, na);
+		of_dump_addr("one level translation:", addr, na);
 	}
  bail:
 	of_node_put(parent);
@@ -853,8 +855,7 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
 	}
 
 	if (!ranges) {
-		pr_debug("%s: no dma-ranges found for node(%s)\n",
-			 __func__, np->full_name);
+		pr_debug("no dma-ranges found for node(%s)\n", np->full_name);
 		ret = -ENODEV;
 		goto out;
 	}
@@ -871,8 +872,8 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
 	dmaaddr = of_read_number(ranges, naddr);
 	*paddr = of_translate_dma_address(np, ranges);
 	if (*paddr == OF_BAD_ADDR) {
-		pr_err("%s: translation of DMA address(%pad) to CPU address failed node(%s)\n",
-		       __func__, dma_addr, np->full_name);
+		pr_err("translation of DMA address(%pad) to CPU address failed node(%s)\n",
+		       dma_addr, np->full_name);
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/of/base.c b/drivers/of/base.c
index ebf84e3b56d5..7792266db259 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -17,6 +17,9 @@
  *      as published by the Free Software Foundation; either version
  *      2 of the License, or (at your option) any later version.
  */
+
+#define pr_fmt(fmt)	"OF: " fmt
+
 #include <linux/console.h>
 #include <linux/ctype.h>
 #include <linux/cpu.h>
@@ -112,6 +115,7 @@ static ssize_t of_node_property_read(struct file *filp, struct kobject *kobj,
 	return memory_read_from_buffer(buf, count, &offset, pp->value, pp->length);
 }
 
+/* always return newly allocated name, caller must free after use */
 static const char *safe_name(struct kobject *kobj, const char *orig_name)
 {
 	const char *name = orig_name;
@@ -126,9 +130,12 @@ static const char *safe_name(struct kobject *kobj, const char *orig_name)
 		name = kasprintf(GFP_KERNEL, "%s#%i", orig_name, ++i);
 	}
 
-	if (name != orig_name)
-		pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n",
+	if (name == orig_name) {
+		name = kstrdup(orig_name, GFP_KERNEL);
+	} else {
+		pr_warn("Duplicate name in %s, renamed to \"%s\"\n",
 			kobject_name(kobj), name);
+	}
 	return name;
 }
 
@@ -159,6 +166,7 @@ int __of_add_property_sysfs(struct device_node *np, struct property *pp)
 int __of_attach_node_sysfs(struct device_node *np)
 {
 	const char *name;
+	struct kobject *parent;
 	struct property *pp;
 	int rc;
 
@@ -171,15 +179,16 @@ int __of_attach_node_sysfs(struct device_node *np)
 	np->kobj.kset = of_kset;
 	if (!np->parent) {
 		/* Nodes without parents are new top level trees */
-		rc = kobject_add(&np->kobj, NULL, "%s",
-				 safe_name(&of_kset->kobj, "base"));
+		name = safe_name(&of_kset->kobj, "base");
+		parent = NULL;
 	} else {
 		name = safe_name(&np->parent->kobj, kbasename(np->full_name));
-		if (!name || !name[0])
-			return -EINVAL;
-
-		rc = kobject_add(&np->kobj, &np->parent->kobj, "%s", name);
+		parent = &np->parent->kobj;
 	}
+	if (!name)
+		return -ENOMEM;
+	rc = kobject_add(&np->kobj, parent, "%s", name);
+	kfree(name);
 	if (rc)
 		return rc;
 
@@ -198,7 +207,7 @@ void __init of_core_init(void)
 	of_kset = kset_create_and_add("devicetree", NULL, firmware_kobj);
 	if (!of_kset) {
 		mutex_unlock(&of_mutex);
-		pr_err("devicetree: failed to register existing nodes\n");
+		pr_err("failed to register existing nodes\n");
 		return;
 	}
 	for_each_of_allnodes(np)
@@ -493,6 +502,28 @@ int of_device_is_compatible(const struct device_node *device,
 }
 EXPORT_SYMBOL(of_device_is_compatible);
 
+/** Checks if the device is compatible with any of the entries in
+ *  a NULL terminated array of strings. Returns the best match
+ *  score or 0.
+ */
+int of_device_compatible_match(struct device_node *device,
+			       const char *const *compat)
+{
+	unsigned int tmp, score = 0;
+
+	if (!compat)
+		return 0;
+
+	while (*compat) {
+		tmp = of_device_is_compatible(device, *compat);
+		if (tmp > score)
+			score = tmp;
+		compat++;
+	}
+
+	return score;
+}
+
 /**
  * of_machine_is_compatible - Test root of device tree for a given compatible value
  * @compat: compatible string to look for in root node's compatible property.
@@ -1815,6 +1846,12 @@ int __of_remove_property(struct device_node *np, struct property *prop)
 	return 0;
 }
 
+void __of_sysfs_remove_bin_file(struct device_node *np, struct property *prop)
+{
+	sysfs_remove_bin_file(&np->kobj, &prop->attr);
+	kfree(prop->attr.attr.name);
+}
+
 void __of_remove_property_sysfs(struct device_node *np, struct property *prop)
 {
 	if (!IS_ENABLED(CONFIG_SYSFS))
@@ -1822,7 +1859,7 @@ void __of_remove_property_sysfs(struct device_node *np, struct property *prop)
 
 	/* at early boot, bail here and defer setup to of_init() */
 	if (of_kset && of_node_is_attached(np))
-		sysfs_remove_bin_file(&np->kobj, &prop->attr);
+		__of_sysfs_remove_bin_file(np, prop);
 }
 
 /**
@@ -1895,7 +1932,7 @@ void __of_update_property_sysfs(struct device_node *np, struct property *newprop
 		return;
 
 	if (oldprop)
-		sysfs_remove_bin_file(&np->kobj, &oldprop->attr);
+		__of_sysfs_remove_bin_file(np, oldprop);
 	__of_add_property_sysfs(np, newprop);
 }
 
@@ -2257,8 +2294,8 @@ struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
 		of_node_put(node);
 
 		if (!port) {
-			pr_err("%s(): no port node found in %s\n",
-			       __func__, parent->full_name);
+			pr_err("graph: no port node found in %s\n",
+			       parent->full_name);
 			return NULL;
 		}
 	} else {
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index 3033fa3250dc..888fdbc09992 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -6,6 +6,8 @@
  * device tree nodes.
  */
 
+#define pr_fmt(fmt)	"OF: " fmt
+
 #include <linux/of.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
@@ -55,7 +57,7 @@ void __of_detach_node_sysfs(struct device_node *np)
 	/* only remove properties if on sysfs */
 	if (of_node_is_attached(np)) {
 		for_each_property_of_node(np, pp)
-			sysfs_remove_bin_file(&np->kobj, &pp->attr);
+			__of_sysfs_remove_bin_file(np, pp);
 		kobject_del(&np->kobj);
 	}
 
@@ -96,13 +98,13 @@ int of_reconfig_notify(unsigned long action, struct of_reconfig_data *p)
 	switch (action) {
 	case OF_RECONFIG_ATTACH_NODE:
 	case OF_RECONFIG_DETACH_NODE:
-		pr_debug("of/notify %-15s %s\n", action_names[action],
+		pr_debug("notify %-15s %s\n", action_names[action],
 			pr->dn->full_name);
 		break;
 	case OF_RECONFIG_ADD_PROPERTY:
 	case OF_RECONFIG_REMOVE_PROPERTY:
 	case OF_RECONFIG_UPDATE_PROPERTY:
-		pr_debug("of/notify %-15s %s:%s\n", action_names[action],
+		pr_debug("notify %-15s %s:%s\n", action_names[action],
 			pr->dn->full_name, pr->prop->name);
 		break;
 
@@ -460,12 +462,12 @@ static void __of_changeset_entry_dump(struct of_changeset_entry *ce)
 	case OF_RECONFIG_ADD_PROPERTY:
 	case OF_RECONFIG_REMOVE_PROPERTY:
 	case OF_RECONFIG_UPDATE_PROPERTY:
-		pr_debug("of/cset<%p> %-15s %s/%s\n", ce, action_names[ce->action],
+		pr_debug("cset<%p> %-15s %s/%s\n", ce, action_names[ce->action],
 			ce->np->full_name, ce->prop->name);
 		break;
 	case OF_RECONFIG_ATTACH_NODE:
 	case OF_RECONFIG_DETACH_NODE:
-		pr_debug("of/cset<%p> %-15s %s\n", ce, action_names[ce->action],
+		pr_debug("cset<%p> %-15s %s\n", ce, action_names[ce->action],
 			ce->np->full_name);
 		break;
 	}
@@ -531,13 +533,13 @@ static void __of_changeset_entry_notify(struct of_changeset_entry *ce, bool reve
 		ret = of_property_notify(ce->action, ce->np, ce->prop, ce->old_prop);
 		break;
 	default:
-		pr_err("%s: invalid devicetree changeset action: %i\n", __func__,
+		pr_err("invalid devicetree changeset action: %i\n",
 			(int)ce->action);
 		return;
 	}
 
 	if (ret)
-		pr_err("%s: notifier error @%s\n", __func__, ce->np->full_name);
+		pr_err("changeset notifier error @%s\n", ce->np->full_name);
 }
 
 static int __of_changeset_entry_apply(struct of_changeset_entry *ce)
@@ -568,8 +570,8 @@ static int __of_changeset_entry_apply(struct of_changeset_entry *ce)
 
 		ret = __of_add_property(ce->np, ce->prop);
 		if (ret) {
-			pr_err("%s: add_property failed @%s/%s\n",
-				__func__, ce->np->full_name,
+			pr_err("changeset: add_property failed @%s/%s\n",
+				ce->np->full_name,
 				ce->prop->name);
 			break;
 		}
@@ -577,8 +579,8 @@ static int __of_changeset_entry_apply(struct of_changeset_entry *ce)
 	case OF_RECONFIG_REMOVE_PROPERTY:
 		ret = __of_remove_property(ce->np, ce->prop);
 		if (ret) {
-			pr_err("%s: remove_property failed @%s/%s\n",
-				__func__, ce->np->full_name,
+			pr_err("changeset: remove_property failed @%s/%s\n",
+				ce->np->full_name,
 				ce->prop->name);
 			break;
 		}
@@ -596,8 +598,8 @@ static int __of_changeset_entry_apply(struct of_changeset_entry *ce)
 
 		ret = __of_update_property(ce->np, ce->prop, &old_prop);
 		if (ret) {
-			pr_err("%s: update_property failed @%s/%s\n",
-				__func__, ce->np->full_name,
+			pr_err("changeset: update_property failed @%s/%s\n",
+				ce->np->full_name,
 				ce->prop->name);
 			break;
 		}
@@ -677,24 +679,24 @@ int __of_changeset_apply(struct of_changeset *ocs)
 	int ret;
 
 	/* perform the rest of the work */
-	pr_debug("of_changeset: applying...\n");
+	pr_debug("changeset: applying...\n");
 	list_for_each_entry(ce, &ocs->entries, node) {
 		ret = __of_changeset_entry_apply(ce);
 		if (ret) {
-			pr_err("%s: Error applying changeset (%d)\n", __func__, ret);
+			pr_err("Error applying changeset (%d)\n", ret);
 			list_for_each_entry_continue_reverse(ce, &ocs->entries, node)
 				__of_changeset_entry_revert(ce);
 			return ret;
 		}
 	}
-	pr_debug("of_changeset: applied, emitting notifiers.\n");
+	pr_debug("changeset: applied, emitting notifiers.\n");
 
 	/* drop the global lock while emitting notifiers */
 	mutex_unlock(&of_mutex);
 	list_for_each_entry(ce, &ocs->entries, node)
 		__of_changeset_entry_notify(ce, 0);
 	mutex_lock(&of_mutex);
-	pr_debug("of_changeset: notifiers sent.\n");
+	pr_debug("changeset: notifiers sent.\n");
 
 	return 0;
 }
@@ -728,24 +730,24 @@ int __of_changeset_revert(struct of_changeset *ocs)
 	struct of_changeset_entry *ce;
 	int ret;
 
-	pr_debug("of_changeset: reverting...\n");
+	pr_debug("changeset: reverting...\n");
 	list_for_each_entry_reverse(ce, &ocs->entries, node) {
 		ret = __of_changeset_entry_revert(ce);
 		if (ret) {
-			pr_err("%s: Error reverting changeset (%d)\n", __func__, ret);
+			pr_err("Error reverting changeset (%d)\n", ret);
 			list_for_each_entry_continue(ce, &ocs->entries, node)
 				__of_changeset_entry_apply(ce);
 			return ret;
 		}
 	}
-	pr_debug("of_changeset: reverted, emitting notifiers.\n");
+	pr_debug("changeset: reverted, emitting notifiers.\n");
 
 	/* drop the global lock while emitting notifiers */
 	mutex_unlock(&of_mutex);
 	list_for_each_entry_reverse(ce, &ocs->entries, node)
 		__of_changeset_entry_notify(ce, 1);
 	mutex_lock(&of_mutex);
-	pr_debug("of_changeset: notifiers sent.\n");
+	pr_debug("changeset: notifiers sent.\n");
 
 	return 0;
 }
@@ -795,10 +797,9 @@ int of_changeset_action(struct of_changeset *ocs, unsigned long action,
 	struct of_changeset_entry *ce;
 
 	ce = kzalloc(sizeof(*ce), GFP_KERNEL);
-	if (!ce) {
-		pr_err("%s: Failed to allocate\n", __func__);
+	if (!ce)
 		return -ENOMEM;
-	}
+
 	/* get a reference to the node */
 	ce->action = action;
 	ce->np = of_node_get(np);
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 0e02947a8a7a..55f1b8391149 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -9,6 +9,8 @@
  * version 2 as published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt)	"OF: fdt:" fmt
+
 #include <linux/crc32.h>
 #include <linux/kernel.h>
 #include <linux/initrd.h>
@@ -182,14 +184,12 @@ static void populate_properties(const void *blob,
 
 		val = fdt_getprop_by_offset(blob, cur, &pname, &sz);
 		if (!val) {
-			pr_warn("%s: Cannot locate property at 0x%x\n",
-				__func__, cur);
+			pr_warn("Cannot locate property at 0x%x\n", cur);
 			continue;
 		}
 
 		if (!pname) {
-			pr_warn("%s: Cannot find property name at 0x%x\n",
-				__func__, cur);
+			pr_warn("Cannot find property name at 0x%x\n", cur);
 			continue;
 		}
 
@@ -439,7 +439,7 @@ static int unflatten_dt_nodes(const void *blob,
 	}
 
 	if (offset < 0 && offset != -FDT_ERR_NOTFOUND) {
-		pr_err("%s: Error %d processing FDT\n", __func__, offset);
+		pr_err("Error %d processing FDT\n", offset);
 		return -EINVAL;
 	}
 
@@ -472,7 +472,8 @@ static int unflatten_dt_nodes(const void *blob,
 static void *__unflatten_device_tree(const void *blob,
 				     struct device_node *dad,
 				     struct device_node **mynodes,
-				     void *(*dt_alloc)(u64 size, u64 align))
+				     void *(*dt_alloc)(u64 size, u64 align),
+				     bool detached)
 {
 	int size;
 	void *mem;
@@ -516,6 +517,11 @@ static void *__unflatten_device_tree(const void *blob,
 		pr_warning("End of tree marker overwritten: %08x\n",
 			   be32_to_cpup(mem + size));
 
+	if (detached) {
+		of_node_set_flag(*mynodes, OF_DETACHED);
+		pr_debug("unflattened tree is detached\n");
+	}
+
 	pr_debug(" <- unflatten_device_tree()\n");
 	return mem;
 }
@@ -548,7 +554,8 @@ void *of_fdt_unflatten_tree(const unsigned long *blob,
 	void *mem;
 
 	mutex_lock(&of_fdt_unflatten_mutex);
-	mem = __unflatten_device_tree(blob, dad, mynodes, &kernel_tree_alloc);
+	mem = __unflatten_device_tree(blob, dad, mynodes, &kernel_tree_alloc,
+				      true);
 	mutex_unlock(&of_fdt_unflatten_mutex);
 
 	return mem;
@@ -1237,7 +1244,7 @@ bool __init early_init_dt_scan(void *params)
 void __init unflatten_device_tree(void)
 {
 	__unflatten_device_tree(initial_boot_params, NULL, &of_root,
-				early_init_dt_alloc_memory_arch);
+				early_init_dt_alloc_memory_arch, false);
 
 	/* Get pointer to "/chosen" and "/aliases" nodes for use everywhere */
 	of_alias_scan(early_init_dt_alloc_memory_arch);
@@ -1294,7 +1301,7 @@ static int __init of_fdt_raw_init(void)
 
 	if (of_fdt_crc32 != crc32_be(~0, initial_boot_params,
 				     fdt_totalsize(initial_boot_params))) {
-		pr_warn("fdt: not creating '/sys/firmware/fdt': CRC check failed\n");
+		pr_warn("not creating '/sys/firmware/fdt': CRC check failed\n");
 		return 0;
 	}
 	of_fdt_raw_attr.size = fdt_totalsize(initial_boot_params);
diff --git a/drivers/of/fdt_address.c b/drivers/of/fdt_address.c
index dca8f9b93745..843a542dac7d 100644
--- a/drivers/of/fdt_address.c
+++ b/drivers/of/fdt_address.c
@@ -12,6 +12,9 @@
  * the Free Software Foundation; either version 2, or (at your option)
  * any later version.
  */
+
+#define pr_fmt(fmt)	"OF: fdt: " fmt
+
 #include <linux/kernel.h>
 #include <linux/libfdt.h>
 #include <linux/of.h>
@@ -30,7 +33,7 @@ static void __init of_dump_addr(const char *s, const __be32 *addr, int na)
 	pr_debug("%s", s);
 	while(na--)
 		pr_cont(" %08x", *(addr++));
-	pr_debug("\n");
+	pr_cont("\n");
 }
 #else
 static void __init of_dump_addr(const char *s, const __be32 *addr, int na) { }
@@ -77,7 +80,7 @@ static u64 __init fdt_bus_default_map(__be32 *addr, const __be32 *range,
 	s  = of_read_number(range + na + pna, ns);
 	da = of_read_number(addr, na);
 
-	pr_debug("FDT: default map, cp=%llx, s=%llx, da=%llx\n",
+	pr_debug("default map, cp=%llx, s=%llx, da=%llx\n",
 	    cp, s, da);
 
 	if (da < cp || da >= (cp + s))
@@ -123,11 +126,11 @@ static int __init fdt_translate_one(const void *blob, int parent,
 	if (rlen == 0) {
 		offset = of_read_number(addr, na);
 		memset(addr, 0, pna * 4);
-		pr_debug("FDT: empty ranges, 1:1 translation\n");
+		pr_debug("empty ranges, 1:1 translation\n");
 		goto finish;
 	}
 
-	pr_debug("FDT: walking ranges...\n");
+	pr_debug("walking ranges...\n");
 
 	/* Now walk through the ranges */
 	rlen /= 4;
@@ -138,14 +141,14 @@ static int __init fdt_translate_one(const void *blob, int parent,
 			break;
 	}
 	if (offset == OF_BAD_ADDR) {
-		pr_debug("FDT: not found !\n");
+		pr_debug("not found !\n");
 		return 1;
 	}
 	memcpy(addr, ranges + na, 4 * pna);
 
  finish:
-	of_dump_addr("FDT: parent translation for:", addr, pna);
-	pr_debug("FDT: with offset: %llx\n", offset);
+	of_dump_addr("parent translation for:", addr, pna);
+	pr_debug("with offset: %llx\n", offset);
 
 	/* Translate it into parent bus space */
 	return pbus->translate(addr, offset, pna);
@@ -170,12 +173,12 @@ static u64 __init fdt_translate_address(const void *blob, int node_offset)
 	int na, ns, pna, pns;
 	u64 result = OF_BAD_ADDR;
 
-	pr_debug("FDT: ** translation for device %s **\n",
+	pr_debug("** translation for device %s **\n",
 		 fdt_get_name(blob, node_offset, NULL));
 
 	reg = fdt_getprop(blob, node_offset, "reg", &len);
 	if (!reg) {
-		pr_err("FDT: warning: device tree node '%s' has no address.\n",
+		pr_err("warning: device tree node '%s' has no address.\n",
 			fdt_get_name(blob, node_offset, NULL));
 		goto bail;
 	}
@@ -189,15 +192,15 @@ static u64 __init fdt_translate_address(const void *blob, int node_offset)
 	/* Cound address cells & copy address locally */
 	bus->count_cells(blob, parent, &na, &ns);
 	if (!OF_CHECK_COUNTS(na, ns)) {
-		pr_err("FDT: Bad cell count for %s\n",
+		pr_err("Bad cell count for %s\n",
 		       fdt_get_name(blob, node_offset, NULL));
 		goto bail;
 	}
 	memcpy(addr, reg, na * 4);
 
-	pr_debug("FDT: bus (na=%d, ns=%d) on %s\n",
+	pr_debug("bus (na=%d, ns=%d) on %s\n",
 		 na, ns, fdt_get_name(blob, parent, NULL));
-	of_dump_addr("OF: translating address:", addr, na);
+	of_dump_addr("translating address:", addr, na);
 
 	/* Translate */
 	for (;;) {
@@ -207,7 +210,7 @@ static u64 __init fdt_translate_address(const void *blob, int node_offset)
 
 		/* If root, we have finished */
 		if (parent < 0) {
-			pr_debug("FDT: reached root node\n");
+			pr_debug("reached root node\n");
 			result = of_read_number(addr, na);
 			break;
 		}
@@ -216,12 +219,12 @@ static u64 __init fdt_translate_address(const void *blob, int node_offset)
 		pbus = &of_busses[0];
 		pbus->count_cells(blob, parent, &pna, &pns);
 		if (!OF_CHECK_COUNTS(pna, pns)) {
-			pr_err("FDT: Bad cell count for %s\n",
+			pr_err("Bad cell count for %s\n",
 				fdt_get_name(blob, node_offset, NULL));
 			break;
 		}
 
-		pr_debug("FDT: parent bus (na=%d, ns=%d) on %s\n",
+		pr_debug("parent bus (na=%d, ns=%d) on %s\n",
 			 pna, pns, fdt_get_name(blob, parent, NULL));
 
 		/* Apply bus translation */
@@ -234,7 +237,7 @@ static u64 __init fdt_translate_address(const void *blob, int node_offset)
 		ns = pns;
 		bus = pbus;
 
-		of_dump_addr("FDT: one level translation:", addr, na);
+		of_dump_addr("one level translation:", addr, na);
 	}
  bail:
 	return result;
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 6ec743faabe8..89a71c6074fc 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -18,6 +18,8 @@
  * driver.
  */
 
+#define pr_fmt(fmt)	"OF: " fmt
+
 #include <linux/device.h>
 #include <linux/errno.h>
 #include <linux/list.h>
@@ -557,6 +559,8 @@ void __init of_irq_init(const struct of_device_id *matches)
 			 * its children can get processed in a subsequent pass.
 			 */
 			list_add_tail(&desc->list, &intc_parent_list);
+
+			of_node_set_flag(desc->dev, OF_POPULATED);
 		}
 
 		/* Get the next pending parent that might have children */
diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
index 13f4fed38048..589b30c68e14 100644
--- a/drivers/of/of_pci.c
+++ b/drivers/of/of_pci.c
@@ -1,3 +1,5 @@
+#define pr_fmt(fmt)	"OF: PCI: " fmt
+
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/of.h>
@@ -138,7 +140,7 @@ void of_pci_check_probe_only(void)
 	else
 		pci_clear_flags(PCI_PROBE_ONLY);
 
-	pr_info("PCI: PROBE_ONLY %sabled\n", val ? "en" : "dis");
+	pr_info("PROBE_ONLY %sabled\n", val ? "en" : "dis");
 }
 EXPORT_SYMBOL_GPL(of_pci_check_probe_only);
 
@@ -181,7 +183,7 @@ int of_pci_get_host_bridge_resources(struct device_node *dev,
 	if (!bus_range)
 		return -ENOMEM;
 
-	pr_info("PCI host bridge %s ranges:\n", dev->full_name);
+	pr_info("host bridge %s ranges:\n", dev->full_name);
 
 	err = of_pci_parse_bus_range(dev, bus_range);
 	if (err) {
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index 829469faeb23..18bbb4517e25 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -83,6 +83,9 @@ extern int __of_attach_node_sysfs(struct device_node *np);
 extern void __of_detach_node(struct device_node *np);
 extern void __of_detach_node_sysfs(struct device_node *np);
 
+extern void __of_sysfs_remove_bin_file(struct device_node *np,
+				       struct property *prop);
+
 /* iterators for transactions, used for overlays */
 /* forward iterator */
 #define for_each_transaction_entry(_oft, _te) \
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 06af99f64ad8..366d8c3c7989 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -13,6 +13,8 @@
  * License or (at your optional) any later version of the license.
  */
 
+#define pr_fmt(fmt)	"OF: reserved mem: " fmt
+
 #include <linux/err.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
@@ -76,7 +78,7 @@ void __init fdt_reserved_mem_save_node(unsigned long node, const char *uname,
 	struct reserved_mem *rmem = &reserved_mem[reserved_mem_count];
 
 	if (reserved_mem_count == ARRAY_SIZE(reserved_mem)) {
-		pr_err("Reserved memory: not enough space all defined regions.\n");
+		pr_err("not enough space all defined regions.\n");
 		return;
 	}
 
@@ -109,8 +111,7 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 		return -EINVAL;
 
 	if (len != dt_root_size_cells * sizeof(__be32)) {
-		pr_err("Reserved memory: invalid size property in '%s' node.\n",
-				uname);
+		pr_err("invalid size property in '%s' node.\n", uname);
 		return -EINVAL;
 	}
 	size = dt_mem_next_cell(dt_root_size_cells, &prop);
@@ -120,7 +121,7 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 	prop = of_get_flat_dt_prop(node, "alignment", &len);
 	if (prop) {
 		if (len != dt_root_addr_cells * sizeof(__be32)) {
-			pr_err("Reserved memory: invalid alignment property in '%s' node.\n",
+			pr_err("invalid alignment property in '%s' node.\n",
 				uname);
 			return -EINVAL;
 		}
@@ -142,7 +143,7 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 	if (prop) {
 
 		if (len % t_len != 0) {
-			pr_err("Reserved memory: invalid alloc-ranges property in '%s', skipping node.\n",
+			pr_err("invalid alloc-ranges property in '%s', skipping node.\n",
 			       uname);
 			return -EINVAL;
 		}
@@ -157,7 +158,7 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 			ret = early_init_dt_alloc_reserved_memory_arch(size,
 					align, start, end, nomap, &base);
 			if (ret == 0) {
-				pr_debug("Reserved memory: allocated memory for '%s' node: base %pa, size %ld MiB\n",
+				pr_debug("allocated memory for '%s' node: base %pa, size %ld MiB\n",
 					uname, &base,
 					(unsigned long)size / SZ_1M);
 				break;
@@ -169,13 +170,12 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 		ret = early_init_dt_alloc_reserved_memory_arch(size, align,
 							0, 0, nomap, &base);
 		if (ret == 0)
-			pr_debug("Reserved memory: allocated memory for '%s' node: base %pa, size %ld MiB\n",
+			pr_debug("allocated memory for '%s' node: base %pa, size %ld MiB\n",
 				uname, &base, (unsigned long)size / SZ_1M);
 	}
 
 	if (base == 0) {
-		pr_info("Reserved memory: failed to allocate memory for node '%s'\n",
-			uname);
+		pr_info("failed to allocate memory for node '%s'\n", uname);
 		return -ENOMEM;
 	}
 
@@ -204,7 +204,7 @@ static int __init __reserved_mem_init_node(struct reserved_mem *rmem)
 			continue;
 
 		if (initfn(rmem) == 0) {
-			pr_info("Reserved memory: initialized node %s, compatible id %s\n",
+			pr_info("initialized node %s, compatible id %s\n",
 				rmem->name, compat);
 			return 0;
 		}
@@ -246,7 +246,7 @@ static void __init __rmem_check_for_overlap(void)
 
 			this_end = this->base + this->size;
 			next_end = next->base + next->size;
-			pr_err("Reserved memory: OVERLAP DETECTED!\n%s (%pa--%pa) overlaps with %s (%pa--%pa)\n",
+			pr_err("OVERLAP DETECTED!\n%s (%pa--%pa) overlaps with %s (%pa--%pa)\n",
 			       this->name, &this->base, &this_end,
 			       next->name, &next->base, &next_end);
 		}
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 82250815e9a5..318dbb51e7a2 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -8,7 +8,9 @@
  * modify it under the terms of the GNU General Public License
  * version 2 as published by the Free Software Foundation.
  */
-#undef DEBUG
+
+#define pr_fmt(fmt)	"OF: overlay: " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -137,8 +139,8 @@ static int of_overlay_apply_one(struct of_overlay *ov,
 	for_each_property_of_node(overlay, prop) {
 		ret = of_overlay_apply_single_property(ov, target, prop);
 		if (ret) {
-			pr_err("%s: Failed to apply prop @%s/%s\n",
-				__func__, target->full_name, prop->name);
+			pr_err("Failed to apply prop @%s/%s\n",
+			       target->full_name, prop->name);
 			return ret;
 		}
 	}
@@ -146,9 +148,8 @@ static int of_overlay_apply_one(struct of_overlay *ov,
 	for_each_child_of_node(overlay, child) {
 		ret = of_overlay_apply_single_device_node(ov, target, child);
 		if (ret != 0) {
-			pr_err("%s: Failed to apply single node @%s/%s\n",
-					__func__, target->full_name,
-					child->name);
+			pr_err("Failed to apply single node @%s/%s\n",
+			       target->full_name, child->name);
 			of_node_put(child);
 			return ret;
 		}
@@ -176,8 +177,7 @@ static int of_overlay_apply(struct of_overlay *ov)
 
 		err = of_overlay_apply_one(ov, ovinfo->target, ovinfo->overlay);
 		if (err != 0) {
-			pr_err("%s: overlay failed '%s'\n",
-				__func__, ovinfo->target->full_name);
+			pr_err("apply failed '%s'\n", ovinfo->target->full_name);
 			return err;
 		}
 	}
@@ -208,7 +208,7 @@ static struct device_node *find_target_node(struct device_node *info_node)
 	if (ret == 0)
 		return of_find_node_by_path(path);
 
-	pr_err("%s: Failed to find target for node %p (%s)\n", __func__,
+	pr_err("Failed to find target for node %p (%s)\n",
 		info_node, info_node->name);
 
 	return NULL;
@@ -355,8 +355,6 @@ int of_overlay_create(struct device_node *tree)
 
 	id = idr_alloc(&ov_idr, ov, 0, 0, GFP_KERNEL);
 	if (id < 0) {
-		pr_err("%s: idr_alloc() failed for tree@%s\n",
-				__func__, tree->full_name);
 		err = id;
 		goto err_destroy_trans;
 	}
@@ -365,26 +363,21 @@ int of_overlay_create(struct device_node *tree)
 	/* build the overlay info structures */
 	err = of_build_overlay_info(ov, tree);
 	if (err) {
-		pr_err("%s: of_build_overlay_info() failed for tree@%s\n",
-				__func__, tree->full_name);
+		pr_err("of_build_overlay_info() failed for tree@%s\n",
+		       tree->full_name);
 		goto err_free_idr;
 	}
 
 	/* apply the overlay */
 	err = of_overlay_apply(ov);
-	if (err) {
-		pr_err("%s: of_overlay_apply() failed for tree@%s\n",
-				__func__, tree->full_name);
+	if (err)
 		goto err_abort_trans;
-	}
 
 	/* apply the changeset */
 	err = __of_changeset_apply(&ov->cset);
-	if (err) {
-		pr_err("%s: __of_changeset_apply() failed for tree@%s\n",
-				__func__, tree->full_name);
+	if (err)
 		goto err_revert_overlay;
-	}
+
 
 	/* add to the tail of the overlay list */
 	list_add_tail(&ov->node, &ov_list);
@@ -469,8 +462,7 @@ static int overlay_removal_is_ok(struct of_overlay *ov)
 
 	list_for_each_entry(ce, &ov->cset.entries, node) {
 		if (!overlay_is_topmost(ov, ce->np)) {
-			pr_err("%s: overlay #%d is not topmost\n",
-					__func__, ov->id);
+			pr_err("overlay #%d is not topmost\n", ov->id);
 			return 0;
 		}
 	}
@@ -496,16 +488,13 @@ int of_overlay_destroy(int id)
 	ov = idr_find(&ov_idr, id);
 	if (ov == NULL) {
 		err = -ENODEV;
-		pr_err("%s: Could not find overlay #%d\n",
-				__func__, id);
+		pr_err("destroy: Could not find overlay #%d\n", id);
 		goto out;
 	}
 
 	/* check whether the overlay is safe to remove */
 	if (!overlay_removal_is_ok(ov)) {
 		err = -EBUSY;
-		pr_err("%s: removal check failed for overlay #%d\n",
-				__func__, id);
 		goto out;
 	}
 
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 16e8daffac06..765390e3ed8d 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -11,6 +11,9 @@
  *  2 of the License, or (at your option) any later version.
  *
  */
+
+#define pr_fmt(fmt)	"OF: " fmt
+
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/amba/bus.h>
@@ -31,7 +34,6 @@ const struct of_device_id of_default_bus_match_table[] = {
 #endif /* CONFIG_ARM_AMBA */
 	{} /* Empty terminated list */
 };
-EXPORT_SYMBOL(of_default_bus_match_table);
 
 static int of_dev_node_match(struct device *dev, void *data)
 {
@@ -234,11 +236,8 @@ static struct amba_device *of_amba_device_create(struct device_node *node,
 		return NULL;
 
 	dev = amba_device_alloc(NULL, 0, 0);
-	if (!dev) {
-		pr_err("%s(): amba_device_alloc() failed for %s\n",
-		       __func__, node->full_name);
+	if (!dev)
 		goto err_clear_flag;
-	}
 
 	/* setup generic device info */
 	dev->dev.of_node = of_node_get(node);
@@ -261,15 +260,15 @@ static struct amba_device *of_amba_device_create(struct device_node *node,
 
 	ret = of_address_to_resource(node, 0, &dev->res);
 	if (ret) {
-		pr_err("%s(): of_address_to_resource() failed (%d) for %s\n",
-		       __func__, ret, node->full_name);
+		pr_err("amba: of_address_to_resource() failed (%d) for %s\n",
+		       ret, node->full_name);
 		goto err_free;
 	}
 
 	ret = amba_device_add(dev, &iomem_resource);
 	if (ret) {
-		pr_err("%s(): amba_device_add() failed (%d) for %s\n",
-		       __func__, ret, node->full_name);
+		pr_err("amba_device_add() failed (%d) for %s\n",
+		       ret, node->full_name);
 		goto err_free;
 	}
 
@@ -363,6 +362,12 @@ static int of_platform_bus_create(struct device_node *bus,
 		return 0;
 	}
 
+	if (of_node_check_flag(bus, OF_POPULATED_BUS)) {
+		pr_debug("%s() - skipping %s, already populated\n",
+			__func__, bus->full_name);
+		return 0;
+	}
+
 	auxdata = of_dev_lookup(lookup, bus);
 	if (auxdata) {
 		bus_id = auxdata->name;
@@ -414,7 +419,7 @@ int of_platform_bus_probe(struct device_node *root,
 	if (!root)
 		return -EINVAL;
 
-	pr_debug("of_platform_bus_probe()\n");
+	pr_debug("%s()\n", __func__);
 	pr_debug(" starting at: %s\n", root->full_name);
 
 	/* Do a self check of bus type, if there's a match, create children */
@@ -466,6 +471,9 @@ int of_platform_populate(struct device_node *root,
 	if (!root)
 		return -EINVAL;
 
+	pr_debug("%s()\n", __func__);
+	pr_debug(" starting at: %s\n", root->full_name);
+
 	for_each_child_of_node(root, child) {
 		rc = of_platform_bus_create(child, matches, lookup, parent, true);
 		if (rc) {
@@ -489,6 +497,15 @@ int of_platform_default_populate(struct device_node *root,
 }
 EXPORT_SYMBOL_GPL(of_platform_default_populate);
 
+static int __init of_platform_default_populate_init(void)
+{
+	if (of_have_populated_dt())
+		of_platform_default_populate(NULL, NULL, NULL);
+
+	return 0;
+}
+arch_initcall_sync(of_platform_default_populate_init);
+
 static int of_platform_device_destroy(struct device *dev, void *data)
 {
 	/* Do not touch devices not populated from the device tree */
diff --git a/drivers/of/resolver.c b/drivers/of/resolver.c
index d313d492f278..46325d6394cf 100644
--- a/drivers/of/resolver.c
+++ b/drivers/of/resolver.c
@@ -9,6 +9,8 @@
  * version 2 as published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt)	"OF: resolver: " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -313,6 +315,11 @@ int of_resolve_phandles(struct device_node *resolve)
 	phandle phandle, phandle_delta;
 	int err;
 
+	if (!resolve)
+		pr_err("%s: null node\n", __func__);
+	if (resolve && !of_node_check_flag(resolve, OF_DETACHED))
+		pr_err("%s: node %s not detached\n", __func__,
+			 resolve->full_name);
 	/* the resolve node must exist, and be detached */
 	if (!resolve || !of_node_check_flag(resolve, OF_DETACHED))
 		return -EINVAL;
@@ -369,6 +376,7 @@ int of_resolve_phandles(struct device_node *resolve)
 
 	/* we need to fixup, but no root symbols... */
 	if (!root_sym) {
+		pr_err("%s: no symbols in root of device tree.\n", __func__);
 		err = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index f34ed9310323..53c83d66eb7e 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -771,7 +771,7 @@ static void __init of_unittest_platform_populate(void)
 	};
 
 	np = of_find_node_by_path("/testcase-data");
-	of_platform_populate(np, of_default_bus_match_table, NULL, NULL);
+	of_platform_default_populate(np, NULL, NULL);
 
 	/* Test that a missing irq domain returns -EPROBE_DEFER */
 	np = of_find_node_by_path("/testcase-data/testcase-device1");
@@ -1871,8 +1871,7 @@ static void __init of_unittest_overlay(void)
 		goto out;
 	}
 
-	ret = of_platform_populate(bus_np, of_default_bus_match_table,
-			NULL, NULL);
+	ret = of_platform_default_populate(bus_np, NULL, NULL);
 	if (ret != 0) {
 		unittest(0, "could not populate bus @ \"%s\"\n", bus_path);
 		goto out;
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 56389be5d08b..67f9916ff14d 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -25,7 +25,7 @@ config PCI_MSI
 	   If you don't know what to do here, say Y.
 
 config PCI_MSI_IRQ_DOMAIN
-	bool
+	def_bool ARM || ARM64 || X86
 	depends on PCI_MSI
 	select GENERIC_MSI_IRQ_DOMAIN
 
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index dd7cdbee8029..c288e5a52575 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -91,6 +91,35 @@ void pci_bus_remove_resources(struct pci_bus *bus)
 	}
 }
 
+int devm_request_pci_bus_resources(struct device *dev,
+				   struct list_head *resources)
+{
+	struct resource_entry *win;
+	struct resource *parent, *res;
+	int err;
+
+	resource_list_for_each_entry(win, resources) {
+		res = win->res;
+		switch (resource_type(res)) {
+		case IORESOURCE_IO:
+			parent = &ioport_resource;
+			break;
+		case IORESOURCE_MEM:
+			parent = &iomem_resource;
+			break;
+		default:
+			continue;
+		}
+
+		err = devm_request_resource(dev, parent, res);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_request_pci_bus_resources);
+
 static struct pci_bus_region pci_32_bit = {0, 0xffffffffULL};
 #ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
 static struct pci_bus_region pci_64_bit = {0,
@@ -291,6 +320,7 @@ void pci_bus_add_device(struct pci_dev *dev)
 	pci_fixup_device(pci_fixup_final, dev);
 	pci_create_sysfs_dev_files(dev);
 	pci_proc_attach_device(dev);
+	pci_bridge_d3_device_changed(dev);
 
 	dev->match_driver = true;
 	retval = device_attach(&dev->dev);
@@ -397,4 +427,3 @@ void pci_bus_put(struct pci_bus *bus)
 		put_device(&bus->dev);
 }
 EXPORT_SYMBOL(pci_bus_put);
-
diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c
index f9832ad8efe2..66e0d718472f 100644
--- a/drivers/pci/ecam.c
+++ b/drivers/pci/ecam.c
@@ -19,10 +19,9 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pci-ecam.h>
 #include <linux/slab.h>
 
-#include "ecam.h"
-
 /*
  * On 64-bit systems, we do a single ioremap for the whole config space
  * since we have enough virtual address range available.  On 32-bit, we
@@ -52,6 +51,7 @@ struct pci_config_window *pci_ecam_create(struct device *dev,
 	if (!cfg)
 		return ERR_PTR(-ENOMEM);
 
+	cfg->parent = dev;
 	cfg->ops = ops;
 	cfg->busr.start = busr->start;
 	cfg->busr.end = busr->end;
@@ -95,7 +95,7 @@ struct pci_config_window *pci_ecam_create(struct device *dev,
 	}
 
 	if (ops->init) {
-		err = ops->init(dev, cfg);
+		err = ops->init(cfg);
 		if (err)
 			goto err_exit;
 	}
diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig
index 5d2374e4ee7f..9b485d873b0d 100644
--- a/drivers/pci/host/Kconfig
+++ b/drivers/pci/host/Kconfig
@@ -3,8 +3,9 @@ menu "PCI host controller drivers"
 
 config PCI_DRA7XX
 	bool "TI DRA7xx PCIe controller"
-	select PCIE_DW
 	depends on OF && HAS_IOMEM && TI_PIPE3
+	depends on PCI_MSI_IRQ_DOMAIN
+	select PCIE_DW
 	help
 	 Enables support for the PCIe controller in the DRA7xx SoC.  There
 	 are two instances of PCIe controller in DRA7xx.  This controller can
@@ -16,11 +17,20 @@ config PCI_MVEBU
 	depends on ARM
 	depends on OF
 
+config PCI_AARDVARK
+	bool "Aardvark PCIe controller"
+	depends on ARCH_MVEBU && ARM64
+	depends on OF
+	depends on PCI_MSI_IRQ_DOMAIN
+	help
+	 Add support for Aardvark 64bit PCIe Host Controller. This
+	 controller is part of the South Bridge of the Marvel Armada
+	 3700 SoC.
 
 config PCIE_XILINX_NWL
 	bool "NWL PCIe Core"
 	depends on ARCH_ZYNQMP
-	select PCI_MSI_IRQ_DOMAIN if PCI_MSI
+	depends on PCI_MSI_IRQ_DOMAIN
 	help
 	 Say 'Y' here if you want kernel support for Xilinx
 	 NWL PCIe controller. The controller can act as Root Port
@@ -29,6 +39,7 @@ config PCIE_XILINX_NWL
 
 config PCIE_DW_PLAT
 	bool "Platform bus based DesignWare PCIe Controller"
+	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW
 	---help---
 	 This selects the DesignWare PCIe controller support. Select this if
@@ -40,16 +51,19 @@ config PCIE_DW_PLAT
 
 config PCIE_DW
 	bool
+	depends on PCI_MSI_IRQ_DOMAIN
 
 config PCI_EXYNOS
 	bool "Samsung Exynos PCIe controller"
 	depends on SOC_EXYNOS5440
+	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIEPORTBUS
 	select PCIE_DW
 
 config PCI_IMX6
 	bool "Freescale i.MX6 PCIe controller"
 	depends on SOC_IMX6Q
+	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIEPORTBUS
 	select PCIE_DW
 
@@ -72,8 +86,7 @@ config PCI_RCAR_GEN2
 config PCIE_RCAR
 	bool "Renesas R-Car PCIe controller"
 	depends on ARCH_RENESAS || (ARM && COMPILE_TEST)
-	select PCI_MSI
-	select PCI_MSI_IRQ_DOMAIN
+	depends on PCI_MSI_IRQ_DOMAIN
 	help
 	  Say Y here if you want PCIe controller support on R-Car SoCs.
 
@@ -85,6 +98,7 @@ config PCI_HOST_GENERIC
 	bool "Generic PCI host controller"
 	depends on (ARM || ARM64) && OF
 	select PCI_HOST_COMMON
+	select IRQ_DOMAIN
 	help
 	  Say Y here if you want to support a simple generic PCI host
 	  controller, such as the one emulated by kvmtool.
@@ -92,6 +106,7 @@ config PCI_HOST_GENERIC
 config PCIE_SPEAR13XX
 	bool "STMicroelectronics SPEAr PCIe controller"
 	depends on ARCH_SPEAR13XX
+	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIEPORTBUS
 	select PCIE_DW
 	help
@@ -100,6 +115,7 @@ config PCIE_SPEAR13XX
 config PCI_KEYSTONE
 	bool "TI Keystone PCIe controller"
 	depends on ARCH_KEYSTONE
+	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW
 	select PCIEPORTBUS
 	help
@@ -120,7 +136,6 @@ config PCI_XGENE
 	depends on ARCH_XGENE
 	depends on OF
 	select PCIEPORTBUS
-	select PCI_MSI_IRQ_DOMAIN if PCI_MSI
 	help
 	  Say Y here if you want internal PCI support on APM X-Gene SoC.
 	  There are 5 internal PCIe ports available. Each port is GEN3 capable
@@ -128,7 +143,8 @@ config PCI_XGENE
 
 config PCI_XGENE_MSI
 	bool "X-Gene v1 PCIe MSI feature"
-	depends on PCI_XGENE && PCI_MSI
+	depends on PCI_XGENE
+	depends on PCI_MSI_IRQ_DOMAIN
 	default y
 	help
 	  Say Y here if you want PCIe MSI support for the APM X-Gene v1 SoC.
@@ -137,6 +153,7 @@ config PCI_XGENE_MSI
 config PCI_LAYERSCAPE
 	bool "Freescale Layerscape PCIe controller"
 	depends on OF && (ARM || ARCH_LAYERSCAPE)
+	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW
 	select MFD_SYSCON
 	help
@@ -177,8 +194,7 @@ config PCIE_IPROC_BCMA
 config PCIE_IPROC_MSI
 	bool "Broadcom iProc PCIe MSI support"
 	depends on PCIE_IPROC_PLATFORM || PCIE_IPROC_BCMA
-	depends on PCI_MSI
-	select PCI_MSI_IRQ_DOMAIN
+	depends on PCI_MSI_IRQ_DOMAIN
 	default ARCH_BCM_IPROC
 	help
 	  Say Y here if you want to enable MSI support for Broadcom's iProc
@@ -195,8 +211,8 @@ config PCIE_ALTERA
 
 config PCIE_ALTERA_MSI
 	bool "Altera PCIe MSI feature"
-	depends on PCIE_ALTERA && PCI_MSI
-	select PCI_MSI_IRQ_DOMAIN
+	depends on PCIE_ALTERA
+	depends on PCI_MSI_IRQ_DOMAIN
 	help
 	  Say Y here if you want PCIe MSI support for the Altera FPGA.
 	  This MSI driver supports Altera MSI to GIC controller IP.
@@ -204,6 +220,7 @@ config PCIE_ALTERA_MSI
 config PCI_HISI
 	depends on OF && ARM64
 	bool "HiSilicon Hip05 and Hip06 SoCs PCIe controllers"
+	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIEPORTBUS
 	select PCIE_DW
 	help
@@ -213,6 +230,7 @@ config PCI_HISI
 config PCIE_QCOM
 	bool "Qualcomm PCIe controller"
 	depends on ARCH_QCOM && OF
+	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW
 	select PCIEPORTBUS
 	help
@@ -237,6 +255,7 @@ config PCI_HOST_THUNDER_ECAM
 config PCIE_ARMADA_8K
 	bool "Marvell Armada-8K PCIe controller"
 	depends on ARCH_MVEBU
+	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW
 	select PCIEPORTBUS
 	help
@@ -245,4 +264,14 @@ config PCIE_ARMADA_8K
 	  Designware hardware and therefore the driver re-uses the
 	  Designware core functions to implement the driver.
 
+config PCIE_ARTPEC6
+	bool "Axis ARTPEC-6 PCIe controller"
+	depends on MACH_ARTPEC6
+	depends on PCI_MSI_IRQ_DOMAIN
+	select PCIE_DW
+	select PCIEPORTBUS
+	help
+	  Say Y here to enable PCIe controller support on Axis ARTPEC-6
+	  SoCs.  This PCIe controller uses the DesignWare core.
+
 endmenu
diff --git a/drivers/pci/host/Makefile b/drivers/pci/host/Makefile
index 9c8698e89e96..88434101e4c4 100644
--- a/drivers/pci/host/Makefile
+++ b/drivers/pci/host/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_PCI_EXYNOS) += pci-exynos.o
 obj-$(CONFIG_PCI_IMX6) += pci-imx6.o
 obj-$(CONFIG_PCI_HYPERV) += pci-hyperv.o
 obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o
+obj-$(CONFIG_PCI_AARDVARK) += pci-aardvark.o
 obj-$(CONFIG_PCI_TEGRA) += pci-tegra.o
 obj-$(CONFIG_PCI_RCAR_GEN2) += pci-rcar-gen2.o
 obj-$(CONFIG_PCIE_RCAR) += pcie-rcar.o
@@ -29,3 +30,4 @@ obj-$(CONFIG_PCIE_QCOM) += pcie-qcom.o
 obj-$(CONFIG_PCI_HOST_THUNDER_ECAM) += pci-thunder-ecam.o
 obj-$(CONFIG_PCI_HOST_THUNDER_PEM) += pci-thunder-pem.o
 obj-$(CONFIG_PCIE_ARMADA_8K) += pcie-armada8k.o
+obj-$(CONFIG_PCIE_ARTPEC6) += pcie-artpec6.o
diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c
new file mode 100644
index 000000000000..ef9893fa3176
--- /dev/null
+++ b/drivers/pci/host/pci-aardvark.c
@@ -0,0 +1,1001 @@
+/*
+ * Driver for the Aardvark PCIe controller, used on Marvell Armada
+ * 3700.
+ *
+ * Copyright (C) 2016 Marvell
+ *
+ * Author: Hezi Shahmoon <hezi.shahmoon@marvell.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+
+/* PCIe core registers */
+#define PCIE_CORE_CMD_STATUS_REG				0x4
+#define     PCIE_CORE_CMD_IO_ACCESS_EN				BIT(0)
+#define     PCIE_CORE_CMD_MEM_ACCESS_EN				BIT(1)
+#define     PCIE_CORE_CMD_MEM_IO_REQ_EN				BIT(2)
+#define PCIE_CORE_DEV_CTRL_STATS_REG				0xc8
+#define     PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE	(0 << 4)
+#define     PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT	5
+#define     PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE		(0 << 11)
+#define     PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT	12
+#define PCIE_CORE_LINK_CTRL_STAT_REG				0xd0
+#define     PCIE_CORE_LINK_L0S_ENTRY				BIT(0)
+#define     PCIE_CORE_LINK_TRAINING				BIT(5)
+#define     PCIE_CORE_LINK_WIDTH_SHIFT				20
+#define PCIE_CORE_ERR_CAPCTL_REG				0x118
+#define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX			BIT(5)
+#define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN			BIT(6)
+#define     PCIE_CORE_ERR_CAPCTL_ECRC_CHCK			BIT(7)
+#define     PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV			BIT(8)
+
+/* PIO registers base address and register offsets */
+#define PIO_BASE_ADDR				0x4000
+#define PIO_CTRL				(PIO_BASE_ADDR + 0x0)
+#define   PIO_CTRL_TYPE_MASK			GENMASK(3, 0)
+#define   PIO_CTRL_ADDR_WIN_DISABLE		BIT(24)
+#define PIO_STAT				(PIO_BASE_ADDR + 0x4)
+#define   PIO_COMPLETION_STATUS_SHIFT		7
+#define   PIO_COMPLETION_STATUS_MASK		GENMASK(9, 7)
+#define   PIO_COMPLETION_STATUS_OK		0
+#define   PIO_COMPLETION_STATUS_UR		1
+#define   PIO_COMPLETION_STATUS_CRS		2
+#define   PIO_COMPLETION_STATUS_CA		4
+#define   PIO_NON_POSTED_REQ			BIT(0)
+#define PIO_ADDR_LS				(PIO_BASE_ADDR + 0x8)
+#define PIO_ADDR_MS				(PIO_BASE_ADDR + 0xc)
+#define PIO_WR_DATA				(PIO_BASE_ADDR + 0x10)
+#define PIO_WR_DATA_STRB			(PIO_BASE_ADDR + 0x14)
+#define PIO_RD_DATA				(PIO_BASE_ADDR + 0x18)
+#define PIO_START				(PIO_BASE_ADDR + 0x1c)
+#define PIO_ISR					(PIO_BASE_ADDR + 0x20)
+#define PIO_ISRM				(PIO_BASE_ADDR + 0x24)
+
+/* Aardvark Control registers */
+#define CONTROL_BASE_ADDR			0x4800
+#define PCIE_CORE_CTRL0_REG			(CONTROL_BASE_ADDR + 0x0)
+#define     PCIE_GEN_SEL_MSK			0x3
+#define     PCIE_GEN_SEL_SHIFT			0x0
+#define     SPEED_GEN_1				0
+#define     SPEED_GEN_2				1
+#define     SPEED_GEN_3				2
+#define     IS_RC_MSK				1
+#define     IS_RC_SHIFT				2
+#define     LANE_CNT_MSK			0x18
+#define     LANE_CNT_SHIFT			0x3
+#define     LANE_COUNT_1			(0 << LANE_CNT_SHIFT)
+#define     LANE_COUNT_2			(1 << LANE_CNT_SHIFT)
+#define     LANE_COUNT_4			(2 << LANE_CNT_SHIFT)
+#define     LANE_COUNT_8			(3 << LANE_CNT_SHIFT)
+#define     LINK_TRAINING_EN			BIT(6)
+#define     LEGACY_INTA				BIT(28)
+#define     LEGACY_INTB				BIT(29)
+#define     LEGACY_INTC				BIT(30)
+#define     LEGACY_INTD				BIT(31)
+#define PCIE_CORE_CTRL1_REG			(CONTROL_BASE_ADDR + 0x4)
+#define     HOT_RESET_GEN			BIT(0)
+#define PCIE_CORE_CTRL2_REG			(CONTROL_BASE_ADDR + 0x8)
+#define     PCIE_CORE_CTRL2_RESERVED		0x7
+#define     PCIE_CORE_CTRL2_TD_ENABLE		BIT(4)
+#define     PCIE_CORE_CTRL2_STRICT_ORDER_ENABLE	BIT(5)
+#define     PCIE_CORE_CTRL2_OB_WIN_ENABLE	BIT(6)
+#define     PCIE_CORE_CTRL2_MSI_ENABLE		BIT(10)
+#define PCIE_ISR0_REG				(CONTROL_BASE_ADDR + 0x40)
+#define PCIE_ISR0_MASK_REG			(CONTROL_BASE_ADDR + 0x44)
+#define     PCIE_ISR0_MSI_INT_PENDING		BIT(24)
+#define     PCIE_ISR0_INTX_ASSERT(val)		BIT(16 + (val))
+#define     PCIE_ISR0_INTX_DEASSERT(val)	BIT(20 + (val))
+#define	    PCIE_ISR0_ALL_MASK			GENMASK(26, 0)
+#define PCIE_ISR1_REG				(CONTROL_BASE_ADDR + 0x48)
+#define PCIE_ISR1_MASK_REG			(CONTROL_BASE_ADDR + 0x4C)
+#define     PCIE_ISR1_POWER_STATE_CHANGE	BIT(4)
+#define     PCIE_ISR1_FLUSH			BIT(5)
+#define     PCIE_ISR1_ALL_MASK			GENMASK(5, 4)
+#define PCIE_MSI_ADDR_LOW_REG			(CONTROL_BASE_ADDR + 0x50)
+#define PCIE_MSI_ADDR_HIGH_REG			(CONTROL_BASE_ADDR + 0x54)
+#define PCIE_MSI_STATUS_REG			(CONTROL_BASE_ADDR + 0x58)
+#define PCIE_MSI_MASK_REG			(CONTROL_BASE_ADDR + 0x5C)
+#define PCIE_MSI_PAYLOAD_REG			(CONTROL_BASE_ADDR + 0x9C)
+
+/* PCIe window configuration */
+#define OB_WIN_BASE_ADDR			0x4c00
+#define OB_WIN_BLOCK_SIZE			0x20
+#define OB_WIN_REG_ADDR(win, offset)		(OB_WIN_BASE_ADDR + \
+						 OB_WIN_BLOCK_SIZE * (win) + \
+						 (offset))
+#define OB_WIN_MATCH_LS(win)			OB_WIN_REG_ADDR(win, 0x00)
+#define OB_WIN_MATCH_MS(win)			OB_WIN_REG_ADDR(win, 0x04)
+#define OB_WIN_REMAP_LS(win)			OB_WIN_REG_ADDR(win, 0x08)
+#define OB_WIN_REMAP_MS(win)			OB_WIN_REG_ADDR(win, 0x0c)
+#define OB_WIN_MASK_LS(win)			OB_WIN_REG_ADDR(win, 0x10)
+#define OB_WIN_MASK_MS(win)			OB_WIN_REG_ADDR(win, 0x14)
+#define OB_WIN_ACTIONS(win)			OB_WIN_REG_ADDR(win, 0x18)
+
+/* PCIe window types */
+#define OB_PCIE_MEM				0x0
+#define OB_PCIE_IO				0x4
+
+/* LMI registers base address and register offsets */
+#define LMI_BASE_ADDR				0x6000
+#define CFG_REG					(LMI_BASE_ADDR + 0x0)
+#define     LTSSM_SHIFT				24
+#define     LTSSM_MASK				0x3f
+#define     LTSSM_L0				0x10
+#define     RC_BAR_CONFIG			0x300
+
+/* PCIe core controller registers */
+#define CTRL_CORE_BASE_ADDR			0x18000
+#define CTRL_CONFIG_REG				(CTRL_CORE_BASE_ADDR + 0x0)
+#define     CTRL_MODE_SHIFT			0x0
+#define     CTRL_MODE_MASK			0x1
+#define     PCIE_CORE_MODE_DIRECT		0x0
+#define     PCIE_CORE_MODE_COMMAND		0x1
+
+/* PCIe Central Interrupts Registers */
+#define CENTRAL_INT_BASE_ADDR			0x1b000
+#define HOST_CTRL_INT_STATUS_REG		(CENTRAL_INT_BASE_ADDR + 0x0)
+#define HOST_CTRL_INT_MASK_REG			(CENTRAL_INT_BASE_ADDR + 0x4)
+#define     PCIE_IRQ_CMDQ_INT			BIT(0)
+#define     PCIE_IRQ_MSI_STATUS_INT		BIT(1)
+#define     PCIE_IRQ_CMD_SENT_DONE		BIT(3)
+#define     PCIE_IRQ_DMA_INT			BIT(4)
+#define     PCIE_IRQ_IB_DXFERDONE		BIT(5)
+#define     PCIE_IRQ_OB_DXFERDONE		BIT(6)
+#define     PCIE_IRQ_OB_RXFERDONE		BIT(7)
+#define     PCIE_IRQ_COMPQ_INT			BIT(12)
+#define     PCIE_IRQ_DIR_RD_DDR_DET		BIT(13)
+#define     PCIE_IRQ_DIR_WR_DDR_DET		BIT(14)
+#define     PCIE_IRQ_CORE_INT			BIT(16)
+#define     PCIE_IRQ_CORE_INT_PIO		BIT(17)
+#define     PCIE_IRQ_DPMU_INT			BIT(18)
+#define     PCIE_IRQ_PCIE_MIS_INT		BIT(19)
+#define     PCIE_IRQ_MSI_INT1_DET		BIT(20)
+#define     PCIE_IRQ_MSI_INT2_DET		BIT(21)
+#define     PCIE_IRQ_RC_DBELL_DET		BIT(22)
+#define     PCIE_IRQ_EP_STATUS			BIT(23)
+#define     PCIE_IRQ_ALL_MASK			0xfff0fb
+#define     PCIE_IRQ_ENABLE_INTS_MASK		PCIE_IRQ_CORE_INT
+
+/* Transaction types */
+#define PCIE_CONFIG_RD_TYPE0			0x8
+#define PCIE_CONFIG_RD_TYPE1			0x9
+#define PCIE_CONFIG_WR_TYPE0			0xa
+#define PCIE_CONFIG_WR_TYPE1			0xb
+
+/* PCI_BDF shifts 8bit, so we need extra 4bit shift */
+#define PCIE_BDF(dev)				(dev << 4)
+#define PCIE_CONF_BUS(bus)			(((bus) & 0xff) << 20)
+#define PCIE_CONF_DEV(dev)			(((dev) & 0x1f) << 15)
+#define PCIE_CONF_FUNC(fun)			(((fun) & 0x7)	<< 12)
+#define PCIE_CONF_REG(reg)			((reg) & 0xffc)
+#define PCIE_CONF_ADDR(bus, devfn, where)	\
+	(PCIE_CONF_BUS(bus) | PCIE_CONF_DEV(PCI_SLOT(devfn))	| \
+	 PCIE_CONF_FUNC(PCI_FUNC(devfn)) | PCIE_CONF_REG(where))
+
+#define PIO_TIMEOUT_MS			1
+
+#define LINK_WAIT_MAX_RETRIES		10
+#define LINK_WAIT_USLEEP_MIN		90000
+#define LINK_WAIT_USLEEP_MAX		100000
+
+#define LEGACY_IRQ_NUM			4
+#define MSI_IRQ_NUM			32
+
+struct advk_pcie {
+	struct platform_device *pdev;
+	void __iomem *base;
+	struct list_head resources;
+	struct irq_domain *irq_domain;
+	struct irq_chip irq_chip;
+	struct msi_controller msi;
+	struct irq_domain *msi_domain;
+	struct irq_chip msi_irq_chip;
+	DECLARE_BITMAP(msi_irq_in_use, MSI_IRQ_NUM);
+	struct mutex msi_used_lock;
+	u16 msi_msg;
+	int root_bus_nr;
+};
+
+static inline void advk_writel(struct advk_pcie *pcie, u32 val, u64 reg)
+{
+	writel(val, pcie->base + reg);
+}
+
+static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg)
+{
+	return readl(pcie->base + reg);
+}
+
+static int advk_pcie_link_up(struct advk_pcie *pcie)
+{
+	u32 val, ltssm_state;
+
+	val = advk_readl(pcie, CFG_REG);
+	ltssm_state = (val >> LTSSM_SHIFT) & LTSSM_MASK;
+	return ltssm_state >= LTSSM_L0;
+}
+
+static int advk_pcie_wait_for_link(struct advk_pcie *pcie)
+{
+	int retries;
+
+	/* check if the link is up or not */
+	for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) {
+		if (advk_pcie_link_up(pcie)) {
+			dev_info(&pcie->pdev->dev, "link up\n");
+			return 0;
+		}
+
+		usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX);
+	}
+
+	dev_err(&pcie->pdev->dev, "link never came up\n");
+
+	return -ETIMEDOUT;
+}
+
+/*
+ * Set PCIe address window register which could be used for memory
+ * mapping.
+ */
+static void advk_pcie_set_ob_win(struct advk_pcie *pcie,
+				 u32 win_num, u32 match_ms,
+				 u32 match_ls, u32 mask_ms,
+				 u32 mask_ls, u32 remap_ms,
+				 u32 remap_ls, u32 action)
+{
+	advk_writel(pcie, match_ls, OB_WIN_MATCH_LS(win_num));
+	advk_writel(pcie, match_ms, OB_WIN_MATCH_MS(win_num));
+	advk_writel(pcie, mask_ms, OB_WIN_MASK_MS(win_num));
+	advk_writel(pcie, mask_ls, OB_WIN_MASK_LS(win_num));
+	advk_writel(pcie, remap_ms, OB_WIN_REMAP_MS(win_num));
+	advk_writel(pcie, remap_ls, OB_WIN_REMAP_LS(win_num));
+	advk_writel(pcie, action, OB_WIN_ACTIONS(win_num));
+	advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num));
+}
+
+static void advk_pcie_setup_hw(struct advk_pcie *pcie)
+{
+	u32 reg;
+	int i;
+
+	/* Point PCIe unit MBUS decode windows to DRAM space */
+	for (i = 0; i < 8; i++)
+		advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0);
+
+	/* Set to Direct mode */
+	reg = advk_readl(pcie, CTRL_CONFIG_REG);
+	reg &= ~(CTRL_MODE_MASK << CTRL_MODE_SHIFT);
+	reg |= ((PCIE_CORE_MODE_DIRECT & CTRL_MODE_MASK) << CTRL_MODE_SHIFT);
+	advk_writel(pcie, reg, CTRL_CONFIG_REG);
+
+	/* Set PCI global control register to RC mode */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg |= (IS_RC_MSK << IS_RC_SHIFT);
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/* Set Advanced Error Capabilities and Control PF0 register */
+	reg = PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX |
+		PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN |
+		PCIE_CORE_ERR_CAPCTL_ECRC_CHCK |
+		PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV;
+	advk_writel(pcie, reg, PCIE_CORE_ERR_CAPCTL_REG);
+
+	/* Set PCIe Device Control and Status 1 PF0 register */
+	reg = PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE |
+		(7 << PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT) |
+		PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE |
+		PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT;
+	advk_writel(pcie, reg, PCIE_CORE_DEV_CTRL_STATS_REG);
+
+	/* Program PCIe Control 2 to disable strict ordering */
+	reg = PCIE_CORE_CTRL2_RESERVED |
+		PCIE_CORE_CTRL2_TD_ENABLE;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG);
+
+	/* Set GEN2 */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg &= ~PCIE_GEN_SEL_MSK;
+	reg |= SPEED_GEN_2;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/* Set lane X1 */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg &= ~LANE_CNT_MSK;
+	reg |= LANE_COUNT_1;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/* Enable link training */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+	reg |= LINK_TRAINING_EN;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+	/* Enable MSI */
+	reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG);
+	reg |= PCIE_CORE_CTRL2_MSI_ENABLE;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG);
+
+	/* Clear all interrupts */
+	advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_REG);
+	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG);
+	advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG);
+
+	/* Disable All ISR0/1 Sources */
+	reg = PCIE_ISR0_ALL_MASK;
+	reg &= ~PCIE_ISR0_MSI_INT_PENDING;
+	advk_writel(pcie, reg, PCIE_ISR0_MASK_REG);
+
+	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG);
+
+	/* Unmask all MSI's */
+	advk_writel(pcie, 0, PCIE_MSI_MASK_REG);
+
+	/* Enable summary interrupt for GIC SPI source */
+	reg = PCIE_IRQ_ALL_MASK & (~PCIE_IRQ_ENABLE_INTS_MASK);
+	advk_writel(pcie, reg, HOST_CTRL_INT_MASK_REG);
+
+	reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG);
+	reg |= PCIE_CORE_CTRL2_OB_WIN_ENABLE;
+	advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG);
+
+	/* Bypass the address window mapping for PIO */
+	reg = advk_readl(pcie, PIO_CTRL);
+	reg |= PIO_CTRL_ADDR_WIN_DISABLE;
+	advk_writel(pcie, reg, PIO_CTRL);
+
+	/* Start link training */
+	reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG);
+	reg |= PCIE_CORE_LINK_TRAINING;
+	advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG);
+
+	advk_pcie_wait_for_link(pcie);
+
+	reg = PCIE_CORE_LINK_L0S_ENTRY |
+		(1 << PCIE_CORE_LINK_WIDTH_SHIFT);
+	advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG);
+
+	reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
+	reg |= PCIE_CORE_CMD_MEM_ACCESS_EN |
+		PCIE_CORE_CMD_IO_ACCESS_EN |
+		PCIE_CORE_CMD_MEM_IO_REQ_EN;
+	advk_writel(pcie, reg, PCIE_CORE_CMD_STATUS_REG);
+}
+
+static void advk_pcie_check_pio_status(struct advk_pcie *pcie)
+{
+	u32 reg;
+	unsigned int status;
+	char *strcomp_status, *str_posted;
+
+	reg = advk_readl(pcie, PIO_STAT);
+	status = (reg & PIO_COMPLETION_STATUS_MASK) >>
+		PIO_COMPLETION_STATUS_SHIFT;
+
+	if (!status)
+		return;
+
+	switch (status) {
+	case PIO_COMPLETION_STATUS_UR:
+		strcomp_status = "UR";
+		break;
+	case PIO_COMPLETION_STATUS_CRS:
+		strcomp_status = "CRS";
+		break;
+	case PIO_COMPLETION_STATUS_CA:
+		strcomp_status = "CA";
+		break;
+	default:
+		strcomp_status = "Unknown";
+		break;
+	}
+
+	if (reg & PIO_NON_POSTED_REQ)
+		str_posted = "Non-posted";
+	else
+		str_posted = "Posted";
+
+	dev_err(&pcie->pdev->dev, "%s PIO Response Status: %s, %#x @ %#x\n",
+		str_posted, strcomp_status, reg, advk_readl(pcie, PIO_ADDR_LS));
+}
+
+static int advk_pcie_wait_pio(struct advk_pcie *pcie)
+{
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(PIO_TIMEOUT_MS);
+
+	while (time_before(jiffies, timeout)) {
+		u32 start, isr;
+
+		start = advk_readl(pcie, PIO_START);
+		isr = advk_readl(pcie, PIO_ISR);
+		if (!start && isr)
+			return 0;
+	}
+
+	dev_err(&pcie->pdev->dev, "config read/write timed out\n");
+	return -ETIMEDOUT;
+}
+
+static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
+			     int where, int size, u32 *val)
+{
+	struct advk_pcie *pcie = bus->sysdata;
+	u32 reg;
+	int ret;
+
+	if (PCI_SLOT(devfn) != 0) {
+		*val = 0xffffffff;
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	}
+
+	/* Start PIO */
+	advk_writel(pcie, 0, PIO_START);
+	advk_writel(pcie, 1, PIO_ISR);
+
+	/* Program the control register */
+	reg = advk_readl(pcie, PIO_CTRL);
+	reg &= ~PIO_CTRL_TYPE_MASK;
+	if (bus->number ==  pcie->root_bus_nr)
+		reg |= PCIE_CONFIG_RD_TYPE0;
+	else
+		reg |= PCIE_CONFIG_RD_TYPE1;
+	advk_writel(pcie, reg, PIO_CTRL);
+
+	/* Program the address registers */
+	reg = PCIE_BDF(devfn) | PCIE_CONF_REG(where);
+	advk_writel(pcie, reg, PIO_ADDR_LS);
+	advk_writel(pcie, 0, PIO_ADDR_MS);
+
+	/* Program the data strobe */
+	advk_writel(pcie, 0xf, PIO_WR_DATA_STRB);
+
+	/* Start the transfer */
+	advk_writel(pcie, 1, PIO_START);
+
+	ret = advk_pcie_wait_pio(pcie);
+	if (ret < 0)
+		return PCIBIOS_SET_FAILED;
+
+	advk_pcie_check_pio_status(pcie);
+
+	/* Get the read result */
+	*val = advk_readl(pcie, PIO_RD_DATA);
+	if (size == 1)
+		*val = (*val >> (8 * (where & 3))) & 0xff;
+	else if (size == 2)
+		*val = (*val >> (8 * (where & 3))) & 0xffff;
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
+				int where, int size, u32 val)
+{
+	struct advk_pcie *pcie = bus->sysdata;
+	u32 reg;
+	u32 data_strobe = 0x0;
+	int offset;
+	int ret;
+
+	if (PCI_SLOT(devfn) != 0)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (where % size)
+		return PCIBIOS_SET_FAILED;
+
+	/* Start PIO */
+	advk_writel(pcie, 0, PIO_START);
+	advk_writel(pcie, 1, PIO_ISR);
+
+	/* Program the control register */
+	reg = advk_readl(pcie, PIO_CTRL);
+	reg &= ~PIO_CTRL_TYPE_MASK;
+	if (bus->number == pcie->root_bus_nr)
+		reg |= PCIE_CONFIG_WR_TYPE0;
+	else
+		reg |= PCIE_CONFIG_WR_TYPE1;
+	advk_writel(pcie, reg, PIO_CTRL);
+
+	/* Program the address registers */
+	reg = PCIE_CONF_ADDR(bus->number, devfn, where);
+	advk_writel(pcie, reg, PIO_ADDR_LS);
+	advk_writel(pcie, 0, PIO_ADDR_MS);
+
+	/* Calculate the write strobe */
+	offset      = where & 0x3;
+	reg         = val << (8 * offset);
+	data_strobe = GENMASK(size - 1, 0) << offset;
+
+	/* Program the data register */
+	advk_writel(pcie, reg, PIO_WR_DATA);
+
+	/* Program the data strobe */
+	advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB);
+
+	/* Start the transfer */
+	advk_writel(pcie, 1, PIO_START);
+
+	ret = advk_pcie_wait_pio(pcie);
+	if (ret < 0)
+		return PCIBIOS_SET_FAILED;
+
+	advk_pcie_check_pio_status(pcie);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops advk_pcie_ops = {
+	.read = advk_pcie_rd_conf,
+	.write = advk_pcie_wr_conf,
+};
+
+static int advk_pcie_alloc_msi(struct advk_pcie *pcie)
+{
+	int hwirq;
+
+	mutex_lock(&pcie->msi_used_lock);
+	hwirq = find_first_zero_bit(pcie->msi_irq_in_use, MSI_IRQ_NUM);
+	if (hwirq >= MSI_IRQ_NUM)
+		hwirq = -ENOSPC;
+	else
+		set_bit(hwirq, pcie->msi_irq_in_use);
+	mutex_unlock(&pcie->msi_used_lock);
+
+	return hwirq;
+}
+
+static void advk_pcie_free_msi(struct advk_pcie *pcie, int hwirq)
+{
+	mutex_lock(&pcie->msi_used_lock);
+	if (!test_bit(hwirq, pcie->msi_irq_in_use))
+		dev_err(&pcie->pdev->dev, "trying to free unused MSI#%d\n",
+			hwirq);
+	else
+		clear_bit(hwirq, pcie->msi_irq_in_use);
+	mutex_unlock(&pcie->msi_used_lock);
+}
+
+static int advk_pcie_setup_msi_irq(struct msi_controller *chip,
+				   struct pci_dev *pdev,
+				   struct msi_desc *desc)
+{
+	struct advk_pcie *pcie = pdev->bus->sysdata;
+	struct msi_msg msg;
+	int virq, hwirq;
+	phys_addr_t msi_msg_phys;
+
+	/* We support MSI, but not MSI-X */
+	if (desc->msi_attrib.is_msix)
+		return -EINVAL;
+
+	hwirq = advk_pcie_alloc_msi(pcie);
+	if (hwirq < 0)
+		return hwirq;
+
+	virq = irq_create_mapping(pcie->msi_domain, hwirq);
+	if (!virq) {
+		advk_pcie_free_msi(pcie, hwirq);
+		return -EINVAL;
+	}
+
+	irq_set_msi_desc(virq, desc);
+
+	msi_msg_phys = virt_to_phys(&pcie->msi_msg);
+
+	msg.address_lo = lower_32_bits(msi_msg_phys);
+	msg.address_hi = upper_32_bits(msi_msg_phys);
+	msg.data = virq;
+
+	pci_write_msi_msg(virq, &msg);
+
+	return 0;
+}
+
+static void advk_pcie_teardown_msi_irq(struct msi_controller *chip,
+				       unsigned int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+	struct msi_desc *msi = irq_data_get_msi_desc(d);
+	struct advk_pcie *pcie = msi_desc_to_pci_sysdata(msi);
+	unsigned long hwirq = d->hwirq;
+
+	irq_dispose_mapping(irq);
+	advk_pcie_free_msi(pcie, hwirq);
+}
+
+static int advk_pcie_msi_map(struct irq_domain *domain,
+			     unsigned int virq, irq_hw_number_t hw)
+{
+	struct advk_pcie *pcie = domain->host_data;
+
+	irq_set_chip_and_handler(virq, &pcie->msi_irq_chip,
+				 handle_simple_irq);
+
+	return 0;
+}
+
+static const struct irq_domain_ops advk_pcie_msi_irq_ops = {
+	.map = advk_pcie_msi_map,
+};
+
+static void advk_pcie_irq_mask(struct irq_data *d)
+{
+	struct advk_pcie *pcie = d->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	u32 mask;
+
+	mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+	mask |= PCIE_ISR0_INTX_ASSERT(hwirq);
+	advk_writel(pcie, mask, PCIE_ISR0_MASK_REG);
+}
+
+static void advk_pcie_irq_unmask(struct irq_data *d)
+{
+	struct advk_pcie *pcie = d->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	u32 mask;
+
+	mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+	mask &= ~PCIE_ISR0_INTX_ASSERT(hwirq);
+	advk_writel(pcie, mask, PCIE_ISR0_MASK_REG);
+}
+
+static int advk_pcie_irq_map(struct irq_domain *h,
+			     unsigned int virq, irq_hw_number_t hwirq)
+{
+	struct advk_pcie *pcie = h->host_data;
+
+	advk_pcie_irq_mask(irq_get_irq_data(virq));
+	irq_set_status_flags(virq, IRQ_LEVEL);
+	irq_set_chip_and_handler(virq, &pcie->irq_chip,
+				 handle_level_irq);
+	irq_set_chip_data(virq, pcie);
+
+	return 0;
+}
+
+static const struct irq_domain_ops advk_pcie_irq_domain_ops = {
+	.map = advk_pcie_irq_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int advk_pcie_init_msi_irq_domain(struct advk_pcie *pcie)
+{
+	struct device *dev = &pcie->pdev->dev;
+	struct device_node *node = dev->of_node;
+	struct irq_chip *msi_irq_chip;
+	struct msi_controller *msi;
+	phys_addr_t msi_msg_phys;
+	int ret;
+
+	msi_irq_chip = &pcie->msi_irq_chip;
+
+	msi_irq_chip->name = devm_kasprintf(dev, GFP_KERNEL, "%s-msi",
+					    dev_name(dev));
+	if (!msi_irq_chip->name)
+		return -ENOMEM;
+
+	msi_irq_chip->irq_enable = pci_msi_unmask_irq;
+	msi_irq_chip->irq_disable = pci_msi_mask_irq;
+	msi_irq_chip->irq_mask = pci_msi_mask_irq;
+	msi_irq_chip->irq_unmask = pci_msi_unmask_irq;
+
+	msi = &pcie->msi;
+
+	msi->setup_irq = advk_pcie_setup_msi_irq;
+	msi->teardown_irq = advk_pcie_teardown_msi_irq;
+	msi->of_node = node;
+
+	mutex_init(&pcie->msi_used_lock);
+
+	msi_msg_phys = virt_to_phys(&pcie->msi_msg);
+
+	advk_writel(pcie, lower_32_bits(msi_msg_phys),
+		    PCIE_MSI_ADDR_LOW_REG);
+	advk_writel(pcie, upper_32_bits(msi_msg_phys),
+		    PCIE_MSI_ADDR_HIGH_REG);
+
+	pcie->msi_domain =
+		irq_domain_add_linear(NULL, MSI_IRQ_NUM,
+				      &advk_pcie_msi_irq_ops, pcie);
+	if (!pcie->msi_domain)
+		return -ENOMEM;
+
+	ret = of_pci_msi_chip_add(msi);
+	if (ret < 0) {
+		irq_domain_remove(pcie->msi_domain);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void advk_pcie_remove_msi_irq_domain(struct advk_pcie *pcie)
+{
+	of_pci_msi_chip_remove(&pcie->msi);
+	irq_domain_remove(pcie->msi_domain);
+}
+
+static int advk_pcie_init_irq_domain(struct advk_pcie *pcie)
+{
+	struct device *dev = &pcie->pdev->dev;
+	struct device_node *node = dev->of_node;
+	struct device_node *pcie_intc_node;
+	struct irq_chip *irq_chip;
+
+	pcie_intc_node =  of_get_next_child(node, NULL);
+	if (!pcie_intc_node) {
+		dev_err(dev, "No PCIe Intc node found\n");
+		return -ENODEV;
+	}
+
+	irq_chip = &pcie->irq_chip;
+
+	irq_chip->name = devm_kasprintf(dev, GFP_KERNEL, "%s-irq",
+					dev_name(dev));
+	if (!irq_chip->name) {
+		of_node_put(pcie_intc_node);
+		return -ENOMEM;
+	}
+
+	irq_chip->irq_mask = advk_pcie_irq_mask;
+	irq_chip->irq_mask_ack = advk_pcie_irq_mask;
+	irq_chip->irq_unmask = advk_pcie_irq_unmask;
+
+	pcie->irq_domain =
+		irq_domain_add_linear(pcie_intc_node, LEGACY_IRQ_NUM,
+				      &advk_pcie_irq_domain_ops, pcie);
+	if (!pcie->irq_domain) {
+		dev_err(dev, "Failed to get a INTx IRQ domain\n");
+		of_node_put(pcie_intc_node);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void advk_pcie_remove_irq_domain(struct advk_pcie *pcie)
+{
+	irq_domain_remove(pcie->irq_domain);
+}
+
+static void advk_pcie_handle_msi(struct advk_pcie *pcie)
+{
+	u32 msi_val, msi_mask, msi_status, msi_idx;
+	u16 msi_data;
+
+	msi_mask = advk_readl(pcie, PCIE_MSI_MASK_REG);
+	msi_val = advk_readl(pcie, PCIE_MSI_STATUS_REG);
+	msi_status = msi_val & ~msi_mask;
+
+	for (msi_idx = 0; msi_idx < MSI_IRQ_NUM; msi_idx++) {
+		if (!(BIT(msi_idx) & msi_status))
+			continue;
+
+		advk_writel(pcie, BIT(msi_idx), PCIE_MSI_STATUS_REG);
+		msi_data = advk_readl(pcie, PCIE_MSI_PAYLOAD_REG) & 0xFF;
+		generic_handle_irq(msi_data);
+	}
+
+	advk_writel(pcie, PCIE_ISR0_MSI_INT_PENDING,
+		    PCIE_ISR0_REG);
+}
+
+static void advk_pcie_handle_int(struct advk_pcie *pcie)
+{
+	u32 val, mask, status;
+	int i, virq;
+
+	val = advk_readl(pcie, PCIE_ISR0_REG);
+	mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+	status = val & ((~mask) & PCIE_ISR0_ALL_MASK);
+
+	if (!status) {
+		advk_writel(pcie, val, PCIE_ISR0_REG);
+		return;
+	}
+
+	/* Process MSI interrupts */
+	if (status & PCIE_ISR0_MSI_INT_PENDING)
+		advk_pcie_handle_msi(pcie);
+
+	/* Process legacy interrupts */
+	for (i = 0; i < LEGACY_IRQ_NUM; i++) {
+		if (!(status & PCIE_ISR0_INTX_ASSERT(i)))
+			continue;
+
+		advk_writel(pcie, PCIE_ISR0_INTX_ASSERT(i),
+			    PCIE_ISR0_REG);
+
+		virq = irq_find_mapping(pcie->irq_domain, i);
+		generic_handle_irq(virq);
+	}
+}
+
+static irqreturn_t advk_pcie_irq_handler(int irq, void *arg)
+{
+	struct advk_pcie *pcie = arg;
+	u32 status;
+
+	status = advk_readl(pcie, HOST_CTRL_INT_STATUS_REG);
+	if (!(status & PCIE_IRQ_CORE_INT))
+		return IRQ_NONE;
+
+	advk_pcie_handle_int(pcie);
+
+	/* Clear interrupt */
+	advk_writel(pcie, PCIE_IRQ_CORE_INT, HOST_CTRL_INT_STATUS_REG);
+
+	return IRQ_HANDLED;
+}
+
+static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie)
+{
+	int err, res_valid = 0;
+	struct device *dev = &pcie->pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct resource_entry *win;
+	resource_size_t iobase;
+
+	INIT_LIST_HEAD(&pcie->resources);
+
+	err = of_pci_get_host_bridge_resources(np, 0, 0xff, &pcie->resources,
+					       &iobase);
+	if (err)
+		return err;
+
+	err = devm_request_pci_bus_resources(dev, &pcie->resources);
+	if (err)
+		goto out_release_res;
+
+	resource_list_for_each_entry(win, &pcie->resources) {
+		struct resource *res = win->res;
+
+		switch (resource_type(res)) {
+		case IORESOURCE_IO:
+			advk_pcie_set_ob_win(pcie, 1,
+					     upper_32_bits(res->start),
+					     lower_32_bits(res->start),
+					     0,	0xF8000000, 0,
+					     lower_32_bits(res->start),
+					     OB_PCIE_IO);
+			err = pci_remap_iospace(res, iobase);
+			if (err)
+				dev_warn(dev, "error %d: failed to map resource %pR\n",
+					 err, res);
+			break;
+		case IORESOURCE_MEM:
+			advk_pcie_set_ob_win(pcie, 0,
+					     upper_32_bits(res->start),
+					     lower_32_bits(res->start),
+					     0x0, 0xF8000000, 0,
+					     lower_32_bits(res->start),
+					     (2 << 20) | OB_PCIE_MEM);
+			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
+			break;
+		case IORESOURCE_BUS:
+			pcie->root_bus_nr = res->start;
+			break;
+		}
+	}
+
+	if (!res_valid) {
+		dev_err(dev, "non-prefetchable memory resource required\n");
+		err = -EINVAL;
+		goto out_release_res;
+	}
+
+	return 0;
+
+out_release_res:
+	pci_free_resource_list(&pcie->resources);
+	return err;
+}
+
+static int advk_pcie_probe(struct platform_device *pdev)
+{
+	struct advk_pcie *pcie;
+	struct resource *res;
+	struct pci_bus *bus, *child;
+	struct msi_controller *msi;
+	struct device_node *msi_node;
+	int ret, irq;
+
+	pcie = devm_kzalloc(&pdev->dev, sizeof(struct advk_pcie),
+			    GFP_KERNEL);
+	if (!pcie)
+		return -ENOMEM;
+
+	pcie->pdev = pdev;
+	platform_set_drvdata(pdev, pcie);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	pcie->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(pcie->base)) {
+		dev_err(&pdev->dev, "Failed to map registers\n");
+		return PTR_ERR(pcie->base);
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	ret = devm_request_irq(&pdev->dev, irq, advk_pcie_irq_handler,
+			       IRQF_SHARED | IRQF_NO_THREAD, "advk-pcie",
+			       pcie);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to register interrupt\n");
+		return ret;
+	}
+
+	ret = advk_pcie_parse_request_of_pci_ranges(pcie);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to parse resources\n");
+		return ret;
+	}
+
+	advk_pcie_setup_hw(pcie);
+
+	ret = advk_pcie_init_irq_domain(pcie);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to initialize irq\n");
+		return ret;
+	}
+
+	ret = advk_pcie_init_msi_irq_domain(pcie);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to initialize irq\n");
+		advk_pcie_remove_irq_domain(pcie);
+		return ret;
+	}
+
+	msi_node = of_parse_phandle(pdev->dev.of_node, "msi-parent", 0);
+	if (msi_node)
+		msi = of_pci_find_msi_chip_by_node(msi_node);
+	else
+		msi = NULL;
+
+	bus = pci_scan_root_bus_msi(&pdev->dev, 0, &advk_pcie_ops,
+				    pcie, &pcie->resources, &pcie->msi);
+	if (!bus) {
+		advk_pcie_remove_msi_irq_domain(pcie);
+		advk_pcie_remove_irq_domain(pcie);
+		return -ENOMEM;
+	}
+
+	pci_bus_assign_resources(bus);
+
+	list_for_each_entry(child, &bus->children, node)
+		pcie_bus_configure_settings(child);
+
+	pci_bus_add_devices(bus);
+
+	return 0;
+}
+
+static const struct of_device_id advk_pcie_of_match_table[] = {
+	{ .compatible = "marvell,armada-3700-pcie", },
+	{},
+};
+
+static struct platform_driver advk_pcie_driver = {
+	.driver = {
+		.name = "advk-pcie",
+		.of_match_table = advk_pcie_of_match_table,
+		/* Driver unloading/unbinding currently not supported */
+		.suppress_bind_attrs = true,
+	},
+	.probe = advk_pcie_probe,
+};
+builtin_platform_driver(advk_pcie_driver);
diff --git a/drivers/pci/host/pci-dra7xx.c b/drivers/pci/host/pci-dra7xx.c
index f441130407e7..81b3949a26db 100644
--- a/drivers/pci/host/pci-dra7xx.c
+++ b/drivers/pci/host/pci-dra7xx.c
@@ -181,14 +181,14 @@ static int dra7xx_pcie_init_irq_domain(struct pcie_port *pp)
 
 	if (!pcie_intc_node) {
 		dev_err(dev, "No PCIe Intc node found\n");
-		return PTR_ERR(pcie_intc_node);
+		return -ENODEV;
 	}
 
 	pp->irq_domain = irq_domain_add_linear(pcie_intc_node, 4,
 					       &intx_domain_ops, pp);
 	if (!pp->irq_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
-		return PTR_ERR(pp->irq_domain);
+		return -ENODEV;
 	}
 
 	return 0;
diff --git a/drivers/pci/host/pci-host-common.c b/drivers/pci/host/pci-host-common.c
index 8cba7ab73df9..9d9d34e959b6 100644
--- a/drivers/pci/host/pci-host-common.c
+++ b/drivers/pci/host/pci-host-common.c
@@ -20,10 +20,9 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
+#include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
 
-#include "../ecam.h"
-
 static int gen_pci_parse_request_of_pci_ranges(struct device *dev,
 		       struct list_head *resources, struct resource **bus_range)
 {
@@ -36,44 +35,34 @@ static int gen_pci_parse_request_of_pci_ranges(struct device *dev,
 	if (err)
 		return err;
 
+	err = devm_request_pci_bus_resources(dev, resources);
+	if (err)
+		return err;
+
 	resource_list_for_each_entry(win, resources) {
-		struct resource *parent, *res = win->res;
+		struct resource *res = win->res;
 
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
-			parent = &ioport_resource;
 			err = pci_remap_iospace(res, iobase);
-			if (err) {
+			if (err)
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 err, res);
-				continue;
-			}
 			break;
 		case IORESOURCE_MEM:
-			parent = &iomem_resource;
 			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
 			break;
 		case IORESOURCE_BUS:
 			*bus_range = res;
-		default:
-			continue;
+			break;
 		}
-
-		err = devm_request_resource(dev, parent, res);
-		if (err)
-			goto out_release_res;
-	}
-
-	if (!res_valid) {
-		dev_err(dev, "non-prefetchable memory resource required\n");
-		err = -EINVAL;
-		goto out_release_res;
 	}
 
-	return 0;
+	if (res_valid)
+		return 0;
 
-out_release_res:
-	return err;
+	dev_err(dev, "non-prefetchable memory resource required\n");
+	return -EINVAL;
 }
 
 static void gen_pci_unmap_cfg(void *ptr)
@@ -155,7 +144,14 @@ int pci_host_common_probe(struct platform_device *pdev,
 
 	pci_fixup_irqs(pci_common_swizzle, of_irq_parse_and_map_pci);
 
-	if (!pci_has_flag(PCI_PROBE_ONLY)) {
+	/*
+	 * We insert PCI resources into the iomem_resource and
+	 * ioport_resource trees in either pci_bus_claim_resources()
+	 * or pci_bus_assign_resources().
+	 */
+	if (pci_has_flag(PCI_PROBE_ONLY)) {
+		pci_bus_claim_resources(bus);
+	} else {
 		pci_bus_size_bridges(bus);
 		pci_bus_assign_resources(bus);
 
diff --git a/drivers/pci/host/pci-host-generic.c b/drivers/pci/host/pci-host-generic.c
index 6eaceab1bf04..c05ea9d72f69 100644
--- a/drivers/pci/host/pci-host-generic.c
+++ b/drivers/pci/host/pci-host-generic.c
@@ -20,13 +20,12 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
+#include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
 
-#include "../ecam.h"
-
 static struct pci_ecam_ops gen_pci_cfg_cam_bus_ops = {
 	.bus_shift	= 16,
 	.pci_ops	= {
@@ -46,8 +45,6 @@ static const struct of_device_id gen_pci_of_match[] = {
 	{ },
 };
 
-MODULE_DEVICE_TABLE(of, gen_pci_of_match);
-
 static int gen_pci_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
@@ -66,8 +63,4 @@ static struct platform_driver gen_pci_driver = {
 	},
 	.probe = gen_pci_probe,
 };
-module_platform_driver(gen_pci_driver);
-
-MODULE_DESCRIPTION("Generic PCI host driver");
-MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(gen_pci_driver);
diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c
index 7e9b2de2aa24..6955ffdb89f3 100644
--- a/drivers/pci/host/pci-hyperv.c
+++ b/drivers/pci/host/pci-hyperv.c
@@ -732,16 +732,18 @@ static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info,
 
 	pdev = msi_desc_to_pci_dev(msi);
 	hbus = info->data;
-	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
-	if (!hpdev)
+	int_desc = irq_data_get_irq_chip_data(irq_data);
+	if (!int_desc)
 		return;
 
-	int_desc = irq_data_get_irq_chip_data(irq_data);
-	if (int_desc) {
-		irq_data->chip_data = NULL;
-		hv_int_desc_free(hpdev, int_desc);
+	irq_data->chip_data = NULL;
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
+	if (!hpdev) {
+		kfree(int_desc);
+		return;
 	}
 
+	hv_int_desc_free(hpdev, int_desc);
 	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
 }
 
@@ -1657,14 +1659,16 @@ static void hv_pci_onchannelcallback(void *context)
 			continue;
 		}
 
+		/* Zero length indicates there are no more packets. */
+		if (ret || !bytes_recvd)
+			break;
+
 		/*
 		 * All incoming packets must be at least as large as a
 		 * response.
 		 */
-		if (bytes_recvd <= sizeof(struct pci_response)) {
-			kfree(buffer);
-			return;
-		}
+		if (bytes_recvd <= sizeof(struct pci_response))
+			continue;
 		desc = (struct vmpacket_descriptor *)buffer;
 
 		switch (desc->type) {
@@ -1679,8 +1683,7 @@ static void hv_pci_onchannelcallback(void *context)
 			comp_packet->completion_func(comp_packet->compl_ctxt,
 						     response,
 						     bytes_recvd);
-			kfree(buffer);
-			return;
+			break;
 
 		case VM_PKT_DATA_INBAND:
 
@@ -1727,8 +1730,9 @@ static void hv_pci_onchannelcallback(void *context)
 				desc->type, req_id, bytes_recvd);
 			break;
 		}
-		break;
 	}
+
+	kfree(buffer);
 }
 
 /**
diff --git a/drivers/pci/host/pci-keystone.c b/drivers/pci/host/pci-keystone.c
index 6b8301ef21ca..8ba28834d470 100644
--- a/drivers/pci/host/pci-keystone.c
+++ b/drivers/pci/host/pci-keystone.c
@@ -17,7 +17,7 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/msi.h>
 #include <linux/of_irq.h>
 #include <linux/of.h>
@@ -360,7 +360,6 @@ static const struct of_device_id ks_pcie_of_match[] = {
 	},
 	{ },
 };
-MODULE_DEVICE_TABLE(of, ks_pcie_of_match);
 
 static int __exit ks_pcie_remove(struct platform_device *pdev)
 {
@@ -439,9 +438,4 @@ static struct platform_driver ks_pcie_driver __refdata = {
 		.of_match_table = of_match_ptr(ks_pcie_of_match),
 	},
 };
-
-module_platform_driver(ks_pcie_driver);
-
-MODULE_AUTHOR("Murali Karicheri <m-karicheri2@ti.com>");
-MODULE_DESCRIPTION("Keystone PCIe host controller driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(ks_pcie_driver);
diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c
index a21e229d95e0..114ba819277a 100644
--- a/drivers/pci/host/pci-layerscape.c
+++ b/drivers/pci/host/pci-layerscape.c
@@ -12,7 +12,7 @@
 
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of_pci.h>
 #include <linux/of_platform.h>
 #include <linux/of_irq.h>
@@ -211,7 +211,6 @@ static const struct of_device_id ls_pcie_of_match[] = {
 	{ .compatible = "fsl,ls2085a-pcie", .data = &ls2080_drvdata },
 	{ },
 };
-MODULE_DEVICE_TABLE(of, ls_pcie_of_match);
 
 static int __init ls_add_pcie_port(struct pcie_port *pp,
 				   struct platform_device *pdev)
@@ -275,9 +274,4 @@ static struct platform_driver ls_pcie_driver = {
 		.of_match_table = ls_pcie_of_match,
 	},
 };
-
-module_platform_driver_probe(ls_pcie_driver, ls_pcie_probe);
-
-MODULE_AUTHOR("Minghuan Lian <Minghuan.Lian@freescale.com>");
-MODULE_DESCRIPTION("Freescale Layerscape PCIe host controller driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver_probe(ls_pcie_driver, ls_pcie_probe);
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index 6b451df6502c..307f81d6b479 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -1,6 +1,8 @@
 /*
  * PCIe driver for Marvell Armada 370 and Armada XP SoCs
  *
+ * Author: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
  * This file is licensed under the terms of the GNU General Public
  * License version 2.  This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
@@ -11,7 +13,7 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/gpio.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/mbus.h>
 #include <linux/msi.h>
 #include <linux/slab.h>
@@ -839,25 +841,22 @@ static struct pci_ops mvebu_pcie_ops = {
 static int mvebu_pcie_setup(int nr, struct pci_sys_data *sys)
 {
 	struct mvebu_pcie *pcie = sys_to_pcie(sys);
-	int i;
+	int err, i;
 
 	pcie->mem.name = "PCI MEM";
 	pcie->realio.name = "PCI I/O";
 
-	if (request_resource(&iomem_resource, &pcie->mem))
-		return 0;
-
-	if (resource_size(&pcie->realio) != 0) {
-		if (request_resource(&ioport_resource, &pcie->realio)) {
-			release_resource(&pcie->mem);
-			return 0;
-		}
+	if (resource_size(&pcie->realio) != 0)
 		pci_add_resource_offset(&sys->resources, &pcie->realio,
 					sys->io_offset);
-	}
+
 	pci_add_resource_offset(&sys->resources, &pcie->mem, sys->mem_offset);
 	pci_add_resource(&sys->resources, &pcie->busn);
 
+	err = devm_request_pci_bus_resources(&pcie->pdev->dev, &sys->resources);
+	if (err)
+		return 0;
+
 	for (i = 0; i < pcie->nports; i++) {
 		struct mvebu_pcie_port *port = &pcie->ports[i];
 
@@ -1298,7 +1297,6 @@ static const struct of_device_id mvebu_pcie_of_match_table[] = {
 	{ .compatible = "marvell,kirkwood-pcie", },
 	{},
 };
-MODULE_DEVICE_TABLE(of, mvebu_pcie_of_match_table);
 
 static const struct dev_pm_ops mvebu_pcie_pm_ops = {
 	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mvebu_pcie_suspend, mvebu_pcie_resume)
@@ -1314,8 +1312,4 @@ static struct platform_driver mvebu_pcie_driver = {
 	},
 	.probe = mvebu_pcie_probe,
 };
-module_platform_driver(mvebu_pcie_driver);
-
-MODULE_AUTHOR("Thomas Petazzoni <thomas.petazzoni@free-electrons.com>");
-MODULE_DESCRIPTION("Marvell EBU PCIe driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(mvebu_pcie_driver);
diff --git a/drivers/pci/host/pci-rcar-gen2.c b/drivers/pci/host/pci-rcar-gen2.c
index 9980a4bdae7e..597566f96f5e 100644
--- a/drivers/pci/host/pci-rcar-gen2.c
+++ b/drivers/pci/host/pci-rcar-gen2.c
@@ -4,6 +4,8 @@
  * Copyright (C) 2013 Renesas Solutions Corp.
  * Copyright (C) 2013 Cogent Embedded, Inc.
  *
+ * Author: Valentine Barshak <valentine.barshak@cogentembedded.com>
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
@@ -14,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
 #include <linux/pci.h>
@@ -97,7 +98,6 @@
 struct rcar_pci_priv {
 	struct device *dev;
 	void __iomem *reg;
-	struct resource io_res;
 	struct resource mem_res;
 	struct resource *cfg_res;
 	unsigned busnr;
@@ -194,6 +194,7 @@ static int rcar_pci_setup(int nr, struct pci_sys_data *sys)
 	struct rcar_pci_priv *priv = sys->private_data;
 	void __iomem *reg = priv->reg;
 	u32 val;
+	int ret;
 
 	pm_runtime_enable(priv->dev);
 	pm_runtime_get_sync(priv->dev);
@@ -273,8 +274,10 @@ static int rcar_pci_setup(int nr, struct pci_sys_data *sys)
 		rcar_pci_setup_errirq(priv);
 
 	/* Add PCI resources */
-	pci_add_resource(&sys->resources, &priv->io_res);
 	pci_add_resource(&sys->resources, &priv->mem_res);
+	ret = devm_request_pci_bus_resources(priv->dev, &sys->resources);
+	if (ret < 0)
+		return ret;
 
 	/* Setup bus number based on platform device id / of bus-range */
 	sys->busnr = priv->busnr;
@@ -371,14 +374,6 @@ static int rcar_pci_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	priv->mem_res = *mem_res;
-	/*
-	 * The controller does not support/use port I/O,
-	 * so setup a dummy port I/O region here.
-	 */
-	priv->io_res.start = priv->mem_res.start;
-	priv->io_res.end = priv->mem_res.end;
-	priv->io_res.flags = IORESOURCE_IO;
-
 	priv->cfg_res = cfg_res;
 
 	priv->irq = platform_get_irq(pdev, 0);
@@ -421,6 +416,7 @@ static int rcar_pci_probe(struct platform_device *pdev)
 	hw_private[0] = priv;
 	memset(&hw, 0, sizeof(hw));
 	hw.nr_controllers = ARRAY_SIZE(hw_private);
+	hw.io_optional = 1;
 	hw.private_data = hw_private;
 	hw.map_irq = rcar_pci_map_irq;
 	hw.ops = &rcar_pci_ops;
@@ -437,8 +433,6 @@ static struct of_device_id rcar_pci_of_match[] = {
 	{ },
 };
 
-MODULE_DEVICE_TABLE(of, rcar_pci_of_match);
-
 static struct platform_driver rcar_pci_driver = {
 	.driver = {
 		.name = "pci-rcar-gen2",
@@ -447,9 +441,4 @@ static struct platform_driver rcar_pci_driver = {
 	},
 	.probe = rcar_pci_probe,
 };
-
-module_platform_driver(rcar_pci_driver);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("Renesas R-Car Gen2 internal PCI");
-MODULE_AUTHOR("Valentine Barshak <valentine.barshak@cogentembedded.com>");
+builtin_platform_driver(rcar_pci_driver);
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index c388468c202a..6de0757b11e4 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -9,6 +9,8 @@
  *
  * Bits taken from arch/arm/mach-dove/pcie.c
  *
+ * Author: Thierry Reding <treding@nvidia.com>
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -32,7 +34,7 @@
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/msi.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
@@ -183,26 +185,26 @@
 
 #define AFI_PEXBIAS_CTRL_0		0x168
 
-#define RP_VEND_XP	0x00000F00
+#define RP_VEND_XP	0x00000f00
 #define  RP_VEND_XP_DL_UP	(1 << 30)
 
-#define RP_PRIV_MISC	0x00000FE0
-#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT (0xE << 0)
-#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT (0xF << 0)
+#define RP_PRIV_MISC	0x00000fe0
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT (0xe << 0)
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT (0xf << 0)
 
 #define RP_LINK_CONTROL_STATUS			0x00000090
 #define  RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE	0x20000000
 #define  RP_LINK_CONTROL_STATUS_LINKSTAT_MASK	0x3fff0000
 
-#define PADS_CTL_SEL		0x0000009C
+#define PADS_CTL_SEL		0x0000009c
 
-#define PADS_CTL		0x000000A0
+#define PADS_CTL		0x000000a0
 #define  PADS_CTL_IDDQ_1L	(1 << 0)
 #define  PADS_CTL_TX_DATA_EN_1L	(1 << 6)
 #define  PADS_CTL_RX_DATA_EN_1L	(1 << 10)
 
-#define PADS_PLL_CTL_TEGRA20			0x000000B8
-#define PADS_PLL_CTL_TEGRA30			0x000000B4
+#define PADS_PLL_CTL_TEGRA20			0x000000b8
+#define PADS_PLL_CTL_TEGRA30			0x000000b4
 #define  PADS_PLL_CTL_RST_B4SM			(1 << 1)
 #define  PADS_PLL_CTL_LOCKDET			(1 << 8)
 #define  PADS_PLL_CTL_REFCLK_MASK		(0x3 << 16)
@@ -214,9 +216,9 @@
 #define  PADS_PLL_CTL_TXCLKREF_DIV5		(1 << 20)
 #define  PADS_PLL_CTL_TXCLKREF_BUF_EN		(1 << 22)
 
-#define PADS_REFCLK_CFG0			0x000000C8
-#define PADS_REFCLK_CFG1			0x000000CC
-#define PADS_REFCLK_BIAS			0x000000D0
+#define PADS_REFCLK_CFG0			0x000000c8
+#define PADS_REFCLK_CFG1			0x000000cc
+#define PADS_REFCLK_BIAS			0x000000d0
 
 /*
  * Fields in PADS_REFCLK_CFG*. Those registers form an array of 16-bit
@@ -228,15 +230,6 @@
 #define PADS_REFCLK_CFG_PREDI_SHIFT		8  /* 11:8 */
 #define PADS_REFCLK_CFG_DRVI_SHIFT		12 /* 15:12 */
 
-/* Default value provided by HW engineering is 0xfa5c */
-#define PADS_REFCLK_CFG_VALUE \
-	( \
-		(0x17 << PADS_REFCLK_CFG_TERM_SHIFT)   | \
-		(0    << PADS_REFCLK_CFG_E_TERM_SHIFT) | \
-		(0xa  << PADS_REFCLK_CFG_PREDI_SHIFT)  | \
-		(0xf  << PADS_REFCLK_CFG_DRVI_SHIFT)     \
-	)
-
 struct tegra_msi {
 	struct msi_controller chip;
 	DECLARE_BITMAP(used, INT_PCI_MSI_NR);
@@ -252,6 +245,8 @@ struct tegra_pcie_soc_data {
 	unsigned int msi_base_shift;
 	u32 pads_pll_ctl;
 	u32 tx_ref_sel;
+	u32 pads_refclk_cfg0;
+	u32 pads_refclk_cfg1;
 	bool has_pex_clkreq_en;
 	bool has_pex_bias_ctrl;
 	bool has_intr_prsnt_sense;
@@ -274,7 +269,6 @@ struct tegra_pcie {
 	struct list_head buses;
 	struct resource *cs;
 
-	struct resource all;
 	struct resource io;
 	struct resource pio;
 	struct resource mem;
@@ -623,30 +617,21 @@ static int tegra_pcie_setup(int nr, struct pci_sys_data *sys)
 	sys->mem_offset = pcie->offset.mem;
 	sys->io_offset = pcie->offset.io;
 
-	err = devm_request_resource(pcie->dev, &pcie->all, &pcie->io);
-	if (err < 0)
-		return err;
-
-	err = devm_request_resource(pcie->dev, &ioport_resource, &pcie->pio);
-	if (err < 0)
-		return err;
-
-	err = devm_request_resource(pcie->dev, &pcie->all, &pcie->mem);
+	err = devm_request_resource(pcie->dev, &iomem_resource, &pcie->io);
 	if (err < 0)
 		return err;
 
-	err = devm_request_resource(pcie->dev, &pcie->all, &pcie->prefetch);
-	if (err)
-		return err;
-
 	pci_add_resource_offset(&sys->resources, &pcie->pio, sys->io_offset);
 	pci_add_resource_offset(&sys->resources, &pcie->mem, sys->mem_offset);
 	pci_add_resource_offset(&sys->resources, &pcie->prefetch,
 				sys->mem_offset);
 	pci_add_resource(&sys->resources, &pcie->busn);
 
-	pci_ioremap_io(pcie->pio.start, pcie->io.start);
+	err = devm_request_pci_bus_resources(pcie->dev, &sys->resources);
+	if (err < 0)
+		return err;
 
+	pci_remap_iospace(&pcie->pio, pcie->io.start);
 	return 1;
 }
 
@@ -838,12 +823,6 @@ static int tegra_pcie_phy_enable(struct tegra_pcie *pcie)
 	value |= PADS_PLL_CTL_RST_B4SM;
 	pads_writel(pcie, value, soc->pads_pll_ctl);
 
-	/* Configure the reference clock driver */
-	value = PADS_REFCLK_CFG_VALUE | (PADS_REFCLK_CFG_VALUE << 16);
-	pads_writel(pcie, value, PADS_REFCLK_CFG0);
-	if (soc->num_ports > 2)
-		pads_writel(pcie, PADS_REFCLK_CFG_VALUE, PADS_REFCLK_CFG1);
-
 	/* wait for the PLL to lock */
 	err = tegra_pcie_pll_wait(pcie, 500);
 	if (err < 0) {
@@ -927,6 +906,7 @@ static int tegra_pcie_port_phy_power_off(struct tegra_pcie_port *port)
 
 static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie)
 {
+	const struct tegra_pcie_soc_data *soc = pcie->soc_data;
 	struct tegra_pcie_port *port;
 	int err;
 
@@ -952,6 +932,12 @@ static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie)
 		}
 	}
 
+	/* Configure the reference clock driver */
+	pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0);
+
+	if (soc->num_ports > 2)
+		pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1);
+
 	return 0;
 }
 
@@ -1822,12 +1808,6 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 	struct resource res;
 	int err;
 
-	memset(&pcie->all, 0, sizeof(pcie->all));
-	pcie->all.flags = IORESOURCE_MEM;
-	pcie->all.name = np->full_name;
-	pcie->all.start = ~0;
-	pcie->all.end = 0;
-
 	if (of_pci_range_parser_init(&parser, np)) {
 		dev_err(pcie->dev, "missing \"ranges\" property\n");
 		return -EINVAL;
@@ -1880,18 +1860,8 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 			}
 			break;
 		}
-
-		if (res.start <= pcie->all.start)
-			pcie->all.start = res.start;
-
-		if (res.end >= pcie->all.end)
-			pcie->all.end = res.end;
 	}
 
-	err = devm_request_resource(pcie->dev, &iomem_resource, &pcie->all);
-	if (err < 0)
-		return err;
-
 	err = of_pci_parse_bus_range(np, &pcie->busn);
 	if (err < 0) {
 		dev_err(pcie->dev, "failed to parse ranges property: %d\n",
@@ -2078,6 +2048,7 @@ static const struct tegra_pcie_soc_data tegra20_pcie_data = {
 	.msi_base_shift = 0,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA20,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_DIV10,
+	.pads_refclk_cfg0 = 0xfa5cfa5c,
 	.has_pex_clkreq_en = false,
 	.has_pex_bias_ctrl = false,
 	.has_intr_prsnt_sense = false,
@@ -2090,6 +2061,8 @@ static const struct tegra_pcie_soc_data tegra30_pcie_data = {
 	.msi_base_shift = 8,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
+	.pads_refclk_cfg0 = 0xfa5cfa5c,
+	.pads_refclk_cfg1 = 0xfa5cfa5c,
 	.has_pex_clkreq_en = true,
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
@@ -2102,6 +2075,7 @@ static const struct tegra_pcie_soc_data tegra124_pcie_data = {
 	.msi_base_shift = 8,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
+	.pads_refclk_cfg0 = 0x44ac44ac,
 	.has_pex_clkreq_en = true,
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
@@ -2115,7 +2089,6 @@ static const struct of_device_id tegra_pcie_of_match[] = {
 	{ .compatible = "nvidia,tegra20-pcie", .data = &tegra20_pcie_data },
 	{ },
 };
-MODULE_DEVICE_TABLE(of, tegra_pcie_of_match);
 
 static void *tegra_pcie_ports_seq_start(struct seq_file *s, loff_t *pos)
 {
@@ -2249,8 +2222,6 @@ static int tegra_pcie_probe(struct platform_device *pdev)
 	if (err < 0)
 		return err;
 
-	pcibios_min_mem = 0;
-
 	err = tegra_pcie_get_resources(pcie);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to request resources: %d\n", err);
@@ -2306,8 +2277,4 @@ static struct platform_driver tegra_pcie_driver = {
 	},
 	.probe = tegra_pcie_probe,
 };
-module_platform_driver(tegra_pcie_driver);
-
-MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>");
-MODULE_DESCRIPTION("NVIDIA Tegra PCIe driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(tegra_pcie_driver);
diff --git a/drivers/pci/host/pci-thunder-ecam.c b/drivers/pci/host/pci-thunder-ecam.c
index 540d030613eb..d50a3dc2d8db 100644
--- a/drivers/pci/host/pci-thunder-ecam.c
+++ b/drivers/pci/host/pci-thunder-ecam.c
@@ -7,14 +7,13 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/of_pci.h>
 #include <linux/of.h>
+#include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
 
-#include "../ecam.h"
-
 static void set_val(u32 v, int where, int size, u32 *val)
 {
 	int shift = (where & 3) * 8;
@@ -360,7 +359,6 @@ static const struct of_device_id thunder_ecam_of_match[] = {
 	{ .compatible = "cavium,pci-host-thunder-ecam" },
 	{ },
 };
-MODULE_DEVICE_TABLE(of, thunder_ecam_of_match);
 
 static int thunder_ecam_probe(struct platform_device *pdev)
 {
@@ -374,7 +372,4 @@ static struct platform_driver thunder_ecam_driver = {
 	},
 	.probe = thunder_ecam_probe,
 };
-module_platform_driver(thunder_ecam_driver);
-
-MODULE_DESCRIPTION("Thunder ECAM PCI host driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(thunder_ecam_driver);
diff --git a/drivers/pci/host/pci-thunder-pem.c b/drivers/pci/host/pci-thunder-pem.c
index 9b8ab94f3c8c..6abaf80ffb39 100644
--- a/drivers/pci/host/pci-thunder-pem.c
+++ b/drivers/pci/host/pci-thunder-pem.c
@@ -15,13 +15,12 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
+#include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
 
-#include "../ecam.h"
-
 #define PEM_CFG_WR 0x28
 #define PEM_CFG_RD 0x30
 
@@ -285,8 +284,9 @@ static int thunder_pem_config_write(struct pci_bus *bus, unsigned int devfn,
 	return pci_generic_config_write(bus, devfn, where, size, val);
 }
 
-static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg)
+static int thunder_pem_init(struct pci_config_window *cfg)
 {
+	struct device *dev = cfg->parent;
 	resource_size_t bar4_start;
 	struct resource *res_pem;
 	struct thunder_pem_pci *pem_pci;
@@ -346,7 +346,6 @@ static const struct of_device_id thunder_pem_of_match[] = {
 	{ .compatible = "cavium,pci-host-thunder-pem" },
 	{ },
 };
-MODULE_DEVICE_TABLE(of, thunder_pem_of_match);
 
 static int thunder_pem_probe(struct platform_device *pdev)
 {
@@ -360,7 +359,4 @@ static struct platform_driver thunder_pem_driver = {
 	},
 	.probe = thunder_pem_probe,
 };
-module_platform_driver(thunder_pem_driver);
-
-MODULE_DESCRIPTION("Thunder PEM PCIe host driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(thunder_pem_driver);
diff --git a/drivers/pci/host/pci-versatile.c b/drivers/pci/host/pci-versatile.c
index f843a72dc51c..f234405770ab 100644
--- a/drivers/pci/host/pci-versatile.c
+++ b/drivers/pci/host/pci-versatile.c
@@ -80,21 +80,21 @@ static int versatile_pci_parse_request_of_pci_ranges(struct device *dev,
 	if (err)
 		return err;
 
+	err = devm_request_pci_bus_resources(dev, res);
+	if (err)
+		goto out_release_res;
+
 	resource_list_for_each_entry(win, res) {
-		struct resource *parent, *res = win->res;
+		struct resource *res = win->res;
 
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
-			parent = &ioport_resource;
 			err = pci_remap_iospace(res, iobase);
-			if (err) {
+			if (err)
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 err, res);
-				continue;
-			}
 			break;
 		case IORESOURCE_MEM:
-			parent = &iomem_resource;
 			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
 
 			writel(res->start >> 28, PCI_IMAP(mem));
@@ -102,23 +102,14 @@ static int versatile_pci_parse_request_of_pci_ranges(struct device *dev,
 			mem++;
 
 			break;
-		case IORESOURCE_BUS:
-		default:
-			continue;
 		}
-
-		err = devm_request_resource(dev, parent, res);
-		if (err)
-			goto out_release_res;
 	}
 
-	if (!res_valid) {
-		dev_err(dev, "non-prefetchable memory resource required\n");
-		err = -EINVAL;
-		goto out_release_res;
-	}
+	if (res_valid)
+		return 0;
 
-	return 0;
+	dev_err(dev, "non-prefetchable memory resource required\n");
+	err = -EINVAL;
 
 out_release_res:
 	pci_free_resource_list(res);
diff --git a/drivers/pci/host/pci-xgene.c b/drivers/pci/host/pci-xgene.c
index ae00ce22d5a6..a81273c23341 100644
--- a/drivers/pci/host/pci-xgene.c
+++ b/drivers/pci/host/pci-xgene.c
@@ -21,7 +21,7 @@
 #include <linux/io.h>
 #include <linux/jiffies.h>
 #include <linux/memblock.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -540,14 +540,20 @@ static int xgene_pcie_probe_bridge(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = devm_request_pci_bus_resources(&pdev->dev, &res);
+	if (ret)
+		goto error;
+
 	ret = xgene_pcie_setup(port, &res, iobase);
 	if (ret)
-		return ret;
+		goto error;
 
 	bus = pci_create_root_bus(&pdev->dev, 0,
 					&xgene_pcie_ops, port, &res);
-	if (!bus)
-		return -ENOMEM;
+	if (!bus) {
+		ret = -ENOMEM;
+		goto error;
+	}
 
 	pci_scan_child_bus(bus);
 	pci_assign_unassigned_bus_resources(bus);
@@ -555,6 +561,10 @@ static int xgene_pcie_probe_bridge(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, port);
 	return 0;
+
+error:
+	pci_free_resource_list(&res);
+	return ret;
 }
 
 static const struct of_device_id xgene_pcie_match_table[] = {
@@ -569,8 +579,4 @@ static struct platform_driver xgene_pcie_driver = {
 	},
 	.probe = xgene_pcie_probe_bridge,
 };
-module_platform_driver(xgene_pcie_driver);
-
-MODULE_AUTHOR("Tanmay Inamdar <tinamdar@apm.com>");
-MODULE_DESCRIPTION("APM X-Gene PCIe driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(xgene_pcie_driver);
diff --git a/drivers/pci/host/pcie-altera.c b/drivers/pci/host/pcie-altera.c
index dbac6fb3f0bd..2b7837650db8 100644
--- a/drivers/pci/host/pcie-altera.c
+++ b/drivers/pci/host/pcie-altera.c
@@ -61,6 +61,8 @@
 #define TLP_LOOP			500
 #define RP_DEVFN			0
 
+#define LINK_UP_TIMEOUT			5000
+
 #define INTX_NUM			4
 
 #define DWORD_MASK			3
@@ -81,9 +83,30 @@ struct tlp_rp_regpair_t {
 	u32 reg1;
 };
 
+static inline void cra_writel(struct altera_pcie *pcie, const u32 value,
+			      const u32 reg)
+{
+	writel_relaxed(value, pcie->cra_base + reg);
+}
+
+static inline u32 cra_readl(struct altera_pcie *pcie, const u32 reg)
+{
+	return readl_relaxed(pcie->cra_base + reg);
+}
+
+static bool altera_pcie_link_is_up(struct altera_pcie *pcie)
+{
+	return !!((cra_readl(pcie, RP_LTSSM) & RP_LTSSM_MASK) == LTSSM_L0);
+}
+
 static void altera_pcie_retrain(struct pci_dev *dev)
 {
 	u16 linkcap, linkstat;
+	struct altera_pcie *pcie = dev->bus->sysdata;
+	int timeout =  0;
+
+	if (!altera_pcie_link_is_up(pcie))
+		return;
 
 	/*
 	 * Set the retrain bit if the PCIe rootport support > 2.5GB/s, but
@@ -95,9 +118,16 @@ static void altera_pcie_retrain(struct pci_dev *dev)
 		return;
 
 	pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &linkstat);
-	if ((linkstat & PCI_EXP_LNKSTA_CLS) == PCI_EXP_LNKSTA_CLS_2_5GB)
+	if ((linkstat & PCI_EXP_LNKSTA_CLS) == PCI_EXP_LNKSTA_CLS_2_5GB) {
 		pcie_capability_set_word(dev, PCI_EXP_LNKCTL,
 					 PCI_EXP_LNKCTL_RL);
+		while (!altera_pcie_link_is_up(pcie)) {
+			timeout++;
+			if (timeout > LINK_UP_TIMEOUT)
+				break;
+			udelay(5);
+		}
+	}
 }
 DECLARE_PCI_FIXUP_EARLY(0x1172, PCI_ANY_ID, altera_pcie_retrain);
 
@@ -120,17 +150,6 @@ static bool altera_pcie_hide_rc_bar(struct pci_bus *bus, unsigned int  devfn,
 	return false;
 }
 
-static inline void cra_writel(struct altera_pcie *pcie, const u32 value,
-			      const u32 reg)
-{
-	writel_relaxed(value, pcie->cra_base + reg);
-}
-
-static inline u32 cra_readl(struct altera_pcie *pcie, const u32 reg)
-{
-	return readl_relaxed(pcie->cra_base + reg);
-}
-
 static void tlp_write_tx(struct altera_pcie *pcie,
 			 struct tlp_rp_regpair_t *tlp_rp_regdata)
 {
@@ -139,11 +158,6 @@ static void tlp_write_tx(struct altera_pcie *pcie,
 	cra_writel(pcie, tlp_rp_regdata->ctrl, RP_TX_CNTRL);
 }
 
-static bool altera_pcie_link_is_up(struct altera_pcie *pcie)
-{
-	return !!((cra_readl(pcie, RP_LTSSM) & RP_LTSSM_MASK) == LTSSM_L0);
-}
-
 static bool altera_pcie_valid_config(struct altera_pcie *pcie,
 				     struct pci_bus *bus, int dev)
 {
@@ -415,11 +429,6 @@ static void altera_pcie_isr(struct irq_desc *desc)
 	chained_irq_exit(chip, desc);
 }
 
-static void altera_pcie_release_of_pci_ranges(struct altera_pcie *pcie)
-{
-	pci_free_resource_list(&pcie->resources);
-}
-
 static int altera_pcie_parse_request_of_pci_ranges(struct altera_pcie *pcie)
 {
 	int err, res_valid = 0;
@@ -432,33 +441,25 @@ static int altera_pcie_parse_request_of_pci_ranges(struct altera_pcie *pcie)
 	if (err)
 		return err;
 
+	err = devm_request_pci_bus_resources(dev, &pcie->resources);
+	if (err)
+		goto out_release_res;
+
 	resource_list_for_each_entry(win, &pcie->resources) {
-		struct resource *parent, *res = win->res;
+		struct resource *res = win->res;
 
-		switch (resource_type(res)) {
-		case IORESOURCE_MEM:
-			parent = &iomem_resource;
+		if (resource_type(res) == IORESOURCE_MEM)
 			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
-			break;
-		default:
-			continue;
-		}
-
-		err = devm_request_resource(dev, parent, res);
-		if (err)
-			goto out_release_res;
 	}
 
-	if (!res_valid) {
-		dev_err(dev, "non-prefetchable memory resource required\n");
-		err = -EINVAL;
-		goto out_release_res;
-	}
+	if (res_valid)
+		return 0;
 
-	return 0;
+	dev_err(dev, "non-prefetchable memory resource required\n");
+	err = -EINVAL;
 
 out_release_res:
-	altera_pcie_release_of_pci_ranges(pcie);
+	pci_free_resource_list(&pcie->resources);
 	return err;
 }
 
diff --git a/drivers/pci/host/pcie-armada8k.c b/drivers/pci/host/pcie-armada8k.c
index 55723567b5d4..0f4f570068e3 100644
--- a/drivers/pci/host/pcie-armada8k.c
+++ b/drivers/pci/host/pcie-armada8k.c
@@ -5,6 +5,9 @@
  *
  * Copyright (C) 2016 Marvell Technology Group Ltd.
  *
+ * Author: Yehuda Yitshak <yehuday@marvell.com>
+ * Author: Shadi Ammouri <shadi@marvell.com>
+ *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
@@ -14,7 +17,7 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/pci.h>
 #include <linux/phy/phy.h>
@@ -244,7 +247,6 @@ static const struct of_device_id armada8k_pcie_of_match[] = {
 	{ .compatible = "marvell,armada8k-pcie", },
 	{},
 };
-MODULE_DEVICE_TABLE(of, armada8k_pcie_of_match);
 
 static struct platform_driver armada8k_pcie_driver = {
 	.probe		= armada8k_pcie_probe,
@@ -253,10 +255,4 @@ static struct platform_driver armada8k_pcie_driver = {
 		.of_match_table = of_match_ptr(armada8k_pcie_of_match),
 	},
 };
-
-module_platform_driver(armada8k_pcie_driver);
-
-MODULE_DESCRIPTION("Armada 8k PCIe host controller driver");
-MODULE_AUTHOR("Yehuda Yitshak <yehuday@marvell.com>");
-MODULE_AUTHOR("Shadi Ammouri <shadi@marvell.com>");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(armada8k_pcie_driver);
diff --git a/drivers/pci/host/pcie-artpec6.c b/drivers/pci/host/pcie-artpec6.c
new file mode 100644
index 000000000000..16ba70b7ec65
--- /dev/null
+++ b/drivers/pci/host/pcie-artpec6.c
@@ -0,0 +1,280 @@
+/*
+ * PCIe host controller driver for Axis ARTPEC-6 SoC
+ *
+ * Author: Niklas Cassel <niklas.cassel@axis.com>
+ *
+ * Based on work done by Phil Edworthy <phil@edworthys.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/resource.h>
+#include <linux/signal.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+
+#include "pcie-designware.h"
+
+#define to_artpec6_pcie(x)	container_of(x, struct artpec6_pcie, pp)
+
+struct artpec6_pcie {
+	struct pcie_port	pp;
+	struct regmap		*regmap;
+	void __iomem		*phy_base;
+};
+
+/* PCIe Port Logic registers (memory-mapped) */
+#define PL_OFFSET			0x700
+#define PCIE_PHY_DEBUG_R0		(PL_OFFSET + 0x28)
+#define PCIE_PHY_DEBUG_R1		(PL_OFFSET + 0x2c)
+
+#define MISC_CONTROL_1_OFF		(PL_OFFSET + 0x1bc)
+#define  DBI_RO_WR_EN			1
+
+/* ARTPEC-6 specific registers */
+#define PCIECFG				0x18
+#define  PCIECFG_DBG_OEN		(1 << 24)
+#define  PCIECFG_CORE_RESET_REQ		(1 << 21)
+#define  PCIECFG_LTSSM_ENABLE		(1 << 20)
+#define  PCIECFG_CLKREQ_B		(1 << 11)
+#define  PCIECFG_REFCLK_ENABLE		(1 << 10)
+#define  PCIECFG_PLL_ENABLE		(1 << 9)
+#define  PCIECFG_PCLK_ENABLE		(1 << 8)
+#define  PCIECFG_RISRCREN		(1 << 4)
+#define  PCIECFG_MODE_TX_DRV_EN		(1 << 3)
+#define  PCIECFG_CISRREN		(1 << 2)
+#define  PCIECFG_MACRO_ENABLE		(1 << 0)
+
+#define NOCCFG				0x40
+#define NOCCFG_ENABLE_CLK_PCIE		(1 << 4)
+#define NOCCFG_POWER_PCIE_IDLEACK	(1 << 3)
+#define NOCCFG_POWER_PCIE_IDLE		(1 << 2)
+#define NOCCFG_POWER_PCIE_IDLEREQ	(1 << 1)
+
+#define PHY_STATUS			0x118
+#define PHY_COSPLLLOCK			(1 << 0)
+
+#define ARTPEC6_CPU_TO_BUS_ADDR		0x0fffffff
+
+static int artpec6_pcie_establish_link(struct pcie_port *pp)
+{
+	struct artpec6_pcie *artpec6_pcie = to_artpec6_pcie(pp);
+	u32 val;
+	unsigned int retries;
+
+	/* Hold DW core in reset */
+	regmap_read(artpec6_pcie->regmap, PCIECFG, &val);
+	val |= PCIECFG_CORE_RESET_REQ;
+	regmap_write(artpec6_pcie->regmap, PCIECFG, val);
+
+	regmap_read(artpec6_pcie->regmap, PCIECFG, &val);
+	val |=  PCIECFG_RISRCREN |	/* Receiver term. 50 Ohm */
+		PCIECFG_MODE_TX_DRV_EN |
+		PCIECFG_CISRREN |	/* Reference clock term. 100 Ohm */
+		PCIECFG_MACRO_ENABLE;
+	val |= PCIECFG_REFCLK_ENABLE;
+	val &= ~PCIECFG_DBG_OEN;
+	val &= ~PCIECFG_CLKREQ_B;
+	regmap_write(artpec6_pcie->regmap, PCIECFG, val);
+	usleep_range(5000, 6000);
+
+	regmap_read(artpec6_pcie->regmap, NOCCFG, &val);
+	val |= NOCCFG_ENABLE_CLK_PCIE;
+	regmap_write(artpec6_pcie->regmap, NOCCFG, val);
+	usleep_range(20, 30);
+
+	regmap_read(artpec6_pcie->regmap, PCIECFG, &val);
+	val |= PCIECFG_PCLK_ENABLE | PCIECFG_PLL_ENABLE;
+	regmap_write(artpec6_pcie->regmap, PCIECFG, val);
+	usleep_range(6000, 7000);
+
+	regmap_read(artpec6_pcie->regmap, NOCCFG, &val);
+	val &= ~NOCCFG_POWER_PCIE_IDLEREQ;
+	regmap_write(artpec6_pcie->regmap, NOCCFG, val);
+
+	retries = 50;
+	do {
+		usleep_range(1000, 2000);
+		regmap_read(artpec6_pcie->regmap, NOCCFG, &val);
+		retries--;
+	} while (retries &&
+		(val & (NOCCFG_POWER_PCIE_IDLEACK | NOCCFG_POWER_PCIE_IDLE)));
+
+	retries = 50;
+	do {
+		usleep_range(1000, 2000);
+		val = readl(artpec6_pcie->phy_base + PHY_STATUS);
+		retries--;
+	} while (retries && !(val & PHY_COSPLLLOCK));
+
+	/* Take DW core out of reset */
+	regmap_read(artpec6_pcie->regmap, PCIECFG, &val);
+	val &= ~PCIECFG_CORE_RESET_REQ;
+	regmap_write(artpec6_pcie->regmap, PCIECFG, val);
+	usleep_range(100, 200);
+
+	/*
+	 * Enable writing to config regs. This is required as the Synopsys
+	 * driver changes the class code. That register needs DBI write enable.
+	 */
+	writel(DBI_RO_WR_EN, pp->dbi_base + MISC_CONTROL_1_OFF);
+
+	pp->io_base &= ARTPEC6_CPU_TO_BUS_ADDR;
+	pp->mem_base &= ARTPEC6_CPU_TO_BUS_ADDR;
+	pp->cfg0_base &= ARTPEC6_CPU_TO_BUS_ADDR;
+	pp->cfg1_base &= ARTPEC6_CPU_TO_BUS_ADDR;
+
+	/* setup root complex */
+	dw_pcie_setup_rc(pp);
+
+	/* assert LTSSM enable */
+	regmap_read(artpec6_pcie->regmap, PCIECFG, &val);
+	val |= PCIECFG_LTSSM_ENABLE;
+	regmap_write(artpec6_pcie->regmap, PCIECFG, val);
+
+	/* check if the link is up or not */
+	if (!dw_pcie_wait_for_link(pp))
+		return 0;
+
+	dev_dbg(pp->dev, "DEBUG_R0: 0x%08x, DEBUG_R1: 0x%08x\n",
+		readl(pp->dbi_base + PCIE_PHY_DEBUG_R0),
+		readl(pp->dbi_base + PCIE_PHY_DEBUG_R1));
+
+	return -ETIMEDOUT;
+}
+
+static void artpec6_pcie_enable_interrupts(struct pcie_port *pp)
+{
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		dw_pcie_msi_init(pp);
+}
+
+static void artpec6_pcie_host_init(struct pcie_port *pp)
+{
+	artpec6_pcie_establish_link(pp);
+	artpec6_pcie_enable_interrupts(pp);
+}
+
+static int artpec6_pcie_link_up(struct pcie_port *pp)
+{
+	u32 rc;
+
+	/*
+	 * Get status from Synopsys IP
+	 * link is debug bit 36, debug register 1 starts at bit 32
+	 */
+	rc = readl(pp->dbi_base + PCIE_PHY_DEBUG_R1) & (0x1 << (36 - 32));
+	if (rc)
+		return 1;
+
+	return 0;
+}
+
+static struct pcie_host_ops artpec6_pcie_host_ops = {
+	.link_up = artpec6_pcie_link_up,
+	.host_init = artpec6_pcie_host_init,
+};
+
+static irqreturn_t artpec6_pcie_msi_handler(int irq, void *arg)
+{
+	struct pcie_port *pp = arg;
+
+	return dw_handle_msi_irq(pp);
+}
+
+static int __init artpec6_add_pcie_port(struct pcie_port *pp,
+					struct platform_device *pdev)
+{
+	int ret;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		pp->msi_irq = platform_get_irq_byname(pdev, "msi");
+		if (pp->msi_irq <= 0) {
+			dev_err(&pdev->dev, "failed to get MSI irq\n");
+			return -ENODEV;
+		}
+
+		ret = devm_request_irq(&pdev->dev, pp->msi_irq,
+				       artpec6_pcie_msi_handler,
+				       IRQF_SHARED | IRQF_NO_THREAD,
+				       "artpec6-pcie-msi", pp);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to request MSI irq\n");
+			return ret;
+		}
+	}
+
+	pp->root_bus_nr = -1;
+	pp->ops = &artpec6_pcie_host_ops;
+
+	ret = dw_pcie_host_init(pp);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to initialize host\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int artpec6_pcie_probe(struct platform_device *pdev)
+{
+	struct artpec6_pcie *artpec6_pcie;
+	struct pcie_port *pp;
+	struct resource *dbi_base;
+	struct resource *phy_base;
+	int ret;
+
+	artpec6_pcie = devm_kzalloc(&pdev->dev, sizeof(*artpec6_pcie),
+				    GFP_KERNEL);
+	if (!artpec6_pcie)
+		return -ENOMEM;
+
+	pp = &artpec6_pcie->pp;
+	pp->dev = &pdev->dev;
+
+	dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi");
+	pp->dbi_base = devm_ioremap_resource(&pdev->dev, dbi_base);
+	if (IS_ERR(pp->dbi_base))
+		return PTR_ERR(pp->dbi_base);
+
+	phy_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "phy");
+	artpec6_pcie->phy_base = devm_ioremap_resource(&pdev->dev, phy_base);
+	if (IS_ERR(artpec6_pcie->phy_base))
+		return PTR_ERR(artpec6_pcie->phy_base);
+
+	artpec6_pcie->regmap =
+		syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+						"axis,syscon-pcie");
+	if (IS_ERR(artpec6_pcie->regmap))
+		return PTR_ERR(artpec6_pcie->regmap);
+
+	ret = artpec6_add_pcie_port(pp, pdev);
+	if (ret < 0)
+		return ret;
+
+	platform_set_drvdata(pdev, artpec6_pcie);
+	return 0;
+}
+
+static const struct of_device_id artpec6_pcie_of_match[] = {
+	{ .compatible = "axis,artpec6-pcie", },
+	{},
+};
+
+static struct platform_driver artpec6_pcie_driver = {
+	.probe = artpec6_pcie_probe,
+	.driver = {
+		.name	= "artpec6-pcie",
+		.of_match_table = artpec6_pcie_of_match,
+	},
+};
+builtin_platform_driver(artpec6_pcie_driver);
diff --git a/drivers/pci/host/pcie-designware-plat.c b/drivers/pci/host/pcie-designware-plat.c
index b3500994d08a..c8079dc81c10 100644
--- a/drivers/pci/host/pcie-designware-plat.c
+++ b/drivers/pci/host/pcie-designware-plat.c
@@ -14,7 +14,7 @@
 #include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of_gpio.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
@@ -121,7 +121,6 @@ static const struct of_device_id dw_plat_pcie_of_match[] = {
 	{ .compatible = "snps,dw-pcie", },
 	{},
 };
-MODULE_DEVICE_TABLE(of, dw_plat_pcie_of_match);
 
 static struct platform_driver dw_plat_pcie_driver = {
 	.driver = {
@@ -130,9 +129,4 @@ static struct platform_driver dw_plat_pcie_driver = {
 	},
 	.probe = dw_plat_pcie_probe,
 };
-
-module_platform_driver(dw_plat_pcie_driver);
-
-MODULE_AUTHOR("Joao Pinto <Joao.Pinto@synopsys.com>");
-MODULE_DESCRIPTION("Synopsys PCIe host controller glue platform driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(dw_plat_pcie_driver);
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index aafd766546f3..12afce19890b 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -452,6 +452,10 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	if (ret)
 		return ret;
 
+	ret = devm_request_pci_bus_resources(&pdev->dev, &res);
+	if (ret)
+		goto error;
+
 	/* Get the I/O and memory ranges from DT */
 	resource_list_for_each_entry(win, &res) {
 		switch (resource_type(win->res)) {
@@ -461,11 +465,9 @@ int dw_pcie_host_init(struct pcie_port *pp)
 			pp->io_size = resource_size(pp->io);
 			pp->io_bus_addr = pp->io->start - win->offset;
 			ret = pci_remap_iospace(pp->io, pp->io_base);
-			if (ret) {
+			if (ret)
 				dev_warn(pp->dev, "error %d: failed to map resource %pR\n",
 					 ret, pp->io);
-				continue;
-			}
 			break;
 		case IORESOURCE_MEM:
 			pp->mem = win->res;
@@ -483,8 +485,6 @@ int dw_pcie_host_init(struct pcie_port *pp)
 		case IORESOURCE_BUS:
 			pp->busn = win->res;
 			break;
-		default:
-			continue;
 		}
 	}
 
@@ -493,7 +493,8 @@ int dw_pcie_host_init(struct pcie_port *pp)
 					resource_size(pp->cfg));
 		if (!pp->dbi_base) {
 			dev_err(pp->dev, "error with ioremap\n");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto error;
 		}
 	}
 
@@ -504,7 +505,8 @@ int dw_pcie_host_init(struct pcie_port *pp)
 						pp->cfg0_size);
 		if (!pp->va_cfg0_base) {
 			dev_err(pp->dev, "error with ioremap in function\n");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto error;
 		}
 	}
 
@@ -513,7 +515,8 @@ int dw_pcie_host_init(struct pcie_port *pp)
 						pp->cfg1_size);
 		if (!pp->va_cfg1_base) {
 			dev_err(pp->dev, "error with ioremap\n");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto error;
 		}
 	}
 
@@ -528,7 +531,8 @@ int dw_pcie_host_init(struct pcie_port *pp)
 						&dw_pcie_msi_chip);
 			if (!pp->irq_domain) {
 				dev_err(pp->dev, "irq domain init failed\n");
-				return -ENXIO;
+				ret = -ENXIO;
+				goto error;
 			}
 
 			for (i = 0; i < MAX_MSI_IRQS; i++)
@@ -536,7 +540,7 @@ int dw_pcie_host_init(struct pcie_port *pp)
 		} else {
 			ret = pp->ops->msi_host_init(pp, &dw_pcie_msi_chip);
 			if (ret < 0)
-				return ret;
+				goto error;
 		}
 	}
 
@@ -552,8 +556,10 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	} else
 		bus = pci_scan_root_bus(pp->dev, pp->root_bus_nr, &dw_pcie_ops,
 					pp, &res);
-	if (!bus)
-		return -ENOMEM;
+	if (!bus) {
+		ret = -ENOMEM;
+		goto error;
+	}
 
 	if (pp->ops->scan_bus)
 		pp->ops->scan_bus(pp);
@@ -571,6 +577,10 @@ int dw_pcie_host_init(struct pcie_port *pp)
 
 	pci_bus_add_devices(bus);
 	return 0;
+
+error:
+	pci_free_resource_list(&res);
+	return ret;
 }
 
 static int dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
diff --git a/drivers/pci/host/pcie-hisi.c b/drivers/pci/host/pcie-hisi.c
index 3e98d4edae2d..7ee9dfcc45fb 100644
--- a/drivers/pci/host/pcie-hisi.c
+++ b/drivers/pci/host/pcie-hisi.c
@@ -12,7 +12,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/interrupt.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/mfd/syscon.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
@@ -235,9 +235,6 @@ static const struct of_device_id hisi_pcie_of_match[] = {
 	{},
 };
 
-
-MODULE_DEVICE_TABLE(of, hisi_pcie_of_match);
-
 static struct platform_driver hisi_pcie_driver = {
 	.probe  = hisi_pcie_probe,
 	.driver = {
@@ -245,10 +242,4 @@ static struct platform_driver hisi_pcie_driver = {
 		   .of_match_table = hisi_pcie_of_match,
 	},
 };
-
-module_platform_driver(hisi_pcie_driver);
-
-MODULE_AUTHOR("Zhou Wang <wangzhou1@hisilicon.com>");
-MODULE_AUTHOR("Dacai Zhu <zhudacai@hisilicon.com>");
-MODULE_AUTHOR("Gabriele Paoloni <gabriele.paoloni@huawei.com>");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(hisi_pcie_driver);
diff --git a/drivers/pci/host/pcie-iproc.c b/drivers/pci/host/pcie-iproc.c
index a576aeeb22da..e167b2f0098d 100644
--- a/drivers/pci/host/pcie-iproc.c
+++ b/drivers/pci/host/pcie-iproc.c
@@ -462,6 +462,10 @@ int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res)
 	if (!pcie || !pcie->dev || !pcie->base)
 		return -EINVAL;
 
+	ret = devm_request_pci_bus_resources(pcie->dev, res);
+	if (ret)
+		return ret;
+
 	ret = phy_init(pcie->phy);
 	if (ret) {
 		dev_err(pcie->dev, "unable to initialize PCIe PHY\n");
diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c
index 35092188039b..65db7a221509 100644
--- a/drivers/pci/host/pcie-rcar.c
+++ b/drivers/pci/host/pcie-rcar.c
@@ -7,6 +7,8 @@
  *  arch/sh/drivers/pci/ops-sh7786.c
  *  Copyright (C) 2009 - 2011  Paul Mundt
  *
+ * Author: Phil Edworthy <phil.edworthy@renesas.com>
+ *
  * This file is licensed under the terms of the GNU General Public
  * License version 2.  This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
@@ -18,7 +20,7 @@
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/msi.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -936,12 +938,6 @@ static const struct of_device_id rcar_pcie_of_match[] = {
 	{ .compatible = "renesas,pcie-r8a7795", .data = rcar_pcie_hw_init },
 	{},
 };
-MODULE_DEVICE_TABLE(of, rcar_pcie_of_match);
-
-static void rcar_pcie_release_of_pci_ranges(struct rcar_pcie *pci)
-{
-	pci_free_resource_list(&pci->resources);
-}
 
 static int rcar_pcie_parse_request_of_pci_ranges(struct rcar_pcie *pci)
 {
@@ -955,37 +951,25 @@ static int rcar_pcie_parse_request_of_pci_ranges(struct rcar_pcie *pci)
 	if (err)
 		return err;
 
+	err = devm_request_pci_bus_resources(dev, &pci->resources);
+	if (err)
+		goto out_release_res;
+
 	resource_list_for_each_entry(win, &pci->resources) {
-		struct resource *parent, *res = win->res;
+		struct resource *res = win->res;
 
-		switch (resource_type(res)) {
-		case IORESOURCE_IO:
-			parent = &ioport_resource;
+		if (resource_type(res) == IORESOURCE_IO) {
 			err = pci_remap_iospace(res, iobase);
-			if (err) {
+			if (err)
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 err, res);
-				continue;
-			}
-			break;
-		case IORESOURCE_MEM:
-			parent = &iomem_resource;
-			break;
-
-		case IORESOURCE_BUS:
-		default:
-			continue;
 		}
-
-		err = devm_request_resource(dev, parent, res);
-		if (err)
-			goto out_release_res;
 	}
 
 	return 0;
 
 out_release_res:
-	rcar_pcie_release_of_pci_ranges(pci);
+	pci_free_resource_list(&pci->resources);
 	return err;
 }
 
@@ -1073,8 +1057,4 @@ static struct platform_driver rcar_pcie_driver = {
 	},
 	.probe = rcar_pcie_probe,
 };
-module_platform_driver(rcar_pcie_driver);
-
-MODULE_AUTHOR("Phil Edworthy <phil.edworthy@renesas.com>");
-MODULE_DESCRIPTION("Renesas R-Car PCIe driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(rcar_pcie_driver);
diff --git a/drivers/pci/host/pcie-xilinx-nwl.c b/drivers/pci/host/pcie-xilinx-nwl.c
index 3479d30e2be8..0b597d9190b4 100644
--- a/drivers/pci/host/pcie-xilinx-nwl.c
+++ b/drivers/pci/host/pcie-xilinx-nwl.c
@@ -825,27 +825,33 @@ static int nwl_pcie_probe(struct platform_device *pdev)
 
 	err = of_pci_get_host_bridge_resources(node, 0, 0xff, &res, &iobase);
 	if (err) {
-		pr_err("Getting bridge resources failed\n");
+		dev_err(pcie->dev, "Getting bridge resources failed\n");
 		return err;
 	}
 
+	err = devm_request_pci_bus_resources(pcie->dev, &res);
+	if (err)
+		goto error;
+
 	err = nwl_pcie_init_irq_domain(pcie);
 	if (err) {
 		dev_err(pcie->dev, "Failed creating IRQ Domain\n");
-		return err;
+		goto error;
 	}
 
 	bus = pci_create_root_bus(&pdev->dev, pcie->root_busno,
 				  &nwl_pcie_ops, pcie, &res);
-	if (!bus)
-		return -ENOMEM;
+	if (!bus) {
+		err = -ENOMEM;
+		goto error;
+	}
 
 	if (IS_ENABLED(CONFIG_PCI_MSI)) {
 		err = nwl_pcie_enable_msi(pcie, bus);
 		if (err < 0) {
 			dev_err(&pdev->dev,
 				"failed to enable MSI support: %d\n", err);
-			return err;
+			goto error;
 		}
 	}
 	pci_scan_child_bus(bus);
@@ -855,6 +861,10 @@ static int nwl_pcie_probe(struct platform_device *pdev)
 	pci_bus_add_devices(bus);
 	platform_set_drvdata(pdev, pcie);
 	return 0;
+
+error:
+	pci_free_resource_list(&res);
+	return err;
 }
 
 static int nwl_pcie_remove(struct platform_device *pdev)
diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c
index 65f0fe0c2eaf..a30e01639557 100644
--- a/drivers/pci/host/pcie-xilinx.c
+++ b/drivers/pci/host/pcie-xilinx.c
@@ -550,7 +550,7 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port)
 	pcie_intc_node = of_get_next_child(node, NULL);
 	if (!pcie_intc_node) {
 		dev_err(dev, "No PCIe Intc node found\n");
-		return PTR_ERR(pcie_intc_node);
+		return -ENODEV;
 	}
 
 	port->irq_domain = irq_domain_add_linear(pcie_intc_node, 4,
@@ -558,7 +558,7 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port)
 						 port);
 	if (!port->irq_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
-		return PTR_ERR(port->irq_domain);
+		return -ENODEV;
 	}
 
 	/* Setup MSI */
@@ -569,7 +569,7 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port)
 							 &xilinx_pcie_msi_chip);
 		if (!port->irq_domain) {
 			dev_err(dev, "Failed to get a MSI IRQ domain\n");
-			return PTR_ERR(port->irq_domain);
+			return -ENODEV;
 		}
 
 		xilinx_pcie_enable_msi(port);
@@ -660,7 +660,6 @@ static int xilinx_pcie_probe(struct platform_device *pdev)
 	struct xilinx_pcie_port *port;
 	struct device *dev = &pdev->dev;
 	struct pci_bus *bus;
-
 	int err;
 	resource_size_t iobase = 0;
 	LIST_HEAD(res);
@@ -694,10 +693,17 @@ static int xilinx_pcie_probe(struct platform_device *pdev)
 		dev_err(dev, "Getting bridge resources failed\n");
 		return err;
 	}
+
+	err = devm_request_pci_bus_resources(dev, &res);
+	if (err)
+		goto error;
+
 	bus = pci_create_root_bus(&pdev->dev, 0,
 				  &xilinx_pcie_ops, port, &res);
-	if (!bus)
-		return -ENOMEM;
+	if (!bus) {
+		err = -ENOMEM;
+		goto error;
+	}
 
 #ifdef CONFIG_PCI_MSI
 	xilinx_pcie_msi_chip.dev = port->dev;
@@ -712,6 +718,10 @@ static int xilinx_pcie_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, port);
 
 	return 0;
+
+error:
+	pci_free_resource_list(&res);
+	return err;
 }
 
 /**
diff --git a/drivers/pci/hotplug/Kconfig b/drivers/pci/hotplug/Kconfig
index df8caec59789..aadce45a9b4a 100644
--- a/drivers/pci/hotplug/Kconfig
+++ b/drivers/pci/hotplug/Kconfig
@@ -113,6 +113,19 @@ config HOTPLUG_PCI_SHPC
 
 	  When in doubt, say N.
 
+config HOTPLUG_PCI_POWERNV
+	tristate "PowerPC PowerNV PCI Hotplug driver"
+	depends on PPC_POWERNV && EEH
+	select OF_DYNAMIC
+	help
+	  Say Y here if you run PowerPC PowerNV platform that supports
+	  PCI Hotplug
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called pnv-php.
+
+	  When in doubt, say N.
+
 config HOTPLUG_PCI_RPA
 	tristate "RPA PCI Hotplug driver"
 	depends on PPC_PSERIES && EEH
diff --git a/drivers/pci/hotplug/Makefile b/drivers/pci/hotplug/Makefile
index b616e7588ff4..e33cdda45a4d 100644
--- a/drivers/pci/hotplug/Makefile
+++ b/drivers/pci/hotplug/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_HOTPLUG_PCI_PCIE)		+= pciehp.o
 obj-$(CONFIG_HOTPLUG_PCI_CPCI_ZT5550)	+= cpcihp_zt5550.o
 obj-$(CONFIG_HOTPLUG_PCI_CPCI_GENERIC)	+= cpcihp_generic.o
 obj-$(CONFIG_HOTPLUG_PCI_SHPC)		+= shpchp.o
+obj-$(CONFIG_HOTPLUG_PCI_POWERNV)	+= pnv-php.o
 obj-$(CONFIG_HOTPLUG_PCI_RPA)		+= rpaphp.o
 obj-$(CONFIG_HOTPLUG_PCI_RPA_DLPAR)	+= rpadlpar_io.o
 obj-$(CONFIG_HOTPLUG_PCI_SGI)		+= sgi_hotplug.o
@@ -50,6 +51,8 @@ ibmphp-objs		:=	ibmphp_core.o	\
 acpiphp-objs		:=	acpiphp_core.o	\
 				acpiphp_glue.o
 
+pnv-php-objs		:=	pnv_php.o
+
 rpaphp-objs		:=	rpaphp_core.o	\
 				rpaphp_pci.o	\
 				rpaphp_slot.o
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index fa49f9143b80..6a33ddcfa20b 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -675,6 +675,8 @@ static void acpiphp_check_bridge(struct acpiphp_bridge *bridge)
 	if (bridge->is_going_away)
 		return;
 
+	pm_runtime_get_sync(&bridge->pci_dev->dev);
+
 	list_for_each_entry(slot, &bridge->slots, node) {
 		struct pci_bus *bus = slot->bus;
 		struct pci_dev *dev, *tmp;
@@ -694,6 +696,8 @@ static void acpiphp_check_bridge(struct acpiphp_bridge *bridge)
 			disable_slot(slot);
 		}
 	}
+
+	pm_runtime_put(&bridge->pci_dev->dev);
 }
 
 /*
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 5c24e938042f..08e84d61874e 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -546,6 +546,10 @@ static irqreturn_t pcie_isr(int irq, void *dev_id)
 	u8 present;
 	bool link;
 
+	/* Interrupts cannot originate from a controller that's asleep */
+	if (pdev->current_state == PCI_D3cold)
+		return IRQ_NONE;
+
 	/*
 	 * In order to guarantee that all interrupt events are
 	 * serviced, we need to re-inspect Slot Status register after
diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c
new file mode 100644
index 000000000000..e6245b03f0a1
--- /dev/null
+++ b/drivers/pci/hotplug/pnv_php.c
@@ -0,0 +1,711 @@
+/*
+ * PCI Hotplug Driver for PowerPC PowerNV platform.
+ *
+ * Copyright Gavin Shan, IBM Corporation 2016.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/libfdt.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+
+#include <asm/opal.h>
+#include <asm/pnv-pci.h>
+#include <asm/ppc-pci.h>
+
+#define DRIVER_VERSION	"0.1"
+#define DRIVER_AUTHOR	"Gavin Shan, IBM Corporation"
+#define DRIVER_DESC	"PowerPC PowerNV PCI Hotplug Driver"
+
+static LIST_HEAD(pnv_php_slot_list);
+static DEFINE_SPINLOCK(pnv_php_lock);
+
+static void pnv_php_register(struct device_node *dn);
+static void pnv_php_unregister_one(struct device_node *dn);
+static void pnv_php_unregister(struct device_node *dn);
+
+static void pnv_php_free_slot(struct kref *kref)
+{
+	struct pnv_php_slot *php_slot = container_of(kref,
+					struct pnv_php_slot, kref);
+
+	WARN_ON(!list_empty(&php_slot->children));
+	kfree(php_slot->name);
+	kfree(php_slot);
+}
+
+static inline void pnv_php_put_slot(struct pnv_php_slot *php_slot)
+{
+
+	if (WARN_ON(!php_slot))
+		return;
+
+	kref_put(&php_slot->kref, pnv_php_free_slot);
+}
+
+static struct pnv_php_slot *pnv_php_match(struct device_node *dn,
+					  struct pnv_php_slot *php_slot)
+{
+	struct pnv_php_slot *target, *tmp;
+
+	if (php_slot->dn == dn) {
+		kref_get(&php_slot->kref);
+		return php_slot;
+	}
+
+	list_for_each_entry(tmp, &php_slot->children, link) {
+		target = pnv_php_match(dn, tmp);
+		if (target)
+			return target;
+	}
+
+	return NULL;
+}
+
+struct pnv_php_slot *pnv_php_find_slot(struct device_node *dn)
+{
+	struct pnv_php_slot *php_slot, *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pnv_php_lock, flags);
+	list_for_each_entry(tmp, &pnv_php_slot_list, link) {
+		php_slot = pnv_php_match(dn, tmp);
+		if (php_slot) {
+			spin_unlock_irqrestore(&pnv_php_lock, flags);
+			return php_slot;
+		}
+	}
+	spin_unlock_irqrestore(&pnv_php_lock, flags);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(pnv_php_find_slot);
+
+/*
+ * Remove pdn for all children of the indicated device node.
+ * The function should remove pdn in a depth-first manner.
+ */
+static void pnv_php_rmv_pdns(struct device_node *dn)
+{
+	struct device_node *child;
+
+	for_each_child_of_node(dn, child) {
+		pnv_php_rmv_pdns(child);
+
+		pci_remove_device_node_info(child);
+	}
+}
+
+/*
+ * Detach all child nodes of the indicated device nodes. The
+ * function should handle device nodes in depth-first manner.
+ *
+ * We should not invoke of_node_release() as the memory for
+ * individual device node is part of large memory block. The
+ * large block is allocated from memblock (system bootup) or
+ * kmalloc() when unflattening the device tree by OF changeset.
+ * We can not free the large block allocated from memblock. For
+ * later case, it should be released at once.
+ */
+static void pnv_php_detach_device_nodes(struct device_node *parent)
+{
+	struct device_node *dn;
+	int refcount;
+
+	for_each_child_of_node(parent, dn) {
+		pnv_php_detach_device_nodes(dn);
+
+		of_node_put(dn);
+		refcount = atomic_read(&dn->kobj.kref.refcount);
+		if (unlikely(refcount != 1))
+			pr_warn("Invalid refcount %d on <%s>\n",
+				refcount, of_node_full_name(dn));
+
+		of_detach_node(dn);
+	}
+}
+
+static void pnv_php_rmv_devtree(struct pnv_php_slot *php_slot)
+{
+	pnv_php_rmv_pdns(php_slot->dn);
+
+	/*
+	 * Decrease the refcount if the device nodes were created
+	 * through OF changeset before detaching them.
+	 */
+	if (php_slot->fdt)
+		of_changeset_destroy(&php_slot->ocs);
+	pnv_php_detach_device_nodes(php_slot->dn);
+
+	if (php_slot->fdt) {
+		kfree(php_slot->dt);
+		kfree(php_slot->fdt);
+		php_slot->dt        = NULL;
+		php_slot->dn->child = NULL;
+		php_slot->fdt       = NULL;
+	}
+}
+
+/*
+ * As the nodes in OF changeset are applied in reverse order, we
+ * need revert the nodes in advance so that we have correct node
+ * order after the changeset is applied.
+ */
+static void pnv_php_reverse_nodes(struct device_node *parent)
+{
+	struct device_node *child, *next;
+
+	/* In-depth first */
+	for_each_child_of_node(parent, child)
+		pnv_php_reverse_nodes(child);
+
+	/* Reverse the nodes in the child list */
+	child = parent->child;
+	parent->child = NULL;
+	while (child) {
+		next = child->sibling;
+
+		child->sibling = parent->child;
+		parent->child = child;
+		child = next;
+	}
+}
+
+static int pnv_php_populate_changeset(struct of_changeset *ocs,
+				      struct device_node *dn)
+{
+	struct device_node *child;
+	int ret = 0;
+
+	for_each_child_of_node(dn, child) {
+		ret = of_changeset_attach_node(ocs, child);
+		if (unlikely(ret))
+			break;
+
+		ret = pnv_php_populate_changeset(ocs, child);
+		if (unlikely(ret))
+			break;
+	}
+
+	return ret;
+}
+
+static void *pnv_php_add_one_pdn(struct device_node *dn, void *data)
+{
+	struct pci_controller *hose = (struct pci_controller *)data;
+	struct pci_dn *pdn;
+
+	pdn = pci_add_device_node_info(hose, dn);
+	if (unlikely(!pdn))
+		return ERR_PTR(-ENOMEM);
+
+	return NULL;
+}
+
+static void pnv_php_add_pdns(struct pnv_php_slot *slot)
+{
+	struct pci_controller *hose = pci_bus_to_host(slot->bus);
+
+	pci_traverse_device_nodes(slot->dn, pnv_php_add_one_pdn, hose);
+}
+
+static int pnv_php_add_devtree(struct pnv_php_slot *php_slot)
+{
+	void *fdt, *fdt1, *dt;
+	int ret;
+
+	/* We don't know the FDT blob size. We try to get it through
+	 * maximal memory chunk and then copy it to another chunk that
+	 * fits the real size.
+	 */
+	fdt1 = kzalloc(0x10000, GFP_KERNEL);
+	if (unlikely(!fdt1)) {
+		ret = -ENOMEM;
+		dev_warn(&php_slot->pdev->dev, "Cannot alloc FDT blob\n");
+		goto out;
+	}
+
+	ret = pnv_pci_get_device_tree(php_slot->dn->phandle, fdt1, 0x10000);
+	if (unlikely(ret)) {
+		dev_warn(&php_slot->pdev->dev, "Error %d getting FDT blob\n",
+			 ret);
+		goto free_fdt1;
+	}
+
+	fdt = kzalloc(fdt_totalsize(fdt1), GFP_KERNEL);
+	if (unlikely(!fdt)) {
+		ret = -ENOMEM;
+		dev_warn(&php_slot->pdev->dev, "Cannot %d bytes memory\n",
+			 fdt_totalsize(fdt1));
+		goto free_fdt1;
+	}
+
+	/* Unflatten device tree blob */
+	memcpy(fdt, fdt1, fdt_totalsize(fdt1));
+	dt = of_fdt_unflatten_tree(fdt, php_slot->dn, NULL);
+	if (unlikely(!dt)) {
+		ret = -EINVAL;
+		dev_warn(&php_slot->pdev->dev, "Cannot unflatten FDT\n");
+		goto free_fdt;
+	}
+
+	/* Initialize and apply the changeset */
+	of_changeset_init(&php_slot->ocs);
+	pnv_php_reverse_nodes(php_slot->dn);
+	ret = pnv_php_populate_changeset(&php_slot->ocs, php_slot->dn);
+	if (unlikely(ret)) {
+		pnv_php_reverse_nodes(php_slot->dn);
+		dev_warn(&php_slot->pdev->dev, "Error %d populating changeset\n",
+			 ret);
+		goto free_dt;
+	}
+
+	php_slot->dn->child = NULL;
+	ret = of_changeset_apply(&php_slot->ocs);
+	if (unlikely(ret)) {
+		dev_warn(&php_slot->pdev->dev, "Error %d applying changeset\n",
+			 ret);
+		goto destroy_changeset;
+	}
+
+	/* Add device node firmware data */
+	pnv_php_add_pdns(php_slot);
+	php_slot->fdt = fdt;
+	php_slot->dt  = dt;
+	kfree(fdt1);
+	goto out;
+
+destroy_changeset:
+	of_changeset_destroy(&php_slot->ocs);
+free_dt:
+	kfree(dt);
+	php_slot->dn->child = NULL;
+free_fdt:
+	kfree(fdt);
+free_fdt1:
+	kfree(fdt1);
+out:
+	return ret;
+}
+
+int pnv_php_set_slot_power_state(struct hotplug_slot *slot,
+				 uint8_t state)
+{
+	struct pnv_php_slot *php_slot = slot->private;
+	struct opal_msg msg;
+	int ret;
+
+	ret = pnv_pci_set_power_state(php_slot->id, state, &msg);
+	if (likely(ret > 0)) {
+		if (be64_to_cpu(msg.params[1]) != php_slot->dn->phandle	||
+		    be64_to_cpu(msg.params[2]) != state			||
+		    be64_to_cpu(msg.params[3]) != OPAL_SUCCESS) {
+			dev_warn(&php_slot->pdev->dev, "Wrong msg (%lld, %lld, %lld)\n",
+				 be64_to_cpu(msg.params[1]),
+				 be64_to_cpu(msg.params[2]),
+				 be64_to_cpu(msg.params[3]));
+			return -ENOMSG;
+		}
+	} else if (unlikely(ret < 0)) {
+		dev_warn(&php_slot->pdev->dev, "Error %d powering %s\n",
+			 ret, (state == OPAL_PCI_SLOT_POWER_ON) ? "on" : "off");
+		return ret;
+	}
+
+	if (state == OPAL_PCI_SLOT_POWER_OFF || state == OPAL_PCI_SLOT_OFFLINE)
+		pnv_php_rmv_devtree(php_slot);
+	else
+		ret = pnv_php_add_devtree(php_slot);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pnv_php_set_slot_power_state);
+
+static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state)
+{
+	struct pnv_php_slot *php_slot = slot->private;
+	uint8_t power_state = OPAL_PCI_SLOT_POWER_ON;
+	int ret;
+
+	/*
+	 * Retrieve power status from firmware. If we fail
+	 * getting that, the power status fails back to
+	 * be on.
+	 */
+	ret = pnv_pci_get_power_state(php_slot->id, &power_state);
+	if (unlikely(ret)) {
+		dev_warn(&php_slot->pdev->dev, "Error %d getting power status\n",
+			 ret);
+	} else {
+		*state = power_state;
+		slot->info->power_status = power_state;
+	}
+
+	return 0;
+}
+
+static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
+{
+	struct pnv_php_slot *php_slot = slot->private;
+	uint8_t presence = OPAL_PCI_SLOT_EMPTY;
+	int ret;
+
+	/*
+	 * Retrieve presence status from firmware. If we can't
+	 * get that, it will fail back to be empty.
+	 */
+	ret = pnv_pci_get_presence_state(php_slot->id, &presence);
+	if (likely(ret >= 0)) {
+		*state = presence;
+		slot->info->adapter_status = presence;
+		ret = 0;
+	} else {
+		dev_warn(&php_slot->pdev->dev, "Error %d getting presence\n",
+			 ret);
+	}
+
+	return ret;
+}
+
+static int pnv_php_set_attention_state(struct hotplug_slot *slot, u8 state)
+{
+	/* FIXME: Make it real once firmware supports it */
+	slot->info->attention_status = state;
+
+	return 0;
+}
+
+static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan)
+{
+	struct hotplug_slot *slot = &php_slot->slot;
+	uint8_t presence = OPAL_PCI_SLOT_EMPTY;
+	uint8_t power_status = OPAL_PCI_SLOT_POWER_ON;
+	int ret;
+
+	/* Check if the slot has been configured */
+	if (php_slot->state != PNV_PHP_STATE_REGISTERED)
+		return 0;
+
+	/* Retrieve slot presence status */
+	ret = pnv_php_get_adapter_state(slot, &presence);
+	if (unlikely(ret))
+		return ret;
+
+	/* Proceed if there have nothing behind the slot */
+	if (presence == OPAL_PCI_SLOT_EMPTY)
+		goto scan;
+
+	/*
+	 * If the power supply to the slot is off, we can't detect
+	 * adapter presence state. That means we have to turn the
+	 * slot on before going to probe slot's presence state.
+	 *
+	 * On the first time, we don't change the power status to
+	 * boost system boot with assumption that the firmware
+	 * supplies consistent slot power status: empty slot always
+	 * has its power off and non-empty slot has its power on.
+	 */
+	if (!php_slot->power_state_check) {
+		php_slot->power_state_check = true;
+
+		ret = pnv_php_get_power_state(slot, &power_status);
+		if (unlikely(ret))
+			return ret;
+
+		if (power_status != OPAL_PCI_SLOT_POWER_ON)
+			return 0;
+	}
+
+	/* Check the power status. Scan the slot if it is already on */
+	ret = pnv_php_get_power_state(slot, &power_status);
+	if (unlikely(ret))
+		return ret;
+
+	if (power_status == OPAL_PCI_SLOT_POWER_ON)
+		goto scan;
+
+	/* Power is off, turn it on and then scan the slot */
+	ret = pnv_php_set_slot_power_state(slot, OPAL_PCI_SLOT_POWER_ON);
+	if (unlikely(ret))
+		return ret;
+
+scan:
+	if (presence == OPAL_PCI_SLOT_PRESENT) {
+		if (rescan) {
+			pci_lock_rescan_remove();
+			pci_hp_add_devices(php_slot->bus);
+			pci_unlock_rescan_remove();
+		}
+
+		/* Rescan for child hotpluggable slots */
+		php_slot->state = PNV_PHP_STATE_POPULATED;
+		if (rescan)
+			pnv_php_register(php_slot->dn);
+	} else {
+		php_slot->state = PNV_PHP_STATE_POPULATED;
+	}
+
+	return 0;
+}
+
+static int pnv_php_enable_slot(struct hotplug_slot *slot)
+{
+	struct pnv_php_slot *php_slot = container_of(slot,
+						     struct pnv_php_slot, slot);
+
+	return pnv_php_enable(php_slot, true);
+}
+
+static int pnv_php_disable_slot(struct hotplug_slot *slot)
+{
+	struct pnv_php_slot *php_slot = slot->private;
+	int ret;
+
+	if (php_slot->state != PNV_PHP_STATE_POPULATED)
+		return 0;
+
+	/* Remove all devices behind the slot */
+	pci_lock_rescan_remove();
+	pci_hp_remove_devices(php_slot->bus);
+	pci_unlock_rescan_remove();
+
+	/* Detach the child hotpluggable slots */
+	pnv_php_unregister(php_slot->dn);
+
+	/* Notify firmware and remove device nodes */
+	ret = pnv_php_set_slot_power_state(slot, OPAL_PCI_SLOT_POWER_OFF);
+
+	php_slot->state = PNV_PHP_STATE_REGISTERED;
+	return ret;
+}
+
+static struct hotplug_slot_ops php_slot_ops = {
+	.get_power_status	= pnv_php_get_power_state,
+	.get_adapter_status	= pnv_php_get_adapter_state,
+	.set_attention_status	= pnv_php_set_attention_state,
+	.enable_slot		= pnv_php_enable_slot,
+	.disable_slot		= pnv_php_disable_slot,
+};
+
+static void pnv_php_release(struct hotplug_slot *slot)
+{
+	struct pnv_php_slot *php_slot = slot->private;
+	unsigned long flags;
+
+	/* Remove from global or child list */
+	spin_lock_irqsave(&pnv_php_lock, flags);
+	list_del(&php_slot->link);
+	spin_unlock_irqrestore(&pnv_php_lock, flags);
+
+	/* Detach from parent */
+	pnv_php_put_slot(php_slot);
+	pnv_php_put_slot(php_slot->parent);
+}
+
+static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn)
+{
+	struct pnv_php_slot *php_slot;
+	struct pci_bus *bus;
+	const char *label;
+	uint64_t id;
+
+	label = of_get_property(dn, "ibm,slot-label", NULL);
+	if (unlikely(!label))
+		return NULL;
+
+	if (pnv_pci_get_slot_id(dn, &id))
+		return NULL;
+
+	bus = pci_find_bus_by_node(dn);
+	if (unlikely(!bus))
+		return NULL;
+
+	php_slot = kzalloc(sizeof(*php_slot), GFP_KERNEL);
+	if (unlikely(!php_slot))
+		return NULL;
+
+	php_slot->name = kstrdup(label, GFP_KERNEL);
+	if (unlikely(!php_slot->name)) {
+		kfree(php_slot);
+		return NULL;
+	}
+
+	if (likely(dn->child && PCI_DN(dn->child)))
+		php_slot->slot_no = PCI_SLOT(PCI_DN(dn->child)->devfn);
+	else
+		php_slot->slot_no = -1;   /* Placeholder slot */
+
+	kref_init(&php_slot->kref);
+	php_slot->state	                = PNV_PHP_STATE_INITIALIZED;
+	php_slot->dn	                = dn;
+	php_slot->pdev	                = bus->self;
+	php_slot->bus	                = bus;
+	php_slot->id	                = id;
+	php_slot->power_state_check     = false;
+	php_slot->slot.ops              = &php_slot_ops;
+	php_slot->slot.info             = &php_slot->slot_info;
+	php_slot->slot.release          = pnv_php_release;
+	php_slot->slot.private          = php_slot;
+
+	INIT_LIST_HEAD(&php_slot->children);
+	INIT_LIST_HEAD(&php_slot->link);
+
+	return php_slot;
+}
+
+static int pnv_php_register_slot(struct pnv_php_slot *php_slot)
+{
+	struct pnv_php_slot *parent;
+	struct device_node *dn = php_slot->dn;
+	unsigned long flags;
+	int ret;
+
+	/* Check if the slot is registered or not */
+	parent = pnv_php_find_slot(php_slot->dn);
+	if (unlikely(parent)) {
+		pnv_php_put_slot(parent);
+		return -EEXIST;
+	}
+
+	/* Register PCI slot */
+	ret = pci_hp_register(&php_slot->slot, php_slot->bus,
+			      php_slot->slot_no, php_slot->name);
+	if (unlikely(ret)) {
+		dev_warn(&php_slot->pdev->dev, "Error %d registering slot\n",
+			 ret);
+		return ret;
+	}
+
+	/* Attach to the parent's child list or global list */
+	while ((dn = of_get_parent(dn))) {
+		if (!PCI_DN(dn)) {
+			of_node_put(dn);
+			break;
+		}
+
+		parent = pnv_php_find_slot(dn);
+		if (parent) {
+			of_node_put(dn);
+			break;
+		}
+
+		of_node_put(dn);
+	}
+
+	spin_lock_irqsave(&pnv_php_lock, flags);
+	php_slot->parent = parent;
+	if (parent)
+		list_add_tail(&php_slot->link, &parent->children);
+	else
+		list_add_tail(&php_slot->link, &pnv_php_slot_list);
+	spin_unlock_irqrestore(&pnv_php_lock, flags);
+
+	php_slot->state = PNV_PHP_STATE_REGISTERED;
+	return 0;
+}
+
+static int pnv_php_register_one(struct device_node *dn)
+{
+	struct pnv_php_slot *php_slot;
+	const __be32 *prop32;
+	int ret;
+
+	/* Check if it's hotpluggable slot */
+	prop32 = of_get_property(dn, "ibm,slot-pluggable", NULL);
+	if (!prop32 || !of_read_number(prop32, 1))
+		return -ENXIO;
+
+	prop32 = of_get_property(dn, "ibm,reset-by-firmware", NULL);
+	if (!prop32 || !of_read_number(prop32, 1))
+		return -ENXIO;
+
+	php_slot = pnv_php_alloc_slot(dn);
+	if (unlikely(!php_slot))
+		return -ENODEV;
+
+	ret = pnv_php_register_slot(php_slot);
+	if (unlikely(ret))
+		goto free_slot;
+
+	ret = pnv_php_enable(php_slot, false);
+	if (unlikely(ret))
+		goto unregister_slot;
+
+	return 0;
+
+unregister_slot:
+	pnv_php_unregister_one(php_slot->dn);
+free_slot:
+	pnv_php_put_slot(php_slot);
+	return ret;
+}
+
+static void pnv_php_register(struct device_node *dn)
+{
+	struct device_node *child;
+
+	/*
+	 * The parent slots should be registered before their
+	 * child slots.
+	 */
+	for_each_child_of_node(dn, child) {
+		pnv_php_register_one(child);
+		pnv_php_register(child);
+	}
+}
+
+static void pnv_php_unregister_one(struct device_node *dn)
+{
+	struct pnv_php_slot *php_slot;
+
+	php_slot = pnv_php_find_slot(dn);
+	if (!php_slot)
+		return;
+
+	php_slot->state = PNV_PHP_STATE_OFFLINE;
+	pnv_php_put_slot(php_slot);
+	pci_hp_deregister(&php_slot->slot);
+}
+
+static void pnv_php_unregister(struct device_node *dn)
+{
+	struct device_node *child;
+
+	/* The child slots should go before their parent slots */
+	for_each_child_of_node(dn, child) {
+		pnv_php_unregister(child);
+		pnv_php_unregister_one(child);
+	}
+}
+
+static int __init pnv_php_init(void)
+{
+	struct device_node *dn;
+
+	pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+	for_each_compatible_node(dn, NULL, "ibm,ioda2-phb")
+		pnv_php_register(dn);
+
+	return 0;
+}
+
+static void __exit pnv_php_exit(void)
+{
+	struct device_node *dn;
+
+	for_each_compatible_node(dn, NULL, "ibm,ioda2-phb")
+		pnv_php_unregister(dn);
+}
+
+module_init(pnv_php_init);
+module_exit(pnv_php_exit);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c
index 6937c725b00b..388c4d8fcdd1 100644
--- a/drivers/pci/hotplug/rpaphp_slot.c
+++ b/drivers/pci/hotplug/rpaphp_slot.c
@@ -117,8 +117,10 @@ EXPORT_SYMBOL_GPL(rpaphp_deregister_slot);
 int rpaphp_register_slot(struct slot *slot)
 {
 	struct hotplug_slot *php_slot = slot->hotplug_slot;
+	struct device_node *child;
+	u32 my_index;
 	int retval;
-	int slotno;
+	int slotno = -1;
 
 	dbg("%s registering slot:path[%s] index[%x], name[%s] pdomain[%x] type[%d]\n",
 		__func__, slot->dn->full_name, slot->index, slot->name,
@@ -130,10 +132,15 @@ int rpaphp_register_slot(struct slot *slot)
 		return -EAGAIN;
 	}
 
-	if (slot->dn->child)
-		slotno = PCI_SLOT(PCI_DN(slot->dn->child)->devfn);
-	else
-		slotno = -1;
+	for_each_child_of_node(slot->dn, child) {
+		retval = of_property_read_u32(child, "ibm,my-drc-index", &my_index);
+		if (my_index == slot->index) {
+			slotno = PCI_SLOT(PCI_DN(child)->devfn);
+			of_node_put(child);
+			break;
+		}
+	}
+
 	retval = pci_hp_register(php_slot, slot->bus, slotno, slot->name);
 	if (retval) {
 		err("pci_hp_register failed with error %d\n", retval);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index a080f4496fe2..a02981efdad5 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -4,6 +4,7 @@
  *
  * Copyright (C) 2003-2004 Intel
  * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
+ * Copyright (C) 2016 Christoph Hellwig.
  */
 
 #include <linux/err.h>
@@ -207,6 +208,12 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 	desc->masked = __pci_msi_desc_mask_irq(desc, mask, flag);
 }
 
+static void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
+{
+	return desc->mask_base +
+		desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+}
+
 /*
  * This internal function does not flush PCI writes to the device.
  * All users must ensure that they read from the device before either
@@ -217,8 +224,6 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag)
 {
 	u32 mask_bits = desc->masked;
-	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
-						PCI_MSIX_ENTRY_VECTOR_CTRL;
 
 	if (pci_msi_ignore_mask)
 		return 0;
@@ -226,7 +231,7 @@ u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag)
 	mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
 	if (flag)
 		mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
-	writel(mask_bits, desc->mask_base + offset);
+	writel(mask_bits, pci_msix_desc_addr(desc) + PCI_MSIX_ENTRY_VECTOR_CTRL);
 
 	return mask_bits;
 }
@@ -284,8 +289,7 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 	BUG_ON(dev->current_state != PCI_D0);
 
 	if (entry->msi_attrib.is_msix) {
-		void __iomem *base = entry->mask_base +
-			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+		void __iomem *base = pci_msix_desc_addr(entry);
 
 		msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR);
 		msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR);
@@ -315,9 +319,7 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 	if (dev->current_state != PCI_D0) {
 		/* Don't touch the hardware now */
 	} else if (entry->msi_attrib.is_msix) {
-		void __iomem *base;
-		base = entry->mask_base +
-			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+		void __iomem *base = pci_msix_desc_addr(entry);
 
 		writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR);
 		writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR);
@@ -567,6 +569,7 @@ static struct msi_desc *msi_setup_entry(struct pci_dev *dev, int nvec)
 	entry->msi_attrib.multi_cap	= (control & PCI_MSI_FLAGS_QMASK) >> 1;
 	entry->msi_attrib.multiple	= ilog2(__roundup_pow_of_two(nvec));
 	entry->nvec_used		= nvec;
+	entry->affinity			= dev->irq_affinity;
 
 	if (control & PCI_MSI_FLAGS_64BIT)
 		entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_64;
@@ -678,10 +681,18 @@ static void __iomem *msix_map_region(struct pci_dev *dev, unsigned nr_entries)
 static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 			      struct msix_entry *entries, int nvec)
 {
+	const struct cpumask *mask = NULL;
 	struct msi_desc *entry;
-	int i;
+	int cpu = -1, i;
 
 	for (i = 0; i < nvec; i++) {
+		if (dev->irq_affinity) {
+			cpu = cpumask_next(cpu, dev->irq_affinity);
+			if (cpu >= nr_cpu_ids)
+				cpu = cpumask_first(dev->irq_affinity);
+			mask = cpumask_of(cpu);
+		}
+
 		entry = alloc_msi_entry(&dev->dev);
 		if (!entry) {
 			if (!i)
@@ -694,10 +705,14 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 
 		entry->msi_attrib.is_msix	= 1;
 		entry->msi_attrib.is_64		= 1;
-		entry->msi_attrib.entry_nr	= entries[i].entry;
+		if (entries)
+			entry->msi_attrib.entry_nr = entries[i].entry;
+		else
+			entry->msi_attrib.entry_nr = i;
 		entry->msi_attrib.default_irq	= dev->irq;
 		entry->mask_base		= base;
 		entry->nvec_used		= 1;
+		entry->affinity			= mask;
 
 		list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
 	}
@@ -712,13 +727,11 @@ static void msix_program_entries(struct pci_dev *dev,
 	int i = 0;
 
 	for_each_pci_msi_entry(entry, dev) {
-		int offset = entries[i].entry * PCI_MSIX_ENTRY_SIZE +
-						PCI_MSIX_ENTRY_VECTOR_CTRL;
-
-		entries[i].vector = entry->irq;
-		entry->masked = readl(entry->mask_base + offset);
+		if (entries)
+			entries[i++].vector = entry->irq;
+		entry->masked = readl(pci_msix_desc_addr(entry) +
+				PCI_MSIX_ENTRY_VECTOR_CTRL);
 		msix_mask_irq(entry, 1);
-		i++;
 	}
 }
 
@@ -931,7 +944,7 @@ EXPORT_SYMBOL(pci_msix_vec_count);
 /**
  * pci_enable_msix - configure device's MSI-X capability structure
  * @dev: pointer to the pci_dev data structure of MSI-X device function
- * @entries: pointer to an array of MSI-X entries
+ * @entries: pointer to an array of MSI-X entries (optional)
  * @nvec: number of MSI-X irqs requested for allocation by device driver
  *
  * Setup the MSI-X capability structure of device function with the number
@@ -951,22 +964,21 @@ int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
 	if (!pci_msi_supported(dev, nvec))
 		return -EINVAL;
 
-	if (!entries)
-		return -EINVAL;
-
 	nr_entries = pci_msix_vec_count(dev);
 	if (nr_entries < 0)
 		return nr_entries;
 	if (nvec > nr_entries)
 		return nr_entries;
 
-	/* Check for any invalid entries */
-	for (i = 0; i < nvec; i++) {
-		if (entries[i].entry >= nr_entries)
-			return -EINVAL;		/* invalid entry */
-		for (j = i + 1; j < nvec; j++) {
-			if (entries[i].entry == entries[j].entry)
-				return -EINVAL;	/* duplicate entry */
+	if (entries) {
+		/* Check for any invalid entries */
+		for (i = 0; i < nvec; i++) {
+			if (entries[i].entry >= nr_entries)
+				return -EINVAL;		/* invalid entry */
+			for (j = i + 1; j < nvec; j++) {
+				if (entries[i].entry == entries[j].entry)
+					return -EINVAL;	/* duplicate entry */
+			}
 		}
 	}
 	WARN_ON(!!dev->msix_enabled);
@@ -1026,19 +1038,8 @@ int pci_msi_enabled(void)
 }
 EXPORT_SYMBOL(pci_msi_enabled);
 
-/**
- * pci_enable_msi_range - configure device's MSI capability structure
- * @dev: device to configure
- * @minvec: minimal number of interrupts to configure
- * @maxvec: maximum number of interrupts to configure
- *
- * This function tries to allocate a maximum possible number of interrupts in a
- * range between @minvec and @maxvec. It returns a negative errno if an error
- * occurs. If it succeeds, it returns the actual number of interrupts allocated
- * and updates the @dev's irq member to the lowest new interrupt number;
- * the other interrupt numbers allocated to this device are consecutive.
- **/
-int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
+static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
+		unsigned int flags)
 {
 	int nvec;
 	int rc;
@@ -1061,25 +1062,85 @@ int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
 	nvec = pci_msi_vec_count(dev);
 	if (nvec < 0)
 		return nvec;
-	else if (nvec < minvec)
+	if (nvec < minvec)
 		return -EINVAL;
-	else if (nvec > maxvec)
+
+	if (nvec > maxvec)
 		nvec = maxvec;
 
-	do {
+	for (;;) {
+		if (!(flags & PCI_IRQ_NOAFFINITY)) {
+			dev->irq_affinity = irq_create_affinity_mask(&nvec);
+			if (nvec < minvec)
+				return -ENOSPC;
+		}
+
 		rc = msi_capability_init(dev, nvec);
-		if (rc < 0) {
+		if (rc == 0)
+			return nvec;
+
+		kfree(dev->irq_affinity);
+		dev->irq_affinity = NULL;
+
+		if (rc < 0)
 			return rc;
-		} else if (rc > 0) {
-			if (rc < minvec)
+		if (rc < minvec)
+			return -ENOSPC;
+
+		nvec = rc;
+	}
+}
+
+/**
+ * pci_enable_msi_range - configure device's MSI capability structure
+ * @dev: device to configure
+ * @minvec: minimal number of interrupts to configure
+ * @maxvec: maximum number of interrupts to configure
+ *
+ * This function tries to allocate a maximum possible number of interrupts in a
+ * range between @minvec and @maxvec. It returns a negative errno if an error
+ * occurs. If it succeeds, it returns the actual number of interrupts allocated
+ * and updates the @dev's irq member to the lowest new interrupt number;
+ * the other interrupt numbers allocated to this device are consecutive.
+ **/
+int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
+{
+	return __pci_enable_msi_range(dev, minvec, maxvec, PCI_IRQ_NOAFFINITY);
+}
+EXPORT_SYMBOL(pci_enable_msi_range);
+
+static int __pci_enable_msix_range(struct pci_dev *dev,
+		struct msix_entry *entries, int minvec, int maxvec,
+		unsigned int flags)
+{
+	int nvec = maxvec;
+	int rc;
+
+	if (maxvec < minvec)
+		return -ERANGE;
+
+	for (;;) {
+		if (!(flags & PCI_IRQ_NOAFFINITY)) {
+			dev->irq_affinity = irq_create_affinity_mask(&nvec);
+			if (nvec < minvec)
 				return -ENOSPC;
-			nvec = rc;
 		}
-	} while (rc);
 
-	return nvec;
+		rc = pci_enable_msix(dev, entries, nvec);
+		if (rc == 0)
+			return nvec;
+
+		kfree(dev->irq_affinity);
+		dev->irq_affinity = NULL;
+
+		if (rc < 0)
+			return rc;
+		if (rc < minvec)
+			return -ENOSPC;
+
+		nvec = rc;
+	}
 }
-EXPORT_SYMBOL(pci_enable_msi_range);
 
 /**
  * pci_enable_msix_range - configure device's MSI-X capability structure
@@ -1097,28 +1158,101 @@ EXPORT_SYMBOL(pci_enable_msi_range);
  * with new allocated MSI-X interrupts.
  **/
 int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
-			       int minvec, int maxvec)
+		int minvec, int maxvec)
 {
-	int nvec = maxvec;
-	int rc;
+	return __pci_enable_msix_range(dev, entries, minvec, maxvec,
+			PCI_IRQ_NOAFFINITY);
+}
+EXPORT_SYMBOL(pci_enable_msix_range);
 
-	if (maxvec < minvec)
-		return -ERANGE;
+/**
+ * pci_alloc_irq_vectors - allocate multiple IRQs for a device
+ * @dev:		PCI device to operate on
+ * @min_vecs:		minimum number of vectors required (must be >= 1)
+ * @max_vecs:		maximum (desired) number of vectors
+ * @flags:		flags or quirks for the allocation
+ *
+ * Allocate up to @max_vecs interrupt vectors for @dev, using MSI-X or MSI
+ * vectors if available, and fall back to a single legacy vector
+ * if neither is available.  Return the number of vectors allocated,
+ * (which might be smaller than @max_vecs) if successful, or a negative
+ * error code on error. If less than @min_vecs interrupt vectors are
+ * available for @dev the function will fail with -ENOSPC.
+ *
+ * To get the Linux IRQ number used for a vector that can be passed to
+ * request_irq() use the pci_irq_vector() helper.
+ */
+int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs,
+		unsigned int max_vecs, unsigned int flags)
+{
+	int vecs = -ENOSPC;
 
-	do {
-		rc = pci_enable_msix(dev, entries, nvec);
-		if (rc < 0) {
-			return rc;
-		} else if (rc > 0) {
-			if (rc < minvec)
-				return -ENOSPC;
-			nvec = rc;
+	if (!(flags & PCI_IRQ_NOMSIX)) {
+		vecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs,
+				flags);
+		if (vecs > 0)
+			return vecs;
+	}
+
+	if (!(flags & PCI_IRQ_NOMSI)) {
+		vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, flags);
+		if (vecs > 0)
+			return vecs;
+	}
+
+	/* use legacy irq if allowed */
+	if (!(flags & PCI_IRQ_NOLEGACY) && min_vecs == 1)
+		return 1;
+	return vecs;
+}
+EXPORT_SYMBOL(pci_alloc_irq_vectors);
+
+/**
+ * pci_free_irq_vectors - free previously allocated IRQs for a device
+ * @dev:		PCI device to operate on
+ *
+ * Undoes the allocations and enabling in pci_alloc_irq_vectors().
+ */
+void pci_free_irq_vectors(struct pci_dev *dev)
+{
+	pci_disable_msix(dev);
+	pci_disable_msi(dev);
+}
+EXPORT_SYMBOL(pci_free_irq_vectors);
+
+/**
+ * pci_irq_vector - return Linux IRQ number of a device vector
+ * @dev: PCI device to operate on
+ * @nr: device-relative interrupt vector index (0-based).
+ */
+int pci_irq_vector(struct pci_dev *dev, unsigned int nr)
+{
+	if (dev->msix_enabled) {
+		struct msi_desc *entry;
+		int i = 0;
+
+		for_each_pci_msi_entry(entry, dev) {
+			if (i == nr)
+				return entry->irq;
+			i++;
 		}
-	} while (rc);
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
 
-	return nvec;
+	if (dev->msi_enabled) {
+		struct msi_desc *entry = first_pci_msi_entry(dev);
+
+		if (WARN_ON_ONCE(nr >= entry->nvec_used))
+			return -EINVAL;
+	} else {
+		if (WARN_ON_ONCE(nr > 0))
+			return -EINVAL;
+	}
+
+	return dev->irq + nr;
 }
-EXPORT_SYMBOL(pci_enable_msix_range);
+EXPORT_SYMBOL(pci_irq_vector);
 
 struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc)
 {
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index d7ffd66814bb..e39a67c8ef39 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -777,7 +777,7 @@ static int pci_pm_suspend_noirq(struct device *dev)
 
 	if (!pci_dev->state_saved) {
 		pci_save_state(pci_dev);
-		if (!pci_has_subordinate(pci_dev))
+		if (pci_power_manageable(pci_dev))
 			pci_prepare_to_sleep(pci_dev);
 	}
 
@@ -1144,7 +1144,6 @@ static int pci_pm_runtime_suspend(struct device *dev)
 		return -ENOSYS;
 
 	pci_dev->state_saved = false;
-	pci_dev->no_d3cold = false;
 	error = pm->runtime_suspend(dev);
 	if (error) {
 		/*
@@ -1161,8 +1160,6 @@ static int pci_pm_runtime_suspend(struct device *dev)
 
 		return error;
 	}
-	if (!pci_dev->d3cold_allowed)
-		pci_dev->no_d3cold = true;
 
 	pci_fixup_device(pci_fixup_suspend, pci_dev);
 
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index d319a9ca9b7b..bcd10c795284 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -406,6 +406,11 @@ static ssize_t d3cold_allowed_store(struct device *dev,
 		return -EINVAL;
 
 	pdev->d3cold_allowed = !!val;
+	if (pdev->d3cold_allowed)
+		pci_d3cold_enable(pdev);
+	else
+		pci_d3cold_disable(pdev);
+
 	pm_runtime_resume(dev);
 
 	return count;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index badbddc683f0..aab9d5115a5f 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -7,8 +7,10 @@
  *	Copyright 1997 -- 2000 Martin Mares <mj@ucw.cz>
  */
 
+#include <linux/acpi.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
+#include <linux/dmi.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_pci.h>
@@ -25,7 +27,9 @@
 #include <linux/device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pci_hotplug.h>
+#include <linux/vmalloc.h>
 #include <asm/setup.h>
+#include <asm/dma.h>
 #include <linux/aer.h>
 #include "pci.h"
 
@@ -81,6 +85,9 @@ unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE;
 unsigned long pci_hotplug_io_size  = DEFAULT_HOTPLUG_IO_SIZE;
 unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE;
 
+#define DEFAULT_HOTPLUG_BUS_SIZE	1
+unsigned long pci_hotplug_bus_size = DEFAULT_HOTPLUG_BUS_SIZE;
+
 enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_DEFAULT;
 
 /*
@@ -101,6 +108,21 @@ unsigned int pcibios_max_latency = 255;
 /* If set, the PCIe ARI capability will not be used. */
 static bool pcie_ari_disabled;
 
+/* Disable bridge_d3 for all PCIe ports */
+static bool pci_bridge_d3_disable;
+/* Force bridge_d3 for all PCIe ports */
+static bool pci_bridge_d3_force;
+
+static int __init pcie_port_pm_setup(char *str)
+{
+	if (!strcmp(str, "off"))
+		pci_bridge_d3_disable = true;
+	else if (!strcmp(str, "force"))
+		pci_bridge_d3_force = true;
+	return 1;
+}
+__setup("pcie_port_pm=", pcie_port_pm_setup);
+
 /**
  * pci_bus_max_busnr - returns maximum PCI bus number of given bus' children
  * @bus: pointer to PCI bus structure to search
@@ -2156,6 +2178,164 @@ void pci_config_pm_runtime_put(struct pci_dev *pdev)
 }
 
 /**
+ * pci_bridge_d3_possible - Is it possible to put the bridge into D3
+ * @bridge: Bridge to check
+ *
+ * This function checks if it is possible to move the bridge to D3.
+ * Currently we only allow D3 for recent enough PCIe ports.
+ */
+static bool pci_bridge_d3_possible(struct pci_dev *bridge)
+{
+	unsigned int year;
+
+	if (!pci_is_pcie(bridge))
+		return false;
+
+	switch (pci_pcie_type(bridge)) {
+	case PCI_EXP_TYPE_ROOT_PORT:
+	case PCI_EXP_TYPE_UPSTREAM:
+	case PCI_EXP_TYPE_DOWNSTREAM:
+		if (pci_bridge_d3_disable)
+			return false;
+		if (pci_bridge_d3_force)
+			return true;
+
+		/*
+		 * It should be safe to put PCIe ports from 2015 or newer
+		 * to D3.
+		 */
+		if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) &&
+		    year >= 2015) {
+			return true;
+		}
+		break;
+	}
+
+	return false;
+}
+
+static int pci_dev_check_d3cold(struct pci_dev *dev, void *data)
+{
+	bool *d3cold_ok = data;
+	bool no_d3cold;
+
+	/*
+	 * The device needs to be allowed to go D3cold and if it is wake
+	 * capable to do so from D3cold.
+	 */
+	no_d3cold = dev->no_d3cold || !dev->d3cold_allowed ||
+		(device_may_wakeup(&dev->dev) && !pci_pme_capable(dev, PCI_D3cold)) ||
+		!pci_power_manageable(dev);
+
+	*d3cold_ok = !no_d3cold;
+
+	return no_d3cold;
+}
+
+/*
+ * pci_bridge_d3_update - Update bridge D3 capabilities
+ * @dev: PCI device which is changed
+ * @remove: Is the device being removed
+ *
+ * Update upstream bridge PM capabilities accordingly depending on if the
+ * device PM configuration was changed or the device is being removed.  The
+ * change is also propagated upstream.
+ */
+static void pci_bridge_d3_update(struct pci_dev *dev, bool remove)
+{
+	struct pci_dev *bridge;
+	bool d3cold_ok = true;
+
+	bridge = pci_upstream_bridge(dev);
+	if (!bridge || !pci_bridge_d3_possible(bridge))
+		return;
+
+	pci_dev_get(bridge);
+	/*
+	 * If the device is removed we do not care about its D3cold
+	 * capabilities.
+	 */
+	if (!remove)
+		pci_dev_check_d3cold(dev, &d3cold_ok);
+
+	if (d3cold_ok) {
+		/*
+		 * We need to go through all children to find out if all of
+		 * them can still go to D3cold.
+		 */
+		pci_walk_bus(bridge->subordinate, pci_dev_check_d3cold,
+			     &d3cold_ok);
+	}
+
+	if (bridge->bridge_d3 != d3cold_ok) {
+		bridge->bridge_d3 = d3cold_ok;
+		/* Propagate change to upstream bridges */
+		pci_bridge_d3_update(bridge, false);
+	}
+
+	pci_dev_put(bridge);
+}
+
+/**
+ * pci_bridge_d3_device_changed - Update bridge D3 capabilities on change
+ * @dev: PCI device that was changed
+ *
+ * If a device is added or its PM configuration, such as is it allowed to
+ * enter D3cold, is changed this function updates upstream bridge PM
+ * capabilities accordingly.
+ */
+void pci_bridge_d3_device_changed(struct pci_dev *dev)
+{
+	pci_bridge_d3_update(dev, false);
+}
+
+/**
+ * pci_bridge_d3_device_removed - Update bridge D3 capabilities on remove
+ * @dev: PCI device being removed
+ *
+ * Function updates upstream bridge PM capabilities based on other devices
+ * still left on the bus.
+ */
+void pci_bridge_d3_device_removed(struct pci_dev *dev)
+{
+	pci_bridge_d3_update(dev, true);
+}
+
+/**
+ * pci_d3cold_enable - Enable D3cold for device
+ * @dev: PCI device to handle
+ *
+ * This function can be used in drivers to enable D3cold from the device
+ * they handle.  It also updates upstream PCI bridge PM capabilities
+ * accordingly.
+ */
+void pci_d3cold_enable(struct pci_dev *dev)
+{
+	if (dev->no_d3cold) {
+		dev->no_d3cold = false;
+		pci_bridge_d3_device_changed(dev);
+	}
+}
+EXPORT_SYMBOL_GPL(pci_d3cold_enable);
+
+/**
+ * pci_d3cold_disable - Disable D3cold for device
+ * @dev: PCI device to handle
+ *
+ * This function can be used in drivers to disable D3cold from the device
+ * they handle.  It also updates upstream PCI bridge PM capabilities
+ * accordingly.
+ */
+void pci_d3cold_disable(struct pci_dev *dev)
+{
+	if (!dev->no_d3cold) {
+		dev->no_d3cold = true;
+		pci_bridge_d3_device_changed(dev);
+	}
+}
+EXPORT_SYMBOL_GPL(pci_d3cold_disable);
+
+/**
  * pci_pm_init - Initialize PM functions of given PCI device
  * @dev: PCI device to handle.
  */
@@ -2189,6 +2369,7 @@ void pci_pm_init(struct pci_dev *dev)
 	dev->pm_cap = pm;
 	dev->d3_delay = PCI_PM_D3_WAIT;
 	dev->d3cold_delay = PCI_PM_D3COLD_WAIT;
+	dev->bridge_d3 = pci_bridge_d3_possible(dev);
 	dev->d3cold_allowed = true;
 
 	dev->d1_support = false;
@@ -3165,6 +3346,23 @@ int __weak pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
 #endif
 }
 
+/**
+ *	pci_unmap_iospace - Unmap the memory mapped I/O space
+ *	@res: resource to be unmapped
+ *
+ *	Unmap the CPU virtual address @res from virtual address space.
+ *	Only architectures that have memory mapped IO functions defined
+ *	(and the PCI_IOBASE value defined) should call this function.
+ */
+void pci_unmap_iospace(struct resource *res)
+{
+#if defined(PCI_IOBASE) && defined(CONFIG_MMU)
+	unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start;
+
+	unmap_kernel_range(vaddr, resource_size(res));
+#endif
+}
+
 static void __pci_set_master(struct pci_dev *dev, bool enable)
 {
 	u16 old_cmd, cmd;
@@ -4755,6 +4953,7 @@ static DEFINE_SPINLOCK(resource_alignment_lock);
 static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev)
 {
 	int seg, bus, slot, func, align_order, count;
+	unsigned short vendor, device, subsystem_vendor, subsystem_device;
 	resource_size_t align = 0;
 	char *p;
 
@@ -4768,28 +4967,55 @@ static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev)
 		} else {
 			align_order = -1;
 		}
-		if (sscanf(p, "%x:%x:%x.%x%n",
-			&seg, &bus, &slot, &func, &count) != 4) {
-			seg = 0;
-			if (sscanf(p, "%x:%x.%x%n",
-					&bus, &slot, &func, &count) != 3) {
-				/* Invalid format */
-				printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: %s\n",
-					p);
+		if (strncmp(p, "pci:", 4) == 0) {
+			/* PCI vendor/device (subvendor/subdevice) ids are specified */
+			p += 4;
+			if (sscanf(p, "%hx:%hx:%hx:%hx%n",
+				&vendor, &device, &subsystem_vendor, &subsystem_device, &count) != 4) {
+				if (sscanf(p, "%hx:%hx%n", &vendor, &device, &count) != 2) {
+					printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: pci:%s\n",
+						p);
+					break;
+				}
+				subsystem_vendor = subsystem_device = 0;
+			}
+			p += count;
+			if ((!vendor || (vendor == dev->vendor)) &&
+				(!device || (device == dev->device)) &&
+				(!subsystem_vendor || (subsystem_vendor == dev->subsystem_vendor)) &&
+				(!subsystem_device || (subsystem_device == dev->subsystem_device))) {
+				if (align_order == -1)
+					align = PAGE_SIZE;
+				else
+					align = 1 << align_order;
+				/* Found */
 				break;
 			}
 		}
-		p += count;
-		if (seg == pci_domain_nr(dev->bus) &&
-			bus == dev->bus->number &&
-			slot == PCI_SLOT(dev->devfn) &&
-			func == PCI_FUNC(dev->devfn)) {
-			if (align_order == -1)
-				align = PAGE_SIZE;
-			else
-				align = 1 << align_order;
-			/* Found */
-			break;
+		else {
+			if (sscanf(p, "%x:%x:%x.%x%n",
+				&seg, &bus, &slot, &func, &count) != 4) {
+				seg = 0;
+				if (sscanf(p, "%x:%x.%x%n",
+						&bus, &slot, &func, &count) != 3) {
+					/* Invalid format */
+					printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: %s\n",
+						p);
+					break;
+				}
+			}
+			p += count;
+			if (seg == pci_domain_nr(dev->bus) &&
+				bus == dev->bus->number &&
+				slot == PCI_SLOT(dev->devfn) &&
+				func == PCI_FUNC(dev->devfn)) {
+				if (align_order == -1)
+					align = PAGE_SIZE;
+				else
+					align = 1 << align_order;
+				/* Found */
+				break;
+			}
 		}
 		if (*p != ';' && *p != ',') {
 			/* End of param or invalid format */
@@ -4897,7 +5123,7 @@ static ssize_t pci_resource_alignment_store(struct bus_type *bus,
 	return pci_set_resource_alignment_param(buf, count);
 }
 
-BUS_ATTR(resource_alignment, 0644, pci_resource_alignment_show,
+static BUS_ATTR(resource_alignment, 0644, pci_resource_alignment_show,
 					pci_resource_alignment_store);
 
 static int __init pci_resource_alignment_sysfs_init(void)
@@ -4923,7 +5149,7 @@ int pci_get_new_domain_nr(void)
 }
 
 #ifdef CONFIG_PCI_DOMAINS_GENERIC
-void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent)
+static int of_pci_bus_find_domain_nr(struct device *parent)
 {
 	static int use_dt_domains = -1;
 	int domain = -1;
@@ -4967,7 +5193,13 @@ void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent)
 		domain = -1;
 	}
 
-	bus->domain_nr = domain;
+	return domain;
+}
+
+int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent)
+{
+	return acpi_disabled ? of_pci_bus_find_domain_nr(parent) :
+			       acpi_pci_bus_find_domain_nr(bus);
 }
 #endif
 #endif
@@ -5021,6 +5253,11 @@ static int __init pci_setup(char *str)
 				pci_hotplug_io_size = memparse(str + 9, &str);
 			} else if (!strncmp(str, "hpmemsize=", 10)) {
 				pci_hotplug_mem_size = memparse(str + 10, &str);
+			} else if (!strncmp(str, "hpbussize=", 10)) {
+				pci_hotplug_bus_size =
+					simple_strtoul(str + 10, &str, 0);
+				if (pci_hotplug_bus_size > 0xff)
+					pci_hotplug_bus_size = DEFAULT_HOTPLUG_BUS_SIZE;
 			} else if (!strncmp(str, "pcie_bus_tune_off", 17)) {
 				pcie_bus_config = PCIE_BUS_TUNE_OFF;
 			} else if (!strncmp(str, "pcie_bus_safe", 13)) {
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index a814bbb80fcb..9730c474b016 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -82,6 +82,8 @@ void pci_pm_init(struct pci_dev *dev);
 void pci_ea_init(struct pci_dev *dev);
 void pci_allocate_cap_save_buffers(struct pci_dev *dev);
 void pci_free_cap_save_buffers(struct pci_dev *dev);
+void pci_bridge_d3_device_changed(struct pci_dev *dev);
+void pci_bridge_d3_device_removed(struct pci_dev *dev);
 
 static inline void pci_wakeup_event(struct pci_dev *dev)
 {
@@ -94,6 +96,15 @@ static inline bool pci_has_subordinate(struct pci_dev *pci_dev)
 	return !!(pci_dev->subordinate);
 }
 
+static inline bool pci_power_manageable(struct pci_dev *pci_dev)
+{
+	/*
+	 * Currently we allow normal PCI devices and PCI bridges transition
+	 * into D3 if their bridge_d3 is set.
+	 */
+	return !pci_has_subordinate(pci_dev) || pci_dev->bridge_d3;
+}
+
 struct pci_vpd_ops {
 	ssize_t (*read)(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
 	ssize_t (*write)(struct pci_dev *dev, loff_t pos, size_t count, const void *buf);
diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig
index 22ca6412bd15..7fcea75afa4c 100644
--- a/drivers/pci/pcie/Kconfig
+++ b/drivers/pci/pcie/Kconfig
@@ -83,7 +83,7 @@ config PCIE_PME
 	depends on PCIEPORTBUS && PM
 
 config PCIE_DPC
-	tristate "PCIe Downstream Port Containment support"
+	bool "PCIe Downstream Port Containment support"
 	depends on PCIEPORTBUS
 	default n
 	help
@@ -92,6 +92,3 @@ config PCIE_DPC
 	  will be handled by the DPC driver.  If your system doesn't
 	  have this capability or you do not want to use this feature,
 	  it is safe to answer N.
-
-	  To compile this driver as a module, choose M here: the module
-	  will be called pcie-dpc.
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 2dfe7fdb77e7..0ec649d961d7 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -139,7 +139,7 @@ static void pcie_set_clkpm_nocheck(struct pcie_link_state *link, int enable)
 static void pcie_set_clkpm(struct pcie_link_state *link, int enable)
 {
 	/* Don't enable Clock PM if the link is not Clock PM capable */
-	if (!link->clkpm_capable && enable)
+	if (!link->clkpm_capable)
 		enable = 0;
 	/* Need nothing if the specified equals to current state */
 	if (link->clkpm_enabled == enable)
diff --git a/drivers/pci/pcie/pcie-dpc.c b/drivers/pci/pcie/pcie-dpc.c
index ab552f1bc08f..250f87861786 100644
--- a/drivers/pci/pcie/pcie-dpc.c
+++ b/drivers/pci/pcie/pcie-dpc.c
@@ -15,8 +15,8 @@
 
 struct dpc_dev {
 	struct pcie_device	*dev;
-	struct work_struct 	work;
-	int 			cap_pos;
+	struct work_struct	work;
+	int			cap_pos;
 };
 
 static void dpc_wait_link_inactive(struct pci_dev *pdev)
@@ -89,7 +89,7 @@ static int dpc_probe(struct pcie_device *dev)
 	int status;
 	u16 ctl, cap;
 
-	dpc = kzalloc(sizeof(*dpc), GFP_KERNEL);
+	dpc = devm_kzalloc(&dev->device, sizeof(*dpc), GFP_KERNEL);
 	if (!dpc)
 		return -ENOMEM;
 
@@ -98,11 +98,12 @@ static int dpc_probe(struct pcie_device *dev)
 	INIT_WORK(&dpc->work, interrupt_event_handler);
 	set_service_data(dev, dpc);
 
-	status = request_irq(dev->irq, dpc_irq, IRQF_SHARED, "pcie-dpc", dpc);
+	status = devm_request_irq(&dev->device, dev->irq, dpc_irq, IRQF_SHARED,
+				  "pcie-dpc", dpc);
 	if (status) {
 		dev_warn(&dev->device, "request IRQ%d failed: %d\n", dev->irq,
 			 status);
-		goto out;
+		return status;
 	}
 
 	pci_read_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CAP, &cap);
@@ -117,9 +118,6 @@ static int dpc_probe(struct pcie_device *dev)
 		FLAG(cap, PCI_EXP_DPC_CAP_SW_TRIGGER), (cap >> 8) & 0xf,
 		FLAG(cap, PCI_EXP_DPC_CAP_DL_ACTIVE));
 	return status;
- out:
-	kfree(dpc);
-	return status;
 }
 
 static void dpc_remove(struct pcie_device *dev)
@@ -131,14 +129,11 @@ static void dpc_remove(struct pcie_device *dev)
 	pci_read_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CTL, &ctl);
 	ctl &= ~(PCI_EXP_DPC_CTL_EN_NONFATAL | PCI_EXP_DPC_CTL_INT_EN);
 	pci_write_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CTL, ctl);
-
-	free_irq(dev->irq, dpc);
-	kfree(dpc);
 }
 
 static struct pcie_port_service_driver dpcdriver = {
 	.name		= "dpc",
-	.port_type	= PCI_EXP_TYPE_ROOT_PORT | PCI_EXP_TYPE_DOWNSTREAM,
+	.port_type	= PCIE_ANY_PORT,
 	.service	= PCIE_PORT_SERVICE_DPC,
 	.probe		= dpc_probe,
 	.remove		= dpc_remove,
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 32d4d0a3d20e..e9270b4026f3 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/pm.h>
+#include <linux/pm_runtime.h>
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/pcieport_if.h>
@@ -342,6 +343,8 @@ static int pcie_device_init(struct pci_dev *pdev, int service, int irq)
 		return retval;
 	}
 
+	pm_runtime_no_callbacks(device);
+
 	return 0;
 }
 
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index be35da2e105e..70d7ad8c6d17 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -93,6 +93,26 @@ static int pcie_port_resume_noirq(struct device *dev)
 	return 0;
 }
 
+static int pcie_port_runtime_suspend(struct device *dev)
+{
+	return to_pci_dev(dev)->bridge_d3 ? 0 : -EBUSY;
+}
+
+static int pcie_port_runtime_resume(struct device *dev)
+{
+	return 0;
+}
+
+static int pcie_port_runtime_idle(struct device *dev)
+{
+	/*
+	 * Assume the PCI core has set bridge_d3 whenever it thinks the port
+	 * should be good to go to D3.  Everything else, including moving
+	 * the port to D3, is handled by the PCI core.
+	 */
+	return to_pci_dev(dev)->bridge_d3 ? 0 : -EBUSY;
+}
+
 static const struct dev_pm_ops pcie_portdrv_pm_ops = {
 	.suspend	= pcie_port_device_suspend,
 	.resume		= pcie_port_device_resume,
@@ -101,6 +121,9 @@ static const struct dev_pm_ops pcie_portdrv_pm_ops = {
 	.poweroff	= pcie_port_device_suspend,
 	.restore	= pcie_port_device_resume,
 	.resume_noirq	= pcie_port_resume_noirq,
+	.runtime_suspend = pcie_port_runtime_suspend,
+	.runtime_resume	= pcie_port_runtime_resume,
+	.runtime_idle	= pcie_port_runtime_idle,
 };
 
 #define PCIE_PORTDRV_PM_OPS	(&pcie_portdrv_pm_ops)
@@ -134,16 +157,39 @@ static int pcie_portdrv_probe(struct pci_dev *dev,
 		return status;
 
 	pci_save_state(dev);
+
 	/*
-	 * D3cold may not work properly on some PCIe port, so disable
-	 * it by default.
+	 * Prevent runtime PM if the port is advertising support for PCIe
+	 * hotplug.  Otherwise the BIOS hotplug SMI code might not be able
+	 * to enumerate devices behind this port properly (the port is
+	 * powered down preventing all config space accesses to the
+	 * subordinate devices).  We can't be sure for native PCIe hotplug
+	 * either so prevent that as well.
 	 */
-	dev->d3cold_allowed = false;
+	if (!dev->is_hotplug_bridge) {
+		/*
+		 * Keep the port resumed 100ms to make sure things like
+		 * config space accesses from userspace (lspci) will not
+		 * cause the port to repeatedly suspend and resume.
+		 */
+		pm_runtime_set_autosuspend_delay(&dev->dev, 100);
+		pm_runtime_use_autosuspend(&dev->dev);
+		pm_runtime_mark_last_busy(&dev->dev);
+		pm_runtime_put_autosuspend(&dev->dev);
+		pm_runtime_allow(&dev->dev);
+	}
+
 	return 0;
 }
 
 static void pcie_portdrv_remove(struct pci_dev *dev)
 {
+	if (!dev->is_hotplug_bridge) {
+		pm_runtime_forbid(&dev->dev);
+		pm_runtime_get_noresume(&dev->dev);
+		pm_runtime_dont_use_autosuspend(&dev->dev);
+	}
+
 	pcie_port_device_remove(dev);
 }
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 8e3ef720997d..93f280df3428 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -16,6 +16,7 @@
 #include <linux/aer.h>
 #include <linux/acpi.h>
 #include <linux/irqdomain.h>
+#include <linux/pm_runtime.h>
 #include "pci.h"
 
 #define CARDBUS_LATENCY_TIMER	176	/* secondary latency timer */
@@ -832,6 +833,12 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 	u8 primary, secondary, subordinate;
 	int broken = 0;
 
+	/*
+	 * Make sure the bridge is powered on to be able to access config
+	 * space of devices below it.
+	 */
+	pm_runtime_get_sync(&dev->dev);
+
 	pci_read_config_dword(dev, PCI_PRIMARY_BUS, &buses);
 	primary = buses & 0xFF;
 	secondary = (buses >> 8) & 0xFF;
@@ -1012,6 +1019,8 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 out:
 	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bctl);
 
+	pm_runtime_put(&dev->dev);
+
 	return max;
 }
 EXPORT_SYMBOL(pci_scan_bridge);
@@ -2077,6 +2086,15 @@ unsigned int pci_scan_child_bus(struct pci_bus *bus)
 		}
 
 	/*
+	 * Make sure a hotplug bridge has at least the minimum requested
+	 * number of buses.
+	 */
+	if (bus->self && bus->self->is_hotplug_bridge && pci_hotplug_bus_size) {
+		if (max - bus->busn_res.start < pci_hotplug_bus_size - 1)
+			max = bus->busn_res.start + pci_hotplug_bus_size - 1;
+	}
+
+	/*
 	 * We've scanned the bus and so we know all about what's on
 	 * the other side of any bridges that may be on this bus plus
 	 * any devices.
@@ -2127,7 +2145,9 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 	b->sysdata = sysdata;
 	b->ops = ops;
 	b->number = b->busn_res.start = bus;
-	pci_bus_assign_domain_nr(b, parent);
+#ifdef CONFIG_PCI_DOMAINS_GENERIC
+	b->domain_nr = pci_bus_find_domain_nr(b, parent);
+#endif
 	b2 = pci_find_bus(pci_domain_nr(b), bus);
 	if (b2) {
 		/* If we already got to this bus through a different bridge, ignore it */
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 3f155e78513f..2408abe4ee8c 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -231,7 +231,7 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct pci_dev *dev = PDE_DATA(file_inode(file));
 	struct pci_filp_private *fpriv = file->private_data;
-	int i, ret;
+	int i, ret, write_combine;
 
 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
@@ -245,9 +245,12 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 	if (i >= PCI_ROM_RESOURCE)
 		return -ENODEV;
 
+	if (fpriv->mmap_state == pci_mmap_mem)
+		write_combine = fpriv->write_combine;
+	else
+		write_combine = 0;
 	ret = pci_mmap_page_range(dev, vma,
-				  fpriv->mmap_state,
-				  fpriv->write_combine);
+				  fpriv->mmap_state, write_combine);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index ee72ebe18f4b..37ff0158e45f 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3189,13 +3189,15 @@ static void quirk_no_bus_reset(struct pci_dev *dev)
 }
 
 /*
- * Atheros AR93xx chips do not behave after a bus reset.  The device will
- * throw a Link Down error on AER-capable systems and regardless of AER,
- * config space of the device is never accessible again and typically
- * causes the system to hang or reset when access is attempted.
+ * Some Atheros AR9xxx and QCA988x chips do not behave after a bus reset.
+ * The device will throw a Link Down error on AER-capable systems and
+ * regardless of AER, config space of the device is never accessible again
+ * and typically causes the system to hang or reset when access is attempted.
  * http://www.spinics.net/lists/linux-pci/msg34797.html
  */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0030, quirk_no_bus_reset);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0032, quirk_no_bus_reset);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x003c, quirk_no_bus_reset);
 
 static void quirk_no_pm_reset(struct pci_dev *dev)
 {
@@ -3711,6 +3713,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9172,
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c59 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x917a,
 			 quirk_dma_func1_alias);
+/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c78 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9182,
+			 quirk_dma_func1_alias);
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c46 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0,
 			 quirk_dma_func1_alias);
@@ -3747,6 +3752,9 @@ static const struct pci_device_id fixed_dma_alias_tbl[] = {
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x0285,
 			 PCI_VENDOR_ID_ADAPTEC2, 0x02bb), /* Adaptec 3405 */
 	  .driver_data = PCI_DEVFN(1, 0) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x0285,
+			 PCI_VENDOR_ID_ADAPTEC2, 0x02bc), /* Adaptec 3805 */
+	  .driver_data = PCI_DEVFN(1, 0) },
 	{ 0 }
 };
 
@@ -4087,6 +4095,7 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_AMD, 0x7809, pci_quirk_amd_sb_acs },
 	{ PCI_VENDOR_ID_SOLARFLARE, 0x0903, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_SOLARFLARE, 0x0923, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_SOLARFLARE, 0x0A03, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_INTEL, 0x10C6, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_INTEL, 0x10DB, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_INTEL, 0x10DD, pci_quirk_mf_endpoint_acs },
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 8982026637d5..d1ef7acf6930 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -96,6 +96,8 @@ static void pci_remove_bus_device(struct pci_dev *dev)
 		dev->subordinate = NULL;
 	}
 
+	pci_bridge_d3_device_removed(dev);
+
 	pci_destroy_dev(dev);
 }
 
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 55641a39a3e9..c74059e10a6d 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -695,11 +695,16 @@ static void __pci_setup_bridge(struct pci_bus *bus, unsigned long type)
 	pci_write_config_word(bridge, PCI_BRIDGE_CONTROL, bus->bridge_ctl);
 }
 
+void __weak pcibios_setup_bridge(struct pci_bus *bus, unsigned long type)
+{
+}
+
 void pci_setup_bridge(struct pci_bus *bus)
 {
 	unsigned long type = IORESOURCE_IO | IORESOURCE_MEM |
 				  IORESOURCE_PREFETCH;
 
+	pcibios_setup_bridge(bus, type);
 	__pci_setup_bridge(bus, type);
 }
 
@@ -1423,6 +1428,74 @@ void pci_bus_assign_resources(const struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pci_bus_assign_resources);
 
+static void pci_claim_device_resources(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) {
+		struct resource *r = &dev->resource[i];
+
+		if (!r->flags || r->parent)
+			continue;
+
+		pci_claim_resource(dev, i);
+	}
+}
+
+static void pci_claim_bridge_resources(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++) {
+		struct resource *r = &dev->resource[i];
+
+		if (!r->flags || r->parent)
+			continue;
+
+		pci_claim_bridge_resource(dev, i);
+	}
+}
+
+static void pci_bus_allocate_dev_resources(struct pci_bus *b)
+{
+	struct pci_dev *dev;
+	struct pci_bus *child;
+
+	list_for_each_entry(dev, &b->devices, bus_list) {
+		pci_claim_device_resources(dev);
+
+		child = dev->subordinate;
+		if (child)
+			pci_bus_allocate_dev_resources(child);
+	}
+}
+
+static void pci_bus_allocate_resources(struct pci_bus *b)
+{
+	struct pci_bus *child;
+
+	/*
+	 * Carry out a depth-first search on the PCI bus
+	 * tree to allocate bridge apertures. Read the
+	 * programmed bridge bases and recursively claim
+	 * the respective bridge resources.
+	 */
+	if (b->self) {
+		pci_read_bridge_bases(b);
+		pci_claim_bridge_resources(b->self);
+	}
+
+	list_for_each_entry(child, &b->children, node)
+		pci_bus_allocate_resources(child);
+}
+
+void pci_bus_claim_resources(struct pci_bus *b)
+{
+	pci_bus_allocate_resources(b);
+	pci_bus_allocate_dev_resources(b);
+}
+EXPORT_SYMBOL(pci_bus_claim_resources);
+
 static void __pci_bridge_assign_resources(const struct pci_dev *bridge,
 					  struct list_head *add_head,
 					  struct list_head *fail_head)
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 5f70fee59a94..d6ff5e82377d 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -1086,7 +1086,7 @@ out:
 	return err;
 }
 
-static void __init_refok pcifront_backend_changed(struct xenbus_device *xdev,
+static void __ref pcifront_backend_changed(struct xenbus_device *xdev,
 						  enum xenbus_state be_state)
 {
 	struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
diff --git a/drivers/phy/phy-rockchip-emmc.c b/drivers/phy/phy-rockchip-emmc.c
index 6ebcf3e41c46..fd57345ffed2 100644
--- a/drivers/phy/phy-rockchip-emmc.c
+++ b/drivers/phy/phy-rockchip-emmc.c
@@ -14,6 +14,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
@@ -31,42 +32,64 @@
 		((val) << (shift) | (mask) << ((shift) + 16))
 
 /* Register definition */
-#define GRF_EMMCPHY_CON0	0x0
-#define GRF_EMMCPHY_CON1	0x4
-#define GRF_EMMCPHY_CON2	0x8
-#define GRF_EMMCPHY_CON3	0xc
-#define GRF_EMMCPHY_CON4	0x10
-#define GRF_EMMCPHY_CON5	0x14
-#define GRF_EMMCPHY_CON6	0x18
-#define GRF_EMMCPHY_STATUS	0x20
-
-#define PHYCTRL_PDB_MASK	0x1
-#define PHYCTRL_PDB_SHIFT	0x0
-#define PHYCTRL_PDB_PWR_ON	0x1
-#define PHYCTRL_PDB_PWR_OFF	0x0
-#define PHYCTRL_ENDLL_MASK	0x1
-#define PHYCTRL_ENDLL_SHIFT     0x1
-#define PHYCTRL_ENDLL_ENABLE	0x1
-#define PHYCTRL_ENDLL_DISABLE	0x0
-#define PHYCTRL_CALDONE_MASK	0x1
-#define PHYCTRL_CALDONE_SHIFT   0x6
-#define PHYCTRL_CALDONE_DONE	0x1
-#define PHYCTRL_CALDONE_GOING	0x0
-#define PHYCTRL_DLLRDY_MASK	0x1
-#define PHYCTRL_DLLRDY_SHIFT	0x5
-#define PHYCTRL_DLLRDY_DONE	0x1
-#define PHYCTRL_DLLRDY_GOING	0x0
+#define GRF_EMMCPHY_CON0		0x0
+#define GRF_EMMCPHY_CON1		0x4
+#define GRF_EMMCPHY_CON2		0x8
+#define GRF_EMMCPHY_CON3		0xc
+#define GRF_EMMCPHY_CON4		0x10
+#define GRF_EMMCPHY_CON5		0x14
+#define GRF_EMMCPHY_CON6		0x18
+#define GRF_EMMCPHY_STATUS		0x20
+
+#define PHYCTRL_PDB_MASK		0x1
+#define PHYCTRL_PDB_SHIFT		0x0
+#define PHYCTRL_PDB_PWR_ON		0x1
+#define PHYCTRL_PDB_PWR_OFF		0x0
+#define PHYCTRL_ENDLL_MASK		0x1
+#define PHYCTRL_ENDLL_SHIFT		0x1
+#define PHYCTRL_ENDLL_ENABLE		0x1
+#define PHYCTRL_ENDLL_DISABLE		0x0
+#define PHYCTRL_CALDONE_MASK		0x1
+#define PHYCTRL_CALDONE_SHIFT		0x6
+#define PHYCTRL_CALDONE_DONE		0x1
+#define PHYCTRL_CALDONE_GOING		0x0
+#define PHYCTRL_DLLRDY_MASK		0x1
+#define PHYCTRL_DLLRDY_SHIFT		0x5
+#define PHYCTRL_DLLRDY_DONE		0x1
+#define PHYCTRL_DLLRDY_GOING		0x0
+#define PHYCTRL_FREQSEL_200M		0x0
+#define PHYCTRL_FREQSEL_50M		0x1
+#define PHYCTRL_FREQSEL_100M		0x2
+#define PHYCTRL_FREQSEL_150M		0x3
+#define PHYCTRL_FREQSEL_MASK		0x3
+#define PHYCTRL_FREQSEL_SHIFT		0xc
+#define PHYCTRL_DR_MASK			0x7
+#define PHYCTRL_DR_SHIFT		0x4
+#define PHYCTRL_DR_50OHM		0x0
+#define PHYCTRL_DR_33OHM		0x1
+#define PHYCTRL_DR_66OHM		0x2
+#define PHYCTRL_DR_100OHM		0x3
+#define PHYCTRL_DR_40OHM		0x4
+#define PHYCTRL_OTAPDLYENA		0x1
+#define PHYCTRL_OTAPDLYENA_MASK		0x1
+#define PHYCTRL_OTAPDLYENA_SHIFT	0xb
+#define PHYCTRL_OTAPDLYSEL_MASK		0xf
+#define PHYCTRL_OTAPDLYSEL_SHIFT	0x7
 
 struct rockchip_emmc_phy {
 	unsigned int	reg_offset;
 	struct regmap	*reg_base;
+	struct clk	*emmcclk;
 };
 
-static int rockchip_emmc_phy_power(struct rockchip_emmc_phy *rk_phy,
-				   bool on_off)
+static int rockchip_emmc_phy_power(struct phy *phy, bool on_off)
 {
+	struct rockchip_emmc_phy *rk_phy = phy_get_drvdata(phy);
 	unsigned int caldone;
 	unsigned int dllrdy;
+	unsigned int freqsel = PHYCTRL_FREQSEL_200M;
+	unsigned long rate;
+	unsigned long timeout;
 
 	/*
 	 * Keep phyctrl_pdb and phyctrl_endll low to allow
@@ -87,6 +110,43 @@ static int rockchip_emmc_phy_power(struct rockchip_emmc_phy *rk_phy,
 	if (on_off == PHYCTRL_PDB_PWR_OFF)
 		return 0;
 
+	rate = clk_get_rate(rk_phy->emmcclk);
+
+	if (rate != 0) {
+		unsigned long ideal_rate;
+		unsigned long diff;
+
+		switch (rate) {
+		case 1 ... 74999999:
+			ideal_rate = 50000000;
+			freqsel = PHYCTRL_FREQSEL_50M;
+			break;
+		case 75000000 ... 124999999:
+			ideal_rate = 100000000;
+			freqsel = PHYCTRL_FREQSEL_100M;
+			break;
+		case 125000000 ... 174999999:
+			ideal_rate = 150000000;
+			freqsel = PHYCTRL_FREQSEL_150M;
+			break;
+		default:
+			ideal_rate = 200000000;
+			break;
+		};
+
+		diff = (rate > ideal_rate) ?
+			rate - ideal_rate : ideal_rate - rate;
+
+		/*
+		 * In order for tuning delays to be accurate we need to be
+		 * pretty spot on for the DLL range, so warn if we're too
+		 * far off.  Also warn if we're above the 200 MHz max.  Don't
+		 * warn for really slow rates since we won't be tuning then.
+		 */
+		if ((rate > 50000000 && diff > 15000000) || (rate > 200000000))
+			dev_warn(&phy->dev, "Unsupported rate: %lu\n", rate);
+	}
+
 	/*
 	 * According to the user manual, calpad calibration
 	 * cycle takes more than 2us without the minimal recommended
@@ -113,20 +173,62 @@ static int rockchip_emmc_phy_power(struct rockchip_emmc_phy *rk_phy,
 		return -ETIMEDOUT;
 	}
 
+	/* Set the frequency of the DLL operation */
+	regmap_write(rk_phy->reg_base,
+		     rk_phy->reg_offset + GRF_EMMCPHY_CON0,
+		     HIWORD_UPDATE(freqsel, PHYCTRL_FREQSEL_MASK,
+				   PHYCTRL_FREQSEL_SHIFT));
+
+	/* Turn on the DLL */
 	regmap_write(rk_phy->reg_base,
 		     rk_phy->reg_offset + GRF_EMMCPHY_CON6,
 		     HIWORD_UPDATE(PHYCTRL_ENDLL_ENABLE,
 				   PHYCTRL_ENDLL_MASK,
 				   PHYCTRL_ENDLL_SHIFT));
+
 	/*
-	 * After enable analog DLL circuits, we need extra 10.2us
-	 * for dll to be ready for work.
+	 * We turned on the DLL even though the rate was 0 because we the
+	 * clock might be turned on later.  ...but we can't wait for the DLL
+	 * to lock when the rate is 0 because it will never lock with no
+	 * input clock.
+	 *
+	 * Technically we should be checking the lock later when the clock
+	 * is turned on, but for now we won't.
 	 */
-	udelay(11);
-	regmap_read(rk_phy->reg_base,
-		    rk_phy->reg_offset + GRF_EMMCPHY_STATUS,
-		    &dllrdy);
-	dllrdy = (dllrdy >> PHYCTRL_DLLRDY_SHIFT) & PHYCTRL_DLLRDY_MASK;
+	if (rate == 0)
+		return 0;
+
+	/*
+	 * After enabling analog DLL circuits docs say that we need 10.2 us if
+	 * our source clock is at 50 MHz and that lock time scales linearly
+	 * with clock speed.  If we are powering on the PHY and the card clock
+	 * is super slow (like 100 kHZ) this could take as long as 5.1 ms as
+	 * per the math: 10.2 us * (50000000 Hz / 100000 Hz) => 5.1 ms
+	 * Hopefully we won't be running at 100 kHz, but we should still make
+	 * sure we wait long enough.
+	 *
+	 * NOTE: There appear to be corner cases where the DLL seems to take
+	 * extra long to lock for reasons that aren't understood.  In some
+	 * extreme cases we've seen it take up to over 10ms (!).  We'll be
+	 * generous and give it 50ms.  We still busy wait here because:
+	 * - In most cases it should be super fast.
+	 * - This is not called lots during normal operation so it shouldn't
+	 *   be a power or performance problem to busy wait.  We expect it
+	 *   only at boot / resume.  In both cases, eMMC is probably on the
+	 *   critical path so busy waiting a little extra time should be OK.
+	 */
+	timeout = jiffies + msecs_to_jiffies(50);
+	do {
+		udelay(1);
+
+		regmap_read(rk_phy->reg_base,
+			rk_phy->reg_offset + GRF_EMMCPHY_STATUS,
+			&dllrdy);
+		dllrdy = (dllrdy >> PHYCTRL_DLLRDY_SHIFT) & PHYCTRL_DLLRDY_MASK;
+		if (dllrdy == PHYCTRL_DLLRDY_DONE)
+			break;
+	} while (!time_after(jiffies, timeout));
+
 	if (dllrdy != PHYCTRL_DLLRDY_DONE) {
 		pr_err("rockchip_emmc_phy_power: dllrdy timeout.\n");
 		return -ETIMEDOUT;
@@ -135,33 +237,82 @@ static int rockchip_emmc_phy_power(struct rockchip_emmc_phy *rk_phy,
 	return 0;
 }
 
-static int rockchip_emmc_phy_power_off(struct phy *phy)
+static int rockchip_emmc_phy_init(struct phy *phy)
 {
 	struct rockchip_emmc_phy *rk_phy = phy_get_drvdata(phy);
 	int ret = 0;
 
-	/* Power down emmc phy analog blocks */
-	ret = rockchip_emmc_phy_power(rk_phy, PHYCTRL_PDB_PWR_OFF);
-	if (ret)
-		return ret;
+	/*
+	 * We purposely get the clock here and not in probe to avoid the
+	 * circular dependency problem.  We expect:
+	 * - PHY driver to probe
+	 * - SDHCI driver to start probe
+	 * - SDHCI driver to register it's clock
+	 * - SDHCI driver to get the PHY
+	 * - SDHCI driver to init the PHY
+	 *
+	 * The clock is optional, so upon any error we just set to NULL.
+	 *
+	 * NOTE: we don't do anything special for EPROBE_DEFER here.  Given the
+	 * above expected use case, EPROBE_DEFER isn't sensible to expect, so
+	 * it's just like any other error.
+	 */
+	rk_phy->emmcclk = clk_get(&phy->dev, "emmcclk");
+	if (IS_ERR(rk_phy->emmcclk)) {
+		dev_dbg(&phy->dev, "Error getting emmcclk: %d\n", ret);
+		rk_phy->emmcclk = NULL;
+	}
+
+	return ret;
+}
+
+static int rockchip_emmc_phy_exit(struct phy *phy)
+{
+	struct rockchip_emmc_phy *rk_phy = phy_get_drvdata(phy);
+
+	clk_put(rk_phy->emmcclk);
 
 	return 0;
 }
 
+static int rockchip_emmc_phy_power_off(struct phy *phy)
+{
+	/* Power down emmc phy analog blocks */
+	return rockchip_emmc_phy_power(phy, PHYCTRL_PDB_PWR_OFF);
+}
+
 static int rockchip_emmc_phy_power_on(struct phy *phy)
 {
 	struct rockchip_emmc_phy *rk_phy = phy_get_drvdata(phy);
-	int ret = 0;
 
-	/* Power up emmc phy analog blocks */
-	ret = rockchip_emmc_phy_power(rk_phy, PHYCTRL_PDB_PWR_ON);
-	if (ret)
-		return ret;
+	/* Drive impedance: 50 Ohm */
+	regmap_write(rk_phy->reg_base,
+		     rk_phy->reg_offset + GRF_EMMCPHY_CON6,
+		     HIWORD_UPDATE(PHYCTRL_DR_50OHM,
+				   PHYCTRL_DR_MASK,
+				   PHYCTRL_DR_SHIFT));
 
-	return 0;
+	/* Output tap delay: enable */
+	regmap_write(rk_phy->reg_base,
+		     rk_phy->reg_offset + GRF_EMMCPHY_CON0,
+		     HIWORD_UPDATE(PHYCTRL_OTAPDLYENA,
+				   PHYCTRL_OTAPDLYENA_MASK,
+				   PHYCTRL_OTAPDLYENA_SHIFT));
+
+	/* Output tap delay */
+	regmap_write(rk_phy->reg_base,
+		     rk_phy->reg_offset + GRF_EMMCPHY_CON0,
+		     HIWORD_UPDATE(4,
+				   PHYCTRL_OTAPDLYSEL_MASK,
+				   PHYCTRL_OTAPDLYSEL_SHIFT));
+
+	/* Power up emmc phy analog blocks */
+	return rockchip_emmc_phy_power(phy, PHYCTRL_PDB_PWR_ON);
 }
 
 static const struct phy_ops ops = {
+	.init		= rockchip_emmc_phy_init,
+	.exit		= rockchip_emmc_phy_exit,
 	.power_on	= rockchip_emmc_phy_power_on,
 	.power_off	= rockchip_emmc_phy_power_off,
 	.owner		= THIS_MODULE,
diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c
index 4034d2d4c507..a66be137324c 100644
--- a/drivers/platform/x86/apple-gmux.c
+++ b/drivers/platform/x86/apple-gmux.c
@@ -31,19 +31,21 @@
 /**
  * DOC: Overview
  *
- * :1:  http://www.latticesemi.com/en/Products/FPGAandCPLD/LatticeXP2.aspx
- * :2:  http://www.renesas.com/products/mpumcu/h8s/h8s2100/h8s2113/index.jsp
- *
  * gmux is a microcontroller built into the MacBook Pro to support dual GPUs:
- * A {1}[Lattice XP2] on pre-retinas, a {2}[Renesas R4F2113] on retinas.
+ * A `Lattice XP2`_ on pre-retinas, a `Renesas R4F2113`_ on retinas.
  *
  * (The MacPro6,1 2013 also has a gmux, however it is unclear why since it has
  * dual GPUs but no built-in display.)
  *
  * gmux is connected to the LPC bus of the southbridge. Its I/O ports are
  * accessed differently depending on the microcontroller: Driver functions
- * to access a pre-retina gmux are infixed `_pio_`, those for a retina gmux
- * are infixed `_index_`.
+ * to access a pre-retina gmux are infixed ``_pio_``, those for a retina gmux
+ * are infixed ``_index_``.
+ *
+ * .. _Lattice XP2:
+ *     http://www.latticesemi.com/en/Products/FPGAandCPLD/LatticeXP2.aspx
+ * .. _Renesas R4F2113:
+ *     http://www.renesas.com/products/mpumcu/h8s/h8s2100/h8s2113/index.jsp
  */
 
 struct apple_gmux_data {
@@ -272,15 +274,15 @@ static bool gmux_is_indexed(struct apple_gmux_data *gmux_data)
 /**
  * DOC: Backlight control
  *
- * :3:  http://www.ti.com/lit/ds/symlink/lp8543.pdf
- * :4:  http://www.ti.com/lit/ds/symlink/lp8545.pdf
- *
  * On single GPU MacBooks, the PWM signal for the backlight is generated by
  * the GPU. On dual GPU MacBook Pros by contrast, either GPU may be suspended
  * to conserve energy. Hence the PWM signal needs to be generated by a separate
  * backlight driver which is controlled by gmux. The earliest generation
- * MBP5 2008/09 uses a {3}[TI LP8543] backlight driver. All newer models
- * use a {4}[TI LP8545].
+ * MBP5 2008/09 uses a `TI LP8543`_ backlight driver. All newer models
+ * use a `TI LP8545`_.
+ *
+ * .. _TI LP8543: http://www.ti.com/lit/ds/symlink/lp8543.pdf
+ * .. _TI LP8545: http://www.ti.com/lit/ds/symlink/lp8545.pdf
  */
 
 static int gmux_get_brightness(struct backlight_device *bd)
@@ -312,28 +314,20 @@ static const struct backlight_ops gmux_bl_ops = {
 /**
  * DOC: Graphics mux
  *
- * :5:  http://pimg-fpiw.uspto.gov/fdd/07/870/086/0.pdf
- * :6:  http://www.nxp.com/documents/data_sheet/CBTL06141.pdf
- * :7:  http://www.ti.com/lit/ds/symlink/hd3ss212.pdf
- * :8:  https://www.pericom.com/assets/Datasheets/PI3VDP12412.pdf
- * :9:  http://www.ti.com/lit/ds/symlink/sn74lv4066a.pdf
- * :10: http://pdf.datasheetarchive.com/indexerfiles/Datasheets-SW16/DSASW00308511.pdf
- * :11: http://www.ti.com/lit/ds/symlink/ts3ds10224.pdf
- *
  * On pre-retinas, the LVDS outputs of both GPUs feed into gmux which muxes
  * either of them to the panel. One of the tricks gmux has up its sleeve is
  * to lengthen the blanking interval of its output during a switch to
  * synchronize it with the GPU switched to. This allows for a flicker-free
- * switch that is imperceptible by the user ({5}[US 8,687,007 B2]).
+ * switch that is imperceptible by the user (`US 8,687,007 B2`_).
  *
  * On retinas, muxing is no longer done by gmux itself, but by a separate
  * chip which is controlled by gmux. The chip is triple sourced, it is
- * either an {6}[NXP CBTL06142], {7}[TI HD3SS212] or {8}[Pericom PI3VDP12412].
+ * either an `NXP CBTL06142`_, `TI HD3SS212`_ or `Pericom PI3VDP12412`_.
  * The panel is driven with eDP instead of LVDS since the pixel clock
  * required for retina resolution exceeds LVDS' limits.
  *
  * Pre-retinas are able to switch the panel's DDC pins separately.
- * This is handled by a {9}[TI SN74LV4066A] which is controlled by gmux.
+ * This is handled by a `TI SN74LV4066A`_ which is controlled by gmux.
  * The inactive GPU can thus probe the panel's EDID without switching over
  * the entire panel. Retinas lack this functionality as the chips used for
  * eDP muxing are incapable of switching the AUX channel separately (see
@@ -344,15 +338,15 @@ static const struct backlight_ops gmux_bl_ops = {
  *
  * The external DP port is only fully switchable on the first two unibody
  * MacBook Pro generations, MBP5 2008/09 and MBP6 2010. This is done by an
- * {6}[NXP CBTL06141] which is controlled by gmux. It's the predecessor of the
+ * `NXP CBTL06141`_ which is controlled by gmux. It's the predecessor of the
  * eDP mux on retinas, the difference being support for 2.7 versus 5.4 Gbit/s.
  *
  * The following MacBook Pro generations replaced the external DP port with a
  * combined DP/Thunderbolt port and lost the ability to switch it between GPUs,
  * connecting it either to the discrete GPU or the Thunderbolt controller.
  * Oddly enough, while the full port is no longer switchable, AUX and HPD
- * are still switchable by way of an {10}[NXP CBTL03062] (on pre-retinas
- * MBP8 2011 and MBP9 2012) or two {11}[TI TS3DS10224] (on retinas) under the
+ * are still switchable by way of an `NXP CBTL03062`_ (on pre-retinas
+ * MBP8 2011 and MBP9 2012) or two `TI TS3DS10224`_ (on retinas) under the
  * control of gmux. Since the integrated GPU is missing the main link,
  * external displays appear to it as phantoms which fail to link-train.
  *
@@ -365,10 +359,19 @@ static const struct backlight_ops gmux_bl_ops = {
  * of this feature.
  *
  * gmux' initial switch state on bootup is user configurable via the EFI
- * variable `gpu-power-prefs-fa4ce28d-b62f-4c99-9cc3-6815686e30f9` (5th byte,
+ * variable ``gpu-power-prefs-fa4ce28d-b62f-4c99-9cc3-6815686e30f9`` (5th byte,
  * 1 = IGD, 0 = DIS). Based on this setting, the EFI firmware tells gmux to
  * switch the panel and the external DP connector and allocates a framebuffer
  * for the selected GPU.
+ *
+ * .. _US 8,687,007 B2: http://pimg-fpiw.uspto.gov/fdd/07/870/086/0.pdf
+ * .. _NXP CBTL06141:   http://www.nxp.com/documents/data_sheet/CBTL06141.pdf
+ * .. _NXP CBTL06142:   http://www.nxp.com/documents/data_sheet/CBTL06141.pdf
+ * .. _TI HD3SS212:     http://www.ti.com/lit/ds/symlink/hd3ss212.pdf
+ * .. _Pericom PI3VDP12412: https://www.pericom.com/assets/Datasheets/PI3VDP12412.pdf
+ * .. _TI SN74LV4066A:  http://www.ti.com/lit/ds/symlink/sn74lv4066a.pdf
+ * .. _NXP CBTL03062:   http://pdf.datasheetarchive.com/indexerfiles/Datasheets-SW16/DSASW00308511.pdf
+ * .. _TI TS3DS10224:   http://www.ti.com/lit/ds/symlink/ts3ds10224.pdf
  */
 
 static void gmux_read_switch_state(struct apple_gmux_data *gmux_data)
diff --git a/drivers/platform/x86/intel_pmc_ipc.c b/drivers/platform/x86/intel_pmc_ipc.c
index 6f497e80c9df..b86e1bcaa055 100644
--- a/drivers/platform/x86/intel_pmc_ipc.c
+++ b/drivers/platform/x86/intel_pmc_ipc.c
@@ -85,7 +85,7 @@
  * platform device and to export resources for those functions.
  */
 #define TCO_DEVICE_NAME			"iTCO_wdt"
-#define SMI_EN_OFFSET			0x30
+#define SMI_EN_OFFSET			0x40
 #define SMI_EN_SIZE			4
 #define TCO_BASE_OFFSET			0x60
 #define TCO_REGS_SIZE			16
@@ -94,6 +94,8 @@
 #define TELEM_SSRAM_SIZE		240
 #define TELEM_PMC_SSRAM_OFFSET		0x1B00
 #define TELEM_PUNIT_SSRAM_OFFSET	0x1A00
+#define TCO_PMC_OFFSET			0x8
+#define TCO_PMC_SIZE			0x4
 
 static const int iTCO_version = 3;
 
@@ -502,7 +504,7 @@ static struct resource tco_res[] = {
 
 static struct itco_wdt_platform_data tco_info = {
 	.name = "Apollo Lake SoC",
-	.version = 3,
+	.version = 5,
 };
 
 #define TELEMETRY_RESOURCE_PUNIT_SSRAM	0
@@ -572,8 +574,8 @@ static int ipc_create_tco_device(void)
 	res->end = res->start + SMI_EN_SIZE - 1;
 
 	res = tco_res + TCO_RESOURCE_GCR_MEM;
-	res->start = ipcdev.gcr_base;
-	res->end = res->start + ipcdev.gcr_size - 1;
+	res->start = ipcdev.gcr_base + TCO_PMC_OFFSET;
+	res->end = res->start + TCO_PMC_SIZE - 1;
 
 	ret = platform_device_add_resources(pdev, tco_res, ARRAY_SIZE(tco_res));
 	if (ret) {
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index 7053abced0bc..3bfac539334b 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -46,6 +46,16 @@ config POWER_RESET_AXXIA
 
 	  Say Y if you have an Axxia family SoC.
 
+config POWER_RESET_BRCMKONA
+	bool "Broadcom Kona reset driver"
+	depends on ARM || COMPILE_TEST
+	default ARCH_BCM_MOBILE
+	help
+	  This driver provides restart support for Broadcom Kona chips.
+
+	  Say Y here if you have a Broadcom Kona-based board and you wish
+	  to have restart support.
+
 config POWER_RESET_BRCMSTB
 	bool "Broadcom STB reset driver"
 	depends on ARM || MIPS || COMPILE_TEST
diff --git a/drivers/power/reset/Makefile b/drivers/power/reset/Makefile
index d6b2560d5c4a..1be307c7fc25 100644
--- a/drivers/power/reset/Makefile
+++ b/drivers/power/reset/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_POWER_RESET_AT91_POWEROFF) += at91-poweroff.o
 obj-$(CONFIG_POWER_RESET_AT91_RESET) += at91-reset.o
 obj-$(CONFIG_POWER_RESET_AT91_SAMA5D2_SHDWC) += at91-sama5d2_shdwc.o
 obj-$(CONFIG_POWER_RESET_AXXIA) += axxia-reset.o
+obj-$(CONFIG_POWER_RESET_BRCMKONA) += brcm-kona-reset.o
 obj-$(CONFIG_POWER_RESET_BRCMSTB) += brcmstb-reboot.o
 obj-$(CONFIG_POWER_RESET_GPIO) += gpio-poweroff.o
 obj-$(CONFIG_POWER_RESET_GPIO_RESTART) += gpio-restart.o
diff --git a/drivers/power/reset/brcm-kona-reset.c b/drivers/power/reset/brcm-kona-reset.c
new file mode 100644
index 000000000000..8eaa959d8be6
--- /dev/null
+++ b/drivers/power/reset/brcm-kona-reset.c
@@ -0,0 +1,73 @@
+/*
+ * Copyright (C) 2016 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/io.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/reboot.h>
+
+#define RSTMGR_REG_WR_ACCESS_OFFSET	0
+#define RSTMGR_REG_CHIP_SOFT_RST_OFFSET	4
+
+#define RSTMGR_WR_PASSWORD		0xa5a5
+#define RSTMGR_WR_PASSWORD_SHIFT	8
+#define RSTMGR_WR_ACCESS_ENABLE		1
+
+static void __iomem *kona_reset_base;
+
+static int kona_reset_handler(struct notifier_block *this,
+				unsigned long mode, void *cmd)
+{
+	/*
+	 * A soft reset is triggered by writing a 0 to bit 0 of the soft reset
+	 * register. To write to that register we must first write the password
+	 * and the enable bit in the write access enable register.
+	 */
+	writel((RSTMGR_WR_PASSWORD << RSTMGR_WR_PASSWORD_SHIFT) |
+		RSTMGR_WR_ACCESS_ENABLE,
+		kona_reset_base + RSTMGR_REG_WR_ACCESS_OFFSET);
+	writel(0, kona_reset_base + RSTMGR_REG_CHIP_SOFT_RST_OFFSET);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block kona_reset_nb = {
+	.notifier_call = kona_reset_handler,
+	.priority = 128,
+};
+
+static int kona_reset_probe(struct platform_device *pdev)
+{
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	kona_reset_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(kona_reset_base))
+		return PTR_ERR(kona_reset_base);
+
+	return register_restart_handler(&kona_reset_nb);
+}
+
+static const struct of_device_id of_match[] = {
+	{ .compatible = "brcm,bcm21664-resetmgr" },
+	{},
+};
+
+static struct platform_driver bcm_kona_reset_driver = {
+	.probe = kona_reset_probe,
+	.driver = {
+		.name = "brcm-kona-reset",
+		.of_match_table = of_match,
+	},
+};
+
+builtin_platform_driver(bcm_kona_reset_driver);
diff --git a/drivers/power/reset/vexpress-poweroff.c b/drivers/power/reset/vexpress-poweroff.c
index 6a9bf7089373..102f95a09460 100644
--- a/drivers/power/reset/vexpress-poweroff.c
+++ b/drivers/power/reset/vexpress-poweroff.c
@@ -74,8 +74,8 @@ static ssize_t vexpress_reset_active_store(struct device *dev,
 	return err ? err : count;
 }
 
-DEVICE_ATTR(active, S_IRUGO | S_IWUSR, vexpress_reset_active_show,
-		vexpress_reset_active_store);
+static DEVICE_ATTR(active, S_IRUGO | S_IWUSR, vexpress_reset_active_show,
+		   vexpress_reset_active_store);
 
 
 enum vexpress_reset_func { FUNC_RESET, FUNC_SHUTDOWN, FUNC_REBOOT };
diff --git a/drivers/pwm/pwm-clps711x.c b/drivers/pwm/pwm-clps711x.c
index 7d335422cfda..26ec24e457b1 100644
--- a/drivers/pwm/pwm-clps711x.c
+++ b/drivers/pwm/pwm-clps711x.c
@@ -155,7 +155,7 @@ static int clps711x_pwm_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id __maybe_unused clps711x_pwm_dt_ids[] = {
-	{ .compatible = "cirrus,clps711x-pwm", },
+	{ .compatible = "cirrus,ep7209-pwm", },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, clps711x_pwm_dt_ids);
diff --git a/drivers/pwm/pwm-omap-dmtimer.c b/drivers/pwm/pwm-omap-dmtimer.c
index 3e95090cd7cf..5ad42f33e70c 100644
--- a/drivers/pwm/pwm-omap-dmtimer.c
+++ b/drivers/pwm/pwm-omap-dmtimer.c
@@ -245,7 +245,7 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev)
 	struct pwm_omap_dmtimer_chip *omap;
 	struct pwm_omap_dmtimer_pdata *pdata;
 	pwm_omap_dmtimer *dm_timer;
-	u32 prescaler;
+	u32 v;
 	int status;
 
 	pdata = dev_get_platdata(&pdev->dev);
@@ -306,10 +306,12 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev)
 	if (pm_runtime_active(&omap->dm_timer_pdev->dev))
 		omap->pdata->stop(omap->dm_timer);
 
-	/* setup dmtimer prescaler */
-	if (!of_property_read_u32(pdev->dev.of_node, "ti,prescaler",
-				&prescaler))
-		omap->pdata->set_prescaler(omap->dm_timer, prescaler);
+	if (!of_property_read_u32(pdev->dev.of_node, "ti,prescaler", &v))
+		omap->pdata->set_prescaler(omap->dm_timer, v);
+
+	/* setup dmtimer clock source */
+	if (!of_property_read_u32(pdev->dev.of_node, "ti,clock-source", &v))
+		omap->pdata->set_source(omap->dm_timer, v);
 
 	omap->chip.dev = &pdev->dev;
 	omap->chip.ops = &pwm_omap_dmtimer_ops;
diff --git a/drivers/rapidio/Kconfig b/drivers/rapidio/Kconfig
index b5a10d3c92c7..d6d2f20c4597 100644
--- a/drivers/rapidio/Kconfig
+++ b/drivers/rapidio/Kconfig
@@ -67,6 +67,15 @@ config RAPIDIO_ENUM_BASIC
 
 endchoice
 
+config RAPIDIO_CHMAN
+	tristate "RapidIO Channelized Messaging driver"
+	depends on RAPIDIO
+	help
+	  This option includes RapidIO channelized messaging driver which
+	  provides socket-like interface to allow sharing of single RapidIO
+	  messaging mailbox between multiple user-space applications.
+	  See "Documentation/rapidio/rio_cm.txt" for driver description.
+
 config RAPIDIO_MPORT_CDEV
 	tristate "RapidIO /dev mport device driver"
 	depends on RAPIDIO
diff --git a/drivers/rapidio/Makefile b/drivers/rapidio/Makefile
index 6271ada6993f..74dcea45ad49 100644
--- a/drivers/rapidio/Makefile
+++ b/drivers/rapidio/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_RAPIDIO) += rapidio.o
 rapidio-y := rio.o rio-access.o rio-driver.o rio-sysfs.o
 
 obj-$(CONFIG_RAPIDIO_ENUM_BASIC) += rio-scan.o
+obj-$(CONFIG_RAPIDIO_CHMAN)	+= rio_cm.o
 
 obj-$(CONFIG_RAPIDIO)		+= switches/
 obj-$(CONFIG_RAPIDIO)		+= devices/
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index e165b7ce29d7..436dfe871d32 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -1813,7 +1813,7 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv,
 	if (rdev->pef & RIO_PEF_EXT_FEATURES) {
 		rdev->efptr = rval & 0xffff;
 		rdev->phys_efptr = rio_mport_get_physefb(mport, 0, destid,
-							 hopcount);
+						hopcount, &rdev->phys_rmap);
 
 		rdev->em_efptr = rio_mport_get_feature(mport, 0, destid,
 						hopcount, RIO_EFB_ERR_MGMNT);
@@ -2242,7 +2242,7 @@ static void mport_mm_open(struct vm_area_struct *vma)
 {
 	struct rio_mport_mapping *map = vma->vm_private_data;
 
-rmcd_debug(MMAP, "0x%pad", &map->phys_addr);
+	rmcd_debug(MMAP, "%pad", &map->phys_addr);
 	kref_get(&map->ref);
 }
 
@@ -2250,7 +2250,7 @@ static void mport_mm_close(struct vm_area_struct *vma)
 {
 	struct rio_mport_mapping *map = vma->vm_private_data;
 
-rmcd_debug(MMAP, "0x%pad", &map->phys_addr);
+	rmcd_debug(MMAP, "%pad", &map->phys_addr);
 	mutex_lock(&map->md->buf_mutex);
 	kref_put(&map->ref, mport_release_mapping);
 	mutex_unlock(&map->md->buf_mutex);
diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c
index b5b455614f8a..32f0f014a067 100644
--- a/drivers/rapidio/devices/tsi721.c
+++ b/drivers/rapidio/devices/tsi721.c
@@ -37,11 +37,20 @@
 #include "tsi721.h"
 
 #ifdef DEBUG
-u32 dbg_level = DBG_INIT | DBG_EXIT;
+u32 dbg_level;
 module_param(dbg_level, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(dbg_level, "Debugging output level (default 0 = none)");
 #endif
 
+static int pcie_mrrs = -1;
+module_param(pcie_mrrs, int, S_IRUGO);
+MODULE_PARM_DESC(pcie_mrrs, "PCIe MRRS override value (0...5)");
+
+static u8 mbox_sel = 0x0f;
+module_param(mbox_sel, byte, S_IRUGO);
+MODULE_PARM_DESC(mbox_sel,
+		 "RIO Messaging MBOX Selection Mask (default: 0x0f = all)");
+
 static void tsi721_omsg_handler(struct tsi721_device *priv, int ch);
 static void tsi721_imsg_handler(struct tsi721_device *priv, int ch);
 
@@ -1081,7 +1090,7 @@ static void tsi721_init_pc2sr_mapping(struct tsi721_device *priv)
  * from rstart to lstart.
  */
 static int tsi721_rio_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
-		u64 rstart, u32 size, u32 flags)
+		u64 rstart, u64 size, u32 flags)
 {
 	struct tsi721_device *priv = mport->priv;
 	int i, avail = -1;
@@ -1094,6 +1103,10 @@ static int tsi721_rio_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
 	struct tsi721_ib_win_mapping *map = NULL;
 	int ret = -EBUSY;
 
+	/* Max IBW size supported by HW is 16GB */
+	if (size > 0x400000000UL)
+		return -EINVAL;
+
 	if (direct) {
 		/* Calculate minimal acceptable window size and base address */
 
@@ -1101,15 +1114,15 @@ static int tsi721_rio_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
 		ibw_start = lstart & ~(ibw_size - 1);
 
 		tsi_debug(IBW, &priv->pdev->dev,
-			"Direct (RIO_0x%llx -> PCIe_0x%pad), size=0x%x, ibw_start = 0x%llx",
+			"Direct (RIO_0x%llx -> PCIe_%pad), size=0x%llx, ibw_start = 0x%llx",
 			rstart, &lstart, size, ibw_start);
 
 		while ((lstart + size) > (ibw_start + ibw_size)) {
 			ibw_size *= 2;
 			ibw_start = lstart & ~(ibw_size - 1);
-			if (ibw_size > 0x80000000) { /* Limit max size to 2GB */
+			/* Check for crossing IBW max size 16GB */
+			if (ibw_size > 0x400000000UL)
 				return -EBUSY;
-			}
 		}
 
 		loc_start = ibw_start;
@@ -1120,7 +1133,7 @@ static int tsi721_rio_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
 
 	} else {
 		tsi_debug(IBW, &priv->pdev->dev,
-			"Translated (RIO_0x%llx -> PCIe_0x%pad), size=0x%x",
+			"Translated (RIO_0x%llx -> PCIe_%pad), size=0x%llx",
 			rstart, &lstart, size);
 
 		if (!is_power_of_2(size) || size < 0x1000 ||
@@ -1215,7 +1228,7 @@ static int tsi721_rio_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
 	priv->ibwin_cnt--;
 
 	tsi_debug(IBW, &priv->pdev->dev,
-		"Configured IBWIN%d (RIO_0x%llx -> PCIe_0x%pad), size=0x%llx",
+		"Configured IBWIN%d (RIO_0x%llx -> PCIe_%pad), size=0x%llx",
 		i, ibw_start, &loc_start, ibw_size);
 
 	return 0;
@@ -1237,7 +1250,7 @@ static void tsi721_rio_unmap_inb_mem(struct rio_mport *mport,
 	int i;
 
 	tsi_debug(IBW, &priv->pdev->dev,
-		"Unmap IBW mapped to PCIe_0x%pad", &lstart);
+		"Unmap IBW mapped to PCIe_%pad", &lstart);
 
 	/* Search for matching active inbound translation window */
 	for (i = 0; i < TSI721_IBWIN_NUM; i++) {
@@ -1877,6 +1890,11 @@ static int tsi721_open_outb_mbox(struct rio_mport *mport, void *dev_id,
 		goto out;
 	}
 
+	if ((mbox_sel & (1 << mbox)) == 0) {
+		rc = -ENODEV;
+		goto out;
+	}
+
 	priv->omsg_ring[mbox].dev_id = dev_id;
 	priv->omsg_ring[mbox].size = entries;
 	priv->omsg_ring[mbox].sts_rdptr = 0;
@@ -2161,6 +2179,11 @@ static int tsi721_open_inb_mbox(struct rio_mport *mport, void *dev_id,
 		goto out;
 	}
 
+	if ((mbox_sel & (1 << mbox)) == 0) {
+		rc = -ENODEV;
+		goto out;
+	}
+
 	/* Initialize IB Messaging Ring */
 	priv->imsg_ring[mbox].dev_id = dev_id;
 	priv->imsg_ring[mbox].size = entries;
@@ -2532,11 +2555,11 @@ static int tsi721_query_mport(struct rio_mport *mport,
 	struct tsi721_device *priv = mport->priv;
 	u32 rval;
 
-	rval = ioread32(priv->regs + (0x100 + RIO_PORT_N_ERR_STS_CSR(0)));
+	rval = ioread32(priv->regs + 0x100 + RIO_PORT_N_ERR_STS_CSR(0, 0));
 	if (rval & RIO_PORT_N_ERR_STS_PORT_OK) {
-		rval = ioread32(priv->regs + (0x100 + RIO_PORT_N_CTL2_CSR(0)));
+		rval = ioread32(priv->regs + 0x100 + RIO_PORT_N_CTL2_CSR(0, 0));
 		attr->link_speed = (rval & RIO_PORT_N_CTL2_SEL_BAUD) >> 28;
-		rval = ioread32(priv->regs + (0x100 + RIO_PORT_N_CTL_CSR(0)));
+		rval = ioread32(priv->regs + 0x100 + RIO_PORT_N_CTL_CSR(0, 0));
 		attr->link_width = (rval & RIO_PORT_N_CTL_IPW) >> 27;
 	} else
 		attr->link_speed = RIO_LINK_DOWN;
@@ -2650,9 +2673,9 @@ static int tsi721_setup_mport(struct tsi721_device *priv)
 	mport->ops = &tsi721_rio_ops;
 	mport->index = 0;
 	mport->sys_size = 0; /* small system */
-	mport->phy_type = RIO_PHY_SERIAL;
 	mport->priv = (void *)priv;
 	mport->phys_efptr = 0x100;
+	mport->phys_rmap = 1;
 	mport->dev.parent = &pdev->dev;
 	mport->dev.release = tsi721_mport_release;
 
@@ -2840,6 +2863,16 @@ static int tsi721_probe(struct pci_dev *pdev,
 	pcie_capability_clear_and_set_word(pdev, PCI_EXP_DEVCTL,
 		PCI_EXP_DEVCTL_RELAX_EN | PCI_EXP_DEVCTL_NOSNOOP_EN, 0);
 
+	/* Override PCIe Maximum Read Request Size setting if requested */
+	if (pcie_mrrs >= 0) {
+		if (pcie_mrrs <= 5)
+			pcie_capability_clear_and_set_word(pdev, PCI_EXP_DEVCTL,
+					PCI_EXP_DEVCTL_READRQ, pcie_mrrs << 12);
+		else
+			tsi_info(&pdev->dev,
+				 "Invalid MRRS override value %d", pcie_mrrs);
+	}
+
 	/* Adjust PCIe completion timeout. */
 	pcie_capability_clear_and_set_word(pdev, PCI_EXP_DEVCTL2, 0xf, 0x2);
 
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
index 5456dbddc929..5941437cbdd1 100644
--- a/drivers/rapidio/devices/tsi721.h
+++ b/drivers/rapidio/devices/tsi721.h
@@ -661,7 +661,7 @@ enum dma_rtype {
  */
 #define TSI721_DMA_CHNUM	TSI721_DMA_MAXCH
 
-#define TSI721_DMACH_MAINT	0	/* DMA channel for maint requests */
+#define TSI721_DMACH_MAINT	7	/* DMA channel for maint requests */
 #define TSI721_DMACH_MAINT_NBD	32	/* Number of BDs for maint requests */
 
 #define TSI721_DMACH_DMA	1	/* DMA channel for data transfers */
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index 155cae1e62de..e2a418598129 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -36,18 +36,26 @@
 
 #include "tsi721.h"
 
-#define TSI721_DMA_TX_QUEUE_SZ	16	/* number of transaction descriptors */
-
 #ifdef CONFIG_PCI_MSI
 static irqreturn_t tsi721_bdma_msix(int irq, void *ptr);
 #endif
 static int tsi721_submit_sg(struct tsi721_tx_desc *desc);
 
 static unsigned int dma_desc_per_channel = 128;
-module_param(dma_desc_per_channel, uint, S_IWUSR | S_IRUGO);
+module_param(dma_desc_per_channel, uint, S_IRUGO);
 MODULE_PARM_DESC(dma_desc_per_channel,
 		 "Number of DMA descriptors per channel (default: 128)");
 
+static unsigned int dma_txqueue_sz = 16;
+module_param(dma_txqueue_sz, uint, S_IRUGO);
+MODULE_PARM_DESC(dma_txqueue_sz,
+		 "DMA Transactions Queue Size (default: 16)");
+
+static u8 dma_sel = 0x7f;
+module_param(dma_sel, byte, S_IRUGO);
+MODULE_PARM_DESC(dma_sel,
+		 "DMA Channel Selection Mask (default: 0x7f = all)");
+
 static inline struct tsi721_bdma_chan *to_tsi721_chan(struct dma_chan *chan)
 {
 	return container_of(chan, struct tsi721_bdma_chan, dchan);
@@ -718,6 +726,7 @@ static dma_cookie_t tsi721_tx_submit(struct dma_async_tx_descriptor *txd)
 	cookie = dma_cookie_assign(txd);
 	desc->status = DMA_IN_PROGRESS;
 	list_add_tail(&desc->desc_node, &bdma_chan->queue);
+	tsi721_advance_work(bdma_chan, NULL);
 
 	spin_unlock_bh(&bdma_chan->lock);
 	return cookie;
@@ -732,7 +741,7 @@ static int tsi721_alloc_chan_resources(struct dma_chan *dchan)
 	tsi_debug(DMA, &dchan->dev->device, "DMAC%d", bdma_chan->id);
 
 	if (bdma_chan->bd_base)
-		return TSI721_DMA_TX_QUEUE_SZ;
+		return dma_txqueue_sz;
 
 	/* Initialize BDMA channel */
 	if (tsi721_bdma_ch_init(bdma_chan, dma_desc_per_channel)) {
@@ -742,7 +751,7 @@ static int tsi721_alloc_chan_resources(struct dma_chan *dchan)
 	}
 
 	/* Allocate queue of transaction descriptors */
-	desc = kcalloc(TSI721_DMA_TX_QUEUE_SZ, sizeof(struct tsi721_tx_desc),
+	desc = kcalloc(dma_txqueue_sz, sizeof(struct tsi721_tx_desc),
 			GFP_ATOMIC);
 	if (!desc) {
 		tsi_err(&dchan->dev->device,
@@ -754,7 +763,7 @@ static int tsi721_alloc_chan_resources(struct dma_chan *dchan)
 
 	bdma_chan->tx_desc = desc;
 
-	for (i = 0; i < TSI721_DMA_TX_QUEUE_SZ; i++) {
+	for (i = 0; i < dma_txqueue_sz; i++) {
 		dma_async_tx_descriptor_init(&desc[i].txd, dchan);
 		desc[i].txd.tx_submit = tsi721_tx_submit;
 		desc[i].txd.flags = DMA_CTRL_ACK;
@@ -766,7 +775,7 @@ static int tsi721_alloc_chan_resources(struct dma_chan *dchan)
 	bdma_chan->active = true;
 	tsi721_bdma_interrupt_enable(bdma_chan, 1);
 
-	return TSI721_DMA_TX_QUEUE_SZ;
+	return dma_txqueue_sz;
 }
 
 static void tsi721_sync_dma_irq(struct tsi721_bdma_chan *bdma_chan)
@@ -962,7 +971,7 @@ void tsi721_dma_stop_all(struct tsi721_device *priv)
 	int i;
 
 	for (i = 0; i < TSI721_DMA_MAXCH; i++) {
-		if (i != TSI721_DMACH_MAINT)
+		if ((i != TSI721_DMACH_MAINT) && (dma_sel & (1 << i)))
 			tsi721_dma_stop(&priv->bdma[i]);
 	}
 }
@@ -979,7 +988,7 @@ int tsi721_register_dma(struct tsi721_device *priv)
 	for (i = 0; i < TSI721_DMA_MAXCH; i++) {
 		struct tsi721_bdma_chan *bdma_chan = &priv->bdma[i];
 
-		if (i == TSI721_DMACH_MAINT)
+		if ((i == TSI721_DMACH_MAINT) || (dma_sel & (1 << i)) == 0)
 			continue;
 
 		bdma_chan->regs = priv->regs + TSI721_DMAC_BASE(i);
diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c
index a63a380809d1..23429bdaca84 100644
--- a/drivers/rapidio/rio-scan.c
+++ b/drivers/rapidio/rio-scan.c
@@ -49,15 +49,6 @@ struct rio_id_table {
 static int next_destid = 0;
 static int next_comptag = 1;
 
-static int rio_mport_phys_table[] = {
-	RIO_EFB_PAR_EP_ID,
-	RIO_EFB_PAR_EP_REC_ID,
-	RIO_EFB_SER_EP_ID,
-	RIO_EFB_SER_EP_REC_ID,
-	-1,
-};
-
-
 /**
  * rio_destid_alloc - Allocate next available destID for given network
  * @net: RIO network
@@ -380,10 +371,15 @@ static struct rio_dev *rio_setup_device(struct rio_net *net,
 	if (rdev->pef & RIO_PEF_EXT_FEATURES) {
 		rdev->efptr = result & 0xffff;
 		rdev->phys_efptr = rio_mport_get_physefb(port, 0, destid,
-							 hopcount);
+						hopcount, &rdev->phys_rmap);
+		pr_debug("RIO: %s Register Map %d device\n",
+			 __func__, rdev->phys_rmap);
 
 		rdev->em_efptr = rio_mport_get_feature(port, 0, destid,
 						hopcount, RIO_EFB_ERR_MGMNT);
+		if (!rdev->em_efptr)
+			rdev->em_efptr = rio_mport_get_feature(port, 0, destid,
+						hopcount, RIO_EFB_ERR_MGMNT_HS);
 	}
 
 	rio_mport_read_config_32(port, destid, hopcount, RIO_SRC_OPS_CAR,
@@ -445,7 +441,7 @@ static struct rio_dev *rio_setup_device(struct rio_net *net,
 			rio_route_clr_table(rdev, RIO_GLOBAL_TABLE, 0);
 	} else {
 		if (do_enum)
-			/*Enable Input Output Port (transmitter reviever)*/
+			/*Enable Input Output Port (transmitter receiver)*/
 			rio_enable_rx_tx_port(port, 0, destid, hopcount, 0);
 
 		dev_set_name(&rdev->dev, "%02x:e:%04x", rdev->net->id,
@@ -481,10 +477,8 @@ cleanup:
 
 /**
  * rio_sport_is_active- Tests if a switch port has an active connection.
- * @port: Master port to send transaction
- * @destid: Associated destination ID for switch
- * @hopcount: Hopcount to reach switch
- * @sport: Switch port number
+ * @rdev: RapidIO device object
+ * @sp: Switch port number
  *
  * Reads the port error status CSR for a particular switch port to
  * determine if the port has an active link.  Returns
@@ -492,31 +486,12 @@ cleanup:
  * inactive.
  */
 static int
-rio_sport_is_active(struct rio_mport *port, u16 destid, u8 hopcount, int sport)
+rio_sport_is_active(struct rio_dev *rdev, int sp)
 {
 	u32 result = 0;
-	u32 ext_ftr_ptr;
 
-	ext_ftr_ptr = rio_mport_get_efb(port, 0, destid, hopcount, 0);
-
-	while (ext_ftr_ptr) {
-		rio_mport_read_config_32(port, destid, hopcount,
-					 ext_ftr_ptr, &result);
-		result = RIO_GET_BLOCK_ID(result);
-		if ((result == RIO_EFB_SER_EP_FREE_ID) ||
-		    (result == RIO_EFB_SER_EP_FREE_ID_V13P) ||
-		    (result == RIO_EFB_SER_EP_FREC_ID))
-			break;
-
-		ext_ftr_ptr = rio_mport_get_efb(port, 0, destid, hopcount,
-						ext_ftr_ptr);
-	}
-
-	if (ext_ftr_ptr)
-		rio_mport_read_config_32(port, destid, hopcount,
-					 ext_ftr_ptr +
-					 RIO_PORT_N_ERR_STS_CSR(sport),
-					 &result);
+	rio_read_config_32(rdev, RIO_DEV_PORT_N_ERR_STS_CSR(rdev, sp),
+			   &result);
 
 	return result & RIO_PORT_N_ERR_STS_PORT_OK;
 }
@@ -655,9 +630,7 @@ static int rio_enum_peer(struct rio_net *net, struct rio_mport *port,
 
 			cur_destid = next_destid;
 
-			if (rio_sport_is_active
-			    (port, RIO_ANY_DESTID(port->sys_size), hopcount,
-			     port_num)) {
+			if (rio_sport_is_active(rdev, port_num)) {
 				pr_debug(
 				    "RIO: scanning device on port %d\n",
 				    port_num);
@@ -785,8 +758,7 @@ rio_disc_peer(struct rio_net *net, struct rio_mport *port, u16 destid,
 			if (RIO_GET_PORT_NUM(rdev->swpinfo) == port_num)
 				continue;
 
-			if (rio_sport_is_active
-			    (port, destid, hopcount, port_num)) {
+			if (rio_sport_is_active(rdev, port_num)) {
 				pr_debug(
 				    "RIO: scanning device on port %d\n",
 				    port_num);
@@ -831,21 +803,11 @@ rio_disc_peer(struct rio_net *net, struct rio_mport *port, u16 destid,
 static int rio_mport_is_active(struct rio_mport *port)
 {
 	u32 result = 0;
-	u32 ext_ftr_ptr;
-	int *entry = rio_mport_phys_table;
-
-	do {
-		if ((ext_ftr_ptr =
-		     rio_mport_get_feature(port, 1, 0, 0, *entry)))
-			break;
-	} while (*++entry >= 0);
-
-	if (ext_ftr_ptr)
-		rio_local_read_config_32(port,
-					 ext_ftr_ptr +
-					 RIO_PORT_N_ERR_STS_CSR(port->index),
-					 &result);
 
+	rio_local_read_config_32(port,
+		port->phys_efptr +
+			RIO_PORT_N_ERR_STS_CSR(port->index, port->phys_rmap),
+		&result);
 	return result & RIO_PORT_N_ERR_STS_PORT_OK;
 }
 
diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c
index 0dcaa660cba1..37042858c2db 100644
--- a/drivers/rapidio/rio.c
+++ b/drivers/rapidio/rio.c
@@ -268,6 +268,12 @@ int rio_request_inb_mbox(struct rio_mport *mport,
 		mport->inb_msg[mbox].mcback = minb;
 
 		rc = mport->ops->open_inb_mbox(mport, dev_id, mbox, entries);
+		if (rc) {
+			mport->inb_msg[mbox].mcback = NULL;
+			mport->inb_msg[mbox].res = NULL;
+			release_resource(res);
+			kfree(res);
+		}
 	} else
 		rc = -ENOMEM;
 
@@ -285,13 +291,22 @@ int rio_request_inb_mbox(struct rio_mport *mport,
  */
 int rio_release_inb_mbox(struct rio_mport *mport, int mbox)
 {
-	if (mport->ops->close_inb_mbox) {
-		mport->ops->close_inb_mbox(mport, mbox);
+	int rc;
 
-		/* Release the mailbox resource */
-		return release_resource(mport->inb_msg[mbox].res);
-	} else
-		return -ENOSYS;
+	if (!mport->ops->close_inb_mbox || !mport->inb_msg[mbox].res)
+		return -EINVAL;
+
+	mport->ops->close_inb_mbox(mport, mbox);
+	mport->inb_msg[mbox].mcback = NULL;
+
+	rc = release_resource(mport->inb_msg[mbox].res);
+	if (rc)
+		return rc;
+
+	kfree(mport->inb_msg[mbox].res);
+	mport->inb_msg[mbox].res = NULL;
+
+	return 0;
 }
 
 /**
@@ -336,6 +351,12 @@ int rio_request_outb_mbox(struct rio_mport *mport,
 		mport->outb_msg[mbox].mcback = moutb;
 
 		rc = mport->ops->open_outb_mbox(mport, dev_id, mbox, entries);
+		if (rc) {
+			mport->outb_msg[mbox].mcback = NULL;
+			mport->outb_msg[mbox].res = NULL;
+			release_resource(res);
+			kfree(res);
+		}
 	} else
 		rc = -ENOMEM;
 
@@ -353,13 +374,22 @@ int rio_request_outb_mbox(struct rio_mport *mport,
  */
 int rio_release_outb_mbox(struct rio_mport *mport, int mbox)
 {
-	if (mport->ops->close_outb_mbox) {
-		mport->ops->close_outb_mbox(mport, mbox);
+	int rc;
 
-		/* Release the mailbox resource */
-		return release_resource(mport->outb_msg[mbox].res);
-	} else
-		return -ENOSYS;
+	if (!mport->ops->close_outb_mbox || !mport->outb_msg[mbox].res)
+		return -EINVAL;
+
+	mport->ops->close_outb_mbox(mport, mbox);
+	mport->outb_msg[mbox].mcback = NULL;
+
+	rc = release_resource(mport->outb_msg[mbox].res);
+	if (rc)
+		return rc;
+
+	kfree(mport->outb_msg[mbox].res);
+	mport->outb_msg[mbox].res = NULL;
+
+	return 0;
 }
 
 /**
@@ -756,10 +786,11 @@ EXPORT_SYMBOL_GPL(rio_unmap_outb_region);
  * @local: Indicate a local master port or remote device access
  * @destid: Destination ID of the device
  * @hopcount: Number of switch hops to the device
+ * @rmap: pointer to location to store register map type info
  */
 u32
 rio_mport_get_physefb(struct rio_mport *port, int local,
-		      u16 destid, u8 hopcount)
+		      u16 destid, u8 hopcount, u32 *rmap)
 {
 	u32 ext_ftr_ptr;
 	u32 ftr_header;
@@ -777,14 +808,21 @@ rio_mport_get_physefb(struct rio_mport *port, int local,
 		ftr_header = RIO_GET_BLOCK_ID(ftr_header);
 		switch (ftr_header) {
 
-		case RIO_EFB_SER_EP_ID_V13P:
-		case RIO_EFB_SER_EP_REC_ID_V13P:
-		case RIO_EFB_SER_EP_FREE_ID_V13P:
 		case RIO_EFB_SER_EP_ID:
 		case RIO_EFB_SER_EP_REC_ID:
 		case RIO_EFB_SER_EP_FREE_ID:
-		case RIO_EFB_SER_EP_FREC_ID:
+		case RIO_EFB_SER_EP_M1_ID:
+		case RIO_EFB_SER_EP_SW_M1_ID:
+		case RIO_EFB_SER_EPF_M1_ID:
+		case RIO_EFB_SER_EPF_SW_M1_ID:
+			*rmap = 1;
+			return ext_ftr_ptr;
 
+		case RIO_EFB_SER_EP_M2_ID:
+		case RIO_EFB_SER_EP_SW_M2_ID:
+		case RIO_EFB_SER_EPF_M2_ID:
+		case RIO_EFB_SER_EPF_SW_M2_ID:
+			*rmap = 2;
 			return ext_ftr_ptr;
 
 		default:
@@ -843,16 +881,16 @@ int rio_set_port_lockout(struct rio_dev *rdev, u32 pnum, int lock)
 	u32 regval;
 
 	rio_read_config_32(rdev,
-				 rdev->phys_efptr + RIO_PORT_N_CTL_CSR(pnum),
-				 &regval);
+		RIO_DEV_PORT_N_CTL_CSR(rdev, pnum),
+		&regval);
 	if (lock)
 		regval |= RIO_PORT_N_CTL_LOCKOUT;
 	else
 		regval &= ~RIO_PORT_N_CTL_LOCKOUT;
 
 	rio_write_config_32(rdev,
-				  rdev->phys_efptr + RIO_PORT_N_CTL_CSR(pnum),
-				  regval);
+		RIO_DEV_PORT_N_CTL_CSR(rdev, pnum),
+		regval);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(rio_set_port_lockout);
@@ -876,6 +914,7 @@ int rio_enable_rx_tx_port(struct rio_mport *port,
 #ifdef CONFIG_RAPIDIO_ENABLE_RX_TX_PORTS
 	u32 regval;
 	u32 ext_ftr_ptr;
+	u32 rmap;
 
 	/*
 	* enable rx input tx output port
@@ -883,34 +922,29 @@ int rio_enable_rx_tx_port(struct rio_mport *port,
 	pr_debug("rio_enable_rx_tx_port(local = %d, destid = %d, hopcount = "
 		 "%d, port_num = %d)\n", local, destid, hopcount, port_num);
 
-	ext_ftr_ptr = rio_mport_get_physefb(port, local, destid, hopcount);
+	ext_ftr_ptr = rio_mport_get_physefb(port, local, destid,
+					    hopcount, &rmap);
 
 	if (local) {
-		rio_local_read_config_32(port, ext_ftr_ptr +
-				RIO_PORT_N_CTL_CSR(0),
+		rio_local_read_config_32(port,
+				ext_ftr_ptr + RIO_PORT_N_CTL_CSR(0, rmap),
 				&regval);
 	} else {
 		if (rio_mport_read_config_32(port, destid, hopcount,
-		ext_ftr_ptr + RIO_PORT_N_CTL_CSR(port_num), &regval) < 0)
+			ext_ftr_ptr + RIO_PORT_N_CTL_CSR(port_num, rmap),
+				&regval) < 0)
 			return -EIO;
 	}
 
-	if (regval & RIO_PORT_N_CTL_P_TYP_SER) {
-		/* serial */
-		regval = regval | RIO_PORT_N_CTL_EN_RX_SER
-				| RIO_PORT_N_CTL_EN_TX_SER;
-	} else {
-		/* parallel */
-		regval = regval | RIO_PORT_N_CTL_EN_RX_PAR
-				| RIO_PORT_N_CTL_EN_TX_PAR;
-	}
+	regval = regval | RIO_PORT_N_CTL_EN_RX | RIO_PORT_N_CTL_EN_TX;
 
 	if (local) {
-		rio_local_write_config_32(port, ext_ftr_ptr +
-					  RIO_PORT_N_CTL_CSR(0), regval);
+		rio_local_write_config_32(port,
+			ext_ftr_ptr + RIO_PORT_N_CTL_CSR(0, rmap), regval);
 	} else {
 		if (rio_mport_write_config_32(port, destid, hopcount,
-		    ext_ftr_ptr + RIO_PORT_N_CTL_CSR(port_num), regval) < 0)
+			ext_ftr_ptr + RIO_PORT_N_CTL_CSR(port_num, rmap),
+				regval) < 0)
 			return -EIO;
 	}
 #endif
@@ -1012,14 +1046,14 @@ rio_get_input_status(struct rio_dev *rdev, int pnum, u32 *lnkresp)
 		/* Read from link maintenance response register
 		 * to clear valid bit */
 		rio_read_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_MNT_RSP_CSR(pnum),
+			RIO_DEV_PORT_N_MNT_RSP_CSR(rdev, pnum),
 			&regval);
 		udelay(50);
 	}
 
 	/* Issue Input-status command */
 	rio_write_config_32(rdev,
-		rdev->phys_efptr + RIO_PORT_N_MNT_REQ_CSR(pnum),
+		RIO_DEV_PORT_N_MNT_REQ_CSR(rdev, pnum),
 		RIO_MNT_REQ_CMD_IS);
 
 	/* Exit if the response is not expected */
@@ -1030,7 +1064,7 @@ rio_get_input_status(struct rio_dev *rdev, int pnum, u32 *lnkresp)
 	while (checkcount--) {
 		udelay(50);
 		rio_read_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_MNT_RSP_CSR(pnum),
+			RIO_DEV_PORT_N_MNT_RSP_CSR(rdev, pnum),
 			&regval);
 		if (regval & RIO_PORT_N_MNT_RSP_RVAL) {
 			*lnkresp = regval;
@@ -1046,6 +1080,13 @@ rio_get_input_status(struct rio_dev *rdev, int pnum, u32 *lnkresp)
  * @rdev: Pointer to RIO device control structure
  * @pnum: Switch port number to clear errors
  * @err_status: port error status (if 0 reads register from device)
+ *
+ * TODO: Currently this routine is not compatible with recovery process
+ * specified for idt_gen3 RapidIO switch devices. It has to be reviewed
+ * to implement universal recovery process that is compatible full range
+ * off available devices.
+ * IDT gen3 switch driver now implements HW-specific error handler that
+ * issues soft port reset to the port to reset ERR_STOP bits and ackIDs.
  */
 static int rio_clr_err_stopped(struct rio_dev *rdev, u32 pnum, u32 err_status)
 {
@@ -1055,10 +1096,10 @@ static int rio_clr_err_stopped(struct rio_dev *rdev, u32 pnum, u32 err_status)
 
 	if (err_status == 0)
 		rio_read_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_ERR_STS_CSR(pnum),
+			RIO_DEV_PORT_N_ERR_STS_CSR(rdev, pnum),
 			&err_status);
 
-	if (err_status & RIO_PORT_N_ERR_STS_PW_OUT_ES) {
+	if (err_status & RIO_PORT_N_ERR_STS_OUT_ES) {
 		pr_debug("RIO_EM: servicing Output Error-Stopped state\n");
 		/*
 		 * Send a Link-Request/Input-Status control symbol
@@ -1073,7 +1114,7 @@ static int rio_clr_err_stopped(struct rio_dev *rdev, u32 pnum, u32 err_status)
 		far_ackid = (regval & RIO_PORT_N_MNT_RSP_ASTAT) >> 5;
 		far_linkstat = regval & RIO_PORT_N_MNT_RSP_LSTAT;
 		rio_read_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_ACK_STS_CSR(pnum),
+			RIO_DEV_PORT_N_ACK_STS_CSR(rdev, pnum),
 			&regval);
 		pr_debug("RIO_EM: SP%d_ACK_STS_CSR=0x%08x\n", pnum, regval);
 		near_ackid = (regval & RIO_PORT_N_ACK_INBOUND) >> 24;
@@ -1091,43 +1132,43 @@ static int rio_clr_err_stopped(struct rio_dev *rdev, u32 pnum, u32 err_status)
 			 * far inbound.
 			 */
 			rio_write_config_32(rdev,
-				rdev->phys_efptr + RIO_PORT_N_ACK_STS_CSR(pnum),
+				RIO_DEV_PORT_N_ACK_STS_CSR(rdev, pnum),
 				(near_ackid << 24) |
 					(far_ackid << 8) | far_ackid);
 			/* Align far outstanding/outbound ackIDs with
 			 * near inbound.
 			 */
 			far_ackid++;
-			if (nextdev)
-				rio_write_config_32(nextdev,
-					nextdev->phys_efptr +
-					RIO_PORT_N_ACK_STS_CSR(RIO_GET_PORT_NUM(nextdev->swpinfo)),
-					(far_ackid << 24) |
-					(near_ackid << 8) | near_ackid);
-			else
-				pr_debug("RIO_EM: Invalid nextdev pointer (NULL)\n");
+			if (!nextdev) {
+				pr_debug("RIO_EM: nextdev pointer == NULL\n");
+				goto rd_err;
+			}
+
+			rio_write_config_32(nextdev,
+				RIO_DEV_PORT_N_ACK_STS_CSR(nextdev,
+					RIO_GET_PORT_NUM(nextdev->swpinfo)),
+				(far_ackid << 24) |
+				(near_ackid << 8) | near_ackid);
 		}
 rd_err:
-		rio_read_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_ERR_STS_CSR(pnum),
-			&err_status);
+		rio_read_config_32(rdev, RIO_DEV_PORT_N_ERR_STS_CSR(rdev, pnum),
+				   &err_status);
 		pr_debug("RIO_EM: SP%d_ERR_STS_CSR=0x%08x\n", pnum, err_status);
 	}
 
-	if ((err_status & RIO_PORT_N_ERR_STS_PW_INP_ES) && nextdev) {
+	if ((err_status & RIO_PORT_N_ERR_STS_INP_ES) && nextdev) {
 		pr_debug("RIO_EM: servicing Input Error-Stopped state\n");
 		rio_get_input_status(nextdev,
 				     RIO_GET_PORT_NUM(nextdev->swpinfo), NULL);
 		udelay(50);
 
-		rio_read_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_ERR_STS_CSR(pnum),
-			&err_status);
+		rio_read_config_32(rdev, RIO_DEV_PORT_N_ERR_STS_CSR(rdev, pnum),
+				   &err_status);
 		pr_debug("RIO_EM: SP%d_ERR_STS_CSR=0x%08x\n", pnum, err_status);
 	}
 
-	return (err_status & (RIO_PORT_N_ERR_STS_PW_OUT_ES |
-			      RIO_PORT_N_ERR_STS_PW_INP_ES)) ? 1 : 0;
+	return (err_status & (RIO_PORT_N_ERR_STS_OUT_ES |
+			      RIO_PORT_N_ERR_STS_INP_ES)) ? 1 : 0;
 }
 
 /**
@@ -1227,9 +1268,8 @@ int rio_inb_pwrite_handler(struct rio_mport *mport, union rio_pw_msg *pw_msg)
 	if (rdev->rswitch->ops && rdev->rswitch->ops->em_handle)
 		rdev->rswitch->ops->em_handle(rdev, portnum);
 
-	rio_read_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_ERR_STS_CSR(portnum),
-			&err_status);
+	rio_read_config_32(rdev, RIO_DEV_PORT_N_ERR_STS_CSR(rdev, portnum),
+			   &err_status);
 	pr_debug("RIO_PW: SP%d_ERR_STS_CSR=0x%08x\n", portnum, err_status);
 
 	if (err_status & RIO_PORT_N_ERR_STS_PORT_OK) {
@@ -1246,8 +1286,8 @@ int rio_inb_pwrite_handler(struct rio_mport *mport, union rio_pw_msg *pw_msg)
 		 * Depending on the link partner state, two attempts
 		 * may be needed for successful recovery.
 		 */
-		if (err_status & (RIO_PORT_N_ERR_STS_PW_OUT_ES |
-				  RIO_PORT_N_ERR_STS_PW_INP_ES)) {
+		if (err_status & (RIO_PORT_N_ERR_STS_OUT_ES |
+				  RIO_PORT_N_ERR_STS_INP_ES)) {
 			if (rio_clr_err_stopped(rdev, portnum, err_status))
 				rio_clr_err_stopped(rdev, portnum, 0);
 		}
@@ -1257,10 +1297,18 @@ int rio_inb_pwrite_handler(struct rio_mport *mport, union rio_pw_msg *pw_msg)
 			rdev->rswitch->port_ok &= ~(1 << portnum);
 			rio_set_port_lockout(rdev, portnum, 1);
 
+			if (rdev->phys_rmap == 1) {
 			rio_write_config_32(rdev,
-				rdev->phys_efptr +
-					RIO_PORT_N_ACK_STS_CSR(portnum),
+				RIO_DEV_PORT_N_ACK_STS_CSR(rdev, portnum),
 				RIO_PORT_N_ACK_CLEAR);
+			} else {
+				rio_write_config_32(rdev,
+					RIO_DEV_PORT_N_OB_ACK_CSR(rdev, portnum),
+					RIO_PORT_N_OB_ACK_CLEAR);
+				rio_write_config_32(rdev,
+					RIO_DEV_PORT_N_IB_ACK_CSR(rdev, portnum),
+					0);
+			}
 
 			/* Schedule Extraction Service */
 			pr_debug("RIO_PW: Device Extraction on [%s]-P%d\n",
@@ -1289,9 +1337,8 @@ int rio_inb_pwrite_handler(struct rio_mport *mport, union rio_pw_msg *pw_msg)
 	}
 
 	/* Clear remaining error bits and Port-Write Pending bit */
-	rio_write_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_ERR_STS_CSR(portnum),
-			err_status);
+	rio_write_config_32(rdev, RIO_DEV_PORT_N_ERR_STS_CSR(rdev, portnum),
+			    err_status);
 
 	return 0;
 }
@@ -1342,20 +1389,7 @@ EXPORT_SYMBOL_GPL(rio_mport_get_efb);
  * Tell if a device supports a given RapidIO capability.
  * Returns the offset of the requested extended feature
  * block within the device's RIO configuration space or
- * 0 in case the device does not support it.  Possible
- * values for @ftr:
- *
- * %RIO_EFB_PAR_EP_ID		LP/LVDS EP Devices
- *
- * %RIO_EFB_PAR_EP_REC_ID	LP/LVDS EP Recovery Devices
- *
- * %RIO_EFB_PAR_EP_FREE_ID	LP/LVDS EP Free Devices
- *
- * %RIO_EFB_SER_EP_ID		LP/Serial EP Devices
- *
- * %RIO_EFB_SER_EP_REC_ID	LP/Serial EP Recovery Devices
- *
- * %RIO_EFB_SER_EP_FREE_ID	LP/Serial EP Free Devices
+ * 0 in case the device does not support it.
  */
 u32
 rio_mport_get_feature(struct rio_mport * port, int local, u16 destid,
@@ -1848,7 +1882,9 @@ EXPORT_SYMBOL_GPL(rio_release_dma);
  * Initializes RapidIO capable DMA channel for the specified data transfer.
  * Uses DMA channel private extension to pass information related to remote
  * target RIO device.
- * Returns pointer to DMA transaction descriptor or NULL if failed.
+ *
+ * Returns: pointer to DMA transaction descriptor if successful,
+ *          error-valued pointer or NULL if failed.
  */
 struct dma_async_tx_descriptor *rio_dma_prep_xfer(struct dma_chan *dchan,
 	u16 destid, struct rio_dma_data *data,
@@ -1883,7 +1919,9 @@ EXPORT_SYMBOL_GPL(rio_dma_prep_xfer);
  * Initializes RapidIO capable DMA channel for the specified data transfer.
  * Uses DMA channel private extension to pass information related to remote
  * target RIO device.
- * Returns pointer to DMA transaction descriptor or NULL if failed.
+ *
+ * Returns: pointer to DMA transaction descriptor if successful,
+ *          error-valued pointer or NULL if failed.
  */
 struct dma_async_tx_descriptor *rio_dma_prep_slave_sg(struct rio_dev *rdev,
 	struct dma_chan *dchan, struct rio_dma_data *data,
diff --git a/drivers/rapidio/rio.h b/drivers/rapidio/rio.h
index 625d09add001..9796b3fee70d 100644
--- a/drivers/rapidio/rio.h
+++ b/drivers/rapidio/rio.h
@@ -22,7 +22,7 @@
 extern u32 rio_mport_get_feature(struct rio_mport *mport, int local, u16 destid,
 				 u8 hopcount, int ftr);
 extern u32 rio_mport_get_physefb(struct rio_mport *port, int local,
-				 u16 destid, u8 hopcount);
+				 u16 destid, u8 hopcount, u32 *rmap);
 extern u32 rio_mport_get_efb(struct rio_mport *port, int local, u16 destid,
 			     u8 hopcount, u32 from);
 extern int rio_mport_chk_dev_access(struct rio_mport *mport, u16 destid,
diff --git a/drivers/rapidio/rio_cm.c b/drivers/rapidio/rio_cm.c
new file mode 100644
index 000000000000..cecc15a880de
--- /dev/null
+++ b/drivers/rapidio/rio_cm.c
@@ -0,0 +1,2366 @@
+/*
+ * rio_cm - RapidIO Channelized Messaging Driver
+ *
+ * Copyright 2013-2016 Integrated Device Technology, Inc.
+ * Copyright (c) 2015, Prodrive Technologies
+ * Copyright (c) 2015, RapidIO Trade Association
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * THIS PROGRAM IS DISTRIBUTED IN THE HOPE THAT IT WILL BE USEFUL,
+ * BUT WITHOUT ANY WARRANTY; WITHOUT EVEN THE IMPLIED WARRANTY OF
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.  SEE THE
+ * GNU GENERAL PUBLIC LICENSE FOR MORE DETAILS.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/dma-mapping.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/rio.h>
+#include <linux/rio_drv.h>
+#include <linux/slab.h>
+#include <linux/idr.h>
+#include <linux/interrupt.h>
+#include <linux/cdev.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/reboot.h>
+#include <linux/bitops.h>
+#include <linux/printk.h>
+#include <linux/rio_cm_cdev.h>
+
+#define DRV_NAME        "rio_cm"
+#define DRV_VERSION     "1.0.0"
+#define DRV_AUTHOR      "Alexandre Bounine <alexandre.bounine@idt.com>"
+#define DRV_DESC        "RapidIO Channelized Messaging Driver"
+#define DEV_NAME	"rio_cm"
+
+/* Debug output filtering masks */
+enum {
+	DBG_NONE	= 0,
+	DBG_INIT	= BIT(0), /* driver init */
+	DBG_EXIT	= BIT(1), /* driver exit */
+	DBG_MPORT	= BIT(2), /* mport add/remove */
+	DBG_RDEV	= BIT(3), /* RapidIO device add/remove */
+	DBG_CHOP	= BIT(4), /* channel operations */
+	DBG_WAIT	= BIT(5), /* waiting for events */
+	DBG_TX		= BIT(6), /* message TX */
+	DBG_TX_EVENT	= BIT(7), /* message TX event */
+	DBG_RX_DATA	= BIT(8), /* inbound data messages */
+	DBG_RX_CMD	= BIT(9), /* inbound REQ/ACK/NACK messages */
+	DBG_ALL		= ~0,
+};
+
+#ifdef DEBUG
+#define riocm_debug(level, fmt, arg...) \
+	do { \
+		if (DBG_##level & dbg_level) \
+			pr_debug(DRV_NAME ": %s " fmt "\n", \
+				__func__, ##arg); \
+	} while (0)
+#else
+#define riocm_debug(level, fmt, arg...) \
+		no_printk(KERN_DEBUG pr_fmt(DRV_NAME fmt "\n"), ##arg)
+#endif
+
+#define riocm_warn(fmt, arg...) \
+	pr_warn(DRV_NAME ": %s WARNING " fmt "\n", __func__, ##arg)
+
+#define riocm_error(fmt, arg...) \
+	pr_err(DRV_NAME ": %s ERROR " fmt "\n", __func__, ##arg)
+
+
+static int cmbox = 1;
+module_param(cmbox, int, S_IRUGO);
+MODULE_PARM_DESC(cmbox, "RapidIO Mailbox number (default 1)");
+
+static int chstart = 256;
+module_param(chstart, int, S_IRUGO);
+MODULE_PARM_DESC(chstart,
+		 "Start channel number for dynamic allocation (default 256)");
+
+#ifdef DEBUG
+static u32 dbg_level = DBG_NONE;
+module_param(dbg_level, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(dbg_level, "Debugging output level (default 0 = none)");
+#endif
+
+MODULE_AUTHOR(DRV_AUTHOR);
+MODULE_DESCRIPTION(DRV_DESC);
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_VERSION);
+
+#define RIOCM_TX_RING_SIZE	128
+#define RIOCM_RX_RING_SIZE	128
+#define RIOCM_CONNECT_TO	3 /* connect response TO (in sec) */
+
+#define RIOCM_MAX_CHNUM		0xffff /* Use full range of u16 field */
+#define RIOCM_CHNUM_AUTO	0
+#define RIOCM_MAX_EP_COUNT	0x10000 /* Max number of endpoints */
+
+enum rio_cm_state {
+	RIO_CM_IDLE,
+	RIO_CM_CONNECT,
+	RIO_CM_CONNECTED,
+	RIO_CM_DISCONNECT,
+	RIO_CM_CHAN_BOUND,
+	RIO_CM_LISTEN,
+	RIO_CM_DESTROYING,
+};
+
+enum rio_cm_pkt_type {
+	RIO_CM_SYS	= 0xaa,
+	RIO_CM_CHAN	= 0x55,
+};
+
+enum rio_cm_chop {
+	CM_CONN_REQ,
+	CM_CONN_ACK,
+	CM_CONN_CLOSE,
+	CM_DATA_MSG,
+};
+
+struct rio_ch_base_bhdr {
+	u32 src_id;
+	u32 dst_id;
+#define RIO_HDR_LETTER_MASK 0xffff0000
+#define RIO_HDR_MBOX_MASK   0x0000ffff
+	u8  src_mbox;
+	u8  dst_mbox;
+	u8  type;
+} __attribute__((__packed__));
+
+struct rio_ch_chan_hdr {
+	struct rio_ch_base_bhdr bhdr;
+	u8 ch_op;
+	u16 dst_ch;
+	u16 src_ch;
+	u16 msg_len;
+	u16 rsrvd;
+} __attribute__((__packed__));
+
+struct tx_req {
+	struct list_head node;
+	struct rio_dev   *rdev;
+	void		 *buffer;
+	size_t		 len;
+};
+
+struct cm_dev {
+	struct list_head	list;
+	struct rio_mport	*mport;
+	void			*rx_buf[RIOCM_RX_RING_SIZE];
+	int			rx_slots;
+	struct mutex		rx_lock;
+
+	void			*tx_buf[RIOCM_TX_RING_SIZE];
+	int			tx_slot;
+	int			tx_cnt;
+	int			tx_ack_slot;
+	struct list_head	tx_reqs;
+	spinlock_t		tx_lock;
+
+	struct list_head	peers;
+	u32			npeers;
+	struct workqueue_struct *rx_wq;
+	struct work_struct	rx_work;
+};
+
+struct chan_rx_ring {
+	void	*buf[RIOCM_RX_RING_SIZE];
+	int	head;
+	int	tail;
+	int	count;
+
+	/* Tracking RX buffers reported to upper level */
+	void	*inuse[RIOCM_RX_RING_SIZE];
+	int	inuse_cnt;
+};
+
+struct rio_channel {
+	u16			id;	/* local channel ID */
+	struct kref		ref;	/* channel refcount */
+	struct file		*filp;
+	struct cm_dev		*cmdev;	/* associated CM device object */
+	struct rio_dev		*rdev;	/* remote RapidIO device */
+	enum rio_cm_state	state;
+	int			error;
+	spinlock_t		lock;
+	void			*context;
+	u32			loc_destid;	/* local destID */
+	u32			rem_destid;	/* remote destID */
+	u16			rem_channel;	/* remote channel ID */
+	struct list_head	accept_queue;
+	struct list_head	ch_node;
+	struct completion	comp;
+	struct completion	comp_close;
+	struct chan_rx_ring	rx_ring;
+};
+
+struct cm_peer {
+	struct list_head node;
+	struct rio_dev *rdev;
+};
+
+struct rio_cm_work {
+	struct work_struct work;
+	struct cm_dev *cm;
+	void *data;
+};
+
+struct conn_req {
+	struct list_head node;
+	u32 destid;	/* requester destID */
+	u16 chan;	/* requester channel ID */
+	struct cm_dev *cmdev;
+};
+
+/*
+ * A channel_dev structure represents a CM_CDEV
+ * @cdev	Character device
+ * @dev		Associated device object
+ */
+struct channel_dev {
+	struct cdev	cdev;
+	struct device	*dev;
+};
+
+static struct rio_channel *riocm_ch_alloc(u16 ch_num);
+static void riocm_ch_free(struct kref *ref);
+static int riocm_post_send(struct cm_dev *cm, struct rio_dev *rdev,
+			   void *buffer, size_t len);
+static int riocm_ch_close(struct rio_channel *ch);
+
+static DEFINE_SPINLOCK(idr_lock);
+static DEFINE_IDR(ch_idr);
+
+static LIST_HEAD(cm_dev_list);
+static DECLARE_RWSEM(rdev_sem);
+
+static struct class *dev_class;
+static unsigned int dev_major;
+static unsigned int dev_minor_base;
+static dev_t dev_number;
+static struct channel_dev riocm_cdev;
+
+#define is_msg_capable(src_ops, dst_ops)			\
+			((src_ops & RIO_SRC_OPS_DATA_MSG) &&	\
+			 (dst_ops & RIO_DST_OPS_DATA_MSG))
+#define dev_cm_capable(dev) \
+	is_msg_capable(dev->src_ops, dev->dst_ops)
+
+static int riocm_cmp(struct rio_channel *ch, enum rio_cm_state cmp)
+{
+	int ret;
+
+	spin_lock_bh(&ch->lock);
+	ret = (ch->state == cmp);
+	spin_unlock_bh(&ch->lock);
+	return ret;
+}
+
+static int riocm_cmp_exch(struct rio_channel *ch,
+			   enum rio_cm_state cmp, enum rio_cm_state exch)
+{
+	int ret;
+
+	spin_lock_bh(&ch->lock);
+	ret = (ch->state == cmp);
+	if (ret)
+		ch->state = exch;
+	spin_unlock_bh(&ch->lock);
+	return ret;
+}
+
+static enum rio_cm_state riocm_exch(struct rio_channel *ch,
+				    enum rio_cm_state exch)
+{
+	enum rio_cm_state old;
+
+	spin_lock_bh(&ch->lock);
+	old = ch->state;
+	ch->state = exch;
+	spin_unlock_bh(&ch->lock);
+	return old;
+}
+
+static struct rio_channel *riocm_get_channel(u16 nr)
+{
+	struct rio_channel *ch;
+
+	spin_lock_bh(&idr_lock);
+	ch = idr_find(&ch_idr, nr);
+	if (ch)
+		kref_get(&ch->ref);
+	spin_unlock_bh(&idr_lock);
+	return ch;
+}
+
+static void riocm_put_channel(struct rio_channel *ch)
+{
+	kref_put(&ch->ref, riocm_ch_free);
+}
+
+static void *riocm_rx_get_msg(struct cm_dev *cm)
+{
+	void *msg;
+	int i;
+
+	msg = rio_get_inb_message(cm->mport, cmbox);
+	if (msg) {
+		for (i = 0; i < RIOCM_RX_RING_SIZE; i++) {
+			if (cm->rx_buf[i] == msg) {
+				cm->rx_buf[i] = NULL;
+				cm->rx_slots++;
+				break;
+			}
+		}
+
+		if (i == RIOCM_RX_RING_SIZE)
+			riocm_warn("no record for buffer 0x%p", msg);
+	}
+
+	return msg;
+}
+
+/*
+ * riocm_rx_fill - fills a ring of receive buffers for given cm device
+ * @cm: cm_dev object
+ * @nent: max number of entries to fill
+ *
+ * Returns: none
+ */
+static void riocm_rx_fill(struct cm_dev *cm, int nent)
+{
+	int i;
+
+	if (cm->rx_slots == 0)
+		return;
+
+	for (i = 0; i < RIOCM_RX_RING_SIZE && cm->rx_slots && nent; i++) {
+		if (cm->rx_buf[i] == NULL) {
+			cm->rx_buf[i] = kmalloc(RIO_MAX_MSG_SIZE, GFP_KERNEL);
+			if (cm->rx_buf[i] == NULL)
+				break;
+			rio_add_inb_buffer(cm->mport, cmbox, cm->rx_buf[i]);
+			cm->rx_slots--;
+			nent--;
+		}
+	}
+}
+
+/*
+ * riocm_rx_free - frees all receive buffers associated with given cm device
+ * @cm: cm_dev object
+ *
+ * Returns: none
+ */
+static void riocm_rx_free(struct cm_dev *cm)
+{
+	int i;
+
+	for (i = 0; i < RIOCM_RX_RING_SIZE; i++) {
+		if (cm->rx_buf[i] != NULL) {
+			kfree(cm->rx_buf[i]);
+			cm->rx_buf[i] = NULL;
+		}
+	}
+}
+
+/*
+ * riocm_req_handler - connection request handler
+ * @cm: cm_dev object
+ * @req_data: pointer to the request packet
+ *
+ * Returns: 0 if success, or
+ *          -EINVAL if channel is not in correct state,
+ *          -ENODEV if cannot find a channel with specified ID,
+ *          -ENOMEM if unable to allocate memory to store the request
+ */
+static int riocm_req_handler(struct cm_dev *cm, void *req_data)
+{
+	struct rio_channel *ch;
+	struct conn_req *req;
+	struct rio_ch_chan_hdr *hh = req_data;
+	u16 chnum;
+
+	chnum = ntohs(hh->dst_ch);
+
+	ch = riocm_get_channel(chnum);
+
+	if (!ch)
+		return -ENODEV;
+
+	if (ch->state != RIO_CM_LISTEN) {
+		riocm_debug(RX_CMD, "channel %d is not in listen state", chnum);
+		riocm_put_channel(ch);
+		return -EINVAL;
+	}
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req) {
+		riocm_put_channel(ch);
+		return -ENOMEM;
+	}
+
+	req->destid = ntohl(hh->bhdr.src_id);
+	req->chan = ntohs(hh->src_ch);
+	req->cmdev = cm;
+
+	spin_lock_bh(&ch->lock);
+	list_add_tail(&req->node, &ch->accept_queue);
+	spin_unlock_bh(&ch->lock);
+	complete(&ch->comp);
+	riocm_put_channel(ch);
+
+	return 0;
+}
+
+/*
+ * riocm_resp_handler - response to connection request handler
+ * @resp_data: pointer to the response packet
+ *
+ * Returns: 0 if success, or
+ *          -EINVAL if channel is not in correct state,
+ *          -ENODEV if cannot find a channel with specified ID,
+ */
+static int riocm_resp_handler(void *resp_data)
+{
+	struct rio_channel *ch;
+	struct rio_ch_chan_hdr *hh = resp_data;
+	u16 chnum;
+
+	chnum = ntohs(hh->dst_ch);
+	ch = riocm_get_channel(chnum);
+	if (!ch)
+		return -ENODEV;
+
+	if (ch->state != RIO_CM_CONNECT) {
+		riocm_put_channel(ch);
+		return -EINVAL;
+	}
+
+	riocm_exch(ch, RIO_CM_CONNECTED);
+	ch->rem_channel = ntohs(hh->src_ch);
+	complete(&ch->comp);
+	riocm_put_channel(ch);
+
+	return 0;
+}
+
+/*
+ * riocm_close_handler - channel close request handler
+ * @req_data: pointer to the request packet
+ *
+ * Returns: 0 if success, or
+ *          -ENODEV if cannot find a channel with specified ID,
+ *            + error codes returned by riocm_ch_close.
+ */
+static int riocm_close_handler(void *data)
+{
+	struct rio_channel *ch;
+	struct rio_ch_chan_hdr *hh = data;
+	int ret;
+
+	riocm_debug(RX_CMD, "for ch=%d", ntohs(hh->dst_ch));
+
+	spin_lock_bh(&idr_lock);
+	ch = idr_find(&ch_idr, ntohs(hh->dst_ch));
+	if (!ch) {
+		spin_unlock_bh(&idr_lock);
+		return -ENODEV;
+	}
+	idr_remove(&ch_idr, ch->id);
+	spin_unlock_bh(&idr_lock);
+
+	riocm_exch(ch, RIO_CM_DISCONNECT);
+
+	ret = riocm_ch_close(ch);
+	if (ret)
+		riocm_debug(RX_CMD, "riocm_ch_close() returned %d", ret);
+
+	return 0;
+}
+
+/*
+ * rio_cm_handler - function that services request (non-data) packets
+ * @cm: cm_dev object
+ * @data: pointer to the packet
+ */
+static void rio_cm_handler(struct cm_dev *cm, void *data)
+{
+	struct rio_ch_chan_hdr *hdr;
+
+	if (!rio_mport_is_running(cm->mport))
+		goto out;
+
+	hdr = data;
+
+	riocm_debug(RX_CMD, "OP=%x for ch=%d from %d",
+		    hdr->ch_op, ntohs(hdr->dst_ch), ntohs(hdr->src_ch));
+
+	switch (hdr->ch_op) {
+	case CM_CONN_REQ:
+		riocm_req_handler(cm, data);
+		break;
+	case CM_CONN_ACK:
+		riocm_resp_handler(data);
+		break;
+	case CM_CONN_CLOSE:
+		riocm_close_handler(data);
+		break;
+	default:
+		riocm_error("Invalid packet header");
+		break;
+	}
+out:
+	kfree(data);
+}
+
+/*
+ * rio_rx_data_handler - received data packet handler
+ * @cm: cm_dev object
+ * @buf: data packet
+ *
+ * Returns: 0 if success, or
+ *          -ENODEV if cannot find a channel with specified ID,
+ *          -EIO if channel is not in CONNECTED state,
+ *          -ENOMEM if channel RX queue is full (packet discarded)
+ */
+static int rio_rx_data_handler(struct cm_dev *cm, void *buf)
+{
+	struct rio_ch_chan_hdr *hdr;
+	struct rio_channel *ch;
+
+	hdr = buf;
+
+	riocm_debug(RX_DATA, "for ch=%d", ntohs(hdr->dst_ch));
+
+	ch = riocm_get_channel(ntohs(hdr->dst_ch));
+	if (!ch) {
+		/* Discard data message for non-existing channel */
+		kfree(buf);
+		return -ENODEV;
+	}
+
+	/* Place pointer to the buffer into channel's RX queue */
+	spin_lock(&ch->lock);
+
+	if (ch->state != RIO_CM_CONNECTED) {
+		/* Channel is not ready to receive data, discard a packet */
+		riocm_debug(RX_DATA, "ch=%d is in wrong state=%d",
+			    ch->id, ch->state);
+		spin_unlock(&ch->lock);
+		kfree(buf);
+		riocm_put_channel(ch);
+		return -EIO;
+	}
+
+	if (ch->rx_ring.count == RIOCM_RX_RING_SIZE) {
+		/* If RX ring is full, discard a packet */
+		riocm_debug(RX_DATA, "ch=%d is full", ch->id);
+		spin_unlock(&ch->lock);
+		kfree(buf);
+		riocm_put_channel(ch);
+		return -ENOMEM;
+	}
+
+	ch->rx_ring.buf[ch->rx_ring.head] = buf;
+	ch->rx_ring.head++;
+	ch->rx_ring.count++;
+	ch->rx_ring.head %= RIOCM_RX_RING_SIZE;
+
+	complete(&ch->comp);
+
+	spin_unlock(&ch->lock);
+	riocm_put_channel(ch);
+
+	return 0;
+}
+
+/*
+ * rio_ibmsg_handler - inbound message packet handler
+ */
+static void rio_ibmsg_handler(struct work_struct *work)
+{
+	struct cm_dev *cm = container_of(work, struct cm_dev, rx_work);
+	void *data;
+	struct rio_ch_chan_hdr *hdr;
+
+	if (!rio_mport_is_running(cm->mport))
+		return;
+
+	while (1) {
+		mutex_lock(&cm->rx_lock);
+		data = riocm_rx_get_msg(cm);
+		if (data)
+			riocm_rx_fill(cm, 1);
+		mutex_unlock(&cm->rx_lock);
+
+		if (data == NULL)
+			break;
+
+		hdr = data;
+
+		if (hdr->bhdr.type != RIO_CM_CHAN) {
+			/* For now simply discard packets other than channel */
+			riocm_error("Unsupported TYPE code (0x%x). Msg dropped",
+				    hdr->bhdr.type);
+			kfree(data);
+			continue;
+		}
+
+		/* Process a channel message */
+		if (hdr->ch_op == CM_DATA_MSG)
+			rio_rx_data_handler(cm, data);
+		else
+			rio_cm_handler(cm, data);
+	}
+}
+
+static void riocm_inb_msg_event(struct rio_mport *mport, void *dev_id,
+				int mbox, int slot)
+{
+	struct cm_dev *cm = dev_id;
+
+	if (rio_mport_is_running(cm->mport) && !work_pending(&cm->rx_work))
+		queue_work(cm->rx_wq, &cm->rx_work);
+}
+
+/*
+ * rio_txcq_handler - TX completion handler
+ * @cm: cm_dev object
+ * @slot: TX queue slot
+ *
+ * TX completion handler also ensures that pending request packets are placed
+ * into transmit queue as soon as a free slot becomes available. This is done
+ * to give higher priority to request packets during high intensity data flow.
+ */
+static void rio_txcq_handler(struct cm_dev *cm, int slot)
+{
+	int ack_slot;
+
+	/* ATTN: Add TX completion notification if/when direct buffer
+	 * transfer is implemented. At this moment only correct tracking
+	 * of tx_count is important.
+	 */
+	riocm_debug(TX_EVENT, "for mport_%d slot %d tx_cnt %d",
+		    cm->mport->id, slot, cm->tx_cnt);
+
+	spin_lock(&cm->tx_lock);
+	ack_slot = cm->tx_ack_slot;
+
+	if (ack_slot == slot)
+		riocm_debug(TX_EVENT, "slot == ack_slot");
+
+	while (cm->tx_cnt && ((ack_slot != slot) ||
+	       (cm->tx_cnt == RIOCM_TX_RING_SIZE))) {
+
+		cm->tx_buf[ack_slot] = NULL;
+		++ack_slot;
+		ack_slot &= (RIOCM_TX_RING_SIZE - 1);
+		cm->tx_cnt--;
+	}
+
+	if (cm->tx_cnt < 0 || cm->tx_cnt > RIOCM_TX_RING_SIZE)
+		riocm_error("tx_cnt %d out of sync", cm->tx_cnt);
+
+	WARN_ON((cm->tx_cnt < 0) || (cm->tx_cnt > RIOCM_TX_RING_SIZE));
+
+	cm->tx_ack_slot = ack_slot;
+
+	/*
+	 * If there are pending requests, insert them into transmit queue
+	 */
+	if (!list_empty(&cm->tx_reqs) && (cm->tx_cnt < RIOCM_TX_RING_SIZE)) {
+		struct tx_req *req, *_req;
+		int rc;
+
+		list_for_each_entry_safe(req, _req, &cm->tx_reqs, node) {
+			list_del(&req->node);
+			cm->tx_buf[cm->tx_slot] = req->buffer;
+			rc = rio_add_outb_message(cm->mport, req->rdev, cmbox,
+						  req->buffer, req->len);
+			kfree(req->buffer);
+			kfree(req);
+
+			++cm->tx_cnt;
+			++cm->tx_slot;
+			cm->tx_slot &= (RIOCM_TX_RING_SIZE - 1);
+			if (cm->tx_cnt == RIOCM_TX_RING_SIZE)
+				break;
+		}
+	}
+
+	spin_unlock(&cm->tx_lock);
+}
+
+static void riocm_outb_msg_event(struct rio_mport *mport, void *dev_id,
+				 int mbox, int slot)
+{
+	struct cm_dev *cm = dev_id;
+
+	if (cm && rio_mport_is_running(cm->mport))
+		rio_txcq_handler(cm, slot);
+}
+
+static int riocm_queue_req(struct cm_dev *cm, struct rio_dev *rdev,
+			   void *buffer, size_t len)
+{
+	unsigned long flags;
+	struct tx_req *treq;
+
+	treq = kzalloc(sizeof(*treq), GFP_KERNEL);
+	if (treq == NULL)
+		return -ENOMEM;
+
+	treq->rdev = rdev;
+	treq->buffer = buffer;
+	treq->len = len;
+
+	spin_lock_irqsave(&cm->tx_lock, flags);
+	list_add_tail(&treq->node, &cm->tx_reqs);
+	spin_unlock_irqrestore(&cm->tx_lock, flags);
+	return 0;
+}
+
+/*
+ * riocm_post_send - helper function that places packet into msg TX queue
+ * @cm: cm_dev object
+ * @rdev: target RapidIO device object (required by outbound msg interface)
+ * @buffer: pointer to a packet buffer to send
+ * @len: length of data to transfer
+ * @req: request priority flag
+ *
+ * Returns: 0 if success, or error code otherwise.
+ */
+static int riocm_post_send(struct cm_dev *cm, struct rio_dev *rdev,
+			   void *buffer, size_t len)
+{
+	int rc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cm->tx_lock, flags);
+
+	if (cm->mport == NULL) {
+		rc = -ENODEV;
+		goto err_out;
+	}
+
+	if (cm->tx_cnt == RIOCM_TX_RING_SIZE) {
+		riocm_debug(TX, "Tx Queue is full");
+		rc = -EBUSY;
+		goto err_out;
+	}
+
+	cm->tx_buf[cm->tx_slot] = buffer;
+	rc = rio_add_outb_message(cm->mport, rdev, cmbox, buffer, len);
+
+	riocm_debug(TX, "Add buf@%p destid=%x tx_slot=%d tx_cnt=%d",
+		 buffer, rdev->destid, cm->tx_slot, cm->tx_cnt);
+
+	++cm->tx_cnt;
+	++cm->tx_slot;
+	cm->tx_slot &= (RIOCM_TX_RING_SIZE - 1);
+
+err_out:
+	spin_unlock_irqrestore(&cm->tx_lock, flags);
+	return rc;
+}
+
+/*
+ * riocm_ch_send - sends a data packet to a remote device
+ * @ch_id: local channel ID
+ * @buf: pointer to a data buffer to send (including CM header)
+ * @len: length of data to transfer (including CM header)
+ *
+ * ATTN: ASSUMES THAT THE HEADER SPACE IS RESERVED PART OF THE DATA PACKET
+ *
+ * Returns: 0 if success, or
+ *          -EINVAL if one or more input parameters is/are not valid,
+ *          -ENODEV if cannot find a channel with specified ID,
+ *          -EAGAIN if a channel is not in CONNECTED state,
+ *	    + error codes returned by HW send routine.
+ */
+static int riocm_ch_send(u16 ch_id, void *buf, int len)
+{
+	struct rio_channel *ch;
+	struct rio_ch_chan_hdr *hdr;
+	int ret;
+
+	if (buf == NULL || ch_id == 0 || len == 0 || len > RIO_MAX_MSG_SIZE)
+		return -EINVAL;
+
+	ch = riocm_get_channel(ch_id);
+	if (!ch) {
+		riocm_error("%s(%d) ch_%d not found", current->comm,
+			    task_pid_nr(current), ch_id);
+		return -ENODEV;
+	}
+
+	if (!riocm_cmp(ch, RIO_CM_CONNECTED)) {
+		ret = -EAGAIN;
+		goto err_out;
+	}
+
+	/*
+	 * Fill buffer header section with corresponding channel data
+	 */
+	hdr = buf;
+
+	hdr->bhdr.src_id = htonl(ch->loc_destid);
+	hdr->bhdr.dst_id = htonl(ch->rem_destid);
+	hdr->bhdr.src_mbox = cmbox;
+	hdr->bhdr.dst_mbox = cmbox;
+	hdr->bhdr.type = RIO_CM_CHAN;
+	hdr->ch_op = CM_DATA_MSG;
+	hdr->dst_ch = htons(ch->rem_channel);
+	hdr->src_ch = htons(ch->id);
+	hdr->msg_len = htons((u16)len);
+
+	/* ATTN: the function call below relies on the fact that underlying
+	 * HW-specific add_outb_message() routine copies TX data into its own
+	 * internal transfer buffer (true for all RIONET compatible mport
+	 * drivers). Must be reviewed if mport driver uses the buffer directly.
+	 */
+
+	ret = riocm_post_send(ch->cmdev, ch->rdev, buf, len);
+	if (ret)
+		riocm_debug(TX, "ch %d send_err=%d", ch->id, ret);
+err_out:
+	riocm_put_channel(ch);
+	return ret;
+}
+
+static int riocm_ch_free_rxbuf(struct rio_channel *ch, void *buf)
+{
+	int i, ret = -EINVAL;
+
+	spin_lock_bh(&ch->lock);
+
+	for (i = 0; i < RIOCM_RX_RING_SIZE; i++) {
+		if (ch->rx_ring.inuse[i] == buf) {
+			ch->rx_ring.inuse[i] = NULL;
+			ch->rx_ring.inuse_cnt--;
+			ret = 0;
+			break;
+		}
+	}
+
+	spin_unlock_bh(&ch->lock);
+
+	if (!ret)
+		kfree(buf);
+
+	return ret;
+}
+
+/*
+ * riocm_ch_receive - fetch a data packet received for the specified channel
+ * @ch: local channel ID
+ * @buf: pointer to a packet buffer
+ * @timeout: timeout to wait for incoming packet (in jiffies)
+ *
+ * Returns: 0 and valid buffer pointer if success, or NULL pointer and one of:
+ *          -EAGAIN if a channel is not in CONNECTED state,
+ *          -ENOMEM if in-use tracking queue is full,
+ *          -ETIME if wait timeout expired,
+ *	    -EINTR if wait was interrupted.
+ */
+static int riocm_ch_receive(struct rio_channel *ch, void **buf, long timeout)
+{
+	void *rxmsg = NULL;
+	int i, ret = 0;
+	long wret;
+
+	if (!riocm_cmp(ch, RIO_CM_CONNECTED)) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
+	if (ch->rx_ring.inuse_cnt == RIOCM_RX_RING_SIZE) {
+		/* If we do not have entries to track buffers given to upper
+		 * layer, reject request.
+		 */
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	wret = wait_for_completion_interruptible_timeout(&ch->comp, timeout);
+
+	riocm_debug(WAIT, "wait on %d returned %ld", ch->id, wret);
+
+	if (!wret)
+		ret = -ETIME;
+	else if (wret == -ERESTARTSYS)
+		ret = -EINTR;
+	else
+		ret = riocm_cmp(ch, RIO_CM_CONNECTED) ? 0 : -ECONNRESET;
+
+	if (ret)
+		goto out;
+
+	spin_lock_bh(&ch->lock);
+
+	rxmsg = ch->rx_ring.buf[ch->rx_ring.tail];
+	ch->rx_ring.buf[ch->rx_ring.tail] = NULL;
+	ch->rx_ring.count--;
+	ch->rx_ring.tail++;
+	ch->rx_ring.tail %= RIOCM_RX_RING_SIZE;
+	ret = -ENOMEM;
+
+	for (i = 0; i < RIOCM_RX_RING_SIZE; i++) {
+		if (ch->rx_ring.inuse[i] == NULL) {
+			ch->rx_ring.inuse[i] = rxmsg;
+			ch->rx_ring.inuse_cnt++;
+			ret = 0;
+			break;
+		}
+	}
+
+	if (ret) {
+		/* We have no entry to store pending message: drop it */
+		kfree(rxmsg);
+		rxmsg = NULL;
+	}
+
+	spin_unlock_bh(&ch->lock);
+out:
+	*buf = rxmsg;
+	return ret;
+}
+
+/*
+ * riocm_ch_connect - sends a connect request to a remote device
+ * @loc_ch: local channel ID
+ * @cm: CM device to send connect request
+ * @peer: target RapidIO device
+ * @rem_ch: remote channel ID
+ *
+ * Returns: 0 if success, or
+ *          -EINVAL if the channel is not in IDLE state,
+ *          -EAGAIN if no connection request available immediately,
+ *          -ETIME if ACK response timeout expired,
+ *          -EINTR if wait for response was interrupted.
+ */
+static int riocm_ch_connect(u16 loc_ch, struct cm_dev *cm,
+			    struct cm_peer *peer, u16 rem_ch)
+{
+	struct rio_channel *ch = NULL;
+	struct rio_ch_chan_hdr *hdr;
+	int ret;
+	long wret;
+
+	ch = riocm_get_channel(loc_ch);
+	if (!ch)
+		return -ENODEV;
+
+	if (!riocm_cmp_exch(ch, RIO_CM_IDLE, RIO_CM_CONNECT)) {
+		ret = -EINVAL;
+		goto conn_done;
+	}
+
+	ch->cmdev = cm;
+	ch->rdev = peer->rdev;
+	ch->context = NULL;
+	ch->loc_destid = cm->mport->host_deviceid;
+	ch->rem_channel = rem_ch;
+
+	/*
+	 * Send connect request to the remote RapidIO device
+	 */
+
+	hdr = kzalloc(sizeof(*hdr), GFP_KERNEL);
+	if (hdr == NULL) {
+		ret = -ENOMEM;
+		goto conn_done;
+	}
+
+	hdr->bhdr.src_id = htonl(ch->loc_destid);
+	hdr->bhdr.dst_id = htonl(peer->rdev->destid);
+	hdr->bhdr.src_mbox = cmbox;
+	hdr->bhdr.dst_mbox = cmbox;
+	hdr->bhdr.type = RIO_CM_CHAN;
+	hdr->ch_op = CM_CONN_REQ;
+	hdr->dst_ch = htons(rem_ch);
+	hdr->src_ch = htons(loc_ch);
+
+	/* ATTN: the function call below relies on the fact that underlying
+	 * HW-specific add_outb_message() routine copies TX data into its
+	 * internal transfer buffer. Must be reviewed if mport driver uses
+	 * this buffer directly.
+	 */
+	ret = riocm_post_send(cm, peer->rdev, hdr, sizeof(*hdr));
+
+	if (ret != -EBUSY) {
+		kfree(hdr);
+	} else {
+		ret = riocm_queue_req(cm, peer->rdev, hdr, sizeof(*hdr));
+		if (ret)
+			kfree(hdr);
+	}
+
+	if (ret) {
+		riocm_cmp_exch(ch, RIO_CM_CONNECT, RIO_CM_IDLE);
+		goto conn_done;
+	}
+
+	/* Wait for connect response from the remote device */
+	wret = wait_for_completion_interruptible_timeout(&ch->comp,
+							 RIOCM_CONNECT_TO * HZ);
+	riocm_debug(WAIT, "wait on %d returns %ld", ch->id, wret);
+
+	if (!wret)
+		ret = -ETIME;
+	else if (wret == -ERESTARTSYS)
+		ret = -EINTR;
+	else
+		ret = riocm_cmp(ch, RIO_CM_CONNECTED) ? 0 : -1;
+
+conn_done:
+	riocm_put_channel(ch);
+	return ret;
+}
+
+static int riocm_send_ack(struct rio_channel *ch)
+{
+	struct rio_ch_chan_hdr *hdr;
+	int ret;
+
+	hdr = kzalloc(sizeof(*hdr), GFP_KERNEL);
+	if (hdr == NULL)
+		return -ENOMEM;
+
+	hdr->bhdr.src_id = htonl(ch->loc_destid);
+	hdr->bhdr.dst_id = htonl(ch->rem_destid);
+	hdr->dst_ch = htons(ch->rem_channel);
+	hdr->src_ch = htons(ch->id);
+	hdr->bhdr.src_mbox = cmbox;
+	hdr->bhdr.dst_mbox = cmbox;
+	hdr->bhdr.type = RIO_CM_CHAN;
+	hdr->ch_op = CM_CONN_ACK;
+
+	/* ATTN: the function call below relies on the fact that underlying
+	 * add_outb_message() routine copies TX data into its internal transfer
+	 * buffer. Review if switching to direct buffer version.
+	 */
+	ret = riocm_post_send(ch->cmdev, ch->rdev, hdr, sizeof(*hdr));
+
+	if (ret == -EBUSY && !riocm_queue_req(ch->cmdev,
+					      ch->rdev, hdr, sizeof(*hdr)))
+		return 0;
+	kfree(hdr);
+
+	if (ret)
+		riocm_error("send ACK to ch_%d on %s failed (ret=%d)",
+			    ch->id, rio_name(ch->rdev), ret);
+	return ret;
+}
+
+/*
+ * riocm_ch_accept - accept incoming connection request
+ * @ch_id: channel ID
+ * @new_ch_id: local mport device
+ * @timeout: wait timeout (if 0 non-blocking call, do not wait if connection
+ *           request is not available).
+ *
+ * Returns: pointer to new channel struct if success, or error-valued pointer:
+ *          -ENODEV - cannot find specified channel or mport,
+ *          -EINVAL - the channel is not in IDLE state,
+ *          -EAGAIN - no connection request available immediately (timeout=0),
+ *          -ENOMEM - unable to allocate new channel,
+ *          -ETIME - wait timeout expired,
+ *          -EINTR - wait was interrupted.
+ */
+static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id,
+					   long timeout)
+{
+	struct rio_channel *ch = NULL;
+	struct rio_channel *new_ch = NULL;
+	struct conn_req *req;
+	struct cm_peer *peer;
+	int found = 0;
+	int err = 0;
+	long wret;
+
+	ch = riocm_get_channel(ch_id);
+	if (!ch)
+		return ERR_PTR(-EINVAL);
+
+	if (!riocm_cmp(ch, RIO_CM_LISTEN)) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
+	/* Don't sleep if this is a non blocking call */
+	if (!timeout) {
+		if (!try_wait_for_completion(&ch->comp)) {
+			err = -EAGAIN;
+			goto err_put;
+		}
+	} else {
+		riocm_debug(WAIT, "on %d", ch->id);
+
+		wret = wait_for_completion_interruptible_timeout(&ch->comp,
+								 timeout);
+		if (!wret) {
+			err = -ETIME;
+			goto err_put;
+		} else if (wret == -ERESTARTSYS) {
+			err = -EINTR;
+			goto err_put;
+		}
+	}
+
+	spin_lock_bh(&ch->lock);
+
+	if (ch->state != RIO_CM_LISTEN) {
+		err = -ECANCELED;
+	} else if (list_empty(&ch->accept_queue)) {
+		riocm_debug(WAIT, "on %d accept_queue is empty on completion",
+			    ch->id);
+		err = -EIO;
+	}
+
+	spin_unlock_bh(&ch->lock);
+
+	if (err) {
+		riocm_debug(WAIT, "on %d returns %d", ch->id, err);
+		goto err_put;
+	}
+
+	/* Create new channel for this connection */
+	new_ch = riocm_ch_alloc(RIOCM_CHNUM_AUTO);
+
+	if (IS_ERR(new_ch)) {
+		riocm_error("failed to get channel for new req (%ld)",
+			PTR_ERR(new_ch));
+		err = -ENOMEM;
+		goto err_put;
+	}
+
+	spin_lock_bh(&ch->lock);
+
+	req = list_first_entry(&ch->accept_queue, struct conn_req, node);
+	list_del(&req->node);
+	new_ch->cmdev = ch->cmdev;
+	new_ch->loc_destid = ch->loc_destid;
+	new_ch->rem_destid = req->destid;
+	new_ch->rem_channel = req->chan;
+
+	spin_unlock_bh(&ch->lock);
+	riocm_put_channel(ch);
+	kfree(req);
+
+	down_read(&rdev_sem);
+	/* Find requester's device object */
+	list_for_each_entry(peer, &new_ch->cmdev->peers, node) {
+		if (peer->rdev->destid == new_ch->rem_destid) {
+			riocm_debug(RX_CMD, "found matching device(%s)",
+				    rio_name(peer->rdev));
+			found = 1;
+			break;
+		}
+	}
+	up_read(&rdev_sem);
+
+	if (!found) {
+		/* If peer device object not found, simply ignore the request */
+		err = -ENODEV;
+		goto err_nodev;
+	}
+
+	new_ch->rdev = peer->rdev;
+	new_ch->state = RIO_CM_CONNECTED;
+	spin_lock_init(&new_ch->lock);
+
+	/* Acknowledge the connection request. */
+	riocm_send_ack(new_ch);
+
+	*new_ch_id = new_ch->id;
+	return new_ch;
+err_put:
+	riocm_put_channel(ch);
+err_nodev:
+	if (new_ch) {
+		spin_lock_bh(&idr_lock);
+		idr_remove(&ch_idr, new_ch->id);
+		spin_unlock_bh(&idr_lock);
+		riocm_put_channel(new_ch);
+	}
+	*new_ch_id = 0;
+	return ERR_PTR(err);
+}
+
+/*
+ * riocm_ch_listen - puts a channel into LISTEN state
+ * @ch_id: channel ID
+ *
+ * Returns: 0 if success, or
+ *          -EINVAL if the specified channel does not exists or
+ *                  is not in CHAN_BOUND state.
+ */
+static int riocm_ch_listen(u16 ch_id)
+{
+	struct rio_channel *ch = NULL;
+	int ret = 0;
+
+	riocm_debug(CHOP, "(ch_%d)", ch_id);
+
+	ch = riocm_get_channel(ch_id);
+	if (!ch || !riocm_cmp_exch(ch, RIO_CM_CHAN_BOUND, RIO_CM_LISTEN))
+		ret = -EINVAL;
+	riocm_put_channel(ch);
+	return ret;
+}
+
+/*
+ * riocm_ch_bind - associate a channel object and an mport device
+ * @ch_id: channel ID
+ * @mport_id: local mport device ID
+ * @context: pointer to the additional caller's context
+ *
+ * Returns: 0 if success, or
+ *          -ENODEV if cannot find specified mport,
+ *          -EINVAL if the specified channel does not exist or
+ *                  is not in IDLE state.
+ */
+static int riocm_ch_bind(u16 ch_id, u8 mport_id, void *context)
+{
+	struct rio_channel *ch = NULL;
+	struct cm_dev *cm;
+	int rc = -ENODEV;
+
+	riocm_debug(CHOP, "ch_%d to mport_%d", ch_id, mport_id);
+
+	/* Find matching cm_dev object */
+	down_read(&rdev_sem);
+	list_for_each_entry(cm, &cm_dev_list, list) {
+		if ((cm->mport->id == mport_id) &&
+		     rio_mport_is_running(cm->mport)) {
+			rc = 0;
+			break;
+		}
+	}
+
+	if (rc)
+		goto exit;
+
+	ch = riocm_get_channel(ch_id);
+	if (!ch) {
+		rc = -EINVAL;
+		goto exit;
+	}
+
+	spin_lock_bh(&ch->lock);
+	if (ch->state != RIO_CM_IDLE) {
+		spin_unlock_bh(&ch->lock);
+		rc = -EINVAL;
+		goto err_put;
+	}
+
+	ch->cmdev = cm;
+	ch->loc_destid = cm->mport->host_deviceid;
+	ch->context = context;
+	ch->state = RIO_CM_CHAN_BOUND;
+	spin_unlock_bh(&ch->lock);
+err_put:
+	riocm_put_channel(ch);
+exit:
+	up_read(&rdev_sem);
+	return rc;
+}
+
+/*
+ * riocm_ch_alloc - channel object allocation helper routine
+ * @ch_num: channel ID (1 ... RIOCM_MAX_CHNUM, 0 = automatic)
+ *
+ * Return value: pointer to newly created channel object,
+ *               or error-valued pointer
+ */
+static struct rio_channel *riocm_ch_alloc(u16 ch_num)
+{
+	int id;
+	int start, end;
+	struct rio_channel *ch;
+
+	ch = kzalloc(sizeof(*ch), GFP_KERNEL);
+	if (!ch)
+		return ERR_PTR(-ENOMEM);
+
+	if (ch_num) {
+		/* If requested, try to obtain the specified channel ID */
+		start = ch_num;
+		end = ch_num + 1;
+	} else {
+		/* Obtain channel ID from the dynamic allocation range */
+		start = chstart;
+		end = RIOCM_MAX_CHNUM + 1;
+	}
+
+	idr_preload(GFP_KERNEL);
+	spin_lock_bh(&idr_lock);
+	id = idr_alloc_cyclic(&ch_idr, ch, start, end, GFP_NOWAIT);
+	spin_unlock_bh(&idr_lock);
+	idr_preload_end();
+
+	if (id < 0) {
+		kfree(ch);
+		return ERR_PTR(id == -ENOSPC ? -EBUSY : id);
+	}
+
+	ch->id = (u16)id;
+	ch->state = RIO_CM_IDLE;
+	spin_lock_init(&ch->lock);
+	INIT_LIST_HEAD(&ch->accept_queue);
+	INIT_LIST_HEAD(&ch->ch_node);
+	init_completion(&ch->comp);
+	init_completion(&ch->comp_close);
+	kref_init(&ch->ref);
+	ch->rx_ring.head = 0;
+	ch->rx_ring.tail = 0;
+	ch->rx_ring.count = 0;
+	ch->rx_ring.inuse_cnt = 0;
+
+	return ch;
+}
+
+/*
+ * riocm_ch_create - creates a new channel object and allocates ID for it
+ * @ch_num: channel ID (1 ... RIOCM_MAX_CHNUM, 0 = automatic)
+ *
+ * Allocates and initializes a new channel object. If the parameter ch_num > 0
+ * and is within the valid range, riocm_ch_create tries to allocate the
+ * specified ID for the new channel. If ch_num = 0, channel ID will be assigned
+ * automatically from the range (chstart ... RIOCM_MAX_CHNUM).
+ * Module parameter 'chstart' defines start of an ID range available for dynamic
+ * allocation. Range below 'chstart' is reserved for pre-defined ID numbers.
+ * Available channel numbers are limited by 16-bit size of channel numbers used
+ * in the packet header.
+ *
+ * Return value: PTR to rio_channel structure if successful (with channel number
+ *               updated via pointer) or error-valued pointer if error.
+ */
+static struct rio_channel *riocm_ch_create(u16 *ch_num)
+{
+	struct rio_channel *ch = NULL;
+
+	ch = riocm_ch_alloc(*ch_num);
+
+	if (IS_ERR(ch))
+		riocm_debug(CHOP, "Failed to allocate channel %d (err=%ld)",
+			    *ch_num, PTR_ERR(ch));
+	else
+		*ch_num = ch->id;
+
+	return ch;
+}
+
+/*
+ * riocm_ch_free - channel object release routine
+ * @ref: pointer to a channel's kref structure
+ */
+static void riocm_ch_free(struct kref *ref)
+{
+	struct rio_channel *ch = container_of(ref, struct rio_channel, ref);
+	int i;
+
+	riocm_debug(CHOP, "(ch_%d)", ch->id);
+
+	if (ch->rx_ring.inuse_cnt) {
+		for (i = 0;
+		     i < RIOCM_RX_RING_SIZE && ch->rx_ring.inuse_cnt; i++) {
+			if (ch->rx_ring.inuse[i] != NULL) {
+				kfree(ch->rx_ring.inuse[i]);
+				ch->rx_ring.inuse_cnt--;
+			}
+		}
+	}
+
+	if (ch->rx_ring.count)
+		for (i = 0; i < RIOCM_RX_RING_SIZE && ch->rx_ring.count; i++) {
+			if (ch->rx_ring.buf[i] != NULL) {
+				kfree(ch->rx_ring.buf[i]);
+				ch->rx_ring.count--;
+			}
+		}
+
+	complete(&ch->comp_close);
+}
+
+static int riocm_send_close(struct rio_channel *ch)
+{
+	struct rio_ch_chan_hdr *hdr;
+	int ret;
+
+	/*
+	 * Send CH_CLOSE notification to the remote RapidIO device
+	 */
+
+	hdr = kzalloc(sizeof(*hdr), GFP_KERNEL);
+	if (hdr == NULL)
+		return -ENOMEM;
+
+	hdr->bhdr.src_id = htonl(ch->loc_destid);
+	hdr->bhdr.dst_id = htonl(ch->rem_destid);
+	hdr->bhdr.src_mbox = cmbox;
+	hdr->bhdr.dst_mbox = cmbox;
+	hdr->bhdr.type = RIO_CM_CHAN;
+	hdr->ch_op = CM_CONN_CLOSE;
+	hdr->dst_ch = htons(ch->rem_channel);
+	hdr->src_ch = htons(ch->id);
+
+	/* ATTN: the function call below relies on the fact that underlying
+	 * add_outb_message() routine copies TX data into its internal transfer
+	 * buffer. Needs to be reviewed if switched to direct buffer mode.
+	 */
+	ret = riocm_post_send(ch->cmdev, ch->rdev, hdr, sizeof(*hdr));
+
+	if (ret == -EBUSY && !riocm_queue_req(ch->cmdev, ch->rdev,
+					      hdr, sizeof(*hdr)))
+		return 0;
+	kfree(hdr);
+
+	if (ret)
+		riocm_error("ch(%d) send CLOSE failed (ret=%d)", ch->id, ret);
+
+	return ret;
+}
+
+/*
+ * riocm_ch_close - closes a channel object with specified ID (by local request)
+ * @ch: channel to be closed
+ */
+static int riocm_ch_close(struct rio_channel *ch)
+{
+	unsigned long tmo = msecs_to_jiffies(3000);
+	enum rio_cm_state state;
+	long wret;
+	int ret = 0;
+
+	riocm_debug(CHOP, "ch_%d by %s(%d)",
+		    ch->id, current->comm, task_pid_nr(current));
+
+	state = riocm_exch(ch, RIO_CM_DESTROYING);
+	if (state == RIO_CM_CONNECTED)
+		riocm_send_close(ch);
+
+	complete_all(&ch->comp);
+
+	riocm_put_channel(ch);
+	wret = wait_for_completion_interruptible_timeout(&ch->comp_close, tmo);
+
+	riocm_debug(WAIT, "wait on %d returns %ld", ch->id, wret);
+
+	if (wret == 0) {
+		/* Timeout on wait occurred */
+		riocm_debug(CHOP, "%s(%d) timed out waiting for ch %d",
+		       current->comm, task_pid_nr(current), ch->id);
+		ret = -ETIMEDOUT;
+	} else if (wret == -ERESTARTSYS) {
+		/* Wait_for_completion was interrupted by a signal */
+		riocm_debug(CHOP, "%s(%d) wait for ch %d was interrupted",
+			current->comm, task_pid_nr(current), ch->id);
+		ret = -EINTR;
+	}
+
+	if (!ret) {
+		riocm_debug(CHOP, "ch_%d resources released", ch->id);
+		kfree(ch);
+	} else {
+		riocm_debug(CHOP, "failed to release ch_%d resources", ch->id);
+	}
+
+	return ret;
+}
+
+/*
+ * riocm_cdev_open() - Open character device
+ */
+static int riocm_cdev_open(struct inode *inode, struct file *filp)
+{
+	riocm_debug(INIT, "by %s(%d) filp=%p ",
+		    current->comm, task_pid_nr(current), filp);
+
+	if (list_empty(&cm_dev_list))
+		return -ENODEV;
+
+	return 0;
+}
+
+/*
+ * riocm_cdev_release() - Release character device
+ */
+static int riocm_cdev_release(struct inode *inode, struct file *filp)
+{
+	struct rio_channel *ch, *_c;
+	unsigned int i;
+	LIST_HEAD(list);
+
+	riocm_debug(EXIT, "by %s(%d) filp=%p",
+		    current->comm, task_pid_nr(current), filp);
+
+	/* Check if there are channels associated with this file descriptor */
+	spin_lock_bh(&idr_lock);
+	idr_for_each_entry(&ch_idr, ch, i) {
+		if (ch && ch->filp == filp) {
+			riocm_debug(EXIT, "ch_%d not released by %s(%d)",
+				    ch->id, current->comm,
+				    task_pid_nr(current));
+			idr_remove(&ch_idr, ch->id);
+			list_add(&ch->ch_node, &list);
+		}
+	}
+	spin_unlock_bh(&idr_lock);
+
+	if (!list_empty(&list)) {
+		list_for_each_entry_safe(ch, _c, &list, ch_node) {
+			list_del(&ch->ch_node);
+			riocm_ch_close(ch);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * cm_ep_get_list_size() - Reports number of endpoints in the network
+ */
+static int cm_ep_get_list_size(void __user *arg)
+{
+	u32 __user *p = arg;
+	u32 mport_id;
+	u32 count = 0;
+	struct cm_dev *cm;
+
+	if (get_user(mport_id, p))
+		return -EFAULT;
+	if (mport_id >= RIO_MAX_MPORTS)
+		return -EINVAL;
+
+	/* Find a matching cm_dev object */
+	down_read(&rdev_sem);
+	list_for_each_entry(cm, &cm_dev_list, list) {
+		if (cm->mport->id == mport_id) {
+			count = cm->npeers;
+			up_read(&rdev_sem);
+			if (copy_to_user(arg, &count, sizeof(u32)))
+				return -EFAULT;
+			return 0;
+		}
+	}
+	up_read(&rdev_sem);
+
+	return -ENODEV;
+}
+
+/*
+ * cm_ep_get_list() - Returns list of attached endpoints
+ */
+static int cm_ep_get_list(void __user *arg)
+{
+	struct cm_dev *cm;
+	struct cm_peer *peer;
+	u32 info[2];
+	void *buf;
+	u32 nent;
+	u32 *entry_ptr;
+	u32 i = 0;
+	int ret = 0;
+
+	if (copy_from_user(&info, arg, sizeof(info)))
+		return -EFAULT;
+
+	if (info[1] >= RIO_MAX_MPORTS || info[0] > RIOCM_MAX_EP_COUNT)
+		return -EINVAL;
+
+	/* Find a matching cm_dev object */
+	down_read(&rdev_sem);
+	list_for_each_entry(cm, &cm_dev_list, list)
+		if (cm->mport->id == (u8)info[1])
+			goto found;
+
+	up_read(&rdev_sem);
+	return -ENODEV;
+
+found:
+	nent = min(info[0], cm->npeers);
+	buf = kcalloc(nent + 2, sizeof(u32), GFP_KERNEL);
+	if (!buf) {
+		up_read(&rdev_sem);
+		return -ENOMEM;
+	}
+
+	entry_ptr = (u32 *)((uintptr_t)buf + 2*sizeof(u32));
+
+	list_for_each_entry(peer, &cm->peers, node) {
+		*entry_ptr = (u32)peer->rdev->destid;
+		entry_ptr++;
+		if (++i == nent)
+			break;
+	}
+	up_read(&rdev_sem);
+
+	((u32 *)buf)[0] = i; /* report an updated number of entries */
+	((u32 *)buf)[1] = info[1]; /* put back an mport ID */
+	if (copy_to_user(arg, buf, sizeof(u32) * (info[0] + 2)))
+		ret = -EFAULT;
+
+	kfree(buf);
+	return ret;
+}
+
+/*
+ * cm_mport_get_list() - Returns list of available local mport devices
+ */
+static int cm_mport_get_list(void __user *arg)
+{
+	int ret = 0;
+	u32 entries;
+	void *buf;
+	struct cm_dev *cm;
+	u32 *entry_ptr;
+	int count = 0;
+
+	if (copy_from_user(&entries, arg, sizeof(entries)))
+		return -EFAULT;
+	if (entries == 0 || entries > RIO_MAX_MPORTS)
+		return -EINVAL;
+	buf = kcalloc(entries + 1, sizeof(u32), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* Scan all registered cm_dev objects */
+	entry_ptr = (u32 *)((uintptr_t)buf + sizeof(u32));
+	down_read(&rdev_sem);
+	list_for_each_entry(cm, &cm_dev_list, list) {
+		if (count++ < entries) {
+			*entry_ptr = (cm->mport->id << 16) |
+				      cm->mport->host_deviceid;
+			entry_ptr++;
+		}
+	}
+	up_read(&rdev_sem);
+
+	*((u32 *)buf) = count; /* report a real number of entries */
+	if (copy_to_user(arg, buf, sizeof(u32) * (count + 1)))
+		ret = -EFAULT;
+
+	kfree(buf);
+	return ret;
+}
+
+/*
+ * cm_chan_create() - Create a message exchange channel
+ */
+static int cm_chan_create(struct file *filp, void __user *arg)
+{
+	u16 __user *p = arg;
+	u16 ch_num;
+	struct rio_channel *ch;
+
+	if (get_user(ch_num, p))
+		return -EFAULT;
+
+	riocm_debug(CHOP, "ch_%d requested by %s(%d)",
+		    ch_num, current->comm, task_pid_nr(current));
+	ch = riocm_ch_create(&ch_num);
+	if (IS_ERR(ch))
+		return PTR_ERR(ch);
+
+	ch->filp = filp;
+	riocm_debug(CHOP, "ch_%d created by %s(%d)",
+		    ch_num, current->comm, task_pid_nr(current));
+	return put_user(ch_num, p);
+}
+
+/*
+ * cm_chan_close() - Close channel
+ * @filp:	Pointer to file object
+ * @arg:	Channel to close
+ */
+static int cm_chan_close(struct file *filp, void __user *arg)
+{
+	u16 __user *p = arg;
+	u16 ch_num;
+	struct rio_channel *ch;
+
+	if (get_user(ch_num, p))
+		return -EFAULT;
+
+	riocm_debug(CHOP, "ch_%d by %s(%d)",
+		    ch_num, current->comm, task_pid_nr(current));
+
+	spin_lock_bh(&idr_lock);
+	ch = idr_find(&ch_idr, ch_num);
+	if (!ch) {
+		spin_unlock_bh(&idr_lock);
+		return 0;
+	}
+	if (ch->filp != filp) {
+		spin_unlock_bh(&idr_lock);
+		return -EINVAL;
+	}
+	idr_remove(&ch_idr, ch->id);
+	spin_unlock_bh(&idr_lock);
+
+	return riocm_ch_close(ch);
+}
+
+/*
+ * cm_chan_bind() - Bind channel
+ * @arg:	Channel number
+ */
+static int cm_chan_bind(void __user *arg)
+{
+	struct rio_cm_channel chan;
+
+	if (copy_from_user(&chan, arg, sizeof(chan)))
+		return -EFAULT;
+	if (chan.mport_id >= RIO_MAX_MPORTS)
+		return -EINVAL;
+
+	return riocm_ch_bind(chan.id, chan.mport_id, NULL);
+}
+
+/*
+ * cm_chan_listen() - Listen on channel
+ * @arg:	Channel number
+ */
+static int cm_chan_listen(void __user *arg)
+{
+	u16 __user *p = arg;
+	u16 ch_num;
+
+	if (get_user(ch_num, p))
+		return -EFAULT;
+
+	return riocm_ch_listen(ch_num);
+}
+
+/*
+ * cm_chan_accept() - Accept incoming connection
+ * @filp:	Pointer to file object
+ * @arg:	Channel number
+ */
+static int cm_chan_accept(struct file *filp, void __user *arg)
+{
+	struct rio_cm_accept param;
+	long accept_to;
+	struct rio_channel *ch;
+
+	if (copy_from_user(&param, arg, sizeof(param)))
+		return -EFAULT;
+
+	riocm_debug(CHOP, "on ch_%d by %s(%d)",
+		    param.ch_num, current->comm, task_pid_nr(current));
+
+	accept_to = param.wait_to ?
+			msecs_to_jiffies(param.wait_to) : 0;
+
+	ch = riocm_ch_accept(param.ch_num, &param.ch_num, accept_to);
+	if (IS_ERR(ch))
+		return PTR_ERR(ch);
+	ch->filp = filp;
+
+	riocm_debug(CHOP, "new ch_%d for %s(%d)",
+		    ch->id, current->comm, task_pid_nr(current));
+
+	if (copy_to_user(arg, &param, sizeof(param)))
+		return -EFAULT;
+	return 0;
+}
+
+/*
+ * cm_chan_connect() - Connect on channel
+ * @arg:	Channel information
+ */
+static int cm_chan_connect(void __user *arg)
+{
+	struct rio_cm_channel chan;
+	struct cm_dev *cm;
+	struct cm_peer *peer;
+	int ret = -ENODEV;
+
+	if (copy_from_user(&chan, arg, sizeof(chan)))
+		return -EFAULT;
+	if (chan.mport_id >= RIO_MAX_MPORTS)
+		return -EINVAL;
+
+	down_read(&rdev_sem);
+
+	/* Find matching cm_dev object */
+	list_for_each_entry(cm, &cm_dev_list, list) {
+		if (cm->mport->id == chan.mport_id) {
+			ret = 0;
+			break;
+		}
+	}
+
+	if (ret)
+		goto err_out;
+
+	if (chan.remote_destid >= RIO_ANY_DESTID(cm->mport->sys_size)) {
+		ret = -EINVAL;
+		goto err_out;
+	}
+
+	/* Find corresponding RapidIO endpoint device object */
+	ret = -ENODEV;
+
+	list_for_each_entry(peer, &cm->peers, node) {
+		if (peer->rdev->destid == chan.remote_destid) {
+			ret = 0;
+			break;
+		}
+	}
+
+	if (ret)
+		goto err_out;
+
+	up_read(&rdev_sem);
+
+	return riocm_ch_connect(chan.id, cm, peer, chan.remote_channel);
+err_out:
+	up_read(&rdev_sem);
+	return ret;
+}
+
+/*
+ * cm_chan_msg_send() - Send a message through channel
+ * @arg:	Outbound message information
+ */
+static int cm_chan_msg_send(void __user *arg)
+{
+	struct rio_cm_msg msg;
+	void *buf;
+	int ret = 0;
+
+	if (copy_from_user(&msg, arg, sizeof(msg)))
+		return -EFAULT;
+	if (msg.size > RIO_MAX_MSG_SIZE)
+		return -EINVAL;
+
+	buf = kmalloc(msg.size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, (void __user *)(uintptr_t)msg.msg, msg.size)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = riocm_ch_send(msg.ch_num, buf, msg.size);
+out:
+	kfree(buf);
+	return ret;
+}
+
+/*
+ * cm_chan_msg_rcv() - Receive a message through channel
+ * @arg:	Inbound message information
+ */
+static int cm_chan_msg_rcv(void __user *arg)
+{
+	struct rio_cm_msg msg;
+	struct rio_channel *ch;
+	void *buf;
+	long rxto;
+	int ret = 0, msg_size;
+
+	if (copy_from_user(&msg, arg, sizeof(msg)))
+		return -EFAULT;
+
+	if (msg.ch_num == 0 || msg.size == 0)
+		return -EINVAL;
+
+	ch = riocm_get_channel(msg.ch_num);
+	if (!ch)
+		return -ENODEV;
+
+	rxto = msg.rxto ? msecs_to_jiffies(msg.rxto) : MAX_SCHEDULE_TIMEOUT;
+
+	ret = riocm_ch_receive(ch, &buf, rxto);
+	if (ret)
+		goto out;
+
+	msg_size = min(msg.size, (u16)(RIO_MAX_MSG_SIZE));
+
+	if (copy_to_user((void __user *)(uintptr_t)msg.msg, buf, msg_size))
+		ret = -EFAULT;
+
+	riocm_ch_free_rxbuf(ch, buf);
+out:
+	riocm_put_channel(ch);
+	return ret;
+}
+
+/*
+ * riocm_cdev_ioctl() - IOCTL requests handler
+ */
+static long
+riocm_cdev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case RIO_CM_EP_GET_LIST_SIZE:
+		return cm_ep_get_list_size((void __user *)arg);
+	case RIO_CM_EP_GET_LIST:
+		return cm_ep_get_list((void __user *)arg);
+	case RIO_CM_CHAN_CREATE:
+		return cm_chan_create(filp, (void __user *)arg);
+	case RIO_CM_CHAN_CLOSE:
+		return cm_chan_close(filp, (void __user *)arg);
+	case RIO_CM_CHAN_BIND:
+		return cm_chan_bind((void __user *)arg);
+	case RIO_CM_CHAN_LISTEN:
+		return cm_chan_listen((void __user *)arg);
+	case RIO_CM_CHAN_ACCEPT:
+		return cm_chan_accept(filp, (void __user *)arg);
+	case RIO_CM_CHAN_CONNECT:
+		return cm_chan_connect((void __user *)arg);
+	case RIO_CM_CHAN_SEND:
+		return cm_chan_msg_send((void __user *)arg);
+	case RIO_CM_CHAN_RECEIVE:
+		return cm_chan_msg_rcv((void __user *)arg);
+	case RIO_CM_MPORT_GET_LIST:
+		return cm_mport_get_list((void __user *)arg);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct file_operations riocm_cdev_fops = {
+	.owner		= THIS_MODULE,
+	.open		= riocm_cdev_open,
+	.release	= riocm_cdev_release,
+	.unlocked_ioctl = riocm_cdev_ioctl,
+};
+
+/*
+ * riocm_add_dev - add new remote RapidIO device into channel management core
+ * @dev: device object associated with RapidIO device
+ * @sif: subsystem interface
+ *
+ * Adds the specified RapidIO device (if applicable) into peers list of
+ * the corresponding channel management device (cm_dev).
+ */
+static int riocm_add_dev(struct device *dev, struct subsys_interface *sif)
+{
+	struct cm_peer *peer;
+	struct rio_dev *rdev = to_rio_dev(dev);
+	struct cm_dev *cm;
+
+	/* Check if the remote device has capabilities required to support CM */
+	if (!dev_cm_capable(rdev))
+		return 0;
+
+	riocm_debug(RDEV, "(%s)", rio_name(rdev));
+
+	peer = kmalloc(sizeof(*peer), GFP_KERNEL);
+	if (!peer)
+		return -ENOMEM;
+
+	/* Find a corresponding cm_dev object */
+	down_write(&rdev_sem);
+	list_for_each_entry(cm, &cm_dev_list, list) {
+		if (cm->mport == rdev->net->hport)
+			goto found;
+	}
+
+	up_write(&rdev_sem);
+	kfree(peer);
+	return -ENODEV;
+
+found:
+	peer->rdev = rdev;
+	list_add_tail(&peer->node, &cm->peers);
+	cm->npeers++;
+
+	up_write(&rdev_sem);
+	return 0;
+}
+
+/*
+ * riocm_remove_dev - remove remote RapidIO device from channel management core
+ * @dev: device object associated with RapidIO device
+ * @sif: subsystem interface
+ *
+ * Removes the specified RapidIO device (if applicable) from peers list of
+ * the corresponding channel management device (cm_dev).
+ */
+static void riocm_remove_dev(struct device *dev, struct subsys_interface *sif)
+{
+	struct rio_dev *rdev = to_rio_dev(dev);
+	struct cm_dev *cm;
+	struct cm_peer *peer;
+	struct rio_channel *ch, *_c;
+	unsigned int i;
+	bool found = false;
+	LIST_HEAD(list);
+
+	/* Check if the remote device has capabilities required to support CM */
+	if (!dev_cm_capable(rdev))
+		return;
+
+	riocm_debug(RDEV, "(%s)", rio_name(rdev));
+
+	/* Find matching cm_dev object */
+	down_write(&rdev_sem);
+	list_for_each_entry(cm, &cm_dev_list, list) {
+		if (cm->mport == rdev->net->hport) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		up_write(&rdev_sem);
+		return;
+	}
+
+	/* Remove remote device from the list of peers */
+	found = false;
+	list_for_each_entry(peer, &cm->peers, node) {
+		if (peer->rdev == rdev) {
+			riocm_debug(RDEV, "removing peer %s", rio_name(rdev));
+			found = true;
+			list_del(&peer->node);
+			cm->npeers--;
+			kfree(peer);
+			break;
+		}
+	}
+
+	up_write(&rdev_sem);
+
+	if (!found)
+		return;
+
+	/*
+	 * Release channels associated with this peer
+	 */
+
+	spin_lock_bh(&idr_lock);
+	idr_for_each_entry(&ch_idr, ch, i) {
+		if (ch && ch->rdev == rdev) {
+			if (atomic_read(&rdev->state) != RIO_DEVICE_SHUTDOWN)
+				riocm_exch(ch, RIO_CM_DISCONNECT);
+			idr_remove(&ch_idr, ch->id);
+			list_add(&ch->ch_node, &list);
+		}
+	}
+	spin_unlock_bh(&idr_lock);
+
+	if (!list_empty(&list)) {
+		list_for_each_entry_safe(ch, _c, &list, ch_node) {
+			list_del(&ch->ch_node);
+			riocm_ch_close(ch);
+		}
+	}
+}
+
+/*
+ * riocm_cdev_add() - Create rio_cm char device
+ * @devno: device number assigned to device (MAJ + MIN)
+ */
+static int riocm_cdev_add(dev_t devno)
+{
+	int ret;
+
+	cdev_init(&riocm_cdev.cdev, &riocm_cdev_fops);
+	riocm_cdev.cdev.owner = THIS_MODULE;
+	ret = cdev_add(&riocm_cdev.cdev, devno, 1);
+	if (ret < 0) {
+		riocm_error("Cannot register a device with error %d", ret);
+		return ret;
+	}
+
+	riocm_cdev.dev = device_create(dev_class, NULL, devno, NULL, DEV_NAME);
+	if (IS_ERR(riocm_cdev.dev)) {
+		cdev_del(&riocm_cdev.cdev);
+		return PTR_ERR(riocm_cdev.dev);
+	}
+
+	riocm_debug(MPORT, "Added %s cdev(%d:%d)",
+		    DEV_NAME, MAJOR(devno), MINOR(devno));
+
+	return 0;
+}
+
+/*
+ * riocm_add_mport - add new local mport device into channel management core
+ * @dev: device object associated with mport
+ * @class_intf: class interface
+ *
+ * When a new mport device is added, CM immediately reserves inbound and
+ * outbound RapidIO mailboxes that will be used.
+ */
+static int riocm_add_mport(struct device *dev,
+			   struct class_interface *class_intf)
+{
+	int rc;
+	int i;
+	struct cm_dev *cm;
+	struct rio_mport *mport = to_rio_mport(dev);
+
+	riocm_debug(MPORT, "add mport %s", mport->name);
+
+	cm = kzalloc(sizeof(*cm), GFP_KERNEL);
+	if (!cm)
+		return -ENOMEM;
+
+	cm->mport = mport;
+
+	rc = rio_request_outb_mbox(mport, cm, cmbox,
+				   RIOCM_TX_RING_SIZE, riocm_outb_msg_event);
+	if (rc) {
+		riocm_error("failed to allocate OBMBOX_%d on %s",
+			    cmbox, mport->name);
+		kfree(cm);
+		return -ENODEV;
+	}
+
+	rc = rio_request_inb_mbox(mport, cm, cmbox,
+				  RIOCM_RX_RING_SIZE, riocm_inb_msg_event);
+	if (rc) {
+		riocm_error("failed to allocate IBMBOX_%d on %s",
+			    cmbox, mport->name);
+		rio_release_outb_mbox(mport, cmbox);
+		kfree(cm);
+		return -ENODEV;
+	}
+
+	/*
+	 * Allocate and register inbound messaging buffers to be ready
+	 * to receive channel and system management requests
+	 */
+	for (i = 0; i < RIOCM_RX_RING_SIZE; i++)
+		cm->rx_buf[i] = NULL;
+
+	cm->rx_slots = RIOCM_RX_RING_SIZE;
+	mutex_init(&cm->rx_lock);
+	riocm_rx_fill(cm, RIOCM_RX_RING_SIZE);
+	cm->rx_wq = create_workqueue(DRV_NAME "/rxq");
+	INIT_WORK(&cm->rx_work, rio_ibmsg_handler);
+
+	cm->tx_slot = 0;
+	cm->tx_cnt = 0;
+	cm->tx_ack_slot = 0;
+	spin_lock_init(&cm->tx_lock);
+
+	INIT_LIST_HEAD(&cm->peers);
+	cm->npeers = 0;
+	INIT_LIST_HEAD(&cm->tx_reqs);
+
+	down_write(&rdev_sem);
+	list_add_tail(&cm->list, &cm_dev_list);
+	up_write(&rdev_sem);
+
+	return 0;
+}
+
+/*
+ * riocm_remove_mport - remove local mport device from channel management core
+ * @dev: device object associated with mport
+ * @class_intf: class interface
+ *
+ * Removes a local mport device from the list of registered devices that provide
+ * channel management services. Returns an error if the specified mport is not
+ * registered with the CM core.
+ */
+static void riocm_remove_mport(struct device *dev,
+			       struct class_interface *class_intf)
+{
+	struct rio_mport *mport = to_rio_mport(dev);
+	struct cm_dev *cm;
+	struct cm_peer *peer, *temp;
+	struct rio_channel *ch, *_c;
+	unsigned int i;
+	bool found = false;
+	LIST_HEAD(list);
+
+	riocm_debug(MPORT, "%s", mport->name);
+
+	/* Find a matching cm_dev object */
+	down_write(&rdev_sem);
+	list_for_each_entry(cm, &cm_dev_list, list) {
+		if (cm->mport == mport) {
+			list_del(&cm->list);
+			found = true;
+			break;
+		}
+	}
+	up_write(&rdev_sem);
+	if (!found)
+		return;
+
+	flush_workqueue(cm->rx_wq);
+	destroy_workqueue(cm->rx_wq);
+
+	/* Release channels bound to this mport */
+	spin_lock_bh(&idr_lock);
+	idr_for_each_entry(&ch_idr, ch, i) {
+		if (ch->cmdev == cm) {
+			riocm_debug(RDEV, "%s drop ch_%d",
+				    mport->name, ch->id);
+			idr_remove(&ch_idr, ch->id);
+			list_add(&ch->ch_node, &list);
+		}
+	}
+	spin_unlock_bh(&idr_lock);
+
+	if (!list_empty(&list)) {
+		list_for_each_entry_safe(ch, _c, &list, ch_node) {
+			list_del(&ch->ch_node);
+			riocm_ch_close(ch);
+		}
+	}
+
+	rio_release_inb_mbox(mport, cmbox);
+	rio_release_outb_mbox(mport, cmbox);
+
+	/* Remove and free peer entries */
+	if (!list_empty(&cm->peers))
+		riocm_debug(RDEV, "ATTN: peer list not empty");
+	list_for_each_entry_safe(peer, temp, &cm->peers, node) {
+		riocm_debug(RDEV, "removing peer %s", rio_name(peer->rdev));
+		list_del(&peer->node);
+		kfree(peer);
+	}
+
+	riocm_rx_free(cm);
+	kfree(cm);
+	riocm_debug(MPORT, "%s done", mport->name);
+}
+
+static int rio_cm_shutdown(struct notifier_block *nb, unsigned long code,
+	void *unused)
+{
+	struct rio_channel *ch;
+	unsigned int i;
+
+	riocm_debug(EXIT, ".");
+
+	spin_lock_bh(&idr_lock);
+	idr_for_each_entry(&ch_idr, ch, i) {
+		riocm_debug(EXIT, "close ch %d", ch->id);
+		if (ch->state == RIO_CM_CONNECTED)
+			riocm_send_close(ch);
+	}
+	spin_unlock_bh(&idr_lock);
+
+	return NOTIFY_DONE;
+}
+
+/*
+ * riocm_interface handles addition/removal of remote RapidIO devices
+ */
+static struct subsys_interface riocm_interface = {
+	.name		= "rio_cm",
+	.subsys		= &rio_bus_type,
+	.add_dev	= riocm_add_dev,
+	.remove_dev	= riocm_remove_dev,
+};
+
+/*
+ * rio_mport_interface handles addition/removal local mport devices
+ */
+static struct class_interface rio_mport_interface __refdata = {
+	.class = &rio_mport_class,
+	.add_dev = riocm_add_mport,
+	.remove_dev = riocm_remove_mport,
+};
+
+static struct notifier_block rio_cm_notifier = {
+	.notifier_call = rio_cm_shutdown,
+};
+
+static int __init riocm_init(void)
+{
+	int ret;
+
+	/* Create device class needed by udev */
+	dev_class = class_create(THIS_MODULE, DRV_NAME);
+	if (IS_ERR(dev_class)) {
+		riocm_error("Cannot create " DRV_NAME " class");
+		return PTR_ERR(dev_class);
+	}
+
+	ret = alloc_chrdev_region(&dev_number, 0, 1, DRV_NAME);
+	if (ret) {
+		class_destroy(dev_class);
+		return ret;
+	}
+
+	dev_major = MAJOR(dev_number);
+	dev_minor_base = MINOR(dev_number);
+	riocm_debug(INIT, "Registered class with %d major", dev_major);
+
+	/*
+	 * Register as rapidio_port class interface to get notifications about
+	 * mport additions and removals.
+	 */
+	ret = class_interface_register(&rio_mport_interface);
+	if (ret) {
+		riocm_error("class_interface_register error: %d", ret);
+		goto err_reg;
+	}
+
+	/*
+	 * Register as RapidIO bus interface to get notifications about
+	 * addition/removal of remote RapidIO devices.
+	 */
+	ret = subsys_interface_register(&riocm_interface);
+	if (ret) {
+		riocm_error("subsys_interface_register error: %d", ret);
+		goto err_cl;
+	}
+
+	ret = register_reboot_notifier(&rio_cm_notifier);
+	if (ret) {
+		riocm_error("failed to register reboot notifier (err=%d)", ret);
+		goto err_sif;
+	}
+
+	ret = riocm_cdev_add(dev_number);
+	if (ret) {
+		unregister_reboot_notifier(&rio_cm_notifier);
+		ret = -ENODEV;
+		goto err_sif;
+	}
+
+	return 0;
+err_sif:
+	subsys_interface_unregister(&riocm_interface);
+err_cl:
+	class_interface_unregister(&rio_mport_interface);
+err_reg:
+	unregister_chrdev_region(dev_number, 1);
+	class_destroy(dev_class);
+	return ret;
+}
+
+static void __exit riocm_exit(void)
+{
+	riocm_debug(EXIT, "enter");
+	unregister_reboot_notifier(&rio_cm_notifier);
+	subsys_interface_unregister(&riocm_interface);
+	class_interface_unregister(&rio_mport_interface);
+	idr_destroy(&ch_idr);
+
+	device_unregister(riocm_cdev.dev);
+	cdev_del(&(riocm_cdev.cdev));
+
+	class_destroy(dev_class);
+	unregister_chrdev_region(dev_number, 1);
+}
+
+late_initcall(riocm_init);
+module_exit(riocm_exit);
diff --git a/drivers/rapidio/switches/Kconfig b/drivers/rapidio/switches/Kconfig
index 345841562f95..92767fd3b541 100644
--- a/drivers/rapidio/switches/Kconfig
+++ b/drivers/rapidio/switches/Kconfig
@@ -22,3 +22,9 @@ config RAPIDIO_CPS_GEN2
 	default n
 	---help---
 	  Includes support for ITD CPS Gen.2 serial RapidIO switches.
+
+config RAPIDIO_RXS_GEN3
+	tristate "IDT RXS Gen.3 SRIO switch support"
+	default n
+	---help---
+	  Includes support for ITD RXS Gen.3 serial RapidIO switches.
diff --git a/drivers/rapidio/switches/Makefile b/drivers/rapidio/switches/Makefile
index 051cc6b38188..6bdd54c4e733 100644
--- a/drivers/rapidio/switches/Makefile
+++ b/drivers/rapidio/switches/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_RAPIDIO_TSI57X)	+= tsi57x.o
 obj-$(CONFIG_RAPIDIO_CPS_XX)	+= idtcps.o
 obj-$(CONFIG_RAPIDIO_TSI568)	+= tsi568.o
 obj-$(CONFIG_RAPIDIO_CPS_GEN2)	+= idt_gen2.o
+obj-$(CONFIG_RAPIDIO_RXS_GEN3)	+= idt_gen3.o
diff --git a/drivers/rapidio/switches/idt_gen2.c b/drivers/rapidio/switches/idt_gen2.c
index 9f7fe21580bb..e67b923b1ca6 100644
--- a/drivers/rapidio/switches/idt_gen2.c
+++ b/drivers/rapidio/switches/idt_gen2.c
@@ -436,10 +436,11 @@ static int idtg2_probe(struct rio_dev *rdev, const struct rio_device_id *id)
 				    RIO_STD_RTE_DEFAULT_PORT, IDT_NO_ROUTE);
 	}
 
+	spin_unlock(&rdev->rswitch->lock);
+
 	/* Create device-specific sysfs attributes */
 	idtg2_sysfs(rdev, true);
 
-	spin_unlock(&rdev->rswitch->lock);
 	return 0;
 }
 
@@ -452,11 +453,9 @@ static void idtg2_remove(struct rio_dev *rdev)
 		return;
 	}
 	rdev->rswitch->ops = NULL;
-
+	spin_unlock(&rdev->rswitch->lock);
 	/* Remove device-specific sysfs attributes */
 	idtg2_sysfs(rdev, false);
-
-	spin_unlock(&rdev->rswitch->lock);
 }
 
 static struct rio_device_id idtg2_id_table[] = {
diff --git a/drivers/rapidio/switches/idt_gen3.c b/drivers/rapidio/switches/idt_gen3.c
new file mode 100644
index 000000000000..c5923a547bed
--- /dev/null
+++ b/drivers/rapidio/switches/idt_gen3.c
@@ -0,0 +1,382 @@
+/*
+ * IDT RXS Gen.3 Serial RapidIO switch family support
+ *
+ * Copyright 2016 Integrated Device Technology, Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/stat.h>
+#include <linux/module.h>
+#include <linux/rio.h>
+#include <linux/rio_drv.h>
+#include <linux/rio_ids.h>
+#include <linux/delay.h>
+
+#include <asm/page.h>
+#include "../rio.h"
+
+#define RIO_EM_PW_STAT		0x40020
+#define RIO_PW_CTL		0x40204
+#define RIO_PW_CTL_PW_TMR		0xffffff00
+#define RIO_PW_ROUTE		0x40208
+
+#define RIO_EM_DEV_INT_EN	0x40030
+
+#define RIO_PLM_SPx_IMP_SPEC_CTL(x)	(0x10100 + (x)*0x100)
+#define RIO_PLM_SPx_IMP_SPEC_CTL_SOFT_RST	0x02000000
+
+#define RIO_PLM_SPx_PW_EN(x)	(0x10118 + (x)*0x100)
+#define RIO_PLM_SPx_PW_EN_OK2U	0x40000000
+#define RIO_PLM_SPx_PW_EN_LINIT 0x10000000
+
+#define RIO_BC_L2_Gn_ENTRYx_CSR(n, x)	(0x31000 + (n)*0x400 + (x)*0x4)
+#define RIO_SPx_L2_Gn_ENTRYy_CSR(x, n, y) \
+				(0x51000 + (x)*0x2000 + (n)*0x400 + (y)*0x4)
+
+static int
+idtg3_route_add_entry(struct rio_mport *mport, u16 destid, u8 hopcount,
+		       u16 table, u16 route_destid, u8 route_port)
+{
+	u32 rval;
+	u32 entry = route_port;
+	int err = 0;
+
+	pr_debug("RIO: %s t=0x%x did_%x to p_%x\n",
+		 __func__, table, route_destid, entry);
+
+	if (route_destid > 0xFF)
+		return -EINVAL;
+
+	if (route_port == RIO_INVALID_ROUTE)
+		entry = RIO_RT_ENTRY_DROP_PKT;
+
+	if (table == RIO_GLOBAL_TABLE) {
+		/* Use broadcast register to update all per-port tables */
+		err = rio_mport_write_config_32(mport, destid, hopcount,
+				RIO_BC_L2_Gn_ENTRYx_CSR(0, route_destid),
+				entry);
+		return err;
+	}
+
+	/*
+	 * Verify that specified port/table number is valid
+	 */
+	err = rio_mport_read_config_32(mport, destid, hopcount,
+				       RIO_SWP_INFO_CAR, &rval);
+	if (err)
+		return err;
+
+	if (table >= RIO_GET_TOTAL_PORTS(rval))
+		return -EINVAL;
+
+	err = rio_mport_write_config_32(mport, destid, hopcount,
+			RIO_SPx_L2_Gn_ENTRYy_CSR(table, 0, route_destid),
+			entry);
+	return err;
+}
+
+static int
+idtg3_route_get_entry(struct rio_mport *mport, u16 destid, u8 hopcount,
+		       u16 table, u16 route_destid, u8 *route_port)
+{
+	u32 rval;
+	int err;
+
+	if (route_destid > 0xFF)
+		return -EINVAL;
+
+	err = rio_mport_read_config_32(mport, destid, hopcount,
+				       RIO_SWP_INFO_CAR, &rval);
+	if (err)
+		return err;
+
+	/*
+	 * This switch device does not have the dedicated global routing table.
+	 * It is substituted by reading routing table of the ingress port of
+	 * maintenance read requests.
+	 */
+	if (table == RIO_GLOBAL_TABLE)
+		table = RIO_GET_PORT_NUM(rval);
+	else if (table >= RIO_GET_TOTAL_PORTS(rval))
+		return -EINVAL;
+
+	err = rio_mport_read_config_32(mport, destid, hopcount,
+			RIO_SPx_L2_Gn_ENTRYy_CSR(table, 0, route_destid),
+			&rval);
+	if (err)
+		return err;
+
+	if (rval == RIO_RT_ENTRY_DROP_PKT)
+		*route_port = RIO_INVALID_ROUTE;
+	else
+		*route_port = (u8)rval;
+
+	return 0;
+}
+
+static int
+idtg3_route_clr_table(struct rio_mport *mport, u16 destid, u8 hopcount,
+		       u16 table)
+{
+	u32 i;
+	u32 rval;
+	int err;
+
+	if (table == RIO_GLOBAL_TABLE) {
+		for (i = 0; i <= 0xff; i++) {
+			err = rio_mport_write_config_32(mport, destid, hopcount,
+						RIO_BC_L2_Gn_ENTRYx_CSR(0, i),
+						RIO_RT_ENTRY_DROP_PKT);
+			if (err)
+				break;
+		}
+
+		return err;
+	}
+
+	err = rio_mport_read_config_32(mport, destid, hopcount,
+				       RIO_SWP_INFO_CAR, &rval);
+	if (err)
+		return err;
+
+	if (table >= RIO_GET_TOTAL_PORTS(rval))
+		return -EINVAL;
+
+	for (i = 0; i <= 0xff; i++) {
+		err = rio_mport_write_config_32(mport, destid, hopcount,
+					RIO_SPx_L2_Gn_ENTRYy_CSR(table, 0, i),
+					RIO_RT_ENTRY_DROP_PKT);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+/*
+ * This routine performs device-specific initialization only.
+ * All standard EM configuration should be performed at upper level.
+ */
+static int
+idtg3_em_init(struct rio_dev *rdev)
+{
+	int i, tmp;
+	u32 rval;
+
+	pr_debug("RIO: %s [%d:%d]\n", __func__, rdev->destid, rdev->hopcount);
+
+	/* Disable assertion of interrupt signal */
+	rio_write_config_32(rdev, RIO_EM_DEV_INT_EN, 0);
+
+	/* Disable port-write event notifications during initialization */
+	rio_write_config_32(rdev, rdev->em_efptr + RIO_EM_PW_TX_CTRL,
+			    RIO_EM_PW_TX_CTRL_PW_DIS);
+
+	/* Configure Port-Write notifications for hot-swap events */
+	tmp = RIO_GET_TOTAL_PORTS(rdev->swpinfo);
+	for (i = 0; i < tmp; i++) {
+
+		rio_read_config_32(rdev,
+			RIO_DEV_PORT_N_ERR_STS_CSR(rdev, i),
+			&rval);
+		if (rval & RIO_PORT_N_ERR_STS_PORT_UA)
+			continue;
+
+		/* Clear events signaled before enabling notification */
+		rio_write_config_32(rdev,
+			rdev->em_efptr + RIO_EM_PN_ERR_DETECT(i), 0);
+
+		/* Enable event notifications */
+		rio_write_config_32(rdev,
+			rdev->em_efptr + RIO_EM_PN_ERRRATE_EN(i),
+			RIO_EM_PN_ERRRATE_EN_OK2U | RIO_EM_PN_ERRRATE_EN_U2OK);
+		/* Enable port-write generation on events */
+		rio_write_config_32(rdev, RIO_PLM_SPx_PW_EN(i),
+			RIO_PLM_SPx_PW_EN_OK2U | RIO_PLM_SPx_PW_EN_LINIT);
+
+	}
+
+	/* Set Port-Write destination port */
+	tmp = RIO_GET_PORT_NUM(rdev->swpinfo);
+	rio_write_config_32(rdev, RIO_PW_ROUTE, 1 << tmp);
+
+
+	/* Enable sending port-write event notifications */
+	rio_write_config_32(rdev, rdev->em_efptr + RIO_EM_PW_TX_CTRL, 0);
+
+	/* set TVAL = ~50us */
+	rio_write_config_32(rdev,
+		rdev->phys_efptr + RIO_PORT_LINKTO_CTL_CSR, 0x8e << 8);
+	return 0;
+}
+
+
+/*
+ * idtg3_em_handler - device-specific error handler
+ *
+ * If the link is down (PORT_UNINIT) does nothing - this is considered
+ * as link partner removal from the port.
+ *
+ * If the link is up (PORT_OK) - situation is handled as *new* device insertion.
+ * In this case ERR_STOP bits are cleared by issuing soft reset command to the
+ * reporting port. Inbound and outbound ackIDs are cleared by the reset as well.
+ * This way the port is synchronized with freshly inserted device (assuming it
+ * was reset/powered-up on insertion).
+ *
+ * TODO: This is not sufficient in a situation when a link between two devices
+ * was down and up again (e.g. cable disconnect). For that situation full ackID
+ * realignment process has to be implemented.
+ */
+static int
+idtg3_em_handler(struct rio_dev *rdev, u8 pnum)
+{
+	u32 err_status;
+	u32 rval;
+
+	rio_read_config_32(rdev,
+			RIO_DEV_PORT_N_ERR_STS_CSR(rdev, pnum),
+			&err_status);
+
+	/* Do nothing for device/link removal */
+	if (err_status & RIO_PORT_N_ERR_STS_PORT_UNINIT)
+		return 0;
+
+	/* When link is OK we have a device insertion.
+	 * Request port soft reset to clear errors if they present.
+	 * Inbound and outbound ackIDs will be 0 after reset.
+	 */
+	if (err_status & (RIO_PORT_N_ERR_STS_OUT_ES |
+				RIO_PORT_N_ERR_STS_INP_ES)) {
+		rio_read_config_32(rdev, RIO_PLM_SPx_IMP_SPEC_CTL(pnum), &rval);
+		rio_write_config_32(rdev, RIO_PLM_SPx_IMP_SPEC_CTL(pnum),
+				    rval | RIO_PLM_SPx_IMP_SPEC_CTL_SOFT_RST);
+		udelay(10);
+		rio_write_config_32(rdev, RIO_PLM_SPx_IMP_SPEC_CTL(pnum), rval);
+		msleep(500);
+	}
+
+	return 0;
+}
+
+static struct rio_switch_ops idtg3_switch_ops = {
+	.owner = THIS_MODULE,
+	.add_entry = idtg3_route_add_entry,
+	.get_entry = idtg3_route_get_entry,
+	.clr_table = idtg3_route_clr_table,
+	.em_init   = idtg3_em_init,
+	.em_handle = idtg3_em_handler,
+};
+
+static int idtg3_probe(struct rio_dev *rdev, const struct rio_device_id *id)
+{
+	pr_debug("RIO: %s for %s\n", __func__, rio_name(rdev));
+
+	spin_lock(&rdev->rswitch->lock);
+
+	if (rdev->rswitch->ops) {
+		spin_unlock(&rdev->rswitch->lock);
+		return -EINVAL;
+	}
+
+	rdev->rswitch->ops = &idtg3_switch_ops;
+
+	if (rdev->do_enum) {
+		/* Disable hierarchical routing support: Existing fabric
+		 * enumeration/discovery process (see rio-scan.c) uses 8-bit
+		 * flat destination ID routing only.
+		 */
+		rio_write_config_32(rdev, 0x5000 + RIO_BC_RT_CTL_CSR, 0);
+	}
+
+	spin_unlock(&rdev->rswitch->lock);
+
+	return 0;
+}
+
+static void idtg3_remove(struct rio_dev *rdev)
+{
+	pr_debug("RIO: %s for %s\n", __func__, rio_name(rdev));
+	spin_lock(&rdev->rswitch->lock);
+	if (rdev->rswitch->ops == &idtg3_switch_ops)
+		rdev->rswitch->ops = NULL;
+	spin_unlock(&rdev->rswitch->lock);
+}
+
+/*
+ * Gen3 switches repeat sending PW messages until a corresponding event flag
+ * is cleared. Use shutdown notification to disable generation of port-write
+ * messages if their destination node is shut down.
+ */
+static void idtg3_shutdown(struct rio_dev *rdev)
+{
+	int i;
+	u32 rval;
+	u16 destid;
+
+	/* Currently the enumerator node acts also as PW handler */
+	if (!rdev->do_enum)
+		return;
+
+	pr_debug("RIO: %s(%s)\n", __func__, rio_name(rdev));
+
+	rio_read_config_32(rdev, RIO_PW_ROUTE, &rval);
+	i = RIO_GET_PORT_NUM(rdev->swpinfo);
+
+	/* Check port-write destination port */
+	if (!((1 << i) & rval))
+		return;
+
+	/* Disable sending port-write event notifications if PW destID
+	 * matches to one of the enumerator node
+	 */
+	rio_read_config_32(rdev, rdev->em_efptr + RIO_EM_PW_TGT_DEVID, &rval);
+
+	if (rval & RIO_EM_PW_TGT_DEVID_DEV16)
+		destid = rval >> 16;
+	else
+		destid = ((rval & RIO_EM_PW_TGT_DEVID_D8) >> 16);
+
+	if (rdev->net->hport->host_deviceid == destid) {
+		rio_write_config_32(rdev,
+				    rdev->em_efptr + RIO_EM_PW_TX_CTRL, 0);
+		pr_debug("RIO: %s(%s) PW transmission disabled\n",
+			 __func__, rio_name(rdev));
+	}
+}
+
+static struct rio_device_id idtg3_id_table[] = {
+	{RIO_DEVICE(RIO_DID_IDTRXS1632, RIO_VID_IDT)},
+	{RIO_DEVICE(RIO_DID_IDTRXS2448, RIO_VID_IDT)},
+	{ 0, }	/* terminate list */
+};
+
+static struct rio_driver idtg3_driver = {
+	.name = "idt_gen3",
+	.id_table = idtg3_id_table,
+	.probe = idtg3_probe,
+	.remove = idtg3_remove,
+	.shutdown = idtg3_shutdown,
+};
+
+static int __init idtg3_init(void)
+{
+	return rio_register_driver(&idtg3_driver);
+}
+
+static void __exit idtg3_exit(void)
+{
+	pr_debug("RIO: %s\n", __func__);
+	rio_unregister_driver(&idtg3_driver);
+	pr_debug("RIO: %s done\n", __func__);
+}
+
+device_initcall(idtg3_init);
+module_exit(idtg3_exit);
+
+MODULE_DESCRIPTION("IDT RXS Gen.3 Serial RapidIO switch family driver");
+MODULE_AUTHOR("Integrated Device Technology, Inc.");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rapidio/switches/tsi57x.c b/drivers/rapidio/switches/tsi57x.c
index 42c8b014fe15..2700d15f7584 100644
--- a/drivers/rapidio/switches/tsi57x.c
+++ b/drivers/rapidio/switches/tsi57x.c
@@ -175,12 +175,10 @@ tsi57x_em_init(struct rio_dev *rdev)
 
 		/* Clear all pending interrupts */
 		rio_read_config_32(rdev,
-				rdev->phys_efptr +
-					RIO_PORT_N_ERR_STS_CSR(portnum),
+				RIO_DEV_PORT_N_ERR_STS_CSR(rdev, portnum),
 				&regval);
 		rio_write_config_32(rdev,
-				rdev->phys_efptr +
-					RIO_PORT_N_ERR_STS_CSR(portnum),
+				RIO_DEV_PORT_N_ERR_STS_CSR(rdev, portnum),
 				regval & 0x07120214);
 
 		rio_read_config_32(rdev,
@@ -198,7 +196,7 @@ tsi57x_em_init(struct rio_dev *rdev)
 
 		/* Skip next (odd) port if the current port is in x4 mode */
 		rio_read_config_32(rdev,
-				rdev->phys_efptr + RIO_PORT_N_CTL_CSR(portnum),
+				RIO_DEV_PORT_N_CTL_CSR(rdev, portnum),
 				&regval);
 		if ((regval & RIO_PORT_N_CTL_PWIDTH) == RIO_PORT_N_CTL_PWIDTH_4)
 			portnum++;
@@ -221,23 +219,23 @@ tsi57x_em_handler(struct rio_dev *rdev, u8 portnum)
 	u32 regval;
 
 	rio_read_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_ERR_STS_CSR(portnum),
+			RIO_DEV_PORT_N_ERR_STS_CSR(rdev, portnum),
 			&err_status);
 
 	if ((err_status & RIO_PORT_N_ERR_STS_PORT_OK) &&
-	    (err_status & (RIO_PORT_N_ERR_STS_PW_OUT_ES |
-			  RIO_PORT_N_ERR_STS_PW_INP_ES))) {
+	    (err_status & (RIO_PORT_N_ERR_STS_OUT_ES |
+			  RIO_PORT_N_ERR_STS_INP_ES))) {
 		/* Remove any queued packets by locking/unlocking port */
 		rio_read_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_CTL_CSR(portnum),
+			RIO_DEV_PORT_N_CTL_CSR(rdev, portnum),
 			&regval);
 		if (!(regval & RIO_PORT_N_CTL_LOCKOUT)) {
 			rio_write_config_32(rdev,
-				rdev->phys_efptr + RIO_PORT_N_CTL_CSR(portnum),
+				RIO_DEV_PORT_N_CTL_CSR(rdev, portnum),
 				regval | RIO_PORT_N_CTL_LOCKOUT);
 			udelay(50);
 			rio_write_config_32(rdev,
-				rdev->phys_efptr + RIO_PORT_N_CTL_CSR(portnum),
+				RIO_DEV_PORT_N_CTL_CSR(rdev, portnum),
 				regval);
 		}
 
@@ -245,7 +243,7 @@ tsi57x_em_handler(struct rio_dev *rdev, u8 portnum)
 		 * valid bit
 		 */
 		rio_read_config_32(rdev,
-			rdev->phys_efptr + RIO_PORT_N_MNT_RSP_CSR(portnum),
+			RIO_DEV_PORT_N_MNT_RSP_CSR(rdev, portnum),
 			&regval);
 
 		/* Send a Packet-Not-Accepted/Link-Request-Input-Status control
@@ -259,8 +257,8 @@ tsi57x_em_handler(struct rio_dev *rdev, u8 portnum)
 			while (checkcount--) {
 				udelay(50);
 				rio_read_config_32(rdev,
-					rdev->phys_efptr +
-						RIO_PORT_N_MNT_RSP_CSR(portnum),
+					RIO_DEV_PORT_N_MNT_RSP_CSR(rdev,
+								   portnum),
 					&regval);
 				if (regval & RIO_PORT_N_MNT_RSP_RVAL)
 					goto exit_es;
diff --git a/drivers/regulator/ab8500-ext.c b/drivers/regulator/ab8500-ext.c
index 84c1ee39ddae..2ca00045eb99 100644
--- a/drivers/regulator/ab8500-ext.c
+++ b/drivers/regulator/ab8500-ext.c
@@ -25,6 +25,456 @@
 #include <linux/mfd/abx500/ab8500.h>
 #include <linux/regulator/ab8500.h>
 
+static struct regulator_consumer_supply ab8500_vaux1_consumers[] = {
+	/* Main display, u8500 R3 uib */
+	REGULATOR_SUPPLY("vddi", "mcde_disp_sony_acx424akp.0"),
+	/* Main display, u8500 uib and ST uib */
+	REGULATOR_SUPPLY("vdd1", "samsung_s6d16d0.0"),
+	/* Secondary display, ST uib */
+	REGULATOR_SUPPLY("vdd1", "samsung_s6d16d0.1"),
+	/* SFH7741 proximity sensor */
+	REGULATOR_SUPPLY("vcc", "gpio-keys.0"),
+	/* BH1780GLS ambient light sensor */
+	REGULATOR_SUPPLY("vcc", "2-0029"),
+	/* lsm303dlh accelerometer */
+	REGULATOR_SUPPLY("vdd", "2-0018"),
+	/* lsm303dlhc accelerometer */
+	REGULATOR_SUPPLY("vdd", "2-0019"),
+	/* lsm303dlh magnetometer */
+	REGULATOR_SUPPLY("vdd", "2-001e"),
+	/* Rohm BU21013 Touchscreen devices */
+	REGULATOR_SUPPLY("avdd", "3-005c"),
+	REGULATOR_SUPPLY("avdd", "3-005d"),
+	/* Synaptics RMI4 Touchscreen device */
+	REGULATOR_SUPPLY("vdd", "3-004b"),
+	/* L3G4200D Gyroscope device */
+	REGULATOR_SUPPLY("vdd", "2-0068"),
+	/* Ambient light sensor device */
+	REGULATOR_SUPPLY("vdd", "3-0029"),
+	/* Pressure sensor device */
+	REGULATOR_SUPPLY("vdd", "2-005c"),
+	/* Cypress TrueTouch Touchscreen device */
+	REGULATOR_SUPPLY("vcpin", "spi8.0"),
+	/* Camera device */
+	REGULATOR_SUPPLY("vaux12v5", "mmio_camera"),
+};
+
+static struct regulator_consumer_supply ab8500_vaux2_consumers[] = {
+	/* On-board eMMC power */
+	REGULATOR_SUPPLY("vmmc", "sdi4"),
+	/* AB8500 audio codec */
+	REGULATOR_SUPPLY("vcc-N2158", "ab8500-codec.0"),
+	/* AB8500 accessory detect 1 */
+	REGULATOR_SUPPLY("vcc-N2158", "ab8500-acc-det.0"),
+	/* AB8500 Tv-out device */
+	REGULATOR_SUPPLY("vcc-N2158", "mcde_tv_ab8500.4"),
+	/* AV8100 HDMI device */
+	REGULATOR_SUPPLY("vcc-N2158", "av8100_hdmi.3"),
+};
+
+static struct regulator_consumer_supply ab8500_vaux3_consumers[] = {
+	REGULATOR_SUPPLY("v-SD-STM", "stm"),
+	/* External MMC slot power */
+	REGULATOR_SUPPLY("vmmc", "sdi0"),
+};
+
+static struct regulator_consumer_supply ab8500_vtvout_consumers[] = {
+	/* TV-out DENC supply */
+	REGULATOR_SUPPLY("vtvout", "ab8500-denc.0"),
+	/* Internal general-purpose ADC */
+	REGULATOR_SUPPLY("vddadc", "ab8500-gpadc.0"),
+	/* ADC for charger */
+	REGULATOR_SUPPLY("vddadc", "ab8500-charger.0"),
+	/* AB8500 Tv-out device */
+	REGULATOR_SUPPLY("vtvout", "mcde_tv_ab8500.4"),
+};
+
+static struct regulator_consumer_supply ab8500_vaud_consumers[] = {
+	/* AB8500 audio-codec main supply */
+	REGULATOR_SUPPLY("vaud", "ab8500-codec.0"),
+};
+
+static struct regulator_consumer_supply ab8500_vamic1_consumers[] = {
+	/* AB8500 audio-codec Mic1 supply */
+	REGULATOR_SUPPLY("vamic1", "ab8500-codec.0"),
+};
+
+static struct regulator_consumer_supply ab8500_vamic2_consumers[] = {
+	/* AB8500 audio-codec Mic2 supply */
+	REGULATOR_SUPPLY("vamic2", "ab8500-codec.0"),
+};
+
+static struct regulator_consumer_supply ab8500_vdmic_consumers[] = {
+	/* AB8500 audio-codec DMic supply */
+	REGULATOR_SUPPLY("vdmic", "ab8500-codec.0"),
+};
+
+static struct regulator_consumer_supply ab8500_vintcore_consumers[] = {
+	/* SoC core supply, no device */
+	REGULATOR_SUPPLY("v-intcore", NULL),
+	/* USB Transceiver */
+	REGULATOR_SUPPLY("vddulpivio18", "ab8500-usb.0"),
+	/* Handled by abx500 clk driver */
+	REGULATOR_SUPPLY("v-intcore", "abx500-clk.0"),
+};
+
+static struct regulator_consumer_supply ab8500_vana_consumers[] = {
+	/* DB8500 DSI */
+	REGULATOR_SUPPLY("vdddsi1v2", "mcde"),
+	REGULATOR_SUPPLY("vdddsi1v2", "b2r2_core"),
+	REGULATOR_SUPPLY("vdddsi1v2", "b2r2_1_core"),
+	REGULATOR_SUPPLY("vdddsi1v2", "dsilink.0"),
+	REGULATOR_SUPPLY("vdddsi1v2", "dsilink.1"),
+	REGULATOR_SUPPLY("vdddsi1v2", "dsilink.2"),
+	/* DB8500 CSI */
+	REGULATOR_SUPPLY("vddcsi1v2", "mmio_camera"),
+};
+
+/* ab8500 regulator register initialization */
+static struct ab8500_regulator_reg_init ab8500_reg_init[] = {
+	/*
+	 * VanaRequestCtrl          = HP/LP depending on VxRequest
+	 * VextSupply1RequestCtrl   = HP/LP depending on VxRequest
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL2,       0xf0, 0x00),
+	/*
+	 * VextSupply2RequestCtrl   = HP/LP depending on VxRequest
+	 * VextSupply3RequestCtrl   = HP/LP depending on VxRequest
+	 * Vaux1RequestCtrl         = HP/LP depending on VxRequest
+	 * Vaux2RequestCtrl         = HP/LP depending on VxRequest
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL3,       0xff, 0x00),
+	/*
+	 * Vaux3RequestCtrl         = HP/LP depending on VxRequest
+	 * SwHPReq                  = Control through SWValid disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUREQUESTCTRL4,       0x07, 0x00),
+	/*
+	 * VanaSysClkReq1HPValid    = disabled
+	 * Vaux1SysClkReq1HPValid   = disabled
+	 * Vaux2SysClkReq1HPValid   = disabled
+	 * Vaux3SysClkReq1HPValid   = disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID1, 0xe8, 0x00),
+	/*
+	 * VextSupply1SysClkReq1HPValid = disabled
+	 * VextSupply2SysClkReq1HPValid = disabled
+	 * VextSupply3SysClkReq1HPValid = SysClkReq1 controlled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQ1HPVALID2, 0x70, 0x40),
+	/*
+	 * VanaHwHPReq1Valid        = disabled
+	 * Vaux1HwHPreq1Valid       = disabled
+	 * Vaux2HwHPReq1Valid       = disabled
+	 * Vaux3HwHPReqValid        = disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID1,     0xe8, 0x00),
+	/*
+	 * VextSupply1HwHPReq1Valid = disabled
+	 * VextSupply2HwHPReq1Valid = disabled
+	 * VextSupply3HwHPReq1Valid = disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ1VALID2,     0x07, 0x00),
+	/*
+	 * VanaHwHPReq2Valid        = disabled
+	 * Vaux1HwHPReq2Valid       = disabled
+	 * Vaux2HwHPReq2Valid       = disabled
+	 * Vaux3HwHPReq2Valid       = disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID1,     0xe8, 0x00),
+	/*
+	 * VextSupply1HwHPReq2Valid = disabled
+	 * VextSupply2HwHPReq2Valid = disabled
+	 * VextSupply3HwHPReq2Valid = HWReq2 controlled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUHWHPREQ2VALID2,     0x07, 0x04),
+	/*
+	 * VanaSwHPReqValid         = disabled
+	 * Vaux1SwHPReqValid        = disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID1,      0xa0, 0x00),
+	/*
+	 * Vaux2SwHPReqValid        = disabled
+	 * Vaux3SwHPReqValid        = disabled
+	 * VextSupply1SwHPReqValid  = disabled
+	 * VextSupply2SwHPReqValid  = disabled
+	 * VextSupply3SwHPReqValid  = disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUSWHPREQVALID2,      0x1f, 0x00),
+	/*
+	 * SysClkReq2Valid1         = SysClkReq2 controlled
+	 * SysClkReq3Valid1         = disabled
+	 * SysClkReq4Valid1         = SysClkReq4 controlled
+	 * SysClkReq5Valid1         = disabled
+	 * SysClkReq6Valid1         = SysClkReq6 controlled
+	 * SysClkReq7Valid1         = disabled
+	 * SysClkReq8Valid1         = disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID1,    0xfe, 0x2a),
+	/*
+	 * SysClkReq2Valid2         = disabled
+	 * SysClkReq3Valid2         = disabled
+	 * SysClkReq4Valid2         = disabled
+	 * SysClkReq5Valid2         = disabled
+	 * SysClkReq6Valid2         = SysClkReq6 controlled
+	 * SysClkReq7Valid2         = disabled
+	 * SysClkReq8Valid2         = disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUSYSCLKREQVALID2,    0xfe, 0x20),
+	/*
+	 * VTVoutEna                = disabled
+	 * Vintcore12Ena            = disabled
+	 * Vintcore12Sel            = 1.25 V
+	 * Vintcore12LP             = inactive (HP)
+	 * VTVoutLP                 = inactive (HP)
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUMISC1,              0xfe, 0x10),
+	/*
+	 * VaudioEna                = disabled
+	 * VdmicEna                 = disabled
+	 * Vamic1Ena                = disabled
+	 * Vamic2Ena                = disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_VAUDIOSUPPLY,           0x1e, 0x00),
+	/*
+	 * Vamic1_dzout             = high-Z when Vamic1 is disabled
+	 * Vamic2_dzout             = high-Z when Vamic2 is disabled
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUCTRL1VAMIC,         0x03, 0x00),
+	/*
+	 * VPll                     = Hw controlled (NOTE! PRCMU bits)
+	 * VanaRegu                 = force off
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_VPLLVANAREGU,           0x0f, 0x02),
+	/*
+	 * VrefDDREna               = disabled
+	 * VrefDDRSleepMode         = inactive (no pulldown)
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_VREFDDR,                0x03, 0x00),
+	/*
+	 * VextSupply1Regu          = force LP
+	 * VextSupply2Regu          = force OFF
+	 * VextSupply3Regu          = force HP (-> STBB2=LP and TPS=LP)
+	 * ExtSupply2Bypass         = ExtSupply12LPn ball is 0 when Ena is 0
+	 * ExtSupply3Bypass         = ExtSupply3LPn ball is 0 when Ena is 0
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_EXTSUPPLYREGU,          0xff, 0x13),
+	/*
+	 * Vaux1Regu                = force HP
+	 * Vaux2Regu                = force off
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_VAUX12REGU,             0x0f, 0x01),
+	/*
+	 * Vaux3Regu                = force off
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3REGU,          0x03, 0x00),
+	/*
+	 * Vaux1Sel                 = 2.8 V
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_VAUX1SEL,               0x0f, 0x0C),
+	/*
+	 * Vaux2Sel                 = 2.9 V
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_VAUX2SEL,               0x0f, 0x0d),
+	/*
+	 * Vaux3Sel                 = 2.91 V
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_VRF1VAUX3SEL,           0x07, 0x07),
+	/*
+	 * VextSupply12LP           = disabled (no LP)
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUCTRL2SPARE,         0x01, 0x00),
+	/*
+	 * Vaux1Disch               = short discharge time
+	 * Vaux2Disch               = short discharge time
+	 * Vaux3Disch               = short discharge time
+	 * Vintcore12Disch          = short discharge time
+	 * VTVoutDisch              = short discharge time
+	 * VaudioDisch              = short discharge time
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH,          0xfc, 0x00),
+	/*
+	 * VanaDisch                = short discharge time
+	 * VdmicPullDownEna         = pulldown disabled when Vdmic is disabled
+	 * VdmicDisch               = short discharge time
+	 */
+	INIT_REGULATOR_REGISTER(AB8500_REGUCTRLDISCH2,         0x16, 0x00),
+};
+
+/* AB8500 regulators */
+static struct regulator_init_data ab8500_regulators[AB8500_NUM_REGULATORS] = {
+	/* supplies to the display/camera */
+	[AB8500_LDO_AUX1] = {
+		.supply_regulator = "ab8500-ext-supply3",
+		.constraints = {
+			.name = "V-DISPLAY",
+			.min_uV = 2800000,
+			.max_uV = 3300000,
+			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+					  REGULATOR_CHANGE_STATUS,
+			.boot_on = 1, /* display is on at boot */
+		},
+		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaux1_consumers),
+		.consumer_supplies = ab8500_vaux1_consumers,
+	},
+	/* supplies to the on-board eMMC */
+	[AB8500_LDO_AUX2] = {
+		.supply_regulator = "ab8500-ext-supply3",
+		.constraints = {
+			.name = "V-eMMC1",
+			.min_uV = 1100000,
+			.max_uV = 3300000,
+			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+					  REGULATOR_CHANGE_STATUS |
+					  REGULATOR_CHANGE_MODE,
+			.valid_modes_mask = REGULATOR_MODE_NORMAL |
+					    REGULATOR_MODE_IDLE,
+		},
+		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaux2_consumers),
+		.consumer_supplies = ab8500_vaux2_consumers,
+	},
+	/* supply for VAUX3, supplies to SDcard slots */
+	[AB8500_LDO_AUX3] = {
+		.supply_regulator = "ab8500-ext-supply3",
+		.constraints = {
+			.name = "V-MMC-SD",
+			.min_uV = 1100000,
+			.max_uV = 3300000,
+			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+					  REGULATOR_CHANGE_STATUS |
+					  REGULATOR_CHANGE_MODE,
+			.valid_modes_mask = REGULATOR_MODE_NORMAL |
+					    REGULATOR_MODE_IDLE,
+		},
+		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaux3_consumers),
+		.consumer_supplies = ab8500_vaux3_consumers,
+	},
+	/* supply for tvout, gpadc, TVOUT LDO */
+	[AB8500_LDO_TVOUT] = {
+		.constraints = {
+			.name = "V-TVOUT",
+			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+		},
+		.num_consumer_supplies = ARRAY_SIZE(ab8500_vtvout_consumers),
+		.consumer_supplies = ab8500_vtvout_consumers,
+	},
+	/* supply for ab8500-vaudio, VAUDIO LDO */
+	[AB8500_LDO_AUDIO] = {
+		.constraints = {
+			.name = "V-AUD",
+			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+		},
+		.num_consumer_supplies = ARRAY_SIZE(ab8500_vaud_consumers),
+		.consumer_supplies = ab8500_vaud_consumers,
+	},
+	/* supply for v-anamic1 VAMic1-LDO */
+	[AB8500_LDO_ANAMIC1] = {
+		.constraints = {
+			.name = "V-AMIC1",
+			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+		},
+		.num_consumer_supplies = ARRAY_SIZE(ab8500_vamic1_consumers),
+		.consumer_supplies = ab8500_vamic1_consumers,
+	},
+	/* supply for v-amic2, VAMIC2 LDO, reuse constants for AMIC1 */
+	[AB8500_LDO_ANAMIC2] = {
+		.constraints = {
+			.name = "V-AMIC2",
+			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+		},
+		.num_consumer_supplies = ARRAY_SIZE(ab8500_vamic2_consumers),
+		.consumer_supplies = ab8500_vamic2_consumers,
+	},
+	/* supply for v-dmic, VDMIC LDO */
+	[AB8500_LDO_DMIC] = {
+		.constraints = {
+			.name = "V-DMIC",
+			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+		},
+		.num_consumer_supplies = ARRAY_SIZE(ab8500_vdmic_consumers),
+		.consumer_supplies = ab8500_vdmic_consumers,
+	},
+	/* supply for v-intcore12, VINTCORE12 LDO */
+	[AB8500_LDO_INTCORE] = {
+		.constraints = {
+			.name = "V-INTCORE",
+			.min_uV = 1250000,
+			.max_uV = 1350000,
+			.input_uV = 1800000,
+			.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE |
+					  REGULATOR_CHANGE_STATUS |
+					  REGULATOR_CHANGE_MODE |
+					  REGULATOR_CHANGE_DRMS,
+			.valid_modes_mask = REGULATOR_MODE_NORMAL |
+					    REGULATOR_MODE_IDLE,
+		},
+		.num_consumer_supplies = ARRAY_SIZE(ab8500_vintcore_consumers),
+		.consumer_supplies = ab8500_vintcore_consumers,
+	},
+	/* supply for U8500 CSI-DSI, VANA LDO */
+	[AB8500_LDO_ANA] = {
+		.constraints = {
+			.name = "V-CSI-DSI",
+			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+		},
+		.num_consumer_supplies = ARRAY_SIZE(ab8500_vana_consumers),
+		.consumer_supplies = ab8500_vana_consumers,
+	},
+};
+
+/* supply for VextSupply3 */
+static struct regulator_consumer_supply ab8500_ext_supply3_consumers[] = {
+	/* SIM supply for 3 V SIM cards */
+	REGULATOR_SUPPLY("vinvsim", "sim-detect.0"),
+};
+
+/*
+ * AB8500 external regulators
+ */
+static struct regulator_init_data ab8500_ext_regulators[] = {
+	/* fixed Vbat supplies VSMPS1_EXT_1V8 */
+	[AB8500_EXT_SUPPLY1] = {
+		.constraints = {
+			.name = "ab8500-ext-supply1",
+			.min_uV = 1800000,
+			.max_uV = 1800000,
+			.initial_mode = REGULATOR_MODE_IDLE,
+			.boot_on = 1,
+			.always_on = 1,
+		},
+	},
+	/* fixed Vbat supplies VSMPS2_EXT_1V36 and VSMPS5_EXT_1V15 */
+	[AB8500_EXT_SUPPLY2] = {
+		.constraints = {
+			.name = "ab8500-ext-supply2",
+			.min_uV = 1360000,
+			.max_uV = 1360000,
+		},
+	},
+	/* fixed Vbat supplies VSMPS3_EXT_3V4 and VSMPS4_EXT_3V4 */
+	[AB8500_EXT_SUPPLY3] = {
+		.constraints = {
+			.name = "ab8500-ext-supply3",
+			.min_uV = 3400000,
+			.max_uV = 3400000,
+			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+			.boot_on = 1,
+		},
+		.num_consumer_supplies =
+			ARRAY_SIZE(ab8500_ext_supply3_consumers),
+		.consumer_supplies = ab8500_ext_supply3_consumers,
+	},
+};
+
+static struct ab8500_regulator_platform_data ab8500_regulator_plat_data = {
+	.reg_init               = ab8500_reg_init,
+	.num_reg_init           = ARRAY_SIZE(ab8500_reg_init),
+	.regulator              = ab8500_regulators,
+	.num_regulator          = ARRAY_SIZE(ab8500_regulators),
+	.ext_regulator          = ab8500_ext_regulators,
+	.num_ext_regulator      = ARRAY_SIZE(ab8500_ext_regulators),
+};
+
 /**
  * struct ab8500_ext_regulator_info - ab8500 regulator information
  * @dev: device pointer
@@ -344,8 +794,7 @@ static struct of_regulator_match ab8500_ext_regulator_match[] = {
 static int ab8500_ext_regulator_probe(struct platform_device *pdev)
 {
 	struct ab8500 *ab8500 = dev_get_drvdata(pdev->dev.parent);
-	struct ab8500_platform_data *ppdata;
-	struct ab8500_regulator_platform_data *pdata;
+	struct ab8500_regulator_platform_data *pdata = &ab8500_regulator_plat_data;
 	struct device_node *np = pdev->dev.of_node;
 	struct regulator_config config = { };
 	int i, err;
@@ -366,18 +815,6 @@ static int ab8500_ext_regulator_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	ppdata = dev_get_platdata(ab8500->dev);
-	if (!ppdata) {
-		dev_err(&pdev->dev, "null parent pdata\n");
-		return -EINVAL;
-	}
-
-	pdata = ppdata->regulator;
-	if (!pdata) {
-		dev_err(&pdev->dev, "null pdata\n");
-		return -EINVAL;
-	}
-
 	/* make sure the platform data has the correct size */
 	if (pdata->num_ext_regulator != ARRAY_SIZE(ab8500_ext_regulator_info)) {
 		dev_err(&pdev->dev, "Configuration error: size mismatch.\n");
diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig
index 0b2733db0e9e..4be1b8c21f6f 100644
--- a/drivers/reset/Kconfig
+++ b/drivers/reset/Kconfig
@@ -12,8 +12,22 @@ menuconfig RESET_CONTROLLER
 
 	  If unsure, say no.
 
+if RESET_CONTROLLER
+
 config RESET_OXNAS
 	bool
 
+config TI_SYSCON_RESET
+	tristate "TI SYSCON Reset Driver"
+	depends on HAS_IOMEM
+	select MFD_SYSCON
+	help
+	  This enables the reset driver support for TI devices with
+	  memory-mapped reset registers as part of a syscon device node. If
+	  you wish to use the reset framework for such memory-mapped devices,
+	  say Y here. Otherwise, say N.
+
 source "drivers/reset/sti/Kconfig"
 source "drivers/reset/hisilicon/Kconfig"
+
+endif
diff --git a/drivers/reset/Makefile b/drivers/reset/Makefile
index f173fc3847b4..5d65a93d3c43 100644
--- a/drivers/reset/Makefile
+++ b/drivers/reset/Makefile
@@ -3,9 +3,11 @@ obj-$(CONFIG_ARCH_LPC18XX) += reset-lpc18xx.o
 obj-$(CONFIG_ARCH_SOCFPGA) += reset-socfpga.o
 obj-$(CONFIG_ARCH_BERLIN) += reset-berlin.o
 obj-$(CONFIG_MACH_PISTACHIO) += reset-pistachio.o
+obj-$(CONFIG_ARCH_MESON) += reset-meson.o
 obj-$(CONFIG_ARCH_SUNXI) += reset-sunxi.o
 obj-$(CONFIG_ARCH_STI) += sti/
 obj-$(CONFIG_ARCH_HISI) += hisilicon/
 obj-$(CONFIG_ARCH_ZYNQ) += reset-zynq.o
 obj-$(CONFIG_ATH79) += reset-ath79.o
 obj-$(CONFIG_RESET_OXNAS) += reset-oxnas.o
+obj-$(CONFIG_TI_SYSCON_RESET) += reset-ti-syscon.o
diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index 72b32bd15549..395dc9ce492e 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -93,6 +93,43 @@ void reset_controller_unregister(struct reset_controller_dev *rcdev)
 }
 EXPORT_SYMBOL_GPL(reset_controller_unregister);
 
+static void devm_reset_controller_release(struct device *dev, void *res)
+{
+	reset_controller_unregister(*(struct reset_controller_dev **)res);
+}
+
+/**
+ * devm_reset_controller_register - resource managed reset_controller_register()
+ * @dev: device that is registering this reset controller
+ * @rcdev: a pointer to the initialized reset controller device
+ *
+ * Managed reset_controller_register(). For reset controllers registered by
+ * this function, reset_controller_unregister() is automatically called on
+ * driver detach. See reset_controller_register() for more information.
+ */
+int devm_reset_controller_register(struct device *dev,
+				   struct reset_controller_dev *rcdev)
+{
+	struct reset_controller_dev **rcdevp;
+	int ret;
+
+	rcdevp = devres_alloc(devm_reset_controller_release, sizeof(*rcdevp),
+			      GFP_KERNEL);
+	if (!rcdevp)
+		return -ENOMEM;
+
+	ret = reset_controller_register(rcdev);
+	if (!ret) {
+		*rcdevp = rcdev;
+		devres_add(dev, rcdevp);
+	} else {
+		devres_free(rcdevp);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devm_reset_controller_register);
+
 /**
  * reset_control_reset - reset the controlled device
  * @rstc: reset controller
diff --git a/drivers/reset/hisilicon/hi6220_reset.c b/drivers/reset/hisilicon/hi6220_reset.c
index 8f55fd4a2630..35ce53edabf9 100644
--- a/drivers/reset/hisilicon/hi6220_reset.c
+++ b/drivers/reset/hisilicon/hi6220_reset.c
@@ -1,7 +1,8 @@
 /*
  * Hisilicon Hi6220 reset controller driver
  *
- * Copyright (c) 2015 Hisilicon Limited.
+ * Copyright (c) 2016 Linaro Limited.
+ * Copyright (c) 2015-2016 Hisilicon Limited.
  *
  * Author: Feng Chen <puck.chen@hisilicon.com>
  *
@@ -15,81 +16,130 @@
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
 #include <linux/reset-controller.h>
 #include <linux/reset.h>
 #include <linux/platform_device.h>
 
-#define ASSERT_OFFSET            0x300
-#define DEASSERT_OFFSET          0x304
-#define MAX_INDEX                0x509
+#define PERIPH_ASSERT_OFFSET      0x300
+#define PERIPH_DEASSERT_OFFSET    0x304
+#define PERIPH_MAX_INDEX          0x509
+
+#define SC_MEDIA_RSTEN            0x052C
+#define SC_MEDIA_RSTDIS           0x0530
+#define MEDIA_MAX_INDEX           8
 
 #define to_reset_data(x) container_of(x, struct hi6220_reset_data, rc_dev)
 
+enum hi6220_reset_ctrl_type {
+	PERIPHERAL,
+	MEDIA,
+};
+
 struct hi6220_reset_data {
-	void __iomem			*assert_base;
-	void __iomem			*deassert_base;
-	struct reset_controller_dev	rc_dev;
+	struct reset_controller_dev rc_dev;
+	struct regmap *regmap;
 };
 
-static int hi6220_reset_assert(struct reset_controller_dev *rc_dev,
-			       unsigned long idx)
+static int hi6220_peripheral_assert(struct reset_controller_dev *rc_dev,
+				    unsigned long idx)
 {
 	struct hi6220_reset_data *data = to_reset_data(rc_dev);
+	struct regmap *regmap = data->regmap;
+	u32 bank = idx >> 8;
+	u32 offset = idx & 0xff;
+	u32 reg = PERIPH_ASSERT_OFFSET + bank * 0x10;
 
-	int bank = idx >> 8;
-	int offset = idx & 0xff;
+	return regmap_write(regmap, reg, BIT(offset));
+}
 
-	writel(BIT(offset), data->assert_base + (bank * 0x10));
+static int hi6220_peripheral_deassert(struct reset_controller_dev *rc_dev,
+				      unsigned long idx)
+{
+	struct hi6220_reset_data *data = to_reset_data(rc_dev);
+	struct regmap *regmap = data->regmap;
+	u32 bank = idx >> 8;
+	u32 offset = idx & 0xff;
+	u32 reg = PERIPH_DEASSERT_OFFSET + bank * 0x10;
 
-	return 0;
+	return regmap_write(regmap, reg, BIT(offset));
 }
 
-static int hi6220_reset_deassert(struct reset_controller_dev *rc_dev,
-				 unsigned long idx)
+static const struct reset_control_ops hi6220_peripheral_reset_ops = {
+	.assert = hi6220_peripheral_assert,
+	.deassert = hi6220_peripheral_deassert,
+};
+
+static int hi6220_media_assert(struct reset_controller_dev *rc_dev,
+			       unsigned long idx)
 {
 	struct hi6220_reset_data *data = to_reset_data(rc_dev);
+	struct regmap *regmap = data->regmap;
 
-	int bank = idx >> 8;
-	int offset = idx & 0xff;
+	return regmap_write(regmap, SC_MEDIA_RSTEN, BIT(idx));
+}
 
-	writel(BIT(offset), data->deassert_base + (bank * 0x10));
+static int hi6220_media_deassert(struct reset_controller_dev *rc_dev,
+				 unsigned long idx)
+{
+	struct hi6220_reset_data *data = to_reset_data(rc_dev);
+	struct regmap *regmap = data->regmap;
 
-	return 0;
+	return regmap_write(regmap, SC_MEDIA_RSTDIS, BIT(idx));
 }
 
-static const struct reset_control_ops hi6220_reset_ops = {
-	.assert = hi6220_reset_assert,
-	.deassert = hi6220_reset_deassert,
+static const struct reset_control_ops hi6220_media_reset_ops = {
+	.assert = hi6220_media_assert,
+	.deassert = hi6220_media_deassert,
 };
 
 static int hi6220_reset_probe(struct platform_device *pdev)
 {
+	struct device_node *np = pdev->dev.of_node;
+	struct device *dev = &pdev->dev;
+	enum hi6220_reset_ctrl_type type;
 	struct hi6220_reset_data *data;
-	struct resource *res;
-	void __iomem *src_base;
+	struct regmap *regmap;
 
-	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	src_base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(src_base))
-		return PTR_ERR(src_base);
+	type = (enum hi6220_reset_ctrl_type)of_device_get_match_data(dev);
+
+	regmap = syscon_node_to_regmap(np);
+	if (IS_ERR(regmap)) {
+		dev_err(dev, "failed to get reset controller regmap\n");
+		return PTR_ERR(regmap);
+	}
 
-	data->assert_base = src_base + ASSERT_OFFSET;
-	data->deassert_base = src_base + DEASSERT_OFFSET;
-	data->rc_dev.nr_resets = MAX_INDEX;
-	data->rc_dev.ops = &hi6220_reset_ops;
-	data->rc_dev.of_node = pdev->dev.of_node;
+	data->regmap = regmap;
+	data->rc_dev.of_node = np;
+	if (type == MEDIA) {
+		data->rc_dev.ops = &hi6220_media_reset_ops;
+		data->rc_dev.nr_resets = MEDIA_MAX_INDEX;
+	} else {
+		data->rc_dev.ops = &hi6220_peripheral_reset_ops;
+		data->rc_dev.nr_resets = PERIPH_MAX_INDEX;
+	}
 
 	return reset_controller_register(&data->rc_dev);
 }
 
 static const struct of_device_id hi6220_reset_match[] = {
-	{ .compatible = "hisilicon,hi6220-sysctrl" },
-	{ },
+	{
+		.compatible = "hisilicon,hi6220-sysctrl",
+		.data = (void *)PERIPHERAL,
+	},
+	{
+		.compatible = "hisilicon,hi6220-mediactrl",
+		.data = (void *)MEDIA,
+	},
+	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, hi6220_reset_match);
 
 static struct platform_driver hi6220_reset_driver = {
 	.probe = hi6220_reset_probe,
diff --git a/drivers/reset/reset-ath79.c b/drivers/reset/reset-ath79.c
index ccb940a8d9fb..16d410cd6146 100644
--- a/drivers/reset/reset-ath79.c
+++ b/drivers/reset/reset-ath79.c
@@ -112,7 +112,7 @@ static int ath79_reset_probe(struct platform_device *pdev)
 	ath79_reset->rcdev.of_reset_n_cells = 1;
 	ath79_reset->rcdev.nr_resets = 32;
 
-	err = reset_controller_register(&ath79_reset->rcdev);
+	err = devm_reset_controller_register(&pdev->dev, &ath79_reset->rcdev);
 	if (err)
 		return err;
 
@@ -131,7 +131,6 @@ static int ath79_reset_remove(struct platform_device *pdev)
 	struct ath79_reset *ath79_reset = platform_get_drvdata(pdev);
 
 	unregister_restart_handler(&ath79_reset->restart_nb);
-	reset_controller_unregister(&ath79_reset->rcdev);
 
 	return 0;
 }
diff --git a/drivers/reset/reset-meson.c b/drivers/reset/reset-meson.c
new file mode 100644
index 000000000000..c32f11a30c5f
--- /dev/null
+++ b/drivers/reset/reset-meson.c
@@ -0,0 +1,136 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * BSD LICENSE
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset-controller.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#define REG_COUNT	8
+#define BITS_PER_REG	32
+
+struct meson_reset {
+	void __iomem *reg_base;
+	struct reset_controller_dev rcdev;
+};
+
+static int meson_reset_reset(struct reset_controller_dev *rcdev,
+			      unsigned long id)
+{
+	struct meson_reset *data =
+		container_of(rcdev, struct meson_reset, rcdev);
+	unsigned int bank = id / BITS_PER_REG;
+	unsigned int offset = id % BITS_PER_REG;
+	void __iomem *reg_addr = data->reg_base + (bank << 2);
+
+	if (bank >= REG_COUNT)
+		return -EINVAL;
+
+	writel(BIT(offset), reg_addr);
+
+	return 0;
+}
+
+static const struct reset_control_ops meson_reset_ops = {
+	.reset		= meson_reset_reset,
+};
+
+static const struct of_device_id meson_reset_dt_ids[] = {
+	 { .compatible = "amlogic,meson8b-reset", },
+	 { .compatible = "amlogic,meson-gxbb-reset", },
+	 { /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, meson_reset_dt_ids);
+
+static int meson_reset_probe(struct platform_device *pdev)
+{
+	struct meson_reset *data;
+	struct resource *res;
+
+	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->reg_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(data->reg_base))
+		return PTR_ERR(data->reg_base);
+
+	platform_set_drvdata(pdev, data);
+
+	data->rcdev.owner = THIS_MODULE;
+	data->rcdev.nr_resets = REG_COUNT * BITS_PER_REG;
+	data->rcdev.ops = &meson_reset_ops;
+	data->rcdev.of_node = pdev->dev.of_node;
+
+	return devm_reset_controller_register(&pdev->dev, &data->rcdev);
+}
+
+static struct platform_driver meson_reset_driver = {
+	.probe	= meson_reset_probe,
+	.driver = {
+		.name		= "meson_reset",
+		.of_match_table	= meson_reset_dt_ids,
+	},
+};
+
+module_platform_driver(meson_reset_driver);
+
+MODULE_AUTHOR("Neil Armstrong <narmstrong@baylibre.com>");
+MODULE_DESCRIPTION("Amlogic Meson Reset Controller driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/reset/reset-oxnas.c b/drivers/reset/reset-oxnas.c
index c60fb2dace3e..944980572f79 100644
--- a/drivers/reset/reset-oxnas.c
+++ b/drivers/reset/reset-oxnas.c
@@ -112,21 +112,11 @@ static int oxnas_reset_probe(struct platform_device *pdev)
 	data->rcdev.ops = &oxnas_reset_ops;
 	data->rcdev.of_node = pdev->dev.of_node;
 
-	return reset_controller_register(&data->rcdev);
-}
-
-static int oxnas_reset_remove(struct platform_device *pdev)
-{
-	struct oxnas_reset *data = platform_get_drvdata(pdev);
-
-	reset_controller_unregister(&data->rcdev);
-
-	return 0;
+	return devm_reset_controller_register(&pdev->dev, &data->rcdev);
 }
 
 static struct platform_driver oxnas_reset_driver = {
 	.probe	= oxnas_reset_probe,
-	.remove	= oxnas_reset_remove,
 	.driver = {
 		.name		= "oxnas-reset",
 		.of_match_table	= oxnas_reset_dt_ids,
diff --git a/drivers/reset/reset-pistachio.c b/drivers/reset/reset-pistachio.c
index 72a97a15a4c8..bbc4c06dd33b 100644
--- a/drivers/reset/reset-pistachio.c
+++ b/drivers/reset/reset-pistachio.c
@@ -121,16 +121,7 @@ static int pistachio_reset_probe(struct platform_device *pdev)
 	rd->rcdev.ops = &pistachio_reset_ops;
 	rd->rcdev.of_node = np;
 
-	return reset_controller_register(&rd->rcdev);
-}
-
-static int pistachio_reset_remove(struct platform_device *pdev)
-{
-	struct pistachio_reset_data *data = platform_get_drvdata(pdev);
-
-	reset_controller_unregister(&data->rcdev);
-
-	return 0;
+	return devm_reset_controller_register(dev, &rd->rcdev);
 }
 
 static const struct of_device_id pistachio_reset_dt_ids[] = {
@@ -141,7 +132,6 @@ MODULE_DEVICE_TABLE(of, pistachio_reset_dt_ids);
 
 static struct platform_driver pistachio_reset_driver = {
 	.probe	= pistachio_reset_probe,
-	.remove	= pistachio_reset_remove,
 	.driver = {
 		.name		= "pistachio-reset",
 		.of_match_table	= pistachio_reset_dt_ids,
diff --git a/drivers/reset/reset-socfpga.c b/drivers/reset/reset-socfpga.c
index cd05a7032b17..12add9b0fa49 100644
--- a/drivers/reset/reset-socfpga.c
+++ b/drivers/reset/reset-socfpga.c
@@ -134,16 +134,7 @@ static int socfpga_reset_probe(struct platform_device *pdev)
 	data->rcdev.ops = &socfpga_reset_ops;
 	data->rcdev.of_node = pdev->dev.of_node;
 
-	return reset_controller_register(&data->rcdev);
-}
-
-static int socfpga_reset_remove(struct platform_device *pdev)
-{
-	struct socfpga_reset_data *data = platform_get_drvdata(pdev);
-
-	reset_controller_unregister(&data->rcdev);
-
-	return 0;
+	return devm_reset_controller_register(dev, &data->rcdev);
 }
 
 static const struct of_device_id socfpga_reset_dt_ids[] = {
@@ -153,7 +144,6 @@ static const struct of_device_id socfpga_reset_dt_ids[] = {
 
 static struct platform_driver socfpga_reset_driver = {
 	.probe	= socfpga_reset_probe,
-	.remove	= socfpga_reset_remove,
 	.driver = {
 		.name		= "socfpga-reset",
 		.of_match_table	= socfpga_reset_dt_ids,
diff --git a/drivers/reset/reset-sunxi.c b/drivers/reset/reset-sunxi.c
index 677f86555212..3080190b3f90 100644
--- a/drivers/reset/reset-sunxi.c
+++ b/drivers/reset/reset-sunxi.c
@@ -165,21 +165,11 @@ static int sunxi_reset_probe(struct platform_device *pdev)
 	data->rcdev.ops = &sunxi_reset_ops;
 	data->rcdev.of_node = pdev->dev.of_node;
 
-	return reset_controller_register(&data->rcdev);
-}
-
-static int sunxi_reset_remove(struct platform_device *pdev)
-{
-	struct sunxi_reset_data *data = platform_get_drvdata(pdev);
-
-	reset_controller_unregister(&data->rcdev);
-
-	return 0;
+	return devm_reset_controller_register(&pdev->dev, &data->rcdev);
 }
 
 static struct platform_driver sunxi_reset_driver = {
 	.probe	= sunxi_reset_probe,
-	.remove	= sunxi_reset_remove,
 	.driver = {
 		.name		= "sunxi-reset",
 		.of_match_table	= sunxi_reset_dt_ids,
diff --git a/drivers/reset/reset-ti-syscon.c b/drivers/reset/reset-ti-syscon.c
new file mode 100644
index 000000000000..47f0ffd3b013
--- /dev/null
+++ b/drivers/reset/reset-ti-syscon.c
@@ -0,0 +1,237 @@
+/*
+ * TI SYSCON regmap reset driver
+ *
+ * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/
+ *	Andrew F. Davis <afd@ti.com>
+ *	Suman Anna <afd@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+
+#include <dt-bindings/reset/ti-syscon.h>
+
+/**
+ * struct ti_syscon_reset_control - reset control structure
+ * @assert_offset: reset assert control register offset from syscon base
+ * @assert_bit: reset assert bit in the reset assert control register
+ * @deassert_offset: reset deassert control register offset from syscon base
+ * @deassert_bit: reset deassert bit in the reset deassert control register
+ * @status_offset: reset status register offset from syscon base
+ * @status_bit: reset status bit in the reset status register
+ * @flags: reset flag indicating how the (de)assert and status are handled
+ */
+struct ti_syscon_reset_control {
+	unsigned int assert_offset;
+	unsigned int assert_bit;
+	unsigned int deassert_offset;
+	unsigned int deassert_bit;
+	unsigned int status_offset;
+	unsigned int status_bit;
+	u32 flags;
+};
+
+/**
+ * struct ti_syscon_reset_data - reset controller information structure
+ * @rcdev: reset controller entity
+ * @regmap: regmap handle containing the memory-mapped reset registers
+ * @controls: array of reset controls
+ * @nr_controls: number of controls in control array
+ */
+struct ti_syscon_reset_data {
+	struct reset_controller_dev rcdev;
+	struct regmap *regmap;
+	struct ti_syscon_reset_control *controls;
+	unsigned int nr_controls;
+};
+
+#define to_ti_syscon_reset_data(rcdev)	\
+	container_of(rcdev, struct ti_syscon_reset_data, rcdev)
+
+/**
+ * ti_syscon_reset_assert() - assert device reset
+ * @rcdev: reset controller entity
+ * @id: ID of the reset to be asserted
+ *
+ * This function implements the reset driver op to assert a device's reset.
+ * This asserts the reset in a manner prescribed by the reset flags.
+ *
+ * Return: 0 for successful request, else a corresponding error value
+ */
+static int ti_syscon_reset_assert(struct reset_controller_dev *rcdev,
+				  unsigned long id)
+{
+	struct ti_syscon_reset_data *data = to_ti_syscon_reset_data(rcdev);
+	struct ti_syscon_reset_control *control;
+	unsigned int mask, value;
+
+	if (id >= data->nr_controls)
+		return -EINVAL;
+
+	control = &data->controls[id];
+
+	if (control->flags & ASSERT_NONE)
+		return -ENOTSUPP; /* assert not supported for this reset */
+
+	mask = BIT(control->assert_bit);
+	value = (control->flags & ASSERT_SET) ? mask : 0x0;
+
+	return regmap_update_bits(data->regmap, control->assert_offset, mask, value);
+}
+
+/**
+ * ti_syscon_reset_deassert() - deassert device reset
+ * @rcdev: reset controller entity
+ * @id: ID of reset to be deasserted
+ *
+ * This function implements the reset driver op to deassert a device's reset.
+ * This deasserts the reset in a manner prescribed by the reset flags.
+ *
+ * Return: 0 for successful request, else a corresponding error value
+ */
+static int ti_syscon_reset_deassert(struct reset_controller_dev *rcdev,
+				    unsigned long id)
+{
+	struct ti_syscon_reset_data *data = to_ti_syscon_reset_data(rcdev);
+	struct ti_syscon_reset_control *control;
+	unsigned int mask, value;
+
+	if (id >= data->nr_controls)
+		return -EINVAL;
+
+	control = &data->controls[id];
+
+	if (control->flags & DEASSERT_NONE)
+		return -ENOTSUPP; /* deassert not supported for this reset */
+
+	mask = BIT(control->deassert_bit);
+	value = (control->flags & DEASSERT_SET) ? mask : 0x0;
+
+	return regmap_update_bits(data->regmap, control->deassert_offset, mask, value);
+}
+
+/**
+ * ti_syscon_reset_status() - check device reset status
+ * @rcdev: reset controller entity
+ * @id: ID of the reset for which the status is being requested
+ *
+ * This function implements the reset driver op to return the status of a
+ * device's reset.
+ *
+ * Return: 0 if reset is deasserted, true if reset is asserted, else a
+ * corresponding error value
+ */
+static int ti_syscon_reset_status(struct reset_controller_dev *rcdev,
+				  unsigned long id)
+{
+	struct ti_syscon_reset_data *data = to_ti_syscon_reset_data(rcdev);
+	struct ti_syscon_reset_control *control;
+	unsigned int reset_state;
+	int ret;
+
+	if (id >= data->nr_controls)
+		return -EINVAL;
+
+	control = &data->controls[id];
+
+	if (control->flags & STATUS_NONE)
+		return -ENOTSUPP; /* status not supported for this reset */
+
+	ret = regmap_read(data->regmap, control->status_offset, &reset_state);
+	if (ret)
+		return ret;
+
+	return (reset_state & BIT(control->status_bit)) &&
+			(control->flags & STATUS_SET);
+}
+
+static struct reset_control_ops ti_syscon_reset_ops = {
+	.assert		= ti_syscon_reset_assert,
+	.deassert	= ti_syscon_reset_deassert,
+	.status		= ti_syscon_reset_status,
+};
+
+static int ti_syscon_reset_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct ti_syscon_reset_data *data;
+	struct regmap *regmap;
+	const __be32 *list;
+	struct ti_syscon_reset_control *controls;
+	int size, nr_controls, i;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	regmap = syscon_node_to_regmap(np->parent);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	list = of_get_property(np, "ti,reset-bits", &size);
+	if (!list || (size / sizeof(*list)) % 7 != 0) {
+		dev_err(dev, "invalid DT reset description\n");
+		return -EINVAL;
+	}
+
+	nr_controls = (size / sizeof(*list)) / 7;
+	controls = devm_kzalloc(dev, nr_controls * sizeof(*controls), GFP_KERNEL);
+	if (!controls)
+		return -ENOMEM;
+
+	for (i = 0; i < nr_controls; i++) {
+		controls[i].assert_offset = be32_to_cpup(list++);
+		controls[i].assert_bit = be32_to_cpup(list++);
+		controls[i].deassert_offset = be32_to_cpup(list++);
+		controls[i].deassert_bit = be32_to_cpup(list++);
+		controls[i].status_offset = be32_to_cpup(list++);
+		controls[i].status_bit = be32_to_cpup(list++);
+		controls[i].flags = be32_to_cpup(list++);
+	}
+
+	data->rcdev.ops = &ti_syscon_reset_ops;
+	data->rcdev.owner = THIS_MODULE;
+	data->rcdev.of_node = np;
+	data->rcdev.nr_resets = nr_controls;
+	data->regmap = regmap;
+	data->controls = controls;
+	data->nr_controls = nr_controls;
+
+	platform_set_drvdata(pdev, data);
+
+	return devm_reset_controller_register(dev, &data->rcdev);
+}
+
+static const struct of_device_id ti_syscon_reset_of_match[] = {
+	{ .compatible = "ti,syscon-reset", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, ti_syscon_reset_of_match);
+
+static struct platform_driver ti_syscon_reset_driver = {
+	.probe = ti_syscon_reset_probe,
+	.driver = {
+		.name = "ti-syscon-reset",
+		.of_match_table = ti_syscon_reset_of_match,
+	},
+};
+module_platform_driver(ti_syscon_reset_driver);
+
+MODULE_AUTHOR("Andrew F. Davis <afd@ti.com>");
+MODULE_AUTHOR("Suman Anna <s-anna@ti.com>");
+MODULE_DESCRIPTION("TI SYSCON Regmap Reset Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/reset/reset-zynq.c b/drivers/reset/reset-zynq.c
index a7e87bc45885..138f2f205662 100644
--- a/drivers/reset/reset-zynq.c
+++ b/drivers/reset/reset-zynq.c
@@ -122,16 +122,7 @@ static int zynq_reset_probe(struct platform_device *pdev)
 	priv->rcdev.ops = &zynq_reset_ops;
 	priv->rcdev.of_node = pdev->dev.of_node;
 
-	return reset_controller_register(&priv->rcdev);
-}
-
-static int zynq_reset_remove(struct platform_device *pdev)
-{
-	struct zynq_reset_data *priv = platform_get_drvdata(pdev);
-
-	reset_controller_unregister(&priv->rcdev);
-
-	return 0;
+	return devm_reset_controller_register(&pdev->dev, &priv->rcdev);
 }
 
 static const struct of_device_id zynq_reset_dt_ids[] = {
@@ -141,7 +132,6 @@ static const struct of_device_id zynq_reset_dt_ids[] = {
 
 static struct platform_driver zynq_reset_driver = {
 	.probe	= zynq_reset_probe,
-	.remove	= zynq_reset_remove,
 	.driver = {
 		.name		= KBUILD_MODNAME,
 		.of_match_table	= zynq_reset_dt_ids,
diff --git a/drivers/reset/sti/Kconfig b/drivers/reset/sti/Kconfig
index f8c15a37fb35..613178553612 100644
--- a/drivers/reset/sti/Kconfig
+++ b/drivers/reset/sti/Kconfig
@@ -2,7 +2,6 @@ if ARCH_STI
 
 config STI_RESET_SYSCFG
 	bool
-	select RESET_CONTROLLER
 
 config STIH415_RESET
 	bool
diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c
index 9c18d6fd8107..ea20f627dabe 100644
--- a/drivers/rtc/rtc-opal.c
+++ b/drivers/rtc/rtc-opal.c
@@ -134,7 +134,7 @@ static int opal_get_tpo_time(struct device *dev, struct rtc_wkalrm *alarm)
 		goto exit;
 	}
 
-	rc = be64_to_cpu(msg.params[1]);
+	rc = opal_get_async_rc(msg);
 	if (rc != OPAL_SUCCESS) {
 		rc = -EIO;
 		goto exit;
@@ -181,7 +181,7 @@ static int opal_set_tpo_time(struct device *dev, struct rtc_wkalrm *alarm)
 		goto exit;
 	}
 
-	rc = be64_to_cpu(msg.params[1]);
+	rc = opal_get_async_rc(msg);
 	if (rc != OPAL_SUCCESS)
 		rc = -EIO;
 
diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index 0ac520dd1b21..c71df0c7dedc 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -46,7 +46,8 @@ struct read_info_sccb {
 	u64	rnmax2;			/* 104-111 */
 	u8	_pad_112[116 - 112];	/* 112-115 */
 	u8	fac116;			/* 116 */
-	u8	_pad_117[119 - 117];	/* 117-118 */
+	u8	fac117;			/* 117 */
+	u8	_pad_118;		/* 118 */
 	u8	fac119;			/* 119 */
 	u16	hcpua;			/* 120-121 */
 	u8	_pad_122[124 - 122];	/* 122-123 */
@@ -114,7 +115,12 @@ static void __init sclp_facilities_detect(struct read_info_sccb *sccb)
 	sclp.facilities = sccb->facilities;
 	sclp.has_sprp = !!(sccb->fac84 & 0x02);
 	sclp.has_core_type = !!(sccb->fac84 & 0x01);
+	sclp.has_gsls = !!(sccb->fac85 & 0x80);
+	sclp.has_64bscao = !!(sccb->fac116 & 0x80);
+	sclp.has_cmma = !!(sccb->fac116 & 0x40);
 	sclp.has_esca = !!(sccb->fac116 & 0x08);
+	sclp.has_pfmfi = !!(sccb->fac117 & 0x40);
+	sclp.has_ibs = !!(sccb->fac117 & 0x20);
 	sclp.has_hvs = !!(sccb->fac119 & 0x80);
 	if (sccb->fac85 & 0x02)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP;
@@ -145,6 +151,10 @@ static void __init sclp_facilities_detect(struct read_info_sccb *sccb)
 		sclp.has_siif = cpue->siif;
 		sclp.has_sigpif = cpue->sigpif;
 		sclp.has_sief2 = cpue->sief2;
+		sclp.has_gpere = cpue->gpere;
+		sclp.has_ib = cpue->ib;
+		sclp.has_cei = cpue->cei;
+		sclp.has_skey = cpue->skey;
 		break;
 	}
 
diff --git a/drivers/s390/char/sclp_ocf.c b/drivers/s390/char/sclp_ocf.c
index 2553db0fdb52..f59b71776bbd 100644
--- a/drivers/s390/char/sclp_ocf.c
+++ b/drivers/s390/char/sclp_ocf.c
@@ -26,7 +26,7 @@
 #define OCF_LENGTH_CPC_NAME 8UL
 
 static char hmc_network[OCF_LENGTH_HMC_NETWORK + 1];
-static char cpc_name[OCF_LENGTH_CPC_NAME + 1];
+static char cpc_name[OCF_LENGTH_CPC_NAME]; /* in EBCDIC */
 
 static DEFINE_SPINLOCK(sclp_ocf_lock);
 static struct work_struct sclp_ocf_change_work;
@@ -72,9 +72,8 @@ static void sclp_ocf_handler(struct evbuf_header *evbuf)
 	}
 	if (cpc) {
 		size = min(OCF_LENGTH_CPC_NAME, (size_t) cpc->length);
+		memset(cpc_name, 0, OCF_LENGTH_CPC_NAME);
 		memcpy(cpc_name, cpc + 1, size);
-		EBCASC(cpc_name, size);
-		cpc_name[size] = 0;
 	}
 	spin_unlock(&sclp_ocf_lock);
 	schedule_work(&sclp_ocf_change_work);
@@ -85,15 +84,23 @@ static struct sclp_register sclp_ocf_event = {
 	.receiver_fn = sclp_ocf_handler,
 };
 
+void sclp_ocf_cpc_name_copy(char *dst)
+{
+	spin_lock_irq(&sclp_ocf_lock);
+	memcpy(dst, cpc_name, OCF_LENGTH_CPC_NAME);
+	spin_unlock_irq(&sclp_ocf_lock);
+}
+EXPORT_SYMBOL(sclp_ocf_cpc_name_copy);
+
 static ssize_t cpc_name_show(struct kobject *kobj,
 			     struct kobj_attribute *attr, char *page)
 {
-	int rc;
+	char name[OCF_LENGTH_CPC_NAME + 1];
 
-	spin_lock_irq(&sclp_ocf_lock);
-	rc = snprintf(page, PAGE_SIZE, "%s\n", cpc_name);
-	spin_unlock_irq(&sclp_ocf_lock);
-	return rc;
+	sclp_ocf_cpc_name_copy(name);
+	name[OCF_LENGTH_CPC_NAME] = 0;
+	EBCASC(name, OCF_LENGTH_CPC_NAME);
+	return snprintf(page, PAGE_SIZE, "%s\n", name);
 }
 
 static struct kobj_attribute cpc_name_attr =
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index e96aced58627..46be25c7461e 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -37,8 +37,7 @@ enum cfg_task_t {
 
 /* Map for pending configure tasks. */
 static enum cfg_task_t chp_cfg_task[__MAX_CSSID + 1][__MAX_CHPID + 1];
-static DEFINE_MUTEX(cfg_lock);
-static int cfg_busy;
+static DEFINE_SPINLOCK(cfg_lock);
 
 /* Map for channel-path status. */
 static struct sclp_chp_info chp_info;
@@ -666,6 +665,20 @@ static void cfg_set_task(struct chp_id chpid, enum cfg_task_t cfg)
 	chp_cfg_task[chpid.cssid][chpid.id] = cfg;
 }
 
+/* Fetch the first configure task. Set chpid accordingly. */
+static enum cfg_task_t chp_cfg_fetch_task(struct chp_id *chpid)
+{
+	enum cfg_task_t t = cfg_none;
+
+	chp_id_for_each(chpid) {
+		t = cfg_get_task(*chpid);
+		if (t != cfg_none)
+			break;
+	}
+
+	return t;
+}
+
 /* Perform one configure/deconfigure request. Reschedule work function until
  * last request. */
 static void cfg_func(struct work_struct *work)
@@ -674,16 +687,9 @@ static void cfg_func(struct work_struct *work)
 	enum cfg_task_t t;
 	int rc;
 
-	mutex_lock(&cfg_lock);
-	t = cfg_none;
-	chp_id_for_each(&chpid) {
-		t = cfg_get_task(chpid);
-		if (t != cfg_none) {
-			cfg_set_task(chpid, cfg_none);
-			break;
-		}
-	}
-	mutex_unlock(&cfg_lock);
+	spin_lock(&cfg_lock);
+	t = chp_cfg_fetch_task(&chpid);
+	spin_unlock(&cfg_lock);
 
 	switch (t) {
 	case cfg_configure:
@@ -709,12 +715,13 @@ static void cfg_func(struct work_struct *work)
 	case cfg_none:
 		/* Get updated information after last change. */
 		info_update();
-		mutex_lock(&cfg_lock);
-		cfg_busy = 0;
-		mutex_unlock(&cfg_lock);
 		wake_up_interruptible(&cfg_wait_queue);
 		return;
 	}
+	spin_lock(&cfg_lock);
+	if (t == cfg_get_task(chpid))
+		cfg_set_task(chpid, cfg_none);
+	spin_unlock(&cfg_lock);
 	schedule_work(&cfg_work);
 }
 
@@ -729,10 +736,9 @@ void chp_cfg_schedule(struct chp_id chpid, int configure)
 {
 	CIO_MSG_EVENT(2, "chp_cfg_sched%x.%02x=%d\n", chpid.cssid, chpid.id,
 		      configure);
-	mutex_lock(&cfg_lock);
+	spin_lock(&cfg_lock);
 	cfg_set_task(chpid, configure ? cfg_configure : cfg_deconfigure);
-	cfg_busy = 1;
-	mutex_unlock(&cfg_lock);
+	spin_unlock(&cfg_lock);
 	schedule_work(&cfg_work);
 }
 
@@ -746,15 +752,27 @@ void chp_cfg_schedule(struct chp_id chpid, int configure)
 void chp_cfg_cancel_deconfigure(struct chp_id chpid)
 {
 	CIO_MSG_EVENT(2, "chp_cfg_cancel:%x.%02x\n", chpid.cssid, chpid.id);
-	mutex_lock(&cfg_lock);
+	spin_lock(&cfg_lock);
 	if (cfg_get_task(chpid) == cfg_deconfigure)
 		cfg_set_task(chpid, cfg_none);
-	mutex_unlock(&cfg_lock);
+	spin_unlock(&cfg_lock);
+}
+
+static bool cfg_idle(void)
+{
+	struct chp_id chpid;
+	enum cfg_task_t t;
+
+	spin_lock(&cfg_lock);
+	t = chp_cfg_fetch_task(&chpid);
+	spin_unlock(&cfg_lock);
+
+	return t == cfg_none;
 }
 
 static int cfg_wait_idle(void)
 {
-	if (wait_event_interruptible(cfg_wait_queue, !cfg_busy))
+	if (wait_event_interruptible(cfg_wait_queue, cfg_idle()))
 		return -ERESTARTSYS;
 	return 0;
 }
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 4feb27215ab6..ed92fb09fc8e 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -468,6 +468,8 @@ int ap_recv(ap_qid_t qid, unsigned long long *psmid, void *msg, size_t length)
 {
 	struct ap_queue_status status;
 
+	if (msg == NULL)
+		return -EINVAL;
 	status = __ap_recv(qid, psmid, msg, length);
 	switch (status.response_code) {
 	case AP_RESPONSE_NORMAL:
@@ -617,6 +619,8 @@ static enum ap_wait ap_sm_read(struct ap_device *ap_dev)
 {
 	struct ap_queue_status status;
 
+	if (!ap_dev->reply)
+		return AP_WAIT_NONE;
 	status = ap_sm_recv(ap_dev);
 	switch (status.response_code) {
 	case AP_RESPONSE_NORMAL:
@@ -638,6 +642,31 @@ static enum ap_wait ap_sm_read(struct ap_device *ap_dev)
 }
 
 /**
+ * ap_sm_suspend_read(): Receive pending reply messages from an AP device
+ * without changing the device state in between. In suspend mode we don't
+ * allow sending new requests, therefore just fetch pending replies.
+ * @ap_dev: pointer to the AP device
+ *
+ * Returns AP_WAIT_NONE or AP_WAIT_AGAIN
+ */
+static enum ap_wait ap_sm_suspend_read(struct ap_device *ap_dev)
+{
+	struct ap_queue_status status;
+
+	if (!ap_dev->reply)
+		return AP_WAIT_NONE;
+	status = ap_sm_recv(ap_dev);
+	switch (status.response_code) {
+	case AP_RESPONSE_NORMAL:
+		if (ap_dev->queue_count > 0)
+			return AP_WAIT_AGAIN;
+		/* fall through */
+	default:
+		return AP_WAIT_NONE;
+	}
+}
+
+/**
  * ap_sm_write(): Send messages from the request queue to an AP device.
  * @ap_dev: pointer to the AP device
  *
@@ -738,7 +767,7 @@ static enum ap_wait ap_sm_reset_wait(struct ap_device *ap_dev)
 	struct ap_queue_status status;
 	unsigned long info;
 
-	if (ap_dev->queue_count > 0)
+	if (ap_dev->queue_count > 0 && ap_dev->reply)
 		/* Try to read a completed message and get the status */
 		status = ap_sm_recv(ap_dev);
 	else
@@ -778,7 +807,7 @@ static enum ap_wait ap_sm_setirq_wait(struct ap_device *ap_dev)
 	struct ap_queue_status status;
 	unsigned long info;
 
-	if (ap_dev->queue_count > 0)
+	if (ap_dev->queue_count > 0 && ap_dev->reply)
 		/* Try to read a completed message and get the status */
 		status = ap_sm_recv(ap_dev);
 	else
@@ -834,7 +863,7 @@ static ap_func_t *ap_jumptable[NR_AP_STATES][NR_AP_EVENTS] = {
 		[AP_EVENT_TIMEOUT] = ap_sm_reset,
 	},
 	[AP_STATE_SUSPEND_WAIT] = {
-		[AP_EVENT_POLL] = ap_sm_read,
+		[AP_EVENT_POLL] = ap_sm_suspend_read,
 		[AP_EVENT_TIMEOUT] = ap_sm_nop,
 	},
 	[AP_STATE_BORKED] = {
@@ -1335,6 +1364,17 @@ static struct bus_type ap_bus_type = {
 	.resume = ap_dev_resume,
 };
 
+void ap_device_init_reply(struct ap_device *ap_dev,
+			  struct ap_message *reply)
+{
+	ap_dev->reply = reply;
+
+	spin_lock_bh(&ap_dev->lock);
+	ap_sm_wait(ap_sm_event(ap_dev, AP_EVENT_POLL));
+	spin_unlock_bh(&ap_dev->lock);
+}
+EXPORT_SYMBOL(ap_device_init_reply);
+
 static int ap_device_probe(struct device *dev)
 {
 	struct ap_device *ap_dev = to_ap_dev(dev);
@@ -1779,7 +1819,8 @@ int __init ap_module_init(void)
 	if (ap_domain_index < -1 || ap_domain_index > max_domain_id) {
 		pr_warn("%d is not a valid cryptographic domain\n",
 			ap_domain_index);
-		return -EINVAL;
+		rc = -EINVAL;
+		goto out_free;
 	}
 	/* In resume callback we need to know if the user had set the domain.
 	 * If so, we can not just reset it.
@@ -1852,6 +1893,7 @@ out:
 	unregister_reset_call(&ap_reset_call);
 	if (ap_using_interrupts())
 		unregister_adapter_interrupt(&ap_airq);
+out_free:
 	kfree(ap_configuration);
 	return rc;
 }
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 6adcbdf225d1..d7fdf5c024d7 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -262,6 +262,7 @@ void ap_queue_message(struct ap_device *ap_dev, struct ap_message *ap_msg);
 void ap_cancel_message(struct ap_device *ap_dev, struct ap_message *ap_msg);
 void ap_flush_queue(struct ap_device *ap_dev);
 void ap_bus_force_rescan(void);
+void ap_device_init_reply(struct ap_device *ap_dev, struct ap_message *ap_msg);
 
 int ap_module_init(void);
 void ap_module_exit(void);
diff --git a/drivers/s390/crypto/zcrypt_cex2a.c b/drivers/s390/crypto/zcrypt_cex2a.c
index 1e849d6e1dfe..15104aaa075a 100644
--- a/drivers/s390/crypto/zcrypt_cex2a.c
+++ b/drivers/s390/crypto/zcrypt_cex2a.c
@@ -126,7 +126,7 @@ static int zcrypt_cex2a_probe(struct ap_device *ap_dev)
 					   MSGTYPE50_VARIANT_DEFAULT);
 	zdev->ap_dev = ap_dev;
 	zdev->online = 1;
-	ap_dev->reply = &zdev->reply;
+	ap_device_init_reply(ap_dev, &zdev->reply);
 	ap_dev->private = zdev;
 	rc = zcrypt_device_register(zdev);
 	if (rc) {
diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c
index bb3908818505..ccb2e78ebf0e 100644
--- a/drivers/s390/crypto/zcrypt_cex4.c
+++ b/drivers/s390/crypto/zcrypt_cex4.c
@@ -147,7 +147,7 @@ static int zcrypt_cex4_probe(struct ap_device *ap_dev)
 		return -ENODEV;
 	zdev->ap_dev = ap_dev;
 	zdev->online = 1;
-	ap_dev->reply = &zdev->reply;
+	ap_device_init_reply(ap_dev, &zdev->reply);
 	ap_dev->private = zdev;
 	rc = zcrypt_device_register(zdev);
 	if (rc) {
diff --git a/drivers/s390/crypto/zcrypt_pcixcc.c b/drivers/s390/crypto/zcrypt_pcixcc.c
index f41852768953..df8f0c4dacb7 100644
--- a/drivers/s390/crypto/zcrypt_pcixcc.c
+++ b/drivers/s390/crypto/zcrypt_pcixcc.c
@@ -327,7 +327,7 @@ static int zcrypt_pcixcc_probe(struct ap_device *ap_dev)
 	else
 		zdev->ops = zcrypt_msgtype_request(MSGTYPE06_NAME,
 						   MSGTYPE06_VARIANT_NORNG);
-	ap_dev->reply = &zdev->reply;
+	ap_device_init_reply(ap_dev, &zdev->reply);
 	ap_dev->private = zdev;
 	rc = zcrypt_device_register(zdev);
 	if (rc)
diff --git a/drivers/scsi/cxlflash/main.h b/drivers/scsi/cxlflash/main.h
index f54bbd5a6062..e43545c86bcf 100644
--- a/drivers/scsi/cxlflash/main.h
+++ b/drivers/scsi/cxlflash/main.h
@@ -102,8 +102,4 @@ struct asyc_intr_info {
 #define SCAN_HOST	0x04
 };
 
-#ifndef CONFIG_CXL_EEH
-#define cxl_perst_reloads_same_image(_a, _b) do { } while (0)
-#endif
-
 #endif /* _CXLFLASH_MAIN_H */
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index adf61b43eb70..734a0428ef0e 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -4854,20 +4854,17 @@ static int
 lpfc_enable_pci_dev(struct lpfc_hba *phba)
 {
 	struct pci_dev *pdev;
-	int bars = 0;
 
 	/* Obtain PCI device reference */
 	if (!phba->pcidev)
 		goto out_error;
 	else
 		pdev = phba->pcidev;
-	/* Select PCI BARs */
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
 	/* Enable PCI device */
 	if (pci_enable_device_mem(pdev))
 		goto out_error;
 	/* Request PCI resource for the device */
-	if (pci_request_selected_regions(pdev, bars, LPFC_DRIVER_NAME))
+	if (pci_request_mem_regions(pdev, LPFC_DRIVER_NAME))
 		goto out_disable_device;
 	/* Set up device as PCI master and save state for EEH */
 	pci_set_master(pdev);
@@ -4884,7 +4881,7 @@ out_disable_device:
 	pci_disable_device(pdev);
 out_error:
 	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
-			"1401 Failed to enable pci device, bars:x%x\n", bars);
+			"1401 Failed to enable pci device\n");
 	return -ENODEV;
 }
 
@@ -4899,17 +4896,14 @@ static void
 lpfc_disable_pci_dev(struct lpfc_hba *phba)
 {
 	struct pci_dev *pdev;
-	int bars;
 
 	/* Obtain PCI device reference */
 	if (!phba->pcidev)
 		return;
 	else
 		pdev = phba->pcidev;
-	/* Select PCI BARs */
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
 	/* Release PCI resource and disable PCI device */
-	pci_release_selected_regions(pdev, bars);
+	pci_release_mem_regions(pdev);
 	pci_disable_device(pdev);
 
 	return;
@@ -9811,7 +9805,6 @@ lpfc_pci_remove_one_s3(struct pci_dev *pdev)
 	struct lpfc_vport **vports;
 	struct lpfc_hba   *phba = vport->phba;
 	int i;
-	int bars = pci_select_bars(pdev, IORESOURCE_MEM);
 
 	spin_lock_irq(&phba->hbalock);
 	vport->load_flag |= FC_UNLOADING;
@@ -9886,7 +9879,7 @@ lpfc_pci_remove_one_s3(struct pci_dev *pdev)
 
 	lpfc_hba_free(phba);
 
-	pci_release_selected_regions(pdev, bars);
+	pci_release_mem_regions(pdev);
 	pci_disable_device(pdev);
 }
 
diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig
index cb58ef0d9b2c..fe42a2fdf351 100644
--- a/drivers/soc/Kconfig
+++ b/drivers/soc/Kconfig
@@ -1,7 +1,6 @@
 menu "SOC (System On Chip) specific Drivers"
 
 source "drivers/soc/bcm/Kconfig"
-source "drivers/soc/brcmstb/Kconfig"
 source "drivers/soc/fsl/qe/Kconfig"
 source "drivers/soc/mediatek/Kconfig"
 source "drivers/soc/qcom/Kconfig"
@@ -10,6 +9,7 @@ source "drivers/soc/samsung/Kconfig"
 source "drivers/soc/sunxi/Kconfig"
 source "drivers/soc/tegra/Kconfig"
 source "drivers/soc/ti/Kconfig"
+source "drivers/soc/ux500/Kconfig"
 source "drivers/soc/versatile/Kconfig"
 
 endmenu
diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile
index 380230f03874..50c23d0bd457 100644
--- a/drivers/soc/Makefile
+++ b/drivers/soc/Makefile
@@ -3,7 +3,6 @@
 #
 
 obj-y				+= bcm/
-obj-$(CONFIG_SOC_BRCMSTB)	+= brcmstb/
 obj-$(CONFIG_ARCH_DOVE)		+= dove/
 obj-$(CONFIG_MACH_DOVE)		+= dove/
 obj-y				+= fsl/
@@ -15,4 +14,5 @@ obj-$(CONFIG_SOC_SAMSUNG)	+= samsung/
 obj-$(CONFIG_ARCH_SUNXI)	+= sunxi/
 obj-$(CONFIG_ARCH_TEGRA)	+= tegra/
 obj-$(CONFIG_SOC_TI)		+= ti/
+obj-$(CONFIG_ARCH_U8500)	+= ux500/
 obj-$(CONFIG_PLAT_VERSATILE)	+= versatile/
diff --git a/drivers/soc/bcm/Kconfig b/drivers/soc/bcm/Kconfig
index 3066edea184d..a39b0d58ddd0 100644
--- a/drivers/soc/bcm/Kconfig
+++ b/drivers/soc/bcm/Kconfig
@@ -1,9 +1,23 @@
+menu "Broadcom SoC drivers"
+
 config RASPBERRYPI_POWER
 	bool "Raspberry Pi power domain driver"
-	depends on ARCH_BCM2835 || COMPILE_TEST
+	depends on ARCH_BCM2835 || (COMPILE_TEST && OF)
 	depends on RASPBERRYPI_FIRMWARE=y
 	select PM_GENERIC_DOMAINS if PM
-	select PM_GENERIC_DOMAINS_OF if PM
 	help
 	  This enables support for the RPi power domains which can be enabled
 	  or disabled via the RPi firmware.
+
+config SOC_BRCMSTB
+	bool "Broadcom STB SoC drivers"
+	depends on ARM
+	select SOC_BUS
+	help
+	  Enables drivers for the Broadcom Set-Top Box (STB) series of chips.
+	  This option alone enables only some support code, while the drivers
+	  can be enabled individually within this menu.
+
+	  If unsure, say N.
+
+endmenu
diff --git a/drivers/soc/bcm/Makefile b/drivers/soc/bcm/Makefile
index 63aa3eb23087..dc4fced72d21 100644
--- a/drivers/soc/bcm/Makefile
+++ b/drivers/soc/bcm/Makefile
@@ -1 +1,2 @@
 obj-$(CONFIG_RASPBERRYPI_POWER)	+= raspberrypi-power.o
+obj-$(CONFIG_SOC_BRCMSTB)	+= brcmstb/
diff --git a/drivers/soc/brcmstb/Makefile b/drivers/soc/bcm/brcmstb/Makefile
index 9120b2715d3e..9120b2715d3e 100644
--- a/drivers/soc/brcmstb/Makefile
+++ b/drivers/soc/bcm/brcmstb/Makefile
diff --git a/drivers/soc/brcmstb/biuctrl.c b/drivers/soc/bcm/brcmstb/biuctrl.c
index 9049c076f9a1..3c39415d484f 100644
--- a/drivers/soc/brcmstb/biuctrl.c
+++ b/drivers/soc/bcm/brcmstb/biuctrl.c
@@ -19,6 +19,7 @@
 #include <linux/io.h>
 #include <linux/of_address.h>
 #include <linux/syscore_ops.h>
+#include <linux/soc/brcmstb/brcmstb.h>
 
 #define CPU_CREDIT_REG_OFFSET			0x184
 #define  CPU_CREDIT_REG_MCPx_WR_PAIRING_EN_MASK	0x70000000
diff --git a/drivers/soc/brcmstb/common.c b/drivers/soc/bcm/brcmstb/common.c
index 94e7335553f4..94e7335553f4 100644
--- a/drivers/soc/brcmstb/common.c
+++ b/drivers/soc/bcm/brcmstb/common.c
diff --git a/drivers/soc/brcmstb/Kconfig b/drivers/soc/brcmstb/Kconfig
deleted file mode 100644
index 7fec3b4c80a1..000000000000
--- a/drivers/soc/brcmstb/Kconfig
+++ /dev/null
@@ -1,10 +0,0 @@
-menuconfig SOC_BRCMSTB
-	bool "Broadcom STB SoC drivers"
-	depends on ARM
-	select SOC_BUS
-	help
-	  Enables drivers for the Broadcom Set-Top Box (STB) series of chips.
-	  This option alone enables only some support code, while the drivers
-	  can be enabled individually within this menu.
-
-	  If unsure, say N.
diff --git a/drivers/soc/qcom/smem_state.c b/drivers/soc/qcom/smem_state.c
index 54261decb369..d5437ca76ed9 100644
--- a/drivers/soc/qcom/smem_state.c
+++ b/drivers/soc/qcom/smem_state.c
@@ -104,26 +104,26 @@ struct qcom_smem_state *qcom_smem_state_get(struct device *dev,
 
 	if (con_id) {
 		index = of_property_match_string(dev->of_node,
-						 "qcom,state-names",
+						 "qcom,smem-state-names",
 						 con_id);
 		if (index < 0) {
-			dev_err(dev, "missing qcom,state-names\n");
+			dev_err(dev, "missing qcom,smem-state-names\n");
 			return ERR_PTR(index);
 		}
 	}
 
 	ret = of_parse_phandle_with_args(dev->of_node,
-					 "qcom,state",
-					 "#qcom,state-cells",
+					 "qcom,smem-states",
+					 "#qcom,smem-state-cells",
 					 index,
 					 &args);
 	if (ret) {
-		dev_err(dev, "failed to parse qcom,state property\n");
+		dev_err(dev, "failed to parse qcom,smem-states property\n");
 		return ERR_PTR(ret);
 	}
 
 	if (args.args_count != 1) {
-		dev_err(dev, "invalid #qcom,state-cells\n");
+		dev_err(dev, "invalid #qcom,smem-state-cells\n");
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/soc/qcom/smp2p.c b/drivers/soc/qcom/smp2p.c
index f1eed7f9dd67..f51fb2ea7200 100644
--- a/drivers/soc/qcom/smp2p.c
+++ b/drivers/soc/qcom/smp2p.c
@@ -196,7 +196,7 @@ static irqreturn_t qcom_smp2p_intr(int irq, void *data)
 	/* Match newly created entries */
 	for (i = smp2p->valid_entries; i < in->valid_entries; i++) {
 		list_for_each_entry(entry, &smp2p->inbound, node) {
-			memcpy_fromio(buf, in->entries[i].name, sizeof(buf));
+			memcpy(buf, in->entries[i].name, sizeof(buf));
 			if (!strcmp(buf, entry->name)) {
 				entry->value = &in->entries[i].value;
 				break;
@@ -343,12 +343,13 @@ static int qcom_smp2p_outbound_entry(struct qcom_smp2p *smp2p,
 
 	/* Allocate an entry from the smem item */
 	strlcpy(buf, entry->name, SMP2P_MAX_ENTRY_NAME);
-	memcpy_toio(out->entries[out->valid_entries].name, buf, SMP2P_MAX_ENTRY_NAME);
-	out->valid_entries++;
+	memcpy(out->entries[out->valid_entries].name, buf, SMP2P_MAX_ENTRY_NAME);
 
 	/* Make the logical entry reference the physical value */
 	entry->value = &out->entries[out->valid_entries].value;
 
+	out->valid_entries++;
+
 	entry->state = qcom_smem_state_register(node, &smp2p_state_ops, entry);
 	if (IS_ERR(entry->state)) {
 		dev_err(smp2p->dev, "failed to register qcom_smem_state\n");
diff --git a/drivers/soc/qcom/smsm.c b/drivers/soc/qcom/smsm.c
index 6b777af1bc19..d0337b2a71c8 100644
--- a/drivers/soc/qcom/smsm.c
+++ b/drivers/soc/qcom/smsm.c
@@ -495,7 +495,7 @@ static int qcom_smsm_probe(struct platform_device *pdev)
 	if (!smsm->hosts)
 		return -ENOMEM;
 
-	local_node = of_find_node_with_property(pdev->dev.of_node, "#qcom,state-cells");
+	local_node = of_find_node_with_property(pdev->dev.of_node, "#qcom,smem-state-cells");
 	if (!local_node) {
 		dev_err(&pdev->dev, "no state entry\n");
 		return -EINVAL;
diff --git a/drivers/soc/qcom/wcnss_ctrl.c b/drivers/soc/qcom/wcnss_ctrl.c
index c544f3d2c6ee..520aedd29965 100644
--- a/drivers/soc/qcom/wcnss_ctrl.c
+++ b/drivers/soc/qcom/wcnss_ctrl.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016, Linaro Ltd.
  * Copyright (c) 2015, Sony Mobile Communications Inc.
  *
  * This program is free software; you can redistribute it and/or modify
@@ -14,8 +15,16 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/soc/qcom/smd.h>
+#include <linux/io.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/soc/qcom/wcnss_ctrl.h>
 
 #define WCNSS_REQUEST_TIMEOUT	(5 * HZ)
+#define WCNSS_CBC_TIMEOUT	(10 * HZ)
+
+#define WCNSS_ACK_DONE_BOOTING	1
+#define WCNSS_ACK_COLD_BOOTING	2
 
 #define NV_FRAGMENT_SIZE	3072
 #define NVBIN_FILE		"wlan/prima/WCNSS_qcom_wlan_nv.bin"
@@ -25,17 +34,19 @@
  * @dev:	device handle
  * @channel:	SMD channel handle
  * @ack:	completion for outstanding requests
+ * @cbc:	completion for cbc complete indication
  * @ack_status:	status of the outstanding request
- * @download_nv_work: worker for uploading nv binary
+ * @probe_work: worker for uploading nv binary
  */
 struct wcnss_ctrl {
 	struct device *dev;
 	struct qcom_smd_channel *channel;
 
 	struct completion ack;
+	struct completion cbc;
 	int ack_status;
 
-	struct work_struct download_nv_work;
+	struct work_struct probe_work;
 };
 
 /* message types */
@@ -48,6 +59,11 @@ enum {
 	WCNSS_UPLOAD_CAL_RESP,
 	WCNSS_DOWNLOAD_CAL_REQ,
 	WCNSS_DOWNLOAD_CAL_RESP,
+	WCNSS_VBAT_LEVEL_IND,
+	WCNSS_BUILD_VERSION_REQ,
+	WCNSS_BUILD_VERSION_RESP,
+	WCNSS_PM_CONFIG_REQ,
+	WCNSS_CBC_COMPLETE_IND,
 };
 
 /**
@@ -128,7 +144,7 @@ static int wcnss_ctrl_smd_callback(struct qcom_smd_channel *channel,
 			 version->major, version->minor,
 			 version->version, version->revision);
 
-		schedule_work(&wcnss->download_nv_work);
+		complete(&wcnss->ack);
 		break;
 	case WCNSS_DOWNLOAD_NV_RESP:
 		if (count != sizeof(*nvresp)) {
@@ -141,6 +157,10 @@ static int wcnss_ctrl_smd_callback(struct qcom_smd_channel *channel,
 		wcnss->ack_status = nvresp->status;
 		complete(&wcnss->ack);
 		break;
+	case WCNSS_CBC_COMPLETE_IND:
+		dev_dbg(wcnss->dev, "cold boot complete\n");
+		complete(&wcnss->cbc);
+		break;
 	default:
 		dev_info(wcnss->dev, "unknown message type %d\n", hdr->type);
 		break;
@@ -156,20 +176,32 @@ static int wcnss_ctrl_smd_callback(struct qcom_smd_channel *channel,
 static int wcnss_request_version(struct wcnss_ctrl *wcnss)
 {
 	struct wcnss_msg_hdr msg;
+	int ret;
 
 	msg.type = WCNSS_VERSION_REQ;
 	msg.len = sizeof(msg);
+	ret = qcom_smd_send(wcnss->channel, &msg, sizeof(msg));
+	if (ret < 0)
+		return ret;
+
+	ret = wait_for_completion_timeout(&wcnss->ack, WCNSS_CBC_TIMEOUT);
+	if (!ret) {
+		dev_err(wcnss->dev, "timeout waiting for version response\n");
+		return -ETIMEDOUT;
+	}
 
-	return qcom_smd_send(wcnss->channel, &msg, sizeof(msg));
+	return 0;
 }
 
 /**
  * wcnss_download_nv() - send nv binary to WCNSS
- * @work:	work struct to acquire wcnss context
+ * @wcnss:	wcnss_ctrl state handle
+ * @expect_cbc:	indicator to caller that an cbc event is expected
+ *
+ * Returns 0 on success. Negative errno on failure.
  */
-static void wcnss_download_nv(struct work_struct *work)
+static int wcnss_download_nv(struct wcnss_ctrl *wcnss, bool *expect_cbc)
 {
-	struct wcnss_ctrl *wcnss = container_of(work, struct wcnss_ctrl, download_nv_work);
 	struct wcnss_download_nv_req *req;
 	const struct firmware *fw;
 	const void *data;
@@ -178,10 +210,10 @@ static void wcnss_download_nv(struct work_struct *work)
 
 	req = kzalloc(sizeof(*req) + NV_FRAGMENT_SIZE, GFP_KERNEL);
 	if (!req)
-		return;
+		return -ENOMEM;
 
 	ret = request_firmware(&fw, NVBIN_FILE, wcnss->dev);
-	if (ret) {
+	if (ret < 0) {
 		dev_err(wcnss->dev, "Failed to load nv file %s: %d\n",
 			NVBIN_FILE, ret);
 		goto free_req;
@@ -207,7 +239,7 @@ static void wcnss_download_nv(struct work_struct *work)
 		memcpy(req->fragment, data, req->frag_size);
 
 		ret = qcom_smd_send(wcnss->channel, req, req->hdr.len);
-		if (ret) {
+		if (ret < 0) {
 			dev_err(wcnss->dev, "failed to send smd packet\n");
 			goto release_fw;
 		}
@@ -220,16 +252,58 @@ static void wcnss_download_nv(struct work_struct *work)
 	} while (left > 0);
 
 	ret = wait_for_completion_timeout(&wcnss->ack, WCNSS_REQUEST_TIMEOUT);
-	if (!ret)
+	if (!ret) {
 		dev_err(wcnss->dev, "timeout waiting for nv upload ack\n");
-	else if (wcnss->ack_status != 1)
-		dev_err(wcnss->dev, "nv upload response failed err: %d\n",
-			wcnss->ack_status);
+		ret = -ETIMEDOUT;
+	} else {
+		*expect_cbc = wcnss->ack_status == WCNSS_ACK_COLD_BOOTING;
+		ret = 0;
+	}
 
 release_fw:
 	release_firmware(fw);
 free_req:
 	kfree(req);
+
+	return ret;
+}
+
+/**
+ * qcom_wcnss_open_channel() - open additional SMD channel to WCNSS
+ * @wcnss:	wcnss handle, retrieved from drvdata
+ * @name:	SMD channel name
+ * @cb:		callback to handle incoming data on the channel
+ */
+struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb)
+{
+	struct wcnss_ctrl *_wcnss = wcnss;
+
+	return qcom_smd_open_channel(_wcnss->channel, name, cb);
+}
+EXPORT_SYMBOL(qcom_wcnss_open_channel);
+
+static void wcnss_async_probe(struct work_struct *work)
+{
+	struct wcnss_ctrl *wcnss = container_of(work, struct wcnss_ctrl, probe_work);
+	bool expect_cbc;
+	int ret;
+
+	ret = wcnss_request_version(wcnss);
+	if (ret < 0)
+		return;
+
+	ret = wcnss_download_nv(wcnss, &expect_cbc);
+	if (ret < 0)
+		return;
+
+	/* Wait for pending cold boot completion if indicated by the nv downloader */
+	if (expect_cbc) {
+		ret = wait_for_completion_timeout(&wcnss->cbc, WCNSS_REQUEST_TIMEOUT);
+		if (!ret)
+			dev_err(wcnss->dev, "expected cold boot completion\n");
+	}
+
+	of_platform_populate(wcnss->dev->of_node, NULL, NULL, wcnss->dev);
 }
 
 static int wcnss_ctrl_probe(struct qcom_smd_device *sdev)
@@ -244,25 +318,38 @@ static int wcnss_ctrl_probe(struct qcom_smd_device *sdev)
 	wcnss->channel = sdev->channel;
 
 	init_completion(&wcnss->ack);
-	INIT_WORK(&wcnss->download_nv_work, wcnss_download_nv);
+	init_completion(&wcnss->cbc);
+	INIT_WORK(&wcnss->probe_work, wcnss_async_probe);
 
 	qcom_smd_set_drvdata(sdev->channel, wcnss);
+	dev_set_drvdata(&sdev->dev, wcnss);
+
+	schedule_work(&wcnss->probe_work);
+
+	return 0;
+}
+
+static void wcnss_ctrl_remove(struct qcom_smd_device *sdev)
+{
+	struct wcnss_ctrl *wcnss = qcom_smd_get_drvdata(sdev->channel);
 
-	return wcnss_request_version(wcnss);
+	cancel_work_sync(&wcnss->probe_work);
+	of_platform_depopulate(&sdev->dev);
 }
 
-static const struct qcom_smd_id wcnss_ctrl_smd_match[] = {
-	{ .name = "WCNSS_CTRL" },
+static const struct of_device_id wcnss_ctrl_of_match[] = {
+	{ .compatible = "qcom,wcnss", },
 	{}
 };
 
 static struct qcom_smd_driver wcnss_ctrl_driver = {
 	.probe = wcnss_ctrl_probe,
+	.remove = wcnss_ctrl_remove,
 	.callback = wcnss_ctrl_smd_callback,
-	.smd_match_table = wcnss_ctrl_smd_match,
 	.driver  = {
 		.name  = "qcom_wcnss_ctrl",
 		.owner = THIS_MODULE,
+		.of_match_table = wcnss_ctrl_of_match,
 	},
 };
 
diff --git a/drivers/soc/renesas/Makefile b/drivers/soc/renesas/Makefile
index 151fcd3f025b..623039c3514c 100644
--- a/drivers/soc/renesas/Makefile
+++ b/drivers/soc/renesas/Makefile
@@ -1,7 +1,9 @@
 obj-$(CONFIG_ARCH_R8A7779)	+= rcar-sysc.o r8a7779-sysc.o
 obj-$(CONFIG_ARCH_R8A7790)	+= rcar-sysc.o r8a7790-sysc.o
 obj-$(CONFIG_ARCH_R8A7791)	+= rcar-sysc.o r8a7791-sysc.o
+obj-$(CONFIG_ARCH_R8A7792)	+= rcar-sysc.o r8a7792-sysc.o
 # R-Car M2-N is identical to R-Car M2-W w.r.t. power domains.
 obj-$(CONFIG_ARCH_R8A7793)	+= rcar-sysc.o r8a7791-sysc.o
 obj-$(CONFIG_ARCH_R8A7794)	+= rcar-sysc.o r8a7794-sysc.o
 obj-$(CONFIG_ARCH_R8A7795)	+= rcar-sysc.o r8a7795-sysc.o
+obj-$(CONFIG_ARCH_R8A7796)	+= rcar-sysc.o r8a7796-sysc.o
diff --git a/drivers/soc/renesas/r8a7792-sysc.c b/drivers/soc/renesas/r8a7792-sysc.c
new file mode 100644
index 000000000000..ca7467d7b7ec
--- /dev/null
+++ b/drivers/soc/renesas/r8a7792-sysc.c
@@ -0,0 +1,34 @@
+/*
+ * Renesas R-Car V2H (R8A7792) System Controller
+ *
+ * Copyright (C) 2016 Cogent Embedded Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/bug.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+
+#include <dt-bindings/power/r8a7792-sysc.h>
+
+#include "rcar-sysc.h"
+
+static const struct rcar_sysc_area r8a7792_areas[] __initconst = {
+	{ "always-on",	    0, 0, R8A7792_PD_ALWAYS_ON,	-1, PD_ALWAYS_ON },
+	{ "ca15-scu",	0x180, 0, R8A7792_PD_CA15_SCU,	R8A7792_PD_ALWAYS_ON,
+	  PD_SCU },
+	{ "ca15-cpu0",	 0x40, 0, R8A7792_PD_CA15_CPU0,	R8A7792_PD_CA15_SCU,
+	  PD_CPU_NOCR },
+	{ "ca15-cpu1",	 0x40, 1, R8A7792_PD_CA15_CPU1,	R8A7792_PD_CA15_SCU,
+	  PD_CPU_NOCR },
+	{ "sgx",	 0xc0, 0, R8A7792_PD_SGX,	R8A7792_PD_ALWAYS_ON },
+	{ "imp",	0x140, 0, R8A7792_PD_IMP,	R8A7792_PD_ALWAYS_ON },
+};
+
+const struct rcar_sysc_info r8a7792_sysc_info __initconst = {
+	.areas = r8a7792_areas,
+	.num_areas = ARRAY_SIZE(r8a7792_areas),
+};
diff --git a/drivers/soc/renesas/r8a7796-sysc.c b/drivers/soc/renesas/r8a7796-sysc.c
new file mode 100644
index 000000000000..f700c842b9e1
--- /dev/null
+++ b/drivers/soc/renesas/r8a7796-sysc.c
@@ -0,0 +1,48 @@
+/*
+ * Renesas R-Car M3-W System Controller
+ *
+ * Copyright (C) 2016 Glider bvba
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+
+#include <dt-bindings/power/r8a7796-sysc.h>
+
+#include "rcar-sysc.h"
+
+static const struct rcar_sysc_area r8a7796_areas[] __initconst = {
+	{ "always-on",	    0, 0, R8A7796_PD_ALWAYS_ON,	-1, PD_ALWAYS_ON },
+	{ "ca57-scu",	0x1c0, 0, R8A7796_PD_CA57_SCU,	R8A7796_PD_ALWAYS_ON,
+	  PD_SCU },
+	{ "ca57-cpu0",	 0x80, 0, R8A7796_PD_CA57_CPU0,	R8A7796_PD_CA57_SCU,
+	  PD_CPU_NOCR },
+	{ "ca57-cpu1",	 0x80, 1, R8A7796_PD_CA57_CPU1,	R8A7796_PD_CA57_SCU,
+	  PD_CPU_NOCR },
+	{ "ca53-scu",	0x140, 0, R8A7796_PD_CA53_SCU,	R8A7796_PD_ALWAYS_ON,
+	  PD_SCU },
+	{ "ca53-cpu0",	0x200, 0, R8A7796_PD_CA53_CPU0,	R8A7796_PD_CA53_SCU,
+	  PD_CPU_NOCR },
+	{ "ca53-cpu1",	0x200, 1, R8A7796_PD_CA53_CPU1,	R8A7796_PD_CA53_SCU,
+	  PD_CPU_NOCR },
+	{ "ca53-cpu2",	0x200, 2, R8A7796_PD_CA53_CPU2,	R8A7796_PD_CA53_SCU,
+	  PD_CPU_NOCR },
+	{ "ca53-cpu3",	0x200, 3, R8A7796_PD_CA53_CPU3,	R8A7796_PD_CA53_SCU,
+	  PD_CPU_NOCR },
+	{ "cr7",	0x240, 0, R8A7796_PD_CR7,	R8A7796_PD_ALWAYS_ON },
+	{ "a3vc",	0x380, 0, R8A7796_PD_A3VC,	R8A7796_PD_ALWAYS_ON },
+	{ "a2vc0",	0x3c0, 0, R8A7796_PD_A2VC0,	R8A7796_PD_A3VC },
+	{ "a2vc1",	0x3c0, 1, R8A7796_PD_A2VC1,	R8A7796_PD_A3VC },
+	{ "3dg-a",	0x100, 0, R8A7796_PD_3DG_A,	R8A7796_PD_ALWAYS_ON },
+	{ "3dg-b",	0x100, 1, R8A7796_PD_3DG_B,	R8A7796_PD_3DG_A },
+	{ "a3ir",	0x180, 0, R8A7796_PD_A3IR,	R8A7796_PD_ALWAYS_ON },
+};
+
+const struct rcar_sysc_info r8a7796_sysc_info __initconst = {
+	.areas = r8a7796_areas,
+	.num_areas = ARRAY_SIZE(r8a7796_areas),
+};
diff --git a/drivers/soc/renesas/rcar-sysc.c b/drivers/soc/renesas/rcar-sysc.c
index 79dbc770895f..65c8e1eb90c0 100644
--- a/drivers/soc/renesas/rcar-sysc.c
+++ b/drivers/soc/renesas/rcar-sysc.c
@@ -164,15 +164,6 @@ static bool rcar_sysc_power_is_off(const struct rcar_sysc_ch *sysc_ch)
 	return false;
 }
 
-void __iomem *rcar_sysc_init(phys_addr_t base)
-{
-	rcar_sysc_base = ioremap_nocache(base, PAGE_SIZE);
-	if (!rcar_sysc_base)
-		panic("unable to ioremap R-Car SYSC hardware block\n");
-
-	return rcar_sysc_base;
-}
-
 struct rcar_sysc_pd {
 	struct generic_pm_domain genpd;
 	struct rcar_sysc_ch ch;
@@ -293,6 +284,9 @@ static const struct of_device_id rcar_sysc_matches[] = {
 #ifdef CONFIG_ARCH_R8A7791
 	{ .compatible = "renesas,r8a7791-sysc", .data = &r8a7791_sysc_info },
 #endif
+#ifdef CONFIG_ARCH_R8A7792
+	{ .compatible = "renesas,r8a7792-sysc", .data = &r8a7792_sysc_info },
+#endif
 #ifdef CONFIG_ARCH_R8A7793
 	/* R-Car M2-N is identical to R-Car M2-W w.r.t. power domains. */
 	{ .compatible = "renesas,r8a7793-sysc", .data = &r8a7791_sysc_info },
@@ -303,6 +297,9 @@ static const struct of_device_id rcar_sysc_matches[] = {
 #ifdef CONFIG_ARCH_R8A7795
 	{ .compatible = "renesas,r8a7795-sysc", .data = &r8a7795_sysc_info },
 #endif
+#ifdef CONFIG_ARCH_R8A7796
+	{ .compatible = "renesas,r8a7796-sysc", .data = &r8a7796_sysc_info },
+#endif
 	{ /* sentinel */ }
 };
 
@@ -322,6 +319,9 @@ static int __init rcar_sysc_pd_init(void)
 	unsigned int i;
 	int error;
 
+	if (rcar_sysc_base)
+		return 0;
+
 	np = of_find_matching_node_and_match(NULL, rcar_sysc_matches, &match);
 	if (!np)
 		return -ENODEV;
@@ -392,10 +392,35 @@ static int __init rcar_sysc_pd_init(void)
 		domains->domains[area->isr_bit] = &pd->genpd;
 	}
 
-	of_genpd_add_provider_onecell(np, &domains->onecell_data);
+	error = of_genpd_add_provider_onecell(np, &domains->onecell_data);
 
 out_put:
 	of_node_put(np);
 	return error;
 }
 early_initcall(rcar_sysc_pd_init);
+
+void __init rcar_sysc_init(phys_addr_t base, u32 syscier)
+{
+	u32 syscimr;
+
+	if (!rcar_sysc_pd_init())
+		return;
+
+	rcar_sysc_base = ioremap_nocache(base, PAGE_SIZE);
+
+	/*
+	 * Mask all interrupt sources to prevent the CPU from receiving them.
+	 * Make sure not to clear reserved bits that were set before.
+	 */
+	syscimr = ioread32(rcar_sysc_base + SYSCIMR);
+	syscimr |= syscier;
+	pr_debug("%s: syscimr = 0x%08x\n", __func__, syscimr);
+	iowrite32(syscimr, rcar_sysc_base + SYSCIMR);
+
+	/*
+	 * SYSC needs all interrupt sources enabled to control power.
+	 */
+	pr_debug("%s: syscier = 0x%08x\n", __func__, syscier);
+	iowrite32(syscier, rcar_sysc_base + SYSCIER);
+}
diff --git a/drivers/soc/renesas/rcar-sysc.h b/drivers/soc/renesas/rcar-sysc.h
index 5e766174c2f4..77dbe861473f 100644
--- a/drivers/soc/renesas/rcar-sysc.h
+++ b/drivers/soc/renesas/rcar-sysc.h
@@ -53,6 +53,8 @@ struct rcar_sysc_info {
 extern const struct rcar_sysc_info r8a7779_sysc_info;
 extern const struct rcar_sysc_info r8a7790_sysc_info;
 extern const struct rcar_sysc_info r8a7791_sysc_info;
+extern const struct rcar_sysc_info r8a7792_sysc_info;
 extern const struct rcar_sysc_info r8a7794_sysc_info;
 extern const struct rcar_sysc_info r8a7795_sysc_info;
+extern const struct rcar_sysc_info r8a7796_sysc_info;
 #endif /* __SOC_RENESAS_RCAR_SYSC_H__ */
diff --git a/drivers/soc/samsung/Kconfig b/drivers/soc/samsung/Kconfig
index d7fc123006a3..245533907d1b 100644
--- a/drivers/soc/samsung/Kconfig
+++ b/drivers/soc/samsung/Kconfig
@@ -10,4 +10,8 @@ config EXYNOS_PMU
 	bool "Exynos PMU controller driver" if COMPILE_TEST
 	depends on (ARM && ARCH_EXYNOS) || ((ARM || ARM64) && COMPILE_TEST)
 
+config EXYNOS_PM_DOMAINS
+	bool "Exynos PM domains" if COMPILE_TEST
+	depends on PM_GENERIC_DOMAINS || COMPILE_TEST
+
 endif
diff --git a/drivers/soc/samsung/Makefile b/drivers/soc/samsung/Makefile
index f64ac4d80564..3619f2ecddaa 100644
--- a/drivers/soc/samsung/Makefile
+++ b/drivers/soc/samsung/Makefile
@@ -1,2 +1,3 @@
 obj-$(CONFIG_EXYNOS_PMU)	+= exynos-pmu.o exynos3250-pmu.o exynos4-pmu.o \
 					exynos5250-pmu.o exynos5420-pmu.o
+obj-$(CONFIG_EXYNOS_PM_DOMAINS) += pm_domains.o
diff --git a/drivers/soc/samsung/exynos3250-pmu.c b/drivers/soc/samsung/exynos3250-pmu.c
index 20b3ab8aa790..af2f54e14b83 100644
--- a/drivers/soc/samsung/exynos3250-pmu.c
+++ b/drivers/soc/samsung/exynos3250-pmu.c
@@ -14,7 +14,7 @@
 
 #include "exynos-pmu.h"
 
-static struct exynos_pmu_conf exynos3250_pmu_config[] = {
+static const struct exynos_pmu_conf exynos3250_pmu_config[] = {
 	/* { .offset = offset, .val = { AFTR, W-AFTR, SLEEP } */
 	{ EXYNOS3_ARM_CORE0_SYS_PWR_REG,		{ 0x0, 0x0, 0x2} },
 	{ EXYNOS3_DIS_IRQ_ARM_CORE0_LOCAL_SYS_PWR_REG,	{ 0x0, 0x0, 0x0} },
diff --git a/drivers/soc/samsung/exynos5420-pmu.c b/drivers/soc/samsung/exynos5420-pmu.c
index b962fb6a5d22..3f2c64180ef8 100644
--- a/drivers/soc/samsung/exynos5420-pmu.c
+++ b/drivers/soc/samsung/exynos5420-pmu.c
@@ -17,7 +17,7 @@
 
 #include "exynos-pmu.h"
 
-static struct exynos_pmu_conf exynos5420_pmu_config[] = {
+static const struct exynos_pmu_conf exynos5420_pmu_config[] = {
 	/* { .offset = offset, .val = { AFTR, LPA, SLEEP } */
 	{ EXYNOS5_ARM_CORE0_SYS_PWR_REG,		{ 0x0, 0x0, 0x0} },
 	{ EXYNOS5_DIS_IRQ_ARM_CORE0_LOCAL_SYS_PWR_REG,	{ 0x0, 0x0, 0x0} },
diff --git a/arch/arm/mach-exynos/pm_domains.c b/drivers/soc/samsung/pm_domains.c
index 875a2bab64f6..4822346aadc6 100644
--- a/arch/arm/mach-exynos/pm_domains.c
+++ b/drivers/soc/samsung/pm_domains.c
@@ -23,9 +23,13 @@
 #include <linux/of_platform.h>
 #include <linux/sched.h>
 
-#define INT_LOCAL_PWR_EN	0x7
 #define MAX_CLK_PER_DOMAIN	4
 
+struct exynos_pm_domain_config {
+	/* Value for LOCAL_PWR_CFG and STATUS fields for each domain */
+	u32 local_pwr_cfg;
+};
+
 /*
  * Exynos specific wrapper around the generic power domain
  */
@@ -38,6 +42,7 @@ struct exynos_pm_domain {
 	struct clk *clk[MAX_CLK_PER_DOMAIN];
 	struct clk *pclk[MAX_CLK_PER_DOMAIN];
 	struct clk *asb_clk[MAX_CLK_PER_DOMAIN];
+	u32 local_pwr_cfg;
 };
 
 static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
@@ -69,13 +74,13 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
 		}
 	}
 
-	pwr = power_on ? INT_LOCAL_PWR_EN : 0;
-	__raw_writel(pwr, base);
+	pwr = power_on ? pd->local_pwr_cfg : 0;
+	writel_relaxed(pwr, base);
 
 	/* Wait max 1ms */
 	timeout = 10;
 
-	while ((__raw_readl(base + 0x4) & INT_LOCAL_PWR_EN) != pwr) {
+	while ((readl_relaxed(base + 0x4) & pd->local_pwr_cfg) != pwr) {
 		if (!timeout) {
 			op = (power_on) ? "enable" : "disable";
 			pr_err("Power domain %s %s failed\n", domain->name, op);
@@ -119,14 +124,30 @@ static int exynos_pd_power_off(struct generic_pm_domain *domain)
 	return exynos_pd_power(domain, false);
 }
 
+static const struct exynos_pm_domain_config exynos4210_cfg __initconst = {
+	.local_pwr_cfg		= 0x7,
+};
+
+static const struct of_device_id exynos_pm_domain_of_match[] __initconst = {
+	{
+		.compatible = "samsung,exynos4210-pd",
+		.data = &exynos4210_cfg,
+	},
+	{ },
+};
+
 static __init int exynos4_pm_init_power_domain(void)
 {
 	struct device_node *np;
+	const struct of_device_id *match;
 
-	for_each_compatible_node(np, NULL, "samsung,exynos4210-pd") {
+	for_each_matching_node_and_match(np, exynos_pm_domain_of_match, &match) {
+		const struct exynos_pm_domain_config *pm_domain_cfg;
 		struct exynos_pm_domain *pd;
 		int on, i;
 
+		pm_domain_cfg = match->data;
+
 		pd = kzalloc(sizeof(*pd), GFP_KERNEL);
 		if (!pd) {
 			pr_err("%s: failed to allocate memory for domain\n",
@@ -153,6 +174,7 @@ static __init int exynos4_pm_init_power_domain(void)
 
 		pd->pd.power_off = exynos_pd_power_off;
 		pd->pd.power_on = exynos_pd_power_on;
+		pd->local_pwr_cfg = pm_domain_cfg->local_pwr_cfg;
 
 		for (i = 0; i < MAX_CLK_PER_DOMAIN; i++) {
 			char clk_name[8];
@@ -185,14 +207,14 @@ static __init int exynos4_pm_init_power_domain(void)
 			clk_put(pd->oscclk);
 
 no_clk:
-		on = __raw_readl(pd->base + 0x4) & INT_LOCAL_PWR_EN;
+		on = readl_relaxed(pd->base + 0x4) & pd->local_pwr_cfg;
 
 		pm_genpd_init(&pd->pd, NULL, !on);
 		of_genpd_add_provider_simple(np, &pd->pd);
 	}
 
 	/* Assign the child power domains to their parents */
-	for_each_compatible_node(np, NULL, "samsung,exynos4210-pd") {
+	for_each_matching_node(np, exynos_pm_domain_of_match) {
 		struct generic_pm_domain *child_domain, *parent_domain;
 		struct of_phandle_args args;
 
diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index bb173456bbff..71c834f3847e 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -51,6 +51,7 @@
 #define  PMC_CNTRL_CPU_PWRREQ_POLARITY	(1 << 15)  /* CPU pwr req polarity */
 #define  PMC_CNTRL_CPU_PWRREQ_OE	(1 << 16)  /* CPU pwr req enable */
 #define  PMC_CNTRL_INTR_POLARITY	(1 << 17)  /* inverts INTR polarity */
+#define  PMC_CNTRL_MAIN_RST		(1 <<  4)
 
 #define DPD_SAMPLE			0x020
 #define  DPD_SAMPLE_ENABLE		(1 << 0)
@@ -80,6 +81,14 @@
 #define PMC_SENSOR_CTRL_SCRATCH_WRITE	(1 << 2)
 #define PMC_SENSOR_CTRL_ENABLE_RST	(1 << 1)
 
+#define PMC_RST_STATUS			0x1b4
+#define  PMC_RST_STATUS_POR		0
+#define  PMC_RST_STATUS_WATCHDOG	1
+#define  PMC_RST_STATUS_SENSOR		2
+#define  PMC_RST_STATUS_SW_MAIN		3
+#define  PMC_RST_STATUS_LP0		4
+#define  PMC_RST_STATUS_AOTAG		5
+
 #define IO_DPD_REQ			0x1b8
 #define  IO_DPD_REQ_CODE_IDLE		(0 << 30)
 #define  IO_DPD_REQ_CODE_OFF		(1 << 30)
@@ -399,6 +408,7 @@ static int tegra_powergate_power_up(struct tegra_powergate *pg,
 disable_clks:
 	tegra_powergate_disable_clocks(pg);
 	usleep_range(10, 20);
+
 powergate_off:
 	tegra_powergate_set(pg->id, false);
 
@@ -436,6 +446,7 @@ assert_resets:
 	usleep_range(10, 20);
 	tegra_powergate_reset_deassert(pg);
 	usleep_range(10, 20);
+
 disable_clks:
 	tegra_powergate_disable_clocks(pg);
 
@@ -540,6 +551,9 @@ int tegra_powergate_sequence_power_up(unsigned int id, struct clk *clk,
 	struct tegra_powergate pg;
 	int err;
 
+	if (!tegra_powergate_is_available(id))
+		return -EINVAL;
+
 	pg.id = id;
 	pg.clks = &clk;
 	pg.num_clks = 1;
@@ -638,9 +652,10 @@ static int tegra_pmc_restart_notify(struct notifier_block *this,
 
 	tegra_pmc_writel(value, PMC_SCRATCH0);
 
-	value = tegra_pmc_readl(0);
-	value |= 0x10;
-	tegra_pmc_writel(value, 0);
+	/* reset everything but PMC_SCRATCH0 and PMC_RST_STATUS */
+	value = tegra_pmc_readl(PMC_CNTRL);
+	value |= PMC_CNTRL_MAIN_RST;
+	tegra_pmc_writel(value, PMC_CNTRL);
 
 	return NOTIFY_DONE;
 }
@@ -722,13 +737,14 @@ static int tegra_powergate_of_get_clks(struct tegra_powergate *pg,
 err:
 	while (i--)
 		clk_put(pg->clks[i]);
+
 	kfree(pg->clks);
 
 	return err;
 }
 
 static int tegra_powergate_of_get_resets(struct tegra_powergate *pg,
-					 struct device_node *np)
+					 struct device_node *np, bool off)
 {
 	struct reset_control *rst;
 	unsigned int i, count;
@@ -748,6 +764,16 @@ static int tegra_powergate_of_get_resets(struct tegra_powergate *pg,
 			err = PTR_ERR(pg->resets[i]);
 			goto error;
 		}
+
+		if (off)
+			err = reset_control_assert(pg->resets[i]);
+		else
+			err = reset_control_deassert(pg->resets[i]);
+
+		if (err) {
+			reset_control_put(pg->resets[i]);
+			goto error;
+		}
 	}
 
 	pg->num_resets = count;
@@ -757,6 +783,7 @@ static int tegra_powergate_of_get_resets(struct tegra_powergate *pg,
 error:
 	while (i--)
 		reset_control_put(pg->resets[i]);
+
 	kfree(pg->resets);
 
 	return err;
@@ -765,16 +792,19 @@ error:
 static void tegra_powergate_add(struct tegra_pmc *pmc, struct device_node *np)
 {
 	struct tegra_powergate *pg;
+	int id, err;
 	bool off;
-	int id;
 
 	pg = kzalloc(sizeof(*pg), GFP_KERNEL);
 	if (!pg)
-		goto error;
+		return;
 
 	id = tegra_powergate_lookup(pmc, np->name);
-	if (id < 0)
+	if (id < 0) {
+		dev_err(pmc->dev, "powergate lookup failed for %s: %d\n",
+			np->name, id);
 		goto free_mem;
+	}
 
 	/*
 	 * Clear the bit for this powergate so it cannot be managed
@@ -788,31 +818,64 @@ static void tegra_powergate_add(struct tegra_pmc *pmc, struct device_node *np)
 	pg->genpd.power_on = tegra_genpd_power_on;
 	pg->pmc = pmc;
 
-	if (tegra_powergate_of_get_clks(pg, np))
+	off = !tegra_powergate_is_powered(pg->id);
+
+	err = tegra_powergate_of_get_clks(pg, np);
+	if (err < 0) {
+		dev_err(pmc->dev, "failed to get clocks for %s: %d\n",
+			np->name, err);
 		goto set_available;
+	}
 
-	if (tegra_powergate_of_get_resets(pg, np))
+	err = tegra_powergate_of_get_resets(pg, np, off);
+	if (err < 0) {
+		dev_err(pmc->dev, "failed to get resets for %s: %d\n",
+			np->name, err);
 		goto remove_clks;
+	}
 
-	off = !tegra_powergate_is_powered(pg->id);
+	if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS))
+		goto power_on_cleanup;
+
+	/*
+	 * FIXME: If XHCI is enabled for Tegra, then power-up the XUSB
+	 * host and super-speed partitions. Once the XHCI driver
+	 * manages the partitions itself this code can be removed. Note
+	 * that we don't register these partitions with the genpd core
+	 * to avoid it from powering down the partitions as they appear
+	 * to be unused.
+	 */
+	if (IS_ENABLED(CONFIG_USB_XHCI_TEGRA) &&
+	    (id == TEGRA_POWERGATE_XUSBA || id == TEGRA_POWERGATE_XUSBC))
+		goto power_on_cleanup;
 
 	pm_genpd_init(&pg->genpd, NULL, off);
 
-	if (of_genpd_add_provider_simple(np, &pg->genpd))
+	err = of_genpd_add_provider_simple(np, &pg->genpd);
+	if (err < 0) {
+		dev_err(pmc->dev, "failed to add genpd provider for %s: %d\n",
+			np->name, err);
 		goto remove_resets;
+	}
 
 	dev_dbg(pmc->dev, "added power domain %s\n", pg->genpd.name);
 
 	return;
 
+power_on_cleanup:
+	if (off)
+		WARN_ON(tegra_powergate_power_up(pg, true));
+
 remove_resets:
 	while (pg->num_resets--)
 		reset_control_put(pg->resets[pg->num_resets]);
+
 	kfree(pg->resets);
 
 remove_clks:
 	while (pg->num_clks--)
 		clk_put(pg->clks[pg->num_clks]);
+
 	kfree(pg->clks);
 
 set_available:
@@ -820,16 +883,20 @@ set_available:
 
 free_mem:
 	kfree(pg);
-
-error:
-	dev_err(pmc->dev, "failed to create power domain for %s\n", np->name);
 }
 
-static void tegra_powergate_init(struct tegra_pmc *pmc)
+static void tegra_powergate_init(struct tegra_pmc *pmc,
+				 struct device_node *parent)
 {
 	struct device_node *np, *child;
+	unsigned int i;
+
+	/* Create a bitmap of the available and valid partitions */
+	for (i = 0; i < pmc->soc->num_powergates; i++)
+		if (pmc->soc->powergates[i])
+			set_bit(i, pmc->powergates_available);
 
-	np = of_get_child_by_name(pmc->dev->of_node, "powergates");
+	np = of_get_child_by_name(parent, "powergates");
 	if (!np)
 		return;
 
@@ -1205,6 +1272,14 @@ static int tegra_pmc_probe(struct platform_device *pdev)
 	struct resource *res;
 	int err;
 
+	/*
+	 * Early initialisation should have configured an initial
+	 * register mapping and setup the soc data pointer. If these
+	 * are not valid then something went badly wrong!
+	 */
+	if (WARN_ON(!pmc->base || !pmc->soc))
+		return -ENODEV;
+
 	err = tegra_pmc_parse_dt(pmc, pdev->dev.of_node);
 	if (err < 0)
 		return err;
@@ -1242,8 +1317,6 @@ static int tegra_pmc_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	tegra_powergate_init(pmc);
-
 	mutex_lock(&pmc->powergates_lock);
 	iounmap(pmc->base);
 	pmc->base = base;
@@ -1477,10 +1550,11 @@ static int __init tegra_pmc_early_init(void)
 	const struct of_device_id *match;
 	struct device_node *np;
 	struct resource regs;
-	unsigned int i;
 	bool invert;
 	u32 value;
 
+	mutex_init(&pmc->powergates_lock);
+
 	np = of_find_matching_node_and_match(NULL, tegra_pmc_match, &match);
 	if (!np) {
 		/*
@@ -1515,39 +1589,40 @@ static int __init tegra_pmc_early_init(void)
 		 */
 		if (of_address_to_resource(np, 0, &regs) < 0) {
 			pr_err("failed to get PMC registers\n");
+			of_node_put(np);
 			return -ENXIO;
 		}
-
-		pmc->soc = match->data;
 	}
 
 	pmc->base = ioremap_nocache(regs.start, resource_size(&regs));
 	if (!pmc->base) {
 		pr_err("failed to map PMC registers\n");
+		of_node_put(np);
 		return -ENXIO;
 	}
 
-	/* Create a bit-map of the available and valid partitions */
-	for (i = 0; i < pmc->soc->num_powergates; i++)
-		if (pmc->soc->powergates[i])
-			set_bit(i, pmc->powergates_available);
+	if (np) {
+		pmc->soc = match->data;
 
-	mutex_init(&pmc->powergates_lock);
+		tegra_powergate_init(pmc, np);
 
-	/*
-	 * Invert the interrupt polarity if a PMC device tree node exists and
-	 * contains the nvidia,invert-interrupt property.
-	 */
-	invert = of_property_read_bool(np, "nvidia,invert-interrupt");
+		/*
+		 * Invert the interrupt polarity if a PMC device tree node
+		 * exists and contains the nvidia,invert-interrupt property.
+		 */
+		invert = of_property_read_bool(np, "nvidia,invert-interrupt");
 
-	value = tegra_pmc_readl(PMC_CNTRL);
+		value = tegra_pmc_readl(PMC_CNTRL);
 
-	if (invert)
-		value |= PMC_CNTRL_INTR_POLARITY;
-	else
-		value &= ~PMC_CNTRL_INTR_POLARITY;
+		if (invert)
+			value |= PMC_CNTRL_INTR_POLARITY;
+		else
+			value &= ~PMC_CNTRL_INTR_POLARITY;
 
-	tegra_pmc_writel(value, PMC_CNTRL);
+		tegra_pmc_writel(value, PMC_CNTRL);
+
+		of_node_put(np);
+	}
 
 	return 0;
 }
diff --git a/drivers/soc/ux500/Kconfig b/drivers/soc/ux500/Kconfig
new file mode 100644
index 000000000000..025a44aef5db
--- /dev/null
+++ b/drivers/soc/ux500/Kconfig
@@ -0,0 +1,7 @@
+config UX500_SOC_ID
+	bool "SoC bus for ST-Ericsson ux500"
+	depends on ARCH_U8500 || COMPILE_TEST
+	default ARCH_U8500
+	help
+	  Include support for the SoC bus on the ARM RealView platforms
+	  providing some sysfs information about the ASIC variant.
diff --git a/drivers/soc/ux500/Makefile b/drivers/soc/ux500/Makefile
new file mode 100644
index 000000000000..0b87ad04b018
--- /dev/null
+++ b/drivers/soc/ux500/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_UX500_SOC_ID) += ux500-soc-id.o
diff --git a/drivers/soc/ux500/ux500-soc-id.c b/drivers/soc/ux500/ux500-soc-id.c
new file mode 100644
index 000000000000..6c1be74e5fcc
--- /dev/null
+++ b/drivers/soc/ux500/ux500-soc-id.c
@@ -0,0 +1,222 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * Author: Rabin Vincent <rabin.vincent@stericsson.com> for ST-Ericsson
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/sys_soc.h>
+
+#include <asm/cputype.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+#include <asm/mach/map.h>
+
+/**
+ * struct dbx500_asic_id - fields of the ASIC ID
+ * @process: the manufacturing process, 0x40 is 40 nm 0x00 is "standard"
+ * @partnumber: hithereto 0x8500 for DB8500
+ * @revision: version code in the series
+ */
+struct dbx500_asic_id {
+	u16	partnumber;
+	u8	revision;
+	u8	process;
+};
+
+static struct dbx500_asic_id dbx500_id;
+
+static unsigned int __init ux500_read_asicid(phys_addr_t addr)
+{
+	void __iomem *virt = ioremap(addr, 4);
+	unsigned int asicid;
+
+	if (!virt)
+		return 0;
+
+	asicid = readl(virt);
+	iounmap(virt);
+
+	return asicid;
+}
+
+static void ux500_print_soc_info(unsigned int asicid)
+{
+	unsigned int rev = dbx500_id.revision;
+
+	pr_info("DB%4x ", dbx500_id.partnumber);
+
+	if (rev == 0x01)
+		pr_cont("Early Drop");
+	else if (rev >= 0xA0)
+		pr_cont("v%d.%d" , (rev >> 4) - 0xA + 1, rev & 0xf);
+	else
+		pr_cont("Unknown");
+
+	pr_cont(" [%#010x]\n", asicid);
+}
+
+static unsigned int partnumber(unsigned int asicid)
+{
+	return (asicid >> 8) & 0xffff;
+}
+
+/*
+ * SOC		MIDR		ASICID ADDRESS		ASICID VALUE
+ * DB8500ed	0x410fc090	0x9001FFF4		0x00850001
+ * DB8500v1	0x411fc091	0x9001FFF4		0x008500A0
+ * DB8500v1.1	0x411fc091	0x9001FFF4		0x008500A1
+ * DB8500v2	0x412fc091	0x9001DBF4		0x008500B0
+ * DB8520v2.2	0x412fc091	0x9001DBF4		0x008500B2
+ * DB5500v1	0x412fc091	0x9001FFF4		0x005500A0
+ * DB9540	0x413fc090	0xFFFFDBF4		0x009540xx
+ */
+
+static void __init ux500_setup_id(void)
+{
+	unsigned int cpuid = read_cpuid_id();
+	unsigned int asicid = 0;
+	phys_addr_t addr = 0;
+
+	switch (cpuid) {
+	case 0x410fc090: /* DB8500ed */
+	case 0x411fc091: /* DB8500v1 */
+		addr = 0x9001FFF4;
+		break;
+
+	case 0x412fc091: /* DB8520 / DB8500v2 / DB5500v1 */
+		asicid = ux500_read_asicid(0x9001DBF4);
+		if (partnumber(asicid) == 0x8500 ||
+		    partnumber(asicid) == 0x8520)
+			/* DB8500v2 */
+			break;
+
+		/* DB5500v1 */
+		addr = 0x9001FFF4;
+		break;
+
+	case 0x413fc090: /* DB9540 */
+		addr = 0xFFFFDBF4;
+		break;
+	}
+
+	if (addr)
+		asicid = ux500_read_asicid(addr);
+
+	if (!asicid) {
+		pr_err("Unable to identify SoC\n");
+		BUG();
+	}
+
+	dbx500_id.process = asicid >> 24;
+	dbx500_id.partnumber = partnumber(asicid);
+	dbx500_id.revision = asicid & 0xff;
+
+	ux500_print_soc_info(asicid);
+}
+
+static const char * __init ux500_get_machine(void)
+{
+	return kasprintf(GFP_KERNEL, "DB%4x", dbx500_id.partnumber);
+}
+
+static const char * __init ux500_get_family(void)
+{
+	return kasprintf(GFP_KERNEL, "ux500");
+}
+
+static const char * __init ux500_get_revision(void)
+{
+	unsigned int rev = dbx500_id.revision;
+
+	if (rev == 0x01)
+		return kasprintf(GFP_KERNEL, "%s", "ED");
+	else if (rev >= 0xA0)
+		return kasprintf(GFP_KERNEL, "%d.%d",
+				 (rev >> 4) - 0xA + 1, rev & 0xf);
+
+	return kasprintf(GFP_KERNEL, "%s", "Unknown");
+}
+
+static ssize_t ux500_get_process(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	if (dbx500_id.process == 0x00)
+		return sprintf(buf, "Standard\n");
+
+	return sprintf(buf, "%02xnm\n", dbx500_id.process);
+}
+
+static const char *db8500_read_soc_id(struct device_node *backupram)
+{
+	void __iomem *base;
+	void __iomem *uid;
+	const char *retstr;
+
+	base = of_iomap(backupram, 0);
+	if (!base)
+		return NULL;
+	uid = base + 0x1fc0;
+
+	/* Throw these device-specific numbers into the entropy pool */
+	add_device_randomness(uid, 0x14);
+	retstr = kasprintf(GFP_KERNEL, "%08x%08x%08x%08x%08x",
+			 readl((u32 *)uid+0),
+			 readl((u32 *)uid+1), readl((u32 *)uid+2),
+			 readl((u32 *)uid+3), readl((u32 *)uid+4));
+	iounmap(base);
+	return retstr;
+}
+
+static void __init soc_info_populate(struct soc_device_attribute *soc_dev_attr,
+				     struct device_node *backupram)
+{
+	soc_dev_attr->soc_id   = db8500_read_soc_id(backupram);
+	soc_dev_attr->machine  = ux500_get_machine();
+	soc_dev_attr->family   = ux500_get_family();
+	soc_dev_attr->revision = ux500_get_revision();
+}
+
+static const struct device_attribute ux500_soc_attr =
+	__ATTR(process,  S_IRUGO, ux500_get_process,  NULL);
+
+static int __init ux500_soc_device_init(void)
+{
+	struct device *parent;
+	struct soc_device *soc_dev;
+	struct soc_device_attribute *soc_dev_attr;
+	struct device_node *backupram;
+
+	backupram = of_find_compatible_node(NULL, NULL, "ste,dbx500-backupram");
+	if (!backupram)
+		return 0;
+
+	ux500_setup_id();
+
+	soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL);
+	if (!soc_dev_attr)
+		return -ENOMEM;
+
+	soc_info_populate(soc_dev_attr, backupram);
+
+	soc_dev = soc_device_register(soc_dev_attr);
+	if (IS_ERR(soc_dev)) {
+	        kfree(soc_dev_attr);
+		return PTR_ERR(soc_dev);
+	}
+
+	parent = soc_device_to_device(soc_dev);
+	device_create_file(parent, &ux500_soc_attr);
+
+	return 0;
+}
+subsys_initcall(ux500_soc_device_init);
diff --git a/drivers/spi/spi-st-ssc4.c b/drivers/spi/spi-st-ssc4.c
index d5adf9f31602..a56eca0e95a6 100644
--- a/drivers/spi/spi-st-ssc4.c
+++ b/drivers/spi/spi-st-ssc4.c
@@ -68,32 +68,6 @@ struct spi_st {
 	struct completion	done;
 };
 
-static int spi_st_clk_enable(struct spi_st *spi_st)
-{
-	/*
-	 * Current platforms use one of the core clocks for SPI and I2C.
-	 * If we attempt to disable the clock, the system will hang.
-	 *
-	 * TODO: Remove this when platform supports power domains.
-	 */
-	return 0;
-
-	return clk_prepare_enable(spi_st->clk);
-}
-
-static void spi_st_clk_disable(struct spi_st *spi_st)
-{
-	/*
-	 * Current platforms use one of the core clocks for SPI and I2C.
-	 * If we attempt to disable the clock, the system will hang.
-	 *
-	 * TODO: Remove this when platform supports power domains.
-	 */
-	return;
-
-	clk_disable_unprepare(spi_st->clk);
-}
-
 /* Load the TX FIFO */
 static void ssc_write_tx_fifo(struct spi_st *spi_st)
 {
@@ -349,7 +323,7 @@ static int spi_st_probe(struct platform_device *pdev)
 		goto put_master;
 	}
 
-	ret = spi_st_clk_enable(spi_st);
+	ret = clk_prepare_enable(spi_st->clk);
 	if (ret)
 		goto put_master;
 
@@ -408,7 +382,7 @@ static int spi_st_probe(struct platform_device *pdev)
 	return 0;
 
 clk_disable:
-	spi_st_clk_disable(spi_st);
+	clk_disable_unprepare(spi_st->clk);
 put_master:
 	spi_master_put(master);
 	return ret;
@@ -419,7 +393,7 @@ static int spi_st_remove(struct platform_device *pdev)
 	struct spi_master *master = platform_get_drvdata(pdev);
 	struct spi_st *spi_st = spi_master_get_devdata(master);
 
-	spi_st_clk_disable(spi_st);
+	clk_disable_unprepare(spi_st->clk);
 
 	pinctrl_pm_select_sleep_state(&pdev->dev);
 
@@ -435,7 +409,7 @@ static int spi_st_runtime_suspend(struct device *dev)
 	writel_relaxed(0, spi_st->base + SSC_IEN);
 	pinctrl_pm_select_sleep_state(dev);
 
-	spi_st_clk_disable(spi_st);
+	clk_disable_unprepare(spi_st->clk);
 
 	return 0;
 }
@@ -446,7 +420,7 @@ static int spi_st_runtime_resume(struct device *dev)
 	struct spi_st *spi_st = spi_master_get_devdata(master);
 	int ret;
 
-	ret = spi_st_clk_enable(spi_st);
+	ret = clk_prepare_enable(spi_st->clk);
 	pinctrl_pm_select_default_state(dev);
 
 	return ret;
diff --git a/drivers/staging/android/sync_debug.h b/drivers/staging/android/sync_debug.h
index 425ebc5c32aa..fab66396d421 100644
--- a/drivers/staging/android/sync_debug.h
+++ b/drivers/staging/android/sync_debug.h
@@ -34,7 +34,8 @@ struct sync_timeline {
 	char			name[32];
 
 	/* protected by child_list_lock */
-	int			context, value;
+	u64			context;
+	int			value;
 
 	struct list_head	child_list_head;
 	spinlock_t		child_list_lock;
diff --git a/drivers/tty/hvc/hvc_console.h b/drivers/tty/hvc/hvc_console.h
index 913101980827..798c48d0d32c 100644
--- a/drivers/tty/hvc/hvc_console.h
+++ b/drivers/tty/hvc/hvc_console.h
@@ -60,6 +60,7 @@ struct hvc_struct {
 	struct winsize ws;
 	struct work_struct tty_resize;
 	struct list_head next;
+	unsigned long flags;
 };
 
 /* implemented by a low level driver */
diff --git a/drivers/tty/hvc/hvc_irq.c b/drivers/tty/hvc/hvc_irq.c
index c9adb0559f61..bc7a96874637 100644
--- a/drivers/tty/hvc/hvc_irq.c
+++ b/drivers/tty/hvc/hvc_irq.c
@@ -14,6 +14,11 @@ static irqreturn_t hvc_handle_interrupt(int irq, void *dev_instance)
 	/* if hvc_poll request a repoll, then kick the hvcd thread */
 	if (hvc_poll(dev_instance))
 		hvc_kick();
+
+	/*
+	 * We're safe to always return IRQ_HANDLED as the hvcd thread will
+	 * iterate through each hvc_struct.
+	 */
 	return IRQ_HANDLED;
 }
 
@@ -28,8 +33,8 @@ int notifier_add_irq(struct hvc_struct *hp, int irq)
 		hp->irq_requested = 0;
 		return 0;
 	}
-	rc = request_irq(irq, hvc_handle_interrupt, 0,
-			   "hvc_console", hp);
+	rc = request_irq(irq, hvc_handle_interrupt, hp->flags,
+			"hvc_console", hp);
 	if (!rc)
 		hp->irq_requested = 1;
 	return rc;
diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c
index 47b54c6aefd2..510799311099 100644
--- a/drivers/tty/hvc/hvc_opal.c
+++ b/drivers/tty/hvc/hvc_opal.c
@@ -214,7 +214,13 @@ static int hvc_opal_probe(struct platform_device *dev)
 		dev->dev.of_node->full_name,
 		boot ? " (boot console)" : "");
 
-	irq = opal_event_request(ilog2(OPAL_EVENT_CONSOLE_INPUT));
+	irq = irq_of_parse_and_map(dev->dev.of_node, 0);
+	if (!irq) {
+		pr_info("hvc%d: No interrupts property, using OPAL event\n",
+				termno);
+		irq = opal_event_request(ilog2(OPAL_EVENT_CONSOLE_INPUT));
+	}
+
 	if (!irq) {
 		pr_err("hvc_opal: Unable to map interrupt for device %s\n",
 			dev->dev.of_node->full_name);
@@ -224,6 +230,9 @@ static int hvc_opal_probe(struct platform_device *dev)
 	hp = hvc_alloc(termno, irq, ops, MAX_VIO_PUT_CHARS);
 	if (IS_ERR(hp))
 		return PTR_ERR(hp);
+
+	/* hvc consoles on powernv may need to share a single irq */
+	hp->flags = IRQF_SHARED;
 	dev_set_drvdata(&dev->dev, hp);
 
 	return 0;
diff --git a/drivers/tty/serial/clps711x.c b/drivers/tty/serial/clps711x.c
index 5beafd2d2218..ac1328629baa 100644
--- a/drivers/tty/serial/clps711x.c
+++ b/drivers/tty/serial/clps711x.c
@@ -539,7 +539,7 @@ static int uart_clps711x_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id __maybe_unused clps711x_uart_dt_ids[] = {
-	{ .compatible = "cirrus,clps711x-uart", },
+	{ .compatible = "cirrus,ep7209-uart", },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, clps711x_uart_dt_ids);
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index c10972fcc8e4..4fd041bec332 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -387,7 +387,7 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
 	 * need to have the registers polled during D3, so avoid D3cold.
 	 */
 	if (xhci->quirks & XHCI_COMP_MODE_QUIRK)
-		pdev->no_d3cold = true;
+		pci_d3cold_disable(pdev);
 
 	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
 		xhci_pme_quirk(hcd);
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index e5b14f52628f..939f057836e1 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/i2c.h>
 #include <linux/backlight.h>
+#include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/of.h>
 #include <linux/platform_data/lp855x.h>
@@ -74,6 +75,7 @@ struct lp855x {
 	struct lp855x_platform_data *pdata;
 	struct pwm_device *pwm;
 	struct regulator *supply;	/* regulator for VDD input */
+	struct regulator *enable;	/* regulator for EN/VDDIO input */
 };
 
 static int lp855x_write_byte(struct lp855x *lp, u8 reg, u8 data)
@@ -433,6 +435,19 @@ static int lp855x_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 		lp->supply = NULL;
 	}
 
+	lp->enable = devm_regulator_get_optional(lp->dev, "enable");
+	if (IS_ERR(lp->enable)) {
+		ret = PTR_ERR(lp->enable);
+		if (ret == -ENODEV) {
+			lp->enable = NULL;
+		} else {
+			if (ret != -EPROBE_DEFER)
+				dev_err(lp->dev, "error getting enable regulator: %d\n",
+					ret);
+			return ret;
+		}
+	}
+
 	if (lp->supply) {
 		ret = regulator_enable(lp->supply);
 		if (ret < 0) {
@@ -441,6 +456,20 @@ static int lp855x_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 		}
 	}
 
+	if (lp->enable) {
+		ret = regulator_enable(lp->enable);
+		if (ret < 0) {
+			dev_err(lp->dev, "failed to enable vddio: %d\n", ret);
+			return ret;
+		}
+
+		/*
+		 * LP8555 datasheet says t_RESPONSE (time between VDDIO and
+		 * I2C) is 1ms.
+		 */
+		usleep_range(1000, 2000);
+	}
+
 	i2c_set_clientdata(cl, lp);
 
 	ret = lp855x_configure(lp);
diff --git a/drivers/video/fbdev/bfin_adv7393fb.c b/drivers/video/fbdev/bfin_adv7393fb.c
index 8fe41caac38e..e2d7d039ce3b 100644
--- a/drivers/video/fbdev/bfin_adv7393fb.c
+++ b/drivers/video/fbdev/bfin_adv7393fb.c
@@ -10,6 +10,8 @@
  * TODO: Code Cleanup
  */
 
+#define DRIVER_NAME "bfin-adv7393"
+
 #define pr_fmt(fmt) DRIVER_NAME ": " fmt
 
 #include <linux/module.h>
diff --git a/drivers/video/fbdev/bfin_adv7393fb.h b/drivers/video/fbdev/bfin_adv7393fb.h
index cd591b5152a5..afd0380e19e1 100644
--- a/drivers/video/fbdev/bfin_adv7393fb.h
+++ b/drivers/video/fbdev/bfin_adv7393fb.h
@@ -59,8 +59,6 @@ enum {
 	BLANK_OFF,
 };
 
-#define DRIVER_NAME "bfin-adv7393"
-
 struct adv7393fb_modes {
 	const s8 name[25];	/* Full name */
 	u16 xres;		/* Active Horizonzal Pixels  */
diff --git a/drivers/video/fbdev/clps711x-fb.c b/drivers/video/fbdev/clps711x-fb.c
index 649b32f78c08..ff561073ee4e 100644
--- a/drivers/video/fbdev/clps711x-fb.c
+++ b/drivers/video/fbdev/clps711x-fb.c
@@ -273,7 +273,7 @@ static int clps711x_fb_probe(struct platform_device *pdev)
 	}
 
 	cfb->syscon =
-		syscon_regmap_lookup_by_compatible("cirrus,clps711x-syscon1");
+		syscon_regmap_lookup_by_compatible("cirrus,ep7209-syscon1");
 	if (IS_ERR(cfb->syscon)) {
 		ret = PTR_ERR(cfb->syscon);
 		goto out_fb_release;
@@ -376,7 +376,7 @@ static int clps711x_fb_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id clps711x_fb_dt_ids[] = {
-	{ .compatible = "cirrus,clps711x-fb", },
+	{ .compatible = "cirrus,ep7209-fb", },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, clps711x_fb_dt_ids);
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/connector-analog-tv.c b/drivers/video/fbdev/omap2/omapfb/displays/connector-analog-tv.c
index 8511c648a15c..9d78411a3bf7 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/connector-analog-tv.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/connector-analog-tv.c
@@ -14,7 +14,7 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include <video/omap-panel-data.h>
 
 struct panel_drv_data {
@@ -25,7 +25,6 @@ struct panel_drv_data {
 
 	struct omap_video_timings timings;
 
-	enum omap_dss_venc_type connector_type;
 	bool invert_polarity;
 };
 
@@ -45,10 +44,6 @@ static const struct omap_video_timings tvc_pal_timings = {
 
 static const struct of_device_id tvc_of_match[];
 
-struct tvc_of_data {
-	enum omap_dss_venc_type connector_type;
-};
-
 #define to_panel_data(x) container_of(x, struct panel_drv_data, dssdev)
 
 static int tvc_connect(struct omap_dss_device *dssdev)
@@ -99,7 +94,7 @@ static int tvc_enable(struct omap_dss_device *dssdev)
 	in->ops.atv->set_timings(in, &ddata->timings);
 
 	if (!ddata->dev->of_node) {
-		in->ops.atv->set_type(in, ddata->connector_type);
+		in->ops.atv->set_type(in, OMAP_DSS_VENC_TYPE_COMPOSITE);
 
 		in->ops.atv->invert_vid_out_polarity(in,
 			ddata->invert_polarity);
@@ -207,7 +202,6 @@ static int tvc_probe_pdata(struct platform_device *pdev)
 
 	ddata->in = in;
 
-	ddata->connector_type = pdata->connector_type;
 	ddata->invert_polarity = pdata->invert_polarity;
 
 	dssdev = &ddata->dssdev;
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/connector-dvi.c b/drivers/video/fbdev/omap2/omapfb/displays/connector-dvi.c
index d811e6dcaef7..06e1db34541e 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/connector-dvi.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/connector-dvi.c
@@ -16,8 +16,7 @@
 
 #include <drm/drm_edid.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include <video/omapfb_dss.h>
 
 static const struct omap_video_timings dvic_default_timings = {
 	.x_res		= 640,
@@ -236,46 +235,6 @@ static struct omap_dss_driver dvic_driver = {
 	.detect		= dvic_detect,
 };
 
-static int dvic_probe_pdata(struct platform_device *pdev)
-{
-	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
-	struct connector_dvi_platform_data *pdata;
-	struct omap_dss_device *in, *dssdev;
-	int i2c_bus_num;
-
-	pdata = dev_get_platdata(&pdev->dev);
-	i2c_bus_num = pdata->i2c_bus_num;
-
-	if (i2c_bus_num != -1) {
-		struct i2c_adapter *adapter;
-
-		adapter = i2c_get_adapter(i2c_bus_num);
-		if (!adapter) {
-			dev_err(&pdev->dev,
-					"Failed to get I2C adapter, bus %d\n",
-					i2c_bus_num);
-			return -EPROBE_DEFER;
-		}
-
-		ddata->i2c_adapter = adapter;
-	}
-
-	in = omap_dss_find_output(pdata->source);
-	if (in == NULL) {
-		i2c_put_adapter(ddata->i2c_adapter);
-
-		dev_err(&pdev->dev, "Failed to find video source\n");
-		return -EPROBE_DEFER;
-	}
-
-	ddata->in = in;
-
-	dssdev = &ddata->dssdev;
-	dssdev->name = pdata->name;
-
-	return 0;
-}
-
 static int dvic_probe_of(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
@@ -313,23 +272,18 @@ static int dvic_probe(struct platform_device *pdev)
 	struct omap_dss_device *dssdev;
 	int r;
 
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
 	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
 	if (!ddata)
 		return -ENOMEM;
 
 	platform_set_drvdata(pdev, ddata);
 
-	if (dev_get_platdata(&pdev->dev)) {
-		r = dvic_probe_pdata(pdev);
-		if (r)
-			return r;
-	} else if (pdev->dev.of_node) {
-		r = dvic_probe_of(pdev);
-		if (r)
-			return r;
-	} else {
-		return -ENODEV;
-	}
+	r = dvic_probe_of(pdev);
+	if (r)
+		return r;
 
 	ddata->timings = dvic_default_timings;
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/connector-hdmi.c b/drivers/video/fbdev/omap2/omapfb/displays/connector-hdmi.c
index 6ee4129bc0c0..58d5803ede67 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/connector-hdmi.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/connector-hdmi.c
@@ -17,8 +17,7 @@
 
 #include <drm/drm_edid.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include <video/omapfb_dss.h>
 
 static const struct omap_video_timings hdmic_default_timings = {
 	.x_res		= 640,
@@ -206,30 +205,6 @@ static struct omap_dss_driver hdmic_driver = {
 	.set_hdmi_infoframe	= hdmic_set_infoframe,
 };
 
-static int hdmic_probe_pdata(struct platform_device *pdev)
-{
-	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
-	struct connector_hdmi_platform_data *pdata;
-	struct omap_dss_device *in, *dssdev;
-
-	pdata = dev_get_platdata(&pdev->dev);
-
-	ddata->hpd_gpio = -ENODEV;
-
-	in = omap_dss_find_output(pdata->source);
-	if (in == NULL) {
-		dev_err(&pdev->dev, "Failed to find video source\n");
-		return -EPROBE_DEFER;
-	}
-
-	ddata->in = in;
-
-	dssdev = &ddata->dssdev;
-	dssdev->name = pdata->name;
-
-	return 0;
-}
-
 static int hdmic_probe_of(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
@@ -261,6 +236,9 @@ static int hdmic_probe(struct platform_device *pdev)
 	struct omap_dss_device *dssdev;
 	int r;
 
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
 	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
 	if (!ddata)
 		return -ENOMEM;
@@ -268,17 +246,9 @@ static int hdmic_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ddata);
 	ddata->dev = &pdev->dev;
 
-	if (dev_get_platdata(&pdev->dev)) {
-		r = hdmic_probe_pdata(pdev);
-		if (r)
-			return r;
-	} else if (pdev->dev.of_node) {
-		r = hdmic_probe_of(pdev);
-		if (r)
-			return r;
-	} else {
-		return -ENODEV;
-	}
+	r = hdmic_probe_of(pdev);
+	if (r)
+		return r;
 
 	if (gpio_is_valid(ddata->hpd_gpio)) {
 		r = devm_gpio_request_one(&pdev->dev, ddata->hpd_gpio,
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/encoder-opa362.c b/drivers/video/fbdev/omap2/omapfb/displays/encoder-opa362.c
index 8c246c213e06..a9a67167cc3d 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/encoder-opa362.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/encoder-opa362.c
@@ -20,7 +20,7 @@
 #include <linux/slab.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/encoder-tfp410.c b/drivers/video/fbdev/omap2/omapfb/displays/encoder-tfp410.c
index d9048b3df495..8c0953d069b7 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/encoder-tfp410.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/encoder-tfp410.c
@@ -15,8 +15,7 @@
 #include <linux/slab.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include <video/omapfb_dss.h>
 
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
@@ -166,32 +165,6 @@ static const struct omapdss_dvi_ops tfp410_dvi_ops = {
 	.get_timings	= tfp410_get_timings,
 };
 
-static int tfp410_probe_pdata(struct platform_device *pdev)
-{
-	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
-	struct encoder_tfp410_platform_data *pdata;
-	struct omap_dss_device *dssdev, *in;
-
-	pdata = dev_get_platdata(&pdev->dev);
-
-	ddata->pd_gpio = pdata->power_down_gpio;
-
-	ddata->data_lines = pdata->data_lines;
-
-	in = omap_dss_find_output(pdata->source);
-	if (in == NULL) {
-		dev_err(&pdev->dev, "Failed to find video source\n");
-		return -ENODEV;
-	}
-
-	ddata->in = in;
-
-	dssdev = &ddata->dssdev;
-	dssdev->name = pdata->name;
-
-	return 0;
-}
-
 static int tfp410_probe_of(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
@@ -225,23 +198,18 @@ static int tfp410_probe(struct platform_device *pdev)
 	struct omap_dss_device *dssdev;
 	int r;
 
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
 	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
 	if (!ddata)
 		return -ENOMEM;
 
 	platform_set_drvdata(pdev, ddata);
 
-	if (dev_get_platdata(&pdev->dev)) {
-		r = tfp410_probe_pdata(pdev);
-		if (r)
-			return r;
-	} else if (pdev->dev.of_node) {
-		r = tfp410_probe_of(pdev);
-		if (r)
-			return r;
-	} else {
-		return -ENODEV;
-	}
+	r = tfp410_probe_of(pdev);
+	if (r)
+		return r;
 
 	if (gpio_is_valid(ddata->pd_gpio)) {
 		r = devm_gpio_request_one(&pdev->dev, ddata->pd_gpio,
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/encoder-tpd12s015.c b/drivers/video/fbdev/omap2/omapfb/displays/encoder-tpd12s015.c
index 677e2545fcbe..80dc47347e21 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/encoder-tpd12s015.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/encoder-tpd12s015.c
@@ -16,8 +16,7 @@
 #include <linux/platform_device.h>
 #include <linux/gpio/consumer.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include <video/omapfb_dss.h>
 
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dpi.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dpi.c
index e780fd4f8b46..ace3d818afe5 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dpi.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dpi.c
@@ -16,7 +16,7 @@
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include <video/omap-panel-data.h>
 #include <video/of_display_timing.h>
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c
index 3414c2609320..b58012b82b6f 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c
@@ -25,8 +25,7 @@
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include <video/omapfb_dss.h>
 #include <video/mipi_display.h>
 
 /* DSI Virtual channel. Hardcoded for now. */
@@ -1127,40 +1126,6 @@ static struct omap_dss_driver dsicm_ops = {
 	.memory_read	= dsicm_memory_read,
 };
 
-static int dsicm_probe_pdata(struct platform_device *pdev)
-{
-	const struct panel_dsicm_platform_data *pdata;
-	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
-	struct omap_dss_device *dssdev, *in;
-
-	pdata = dev_get_platdata(&pdev->dev);
-
-	in = omap_dss_find_output(pdata->source);
-	if (in == NULL) {
-		dev_err(&pdev->dev, "failed to find video source\n");
-		return -EPROBE_DEFER;
-	}
-	ddata->in = in;
-
-	ddata->reset_gpio = pdata->reset_gpio;
-
-	if (pdata->use_ext_te)
-		ddata->ext_te_gpio = pdata->ext_te_gpio;
-	else
-		ddata->ext_te_gpio = -1;
-
-	ddata->ulps_timeout = pdata->ulps_timeout;
-
-	ddata->use_dsi_backlight = pdata->use_dsi_backlight;
-
-	ddata->pin_config = pdata->pin_config;
-
-	dssdev = &ddata->dssdev;
-	dssdev->name = pdata->name;
-
-	return 0;
-}
-
 static int dsicm_probe_of(struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
@@ -1207,6 +1172,9 @@ static int dsicm_probe(struct platform_device *pdev)
 
 	dev_dbg(dev, "probe\n");
 
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
 	ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL);
 	if (!ddata)
 		return -ENOMEM;
@@ -1214,17 +1182,9 @@ static int dsicm_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ddata);
 	ddata->pdev = pdev;
 
-	if (dev_get_platdata(dev)) {
-		r = dsicm_probe_pdata(pdev);
-		if (r)
-			return r;
-	} else if (pdev->dev.of_node) {
-		r = dsicm_probe_of(pdev);
-		if (r)
-			return r;
-	} else {
-		return -ENODEV;
-	}
+	r = dsicm_probe_of(pdev);
+	if (r)
+		return r;
 
 	ddata->timings.x_res = 864;
 	ddata->timings.y_res = 480;
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-lgphilips-lb035q02.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-lgphilips-lb035q02.c
index 18eb60e9c9ec..f14691ce8d02 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-lgphilips-lb035q02.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-lgphilips-lb035q02.c
@@ -16,8 +16,7 @@
 #include <linux/mutex.h>
 #include <linux/gpio.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include <video/omapfb_dss.h>
 
 static struct omap_video_timings lb035q02_timings = {
 	.x_res = 320,
@@ -240,44 +239,6 @@ static struct omap_dss_driver lb035q02_ops = {
 	.get_resolution	= omapdss_default_get_resolution,
 };
 
-static int lb035q02_probe_pdata(struct spi_device *spi)
-{
-	const struct panel_lb035q02_platform_data *pdata;
-	struct panel_drv_data *ddata = dev_get_drvdata(&spi->dev);
-	struct omap_dss_device *dssdev, *in;
-	int r;
-
-	pdata = dev_get_platdata(&spi->dev);
-
-	in = omap_dss_find_output(pdata->source);
-	if (in == NULL) {
-		dev_err(&spi->dev, "failed to find video source '%s'\n",
-				pdata->source);
-		return -EPROBE_DEFER;
-	}
-
-	ddata->in = in;
-
-	ddata->data_lines = pdata->data_lines;
-
-	dssdev = &ddata->dssdev;
-	dssdev->name = pdata->name;
-
-	r = devm_gpio_request_one(&spi->dev, pdata->enable_gpio,
-					GPIOF_OUT_INIT_LOW, "panel enable");
-	if (r)
-		goto err_gpio;
-
-	ddata->enable_gpio = gpio_to_desc(pdata->enable_gpio);
-
-	ddata->backlight_gpio = pdata->backlight_gpio;
-
-	return 0;
-err_gpio:
-	omap_dss_put_device(ddata->in);
-	return r;
-}
-
 static int lb035q02_probe_of(struct spi_device *spi)
 {
 	struct device_node *node = spi->dev.of_node;
@@ -312,6 +273,9 @@ static int lb035q02_panel_spi_probe(struct spi_device *spi)
 	struct omap_dss_device *dssdev;
 	int r;
 
+	if (!spi->dev.of_node)
+		return -ENODEV;
+
 	ddata = devm_kzalloc(&spi->dev, sizeof(*ddata), GFP_KERNEL);
 	if (ddata == NULL)
 		return -ENOMEM;
@@ -320,17 +284,9 @@ static int lb035q02_panel_spi_probe(struct spi_device *spi)
 
 	ddata->spi = spi;
 
-	if (dev_get_platdata(&spi->dev)) {
-		r = lb035q02_probe_pdata(spi);
-		if (r)
-			return r;
-	} else if (spi->dev.of_node) {
-		r = lb035q02_probe_of(spi);
-		if (r)
-			return r;
-	} else {
-		return -ENODEV;
-	}
+	r = lb035q02_probe_of(spi);
+	if (r)
+		return r;
 
 	if (gpio_is_valid(ddata->backlight_gpio)) {
 		r = devm_gpio_request_one(&spi->dev, ddata->backlight_gpio,
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-nec-nl8048hl11.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-nec-nl8048hl11.c
index 8a928c9a2fc9..a2cbadd3eca3 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-nec-nl8048hl11.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-nec-nl8048hl11.c
@@ -18,8 +18,7 @@
 #include <linux/gpio.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include <video/omapfb_dss.h>
 
 struct panel_drv_data {
 	struct omap_dss_device	dssdev;
@@ -233,33 +232,6 @@ static struct omap_dss_driver nec_8048_ops = {
 };
 
 
-static int nec_8048_probe_pdata(struct spi_device *spi)
-{
-	const struct panel_nec_nl8048hl11_platform_data *pdata;
-	struct panel_drv_data *ddata = dev_get_drvdata(&spi->dev);
-	struct omap_dss_device *dssdev, *in;
-
-	pdata = dev_get_platdata(&spi->dev);
-
-	ddata->qvga_gpio = pdata->qvga_gpio;
-	ddata->res_gpio = pdata->res_gpio;
-
-	in = omap_dss_find_output(pdata->source);
-	if (in == NULL) {
-		dev_err(&spi->dev, "failed to find video source '%s'\n",
-				pdata->source);
-		return -EPROBE_DEFER;
-	}
-	ddata->in = in;
-
-	ddata->data_lines = pdata->data_lines;
-
-	dssdev = &ddata->dssdev;
-	dssdev->name = pdata->name;
-
-	return 0;
-}
-
 static int nec_8048_probe_of(struct spi_device *spi)
 {
 	struct device_node *node = spi->dev.of_node;
@@ -296,6 +268,9 @@ static int nec_8048_probe(struct spi_device *spi)
 
 	dev_dbg(&spi->dev, "%s\n", __func__);
 
+	if (!spi->dev.of_node)
+		return -ENODEV;
+
 	spi->mode = SPI_MODE_0;
 	spi->bits_per_word = 32;
 
@@ -315,17 +290,9 @@ static int nec_8048_probe(struct spi_device *spi)
 
 	ddata->spi = spi;
 
-	if (dev_get_platdata(&spi->dev)) {
-		r = nec_8048_probe_pdata(spi);
-		if (r)
-			return r;
-	} else if (spi->dev.of_node) {
-		r = nec_8048_probe_of(spi);
-		if (r)
-			return r;
-	} else {
-		return -ENODEV;
-	}
+	r = nec_8048_probe_of(spi);
+	if (r)
+		return r;
 
 	if (gpio_is_valid(ddata->qvga_gpio)) {
 		r = devm_gpio_request_one(&spi->dev, ddata->qvga_gpio,
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-sharp-ls037v7dw01.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-sharp-ls037v7dw01.c
index 1954ec913ce5..a8be18a87fa0 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-sharp-ls037v7dw01.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-sharp-ls037v7dw01.c
@@ -17,8 +17,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/regulator/consumer.h>
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include <video/omapfb_dss.h>
 
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
@@ -197,69 +196,6 @@ static struct omap_dss_driver sharp_ls_ops = {
 	.get_resolution	= omapdss_default_get_resolution,
 };
 
-static int sharp_ls_get_gpio(struct device *dev, int gpio, unsigned long flags,
-		  char *desc, struct gpio_desc **gpiod)
-{
-	int r;
-
-	r = devm_gpio_request_one(dev, gpio, flags, desc);
-	if (r) {
-		*gpiod = NULL;
-		return r == -ENOENT ? 0 : r;
-	}
-
-	*gpiod = gpio_to_desc(gpio);
-
-	return 0;
-}
-
-static int sharp_ls_probe_pdata(struct platform_device *pdev)
-{
-	const struct panel_sharp_ls037v7dw01_platform_data *pdata;
-	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
-	struct omap_dss_device *dssdev, *in;
-	int r;
-
-	pdata = dev_get_platdata(&pdev->dev);
-
-	in = omap_dss_find_output(pdata->source);
-	if (in == NULL) {
-		dev_err(&pdev->dev, "failed to find video source '%s'\n",
-				pdata->source);
-		return -EPROBE_DEFER;
-	}
-
-	ddata->in = in;
-
-	ddata->data_lines = pdata->data_lines;
-
-	dssdev = &ddata->dssdev;
-	dssdev->name = pdata->name;
-
-	r = sharp_ls_get_gpio(&pdev->dev, pdata->mo_gpio, GPIOF_OUT_INIT_LOW,
-		"lcd MO", &ddata->mo_gpio);
-	if (r)
-		return r;
-	r = sharp_ls_get_gpio(&pdev->dev, pdata->lr_gpio, GPIOF_OUT_INIT_HIGH,
-		"lcd LR", &ddata->lr_gpio);
-	if (r)
-		return r;
-	r = sharp_ls_get_gpio(&pdev->dev, pdata->ud_gpio, GPIOF_OUT_INIT_HIGH,
-		"lcd UD", &ddata->ud_gpio);
-	if (r)
-		return r;
-	r = sharp_ls_get_gpio(&pdev->dev, pdata->resb_gpio, GPIOF_OUT_INIT_LOW,
-		"lcd RESB", &ddata->resb_gpio);
-	if (r)
-		return r;
-	r = sharp_ls_get_gpio(&pdev->dev, pdata->ini_gpio, GPIOF_OUT_INIT_LOW,
-		"lcd INI", &ddata->ini_gpio);
-	if (r)
-		return r;
-
-	return 0;
-}
-
 static  int sharp_ls_get_gpio_of(struct device *dev, int index, int val,
 	const char *desc, struct gpio_desc **gpiod)
 {
@@ -330,23 +266,18 @@ static int sharp_ls_probe(struct platform_device *pdev)
 	struct omap_dss_device *dssdev;
 	int r;
 
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
 	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
 	if (ddata == NULL)
 		return -ENOMEM;
 
 	platform_set_drvdata(pdev, ddata);
 
-	if (dev_get_platdata(&pdev->dev)) {
-		r = sharp_ls_probe_pdata(pdev);
-		if (r)
-			return r;
-	} else if (pdev->dev.of_node) {
-		r = sharp_ls_probe_of(pdev);
-		if (r)
-			return r;
-	} else {
-		return -ENODEV;
-	}
+	r = sharp_ls_probe_of(pdev);
+	if (r)
+		return r;
 
 	ddata->videomode = sharp_ls_timings;
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-sony-acx565akm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-sony-acx565akm.c
index 31efcca801bd..468560a6daae 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-sony-acx565akm.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-sony-acx565akm.c
@@ -33,7 +33,7 @@
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include <video/omap-panel-data.h>
 
 #define MIPID_CMD_READ_DISP_ID		0x04
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td028ttec1.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td028ttec1.c
index 4d657f3ab679..b529a8c2b652 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td028ttec1.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td028ttec1.c
@@ -28,8 +28,7 @@
 #include <linux/delay.h>
 #include <linux/spi/spi.h>
 #include <linux/gpio.h>
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include <video/omapfb_dss.h>
 
 struct panel_drv_data {
 	struct omap_dss_device dssdev;
@@ -365,31 +364,6 @@ static struct omap_dss_driver td028ttec1_ops = {
 	.check_timings	= td028ttec1_panel_check_timings,
 };
 
-static int td028ttec1_panel_probe_pdata(struct spi_device *spi)
-{
-	const struct panel_tpo_td028ttec1_platform_data *pdata;
-	struct panel_drv_data *ddata = dev_get_drvdata(&spi->dev);
-	struct omap_dss_device *dssdev, *in;
-
-	pdata = dev_get_platdata(&spi->dev);
-
-	in = omap_dss_find_output(pdata->source);
-	if (in == NULL) {
-		dev_err(&spi->dev, "failed to find video source '%s'\n",
-				pdata->source);
-		return -EPROBE_DEFER;
-	}
-
-	ddata->in = in;
-
-	ddata->data_lines = pdata->data_lines;
-
-	dssdev = &ddata->dssdev;
-	dssdev->name = pdata->name;
-
-	return 0;
-}
-
 static int td028ttec1_probe_of(struct spi_device *spi)
 {
 	struct device_node *node = spi->dev.of_node;
@@ -415,6 +389,9 @@ static int td028ttec1_panel_probe(struct spi_device *spi)
 
 	dev_dbg(&spi->dev, "%s\n", __func__);
 
+	if (!spi->dev.of_node)
+		return -ENODEV;
+
 	spi->bits_per_word = 9;
 	spi->mode = SPI_MODE_3;
 
@@ -432,17 +409,9 @@ static int td028ttec1_panel_probe(struct spi_device *spi)
 
 	ddata->spi_dev = spi;
 
-	if (dev_get_platdata(&spi->dev)) {
-		r = td028ttec1_panel_probe_pdata(spi);
-		if (r)
-			return r;
-	} else if (spi->dev.of_node) {
-		r = td028ttec1_probe_of(spi);
-		if (r)
-			return r;
-	} else {
-		return -ENODEV;
-	}
+	r = td028ttec1_probe_of(spi);
+	if (r)
+		return r;
 
 	ddata->videomode = td028ttec1_panel_timings;
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c
index 68e3b68a2920..51e628b85f4a 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c
@@ -19,8 +19,7 @@
 #include <linux/slab.h>
 #include <linux/of_gpio.h>
 
-#include <video/omapdss.h>
-#include <video/omap-panel-data.h>
+#include <video/omapfb_dss.h>
 
 #define TPO_R02_MODE(x)		((x) & 7)
 #define TPO_R02_MODE_800x480	7
@@ -465,32 +464,6 @@ static struct omap_dss_driver tpo_td043_ops = {
 };
 
 
-static int tpo_td043_probe_pdata(struct spi_device *spi)
-{
-	const struct panel_tpo_td043mtea1_platform_data *pdata;
-	struct panel_drv_data *ddata = dev_get_drvdata(&spi->dev);
-	struct omap_dss_device *dssdev, *in;
-
-	pdata = dev_get_platdata(&spi->dev);
-
-	ddata->nreset_gpio = pdata->nreset_gpio;
-
-	in = omap_dss_find_output(pdata->source);
-	if (in == NULL) {
-		dev_err(&spi->dev, "failed to find video source '%s'\n",
-				pdata->source);
-		return -EPROBE_DEFER;
-	}
-	ddata->in = in;
-
-	ddata->data_lines = pdata->data_lines;
-
-	dssdev = &ddata->dssdev;
-	dssdev->name = pdata->name;
-
-	return 0;
-}
-
 static int tpo_td043_probe_of(struct spi_device *spi)
 {
 	struct device_node *node = spi->dev.of_node;
@@ -524,6 +497,9 @@ static int tpo_td043_probe(struct spi_device *spi)
 
 	dev_dbg(&spi->dev, "%s\n", __func__);
 
+	if (!spi->dev.of_node)
+		return -ENODEV;
+
 	spi->bits_per_word = 16;
 	spi->mode = SPI_MODE_0;
 
@@ -541,17 +517,9 @@ static int tpo_td043_probe(struct spi_device *spi)
 
 	ddata->spi = spi;
 
-	if (dev_get_platdata(&spi->dev)) {
-		r = tpo_td043_probe_pdata(spi);
-		if (r)
-			return r;
-	} else if (spi->dev.of_node) {
-		r = tpo_td043_probe_of(spi);
-		if (r)
-			return r;
-	} else {
-		return -ENODEV;
-	}
+	r = tpo_td043_probe_of(spi);
+	if (r)
+		return r;
 
 	ddata->mode = TPO_R02_MODE_800x480;
 	memcpy(ddata->gamma, tpo_td043_def_gamma, sizeof(ddata->gamma));
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/apply.c b/drivers/video/fbdev/omap2/omapfb/dss/apply.c
index 663ccc3bf4e5..2481f4871f66 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/apply.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/apply.c
@@ -23,7 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/jiffies.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/core.c b/drivers/video/fbdev/omap2/omapfb/dss/core.c
index 5a87179b7312..29de4827589d 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/core.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/core.c
@@ -35,7 +35,7 @@
 #include <linux/suspend.h>
 #include <linux/slab.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
@@ -208,8 +208,6 @@ static int __init omap_dss_probe(struct platform_device *pdev)
 		core.default_display_name = def_disp_name;
 	else if (pdata->default_display_name)
 		core.default_display_name = pdata->default_display_name;
-	else if (pdata->default_device)
-		core.default_display_name = pdata->default_device->name;
 
 	register_pm_notifier(&omap_dss_pm_notif_block);
 
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc-compat.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc-compat.c
index 6607db37a5e4..3691bde4ce0a 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dispc-compat.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc-compat.c
@@ -26,7 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/seq_file.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
index 5491e304f4fe..7a75dfda9845 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
@@ -41,7 +41,7 @@
 #include <linux/of.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc_coefs.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc_coefs.c
index 038c15b04215..59c9a5c47ca9 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dispc_coefs.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc_coefs.c
@@ -18,7 +18,7 @@
  */
 
 #include <linux/kernel.h>
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dispc.h"
 
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c
index 75b5286029ee..b3fdbfd0b82d 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c
@@ -25,7 +25,7 @@
 #include <linux/platform_device.h>
 #include <linux/sysfs.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include "dss.h"
 
 static ssize_t display_name_show(struct omap_dss_device *dssdev, char *buf)
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/display.c b/drivers/video/fbdev/omap2/omapfb/dss/display.c
index ef5b9027985d..dd5468695c43 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/display.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/display.c
@@ -28,7 +28,7 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include "dss.h"
 #include "dss_features.h"
 
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dpi.c b/drivers/video/fbdev/omap2/omapfb/dss/dpi.c
index 7953e6a52346..da09806b940c 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dpi.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dpi.c
@@ -34,7 +34,7 @@
 #include <linux/clk.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dsi.c b/drivers/video/fbdev/omap2/omapfb/dss/dsi.c
index d63e59807707..9e4800a4e3d1 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dsi.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dsi.c
@@ -42,7 +42,7 @@
 #include <linux/of_platform.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include <video/mipi_display.h>
 
 #include "dss.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c
index bf407b6ba15c..d356a252ab4a 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c
@@ -18,7 +18,7 @@
 #include <linux/of.h>
 #include <linux/seq_file.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss.c b/drivers/video/fbdev/omap2/omapfb/dss/dss.c
index 0078c4d1fc31..47d7f69ad9ad 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss.c
@@ -41,7 +41,7 @@
 #include <linux/suspend.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss.h b/drivers/video/fbdev/omap2/omapfb/dss/dss.h
index 0184a8461df1..a3cc0ca8f9d2 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss.h
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss.h
@@ -73,6 +73,17 @@
 #define FLD_MOD(orig, val, start, end) \
 	(((orig) & ~FLD_MASK(start, end)) | FLD_VAL(val, start, end))
 
+enum omap_dss_clk_source {
+	OMAP_DSS_CLK_SRC_FCK = 0,		/* OMAP2/3: DSS1_ALWON_FCLK
+						 * OMAP4: DSS_FCLK */
+	OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC,	/* OMAP3: DSI1_PLL_FCLK
+						 * OMAP4: PLL1_CLK1 */
+	OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI,	/* OMAP3: DSI2_PLL_FCLK
+						 * OMAP4: PLL1_CLK2 */
+	OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC,	/* OMAP4: PLL2_CLK1 */
+	OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI,	/* OMAP4: PLL2_CLK2 */
+};
+
 enum dss_io_pad_mode {
 	DSS_IO_PAD_MODE_RESET,
 	DSS_IO_PAD_MODE_RFBI,
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c b/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c
index c886a2927f73..8fc843b56b26 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c
@@ -23,7 +23,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi.h b/drivers/video/fbdev/omap2/omapfb/dss/hdmi.h
index 53616b02b613..f6de87e078b0 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi.h
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi.h
@@ -23,7 +23,8 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/hdmi.h>
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
+#include <sound/omap-hdmi-audio.h>
 
 #include "dss.h"
 
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c
index 2e71aec838b1..926a6f20dbb2 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c
@@ -33,7 +33,7 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/component.h>
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include <sound/omap-hdmi-audio.h>
 
 #include "hdmi4_core.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5.c
index aade6d99662a..0ee829a165c3 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5.c
@@ -38,7 +38,7 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/component.h>
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include <sound/omap-hdmi-audio.h>
 
 #include "hdmi5_core.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_common.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_common.c
index 1b8fcc6c4ba1..189a5ad125a3 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_common.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_common.c
@@ -4,7 +4,7 @@
 #include <linux/kernel.h>
 #include <linux/err.h>
 #include <linux/of.h>
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "hdmi.h"
 
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_phy.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_phy.c
index 1f5d19c119ce..9a13c35fd6d8 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_phy.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_phy.c
@@ -13,7 +13,7 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "hdmi.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_pll.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_pll.c
index 06e23a7c432c..eac3665aba6c 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_pll.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_pll.c
@@ -17,7 +17,7 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "hdmi.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_wp.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_wp.c
index 7c544bc56fb5..705373e4cf38 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_wp.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_wp.c
@@ -14,7 +14,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "hdmi.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c
index a7414fb12830..9e2a67fdf4d2 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c
@@ -26,7 +26,7 @@
 #include <linux/platform_device.h>
 #include <linux/jiffies.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/manager.c b/drivers/video/fbdev/omap2/omapfb/dss/manager.c
index 08a67f4f6a20..69f86d2cc274 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/manager.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/manager.c
@@ -28,7 +28,7 @@
 #include <linux/platform_device.h>
 #include <linux/jiffies.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
@@ -69,7 +69,6 @@ int dss_init_overlay_managers(void)
 			break;
 		}
 
-		mgr->caps = 0;
 		mgr->supported_displays =
 			dss_feat_get_supported_displays(mgr->id);
 		mgr->supported_outputs =
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/output.c b/drivers/video/fbdev/omap2/omapfb/dss/output.c
index 16072159bd24..bed9a978269d 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/output.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/output.c
@@ -21,7 +21,7 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c
index 4cc5ddebfb34..f1f6c0aea752 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c
@@ -26,7 +26,7 @@
 #include <linux/kobject.h>
 #include <linux/platform_device.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/overlay.c b/drivers/video/fbdev/omap2/omapfb/dss/overlay.c
index 2f7cee985cdd..d6c5d75d2ef8 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/overlay.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/overlay.c
@@ -30,7 +30,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/pll.c b/drivers/video/fbdev/omap2/omapfb/dss/pll.c
index f974ddcd3b6e..0564c5606cd0 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/pll.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/pll.c
@@ -22,7 +22,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/sched.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/rfbi.c b/drivers/video/fbdev/omap2/omapfb/dss/rfbi.c
index aea6a1d0fb20..562b0c4ae0c6 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/rfbi.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/rfbi.c
@@ -38,7 +38,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include "dss.h"
 
 struct rfbi_reg { u16 idx; };
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/sdi.c b/drivers/video/fbdev/omap2/omapfb/dss/sdi.c
index d747cc6b59e1..c4be732a4714 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/sdi.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/sdi.c
@@ -29,7 +29,7 @@
 #include <linux/of.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include "dss.h"
 
 static struct {
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/venc.c b/drivers/video/fbdev/omap2/omapfb/dss/venc.c
index 26e0ee30adf8..392464da12e4 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/venc.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/venc.c
@@ -37,7 +37,7 @@
 #include <linux/of.h>
 #include <linux/component.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/video-pll.c b/drivers/video/fbdev/omap2/omapfb/dss/video-pll.c
index b1ec59e42940..a890540f2037 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/video-pll.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/video-pll.c
@@ -17,7 +17,7 @@
 #include <linux/platform_device.h>
 #include <linux/sched.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #include "dss.h"
 #include "dss_features.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
index 9ddfdd63b84c..ef69273074ba 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
@@ -30,7 +30,7 @@
 #include <linux/export.h>
 #include <linux/sizes.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include <video/omapvrfb.h>
 
 #include "omapfb.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
index d3af01c94a58..2fb90cb6803f 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
@@ -30,7 +30,7 @@
 #include <linux/platform_device.h>
 #include <linux/omapfb.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include <video/omapvrfb.h>
 
 #include "omapfb.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c b/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c
index 18fa9e1d0033..8087a009c54f 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c
@@ -29,7 +29,7 @@
 #include <linux/mm.h>
 #include <linux/omapfb.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 #include <video/omapvrfb.h>
 
 #include "omapfb.h"
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb.h b/drivers/video/fbdev/omap2/omapfb/omapfb.h
index 623cd872a367..bcb9ff4a607d 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb.h
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb.h
@@ -31,7 +31,7 @@
 #include <linux/dma-attrs.h>
 #include <linux/dma-mapping.h>
 
-#include <video/omapdss.h>
+#include <video/omapfb_dss.h>
 
 #ifdef DEBUG
 extern bool omapfb_debug;
diff --git a/drivers/video/logo/logo.c b/drivers/video/logo/logo.c
index 10fbfd8ab963..b6bc4a0bda2a 100644
--- a/drivers/video/logo/logo.c
+++ b/drivers/video/logo/logo.c
@@ -36,11 +36,11 @@ static int __init fb_logo_late_init(void)
 
 late_initcall(fb_logo_late_init);
 
-/* logo's are marked __initdata. Use __init_refok to tell
+/* logo's are marked __initdata. Use __ref to tell
  * modpost that it is intended that this function uses data
  * marked __initdata.
  */
-const struct linux_logo * __init_refok fb_find_logo(int depth)
+const struct linux_logo * __ref fb_find_logo(int depth)
 {
 	const struct linux_logo *logo = NULL;
 
diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c
index a2eec97d5064..bb09de633939 100644
--- a/drivers/w1/masters/omap_hdq.c
+++ b/drivers/w1/masters/omap_hdq.c
@@ -390,8 +390,6 @@ static int hdq_read_byte(struct hdq_data *hdq_data, u8 *val)
 		goto out;
 	}
 
-	hdq_data->hdq_irqstatus = 0;
-
 	if (!(hdq_data->hdq_irqstatus & OMAP_HDQ_INT_STATUS_RXCOMPLETE)) {
 		hdq_reg_merge(hdq_data, OMAP_HDQ_CTRL_STATUS,
 			OMAP_HDQ_CTRL_STATUS_DIR | OMAP_HDQ_CTRL_STATUS_GO,
diff --git a/drivers/w1/slaves/w1_ds2406.c b/drivers/w1/slaves/w1_ds2406.c
index d488961a8c90..51f2f66d6555 100644
--- a/drivers/w1/slaves/w1_ds2406.c
+++ b/drivers/w1/slaves/w1_ds2406.c
@@ -153,16 +153,4 @@ static struct w1_family w1_family_12 = {
 	.fid = W1_FAMILY_DS2406,
 	.fops = &w1_f12_fops,
 };
-
-static int __init w1_f12_init(void)
-{
-	return w1_register_family(&w1_family_12);
-}
-
-static void __exit w1_f12_exit(void)
-{
-	w1_unregister_family(&w1_family_12);
-}
-
-module_init(w1_f12_init);
-module_exit(w1_f12_exit);
+module_w1_family(w1_family_12);
diff --git a/drivers/w1/slaves/w1_ds2408.c b/drivers/w1/slaves/w1_ds2408.c
index 7dfa0e11688a..aec5958e66e9 100644
--- a/drivers/w1/slaves/w1_ds2408.c
+++ b/drivers/w1/slaves/w1_ds2408.c
@@ -351,16 +351,4 @@ static struct w1_family w1_family_29 = {
 	.fid = W1_FAMILY_DS2408,
 	.fops = &w1_f29_fops,
 };
-
-static int __init w1_f29_init(void)
-{
-	return w1_register_family(&w1_family_29);
-}
-
-static void __exit w1_f29_exit(void)
-{
-	w1_unregister_family(&w1_family_29);
-}
-
-module_init(w1_f29_init);
-module_exit(w1_f29_exit);
+module_w1_family(w1_family_29);
diff --git a/drivers/w1/slaves/w1_ds2413.c b/drivers/w1/slaves/w1_ds2413.c
index ee28fc1ff390..f2e1c51533b9 100644
--- a/drivers/w1/slaves/w1_ds2413.c
+++ b/drivers/w1/slaves/w1_ds2413.c
@@ -135,16 +135,4 @@ static struct w1_family w1_family_3a = {
 	.fid = W1_FAMILY_DS2413,
 	.fops = &w1_f3a_fops,
 };
-
-static int __init w1_f3a_init(void)
-{
-	return w1_register_family(&w1_family_3a);
-}
-
-static void __exit w1_f3a_exit(void)
-{
-	w1_unregister_family(&w1_family_3a);
-}
-
-module_init(w1_f3a_init);
-module_exit(w1_f3a_exit);
+module_w1_family(w1_family_3a);
diff --git a/drivers/w1/slaves/w1_ds2423.c b/drivers/w1/slaves/w1_ds2423.c
index 7e41b7d91fb5..4ab54fd9dde2 100644
--- a/drivers/w1/slaves/w1_ds2423.c
+++ b/drivers/w1/slaves/w1_ds2423.c
@@ -138,19 +138,7 @@ static struct w1_family w1_family_1d = {
 	.fid = W1_COUNTER_DS2423,
 	.fops = &w1_f1d_fops,
 };
-
-static int __init w1_f1d_init(void)
-{
-	return w1_register_family(&w1_family_1d);
-}
-
-static void __exit w1_f1d_exit(void)
-{
-	w1_unregister_family(&w1_family_1d);
-}
-
-module_init(w1_f1d_init);
-module_exit(w1_f1d_exit);
+module_w1_family(w1_family_1d);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Mika Laitio <lamikr@pilppa.org>");
diff --git a/drivers/w1/slaves/w1_ds2431.c b/drivers/w1/slaves/w1_ds2431.c
index 9c4ff9d28adc..80572cb63ba8 100644
--- a/drivers/w1/slaves/w1_ds2431.c
+++ b/drivers/w1/slaves/w1_ds2431.c
@@ -288,19 +288,7 @@ static struct w1_family w1_family_2d = {
 	.fid = W1_EEPROM_DS2431,
 	.fops = &w1_f2d_fops,
 };
-
-static int __init w1_f2d_init(void)
-{
-	return w1_register_family(&w1_family_2d);
-}
-
-static void __exit w1_f2d_fini(void)
-{
-	w1_unregister_family(&w1_family_2d);
-}
-
-module_init(w1_f2d_init);
-module_exit(w1_f2d_fini);
+module_w1_family(w1_family_2d);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Bernhard Weirich <bernhard.weirich@riedel.net>");
diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c
index 72319a968a9e..6cf378c89ecb 100644
--- a/drivers/w1/slaves/w1_ds2433.c
+++ b/drivers/w1/slaves/w1_ds2433.c
@@ -305,16 +305,4 @@ static struct w1_family w1_family_23 = {
 	.fid = W1_EEPROM_DS2433,
 	.fops = &w1_f23_fops,
 };
-
-static int __init w1_f23_init(void)
-{
-	return w1_register_family(&w1_family_23);
-}
-
-static void __exit w1_f23_fini(void)
-{
-	w1_unregister_family(&w1_family_23);
-}
-
-module_init(w1_f23_init);
-module_exit(w1_f23_fini);
+module_w1_family(w1_family_23);
diff --git a/drivers/w1/slaves/w1_ds2760.c b/drivers/w1/slaves/w1_ds2760.c
index d9079d48d112..ffa37f773b3b 100644
--- a/drivers/w1/slaves/w1_ds2760.c
+++ b/drivers/w1/slaves/w1_ds2760.c
@@ -121,25 +121,14 @@ static const struct attribute_group *w1_ds2760_groups[] = {
 	NULL,
 };
 
-static DEFINE_IDA(bat_ida);
-
 static int w1_ds2760_add_slave(struct w1_slave *sl)
 {
 	int ret;
-	int id;
 	struct platform_device *pdev;
 
-	id = ida_simple_get(&bat_ida, 0, 0, GFP_KERNEL);
-	if (id < 0) {
-		ret = id;
-		goto noid;
-	}
-
-	pdev = platform_device_alloc("ds2760-battery", id);
-	if (!pdev) {
-		ret = -ENOMEM;
-		goto pdev_alloc_failed;
-	}
+	pdev = platform_device_alloc("ds2760-battery", PLATFORM_DEVID_AUTO);
+	if (!pdev)
+		return -ENOMEM;
 	pdev->dev.parent = &sl->dev;
 
 	ret = platform_device_add(pdev);
@@ -148,24 +137,19 @@ static int w1_ds2760_add_slave(struct w1_slave *sl)
 
 	dev_set_drvdata(&sl->dev, pdev);
 
-	goto success;
+	return 0;
 
 pdev_add_failed:
 	platform_device_put(pdev);
-pdev_alloc_failed:
-	ida_simple_remove(&bat_ida, id);
-noid:
-success:
+
 	return ret;
 }
 
 static void w1_ds2760_remove_slave(struct w1_slave *sl)
 {
 	struct platform_device *pdev = dev_get_drvdata(&sl->dev);
-	int id = pdev->id;
 
 	platform_device_unregister(pdev);
-	ida_simple_remove(&bat_ida, id);
 }
 
 static struct w1_family_ops w1_ds2760_fops = {
@@ -178,28 +162,13 @@ static struct w1_family w1_ds2760_family = {
 	.fid = W1_FAMILY_DS2760,
 	.fops = &w1_ds2760_fops,
 };
-
-static int __init w1_ds2760_init(void)
-{
-	pr_info("1-Wire driver for the DS2760 battery monitor chip - (c) 2004-2005, Szabolcs Gyurko\n");
-	ida_init(&bat_ida);
-	return w1_register_family(&w1_ds2760_family);
-}
-
-static void __exit w1_ds2760_exit(void)
-{
-	w1_unregister_family(&w1_ds2760_family);
-	ida_destroy(&bat_ida);
-}
+module_w1_family(w1_ds2760_family);
 
 EXPORT_SYMBOL(w1_ds2760_read);
 EXPORT_SYMBOL(w1_ds2760_write);
 EXPORT_SYMBOL(w1_ds2760_store_eeprom);
 EXPORT_SYMBOL(w1_ds2760_recall_eeprom);
 
-module_init(w1_ds2760_init);
-module_exit(w1_ds2760_exit);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Szabolcs Gyurko <szabolcs.gyurko@tlt.hu>");
 MODULE_DESCRIPTION("1-wire Driver Dallas 2760 battery monitor chip");
diff --git a/drivers/w1/slaves/w1_ds2780.c b/drivers/w1/slaves/w1_ds2780.c
index 50e85f7929d4..f5c2aa429a92 100644
--- a/drivers/w1/slaves/w1_ds2780.c
+++ b/drivers/w1/slaves/w1_ds2780.c
@@ -113,25 +113,14 @@ static const struct attribute_group *w1_ds2780_groups[] = {
 	NULL,
 };
 
-static DEFINE_IDA(bat_ida);
-
 static int w1_ds2780_add_slave(struct w1_slave *sl)
 {
 	int ret;
-	int id;
 	struct platform_device *pdev;
 
-	id = ida_simple_get(&bat_ida, 0, 0, GFP_KERNEL);
-	if (id < 0) {
-		ret = id;
-		goto noid;
-	}
-
-	pdev = platform_device_alloc("ds2780-battery", id);
-	if (!pdev) {
-		ret = -ENOMEM;
-		goto pdev_alloc_failed;
-	}
+	pdev = platform_device_alloc("ds2780-battery", PLATFORM_DEVID_AUTO);
+	if (!pdev)
+		return -ENOMEM;
 	pdev->dev.parent = &sl->dev;
 
 	ret = platform_device_add(pdev);
@@ -144,19 +133,15 @@ static int w1_ds2780_add_slave(struct w1_slave *sl)
 
 pdev_add_failed:
 	platform_device_put(pdev);
-pdev_alloc_failed:
-	ida_simple_remove(&bat_ida, id);
-noid:
+
 	return ret;
 }
 
 static void w1_ds2780_remove_slave(struct w1_slave *sl)
 {
 	struct platform_device *pdev = dev_get_drvdata(&sl->dev);
-	int id = pdev->id;
 
 	platform_device_unregister(pdev);
-	ida_simple_remove(&bat_ida, id);
 }
 
 static struct w1_family_ops w1_ds2780_fops = {
@@ -169,21 +154,7 @@ static struct w1_family w1_ds2780_family = {
 	.fid = W1_FAMILY_DS2780,
 	.fops = &w1_ds2780_fops,
 };
-
-static int __init w1_ds2780_init(void)
-{
-	ida_init(&bat_ida);
-	return w1_register_family(&w1_ds2780_family);
-}
-
-static void __exit w1_ds2780_exit(void)
-{
-	w1_unregister_family(&w1_ds2780_family);
-	ida_destroy(&bat_ida);
-}
-
-module_init(w1_ds2780_init);
-module_exit(w1_ds2780_exit);
+module_w1_family(w1_ds2780_family);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Clifton Barnes <cabarnes@indesign-llc.com>");
diff --git a/drivers/w1/slaves/w1_ds2781.c b/drivers/w1/slaves/w1_ds2781.c
index 1eb98fb1688d..9c03e014cf9e 100644
--- a/drivers/w1/slaves/w1_ds2781.c
+++ b/drivers/w1/slaves/w1_ds2781.c
@@ -17,7 +17,6 @@
 #include <linux/types.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
-#include <linux/idr.h>
 
 #include "../w1.h"
 #include "../w1_int.h"
@@ -111,25 +110,14 @@ static const struct attribute_group *w1_ds2781_groups[] = {
 	NULL,
 };
 
-static DEFINE_IDA(bat_ida);
-
 static int w1_ds2781_add_slave(struct w1_slave *sl)
 {
 	int ret;
-	int id;
 	struct platform_device *pdev;
 
-	id = ida_simple_get(&bat_ida, 0, 0, GFP_KERNEL);
-	if (id < 0) {
-		ret = id;
-		goto noid;
-	}
-
-	pdev = platform_device_alloc("ds2781-battery", id);
-	if (!pdev) {
-		ret = -ENOMEM;
-		goto pdev_alloc_failed;
-	}
+	pdev = platform_device_alloc("ds2781-battery", PLATFORM_DEVID_AUTO);
+	if (!pdev)
+		return -ENOMEM;
 	pdev->dev.parent = &sl->dev;
 
 	ret = platform_device_add(pdev);
@@ -142,19 +130,15 @@ static int w1_ds2781_add_slave(struct w1_slave *sl)
 
 pdev_add_failed:
 	platform_device_put(pdev);
-pdev_alloc_failed:
-	ida_simple_remove(&bat_ida, id);
-noid:
+
 	return ret;
 }
 
 static void w1_ds2781_remove_slave(struct w1_slave *sl)
 {
 	struct platform_device *pdev = dev_get_drvdata(&sl->dev);
-	int id = pdev->id;
 
 	platform_device_unregister(pdev);
-	ida_simple_remove(&bat_ida, id);
 }
 
 static struct w1_family_ops w1_ds2781_fops = {
@@ -167,21 +151,7 @@ static struct w1_family w1_ds2781_family = {
 	.fid = W1_FAMILY_DS2781,
 	.fops = &w1_ds2781_fops,
 };
-
-static int __init w1_ds2781_init(void)
-{
-	ida_init(&bat_ida);
-	return w1_register_family(&w1_ds2781_family);
-}
-
-static void __exit w1_ds2781_exit(void)
-{
-	w1_unregister_family(&w1_ds2781_family);
-	ida_destroy(&bat_ida);
-}
-
-module_init(w1_ds2781_init);
-module_exit(w1_ds2781_exit);
+module_w1_family(w1_ds2781_family);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Renata Sayakhova <renata@oktetlabs.ru>");
diff --git a/drivers/w1/slaves/w1_ds28e04.c b/drivers/w1/slaves/w1_ds28e04.c
index 365d6dff21de..5e348d38ec5c 100644
--- a/drivers/w1/slaves/w1_ds28e04.c
+++ b/drivers/w1/slaves/w1_ds28e04.c
@@ -427,16 +427,4 @@ static struct w1_family w1_family_1C = {
 	.fid = W1_FAMILY_DS28E04,
 	.fops = &w1_f1C_fops,
 };
-
-static int __init w1_f1C_init(void)
-{
-	return w1_register_family(&w1_family_1C);
-}
-
-static void __exit w1_f1C_fini(void)
-{
-	w1_unregister_family(&w1_family_1C);
-}
-
-module_init(w1_f1C_init);
-module_exit(w1_f1C_fini);
+module_w1_family(w1_family_1C);
diff --git a/drivers/w1/w1_family.h b/drivers/w1/w1_family.h
index ed5dcb80a1f7..10a7a0767187 100644
--- a/drivers/w1/w1_family.h
+++ b/drivers/w1/w1_family.h
@@ -88,4 +88,16 @@ struct w1_family * w1_family_registered(u8);
 void w1_unregister_family(struct w1_family *);
 int w1_register_family(struct w1_family *);
 
+/**
+ * module_w1_driver() - Helper macro for registering a 1-Wire families
+ * @__w1_family: w1_family struct
+ *
+ * Helper macro for 1-Wire families which do not do anything special in module
+ * init/exit. This eliminates a lot of boilerplate. Each module may only
+ * use this macro once, and calling it replaces module_init() and module_exit()
+ */
+#define module_w1_family(__w1_family) \
+	module_driver(__w1_family, w1_register_family, \
+			w1_unregister_family)
+
 #endif /* __W1_FAMILY_H */
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index b4b3e256491b..1bffe006ca9a 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -48,7 +48,6 @@ config WATCHDOG_NOWAYOUT
 
 config WATCHDOG_SYSFS
 	bool "Read different watchdog information through sysfs"
-	default n
 	help
 	  Say Y here if you want to enable watchdog device status read through
 	  sysfs attributes.
@@ -516,6 +515,15 @@ config MAX63XX_WATCHDOG
 	help
 	  Support for memory mapped max63{69,70,71,72,73,74} watchdog timer.
 
+config MAX77620_WATCHDOG
+	tristate "Maxim Max77620 Watchdog Timer"
+	depends on MFD_MAX77620
+	help
+	 This is the driver for the Max77620 watchdog timer.
+	 Say 'Y' here to enable the watchdog timer support for
+	 MAX77620 chips. To compile this driver as a module,
+	 choose M here: the module will be called max77620_wdt.
+
 config IMX2_WDT
 	tristate "IMX2+ Watchdog"
 	depends on ARCH_MXC || ARCH_LAYERSCAPE
@@ -609,6 +617,16 @@ config QCOM_WDT
 	  To compile this driver as a module, choose M here: the
 	  module will be called qcom_wdt.
 
+config MESON_GXBB_WATCHDOG
+	tristate "Amlogic Meson GXBB SoCs watchdog support"
+	depends on ARCH_MESON
+	select WATCHDOG_CORE
+	help
+	  Say Y here to include support for the watchdog timer
+	  in Amlogic Meson GXBB SoCs.
+	  To compile this driver as a module, choose M here: the
+	  module will be called meson_gxbb_wdt.
+
 config MESON_WATCHDOG
 	tristate "Amlogic Meson SoCs watchdog support"
 	depends on ARCH_MESON
@@ -669,6 +687,19 @@ config RENESAS_WDT
 	  This driver adds watchdog support for the integrated watchdogs in the
 	  Renesas R-Car and other SH-Mobile SoCs (usually named RWDT or SWDT).
 
+config ASPEED_WATCHDOG
+	tristate "Aspeed 2400 watchdog support"
+	depends on ARCH_ASPEED || COMPILE_TEST
+	select WATCHDOG_CORE
+	help
+	  Say Y here to include support for the watchdog timer
+	  in Apseed BMC SoCs.
+
+	  This driver is required to reboot the SoC.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called aspeed_wdt.
+
 # AVR32 Architecture
 
 config AT32AP700X_WDT
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index a46e7c1380ac..c22ad3ea3539 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -67,6 +67,7 @@ obj-$(CONFIG_ST_LPC_WATCHDOG) += st_lpc_wdt.o
 obj-$(CONFIG_QCOM_WDT) += qcom-wdt.o
 obj-$(CONFIG_BCM_KONA_WDT) += bcm_kona_wdt.o
 obj-$(CONFIG_TEGRA_WATCHDOG) += tegra_wdt.o
+obj-$(CONFIG_MESON_GXBB_WATCHDOG) += meson_gxbb_wdt.o
 obj-$(CONFIG_MESON_WATCHDOG) += meson_wdt.o
 obj-$(CONFIG_MEDIATEK_WATCHDOG) += mtk_wdt.o
 obj-$(CONFIG_DIGICOLOR_WATCHDOG) += digicolor_wdt.o
@@ -74,6 +75,7 @@ obj-$(CONFIG_LPC18XX_WATCHDOG) += lpc18xx_wdt.o
 obj-$(CONFIG_BCM7038_WDT) += bcm7038_wdt.o
 obj-$(CONFIG_ATLAS7_WATCHDOG) += atlas7_wdt.o
 obj-$(CONFIG_RENESAS_WDT) += renesas_wdt.o
+obj-$(CONFIG_ASPEED_WATCHDOG) += aspeed_wdt.o
 
 # AVR32 Architecture
 obj-$(CONFIG_AT32AP700X_WDT) += at32ap700x_wdt.o
@@ -203,6 +205,7 @@ obj-$(CONFIG_TANGOX_WATCHDOG) += tangox_wdt.o
 obj-$(CONFIG_WM831X_WATCHDOG) += wm831x_wdt.o
 obj-$(CONFIG_WM8350_WATCHDOG) += wm8350_wdt.o
 obj-$(CONFIG_MAX63XX_WATCHDOG) += max63xx_wdt.o
+obj-$(CONFIG_MAX77620_WATCHDOG) += max77620_wdt.o
 obj-$(CONFIG_ZIIRAVE_WATCHDOG) += ziirave_wdt.o
 obj-$(CONFIG_SOFT_WATCHDOG) += softdog.o
 obj-$(CONFIG_MENF21BMC_WATCHDOG) += menf21bmc_wdt.o
diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c
new file mode 100644
index 000000000000..f5ad8023c2e6
--- /dev/null
+++ b/drivers/watchdog/aspeed_wdt.c
@@ -0,0 +1,212 @@
+/*
+ * Copyright 2016 IBM Corporation
+ *
+ * Joel Stanley <joel@jms.id.au>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/watchdog.h>
+
+struct aspeed_wdt {
+	struct watchdog_device	wdd;
+	void __iomem		*base;
+	u32			ctrl;
+};
+
+static const struct of_device_id aspeed_wdt_of_table[] = {
+	{ .compatible = "aspeed,ast2400-wdt" },
+	{ .compatible = "aspeed,ast2500-wdt" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, aspeed_wdt_of_table);
+
+#define WDT_STATUS		0x00
+#define WDT_RELOAD_VALUE	0x04
+#define WDT_RESTART		0x08
+#define WDT_CTRL		0x0C
+#define   WDT_CTRL_RESET_MODE_SOC	(0x00 << 5)
+#define   WDT_CTRL_RESET_MODE_FULL_CHIP	(0x01 << 5)
+#define   WDT_CTRL_1MHZ_CLK		BIT(4)
+#define   WDT_CTRL_WDT_EXT		BIT(3)
+#define   WDT_CTRL_WDT_INTR		BIT(2)
+#define   WDT_CTRL_RESET_SYSTEM		BIT(1)
+#define   WDT_CTRL_ENABLE		BIT(0)
+
+#define WDT_RESTART_MAGIC	0x4755
+
+/* 32 bits at 1MHz, in milliseconds */
+#define WDT_MAX_TIMEOUT_MS	4294967
+#define WDT_DEFAULT_TIMEOUT	30
+#define WDT_RATE_1MHZ		1000000
+
+static struct aspeed_wdt *to_aspeed_wdt(struct watchdog_device *wdd)
+{
+	return container_of(wdd, struct aspeed_wdt, wdd);
+}
+
+static void aspeed_wdt_enable(struct aspeed_wdt *wdt, int count)
+{
+	wdt->ctrl |= WDT_CTRL_ENABLE;
+
+	writel(0, wdt->base + WDT_CTRL);
+	writel(count, wdt->base + WDT_RELOAD_VALUE);
+	writel(WDT_RESTART_MAGIC, wdt->base + WDT_RESTART);
+	writel(wdt->ctrl, wdt->base + WDT_CTRL);
+}
+
+static int aspeed_wdt_start(struct watchdog_device *wdd)
+{
+	struct aspeed_wdt *wdt = to_aspeed_wdt(wdd);
+
+	aspeed_wdt_enable(wdt, wdd->timeout * WDT_RATE_1MHZ);
+
+	return 0;
+}
+
+static int aspeed_wdt_stop(struct watchdog_device *wdd)
+{
+	struct aspeed_wdt *wdt = to_aspeed_wdt(wdd);
+
+	wdt->ctrl &= ~WDT_CTRL_ENABLE;
+	writel(wdt->ctrl, wdt->base + WDT_CTRL);
+
+	return 0;
+}
+
+static int aspeed_wdt_ping(struct watchdog_device *wdd)
+{
+	struct aspeed_wdt *wdt = to_aspeed_wdt(wdd);
+
+	writel(WDT_RESTART_MAGIC, wdt->base + WDT_RESTART);
+
+	return 0;
+}
+
+static int aspeed_wdt_set_timeout(struct watchdog_device *wdd,
+				  unsigned int timeout)
+{
+	struct aspeed_wdt *wdt = to_aspeed_wdt(wdd);
+	u32 actual;
+
+	wdd->timeout = timeout;
+
+	actual = min(timeout, wdd->max_hw_heartbeat_ms * 1000);
+
+	writel(actual * WDT_RATE_1MHZ, wdt->base + WDT_RELOAD_VALUE);
+	writel(WDT_RESTART_MAGIC, wdt->base + WDT_RESTART);
+
+	return 0;
+}
+
+static int aspeed_wdt_restart(struct watchdog_device *wdd,
+			      unsigned long action, void *data)
+{
+	struct aspeed_wdt *wdt = to_aspeed_wdt(wdd);
+
+	aspeed_wdt_enable(wdt, 128 * WDT_RATE_1MHZ / 1000);
+
+	mdelay(1000);
+
+	return 0;
+}
+
+static const struct watchdog_ops aspeed_wdt_ops = {
+	.start		= aspeed_wdt_start,
+	.stop		= aspeed_wdt_stop,
+	.ping		= aspeed_wdt_ping,
+	.set_timeout	= aspeed_wdt_set_timeout,
+	.restart	= aspeed_wdt_restart,
+	.owner		= THIS_MODULE,
+};
+
+static const struct watchdog_info aspeed_wdt_info = {
+	.options	= WDIOF_KEEPALIVEPING
+			| WDIOF_MAGICCLOSE
+			| WDIOF_SETTIMEOUT,
+	.identity	= KBUILD_MODNAME,
+};
+
+static int aspeed_wdt_remove(struct platform_device *pdev)
+{
+	struct aspeed_wdt *wdt = platform_get_drvdata(pdev);
+
+	watchdog_unregister_device(&wdt->wdd);
+
+	return 0;
+}
+
+static int aspeed_wdt_probe(struct platform_device *pdev)
+{
+	struct aspeed_wdt *wdt;
+	struct resource *res;
+	int ret;
+
+	wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
+	if (!wdt)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	wdt->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(wdt->base))
+		return PTR_ERR(wdt->base);
+
+	/*
+	 * The ast2400 wdt can run at PCLK, or 1MHz. The ast2500 only
+	 * runs at 1MHz. We chose to always run at 1MHz, as there's no
+	 * good reason to have a faster watchdog counter.
+	 */
+	wdt->wdd.info = &aspeed_wdt_info;
+	wdt->wdd.ops = &aspeed_wdt_ops;
+	wdt->wdd.max_hw_heartbeat_ms = WDT_MAX_TIMEOUT_MS;
+	wdt->wdd.parent = &pdev->dev;
+
+	wdt->wdd.timeout = WDT_DEFAULT_TIMEOUT;
+	watchdog_init_timeout(&wdt->wdd, 0, &pdev->dev);
+
+	/*
+	 * Control reset on a per-device basis to ensure the
+	 * host is not affected by a BMC reboot, so only reset
+	 * the SOC and not the full chip
+	 */
+	wdt->ctrl = WDT_CTRL_RESET_MODE_SOC |
+		WDT_CTRL_1MHZ_CLK |
+		WDT_CTRL_RESET_SYSTEM;
+
+	if (readl(wdt->base + WDT_CTRL) & WDT_CTRL_ENABLE)  {
+		aspeed_wdt_start(&wdt->wdd);
+		set_bit(WDOG_HW_RUNNING, &wdt->wdd.status);
+	}
+
+	ret = watchdog_register_device(&wdt->wdd);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register\n");
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, wdt);
+
+	return 0;
+}
+
+static struct platform_driver aspeed_watchdog_driver = {
+	.probe = aspeed_wdt_probe,
+	.remove = aspeed_wdt_remove,
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.of_match_table = of_match_ptr(aspeed_wdt_of_table),
+	},
+};
+module_platform_driver(aspeed_watchdog_driver);
+
+MODULE_DESCRIPTION("Aspeed Watchdog Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/watchdog/bcm2835_wdt.c b/drivers/watchdog/bcm2835_wdt.c
index 2e6164c4abc0..4dddd8298a22 100644
--- a/drivers/watchdog/bcm2835_wdt.c
+++ b/drivers/watchdog/bcm2835_wdt.c
@@ -82,12 +82,6 @@ static int bcm2835_wdt_stop(struct watchdog_device *wdog)
 	return 0;
 }
 
-static int bcm2835_wdt_set_timeout(struct watchdog_device *wdog, unsigned int t)
-{
-	wdog->timeout = t;
-	return 0;
-}
-
 static unsigned int bcm2835_wdt_get_timeleft(struct watchdog_device *wdog)
 {
 	struct bcm2835_wdt *wdt = watchdog_get_drvdata(wdog);
@@ -96,15 +90,14 @@ static unsigned int bcm2835_wdt_get_timeleft(struct watchdog_device *wdog)
 	return WDOG_TICKS_TO_SECS(ret & PM_WDOG_TIME_SET);
 }
 
-static struct watchdog_ops bcm2835_wdt_ops = {
+static const struct watchdog_ops bcm2835_wdt_ops = {
 	.owner =	THIS_MODULE,
 	.start =	bcm2835_wdt_start,
 	.stop =		bcm2835_wdt_stop,
-	.set_timeout =	bcm2835_wdt_set_timeout,
 	.get_timeleft =	bcm2835_wdt_get_timeleft,
 };
 
-static struct watchdog_info bcm2835_wdt_info = {
+static const struct watchdog_info bcm2835_wdt_info = {
 	.options =	WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE |
 			WDIOF_KEEPALIVEPING,
 	.identity =	"Broadcom BCM2835 Watchdog timer",
diff --git a/drivers/watchdog/da9063_wdt.c b/drivers/watchdog/da9063_wdt.c
index a100f648880d..5d6b4e5f7989 100644
--- a/drivers/watchdog/da9063_wdt.c
+++ b/drivers/watchdog/da9063_wdt.c
@@ -34,6 +34,7 @@ static const unsigned int wdt_timeout[] = { 0, 2, 4, 8, 16, 32, 65, 131 };
 #define DA9063_WDT_MIN_TIMEOUT		wdt_timeout[DA9063_TWDSCALE_MIN]
 #define DA9063_WDT_MAX_TIMEOUT		wdt_timeout[DA9063_TWDSCALE_MAX]
 #define DA9063_WDG_TIMEOUT		wdt_timeout[3]
+#define DA9063_RESET_PROTECTION_MS	256
 
 struct da9063_watchdog {
 	struct da9063 *da9063;
@@ -171,6 +172,7 @@ static int da9063_wdt_probe(struct platform_device *pdev)
 	wdt->wdtdev.ops = &da9063_watchdog_ops;
 	wdt->wdtdev.min_timeout = DA9063_WDT_MIN_TIMEOUT;
 	wdt->wdtdev.max_timeout = DA9063_WDT_MAX_TIMEOUT;
+	wdt->wdtdev.min_hw_heartbeat_ms = DA9063_RESET_PROTECTION_MS;
 	wdt->wdtdev.timeout = DA9063_WDG_TIMEOUT;
 	wdt->wdtdev.parent = &pdev->dev;
 
diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c
index d4ba262da7ba..1b7e9169072f 100644
--- a/drivers/watchdog/f71808e_wdt.c
+++ b/drivers/watchdog/f71808e_wdt.c
@@ -45,9 +45,11 @@
 #define SIO_REG_DEVREV		0x22	/* Device revision */
 #define SIO_REG_MANID		0x23	/* Fintek ID (2 bytes) */
 #define SIO_REG_ROM_ADDR_SEL	0x27	/* ROM address select */
+#define SIO_F81866_REG_PORT_SEL	0x27	/* F81866 Multi-Function Register */
 #define SIO_REG_MFUNCT1		0x29	/* Multi function select 1 */
 #define SIO_REG_MFUNCT2		0x2a	/* Multi function select 2 */
 #define SIO_REG_MFUNCT3		0x2b	/* Multi function select 3 */
+#define SIO_F81866_REG_GPIO1	0x2c	/* F81866 GPIO1 Enable Register */
 #define SIO_REG_ENABLE		0x30	/* Logical device enable */
 #define SIO_REG_ADDR		0x60	/* Logical device address (2 bytes) */
 
@@ -60,6 +62,7 @@
 #define SIO_F71882_ID		0x0541	/* Chipset ID */
 #define SIO_F71889_ID		0x0723	/* Chipset ID */
 #define SIO_F81865_ID		0x0704	/* Chipset ID */
+#define SIO_F81866_ID		0x1010	/* Chipset ID */
 
 #define F71808FG_REG_WDO_CONF		0xf0
 #define F71808FG_REG_WDT_CONF		0xf5
@@ -116,7 +119,8 @@ module_param(start_withtimeout, uint, 0);
 MODULE_PARM_DESC(start_withtimeout, "Start watchdog timer on module load with"
 	" given initial timeout. Zero (default) disables this feature.");
 
-enum chips { f71808fg, f71858fg, f71862fg, f71869, f71882fg, f71889fg, f81865 };
+enum chips { f71808fg, f71858fg, f71862fg, f71869, f71882fg, f71889fg, f81865,
+	     f81866};
 
 static const char *f71808e_names[] = {
 	"f71808fg",
@@ -126,6 +130,7 @@ static const char *f71808e_names[] = {
 	"f71882fg",
 	"f71889fg",
 	"f81865",
+	"f81866",
 };
 
 /* Super-I/O Function prototypes */
@@ -370,6 +375,22 @@ static int watchdog_start(void)
 		superio_clear_bit(watchdog.sioaddr, SIO_REG_MFUNCT3, 5);
 		break;
 
+	case f81866:
+		/* Set pin 70 to WDTRST# */
+		superio_clear_bit(watchdog.sioaddr, SIO_F81866_REG_PORT_SEL,
+				  BIT(3) | BIT(0));
+		superio_set_bit(watchdog.sioaddr, SIO_F81866_REG_PORT_SEL,
+				BIT(2));
+		/*
+		 * GPIO1 Control Register when 27h BIT3:2 = 01 & BIT0 = 0.
+		 * The PIN 70(GPIO15/WDTRST) is controlled by 2Ch:
+		 *     BIT5: 0 -> WDTRST#
+		 *           1 -> GPIO15
+		 */
+		superio_clear_bit(watchdog.sioaddr, SIO_F81866_REG_GPIO1,
+				  BIT(5));
+		break;
+
 	default:
 		/*
 		 * 'default' label to shut up the compiler and catch
@@ -382,7 +403,7 @@ static int watchdog_start(void)
 	superio_select(watchdog.sioaddr, SIO_F71808FG_LD_WDT);
 	superio_set_bit(watchdog.sioaddr, SIO_REG_ENABLE, 0);
 
-	if (watchdog.type == f81865)
+	if (watchdog.type == f81865 || watchdog.type == f81866)
 		superio_set_bit(watchdog.sioaddr, F81865_REG_WDO_CONF,
 				F81865_FLAG_WDOUT_EN);
 	else
@@ -788,6 +809,9 @@ static int __init f71808e_find(int sioaddr)
 	case SIO_F81865_ID:
 		watchdog.type = f81865;
 		break;
+	case SIO_F81866_ID:
+		watchdog.type = f81866;
+		break;
 	default:
 		pr_info("Unrecognized Fintek device: %04x\n",
 			(unsigned int)devid);
diff --git a/drivers/watchdog/gpio_wdt.c b/drivers/watchdog/gpio_wdt.c
index ba066e4a707b..93457cabc178 100644
--- a/drivers/watchdog/gpio_wdt.c
+++ b/drivers/watchdog/gpio_wdt.c
@@ -151,6 +151,8 @@ static int gpio_wdt_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, priv);
+
 	priv->gpio = of_get_gpio_flags(pdev->dev.of_node, 0, &flags);
 	if (!gpio_is_valid(priv->gpio))
 		return priv->gpio;
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index 0acc6c5f729d..54cab189a763 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -150,6 +150,7 @@ static inline u32 no_reboot_bit(void)
 	u32 enable_bit;
 
 	switch (iTCO_wdt_private.iTCO_version) {
+	case 5:
 	case 3:
 		enable_bit = 0x00000010;
 		break;
@@ -512,6 +513,7 @@ static int iTCO_wdt_probe(struct platform_device *dev)
 
 	/* Clear out the (probably old) status */
 	switch (iTCO_wdt_private.iTCO_version) {
+	case 5:
 	case 4:
 		outw(0x0008, TCO1_STS);	/* Clear the Time Out Status bit */
 		outw(0x0002, TCO2_STS);	/* Clear SECOND_TO_STS bit */
diff --git a/drivers/watchdog/max77620_wdt.c b/drivers/watchdog/max77620_wdt.c
new file mode 100644
index 000000000000..48b84df2afda
--- /dev/null
+++ b/drivers/watchdog/max77620_wdt.c
@@ -0,0 +1,227 @@
+/*
+ * Maxim MAX77620 Watchdog Driver
+ *
+ * Copyright (C) 2016 NVIDIA CORPORATION. All rights reserved.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mfd/max77620.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/watchdog.h>
+
+static bool nowayout = WATCHDOG_NOWAYOUT;
+
+struct max77620_wdt {
+	struct device			*dev;
+	struct regmap			*rmap;
+	struct watchdog_device		wdt_dev;
+};
+
+static int max77620_wdt_start(struct watchdog_device *wdt_dev)
+{
+	struct max77620_wdt *wdt = watchdog_get_drvdata(wdt_dev);
+
+	return regmap_update_bits(wdt->rmap, MAX77620_REG_CNFGGLBL2,
+				  MAX77620_WDTEN, MAX77620_WDTEN);
+}
+
+static int max77620_wdt_stop(struct watchdog_device *wdt_dev)
+{
+	struct max77620_wdt *wdt = watchdog_get_drvdata(wdt_dev);
+
+	return regmap_update_bits(wdt->rmap, MAX77620_REG_CNFGGLBL2,
+				  MAX77620_WDTEN, 0);
+}
+
+static int max77620_wdt_ping(struct watchdog_device *wdt_dev)
+{
+	struct max77620_wdt *wdt = watchdog_get_drvdata(wdt_dev);
+
+	return regmap_update_bits(wdt->rmap, MAX77620_REG_CNFGGLBL3,
+				  MAX77620_WDTC_MASK, 0x1);
+}
+
+static int max77620_wdt_set_timeout(struct watchdog_device *wdt_dev,
+				    unsigned int timeout)
+{
+	struct max77620_wdt *wdt = watchdog_get_drvdata(wdt_dev);
+	unsigned int wdt_timeout;
+	u8 regval;
+	int ret;
+
+	switch (timeout) {
+	case 0 ... 2:
+		regval = MAX77620_TWD_2s;
+		wdt_timeout = 2;
+		break;
+
+	case 3 ... 16:
+		regval = MAX77620_TWD_16s;
+		wdt_timeout = 16;
+		break;
+
+	case 17 ... 64:
+		regval = MAX77620_TWD_64s;
+		wdt_timeout = 64;
+		break;
+
+	default:
+		regval = MAX77620_TWD_128s;
+		wdt_timeout = 128;
+		break;
+	}
+
+	ret = regmap_update_bits(wdt->rmap, MAX77620_REG_CNFGGLBL3,
+				 MAX77620_WDTC_MASK, 0x1);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_update_bits(wdt->rmap, MAX77620_REG_CNFGGLBL2,
+				 MAX77620_TWD_MASK, regval);
+	if (ret < 0)
+		return ret;
+
+	wdt_dev->timeout = wdt_timeout;
+
+	return 0;
+}
+
+static const struct watchdog_info max77620_wdt_info = {
+	.identity = "max77620-watchdog",
+	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
+};
+
+static const struct watchdog_ops max77620_wdt_ops = {
+	.start		= max77620_wdt_start,
+	.stop		= max77620_wdt_stop,
+	.ping		= max77620_wdt_ping,
+	.set_timeout	= max77620_wdt_set_timeout,
+};
+
+static int max77620_wdt_probe(struct platform_device *pdev)
+{
+	struct max77620_wdt *wdt;
+	struct watchdog_device *wdt_dev;
+	unsigned int regval;
+	int ret;
+
+	wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
+	if (!wdt)
+		return -ENOMEM;
+
+	wdt->dev = &pdev->dev;
+	wdt->rmap = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!wdt->rmap) {
+		dev_err(wdt->dev, "Failed to get parent regmap\n");
+		return -ENODEV;
+	}
+
+	wdt_dev = &wdt->wdt_dev;
+	wdt_dev->info = &max77620_wdt_info;
+	wdt_dev->ops = &max77620_wdt_ops;
+	wdt_dev->min_timeout = 2;
+	wdt_dev->max_timeout = 128;
+	wdt_dev->max_hw_heartbeat_ms = 128 * 1000;
+
+	platform_set_drvdata(pdev, wdt);
+
+	/* Enable WD_RST_WK - WDT expire results in a restart */
+	ret = regmap_update_bits(wdt->rmap, MAX77620_REG_ONOFFCNFG2,
+				 MAX77620_ONOFFCNFG2_WD_RST_WK,
+				 MAX77620_ONOFFCNFG2_WD_RST_WK);
+	if (ret < 0) {
+		dev_err(wdt->dev, "Failed to set WD_RST_WK: %d\n", ret);
+		return ret;
+	}
+
+	/* Set WDT clear in OFF and sleep mode */
+	ret = regmap_update_bits(wdt->rmap, MAX77620_REG_CNFGGLBL2,
+				 MAX77620_WDTOFFC | MAX77620_WDTSLPC,
+				 MAX77620_WDTOFFC | MAX77620_WDTSLPC);
+	if (ret < 0) {
+		dev_err(wdt->dev, "Failed to set WDT OFF mode: %d\n", ret);
+		return ret;
+	}
+
+	/* Check if WDT running and if yes then set flags properly */
+	ret = regmap_read(wdt->rmap, MAX77620_REG_CNFGGLBL2, &regval);
+	if (ret < 0) {
+		dev_err(wdt->dev, "Failed to read WDT CFG register: %d\n", ret);
+		return ret;
+	}
+
+	switch (regval & MAX77620_TWD_MASK) {
+	case MAX77620_TWD_2s:
+		wdt_dev->timeout = 2;
+		break;
+	case MAX77620_TWD_16s:
+		wdt_dev->timeout = 16;
+		break;
+	case MAX77620_TWD_64s:
+		wdt_dev->timeout = 64;
+		break;
+	default:
+		wdt_dev->timeout = 128;
+		break;
+	}
+
+	if (regval & MAX77620_WDTEN)
+		set_bit(WDOG_HW_RUNNING, &wdt_dev->status);
+
+	watchdog_set_nowayout(wdt_dev, nowayout);
+	watchdog_set_drvdata(wdt_dev, wdt);
+
+	ret = watchdog_register_device(wdt_dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "watchdog registration failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int max77620_wdt_remove(struct platform_device *pdev)
+{
+	struct max77620_wdt *wdt = platform_get_drvdata(pdev);
+
+	max77620_wdt_stop(&wdt->wdt_dev);
+	watchdog_unregister_device(&wdt->wdt_dev);
+
+	return 0;
+}
+
+static struct platform_device_id max77620_wdt_devtype[] = {
+	{ .name = "max77620-watchdog", },
+	{ },
+};
+
+static struct platform_driver max77620_wdt_driver = {
+	.driver	= {
+		.name	= "max77620-watchdog",
+	},
+	.probe	= max77620_wdt_probe,
+	.remove	= max77620_wdt_remove,
+	.id_table = max77620_wdt_devtype,
+};
+
+module_platform_driver(max77620_wdt_driver);
+
+MODULE_DESCRIPTION("Max77620 watchdog timer driver");
+
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started "
+	"(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
+
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/watchdog/meson_gxbb_wdt.c b/drivers/watchdog/meson_gxbb_wdt.c
new file mode 100644
index 000000000000..44d180a2c5e5
--- /dev/null
+++ b/drivers/watchdog/meson_gxbb_wdt.c
@@ -0,0 +1,270 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * BSD LICENSE
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/watchdog.h>
+
+#define DEFAULT_TIMEOUT	30	/* seconds */
+
+#define GXBB_WDT_CTRL_REG			0x0
+#define GXBB_WDT_TCNT_REG			0x8
+#define GXBB_WDT_RSET_REG			0xc
+
+#define GXBB_WDT_CTRL_CLKDIV_EN			BIT(25)
+#define GXBB_WDT_CTRL_CLK_EN			BIT(24)
+#define GXBB_WDT_CTRL_EE_RESET			BIT(21)
+#define GXBB_WDT_CTRL_EN			BIT(18)
+#define GXBB_WDT_CTRL_DIV_MASK			(BIT(18) - 1)
+
+#define GXBB_WDT_TCNT_SETUP_MASK		(BIT(16) - 1)
+#define GXBB_WDT_TCNT_CNT_SHIFT			16
+
+struct meson_gxbb_wdt {
+	void __iomem *reg_base;
+	struct watchdog_device wdt_dev;
+	struct clk *clk;
+};
+
+static int meson_gxbb_wdt_start(struct watchdog_device *wdt_dev)
+{
+	struct meson_gxbb_wdt *data = watchdog_get_drvdata(wdt_dev);
+
+	writel(readl(data->reg_base + GXBB_WDT_CTRL_REG) | GXBB_WDT_CTRL_EN,
+	       data->reg_base + GXBB_WDT_CTRL_REG);
+
+	return 0;
+}
+
+static int meson_gxbb_wdt_stop(struct watchdog_device *wdt_dev)
+{
+	struct meson_gxbb_wdt *data = watchdog_get_drvdata(wdt_dev);
+
+	writel(readl(data->reg_base + GXBB_WDT_CTRL_REG) & ~GXBB_WDT_CTRL_EN,
+	       data->reg_base + GXBB_WDT_CTRL_REG);
+
+	return 0;
+}
+
+static int meson_gxbb_wdt_ping(struct watchdog_device *wdt_dev)
+{
+	struct meson_gxbb_wdt *data = watchdog_get_drvdata(wdt_dev);
+
+	writel(0, data->reg_base + GXBB_WDT_RSET_REG);
+
+	return 0;
+}
+
+static int meson_gxbb_wdt_set_timeout(struct watchdog_device *wdt_dev,
+				      unsigned int timeout)
+{
+	struct meson_gxbb_wdt *data = watchdog_get_drvdata(wdt_dev);
+	unsigned long tcnt = timeout * 1000;
+
+	if (tcnt > GXBB_WDT_TCNT_SETUP_MASK)
+		tcnt = GXBB_WDT_TCNT_SETUP_MASK;
+
+	wdt_dev->timeout = timeout;
+
+	meson_gxbb_wdt_ping(wdt_dev);
+
+	writel(tcnt, data->reg_base + GXBB_WDT_TCNT_REG);
+
+	return 0;
+}
+
+static unsigned int meson_gxbb_wdt_get_timeleft(struct watchdog_device *wdt_dev)
+{
+	struct meson_gxbb_wdt *data = watchdog_get_drvdata(wdt_dev);
+	unsigned long reg;
+
+	reg = readl(data->reg_base + GXBB_WDT_TCNT_REG);
+
+	return ((reg >> GXBB_WDT_TCNT_CNT_SHIFT) -
+		(reg & GXBB_WDT_TCNT_SETUP_MASK)) / 1000;
+}
+
+static const struct watchdog_ops meson_gxbb_wdt_ops = {
+	.start = meson_gxbb_wdt_start,
+	.stop = meson_gxbb_wdt_stop,
+	.ping = meson_gxbb_wdt_ping,
+	.set_timeout = meson_gxbb_wdt_set_timeout,
+	.get_timeleft = meson_gxbb_wdt_get_timeleft,
+};
+
+static const struct watchdog_info meson_gxbb_wdt_info = {
+	.identity = "Meson GXBB Watchdog",
+	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
+};
+
+static int __maybe_unused meson_gxbb_wdt_resume(struct device *dev)
+{
+	struct meson_gxbb_wdt *data = dev_get_drvdata(dev);
+
+	if (watchdog_active(&data->wdt_dev))
+		meson_gxbb_wdt_start(&data->wdt_dev);
+
+	return 0;
+}
+
+static int __maybe_unused meson_gxbb_wdt_suspend(struct device *dev)
+{
+	struct meson_gxbb_wdt *data = dev_get_drvdata(dev);
+
+	if (watchdog_active(&data->wdt_dev))
+		meson_gxbb_wdt_stop(&data->wdt_dev);
+
+	return 0;
+}
+
+static const struct dev_pm_ops meson_gxbb_wdt_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(meson_gxbb_wdt_suspend, meson_gxbb_wdt_resume)
+};
+
+static const struct of_device_id meson_gxbb_wdt_dt_ids[] = {
+	 { .compatible = "amlogic,meson-gxbb-wdt", },
+	 { /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, meson_gxbb_wdt_dt_ids);
+
+static int meson_gxbb_wdt_probe(struct platform_device *pdev)
+{
+	struct meson_gxbb_wdt *data;
+	struct resource *res;
+	int ret;
+
+	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->reg_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(data->reg_base))
+		return PTR_ERR(data->reg_base);
+
+	data->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(data->clk))
+		return PTR_ERR(data->clk);
+
+	clk_prepare_enable(data->clk);
+
+	platform_set_drvdata(pdev, data);
+
+	data->wdt_dev.parent = &pdev->dev;
+	data->wdt_dev.info = &meson_gxbb_wdt_info;
+	data->wdt_dev.ops = &meson_gxbb_wdt_ops;
+	data->wdt_dev.max_hw_heartbeat_ms = GXBB_WDT_TCNT_SETUP_MASK;
+	data->wdt_dev.min_timeout = 1;
+	data->wdt_dev.timeout = DEFAULT_TIMEOUT;
+	watchdog_set_drvdata(&data->wdt_dev, data);
+
+	/* Setup with 1ms timebase */
+	writel(((clk_get_rate(data->clk) / 1000) & GXBB_WDT_CTRL_DIV_MASK) |
+		GXBB_WDT_CTRL_EE_RESET |
+		GXBB_WDT_CTRL_CLK_EN |
+		GXBB_WDT_CTRL_CLKDIV_EN,
+		data->reg_base + GXBB_WDT_CTRL_REG);
+
+	meson_gxbb_wdt_set_timeout(&data->wdt_dev, data->wdt_dev.timeout);
+
+	ret = watchdog_register_device(&data->wdt_dev);
+	if (ret) {
+		clk_disable_unprepare(data->clk);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int meson_gxbb_wdt_remove(struct platform_device *pdev)
+{
+	struct meson_gxbb_wdt *data = platform_get_drvdata(pdev);
+
+	watchdog_unregister_device(&data->wdt_dev);
+
+	clk_disable_unprepare(data->clk);
+
+	return 0;
+}
+
+static void meson_gxbb_wdt_shutdown(struct platform_device *pdev)
+{
+	struct meson_gxbb_wdt *data = platform_get_drvdata(pdev);
+
+	meson_gxbb_wdt_stop(&data->wdt_dev);
+}
+
+static struct platform_driver meson_gxbb_wdt_driver = {
+	.probe	= meson_gxbb_wdt_probe,
+	.remove	= meson_gxbb_wdt_remove,
+	.shutdown = meson_gxbb_wdt_shutdown,
+	.driver = {
+		.name = "meson-gxbb-wdt",
+		.pm = &meson_gxbb_wdt_pm_ops,
+		.of_match_table	= meson_gxbb_wdt_dt_ids,
+	},
+};
+
+module_platform_driver(meson_gxbb_wdt_driver);
+
+MODULE_ALIAS("platform:meson-gxbb-wdt");
+MODULE_AUTHOR("Neil Armstrong <narmstrong@baylibre.com>");
+MODULE_DESCRIPTION("Amlogic Meson GXBB Watchdog timer driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/watchdog/nv_tco.c b/drivers/watchdog/nv_tco.c
index bd917bb757b8..a0fabf6f92b0 100644
--- a/drivers/watchdog/nv_tco.c
+++ b/drivers/watchdog/nv_tco.c
@@ -294,6 +294,8 @@ static const struct pci_device_id tco_pci_tbl[] = {
 	  PCI_ANY_ID, PCI_ANY_ID, },
 	{ PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP55_SMBUS,
 	  PCI_ANY_ID, PCI_ANY_ID, },
+	{ PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP78S_SMBUS,
+	  PCI_ANY_ID, PCI_ANY_ID, },
 	{ PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP79_SMBUS,
 	  PCI_ANY_ID, PCI_ANY_ID, },
 	{ 0, },			/* End of list */
diff --git a/drivers/watchdog/pcwd.c b/drivers/watchdog/pcwd.c
index e936f15dc7c7..3ad5206d7935 100644
--- a/drivers/watchdog/pcwd.c
+++ b/drivers/watchdog/pcwd.c
@@ -992,19 +992,7 @@ static struct isa_driver pcwd_isa_driver = {
 	},
 };
 
-static int __init pcwd_init_module(void)
-{
-	return isa_register_driver(&pcwd_isa_driver, PCWD_ISA_NR_CARDS);
-}
-
-static void __exit pcwd_cleanup_module(void)
-{
-	isa_unregister_driver(&pcwd_isa_driver);
-	pr_info("Watchdog Module Unloaded\n");
-}
-
-module_init(pcwd_init_module);
-module_exit(pcwd_cleanup_module);
+module_isa_driver(pcwd_isa_driver, PCWD_ISA_NR_CARDS);
 
 MODULE_AUTHOR("Ken Hollis <kenji@bitgate.com>, "
 		"Wim Van Sebroeck <wim@iguana.be>");
diff --git a/drivers/watchdog/pic32-dmt.c b/drivers/watchdog/pic32-dmt.c
index 962f58c03353..c797305f8338 100644
--- a/drivers/watchdog/pic32-dmt.c
+++ b/drivers/watchdog/pic32-dmt.c
@@ -176,8 +176,8 @@ static int pic32_dmt_probe(struct platform_device *pdev)
 	struct watchdog_device *wdd = &pic32_dmt_wdd;
 
 	dmt = devm_kzalloc(&pdev->dev, sizeof(*dmt), GFP_KERNEL);
-	if (IS_ERR(dmt))
-		return PTR_ERR(dmt);
+	if (!dmt)
+		return -ENOMEM;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	dmt->regs = devm_ioremap_resource(&pdev->dev, mem);
@@ -245,7 +245,6 @@ static struct platform_driver pic32_dmt_driver = {
 	.remove		= pic32_dmt_remove,
 	.driver		= {
 		.name		= "pic32-dmt",
-		.owner		= THIS_MODULE,
 		.of_match_table = of_match_ptr(pic32_dmt_of_ids),
 	}
 };
diff --git a/drivers/watchdog/pic32-wdt.c b/drivers/watchdog/pic32-wdt.c
index 6047aa89a4d3..e2761068dc6f 100644
--- a/drivers/watchdog/pic32-wdt.c
+++ b/drivers/watchdog/pic32-wdt.c
@@ -174,8 +174,8 @@ static int pic32_wdt_drv_probe(struct platform_device *pdev)
 	struct resource *mem;
 
 	wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
-	if (IS_ERR(wdt))
-		return PTR_ERR(wdt);
+	if (!wdt)
+		return -ENOMEM;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	wdt->regs = devm_ioremap_resource(&pdev->dev, mem);
@@ -183,8 +183,8 @@ static int pic32_wdt_drv_probe(struct platform_device *pdev)
 		return PTR_ERR(wdt->regs);
 
 	wdt->rst_base = devm_ioremap(&pdev->dev, PIC32_BASE_RESET, 0x10);
-	if (IS_ERR(wdt->rst_base))
-		return PTR_ERR(wdt->rst_base);
+	if (!wdt->rst_base)
+		return -ENOMEM;
 
 	wdt->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(wdt->clk)) {
@@ -251,7 +251,6 @@ static struct platform_driver pic32_wdt_driver = {
 	.remove		= pic32_wdt_drv_remove,
 	.driver		= {
 		.name		= "pic32-wdt",
-		.owner		= THIS_MODULE,
 		.of_match_table = of_match_ptr(pic32_wdt_dt_ids),
 	}
 };
diff --git a/drivers/watchdog/qcom-wdt.c b/drivers/watchdog/qcom-wdt.c
index a043fa4f60e5..5796b5d1b3f2 100644
--- a/drivers/watchdog/qcom-wdt.c
+++ b/drivers/watchdog/qcom-wdt.c
@@ -18,19 +18,45 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/watchdog.h>
+#include <linux/of_device.h>
+
+enum wdt_reg {
+	WDT_RST,
+	WDT_EN,
+	WDT_STS,
+	WDT_BARK_TIME,
+	WDT_BITE_TIME,
+};
 
-#define WDT_RST		0x38
-#define WDT_EN		0x40
-#define WDT_STS		0x44
-#define WDT_BITE_TIME	0x5C
+static const u32 reg_offset_data_apcs_tmr[] = {
+	[WDT_RST] = 0x38,
+	[WDT_EN] = 0x40,
+	[WDT_STS] = 0x44,
+	[WDT_BARK_TIME] = 0x4C,
+	[WDT_BITE_TIME] = 0x5C,
+};
+
+static const u32 reg_offset_data_kpss[] = {
+	[WDT_RST] = 0x4,
+	[WDT_EN] = 0x8,
+	[WDT_STS] = 0xC,
+	[WDT_BARK_TIME] = 0x10,
+	[WDT_BITE_TIME] = 0x14,
+};
 
 struct qcom_wdt {
 	struct watchdog_device	wdd;
 	struct clk		*clk;
 	unsigned long		rate;
 	void __iomem		*base;
+	const u32		*layout;
 };
 
+static void __iomem *wdt_addr(struct qcom_wdt *wdt, enum wdt_reg reg)
+{
+	return wdt->base + wdt->layout[reg];
+}
+
 static inline
 struct qcom_wdt *to_qcom_wdt(struct watchdog_device *wdd)
 {
@@ -41,10 +67,11 @@ static int qcom_wdt_start(struct watchdog_device *wdd)
 {
 	struct qcom_wdt *wdt = to_qcom_wdt(wdd);
 
-	writel(0, wdt->base + WDT_EN);
-	writel(1, wdt->base + WDT_RST);
-	writel(wdd->timeout * wdt->rate, wdt->base + WDT_BITE_TIME);
-	writel(1, wdt->base + WDT_EN);
+	writel(0, wdt_addr(wdt, WDT_EN));
+	writel(1, wdt_addr(wdt, WDT_RST));
+	writel(wdd->timeout * wdt->rate, wdt_addr(wdt, WDT_BARK_TIME));
+	writel(wdd->timeout * wdt->rate, wdt_addr(wdt, WDT_BITE_TIME));
+	writel(1, wdt_addr(wdt, WDT_EN));
 	return 0;
 }
 
@@ -52,7 +79,7 @@ static int qcom_wdt_stop(struct watchdog_device *wdd)
 {
 	struct qcom_wdt *wdt = to_qcom_wdt(wdd);
 
-	writel(0, wdt->base + WDT_EN);
+	writel(0, wdt_addr(wdt, WDT_EN));
 	return 0;
 }
 
@@ -60,7 +87,7 @@ static int qcom_wdt_ping(struct watchdog_device *wdd)
 {
 	struct qcom_wdt *wdt = to_qcom_wdt(wdd);
 
-	writel(1, wdt->base + WDT_RST);
+	writel(1, wdt_addr(wdt, WDT_RST));
 	return 0;
 }
 
@@ -83,10 +110,11 @@ static int qcom_wdt_restart(struct watchdog_device *wdd, unsigned long action,
 	 */
 	timeout = 128 * wdt->rate / 1000;
 
-	writel(0, wdt->base + WDT_EN);
-	writel(1, wdt->base + WDT_RST);
-	writel(timeout, wdt->base + WDT_BITE_TIME);
-	writel(1, wdt->base + WDT_EN);
+	writel(0, wdt_addr(wdt, WDT_EN));
+	writel(1, wdt_addr(wdt, WDT_RST));
+	writel(timeout, wdt_addr(wdt, WDT_BARK_TIME));
+	writel(timeout, wdt_addr(wdt, WDT_BITE_TIME));
+	writel(1, wdt_addr(wdt, WDT_EN));
 
 	/*
 	 * Actually make sure the above sequence hits hardware before sleeping.
@@ -119,9 +147,16 @@ static int qcom_wdt_probe(struct platform_device *pdev)
 	struct qcom_wdt *wdt;
 	struct resource *res;
 	struct device_node *np = pdev->dev.of_node;
+	const u32 *regs;
 	u32 percpu_offset;
 	int ret;
 
+	regs = of_device_get_match_data(&pdev->dev);
+	if (!regs) {
+		dev_err(&pdev->dev, "Unsupported QCOM WDT module\n");
+		return -ENODEV;
+	}
+
 	wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
 	if (!wdt)
 		return -ENOMEM;
@@ -172,6 +207,7 @@ static int qcom_wdt_probe(struct platform_device *pdev)
 	wdt->wdd.min_timeout = 1;
 	wdt->wdd.max_timeout = 0x10000000U / wdt->rate;
 	wdt->wdd.parent = &pdev->dev;
+	wdt->layout = regs;
 
 	if (readl(wdt->base + WDT_STS) & 1)
 		wdt->wdd.bootstatus = WDIOF_CARDRESET;
@@ -208,8 +244,9 @@ static int qcom_wdt_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id qcom_wdt_of_table[] = {
-	{ .compatible = "qcom,kpss-timer" },
-	{ .compatible = "qcom,scss-timer" },
+	{ .compatible = "qcom,kpss-timer", .data = reg_offset_data_apcs_tmr },
+	{ .compatible = "qcom,scss-timer", .data = reg_offset_data_apcs_tmr },
+	{ .compatible = "qcom,kpss-wdt", .data = reg_offset_data_kpss },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, qcom_wdt_of_table);
diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c
index ad383f6f15fc..ce0c38bd0f00 100644
--- a/drivers/watchdog/sbsa_gwdt.c
+++ b/drivers/watchdog/sbsa_gwdt.c
@@ -180,15 +180,6 @@ static int sbsa_gwdt_keepalive(struct watchdog_device *wdd)
 	return 0;
 }
 
-static unsigned int sbsa_gwdt_status(struct watchdog_device *wdd)
-{
-	struct sbsa_gwdt *gwdt = watchdog_get_drvdata(wdd);
-	u32 status = readl(gwdt->control_base + SBSA_GWDT_WCS);
-
-	/* is the watchdog timer running? */
-	return (status & SBSA_GWDT_WCS_EN) << WDOG_ACTIVE;
-}
-
 static int sbsa_gwdt_start(struct watchdog_device *wdd)
 {
 	struct sbsa_gwdt *gwdt = watchdog_get_drvdata(wdd);
@@ -228,7 +219,6 @@ static struct watchdog_ops sbsa_gwdt_ops = {
 	.owner		= THIS_MODULE,
 	.start		= sbsa_gwdt_start,
 	.stop		= sbsa_gwdt_stop,
-	.status		= sbsa_gwdt_status,
 	.ping		= sbsa_gwdt_keepalive,
 	.set_timeout	= sbsa_gwdt_set_timeout,
 	.get_timeleft	= sbsa_gwdt_get_timeleft,
@@ -273,7 +263,7 @@ static int sbsa_gwdt_probe(struct platform_device *pdev)
 	wdd->info = &sbsa_gwdt_info;
 	wdd->ops = &sbsa_gwdt_ops;
 	wdd->min_timeout = 1;
-	wdd->max_timeout = U32_MAX / gwdt->clk;
+	wdd->max_hw_heartbeat_ms = U32_MAX / gwdt->clk * 1000;
 	wdd->timeout = DEFAULT_TIMEOUT;
 	watchdog_set_drvdata(wdd, gwdt);
 	watchdog_set_nowayout(wdd, nowayout);
@@ -283,6 +273,8 @@ static int sbsa_gwdt_probe(struct platform_device *pdev)
 		dev_warn(dev, "System reset by WDT.\n");
 		wdd->bootstatus |= WDIOF_CARDRESET;
 	}
+	if (status & SBSA_GWDT_WCS_EN)
+		set_bit(WDOG_HW_RUNNING, &wdd->status);
 
 	if (action) {
 		irq = platform_get_irq(pdev, 0);
@@ -310,7 +302,7 @@ static int sbsa_gwdt_probe(struct platform_device *pdev)
 	 * the timeout is (WOR * 2), so the maximum timeout should be doubled.
 	 */
 	if (!action)
-		wdd->max_timeout *= 2;
+		wdd->max_hw_heartbeat_ms *= 2;
 
 	watchdog_init_timeout(wdd, timeout, dev);
 	/*
diff --git a/drivers/watchdog/sirfsoc_wdt.c b/drivers/watchdog/sirfsoc_wdt.c
index d0578ab2e636..3050a0031479 100644
--- a/drivers/watchdog/sirfsoc_wdt.c
+++ b/drivers/watchdog/sirfsoc_wdt.c
@@ -39,13 +39,18 @@ MODULE_PARM_DESC(timeout, "Default watchdog timeout (in seconds)");
 MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
 			__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
+static void __iomem *sirfsoc_wdt_base(struct watchdog_device *wdd)
+{
+	return (void __iomem __force *)watchdog_get_drvdata(wdd);
+}
+
 static unsigned int sirfsoc_wdt_gettimeleft(struct watchdog_device *wdd)
 {
 	u32 counter, match;
 	void __iomem *wdt_base;
 	int time_left;
 
-	wdt_base = watchdog_get_drvdata(wdd);
+	wdt_base = sirfsoc_wdt_base(wdd);
 	counter = readl(wdt_base + SIRFSOC_TIMER_COUNTER_LO);
 	match = readl(wdt_base +
 		SIRFSOC_TIMER_MATCH_0 + (SIRFSOC_TIMER_WDT_INDEX << 2));
@@ -61,7 +66,7 @@ static int sirfsoc_wdt_updatetimeout(struct watchdog_device *wdd)
 	void __iomem *wdt_base;
 
 	timeout_ticks = wdd->timeout * CLOCK_FREQ;
-	wdt_base = watchdog_get_drvdata(wdd);
+	wdt_base = sirfsoc_wdt_base(wdd);
 
 	/* Enable the latch before reading the LATCH_LO register */
 	writel(1, wdt_base + SIRFSOC_TIMER_LATCH);
@@ -79,7 +84,7 @@ static int sirfsoc_wdt_updatetimeout(struct watchdog_device *wdd)
 
 static int sirfsoc_wdt_enable(struct watchdog_device *wdd)
 {
-	void __iomem *wdt_base = watchdog_get_drvdata(wdd);
+	void __iomem *wdt_base = sirfsoc_wdt_base(wdd);
 	sirfsoc_wdt_updatetimeout(wdd);
 
 	/*
@@ -96,7 +101,7 @@ static int sirfsoc_wdt_enable(struct watchdog_device *wdd)
 
 static int sirfsoc_wdt_disable(struct watchdog_device *wdd)
 {
-	void __iomem *wdt_base = watchdog_get_drvdata(wdd);
+	void __iomem *wdt_base = sirfsoc_wdt_base(wdd);
 
 	writel(0, wdt_base + SIRFSOC_TIMER_WATCHDOG_EN);
 	writel(readl(wdt_base + SIRFSOC_TIMER_INT_EN)
@@ -150,7 +155,7 @@ static int sirfsoc_wdt_probe(struct platform_device *pdev)
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
-	watchdog_set_drvdata(&sirfsoc_wdd, base);
+	watchdog_set_drvdata(&sirfsoc_wdd, (__force void *)base);
 
 	watchdog_init_timeout(&sirfsoc_wdd, timeout, &pdev->dev);
 	watchdog_set_nowayout(&sirfsoc_wdd, nowayout);
diff --git a/drivers/watchdog/softdog.c b/drivers/watchdog/softdog.c
index 99a06f9e3930..b067edf246df 100644
--- a/drivers/watchdog/softdog.c
+++ b/drivers/watchdog/softdog.c
@@ -17,36 +17,19 @@
  *
  *	Software only watchdog driver. Unlike its big brother the WDT501P
  *	driver this won't always recover a failed machine.
- *
- *  03/96: Angelo Haritsis <ah@doc.ic.ac.uk> :
- *	Modularised.
- *	Added soft_margin; use upon insmod to change the timer delay.
- *	NB: uses same minor as wdt (WATCHDOG_MINOR); we could use separate
- *	    minors.
- *
- *  19980911 Alan Cox
- *	Made SMP safe for 2.3.x
- *
- *  20011127 Joel Becker (jlbec@evilplan.org>
- *	Added soft_noboot; Allows testing the softdog trigger without
- *	requiring a recompile.
- *	Added WDIOC_GETTIMEOUT and WDIOC_SETTIMOUT.
- *
- *  20020530 Joel Becker <joel.becker@oracle.com>
- *	Added Matt Domsch's nowayout module option.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <linux/types.h>
+#include <linux/reboot.h>
 #include <linux/timer.h>
+#include <linux/types.h>
 #include <linux/watchdog.h>
-#include <linux/reboot.h>
-#include <linux/init.h>
-#include <linux/jiffies.h>
-#include <linux/kernel.h>
 
 #define TIMER_MARGIN	60		/* Default is 60 seconds */
 static unsigned int soft_margin = TIMER_MARGIN;	/* in seconds */
@@ -71,25 +54,12 @@ module_param(soft_panic, int, 0);
 MODULE_PARM_DESC(soft_panic,
 	"Softdog action, set to 1 to panic, 0 to reboot (default=0)");
 
-/*
- *	Our timer
- */
-
-static void watchdog_fire(unsigned long);
-
-static struct timer_list watchdog_ticktock =
-		TIMER_INITIALIZER(watchdog_fire, 0, 0);
-
-/*
- *	If the timer expires..
- */
-
-static void watchdog_fire(unsigned long data)
+static void softdog_fire(unsigned long data)
 {
 	module_put(THIS_MODULE);
-	if (soft_noboot)
+	if (soft_noboot) {
 		pr_crit("Triggered - Reboot ignored\n");
-	else if (soft_panic) {
+	} else if (soft_panic) {
 		pr_crit("Initiating panic\n");
 		panic("Software Watchdog Timer expired");
 	} else {
@@ -99,35 +69,24 @@ static void watchdog_fire(unsigned long data)
 	}
 }
 
-/*
- *	Softdog operations
- */
+static struct timer_list softdog_ticktock =
+		TIMER_INITIALIZER(softdog_fire, 0, 0);
 
 static int softdog_ping(struct watchdog_device *w)
 {
-	if (!mod_timer(&watchdog_ticktock, jiffies+(w->timeout*HZ)))
+	if (!mod_timer(&softdog_ticktock, jiffies + (w->timeout * HZ)))
 		__module_get(THIS_MODULE);
 	return 0;
 }
 
 static int softdog_stop(struct watchdog_device *w)
 {
-	if (del_timer(&watchdog_ticktock))
+	if (del_timer(&softdog_ticktock))
 		module_put(THIS_MODULE);
 
 	return 0;
 }
 
-static int softdog_set_timeout(struct watchdog_device *w, unsigned int t)
-{
-	w->timeout = t;
-	return 0;
-}
-
-/*
- *	Kernel Interfaces
- */
-
 static struct watchdog_info softdog_info = {
 	.identity = "Software Watchdog",
 	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
@@ -137,29 +96,21 @@ static struct watchdog_ops softdog_ops = {
 	.owner = THIS_MODULE,
 	.start = softdog_ping,
 	.stop = softdog_stop,
-	.set_timeout = softdog_set_timeout,
 };
 
 static struct watchdog_device softdog_dev = {
 	.info = &softdog_info,
 	.ops = &softdog_ops,
 	.min_timeout = 1,
-	.max_timeout = 0xFFFF
+	.max_timeout = 65535,
+	.timeout = TIMER_MARGIN,
 };
 
-static int __init watchdog_init(void)
+static int __init softdog_init(void)
 {
 	int ret;
 
-	/* Check that the soft_margin value is within it's range;
-	   if not reset to the default */
-	if (soft_margin < 1 || soft_margin > 65535) {
-		pr_info("soft_margin must be 0 < soft_margin < 65536, using %d\n",
-			TIMER_MARGIN);
-		return -EINVAL;
-	}
-	softdog_dev.timeout = soft_margin;
-
+	watchdog_init_timeout(&softdog_dev, soft_margin, NULL);
 	watchdog_set_nowayout(&softdog_dev, nowayout);
 	watchdog_stop_on_reboot(&softdog_dev);
 
@@ -167,19 +118,18 @@ static int __init watchdog_init(void)
 	if (ret)
 		return ret;
 
-	pr_info("Software Watchdog Timer: 0.08 initialized. soft_noboot=%d soft_margin=%d sec soft_panic=%d (nowayout=%d)\n",
-		soft_noboot, soft_margin, soft_panic, nowayout);
+	pr_info("initialized. soft_noboot=%d soft_margin=%d sec soft_panic=%d (nowayout=%d)\n",
+		soft_noboot, softdog_dev.timeout, soft_panic, nowayout);
 
 	return 0;
 }
+module_init(softdog_init);
 
-static void __exit watchdog_exit(void)
+static void __exit softdog_exit(void)
 {
 	watchdog_unregister_device(&softdog_dev);
 }
-
-module_init(watchdog_init);
-module_exit(watchdog_exit);
+module_exit(softdog_exit);
 
 MODULE_AUTHOR("Alan Cox");
 MODULE_DESCRIPTION("Software Watchdog Device Driver");
diff --git a/drivers/watchdog/tangox_wdt.c b/drivers/watchdog/tangox_wdt.c
index cfbed7e051b6..202c4b9cc921 100644
--- a/drivers/watchdog/tangox_wdt.c
+++ b/drivers/watchdog/tangox_wdt.c
@@ -149,7 +149,7 @@ static int tangox_wdt_probe(struct platform_device *pdev)
 	dev->wdt.ops = &tangox_wdt_ops;
 	dev->wdt.timeout = DEFAULT_TIMEOUT;
 	dev->wdt.min_timeout = 1;
-	dev->wdt.max_timeout = (U32_MAX - 1) / dev->clk_rate;
+	dev->wdt.max_hw_heartbeat_ms = (U32_MAX - 1) / dev->clk_rate;
 
 	watchdog_init_timeout(&dev->wdt, timeout, &pdev->dev);
 	watchdog_set_nowayout(&dev->wdt, nowayout);
@@ -170,7 +170,7 @@ static int tangox_wdt_probe(struct platform_device *pdev)
 	 * already running.
 	 */
 	if (readl(dev->base + WD_COUNTER)) {
-		set_bit(WDOG_ACTIVE, &dev->wdt.status);
+		set_bit(WDOG_HW_RUNNING, &dev->wdt.status);
 		tangox_wdt_start(&dev->wdt);
 	}
 
diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c
index 7c3ba58ae1be..6abb83cd7681 100644
--- a/drivers/watchdog/watchdog_core.c
+++ b/drivers/watchdog/watchdog_core.c
@@ -88,7 +88,7 @@ static void watchdog_check_min_max_timeout(struct watchdog_device *wdd)
 	 * Check that we have valid min and max timeout values, if
 	 * not reset them both to 0 (=not used or unknown)
 	 */
-	if (wdd->min_timeout > wdd->max_timeout) {
+	if (!wdd->max_hw_heartbeat_ms && wdd->min_timeout > wdd->max_timeout) {
 		pr_info("Invalid min and max timeout values, resetting to 0!\n");
 		wdd->min_timeout = 0;
 		wdd->max_timeout = 0;
@@ -329,6 +329,43 @@ void watchdog_unregister_device(struct watchdog_device *wdd)
 
 EXPORT_SYMBOL_GPL(watchdog_unregister_device);
 
+static void devm_watchdog_unregister_device(struct device *dev, void *res)
+{
+	watchdog_unregister_device(*(struct watchdog_device **)res);
+}
+
+/**
+ * devm_watchdog_register_device() - resource managed watchdog_register_device()
+ * @dev: device that is registering this watchdog device
+ * @wdd: watchdog device
+ *
+ * Managed watchdog_register_device(). For watchdog device registered by this
+ * function,  watchdog_unregister_device() is automatically called on driver
+ * detach. See watchdog_register_device() for more information.
+ */
+int devm_watchdog_register_device(struct device *dev,
+				struct watchdog_device *wdd)
+{
+	struct watchdog_device **rcwdd;
+	int ret;
+
+	rcwdd = devres_alloc(devm_watchdog_unregister_device, sizeof(*wdd),
+			     GFP_KERNEL);
+	if (!rcwdd)
+		return -ENOMEM;
+
+	ret = watchdog_register_device(wdd);
+	if (!ret) {
+		*rcwdd = wdd;
+		devres_add(dev, rcwdd);
+	} else {
+		devres_free(rcwdd);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devm_watchdog_register_device);
+
 static int __init watchdog_deferred_registration(void)
 {
 	mutex_lock(&wtd_deferred_reg_mutex);
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index 3595cffa24ea..040bf8382f46 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -69,6 +69,7 @@ struct watchdog_core_data {
 	unsigned long status;		/* Internal status bits */
 #define _WDOG_DEV_OPEN		0	/* Opened ? */
 #define _WDOG_ALLOW_RELEASE	1	/* Did we receive the magic char ? */
+#define _WDOG_KEEPALIVE		2	/* Did we receive a keepalive ? */
 };
 
 /* the dev_t structure to store the dynamically allocated watchdog devices */
@@ -92,9 +93,13 @@ static inline bool watchdog_need_worker(struct watchdog_device *wdd)
 	 *   thus is aware that the framework supports generating heartbeat
 	 *   requests.
 	 * - Userspace requests a longer timeout than the hardware can handle.
+	 *
+	 * Alternatively, if userspace has not opened the watchdog
+	 * device, we take care of feeding the watchdog if it is
+	 * running.
 	 */
-	return hm && ((watchdog_active(wdd) && t > hm) ||
-		      (t && !watchdog_active(wdd) && watchdog_hw_running(wdd)));
+	return (hm && watchdog_active(wdd) && t > hm) ||
+		(t && !watchdog_active(wdd) && watchdog_hw_running(wdd));
 }
 
 static long watchdog_next_keepalive(struct watchdog_device *wdd)
@@ -107,7 +112,7 @@ static long watchdog_next_keepalive(struct watchdog_device *wdd)
 	unsigned int hw_heartbeat_ms;
 
 	virt_timeout = wd_data->last_keepalive + msecs_to_jiffies(timeout_ms);
-	hw_heartbeat_ms = min(timeout_ms, wdd->max_hw_heartbeat_ms);
+	hw_heartbeat_ms = min_not_zero(timeout_ms, wdd->max_hw_heartbeat_ms);
 	keepalive_interval = msecs_to_jiffies(hw_heartbeat_ms / 2);
 
 	if (!watchdog_active(wdd))
@@ -180,6 +185,8 @@ static int watchdog_ping(struct watchdog_device *wdd)
 	if (!watchdog_active(wdd) && !watchdog_hw_running(wdd))
 		return 0;
 
+	set_bit(_WDOG_KEEPALIVE, &wd_data->status);
+
 	wd_data->last_keepalive = jiffies;
 	return __watchdog_ping(wdd);
 }
@@ -219,6 +226,8 @@ static int watchdog_start(struct watchdog_device *wdd)
 	if (watchdog_active(wdd))
 		return 0;
 
+	set_bit(_WDOG_KEEPALIVE, &wd_data->status);
+
 	started_at = jiffies;
 	if (watchdog_hw_running(wdd) && wdd->ops->ping)
 		err = wdd->ops->ping(wdd);
@@ -258,10 +267,12 @@ static int watchdog_stop(struct watchdog_device *wdd)
 		return -EBUSY;
 	}
 
-	if (wdd->ops->stop)
+	if (wdd->ops->stop) {
+		clear_bit(WDOG_HW_RUNNING, &wdd->status);
 		err = wdd->ops->stop(wdd);
-	else
+	} else {
 		set_bit(WDOG_HW_RUNNING, &wdd->status);
+	}
 
 	if (err == 0) {
 		clear_bit(WDOG_ACTIVE, &wdd->status);
@@ -282,10 +293,27 @@ static int watchdog_stop(struct watchdog_device *wdd)
 
 static unsigned int watchdog_get_status(struct watchdog_device *wdd)
 {
-	if (!wdd->ops->status)
-		return 0;
+	struct watchdog_core_data *wd_data = wdd->wd_data;
+	unsigned int status;
+
+	if (wdd->ops->status)
+		status = wdd->ops->status(wdd);
+	else
+		status = wdd->bootstatus & (WDIOF_CARDRESET |
+					    WDIOF_OVERHEAT |
+					    WDIOF_FANFAULT |
+					    WDIOF_EXTERN1 |
+					    WDIOF_EXTERN2 |
+					    WDIOF_POWERUNDER |
+					    WDIOF_POWEROVER);
 
-	return wdd->ops->status(wdd);
+	if (test_bit(_WDOG_ALLOW_RELEASE, &wd_data->status))
+		status |= WDIOF_MAGICCLOSE;
+
+	if (test_and_clear_bit(_WDOG_KEEPALIVE, &wd_data->status))
+		status |= WDIOF_KEEPALIVEPING;
+
+	return status;
 }
 
 /*
@@ -361,7 +389,7 @@ static ssize_t status_show(struct device *dev, struct device_attribute *attr,
 	status = watchdog_get_status(wdd);
 	mutex_unlock(&wd_data->lock);
 
-	return sprintf(buf, "%u\n", status);
+	return sprintf(buf, "0x%x\n", status);
 }
 static DEVICE_ATTR_RO(status);
 
@@ -429,9 +457,7 @@ static umode_t wdt_is_visible(struct kobject *kobj, struct attribute *attr,
 	struct watchdog_device *wdd = dev_get_drvdata(dev);
 	umode_t mode = attr->mode;
 
-	if (attr == &dev_attr_status.attr && !wdd->ops->status)
-		mode = 0;
-	else if (attr == &dev_attr_timeleft.attr && !wdd->ops->get_timeleft)
+	if (attr == &dev_attr_timeleft.attr && !wdd->ops->get_timeleft)
 		mode = 0;
 
 	return mode;
@@ -948,17 +974,22 @@ int __init watchdog_dev_init(void)
 	err = class_register(&watchdog_class);
 	if (err < 0) {
 		pr_err("couldn't register class\n");
-		return err;
+		goto err_register;
 	}
 
 	err = alloc_chrdev_region(&watchdog_devt, 0, MAX_DOGS, "watchdog");
 	if (err < 0) {
 		pr_err("watchdog: unable to allocate char dev region\n");
-		class_unregister(&watchdog_class);
-		return err;
+		goto err_alloc;
 	}
 
 	return 0;
+
+err_alloc:
+	class_unregister(&watchdog_class);
+err_register:
+	destroy_workqueue(watchdog_wq);
+	return err;
 }
 
 /*
diff --git a/drivers/watchdog/ziirave_wdt.c b/drivers/watchdog/ziirave_wdt.c
index cbe373de3659..fa1efef3c96e 100644
--- a/drivers/watchdog/ziirave_wdt.c
+++ b/drivers/watchdog/ziirave_wdt.c
@@ -339,7 +339,7 @@ static int ziirave_wdt_remove(struct i2c_client *client)
 }
 
 static struct i2c_device_id ziirave_wdt_id[] = {
-	{ "ziirave-wdt", 0 },
+	{ "rave-wdt", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, ziirave_wdt_id);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index a7a28110dc80..7f6aff3f72eb 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -605,28 +605,30 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 			 * Do the same thing for the memory mapping - between
 			 * elf_bss and last_bss is the bss section.
 			 */
-			k = load_addr + eppnt->p_memsz + eppnt->p_vaddr;
+			k = load_addr + eppnt->p_vaddr + eppnt->p_memsz;
 			if (k > last_bss)
 				last_bss = k;
 		}
 	}
 
+	/*
+	 * Now fill out the bss section: first pad the last page from
+	 * the file up to the page boundary, and zero it from elf_bss
+	 * up to the end of the page.
+	 */
+	if (padzero(elf_bss)) {
+		error = -EFAULT;
+		goto out;
+	}
+	/*
+	 * Next, align both the file and mem bss up to the page size,
+	 * since this is where elf_bss was just zeroed up to, and where
+	 * last_bss will end after the vm_brk() below.
+	 */
+	elf_bss = ELF_PAGEALIGN(elf_bss);
+	last_bss = ELF_PAGEALIGN(last_bss);
+	/* Finally, if there is still more bss to allocate, do it. */
 	if (last_bss > elf_bss) {
-		/*
-		 * Now fill out the bss section.  First pad the last page up
-		 * to the page boundary, and then perform a mmap to make sure
-		 * that there are zero-mapped pages up to and including the
-		 * last bss page.
-		 */
-		if (padzero(elf_bss)) {
-			error = -EFAULT;
-			goto out;
-		}
-
-		/* What we have mapped so far */
-		elf_bss = ELF_PAGESTART(elf_bss + ELF_MIN_ALIGN - 1);
-
-		/* Map the last of the bss segment */
 		error = vm_brk(elf_bss, last_bss - elf_bss);
 		if (error)
 			goto out;
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index 490538536cb4..dd2d3f0cd55d 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -24,7 +24,8 @@
 
 static int load_em86(struct linux_binprm *bprm)
 {
-	char *interp, *i_name, *i_arg;
+	const char *i_name, *i_arg;
+	char *interp;
 	struct file * file;
 	int retval;
 	struct elfhdr	elf_ex;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b2620d1f883f..443fcc402114 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -439,6 +439,8 @@ struct btrfs_space_info {
 	struct list_head list;
 	/* Protected by the spinlock 'lock'. */
 	struct list_head ro_bgs;
+	struct list_head priority_tickets;
+	struct list_head tickets;
 
 	struct rw_semaphore groups_sem;
 	/* for block groups in our same type */
@@ -2624,6 +2626,15 @@ enum btrfs_reserve_flush_enum {
 	BTRFS_RESERVE_FLUSH_ALL,
 };
 
+enum btrfs_flush_state {
+	FLUSH_DELAYED_ITEMS_NR	=	1,
+	FLUSH_DELAYED_ITEMS	=	2,
+	FLUSH_DELALLOC		=	3,
+	FLUSH_DELALLOC_WAIT	=	4,
+	ALLOC_CHUNK		=	5,
+	COMMIT_TRANS		=	6,
+};
+
 int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len);
 int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes);
 void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len);
@@ -2661,8 +2672,8 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
 			   struct btrfs_block_rsv *block_rsv, u64 min_reserved,
 			   enum btrfs_reserve_flush_enum flush);
 int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
-			    struct btrfs_block_rsv *dst_rsv,
-			    u64 num_bytes);
+			    struct btrfs_block_rsv *dst_rsv, u64 num_bytes,
+			    int update_size);
 int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
 			     struct btrfs_block_rsv *dest, u64 num_bytes,
 			     int min_factor);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index d3aaabbfada0..dd3c040139a2 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -553,7 +553,7 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans,
 	dst_rsv = &root->fs_info->delayed_block_rsv;
 
 	num_bytes = btrfs_calc_trans_metadata_size(root, 1);
-	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
+	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
 	if (!ret) {
 		trace_btrfs_space_reservation(root->fs_info, "delayed_item",
 					      item->key.objectid,
@@ -598,6 +598,29 @@ static int btrfs_delayed_inode_reserve_metadata(
 	num_bytes = btrfs_calc_trans_metadata_size(root, 1);
 
 	/*
+	 * If our block_rsv is the delalloc block reserve then check and see if
+	 * we have our extra reservation for updating the inode.  If not fall
+	 * through and try to reserve space quickly.
+	 *
+	 * We used to try and steal from the delalloc block rsv or the global
+	 * reserve, but we'd steal a full reservation, which isn't kind.  We are
+	 * here through delalloc which means we've likely just cowed down close
+	 * to the leaf that contains the inode, so we would steal less just
+	 * doing the fallback inode update, so if we do end up having to steal
+	 * from the global block rsv we hopefully only steal one or two blocks
+	 * worth which is less likely to hurt us.
+	 */
+	if (src_rsv && src_rsv->type == BTRFS_BLOCK_RSV_DELALLOC) {
+		spin_lock(&BTRFS_I(inode)->lock);
+		if (test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
+				       &BTRFS_I(inode)->runtime_flags))
+			release = true;
+		else
+			src_rsv = NULL;
+		spin_unlock(&BTRFS_I(inode)->lock);
+	}
+
+	/*
 	 * btrfs_dirty_inode will update the inode under btrfs_join_transaction
 	 * which doesn't reserve space for speed.  This is a problem since we
 	 * still need to reserve space for this update, so try to reserve the
@@ -626,51 +649,10 @@ static int btrfs_delayed_inode_reserve_metadata(
 						      num_bytes, 1);
 		}
 		return ret;
-	} else if (src_rsv->type == BTRFS_BLOCK_RSV_DELALLOC) {
-		spin_lock(&BTRFS_I(inode)->lock);
-		if (test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-				       &BTRFS_I(inode)->runtime_flags)) {
-			spin_unlock(&BTRFS_I(inode)->lock);
-			release = true;
-			goto migrate;
-		}
-		spin_unlock(&BTRFS_I(inode)->lock);
-
-		/* Ok we didn't have space pre-reserved.  This shouldn't happen
-		 * too often but it can happen if we do delalloc to an existing
-		 * inode which gets dirtied because of the time update, and then
-		 * isn't touched again until after the transaction commits and
-		 * then we try to write out the data.  First try to be nice and
-		 * reserve something strictly for us.  If not be a pain and try
-		 * to steal from the delalloc block rsv.
-		 */
-		ret = btrfs_block_rsv_add(root, dst_rsv, num_bytes,
-					  BTRFS_RESERVE_NO_FLUSH);
-		if (!ret)
-			goto out;
-
-		ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
-		if (!ret)
-			goto out;
-
-		if (btrfs_test_opt(root, ENOSPC_DEBUG)) {
-			btrfs_debug(root->fs_info,
-				    "block rsv migrate returned %d", ret);
-			WARN_ON(1);
-		}
-		/*
-		 * Ok this is a problem, let's just steal from the global rsv
-		 * since this really shouldn't happen that often.
-		 */
-		ret = btrfs_block_rsv_migrate(&root->fs_info->global_block_rsv,
-					      dst_rsv, num_bytes);
-		goto out;
 	}
 
-migrate:
-	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
+	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
 
-out:
 	/*
 	 * Migrate only takes a reservation, it doesn't touch the size of the
 	 * block_rsv.  This is to simplify people who don't normally have things
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b480fd555774..e9376b1657e2 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -111,6 +111,16 @@ static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
 			       u64 num_bytes);
 int btrfs_pin_extent(struct btrfs_root *root,
 		     u64 bytenr, u64 num_bytes, int reserved);
+static int __reserve_metadata_bytes(struct btrfs_root *root,
+				    struct btrfs_space_info *space_info,
+				    u64 orig_bytes,
+				    enum btrfs_reserve_flush_enum flush);
+static void space_info_add_new_bytes(struct btrfs_fs_info *fs_info,
+				     struct btrfs_space_info *space_info,
+				     u64 num_bytes);
+static void space_info_add_old_bytes(struct btrfs_fs_info *fs_info,
+				     struct btrfs_space_info *space_info,
+				     u64 num_bytes);
 
 static noinline int
 block_group_cache_done(struct btrfs_block_group_cache *cache)
@@ -3913,6 +3923,7 @@ static const char *alloc_name(u64 flags)
 
 static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 			     u64 total_bytes, u64 bytes_used,
+			     u64 bytes_readonly,
 			     struct btrfs_space_info **space_info)
 {
 	struct btrfs_space_info *found;
@@ -3933,8 +3944,11 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 		found->disk_total += total_bytes * factor;
 		found->bytes_used += bytes_used;
 		found->disk_used += bytes_used * factor;
+		found->bytes_readonly += bytes_readonly;
 		if (total_bytes > 0)
 			found->full = 0;
+		space_info_add_new_bytes(info, found, total_bytes -
+					 bytes_used - bytes_readonly);
 		spin_unlock(&found->lock);
 		*space_info = found;
 		return 0;
@@ -3960,7 +3974,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 	found->disk_used = bytes_used * factor;
 	found->bytes_pinned = 0;
 	found->bytes_reserved = 0;
-	found->bytes_readonly = 0;
+	found->bytes_readonly = bytes_readonly;
 	found->bytes_may_use = 0;
 	found->full = 0;
 	found->max_extent_size = 0;
@@ -3969,6 +3983,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 	found->flush = 0;
 	init_waitqueue_head(&found->wait);
 	INIT_LIST_HEAD(&found->ro_bgs);
+	INIT_LIST_HEAD(&found->tickets);
+	INIT_LIST_HEAD(&found->priority_tickets);
 
 	ret = kobject_init_and_add(&found->kobj, &space_info_ktype,
 				    info->space_info_kobj, "%s",
@@ -4470,7 +4486,7 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 	space_info = __find_space_info(extent_root->fs_info, flags);
 	if (!space_info) {
 		ret = update_space_info(extent_root->fs_info, flags,
-					0, 0, &space_info);
+					0, 0, 0, &space_info);
 		BUG_ON(ret); /* -ENOMEM */
 	}
 	BUG_ON(!space_info); /* Logic error */
@@ -4582,12 +4598,19 @@ static int can_overcommit(struct btrfs_root *root,
 			  struct btrfs_space_info *space_info, u64 bytes,
 			  enum btrfs_reserve_flush_enum flush)
 {
-	struct btrfs_block_rsv *global_rsv = &root->fs_info->global_block_rsv;
-	u64 profile = btrfs_get_alloc_profile(root, 0);
+	struct btrfs_block_rsv *global_rsv;
+	u64 profile;
 	u64 space_size;
 	u64 avail;
 	u64 used;
 
+	/* Don't overcommit when in mixed mode. */
+	if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
+		return 0;
+
+	BUG_ON(root->fs_info == NULL);
+	global_rsv = &root->fs_info->global_block_rsv;
+	profile = btrfs_get_alloc_profile(root, 0);
 	used = space_info->bytes_used + space_info->bytes_reserved +
 		space_info->bytes_pinned + space_info->bytes_readonly;
 
@@ -4739,6 +4762,11 @@ skip_async:
 			spin_unlock(&space_info->lock);
 			break;
 		}
+		if (list_empty(&space_info->tickets) &&
+		    list_empty(&space_info->priority_tickets)) {
+			spin_unlock(&space_info->lock);
+			break;
+		}
 		spin_unlock(&space_info->lock);
 
 		loops++;
@@ -4807,13 +4835,11 @@ commit:
 	return btrfs_commit_transaction(trans, root);
 }
 
-enum flush_state {
-	FLUSH_DELAYED_ITEMS_NR	=	1,
-	FLUSH_DELAYED_ITEMS	=	2,
-	FLUSH_DELALLOC		=	3,
-	FLUSH_DELALLOC_WAIT	=	4,
-	ALLOC_CHUNK		=	5,
-	COMMIT_TRANS		=	6,
+struct reserve_ticket {
+	u64 bytes;
+	int error;
+	struct list_head list;
+	wait_queue_head_t wait;
 };
 
 static int flush_space(struct btrfs_root *root,
@@ -4866,6 +4892,8 @@ static int flush_space(struct btrfs_root *root,
 		break;
 	}
 
+	trace_btrfs_flush_space(root->fs_info, space_info->flags, num_bytes,
+				orig_bytes, state, ret);
 	return ret;
 }
 
@@ -4873,17 +4901,22 @@ static inline u64
 btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
 				 struct btrfs_space_info *space_info)
 {
+	struct reserve_ticket *ticket;
 	u64 used;
 	u64 expected;
-	u64 to_reclaim;
+	u64 to_reclaim = 0;
 
 	to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
-	spin_lock(&space_info->lock);
 	if (can_overcommit(root, space_info, to_reclaim,
-			   BTRFS_RESERVE_FLUSH_ALL)) {
-		to_reclaim = 0;
-		goto out;
-	}
+			   BTRFS_RESERVE_FLUSH_ALL))
+		return 0;
+
+	list_for_each_entry(ticket, &space_info->tickets, list)
+		to_reclaim += ticket->bytes;
+	list_for_each_entry(ticket, &space_info->priority_tickets, list)
+		to_reclaim += ticket->bytes;
+	if (to_reclaim)
+		return to_reclaim;
 
 	used = space_info->bytes_used + space_info->bytes_reserved +
 	       space_info->bytes_pinned + space_info->bytes_readonly +
@@ -4899,14 +4932,11 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
 		to_reclaim = 0;
 	to_reclaim = min(to_reclaim, space_info->bytes_may_use +
 				     space_info->bytes_reserved);
-out:
-	spin_unlock(&space_info->lock);
-
 	return to_reclaim;
 }
 
 static inline int need_do_async_reclaim(struct btrfs_space_info *space_info,
-					struct btrfs_fs_info *fs_info, u64 used)
+					struct btrfs_root *root, u64 used)
 {
 	u64 thresh = div_factor_fine(space_info->total_bytes, 98);
 
@@ -4914,73 +4944,177 @@ static inline int need_do_async_reclaim(struct btrfs_space_info *space_info,
 	if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh)
 		return 0;
 
-	return (used >= thresh && !btrfs_fs_closing(fs_info) &&
-		!test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state));
+	if (!btrfs_calc_reclaim_metadata_size(root, space_info))
+		return 0;
+
+	return (used >= thresh && !btrfs_fs_closing(root->fs_info) &&
+		!test_bit(BTRFS_FS_STATE_REMOUNTING,
+			  &root->fs_info->fs_state));
 }
 
-static int btrfs_need_do_async_reclaim(struct btrfs_space_info *space_info,
-				       struct btrfs_fs_info *fs_info,
-				       int flush_state)
+static void wake_all_tickets(struct list_head *head)
 {
-	u64 used;
-
-	spin_lock(&space_info->lock);
-	/*
-	 * We run out of space and have not got any free space via flush_space,
-	 * so don't bother doing async reclaim.
-	 */
-	if (flush_state > COMMIT_TRANS && space_info->full) {
-		spin_unlock(&space_info->lock);
-		return 0;
-	}
+	struct reserve_ticket *ticket;
 
-	used = space_info->bytes_used + space_info->bytes_reserved +
-	       space_info->bytes_pinned + space_info->bytes_readonly +
-	       space_info->bytes_may_use;
-	if (need_do_async_reclaim(space_info, fs_info, used)) {
-		spin_unlock(&space_info->lock);
-		return 1;
+	while (!list_empty(head)) {
+		ticket = list_first_entry(head, struct reserve_ticket, list);
+		list_del_init(&ticket->list);
+		ticket->error = -ENOSPC;
+		wake_up(&ticket->wait);
 	}
-	spin_unlock(&space_info->lock);
-
-	return 0;
 }
 
+/*
+ * This is for normal flushers, we can wait all goddamned day if we want to.  We
+ * will loop and continuously try to flush as long as we are making progress.
+ * We count progress as clearing off tickets each time we have to loop.
+ */
 static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 {
+	struct reserve_ticket *last_ticket = NULL;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_space_info *space_info;
 	u64 to_reclaim;
 	int flush_state;
+	int commit_cycles = 0;
 
 	fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work);
 	space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
 
+	spin_lock(&space_info->lock);
 	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
 						      space_info);
-	if (!to_reclaim)
+	if (!to_reclaim) {
+		space_info->flush = 0;
+		spin_unlock(&space_info->lock);
 		return;
+	}
+	last_ticket = list_first_entry(&space_info->tickets,
+				       struct reserve_ticket, list);
+	spin_unlock(&space_info->lock);
 
 	flush_state = FLUSH_DELAYED_ITEMS_NR;
 	do {
+		struct reserve_ticket *ticket;
+		int ret;
+
+		ret = flush_space(fs_info->fs_root, space_info, to_reclaim,
+			    to_reclaim, flush_state);
+		spin_lock(&space_info->lock);
+		if (list_empty(&space_info->tickets)) {
+			space_info->flush = 0;
+			spin_unlock(&space_info->lock);
+			return;
+		}
+		to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
+							      space_info);
+		ticket = list_first_entry(&space_info->tickets,
+					  struct reserve_ticket, list);
+		if (last_ticket == ticket) {
+			flush_state++;
+		} else {
+			last_ticket = ticket;
+			flush_state = FLUSH_DELAYED_ITEMS_NR;
+			if (commit_cycles)
+				commit_cycles--;
+		}
+
+		if (flush_state > COMMIT_TRANS) {
+			commit_cycles++;
+			if (commit_cycles > 2) {
+				wake_all_tickets(&space_info->tickets);
+				space_info->flush = 0;
+			} else {
+				flush_state = FLUSH_DELAYED_ITEMS_NR;
+			}
+		}
+		spin_unlock(&space_info->lock);
+	} while (flush_state <= COMMIT_TRANS);
+}
+
+void btrfs_init_async_reclaim_work(struct work_struct *work)
+{
+	INIT_WORK(work, btrfs_async_reclaim_metadata_space);
+}
+
+static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
+					    struct btrfs_space_info *space_info,
+					    struct reserve_ticket *ticket)
+{
+	u64 to_reclaim;
+	int flush_state = FLUSH_DELAYED_ITEMS_NR;
+
+	spin_lock(&space_info->lock);
+	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
+						      space_info);
+	if (!to_reclaim) {
+		spin_unlock(&space_info->lock);
+		return;
+	}
+	spin_unlock(&space_info->lock);
+
+	do {
 		flush_space(fs_info->fs_root, space_info, to_reclaim,
 			    to_reclaim, flush_state);
 		flush_state++;
-		if (!btrfs_need_do_async_reclaim(space_info, fs_info,
-						 flush_state))
+		spin_lock(&space_info->lock);
+		if (ticket->bytes == 0) {
+			spin_unlock(&space_info->lock);
 			return;
+		}
+		spin_unlock(&space_info->lock);
+
+		/*
+		 * Priority flushers can't wait on delalloc without
+		 * deadlocking.
+		 */
+		if (flush_state == FLUSH_DELALLOC ||
+		    flush_state == FLUSH_DELALLOC_WAIT)
+			flush_state = ALLOC_CHUNK;
 	} while (flush_state < COMMIT_TRANS);
 }
 
-void btrfs_init_async_reclaim_work(struct work_struct *work)
+static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
+			       struct btrfs_space_info *space_info,
+			       struct reserve_ticket *ticket, u64 orig_bytes)
+
 {
-	INIT_WORK(work, btrfs_async_reclaim_metadata_space);
+	DEFINE_WAIT(wait);
+	int ret = 0;
+
+	spin_lock(&space_info->lock);
+	while (ticket->bytes > 0 && ticket->error == 0) {
+		ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE);
+		if (ret) {
+			ret = -EINTR;
+			break;
+		}
+		spin_unlock(&space_info->lock);
+
+		schedule();
+
+		finish_wait(&ticket->wait, &wait);
+		spin_lock(&space_info->lock);
+	}
+	if (!ret)
+		ret = ticket->error;
+	if (!list_empty(&ticket->list))
+		list_del_init(&ticket->list);
+	if (ticket->bytes && ticket->bytes < orig_bytes) {
+		u64 num_bytes = orig_bytes - ticket->bytes;
+		space_info->bytes_may_use -= num_bytes;
+		trace_btrfs_space_reservation(fs_info, "space_info",
+					      space_info->flags, num_bytes, 0);
+	}
+	spin_unlock(&space_info->lock);
+
+	return ret;
 }
 
 /**
  * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space
  * @root - the root we're allocating for
- * @block_rsv - the block_rsv we're allocating for
+ * @space_info - the space info we want to allocate from
  * @orig_bytes - the number of bytes we want
  * @flush - whether or not we can flush to make our reservation
  *
@@ -4991,81 +5125,36 @@ void btrfs_init_async_reclaim_work(struct work_struct *work)
  * regain reservations will be made and this will fail if there is not enough
  * space already.
  */
-static int reserve_metadata_bytes(struct btrfs_root *root,
-				  struct btrfs_block_rsv *block_rsv,
-				  u64 orig_bytes,
-				  enum btrfs_reserve_flush_enum flush)
+static int __reserve_metadata_bytes(struct btrfs_root *root,
+				    struct btrfs_space_info *space_info,
+				    u64 orig_bytes,
+				    enum btrfs_reserve_flush_enum flush)
 {
-	struct btrfs_space_info *space_info = block_rsv->space_info;
+	struct reserve_ticket ticket;
 	u64 used;
-	u64 num_bytes = orig_bytes;
-	int flush_state = FLUSH_DELAYED_ITEMS_NR;
 	int ret = 0;
-	bool flushing = false;
 
-again:
-	ret = 0;
-	spin_lock(&space_info->lock);
-	/*
-	 * We only want to wait if somebody other than us is flushing and we
-	 * are actually allowed to flush all things.
-	 */
-	while (flush == BTRFS_RESERVE_FLUSH_ALL && !flushing &&
-	       space_info->flush) {
-		spin_unlock(&space_info->lock);
-		/*
-		 * If we have a trans handle we can't wait because the flusher
-		 * may have to commit the transaction, which would mean we would
-		 * deadlock since we are waiting for the flusher to finish, but
-		 * hold the current transaction open.
-		 */
-		if (current->journal_info)
-			return -EAGAIN;
-		ret = wait_event_killable(space_info->wait, !space_info->flush);
-		/* Must have been killed, return */
-		if (ret)
-			return -EINTR;
-
-		spin_lock(&space_info->lock);
-	}
+	ASSERT(orig_bytes);
+	ASSERT(!current->journal_info || flush != BTRFS_RESERVE_FLUSH_ALL);
 
+	spin_lock(&space_info->lock);
 	ret = -ENOSPC;
 	used = space_info->bytes_used + space_info->bytes_reserved +
 		space_info->bytes_pinned + space_info->bytes_readonly +
 		space_info->bytes_may_use;
 
 	/*
-	 * The idea here is that we've not already over-reserved the block group
-	 * then we can go ahead and save our reservation first and then start
-	 * flushing if we need to.  Otherwise if we've already overcommitted
-	 * lets start flushing stuff first and then come back and try to make
-	 * our reservation.
+	 * If we have enough space then hooray, make our reservation and carry
+	 * on.  If not see if we can overcommit, and if we can, hooray carry on.
+	 * If not things get more complicated.
 	 */
-	if (used <= space_info->total_bytes) {
-		if (used + orig_bytes <= space_info->total_bytes) {
-			space_info->bytes_may_use += orig_bytes;
-			trace_btrfs_space_reservation(root->fs_info,
-				"space_info", space_info->flags, orig_bytes, 1);
-			ret = 0;
-		} else {
-			/*
-			 * Ok set num_bytes to orig_bytes since we aren't
-			 * overocmmitted, this way we only try and reclaim what
-			 * we need.
-			 */
-			num_bytes = orig_bytes;
-		}
-	} else {
-		/*
-		 * Ok we're over committed, set num_bytes to the overcommitted
-		 * amount plus the amount of bytes that we need for this
-		 * reservation.
-		 */
-		num_bytes = used - space_info->total_bytes +
-			(orig_bytes * 2);
-	}
-
-	if (ret && can_overcommit(root, space_info, orig_bytes, flush)) {
+	if (used + orig_bytes <= space_info->total_bytes) {
+		space_info->bytes_may_use += orig_bytes;
+		trace_btrfs_space_reservation(root->fs_info, "space_info",
+					      space_info->flags, orig_bytes,
+					      1);
+		ret = 0;
+	} else if (can_overcommit(root, space_info, orig_bytes, flush)) {
 		space_info->bytes_may_use += orig_bytes;
 		trace_btrfs_space_reservation(root->fs_info, "space_info",
 					      space_info->flags, orig_bytes,
@@ -5074,16 +5163,31 @@ again:
 	}
 
 	/*
-	 * Couldn't make our reservation, save our place so while we're trying
-	 * to reclaim space we can actually use it instead of somebody else
-	 * stealing it from us.
+	 * If we couldn't make a reservation then setup our reservation ticket
+	 * and kick the async worker if it's not already running.
 	 *
-	 * We make the other tasks wait for the flush only when we can flush
-	 * all things.
+	 * If we are a priority flusher then we just need to add our ticket to
+	 * the list and we will do our own flushing further down.
 	 */
 	if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
-		flushing = true;
-		space_info->flush = 1;
+		ticket.bytes = orig_bytes;
+		ticket.error = 0;
+		init_waitqueue_head(&ticket.wait);
+		if (flush == BTRFS_RESERVE_FLUSH_ALL) {
+			list_add_tail(&ticket.list, &space_info->tickets);
+			if (!space_info->flush) {
+				space_info->flush = 1;
+				trace_btrfs_trigger_flush(root->fs_info,
+							  space_info->flags,
+							  orig_bytes, flush,
+							  "enospc");
+				queue_work(system_unbound_wq,
+					   &root->fs_info->async_reclaim_work);
+			}
+		} else {
+			list_add_tail(&ticket.list,
+				      &space_info->priority_tickets);
+		}
 	} else if (!ret && space_info->flags & BTRFS_BLOCK_GROUP_METADATA) {
 		used += orig_bytes;
 		/*
@@ -5092,39 +5196,67 @@ again:
 		 * the async reclaim as we will panic.
 		 */
 		if (!root->fs_info->log_root_recovering &&
-		    need_do_async_reclaim(space_info, root->fs_info, used) &&
-		    !work_busy(&root->fs_info->async_reclaim_work))
+		    need_do_async_reclaim(space_info, root, used) &&
+		    !work_busy(&root->fs_info->async_reclaim_work)) {
+			trace_btrfs_trigger_flush(root->fs_info,
+						  space_info->flags,
+						  orig_bytes, flush,
+						  "preempt");
 			queue_work(system_unbound_wq,
 				   &root->fs_info->async_reclaim_work);
+		}
 	}
 	spin_unlock(&space_info->lock);
-
 	if (!ret || flush == BTRFS_RESERVE_NO_FLUSH)
-		goto out;
+		return ret;
 
-	ret = flush_space(root, space_info, num_bytes, orig_bytes,
-			  flush_state);
-	flush_state++;
+	if (flush == BTRFS_RESERVE_FLUSH_ALL)
+		return wait_reserve_ticket(root->fs_info, space_info, &ticket,
+					   orig_bytes);
 
-	/*
-	 * If we are FLUSH_LIMIT, we can not flush delalloc, or the deadlock
-	 * would happen. So skip delalloc flush.
-	 */
-	if (flush == BTRFS_RESERVE_FLUSH_LIMIT &&
-	    (flush_state == FLUSH_DELALLOC ||
-	     flush_state == FLUSH_DELALLOC_WAIT))
-		flush_state = ALLOC_CHUNK;
+	ret = 0;
+	priority_reclaim_metadata_space(root->fs_info, space_info, &ticket);
+	spin_lock(&space_info->lock);
+	if (ticket.bytes) {
+		if (ticket.bytes < orig_bytes) {
+			u64 num_bytes = orig_bytes - ticket.bytes;
+			space_info->bytes_may_use -= num_bytes;
+			trace_btrfs_space_reservation(root->fs_info,
+					"space_info", space_info->flags,
+					num_bytes, 0);
 
-	if (!ret)
-		goto again;
-	else if (flush == BTRFS_RESERVE_FLUSH_LIMIT &&
-		 flush_state < COMMIT_TRANS)
-		goto again;
-	else if (flush == BTRFS_RESERVE_FLUSH_ALL &&
-		 flush_state <= COMMIT_TRANS)
-		goto again;
+		}
+		list_del_init(&ticket.list);
+		ret = -ENOSPC;
+	}
+	spin_unlock(&space_info->lock);
+	ASSERT(list_empty(&ticket.list));
+	return ret;
+}
 
-out:
+/**
+ * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space
+ * @root - the root we're allocating for
+ * @block_rsv - the block_rsv we're allocating for
+ * @orig_bytes - the number of bytes we want
+ * @flush - whether or not we can flush to make our reservation
+ *
+ * This will reserve orgi_bytes number of bytes from the space info associated
+ * with the block_rsv.  If there is not enough space it will make an attempt to
+ * flush out space to make room.  It will do this by flushing delalloc if
+ * possible or committing the transaction.  If flush is 0 then no attempts to
+ * regain reservations will be made and this will fail if there is not enough
+ * space already.
+ */
+static int reserve_metadata_bytes(struct btrfs_root *root,
+				  struct btrfs_block_rsv *block_rsv,
+				  u64 orig_bytes,
+				  enum btrfs_reserve_flush_enum flush)
+{
+	int ret;
+
+	ret = __reserve_metadata_bytes(root, block_rsv->space_info, orig_bytes,
+				       flush);
 	if (ret == -ENOSPC &&
 	    unlikely(root->orphan_cleanup_state == ORPHAN_CLEANUP_STARTED)) {
 		struct btrfs_block_rsv *global_rsv =
@@ -5137,13 +5269,8 @@ out:
 	if (ret == -ENOSPC)
 		trace_btrfs_space_reservation(root->fs_info,
 					      "space_info:enospc",
-					      space_info->flags, orig_bytes, 1);
-	if (flushing) {
-		spin_lock(&space_info->lock);
-		space_info->flush = 0;
-		wake_up_all(&space_info->wait);
-		spin_unlock(&space_info->lock);
-	}
+					      block_rsv->space_info->flags,
+					      orig_bytes, 1);
 	return ret;
 }
 
@@ -5219,6 +5346,108 @@ int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+/*
+ * This is for space we already have accounted in space_info->bytes_may_use, so
+ * basically when we're returning space from block_rsv's.
+ */
+static void space_info_add_old_bytes(struct btrfs_fs_info *fs_info,
+				     struct btrfs_space_info *space_info,
+				     u64 num_bytes)
+{
+	struct reserve_ticket *ticket;
+	struct list_head *head;
+	u64 used;
+	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_NO_FLUSH;
+	bool check_overcommit = false;
+
+	spin_lock(&space_info->lock);
+	head = &space_info->priority_tickets;
+
+	/*
+	 * If we are over our limit then we need to check and see if we can
+	 * overcommit, and if we can't then we just need to free up our space
+	 * and not satisfy any requests.
+	 */
+	used = space_info->bytes_used + space_info->bytes_reserved +
+		space_info->bytes_pinned + space_info->bytes_readonly +
+		space_info->bytes_may_use;
+	if (used - num_bytes >= space_info->total_bytes)
+		check_overcommit = true;
+again:
+	while (!list_empty(head) && num_bytes) {
+		ticket = list_first_entry(head, struct reserve_ticket,
+					  list);
+		/*
+		 * We use 0 bytes because this space is already reserved, so
+		 * adding the ticket space would be a double count.
+		 */
+		if (check_overcommit &&
+		    !can_overcommit(fs_info->extent_root, space_info, 0,
+				    flush))
+			break;
+		if (num_bytes >= ticket->bytes) {
+			list_del_init(&ticket->list);
+			num_bytes -= ticket->bytes;
+			ticket->bytes = 0;
+			wake_up(&ticket->wait);
+		} else {
+			ticket->bytes -= num_bytes;
+			num_bytes = 0;
+		}
+	}
+
+	if (num_bytes && head == &space_info->priority_tickets) {
+		head = &space_info->tickets;
+		flush = BTRFS_RESERVE_FLUSH_ALL;
+		goto again;
+	}
+	space_info->bytes_may_use -= num_bytes;
+	trace_btrfs_space_reservation(fs_info, "space_info",
+				      space_info->flags, num_bytes, 0);
+	spin_unlock(&space_info->lock);
+}
+
+/*
+ * This is for newly allocated space that isn't accounted in
+ * space_info->bytes_may_use yet.  So if we allocate a chunk or unpin an extent
+ * we use this helper.
+ */
+static void space_info_add_new_bytes(struct btrfs_fs_info *fs_info,
+				     struct btrfs_space_info *space_info,
+				     u64 num_bytes)
+{
+	struct reserve_ticket *ticket;
+	struct list_head *head = &space_info->priority_tickets;
+
+again:
+	while (!list_empty(head) && num_bytes) {
+		ticket = list_first_entry(head, struct reserve_ticket,
+					  list);
+		if (num_bytes >= ticket->bytes) {
+			trace_btrfs_space_reservation(fs_info, "space_info",
+						      space_info->flags,
+						      ticket->bytes, 1);
+			list_del_init(&ticket->list);
+			num_bytes -= ticket->bytes;
+			space_info->bytes_may_use += ticket->bytes;
+			ticket->bytes = 0;
+			wake_up(&ticket->wait);
+		} else {
+			trace_btrfs_space_reservation(fs_info, "space_info",
+						      space_info->flags,
+						      num_bytes, 1);
+			space_info->bytes_may_use += num_bytes;
+			ticket->bytes -= num_bytes;
+			num_bytes = 0;
+		}
+	}
+
+	if (num_bytes && head == &space_info->priority_tickets) {
+		head = &space_info->tickets;
+		goto again;
+	}
+}
+
 static void block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 				    struct btrfs_block_rsv *block_rsv,
 				    struct btrfs_block_rsv *dest, u64 num_bytes)
@@ -5253,18 +5482,15 @@ static void block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 			}
 			spin_unlock(&dest->lock);
 		}
-		if (num_bytes) {
-			spin_lock(&space_info->lock);
-			space_info->bytes_may_use -= num_bytes;
-			trace_btrfs_space_reservation(fs_info, "space_info",
-					space_info->flags, num_bytes, 0);
-			spin_unlock(&space_info->lock);
-		}
+		if (num_bytes)
+			space_info_add_old_bytes(fs_info, space_info,
+						 num_bytes);
 	}
 }
 
-static int block_rsv_migrate_bytes(struct btrfs_block_rsv *src,
-				   struct btrfs_block_rsv *dst, u64 num_bytes)
+int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src,
+			    struct btrfs_block_rsv *dst, u64 num_bytes,
+			    int update_size)
 {
 	int ret;
 
@@ -5272,7 +5498,7 @@ static int block_rsv_migrate_bytes(struct btrfs_block_rsv *src,
 	if (ret)
 		return ret;
 
-	block_rsv_add_bytes(dst, num_bytes, 1);
+	block_rsv_add_bytes(dst, num_bytes, update_size);
 	return 0;
 }
 
@@ -5379,13 +5605,6 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
 	return ret;
 }
 
-int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
-			    struct btrfs_block_rsv *dst_rsv,
-			    u64 num_bytes)
-{
-	return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
-}
-
 void btrfs_block_rsv_release(struct btrfs_root *root,
 			     struct btrfs_block_rsv *block_rsv,
 			     u64 num_bytes)
@@ -5398,48 +5617,21 @@ void btrfs_block_rsv_release(struct btrfs_root *root,
 				num_bytes);
 }
 
-/*
- * helper to calculate size of global block reservation.
- * the desired value is sum of space used by extent tree,
- * checksum tree and root tree
- */
-static u64 calc_global_metadata_size(struct btrfs_fs_info *fs_info)
-{
-	struct btrfs_space_info *sinfo;
-	u64 num_bytes;
-	u64 meta_used;
-	u64 data_used;
-	int csum_size = btrfs_super_csum_size(fs_info->super_copy);
-
-	sinfo = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_DATA);
-	spin_lock(&sinfo->lock);
-	data_used = sinfo->bytes_used;
-	spin_unlock(&sinfo->lock);
-
-	sinfo = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
-	spin_lock(&sinfo->lock);
-	if (sinfo->flags & BTRFS_BLOCK_GROUP_DATA)
-		data_used = 0;
-	meta_used = sinfo->bytes_used;
-	spin_unlock(&sinfo->lock);
-
-	num_bytes = (data_used >> fs_info->sb->s_blocksize_bits) *
-		    csum_size * 2;
-	num_bytes += div_u64(data_used + meta_used, 50);
-
-	if (num_bytes * 3 > meta_used)
-		num_bytes = div_u64(meta_used, 3);
-
-	return ALIGN(num_bytes, fs_info->extent_root->nodesize << 10);
-}
-
 static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
 	struct btrfs_space_info *sinfo = block_rsv->space_info;
 	u64 num_bytes;
 
-	num_bytes = calc_global_metadata_size(fs_info);
+	/*
+	 * The global block rsv is based on the size of the extent tree, the
+	 * checksum tree and the root tree.  If the fs is empty we want to set
+	 * it to a minimal amount for safety.
+	 */
+	num_bytes = btrfs_root_used(&fs_info->extent_root->root_item) +
+		btrfs_root_used(&fs_info->csum_root->root_item) +
+		btrfs_root_used(&fs_info->tree_root->root_item);
+	num_bytes = max_t(u64, num_bytes, SZ_16M);
 
 	spin_lock(&sinfo->lock);
 	spin_lock(&block_rsv->lock);
@@ -5554,7 +5746,13 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
 				  struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_block_rsv *src_rsv = get_block_rsv(trans, root);
+	/*
+	 * We always use trans->block_rsv here as we will have reserved space
+	 * for our orphan when starting the transaction, using get_block_rsv()
+	 * here will sometimes make us choose the wrong block rsv as we could be
+	 * doing a reloc inode for a non refcounted root.
+	 */
+	struct btrfs_block_rsv *src_rsv = trans->block_rsv;
 	struct btrfs_block_rsv *dst_rsv = root->orphan_block_rsv;
 
 	/*
@@ -5565,7 +5763,7 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
 	u64 num_bytes = btrfs_calc_trans_metadata_size(root, 1);
 	trace_btrfs_space_reservation(root->fs_info, "orphan",
 				      btrfs_ino(inode), num_bytes, 1);
-	return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
+	return btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
 }
 
 void btrfs_orphan_release_metadata(struct inode *inode)
@@ -5620,7 +5818,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				  BTRFS_RESERVE_FLUSH_ALL);
 
 	if (ret == -ENOSPC && use_global_rsv)
-		ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes);
+		ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, 1);
 
 	if (ret && *qgroup_reserved)
 		btrfs_qgroup_free_meta(root, *qgroup_reserved);
@@ -5730,21 +5928,26 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	u64 to_reserve = 0;
 	u64 csum_bytes;
 	unsigned nr_extents = 0;
-	int extra_reserve = 0;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
 	int ret = 0;
 	bool delalloc_lock = true;
 	u64 to_free = 0;
 	unsigned dropped;
+	bool release_extra = false;
 
 	/* If we are a free space inode we need to not flush since we will be in
 	 * the middle of a transaction commit.  We also don't need the delalloc
 	 * mutex since we won't race with anybody.  We need this mostly to make
 	 * lockdep shut its filthy mouth.
+	 *
+	 * If we have a transaction open (can happen if we call truncate_block
+	 * from truncate), then we need FLUSH_LIMIT so we don't deadlock.
 	 */
 	if (btrfs_is_free_space_inode(inode)) {
 		flush = BTRFS_RESERVE_NO_FLUSH;
 		delalloc_lock = false;
+	} else if (current->journal_info) {
+		flush = BTRFS_RESERVE_FLUSH_LIMIT;
 	}
 
 	if (flush != BTRFS_RESERVE_NO_FLUSH &&
@@ -5761,24 +5964,15 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 					 BTRFS_MAX_EXTENT_SIZE - 1,
 					 BTRFS_MAX_EXTENT_SIZE);
 	BTRFS_I(inode)->outstanding_extents += nr_extents;
-	nr_extents = 0;
 
+	nr_extents = 0;
 	if (BTRFS_I(inode)->outstanding_extents >
 	    BTRFS_I(inode)->reserved_extents)
-		nr_extents = BTRFS_I(inode)->outstanding_extents -
+		nr_extents += BTRFS_I(inode)->outstanding_extents -
 			BTRFS_I(inode)->reserved_extents;
 
-	/*
-	 * Add an item to reserve for updating the inode when we complete the
-	 * delalloc io.
-	 */
-	if (!test_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-		      &BTRFS_I(inode)->runtime_flags)) {
-		nr_extents++;
-		extra_reserve = 1;
-	}
-
-	to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
+	/* We always want to reserve a slot for updating the inode. */
+	to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents + 1);
 	to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
 	csum_bytes = BTRFS_I(inode)->csum_bytes;
 	spin_unlock(&BTRFS_I(inode)->lock);
@@ -5790,17 +5984,17 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 			goto out_fail;
 	}
 
-	ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
+	ret = btrfs_block_rsv_add(root, block_rsv, to_reserve, flush);
 	if (unlikely(ret)) {
 		btrfs_qgroup_free_meta(root, nr_extents * root->nodesize);
 		goto out_fail;
 	}
 
 	spin_lock(&BTRFS_I(inode)->lock);
-	if (extra_reserve) {
-		set_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-			&BTRFS_I(inode)->runtime_flags);
-		nr_extents--;
+	if (test_and_set_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
+			     &BTRFS_I(inode)->runtime_flags)) {
+		to_reserve -= btrfs_calc_trans_metadata_size(root, 1);
+		release_extra = true;
 	}
 	BTRFS_I(inode)->reserved_extents += nr_extents;
 	spin_unlock(&BTRFS_I(inode)->lock);
@@ -5811,8 +6005,10 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	if (to_reserve)
 		trace_btrfs_space_reservation(root->fs_info, "delalloc",
 					      btrfs_ino(inode), to_reserve, 1);
-	block_rsv_add_bytes(block_rsv, to_reserve, 1);
-
+	if (release_extra)
+		btrfs_block_rsv_release(root, block_rsv,
+					btrfs_calc_trans_metadata_size(root,
+								       1));
 	return 0;
 
 out_fail:
@@ -6044,6 +6240,9 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 			spin_unlock(&cache->lock);
 			spin_unlock(&cache->space_info->lock);
 
+			trace_btrfs_space_reservation(root->fs_info, "pinned",
+						      cache->space_info->flags,
+						      num_bytes, 1);
 			set_extent_dirty(info->pinned_extents,
 					 bytenr, bytenr + num_bytes - 1,
 					 GFP_NOFS | __GFP_NOFAIL);
@@ -6118,10 +6317,10 @@ static int pin_down_extent(struct btrfs_root *root,
 	spin_unlock(&cache->lock);
 	spin_unlock(&cache->space_info->lock);
 
+	trace_btrfs_space_reservation(root->fs_info, "pinned",
+				      cache->space_info->flags, num_bytes, 1);
 	set_extent_dirty(root->fs_info->pinned_extents, bytenr,
 			 bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL);
-	if (reserved)
-		trace_btrfs_reserved_extent_free(root, bytenr, num_bytes);
 	return 0;
 }
 
@@ -6476,6 +6675,9 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end,
 		spin_lock(&cache->lock);
 		cache->pinned -= len;
 		space_info->bytes_pinned -= len;
+
+		trace_btrfs_space_reservation(fs_info, "pinned",
+					      space_info->flags, len, 0);
 		space_info->max_extent_size = 0;
 		percpu_counter_add(&space_info->total_bytes_pinned, -len);
 		if (cache->ro) {
@@ -6483,17 +6685,29 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end,
 			readonly = true;
 		}
 		spin_unlock(&cache->lock);
-		if (!readonly && global_rsv->space_info == space_info) {
+		if (!readonly && return_free_space &&
+		    global_rsv->space_info == space_info) {
+			u64 to_add = len;
+			WARN_ON(!return_free_space);
 			spin_lock(&global_rsv->lock);
 			if (!global_rsv->full) {
-				len = min(len, global_rsv->size -
-					  global_rsv->reserved);
-				global_rsv->reserved += len;
-				space_info->bytes_may_use += len;
+				to_add = min(len, global_rsv->size -
+					     global_rsv->reserved);
+				global_rsv->reserved += to_add;
+				space_info->bytes_may_use += to_add;
 				if (global_rsv->reserved >= global_rsv->size)
 					global_rsv->full = 1;
+				trace_btrfs_space_reservation(fs_info,
+							      "space_info",
+							      space_info->flags,
+							      to_add, 1);
+				len -= to_add;
 			}
 			spin_unlock(&global_rsv->lock);
+			/* Add to any tickets we may have */
+			if (len)
+				space_info_add_new_bytes(fs_info, space_info,
+							 len);
 		}
 		spin_unlock(&space_info->lock);
 	}
@@ -7782,12 +7996,10 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root,
 			ret = btrfs_discard_extent(root, start, len, NULL);
 		btrfs_add_free_space(cache, start, len);
 		btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc);
+		trace_btrfs_reserved_extent_free(root, start, len);
 	}
 
 	btrfs_put_block_group(cache);
-
-	trace_btrfs_reserved_extent_free(root, start, len);
-
 	return ret;
 }
 
@@ -9791,13 +10003,15 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		space_info = list_entry(info->space_info.next,
 					struct btrfs_space_info,
 					list);
-		if (btrfs_test_opt(info->tree_root, ENOSPC_DEBUG)) {
-			if (WARN_ON(space_info->bytes_pinned > 0 ||
+
+		/*
+		 * Do not hide this behind enospc_debug, this is actually
+		 * important and indicates a real bug if this happens.
+		 */
+		if (WARN_ON(space_info->bytes_pinned > 0 ||
 			    space_info->bytes_reserved > 0 ||
-			    space_info->bytes_may_use > 0)) {
-				dump_space_info(space_info, 0, 0);
-			}
-		}
+			    space_info->bytes_may_use > 0))
+			dump_space_info(space_info, 0, 0);
 		list_del(&space_info->list);
 		for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
 			struct kobject *kobj;
@@ -10005,9 +10219,10 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 			goto error;
 		}
 
+		trace_btrfs_add_block_group(root->fs_info, cache, 0);
 		ret = update_space_info(info, cache->flags, found_key.offset,
 					btrfs_block_group_used(&cache->item),
-					&space_info);
+					cache->bytes_super, &space_info);
 		if (ret) {
 			btrfs_remove_free_space_cache(cache);
 			spin_lock(&info->block_group_cache_lock);
@@ -10020,9 +10235,6 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		}
 
 		cache->space_info = space_info;
-		spin_lock(&cache->space_info->lock);
-		cache->space_info->bytes_readonly += cache->bytes_super;
-		spin_unlock(&cache->space_info->lock);
 
 		__link_block_group(space_info, cache);
 
@@ -10114,7 +10326,6 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	int ret;
 	struct btrfs_root *extent_root;
 	struct btrfs_block_group_cache *cache;
-
 	extent_root = root->fs_info->extent_root;
 
 	btrfs_set_log_full_commit(root->fs_info, trans);
@@ -10160,7 +10371,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	 * assigned to our block group, but don't update its counters just yet.
 	 * We want our bg to be added to the rbtree with its ->space_info set.
 	 */
-	ret = update_space_info(root->fs_info, cache->flags, 0, 0,
+	ret = update_space_info(root->fs_info, cache->flags, 0, 0, 0,
 				&cache->space_info);
 	if (ret) {
 		btrfs_remove_free_space_cache(cache);
@@ -10179,8 +10390,9 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	 * Now that our block group has its ->space_info set and is inserted in
 	 * the rbtree, update the space info's counters.
 	 */
+	trace_btrfs_add_block_group(root->fs_info, cache, 1);
 	ret = update_space_info(root->fs_info, cache->flags, size, bytes_used,
-				&cache->space_info);
+				cache->bytes_super, &cache->space_info);
 	if (ret) {
 		btrfs_remove_free_space_cache(cache);
 		spin_lock(&root->fs_info->block_group_cache_lock);
@@ -10193,16 +10405,11 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	}
 	update_global_block_rsv(root->fs_info);
 
-	spin_lock(&cache->space_info->lock);
-	cache->space_info->bytes_readonly += cache->bytes_super;
-	spin_unlock(&cache->space_info->lock);
-
 	__link_block_group(cache->space_info, cache);
 
 	list_add_tail(&cache->bg_list, &trans->new_bgs);
 
 	set_avail_alloc_bits(extent_root->fs_info, type);
-
 	return 0;
 }
 
@@ -10747,21 +10954,21 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
 		mixed = 1;
 
 	flags = BTRFS_BLOCK_GROUP_SYSTEM;
-	ret = update_space_info(fs_info, flags, 0, 0, &space_info);
+	ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
 	if (ret)
 		goto out;
 
 	if (mixed) {
 		flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA;
-		ret = update_space_info(fs_info, flags, 0, 0, &space_info);
+		ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
 	} else {
 		flags = BTRFS_BLOCK_GROUP_METADATA;
-		ret = update_space_info(fs_info, flags, 0, 0, &space_info);
+		ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
 		if (ret)
 			goto out;
 
 		flags = BTRFS_BLOCK_GROUP_DATA;
-		ret = update_space_info(fs_info, flags, 0, 0, &space_info);
+		ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
 	}
 out:
 	return ret;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 2234e88cf674..bcfb4a27ddd4 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1629,13 +1629,11 @@ again:
 		 * managed to copy.
 		 */
 		if (num_sectors > dirty_sectors) {
-			/*
-			 * we round down because we don't want to count
-			 * any partial blocks actually sent through the
-			 * IO machines
-			 */
-			release_bytes = round_down(release_bytes - copied,
-				      root->sectorsize);
+
+			/* release everything except the sectors we dirtied */
+			release_bytes -= dirty_sectors <<
+				root->fs_info->sb->s_blocksize_bits;
+
 			if (copied > 0) {
 				spin_lock(&BTRFS_I(inode)->lock);
 				BTRFS_I(inode)->outstanding_extents++;
@@ -2479,7 +2477,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	}
 
 	ret = btrfs_block_rsv_migrate(&root->fs_info->trans_block_rsv, rsv,
-				      min_size);
+				      min_size, 0);
 	BUG_ON(ret);
 	trans->block_rsv = rsv;
 
@@ -2522,7 +2520,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		}
 
 		ret = btrfs_block_rsv_migrate(&root->fs_info->trans_block_rsv,
-					      rsv, min_size);
+					      rsv, min_size, 0);
 		BUG_ON(ret);	/* shouldn't happen */
 		trans->block_rsv = rsv;
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index df731c0ebec7..8078077d1090 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5263,7 +5263,7 @@ void btrfs_evict_inode(struct inode *inode)
 		if (steal_from_global) {
 			if (!btrfs_check_space_for_delayed_refs(trans, root))
 				ret = btrfs_block_rsv_migrate(global_rsv, rsv,
-							      min_size);
+							      min_size, 0);
 			else
 				ret = -ENOSPC;
 		}
@@ -9116,7 +9116,7 @@ static int btrfs_truncate(struct inode *inode)
 
 	/* Migrate the slack space for the truncate to our reserve */
 	ret = btrfs_block_rsv_migrate(&root->fs_info->trans_block_rsv, rsv,
-				      min_size);
+				      min_size, 0);
 	BUG_ON(ret);
 
 	/*
@@ -9156,7 +9156,7 @@ static int btrfs_truncate(struct inode *inode)
 		}
 
 		ret = btrfs_block_rsv_migrate(&root->fs_info->trans_block_rsv,
-					      rsv, min_size);
+					      rsv, min_size, 0);
 		BUG_ON(ret);	/* shouldn't happen */
 		trans->block_rsv = rsv;
 	}
@@ -9177,7 +9177,6 @@ static int btrfs_truncate(struct inode *inode)
 		ret = btrfs_end_transaction(trans, root);
 		btrfs_btree_balance_dirty(root);
 	}
-
 out:
 	btrfs_free_block_rsv(root, rsv);
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 0477dca154ed..fc067b07e31f 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2604,25 +2604,28 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans,
 
 	trans->block_rsv = rc->block_rsv;
 	rc->reserved_bytes += num_bytes;
+
+	/*
+	 * We are under a transaction here so we can only do limited flushing.
+	 * If we get an enospc just kick back -EAGAIN so we know to drop the
+	 * transaction and try to refill when we can flush all the things.
+	 */
 	ret = btrfs_block_rsv_refill(root, rc->block_rsv, num_bytes,
-				BTRFS_RESERVE_FLUSH_ALL);
+				BTRFS_RESERVE_FLUSH_LIMIT);
 	if (ret) {
-		if (ret == -EAGAIN) {
-			tmp = rc->extent_root->nodesize *
-				RELOCATION_RESERVED_NODES;
-			while (tmp <= rc->reserved_bytes)
-				tmp <<= 1;
-			/*
-			 * only one thread can access block_rsv at this point,
-			 * so we don't need hold lock to protect block_rsv.
-			 * we expand more reservation size here to allow enough
-			 * space for relocation and we will return earlier in
-			 * enospc case.
-			 */
-			rc->block_rsv->size = tmp + rc->extent_root->nodesize *
-					      RELOCATION_RESERVED_NODES;
-		}
-		return ret;
+		tmp = rc->extent_root->nodesize * RELOCATION_RESERVED_NODES;
+		while (tmp <= rc->reserved_bytes)
+			tmp <<= 1;
+		/*
+		 * only one thread can access block_rsv at this point,
+		 * so we don't need hold lock to protect block_rsv.
+		 * we expand more reservation size here to allow enough
+		 * space for relocation and we will return eailer in
+		 * enospc case.
+		 */
+		rc->block_rsv->size = tmp + rc->extent_root->nodesize *
+			RELOCATION_RESERVED_NODES;
+		return -EAGAIN;
 	}
 
 	return 0;
@@ -3871,6 +3874,7 @@ static noinline_for_stack
 int prepare_to_relocate(struct reloc_control *rc)
 {
 	struct btrfs_trans_handle *trans;
+	int ret;
 
 	rc->block_rsv = btrfs_alloc_block_rsv(rc->extent_root,
 					      BTRFS_BLOCK_RSV_TEMP);
@@ -3885,6 +3889,11 @@ int prepare_to_relocate(struct reloc_control *rc)
 	rc->reserved_bytes = 0;
 	rc->block_rsv->size = rc->extent_root->nodesize *
 			      RELOCATION_RESERVED_NODES;
+	ret = btrfs_block_rsv_refill(rc->extent_root,
+				     rc->block_rsv, rc->block_rsv->size,
+				     BTRFS_RESERVE_FLUSH_ALL);
+	if (ret)
+		return ret;
 
 	rc->create_reloc_tree = 1;
 	set_reloc_control(rc);
@@ -4643,7 +4652,7 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
 	if (rc->merge_reloc_tree) {
 		ret = btrfs_block_rsv_migrate(&pending->block_rsv,
 					      rc->block_rsv,
-					      rc->nodes_relocated);
+					      rc->nodes_relocated, 1);
 		if (ret)
 			return ret;
 	}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 26a9d10d75e9..d5b6f959a3c3 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1730,7 +1730,8 @@ enum {
 	POOL_WRITE	= 2,
 };
 
-static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
+static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
+				s64 pool, struct ceph_string *pool_ns)
 {
 	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -1738,6 +1739,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
 	struct rb_node **p, *parent;
 	struct ceph_pool_perm *perm;
 	struct page **pages;
+	size_t pool_ns_len;
 	int err = 0, err2 = 0, have = 0;
 
 	down_read(&mdsc->pool_perm_rwsem);
@@ -1749,17 +1751,31 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
 		else if (pool > perm->pool)
 			p = &(*p)->rb_right;
 		else {
-			have = perm->perm;
-			break;
+			int ret = ceph_compare_string(pool_ns,
+						perm->pool_ns,
+						perm->pool_ns_len);
+			if (ret < 0)
+				p = &(*p)->rb_left;
+			else if (ret > 0)
+				p = &(*p)->rb_right;
+			else {
+				have = perm->perm;
+				break;
+			}
 		}
 	}
 	up_read(&mdsc->pool_perm_rwsem);
 	if (*p)
 		goto out;
 
-	dout("__ceph_pool_perm_get pool %u no perm cached\n", pool);
+	if (pool_ns)
+		dout("__ceph_pool_perm_get pool %lld ns %.*s no perm cached\n",
+		     pool, (int)pool_ns->len, pool_ns->str);
+	else
+		dout("__ceph_pool_perm_get pool %lld no perm cached\n", pool);
 
 	down_write(&mdsc->pool_perm_rwsem);
+	p = &mdsc->pool_perm_tree.rb_node;
 	parent = NULL;
 	while (*p) {
 		parent = *p;
@@ -1769,8 +1785,17 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
 		else if (pool > perm->pool)
 			p = &(*p)->rb_right;
 		else {
-			have = perm->perm;
-			break;
+			int ret = ceph_compare_string(pool_ns,
+						perm->pool_ns,
+						perm->pool_ns_len);
+			if (ret < 0)
+				p = &(*p)->rb_left;
+			else if (ret > 0)
+				p = &(*p)->rb_right;
+			else {
+				have = perm->perm;
+				break;
+			}
 		}
 	}
 	if (*p) {
@@ -1788,6 +1813,8 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
 	rd_req->r_flags = CEPH_OSD_FLAG_READ;
 	osd_req_op_init(rd_req, 0, CEPH_OSD_OP_STAT, 0);
 	rd_req->r_base_oloc.pool = pool;
+	if (pool_ns)
+		rd_req->r_base_oloc.pool_ns = ceph_get_string(pool_ns);
 	ceph_oid_printf(&rd_req->r_base_oid, "%llx.00000000", ci->i_vino.ino);
 
 	err = ceph_osdc_alloc_messages(rd_req, GFP_NOFS);
@@ -1841,7 +1868,8 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
 		goto out_unlock;
 	}
 
-	perm = kmalloc(sizeof(*perm), GFP_NOFS);
+	pool_ns_len = pool_ns ? pool_ns->len : 0;
+	perm = kmalloc(sizeof(*perm) + pool_ns_len + 1, GFP_NOFS);
 	if (!perm) {
 		err = -ENOMEM;
 		goto out_unlock;
@@ -1849,6 +1877,11 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
 
 	perm->pool = pool;
 	perm->perm = have;
+	perm->pool_ns_len = pool_ns_len;
+	if (pool_ns_len > 0)
+		memcpy(perm->pool_ns, pool_ns->str, pool_ns_len);
+	perm->pool_ns[pool_ns_len] = 0;
+
 	rb_link_node(&perm->node, parent, p);
 	rb_insert_color(&perm->node, &mdsc->pool_perm_tree);
 	err = 0;
@@ -1860,43 +1893,46 @@ out_unlock:
 out:
 	if (!err)
 		err = have;
-	dout("__ceph_pool_perm_get pool %u result = %d\n", pool, err);
+	if (pool_ns)
+		dout("__ceph_pool_perm_get pool %lld ns %.*s result = %d\n",
+		     pool, (int)pool_ns->len, pool_ns->str, err);
+	else
+		dout("__ceph_pool_perm_get pool %lld result = %d\n", pool, err);
 	return err;
 }
 
 int ceph_pool_perm_check(struct ceph_inode_info *ci, int need)
 {
-	u32 pool;
+	s64 pool;
+	struct ceph_string *pool_ns;
 	int ret, flags;
 
-	/* does not support pool namespace yet */
-	if (ci->i_pool_ns_len)
-		return -EIO;
-
 	if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode),
 				NOPOOLPERM))
 		return 0;
 
 	spin_lock(&ci->i_ceph_lock);
 	flags = ci->i_ceph_flags;
-	pool = ceph_file_layout_pg_pool(ci->i_layout);
+	pool = ci->i_layout.pool_id;
 	spin_unlock(&ci->i_ceph_lock);
 check:
 	if (flags & CEPH_I_POOL_PERM) {
 		if ((need & CEPH_CAP_FILE_RD) && !(flags & CEPH_I_POOL_RD)) {
-			dout("ceph_pool_perm_check pool %u no read perm\n",
+			dout("ceph_pool_perm_check pool %lld no read perm\n",
 			     pool);
 			return -EPERM;
 		}
 		if ((need & CEPH_CAP_FILE_WR) && !(flags & CEPH_I_POOL_WR)) {
-			dout("ceph_pool_perm_check pool %u no write perm\n",
+			dout("ceph_pool_perm_check pool %lld no write perm\n",
 			     pool);
 			return -EPERM;
 		}
 		return 0;
 	}
 
-	ret = __ceph_pool_perm_get(ci, pool);
+	pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
+	ret = __ceph_pool_perm_get(ci, pool, pool_ns);
+	ceph_put_string(pool_ns);
 	if (ret < 0)
 		return ret;
 
@@ -1907,10 +1943,11 @@ check:
 		flags |= CEPH_I_POOL_WR;
 
 	spin_lock(&ci->i_ceph_lock);
-	if (pool == ceph_file_layout_pg_pool(ci->i_layout)) {
-		ci->i_ceph_flags = flags;
+	if (pool == ci->i_layout.pool_id &&
+	    pool_ns == rcu_dereference_raw(ci->i_layout.pool_ns)) {
+		ci->i_ceph_flags |= flags;
         } else {
-		pool = ceph_file_layout_pg_pool(ci->i_layout);
+		pool = ci->i_layout.pool_id;
 		flags = ci->i_ceph_flags;
 	}
 	spin_unlock(&ci->i_ceph_lock);
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 238c55b01723..5bc5d37b1217 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -71,7 +71,7 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
 					      &ceph_fscache_fsid_object_def,
 					      fsc, true);
 	if (!fsc->fscache)
-		pr_err("Unable to resgister fsid: %p fscache cookie", fsc);
+		pr_err("Unable to register fsid: %p fscache cookie\n", fsc);
 
 	return 0;
 }
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 6f60d0a3d0f9..99115cae1652 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -40,6 +40,11 @@
  * cluster to release server state.
  */
 
+static u64 __get_oldest_flush_tid(struct ceph_mds_client *mdsc);
+static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
+				 struct ceph_mds_session *session,
+				 struct ceph_inode_info *ci,
+				 u64 oldest_flush_tid);
 
 /*
  * Generate readable cap strings for debugging output.
@@ -849,12 +854,14 @@ int __ceph_caps_used(struct ceph_inode_info *ci)
  */
 int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
 {
-	int want = 0;
-	int mode;
-	for (mode = 0; mode < CEPH_FILE_MODE_NUM; mode++)
-		if (ci->i_nr_by_mode[mode])
-			want |= ceph_caps_for_mode(mode);
-	return want;
+	int i, bits = 0;
+	for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
+		if (ci->i_nr_by_mode[i])
+			bits |= 1 << i;
+	}
+	if (bits == 0)
+		return 0;
+	return ceph_caps_for_mode(bits >> 1);
 }
 
 /*
@@ -991,7 +998,7 @@ static int send_cap_msg(struct ceph_mds_session *session,
 			u32 seq, u64 flush_tid, u64 oldest_flush_tid,
 			u32 issue_seq, u32 mseq, u64 size, u64 max_size,
 			struct timespec *mtime, struct timespec *atime,
-			struct timespec *ctime, u64 time_warp_seq,
+			struct timespec *ctime, u32 time_warp_seq,
 			kuid_t uid, kgid_t gid, umode_t mode,
 			u64 xattr_version,
 			struct ceph_buffer *xattrs_buf,
@@ -1116,8 +1123,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	struct inode *inode = &ci->vfs_inode;
 	u64 cap_id = cap->cap_id;
 	int held, revoking, dropping, keep;
-	u64 seq, issue_seq, mseq, time_warp_seq, follows;
-	u64 size, max_size;
+	u64 follows, size, max_size;
+	u32 seq, issue_seq, mseq, time_warp_seq;
 	struct timespec mtime, atime, ctime;
 	int wake = 0;
 	umode_t mode;
@@ -1215,6 +1222,22 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	return delayed;
 }
 
+static inline int __send_flush_snap(struct inode *inode,
+				    struct ceph_mds_session *session,
+				    struct ceph_cap_snap *capsnap,
+				    u32 mseq, u64 oldest_flush_tid)
+{
+	return send_cap_msg(session, ceph_vino(inode).ino, 0,
+			CEPH_CAP_OP_FLUSHSNAP, capsnap->issued, 0,
+			capsnap->dirty, 0, capsnap->cap_flush.tid,
+			oldest_flush_tid, 0, mseq, capsnap->size, 0,
+			&capsnap->mtime, &capsnap->atime,
+			&capsnap->ctime, capsnap->time_warp_seq,
+			capsnap->uid, capsnap->gid, capsnap->mode,
+			capsnap->xattr_version, capsnap->xattr_blob,
+			capsnap->follows, capsnap->inline_data);
+}
+
 /*
  * When a snapshot is taken, clients accumulate dirty metadata on
  * inodes with capabilities in ceph_cap_snaps to describe the file
@@ -1222,37 +1245,22 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
  * asynchronously back to the MDS once sync writes complete and dirty
  * data is written out.
  *
- * Unless @kick is true, skip cap_snaps that were already sent to
- * the MDS (i.e., during this session).
- *
  * Called under i_ceph_lock.  Takes s_mutex as needed.
  */
-void __ceph_flush_snaps(struct ceph_inode_info *ci,
-			struct ceph_mds_session **psession,
-			int kick)
+static void __ceph_flush_snaps(struct ceph_inode_info *ci,
+			       struct ceph_mds_session *session)
 		__releases(ci->i_ceph_lock)
 		__acquires(ci->i_ceph_lock)
 {
 	struct inode *inode = &ci->vfs_inode;
-	int mds;
+	struct ceph_mds_client *mdsc = session->s_mdsc;
 	struct ceph_cap_snap *capsnap;
-	u32 mseq;
-	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
-	struct ceph_mds_session *session = NULL; /* if session != NULL, we hold
-						    session->s_mutex */
-	u64 next_follows = 0;  /* keep track of how far we've gotten through the
-			     i_cap_snaps list, and skip these entries next time
-			     around to avoid an infinite loop */
+	u64 oldest_flush_tid = 0;
+	u64 first_tid = 1, last_tid = 0;
 
-	if (psession)
-		session = *psession;
+	dout("__flush_snaps %p session %p\n", inode, session);
 
-	dout("__flush_snaps %p\n", inode);
-retry:
 	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
-		/* avoid an infiniute loop after retry */
-		if (capsnap->follows < next_follows)
-			continue;
 		/*
 		 * we need to wait for sync writes to complete and for dirty
 		 * pages to be written out.
@@ -1263,97 +1271,129 @@ retry:
 		/* should be removed by ceph_try_drop_cap_snap() */
 		BUG_ON(!capsnap->need_flush);
 
-		/* pick mds, take s_mutex */
-		if (ci->i_auth_cap == NULL) {
-			dout("no auth cap (migrating?), doing nothing\n");
-			goto out;
-		}
-
 		/* only flush each capsnap once */
-		if (!kick && !list_empty(&capsnap->flushing_item)) {
-			dout("already flushed %p, skipping\n", capsnap);
+		if (capsnap->cap_flush.tid > 0) {
+			dout(" already flushed %p, skipping\n", capsnap);
 			continue;
 		}
 
-		mds = ci->i_auth_cap->session->s_mds;
-		mseq = ci->i_auth_cap->mseq;
+		spin_lock(&mdsc->cap_dirty_lock);
+		capsnap->cap_flush.tid = ++mdsc->last_cap_flush_tid;
+		list_add_tail(&capsnap->cap_flush.g_list,
+			      &mdsc->cap_flush_list);
+		if (oldest_flush_tid == 0)
+			oldest_flush_tid = __get_oldest_flush_tid(mdsc);
+		if (list_empty(&ci->i_flushing_item)) {
+			list_add_tail(&ci->i_flushing_item,
+				      &session->s_cap_flushing);
+		}
+		spin_unlock(&mdsc->cap_dirty_lock);
+
+		list_add_tail(&capsnap->cap_flush.i_list,
+			      &ci->i_cap_flush_list);
 
-		if (session && session->s_mds != mds) {
-			dout("oops, wrong session %p mutex\n", session);
-			if (kick)
-				goto out;
+		if (first_tid == 1)
+			first_tid = capsnap->cap_flush.tid;
+		last_tid = capsnap->cap_flush.tid;
+	}
 
-			mutex_unlock(&session->s_mutex);
-			ceph_put_mds_session(session);
-			session = NULL;
+	ci->i_ceph_flags &= ~CEPH_I_FLUSH_SNAPS;
+
+	while (first_tid <= last_tid) {
+		struct ceph_cap *cap = ci->i_auth_cap;
+		struct ceph_cap_flush *cf;
+		int ret;
+
+		if (!(cap && cap->session == session)) {
+			dout("__flush_snaps %p auth cap %p not mds%d, "
+			     "stop\n", inode, cap, session->s_mds);
+			break;
 		}
-		if (!session) {
-			spin_unlock(&ci->i_ceph_lock);
-			mutex_lock(&mdsc->mutex);
-			session = __ceph_lookup_mds_session(mdsc, mds);
-			mutex_unlock(&mdsc->mutex);
-			if (session) {
-				dout("inverting session/ino locks on %p\n",
-				     session);
-				mutex_lock(&session->s_mutex);
+
+		ret = -ENOENT;
+		list_for_each_entry(cf, &ci->i_cap_flush_list, i_list) {
+			if (cf->tid >= first_tid) {
+				ret = 0;
+				break;
 			}
-			/*
-			 * if session == NULL, we raced against a cap
-			 * deletion or migration.  retry, and we'll
-			 * get a better @mds value next time.
-			 */
-			spin_lock(&ci->i_ceph_lock);
-			goto retry;
 		}
+		if (ret < 0)
+			break;
 
-		spin_lock(&mdsc->cap_dirty_lock);
-		capsnap->flush_tid = ++mdsc->last_cap_flush_tid;
-		spin_unlock(&mdsc->cap_dirty_lock);
+		first_tid = cf->tid + 1;
 
+		capsnap = container_of(cf, struct ceph_cap_snap, cap_flush);
 		atomic_inc(&capsnap->nref);
-		if (list_empty(&capsnap->flushing_item))
-			list_add_tail(&capsnap->flushing_item,
-				      &session->s_cap_snaps_flushing);
 		spin_unlock(&ci->i_ceph_lock);
 
-		dout("flush_snaps %p cap_snap %p follows %lld tid %llu\n",
-		     inode, capsnap, capsnap->follows, capsnap->flush_tid);
-		send_cap_msg(session, ceph_vino(inode).ino, 0,
-			     CEPH_CAP_OP_FLUSHSNAP, capsnap->issued, 0,
-			     capsnap->dirty, 0, capsnap->flush_tid, 0,
-			     0, mseq, capsnap->size, 0,
-			     &capsnap->mtime, &capsnap->atime,
-			     &capsnap->ctime, capsnap->time_warp_seq,
-			     capsnap->uid, capsnap->gid, capsnap->mode,
-			     capsnap->xattr_version, capsnap->xattr_blob,
-			     capsnap->follows, capsnap->inline_data);
-
-		next_follows = capsnap->follows + 1;
-		ceph_put_cap_snap(capsnap);
+		dout("__flush_snaps %p capsnap %p tid %llu %s\n",
+		     inode, capsnap, cf->tid, ceph_cap_string(capsnap->dirty));
+
+		ret = __send_flush_snap(inode, session, capsnap, cap->mseq,
+					oldest_flush_tid);
+		if (ret < 0) {
+			pr_err("__flush_snaps: error sending cap flushsnap, "
+			       "ino (%llx.%llx) tid %llu follows %llu\n",
+				ceph_vinop(inode), cf->tid, capsnap->follows);
+		}
 
+		ceph_put_cap_snap(capsnap);
 		spin_lock(&ci->i_ceph_lock);
-		goto retry;
 	}
+}
 
-	/* we flushed them all; remove this inode from the queue */
-	spin_lock(&mdsc->snap_flush_lock);
-	list_del_init(&ci->i_snap_flush_item);
-	spin_unlock(&mdsc->snap_flush_lock);
+void ceph_flush_snaps(struct ceph_inode_info *ci,
+		      struct ceph_mds_session **psession)
+{
+	struct inode *inode = &ci->vfs_inode;
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_session *session = *psession;
+	int mds;
+	dout("ceph_flush_snaps %p\n", inode);
+retry:
+	spin_lock(&ci->i_ceph_lock);
+	if (!(ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)) {
+		dout(" no capsnap needs flush, doing nothing\n");
+		goto out;
+	}
+	if (!ci->i_auth_cap) {
+		dout(" no auth cap (migrating?), doing nothing\n");
+		goto out;
+	}
 
-out:
-	if (psession)
-		*psession = session;
-	else if (session) {
+	mds = ci->i_auth_cap->session->s_mds;
+	if (session && session->s_mds != mds) {
+		dout(" oops, wrong session %p mutex\n", session);
 		mutex_unlock(&session->s_mutex);
 		ceph_put_mds_session(session);
+		session = NULL;
+	}
+	if (!session) {
+		spin_unlock(&ci->i_ceph_lock);
+		mutex_lock(&mdsc->mutex);
+		session = __ceph_lookup_mds_session(mdsc, mds);
+		mutex_unlock(&mdsc->mutex);
+		if (session) {
+			dout(" inverting session/ino locks on %p\n", session);
+			mutex_lock(&session->s_mutex);
+		}
+		goto retry;
 	}
-}
 
-static void ceph_flush_snaps(struct ceph_inode_info *ci)
-{
-	spin_lock(&ci->i_ceph_lock);
-	__ceph_flush_snaps(ci, NULL, 0);
+	__ceph_flush_snaps(ci, session);
+out:
 	spin_unlock(&ci->i_ceph_lock);
+
+	if (psession) {
+		*psession = session;
+	} else {
+		mutex_unlock(&session->s_mutex);
+		ceph_put_mds_session(session);
+	}
+	/* we flushed them all; remove this inode from the queue */
+	spin_lock(&mdsc->snap_flush_lock);
+	list_del_init(&ci->i_snap_flush_item);
+	spin_unlock(&mdsc->snap_flush_lock);
 }
 
 /*
@@ -1411,52 +1451,6 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
 	return dirty;
 }
 
-static void __add_cap_flushing_to_inode(struct ceph_inode_info *ci,
-					struct ceph_cap_flush *cf)
-{
-	struct rb_node **p = &ci->i_cap_flush_tree.rb_node;
-	struct rb_node *parent = NULL;
-	struct ceph_cap_flush *other = NULL;
-
-	while (*p) {
-		parent = *p;
-		other = rb_entry(parent, struct ceph_cap_flush, i_node);
-
-		if (cf->tid < other->tid)
-			p = &(*p)->rb_left;
-		else if (cf->tid > other->tid)
-			p = &(*p)->rb_right;
-		else
-			BUG();
-	}
-
-	rb_link_node(&cf->i_node, parent, p);
-	rb_insert_color(&cf->i_node, &ci->i_cap_flush_tree);
-}
-
-static void __add_cap_flushing_to_mdsc(struct ceph_mds_client *mdsc,
-				       struct ceph_cap_flush *cf)
-{
-	struct rb_node **p = &mdsc->cap_flush_tree.rb_node;
-	struct rb_node *parent = NULL;
-	struct ceph_cap_flush *other = NULL;
-
-	while (*p) {
-		parent = *p;
-		other = rb_entry(parent, struct ceph_cap_flush, g_node);
-
-		if (cf->tid < other->tid)
-			p = &(*p)->rb_left;
-		else if (cf->tid > other->tid)
-			p = &(*p)->rb_right;
-		else
-			BUG();
-	}
-
-	rb_link_node(&cf->g_node, parent, p);
-	rb_insert_color(&cf->g_node, &mdsc->cap_flush_tree);
-}
-
 struct ceph_cap_flush *ceph_alloc_cap_flush(void)
 {
 	return kmem_cache_alloc(ceph_cap_flush_cachep, GFP_KERNEL);
@@ -1470,23 +1464,54 @@ void ceph_free_cap_flush(struct ceph_cap_flush *cf)
 
 static u64 __get_oldest_flush_tid(struct ceph_mds_client *mdsc)
 {
-	struct rb_node *n = rb_first(&mdsc->cap_flush_tree);
-	if (n) {
+	if (!list_empty(&mdsc->cap_flush_list)) {
 		struct ceph_cap_flush *cf =
-			rb_entry(n, struct ceph_cap_flush, g_node);
+			list_first_entry(&mdsc->cap_flush_list,
+					 struct ceph_cap_flush, g_list);
 		return cf->tid;
 	}
 	return 0;
 }
 
 /*
+ * Remove cap_flush from the mdsc's or inode's flushing cap list.
+ * Return true if caller needs to wake up flush waiters.
+ */
+static bool __finish_cap_flush(struct ceph_mds_client *mdsc,
+			       struct ceph_inode_info *ci,
+			       struct ceph_cap_flush *cf)
+{
+	struct ceph_cap_flush *prev;
+	bool wake = cf->wake;
+	if (mdsc) {
+		/* are there older pending cap flushes? */
+		if (wake && cf->g_list.prev != &mdsc->cap_flush_list) {
+			prev = list_prev_entry(cf, g_list);
+			prev->wake = true;
+			wake = false;
+		}
+		list_del(&cf->g_list);
+	} else if (ci) {
+		if (wake && cf->i_list.prev != &ci->i_cap_flush_list) {
+			prev = list_prev_entry(cf, i_list);
+			prev->wake = true;
+			wake = false;
+		}
+		list_del(&cf->i_list);
+	} else {
+		BUG_ON(1);
+	}
+	return wake;
+}
+
+/*
  * Add dirty inode to the flushing list.  Assigned a seq number so we
  * can wait for caps to flush without starving.
  *
  * Called under i_ceph_lock.
  */
 static int __mark_caps_flushing(struct inode *inode,
-				struct ceph_mds_session *session,
+				struct ceph_mds_session *session, bool wake,
 				u64 *flush_tid, u64 *oldest_flush_tid)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
@@ -1509,26 +1534,22 @@ static int __mark_caps_flushing(struct inode *inode,
 
 	swap(cf, ci->i_prealloc_cap_flush);
 	cf->caps = flushing;
+	cf->wake = wake;
 
 	spin_lock(&mdsc->cap_dirty_lock);
 	list_del_init(&ci->i_dirty_item);
 
 	cf->tid = ++mdsc->last_cap_flush_tid;
-	__add_cap_flushing_to_mdsc(mdsc, cf);
+	list_add_tail(&cf->g_list, &mdsc->cap_flush_list);
 	*oldest_flush_tid = __get_oldest_flush_tid(mdsc);
 
 	if (list_empty(&ci->i_flushing_item)) {
 		list_add_tail(&ci->i_flushing_item, &session->s_cap_flushing);
 		mdsc->num_cap_flushing++;
-		dout(" inode %p now flushing tid %llu\n", inode, cf->tid);
-	} else {
-		list_move_tail(&ci->i_flushing_item, &session->s_cap_flushing);
-		dout(" inode %p now flushing (more) tid %llu\n",
-		     inode, cf->tid);
 	}
 	spin_unlock(&mdsc->cap_dirty_lock);
 
-	__add_cap_flushing_to_inode(ci, cf);
+	list_add_tail(&cf->i_list, &ci->i_cap_flush_list);
 
 	*flush_tid = cf->tid;
 	return flushing;
@@ -1583,10 +1604,11 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 	int mds = -1;   /* keep track of how far we've gone through i_caps list
 			   to avoid an infinite loop on retry */
 	struct rb_node *p;
-	int tried_invalidate = 0;
-	int delayed = 0, sent = 0, force_requeue = 0, num;
-	int queue_invalidate = 0;
-	int is_delayed = flags & CHECK_CAPS_NODELAY;
+	int delayed = 0, sent = 0, num;
+	bool is_delayed = flags & CHECK_CAPS_NODELAY;
+	bool queue_invalidate = false;
+	bool force_requeue = false;
+	bool tried_invalidate = false;
 
 	/* if we are unmounting, flush any unused caps immediately. */
 	if (mdsc->stopping)
@@ -1597,9 +1619,6 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 	if (ci->i_ceph_flags & CEPH_I_FLUSH)
 		flags |= CHECK_CAPS_FLUSH;
 
-	/* flush snaps first time around only */
-	if (!list_empty(&ci->i_cap_snaps))
-		__ceph_flush_snaps(ci, &session, 0);
 	goto retry_locked;
 retry:
 	spin_lock(&ci->i_ceph_lock);
@@ -1666,17 +1685,17 @@ retry_locked:
 			if (revoking & (CEPH_CAP_FILE_CACHE|
 					CEPH_CAP_FILE_LAZYIO)) {
 				dout("check_caps queuing invalidate\n");
-				queue_invalidate = 1;
+				queue_invalidate = true;
 				ci->i_rdcache_revoking = ci->i_rdcache_gen;
 			} else {
 				dout("check_caps failed to invalidate pages\n");
 				/* we failed to invalidate pages.  check these
 				   caps again later. */
-				force_requeue = 1;
+				force_requeue = true;
 				__cap_set_timeouts(mdsc, ci);
 			}
 		}
-		tried_invalidate = 1;
+		tried_invalidate = true;
 		goto retry_locked;
 	}
 
@@ -1720,10 +1739,15 @@ retry_locked:
 			}
 		}
 		/* flush anything dirty? */
-		if (cap == ci->i_auth_cap && (flags & CHECK_CAPS_FLUSH) &&
-		    ci->i_dirty_caps) {
-			dout("flushing dirty caps\n");
-			goto ack;
+		if (cap == ci->i_auth_cap) {
+			if ((flags & CHECK_CAPS_FLUSH) && ci->i_dirty_caps) {
+				dout("flushing dirty caps\n");
+				goto ack;
+			}
+			if (ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS) {
+				dout("flushing snap caps\n");
+				goto ack;
+			}
 		}
 
 		/* completed revocation? going down and there are no caps? */
@@ -1782,6 +1806,26 @@ ack:
 				goto retry;
 			}
 		}
+
+		/* kick flushing and flush snaps before sending normal
+		 * cap message */
+		if (cap == ci->i_auth_cap &&
+		    (ci->i_ceph_flags &
+		     (CEPH_I_KICK_FLUSH | CEPH_I_FLUSH_SNAPS))) {
+			if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH) {
+				spin_lock(&mdsc->cap_dirty_lock);
+				oldest_flush_tid = __get_oldest_flush_tid(mdsc);
+				spin_unlock(&mdsc->cap_dirty_lock);
+				__kick_flushing_caps(mdsc, session, ci,
+						     oldest_flush_tid);
+				ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
+			}
+			if (ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)
+				__ceph_flush_snaps(ci, session);
+
+			goto retry_locked;
+		}
+
 		/* take snap_rwsem after session mutex */
 		if (!took_snap_rwsem) {
 			if (down_read_trylock(&mdsc->snap_rwsem) == 0) {
@@ -1796,7 +1840,7 @@ ack:
 		}
 
 		if (cap == ci->i_auth_cap && ci->i_dirty_caps) {
-			flushing = __mark_caps_flushing(inode, session,
+			flushing = __mark_caps_flushing(inode, session, false,
 							&flush_tid,
 							&oldest_flush_tid);
 		} else {
@@ -1822,7 +1866,7 @@ ack:
 	 * otherwise cancel.
 	 */
 	if (delayed && is_delayed)
-		force_requeue = 1;   /* __send_cap delayed release; requeue */
+		force_requeue = true;   /* __send_cap delayed release; requeue */
 	if (!delayed && !is_delayed)
 		__cap_delay_cancel(mdsc, ci);
 	else if (!is_delayed || force_requeue)
@@ -1873,8 +1917,8 @@ retry:
 		if (cap->session->s_state < CEPH_MDS_SESSION_OPEN)
 			goto out;
 
-		flushing = __mark_caps_flushing(inode, session, &flush_tid,
-						&oldest_flush_tid);
+		flushing = __mark_caps_flushing(inode, session, true,
+						&flush_tid, &oldest_flush_tid);
 
 		/* __send_cap drops i_ceph_lock */
 		delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, used, want,
@@ -1887,10 +1931,11 @@ retry:
 			spin_unlock(&ci->i_ceph_lock);
 		}
 	} else {
-		struct rb_node *n = rb_last(&ci->i_cap_flush_tree);
-		if (n) {
+		if (!list_empty(&ci->i_cap_flush_list)) {
 			struct ceph_cap_flush *cf =
-				rb_entry(n, struct ceph_cap_flush, i_node);
+				list_last_entry(&ci->i_cap_flush_list,
+						struct ceph_cap_flush, i_list);
+			cf->wake = true;
 			flush_tid = cf->tid;
 		}
 		flushing = ci->i_flushing_caps;
@@ -1910,14 +1955,13 @@ out:
 static int caps_are_flushed(struct inode *inode, u64 flush_tid)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_cap_flush *cf;
-	struct rb_node *n;
 	int ret = 1;
 
 	spin_lock(&ci->i_ceph_lock);
-	n = rb_first(&ci->i_cap_flush_tree);
-	if (n) {
-		cf = rb_entry(n, struct ceph_cap_flush, i_node);
+	if (!list_empty(&ci->i_cap_flush_list)) {
+		struct ceph_cap_flush * cf =
+			list_first_entry(&ci->i_cap_flush_list,
+					 struct ceph_cap_flush, i_list);
 		if (cf->tid <= flush_tid)
 			ret = 0;
 	}
@@ -1926,53 +1970,6 @@ static int caps_are_flushed(struct inode *inode, u64 flush_tid)
 }
 
 /*
- * Wait on any unsafe replies for the given inode.  First wait on the
- * newest request, and make that the upper bound.  Then, if there are
- * more requests, keep waiting on the oldest as long as it is still older
- * than the original request.
- */
-static void sync_write_wait(struct inode *inode)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct list_head *head = &ci->i_unsafe_writes;
-	struct ceph_osd_request *req;
-	u64 last_tid;
-
-	if (!S_ISREG(inode->i_mode))
-		return;
-
-	spin_lock(&ci->i_unsafe_lock);
-	if (list_empty(head))
-		goto out;
-
-	/* set upper bound as _last_ entry in chain */
-	req = list_last_entry(head, struct ceph_osd_request,
-			      r_unsafe_item);
-	last_tid = req->r_tid;
-
-	do {
-		ceph_osdc_get_request(req);
-		spin_unlock(&ci->i_unsafe_lock);
-		dout("sync_write_wait on tid %llu (until %llu)\n",
-		     req->r_tid, last_tid);
-		wait_for_completion(&req->r_safe_completion);
-		spin_lock(&ci->i_unsafe_lock);
-		ceph_osdc_put_request(req);
-
-		/*
-		 * from here on look at first entry in chain, since we
-		 * only want to wait for anything older than last_tid
-		 */
-		if (list_empty(head))
-			break;
-		req = list_first_entry(head, struct ceph_osd_request,
-				       r_unsafe_item);
-	} while (req->r_tid < last_tid);
-out:
-	spin_unlock(&ci->i_unsafe_lock);
-}
-
-/*
  * wait for any unsafe requests to complete.
  */
 static int unsafe_request_wait(struct inode *inode)
@@ -2024,7 +2021,8 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	int dirty;
 
 	dout("fsync %p%s\n", inode, datasync ? " datasync" : "");
-	sync_write_wait(inode);
+
+	ceph_sync_write_wait(inode);
 
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (ret < 0)
@@ -2087,87 +2085,74 @@ int ceph_write_inode(struct inode *inode, struct writeback_control *wbc)
 	return err;
 }
 
-/*
- * After a recovering MDS goes active, we need to resend any caps
- * we were flushing.
- *
- * Caller holds session->s_mutex.
- */
-static void kick_flushing_capsnaps(struct ceph_mds_client *mdsc,
-				   struct ceph_mds_session *session)
-{
-	struct ceph_cap_snap *capsnap;
-
-	dout("kick_flushing_capsnaps mds%d\n", session->s_mds);
-	list_for_each_entry(capsnap, &session->s_cap_snaps_flushing,
-			    flushing_item) {
-		struct ceph_inode_info *ci = capsnap->ci;
-		struct inode *inode = &ci->vfs_inode;
-		struct ceph_cap *cap;
-
-		spin_lock(&ci->i_ceph_lock);
-		cap = ci->i_auth_cap;
-		if (cap && cap->session == session) {
-			dout("kick_flushing_caps %p cap %p capsnap %p\n", inode,
-			     cap, capsnap);
-			__ceph_flush_snaps(ci, &session, 1);
-		} else {
-			pr_err("%p auth cap %p not mds%d ???\n", inode,
-			       cap, session->s_mds);
-		}
-		spin_unlock(&ci->i_ceph_lock);
-	}
-}
-
-static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
-				struct ceph_mds_session *session,
-				struct ceph_inode_info *ci)
+static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
+				 struct ceph_mds_session *session,
+				 struct ceph_inode_info *ci,
+				 u64 oldest_flush_tid)
+	__releases(ci->i_ceph_lock)
+	__acquires(ci->i_ceph_lock)
 {
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap *cap;
 	struct ceph_cap_flush *cf;
-	struct rb_node *n;
-	int delayed = 0;
+	int ret;
 	u64 first_tid = 0;
-	u64 oldest_flush_tid;
 
-	spin_lock(&mdsc->cap_dirty_lock);
-	oldest_flush_tid = __get_oldest_flush_tid(mdsc);
-	spin_unlock(&mdsc->cap_dirty_lock);
+	list_for_each_entry(cf, &ci->i_cap_flush_list, i_list) {
+		if (cf->tid < first_tid)
+			continue;
 
-	while (true) {
-		spin_lock(&ci->i_ceph_lock);
 		cap = ci->i_auth_cap;
 		if (!(cap && cap->session == session)) {
-			pr_err("%p auth cap %p not mds%d ???\n", inode,
-					cap, session->s_mds);
-			spin_unlock(&ci->i_ceph_lock);
+			pr_err("%p auth cap %p not mds%d ???\n",
+			       inode, cap, session->s_mds);
 			break;
 		}
 
-		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
-			cf = rb_entry(n, struct ceph_cap_flush, i_node);
-			if (cf->tid >= first_tid)
-				break;
-		}
-		if (!n) {
+		first_tid = cf->tid + 1;
+
+		if (cf->caps) {
+			dout("kick_flushing_caps %p cap %p tid %llu %s\n",
+			     inode, cap, cf->tid, ceph_cap_string(cf->caps));
+			ci->i_ceph_flags |= CEPH_I_NODELAY;
+			ret = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
+					  __ceph_caps_used(ci),
+					  __ceph_caps_wanted(ci),
+					  cap->issued | cap->implemented,
+					  cf->caps, cf->tid, oldest_flush_tid);
+			if (ret) {
+				pr_err("kick_flushing_caps: error sending "
+					"cap flush, ino (%llx.%llx) "
+					"tid %llu flushing %s\n",
+					ceph_vinop(inode), cf->tid,
+					ceph_cap_string(cf->caps));
+			}
+		} else {
+			struct ceph_cap_snap *capsnap =
+					container_of(cf, struct ceph_cap_snap,
+						    cap_flush);
+			dout("kick_flushing_caps %p capsnap %p tid %llu %s\n",
+			     inode, capsnap, cf->tid,
+			     ceph_cap_string(capsnap->dirty));
+
+			atomic_inc(&capsnap->nref);
 			spin_unlock(&ci->i_ceph_lock);
-			break;
-		}
 
-		cf = rb_entry(n, struct ceph_cap_flush, i_node);
+			ret = __send_flush_snap(inode, session, capsnap, cap->mseq,
+						oldest_flush_tid);
+			if (ret < 0) {
+				pr_err("kick_flushing_caps: error sending "
+					"cap flushsnap, ino (%llx.%llx) "
+					"tid %llu follows %llu\n",
+					ceph_vinop(inode), cf->tid,
+					capsnap->follows);
+			}
 
-		first_tid = cf->tid + 1;
+			ceph_put_cap_snap(capsnap);
+		}
 
-		dout("kick_flushing_caps %p cap %p tid %llu %s\n", inode,
-		     cap, cf->tid, ceph_cap_string(cf->caps));
-		delayed |= __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
-				      __ceph_caps_used(ci),
-				      __ceph_caps_wanted(ci),
-				      cap->issued | cap->implemented,
-				      cf->caps, cf->tid, oldest_flush_tid);
+		spin_lock(&ci->i_ceph_lock);
 	}
-	return delayed;
 }
 
 void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
@@ -2175,8 +2160,14 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
 {
 	struct ceph_inode_info *ci;
 	struct ceph_cap *cap;
+	u64 oldest_flush_tid;
 
 	dout("early_kick_flushing_caps mds%d\n", session->s_mds);
+
+	spin_lock(&mdsc->cap_dirty_lock);
+	oldest_flush_tid = __get_oldest_flush_tid(mdsc);
+	spin_unlock(&mdsc->cap_dirty_lock);
+
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
 		spin_lock(&ci->i_ceph_lock);
 		cap = ci->i_auth_cap;
@@ -2196,10 +2187,11 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
 		 */
 		if ((cap->issued & ci->i_flushing_caps) !=
 		    ci->i_flushing_caps) {
-			spin_unlock(&ci->i_ceph_lock);
-			if (!__kick_flushing_caps(mdsc, session, ci))
-				continue;
-			spin_lock(&ci->i_ceph_lock);
+			ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
+			__kick_flushing_caps(mdsc, session, ci,
+					     oldest_flush_tid);
+		} else {
+			ci->i_ceph_flags |= CEPH_I_KICK_FLUSH;
 		}
 
 		spin_unlock(&ci->i_ceph_lock);
@@ -2210,50 +2202,56 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 			     struct ceph_mds_session *session)
 {
 	struct ceph_inode_info *ci;
-
-	kick_flushing_capsnaps(mdsc, session);
+	struct ceph_cap *cap;
+	u64 oldest_flush_tid;
 
 	dout("kick_flushing_caps mds%d\n", session->s_mds);
+
+	spin_lock(&mdsc->cap_dirty_lock);
+	oldest_flush_tid = __get_oldest_flush_tid(mdsc);
+	spin_unlock(&mdsc->cap_dirty_lock);
+
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
-		int delayed = __kick_flushing_caps(mdsc, session, ci);
-		if (delayed) {
-			spin_lock(&ci->i_ceph_lock);
-			__cap_delay_requeue(mdsc, ci);
+		spin_lock(&ci->i_ceph_lock);
+		cap = ci->i_auth_cap;
+		if (!(cap && cap->session == session)) {
+			pr_err("%p auth cap %p not mds%d ???\n",
+				&ci->vfs_inode, cap, session->s_mds);
 			spin_unlock(&ci->i_ceph_lock);
+			continue;
+		}
+		if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH) {
+			ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
+			__kick_flushing_caps(mdsc, session, ci,
+					     oldest_flush_tid);
 		}
+		spin_unlock(&ci->i_ceph_lock);
 	}
 }
 
 static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc,
 				     struct ceph_mds_session *session,
 				     struct inode *inode)
+	__releases(ci->i_ceph_lock)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_cap *cap;
 
-	spin_lock(&ci->i_ceph_lock);
 	cap = ci->i_auth_cap;
 	dout("kick_flushing_inode_caps %p flushing %s\n", inode,
 	     ceph_cap_string(ci->i_flushing_caps));
 
-	__ceph_flush_snaps(ci, &session, 1);
-
-	if (ci->i_flushing_caps) {
-		int delayed;
-
+	if (!list_empty(&ci->i_cap_flush_list)) {
+		u64 oldest_flush_tid;
 		spin_lock(&mdsc->cap_dirty_lock);
 		list_move_tail(&ci->i_flushing_item,
 			       &cap->session->s_cap_flushing);
+		oldest_flush_tid = __get_oldest_flush_tid(mdsc);
 		spin_unlock(&mdsc->cap_dirty_lock);
 
+		ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
+		__kick_flushing_caps(mdsc, session, ci, oldest_flush_tid);
 		spin_unlock(&ci->i_ceph_lock);
-
-		delayed = __kick_flushing_caps(mdsc, session, ci);
-		if (delayed) {
-			spin_lock(&ci->i_ceph_lock);
-			__cap_delay_requeue(mdsc, ci);
-			spin_unlock(&ci->i_ceph_lock);
-		}
 	} else {
 		spin_unlock(&ci->i_ceph_lock);
 	}
@@ -2580,16 +2578,19 @@ void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps)
  * drop cap_snap that is not associated with any snapshot.
  * we don't need to send FLUSHSNAP message for it.
  */
-static int ceph_try_drop_cap_snap(struct ceph_cap_snap *capsnap)
+static int ceph_try_drop_cap_snap(struct ceph_inode_info *ci,
+				  struct ceph_cap_snap *capsnap)
 {
 	if (!capsnap->need_flush &&
 	    !capsnap->writing && !capsnap->dirty_pages) {
-
 		dout("dropping cap_snap %p follows %llu\n",
 		     capsnap, capsnap->follows);
+		BUG_ON(capsnap->cap_flush.tid > 0);
 		ceph_put_snap_context(capsnap->context);
+		if (!list_is_last(&capsnap->ci_item, &ci->i_cap_snaps))
+			ci->i_ceph_flags |= CEPH_I_FLUSH_SNAPS;
+
 		list_del(&capsnap->ci_item);
-		list_del(&capsnap->flushing_item);
 		ceph_put_cap_snap(capsnap);
 		return 1;
 	}
@@ -2636,7 +2637,7 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
 							struct ceph_cap_snap,
 							ci_item);
 				capsnap->writing = 0;
-				if (ceph_try_drop_cap_snap(capsnap))
+				if (ceph_try_drop_cap_snap(ci, capsnap))
 					put++;
 				else if (__ceph_finish_cap_snap(ci, capsnap))
 					flushsnaps = 1;
@@ -2661,7 +2662,7 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
 	if (last && !flushsnaps)
 		ceph_check_caps(ci, 0, NULL);
 	else if (flushsnaps)
-		ceph_flush_snaps(ci);
+		ceph_flush_snaps(ci, NULL);
 	if (wake)
 		wake_up_all(&ci->i_cap_wq);
 	while (put-- > 0)
@@ -2679,15 +2680,19 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				struct ceph_snap_context *snapc)
 {
 	struct inode *inode = &ci->vfs_inode;
-	int last = 0;
-	int complete_capsnap = 0;
-	int drop_capsnap = 0;
-	int found = 0;
 	struct ceph_cap_snap *capsnap = NULL;
+	int put = 0;
+	bool last = false;
+	bool found = false;
+	bool flush_snaps = false;
+	bool complete_capsnap = false;
 
 	spin_lock(&ci->i_ceph_lock);
 	ci->i_wrbuffer_ref -= nr;
-	last = !ci->i_wrbuffer_ref;
+	if (ci->i_wrbuffer_ref == 0) {
+		last = true;
+		put++;
+	}
 
 	if (ci->i_head_snapc == snapc) {
 		ci->i_wrbuffer_ref_head -= nr;
@@ -2707,15 +2712,22 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 	} else {
 		list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
 			if (capsnap->context == snapc) {
-				found = 1;
+				found = true;
 				break;
 			}
 		}
 		BUG_ON(!found);
 		capsnap->dirty_pages -= nr;
 		if (capsnap->dirty_pages == 0) {
-			complete_capsnap = 1;
-			drop_capsnap = ceph_try_drop_cap_snap(capsnap);
+			complete_capsnap = true;
+			if (!capsnap->writing) {
+				if (ceph_try_drop_cap_snap(ci, capsnap)) {
+					put++;
+				} else {
+					ci->i_ceph_flags |= CEPH_I_FLUSH_SNAPS;
+					flush_snaps = true;
+				}
+			}
 		}
 		dout("put_wrbuffer_cap_refs on %p cap_snap %p "
 		     " snap %lld %d/%d -> %d/%d %s%s\n",
@@ -2730,12 +2742,12 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 
 	if (last) {
 		ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
-		iput(inode);
-	} else if (complete_capsnap) {
-		ceph_flush_snaps(ci);
-		wake_up_all(&ci->i_cap_wq);
+	} else if (flush_snaps) {
+		ceph_flush_snaps(ci, NULL);
 	}
-	if (drop_capsnap)
+	if (complete_capsnap)
+		wake_up_all(&ci->i_cap_wq);
+	while (put-- > 0)
 		iput(inode);
 }
 
@@ -2779,12 +2791,11 @@ static void invalidate_aliases(struct inode *inode)
  */
 static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			     struct inode *inode, struct ceph_mds_caps *grant,
-			     u64 inline_version,
-			     void *inline_data, int inline_len,
+			     struct ceph_string **pns, u64 inline_version,
+			     void *inline_data, u32 inline_len,
 			     struct ceph_buffer *xattr_buf,
 			     struct ceph_mds_session *session,
-			     struct ceph_cap *cap, int issued,
-			     u32 pool_ns_len)
+			     struct ceph_cap *cap, int issued)
 	__releases(ci->i_ceph_lock)
 	__releases(mdsc->snap_rwsem)
 {
@@ -2895,8 +2906,18 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 
 	if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
 		/* file layout may have changed */
-		ci->i_layout = grant->layout;
-		ci->i_pool_ns_len = pool_ns_len;
+		s64 old_pool = ci->i_layout.pool_id;
+		struct ceph_string *old_ns;
+
+		ceph_file_layout_from_legacy(&ci->i_layout, &grant->layout);
+		old_ns = rcu_dereference_protected(ci->i_layout.pool_ns,
+					lockdep_is_held(&ci->i_ceph_lock));
+		rcu_assign_pointer(ci->i_layout.pool_ns, *pns);
+
+		if (ci->i_layout.pool_id != old_pool || *pns != old_ns)
+			ci->i_ceph_flags &= ~CEPH_I_POOL_PERM;
+
+		*pns = old_ns;
 
 		/* size/truncate_seq? */
 		queue_trunc = ceph_fill_file_size(inode, issued,
@@ -2979,13 +3000,13 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			fill_inline = true;
 	}
 
-	spin_unlock(&ci->i_ceph_lock);
-
 	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
-		kick_flushing_inode_caps(mdsc, session, inode);
-		up_read(&mdsc->snap_rwsem);
 		if (newcaps & ~issued)
 			wake = true;
+		kick_flushing_inode_caps(mdsc, session, inode);
+		up_read(&mdsc->snap_rwsem);
+	} else {
+		spin_unlock(&ci->i_ceph_lock);
 	}
 
 	if (fill_inline)
@@ -3029,23 +3050,24 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
-	struct ceph_cap_flush *cf;
-	struct rb_node *n;
+	struct ceph_cap_flush *cf, *tmp_cf;
 	LIST_HEAD(to_remove);
 	unsigned seq = le32_to_cpu(m->seq);
 	int dirty = le32_to_cpu(m->dirty);
 	int cleaned = 0;
-	int drop = 0;
+	bool drop = false;
+	bool wake_ci = 0;
+	bool wake_mdsc = 0;
 
-	n = rb_first(&ci->i_cap_flush_tree);
-	while (n) {
-		cf = rb_entry(n, struct ceph_cap_flush, i_node);
-		n = rb_next(&cf->i_node);
+	list_for_each_entry_safe(cf, tmp_cf, &ci->i_cap_flush_list, i_list) {
 		if (cf->tid == flush_tid)
 			cleaned = cf->caps;
+		if (cf->caps == 0) /* capsnap */
+			continue;
 		if (cf->tid <= flush_tid) {
-			rb_erase(&cf->i_node, &ci->i_cap_flush_tree);
-			list_add_tail(&cf->list, &to_remove);
+			if (__finish_cap_flush(NULL, ci, cf))
+				wake_ci = true;
+			list_add_tail(&cf->i_list, &to_remove);
 		} else {
 			cleaned &= ~cf->caps;
 			if (!cleaned)
@@ -3066,31 +3088,29 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 
 	spin_lock(&mdsc->cap_dirty_lock);
 
-	if (!list_empty(&to_remove)) {
-		list_for_each_entry(cf, &to_remove, list)
-			rb_erase(&cf->g_node, &mdsc->cap_flush_tree);
-
-		n = rb_first(&mdsc->cap_flush_tree);
-		cf = n ? rb_entry(n, struct ceph_cap_flush, g_node) : NULL;
-		if (!cf || cf->tid > flush_tid)
-			wake_up_all(&mdsc->cap_flushing_wq);
+	list_for_each_entry(cf, &to_remove, i_list) {
+		if (__finish_cap_flush(mdsc, NULL, cf))
+			wake_mdsc = true;
 	}
 
 	if (ci->i_flushing_caps == 0) {
-		list_del_init(&ci->i_flushing_item);
-		if (!list_empty(&session->s_cap_flushing))
-			dout(" mds%d still flushing cap on %p\n",
-			     session->s_mds,
-			     &list_entry(session->s_cap_flushing.next,
-					 struct ceph_inode_info,
-					 i_flushing_item)->vfs_inode);
+		if (list_empty(&ci->i_cap_flush_list)) {
+			list_del_init(&ci->i_flushing_item);
+			if (!list_empty(&session->s_cap_flushing)) {
+				dout(" mds%d still flushing cap on %p\n",
+				     session->s_mds,
+				     &list_first_entry(&session->s_cap_flushing,
+						struct ceph_inode_info,
+						i_flushing_item)->vfs_inode);
+			}
+		}
 		mdsc->num_cap_flushing--;
 		dout(" inode %p now !flushing\n", inode);
 
 		if (ci->i_dirty_caps == 0) {
 			dout(" inode %p now clean\n", inode);
 			BUG_ON(!list_empty(&ci->i_dirty_item));
-			drop = 1;
+			drop = true;
 			if (ci->i_wr_ref == 0 &&
 			    ci->i_wrbuffer_ref_head == 0) {
 				BUG_ON(!ci->i_head_snapc);
@@ -3102,17 +3122,21 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 		}
 	}
 	spin_unlock(&mdsc->cap_dirty_lock);
-	wake_up_all(&ci->i_cap_wq);
 
 out:
 	spin_unlock(&ci->i_ceph_lock);
 
 	while (!list_empty(&to_remove)) {
 		cf = list_first_entry(&to_remove,
-				      struct ceph_cap_flush, list);
-		list_del(&cf->list);
+				      struct ceph_cap_flush, i_list);
+		list_del(&cf->i_list);
 		ceph_free_cap_flush(cf);
 	}
+
+	if (wake_ci)
+		wake_up_all(&ci->i_cap_wq);
+	if (wake_mdsc)
+		wake_up_all(&mdsc->cap_flushing_wq);
 	if (drop)
 		iput(inode);
 }
@@ -3131,7 +3155,9 @@ static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid,
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	u64 follows = le64_to_cpu(m->snap_follows);
 	struct ceph_cap_snap *capsnap;
-	int drop = 0;
+	bool flushed = false;
+	bool wake_ci = false;
+	bool wake_mdsc = false;
 
 	dout("handle_cap_flushsnap_ack inode %p ci %p mds%d follows %lld\n",
 	     inode, ci, session->s_mds, follows);
@@ -3139,30 +3165,47 @@ static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid,
 	spin_lock(&ci->i_ceph_lock);
 	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
 		if (capsnap->follows == follows) {
-			if (capsnap->flush_tid != flush_tid) {
+			if (capsnap->cap_flush.tid != flush_tid) {
 				dout(" cap_snap %p follows %lld tid %lld !="
 				     " %lld\n", capsnap, follows,
-				     flush_tid, capsnap->flush_tid);
+				     flush_tid, capsnap->cap_flush.tid);
 				break;
 			}
-			WARN_ON(capsnap->dirty_pages || capsnap->writing);
-			dout(" removing %p cap_snap %p follows %lld\n",
-			     inode, capsnap, follows);
-			ceph_put_snap_context(capsnap->context);
-			list_del(&capsnap->ci_item);
-			list_del(&capsnap->flushing_item);
-			ceph_put_cap_snap(capsnap);
-			wake_up_all(&mdsc->cap_flushing_wq);
-			drop = 1;
+			flushed = true;
 			break;
 		} else {
 			dout(" skipping cap_snap %p follows %lld\n",
 			     capsnap, capsnap->follows);
 		}
 	}
+	if (flushed) {
+		WARN_ON(capsnap->dirty_pages || capsnap->writing);
+		dout(" removing %p cap_snap %p follows %lld\n",
+		     inode, capsnap, follows);
+		list_del(&capsnap->ci_item);
+		if (__finish_cap_flush(NULL, ci, &capsnap->cap_flush))
+			wake_ci = true;
+
+		spin_lock(&mdsc->cap_dirty_lock);
+
+		if (list_empty(&ci->i_cap_flush_list))
+			list_del_init(&ci->i_flushing_item);
+
+		if (__finish_cap_flush(mdsc, NULL, &capsnap->cap_flush))
+			wake_mdsc = true;
+
+		spin_unlock(&mdsc->cap_dirty_lock);
+	}
 	spin_unlock(&ci->i_ceph_lock);
-	if (drop)
+	if (flushed) {
+		ceph_put_snap_context(capsnap->context);
+		ceph_put_cap_snap(capsnap);
+		if (wake_ci)
+			wake_up_all(&ci->i_cap_wq);
+		if (wake_mdsc)
+			wake_up_all(&mdsc->cap_flushing_wq);
 		iput(inode);
+	}
 }
 
 /*
@@ -3267,7 +3310,8 @@ retry:
 			tcap->implemented |= issued;
 			if (cap == ci->i_auth_cap)
 				ci->i_auth_cap = tcap;
-			if (ci->i_flushing_caps && ci->i_auth_cap == tcap) {
+			if (!list_empty(&ci->i_cap_flush_list) &&
+			    ci->i_auth_cap == tcap) {
 				spin_lock(&mdsc->cap_dirty_lock);
 				list_move_tail(&ci->i_flushing_item,
 					       &tcap->session->s_cap_flushing);
@@ -3420,20 +3464,18 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	struct ceph_cap *cap;
 	struct ceph_mds_caps *h;
 	struct ceph_mds_cap_peer *peer = NULL;
-	struct ceph_snap_realm *realm;
+	struct ceph_snap_realm *realm = NULL;
+	struct ceph_string *pool_ns = NULL;
 	int mds = session->s_mds;
 	int op, issued;
 	u32 seq, mseq;
 	struct ceph_vino vino;
-	u64 cap_id;
-	u64 size, max_size;
 	u64 tid;
 	u64 inline_version = 0;
 	void *inline_data = NULL;
 	u32  inline_len = 0;
 	void *snaptrace;
 	size_t snaptrace_len;
-	u32 pool_ns_len = 0;
 	void *p, *end;
 
 	dout("handle_caps from mds%d\n", mds);
@@ -3447,11 +3489,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	op = le32_to_cpu(h->op);
 	vino.ino = le64_to_cpu(h->ino);
 	vino.snap = CEPH_NOSNAP;
-	cap_id = le64_to_cpu(h->cap_id);
 	seq = le32_to_cpu(h->seq);
 	mseq = le32_to_cpu(h->migrate_seq);
-	size = le64_to_cpu(h->size);
-	max_size = le64_to_cpu(h->max_size);
 
 	snaptrace = h + 1;
 	snaptrace_len = le32_to_cpu(h->snap_trace_len);
@@ -3490,6 +3529,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		u64 flush_tid;
 		u32 caller_uid, caller_gid;
 		u32 osd_epoch_barrier;
+		u32 pool_ns_len;
 		/* version >= 5 */
 		ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad);
 		/* version >= 6 */
@@ -3499,6 +3539,11 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		ceph_decode_32_safe(&p, end, caller_gid, bad);
 		/* version >= 8 */
 		ceph_decode_32_safe(&p, end, pool_ns_len, bad);
+		if (pool_ns_len > 0) {
+			ceph_decode_need(&p, end, pool_ns_len, bad);
+			pool_ns = ceph_find_or_create_string(p, pool_ns_len);
+			p += pool_ns_len;
+		}
 	}
 
 	/* lookup ino */
@@ -3519,7 +3564,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 			cap = ceph_get_cap(mdsc, NULL);
 			cap->cap_ino = vino.ino;
 			cap->queue_release = 1;
-			cap->cap_id = cap_id;
+			cap->cap_id = le64_to_cpu(h->cap_id);
 			cap->mseq = mseq;
 			cap->seq = seq;
 			spin_lock(&session->s_cap_lock);
@@ -3554,10 +3599,9 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		}
 		handle_cap_import(mdsc, inode, h, peer, session,
 				  &cap, &issued);
-		handle_cap_grant(mdsc, inode, h,
+		handle_cap_grant(mdsc, inode, h, &pool_ns,
 				 inline_version, inline_data, inline_len,
-				 msg->middle, session, cap, issued,
-				 pool_ns_len);
+				 msg->middle, session, cap, issued);
 		if (realm)
 			ceph_put_snap_realm(mdsc, realm);
 		goto done_unlocked;
@@ -3579,10 +3623,9 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	case CEPH_CAP_OP_GRANT:
 		__ceph_caps_issued(ci, &issued);
 		issued |= __ceph_caps_dirty(ci);
-		handle_cap_grant(mdsc, inode, h,
+		handle_cap_grant(mdsc, inode, h, &pool_ns,
 				 inline_version, inline_data, inline_len,
-				 msg->middle, session, cap, issued,
-				 pool_ns_len);
+				 msg->middle, session, cap, issued);
 		goto done_unlocked;
 
 	case CEPH_CAP_OP_FLUSH_ACK:
@@ -3613,6 +3656,7 @@ done:
 	mutex_unlock(&session->s_mutex);
 done_unlocked:
 	iput(inode);
+	ceph_put_string(pool_ns);
 	return;
 
 bad:
@@ -3673,6 +3717,16 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
 	dout("flush_dirty_caps done\n");
 }
 
+void __ceph_get_fmode(struct ceph_inode_info *ci, int fmode)
+{
+	int i;
+	int bits = (fmode << 1) | 1;
+	for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
+		if (bits & (1 << i))
+			ci->i_nr_by_mode[i]++;
+	}
+}
+
 /*
  * Drop open file reference.  If we were the last open file,
  * we may need to release capabilities to the MDS (or schedule
@@ -3680,15 +3734,20 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
  */
 void ceph_put_fmode(struct ceph_inode_info *ci, int fmode)
 {
-	struct inode *inode = &ci->vfs_inode;
-	int last = 0;
-
+	int i, last = 0;
+	int bits = (fmode << 1) | 1;
 	spin_lock(&ci->i_ceph_lock);
-	dout("put_fmode %p fmode %d %d -> %d\n", inode, fmode,
-	     ci->i_nr_by_mode[fmode], ci->i_nr_by_mode[fmode]-1);
-	BUG_ON(ci->i_nr_by_mode[fmode] == 0);
-	if (--ci->i_nr_by_mode[fmode] == 0)
-		last++;
+	for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
+		if (bits & (1 << i)) {
+			BUG_ON(ci->i_nr_by_mode[i] == 0);
+			if (--ci->i_nr_by_mode[i] == 0)
+				last++;
+		}
+	}
+	dout("put_fmode %p fmode %d {%d,%d,%d,%d}\n",
+	     &ci->vfs_inode, fmode,
+	     ci->i_nr_by_mode[0], ci->i_nr_by_mode[1],
+	     ci->i_nr_by_mode[2], ci->i_nr_by_mode[3]);
 	spin_unlock(&ci->i_ceph_lock);
 
 	if (last && ci->i_vino.snap == CEPH_NOSNAP)
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 6e0fedf6713b..c64a0b794d49 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -59,7 +59,7 @@ int ceph_init_dentry(struct dentry *dentry)
 
 	di->dentry = dentry;
 	di->lease_session = NULL;
-	dentry->d_time = jiffies;
+	di->time = jiffies;
 	/* avoid reordering d_fsdata setup so that the check above is safe */
 	smp_mb();
 	dentry->d_fsdata = di;
@@ -1124,7 +1124,7 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
 void ceph_invalidate_dentry_lease(struct dentry *dentry)
 {
 	spin_lock(&dentry->d_lock);
-	dentry->d_time = jiffies;
+	ceph_dentry(dentry)->time = jiffies;
 	ceph_dentry(dentry)->lease_shared_gen = 0;
 	spin_unlock(&dentry->d_lock);
 }
@@ -1133,7 +1133,8 @@ void ceph_invalidate_dentry_lease(struct dentry *dentry)
  * Check if dentry lease is valid.  If not, delete the lease.  Try to
  * renew if the least is more than half up.
  */
-static int dentry_lease_is_valid(struct dentry *dentry)
+static int dentry_lease_is_valid(struct dentry *dentry, unsigned int flags,
+				 struct inode *dir)
 {
 	struct ceph_dentry_info *di;
 	struct ceph_mds_session *s;
@@ -1141,12 +1142,11 @@ static int dentry_lease_is_valid(struct dentry *dentry)
 	u32 gen;
 	unsigned long ttl;
 	struct ceph_mds_session *session = NULL;
-	struct inode *dir = NULL;
 	u32 seq = 0;
 
 	spin_lock(&dentry->d_lock);
 	di = ceph_dentry(dentry);
-	if (di->lease_session) {
+	if (di && di->lease_session) {
 		s = di->lease_session;
 		spin_lock(&s->s_gen_ttl_lock);
 		gen = s->s_cap_gen;
@@ -1154,17 +1154,24 @@ static int dentry_lease_is_valid(struct dentry *dentry)
 		spin_unlock(&s->s_gen_ttl_lock);
 
 		if (di->lease_gen == gen &&
-		    time_before(jiffies, dentry->d_time) &&
+		    time_before(jiffies, di->time) &&
 		    time_before(jiffies, ttl)) {
 			valid = 1;
 			if (di->lease_renew_after &&
 			    time_after(jiffies, di->lease_renew_after)) {
-				/* we should renew */
-				dir = d_inode(dentry->d_parent);
-				session = ceph_get_mds_session(s);
-				seq = di->lease_seq;
-				di->lease_renew_after = 0;
-				di->lease_renew_from = jiffies;
+				/*
+				 * We should renew. If we're in RCU walk mode
+				 * though, we can't do that so just return
+				 * -ECHILD.
+				 */
+				if (flags & LOOKUP_RCU) {
+					valid = -ECHILD;
+				} else {
+					session = ceph_get_mds_session(s);
+					seq = di->lease_seq;
+					di->lease_renew_after = 0;
+					di->lease_renew_from = jiffies;
+				}
 			}
 		}
 	}
@@ -1207,15 +1214,19 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 	struct dentry *parent;
 	struct inode *dir;
 
-	if (flags & LOOKUP_RCU)
-		return -ECHILD;
+	if (flags & LOOKUP_RCU) {
+		parent = ACCESS_ONCE(dentry->d_parent);
+		dir = d_inode_rcu(parent);
+		if (!dir)
+			return -ECHILD;
+	} else {
+		parent = dget_parent(dentry);
+		dir = d_inode(parent);
+	}
 
 	dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
 	     dentry, d_inode(dentry), ceph_dentry(dentry)->offset);
 
-	parent = dget_parent(dentry);
-	dir = d_inode(parent);
-
 	/* always trust cached snapped dentries, snapdir dentry */
 	if (ceph_snap(dir) != CEPH_NOSNAP) {
 		dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
@@ -1224,12 +1235,16 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 	} else if (d_really_is_positive(dentry) &&
 		   ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) {
 		valid = 1;
-	} else if (dentry_lease_is_valid(dentry) ||
-		   dir_lease_is_valid(dir, dentry)) {
-		if (d_really_is_positive(dentry))
-			valid = ceph_is_any_caps(d_inode(dentry));
-		else
-			valid = 1;
+	} else {
+		valid = dentry_lease_is_valid(dentry, flags, dir);
+		if (valid == -ECHILD)
+			return valid;
+		if (valid || dir_lease_is_valid(dir, dentry)) {
+			if (d_really_is_positive(dentry))
+				valid = ceph_is_any_caps(d_inode(dentry));
+			else
+				valid = 1;
+		}
 	}
 
 	if (!valid) {
@@ -1238,6 +1253,9 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		struct ceph_mds_request *req;
 		int op, mask, err;
 
+		if (flags & LOOKUP_RCU)
+			return -ECHILD;
+
 		op = ceph_snap(dir) == CEPH_SNAPDIR ?
 			CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP;
 		req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS);
@@ -1273,7 +1291,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		ceph_dir_clear_complete(dir);
 	}
 
-	dput(parent);
+	if (!(flags & LOOKUP_RCU))
+		dput(parent);
 	return valid;
 }
 
@@ -1286,10 +1305,14 @@ static void ceph_d_release(struct dentry *dentry)
 
 	dout("d_release %p\n", dentry);
 	ceph_dentry_lru_del(dentry);
+
+	spin_lock(&dentry->d_lock);
+	dentry->d_fsdata = NULL;
+	spin_unlock(&dentry->d_lock);
+
 	if (di->lease_session)
 		ceph_put_mds_session(di->lease_session);
 	kmem_cache_free(ceph_dentry_cachep, di);
-	dentry->d_fsdata = NULL;
 }
 
 static int ceph_snapdir_d_revalidate(struct dentry *dentry,
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 0daaf7ceedc5..0f5375d8e030 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -708,7 +708,7 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 		}
 	}
 
-	ceph_put_page_vector(osd_data->pages, num_pages, false);
+	ceph_put_page_vector(osd_data->pages, num_pages, !aio_req->write);
 	ceph_osdc_put_request(req);
 
 	if (rc < 0)
@@ -821,6 +821,54 @@ static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe)
 	}
 }
 
+/*
+ * Wait on any unsafe replies for the given inode.  First wait on the
+ * newest request, and make that the upper bound.  Then, if there are
+ * more requests, keep waiting on the oldest as long as it is still older
+ * than the original request.
+ */
+void ceph_sync_write_wait(struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct list_head *head = &ci->i_unsafe_writes;
+	struct ceph_osd_request *req;
+	u64 last_tid;
+
+	if (!S_ISREG(inode->i_mode))
+		return;
+
+	spin_lock(&ci->i_unsafe_lock);
+	if (list_empty(head))
+		goto out;
+
+	/* set upper bound as _last_ entry in chain */
+
+	req = list_last_entry(head, struct ceph_osd_request,
+			      r_unsafe_item);
+	last_tid = req->r_tid;
+
+	do {
+		ceph_osdc_get_request(req);
+		spin_unlock(&ci->i_unsafe_lock);
+
+		dout("sync_write_wait on tid %llu (until %llu)\n",
+		     req->r_tid, last_tid);
+		wait_for_completion(&req->r_safe_completion);
+		ceph_osdc_put_request(req);
+
+		spin_lock(&ci->i_unsafe_lock);
+		/*
+		 * from here on look at first entry in chain, since we
+		 * only want to wait for anything older than last_tid
+		 */
+		if (list_empty(head))
+			break;
+		req = list_first_entry(head, struct ceph_osd_request,
+				       r_unsafe_item);
+	} while (req->r_tid < last_tid);
+out:
+	spin_unlock(&ci->i_unsafe_lock);
+}
 
 static ssize_t
 ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
@@ -964,7 +1012,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 				len = ret;
 		}
 
-		ceph_put_page_vector(pages, num_pages, false);
+		ceph_put_page_vector(pages, num_pages, !write);
 
 		ceph_osdc_put_request(req);
 		if (ret < 0)
@@ -985,6 +1033,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	}
 
 	if (aio_req) {
+		LIST_HEAD(osd_reqs);
+
 		if (aio_req->num_reqs == 0) {
 			kfree(aio_req);
 			return ret;
@@ -993,8 +1043,9 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		ceph_get_cap_refs(ci, write ? CEPH_CAP_FILE_WR :
 					      CEPH_CAP_FILE_RD);
 
-		while (!list_empty(&aio_req->osd_reqs)) {
-			req = list_first_entry(&aio_req->osd_reqs,
+		list_splice(&aio_req->osd_reqs, &osd_reqs);
+		while (!list_empty(&osd_reqs)) {
+			req = list_first_entry(&osd_reqs,
 					       struct ceph_osd_request,
 					       r_unsafe_item);
 			list_del_init(&req->r_unsafe_item);
@@ -1448,16 +1499,14 @@ static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	loff_t i_size;
-	int ret;
+	loff_t ret;
 
 	inode_lock(inode);
 
 	if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
 		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
-		if (ret < 0) {
-			offset = ret;
+		if (ret < 0)
 			goto out;
-		}
 	}
 
 	i_size = i_size_read(inode);
@@ -1473,7 +1522,7 @@ static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
 		 * write() or lseek() might have altered it
 		 */
 		if (offset == 0) {
-			offset = file->f_pos;
+			ret = file->f_pos;
 			goto out;
 		}
 		offset += file->f_pos;
@@ -1493,11 +1542,11 @@ static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
 		break;
 	}
 
-	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
+	ret = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 
 out:
 	inode_unlock(inode);
-	return offset;
+	return ret;
 }
 
 static inline void ceph_zero_partial_page(
@@ -1583,9 +1632,9 @@ static int ceph_zero_objects(struct inode *inode, loff_t offset, loff_t length)
 {
 	int ret = 0;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	s32 stripe_unit = ceph_file_layout_su(ci->i_layout);
-	s32 stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
-	s32 object_size = ceph_file_layout_object_size(ci->i_layout);
+	s32 stripe_unit = ci->i_layout.stripe_unit;
+	s32 stripe_count = ci->i_layout.stripe_count;
+	s32 object_size = ci->i_layout.object_size;
 	u64 object_set_size = object_size * stripe_count;
 	u64 nearly, t;
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 99bdef66213a..dd3a6dbf71eb 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -446,7 +446,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	ci->i_symlink = NULL;
 
 	memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
-	ci->i_pool_ns_len = 0;
+	RCU_INIT_POINTER(ci->i_layout.pool_ns, NULL);
 
 	ci->i_fragtree = RB_ROOT;
 	mutex_init(&ci->i_fragtree_mutex);
@@ -468,7 +468,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	INIT_LIST_HEAD(&ci->i_dirty_item);
 	INIT_LIST_HEAD(&ci->i_flushing_item);
 	ci->i_prealloc_cap_flush = NULL;
-	ci->i_cap_flush_tree = RB_ROOT;
+	INIT_LIST_HEAD(&ci->i_cap_flush_list);
 	init_waitqueue_head(&ci->i_cap_wq);
 	ci->i_hold_caps_min = 0;
 	ci->i_hold_caps_max = 0;
@@ -477,7 +477,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	ci->i_head_snapc = NULL;
 	ci->i_snap_caps = 0;
 
-	for (i = 0; i < CEPH_FILE_MODE_NUM; i++)
+	for (i = 0; i < CEPH_FILE_MODE_BITS; i++)
 		ci->i_nr_by_mode[i] = 0;
 
 	mutex_init(&ci->i_truncate_mutex);
@@ -570,6 +570,8 @@ void ceph_destroy_inode(struct inode *inode)
 	if (ci->i_xattrs.prealloc_blob)
 		ceph_buffer_put(ci->i_xattrs.prealloc_blob);
 
+	ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns));
+
 	call_rcu(&inode->i_rcu, ceph_i_callback);
 }
 
@@ -583,6 +585,14 @@ int ceph_drop_inode(struct inode *inode)
 	return 1;
 }
 
+void ceph_evict_inode(struct inode *inode)
+{
+	/* wait unsafe sync writes */
+	ceph_sync_write_wait(inode);
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+}
+
 static inline blkcnt_t calc_inode_blocks(u64 size)
 {
 	return (size + (1<<9) - 1) >> 9;
@@ -733,6 +743,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	int issued = 0, implemented, new_issued;
 	struct timespec mtime, atime, ctime;
 	struct ceph_buffer *xattr_blob = NULL;
+	struct ceph_string *pool_ns = NULL;
 	struct ceph_cap *new_cap = NULL;
 	int err = 0;
 	bool wake = false;
@@ -760,6 +771,10 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 			       iinfo->xattr_len);
 	}
 
+	if (iinfo->pool_ns_len > 0)
+		pool_ns = ceph_find_or_create_string(iinfo->pool_ns_data,
+						     iinfo->pool_ns_len);
+
 	spin_lock(&ci->i_ceph_lock);
 
 	/*
@@ -814,10 +829,18 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 
 	if (new_version ||
 	    (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
-		if (ci->i_layout.fl_pg_pool != info->layout.fl_pg_pool)
+		s64 old_pool = ci->i_layout.pool_id;
+		struct ceph_string *old_ns;
+
+		ceph_file_layout_from_legacy(&ci->i_layout, &info->layout);
+		old_ns = rcu_dereference_protected(ci->i_layout.pool_ns,
+					lockdep_is_held(&ci->i_ceph_lock));
+		rcu_assign_pointer(ci->i_layout.pool_ns, pool_ns);
+
+		if (ci->i_layout.pool_id != old_pool || pool_ns != old_ns)
 			ci->i_ceph_flags &= ~CEPH_I_POOL_PERM;
-		ci->i_layout = info->layout;
-		ci->i_pool_ns_len = iinfo->pool_ns_len;
+
+		pool_ns = old_ns;
 
 		queue_trunc = ceph_fill_file_size(inode, issued,
 					le32_to_cpu(info->truncate_seq),
@@ -985,6 +1008,7 @@ out:
 		ceph_put_cap(mdsc, new_cap);
 	if (xattr_blob)
 		ceph_buffer_put(xattr_blob);
+	ceph_put_string(pool_ns);
 	return err;
 }
 
@@ -1018,7 +1042,7 @@ static void update_dentry_lease(struct dentry *dentry,
 		goto out_unlock;
 
 	if (di->lease_gen == session->s_cap_gen &&
-	    time_before(ttl, dentry->d_time))
+	    time_before(ttl, di->time))
 		goto out_unlock;  /* we already have a newer lease. */
 
 	if (di->lease_session && di->lease_session != session)
@@ -1032,7 +1056,7 @@ static void update_dentry_lease(struct dentry *dentry,
 	di->lease_seq = le32_to_cpu(lease->seq);
 	di->lease_renew_after = half_ttl;
 	di->lease_renew_from = 0;
-	dentry->d_time = ttl;
+	di->time = ttl;
 out_unlock:
 	spin_unlock(&dentry->d_lock);
 	return;
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index be6b1657b1af..7d752d53353a 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -21,10 +21,10 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
 
 	err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT, false);
 	if (!err) {
-		l.stripe_unit = ceph_file_layout_su(ci->i_layout);
-		l.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
-		l.object_size = ceph_file_layout_object_size(ci->i_layout);
-		l.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool);
+		l.stripe_unit = ci->i_layout.stripe_unit;
+		l.stripe_count = ci->i_layout.stripe_count;
+		l.object_size = ci->i_layout.object_size;
+		l.data_pool = ci->i_layout.pool_id;
 		l.preferred_osd = (s32)-1;
 		if (copy_to_user(arg, &l, sizeof(l)))
 			return -EFAULT;
@@ -82,19 +82,19 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 	if (l.stripe_count)
 		nl.stripe_count = l.stripe_count;
 	else
-		nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
+		nl.stripe_count = ci->i_layout.stripe_count;
 	if (l.stripe_unit)
 		nl.stripe_unit = l.stripe_unit;
 	else
-		nl.stripe_unit = ceph_file_layout_su(ci->i_layout);
+		nl.stripe_unit = ci->i_layout.stripe_unit;
 	if (l.object_size)
 		nl.object_size = l.object_size;
 	else
-		nl.object_size = ceph_file_layout_object_size(ci->i_layout);
+		nl.object_size = ci->i_layout.object_size;
 	if (l.data_pool)
 		nl.data_pool = l.data_pool;
 	else
-		nl.data_pool = ceph_file_layout_pg_pool(ci->i_layout);
+		nl.data_pool = ci->i_layout.pool_id;
 
 	/* this is obsolete, and always -1 */
 	nl.preferred_osd = le64_to_cpu(-1);
@@ -183,7 +183,7 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
 	struct ceph_osd_client *osdc =
 		&ceph_sb_to_client(inode->i_sb)->client->osdc;
 	struct ceph_object_locator oloc;
-	struct ceph_object_id oid;
+	CEPH_DEFINE_OID_ONSTACK(oid);
 	u64 len = 1, olen;
 	u64 tmp;
 	struct ceph_pg pgid;
@@ -202,8 +202,8 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
 		return -EIO;
 	}
 	dl.file_offset -= dl.object_offset;
-	dl.object_size = ceph_file_layout_object_size(ci->i_layout);
-	dl.block_size = ceph_file_layout_su(ci->i_layout);
+	dl.object_size = ci->i_layout.object_size;
+	dl.block_size = ci->i_layout.stripe_unit;
 
 	/* block_offset = object_offset % block_size */
 	tmp = dl.object_offset;
@@ -212,10 +212,13 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
 	snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
 		 ceph_ino(inode), dl.object_no);
 
-	oloc.pool = ceph_file_layout_pg_pool(ci->i_layout);
+	oloc.pool = ci->i_layout.pool_id;
+	oloc.pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
 	ceph_oid_printf(&oid, "%s", dl.object_name);
 
 	r = ceph_object_locator_to_pg(osdc->osdmap, &oid, &oloc, &pgid);
+
+	ceph_oloc_destroy(&oloc);
 	if (r < 0) {
 		up_read(&osdc->lock);
 		return r;
@@ -247,9 +250,8 @@ static long ceph_ioctl_lazyio(struct file *file)
 
 	if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
 		spin_lock(&ci->i_ceph_lock);
-		ci->i_nr_by_mode[fi->fmode]--;
 		fi->fmode |= CEPH_FILE_MODE_LAZY;
-		ci->i_nr_by_mode[fi->fmode]++;
+		ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++;
 		spin_unlock(&ci->i_ceph_lock);
 		dout("ioctl_layzio: file %p marked lazy\n", file);
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 4e8678a612b6..fa59a85226b2 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -48,7 +48,7 @@
 struct ceph_reconnect_state {
 	int nr_caps;
 	struct ceph_pagelist *pagelist;
-	bool flock;
+	unsigned msg_version;
 };
 
 static void __wake_requests(struct ceph_mds_client *mdsc,
@@ -100,12 +100,15 @@ static int parse_reply_info_in(void **p, void *end,
 	} else
 		info->inline_version = CEPH_INLINE_NONE;
 
+	info->pool_ns_len = 0;
+	info->pool_ns_data = NULL;
 	if (features & CEPH_FEATURE_FS_FILE_LAYOUT_V2) {
 		ceph_decode_32_safe(p, end, info->pool_ns_len, bad);
-		ceph_decode_need(p, end, info->pool_ns_len, bad);
-		*p += info->pool_ns_len;
-	} else {
-		info->pool_ns_len = 0;
+		if (info->pool_ns_len > 0) {
+			ceph_decode_need(p, end, info->pool_ns_len, bad);
+			info->pool_ns_data = *p;
+			*p += info->pool_ns_len;
+		}
 	}
 
 	return 0;
@@ -469,7 +472,6 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	s->s_cap_iterator = NULL;
 	INIT_LIST_HEAD(&s->s_cap_releases);
 	INIT_LIST_HEAD(&s->s_cap_flushing);
-	INIT_LIST_HEAD(&s->s_cap_snaps_flushing);
 
 	dout("register_session mds%d\n", mds);
 	if (mds >= mdsc->max_sessions) {
@@ -1145,19 +1147,17 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		    ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
 			invalidate = true;
 
-		while (true) {
-			struct rb_node *n = rb_first(&ci->i_cap_flush_tree);
-			if (!n)
-				break;
-			cf = rb_entry(n, struct ceph_cap_flush, i_node);
-			rb_erase(&cf->i_node, &ci->i_cap_flush_tree);
-			list_add(&cf->list, &to_remove);
+		while (!list_empty(&ci->i_cap_flush_list)) {
+			cf = list_first_entry(&ci->i_cap_flush_list,
+					      struct ceph_cap_flush, i_list);
+			list_del(&cf->i_list);
+			list_add(&cf->i_list, &to_remove);
 		}
 
 		spin_lock(&mdsc->cap_dirty_lock);
 
-		list_for_each_entry(cf, &to_remove, list)
-			rb_erase(&cf->g_node, &mdsc->cap_flush_tree);
+		list_for_each_entry(cf, &to_remove, i_list)
+			list_del(&cf->g_list);
 
 		if (!list_empty(&ci->i_dirty_item)) {
 			pr_warn_ratelimited(
@@ -1181,7 +1181,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		spin_unlock(&mdsc->cap_dirty_lock);
 
 		if (!ci->i_dirty_caps && ci->i_prealloc_cap_flush) {
-			list_add(&ci->i_prealloc_cap_flush->list, &to_remove);
+			list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove);
 			ci->i_prealloc_cap_flush = NULL;
 		}
 	}
@@ -1189,8 +1189,8 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	while (!list_empty(&to_remove)) {
 		struct ceph_cap_flush *cf;
 		cf = list_first_entry(&to_remove,
-				      struct ceph_cap_flush, list);
-		list_del(&cf->list);
+				      struct ceph_cap_flush, i_list);
+		list_del(&cf->i_list);
 		ceph_free_cap_flush(cf);
 	}
 
@@ -1212,6 +1212,8 @@ static void remove_session_caps(struct ceph_mds_session *session)
 	dout("remove_session_caps on %p\n", session);
 	iterate_session_caps(session, remove_session_caps_cb, fsc);
 
+	wake_up_all(&fsc->mdsc->cap_flushing_wq);
+
 	spin_lock(&session->s_cap_lock);
 	if (session->s_nr_caps > 0) {
 		struct inode *inode;
@@ -1478,35 +1480,21 @@ static int trim_caps(struct ceph_mds_client *mdsc,
 	return 0;
 }
 
-static int check_capsnap_flush(struct ceph_inode_info *ci,
-			       u64 want_snap_seq)
-{
-	int ret = 1;
-	spin_lock(&ci->i_ceph_lock);
-	if (want_snap_seq > 0 && !list_empty(&ci->i_cap_snaps)) {
-		struct ceph_cap_snap *capsnap =
-			list_first_entry(&ci->i_cap_snaps,
-					 struct ceph_cap_snap, ci_item);
-		ret = capsnap->follows >= want_snap_seq;
-	}
-	spin_unlock(&ci->i_ceph_lock);
-	return ret;
-}
-
 static int check_caps_flush(struct ceph_mds_client *mdsc,
 			    u64 want_flush_tid)
 {
-	struct rb_node *n;
-	struct ceph_cap_flush *cf;
 	int ret = 1;
 
 	spin_lock(&mdsc->cap_dirty_lock);
-	n = rb_first(&mdsc->cap_flush_tree);
-	cf = n ? rb_entry(n, struct ceph_cap_flush, g_node) : NULL;
-	if (cf && cf->tid <= want_flush_tid) {
-		dout("check_caps_flush still flushing tid %llu <= %llu\n",
-		     cf->tid, want_flush_tid);
-		ret = 0;
+	if (!list_empty(&mdsc->cap_flush_list)) {
+		struct ceph_cap_flush *cf =
+			list_first_entry(&mdsc->cap_flush_list,
+					 struct ceph_cap_flush, g_list);
+		if (cf->tid <= want_flush_tid) {
+			dout("check_caps_flush still flushing tid "
+			     "%llu <= %llu\n", cf->tid, want_flush_tid);
+			ret = 0;
+		}
 	}
 	spin_unlock(&mdsc->cap_dirty_lock);
 	return ret;
@@ -1518,54 +1506,9 @@ static int check_caps_flush(struct ceph_mds_client *mdsc,
  * returns true if we've flushed through want_flush_tid
  */
 static void wait_caps_flush(struct ceph_mds_client *mdsc,
-			    u64 want_flush_tid, u64 want_snap_seq)
+			    u64 want_flush_tid)
 {
-	int mds;
-
-	dout("check_caps_flush want %llu snap want %llu\n",
-	     want_flush_tid, want_snap_seq);
-	mutex_lock(&mdsc->mutex);
-	for (mds = 0; mds < mdsc->max_sessions; ) {
-		struct ceph_mds_session *session = mdsc->sessions[mds];
-		struct inode *inode = NULL;
-
-		if (!session) {
-			mds++;
-			continue;
-		}
-		get_session(session);
-		mutex_unlock(&mdsc->mutex);
-
-		mutex_lock(&session->s_mutex);
-		if (!list_empty(&session->s_cap_snaps_flushing)) {
-			struct ceph_cap_snap *capsnap =
-				list_first_entry(&session->s_cap_snaps_flushing,
-						 struct ceph_cap_snap,
-						 flushing_item);
-			struct ceph_inode_info *ci = capsnap->ci;
-			if (!check_capsnap_flush(ci, want_snap_seq)) {
-				dout("check_cap_flush still flushing snap %p "
-				     "follows %lld <= %lld to mds%d\n",
-				     &ci->vfs_inode, capsnap->follows,
-				     want_snap_seq, mds);
-				inode = igrab(&ci->vfs_inode);
-			}
-		}
-		mutex_unlock(&session->s_mutex);
-		ceph_put_mds_session(session);
-
-		if (inode) {
-			wait_event(mdsc->cap_flushing_wq,
-				   check_capsnap_flush(ceph_inode(inode),
-						       want_snap_seq));
-			iput(inode);
-		} else {
-			mds++;
-		}
-
-		mutex_lock(&mdsc->mutex);
-	}
-	mutex_unlock(&mdsc->mutex);
+	dout("check_caps_flush want %llu\n", want_flush_tid);
 
 	wait_event(mdsc->cap_flushing_wq,
 		   check_caps_flush(mdsc, want_flush_tid));
@@ -2163,6 +2106,11 @@ static int __do_request(struct ceph_mds_client *mdsc,
 	mds = __choose_mds(mdsc, req);
 	if (mds < 0 ||
 	    ceph_mdsmap_get_state(mdsc->mdsmap, mds) < CEPH_MDS_STATE_ACTIVE) {
+		if (mdsc->mdsmap_err) {
+			err = mdsc->mdsmap_err;
+			dout("do_request mdsmap err %d\n", err);
+			goto finish;
+		}
 		dout("do_request no mds or not active, waiting for map\n");
 		list_add(&req->r_wait, &mdsc->waiting_for_map);
 		goto out;
@@ -2292,14 +2240,6 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 		ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir),
 				  CEPH_CAP_PIN);
 
-	/* deny access to directories with pool_ns layouts */
-	if (req->r_inode && S_ISDIR(req->r_inode->i_mode) &&
-	    ceph_inode(req->r_inode)->i_pool_ns_len)
-		return -EIO;
-	if (req->r_locked_dir &&
-	    ceph_inode(req->r_locked_dir)->i_pool_ns_len)
-		return -EIO;
-
 	/* issue */
 	mutex_lock(&mdsc->mutex);
 	__register_request(mdsc, req, dir);
@@ -2791,13 +2731,13 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		struct ceph_mds_cap_reconnect v2;
 		struct ceph_mds_cap_reconnect_v1 v1;
 	} rec;
-	size_t reclen;
 	struct ceph_inode_info *ci;
 	struct ceph_reconnect_state *recon_state = arg;
 	struct ceph_pagelist *pagelist = recon_state->pagelist;
 	char *path;
 	int pathlen, err;
 	u64 pathbase;
+	u64 snap_follows;
 	struct dentry *dentry;
 
 	ci = cap->ci;
@@ -2820,9 +2760,6 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		path = NULL;
 		pathlen = 0;
 	}
-	err = ceph_pagelist_encode_string(pagelist, path, pathlen);
-	if (err)
-		goto out_free;
 
 	spin_lock(&ci->i_ceph_lock);
 	cap->seq = 0;        /* reset cap seq */
@@ -2830,14 +2767,13 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	cap->mseq = 0;       /* and migrate_seq */
 	cap->cap_gen = cap->session->s_cap_gen;
 
-	if (recon_state->flock) {
+	if (recon_state->msg_version >= 2) {
 		rec.v2.cap_id = cpu_to_le64(cap->cap_id);
 		rec.v2.wanted = cpu_to_le32(__ceph_caps_wanted(ci));
 		rec.v2.issued = cpu_to_le32(cap->issued);
 		rec.v2.snaprealm = cpu_to_le64(ci->i_snap_realm->ino);
 		rec.v2.pathbase = cpu_to_le64(pathbase);
 		rec.v2.flock_len = 0;
-		reclen = sizeof(rec.v2);
 	} else {
 		rec.v1.cap_id = cpu_to_le64(cap->cap_id);
 		rec.v1.wanted = cpu_to_le32(__ceph_caps_wanted(ci));
@@ -2847,13 +2783,23 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		ceph_encode_timespec(&rec.v1.atime, &inode->i_atime);
 		rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino);
 		rec.v1.pathbase = cpu_to_le64(pathbase);
-		reclen = sizeof(rec.v1);
+	}
+
+	if (list_empty(&ci->i_cap_snaps)) {
+		snap_follows = 0;
+	} else {
+		struct ceph_cap_snap *capsnap =
+			list_first_entry(&ci->i_cap_snaps,
+					 struct ceph_cap_snap, ci_item);
+		snap_follows = capsnap->follows;
 	}
 	spin_unlock(&ci->i_ceph_lock);
 
-	if (recon_state->flock) {
+	if (recon_state->msg_version >= 2) {
 		int num_fcntl_locks, num_flock_locks;
 		struct ceph_filelock *flocks;
+		size_t struct_len, total_len = 0;
+		u8 struct_v = 0;
 
 encode_again:
 		ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks);
@@ -2872,20 +2818,51 @@ encode_again:
 				goto encode_again;
 			goto out_free;
 		}
+
+		if (recon_state->msg_version >= 3) {
+			/* version, compat_version and struct_len */
+			total_len = 2 * sizeof(u8) + sizeof(u32);
+			struct_v = 2;
+		}
 		/*
 		 * number of encoded locks is stable, so copy to pagelist
 		 */
-		rec.v2.flock_len = cpu_to_le32(2*sizeof(u32) +
-				    (num_fcntl_locks+num_flock_locks) *
-				    sizeof(struct ceph_filelock));
-		err = ceph_pagelist_append(pagelist, &rec, reclen);
-		if (!err)
-			err = ceph_locks_to_pagelist(flocks, pagelist,
-						     num_fcntl_locks,
-						     num_flock_locks);
+		struct_len = 2 * sizeof(u32) +
+			    (num_fcntl_locks + num_flock_locks) *
+			    sizeof(struct ceph_filelock);
+		rec.v2.flock_len = cpu_to_le32(struct_len);
+
+		struct_len += sizeof(rec.v2);
+		struct_len += sizeof(u32) + pathlen;
+
+		if (struct_v >= 2)
+			struct_len += sizeof(u64); /* snap_follows */
+
+		total_len += struct_len;
+		err = ceph_pagelist_reserve(pagelist, total_len);
+
+		if (!err) {
+			if (recon_state->msg_version >= 3) {
+				ceph_pagelist_encode_8(pagelist, struct_v);
+				ceph_pagelist_encode_8(pagelist, 1);
+				ceph_pagelist_encode_32(pagelist, struct_len);
+			}
+			ceph_pagelist_encode_string(pagelist, path, pathlen);
+			ceph_pagelist_append(pagelist, &rec, sizeof(rec.v2));
+			ceph_locks_to_pagelist(flocks, pagelist,
+					       num_fcntl_locks,
+					       num_flock_locks);
+			if (struct_v >= 2)
+				ceph_pagelist_encode_64(pagelist, snap_follows);
+		}
 		kfree(flocks);
 	} else {
-		err = ceph_pagelist_append(pagelist, &rec, reclen);
+		size_t size = sizeof(u32) + pathlen + sizeof(rec.v1);
+		err = ceph_pagelist_reserve(pagelist, size);
+		if (!err) {
+			ceph_pagelist_encode_string(pagelist, path, pathlen);
+			ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1));
+		}
 	}
 
 	recon_state->nr_caps++;
@@ -2976,7 +2953,12 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 
 	recon_state.nr_caps = 0;
 	recon_state.pagelist = pagelist;
-	recon_state.flock = session->s_con.peer_features & CEPH_FEATURE_FLOCK;
+	if (session->s_con.peer_features & CEPH_FEATURE_MDSENC)
+		recon_state.msg_version = 3;
+	else if (session->s_con.peer_features & CEPH_FEATURE_FLOCK)
+		recon_state.msg_version = 2;
+	else
+		recon_state.msg_version = 1;
 	err = iterate_session_caps(session, encode_caps_cb, &recon_state);
 	if (err < 0)
 		goto fail;
@@ -3005,8 +2987,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 			goto fail;
 	}
 
-	if (recon_state.flock)
-		reply->hdr.version = cpu_to_le16(2);
+	reply->hdr.version = cpu_to_le16(recon_state.msg_version);
 
 	/* raced with cap release? */
 	if (s_nr_caps != recon_state.nr_caps) {
@@ -3231,7 +3212,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 				msecs_to_jiffies(le32_to_cpu(h->duration_ms));
 
 			di->lease_seq = seq;
-			dentry->d_time = di->lease_renew_from + duration;
+			di->time = di->lease_renew_from + duration;
 			di->lease_renew_after = di->lease_renew_from +
 				(duration >> 1);
 			di->lease_renew_from = 0;
@@ -3297,47 +3278,6 @@ void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
 }
 
 /*
- * Preemptively release a lease we expect to invalidate anyway.
- * Pass @inode always, @dentry is optional.
- */
-void ceph_mdsc_lease_release(struct ceph_mds_client *mdsc, struct inode *inode,
-			     struct dentry *dentry)
-{
-	struct ceph_dentry_info *di;
-	struct ceph_mds_session *session;
-	u32 seq;
-
-	BUG_ON(inode == NULL);
-	BUG_ON(dentry == NULL);
-
-	/* is dentry lease valid? */
-	spin_lock(&dentry->d_lock);
-	di = ceph_dentry(dentry);
-	if (!di || !di->lease_session ||
-	    di->lease_session->s_mds < 0 ||
-	    di->lease_gen != di->lease_session->s_cap_gen ||
-	    !time_before(jiffies, dentry->d_time)) {
-		dout("lease_release inode %p dentry %p -- "
-		     "no lease\n",
-		     inode, dentry);
-		spin_unlock(&dentry->d_lock);
-		return;
-	}
-
-	/* we do have a lease on this dentry; note mds and seq */
-	session = ceph_get_mds_session(di->lease_session);
-	seq = di->lease_seq;
-	__ceph_mdsc_drop_dentry_lease(dentry);
-	spin_unlock(&dentry->d_lock);
-
-	dout("lease_release inode %p dentry %p to mds%d\n",
-	     inode, dentry, session->s_mds);
-	ceph_mdsc_lease_send_msg(session, inode, dentry,
-				 CEPH_MDS_LEASE_RELEASE, seq);
-	ceph_put_mds_session(session);
-}
-
-/*
  * drop all leases (and dentry refs) in preparation for umount
  */
 static void drop_leases(struct ceph_mds_client *mdsc)
@@ -3470,7 +3410,7 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	INIT_LIST_HEAD(&mdsc->snap_flush_list);
 	spin_lock_init(&mdsc->snap_flush_lock);
 	mdsc->last_cap_flush_tid = 1;
-	mdsc->cap_flush_tree = RB_ROOT;
+	INIT_LIST_HEAD(&mdsc->cap_flush_list);
 	INIT_LIST_HEAD(&mdsc->cap_dirty);
 	INIT_LIST_HEAD(&mdsc->cap_dirty_migrating);
 	mdsc->num_cap_flushing = 0;
@@ -3585,7 +3525,7 @@ restart:
 
 void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 {
-	u64 want_tid, want_flush, want_snap;
+	u64 want_tid, want_flush;
 
 	if (ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
 		return;
@@ -3598,17 +3538,19 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 	ceph_flush_dirty_caps(mdsc);
 	spin_lock(&mdsc->cap_dirty_lock);
 	want_flush = mdsc->last_cap_flush_tid;
+	if (!list_empty(&mdsc->cap_flush_list)) {
+		struct ceph_cap_flush *cf =
+			list_last_entry(&mdsc->cap_flush_list,
+					struct ceph_cap_flush, g_list);
+		cf->wake = true;
+	}
 	spin_unlock(&mdsc->cap_dirty_lock);
 
-	down_read(&mdsc->snap_rwsem);
-	want_snap = mdsc->last_snap_seq;
-	up_read(&mdsc->snap_rwsem);
-
-	dout("sync want tid %lld flush_seq %lld snap_seq %lld\n",
-	     want_tid, want_flush, want_snap);
+	dout("sync want tid %lld flush_seq %lld\n",
+	     want_tid, want_flush);
 
 	wait_unsafe_requests(mdsc, want_tid);
-	wait_caps_flush(mdsc, want_flush, want_snap);
+	wait_caps_flush(mdsc, want_flush);
 }
 
 /*
@@ -3729,11 +3671,86 @@ void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
 	dout("mdsc_destroy %p done\n", mdsc);
 }
 
+void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
+{
+	struct ceph_fs_client *fsc = mdsc->fsc;
+	const char *mds_namespace = fsc->mount_options->mds_namespace;
+	void *p = msg->front.iov_base;
+	void *end = p + msg->front.iov_len;
+	u32 epoch;
+	u32 map_len;
+	u32 num_fs;
+	u32 mount_fscid = (u32)-1;
+	u8 struct_v, struct_cv;
+	int err = -EINVAL;
+
+	ceph_decode_need(&p, end, sizeof(u32), bad);
+	epoch = ceph_decode_32(&p);
+
+	dout("handle_fsmap epoch %u\n", epoch);
+
+	ceph_decode_need(&p, end, 2 + sizeof(u32), bad);
+	struct_v = ceph_decode_8(&p);
+	struct_cv = ceph_decode_8(&p);
+	map_len = ceph_decode_32(&p);
+
+	ceph_decode_need(&p, end, sizeof(u32) * 3, bad);
+	p += sizeof(u32) * 2; /* skip epoch and legacy_client_fscid */
+
+	num_fs = ceph_decode_32(&p);
+	while (num_fs-- > 0) {
+		void *info_p, *info_end;
+		u32 info_len;
+		u8 info_v, info_cv;
+		u32 fscid, namelen;
+
+		ceph_decode_need(&p, end, 2 + sizeof(u32), bad);
+		info_v = ceph_decode_8(&p);
+		info_cv = ceph_decode_8(&p);
+		info_len = ceph_decode_32(&p);
+		ceph_decode_need(&p, end, info_len, bad);
+		info_p = p;
+		info_end = p + info_len;
+		p = info_end;
+
+		ceph_decode_need(&info_p, info_end, sizeof(u32) * 2, bad);
+		fscid = ceph_decode_32(&info_p);
+		namelen = ceph_decode_32(&info_p);
+		ceph_decode_need(&info_p, info_end, namelen, bad);
+
+		if (mds_namespace &&
+		    strlen(mds_namespace) == namelen &&
+		    !strncmp(mds_namespace, (char *)info_p, namelen)) {
+			mount_fscid = fscid;
+			break;
+		}
+	}
+
+	ceph_monc_got_map(&fsc->client->monc, CEPH_SUB_FSMAP, epoch);
+	if (mount_fscid != (u32)-1) {
+		fsc->client->monc.fs_cluster_id = mount_fscid;
+		ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP,
+				   0, true);
+		ceph_monc_renew_subs(&fsc->client->monc);
+	} else {
+		err = -ENOENT;
+		goto err_out;
+	}
+	return;
+bad:
+	pr_err("error decoding fsmap\n");
+err_out:
+	mutex_lock(&mdsc->mutex);
+	mdsc->mdsmap_err = -ENOENT;
+	__wake_requests(mdsc, &mdsc->waiting_for_map);
+	mutex_unlock(&mdsc->mutex);
+	return;
+}
 
 /*
  * handle mds map update.
  */
-void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
+void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 {
 	u32 epoch;
 	u32 maplen;
@@ -3840,7 +3857,10 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 
 	switch (type) {
 	case CEPH_MSG_MDS_MAP:
-		ceph_mdsc_handle_map(mdsc, msg);
+		ceph_mdsc_handle_mdsmap(mdsc, msg);
+		break;
+	case CEPH_MSG_FS_MAP_USER:
+		ceph_mdsc_handle_fsmap(mdsc, msg);
 		break;
 	case CEPH_MSG_CLIENT_SESSION:
 		handle_session(s, msg);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index e7d38aac7109..6b3679737d4a 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -45,6 +45,7 @@ struct ceph_mds_reply_info_in {
 	u32 inline_len;
 	char *inline_data;
 	u32 pool_ns_len;
+	char *pool_ns_data;
 };
 
 struct ceph_mds_reply_dir_entry {
@@ -151,7 +152,6 @@ struct ceph_mds_session {
 
 	/* protected by mutex */
 	struct list_head  s_cap_flushing;     /* inodes w/ flushing caps */
-	struct list_head  s_cap_snaps_flushing;
 	unsigned long     s_renew_requested; /* last time we sent a renew req */
 	u64               s_renew_seq;
 
@@ -275,8 +275,10 @@ struct ceph_mds_request {
 
 struct ceph_pool_perm {
 	struct rb_node node;
-	u32 pool;
 	int perm;
+	s64 pool;
+	size_t pool_ns_len;
+	char pool_ns[];
 };
 
 /*
@@ -290,6 +292,7 @@ struct ceph_mds_client {
 	struct completion       safe_umount_waiters;
 	wait_queue_head_t       session_close_wq;
 	struct list_head        waiting_for_map;
+	int 			mdsmap_err;
 
 	struct ceph_mds_session **sessions;    /* NULL for mds if no session */
 	atomic_t		num_sessions;
@@ -321,7 +324,7 @@ struct ceph_mds_client {
 	spinlock_t       snap_flush_lock;
 
 	u64               last_cap_flush_tid;
-	struct rb_root    cap_flush_tree;
+	struct list_head  cap_flush_list;
 	struct list_head  cap_dirty;        /* inodes with dirty caps */
 	struct list_head  cap_dirty_migrating; /* ...that are migration... */
 	int               num_cap_flushing; /* # caps we are flushing */
@@ -382,10 +385,6 @@ extern void ceph_mdsc_destroy(struct ceph_fs_client *fsc);
 
 extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);
 
-extern void ceph_mdsc_lease_release(struct ceph_mds_client *mdsc,
-				    struct inode *inode,
-				    struct dentry *dn);
-
 extern void ceph_invalidate_dir_request(struct ceph_mds_request *req);
 extern int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
 					   struct inode *dir);
@@ -420,8 +419,10 @@ extern void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
 				     struct dentry *dentry, char action,
 				     u32 seq);
 
-extern void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc,
-				 struct ceph_msg *msg);
+extern void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc,
+				    struct ceph_msg *msg);
+extern void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc,
+				   struct ceph_msg *msg);
 
 extern struct ceph_mds_session *
 ceph_mdsc_open_export_target_session(struct ceph_mds_client *mdsc, int target);
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 9caaa7ffc93f..9ff5219d849e 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -520,9 +520,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 	ihold(inode);
 
 	atomic_set(&capsnap->nref, 1);
-	capsnap->ci = ci;
 	INIT_LIST_HEAD(&capsnap->ci_item);
-	INIT_LIST_HEAD(&capsnap->flushing_item);
 
 	capsnap->follows = old_snapc->seq;
 	capsnap->issued = __ceph_caps_issued(ci, NULL);
@@ -551,7 +549,6 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 	ci->i_wrbuffer_ref_head = 0;
 	capsnap->context = old_snapc;
 	list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps);
-	old_snapc = NULL;
 
 	if (used & CEPH_CAP_FILE_WR) {
 		dout("queue_cap_snap %p cap_snap %p snapc %p"
@@ -563,6 +560,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 		__ceph_finish_cap_snap(ci, capsnap);
 	}
 	capsnap = NULL;
+	old_snapc = NULL;
 
 update_snapc:
 	if (ci->i_head_snapc) {
@@ -603,6 +601,8 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 		     capsnap->dirty_pages);
 		return 0;
 	}
+
+	ci->i_ceph_flags |= CEPH_I_FLUSH_SNAPS;
 	dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu\n",
 	     inode, capsnap, capsnap->context,
 	     capsnap->context->seq, ceph_cap_string(capsnap->dirty),
@@ -799,9 +799,7 @@ static void flush_snaps(struct ceph_mds_client *mdsc)
 		inode = &ci->vfs_inode;
 		ihold(inode);
 		spin_unlock(&mdsc->snap_flush_lock);
-		spin_lock(&ci->i_ceph_lock);
-		__ceph_flush_snaps(ci, &session, 0);
-		spin_unlock(&ci->i_ceph_lock);
+		ceph_flush_snaps(ci, &session);
 		iput(inode);
 		spin_lock(&mdsc->snap_flush_lock);
 	}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 91e02481ce06..e247f6f0feb7 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -108,7 +108,6 @@ static int ceph_sync_fs(struct super_block *sb, int wait)
  * mount options
  */
 enum {
-	Opt_mds_namespace,
 	Opt_wsize,
 	Opt_rsize,
 	Opt_rasize,
@@ -121,6 +120,7 @@ enum {
 	Opt_last_int,
 	/* int args above */
 	Opt_snapdirname,
+	Opt_mds_namespace,
 	Opt_last_string,
 	/* string args above */
 	Opt_dirstat,
@@ -144,7 +144,6 @@ enum {
 };
 
 static match_table_t fsopt_tokens = {
-	{Opt_mds_namespace, "mds_namespace=%d"},
 	{Opt_wsize, "wsize=%d"},
 	{Opt_rsize, "rsize=%d"},
 	{Opt_rasize, "rasize=%d"},
@@ -156,6 +155,7 @@ static match_table_t fsopt_tokens = {
 	{Opt_congestion_kb, "write_congestion_kb=%d"},
 	/* int args above */
 	{Opt_snapdirname, "snapdirname=%s"},
+	{Opt_mds_namespace, "mds_namespace=%s"},
 	/* string args above */
 	{Opt_dirstat, "dirstat"},
 	{Opt_nodirstat, "nodirstat"},
@@ -212,11 +212,14 @@ static int parse_fsopt_token(char *c, void *private)
 		if (!fsopt->snapdir_name)
 			return -ENOMEM;
 		break;
-
-		/* misc */
 	case Opt_mds_namespace:
-		fsopt->mds_namespace = intval;
+		fsopt->mds_namespace = kstrndup(argstr[0].from,
+						argstr[0].to-argstr[0].from,
+						GFP_KERNEL);
+		if (!fsopt->mds_namespace)
+			return -ENOMEM;
 		break;
+		/* misc */
 	case Opt_wsize:
 		fsopt->wsize = intval;
 		break;
@@ -302,6 +305,7 @@ static void destroy_mount_options(struct ceph_mount_options *args)
 {
 	dout("destroy_mount_options %p\n", args);
 	kfree(args->snapdir_name);
+	kfree(args->mds_namespace);
 	kfree(args->server_path);
 	kfree(args);
 }
@@ -333,6 +337,9 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt,
 	ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name);
 	if (ret)
 		return ret;
+	ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace);
+	if (ret)
+		return ret;
 
 	ret = strcmp_null(fsopt1->server_path, fsopt2->server_path);
 	if (ret)
@@ -376,7 +383,6 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
 	fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT;
 	fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
 	fsopt->congestion_kb = default_congestion_kb();
-	fsopt->mds_namespace = CEPH_FS_CLUSTER_ID_NONE;
 
 	/*
 	 * Distinguish the server list from the path in "dev_name".
@@ -469,8 +475,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 		seq_puts(m, ",noacl");
 #endif
 
-	if (fsopt->mds_namespace != CEPH_FS_CLUSTER_ID_NONE)
-		seq_printf(m, ",mds_namespace=%d", fsopt->mds_namespace);
+	if (fsopt->mds_namespace)
+		seq_printf(m, ",mds_namespace=%s", fsopt->mds_namespace);
 	if (fsopt->wsize)
 		seq_printf(m, ",wsize=%d", fsopt->wsize);
 	if (fsopt->rsize != CEPH_RSIZE_DEFAULT)
@@ -509,9 +515,11 @@ static int extra_mon_dispatch(struct ceph_client *client, struct ceph_msg *msg)
 
 	switch (type) {
 	case CEPH_MSG_MDS_MAP:
-		ceph_mdsc_handle_map(fsc->mdsc, msg);
+		ceph_mdsc_handle_mdsmap(fsc->mdsc, msg);
+		return 0;
+	case CEPH_MSG_FS_MAP_USER:
+		ceph_mdsc_handle_fsmap(fsc->mdsc, msg);
 		return 0;
-
 	default:
 		return -1;
 	}
@@ -543,8 +551,14 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 		goto fail;
 	}
 	fsc->client->extra_mon_dispatch = extra_mon_dispatch;
-	fsc->client->monc.fs_cluster_id = fsopt->mds_namespace;
-	ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP, 0, true);
+
+	if (fsopt->mds_namespace == NULL) {
+		ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP,
+				   0, true);
+	} else {
+		ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_FSMAP,
+				   0, false);
+	}
 
 	fsc->mount_options = fsopt;
 
@@ -672,8 +686,8 @@ static int __init init_caches(void)
 	if (ceph_dentry_cachep == NULL)
 		goto bad_dentry;
 
-	ceph_file_cachep = KMEM_CACHE(ceph_file_info,
-				      SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
+	ceph_file_cachep = KMEM_CACHE(ceph_file_info, SLAB_MEM_SPREAD);
+
 	if (ceph_file_cachep == NULL)
 		goto bad_file;
 
@@ -731,6 +745,7 @@ static const struct super_operations ceph_super_ops = {
 	.destroy_inode	= ceph_destroy_inode,
 	.write_inode    = ceph_write_inode,
 	.drop_inode	= ceph_drop_inode,
+	.evict_inode	= ceph_evict_inode,
 	.sync_fs        = ceph_sync_fs,
 	.put_super	= ceph_put_super,
 	.show_options   = ceph_show_options,
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 0168b49fb6ad..3e3fa9163059 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -62,7 +62,6 @@ struct ceph_mount_options {
 	int cap_release_safety;
 	int max_readdir;       /* max readdir result (entires) */
 	int max_readdir_bytes; /* max readdir result (bytes) */
-	int mds_namespace;
 
 	/*
 	 * everything above this point can be memcmp'd; everything below
@@ -70,6 +69,7 @@ struct ceph_mount_options {
 	 */
 
 	char *snapdir_name;   /* default ".snap" */
+	char *mds_namespace;  /* default NULL */
 	char *server_path;    /* default  "/" */
 };
 
@@ -147,6 +147,14 @@ struct ceph_cap {
 #define CHECK_CAPS_AUTHONLY   2  /* only check auth cap */
 #define CHECK_CAPS_FLUSH      4  /* flush any dirty caps */
 
+struct ceph_cap_flush {
+	u64 tid;
+	int caps; /* 0 means capsnap */
+	bool wake; /* wake up flush waiters when finish ? */
+	struct list_head g_list; // global
+	struct list_head i_list; // per inode
+};
+
 /*
  * Snapped cap state that is pending flush to mds.  When a snapshot occurs,
  * we first complete any in-process sync writes and writeback any dirty
@@ -154,10 +162,11 @@ struct ceph_cap {
  */
 struct ceph_cap_snap {
 	atomic_t nref;
-	struct ceph_inode_info *ci;
-	struct list_head ci_item, flushing_item;
+	struct list_head ci_item;
+
+	struct ceph_cap_flush cap_flush;
 
-	u64 follows, flush_tid;
+	u64 follows;
 	int issued, dirty;
 	struct ceph_snap_context *context;
 
@@ -186,16 +195,6 @@ static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
 	}
 }
 
-struct ceph_cap_flush {
-	u64 tid;
-	int caps;
-	struct rb_node g_node; // global
-	union {
-		struct rb_node i_node; // inode
-		struct list_head list;
-	};
-};
-
 /*
  * The frag tree describes how a directory is fragmented, potentially across
  * multiple metadata servers.  It is also used to indicate points where
@@ -246,7 +245,7 @@ struct ceph_dentry_info {
 	unsigned long lease_renew_after, lease_renew_from;
 	struct list_head lru;
 	struct dentry *dentry;
-	u64 time;
+	unsigned long time;
 	u64 offset;
 };
 
@@ -287,7 +286,6 @@ struct ceph_inode_info {
 
 	struct ceph_dir_layout i_dir_layout;
 	struct ceph_file_layout i_layout;
-	size_t i_pool_ns_len;
 	char *i_symlink;
 
 	/* for dirs */
@@ -311,7 +309,7 @@ struct ceph_inode_info {
 	 * overlapping, pipelined cap flushes to the mds.  we can probably
 	 * reduce the tid to 8 bits if we're concerned about inode size. */
 	struct ceph_cap_flush *i_prealloc_cap_flush;
-	struct rb_root i_cap_flush_tree;
+	struct list_head i_cap_flush_list;
 	wait_queue_head_t i_cap_wq;      /* threads waiting on a capability */
 	unsigned long i_hold_caps_min; /* jiffies */
 	unsigned long i_hold_caps_max; /* jiffies */
@@ -322,7 +320,7 @@ struct ceph_inode_info {
 						    dirty|flushing caps */
 	unsigned i_snap_caps;           /* cap bits for snapped files */
 
-	int i_nr_by_mode[CEPH_FILE_MODE_NUM];  /* open file counts */
+	int i_nr_by_mode[CEPH_FILE_MODE_BITS];  /* open file counts */
 
 	struct mutex i_truncate_mutex;
 	u32 i_truncate_seq;        /* last truncate to smaller size */
@@ -471,6 +469,8 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
 #define CEPH_I_POOL_WR		(1 << 6)  /* can write to pool */
 #define CEPH_I_SEC_INITED	(1 << 7)  /* security initialized */
 #define CEPH_I_CAP_DROPPED	(1 << 8)  /* caps were forcibly dropped */
+#define CEPH_I_KICK_FLUSH	(1 << 9)  /* kick flushing caps */
+#define CEPH_I_FLUSH_SNAPS	(1 << 10) /* need flush snapss */
 
 static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
 					   long long release_count,
@@ -750,6 +750,7 @@ extern const struct inode_operations ceph_file_iops;
 extern struct inode *ceph_alloc_inode(struct super_block *sb);
 extern void ceph_destroy_inode(struct inode *inode);
 extern int ceph_drop_inode(struct inode *inode);
+extern void ceph_evict_inode(struct inode *inode);
 
 extern struct inode *ceph_get_inode(struct super_block *sb,
 				    struct ceph_vino vino);
@@ -890,9 +891,8 @@ extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps);
 extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had);
 extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				       struct ceph_snap_context *snapc);
-extern void __ceph_flush_snaps(struct ceph_inode_info *ci,
-			       struct ceph_mds_session **psession,
-			       int again);
+extern void ceph_flush_snaps(struct ceph_inode_info *ci,
+			     struct ceph_mds_session **psession);
 extern void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 			    struct ceph_mds_session *session);
 extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc);
@@ -907,10 +907,7 @@ extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
 			 loff_t endoff, int *got, struct page **pinned_page);
 
 /* for counting open files by mode */
-static inline void __ceph_get_fmode(struct ceph_inode_info *ci, int mode)
-{
-	ci->i_nr_by_mode[mode]++;
-}
+extern void __ceph_get_fmode(struct ceph_inode_info *ci, int mode);
 extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode);
 
 /* addr.c */
@@ -931,6 +928,7 @@ extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 extern int ceph_release(struct inode *inode, struct file *filp);
 extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 				  char *data, size_t len);
+extern void ceph_sync_write_wait(struct inode *inode);
 /* dir.c */
 extern const struct file_operations ceph_dir_fops;
 extern const struct file_operations ceph_snapdir_fops;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 4870b29df224..adc231892b0d 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -57,81 +57,88 @@ struct ceph_vxattr {
 
 static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
 {
-	size_t s;
-	char *p = (char *)&ci->i_layout;
-
-	for (s = 0; s < sizeof(ci->i_layout); s++, p++)
-		if (*p)
-			return true;
-	return false;
+	struct ceph_file_layout *fl = &ci->i_layout;
+	return (fl->stripe_unit > 0 || fl->stripe_count > 0 ||
+		fl->object_size > 0 || fl->pool_id >= 0 ||
+		rcu_dereference_raw(fl->pool_ns) != NULL);
 }
 
 static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
 				   size_t size)
 {
-	int ret;
 	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
-	s64 pool = ceph_file_layout_pg_pool(ci->i_layout);
+	struct ceph_string *pool_ns;
+	s64 pool = ci->i_layout.pool_id;
 	const char *pool_name;
+	const char *ns_field = " pool_namespace=";
 	char buf[128];
+	size_t len, total_len = 0;
+	int ret;
+
+	pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
 
 	dout("ceph_vxattrcb_layout %p\n", &ci->vfs_inode);
 	down_read(&osdc->lock);
 	pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
 	if (pool_name) {
-		size_t len = strlen(pool_name);
-		ret = snprintf(buf, sizeof(buf),
-		"stripe_unit=%lld stripe_count=%lld object_size=%lld pool=",
-		(unsigned long long)ceph_file_layout_su(ci->i_layout),
-		(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
-	        (unsigned long long)ceph_file_layout_object_size(ci->i_layout));
-		if (!size) {
-			ret += len;
-		} else if (ret + len > size) {
-			ret = -ERANGE;
-		} else {
-			memcpy(val, buf, ret);
+		len = snprintf(buf, sizeof(buf),
+		"stripe_unit=%u stripe_count=%u object_size=%u pool=",
+		ci->i_layout.stripe_unit, ci->i_layout.stripe_count,
+	        ci->i_layout.object_size);
+		total_len = len + strlen(pool_name);
+	} else {
+		len = snprintf(buf, sizeof(buf),
+		"stripe_unit=%u stripe_count=%u object_size=%u pool=%lld",
+		ci->i_layout.stripe_unit, ci->i_layout.stripe_count,
+	        ci->i_layout.object_size, (unsigned long long)pool);
+		total_len = len;
+	}
+
+	if (pool_ns)
+		total_len += strlen(ns_field) + pool_ns->len;
+
+	if (!size) {
+		ret = total_len;
+	} else if (total_len > size) {
+		ret = -ERANGE;
+	} else {
+		memcpy(val, buf, len);
+		ret = len;
+		if (pool_name) {
+			len = strlen(pool_name);
 			memcpy(val + ret, pool_name, len);
 			ret += len;
 		}
-	} else {
-		ret = snprintf(buf, sizeof(buf),
-		"stripe_unit=%lld stripe_count=%lld object_size=%lld pool=%lld",
-		(unsigned long long)ceph_file_layout_su(ci->i_layout),
-		(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
-	        (unsigned long long)ceph_file_layout_object_size(ci->i_layout),
-		(unsigned long long)pool);
-		if (size) {
-			if (ret <= size)
-				memcpy(val, buf, ret);
-			else
-				ret = -ERANGE;
+		if (pool_ns) {
+			len = strlen(ns_field);
+			memcpy(val + ret, ns_field, len);
+			ret += len;
+			memcpy(val + ret, pool_ns->str, pool_ns->len);
+			ret += pool_ns->len;
 		}
 	}
 	up_read(&osdc->lock);
+	ceph_put_string(pool_ns);
 	return ret;
 }
 
 static size_t ceph_vxattrcb_layout_stripe_unit(struct ceph_inode_info *ci,
 					       char *val, size_t size)
 {
-	return snprintf(val, size, "%lld",
-			(unsigned long long)ceph_file_layout_su(ci->i_layout));
+	return snprintf(val, size, "%u", ci->i_layout.stripe_unit);
 }
 
 static size_t ceph_vxattrcb_layout_stripe_count(struct ceph_inode_info *ci,
 						char *val, size_t size)
 {
-	return snprintf(val, size, "%lld",
-	       (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout));
+	return snprintf(val, size, "%u", ci->i_layout.stripe_count);
 }
 
 static size_t ceph_vxattrcb_layout_object_size(struct ceph_inode_info *ci,
 					       char *val, size_t size)
 {
-	return snprintf(val, size, "%lld",
-	       (unsigned long long)ceph_file_layout_object_size(ci->i_layout));
+	return snprintf(val, size, "%u", ci->i_layout.object_size);
 }
 
 static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
@@ -140,7 +147,7 @@ static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
 	int ret;
 	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
-	s64 pool = ceph_file_layout_pg_pool(ci->i_layout);
+	s64 pool = ci->i_layout.pool_id;
 	const char *pool_name;
 
 	down_read(&osdc->lock);
@@ -153,6 +160,18 @@ static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
 	return ret;
 }
 
+static size_t ceph_vxattrcb_layout_pool_namespace(struct ceph_inode_info *ci,
+						  char *val, size_t size)
+{
+	int ret = 0;
+	struct ceph_string *ns = ceph_try_get_string(ci->i_layout.pool_ns);
+	if (ns) {
+		ret = snprintf(val, size, "%.*s", (int)ns->len, ns->str);
+		ceph_put_string(ns);
+	}
+	return ret;
+}
+
 /* directories */
 
 static size_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val,
@@ -241,6 +260,7 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
 	XATTR_LAYOUT_FIELD(dir, layout, stripe_count),
 	XATTR_LAYOUT_FIELD(dir, layout, object_size),
 	XATTR_LAYOUT_FIELD(dir, layout, pool),
+	XATTR_LAYOUT_FIELD(dir, layout, pool_namespace),
 	XATTR_NAME_CEPH(dir, entries),
 	XATTR_NAME_CEPH(dir, files),
 	XATTR_NAME_CEPH(dir, subdirs),
@@ -268,6 +288,7 @@ static struct ceph_vxattr ceph_file_vxattrs[] = {
 	XATTR_LAYOUT_FIELD(file, layout, stripe_count),
 	XATTR_LAYOUT_FIELD(file, layout, object_size),
 	XATTR_LAYOUT_FIELD(file, layout, pool),
+	XATTR_LAYOUT_FIELD(file, layout, pool_namespace),
 	{ .name = NULL, 0 }	/* Required table terminator */
 };
 static size_t ceph_file_vxattrs_name_size;	/* total size of all names */
diff --git a/fs/exec.c b/fs/exec.c
index ca239fc86d8d..a1789cd684bf 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -866,7 +866,8 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 		goto out;
 	}
 
-	*buf = vmalloc(i_size);
+	if (id != READING_FIRMWARE_PREALLOC_BUFFER)
+		*buf = vmalloc(i_size);
 	if (!*buf) {
 		ret = -ENOMEM;
 		goto out;
@@ -897,8 +898,10 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 
 out_free:
 	if (ret < 0) {
-		vfree(*buf);
-		*buf = NULL;
+		if (id != READING_FIRMWARE_PREALLOC_BUFFER) {
+			vfree(*buf);
+			*buf = NULL;
+		}
 	}
 
 out:
diff --git a/fs/inode.c b/fs/inode.c
index 9cef4e16aeda..ad445542c285 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -345,7 +345,7 @@ EXPORT_SYMBOL(inc_nlink);
 void address_space_init_once(struct address_space *mapping)
 {
 	memset(mapping, 0, sizeof(*mapping));
-	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
+	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC | __GFP_ACCOUNT);
 	spin_lock_init(&mapping->tree_lock);
 	init_rwsem(&mapping->i_mmap_rwsem);
 	INIT_LIST_HEAD(&mapping->private_list);
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 8664417955a2..6abdda209642 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_NFS_FS) += nfs.o
 
 CFLAGS_nfstrace.o += -I$(src)
 nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \
-			   direct.o pagelist.o read.o symlink.o unlink.o \
+			   io.o direct.o pagelist.o read.o symlink.o unlink.o \
 			   write.o namespace.o mount_clnt.o nfstrace.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
 nfs-$(CONFIG_SYSCTL)	+= sysctl.o
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index e5b89675263e..a69ef4e9c24c 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -65,8 +65,8 @@ nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 		if (!p)
 			return -EIO;
 		b->simple.nr_sigs = be32_to_cpup(p++);
-		if (!b->simple.nr_sigs) {
-			dprintk("no signature\n");
+		if (!b->simple.nr_sigs || b->simple.nr_sigs > PNFS_BLOCK_MAX_UUIDS) {
+			dprintk("Bad signature count: %d\n", b->simple.nr_sigs);
 			return -EIO;
 		}
 
@@ -89,7 +89,8 @@ nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 			memcpy(&b->simple.sigs[i].sig, p,
 				b->simple.sigs[i].sig_len);
 
-			b->simple.len += 8 + 4 + b->simple.sigs[i].sig_len;
+			b->simple.len += 8 + 4 + \
+				(XDR_QUADLEN(b->simple.sigs[i].sig_len) << 2);
 		}
 		break;
 	case PNFS_BLOCK_VOLUME_SLICE:
@@ -104,7 +105,12 @@ nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 		p = xdr_inline_decode(xdr, 4);
 		if (!p)
 			return -EIO;
+
 		b->concat.volumes_count = be32_to_cpup(p++);
+		if (b->concat.volumes_count > PNFS_BLOCK_MAX_DEVICES) {
+			dprintk("Too many volumes: %d\n", b->concat.volumes_count);
+			return -EIO;
+		}
 
 		p = xdr_inline_decode(xdr, b->concat.volumes_count * 4);
 		if (!p)
@@ -116,8 +122,13 @@ nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 		p = xdr_inline_decode(xdr, 8 + 4);
 		if (!p)
 			return -EIO;
+
 		p = xdr_decode_hyper(p, &b->stripe.chunk_size);
 		b->stripe.volumes_count = be32_to_cpup(p++);
+		if (b->stripe.volumes_count > PNFS_BLOCK_MAX_DEVICES) {
+			dprintk("Too many volumes: %d\n", b->stripe.volumes_count);
+			return -EIO;
+		}
 
 		p = xdr_inline_decode(xdr, b->stripe.volumes_count * 4);
 		if (!p)
@@ -224,18 +235,20 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d,
 		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
 {
 	struct pnfs_block_volume *v = &volumes[idx];
+	struct block_device *bdev;
 	dev_t dev;
 
 	dev = bl_resolve_deviceid(server, v, gfp_mask);
 	if (!dev)
 		return -EIO;
 
-	d->bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_WRITE, NULL);
-	if (IS_ERR(d->bdev)) {
+	bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_WRITE, NULL);
+	if (IS_ERR(bdev)) {
 		printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n",
-			MAJOR(dev), MINOR(dev), PTR_ERR(d->bdev));
-		return PTR_ERR(d->bdev);
+			MAJOR(dev), MINOR(dev), PTR_ERR(bdev));
+		return PTR_ERR(bdev);
 	}
+	d->bdev = bdev;
 
 
 	d->len = i_size_read(d->bdev->bd_inode);
@@ -287,44 +300,71 @@ bl_validate_designator(struct pnfs_block_volume *v)
 	}
 }
 
+/*
+ * Try to open the udev path for the WWN.  At least on Debian the udev
+ * by-id path will always point to the dm-multipath device if one exists.
+ */
+static struct block_device *
+bl_open_udev_path(struct pnfs_block_volume *v)
+{
+	struct block_device *bdev;
+	const char *devname;
+
+	devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%*phN",
+				v->scsi.designator_len, v->scsi.designator);
+	if (!devname)
+		return ERR_PTR(-ENOMEM);
+
+	bdev = blkdev_get_by_path(devname, FMODE_READ | FMODE_WRITE, NULL);
+	if (IS_ERR(bdev)) {
+		pr_warn("pNFS: failed to open device %s (%ld)\n",
+			devname, PTR_ERR(bdev));
+	}
+
+	kfree(devname);
+	return bdev;
+}
+
+/*
+ * Try to open the RH/Fedora specific dm-mpath udev path for this WWN, as the
+ * wwn- links will only point to the first discovered SCSI device there.
+ */
+static struct block_device *
+bl_open_dm_mpath_udev_path(struct pnfs_block_volume *v)
+{
+	struct block_device *bdev;
+	const char *devname;
+
+	devname = kasprintf(GFP_KERNEL,
+			"/dev/disk/by-id/dm-uuid-mpath-%d%*phN",
+			v->scsi.designator_type,
+			v->scsi.designator_len, v->scsi.designator);
+	if (!devname)
+		return ERR_PTR(-ENOMEM);
+
+	bdev = blkdev_get_by_path(devname, FMODE_READ | FMODE_WRITE, NULL);
+	kfree(devname);
+	return bdev;
+}
+
 static int
 bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
 {
 	struct pnfs_block_volume *v = &volumes[idx];
+	struct block_device *bdev;
 	const struct pr_ops *ops;
-	const char *devname;
 	int error;
 
 	if (!bl_validate_designator(v))
 		return -EINVAL;
 
-	switch (v->scsi.designator_len) {
-	case 8:
-		devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%8phN",
-				v->scsi.designator);
-		break;
-	case 12:
-		devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%12phN",
-				v->scsi.designator);
-		break;
-	case 16:
-		devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/wwn-0x%16phN",
-				v->scsi.designator);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	d->bdev = blkdev_get_by_path(devname, FMODE_READ, NULL);
-	if (IS_ERR(d->bdev)) {
-		pr_warn("pNFS: failed to open device %s (%ld)\n",
-			devname, PTR_ERR(d->bdev));
-		kfree(devname);
-		return PTR_ERR(d->bdev);
-	}
-
-	kfree(devname);
+	bdev = bl_open_dm_mpath_udev_path(v);
+	if (IS_ERR(bdev))
+		bdev = bl_open_udev_path(v);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
+	d->bdev = bdev;
 
 	d->len = i_size_read(d->bdev->bd_inode);
 	d->map = bl_map_simple;
@@ -352,7 +392,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 	return 0;
 
 out_blkdev_put:
-	blkdev_put(d->bdev, FMODE_READ);
+	blkdev_put(d->bdev, FMODE_READ | FMODE_WRITE);
 	return error;
 }
 
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
index 720b3ff55fa9..992bcb19c11e 100644
--- a/fs/nfs/blocklayout/extent_tree.c
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -121,6 +121,16 @@ ext_try_to_merge_right(struct rb_root *root, struct pnfs_block_extent *be)
 	return be;
 }
 
+static void __ext_put_deviceids(struct list_head *head)
+{
+	struct pnfs_block_extent *be, *tmp;
+
+	list_for_each_entry_safe(be, tmp, head, be_list) {
+		nfs4_put_deviceid_node(be->be_device);
+		kfree(be);
+	}
+}
+
 static void
 __ext_tree_insert(struct rb_root *root,
 		struct pnfs_block_extent *new, bool merge_ok)
@@ -163,7 +173,8 @@ free_new:
 }
 
 static int
-__ext_tree_remove(struct rb_root *root, sector_t start, sector_t end)
+__ext_tree_remove(struct rb_root *root,
+		sector_t start, sector_t end, struct list_head *tmp)
 {
 	struct pnfs_block_extent *be;
 	sector_t len1 = 0, len2 = 0;
@@ -223,8 +234,7 @@ __ext_tree_remove(struct rb_root *root, sector_t start, sector_t end)
 			struct pnfs_block_extent *next = ext_tree_next(be);
 
 			rb_erase(&be->be_node, root);
-			nfs4_put_deviceid_node(be->be_device);
-			kfree(be);
+			list_add_tail(&be->be_list, tmp);
 			be = next;
 		}
 
@@ -350,16 +360,18 @@ int ext_tree_remove(struct pnfs_block_layout *bl, bool rw,
 		sector_t start, sector_t end)
 {
 	int err, err2;
+	LIST_HEAD(tmp);
 
 	spin_lock(&bl->bl_ext_lock);
-	err = __ext_tree_remove(&bl->bl_ext_ro, start, end);
+	err = __ext_tree_remove(&bl->bl_ext_ro, start, end, &tmp);
 	if (rw) {
-		err2 = __ext_tree_remove(&bl->bl_ext_rw, start, end);
+		err2 = __ext_tree_remove(&bl->bl_ext_rw, start, end, &tmp);
 		if (!err)
 			err = err2;
 	}
 	spin_unlock(&bl->bl_ext_lock);
 
+	__ext_put_deviceids(&tmp);
 	return err;
 }
 
@@ -396,12 +408,13 @@ ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
 	sector_t end = start + len;
 	struct pnfs_block_extent *be;
 	int err = 0;
+	LIST_HEAD(tmp);
 
 	spin_lock(&bl->bl_ext_lock);
 	/*
 	 * First remove all COW extents or holes from written to range.
 	 */
-	err = __ext_tree_remove(&bl->bl_ext_ro, start, end);
+	err = __ext_tree_remove(&bl->bl_ext_ro, start, end, &tmp);
 	if (err)
 		goto out;
 
@@ -459,6 +472,8 @@ ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
 	}
 out:
 	spin_unlock(&bl->bl_ext_lock);
+
+	__ext_put_deviceids(&tmp);
 	return err;
 }
 
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index aaa2e8d3df6f..c92a75e066a6 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -119,27 +119,30 @@ out:
  * hashed by filehandle.
  */
 static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
-		struct nfs_fh *fh, nfs4_stateid *stateid)
+		struct nfs_fh *fh)
 {
 	struct nfs_server *server;
+	struct nfs_inode *nfsi;
 	struct inode *ino;
 	struct pnfs_layout_hdr *lo;
 
+restart:
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
 		list_for_each_entry(lo, &server->layouts, plh_layouts) {
-			if (!nfs4_stateid_match_other(&lo->plh_stateid, stateid))
+			nfsi = NFS_I(lo->plh_inode);
+			if (nfs_compare_fh(fh, &nfsi->fh))
 				continue;
-			if (nfs_compare_fh(fh, &NFS_I(lo->plh_inode)->fh))
+			if (nfsi->layout != lo)
 				continue;
 			ino = igrab(lo->plh_inode);
 			if (!ino)
 				break;
 			spin_lock(&ino->i_lock);
 			/* Is this layout in the process of being freed? */
-			if (NFS_I(ino)->layout != lo) {
+			if (nfsi->layout != lo) {
 				spin_unlock(&ino->i_lock);
 				iput(ino);
-				break;
+				goto restart;
 			}
 			pnfs_get_layout_hdr(lo);
 			spin_unlock(&ino->i_lock);
@@ -151,13 +154,13 @@ static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
 }
 
 static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp,
-		struct nfs_fh *fh, nfs4_stateid *stateid)
+		struct nfs_fh *fh)
 {
 	struct pnfs_layout_hdr *lo;
 
 	spin_lock(&clp->cl_lock);
 	rcu_read_lock();
-	lo = get_layout_by_fh_locked(clp, fh, stateid);
+	lo = get_layout_by_fh_locked(clp, fh);
 	rcu_read_unlock();
 	spin_unlock(&clp->cl_lock);
 
@@ -167,17 +170,39 @@ static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp,
 /*
  * Enforce RFC5661 section 12.5.5.2.1. (Layout Recall and Return Sequencing)
  */
-static bool pnfs_check_stateid_sequence(struct pnfs_layout_hdr *lo,
+static u32 pnfs_check_callback_stateid(struct pnfs_layout_hdr *lo,
 					const nfs4_stateid *new)
 {
 	u32 oldseq, newseq;
 
-	oldseq = be32_to_cpu(lo->plh_stateid.seqid);
+	/* Is the stateid still not initialised? */
+	if (!pnfs_layout_is_valid(lo))
+		return NFS4ERR_DELAY;
+
+	/* Mismatched stateid? */
+	if (!nfs4_stateid_match_other(&lo->plh_stateid, new))
+		return NFS4ERR_BAD_STATEID;
+
 	newseq = be32_to_cpu(new->seqid);
+	/* Are we already in a layout recall situation? */
+	if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags) &&
+	    lo->plh_return_seq != 0) {
+		if (newseq < lo->plh_return_seq)
+			return NFS4ERR_OLD_STATEID;
+		if (newseq > lo->plh_return_seq)
+			return NFS4ERR_DELAY;
+		goto out;
+	}
 
+	/* Check that the stateid matches what we think it should be. */
+	oldseq = be32_to_cpu(lo->plh_stateid.seqid);
 	if (newseq > oldseq + 1)
-		return false;
-	return true;
+		return NFS4ERR_DELAY;
+	/* Crazy server! */
+	if (newseq <= oldseq)
+		return NFS4ERR_OLD_STATEID;
+out:
+	return NFS_OK;
 }
 
 static u32 initiate_file_draining(struct nfs_client *clp,
@@ -188,7 +213,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
 	LIST_HEAD(free_me_list);
 
-	lo = get_layout_by_fh(clp, &args->cbl_fh, &args->cbl_stateid);
+	lo = get_layout_by_fh(clp, &args->cbl_fh);
 	if (!lo) {
 		trace_nfs4_cb_layoutrecall_file(clp, &args->cbl_fh, NULL,
 				&args->cbl_stateid, -rv);
@@ -196,18 +221,15 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	}
 
 	ino = lo->plh_inode;
+	pnfs_layoutcommit_inode(ino, false);
+
 
 	spin_lock(&ino->i_lock);
-	if (!pnfs_check_stateid_sequence(lo, &args->cbl_stateid)) {
-		rv = NFS4ERR_DELAY;
+	rv = pnfs_check_callback_stateid(lo, &args->cbl_stateid);
+	if (rv != NFS_OK)
 		goto unlock;
-	}
 	pnfs_set_layout_stateid(lo, &args->cbl_stateid, true);
-	spin_unlock(&ino->i_lock);
-
-	pnfs_layoutcommit_inode(ino, false);
 
-	spin_lock(&ino->i_lock);
 	/*
 	 * Enforce RFC5661 Section 12.5.5.2.1.5 (Bulk Recall and Return)
 	 */
@@ -223,11 +245,13 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 		goto unlock;
 	}
 
+	/* Embrace your forgetfulness! */
+	rv = NFS4ERR_NOMATCHING_LAYOUT;
+
 	if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
 		NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo,
 			&args->cbl_range);
 	}
-	pnfs_mark_layout_returned_if_empty(lo);
 unlock:
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&free_me_list);
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index d81f96aacd51..656f68f7fe53 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -925,7 +925,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	if (hdr_arg.minorversion == 0) {
 		cps.clp = nfs4_find_client_ident(SVC_NET(rqstp), hdr_arg.cb_ident);
 		if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp))
-			return rpc_drop_reply;
+			goto out_invalidcred;
 	}
 
 	cps.minorversion = hdr_arg.minorversion;
@@ -953,6 +953,10 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	nfs_put_client(cps.clp);
 	dprintk("%s: done, status = %u\n", __func__, ntohl(status));
 	return rpc_success;
+
+out_invalidcred:
+	pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n");
+	return rpc_autherr_badcred;
 }
 
 /*
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 487c5607d52f..003ebce4bbc4 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -367,8 +367,6 @@ nfs_found_client(const struct nfs_client_initdata *cl_init,
  */
 struct nfs_client *
 nfs_get_client(const struct nfs_client_initdata *cl_init,
-	       const struct rpc_timeout *timeparms,
-	       const char *ip_addr,
 	       rpc_authflavor_t authflavour)
 {
 	struct nfs_client *clp, *new = NULL;
@@ -399,7 +397,7 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 					&nn->nfs_client_list);
 			spin_unlock(&nn->nfs_client_lock);
 			new->cl_flags = cl_init->init_flags;
-			return rpc_ops->init_client(new, timeparms, ip_addr);
+			return rpc_ops->init_client(new, cl_init);
 		}
 
 		spin_unlock(&nn->nfs_client_lock);
@@ -470,7 +468,7 @@ EXPORT_SYMBOL_GPL(nfs_init_timeout_values);
  * Create an RPC client handle
  */
 int nfs_create_rpc_client(struct nfs_client *clp,
-			  const struct rpc_timeout *timeparms,
+			  const struct nfs_client_initdata *cl_init,
 			  rpc_authflavor_t flavor)
 {
 	struct rpc_clnt		*clnt = NULL;
@@ -479,8 +477,9 @@ int nfs_create_rpc_client(struct nfs_client *clp,
 		.protocol	= clp->cl_proto,
 		.address	= (struct sockaddr *)&clp->cl_addr,
 		.addrsize	= clp->cl_addrlen,
-		.timeout	= timeparms,
+		.timeout	= cl_init->timeparms,
 		.servername	= clp->cl_hostname,
+		.nodename	= cl_init->nodename,
 		.program	= &nfs_program,
 		.version	= clp->rpc_ops->version,
 		.authflavor	= flavor,
@@ -591,14 +590,12 @@ EXPORT_SYMBOL_GPL(nfs_init_server_rpcclient);
  * nfs_init_client - Initialise an NFS2 or NFS3 client
  *
  * @clp: nfs_client to initialise
- * @timeparms: timeout parameters for underlying RPC transport
- * @ip_addr: IP presentation address (not used)
+ * @cl_init: Initialisation parameters
  *
  * Returns pointer to an NFS client, or an ERR_PTR value.
  */
 struct nfs_client *nfs_init_client(struct nfs_client *clp,
-		    const struct rpc_timeout *timeparms,
-		    const char *ip_addr)
+				   const struct nfs_client_initdata *cl_init)
 {
 	int error;
 
@@ -612,7 +609,7 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp,
 	 * Create a client RPC handle for doing FSSTAT with UNIX auth only
 	 * - RFC 2623, sec 2.3.2
 	 */
-	error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
+	error = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_UNIX);
 	if (error < 0)
 		goto error;
 	nfs_mark_client_ready(clp, NFS_CS_READY);
@@ -633,6 +630,7 @@ static int nfs_init_server(struct nfs_server *server,
 			   const struct nfs_parsed_mount_data *data,
 			   struct nfs_subversion *nfs_mod)
 {
+	struct rpc_timeout timeparms;
 	struct nfs_client_initdata cl_init = {
 		.hostname = data->nfs_server.hostname,
 		.addr = (const struct sockaddr *)&data->nfs_server.address,
@@ -640,8 +638,8 @@ static int nfs_init_server(struct nfs_server *server,
 		.nfs_mod = nfs_mod,
 		.proto = data->nfs_server.protocol,
 		.net = data->net,
+		.timeparms = &timeparms,
 	};
-	struct rpc_timeout timeparms;
 	struct nfs_client *clp;
 	int error;
 
@@ -653,7 +651,7 @@ static int nfs_init_server(struct nfs_server *server,
 		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 
 	/* Allocate or find a client reference we can use */
-	clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX);
+	clp = nfs_get_client(&cl_init, RPC_AUTH_UNIX);
 	if (IS_ERR(clp)) {
 		dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp));
 		return PTR_ERR(clp);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index baaa38859899..177fefb26c18 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2252,21 +2252,37 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, st
 	return NULL;
 }
 
-static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res)
+static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res, bool may_block)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_access_entry *cache;
-	int err = -ENOENT;
+	bool retry = true;
+	int err;
 
 	spin_lock(&inode->i_lock);
-	if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS)
-		goto out_zap;
-	cache = nfs_access_search_rbtree(inode, cred);
-	if (cache == NULL)
-		goto out;
-	if (!nfs_have_delegated_attributes(inode) &&
-	    !time_in_range_open(jiffies, cache->jiffies, cache->jiffies + nfsi->attrtimeo))
-		goto out_stale;
+	for(;;) {
+		if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS)
+			goto out_zap;
+		cache = nfs_access_search_rbtree(inode, cred);
+		err = -ENOENT;
+		if (cache == NULL)
+			goto out;
+		/* Found an entry, is our attribute cache valid? */
+		if (!nfs_attribute_cache_expired(inode) &&
+		    !(nfsi->cache_validity & NFS_INO_INVALID_ATTR))
+			break;
+		err = -ECHILD;
+		if (!may_block)
+			goto out;
+		if (!retry)
+			goto out_zap;
+		spin_unlock(&inode->i_lock);
+		err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+		if (err)
+			return err;
+		spin_lock(&inode->i_lock);
+		retry = false;
+	}
 	res->jiffies = cache->jiffies;
 	res->cred = cache->cred;
 	res->mask = cache->mask;
@@ -2275,12 +2291,6 @@ static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, str
 out:
 	spin_unlock(&inode->i_lock);
 	return err;
-out_stale:
-	rb_erase(&cache->rb_node, &nfsi->access_cache);
-	list_del(&cache->lru);
-	spin_unlock(&inode->i_lock);
-	nfs_access_free_entry(cache);
-	return -ENOENT;
 out_zap:
 	spin_unlock(&inode->i_lock);
 	nfs_access_zap_cache(inode);
@@ -2307,13 +2317,12 @@ static int nfs_access_get_cached_rcu(struct inode *inode, struct rpc_cred *cred,
 		cache = NULL;
 	if (cache == NULL)
 		goto out;
-	if (!nfs_have_delegated_attributes(inode) &&
-	    !time_in_range_open(jiffies, cache->jiffies, cache->jiffies + nfsi->attrtimeo))
+	err = nfs_revalidate_inode_rcu(NFS_SERVER(inode), inode);
+	if (err)
 		goto out;
 	res->jiffies = cache->jiffies;
 	res->cred = cache->cred;
 	res->mask = cache->mask;
-	err = 0;
 out:
 	rcu_read_unlock();
 	return err;
@@ -2402,18 +2411,19 @@ EXPORT_SYMBOL_GPL(nfs_access_set_mask);
 static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 {
 	struct nfs_access_entry cache;
+	bool may_block = (mask & MAY_NOT_BLOCK) == 0;
 	int status;
 
 	trace_nfs_access_enter(inode);
 
 	status = nfs_access_get_cached_rcu(inode, cred, &cache);
 	if (status != 0)
-		status = nfs_access_get_cached(inode, cred, &cache);
+		status = nfs_access_get_cached(inode, cred, &cache, may_block);
 	if (status == 0)
 		goto out_cached;
 
 	status = -ECHILD;
-	if (mask & MAY_NOT_BLOCK)
+	if (!may_block)
 		goto out;
 
 	/* Be clever: ask server to check for all possible rights */
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index e6210ead71d0..72b7d13ee3c6 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -196,6 +196,12 @@ static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq,
 	WARN_ON_ONCE(verfp->committed < 0);
 }
 
+static int nfs_direct_cmp_verf(const struct nfs_writeverf *v1,
+		const struct nfs_writeverf *v2)
+{
+	return nfs_write_verifier_cmp(&v1->verifier, &v2->verifier);
+}
+
 /*
  * nfs_direct_cmp_hdr_verf - compare verifier for pgio header
  * @dreq - direct request possibly spanning multiple servers
@@ -215,7 +221,7 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
 		nfs_direct_set_hdr_verf(dreq, hdr);
 		return 0;
 	}
-	return memcmp(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
+	return nfs_direct_cmp_verf(verfp, &hdr->verf);
 }
 
 /*
@@ -238,7 +244,7 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
 	if (verfp->committed < 0)
 		return 1;
 
-	return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf));
+	return nfs_direct_cmp_verf(verfp, &data->verf);
 }
 
 /**
@@ -366,22 +372,10 @@ out:
  * Synchronous I/O uses a stack-allocated iocb.  Thus we can't trust
  * the iocb is still valid here if this is a synchronous request.
  */
-static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
+static void nfs_direct_complete(struct nfs_direct_req *dreq)
 {
 	struct inode *inode = dreq->inode;
 
-	if (dreq->iocb && write) {
-		loff_t pos = dreq->iocb->ki_pos + dreq->count;
-
-		spin_lock(&inode->i_lock);
-		if (i_size_read(inode) < pos)
-			i_size_write(inode, pos);
-		spin_unlock(&inode->i_lock);
-	}
-
-	if (write)
-		nfs_zap_mapping(inode, inode->i_mapping);
-
 	inode_dio_end(inode);
 
 	if (dreq->iocb) {
@@ -436,7 +430,7 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	}
 out_put:
 	if (put_dreq(dreq))
-		nfs_direct_complete(dreq, false);
+		nfs_direct_complete(dreq);
 	hdr->release(hdr);
 }
 
@@ -542,7 +536,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 	}
 
 	if (put_dreq(dreq))
-		nfs_direct_complete(dreq, false);
+		nfs_direct_complete(dreq);
 	return 0;
 }
 
@@ -583,17 +577,12 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
 	if (!count)
 		goto out;
 
-	inode_lock(inode);
-	result = nfs_sync_mapping(mapping);
-	if (result)
-		goto out_unlock;
-
 	task_io_account_read(count);
 
 	result = -ENOMEM;
 	dreq = nfs_direct_req_alloc();
 	if (dreq == NULL)
-		goto out_unlock;
+		goto out;
 
 	dreq->inode = inode;
 	dreq->bytes_left = dreq->max_count = count;
@@ -608,10 +597,12 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
+	nfs_start_io_direct(inode);
+
 	NFS_I(inode)->read_io += count;
 	result = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);
 
-	inode_unlock(inode);
+	nfs_end_io_direct(inode);
 
 	if (!result) {
 		result = nfs_direct_wait(dreq);
@@ -619,13 +610,8 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
 			iocb->ki_pos += result;
 	}
 
-	nfs_direct_req_release(dreq);
-	return result;
-
 out_release:
 	nfs_direct_req_release(dreq);
-out_unlock:
-	inode_unlock(inode);
 out:
 	return result;
 }
@@ -657,6 +643,8 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
 
 	dreq->count = 0;
+	dreq->verf.committed = NFS_INVALID_STABLE_HOW;
+	nfs_clear_pnfs_ds_commit_verifiers(&dreq->ds_cinfo);
 	for (i = 0; i < dreq->mirror_count; i++)
 		dreq->mirrors[i].count = 0;
 	get_dreq(dreq);
@@ -775,7 +763,8 @@ static void nfs_direct_write_schedule_work(struct work_struct *work)
 			nfs_direct_write_reschedule(dreq);
 			break;
 		default:
-			nfs_direct_complete(dreq, true);
+			nfs_zap_mapping(dreq->inode, dreq->inode->i_mapping);
+			nfs_direct_complete(dreq);
 	}
 }
 
@@ -991,6 +980,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 {
 	ssize_t result = -EINVAL;
+	size_t count;
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
@@ -1001,34 +991,24 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 	dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n",
 		file, iov_iter_count(iter), (long long) iocb->ki_pos);
 
-	nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES,
-		      iov_iter_count(iter));
+	result = generic_write_checks(iocb, iter);
+	if (result <= 0)
+		return result;
+	count = result;
+	nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);
 
 	pos = iocb->ki_pos;
 	end = (pos + iov_iter_count(iter) - 1) >> PAGE_SHIFT;
 
-	inode_lock(inode);
-
-	result = nfs_sync_mapping(mapping);
-	if (result)
-		goto out_unlock;
-
-	if (mapping->nrpages) {
-		result = invalidate_inode_pages2_range(mapping,
-					pos >> PAGE_SHIFT, end);
-		if (result)
-			goto out_unlock;
-	}
-
-	task_io_account_write(iov_iter_count(iter));
+	task_io_account_write(count);
 
 	result = -ENOMEM;
 	dreq = nfs_direct_req_alloc();
 	if (!dreq)
-		goto out_unlock;
+		goto out;
 
 	dreq->inode = inode;
-	dreq->bytes_left = dreq->max_count = iov_iter_count(iter);
+	dreq->bytes_left = dreq->max_count = count;
 	dreq->io_start = pos;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
@@ -1040,6 +1020,8 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
+	nfs_start_io_direct(inode);
+
 	result = nfs_direct_write_schedule_iovec(dreq, iter, pos);
 
 	if (mapping->nrpages) {
@@ -1047,30 +1029,19 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 					      pos >> PAGE_SHIFT, end);
 	}
 
-	inode_unlock(inode);
+	nfs_end_io_direct(inode);
 
 	if (!result) {
 		result = nfs_direct_wait(dreq);
 		if (result > 0) {
-			struct inode *inode = mapping->host;
-
 			iocb->ki_pos = pos + result;
-			spin_lock(&inode->i_lock);
-			if (i_size_read(inode) < iocb->ki_pos)
-				i_size_write(inode, iocb->ki_pos);
-			spin_unlock(&inode->i_lock);
-
 			/* XXX: should check the generic_write_sync retval */
 			generic_write_sync(iocb, result);
 		}
 	}
-	nfs_direct_req_release(dreq);
-	return result;
-
 out_release:
 	nfs_direct_req_release(dreq);
-out_unlock:
-	inode_unlock(inode);
+out:
 	return result;
 }
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 717a8d6af52d..7d620970f2e1 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -170,12 +170,14 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 		iocb->ki_filp,
 		iov_iter_count(to), (unsigned long) iocb->ki_pos);
 
-	result = nfs_revalidate_mapping_protected(inode, iocb->ki_filp->f_mapping);
+	nfs_start_io_read(inode);
+	result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
 	if (!result) {
 		result = generic_file_read_iter(iocb, to);
 		if (result > 0)
 			nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result);
 	}
+	nfs_end_io_read(inode);
 	return result;
 }
 EXPORT_SYMBOL_GPL(nfs_file_read);
@@ -191,12 +193,14 @@ nfs_file_splice_read(struct file *filp, loff_t *ppos,
 	dprintk("NFS: splice_read(%pD2, %lu@%Lu)\n",
 		filp, (unsigned long) count, (unsigned long long) *ppos);
 
-	res = nfs_revalidate_mapping_protected(inode, filp->f_mapping);
+	nfs_start_io_read(inode);
+	res = nfs_revalidate_mapping(inode, filp->f_mapping);
 	if (!res) {
 		res = generic_file_splice_read(filp, ppos, pipe, count, flags);
 		if (res > 0)
 			nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, res);
 	}
+	nfs_end_io_read(inode);
 	return res;
 }
 EXPORT_SYMBOL_GPL(nfs_file_splice_read);
@@ -272,16 +276,13 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 	trace_nfs_fsync_enter(inode);
 
-	inode_dio_wait(inode);
 	do {
 		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 		if (ret != 0)
 			break;
-		inode_lock(inode);
 		ret = nfs_file_fsync_commit(file, start, end, datasync);
 		if (!ret)
 			ret = pnfs_sync_inode(inode, !!datasync);
-		inode_unlock(inode);
 		/*
 		 * If nfs_file_fsync_commit detected a server reboot, then
 		 * resend all dirty pages that might have been covered by
@@ -359,19 +360,6 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
 		file, mapping->host->i_ino, len, (long long) pos);
 
 start:
-	/*
-	 * Prevent starvation issues if someone is doing a consistency
-	 * sync-to-disk
-	 */
-	ret = wait_on_bit_action(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING,
-				 nfs_wait_bit_killable, TASK_KILLABLE);
-	if (ret)
-		return ret;
-	/*
-	 * Wait for O_DIRECT to complete
-	 */
-	inode_dio_wait(mapping->host);
-
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
@@ -432,7 +420,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 		return status;
 	NFS_I(mapping->host)->write_io += copied;
 
-	if (nfs_ctx_key_to_expire(ctx)) {
+	if (nfs_ctx_key_to_expire(ctx, mapping->host)) {
 		status = nfs_wb_all(mapping->host);
 		if (status < 0)
 			return status;
@@ -470,31 +458,8 @@ static void nfs_invalidate_page(struct page *page, unsigned int offset,
  */
 static int nfs_release_page(struct page *page, gfp_t gfp)
 {
-	struct address_space *mapping = page->mapping;
-
 	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
-	/* Always try to initiate a 'commit' if relevant, but only
-	 * wait for it if the caller allows blocking.  Even then,
-	 * only wait 1 second and only if the 'bdi' is not congested.
-	 * Waiting indefinitely can cause deadlocks when the NFS
-	 * server is on this machine, when a new TCP connection is
-	 * needed and in other rare cases.  There is no particular
-	 * need to wait extensively here.  A short wait has the
-	 * benefit that someone else can worry about the freezer.
-	 */
-	if (mapping) {
-		struct nfs_server *nfss = NFS_SERVER(mapping->host);
-		nfs_commit_inode(mapping->host, 0);
-		if (gfpflags_allow_blocking(gfp) &&
-		    !bdi_write_congested(&nfss->backing_dev_info)) {
-			wait_on_page_bit_killable_timeout(page, PG_private,
-							  HZ);
-			if (PagePrivate(page))
-				set_bdi_congested(&nfss->backing_dev_info,
-						  BLK_RW_ASYNC);
-		}
-	}
 	/* If PagePrivate() is set, then the page is not freeable */
 	if (PagePrivate(page))
 		return 0;
@@ -604,6 +569,8 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		filp, filp->f_mapping->host->i_ino,
 		(long long)page_offset(page));
 
+	sb_start_pagefault(inode->i_sb);
+
 	/* make sure the cache has finished storing the page */
 	nfs_fscache_wait_on_page_write(NFS_I(inode), page);
 
@@ -630,6 +597,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 out_unlock:
 	unlock_page(page);
 out:
+	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
 
@@ -645,7 +613,7 @@ static int nfs_need_check_write(struct file *filp, struct inode *inode)
 
 	ctx = nfs_file_open_context(filp);
 	if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags) ||
-	    nfs_ctx_key_to_expire(ctx))
+	    nfs_ctx_key_to_expire(ctx, inode))
 		return 1;
 	return 0;
 }
@@ -656,23 +624,17 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(file);
 	unsigned long written = 0;
 	ssize_t result;
-	size_t count = iov_iter_count(from);
 
 	result = nfs_key_timeout_notify(file, inode);
 	if (result)
 		return result;
 
-	if (iocb->ki_flags & IOCB_DIRECT) {
-		result = generic_write_checks(iocb, from);
-		if (result <= 0)
-			return result;
+	if (iocb->ki_flags & IOCB_DIRECT)
 		return nfs_file_direct_write(iocb, from);
-	}
 
 	dprintk("NFS: write(%pD2, %zu@%Ld)\n",
-		file, count, (long long) iocb->ki_pos);
+		file, iov_iter_count(from), (long long) iocb->ki_pos);
 
-	result = -EBUSY;
 	if (IS_SWAPFILE(inode))
 		goto out_swapfile;
 	/*
@@ -684,28 +646,33 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 			goto out;
 	}
 
-	result = count;
-	if (!count)
+	nfs_start_io_write(inode);
+	result = generic_write_checks(iocb, from);
+	if (result > 0) {
+		current->backing_dev_info = inode_to_bdi(inode);
+		result = generic_perform_write(file, from, iocb->ki_pos);
+		current->backing_dev_info = NULL;
+	}
+	nfs_end_io_write(inode);
+	if (result <= 0)
 		goto out;
 
-	result = generic_file_write_iter(iocb, from);
-	if (result > 0)
-		written = result;
+	written = generic_write_sync(iocb, result);
+	iocb->ki_pos += written;
 
 	/* Return error values */
-	if (result >= 0 && nfs_need_check_write(file, inode)) {
+	if (nfs_need_check_write(file, inode)) {
 		int err = vfs_fsync(file, 0);
 		if (err < 0)
 			result = err;
 	}
-	if (result > 0)
-		nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
+	nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
 out:
 	return result;
 
 out_swapfile:
 	printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
-	goto out;
+	return -EBUSY;
 }
 EXPORT_SYMBOL_GPL(nfs_file_write);
 
@@ -780,11 +747,6 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 }
 
 static int
-is_time_granular(struct timespec *ts) {
-	return ((ts->tv_sec == 0) && (ts->tv_nsec <= 1000));
-}
-
-static int
 do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
 	struct inode *inode = filp->f_mapping->host;
@@ -817,12 +779,8 @@ do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	 * This makes locking act as a cache coherency point.
 	 */
 	nfs_sync_mapping(filp->f_mapping);
-	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) {
-		if (is_time_granular(&NFS_SERVER(inode)->time_delta))
-			__nfs_revalidate_inode(NFS_SERVER(inode), inode);
-		else
-			nfs_zap_caches(inode);
-	}
+	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
+		nfs_zap_mapping(inode, filp->f_mapping);
 out:
 	return status;
 }
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index aa59757389dc..a3fc48ba4931 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -255,13 +255,16 @@ static int filelayout_read_done_cb(struct rpc_task *task,
 static void
 filelayout_set_layoutcommit(struct nfs_pgio_header *hdr)
 {
+	loff_t end_offs = 0;
 
 	if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds ||
-	    hdr->res.verf->committed != NFS_DATA_SYNC)
+	    hdr->res.verf->committed == NFS_FILE_SYNC)
 		return;
+	if (hdr->res.verf->committed == NFS_DATA_SYNC)
+		end_offs = hdr->mds_offset + (loff_t)hdr->res.count;
 
-	pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
-			hdr->mds_offset + hdr->res.count);
+	/* Note: if the write is unstable, don't set end_offs until commit */
+	pnfs_set_layoutcommit(hdr->inode, hdr->lseg, end_offs);
 	dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
 		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
 }
@@ -354,6 +357,12 @@ static int filelayout_write_done_cb(struct rpc_task *task,
 	}
 
 	filelayout_set_layoutcommit(hdr);
+
+	/* zero out the fattr */
+	hdr->fattr.valid = 0;
+	if (task->tk_status >= 0)
+		nfs_writeback_update_inode(hdr);
+
 	return 0;
 }
 
@@ -375,8 +384,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 		return -EAGAIN;
 	}
 
-	if (data->verf.committed == NFS_UNSTABLE)
-		pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
+	pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
 
 	return 0;
 }
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 0e8018bc9880..e6206eaf2bdf 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1325,15 +1325,16 @@ ff_layout_need_layoutcommit(struct pnfs_layout_segment *lseg)
  * we always send layoutcommit after DS writes.
  */
 static void
-ff_layout_set_layoutcommit(struct nfs_pgio_header *hdr)
+ff_layout_set_layoutcommit(struct inode *inode,
+		struct pnfs_layout_segment *lseg,
+		loff_t end_offset)
 {
-	if (!ff_layout_need_layoutcommit(hdr->lseg))
+	if (!ff_layout_need_layoutcommit(lseg))
 		return;
 
-	pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
-			hdr->mds_offset + hdr->res.count);
-	dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
-		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
+	pnfs_set_layoutcommit(inode, lseg, end_offset);
+	dprintk("%s inode %lu pls_end_pos %llu\n", __func__, inode->i_ino,
+		(unsigned long long) NFS_I(inode)->layout->plh_lwb);
 }
 
 static bool
@@ -1469,6 +1470,7 @@ static void ff_layout_read_release(void *data)
 static int ff_layout_write_done_cb(struct rpc_task *task,
 				struct nfs_pgio_header *hdr)
 {
+	loff_t end_offs = 0;
 	int err;
 
 	trace_nfs4_pnfs_write(hdr, task->tk_status);
@@ -1494,7 +1496,10 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
 
 	if (hdr->res.verf->committed == NFS_FILE_SYNC ||
 	    hdr->res.verf->committed == NFS_DATA_SYNC)
-		ff_layout_set_layoutcommit(hdr);
+		end_offs = hdr->mds_offset + (loff_t)hdr->res.count;
+
+	/* Note: if the write is unstable, don't set end_offs until commit */
+	ff_layout_set_layoutcommit(hdr->inode, hdr->lseg, end_offs);
 
 	/* zero out fattr since we don't care DS attr at all */
 	hdr->fattr.valid = 0;
@@ -1530,9 +1535,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 		return -EAGAIN;
 	}
 
-	if (data->verf.committed == NFS_UNSTABLE
-	    && ff_layout_need_layoutcommit(data->lseg))
-		pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
+	ff_layout_set_layoutcommit(data->inode, data->lseg, data->lwb);
 
 	return 0;
 }
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index dda689d7a8a7..bf4ec5ecc97e 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -662,9 +662,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	trace_nfs_getattr_enter(inode);
 	/* Flush out writes to the server in order to update c/mtime.  */
 	if (S_ISREG(inode->i_mode)) {
-		inode_lock(inode);
-		err = nfs_sync_inode(inode);
-		inode_unlock(inode);
+		err = filemap_write_and_wait(inode->i_mapping);
 		if (err)
 			goto out;
 	}
@@ -879,7 +877,10 @@ void nfs_inode_attach_open_context(struct nfs_open_context *ctx)
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	spin_lock(&inode->i_lock);
-	list_add(&ctx->list, &nfsi->open_files);
+	if (ctx->mode & FMODE_WRITE)
+		list_add(&ctx->list, &nfsi->open_files);
+	else
+		list_add_tail(&ctx->list, &nfsi->open_files);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context);
@@ -972,6 +973,13 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 	if (NFS_STALE(inode))
 		goto out;
 
+	/* pNFS: Attributes aren't updated until we layoutcommit */
+	if (S_ISREG(inode->i_mode)) {
+		status = pnfs_sync_inode(inode, false);
+		if (status)
+			goto out;
+	}
+
 	status = -ENOMEM;
 	fattr = nfs_alloc_fattr();
 	if (fattr == NULL)
@@ -1122,14 +1130,12 @@ out:
 }
 
 /**
- * __nfs_revalidate_mapping - Revalidate the pagecache
+ * nfs_revalidate_mapping - Revalidate the pagecache
  * @inode - pointer to host inode
  * @mapping - pointer to mapping
- * @may_lock - take inode->i_mutex?
  */
-static int __nfs_revalidate_mapping(struct inode *inode,
-		struct address_space *mapping,
-		bool may_lock)
+int nfs_revalidate_mapping(struct inode *inode,
+		struct address_space *mapping)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	unsigned long *bitlock = &nfsi->flags;
@@ -1178,12 +1184,7 @@ static int __nfs_revalidate_mapping(struct inode *inode,
 	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
 	spin_unlock(&inode->i_lock);
 	trace_nfs_invalidate_mapping_enter(inode);
-	if (may_lock) {
-		inode_lock(inode);
-		ret = nfs_invalidate_mapping(inode, mapping);
-		inode_unlock(inode);
-	} else
-		ret = nfs_invalidate_mapping(inode, mapping);
+	ret = nfs_invalidate_mapping(inode, mapping);
 	trace_nfs_invalidate_mapping_exit(inode, ret);
 
 	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
@@ -1193,27 +1194,28 @@ out:
 	return ret;
 }
 
-/**
- * nfs_revalidate_mapping - Revalidate the pagecache
- * @inode - pointer to host inode
- * @mapping - pointer to mapping
- */
-int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
+static bool nfs_file_has_writers(struct nfs_inode *nfsi)
 {
-	return __nfs_revalidate_mapping(inode, mapping, false);
+	struct inode *inode = &nfsi->vfs_inode;
+
+	assert_spin_locked(&inode->i_lock);
+
+	if (!S_ISREG(inode->i_mode))
+		return false;
+	if (list_empty(&nfsi->open_files))
+		return false;
+	/* Note: This relies on nfsi->open_files being ordered with writers
+	 *       being placed at the head of the list.
+	 *       See nfs_inode_attach_open_context()
+	 */
+	return (list_first_entry(&nfsi->open_files,
+			struct nfs_open_context,
+			list)->mode & FMODE_WRITE) == FMODE_WRITE;
 }
 
-/**
- * nfs_revalidate_mapping_protected - Revalidate the pagecache
- * @inode - pointer to host inode
- * @mapping - pointer to mapping
- *
- * Differs from nfs_revalidate_mapping() in that it grabs the inode->i_mutex
- * while invalidating the mapping.
- */
-int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping)
+static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi)
 {
-	return __nfs_revalidate_mapping(inode, mapping, true);
+	return nfs_file_has_writers(nfsi) && nfs_file_io_is_buffered(nfsi);
 }
 
 static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
@@ -1280,22 +1282,24 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
 		return -EIO;
 
-	if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
-			inode->i_version != fattr->change_attr)
-		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+	if (!nfs_file_has_buffered_writers(nfsi)) {
+		/* Verify a few of the more important attributes */
+		if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && inode->i_version != fattr->change_attr)
+			invalid |= NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE;
 
-	/* Verify a few of the more important attributes */
-	if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime))
-		invalid |= NFS_INO_INVALID_ATTR;
+		if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime))
+			invalid |= NFS_INO_INVALID_ATTR;
 
-	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
-		cur_size = i_size_read(inode);
-		new_isize = nfs_size_to_loff_t(fattr->size);
-		if (cur_size != new_isize)
-			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+		if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec_equal(&inode->i_ctime, &fattr->ctime))
+			invalid |= NFS_INO_INVALID_ATTR;
+
+		if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
+			cur_size = i_size_read(inode);
+			new_isize = nfs_size_to_loff_t(fattr->size);
+			if (cur_size != new_isize)
+				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+		}
 	}
-	if (nfsi->nrequests != 0)
-		invalid &= ~NFS_INO_REVAL_PAGECACHE;
 
 	/* Have any file permissions changed? */
 	if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
@@ -1470,28 +1474,12 @@ static int nfs_inode_attrs_need_update(const struct inode *inode, const struct n
 		((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
 }
 
-/*
- * Don't trust the change_attribute, mtime, ctime or size if
- * a pnfs LAYOUTCOMMIT is outstanding
- */
-static void nfs_inode_attrs_handle_layoutcommit(struct inode *inode,
-		struct nfs_fattr *fattr)
-{
-	if (pnfs_layoutcommit_outstanding(inode))
-		fattr->valid &= ~(NFS_ATTR_FATTR_CHANGE |
-				NFS_ATTR_FATTR_MTIME |
-				NFS_ATTR_FATTR_CTIME |
-				NFS_ATTR_FATTR_SIZE);
-}
-
 static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
 	int ret;
 
 	trace_nfs_refresh_inode_enter(inode);
 
-	nfs_inode_attrs_handle_layoutcommit(inode, fattr);
-
 	if (nfs_inode_attrs_need_update(inode, fattr))
 		ret = nfs_update_inode(inode, fattr);
 	else
@@ -1527,7 +1515,7 @@ EXPORT_SYMBOL_GPL(nfs_refresh_inode);
 
 static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
-	unsigned long invalid = NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+	unsigned long invalid = NFS_INO_INVALID_ATTR;
 
 	/*
 	 * Don't revalidate the pagecache if we hold a delegation, but do
@@ -1676,6 +1664,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	unsigned long invalid = 0;
 	unsigned long now = jiffies;
 	unsigned long save_cache_validity;
+	bool have_writers = nfs_file_has_buffered_writers(nfsi);
 	bool cache_revalidated = true;
 
 	dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n",
@@ -1725,17 +1714,25 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	/* Do atomic weak cache consistency updates */
 	invalid |= nfs_wcc_update_inode(inode, fattr);
 
+	if (pnfs_layoutcommit_outstanding(inode)) {
+		nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_ATTR;
+		cache_revalidated = false;
+	}
+
 	/* More cache consistency checks */
 	if (fattr->valid & NFS_ATTR_FATTR_CHANGE) {
 		if (inode->i_version != fattr->change_attr) {
 			dprintk("NFS: change_attr change on server for file %s/%ld\n",
 					inode->i_sb->s_id, inode->i_ino);
-			invalid |= NFS_INO_INVALID_ATTR
-				| NFS_INO_INVALID_DATA
-				| NFS_INO_INVALID_ACCESS
-				| NFS_INO_INVALID_ACL;
-			if (S_ISDIR(inode->i_mode))
-				nfs_force_lookup_revalidate(inode);
+			/* Could it be a race with writeback? */
+			if (!have_writers) {
+				invalid |= NFS_INO_INVALID_ATTR
+					| NFS_INO_INVALID_DATA
+					| NFS_INO_INVALID_ACCESS
+					| NFS_INO_INVALID_ACL;
+				if (S_ISDIR(inode->i_mode))
+					nfs_force_lookup_revalidate(inode);
+			}
 			inode->i_version = fattr->change_attr;
 		}
 	} else {
@@ -1768,9 +1765,10 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		if (new_isize != cur_isize) {
 			/* Do we perhaps have any outstanding writes, or has
 			 * the file grown beyond our last write? */
-			if ((nfsi->nrequests == 0) || new_isize > cur_isize) {
+			if (nfsi->nrequests == 0 || new_isize > cur_isize) {
 				i_size_write(inode, new_isize);
-				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
+				if (!have_writers)
+					invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
 			}
 			dprintk("NFS: isize change on server for file %s/%ld "
 					"(%Ld to %Ld)\n",
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 5ea04d87fc65..7ce5e023c3c3 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -66,13 +66,16 @@ struct nfs_clone_mount {
 
 struct nfs_client_initdata {
 	unsigned long init_flags;
-	const char *hostname;
-	const struct sockaddr *addr;
+	const char *hostname;			/* Hostname of the server */
+	const struct sockaddr *addr;		/* Address of the server */
+	const char *nodename;			/* Hostname of the client */
+	const char *ip_addr;			/* IP address of the client */
 	size_t addrlen;
 	struct nfs_subversion *nfs_mod;
 	int proto;
 	u32 minorversion;
 	struct net *net;
+	const struct rpc_timeout *timeparms;
 };
 
 /*
@@ -147,9 +150,8 @@ extern void nfs_umount(const struct nfs_mount_request *info);
 extern const struct rpc_program nfs_program;
 extern void nfs_clients_init(struct net *net);
 extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *);
-int nfs_create_rpc_client(struct nfs_client *, const struct rpc_timeout *, rpc_authflavor_t);
+int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t);
 struct nfs_client *nfs_get_client(const struct nfs_client_initdata *,
-				  const struct rpc_timeout *, const char *,
 				  rpc_authflavor_t);
 int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *);
 void nfs_server_insert_lists(struct nfs_server *);
@@ -184,7 +186,7 @@ extern struct nfs_server *nfs_clone_server(struct nfs_server *,
 					   rpc_authflavor_t);
 extern int nfs_wait_client_init_complete(const struct nfs_client *clp);
 extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
-extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
+extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 					     const struct sockaddr *ds_addr,
 					     int ds_addrlen, int ds_proto,
 					     unsigned int ds_timeo,
@@ -193,7 +195,7 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 					     rpc_authflavor_t au_flavor);
 extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *,
 						struct inode *);
-extern struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
+extern struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 			const struct sockaddr *ds_addr, int ds_addrlen,
 			int ds_proto, unsigned int ds_timeo,
 			unsigned int ds_retrans, rpc_authflavor_t au_flavor);
@@ -338,8 +340,7 @@ nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src)
 /* proc.c */
 void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
 extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
-			   const struct rpc_timeout *timeparms,
-			   const char *ip_addr);
+			   const struct nfs_client_initdata *);
 
 /* dir.c */
 extern void nfs_force_use_readdirplus(struct inode *dir);
@@ -411,6 +412,19 @@ extern void __exit unregister_nfs_fs(void);
 extern bool nfs_sb_active(struct super_block *sb);
 extern void nfs_sb_deactive(struct super_block *sb);
 
+/* io.c */
+extern void nfs_start_io_read(struct inode *inode);
+extern void nfs_end_io_read(struct inode *inode);
+extern void nfs_start_io_write(struct inode *inode);
+extern void nfs_end_io_write(struct inode *inode);
+extern void nfs_start_io_direct(struct inode *inode);
+extern void nfs_end_io_direct(struct inode *inode);
+
+static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi)
+{
+	return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0;
+}
+
 /* namespace.c */
 #define NFS_PATH_CANONICAL 1
 extern char *nfs_path(char **p, struct dentry *dentry,
@@ -496,9 +510,29 @@ void nfs_init_cinfo(struct nfs_commit_info *cinfo,
 		    struct inode *inode,
 		    struct nfs_direct_req *dreq);
 int nfs_key_timeout_notify(struct file *filp, struct inode *inode);
-bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx);
+bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode);
 void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio);
 
+int nfs_filemap_write_and_wait_range(struct address_space *mapping,
+		loff_t lstart, loff_t lend);
+
+#ifdef CONFIG_NFS_V4_1
+static inline
+void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo)
+{
+	int i;
+
+	for (i = 0; i < cinfo->nbuckets; i++)
+		cinfo->buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW;
+}
+#else
+static inline
+void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo)
+{
+}
+#endif
+
+
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,
 		struct page *, struct page *, enum migrate_mode);
@@ -506,6 +540,13 @@ extern int nfs_migrate_page(struct address_space *,
 #define nfs_migrate_page NULL
 #endif
 
+static inline int
+nfs_write_verifier_cmp(const struct nfs_write_verifier *v1,
+		const struct nfs_write_verifier *v2)
+{
+	return memcmp(v1->data, v2->data, sizeof(v1->data));
+}
+
 /* unlink.c */
 extern struct rpc_task *
 nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
@@ -521,8 +562,7 @@ extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
 /* nfs4proc.c */
 extern void __nfs4_read_done_cb(struct nfs_pgio_header *);
 extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
-			    const struct rpc_timeout *timeparms,
-			    const char *ip_addr);
+			    const struct nfs_client_initdata *);
 extern int nfs40_walk_client_list(struct nfs_client *clp,
 				struct nfs_client **result,
 				struct rpc_cred *cred);
diff --git a/fs/nfs/io.c b/fs/nfs/io.c
new file mode 100644
index 000000000000..1fc5d1ce327e
--- /dev/null
+++ b/fs/nfs/io.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright (c) 2016 Trond Myklebust
+ *
+ * I/O and data path helper functionality.
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/rwsem.h>
+#include <linux/fs.h>
+#include <linux/nfs_fs.h>
+
+#include "internal.h"
+
+/* Call with exclusively locked inode->i_rwsem */
+static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode)
+{
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+		clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
+		inode_dio_wait(inode);
+	}
+}
+
+/**
+ * nfs_start_io_read - declare the file is being used for buffered reads
+ * @inode - file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ * On exit, the function ensures that the NFS_INO_ODIRECT flag is unset,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that buffered read operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas direct I/O
+ * operations need to wait to grab an exclusive lock in order to set
+ * NFS_INO_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
+ */
+void
+nfs_start_io_read(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	/* Be an optimist! */
+	down_read(&inode->i_rwsem);
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0)
+		return;
+	up_read(&inode->i_rwsem);
+	/* Slow path.... */
+	down_write(&inode->i_rwsem);
+	nfs_block_o_direct(nfsi, inode);
+	downgrade_write(&inode->i_rwsem);
+}
+
+/**
+ * nfs_end_io_read - declare that the buffered read operation is done
+ * @inode - file inode
+ *
+ * Declare that a buffered read operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void
+nfs_end_io_read(struct inode *inode)
+{
+	up_read(&inode->i_rwsem);
+}
+
+/**
+ * nfs_start_io_write - declare the file is being used for buffered writes
+ * @inode - file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ */
+void
+nfs_start_io_write(struct inode *inode)
+{
+	down_write(&inode->i_rwsem);
+	nfs_block_o_direct(NFS_I(inode), inode);
+}
+
+/**
+ * nfs_end_io_write - declare that the buffered write operation is done
+ * @inode - file inode
+ *
+ * Declare that a buffered write operation is done, and release the
+ * lock on inode->i_rwsem.
+ */
+void
+nfs_end_io_write(struct inode *inode)
+{
+	up_write(&inode->i_rwsem);
+}
+
+/* Call with exclusively locked inode->i_rwsem */
+static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode)
+{
+	if (!test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+		set_bit(NFS_INO_ODIRECT, &nfsi->flags);
+		nfs_wb_all(inode);
+	}
+}
+
+/**
+ * nfs_end_io_direct - declare the file is being used for direct i/o
+ * @inode - file inode
+ *
+ * Declare that a direct I/O operation is about to start, and ensure
+ * that we block all buffered I/O.
+ * On exit, the function ensures that the NFS_INO_ODIRECT flag is set,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that direct I/O operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas buffered I/O
+ * operations need to wait to grab an exclusive lock in order to clear
+ * NFS_INO_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
+ */
+void
+nfs_start_io_direct(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	/* Be an optimist! */
+	down_read(&inode->i_rwsem);
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) != 0)
+		return;
+	up_read(&inode->i_rwsem);
+	/* Slow path.... */
+	down_write(&inode->i_rwsem);
+	nfs_block_buffered(nfsi, inode);
+	downgrade_write(&inode->i_rwsem);
+}
+
+/**
+ * nfs_end_io_direct - declare that the direct i/o operation is done
+ * @inode - file inode
+ *
+ * Declare that a direct I/O operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void
+nfs_end_io_direct(struct inode *inode)
+{
+	up_read(&inode->i_rwsem);
+}
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index 9e9fa347a948..ee753547fb0a 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -76,19 +76,23 @@ struct nfs_server *nfs3_clone_server(struct nfs_server *source,
  * low timeout interval so that if a connection is lost, we retry through
  * the MDS.
  */
-struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
+struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 		const struct sockaddr *ds_addr, int ds_addrlen,
 		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
 		rpc_authflavor_t au_flavor)
 {
+	struct rpc_timeout ds_timeout;
+	struct nfs_client *mds_clp = mds_srv->nfs_client;
 	struct nfs_client_initdata cl_init = {
 		.addr = ds_addr,
 		.addrlen = ds_addrlen,
+		.nodename = mds_clp->cl_rpcclient->cl_nodename,
+		.ip_addr = mds_clp->cl_ipaddr,
 		.nfs_mod = &nfs_v3,
 		.proto = ds_proto,
 		.net = mds_clp->cl_net,
+		.timeparms = &ds_timeout,
 	};
-	struct rpc_timeout ds_timeout;
 	struct nfs_client *clp;
 	char buf[INET6_ADDRSTRLEN + 1];
 
@@ -97,10 +101,12 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
 		return ERR_PTR(-EINVAL);
 	cl_init.hostname = buf;
 
+	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
+		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+
 	/* Use the MDS nfs_client cl_ipaddr. */
 	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
-	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
-			     au_flavor);
+	clp = nfs_get_client(&cl_init, au_flavor);
 
 	return clp;
 }
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index aa03ed09ba06..33da841a21bb 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -113,15 +113,17 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE))
 		return -EOPNOTSUPP;
 
-	nfs_wb_all(inode);
 	inode_lock(inode);
+	err = nfs_sync_inode(inode);
+	if (err)
+		goto out_unlock;
 
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
 	if (err == 0)
 		truncate_pagecache_range(inode, offset, (offset + len) -1);
 	if (err == -EOPNOTSUPP)
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
-
+out_unlock:
 	inode_unlock(inode);
 	return err;
 }
@@ -154,11 +156,20 @@ static ssize_t _nfs42_proc_copy(struct file *src, loff_t pos_src,
 	if (status)
 		return status;
 
+	status = nfs_filemap_write_and_wait_range(file_inode(src)->i_mapping,
+			pos_src, pos_src + (loff_t)count - 1);
+	if (status)
+		return status;
+
 	status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
 				     dst_lock, FMODE_WRITE);
 	if (status)
 		return status;
 
+	status = nfs_sync_inode(dst_inode);
+	if (status)
+		return status;
+
 	status = nfs4_call_sync(server->client, server, &msg,
 				&args.seq_args, &res.seq_res, 0);
 	if (status == -ENOTSUPP)
@@ -258,7 +269,11 @@ static loff_t _nfs42_proc_llseek(struct file *filep,
 	if (status)
 		return status;
 
-	nfs_wb_all(inode);
+	status = nfs_filemap_write_and_wait_range(inode->i_mapping,
+			offset, LLONG_MAX);
+	if (status)
+		return status;
+
 	status = nfs4_call_sync(server->client, server, &msg,
 				&args.seq_args, &res.seq_res, 0);
 	if (status == -ENOTSUPP)
@@ -336,8 +351,7 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
 			 * Mark the bad layout state as invalid, then retry
 			 * with the current stateid.
 			 */
-			set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-			pnfs_mark_matching_lsegs_invalid(lo, &head, NULL, 0);
+			pnfs_mark_layout_stateid_invalid(lo, &head);
 			spin_unlock(&inode->i_lock);
 			pnfs_free_lseg_list(&head);
 		} else
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 6dc6f2aea0d6..8b2605882a20 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -330,13 +330,21 @@ static int decode_write_response(struct xdr_stream *xdr,
 				 struct nfs42_write_res *res)
 {
 	__be32 *p;
-	int stateids;
 
 	p = xdr_inline_decode(xdr, 4 + 8 + 4);
 	if (unlikely(!p))
 		goto out_overflow;
 
-	stateids = be32_to_cpup(p++);
+	/*
+	 * We never use asynchronous mode, so warn if a server returns
+	 * a stateid.
+	 */
+	if (unlikely(*p != 0)) {
+		pr_err_once("%s: server has set unrequested "
+				"asynchronous mode\n", __func__);
+		return -EREMOTEIO;
+	}
+	p++;
 	p = xdr_decode_hyper(p, &res->count);
 	res->verifier.committed = be32_to_cpup(p);
 	return decode_verifier(xdr, &res->verifier.verifier);
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 768456fa1b17..4be567a54958 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -185,6 +185,7 @@ struct nfs4_state {
 struct nfs4_exception {
 	struct nfs4_state *state;
 	struct inode *inode;
+	nfs4_stateid *stateid;
 	long timeout;
 	unsigned char delay : 1,
 		      recovering : 1,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 10410e8b5853..8d7d08d4f95f 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -349,10 +349,10 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp)
  * Returns pointer to an NFS client, or an ERR_PTR value.
  */
 struct nfs_client *nfs4_init_client(struct nfs_client *clp,
-				    const struct rpc_timeout *timeparms,
-				    const char *ip_addr)
+				    const struct nfs_client_initdata *cl_init)
 {
 	char buf[INET6_ADDRSTRLEN + 1];
+	const char *ip_addr = cl_init->ip_addr;
 	struct nfs_client *old;
 	int error;
 
@@ -370,9 +370,9 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
 	__set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
 
-	error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I);
+	error = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_GSS_KRB5I);
 	if (error == -EINVAL)
-		error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
+		error = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_UNIX);
 	if (error < 0)
 		goto error;
 
@@ -793,10 +793,12 @@ static int nfs4_set_client(struct nfs_server *server,
 		.hostname = hostname,
 		.addr = addr,
 		.addrlen = addrlen,
+		.ip_addr = ip_addr,
 		.nfs_mod = &nfs_v4,
 		.proto = proto,
 		.minorversion = minorversion,
 		.net = net,
+		.timeparms = timeparms,
 	};
 	struct nfs_client *clp;
 	int error;
@@ -809,7 +811,7 @@ static int nfs4_set_client(struct nfs_server *server,
 		set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
 
 	/* Allocate or find a client reference we can use */
-	clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour);
+	clp = nfs_get_client(&cl_init, authflavour);
 	if (IS_ERR(clp)) {
 		error = PTR_ERR(clp);
 		goto error;
@@ -842,20 +844,24 @@ error:
  * low timeout interval so that if a connection is lost, we retry through
  * the MDS.
  */
-struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
+struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 		const struct sockaddr *ds_addr, int ds_addrlen,
 		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
 		u32 minor_version, rpc_authflavor_t au_flavor)
 {
+	struct rpc_timeout ds_timeout;
+	struct nfs_client *mds_clp = mds_srv->nfs_client;
 	struct nfs_client_initdata cl_init = {
 		.addr = ds_addr,
 		.addrlen = ds_addrlen,
+		.nodename = mds_clp->cl_rpcclient->cl_nodename,
+		.ip_addr = mds_clp->cl_ipaddr,
 		.nfs_mod = &nfs_v4,
 		.proto = ds_proto,
 		.minorversion = minor_version,
 		.net = mds_clp->cl_net,
+		.timeparms = &ds_timeout,
 	};
-	struct rpc_timeout ds_timeout;
 	struct nfs_client *clp;
 	char buf[INET6_ADDRSTRLEN + 1];
 
@@ -863,14 +869,16 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 		return ERR_PTR(-EINVAL);
 	cl_init.hostname = buf;
 
+	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
+		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+
 	/*
 	 * Set an authflavor equual to the MDS value. Use the MDS nfs_client
 	 * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
 	 * (section 13.1 RFC 5661).
 	 */
 	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
-	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
-			     au_flavor);
+	clp = nfs_get_client(&cl_init, au_flavor);
 
 	dprintk("<-- %s %p\n", __func__, clp);
 	return clp;
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 014b0e41ace5..d085ad794884 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -66,7 +66,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	if (openflags & O_TRUNC) {
 		attr.ia_valid |= ATTR_SIZE;
 		attr.ia_size = 0;
-		nfs_sync_inode(inode);
+		filemap_write_and_wait(inode->i_mapping);
 	}
 
 	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr, NULL);
@@ -133,21 +133,9 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
 				    size_t count, unsigned int flags)
 {
-	struct inode *in_inode = file_inode(file_in);
-	struct inode *out_inode = file_inode(file_out);
-	int ret;
-
-	if (in_inode == out_inode)
+	if (file_inode(file_in) == file_inode(file_out))
 		return -EINVAL;
 
-	/* flush any pending writes */
-	ret = nfs_sync_inode(in_inode);
-	if (ret)
-		return ret;
-	ret = nfs_sync_inode(out_inode);
-	if (ret)
-		return ret;
-
 	return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ff416d0e24bc..da5c9e58e907 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -363,6 +363,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_state *state = exception->state;
+	const nfs4_stateid *stateid = exception->stateid;
 	struct inode *inode = exception->inode;
 	int ret = errorcode;
 
@@ -376,9 +377,18 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 		case -NFS4ERR_DELEG_REVOKED:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_BAD_STATEID:
-			if (inode && nfs_async_inode_return_delegation(inode,
-						NULL) == 0)
-				goto wait_on_recovery;
+			if (inode) {
+				int err;
+
+				err = nfs_async_inode_return_delegation(inode,
+						stateid);
+				if (err == 0)
+					goto wait_on_recovery;
+				if (stateid != NULL && stateid->type == NFS4_DELEGATION_STATEID_TYPE) {
+					exception->retry = 1;
+					break;
+				}
+			}
 			if (state == NULL)
 				break;
 			ret = nfs4_schedule_stateid_recovery(server, state);
@@ -427,6 +437,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
 		case -NFS4ERR_GRACE:
+		case -NFS4ERR_LAYOUTTRYLATER:
 		case -NFS4ERR_RECALLCONFLICT:
 			exception->delay = 1;
 			return 0;
@@ -2669,28 +2680,17 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir,
 	return res;
 }
 
-static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
-			    struct nfs_fattr *fattr, struct iattr *sattr,
-			    struct nfs4_state *state, struct nfs4_label *ilabel,
-			    struct nfs4_label *olabel)
+static int _nfs4_do_setattr(struct inode *inode,
+			    struct nfs_setattrargs *arg,
+			    struct nfs_setattrres *res,
+			    struct rpc_cred *cred,
+			    struct nfs4_state *state)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
-        struct nfs_setattrargs  arg = {
-                .fh             = NFS_FH(inode),
-                .iap            = sattr,
-		.server		= server,
-		.bitmask = server->attr_bitmask,
-		.label		= ilabel,
-        };
-        struct nfs_setattrres  res = {
-		.fattr		= fattr,
-		.label		= olabel,
-		.server		= server,
-        };
         struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_SETATTR],
-		.rpc_argp	= &arg,
-		.rpc_resp	= &res,
+		.rpc_argp	= arg,
+		.rpc_resp	= res,
 		.rpc_cred	= cred,
         };
 	struct rpc_cred *delegation_cred = NULL;
@@ -2699,17 +2699,13 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 	bool truncate;
 	int status;
 
-	arg.bitmask = nfs4_bitmask(server, ilabel);
-	if (ilabel)
-		arg.bitmask = nfs4_bitmask(server, olabel);
-
-	nfs_fattr_init(fattr);
+	nfs_fattr_init(res->fattr);
 
 	/* Servers should only apply open mode checks for file size changes */
-	truncate = (sattr->ia_valid & ATTR_SIZE) ? true : false;
+	truncate = (arg->iap->ia_valid & ATTR_SIZE) ? true : false;
 	fmode = truncate ? FMODE_WRITE : FMODE_READ;
 
-	if (nfs4_copy_delegation_stateid(inode, fmode, &arg.stateid, &delegation_cred)) {
+	if (nfs4_copy_delegation_stateid(inode, fmode, &arg->stateid, &delegation_cred)) {
 		/* Use that stateid */
 	} else if (truncate && state != NULL) {
 		struct nfs_lockowner lockowner = {
@@ -2719,19 +2715,19 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 		if (!nfs4_valid_open_stateid(state))
 			return -EBADF;
 		if (nfs4_select_rw_stateid(state, FMODE_WRITE, &lockowner,
-				&arg.stateid, &delegation_cred) == -EIO)
+				&arg->stateid, &delegation_cred) == -EIO)
 			return -EBADF;
 	} else
-		nfs4_stateid_copy(&arg.stateid, &zero_stateid);
+		nfs4_stateid_copy(&arg->stateid, &zero_stateid);
 	if (delegation_cred)
 		msg.rpc_cred = delegation_cred;
 
-	status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
+	status = nfs4_call_sync(server->client, server, &msg, &arg->seq_args, &res->seq_res, 1);
 
 	put_rpccred(delegation_cred);
 	if (status == 0 && state != NULL)
 		renew_lease(server, timestamp);
-	trace_nfs4_setattr(inode, &arg.stateid, status);
+	trace_nfs4_setattr(inode, &arg->stateid, status);
 	return status;
 }
 
@@ -2741,13 +2737,31 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 			   struct nfs4_label *olabel)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
+        struct nfs_setattrargs  arg = {
+                .fh             = NFS_FH(inode),
+                .iap            = sattr,
+		.server		= server,
+		.bitmask = server->attr_bitmask,
+		.label		= ilabel,
+        };
+        struct nfs_setattrres  res = {
+		.fattr		= fattr,
+		.label		= olabel,
+		.server		= server,
+        };
 	struct nfs4_exception exception = {
 		.state = state,
 		.inode = inode,
+		.stateid = &arg.stateid,
 	};
 	int err;
+
+	arg.bitmask = nfs4_bitmask(server, ilabel);
+	if (ilabel)
+		arg.bitmask = nfs4_bitmask(server, olabel);
+
 	do {
-		err = _nfs4_do_setattr(inode, cred, fattr, sattr, state, ilabel, olabel);
+		err = _nfs4_do_setattr(inode, &arg, &res, cred, state);
 		switch (err) {
 		case -NFS4ERR_OPENMODE:
 			if (!(sattr->ia_valid & ATTR_SIZE)) {
@@ -3267,13 +3281,6 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	return status;
 }
 
-static int nfs4_do_find_root_sec(struct nfs_server *server,
-		struct nfs_fh *fhandle, struct nfs_fsinfo *info)
-{
-	int mv = server->nfs_client->cl_minorversion;
-	return nfs_v4_minor_ops[mv]->find_root_sec(server, fhandle, info);
-}
-
 /**
  * nfs4_proc_get_rootfh - get file handle for server's pseudoroot
  * @server: initialized nfs_server handle
@@ -3293,7 +3300,8 @@ int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle,
 		status = nfs4_lookup_root(server, fhandle, info);
 
 	if (auth_probe || status == NFS4ERR_WRONGSEC)
-		status = nfs4_do_find_root_sec(server, fhandle, info);
+		status = server->nfs_client->cl_mvops->find_root_sec(server,
+				fhandle, info);
 
 	if (status == 0)
 		status = nfs4_server_capabilities(server, fhandle);
@@ -4392,7 +4400,8 @@ static void nfs4_proc_read_setup(struct nfs_pgio_header *hdr,
 				 struct rpc_message *msg)
 {
 	hdr->timestamp   = jiffies;
-	hdr->pgio_done_cb = nfs4_read_done_cb;
+	if (!hdr->pgio_done_cb)
+		hdr->pgio_done_cb = nfs4_read_done_cb;
 	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
 	nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0);
 }
@@ -7869,11 +7878,13 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 	struct inode *inode = lgp->args.inode;
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layout_hdr *lo;
-	int status = task->tk_status;
+	int nfs4err = task->tk_status;
+	int err, status = 0;
+	LIST_HEAD(head);
 
 	dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
 
-	switch (status) {
+	switch (nfs4err) {
 	case 0:
 		goto out;
 
@@ -7905,45 +7916,42 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 			status = -EOVERFLOW;
 			goto out;
 		}
-		/* Fallthrough */
+		status = -EBUSY;
+		break;
 	case -NFS4ERR_RECALLCONFLICT:
-		nfs4_handle_exception(server, -NFS4ERR_RECALLCONFLICT,
-					exception);
 		status = -ERECALLCONFLICT;
-		goto out;
+		break;
 	case -NFS4ERR_EXPIRED:
 	case -NFS4ERR_BAD_STATEID:
 		exception->timeout = 0;
 		spin_lock(&inode->i_lock);
-		if (nfs4_stateid_match(&lgp->args.stateid,
+		lo = NFS_I(inode)->layout;
+		/* If the open stateid was bad, then recover it. */
+		if (!lo || test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) ||
+		    nfs4_stateid_match_other(&lgp->args.stateid,
 					&lgp->args.ctx->state->stateid)) {
 			spin_unlock(&inode->i_lock);
-			/* If the open stateid was bad, then recover it. */
 			exception->state = lgp->args.ctx->state;
 			break;
 		}
-		lo = NFS_I(inode)->layout;
-		if (lo && !test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) &&
-		    nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) {
-			LIST_HEAD(head);
-
-			/*
-			 * Mark the bad layout state as invalid, then retry
-			 * with the current stateid.
-			 */
-			set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-			pnfs_mark_matching_lsegs_invalid(lo, &head, NULL, 0);
-			spin_unlock(&inode->i_lock);
-			pnfs_free_lseg_list(&head);
-			status = -EAGAIN;
-			goto out;
-		} else
-			spin_unlock(&inode->i_lock);
-	}
 
-	status = nfs4_handle_exception(server, status, exception);
-	if (exception->retry)
+		/*
+		 * Mark the bad layout state as invalid, then retry
+		 */
+		pnfs_mark_layout_stateid_invalid(lo, &head);
+		spin_unlock(&inode->i_lock);
+		pnfs_free_lseg_list(&head);
 		status = -EAGAIN;
+		goto out;
+	}
+
+	err = nfs4_handle_exception(server, nfs4err, exception);
+	if (!status) {
+		if (exception->retry)
+			status = -EAGAIN;
+		else
+			status = err;
+	}
 out:
 	dprintk("<-- %s\n", __func__);
 	return status;
@@ -8129,8 +8137,7 @@ static void nfs4_layoutreturn_release(void *calldata)
 	spin_lock(&lo->plh_inode->i_lock);
 	pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range,
 			be32_to_cpu(lrp->args.stateid.seqid));
-	pnfs_mark_layout_returned_if_empty(lo);
-	if (lrp->res.lrs_present)
+	if (lrp->res.lrs_present && pnfs_layout_is_valid(lo))
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
 	pnfs_clear_layoutreturn_waitbit(lo);
 	spin_unlock(&lo->plh_inode->i_lock);
@@ -8835,7 +8842,7 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 #endif
 };
 
-ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
+static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 {
 	ssize_t error, error2;
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 661e753fe1c9..7bd3a5c09d31 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1985,9 +1985,14 @@ encode_layoutcommit(struct xdr_stream *xdr,
 	p = xdr_encode_hyper(p, args->lastbytewritten + 1);	/* length */
 	*p = cpu_to_be32(0); /* reclaim */
 	encode_nfs4_stateid(xdr, &args->stateid);
-	p = reserve_space(xdr, 20);
-	*p++ = cpu_to_be32(1); /* newoffset = TRUE */
-	p = xdr_encode_hyper(p, args->lastbytewritten);
+	if (args->lastbytewritten != U64_MAX) {
+		p = reserve_space(xdr, 20);
+		*p++ = cpu_to_be32(1); /* newoffset = TRUE */
+		p = xdr_encode_hyper(p, args->lastbytewritten);
+	} else {
+		p = reserve_space(xdr, 12);
+		*p++ = cpu_to_be32(0); /* newoffset = FALSE */
+	}
 	*p++ = cpu_to_be32(0); /* Never send time_modify_changed */
 	*p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */
 
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 31c7763b94d5..2ca9167bc97d 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -37,7 +37,6 @@
 			{ 1 << NFS_INO_ADVISE_RDPLUS, "ADVISE_RDPLUS" }, \
 			{ 1 << NFS_INO_STALE, "STALE" }, \
 			{ 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \
-			{ 1 << NFS_INO_FLUSHING, "FLUSHING" }, \
 			{ 1 << NFS_INO_FSCACHE, "FSCACHE" }, \
 			{ 1 << NFS_INO_LAYOUTCOMMIT, "NEED_LAYOUTCOMMIT" }, \
 			{ 1 << NFS_INO_LAYOUTCOMMITTING, "LAYOUTCOMMIT" })
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 0fbe734cc38c..70806cae0d36 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -259,7 +259,7 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
  * is required.
  * Note that caller must hold inode->i_lock.
  */
-static int
+int
 pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
 		struct list_head *lseg_list)
 {
@@ -334,14 +334,17 @@ pnfs_layout_io_test_failed(struct pnfs_layout_hdr *lo, u32 iomode)
 }
 
 static void
-init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
+pnfs_init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg,
+		const struct pnfs_layout_range *range,
+		const nfs4_stateid *stateid)
 {
 	INIT_LIST_HEAD(&lseg->pls_list);
 	INIT_LIST_HEAD(&lseg->pls_lc_list);
 	atomic_set(&lseg->pls_refcount, 1);
-	smp_mb();
 	set_bit(NFS_LSEG_VALID, &lseg->pls_flags);
 	lseg->pls_layout = lo;
+	lseg->pls_range = *range;
+	lseg->pls_seq = be32_to_cpu(stateid->seqid);
 }
 
 static void pnfs_free_lseg(struct pnfs_layout_segment *lseg)
@@ -486,15 +489,6 @@ pnfs_lseg_range_intersecting(const struct pnfs_layout_range *l1,
 	       (end2 == NFS4_MAX_UINT64 || end2 > start1);
 }
 
-static bool
-should_free_lseg(const struct pnfs_layout_range *lseg_range,
-		 const struct pnfs_layout_range *recall_range)
-{
-	return (recall_range->iomode == IOMODE_ANY ||
-		lseg_range->iomode == recall_range->iomode) &&
-	       pnfs_lseg_range_intersecting(lseg_range, recall_range);
-}
-
 static bool pnfs_lseg_dec_and_remove_zero(struct pnfs_layout_segment *lseg,
 		struct list_head *tmp_list)
 {
@@ -533,6 +527,27 @@ static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
 	return (s32)(s1 - s2) > 0;
 }
 
+static bool
+pnfs_should_free_range(const struct pnfs_layout_range *lseg_range,
+		 const struct pnfs_layout_range *recall_range)
+{
+	return (recall_range->iomode == IOMODE_ANY ||
+		lseg_range->iomode == recall_range->iomode) &&
+	       pnfs_lseg_range_intersecting(lseg_range, recall_range);
+}
+
+static bool
+pnfs_match_lseg_recall(const struct pnfs_layout_segment *lseg,
+		const struct pnfs_layout_range *recall_range,
+		u32 seq)
+{
+	if (seq != 0 && pnfs_seqid_is_newer(lseg->pls_seq, seq))
+		return false;
+	if (recall_range == NULL)
+		return true;
+	return pnfs_should_free_range(&lseg->pls_range, recall_range);
+}
+
 /**
  * pnfs_mark_matching_lsegs_invalid - tear down lsegs or mark them for later
  * @lo: layout header containing the lsegs
@@ -562,10 +577,7 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 	if (list_empty(&lo->plh_segs))
 		return 0;
 	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
-		if (!recall_range ||
-		    should_free_lseg(&lseg->pls_range, recall_range)) {
-			if (seq && pnfs_seqid_is_newer(lseg->pls_seq, seq))
-				continue;
+		if (pnfs_match_lseg_recall(lseg, recall_range, seq)) {
 			dprintk("%s: freeing lseg %p iomode %d seq %u"
 				"offset %llu length %llu\n", __func__,
 				lseg, lseg->pls_range.iomode, lseg->pls_seq,
@@ -761,24 +773,25 @@ void
 pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
 			bool update_barrier)
 {
-	u32 oldseq, newseq, new_barrier;
-	int empty = list_empty(&lo->plh_segs);
+	u32 oldseq, newseq, new_barrier = 0;
+	bool invalid = !pnfs_layout_is_valid(lo);
 
 	oldseq = be32_to_cpu(lo->plh_stateid.seqid);
 	newseq = be32_to_cpu(new->seqid);
-	if (empty || pnfs_seqid_is_newer(newseq, oldseq)) {
+	if (invalid || pnfs_seqid_is_newer(newseq, oldseq)) {
 		nfs4_stateid_copy(&lo->plh_stateid, new);
-		if (update_barrier) {
-			new_barrier = be32_to_cpu(new->seqid);
-		} else {
-			/* Because of wraparound, we want to keep the barrier
-			 * "close" to the current seqids.
-			 */
-			new_barrier = newseq - atomic_read(&lo->plh_outstanding);
-		}
-		if (empty || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
-			lo->plh_barrier = new_barrier;
+		/*
+		 * Because of wraparound, we want to keep the barrier
+		 * "close" to the current seqids.
+		 */
+		new_barrier = newseq - atomic_read(&lo->plh_outstanding);
 	}
+	if (update_barrier)
+		new_barrier = be32_to_cpu(new->seqid);
+	else if (new_barrier == 0)
+		return;
+	if (invalid || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
+		lo->plh_barrier = new_barrier;
 }
 
 static bool
@@ -873,15 +886,37 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
 	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 }
 
+static void
+pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
+{
+	lo->plh_return_iomode = 0;
+	lo->plh_return_seq = 0;
+	clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+}
+
 static bool
-pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
+pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo,
+		nfs4_stateid *stateid,
+		enum pnfs_iomode *iomode)
 {
 	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
 		return false;
-	lo->plh_return_iomode = 0;
-	lo->plh_return_seq = 0;
 	pnfs_get_layout_hdr(lo);
-	clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+	if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) {
+		if (stateid != NULL) {
+			nfs4_stateid_copy(stateid, &lo->plh_stateid);
+			if (lo->plh_return_seq != 0)
+				stateid->seqid = cpu_to_be32(lo->plh_return_seq);
+		}
+		if (iomode != NULL)
+			*iomode = lo->plh_return_iomode;
+		pnfs_clear_layoutreturn_info(lo);
+		return true;
+	}
+	if (stateid != NULL)
+		nfs4_stateid_copy(stateid, &lo->plh_stateid);
+	if (iomode != NULL)
+		*iomode = IOMODE_ANY;
 	return true;
 }
 
@@ -949,10 +984,7 @@ static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo)
 		enum pnfs_iomode iomode;
 		bool send;
 
-		nfs4_stateid_copy(&stateid, &lo->plh_stateid);
-		stateid.seqid = cpu_to_be32(lo->plh_return_seq);
-		iomode = lo->plh_return_iomode;
-		send = pnfs_prepare_layoutreturn(lo);
+		send = pnfs_prepare_layoutreturn(lo, &stateid, &iomode);
 		spin_unlock(&inode->i_lock);
 		if (send) {
 			/* Send an async layoutreturn so we dont deadlock */
@@ -989,7 +1021,6 @@ _pnfs_return_layout(struct inode *ino)
 		dprintk("NFS: %s no layout to return\n", __func__);
 		goto out;
 	}
-	nfs4_stateid_copy(&stateid, &nfsi->layout->plh_stateid);
 	/* Reference matched in nfs4_layoutreturn_release */
 	pnfs_get_layout_hdr(lo);
 	empty = list_empty(&lo->plh_segs);
@@ -1012,8 +1043,7 @@ _pnfs_return_layout(struct inode *ino)
 		goto out_put_layout_hdr;
 	}
 
-	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-	send = pnfs_prepare_layoutreturn(lo);
+	send = pnfs_prepare_layoutreturn(lo, &stateid, NULL);
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 	if (send)
@@ -1080,11 +1110,10 @@ bool pnfs_roc(struct inode *ino)
 			goto out_noroc;
 	}
 
-	nfs4_stateid_copy(&stateid, &lo->plh_stateid);
 	/* always send layoutreturn if being marked so */
-	if (test_and_clear_bit(NFS_LAYOUT_RETURN_REQUESTED,
-				   &lo->plh_flags))
-		layoutreturn = pnfs_prepare_layoutreturn(lo);
+	if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+		layoutreturn = pnfs_prepare_layoutreturn(lo,
+				&stateid, NULL);
 
 	list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list)
 		/* If we are sending layoutreturn, invalidate all valid lsegs */
@@ -1132,7 +1161,6 @@ void pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
 
 	spin_lock(&ino->i_lock);
 	lo = NFS_I(ino)->layout;
-	pnfs_mark_layout_returned_if_empty(lo);
 	if (pnfs_seqid_is_newer(barrier, lo->plh_barrier))
 		lo->plh_barrier = barrier;
 	spin_unlock(&ino->i_lock);
@@ -1505,7 +1533,7 @@ pnfs_update_layout(struct inode *ino,
 	struct pnfs_layout_segment *lseg = NULL;
 	nfs4_stateid stateid;
 	long timeout = 0;
-	unsigned long giveup = jiffies + rpc_get_timeout(server->client);
+	unsigned long giveup = jiffies + (clp->cl_lease_time << 1);
 	bool first;
 
 	if (!pnfs_enabled_sb(NFS_SERVER(ino))) {
@@ -1645,33 +1673,44 @@ lookup_again:
 	lseg = send_layoutget(lo, ctx, &stateid, &arg, &timeout, gfp_flags);
 	trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				 PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET);
+	atomic_dec(&lo->plh_outstanding);
 	if (IS_ERR(lseg)) {
 		switch(PTR_ERR(lseg)) {
-		case -ERECALLCONFLICT:
+		case -EBUSY:
 			if (time_after(jiffies, giveup))
 				lseg = NULL;
-			/* Fallthrough */
-		case -EAGAIN:
-			pnfs_put_layout_hdr(lo);
-			if (first)
-				pnfs_clear_first_layoutget(lo);
-			if (lseg) {
-				trace_pnfs_update_layout(ino, pos, count,
-					iomode, lo, lseg, PNFS_UPDATE_LAYOUT_RETRY);
-				goto lookup_again;
+			break;
+		case -ERECALLCONFLICT:
+			/* Huh? We hold no layouts, how is there a recall? */
+			if (first) {
+				lseg = NULL;
+				break;
 			}
+			/* Destroy the existing layout and start over */
+			if (time_after(jiffies, giveup))
+				pnfs_destroy_layout(NFS_I(ino));
 			/* Fallthrough */
+		case -EAGAIN:
+			break;
 		default:
 			if (!nfs_error_is_fatal(PTR_ERR(lseg))) {
 				pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
 				lseg = NULL;
 			}
+			goto out_put_layout_hdr;
+		}
+		if (lseg) {
+			if (first)
+				pnfs_clear_first_layoutget(lo);
+			trace_pnfs_update_layout(ino, pos, count,
+				iomode, lo, lseg, PNFS_UPDATE_LAYOUT_RETRY);
+			pnfs_put_layout_hdr(lo);
+			goto lookup_again;
 		}
 	} else {
 		pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
 	}
 
-	atomic_dec(&lo->plh_outstanding);
 out_put_layout_hdr:
 	if (first)
 		pnfs_clear_first_layoutget(lo);
@@ -1735,9 +1774,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		return lseg;
 	}
 
-	init_lseg(lo, lseg);
-	lseg->pls_range = res->range;
-	lseg->pls_seq = be32_to_cpu(res->stateid.seqid);
+	pnfs_init_lseg(lo, lseg, &res->range, &res->stateid);
 
 	spin_lock(&ino->i_lock);
 	if (pnfs_layoutgets_blocked(lo)) {
@@ -1758,16 +1795,19 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		 * inode invalid, and don't bother validating the stateid
 		 * sequence number.
 		 */
-		pnfs_mark_matching_lsegs_invalid(lo, &free_me, NULL, 0);
+		pnfs_mark_layout_stateid_invalid(lo, &free_me);
 
 		nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
 		lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
 	}
 
-	clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-
 	pnfs_get_lseg(lseg);
 	pnfs_layout_insert_lseg(lo, lseg, &free_me);
+	if (!pnfs_layout_is_valid(lo)) {
+		pnfs_clear_layoutreturn_info(lo);
+		clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+	}
+
 
 	if (res->return_on_close)
 		set_bit(NFS_LSEG_ROC, &lseg->pls_flags);
@@ -1787,14 +1827,14 @@ static void
 pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode,
 			 u32 seq)
 {
-	if (lo->plh_return_iomode == iomode)
-		return;
-	if (lo->plh_return_iomode != 0)
+	if (lo->plh_return_iomode != 0 && lo->plh_return_iomode != iomode)
 		iomode = IOMODE_ANY;
 	lo->plh_return_iomode = iomode;
 	set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
-	if (!lo->plh_return_seq || pnfs_seqid_is_newer(seq, lo->plh_return_seq))
+	if (seq != 0) {
+		WARN_ON_ONCE(lo->plh_return_seq != 0 && lo->plh_return_seq != seq);
 		lo->plh_return_seq = seq;
+	}
 }
 
 /**
@@ -1824,7 +1864,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 	assert_spin_locked(&lo->plh_inode->i_lock);
 
 	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
-		if (should_free_lseg(&lseg->pls_range, return_range)) {
+		if (pnfs_match_lseg_recall(lseg, return_range, seq)) {
 			dprintk("%s: marking lseg %p iomode %d "
 				"offset %llu length %llu\n", __func__,
 				lseg, lseg->pls_range.iomode,
@@ -1855,19 +1895,17 @@ void pnfs_error_mark_layout_for_return(struct inode *inode,
 	bool return_now = false;
 
 	spin_lock(&inode->i_lock);
-	pnfs_set_plh_return_info(lo, range.iomode, lseg->pls_seq);
+	pnfs_set_plh_return_info(lo, range.iomode, 0);
 	/*
 	 * mark all matching lsegs so that we are sure to have no live
 	 * segments at hand when sending layoutreturn. See pnfs_put_lseg()
 	 * for how it works.
 	 */
-	if (!pnfs_mark_matching_lsegs_return(lo, &free_me,
-						&range, lseg->pls_seq)) {
+	if (!pnfs_mark_matching_lsegs_return(lo, &free_me, &range, 0)) {
 		nfs4_stateid stateid;
-		enum pnfs_iomode iomode = lo->plh_return_iomode;
+		enum pnfs_iomode iomode;
 
-		nfs4_stateid_copy(&stateid, &lo->plh_stateid);
-		return_now = pnfs_prepare_layoutreturn(lo);
+		return_now = pnfs_prepare_layoutreturn(lo, &stateid, &iomode);
 		spin_unlock(&inode->i_lock);
 		if (return_now)
 			pnfs_send_layoutreturn(lo, &stateid, iomode, false);
@@ -2382,7 +2420,10 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	nfs_fattr_init(&data->fattr);
 	data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
 	data->res.fattr = &data->fattr;
-	data->args.lastbytewritten = end_pos - 1;
+	if (end_pos != 0)
+		data->args.lastbytewritten = end_pos - 1;
+	else
+		data->args.lastbytewritten = U64_MAX;
 	data->res.server = NFS_SERVER(inode);
 
 	if (ld->prepare_layoutcommit) {
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index b21bd0bee784..31d99b2927b0 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -268,6 +268,8 @@ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
 				const struct pnfs_layout_range *recall_range,
 				u32 seq);
+int pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
+		struct list_head *lseg_list);
 bool pnfs_roc(struct inode *ino);
 void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
@@ -375,6 +377,11 @@ static inline bool nfs_have_layout(struct inode *inode)
 	return NFS_I(inode)->layout != NULL;
 }
 
+static inline bool pnfs_layout_is_valid(const struct pnfs_layout_hdr *lo)
+{
+	return test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) == 0;
+}
+
 static inline struct nfs4_deviceid_node *
 nfs4_get_deviceid(struct nfs4_deviceid_node *d)
 {
@@ -545,19 +552,6 @@ pnfs_calc_offset_length(u64 offset, u64 end)
 	return 1 + end - offset;
 }
 
-/**
- * pnfs_mark_layout_returned_if_empty - marks the layout as returned
- * @lo: layout header
- *
- * Note: Caller must hold inode->i_lock
- */
-static inline void
-pnfs_mark_layout_returned_if_empty(struct pnfs_layout_hdr *lo)
-{
-	if (list_empty(&lo->plh_segs))
-		set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-}
-
 static inline void
 pnfs_copy_range(struct pnfs_layout_range *dst,
 		const struct pnfs_layout_range *src)
@@ -629,6 +623,13 @@ pnfs_sync_inode(struct inode *inode, bool datasync)
 }
 
 static inline bool
+pnfs_layoutcommit_outstanding(struct inode *inode)
+{
+	return false;
+}
+
+
+static inline bool
 pnfs_roc(struct inode *ino)
 {
 	return false;
@@ -716,13 +717,6 @@ pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src,
 	return false;
 }
 
-static inline bool
-pnfs_layoutcommit_outstanding(struct inode *inode)
-{
-	return false;
-}
-
-
 static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
 {
 	return NULL;
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index b38e3c0dc790..f3468b57a32a 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -595,7 +595,7 @@ static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
 }
 
 static struct nfs_client *(*get_v3_ds_connect)(
-			struct nfs_client *mds_clp,
+			struct nfs_server *mds_srv,
 			const struct sockaddr *ds_addr,
 			int ds_addrlen,
 			int ds_proto,
@@ -654,7 +654,7 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 			rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
 					rpc_clnt_test_and_add_xprt, NULL);
 		} else
-			clp = get_v3_ds_connect(mds_srv->nfs_client,
+			clp = get_v3_ds_connect(mds_srv,
 					(struct sockaddr *)&da->da_addr,
 					da->da_addrlen, IPPROTO_TCP,
 					timeo, retrans, au_flavor);
@@ -690,7 +690,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 		dprintk("%s: DS %s: trying address %s\n",
 			__func__, ds->ds_remotestr, da->da_remotestr);
 
-		clp = nfs4_set_ds_client(mds_srv->nfs_client,
+		clp = nfs4_set_ds_client(mds_srv,
 					(struct sockaddr *)&da->da_addr,
 					da->da_addrlen, IPPROTO_TCP,
 					timeo, retrans, minor_version,
@@ -940,6 +940,13 @@ EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit);
 int
 pnfs_nfs_generic_sync(struct inode *inode, bool datasync)
 {
+	int ret;
+
+	if (!pnfs_layoutcommit_outstanding(inode))
+		return 0;
+	ret = nfs_commit_inode(inode, FLUSH_SYNC);
+	if (ret < 0)
+		return ret;
 	if (datasync)
 		return 0;
 	return pnfs_layoutcommit_inode(inode, true);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2137e0202f25..18d446e1a82b 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1684,6 +1684,7 @@ static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args,
 {
 	rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR;
 	unsigned int i;
+	int use_auth_null = false;
 
 	/*
 	 * If the sec= mount option is used, the specified flavor or AUTH_NULL
@@ -1691,14 +1692,21 @@ static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args,
 	 *
 	 * AUTH_NULL has a special meaning when it's in the server list - it
 	 * means that the server will ignore the rpc creds, so any flavor
-	 * can be used.
+	 * can be used but still use the sec= that was specified.
 	 */
 	for (i = 0; i < count; i++) {
 		flavor = server_authlist[i];
 
-		if (nfs_auth_info_match(&args->auth_info, flavor) ||
-		    flavor == RPC_AUTH_NULL)
+		if (nfs_auth_info_match(&args->auth_info, flavor))
 			goto out;
+
+		if (flavor == RPC_AUTH_NULL)
+			use_auth_null = true;
+	}
+
+	if (use_auth_null) {
+		flavor = RPC_AUTH_NULL;
+		goto out;
 	}
 
 	dfprintk(MOUNT,
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 593fa21a02c0..3a6724c6eb5f 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -625,7 +625,7 @@ static int nfs_writepage_locked(struct page *page,
 	int err;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
-	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc),
+	nfs_pageio_init_write(&pgio, inode, 0,
 				false, &nfs_async_write_completion_ops);
 	err = nfs_do_writepage(page, wbc, &pgio, launder);
 	nfs_pageio_complete(&pgio);
@@ -657,16 +657,9 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control *
 int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
-	unsigned long *bitlock = &NFS_I(inode)->flags;
 	struct nfs_pageio_descriptor pgio;
 	int err;
 
-	/* Stop dirtying of new pages while we sync */
-	err = wait_on_bit_lock_action(bitlock, NFS_INO_FLUSHING,
-			nfs_wait_bit_killable, TASK_KILLABLE);
-	if (err)
-		goto out_err;
-
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
 	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false,
@@ -674,10 +667,6 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
 	nfs_pageio_complete(&pgio);
 
-	clear_bit_unlock(NFS_INO_FLUSHING, bitlock);
-	smp_mb__after_atomic();
-	wake_up_bit(bitlock, NFS_INO_FLUSHING);
-
 	if (err < 0)
 		goto out_err;
 	err = pgio.pg_error;
@@ -1195,9 +1184,11 @@ nfs_key_timeout_notify(struct file *filp, struct inode *inode)
 /*
  * Test if the open context credential key is marked to expire soon.
  */
-bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx)
+bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode)
 {
-	return rpcauth_cred_key_to_expire(ctx->cred);
+	struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth;
+
+	return rpcauth_cred_key_to_expire(auth, ctx->cred);
 }
 
 /*
@@ -1289,6 +1280,9 @@ int nfs_updatepage(struct file *file, struct page *page,
 	dprintk("NFS:       nfs_updatepage(%pD2 %d@%lld)\n",
 		file, count, (long long)(page_file_offset(page) + offset));
 
+	if (!count)
+		goto out;
+
 	if (nfs_can_extend_write(file, page, inode)) {
 		count = max(count + offset, nfs_page_length(page));
 		offset = 0;
@@ -1299,7 +1293,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 		nfs_set_pageerror(page);
 	else
 		__set_page_dirty_nobuffers(page);
-
+out:
 	dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
 			status, (long long)i_size_read(inode));
 	return status;
@@ -1800,7 +1794,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 
 		/* Okay, COMMIT succeeded, apparently. Check the verifier
 		 * returned by the server against all stored verfs. */
-		if (!memcmp(&req->wb_verf, &data->verf.verifier, sizeof(req->wb_verf))) {
+		if (!nfs_write_verifier_cmp(&req->wb_verf, &data->verf.verifier)) {
 			/* We have a match */
 			nfs_inode_remove_request(req);
 			dprintk(" OK\n");
@@ -1924,6 +1918,24 @@ out_mark_dirty:
 EXPORT_SYMBOL_GPL(nfs_write_inode);
 
 /*
+ * Wrapper for filemap_write_and_wait_range()
+ *
+ * Needed for pNFS in order to ensure data becomes visible to the
+ * client.
+ */
+int nfs_filemap_write_and_wait_range(struct address_space *mapping,
+		loff_t lstart, loff_t lend)
+{
+	int ret;
+
+	ret = filemap_write_and_wait_range(mapping, lstart, lend);
+	if (ret == 0)
+		ret = pnfs_sync_inode(mapping->host, true);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nfs_filemap_write_and_wait_range);
+
+/*
  * flush the inode to disk.
  */
 int nfs_wb_all(struct inode *inode)
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 1a85d94f5b25..2c90e285d7c6 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -622,10 +622,10 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
 	lock = nilfs_mdt_bgl_lock(inode, group);
 
 	if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
-		nilfs_warning(inode->i_sb, __func__,
-			      "entry number %llu already freed: ino=%lu",
-			      (unsigned long long)req->pr_entry_nr,
-			      (unsigned long)inode->i_ino);
+		nilfs_msg(inode->i_sb, KERN_WARNING,
+			  "%s (ino=%lu): entry number %llu already freed",
+			  __func__, inode->i_ino,
+			  (unsigned long long)req->pr_entry_nr);
 	else
 		nilfs_palloc_group_desc_add_entries(desc, lock, 1);
 
@@ -663,10 +663,10 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
 	lock = nilfs_mdt_bgl_lock(inode, group);
 
 	if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
-		nilfs_warning(inode->i_sb, __func__,
-			      "entry number %llu already freed: ino=%lu",
-			      (unsigned long long)req->pr_entry_nr,
-			      (unsigned long)inode->i_ino);
+		nilfs_msg(inode->i_sb, KERN_WARNING,
+			  "%s (ino=%lu): entry number %llu already freed",
+			  __func__, inode->i_ino,
+			  (unsigned long long)req->pr_entry_nr);
 	else
 		nilfs_palloc_group_desc_add_entries(desc, lock, 1);
 
@@ -772,10 +772,10 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 		do {
 			if (!nilfs_clear_bit_atomic(lock, group_offset,
 						    bitmap)) {
-				nilfs_warning(inode->i_sb, __func__,
-					      "entry number %llu already freed: ino=%lu",
-					      (unsigned long long)entry_nrs[j],
-					      (unsigned long)inode->i_ino);
+				nilfs_msg(inode->i_sb, KERN_WARNING,
+					  "%s (ino=%lu): entry number %llu already freed",
+					  __func__, inode->i_ino,
+					  (unsigned long long)entry_nrs[j]);
 			} else {
 				n++;
 			}
@@ -816,12 +816,11 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 		for (k = 0; k < nempties; k++) {
 			ret = nilfs_palloc_delete_entry_block(inode,
 							      last_nrs[k]);
-			if (ret && ret != -ENOENT) {
-				nilfs_warning(inode->i_sb, __func__,
-					      "failed to delete block of entry %llu: ino=%lu, err=%d",
-					      (unsigned long long)last_nrs[k],
-					      (unsigned long)inode->i_ino, ret);
-			}
+			if (ret && ret != -ENOENT)
+				nilfs_msg(inode->i_sb, KERN_WARNING,
+					  "error %d deleting block that object (entry=%llu, ino=%lu) belongs to",
+					  ret, (unsigned long long)last_nrs[k],
+					  inode->i_ino);
 		}
 
 		desc_kaddr = kmap_atomic(desc_bh->b_page);
@@ -835,12 +834,10 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 
 		if (nfree == nilfs_palloc_entries_per_group(inode)) {
 			ret = nilfs_palloc_delete_bitmap_block(inode, group);
-			if (ret && ret != -ENOENT) {
-				nilfs_warning(inode->i_sb, __func__,
-					      "failed to delete bitmap block of group %lu: ino=%lu, err=%d",
-					      group,
-					      (unsigned long)inode->i_ino, ret);
-			}
+			if (ret && ret != -ENOENT)
+				nilfs_msg(inode->i_sb, KERN_WARNING,
+					  "error %d deleting bitmap block of group=%lu, ino=%lu",
+					  ret, group, inode->i_ino);
 		}
 	}
 	return 0;
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index f2a7877e0c8c..01fb1831ca25 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -41,8 +41,8 @@ static int nilfs_bmap_convert_error(struct nilfs_bmap *bmap,
 	struct inode *inode = bmap->b_inode;
 
 	if (err == -EINVAL) {
-		nilfs_error(inode->i_sb, fname,
-			    "broken bmap (inode number=%lu)", inode->i_ino);
+		__nilfs_error(inode->i_sb, fname,
+			      "broken bmap (inode number=%lu)", inode->i_ino);
 		err = -EIO;
 	}
 	return err;
diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h
index b6a4c8f93ac8..2b6ffbe5997a 100644
--- a/fs/nilfs2/bmap.h
+++ b/fs/nilfs2/bmap.h
@@ -22,7 +22,7 @@
 #include <linux/types.h>
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
-#include <linux/nilfs2_fs.h>
+#include <linux/nilfs2_ondisk.h>	/* nilfs_binfo, nilfs_inode, etc */
 #include "alloc.h"
 #include "dat.h"
 
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 4cca998ec7a0..d5c23da43513 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -41,7 +41,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 	struct inode *inode = NILFS_BTNC_I(btnc);
 	struct buffer_head *bh;
 
-	bh = nilfs_grab_buffer(inode, btnc, blocknr, 1 << BH_NILFS_Node);
+	bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node));
 	if (unlikely(!bh))
 		return NULL;
 
@@ -70,7 +70,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
 	struct page *page;
 	int err;
 
-	bh = nilfs_grab_buffer(inode, btnc, blocknr, 1 << BH_NILFS_Node);
+	bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node));
 	if (unlikely(!bh))
 		return -ENOMEM;
 
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 982d1e3df3a5..2e315f9f2e51 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -339,12 +339,14 @@ static int nilfs_btree_node_lookup(const struct nilfs_btree_node *node,
  * nilfs_btree_node_broken - verify consistency of btree node
  * @node: btree node block to be examined
  * @size: node size (in bytes)
+ * @inode: host inode of btree
  * @blocknr: block number
  *
  * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned.
  */
 static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
-				   size_t size, sector_t blocknr)
+				   size_t size, struct inode *inode,
+				   sector_t blocknr)
 {
 	int level, flags, nchildren;
 	int ret = 0;
@@ -358,9 +360,10 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
 		     (flags & NILFS_BTREE_NODE_ROOT) ||
 		     nchildren < 0 ||
 		     nchildren > NILFS_BTREE_NODE_NCHILDREN_MAX(size))) {
-		printk(KERN_CRIT "NILFS: bad btree node (blocknr=%llu): "
-		       "level = %d, flags = 0x%x, nchildren = %d\n",
-		       (unsigned long long)blocknr, level, flags, nchildren);
+		nilfs_msg(inode->i_sb, KERN_CRIT,
+			  "bad btree node (ino=%lu, blocknr=%llu): level = %d, flags = 0x%x, nchildren = %d",
+			  inode->i_ino, (unsigned long long)blocknr, level,
+			  flags, nchildren);
 		ret = 1;
 	}
 	return ret;
@@ -369,12 +372,12 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
 /**
  * nilfs_btree_root_broken - verify consistency of btree root node
  * @node: btree root node to be examined
- * @ino: inode number
+ * @inode: host inode of btree
  *
  * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned.
  */
 static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
-				   unsigned long ino)
+				   struct inode *inode)
 {
 	int level, flags, nchildren;
 	int ret = 0;
@@ -387,8 +390,9 @@ static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
 		     level >= NILFS_BTREE_LEVEL_MAX ||
 		     nchildren < 0 ||
 		     nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) {
-		pr_crit("NILFS: bad btree root (inode number=%lu): level = %d, flags = 0x%x, nchildren = %d\n",
-			ino, level, flags, nchildren);
+		nilfs_msg(inode->i_sb, KERN_CRIT,
+			  "bad btree root (ino=%lu): level = %d, flags = 0x%x, nchildren = %d",
+			  inode->i_ino, level, flags, nchildren);
 		ret = 1;
 	}
 	return ret;
@@ -396,13 +400,15 @@ static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
 
 int nilfs_btree_broken_node_block(struct buffer_head *bh)
 {
+	struct inode *inode;
 	int ret;
 
 	if (buffer_nilfs_checked(bh))
 		return 0;
 
+	inode = bh->b_page->mapping->host;
 	ret = nilfs_btree_node_broken((struct nilfs_btree_node *)bh->b_data,
-				       bh->b_size, bh->b_blocknr);
+				      bh->b_size, inode, bh->b_blocknr);
 	if (likely(!ret))
 		set_buffer_nilfs_checked(bh);
 	return ret;
@@ -448,13 +454,15 @@ nilfs_btree_get_node(const struct nilfs_bmap *btree,
 	return node;
 }
 
-static int
-nilfs_btree_bad_node(struct nilfs_btree_node *node, int level)
+static int nilfs_btree_bad_node(const struct nilfs_bmap *btree,
+				struct nilfs_btree_node *node, int level)
 {
 	if (unlikely(nilfs_btree_node_get_level(node) != level)) {
 		dump_stack();
-		printk(KERN_CRIT "NILFS: btree level mismatch: %d != %d\n",
-		       nilfs_btree_node_get_level(node), level);
+		nilfs_msg(btree->b_inode->i_sb, KERN_CRIT,
+			  "btree level mismatch (ino=%lu): %d != %d",
+			  btree->b_inode->i_ino,
+			  nilfs_btree_node_get_level(node), level);
 		return 1;
 	}
 	return 0;
@@ -509,6 +517,9 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr,
 
  out_no_wait:
 	if (!buffer_uptodate(bh)) {
+		nilfs_msg(btree->b_inode->i_sb, KERN_ERR,
+			  "I/O error reading b-tree node block (ino=%lu, blocknr=%llu)",
+			  btree->b_inode->i_ino, (unsigned long long)ptr);
 		brelse(bh);
 		return -EIO;
 	}
@@ -568,7 +579,7 @@ static int nilfs_btree_do_lookup(const struct nilfs_bmap *btree,
 			return ret;
 
 		node = nilfs_btree_get_nonroot_node(path, level);
-		if (nilfs_btree_bad_node(node, level))
+		if (nilfs_btree_bad_node(btree, node, level))
 			return -EINVAL;
 		if (!found)
 			found = nilfs_btree_node_lookup(node, key, &index);
@@ -616,7 +627,7 @@ static int nilfs_btree_do_lookup_last(const struct nilfs_bmap *btree,
 		if (ret < 0)
 			return ret;
 		node = nilfs_btree_get_nonroot_node(path, level);
-		if (nilfs_btree_bad_node(node, level))
+		if (nilfs_btree_bad_node(btree, node, level))
 			return -EINVAL;
 		index = nilfs_btree_node_get_nchildren(node) - 1;
 		ptr = nilfs_btree_node_get_ptr(node, index, ncmax);
@@ -2072,8 +2083,10 @@ static int nilfs_btree_propagate(struct nilfs_bmap *btree,
 	ret = nilfs_btree_do_lookup(btree, path, key, NULL, level + 1, 0);
 	if (ret < 0) {
 		if (unlikely(ret == -ENOENT))
-			printk(KERN_CRIT "%s: key = %llu, level == %d\n",
-			       __func__, (unsigned long long)key, level);
+			nilfs_msg(btree->b_inode->i_sb, KERN_CRIT,
+				  "writing node/leaf block does not appear in b-tree (ino=%lu) at key=%llu, level=%d",
+				  btree->b_inode->i_ino,
+				  (unsigned long long)key, level);
 		goto out;
 	}
 
@@ -2110,12 +2123,11 @@ static void nilfs_btree_add_dirty_buffer(struct nilfs_bmap *btree,
 	if (level < NILFS_BTREE_LEVEL_NODE_MIN ||
 	    level >= NILFS_BTREE_LEVEL_MAX) {
 		dump_stack();
-		printk(KERN_WARNING
-		       "%s: invalid btree level: %d (key=%llu, ino=%lu, "
-		       "blocknr=%llu)\n",
-		       __func__, level, (unsigned long long)key,
-		       NILFS_BMAP_I(btree)->vfs_inode.i_ino,
-		       (unsigned long long)bh->b_blocknr);
+		nilfs_msg(btree->b_inode->i_sb, KERN_WARNING,
+			  "invalid btree level: %d (key=%llu, ino=%lu, blocknr=%llu)",
+			  level, (unsigned long long)key,
+			  btree->b_inode->i_ino,
+			  (unsigned long long)bh->b_blocknr);
 		return;
 	}
 
@@ -2394,8 +2406,7 @@ int nilfs_btree_init(struct nilfs_bmap *bmap)
 
 	__nilfs_btree_init(bmap);
 
-	if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap),
-				    bmap->b_inode->i_ino))
+	if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap), bmap->b_inode))
 		ret = -EIO;
 	return ret;
 }
diff --git a/fs/nilfs2/btree.h b/fs/nilfs2/btree.h
index df1a25faa83b..2184e47fa4bf 100644
--- a/fs/nilfs2/btree.h
+++ b/fs/nilfs2/btree.h
@@ -22,7 +22,7 @@
 #include <linux/types.h>
 #include <linux/buffer_head.h>
 #include <linux/list.h>
-#include <linux/nilfs2_fs.h>
+#include <linux/nilfs2_ondisk.h>	/* nilfs_btree_node */
 #include "btnode.h"
 #include "bmap.h"
 
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index 8a3d3b65af3f..a15a1601e931 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -21,7 +21,6 @@
 #include <linux/string.h>
 #include <linux/buffer_head.h>
 #include <linux/errno.h>
-#include <linux/nilfs2_fs.h>
 #include "mdt.h"
 #include "cpfile.h"
 
@@ -332,9 +331,9 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 	int ret, ncps, nicps, nss, count, i;
 
 	if (unlikely(start == 0 || start > end)) {
-		printk(KERN_ERR "%s: invalid range of checkpoint numbers: "
-		       "[%llu, %llu)\n", __func__,
-		       (unsigned long long)start, (unsigned long long)end);
+		nilfs_msg(cpfile->i_sb, KERN_ERR,
+			  "cannot delete checkpoints: invalid range [%llu, %llu)",
+			  (unsigned long long)start, (unsigned long long)end);
 		return -EINVAL;
 	}
 
@@ -386,9 +385,9 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 								   cpfile, cno);
 					if (ret == 0)
 						continue;
-					printk(KERN_ERR
-					       "%s: cannot delete block\n",
-					       __func__);
+					nilfs_msg(cpfile->i_sb, KERN_ERR,
+						  "error %d deleting checkpoint block",
+						  ret);
 					break;
 				}
 			}
@@ -991,14 +990,12 @@ int nilfs_cpfile_read(struct super_block *sb, size_t cpsize,
 	int err;
 
 	if (cpsize > sb->s_blocksize) {
-		printk(KERN_ERR
-		       "NILFS: too large checkpoint size: %zu bytes.\n",
-		       cpsize);
+		nilfs_msg(sb, KERN_ERR,
+			  "too large checkpoint size: %zu bytes", cpsize);
 		return -EINVAL;
 	} else if (cpsize < NILFS_MIN_CHECKPOINT_SIZE) {
-		printk(KERN_ERR
-		       "NILFS: too small checkpoint size: %zu bytes.\n",
-		       cpsize);
+		nilfs_msg(sb, KERN_ERR,
+			  "too small checkpoint size: %zu bytes", cpsize);
 		return -EINVAL;
 	}
 
diff --git a/fs/nilfs2/cpfile.h b/fs/nilfs2/cpfile.h
index 0249744ae234..6eca972f9673 100644
--- a/fs/nilfs2/cpfile.h
+++ b/fs/nilfs2/cpfile.h
@@ -21,7 +21,8 @@
 
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
-#include <linux/nilfs2_fs.h>
+#include <linux/nilfs2_api.h>		/* nilfs_cpstat */
+#include <linux/nilfs2_ondisk.h>	/* nilfs_inode, nilfs_checkpoint */
 
 
 int nilfs_cpfile_get_checkpoint(struct inode *, __u64, int,
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 7367610ea807..dffedb2f8817 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -349,10 +349,11 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr)
 	kaddr = kmap_atomic(entry_bh->b_page);
 	entry = nilfs_palloc_block_get_entry(dat, vblocknr, entry_bh, kaddr);
 	if (unlikely(entry->de_blocknr == cpu_to_le64(0))) {
-		printk(KERN_CRIT "%s: vbn = %llu, [%llu, %llu)\n", __func__,
-		       (unsigned long long)vblocknr,
-		       (unsigned long long)le64_to_cpu(entry->de_start),
-		       (unsigned long long)le64_to_cpu(entry->de_end));
+		nilfs_msg(dat->i_sb, KERN_CRIT,
+			  "%s: invalid vblocknr = %llu, [%llu, %llu)",
+			  __func__, (unsigned long long)vblocknr,
+			  (unsigned long long)le64_to_cpu(entry->de_start),
+			  (unsigned long long)le64_to_cpu(entry->de_end));
 		kunmap_atomic(kaddr);
 		brelse(entry_bh);
 		return -EINVAL;
@@ -479,14 +480,12 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size,
 	int err;
 
 	if (entry_size > sb->s_blocksize) {
-		printk(KERN_ERR
-		       "NILFS: too large DAT entry size: %zu bytes.\n",
-		       entry_size);
+		nilfs_msg(sb, KERN_ERR, "too large DAT entry size: %zu bytes",
+			  entry_size);
 		return -EINVAL;
 	} else if (entry_size < NILFS_MIN_DAT_ENTRY_SIZE) {
-		printk(KERN_ERR
-		       "NILFS: too small DAT entry size: %zu bytes.\n",
-		       entry_size);
+		nilfs_msg(sb, KERN_ERR, "too small DAT entry size: %zu bytes",
+			  entry_size);
 		return -EINVAL;
 	}
 
diff --git a/fs/nilfs2/dat.h b/fs/nilfs2/dat.h
index abbfdabcabea..57dc6cf466d0 100644
--- a/fs/nilfs2/dat.h
+++ b/fs/nilfs2/dat.h
@@ -22,6 +22,7 @@
 #include <linux/types.h>
 #include <linux/buffer_head.h>
 #include <linux/fs.h>
+#include <linux/nilfs2_ondisk.h>	/* nilfs_inode, nilfs_checkpoint */
 
 
 struct nilfs_palloc_req;
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index e506f4f7120a..908ebbf0ac7e 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -42,6 +42,28 @@
 #include "nilfs.h"
 #include "page.h"
 
+static inline unsigned int nilfs_rec_len_from_disk(__le16 dlen)
+{
+	unsigned int len = le16_to_cpu(dlen);
+
+#if (PAGE_SIZE >= 65536)
+	if (len == NILFS_MAX_REC_LEN)
+		return 1 << 16;
+#endif
+	return len;
+}
+
+static inline __le16 nilfs_rec_len_to_disk(unsigned int len)
+{
+#if (PAGE_SIZE >= 65536)
+	if (len == (1 << 16))
+		return cpu_to_le16(NILFS_MAX_REC_LEN);
+
+	BUG_ON(len > (1 << 16));
+#endif
+	return cpu_to_le16(len);
+}
+
 /*
  * nilfs uses block-sized chunks. Arguably, sector-sized ones would be
  * more robust, but we have what we have
@@ -140,10 +162,9 @@ out:
 	/* Too bad, we had an error */
 
 Ebadsize:
-	nilfs_error(sb, "nilfs_check_page",
+	nilfs_error(sb,
 		    "size of directory #%lu is not a multiple of chunk size",
-		    dir->i_ino
-	);
+		    dir->i_ino);
 	goto fail;
 Eshort:
 	error = "rec_len is smaller than minimal";
@@ -157,19 +178,18 @@ Enamelen:
 Espan:
 	error = "directory entry across blocks";
 bad_entry:
-	nilfs_error(sb, "nilfs_check_page", "bad entry in directory #%lu: %s - "
-		    "offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
-		    dir->i_ino, error, (page->index<<PAGE_SHIFT)+offs,
-		    (unsigned long) le64_to_cpu(p->inode),
+	nilfs_error(sb,
+		    "bad entry in directory #%lu: %s - offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
+		    dir->i_ino, error, (page->index << PAGE_SHIFT) + offs,
+		    (unsigned long)le64_to_cpu(p->inode),
 		    rec_len, p->name_len);
 	goto fail;
 Eend:
 	p = (struct nilfs_dir_entry *)(kaddr + offs);
-	nilfs_error(sb, "nilfs_check_page",
-		    "entry in directory #%lu spans the page boundary"
-		    "offset=%lu, inode=%lu",
-		    dir->i_ino, (page->index<<PAGE_SHIFT)+offs,
-		    (unsigned long) le64_to_cpu(p->inode));
+	nilfs_error(sb,
+		    "entry in directory #%lu spans the page boundary offset=%lu, inode=%lu",
+		    dir->i_ino, (page->index << PAGE_SHIFT) + offs,
+		    (unsigned long)le64_to_cpu(p->inode));
 fail:
 	SetPageError(page);
 	return false;
@@ -267,8 +287,7 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx)
 		struct page *page = nilfs_get_page(inode, n);
 
 		if (IS_ERR(page)) {
-			nilfs_error(sb, __func__, "bad page in #%lu",
-				    inode->i_ino);
+			nilfs_error(sb, "bad page in #%lu", inode->i_ino);
 			ctx->pos += PAGE_SIZE - offset;
 			return -EIO;
 		}
@@ -278,8 +297,7 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx)
 			NILFS_DIR_REC_LEN(1);
 		for ( ; (char *)de <= limit; de = nilfs_next_entry(de)) {
 			if (de->rec_len == 0) {
-				nilfs_error(sb, __func__,
-					    "zero-length directory entry");
+				nilfs_error(sb, "zero-length directory entry");
 				nilfs_put_page(page);
 				return -EIO;
 			}
@@ -345,7 +363,7 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr,
 			kaddr += nilfs_last_byte(dir, n) - reclen;
 			while ((char *) de <= kaddr) {
 				if (de->rec_len == 0) {
-					nilfs_error(dir->i_sb, __func__,
+					nilfs_error(dir->i_sb,
 						"zero-length directory entry");
 					nilfs_put_page(page);
 					goto out;
@@ -360,7 +378,7 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr,
 			n = 0;
 		/* next page is past the blocks we've got */
 		if (unlikely(n > (dir->i_blocks >> (PAGE_SHIFT - 9)))) {
-			nilfs_error(dir->i_sb, __func__,
+			nilfs_error(dir->i_sb,
 			       "dir %lu size %lld exceeds block count %llu",
 			       dir->i_ino, dir->i_size,
 			       (unsigned long long)dir->i_blocks);
@@ -469,7 +487,7 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode)
 				goto got_it;
 			}
 			if (de->rec_len == 0) {
-				nilfs_error(dir->i_sb, __func__,
+				nilfs_error(dir->i_sb,
 					    "zero-length directory entry");
 				err = -EIO;
 				goto out_unlock;
@@ -541,7 +559,7 @@ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page)
 
 	while ((char *)de < (char *)dir) {
 		if (de->rec_len == 0) {
-			nilfs_error(inode->i_sb, __func__,
+			nilfs_error(inode->i_sb,
 				    "zero-length directory entry");
 			err = -EIO;
 			goto out;
@@ -628,7 +646,7 @@ int nilfs_empty_dir(struct inode *inode)
 
 		while ((char *)de <= kaddr) {
 			if (de->rec_len == 0) {
-				nilfs_error(inode->i_sb, __func__,
+				nilfs_error(inode->i_sb,
 					    "zero-length directory entry (kaddr=%p, de=%p)",
 					    kaddr, de);
 				goto not_empty;
diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c
index 251a44928405..96e3ed0d9652 100644
--- a/fs/nilfs2/direct.c
+++ b/fs/nilfs2/direct.c
@@ -337,14 +337,16 @@ static int nilfs_direct_assign(struct nilfs_bmap *bmap,
 
 	key = nilfs_bmap_data_get_key(bmap, *bh);
 	if (unlikely(key > NILFS_DIRECT_KEY_MAX)) {
-		printk(KERN_CRIT "%s: invalid key: %llu\n", __func__,
-		       (unsigned long long)key);
+		nilfs_msg(bmap->b_inode->i_sb, KERN_CRIT,
+			  "%s (ino=%lu): invalid key: %llu", __func__,
+			  bmap->b_inode->i_ino, (unsigned long long)key);
 		return -EINVAL;
 	}
 	ptr = nilfs_direct_get_ptr(bmap, key);
 	if (unlikely(ptr == NILFS_BMAP_INVALID_PTR)) {
-		printk(KERN_CRIT "%s: invalid pointer: %llu\n", __func__,
-		       (unsigned long long)ptr);
+		nilfs_msg(bmap->b_inode->i_sb, KERN_CRIT,
+			  "%s (ino=%lu): invalid pointer: %llu", __func__,
+			  bmap->b_inode->i_ino, (unsigned long long)ptr);
 		return -EINVAL;
 	}
 
diff --git a/fs/nilfs2/direct.h b/fs/nilfs2/direct.h
index 3015a6e78724..cfe85e848bba 100644
--- a/fs/nilfs2/direct.h
+++ b/fs/nilfs2/direct.h
@@ -24,16 +24,6 @@
 #include "bmap.h"
 
 
-/**
- * struct nilfs_direct_node - direct node
- * @dn_flags: flags
- * @dn_pad: padding
- */
-struct nilfs_direct_node {
-	__u8 dn_flags;
-	__u8 pad[7];
-};
-
 #define NILFS_DIRECT_NBLOCKS	(NILFS_BMAP_SIZE / sizeof(__le64) - 1)
 #define NILFS_DIRECT_KEY_MIN	0
 #define NILFS_DIRECT_KEY_MAX	(NILFS_DIRECT_NBLOCKS - 1)
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index e9148f94d696..853a831dcde0 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -148,8 +148,15 @@ int nilfs_gccache_submit_read_node(struct inode *inode, sector_t pbn,
 int nilfs_gccache_wait_and_mark_dirty(struct buffer_head *bh)
 {
 	wait_on_buffer(bh);
-	if (!buffer_uptodate(bh))
+	if (!buffer_uptodate(bh)) {
+		struct inode *inode = bh->b_page->mapping->host;
+
+		nilfs_msg(inode->i_sb, KERN_ERR,
+			  "I/O error reading %s block for GC (ino=%lu, vblocknr=%llu)",
+			  buffer_nilfs_node(bh) ? "node" : "data",
+			  inode->i_ino, (unsigned long long)bh->b_blocknr);
 		return -EIO;
+	}
 	if (buffer_dirty(bh))
 		return -EEXIST;
 
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 1d2b1805327a..b8fa45c20c63 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -145,15 +145,14 @@ int nilfs_ifile_get_inode_block(struct inode *ifile, ino_t ino,
 	int err;
 
 	if (unlikely(!NILFS_VALID_INODE(sb, ino))) {
-		nilfs_error(sb, __func__, "bad inode number: %lu",
-			    (unsigned long) ino);
+		nilfs_error(sb, "bad inode number: %lu", (unsigned long)ino);
 		return -EINVAL;
 	}
 
 	err = nilfs_palloc_get_entry_block(ifile, ino, 0, out_bh);
 	if (unlikely(err))
-		nilfs_warning(sb, __func__, "unable to read inode: %lu",
-			      (unsigned long) ino);
+		nilfs_msg(sb, KERN_WARNING, "error %d reading inode: ino=%lu",
+			  err, (unsigned long)ino);
 	return err;
 }
 
diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h
index 23ad2f091e76..188b94fe0ec5 100644
--- a/fs/nilfs2/ifile.h
+++ b/fs/nilfs2/ifile.h
@@ -23,7 +23,6 @@
 
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
-#include <linux/nilfs2_fs.h>
 #include "mdt.h"
 #include "alloc.h"
 
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index a0ebdb17e912..af04f553d7c9 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -112,13 +112,10 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
 				 * However, the page having this block must
 				 * be locked in this case.
 				 */
-				printk(KERN_WARNING
-				       "nilfs_get_block: a race condition "
-				       "while inserting a data block. "
-				       "(inode number=%lu, file block "
-				       "offset=%llu)\n",
-				       inode->i_ino,
-				       (unsigned long long)blkoff);
+				nilfs_msg(inode->i_sb, KERN_WARNING,
+					  "%s (ino=%lu): a race condition while inserting a data block at offset=%llu",
+					  __func__, inode->i_ino,
+					  (unsigned long long)blkoff);
 				err = 0;
 			}
 			nilfs_transaction_abort(inode->i_sb);
@@ -359,7 +356,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 
 	root = NILFS_I(dir)->i_root;
 	ii = NILFS_I(inode);
-	ii->i_state = 1 << NILFS_I_NEW;
+	ii->i_state = BIT(NILFS_I_NEW);
 	ii->i_root = root;
 
 	err = nilfs_ifile_create_inode(root->ifile, &ino, &ii->i_bh);
@@ -558,7 +555,7 @@ static int nilfs_iget_set(struct inode *inode, void *opaque)
 
 	inode->i_ino = args->ino;
 	if (args->for_gc) {
-		NILFS_I(inode)->i_state = 1 << NILFS_I_GCINODE;
+		NILFS_I(inode)->i_state = BIT(NILFS_I_GCINODE);
 		NILFS_I(inode)->i_cno = args->cno;
 		NILFS_I(inode)->i_root = NULL;
 	} else {
@@ -726,9 +723,9 @@ repeat:
 		goto repeat;
 
 failed:
-	nilfs_warning(ii->vfs_inode.i_sb, __func__,
-		      "failed to truncate bmap (ino=%lu, err=%d)",
-		      ii->vfs_inode.i_ino, ret);
+	nilfs_msg(ii->vfs_inode.i_sb, KERN_WARNING,
+		  "error %d truncating bmap (ino=%lu)", ret,
+		  ii->vfs_inode.i_ino);
 }
 
 void nilfs_truncate(struct inode *inode)
@@ -939,9 +936,9 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty)
 			 * This will happen when somebody is freeing
 			 * this inode.
 			 */
-			nilfs_warning(inode->i_sb, __func__,
-				      "cannot get inode (ino=%lu)",
-				      inode->i_ino);
+			nilfs_msg(inode->i_sb, KERN_WARNING,
+				  "cannot set file dirty (ino=%lu): the file is being freed",
+				  inode->i_ino);
 			spin_unlock(&nilfs->ns_inode_lock);
 			return -EINVAL; /*
 					 * NILFS_I_DIRTY may remain for
@@ -962,8 +959,9 @@ int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
 
 	err = nilfs_load_inode_block(inode, &ibh);
 	if (unlikely(err)) {
-		nilfs_warning(inode->i_sb, __func__,
-			      "failed to reget inode block.");
+		nilfs_msg(inode->i_sb, KERN_WARNING,
+			  "cannot mark inode dirty (ino=%lu): error %d loading inode block",
+			  inode->i_ino, err);
 		return err;
 	}
 	nilfs_update_inode(inode, ibh, flags);
@@ -989,8 +987,8 @@ void nilfs_dirty_inode(struct inode *inode, int flags)
 	struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
 
 	if (is_bad_inode(inode)) {
-		nilfs_warning(inode->i_sb, __func__,
-			      "tried to mark bad_inode dirty. ignored.");
+		nilfs_msg(inode->i_sb, KERN_WARNING,
+			  "tried to mark bad_inode dirty. ignored.");
 		dump_stack();
 		return;
 	}
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 358b57e2cdf9..f1d7989459fd 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -25,7 +25,6 @@
 #include <linux/compat.h>	/* compat_ptr() */
 #include <linux/mount.h>	/* mnt_want_write_file(), mnt_drop_write_file() */
 #include <linux/buffer_head.h>
-#include <linux/nilfs2_fs.h>
 #include "nilfs.h"
 #include "segment.h"
 #include "bmap.h"
@@ -584,27 +583,25 @@ static int nilfs_ioctl_move_inode_block(struct inode *inode,
 
 	if (unlikely(ret < 0)) {
 		if (ret == -ENOENT)
-			printk(KERN_CRIT
-			       "%s: invalid virtual block address (%s): "
-			       "ino=%llu, cno=%llu, offset=%llu, "
-			       "blocknr=%llu, vblocknr=%llu\n",
-			       __func__, vdesc->vd_flags ? "node" : "data",
-			       (unsigned long long)vdesc->vd_ino,
-			       (unsigned long long)vdesc->vd_cno,
-			       (unsigned long long)vdesc->vd_offset,
-			       (unsigned long long)vdesc->vd_blocknr,
-			       (unsigned long long)vdesc->vd_vblocknr);
+			nilfs_msg(inode->i_sb, KERN_CRIT,
+				  "%s: invalid virtual block address (%s): ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu",
+				  __func__, vdesc->vd_flags ? "node" : "data",
+				  (unsigned long long)vdesc->vd_ino,
+				  (unsigned long long)vdesc->vd_cno,
+				  (unsigned long long)vdesc->vd_offset,
+				  (unsigned long long)vdesc->vd_blocknr,
+				  (unsigned long long)vdesc->vd_vblocknr);
 		return ret;
 	}
 	if (unlikely(!list_empty(&bh->b_assoc_buffers))) {
-		printk(KERN_CRIT "%s: conflicting %s buffer: ino=%llu, "
-		       "cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu\n",
-		       __func__, vdesc->vd_flags ? "node" : "data",
-		       (unsigned long long)vdesc->vd_ino,
-		       (unsigned long long)vdesc->vd_cno,
-		       (unsigned long long)vdesc->vd_offset,
-		       (unsigned long long)vdesc->vd_blocknr,
-		       (unsigned long long)vdesc->vd_vblocknr);
+		nilfs_msg(inode->i_sb, KERN_CRIT,
+			  "%s: conflicting %s buffer: ino=%llu, cno=%llu, offset=%llu, blocknr=%llu, vblocknr=%llu",
+			  __func__, vdesc->vd_flags ? "node" : "data",
+			  (unsigned long long)vdesc->vd_ino,
+			  (unsigned long long)vdesc->vd_cno,
+			  (unsigned long long)vdesc->vd_offset,
+			  (unsigned long long)vdesc->vd_blocknr,
+			  (unsigned long long)vdesc->vd_vblocknr);
 		brelse(bh);
 		return -EEXIST;
 	}
@@ -854,8 +851,8 @@ int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *nilfs,
 	return 0;
 
  failed:
-	printk(KERN_ERR "NILFS: GC failed during preparation: %s: err=%d\n",
-	       msg, ret);
+	nilfs_msg(nilfs->ns_sb, KERN_ERR, "error %d preparing GC: %s", ret,
+		  msg);
 	return ret;
 }
 
@@ -963,10 +960,11 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
 	}
 
 	ret = nilfs_ioctl_move_blocks(inode->i_sb, &argv[0], kbufs[0]);
-	if (ret < 0)
-		printk(KERN_ERR "NILFS: GC failed during preparation: "
-			"cannot read source blocks: err=%d\n", ret);
-	else {
+	if (ret < 0) {
+		nilfs_msg(inode->i_sb, KERN_ERR,
+			  "error %d preparing GC: cannot read source blocks",
+			  ret);
+	} else {
 		if (nilfs_sb_need_update(nilfs))
 			set_nilfs_discontinued(nilfs);
 		ret = nilfs_clean_segments(inode->i_sb, argv, kbufs);
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 0d7b71fbeff8..d56d3a5bea88 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -207,8 +207,12 @@ static int nilfs_mdt_read_block(struct inode *inode, unsigned long block,
 
  out_no_wait:
 	err = -EIO;
-	if (!buffer_uptodate(first_bh))
+	if (!buffer_uptodate(first_bh)) {
+		nilfs_msg(inode->i_sb, KERN_ERR,
+			  "I/O error reading meta-data file (ino=%lu, block-offset=%lu)",
+			  inode->i_ino, block);
 		goto failed_bh;
+	}
  out:
 	*out_bh = first_bh;
 	return 0;
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 1ec8ae5995a5..dbcf1dc93a51 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -283,9 +283,9 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry)
 		goto out;
 
 	if (!inode->i_nlink) {
-		nilfs_warning(inode->i_sb, __func__,
-			      "deleting nonexistent file (%lu), %d",
-			      inode->i_ino, inode->i_nlink);
+		nilfs_msg(inode->i_sb, KERN_WARNING,
+			  "deleting nonexistent file (ino=%lu), %d",
+			  inode->i_ino, inode->i_nlink);
 		set_nlink(inode, 1);
 	}
 	err = nilfs_delete_entry(de, page);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index b1d48bc0532d..33f8c8fc96e8 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -23,7 +23,8 @@
 #include <linux/buffer_head.h>
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>
-#include <linux/nilfs2_fs.h>
+#include <linux/nilfs2_api.h>
+#include <linux/nilfs2_ondisk.h>
 #include "the_nilfs.h"
 #include "bmap.h"
 
@@ -119,20 +120,19 @@ enum {
 /*
  * Macros to check inode numbers
  */
-#define NILFS_MDT_INO_BITS   \
-	((unsigned int)(1 << NILFS_DAT_INO | 1 << NILFS_CPFILE_INO |	\
-			1 << NILFS_SUFILE_INO | 1 << NILFS_IFILE_INO |	\
-			1 << NILFS_ATIME_INO | 1 << NILFS_SKETCH_INO))
+#define NILFS_MDT_INO_BITS						\
+	(BIT(NILFS_DAT_INO) | BIT(NILFS_CPFILE_INO) |			\
+	 BIT(NILFS_SUFILE_INO) | BIT(NILFS_IFILE_INO) |			\
+	 BIT(NILFS_ATIME_INO) | BIT(NILFS_SKETCH_INO))
 
-#define NILFS_SYS_INO_BITS   \
-	((unsigned int)(1 << NILFS_ROOT_INO) | NILFS_MDT_INO_BITS)
+#define NILFS_SYS_INO_BITS (BIT(NILFS_ROOT_INO) | NILFS_MDT_INO_BITS)
 
 #define NILFS_FIRST_INO(sb) (((struct the_nilfs *)sb->s_fs_info)->ns_first_ino)
 
 #define NILFS_MDT_INODE(sb, ino) \
-	((ino) < NILFS_FIRST_INO(sb) && (NILFS_MDT_INO_BITS & (1 << (ino))))
+	((ino) < NILFS_FIRST_INO(sb) && (NILFS_MDT_INO_BITS & BIT(ino)))
 #define NILFS_VALID_INODE(sb, ino) \
-	((ino) >= NILFS_FIRST_INO(sb) || (NILFS_SYS_INO_BITS & (1 << (ino))))
+	((ino) >= NILFS_FIRST_INO(sb) || (NILFS_SYS_INO_BITS & BIT(ino)))
 
 /**
  * struct nilfs_transaction_info: context information for synchronization
@@ -299,10 +299,36 @@ static inline int nilfs_mark_inode_dirty_sync(struct inode *inode)
 /* super.c */
 extern struct inode *nilfs_alloc_inode(struct super_block *);
 extern void nilfs_destroy_inode(struct inode *);
+
 extern __printf(3, 4)
-void nilfs_error(struct super_block *, const char *, const char *, ...);
+void __nilfs_msg(struct super_block *sb, const char *level,
+		 const char *fmt, ...);
 extern __printf(3, 4)
-void nilfs_warning(struct super_block *, const char *, const char *, ...);
+void __nilfs_error(struct super_block *sb, const char *function,
+		   const char *fmt, ...);
+
+#ifdef CONFIG_PRINTK
+
+#define nilfs_msg(sb, level, fmt, ...)					\
+	__nilfs_msg(sb, level, fmt, ##__VA_ARGS__)
+#define nilfs_error(sb, fmt, ...)					\
+	__nilfs_error(sb, __func__, fmt, ##__VA_ARGS__)
+
+#else
+
+#define nilfs_msg(sb, level, fmt, ...)					\
+	do {								\
+		no_printk(fmt, ##__VA_ARGS__);				\
+		(void)(sb);						\
+	} while (0)
+#define nilfs_error(sb, fmt, ...)					\
+	do {								\
+		no_printk(fmt, ##__VA_ARGS__);				\
+		__nilfs_error(sb, "", " ");				\
+	} while (0)
+
+#endif /* CONFIG_PRINTK */
+
 extern struct nilfs_super_block *
 nilfs_read_super_block(struct super_block *, u64, int, struct buffer_head **);
 extern int nilfs_store_magic_and_option(struct super_block *,
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index d97ba5f11b77..f11a3ad2df0c 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -30,9 +30,9 @@
 #include "mdt.h"
 
 
-#define NILFS_BUFFER_INHERENT_BITS  \
-	((1UL << BH_Uptodate) | (1UL << BH_Mapped) | (1UL << BH_NILFS_Node) | \
-	 (1UL << BH_NILFS_Volatile) | (1UL << BH_NILFS_Checked))
+#define NILFS_BUFFER_INHERENT_BITS					\
+	(BIT(BH_Uptodate) | BIT(BH_Mapped) | BIT(BH_NILFS_Node) |	\
+	 BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Checked))
 
 static struct buffer_head *
 __nilfs_get_page_block(struct page *page, unsigned long block, pgoff_t index,
@@ -85,9 +85,9 @@ void nilfs_forget_buffer(struct buffer_head *bh)
 {
 	struct page *page = bh->b_page;
 	const unsigned long clear_bits =
-		(1 << BH_Uptodate | 1 << BH_Dirty | 1 << BH_Mapped |
-		 1 << BH_Async_Write | 1 << BH_NILFS_Volatile |
-		 1 << BH_NILFS_Checked | 1 << BH_NILFS_Redirected);
+		(BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) |
+		 BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
+		 BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected));
 
 	lock_buffer(bh);
 	set_mask_bits(&bh->b_state, clear_bits, 0);
@@ -124,17 +124,17 @@ void nilfs_copy_buffer(struct buffer_head *dbh, struct buffer_head *sbh)
 	dbh->b_bdev = sbh->b_bdev;
 
 	bh = dbh;
-	bits = sbh->b_state & ((1UL << BH_Uptodate) | (1UL << BH_Mapped));
+	bits = sbh->b_state & (BIT(BH_Uptodate) | BIT(BH_Mapped));
 	while ((bh = bh->b_this_page) != dbh) {
 		lock_buffer(bh);
 		bits &= bh->b_state;
 		unlock_buffer(bh);
 	}
-	if (bits & (1UL << BH_Uptodate))
+	if (bits & BIT(BH_Uptodate))
 		SetPageUptodate(dpage);
 	else
 		ClearPageUptodate(dpage);
-	if (bits & (1UL << BH_Mapped))
+	if (bits & BIT(BH_Mapped))
 		SetPageMappedToDisk(dpage);
 	else
 		ClearPageMappedToDisk(dpage);
@@ -215,7 +215,7 @@ static void nilfs_copy_page(struct page *dst, struct page *src, int copy_dirty)
 		create_empty_buffers(dst, sbh->b_size, 0);
 
 	if (copy_dirty)
-		mask |= (1UL << BH_Dirty);
+		mask |= BIT(BH_Dirty);
 
 	dbh = dbufs = page_buffers(dst);
 	do {
@@ -403,11 +403,10 @@ void nilfs_clear_dirty_page(struct page *page, bool silent)
 
 	BUG_ON(!PageLocked(page));
 
-	if (!silent) {
-		nilfs_warning(sb, __func__,
-				"discard page: offset %lld, ino %lu",
-				page_offset(page), inode->i_ino);
-	}
+	if (!silent)
+		nilfs_msg(sb, KERN_WARNING,
+			  "discard dirty page: offset=%lld, ino=%lu",
+			  page_offset(page), inode->i_ino);
 
 	ClearPageUptodate(page);
 	ClearPageMappedToDisk(page);
@@ -415,18 +414,18 @@ void nilfs_clear_dirty_page(struct page *page, bool silent)
 	if (page_has_buffers(page)) {
 		struct buffer_head *bh, *head;
 		const unsigned long clear_bits =
-			(1 << BH_Uptodate | 1 << BH_Dirty | 1 << BH_Mapped |
-			 1 << BH_Async_Write | 1 << BH_NILFS_Volatile |
-			 1 << BH_NILFS_Checked | 1 << BH_NILFS_Redirected);
+			(BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) |
+			 BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
+			 BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected));
 
 		bh = head = page_buffers(page);
 		do {
 			lock_buffer(bh);
-			if (!silent) {
-				nilfs_warning(sb, __func__,
-					"discard block %llu, size %zu",
-					(u64)bh->b_blocknr, bh->b_size);
-			}
+			if (!silent)
+				nilfs_msg(sb, KERN_WARNING,
+					  "discard dirty block: blocknr=%llu, size=%zu",
+					  (u64)bh->b_blocknr, bh->b_size);
+
 			set_mask_bits(&bh->b_state, clear_bits, 0);
 			unlock_buffer(bh);
 		} while (bh = bh->b_this_page, bh != head);
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index d893dc912b62..5139efed1888 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -54,38 +54,37 @@ struct nilfs_recovery_block {
 };
 
 
-static int nilfs_warn_segment_error(int err)
+static int nilfs_warn_segment_error(struct super_block *sb, int err)
 {
+	const char *msg = NULL;
+
 	switch (err) {
 	case NILFS_SEG_FAIL_IO:
-		printk(KERN_WARNING
-		       "NILFS warning: I/O error on loading last segment\n");
+		nilfs_msg(sb, KERN_ERR, "I/O error reading segment");
 		return -EIO;
 	case NILFS_SEG_FAIL_MAGIC:
-		printk(KERN_WARNING
-		       "NILFS warning: Segment magic number invalid\n");
+		msg = "Magic number mismatch";
 		break;
 	case NILFS_SEG_FAIL_SEQ:
-		printk(KERN_WARNING
-		       "NILFS warning: Sequence number mismatch\n");
+		msg = "Sequence number mismatch";
 		break;
 	case NILFS_SEG_FAIL_CHECKSUM_SUPER_ROOT:
-		printk(KERN_WARNING
-		       "NILFS warning: Checksum error in super root\n");
+		msg = "Checksum error in super root";
 		break;
 	case NILFS_SEG_FAIL_CHECKSUM_FULL:
-		printk(KERN_WARNING
-		       "NILFS warning: Checksum error in segment payload\n");
+		msg = "Checksum error in segment payload";
 		break;
 	case NILFS_SEG_FAIL_CONSISTENCY:
-		printk(KERN_WARNING
-		       "NILFS warning: Inconsistent segment\n");
+		msg = "Inconsistency found";
 		break;
 	case NILFS_SEG_NO_SUPER_ROOT:
-		printk(KERN_WARNING
-		       "NILFS warning: No super root in the last segment\n");
+		msg = "No super root in the last segment";
 		break;
+	default:
+		nilfs_msg(sb, KERN_ERR, "unrecognized segment error %d", err);
+		return -EINVAL;
 	}
+	nilfs_msg(sb, KERN_WARNING, "invalid segment: %s", msg);
 	return -EINVAL;
 }
 
@@ -178,7 +177,7 @@ int nilfs_read_super_root_block(struct the_nilfs *nilfs, sector_t sr_block,
 	brelse(bh_sr);
 
  failed:
-	return nilfs_warn_segment_error(ret);
+	return nilfs_warn_segment_error(nilfs->ns_sb, ret);
 }
 
 /**
@@ -553,11 +552,10 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 		put_page(page);
 
  failed_inode:
-		printk(KERN_WARNING
-		       "NILFS warning: error recovering data block "
-		       "(err=%d, ino=%lu, block-offset=%llu)\n",
-		       err, (unsigned long)rb->ino,
-		       (unsigned long long)rb->blkoff);
+		nilfs_msg(sb, KERN_WARNING,
+			  "error %d recovering data block (ino=%lu, block-offset=%llu)",
+			  err, (unsigned long)rb->ino,
+			  (unsigned long long)rb->blkoff);
 		if (!err2)
 			err2 = err;
  next:
@@ -680,8 +678,8 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
 	}
 
 	if (nsalvaged_blocks) {
-		printk(KERN_INFO "NILFS (device %s): salvaged %lu blocks\n",
-		       sb->s_id, nsalvaged_blocks);
+		nilfs_msg(sb, KERN_INFO, "salvaged %lu blocks",
+			  nsalvaged_blocks);
 		ri->ri_need_recovery = NILFS_RECOVERY_ROLLFORWARD_DONE;
 	}
  out:
@@ -692,10 +690,9 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
  confused:
 	err = -EINVAL;
  failed:
-	printk(KERN_ERR
-	       "NILFS (device %s): Error roll-forwarding "
-	       "(err=%d, pseg block=%llu). ",
-	       sb->s_id, err, (unsigned long long)pseg_start);
+	nilfs_msg(sb, KERN_ERR,
+		  "error %d roll-forwarding partial segment at blocknr = %llu",
+		  err, (unsigned long long)pseg_start);
 	goto out;
 }
 
@@ -715,9 +712,8 @@ static void nilfs_finish_roll_forward(struct the_nilfs *nilfs,
 	set_buffer_dirty(bh);
 	err = sync_dirty_buffer(bh);
 	if (unlikely(err))
-		printk(KERN_WARNING
-		       "NILFS warning: buffer sync write failed during "
-		       "post-cleaning of recovery.\n");
+		nilfs_msg(nilfs->ns_sb, KERN_WARNING,
+			  "buffer sync write failed during post-cleaning of recovery.");
 	brelse(bh);
 }
 
@@ -752,8 +748,8 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
 
 	err = nilfs_attach_checkpoint(sb, ri->ri_cno, true, &root);
 	if (unlikely(err)) {
-		printk(KERN_ERR
-		       "NILFS: error loading the latest checkpoint.\n");
+		nilfs_msg(sb, KERN_ERR,
+			  "error %d loading the latest checkpoint", err);
 		return err;
 	}
 
@@ -764,8 +760,9 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
 	if (ri->ri_need_recovery == NILFS_RECOVERY_ROLLFORWARD_DONE) {
 		err = nilfs_prepare_segment_for_recovery(nilfs, sb, ri);
 		if (unlikely(err)) {
-			printk(KERN_ERR "NILFS: Error preparing segments for "
-			       "recovery.\n");
+			nilfs_msg(sb, KERN_ERR,
+				  "error %d preparing segment for recovery",
+				  err);
 			goto failed;
 		}
 
@@ -778,8 +775,9 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
 		nilfs_detach_log_writer(sb);
 
 		if (unlikely(err)) {
-			printk(KERN_ERR "NILFS: Oops! recovery failed. "
-			       "(err=%d)\n", err);
+			nilfs_msg(sb, KERN_ERR,
+				  "error %d writing segment for recovery",
+				  err);
 			goto failed;
 		}
 
@@ -961,5 +959,5 @@ int nilfs_search_super_root(struct the_nilfs *nilfs,
  failed:
 	brelse(bh_sum);
 	nilfs_dispose_segment_list(&segments);
-	return (ret < 0) ? ret : nilfs_warn_segment_error(ret);
+	return ret < 0 ? ret : nilfs_warn_segment_error(nilfs->ns_sb, ret);
 }
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index a962d7d83447..6f87b2ac1aeb 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -514,7 +514,11 @@ static int nilfs_segbuf_wait(struct nilfs_segment_buffer *segbuf)
 	} while (--segbuf->sb_nbio > 0);
 
 	if (unlikely(atomic_read(&segbuf->sb_err) > 0)) {
-		printk(KERN_ERR "NILFS: IO error writing segment\n");
+		nilfs_msg(segbuf->sb_super, KERN_ERR,
+			  "I/O error writing log (start-blocknr=%llu, block-count=%lu) in segment %llu",
+			  (unsigned long long)segbuf->sb_pseg_start,
+			  segbuf->sb_sum.nblocks,
+			  (unsigned long long)segbuf->sb_segnum);
 		err = -EIO;
 	}
 	return err;
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index e78b68a81aec..bedcae2c28e6 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -150,7 +150,8 @@ static void nilfs_dispose_list(struct the_nilfs *, struct list_head *, int);
 #define nilfs_cnt32_lt(a, b)  nilfs_cnt32_gt(b, a)
 #define nilfs_cnt32_le(a, b)  nilfs_cnt32_ge(b, a)
 
-static int nilfs_prepare_segment_lock(struct nilfs_transaction_info *ti)
+static int nilfs_prepare_segment_lock(struct super_block *sb,
+				      struct nilfs_transaction_info *ti)
 {
 	struct nilfs_transaction_info *cur_ti = current->journal_info;
 	void *save = NULL;
@@ -164,8 +165,7 @@ static int nilfs_prepare_segment_lock(struct nilfs_transaction_info *ti)
 		 * it is saved and will be restored on
 		 * nilfs_transaction_commit().
 		 */
-		printk(KERN_WARNING
-		       "NILFS warning: journal info from a different FS\n");
+		nilfs_msg(sb, KERN_WARNING, "journal info from a different FS");
 		save = current->journal_info;
 	}
 	if (!ti) {
@@ -215,7 +215,7 @@ int nilfs_transaction_begin(struct super_block *sb,
 			    int vacancy_check)
 {
 	struct the_nilfs *nilfs;
-	int ret = nilfs_prepare_segment_lock(ti);
+	int ret = nilfs_prepare_segment_lock(sb, ti);
 	struct nilfs_transaction_info *trace_ti;
 
 	if (unlikely(ret < 0))
@@ -373,7 +373,7 @@ static void nilfs_transaction_lock(struct super_block *sb,
 		nilfs_segctor_do_immediate_flush(sci);
 
 		up_write(&nilfs->ns_segctor_sem);
-		yield();
+		cond_resched();
 	}
 	if (gcflag)
 		ti->ti_flags |= NILFS_TI_GC;
@@ -1858,11 +1858,11 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 		 */
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
-			const unsigned long set_bits = (1 << BH_Uptodate);
+			const unsigned long set_bits = BIT(BH_Uptodate);
 			const unsigned long clear_bits =
-				(1 << BH_Dirty | 1 << BH_Async_Write |
-				 1 << BH_Delay | 1 << BH_NILFS_Volatile |
-				 1 << BH_NILFS_Redirected);
+				(BIT(BH_Dirty) | BIT(BH_Async_Write) |
+				 BIT(BH_Delay) | BIT(BH_NILFS_Volatile) |
+				 BIT(BH_NILFS_Redirected));
 
 			set_mask_bits(&bh->b_state, clear_bits, set_bits);
 			if (bh == segbuf->sb_super_root) {
@@ -1951,8 +1951,9 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci,
 			err = nilfs_ifile_get_inode_block(
 				ifile, ii->vfs_inode.i_ino, &ibh);
 			if (unlikely(err)) {
-				nilfs_warning(sci->sc_super, __func__,
-					      "failed to get inode block.");
+				nilfs_msg(sci->sc_super, KERN_WARNING,
+					  "log writer: error %d getting inode block (ino=%lu)",
+					  err, ii->vfs_inode.i_ino);
 				return err;
 			}
 			mark_buffer_dirty(ibh);
@@ -2131,10 +2132,10 @@ static void nilfs_segctor_start_timer(struct nilfs_sc_info *sci)
 static void nilfs_segctor_do_flush(struct nilfs_sc_info *sci, int bn)
 {
 	spin_lock(&sci->sc_state_lock);
-	if (!(sci->sc_flush_request & (1 << bn))) {
+	if (!(sci->sc_flush_request & BIT(bn))) {
 		unsigned long prev_req = sci->sc_flush_request;
 
-		sci->sc_flush_request |= (1 << bn);
+		sci->sc_flush_request |= BIT(bn);
 		if (!prev_req)
 			wake_up(&sci->sc_wait_daemon);
 	}
@@ -2318,7 +2319,7 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
 }
 
 #define FLUSH_FILE_BIT	(0x1) /* data file only */
-#define FLUSH_DAT_BIT	(1 << NILFS_DAT_INO) /* DAT only */
+#define FLUSH_DAT_BIT	BIT(NILFS_DAT_INO) /* DAT only */
 
 /**
  * nilfs_segctor_accept - record accepted sequence count of log-write requests
@@ -2458,8 +2459,7 @@ int nilfs_clean_segments(struct super_block *sb, struct nilfs_argv *argv,
 		if (likely(!err))
 			break;
 
-		nilfs_warning(sb, __func__,
-			      "segment construction failed. (err=%d)", err);
+		nilfs_msg(sb, KERN_WARNING, "error %d cleaning segments", err);
 		set_current_state(TASK_INTERRUPTIBLE);
 		schedule_timeout(sci->sc_interval);
 	}
@@ -2467,9 +2467,9 @@ int nilfs_clean_segments(struct super_block *sb, struct nilfs_argv *argv,
 		int ret = nilfs_discard_segments(nilfs, sci->sc_freesegs,
 						 sci->sc_nfreesegs);
 		if (ret) {
-			printk(KERN_WARNING
-			       "NILFS warning: error %d on discard request, "
-			       "turning discards off for the device\n", ret);
+			nilfs_msg(sb, KERN_WARNING,
+				  "error %d on discard request, turning discards off for the device",
+				  ret);
 			nilfs_clear_opt(nilfs, DISCARD);
 		}
 	}
@@ -2551,10 +2551,9 @@ static int nilfs_segctor_thread(void *arg)
 	/* start sync. */
 	sci->sc_task = current;
 	wake_up(&sci->sc_wait_task); /* for nilfs_segctor_start_thread() */
-	printk(KERN_INFO
-	       "segctord starting. Construction interval = %lu seconds, "
-	       "CP frequency < %lu seconds\n",
-	       sci->sc_interval / HZ, sci->sc_mjcp_freq / HZ);
+	nilfs_msg(sci->sc_super, KERN_INFO,
+		  "segctord starting. Construction interval = %lu seconds, CP frequency < %lu seconds",
+		  sci->sc_interval / HZ, sci->sc_mjcp_freq / HZ);
 
 	spin_lock(&sci->sc_state_lock);
  loop:
@@ -2628,8 +2627,8 @@ static int nilfs_segctor_start_thread(struct nilfs_sc_info *sci)
 	if (IS_ERR(t)) {
 		int err = PTR_ERR(t);
 
-		printk(KERN_ERR "NILFS: error %d creating segctord thread\n",
-		       err);
+		nilfs_msg(sci->sc_super, KERN_ERR,
+			  "error %d creating segctord thread", err);
 		return err;
 	}
 	wait_event(sci->sc_wait_task, sci->sc_task != NULL);
@@ -2739,14 +2738,14 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
 		nilfs_segctor_write_out(sci);
 
 	if (!list_empty(&sci->sc_dirty_files)) {
-		nilfs_warning(sci->sc_super, __func__,
-			      "dirty file(s) after the final construction");
+		nilfs_msg(sci->sc_super, KERN_WARNING,
+			  "disposed unprocessed dirty file(s) when stopping log writer");
 		nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
 	}
 
 	if (!list_empty(&sci->sc_iput_queue)) {
-		nilfs_warning(sci->sc_super, __func__,
-			      "iput queue is not empty");
+		nilfs_msg(sci->sc_super, KERN_WARNING,
+			  "disposed unprocessed inode(s) in iput queue when stopping log writer");
 		nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1);
 	}
 
@@ -2822,8 +2821,8 @@ void nilfs_detach_log_writer(struct super_block *sb)
 	spin_lock(&nilfs->ns_inode_lock);
 	if (!list_empty(&nilfs->ns_dirty_files)) {
 		list_splice_init(&nilfs->ns_dirty_files, &garbage_list);
-		nilfs_warning(sb, __func__,
-			      "Hit dirty file after stopped log writer");
+		nilfs_msg(sb, KERN_WARNING,
+			  "disposed unprocessed dirty file(s) when detaching log writer");
 	}
 	spin_unlock(&nilfs->ns_inode_lock);
 	up_write(&nilfs->ns_segctor_sem);
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index 6565c10b7b76..1060949d7dd2 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -23,7 +23,6 @@
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
 #include <linux/workqueue.h>
-#include <linux/nilfs2_fs.h>
 #include "nilfs.h"
 
 struct nilfs_root;
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 1963595a1580..1541a1e9221a 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -22,7 +22,6 @@
 #include <linux/string.h>
 #include <linux/buffer_head.h>
 #include <linux/errno.h>
-#include <linux/nilfs2_fs.h>
 #include "mdt.h"
 #include "sufile.h"
 
@@ -181,9 +180,9 @@ int nilfs_sufile_updatev(struct inode *sufile, __u64 *segnumv, size_t nsegs,
 	down_write(&NILFS_MDT(sufile)->mi_sem);
 	for (seg = segnumv; seg < segnumv + nsegs; seg++) {
 		if (unlikely(*seg >= nilfs_sufile_get_nsegments(sufile))) {
-			printk(KERN_WARNING
-			       "%s: invalid segment number: %llu\n", __func__,
-			       (unsigned long long)*seg);
+			nilfs_msg(sufile->i_sb, KERN_WARNING,
+				  "%s: invalid segment number: %llu",
+				  __func__, (unsigned long long)*seg);
 			nerr++;
 		}
 	}
@@ -240,8 +239,9 @@ int nilfs_sufile_update(struct inode *sufile, __u64 segnum, int create,
 	int ret;
 
 	if (unlikely(segnum >= nilfs_sufile_get_nsegments(sufile))) {
-		printk(KERN_WARNING "%s: invalid segment number: %llu\n",
-		       __func__, (unsigned long long)segnum);
+		nilfs_msg(sufile->i_sb, KERN_WARNING,
+			  "%s: invalid segment number: %llu",
+			  __func__, (unsigned long long)segnum);
 		return -EINVAL;
 	}
 	down_write(&NILFS_MDT(sufile)->mi_sem);
@@ -419,8 +419,9 @@ void nilfs_sufile_do_cancel_free(struct inode *sufile, __u64 segnum,
 	kaddr = kmap_atomic(su_bh->b_page);
 	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
 	if (unlikely(!nilfs_segment_usage_clean(su))) {
-		printk(KERN_WARNING "%s: segment %llu must be clean\n",
-		       __func__, (unsigned long long)segnum);
+		nilfs_msg(sufile->i_sb, KERN_WARNING,
+			  "%s: segment %llu must be clean", __func__,
+			  (unsigned long long)segnum);
 		kunmap_atomic(kaddr);
 		return;
 	}
@@ -444,7 +445,7 @@ void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum,
 
 	kaddr = kmap_atomic(su_bh->b_page);
 	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
-	if (su->su_flags == cpu_to_le32(1UL << NILFS_SEGMENT_USAGE_DIRTY) &&
+	if (su->su_flags == cpu_to_le32(BIT(NILFS_SEGMENT_USAGE_DIRTY)) &&
 	    su->su_nblocks == cpu_to_le32(0)) {
 		kunmap_atomic(kaddr);
 		return;
@@ -455,7 +456,7 @@ void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum,
 	/* make the segment garbage */
 	su->su_lastmod = cpu_to_le64(0);
 	su->su_nblocks = cpu_to_le32(0);
-	su->su_flags = cpu_to_le32(1UL << NILFS_SEGMENT_USAGE_DIRTY);
+	su->su_flags = cpu_to_le32(BIT(NILFS_SEGMENT_USAGE_DIRTY));
 	kunmap_atomic(kaddr);
 
 	nilfs_sufile_mod_counter(header_bh, clean ? (u64)-1 : 0, dirty ? 0 : 1);
@@ -476,8 +477,9 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
 	kaddr = kmap_atomic(su_bh->b_page);
 	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
 	if (nilfs_segment_usage_clean(su)) {
-		printk(KERN_WARNING "%s: segment %llu is already clean\n",
-		       __func__, (unsigned long long)segnum);
+		nilfs_msg(sufile->i_sb, KERN_WARNING,
+			  "%s: segment %llu is already clean",
+			  __func__, (unsigned long long)segnum);
 		kunmap_atomic(kaddr);
 		return;
 	}
@@ -692,7 +694,7 @@ static int nilfs_sufile_truncate_range(struct inode *sufile,
 		su2 = su;
 		for (j = 0; j < n; j++, su = (void *)su + susz) {
 			if ((le32_to_cpu(su->su_flags) &
-			     ~(1UL << NILFS_SEGMENT_USAGE_ERROR)) ||
+			     ~BIT(NILFS_SEGMENT_USAGE_ERROR)) ||
 			    nilfs_segment_is_active(nilfs, segnum + j)) {
 				ret = -EBUSY;
 				kunmap_atomic(kaddr);
@@ -859,10 +861,10 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
 			si->sui_lastmod = le64_to_cpu(su->su_lastmod);
 			si->sui_nblocks = le32_to_cpu(su->su_nblocks);
 			si->sui_flags = le32_to_cpu(su->su_flags) &
-				~(1UL << NILFS_SEGMENT_USAGE_ACTIVE);
+				~BIT(NILFS_SEGMENT_USAGE_ACTIVE);
 			if (nilfs_segment_is_active(nilfs, segnum + j))
 				si->sui_flags |=
-					(1UL << NILFS_SEGMENT_USAGE_ACTIVE);
+					BIT(NILFS_SEGMENT_USAGE_ACTIVE);
 		}
 		kunmap_atomic(kaddr);
 		brelse(su_bh);
@@ -950,7 +952,7 @@ ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
 			 * disk.
 			 */
 			sup->sup_sui.sui_flags &=
-					~(1UL << NILFS_SEGMENT_USAGE_ACTIVE);
+					~BIT(NILFS_SEGMENT_USAGE_ACTIVE);
 
 			cleansi = nilfs_suinfo_clean(&sup->sup_sui);
 			cleansu = nilfs_segment_usage_clean(su);
@@ -1175,14 +1177,12 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize,
 	int err;
 
 	if (susize > sb->s_blocksize) {
-		printk(KERN_ERR
-		       "NILFS: too large segment usage size: %zu bytes.\n",
-		       susize);
+		nilfs_msg(sb, KERN_ERR,
+			  "too large segment usage size: %zu bytes", susize);
 		return -EINVAL;
 	} else if (susize < NILFS_MIN_SEGMENT_USAGE_SIZE) {
-		printk(KERN_ERR
-		       "NILFS: too small segment usage size: %zu bytes.\n",
-		       susize);
+		nilfs_msg(sb, KERN_ERR,
+			  "too small segment usage size: %zu bytes", susize);
 		return -EINVAL;
 	}
 
diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h
index 46e89872294c..158a9190c8ec 100644
--- a/fs/nilfs2/sufile.h
+++ b/fs/nilfs2/sufile.h
@@ -21,7 +21,6 @@
 
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
-#include <linux/nilfs2_fs.h>
 #include "mdt.h"
 
 
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 666107a18a22..c95d369e90aa 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -71,6 +71,22 @@ struct kmem_cache *nilfs_btree_path_cache;
 static int nilfs_setup_super(struct super_block *sb, int is_mount);
 static int nilfs_remount(struct super_block *sb, int *flags, char *data);
 
+void __nilfs_msg(struct super_block *sb, const char *level, const char *fmt,
+		 ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	if (sb)
+		printk("%sNILFS (%s): %pV\n", level, sb->s_id, &vaf);
+	else
+		printk("%sNILFS: %pV\n", level, &vaf);
+	va_end(args);
+}
+
 static void nilfs_set_error(struct super_block *sb)
 {
 	struct the_nilfs *nilfs = sb->s_fs_info;
@@ -91,19 +107,20 @@ static void nilfs_set_error(struct super_block *sb)
 }
 
 /**
- * nilfs_error() - report failure condition on a filesystem
+ * __nilfs_error() - report failure condition on a filesystem
+ *
+ * __nilfs_error() sets an ERROR_FS flag on the superblock as well as
+ * reporting an error message.  This function should be called when
+ * NILFS detects incoherences or defects of meta data on disk.
  *
- * nilfs_error() sets an ERROR_FS flag on the superblock as well as
- * reporting an error message.  It should be called when NILFS detects
- * incoherences or defects of meta data on disk.  As for sustainable
- * errors such as a single-shot I/O error, nilfs_warning() or the printk()
- * function should be used instead.
+ * This implements the body of nilfs_error() macro.  Normally,
+ * nilfs_error() should be used.  As for sustainable errors such as a
+ * single-shot I/O error, nilfs_msg() should be used instead.
  *
- * The segment constructor must not call this function because it can
- * kill itself.
+ * Callers should not add a trailing newline since this will do it.
  */
-void nilfs_error(struct super_block *sb, const char *function,
-		 const char *fmt, ...)
+void __nilfs_error(struct super_block *sb, const char *function,
+		   const char *fmt, ...)
 {
 	struct the_nilfs *nilfs = sb->s_fs_info;
 	struct va_format vaf;
@@ -133,24 +150,6 @@ void nilfs_error(struct super_block *sb, const char *function,
 		      sb->s_id);
 }
 
-void nilfs_warning(struct super_block *sb, const char *function,
-		   const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	printk(KERN_WARNING "NILFS warning (device %s): %s: %pV\n",
-	       sb->s_id, function, &vaf);
-
-	va_end(args);
-}
-
-
 struct inode *nilfs_alloc_inode(struct super_block *sb)
 {
 	struct nilfs_inode_info *ii;
@@ -196,8 +195,8 @@ static int nilfs_sync_super(struct super_block *sb, int flag)
 	}
 
 	if (unlikely(err)) {
-		printk(KERN_ERR
-		       "NILFS: unable to write superblock (err=%d)\n", err);
+		nilfs_msg(sb, KERN_ERR, "unable to write superblock: err=%d",
+			  err);
 		if (err == -EIO && nilfs->ns_sbh[1]) {
 			/*
 			 * sbp[0] points to newer log than sbp[1],
@@ -267,8 +266,7 @@ struct nilfs_super_block **nilfs_prepare_super(struct super_block *sb,
 		    sbp[1]->s_magic == cpu_to_le16(NILFS_SUPER_MAGIC)) {
 			memcpy(sbp[0], sbp[1], nilfs->ns_sbsize);
 		} else {
-			printk(KERN_CRIT "NILFS: superblock broke on dev %s\n",
-			       sb->s_id);
+			nilfs_msg(sb, KERN_CRIT, "superblock broke");
 			return NULL;
 		}
 	} else if (sbp[1] &&
@@ -378,9 +376,9 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off)
 	offset = sb2off & (nilfs->ns_blocksize - 1);
 	nsbh = sb_getblk(sb, newblocknr);
 	if (!nsbh) {
-		printk(KERN_WARNING
-		       "NILFS warning: unable to move secondary superblock "
-		       "to block %llu\n", (unsigned long long)newblocknr);
+		nilfs_msg(sb, KERN_WARNING,
+			  "unable to move secondary superblock to block %llu",
+			  (unsigned long long)newblocknr);
 		ret = -EIO;
 		goto out;
 	}
@@ -543,10 +541,9 @@ int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt,
 	up_read(&nilfs->ns_segctor_sem);
 	if (unlikely(err)) {
 		if (err == -ENOENT || err == -EINVAL) {
-			printk(KERN_ERR
-			       "NILFS: Invalid checkpoint "
-			       "(checkpoint number=%llu)\n",
-			       (unsigned long long)cno);
+			nilfs_msg(sb, KERN_ERR,
+				  "Invalid checkpoint (checkpoint number=%llu)",
+				  (unsigned long long)cno);
 			err = -EINVAL;
 		}
 		goto failed;
@@ -642,9 +639,8 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	err = nilfs_ifile_count_free_inodes(root->ifile,
 					    &nmaxinodes, &nfreeinodes);
 	if (unlikely(err)) {
-		printk(KERN_WARNING
-			"NILFS warning: fail to count free inodes: err %d.\n",
-			err);
+		nilfs_msg(sb, KERN_WARNING,
+			  "failed to count free inodes: err=%d", err);
 		if (err == -ERANGE) {
 			/*
 			 * If nilfs_palloc_count_max_entries() returns
@@ -776,9 +772,9 @@ static int parse_options(char *options, struct super_block *sb, int is_remount)
 			break;
 		case Opt_snapshot:
 			if (is_remount) {
-				printk(KERN_ERR
-				       "NILFS: \"%s\" option is invalid "
-				       "for remount.\n", p);
+				nilfs_msg(sb, KERN_ERR,
+					  "\"%s\" option is invalid for remount",
+					  p);
 				return 0;
 			}
 			break;
@@ -792,8 +788,8 @@ static int parse_options(char *options, struct super_block *sb, int is_remount)
 			nilfs_clear_opt(nilfs, DISCARD);
 			break;
 		default:
-			printk(KERN_ERR
-			       "NILFS: Unrecognized mount option \"%s\"\n", p);
+			nilfs_msg(sb, KERN_ERR,
+				  "unrecognized mount option \"%s\"", p);
 			return 0;
 		}
 	}
@@ -829,12 +825,10 @@ static int nilfs_setup_super(struct super_block *sb, int is_mount)
 	mnt_count = le16_to_cpu(sbp[0]->s_mnt_count);
 
 	if (nilfs->ns_mount_state & NILFS_ERROR_FS) {
-		printk(KERN_WARNING
-		       "NILFS warning: mounting fs with errors\n");
+		nilfs_msg(sb, KERN_WARNING, "mounting fs with errors");
 #if 0
 	} else if (max_mnt_count >= 0 && mnt_count >= max_mnt_count) {
-		printk(KERN_WARNING
-		       "NILFS warning: maximal mount count reached\n");
+		nilfs_msg(sb, KERN_WARNING, "maximal mount count reached");
 #endif
 	}
 	if (!max_mnt_count)
@@ -897,17 +891,17 @@ int nilfs_check_feature_compatibility(struct super_block *sb,
 	features = le64_to_cpu(sbp->s_feature_incompat) &
 		~NILFS_FEATURE_INCOMPAT_SUPP;
 	if (features) {
-		printk(KERN_ERR "NILFS: couldn't mount because of unsupported "
-		       "optional features (%llx)\n",
-		       (unsigned long long)features);
+		nilfs_msg(sb, KERN_ERR,
+			  "couldn't mount because of unsupported optional features (%llx)",
+			  (unsigned long long)features);
 		return -EINVAL;
 	}
 	features = le64_to_cpu(sbp->s_feature_compat_ro) &
 		~NILFS_FEATURE_COMPAT_RO_SUPP;
 	if (!(sb->s_flags & MS_RDONLY) && features) {
-		printk(KERN_ERR "NILFS: couldn't mount RDWR because of "
-		       "unsupported optional features (%llx)\n",
-		       (unsigned long long)features);
+		nilfs_msg(sb, KERN_ERR,
+			  "couldn't mount RDWR because of unsupported optional features (%llx)",
+			  (unsigned long long)features);
 		return -EINVAL;
 	}
 	return 0;
@@ -923,13 +917,13 @@ static int nilfs_get_root_dentry(struct super_block *sb,
 
 	inode = nilfs_iget(sb, root, NILFS_ROOT_INO);
 	if (IS_ERR(inode)) {
-		printk(KERN_ERR "NILFS: get root inode failed\n");
 		ret = PTR_ERR(inode);
+		nilfs_msg(sb, KERN_ERR, "error %d getting root inode", ret);
 		goto out;
 	}
 	if (!S_ISDIR(inode->i_mode) || !inode->i_blocks || !inode->i_size) {
 		iput(inode);
-		printk(KERN_ERR "NILFS: corrupt root inode.\n");
+		nilfs_msg(sb, KERN_ERR, "corrupt root inode");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -957,7 +951,7 @@ static int nilfs_get_root_dentry(struct super_block *sb,
 	return ret;
 
  failed_dentry:
-	printk(KERN_ERR "NILFS: get root dentry failed\n");
+	nilfs_msg(sb, KERN_ERR, "error %d getting root dentry", ret);
 	goto out;
 }
 
@@ -977,18 +971,18 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 		ret = (ret == -ENOENT) ? -EINVAL : ret;
 		goto out;
 	} else if (!ret) {
-		printk(KERN_ERR "NILFS: The specified checkpoint is "
-		       "not a snapshot (checkpoint number=%llu).\n",
-		       (unsigned long long)cno);
+		nilfs_msg(s, KERN_ERR,
+			  "The specified checkpoint is not a snapshot (checkpoint number=%llu)",
+			  (unsigned long long)cno);
 		ret = -EINVAL;
 		goto out;
 	}
 
 	ret = nilfs_attach_checkpoint(s, cno, false, &root);
 	if (ret) {
-		printk(KERN_ERR "NILFS: error loading snapshot "
-		       "(checkpoint number=%llu).\n",
-	       (unsigned long long)cno);
+		nilfs_msg(s, KERN_ERR,
+			  "error %d while loading snapshot (checkpoint number=%llu)",
+			  ret, (unsigned long long)cno);
 		goto out;
 	}
 	ret = nilfs_get_root_dentry(s, root, root_dentry);
@@ -1058,7 +1052,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	__u64 cno;
 	int err;
 
-	nilfs = alloc_nilfs(sb->s_bdev);
+	nilfs = alloc_nilfs(sb);
 	if (!nilfs)
 		return -ENOMEM;
 
@@ -1083,8 +1077,9 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	cno = nilfs_last_cno(nilfs);
 	err = nilfs_attach_checkpoint(sb, cno, true, &fsroot);
 	if (err) {
-		printk(KERN_ERR "NILFS: error loading last checkpoint "
-		       "(checkpoint number=%llu).\n", (unsigned long long)cno);
+		nilfs_msg(sb, KERN_ERR,
+			  "error %d while loading last checkpoint (checkpoint number=%llu)",
+			  err, (unsigned long long)cno);
 		goto failed_unload;
 	}
 
@@ -1144,9 +1139,8 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 	err = -EINVAL;
 
 	if (!nilfs_valid_fs(nilfs)) {
-		printk(KERN_WARNING "NILFS (device %s): couldn't "
-		       "remount because the filesystem is in an "
-		       "incomplete recovery state.\n", sb->s_id);
+		nilfs_msg(sb, KERN_WARNING,
+			  "couldn't remount because the filesystem is in an incomplete recovery state");
 		goto restore_opts;
 	}
 
@@ -1178,10 +1172,9 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 			~NILFS_FEATURE_COMPAT_RO_SUPP;
 		up_read(&nilfs->ns_sem);
 		if (features) {
-			printk(KERN_WARNING "NILFS (device %s): couldn't "
-			       "remount RDWR because of unsupported optional "
-			       "features (%llx)\n",
-			       sb->s_id, (unsigned long long)features);
+			nilfs_msg(sb, KERN_WARNING,
+				  "couldn't remount RDWR because of unsupported optional features (%llx)",
+				  (unsigned long long)features);
 			err = -EROFS;
 			goto restore_opts;
 		}
@@ -1212,6 +1205,38 @@ struct nilfs_super_data {
 	int flags;
 };
 
+static int nilfs_parse_snapshot_option(const char *option,
+				       const substring_t *arg,
+				       struct nilfs_super_data *sd)
+{
+	unsigned long long val;
+	const char *msg = NULL;
+	int err;
+
+	if (!(sd->flags & MS_RDONLY)) {
+		msg = "read-only option is not specified";
+		goto parse_error;
+	}
+
+	err = kstrtoull(arg->from, 0, &val);
+	if (err) {
+		if (err == -ERANGE)
+			msg = "too large checkpoint number";
+		else
+			msg = "malformed argument";
+		goto parse_error;
+	} else if (val == 0) {
+		msg = "invalid checkpoint number 0";
+		goto parse_error;
+	}
+	sd->cno = val;
+	return 0;
+
+parse_error:
+	nilfs_msg(NULL, KERN_ERR, "invalid option \"%s\": %s", option, msg);
+	return 1;
+}
+
 /**
  * nilfs_identify - pre-read mount options needed to identify mount instance
  * @data: mount options
@@ -1228,24 +1253,9 @@ static int nilfs_identify(char *data, struct nilfs_super_data *sd)
 		p = strsep(&options, ",");
 		if (p != NULL && *p) {
 			token = match_token(p, tokens, args);
-			if (token == Opt_snapshot) {
-				if (!(sd->flags & MS_RDONLY)) {
-					ret++;
-				} else {
-					sd->cno = simple_strtoull(args[0].from,
-								  NULL, 0);
-					/*
-					 * No need to see the end pointer;
-					 * match_token() has done syntax
-					 * checking.
-					 */
-					if (sd->cno == 0)
-						ret++;
-				}
-			}
-			if (ret)
-				printk(KERN_ERR
-				       "NILFS: invalid mount option: %s\n", p);
+			if (token == Opt_snapshot)
+				ret = nilfs_parse_snapshot_option(p, &args[0],
+								  sd);
 		}
 		if (!options)
 			break;
@@ -1326,10 +1336,10 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 	} else if (!sd.cno) {
 		if (nilfs_tree_is_busy(s->s_root)) {
 			if ((flags ^ s->s_flags) & MS_RDONLY) {
-				printk(KERN_ERR "NILFS: the device already "
-				       "has a %s mount.\n",
-				       (s->s_flags & MS_RDONLY) ?
-				       "read-only" : "read/write");
+				nilfs_msg(s, KERN_ERR,
+					  "the device already has a %s mount.",
+					  (s->s_flags & MS_RDONLY) ?
+					  "read-only" : "read/write");
 				err = -EBUSY;
 				goto failed_super;
 			}
diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c
index 8ffa42b704d8..490303e3d517 100644
--- a/fs/nilfs2/sysfs.c
+++ b/fs/nilfs2/sysfs.c
@@ -272,8 +272,8 @@ nilfs_checkpoints_checkpoints_number_show(struct nilfs_checkpoints_attr *attr,
 	err = nilfs_cpfile_get_stat(nilfs->ns_cpfile, &cpstat);
 	up_read(&nilfs->ns_segctor_sem);
 	if (err < 0) {
-		printk(KERN_ERR "NILFS: unable to get checkpoint stat: err=%d\n",
-			err);
+		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+			  "unable to get checkpoint stat: err=%d", err);
 		return err;
 	}
 
@@ -295,8 +295,8 @@ nilfs_checkpoints_snapshots_number_show(struct nilfs_checkpoints_attr *attr,
 	err = nilfs_cpfile_get_stat(nilfs->ns_cpfile, &cpstat);
 	up_read(&nilfs->ns_segctor_sem);
 	if (err < 0) {
-		printk(KERN_ERR "NILFS: unable to get checkpoint stat: err=%d\n",
-			err);
+		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+			  "unable to get checkpoint stat: err=%d", err);
 		return err;
 	}
 
@@ -326,9 +326,9 @@ nilfs_checkpoints_next_checkpoint_show(struct nilfs_checkpoints_attr *attr,
 {
 	__u64 cno;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	cno = nilfs->ns_cno;
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", cno);
 }
@@ -414,8 +414,8 @@ nilfs_segments_dirty_segments_show(struct nilfs_segments_attr *attr,
 	err = nilfs_sufile_get_stat(nilfs->ns_sufile, &sustat);
 	up_read(&nilfs->ns_segctor_sem);
 	if (err < 0) {
-		printk(KERN_ERR "NILFS: unable to get segment stat: err=%d\n",
-			err);
+		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+			  "unable to get segment stat: err=%d", err);
 		return err;
 	}
 
@@ -511,9 +511,9 @@ nilfs_segctor_current_seg_sequence_show(struct nilfs_segctor_attr *attr,
 {
 	u64 seg_seq;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	seg_seq = nilfs->ns_seg_seq;
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", seg_seq);
 }
@@ -525,9 +525,9 @@ nilfs_segctor_current_last_full_seg_show(struct nilfs_segctor_attr *attr,
 {
 	__u64 segnum;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	segnum = nilfs->ns_segnum;
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", segnum);
 }
@@ -539,9 +539,9 @@ nilfs_segctor_next_full_seg_show(struct nilfs_segctor_attr *attr,
 {
 	__u64 nextnum;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	nextnum = nilfs->ns_nextnum;
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", nextnum);
 }
@@ -553,9 +553,9 @@ nilfs_segctor_next_pseg_offset_show(struct nilfs_segctor_attr *attr,
 {
 	unsigned long pseg_offset;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	pseg_offset = nilfs->ns_pseg_offset;
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return snprintf(buf, PAGE_SIZE, "%lu\n", pseg_offset);
 }
@@ -567,9 +567,9 @@ nilfs_segctor_next_checkpoint_show(struct nilfs_segctor_attr *attr,
 {
 	__u64 cno;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	cno = nilfs->ns_cno;
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", cno);
 }
@@ -581,9 +581,9 @@ nilfs_segctor_last_seg_write_time_show(struct nilfs_segctor_attr *attr,
 {
 	time_t ctime;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	ctime = nilfs->ns_ctime;
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return NILFS_SHOW_TIME(ctime, buf);
 }
@@ -595,9 +595,9 @@ nilfs_segctor_last_seg_write_time_secs_show(struct nilfs_segctor_attr *attr,
 {
 	time_t ctime;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	ctime = nilfs->ns_ctime;
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long)ctime);
 }
@@ -609,9 +609,9 @@ nilfs_segctor_last_nongc_write_time_show(struct nilfs_segctor_attr *attr,
 {
 	time_t nongc_ctime;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	nongc_ctime = nilfs->ns_nongc_ctime;
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return NILFS_SHOW_TIME(nongc_ctime, buf);
 }
@@ -623,9 +623,9 @@ nilfs_segctor_last_nongc_write_time_secs_show(struct nilfs_segctor_attr *attr,
 {
 	time_t nongc_ctime;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	nongc_ctime = nilfs->ns_nongc_ctime;
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			(unsigned long long)nongc_ctime);
@@ -638,9 +638,9 @@ nilfs_segctor_dirty_data_blocks_count_show(struct nilfs_segctor_attr *attr,
 {
 	u32 ndirtyblks;
 
-	down_read(&nilfs->ns_sem);
+	down_read(&nilfs->ns_segctor_sem);
 	ndirtyblks = atomic_read(&nilfs->ns_ndirtyblks);
-	up_read(&nilfs->ns_sem);
+	up_read(&nilfs->ns_segctor_sem);
 
 	return snprintf(buf, PAGE_SIZE, "%u\n", ndirtyblks);
 }
@@ -789,14 +789,15 @@ nilfs_superblock_sb_update_frequency_store(struct nilfs_superblock_attr *attr,
 
 	err = kstrtouint(skip_spaces(buf), 0, &val);
 	if (err) {
-		printk(KERN_ERR "NILFS: unable to convert string: err=%d\n",
-			err);
+		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+			  "unable to convert string: err=%d", err);
 		return err;
 	}
 
 	if (val < NILFS_SB_FREQ) {
 		val = NILFS_SB_FREQ;
-		printk(KERN_WARNING "NILFS: superblock update frequency cannot be lesser than 10 seconds\n");
+		nilfs_msg(nilfs->ns_sb, KERN_WARNING,
+			  "superblock update frequency cannot be lesser than 10 seconds");
 	}
 
 	down_write(&nilfs->ns_sem);
@@ -999,7 +1000,8 @@ int nilfs_sysfs_create_device_group(struct super_block *sb)
 	nilfs->ns_dev_subgroups = kzalloc(devgrp_size, GFP_KERNEL);
 	if (unlikely(!nilfs->ns_dev_subgroups)) {
 		err = -ENOMEM;
-		printk(KERN_ERR "NILFS: unable to allocate memory for device group\n");
+		nilfs_msg(sb, KERN_ERR,
+			  "unable to allocate memory for device group");
 		goto failed_create_device_group;
 	}
 
@@ -1109,15 +1111,15 @@ int __init nilfs_sysfs_init(void)
 	nilfs_kset = kset_create_and_add(NILFS_ROOT_GROUP_NAME, NULL, fs_kobj);
 	if (!nilfs_kset) {
 		err = -ENOMEM;
-		printk(KERN_ERR "NILFS: unable to create sysfs entry: err %d\n",
-			err);
+		nilfs_msg(NULL, KERN_ERR,
+			  "unable to create sysfs entry: err=%d", err);
 		goto failed_sysfs_init;
 	}
 
 	err = sysfs_create_group(&nilfs_kset->kobj, &nilfs_feature_attr_group);
 	if (unlikely(err)) {
-		printk(KERN_ERR "NILFS: unable to create feature group: err %d\n",
-			err);
+		nilfs_msg(NULL, KERN_ERR,
+			  "unable to create feature group: err=%d", err);
 		goto cleanup_sysfs_init;
 	}
 
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index e9fd241b9a0a..2dd75bf619ad 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -56,12 +56,12 @@ void nilfs_set_last_segment(struct the_nilfs *nilfs,
 
 /**
  * alloc_nilfs - allocate a nilfs object
- * @bdev: block device to which the_nilfs is related
+ * @sb: super block instance
  *
  * Return Value: On success, pointer to the_nilfs is returned.
  * On error, NULL is returned.
  */
-struct the_nilfs *alloc_nilfs(struct block_device *bdev)
+struct the_nilfs *alloc_nilfs(struct super_block *sb)
 {
 	struct the_nilfs *nilfs;
 
@@ -69,7 +69,8 @@ struct the_nilfs *alloc_nilfs(struct block_device *bdev)
 	if (!nilfs)
 		return NULL;
 
-	nilfs->ns_bdev = bdev;
+	nilfs->ns_sb = sb;
+	nilfs->ns_bdev = sb->s_bdev;
 	atomic_set(&nilfs->ns_ndirtyblks, 0);
 	init_rwsem(&nilfs->ns_sem);
 	mutex_init(&nilfs->ns_snapshot_mount_mutex);
@@ -191,7 +192,10 @@ static int nilfs_store_log_cursor(struct the_nilfs *nilfs,
 		nilfs_get_segnum_of_block(nilfs, nilfs->ns_last_pseg);
 	nilfs->ns_cno = nilfs->ns_last_cno + 1;
 	if (nilfs->ns_segnum >= nilfs->ns_nsegments) {
-		printk(KERN_ERR "NILFS invalid last segment number.\n");
+		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+			  "pointed segment number is out of range: segnum=%llu, nsegments=%lu",
+			  (unsigned long long)nilfs->ns_segnum,
+			  nilfs->ns_nsegments);
 		ret = -EINVAL;
 	}
 	return ret;
@@ -215,12 +219,12 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	int err;
 
 	if (!valid_fs) {
-		printk(KERN_WARNING "NILFS warning: mounting unchecked fs\n");
+		nilfs_msg(sb, KERN_WARNING, "mounting unchecked fs");
 		if (s_flags & MS_RDONLY) {
-			printk(KERN_INFO "NILFS: INFO: recovery "
-			       "required for readonly filesystem.\n");
-			printk(KERN_INFO "NILFS: write access will "
-			       "be enabled during recovery.\n");
+			nilfs_msg(sb, KERN_INFO,
+				  "recovery required for readonly filesystem");
+			nilfs_msg(sb, KERN_INFO,
+				  "write access will be enabled during recovery");
 		}
 	}
 
@@ -235,13 +239,12 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 			goto scan_error;
 
 		if (!nilfs_valid_sb(sbp[1])) {
-			printk(KERN_WARNING
-			       "NILFS warning: unable to fall back to spare"
-			       "super block\n");
+			nilfs_msg(sb, KERN_WARNING,
+				  "unable to fall back to spare super block");
 			goto scan_error;
 		}
-		printk(KERN_INFO
-		       "NILFS: try rollback from an earlier position\n");
+		nilfs_msg(sb, KERN_INFO,
+			  "trying rollback from an earlier position");
 
 		/*
 		 * restore super block with its spare and reconfigure
@@ -254,10 +257,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 		/* verify consistency between two super blocks */
 		blocksize = BLOCK_SIZE << le32_to_cpu(sbp[0]->s_log_block_size);
 		if (blocksize != nilfs->ns_blocksize) {
-			printk(KERN_WARNING
-			       "NILFS warning: blocksize differs between "
-			       "two super blocks (%d != %d)\n",
-			       blocksize, nilfs->ns_blocksize);
+			nilfs_msg(sb, KERN_WARNING,
+				  "blocksize differs between two super blocks (%d != %d)",
+				  blocksize, nilfs->ns_blocksize);
 			goto scan_error;
 		}
 
@@ -276,7 +278,8 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 
 	err = nilfs_load_super_root(nilfs, sb, ri.ri_super_root);
 	if (unlikely(err)) {
-		printk(KERN_ERR "NILFS: error loading super root.\n");
+		nilfs_msg(sb, KERN_ERR, "error %d while loading super root",
+			  err);
 		goto failed;
 	}
 
@@ -287,30 +290,29 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 		__u64 features;
 
 		if (nilfs_test_opt(nilfs, NORECOVERY)) {
-			printk(KERN_INFO "NILFS: norecovery option specified. "
-			       "skipping roll-forward recovery\n");
+			nilfs_msg(sb, KERN_INFO,
+				  "norecovery option specified, skipping roll-forward recovery");
 			goto skip_recovery;
 		}
 		features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) &
 			~NILFS_FEATURE_COMPAT_RO_SUPP;
 		if (features) {
-			printk(KERN_ERR "NILFS: couldn't proceed with "
-			       "recovery because of unsupported optional "
-			       "features (%llx)\n",
-			       (unsigned long long)features);
+			nilfs_msg(sb, KERN_ERR,
+				  "couldn't proceed with recovery because of unsupported optional features (%llx)",
+				  (unsigned long long)features);
 			err = -EROFS;
 			goto failed_unload;
 		}
 		if (really_read_only) {
-			printk(KERN_ERR "NILFS: write access "
-			       "unavailable, cannot proceed.\n");
+			nilfs_msg(sb, KERN_ERR,
+				  "write access unavailable, cannot proceed");
 			err = -EROFS;
 			goto failed_unload;
 		}
 		sb->s_flags &= ~MS_RDONLY;
 	} else if (nilfs_test_opt(nilfs, NORECOVERY)) {
-		printk(KERN_ERR "NILFS: recovery cancelled because norecovery "
-		       "option was specified for a read/write mount\n");
+		nilfs_msg(sb, KERN_ERR,
+			  "recovery cancelled because norecovery option was specified for a read/write mount");
 		err = -EINVAL;
 		goto failed_unload;
 	}
@@ -325,11 +327,12 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	up_write(&nilfs->ns_sem);
 
 	if (err) {
-		printk(KERN_ERR "NILFS: failed to update super block. "
-		       "recovery unfinished.\n");
+		nilfs_msg(sb, KERN_ERR,
+			  "error %d updating super block. recovery unfinished.",
+			  err);
 		goto failed_unload;
 	}
-	printk(KERN_INFO "NILFS: recovery complete.\n");
+	nilfs_msg(sb, KERN_INFO, "recovery complete");
 
  skip_recovery:
 	nilfs_clear_recovery_info(&ri);
@@ -337,7 +340,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 	return 0;
 
  scan_error:
-	printk(KERN_ERR "NILFS: error searching super root.\n");
+	nilfs_msg(sb, KERN_ERR, "error %d while searching super root", err);
 	goto failed;
 
  failed_unload:
@@ -384,12 +387,11 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 				   struct nilfs_super_block *sbp)
 {
 	if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) {
-		printk(KERN_ERR "NILFS: unsupported revision "
-		       "(superblock rev.=%d.%d, current rev.=%d.%d). "
-		       "Please check the version of mkfs.nilfs.\n",
-		       le32_to_cpu(sbp->s_rev_level),
-		       le16_to_cpu(sbp->s_minor_rev_level),
-		       NILFS_CURRENT_REV, NILFS_MINOR_REV);
+		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+			  "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).",
+			  le32_to_cpu(sbp->s_rev_level),
+			  le16_to_cpu(sbp->s_minor_rev_level),
+			  NILFS_CURRENT_REV, NILFS_MINOR_REV);
 		return -EINVAL;
 	}
 	nilfs->ns_sbsize = le16_to_cpu(sbp->s_bytes);
@@ -398,12 +400,14 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 
 	nilfs->ns_inode_size = le16_to_cpu(sbp->s_inode_size);
 	if (nilfs->ns_inode_size > nilfs->ns_blocksize) {
-		printk(KERN_ERR "NILFS: too large inode size: %d bytes.\n",
-		       nilfs->ns_inode_size);
+		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+			  "too large inode size: %d bytes",
+			  nilfs->ns_inode_size);
 		return -EINVAL;
 	} else if (nilfs->ns_inode_size < NILFS_MIN_INODE_SIZE) {
-		printk(KERN_ERR "NILFS: too small inode size: %d bytes.\n",
-		       nilfs->ns_inode_size);
+		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+			  "too small inode size: %d bytes",
+			  nilfs->ns_inode_size);
 		return -EINVAL;
 	}
 
@@ -411,7 +415,9 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 
 	nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment);
 	if (nilfs->ns_blocks_per_segment < NILFS_SEG_MIN_BLOCKS) {
-		printk(KERN_ERR "NILFS: too short segment.\n");
+		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+			  "too short segment: %lu blocks",
+			  nilfs->ns_blocks_per_segment);
 		return -EINVAL;
 	}
 
@@ -420,7 +426,9 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 		le32_to_cpu(sbp->s_r_segments_percentage);
 	if (nilfs->ns_r_segments_percentage < 1 ||
 	    nilfs->ns_r_segments_percentage > 99) {
-		printk(KERN_ERR "NILFS: invalid reserved segments percentage.\n");
+		nilfs_msg(nilfs->ns_sb, KERN_ERR,
+			  "invalid reserved segments percentage: %lu",
+			  nilfs->ns_r_segments_percentage);
 		return -EINVAL;
 	}
 
@@ -504,16 +512,16 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
 
 	if (!sbp[0]) {
 		if (!sbp[1]) {
-			printk(KERN_ERR "NILFS: unable to read superblock\n");
+			nilfs_msg(sb, KERN_ERR, "unable to read superblock");
 			return -EIO;
 		}
-		printk(KERN_WARNING
-		       "NILFS warning: unable to read primary superblock "
-		       "(blocksize = %d)\n", blocksize);
+		nilfs_msg(sb, KERN_WARNING,
+			  "unable to read primary superblock (blocksize = %d)",
+			  blocksize);
 	} else if (!sbp[1]) {
-		printk(KERN_WARNING
-		       "NILFS warning: unable to read secondary superblock "
-		       "(blocksize = %d)\n", blocksize);
+		nilfs_msg(sb, KERN_WARNING,
+			  "unable to read secondary superblock (blocksize = %d)",
+			  blocksize);
 	}
 
 	/*
@@ -535,14 +543,14 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
 	}
 	if (!valid[swp]) {
 		nilfs_release_super_block(nilfs);
-		printk(KERN_ERR "NILFS: Can't find nilfs on dev %s.\n",
-		       sb->s_id);
+		nilfs_msg(sb, KERN_ERR, "couldn't find nilfs on the device");
 		return -EINVAL;
 	}
 
 	if (!valid[!swp])
-		printk(KERN_WARNING "NILFS warning: broken superblock. "
-		       "using spare superblock (blocksize = %d).\n", blocksize);
+		nilfs_msg(sb, KERN_WARNING,
+			  "broken superblock, retrying with spare superblock (blocksize = %d)",
+			  blocksize);
 	if (swp)
 		nilfs_swap_super_block(nilfs);
 
@@ -576,7 +584,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 
 	blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE);
 	if (!blocksize) {
-		printk(KERN_ERR "NILFS: unable to set blocksize\n");
+		nilfs_msg(sb, KERN_ERR, "unable to set blocksize");
 		err = -EINVAL;
 		goto out;
 	}
@@ -595,8 +603,9 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbp->s_log_block_size);
 	if (blocksize < NILFS_MIN_BLOCK_SIZE ||
 	    blocksize > NILFS_MAX_BLOCK_SIZE) {
-		printk(KERN_ERR "NILFS: couldn't mount because of unsupported "
-		       "filesystem blocksize %d\n", blocksize);
+		nilfs_msg(sb, KERN_ERR,
+			  "couldn't mount because of unsupported filesystem blocksize %d",
+			  blocksize);
 		err = -EINVAL;
 		goto failed_sbh;
 	}
@@ -604,10 +613,9 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 		int hw_blocksize = bdev_logical_block_size(sb->s_bdev);
 
 		if (blocksize < hw_blocksize) {
-			printk(KERN_ERR
-			       "NILFS: blocksize %d too small for device "
-			       "(sector-size = %d).\n",
-			       blocksize, hw_blocksize);
+			nilfs_msg(sb, KERN_ERR,
+				  "blocksize %d too small for device (sector-size = %d)",
+				  blocksize, hw_blocksize);
 			err = -EINVAL;
 			goto failed_sbh;
 		}
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 79369fd6b13b..b305c6f033e7 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -43,6 +43,7 @@ enum {
  * struct the_nilfs - struct to supervise multiple nilfs mount points
  * @ns_flags: flags
  * @ns_flushed_device: flag indicating if all volatile data was flushed
+ * @ns_sb: back pointer to super block instance
  * @ns_bdev: block device
  * @ns_sem: semaphore for shared states
  * @ns_snapshot_mount_mutex: mutex to protect snapshot mounts
@@ -102,6 +103,7 @@ struct the_nilfs {
 	unsigned long		ns_flags;
 	int			ns_flushed_device;
 
+	struct super_block     *ns_sb;
 	struct block_device    *ns_bdev;
 	struct rw_semaphore	ns_sem;
 	struct mutex		ns_snapshot_mount_mutex;
@@ -120,11 +122,8 @@ struct the_nilfs {
 	unsigned int		ns_sb_update_freq;
 
 	/*
-	 * Following fields are dedicated to a writable FS-instance.
-	 * Except for the period seeking checkpoint, code outside the segment
-	 * constructor must lock a segment semaphore while accessing these
-	 * fields.
-	 * The writable FS-instance is sole during a lifetime of the_nilfs.
+	 * The following fields are updated by a writable FS-instance.
+	 * These fields are protected by ns_segctor_sem outside load_nilfs().
 	 */
 	u64			ns_seg_seq;
 	__u64			ns_segnum;
@@ -281,7 +280,7 @@ static inline int nilfs_sb_will_flip(struct the_nilfs *nilfs)
 }
 
 void nilfs_set_last_segment(struct the_nilfs *, sector_t, u64, __u64);
-struct the_nilfs *alloc_nilfs(struct block_device *bdev);
+struct the_nilfs *alloc_nilfs(struct super_block *sb);
 void destroy_nilfs(struct the_nilfs *nilfs);
 int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data);
 int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb);
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 460c0cedab3a..7dabbc31060e 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6106,6 +6106,43 @@ void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb,
 	}
 }
 
+/*
+ * Try to flush truncate logs if we can free enough clusters from it.
+ * As for return value, "< 0" means error, "0" no space and "1" means
+ * we have freed enough spaces and let the caller try to allocate again.
+ */
+int ocfs2_try_to_free_truncate_log(struct ocfs2_super *osb,
+					unsigned int needed)
+{
+	tid_t target;
+	int ret = 0;
+	unsigned int truncated_clusters;
+
+	inode_lock(osb->osb_tl_inode);
+	truncated_clusters = osb->truncated_clusters;
+	inode_unlock(osb->osb_tl_inode);
+
+	/*
+	 * Check whether we can succeed in allocating if we free
+	 * the truncate log.
+	 */
+	if (truncated_clusters < needed)
+		goto out;
+
+	ret = ocfs2_flush_truncate_log(osb);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (jbd2_journal_start_commit(osb->journal->j_journal, &target)) {
+		jbd2_log_wait_commit(osb->journal->j_journal, target);
+		ret = 1;
+	}
+out:
+	return ret;
+}
+
 static int ocfs2_get_truncate_log_info(struct ocfs2_super *osb,
 				       int slot_num,
 				       struct inode **tl_inode,
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index f3dc1b0dfffc..4a5152ec88a3 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -188,6 +188,8 @@ int ocfs2_truncate_log_append(struct ocfs2_super *osb,
 			      u64 start_blk,
 			      unsigned int num_clusters);
 int __ocfs2_flush_truncate_log(struct ocfs2_super *osb);
+int ocfs2_try_to_free_truncate_log(struct ocfs2_super *osb,
+				   unsigned int needed);
 
 /*
  * Process local structure which describes the block unlinks done
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index af2adfcb0f6f..98d36548153d 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1645,43 +1645,6 @@ static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh,
 	return ret;
 }
 
-/*
- * Try to flush truncate logs if we can free enough clusters from it.
- * As for return value, "< 0" means error, "0" no space and "1" means
- * we have freed enough spaces and let the caller try to allocate again.
- */
-static int ocfs2_try_to_free_truncate_log(struct ocfs2_super *osb,
-					  unsigned int needed)
-{
-	tid_t target;
-	int ret = 0;
-	unsigned int truncated_clusters;
-
-	inode_lock(osb->osb_tl_inode);
-	truncated_clusters = osb->truncated_clusters;
-	inode_unlock(osb->osb_tl_inode);
-
-	/*
-	 * Check whether we can succeed in allocating if we free
-	 * the truncate log.
-	 */
-	if (truncated_clusters < needed)
-		goto out;
-
-	ret = ocfs2_flush_truncate_log(osb);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
-
-	if (jbd2_journal_start_commit(osb->journal->j_journal, &target)) {
-		jbd2_log_wait_commit(osb->journal->j_journal, target);
-		ret = 1;
-	}
-out:
-	return ret;
-}
-
 int ocfs2_write_begin_nolock(struct address_space *mapping,
 			     loff_t pos, unsigned len, ocfs2_write_type_t type,
 			     struct page **pagep, void **fsdata,
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 8107d0d0c3f6..e9f3705c4c9f 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -1004,6 +1004,8 @@ int dlm_finalize_reco_handler(struct o2net_msg *msg, u32 len, void *data,
 int dlm_do_master_requery(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 			  u8 nodenum, u8 *real_master);
 
+void __dlm_do_purge_lockres(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res);
 
 int dlm_dispatch_assert_master(struct dlm_ctxt *dlm,
 			       struct dlm_lock_resource *res,
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 13719d3f35f8..6ea06f8a7d29 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2276,9 +2276,12 @@ int dlm_drop_lockres_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 		mlog(ML_ERROR, "%s: res %.*s, DEREF to node %u got %d\n",
 		     dlm->name, namelen, lockname, res->owner, r);
 		dlm_print_one_lock_resource(res);
-		BUG();
-	}
-	return ret ? ret : r;
+		if (r == -ENOMEM)
+			BUG();
+	} else
+		ret = r;
+
+	return ret;
 }
 
 int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
@@ -2416,48 +2419,26 @@ int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data,
 	}
 
 	spin_lock(&res->spinlock);
-	BUG_ON(!(res->state & DLM_LOCK_RES_DROPPING_REF));
-	if (!list_empty(&res->purge)) {
-		mlog(0, "%s: Removing res %.*s from purgelist\n",
-			dlm->name, res->lockname.len, res->lockname.name);
-		list_del_init(&res->purge);
-		dlm_lockres_put(res);
-		dlm->purge_count--;
-	}
-
-	if (!__dlm_lockres_unused(res)) {
-		mlog(ML_ERROR, "%s: res %.*s in use after deref\n",
-			dlm->name, res->lockname.len, res->lockname.name);
-		__dlm_print_one_lock_resource(res);
-		BUG();
-	}
-
-	__dlm_unhash_lockres(dlm, res);
-
-	spin_lock(&dlm->track_lock);
-	if (!list_empty(&res->tracking))
-		list_del_init(&res->tracking);
-	else {
-		mlog(ML_ERROR, "%s: Resource %.*s not on the Tracking list\n",
-		     dlm->name, res->lockname.len, res->lockname.name);
-		__dlm_print_one_lock_resource(res);
+	if (!(res->state & DLM_LOCK_RES_DROPPING_REF)) {
+		spin_unlock(&res->spinlock);
+		spin_unlock(&dlm->spinlock);
+		mlog(ML_NOTICE, "%s:%.*s: node %u sends deref done "
+			"but it is already derefed!\n", dlm->name,
+			res->lockname.len, res->lockname.name, node);
+		ret = 0;
+		goto done;
 	}
-	spin_unlock(&dlm->track_lock);
 
-	/* lockres is not in the hash now. drop the flag and wake up
-	 * any processes waiting in dlm_get_lock_resource.
-	 */
-	res->state &= ~DLM_LOCK_RES_DROPPING_REF;
+	__dlm_do_purge_lockres(dlm, res);
 	spin_unlock(&res->spinlock);
 	wake_up(&res->wq);
 
-	dlm_lockres_put(res);
-
 	spin_unlock(&dlm->spinlock);
 
 	ret = 0;
-
 done:
+	if (res)
+		dlm_lockres_put(res);
 	dlm_put(dlm);
 	return ret;
 }
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index f6b313898763..dd5cb8bcefd1 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2343,6 +2343,7 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 	struct dlm_lock_resource *res;
 	int i;
 	struct hlist_head *bucket;
+	struct hlist_node *tmp;
 	struct dlm_lock *lock;
 
 
@@ -2365,7 +2366,7 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 	 */
 	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
 		bucket = dlm_lockres_hash(dlm, i);
-		hlist_for_each_entry(res, bucket, hash_node) {
+		hlist_for_each_entry_safe(res, tmp, bucket, hash_node) {
  			/* always prune any $RECOVERY entries for dead nodes,
  			 * otherwise hangs can occur during later recovery */
 			if (dlm_is_recovery_lock(res->lockname.name,
@@ -2386,8 +2387,17 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 						break;
 					}
 				}
-				dlm_lockres_clear_refmap_bit(dlm, res,
-						dead_node);
+
+				if ((res->owner == dead_node) &&
+							(res->state & DLM_LOCK_RES_DROPPING_REF)) {
+					dlm_lockres_get(res);
+					__dlm_do_purge_lockres(dlm, res);
+					spin_unlock(&res->spinlock);
+					wake_up(&res->wq);
+					dlm_lockres_put(res);
+					continue;
+				} else if (res->owner == dlm->node_num)
+					dlm_lockres_clear_refmap_bit(dlm, res, dead_node);
 				spin_unlock(&res->spinlock);
 				continue;
 			}
@@ -2398,14 +2408,17 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 				if (res->state & DLM_LOCK_RES_DROPPING_REF) {
 					mlog(0, "%s:%.*s: owned by "
 						"dead node %u, this node was "
-						"dropping its ref when it died. "
-						"continue, dropping the flag.\n",
+						"dropping its ref when master died. "
+						"continue, purging the lockres.\n",
 						dlm->name, res->lockname.len,
 						res->lockname.name, dead_node);
+					dlm_lockres_get(res);
+					__dlm_do_purge_lockres(dlm, res);
+					spin_unlock(&res->spinlock);
+					wake_up(&res->wq);
+					dlm_lockres_put(res);
+					continue;
 				}
-				res->state &= ~DLM_LOCK_RES_DROPPING_REF;
-				dlm_move_lockres_to_recovery_list(dlm,
-						res);
 			} else if (res->owner == dlm->node_num) {
 				dlm_free_dead_locks(dlm, res, dead_node);
 				__dlm_lockres_calc_usage(dlm, res);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 68d239ba0c63..838a06d4066a 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -160,6 +160,52 @@ void dlm_lockres_calc_usage(struct dlm_ctxt *dlm,
 	spin_unlock(&dlm->spinlock);
 }
 
+/*
+ * Do the real purge work:
+ *     unhash the lockres, and
+ *     clear flag DLM_LOCK_RES_DROPPING_REF.
+ * It requires dlm and lockres spinlock to be taken.
+ */
+void __dlm_do_purge_lockres(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res)
+{
+	assert_spin_locked(&dlm->spinlock);
+	assert_spin_locked(&res->spinlock);
+
+	if (!list_empty(&res->purge)) {
+		mlog(0, "%s: Removing res %.*s from purgelist\n",
+		     dlm->name, res->lockname.len, res->lockname.name);
+		list_del_init(&res->purge);
+		dlm_lockres_put(res);
+		dlm->purge_count--;
+	}
+
+	if (!__dlm_lockres_unused(res)) {
+		mlog(ML_ERROR, "%s: res %.*s in use after deref\n",
+		     dlm->name, res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+		BUG();
+	}
+
+	__dlm_unhash_lockres(dlm, res);
+
+	spin_lock(&dlm->track_lock);
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "%s: Resource %.*s not on the Tracking list\n",
+		     dlm->name, res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+	}
+	spin_unlock(&dlm->track_lock);
+
+	/*
+	 * lockres is not in the hash now. drop the flag and wake up
+	 * any processes waiting in dlm_get_lock_resource.
+	 */
+	res->state &= ~DLM_LOCK_RES_DROPPING_REF;
+}
+
 static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 			     struct dlm_lock_resource *res)
 {
@@ -175,6 +221,13 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 	     res->lockname.len, res->lockname.name, master);
 
 	if (!master) {
+		if (res->state & DLM_LOCK_RES_DROPPING_REF) {
+			mlog(ML_NOTICE, "%s: res %.*s already in DLM_LOCK_RES_DROPPING_REF state\n",
+				dlm->name, res->lockname.len, res->lockname.name);
+			spin_unlock(&res->spinlock);
+			return;
+		}
+
 		res->state |= DLM_LOCK_RES_DROPPING_REF;
 		/* drop spinlock...  retake below */
 		spin_unlock(&res->spinlock);
@@ -203,8 +256,8 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 		dlm->purge_count--;
 	}
 
-	if (!master && ret != 0) {
-		mlog(0, "%s: deref %.*s in progress or master goes down\n",
+	if (!master && ret == DLM_DEREF_RESPONSE_INPROG) {
+		mlog(0, "%s: deref %.*s in progress\n",
 			dlm->name, res->lockname.len, res->lockname.name);
 		spin_unlock(&res->spinlock);
 		return;
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index ced70c8139f7..c9e828ec3c8e 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -1007,10 +1007,17 @@ static int user_cluster_connect(struct ocfs2_cluster_connection *conn)
 	lc->oc_type = NO_CONTROLD;
 
 	rc = dlm_new_lockspace(conn->cc_name, conn->cc_cluster_name,
-			       DLM_LSFL_FS, DLM_LVB_LEN,
+			       DLM_LSFL_FS | DLM_LSFL_NEWEXCL, DLM_LVB_LEN,
 			       &ocfs2_ls_ops, conn, &ops_rv, &fsdlm);
-	if (rc)
+	if (rc) {
+		if (rc == -EEXIST || rc == -EPROTO)
+			printk(KERN_ERR "ocfs2: Unable to create the "
+				"lockspace %s (%d), because a ocfs2-tools "
+				"program is running on this file system "
+				"with the same name lockspace\n",
+				conn->cc_name, rc);
 		goto out;
+	}
 
 	if (ops_rv == -EOPNOTSUPP) {
 		lc->oc_type = WITH_CONTROLD;
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 2f19aeec5482..ea47120a85ff 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1164,7 +1164,8 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
 					     int flags,
 					     struct ocfs2_alloc_context **ac)
 {
-	int status;
+	int status, ret = 0;
+	int retried = 0;
 
 	*ac = kzalloc(sizeof(struct ocfs2_alloc_context), GFP_KERNEL);
 	if (!(*ac)) {
@@ -1189,7 +1190,24 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
 	}
 
 	if (status == -ENOSPC) {
+retry:
 		status = ocfs2_reserve_cluster_bitmap_bits(osb, *ac);
+		/* Retry if there is sufficient space cached in truncate log */
+		if (status == -ENOSPC && !retried) {
+			retried = 1;
+			ocfs2_inode_unlock((*ac)->ac_inode, 1);
+			inode_unlock((*ac)->ac_inode);
+
+			ret = ocfs2_try_to_free_truncate_log(osb, bits_wanted);
+			if (ret == 1)
+				goto retry;
+
+			if (ret < 0)
+				mlog_errno(ret);
+
+			inode_lock((*ac)->ac_inode);
+			ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+		}
 		if (status < 0) {
 			if (status != -ENOSPC)
 				mlog_errno(status);
diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c
index 5dfc4f3cfe68..00235bf644dc 100644
--- a/fs/orangefs/dcache.c
+++ b/fs/orangefs/dcache.c
@@ -73,6 +73,7 @@ static int orangefs_revalidate_lookup(struct dentry *dentry)
 		}
 	}
 
+	dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
 	ret = 1;
 out_release_op:
 	op_release(new_op);
@@ -94,6 +95,9 @@ static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	int ret;
 
+	if (time_before(jiffies, dentry->d_time))
+		return 1;
+
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 2e63e6d0a68e..28a0557a69be 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -262,7 +262,7 @@ int orangefs_getattr(struct vfsmount *mnt,
 		     "orangefs_getattr: called on %s\n",
 		     dentry->d_name.name);
 
-	ret = orangefs_inode_getattr(inode, 0, 1);
+	ret = orangefs_inode_getattr(inode, 0, 0);
 	if (ret == 0) {
 		generic_fillattr(inode, kstat);
 
@@ -384,7 +384,7 @@ struct inode *orangefs_iget(struct super_block *sb, struct orangefs_object_kref
 	if (!inode || !(inode->i_state & I_NEW))
 		return inode;
 
-	error = orangefs_inode_getattr(inode, 1, 0);
+	error = orangefs_inode_getattr(inode, 1, 1);
 	if (error) {
 		iget_failed(inode);
 		return ERR_PTR(error);
@@ -429,7 +429,7 @@ struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir,
 	orangefs_set_inode(inode, ref);
 	inode->i_ino = hash;	/* needed for stat etc */
 
-	error = orangefs_inode_getattr(inode, 1, 0);
+	error = orangefs_inode_getattr(inode, 1, 1);
 	if (error)
 		goto out_iput;
 
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
index 7e8dfa97c44a..62c525936ee8 100644
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -72,6 +72,8 @@ static int orangefs_create(struct inode *dir,
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
+	dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
 		     "%s: dentry instantiated for %s\n",
@@ -181,6 +183,8 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 
+	dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+
 	inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
 	if (IS_ERR(inode)) {
 		gossip_debug(GOSSIP_NAME_DEBUG,
@@ -189,6 +193,8 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 
+	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
+
 	gossip_debug(GOSSIP_NAME_DEBUG,
 		     "%s:%s:%d "
 		     "Found good inode [%lu] with count [%d]\n",
@@ -316,6 +322,8 @@ static int orangefs_symlink(struct inode *dir,
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
+	dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
 		     "Inode (Symlink) %pU -> %s\n",
@@ -378,6 +386,8 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
+	dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
 		     "Inode (Directory) %pU -> %s\n",
@@ -408,6 +418,8 @@ static int orangefs_rename(struct inode *old_dir,
 		     "orangefs_rename: called (%pd2 => %pd2) ct=%d\n",
 		     old_dentry, new_dentry, d_count(new_dentry));
 
+	ORANGEFS_I(new_dentry->d_parent->d_inode)->getattr_time = jiffies - 1;
+
 	new_op = op_alloc(ORANGEFS_VFS_OP_RENAME);
 	if (!new_op)
 		return -EINVAL;
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 4b6e132d5a0f..633c07a6e3d8 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -246,6 +246,8 @@ struct orangefs_inode_s {
 	 * with this object
 	 */
 	unsigned long pinode_flags;
+
+	unsigned long getattr_time;
 };
 
 #define P_ATIME_FLAG 0
@@ -527,7 +529,7 @@ int orangefs_inode_setxattr(struct inode *inode,
 			 size_t size,
 			 int flags);
 
-int orangefs_inode_getattr(struct inode *inode, int new, int size);
+int orangefs_inode_getattr(struct inode *inode, int new, int bypass);
 
 int orangefs_inode_check_changed(struct inode *inode);
 
@@ -546,6 +548,8 @@ extern struct mutex request_mutex;
 extern int debug;
 extern int op_timeout_secs;
 extern int slot_timeout_secs;
+extern int dcache_timeout_msecs;
+extern int getattr_timeout_msecs;
 extern struct list_head orangefs_superblocks;
 extern spinlock_t orangefs_superblocks_lock;
 extern struct list_head orangefs_request_list;
diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c
index 6f072a8c0de1..e9fd5755c05f 100644
--- a/fs/orangefs/orangefs-mod.c
+++ b/fs/orangefs/orangefs-mod.c
@@ -47,6 +47,8 @@ struct client_debug_mask client_debug_mask = { NULL, 0, 0 };
 unsigned int kernel_mask_set_mod_init; /* implicitly false */
 int op_timeout_secs = ORANGEFS_DEFAULT_OP_TIMEOUT_SECS;
 int slot_timeout_secs = ORANGEFS_DEFAULT_SLOT_TIMEOUT_SECS;
+int dcache_timeout_msecs = 50;
+int getattr_timeout_msecs = 50;
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("ORANGEFS Development Team");
diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c
index 5c03113e3ad2..375708c2db87 100644
--- a/fs/orangefs/orangefs-sysfs.c
+++ b/fs/orangefs/orangefs-sysfs.c
@@ -61,10 +61,21 @@
  *			Slots are requested and waited for,
  *			the wait times out after slot_timeout_secs.
  *
+ * What:		/sys/fs/orangefs/dcache_timeout_msecs
+ * Date:		Jul 2016
+ * Contact:		Martin Brandenburg <martin@omnibond.com>
+ * Description:
+ *			Time lookup is valid in milliseconds.
+ *
+ * What:		/sys/fs/orangefs/getattr_timeout_msecs
+ * Date:		Jul 2016
+ * Contact:		Martin Brandenburg <martin@omnibond.com>
+ * Description:
+ *			Time getattr is valid in milliseconds.
  *
  * What:		/sys/fs/orangefs/acache/...
  * Date:		Jun 2015
- * Contact:		Mike Marshall <hubcap@omnibond.com>
+ * Contact:		Martin Brandenburg <martin@omnibond.com>
  * Description:
  * 			Attribute cache configurable settings.
  *
@@ -117,6 +128,8 @@ struct orangefs_obj {
 	int perf_history_size;
 	int perf_time_interval_secs;
 	int slot_timeout_secs;
+	int dcache_timeout_msecs;
+	int getattr_timeout_msecs;
 };
 
 struct acache_orangefs_obj {
@@ -658,6 +671,20 @@ static ssize_t sysfs_int_show(char *kobj_id, char *buf, void *attr)
 				       "%d\n",
 				       slot_timeout_secs);
 			goto out;
+		} else if (!strcmp(orangefs_attr->attr.name,
+				   "dcache_timeout_msecs")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%d\n",
+				       dcache_timeout_msecs);
+			goto out;
+		} else if (!strcmp(orangefs_attr->attr.name,
+				   "getattr_timeout_msecs")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%d\n",
+				       getattr_timeout_msecs);
+			goto out;
 		} else {
 			goto out;
 		}
@@ -734,6 +761,12 @@ static ssize_t int_store(struct orangefs_obj *orangefs_obj,
 	} else if (!strcmp(attr->attr.name, "slot_timeout_secs")) {
 		rc = kstrtoint(buf, 0, &slot_timeout_secs);
 		goto out;
+	} else if (!strcmp(attr->attr.name, "dcache_timeout_msecs")) {
+		rc = kstrtoint(buf, 0, &dcache_timeout_msecs);
+		goto out;
+	} else if (!strcmp(attr->attr.name, "getattr_timeout_msecs")) {
+		rc = kstrtoint(buf, 0, &getattr_timeout_msecs);
+		goto out;
 	} else {
 		goto out;
 	}
@@ -1361,6 +1394,12 @@ static struct orangefs_attribute op_timeout_secs_attribute =
 static struct orangefs_attribute slot_timeout_secs_attribute =
 	__ATTR(slot_timeout_secs, 0664, int_orangefs_show, int_store);
 
+static struct orangefs_attribute dcache_timeout_msecs_attribute =
+	__ATTR(dcache_timeout_msecs, 0664, int_orangefs_show, int_store);
+
+static struct orangefs_attribute getattr_timeout_msecs_attribute =
+	__ATTR(getattr_timeout_msecs, 0664, int_orangefs_show, int_store);
+
 static struct orangefs_attribute perf_counter_reset_attribute =
 	__ATTR(perf_counter_reset,
 	       0664,
@@ -1382,6 +1421,8 @@ static struct orangefs_attribute perf_time_interval_secs_attribute =
 static struct attribute *orangefs_default_attrs[] = {
 	&op_timeout_secs_attribute.attr,
 	&slot_timeout_secs_attribute.attr,
+	&dcache_timeout_msecs_attribute.attr,
+	&getattr_timeout_msecs_attribute.attr,
 	&perf_counter_reset_attribute.attr,
 	&perf_history_size_attribute.attr,
 	&perf_time_interval_secs_attribute.attr,
diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c
index c5fbc62357c6..d13c7291fd05 100644
--- a/fs/orangefs/orangefs-utils.c
+++ b/fs/orangefs/orangefs-utils.c
@@ -251,7 +251,7 @@ static int orangefs_inode_is_stale(struct inode *inode, int new,
 	return 0;
 }
 
-int orangefs_inode_getattr(struct inode *inode, int new, int size)
+int orangefs_inode_getattr(struct inode *inode, int new, int bypass)
 {
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
 	struct orangefs_kernel_op_s *new_op;
@@ -261,12 +261,16 @@ int orangefs_inode_getattr(struct inode *inode, int new, int size)
 	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: called on inode %pU\n", __func__,
 	    get_khandle_from_ino(inode));
 
+	if (!new && !bypass) {
+		if (time_before(jiffies, orangefs_inode->getattr_time))
+			return 0;
+	}
+
 	new_op = op_alloc(ORANGEFS_VFS_OP_GETATTR);
 	if (!new_op)
 		return -ENOMEM;
 	new_op->upcall.req.getattr.refn = orangefs_inode->refn;
-	new_op->upcall.req.getattr.mask = size ?
-	    ORANGEFS_ATTR_SYS_ALL_NOHINT : ORANGEFS_ATTR_SYS_ALL_NOHINT_NOSIZE;
+	new_op->upcall.req.getattr.mask = ORANGEFS_ATTR_SYS_ALL_NOHINT;
 
 	ret = service_operation(new_op, __func__,
 	    get_interruptible_flag(inode));
@@ -287,20 +291,18 @@ int orangefs_inode_getattr(struct inode *inode, int new, int size)
 	case S_IFREG:
 		inode->i_flags = orangefs_inode_flags(&new_op->
 		    downcall.resp.getattr.attributes);
-		if (size) {
-			inode_size = (loff_t)new_op->
-			    downcall.resp.getattr.attributes.size;
-			rounded_up_size =
-			    (inode_size + (4096 - (inode_size % 4096)));
-			inode->i_size = inode_size;
-			orangefs_inode->blksize =
-			    new_op->downcall.resp.getattr.attributes.blksize;
-			spin_lock(&inode->i_lock);
-			inode->i_bytes = inode_size;
-			inode->i_blocks =
-			    (unsigned long)(rounded_up_size / 512);
-			spin_unlock(&inode->i_lock);
-		}
+		inode_size = (loff_t)new_op->
+		    downcall.resp.getattr.attributes.size;
+		rounded_up_size =
+		    (inode_size + (4096 - (inode_size % 4096)));
+		inode->i_size = inode_size;
+		orangefs_inode->blksize =
+		    new_op->downcall.resp.getattr.attributes.blksize;
+		spin_lock(&inode->i_lock);
+		inode->i_bytes = inode_size;
+		inode->i_blocks =
+		    (unsigned long)(rounded_up_size / 512);
+		spin_unlock(&inode->i_lock);
 		break;
 	case S_IFDIR:
 		inode->i_size = PAGE_SIZE;
@@ -345,6 +347,7 @@ int orangefs_inode_getattr(struct inode *inode, int new, int size)
 	inode->i_mode = type | (is_root_handle(inode) ? S_ISVTX : 0) |
 	    orangefs_inode_perms(&new_op->downcall.resp.getattr.attributes);
 
+	orangefs_inode->getattr_time = jiffies + getattr_timeout_msecs*HZ/1000;
 	ret = 0;
 out:
 	op_release(new_op);
@@ -418,6 +421,7 @@ int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr)
 		ClearMtimeFlag(orangefs_inode);
 		ClearCtimeFlag(orangefs_inode);
 		ClearModeFlag(orangefs_inode);
+		orangefs_inode->getattr_time = jiffies - 1;
 	}
 
 	return ret;
diff --git a/fs/orangefs/protocol.h b/fs/orangefs/protocol.h
index 1efc6f8a5224..3d7418c728f5 100644
--- a/fs/orangefs/protocol.h
+++ b/fs/orangefs/protocol.h
@@ -207,14 +207,6 @@ typedef __s64 ORANGEFS_offset;
 	 ORANGEFS_ATTR_SYS_DIRENT_COUNT		|	\
 	 ORANGEFS_ATTR_SYS_BLKSIZE)
 
-#define ORANGEFS_ATTR_SYS_ALL_NOHINT_NOSIZE		\
-	(ORANGEFS_ATTR_SYS_COMMON_ALL		|	\
-	 ORANGEFS_ATTR_SYS_LNK_TARGET		|	\
-	 ORANGEFS_ATTR_SYS_DFILE_COUNT		|	\
-	 ORANGEFS_ATTR_SYS_MIRROR_COPIES_COUNT	|	\
-	 ORANGEFS_ATTR_SYS_DIRENT_COUNT		|	\
-	 ORANGEFS_ATTR_SYS_BLKSIZE)
-
 #define ORANGEFS_XATTR_REPLACE 0x2
 #define ORANGEFS_XATTR_CREATE  0x1
 #define ORANGEFS_MAX_SERVER_ADDR_LEN 256
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 7151ea428041..a8c13605b434 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -4,6 +4,7 @@
 
 obj-y   += proc.o
 
+CFLAGS_task_mmu.o	+= -Wno-override-init
 proc-y			:= nommu.o task_nommu.o
 proc-$(CONFIG_MMU)	:= task_mmu.o
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 31370da2ee7c..54e270262979 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -579,11 +579,8 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
 	unsigned long totalpages = totalram_pages + total_swap_pages;
 	unsigned long points = 0;
 
-	read_lock(&tasklist_lock);
-	if (pid_alive(task))
-		points = oom_badness(task, NULL, NULL, totalpages) *
-						1000 / totalpages;
-	read_unlock(&tasklist_lock);
+	points = oom_badness(task, NULL, NULL, totalpages) *
+					1000 / totalpages;
 	seq_printf(m, "%lu\n", points);
 
 	return 0;
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 510413eb25b8..7907e456ac4f 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -80,19 +80,17 @@ static u64 get_iowait_time(int cpu)
 static int show_stat(struct seq_file *p, void *v)
 {
 	int i, j;
-	unsigned long jif;
 	u64 user, nice, system, idle, iowait, irq, softirq, steal;
 	u64 guest, guest_nice;
 	u64 sum = 0;
 	u64 sum_softirq = 0;
 	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
-	struct timespec boottime;
+	struct timespec64 boottime;
 
 	user = nice = system = idle = iowait =
 		irq = softirq = steal = 0;
 	guest = guest_nice = 0;
-	getboottime(&boottime);
-	jif = boottime.tv_sec;
+	getboottime64(&boottime);
 
 	for_each_possible_cpu(i) {
 		user += kcpustat_cpu(i).cpustat[CPUTIME_USER];
@@ -163,12 +161,12 @@ static int show_stat(struct seq_file *p, void *v)
 
 	seq_printf(p,
 		"\nctxt %llu\n"
-		"btime %lu\n"
+		"btime %llu\n"
 		"processes %lu\n"
 		"procs_running %lu\n"
 		"procs_blocked %lu\n",
 		nr_context_switches(),
-		(unsigned long)jif,
+		(unsigned long long)boottime.tv_sec,
 		total_forks,
 		nr_running(),
 		nr_iowait());
diff --git a/fs/reiserfs/ibalance.c b/fs/reiserfs/ibalance.c
index b751eea32e20..5db6f45b3fed 100644
--- a/fs/reiserfs/ibalance.c
+++ b/fs/reiserfs/ibalance.c
@@ -1153,8 +1153,9 @@ int balance_internal(struct tree_balance *tb,
 				       insert_ptr);
 	}
 
-	memcpy(new_insert_key_addr, &new_insert_key, KEY_SIZE);
 	insert_ptr[0] = new_insert_ptr;
+	if (new_insert_ptr)
+		memcpy(new_insert_key_addr, &new_insert_key, KEY_SIZE);
 
 	return order;
 }
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 788c6c35291a..c1a524de67c5 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -420,6 +420,13 @@ static inline struct acpi_data_node *to_acpi_data_node(struct fwnode_handle *fwn
 		container_of(fwnode, struct acpi_data_node, fwnode) : NULL;
 }
 
+static inline bool acpi_data_node_match(struct fwnode_handle *fwnode,
+					const char *name)
+{
+	return is_acpi_data_node(fwnode) ?
+		(!strcmp(to_acpi_data_node(fwnode)->name, name)) : false;
+}
+
 static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev)
 {
 	return &adev->fwnode;
diff --git a/include/acpi/acpi_io.h b/include/acpi/acpi_io.h
index dd86c5fc102d..d7d0f495a34e 100644
--- a/include/acpi/acpi_io.h
+++ b/include/acpi/acpi_io.h
@@ -13,7 +13,7 @@ static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
 }
 #endif
 
-void __iomem *__init_refok
+void __iomem *__ref
 acpi_os_map_iomem(acpi_physical_address phys, acpi_size size);
 void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size);
 void __iomem *acpi_os_get_iomem(acpi_physical_address phys, unsigned int size);
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 54643d1f5af4..24563970ff7b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -164,7 +164,7 @@
 
 #define ___OF_TABLE(cfg, name)	_OF_TABLE_##cfg(name)
 #define __OF_TABLE(cfg, name)	___OF_TABLE(cfg, name)
-#define OF_TABLE(cfg, name)	__OF_TABLE(config_enabled(cfg), name)
+#define OF_TABLE(cfg, name)	__OF_TABLE(IS_ENABLED(cfg), name)
 #define _OF_TABLE_0(name)
 #define _OF_TABLE_1(name)						\
 	. = ALIGN(8);							\
diff --git a/include/drm/bridge/analogix_dp.h b/include/drm/bridge/analogix_dp.h
index 25afb31f0389..261b86d20e77 100644
--- a/include/drm/bridge/analogix_dp.h
+++ b/include/drm/bridge/analogix_dp.h
@@ -16,8 +16,14 @@
 enum analogix_dp_devtype {
 	EXYNOS_DP,
 	RK3288_DP,
+	RK3399_EDP,
 };
 
+static inline bool is_rockchip(enum analogix_dp_devtype type)
+{
+	return type == RK3288_DP || type == RK3399_EDP;
+}
+
 struct analogix_dp_plat_data {
 	enum analogix_dp_devtype dev_type;
 	struct drm_panel *panel;
@@ -28,7 +34,8 @@ struct analogix_dp_plat_data {
 	int (*power_off)(struct analogix_dp_plat_data *);
 	int (*attach)(struct analogix_dp_plat_data *, struct drm_bridge *,
 		      struct drm_connector *);
-	int (*get_modes)(struct analogix_dp_plat_data *);
+	int (*get_modes)(struct analogix_dp_plat_data *,
+			 struct drm_connector *);
 };
 
 int analogix_dp_resume(struct device *dev);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 84f1a8eefbdb..d3778652e462 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -56,6 +56,7 @@
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 #include <linux/workqueue.h>
+#include <linux/fence.h>
 
 #include <asm/mman.h>
 #include <asm/pgalloc.h>
@@ -66,6 +67,7 @@
 
 #include <drm/drm_agpsupport.h>
 #include <drm/drm_crtc.h>
+#include <drm/drm_fourcc.h>
 #include <drm/drm_global.h>
 #include <drm/drm_hashtab.h>
 #include <drm/drm_mem_util.h>
@@ -83,6 +85,8 @@ struct drm_local_map;
 struct drm_device_dma;
 struct drm_dma_handle;
 struct drm_gem_object;
+struct drm_master;
+struct drm_vblank_crtc;
 
 struct device_node;
 struct videomode;
@@ -281,13 +285,14 @@ struct drm_ioctl_desc {
 
 /* Event queued up for userspace to read */
 struct drm_pending_event {
+	struct completion *completion;
 	struct drm_event *event;
+	struct fence *fence;
 	struct list_head link;
 	struct list_head pending_link;
 	struct drm_file *file_priv;
 	pid_t pid; /* pid of requester, no guarantee it's valid by the time
 		      we deliver the event, for tracing only */
-	void (*destroy)(struct drm_pending_event *event);
 };
 
 /* initial implementaton using a linked list - todo hashtab */
@@ -299,8 +304,6 @@ struct drm_prime_file_private {
 /** File private data */
 struct drm_file {
 	unsigned authenticated :1;
-	/* Whether we're master for a minor. Protected by master_mutex */
-	unsigned is_master :1;
 	/* true when the client has asked us to expose stereo 3D mode flags */
 	unsigned stereo_allowed :1;
 	/*
@@ -311,10 +314,10 @@ struct drm_file {
 	/* true if client understands atomic properties */
 	unsigned atomic:1;
 	/*
-	 * This client is allowed to gain master privileges for @master.
+	 * This client is the creator of @master.
 	 * Protected by struct drm_device::master_mutex.
 	 */
-	unsigned allowed_master:1;
+	unsigned is_master:1;
 
 	struct pid *pid;
 	kuid_t uid;
@@ -332,7 +335,7 @@ struct drm_file {
 	void *driver_priv;
 
 	struct drm_master *master; /* master this node is currently associated with
-				      N.B. not always minor->master */
+				      N.B. not always dev->master */
 	/**
 	 * fbs - List of framebuffers associated with this file.
 	 *
@@ -371,32 +374,6 @@ struct drm_lock_data {
 	int idle_has_lock;
 };
 
-/**
- * struct drm_master - drm master structure
- *
- * @refcount: Refcount for this master object.
- * @minor: Link back to minor char device we are master for. Immutable.
- * @unique: Unique identifier: e.g. busid. Protected by drm_global_mutex.
- * @unique_len: Length of unique field. Protected by drm_global_mutex.
- * @magic_map: Map of used authentication tokens. Protected by struct_mutex.
- * @lock: DRI lock information.
- * @driver_priv: Pointer to driver-private information.
- */
-struct drm_master {
-	struct kref refcount;
-	struct drm_minor *minor;
-	char *unique;
-	int unique_len;
-	struct idr magic_map;
-	struct drm_lock_data lock;
-	void *driver_priv;
-};
-
-/* Size of ringbuffer for vblank timestamps. Just double-buffer
- * in initial implementation.
- */
-#define DRM_VBLANKTIME_RBSIZE 2
-
 /* Flags and return codes for get_vblank_timestamp() driver function. */
 #define DRM_CALLED_FROM_VBLIRQ 1
 #define DRM_VBLANKTIME_SCANOUTPOS_METHOD (1 << 0)
@@ -420,8 +397,6 @@ struct drm_driver {
 	void (*postclose) (struct drm_device *, struct drm_file *);
 	void (*lastclose) (struct drm_device *);
 	int (*unload) (struct drm_device *);
-	int (*suspend) (struct drm_device *, pm_message_t state);
-	int (*resume) (struct drm_device *);
 	int (*dma_ioctl) (struct drm_device *dev, void *data, struct drm_file *file_priv);
 	int (*dma_quiescent) (struct drm_device *);
 	int (*context_dtor) (struct drm_device *dev, int context);
@@ -434,7 +409,7 @@ struct drm_driver {
 	 *
 	 * Driver callback for fetching a raw hardware vblank counter for @crtc.
 	 * If a device doesn't have a hardware counter, the driver can simply
-	 * return the value of drm_vblank_count. The DRM core will account for
+	 * use drm_vblank_no_hw_counter() function. The DRM core will account for
 	 * missed vblank events while interrupts where disabled based on system
 	 * timestamps.
 	 *
@@ -452,8 +427,8 @@ struct drm_driver {
 	 * @pipe: which irq to enable
 	 *
 	 * Enable vblank interrupts for @crtc.  If the device doesn't have
-	 * a hardware vblank counter, this routine should be a no-op, since
-	 * interrupts will have to stay on to keep the count accurate.
+	 * a hardware vblank counter, the driver should use the
+	 * drm_vblank_no_hw_counter() function that keeps a virtual counter.
 	 *
 	 * RETURNS
 	 * Zero on success, appropriate errno if the given @crtc's vblank
@@ -467,8 +442,8 @@ struct drm_driver {
 	 * @pipe: which irq to enable
 	 *
 	 * Disable vblank interrupts for @crtc.  If the device doesn't have
-	 * a hardware vblank counter, this routine should be a no-op, since
-	 * interrupts will have to stay on to keep the count accurate.
+	 * a hardware vblank counter, the driver should use the
+	 * drm_vblank_no_hw_counter() function that keeps a virtual counter.
 	 */
 	void (*disable_vblank) (struct drm_device *dev, unsigned int pipe);
 
@@ -573,8 +548,7 @@ struct drm_driver {
 
 	int (*master_set)(struct drm_device *dev, struct drm_file *file_priv,
 			  bool from_open);
-	void (*master_drop)(struct drm_device *dev, struct drm_file *file_priv,
-			    bool from_release);
+	void (*master_drop)(struct drm_device *dev, struct drm_file *file_priv);
 
 	int (*debugfs_init)(struct drm_minor *minor);
 	void (*debugfs_cleanup)(struct drm_minor *minor);
@@ -708,38 +682,6 @@ struct drm_minor {
 
 	struct list_head debugfs_list;
 	struct mutex debugfs_lock; /* Protects debugfs_list. */
-
-	/* currently active master for this node. Protected by master_mutex */
-	struct drm_master *master;
-};
-
-
-struct drm_pending_vblank_event {
-	struct drm_pending_event base;
-	unsigned int pipe;
-	struct drm_event_vblank event;
-};
-
-struct drm_vblank_crtc {
-	struct drm_device *dev;		/* pointer to the drm_device */
-	wait_queue_head_t queue;	/**< VBLANK wait queue */
-	struct timer_list disable_timer;		/* delayed disable timer */
-
-	/* vblank counter, protected by dev->vblank_time_lock for writes */
-	u32 count;
-	/* vblank timestamps, protected by dev->vblank_time_lock for writes */
-	struct timeval time[DRM_VBLANKTIME_RBSIZE];
-
-	atomic_t refcount;		/* number of users of vblank interruptsper crtc */
-	u32 last;			/* protected by dev->vbl_lock, used */
-					/* for wraparound handling */
-	u32 last_wait;			/* Last vblank seqno waited per CRTC */
-	unsigned int inmodeset;		/* Display driver is setting mode */
-	unsigned int pipe;		/* crtc index */
-	int framedur_ns;		/* frame/field duration in ns */
-	int linedur_ns;			/* line duration in ns */
-	bool enabled;			/* so we don't call enable more than
-					   once per disable */
 };
 
 /**
@@ -759,6 +701,10 @@ struct drm_device {
 	struct drm_minor *control;		/**< Control node */
 	struct drm_minor *primary;		/**< Primary node */
 	struct drm_minor *render;		/**< Render node */
+
+	/* currently active master for this device. Protected by master_mutex */
+	struct drm_master *master;
+
 	atomic_t unplugged;			/**< Flag whether dev is dead */
 	struct inode *anon_inode;		/**< inode for private address-space */
 	char *unique;				/**< unique name of the device */
@@ -872,6 +818,8 @@ struct drm_device {
 	int switch_power_state;
 };
 
+#include <drm/drm_irq.h>
+
 #define DRM_SWITCH_POWER_ON 0
 #define DRM_SWITCH_POWER_OFF 1
 #define DRM_SWITCH_POWER_CHANGING 2
@@ -928,7 +876,6 @@ int drm_open(struct inode *inode, struct file *filp);
 ssize_t drm_read(struct file *filp, char __user *buffer,
 		 size_t count, loff_t *offset);
 int drm_release(struct inode *inode, struct file *filp);
-int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv);
 unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait);
 int drm_event_reserve_init_locked(struct drm_device *dev,
 				  struct drm_file *file_priv,
@@ -959,75 +906,14 @@ void drm_clflush_virt_range(void *addr, unsigned long length);
  * DMA quiscent + idle. DMA quiescent usually requires the hardware lock.
  */
 
-				/* IRQ support (drm_irq.h) */
-extern int drm_irq_install(struct drm_device *dev, int irq);
-extern int drm_irq_uninstall(struct drm_device *dev);
-
-extern int drm_vblank_init(struct drm_device *dev, unsigned int num_crtcs);
-extern int drm_wait_vblank(struct drm_device *dev, void *data,
-			   struct drm_file *filp);
-extern u32 drm_vblank_count(struct drm_device *dev, unsigned int pipe);
-extern u32 drm_crtc_vblank_count(struct drm_crtc *crtc);
-extern u32 drm_vblank_count_and_time(struct drm_device *dev, unsigned int pipe,
-				     struct timeval *vblanktime);
-extern u32 drm_crtc_vblank_count_and_time(struct drm_crtc *crtc,
-					  struct timeval *vblanktime);
-extern void drm_send_vblank_event(struct drm_device *dev, unsigned int pipe,
-				  struct drm_pending_vblank_event *e);
-extern void drm_crtc_send_vblank_event(struct drm_crtc *crtc,
-				       struct drm_pending_vblank_event *e);
-extern void drm_arm_vblank_event(struct drm_device *dev, unsigned int pipe,
-				 struct drm_pending_vblank_event *e);
-extern void drm_crtc_arm_vblank_event(struct drm_crtc *crtc,
-				      struct drm_pending_vblank_event *e);
-extern bool drm_handle_vblank(struct drm_device *dev, unsigned int pipe);
-extern bool drm_crtc_handle_vblank(struct drm_crtc *crtc);
-extern int drm_vblank_get(struct drm_device *dev, unsigned int pipe);
-extern void drm_vblank_put(struct drm_device *dev, unsigned int pipe);
-extern int drm_crtc_vblank_get(struct drm_crtc *crtc);
-extern void drm_crtc_vblank_put(struct drm_crtc *crtc);
-extern void drm_wait_one_vblank(struct drm_device *dev, unsigned int pipe);
-extern void drm_crtc_wait_one_vblank(struct drm_crtc *crtc);
-extern void drm_vblank_off(struct drm_device *dev, unsigned int pipe);
-extern void drm_vblank_on(struct drm_device *dev, unsigned int pipe);
-extern void drm_crtc_vblank_off(struct drm_crtc *crtc);
-extern void drm_crtc_vblank_reset(struct drm_crtc *crtc);
-extern void drm_crtc_vblank_on(struct drm_crtc *crtc);
-extern void drm_vblank_cleanup(struct drm_device *dev);
-extern u32 drm_vblank_no_hw_counter(struct drm_device *dev, unsigned int pipe);
-
-extern int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev,
-						 unsigned int pipe, int *max_error,
-						 struct timeval *vblank_time,
-						 unsigned flags,
-						 const struct drm_display_mode *mode);
-extern void drm_calc_timestamping_constants(struct drm_crtc *crtc,
-					    const struct drm_display_mode *mode);
-
-/**
- * drm_crtc_vblank_waitqueue - get vblank waitqueue for the CRTC
- * @crtc: which CRTC's vblank waitqueue to retrieve
- *
- * This function returns a pointer to the vblank waitqueue for the CRTC.
- * Drivers can use this to implement vblank waits using wait_event() & co.
- */
-static inline wait_queue_head_t *drm_crtc_vblank_waitqueue(struct drm_crtc *crtc)
-{
-	return &crtc->dev->vblank[drm_crtc_index(crtc)].queue;
-}
-
 /* Modesetting support */
 extern void drm_vblank_pre_modeset(struct drm_device *dev, unsigned int pipe);
 extern void drm_vblank_post_modeset(struct drm_device *dev, unsigned int pipe);
 
-				/* Stub support (drm_stub.h) */
-extern struct drm_master *drm_master_get(struct drm_master *master);
-extern void drm_master_put(struct drm_master **master);
-
-extern void drm_put_dev(struct drm_device *dev);
-extern void drm_unplug_dev(struct drm_device *dev);
+/* drm_drv.c */
+void drm_put_dev(struct drm_device *dev);
+void drm_unplug_dev(struct drm_device *dev);
 extern unsigned int drm_debug;
-extern bool drm_atomic;
 
 				/* Debugfs support */
 #if defined(CONFIG_DEBUG_FS)
@@ -1078,11 +964,13 @@ extern void drm_sysfs_hotplug_event(struct drm_device *dev);
 
 struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 				 struct device *parent);
+int drm_dev_init(struct drm_device *dev,
+		 struct drm_driver *driver,
+		 struct device *parent);
 void drm_dev_ref(struct drm_device *dev);
 void drm_dev_unref(struct drm_device *dev);
 int drm_dev_register(struct drm_device *dev, unsigned long flags);
 void drm_dev_unregister(struct drm_device *dev);
-int drm_dev_set_unique(struct drm_device *dev, const char *name);
 
 struct drm_minor *drm_minor_acquire(unsigned int minor_id);
 void drm_minor_release(struct drm_minor *minor);
@@ -1135,7 +1023,6 @@ extern int drm_pcie_get_max_link_width(struct drm_device *dev, u32 *mlw);
 
 /* platform section */
 extern int drm_platform_init(struct drm_driver *driver, struct platform_device *platform_device);
-extern int drm_platform_set_busid(struct drm_device *d, struct drm_master *m);
 
 /* returns true if currently okay to sleep */
 static __inline__ bool drm_can_sleep(void)
diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h
index 92c84e9ab09a..856a9c85a838 100644
--- a/include/drm/drm_atomic.h
+++ b/include/drm/drm_atomic.h
@@ -30,6 +30,12 @@
 
 #include <drm/drm_crtc.h>
 
+void drm_crtc_commit_put(struct drm_crtc_commit *commit);
+static inline void drm_crtc_commit_get(struct drm_crtc_commit *commit)
+{
+	kref_get(&commit->ref);
+}
+
 struct drm_atomic_state * __must_check
 drm_atomic_state_alloc(struct drm_device *dev);
 void drm_atomic_state_clear(struct drm_atomic_state *state);
@@ -71,7 +77,7 @@ static inline struct drm_crtc_state *
 drm_atomic_get_existing_crtc_state(struct drm_atomic_state *state,
 				   struct drm_crtc *crtc)
 {
-	return state->crtc_states[drm_crtc_index(crtc)];
+	return state->crtcs[drm_crtc_index(crtc)].state;
 }
 
 /**
@@ -86,7 +92,7 @@ static inline struct drm_plane_state *
 drm_atomic_get_existing_plane_state(struct drm_atomic_state *state,
 				    struct drm_plane *plane)
 {
-	return state->plane_states[drm_plane_index(plane)];
+	return state->planes[drm_plane_index(plane)].state;
 }
 
 /**
@@ -106,7 +112,43 @@ drm_atomic_get_existing_connector_state(struct drm_atomic_state *state,
 	if (index >= state->num_connector)
 		return NULL;
 
-	return state->connector_states[index];
+	return state->connectors[index].state;
+}
+
+/**
+ * __drm_atomic_get_current_plane_state - get current plane state
+ * @state: global atomic state object
+ * @plane: plane to grab
+ *
+ * This function returns the plane state for the given plane, either from
+ * @state, or if the plane isn't part of the atomic state update, from @plane.
+ * This is useful in atomic check callbacks, when drivers need to peek at, but
+ * not change, state of other planes, since it avoids threading an error code
+ * back up the call chain.
+ *
+ * WARNING:
+ *
+ * Note that this function is in general unsafe since it doesn't check for the
+ * required locking for access state structures. Drivers must ensure that it is
+ * safe to access the returned state structure through other means. One common
+ * example is when planes are fixed to a single CRTC, and the driver knows that
+ * the CRTC lock is held already. In that case holding the CRTC lock gives a
+ * read-lock on all planes connected to that CRTC. But if planes can be
+ * reassigned things get more tricky. In that case it's better to use
+ * drm_atomic_get_plane_state and wire up full error handling.
+ *
+ * Returns:
+ *
+ * Read-only pointer to the current plane state.
+ */
+static inline const struct drm_plane_state *
+__drm_atomic_get_current_plane_state(struct drm_atomic_state *state,
+				     struct drm_plane *plane)
+{
+	if (state->planes[drm_plane_index(plane)].state)
+		return state->planes[drm_plane_index(plane)].state;
+
+	return plane->state;
 }
 
 int __must_check
@@ -139,29 +181,39 @@ int __must_check drm_atomic_check_only(struct drm_atomic_state *state);
 int __must_check drm_atomic_commit(struct drm_atomic_state *state);
 int __must_check drm_atomic_nonblocking_commit(struct drm_atomic_state *state);
 
-#define for_each_connector_in_state(state, connector, connector_state, __i) \
+#define for_each_connector_in_state(__state, connector, connector_state, __i) \
 	for ((__i) = 0;							\
-	     (__i) < (state)->num_connector &&				\
-	     ((connector) = (state)->connectors[__i],			\
-	     (connector_state) = (state)->connector_states[__i], 1); 	\
+	     (__i) < (__state)->num_connector &&				\
+	     ((connector) = (__state)->connectors[__i].ptr,			\
+	     (connector_state) = (__state)->connectors[__i].state, 1); 	\
 	     (__i)++)							\
 		for_each_if (connector)
 
-#define for_each_crtc_in_state(state, crtc, crtc_state, __i)	\
+#define for_each_crtc_in_state(__state, crtc, crtc_state, __i)	\
 	for ((__i) = 0;						\
-	     (__i) < (state)->dev->mode_config.num_crtc &&	\
-	     ((crtc) = (state)->crtcs[__i],			\
-	     (crtc_state) = (state)->crtc_states[__i], 1);	\
+	     (__i) < (__state)->dev->mode_config.num_crtc &&	\
+	     ((crtc) = (__state)->crtcs[__i].ptr,			\
+	     (crtc_state) = (__state)->crtcs[__i].state, 1);	\
 	     (__i)++)						\
 		for_each_if (crtc_state)
 
-#define for_each_plane_in_state(state, plane, plane_state, __i)		\
+#define for_each_plane_in_state(__state, plane, plane_state, __i)		\
 	for ((__i) = 0;							\
-	     (__i) < (state)->dev->mode_config.num_total_plane &&	\
-	     ((plane) = (state)->planes[__i],				\
-	     (plane_state) = (state)->plane_states[__i], 1);		\
+	     (__i) < (__state)->dev->mode_config.num_total_plane &&	\
+	     ((plane) = (__state)->planes[__i].ptr,				\
+	     (plane_state) = (__state)->planes[__i].state, 1);		\
 	     (__i)++)							\
 		for_each_if (plane_state)
+
+/**
+ * drm_atomic_crtc_needs_modeset - compute combined modeset need
+ * @state: &drm_crtc_state for the CRTC
+ *
+ * To give drivers flexibility struct &drm_crtc_state has 3 booleans to track
+ * whether the state CRTC changed enough to need a full modeset cycle:
+ * connectors_changed, mode_changed and active_change. This helper simply
+ * combines these three to compute the overall need for a modeset for @state.
+ */
 static inline bool
 drm_atomic_crtc_needs_modeset(struct drm_crtc_state *state)
 {
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index d473dcc91f54..d86ae5dcd7b4 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -38,6 +38,7 @@ int drm_atomic_helper_check_planes(struct drm_device *dev,
 			       struct drm_atomic_state *state);
 int drm_atomic_helper_check(struct drm_device *dev,
 			    struct drm_atomic_state *state);
+void drm_atomic_helper_commit_tail(struct drm_atomic_state *state);
 int drm_atomic_helper_commit(struct drm_device *dev,
 			     struct drm_atomic_state *state,
 			     bool nonblock);
@@ -71,8 +72,15 @@ void drm_atomic_helper_commit_planes_on_crtc(struct drm_crtc_state *old_crtc_sta
 void drm_atomic_helper_disable_planes_on_crtc(struct drm_crtc *crtc,
 					      bool atomic);
 
-void drm_atomic_helper_swap_state(struct drm_device *dev,
-				  struct drm_atomic_state *state);
+void drm_atomic_helper_swap_state(struct drm_atomic_state *state,
+				  bool stall);
+
+/* nonblocking commit helpers */
+int drm_atomic_helper_setup_commit(struct drm_atomic_state *state,
+				   bool nonblock);
+void drm_atomic_helper_wait_for_dependencies(struct drm_atomic_state *state);
+void drm_atomic_helper_commit_hw_done(struct drm_atomic_state *state);
+void drm_atomic_helper_commit_cleanup_done(struct drm_atomic_state *state);
 
 /* implementations for legacy interfaces */
 int drm_atomic_helper_update_plane(struct drm_plane *plane,
@@ -147,9 +155,9 @@ void
 __drm_atomic_helper_connector_destroy_state(struct drm_connector_state *state);
 void drm_atomic_helper_connector_destroy_state(struct drm_connector *connector,
 					  struct drm_connector_state *state);
-void drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
-					u16 *red, u16 *green, u16 *blue,
-					uint32_t start, uint32_t size);
+int drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
+				       u16 *red, u16 *green, u16 *blue,
+				       uint32_t size);
 
 /**
  * drm_atomic_crtc_for_each_plane - iterate over planes currently attached to CRTC
@@ -159,7 +167,7 @@ void drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
  * This iterates over the current state, useful (for example) when applying
  * atomic state after it has been checked and swapped.  To iterate over the
  * planes which *will* be attached (for ->atomic_check()) see
- * drm_crtc_for_each_pending_plane()
+ * drm_atomic_crtc_state_for_each_plane().
  */
 #define drm_atomic_crtc_for_each_plane(plane, crtc) \
 	drm_for_each_plane_mask(plane, (crtc)->dev, (crtc)->state->plane_mask)
@@ -171,11 +179,31 @@ void drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
  *
  * Similar to drm_crtc_for_each_plane(), but iterates the planes that will be
  * attached if the specified state is applied.  Useful during (for example)
- * ->atomic_check() operations, to validate the incoming state
+ * ->atomic_check() operations, to validate the incoming state.
  */
 #define drm_atomic_crtc_state_for_each_plane(plane, crtc_state) \
 	drm_for_each_plane_mask(plane, (crtc_state)->state->dev, (crtc_state)->plane_mask)
 
+/**
+ * drm_crtc_atomic_state_for_each_plane_state - iterate over attached planes in new state
+ * @plane: the loop cursor
+ * @plane_state: loop cursor for the plane's state, must be const
+ * @crtc_state: the incoming crtc-state
+ *
+ * Similar to drm_crtc_for_each_plane(), but iterates the planes that will be
+ * attached if the specified state is applied.  Useful during (for example)
+ * ->atomic_check() operations, to validate the incoming state.
+ *
+ * Compared to just drm_atomic_crtc_state_for_each_plane() this also fills in a
+ * const plane_state. This is useful when a driver just wants to peek at other
+ * active planes on this crtc, but does not need to change it.
+ */
+#define drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) \
+	drm_for_each_plane_mask(plane, (crtc_state)->state->dev, (crtc_state)->plane_mask) \
+		for_each_if ((plane_state = \
+			      __drm_atomic_get_current_plane_state((crtc_state)->state, \
+								   plane)))
+
 /*
  * drm_atomic_plane_disabling - check whether a plane is being disabled
  * @plane: plane object
diff --git a/include/drm/drm_auth.h b/include/drm/drm_auth.h
new file mode 100644
index 000000000000..610223b0481b
--- /dev/null
+++ b/include/drm/drm_auth.h
@@ -0,0 +1,59 @@
+/*
+ * Internal Header for the Direct Rendering Manager
+ *
+ * Copyright 2016 Intel Corporation
+ *
+ * Author: Daniel Vetter <daniel.vetter@ffwll.ch>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _DRM_AUTH_H_
+#define _DRM_AUTH_H_
+
+/**
+ * struct drm_master - drm master structure
+ *
+ * @refcount: Refcount for this master object.
+ * @dev: Link back to the DRM device
+ * @unique: Unique identifier: e.g. busid. Protected by drm_global_mutex.
+ * @unique_len: Length of unique field. Protected by drm_global_mutex.
+ * @magic_map: Map of used authentication tokens. Protected by struct_mutex.
+ * @lock: DRI lock information.
+ * @driver_priv: Pointer to driver-private information.
+ *
+ * Note that master structures are only relevant for the legacy/primary device
+ * nodes, hence there can only be one per device, not one per drm_minor.
+ */
+struct drm_master {
+	struct kref refcount;
+	struct drm_device *dev;
+	char *unique;
+	int unique_len;
+	struct idr magic_map;
+	struct drm_lock_data lock;
+	void *driver_priv;
+};
+
+struct drm_master *drm_master_get(struct drm_master *master);
+void drm_master_put(struct drm_master **master);
+bool drm_is_current_master(struct drm_file *fpriv);
+
+#endif
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index d1559cd04e3d..3edeaf88ebc0 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -44,6 +44,7 @@ struct drm_file;
 struct drm_clip_rect;
 struct device_node;
 struct fence;
+struct edid;
 
 struct drm_mode_object {
 	uint32_t id;
@@ -253,6 +254,8 @@ struct drm_framebuffer {
 	int bits_per_pixel;
 	int flags;
 	uint32_t pixel_format; /* fourcc format */
+	int hot_x;
+	int hot_y;
 	struct list_head filp_head;
 };
 
@@ -314,6 +317,7 @@ struct drm_plane_helper_funcs;
  * 	update to ensure framebuffer cleanup isn't done too early
  * @adjusted_mode: for use by helpers and drivers to compute adjusted mode timings
  * @mode: current mode timings
+ * @mode_blob: &drm_property_blob for @mode
  * @degamma_lut: Lookup table for converting framebuffer pixel data
  *	before apply the conversion matrix
  * @ctm: Transformation matrix
@@ -478,8 +482,8 @@ struct drm_crtc_funcs {
 	 * going on, which should eventually be unified to just one set of
 	 * hooks.
 	 */
-	void (*gamma_set)(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
-			  uint32_t start, uint32_t size);
+	int (*gamma_set)(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
+			 uint32_t size);
 
 	/**
 	 * @destroy:
@@ -701,6 +705,32 @@ struct drm_crtc_funcs {
 				   const struct drm_crtc_state *state,
 				   struct drm_property *property,
 				   uint64_t *val);
+
+	/**
+	 * @late_register:
+	 *
+	 * This optional hook can be used to register additional userspace
+	 * interfaces attached to the crtc like debugfs interfaces.
+	 * It is called late in the driver load sequence from drm_dev_register().
+	 * Everything added from this callback should be unregistered in
+	 * the early_unregister callback.
+	 *
+	 * Returns:
+	 *
+	 * 0 on success, or a negative error code on failure.
+	 */
+	int (*late_register)(struct drm_crtc *crtc);
+
+	/**
+	 * @early_unregister:
+	 *
+	 * This optional hook should be used to unregister the additional
+	 * userspace interfaces attached to the crtc from
+	 * late_unregister(). It is called from drm_dev_unregister(),
+	 * early in the driver unload sequence to disable userspace access
+	 * before data structures are torndown.
+	 */
+	void (*early_unregister)(struct drm_crtc *crtc);
 };
 
 /**
@@ -708,6 +738,7 @@ struct drm_crtc_funcs {
  * @dev: parent DRM device
  * @port: OF node used by drm_of_find_possible_crtcs()
  * @head: list management
+ * @name: human readable name, can be overwritten by the driver
  * @mutex: per-CRTC locking
  * @base: base KMS object for ID tracking etc.
  * @primary: primary plane for this CRTC
@@ -724,9 +755,6 @@ struct drm_crtc_funcs {
  * @gamma_store: gamma ramp values
  * @helper_private: mid-layer private data
  * @properties: property tracking for this CRTC
- * @state: current atomic state for this CRTC
- * @acquire_ctx: per-CRTC implicit acquire context used by atomic drivers for
- * 	legacy IOCTLs
  *
  * Each CRTC may have one or more connectors associated with it.  This structure
  * allows the CRTC to be controlled.
@@ -738,12 +766,13 @@ struct drm_crtc {
 
 	char *name;
 
-	/*
-	 * crtc mutex
+	/**
+	 * @mutex:
 	 *
 	 * This provides a read lock for the overall crtc state (mode, dpms
 	 * state, ...) and a write lock for everything which can be update
-	 * without a full modeset (fb, cursor data, ...)
+	 * without a full modeset (fb, cursor data, crtc properties ...). Full
+	 * modeset also need to grab dev->mode_config.connection_mutex.
 	 */
 	struct drm_modeset_lock mutex;
 
@@ -753,6 +782,12 @@ struct drm_crtc {
 	struct drm_plane *primary;
 	struct drm_plane *cursor;
 
+	/**
+	 * @index: Position inside the mode_config.list, can be used as an array
+	 * index. It is invariant over the lifetime of the CRTC.
+	 */
+	unsigned index;
+
 	/* position of cursor plane on crtc */
 	int cursor_x;
 	int cursor_y;
@@ -779,11 +814,37 @@ struct drm_crtc {
 
 	struct drm_object_properties properties;
 
+	/**
+	 * @state:
+	 *
+	 * Current atomic state for this CRTC.
+	 */
 	struct drm_crtc_state *state;
 
-	/*
-	 * For legacy crtc IOCTLs so that atomic drivers can get at the locking
-	 * acquire context.
+	/**
+	 * @commit_list:
+	 *
+	 * List of &drm_crtc_commit structures tracking pending commits.
+	 * Protected by @commit_lock. This list doesn't hold its own full
+	 * reference, but burrows it from the ongoing commit. Commit entries
+	 * must be removed from this list once the commit is fully completed,
+	 * but before it's correspoding &drm_atomic_state gets destroyed.
+	 */
+	struct list_head commit_list;
+
+	/**
+	 * @commit_lock:
+	 *
+	 * Spinlock to protect @commit_list.
+	 */
+	spinlock_t commit_lock;
+
+	/**
+	 * @acquire_ctx:
+	 *
+	 * Per-CRTC implicit acquire context used by atomic drivers for legacy
+	 * IOCTLs, so that atomic drivers can get at the locking acquire
+	 * context.
 	 */
 	struct drm_modeset_acquire_ctx *acquire_ctx;
 };
@@ -926,6 +987,33 @@ struct drm_connector_funcs {
 			     uint64_t val);
 
 	/**
+	 * @late_register:
+	 *
+	 * This optional hook can be used to register additional userspace
+	 * interfaces attached to the connector, light backlight control, i2c,
+	 * DP aux or similar interfaces. It is called late in the driver load
+	 * sequence from drm_connector_register() when registering all the
+	 * core drm connector interfaces. Everything added from this callback
+	 * should be unregistered in the early_unregister callback.
+	 *
+	 * Returns:
+	 *
+	 * 0 on success, or a negative error code on failure.
+	 */
+	int (*late_register)(struct drm_connector *connector);
+
+	/**
+	 * @early_unregister:
+	 *
+	 * This optional hook should be used to unregister the additional
+	 * userspace interfaces attached to the connector from
+	 * late_unregister(). It is called from drm_connector_unregister(),
+	 * early in the driver unload sequence to disable userspace access
+	 * before data structures are torndown.
+	 */
+	void (*early_unregister)(struct drm_connector *connector);
+
+	/**
 	 * @destroy:
 	 *
 	 * Clean up connector resources. This is called at driver unload time
@@ -1069,6 +1157,32 @@ struct drm_encoder_funcs {
 	 * hotplugged in DRM.
 	 */
 	void (*destroy)(struct drm_encoder *encoder);
+
+	/**
+	 * @late_register:
+	 *
+	 * This optional hook can be used to register additional userspace
+	 * interfaces attached to the encoder like debugfs interfaces.
+	 * It is called late in the driver load sequence from drm_dev_register().
+	 * Everything added from this callback should be unregistered in
+	 * the early_unregister callback.
+	 *
+	 * Returns:
+	 *
+	 * 0 on success, or a negative error code on failure.
+	 */
+	int (*late_register)(struct drm_encoder *encoder);
+
+	/**
+	 * @early_unregister:
+	 *
+	 * This optional hook should be used to unregister the additional
+	 * userspace interfaces attached to the encoder from
+	 * late_unregister(). It is called from drm_dev_unregister(),
+	 * early in the driver unload sequence to disable userspace access
+	 * before data structures are torndown.
+	 */
+	void (*early_unregister)(struct drm_encoder *encoder);
 };
 
 #define DRM_CONNECTOR_MAX_ENCODER 3
@@ -1078,7 +1192,7 @@ struct drm_encoder_funcs {
  * @dev: parent DRM device
  * @head: list management
  * @base: base KMS object
- * @name: encoder name
+ * @name: human readable name, can be overwritten by the driver
  * @encoder_type: one of the %DRM_MODE_ENCODER_<foo> types in drm_mode.h
  * @possible_crtcs: bitmask of potential CRTC bindings
  * @possible_clones: bitmask of potential sibling encoders for cloning
@@ -1097,6 +1211,13 @@ struct drm_encoder {
 	struct drm_mode_object base;
 	char *name;
 	int encoder_type;
+
+	/**
+	 * @index: Position inside the mode_config.list, can be used as an array
+	 * index. It is invariant over the lifetime of the encoder.
+	 */
+	unsigned index;
+
 	uint32_t possible_crtcs;
 	uint32_t possible_clones;
 
@@ -1124,12 +1245,13 @@ struct drm_encoder {
  * @attr: sysfs attributes
  * @head: list management
  * @base: base KMS object
- * @name: connector name
+ * @name: human readable name, can be overwritten by the driver
  * @connector_type: one of the %DRM_MODE_CONNECTOR_<foo> types from drm_mode.h
  * @connector_type_id: index into connector type enum
  * @interlace_allowed: can this connector handle interlaced modes?
  * @doublescan_allowed: can this connector handle doublescan?
  * @stereo_allowed: can this connector handle stereo modes?
+ * @registered: is this connector exposed (registered) with userspace?
  * @modes: modes available on this connector (from fill_modes() + user)
  * @status: one of the drm_connector_status enums (connected, not, or unknown)
  * @probed_modes: list of modes derived directly from the display
@@ -1137,7 +1259,6 @@ struct drm_encoder {
  * @funcs: connector control functions
  * @edid_blob_ptr: DRM property containing EDID if present
  * @properties: property tracking for this connector
- * @path_blob_ptr: DRM blob property data for the DP MST path property
  * @polled: a %DRM_CONNECTOR_POLL_<foo> value for core driven polling
  * @dpms: current dpms state
  * @helper_private: mid-layer private data
@@ -1181,12 +1302,21 @@ struct drm_connector {
 	struct drm_mode_object base;
 
 	char *name;
-	int connector_id;
+
+	/**
+	 * @index: Compacted connector index, which matches the position inside
+	 * the mode_config.list for drivers not supporting hot-add/removing. Can
+	 * be used as an array index. It is invariant over the lifetime of the
+	 * connector.
+	 */
+	unsigned index;
+
 	int connector_type;
 	int connector_type_id;
 	bool interlace_allowed;
 	bool doublescan_allowed;
 	bool stereo_allowed;
+	bool registered;
 	struct list_head modes; /* list of modes on this connector */
 
 	enum drm_connector_status status;
@@ -1200,8 +1330,23 @@ struct drm_connector {
 	struct drm_property_blob *edid_blob_ptr;
 	struct drm_object_properties properties;
 
+	/**
+	 * @path_blob_ptr:
+	 *
+	 * DRM blob property data for the DP MST path property.
+	 */
 	struct drm_property_blob *path_blob_ptr;
 
+	/**
+	 * @tile_blob_ptr:
+	 *
+	 * DRM blob property data for the tile property (used mostly by DP MST).
+	 * This is meant for screens which are driven through separate display
+	 * pipelines represented by &drm_crtc, which might not be running with
+	 * genlocked clocks. For tiled panels which are genlocked, like
+	 * dual-link LVDS or dual-link DSI, the driver should try to not expose
+	 * the tiling and virtualize both &drm_crtc and &drm_plane if needed.
+	 */
 	struct drm_property_blob *tile_blob_ptr;
 
 	uint8_t polled; /* DRM_CONNECTOR_POLL_* */
@@ -1263,6 +1408,7 @@ struct drm_connector {
  *	plane (in 16.16)
  * @src_w: width of visible portion of plane (in 16.16)
  * @src_h: height of visible portion of plane (in 16.16)
+ * @rotation: rotation of the plane
  * @state: backpointer to global drm_atomic_state
  */
 struct drm_plane_state {
@@ -1490,6 +1636,31 @@ struct drm_plane_funcs {
 				   const struct drm_plane_state *state,
 				   struct drm_property *property,
 				   uint64_t *val);
+	/**
+	 * @late_register:
+	 *
+	 * This optional hook can be used to register additional userspace
+	 * interfaces attached to the plane like debugfs interfaces.
+	 * It is called late in the driver load sequence from drm_dev_register().
+	 * Everything added from this callback should be unregistered in
+	 * the early_unregister callback.
+	 *
+	 * Returns:
+	 *
+	 * 0 on success, or a negative error code on failure.
+	 */
+	int (*late_register)(struct drm_plane *plane);
+
+	/**
+	 * @early_unregister:
+	 *
+	 * This optional hook should be used to unregister the additional
+	 * userspace interfaces attached to the plane from
+	 * late_unregister(). It is called from drm_dev_unregister(),
+	 * early in the driver unload sequence to disable userspace access
+	 * before data structures are torndown.
+	 */
+	void (*early_unregister)(struct drm_plane *plane);
 };
 
 enum drm_plane_type {
@@ -1503,6 +1674,7 @@ enum drm_plane_type {
  * struct drm_plane - central DRM plane control structure
  * @dev: DRM device this plane belongs to
  * @head: for list management
+ * @name: human readable name, can be overwritten by the driver
  * @base: base mode object
  * @possible_crtcs: pipes this plane can be bound to
  * @format_types: array of formats supported by this plane
@@ -1516,6 +1688,7 @@ enum drm_plane_type {
  * @properties: property tracking for this plane
  * @type: type of plane (overlay, primary, cursor)
  * @state: current atomic state for this plane
+ * @helper_private: mid-layer private data
  */
 struct drm_plane {
 	struct drm_device *dev;
@@ -1523,6 +1696,13 @@ struct drm_plane {
 
 	char *name;
 
+	/**
+	 * @mutex:
+	 *
+	 * Protects modeset plane state, together with the mutex of &drm_crtc
+	 * this plane is linked to (when active, getting actived or getting
+	 * disabled).
+	 */
 	struct drm_modeset_lock mutex;
 
 	struct drm_mode_object base;
@@ -1543,6 +1723,12 @@ struct drm_plane {
 
 	enum drm_plane_type type;
 
+	/**
+	 * @index: Position inside the mode_config.list, can be used as an array
+	 * index. It is invariant over the lifetime of the plane.
+	 */
+	unsigned index;
+
 	const struct drm_plane_helper_funcs *helper_private;
 
 	struct drm_plane_state *state;
@@ -1694,18 +1880,136 @@ struct drm_bridge {
 };
 
 /**
+ * struct drm_crtc_commit - track modeset commits on a CRTC
+ *
+ * This structure is used to track pending modeset changes and atomic commit on
+ * a per-CRTC basis. Since updating the list should never block this structure
+ * is reference counted to allow waiters to safely wait on an event to complete,
+ * without holding any locks.
+ *
+ * It has 3 different events in total to allow a fine-grained synchronization
+ * between outstanding updates::
+ *
+ *	atomic commit thread			hardware
+ *
+ * 	write new state into hardware	---->	...
+ * 	signal hw_done
+ * 						switch to new state on next
+ * 	...					v/hblank
+ *
+ *	wait for buffers to show up		...
+ *
+ *	...					send completion irq
+ *						irq handler signals flip_done
+ *	cleanup old buffers
+ *
+ * 	signal cleanup_done
+ *
+ * 	wait for flip_done		<----
+ * 	clean up atomic state
+ *
+ * The important bit to know is that cleanup_done is the terminal event, but the
+ * ordering between flip_done and hw_done is entirely up to the specific driver
+ * and modeset state change.
+ *
+ * For an implementation of how to use this look at
+ * drm_atomic_helper_setup_commit() from the atomic helper library.
+ */
+struct drm_crtc_commit {
+	/**
+	 * @crtc:
+	 *
+	 * DRM CRTC for this commit.
+	 */
+	struct drm_crtc *crtc;
+
+	/**
+	 * @ref:
+	 *
+	 * Reference count for this structure. Needed to allow blocking on
+	 * completions without the risk of the completion disappearing
+	 * meanwhile.
+	 */
+	struct kref ref;
+
+	/**
+	 * @flip_done:
+	 *
+	 * Will be signaled when the hardware has flipped to the new set of
+	 * buffers. Signals at the same time as when the drm event for this
+	 * commit is sent to userspace, or when an out-fence is singalled. Note
+	 * that for most hardware, in most cases this happens after @hw_done is
+	 * signalled.
+	 */
+	struct completion flip_done;
+
+	/**
+	 * @hw_done:
+	 *
+	 * Will be signalled when all hw register changes for this commit have
+	 * been written out. Especially when disabling a pipe this can be much
+	 * later than than @flip_done, since that can signal already when the
+	 * screen goes black, whereas to fully shut down a pipe more register
+	 * I/O is required.
+	 *
+	 * Note that this does not need to include separately reference-counted
+	 * resources like backing storage buffer pinning, or runtime pm
+	 * management.
+	 */
+	struct completion hw_done;
+
+	/**
+	 * @cleanup_done:
+	 *
+	 * Will be signalled after old buffers have been cleaned up by calling
+	 * drm_atomic_helper_cleanup_planes(). Since this can only happen after
+	 * a vblank wait completed it might be a bit later. This completion is
+	 * useful to throttle updates and avoid hardware updates getting ahead
+	 * of the buffer cleanup too much.
+	 */
+	struct completion cleanup_done;
+
+	/**
+	 * @commit_entry:
+	 *
+	 * Entry on the per-CRTC commit_list. Protected by crtc->commit_lock.
+	 */
+	struct list_head commit_entry;
+
+	/**
+	 * @event:
+	 *
+	 * &drm_pending_vblank_event pointer to clean up private events.
+	 */
+	struct drm_pending_vblank_event *event;
+};
+
+struct __drm_planes_state {
+	struct drm_plane *ptr;
+	struct drm_plane_state *state;
+};
+
+struct __drm_crtcs_state {
+	struct drm_crtc *ptr;
+	struct drm_crtc_state *state;
+	struct drm_crtc_commit *commit;
+};
+
+struct __drm_connnectors_state {
+	struct drm_connector *ptr;
+	struct drm_connector_state *state;
+};
+
+/**
  * struct drm_atomic_state - the global state object for atomic updates
  * @dev: parent DRM device
  * @allow_modeset: allow full modeset
  * @legacy_cursor_update: hint to enforce legacy cursor IOCTL semantics
  * @legacy_set_config: Disable conflicting encoders instead of failing with -EINVAL.
- * @planes: pointer to array of plane pointers
- * @plane_states: pointer to array of plane states pointers
+ * @planes: pointer to array of structures with per-plane data
  * @crtcs: pointer to array of CRTC pointers
- * @crtc_states: pointer to array of CRTC states pointers
  * @num_connector: size of the @connectors and @connector_states arrays
- * @connectors: pointer to array of connector pointers
- * @connector_states: pointer to array of connector states pointers
+ * @connectors: pointer to array of structures with per-connector data
  * @acquire_ctx: acquire context for this atomic modeset state update
  */
 struct drm_atomic_state {
@@ -1713,15 +2017,20 @@ struct drm_atomic_state {
 	bool allow_modeset : 1;
 	bool legacy_cursor_update : 1;
 	bool legacy_set_config : 1;
-	struct drm_plane **planes;
-	struct drm_plane_state **plane_states;
-	struct drm_crtc **crtcs;
-	struct drm_crtc_state **crtc_states;
+	struct __drm_planes_state *planes;
+	struct __drm_crtcs_state *crtcs;
 	int num_connector;
-	struct drm_connector **connectors;
-	struct drm_connector_state **connector_states;
+	struct __drm_connnectors_state *connectors;
 
 	struct drm_modeset_acquire_ctx *acquire_ctx;
+
+	/**
+	 * @commit_work:
+	 *
+	 * Work item which can be used by the driver or helpers to execute the
+	 * commit without blocking.
+	 */
+	struct work_struct commit_work;
 };
 
 
@@ -2022,13 +2331,9 @@ struct drm_mode_config_funcs {
  * @connection_mutex: ww mutex protecting connector state and routing
  * @acquire_ctx: global implicit acquire context used by atomic drivers for
  * 	legacy IOCTLs
- * @idr_mutex: mutex for KMS ID allocation and management
- * @crtc_idr: main KMS ID tracking object
  * @fb_lock: mutex to protect fb state and lists
  * @num_fb: number of fbs available
  * @fb_list: list of framebuffers available
- * @num_connector: number of connectors on this device
- * @connector_list: list of connector objects
  * @num_encoder: number of encoders on this device
  * @encoder_list: list of encoder objects
  * @num_overlay_plane: number of overlay planes on this device
@@ -2045,24 +2350,16 @@ struct drm_mode_config_funcs {
  * @fb_base: base address of the framebuffer
  * @poll_enabled: track polling support for this device
  * @poll_running: track polling status for this device
+ * @delayed_event: track delayed poll uevent deliver for this device
  * @output_poll_work: delayed work for polling in process context
  * @property_blob_list: list of all the blob property objects
  * @blob_lock: mutex for blob property allocation and management
  * @*_property: core property tracking
- * @degamma_lut_property: LUT used to convert the framebuffer's colors to linear
- *	gamma
- * @degamma_lut_size_property: size of the degamma LUT as supported by the
- *	driver (read-only)
- * @ctm_property: Matrix used to convert colors after the lookup in the
- *	degamma LUT
- * @gamma_lut_property: LUT used to convert the colors, after the CSC matrix, to
- *	the gamma space of the connected screen (read-only)
- * @gamma_lut_size_property: size of the gamma LUT as supported by the driver
  * @preferred_depth: preferred RBG pixel depth, used by fb helpers
  * @prefer_shadow: hint to userspace to prefer shadow-fb rendering
- * @async_page_flip: does this device support async flips on the primary plane?
  * @cursor_width: hint to userspace for max cursor width
  * @cursor_height: hint to userspace for max cursor height
+ * @helper_private: mid-layer private data
  *
  * Core mode resource tracking structure.  All CRTC, encoders, and connectors
  * enumerated by the driver are added here, as are global properties.  Some
@@ -2072,17 +2369,46 @@ struct drm_mode_config {
 	struct mutex mutex; /* protects configuration (mode lists etc.) */
 	struct drm_modeset_lock connection_mutex; /* protects connector->encoder and encoder->crtc links */
 	struct drm_modeset_acquire_ctx *acquire_ctx; /* for legacy _lock_all() / _unlock_all() */
-	struct mutex idr_mutex; /* for IDR management */
-	struct idr crtc_idr; /* use this idr for all IDs, fb, crtc, connector, modes - just makes life easier */
-	struct idr tile_idr; /* use this idr for all IDs, fb, crtc, connector, modes - just makes life easier */
-	/* this is limited to one for now */
+
+	/**
+	 * @idr_mutex:
+	 *
+	 * Mutex for KMS ID allocation and management. Protects both @crtc_idr
+	 * and @tile_idr.
+	 */
+	struct mutex idr_mutex;
+
+	/**
+	 * @crtc_idr:
+	 *
+	 * Main KMS ID tracking object. Use this idr for all IDs, fb, crtc,
+	 * connector, modes - just makes life easier to have only one.
+	 */
+	struct idr crtc_idr;
+
+	/**
+	 * @tile_idr:
+	 *
+	 * Use this idr for allocating new IDs for tiled sinks like use in some
+	 * high-res DP MST screens.
+	 */
+	struct idr tile_idr;
 
 	struct mutex fb_lock; /* proctects global and per-file fb lists */
 	int num_fb;
 	struct list_head fb_list;
 
+	/**
+	 * @num_connector: Number of connectors on this device.
+	 */
 	int num_connector;
+	/**
+	 * @connector_ida: ID allocator for connector indices.
+	 */
 	struct ida connector_ida;
+	/**
+	 * @connector_list: List of connector objects.
+	 */
 	struct list_head connector_list;
 	int num_encoder;
 	struct list_head encoder_list;
@@ -2117,71 +2443,251 @@ struct drm_mode_config {
 
 	/* pointers to standard properties */
 	struct list_head property_blob_list;
+	/**
+	 * @edid_property: Default connector property to hold the EDID of the
+	 * currently connected sink, if any.
+	 */
 	struct drm_property *edid_property;
+	/**
+	 * @dpms_property: Default connector property to control the
+	 * connector's DPMS state.
+	 */
 	struct drm_property *dpms_property;
+	/**
+	 * @path_property: Default connector property to hold the DP MST path
+	 * for the port.
+	 */
 	struct drm_property *path_property;
+	/**
+	 * @tile_property: Default connector property to store the tile
+	 * position of a tiled screen, for sinks which need to be driven with
+	 * multiple CRTCs.
+	 */
 	struct drm_property *tile_property;
+	/**
+	 * @plane_type_property: Default plane property to differentiate
+	 * CURSOR, PRIMARY and OVERLAY legacy uses of planes.
+	 */
 	struct drm_property *plane_type_property;
+	/**
+	 * @rotation_property: Optional property for planes or CRTCs to specifiy
+	 * rotation.
+	 */
 	struct drm_property *rotation_property;
+	/**
+	 * @prop_src_x: Default atomic plane property for the plane source
+	 * position in the connected &drm_framebuffer.
+	 */
 	struct drm_property *prop_src_x;
+	/**
+	 * @prop_src_y: Default atomic plane property for the plane source
+	 * position in the connected &drm_framebuffer.
+	 */
 	struct drm_property *prop_src_y;
+	/**
+	 * @prop_src_w: Default atomic plane property for the plane source
+	 * position in the connected &drm_framebuffer.
+	 */
 	struct drm_property *prop_src_w;
+	/**
+	 * @prop_src_h: Default atomic plane property for the plane source
+	 * position in the connected &drm_framebuffer.
+	 */
 	struct drm_property *prop_src_h;
+	/**
+	 * @prop_crtc_x: Default atomic plane property for the plane destination
+	 * position in the &drm_crtc is is being shown on.
+	 */
 	struct drm_property *prop_crtc_x;
+	/**
+	 * @prop_crtc_y: Default atomic plane property for the plane destination
+	 * position in the &drm_crtc is is being shown on.
+	 */
 	struct drm_property *prop_crtc_y;
+	/**
+	 * @prop_crtc_w: Default atomic plane property for the plane destination
+	 * position in the &drm_crtc is is being shown on.
+	 */
 	struct drm_property *prop_crtc_w;
+	/**
+	 * @prop_crtc_h: Default atomic plane property for the plane destination
+	 * position in the &drm_crtc is is being shown on.
+	 */
 	struct drm_property *prop_crtc_h;
+	/**
+	 * @prop_fb_id: Default atomic plane property to specify the
+	 * &drm_framebuffer.
+	 */
 	struct drm_property *prop_fb_id;
+	/**
+	 * @prop_crtc_id: Default atomic plane property to specify the
+	 * &drm_crtc.
+	 */
 	struct drm_property *prop_crtc_id;
+	/**
+	 * @prop_active: Default atomic CRTC property to control the active
+	 * state, which is the simplified implementation for DPMS in atomic
+	 * drivers.
+	 */
 	struct drm_property *prop_active;
+	/**
+	 * @prop_mode_id: Default atomic CRTC property to set the mode for a
+	 * CRTC. A 0 mode implies that the CRTC is entirely disabled - all
+	 * connectors must be of and active must be set to disabled, too.
+	 */
 	struct drm_property *prop_mode_id;
 
-	/* DVI-I properties */
+	/**
+	 * @dvi_i_subconnector_property: Optional DVI-I property to
+	 * differentiate between analog or digital mode.
+	 */
 	struct drm_property *dvi_i_subconnector_property;
+	/**
+	 * @dvi_i_select_subconnector_property: Optional DVI-I property to
+	 * select between analog or digital mode.
+	 */
 	struct drm_property *dvi_i_select_subconnector_property;
 
-	/* TV properties */
+	/**
+	 * @tv_subconnector_property: Optional TV property to differentiate
+	 * between different TV connector types.
+	 */
 	struct drm_property *tv_subconnector_property;
+	/**
+	 * @tv_select_subconnector_property: Optional TV property to select
+	 * between different TV connector types.
+	 */
 	struct drm_property *tv_select_subconnector_property;
+	/**
+	 * @tv_mode_property: Optional TV property to select
+	 * the output TV mode.
+	 */
 	struct drm_property *tv_mode_property;
+	/**
+	 * @tv_left_margin_property: Optional TV property to set the left
+	 * margin.
+	 */
 	struct drm_property *tv_left_margin_property;
+	/**
+	 * @tv_right_margin_property: Optional TV property to set the right
+	 * margin.
+	 */
 	struct drm_property *tv_right_margin_property;
+	/**
+	 * @tv_top_margin_property: Optional TV property to set the right
+	 * margin.
+	 */
 	struct drm_property *tv_top_margin_property;
+	/**
+	 * @tv_bottom_margin_property: Optional TV property to set the right
+	 * margin.
+	 */
 	struct drm_property *tv_bottom_margin_property;
+	/**
+	 * @tv_brightness_property: Optional TV property to set the
+	 * brightness.
+	 */
 	struct drm_property *tv_brightness_property;
+	/**
+	 * @tv_contrast_property: Optional TV property to set the
+	 * contrast.
+	 */
 	struct drm_property *tv_contrast_property;
+	/**
+	 * @tv_flicker_reduction_property: Optional TV property to control the
+	 * flicker reduction mode.
+	 */
 	struct drm_property *tv_flicker_reduction_property;
+	/**
+	 * @tv_overscan_property: Optional TV property to control the overscan
+	 * setting.
+	 */
 	struct drm_property *tv_overscan_property;
+	/**
+	 * @tv_saturation_property: Optional TV property to set the
+	 * saturation.
+	 */
 	struct drm_property *tv_saturation_property;
+	/**
+	 * @tv_hue_property: Optional TV property to set the hue.
+	 */
 	struct drm_property *tv_hue_property;
 
-	/* Optional properties */
+	/**
+	 * @scaling_mode_property: Optional connector property to control the
+	 * upscaling, mostly used for built-in panels.
+	 */
 	struct drm_property *scaling_mode_property;
+	/**
+	 * @aspect_ratio_property: Optional connector property to control the
+	 * HDMI infoframe aspect ratio setting.
+	 */
 	struct drm_property *aspect_ratio_property;
+	/**
+	 * @dirty_info_property: Optional connector property to give userspace a
+	 * hint that the DIRTY_FB ioctl should be used.
+	 */
 	struct drm_property *dirty_info_property;
 
-	/* Optional color correction properties */
+	/**
+	 * @degamma_lut_property: Optional CRTC property to set the LUT used to
+	 * convert the framebuffer's colors to linear gamma.
+	 */
 	struct drm_property *degamma_lut_property;
+	/**
+	 * @degamma_lut_size_property: Optional CRTC property for the size of
+	 * the degamma LUT as supported by the driver (read-only).
+	 */
 	struct drm_property *degamma_lut_size_property;
+	/**
+	 * @ctm_property: Optional CRTC property to set the
+	 * matrix used to convert colors after the lookup in the
+	 * degamma LUT.
+	 */
 	struct drm_property *ctm_property;
+	/**
+	 * @gamma_lut_property: Optional CRTC property to set the LUT used to
+	 * convert the colors, after the CTM matrix, to the gamma space of the
+	 * connected screen.
+	 */
 	struct drm_property *gamma_lut_property;
+	/**
+	 * @gamma_lut_size_property: Optional CRTC property for the size of the
+	 * gamma LUT as supported by the driver (read-only).
+	 */
 	struct drm_property *gamma_lut_size_property;
 
-	/* properties for virtual machine layout */
+	/**
+	 * @suggested_x_property: Optional connector property with a hint for
+	 * the position of the output on the host's screen.
+	 */
 	struct drm_property *suggested_x_property;
+	/**
+	 * @suggested_y_property: Optional connector property with a hint for
+	 * the position of the output on the host's screen.
+	 */
 	struct drm_property *suggested_y_property;
 
 	/* dumb ioctl parameters */
 	uint32_t preferred_depth, prefer_shadow;
 
-	/* whether async page flip is supported or not */
+	/**
+	 * @async_page_flip: Does this device support async flips on the primary
+	 * plane?
+	 */
 	bool async_page_flip;
 
-	/* whether the driver supports fb modifiers */
+	/**
+	 * @allow_fb_modifiers:
+	 *
+	 * Whether the driver supports fb modifiers in the ADDFB2.1 ioctl call.
+	 */
 	bool allow_fb_modifiers;
 
 	/* cursor size */
 	uint32_t cursor_width, cursor_height;
+
+	struct drm_mode_config_helper_funcs *helper_private;
 };
 
 /**
@@ -2230,7 +2736,18 @@ int drm_crtc_init_with_planes(struct drm_device *dev,
 			      const struct drm_crtc_funcs *funcs,
 			      const char *name, ...);
 extern void drm_crtc_cleanup(struct drm_crtc *crtc);
-extern unsigned int drm_crtc_index(struct drm_crtc *crtc);
+
+/**
+ * drm_crtc_index - find the index of a registered CRTC
+ * @crtc: CRTC to find index for
+ *
+ * Given a registered CRTC, return the index of that CRTC within a DRM
+ * device's list of CRTCs.
+ */
+static inline unsigned int drm_crtc_index(struct drm_crtc *crtc)
+{
+	return crtc->index;
+}
 
 /**
  * drm_crtc_mask - find the mask of a registered CRTC
@@ -2244,47 +2761,36 @@ static inline uint32_t drm_crtc_mask(struct drm_crtc *crtc)
 	return 1 << drm_crtc_index(crtc);
 }
 
-extern void drm_connector_ida_init(void);
-extern void drm_connector_ida_destroy(void);
-extern int drm_connector_init(struct drm_device *dev,
-			      struct drm_connector *connector,
-			      const struct drm_connector_funcs *funcs,
-			      int connector_type);
+int drm_connector_init(struct drm_device *dev,
+		       struct drm_connector *connector,
+		       const struct drm_connector_funcs *funcs,
+		       int connector_type);
 int drm_connector_register(struct drm_connector *connector);
 void drm_connector_unregister(struct drm_connector *connector);
 
 extern void drm_connector_cleanup(struct drm_connector *connector);
 static inline unsigned drm_connector_index(struct drm_connector *connector)
 {
-	return connector->connector_id;
+	return connector->index;
 }
 
-/* helpers to {un}register all connectors from sysfs for device */
-extern int drm_connector_register_all(struct drm_device *dev);
-extern void drm_connector_unregister_all(struct drm_device *dev);
-
-extern int drm_bridge_add(struct drm_bridge *bridge);
-extern void drm_bridge_remove(struct drm_bridge *bridge);
-extern struct drm_bridge *of_drm_find_bridge(struct device_node *np);
-extern int drm_bridge_attach(struct drm_device *dev, struct drm_bridge *bridge);
-
-bool drm_bridge_mode_fixup(struct drm_bridge *bridge,
-			const struct drm_display_mode *mode,
-			struct drm_display_mode *adjusted_mode);
-void drm_bridge_disable(struct drm_bridge *bridge);
-void drm_bridge_post_disable(struct drm_bridge *bridge);
-void drm_bridge_mode_set(struct drm_bridge *bridge,
-			struct drm_display_mode *mode,
-			struct drm_display_mode *adjusted_mode);
-void drm_bridge_pre_enable(struct drm_bridge *bridge);
-void drm_bridge_enable(struct drm_bridge *bridge);
-
 extern __printf(5, 6)
 int drm_encoder_init(struct drm_device *dev,
 		     struct drm_encoder *encoder,
 		     const struct drm_encoder_funcs *funcs,
 		     int encoder_type, const char *name, ...);
-extern unsigned int drm_encoder_index(struct drm_encoder *encoder);
+
+/**
+ * drm_encoder_index - find the index of a registered encoder
+ * @encoder: encoder to find index for
+ *
+ * Given a registered encoder, return the index of that encoder within a DRM
+ * device's list of encoders.
+ */
+static inline unsigned int drm_encoder_index(struct drm_encoder *encoder)
+{
+	return encoder->index;
+}
 
 /**
  * drm_encoder_crtc_ok - can a given crtc drive a given encoder?
@@ -2315,17 +2821,24 @@ extern int drm_plane_init(struct drm_device *dev,
 			  const uint32_t *formats, unsigned int format_count,
 			  bool is_primary);
 extern void drm_plane_cleanup(struct drm_plane *plane);
-extern unsigned int drm_plane_index(struct drm_plane *plane);
+
+/**
+ * drm_plane_index - find the index of a registered plane
+ * @plane: plane to find index for
+ *
+ * Given a registered plane, return the index of that plane within a DRM
+ * device's list of planes.
+ */
+static inline unsigned int drm_plane_index(struct drm_plane *plane)
+{
+	return plane->index;
+}
 extern struct drm_plane * drm_plane_from_index(struct drm_device *dev, int idx);
 extern void drm_plane_force_disable(struct drm_plane *plane);
-extern int drm_plane_check_pixel_format(const struct drm_plane *plane,
-					u32 format);
 extern void drm_crtc_get_hv_timing(const struct drm_display_mode *mode,
 				   int *hdisplay, int *vdisplay);
-extern int drm_crtc_check_viewport(const struct drm_crtc *crtc,
-				   int x, int y,
-				   const struct drm_display_mode *mode,
-				   const struct drm_framebuffer *fb);
+extern int drm_crtc_force_disable(struct drm_crtc *crtc);
+extern int drm_crtc_force_disable_all(struct drm_device *dev);
 
 extern void drm_encoder_cleanup(struct drm_encoder *encoder);
 
@@ -2336,16 +2849,6 @@ extern const char *drm_get_dvi_i_subconnector_name(int val);
 extern const char *drm_get_dvi_i_select_name(int val);
 extern const char *drm_get_tv_subconnector_name(int val);
 extern const char *drm_get_tv_select_name(int val);
-extern void drm_fb_release(struct drm_file *file_priv);
-extern void drm_property_destroy_user_blobs(struct drm_device *dev,
-                                            struct drm_file *file_priv);
-extern bool drm_probe_ddc(struct i2c_adapter *adapter);
-extern struct edid *drm_get_edid(struct drm_connector *connector,
-				 struct i2c_adapter *adapter);
-extern struct edid *drm_get_edid_switcheroo(struct drm_connector *connector,
-					    struct i2c_adapter *adapter);
-extern struct edid *drm_edid_duplicate(const struct edid *edid);
-extern int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid);
 extern void drm_mode_config_init(struct drm_device *dev);
 extern void drm_mode_config_reset(struct drm_device *dev);
 extern void drm_mode_config_cleanup(struct drm_device *dev);
@@ -2369,13 +2872,6 @@ static inline bool drm_property_type_is(struct drm_property *property,
 	return property->flags & type;
 }
 
-static inline bool drm_property_type_valid(struct drm_property *property)
-{
-	if (property->flags & DRM_MODE_PROP_EXTENDED_TYPE)
-		return !(property->flags & DRM_MODE_PROP_LEGACY_TYPE);
-	return !!(property->flags & DRM_MODE_PROP_LEGACY_TYPE);
-}
-
 extern int drm_object_property_set_value(struct drm_mode_object *obj,
 					 struct drm_property *property,
 					 uint64_t val);
@@ -2433,86 +2929,15 @@ extern int drm_mode_create_scaling_mode_property(struct drm_device *dev);
 extern int drm_mode_create_aspect_ratio_property(struct drm_device *dev);
 extern int drm_mode_create_dirty_info_property(struct drm_device *dev);
 extern int drm_mode_create_suggested_offset_properties(struct drm_device *dev);
-extern bool drm_property_change_valid_get(struct drm_property *property,
-					 uint64_t value, struct drm_mode_object **ref);
-extern void drm_property_change_valid_put(struct drm_property *property,
-		struct drm_mode_object *ref);
 
 extern int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 					     struct drm_encoder *encoder);
 extern int drm_mode_crtc_set_gamma_size(struct drm_crtc *crtc,
 					 int gamma_size);
-extern struct drm_mode_object *drm_mode_object_find(struct drm_device *dev,
-		uint32_t id, uint32_t type);
-void drm_mode_object_reference(struct drm_mode_object *obj);
-void drm_mode_object_unreference(struct drm_mode_object *obj);
 
-/* IOCTLs */
-extern int drm_mode_getresources(struct drm_device *dev,
-				 void *data, struct drm_file *file_priv);
-extern int drm_mode_getplane_res(struct drm_device *dev, void *data,
-				   struct drm_file *file_priv);
-extern int drm_mode_getcrtc(struct drm_device *dev,
-			    void *data, struct drm_file *file_priv);
-extern int drm_mode_getconnector(struct drm_device *dev,
-			      void *data, struct drm_file *file_priv);
 extern int drm_mode_set_config_internal(struct drm_mode_set *set);
-extern int drm_mode_setcrtc(struct drm_device *dev,
-			    void *data, struct drm_file *file_priv);
-extern int drm_mode_getplane(struct drm_device *dev,
-			       void *data, struct drm_file *file_priv);
-extern int drm_mode_setplane(struct drm_device *dev,
-			       void *data, struct drm_file *file_priv);
-extern int drm_mode_cursor_ioctl(struct drm_device *dev,
-				void *data, struct drm_file *file_priv);
-extern int drm_mode_cursor2_ioctl(struct drm_device *dev,
-				void *data, struct drm_file *file_priv);
-extern int drm_mode_addfb(struct drm_device *dev,
-			  void *data, struct drm_file *file_priv);
-extern int drm_mode_addfb2(struct drm_device *dev,
-			   void *data, struct drm_file *file_priv);
+
 extern uint32_t drm_mode_legacy_fb_format(uint32_t bpp, uint32_t depth);
-extern int drm_mode_rmfb(struct drm_device *dev,
-			 void *data, struct drm_file *file_priv);
-extern int drm_mode_getfb(struct drm_device *dev,
-			  void *data, struct drm_file *file_priv);
-extern int drm_mode_dirtyfb_ioctl(struct drm_device *dev,
-				  void *data, struct drm_file *file_priv);
-
-extern int drm_mode_getproperty_ioctl(struct drm_device *dev,
-				      void *data, struct drm_file *file_priv);
-extern int drm_mode_getblob_ioctl(struct drm_device *dev,
-				  void *data, struct drm_file *file_priv);
-extern int drm_mode_createblob_ioctl(struct drm_device *dev,
-				     void *data, struct drm_file *file_priv);
-extern int drm_mode_destroyblob_ioctl(struct drm_device *dev,
-				      void *data, struct drm_file *file_priv);
-extern int drm_mode_connector_property_set_ioctl(struct drm_device *dev,
-					      void *data, struct drm_file *file_priv);
-extern int drm_mode_getencoder(struct drm_device *dev,
-			       void *data, struct drm_file *file_priv);
-extern int drm_mode_gamma_get_ioctl(struct drm_device *dev,
-				    void *data, struct drm_file *file_priv);
-extern int drm_mode_gamma_set_ioctl(struct drm_device *dev,
-				    void *data, struct drm_file *file_priv);
-extern u8 drm_match_cea_mode(const struct drm_display_mode *to_match);
-extern enum hdmi_picture_aspect drm_get_cea_aspect_ratio(const u8 video_code);
-extern bool drm_detect_hdmi_monitor(struct edid *edid);
-extern bool drm_detect_monitor_audio(struct edid *edid);
-extern bool drm_rgb_quant_range_selectable(struct edid *edid);
-extern int drm_mode_page_flip_ioctl(struct drm_device *dev,
-				    void *data, struct drm_file *file_priv);
-extern int drm_add_modes_noedid(struct drm_connector *connector,
-				int hdisplay, int vdisplay);
-extern void drm_set_preferred_mode(struct drm_connector *connector,
-				   int hpref, int vpref);
-
-extern int drm_edid_header_is_valid(const u8 *raw_edid);
-extern bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid,
-				 bool *edid_corrupt);
-extern bool drm_edid_is_valid(struct edid *edid);
-extern void drm_edid_get_monitor_name(struct edid *edid, char *name,
-				      int buflen);
 
 extern struct drm_tile_group *drm_mode_create_tile_group(struct drm_device *dev,
 							 char topology[8]);
@@ -2520,41 +2945,24 @@ extern struct drm_tile_group *drm_mode_get_tile_group(struct drm_device *dev,
 					       char topology[8]);
 extern void drm_mode_put_tile_group(struct drm_device *dev,
 				   struct drm_tile_group *tg);
-struct drm_display_mode *drm_mode_find_dmt(struct drm_device *dev,
-					   int hsize, int vsize, int fresh,
-					   bool rb);
 
-extern int drm_mode_create_dumb_ioctl(struct drm_device *dev,
-				      void *data, struct drm_file *file_priv);
-extern int drm_mode_mmap_dumb_ioctl(struct drm_device *dev,
-				    void *data, struct drm_file *file_priv);
-extern int drm_mode_destroy_dumb_ioctl(struct drm_device *dev,
-				      void *data, struct drm_file *file_priv);
-extern int drm_mode_obj_get_properties_ioctl(struct drm_device *dev, void *data,
-					     struct drm_file *file_priv);
-extern int drm_mode_obj_set_property_ioctl(struct drm_device *dev, void *data,
-					   struct drm_file *file_priv);
 extern int drm_mode_plane_set_obj_prop(struct drm_plane *plane,
 				       struct drm_property *property,
 				       uint64_t value);
-extern int drm_mode_atomic_ioctl(struct drm_device *dev,
-				 void *data, struct drm_file *file_priv);
-
-extern void drm_fb_get_bpp_depth(uint32_t format, unsigned int *depth,
-				 int *bpp);
-extern int drm_format_num_planes(uint32_t format);
-extern int drm_format_plane_cpp(uint32_t format, int plane);
-extern int drm_format_horz_chroma_subsampling(uint32_t format);
-extern int drm_format_vert_chroma_subsampling(uint32_t format);
-extern int drm_format_plane_width(int width, uint32_t format, int plane);
-extern int drm_format_plane_height(int height, uint32_t format, int plane);
-extern const char *drm_get_format_name(uint32_t format);
+
 extern struct drm_property *drm_mode_create_rotation_property(struct drm_device *dev,
 							      unsigned int supported_rotations);
 extern unsigned int drm_rotation_simplify(unsigned int rotation,
 					  unsigned int supported_rotations);
-
+extern void drm_crtc_enable_color_mgmt(struct drm_crtc *crtc,
+				       uint degamma_lut_size,
+				       bool has_ctm,
+				       uint gamma_lut_size);
 /* Helpers */
+struct drm_mode_object *drm_mode_object_find(struct drm_device *dev,
+					     uint32_t id, uint32_t type);
+void drm_mode_object_reference(struct drm_mode_object *obj);
+void drm_mode_object_unreference(struct drm_mode_object *obj);
 
 static inline struct drm_plane *drm_plane_find(struct drm_device *dev,
 		uint32_t id)
@@ -2720,4 +3128,50 @@ assert_drm_connector_list_read_locked(struct drm_mode_config *mode_config)
 	     &fb->head != (&(dev)->mode_config.fb_list);			\
 	     fb = list_next_entry(fb, head))
 
+/* drm_edid.c */
+bool drm_probe_ddc(struct i2c_adapter *adapter);
+struct edid *drm_get_edid(struct drm_connector *connector,
+			  struct i2c_adapter *adapter);
+struct edid *drm_get_edid_switcheroo(struct drm_connector *connector,
+				     struct i2c_adapter *adapter);
+struct edid *drm_edid_duplicate(const struct edid *edid);
+int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid);
+
+u8 drm_match_cea_mode(const struct drm_display_mode *to_match);
+enum hdmi_picture_aspect drm_get_cea_aspect_ratio(const u8 video_code);
+bool drm_detect_hdmi_monitor(struct edid *edid);
+bool drm_detect_monitor_audio(struct edid *edid);
+bool drm_rgb_quant_range_selectable(struct edid *edid);
+int drm_add_modes_noedid(struct drm_connector *connector,
+			 int hdisplay, int vdisplay);
+void drm_set_preferred_mode(struct drm_connector *connector,
+			    int hpref, int vpref);
+
+int drm_edid_header_is_valid(const u8 *raw_edid);
+bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid,
+			  bool *edid_corrupt);
+bool drm_edid_is_valid(struct edid *edid);
+void drm_edid_get_monitor_name(struct edid *edid, char *name,
+			       int buflen);
+struct drm_display_mode *drm_mode_find_dmt(struct drm_device *dev,
+					   int hsize, int vsize, int fresh,
+					   bool rb);
+
+/* drm_bridge.c */
+extern int drm_bridge_add(struct drm_bridge *bridge);
+extern void drm_bridge_remove(struct drm_bridge *bridge);
+extern struct drm_bridge *of_drm_find_bridge(struct device_node *np);
+extern int drm_bridge_attach(struct drm_device *dev, struct drm_bridge *bridge);
+
+bool drm_bridge_mode_fixup(struct drm_bridge *bridge,
+			const struct drm_display_mode *mode,
+			struct drm_display_mode *adjusted_mode);
+void drm_bridge_disable(struct drm_bridge *bridge);
+void drm_bridge_post_disable(struct drm_bridge *bridge);
+void drm_bridge_mode_set(struct drm_bridge *bridge,
+			struct drm_display_mode *mode,
+			struct drm_display_mode *adjusted_mode);
+void drm_bridge_pre_enable(struct drm_bridge *bridge);
+void drm_bridge_enable(struct drm_bridge *bridge);
+
 #endif /* __DRM_CRTC_H__ */
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index 97fa894d4ee2..4b37afa2b73b 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -48,9 +48,6 @@ extern bool drm_crtc_helper_set_mode(struct drm_crtc *crtc,
 				     struct drm_display_mode *mode,
 				     int x, int y,
 				     struct drm_framebuffer *old_fb);
-extern void drm_helper_crtc_enable_color_mgmt(struct drm_crtc *crtc,
-					      int degamma_lut_size,
-					      int gamma_lut_size);
 extern bool drm_helper_crtc_in_use(struct drm_crtc *crtc);
 extern bool drm_helper_encoder_in_use(struct drm_encoder *encoder);
 
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 9d03f167007b..63b8bd502444 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -622,6 +622,7 @@ u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SI
 #define DP_BRANCH_OUI_HEADER_SIZE	0xc
 #define DP_RECEIVER_CAP_SIZE		0xf
 #define EDP_PSR_RECEIVER_CAP_SIZE	2
+#define EDP_DISPLAY_CTL_CAP_SIZE	3
 
 void drm_dp_link_train_clock_recovery_delay(const u8 dpcd[DP_RECEIVER_CAP_SIZE]);
 void drm_dp_link_train_channel_eq_delay(const u8 dpcd[DP_RECEIVER_CAP_SIZE]);
@@ -656,6 +657,8 @@ struct edp_vsc_psr {
 #define EDP_VSC_PSR_UPDATE_RFB		(1<<1)
 #define EDP_VSC_PSR_CRC_VALUES_VALID	(1<<2)
 
+int drm_dp_psr_setup_time(const u8 psr_cap[EDP_PSR_RECEIVER_CAP_SIZE]);
+
 static inline int
 drm_dp_max_link_rate(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
 {
@@ -746,7 +749,14 @@ struct drm_dp_aux {
 	struct mutex hw_mutex;
 	ssize_t (*transfer)(struct drm_dp_aux *aux,
 			    struct drm_dp_aux_msg *msg);
-	unsigned i2c_nack_count, i2c_defer_count;
+	/**
+	 * @i2c_nack_count: Counts I2C NACKs, used for DP validation.
+	 */
+	unsigned i2c_nack_count;
+	/**
+	 * @i2c_defer_count: Counts I2C DEFERs, used for DP validation.
+	 */
+	unsigned i2c_defer_count;
 };
 
 ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset,
@@ -804,6 +814,7 @@ int drm_dp_link_power_up(struct drm_dp_aux *aux, struct drm_dp_link *link);
 int drm_dp_link_power_down(struct drm_dp_aux *aux, struct drm_dp_link *link);
 int drm_dp_link_configure(struct drm_dp_aux *aux, struct drm_dp_link *link);
 
+void drm_dp_aux_init(struct drm_dp_aux *aux);
 int drm_dp_aux_register(struct drm_dp_aux *aux);
 void drm_dp_aux_unregister(struct drm_dp_aux *aux);
 
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index fdb47051d549..003207670597 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -87,7 +87,15 @@ struct drm_dp_mst_port {
 	struct drm_connector *connector;
 	struct drm_dp_mst_topology_mgr *mgr;
 
-	struct edid *cached_edid; /* for DP logical ports - make tiling work */
+	/**
+	 * @cached_edid: for DP logical ports - make tiling work by ensuring
+	 * that the EDID for all connectors is read immediately.
+	 */
+	struct edid *cached_edid;
+	/**
+	 * @has_audio: Tracks whether the sink connector to this port is
+	 * audio-capable.
+	 */
 	bool has_audio;
 };
 
@@ -397,71 +405,154 @@ struct drm_dp_payload {
 
 /**
  * struct drm_dp_mst_topology_mgr - DisplayPort MST manager
- * @dev: device pointer for adding i2c devices etc.
- * @cbs: callbacks for connector addition and destruction.
- * @max_dpcd_transaction_bytes - maximum number of bytes to read/write in one go.
- * @aux: aux channel for the DP connector.
- * @max_payloads: maximum number of payloads the GPU can generate.
- * @conn_base_id: DRM connector ID this mgr is connected to.
- * @down_rep_recv: msg receiver state for down replies.
- * @up_req_recv: msg receiver state for up requests.
- * @lock: protects mst state, primary, dpcd.
- * @mst_state: if this manager is enabled for an MST capable port.
- * @mst_primary: pointer to the primary branch device.
- * @dpcd: cache of DPCD for primary port.
- * @pbn_div: PBN to slots divisor.
  *
  * This struct represents the toplevel displayport MST topology manager.
  * There should be one instance of this for every MST capable DP connector
  * on the GPU.
  */
 struct drm_dp_mst_topology_mgr {
-
+	/**
+	 * @dev: device pointer for adding i2c devices etc.
+	 */
 	struct device *dev;
+	/**
+	 * @cbs: callbacks for connector addition and destruction.
+	 */
 	const struct drm_dp_mst_topology_cbs *cbs;
+	/**
+	 * @max_dpcd_transaction_bytes: maximum number of bytes to read/write
+	 * in one go.
+	 */
 	int max_dpcd_transaction_bytes;
-	struct drm_dp_aux *aux; /* auxch for this topology mgr to use */
+	/**
+	 * @aux: AUX channel for the DP MST connector this topolgy mgr is
+	 * controlling.
+	 */
+	struct drm_dp_aux *aux;
+	/**
+	 * @max_payloads: maximum number of payloads the GPU can generate.
+	 */
 	int max_payloads;
+	/**
+	 * @conn_base_id: DRM connector ID this mgr is connected to. Only used
+	 * to build the MST connector path value.
+	 */
 	int conn_base_id;
 
-	/* only ever accessed from the workqueue - which should be serialised */
+	/**
+	 * @down_rep_recv: Message receiver state for down replies. This and
+	 * @up_req_recv are only ever access from the work item, which is
+	 * serialised.
+	 */
 	struct drm_dp_sideband_msg_rx down_rep_recv;
+	/**
+	 * @up_req_recv: Message receiver state for up requests. This and
+	 * @down_rep_recv are only ever access from the work item, which is
+	 * serialised.
+	 */
 	struct drm_dp_sideband_msg_rx up_req_recv;
 
-	/* pointer to info about the initial MST device */
-	struct mutex lock; /* protects mst_state + primary + dpcd */
+	/**
+	 * @lock: protects mst state, primary, dpcd.
+	 */
+	struct mutex lock;
 
+	/**
+	 * @mst_state: If this manager is enabled for an MST capable port. False
+	 * if no MST sink/branch devices is connected.
+	 */
 	bool mst_state;
+	/**
+	 * @mst_primary: Pointer to the primary/first branch device.
+	 */
 	struct drm_dp_mst_branch *mst_primary;
 
+	/**
+	 * @dpcd: Cache of DPCD for primary port.
+	 */
 	u8 dpcd[DP_RECEIVER_CAP_SIZE];
+	/**
+	 * @sink_count: Sink count from DEVICE_SERVICE_IRQ_VECTOR_ESI0.
+	 */
 	u8 sink_count;
+	/**
+	 * @pbn_div: PBN to slots divisor.
+	 */
 	int pbn_div;
+	/**
+	 * @total_slots: Total slots that can be allocated.
+	 */
 	int total_slots;
+	/**
+	 * @avail_slots: Still available slots that can be allocated.
+	 */
 	int avail_slots;
+	/**
+	 * @total_pbn: Total PBN count.
+	 */
 	int total_pbn;
 
-	/* messages to be transmitted */
-	/* qlock protects the upq/downq and in_progress,
-	   the mstb tx_slots and txmsg->state once they are queued */
+	/**
+	 * @qlock: protects @tx_msg_downq, the tx_slots in struct
+	 * &drm_dp_mst_branch and txmsg->state once they are queued
+	 */
 	struct mutex qlock;
+	/**
+	 * @tx_msg_downq: List of pending down replies.
+	 */
 	struct list_head tx_msg_downq;
-	bool tx_down_in_progress;
 
-	/* payload info + lock for it */
+	/**
+	 * @payload_lock: Protect payload information.
+	 */
 	struct mutex payload_lock;
+	/**
+	 * @proposed_vcpis: Array of pointers for the new VCPI allocation. The
+	 * VCPI structure itself is embedded into the corresponding
+	 * &drm_dp_mst_port structure.
+	 */
 	struct drm_dp_vcpi **proposed_vcpis;
+	/**
+	 * @payloads: Array of payloads.
+	 */
 	struct drm_dp_payload *payloads;
+	/**
+	 * @payload_mask: Elements of @payloads actually in use. Since
+	 * reallocation of active outputs isn't possible gaps can be created by
+	 * disabling outputs out of order compared to how they've been enabled.
+	 */
 	unsigned long payload_mask;
+	/**
+	 * @vcpi_mask: Similar to @payload_mask, but for @proposed_vcpis.
+	 */
 	unsigned long vcpi_mask;
 
+	/**
+	 * @tx_waitq: Wait to queue stall for the tx worker.
+	 */
 	wait_queue_head_t tx_waitq;
+	/**
+	 * @work: Probe work.
+	 */
 	struct work_struct work;
-
+	/**
+	 * @tx_work: Sideband transmit worker. This can nest within the main
+	 * @work worker for each transaction @work launches.
+	 */
 	struct work_struct tx_work;
 
+	/**
+	 * @destroy_connector_list: List of to be destroyed connectors.
+	 */
 	struct list_head destroy_connector_list;
+	/**
+	 * @destroy_connector_lock: Protects @connector_list.
+	 */
 	struct mutex destroy_connector_lock;
+	/**
+	 * @destroy_connector_work: Work item to destroy connectors. Needed to
+	 * avoid locking inversion.
+	 */
 	struct work_struct destroy_connector_work;
 };
 
diff --git a/include/drm/drm_fb_cma_helper.h b/include/drm/drm_fb_cma_helper.h
index fd0dde9f0a6d..f313211f8ed5 100644
--- a/include/drm/drm_fb_cma_helper.h
+++ b/include/drm/drm_fb_cma_helper.h
@@ -23,6 +23,7 @@ void drm_fbdev_cma_fini(struct drm_fbdev_cma *fbdev_cma);
 
 void drm_fbdev_cma_restore_mode(struct drm_fbdev_cma *fbdev_cma);
 void drm_fbdev_cma_hotplug_event(struct drm_fbdev_cma *fbdev_cma);
+void drm_fbdev_cma_set_suspend(struct drm_fbdev_cma *fbdev_cma, int state);
 int drm_fbdev_cma_create_with_funcs(struct drm_fb_helper *helper,
 	struct drm_fb_helper_surface_size *sizes,
 	const struct drm_framebuffer_funcs *funcs);
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index 5b4aa35026a3..db8d4780eaa2 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -212,17 +212,6 @@ struct drm_fb_helper {
 	 * needs to be reprobe when fbdev is in control again.
 	 */
 	bool delayed_hotplug;
-
-	/**
-	 * @atomic:
-	 *
-	 * Use atomic updates for restore_fbdev_mode(), etc.  This defaults to
-	 * true if driver has DRIVER_ATOMIC feature flag, but drivers can
-	 * override it to true after drm_fb_helper_init() if they support atomic
-	 * modeset but do not yet advertise DRIVER_ATOMIC (note that fb-helper
-	 * does not require ASYNC commits).
-	 */
-	bool atomic;
 };
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
diff --git a/include/drm/drm_fourcc.h b/include/drm/drm_fourcc.h
new file mode 100644
index 000000000000..7f90a396cf2b
--- /dev/null
+++ b/include/drm/drm_fourcc.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (c) 2016 Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ *
+ * Permission to use, copy, modify, distribute, and sell this software and its
+ * documentation for any purpose is hereby granted without fee, provided that
+ * the above copyright notice appear in all copies and that both that copyright
+ * notice and this permission notice appear in supporting documentation, and
+ * that the name of the copyright holders not be used in advertising or
+ * publicity pertaining to distribution of the software without specific,
+ * written prior permission.  The copyright holders make no representations
+ * about the suitability of this software for any purpose.  It is provided "as
+ * is" without express or implied warranty.
+ *
+ * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
+ * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO
+ * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR
+ * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
+ * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+ * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
+ * OF THIS SOFTWARE.
+ */
+#ifndef __DRM_FOURCC_H__
+#define __DRM_FOURCC_H__
+
+#include <linux/types.h>
+#include <uapi/drm/drm_fourcc.h>
+
+void drm_fb_get_bpp_depth(uint32_t format, unsigned int *depth, int *bpp);
+int drm_format_num_planes(uint32_t format);
+int drm_format_plane_cpp(uint32_t format, int plane);
+int drm_format_horz_chroma_subsampling(uint32_t format);
+int drm_format_vert_chroma_subsampling(uint32_t format);
+int drm_format_plane_width(int width, uint32_t format, int plane);
+int drm_format_plane_height(int height, uint32_t format, int plane);
+const char *drm_get_format_name(uint32_t format);
+
+#endif /* __DRM_FOURCC_H__ */
diff --git a/include/drm/drm_irq.h b/include/drm/drm_irq.h
new file mode 100644
index 000000000000..2401b14d301f
--- /dev/null
+++ b/include/drm/drm_irq.h
@@ -0,0 +1,183 @@
+/*
+ * Copyright 2016 Intel Corp.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _DRM_IRQ_H_
+#define _DRM_IRQ_H_
+
+#include <linux/seqlock.h>
+
+/**
+ * struct drm_pending_vblank_event - pending vblank event tracking
+ */
+struct drm_pending_vblank_event {
+	/**
+	 * @base: Base structure for tracking pending DRM events.
+	 */
+	struct drm_pending_event base;
+	/**
+	 * @pipe: drm_crtc_index() of the &drm_crtc this event is for.
+	 */
+	unsigned int pipe;
+	/**
+	 * @event: Actual event which will be sent to userspace.
+	 */
+	struct drm_event_vblank event;
+};
+
+/**
+ * struct drm_vblank_crtc - vblank tracking for a CRTC
+ *
+ * This structure tracks the vblank state for one CRTC.
+ *
+ * Note that for historical reasons - the vblank handling code is still shared
+ * with legacy/non-kms drivers - this is a free-standing structure not directly
+ * connected to struct &drm_crtc. But all public interface functions are taking
+ * a struct &drm_crtc to hide this implementation detail.
+ */
+struct drm_vblank_crtc {
+	/**
+	 * @dev: Pointer to the &drm_device.
+	 */
+	struct drm_device *dev;
+	/**
+	 * @queue: Wait queue for vblank waiters.
+	 */
+	wait_queue_head_t queue;	/**< VBLANK wait queue */
+	/**
+	 * @disable_timer: Disable timer for the delayed vblank disabling
+	 * hysteresis logic. Vblank disabling is controlled through the
+	 * drm_vblank_offdelay module option and the setting of the
+	 * max_vblank_count value in the &drm_device structure.
+	 */
+	struct timer_list disable_timer;
+
+	/**
+	 * @seqlock: Protect vblank count and time.
+	 */
+	seqlock_t seqlock;		/* protects vblank count and time */
+
+	/**
+	 * @count: Current software vblank counter.
+	 */
+	u32 count;
+	/**
+	 * @time: Vblank timestamp corresponding to @count.
+	 */
+	struct timeval time;
+
+	/**
+	 * @refcount: Number of users/waiters of the vblank interrupt. Only when
+	 * this refcount reaches 0 can the hardware interrupt be disabled using
+	 * @disable_timer.
+	 */
+	atomic_t refcount;		/* number of users of vblank interruptsper crtc */
+	/**
+	 * @last: Protected by dev->vbl_lock, used for wraparound handling.
+	 */
+	u32 last;
+	/**
+	 * @inmodeset: Tracks whether the vblank is disabled due to a modeset.
+	 * For legacy driver bit 2 additionally tracks whether an additional
+	 * temporary vblank reference has been acquired to paper over the
+	 * hardware counter resetting/jumping. KMS drivers should instead just
+	 * call drm_crtc_vblank_off() and drm_crtc_vblank_on(), which explicitly
+	 * save and restore the vblank count.
+	 */
+	unsigned int inmodeset;		/* Display driver is setting mode */
+	/**
+	 * @pipe: drm_crtc_index() of the &drm_crtc corresponding to this
+	 * structure.
+	 */
+	unsigned int pipe;
+	/**
+	 * @framedur_ns: Frame/Field duration in ns, used by
+	 * drm_calc_vbltimestamp_from_scanoutpos() and computed by
+	 * drm_calc_timestamping_constants().
+	 */
+	int framedur_ns;
+	/**
+	 * @linedur_ns: Line duration in ns, used by
+	 * drm_calc_vbltimestamp_from_scanoutpos() and computed by
+	 * drm_calc_timestamping_constants().
+	 */
+	int linedur_ns;
+	/**
+	 * @enabled: Tracks the enabling state of the corresponding &drm_crtc to
+	 * avoid double-disabling and hence corrupting saved state. Needed by
+	 * drivers not using atomic KMS, since those might go through their CRTC
+	 * disabling functions multiple times.
+	 */
+	bool enabled;
+};
+
+extern int drm_irq_install(struct drm_device *dev, int irq);
+extern int drm_irq_uninstall(struct drm_device *dev);
+
+extern int drm_vblank_init(struct drm_device *dev, unsigned int num_crtcs);
+extern int drm_wait_vblank(struct drm_device *dev, void *data,
+			   struct drm_file *filp);
+extern u32 drm_vblank_count(struct drm_device *dev, unsigned int pipe);
+extern u32 drm_crtc_vblank_count(struct drm_crtc *crtc);
+extern u32 drm_crtc_vblank_count_and_time(struct drm_crtc *crtc,
+					  struct timeval *vblanktime);
+extern void drm_crtc_send_vblank_event(struct drm_crtc *crtc,
+				       struct drm_pending_vblank_event *e);
+extern void drm_crtc_arm_vblank_event(struct drm_crtc *crtc,
+				      struct drm_pending_vblank_event *e);
+extern bool drm_handle_vblank(struct drm_device *dev, unsigned int pipe);
+extern bool drm_crtc_handle_vblank(struct drm_crtc *crtc);
+extern int drm_crtc_vblank_get(struct drm_crtc *crtc);
+extern void drm_crtc_vblank_put(struct drm_crtc *crtc);
+extern void drm_wait_one_vblank(struct drm_device *dev, unsigned int pipe);
+extern void drm_crtc_wait_one_vblank(struct drm_crtc *crtc);
+extern void drm_vblank_off(struct drm_device *dev, unsigned int pipe);
+extern void drm_vblank_on(struct drm_device *dev, unsigned int pipe);
+extern void drm_crtc_vblank_off(struct drm_crtc *crtc);
+extern void drm_crtc_vblank_reset(struct drm_crtc *crtc);
+extern void drm_crtc_vblank_on(struct drm_crtc *crtc);
+extern void drm_vblank_cleanup(struct drm_device *dev);
+extern u32 drm_accurate_vblank_count(struct drm_crtc *crtc);
+extern u32 drm_vblank_no_hw_counter(struct drm_device *dev, unsigned int pipe);
+
+extern int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev,
+						 unsigned int pipe, int *max_error,
+						 struct timeval *vblank_time,
+						 unsigned flags,
+						 const struct drm_display_mode *mode);
+extern void drm_calc_timestamping_constants(struct drm_crtc *crtc,
+					    const struct drm_display_mode *mode);
+
+/**
+ * drm_crtc_vblank_waitqueue - get vblank waitqueue for the CRTC
+ * @crtc: which CRTC's vblank waitqueue to retrieve
+ *
+ * This function returns a pointer to the vblank waitqueue for the CRTC.
+ * Drivers can use this to implement vblank waits using wait_event() and related
+ * functions.
+ */
+static inline wait_queue_head_t *drm_crtc_vblank_waitqueue(struct drm_crtc *crtc)
+{
+	return &crtc->dev->vblank[drm_crtc_index(crtc)].queue;
+}
+
+#endif
diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h
index a5ef2c7e40f8..cf0e7d89bcdf 100644
--- a/include/drm/drm_legacy.h
+++ b/include/drm/drm_legacy.h
@@ -1,6 +1,8 @@
 #ifndef __DRM_DRM_LEGACY_H__
 #define __DRM_DRM_LEGACY_H__
 
+#include <drm/drm_auth.h>
+
 /*
  * Legacy driver interfaces for the Direct Rendering Manager
  *
diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h
index 7a9840f8b38e..47ac92584d76 100644
--- a/include/drm/drm_mipi_dsi.h
+++ b/include/drm/drm_mipi_dsi.h
@@ -180,6 +180,8 @@ struct mipi_dsi_device {
 	unsigned long mode_flags;
 };
 
+#define MIPI_DSI_MODULE_PREFIX "mipi-dsi:"
+
 static inline struct mipi_dsi_device *to_mipi_dsi_device(struct device *dev)
 {
 	return container_of(dev, struct mipi_dsi_device, dev);
@@ -263,6 +265,7 @@ int mipi_dsi_dcs_set_column_address(struct mipi_dsi_device *dsi, u16 start,
 				    u16 end);
 int mipi_dsi_dcs_set_page_address(struct mipi_dsi_device *dsi, u16 start,
 				  u16 end);
+int mipi_dsi_dcs_set_tear_scanline(struct mipi_dsi_device *dsi, u16 scanline);
 int mipi_dsi_dcs_set_tear_off(struct mipi_dsi_device *dsi);
 int mipi_dsi_dcs_set_tear_on(struct mipi_dsi_device *dsi,
 			     enum mipi_dsi_dcs_tear_mode mode);
diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h
index 625966a906f2..ff481770d76b 100644
--- a/include/drm/drm_modes.h
+++ b/include/drm/drm_modes.h
@@ -169,6 +169,8 @@ enum drm_mode_status {
  *
  * The horizontal and vertical timings are defined per the following diagram.
  *
+ * ::
+ *
  *
  *               Active                 Front           Sync           Back
  *              Region                 Porch                          Porch
diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index d4619dc2eecb..b55f21857a98 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -736,6 +736,11 @@ struct drm_connector_helper_funcs {
 	 * inspect dynamic configuration state should instead use
 	 * @atomic_best_encoder.
 	 *
+	 * You can leave this function to NULL if the connector is only
+	 * attached to a single encoder and you are using the atomic helpers.
+	 * In this case, the core will call drm_atomic_helper_best_encoder()
+	 * for you.
+	 *
 	 * RETURNS:
 	 *
 	 * Encoder that should be used for the given connector and connector
@@ -752,8 +757,9 @@ struct drm_connector_helper_funcs {
 	 * need to select the best encoder depending upon the desired
 	 * configuration and can't select it statically.
 	 *
-	 * This function is used by drm_atomic_helper_check_modeset() and either
-	 * this or @best_encoder is required.
+	 * This function is used by drm_atomic_helper_check_modeset().
+	 * If it is not implemented, the core will fallback to @best_encoder
+	 * (or drm_atomic_helper_best_encoder() if @best_encoder is NULL).
 	 *
 	 * NOTE:
 	 *
@@ -925,4 +931,43 @@ static inline void drm_plane_helper_add(struct drm_plane *plane,
 	plane->helper_private = funcs;
 }
 
+/**
+ * struct drm_mode_config_helper_funcs - global modeset helper operations
+ *
+ * These helper functions are used by the atomic helpers.
+ */
+struct drm_mode_config_helper_funcs {
+	/**
+	 * @atomic_commit_tail:
+	 *
+	 * This hook is used by the default atomic_commit() hook implemented in
+	 * drm_atomic_helper_commit() together with the nonblocking commit
+	 * helpers (see drm_atomic_helper_setup_commit() for a starting point)
+	 * to implement blocking and nonblocking commits easily. It is not used
+	 * by the atomic helpers
+	 *
+	 * This hook should first commit the given atomic state to the hardware.
+	 * But drivers can add more waiting calls at the start of their
+	 * implementation, e.g. to wait for driver-internal request for implicit
+	 * syncing, before starting to commit the update to the hardware.
+	 *
+	 * After the atomic update is committed to the hardware this hook needs
+	 * to call drm_atomic_helper_commit_hw_done(). Then wait for the upate
+	 * to be executed by the hardware, for example using
+	 * drm_atomic_helper_wait_for_vblanks(), and then clean up the old
+	 * framebuffers using drm_atomic_helper_cleanup_planes().
+	 *
+	 * When disabling a CRTC this hook _must_ stall for the commit to
+	 * complete. Vblank waits don't work on disabled CRTC, hence the core
+	 * can't take care of this. And it also can't rely on the vblank event,
+	 * since that can be signalled already when the screen shows black,
+	 * which can happen much earlier than the last hardware access needed to
+	 * shut off the display pipeline completely.
+	 *
+	 * This hook is optional, the default implementation is
+	 * drm_atomic_helper_commit_tail().
+	 */
+	void (*atomic_commit_tail)(struct drm_atomic_state *state);
+};
+
 #endif
diff --git a/include/drm/drm_plane_helper.h b/include/drm/drm_plane_helper.h
index 4421f3f4ca8d..0e0c3573cce0 100644
--- a/include/drm/drm_plane_helper.h
+++ b/include/drm/drm_plane_helper.h
@@ -46,6 +46,7 @@ int drm_plane_helper_check_update(struct drm_plane *plane,
 				  struct drm_rect *src,
 				  struct drm_rect *dest,
 				  const struct drm_rect *clip,
+				  unsigned int rotation,
 				  int min_scale,
 				  int max_scale,
 				  bool can_position,
diff --git a/include/drm/drm_simple_kms_helper.h b/include/drm/drm_simple_kms_helper.h
new file mode 100644
index 000000000000..269039722f91
--- /dev/null
+++ b/include/drm/drm_simple_kms_helper.h
@@ -0,0 +1,94 @@
+/*
+ * Copyright (C) 2016 Noralf Trønnes
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_DRM_SIMPLE_KMS_HELPER_H
+#define __LINUX_DRM_SIMPLE_KMS_HELPER_H
+
+struct drm_simple_display_pipe;
+
+/**
+ * struct drm_simple_display_pipe_funcs - helper operations for a simple
+ *                                        display pipeline
+ */
+struct drm_simple_display_pipe_funcs {
+	/**
+	 * @enable:
+	 *
+	 * This function should be used to enable the pipeline.
+	 * It is called when the underlying crtc is enabled.
+	 * This hook is optional.
+	 */
+	void (*enable)(struct drm_simple_display_pipe *pipe,
+		       struct drm_crtc_state *crtc_state);
+	/**
+	 * @disable:
+	 *
+	 * This function should be used to disable the pipeline.
+	 * It is called when the underlying crtc is disabled.
+	 * This hook is optional.
+	 */
+	void (*disable)(struct drm_simple_display_pipe *pipe);
+
+	/**
+	 * @check:
+	 *
+	 * This function is called in the check phase of an atomic update,
+	 * specifically when the underlying plane is checked.
+	 * The simple display pipeline helpers already check that the plane is
+	 * not scaled, fills the entire visible area and is always enabled
+	 * when the crtc is also enabled.
+	 * This hook is optional.
+	 *
+	 * RETURNS:
+	 *
+	 * 0 on success, -EINVAL if the state or the transition can't be
+	 * supported, -ENOMEM on memory allocation failure and -EDEADLK if an
+	 * attempt to obtain another state object ran into a &drm_modeset_lock
+	 * deadlock.
+	 */
+	int (*check)(struct drm_simple_display_pipe *pipe,
+		     struct drm_plane_state *plane_state,
+		     struct drm_crtc_state *crtc_state);
+	/**
+	 * @update:
+	 *
+	 * This function is called when the underlying plane state is updated.
+	 * This hook is optional.
+	 */
+	void (*update)(struct drm_simple_display_pipe *pipe,
+		       struct drm_plane_state *plane_state);
+};
+
+/**
+ * struct drm_simple_display_pipe - simple display pipeline
+ * @crtc: CRTC control structure
+ * @plane: Plane control structure
+ * @encoder: Encoder control structure
+ * @connector: Connector control structure
+ * @funcs: Pipeline control functions (optional)
+ *
+ * Simple display pipeline with plane, crtc and encoder collapsed into one
+ * entity. It should be initialized by calling drm_simple_display_pipe_init().
+ */
+struct drm_simple_display_pipe {
+	struct drm_crtc crtc;
+	struct drm_plane plane;
+	struct drm_encoder encoder;
+	struct drm_connector *connector;
+
+	const struct drm_simple_display_pipe_funcs *funcs;
+};
+
+int drm_simple_display_pipe_init(struct drm_device *dev,
+			struct drm_simple_display_pipe *pipe,
+			const struct drm_simple_display_pipe_funcs *funcs,
+			const uint32_t *formats, unsigned int format_count,
+			struct drm_connector *connector);
+
+#endif /* __LINUX_DRM_SIMPLE_KMS_HELPER_H */
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index 595f85c392ac..b1755f8db36b 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -92,4 +92,7 @@ extern bool i915_gpu_turbo_disable(void);
 #define    I845_TSEG_SIZE_512K	(2 << 1)
 #define    I845_TSEG_SIZE_1M	(3 << 1)
 
+#define INTEL_BSM 0x5c
+#define   INTEL_BSM_MASK (0xFFFF << 20)
+
 #endif				/* _I915_DRM_H_ */
diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h
index 9e9bddaa58a5..f49edecd66a3 100644
--- a/include/drm/intel-gtt.h
+++ b/include/drm/intel-gtt.h
@@ -13,6 +13,9 @@ void intel_gmch_remove(void);
 bool intel_enable_gtt(void);
 
 void intel_gtt_chipset_flush(void);
+void intel_gtt_insert_page(dma_addr_t addr,
+			   unsigned int pg,
+			   unsigned int flags);
 void intel_gtt_insert_sg_entries(struct sg_table *st,
 				 unsigned int pg_start,
 				 unsigned int flags);
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 4cecb0b75b9c..6f2c59887ba6 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -173,7 +173,7 @@ struct ttm_tt;
  * @lru: List head for the lru list.
  * @ddestroy: List head for the delayed destroy list.
  * @swap: List head for swap LRU list.
- * @priv_flags: Flags describing buffer object internal state.
+ * @moving: Fence set when BO is moving
  * @vma_node: Address space manager node.
  * @offset: The current GPU offset, which can have different meanings
  * depending on the memory type. For SYSTEM type memory, it should be 0.
@@ -239,7 +239,7 @@ struct ttm_buffer_object {
 	 * Members protected by a bo reservation.
 	 */
 
-	unsigned long priv_flags;
+	struct fence *moving;
 
 	struct drm_vma_offset_node vma_node;
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 513f7f96b80a..4348d6d5877a 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -258,8 +258,10 @@ struct ttm_mem_type_manager_func {
  * reserved by the TTM vm system.
  * @io_reserve_lru: Optional lru list for unreserving io mem regions.
  * @io_reserve_fastpath: Only use bdev::driver::io_mem_reserve to obtain
+ * @move_lock: lock for move fence
  * static information. bdev::driver::io_mem_free is never used.
  * @lru: The lru list for this memory type.
+ * @move: The fence of the last pipelined move operation.
  *
  * This structure is used to identify and manage memory types for a device.
  * It's set up by the ttm_bo_driver::init_mem_type method.
@@ -286,6 +288,7 @@ struct ttm_mem_type_manager {
 	struct mutex io_reserve_mutex;
 	bool use_io_reserve_lru;
 	bool io_reserve_fastpath;
+	spinlock_t move_lock;
 
 	/*
 	 * Protected by @io_reserve_mutex:
@@ -298,6 +301,11 @@ struct ttm_mem_type_manager {
 	 */
 
 	struct list_head lru;
+
+	/*
+	 * Protected by @move_lock.
+	 */
+	struct fence *move;
 };
 
 /**
@@ -503,9 +511,6 @@ struct ttm_bo_global {
 
 #define TTM_NUM_MEM_TYPES 8
 
-#define TTM_BO_PRIV_FLAG_MOVING  0	/* Buffer object is moving and needs
-					   idling before CPU mapping */
-#define TTM_BO_PRIV_FLAG_MAX 1
 /**
  * struct ttm_bo_device - Buffer object driver device-specific data.
  *
@@ -979,6 +984,7 @@ extern int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
  *
  * @bo: A pointer to a struct ttm_buffer_object.
  * @evict: 1: This is an eviction. Don't try to pipeline.
+ * @interruptible: Sleep interruptible if waiting.
  * @no_wait_gpu: Return immediately if the GPU is busy.
  * @new_mem: struct ttm_mem_reg indicating where to move.
  *
@@ -993,7 +999,8 @@ extern int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
  */
 
 extern int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
-			      bool evict, bool no_wait_gpu,
+			      bool evict, bool interruptible,
+			      bool no_wait_gpu,
 			      struct ttm_mem_reg *new_mem);
 
 /**
@@ -1011,7 +1018,6 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  * @bo: A pointer to a struct ttm_buffer_object.
  * @fence: A fence object that signals when moving is complete.
  * @evict: This is an evict move. Don't return until the buffer is idle.
- * @no_wait_gpu: Return immediately if the GPU is busy.
  * @new_mem: struct ttm_mem_reg indicating where to move.
  *
  * Accelerated move function to be called when an accelerated move
@@ -1023,9 +1029,24 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  */
 
 extern int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
-				     struct fence *fence,
-				     bool evict, bool no_wait_gpu,
+				     struct fence *fence, bool evict,
 				     struct ttm_mem_reg *new_mem);
+
+/**
+ * ttm_bo_pipeline_move.
+ *
+ * @bo: A pointer to a struct ttm_buffer_object.
+ * @fence: A fence object that signals when moving is complete.
+ * @evict: This is an evict move. Don't return until the buffer is idle.
+ * @new_mem: struct ttm_mem_reg indicating where to move.
+ *
+ * Function for pipelining accelerated moves. Either free the memory
+ * immediately or hang it on a temporary buffer object.
+ */
+int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
+			 struct fence *fence, bool evict,
+			 struct ttm_mem_reg *new_mem);
+
 /**
  * ttm_io_prot
  *
diff --git a/include/dt-bindings/clock/exynos5410.h b/include/dt-bindings/clock/exynos5410.h
index 9b180f032e2d..85b467b3a207 100644
--- a/include/dt-bindings/clock/exynos5410.h
+++ b/include/dt-bindings/clock/exynos5410.h
@@ -1,33 +1,65 @@
+/*
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Copyright (c) 2016 Krzysztof Kozlowski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Device Tree binding constants for Exynos5421 clock controller.
+*/
+
 #ifndef _DT_BINDINGS_CLOCK_EXYNOS_5410_H
 #define _DT_BINDINGS_CLOCK_EXYNOS_5410_H
 
 /* core clocks */
-#define CLK_FIN_PLL 1
-#define CLK_FOUT_APLL 2
-#define CLK_FOUT_CPLL 3
-#define CLK_FOUT_MPLL 4
-#define CLK_FOUT_BPLL 5
-#define CLK_FOUT_KPLL 6
+#define CLK_FIN_PLL		1
+#define CLK_FOUT_APLL		2
+#define CLK_FOUT_CPLL		3
+#define CLK_FOUT_MPLL		4
+#define CLK_FOUT_BPLL		5
+#define CLK_FOUT_KPLL		6
 
 /* gate for special clocks (sclk) */
-#define CLK_SCLK_UART0 128
-#define CLK_SCLK_UART1 129
-#define CLK_SCLK_UART2 130
-#define CLK_SCLK_UART3 131
-#define CLK_SCLK_MMC0 132
-#define CLK_SCLK_MMC1 133
-#define CLK_SCLK_MMC2 134
+#define CLK_SCLK_UART0		128
+#define CLK_SCLK_UART1		129
+#define CLK_SCLK_UART2		130
+#define CLK_SCLK_UART3		131
+#define CLK_SCLK_MMC0		132
+#define CLK_SCLK_MMC1		133
+#define CLK_SCLK_MMC2		134
+#define CLK_SCLK_USBD300	150
+#define CLK_SCLK_USBD301	151
+#define CLK_SCLK_USBPHY300	152
+#define CLK_SCLK_USBPHY301	153
+#define CLK_SCLK_PWM		155
 
 /* gate clocks */
-#define CLK_UART0 257
-#define CLK_UART1 258
-#define CLK_UART2 259
-#define CLK_UART3 260
-#define CLK_MCT 315
-#define CLK_MMC0 351
-#define CLK_MMC1 352
-#define CLK_MMC2 353
+#define CLK_UART0		257
+#define CLK_UART1		258
+#define CLK_UART2		259
+#define CLK_I2C0		261
+#define CLK_I2C1		262
+#define CLK_I2C2		263
+#define CLK_I2C3		264
+#define CLK_USI0		265
+#define CLK_USI1		266
+#define CLK_USI2		267
+#define CLK_USI3		268
+#define CLK_UART3		260
+#define CLK_PWM			279
+#define CLK_MCT			315
+#define CLK_WDT			316
+#define CLK_RTC			317
+#define CLK_TMU			318
+#define CLK_MMC0		351
+#define CLK_MMC1		352
+#define CLK_MMC2		353
+#define CLK_USBH20		365
+#define CLK_USBD300		366
+#define CLK_USBD301		367
+#define CLK_SSS			471
 
-#define CLK_NR_CLKS 512
+#define CLK_NR_CLKS		512
 
 #endif /* _DT_BINDINGS_CLOCK_EXYNOS_5410_H */
diff --git a/include/dt-bindings/clock/exynos5433.h b/include/dt-bindings/clock/exynos5433.h
index 8e024fea26e7..4fa6bb2136e3 100644
--- a/include/dt-bindings/clock/exynos5433.h
+++ b/include/dt-bindings/clock/exynos5433.h
@@ -622,8 +622,9 @@
 #define CLK_SCLK_UFSUNIPRO		112
 #define CLK_SCLK_USBHOST30		113
 #define CLK_SCLK_USBDRD30		114
+#define CLK_PCIE			115
 
-#define FSYS_NR_CLK			115
+#define FSYS_NR_CLK			116
 
 /* CMU_G2D */
 #define CLK_MUX_ACLK_G2D_266_USER	1
diff --git a/include/dt-bindings/clock/gxbb-clkc.h b/include/dt-bindings/clock/gxbb-clkc.h
new file mode 100644
index 000000000000..f889d80246cb
--- /dev/null
+++ b/include/dt-bindings/clock/gxbb-clkc.h
@@ -0,0 +1,12 @@
+/*
+ * GXBB clock tree IDs
+ */
+
+#ifndef __GXBB_CLKC_H
+#define __GXBB_CLKC_H
+
+#define CLKID_CPUCLK		1
+#define CLKID_CLK81		12
+#define CLKID_ETH		36
+
+#endif /* __GXBB_CLKC_H */
diff --git a/include/dt-bindings/clock/hi6220-clock.h b/include/dt-bindings/clock/hi6220-clock.h
index 70ee3833a7a0..6b03c84f4278 100644
--- a/include/dt-bindings/clock/hi6220-clock.h
+++ b/include/dt-bindings/clock/hi6220-clock.h
@@ -55,8 +55,9 @@
 #define HI6220_TIMER7_PCLK	34
 #define HI6220_TIMER8_PCLK	35
 #define HI6220_UART0_PCLK	36
-
-#define HI6220_AO_NR_CLKS	37
+#define HI6220_RTC0_PCLK	37
+#define HI6220_RTC1_PCLK	38
+#define HI6220_AO_NR_CLKS	39
 
 /* clk in Hi6220 systrl */
 /* gate clock */
diff --git a/include/dt-bindings/clock/lpc32xx-clock.h b/include/dt-bindings/clock/lpc32xx-clock.h
index d41b6fea1450..e624d3a52798 100644
--- a/include/dt-bindings/clock/lpc32xx-clock.h
+++ b/include/dt-bindings/clock/lpc32xx-clock.h
@@ -48,6 +48,7 @@
 #define LPC32XX_CLK_PWM2	33
 #define LPC32XX_CLK_ADC		34
 #define LPC32XX_CLK_HCLK_PLL	35
+#define LPC32XX_CLK_PERIPH	36
 
 /* LPC32XX USB clocks */
 #define LPC32XX_USB_CLK_I2C	1
diff --git a/include/dt-bindings/clock/meson8b-clkc.h b/include/dt-bindings/clock/meson8b-clkc.h
index bd2720d58e0c..595a58d0969a 100644
--- a/include/dt-bindings/clock/meson8b-clkc.h
+++ b/include/dt-bindings/clock/meson8b-clkc.h
@@ -19,7 +19,9 @@
 #define CLKID_MALI		11
 #define CLKID_CPUCLK		12
 #define CLKID_ZERO		13
+#define CLKID_MPEG_SEL		14
+#define CLKID_MPEG_DIV		15
 
-#define CLK_NR_CLKS		(CLKID_ZERO + 1)
+#define CLK_NR_CLKS		(CLKID_MPEG_DIV + 1)
 
 #endif /* __MESON8B_CLKC_H */
diff --git a/include/dt-bindings/clock/r8a7792-clock.h b/include/dt-bindings/clock/r8a7792-clock.h
new file mode 100644
index 000000000000..9a8b392ceb00
--- /dev/null
+++ b/include/dt-bindings/clock/r8a7792-clock.h
@@ -0,0 +1,102 @@
+/*
+ * Copyright (C) 2016 Cogent Embedded, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_R8A7792_H__
+#define __DT_BINDINGS_CLOCK_R8A7792_H__
+
+/* CPG */
+#define R8A7792_CLK_MAIN		0
+#define R8A7792_CLK_PLL0		1
+#define R8A7792_CLK_PLL1		2
+#define R8A7792_CLK_PLL3		3
+#define R8A7792_CLK_LB			4
+#define R8A7792_CLK_QSPI		5
+#define R8A7792_CLK_Z			6
+
+/* MSTP0 */
+#define R8A7792_CLK_MSIOF0		0
+
+/* MSTP1 */
+#define R8A7792_CLK_JPU			6
+#define R8A7792_CLK_TMU1		11
+#define R8A7792_CLK_TMU3		21
+#define R8A7792_CLK_TMU2		22
+#define R8A7792_CLK_CMT0		24
+#define R8A7792_CLK_TMU0		25
+#define R8A7792_CLK_VSP1DU1		27
+#define R8A7792_CLK_VSP1DU0		28
+#define R8A7792_CLK_VSP1_SY		31
+
+/* MSTP2 */
+#define R8A7792_CLK_MSIOF1		8
+#define R8A7792_CLK_SYS_DMAC1		18
+#define R8A7792_CLK_SYS_DMAC0		19
+
+/* MSTP3 */
+#define R8A7792_CLK_TPU0		4
+#define R8A7792_CLK_SDHI0		14
+#define R8A7792_CLK_CMT1		29
+
+/* MSTP4 */
+#define R8A7792_CLK_IRQC		7
+
+/* MSTP5 */
+#define R8A7792_CLK_AUDIO_DMAC0		2
+#define R8A7792_CLK_THERMAL		22
+#define R8A7792_CLK_PWM			23
+
+/* MSTP7 */
+#define R8A7792_CLK_HSCIF1		16
+#define R8A7792_CLK_HSCIF0		17
+#define R8A7792_CLK_SCIF3		18
+#define R8A7792_CLK_SCIF2		19
+#define R8A7792_CLK_SCIF1		20
+#define R8A7792_CLK_SCIF0		21
+#define R8A7792_CLK_DU1			23
+#define R8A7792_CLK_DU0			24
+
+/* MSTP8 */
+#define R8A7792_CLK_VIN5		4
+#define R8A7792_CLK_VIN4		5
+#define R8A7792_CLK_VIN3		8
+#define R8A7792_CLK_VIN2		9
+#define R8A7792_CLK_VIN1		10
+#define R8A7792_CLK_VIN0		11
+#define R8A7792_CLK_ETHERAVB		12
+
+/* MSTP9 */
+#define R8A7792_CLK_GPIO7		4
+#define R8A7792_CLK_GPIO6		5
+#define R8A7792_CLK_GPIO5		7
+#define R8A7792_CLK_GPIO4		8
+#define R8A7792_CLK_GPIO3		9
+#define R8A7792_CLK_GPIO2		10
+#define R8A7792_CLK_GPIO1		11
+#define R8A7792_CLK_GPIO0		12
+#define R8A7792_CLK_GPIO11		13
+#define R8A7792_CLK_GPIO10		14
+#define R8A7792_CLK_CAN1		15
+#define R8A7792_CLK_CAN0		16
+#define R8A7792_CLK_QSPI_MOD		17
+#define R8A7792_CLK_GPIO9		19
+#define R8A7792_CLK_GPIO8		21
+#define R8A7792_CLK_I2C5		25
+#define R8A7792_CLK_IICDVFS		26
+#define R8A7792_CLK_I2C4		27
+#define R8A7792_CLK_I2C3		28
+#define R8A7792_CLK_I2C2		29
+#define R8A7792_CLK_I2C1		30
+#define R8A7792_CLK_I2C0		31
+
+/* MSTP10 */
+#define R8A7792_CLK_SSI_ALL		5
+#define R8A7792_CLK_SSI4		11
+#define R8A7792_CLK_SSI3		12
+
+#endif /* __DT_BINDINGS_CLOCK_R8A7792_H__ */
diff --git a/include/dt-bindings/clock/r8a7794-clock.h b/include/dt-bindings/clock/r8a7794-clock.h
index 4d3ecd626c1f..a3491ba2f6ec 100644
--- a/include/dt-bindings/clock/r8a7794-clock.h
+++ b/include/dt-bindings/clock/r8a7794-clock.h
@@ -67,7 +67,6 @@
 #define R8A7794_CLK_IRQC		7
 
 /* MSTP5 */
-#define R8A7794_CLK_THERMAL		22
 #define R8A7794_CLK_PWM			23
 
 /* MSTP7 */
diff --git a/include/dt-bindings/clock/r8a7796-cpg-mssr.h b/include/dt-bindings/clock/r8a7796-cpg-mssr.h
new file mode 100644
index 000000000000..1e5942695f0d
--- /dev/null
+++ b/include/dt-bindings/clock/r8a7796-cpg-mssr.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2016 Renesas Electronics Corp.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef __DT_BINDINGS_CLOCK_R8A7796_CPG_MSSR_H__
+#define __DT_BINDINGS_CLOCK_R8A7796_CPG_MSSR_H__
+
+#include <dt-bindings/clock/renesas-cpg-mssr.h>
+
+/* r8a7796 CPG Core Clocks */
+#define R8A7796_CLK_Z			0
+#define R8A7796_CLK_Z2			1
+#define R8A7796_CLK_ZR			2
+#define R8A7796_CLK_ZG			3
+#define R8A7796_CLK_ZTR			4
+#define R8A7796_CLK_ZTRD2		5
+#define R8A7796_CLK_ZT			6
+#define R8A7796_CLK_ZX			7
+#define R8A7796_CLK_S0D1		8
+#define R8A7796_CLK_S0D2		9
+#define R8A7796_CLK_S0D3		10
+#define R8A7796_CLK_S0D4		11
+#define R8A7796_CLK_S0D6		12
+#define R8A7796_CLK_S0D8		13
+#define R8A7796_CLK_S0D12		14
+#define R8A7796_CLK_S1D1		15
+#define R8A7796_CLK_S1D2		16
+#define R8A7796_CLK_S1D4		17
+#define R8A7796_CLK_S2D1		18
+#define R8A7796_CLK_S2D2		19
+#define R8A7796_CLK_S2D4		20
+#define R8A7796_CLK_S3D1		21
+#define R8A7796_CLK_S3D2		22
+#define R8A7796_CLK_S3D4		23
+#define R8A7796_CLK_LB			24
+#define R8A7796_CLK_CL			25
+#define R8A7796_CLK_ZB3			26
+#define R8A7796_CLK_ZB3D2		27
+#define R8A7796_CLK_ZB3D4		28
+#define R8A7796_CLK_CR			29
+#define R8A7796_CLK_CRD2		30
+#define R8A7796_CLK_SD0H		31
+#define R8A7796_CLK_SD0			32
+#define R8A7796_CLK_SD1H		33
+#define R8A7796_CLK_SD1			34
+#define R8A7796_CLK_SD2H		35
+#define R8A7796_CLK_SD2			36
+#define R8A7796_CLK_SD3H		37
+#define R8A7796_CLK_SD3			38
+#define R8A7796_CLK_SSP2		39
+#define R8A7796_CLK_SSP1		40
+#define R8A7796_CLK_SSPRS		41
+#define R8A7796_CLK_RPC			42
+#define R8A7796_CLK_RPCD2		43
+#define R8A7796_CLK_MSO			44
+#define R8A7796_CLK_CANFD		45
+#define R8A7796_CLK_HDMI		46
+#define R8A7796_CLK_CSI0		47
+#define R8A7796_CLK_CSIREF		48
+#define R8A7796_CLK_CP			49
+#define R8A7796_CLK_CPEX		50
+#define R8A7796_CLK_R			51
+#define R8A7796_CLK_OSC			52
+
+#endif /* __DT_BINDINGS_CLOCK_R8A7796_CPG_MSSR_H__ */
diff --git a/include/dt-bindings/clock/rk3228-cru.h b/include/dt-bindings/clock/rk3228-cru.h
index 5d43ed9b05ad..b27e2b1a65e3 100644
--- a/include/dt-bindings/clock/rk3228-cru.h
+++ b/include/dt-bindings/clock/rk3228-cru.h
@@ -52,6 +52,15 @@
 #define SCLK_EMMC_SAMPLE	121
 #define SCLK_VOP		122
 #define SCLK_HDMI_HDCP		123
+#define SCLK_MAC_SRC		124
+#define SCLK_MAC_EXTCLK		125
+#define SCLK_MAC		126
+#define SCLK_MAC_REFOUT		127
+#define SCLK_MAC_REF		128
+#define SCLK_MAC_RX		129
+#define SCLK_MAC_TX		130
+#define SCLK_MAC_PHY		131
+#define SCLK_MAC_OUT		132
 
 /* dclk gates */
 #define DCLK_VOP		190
@@ -61,6 +70,7 @@
 #define ACLK_DMAC		194
 #define ACLK_PERI		210
 #define ACLK_VOP		211
+#define ACLK_GMAC		212
 
 /* pclk gates */
 #define PCLK_GPIO0		320
@@ -82,8 +92,13 @@
 #define PCLK_PERI		363
 #define PCLK_HDMI_CTRL		364
 #define PCLK_HDMI_PHY		365
+#define PCLK_GMAC		367
 
 /* hclk gates */
+#define HCLK_I2S0_8CH		442
+#define HCLK_I2S1_8CH		443
+#define HCLK_I2S2_2CH		444
+#define HCLK_SPDIF_8CH		445
 #define HCLK_VOP		452
 #define HCLK_NANDC		453
 #define HCLK_SDMMC		456
diff --git a/include/dt-bindings/clock/stih407-clks.h b/include/dt-bindings/clock/stih407-clks.h
index 7af2b717b3b2..082edd9badfa 100644
--- a/include/dt-bindings/clock/stih407-clks.h
+++ b/include/dt-bindings/clock/stih407-clks.h
@@ -5,6 +5,10 @@
 #ifndef _DT_BINDINGS_CLK_STIH407
 #define _DT_BINDINGS_CLK_STIH407
 
+/* CLOCKGEN A0 */
+#define CLK_IC_LMI0		0
+#define CLK_IC_LMI1		1
+
 /* CLOCKGEN C0 */
 #define CLK_ICN_GPU		0
 #define CLK_FDMA		1
diff --git a/include/dt-bindings/clock/sun8i-h3-ccu.h b/include/dt-bindings/clock/sun8i-h3-ccu.h
new file mode 100644
index 000000000000..efb7ba2bd515
--- /dev/null
+++ b/include/dt-bindings/clock/sun8i-h3-ccu.h
@@ -0,0 +1,145 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _DT_BINDINGS_CLK_SUN8I_H3_H_
+#define _DT_BINDINGS_CLK_SUN8I_H3_H_
+
+#define CLK_CPUX		14
+
+#define CLK_BUS_CE		20
+#define CLK_BUS_DMA		21
+#define CLK_BUS_MMC0		22
+#define CLK_BUS_MMC1		23
+#define CLK_BUS_MMC2		24
+#define CLK_BUS_NAND		25
+#define CLK_BUS_DRAM		26
+#define CLK_BUS_EMAC		27
+#define CLK_BUS_TS		28
+#define CLK_BUS_HSTIMER		29
+#define CLK_BUS_SPI0		30
+#define CLK_BUS_SPI1		31
+#define CLK_BUS_OTG		32
+#define CLK_BUS_EHCI0		33
+#define CLK_BUS_EHCI1		34
+#define CLK_BUS_EHCI2		35
+#define CLK_BUS_EHCI3		36
+#define CLK_BUS_OHCI0		37
+#define CLK_BUS_OHCI1		38
+#define CLK_BUS_OHCI2		39
+#define CLK_BUS_OHCI3		40
+#define CLK_BUS_VE		41
+#define CLK_BUS_TCON0		42
+#define CLK_BUS_TCON1		43
+#define CLK_BUS_DEINTERLACE	44
+#define CLK_BUS_CSI		45
+#define CLK_BUS_TVE		46
+#define CLK_BUS_HDMI		47
+#define CLK_BUS_DE		48
+#define CLK_BUS_GPU		49
+#define CLK_BUS_MSGBOX		50
+#define CLK_BUS_SPINLOCK	51
+#define CLK_BUS_CODEC		52
+#define CLK_BUS_SPDIF		53
+#define CLK_BUS_PIO		54
+#define CLK_BUS_THS		55
+#define CLK_BUS_I2S0		56
+#define CLK_BUS_I2S1		57
+#define CLK_BUS_I2S2		58
+#define CLK_BUS_I2C0		59
+#define CLK_BUS_I2C1		60
+#define CLK_BUS_I2C2		61
+#define CLK_BUS_UART0		62
+#define CLK_BUS_UART1		63
+#define CLK_BUS_UART2		64
+#define CLK_BUS_UART3		65
+#define CLK_BUS_SCR		66
+#define CLK_BUS_EPHY		67
+#define CLK_BUS_DBG		68
+
+#define CLK_THS			69
+#define CLK_NAND		70
+#define CLK_MMC0		71
+#define CLK_MMC0_SAMPLE		72
+#define CLK_MMC0_OUTPUT		73
+#define CLK_MMC1		74
+#define CLK_MMC1_SAMPLE		75
+#define CLK_MMC1_OUTPUT		76
+#define CLK_MMC2		77
+#define CLK_MMC2_SAMPLE		78
+#define CLK_MMC2_OUTPUT		79
+#define CLK_TS			80
+#define CLK_CE			81
+#define CLK_SPI0		82
+#define CLK_SPI1		83
+#define CLK_I2S0		84
+#define CLK_I2S1		85
+#define CLK_I2S2		86
+#define CLK_SPDIF		87
+#define CLK_USB_PHY0		88
+#define CLK_USB_PHY1		89
+#define CLK_USB_PHY2		90
+#define CLK_USB_PHY3		91
+#define CLK_USB_OHCI0		92
+#define CLK_USB_OHCI1		93
+#define CLK_USB_OHCI2		94
+#define CLK_USB_OHCI3		95
+
+#define CLK_DRAM_VE		97
+#define CLK_DRAM_CSI		98
+#define CLK_DRAM_DEINTERLACE	99
+#define CLK_DRAM_TS		100
+#define CLK_DE			101
+#define CLK_TCON0		102
+#define CLK_TVE			103
+#define CLK_DEINTERLACE		104
+#define CLK_CSI_MISC		105
+#define CLK_CSI_SCLK		106
+#define CLK_CSI_MCLK		107
+#define CLK_VE			108
+#define CLK_AC_DIG		109
+#define CLK_AVS			110
+#define CLK_HDMI		111
+#define CLK_HDMI_DDC		112
+
+#define CLK_GPU			114
+
+#endif /* _DT_BINDINGS_CLK_SUN8I_H3_H_ */
diff --git a/include/dt-bindings/clock/tegra210-car.h b/include/dt-bindings/clock/tegra210-car.h
index bd3530e56d46..35288b20f2c9 100644
--- a/include/dt-bindings/clock/tegra210-car.h
+++ b/include/dt-bindings/clock/tegra210-car.h
@@ -308,7 +308,7 @@
 #define TEGRA210_CLK_CLK_OUT_3 279
 #define TEGRA210_CLK_BLINK 280
 /* 281 */
-/* 282 */
+#define TEGRA210_CLK_SOR1_SRC 282
 /* 283 */
 #define TEGRA210_CLK_XUSB_HOST_SRC 284
 #define TEGRA210_CLK_XUSB_FALCON_SRC 285
diff --git a/include/dt-bindings/memory/mt2701-larb-port.h b/include/dt-bindings/memory/mt2701-larb-port.h
new file mode 100644
index 000000000000..78f66786da91
--- /dev/null
+++ b/include/dt-bindings/memory/mt2701-larb-port.h
@@ -0,0 +1,85 @@
+/*
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Honghui Zhang <honghui.zhang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _MT2701_LARB_PORT_H_
+#define _MT2701_LARB_PORT_H_
+
+/*
+ * Mediatek m4u generation 1 such as mt2701 has flat m4u port numbers,
+ * the first port's id for larb[N] would be the last port's id of larb[N - 1]
+ * plus one while larb[0]'s first port number is 0. The definition of
+ * MT2701_M4U_ID_LARBx is following HW register spec.
+ * But m4u generation 2 like mt8173 have different port number, it use fixed
+ * offset for each larb, the first port's id for larb[N] would be (N * 32).
+ */
+#define LARB0_PORT_OFFSET		0
+#define LARB1_PORT_OFFSET		11
+#define LARB2_PORT_OFFSET		21
+#define LARB3_PORT_OFFSET		43
+
+#define MT2701_M4U_ID_LARB0(port)	((port) + LARB0_PORT_OFFSET)
+#define MT2701_M4U_ID_LARB1(port)	((port) + LARB1_PORT_OFFSET)
+#define MT2701_M4U_ID_LARB2(port)	((port) + LARB2_PORT_OFFSET)
+
+/* Port define for larb0 */
+#define MT2701_M4U_PORT_DISP_OVL_0		MT2701_M4U_ID_LARB0(0)
+#define MT2701_M4U_PORT_DISP_RDMA1		MT2701_M4U_ID_LARB0(1)
+#define MT2701_M4U_PORT_DISP_RDMA		MT2701_M4U_ID_LARB0(2)
+#define MT2701_M4U_PORT_DISP_WDMA		MT2701_M4U_ID_LARB0(3)
+#define MT2701_M4U_PORT_MM_CMDQ			MT2701_M4U_ID_LARB0(4)
+#define MT2701_M4U_PORT_MDP_RDMA		MT2701_M4U_ID_LARB0(5)
+#define MT2701_M4U_PORT_MDP_WDMA		MT2701_M4U_ID_LARB0(6)
+#define MT2701_M4U_PORT_MDP_ROTO		MT2701_M4U_ID_LARB0(7)
+#define MT2701_M4U_PORT_MDP_ROTCO		MT2701_M4U_ID_LARB0(8)
+#define MT2701_M4U_PORT_MDP_ROTVO		MT2701_M4U_ID_LARB0(9)
+#define MT2701_M4U_PORT_MDP_RDMA1		MT2701_M4U_ID_LARB0(10)
+
+/* Port define for larb1 */
+#define MT2701_M4U_PORT_VDEC_MC_EXT		MT2701_M4U_ID_LARB1(0)
+#define MT2701_M4U_PORT_VDEC_PP_EXT		MT2701_M4U_ID_LARB1(1)
+#define MT2701_M4U_PORT_VDEC_PPWRAP_EXT		MT2701_M4U_ID_LARB1(2)
+#define MT2701_M4U_PORT_VDEC_AVC_MV_EXT		MT2701_M4U_ID_LARB1(3)
+#define MT2701_M4U_PORT_VDEC_PRED_RD_EXT	MT2701_M4U_ID_LARB1(4)
+#define MT2701_M4U_PORT_VDEC_PRED_WR_EXT	MT2701_M4U_ID_LARB1(5)
+#define MT2701_M4U_PORT_VDEC_VLD_EXT		MT2701_M4U_ID_LARB1(6)
+#define MT2701_M4U_PORT_VDEC_VLD2_EXT		MT2701_M4U_ID_LARB1(7)
+#define MT2701_M4U_PORT_VDEC_TILE_EXT		MT2701_M4U_ID_LARB1(8)
+#define MT2701_M4U_PORT_VDEC_IMG_RESZ_EXT	MT2701_M4U_ID_LARB1(9)
+
+/* Port define for larb2 */
+#define MT2701_M4U_PORT_VENC_RCPU		MT2701_M4U_ID_LARB2(0)
+#define MT2701_M4U_PORT_VENC_REC_FRM		MT2701_M4U_ID_LARB2(1)
+#define MT2701_M4U_PORT_VENC_BSDMA		MT2701_M4U_ID_LARB2(2)
+#define MT2701_M4U_PORT_JPGENC_RDMA		MT2701_M4U_ID_LARB2(3)
+#define MT2701_M4U_PORT_VENC_LT_RCPU		MT2701_M4U_ID_LARB2(4)
+#define MT2701_M4U_PORT_VENC_LT_REC_FRM		MT2701_M4U_ID_LARB2(5)
+#define MT2701_M4U_PORT_VENC_LT_BSDMA		MT2701_M4U_ID_LARB2(6)
+#define MT2701_M4U_PORT_JPGDEC_BSDMA		MT2701_M4U_ID_LARB2(7)
+#define MT2701_M4U_PORT_VENC_SV_COMV		MT2701_M4U_ID_LARB2(8)
+#define MT2701_M4U_PORT_VENC_RD_COMV		MT2701_M4U_ID_LARB2(9)
+#define MT2701_M4U_PORT_JPGENC_BSDMA		MT2701_M4U_ID_LARB2(10)
+#define MT2701_M4U_PORT_VENC_CUR_LUMA		MT2701_M4U_ID_LARB2(11)
+#define MT2701_M4U_PORT_VENC_CUR_CHROMA		MT2701_M4U_ID_LARB2(12)
+#define MT2701_M4U_PORT_VENC_REF_LUMA		MT2701_M4U_ID_LARB2(13)
+#define MT2701_M4U_PORT_VENC_REF_CHROMA		MT2701_M4U_ID_LARB2(14)
+#define MT2701_M4U_PORT_IMG_RESZ		MT2701_M4U_ID_LARB2(15)
+#define MT2701_M4U_PORT_VENC_LT_SV_COMV		MT2701_M4U_ID_LARB2(16)
+#define MT2701_M4U_PORT_VENC_LT_RD_COMV		MT2701_M4U_ID_LARB2(17)
+#define MT2701_M4U_PORT_VENC_LT_CUR_LUMA	MT2701_M4U_ID_LARB2(18)
+#define MT2701_M4U_PORT_VENC_LT_CUR_CHROMA	MT2701_M4U_ID_LARB2(19)
+#define MT2701_M4U_PORT_VENC_LT_REF_LUMA	MT2701_M4U_ID_LARB2(20)
+#define MT2701_M4U_PORT_VENC_LT_REF_CHROMA	MT2701_M4U_ID_LARB2(21)
+#define MT2701_M4U_PORT_JPGDEC_WDMA		MT2701_M4U_ID_LARB2(22)
+
+#endif
diff --git a/include/dt-bindings/pinctrl/keystone.h b/include/dt-bindings/pinctrl/keystone.h
new file mode 100644
index 000000000000..7f97d776a8ff
--- /dev/null
+++ b/include/dt-bindings/pinctrl/keystone.h
@@ -0,0 +1,39 @@
+/*
+ * This header provides constants for Keystone pinctrl bindings.
+ *
+ * Copyright (C) 2016 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_PINCTRL_KEYSTONE_H
+#define _DT_BINDINGS_PINCTRL_KEYSTONE_H
+
+#define MUX_MODE0	0
+#define MUX_MODE1	1
+#define MUX_MODE2	2
+#define MUX_MODE3	3
+#define MUX_MODE4	4
+#define MUX_MODE5	5
+
+#define BUFFER_CLASS_B	(0 << 19)
+#define BUFFER_CLASS_C	(1 << 19)
+#define BUFFER_CLASS_D	(2 << 19)
+#define BUFFER_CLASS_E	(3 << 19)
+
+#define PULL_DISABLE	(1 << 16)
+#define PIN_PULLUP	(1 << 17)
+#define PIN_PULLDOWN	(0 << 17)
+
+#define KEYSTONE_IOPAD_OFFSET(pa, offset) (((pa) & 0xffff) - (offset))
+
+#define K2G_CORE_IOPAD(pa) KEYSTONE_IOPAD_OFFSET((pa), 0x1000)
+
+#endif
diff --git a/include/dt-bindings/power/r8a7792-sysc.h b/include/dt-bindings/power/r8a7792-sysc.h
new file mode 100644
index 000000000000..74f4a78e29aa
--- /dev/null
+++ b/include/dt-bindings/power/r8a7792-sysc.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2016 Cogent Embedded Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+#ifndef __DT_BINDINGS_POWER_R8A7792_SYSC_H__
+#define __DT_BINDINGS_POWER_R8A7792_SYSC_H__
+
+/*
+ * These power domain indices match the numbers of the interrupt bits
+ * representing the power areas in the various Interrupt Registers
+ * (e.g. SYSCISR, Interrupt Status Register)
+ */
+
+#define R8A7792_PD_CA15_CPU0		0
+#define R8A7792_PD_CA15_CPU1		1
+#define R8A7792_PD_CA15_SCU		12
+#define R8A7792_PD_SGX			20
+#define R8A7792_PD_IMP			24
+
+/* Always-on power area */
+#define R8A7792_PD_ALWAYS_ON		32
+
+#endif /* __DT_BINDINGS_POWER_R8A7792_SYSC_H__ */
diff --git a/include/dt-bindings/power/r8a7796-sysc.h b/include/dt-bindings/power/r8a7796-sysc.h
new file mode 100644
index 000000000000..5b4daab44daa
--- /dev/null
+++ b/include/dt-bindings/power/r8a7796-sysc.h
@@ -0,0 +1,36 @@
+/*
+ * Copyright (C) 2016 Glider bvba
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ */
+#ifndef __DT_BINDINGS_POWER_R8A7796_SYSC_H__
+#define __DT_BINDINGS_POWER_R8A7796_SYSC_H__
+
+/*
+ * These power domain indices match the numbers of the interrupt bits
+ * representing the power areas in the various Interrupt Registers
+ * (e.g. SYSCISR, Interrupt Status Register)
+ */
+
+#define R8A7796_PD_CA57_CPU0		 0
+#define R8A7796_PD_CA57_CPU1		 1
+#define R8A7796_PD_CA53_CPU0		 5
+#define R8A7796_PD_CA53_CPU1		 6
+#define R8A7796_PD_CA53_CPU2		 7
+#define R8A7796_PD_CA53_CPU3		 8
+#define R8A7796_PD_CA57_SCU		12
+#define R8A7796_PD_CR7			13
+#define R8A7796_PD_A3VC			14
+#define R8A7796_PD_3DG_A		17
+#define R8A7796_PD_3DG_B		18
+#define R8A7796_PD_CA53_SCU		21
+#define R8A7796_PD_A3IR			24
+#define R8A7796_PD_A2VC0		25
+#define R8A7796_PD_A2VC1		26
+
+/* Always-on power area */
+#define R8A7796_PD_ALWAYS_ON		32
+
+#endif /* __DT_BINDINGS_POWER_R8A7796_SYSC_H__ */
diff --git a/include/dt-bindings/reset/amlogic,meson-gxbb-reset.h b/include/dt-bindings/reset/amlogic,meson-gxbb-reset.h
new file mode 100644
index 000000000000..524d6077ac1b
--- /dev/null
+++ b/include/dt-bindings/reset/amlogic,meson-gxbb-reset.h
@@ -0,0 +1,210 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * BSD LICENSE
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef _DT_BINDINGS_AMLOGIC_MESON_GXBB_RESET_H
+#define _DT_BINDINGS_AMLOGIC_MESON_GXBB_RESET_H
+
+/*	RESET0					*/
+#define RESET_HIU			0
+/*					1	*/
+#define RESET_DOS_RESET			2
+#define RESET_DDR_TOP			3
+#define RESET_DCU_RESET			4
+#define RESET_VIU			5
+#define RESET_AIU			6
+#define RESET_VID_PLL_DIV		7
+/*					8	*/
+#define RESET_PMUX			9
+#define RESET_VENC			10
+#define RESET_ASSIST			11
+#define RESET_AFIFO2			12
+#define RESET_VCBUS			13
+/*					14	*/
+/*					15	*/
+#define RESET_GIC			16
+#define RESET_CAPB3_DECODE		17
+#define RESET_NAND_CAPB3		18
+#define RESET_HDMITX_CAPB3		19
+#define RESET_MALI_CAPB3		20
+#define RESET_DOS_CAPB3			21
+#define RESET_SYS_CPU_CAPB3		22
+#define RESET_CBUS_CAPB3		23
+#define RESET_AHB_CNTL			24
+#define RESET_AHB_DATA			25
+#define RESET_VCBUS_CLK81		26
+#define RESET_MMC			27
+#define RESET_MIPI_0			28
+#define RESET_MIPI_1			29
+#define RESET_MIPI_2			30
+#define RESET_MIPI_3			31
+/*	RESET1					*/
+#define RESET_CPPM			32
+#define RESET_DEMUX			33
+#define RESET_USB_OTG			34
+#define RESET_DDR			35
+#define RESET_AO_RESET			36
+#define RESET_BT656			37
+#define RESET_AHB_SRAM			38
+/*					39	*/
+#define RESET_PARSER			40
+#define RESET_BLKMV			41
+#define RESET_ISA			42
+#define RESET_ETHERNET			43
+#define RESET_SD_EMMC_A			44
+#define RESET_SD_EMMC_B			45
+#define RESET_SD_EMMC_C			46
+#define RESET_ROM_BOOT			47
+#define RESET_SYS_CPU_0			48
+#define RESET_SYS_CPU_1			49
+#define RESET_SYS_CPU_2			50
+#define RESET_SYS_CPU_3			51
+#define RESET_SYS_CPU_CORE_0		52
+#define RESET_SYS_CPU_CORE_1		53
+#define RESET_SYS_CPU_CORE_2		54
+#define RESET_SYS_CPU_CORE_3		55
+#define RESET_SYS_PLL_DIV		56
+#define RESET_SYS_CPU_AXI		57
+#define RESET_SYS_CPU_L2		58
+#define RESET_SYS_CPU_P			59
+#define RESET_SYS_CPU_MBIST		60
+/*					61	*/
+/*					62	*/
+/*					63	*/
+/*	RESET2					*/
+#define RESET_VD_RMEM			64
+#define RESET_AUDIN			65
+#define RESET_HDMI_TX			66
+/*					67	*/
+/*					68	*/
+/*					69	*/
+#define RESET_GE2D			70
+#define RESET_PARSER_REG		71
+#define RESET_PARSER_FETCH		72
+#define RESET_PARSER_CTL		73
+#define RESET_PARSER_TOP		74
+/*					75	*/
+/*					76	*/
+#define RESET_AO_CPU_RESET		77
+#define RESET_MALI			78
+#define RESET_HDMI_SYSTEM_RESET		79
+/*					80-95	*/
+/*	RESET3					*/
+#define RESET_RING_OSCILLATOR		96
+#define RESET_SYS_CPU			97
+#define RESET_EFUSE			98
+#define RESET_SYS_CPU_BVCI		99
+#define RESET_AIFIFO			100
+#define RESET_TVFE			101
+#define RESET_AHB_BRIDGE_CNTL		102
+/*					103	*/
+#define RESET_AUDIO_DAC			104
+#define RESET_DEMUX_TOP			105
+#define RESET_DEMUX_DES			106
+#define RESET_DEMUX_S2P_0		107
+#define RESET_DEMUX_S2P_1		108
+#define RESET_DEMUX_RESET_0		109
+#define RESET_DEMUX_RESET_1		110
+#define RESET_DEMUX_RESET_2		111
+/*					112-127	*/
+/*	RESET4					*/
+/*					128	*/
+/*					129	*/
+/*					130	*/
+/*					131	*/
+#define RESET_DVIN_RESET		132
+#define RESET_RDMA			133
+#define RESET_VENCI			134
+#define RESET_VENCP			135
+/*					136	*/
+#define RESET_VDAC			137
+#define RESET_RTC			138
+/*					139	*/
+#define RESET_VDI6			140
+#define RESET_VENCL			141
+#define RESET_I2C_MASTER_2		142
+#define RESET_I2C_MASTER_1		143
+/*					144-159	*/
+/*	RESET5					*/
+/*					160-191	*/
+/*	RESET6					*/
+#define RESET_PERIPHS_GENERAL		192
+#define RESET_PERIPHS_SPICC		193
+#define RESET_PERIPHS_SMART_CARD	194
+#define RESET_PERIPHS_SAR_ADC		195
+#define RESET_PERIPHS_I2C_MASTER_0	196
+#define RESET_SANA			197
+/*					198	*/
+#define RESET_PERIPHS_STREAM_INTERFACE	199
+#define RESET_PERIPHS_SDIO		200
+#define RESET_PERIPHS_UART_0		201
+#define RESET_PERIPHS_UART_1_2		202
+#define RESET_PERIPHS_ASYNC_0		203
+#define RESET_PERIPHS_ASYNC_1		204
+#define RESET_PERIPHS_SPI_0		205
+#define RESET_PERIPHS_SDHC		206
+#define RESET_UART_SLIP			207
+/*					208-223	*/
+/*	RESET7					*/
+#define RESET_USB_DDR_0			224
+#define RESET_USB_DDR_1			225
+#define RESET_USB_DDR_2			226
+#define RESET_USB_DDR_3			227
+/*					228	*/
+#define RESET_DEVICE_MMC_ARB		229
+/*					230	*/
+#define RESET_VID_LOCK			231
+#define RESET_A9_DMC_PIPEL		232
+/*					233-255	*/
+
+#endif
diff --git a/include/dt-bindings/reset/amlogic,meson8b-reset.h b/include/dt-bindings/reset/amlogic,meson8b-reset.h
new file mode 100644
index 000000000000..614aff2c7aff
--- /dev/null
+++ b/include/dt-bindings/reset/amlogic,meson8b-reset.h
@@ -0,0 +1,175 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * BSD LICENSE
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef _DT_BINDINGS_AMLOGIC_MESON8B_RESET_H
+#define _DT_BINDINGS_AMLOGIC_MESON8B_RESET_H
+
+/*	RESET0					*/
+#define RESET_HIU			0
+#define RESET_VLD			1
+#define RESET_IQIDCT			2
+#define RESET_MC			3
+/*					8	*/
+#define RESET_VIU			5
+#define RESET_AIU			6
+#define RESET_MCPU			7
+#define RESET_CCPU			8
+#define RESET_PMUX			9
+#define RESET_VENC			10
+#define RESET_ASSIST			11
+#define RESET_AFIFO2			12
+#define RESET_MDEC			13
+#define RESET_VLD_PART			14
+#define RESET_VIFIFO			15
+/*					16-31	*/
+/*	RESET1					*/
+/*					32	*/
+#define RESET_DEMUX			33
+#define RESET_USB_OTG			34
+#define RESET_DDR			35
+#define RESET_VDAC_1			36
+#define RESET_BT656			37
+#define RESET_AHB_SRAM			38
+#define RESET_AHB_BRIDGE		39
+#define RESET_PARSER			40
+#define RESET_BLKMV			41
+#define RESET_ISA			42
+#define RESET_ETHERNET			43
+#define RESET_ABUF			44
+#define RESET_AHB_DATA			45
+#define RESET_AHB_CNTL			46
+#define RESET_ROM_BOOT			47
+/*					48-63	*/
+/*	RESET2					*/
+#define RESET_VD_RMEM			64
+#define RESET_AUDIN			65
+#define RESET_DBLK			66
+#define RESET_PIC_DC			66
+#define RESET_PSC			66
+#define RESET_NAND			66
+#define RESET_GE2D			70
+#define RESET_PARSER_REG		71
+#define RESET_PARSER_FETCH		72
+#define RESET_PARSER_CTL		73
+#define RESET_PARSER_TOP		74
+#define RESET_HDMI_APB			75
+#define RESET_AUDIO_APB			76
+#define RESET_MEDIA_CPU			77
+#define RESET_MALI			78
+#define RESET_HDMI_SYSTEM_RESET		79
+/*					80-95	*/
+/*	RESET3					*/
+#define RESET_RING_OSCILLATOR		96
+#define RESET_SYS_CPU_0			97
+#define RESET_EFUSE			98
+#define RESET_SYS_CPU_BVCI		99
+#define RESET_AIFIFO			100
+#define RESET_AUDIO_PLL_MODULATOR	101
+#define RESET_AHB_BRIDGE_CNTL		102
+#define RESET_SYS_CPU_1			103
+#define RESET_AUDIO_DAC			104
+#define RESET_DEMUX_TOP			105
+#define RESET_DEMUX_DES			106
+#define RESET_DEMUX_S2P_0		107
+#define RESET_DEMUX_S2P_1		108
+#define RESET_DEMUX_RESET_0		109
+#define RESET_DEMUX_RESET_1		110
+#define RESET_DEMUX_RESET_2		111
+/*					112-127	*/
+/*	RESET4					*/
+#define RESET_PL310			128
+#define RESET_A5_APB			129
+#define RESET_A5_AXI			130
+#define RESET_A5			131
+#define RESET_DVIN			132
+#define RESET_RDMA			133
+#define RESET_VENCI			134
+#define RESET_VENCP			135
+#define RESET_VENCT			136
+#define RESET_VDAC_4			137
+#define RESET_RTC			138
+#define RESET_A5_DEBUG			139
+#define RESET_VDI6			140
+#define RESET_VENCL			141
+/*					142-159	*/
+/*	RESET5					*/
+#define RESET_DDR_PLL			160
+#define RESET_MISC_PLL			161
+#define RESET_SYS_PLL			162
+#define RESET_HPLL_PLL			163
+#define RESET_AUDIO_PLL			164
+#define RESET_VID2_PLL			165
+/*					166-191	*/
+/*	RESET6					*/
+#define RESET_PERIPHS_GENERAL		192
+#define RESET_PERIPHS_IR_REMOTE		193
+#define RESET_PERIPHS_SMART_CARD	194
+#define RESET_PERIPHS_SAR_ADC		195
+#define RESET_PERIPHS_I2C_MASTER_0	196
+#define RESET_PERIPHS_I2C_MASTER_1	197
+#define RESET_PERIPHS_I2C_SLAVE		198
+#define RESET_PERIPHS_STREAM_INTERFACE	199
+#define RESET_PERIPHS_SDIO		200
+#define RESET_PERIPHS_UART_0		201
+#define RESET_PERIPHS_UART_1		202
+#define RESET_PERIPHS_ASYNC_0		203
+#define RESET_PERIPHS_ASYNC_1		204
+#define RESET_PERIPHS_SPI_0		205
+#define RESET_PERIPHS_SPI_1		206
+#define RESET_PERIPHS_LED_PWM		207
+/*					208-223	*/
+/*	RESET7					*/
+/*					224-255	*/
+
+#endif
diff --git a/include/dt-bindings/reset/hisi,hi6220-resets.h b/include/dt-bindings/reset/hisi,hi6220-resets.h
index ca08a7e5248e..322ec5335b65 100644
--- a/include/dt-bindings/reset/hisi,hi6220-resets.h
+++ b/include/dt-bindings/reset/hisi,hi6220-resets.h
@@ -64,4 +64,12 @@
 #define PERIPH_RSDIST9_CARM_SOCDBG      0x507
 #define PERIPH_RSDIST9_CARM_ETM         0x508
 
+#define MEDIA_G3D                       0
+#define MEDIA_CODEC_VPU                 2
+#define MEDIA_CODEC_JPEG                3
+#define MEDIA_ISP                       4
+#define MEDIA_ADE                       5
+#define MEDIA_MMU                       6
+#define MEDIA_XG2RAM1                   7
+
 #endif /*_DT_BINDINGS_RESET_CONTROLLER_HI6220*/
diff --git a/include/dt-bindings/reset/sun8i-h3-ccu.h b/include/dt-bindings/reset/sun8i-h3-ccu.h
new file mode 100644
index 000000000000..6b7af80c26ec
--- /dev/null
+++ b/include/dt-bindings/reset/sun8i-h3-ccu.h
@@ -0,0 +1,103 @@
+/*
+ * Copyright (C) 2016 Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ *  a) This file is free software; you can redistribute it and/or
+ *     modify it under the terms of the GNU General Public License as
+ *     published by the Free Software Foundation; either version 2 of the
+ *     License, or (at your option) any later version.
+ *
+ *     This file is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ *  b) Permission is hereby granted, free of charge, to any person
+ *     obtaining a copy of this software and associated documentation
+ *     files (the "Software"), to deal in the Software without
+ *     restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or
+ *     sell copies of the Software, and to permit persons to whom the
+ *     Software is furnished to do so, subject to the following
+ *     conditions:
+ *
+ *     The above copyright notice and this permission notice shall be
+ *     included in all copies or substantial portions of the Software.
+ *
+ *     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ *     EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ *     OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ *     NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ *     HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ *     WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ *     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ *     OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _DT_BINDINGS_RST_SUN8I_H3_H_
+#define _DT_BINDINGS_RST_SUN8I_H3_H_
+
+#define RST_USB_PHY0		0
+#define RST_USB_PHY1		1
+#define RST_USB_PHY2		2
+#define RST_USB_PHY3		3
+
+#define RST_MBUS		4
+
+#define RST_BUS_CE		5
+#define RST_BUS_DMA		6
+#define RST_BUS_MMC0		7
+#define RST_BUS_MMC1		8
+#define RST_BUS_MMC2		9
+#define RST_BUS_NAND		10
+#define RST_BUS_DRAM		11
+#define RST_BUS_EMAC		12
+#define RST_BUS_TS		13
+#define RST_BUS_HSTIMER		14
+#define RST_BUS_SPI0		15
+#define RST_BUS_SPI1		16
+#define RST_BUS_OTG		17
+#define RST_BUS_EHCI0		18
+#define RST_BUS_EHCI1		19
+#define RST_BUS_EHCI2		20
+#define RST_BUS_EHCI3		21
+#define RST_BUS_OHCI0		22
+#define RST_BUS_OHCI1		23
+#define RST_BUS_OHCI2		24
+#define RST_BUS_OHCI3		25
+#define RST_BUS_VE		26
+#define RST_BUS_TCON0		27
+#define RST_BUS_TCON1		28
+#define RST_BUS_DEINTERLACE	29
+#define RST_BUS_CSI		30
+#define RST_BUS_TVE		31
+#define RST_BUS_HDMI0		32
+#define RST_BUS_HDMI1		33
+#define RST_BUS_DE		34
+#define RST_BUS_GPU		35
+#define RST_BUS_MSGBOX		36
+#define RST_BUS_SPINLOCK	37
+#define RST_BUS_DBG		38
+#define RST_BUS_EPHY		39
+#define RST_BUS_CODEC		40
+#define RST_BUS_SPDIF		41
+#define RST_BUS_THS		42
+#define RST_BUS_I2S0		43
+#define RST_BUS_I2S1		44
+#define RST_BUS_I2S2		45
+#define RST_BUS_I2C0		46
+#define RST_BUS_I2C1		47
+#define RST_BUS_I2C2		48
+#define RST_BUS_UART0		49
+#define RST_BUS_UART1		50
+#define RST_BUS_UART2		51
+#define RST_BUS_UART3		52
+#define RST_BUS_SCR		53
+
+#endif /* _DT_BINDINGS_RST_SUN8I_H3_H_ */
diff --git a/include/dt-bindings/reset/ti-syscon.h b/include/dt-bindings/reset/ti-syscon.h
new file mode 100644
index 000000000000..884fd91df8e9
--- /dev/null
+++ b/include/dt-bindings/reset/ti-syscon.h
@@ -0,0 +1,38 @@
+/*
+ * TI Syscon Reset definitions
+ *
+ * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DT_BINDINGS_RESET_TI_SYSCON_H__
+#define __DT_BINDINGS_RESET_TI_SYSCON_H__
+
+/*
+ * The reset does not support the feature and corresponding
+ * values are not valid
+ */
+#define ASSERT_NONE	(1 << 0)
+#define DEASSERT_NONE	(1 << 1)
+#define STATUS_NONE	(1 << 2)
+
+/* When set this function is activated by setting(vs clearing) this bit */
+#define ASSERT_SET	(1 << 3)
+#define DEASSERT_SET	(1 << 4)
+#define STATUS_SET	(1 << 5)
+
+/* The following are the inverse of the above and are added for consistency */
+#define ASSERT_CLEAR	(0 << 3)
+#define DEASSERT_CLEAR	(0 << 4)
+#define STATUS_CLEAR	(0 << 5)
+
+#endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index da0a524802cb..540da5149ba7 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -1,6 +1,5 @@
 /*
- * Copyright (C) 2012 ARM Ltd.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
+ * Copyright (C) 2015, 2016 ARM Ltd.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -12,16 +11,10 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-
-#ifndef __ASM_ARM_KVM_VGIC_H
-#define __ASM_ARM_KVM_VGIC_H
-
-#ifdef CONFIG_KVM_NEW_VGIC
-#include <kvm/vgic/vgic.h>
-#else
+#ifndef __KVM_ARM_VGIC_H
+#define __KVM_ARM_VGIC_H
 
 #include <linux/kernel.h>
 #include <linux/kvm.h>
@@ -29,248 +22,187 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <kvm/iodev.h>
-#include <linux/irqchip/arm-gic-common.h>
+#include <linux/list.h>
 
-#define VGIC_NR_IRQS_LEGACY	256
+#define VGIC_V3_MAX_CPUS	255
+#define VGIC_V2_MAX_CPUS	8
+#define VGIC_NR_IRQS_LEGACY     256
 #define VGIC_NR_SGIS		16
 #define VGIC_NR_PPIS		16
 #define VGIC_NR_PRIVATE_IRQS	(VGIC_NR_SGIS + VGIC_NR_PPIS)
+#define VGIC_MAX_PRIVATE	(VGIC_NR_PRIVATE_IRQS - 1)
+#define VGIC_MAX_SPI		1019
+#define VGIC_MAX_RESERVED	1023
+#define VGIC_MIN_LPI		8192
 
-#define VGIC_V2_MAX_LRS		(1 << 6)
-#define VGIC_V3_MAX_LRS		16
-#define VGIC_MAX_IRQS		1024
-#define VGIC_V2_MAX_CPUS	8
-#define VGIC_V3_MAX_CPUS	255
+enum vgic_type {
+	VGIC_V2,		/* Good ol' GICv2 */
+	VGIC_V3,		/* New fancy GICv3 */
+};
 
-#if (VGIC_NR_IRQS_LEGACY & 31)
-#error "VGIC_NR_IRQS must be a multiple of 32"
-#endif
+/* same for all guests, as depending only on the _host's_ GIC model */
+struct vgic_global {
+	/* type of the host GIC */
+	enum vgic_type		type;
 
-#if (VGIC_NR_IRQS_LEGACY > VGIC_MAX_IRQS)
-#error "VGIC_NR_IRQS must be <= 1024"
-#endif
+	/* Physical address of vgic virtual cpu interface */
+	phys_addr_t		vcpu_base;
 
-/*
- * The GIC distributor registers describing interrupts have two parts:
- * - 32 per-CPU interrupts (SGI + PPI)
- * - a bunch of shared interrupts (SPI)
- */
-struct vgic_bitmap {
-	/*
-	 * - One UL per VCPU for private interrupts (assumes UL is at
-	 *   least 32 bits)
-	 * - As many UL as necessary for shared interrupts.
-	 *
-	 * The private interrupts are accessed via the "private"
-	 * field, one UL per vcpu (the state for vcpu n is in
-	 * private[n]). The shared interrupts are accessed via the
-	 * "shared" pointer (IRQn state is at bit n-32 in the bitmap).
-	 */
-	unsigned long *private;
-	unsigned long *shared;
-};
+	/* virtual control interface mapping */
+	void __iomem		*vctrl_base;
 
-struct vgic_bytemap {
-	/*
-	 * - 8 u32 per VCPU for private interrupts
-	 * - As many u32 as necessary for shared interrupts.
-	 *
-	 * The private interrupts are accessed via the "private"
-	 * field, (the state for vcpu n is in private[n*8] to
-	 * private[n*8 + 7]). The shared interrupts are accessed via
-	 * the "shared" pointer (IRQn state is at byte (n-32)%4 of the
-	 * shared[(n-32)/4] word).
-	 */
-	u32 *private;
-	u32 *shared;
-};
+	/* Number of implemented list registers */
+	int			nr_lr;
 
-struct kvm_vcpu;
+	/* Maintenance IRQ number */
+	unsigned int		maint_irq;
 
-enum vgic_type {
-	VGIC_V2,		/* Good ol' GICv2 */
-	VGIC_V3,		/* New fancy GICv3 */
+	/* maximum number of VCPUs allowed (GICv2 limits us to 8) */
+	int			max_gic_vcpus;
+
+	/* Only needed for the legacy KVM_CREATE_IRQCHIP */
+	bool			can_emulate_gicv2;
 };
 
-#define LR_STATE_PENDING	(1 << 0)
-#define LR_STATE_ACTIVE		(1 << 1)
-#define LR_STATE_MASK		(3 << 0)
-#define LR_EOI_INT		(1 << 2)
-#define LR_HW			(1 << 3)
+extern struct vgic_global kvm_vgic_global_state;
 
-struct vgic_lr {
-	unsigned irq:10;
-	union {
-		unsigned hwirq:10;
-		unsigned source:3;
-	};
-	unsigned state:4;
-};
+#define VGIC_V2_MAX_LRS		(1 << 6)
+#define VGIC_V3_MAX_LRS		16
+#define VGIC_V3_LR_INDEX(lr)	(VGIC_V3_MAX_LRS - 1 - lr)
 
-struct vgic_vmcr {
-	u32	ctlr;
-	u32	abpr;
-	u32	bpr;
-	u32	pmr;
+enum vgic_irq_config {
+	VGIC_CONFIG_EDGE = 0,
+	VGIC_CONFIG_LEVEL
 };
 
-struct vgic_ops {
-	struct vgic_lr	(*get_lr)(const struct kvm_vcpu *, int);
-	void	(*set_lr)(struct kvm_vcpu *, int, struct vgic_lr);
-	u64	(*get_elrsr)(const struct kvm_vcpu *vcpu);
-	u64	(*get_eisr)(const struct kvm_vcpu *vcpu);
-	void	(*clear_eisr)(struct kvm_vcpu *vcpu);
-	u32	(*get_interrupt_status)(const struct kvm_vcpu *vcpu);
-	void	(*enable_underflow)(struct kvm_vcpu *vcpu);
-	void	(*disable_underflow)(struct kvm_vcpu *vcpu);
-	void	(*get_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
-	void	(*set_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
-	void	(*enable)(struct kvm_vcpu *vcpu);
+struct vgic_irq {
+	spinlock_t irq_lock;		/* Protects the content of the struct */
+	struct list_head lpi_list;	/* Used to link all LPIs together */
+	struct list_head ap_list;
+
+	struct kvm_vcpu *vcpu;		/* SGIs and PPIs: The VCPU
+					 * SPIs and LPIs: The VCPU whose ap_list
+					 * this is queued on.
+					 */
+
+	struct kvm_vcpu *target_vcpu;	/* The VCPU that this interrupt should
+					 * be sent to, as a result of the
+					 * targets reg (v2) or the
+					 * affinity reg (v3).
+					 */
+
+	u32 intid;			/* Guest visible INTID */
+	bool pending;
+	bool line_level;		/* Level only */
+	bool soft_pending;		/* Level only */
+	bool active;			/* not used for LPIs */
+	bool enabled;
+	bool hw;			/* Tied to HW IRQ */
+	struct kref refcount;		/* Used for LPIs */
+	u32 hwintid;			/* HW INTID number */
+	union {
+		u8 targets;			/* GICv2 target VCPUs mask */
+		u32 mpidr;			/* GICv3 target VCPU */
+	};
+	u8 source;			/* GICv2 SGIs only */
+	u8 priority;
+	enum vgic_irq_config config;	/* Level or edge */
 };
 
-struct vgic_params {
-	/* vgic type */
-	enum vgic_type	type;
-	/* Physical address of vgic virtual cpu interface */
-	phys_addr_t	vcpu_base;
-	/* Number of list registers */
-	u32		nr_lr;
-	/* Interrupt number */
-	unsigned int	maint_irq;
-	/* Virtual control interface base address */
-	void __iomem	*vctrl_base;
-	int		max_gic_vcpus;
-	/* Only needed for the legacy KVM_CREATE_IRQCHIP */
-	bool		can_emulate_gicv2;
-};
+struct vgic_register_region;
+struct vgic_its;
 
-struct vgic_vm_ops {
-	bool	(*queue_sgi)(struct kvm_vcpu *, int irq);
-	void	(*add_sgi_source)(struct kvm_vcpu *, int irq, int source);
-	int	(*init_model)(struct kvm *);
-	int	(*map_resources)(struct kvm *, const struct vgic_params *);
+enum iodev_type {
+	IODEV_CPUIF,
+	IODEV_DIST,
+	IODEV_REDIST,
+	IODEV_ITS
 };
 
 struct vgic_io_device {
-	gpa_t addr;
-	int len;
-	const struct vgic_io_range *reg_ranges;
-	struct kvm_vcpu *redist_vcpu;
+	gpa_t base_addr;
+	union {
+		struct kvm_vcpu *redist_vcpu;
+		struct vgic_its *its;
+	};
+	const struct vgic_register_region *regions;
+	enum iodev_type iodev_type;
+	int nr_regions;
 	struct kvm_io_device dev;
 };
 
-struct irq_phys_map {
-	u32			virt_irq;
-	u32			phys_irq;
-};
-
-struct irq_phys_map_entry {
-	struct list_head	entry;
-	struct rcu_head		rcu;
-	struct irq_phys_map	map;
+struct vgic_its {
+	/* The base address of the ITS control register frame */
+	gpa_t			vgic_its_base;
+
+	bool			enabled;
+	bool			initialized;
+	struct vgic_io_device	iodev;
+	struct kvm_device	*dev;
+
+	/* These registers correspond to GITS_BASER{0,1} */
+	u64			baser_device_table;
+	u64			baser_coll_table;
+
+	/* Protects the command queue */
+	struct mutex		cmd_lock;
+	u64			cbaser;
+	u32			creadr;
+	u32			cwriter;
+
+	/* Protects the device and collection lists */
+	struct mutex		its_lock;
+	struct list_head	device_list;
+	struct list_head	collection_list;
 };
 
 struct vgic_dist {
-	spinlock_t		lock;
 	bool			in_kernel;
 	bool			ready;
+	bool			initialized;
 
 	/* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
 	u32			vgic_model;
 
-	int			nr_cpus;
-	int			nr_irqs;
+	/* Do injected MSIs require an additional device ID? */
+	bool			msis_require_devid;
+
+	int			nr_spis;
 
+	/* TODO: Consider moving to global state */
 	/* Virtual control interface mapping */
 	void __iomem		*vctrl_base;
 
-	/* Distributor and vcpu interface mapping in the guest */
-	phys_addr_t		vgic_dist_base;
-	/* GICv2 and GICv3 use different mapped register blocks */
+	/* base addresses in guest physical address space: */
+	gpa_t			vgic_dist_base;		/* distributor */
 	union {
-		phys_addr_t		vgic_cpu_base;
-		phys_addr_t		vgic_redist_base;
+		/* either a GICv2 CPU interface */
+		gpa_t			vgic_cpu_base;
+		/* or a number of GICv3 redistributor regions */
+		gpa_t			vgic_redist_base;
 	};
 
-	/* Distributor enabled */
-	u32			enabled;
-
-	/* Interrupt enabled (one bit per IRQ) */
-	struct vgic_bitmap	irq_enabled;
-
-	/* Level-triggered interrupt external input is asserted */
-	struct vgic_bitmap	irq_level;
-
-	/*
-	 * Interrupt state is pending on the distributor
-	 */
-	struct vgic_bitmap	irq_pending;
-
-	/*
-	 * Tracks writes to GICD_ISPENDRn and GICD_ICPENDRn for level-triggered
-	 * interrupts.  Essentially holds the state of the flip-flop in
-	 * Figure 4-10 on page 4-101 in ARM IHI 0048B.b.
-	 * Once set, it is only cleared for level-triggered interrupts on
-	 * guest ACKs (when we queue it) or writes to GICD_ICPENDRn.
-	 */
-	struct vgic_bitmap	irq_soft_pend;
-
-	/* Level-triggered interrupt queued on VCPU interface */
-	struct vgic_bitmap	irq_queued;
-
-	/* Interrupt was active when unqueue from VCPU interface */
-	struct vgic_bitmap	irq_active;
-
-	/* Interrupt priority. Not used yet. */
-	struct vgic_bytemap	irq_priority;
+	/* distributor enabled */
+	bool			enabled;
 
-	/* Level/edge triggered */
-	struct vgic_bitmap	irq_cfg;
+	struct vgic_irq		*spis;
 
-	/*
-	 * Source CPU per SGI and target CPU:
-	 *
-	 * Each byte represent a SGI observable on a VCPU, each bit of
-	 * this byte indicating if the corresponding VCPU has
-	 * generated this interrupt. This is a GICv2 feature only.
-	 *
-	 * For VCPUn (n < 8), irq_sgi_sources[n*16] to [n*16 + 15] are
-	 * the SGIs observable on VCPUn.
-	 */
-	u8			*irq_sgi_sources;
+	struct vgic_io_device	dist_iodev;
 
-	/*
-	 * Target CPU for each SPI:
-	 *
-	 * Array of available SPI, each byte indicating the target
-	 * VCPU for SPI. IRQn (n >=32) is at irq_spi_cpu[n-32].
-	 */
-	u8			*irq_spi_cpu;
+	bool			has_its;
 
 	/*
-	 * Reverse lookup of irq_spi_cpu for faster compute pending:
-	 *
-	 * Array of bitmaps, one per VCPU, describing if IRQn is
-	 * routed to a particular VCPU.
+	 * Contains the attributes and gpa of the LPI configuration table.
+	 * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share
+	 * one address across all redistributors.
+	 * GICv3 spec: 6.1.2 "LPI Configuration tables"
 	 */
-	struct vgic_bitmap	*irq_spi_target;
-
-	/* Target MPIDR for each IRQ (needed for GICv3 IROUTERn) only */
-	u32			*irq_spi_mpidr;
+	u64			propbaser;
 
-	/* Bitmap indicating which CPU has something pending */
-	unsigned long		*irq_pending_on_cpu;
-
-	/* Bitmap indicating which CPU has active IRQs */
-	unsigned long		*irq_active_on_cpu;
-
-	struct vgic_vm_ops	vm_ops;
-	struct vgic_io_device	dist_iodev;
-	struct vgic_io_device	*redist_iodevs;
-
-	/* Virtual irq to hwirq mapping */
-	spinlock_t		irq_phys_map_lock;
-	struct list_head	irq_phys_map_list;
+	/* Protects the lpi_list and the count value below. */
+	spinlock_t		lpi_list_lock;
+	struct list_head	lpi_list_head;
+	int			lpi_list_count;
 };
 
 struct vgic_v2_cpu_if {
@@ -298,78 +230,88 @@ struct vgic_v3_cpu_if {
 };
 
 struct vgic_cpu {
-	/* Pending/active/both interrupts on this VCPU */
-	DECLARE_BITMAP(pending_percpu, VGIC_NR_PRIVATE_IRQS);
-	DECLARE_BITMAP(active_percpu, VGIC_NR_PRIVATE_IRQS);
-	DECLARE_BITMAP(pend_act_percpu, VGIC_NR_PRIVATE_IRQS);
-
-	/* Pending/active/both shared interrupts, dynamically sized */
-	unsigned long	*pending_shared;
-	unsigned long   *active_shared;
-	unsigned long   *pend_act_shared;
-
 	/* CPU vif control registers for world switch */
 	union {
 		struct vgic_v2_cpu_if	vgic_v2;
 		struct vgic_v3_cpu_if	vgic_v3;
 	};
 
-	/* Protected by the distributor's irq_phys_map_lock */
-	struct list_head	irq_phys_map_list;
+	unsigned int used_lrs;
+	struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
 
-	u64		live_lrs;
-};
+	spinlock_t ap_list_lock;	/* Protects the ap_list */
+
+	/*
+	 * List of IRQs that this VCPU should consider because they are either
+	 * Active or Pending (hence the name; AP list), or because they recently
+	 * were one of the two and need to be migrated off this list to another
+	 * VCPU.
+	 */
+	struct list_head ap_list_head;
 
-#define LR_EMPTY	0xff
+	u64 live_lrs;
 
-#define INT_STATUS_EOI		(1 << 0)
-#define INT_STATUS_UNDERFLOW	(1 << 1)
+	/*
+	 * Members below are used with GICv3 emulation only and represent
+	 * parts of the redistributor.
+	 */
+	struct vgic_io_device	rd_iodev;
+	struct vgic_io_device	sgi_iodev;
 
-struct kvm;
-struct kvm_vcpu;
+	/* Contains the attributes and gpa of the LPI pending tables. */
+	u64 pendbaser;
+
+	bool lpis_enabled;
+};
 
 int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
-int kvm_vgic_hyp_init(void);
-int kvm_vgic_map_resources(struct kvm *kvm);
-int kvm_vgic_get_max_vcpus(void);
 void kvm_vgic_early_init(struct kvm *kvm);
 int kvm_vgic_create(struct kvm *kvm, u32 type);
 void kvm_vgic_destroy(struct kvm *kvm);
 void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
-void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
-void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
-int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
+int kvm_vgic_map_resources(struct kvm *kvm);
+int kvm_vgic_hyp_init(void);
+
+int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
 			bool level);
-int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
-			       unsigned int virt_irq, bool level);
-void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
-int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
-int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int phys_irq);
+int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
+			       bool level);
+int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq);
 int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
 bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
 
+int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
+
 #define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
-#define vgic_initialized(k)	(!!((k)->arch.vgic.nr_cpus))
+#define vgic_initialized(k)	((k)->arch.vgic.initialized)
 #define vgic_ready(k)		((k)->arch.vgic.ready)
 #define vgic_valid_spi(k, i)	(((i) >= VGIC_NR_PRIVATE_IRQS) && \
-				 ((i) < (k)->arch.vgic.nr_irqs))
+			((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
+
+bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
+void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
 
-int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info,
-		  const struct vgic_ops **ops,
-		  const struct vgic_params **params);
 #ifdef CONFIG_KVM_ARM_VGIC_V3
-int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
-		  const struct vgic_ops **ops,
-		  const struct vgic_params **params);
+void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
 #else
-static inline int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
-				const struct vgic_ops **ops,
-				const struct vgic_params **params)
+static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
 {
-	return -ENODEV;
 }
 #endif
 
-#endif	/* old VGIC include */
-#endif
+/**
+ * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
+ *
+ * The host's GIC naturally limits the maximum amount of VCPUs a guest
+ * can use.
+ */
+static inline int kvm_vgic_get_max_vcpus(void)
+{
+	return kvm_vgic_global_state.max_gic_vcpus;
+}
+
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
+
+#endif /* __KVM_ARM_VGIC_H */
diff --git a/include/kvm/vgic/vgic.h b/include/kvm/vgic/vgic.h
deleted file mode 100644
index 3fbd175265ae..000000000000
--- a/include/kvm/vgic/vgic.h
+++ /dev/null
@@ -1,246 +0,0 @@
-/*
- * Copyright (C) 2015, 2016 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_ARM_KVM_VGIC_VGIC_H
-#define __ASM_ARM_KVM_VGIC_VGIC_H
-
-#include <linux/kernel.h>
-#include <linux/kvm.h>
-#include <linux/irqreturn.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-#include <kvm/iodev.h>
-
-#define VGIC_V3_MAX_CPUS	255
-#define VGIC_V2_MAX_CPUS	8
-#define VGIC_NR_IRQS_LEGACY     256
-#define VGIC_NR_SGIS		16
-#define VGIC_NR_PPIS		16
-#define VGIC_NR_PRIVATE_IRQS	(VGIC_NR_SGIS + VGIC_NR_PPIS)
-#define VGIC_MAX_PRIVATE	(VGIC_NR_PRIVATE_IRQS - 1)
-#define VGIC_MAX_SPI		1019
-#define VGIC_MAX_RESERVED	1023
-#define VGIC_MIN_LPI		8192
-
-enum vgic_type {
-	VGIC_V2,		/* Good ol' GICv2 */
-	VGIC_V3,		/* New fancy GICv3 */
-};
-
-/* same for all guests, as depending only on the _host's_ GIC model */
-struct vgic_global {
-	/* type of the host GIC */
-	enum vgic_type		type;
-
-	/* Physical address of vgic virtual cpu interface */
-	phys_addr_t		vcpu_base;
-
-	/* virtual control interface mapping */
-	void __iomem		*vctrl_base;
-
-	/* Number of implemented list registers */
-	int			nr_lr;
-
-	/* Maintenance IRQ number */
-	unsigned int		maint_irq;
-
-	/* maximum number of VCPUs allowed (GICv2 limits us to 8) */
-	int			max_gic_vcpus;
-
-	/* Only needed for the legacy KVM_CREATE_IRQCHIP */
-	bool			can_emulate_gicv2;
-};
-
-extern struct vgic_global kvm_vgic_global_state;
-
-#define VGIC_V2_MAX_LRS		(1 << 6)
-#define VGIC_V3_MAX_LRS		16
-#define VGIC_V3_LR_INDEX(lr)	(VGIC_V3_MAX_LRS - 1 - lr)
-
-enum vgic_irq_config {
-	VGIC_CONFIG_EDGE = 0,
-	VGIC_CONFIG_LEVEL
-};
-
-struct vgic_irq {
-	spinlock_t irq_lock;		/* Protects the content of the struct */
-	struct list_head ap_list;
-
-	struct kvm_vcpu *vcpu;		/* SGIs and PPIs: The VCPU
-					 * SPIs and LPIs: The VCPU whose ap_list
-					 * this is queued on.
-					 */
-
-	struct kvm_vcpu *target_vcpu;	/* The VCPU that this interrupt should
-					 * be sent to, as a result of the
-					 * targets reg (v2) or the
-					 * affinity reg (v3).
-					 */
-
-	u32 intid;			/* Guest visible INTID */
-	bool pending;
-	bool line_level;		/* Level only */
-	bool soft_pending;		/* Level only */
-	bool active;			/* not used for LPIs */
-	bool enabled;
-	bool hw;			/* Tied to HW IRQ */
-	u32 hwintid;			/* HW INTID number */
-	union {
-		u8 targets;			/* GICv2 target VCPUs mask */
-		u32 mpidr;			/* GICv3 target VCPU */
-	};
-	u8 source;			/* GICv2 SGIs only */
-	u8 priority;
-	enum vgic_irq_config config;	/* Level or edge */
-};
-
-struct vgic_register_region;
-
-struct vgic_io_device {
-	gpa_t base_addr;
-	struct kvm_vcpu *redist_vcpu;
-	const struct vgic_register_region *regions;
-	int nr_regions;
-	struct kvm_io_device dev;
-};
-
-struct vgic_dist {
-	bool			in_kernel;
-	bool			ready;
-	bool			initialized;
-
-	/* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
-	u32			vgic_model;
-
-	int			nr_spis;
-
-	/* TODO: Consider moving to global state */
-	/* Virtual control interface mapping */
-	void __iomem		*vctrl_base;
-
-	/* base addresses in guest physical address space: */
-	gpa_t			vgic_dist_base;		/* distributor */
-	union {
-		/* either a GICv2 CPU interface */
-		gpa_t			vgic_cpu_base;
-		/* or a number of GICv3 redistributor regions */
-		gpa_t			vgic_redist_base;
-	};
-
-	/* distributor enabled */
-	bool			enabled;
-
-	struct vgic_irq		*spis;
-
-	struct vgic_io_device	dist_iodev;
-	struct vgic_io_device	*redist_iodevs;
-};
-
-struct vgic_v2_cpu_if {
-	u32		vgic_hcr;
-	u32		vgic_vmcr;
-	u32		vgic_misr;	/* Saved only */
-	u64		vgic_eisr;	/* Saved only */
-	u64		vgic_elrsr;	/* Saved only */
-	u32		vgic_apr;
-	u32		vgic_lr[VGIC_V2_MAX_LRS];
-};
-
-struct vgic_v3_cpu_if {
-#ifdef CONFIG_KVM_ARM_VGIC_V3
-	u32		vgic_hcr;
-	u32		vgic_vmcr;
-	u32		vgic_sre;	/* Restored only, change ignored */
-	u32		vgic_misr;	/* Saved only */
-	u32		vgic_eisr;	/* Saved only */
-	u32		vgic_elrsr;	/* Saved only */
-	u32		vgic_ap0r[4];
-	u32		vgic_ap1r[4];
-	u64		vgic_lr[VGIC_V3_MAX_LRS];
-#endif
-};
-
-struct vgic_cpu {
-	/* CPU vif control registers for world switch */
-	union {
-		struct vgic_v2_cpu_if	vgic_v2;
-		struct vgic_v3_cpu_if	vgic_v3;
-	};
-
-	unsigned int used_lrs;
-	struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
-
-	spinlock_t ap_list_lock;	/* Protects the ap_list */
-
-	/*
-	 * List of IRQs that this VCPU should consider because they are either
-	 * Active or Pending (hence the name; AP list), or because they recently
-	 * were one of the two and need to be migrated off this list to another
-	 * VCPU.
-	 */
-	struct list_head ap_list_head;
-
-	u64 live_lrs;
-};
-
-int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
-void kvm_vgic_early_init(struct kvm *kvm);
-int kvm_vgic_create(struct kvm *kvm, u32 type);
-void kvm_vgic_destroy(struct kvm *kvm);
-void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
-void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
-int kvm_vgic_map_resources(struct kvm *kvm);
-int kvm_vgic_hyp_init(void);
-
-int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
-			bool level);
-int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
-			       bool level);
-int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq);
-int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
-bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
-
-int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
-
-#define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
-#define vgic_initialized(k)	((k)->arch.vgic.initialized)
-#define vgic_ready(k)		((k)->arch.vgic.ready)
-#define vgic_valid_spi(k, i)	(((i) >= VGIC_NR_PRIVATE_IRQS) && \
-			((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
-
-bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
-void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
-void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
-
-#ifdef CONFIG_KVM_ARM_VGIC_V3
-void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
-#else
-static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
-{
-}
-#endif
-
-/**
- * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
- *
- * The host's GIC naturally limits the maximum amount of VCPUs a guest
- * can use.
- */
-static inline int kvm_vgic_get_max_vcpus(void)
-{
-	return kvm_vgic_global_state.max_gic_vcpus;
-}
-
-#endif /* __ASM_ARM_KVM_VGIC_VGIC_H */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index db7c8bd39a3c..4d8452c2384b 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -608,6 +608,12 @@ static inline struct acpi_data_node *to_acpi_data_node(struct fwnode_handle *fwn
 	return NULL;
 }
 
+static inline bool acpi_data_node_match(struct fwnode_handle *fwnode,
+					const char *name)
+{
+	return false;
+}
+
 static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev)
 {
 	return NULL;
diff --git a/include/linux/capability.h b/include/linux/capability.h
index 5f3c63dde2d5..dbc21c719ce6 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -38,6 +38,7 @@ struct cpu_vfs_cap_data {
 struct file;
 struct inode;
 struct dentry;
+struct task_struct;
 struct user_namespace;
 
 extern const kernel_cap_t __cap_empty_set;
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index dfce616002ad..7868d602c0a0 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -34,9 +34,9 @@
 #define CEPH_MAX_MON   31
 
 /*
- * ceph_file_layout - describe data layout for a file/inode
+ * legacy ceph_file_layoute
  */
-struct ceph_file_layout {
+struct ceph_file_layout_legacy {
 	/* file -> object mapping */
 	__le32 fl_stripe_unit;     /* stripe unit, in bytes.  must be multiple
 				      of page size. */
@@ -53,33 +53,27 @@ struct ceph_file_layout {
 	__le32 fl_pg_pool;      /* namespace, crush ruleset, rep level */
 } __attribute__ ((packed));
 
-#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit))
-#define ceph_file_layout_stripe_count(l) \
-	((__s32)le32_to_cpu((l).fl_stripe_count))
-#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size))
-#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash))
-#define ceph_file_layout_object_su(l) \
-	((__s32)le32_to_cpu((l).fl_object_stripe_unit))
-#define ceph_file_layout_pg_pool(l) \
-	((__s32)le32_to_cpu((l).fl_pg_pool))
-
-static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l)
-{
-	return le32_to_cpu(l->fl_stripe_unit) *
-		le32_to_cpu(l->fl_stripe_count);
-}
-
-/* "period" == bytes before i start on a new set of objects */
-static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l)
-{
-	return le32_to_cpu(l->fl_object_size) *
-		le32_to_cpu(l->fl_stripe_count);
-}
+struct ceph_string;
+/*
+ * ceph_file_layout - describe data layout for a file/inode
+ */
+struct ceph_file_layout {
+	/* file -> object mapping */
+	u32 stripe_unit;   /* stripe unit, in bytes */
+	u32 stripe_count;  /* over this many objects */
+	u32 object_size;   /* until objects are this big */
+	s64 pool_id;        /* rados pool id */
+	struct ceph_string __rcu *pool_ns; /* rados pool namespace */
+};
+
+extern int ceph_file_layout_is_valid(const struct ceph_file_layout *layout);
+extern void ceph_file_layout_from_legacy(struct ceph_file_layout *fl,
+				struct ceph_file_layout_legacy *legacy);
+extern void ceph_file_layout_to_legacy(struct ceph_file_layout *fl,
+				struct ceph_file_layout_legacy *legacy);
 
 #define CEPH_MIN_STRIPE_UNIT 65536
 
-int ceph_file_layout_is_valid(const struct ceph_file_layout *layout);
-
 struct ceph_dir_layout {
 	__u8   dl_dir_hash;   /* see ceph_hash.h for ids */
 	__u8   dl_unused1;
@@ -127,6 +121,7 @@ struct ceph_dir_layout {
 
 /* client <-> mds */
 #define CEPH_MSG_MDS_MAP                21
+#define CEPH_MSG_FS_MAP_USER            103
 
 #define CEPH_MSG_CLIENT_SESSION         22
 #define CEPH_MSG_CLIENT_RECONNECT       23
@@ -399,7 +394,7 @@ union ceph_mds_request_args {
 		__le32 flags;
 	} __attribute__ ((packed)) setxattr;
 	struct {
-		struct ceph_file_layout layout;
+		struct ceph_file_layout_legacy layout;
 	} __attribute__ ((packed)) setlayout;
 	struct {
 		__u8 rule; /* currently fcntl or flock */
@@ -478,7 +473,7 @@ struct ceph_mds_reply_inode {
 	__le64 version;                /* inode version */
 	__le64 xattr_version;          /* version for xattr blob */
 	struct ceph_mds_reply_cap cap; /* caps issued for this inode */
-	struct ceph_file_layout layout;
+	struct ceph_file_layout_legacy layout;
 	struct ceph_timespec ctime, mtime, atime;
 	__le32 time_warp_seq;
 	__le64 size, max_size, truncate_size;
@@ -531,7 +526,7 @@ struct ceph_filelock {
 #define CEPH_FILE_MODE_WR         2
 #define CEPH_FILE_MODE_RDWR       3  /* RD | WR */
 #define CEPH_FILE_MODE_LAZY       4  /* lazy io */
-#define CEPH_FILE_MODE_NUM        8  /* bc these are bit fields.. mostly */
+#define CEPH_FILE_MODE_BITS       4
 
 int ceph_flags_to_mode(int flags);
 
@@ -673,7 +668,7 @@ struct ceph_mds_caps {
 	__le64 size, max_size, truncate_size;
 	__le32 truncate_seq;
 	struct ceph_timespec mtime, atime, ctime;
-	struct ceph_file_layout layout;
+	struct ceph_file_layout_legacy layout;
 	__le32 time_warp_seq;
 } __attribute__ ((packed));
 
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index 19e9932f3e77..f990f2cc907a 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -3,6 +3,7 @@
 
 #include <linux/err.h>
 #include <linux/bug.h>
+#include <linux/slab.h>
 #include <linux/time.h>
 #include <asm/unaligned.h>
 
@@ -217,6 +218,60 @@ static inline void ceph_encode_string(void **p, void *end,
 	*p += len;
 }
 
+/*
+ * version and length starting block encoders/decoders
+ */
+
+/* current code version (u8) + compat code version (u8) + len of struct (u32) */
+#define CEPH_ENCODING_START_BLK_LEN 6
+
+/**
+ * ceph_start_encoding - start encoding block
+ * @struct_v: current (code) version of the encoding
+ * @struct_compat: oldest code version that can decode it
+ * @struct_len: length of struct encoding
+ */
+static inline void ceph_start_encoding(void **p, u8 struct_v, u8 struct_compat,
+				       u32 struct_len)
+{
+	ceph_encode_8(p, struct_v);
+	ceph_encode_8(p, struct_compat);
+	ceph_encode_32(p, struct_len);
+}
+
+/**
+ * ceph_start_decoding - start decoding block
+ * @v: current version of the encoding that the code supports
+ * @name: name of the struct (free-form)
+ * @struct_v: out param for the encoding version
+ * @struct_len: out param for the length of struct encoding
+ *
+ * Validates the length of struct encoding, so unsafe ceph_decode_*
+ * variants can be used for decoding.
+ */
+static inline int ceph_start_decoding(void **p, void *end, u8 v,
+				      const char *name, u8 *struct_v,
+				      u32 *struct_len)
+{
+	u8 struct_compat;
+
+	ceph_decode_need(p, end, CEPH_ENCODING_START_BLK_LEN, bad);
+	*struct_v = ceph_decode_8(p);
+	struct_compat = ceph_decode_8(p);
+	if (v < struct_compat) {
+		pr_warn("got struct_v %d struct_compat %d > %d of %s\n",
+			*struct_v, struct_compat, v, name);
+		return -EINVAL;
+	}
+
+	*struct_len = ceph_decode_32(p);
+	ceph_decode_need(p, end, *struct_len, bad);
+	return 0;
+
+bad:
+	return -ERANGE;
+}
+
 #define ceph_encode_need(p, end, n, bad)			\
 	do {							\
 		if (!likely(ceph_has_room(p, end, n)))		\
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 690985daad1c..83fc1fff7061 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -21,6 +21,7 @@
 #include <linux/ceph/mon_client.h>
 #include <linux/ceph/osd_client.h>
 #include <linux/ceph/ceph_fs.h>
+#include <linux/ceph/string_table.h>
 
 /*
  * mount options
@@ -214,8 +215,9 @@ static void erase_##name(struct rb_root *root, type *t)			\
 }
 
 #define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld)		\
+extern type __lookup_##name##_key;					\
 static type *lookup_##name(struct rb_root *root,			\
-			   typeof(((type *)0)->keyfld) key)		\
+			   typeof(__lookup_##name##_key.keyfld) key)	\
 {									\
 	struct rb_node *n = root->rb_node;				\
 									\
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index e2a92df08b47..24d704d1ea5c 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -95,7 +95,7 @@ struct ceph_mon_client {
 		struct ceph_mon_subscribe_item item;
 		bool want;
 		u32 have; /* epoch */
-	} subs[3];
+	} subs[4];
 	int fs_cluster_id; /* "mdsmap.<id>" sub */
 
 #ifdef CONFIG_DEBUG_FS
@@ -111,9 +111,10 @@ extern int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl);
 extern void ceph_monc_stop(struct ceph_mon_client *monc);
 
 enum {
-	CEPH_SUB_MDSMAP = 0,
-	CEPH_SUB_MONMAP,
+	CEPH_SUB_MONMAP = 0,
 	CEPH_SUB_OSDMAP,
+	CEPH_SUB_FSMAP,
+	CEPH_SUB_MDSMAP,
 };
 
 extern const char *ceph_sub_str[];
diff --git a/include/linux/ceph/msgpool.h b/include/linux/ceph/msgpool.h
index 4b0d38960726..ddd0d48d0384 100644
--- a/include/linux/ceph/msgpool.h
+++ b/include/linux/ceph/msgpool.h
@@ -2,7 +2,6 @@
 #define _FS_CEPH_MSGPOOL
 
 #include <linux/mempool.h>
-#include <linux/ceph/messenger.h>
 
 /*
  * we use memory pools for preallocating messages we may receive, to
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 1b3b6e155392..858932304260 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -9,6 +9,7 @@
 #include <linux/ceph/types.h>
 #include <linux/ceph/osdmap.h>
 #include <linux/ceph/messenger.h>
+#include <linux/ceph/msgpool.h>
 #include <linux/ceph/auth.h>
 #include <linux/ceph/pagelist.h>
 
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 9ccf4dbe55f8..9a9041784dcf 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -63,11 +63,13 @@ static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool)
 
 struct ceph_object_locator {
 	s64 pool;
+	struct ceph_string *pool_ns;
 };
 
 static inline void ceph_oloc_init(struct ceph_object_locator *oloc)
 {
 	oloc->pool = -1;
+	oloc->pool_ns = NULL;
 }
 
 static inline bool ceph_oloc_empty(const struct ceph_object_locator *oloc)
@@ -75,11 +77,9 @@ static inline bool ceph_oloc_empty(const struct ceph_object_locator *oloc)
 	return oloc->pool == -1;
 }
 
-static inline void ceph_oloc_copy(struct ceph_object_locator *dest,
-				  const struct ceph_object_locator *src)
-{
-	dest->pool = src->pool;
-}
+void ceph_oloc_copy(struct ceph_object_locator *dest,
+		    const struct ceph_object_locator *src);
+void ceph_oloc_destroy(struct ceph_object_locator *oloc);
 
 /*
  * Maximum supported by kernel client object name length
@@ -115,6 +115,11 @@ static inline void ceph_oid_init(struct ceph_object_id *oid)
 	oid->name_len = 0;
 }
 
+#define CEPH_OID_INIT_ONSTACK(oid)					\
+    ({ ceph_oid_init(&oid); oid; })
+#define CEPH_DEFINE_OID_ONSTACK(oid)					\
+	struct ceph_object_id oid = CEPH_OID_INIT_ONSTACK(oid)
+
 static inline bool ceph_oid_empty(const struct ceph_object_id *oid)
 {
 	return oid->name == oid->inline_name && !oid->name_len;
diff --git a/include/linux/ceph/string_table.h b/include/linux/ceph/string_table.h
new file mode 100644
index 000000000000..1b02c96daf75
--- /dev/null
+++ b/include/linux/ceph/string_table.h
@@ -0,0 +1,62 @@
+#ifndef _FS_CEPH_STRING_TABLE_H
+#define _FS_CEPH_STRING_TABLE_H
+
+#include <linux/types.h>
+#include <linux/kref.h>
+#include <linux/rbtree.h>
+#include <linux/rcupdate.h>
+
+struct ceph_string {
+	struct kref kref;
+	union {
+		struct rb_node node;
+		struct rcu_head rcu;
+	};
+	size_t len;
+	char str[];
+};
+
+extern void ceph_release_string(struct kref *ref);
+extern struct ceph_string *ceph_find_or_create_string(const char *str,
+						      size_t len);
+extern bool ceph_strings_empty(void);
+
+static inline struct ceph_string *ceph_get_string(struct ceph_string *str)
+{
+	kref_get(&str->kref);
+	return str;
+}
+
+static inline void ceph_put_string(struct ceph_string *str)
+{
+	if (!str)
+		return;
+	kref_put(&str->kref, ceph_release_string);
+}
+
+static inline int ceph_compare_string(struct ceph_string *cs,
+				      const char* str, size_t len)
+{
+	size_t cs_len = cs ? cs->len : 0;
+	if (cs_len != len)
+		return cs_len - len;
+	if (len == 0)
+		return 0;
+	return strncmp(cs->str, str, len);
+}
+
+#define ceph_try_get_string(x)					\
+({								\
+	struct ceph_string *___str;				\
+	rcu_read_lock();					\
+	for (;;) {						\
+		___str = rcu_dereference(x);			\
+		if (!___str ||					\
+		    kref_get_unless_zero(&___str->kref))	\
+			break;					\
+	}							\
+	rcu_read_unlock();					\
+	(___str);						\
+})
+
+#endif
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index fb39d5add173..a39c0c530778 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -33,6 +33,8 @@
 #define CLK_RECALC_NEW_RATES	BIT(9) /* recalc rates after notifications */
 #define CLK_SET_RATE_UNGATE	BIT(10) /* clock needs to run to set rate */
 #define CLK_IS_CRITICAL		BIT(11) /* do not gate, ever */
+/* parents need enable during gate/ungate, set rate and re-parent */
+#define CLK_OPS_PARENT_ENABLE	BIT(12)
 
 struct clk;
 struct clk_hw;
@@ -293,6 +295,7 @@ void clk_unregister_fixed_rate(struct clk *clk);
 struct clk_hw *clk_hw_register_fixed_rate_with_accuracy(struct device *dev,
 		const char *name, const char *parent_name, unsigned long flags,
 		unsigned long fixed_rate, unsigned long fixed_accuracy);
+void clk_hw_unregister_fixed_rate(struct clk_hw *hw);
 
 void of_fixed_clk_setup(struct device_node *np);
 
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 834179f3fa72..123c02788807 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -20,8 +20,6 @@ struct device;
 
 struct clk;
 
-#ifdef CONFIG_COMMON_CLK
-
 /**
  * DOC: clk notifier callback types
  *
@@ -78,6 +76,8 @@ struct clk_notifier_data {
 	unsigned long		new_rate;
 };
 
+#ifdef CONFIG_COMMON_CLK
+
 /**
  * clk_notifier_register: register a clock rate-change notifier callback
  * @clk: clock whose rate we are interested in
@@ -140,6 +140,18 @@ bool clk_is_match(const struct clk *p, const struct clk *q);
 
 #else
 
+static inline int clk_notifier_register(struct clk *clk,
+					struct notifier_block *nb)
+{
+	return -ENOTSUPP;
+}
+
+static inline int clk_notifier_unregister(struct clk *clk,
+					  struct notifier_block *nb)
+{
+	return -ENOTSUPP;
+}
+
 static inline long clk_get_accuracy(struct clk *clk)
 {
 	return -ENOTSUPP;
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index d9aef2a0ec8e..c78fc27418f2 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -99,7 +99,8 @@ static inline void context_tracking_init(void) { }
 
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-static inline void guest_enter(void)
+/* must be called with irqs disabled */
+static inline void guest_enter_irqoff(void)
 {
 	if (vtime_accounting_cpu_enabled())
 		vtime_guest_enter(current);
@@ -108,9 +109,19 @@ static inline void guest_enter(void)
 
 	if (context_tracking_is_enabled())
 		__context_tracking_enter(CONTEXT_GUEST);
+
+	/* KVM does not hold any references to rcu protected data when it
+	 * switches CPU into a guest mode. In fact switching to a guest mode
+	 * is very similar to exiting to userspace from rcu point of view. In
+	 * addition CPU may stay in a guest mode for quite a long time (up to
+	 * one time slice). Lets treat guest mode as quiescent state, just like
+	 * we do with user-mode execution.
+	 */
+	if (!context_tracking_cpu_is_enabled())
+		rcu_virt_note_context_switch(smp_processor_id());
 }
 
-static inline void guest_exit(void)
+static inline void guest_exit_irqoff(void)
 {
 	if (context_tracking_is_enabled())
 		__context_tracking_exit(CONTEXT_GUEST);
@@ -122,7 +133,7 @@ static inline void guest_exit(void)
 }
 
 #else
-static inline void guest_enter(void)
+static inline void guest_enter_irqoff(void)
 {
 	/*
 	 * This is running in ioctl context so its safe
@@ -131,9 +142,10 @@ static inline void guest_enter(void)
 	 */
 	vtime_account_system(current);
 	current->flags |= PF_VCPU;
+	rcu_virt_note_context_switch(smp_processor_id());
 }
 
-static inline void guest_exit(void)
+static inline void guest_exit_irqoff(void)
 {
 	/* Flush the guest cputime we spent on the guest */
 	vtime_account_system(current);
@@ -141,4 +153,22 @@ static inline void guest_exit(void)
 }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
 
+static inline void guest_enter(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	guest_enter_irqoff();
+	local_irq_restore(flags);
+}
+
+static inline void guest_exit(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	guest_exit_irqoff();
+	local_irq_restore(flags);
+}
+
 #endif
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index e828cf65d7df..da7fbf1cdd56 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -579,7 +579,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
 }
 
 /**
- * cpumask_parse - extract a cpumask from from a string
+ * cpumask_parse - extract a cpumask from a string
  * @buf: the buffer to extract from
  * @dstp: the cpumask to set.
  *
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 4551c6f2a6c4..e0b0741ae671 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -242,6 +242,4 @@ int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *,
 		 unsigned long);
 void *dma_buf_vmap(struct dma_buf *);
 void dma_buf_vunmap(struct dma_buf *, void *vaddr);
-int dma_buf_debugfs_create_file(const char *name,
-				int (*write)(struct seq_file *));
 #endif /* __DMA_BUF_H__ */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 7f80a75ee9e3..7f5a58225385 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -879,7 +879,7 @@ extern void efi_init (void);
 extern void *efi_get_pal_addr (void);
 extern void efi_map_pal_code (void);
 extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg);
-extern void efi_gettimeofday (struct timespec *ts);
+extern void efi_gettimeofday (struct timespec64 *ts);
 extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if possible */
 #ifdef CONFIG_X86
 extern void efi_late_init(void);
diff --git a/include/linux/export.h b/include/linux/export.h
index 2f9ccbe6a639..c565f87f005e 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -82,7 +82,7 @@ extern struct module __this_module;
 #include <generated/autoksyms.h>
 
 #define __EXPORT_SYMBOL(sym, sec)				\
-	__cond_export_sym(sym, sec, config_enabled(__KSYM_##sym))
+	__cond_export_sym(sym, sec, __is_defined(__KSYM_##sym))
 #define __cond_export_sym(sym, sec, conf)			\
 	___cond_export_sym(sym, sec, conf)
 #define ___cond_export_sym(sym, sec, enabled)			\
diff --git a/include/linux/fence-array.h b/include/linux/fence-array.h
new file mode 100644
index 000000000000..86baaa45567c
--- /dev/null
+++ b/include/linux/fence-array.h
@@ -0,0 +1,73 @@
+/*
+ * fence-array: aggregates fence to be waited together
+ *
+ * Copyright (C) 2016 Collabora Ltd
+ * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Gustavo Padovan <gustavo@padovan.org>
+ *	Christian König <christian.koenig@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __LINUX_FENCE_ARRAY_H
+#define __LINUX_FENCE_ARRAY_H
+
+#include <linux/fence.h>
+
+/**
+ * struct fence_array_cb - callback helper for fence array
+ * @cb: fence callback structure for signaling
+ * @array: reference to the parent fence array object
+ */
+struct fence_array_cb {
+	struct fence_cb cb;
+	struct fence_array *array;
+};
+
+/**
+ * struct fence_array - fence to represent an array of fences
+ * @base: fence base class
+ * @lock: spinlock for fence handling
+ * @num_fences: number of fences in the array
+ * @num_pending: fences in the array still pending
+ * @fences: array of the fences
+ */
+struct fence_array {
+	struct fence base;
+
+	spinlock_t lock;
+	unsigned num_fences;
+	atomic_t num_pending;
+	struct fence **fences;
+};
+
+extern const struct fence_ops fence_array_ops;
+
+/**
+ * to_fence_array - cast a fence to a fence_array
+ * @fence: fence to cast to a fence_array
+ *
+ * Returns NULL if the fence is not a fence_array,
+ * or the fence_array otherwise.
+ */
+static inline struct fence_array *to_fence_array(struct fence *fence)
+{
+	if (fence->ops != &fence_array_ops)
+		return NULL;
+
+	return container_of(fence, struct fence_array, base);
+}
+
+struct fence_array *fence_array_create(int num_fences, struct fence **fences,
+				       u64 context, unsigned seqno,
+				       bool signal_on_any);
+
+#endif /* __LINUX_FENCE_ARRAY_H */
diff --git a/include/linux/fence.h b/include/linux/fence.h
index 1de1b3f6fb76..523ea3fbbddd 100644
--- a/include/linux/fence.h
+++ b/include/linux/fence.h
@@ -77,7 +77,8 @@ struct fence {
 	struct rcu_head rcu;
 	struct list_head cb_list;
 	spinlock_t *lock;
-	unsigned context, seqno;
+	u64 context;
+	unsigned seqno;
 	unsigned long flags;
 	ktime_t timestamp;
 	int status;
@@ -178,7 +179,7 @@ struct fence_ops {
 };
 
 void fence_init(struct fence *fence, const struct fence_ops *ops,
-		spinlock_t *lock, unsigned context, unsigned seqno);
+		spinlock_t *lock, u64 context, unsigned seqno);
 
 void fence_release(struct kref *kref);
 void fence_free(struct fence *fence);
@@ -352,27 +353,27 @@ static inline signed long fence_wait(struct fence *fence, bool intr)
 	return ret < 0 ? ret : 0;
 }
 
-unsigned fence_context_alloc(unsigned num);
+u64 fence_context_alloc(unsigned num);
 
 #define FENCE_TRACE(f, fmt, args...) \
 	do {								\
 		struct fence *__ff = (f);				\
 		if (config_enabled(CONFIG_FENCE_TRACE))			\
-			pr_info("f %u#%u: " fmt,			\
+			pr_info("f %llu#%u: " fmt,			\
 				__ff->context, __ff->seqno, ##args);	\
 	} while (0)
 
 #define FENCE_WARN(f, fmt, args...) \
 	do {								\
 		struct fence *__ff = (f);				\
-		pr_warn("f %u#%u: " fmt, __ff->context, __ff->seqno,	\
+		pr_warn("f %llu#%u: " fmt, __ff->context, __ff->seqno,	\
 			 ##args);					\
 	} while (0)
 
 #define FENCE_ERR(f, fmt, args...) \
 	do {								\
 		struct fence *__ff = (f);				\
-		pr_err("f %u#%u: " fmt, __ff->context, __ff->seqno,	\
+		pr_err("f %llu#%u: " fmt, __ff->context, __ff->seqno,	\
 			##args);					\
 	} while (0)
 
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index 5c41c5e75b5c..b1f9f0ccb8ac 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -47,6 +47,8 @@ int request_firmware_nowait(
 	void (*cont)(const struct firmware *fw, void *context));
 int request_firmware_direct(const struct firmware **fw, const char *name,
 			    struct device *device);
+int request_firmware_into_buf(const struct firmware **firmware_p,
+	const char *name, struct device *device, void *buf, size_t size);
 
 void release_firmware(const struct firmware *fw);
 #else
@@ -75,5 +77,11 @@ static inline int request_firmware_direct(const struct firmware **fw,
 	return -EINVAL;
 }
 
+static inline int request_firmware_into_buf(const struct firmware **firmware_p,
+	const char *name, struct device *device, void *buf, size_t size)
+{
+	return -EINVAL;
+}
+
 #endif
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 577365a77b47..f3f0b4c8e8ac 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2652,6 +2652,7 @@ extern int do_pipe_flags(int *, int);
 #define __kernel_read_file_id(id) \
 	id(UNKNOWN, unknown)		\
 	id(FIRMWARE, firmware)		\
+	id(FIRMWARE_PREALLOC_BUFFER, firmware)	\
 	id(MODULE, kernel-module)		\
 	id(KEXEC_IMAGE, kexec-image)		\
 	id(KEXEC_INITRAMFS, kexec-initramfs)	\
diff --git a/include/linux/init.h b/include/linux/init.h
index aedb254abc37..6935d02474aa 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -77,12 +77,6 @@
 #define __refdata        __section(.ref.data)
 #define __refconst       __constsection(.ref.rodata)
 
-/* compatibility defines */
-#define __init_refok     __ref
-#define __initdata_refok __refdata
-#define __exit_refok     __ref
-
-
 #ifdef MODULE
 #define __exitused
 #else
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index e399029b68c5..645ad06b5d52 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -100,14 +100,16 @@ io_mapping_unmap_atomic(void __iomem *vaddr)
 }
 
 static inline void __iomem *
-io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
+io_mapping_map_wc(struct io_mapping *mapping,
+		  unsigned long offset,
+		  unsigned long size)
 {
 	resource_size_t phys_addr;
 
 	BUG_ON(offset >= mapping->size);
 	phys_addr = mapping->base + offset;
 
-	return ioremap_wc(phys_addr, PAGE_SIZE);
+	return ioremap_wc(phys_addr, size);
 }
 
 static inline void
@@ -155,7 +157,9 @@ io_mapping_unmap_atomic(void __iomem *vaddr)
 
 /* Non-atomic map/unmap */
 static inline void __iomem *
-io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
+io_mapping_map_wc(struct io_mapping *mapping,
+		  unsigned long offset,
+		  unsigned long size)
 {
 	return ((char __force __iomem *) mapping) + offset;
 }
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 664683aedcce..a35fb8b42e1a 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -152,6 +152,7 @@ struct iommu_dm_region {
  * @domain_set_attr: Change domain attributes
  * @get_dm_regions: Request list of direct mapping requirements for a device
  * @put_dm_regions: Free list of direct mapping requirements for a device
+ * @apply_dm_region: Temporary helper call-back for iova reserved ranges
  * @domain_window_enable: Configure and enable a particular window for a domain
  * @domain_window_disable: Disable a particular window for a domain
  * @domain_set_windows: Set the number of windows for a domain
@@ -186,6 +187,8 @@ struct iommu_ops {
 	/* Request/Free a list of direct mapping requirements for a device */
 	void (*get_dm_regions)(struct device *dev, struct list_head *list);
 	void (*put_dm_regions)(struct device *dev, struct list_head *list);
+	void (*apply_dm_region)(struct device *dev, struct iommu_domain *domain,
+				struct iommu_dm_region *region);
 
 	/* Window handling functions */
 	int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr,
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 1eee6bcfcf76..d10e54f03c09 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -63,8 +63,6 @@ struct ipc_namespace {
 };
 
 extern struct ipc_namespace init_ipc_ns;
-extern atomic_t nr_ipc_ns;
-
 extern spinlock_t mq_lock;
 
 #ifdef CONFIG_SYSVIPC
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 107eed475b94..56b0b7ec66aa 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -112,34 +112,76 @@
 #define GICR_WAKER_ProcessorSleep	(1U << 1)
 #define GICR_WAKER_ChildrenAsleep	(1U << 2)
 
-#define GICR_PROPBASER_NonShareable	(0U << 10)
-#define GICR_PROPBASER_InnerShareable	(1U << 10)
-#define GICR_PROPBASER_OuterShareable	(2U << 10)
-#define GICR_PROPBASER_SHAREABILITY_MASK (3UL << 10)
-#define GICR_PROPBASER_nCnB		(0U << 7)
-#define GICR_PROPBASER_nC		(1U << 7)
-#define GICR_PROPBASER_RaWt		(2U << 7)
-#define GICR_PROPBASER_RaWb		(3U << 7)
-#define GICR_PROPBASER_WaWt		(4U << 7)
-#define GICR_PROPBASER_WaWb		(5U << 7)
-#define GICR_PROPBASER_RaWaWt		(6U << 7)
-#define GICR_PROPBASER_RaWaWb		(7U << 7)
-#define GICR_PROPBASER_CACHEABILITY_MASK (7U << 7)
-#define GICR_PROPBASER_IDBITS_MASK	(0x1f)
-
-#define GICR_PENDBASER_NonShareable	(0U << 10)
-#define GICR_PENDBASER_InnerShareable	(1U << 10)
-#define GICR_PENDBASER_OuterShareable	(2U << 10)
-#define GICR_PENDBASER_SHAREABILITY_MASK (3UL << 10)
-#define GICR_PENDBASER_nCnB		(0U << 7)
-#define GICR_PENDBASER_nC		(1U << 7)
-#define GICR_PENDBASER_RaWt		(2U << 7)
-#define GICR_PENDBASER_RaWb		(3U << 7)
-#define GICR_PENDBASER_WaWt		(4U << 7)
-#define GICR_PENDBASER_WaWb		(5U << 7)
-#define GICR_PENDBASER_RaWaWt		(6U << 7)
-#define GICR_PENDBASER_RaWaWb		(7U << 7)
-#define GICR_PENDBASER_CACHEABILITY_MASK (7U << 7)
+#define GIC_BASER_CACHE_nCnB		0ULL
+#define GIC_BASER_CACHE_SameAsInner	0ULL
+#define GIC_BASER_CACHE_nC		1ULL
+#define GIC_BASER_CACHE_RaWt		2ULL
+#define GIC_BASER_CACHE_RaWb		3ULL
+#define GIC_BASER_CACHE_WaWt		4ULL
+#define GIC_BASER_CACHE_WaWb		5ULL
+#define GIC_BASER_CACHE_RaWaWt		6ULL
+#define GIC_BASER_CACHE_RaWaWb		7ULL
+#define GIC_BASER_CACHE_MASK		7ULL
+#define GIC_BASER_NonShareable		0ULL
+#define GIC_BASER_InnerShareable	1ULL
+#define GIC_BASER_OuterShareable	2ULL
+#define GIC_BASER_SHAREABILITY_MASK	3ULL
+
+#define GIC_BASER_CACHEABILITY(reg, inner_outer, type)			\
+	(GIC_BASER_CACHE_##type << reg##_##inner_outer##_CACHEABILITY_SHIFT)
+
+#define GIC_BASER_SHAREABILITY(reg, type)				\
+	(GIC_BASER_##type << reg##_SHAREABILITY_SHIFT)
+
+#define GICR_PROPBASER_SHAREABILITY_SHIFT		(10)
+#define GICR_PROPBASER_INNER_CACHEABILITY_SHIFT		(7)
+#define GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT		(56)
+#define GICR_PROPBASER_SHAREABILITY_MASK				\
+	GIC_BASER_SHAREABILITY(GICR_PROPBASER, SHAREABILITY_MASK)
+#define GICR_PROPBASER_INNER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, MASK)
+#define GICR_PROPBASER_OUTER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, MASK)
+#define GICR_PROPBASER_CACHEABILITY_MASK GICR_PROPBASER_INNER_CACHEABILITY_MASK
+
+#define GICR_PROPBASER_InnerShareable					\
+	GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable)
+
+#define GICR_PROPBASER_nCnB	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nCnB)
+#define GICR_PROPBASER_nC 	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nC)
+#define GICR_PROPBASER_RaWt	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWt)
+#define GICR_PROPBASER_RaWb	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWt)
+#define GICR_PROPBASER_WaWt	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWt)
+#define GICR_PROPBASER_WaWb	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWb)
+#define GICR_PROPBASER_RaWaWt	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWt)
+#define GICR_PROPBASER_RaWaWb	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWb)
+
+#define GICR_PROPBASER_IDBITS_MASK			(0x1f)
+
+#define GICR_PENDBASER_SHAREABILITY_SHIFT		(10)
+#define GICR_PENDBASER_INNER_CACHEABILITY_SHIFT		(7)
+#define GICR_PENDBASER_OUTER_CACHEABILITY_SHIFT		(56)
+#define GICR_PENDBASER_SHAREABILITY_MASK				\
+	GIC_BASER_SHAREABILITY(GICR_PENDBASER, SHAREABILITY_MASK)
+#define GICR_PENDBASER_INNER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, MASK)
+#define GICR_PENDBASER_OUTER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, MASK)
+#define GICR_PENDBASER_CACHEABILITY_MASK GICR_PENDBASER_INNER_CACHEABILITY_MASK
+
+#define GICR_PENDBASER_InnerShareable					\
+	GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable)
+
+#define GICR_PENDBASER_nCnB	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nCnB)
+#define GICR_PENDBASER_nC 	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nC)
+#define GICR_PENDBASER_RaWt	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWt)
+#define GICR_PENDBASER_RaWb	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWt)
+#define GICR_PENDBASER_WaWt	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWt)
+#define GICR_PENDBASER_WaWb	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWb)
+#define GICR_PENDBASER_RaWaWt	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWaWt)
+#define GICR_PENDBASER_RaWaWb	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWaWb)
+
+#define GICR_PENDBASER_PTZ				BIT_ULL(62)
 
 /*
  * Re-Distributor registers, offsets from SGI_base
@@ -175,54 +217,83 @@
 #define GITS_CWRITER			0x0088
 #define GITS_CREADR			0x0090
 #define GITS_BASER			0x0100
+#define GITS_IDREGS_BASE		0xffd0
+#define GITS_PIDR0			0xffe0
+#define GITS_PIDR1			0xffe4
 #define GITS_PIDR2			GICR_PIDR2
+#define GITS_PIDR4			0xffd0
+#define GITS_CIDR0			0xfff0
+#define GITS_CIDR1			0xfff4
+#define GITS_CIDR2			0xfff8
+#define GITS_CIDR3			0xfffc
 
 #define GITS_TRANSLATER			0x10040
 
 #define GITS_CTLR_ENABLE		(1U << 0)
 #define GITS_CTLR_QUIESCENT		(1U << 31)
 
+#define GITS_TYPER_PLPIS		(1UL << 0)
+#define GITS_TYPER_IDBITS_SHIFT		8
 #define GITS_TYPER_DEVBITS_SHIFT	13
 #define GITS_TYPER_DEVBITS(r)		((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)
 #define GITS_TYPER_PTA			(1UL << 19)
-
-#define GITS_CBASER_VALID		(1UL << 63)
-#define GITS_CBASER_nCnB		(0UL << 59)
-#define GITS_CBASER_nC			(1UL << 59)
-#define GITS_CBASER_RaWt		(2UL << 59)
-#define GITS_CBASER_RaWb		(3UL << 59)
-#define GITS_CBASER_WaWt		(4UL << 59)
-#define GITS_CBASER_WaWb		(5UL << 59)
-#define GITS_CBASER_RaWaWt		(6UL << 59)
-#define GITS_CBASER_RaWaWb		(7UL << 59)
-#define GITS_CBASER_CACHEABILITY_MASK	(7UL << 59)
-#define GITS_CBASER_NonShareable	(0UL << 10)
-#define GITS_CBASER_InnerShareable	(1UL << 10)
-#define GITS_CBASER_OuterShareable	(2UL << 10)
-#define GITS_CBASER_SHAREABILITY_MASK	(3UL << 10)
+#define GITS_TYPER_HWCOLLCNT_SHIFT	24
+
+#define GITS_CBASER_VALID			(1UL << 63)
+#define GITS_CBASER_SHAREABILITY_SHIFT		(10)
+#define GITS_CBASER_INNER_CACHEABILITY_SHIFT	(59)
+#define GITS_CBASER_OUTER_CACHEABILITY_SHIFT	(53)
+#define GITS_CBASER_SHAREABILITY_MASK					\
+	GIC_BASER_SHAREABILITY(GITS_CBASER, SHAREABILITY_MASK)
+#define GITS_CBASER_INNER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, MASK)
+#define GITS_CBASER_OUTER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GITS_CBASER, OUTER, MASK)
+#define GITS_CBASER_CACHEABILITY_MASK GITS_CBASER_INNER_CACHEABILITY_MASK
+
+#define GITS_CBASER_InnerShareable					\
+	GIC_BASER_SHAREABILITY(GITS_CBASER, InnerShareable)
+
+#define GITS_CBASER_nCnB	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nCnB)
+#define GITS_CBASER_nC		GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nC)
+#define GITS_CBASER_RaWt	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWt)
+#define GITS_CBASER_RaWb	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWt)
+#define GITS_CBASER_WaWt	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWt)
+#define GITS_CBASER_WaWb	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWb)
+#define GITS_CBASER_RaWaWt	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWt)
+#define GITS_CBASER_RaWaWb	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWb)
 
 #define GITS_BASER_NR_REGS		8
 
-#define GITS_BASER_VALID		(1UL << 63)
-#define GITS_BASER_INDIRECT		(1UL << 62)
-#define GITS_BASER_nCnB			(0UL << 59)
-#define GITS_BASER_nC			(1UL << 59)
-#define GITS_BASER_RaWt			(2UL << 59)
-#define GITS_BASER_RaWb			(3UL << 59)
-#define GITS_BASER_WaWt			(4UL << 59)
-#define GITS_BASER_WaWb			(5UL << 59)
-#define GITS_BASER_RaWaWt		(6UL << 59)
-#define GITS_BASER_RaWaWb		(7UL << 59)
-#define GITS_BASER_CACHEABILITY_MASK	(7UL << 59)
-#define GITS_BASER_TYPE_SHIFT		(56)
+#define GITS_BASER_VALID			(1UL << 63)
+#define GITS_BASER_INDIRECT			(1ULL << 62)
+
+#define GITS_BASER_INNER_CACHEABILITY_SHIFT	(59)
+#define GITS_BASER_OUTER_CACHEABILITY_SHIFT	(53)
+#define GITS_BASER_INNER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GITS_BASER, INNER, MASK)
+#define GITS_BASER_CACHEABILITY_MASK		GITS_BASER_INNER_CACHEABILITY_MASK
+#define GITS_BASER_OUTER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, MASK)
+#define GITS_BASER_SHAREABILITY_MASK					\
+	GIC_BASER_SHAREABILITY(GITS_BASER, SHAREABILITY_MASK)
+
+#define GITS_BASER_nCnB		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nCnB)
+#define GITS_BASER_nC		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nC)
+#define GITS_BASER_RaWt		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWt)
+#define GITS_BASER_RaWb		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWt)
+#define GITS_BASER_WaWt		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWt)
+#define GITS_BASER_WaWb		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWb)
+#define GITS_BASER_RaWaWt	GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWaWt)
+#define GITS_BASER_RaWaWb	GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWaWb)
+
+#define GITS_BASER_TYPE_SHIFT			(56)
 #define GITS_BASER_TYPE(r)		(((r) >> GITS_BASER_TYPE_SHIFT) & 7)
-#define GITS_BASER_ENTRY_SIZE_SHIFT	(48)
+#define GITS_BASER_ENTRY_SIZE_SHIFT		(48)
 #define GITS_BASER_ENTRY_SIZE(r)	((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0xff) + 1)
-#define GITS_BASER_NonShareable		(0UL << 10)
-#define GITS_BASER_InnerShareable	(1UL << 10)
-#define GITS_BASER_OuterShareable	(2UL << 10)
 #define GITS_BASER_SHAREABILITY_SHIFT	(10)
-#define GITS_BASER_SHAREABILITY_MASK	(3UL << GITS_BASER_SHAREABILITY_SHIFT)
+#define GITS_BASER_InnerShareable					\
+	GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
 #define GITS_BASER_PAGE_SIZE_SHIFT	(8)
 #define GITS_BASER_PAGE_SIZE_4K		(0UL << GITS_BASER_PAGE_SIZE_SHIFT)
 #define GITS_BASER_PAGE_SIZE_16K	(1UL << GITS_BASER_PAGE_SIZE_SHIFT)
@@ -230,6 +301,7 @@
 #define GITS_BASER_PAGE_SIZE_MASK	(3UL << GITS_BASER_PAGE_SIZE_SHIFT)
 #define GITS_BASER_PAGES_MAX		256
 #define GITS_BASER_PAGES_SHIFT		(0)
+#define GITS_BASER_NR_PAGES(r)		(((r) & 0xff) + 1)
 
 #define GITS_BASER_TYPE_NONE		0
 #define GITS_BASER_TYPE_DEVICE		1
@@ -247,7 +319,10 @@
  */
 #define GITS_CMD_MAPD			0x08
 #define GITS_CMD_MAPC			0x09
-#define GITS_CMD_MAPVI			0x0a
+#define GITS_CMD_MAPTI			0x0a
+/* older GIC documentation used MAPVI for this command */
+#define GITS_CMD_MAPVI			GITS_CMD_MAPTI
+#define GITS_CMD_MAPI			0x0b
 #define GITS_CMD_MOVI			0x01
 #define GITS_CMD_DISCARD		0x0f
 #define GITS_CMD_INV			0x0c
@@ -258,6 +333,22 @@
 #define GITS_CMD_SYNC			0x05
 
 /*
+ * ITS error numbers
+ */
+#define E_ITS_MOVI_UNMAPPED_INTERRUPT		0x010107
+#define E_ITS_MOVI_UNMAPPED_COLLECTION		0x010109
+#define E_ITS_CLEAR_UNMAPPED_INTERRUPT		0x010507
+#define E_ITS_MAPD_DEVICE_OOR			0x010801
+#define E_ITS_MAPC_PROCNUM_OOR			0x010902
+#define E_ITS_MAPC_COLLECTION_OOR		0x010903
+#define E_ITS_MAPTI_UNMAPPED_DEVICE		0x010a04
+#define E_ITS_MAPTI_PHYSICALID_OOR		0x010a06
+#define E_ITS_INV_UNMAPPED_INTERRUPT		0x010c07
+#define E_ITS_INVALL_UNMAPPED_COLLECTION	0x010d09
+#define E_ITS_MOVALL_PROCNUM_OOR		0x010e01
+#define E_ITS_DISCARD_UNMAPPED_INTERRUPT	0x010f07
+
+/*
  * CPU interface registers
  */
 #define ICC_CTLR_EL1_EOImode_drop_dir	(0U << 1)
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index c9cf374445d8..d600303306eb 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -56,6 +56,7 @@ void kasan_cache_destroy(struct kmem_cache *cache);
 void kasan_poison_slab(struct page *page);
 void kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
 void kasan_poison_object_data(struct kmem_cache *cache, void *object);
+void kasan_init_slab_obj(struct kmem_cache *cache, const void *object);
 
 void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags);
 void kasan_kfree_large(const void *ptr);
@@ -102,6 +103,8 @@ static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
 					void *object) {}
 static inline void kasan_poison_object_data(struct kmem_cache *cache,
 					void *object) {}
+static inline void kasan_init_slab_obj(struct kmem_cache *cache,
+				const void *object) {}
 
 static inline void kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags) {}
 static inline void kasan_kfree_large(const void *ptr) {}
diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h
index b33c7797eb57..15ec117ec537 100644
--- a/include/linux/kconfig.h
+++ b/include/linux/kconfig.h
@@ -3,6 +3,21 @@
 
 #include <generated/autoconf.h>
 
+#define __ARG_PLACEHOLDER_1 0,
+#define __take_second_arg(__ignored, val, ...) val
+
+/*
+ * The use of "&&" / "||" is limited in certain expressions.
+ * The followings enable to calculate "and" / "or" with macro expansion only.
+ */
+#define __and(x, y)			___and(x, y)
+#define ___and(x, y)			____and(__ARG_PLACEHOLDER_##x, y)
+#define ____and(arg1_or_junk, y)	__take_second_arg(arg1_or_junk y, 0)
+
+#define __or(x, y)			___or(x, y)
+#define ___or(x, y)			____or(__ARG_PLACEHOLDER_##x, y)
+#define ____or(arg1_or_junk, y)		__take_second_arg(arg1_or_junk 1, y)
+
 /*
  * Helper macros to use CONFIG_ options in C/CPP expressions. Note that
  * these only work with boolean and tristate options.
@@ -16,11 +31,10 @@
  * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
  * the last step cherry picks the 2nd arg, we get a zero.
  */
-#define __ARG_PLACEHOLDER_1 0,
-#define config_enabled(cfg) _config_enabled(cfg)
-#define _config_enabled(value) __config_enabled(__ARG_PLACEHOLDER_##value)
-#define __config_enabled(arg1_or_junk) ___config_enabled(arg1_or_junk 1, 0)
-#define ___config_enabled(__ignored, val, ...) val
+#define config_enabled(cfg)		___is_defined(cfg)
+#define __is_defined(x)			___is_defined(x)
+#define ___is_defined(val)		____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk)	__take_second_arg(arg1_or_junk 1, 0)
 
 /*
  * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
@@ -41,14 +55,13 @@
  * This is similar to IS_ENABLED(), but returns false when invoked from
  * built-in code when CONFIG_FOO is set to 'm'.
  */
-#define IS_REACHABLE(option) (config_enabled(option) || \
-		 (config_enabled(option##_MODULE) && config_enabled(MODULE)))
+#define IS_REACHABLE(option) __or(IS_BUILTIN(option), \
+				__and(IS_MODULE(option), __is_defined(MODULE)))
 
 /*
  * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm',
  * 0 otherwise.
  */
-#define IS_ENABLED(option) \
-	(IS_BUILTIN(option) || IS_MODULE(option))
+#define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option))
 
 #endif /* __LINUX_KCONFIG_H */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index c42082112ec8..d96a6118d26a 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -11,7 +11,6 @@
 #include <linux/log2.h>
 #include <linux/typecheck.h>
 #include <linux/printk.h>
-#include <linux/dynamic_debug.h>
 #include <asm/byteorder.h>
 #include <uapi/linux/kernel.h>
 
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index e8acb2b43dd9..d7437777baaa 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -14,6 +14,8 @@
 
 #if !defined(__ASSEMBLY__)
 
+#include <asm/io.h>
+
 #include <uapi/linux/kexec.h>
 
 #ifdef CONFIG_KEXEC_CORE
@@ -41,7 +43,7 @@
 #endif
 
 #ifndef KEXEC_CONTROL_MEMORY_GFP
-#define KEXEC_CONTROL_MEMORY_GFP GFP_KERNEL
+#define KEXEC_CONTROL_MEMORY_GFP (GFP_KERNEL | __GFP_NORETRY)
 #endif
 
 #ifndef KEXEC_CONTROL_PAGE_SIZE
@@ -228,12 +230,13 @@ extern void *kexec_purgatory_get_symbol_addr(struct kimage *image,
 extern void __crash_kexec(struct pt_regs *);
 extern void crash_kexec(struct pt_regs *);
 int kexec_should_crash(struct task_struct *);
+int kexec_crash_loaded(void);
 void crash_save_cpu(struct pt_regs *regs, int cpu);
 void crash_save_vmcoreinfo(void);
 void arch_crash_save_vmcoreinfo(void);
 __printf(1, 2)
 void vmcoreinfo_append_str(const char *fmt, ...);
-unsigned long paddr_vmcoreinfo_note(void);
+phys_addr_t paddr_vmcoreinfo_note(void);
 
 #define VMCOREINFO_OSRELEASE(value) \
 	vmcoreinfo_append_str("OSRELEASE=%s\n", value)
@@ -318,12 +321,51 @@ int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 void arch_kexec_protect_crashkres(void);
 void arch_kexec_unprotect_crashkres(void);
 
+#ifndef page_to_boot_pfn
+static inline unsigned long page_to_boot_pfn(struct page *page)
+{
+	return page_to_pfn(page);
+}
+#endif
+
+#ifndef boot_pfn_to_page
+static inline struct page *boot_pfn_to_page(unsigned long boot_pfn)
+{
+	return pfn_to_page(boot_pfn);
+}
+#endif
+
+#ifndef phys_to_boot_phys
+static inline unsigned long phys_to_boot_phys(phys_addr_t phys)
+{
+	return phys;
+}
+#endif
+
+#ifndef boot_phys_to_phys
+static inline phys_addr_t boot_phys_to_phys(unsigned long boot_phys)
+{
+	return boot_phys;
+}
+#endif
+
+static inline unsigned long virt_to_boot_phys(void *addr)
+{
+	return phys_to_boot_phys(__pa((unsigned long)addr));
+}
+
+static inline void *boot_phys_to_virt(unsigned long entry)
+{
+	return phys_to_virt(boot_phys_to_phys(entry));
+}
+
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
 static inline void __crash_kexec(struct pt_regs *regs) { }
 static inline void crash_kexec(struct pt_regs *regs) { }
 static inline int kexec_should_crash(struct task_struct *p) { return 0; }
+static inline int kexec_crash_loaded(void) { return 0; }
 #define kexec_in_progress false
 #endif /* CONFIG_KEXEC_CORE */
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1c9c973a7dd9..aafd702f3e21 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -164,6 +164,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev);
 int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			      struct kvm_io_device *dev);
+struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+					 gpa_t addr);
 
 #ifdef CONFIG_KVM_ASYNC_PF
 struct kvm_async_pf {
@@ -371,7 +373,15 @@ struct kvm {
 	struct srcu_struct srcu;
 	struct srcu_struct irq_srcu;
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
+
+	/*
+	 * created_vcpus is protected by kvm->lock, and is incremented
+	 * at the beginning of KVM_CREATE_VCPU.  online_vcpus is only
+	 * incremented after storing the kvm_vcpu pointer in vcpus,
+	 * and is accessed atomically.
+	 */
 	atomic_t online_vcpus;
+	int created_vcpus;
 	int last_boosted_vcpu;
 	struct list_head vm_list;
 	struct mutex lock;
@@ -867,45 +877,6 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm,
 }
 #endif
 
-/* must be called with irqs disabled */
-static inline void __kvm_guest_enter(void)
-{
-	guest_enter();
-	/* KVM does not hold any references to rcu protected data when it
-	 * switches CPU into a guest mode. In fact switching to a guest mode
-	 * is very similar to exiting to userspace from rcu point of view. In
-	 * addition CPU may stay in a guest mode for quite a long time (up to
-	 * one time slice). Lets treat guest mode as quiescent state, just like
-	 * we do with user-mode execution.
-	 */
-	if (!context_tracking_cpu_is_enabled())
-		rcu_virt_note_context_switch(smp_processor_id());
-}
-
-/* must be called with irqs disabled */
-static inline void __kvm_guest_exit(void)
-{
-	guest_exit();
-}
-
-static inline void kvm_guest_enter(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__kvm_guest_enter();
-	local_irq_restore(flags);
-}
-
-static inline void kvm_guest_exit(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__kvm_guest_exit();
-	local_irq_restore(flags);
-}
-
 /*
  * search_memslots() and __gfn_to_memslot() are here because they are
  * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c.
@@ -1042,7 +1013,8 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			const struct kvm_irq_routing_entry *entries,
 			unsigned nr,
 			unsigned flags);
-int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm *kvm,
+			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue);
 void kvm_free_irq_routing(struct kvm *kvm);
 
@@ -1097,12 +1069,6 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 #endif /* CONFIG_HAVE_KVM_EVENTFD */
 
-#ifdef CONFIG_KVM_APIC_ARCHITECTURE
-bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu);
-#else
-static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; }
-#endif
-
 static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
 {
 	/*
diff --git a/include/linux/mailbox/brcm-message.h b/include/linux/mailbox/brcm-message.h
new file mode 100644
index 000000000000..6b55c938b401
--- /dev/null
+++ b/include/linux/mailbox/brcm-message.h
@@ -0,0 +1,56 @@
+/*
+ *  Copyright (C) 2016 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Common header for Broadcom mailbox messages which is shared across
+ * Broadcom SoCs and Broadcom mailbox client drivers.
+ */
+
+#ifndef _LINUX_BRCM_MESSAGE_H_
+#define _LINUX_BRCM_MESSAGE_H_
+
+#include <linux/scatterlist.h>
+
+enum brcm_message_type {
+	BRCM_MESSAGE_UNKNOWN = 0,
+	BRCM_MESSAGE_SPU,
+	BRCM_MESSAGE_SBA,
+	BRCM_MESSAGE_MAX,
+};
+
+struct brcm_sba_command {
+	u64 cmd;
+#define BRCM_SBA_CMD_TYPE_A		BIT(0)
+#define BRCM_SBA_CMD_TYPE_B		BIT(1)
+#define BRCM_SBA_CMD_TYPE_C		BIT(2)
+#define BRCM_SBA_CMD_HAS_RESP		BIT(3)
+#define BRCM_SBA_CMD_HAS_OUTPUT		BIT(4)
+	u64 flags;
+	dma_addr_t input;
+	size_t input_len;
+	dma_addr_t resp;
+	size_t resp_len;
+	dma_addr_t output;
+	size_t output_len;
+};
+
+struct brcm_message {
+	enum brcm_message_type type;
+	union {
+		struct {
+			struct scatterlist *src;
+			struct scatterlist *dst;
+		} spu;
+		struct {
+			struct brcm_sba_command *cmds;
+			unsigned int cmds_count;
+		} sba;
+	};
+	void *ctx;
+	int error;
+};
+
+#endif /* _LINUX_BRCM_MESSAGE_H_ */
diff --git a/include/linux/mbus.h b/include/linux/mbus.h
index ea34a867caa0..d610232762e3 100644
--- a/include/linux/mbus.h
+++ b/include/linux/mbus.h
@@ -66,7 +66,7 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(vo
 }
 #endif
 
-int mvebu_mbus_save_cpu_target(u32 *store_addr);
+int mvebu_mbus_save_cpu_target(u32 __iomem *store_addr);
 void mvebu_mbus_get_pcie_mem_aperture(struct resource *res);
 void mvebu_mbus_get_pcie_io_aperture(struct resource *res);
 int mvebu_mbus_get_dram_win_info(phys_addr_t phyaddr, u8 *target, u8 *attr);
diff --git a/include/linux/mfd/abx500/ab8500-sysctrl.h b/include/linux/mfd/abx500/ab8500-sysctrl.h
index 689312745b2f..01024d1aed0e 100644
--- a/include/linux/mfd/abx500/ab8500-sysctrl.h
+++ b/include/linux/mfd/abx500/ab8500-sysctrl.h
@@ -37,12 +37,6 @@ static inline int ab8500_sysctrl_clear(u16 reg, u8 bits)
 	return ab8500_sysctrl_write(reg, bits, 0);
 }
 
-/* Configuration data for SysClkReq1RfClkBuf - SysClkReq8RfClkBuf */
-struct ab8500_sysctrl_platform_data {
-	u8 initial_req_buf_config[8];
-	u16 (*reboot_reason_code)(const char *cmd);
-};
-
 /* Registers */
 #define AB8500_TURNONSTATUS		0x100
 #define AB8500_RESETSTATUS		0x101
diff --git a/include/linux/mfd/altera-a10sr.h b/include/linux/mfd/altera-a10sr.h
new file mode 100644
index 000000000000..45a5e6e7db54
--- /dev/null
+++ b/include/linux/mfd/altera-a10sr.h
@@ -0,0 +1,85 @@
+/*
+ * Copyright Intel Corporation (C) 2014-2016. All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Declarations for Altera Arria10 MAX5 System Resource Chip
+ *
+ * Adapted from DA9052
+ */
+
+#ifndef __MFD_ALTERA_A10SR_H
+#define __MFD_ALTERA_A10SR_H
+
+#include <linux/completion.h>
+#include <linux/list.h>
+#include <linux/mfd/core.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+/* Write registers are always on even addresses */
+#define  WRITE_REG_MASK              0xFE
+/* Odd registers are always on odd addresses */
+#define  READ_REG_MASK               0x01
+
+#define ALTR_A10SR_BITS_PER_REGISTER  8
+/*
+ * To find the correct register, we divide the input GPIO by
+ * the number of GPIO in each register. We then need to multiply
+ * by 2 because the reads are at odd addresses.
+ */
+#define ALTR_A10SR_REG_OFFSET(X)     (((X) / ALTR_A10SR_BITS_PER_REGISTER) << 1)
+#define ALTR_A10SR_REG_BIT(X)        ((X) % ALTR_A10SR_BITS_PER_REGISTER)
+#define ALTR_A10SR_REG_BIT_CHG(X, Y) ((X) << ALTR_A10SR_REG_BIT(Y))
+#define ALTR_A10SR_REG_BIT_MASK(X)   (1 << ALTR_A10SR_REG_BIT(X))
+
+/* Arria10 System Controller Register Defines */
+#define ALTR_A10SR_NOP                0x00    /* No Change */
+#define ALTR_A10SR_VERSION_READ       0x00    /* MAX5 Version Read */
+
+#define ALTR_A10SR_LED_REG            0x02    /* LED - Upper 4 bits */
+/* LED register Bit Definitions */
+#define ALTR_A10SR_LED_VALID_SHIFT        4       /* LED - Upper 4 bits valid */
+#define ALTR_A10SR_OUT_VALID_RANGE_LO     ALTR_A10SR_LED_VALID_SHIFT
+#define ALTR_A10SR_OUT_VALID_RANGE_HI     7
+
+#define ALTR_A10SR_PBDSW_REG          0x04    /* PB & DIP SW - Input only */
+#define ALTR_A10SR_PBDSW_IRQ_REG      0x06    /* PB & DIP SW Flag Clear */
+/* Pushbutton & DIP Switch Bit Definitions */
+#define ALTR_A10SR_IN_VALID_RANGE_LO      8
+#define ALTR_A10SR_IN_VALID_RANGE_HI      15
+
+#define ALTR_A10SR_PWR_GOOD1_REG      0x08    /* Power Good1 Read */
+#define ALTR_A10SR_PWR_GOOD2_REG      0x0A    /* Power Good2 Read */
+#define ALTR_A10SR_PWR_GOOD3_REG      0x0C    /* Power Good3 Read */
+#define ALTR_A10SR_FMCAB_REG          0x0E    /* FMCA/B & PCIe Pwr Enable */
+#define ALTR_A10SR_HPS_RST_REG        0x10    /* HPS Reset */
+#define ALTR_A10SR_USB_QSPI_REG       0x12    /* USB, BQSPI, FILE Reset */
+#define ALTR_A10SR_SFPA_REG           0x14    /* SFPA Control Reg */
+#define ALTR_A10SR_SFPB_REG           0x16    /* SFPB Control Reg */
+#define ALTR_A10SR_I2C_M_REG          0x18    /* I2C Master Select */
+#define ALTR_A10SR_WARM_RST_REG       0x1A    /* HPS Warm Reset */
+#define ALTR_A10SR_WR_KEY_REG         0x1C    /* HPS Warm Reset Key */
+#define ALTR_A10SR_PMBUS_REG          0x1E    /* HPS PM Bus */
+
+/**
+ * struct altr_a10sr - Altera Max5 MFD device private data structure
+ * @dev:  : this device
+ * @regmap: the regmap assigned to the parent device.
+ */
+struct altr_a10sr {
+	struct device *dev;
+	struct regmap *regmap;
+};
+
+#endif /* __MFD_ALTERA_A10SR_H */
diff --git a/include/linux/mfd/arizona/core.h b/include/linux/mfd/arizona/core.h
index d55a42297d49..58ab4c0fe761 100644
--- a/include/linux/mfd/arizona/core.h
+++ b/include/linux/mfd/arizona/core.h
@@ -14,6 +14,7 @@
 #define _WM_ARIZONA_CORE_H
 
 #include <linux/interrupt.h>
+#include <linux/notifier.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/mfd/arizona/pdata.h>
@@ -148,8 +149,17 @@ struct arizona {
 	uint16_t dac_comp_coeff;
 	uint8_t dac_comp_enabled;
 	struct mutex dac_comp_lock;
+
+	struct blocking_notifier_head notifier;
 };
 
+static inline int arizona_call_notifiers(struct arizona *arizona,
+					 unsigned long event,
+					 void *data)
+{
+	return blocking_notifier_call_chain(&arizona->notifier, event, data);
+}
+
 int arizona_clk32k_enable(struct arizona *arizona);
 int arizona_clk32k_disable(struct arizona *arizona);
 
diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index cd7e78eae006..0d06c5d0af93 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -856,12 +856,6 @@
 #define ARIZONA_ISRC1INT4MIX_INPUT_1_SOURCE      0xB38
 #define ARIZONA_ISRC2DEC1MIX_INPUT_1_SOURCE      0xB40
 #define ARIZONA_ISRC2DEC2MIX_INPUT_1_SOURCE      0xB48
-#define ARIZONA_ISRC2INT1MIX_INPUT_1_SOURCE      0xB60
-#define ARIZONA_ISRC2INT2MIX_INPUT_1_SOURCE      0xB68
-#define ARIZONA_ISRC1INT3MIX_INPUT_1_SOURCE      0xB30
-#define ARIZONA_ISRC1INT4MIX_INPUT_1_SOURCE      0xB38
-#define ARIZONA_ISRC2DEC1MIX_INPUT_1_SOURCE      0xB40
-#define ARIZONA_ISRC2DEC2MIX_INPUT_1_SOURCE      0xB48
 #define ARIZONA_ISRC2DEC3MIX_INPUT_1_SOURCE      0xB50
 #define ARIZONA_ISRC2DEC4MIX_INPUT_1_SOURCE      0xB58
 #define ARIZONA_ISRC2INT1MIX_INPUT_1_SOURCE      0xB60
diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h
index bf5109d38a26..5d374601404c 100644
--- a/include/linux/mfd/dbx500-prcmu.h
+++ b/include/linux/mfd/dbx500-prcmu.h
@@ -178,16 +178,6 @@ enum ddr_pwrst {
 
 #define DB8500_PRCMU_LEGACY_OFFSET		0xDD4
 
-struct prcmu_pdata
-{
-	bool enable_set_ddr_opp;
-	bool enable_ape_opp_100_voltage;
-	struct ab8500_platform_data *ab_platdata;
-	u32 version_offset;
-	u32 legacy_offset;
-	u32 adt_offset;
-};
-
 #define PRCMU_FW_PROJECT_U8500		2
 #define PRCMU_FW_PROJECT_U8400		3
 #define PRCMU_FW_PROJECT_U9500		4 /* Customer specific */
diff --git a/include/linux/mfd/hi655x-pmic.h b/include/linux/mfd/hi655x-pmic.h
index dbbe9a644622..62f03c2b1bb0 100644
--- a/include/linux/mfd/hi655x-pmic.h
+++ b/include/linux/mfd/hi655x-pmic.h
@@ -34,14 +34,23 @@
 #define PMU_VER_START                   0x10
 #define PMU_VER_END                     0x38
 
-#define RESERVE_INT                     BIT(7)
-#define PWRON_D20R_INT                  BIT(6)
-#define PWRON_D20F_INT                  BIT(5)
-#define PWRON_D4SR_INT                  BIT(4)
-#define VSYS_6P0_D200UR_INT             BIT(3)
-#define VSYS_UV_D3R_INT                 BIT(2)
-#define VSYS_2P5_R_INT                  BIT(1)
-#define OTMP_D1R_INT                    BIT(0)
+#define RESERVE_INT                     7
+#define PWRON_D20R_INT                  6
+#define PWRON_D20F_INT                  5
+#define PWRON_D4SR_INT                  4
+#define VSYS_6P0_D200UR_INT             3
+#define VSYS_UV_D3R_INT                 2
+#define VSYS_2P5_R_INT                  1
+#define OTMP_D1R_INT                    0
+
+#define RESERVE_INT_MASK                BIT(RESERVE_INT)
+#define PWRON_D20R_INT_MASK             BIT(PWRON_D20R_INT)
+#define PWRON_D20F_INT_MASK             BIT(PWRON_D20F_INT)
+#define PWRON_D4SR_INT_MASK             BIT(PWRON_D4SR_INT)
+#define VSYS_6P0_D200UR_INT_MASK        BIT(VSYS_6P0_D200UR_INT)
+#define VSYS_UV_D3R_INT_MASK            BIT(VSYS_UV_D3R_INT)
+#define VSYS_2P5_R_INT_MASK             BIT(VSYS_2P5_R_INT)
+#define OTMP_D1R_INT_MASK               BIT(OTMP_D1R_INT)
 
 struct hi655x_pmic {
 	struct resource *res;
diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h
index cb83883918a7..de748bc7525e 100644
--- a/include/linux/mfd/stmpe.h
+++ b/include/linux/mfd/stmpe.h
@@ -62,6 +62,7 @@ enum {
 
 struct stmpe_variant_info;
 struct stmpe_client_info;
+struct stmpe_platform_data;
 
 /**
  * struct stmpe - STMPE MFD structure
@@ -117,25 +118,4 @@ extern int stmpe_disable(struct stmpe *stmpe, unsigned int blocks);
 
 #define STMPE_GPIO_NOREQ_811_TOUCH	(0xf0)
 
-/**
- * struct stmpe_platform_data - STMPE platform data
- * @id: device id to distinguish between multiple STMPEs on the same board
- * @blocks: bitmask of blocks to enable (use STMPE_BLOCK_*)
- * @irq_trigger: IRQ trigger to use for the interrupt to the host
- * @autosleep: bool to enable/disable stmpe autosleep
- * @autosleep_timeout: inactivity timeout in milliseconds for autosleep
- * @irq_over_gpio: true if gpio is used to get irq
- * @irq_gpio: gpio number over which irq will be requested (significant only if
- *	      irq_over_gpio is true)
- */
-struct stmpe_platform_data {
-	int id;
-	unsigned int blocks;
-	unsigned int irq_trigger;
-	bool autosleep;
-	bool irq_over_gpio;
-	int irq_gpio;
-	int autosleep_timeout;
-};
-
 #endif
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index 1fd50dcfe47c..2567a87872b0 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -153,7 +153,7 @@
 
 struct ti_tscadc_dev {
 	struct device *dev;
-	struct regmap *regmap_tscadc;
+	struct regmap *regmap;
 	void __iomem *tscadc_base;
 	int irq;
 	int used_cells;	/* 1-2 */
diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h
index 8e95cd87cd74..36795a1be479 100644
--- a/include/linux/mfd/twl6040.h
+++ b/include/linux/mfd/twl6040.h
@@ -226,6 +226,7 @@ struct twl6040 {
 	struct regmap_irq_chip_data *irq_data;
 	struct regulator_bulk_data supplies[2]; /* supplies for vio, v2v1 */
 	struct clk *clk32k;
+	struct clk *mclk;
 	struct mutex mutex;
 	struct mutex irq_mutex;
 	struct mfd_cell cells[TWL6040_CELLS];
@@ -237,8 +238,8 @@ struct twl6040 {
 
 	/* PLL configuration */
 	int pll;
-	unsigned int sysclk;
-	unsigned int mclk;
+	unsigned int sysclk_rate;
+	unsigned int mclk_rate;
 
 	unsigned int irq;
 	unsigned int irq_ready;
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 33e17f6a327a..634c4c51fe3a 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -49,7 +49,7 @@ static inline void vm_unacct_memory(long pages)
  *
  * Returns true if the prot flags are valid
  */
-static inline int arch_validate_prot(unsigned long prot)
+static inline bool arch_validate_prot(unsigned long prot)
 {
 	return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0;
 }
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index eb0151bac50c..d8673ca968ba 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -95,6 +95,7 @@ struct mmc_ext_csd {
 	u8			raw_partition_support;	/* 160 */
 	u8			raw_rpmb_size_mult;	/* 168 */
 	u8			raw_erased_mem_count;	/* 181 */
+	u8			strobe_support;		/* 184 */
 	u8			raw_ext_csd_structure;	/* 194 */
 	u8			raw_card_type;		/* 196 */
 	u8			raw_driver_strength;	/* 197 */
@@ -279,6 +280,7 @@ struct mmc_card {
 #define MMC_QUIRK_SEC_ERASE_TRIM_BROKEN (1<<10)	/* Skip secure for erase/trim */
 #define MMC_QUIRK_BROKEN_IRQ_POLLING	(1<<11)	/* Polling SDIO_CCCR_INTx could create a fake interrupt */
 #define MMC_QUIRK_TRIM_BROKEN	(1<<12)		/* Skip trim */
+#define MMC_QUIRK_BROKEN_HPI	(1<<13)		/* Disable broken HPI support */
 
 
 	unsigned int		erase_size;	/* erase size in sectors */
@@ -353,6 +355,9 @@ struct mmc_fixup {
 	/* SDIO-specfic fields. You can use SDIO_ANY_ID here of course */
 	u16 cis_vendor, cis_device;
 
+	/* for MMC cards */
+	unsigned int ext_csd_rev;
+
 	void (*vendor_fixup)(struct mmc_card *card, int data);
 	int data;
 };
@@ -361,11 +366,20 @@ struct mmc_fixup {
 #define CID_OEMID_ANY ((unsigned short) -1)
 #define CID_NAME_ANY (NULL)
 
+#define EXT_CSD_REV_ANY (-1u)
+
+#define CID_MANFID_SANDISK      0x2
+#define CID_MANFID_TOSHIBA      0x11
+#define CID_MANFID_MICRON       0x13
+#define CID_MANFID_SAMSUNG      0x15
+#define CID_MANFID_KINGSTON     0x70
+#define CID_MANFID_HYNIX	0x90
+
 #define END_FIXUP { NULL }
 
 #define _FIXUP_EXT(_name, _manfid, _oemid, _rev_start, _rev_end,	\
 		   _cis_vendor, _cis_device,				\
-		   _fixup, _data)					\
+		   _fixup, _data, _ext_csd_rev)				\
 	{						   \
 		.name = (_name),			   \
 		.manfid = (_manfid),			   \
@@ -376,23 +390,30 @@ struct mmc_fixup {
 		.cis_device = (_cis_device),		   \
 		.vendor_fixup = (_fixup),		   \
 		.data = (_data),			   \
+		.ext_csd_rev = (_ext_csd_rev),		   \
 	 }
 
 #define MMC_FIXUP_REV(_name, _manfid, _oemid, _rev_start, _rev_end,	\
-		      _fixup, _data)					\
+		      _fixup, _data, _ext_csd_rev)			\
 	_FIXUP_EXT(_name, _manfid,					\
 		   _oemid, _rev_start, _rev_end,			\
 		   SDIO_ANY_ID, SDIO_ANY_ID,				\
-		   _fixup, _data)					\
+		   _fixup, _data, _ext_csd_rev)				\
 
 #define MMC_FIXUP(_name, _manfid, _oemid, _fixup, _data) \
-	MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data)
+	MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data,	\
+		      EXT_CSD_REV_ANY)
+
+#define MMC_FIXUP_EXT_CSD_REV(_name, _manfid, _oemid, _fixup, _data,	\
+			      _ext_csd_rev)				\
+	MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data,	\
+		      _ext_csd_rev)
 
 #define SDIO_FIXUP(_vendor, _device, _fixup, _data)			\
 	_FIXUP_EXT(CID_NAME_ANY, CID_MANFID_ANY,			\
 		    CID_OEMID_ANY, 0, -1ull,				\
 		   _vendor, _device,					\
-		   _fixup, _data)					\
+		   _fixup, _data, EXT_CSD_REV_ANY)			\
 
 #define cid_rev(hwrev, fwrev, year, month)	\
 	(((u64) hwrev) << 40 |                  \
@@ -511,6 +532,11 @@ static inline int mmc_card_broken_irq_polling(const struct mmc_card *c)
 	return c->quirks & MMC_QUIRK_BROKEN_IRQ_POLLING;
 }
 
+static inline int mmc_card_broken_hpi(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_BROKEN_HPI;
+}
+
 #define mmc_card_name(c)	((c)->cid.prod_name)
 #define mmc_card_id(c)		(dev_name(&(c)->dev))
 
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index f7ed271a1d54..83b0edfce471 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -112,7 +112,6 @@ struct dw_mci_dma_slave {
  * @part_buf: Simple buffer for partial fifo reads/writes.
  * @push_data: Pointer to FIFO push function.
  * @pull_data: Pointer to FIFO pull function.
- * @quirks: Set of quirks that apply to specific versions of the IP.
  * @vqmmc_enabled: Status of vqmmc, should be true or false.
  * @irq_flags: The flags to be passed to request_irq.
  * @irq: The irq value to be passed to request_irq.
@@ -218,9 +217,6 @@ struct dw_mci {
 	void (*push_data)(struct dw_mci *host, void *buf, int cnt);
 	void (*pull_data)(struct dw_mci *host, void *buf, int cnt);
 
-	/* Workaround flags */
-	u32			quirks;
-
 	bool			vqmmc_enabled;
 	unsigned long		irq_flags; /* IRQ flags */
 	int			irq;
@@ -242,17 +238,12 @@ struct dw_mci_dma_ops {
 	void (*exit)(struct dw_mci *host);
 };
 
-/* IP Quirks/flags. */
-/* Timer for broken data transfer over scheme */
-#define DW_MCI_QUIRK_BROKEN_DTO			BIT(0)
-
 struct dma_pdata;
 
 /* Board platform data */
 struct dw_mci_board {
 	u32 num_slots;
 
-	u32 quirks; /* Workaround / Quirk flags */
 	unsigned int bus_hz; /* Clock speed at the cclk_in pad */
 
 	u32 caps;	/* Capabilities */
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 45cde8cd39f2..aa4bfbf129e4 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -19,6 +19,7 @@
 
 #include <linux/mmc/core.h>
 #include <linux/mmc/card.h>
+#include <linux/mmc/mmc.h>
 #include <linux/mmc/pm.h>
 
 struct mmc_ios {
@@ -77,6 +78,8 @@ struct mmc_ios {
 #define MMC_SET_DRIVER_TYPE_A	1
 #define MMC_SET_DRIVER_TYPE_C	2
 #define MMC_SET_DRIVER_TYPE_D	3
+
+	bool enhanced_strobe;			/* hs400es selection */
 };
 
 struct mmc_host_ops {
@@ -143,6 +146,9 @@ struct mmc_host_ops {
 
 	/* Prepare HS400 target operating frequency depending host driver */
 	int	(*prepare_hs400_tuning)(struct mmc_host *host, struct mmc_ios *ios);
+	/* Prepare enhanced strobe depending host driver */
+	void	(*hs400_enhanced_strobe)(struct mmc_host *host,
+					 struct mmc_ios *ios);
 	int	(*select_drive_strength)(struct mmc_card *card,
 					 unsigned int max_dtr, int host_drv,
 					 int card_drv, int *drv_type);
@@ -302,6 +308,9 @@ struct mmc_host {
 #define MMC_CAP2_SDIO_IRQ_NOTHREAD (1 << 17)
 #define MMC_CAP2_NO_WRITE_PROTECT (1 << 18)	/* No physical write protect pin, assume that card is always read-write */
 #define MMC_CAP2_NO_SDIO	(1 << 19)	/* Do not send SDIO commands during initialization */
+#define MMC_CAP2_HS400_ES	(1 << 20)	/* Host supports enhanced strobe */
+#define MMC_CAP2_NO_SD		(1 << 21)	/* Do not send SD commands during initialization */
+#define MMC_CAP2_NO_MMC		(1 << 22)	/* Do not send (e)MMC commands during initialization */
 
 	mmc_pm_flag_t		pm_caps;	/* supported pm features */
 
@@ -513,6 +522,11 @@ static inline bool mmc_card_hs400(struct mmc_card *card)
 	return card->host->ios.timing == MMC_TIMING_MMC_HS400;
 }
 
+static inline bool mmc_card_hs400es(struct mmc_card *card)
+{
+	return card->host->ios.enhanced_strobe;
+}
+
 void mmc_retune_timer_stop(struct mmc_host *host);
 
 static inline void mmc_retune_needed(struct mmc_host *host)
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 15f2c4a0a62c..c376209c70ef 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -297,6 +297,7 @@ struct _mmc_csd {
 #define EXT_CSD_PART_CONFIG		179	/* R/W */
 #define EXT_CSD_ERASED_MEM_CONT		181	/* RO */
 #define EXT_CSD_BUS_WIDTH		183	/* R/W */
+#define EXT_CSD_STROBE_SUPPORT		184	/* RO */
 #define EXT_CSD_HS_TIMING		185	/* R/W */
 #define EXT_CSD_POWER_CLASS		187	/* R/W */
 #define EXT_CSD_REV			192	/* RO */
@@ -380,12 +381,14 @@ struct _mmc_csd {
 #define EXT_CSD_CARD_TYPE_HS400_1_2V	(1<<7)	/* Card can run at 200MHz DDR, 1.2V */
 #define EXT_CSD_CARD_TYPE_HS400		(EXT_CSD_CARD_TYPE_HS400_1_8V | \
 					 EXT_CSD_CARD_TYPE_HS400_1_2V)
+#define EXT_CSD_CARD_TYPE_HS400ES	(1<<8)	/* Card can run at HS400ES */
 
 #define EXT_CSD_BUS_WIDTH_1	0	/* Card is in 1 bit mode */
 #define EXT_CSD_BUS_WIDTH_4	1	/* Card is in 4 bit mode */
 #define EXT_CSD_BUS_WIDTH_8	2	/* Card is in 8 bit mode */
 #define EXT_CSD_DDR_BUS_WIDTH_4	5	/* Card is in 4 bit DDR mode */
 #define EXT_CSD_DDR_BUS_WIDTH_8	6	/* Card is in 8 bit DDR mode */
+#define EXT_CSD_BUS_WIDTH_STROBE BIT(7)	/* Enhanced strobe mode */
 
 #define EXT_CSD_TIMING_BC	0	/* Backwards compatility */
 #define EXT_CSD_TIMING_HS	1	/* High speed */
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index fbe8e164a4ee..8dd6e01f45c0 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -783,6 +783,7 @@ static inline void nand_set_controller_data(struct nand_chip *chip, void *priv)
  * NAND Flash Manufacturer ID Codes
  */
 #define NAND_MFR_TOSHIBA	0x98
+#define NAND_MFR_ESMT		0xc8
 #define NAND_MFR_SAMSUNG	0xec
 #define NAND_MFR_FUJITSU	0x04
 #define NAND_MFR_NATIONAL	0x8f
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 7f041bd88b82..c425c7b4c2a0 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -173,10 +173,10 @@ struct spi_nor {
 	int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len);
 	int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len);
 
-	int (*read)(struct spi_nor *nor, loff_t from,
-			size_t len, size_t *retlen, u_char *read_buf);
-	void (*write)(struct spi_nor *nor, loff_t to,
-			size_t len, size_t *retlen, const u_char *write_buf);
+	ssize_t (*read)(struct spi_nor *nor, loff_t from,
+			size_t len, u_char *read_buf);
+	ssize_t (*write)(struct spi_nor *nor, loff_t to,
+			size_t len, const u_char *write_buf);
 	int (*erase)(struct spi_nor *nor, loff_t offs);
 
 	int (*flash_lock)(struct spi_nor *nor, loff_t ofs, uint64_t len);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index d71278c3c5bd..810124b33327 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -205,12 +205,12 @@ struct nfs_inode {
 #define NFS_INO_STALE		(1)		/* possible stale inode */
 #define NFS_INO_ACL_LRU_SET	(2)		/* Inode is on the LRU list */
 #define NFS_INO_INVALIDATING	(3)		/* inode is being invalidated */
-#define NFS_INO_FLUSHING	(4)		/* inode is flushing out data */
 #define NFS_INO_FSCACHE		(5)		/* inode can be cached by FS-Cache */
 #define NFS_INO_FSCACHE_LOCK	(6)		/* FS-Cache cookie management lock */
 #define NFS_INO_LAYOUTCOMMIT	(9)		/* layoutcommit required */
 #define NFS_INO_LAYOUTCOMMITTING (10)		/* layoutcommit inflight */
 #define NFS_INO_LAYOUTSTATS	(11)		/* layoutstats inflight */
+#define NFS_INO_ODIRECT		(12)		/* I/O setting is O_DIRECT */
 
 static inline struct nfs_inode *NFS_I(const struct inode *inode)
 {
@@ -351,7 +351,6 @@ extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *ino
 extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
 extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
 extern int nfs_revalidate_mapping_rcu(struct inode *inode);
-extern int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping);
 extern int nfs_setattr(struct dentry *, struct iattr *);
 extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *);
 extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index c304a11b5b1a..82b81a1c2438 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1596,9 +1596,8 @@ struct nfs_rpc_ops {
 	int (*have_delegation)(struct inode *, fmode_t);
 	int (*return_delegation)(struct inode *);
 	struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *);
-	struct nfs_client *
-		(*init_client) (struct nfs_client *, const struct rpc_timeout *,
-				const char *);
+	struct nfs_client *(*init_client) (struct nfs_client *,
+				const struct nfs_client_initdata *);
 	void	(*free_client) (struct nfs_client *);
 	struct nfs_server *(*create_server)(struct nfs_mount_info *, struct nfs_subversion *);
 	struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *,
diff --git a/include/linux/of.h b/include/linux/of.h
index 15c43f076b23..3d9ff8e9d803 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -238,13 +238,6 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size)
 #define OF_ROOT_NODE_SIZE_CELLS_DEFAULT 1
 #endif
 
-/* Default string compare functions, Allow arch asm/prom.h to override */
-#if !defined(of_compat_cmp)
-#define of_compat_cmp(s1, s2, l)	strcasecmp((s1), (s2))
-#define of_prop_cmp(s1, s2)		strcmp((s1), (s2))
-#define of_node_cmp(s1, s2)		strcasecmp((s1), (s2))
-#endif
-
 #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags)
 #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags)
 
@@ -324,6 +317,8 @@ extern int of_property_read_string_helper(const struct device_node *np,
 					      const char **out_strs, size_t sz, int index);
 extern int of_device_is_compatible(const struct device_node *device,
 				   const char *);
+extern int of_device_compatible_match(struct device_node *device,
+				      const char *const *compat);
 extern bool of_device_is_available(const struct device_node *device);
 extern bool of_device_is_big_endian(const struct device_node *device);
 extern const void *of_get_property(const struct device_node *node,
@@ -726,6 +721,13 @@ static inline void of_property_clear_flag(struct property *p, unsigned long flag
 #define of_match_node(_matches, _node)	NULL
 #endif /* CONFIG_OF */
 
+/* Default string compare functions, Allow arch asm/prom.h to override */
+#if !defined(of_compat_cmp)
+#define of_compat_cmp(s1, s2, l)	strcasecmp((s1), (s2))
+#define of_prop_cmp(s1, s2)		strcmp((s1), (s2))
+#define of_node_cmp(s1, s2)		strcasecmp((s1), (s2))
+#endif
+
 #if defined(CONFIG_OF) && defined(CONFIG_NUMA)
 extern int of_node_to_nid(struct device_node *np);
 #else
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index bd02b44902d0..e80b9c762a03 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -11,7 +11,6 @@ extern int of_get_dma_window(struct device_node *dn, const char *prefix,
 			     int index, unsigned long *busno, dma_addr_t *addr,
 			     size_t *size);
 
-extern void of_iommu_init(void);
 extern const struct iommu_ops *of_iommu_configure(struct device *dev,
 					struct device_node *master_np);
 
@@ -24,7 +23,6 @@ static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
 	return -EINVAL;
 }
 
-static inline void of_iommu_init(void) { }
 static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
 					 struct device_node *master_np)
 {
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 8b5e0a9f2431..610e13271918 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -124,6 +124,15 @@ static inline int page_ref_sub_and_test(struct page *page, int nr)
 	return ret;
 }
 
+static inline int page_ref_inc_return(struct page *page)
+{
+	int ret = atomic_inc_return(&page->_refcount);
+
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+		__page_ref_mod_and_return(page, 1, ret);
+	return ret;
+}
+
 static inline int page_ref_dec_and_test(struct page *page)
 {
 	int ret = atomic_dec_and_test(&page->_refcount);
diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h
index 89ab0572dbc6..7d63a66e8ed4 100644
--- a/include/linux/pci-acpi.h
+++ b/include/linux/pci-acpi.h
@@ -24,6 +24,8 @@ static inline acpi_status pci_acpi_remove_pm_notifier(struct acpi_device *dev)
 }
 extern phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle);
 
+extern phys_addr_t pci_mcfg_lookup(u16 domain, struct resource *bus_res);
+
 static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev)
 {
 	struct pci_bus *pbus = pdev->bus;
diff --git a/drivers/pci/ecam.h b/include/linux/pci-ecam.h
index 9878bebd45bb..7adad206b1f4 100644
--- a/drivers/pci/ecam.h
+++ b/include/linux/pci-ecam.h
@@ -27,8 +27,7 @@ struct pci_config_window;
 struct pci_ecam_ops {
 	unsigned int			bus_shift;
 	struct pci_ops			pci_ops;
-	int				(*init)(struct device *,
-						struct pci_config_window *);
+	int				(*init)(struct pci_config_window *);
 };
 
 /*
@@ -45,6 +44,7 @@ struct pci_config_window {
 		void __iomem		*win;	/* 64-bit single mapping */
 		void __iomem		**winp; /* 32-bit per-bus mapping */
 	};
+	struct device			*parent;/* ECAM res was from this dev */
 };
 
 /* create and free pci_config_window */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index b67e4df20801..2599a980340f 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -101,6 +101,10 @@ enum {
 	DEVICE_COUNT_RESOURCE = PCI_NUM_RESOURCES,
 };
 
+/*
+ * pci_power_t values must match the bits in the Capabilities PME_Support
+ * and Control/Status PowerState fields in the Power Management capability.
+ */
 typedef int __bitwise pci_power_t;
 
 #define PCI_D0		((pci_power_t __force) 0)
@@ -116,7 +120,7 @@ extern const char *pci_power_names[];
 
 static inline const char *pci_power_name(pci_power_t state)
 {
-	return pci_power_names[1 + (int) state];
+	return pci_power_names[1 + (__force int) state];
 }
 
 #define PCI_PM_D2_DELAY		200
@@ -294,6 +298,7 @@ struct pci_dev {
 	unsigned int	d2_support:1;	/* Low power state D2 is supported */
 	unsigned int	no_d1d2:1;	/* D1 and D2 are forbidden */
 	unsigned int	no_d3cold:1;	/* D3cold is forbidden */
+	unsigned int	bridge_d3:1;	/* Allow D3 for bridge */
 	unsigned int	d3cold_allowed:1;	/* D3cold is allowed by user */
 	unsigned int	mmio_always_on:1;	/* disallow turning off io/mem
 						   decoding during bar sizing */
@@ -320,6 +325,7 @@ struct pci_dev {
 	 * directly, use the values stored here. They might be different!
 	 */
 	unsigned int	irq;
+	struct cpumask	*irq_affinity;
 	struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */
 
 	bool match_driver;		/* Skip attaching driver */
@@ -854,6 +860,7 @@ void pci_stop_and_remove_bus_device_locked(struct pci_dev *dev);
 void pci_stop_root_bus(struct pci_bus *bus);
 void pci_remove_root_bus(struct pci_bus *bus);
 void pci_setup_cardbus(struct pci_bus *bus);
+void pcibios_setup_bridge(struct pci_bus *bus, unsigned long type);
 void pci_sort_breadthfirst(void);
 #define dev_is_pci(d) ((d)->bus == &pci_bus_type)
 #define dev_is_pf(d) ((dev_is_pci(d) ? to_pci_dev(d)->is_physfn : false))
@@ -1083,6 +1090,8 @@ int pci_back_from_sleep(struct pci_dev *dev);
 bool pci_dev_run_wake(struct pci_dev *dev);
 bool pci_check_pme_status(struct pci_dev *dev);
 void pci_pme_wakeup_bus(struct pci_bus *bus);
+void pci_d3cold_enable(struct pci_dev *dev);
+void pci_d3cold_disable(struct pci_dev *dev);
 
 static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state,
 				  bool enable)
@@ -1114,6 +1123,7 @@ int pci_set_vpd_size(struct pci_dev *dev, size_t len);
 /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */
 resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx);
 void pci_bus_assign_resources(const struct pci_bus *bus);
+void pci_bus_claim_resources(struct pci_bus *bus);
 void pci_bus_size_bridges(struct pci_bus *bus);
 int pci_claim_resource(struct pci_dev *, int);
 int pci_claim_bridge_resource(struct pci_dev *bridge, int i);
@@ -1143,9 +1153,12 @@ void pci_add_resource(struct list_head *resources, struct resource *res);
 void pci_add_resource_offset(struct list_head *resources, struct resource *res,
 			     resource_size_t offset);
 void pci_free_resource_list(struct list_head *resources);
-void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, unsigned int flags);
+void pci_bus_add_resource(struct pci_bus *bus, struct resource *res,
+			  unsigned int flags);
 struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n);
 void pci_bus_remove_resources(struct pci_bus *bus);
+int devm_request_pci_bus_resources(struct device *dev,
+				   struct list_head *resources);
 
 #define pci_bus_for_each_resource(bus, res, i)				\
 	for (i = 0;							\
@@ -1167,6 +1180,7 @@ int pci_register_io_range(phys_addr_t addr, resource_size_t size);
 unsigned long pci_address_to_pio(phys_addr_t addr);
 phys_addr_t pci_pio_to_address(unsigned long pio);
 int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr);
+void pci_unmap_iospace(struct resource *res);
 
 static inline pci_bus_addr_t pci_bus_address(struct pci_dev *pdev, int bar)
 {
@@ -1237,6 +1251,11 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno);
 int pci_set_vga_state(struct pci_dev *pdev, bool decode,
 		      unsigned int command_bits, u32 flags);
 
+#define PCI_IRQ_NOLEGACY	(1 << 0) /* don't use legacy interrupts */
+#define PCI_IRQ_NOMSI		(1 << 1) /* don't use MSI interrupts */
+#define PCI_IRQ_NOMSIX		(1 << 2) /* don't use MSI-X interrupts */
+#define PCI_IRQ_NOAFFINITY	(1 << 3) /* don't auto-assign affinity */
+
 /* kmem_cache style wrapper around pci_alloc_consistent() */
 
 #include <linux/pci-dma.h>
@@ -1284,6 +1303,11 @@ static inline int pci_enable_msix_exact(struct pci_dev *dev,
 		return rc;
 	return 0;
 }
+int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs,
+		unsigned int max_vecs, unsigned int flags);
+void pci_free_irq_vectors(struct pci_dev *dev);
+int pci_irq_vector(struct pci_dev *dev, unsigned int nr);
+
 #else
 static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; }
 static inline void pci_msi_shutdown(struct pci_dev *dev) { }
@@ -1307,6 +1331,24 @@ static inline int pci_enable_msix_range(struct pci_dev *dev,
 static inline int pci_enable_msix_exact(struct pci_dev *dev,
 		      struct msix_entry *entries, int nvec)
 { return -ENOSYS; }
+static inline int pci_alloc_irq_vectors(struct pci_dev *dev,
+		unsigned int min_vecs, unsigned int max_vecs,
+		unsigned int flags)
+{
+	if (min_vecs > 1)
+		return -EINVAL;
+	return 1;
+}
+static inline void pci_free_irq_vectors(struct pci_dev *dev)
+{
+}
+
+static inline int pci_irq_vector(struct pci_dev *dev, unsigned int nr)
+{
+	if (WARN_ON_ONCE(nr > 0))
+		return -EINVAL;
+	return dev->irq;
+}
 #endif
 
 #ifdef CONFIG_PCIEPORTBUS
@@ -1389,12 +1431,13 @@ static inline int pci_domain_nr(struct pci_bus *bus)
 {
 	return bus->domain_nr;
 }
-void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent);
+#ifdef CONFIG_ACPI
+int acpi_pci_bus_find_domain_nr(struct pci_bus *bus);
 #else
-static inline void pci_bus_assign_domain_nr(struct pci_bus *bus,
-					struct device *parent)
-{
-}
+static inline int acpi_pci_bus_find_domain_nr(struct pci_bus *bus)
+{ return 0; }
+#endif
+int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent);
 #endif
 
 /* some architectures require additional setup to direct VGA traffic */
@@ -1402,6 +1445,34 @@ typedef int (*arch_set_vga_state_t)(struct pci_dev *pdev, bool decode,
 		      unsigned int command_bits, u32 flags);
 void pci_register_set_vga_state(arch_set_vga_state_t func);
 
+static inline int
+pci_request_io_regions(struct pci_dev *pdev, const char *name)
+{
+	return pci_request_selected_regions(pdev,
+			    pci_select_bars(pdev, IORESOURCE_IO), name);
+}
+
+static inline void
+pci_release_io_regions(struct pci_dev *pdev)
+{
+	return pci_release_selected_regions(pdev,
+			    pci_select_bars(pdev, IORESOURCE_IO));
+}
+
+static inline int
+pci_request_mem_regions(struct pci_dev *pdev, const char *name)
+{
+	return pci_request_selected_regions(pdev,
+			    pci_select_bars(pdev, IORESOURCE_MEM), name);
+}
+
+static inline void
+pci_release_mem_regions(struct pci_dev *pdev)
+{
+	return pci_release_selected_regions(pdev,
+			    pci_select_bars(pdev, IORESOURCE_MEM));
+}
+
 #else /* CONFIG_PCI is not enabled */
 
 static inline void pci_set_flags(int flags) { }
@@ -1554,7 +1625,11 @@ static inline const char *pci_name(const struct pci_dev *pdev)
 /* Some archs don't want to expose struct resource to userland as-is
  * in sysfs and /proc
  */
-#ifndef HAVE_ARCH_PCI_RESOURCE_TO_USER
+#ifdef HAVE_ARCH_PCI_RESOURCE_TO_USER
+void pci_resource_to_user(const struct pci_dev *dev, int bar,
+			  const struct resource *rsrc,
+			  resource_size_t *start, resource_size_t *end);
+#else
 static inline void pci_resource_to_user(const struct pci_dev *dev, int bar,
 		const struct resource *rsrc, resource_size_t *start,
 		resource_size_t *end)
@@ -1706,6 +1781,7 @@ extern u8 pci_cache_line_size;
 
 extern unsigned long pci_hotplug_io_size;
 extern unsigned long pci_hotplug_mem_size;
+extern unsigned long pci_hotplug_bus_size;
 
 /* Architecture-specific versions may override these (weak) */
 void pcibios_disable_device(struct pci_dev *dev);
@@ -1722,7 +1798,7 @@ void pcibios_free_irq(struct pci_dev *dev);
 extern struct dev_pm_ops pcibios_pm_ops;
 #endif
 
-#ifdef CONFIG_PCI_MMCONFIG
+#if defined(CONFIG_PCI_MMCONFIG) || defined(CONFIG_ACPI_MCFG)
 void __init pci_mmcfg_early_init(void);
 void __init pci_mmcfg_late_init(void);
 #else
diff --git a/include/linux/platform_data/asoc-ti-mcbsp.h b/include/linux/platform_data/asoc-ti-mcbsp.h
index 3c73c045f8da..e684543254f3 100644
--- a/include/linux/platform_data/asoc-ti-mcbsp.h
+++ b/include/linux/platform_data/asoc-ti-mcbsp.h
@@ -44,7 +44,7 @@ struct omap_mcbsp_platform_data {
 	/* McBSP platform and instance specific features */
 	bool has_wakeup; /* Wakeup capability */
 	bool has_ccr; /* Transceiver has configuration control registers */
-	int (*enable_st_clock)(unsigned int, bool);
+	int (*force_ick_on)(struct clk *clk, bool force_on);
 };
 
 /**
@@ -55,4 +55,6 @@ struct omap_mcbsp_dev_attr {
 	const char *sidetone;
 };
 
+void omap3_mcbsp_init_pdata_callback(struct omap_mcbsp_platform_data *pdata);
+
 #endif
diff --git a/include/linux/platform_data/clk-ux500.h b/include/linux/platform_data/clk-ux500.h
deleted file mode 100644
index 3af0da1f3be5..000000000000
--- a/include/linux/platform_data/clk-ux500.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * Clock definitions for ux500 platforms
- *
- * Copyright (C) 2012 ST-Ericsson SA
- * Author: Ulf Hansson <ulf.hansson@linaro.org>
- *
- * License terms: GNU General Public License (GPL) version 2
- */
-
-#ifndef __CLK_UX500_H
-#define __CLK_UX500_H
-
-void u8500_clk_init(void);
-void u9540_clk_init(void);
-void u8540_clk_init(void);
-
-#endif /* __CLK_UX500_H */
diff --git a/include/linux/platform_data/media/ir-rx51.h b/include/linux/platform_data/media/ir-rx51.h
index 3038120ca46e..812d87307877 100644
--- a/include/linux/platform_data/media/ir-rx51.h
+++ b/include/linux/platform_data/media/ir-rx51.h
@@ -2,10 +2,7 @@
 #define _LIRC_RX51_H
 
 struct lirc_rx51_platform_data {
-	int pwm_timer;
-
 	int(*set_max_mpu_wakeup_lat)(struct device *dev, long t);
-	struct pwm_omap_dmtimer_pdata *dmtimer;
 };
 
 #endif
diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h
index 95ccab3f454a..7daa78a2f342 100644
--- a/include/linux/platform_data/mmc-esdhc-imx.h
+++ b/include/linux/platform_data/mmc-esdhc-imx.h
@@ -46,5 +46,6 @@ struct esdhc_platform_data {
 	bool support_vsel;
 	unsigned int delay_line;
 	unsigned int tuning_step;       /* The delay cell steps in tuning procedure */
+	unsigned int tuning_start_tap;	/* The start delay cell point in tuning procedure */
 };
 #endif /* __ASM_ARCH_IMX_ESDHC_H */
diff --git a/include/linux/platform_data/omapdss.h b/include/linux/platform_data/omapdss.h
new file mode 100644
index 000000000000..679177929045
--- /dev/null
+++ b/include/linux/platform_data/omapdss.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2016 Texas Instruments, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __OMAPDSS_PDATA_H
+#define __OMAPDSS_PDATA_H
+
+enum omapdss_version {
+	OMAPDSS_VER_UNKNOWN = 0,
+	OMAPDSS_VER_OMAP24xx,
+	OMAPDSS_VER_OMAP34xx_ES1,	/* OMAP3430 ES1.0, 2.0 */
+	OMAPDSS_VER_OMAP34xx_ES3,	/* OMAP3430 ES3.0+ */
+	OMAPDSS_VER_OMAP3630,
+	OMAPDSS_VER_AM35xx,
+	OMAPDSS_VER_OMAP4430_ES1,	/* OMAP4430 ES1.0 */
+	OMAPDSS_VER_OMAP4430_ES2,	/* OMAP4430 ES2.0, 2.1, 2.2 */
+	OMAPDSS_VER_OMAP4,		/* All other OMAP4s */
+	OMAPDSS_VER_OMAP5,
+	OMAPDSS_VER_AM43xx,
+	OMAPDSS_VER_DRA7xx,
+};
+
+/* Board specific data */
+struct omap_dss_board_info {
+	const char *default_display_name;
+	int (*dsi_enable_pads)(int dsi_id, unsigned int lane_mask);
+	void (*dsi_disable_pads)(int dsi_id, unsigned int lane_mask);
+	int (*set_min_bus_tput)(struct device *dev, unsigned long r);
+	enum omapdss_version version;
+};
+
+#endif /* __OMAPDSS_PDATA_H */
diff --git a/include/linux/printk.h b/include/linux/printk.h
index f136b22c7772..8dc155dab3ed 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -61,6 +61,11 @@ static inline void console_verbose(void)
 		console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
 }
 
+/* strlen("ratelimit") + 1 */
+#define DEVKMSG_STR_MAX_SIZE 10
+extern char devkmsg_log_str[];
+struct ctl_table;
+
 struct va_format {
 	const char *fmt;
 	va_list *va;
@@ -175,6 +180,10 @@ extern int printk_delay_msec;
 extern int dmesg_restrict;
 extern int kptr_restrict;
 
+extern int
+devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void __user *buf,
+			  size_t *lenp, loff_t *ppos);
+
 extern void wake_up_klogd(void);
 
 char *log_buf_addr_get(void);
@@ -257,21 +266,39 @@ extern asmlinkage void dump_stack(void) __cold;
  * and other debug macros are compiled out unless either DEBUG is defined
  * or CONFIG_DYNAMIC_DEBUG is set.
  */
-#define pr_emerg(fmt, ...) \
-	printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_alert(fmt, ...) \
-	printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_crit(fmt, ...) \
-	printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_err(fmt, ...) \
-	printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_warning(fmt, ...) \
-	printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_warn pr_warning
-#define pr_notice(fmt, ...) \
-	printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_info(fmt, ...) \
-	printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
+
+#ifdef CONFIG_PRINTK
+
+asmlinkage __printf(1, 2) __cold void __pr_emerg(const char *fmt, ...);
+asmlinkage __printf(1, 2) __cold void __pr_alert(const char *fmt, ...);
+asmlinkage __printf(1, 2) __cold void __pr_crit(const char *fmt, ...);
+asmlinkage __printf(1, 2) __cold void __pr_err(const char *fmt, ...);
+asmlinkage __printf(1, 2) __cold void __pr_warn(const char *fmt, ...);
+asmlinkage __printf(1, 2) __cold void __pr_notice(const char *fmt, ...);
+asmlinkage __printf(1, 2) __cold void __pr_info(const char *fmt, ...);
+
+#define pr_emerg(fmt, ...)	__pr_emerg(pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_alert(fmt, ...)	__pr_alert(pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_crit(fmt, ...)	__pr_crit(pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_err(fmt, ...)	__pr_err(pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warn(fmt, ...)	__pr_warn(pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_notice(fmt, ...)	__pr_notice(pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...)	__pr_info(pr_fmt(fmt), ##__VA_ARGS__)
+
+#else
+
+#define pr_emerg(fmt, ...)	printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_alert(fmt, ...)	printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_crit(fmt, ...)	printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_err(fmt, ...)	printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warn(fmt, ...)	printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_notice(fmt, ...)	printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...)	printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
+
+#endif
+
+#define pr_warning pr_warn
+
 /*
  * Like KERN_CONT, pr_cont() should only be used when continuing
  * a line with no newline ('\n') enclosed. Otherwise it defaults
@@ -289,10 +316,11 @@ extern asmlinkage void dump_stack(void) __cold;
 	no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 #endif
 
-#include <linux/dynamic_debug.h>
 
 /* If you are writing a driver, please use dev_dbg instead */
 #if defined(CONFIG_DYNAMIC_DEBUG)
+#include <linux/dynamic_debug.h>
+
 /* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */
 #define pr_debug(fmt, ...) \
 	dynamic_pr_debug(fmt, ##__VA_ARGS__)
diff --git a/include/linux/property.h b/include/linux/property.h
index ecab11e40794..3a2f9ae25c86 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -77,6 +77,9 @@ struct fwnode_handle *device_get_next_child_node(struct device *dev,
 	for (child = device_get_next_child_node(dev, NULL); child;	\
 	     child = device_get_next_child_node(dev, child))
 
+struct fwnode_handle *device_get_named_child_node(struct device *dev,
+						  const char *childname);
+
 void fwnode_handle_put(struct fwnode_handle *fwnode);
 
 unsigned int device_get_child_node_count(struct device *dev);
diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h
index 9e12000914b3..cc32ab852fbc 100644
--- a/include/linux/qcom_scm.h
+++ b/include/linux/qcom_scm.h
@@ -29,6 +29,14 @@ extern bool qcom_scm_hdcp_available(void);
 extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt,
 		u32 *resp);
 
+extern bool qcom_scm_pas_supported(u32 peripheral);
+extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata,
+		size_t size);
+extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr,
+		phys_addr_t size);
+extern int qcom_scm_pas_auth_and_reset(u32 peripheral);
+extern int qcom_scm_pas_shutdown(u32 peripheral);
+
 #define QCOM_SCM_CPU_PWR_DOWN_L2_ON	0x0
 #define QCOM_SCM_CPU_PWR_DOWN_L2_OFF	0x1
 
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index cbfee507c839..4c45105dece3 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -35,7 +35,7 @@
  * 00 - data pointer
  * 01 - internal entry
  * 10 - exceptional entry
- * 11 - locked exceptional entry
+ * 11 - this bit combination is currently unused/reserved
  *
  * The internal entry may be a pointer to the next level in the tree, a
  * sibling entry, or an indicator that the entry in this slot has been moved
diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h
index 18102529254e..57c9e0622a38 100644
--- a/include/linux/ratelimit.h
+++ b/include/linux/ratelimit.h
@@ -2,11 +2,15 @@
 #define _LINUX_RATELIMIT_H
 
 #include <linux/param.h>
+#include <linux/sched.h>
 #include <linux/spinlock.h>
 
 #define DEFAULT_RATELIMIT_INTERVAL	(5 * HZ)
 #define DEFAULT_RATELIMIT_BURST		10
 
+/* issue num suppressed message on exit */
+#define RATELIMIT_MSG_ON_RELEASE	BIT(0)
+
 struct ratelimit_state {
 	raw_spinlock_t	lock;		/* protect the state */
 
@@ -15,6 +19,7 @@ struct ratelimit_state {
 	int		printed;
 	int		missed;
 	unsigned long	begin;
+	unsigned long	flags;
 };
 
 #define RATELIMIT_STATE_INIT(name, interval_init, burst_init) {		\
@@ -34,12 +39,35 @@ struct ratelimit_state {
 static inline void ratelimit_state_init(struct ratelimit_state *rs,
 					int interval, int burst)
 {
+	memset(rs, 0, sizeof(*rs));
+
 	raw_spin_lock_init(&rs->lock);
-	rs->interval = interval;
-	rs->burst = burst;
-	rs->printed = 0;
-	rs->missed = 0;
-	rs->begin = 0;
+	rs->interval	= interval;
+	rs->burst	= burst;
+}
+
+static inline void ratelimit_default_init(struct ratelimit_state *rs)
+{
+	return ratelimit_state_init(rs, DEFAULT_RATELIMIT_INTERVAL,
+					DEFAULT_RATELIMIT_BURST);
+}
+
+static inline void ratelimit_state_exit(struct ratelimit_state *rs)
+{
+	if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE))
+		return;
+
+	if (rs->missed) {
+		pr_warn("%s: %d output lines suppressed due to ratelimiting\n",
+			current->comm, rs->missed);
+		rs->missed = 0;
+	}
+}
+
+static inline void
+ratelimit_set_flags(struct ratelimit_state *rs, unsigned long flags)
+{
+	rs->flags = flags;
 }
 
 extern struct ratelimit_state printk_ratelimit_state;
diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h
index b91ba932bbd4..db1fe6772ad5 100644
--- a/include/linux/reset-controller.h
+++ b/include/linux/reset-controller.h
@@ -53,4 +53,8 @@ struct reset_controller_dev {
 int reset_controller_register(struct reset_controller_dev *rcdev);
 void reset_controller_unregister(struct reset_controller_dev *rcdev);
 
+struct device;
+int devm_reset_controller_register(struct device *dev,
+				   struct reset_controller_dev *rcdev);
+
 #endif
diff --git a/include/linux/reset.h b/include/linux/reset.h
index 45a4abeb6acb..5daff15722d3 100644
--- a/include/linux/reset.h
+++ b/include/linux/reset.h
@@ -71,14 +71,14 @@ static inline struct reset_control *__of_reset_control_get(
 					struct device_node *node,
 					const char *id, int index, int shared)
 {
-	return ERR_PTR(-EINVAL);
+	return ERR_PTR(-ENOTSUPP);
 }
 
 static inline struct reset_control *__devm_reset_control_get(
 					struct device *dev,
 					const char *id, int index, int shared)
 {
-	return ERR_PTR(-EINVAL);
+	return ERR_PTR(-ENOTSUPP);
 }
 
 #endif /* CONFIG_RESET_CONTROLLER */
diff --git a/include/linux/rio.h b/include/linux/rio.h
index aa2323893e8d..37b95c4af99d 100644
--- a/include/linux/rio.h
+++ b/include/linux/rio.h
@@ -163,6 +163,7 @@ enum rio_device_state {
  * @dst_ops: Destination operation capabilities
  * @comp_tag: RIO component tag
  * @phys_efptr: RIO device extended features pointer
+ * @phys_rmap: LP-Serial Register Map Type (1 or 2)
  * @em_efptr: RIO Error Management features pointer
  * @dma_mask: Mask of bits of RIO address this device implements
  * @driver: Driver claiming this device
@@ -193,6 +194,7 @@ struct rio_dev {
 	u32 dst_ops;
 	u32 comp_tag;
 	u32 phys_efptr;
+	u32 phys_rmap;
 	u32 em_efptr;
 	u64 dma_mask;
 	struct rio_driver *driver;	/* RIO driver claiming this device */
@@ -237,11 +239,6 @@ struct rio_dbell {
 	void *dev_id;
 };
 
-enum rio_phy_type {
-	RIO_PHY_PARALLEL,
-	RIO_PHY_SERIAL,
-};
-
 /**
  * struct rio_mport - RIO master port info
  * @dbells: List of doorbell events
@@ -259,8 +256,8 @@ enum rio_phy_type {
  * @id: Port ID, unique among all ports
  * @index: Port index, unique among all port interfaces of the same type
  * @sys_size: RapidIO common transport system size
- * @phy_type: RapidIO phy type
  * @phys_efptr: RIO port extended features pointer
+ * @phys_rmap: LP-Serial EFB Register Mapping type (1 or 2).
  * @name: Port name string
  * @dev: device structure associated with an mport
  * @priv: Master port private data
@@ -289,8 +286,8 @@ struct rio_mport {
 				 * 0 - Small size. 256 devices.
 				 * 1 - Large size, 65536 devices.
 				 */
-	enum rio_phy_type phy_type;	/* RapidIO phy type */
 	u32 phys_efptr;
+	u32 phys_rmap;
 	unsigned char name[RIO_MAX_MPORT_NAME];
 	struct device dev;
 	void *priv;		/* Master port private data */
@@ -425,7 +422,7 @@ struct rio_ops {
 	int (*add_inb_buffer)(struct rio_mport *mport, int mbox, void *buf);
 	void *(*get_inb_message)(struct rio_mport *mport, int mbox);
 	int (*map_inb)(struct rio_mport *mport, dma_addr_t lstart,
-			u64 rstart, u32 size, u32 flags);
+			u64 rstart, u64 size, u32 flags);
 	void (*unmap_inb)(struct rio_mport *mport, dma_addr_t lstart);
 	int (*query_mport)(struct rio_mport *mport,
 			   struct rio_mport_attr *attr);
diff --git a/include/linux/rio_ids.h b/include/linux/rio_ids.h
index 2543bc163d54..334c576c151c 100644
--- a/include/linux/rio_ids.h
+++ b/include/linux/rio_ids.h
@@ -38,5 +38,7 @@
 #define RIO_DID_IDTVPS1616		0x0377
 #define RIO_DID_IDTSPS1616		0x0378
 #define RIO_DID_TSI721			0x80ab
+#define RIO_DID_IDTRXS1632		0x80e5
+#define RIO_DID_IDTRXS2448		0x80e6
 
 #endif				/* LINUX_RIO_IDS_H */
diff --git a/include/linux/rio_regs.h b/include/linux/rio_regs.h
index 1063ae382bc2..40c04efe7409 100644
--- a/include/linux/rio_regs.h
+++ b/include/linux/rio_regs.h
@@ -42,9 +42,11 @@
 #define  RIO_PEF_INB_MBOX2		0x00200000	/* [II, <= 1.2] Mailbox 2 */
 #define  RIO_PEF_INB_MBOX3		0x00100000	/* [II, <= 1.2] Mailbox 3 */
 #define  RIO_PEF_INB_DOORBELL		0x00080000	/* [II, <= 1.2] Doorbells */
+#define  RIO_PEF_DEV32			0x00001000	/* [III] PE supports Common TRansport Dev32 */
 #define  RIO_PEF_EXT_RT			0x00000200	/* [III, 1.3] Extended route table support */
 #define  RIO_PEF_STD_RT			0x00000100	/* [III, 1.3] Standard route table support */
-#define  RIO_PEF_CTLS			0x00000010	/* [III] CTLS */
+#define  RIO_PEF_CTLS			0x00000010	/* [III] Common Transport Large System (< rev.3) */
+#define  RIO_PEF_DEV16			0x00000010	/* [III] PE Supports Common Transport Dev16 (rev.3) */
 #define  RIO_PEF_EXT_FEATURES		0x00000008	/* [I] EFT_PTR valid */
 #define  RIO_PEF_ADDR_66		0x00000004	/* [I] 66 bits */
 #define  RIO_PEF_ADDR_50		0x00000002	/* [I] 50 bits */
@@ -194,70 +196,101 @@
 #define RIO_GET_BLOCK_ID(x)	(x & RIO_EFB_ID_MASK)
 
 /* Extended Feature Block IDs */
-#define RIO_EFB_PAR_EP_ID	0x0001	/* [IV] LP/LVDS EP Devices */
-#define RIO_EFB_PAR_EP_REC_ID	0x0002	/* [IV] LP/LVDS EP Recovery Devices */
-#define RIO_EFB_PAR_EP_FREE_ID	0x0003	/* [IV] LP/LVDS EP Free Devices */
-#define RIO_EFB_SER_EP_ID_V13P	0x0001	/* [VI] LP/Serial EP Devices, RapidIO Spec ver 1.3 and above */
-#define RIO_EFB_SER_EP_REC_ID_V13P	0x0002	/* [VI] LP/Serial EP Recovery Devices, RapidIO Spec ver 1.3 and above */
-#define RIO_EFB_SER_EP_FREE_ID_V13P	0x0003	/* [VI] LP/Serial EP Free Devices, RapidIO Spec ver 1.3 and above */
-#define RIO_EFB_SER_EP_ID	0x0004	/* [VI] LP/Serial EP Devices */
-#define RIO_EFB_SER_EP_REC_ID	0x0005	/* [VI] LP/Serial EP Recovery Devices */
-#define RIO_EFB_SER_EP_FREE_ID	0x0006	/* [VI] LP/Serial EP Free Devices */
-#define RIO_EFB_SER_EP_FREC_ID	0x0009  /* [VI] LP/Serial EP Free Recovery Devices */
+#define RIO_EFB_SER_EP_M1_ID	0x0001	/* [VI] LP-Serial EP Devices, Map I */
+#define RIO_EFB_SER_EP_SW_M1_ID	0x0002	/* [VI] LP-Serial EP w SW Recovery Devices, Map I */
+#define RIO_EFB_SER_EPF_M1_ID	0x0003	/* [VI] LP-Serial EP Free Devices, Map I */
+#define RIO_EFB_SER_EP_ID	0x0004	/* [VI] LP-Serial EP Devices, RIO 1.2 */
+#define RIO_EFB_SER_EP_REC_ID	0x0005	/* [VI] LP-Serial EP w SW Recovery Devices, RIO 1.2 */
+#define RIO_EFB_SER_EP_FREE_ID	0x0006	/* [VI] LP-Serial EP Free Devices, RIO 1.2 */
 #define RIO_EFB_ERR_MGMNT	0x0007  /* [VIII] Error Management Extensions */
+#define RIO_EFB_SER_EPF_SW_M1_ID	0x0009  /* [VI] LP-Serial EP Free w SW Recovery Devices, Map I */
+#define RIO_EFB_SW_ROUTING_TBL	0x000E  /* [III] Switch Routing Table Block */
+#define RIO_EFB_SER_EP_M2_ID	0x0011	/* [VI] LP-Serial EP Devices, Map II */
+#define RIO_EFB_SER_EP_SW_M2_ID	0x0012	/* [VI] LP-Serial EP w SW Recovery Devices, Map II */
+#define RIO_EFB_SER_EPF_M2_ID	0x0013	/* [VI] LP-Serial EP Free Devices, Map II */
+#define RIO_EFB_ERR_MGMNT_HS	0x0017  /* [VIII] Error Management Extensions, Hot-Swap only */
+#define RIO_EFB_SER_EPF_SW_M2_ID	0x0019  /* [VI] LP-Serial EP Free w SW Recovery Devices, Map II */
 
 /*
- * Physical 8/16 LP-LVDS
- * ID=0x0001, Generic End Point Devices
- * ID=0x0002, Generic End Point Devices, software assisted recovery option
- * ID=0x0003, Generic End Point Free Devices
- *
- * Physical LP-Serial
- * ID=0x0004, Generic End Point Devices
- * ID=0x0005, Generic End Point Devices, software assisted recovery option
- * ID=0x0006, Generic End Point Free Devices
+ * Physical LP-Serial Registers Definitions
+ * Parameters in register macros:
+ *    n - port number, m - Register Map Type (1 or 2)
  */
 #define RIO_PORT_MNT_HEADER		0x0000
 #define RIO_PORT_REQ_CTL_CSR		0x0020
-#define RIO_PORT_RSP_CTL_CSR		0x0024	/* 0x0001/0x0002 */
-#define RIO_PORT_LINKTO_CTL_CSR		0x0020	/* Serial */
-#define RIO_PORT_RSPTO_CTL_CSR		0x0024	/* Serial */
+#define RIO_PORT_RSP_CTL_CSR		0x0024
+#define RIO_PORT_LINKTO_CTL_CSR		0x0020
+#define RIO_PORT_RSPTO_CTL_CSR		0x0024
 #define RIO_PORT_GEN_CTL_CSR		0x003c
 #define  RIO_PORT_GEN_HOST		0x80000000
 #define  RIO_PORT_GEN_MASTER		0x40000000
 #define  RIO_PORT_GEN_DISCOVERED	0x20000000
-#define RIO_PORT_N_MNT_REQ_CSR(x)	(0x0040 + x*0x20)	/* 0x0002 */
+#define RIO_PORT_N_MNT_REQ_CSR(n, m)	(0x40 + (n) * (0x20 * (m)))
 #define  RIO_MNT_REQ_CMD_RD		0x03	/* Reset-device command */
 #define  RIO_MNT_REQ_CMD_IS		0x04	/* Input-status command */
-#define RIO_PORT_N_MNT_RSP_CSR(x)	(0x0044 + x*0x20)	/* 0x0002 */
+#define RIO_PORT_N_MNT_RSP_CSR(n, m)	(0x44 + (n) * (0x20 * (m)))
 #define  RIO_PORT_N_MNT_RSP_RVAL	0x80000000 /* Response Valid */
 #define  RIO_PORT_N_MNT_RSP_ASTAT	0x000007e0 /* ackID Status */
 #define  RIO_PORT_N_MNT_RSP_LSTAT	0x0000001f /* Link Status */
-#define RIO_PORT_N_ACK_STS_CSR(x)	(0x0048 + x*0x20)	/* 0x0002 */
+#define RIO_PORT_N_ACK_STS_CSR(n)	(0x48 + (n) * 0x20) /* Only in RM-I */
 #define  RIO_PORT_N_ACK_CLEAR		0x80000000
 #define  RIO_PORT_N_ACK_INBOUND		0x3f000000
 #define  RIO_PORT_N_ACK_OUTSTAND	0x00003f00
 #define  RIO_PORT_N_ACK_OUTBOUND	0x0000003f
-#define RIO_PORT_N_CTL2_CSR(x)		(0x0054 + x*0x20)
+#define RIO_PORT_N_CTL2_CSR(n, m)	(0x54 + (n) * (0x20 * (m)))
 #define  RIO_PORT_N_CTL2_SEL_BAUD	0xf0000000
-#define RIO_PORT_N_ERR_STS_CSR(x)	(0x0058 + x*0x20)
-#define  RIO_PORT_N_ERR_STS_PW_OUT_ES	0x00010000 /* Output Error-stopped */
-#define  RIO_PORT_N_ERR_STS_PW_INP_ES	0x00000100 /* Input Error-stopped */
+#define RIO_PORT_N_ERR_STS_CSR(n, m)	(0x58 + (n) * (0x20 * (m)))
+#define  RIO_PORT_N_ERR_STS_OUT_ES	0x00010000 /* Output Error-stopped */
+#define  RIO_PORT_N_ERR_STS_INP_ES	0x00000100 /* Input Error-stopped */
 #define  RIO_PORT_N_ERR_STS_PW_PEND	0x00000010 /* Port-Write Pending */
+#define  RIO_PORT_N_ERR_STS_PORT_UA	0x00000008 /* Port Unavailable */
 #define  RIO_PORT_N_ERR_STS_PORT_ERR	0x00000004
 #define  RIO_PORT_N_ERR_STS_PORT_OK	0x00000002
 #define  RIO_PORT_N_ERR_STS_PORT_UNINIT	0x00000001
-#define RIO_PORT_N_CTL_CSR(x)		(0x005c + x*0x20)
+#define RIO_PORT_N_CTL_CSR(n, m)	(0x5c + (n) * (0x20 * (m)))
 #define  RIO_PORT_N_CTL_PWIDTH		0xc0000000
 #define  RIO_PORT_N_CTL_PWIDTH_1	0x00000000
 #define  RIO_PORT_N_CTL_PWIDTH_4	0x40000000
 #define  RIO_PORT_N_CTL_IPW		0x38000000 /* Initialized Port Width */
 #define  RIO_PORT_N_CTL_P_TYP_SER	0x00000001
 #define  RIO_PORT_N_CTL_LOCKOUT		0x00000002
-#define  RIO_PORT_N_CTL_EN_RX_SER	0x00200000
-#define  RIO_PORT_N_CTL_EN_TX_SER	0x00400000
-#define  RIO_PORT_N_CTL_EN_RX_PAR	0x08000000
-#define  RIO_PORT_N_CTL_EN_TX_PAR	0x40000000
+#define  RIO_PORT_N_CTL_EN_RX		0x00200000
+#define  RIO_PORT_N_CTL_EN_TX		0x00400000
+#define RIO_PORT_N_OB_ACK_CSR(n)	(0x60 + (n) * 0x40) /* Only in RM-II */
+#define  RIO_PORT_N_OB_ACK_CLEAR	0x80000000
+#define  RIO_PORT_N_OB_ACK_OUTSTD	0x00fff000
+#define  RIO_PORT_N_OB_ACK_OUTBND	0x00000fff
+#define RIO_PORT_N_IB_ACK_CSR(n)	(0x64 + (n) * 0x40) /* Only in RM-II */
+#define  RIO_PORT_N_IB_ACK_INBND	0x00000fff
+
+/*
+ * Device-based helper macros for serial port register access.
+ *   d - pointer to rapidio device object, n - port number
+ */
+
+#define RIO_DEV_PORT_N_MNT_REQ_CSR(d, n)	\
+		(d->phys_efptr + RIO_PORT_N_MNT_REQ_CSR(n, d->phys_rmap))
+
+#define RIO_DEV_PORT_N_MNT_RSP_CSR(d, n)	\
+		(d->phys_efptr + RIO_PORT_N_MNT_RSP_CSR(n, d->phys_rmap))
+
+#define RIO_DEV_PORT_N_ACK_STS_CSR(d, n)	\
+		(d->phys_efptr + RIO_PORT_N_ACK_STS_CSR(n))
+
+#define RIO_DEV_PORT_N_CTL2_CSR(d, n)		\
+		(d->phys_efptr + RIO_PORT_N_CTL2_CSR(n, d->phys_rmap))
+
+#define RIO_DEV_PORT_N_ERR_STS_CSR(d, n)	\
+		(d->phys_efptr + RIO_PORT_N_ERR_STS_CSR(n, d->phys_rmap))
+
+#define RIO_DEV_PORT_N_CTL_CSR(d, n)		\
+		(d->phys_efptr + RIO_PORT_N_CTL_CSR(n, d->phys_rmap))
+
+#define RIO_DEV_PORT_N_OB_ACK_CSR(d, n)		\
+		(d->phys_efptr + RIO_PORT_N_OB_ACK_CSR(n))
+
+#define RIO_DEV_PORT_N_IB_ACK_CSR(d, n)		\
+		(d->phys_efptr + RIO_PORT_N_IB_ACK_CSR(n))
 
 /*
  * Error Management Extensions (RapidIO 1.3+, Part 8)
@@ -268,6 +301,7 @@
 /* General EM Registers (Common for all Ports) */
 
 #define RIO_EM_EFB_HEADER	0x000	/* Error Management Extensions Block Header */
+#define RIO_EM_EMHS_CAR		0x004	/* EM Functionality CAR */
 #define RIO_EM_LTL_ERR_DETECT	0x008	/* Logical/Transport Layer Error Detect CSR */
 #define RIO_EM_LTL_ERR_EN	0x00c	/* Logical/Transport Layer Error Enable CSR */
 #define  REM_LTL_ERR_ILLTRAN		0x08000000 /* Illegal Transaction decode */
@@ -278,15 +312,33 @@
 #define RIO_EM_LTL_ADDR_CAP	0x014	/* Logical/Transport Layer Address Capture CSR */
 #define RIO_EM_LTL_DEVID_CAP	0x018	/* Logical/Transport Layer Device ID Capture CSR */
 #define RIO_EM_LTL_CTRL_CAP	0x01c	/* Logical/Transport Layer Control Capture CSR */
+#define RIO_EM_LTL_DID32_CAP	0x020	/* Logical/Transport Layer Dev32 DestID Capture CSR */
+#define RIO_EM_LTL_SID32_CAP	0x024	/* Logical/Transport Layer Dev32  source ID Capture CSR */
 #define RIO_EM_PW_TGT_DEVID	0x028	/* Port-write Target deviceID CSR */
+#define  RIO_EM_PW_TGT_DEVID_D16M	0xff000000	/* Port-write Target DID16 MSB */
+#define  RIO_EM_PW_TGT_DEVID_D8		0x00ff0000	/* Port-write Target DID16 LSB or DID8 */
+#define  RIO_EM_PW_TGT_DEVID_DEV16	0x00008000	/* Port-write Target DID16 LSB or DID8 */
+#define  RIO_EM_PW_TGT_DEVID_DEV32	0x00004000	/* Port-write Target DID16 LSB or DID8 */
 #define RIO_EM_PKT_TTL		0x02c	/* Packet Time-to-live CSR */
+#define RIO_EM_PKT_TTL_VAL		0xffff0000	/* Packet Time-to-live value */
+#define RIO_EM_PW_TGT32_DEVID	0x030	/* Port-write Dev32 Target deviceID CSR */
+#define RIO_EM_PW_TX_CTRL	0x034	/* Port-write Transmission Control CSR */
+#define RIO_EM_PW_TX_CTRL_PW_DIS	0x00000001	/* Port-write Transmission Disable bit */
 
 /* Per-Port EM Registers */
 
 #define RIO_EM_PN_ERR_DETECT(x)	(0x040 + x*0x40) /* Port N Error Detect CSR */
 #define  REM_PED_IMPL_SPEC		0x80000000
+#define  REM_PED_LINK_OK2U		0x40000000 /* Link OK to Uninit transition */
+#define  REM_PED_LINK_UPDA		0x20000000 /* Link Uninit Packet Discard Active */
+#define  REM_PED_LINK_U2OK		0x10000000 /* Link Uninit to OK transition */
 #define  REM_PED_LINK_TO		0x00000001
+
 #define RIO_EM_PN_ERRRATE_EN(x) (0x044 + x*0x40) /* Port N Error Rate Enable CSR */
+#define RIO_EM_PN_ERRRATE_EN_OK2U	0x40000000 /* Enable notification for OK2U */
+#define RIO_EM_PN_ERRRATE_EN_UPDA	0x20000000 /* Enable notification for UPDA */
+#define RIO_EM_PN_ERRRATE_EN_U2OK	0x10000000 /* Enable notification for U2OK */
+
 #define RIO_EM_PN_ATTRIB_CAP(x)	(0x048 + x*0x40) /* Port N Attributes Capture CSR */
 #define RIO_EM_PN_PKT_CAP_0(x)	(0x04c + x*0x40) /* Port N Packet/Control Symbol Capture 0 CSR */
 #define RIO_EM_PN_PKT_CAP_1(x)	(0x050 + x*0x40) /* Port N Packet Capture 1 CSR */
@@ -294,5 +346,50 @@
 #define RIO_EM_PN_PKT_CAP_3(x)	(0x058 + x*0x40) /* Port N Packet Capture 3 CSR */
 #define RIO_EM_PN_ERRRATE(x)	(0x068 + x*0x40) /* Port N Error Rate CSR */
 #define RIO_EM_PN_ERRRATE_TR(x) (0x06c + x*0x40) /* Port N Error Rate Threshold CSR */
+#define RIO_EM_PN_LINK_UDT(x)	(0x070 + x*0x40) /* Port N Link Uninit Discard Timer CSR */
+#define RIO_EM_PN_LINK_UDT_TO		0xffffff00 /* Link Uninit Timeout value */
+
+/*
+ * Switch Routing Table Register Block ID=0x000E (RapidIO 3.0+, part 3)
+ * Register offsets are defined from beginning of the block.
+ */
+
+/* Broadcast Routing Table Control CSR */
+#define RIO_BC_RT_CTL_CSR	0x020
+#define  RIO_RT_CTL_THREE_LVL		0x80000000
+#define  RIO_RT_CTL_DEV32_RT_CTRL	0x40000000
+#define  RIO_RT_CTL_MC_MASK_SZ		0x03000000 /* 3.0+ Part 11: Multicast */
+
+/* Broadcast Level 0 Info CSR */
+#define RIO_BC_RT_LVL0_INFO_CSR	0x030
+#define  RIO_RT_L0I_NUM_GR		0xff000000
+#define  RIO_RT_L0I_GR_PTR		0x00fffc00
+
+/* Broadcast Level 1 Info CSR */
+#define RIO_BC_RT_LVL1_INFO_CSR	0x034
+#define  RIO_RT_L1I_NUM_GR		0xff000000
+#define  RIO_RT_L1I_GR_PTR		0x00fffc00
+
+/* Broadcast Level 2 Info CSR */
+#define RIO_BC_RT_LVL2_INFO_CSR	0x038
+#define  RIO_RT_L2I_NUM_GR		0xff000000
+#define  RIO_RT_L2I_GR_PTR		0x00fffc00
+
+/* Per-Port Routing Table registers.
+ * Register fields defined in the broadcast section above are
+ * applicable to the corresponding registers below.
+ */
+#define RIO_SPx_RT_CTL_CSR(x)	(0x040 + (0x20 * x))
+#define RIO_SPx_RT_LVL0_INFO_CSR(x)	(0x50 + (0x20 * x))
+#define RIO_SPx_RT_LVL1_INFO_CSR(x)	(0x54 + (0x20 * x))
+#define RIO_SPx_RT_LVL2_INFO_CSR(x)	(0x58 + (0x20 * x))
+
+/* Register Formats for Routing Table Group entry.
+ * Register offsets are calculated using GR_PTR field in the corresponding
+ * table Level_N and group/entry numbers (see RapidIO 3.0+ Part 3).
+ */
+#define RIO_RT_Ln_ENTRY_IMPL_DEF	0xf0000000
+#define RIO_RT_Ln_ENTRY_RTE_VAL		0x000003ff
+#define RIO_RT_ENTRY_DROP_PKT		0x300
 
 #endif				/* LINUX_RIO_REGS_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 553af2923824..62c68e513e39 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1547,6 +1547,9 @@ struct task_struct {
 	/* unserialized, strictly 'current' */
 	unsigned in_execve:1; /* bit to tell LSMs we're in execve */
 	unsigned in_iowait:1;
+#if !defined(TIF_RESTORE_SIGMASK)
+	unsigned restore_sigmask:1;
+#endif
 #ifdef CONFIG_MEMCG
 	unsigned memcg_may_oom:1;
 #ifndef CONFIG_SLOB
@@ -2680,6 +2683,66 @@ extern void sigqueue_free(struct sigqueue *);
 extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
 extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
 
+#ifdef TIF_RESTORE_SIGMASK
+/*
+ * Legacy restore_sigmask accessors.  These are inefficient on
+ * SMP architectures because they require atomic operations.
+ */
+
+/**
+ * set_restore_sigmask() - make sure saved_sigmask processing gets done
+ *
+ * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code
+ * will run before returning to user mode, to process the flag.  For
+ * all callers, TIF_SIGPENDING is already set or it's no harm to set
+ * it.  TIF_RESTORE_SIGMASK need not be in the set of bits that the
+ * arch code will notice on return to user mode, in case those bits
+ * are scarce.  We set TIF_SIGPENDING here to ensure that the arch
+ * signal code always gets run when TIF_RESTORE_SIGMASK is set.
+ */
+static inline void set_restore_sigmask(void)
+{
+	set_thread_flag(TIF_RESTORE_SIGMASK);
+	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+static inline void clear_restore_sigmask(void)
+{
+	clear_thread_flag(TIF_RESTORE_SIGMASK);
+}
+static inline bool test_restore_sigmask(void)
+{
+	return test_thread_flag(TIF_RESTORE_SIGMASK);
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+	return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK);
+}
+
+#else	/* TIF_RESTORE_SIGMASK */
+
+/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */
+static inline void set_restore_sigmask(void)
+{
+	current->restore_sigmask = true;
+	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+static inline void clear_restore_sigmask(void)
+{
+	current->restore_sigmask = false;
+}
+static inline bool test_restore_sigmask(void)
+{
+	return current->restore_sigmask;
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+	if (!current->restore_sigmask)
+		return false;
+	current->restore_sigmask = false;
+	return true;
+}
+#endif
+
 static inline void restore_saved_sigmask(void)
 {
 	if (test_and_clear_restore_sigmask())
diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h
index 35de50a65665..dc5f989be226 100644
--- a/include/linux/scpi_protocol.h
+++ b/include/linux/scpi_protocol.h
@@ -70,6 +70,8 @@ struct scpi_ops {
 	int (*sensor_get_capability)(u16 *sensors);
 	int (*sensor_get_info)(u16 sensor_id, struct scpi_sensor_info *);
 	int (*sensor_get_value)(u16, u64 *);
+	int (*device_get_power_state)(u16);
+	int (*device_set_power_state)(u16, u8);
 };
 
 #if IS_REACHABLE(CONFIG_ARM_SCPI_PROTOCOL)
diff --git a/include/linux/soc/qcom/wcnss_ctrl.h b/include/linux/soc/qcom/wcnss_ctrl.h
new file mode 100644
index 000000000000..a37bc5538f19
--- /dev/null
+++ b/include/linux/soc/qcom/wcnss_ctrl.h
@@ -0,0 +1,8 @@
+#ifndef __WCNSS_CTRL_H__
+#define __WCNSS_CTRL_H__
+
+#include <linux/soc/qcom/smd.h>
+
+struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb);
+
+#endif
diff --git a/include/linux/soc/renesas/rcar-sysc.h b/include/linux/soc/renesas/rcar-sysc.h
index 92fc613ab23d..7b8b280c181b 100644
--- a/include/linux/soc/renesas/rcar-sysc.h
+++ b/include/linux/soc/renesas/rcar-sysc.h
@@ -11,6 +11,6 @@ struct rcar_sysc_ch {
 
 int rcar_sysc_power_down(const struct rcar_sysc_ch *sysc_ch);
 int rcar_sysc_power_up(const struct rcar_sysc_ch *sysc_ch);
-void __iomem *rcar_sysc_init(phys_addr_t base);
+void rcar_sysc_init(phys_addr_t base, u32 syscier);
 
 #endif /* __LINUX_SOC_RENESAS_RCAR_SYSC_H__ */
diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 899791573a40..4ccf184e971f 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -37,7 +37,6 @@ struct rpcsec_gss_info;
 
 /* auth_cred ac_flags bits */
 enum {
-	RPC_CRED_NO_CRKEY_TIMEOUT = 0, /* underlying cred has no key timeout */
 	RPC_CRED_KEY_EXPIRE_SOON = 1, /* underlying cred key will expire soon */
 	RPC_CRED_NOTIFY_TIMEOUT = 2,   /* nofity generic cred when underlying
 					key will expire soon */
@@ -82,6 +81,9 @@ struct rpc_cred {
 
 #define RPCAUTH_CRED_MAGIC	0x0f4aa4f0
 
+/* rpc_auth au_flags */
+#define RPCAUTH_AUTH_NO_CRKEY_TIMEOUT	0x0001 /* underlying cred has no key timeout */
+
 /*
  * Client authentication handle
  */
@@ -107,6 +109,9 @@ struct rpc_auth {
 	/* per-flavor data */
 };
 
+/* rpc_auth au_flags */
+#define RPCAUTH_AUTH_DATATOUCH	0x00000002
+
 struct rpc_auth_create_args {
 	rpc_authflavor_t pseudoflavor;
 	const char *target_name;
@@ -196,7 +201,7 @@ void			rpcauth_destroy_credcache(struct rpc_auth *);
 void			rpcauth_clear_credcache(struct rpc_cred_cache *);
 int			rpcauth_key_timeout_notify(struct rpc_auth *,
 						struct rpc_cred *);
-bool			rpcauth_cred_key_to_expire(struct rpc_cred *);
+bool			rpcauth_cred_key_to_expire(struct rpc_auth *, struct rpc_cred *);
 char *			rpcauth_stringify_acceptor(struct rpc_cred *);
 
 static inline
diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h
index 1f911ccb2a75..68ec78c1aa48 100644
--- a/include/linux/sunrpc/gss_api.h
+++ b/include/linux/sunrpc/gss_api.h
@@ -73,6 +73,7 @@ u32 gss_delete_sec_context(
 rpc_authflavor_t gss_svc_to_pseudoflavor(struct gss_api_mech *, u32 qop,
 					u32 service);
 u32 gss_pseudoflavor_to_service(struct gss_api_mech *, u32 pseudoflavor);
+bool gss_pseudoflavor_to_datatouch(struct gss_api_mech *, u32 pseudoflavor);
 char *gss_service_to_auth_domain_name(struct gss_api_mech *, u32 service);
 
 struct pf_desc {
@@ -81,6 +82,7 @@ struct pf_desc {
 	u32	service;
 	char	*name;
 	char	*auth_domain_name;
+	bool	datatouch;
 };
 
 /* Different mechanisms (e.g., krb5 or spkm3) may implement gss-api, and
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 05a1809c44d9..817af0b4385e 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -230,6 +230,10 @@ void		rpc_wake_up_queued_task(struct rpc_wait_queue *,
 					struct rpc_task *);
 void		rpc_wake_up(struct rpc_wait_queue *);
 struct rpc_task *rpc_wake_up_next(struct rpc_wait_queue *);
+struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq,
+					struct rpc_wait_queue *,
+					bool (*)(struct rpc_task *, void *),
+					void *);
 struct rpc_task *rpc_wake_up_first(struct rpc_wait_queue *,
 					bool (*)(struct rpc_task *, void *),
 					void *);
@@ -247,6 +251,7 @@ void		rpc_show_tasks(struct net *);
 int		rpc_init_mempool(void);
 void		rpc_destroy_mempool(void);
 extern struct workqueue_struct *rpciod_workqueue;
+extern struct workqueue_struct *xprtiod_workqueue;
 void		rpc_prepare_task(struct rpc_task *task);
 
 static inline int rpc_wait_for_completion_task(struct rpc_task *task)
diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index 0ece4ba06f06..bef3fb0abb8f 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -80,6 +80,7 @@ struct sock_xprt {
 #define TCP_RPC_REPLY		(1UL << 6)
 
 #define XPRT_SOCK_CONNECTING	1U
+#define XPRT_SOCK_DATA_READY	(2)
 
 #endif /* __KERNEL__ */
 
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index fa7bc29925c9..697e160c78d0 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -28,6 +28,7 @@
 #include <uapi/linux/sysctl.h>
 
 /* For the /proc/sys support */
+struct completion;
 struct ctl_table;
 struct nsproxy;
 struct ctl_table_root;
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index b4c2a485b28a..352b1542f5cc 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -105,47 +105,6 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 
 #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
 
-#if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
-/*
- * An arch can define its own version of set_restore_sigmask() to get the
- * job done however works, with or without TIF_RESTORE_SIGMASK.
- */
-#define HAVE_SET_RESTORE_SIGMASK	1
-
-/**
- * set_restore_sigmask() - make sure saved_sigmask processing gets done
- *
- * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code
- * will run before returning to user mode, to process the flag.  For
- * all callers, TIF_SIGPENDING is already set or it's no harm to set
- * it.  TIF_RESTORE_SIGMASK need not be in the set of bits that the
- * arch code will notice on return to user mode, in case those bits
- * are scarce.  We set TIF_SIGPENDING here to ensure that the arch
- * signal code always gets run when TIF_RESTORE_SIGMASK is set.
- */
-static inline void set_restore_sigmask(void)
-{
-	set_thread_flag(TIF_RESTORE_SIGMASK);
-	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
-}
-static inline void clear_restore_sigmask(void)
-{
-	clear_thread_flag(TIF_RESTORE_SIGMASK);
-}
-static inline bool test_restore_sigmask(void)
-{
-	return test_thread_flag(TIF_RESTORE_SIGMASK);
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK);
-}
-#endif	/* TIF_RESTORE_SIGMASK && !HAVE_SET_RESTORE_SIGMASK */
-
-#ifndef HAVE_SET_RESTORE_SIGMASK
-#error "no set_restore_sigmask() provided and default one won't work"
-#endif
-
 #endif	/* __KERNEL__ */
 
 #endif /* _LINUX_THREAD_INFO_H */
diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h
index b39a5f3153bd..960bedbdec87 100644
--- a/include/linux/vga_switcheroo.h
+++ b/include/linux/vga_switcheroo.h
@@ -165,6 +165,7 @@ int vga_switcheroo_unlock_ddc(struct pci_dev *pdev);
 
 int vga_switcheroo_process_delayed_switch(void);
 
+bool vga_switcheroo_client_probe_defer(struct pci_dev *pdev);
 enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *dev);
 
 void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic);
@@ -188,6 +189,7 @@ static inline enum vga_switcheroo_handler_flags_t vga_switcheroo_handler_flags(v
 static inline int vga_switcheroo_lock_ddc(struct pci_dev *pdev) { return -ENODEV; }
 static inline int vga_switcheroo_unlock_ddc(struct pci_dev *pdev) { return -ENODEV; }
 static inline int vga_switcheroo_process_delayed_switch(void) { return 0; }
+static inline bool vga_switcheroo_client_probe_defer(struct pci_dev *pdev) { return false; }
 static inline enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *dev) { return VGA_SWITCHEROO_ON; }
 
 static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {}
diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h
index 51732d6c9555..7047bc7f8106 100644
--- a/include/linux/watchdog.h
+++ b/include/linux/watchdog.h
@@ -66,7 +66,8 @@ struct watchdog_ops {
  *		as configurable from user space. Only relevant if
  *		max_hw_heartbeat_ms is not provided.
  * @min_hw_heartbeat_ms:
- *		Minimum time between heartbeats, in milli-seconds.
+ *		Hardware limit for minimum time between heartbeats,
+ *		in milli-seconds.
  * @max_hw_heartbeat_ms:
  *		Hardware limit for maximum timeout, in milli-seconds.
  *		Replaces max_timeout if specified.
@@ -180,4 +181,7 @@ extern int watchdog_init_timeout(struct watchdog_device *wdd,
 extern int watchdog_register_device(struct watchdog_device *);
 extern void watchdog_unregister_device(struct watchdog_device *);
 
+/* devres register variant */
+int devm_watchdog_register_device(struct device *dev, struct watchdog_device *);
+
 #endif  /* ifndef _LINUX_WATCHDOG_H */
diff --git a/include/misc/cxl-base.h b/include/misc/cxl-base.h
index 5ae962512fb8..b2ebc91fe09a 100644
--- a/include/misc/cxl-base.h
+++ b/include/misc/cxl-base.h
@@ -10,6 +10,8 @@
 #ifndef _MISC_CXL_BASE_H
 #define _MISC_CXL_BASE_H
 
+#include <misc/cxl.h>
+
 #ifdef CONFIG_CXL_BASE
 
 #define CXL_IRQ_RANGES 4
@@ -36,12 +38,24 @@ static inline void cxl_ctx_put(void)
        atomic_dec(&cxl_use_count);
 }
 
+struct cxl_afu *cxl_afu_get(struct cxl_afu *afu);
+void cxl_afu_put(struct cxl_afu *afu);
 void cxl_slbia(struct mm_struct *mm);
+bool cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu);
+void cxl_pci_disable_device(struct pci_dev *dev);
+int cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
+void cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev);
 
 #else /* CONFIG_CXL_BASE */
 
 static inline bool cxl_ctx_in_use(void) { return false; }
+static inline struct cxl_afu *cxl_afu_get(struct cxl_afu *afu) { return NULL; }
+static inline void cxl_afu_put(struct cxl_afu *afu) {}
 static inline void cxl_slbia(struct mm_struct *mm) {}
+static inline bool cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu) { return false; }
+static inline void cxl_pci_disable_device(struct pci_dev *dev) {}
+static inline int cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) { return -ENODEV; }
+static inline void cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev) {}
 
 #endif /* CONFIG_CXL_BASE */
 
diff --git a/include/misc/cxl.h b/include/misc/cxl.h
index 56560c5781b4..480d50a0b8ba 100644
--- a/include/misc/cxl.h
+++ b/include/misc/cxl.h
@@ -24,6 +24,46 @@
  * generic PCI API. This API is agnostic to the actual AFU.
  */
 
+#define CXL_SLOT_FLAG_DMA 0x1
+
+/*
+ * Checks if the given card is in a cxl capable slot. Pass CXL_SLOT_FLAG_DMA if
+ * the card requires CAPP DMA mode to also check if the system supports it.
+ * This is intended to be used by bi-modal devices to determine if they can use
+ * cxl mode or if they should continue running in PCI mode.
+ *
+ * Note that this only checks if the slot is cxl capable - it does not
+ * currently check if the CAPP is currently available for chips where it can be
+ * assigned to different PHBs on a first come first serve basis (i.e. P8)
+ */
+bool cxl_slot_is_supported(struct pci_dev *dev, int flags);
+
+
+#define CXL_BIMODE_CXL 1
+#define CXL_BIMODE_PCI 2
+
+/*
+ * Check the mode that the given bi-modal CXL adapter is currently in and
+ * change it if necessary. This does not apply to AFU drivers.
+ *
+ * If the mode matches the requested mode this function will return 0 - if the
+ * driver was expecting the generic CXL driver to have bound to the adapter and
+ * it gets this return value it should fail the probe function to give the CXL
+ * driver a chance to probe it.
+ *
+ * If the mode does not match it will start a background task to unplug the
+ * device from Linux and switch its mode, and will return -EBUSY. At this
+ * point the calling driver should make sure it has released the device and
+ * fail its probe function.
+ *
+ * The offset of the CXL VSEC can be provided to this function. If 0 is passed,
+ * this function will search for a CXL VSEC with ID 0x1280 and return -ENODEV
+ * if it is not found.
+ */
+#ifdef CONFIG_CXL_BIMODAL
+int cxl_check_and_switch_mode(struct pci_dev *dev, int mode, int vsec);
+#endif
+
 /* Get the AFU associated with a pci_dev */
 struct cxl_afu *cxl_pci_to_afu(struct pci_dev *dev);
 
@@ -86,6 +126,13 @@ struct cxl_context *cxl_dev_context_init(struct pci_dev *dev);
 int cxl_release_context(struct cxl_context *ctx);
 
 /*
+ * Set and get private data associated with a context. Allows drivers to have a
+ * back pointer to some useful structure.
+ */
+int cxl_set_priv(struct cxl_context *ctx, void *priv);
+void *cxl_get_priv(struct cxl_context *ctx);
+
+/*
  * Allocate AFU interrupts for this context. num=0 will allocate the default
  * for this AFU as given in the AFU descriptor. This number doesn't include the
  * interrupt 0 (CAIA defines AFU IRQ 0 for page faults). Each interrupt to be
@@ -144,6 +191,25 @@ void cxl_psa_unmap(void __iomem *addr);
 /*  Get the process element for this context */
 int cxl_process_element(struct cxl_context *ctx);
 
+/*
+ * Limit the number of interrupts that a single context can allocate via
+ * cxl_start_work. If using the api with a real phb, this may be used to
+ * request that additional default contexts be created when allocating
+ * interrupts via pci_enable_msix_range. These will be set to the same running
+ * state as the default context, and if that is running it will reuse the
+ * parameters previously passed to cxl_start_context for the default context.
+ */
+int cxl_set_max_irqs_per_process(struct pci_dev *dev, int irqs);
+int cxl_get_max_irqs_per_process(struct pci_dev *dev);
+
+/*
+ * Use to simultaneously iterate over hardware interrupt numbers, contexts and
+ * afu interrupt numbers allocated for the device via pci_enable_msix_range and
+ * is a useful convenience function when working with hardware that has
+ * limitations on the number of interrupts per process. *ctx and *afu_irq
+ * should be NULL and 0 to start the iteration.
+ */
+int cxl_next_msi_hwirq(struct pci_dev *pdev, struct cxl_context **ctx, int *afu_irq);
 
 /*
  * These calls allow drivers to create their own file descriptors and make them
@@ -220,4 +286,52 @@ void cxl_perst_reloads_same_image(struct cxl_afu *afu,
  */
 ssize_t cxl_read_adapter_vpd(struct pci_dev *dev, void *buf, size_t count);
 
+/*
+ * AFU driver ops allow an AFU driver to create their own events to pass to
+ * userspace through the file descriptor as a simpler alternative to overriding
+ * the read() and poll() calls that works with the generic cxl events. These
+ * events are given priority over the generic cxl events, so they will be
+ * delivered first if multiple types of events are pending.
+ *
+ * The AFU driver must call cxl_context_events_pending() to notify the cxl
+ * driver that new events are ready to be delivered for a specific context.
+ * cxl_context_events_pending() will adjust the current count of AFU driver
+ * events for this context, and wake up anyone waiting on the context wait
+ * queue.
+ *
+ * The cxl driver will then call fetch_event() to get a structure defining
+ * the size and address of the driver specific event data. The cxl driver
+ * will build a cxl header with type and process_element fields filled in,
+ * and header.size set to sizeof(struct cxl_event_header) + data_size.
+ * The total size of the event is limited to CXL_READ_MIN_SIZE (4K).
+ *
+ * fetch_event() is called with a spin lock held, so it must not sleep.
+ *
+ * The cxl driver will then deliver the event to userspace, and finally
+ * call event_delivered() to return the status of the operation, identified
+ * by cxl context and AFU driver event data pointers.
+ *   0        Success
+ *   -EFAULT  copy_to_user() has failed
+ *   -EINVAL  Event data pointer is NULL, or event size is greater than
+ *            CXL_READ_MIN_SIZE.
+ */
+struct cxl_afu_driver_ops {
+	struct cxl_event_afu_driver_reserved *(*fetch_event) (
+						struct cxl_context *ctx);
+	void (*event_delivered) (struct cxl_context *ctx,
+				 struct cxl_event_afu_driver_reserved *event,
+				 int rc);
+};
+
+/*
+ * Associate the above driver ops with a specific context.
+ * Reset the current count of AFU driver events.
+ */
+void cxl_set_driver_ops(struct cxl_context *ctx,
+			struct cxl_afu_driver_ops *ops);
+
+/* Notify cxl driver that new events are ready to be delivered for context */
+void cxl_context_events_pending(struct cxl_context *ctx,
+				unsigned int new_events);
+
 #endif /* _MISC_CXL_H */
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 4089abc6e9c0..0933c7455a30 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -275,7 +275,7 @@ static inline struct net *read_pnet(const possible_net_t *pnet)
 #define __net_initconst
 #else
 #define __net_init	__init
-#define __net_exit	__exit_refok
+#define __net_exit	__ref
 #define __net_initdata	__initdata
 #define __net_initconst	__initconst
 #endif
diff --git a/include/soc/imx/cpuidle.h b/include/soc/imx/cpuidle.h
new file mode 100644
index 000000000000..8e7743d3b34d
--- /dev/null
+++ b/include/soc/imx/cpuidle.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright 2016 Pengutronix, <kernel@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __SOC_IMX_CPUIDLE_H__
+#define __SOC_IMX_CPUIDLE_H__
+
+#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SOC_IMX6Q)
+void imx6q_cpuidle_fec_irqs_used(void);
+void imx6q_cpuidle_fec_irqs_unused(void);
+#else
+static inline void imx6q_cpuidle_fec_irqs_used(void) { }
+static inline void imx6q_cpuidle_fec_irqs_unused(void) { }
+#endif
+
+#endif /* __SOC_IMX_CPUIDLE_H__ */
diff --git a/include/soc/tegra/cpuidle.h b/include/soc/tegra/cpuidle.h
index ea04f4225638..1fae9c7800d1 100644
--- a/include/soc/tegra/cpuidle.h
+++ b/include/soc/tegra/cpuidle.h
@@ -14,7 +14,7 @@
 #ifndef __SOC_TEGRA_CPUIDLE_H__
 #define __SOC_TEGRA_CPUIDLE_H__
 
-#ifdef CONFIG_CPU_IDLE
+#if defined(CONFIG_ARM) && defined(CONFIG_CPU_IDLE)
 void tegra_cpuidle_pcie_irqs_in_use(void);
 #else
 static inline void tegra_cpuidle_pcie_irqs_in_use(void)
diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index c0abcdc11470..cee8c00f3d3e 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -68,6 +68,7 @@ struct snd_compr_runtime {
  * @ops: pointer to DSP callbacks
  * @runtime: pointer to runtime structure
  * @device: device pointer
+ * @error_work: delayed work used when closing the stream due to an error
  * @direction: stream direction, playback/recording
  * @metadata_set: metadata set flag, true when set
  * @next_track: has userspace signal next track transition, true when set
@@ -78,6 +79,7 @@ struct snd_compr_stream {
 	struct snd_compr_ops *ops;
 	struct snd_compr_runtime *runtime;
 	struct snd_compr *device;
+	struct delayed_work error_work;
 	enum snd_compr_direction direction;
 	bool metadata_set;
 	bool next_track;
@@ -187,4 +189,7 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream)
 	wake_up(&stream->runtime->sleep);
 }
 
+int snd_compr_stop_error(struct snd_compr_stream *stream,
+			 snd_pcm_state_t state);
+
 #endif
diff --git a/include/sound/cs35l33.h b/include/sound/cs35l33.h
new file mode 100644
index 000000000000..b6eadce76fc8
--- /dev/null
+++ b/include/sound/cs35l33.h
@@ -0,0 +1,48 @@
+/*
+ * linux/sound/cs35l33.h -- Platform data for CS35l33
+ *
+ * Copyright (c) 2016 Cirrus Logic Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CS35L33_H
+#define __CS35L33_H
+
+struct cs35l33_hg {
+	bool enable_hg_algo;
+	unsigned int mem_depth;
+	unsigned int release_rate;
+	unsigned int hd_rm;
+	unsigned int ldo_thld;
+	unsigned int ldo_path_disable;
+	unsigned int ldo_entry_delay;
+	bool vp_hg_auto;
+	unsigned int vp_hg;
+	unsigned int vp_hg_rate;
+	unsigned int vp_hg_va;
+};
+
+struct cs35l33_pdata {
+	/* Boost Controller Voltage Setting */
+	unsigned int boost_ctl;
+
+	/* Boost Controller Peak Current */
+	unsigned int boost_ipk;
+
+	/* Amplifier Drive Select */
+	unsigned int amp_drv_sel;
+
+	/* soft volume ramp */
+	unsigned int ramp_rate;
+
+	/* IMON adc scale */
+	unsigned int imon_adc_scale;
+
+	/* H/G algo configuration */
+	struct cs35l33_hg hg_config;
+};
+
+#endif /* __CS35L33_H */
diff --git a/include/sound/hdmi-codec.h b/include/sound/hdmi-codec.h
index fc3a481ad91e..530c57bdefa0 100644
--- a/include/sound/hdmi-codec.h
+++ b/include/sound/hdmi-codec.h
@@ -53,18 +53,19 @@ struct hdmi_codec_params {
 	int channels;
 };
 
+struct hdmi_codec_pdata;
 struct hdmi_codec_ops {
 	/*
 	 * Called when ASoC starts an audio stream setup.
 	 * Optional
 	 */
-	int (*audio_startup)(struct device *dev);
+	int (*audio_startup)(struct device *dev, void *data);
 
 	/*
 	 * Configures HDMI-encoder for audio stream.
 	 * Mandatory
 	 */
-	int (*hw_params)(struct device *dev,
+	int (*hw_params)(struct device *dev, void *data,
 			 struct hdmi_codec_daifmt *fmt,
 			 struct hdmi_codec_params *hparms);
 
@@ -72,19 +73,20 @@ struct hdmi_codec_ops {
 	 * Shuts down the audio stream.
 	 * Mandatory
 	 */
-	void (*audio_shutdown)(struct device *dev);
+	void (*audio_shutdown)(struct device *dev, void *data);
 
 	/*
 	 * Mute/unmute HDMI audio stream.
 	 * Optional
 	 */
-	int (*digital_mute)(struct device *dev, bool enable);
+	int (*digital_mute)(struct device *dev, void *data, bool enable);
 
 	/*
 	 * Provides EDID-Like-Data from connected HDMI device.
 	 * Optional
 	 */
-	int (*get_eld)(struct device *dev, uint8_t *buf, size_t len);
+	int (*get_eld)(struct device *dev, void *data,
+		       uint8_t *buf, size_t len);
 };
 
 /* HDMI codec initalization data */
@@ -93,6 +95,7 @@ struct hdmi_codec_pdata {
 	uint i2s:1;
 	uint spdif:1;
 	int max_i2s_channels;
+	void *data;
 };
 
 #define HDMI_CODEC_DRV_NAME "hdmi-audio-codec"
diff --git a/include/sound/omap-hdmi-audio.h b/include/sound/omap-hdmi-audio.h
index afdb416898e0..1df2ff61a4dd 100644
--- a/include/sound/omap-hdmi-audio.h
+++ b/include/sound/omap-hdmi-audio.h
@@ -16,11 +16,16 @@
  *
  */
 
-#include <video/omapdss.h>
-
 #ifndef __OMAP_HDMI_AUDIO_H__
 #define __OMAP_HDMI_AUDIO_H__
 
+#include <linux/platform_data/omapdss.h>
+
+struct omap_dss_audio {
+	struct snd_aes_iec958 *iec;
+	struct snd_cea_861_aud_if *cea;
+};
+
 struct omap_hdmi_audio_ops {
 	int (*audio_startup)(struct device *dev,
 			     void (*abort_cb)(struct device *dev));
diff --git a/include/sound/simple_card.h b/include/sound/simple_card.h
index 0399352f3a62..a6a2e1547092 100644
--- a/include/sound/simple_card.h
+++ b/include/sound/simple_card.h
@@ -13,16 +13,7 @@
 #define __SIMPLE_CARD_H
 
 #include <sound/soc.h>
-
-struct asoc_simple_dai {
-	const char *name;
-	unsigned int sysclk;
-	int slots;
-	int slot_width;
-	unsigned int tx_slot_mask;
-	unsigned int rx_slot_mask;
-	struct clk *clk;
-};
+#include <sound/simple_card_utils.h>
 
 struct asoc_simple_card_info {
 	const char *name;
diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h
new file mode 100644
index 000000000000..86088aed9002
--- /dev/null
+++ b/include/sound/simple_card_utils.h
@@ -0,0 +1,36 @@
+/*
+ * simple_card_core.h
+ *
+ * Copyright (c) 2016 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SIMPLE_CARD_CORE_H
+#define __SIMPLE_CARD_CORE_H
+
+#include <sound/soc.h>
+
+struct asoc_simple_dai {
+	const char *name;
+	unsigned int sysclk;
+	int slots;
+	int slot_width;
+	unsigned int tx_slot_mask;
+	unsigned int rx_slot_mask;
+	struct clk *clk;
+};
+
+int asoc_simple_card_parse_daifmt(struct device *dev,
+				  struct device_node *node,
+				  struct device_node *codec,
+				  char *prefix,
+				  unsigned int *retfmt);
+int asoc_simple_card_set_dailink_name(struct device *dev,
+				      struct snd_soc_dai_link *dai_link,
+				      const char *fmt, ...);
+int asoc_simple_card_parse_card_name(struct snd_soc_card *card,
+				     char *prefix);
+
+#endif /* __SIMPLE_CARD_CORE_H */
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 3101d53468aa..f60d755f7ac6 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -358,6 +358,7 @@ struct snd_soc_dapm_context;
 struct regulator;
 struct snd_soc_dapm_widget_list;
 struct snd_soc_dapm_update;
+enum snd_soc_dapm_direction;
 
 int dapm_regulator_event(struct snd_soc_dapm_widget *w,
 			 struct snd_kcontrol *kcontrol, int event);
@@ -382,6 +383,9 @@ int snd_soc_dapm_put_pin_switch(struct snd_kcontrol *kcontrol,
 int snd_soc_dapm_new_controls(struct snd_soc_dapm_context *dapm,
 	const struct snd_soc_dapm_widget *widget,
 	int num);
+struct snd_soc_dapm_widget *snd_soc_dapm_new_control(
+		struct snd_soc_dapm_context *dapm,
+		const struct snd_soc_dapm_widget *widget);
 int snd_soc_dapm_new_dai_widgets(struct snd_soc_dapm_context *dapm,
 				 struct snd_soc_dai *dai);
 int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card);
@@ -451,7 +455,9 @@ void dapm_mark_endpoints_dirty(struct snd_soc_card *card);
 
 /* dapm path query */
 int snd_soc_dapm_dai_get_connected_widgets(struct snd_soc_dai *dai, int stream,
-	struct snd_soc_dapm_widget_list **list);
+	struct snd_soc_dapm_widget_list **list,
+	bool (*custom_stop_condition)(struct snd_soc_dapm_widget *,
+				      enum snd_soc_dapm_direction));
 
 struct snd_soc_dapm_context *snd_soc_dapm_kcontrol_dapm(
 	struct snd_kcontrol *kcontrol);
diff --git a/include/sound/soc.h b/include/sound/soc.h
index fd7b58a58d6f..6144882cc96a 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -179,6 +179,17 @@
 	.get = snd_soc_get_volsw, .put = snd_soc_put_volsw, \
 	.private_value = SOC_DOUBLE_R_S_VALUE(reg_left, reg_right, xshift, \
 					    xmin, xmax, xsign_bit, xinvert) }
+#define SOC_SINGLE_S8_TLV(xname, xreg, xmin, xmax, tlv_array) \
+{	.iface  = SNDRV_CTL_ELEM_IFACE_MIXER, .name = (xname), \
+	.access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \
+		  SNDRV_CTL_ELEM_ACCESS_READWRITE, \
+	.tlv.p  = (tlv_array), \
+	.info = snd_soc_info_volsw, .get = snd_soc_get_volsw,\
+	.put = snd_soc_put_volsw, \
+	.private_value = (unsigned long)&(struct soc_mixer_control) \
+	{.reg = xreg, .rreg = xreg,  \
+	 .min = xmin, .max = xmax, .platform_max = xmax, \
+	.sign_bit = 7,} }
 #define SOC_DOUBLE_S8_TLV(xname, xreg, xmin, xmax, tlv_array) \
 {	.iface  = SNDRV_CTL_ELEM_IFACE_MIXER, .name = (xname), \
 	.access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index e90e82ad6875..5b81ef304388 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -440,6 +440,46 @@ TRACE_EVENT(btrfs_sync_fs,
 	TP_printk("wait = %d", __entry->wait)
 );
 
+TRACE_EVENT(btrfs_add_block_group,
+
+	TP_PROTO(struct btrfs_fs_info *fs_info,
+		 struct btrfs_block_group_cache *block_group, int create),
+
+	TP_ARGS(fs_info, block_group, create),
+
+	TP_STRUCT__entry(
+		__array(	u8,	fsid,	BTRFS_UUID_SIZE	)
+		__field(	u64,	offset			)
+		__field(	u64,	size			)
+		__field(	u64,	flags			)
+		__field(	u64,	bytes_used		)
+		__field(	u64,	bytes_super		)
+		__field(	int,	create			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE);
+		__entry->offset		= block_group->key.objectid;
+		__entry->size		= block_group->key.offset;
+		__entry->flags		= block_group->flags;
+		__entry->bytes_used	=
+			btrfs_block_group_used(&block_group->item);
+		__entry->bytes_super	= block_group->bytes_super;
+		__entry->create		= create;
+	),
+
+	TP_printk("%pU: block_group offset = %llu, size = %llu, "
+		  "flags = %llu(%s), bytes_used = %llu, bytes_super = %llu, "
+		  "create = %d", __entry->fsid,
+		  (unsigned long long)__entry->offset,
+		  (unsigned long long)__entry->size,
+		  (unsigned long long)__entry->flags,
+		  __print_flags((unsigned long)__entry->flags, "|",
+				BTRFS_GROUP_FLAGS),
+		  (unsigned long long)__entry->bytes_used,
+		  (unsigned long long)__entry->bytes_super, __entry->create)
+);
+
 #define show_ref_action(action)						\
 	__print_symbolic(action,					\
 		{ BTRFS_ADD_DELAYED_REF,    "ADD_DELAYED_REF" },	\
@@ -744,6 +784,88 @@ TRACE_EVENT(btrfs_space_reservation,
 		  __entry->bytes)
 );
 
+#define show_flush_action(action)						\
+	__print_symbolic(action,						\
+		{ BTRFS_RESERVE_NO_FLUSH,	"BTRFS_RESERVE_NO_FLUSH"},	\
+		{ BTRFS_RESERVE_FLUSH_LIMIT,	"BTRFS_RESERVE_FLUSH_LIMIT"},	\
+		{ BTRFS_RESERVE_FLUSH_ALL,	"BTRFS_RESERVE_FLUSH_ALL"})
+
+TRACE_EVENT(btrfs_trigger_flush,
+
+	TP_PROTO(struct btrfs_fs_info *fs_info, u64 flags, u64 bytes,
+		 int flush, char *reason),
+
+	TP_ARGS(fs_info, flags, bytes, flush, reason),
+
+	TP_STRUCT__entry(
+		__array(	u8,	fsid,	BTRFS_UUID_SIZE	)
+		__field(	u64,	flags			)
+		__field(	u64,	bytes			)
+		__field(	int,	flush			)
+		__string(	reason,	reason			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE);
+		__entry->flags	= flags;
+		__entry->bytes	= bytes;
+		__entry->flush	= flush;
+		__assign_str(reason, reason)
+	),
+
+	TP_printk("%pU: %s: flush = %d(%s), flags = %llu(%s), bytes = %llu",
+		  __entry->fsid, __get_str(reason), __entry->flush,
+		  show_flush_action(__entry->flush),
+		  (unsigned long long)__entry->flags,
+		  __print_flags((unsigned long)__entry->flags, "|",
+				BTRFS_GROUP_FLAGS),
+		  (unsigned long long)__entry->bytes)
+);
+
+#define show_flush_state(state)							\
+	__print_symbolic(state,							\
+		{ FLUSH_DELAYED_ITEMS_NR,	"FLUSH_DELAYED_ITEMS_NR"},	\
+		{ FLUSH_DELAYED_ITEMS,		"FLUSH_DELAYED_ITEMS"},		\
+		{ FLUSH_DELALLOC,		"FLUSH_DELALLOC"},		\
+		{ FLUSH_DELALLOC_WAIT,		"FLUSH_DELALLOC_WAIT"},		\
+		{ ALLOC_CHUNK,			"ALLOC_CHUNK"},			\
+		{ COMMIT_TRANS,			"COMMIT_TRANS"})
+
+TRACE_EVENT(btrfs_flush_space,
+
+	TP_PROTO(struct btrfs_fs_info *fs_info, u64 flags, u64 num_bytes,
+		 u64 orig_bytes, int state, int ret),
+
+	TP_ARGS(fs_info, flags, num_bytes, orig_bytes, state, ret),
+
+	TP_STRUCT__entry(
+		__array(	u8,	fsid,	BTRFS_UUID_SIZE	)
+		__field(	u64,	flags			)
+		__field(	u64,	num_bytes		)
+		__field(	u64,	orig_bytes		)
+		__field(	int,	state			)
+		__field(	int,	ret			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE);
+		__entry->flags		=	flags;
+		__entry->num_bytes	=	num_bytes;
+		__entry->orig_bytes	=	orig_bytes;
+		__entry->state		=	state;
+		__entry->ret		=	ret;
+	),
+
+	TP_printk("%pU: state = %d(%s), flags = %llu(%s), num_bytes = %llu, "
+		  "orig_bytes = %llu, ret = %d", __entry->fsid, __entry->state,
+		  show_flush_state(__entry->state),
+		  (unsigned long long)__entry->flags,
+		  __print_flags((unsigned long)__entry->flags, "|",
+				BTRFS_GROUP_FLAGS),
+		  (unsigned long long)__entry->num_bytes,
+		  (unsigned long long)__entry->orig_bytes, __entry->ret)
+);
+
 DECLARE_EVENT_CLASS(btrfs__reserved_extent,
 
 	TP_PROTO(struct btrfs_root *root, u64 start, u64 len),
@@ -751,18 +873,21 @@ DECLARE_EVENT_CLASS(btrfs__reserved_extent,
 	TP_ARGS(root, start, len),
 
 	TP_STRUCT__entry(
-		__field(	u64,  root_objectid		)
-		__field(	u64,  start			)
-		__field(	u64,  len			)
+		__array(	u8,	fsid,	BTRFS_UUID_SIZE	)
+		__field(	u64,	root_objectid		)
+		__field(	u64,	start			)
+		__field(	u64,	len			)
 	),
 
 	TP_fast_assign(
+		memcpy(__entry->fsid, root->fs_info->fsid, BTRFS_UUID_SIZE);
 		__entry->root_objectid	= root->root_key.objectid;
 		__entry->start		= start;
 		__entry->len		= len;
 	),
 
-	TP_printk("root = %llu(%s), start = %llu, len = %llu",
+	TP_printk("%pU: root = %llu(%s), start = %llu, len = %llu",
+		  __entry->fsid,
 		  show_root_type(__entry->root_objectid),
 		  (unsigned long long)__entry->start,
 		  (unsigned long long)__entry->len)
@@ -819,6 +944,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
 	TP_ARGS(root, block_group, start, len),
 
 	TP_STRUCT__entry(
+		__array(	u8,	fsid,	BTRFS_UUID_SIZE	)
 		__field(	u64,	root_objectid		)
 		__field(	u64,	bg_objectid		)
 		__field(	u64,	flags			)
@@ -827,6 +953,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
 	),
 
 	TP_fast_assign(
+		memcpy(__entry->fsid, root->fs_info->fsid, BTRFS_UUID_SIZE);
 		__entry->root_objectid	= root->root_key.objectid;
 		__entry->bg_objectid	= block_group->key.objectid;
 		__entry->flags		= block_group->flags;
@@ -834,8 +961,8 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
 		__entry->len		= len;
 	),
 
-	TP_printk("root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), "
-		  "start = %Lu, len = %Lu",
+	TP_printk("%pU: root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), "
+		  "start = %Lu, len = %Lu", __entry->fsid,
 		  show_root_type(__entry->root_objectid), __entry->bg_objectid,
 		  __entry->flags, __print_flags((unsigned long)__entry->flags,
 						"|", BTRFS_GROUP_FLAGS),
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index f28292d73ddb..8ade3eb6c640 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -151,8 +151,9 @@ TRACE_EVENT(kvm_msi_set_irq,
 		__entry->data		= data;
 	),
 
-	TP_printk("dst %u vec %u (%s|%s|%s%s)",
-		  (u8)(__entry->address >> 12), (u8)__entry->data,
+	TP_printk("dst %llx vec %u (%s|%s|%s%s)",
+		  (u8)(__entry->address >> 12) | ((__entry->address >> 32) & 0xffffff00),
+		  (u8)__entry->data,
 		  __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode),
 		  (__entry->address & (1<<2)) ? "logical" : "physical",
 		  (__entry->data & (1<<15)) ? "level" : "edge",
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index cdecf87576e8..462246aa200e 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -487,6 +487,22 @@ struct drm_amdgpu_cs_chunk_data {
 #define AMDGPU_INFO_MMR_SH_INDEX_SHIFT	8
 #define AMDGPU_INFO_MMR_SH_INDEX_MASK	0xff
 
+struct drm_amdgpu_query_fw {
+	/** AMDGPU_INFO_FW_* */
+	__u32 fw_type;
+	/**
+	 * Index of the IP if there are more IPs of
+	 * the same type.
+	 */
+	__u32 ip_instance;
+	/**
+	 * Index of the engine. Whether this is used depends
+	 * on the firmware type. (e.g. MEC, SDMA)
+	 */
+	__u32 index;
+	__u32 _pad;
+};
+
 /* Input structure for the INFO ioctl */
 struct drm_amdgpu_info {
 	/* Where the return value will be stored */
@@ -522,21 +538,7 @@ struct drm_amdgpu_info {
 			__u32 flags;
 		} read_mmr_reg;
 
-		struct {
-			/** AMDGPU_INFO_FW_* */
-			__u32 fw_type;
-			/**
-			 * Index of the IP if there are more IPs of
-			 * the same type.
-			 */
-			__u32 ip_instance;
-			/**
-			 * Index of the engine. Whether this is used depends
-			 * on the firmware type. (e.g. MEC, SDMA)
-			 */
-			__u32 index;
-			__u32 _pad;
-		} query_fw;
+		struct drm_amdgpu_query_fw query_fw;
 	};
 };
 
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index c17d63d8b543..d7e81a3886fd 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -361,6 +361,8 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_GPU_RESET	 35
 #define I915_PARAM_HAS_RESOURCE_STREAMER 36
 #define I915_PARAM_HAS_EXEC_SOFTPIN	 37
+#define I915_PARAM_HAS_POOLED_EU	 38
+#define I915_PARAM_MIN_EU_IN_POOL	 39
 
 typedef struct drm_i915_getparam {
 	__s32 param;
@@ -1171,6 +1173,7 @@ struct drm_i915_gem_context_param {
 #define I915_CONTEXT_PARAM_BAN_PERIOD	0x1
 #define I915_CONTEXT_PARAM_NO_ZEROMAP	0x2
 #define I915_CONTEXT_PARAM_GTT_SIZE	0x3
+#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
 	__u64 value;
 };
 
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index bf19d2cd9078..49f778de8e06 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -201,6 +201,27 @@ struct drm_msm_wait_fence {
 	struct drm_msm_timespec timeout;   /* in */
 };
 
+/* madvise provides a way to tell the kernel in case a buffers contents
+ * can be discarded under memory pressure, which is useful for userspace
+ * bo cache where we want to optimistically hold on to buffer allocate
+ * and potential mmap, but allow the pages to be discarded under memory
+ * pressure.
+ *
+ * Typical usage would involve madvise(DONTNEED) when buffer enters BO
+ * cache, and madvise(WILLNEED) if trying to recycle buffer from BO cache.
+ * In the WILLNEED case, 'retained' indicates to userspace whether the
+ * backing pages still exist.
+ */
+#define MSM_MADV_WILLNEED 0       /* backing pages are needed, status returned in 'retained' */
+#define MSM_MADV_DONTNEED 1       /* backing pages not needed */
+#define __MSM_MADV_PURGED 2       /* internal state */
+
+struct drm_msm_gem_madvise {
+	__u32 handle;         /* in, GEM handle */
+	__u32 madv;           /* in, MSM_MADV_x */
+	__u32 retained;       /* out, whether backing store still exists */
+};
+
 #define DRM_MSM_GET_PARAM              0x00
 /* placeholder:
 #define DRM_MSM_SET_PARAM              0x01
@@ -211,7 +232,8 @@ struct drm_msm_wait_fence {
 #define DRM_MSM_GEM_CPU_FINI           0x05
 #define DRM_MSM_GEM_SUBMIT             0x06
 #define DRM_MSM_WAIT_FENCE             0x07
-#define DRM_MSM_NUM_IOCTLS             0x08
+#define DRM_MSM_GEM_MADVISE            0x08
+#define DRM_MSM_NUM_IOCTLS             0x09
 
 #define DRM_IOCTL_MSM_GET_PARAM        DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GET_PARAM, struct drm_msm_param)
 #define DRM_IOCTL_MSM_GEM_NEW          DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_NEW, struct drm_msm_gem_new)
@@ -220,6 +242,7 @@ struct drm_msm_wait_fence {
 #define DRM_IOCTL_MSM_GEM_CPU_FINI     DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_GEM_CPU_FINI, struct drm_msm_gem_cpu_fini)
 #define DRM_IOCTL_MSM_GEM_SUBMIT       DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_SUBMIT, struct drm_msm_gem_submit)
 #define DRM_IOCTL_MSM_WAIT_FENCE       DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_WAIT_FENCE, struct drm_msm_wait_fence)
+#define DRM_IOCTL_MSM_GEM_MADVISE      DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_MADVISE, struct drm_msm_gem_madvise)
 
 #if defined(__cplusplus)
 }
diff --git a/include/uapi/drm/vc4_drm.h b/include/uapi/drm/vc4_drm.h
index af12e8a184c8..ad7edc3edf7c 100644
--- a/include/uapi/drm/vc4_drm.h
+++ b/include/uapi/drm/vc4_drm.h
@@ -37,6 +37,7 @@ extern "C" {
 #define DRM_VC4_MMAP_BO                           0x04
 #define DRM_VC4_CREATE_SHADER_BO                  0x05
 #define DRM_VC4_GET_HANG_STATE                    0x06
+#define DRM_VC4_GET_PARAM                         0x07
 
 #define DRM_IOCTL_VC4_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SUBMIT_CL, struct drm_vc4_submit_cl)
 #define DRM_IOCTL_VC4_WAIT_SEQNO          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_WAIT_SEQNO, struct drm_vc4_wait_seqno)
@@ -45,6 +46,7 @@ extern "C" {
 #define DRM_IOCTL_VC4_MMAP_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_MMAP_BO, struct drm_vc4_mmap_bo)
 #define DRM_IOCTL_VC4_CREATE_SHADER_BO    DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_CREATE_SHADER_BO, struct drm_vc4_create_shader_bo)
 #define DRM_IOCTL_VC4_GET_HANG_STATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_HANG_STATE, struct drm_vc4_get_hang_state)
+#define DRM_IOCTL_VC4_GET_PARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_PARAM, struct drm_vc4_get_param)
 
 struct drm_vc4_submit_rcl_surface {
 	__u32 hindex; /* Handle index, or ~0 if not present. */
@@ -280,6 +282,17 @@ struct drm_vc4_get_hang_state {
 	__u32 pad[16];
 };
 
+#define DRM_VC4_PARAM_V3D_IDENT0		0
+#define DRM_VC4_PARAM_V3D_IDENT1		1
+#define DRM_VC4_PARAM_V3D_IDENT2		2
+#define DRM_VC4_PARAM_SUPPORTS_BRANCHES		3
+
+struct drm_vc4_get_param {
+	__u32 param;
+	__u32 pad;
+	__u64 value;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/vgem_drm.h b/include/uapi/drm/vgem_drm.h
new file mode 100644
index 000000000000..bf66f5db6da8
--- /dev/null
+++ b/include/uapi/drm/vgem_drm.h
@@ -0,0 +1,62 @@
+/*
+ * Copyright 2016 Intel Corporation
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
+ * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR
+ * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _UAPI_VGEM_DRM_H_
+#define _UAPI_VGEM_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/* Please note that modifications to all structs defined here are
+ * subject to backwards-compatibility constraints.
+ */
+#define DRM_VGEM_FENCE_ATTACH	0x1
+#define DRM_VGEM_FENCE_SIGNAL	0x2
+
+#define DRM_IOCTL_VGEM_FENCE_ATTACH	DRM_IOWR( DRM_COMMAND_BASE + DRM_VGEM_FENCE_ATTACH, struct drm_vgem_fence_attach)
+#define DRM_IOCTL_VGEM_FENCE_SIGNAL	DRM_IOW( DRM_COMMAND_BASE + DRM_VGEM_FENCE_SIGNAL, struct drm_vgem_fence_signal)
+
+struct drm_vgem_fence_attach {
+	__u32 handle;
+	__u32 flags;
+#define VGEM_FENCE_WRITE	0x1
+	__u32 out_fence;
+	__u32 pad;
+};
+
+struct drm_vgem_fence_signal {
+	__u32 fence;
+	__u32 flags;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _UAPI_VGEM_DRM_H_ */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 6d4e92ccdc91..c44747c0796a 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -357,6 +357,7 @@ header-y += reiserfs_fs.h
 header-y += reiserfs_xattr.h
 header-y += resource.h
 header-y += rfkill.h
+header-y += rio_cm_cdev.h
 header-y += rio_mport_cdev.h
 header-y += romfs_fs.h
 header-y += rose.h
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index 12c37a197d24..49bc06295398 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -15,8 +15,6 @@
 
 #include <linux/types.h>
 
-struct task_struct;
-
 /* User-level do most of the mapping between kernel and user
    capabilities based on the version tag given by the kernel. The
    kernel might be somewhat backwards compatible, but don't bet on
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 05ebf475104c..e98bb4cce639 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -866,6 +866,10 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_ARM_PMU_V3 126
 #define KVM_CAP_VCPU_ATTRIBUTES 127
 #define KVM_CAP_MAX_VCPU_ID 128
+#define KVM_CAP_X2APIC_API 129
+#define KVM_CAP_S390_USER_INSTR0 130
+#define KVM_CAP_MSI_DEVID 131
+#define KVM_CAP_PPC_HTM 132
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1024,12 +1028,14 @@ struct kvm_one_reg {
 	__u64 addr;
 };
 
+#define KVM_MSI_VALID_DEVID	(1U << 0)
 struct kvm_msi {
 	__u32 address_lo;
 	__u32 address_hi;
 	__u32 data;
 	__u32 flags;
-	__u8  pad[16];
+	__u32 devid;
+	__u8  pad[12];
 };
 
 struct kvm_arm_device_addr {
@@ -1074,6 +1080,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_FLIC		KVM_DEV_TYPE_FLIC
 	KVM_DEV_TYPE_ARM_VGIC_V3,
 #define KVM_DEV_TYPE_ARM_VGIC_V3	KVM_DEV_TYPE_ARM_VGIC_V3
+	KVM_DEV_TYPE_ARM_VGIC_ITS,
+#define KVM_DEV_TYPE_ARM_VGIC_ITS	KVM_DEV_TYPE_ARM_VGIC_ITS
 	KVM_DEV_TYPE_MAX,
 };
 
@@ -1313,4 +1321,7 @@ struct kvm_assigned_msix_entry {
 	__u16 padding[3];
 };
 
+#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
+
 #endif /* __LINUX_KVM_H */
diff --git a/include/uapi/linux/nilfs2_api.h b/include/uapi/linux/nilfs2_api.h
new file mode 100644
index 000000000000..ef4c1de89b11
--- /dev/null
+++ b/include/uapi/linux/nilfs2_api.h
@@ -0,0 +1,292 @@
+/*
+ * nilfs2_api.h - NILFS2 user space API
+ *
+ * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; either version 2.1 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _LINUX_NILFS2_API_H
+#define _LINUX_NILFS2_API_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/**
+ * struct nilfs_cpinfo - checkpoint information
+ * @ci_flags: flags
+ * @ci_pad: padding
+ * @ci_cno: checkpoint number
+ * @ci_create: creation timestamp
+ * @ci_nblk_inc: number of blocks incremented by this checkpoint
+ * @ci_inodes_count: inodes count
+ * @ci_blocks_count: blocks count
+ * @ci_next: next checkpoint number in snapshot list
+ */
+struct nilfs_cpinfo {
+	__u32 ci_flags;
+	__u32 ci_pad;
+	__u64 ci_cno;
+	__u64 ci_create;
+	__u64 ci_nblk_inc;
+	__u64 ci_inodes_count;
+	__u64 ci_blocks_count;
+	__u64 ci_next;
+};
+
+/* checkpoint flags */
+enum {
+	NILFS_CPINFO_SNAPSHOT,
+	NILFS_CPINFO_INVALID,
+	NILFS_CPINFO_SKETCH,
+	NILFS_CPINFO_MINOR,
+};
+
+#define NILFS_CPINFO_FNS(flag, name)					\
+static inline int							\
+nilfs_cpinfo_##name(const struct nilfs_cpinfo *cpinfo)			\
+{									\
+	return !!(cpinfo->ci_flags & (1UL << NILFS_CPINFO_##flag));	\
+}
+
+NILFS_CPINFO_FNS(SNAPSHOT, snapshot)
+NILFS_CPINFO_FNS(INVALID, invalid)
+NILFS_CPINFO_FNS(MINOR, minor)
+
+/**
+ * nilfs_suinfo - segment usage information
+ * @sui_lastmod: timestamp of last modification
+ * @sui_nblocks: number of written blocks in segment
+ * @sui_flags: segment usage flags
+ */
+struct nilfs_suinfo {
+	__u64 sui_lastmod;
+	__u32 sui_nblocks;
+	__u32 sui_flags;
+};
+
+/* segment usage flags */
+enum {
+	NILFS_SUINFO_ACTIVE,
+	NILFS_SUINFO_DIRTY,
+	NILFS_SUINFO_ERROR,
+};
+
+#define NILFS_SUINFO_FNS(flag, name)					\
+static inline int							\
+nilfs_suinfo_##name(const struct nilfs_suinfo *si)			\
+{									\
+	return si->sui_flags & (1UL << NILFS_SUINFO_##flag);		\
+}
+
+NILFS_SUINFO_FNS(ACTIVE, active)
+NILFS_SUINFO_FNS(DIRTY, dirty)
+NILFS_SUINFO_FNS(ERROR, error)
+
+static inline int nilfs_suinfo_clean(const struct nilfs_suinfo *si)
+{
+	return !si->sui_flags;
+}
+
+/**
+ * nilfs_suinfo_update - segment usage information update
+ * @sup_segnum: segment number
+ * @sup_flags: flags for which fields are active in sup_sui
+ * @sup_reserved: reserved necessary for alignment
+ * @sup_sui: segment usage information
+ */
+struct nilfs_suinfo_update {
+	__u64 sup_segnum;
+	__u32 sup_flags;
+	__u32 sup_reserved;
+	struct nilfs_suinfo sup_sui;
+};
+
+enum {
+	NILFS_SUINFO_UPDATE_LASTMOD,
+	NILFS_SUINFO_UPDATE_NBLOCKS,
+	NILFS_SUINFO_UPDATE_FLAGS,
+	__NR_NILFS_SUINFO_UPDATE_FIELDS,
+};
+
+#define NILFS_SUINFO_UPDATE_FNS(flag, name)				\
+static inline void							\
+nilfs_suinfo_update_set_##name(struct nilfs_suinfo_update *sup)		\
+{									\
+	sup->sup_flags |= 1UL << NILFS_SUINFO_UPDATE_##flag;		\
+}									\
+static inline void							\
+nilfs_suinfo_update_clear_##name(struct nilfs_suinfo_update *sup)	\
+{									\
+	sup->sup_flags &= ~(1UL << NILFS_SUINFO_UPDATE_##flag);		\
+}									\
+static inline int							\
+nilfs_suinfo_update_##name(const struct nilfs_suinfo_update *sup)	\
+{									\
+	return !!(sup->sup_flags & (1UL << NILFS_SUINFO_UPDATE_##flag));\
+}
+
+NILFS_SUINFO_UPDATE_FNS(LASTMOD, lastmod)
+NILFS_SUINFO_UPDATE_FNS(NBLOCKS, nblocks)
+NILFS_SUINFO_UPDATE_FNS(FLAGS, flags)
+
+enum {
+	NILFS_CHECKPOINT,
+	NILFS_SNAPSHOT,
+};
+
+/**
+ * struct nilfs_cpmode - change checkpoint mode structure
+ * @cm_cno: checkpoint number
+ * @cm_mode: mode of checkpoint
+ * @cm_pad: padding
+ */
+struct nilfs_cpmode {
+	__u64 cm_cno;
+	__u32 cm_mode;
+	__u32 cm_pad;
+};
+
+/**
+ * struct nilfs_argv - argument vector
+ * @v_base: pointer on data array from userspace
+ * @v_nmembs: number of members in data array
+ * @v_size: size of data array in bytes
+ * @v_flags: flags
+ * @v_index: start number of target data items
+ */
+struct nilfs_argv {
+	__u64 v_base;
+	__u32 v_nmembs;	/* number of members */
+	__u16 v_size;	/* size of members */
+	__u16 v_flags;
+	__u64 v_index;
+};
+
+/**
+ * struct nilfs_period - period of checkpoint numbers
+ * @p_start: start checkpoint number (inclusive)
+ * @p_end: end checkpoint number (exclusive)
+ */
+struct nilfs_period {
+	__u64 p_start;
+	__u64 p_end;
+};
+
+/**
+ * struct nilfs_cpstat - checkpoint statistics
+ * @cs_cno: checkpoint number
+ * @cs_ncps: number of checkpoints
+ * @cs_nsss: number of snapshots
+ */
+struct nilfs_cpstat {
+	__u64 cs_cno;
+	__u64 cs_ncps;
+	__u64 cs_nsss;
+};
+
+/**
+ * struct nilfs_sustat - segment usage statistics
+ * @ss_nsegs: number of segments
+ * @ss_ncleansegs: number of clean segments
+ * @ss_ndirtysegs: number of dirty segments
+ * @ss_ctime: creation time of the last segment
+ * @ss_nongc_ctime: creation time of the last segment not for GC
+ * @ss_prot_seq: least sequence number of segments which must not be reclaimed
+ */
+struct nilfs_sustat {
+	__u64 ss_nsegs;
+	__u64 ss_ncleansegs;
+	__u64 ss_ndirtysegs;
+	__u64 ss_ctime;
+	__u64 ss_nongc_ctime;
+	__u64 ss_prot_seq;
+};
+
+/**
+ * struct nilfs_vinfo - virtual block number information
+ * @vi_vblocknr: virtual block number
+ * @vi_start: start checkpoint number (inclusive)
+ * @vi_end: end checkpoint number (exclusive)
+ * @vi_blocknr: disk block number
+ */
+struct nilfs_vinfo {
+	__u64 vi_vblocknr;
+	__u64 vi_start;
+	__u64 vi_end;
+	__u64 vi_blocknr;
+};
+
+/**
+ * struct nilfs_vdesc - descriptor of virtual block number
+ * @vd_ino: inode number
+ * @vd_cno: checkpoint number
+ * @vd_vblocknr: virtual block number
+ * @vd_period: period of checkpoint numbers
+ * @vd_blocknr: disk block number
+ * @vd_offset: logical block offset inside a file
+ * @vd_flags: flags (data or node block)
+ * @vd_pad: padding
+ */
+struct nilfs_vdesc {
+	__u64 vd_ino;
+	__u64 vd_cno;
+	__u64 vd_vblocknr;
+	struct nilfs_period vd_period;
+	__u64 vd_blocknr;
+	__u64 vd_offset;
+	__u32 vd_flags;
+	__u32 vd_pad;
+};
+
+/**
+ * struct nilfs_bdesc - descriptor of disk block number
+ * @bd_ino: inode number
+ * @bd_oblocknr: disk block address (for skipping dead blocks)
+ * @bd_blocknr: disk block address
+ * @bd_offset: logical block offset inside a file
+ * @bd_level: level in the b-tree organization
+ * @bd_pad: padding
+ */
+struct nilfs_bdesc {
+	__u64 bd_ino;
+	__u64 bd_oblocknr;
+	__u64 bd_blocknr;
+	__u64 bd_offset;
+	__u32 bd_level;
+	__u32 bd_pad;
+};
+
+#define NILFS_IOCTL_IDENT	'n'
+
+#define NILFS_IOCTL_CHANGE_CPMODE					\
+	_IOW(NILFS_IOCTL_IDENT, 0x80, struct nilfs_cpmode)
+#define NILFS_IOCTL_DELETE_CHECKPOINT					\
+	_IOW(NILFS_IOCTL_IDENT, 0x81, __u64)
+#define NILFS_IOCTL_GET_CPINFO						\
+	_IOR(NILFS_IOCTL_IDENT, 0x82, struct nilfs_argv)
+#define NILFS_IOCTL_GET_CPSTAT						\
+	_IOR(NILFS_IOCTL_IDENT, 0x83, struct nilfs_cpstat)
+#define NILFS_IOCTL_GET_SUINFO						\
+	_IOR(NILFS_IOCTL_IDENT, 0x84, struct nilfs_argv)
+#define NILFS_IOCTL_GET_SUSTAT						\
+	_IOR(NILFS_IOCTL_IDENT, 0x85, struct nilfs_sustat)
+#define NILFS_IOCTL_GET_VINFO						\
+	_IOWR(NILFS_IOCTL_IDENT, 0x86, struct nilfs_argv)
+#define NILFS_IOCTL_GET_BDESCS						\
+	_IOWR(NILFS_IOCTL_IDENT, 0x87, struct nilfs_argv)
+#define NILFS_IOCTL_CLEAN_SEGMENTS					\
+	_IOW(NILFS_IOCTL_IDENT, 0x88, struct nilfs_argv[5])
+#define NILFS_IOCTL_SYNC						\
+	_IOR(NILFS_IOCTL_IDENT, 0x8A, __u64)
+#define NILFS_IOCTL_RESIZE						\
+	_IOW(NILFS_IOCTL_IDENT, 0x8B, __u64)
+#define NILFS_IOCTL_SET_ALLOC_RANGE					\
+	_IOW(NILFS_IOCTL_IDENT, 0x8C, __u64[2])
+#define NILFS_IOCTL_SET_SUINFO						\
+	_IOW(NILFS_IOCTL_IDENT, 0x8D, struct nilfs_argv)
+
+#endif /* _LINUX_NILFS2_API_H */
diff --git a/include/linux/nilfs2_fs.h b/include/uapi/linux/nilfs2_ondisk.h
index 5988dd57ba66..2a8a3addb675 100644
--- a/include/linux/nilfs2_fs.h
+++ b/include/uapi/linux/nilfs2_ondisk.h
@@ -1,5 +1,5 @@
 /*
- * nilfs2_fs.h - NILFS2 on-disk structures and common declarations.
+ * nilfs2_ondisk.h - NILFS2 on-disk structures
  *
  * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
  *
@@ -7,13 +7,6 @@
  * it under the terms of the GNU Lesser General Public License as published
  * by the Free Software Foundation; either version 2.1 of the License, or
  * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * Written by Koji Sato and Ryusuke Konishi.
  */
 /*
  *  linux/include/linux/ext2_fs.h
@@ -30,16 +23,15 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  */
 
-#ifndef _LINUX_NILFS_FS_H
-#define _LINUX_NILFS_FS_H
+#ifndef _LINUX_NILFS2_ONDISK_H
+#define _LINUX_NILFS2_ONDISK_H
 
 #include <linux/types.h>
-#include <linux/ioctl.h>
 #include <linux/magic.h>
-#include <linux/bug.h>
 
 
 #define NILFS_INODE_BMAP_SIZE	7
+
 /**
  * struct nilfs_inode - structure of an inode on disk
  * @i_blocks: blocks count
@@ -56,7 +48,7 @@
  * @i_bmap: block mapping
  * @i_xattr: extended attributes
  * @i_generation: file generation (for NFS)
- * @i_pad:	padding
+ * @i_pad: padding
  */
 struct nilfs_inode {
 	__le64	i_blocks;
@@ -338,29 +330,7 @@ enum {
 #define NILFS_DIR_ROUND			(NILFS_DIR_PAD - 1)
 #define NILFS_DIR_REC_LEN(name_len)	(((name_len) + 12 + NILFS_DIR_ROUND) & \
 					~NILFS_DIR_ROUND)
-#define NILFS_MAX_REC_LEN		((1<<16)-1)
-
-static inline unsigned int nilfs_rec_len_from_disk(__le16 dlen)
-{
-	unsigned int len = le16_to_cpu(dlen);
-
-#if !defined(__KERNEL__) || (PAGE_SIZE >= 65536)
-	if (len == NILFS_MAX_REC_LEN)
-		return 1 << 16;
-#endif
-	return len;
-}
-
-static inline __le16 nilfs_rec_len_to_disk(unsigned int len)
-{
-#if !defined(__KERNEL__) || (PAGE_SIZE >= 65536)
-	if (len == (1 << 16))
-		return cpu_to_le16(NILFS_MAX_REC_LEN);
-	else if (len > (1 << 16))
-		BUG();
-#endif
-	return cpu_to_le16(len);
-}
+#define NILFS_MAX_REC_LEN		((1 << 16) - 1)
 
 /**
  * struct nilfs_finfo - file information
@@ -374,11 +344,10 @@ struct nilfs_finfo {
 	__le64 fi_cno;
 	__le32 fi_nblocks;
 	__le32 fi_ndatablk;
-	/* array of virtual block numbers */
 };
 
 /**
- * struct nilfs_binfo_v - information for the block to which a virtual block number is assigned
+ * struct nilfs_binfo_v - information on a data block (except DAT)
  * @bi_vblocknr: virtual block number
  * @bi_blkoff: block offset
  */
@@ -388,7 +357,7 @@ struct nilfs_binfo_v {
 };
 
 /**
- * struct nilfs_binfo_dat - information for the block which belongs to the DAT file
+ * struct nilfs_binfo_dat - information on a DAT node block
  * @bi_blkoff: block offset
  * @bi_level: level
  * @bi_pad: padding
@@ -454,7 +423,7 @@ struct nilfs_segment_summary {
 #define NILFS_SS_GC     0x0010  /* segment written for cleaner operation */
 
 /**
- * struct nilfs_btree_node - B-tree node
+ * struct nilfs_btree_node - header of B-tree node block
  * @bn_flags: flags
  * @bn_level: level
  * @bn_nchildren: number of children
@@ -476,6 +445,16 @@ struct nilfs_btree_node {
 #define NILFS_BTREE_LEVEL_MAX           14	/* Max level (exclusive) */
 
 /**
+ * struct nilfs_direct_node - header of built-in bmap array
+ * @dn_flags: flags
+ * @dn_pad: padding
+ */
+struct nilfs_direct_node {
+	__u8 dn_flags;
+	__u8 pad[7];
+};
+
+/**
  * struct nilfs_palloc_group_desc - block group descriptor
  * @pg_nfrees: number of free entries in block group
  */
@@ -574,40 +553,6 @@ NILFS_CHECKPOINT_FNS(INVALID, invalid)
 NILFS_CHECKPOINT_FNS(MINOR, minor)
 
 /**
- * struct nilfs_cpinfo - checkpoint information
- * @ci_flags: flags
- * @ci_pad: padding
- * @ci_cno: checkpoint number
- * @ci_create: creation timestamp
- * @ci_nblk_inc: number of blocks incremented by this checkpoint
- * @ci_inodes_count: inodes count
- * @ci_blocks_count: blocks count
- * @ci_next: next checkpoint number in snapshot list
- */
-struct nilfs_cpinfo {
-	__u32 ci_flags;
-	__u32 ci_pad;
-	__u64 ci_cno;
-	__u64 ci_create;
-	__u64 ci_nblk_inc;
-	__u64 ci_inodes_count;
-	__u64 ci_blocks_count;
-	__u64 ci_next;
-};
-
-#define NILFS_CPINFO_FNS(flag, name)					\
-static inline int							\
-nilfs_cpinfo_##name(const struct nilfs_cpinfo *cpinfo)			\
-{									\
-	return !!(cpinfo->ci_flags & (1UL << NILFS_CHECKPOINT_##flag));	\
-}
-
-NILFS_CPINFO_FNS(SNAPSHOT, snapshot)
-NILFS_CPINFO_FNS(INVALID, invalid)
-NILFS_CPINFO_FNS(MINOR, minor)
-
-
-/**
  * struct nilfs_cpfile_header - checkpoint file header
  * @ch_ncheckpoints: number of checkpoints
  * @ch_nsnapshots: number of snapshots
@@ -619,7 +564,7 @@ struct nilfs_cpfile_header {
 	struct nilfs_snapshot_list ch_snapshot_list;
 };
 
-#define NILFS_CPFILE_FIRST_CHECKPOINT_OFFSET	\
+#define NILFS_CPFILE_FIRST_CHECKPOINT_OFFSET				\
 	((sizeof(struct nilfs_cpfile_header) +				\
 	  sizeof(struct nilfs_checkpoint) - 1) /			\
 			sizeof(struct nilfs_checkpoint))
@@ -643,8 +588,6 @@ enum {
 	NILFS_SEGMENT_USAGE_ACTIVE,
 	NILFS_SEGMENT_USAGE_DIRTY,
 	NILFS_SEGMENT_USAGE_ERROR,
-
-	/* ... */
 };
 
 #define NILFS_SEGMENT_USAGE_FNS(flag, name)				\
@@ -699,236 +642,9 @@ struct nilfs_sufile_header {
 	/* ... */
 };
 
-#define NILFS_SUFILE_FIRST_SEGMENT_USAGE_OFFSET	\
+#define NILFS_SUFILE_FIRST_SEGMENT_USAGE_OFFSET				\
 	((sizeof(struct nilfs_sufile_header) +				\
 	  sizeof(struct nilfs_segment_usage) - 1) /			\
 			 sizeof(struct nilfs_segment_usage))
 
-/**
- * nilfs_suinfo - segment usage information
- * @sui_lastmod: timestamp of last modification
- * @sui_nblocks: number of written blocks in segment
- * @sui_flags: segment usage flags
- */
-struct nilfs_suinfo {
-	__u64 sui_lastmod;
-	__u32 sui_nblocks;
-	__u32 sui_flags;
-};
-
-#define NILFS_SUINFO_FNS(flag, name)					\
-static inline int							\
-nilfs_suinfo_##name(const struct nilfs_suinfo *si)			\
-{									\
-	return si->sui_flags & (1UL << NILFS_SEGMENT_USAGE_##flag);	\
-}
-
-NILFS_SUINFO_FNS(ACTIVE, active)
-NILFS_SUINFO_FNS(DIRTY, dirty)
-NILFS_SUINFO_FNS(ERROR, error)
-
-static inline int nilfs_suinfo_clean(const struct nilfs_suinfo *si)
-{
-	return !si->sui_flags;
-}
-
-/* ioctl */
-/**
- * nilfs_suinfo_update - segment usage information update
- * @sup_segnum: segment number
- * @sup_flags: flags for which fields are active in sup_sui
- * @sup_reserved: reserved necessary for alignment
- * @sup_sui: segment usage information
- */
-struct nilfs_suinfo_update {
-	__u64 sup_segnum;
-	__u32 sup_flags;
-	__u32 sup_reserved;
-	struct nilfs_suinfo sup_sui;
-};
-
-enum {
-	NILFS_SUINFO_UPDATE_LASTMOD,
-	NILFS_SUINFO_UPDATE_NBLOCKS,
-	NILFS_SUINFO_UPDATE_FLAGS,
-	__NR_NILFS_SUINFO_UPDATE_FIELDS,
-};
-
-#define NILFS_SUINFO_UPDATE_FNS(flag, name)				\
-static inline void							\
-nilfs_suinfo_update_set_##name(struct nilfs_suinfo_update *sup)		\
-{									\
-	sup->sup_flags |= 1UL << NILFS_SUINFO_UPDATE_##flag;		\
-}									\
-static inline void							\
-nilfs_suinfo_update_clear_##name(struct nilfs_suinfo_update *sup)	\
-{									\
-	sup->sup_flags &= ~(1UL << NILFS_SUINFO_UPDATE_##flag);		\
-}									\
-static inline int							\
-nilfs_suinfo_update_##name(const struct nilfs_suinfo_update *sup)	\
-{									\
-	return !!(sup->sup_flags & (1UL << NILFS_SUINFO_UPDATE_##flag));\
-}
-
-NILFS_SUINFO_UPDATE_FNS(LASTMOD, lastmod)
-NILFS_SUINFO_UPDATE_FNS(NBLOCKS, nblocks)
-NILFS_SUINFO_UPDATE_FNS(FLAGS, flags)
-
-enum {
-	NILFS_CHECKPOINT,
-	NILFS_SNAPSHOT,
-};
-
-/**
- * struct nilfs_cpmode - change checkpoint mode structure
- * @cm_cno: checkpoint number
- * @cm_mode: mode of checkpoint
- * @cm_pad: padding
- */
-struct nilfs_cpmode {
-	__u64 cm_cno;
-	__u32 cm_mode;
-	__u32 cm_pad;
-};
-
-/**
- * struct nilfs_argv - argument vector
- * @v_base: pointer on data array from userspace
- * @v_nmembs: number of members in data array
- * @v_size: size of data array in bytes
- * @v_flags: flags
- * @v_index: start number of target data items
- */
-struct nilfs_argv {
-	__u64 v_base;
-	__u32 v_nmembs;	/* number of members */
-	__u16 v_size;	/* size of members */
-	__u16 v_flags;
-	__u64 v_index;
-};
-
-/**
- * struct nilfs_period - period of checkpoint numbers
- * @p_start: start checkpoint number (inclusive)
- * @p_end: end checkpoint number (exclusive)
- */
-struct nilfs_period {
-	__u64 p_start;
-	__u64 p_end;
-};
-
-/**
- * struct nilfs_cpstat - checkpoint statistics
- * @cs_cno: checkpoint number
- * @cs_ncps: number of checkpoints
- * @cs_nsss: number of snapshots
- */
-struct nilfs_cpstat {
-	__u64 cs_cno;
-	__u64 cs_ncps;
-	__u64 cs_nsss;
-};
-
-/**
- * struct nilfs_sustat - segment usage statistics
- * @ss_nsegs: number of segments
- * @ss_ncleansegs: number of clean segments
- * @ss_ndirtysegs: number of dirty segments
- * @ss_ctime: creation time of the last segment
- * @ss_nongc_ctime: creation time of the last segment not for GC
- * @ss_prot_seq: least sequence number of segments which must not be reclaimed
- */
-struct nilfs_sustat {
-	__u64 ss_nsegs;
-	__u64 ss_ncleansegs;
-	__u64 ss_ndirtysegs;
-	__u64 ss_ctime;
-	__u64 ss_nongc_ctime;
-	__u64 ss_prot_seq;
-};
-
-/**
- * struct nilfs_vinfo - virtual block number information
- * @vi_vblocknr: virtual block number
- * @vi_start: start checkpoint number (inclusive)
- * @vi_end: end checkpoint number (exclusive)
- * @vi_blocknr: disk block number
- */
-struct nilfs_vinfo {
-	__u64 vi_vblocknr;
-	__u64 vi_start;
-	__u64 vi_end;
-	__u64 vi_blocknr;
-};
-
-/**
- * struct nilfs_vdesc - descriptor of virtual block number
- * @vd_ino: inode number
- * @vd_cno: checkpoint number
- * @vd_vblocknr: virtual block number
- * @vd_period: period of checkpoint numbers
- * @vd_blocknr: disk block number
- * @vd_offset: logical block offset inside a file
- * @vd_flags: flags (data or node block)
- * @vd_pad: padding
- */
-struct nilfs_vdesc {
-	__u64 vd_ino;
-	__u64 vd_cno;
-	__u64 vd_vblocknr;
-	struct nilfs_period vd_period;
-	__u64 vd_blocknr;
-	__u64 vd_offset;
-	__u32 vd_flags;
-	__u32 vd_pad;
-};
-
-/**
- * struct nilfs_bdesc - descriptor of disk block number
- * @bd_ino: inode number
- * @bd_oblocknr: disk block address (for skipping dead blocks)
- * @bd_blocknr: disk block address
- * @bd_offset: logical block offset inside a file
- * @bd_level: level in the b-tree organization
- * @bd_pad: padding
- */
-struct nilfs_bdesc {
-	__u64 bd_ino;
-	__u64 bd_oblocknr;
-	__u64 bd_blocknr;
-	__u64 bd_offset;
-	__u32 bd_level;
-	__u32 bd_pad;
-};
-
-#define NILFS_IOCTL_IDENT		'n'
-
-#define NILFS_IOCTL_CHANGE_CPMODE  \
-	_IOW(NILFS_IOCTL_IDENT, 0x80, struct nilfs_cpmode)
-#define NILFS_IOCTL_DELETE_CHECKPOINT  \
-	_IOW(NILFS_IOCTL_IDENT, 0x81, __u64)
-#define NILFS_IOCTL_GET_CPINFO  \
-	_IOR(NILFS_IOCTL_IDENT, 0x82, struct nilfs_argv)
-#define NILFS_IOCTL_GET_CPSTAT  \
-	_IOR(NILFS_IOCTL_IDENT, 0x83, struct nilfs_cpstat)
-#define NILFS_IOCTL_GET_SUINFO  \
-	_IOR(NILFS_IOCTL_IDENT, 0x84, struct nilfs_argv)
-#define NILFS_IOCTL_GET_SUSTAT  \
-	_IOR(NILFS_IOCTL_IDENT, 0x85, struct nilfs_sustat)
-#define NILFS_IOCTL_GET_VINFO  \
-	_IOWR(NILFS_IOCTL_IDENT, 0x86, struct nilfs_argv)
-#define NILFS_IOCTL_GET_BDESCS  \
-	_IOWR(NILFS_IOCTL_IDENT, 0x87, struct nilfs_argv)
-#define NILFS_IOCTL_CLEAN_SEGMENTS  \
-	_IOW(NILFS_IOCTL_IDENT, 0x88, struct nilfs_argv[5])
-#define NILFS_IOCTL_SYNC  \
-	_IOR(NILFS_IOCTL_IDENT, 0x8A, __u64)
-#define NILFS_IOCTL_RESIZE  \
-	_IOW(NILFS_IOCTL_IDENT, 0x8B, __u64)
-#define NILFS_IOCTL_SET_ALLOC_RANGE  \
-	_IOW(NILFS_IOCTL_IDENT, 0x8C, __u64[2])
-#define NILFS_IOCTL_SET_SUINFO  \
-	_IOW(NILFS_IOCTL_IDENT, 0x8D, struct nilfs_argv)
-
-#endif	/* _LINUX_NILFS_FS_H */
+#endif	/* _LINUX_NILFS2_ONDISK_H */
diff --git a/include/uapi/linux/rio_cm_cdev.h b/include/uapi/linux/rio_cm_cdev.h
new file mode 100644
index 000000000000..6edb900d318d
--- /dev/null
+++ b/include/uapi/linux/rio_cm_cdev.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright (c) 2015, Integrated Device Technology Inc.
+ * Copyright (c) 2015, Prodrive Technologies
+ * Copyright (c) 2015, RapidIO Trade Association
+ * All rights reserved.
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License(GPL) Version 2, or the BSD-3 Clause license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * 3. Neither the name of the copyright holder nor the names of its contributors
+ * may be used to endorse or promote products derived from this software without
+ * specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
+ * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR
+ * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RIO_CM_CDEV_H_
+#define _RIO_CM_CDEV_H_
+
+#include <linux/types.h>
+
+struct rio_cm_channel {
+	__u16 id;
+	__u16 remote_channel;
+	__u16 remote_destid;
+	__u8 mport_id;
+};
+
+struct rio_cm_msg {
+	__u16 ch_num;
+	__u16 size;
+	__u32 rxto;	/* receive timeout in mSec. 0 = blocking */
+	__u64 msg;
+};
+
+struct rio_cm_accept {
+	__u16 ch_num;
+	__u16 pad0;
+	__u32 wait_to;	/* accept timeout in mSec. 0 = blocking */
+};
+
+/* RapidIO Channelized Messaging Driver IOCTLs */
+#define RIO_CM_IOC_MAGIC	'c'
+
+#define RIO_CM_EP_GET_LIST_SIZE	_IOWR(RIO_CM_IOC_MAGIC, 1, __u32)
+#define RIO_CM_EP_GET_LIST	_IOWR(RIO_CM_IOC_MAGIC, 2, __u32)
+#define RIO_CM_CHAN_CREATE	_IOWR(RIO_CM_IOC_MAGIC, 3, __u16)
+#define RIO_CM_CHAN_CLOSE	_IOW(RIO_CM_IOC_MAGIC, 4, __u16)
+#define RIO_CM_CHAN_BIND	_IOW(RIO_CM_IOC_MAGIC, 5, struct rio_cm_channel)
+#define RIO_CM_CHAN_LISTEN	_IOW(RIO_CM_IOC_MAGIC, 6, __u16)
+#define RIO_CM_CHAN_ACCEPT	_IOWR(RIO_CM_IOC_MAGIC, 7, struct rio_cm_accept)
+#define RIO_CM_CHAN_CONNECT	_IOW(RIO_CM_IOC_MAGIC, 8, struct rio_cm_channel)
+#define RIO_CM_CHAN_SEND	_IOW(RIO_CM_IOC_MAGIC, 9, struct rio_cm_msg)
+#define RIO_CM_CHAN_RECEIVE	_IOWR(RIO_CM_IOC_MAGIC, 10, struct rio_cm_msg)
+#define RIO_CM_MPORT_GET_LIST	_IOWR(RIO_CM_IOC_MAGIC, 11, __u32)
+
+#endif /* _RIO_CM_CDEV_H_ */
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 0956373b56db..d2b12152e358 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -26,8 +26,6 @@
 #include <linux/types.h>
 #include <linux/compiler.h>
 
-struct completion;
-
 #define CTL_MAXNAME 10		/* how many path components do we allow in a
 				   call to sysctl?   In other words, what is
 				   the largest acceptable value for the nlen
diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h
index 8cd334f99ddc..cbae529b7ce0 100644
--- a/include/uapi/misc/cxl.h
+++ b/include/uapi/misc/cxl.h
@@ -93,6 +93,7 @@ enum cxl_event_type {
 	CXL_EVENT_AFU_INTERRUPT = 1,
 	CXL_EVENT_DATA_STORAGE  = 2,
 	CXL_EVENT_AFU_ERROR     = 3,
+	CXL_EVENT_AFU_DRIVER    = 4,
 };
 
 struct cxl_event_header {
@@ -124,12 +125,28 @@ struct cxl_event_afu_error {
 	__u64 error;
 };
 
+struct cxl_event_afu_driver_reserved {
+	/*
+	 * Defines the buffer passed to the cxl driver by the AFU driver.
+	 *
+	 * This is not ABI since the event header.size passed to the user for
+	 * existing events is set in the read call to sizeof(cxl_event_header)
+	 * + sizeof(whatever event is being dispatched) and the user is already
+	 * required to use a 4K buffer on the read call.
+	 *
+	 * Of course the contents will be ABI, but that's up the AFU driver.
+	 */
+	size_t data_size;
+	u8 data[];
+};
+
 struct cxl_event {
 	struct cxl_event_header header;
 	union {
 		struct cxl_event_afu_interrupt irq;
 		struct cxl_event_data_storage fault;
 		struct cxl_event_afu_error afu_error;
+		struct cxl_event_afu_driver_reserved afu_driver_event;
 	};
 };
 
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 3a2a79401789..7adeaae06961 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -235,9 +235,6 @@ int ipu_di_init_sync_panel(struct ipu_di *, struct ipu_di_signal_cfg *sig);
 struct dmfc_channel;
 int ipu_dmfc_enable_channel(struct dmfc_channel *dmfc);
 void ipu_dmfc_disable_channel(struct dmfc_channel *dmfc);
-int ipu_dmfc_alloc_bandwidth(struct dmfc_channel *dmfc,
-		unsigned long bandwidth_mbs, int burstsize);
-void ipu_dmfc_free_bandwidth(struct dmfc_channel *dmfc);
 void ipu_dmfc_config_wait4eot(struct dmfc_channel *dmfc, int width);
 struct dmfc_channel *ipu_dmfc_get(struct ipu_soc *ipu, int ipuv3_channel);
 void ipu_dmfc_put(struct dmfc_channel *dmfc);
diff --git a/include/video/omap-panel-data.h b/include/video/omap-panel-data.h
index 56830d1dc762..e7003ee6e063 100644
--- a/include/video/omap-panel-data.h
+++ b/include/video/omap-panel-data.h
@@ -27,59 +27,18 @@
 #ifndef __OMAP_PANEL_DATA_H
 #define __OMAP_PANEL_DATA_H
 
-#include <video/omapdss.h>
 #include <video/display_timing.h>
 
-struct omap_dss_device;
-
-/**
- * encoder_tfp410 platform data
- * @name: name for this display entity
- * @power_down_gpio: gpio number for PD pin (or -1 if not available)
- * @data_lines: number of DPI datalines
- */
-struct encoder_tfp410_platform_data {
-	const char *name;
-	const char *source;
-	int power_down_gpio;
-	int data_lines;
-};
-
-
-/**
- * connector_dvi platform data
- * @name: name for this display entity
- * @source: name of the display entity used as a video source
- * @i2c_bus_num: i2c bus number to be used for reading EDID
- */
-struct connector_dvi_platform_data {
-	const char *name;
-	const char *source;
-	int i2c_bus_num;
-};
-
-/**
- * connector_hdmi platform data
- * @name: name for this display entity
- * @source: name of the display entity used as a video source
- */
-struct connector_hdmi_platform_data {
-	const char *name;
-	const char *source;
-};
-
 /**
  * connector_atv platform data
  * @name: name for this display entity
  * @source: name of the display entity used as a video source
- * @connector_type: composite/svideo
  * @invert_polarity: invert signal polarity
  */
 struct connector_atv_platform_data {
 	const char *name;
 	const char *source;
 
-	enum omap_dss_venc_type connector_type;
 	bool invert_polarity;
 };
 
@@ -105,33 +64,6 @@ struct panel_dpi_platform_data {
 };
 
 /**
- * panel_dsicm platform data
- * @name: name for this display entity
- * @source: name of the display entity used as a video source
- * @reset_gpio: gpio to reset the panel (or -1)
- * @use_ext_te: use external TE GPIO
- * @ext_te_gpio: external TE GPIO
- * @ulps_timeout: time to wait before entering ULPS, 0 = disabled (ms)
- * @use_dsi_backlight: true if panel uses DSI command to control backlight
- * @pin_config: DSI pin configuration
- */
-struct panel_dsicm_platform_data {
-	const char *name;
-	const char *source;
-
-	int reset_gpio;
-
-	bool use_ext_te;
-	int ext_te_gpio;
-
-	unsigned ulps_timeout;
-
-	bool use_dsi_backlight;
-
-	struct omap_dsi_pin_config pin_config;
-};
-
-/**
  * panel_acx565akm platform data
  * @name: name for this display entity
  * @source: name of the display entity used as a video source
@@ -147,93 +79,4 @@ struct panel_acx565akm_platform_data {
 	int datapairs;
 };
 
-/**
- * panel_lb035q02 platform data
- * @name: name for this display entity
- * @source: name of the display entity used as a video source
- * @data_lines: number of DPI datalines
- * @backlight_gpio: gpio to enable/disable the backlight (or -1)
- * @enable_gpio: gpio to enable/disable the panel (or -1)
- */
-struct panel_lb035q02_platform_data {
-	const char *name;
-	const char *source;
-
-	int data_lines;
-
-	int backlight_gpio;
-	int enable_gpio;
-};
-
-/**
- * panel_sharp_ls037v7dw01 platform data
- * @name: name for this display entity
- * @source: name of the display entity used as a video source
- * @data_lines: number of DPI datalines
- * @resb_gpio: reset signal GPIO
- * @ini_gpio: power on control GPIO
- * @mo_gpio: selection for resolution(VGA/QVGA) GPIO
- * @lr_gpio: selection for horizontal scanning direction GPIO
- * @ud_gpio: selection for vertical scanning direction GPIO
- */
-struct panel_sharp_ls037v7dw01_platform_data {
-	const char *name;
-	const char *source;
-
-	int data_lines;
-
-	int resb_gpio;
-	int ini_gpio;
-	int mo_gpio;
-	int lr_gpio;
-	int ud_gpio;
-};
-
-/**
- * panel-tpo-td043mtea1 platform data
- * @name: name for this display entity
- * @source: name of the display entity used as a video source
- * @data_lines: number of DPI datalines
- * @nreset_gpio: reset signal
- */
-struct panel_tpo_td043mtea1_platform_data {
-	const char *name;
-	const char *source;
-
-	int data_lines;
-
-	int nreset_gpio;
-};
-
-/**
- * panel-nec-nl8048hl11 platform data
- * @name: name for this display entity
- * @source: name of the display entity used as a video source
- * @data_lines: number of DPI datalines
- * @res_gpio: reset signal
- * @qvga_gpio: selection for resolution(QVGA/WVGA)
- */
-struct panel_nec_nl8048hl11_platform_data {
-	const char *name;
-	const char *source;
-
-	int data_lines;
-
-	int res_gpio;
-	int qvga_gpio;
-};
-
-/**
- * panel-tpo-td028ttec1 platform data
- * @name: name for display entity
- * @source: name of the display entity used as a video source
- * @data_lines: number of DPI datalines
- */
-struct panel_tpo_td028ttec1_platform_data {
-	const char *name;
-	const char *source;
-
-	int data_lines;
-};
-
 #endif /* __OMAP_PANEL_DATA_H */
diff --git a/include/video/omapdss.h b/include/video/omapfb_dss.h
index 8e14ad7327c9..1d38901d599d 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapfb_dss.h
@@ -1,27 +1,20 @@
 /*
- * Copyright (C) 2008 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Copyright (C) 2016 Texas Instruments, Inc.
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
  */
 
-#ifndef __OMAP_OMAPDSS_H
-#define __OMAP_OMAPDSS_H
+#ifndef __OMAPFB_DSS_H
+#define __OMAPFB_DSS_H
 
 #include <linux/list.h>
 #include <linux/kobject.h>
 #include <linux/device.h>
 #include <linux/interrupt.h>
+#include <linux/platform_data/omapdss.h>
 
 #include <video/videomode.h>
 
@@ -167,11 +160,6 @@ enum omap_dss_display_state {
 	OMAP_DSS_DISPLAY_ACTIVE,
 };
 
-struct omap_dss_audio {
-	struct snd_aes_iec958 *iec;
-	struct snd_cea_861_aud_if *cea;
-};
-
 enum omap_dss_rotation_type {
 	OMAP_DSS_ROT_DMA	= 1 << 0,
 	OMAP_DSS_ROT_VRFB	= 1 << 1,
@@ -195,25 +183,6 @@ enum omap_overlay_caps {
 	OMAP_DSS_OVL_CAP_REPLICATION = 1 << 5,
 };
 
-enum omap_overlay_manager_caps {
-	OMAP_DSS_DUMMY_VALUE, /* add a dummy value to prevent compiler error */
-};
-
-enum omap_dss_clk_source {
-	OMAP_DSS_CLK_SRC_FCK = 0,		/* OMAP2/3: DSS1_ALWON_FCLK
-						 * OMAP4: DSS_FCLK */
-	OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC,	/* OMAP3: DSI1_PLL_FCLK
-						 * OMAP4: PLL1_CLK1 */
-	OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI,	/* OMAP3: DSI2_PLL_FCLK
-						 * OMAP4: PLL1_CLK2 */
-	OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC,	/* OMAP4: PLL2_CLK1 */
-	OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI,	/* OMAP4: PLL2_CLK2 */
-};
-
-enum omap_hdmi_flags {
-	OMAP_HDMI_SDA_SCL_EXTERNAL_PULLUP = 1 << 0,
-};
-
 enum omap_dss_output_id {
 	OMAP_DSS_OUTPUT_DPI	= 1 << 0,
 	OMAP_DSS_OUTPUT_DBI	= 1 << 1,
@@ -303,36 +272,6 @@ struct omap_dss_dsi_config {
 	enum omap_dss_dsi_trans_mode trans_mode;
 };
 
-enum omapdss_version {
-	OMAPDSS_VER_UNKNOWN = 0,
-	OMAPDSS_VER_OMAP24xx,
-	OMAPDSS_VER_OMAP34xx_ES1,	/* OMAP3430 ES1.0, 2.0 */
-	OMAPDSS_VER_OMAP34xx_ES3,	/* OMAP3430 ES3.0+ */
-	OMAPDSS_VER_OMAP3630,
-	OMAPDSS_VER_AM35xx,
-	OMAPDSS_VER_OMAP4430_ES1,	/* OMAP4430 ES1.0 */
-	OMAPDSS_VER_OMAP4430_ES2,	/* OMAP4430 ES2.0, 2.1, 2.2 */
-	OMAPDSS_VER_OMAP4,		/* All other OMAP4s */
-	OMAPDSS_VER_OMAP5,
-	OMAPDSS_VER_AM43xx,
-	OMAPDSS_VER_DRA7xx,
-};
-
-/* Board specific data */
-struct omap_dss_board_info {
-	int num_devices;
-	struct omap_dss_device **devices;
-	struct omap_dss_device *default_device;
-	const char *default_display_name;
-	int (*dsi_enable_pads)(int dsi_id, unsigned lane_mask);
-	void (*dsi_disable_pads)(int dsi_id, unsigned lane_mask);
-	int (*set_min_bus_tput)(struct device *dev, unsigned long r);
-	enum omapdss_version version;
-};
-
-/* Init with the board info */
-extern int omap_display_init(struct omap_dss_board_info *board_data);
-
 struct omap_video_timings {
 	/* Unit: pixels */
 	u16 x_res;
@@ -463,7 +402,6 @@ struct omap_overlay_manager {
 	/* static fields */
 	const char *name;
 	enum omap_channel id;
-	enum omap_overlay_manager_caps caps;
 	struct list_head overlays;
 	enum omap_display_type supported_displays;
 	enum omap_dss_output_id supported_outputs;
@@ -919,4 +857,4 @@ omapdss_of_get_first_endpoint(const struct device_node *parent);
 struct omap_dss_device *
 omapdss_of_find_source_for_first_ep(struct device_node *node);
 
-#endif
+#endif /* __OMAPFB_DSS_H */
diff --git a/init/Kconfig b/init/Kconfig
index 46f817abff0e..69886493ff1e 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -55,6 +55,7 @@ config CROSS_COMPILE
 
 config COMPILE_TEST
 	bool "Compile also drivers which will not load"
+	depends on !UML
 	default n
 	help
 	  Some drivers can be compiled on a different platform than they are
@@ -80,6 +81,7 @@ config LOCALVERSION
 config LOCALVERSION_AUTO
 	bool "Automatically append version information to the version string"
 	default y
+	depends on !COMPILE_TEST
 	help
 	  This will try to automatically determine if the current tree is a
 	  release tree by looking for git tags that belong to the current
@@ -952,7 +954,7 @@ menuconfig CGROUPS
 	  controls or device isolation.
 	  See
 		- Documentation/scheduler/sched-design-CFS.txt	(CFS)
-		- Documentation/cgroups/ (features for grouping, isolation
+		- Documentation/cgroup-v1/ (features for grouping, isolation
 					  and resource control)
 
 	  Say N if unsure.
@@ -1009,7 +1011,7 @@ config BLK_CGROUP
 	CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set
 	CONFIG_BLK_DEV_THROTTLING=y.
 
-	See Documentation/cgroups/blkio-controller.txt for more information.
+	See Documentation/cgroup-v1/blkio-controller.txt for more information.
 
 config DEBUG_BLK_CGROUP
 	bool "IO controller debugging"
@@ -2078,7 +2080,7 @@ config TRIM_UNUSED_KSYMS
 	  (especially when using LTO) for optimizing the code and reducing
 	  binary size.  This might have some security advantages as well.
 
-	  If unsure say N.
+	  If unsure, or if you need to build out-of-tree modules, say N.
 
 endif # MODULES
 
diff --git a/init/main.c b/init/main.c
index eae02aa03c9e..a8a58e2794a5 100644
--- a/init/main.c
+++ b/init/main.c
@@ -380,7 +380,7 @@ static void __init setup_command_line(char *command_line)
 
 static __initdata DECLARE_COMPLETION(kthreadd_done);
 
-static noinline void __init_refok rest_init(void)
+static noinline void __ref rest_init(void)
 {
 	int pid;
 
@@ -716,6 +716,12 @@ static bool __init_or_module initcall_blacklisted(initcall_t fn)
 	addr = (unsigned long) dereference_function_descriptor(fn);
 	sprint_symbol_no_offset(fn_name, addr);
 
+	/*
+	 * fn will be "function_name [module_name]" where [module_name] is not
+	 * displayed for built-in init functions.  Strip off the [module_name].
+	 */
+	strreplace(fn_name, ' ', '\0');
+
 	list_for_each_entry(entry, &blacklisted_initcalls, next) {
 		if (!strcmp(fn_name, entry->buf)) {
 			pr_debug("initcall %s blacklisted\n", fn_name);
diff --git a/ipc/msg.c b/ipc/msg.c
index 1471db9a7e61..c6521c205cb4 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -680,7 +680,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 		rcu_read_lock();
 		ipc_lock_object(&msq->q_perm);
 
-		ipc_rcu_putref(msq, ipc_rcu_free);
+		ipc_rcu_putref(msq, msg_rcu_free);
 		/* raced with RMID? */
 		if (!ipc_valid_object(&msq->q_perm)) {
 			err = -EIDRM;
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index ed81aafd2392..a521999de4f1 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -37,8 +37,6 @@ struct ipc_namespace init_ipc_ns = {
 #endif
 };
 
-atomic_t nr_ipc_ns = ATOMIC_INIT(1);
-
 struct msg_msgseg {
 	struct msg_msgseg *next;
 	/* the next part of the message follows immediately */
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 04cb07eb81f1..d87e6baa1323 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -43,7 +43,6 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 		kfree(ns);
 		return ERR_PTR(err);
 	}
-	atomic_inc(&nr_ipc_ns);
 
 	sem_init_ns(ns);
 	msg_init_ns(ns);
@@ -96,7 +95,6 @@ static void free_ipc_ns(struct ipc_namespace *ns)
 	sem_exit_ns(ns);
 	msg_exit_ns(ns);
 	shm_exit_ns(ns);
-	atomic_dec(&nr_ipc_ns);
 
 	put_user_ns(ns->user_ns);
 	ns_free_inum(&ns->ns);
diff --git a/ipc/sem.c b/ipc/sem.c
index ae72b3cddc8d..7c9d4f7683c0 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -438,7 +438,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns
 static inline void sem_lock_and_putref(struct sem_array *sma)
 {
 	sem_lock(sma, NULL, -1);
-	ipc_rcu_putref(sma, ipc_rcu_free);
+	ipc_rcu_putref(sma, sem_rcu_free);
 }
 
 static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
@@ -1381,7 +1381,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 			rcu_read_unlock();
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if (sem_io == NULL) {
-				ipc_rcu_putref(sma, ipc_rcu_free);
+				ipc_rcu_putref(sma, sem_rcu_free);
 				return -ENOMEM;
 			}
 
@@ -1415,20 +1415,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		if (nsems > SEMMSL_FAST) {
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if (sem_io == NULL) {
-				ipc_rcu_putref(sma, ipc_rcu_free);
+				ipc_rcu_putref(sma, sem_rcu_free);
 				return -ENOMEM;
 			}
 		}
 
 		if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) {
-			ipc_rcu_putref(sma, ipc_rcu_free);
+			ipc_rcu_putref(sma, sem_rcu_free);
 			err = -EFAULT;
 			goto out_free;
 		}
 
 		for (i = 0; i < nsems; i++) {
 			if (sem_io[i] > SEMVMX) {
-				ipc_rcu_putref(sma, ipc_rcu_free);
+				ipc_rcu_putref(sma, sem_rcu_free);
 				err = -ERANGE;
 				goto out_free;
 			}
@@ -1720,7 +1720,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	/* step 2: allocate new undo structure */
 	new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
 	if (!new) {
-		ipc_rcu_putref(sma, ipc_rcu_free);
+		ipc_rcu_putref(sma, sem_rcu_free);
 		return ERR_PTR(-ENOMEM);
 	}
 
diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config
new file mode 100644
index 000000000000..9f748ed7bea8
--- /dev/null
+++ b/kernel/configs/android-base.config
@@ -0,0 +1,152 @@
+#  KEEP ALPHABETICALLY SORTED
+# CONFIG_DEVKMEM is not set
+# CONFIG_DEVMEM is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_MODULES is not set
+# CONFIG_OABI_COMPAT is not set
+# CONFIG_SYSVIPC is not set
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_ARMV8_DEPRECATED=y
+CONFIG_ASHMEM=y
+CONFIG_AUDIT=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CP15_BARRIER_EMULATION=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_VERITY=y
+CONFIG_DM_VERITY_FEC=y
+CONFIG_EMBEDDED=y
+CONFIG_FB=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_INET=y
+CONFIG_INET_DIAG_DESTROY=y
+CONFIG_INET_ESP=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IPV6=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_IPV6_PRIVACY=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_NAT=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_NETMAP=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_NET=y
+CONFIG_NETDEVICES=y
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_TPROXY=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_KEY=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_NAT=y
+CONFIG_NO_HZ=y
+CONFIG_PACKET=y
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PREEMPT=y
+CONFIG_QUOTA=y
+CONFIG_RTC_CLASS=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SETEND_EMULATION=y
+CONFIG_STAGING=y
+CONFIG_SWP_EMULATION=y
+CONFIG_SYNC=y
+CONFIG_TUN=y
+CONFIG_UNIX=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_CONFIGFS=y
+CONFIG_USB_CONFIGFS_F_FS=y
+CONFIG_USB_CONFIGFS_F_MIDI=y
+CONFIG_USB_OTG_WAKELOCK=y
+CONFIG_XFRM_USER=y
diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config
new file mode 100644
index 000000000000..e3b953e966d2
--- /dev/null
+++ b/kernel/configs/android-recommended.config
@@ -0,0 +1,121 @@
+#  KEEP ALPHABETICALLY SORTED
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_NF_CONNTRACK_SIP is not set
+# CONFIG_PM_WAKELOCKS_GC is not set
+# CONFIG_VT is not set
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_COMPACTION=y
+CONFIG_DEBUG_RODATA=y
+CONFIG_DM_UEVENT=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_FUSE_FS=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HIDRAW=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_GREENASIA=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_HOLTEK=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_ROCCAT=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_UCLOGIC=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_GPIO=y
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_TABLET=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_ION=y
+CONFIG_JOYSTICK_XPAD=y
+CONFIG_JOYSTICK_XPAD_FF=y
+CONFIG_JOYSTICK_XPAD_LEDS=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KSM=y
+CONFIG_LOGIG940_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGITECH_FF=y
+CONFIG_MD=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_MSDOS_FS=y
+CONFIG_PANIC_TIMEOUT=5
+CONFIG_PANTHERLORD_FF=y
+CONFIG_PERF_EVENTS=y
+CONFIG_PM_DEBUG=y
+CONFIG_PM_RUNTIME=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+CONFIG_POWER_SUPPLY=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=y
+CONFIG_SCHEDSTATS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_SND=y
+CONFIG_SOUND=y
+CONFIG_SUSPEND_TIME=y
+CONFIG_TABLET_USB_ACECAD=y
+CONFIG_TABLET_USB_AIPTEK=y
+CONFIG_TABLET_USB_GTCO=y
+CONFIG_TABLET_USB_HANWANG=y
+CONFIG_TABLET_USB_KBTAB=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_TASK_XACCT=y
+CONFIG_TIMER_STATS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_UHID=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB_USBNET=y
+CONFIG_VFAT_FS=y
diff --git a/kernel/exit.c b/kernel/exit.c
index 84ae830234f8..2f974ae042a6 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -715,7 +715,7 @@ static void check_stack_usage(void)
 
 	spin_lock(&low_water_lock);
 	if (free < lowest_to_date) {
-		pr_warn("%s (%d) used greatest stack depth: %lu bytes left\n",
+		pr_info("%s (%d) used greatest stack depth: %lu bytes left\n",
 			current->comm, task_pid_nr(current), free);
 		lowest_to_date = free;
 	}
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 4384672d3245..980936a90ee6 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -48,7 +48,8 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
 
 	if (kexec_on_panic) {
 		/* Verify we have a valid entry point */
-		if ((entry < crashk_res.start) || (entry > crashk_res.end))
+		if ((entry < phys_to_boot_phys(crashk_res.start)) ||
+		    (entry > phys_to_boot_phys(crashk_res.end)))
 			return -EADDRNOTAVAIL;
 	}
 
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 56b3ed0927b0..561675589511 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -95,6 +95,12 @@ int kexec_should_crash(struct task_struct *p)
 	return 0;
 }
 
+int kexec_crash_loaded(void)
+{
+	return !!kexec_crash_image;
+}
+EXPORT_SYMBOL_GPL(kexec_crash_loaded);
+
 /*
  * When kexec transitions to the new kernel there is a one-to-one
  * mapping between physical and virtual addresses.  On processors
@@ -140,6 +146,7 @@ int kexec_should_crash(struct task_struct *p)
  * allocating pages whose destination address we do not care about.
  */
 #define KIMAGE_NO_DEST (-1UL)
+#define PAGE_COUNT(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT)
 
 static struct page *kimage_alloc_page(struct kimage *image,
 				       gfp_t gfp_mask,
@@ -147,8 +154,9 @@ static struct page *kimage_alloc_page(struct kimage *image,
 
 int sanity_check_segment_list(struct kimage *image)
 {
-	int result, i;
+	int i;
 	unsigned long nr_segments = image->nr_segments;
+	unsigned long total_pages = 0;
 
 	/*
 	 * Verify we have good destination addresses.  The caller is
@@ -163,16 +171,17 @@ int sanity_check_segment_list(struct kimage *image)
 	 * simply because addresses are changed to page size
 	 * granularity.
 	 */
-	result = -EADDRNOTAVAIL;
 	for (i = 0; i < nr_segments; i++) {
 		unsigned long mstart, mend;
 
 		mstart = image->segment[i].mem;
 		mend   = mstart + image->segment[i].memsz;
+		if (mstart > mend)
+			return -EADDRNOTAVAIL;
 		if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK))
-			return result;
+			return -EADDRNOTAVAIL;
 		if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT)
-			return result;
+			return -EADDRNOTAVAIL;
 	}
 
 	/* Verify our destination addresses do not overlap.
@@ -180,7 +189,6 @@ int sanity_check_segment_list(struct kimage *image)
 	 * through very weird things can happen with no
 	 * easy explanation as one segment stops on another.
 	 */
-	result = -EINVAL;
 	for (i = 0; i < nr_segments; i++) {
 		unsigned long mstart, mend;
 		unsigned long j;
@@ -194,7 +202,7 @@ int sanity_check_segment_list(struct kimage *image)
 			pend   = pstart + image->segment[j].memsz;
 			/* Do the segments overlap ? */
 			if ((mend > pstart) && (mstart < pend))
-				return result;
+				return -EINVAL;
 		}
 	}
 
@@ -203,12 +211,26 @@ int sanity_check_segment_list(struct kimage *image)
 	 * and it is easier to check up front than to be surprised
 	 * later on.
 	 */
-	result = -EINVAL;
 	for (i = 0; i < nr_segments; i++) {
 		if (image->segment[i].bufsz > image->segment[i].memsz)
-			return result;
+			return -EINVAL;
+	}
+
+	/*
+	 * Verify that no more than half of memory will be consumed. If the
+	 * request from userspace is too large, a large amount of time will be
+	 * wasted allocating pages, which can cause a soft lockup.
+	 */
+	for (i = 0; i < nr_segments; i++) {
+		if (PAGE_COUNT(image->segment[i].memsz) > totalram_pages / 2)
+			return -EINVAL;
+
+		total_pages += PAGE_COUNT(image->segment[i].memsz);
 	}
 
+	if (total_pages > totalram_pages / 2)
+		return -EINVAL;
+
 	/*
 	 * Verify we have good destination addresses.  Normally
 	 * the caller is responsible for making certain we don't
@@ -220,16 +242,15 @@ int sanity_check_segment_list(struct kimage *image)
 	 */
 
 	if (image->type == KEXEC_TYPE_CRASH) {
-		result = -EADDRNOTAVAIL;
 		for (i = 0; i < nr_segments; i++) {
 			unsigned long mstart, mend;
 
 			mstart = image->segment[i].mem;
 			mend = mstart + image->segment[i].memsz - 1;
 			/* Ensure we are within the crash kernel limits */
-			if ((mstart < crashk_res.start) ||
-			    (mend > crashk_res.end))
-				return result;
+			if ((mstart < phys_to_boot_phys(crashk_res.start)) ||
+			    (mend > phys_to_boot_phys(crashk_res.end)))
+				return -EADDRNOTAVAIL;
 		}
 	}
 
@@ -352,7 +373,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
 		pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order);
 		if (!pages)
 			break;
-		pfn   = page_to_pfn(pages);
+		pfn   = page_to_boot_pfn(pages);
 		epfn  = pfn + count;
 		addr  = pfn << PAGE_SHIFT;
 		eaddr = epfn << PAGE_SHIFT;
@@ -478,7 +499,7 @@ static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
 			return -ENOMEM;
 
 		ind_page = page_address(page);
-		*image->entry = virt_to_phys(ind_page) | IND_INDIRECTION;
+		*image->entry = virt_to_boot_phys(ind_page) | IND_INDIRECTION;
 		image->entry = ind_page;
 		image->last_entry = ind_page +
 				      ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1);
@@ -533,13 +554,13 @@ void kimage_terminate(struct kimage *image)
 #define for_each_kimage_entry(image, ptr, entry) \
 	for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \
 		ptr = (entry & IND_INDIRECTION) ? \
-			phys_to_virt((entry & PAGE_MASK)) : ptr + 1)
+			boot_phys_to_virt((entry & PAGE_MASK)) : ptr + 1)
 
 static void kimage_free_entry(kimage_entry_t entry)
 {
 	struct page *page;
 
-	page = pfn_to_page(entry >> PAGE_SHIFT);
+	page = boot_pfn_to_page(entry >> PAGE_SHIFT);
 	kimage_free_pages(page);
 }
 
@@ -633,7 +654,7 @@ static struct page *kimage_alloc_page(struct kimage *image,
 	 * have a match.
 	 */
 	list_for_each_entry(page, &image->dest_pages, lru) {
-		addr = page_to_pfn(page) << PAGE_SHIFT;
+		addr = page_to_boot_pfn(page) << PAGE_SHIFT;
 		if (addr == destination) {
 			list_del(&page->lru);
 			return page;
@@ -648,12 +669,12 @@ static struct page *kimage_alloc_page(struct kimage *image,
 		if (!page)
 			return NULL;
 		/* If the page cannot be used file it away */
-		if (page_to_pfn(page) >
+		if (page_to_boot_pfn(page) >
 				(KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) {
 			list_add(&page->lru, &image->unusable_pages);
 			continue;
 		}
-		addr = page_to_pfn(page) << PAGE_SHIFT;
+		addr = page_to_boot_pfn(page) << PAGE_SHIFT;
 
 		/* If it is the destination page we want use it */
 		if (addr == destination)
@@ -676,7 +697,7 @@ static struct page *kimage_alloc_page(struct kimage *image,
 			struct page *old_page;
 
 			old_addr = *old & PAGE_MASK;
-			old_page = pfn_to_page(old_addr >> PAGE_SHIFT);
+			old_page = boot_pfn_to_page(old_addr >> PAGE_SHIFT);
 			copy_highpage(page, old_page);
 			*old = addr | (*old & ~PAGE_MASK);
 
@@ -732,7 +753,7 @@ static int kimage_load_normal_segment(struct kimage *image,
 			result  = -ENOMEM;
 			goto out;
 		}
-		result = kimage_add_page(image, page_to_pfn(page)
+		result = kimage_add_page(image, page_to_boot_pfn(page)
 								<< PAGE_SHIFT);
 		if (result < 0)
 			goto out;
@@ -793,7 +814,7 @@ static int kimage_load_crash_segment(struct kimage *image,
 		char *ptr;
 		size_t uchunk, mchunk;
 
-		page = pfn_to_page(maddr >> PAGE_SHIFT);
+		page = boot_pfn_to_page(maddr >> PAGE_SHIFT);
 		if (!page) {
 			result  = -ENOMEM;
 			goto out;
@@ -921,7 +942,7 @@ void __weak crash_free_reserved_phys_range(unsigned long begin,
 	unsigned long addr;
 
 	for (addr = begin; addr < end; addr += PAGE_SIZE)
-		free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
+		free_reserved_page(boot_pfn_to_page(addr >> PAGE_SHIFT));
 }
 
 int crash_shrink_memory(unsigned long new_size)
@@ -1374,7 +1395,7 @@ void vmcoreinfo_append_str(const char *fmt, ...)
 void __weak arch_crash_save_vmcoreinfo(void)
 {}
 
-unsigned long __weak paddr_vmcoreinfo_note(void)
+phys_addr_t __weak paddr_vmcoreinfo_note(void)
 {
 	return __pa((unsigned long)(char *)&vmcoreinfo_note);
 }
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 152da4a48867..ee1bc1bb8feb 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -101,7 +101,7 @@ KERNEL_ATTR_RO(kexec_loaded);
 static ssize_t kexec_crash_loaded_show(struct kobject *kobj,
 				       struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", !!kexec_crash_image);
+	return sprintf(buf, "%d\n", kexec_crash_loaded());
 }
 KERNEL_ATTR_RO(kexec_crash_loaded);
 
@@ -128,8 +128,8 @@ KERNEL_ATTR_RW(kexec_crash_size);
 static ssize_t vmcoreinfo_show(struct kobject *kobj,
 			       struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%lx %x\n",
-		       paddr_vmcoreinfo_note(),
+	phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
+	return sprintf(buf, "%pa %x\n", &vmcore_base,
 		       (unsigned int)sizeof(vmcoreinfo_note));
 }
 KERNEL_ATTR_RO(vmcoreinfo);
diff --git a/kernel/module.c b/kernel/module.c
index 5f71aa63ed2a..a0f48b8b00da 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -60,6 +60,7 @@
 #include <linux/jump_label.h>
 #include <linux/pfn.h>
 #include <linux/bsearch.h>
+#include <linux/dynamic_debug.h>
 #include <uapi/linux/module.h>
 #include "module-internal.h"
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 8aa74497cc5a..ca8cea1ef673 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -108,6 +108,7 @@ void panic(const char *fmt, ...)
 	long i, i_next = 0;
 	int state = 0;
 	int old_cpu, this_cpu;
+	bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers;
 
 	/*
 	 * Disable local interrupts. This will prevent panic_smp_self_stop
@@ -160,7 +161,7 @@ void panic(const char *fmt, ...)
 	 *
 	 * Bypass the panic_cpu check and call __crash_kexec directly.
 	 */
-	if (!crash_kexec_post_notifiers) {
+	if (!_crash_kexec_post_notifiers) {
 		printk_nmi_flush_on_panic();
 		__crash_kexec(NULL);
 	}
@@ -191,7 +192,7 @@ void panic(const char *fmt, ...)
 	 *
 	 * Bypass the panic_cpu check and call __crash_kexec directly.
 	 */
-	if (crash_kexec_post_notifiers)
+	if (_crash_kexec_post_notifiers)
 		__crash_kexec(NULL);
 
 	bust_spinlocks(0);
@@ -571,13 +572,7 @@ EXPORT_SYMBOL(__stack_chk_fail);
 core_param(panic, panic_timeout, int, 0644);
 core_param(pause_on_oops, pause_on_oops, int, 0644);
 core_param(panic_on_warn, panic_on_warn, int, 0644);
-
-static int __init setup_crash_kexec_post_notifiers(char *s)
-{
-	crash_kexec_post_notifiers = true;
-	return 0;
-}
-early_param("crash_kexec_post_notifiers", setup_crash_kexec_post_notifiers);
+core_param(crash_kexec_post_notifiers, crash_kexec_post_notifiers, bool, 0644);
 
 static int __init oops_setup(char *s)
 {
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 7fd2838fa417..5d4505f30083 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -16,9 +16,11 @@
  */
 #include <linux/percpu.h>
 
-typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
+typedef __printf(2, 0) int (*printk_func_t)(int level, const char *fmt,
+					    va_list args);
 
-int __printf(1, 0) vprintk_default(const char *fmt, va_list args);
+__printf(2, 0)
+int vprintk_default(int level, const char *fmt, va_list args);
 
 #ifdef CONFIG_PRINTK_NMI
 
@@ -31,9 +33,10 @@ extern raw_spinlock_t logbuf_lock;
  * via per-CPU variable.
  */
 DECLARE_PER_CPU(printk_func_t, printk_func);
-static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
+__printf(2, 0)
+static inline int vprintk_func(int level, const char *fmt, va_list args)
 {
-	return this_cpu_read(printk_func)(fmt, args);
+	return this_cpu_read(printk_func)(level, fmt, args);
 }
 
 extern atomic_t nmi_message_lost;
@@ -44,9 +47,10 @@ static inline int get_nmi_message_lost(void)
 
 #else /* CONFIG_PRINTK_NMI */
 
-static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
+__printf(2, 0)
+static inline int vprintk_func(int level, const char *fmt, va_list args)
 {
-	return vprintk_default(fmt, args);
+	return vprintk_default(level, fmt, args);
 }
 
 static inline int get_nmi_message_lost(void)
diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c
index b69eb8a2876f..bc3eeb1ae6da 100644
--- a/kernel/printk/nmi.c
+++ b/kernel/printk/nmi.c
@@ -58,7 +58,7 @@ static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
  * one writer running. But the buffer might get flushed from another
  * CPU, so we need to be careful.
  */
-static int vprintk_nmi(const char *fmt, va_list args)
+static int vprintk_nmi(int level, const char *fmt, va_list args)
 {
 	struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
 	int add = 0;
@@ -79,7 +79,16 @@ again:
 	if (!len)
 		smp_rmb();
 
-	add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args);
+	if (level != LOGLEVEL_DEFAULT) {
+		add = snprintf(s->buffer + len, sizeof(s->buffer) - len,
+				KERN_SOH "%c", '0' + level);
+		add += vsnprintf(s->buffer + len + add,
+				 sizeof(s->buffer) - len - add,
+				 fmt, args);
+	} else {
+		add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len,
+				fmt, args);
+	}
 
 	/*
 	 * Do it once again if the buffer has been flushed in the meantime.
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index d4de33934dac..a5ef95ca18c9 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -26,7 +26,6 @@
 #include <linux/nmi.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-#include <linux/interrupt.h>			/* For in_interrupt() */
 #include <linux/delay.h>
 #include <linux/smp.h>
 #include <linux/security.h>
@@ -48,7 +47,7 @@
 #include <linux/uio.h>
 
 #include <asm/uaccess.h>
-#include <asm-generic/sections.h>
+#include <asm/sections.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/printk.h>
@@ -86,6 +85,111 @@ static struct lockdep_map console_lock_dep_map = {
 };
 #endif
 
+enum devkmsg_log_bits {
+	__DEVKMSG_LOG_BIT_ON = 0,
+	__DEVKMSG_LOG_BIT_OFF,
+	__DEVKMSG_LOG_BIT_LOCK,
+};
+
+enum devkmsg_log_masks {
+	DEVKMSG_LOG_MASK_ON             = BIT(__DEVKMSG_LOG_BIT_ON),
+	DEVKMSG_LOG_MASK_OFF            = BIT(__DEVKMSG_LOG_BIT_OFF),
+	DEVKMSG_LOG_MASK_LOCK           = BIT(__DEVKMSG_LOG_BIT_LOCK),
+};
+
+/* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */
+#define DEVKMSG_LOG_MASK_DEFAULT	0
+
+static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT;
+
+static int __control_devkmsg(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strncmp(str, "on", 2)) {
+		devkmsg_log = DEVKMSG_LOG_MASK_ON;
+		return 2;
+	} else if (!strncmp(str, "off", 3)) {
+		devkmsg_log = DEVKMSG_LOG_MASK_OFF;
+		return 3;
+	} else if (!strncmp(str, "ratelimit", 9)) {
+		devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT;
+		return 9;
+	}
+	return -EINVAL;
+}
+
+static int __init control_devkmsg(char *str)
+{
+	if (__control_devkmsg(str) < 0)
+		return 1;
+
+	/*
+	 * Set sysctl string accordingly:
+	 */
+	if (devkmsg_log == DEVKMSG_LOG_MASK_ON) {
+		memset(devkmsg_log_str, 0, DEVKMSG_STR_MAX_SIZE);
+		strncpy(devkmsg_log_str, "on", 2);
+	} else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) {
+		memset(devkmsg_log_str, 0, DEVKMSG_STR_MAX_SIZE);
+		strncpy(devkmsg_log_str, "off", 3);
+	}
+	/* else "ratelimit" which is set by default. */
+
+	/*
+	 * Sysctl cannot change it anymore. The kernel command line setting of
+	 * this parameter is to force the setting to be permanent throughout the
+	 * runtime of the system. This is a precation measure against userspace
+	 * trying to be a smarta** and attempting to change it up on us.
+	 */
+	devkmsg_log |= DEVKMSG_LOG_MASK_LOCK;
+
+	return 0;
+}
+__setup("printk.devkmsg=", control_devkmsg);
+
+char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit";
+
+int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
+			      void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	char old_str[DEVKMSG_STR_MAX_SIZE];
+	unsigned int old;
+	int err;
+
+	if (write) {
+		if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK)
+			return -EINVAL;
+
+		old = devkmsg_log;
+		strncpy(old_str, devkmsg_log_str, DEVKMSG_STR_MAX_SIZE);
+	}
+
+	err = proc_dostring(table, write, buffer, lenp, ppos);
+	if (err)
+		return err;
+
+	if (write) {
+		err = __control_devkmsg(devkmsg_log_str);
+
+		/*
+		 * Do not accept an unknown string OR a known string with
+		 * trailing crap...
+		 */
+		if (err < 0 || (err + 1 != *lenp)) {
+
+			/* ... and restore old setting. */
+			devkmsg_log = old;
+			strncpy(devkmsg_log_str, old_str, DEVKMSG_STR_MAX_SIZE);
+
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Number of registered extended console drivers.
  *
@@ -614,6 +718,7 @@ struct devkmsg_user {
 	u64 seq;
 	u32 idx;
 	enum log_flags prev;
+	struct ratelimit_state rs;
 	struct mutex lock;
 	char buf[CONSOLE_EXT_LOG_MAX];
 };
@@ -623,11 +728,24 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
 	char *buf, *line;
 	int level = default_message_loglevel;
 	int facility = 1;	/* LOG_USER */
+	struct file *file = iocb->ki_filp;
+	struct devkmsg_user *user = file->private_data;
 	size_t len = iov_iter_count(from);
 	ssize_t ret = len;
 
-	if (len > LOG_LINE_MAX)
+	if (!user || len > LOG_LINE_MAX)
 		return -EINVAL;
+
+	/* Ignore when user logging is disabled. */
+	if (devkmsg_log & DEVKMSG_LOG_MASK_OFF)
+		return len;
+
+	/* Ratelimit when not explicitly enabled. */
+	if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) {
+		if (!___ratelimit(&user->rs, current->comm))
+			return ret;
+	}
+
 	buf = kmalloc(len+1, GFP_KERNEL);
 	if (buf == NULL)
 		return -ENOMEM;
@@ -800,19 +918,24 @@ static int devkmsg_open(struct inode *inode, struct file *file)
 	struct devkmsg_user *user;
 	int err;
 
-	/* write-only does not need any file context */
-	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
-		return 0;
+	if (devkmsg_log & DEVKMSG_LOG_MASK_OFF)
+		return -EPERM;
 
-	err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
-				       SYSLOG_FROM_READER);
-	if (err)
-		return err;
+	/* write-only does not need any file context */
+	if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
+		err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
+					       SYSLOG_FROM_READER);
+		if (err)
+			return err;
+	}
 
 	user = kmalloc(sizeof(struct devkmsg_user), GFP_KERNEL);
 	if (!user)
 		return -ENOMEM;
 
+	ratelimit_default_init(&user->rs);
+	ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE);
+
 	mutex_init(&user->lock);
 
 	raw_spin_lock_irq(&logbuf_lock);
@@ -831,6 +954,8 @@ static int devkmsg_release(struct inode *inode, struct file *file)
 	if (!user)
 		return 0;
 
+	ratelimit_state_exit(&user->rs);
+
 	mutex_destroy(&user->lock);
 	kfree(user);
 	return 0;
@@ -986,6 +1111,11 @@ module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(ignore_loglevel,
 		 "ignore loglevel setting (prints all kernel messages to the console)");
 
+static bool suppress_message_printing(int level)
+{
+	return (level >= console_loglevel && !ignore_loglevel);
+}
+
 #ifdef CONFIG_BOOT_PRINTK_DELAY
 
 static int boot_delay; /* msecs delay after each printk during bootup */
@@ -1015,7 +1145,7 @@ static void boot_delay_msec(int level)
 	unsigned long timeout;
 
 	if ((boot_delay == 0 || system_state != SYSTEM_BOOTING)
-		|| (level >= console_loglevel && !ignore_loglevel)) {
+		|| suppress_message_printing(level)) {
 		return;
 	}
 
@@ -1439,8 +1569,6 @@ static void call_console_drivers(int level,
 
 	trace_console(text, len);
 
-	if (level >= console_loglevel && !ignore_loglevel)
-		return;
 	if (!console_drivers)
 		return;
 
@@ -1802,7 +1930,28 @@ asmlinkage int printk_emit(int facility, int level,
 }
 EXPORT_SYMBOL(printk_emit);
 
-int vprintk_default(const char *fmt, va_list args)
+#ifdef CONFIG_PRINTK
+#define define_pr_level(func, loglevel)				\
+asmlinkage __visible void func(const char *fmt, ...)		\
+{								\
+	va_list args;						\
+								\
+	va_start(args, fmt);					\
+	vprintk_default(loglevel, fmt, args);			\
+	va_end(args);						\
+}								\
+EXPORT_SYMBOL(func)
+
+define_pr_level(__pr_emerg, LOGLEVEL_EMERG);
+define_pr_level(__pr_alert, LOGLEVEL_ALERT);
+define_pr_level(__pr_crit, LOGLEVEL_CRIT);
+define_pr_level(__pr_err, LOGLEVEL_ERR);
+define_pr_level(__pr_warn, LOGLEVEL_WARNING);
+define_pr_level(__pr_notice, LOGLEVEL_NOTICE);
+define_pr_level(__pr_info, LOGLEVEL_INFO);
+#endif
+
+int vprintk_default(int level, const char *fmt, va_list args)
 {
 	int r;
 
@@ -1812,7 +1961,7 @@ int vprintk_default(const char *fmt, va_list args)
 		return r;
 	}
 #endif
-	r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
+	r = vprintk_emit(0, level, NULL, 0, fmt, args);
 
 	return r;
 }
@@ -1845,7 +1994,7 @@ asmlinkage __visible int printk(const char *fmt, ...)
 	int r;
 
 	va_start(args, fmt);
-	r = vprintk_func(fmt, args);
+	r = vprintk_func(LOGLEVEL_DEFAULT, fmt, args);
 	va_end(args);
 
 	return r;
@@ -1888,6 +2037,7 @@ static void call_console_drivers(int level,
 static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev,
 			     bool syslog, char *buf, size_t size) { return 0; }
 static size_t cont_print_text(char *text, size_t size) { return 0; }
+static bool suppress_message_printing(int level) { return false; }
 
 /* Still needs to be defined for users */
 DEFINE_PER_CPU(printk_func_t, printk_func);
@@ -2167,6 +2317,13 @@ static void console_cont_flush(char *text, size_t size)
 	if (!cont.len)
 		goto out;
 
+	if (suppress_message_printing(cont.level)) {
+		cont.cons = cont.len;
+		if (cont.flushed)
+			cont.len = 0;
+		goto out;
+	}
+
 	/*
 	 * We still queue earlier records, likely because the console was
 	 * busy. The earlier ones need to be printed before this one, we
@@ -2270,10 +2427,13 @@ skip:
 			break;
 
 		msg = log_from_idx(console_idx);
-		if (msg->flags & LOG_NOCONS) {
+		level = msg->level;
+		if ((msg->flags & LOG_NOCONS) ||
+				suppress_message_printing(level)) {
 			/*
 			 * Skip record we have buffered and already printed
-			 * directly to the console when we received it.
+			 * directly to the console when we received it, and
+			 * record that has level above the console loglevel.
 			 */
 			console_idx = log_next(console_idx);
 			console_seq++;
@@ -2287,7 +2447,6 @@ skip:
 			goto skip;
 		}
 
-		level = msg->level;
 		len += msg_print_text(msg, console_prev, false,
 				      text + len, sizeof(text) - len);
 		if (nr_ext_console_drivers) {
diff --git a/kernel/relay.c b/kernel/relay.c
index 04d7cf3ef8cf..d797502140b9 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -451,6 +451,13 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
 		if (!dentry)
 			goto free_buf;
 		relay_set_buf_dentry(buf, dentry);
+	} else {
+		/* Only retrieve global info, nothing more, nothing less */
+		dentry = chan->cb->create_buf_file(NULL, NULL,
+						   S_IRUSR, buf,
+						   &chan->is_global);
+		if (WARN_ON(dentry))
+			goto free_buf;
 	}
 
  	buf->cpu = cpu;
@@ -562,6 +569,10 @@ static int relay_hotcpu_callback(struct notifier_block *nb,
  *	attributes specified.  The created channel buffer files
  *	will be named base_filename0...base_filenameN-1.  File
  *	permissions will be %S_IRUSR.
+ *
+ *	If opening a buffer (@parent = NULL) that you later wish to register
+ *	in a filesystem, call relay_late_setup_files() once the @parent dentry
+ *	is available.
  */
 struct rchan *relay_open(const char *base_filename,
 			 struct dentry *parent,
@@ -640,8 +651,12 @@ static void __relay_set_buf_dentry(void *info)
  *
  *	Returns 0 if successful, non-zero otherwise.
  *
- *	Use to setup files for a previously buffer-only channel.
- *	Useful to do early tracing in kernel, before VFS is up, for example.
+ *	Use to setup files for a previously buffer-only channel created
+ *	by relay_open() with a NULL parent dentry.
+ *
+ *	For example, this is useful for perfomring early tracing in kernel,
+ *	before VFS is up and then exposing the early results once the dentry
+ *	is available.
  */
 int relay_late_setup_files(struct rchan *chan,
 			   const char *base_filename,
@@ -666,6 +681,20 @@ int relay_late_setup_files(struct rchan *chan,
 	}
 	chan->has_base_filename = 1;
 	chan->parent = parent;
+
+	if (chan->is_global) {
+		err = -EINVAL;
+		if (!WARN_ON_ONCE(!chan->buf[0])) {
+			dentry = relay_create_buf_file(chan, chan->buf[0], 0);
+			if (dentry && !WARN_ON_ONCE(!chan->is_global)) {
+				relay_set_buf_dentry(chan->buf[0], dentry);
+				err = 0;
+			}
+		}
+		mutex_unlock(&relay_channels_mutex);
+		return err;
+	}
+
 	curr_cpu = get_cpu();
 	/*
 	 * The CPU hotplug notifier ran before us and created buffers with
@@ -706,6 +735,7 @@ int relay_late_setup_files(struct rchan *chan,
 
 	return err;
 }
+EXPORT_SYMBOL_GPL(relay_late_setup_files);
 
 /**
  *	relay_switch_subbuf - switch to a new sub-buffer
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index a467e6c28a3b..4a1ca5f6da7e 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -21,6 +21,7 @@
 #include <linux/smpboot.h>
 #include <linux/atomic.h>
 #include <linux/lglock.h>
+#include <linux/nmi.h>
 
 /*
  * Structure to determine completion condition and record errors.  May
@@ -209,6 +210,13 @@ static int multi_cpu_stop(void *data)
 				break;
 			}
 			ack_state(msdata);
+		} else if (curstate > MULTI_STOP_PREPARE) {
+			/*
+			 * At this stage all other CPUs we depend on must spin
+			 * in the same loop. Any reason for hard-lockup should
+			 * be detected and reported on their side.
+			 */
+			touch_nmi_watchdog();
 		}
 	} while (curstate != MULTI_STOP_EXIT);
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 53954631a4e1..b43d0b27c1fe 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -814,6 +814,13 @@ static struct ctl_table kern_table[] = {
 		.extra2		= &ten_thousand,
 	},
 	{
+		.procname	= "printk_devkmsg",
+		.data		= devkmsg_log_str,
+		.maxlen		= DEVKMSG_STR_MAX_SIZE,
+		.mode		= 0644,
+		.proc_handler	= devkmsg_sysctl_set_loglvl,
+	},
+	{
 		.procname	= "dmesg_restrict",
 		.data		= &dmesg_restrict,
 		.maxlen		= sizeof(int),
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 6ab4842b00e8..d513051fcca2 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -29,7 +29,7 @@ task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
 	struct callback_head *head;
 
 	do {
-		head = ACCESS_ONCE(task->task_works);
+		head = READ_ONCE(task->task_works);
 		if (unlikely(head == &work_exited))
 			return -ESRCH;
 		work->next = head;
@@ -57,6 +57,9 @@ task_work_cancel(struct task_struct *task, task_work_func_t func)
 	struct callback_head **pprev = &task->task_works;
 	struct callback_head *work;
 	unsigned long flags;
+
+	if (likely(!task->task_works))
+		return NULL;
 	/*
 	 * If cmpxchg() fails we continue without updating pprev.
 	 * Either we raced with task_work_add() which added the
@@ -64,8 +67,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func)
 	 * we raced with task_work_run(), *pprev == NULL/exited.
 	 */
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
-	while ((work = ACCESS_ONCE(*pprev))) {
-		smp_read_barrier_depends();
+	while ((work = lockless_dereference(*pprev))) {
 		if (work->func != func)
 			pprev = &work->next;
 		else if (cmpxchg(pprev, work, work->next) == work)
@@ -95,7 +97,7 @@ void task_work_run(void)
 		 * work_exited unless the list is empty.
 		 */
 		do {
-			work = ACCESS_ONCE(task->task_works);
+			work = READ_ONCE(task->task_works);
 			head = !work && (task->flags & PF_EXITING) ?
 				&work_exited : NULL;
 		} while (cmpxchg(&task->task_works, work, head) != work);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index f07842e2d69f..2307d7c89dac 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -709,6 +709,8 @@ config KCOV
 	bool "Code coverage for fuzzing"
 	depends on ARCH_HAS_KCOV
 	select DEBUG_FS
+	select GCC_PLUGINS if !COMPILE_TEST
+	select GCC_PLUGIN_SANCOV if !COMPILE_TEST
 	help
 	  KCOV exposes kernel code coverage information in a form suitable
 	  for coverage-guided fuzzing (randomized testing).
@@ -719,6 +721,17 @@ config KCOV
 
 	  For more details, see Documentation/kcov.txt.
 
+config KCOV_INSTRUMENT_ALL
+	bool "Instrument all code by default"
+	depends on KCOV
+	default y if KCOV
+	help
+	  If you are doing generic system call fuzzing (like e.g. syzkaller),
+	  then you will want to instrument the whole kernel and you should
+	  say y here. If you are doing more targeted fuzzing (like e.g.
+	  filesystem fuzzing with AFL) then you will want to enable coverage
+	  for more specific subsets of files, and should say n here.
+
 config DEBUG_SHIRQ
 	bool "Debug shared IRQ handlers"
 	depends on DEBUG_KERNEL
diff --git a/lib/crc32.c b/lib/crc32.c
index 9a907d489d95..7fbd1a112b9d 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -979,7 +979,6 @@ static int __init crc32c_test(void)
 	int i;
 	int errors = 0;
 	int bytes = 0;
-	struct timespec start, stop;
 	u64 nsec;
 	unsigned long flags;
 
@@ -999,20 +998,17 @@ static int __init crc32c_test(void)
 	local_irq_save(flags);
 	local_irq_disable();
 
-	getnstimeofday(&start);
+	nsec = ktime_get_ns();
 	for (i = 0; i < 100; i++) {
 		if (test[i].crc32c_le != __crc32c_le(test[i].crc, test_buf +
 		    test[i].start, test[i].length))
 			errors++;
 	}
-	getnstimeofday(&stop);
+	nsec = ktime_get_ns() - nsec;
 
 	local_irq_restore(flags);
 	local_irq_enable();
 
-	nsec = stop.tv_nsec - start.tv_nsec +
-		1000000000 * (stop.tv_sec - start.tv_sec);
-
 	pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS);
 
 	if (errors)
@@ -1065,7 +1061,6 @@ static int __init crc32_test(void)
 	int i;
 	int errors = 0;
 	int bytes = 0;
-	struct timespec start, stop;
 	u64 nsec;
 	unsigned long flags;
 
@@ -1088,7 +1083,7 @@ static int __init crc32_test(void)
 	local_irq_save(flags);
 	local_irq_disable();
 
-	getnstimeofday(&start);
+	nsec = ktime_get_ns();
 	for (i = 0; i < 100; i++) {
 		if (test[i].crc_le != crc32_le(test[i].crc, test_buf +
 		    test[i].start, test[i].length))
@@ -1098,14 +1093,11 @@ static int __init crc32_test(void)
 		    test[i].start, test[i].length))
 			errors++;
 	}
-	getnstimeofday(&stop);
+	nsec = ktime_get_ns() - nsec;
 
 	local_irq_restore(flags);
 	local_irq_enable();
 
-	nsec = stop.tv_nsec - start.tv_nsec +
-		1000000000 * (stop.tv_sec - start.tv_sec);
-
 	pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n",
 		 CRC_LE_BITS, CRC_BE_BITS);
 
diff --git a/lib/earlycpio.c b/lib/earlycpio.c
index 3eb3e4722b8e..db283ba4d2c1 100644
--- a/lib/earlycpio.c
+++ b/lib/earlycpio.c
@@ -125,7 +125,10 @@ struct cpio_data find_cpio_data(const char *path, void *data,
 		if ((ch[C_MODE] & 0170000) == 0100000 &&
 		    ch[C_NAMESIZE] >= mypathsize &&
 		    !memcmp(p, path, mypathsize)) {
-			*nextoff = (long)nptr - (long)data;
+
+			if (nextoff)
+				*nextoff = (long)nptr - (long)data;
+
 			if (ch[C_NAMESIZE] - mypathsize >= MAX_CPIO_FILE_NAME) {
 				pr_warn(
 				"File %s exceeding MAX_CPIO_FILE_NAME [%d]\n",
diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c
index c27e269210c4..a816f3a80625 100644
--- a/lib/iommu-helper.c
+++ b/lib/iommu-helper.c
@@ -29,8 +29,7 @@ again:
 	index = bitmap_find_next_zero_area(map, size, start, nr, align_mask);
 	if (index < size) {
 		if (iommu_is_span_boundary(index, nr, shift, boundary_size)) {
-			/* we could do more effectively */
-			start = index + 1;
+			start = ALIGN(shift + index, boundary_size) - shift;
 			goto again;
 		}
 		bitmap_set(map, index, nr);
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index c6272ae2015e..5a0f75a3bf01 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -363,6 +363,9 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 		lzeros = 0;
 	}
 
+	miter.consumed = lzeros;
+	sg_miter_stop(&miter);
+
 	nbytes -= lzeros;
 	nbits = nbytes * 8;
 	if (nbits > MAX_EXTERN_MPI_BITS) {
@@ -390,7 +393,10 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 	z = BYTES_PER_MPI_LIMB - nbytes % BYTES_PER_MPI_LIMB;
 	z %= BYTES_PER_MPI_LIMB;
 
-	for (;;) {
+	while (sg_miter_next(&miter)) {
+		buff = miter.addr;
+		len = miter.length;
+
 		for (x = 0; x < len; x++) {
 			a <<= 8;
 			a |= *buff++;
@@ -400,12 +406,6 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 			}
 		}
 		z += x;
-
-		if (!sg_miter_next(&miter))
-			break;
-
-		buff = miter.addr;
-		len = miter.length;
 	}
 
 	return val;
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 61b8fb529cef..1b7bf7314141 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -277,10 +277,11 @@ radix_tree_node_alloc(struct radix_tree_root *root)
 
 		/*
 		 * Even if the caller has preloaded, try to allocate from the
-		 * cache first for the new node to get accounted.
+		 * cache first for the new node to get accounted to the memory
+		 * cgroup.
 		 */
 		ret = kmem_cache_alloc(radix_tree_node_cachep,
-				       gfp_mask | __GFP_ACCOUNT | __GFP_NOWARN);
+				       gfp_mask | __GFP_NOWARN);
 		if (ret)
 			goto out;
 
@@ -303,8 +304,7 @@ radix_tree_node_alloc(struct radix_tree_root *root)
 		kmemleak_update_trace(ret);
 		goto out;
 	}
-	ret = kmem_cache_alloc(radix_tree_node_cachep,
-			       gfp_mask | __GFP_ACCOUNT);
+	ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
 out:
 	BUG_ON(radix_tree_is_internal_node(ret));
 	return ret;
@@ -351,6 +351,12 @@ static int __radix_tree_preload(gfp_t gfp_mask, int nr)
 	struct radix_tree_node *node;
 	int ret = -ENOMEM;
 
+	/*
+	 * Nodes preloaded by one cgroup can be be used by another cgroup, so
+	 * they should never be accounted to any particular memory cgroup.
+	 */
+	gfp_mask &= ~__GFP_ACCOUNT;
+
 	preempt_disable();
 	rtp = this_cpu_ptr(&radix_tree_preloads);
 	while (rtp->nr < nr) {
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index 2c5de86460c5..08f8043cac61 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -46,12 +46,14 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 		rs->begin = jiffies;
 
 	if (time_is_before_jiffies(rs->begin + rs->interval)) {
-		if (rs->missed)
-			printk(KERN_WARNING "%s: %d callbacks suppressed\n",
-				func, rs->missed);
+		if (rs->missed) {
+			if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) {
+				pr_warn("%s: %d callbacks suppressed\n", func, rs->missed);
+				rs->missed = 0;
+			}
+		}
 		rs->begin   = jiffies;
 		rs->printed = 0;
-		rs->missed  = 0;
 	}
 	if (rs->burst && rs->burst > rs->printed) {
 		rs->printed++;
diff --git a/lib/ubsan.c b/lib/ubsan.c
index 8799ae5e2e42..fb0409df1bcf 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -308,7 +308,7 @@ static void handle_object_size_mismatch(struct type_mismatch_data *data,
 		return;
 
 	ubsan_prologue(&data->location, &flags);
-	pr_err("%s address %pk with insufficient space\n",
+	pr_err("%s address %p with insufficient space\n",
 		type_check_kinds[data->type_check_kind],
 		(void *) ptr);
 	pr_err("for an object of type %s\n", data->type->type_name);
diff --git a/mm/gup.c b/mm/gup.c
index 547741f5f7a7..96b2b2fd0fbd 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -723,6 +723,7 @@ retry:
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(fixup_user_fault);
 
 static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 						struct mm_struct *mm,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f904246a8fd5..ef968306fd5b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2216,6 +2216,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 		 * and reducing the surplus.
 		 */
 		spin_unlock(&hugetlb_lock);
+
+		/* yield cpu to avoid soft lockup */
+		cond_resched();
+
 		if (hstate_is_gigantic(h))
 			ret = alloc_fresh_gigantic_page(h, nodes_allowed);
 		else
@@ -4306,7 +4310,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
 	}
-	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
+	BUG_ON(pte && pte_present(*pte) && !pte_huge(*pte));
 
 	return pte;
 }
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index b6f99e81bfeb..88af13c00d3c 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -442,11 +442,6 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object)
 	kasan_poison_shadow(object,
 			round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE),
 			KASAN_KMALLOC_REDZONE);
-	if (cache->flags & SLAB_KASAN) {
-		struct kasan_alloc_meta *alloc_info =
-			get_alloc_info(cache, object);
-		alloc_info->state = KASAN_STATE_INIT;
-	}
 }
 
 static inline int in_irqentry_text(unsigned long ptr)
@@ -510,6 +505,17 @@ struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
 	return (void *)object + cache->kasan_info.free_meta_offset;
 }
 
+void kasan_init_slab_obj(struct kmem_cache *cache, const void *object)
+{
+	struct kasan_alloc_meta *alloc_info;
+
+	if (!(cache->flags & SLAB_KASAN))
+		return;
+
+	alloc_info = get_alloc_info(cache, object);
+	__memset(alloc_info, 0, sizeof(*alloc_info));
+}
+
 void kasan_slab_alloc(struct kmem_cache *cache, void *object, gfp_t flags)
 {
 	kasan_kmalloc(cache, object, cache->object_size, flags);
@@ -529,34 +535,26 @@ static void kasan_poison_slab_free(struct kmem_cache *cache, void *object)
 
 bool kasan_slab_free(struct kmem_cache *cache, void *object)
 {
+	s8 shadow_byte;
+
 	/* RCU slabs could be legally used after free within the RCU period */
 	if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU))
 		return false;
 
-	if (likely(cache->flags & SLAB_KASAN)) {
-		struct kasan_alloc_meta *alloc_info;
-		struct kasan_free_meta *free_info;
+	shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object));
+	if (shadow_byte < 0 || shadow_byte >= KASAN_SHADOW_SCALE_SIZE) {
+		kasan_report_double_free(cache, object, shadow_byte);
+		return true;
+	}
 
-		alloc_info = get_alloc_info(cache, object);
-		free_info = get_free_info(cache, object);
+	kasan_poison_slab_free(cache, object);
 
-		switch (alloc_info->state) {
-		case KASAN_STATE_ALLOC:
-			alloc_info->state = KASAN_STATE_QUARANTINE;
-			quarantine_put(free_info, cache);
-			set_track(&free_info->track, GFP_NOWAIT);
-			kasan_poison_slab_free(cache, object);
-			return true;
-		case KASAN_STATE_QUARANTINE:
-		case KASAN_STATE_FREE:
-			pr_err("Double free");
-			dump_stack();
-			break;
-		default:
-			break;
-		}
-	}
-	return false;
+	if (unlikely(!(cache->flags & SLAB_KASAN)))
+		return false;
+
+	set_track(&get_alloc_info(cache, object)->free_track, GFP_NOWAIT);
+	quarantine_put(get_free_info(cache, object), cache);
+	return true;
 }
 
 void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
@@ -565,7 +563,7 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
 	unsigned long redzone_start;
 	unsigned long redzone_end;
 
-	if (flags & __GFP_RECLAIM)
+	if (gfpflags_allow_blocking(flags))
 		quarantine_reduce();
 
 	if (unlikely(object == NULL))
@@ -579,14 +577,9 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
 	kasan_unpoison_shadow(object, size);
 	kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
 		KASAN_KMALLOC_REDZONE);
-	if (cache->flags & SLAB_KASAN) {
-		struct kasan_alloc_meta *alloc_info =
-			get_alloc_info(cache, object);
 
-		alloc_info->state = KASAN_STATE_ALLOC;
-		alloc_info->alloc_size = size;
-		set_track(&alloc_info->track, flags);
-	}
+	if (cache->flags & SLAB_KASAN)
+		set_track(&get_alloc_info(cache, object)->alloc_track, flags);
 }
 EXPORT_SYMBOL(kasan_kmalloc);
 
@@ -596,7 +589,7 @@ void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags)
 	unsigned long redzone_start;
 	unsigned long redzone_end;
 
-	if (flags & __GFP_RECLAIM)
+	if (gfpflags_allow_blocking(flags))
 		quarantine_reduce();
 
 	if (unlikely(ptr == NULL))
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 31972cdba433..e5c2181fee6f 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -59,13 +59,6 @@ struct kasan_global {
  * Structures to keep alloc and free tracks *
  */
 
-enum kasan_state {
-	KASAN_STATE_INIT,
-	KASAN_STATE_ALLOC,
-	KASAN_STATE_QUARANTINE,
-	KASAN_STATE_FREE
-};
-
 #define KASAN_STACK_DEPTH 64
 
 struct kasan_track {
@@ -74,9 +67,8 @@ struct kasan_track {
 };
 
 struct kasan_alloc_meta {
-	struct kasan_track track;
-	u32 state : 2;	/* enum kasan_state */
-	u32 alloc_size : 30;
+	struct kasan_track alloc_track;
+	struct kasan_track free_track;
 };
 
 struct qlist_node {
@@ -87,7 +79,6 @@ struct kasan_free_meta {
 	 * Otherwise it might be used for the allocator freelist.
 	 */
 	struct qlist_node quarantine_link;
-	struct kasan_track track;
 };
 
 struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
@@ -108,6 +99,8 @@ static inline bool kasan_report_enabled(void)
 
 void kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip);
+void kasan_report_double_free(struct kmem_cache *cache, void *object,
+			s8 shadow);
 
 #if defined(CONFIG_SLAB) || defined(CONFIG_SLUB)
 void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache);
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 65793f150d1f..b6728a33a4ac 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -144,13 +144,15 @@ static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache)
 static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache)
 {
 	void *object = qlink_to_object(qlink, cache);
-	struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object);
 	unsigned long flags;
 
-	local_irq_save(flags);
-	alloc_info->state = KASAN_STATE_FREE;
+	if (IS_ENABLED(CONFIG_SLAB))
+		local_irq_save(flags);
+
 	___cache_free(cache, object, _THIS_IP_);
-	local_irq_restore(flags);
+
+	if (IS_ENABLED(CONFIG_SLAB))
+		local_irq_restore(flags);
 }
 
 static void qlist_free_all(struct qlist_head *q, struct kmem_cache *cache)
@@ -196,7 +198,7 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
 
 void quarantine_reduce(void)
 {
-	size_t new_quarantine_size;
+	size_t new_quarantine_size, percpu_quarantines;
 	unsigned long flags;
 	struct qlist_head to_free = QLIST_INIT;
 	size_t size_to_free = 0;
@@ -214,7 +216,12 @@ void quarantine_reduce(void)
 	 */
 	new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
 		QUARANTINE_FRACTION;
-	new_quarantine_size -= QUARANTINE_PERCPU_SIZE * num_online_cpus();
+	percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus();
+	if (WARN_ONCE(new_quarantine_size < percpu_quarantines,
+		"Too little memory, disabling global KASAN quarantine.\n"))
+		new_quarantine_size = 0;
+	else
+		new_quarantine_size -= percpu_quarantines;
 	WRITE_ONCE(quarantine_size, new_quarantine_size);
 
 	last = global_quarantine.head;
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 861b9776841a..24c1211fe9d5 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -116,6 +116,26 @@ static inline bool init_task_stack_addr(const void *addr)
 			sizeof(init_thread_union.stack));
 }
 
+static DEFINE_SPINLOCK(report_lock);
+
+static void kasan_start_report(unsigned long *flags)
+{
+	/*
+	 * Make sure we don't end up in loop.
+	 */
+	kasan_disable_current();
+	spin_lock_irqsave(&report_lock, *flags);
+	pr_err("==================================================================\n");
+}
+
+static void kasan_end_report(unsigned long *flags)
+{
+	pr_err("==================================================================\n");
+	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
+	spin_unlock_irqrestore(&report_lock, *flags);
+	kasan_enable_current();
+}
+
 static void print_track(struct kasan_track *track)
 {
 	pr_err("PID = %u\n", track->pid);
@@ -129,37 +149,33 @@ static void print_track(struct kasan_track *track)
 	}
 }
 
-static void kasan_object_err(struct kmem_cache *cache, struct page *page,
-				void *object, char *unused_reason)
+static void kasan_object_err(struct kmem_cache *cache, void *object)
 {
 	struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object);
-	struct kasan_free_meta *free_info;
 
 	dump_stack();
-	pr_err("Object at %p, in cache %s\n", object, cache->name);
+	pr_err("Object at %p, in cache %s size: %d\n", object, cache->name,
+		cache->object_size);
+
 	if (!(cache->flags & SLAB_KASAN))
 		return;
-	switch (alloc_info->state) {
-	case KASAN_STATE_INIT:
-		pr_err("Object not allocated yet\n");
-		break;
-	case KASAN_STATE_ALLOC:
-		pr_err("Object allocated with size %u bytes.\n",
-		       alloc_info->alloc_size);
-		pr_err("Allocation:\n");
-		print_track(&alloc_info->track);
-		break;
-	case KASAN_STATE_FREE:
-	case KASAN_STATE_QUARANTINE:
-		pr_err("Object freed, allocated with size %u bytes\n",
-		       alloc_info->alloc_size);
-		free_info = get_free_info(cache, object);
-		pr_err("Allocation:\n");
-		print_track(&alloc_info->track);
-		pr_err("Deallocation:\n");
-		print_track(&free_info->track);
-		break;
-	}
+
+	pr_err("Allocated:\n");
+	print_track(&alloc_info->alloc_track);
+	pr_err("Freed:\n");
+	print_track(&alloc_info->free_track);
+}
+
+void kasan_report_double_free(struct kmem_cache *cache, void *object,
+			s8 shadow)
+{
+	unsigned long flags;
+
+	kasan_start_report(&flags);
+	pr_err("BUG: Double free or freeing an invalid pointer\n");
+	pr_err("Unexpected shadow byte: 0x%hhX\n", shadow);
+	kasan_object_err(cache, object);
+	kasan_end_report(&flags);
 }
 
 static void print_address_description(struct kasan_access_info *info)
@@ -175,8 +191,7 @@ static void print_address_description(struct kasan_access_info *info)
 			struct kmem_cache *cache = page->slab_cache;
 			object = nearest_obj(cache, page,
 						(void *)info->access_addr);
-			kasan_object_err(cache, page, object,
-					"kasan: bad access detected");
+			kasan_object_err(cache, object);
 			return;
 		}
 		dump_page(page, "kasan: bad access detected");
@@ -241,19 +256,13 @@ static void print_shadow_for_address(const void *addr)
 	}
 }
 
-static DEFINE_SPINLOCK(report_lock);
-
 static void kasan_report_error(struct kasan_access_info *info)
 {
 	unsigned long flags;
 	const char *bug_type;
 
-	/*
-	 * Make sure we don't end up in loop.
-	 */
-	kasan_disable_current();
-	spin_lock_irqsave(&report_lock, flags);
-	pr_err("==================================================================\n");
+	kasan_start_report(&flags);
+
 	if (info->access_addr <
 			kasan_shadow_to_mem((void *)KASAN_SHADOW_START)) {
 		if ((unsigned long)info->access_addr < PAGE_SIZE)
@@ -274,10 +283,8 @@ static void kasan_report_error(struct kasan_access_info *info)
 		print_address_description(info);
 		print_shadow_for_address(info->first_bad_addr);
 	}
-	pr_err("==================================================================\n");
-	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
-	spin_unlock_irqrestore(&report_lock, flags);
-	kasan_enable_current();
+
+	kasan_end_report(&flags);
 }
 
 void kasan_report(unsigned long addr, size_t size,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c265212bec8c..66beca1ad92f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2559,6 +2559,15 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 		return 0;
 
 	mctz = soft_limit_tree_node(pgdat->node_id);
+
+	/*
+	 * Do not even bother to check the largest node if the root
+	 * is empty. Do it lockless to prevent lock bouncing. Races
+	 * are acceptable as soft limit is best effort anyway.
+	 */
+	if (RB_EMPTY_ROOT(&mctz->rb_root))
+		return 0;
+
 	/*
 	 * This loop can run a while, specially if mem_cgroup's continuously
 	 * keep exceeding their soft limit and putting the system under
diff --git a/mm/memory.c b/mm/memory.c
index 4425b6059339..83be99d9d8a1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2642,6 +2642,7 @@ int do_swap_page(struct fault_env *fe, pte_t orig_pte)
 	if (page == swapcache) {
 		do_page_add_anon_rmap(page, vma, fe->address, exclusive);
 		mem_cgroup_commit_charge(page, memcg, true, false);
+		activate_page(page);
 	} else { /* ksm created a completely new copy */
 		page_add_new_anon_rmap(page, vma, fe->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
@@ -3133,6 +3134,8 @@ static int do_fault_around(struct fault_env *fe, pgoff_t start_pgoff)
 
 	if (pmd_none(*fe->pmd)) {
 		fe->prealloc_pte = pte_alloc_one(fe->vma->vm_mm, fe->address);
+		if (!fe->prealloc_pte)
+			goto out;
 		smp_wmb(); /* See comment in __pte_alloc() */
 	}
 
diff --git a/mm/mmap.c b/mm/mmap.c
index d44bee96a5fe..ca9d91bca0d6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2653,16 +2653,18 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-static int do_brk(unsigned long addr, unsigned long len)
+static int do_brk(unsigned long addr, unsigned long request)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	unsigned long flags;
+	unsigned long flags, len;
 	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
 
-	len = PAGE_ALIGN(len);
+	len = PAGE_ALIGN(request);
+	if (len < request)
+		return -ENOMEM;
 	if (!len)
 		return 0;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ea759b935360..39a372a2a1d6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5276,7 +5276,7 @@ void __init setup_per_cpu_pageset(void)
 		setup_zone_pageset(zone);
 }
 
-static noinline __init_refok
+static noinline __ref
 int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
 {
 	int i;
@@ -5903,7 +5903,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 	}
 }
 
-static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
+static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
 {
 	unsigned long __maybe_unused start = 0;
 	unsigned long __maybe_unused offset = 0;
diff --git a/mm/slab.c b/mm/slab.c
index 09771ed3e693..261147ba156f 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1877,7 +1877,7 @@ static struct array_cache __percpu *alloc_kmem_cache_cpus(
 	return cpu_cache;
 }
 
-static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
+static int __ref setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	if (slab_state >= FULL)
 		return enable_cpucache(cachep, gfp);
@@ -2604,9 +2604,11 @@ static void cache_init_objs(struct kmem_cache *cachep,
 	}
 
 	for (i = 0; i < cachep->num; i++) {
+		objp = index_to_obj(cachep, page, i);
+		kasan_init_slab_obj(cachep, objp);
+
 		/* constructor could break poison info */
 		if (DEBUG == 0 && cachep->ctor) {
-			objp = index_to_obj(cachep, page, i);
 			kasan_unpoison_object_data(cachep, objp);
 			cachep->ctor(objp);
 			kasan_poison_object_data(cachep, objp);
diff --git a/mm/slub.c b/mm/slub.c
index 74e7c8c30db8..26eb6a99540e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1384,6 +1384,7 @@ static void setup_object(struct kmem_cache *s, struct page *page,
 				void *object)
 {
 	setup_object_debug(s, page, object);
+	kasan_init_slab_obj(s, object);
 	if (unlikely(s->ctor)) {
 		kasan_unpoison_object_data(s, object);
 		s->ctor(object);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 68885dcbaf40..574c67b663fe 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -36,7 +36,7 @@
  * Uses the main allocators if they are available, else bootmem.
  */
 
-static void * __init_refok __earlyonly_bootmem_alloc(int node,
+static void * __ref __earlyonly_bootmem_alloc(int node,
 				unsigned long size,
 				unsigned long align,
 				unsigned long goal)
diff --git a/mm/sparse.c b/mm/sparse.c
index 36d7bbb80e49..1e168bf2779a 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -59,7 +59,7 @@ static inline void set_section_nid(unsigned long section_nr, int nid)
 #endif
 
 #ifdef CONFIG_SPARSEMEM_EXTREME
-static struct mem_section noinline __init_refok *sparse_index_alloc(int nid)
+static noinline struct mem_section __ref *sparse_index_alloc(int nid)
 {
 	struct mem_section *section = NULL;
 	unsigned long array_size = SECTIONS_PER_ROOT *
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 650d26832569..374d95d04178 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2561,7 +2561,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
 			node_lru_pages += lru_pages;
 
-			if (!global_reclaim(sc))
+			if (memcg)
 				shrink_slab(sc->gfp_mask, pgdat->node_id,
 					    memcg, sc->nr_scanned - scanned,
 					    lru_pages);
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
index 958d9856912c..84cbed630c4b 100644
--- a/net/ceph/Makefile
+++ b/net/ceph/Makefile
@@ -11,5 +11,5 @@ libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
 	crypto.o armor.o \
 	auth_x.o \
 	ceph_fs.o ceph_strings.o ceph_hash.o \
-	pagevec.o snapshot.o
+	pagevec.o snapshot.o string_table.o
 
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 55d2bfee16d7..bddfcf6f09c2 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -747,6 +747,8 @@ out:
 static void __exit exit_ceph_lib(void)
 {
 	dout("exit_ceph_lib\n");
+	WARN_ON(!ceph_strings_empty());
+
 	ceph_osdc_cleanup();
 	ceph_msgr_exit();
 	ceph_crypto_shutdown();
diff --git a/net/ceph/ceph_fs.c b/net/ceph/ceph_fs.c
index 41466ccb972a..7d54e944de5e 100644
--- a/net/ceph/ceph_fs.c
+++ b/net/ceph/ceph_fs.c
@@ -9,9 +9,9 @@
  */
 int ceph_file_layout_is_valid(const struct ceph_file_layout *layout)
 {
-	__u32 su = le32_to_cpu(layout->fl_stripe_unit);
-	__u32 sc = le32_to_cpu(layout->fl_stripe_count);
-	__u32 os = le32_to_cpu(layout->fl_object_size);
+	__u32 su = layout->stripe_unit;
+	__u32 sc = layout->stripe_count;
+	__u32 os = layout->object_size;
 
 	/* stripe unit, object size must be non-zero, 64k increment */
 	if (!su || (su & (CEPH_MIN_STRIPE_UNIT-1)))
@@ -27,6 +27,30 @@ int ceph_file_layout_is_valid(const struct ceph_file_layout *layout)
 	return 1;
 }
 
+void ceph_file_layout_from_legacy(struct ceph_file_layout *fl,
+				  struct ceph_file_layout_legacy *legacy)
+{
+	fl->stripe_unit = le32_to_cpu(legacy->fl_stripe_unit);
+	fl->stripe_count = le32_to_cpu(legacy->fl_stripe_count);
+	fl->object_size = le32_to_cpu(legacy->fl_object_size);
+	fl->pool_id = le32_to_cpu(legacy->fl_pg_pool);
+	if (fl->pool_id == 0)
+		fl->pool_id = -1;
+}
+EXPORT_SYMBOL(ceph_file_layout_from_legacy);
+
+void ceph_file_layout_to_legacy(struct ceph_file_layout *fl,
+				struct ceph_file_layout_legacy *legacy)
+{
+	legacy->fl_stripe_unit = cpu_to_le32(fl->stripe_unit);
+	legacy->fl_stripe_count = cpu_to_le32(fl->stripe_count);
+	legacy->fl_object_size = cpu_to_le32(fl->object_size);
+	if (fl->pool_id >= 0)
+		legacy->fl_pg_pool = cpu_to_le32(fl->pool_id);
+	else
+		legacy->fl_pg_pool = 0;
+}
+EXPORT_SYMBOL(ceph_file_layout_to_legacy);
 
 int ceph_flags_to_mode(int flags)
 {
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index e77b04ca7802..c62b2b029a6e 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -156,8 +156,16 @@ static void dump_target(struct seq_file *s, struct ceph_osd_request_target *t)
 	seq_printf(s, "]/%d\t[", t->up.primary);
 	for (i = 0; i < t->acting.size; i++)
 		seq_printf(s, "%s%d", (!i ? "" : ","), t->acting.osds[i]);
-	seq_printf(s, "]/%d\t%*pE\t0x%x", t->acting.primary,
-		   t->target_oid.name_len, t->target_oid.name, t->flags);
+	seq_printf(s, "]/%d\t", t->acting.primary);
+	if (t->target_oloc.pool_ns) {
+		seq_printf(s, "%*pE/%*pE\t0x%x",
+			(int)t->target_oloc.pool_ns->len,
+			t->target_oloc.pool_ns->str,
+			t->target_oid.name_len, t->target_oid.name, t->flags);
+	} else {
+		seq_printf(s, "%*pE\t0x%x", t->target_oid.name_len,
+			t->target_oid.name, t->flags);
+	}
 	if (t->paused)
 		seq_puts(s, "\tP");
 }
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 37c38a7fb5c5..c83326c5ba58 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -227,9 +227,10 @@ static void __schedule_delayed(struct ceph_mon_client *monc)
 }
 
 const char *ceph_sub_str[] = {
-	[CEPH_SUB_MDSMAP] = "mdsmap",
 	[CEPH_SUB_MONMAP] = "monmap",
 	[CEPH_SUB_OSDMAP] = "osdmap",
+	[CEPH_SUB_FSMAP]  = "fsmap.user",
+	[CEPH_SUB_MDSMAP] = "mdsmap",
 };
 
 /*
@@ -1193,6 +1194,7 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 	case CEPH_MSG_MON_MAP:
 	case CEPH_MSG_MDS_MAP:
 	case CEPH_MSG_OSD_MAP:
+	case CEPH_MSG_FS_MAP_USER:
 		m = ceph_msg_new(type, front_len, GFP_NOFS, false);
 		if (!m)
 			return NULL;	/* ENOMEM--return skip == 0 */
diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c
index ddec1c10ac80..aaed59a47b1d 100644
--- a/net/ceph/msgpool.c
+++ b/net/ceph/msgpool.c
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
+#include <linux/ceph/messenger.h>
 #include <linux/ceph/msgpool.h>
 
 static void *msgpool_alloc(gfp_t gfp_mask, void *arg)
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 89469592076c..b5ec09612ff7 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -387,7 +387,9 @@ static void target_copy(struct ceph_osd_request_target *dest,
 static void target_destroy(struct ceph_osd_request_target *t)
 {
 	ceph_oid_destroy(&t->base_oid);
+	ceph_oloc_destroy(&t->base_oloc);
 	ceph_oid_destroy(&t->target_oid);
+	ceph_oloc_destroy(&t->target_oloc);
 }
 
 /*
@@ -533,6 +535,11 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 }
 EXPORT_SYMBOL(ceph_osdc_alloc_request);
 
+static int ceph_oloc_encoding_size(struct ceph_object_locator *oloc)
+{
+	return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0);
+}
+
 int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
 {
 	struct ceph_osd_client *osdc = req->r_osdc;
@@ -540,11 +547,13 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
 	int msg_size;
 
 	WARN_ON(ceph_oid_empty(&req->r_base_oid));
+	WARN_ON(ceph_oloc_empty(&req->r_base_oloc));
 
 	/* create request message */
 	msg_size = 4 + 4 + 4; /* client_inc, osdmap_epoch, flags */
 	msg_size += 4 + 4 + 4 + 8; /* mtime, reassert_version */
-	msg_size += 2 + 4 + 8 + 4 + 4; /* oloc */
+	msg_size += CEPH_ENCODING_START_BLK_LEN +
+			ceph_oloc_encoding_size(&req->r_base_oloc); /* oloc */
 	msg_size += 1 + 8 + 4 + 4; /* pgid */
 	msg_size += 4 + req->r_base_oid.name_len; /* oid */
 	msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op);
@@ -932,7 +941,7 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) {
 		osd_req_op_init(req, which, opcode, 0);
 	} else {
-		u32 object_size = le32_to_cpu(layout->fl_object_size);
+		u32 object_size = layout->object_size;
 		u32 object_base = off - objoff;
 		if (!(truncate_seq == 1 && truncate_size == -1ULL)) {
 			if (truncate_size <= object_base) {
@@ -948,7 +957,8 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	}
 
 	req->r_flags = flags;
-	req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout);
+	req->r_base_oloc.pool = layout->pool_id;
+	req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns);
 	ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum);
 
 	req->r_snapid = vino.snap;
@@ -1489,12 +1499,16 @@ static void encode_request(struct ceph_osd_request *req, struct ceph_msg *msg)
 	p += sizeof(req->r_replay_version);
 
 	/* oloc */
-	ceph_encode_8(&p, 4);
-	ceph_encode_8(&p, 4);
-	ceph_encode_32(&p, 8 + 4 + 4);
+	ceph_start_encoding(&p, 5, 4,
+			    ceph_oloc_encoding_size(&req->r_t.target_oloc));
 	ceph_encode_64(&p, req->r_t.target_oloc.pool);
 	ceph_encode_32(&p, -1); /* preferred */
 	ceph_encode_32(&p, 0); /* key len */
+	if (req->r_t.target_oloc.pool_ns)
+		ceph_encode_string(&p, end, req->r_t.target_oloc.pool_ns->str,
+				   req->r_t.target_oloc.pool_ns->len);
+	else
+		ceph_encode_32(&p, 0);
 
 	/* pgid */
 	ceph_encode_8(&p, 1);
@@ -2594,9 +2608,22 @@ static int ceph_oloc_decode(void **p, void *end,
 	}
 
 	if (struct_v >= 5) {
+		bool changed = false;
+
 		len = ceph_decode_32(p);
 		if (len > 0) {
-			pr_warn("ceph_object_locator::nspace is set\n");
+			ceph_decode_need(p, end, len, e_inval);
+			if (!oloc->pool_ns ||
+			    ceph_compare_string(oloc->pool_ns, *p, len))
+				changed = true;
+			*p += len;
+		} else {
+			if (oloc->pool_ns)
+				changed = true;
+		}
+		if (changed) {
+			/* redirect changes namespace */
+			pr_warn("ceph_object_locator::nspace is changed\n");
 			goto e_inval;
 		}
 	}
@@ -2806,7 +2833,9 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
 		goto out_unlock_session;
 	}
 
+	m.redirect.oloc.pool_ns = req->r_t.target_oloc.pool_ns;
 	ret = decode_MOSDOpReply(msg, &m);
+	m.redirect.oloc.pool_ns = NULL;
 	if (ret) {
 		pr_err("failed to decode MOSDOpReply for tid %llu: %d\n",
 		       req->r_tid, ret);
@@ -2835,7 +2864,11 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
 		unlink_request(osd, req);
 		mutex_unlock(&osd->lock);
 
-		ceph_oloc_copy(&req->r_t.target_oloc, &m.redirect.oloc);
+		/*
+		 * Not ceph_oloc_copy() - changing pool_ns is not
+		 * supported.
+		 */
+		req->r_t.target_oloc.pool = m.redirect.oloc.pool;
 		req->r_flags |= CEPH_OSD_FLAG_REDIRECTED;
 		req->r_tid = 0;
 		__submit_request(req, false);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 7e480bf75bcf..d2436880b305 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1510,6 +1510,24 @@ bad:
 	return ERR_PTR(err);
 }
 
+void ceph_oloc_copy(struct ceph_object_locator *dest,
+		    const struct ceph_object_locator *src)
+{
+	WARN_ON(!ceph_oloc_empty(dest));
+	WARN_ON(dest->pool_ns); /* empty() only covers ->pool */
+
+	dest->pool = src->pool;
+	if (src->pool_ns)
+		dest->pool_ns = ceph_get_string(src->pool_ns);
+}
+EXPORT_SYMBOL(ceph_oloc_copy);
+
+void ceph_oloc_destroy(struct ceph_object_locator *oloc)
+{
+	ceph_put_string(oloc->pool_ns);
+}
+EXPORT_SYMBOL(ceph_oloc_destroy);
+
 void ceph_oid_copy(struct ceph_object_id *dest,
 		   const struct ceph_object_id *src)
 {
@@ -1770,9 +1788,9 @@ int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 				   u64 *ono,
 				   u64 *oxoff, u64 *oxlen)
 {
-	u32 osize = le32_to_cpu(layout->fl_object_size);
-	u32 su = le32_to_cpu(layout->fl_stripe_unit);
-	u32 sc = le32_to_cpu(layout->fl_stripe_count);
+	u32 osize = layout->object_size;
+	u32 su = layout->stripe_unit;
+	u32 sc = layout->stripe_count;
 	u32 bl, stripeno, stripepos, objsetno;
 	u32 su_per_object;
 	u64 t, su_offset;
@@ -1844,12 +1862,34 @@ int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
 	if (!pi)
 		return -ENOENT;
 
-	raw_pgid->pool = oloc->pool;
-	raw_pgid->seed = ceph_str_hash(pi->object_hash, oid->name,
-				       oid->name_len);
-
-	dout("%s %s -> raw_pgid %llu.%x\n", __func__, oid->name,
-	     raw_pgid->pool, raw_pgid->seed);
+	if (!oloc->pool_ns) {
+		raw_pgid->pool = oloc->pool;
+		raw_pgid->seed = ceph_str_hash(pi->object_hash, oid->name,
+					     oid->name_len);
+		dout("%s %s -> raw_pgid %llu.%x\n", __func__, oid->name,
+		     raw_pgid->pool, raw_pgid->seed);
+	} else {
+		char stack_buf[256];
+		char *buf = stack_buf;
+		int nsl = oloc->pool_ns->len;
+		size_t total = nsl + 1 + oid->name_len;
+
+		if (total > sizeof(stack_buf)) {
+			buf = kmalloc(total, GFP_NOIO);
+			if (!buf)
+				return -ENOMEM;
+		}
+		memcpy(buf, oloc->pool_ns->str, nsl);
+		buf[nsl] = '\037';
+		memcpy(buf + nsl + 1, oid->name, oid->name_len);
+		raw_pgid->pool = oloc->pool;
+		raw_pgid->seed = ceph_str_hash(pi->object_hash, buf, total);
+		if (buf != stack_buf)
+			kfree(buf);
+		dout("%s %s ns %.*s -> raw_pgid %llu.%x\n", __func__,
+		     oid->name, nsl, oloc->pool_ns->str,
+		     raw_pgid->pool, raw_pgid->seed);
+	}
 	return 0;
 }
 EXPORT_SYMBOL(ceph_object_locator_to_pg);
diff --git a/net/ceph/string_table.c b/net/ceph/string_table.c
new file mode 100644
index 000000000000..ca53c8319209
--- /dev/null
+++ b/net/ceph/string_table.c
@@ -0,0 +1,111 @@
+#include <linux/slab.h>
+#include <linux/gfp.h>
+#include <linux/string.h>
+#include <linux/spinlock.h>
+#include <linux/ceph/string_table.h>
+
+static DEFINE_SPINLOCK(string_tree_lock);
+static struct rb_root string_tree = RB_ROOT;
+
+struct ceph_string *ceph_find_or_create_string(const char* str, size_t len)
+{
+	struct ceph_string *cs, *exist;
+	struct rb_node **p, *parent;
+	int ret;
+
+	exist = NULL;
+	spin_lock(&string_tree_lock);
+	p = &string_tree.rb_node;
+	while (*p) {
+		exist = rb_entry(*p, struct ceph_string, node);
+		ret = ceph_compare_string(exist, str, len);
+		if (ret > 0)
+			p = &(*p)->rb_left;
+		else if (ret < 0)
+			p = &(*p)->rb_right;
+		else
+			break;
+		exist = NULL;
+	}
+	if (exist && !kref_get_unless_zero(&exist->kref)) {
+		rb_erase(&exist->node, &string_tree);
+		RB_CLEAR_NODE(&exist->node);
+		exist = NULL;
+	}
+	spin_unlock(&string_tree_lock);
+	if (exist)
+		return exist;
+
+	cs = kmalloc(sizeof(*cs) + len + 1, GFP_NOFS);
+	if (!cs)
+		return NULL;
+
+	kref_init(&cs->kref);
+	cs->len = len;
+	memcpy(cs->str, str, len);
+	cs->str[len] = 0;
+
+retry:
+	exist = NULL;
+	parent = NULL;
+	p = &string_tree.rb_node;
+	spin_lock(&string_tree_lock);
+	while (*p) {
+		parent = *p;
+		exist = rb_entry(*p, struct ceph_string, node);
+		ret = ceph_compare_string(exist, str, len);
+		if (ret > 0)
+			p = &(*p)->rb_left;
+		else if (ret < 0)
+			p = &(*p)->rb_right;
+		else
+			break;
+		exist = NULL;
+	}
+	ret = 0;
+	if (!exist) {
+		rb_link_node(&cs->node, parent, p);
+		rb_insert_color(&cs->node, &string_tree);
+	} else if (!kref_get_unless_zero(&exist->kref)) {
+		rb_erase(&exist->node, &string_tree);
+		RB_CLEAR_NODE(&exist->node);
+		ret = -EAGAIN;
+	}
+	spin_unlock(&string_tree_lock);
+	if (ret == -EAGAIN)
+		goto retry;
+
+	if (exist) {
+		kfree(cs);
+		cs = exist;
+	}
+
+	return cs;
+}
+EXPORT_SYMBOL(ceph_find_or_create_string);
+
+static void ceph_free_string(struct rcu_head *head)
+{
+	struct ceph_string *cs = container_of(head, struct ceph_string, rcu);
+	kfree(cs);
+}
+
+void ceph_release_string(struct kref *ref)
+{
+	struct ceph_string *cs = container_of(ref, struct ceph_string, kref);
+
+	spin_lock(&string_tree_lock);
+	if (!RB_EMPTY_NODE(&cs->node)) {
+		rb_erase(&cs->node, &string_tree);
+		RB_CLEAR_NODE(&cs->node);
+	}
+	spin_unlock(&string_tree_lock);
+
+	call_rcu(&cs->rcu, ceph_free_string);
+}
+EXPORT_SYMBOL(ceph_release_string);
+
+bool ceph_strings_empty(void)
+{
+	return RB_EMPTY_ROOT(&string_tree);
+}
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 040ff627c18a..a7e42f9a405c 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -51,9 +51,7 @@ static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp)
 	ret = kstrtoul(val, 0, &num);
 	if (ret == -EINVAL)
 		goto out_inval;
-	nbits = fls(num);
-	if (num > (1U << nbits))
-		nbits++;
+	nbits = fls(num - 1);
 	if (nbits > MAX_HASHTABLE_BITS || nbits < 2)
 		goto out_inval;
 	*(unsigned int *)kp->arg = nbits;
@@ -359,8 +357,10 @@ rpcauth_key_timeout_notify(struct rpc_auth *auth, struct rpc_cred *cred)
 EXPORT_SYMBOL_GPL(rpcauth_key_timeout_notify);
 
 bool
-rpcauth_cred_key_to_expire(struct rpc_cred *cred)
+rpcauth_cred_key_to_expire(struct rpc_auth *auth, struct rpc_cred *cred)
 {
+	if (auth->au_flags & RPCAUTH_AUTH_NO_CRKEY_TIMEOUT)
+		return false;
 	if (!cred->cr_ops->crkey_to_expire)
 		return false;
 	return cred->cr_ops->crkey_to_expire(cred);
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index 54dd3fdead54..168219535a34 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -224,7 +224,7 @@ generic_key_timeout(struct rpc_auth *auth, struct rpc_cred *cred)
 
 
 	/* Fast track for non crkey_timeout (no key) underlying credentials */
-	if (test_bit(RPC_CRED_NO_CRKEY_TIMEOUT, &acred->ac_flags))
+	if (auth->au_flags & RPCAUTH_AUTH_NO_CRKEY_TIMEOUT)
 		return 0;
 
 	/* Fast track for the normal case */
@@ -236,12 +236,6 @@ generic_key_timeout(struct rpc_auth *auth, struct rpc_cred *cred)
 	if (IS_ERR(tcred))
 		return -EACCES;
 
-	if (!tcred->cr_ops->crkey_timeout) {
-		set_bit(RPC_CRED_NO_CRKEY_TIMEOUT, &acred->ac_flags);
-		ret = 0;
-		goto out_put;
-	}
-
 	/* Test for the almost error case */
 	ret = tcred->cr_ops->crkey_timeout(tcred);
 	if (ret != 0) {
@@ -257,7 +251,6 @@ generic_key_timeout(struct rpc_auth *auth, struct rpc_cred *cred)
 		set_bit(RPC_CRED_NOTIFY_TIMEOUT, &acred->ac_flags);
 	}
 
-out_put:
 	put_rpccred(tcred);
 	return ret;
 }
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index e64ae93d5b4f..23c8e7c39656 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1015,8 +1015,11 @@ gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt)
 	auth = &gss_auth->rpc_auth;
 	auth->au_cslack = GSS_CRED_SLACK >> 2;
 	auth->au_rslack = GSS_VERF_SLACK >> 2;
+	auth->au_flags = 0;
 	auth->au_ops = &authgss_ops;
 	auth->au_flavor = flavor;
+	if (gss_pseudoflavor_to_datatouch(gss_auth->mech, flavor))
+		auth->au_flags |= RPCAUTH_AUTH_DATATOUCH;
 	atomic_set(&auth->au_count, 1);
 	kref_init(&gss_auth->kref);
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 65427492b1c9..60595835317a 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -745,12 +745,14 @@ static struct pf_desc gss_kerberos_pfs[] = {
 		.qop = GSS_C_QOP_DEFAULT,
 		.service = RPC_GSS_SVC_INTEGRITY,
 		.name = "krb5i",
+		.datatouch = true,
 	},
 	[2] = {
 		.pseudoflavor = RPC_AUTH_GSS_KRB5P,
 		.qop = GSS_C_QOP_DEFAULT,
 		.service = RPC_GSS_SVC_PRIVACY,
 		.name = "krb5p",
+		.datatouch = true,
 	},
 };
 
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index 7063d856a598..5fec3abbe19b 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -361,6 +361,18 @@ gss_pseudoflavor_to_service(struct gss_api_mech *gm, u32 pseudoflavor)
 }
 EXPORT_SYMBOL(gss_pseudoflavor_to_service);
 
+bool
+gss_pseudoflavor_to_datatouch(struct gss_api_mech *gm, u32 pseudoflavor)
+{
+	int i;
+
+	for (i = 0; i < gm->gm_pf_num; i++) {
+		if (gm->gm_pfs[i].pseudoflavor == pseudoflavor)
+			return gm->gm_pfs[i].datatouch;
+	}
+	return false;
+}
+
 char *
 gss_service_to_auth_domain_name(struct gss_api_mech *gm, u32 service)
 {
diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c
index 8d9eb4d5ddd8..4d17376b2acb 100644
--- a/net/sunrpc/auth_null.c
+++ b/net/sunrpc/auth_null.c
@@ -115,6 +115,7 @@ static
 struct rpc_auth null_auth = {
 	.au_cslack	= NUL_CALLSLACK,
 	.au_rslack	= NUL_REPLYSLACK,
+	.au_flags	= RPCAUTH_AUTH_NO_CRKEY_TIMEOUT,
 	.au_ops		= &authnull_ops,
 	.au_flavor	= RPC_AUTH_NULL,
 	.au_count	= ATOMIC_INIT(0),
diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c
index 9f65452b7cbc..a99278c984e8 100644
--- a/net/sunrpc/auth_unix.c
+++ b/net/sunrpc/auth_unix.c
@@ -228,6 +228,7 @@ static
 struct rpc_auth		unix_auth = {
 	.au_cslack	= UNX_CALLSLACK,
 	.au_rslack	= NUL_REPLYSLACK,
+	.au_flags	= RPCAUTH_AUTH_NO_CRKEY_TIMEOUT,
 	.au_ops		= &authunix_ops,
 	.au_flavor	= RPC_AUTH_UNIX,
 	.au_count	= ATOMIC_INIT(0),
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 2808d550d273..cb49898a5a58 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2577,7 +2577,7 @@ static void rpc_cb_add_xprt_release(void *calldata)
 	kfree(data);
 }
 
-const static struct rpc_call_ops rpc_cb_add_xprt_call_ops = {
+static const struct rpc_call_ops rpc_cb_add_xprt_call_ops = {
 	.rpc_call_done = rpc_cb_add_xprt_done,
 	.rpc_release = rpc_cb_add_xprt_release,
 };
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index fcfd48d263f6..9ae588511aaf 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -54,7 +54,8 @@ static struct rpc_wait_queue delay_queue;
 /*
  * rpciod-related stuff
  */
-struct workqueue_struct *rpciod_workqueue;
+struct workqueue_struct *rpciod_workqueue __read_mostly;
+struct workqueue_struct *xprtiod_workqueue __read_mostly;
 
 /*
  * Disable the timer for a given RPC task. Should be called with
@@ -329,7 +330,8 @@ EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task);
  * lockless RPC_IS_QUEUED() test) before we've had a chance to test
  * the RPC_TASK_RUNNING flag.
  */
-static void rpc_make_runnable(struct rpc_task *task)
+static void rpc_make_runnable(struct workqueue_struct *wq,
+		struct rpc_task *task)
 {
 	bool need_wakeup = !rpc_test_and_set_running(task);
 
@@ -338,7 +340,7 @@ static void rpc_make_runnable(struct rpc_task *task)
 		return;
 	if (RPC_IS_ASYNC(task)) {
 		INIT_WORK(&task->u.tk_work, rpc_async_schedule);
-		queue_work(rpciod_workqueue, &task->u.tk_work);
+		queue_work(wq, &task->u.tk_work);
 	} else
 		wake_up_bit(&task->tk_runstate, RPC_TASK_QUEUED);
 }
@@ -407,13 +409,16 @@ void rpc_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task,
 EXPORT_SYMBOL_GPL(rpc_sleep_on_priority);
 
 /**
- * __rpc_do_wake_up_task - wake up a single rpc_task
+ * __rpc_do_wake_up_task_on_wq - wake up a single rpc_task
+ * @wq: workqueue on which to run task
  * @queue: wait queue
  * @task: task to be woken up
  *
  * Caller must hold queue->lock, and have cleared the task queued flag.
  */
-static void __rpc_do_wake_up_task(struct rpc_wait_queue *queue, struct rpc_task *task)
+static void __rpc_do_wake_up_task_on_wq(struct workqueue_struct *wq,
+		struct rpc_wait_queue *queue,
+		struct rpc_task *task)
 {
 	dprintk("RPC: %5u __rpc_wake_up_task (now %lu)\n",
 			task->tk_pid, jiffies);
@@ -428,7 +433,7 @@ static void __rpc_do_wake_up_task(struct rpc_wait_queue *queue, struct rpc_task
 
 	__rpc_remove_wait_queue(queue, task);
 
-	rpc_make_runnable(task);
+	rpc_make_runnable(wq, task);
 
 	dprintk("RPC:       __rpc_wake_up_task done\n");
 }
@@ -436,16 +441,25 @@ static void __rpc_do_wake_up_task(struct rpc_wait_queue *queue, struct rpc_task
 /*
  * Wake up a queued task while the queue lock is being held
  */
-static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct rpc_task *task)
+static void rpc_wake_up_task_on_wq_queue_locked(struct workqueue_struct *wq,
+		struct rpc_wait_queue *queue, struct rpc_task *task)
 {
 	if (RPC_IS_QUEUED(task)) {
 		smp_rmb();
 		if (task->tk_waitqueue == queue)
-			__rpc_do_wake_up_task(queue, task);
+			__rpc_do_wake_up_task_on_wq(wq, queue, task);
 	}
 }
 
 /*
+ * Wake up a queued task while the queue lock is being held
+ */
+static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct rpc_task *task)
+{
+	rpc_wake_up_task_on_wq_queue_locked(rpciod_workqueue, queue, task);
+}
+
+/*
  * Wake up a task on a specific queue
  */
 void rpc_wake_up_queued_task(struct rpc_wait_queue *queue, struct rpc_task *task)
@@ -518,7 +532,8 @@ static struct rpc_task *__rpc_find_next_queued(struct rpc_wait_queue *queue)
 /*
  * Wake up the first task on the wait queue.
  */
-struct rpc_task *rpc_wake_up_first(struct rpc_wait_queue *queue,
+struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq,
+		struct rpc_wait_queue *queue,
 		bool (*func)(struct rpc_task *, void *), void *data)
 {
 	struct rpc_task	*task = NULL;
@@ -529,7 +544,7 @@ struct rpc_task *rpc_wake_up_first(struct rpc_wait_queue *queue,
 	task = __rpc_find_next_queued(queue);
 	if (task != NULL) {
 		if (func(task, data))
-			rpc_wake_up_task_queue_locked(queue, task);
+			rpc_wake_up_task_on_wq_queue_locked(wq, queue, task);
 		else
 			task = NULL;
 	}
@@ -537,6 +552,15 @@ struct rpc_task *rpc_wake_up_first(struct rpc_wait_queue *queue,
 
 	return task;
 }
+
+/*
+ * Wake up the first task on the wait queue.
+ */
+struct rpc_task *rpc_wake_up_first(struct rpc_wait_queue *queue,
+		bool (*func)(struct rpc_task *, void *), void *data)
+{
+	return rpc_wake_up_first_on_wq(rpciod_workqueue, queue, func, data);
+}
 EXPORT_SYMBOL_GPL(rpc_wake_up_first);
 
 static bool rpc_wake_up_next_func(struct rpc_task *task, void *data)
@@ -814,7 +838,7 @@ void rpc_execute(struct rpc_task *task)
 	bool is_async = RPC_IS_ASYNC(task);
 
 	rpc_set_active(task);
-	rpc_make_runnable(task);
+	rpc_make_runnable(rpciod_workqueue, task);
 	if (!is_async)
 		__rpc_execute(task);
 }
@@ -1071,10 +1095,22 @@ static int rpciod_start(void)
 	 * Create the rpciod thread and wait for it to start.
 	 */
 	dprintk("RPC:       creating workqueue rpciod\n");
-	/* Note: highpri because network receive is latency sensitive */
-	wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+	wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM, 0);
+	if (!wq)
+		goto out_failed;
 	rpciod_workqueue = wq;
-	return rpciod_workqueue != NULL;
+	/* Note: highpri because network receive is latency sensitive */
+	wq = alloc_workqueue("xprtiod", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+	if (!wq)
+		goto free_rpciod;
+	xprtiod_workqueue = wq;
+	return 1;
+free_rpciod:
+	wq = rpciod_workqueue;
+	rpciod_workqueue = NULL;
+	destroy_workqueue(wq);
+out_failed:
+	return 0;
 }
 
 static void rpciod_stop(void)
@@ -1088,6 +1124,9 @@ static void rpciod_stop(void)
 	wq = rpciod_workqueue;
 	rpciod_workqueue = NULL;
 	destroy_workqueue(wq);
+	wq = xprtiod_workqueue;
+	xprtiod_workqueue = NULL;
+	destroy_workqueue(wq);
 }
 
 void
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index cc9852897395..c5b0cb4f4056 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1188,11 +1188,17 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 
 		/* Encode reply */
-		if (test_bit(RQ_DROPME, &rqstp->rq_flags)) {
+		if (*statp == rpc_drop_reply ||
+		    test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 			if (procp->pc_release)
 				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
 			goto dropit;
 		}
+		if (*statp == rpc_autherr_badcred) {
+			if (procp->pc_release)
+				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+			goto err_bad_auth;
+		}
 		if (*statp == rpc_success &&
 		    (xdr = procp->pc_encode) &&
 		    !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) {
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 216a1385718a..8313960cac52 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -220,7 +220,7 @@ static void xprt_clear_locked(struct rpc_xprt *xprt)
 		clear_bit(XPRT_LOCKED, &xprt->state);
 		smp_mb__after_atomic();
 	} else
-		queue_work(rpciod_workqueue, &xprt->task_cleanup);
+		queue_work(xprtiod_workqueue, &xprt->task_cleanup);
 }
 
 /*
@@ -295,7 +295,8 @@ static void __xprt_lock_write_next(struct rpc_xprt *xprt)
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
 		return;
 
-	if (rpc_wake_up_first(&xprt->sending, __xprt_lock_write_func, xprt))
+	if (rpc_wake_up_first_on_wq(xprtiod_workqueue, &xprt->sending,
+				__xprt_lock_write_func, xprt))
 		return;
 	xprt_clear_locked(xprt);
 }
@@ -324,7 +325,8 @@ static void __xprt_lock_write_next_cong(struct rpc_xprt *xprt)
 		return;
 	if (RPCXPRT_CONGESTED(xprt))
 		goto out_unlock;
-	if (rpc_wake_up_first(&xprt->sending, __xprt_lock_write_cong_func, xprt))
+	if (rpc_wake_up_first_on_wq(xprtiod_workqueue, &xprt->sending,
+				__xprt_lock_write_cong_func, xprt))
 		return;
 out_unlock:
 	xprt_clear_locked(xprt);
@@ -645,7 +647,7 @@ void xprt_force_disconnect(struct rpc_xprt *xprt)
 	set_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	/* Try to schedule an autoclose RPC call */
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
-		queue_work(rpciod_workqueue, &xprt->task_cleanup);
+		queue_work(xprtiod_workqueue, &xprt->task_cleanup);
 	xprt_wake_pending_tasks(xprt, -EAGAIN);
 	spin_unlock_bh(&xprt->transport_lock);
 }
@@ -672,7 +674,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie)
 	set_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	/* Try to schedule an autoclose RPC call */
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
-		queue_work(rpciod_workqueue, &xprt->task_cleanup);
+		queue_work(xprtiod_workqueue, &xprt->task_cleanup);
 	xprt_wake_pending_tasks(xprt, -EAGAIN);
 out:
 	spin_unlock_bh(&xprt->transport_lock);
@@ -689,7 +691,7 @@ xprt_init_autodisconnect(unsigned long data)
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
 		goto out_abort;
 	spin_unlock(&xprt->transport_lock);
-	queue_work(rpciod_workqueue, &xprt->task_cleanup);
+	queue_work(xprtiod_workqueue, &xprt->task_cleanup);
 	return;
 out_abort:
 	spin_unlock(&xprt->transport_lock);
diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c
index e7fd76975d86..66c9d63f4797 100644
--- a/net/sunrpc/xprtmultipath.c
+++ b/net/sunrpc/xprtmultipath.c
@@ -271,14 +271,12 @@ struct rpc_xprt *xprt_iter_next_entry_multiple(struct rpc_xprt_iter *xpi,
 		xprt_switch_find_xprt_t find_next)
 {
 	struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch);
-	struct list_head *head;
 
 	if (xps == NULL)
 		return NULL;
-	head = &xps->xps_xprt_list;
-	if (xps->xps_nxprts < 2)
-		return xprt_switch_find_first_entry(head);
-	return xprt_switch_set_next_cursor(head, &xpi->xpi_cursor, find_next);
+	return xprt_switch_set_next_cursor(&xps->xps_xprt_list,
+			&xpi->xpi_cursor,
+			find_next);
 }
 
 static
diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile
index dc9f3b513a05..ef19fa42c50f 100644
--- a/net/sunrpc/xprtrdma/Makefile
+++ b/net/sunrpc/xprtrdma/Makefile
@@ -1,7 +1,7 @@
 obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o
 
 rpcrdma-y := transport.o rpc_rdma.o verbs.o \
-	fmr_ops.o frwr_ops.o physical_ops.o \
+	fmr_ops.o frwr_ops.o \
 	svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \
 	svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \
 	module.o
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index 6326ebe8b595..21cb3b150b37 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -19,13 +19,6 @@
  * verb (fmr_op_unmap).
  */
 
-/* Transport recovery
- *
- * After a transport reconnect, fmr_op_map re-uses the MR already
- * allocated for the RPC, but generates a fresh rkey then maps the
- * MR again. This process is synchronous.
- */
-
 #include "xprt_rdma.h"
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
@@ -35,62 +28,132 @@
 /* Maximum scatter/gather per FMR */
 #define RPCRDMA_MAX_FMR_SGES	(64)
 
-static struct workqueue_struct *fmr_recovery_wq;
-
-#define FMR_RECOVERY_WQ_FLAGS		(WQ_UNBOUND)
+/* Access mode of externally registered pages */
+enum {
+	RPCRDMA_FMR_ACCESS_FLAGS	= IB_ACCESS_REMOTE_WRITE |
+					  IB_ACCESS_REMOTE_READ,
+};
 
-int
-fmr_alloc_recovery_wq(void)
+bool
+fmr_is_supported(struct rpcrdma_ia *ia)
 {
-	fmr_recovery_wq = alloc_workqueue("fmr_recovery", WQ_UNBOUND, 0);
-	return !fmr_recovery_wq ? -ENOMEM : 0;
+	if (!ia->ri_device->alloc_fmr) {
+		pr_info("rpcrdma: 'fmr' mode is not supported by device %s\n",
+			ia->ri_device->name);
+		return false;
+	}
+	return true;
 }
 
-void
-fmr_destroy_recovery_wq(void)
+static int
+fmr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *mw)
 {
-	struct workqueue_struct *wq;
+	static struct ib_fmr_attr fmr_attr = {
+		.max_pages	= RPCRDMA_MAX_FMR_SGES,
+		.max_maps	= 1,
+		.page_shift	= PAGE_SHIFT
+	};
 
-	if (!fmr_recovery_wq)
-		return;
+	mw->fmr.fm_physaddrs = kcalloc(RPCRDMA_MAX_FMR_SGES,
+				       sizeof(u64), GFP_KERNEL);
+	if (!mw->fmr.fm_physaddrs)
+		goto out_free;
 
-	wq = fmr_recovery_wq;
-	fmr_recovery_wq = NULL;
-	destroy_workqueue(wq);
+	mw->mw_sg = kcalloc(RPCRDMA_MAX_FMR_SGES,
+			    sizeof(*mw->mw_sg), GFP_KERNEL);
+	if (!mw->mw_sg)
+		goto out_free;
+
+	sg_init_table(mw->mw_sg, RPCRDMA_MAX_FMR_SGES);
+
+	mw->fmr.fm_mr = ib_alloc_fmr(ia->ri_pd, RPCRDMA_FMR_ACCESS_FLAGS,
+				     &fmr_attr);
+	if (IS_ERR(mw->fmr.fm_mr))
+		goto out_fmr_err;
+
+	return 0;
+
+out_fmr_err:
+	dprintk("RPC:       %s: ib_alloc_fmr returned %ld\n", __func__,
+		PTR_ERR(mw->fmr.fm_mr));
+
+out_free:
+	kfree(mw->mw_sg);
+	kfree(mw->fmr.fm_physaddrs);
+	return -ENOMEM;
 }
 
 static int
 __fmr_unmap(struct rpcrdma_mw *mw)
 {
 	LIST_HEAD(l);
+	int rc;
 
-	list_add(&mw->fmr.fmr->list, &l);
-	return ib_unmap_fmr(&l);
+	list_add(&mw->fmr.fm_mr->list, &l);
+	rc = ib_unmap_fmr(&l);
+	list_del_init(&mw->fmr.fm_mr->list);
+	return rc;
 }
 
-/* Deferred reset of a single FMR. Generate a fresh rkey by
- * replacing the MR. There's no recovery if this fails.
- */
 static void
-__fmr_recovery_worker(struct work_struct *work)
+fmr_op_release_mr(struct rpcrdma_mw *r)
 {
-	struct rpcrdma_mw *mw = container_of(work, struct rpcrdma_mw,
-					    mw_work);
-	struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
+	LIST_HEAD(unmap_list);
+	int rc;
 
-	__fmr_unmap(mw);
-	rpcrdma_put_mw(r_xprt, mw);
-	return;
+	/* Ensure MW is not on any rl_registered list */
+	if (!list_empty(&r->mw_list))
+		list_del(&r->mw_list);
+
+	kfree(r->fmr.fm_physaddrs);
+	kfree(r->mw_sg);
+
+	/* In case this one was left mapped, try to unmap it
+	 * to prevent dealloc_fmr from failing with EBUSY
+	 */
+	rc = __fmr_unmap(r);
+	if (rc)
+		pr_err("rpcrdma: final ib_unmap_fmr for %p failed %i\n",
+		       r, rc);
+
+	rc = ib_dealloc_fmr(r->fmr.fm_mr);
+	if (rc)
+		pr_err("rpcrdma: final ib_dealloc_fmr for %p returned %i\n",
+		       r, rc);
+
+	kfree(r);
 }
 
-/* A broken MR was discovered in a context that can't sleep.
- * Defer recovery to the recovery worker.
+/* Reset of a single FMR.
  */
 static void
-__fmr_queue_recovery(struct rpcrdma_mw *mw)
+fmr_op_recover_mr(struct rpcrdma_mw *mw)
 {
-	INIT_WORK(&mw->mw_work, __fmr_recovery_worker);
-	queue_work(fmr_recovery_wq, &mw->mw_work);
+	struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
+	int rc;
+
+	/* ORDER: invalidate first */
+	rc = __fmr_unmap(mw);
+
+	/* ORDER: then DMA unmap */
+	ib_dma_unmap_sg(r_xprt->rx_ia.ri_device,
+			mw->mw_sg, mw->mw_nents, mw->mw_dir);
+	if (rc)
+		goto out_release;
+
+	rpcrdma_put_mw(r_xprt, mw);
+	r_xprt->rx_stats.mrs_recovered++;
+	return;
+
+out_release:
+	pr_err("rpcrdma: FMR reset failed (%d), %p released\n", rc, mw);
+	r_xprt->rx_stats.mrs_orphaned++;
+
+	spin_lock(&r_xprt->rx_buf.rb_mwlock);
+	list_del(&mw->mw_all);
+	spin_unlock(&r_xprt->rx_buf.rb_mwlock);
+
+	fmr_op_release_mr(mw);
 }
 
 static int
@@ -112,86 +175,21 @@ fmr_op_maxpages(struct rpcrdma_xprt *r_xprt)
 		     RPCRDMA_MAX_HDR_SEGS * RPCRDMA_MAX_FMR_SGES);
 }
 
-static int
-fmr_op_init(struct rpcrdma_xprt *r_xprt)
-{
-	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-	int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ;
-	struct ib_fmr_attr fmr_attr = {
-		.max_pages	= RPCRDMA_MAX_FMR_SGES,
-		.max_maps	= 1,
-		.page_shift	= PAGE_SHIFT
-	};
-	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
-	struct rpcrdma_mw *r;
-	int i, rc;
-
-	spin_lock_init(&buf->rb_mwlock);
-	INIT_LIST_HEAD(&buf->rb_mws);
-	INIT_LIST_HEAD(&buf->rb_all);
-
-	i = max_t(int, RPCRDMA_MAX_DATA_SEGS / RPCRDMA_MAX_FMR_SGES, 1);
-	i += 2;				/* head + tail */
-	i *= buf->rb_max_requests;	/* one set for each RPC slot */
-	dprintk("RPC:       %s: initalizing %d FMRs\n", __func__, i);
-
-	rc = -ENOMEM;
-	while (i--) {
-		r = kzalloc(sizeof(*r), GFP_KERNEL);
-		if (!r)
-			goto out;
-
-		r->fmr.physaddrs = kmalloc(RPCRDMA_MAX_FMR_SGES *
-					   sizeof(u64), GFP_KERNEL);
-		if (!r->fmr.physaddrs)
-			goto out_free;
-
-		r->fmr.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr);
-		if (IS_ERR(r->fmr.fmr))
-			goto out_fmr_err;
-
-		r->mw_xprt = r_xprt;
-		list_add(&r->mw_list, &buf->rb_mws);
-		list_add(&r->mw_all, &buf->rb_all);
-	}
-	return 0;
-
-out_fmr_err:
-	rc = PTR_ERR(r->fmr.fmr);
-	dprintk("RPC:       %s: ib_alloc_fmr status %i\n", __func__, rc);
-	kfree(r->fmr.physaddrs);
-out_free:
-	kfree(r);
-out:
-	return rc;
-}
-
 /* Use the ib_map_phys_fmr() verb to register a memory region
  * for remote access via RDMA READ or RDMA WRITE.
  */
 static int
 fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
-	   int nsegs, bool writing)
+	   int nsegs, bool writing, struct rpcrdma_mw **out)
 {
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct ib_device *device = ia->ri_device;
-	enum dma_data_direction direction = rpcrdma_data_dir(writing);
 	struct rpcrdma_mr_seg *seg1 = seg;
 	int len, pageoff, i, rc;
 	struct rpcrdma_mw *mw;
+	u64 *dma_pages;
 
-	mw = seg1->rl_mw;
-	seg1->rl_mw = NULL;
-	if (!mw) {
-		mw = rpcrdma_get_mw(r_xprt);
-		if (!mw)
-			return -ENOMEM;
-	} else {
-		/* this is a retransmit; generate a fresh rkey */
-		rc = __fmr_unmap(mw);
-		if (rc)
-			return rc;
-	}
+	mw = rpcrdma_get_mw(r_xprt);
+	if (!mw)
+		return -ENOBUFS;
 
 	pageoff = offset_in_page(seg1->mr_offset);
 	seg1->mr_offset -= pageoff;	/* start of page */
@@ -200,8 +198,14 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 	if (nsegs > RPCRDMA_MAX_FMR_SGES)
 		nsegs = RPCRDMA_MAX_FMR_SGES;
 	for (i = 0; i < nsegs;) {
-		rpcrdma_map_one(device, seg, direction);
-		mw->fmr.physaddrs[i] = seg->mr_dma;
+		if (seg->mr_page)
+			sg_set_page(&mw->mw_sg[i],
+				    seg->mr_page,
+				    seg->mr_len,
+				    offset_in_page(seg->mr_offset));
+		else
+			sg_set_buf(&mw->mw_sg[i], seg->mr_offset,
+				   seg->mr_len);
 		len += seg->mr_len;
 		++seg;
 		++i;
@@ -210,49 +214,54 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
 			break;
 	}
-
-	rc = ib_map_phys_fmr(mw->fmr.fmr, mw->fmr.physaddrs,
-			     i, seg1->mr_dma);
+	mw->mw_nents = i;
+	mw->mw_dir = rpcrdma_data_dir(writing);
+	if (i == 0)
+		goto out_dmamap_err;
+
+	if (!ib_dma_map_sg(r_xprt->rx_ia.ri_device,
+			   mw->mw_sg, mw->mw_nents, mw->mw_dir))
+		goto out_dmamap_err;
+
+	for (i = 0, dma_pages = mw->fmr.fm_physaddrs; i < mw->mw_nents; i++)
+		dma_pages[i] = sg_dma_address(&mw->mw_sg[i]);
+	rc = ib_map_phys_fmr(mw->fmr.fm_mr, dma_pages, mw->mw_nents,
+			     dma_pages[0]);
 	if (rc)
 		goto out_maperr;
 
-	seg1->rl_mw = mw;
-	seg1->mr_rkey = mw->fmr.fmr->rkey;
-	seg1->mr_base = seg1->mr_dma + pageoff;
-	seg1->mr_nsegs = i;
-	seg1->mr_len = len;
-	return i;
+	mw->mw_handle = mw->fmr.fm_mr->rkey;
+	mw->mw_length = len;
+	mw->mw_offset = dma_pages[0] + pageoff;
 
-out_maperr:
-	dprintk("RPC:       %s: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n",
-		__func__, len, (unsigned long long)seg1->mr_dma,
-		pageoff, i, rc);
-	while (i--)
-		rpcrdma_unmap_one(device, --seg);
-	return rc;
-}
+	*out = mw;
+	return mw->mw_nents;
 
-static void
-__fmr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
-{
-	struct ib_device *device = r_xprt->rx_ia.ri_device;
-	int nsegs = seg->mr_nsegs;
+out_dmamap_err:
+	pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n",
+	       mw->mw_sg, mw->mw_nents);
+	rpcrdma_defer_mr_recovery(mw);
+	return -EIO;
 
-	while (nsegs--)
-		rpcrdma_unmap_one(device, seg++);
+out_maperr:
+	pr_err("rpcrdma: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n",
+	       len, (unsigned long long)dma_pages[0],
+	       pageoff, mw->mw_nents, rc);
+	rpcrdma_defer_mr_recovery(mw);
+	return -EIO;
 }
 
 /* Invalidate all memory regions that were registered for "req".
  *
  * Sleeps until it is safe for the host CPU to access the
  * previously mapped memory regions.
+ *
+ * Caller ensures that req->rl_registered is not empty.
  */
 static void
 fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
-	struct rpcrdma_mr_seg *seg;
-	unsigned int i, nchunks;
-	struct rpcrdma_mw *mw;
+	struct rpcrdma_mw *mw, *tmp;
 	LIST_HEAD(unmap_list);
 	int rc;
 
@@ -261,90 +270,54 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	/* ORDER: Invalidate all of the req's MRs first
 	 *
 	 * ib_unmap_fmr() is slow, so use a single call instead
-	 * of one call per mapped MR.
+	 * of one call per mapped FMR.
 	 */
-	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
-		seg = &req->rl_segments[i];
-		mw = seg->rl_mw;
-
-		list_add(&mw->fmr.fmr->list, &unmap_list);
-
-		i += seg->mr_nsegs;
-	}
+	list_for_each_entry(mw, &req->rl_registered, mw_list)
+		list_add_tail(&mw->fmr.fm_mr->list, &unmap_list);
 	rc = ib_unmap_fmr(&unmap_list);
 	if (rc)
-		pr_warn("%s: ib_unmap_fmr failed (%i)\n", __func__, rc);
+		goto out_reset;
 
 	/* ORDER: Now DMA unmap all of the req's MRs, and return
 	 * them to the free MW list.
 	 */
-	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
-		seg = &req->rl_segments[i];
+	list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) {
+		list_del_init(&mw->mw_list);
+		list_del_init(&mw->fmr.fm_mr->list);
+		ib_dma_unmap_sg(r_xprt->rx_ia.ri_device,
+				mw->mw_sg, mw->mw_nents, mw->mw_dir);
+		rpcrdma_put_mw(r_xprt, mw);
+	}
 
-		__fmr_dma_unmap(r_xprt, seg);
-		rpcrdma_put_mw(r_xprt, seg->rl_mw);
+	return;
 
-		i += seg->mr_nsegs;
-		seg->mr_nsegs = 0;
-		seg->rl_mw = NULL;
-	}
+out_reset:
+	pr_err("rpcrdma: ib_unmap_fmr failed (%i)\n", rc);
 
-	req->rl_nchunks = 0;
+	list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) {
+		list_del_init(&mw->fmr.fm_mr->list);
+		fmr_op_recover_mr(mw);
+	}
 }
 
 /* Use a slow, safe mechanism to invalidate all memory regions
  * that were registered for "req".
- *
- * In the asynchronous case, DMA unmapping occurs first here
- * because the rpcrdma_mr_seg is released immediately after this
- * call. It's contents won't be available in __fmr_dma_unmap later.
- * FIXME.
  */
 static void
 fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		  bool sync)
 {
-	struct rpcrdma_mr_seg *seg;
 	struct rpcrdma_mw *mw;
-	unsigned int i;
-
-	for (i = 0; req->rl_nchunks; req->rl_nchunks--) {
-		seg = &req->rl_segments[i];
-		mw = seg->rl_mw;
-
-		if (sync) {
-			/* ORDER */
-			__fmr_unmap(mw);
-			__fmr_dma_unmap(r_xprt, seg);
-			rpcrdma_put_mw(r_xprt, mw);
-		} else {
-			__fmr_dma_unmap(r_xprt, seg);
-			__fmr_queue_recovery(mw);
-		}
-
-		i += seg->mr_nsegs;
-		seg->mr_nsegs = 0;
-		seg->rl_mw = NULL;
-	}
-}
-
-static void
-fmr_op_destroy(struct rpcrdma_buffer *buf)
-{
-	struct rpcrdma_mw *r;
-	int rc;
-
-	while (!list_empty(&buf->rb_all)) {
-		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
-		list_del(&r->mw_all);
-		kfree(r->fmr.physaddrs);
 
-		rc = ib_dealloc_fmr(r->fmr.fmr);
-		if (rc)
-			dprintk("RPC:       %s: ib_dealloc_fmr failed %i\n",
-				__func__, rc);
+	while (!list_empty(&req->rl_registered)) {
+		mw = list_first_entry(&req->rl_registered,
+				      struct rpcrdma_mw, mw_list);
+		list_del_init(&mw->mw_list);
 
-		kfree(r);
+		if (sync)
+			fmr_op_recover_mr(mw);
+		else
+			rpcrdma_defer_mr_recovery(mw);
 	}
 }
 
@@ -352,9 +325,10 @@ const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = {
 	.ro_map				= fmr_op_map,
 	.ro_unmap_sync			= fmr_op_unmap_sync,
 	.ro_unmap_safe			= fmr_op_unmap_safe,
+	.ro_recover_mr			= fmr_op_recover_mr,
 	.ro_open			= fmr_op_open,
 	.ro_maxpages			= fmr_op_maxpages,
-	.ro_init			= fmr_op_init,
-	.ro_destroy			= fmr_op_destroy,
+	.ro_init_mr			= fmr_op_init_mr,
+	.ro_release_mr			= fmr_op_release_mr,
 	.ro_displayname			= "fmr",
 };
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index c0947544babe..892b5e1d9b09 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -73,29 +73,71 @@
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
-static struct workqueue_struct *frwr_recovery_wq;
-
-#define FRWR_RECOVERY_WQ_FLAGS		(WQ_UNBOUND | WQ_MEM_RECLAIM)
+bool
+frwr_is_supported(struct rpcrdma_ia *ia)
+{
+	struct ib_device_attr *attrs = &ia->ri_device->attrs;
+
+	if (!(attrs->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS))
+		goto out_not_supported;
+	if (attrs->max_fast_reg_page_list_len == 0)
+		goto out_not_supported;
+	return true;
+
+out_not_supported:
+	pr_info("rpcrdma: 'frwr' mode is not supported by device %s\n",
+		ia->ri_device->name);
+	return false;
+}
 
-int
-frwr_alloc_recovery_wq(void)
+static int
+frwr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r)
 {
-	frwr_recovery_wq = alloc_workqueue("frwr_recovery",
-					   FRWR_RECOVERY_WQ_FLAGS, 0);
-	return !frwr_recovery_wq ? -ENOMEM : 0;
+	unsigned int depth = ia->ri_max_frmr_depth;
+	struct rpcrdma_frmr *f = &r->frmr;
+	int rc;
+
+	f->fr_mr = ib_alloc_mr(ia->ri_pd, IB_MR_TYPE_MEM_REG, depth);
+	if (IS_ERR(f->fr_mr))
+		goto out_mr_err;
+
+	r->mw_sg = kcalloc(depth, sizeof(*r->mw_sg), GFP_KERNEL);
+	if (!r->mw_sg)
+		goto out_list_err;
+
+	sg_init_table(r->mw_sg, depth);
+	init_completion(&f->fr_linv_done);
+	return 0;
+
+out_mr_err:
+	rc = PTR_ERR(f->fr_mr);
+	dprintk("RPC:       %s: ib_alloc_mr status %i\n",
+		__func__, rc);
+	return rc;
+
+out_list_err:
+	rc = -ENOMEM;
+	dprintk("RPC:       %s: sg allocation failure\n",
+		__func__);
+	ib_dereg_mr(f->fr_mr);
+	return rc;
 }
 
-void
-frwr_destroy_recovery_wq(void)
+static void
+frwr_op_release_mr(struct rpcrdma_mw *r)
 {
-	struct workqueue_struct *wq;
+	int rc;
 
-	if (!frwr_recovery_wq)
-		return;
+	/* Ensure MW is not on any rl_registered list */
+	if (!list_empty(&r->mw_list))
+		list_del(&r->mw_list);
 
-	wq = frwr_recovery_wq;
-	frwr_recovery_wq = NULL;
-	destroy_workqueue(wq);
+	rc = ib_dereg_mr(r->frmr.fr_mr);
+	if (rc)
+		pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n",
+		       r, rc);
+	kfree(r->mw_sg);
+	kfree(r);
 }
 
 static int
@@ -124,93 +166,37 @@ __frwr_reset_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r)
 	return 0;
 }
 
-static void
-__frwr_reset_and_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mw *mw)
-{
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct rpcrdma_frmr *f = &mw->frmr;
-	int rc;
-
-	rc = __frwr_reset_mr(ia, mw);
-	ib_dma_unmap_sg(ia->ri_device, f->fr_sg, f->fr_nents, f->fr_dir);
-	if (rc)
-		return;
-
-	rpcrdma_put_mw(r_xprt, mw);
-}
-
-/* Deferred reset of a single FRMR. Generate a fresh rkey by
- * replacing the MR.
+/* Reset of a single FRMR. Generate a fresh rkey by replacing the MR.
  *
  * There's no recovery if this fails. The FRMR is abandoned, but
  * remains in rb_all. It will be cleaned up when the transport is
  * destroyed.
  */
 static void
-__frwr_recovery_worker(struct work_struct *work)
-{
-	struct rpcrdma_mw *r = container_of(work, struct rpcrdma_mw,
-					    mw_work);
-
-	__frwr_reset_and_unmap(r->mw_xprt, r);
-	return;
-}
-
-/* A broken MR was discovered in a context that can't sleep.
- * Defer recovery to the recovery worker.
- */
-static void
-__frwr_queue_recovery(struct rpcrdma_mw *r)
-{
-	INIT_WORK(&r->mw_work, __frwr_recovery_worker);
-	queue_work(frwr_recovery_wq, &r->mw_work);
-}
-
-static int
-__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device,
-	    unsigned int depth)
+frwr_op_recover_mr(struct rpcrdma_mw *mw)
 {
-	struct rpcrdma_frmr *f = &r->frmr;
+	struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	int rc;
 
-	f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth);
-	if (IS_ERR(f->fr_mr))
-		goto out_mr_err;
-
-	f->fr_sg = kcalloc(depth, sizeof(*f->fr_sg), GFP_KERNEL);
-	if (!f->fr_sg)
-		goto out_list_err;
-
-	sg_init_table(f->fr_sg, depth);
-
-	init_completion(&f->fr_linv_done);
-
-	return 0;
+	rc = __frwr_reset_mr(ia, mw);
+	ib_dma_unmap_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir);
+	if (rc)
+		goto out_release;
 
-out_mr_err:
-	rc = PTR_ERR(f->fr_mr);
-	dprintk("RPC:       %s: ib_alloc_mr status %i\n",
-		__func__, rc);
-	return rc;
+	rpcrdma_put_mw(r_xprt, mw);
+	r_xprt->rx_stats.mrs_recovered++;
+	return;
 
-out_list_err:
-	rc = -ENOMEM;
-	dprintk("RPC:       %s: sg allocation failure\n",
-		__func__);
-	ib_dereg_mr(f->fr_mr);
-	return rc;
-}
+out_release:
+	pr_err("rpcrdma: FRMR reset failed %d, %p release\n", rc, mw);
+	r_xprt->rx_stats.mrs_orphaned++;
 
-static void
-__frwr_release(struct rpcrdma_mw *r)
-{
-	int rc;
+	spin_lock(&r_xprt->rx_buf.rb_mwlock);
+	list_del(&mw->mw_all);
+	spin_unlock(&r_xprt->rx_buf.rb_mwlock);
 
-	rc = ib_dereg_mr(r->frmr.fr_mr);
-	if (rc)
-		dprintk("RPC:       %s: ib_dereg_mr status %i\n",
-			__func__, rc);
-	kfree(r->frmr.fr_sg);
+	frwr_op_release_mr(mw);
 }
 
 static int
@@ -346,57 +332,14 @@ frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc)
 	complete_all(&frmr->fr_linv_done);
 }
 
-static int
-frwr_op_init(struct rpcrdma_xprt *r_xprt)
-{
-	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-	struct ib_device *device = r_xprt->rx_ia.ri_device;
-	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
-	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
-	int i;
-
-	spin_lock_init(&buf->rb_mwlock);
-	INIT_LIST_HEAD(&buf->rb_mws);
-	INIT_LIST_HEAD(&buf->rb_all);
-
-	i = max_t(int, RPCRDMA_MAX_DATA_SEGS / depth, 1);
-	i += 2;				/* head + tail */
-	i *= buf->rb_max_requests;	/* one set for each RPC slot */
-	dprintk("RPC:       %s: initalizing %d FRMRs\n", __func__, i);
-
-	while (i--) {
-		struct rpcrdma_mw *r;
-		int rc;
-
-		r = kzalloc(sizeof(*r), GFP_KERNEL);
-		if (!r)
-			return -ENOMEM;
-
-		rc = __frwr_init(r, pd, device, depth);
-		if (rc) {
-			kfree(r);
-			return rc;
-		}
-
-		r->mw_xprt = r_xprt;
-		list_add(&r->mw_list, &buf->rb_mws);
-		list_add(&r->mw_all, &buf->rb_all);
-	}
-
-	return 0;
-}
-
-/* Post a FAST_REG Work Request to register a memory region
+/* Post a REG_MR Work Request to register a memory region
  * for remote access via RDMA READ or RDMA WRITE.
  */
 static int
 frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
-	    int nsegs, bool writing)
+	    int nsegs, bool writing, struct rpcrdma_mw **out)
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct ib_device *device = ia->ri_device;
-	enum dma_data_direction direction = rpcrdma_data_dir(writing);
-	struct rpcrdma_mr_seg *seg1 = seg;
 	struct rpcrdma_mw *mw;
 	struct rpcrdma_frmr *frmr;
 	struct ib_mr *mr;
@@ -405,14 +348,13 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 	int rc, i, n, dma_nents;
 	u8 key;
 
-	mw = seg1->rl_mw;
-	seg1->rl_mw = NULL;
+	mw = NULL;
 	do {
 		if (mw)
-			__frwr_queue_recovery(mw);
+			rpcrdma_defer_mr_recovery(mw);
 		mw = rpcrdma_get_mw(r_xprt);
 		if (!mw)
-			return -ENOMEM;
+			return -ENOBUFS;
 	} while (mw->frmr.fr_state != FRMR_IS_INVALID);
 	frmr = &mw->frmr;
 	frmr->fr_state = FRMR_IS_VALID;
@@ -421,15 +363,14 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 
 	if (nsegs > ia->ri_max_frmr_depth)
 		nsegs = ia->ri_max_frmr_depth;
-
 	for (i = 0; i < nsegs;) {
 		if (seg->mr_page)
-			sg_set_page(&frmr->fr_sg[i],
+			sg_set_page(&mw->mw_sg[i],
 				    seg->mr_page,
 				    seg->mr_len,
 				    offset_in_page(seg->mr_offset));
 		else
-			sg_set_buf(&frmr->fr_sg[i], seg->mr_offset,
+			sg_set_buf(&mw->mw_sg[i], seg->mr_offset,
 				   seg->mr_len);
 
 		++seg;
@@ -440,26 +381,22 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
 			break;
 	}
-	frmr->fr_nents = i;
-	frmr->fr_dir = direction;
-
-	dma_nents = ib_dma_map_sg(device, frmr->fr_sg, frmr->fr_nents, direction);
-	if (!dma_nents) {
-		pr_err("RPC:       %s: failed to dma map sg %p sg_nents %u\n",
-		       __func__, frmr->fr_sg, frmr->fr_nents);
-		return -ENOMEM;
-	}
+	mw->mw_nents = i;
+	mw->mw_dir = rpcrdma_data_dir(writing);
+	if (i == 0)
+		goto out_dmamap_err;
 
-	n = ib_map_mr_sg(mr, frmr->fr_sg, frmr->fr_nents, NULL, PAGE_SIZE);
-	if (unlikely(n != frmr->fr_nents)) {
-		pr_err("RPC:       %s: failed to map mr %p (%u/%u)\n",
-		       __func__, frmr->fr_mr, n, frmr->fr_nents);
-		rc = n < 0 ? n : -EINVAL;
-		goto out_senderr;
-	}
+	dma_nents = ib_dma_map_sg(ia->ri_device,
+				  mw->mw_sg, mw->mw_nents, mw->mw_dir);
+	if (!dma_nents)
+		goto out_dmamap_err;
+
+	n = ib_map_mr_sg(mr, mw->mw_sg, mw->mw_nents, NULL, PAGE_SIZE);
+	if (unlikely(n != mw->mw_nents))
+		goto out_mapmr_err;
 
 	dprintk("RPC:       %s: Using frmr %p to map %u segments (%u bytes)\n",
-		__func__, mw, frmr->fr_nents, mr->length);
+		__func__, mw, mw->mw_nents, mr->length);
 
 	key = (u8)(mr->rkey & 0x000000FF);
 	ib_update_fast_reg_key(mr, ++key);
@@ -481,24 +418,34 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 	if (rc)
 		goto out_senderr;
 
-	seg1->rl_mw = mw;
-	seg1->mr_rkey = mr->rkey;
-	seg1->mr_base = mr->iova;
-	seg1->mr_nsegs = frmr->fr_nents;
-	seg1->mr_len = mr->length;
+	mw->mw_handle = mr->rkey;
+	mw->mw_length = mr->length;
+	mw->mw_offset = mr->iova;
+
+	*out = mw;
+	return mw->mw_nents;
 
-	return frmr->fr_nents;
+out_dmamap_err:
+	pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n",
+	       mw->mw_sg, mw->mw_nents);
+	rpcrdma_defer_mr_recovery(mw);
+	return -EIO;
+
+out_mapmr_err:
+	pr_err("rpcrdma: failed to map mr %p (%u/%u)\n",
+	       frmr->fr_mr, n, mw->mw_nents);
+	rpcrdma_defer_mr_recovery(mw);
+	return -EIO;
 
 out_senderr:
-	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
-	__frwr_queue_recovery(mw);
-	return rc;
+	pr_err("rpcrdma: FRMR registration ib_post_send returned %i\n", rc);
+	rpcrdma_defer_mr_recovery(mw);
+	return -ENOTCONN;
 }
 
 static struct ib_send_wr *
-__frwr_prepare_linv_wr(struct rpcrdma_mr_seg *seg)
+__frwr_prepare_linv_wr(struct rpcrdma_mw *mw)
 {
-	struct rpcrdma_mw *mw = seg->rl_mw;
 	struct rpcrdma_frmr *f = &mw->frmr;
 	struct ib_send_wr *invalidate_wr;
 
@@ -518,16 +465,16 @@ __frwr_prepare_linv_wr(struct rpcrdma_mr_seg *seg)
  *
  * Sleeps until it is safe for the host CPU to access the
  * previously mapped memory regions.
+ *
+ * Caller ensures that req->rl_registered is not empty.
  */
 static void
 frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
 	struct ib_send_wr *invalidate_wrs, *pos, *prev, *bad_wr;
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct rpcrdma_mr_seg *seg;
-	unsigned int i, nchunks;
+	struct rpcrdma_mw *mw, *tmp;
 	struct rpcrdma_frmr *f;
-	struct rpcrdma_mw *mw;
 	int rc;
 
 	dprintk("RPC:       %s: req %p\n", __func__, req);
@@ -537,22 +484,18 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * Chain the LOCAL_INV Work Requests and post them with
 	 * a single ib_post_send() call.
 	 */
+	f = NULL;
 	invalidate_wrs = pos = prev = NULL;
-	seg = NULL;
-	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
-		seg = &req->rl_segments[i];
-
-		pos = __frwr_prepare_linv_wr(seg);
+	list_for_each_entry(mw, &req->rl_registered, mw_list) {
+		pos = __frwr_prepare_linv_wr(mw);
 
 		if (!invalidate_wrs)
 			invalidate_wrs = pos;
 		else
 			prev->next = pos;
 		prev = pos;
-
-		i += seg->mr_nsegs;
+		f = &mw->frmr;
 	}
-	f = &seg->rl_mw->frmr;
 
 	/* Strong send queue ordering guarantees that when the
 	 * last WR in the chain completes, all WRs in the chain
@@ -577,39 +520,27 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * them to the free MW list.
 	 */
 unmap:
-	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
-		seg = &req->rl_segments[i];
-		mw = seg->rl_mw;
-		seg->rl_mw = NULL;
-
-		ib_dma_unmap_sg(ia->ri_device, f->fr_sg, f->fr_nents,
-				f->fr_dir);
+	list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) {
+		list_del_init(&mw->mw_list);
+		ib_dma_unmap_sg(ia->ri_device,
+				mw->mw_sg, mw->mw_nents, mw->mw_dir);
 		rpcrdma_put_mw(r_xprt, mw);
-
-		i += seg->mr_nsegs;
-		seg->mr_nsegs = 0;
 	}
-
-	req->rl_nchunks = 0;
 	return;
 
 reset_mrs:
-	pr_warn("%s: ib_post_send failed %i\n", __func__, rc);
+	pr_err("rpcrdma: FRMR invalidate ib_post_send returned %i\n", rc);
+	rdma_disconnect(ia->ri_id);
 
 	/* Find and reset the MRs in the LOCAL_INV WRs that did not
 	 * get posted. This is synchronous, and slow.
 	 */
-	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
-		seg = &req->rl_segments[i];
-		mw = seg->rl_mw;
+	list_for_each_entry(mw, &req->rl_registered, mw_list) {
 		f = &mw->frmr;
-
 		if (mw->frmr.fr_mr->rkey == bad_wr->ex.invalidate_rkey) {
 			__frwr_reset_mr(ia, mw);
 			bad_wr = bad_wr->next;
 		}
-
-		i += seg->mr_nsegs;
 	}
 	goto unmap;
 }
@@ -621,38 +552,17 @@ static void
 frwr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		   bool sync)
 {
-	struct rpcrdma_mr_seg *seg;
 	struct rpcrdma_mw *mw;
-	unsigned int i;
 
-	for (i = 0; req->rl_nchunks; req->rl_nchunks--) {
-		seg = &req->rl_segments[i];
-		mw = seg->rl_mw;
+	while (!list_empty(&req->rl_registered)) {
+		mw = list_first_entry(&req->rl_registered,
+				      struct rpcrdma_mw, mw_list);
+		list_del_init(&mw->mw_list);
 
 		if (sync)
-			__frwr_reset_and_unmap(r_xprt, mw);
+			frwr_op_recover_mr(mw);
 		else
-			__frwr_queue_recovery(mw);
-
-		i += seg->mr_nsegs;
-		seg->mr_nsegs = 0;
-		seg->rl_mw = NULL;
-	}
-}
-
-static void
-frwr_op_destroy(struct rpcrdma_buffer *buf)
-{
-	struct rpcrdma_mw *r;
-
-	/* Ensure stale MWs for "buf" are no longer in flight */
-	flush_workqueue(frwr_recovery_wq);
-
-	while (!list_empty(&buf->rb_all)) {
-		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
-		list_del(&r->mw_all);
-		__frwr_release(r);
-		kfree(r);
+			rpcrdma_defer_mr_recovery(mw);
 	}
 }
 
@@ -660,9 +570,10 @@ const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = {
 	.ro_map				= frwr_op_map,
 	.ro_unmap_sync			= frwr_op_unmap_sync,
 	.ro_unmap_safe			= frwr_op_unmap_safe,
+	.ro_recover_mr			= frwr_op_recover_mr,
 	.ro_open			= frwr_op_open,
 	.ro_maxpages			= frwr_op_maxpages,
-	.ro_init			= frwr_op_init,
-	.ro_destroy			= frwr_op_destroy,
+	.ro_init_mr			= frwr_op_init_mr,
+	.ro_release_mr			= frwr_op_release_mr,
 	.ro_displayname			= "frwr",
 };
diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c
deleted file mode 100644
index 3750596cc432..000000000000
--- a/net/sunrpc/xprtrdma/physical_ops.c
+++ /dev/null
@@ -1,122 +0,0 @@
-/*
- * Copyright (c) 2015 Oracle.  All rights reserved.
- * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
- */
-
-/* No-op chunk preparation. All client memory is pre-registered.
- * Sometimes referred to as ALLPHYSICAL mode.
- *
- * Physical registration is simple because all client memory is
- * pre-registered and never deregistered. This mode is good for
- * adapter bring up, but is considered not safe: the server is
- * trusted not to abuse its access to client memory not involved
- * in RDMA I/O.
- */
-
-#include "xprt_rdma.h"
-
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-# define RPCDBG_FACILITY	RPCDBG_TRANS
-#endif
-
-static int
-physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
-		 struct rpcrdma_create_data_internal *cdata)
-{
-	struct ib_mr *mr;
-
-	/* Obtain an rkey to use for RPC data payloads.
-	 */
-	mr = ib_get_dma_mr(ia->ri_pd,
-			   IB_ACCESS_LOCAL_WRITE |
-			   IB_ACCESS_REMOTE_WRITE |
-			   IB_ACCESS_REMOTE_READ);
-	if (IS_ERR(mr)) {
-		pr_err("%s: ib_get_dma_mr for failed with %lX\n",
-		       __func__, PTR_ERR(mr));
-		return -ENOMEM;
-	}
-	ia->ri_dma_mr = mr;
-
-	rpcrdma_set_max_header_sizes(ia, cdata, min_t(unsigned int,
-						      RPCRDMA_MAX_DATA_SEGS,
-						      RPCRDMA_MAX_HDR_SEGS));
-	return 0;
-}
-
-/* PHYSICAL memory registration conveys one page per chunk segment.
- */
-static size_t
-physical_op_maxpages(struct rpcrdma_xprt *r_xprt)
-{
-	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
-		     RPCRDMA_MAX_HDR_SEGS);
-}
-
-static int
-physical_op_init(struct rpcrdma_xprt *r_xprt)
-{
-	return 0;
-}
-
-/* The client's physical memory is already exposed for
- * remote access via RDMA READ or RDMA WRITE.
- */
-static int
-physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
-		int nsegs, bool writing)
-{
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-
-	rpcrdma_map_one(ia->ri_device, seg, rpcrdma_data_dir(writing));
-	seg->mr_rkey = ia->ri_dma_mr->rkey;
-	seg->mr_base = seg->mr_dma;
-	return 1;
-}
-
-/* DMA unmap all memory regions that were mapped for "req".
- */
-static void
-physical_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
-{
-	struct ib_device *device = r_xprt->rx_ia.ri_device;
-	unsigned int i;
-
-	for (i = 0; req->rl_nchunks; --req->rl_nchunks)
-		rpcrdma_unmap_one(device, &req->rl_segments[i++]);
-}
-
-/* Use a slow, safe mechanism to invalidate all memory regions
- * that were registered for "req".
- *
- * For physical memory registration, there is no good way to
- * fence a single MR that has been advertised to the server. The
- * client has already handed the server an R_key that cannot be
- * invalidated and is shared by all MRs on this connection.
- * Tearing down the PD might be the only safe choice, but it's
- * not clear that a freshly acquired DMA R_key would be different
- * than the one used by the PD that was just destroyed.
- * FIXME.
- */
-static void
-physical_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
-		       bool sync)
-{
-	physical_op_unmap_sync(r_xprt, req);
-}
-
-static void
-physical_op_destroy(struct rpcrdma_buffer *buf)
-{
-}
-
-const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = {
-	.ro_map				= physical_op_map,
-	.ro_unmap_sync			= physical_op_unmap_sync,
-	.ro_unmap_safe			= physical_op_unmap_safe,
-	.ro_open			= physical_op_open,
-	.ro_maxpages			= physical_op_maxpages,
-	.ro_init			= physical_op_init,
-	.ro_destroy			= physical_op_destroy,
-	.ro_displayname			= "physical",
-};
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 35a81096e83d..a47f170b20ef 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -196,8 +196,7 @@ rpcrdma_tail_pullup(struct xdr_buf *buf)
  * MR when they can.
  */
 static int
-rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg,
-		     int n, int nsegs)
+rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, int n)
 {
 	size_t page_offset;
 	u32 remaining;
@@ -206,7 +205,7 @@ rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg,
 	base = vec->iov_base;
 	page_offset = offset_in_page(base);
 	remaining = vec->iov_len;
-	while (remaining && n < nsegs) {
+	while (remaining && n < RPCRDMA_MAX_SEGS) {
 		seg[n].mr_page = NULL;
 		seg[n].mr_offset = base;
 		seg[n].mr_len = min_t(u32, PAGE_SIZE - page_offset, remaining);
@@ -230,34 +229,34 @@ rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg,
 
 static int
 rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
-	enum rpcrdma_chunktype type, struct rpcrdma_mr_seg *seg, int nsegs)
+	enum rpcrdma_chunktype type, struct rpcrdma_mr_seg *seg)
 {
-	int len, n = 0, p;
-	int page_base;
+	int len, n, p, page_base;
 	struct page **ppages;
 
+	n = 0;
 	if (pos == 0) {
-		n = rpcrdma_convert_kvec(&xdrbuf->head[0], seg, n, nsegs);
-		if (n == nsegs)
-			return -EIO;
+		n = rpcrdma_convert_kvec(&xdrbuf->head[0], seg, n);
+		if (n == RPCRDMA_MAX_SEGS)
+			goto out_overflow;
 	}
 
 	len = xdrbuf->page_len;
 	ppages = xdrbuf->pages + (xdrbuf->page_base >> PAGE_SHIFT);
 	page_base = xdrbuf->page_base & ~PAGE_MASK;
 	p = 0;
-	while (len && n < nsegs) {
+	while (len && n < RPCRDMA_MAX_SEGS) {
 		if (!ppages[p]) {
 			/* alloc the pagelist for receiving buffer */
 			ppages[p] = alloc_page(GFP_ATOMIC);
 			if (!ppages[p])
-				return -ENOMEM;
+				return -EAGAIN;
 		}
 		seg[n].mr_page = ppages[p];
 		seg[n].mr_offset = (void *)(unsigned long) page_base;
 		seg[n].mr_len = min_t(u32, PAGE_SIZE - page_base, len);
 		if (seg[n].mr_len > PAGE_SIZE)
-			return -EIO;
+			goto out_overflow;
 		len -= seg[n].mr_len;
 		++n;
 		++p;
@@ -265,8 +264,8 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 	}
 
 	/* Message overflows the seg array */
-	if (len && n == nsegs)
-		return -EIO;
+	if (len && n == RPCRDMA_MAX_SEGS)
+		goto out_overflow;
 
 	/* When encoding the read list, the tail is always sent inline */
 	if (type == rpcrdma_readch)
@@ -277,20 +276,24 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 		 * xdr pad bytes, saving the server an RDMA operation. */
 		if (xdrbuf->tail[0].iov_len < 4 && xprt_rdma_pad_optimize)
 			return n;
-		n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n, nsegs);
-		if (n == nsegs)
-			return -EIO;
+		n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n);
+		if (n == RPCRDMA_MAX_SEGS)
+			goto out_overflow;
 	}
 
 	return n;
+
+out_overflow:
+	pr_err("rpcrdma: segment array overflow\n");
+	return -EIO;
 }
 
 static inline __be32 *
-xdr_encode_rdma_segment(__be32 *iptr, struct rpcrdma_mr_seg *seg)
+xdr_encode_rdma_segment(__be32 *iptr, struct rpcrdma_mw *mw)
 {
-	*iptr++ = cpu_to_be32(seg->mr_rkey);
-	*iptr++ = cpu_to_be32(seg->mr_len);
-	return xdr_encode_hyper(iptr, seg->mr_base);
+	*iptr++ = cpu_to_be32(mw->mw_handle);
+	*iptr++ = cpu_to_be32(mw->mw_length);
+	return xdr_encode_hyper(iptr, mw->mw_offset);
 }
 
 /* XDR-encode the Read list. Supports encoding a list of read
@@ -310,7 +313,8 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 			 struct rpcrdma_req *req, struct rpc_rqst *rqst,
 			 __be32 *iptr, enum rpcrdma_chunktype rtype)
 {
-	struct rpcrdma_mr_seg *seg = req->rl_nextseg;
+	struct rpcrdma_mr_seg *seg;
+	struct rpcrdma_mw *mw;
 	unsigned int pos;
 	int n, nsegs;
 
@@ -322,15 +326,17 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 	pos = rqst->rq_snd_buf.head[0].iov_len;
 	if (rtype == rpcrdma_areadch)
 		pos = 0;
-	nsegs = rpcrdma_convert_iovs(&rqst->rq_snd_buf, pos, rtype, seg,
-				     RPCRDMA_MAX_SEGS - req->rl_nchunks);
+	seg = req->rl_segments;
+	nsegs = rpcrdma_convert_iovs(&rqst->rq_snd_buf, pos, rtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
 	do {
-		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, false);
-		if (n <= 0)
+		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs,
+						 false, &mw);
+		if (n < 0)
 			return ERR_PTR(n);
+		list_add(&mw->mw_list, &req->rl_registered);
 
 		*iptr++ = xdr_one;	/* item present */
 
@@ -338,20 +344,17 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 		 * have the same "position".
 		 */
 		*iptr++ = cpu_to_be32(pos);
-		iptr = xdr_encode_rdma_segment(iptr, seg);
+		iptr = xdr_encode_rdma_segment(iptr, mw);
 
-		dprintk("RPC: %5u %s: read segment pos %u "
-			"%d@0x%016llx:0x%08x (%s)\n",
+		dprintk("RPC: %5u %s: pos %u %u@0x%016llx:0x%08x (%s)\n",
 			rqst->rq_task->tk_pid, __func__, pos,
-			seg->mr_len, (unsigned long long)seg->mr_base,
-			seg->mr_rkey, n < nsegs ? "more" : "last");
+			mw->mw_length, (unsigned long long)mw->mw_offset,
+			mw->mw_handle, n < nsegs ? "more" : "last");
 
 		r_xprt->rx_stats.read_chunk_count++;
-		req->rl_nchunks++;
 		seg += n;
 		nsegs -= n;
 	} while (nsegs);
-	req->rl_nextseg = seg;
 
 	/* Finish Read list */
 	*iptr++ = xdr_zero;	/* Next item not present */
@@ -375,7 +378,8 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 			  struct rpc_rqst *rqst, __be32 *iptr,
 			  enum rpcrdma_chunktype wtype)
 {
-	struct rpcrdma_mr_seg *seg = req->rl_nextseg;
+	struct rpcrdma_mr_seg *seg;
+	struct rpcrdma_mw *mw;
 	int n, nsegs, nchunks;
 	__be32 *segcount;
 
@@ -384,10 +388,10 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		return iptr;
 	}
 
+	seg = req->rl_segments;
 	nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf,
 				     rqst->rq_rcv_buf.head[0].iov_len,
-				     wtype, seg,
-				     RPCRDMA_MAX_SEGS - req->rl_nchunks);
+				     wtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
@@ -396,26 +400,25 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 
 	nchunks = 0;
 	do {
-		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true);
-		if (n <= 0)
+		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs,
+						 true, &mw);
+		if (n < 0)
 			return ERR_PTR(n);
+		list_add(&mw->mw_list, &req->rl_registered);
 
-		iptr = xdr_encode_rdma_segment(iptr, seg);
+		iptr = xdr_encode_rdma_segment(iptr, mw);
 
-		dprintk("RPC: %5u %s: write segment "
-			"%d@0x016%llx:0x%08x (%s)\n",
+		dprintk("RPC: %5u %s: %u@0x016%llx:0x%08x (%s)\n",
 			rqst->rq_task->tk_pid, __func__,
-			seg->mr_len, (unsigned long long)seg->mr_base,
-			seg->mr_rkey, n < nsegs ? "more" : "last");
+			mw->mw_length, (unsigned long long)mw->mw_offset,
+			mw->mw_handle, n < nsegs ? "more" : "last");
 
 		r_xprt->rx_stats.write_chunk_count++;
 		r_xprt->rx_stats.total_rdma_request += seg->mr_len;
-		req->rl_nchunks++;
 		nchunks++;
 		seg   += n;
 		nsegs -= n;
 	} while (nsegs);
-	req->rl_nextseg = seg;
 
 	/* Update count of segments in this Write chunk */
 	*segcount = cpu_to_be32(nchunks);
@@ -442,7 +445,8 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 			   struct rpcrdma_req *req, struct rpc_rqst *rqst,
 			   __be32 *iptr, enum rpcrdma_chunktype wtype)
 {
-	struct rpcrdma_mr_seg *seg = req->rl_nextseg;
+	struct rpcrdma_mr_seg *seg;
+	struct rpcrdma_mw *mw;
 	int n, nsegs, nchunks;
 	__be32 *segcount;
 
@@ -451,8 +455,8 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 		return iptr;
 	}
 
-	nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, 0, wtype, seg,
-				     RPCRDMA_MAX_SEGS - req->rl_nchunks);
+	seg = req->rl_segments;
+	nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, 0, wtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
@@ -461,26 +465,25 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 
 	nchunks = 0;
 	do {
-		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true);
-		if (n <= 0)
+		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs,
+						 true, &mw);
+		if (n < 0)
 			return ERR_PTR(n);
+		list_add(&mw->mw_list, &req->rl_registered);
 
-		iptr = xdr_encode_rdma_segment(iptr, seg);
+		iptr = xdr_encode_rdma_segment(iptr, mw);
 
-		dprintk("RPC: %5u %s: reply segment "
-			"%d@0x%016llx:0x%08x (%s)\n",
+		dprintk("RPC: %5u %s: %u@0x%016llx:0x%08x (%s)\n",
 			rqst->rq_task->tk_pid, __func__,
-			seg->mr_len, (unsigned long long)seg->mr_base,
-			seg->mr_rkey, n < nsegs ? "more" : "last");
+			mw->mw_length, (unsigned long long)mw->mw_offset,
+			mw->mw_handle, n < nsegs ? "more" : "last");
 
 		r_xprt->rx_stats.reply_chunk_count++;
 		r_xprt->rx_stats.total_rdma_request += seg->mr_len;
-		req->rl_nchunks++;
 		nchunks++;
 		seg   += n;
 		nsegs -= n;
 	} while (nsegs);
-	req->rl_nextseg = seg;
 
 	/* Update count of segments in the Reply chunk */
 	*segcount = cpu_to_be32(nchunks);
@@ -567,6 +570,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	enum rpcrdma_chunktype rtype, wtype;
 	struct rpcrdma_msg *headerp;
+	bool ddp_allowed;
 	ssize_t hdrlen;
 	size_t rpclen;
 	__be32 *iptr;
@@ -583,6 +587,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	headerp->rm_credit = cpu_to_be32(r_xprt->rx_buf.rb_max_requests);
 	headerp->rm_type = rdma_msg;
 
+	/* When the ULP employs a GSS flavor that guarantees integrity
+	 * or privacy, direct data placement of individual data items
+	 * is not allowed.
+	 */
+	ddp_allowed = !(rqst->rq_cred->cr_auth->au_flags &
+						RPCAUTH_AUTH_DATATOUCH);
+
 	/*
 	 * Chunks needed for results?
 	 *
@@ -594,7 +605,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 */
 	if (rpcrdma_results_inline(r_xprt, rqst))
 		wtype = rpcrdma_noch;
-	else if (rqst->rq_rcv_buf.flags & XDRBUF_READ)
+	else if (ddp_allowed && rqst->rq_rcv_buf.flags & XDRBUF_READ)
 		wtype = rpcrdma_writech;
 	else
 		wtype = rpcrdma_replych;
@@ -617,7 +628,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 		rtype = rpcrdma_noch;
 		rpcrdma_inline_pullup(rqst);
 		rpclen = rqst->rq_svec[0].iov_len;
-	} else if (rqst->rq_snd_buf.flags & XDRBUF_WRITE) {
+	} else if (ddp_allowed && rqst->rq_snd_buf.flags & XDRBUF_WRITE) {
 		rtype = rpcrdma_readch;
 		rpclen = rqst->rq_svec[0].iov_len;
 		rpclen += rpcrdma_tail_pullup(&rqst->rq_snd_buf);
@@ -650,8 +661,6 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * send a Call message with a Position Zero Read chunk and a
 	 * regular Read chunk at the same time.
 	 */
-	req->rl_nchunks = 0;
-	req->rl_nextseg = req->rl_segments;
 	iptr = headerp->rm_body.rm_chunks;
 	iptr = rpcrdma_encode_read_list(r_xprt, req, rqst, iptr, rtype);
 	if (IS_ERR(iptr))
@@ -690,10 +699,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 out_overflow:
 	pr_err("rpcrdma: send overflow: hdrlen %zd rpclen %zu %s/%s\n",
 		hdrlen, rpclen, transfertypes[rtype], transfertypes[wtype]);
-	/* Terminate this RPC. Chunks registered above will be
-	 * released by xprt_release -> xprt_rmda_free .
-	 */
-	return -EIO;
+	iptr = ERR_PTR(-EIO);
 
 out_unmap:
 	r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false);
@@ -705,15 +711,13 @@ out_unmap:
  * RDMA'd by server. See map at rpcrdma_create_chunks()! :-)
  */
 static int
-rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __be32 **iptrp)
+rpcrdma_count_chunks(struct rpcrdma_rep *rep, int wrchunk, __be32 **iptrp)
 {
 	unsigned int i, total_len;
 	struct rpcrdma_write_chunk *cur_wchunk;
 	char *base = (char *)rdmab_to_msg(rep->rr_rdmabuf);
 
 	i = be32_to_cpu(**iptrp);
-	if (i > max)
-		return -1;
 	cur_wchunk = (struct rpcrdma_write_chunk *) (*iptrp + 1);
 	total_len = 0;
 	while (i--) {
@@ -744,45 +748,66 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __b
 	return total_len;
 }
 
-/*
- * Scatter inline received data back into provided iov's.
+/**
+ * rpcrdma_inline_fixup - Scatter inline received data into rqst's iovecs
+ * @rqst: controlling RPC request
+ * @srcp: points to RPC message payload in receive buffer
+ * @copy_len: remaining length of receive buffer content
+ * @pad: Write chunk pad bytes needed (zero for pure inline)
+ *
+ * The upper layer has set the maximum number of bytes it can
+ * receive in each component of rq_rcv_buf. These values are set in
+ * the head.iov_len, page_len, tail.iov_len, and buflen fields.
+ *
+ * Unlike the TCP equivalent (xdr_partial_copy_from_skb), in
+ * many cases this function simply updates iov_base pointers in
+ * rq_rcv_buf to point directly to the received reply data, to
+ * avoid copying reply data.
+ *
+ * Returns the count of bytes which had to be memcopied.
  */
-static void
+static unsigned long
 rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
 {
-	int i, npages, curlen, olen;
+	unsigned long fixup_copy_count;
+	int i, npages, curlen;
 	char *destp;
 	struct page **ppages;
 	int page_base;
 
+	/* The head iovec is redirected to the RPC reply message
+	 * in the receive buffer, to avoid a memcopy.
+	 */
+	rqst->rq_rcv_buf.head[0].iov_base = srcp;
+	rqst->rq_private_buf.head[0].iov_base = srcp;
+
+	/* The contents of the receive buffer that follow
+	 * head.iov_len bytes are copied into the page list.
+	 */
 	curlen = rqst->rq_rcv_buf.head[0].iov_len;
-	if (curlen > copy_len) {	/* write chunk header fixup */
+	if (curlen > copy_len)
 		curlen = copy_len;
-		rqst->rq_rcv_buf.head[0].iov_len = curlen;
-	}
-
 	dprintk("RPC:       %s: srcp 0x%p len %d hdrlen %d\n",
 		__func__, srcp, copy_len, curlen);
-
-	/* Shift pointer for first receive segment only */
-	rqst->rq_rcv_buf.head[0].iov_base = srcp;
 	srcp += curlen;
 	copy_len -= curlen;
 
-	olen = copy_len;
-	i = 0;
-	rpcx_to_rdmax(rqst->rq_xprt)->rx_stats.fixup_copy_count += olen;
 	page_base = rqst->rq_rcv_buf.page_base;
 	ppages = rqst->rq_rcv_buf.pages + (page_base >> PAGE_SHIFT);
 	page_base &= ~PAGE_MASK;
-
+	fixup_copy_count = 0;
 	if (copy_len && rqst->rq_rcv_buf.page_len) {
-		npages = PAGE_ALIGN(page_base +
-			rqst->rq_rcv_buf.page_len) >> PAGE_SHIFT;
-		for (; i < npages; i++) {
+		int pagelist_len;
+
+		pagelist_len = rqst->rq_rcv_buf.page_len;
+		if (pagelist_len > copy_len)
+			pagelist_len = copy_len;
+		npages = PAGE_ALIGN(page_base + pagelist_len) >> PAGE_SHIFT;
+		for (i = 0; i < npages; i++) {
 			curlen = PAGE_SIZE - page_base;
-			if (curlen > copy_len)
-				curlen = copy_len;
+			if (curlen > pagelist_len)
+				curlen = pagelist_len;
+
 			dprintk("RPC:       %s: page %d"
 				" srcp 0x%p len %d curlen %d\n",
 				__func__, i, srcp, copy_len, curlen);
@@ -792,39 +817,32 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
 			kunmap_atomic(destp);
 			srcp += curlen;
 			copy_len -= curlen;
-			if (copy_len == 0)
+			fixup_copy_count += curlen;
+			pagelist_len -= curlen;
+			if (!pagelist_len)
 				break;
 			page_base = 0;
 		}
-	}
 
-	if (copy_len && rqst->rq_rcv_buf.tail[0].iov_len) {
-		curlen = copy_len;
-		if (curlen > rqst->rq_rcv_buf.tail[0].iov_len)
-			curlen = rqst->rq_rcv_buf.tail[0].iov_len;
-		if (rqst->rq_rcv_buf.tail[0].iov_base != srcp)
-			memmove(rqst->rq_rcv_buf.tail[0].iov_base, srcp, curlen);
-		dprintk("RPC:       %s: tail srcp 0x%p len %d curlen %d\n",
-			__func__, srcp, copy_len, curlen);
-		rqst->rq_rcv_buf.tail[0].iov_len = curlen;
-		copy_len -= curlen; ++i;
-	} else
-		rqst->rq_rcv_buf.tail[0].iov_len = 0;
-
-	if (pad) {
-		/* implicit padding on terminal chunk */
-		unsigned char *p = rqst->rq_rcv_buf.tail[0].iov_base;
-		while (pad--)
-			p[rqst->rq_rcv_buf.tail[0].iov_len++] = 0;
+		/* Implicit padding for the last segment in a Write
+		 * chunk is inserted inline at the front of the tail
+		 * iovec. The upper layer ignores the content of
+		 * the pad. Simply ensure inline content in the tail
+		 * that follows the Write chunk is properly aligned.
+		 */
+		if (pad)
+			srcp -= pad;
 	}
 
-	if (copy_len)
-		dprintk("RPC:       %s: %d bytes in"
-			" %d extra segments (%d lost)\n",
-			__func__, olen, i, copy_len);
+	/* The tail iovec is redirected to the remaining data
+	 * in the receive buffer, to avoid a memcopy.
+	 */
+	if (copy_len || pad) {
+		rqst->rq_rcv_buf.tail[0].iov_base = srcp;
+		rqst->rq_private_buf.tail[0].iov_base = srcp;
+	}
 
-	/* TBD avoid a warning from call_decode() */
-	rqst->rq_private_buf = rqst->rq_rcv_buf;
+	return fixup_copy_count;
 }
 
 void
@@ -960,14 +978,13 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 		    (headerp->rm_body.rm_chunks[1] == xdr_zero &&
 		     headerp->rm_body.rm_chunks[2] != xdr_zero) ||
 		    (headerp->rm_body.rm_chunks[1] != xdr_zero &&
-		     req->rl_nchunks == 0))
+		     list_empty(&req->rl_registered)))
 			goto badheader;
 		if (headerp->rm_body.rm_chunks[1] != xdr_zero) {
 			/* count any expected write chunks in read reply */
 			/* start at write chunk array count */
 			iptr = &headerp->rm_body.rm_chunks[2];
-			rdmalen = rpcrdma_count_chunks(rep,
-						req->rl_nchunks, 1, &iptr);
+			rdmalen = rpcrdma_count_chunks(rep, 1, &iptr);
 			/* check for validity, and no reply chunk after */
 			if (rdmalen < 0 || *iptr++ != xdr_zero)
 				goto badheader;
@@ -988,8 +1005,10 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 			rep->rr_len -= RPCRDMA_HDRLEN_MIN;
 			status = rep->rr_len;
 		}
-		/* Fix up the rpc results for upper layer */
-		rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len, rdmalen);
+
+		r_xprt->rx_stats.fixup_copy_count +=
+			rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len,
+					     rdmalen);
 		break;
 
 	case rdma_nomsg:
@@ -997,11 +1016,11 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 		if (headerp->rm_body.rm_chunks[0] != xdr_zero ||
 		    headerp->rm_body.rm_chunks[1] != xdr_zero ||
 		    headerp->rm_body.rm_chunks[2] != xdr_one ||
-		    req->rl_nchunks == 0)
+		    list_empty(&req->rl_registered))
 			goto badheader;
 		iptr = (__be32 *)((unsigned char *)headerp +
 							RPCRDMA_HDRLEN_MIN);
-		rdmalen = rpcrdma_count_chunks(rep, req->rl_nchunks, 0, &iptr);
+		rdmalen = rpcrdma_count_chunks(rep, 0, &iptr);
 		if (rdmalen < 0)
 			goto badheader;
 		r_xprt->rx_stats.total_rdma_reply += rdmalen;
@@ -1014,14 +1033,9 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 
 badheader:
 	default:
-		dprintk("%s: invalid rpcrdma reply header (type %d):"
-				" chunks[012] == %d %d %d"
-				" expected chunks <= %d\n",
-				__func__, be32_to_cpu(headerp->rm_type),
-				headerp->rm_body.rm_chunks[0],
-				headerp->rm_body.rm_chunks[1],
-				headerp->rm_body.rm_chunks[2],
-				req->rl_nchunks);
+		dprintk("RPC: %5u %s: invalid rpcrdma reply (type %u)\n",
+			rqst->rq_task->tk_pid, __func__,
+			be32_to_cpu(headerp->rm_type));
 		status = -EIO;
 		r_xprt->rx_stats.bad_reply_count++;
 		break;
@@ -1035,7 +1049,7 @@ out:
 	 * control: waking the next RPC waits until this RPC has
 	 * relinquished all its Send Queue entries.
 	 */
-	if (req->rl_nchunks)
+	if (!list_empty(&req->rl_registered))
 		r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, req);
 
 	spin_lock_bh(&xprt->transport_lock);
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 99d2e5b72726..81f0e879f019 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -558,7 +558,6 @@ out_sendbuf:
 
 out_fail:
 	rpcrdma_buffer_put(req);
-	r_xprt->rx_stats.failed_marshal_count++;
 	return NULL;
 }
 
@@ -590,8 +589,19 @@ xprt_rdma_free(void *buffer)
 	rpcrdma_buffer_put(req);
 }
 
-/*
+/**
+ * xprt_rdma_send_request - marshal and send an RPC request
+ * @task: RPC task with an RPC message in rq_snd_buf
+ *
+ * Return values:
+ *        0:	The request has been sent
+ * ENOTCONN:	Caller needs to invoke connect logic then call again
+ *  ENOBUFS:	Call again later to send the request
+ *      EIO:	A permanent error occurred. The request was not sent,
+ *		and don't try it again
+ *
  * send_request invokes the meat of RPC RDMA. It must do the following:
+ *
  *  1.  Marshal the RPC request into an RPC RDMA request, which means
  *	putting a header in front of data, and creating IOVs for RDMA
  *	from those in the request.
@@ -600,7 +610,6 @@ xprt_rdma_free(void *buffer)
  *	the request (rpcrdma_ep_post).
  *  4.  No partial sends are possible in the RPC-RDMA protocol (as in UDP).
  */
-
 static int
 xprt_rdma_send_request(struct rpc_task *task)
 {
@@ -610,6 +619,9 @@ xprt_rdma_send_request(struct rpc_task *task)
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	int rc = 0;
 
+	/* On retransmit, remove any previously registered chunks */
+	r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false);
+
 	rc = rpcrdma_marshal_req(rqst);
 	if (rc < 0)
 		goto failed_marshal;
@@ -630,11 +642,12 @@ xprt_rdma_send_request(struct rpc_task *task)
 	return 0;
 
 failed_marshal:
-	r_xprt->rx_stats.failed_marshal_count++;
 	dprintk("RPC:       %s: rpcrdma_marshal_req failed, status %i\n",
 		__func__, rc);
 	if (rc == -EIO)
-		return -EIO;
+		r_xprt->rx_stats.failed_marshal_count++;
+	if (rc != -ENOTCONN)
+		return rc;
 drop_connection:
 	xprt_disconnect_done(xprt);
 	return -ENOTCONN;	/* implies disconnect */
@@ -660,7 +673,7 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 		   xprt->stat.bad_xids,
 		   xprt->stat.req_u,
 		   xprt->stat.bklog_u);
-	seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %lu %lu %lu %lu\n",
+	seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %lu %lu %lu %lu ",
 		   r_xprt->rx_stats.read_chunk_count,
 		   r_xprt->rx_stats.write_chunk_count,
 		   r_xprt->rx_stats.reply_chunk_count,
@@ -672,6 +685,10 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 		   r_xprt->rx_stats.failed_marshal_count,
 		   r_xprt->rx_stats.bad_reply_count,
 		   r_xprt->rx_stats.nomsg_call_count);
+	seq_printf(seq, "%lu %lu %lu\n",
+		   r_xprt->rx_stats.mrs_recovered,
+		   r_xprt->rx_stats.mrs_orphaned,
+		   r_xprt->rx_stats.mrs_allocated);
 }
 
 static int
@@ -741,7 +758,6 @@ void xprt_rdma_cleanup(void)
 			__func__, rc);
 
 	rpcrdma_destroy_wq();
-	frwr_destroy_recovery_wq();
 
 	rc = xprt_unregister_transport(&xprt_rdma_bc);
 	if (rc)
@@ -753,20 +769,13 @@ int xprt_rdma_init(void)
 {
 	int rc;
 
-	rc = frwr_alloc_recovery_wq();
-	if (rc)
-		return rc;
-
 	rc = rpcrdma_alloc_wq();
-	if (rc) {
-		frwr_destroy_recovery_wq();
+	if (rc)
 		return rc;
-	}
 
 	rc = xprt_register_transport(&xprt_rdma);
 	if (rc) {
 		rpcrdma_destroy_wq();
-		frwr_destroy_recovery_wq();
 		return rc;
 	}
 
@@ -774,7 +783,6 @@ int xprt_rdma_init(void)
 	if (rc) {
 		xprt_unregister_transport(&xprt_rdma);
 		rpcrdma_destroy_wq();
-		frwr_destroy_recovery_wq();
 		return rc;
 	}
 
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index b044d98a1370..536d0be3f61b 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -379,8 +379,6 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 	struct rpcrdma_ia *ia = &xprt->rx_ia;
 	int rc;
 
-	ia->ri_dma_mr = NULL;
-
 	ia->ri_id = rpcrdma_create_id(xprt, ia, addr);
 	if (IS_ERR(ia->ri_id)) {
 		rc = PTR_ERR(ia->ri_id);
@@ -391,47 +389,29 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 	ia->ri_pd = ib_alloc_pd(ia->ri_device);
 	if (IS_ERR(ia->ri_pd)) {
 		rc = PTR_ERR(ia->ri_pd);
-		dprintk("RPC:       %s: ib_alloc_pd() failed %i\n",
-			__func__, rc);
+		pr_err("rpcrdma: ib_alloc_pd() returned %d\n", rc);
 		goto out2;
 	}
 
-	if (memreg == RPCRDMA_FRMR) {
-		if (!(ia->ri_device->attrs.device_cap_flags &
-				IB_DEVICE_MEM_MGT_EXTENSIONS) ||
-		    (ia->ri_device->attrs.max_fast_reg_page_list_len == 0)) {
-			dprintk("RPC:       %s: FRMR registration "
-				"not supported by HCA\n", __func__);
-			memreg = RPCRDMA_MTHCAFMR;
-		}
-	}
-	if (memreg == RPCRDMA_MTHCAFMR) {
-		if (!ia->ri_device->alloc_fmr) {
-			dprintk("RPC:       %s: MTHCAFMR registration "
-				"not supported by HCA\n", __func__);
-			rc = -EINVAL;
-			goto out3;
-		}
-	}
-
 	switch (memreg) {
 	case RPCRDMA_FRMR:
-		ia->ri_ops = &rpcrdma_frwr_memreg_ops;
-		break;
-	case RPCRDMA_ALLPHYSICAL:
-		ia->ri_ops = &rpcrdma_physical_memreg_ops;
-		break;
+		if (frwr_is_supported(ia)) {
+			ia->ri_ops = &rpcrdma_frwr_memreg_ops;
+			break;
+		}
+		/*FALLTHROUGH*/
 	case RPCRDMA_MTHCAFMR:
-		ia->ri_ops = &rpcrdma_fmr_memreg_ops;
-		break;
+		if (fmr_is_supported(ia)) {
+			ia->ri_ops = &rpcrdma_fmr_memreg_ops;
+			break;
+		}
+		/*FALLTHROUGH*/
 	default:
-		printk(KERN_ERR "RPC: Unsupported memory "
-				"registration mode: %d\n", memreg);
-		rc = -ENOMEM;
+		pr_err("rpcrdma: Unsupported memory registration mode: %d\n",
+		       memreg);
+		rc = -EINVAL;
 		goto out3;
 	}
-	dprintk("RPC:       %s: memory registration strategy is '%s'\n",
-		__func__, ia->ri_ops->ro_displayname);
 
 	return 0;
 
@@ -585,8 +565,6 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 out2:
 	ib_free_cq(sendcq);
 out1:
-	if (ia->ri_dma_mr)
-		ib_dereg_mr(ia->ri_dma_mr);
 	return rc;
 }
 
@@ -600,8 +578,6 @@ out1:
 void
 rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 {
-	int rc;
-
 	dprintk("RPC:       %s: entering, connected is %d\n",
 		__func__, ep->rep_connected);
 
@@ -615,12 +591,6 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 
 	ib_free_cq(ep->rep_attr.recv_cq);
 	ib_free_cq(ep->rep_attr.send_cq);
-
-	if (ia->ri_dma_mr) {
-		rc = ib_dereg_mr(ia->ri_dma_mr);
-		dprintk("RPC:       %s: ib_dereg_mr returned %i\n",
-			__func__, rc);
-	}
 }
 
 /*
@@ -777,6 +747,90 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 	ib_drain_qp(ia->ri_id->qp);
 }
 
+static void
+rpcrdma_mr_recovery_worker(struct work_struct *work)
+{
+	struct rpcrdma_buffer *buf = container_of(work, struct rpcrdma_buffer,
+						  rb_recovery_worker.work);
+	struct rpcrdma_mw *mw;
+
+	spin_lock(&buf->rb_recovery_lock);
+	while (!list_empty(&buf->rb_stale_mrs)) {
+		mw = list_first_entry(&buf->rb_stale_mrs,
+				      struct rpcrdma_mw, mw_list);
+		list_del_init(&mw->mw_list);
+		spin_unlock(&buf->rb_recovery_lock);
+
+		dprintk("RPC:       %s: recovering MR %p\n", __func__, mw);
+		mw->mw_xprt->rx_ia.ri_ops->ro_recover_mr(mw);
+
+		spin_lock(&buf->rb_recovery_lock);
+	}
+	spin_unlock(&buf->rb_recovery_lock);
+}
+
+void
+rpcrdma_defer_mr_recovery(struct rpcrdma_mw *mw)
+{
+	struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+
+	spin_lock(&buf->rb_recovery_lock);
+	list_add(&mw->mw_list, &buf->rb_stale_mrs);
+	spin_unlock(&buf->rb_recovery_lock);
+
+	schedule_delayed_work(&buf->rb_recovery_worker, 0);
+}
+
+static void
+rpcrdma_create_mrs(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	unsigned int count;
+	LIST_HEAD(free);
+	LIST_HEAD(all);
+
+	for (count = 0; count < 32; count++) {
+		struct rpcrdma_mw *mw;
+		int rc;
+
+		mw = kzalloc(sizeof(*mw), GFP_KERNEL);
+		if (!mw)
+			break;
+
+		rc = ia->ri_ops->ro_init_mr(ia, mw);
+		if (rc) {
+			kfree(mw);
+			break;
+		}
+
+		mw->mw_xprt = r_xprt;
+
+		list_add(&mw->mw_list, &free);
+		list_add(&mw->mw_all, &all);
+	}
+
+	spin_lock(&buf->rb_mwlock);
+	list_splice(&free, &buf->rb_mws);
+	list_splice(&all, &buf->rb_all);
+	r_xprt->rx_stats.mrs_allocated += count;
+	spin_unlock(&buf->rb_mwlock);
+
+	dprintk("RPC:       %s: created %u MRs\n", __func__, count);
+}
+
+static void
+rpcrdma_mr_refresh_worker(struct work_struct *work)
+{
+	struct rpcrdma_buffer *buf = container_of(work, struct rpcrdma_buffer,
+						  rb_refresh_worker.work);
+	struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt,
+						   rx_buf);
+
+	rpcrdma_create_mrs(r_xprt);
+}
+
 struct rpcrdma_req *
 rpcrdma_create_req(struct rpcrdma_xprt *r_xprt)
 {
@@ -793,6 +847,7 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt)
 	spin_unlock(&buffer->rb_reqslock);
 	req->rl_cqe.done = rpcrdma_wc_send;
 	req->rl_buffer = &r_xprt->rx_buf;
+	INIT_LIST_HEAD(&req->rl_registered);
 	return req;
 }
 
@@ -832,17 +887,23 @@ int
 rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
 {
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	int i, rc;
 
 	buf->rb_max_requests = r_xprt->rx_data.max_requests;
 	buf->rb_bc_srv_max_requests = 0;
-	spin_lock_init(&buf->rb_lock);
 	atomic_set(&buf->rb_credits, 1);
+	spin_lock_init(&buf->rb_mwlock);
+	spin_lock_init(&buf->rb_lock);
+	spin_lock_init(&buf->rb_recovery_lock);
+	INIT_LIST_HEAD(&buf->rb_mws);
+	INIT_LIST_HEAD(&buf->rb_all);
+	INIT_LIST_HEAD(&buf->rb_stale_mrs);
+	INIT_DELAYED_WORK(&buf->rb_refresh_worker,
+			  rpcrdma_mr_refresh_worker);
+	INIT_DELAYED_WORK(&buf->rb_recovery_worker,
+			  rpcrdma_mr_recovery_worker);
 
-	rc = ia->ri_ops->ro_init(r_xprt);
-	if (rc)
-		goto out;
+	rpcrdma_create_mrs(r_xprt);
 
 	INIT_LIST_HEAD(&buf->rb_send_bufs);
 	INIT_LIST_HEAD(&buf->rb_allreqs);
@@ -862,7 +923,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
 	}
 
 	INIT_LIST_HEAD(&buf->rb_recv_bufs);
-	for (i = 0; i < buf->rb_max_requests + 2; i++) {
+	for (i = 0; i < buf->rb_max_requests; i++) {
 		struct rpcrdma_rep *rep;
 
 		rep = rpcrdma_create_rep(r_xprt);
@@ -918,11 +979,39 @@ rpcrdma_destroy_req(struct rpcrdma_ia *ia, struct rpcrdma_req *req)
 	kfree(req);
 }
 
+static void
+rpcrdma_destroy_mrs(struct rpcrdma_buffer *buf)
+{
+	struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt,
+						   rx_buf);
+	struct rpcrdma_ia *ia = rdmab_to_ia(buf);
+	struct rpcrdma_mw *mw;
+	unsigned int count;
+
+	count = 0;
+	spin_lock(&buf->rb_mwlock);
+	while (!list_empty(&buf->rb_all)) {
+		mw = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
+		list_del(&mw->mw_all);
+
+		spin_unlock(&buf->rb_mwlock);
+		ia->ri_ops->ro_release_mr(mw);
+		count++;
+		spin_lock(&buf->rb_mwlock);
+	}
+	spin_unlock(&buf->rb_mwlock);
+	r_xprt->rx_stats.mrs_allocated = 0;
+
+	dprintk("RPC:       %s: released %u MRs\n", __func__, count);
+}
+
 void
 rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 {
 	struct rpcrdma_ia *ia = rdmab_to_ia(buf);
 
+	cancel_delayed_work_sync(&buf->rb_recovery_worker);
+
 	while (!list_empty(&buf->rb_recv_bufs)) {
 		struct rpcrdma_rep *rep;
 
@@ -944,7 +1033,7 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 	}
 	spin_unlock(&buf->rb_reqslock);
 
-	ia->ri_ops->ro_destroy(buf);
+	rpcrdma_destroy_mrs(buf);
 }
 
 struct rpcrdma_mw *
@@ -962,8 +1051,17 @@ rpcrdma_get_mw(struct rpcrdma_xprt *r_xprt)
 	spin_unlock(&buf->rb_mwlock);
 
 	if (!mw)
-		pr_err("RPC:       %s: no MWs available\n", __func__);
+		goto out_nomws;
 	return mw;
+
+out_nomws:
+	dprintk("RPC:       %s: no MWs available\n", __func__);
+	schedule_delayed_work(&buf->rb_refresh_worker, 0);
+
+	/* Allow the reply handler and refresh worker to run */
+	cond_resched();
+
+	return NULL;
 }
 
 void
@@ -978,8 +1076,6 @@ rpcrdma_put_mw(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mw *mw)
 
 /*
  * Get a set of request/reply buffers.
- *
- * Reply buffer (if available) is attached to send buffer upon return.
  */
 struct rpcrdma_req *
 rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
@@ -998,13 +1094,13 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
 
 out_reqbuf:
 	spin_unlock(&buffers->rb_lock);
-	pr_warn("RPC:       %s: out of request buffers\n", __func__);
+	pr_warn("rpcrdma: out of request buffers (%p)\n", buffers);
 	return NULL;
 out_repbuf:
+	list_add(&req->rl_free, &buffers->rb_send_bufs);
 	spin_unlock(&buffers->rb_lock);
-	pr_warn("RPC:       %s: out of reply buffers\n", __func__);
-	req->rl_reply = NULL;
-	return req;
+	pr_warn("rpcrdma: out of reply buffers (%p)\n", buffers);
+	return NULL;
 }
 
 /*
@@ -1060,14 +1156,6 @@ rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep)
  * Wrappers for internal-use kmalloc memory registration, used by buffer code.
  */
 
-void
-rpcrdma_mapping_error(struct rpcrdma_mr_seg *seg)
-{
-	dprintk("RPC:       map_one: offset %p iova %llx len %zu\n",
-		seg->mr_offset,
-		(unsigned long long)seg->mr_dma, seg->mr_dmalen);
-}
-
 /**
  * rpcrdma_alloc_regbuf - kmalloc and register memory for SEND/RECV buffers
  * @ia: controlling rpcrdma_ia
@@ -1150,7 +1238,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 	if (rep) {
 		rc = rpcrdma_ep_post_recv(ia, ep, rep);
 		if (rc)
-			goto out;
+			return rc;
 		req->rl_reply = NULL;
 	}
 
@@ -1175,10 +1263,12 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 
 	rc = ib_post_send(ia->ri_id->qp, &send_wr, &send_wr_fail);
 	if (rc)
-		dprintk("RPC:       %s: ib_post_send returned %i\n", __func__,
-			rc);
-out:
-	return rc;
+		goto out_postsend_err;
+	return 0;
+
+out_postsend_err:
+	pr_err("rpcrdma: RDMA Send ib_post_send returned %i\n", rc);
+	return -ENOTCONN;
 }
 
 /*
@@ -1203,11 +1293,13 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia,
 				   DMA_BIDIRECTIONAL);
 
 	rc = ib_post_recv(ia->ri_id->qp, &recv_wr, &recv_wr_fail);
-
 	if (rc)
-		dprintk("RPC:       %s: ib_post_recv returned %i\n", __func__,
-			rc);
-	return rc;
+		goto out_postrecv;
+	return 0;
+
+out_postrecv:
+	pr_err("rpcrdma: ib_post_recv returned %i\n", rc);
+	return -ENOTCONN;
 }
 
 /**
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 95cdc66225ee..670fad57153a 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -68,7 +68,6 @@ struct rpcrdma_ia {
 	struct ib_device	*ri_device;
 	struct rdma_cm_id 	*ri_id;
 	struct ib_pd		*ri_pd;
-	struct ib_mr		*ri_dma_mr;
 	struct completion	ri_done;
 	int			ri_async_rc;
 	unsigned int		ri_max_frmr_depth;
@@ -172,23 +171,14 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb)
  *   o recv buffer (posted to provider)
  *   o ib_sge (also donated to provider)
  *   o status of reply (length, success or not)
- *   o bookkeeping state to get run by tasklet (list, etc)
+ *   o bookkeeping state to get run by reply handler (list, etc)
  *
- * These are allocated during initialization, per-transport instance;
- * however, the tasklet execution list itself is global, as it should
- * always be pretty short.
+ * These are allocated during initialization, per-transport instance.
  *
  * N of these are associated with a transport instance, and stored in
  * struct rpcrdma_buffer. N is the max number of outstanding requests.
  */
 
-#define RPCRDMA_MAX_DATA_SEGS	((1 * 1024 * 1024) / PAGE_SIZE)
-
-/* data segments + head/tail for Call + head/tail for Reply */
-#define RPCRDMA_MAX_SEGS 	(RPCRDMA_MAX_DATA_SEGS + 4)
-
-struct rpcrdma_buffer;
-
 struct rpcrdma_rep {
 	struct ib_cqe		rr_cqe;
 	unsigned int		rr_len;
@@ -221,9 +211,6 @@ enum rpcrdma_frmr_state {
 };
 
 struct rpcrdma_frmr {
-	struct scatterlist		*fr_sg;
-	int				fr_nents;
-	enum dma_data_direction		fr_dir;
 	struct ib_mr			*fr_mr;
 	struct ib_cqe			fr_cqe;
 	enum rpcrdma_frmr_state		fr_state;
@@ -235,18 +222,23 @@ struct rpcrdma_frmr {
 };
 
 struct rpcrdma_fmr {
-	struct ib_fmr		*fmr;
-	u64			*physaddrs;
+	struct ib_fmr		*fm_mr;
+	u64			*fm_physaddrs;
 };
 
 struct rpcrdma_mw {
+	struct list_head	mw_list;
+	struct scatterlist	*mw_sg;
+	int			mw_nents;
+	enum dma_data_direction	mw_dir;
 	union {
 		struct rpcrdma_fmr	fmr;
 		struct rpcrdma_frmr	frmr;
 	};
-	struct work_struct	mw_work;
 	struct rpcrdma_xprt	*mw_xprt;
-	struct list_head	mw_list;
+	u32			mw_handle;
+	u32			mw_length;
+	u64			mw_offset;
 	struct list_head	mw_all;
 };
 
@@ -266,33 +258,30 @@ struct rpcrdma_mw {
  * of iovs for send operations. The reason is that the iovs passed to
  * ib_post_{send,recv} must not be modified until the work request
  * completes.
- *
- * NOTES:
- *   o RPCRDMA_MAX_SEGS is the max number of addressible chunk elements we
- *     marshal. The number needed varies depending on the iov lists that
- *     are passed to us, the memory registration mode we are in, and if
- *     physical addressing is used, the layout.
  */
 
+/* Maximum number of page-sized "segments" per chunk list to be
+ * registered or invalidated. Must handle a Reply chunk:
+ */
+enum {
+	RPCRDMA_MAX_IOV_SEGS	= 3,
+	RPCRDMA_MAX_DATA_SEGS	= ((1 * 1024 * 1024) / PAGE_SIZE) + 1,
+	RPCRDMA_MAX_SEGS	= RPCRDMA_MAX_DATA_SEGS +
+				  RPCRDMA_MAX_IOV_SEGS,
+};
+
 struct rpcrdma_mr_seg {		/* chunk descriptors */
-	struct rpcrdma_mw *rl_mw;	/* registered MR */
-	u64		mr_base;	/* registration result */
-	u32		mr_rkey;	/* registration result */
 	u32		mr_len;		/* length of chunk or segment */
-	int		mr_nsegs;	/* number of segments in chunk or 0 */
-	enum dma_data_direction	mr_dir;	/* segment mapping direction */
-	dma_addr_t	mr_dma;		/* segment mapping address */
-	size_t		mr_dmalen;	/* segment mapping length */
 	struct page	*mr_page;	/* owning page, if any */
 	char		*mr_offset;	/* kva if no page, else offset */
 };
 
 #define RPCRDMA_MAX_IOVS	(2)
 
+struct rpcrdma_buffer;
 struct rpcrdma_req {
 	struct list_head	rl_free;
 	unsigned int		rl_niovs;
-	unsigned int		rl_nchunks;
 	unsigned int		rl_connect_cookie;
 	struct rpc_task		*rl_task;
 	struct rpcrdma_buffer	*rl_buffer;
@@ -300,12 +289,13 @@ struct rpcrdma_req {
 	struct ib_sge		rl_send_iov[RPCRDMA_MAX_IOVS];
 	struct rpcrdma_regbuf	*rl_rdmabuf;
 	struct rpcrdma_regbuf	*rl_sendbuf;
-	struct rpcrdma_mr_seg	rl_segments[RPCRDMA_MAX_SEGS];
-	struct rpcrdma_mr_seg	*rl_nextseg;
 
 	struct ib_cqe		rl_cqe;
 	struct list_head	rl_all;
 	bool			rl_backchannel;
+
+	struct list_head	rl_registered;	/* registered segments */
+	struct rpcrdma_mr_seg	rl_segments[RPCRDMA_MAX_SEGS];
 };
 
 static inline struct rpcrdma_req *
@@ -341,6 +331,11 @@ struct rpcrdma_buffer {
 	struct list_head	rb_allreqs;
 
 	u32			rb_bc_max_requests;
+
+	spinlock_t		rb_recovery_lock; /* protect rb_stale_mrs */
+	struct list_head	rb_stale_mrs;
+	struct delayed_work	rb_recovery_worker;
+	struct delayed_work	rb_refresh_worker;
 };
 #define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia)
 
@@ -387,6 +382,9 @@ struct rpcrdma_stats {
 	unsigned long		bad_reply_count;
 	unsigned long		nomsg_call_count;
 	unsigned long		bcall_count;
+	unsigned long		mrs_recovered;
+	unsigned long		mrs_orphaned;
+	unsigned long		mrs_allocated;
 };
 
 /*
@@ -395,23 +393,25 @@ struct rpcrdma_stats {
 struct rpcrdma_xprt;
 struct rpcrdma_memreg_ops {
 	int		(*ro_map)(struct rpcrdma_xprt *,
-				  struct rpcrdma_mr_seg *, int, bool);
+				  struct rpcrdma_mr_seg *, int, bool,
+				  struct rpcrdma_mw **);
 	void		(*ro_unmap_sync)(struct rpcrdma_xprt *,
 					 struct rpcrdma_req *);
 	void		(*ro_unmap_safe)(struct rpcrdma_xprt *,
 					 struct rpcrdma_req *, bool);
+	void		(*ro_recover_mr)(struct rpcrdma_mw *);
 	int		(*ro_open)(struct rpcrdma_ia *,
 				   struct rpcrdma_ep *,
 				   struct rpcrdma_create_data_internal *);
 	size_t		(*ro_maxpages)(struct rpcrdma_xprt *);
-	int		(*ro_init)(struct rpcrdma_xprt *);
-	void		(*ro_destroy)(struct rpcrdma_buffer *);
+	int		(*ro_init_mr)(struct rpcrdma_ia *,
+				      struct rpcrdma_mw *);
+	void		(*ro_release_mr)(struct rpcrdma_mw *);
 	const char	*ro_displayname;
 };
 
 extern const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops;
 extern const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops;
-extern const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops;
 
 /*
  * RPCRDMA transport -- encapsulates the structures above for
@@ -446,6 +446,8 @@ extern int xprt_rdma_pad_optimize;
  */
 int rpcrdma_ia_open(struct rpcrdma_xprt *, struct sockaddr *, int);
 void rpcrdma_ia_close(struct rpcrdma_ia *);
+bool frwr_is_supported(struct rpcrdma_ia *);
+bool fmr_is_supported(struct rpcrdma_ia *);
 
 /*
  * Endpoint calls - xprtrdma/verbs.c
@@ -477,6 +479,8 @@ void rpcrdma_buffer_put(struct rpcrdma_req *);
 void rpcrdma_recv_buffer_get(struct rpcrdma_req *);
 void rpcrdma_recv_buffer_put(struct rpcrdma_rep *);
 
+void rpcrdma_defer_mr_recovery(struct rpcrdma_mw *);
+
 struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(struct rpcrdma_ia *,
 					    size_t, gfp_t);
 void rpcrdma_free_regbuf(struct rpcrdma_ia *,
@@ -484,9 +488,6 @@ void rpcrdma_free_regbuf(struct rpcrdma_ia *,
 
 int rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *, unsigned int);
 
-int frwr_alloc_recovery_wq(void);
-void frwr_destroy_recovery_wq(void);
-
 int rpcrdma_alloc_wq(void);
 void rpcrdma_destroy_wq(void);
 
@@ -494,45 +495,12 @@ void rpcrdma_destroy_wq(void);
  * Wrappers for chunk registration, shared by read/write chunk code.
  */
 
-void rpcrdma_mapping_error(struct rpcrdma_mr_seg *);
-
 static inline enum dma_data_direction
 rpcrdma_data_dir(bool writing)
 {
 	return writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
 }
 
-static inline void
-rpcrdma_map_one(struct ib_device *device, struct rpcrdma_mr_seg *seg,
-		enum dma_data_direction direction)
-{
-	seg->mr_dir = direction;
-	seg->mr_dmalen = seg->mr_len;
-
-	if (seg->mr_page)
-		seg->mr_dma = ib_dma_map_page(device,
-				seg->mr_page, offset_in_page(seg->mr_offset),
-				seg->mr_dmalen, seg->mr_dir);
-	else
-		seg->mr_dma = ib_dma_map_single(device,
-				seg->mr_offset,
-				seg->mr_dmalen, seg->mr_dir);
-
-	if (ib_dma_mapping_error(device, seg->mr_dma))
-		rpcrdma_mapping_error(seg);
-}
-
-static inline void
-rpcrdma_unmap_one(struct ib_device *device, struct rpcrdma_mr_seg *seg)
-{
-	if (seg->mr_page)
-		ib_dma_unmap_page(device,
-				  seg->mr_dma, seg->mr_dmalen, seg->mr_dir);
-	else
-		ib_dma_unmap_single(device,
-				    seg->mr_dma, seg->mr_dmalen, seg->mr_dir);
-}
-
 /*
  * RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c
  */
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 7e2b2fa189c3..111767ab124a 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -124,7 +124,7 @@ static struct ctl_table xs_tunables_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &xprt_min_resvport_limit,
-		.extra2		= &xprt_max_resvport_limit
+		.extra2		= &xprt_max_resvport
 	},
 	{
 		.procname	= "max_resvport",
@@ -132,7 +132,7 @@ static struct ctl_table xs_tunables_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &xprt_min_resvport_limit,
+		.extra1		= &xprt_min_resvport,
 		.extra2		= &xprt_max_resvport_limit
 	},
 	{
@@ -642,6 +642,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
 	struct xdr_buf *xdr = &req->rq_snd_buf;
 	bool zerocopy = true;
+	bool vm_wait = false;
 	int status;
 	int sent;
 
@@ -677,15 +678,33 @@ static int xs_tcp_send_request(struct rpc_task *task)
 			return 0;
 		}
 
+		WARN_ON_ONCE(sent == 0 && status == 0);
+
+		if (status == -EAGAIN ) {
+			/*
+			 * Return EAGAIN if we're sure we're hitting the
+			 * socket send buffer limits.
+			 */
+			if (test_bit(SOCK_NOSPACE, &transport->sock->flags))
+				break;
+			/*
+			 * Did we hit a memory allocation failure?
+			 */
+			if (sent == 0) {
+				status = -ENOBUFS;
+				if (vm_wait)
+					break;
+				/* Retry, knowing now that we're below the
+				 * socket send buffer limit
+				 */
+				vm_wait = true;
+			}
+			continue;
+		}
 		if (status < 0)
 			break;
-		if (sent == 0) {
-			status = -EAGAIN;
-			break;
-		}
+		vm_wait = false;
 	}
-	if (status == -EAGAIN && sk_stream_is_writeable(transport->inet))
-		status = -ENOBUFS;
 
 	switch (status) {
 	case -ENOTSOCK:
@@ -755,11 +774,19 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s
 	sk->sk_error_report = transport->old_error_report;
 }
 
+static void xs_sock_reset_state_flags(struct rpc_xprt *xprt)
+{
+	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+
+	clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state);
+}
+
 static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt)
 {
 	smp_mb__before_atomic();
 	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	clear_bit(XPRT_CLOSING, &xprt->state);
+	xs_sock_reset_state_flags(xprt);
 	smp_mb__after_atomic();
 }
 
@@ -962,10 +989,13 @@ static void xs_local_data_receive(struct sock_xprt *transport)
 		goto out;
 	for (;;) {
 		skb = skb_recv_datagram(sk, 0, 1, &err);
-		if (skb == NULL)
+		if (skb != NULL) {
+			xs_local_data_read_skb(&transport->xprt, sk, skb);
+			skb_free_datagram(sk, skb);
+			continue;
+		}
+		if (!test_and_clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state))
 			break;
-		xs_local_data_read_skb(&transport->xprt, sk, skb);
-		skb_free_datagram(sk, skb);
 	}
 out:
 	mutex_unlock(&transport->recv_mutex);
@@ -1043,10 +1073,13 @@ static void xs_udp_data_receive(struct sock_xprt *transport)
 		goto out;
 	for (;;) {
 		skb = skb_recv_datagram(sk, 0, 1, &err);
-		if (skb == NULL)
+		if (skb != NULL) {
+			xs_udp_data_read_skb(&transport->xprt, sk, skb);
+			skb_free_datagram(sk, skb);
+			continue;
+		}
+		if (!test_and_clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state))
 			break;
-		xs_udp_data_read_skb(&transport->xprt, sk, skb);
-		skb_free_datagram(sk, skb);
 	}
 out:
 	mutex_unlock(&transport->recv_mutex);
@@ -1074,7 +1107,14 @@ static void xs_data_ready(struct sock *sk)
 	if (xprt != NULL) {
 		struct sock_xprt *transport = container_of(xprt,
 				struct sock_xprt, xprt);
-		queue_work(rpciod_workqueue, &transport->recv_worker);
+		transport->old_data_ready(sk);
+		/* Any data means we had a useful conversation, so
+		 * then we don't need to delay the next reconnect
+		 */
+		if (xprt->reestablish_timeout)
+			xprt->reestablish_timeout = 0;
+		if (!test_and_set_bit(XPRT_SOCK_DATA_READY, &transport->sock_state))
+			queue_work(xprtiod_workqueue, &transport->recv_worker);
 	}
 	read_unlock_bh(&sk->sk_callback_lock);
 }
@@ -1474,10 +1514,15 @@ static void xs_tcp_data_receive(struct sock_xprt *transport)
 	for (;;) {
 		lock_sock(sk);
 		read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
-		release_sock(sk);
-		if (read <= 0)
-			break;
-		total += read;
+		if (read <= 0) {
+			clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state);
+			release_sock(sk);
+			if (!test_bit(XPRT_SOCK_DATA_READY, &transport->sock_state))
+				break;
+		} else {
+			release_sock(sk);
+			total += read;
+		}
 		rd_desc.count = 65536;
 	}
 out:
@@ -1493,34 +1538,6 @@ static void xs_tcp_data_receive_workfn(struct work_struct *work)
 }
 
 /**
- * xs_tcp_data_ready - "data ready" callback for TCP sockets
- * @sk: socket with data to read
- *
- */
-static void xs_tcp_data_ready(struct sock *sk)
-{
-	struct sock_xprt *transport;
-	struct rpc_xprt *xprt;
-
-	dprintk("RPC:       xs_tcp_data_ready...\n");
-
-	read_lock_bh(&sk->sk_callback_lock);
-	if (!(xprt = xprt_from_sock(sk)))
-		goto out;
-	transport = container_of(xprt, struct sock_xprt, xprt);
-
-	/* Any data means we had a useful conversation, so
-	 * the we don't need to delay the next reconnect
-	 */
-	if (xprt->reestablish_timeout)
-		xprt->reestablish_timeout = 0;
-	queue_work(rpciod_workqueue, &transport->recv_worker);
-
-out:
-	read_unlock_bh(&sk->sk_callback_lock);
-}
-
-/**
  * xs_tcp_state_change - callback to handle TCP socket state changes
  * @sk: socket whose state has changed
  *
@@ -1714,7 +1731,7 @@ static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task)
 
 static unsigned short xs_get_random_port(void)
 {
-	unsigned short range = xprt_max_resvport - xprt_min_resvport;
+	unsigned short range = xprt_max_resvport - xprt_min_resvport + 1;
 	unsigned short rand = (unsigned short) prandom_u32() % range;
 	return rand + xprt_min_resvport;
 }
@@ -2241,7 +2258,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		xs_save_old_callbacks(transport, sk);
 
 		sk->sk_user_data = xprt;
-		sk->sk_data_ready = xs_tcp_data_ready;
+		sk->sk_data_ready = xs_data_ready;
 		sk->sk_state_change = xs_tcp_state_change;
 		sk->sk_write_space = xs_tcp_write_space;
 		sock_set_flag(sk, SOCK_FASYNC);
@@ -2380,7 +2397,7 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 		/* Start by resetting any existing state */
 		xs_reset_transport(transport);
 
-		queue_delayed_work(rpciod_workqueue,
+		queue_delayed_work(xprtiod_workqueue,
 				   &transport->connect_worker,
 				   xprt->reestablish_timeout);
 		xprt->reestablish_timeout <<= 1;
@@ -2390,7 +2407,7 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 			xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO;
 	} else {
 		dprintk("RPC:       xs_connect scheduled xprt %p\n", xprt);
-		queue_delayed_work(rpciod_workqueue,
+		queue_delayed_work(xprtiod_workqueue,
 				   &transport->connect_worker, 0);
 	}
 }
@@ -3153,8 +3170,12 @@ static int param_set_uint_minmax(const char *val,
 
 static int param_set_portnr(const char *val, const struct kernel_param *kp)
 {
-	return param_set_uint_minmax(val, kp,
+	if (kp->arg == &xprt_min_resvport)
+		return param_set_uint_minmax(val, kp,
 			RPC_MIN_RESVPORT,
+			xprt_max_resvport);
+	return param_set_uint_minmax(val, kp,
+			xprt_min_resvport,
 			RPC_MAX_RESVPORT);
 }
 
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 0f82314621f2..15b196fc2f49 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -202,7 +202,7 @@ hdr-inst := -f $(srctree)/scripts/Makefile.headersinst obj
 # Prefix -I with $(srctree) if it is not an absolute path.
 # skip if -I has no parameter
 addtree = $(if $(patsubst -I%,%,$(1)), \
-$(if $(filter-out -I/%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1))) $(1))
+$(if $(filter-out -I/% -I./% -I../%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1)),$(1)))
 
 # Find all -I options and call addtree
 flags = $(foreach o,$($(1)),$(if $(filter -I%,$(o)),$(call addtree,$(o)),$(o)))
diff --git a/scripts/Makefile b/scripts/Makefile
index 822ab4a6a4aa..1d80897a9644 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -47,4 +47,4 @@ subdir-$(CONFIG_DTC)         += dtc
 subdir-$(CONFIG_GDB_SCRIPTS) += gdb
 
 # Let clean descend into subdirs
-subdir-	+= basic kconfig package
+subdir-	+= basic kconfig package gcc-plugins
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 0d1ca5bf42fb..11602e5efb3b 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -60,7 +60,7 @@ endif
 endif
 
 # Do not include host rules unless needed
-ifneq ($(hostprogs-y)$(hostprogs-m),)
+ifneq ($(hostprogs-y)$(hostprogs-m)$(hostlibs-y)$(hostlibs-m)$(hostcxxlibs-y)$(hostcxxlibs-m),)
 include scripts/Makefile.host
 endif
 
diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean
index 55c96cb8070f..50616ea25131 100644
--- a/scripts/Makefile.clean
+++ b/scripts/Makefile.clean
@@ -38,7 +38,9 @@ subdir-ymn	:= $(addprefix $(obj)/,$(subdir-ymn))
 __clean-files	:= $(extra-y) $(extra-m) $(extra-)       \
 		   $(always) $(targets) $(clean-files)   \
 		   $(host-progs)                         \
-		   $(hostprogs-y) $(hostprogs-m) $(hostprogs-)
+		   $(hostprogs-y) $(hostprogs-m) $(hostprogs-) \
+		   $(hostlibs-y) $(hostlibs-m) $(hostlibs-) \
+		   $(hostcxxlibs-y) $(hostcxxlibs-m)
 
 __clean-files   := $(filter-out $(no-clean-files), $(__clean-files))
 
diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
new file mode 100644
index 000000000000..5e22b60589c1
--- /dev/null
+++ b/scripts/Makefile.gcc-plugins
@@ -0,0 +1,43 @@
+ifdef CONFIG_GCC_PLUGINS
+  __PLUGINCC := $(call cc-ifversion, -ge, 0408, $(HOSTCXX), $(HOSTCC))
+  PLUGINCC := $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-plugin.sh "$(__PLUGINCC)" "$(HOSTCXX)" "$(CC)")
+
+  SANCOV_PLUGIN := -fplugin=$(objtree)/scripts/gcc-plugins/sancov_plugin.so
+
+  gcc-plugin-$(CONFIG_GCC_PLUGIN_CYC_COMPLEXITY)	+= cyc_complexity_plugin.so
+
+  ifdef CONFIG_GCC_PLUGIN_SANCOV
+    ifeq ($(CFLAGS_KCOV),)
+      # It is needed because of the gcc-plugin.sh and gcc version checks.
+      gcc-plugin-$(CONFIG_GCC_PLUGIN_SANCOV)           += sancov_plugin.so
+
+      ifneq ($(PLUGINCC),)
+        CFLAGS_KCOV := $(SANCOV_PLUGIN)
+      else
+        $(warning warning: cannot use CONFIG_KCOV: -fsanitize-coverage=trace-pc is not supported by compiler)
+      endif
+    endif
+  endif
+
+  GCC_PLUGINS_CFLAGS := $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y))
+
+  export PLUGINCC GCC_PLUGINS_CFLAGS GCC_PLUGIN SANCOV_PLUGIN
+
+  ifeq ($(PLUGINCC),)
+    ifneq ($(GCC_PLUGINS_CFLAGS),)
+      ifeq ($(call cc-ifversion, -ge, 0405, y), y)
+        PLUGINCC := $(shell $(CONFIG_SHELL) -x $(srctree)/scripts/gcc-plugin.sh "$(__PLUGINCC)" "$(HOSTCXX)" "$(CC)")
+        $(warning warning: your gcc installation does not support plugins, perhaps the necessary headers are missing?)
+      else
+        $(warning warning: your gcc version does not support plugins, you should upgrade it to gcc 4.5 at least)
+      endif
+    endif
+  else
+    # SANCOV_PLUGIN can be only in CFLAGS_KCOV because avoid duplication.
+    GCC_PLUGINS_CFLAGS := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGINS_CFLAGS))
+  endif
+
+  KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS)
+  GCC_PLUGIN := $(gcc-plugin-y)
+
+endif
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index 133edfae5b8a..45b5b1aaedbd 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -20,7 +20,15 @@
 # Will compile qconf as a C++ program, and menu as a C program.
 # They are linked as C++ code to the executable qconf
 
+# hostcc-option
+# Usage: cflags-y += $(call hostcc-option,-march=winchip-c6,-march=i586)
+
+hostcc-option = $(call try-run,\
+	$(HOSTCC) $(HOSTCFLAGS) $(HOST_EXTRACFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
+
 __hostprogs := $(sort $(hostprogs-y) $(hostprogs-m))
+host-cshlib := $(sort $(hostlibs-y) $(hostlibs-m))
+host-cxxshlib := $(sort $(hostcxxlibs-y) $(hostcxxlibs-m))
 
 # C code
 # Executables compiled from a single .c file
@@ -42,6 +50,10 @@ host-cxxmulti	:= $(foreach m,$(__hostprogs),$(if $($(m)-cxxobjs),$(m)))
 # C++ Object (.o) files compiled from .cc files
 host-cxxobjs	:= $(sort $(foreach m,$(host-cxxmulti),$($(m)-cxxobjs)))
 
+# Object (.o) files used by the shared libaries
+host-cshobjs	:= $(sort $(foreach m,$(host-cshlib),$($(m:.so=-objs))))
+host-cxxshobjs	:= $(sort $(foreach m,$(host-cxxshlib),$($(m:.so=-objs))))
+
 # output directory for programs/.o files
 # hostprogs-y := tools/build may have been specified.
 # Retrieve also directory of .o files from prog-objs or prog-cxxobjs notation
@@ -56,6 +68,10 @@ host-cmulti	:= $(addprefix $(obj)/,$(host-cmulti))
 host-cobjs	:= $(addprefix $(obj)/,$(host-cobjs))
 host-cxxmulti	:= $(addprefix $(obj)/,$(host-cxxmulti))
 host-cxxobjs	:= $(addprefix $(obj)/,$(host-cxxobjs))
+host-cshlib	:= $(addprefix $(obj)/,$(host-cshlib))
+host-cxxshlib	:= $(addprefix $(obj)/,$(host-cxxshlib))
+host-cshobjs	:= $(addprefix $(obj)/,$(host-cshobjs))
+host-cxxshobjs	:= $(addprefix $(obj)/,$(host-cxxshobjs))
 host-objdirs    := $(addprefix $(obj)/,$(host-objdirs))
 
 obj-dirs += $(host-objdirs)
@@ -124,5 +140,42 @@ quiet_cmd_host-cxxobjs	= HOSTCXX $@
 $(host-cxxobjs): $(obj)/%.o: $(src)/%.cc FORCE
 	$(call if_changed_dep,host-cxxobjs)
 
+# Compile .c file, create position independent .o file
+# host-cshobjs -> .o
+quiet_cmd_host-cshobjs	= HOSTCC  -fPIC $@
+      cmd_host-cshobjs	= $(HOSTCC) $(hostc_flags) -fPIC -c -o $@ $<
+$(host-cshobjs): $(obj)/%.o: $(src)/%.c FORCE
+	$(call if_changed_dep,host-cshobjs)
+
+# Compile .c file, create position independent .o file
+# Note that plugin capable gcc versions can be either C or C++ based
+# therefore plugin source files have to be compilable in both C and C++ mode.
+# This is why a C++ compiler is invoked on a .c file.
+# host-cxxshobjs -> .o
+quiet_cmd_host-cxxshobjs	= HOSTCXX -fPIC $@
+      cmd_host-cxxshobjs	= $(HOSTCXX) $(hostcxx_flags) -fPIC -c -o $@ $<
+$(host-cxxshobjs): $(obj)/%.o: $(src)/%.c FORCE
+	$(call if_changed_dep,host-cxxshobjs)
+
+# Link a shared library, based on position independent .o files
+# *.o -> .so shared library (host-cshlib)
+quiet_cmd_host-cshlib	= HOSTLLD -shared $@
+      cmd_host-cshlib	= $(HOSTCC) $(HOSTLDFLAGS) -shared -o $@ \
+			  $(addprefix $(obj)/,$($(@F:.so=-objs))) \
+			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
+$(host-cshlib): FORCE
+	$(call if_changed,host-cshlib)
+$(call multi_depend, $(host-cshlib), .so, -objs)
+
+# Link a shared library, based on position independent .o files
+# *.o -> .so shared library (host-cxxshlib)
+quiet_cmd_host-cxxshlib	= HOSTLLD -shared $@
+      cmd_host-cxxshlib	= $(HOSTCXX) $(HOSTLDFLAGS) -shared -o $@ \
+			  $(addprefix $(obj)/,$($(@F:.so=-objs))) \
+			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
+$(host-cxxshlib): FORCE
+	$(call if_changed,host-cxxshlib)
+$(call multi_depend, $(host-cxxshlib), .so, -objs)
+
 targets += $(host-csingle)  $(host-cmulti) $(host-cobjs)\
-	   $(host-cxxmulti) $(host-cxxobjs)
+	   $(host-cxxmulti) $(host-cxxobjs) $(host-cshlib) $(host-cshobjs) $(host-cxxshlib) $(host-cxxshobjs)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index e7df0f5db7ec..0a07f9014944 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -138,7 +138,7 @@ endif
 
 ifeq ($(CONFIG_KCOV),y)
 _c_flags += $(if $(patsubst n%,, \
-	$(KCOV_INSTRUMENT_$(basetarget).o)$(KCOV_INSTRUMENT)y), \
+	$(KCOV_INSTRUMENT_$(basetarget).o)$(KCOV_INSTRUMENT)$(CONFIG_KCOV_INSTRUMENT_ALL)), \
 	$(CFLAGS_KCOV))
 endif
 
@@ -155,9 +155,10 @@ else
 # $(call addtree,-I$(obj)) locates .h files in srctree, from generated .c files
 #   and locates generated .h files
 # FIXME: Replace both with specific CFLAGS* statements in the makefiles
-__c_flags	= $(call addtree,-I$(obj)) $(call flags,_c_flags)
-__a_flags	=                          $(call flags,_a_flags)
-__cpp_flags     =                          $(call flags,_cpp_flags)
+__c_flags	= $(if $(obj),-I$(srctree)/$(src) -I$(obj)) \
+		  $(call flags,_c_flags)
+__a_flags	= $(call flags,_a_flags)
+__cpp_flags     = $(call flags,_cpp_flags)
 endif
 
 c_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
diff --git a/scripts/basic/bin2c.c b/scripts/basic/bin2c.c
index af187e695345..c3d7eef3ad06 100644
--- a/scripts/basic/bin2c.c
+++ b/scripts/basic/bin2c.c
@@ -29,7 +29,8 @@ int main(int argc, char *argv[])
 	} while (ch != EOF);
 
 	if (argc > 1)
-		printf("\t;\n\nconst int %s_size = %d;\n", argv[1], total);
+		printf("\t;\n\n#include <linux/types.h>\n\nconst size_t %s_size = %d;\n",
+		       argv[1], total);
 
 	return 0;
 }
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 24a08363995a..4de3cc42fc50 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -55,6 +55,7 @@ my $spelling_file = "$D/spelling.txt";
 my $codespell = 0;
 my $codespellfile = "/usr/share/codespell/dictionary.txt";
 my $color = 1;
+my $allow_c99_comments = 1;
 
 sub help {
 	my ($exitcode) = @_;
@@ -227,9 +228,9 @@ if ($^V && $^V lt $minimum_perl_version) {
 	}
 }
 
+#if no filenames are given, push '-' to read patch from stdin
 if ($#ARGV < 0) {
-	print "$P: no input files\n";
-	exit(1);
+	push(@ARGV, '-');
 }
 
 sub hash_save_array_words {
@@ -1144,6 +1145,11 @@ sub sanitise_line {
 		$res =~ s@(\#\s*(?:error|warning)\s+).*@$1$clean@;
 	}
 
+	if ($allow_c99_comments && $res =~ m@(//.*$)@) {
+		my $match = $1;
+		$res =~ s/\Q$match\E/"$;" x length($match)/e;
+	}
+
 	return $res;
 }
 
@@ -2063,6 +2069,7 @@ sub process {
 	my $is_patch = 0;
 	my $in_header_lines = $file ? 0 : 1;
 	my $in_commit_log = 0;		#Scanning lines before patch
+	my $has_commit_log = 0;		#Encountered lines before patch
        my $commit_log_possible_stack_dump = 0;
 	my $commit_log_long_line = 0;
 	my $commit_log_has_diff = 0;
@@ -2453,9 +2460,9 @@ sub process {
 
 # Check for git id commit length and improperly formed commit descriptions
 		if ($in_commit_log && !$commit_log_possible_stack_dump &&
-		    $line !~ /^\s*(?:Link|Patchwork|http|BugLink):/i &&
+		    $line !~ /^\s*(?:Link|Patchwork|http|https|BugLink):/i &&
 		    ($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
-		     ($line =~ /\b[0-9a-f]{12,40}\b/i &&
+		     ($line =~ /(?:\s|^)[0-9a-f]{12,40}(?:[\s"'\(\[]|$)/i &&
 		      $line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i &&
 		      $line !~ /\bfixes:\s*[0-9a-f]{12,40}/i))) {
 			my $init_char = "c";
@@ -2560,6 +2567,7 @@ sub process {
 		      $rawline =~ /^(commit\b|from\b|[\w-]+:).*$/i)) {
 			$in_header_lines = 0;
 			$in_commit_log = 1;
+			$has_commit_log = 1;
 		}
 
 # Check if there is UTF-8 in a commit log when a mail header has explicitly
@@ -2763,6 +2771,10 @@ sub process {
 				 $line =~ /^\+\s*#\s*define\s+\w+\s+$String$/) {
 				$msg_type = "";
 
+			# EFI_GUID is another special case
+			} elsif ($line =~ /^\+.*\bEFI_GUID\s*\(/) {
+				$msg_type = "";
+
 			# Otherwise set the alternate message types
 
 			# a comment starts before $max_line_length
@@ -3337,7 +3349,7 @@ sub process {
 		next if ($line =~ /^[^\+]/);
 
 # check for declarations of signed or unsigned without int
-		while ($line =~ m{($Declare)\s*(?!char\b|short\b|int\b|long\b)\s*($Ident)?\s*[=,;\[\)\(]}g) {
+		while ($line =~ m{\b($Declare)\s*(?!char\b|short\b|int\b|long\b)\s*($Ident)?\s*[=,;\[\)\(]}g) {
 			my $type = $1;
 			my $var = $2;
 			$var = "" if (!defined $var);
@@ -5722,8 +5734,9 @@ sub process {
 			}
 		}
 
-# check for #defines like: 1 << <digit> that could be BIT(digit)
-		if ($line =~ /#\s*define\s+\w+\s+\(?\s*1\s*([ulUL]*)\s*\<\<\s*(?:\d+|$Ident)\s*\)?/) {
+# check for #defines like: 1 << <digit> that could be BIT(digit), it is not exported to uapi
+		if ($realfile !~ m@^include/uapi/@ &&
+		    $line =~ /#\s*define\s+\w+\s+\(?\s*1\s*([ulUL]*)\s*\<\<\s*(?:\d+|$Ident)\s*\)?/) {
 			my $ull = "";
 			$ull = "_ULL" if (defined($1) && $1 =~ /ll/i);
 			if (CHK("BIT_MACRO",
@@ -6044,7 +6057,7 @@ sub process {
 		ERROR("NOT_UNIFIED_DIFF",
 		      "Does not appear to be a unified-diff format patch\n");
 	}
-	if ($is_patch && $filename ne '-' && $chk_signoff && $signoff == 0) {
+	if ($is_patch && $has_commit_log && $chk_signoff && $signoff == 0) {
 		ERROR("MISSING_SIGN_OFF",
 		      "Missing Signed-off-by: line(s)\n");
 	}
diff --git a/scripts/coccicheck b/scripts/coccicheck
index dd85a455b2ba..c92c1528a54d 100755
--- a/scripts/coccicheck
+++ b/scripts/coccicheck
@@ -1,14 +1,24 @@
 #!/bin/bash
-
+# Linux kernel coccicheck
+#
+# Read Documentation/coccinelle.txt
 #
 # This script requires at least spatch
 # version 1.0.0-rc11.
-#
 
+DIR="$(dirname $(readlink -f $0))/.."
 SPATCH="`which ${SPATCH:=spatch}`"
 
-trap kill_running SIGTERM SIGINT
-declare -a SPATCH_PID
+if [ ! -x "$SPATCH" ]; then
+    echo 'spatch is part of the Coccinelle project and is available at http://coccinelle.lip6.fr/'
+    exit 1
+fi
+
+SPATCH_VERSION=$($SPATCH --version | head -1 | awk '{print $3}')
+SPATCH_VERSION_NUM=$(echo $SPATCH_VERSION | ${DIR}/scripts/ld-version.sh)
+
+USE_JOBS="no"
+$SPATCH --help | grep "\-\-jobs" > /dev/null && USE_JOBS="yes"
 
 # The verbosity may be set by the environmental parameter V=
 # as for example with 'make V=1 coccicheck'
@@ -25,7 +35,28 @@ else
 	NPROC="$J"
 fi
 
-FLAGS="$SPFLAGS --very-quiet"
+FLAGS="--very-quiet"
+
+# You can use SPFLAGS to append extra arguments to coccicheck or override any
+# heuristics done in this file as Coccinelle accepts the last options when
+# options conflict.
+#
+# A good example for use of SPFLAGS is if you want to debug your cocci script,
+# you can for instance use the following:
+#
+# $ export COCCI=scripts/coccinelle/misc/irqf_oneshot.cocci
+# $ make coccicheck MODE=report DEBUG_FILE="all.err" SPFLAGS="--profile --show-trying" M=./drivers/mfd/arizona-irq.c
+#
+# "--show-trying" should show you what rule is being processed as it goes to
+# stdout, you do not need a debug file for that. The profile output will be
+# be sent to stdout, if you provide a DEBUG_FILE the profiling data can be
+# inspected there.
+#
+# --profile will not output if --very-quiet is used, so avoid it.
+echo $SPFLAGS | egrep -e "--profile|--show-trying" 2>&1 > /dev/null
+if [ $? -eq 0 ]; then
+	FLAGS="--quiet"
+fi
 
 # spatch only allows include directories with the syntax "-I include"
 # while gcc also allows "-Iinclude" and "-include include"
@@ -51,9 +82,14 @@ if [ "$KBUILD_EXTMOD" != "" ] ; then
     OPTIONS="--patch $srctree $OPTIONS"
 fi
 
-if [ ! -x "$SPATCH" ]; then
-    echo 'spatch is part of the Coccinelle project and is available at http://coccinelle.lip6.fr/'
-    exit 1
+# You can override by using SPFLAGS
+if [ "$USE_JOBS" = "no" ]; then
+	trap kill_running SIGTERM SIGINT
+	declare -a SPATCH_PID
+elif [ "$NPROC" != "1" ]; then
+	# Using 0 should work as well, refer to _SC_NPROCESSORS_ONLN use on
+	# https://github.com/rdicosmo/parmap/blob/master/setcore_stubs.c
+	OPTIONS="$OPTIONS --jobs $NPROC --chunksize 1"
 fi
 
 if [ "$MODE" = "" ] ; then
@@ -72,7 +108,7 @@ if [ "$MODE" = "chain" ] ; then
 	echo 'All available modes will be tried (in that order): patch, report, context, org'
     fi
 elif [ "$MODE" = "report" -o "$MODE" = "org" ] ; then
-    FLAGS="$FLAGS --no-show-diff"
+    FLAGS="--no-show-diff $FLAGS"
 fi
 
 if [ "$ONLINE" = "0" ] ; then
@@ -82,7 +118,26 @@ if [ "$ONLINE" = "0" ] ; then
     echo ''
 fi
 
-run_cmd() {
+run_cmd_parmap() {
+	if [ $VERBOSE -ne 0 ] ; then
+		echo "Running ($NPROC in parallel): $@"
+	fi
+	if [ "$DEBUG_FILE" != "/dev/null" -a "$DEBUG_FILE" != "" ]; then
+		if [ -f $DEBUG_FILE ]; then
+			echo "Debug file $DEBUG_FILE exists, bailing"
+			exit
+		fi
+	else
+		DEBUG_FILE="/dev/null"
+	fi
+	$@ 2>$DEBUG_FILE
+	if [[ $? -ne 0 ]]; then
+		echo "coccicheck failed"
+		exit $?
+	fi
+}
+
+run_cmd_old() {
 	local i
 	if [ $VERBOSE -ne 0 ] ; then
 		echo "Running ($NPROC in parallel): $@"
@@ -97,6 +152,14 @@ run_cmd() {
 	wait
 }
 
+run_cmd() {
+	if [ "$USE_JOBS" = "yes" ]; then
+		run_cmd_parmap $@
+	else
+		run_cmd_old $@
+	fi
+}
+
 kill_running() {
 	for i in $(seq 0 $(( NPROC - 1 )) ); do
 		if [ $VERBOSE -eq 2 ] ; then
@@ -106,10 +169,23 @@ kill_running() {
 	done
 }
 
+# You can override heuristics with SPFLAGS, these must always go last
+OPTIONS="$OPTIONS $SPFLAGS"
+
 coccinelle () {
     COCCI="$1"
 
     OPT=`grep "Option" $COCCI | cut -d':' -f2`
+    REQ=`grep "Requires" $COCCI | cut -d':' -f2 | sed "s| ||"`
+    REQ_NUM=$(echo $REQ | ${DIR}/scripts/ld-version.sh)
+    if [ "$REQ_NUM" != "0" ] ; then
+	    if [ "$SPATCH_VERSION_NUM" -lt "$REQ_NUM" ] ; then
+		    echo "Skipping coccinele SmPL patch: $COCCI"
+		    echo "You have coccinelle:           $SPATCH_VERSION"
+		    echo "This SmPL patch requires:      $REQ"
+		    return
+	    fi
+    fi
 
 #   The option '--parse-cocci' can be used to syntactically check the SmPL files.
 #
diff --git a/scripts/coccinelle/free/devm_free.cocci b/scripts/coccinelle/free/devm_free.cocci
index 3d9349012bb3..c990d2c7ee16 100644
--- a/scripts/coccinelle/free/devm_free.cocci
+++ b/scripts/coccinelle/free/devm_free.cocci
@@ -29,8 +29,24 @@ expression x;
 @@
 
 (
+ x = devm_kmalloc(...)
+|
+ x = devm_kvasprintf(...)
+|
+ x = devm_kasprintf(...)
+|
  x = devm_kzalloc(...)
 |
+ x = devm_kmalloc_array(...)
+|
+ x = devm_kcalloc(...)
+|
+ x = devm_kstrdup(...)
+|
+ x = devm_kmemdup(...)
+|
+ x = devm_get_free_pages(...)
+|
  x = devm_request_irq(...)
 |
  x = devm_ioremap(...)
@@ -48,6 +64,16 @@ position p;
 (
 * kfree@p(x)
 |
+* kzfree@p(x)
+|
+* __krealloc@p(x, ...)
+|
+* krealloc@p(x, ...)
+|
+* free_pages@p(x, ...)
+|
+* free_page@p(x)
+|
 * free_irq@p(x)
 |
 * iounmap@p(x)
diff --git a/scripts/coccinelle/free/ifnullfree.cocci b/scripts/coccinelle/free/ifnullfree.cocci
index 52bd235286fa..14a4cd98e83b 100644
--- a/scripts/coccinelle/free/ifnullfree.cocci
+++ b/scripts/coccinelle/free/ifnullfree.cocci
@@ -20,6 +20,8 @@ expression E;
 (
   kfree(E);
 |
+  kzfree(E);
+|
   debugfs_remove(E);
 |
   debugfs_remove_recursive(E);
@@ -39,7 +41,7 @@ position p;
 @@
 
 * if (E != NULL)
-*	\(kfree@p\|debugfs_remove@p\|debugfs_remove_recursive@p\|
+*	\(kfree@p\|kzfree@p\|debugfs_remove@p\|debugfs_remove_recursive@p\|
 *         usb_free_urb@p\|kmem_cache_destroy@p\|mempool_destroy@p\|
 *         dma_pool_destroy@p\)(E);
 
diff --git a/scripts/coccinelle/free/kfree.cocci b/scripts/coccinelle/free/kfree.cocci
index 577b78056990..ac438da4fd7b 100644
--- a/scripts/coccinelle/free/kfree.cocci
+++ b/scripts/coccinelle/free/kfree.cocci
@@ -20,7 +20,11 @@ expression E;
 position p1;
 @@
 
-kfree@p1(E)
+(
+* kfree@p1(E)
+|
+* kzfree@p1(E)
+)
 
 @print expression@
 constant char [] c;
@@ -60,7 +64,11 @@ position ok;
 @@
 
 while (1) { ...
-  kfree@ok(E)
+(
+* kfree@ok(E)
+|
+* kzfree@ok(E)
+)
   ... when != break;
       when != goto l;
       when forall
@@ -74,7 +82,11 @@ statement S;
 position free.p1!=loop.ok,p2!={print.p,sz.p};
 @@
 
-kfree@p1(E,...)
+(
+* kfree@p1(E,...)
+|
+* kzfree@p1(E,...)
+)
 ...
 (
  iter(...,subE,...) S // no use
diff --git a/scripts/coccinelle/free/kfreeaddr.cocci b/scripts/coccinelle/free/kfreeaddr.cocci
index ce8aacc314cb..d46063b1db8b 100644
--- a/scripts/coccinelle/free/kfreeaddr.cocci
+++ b/scripts/coccinelle/free/kfreeaddr.cocci
@@ -16,7 +16,11 @@ identifier f;
 position p;
 @@
 
+(
 * kfree@p(&e->f)
+|
+* kzfree@p(&e->f)
+)
 
 @script:python depends on org@
 p << r.p;
@@ -28,5 +32,5 @@ cocci.print_main("kfree",p)
 p << r.p;
 @@
 
-msg = "ERROR: kfree of structure field"
+msg = "ERROR: invalid free of structure field"
 coccilib.report.print_report(p[0],msg)
diff --git a/scripts/coccinelle/iterators/device_node_continue.cocci b/scripts/coccinelle/iterators/device_node_continue.cocci
index 38ab744a4037..a36c16db171b 100644
--- a/scripts/coccinelle/iterators/device_node_continue.cocci
+++ b/scripts/coccinelle/iterators/device_node_continue.cocci
@@ -5,8 +5,11 @@
 // Copyright: (C) 2015 Julia Lawall, Inria. GPLv2.
 // URL: http://coccinelle.lip6.fr/
 // Options: --no-includes --include-headers
+// Requires: 1.0.4
 // Keywords: for_each_child_of_node, etc.
 
+// This uses a conjunction, which requires at least coccinelle >= 1.0.4
+
 virtual patch
 virtual context
 virtual org
diff --git a/scripts/coccinelle/misc/noderef.cocci b/scripts/coccinelle/misc/noderef.cocci
index 80a831c91161..007f0de0c715 100644
--- a/scripts/coccinelle/misc/noderef.cocci
+++ b/scripts/coccinelle/misc/noderef.cocci
@@ -16,6 +16,7 @@ virtual patch
 @depends on patch@
 expression *x;
 expression f;
+expression i;
 type T;
 @@
 
@@ -30,15 +31,26 @@ f(...,(T)(x),...,sizeof(
 + *x
    ),...)
 |
-f(...,sizeof(x),...,(T)(
+f(...,sizeof(
+- x
++ *x
+   ),...,(T)(x),...)
+|
+f(...,(T)(x),...,i*sizeof(
 - x
 + *x
    ),...)
+|
+f(...,i*sizeof(
+- x
++ *x
+   ),...,(T)(x),...)
 )
 
 @r depends on !patch@
 expression *x;
 expression f;
+expression i;
 position p;
 type T;
 @@
@@ -49,6 +61,10 @@ type T;
 *f(...,(T)(x),...,sizeof@p(x),...)
 |
 *f(...,sizeof@p(x),...,(T)(x),...)
+|
+*f(...,(T)(x),...,i*sizeof@p(x),...)
+|
+*f(...,i*sizeof@p(x),...,(T)(x),...)
 )
 
 @script:python depends on org@
diff --git a/scripts/dtc/dt_to_config b/scripts/dtc/dt_to_config
new file mode 100755
index 000000000000..9a248b505c58
--- /dev/null
+++ b/scripts/dtc/dt_to_config
@@ -0,0 +1,1213 @@
+#!/usr/bin/perl
+
+# Copyright 2016 by Frank Rowand
+# Copyright 2016 by Gaurav Minocha
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License v2.
+
+use strict 'refs';
+use strict subs;
+
+use Getopt::Long;
+
+$VUFX = "160610a";
+
+$script_name = $0;
+$script_name =~ s|^.*/||;
+
+
+# ----- constants for print_flags()
+
+# Position in string $pr_flags.  Range of 0..($num_pr_flags - 1).
+$pr_flag_pos_mcompatible       = 0;
+$pr_flag_pos_driver            = 1;
+$pr_flag_pos_mdriver           = 2;
+$pr_flag_pos_config            = 3;
+$pr_flag_pos_mconfig           = 4;
+$pr_flag_pos_node_not_enabled  = 5;
+$pr_flag_pos_white_list        = 6;
+$pr_flag_pos_hard_coded        = 7;
+$pr_flag_pos_config_hard_coded = 8;
+$pr_flag_pos_config_none       = 9;
+$pr_flag_pos_config_m          = 10;
+$pr_flag_pos_config_y          = 11;
+$pr_flag_pos_config_test_fail  = 12;
+
+$num_pr_flags = $pr_flag_pos_config_test_fail + 1;
+
+# flags in @pr_flag_value must be unique values to allow simple regular
+# expessions to work for --include_flags and --exclude_flags.
+# Convention: use upper case letters for potential issues or problems.
+
+@pr_flag_value = ('M', 'd', 'D', 'c', 'C', 'E', 'W', 'H', 'x', 'n', 'm', 'y', 'F');
+
+@pr_flag_help = (
+    "multiple compatibles found for this node",
+    "driver found for this compatible",
+    "multiple drivers found for this compatible",
+    "kernel config found for this driver",
+    "multiple config options found for this driver",
+    "node is not enabled",
+    "compatible is white listed",
+    "matching driver and/or kernel config is hard coded",
+    "kernel config hard coded in Makefile",
+    "one or more kernel config file options is not set",
+    "one or more kernel config file options is set to 'm'",
+    "one or more kernel config file options is set to 'y'",
+    "one of more kernel config file options fails to have correct value"
+);
+
+
+# -----
+
+%driver_config = ();   # driver config array, indexed by driver source file
+%driver_count = ();    # driver_cnt, indexed by compatible
+%compat_driver = ();   # compatible driver array, indexed by compatible
+%existing_config = (); # existing config symbols present in given config file
+                       # expected values are: "y", "m", a decimal number, a
+                       # hex number, or a string
+
+# ----- magic compatibles, do not have a driver
+#
+# Will not search for drivers for these compatibles.
+
+%compat_white_list = (
+       'none'                  => '1',
+       'pci'                   => '1',
+       'simple-bus'            => '1',
+);
+
+# Will not search for drivers for these compatibles.
+#
+# These compatibles have a very large number of false positives.
+#
+# 'hardcoded_no_driver' is a magic value.  Other code knows this
+# magic value.  Do not use 'no_driver' here!
+#
+# Revisit each 'hardcoded_no_driver' to see how the compatible
+# is used.  Are there drivers that can be provided?
+
+%driver_hard_code_list = (
+       'cache'                 => ['hardcoded_no_driver'],
+       'eeprom'                => ['hardcoded_no_driver'],
+       'gpio'                  => ['hardcoded_no_driver'],
+       'gpio-keys'             => ['drivers/input/keyboard/gpio_keys.c'],
+       'i2c-gpio'              => ['drivers/i2c/busses/i2c-gpio.c'],
+       'isa'                   => ['arch/mips/mti-malta/malta-dt.c',
+                                    'arch/x86/kernel/devicetree.c'],
+       'led'                   => ['hardcoded_no_driver'],
+       'm25p32'                => ['hardcoded_no_driver'],
+       'm25p64'                => ['hardcoded_no_driver'],
+       'm25p80'                => ['hardcoded_no_driver'],
+       'mtd-ram'               => ['drivers/mtd/maps/physmap_of.c'],
+       'pwm-backlight'         => ['drivers/video/backlight/pwm_bl.c'],
+       'spidev'                => ['hardcoded_no_driver'],
+       'syscon'                => ['drivers/mfd/syscon.c'],
+       'tlv320aic23'           => ['hardcoded_no_driver'],
+       'wm8731'                => ['hardcoded_no_driver'],
+);
+
+# Use these config options instead of searching makefiles
+
+%driver_config_hard_code_list = (
+
+       # this one needed even if %driver_hard_code_list is empty
+       'no_driver'                             => ['no_config'],
+       'hardcoded_no_driver'                   => ['no_config'],
+
+       # drivers/usb/host/ehci-ppc-of.c
+       # drivers/usb/host/ehci-xilinx-of.c
+       #  are included from:
+       #    drivers/usb/host/ehci-hcd.c
+       #  thus the search of Makefile for the included .c files is incorrect
+       # ehci-hcd.c wraps the includes with ifdef CONFIG_USB_EHCI_HCD_..._OF
+       #
+       # similar model for ohci-hcd.c (but no ohci-xilinx-of.c)
+       #
+       # similarly, uhci-hcd.c includes uhci-platform.c
+
+       'drivers/usb/host/ehci-ppc-of.c'        => ['CONFIG_USB_EHCI_HCD',
+                                                   'CONFIG_USB_EHCI_HCD_PPC_OF'],
+       'drivers/usb/host/ohci-ppc-of.c'        => ['CONFIG_USB_OHCI_HCD',
+                                                   'CONFIG_USB_OHCI_HCD_PPC_OF'],
+
+       'drivers/usb/host/ehci-xilinx-of.c'     => ['CONFIG_USB_EHCI_HCD',
+                                                   'CONFIG_USB_EHCI_HCD_XILINX'],
+
+       'drivers/usb/host/uhci-platform.c'      => ['CONFIG_USB_UHCI_HCD',
+                                                   'CONFIG_USB_UHCI_PLATFORM'],
+
+       # scan_makefile will find only one of these config options:
+       #    ifneq ($(CONFIG_SOC_IMX6)$(CONFIG_SOC_LS1021A),)
+       'arch/arm/mach-imx/platsmp.c'           => ['CONFIG_SOC_IMX6 && CONFIG_SMP',
+                                                   'CONFIG_SOC_LS1021A && CONFIG_SMP'],
+);
+
+
+# 'virt/kvm/arm/.*' are controlled by makefiles in other directories,
+# using relative paths, such as 'KVM := ../../../virt/kvm'.  Do not
+# add complexity to find_kconfig() to deal with this.  There is a long
+# term intent to change the kvm related makefiles to the normal kernel
+# style.  After that is done, this entry can be removed from the
+# black_list_driver.
+
+@black_list_driver = (
+       # kvm no longer a problem after commit 503a62862e8f in 4.7-rc1
+       # 'virt/kvm/arm/.*',
+);
+
+
+sub usage()
+{
+       print
+"
+Usage: $script_name [options] device-tree...
+
+    device_tree is: dts_file | dtb_file | proc_device-tree
+
+
+Valid options:
+     -c FILE             Read kernel config options from FILE
+    --config FILE        synonym for 'c'
+    --config-format      config file friendly output format
+    --exclude-flag FLAG  exclude entries with a matching flag
+     -h                  Display this message and exit
+    --help               synonym for 'h'
+    --black-list-driver  use driver black list
+    --white-list-config  use config white list
+    --white-list-driver  use driver white list
+    --include-flag FLAG  include only entries with a matching flag
+    --include-suspect    include only entries with an uppercase flag
+    --short-name         do not show the path portion of the node name
+    --show-lists         report of white and black lists
+    --version            Display program version and exit
+
+
+  Report driver source files that match the compatibles in the device
+  tree file and the kernel config options that enable the driver source
+  files.
+
+  This program must be run in the root directory of a Linux kernel
+  source tree.
+
+  The default format is a report that is intended to be easily human
+  scannable.
+
+  An alternate format can be selected by --config-format.  This will
+  create output that can easily be edited to create a fragment that can
+  be appended to the existing kernel config file.  Each entry consists of
+  multiple lines.  The first line reports flags, the node path, compatible
+  value, driver file matching the compatible, configuration options, and
+  current values of the configuration options.  For each configuration
+  option, the following lines report the current value and the value that
+  is required for the driver file to be included in the kernel.
+
+  If a large number of drivers or config options is listed for a node,
+  and the '$pr_flag_value[$pr_flag_pos_hard_coded]' flag is set consider using --white-list-config and/or
+  --white-list-driver.  If the white list option suppresses the correct
+  entry please report that as a bug.
+
+  CAUTION:
+     This program uses heuristics to guess which driver(s) support each
+     compatible string and which config option(s) enables the driver(s).
+     Do not believe that the reported information is fully correct.
+     This program is intended to aid the process of determining the
+     proper kernel configuration for a device tree, but this is not
+     a fully automated process -- human involvement may still be
+     required!
+
+     The driver match heuristic used is to search for source files
+     containing the compatible string enclosed in quotes.
+
+     This program might not be able to find all drivers matching a
+     compatible string.
+
+     Some makefiles are overly clever.  This program was not made
+     complex enough to handle them.  If no config option is listed
+     for a driver, look at the makefile for the driver source file.
+     Even if a config option is listed for a driver, some other
+     available config options may not be listed.
+
+  FLAG values:
+";
+
+       for ($k = 0; $k < $num_pr_flags; $k++) {
+               printf "     %s   %s\n", $pr_flag_value[$k], $pr_flag_help[$k];
+       }
+
+       print
+"
+     Upper case letters indicate potential issues or problems.
+
+  The flag:
+
+";
+
+       $k = $pr_flag_pos_hard_coded;
+       printf "     %s   %s\n", $pr_flag_value[$k], $pr_flag_help[$k];
+
+       print
+"
+  will be set if the config or driver is in the white lists, even if
+  --white-list-config and --white-list-driver are not specified.
+  This is a hint that 1) many of these reported lines are likely to
+  be incorrect, and 2) using those options will reduce the number of
+  drivers and/or config options reported.
+
+  --white-list-config and --white-list-driver may not be accurate if this
+  program is not well maintained.  Use them with appropriate skepticism.
+  Use the --show-lists option to report the values in the list.
+
+  Return value:
+    0   if no error
+    1   error processing command line
+    2   unable to open or read kernel config file
+    3   unable to open or process input device tree file(s)
+
+  EXAMPLES:
+
+     dt_to_config arch/arm/boot/dts/my_dts_file.dts
+
+       Basic report.
+
+     dt_to_config \\
+        --config \${KBUILD_OUTPUT}/.config \\
+        arch/\${ARCH}/boot/dts/my_dts_file.dts
+
+       Full report, with config file issues noted.
+
+     dt_to_config --include-suspect \\
+        --config \${KBUILD_OUTPUT}/.config \\
+        arch/\${ARCH}/boot/dts/my_dts_file.dts
+
+       Report of node / compatible string / driver tuples that should
+       be further investigated.  A node may have multiple compatible
+       strings.  A compatible string may be matched by multiple drivers.
+       A driver may have config file issues noted.  The compatible string
+       and/or driver may be in the white lists.
+
+     dt_to_config --include-suspect --config-format \\
+        --config ${KBUILD_OUTPUT}/.config \\
+        arch/\${ARCH}/boot/dts/my_dts_file.dts
+
+       Report of node / compatible string / driver tuples that should
+       be further investigated.  The report can be edited to uncomment
+       the config options to select the desired tuple for a given node.
+       A node may have multiple compatible strings.  A compatible string
+       may be matched by multiple drivers.  A driver may have config file
+       issues noted.  The compatible string and/or driver may be in the
+       white lists.
+
+";
+}
+
+sub set_flag()
+{
+       # pr_flags_ref is a reference to $pr_flags
+
+       my $pr_flags_ref = shift;
+       my $pos          = shift;
+
+       substr $$pr_flags_ref, $pos, 1, $pr_flag_value[$pos];
+
+       return $pr_flags;
+}
+
+sub print_flags()
+{
+       # return 1 if anything printed, else 0
+
+       # some fields of pn_arg_ref might not be used in this function, but
+       # extract all of them anyway.
+       my $pn_arg_ref     = shift;
+
+       my $compat         = $pn_arg_ref->{compat};
+       my $compatible_cnt = $pn_arg_ref->{compatible_cnt};
+       my $config         = $pn_arg_ref->{config};
+       my $config_cnt     = $pn_arg_ref->{config_cnt};
+       my $driver         = $pn_arg_ref->{driver};
+       my $driver_cnt     = $pn_arg_ref->{driver_cnt};
+       my $full_node      = $pn_arg_ref->{full_node};
+       my $node           = $pn_arg_ref->{node};
+       my $node_enabled   = $pn_arg_ref->{node_enabled};
+       my $white_list     = $pn_arg_ref->{white_list};
+
+       my $pr_flags       = '-' x $num_pr_flags;
+
+
+       # ----- set flags in $pr_flags
+
+       if ($compatible_cnt > 1) {
+               &set_flag(\$pr_flags, $pr_flag_pos_mcompatible);
+       }
+
+       if ($config_cnt > 1) {
+               &set_flag(\$pr_flags, $pr_flag_pos_mconfig);
+       }
+
+       if ($driver_cnt >= 1) {
+               &set_flag(\$pr_flags, $pr_flag_pos_driver);
+       }
+
+       if ($driver_cnt > 1) {
+               &set_flag(\$pr_flags, $pr_flag_pos_mdriver);
+       }
+
+       # These strings are the same way the linux kernel tests.
+       # The ePapr lists of values is slightly different.
+       if (!(
+             ($node_enabled eq "") ||
+             ($node_enabled eq "ok") ||
+             ($node_enabled eq "okay")
+            )) {
+               &set_flag(\$pr_flags, $pr_flag_pos_node_not_enabled);
+       }
+
+       if ($white_list) {
+               &set_flag(\$pr_flags, $pr_flag_pos_white_list);
+       }
+
+       if (exists($driver_hard_code_list{$compat}) ||
+           (exists($driver_config_hard_code_list{$driver}) &&
+            ($driver ne "no_driver"))) {
+               &set_flag(\$pr_flags, $pr_flag_pos_hard_coded);
+       }
+
+       my @configs = split(' && ', $config);
+       for $configs (@configs) {
+               $not = $configs =~ /^!/;
+               $configs =~ s/^!//;
+
+               if (($configs ne "no_config") && ($configs ne "no_makefile")) {
+                       &set_flag(\$pr_flags, $pr_flag_pos_config);
+               }
+
+               if (($config_cnt >= 1) &&
+                   ($configs !~ /CONFIG_/) &&
+                   (($configs ne "no_config") && ($configs ne "no_makefile"))) {
+                       &set_flag(\$pr_flags, $pr_flag_pos_config_hard_coded);
+               }
+
+               my $existing_config = $existing_config{$configs};
+               if ($existing_config eq "m") {
+                       &set_flag(\$pr_flags, $pr_flag_pos_config_m);
+                       # Possible fail, depends on whether built in or
+                       # module is desired.
+                       &set_flag(\$pr_flags, $pr_flag_pos_config_test_fail);
+               } elsif ($existing_config eq "y") {
+                       &set_flag(\$pr_flags, $pr_flag_pos_config_y);
+                       if ($not) {
+                               &set_flag(\$pr_flags, $pr_flag_pos_config_test_fail);
+                       }
+               } elsif (($config_file) && ($configs =~ /CONFIG_/)) {
+                       &set_flag(\$pr_flags, $pr_flag_pos_config_none);
+                       if (!$not) {
+                               &set_flag(\$pr_flags, $pr_flag_pos_config_test_fail);
+                       }
+               }
+       }
+
+       # ----- include / exclude filters
+
+       if ($include_flag_pattern && ($pr_flags !~ m/$include_flag_pattern/)) {
+               return 0;
+       }
+
+       if ($exclude_flag_pattern && ($pr_flags =~ m/$exclude_flag_pattern/)) {
+               return 0;
+       }
+
+       if ($config_format) {
+               print "# ";
+       }
+       print "$pr_flags : ";
+
+       return 1;
+}
+
+
+sub print_node()
+{
+       # return number of lines printed
+
+       # some fields of pn_arg_ref might not be used in this function, but
+       # extract all of them anyway.
+       my $pn_arg_ref     = shift;
+
+       my $compat         = $pn_arg_ref->{compat};
+       my $compatible_cnt = $pn_arg_ref->{compatible_cnt};
+       my $config         = $pn_arg_ref->{config};
+       my $config_cnt     = $pn_arg_ref->{config_cnt};
+       my $driver         = $pn_arg_ref->{driver};
+       my $driver_cnt     = $pn_arg_ref->{driver_cnt};
+       my $full_node      = $pn_arg_ref->{full_node};
+       my $node           = $pn_arg_ref->{node};
+       my $node_enabled   = $pn_arg_ref->{node_enabled};
+       my $white_list     = $pn_arg_ref->{white_list};
+
+       my $separator;
+
+       if (! &print_flags($pn_arg_ref)) {
+               return 0;
+       }
+
+
+       if ($short_name) {
+               print "$node";
+       } else {
+               print "$full_node";
+       }
+       print " : $compat : $driver : $config : ";
+
+       my @configs = split(' && ', $config);
+
+       if ($config_file) {
+               for $configs (@configs) {
+                       $configs =~ s/^!//;
+                       my $existing_config = $existing_config{$configs};
+                       if (!$existing_config) {
+                               # check for /-m/, /-y/, or /-objs/
+                               if ($configs !~ /CONFIG_/) {
+                                       $existing_config = "x";
+                               };
+                       };
+                       if ($existing_config) {
+                               print "$separator", "$existing_config";
+                               $separator = ", ";
+                       } else {
+                               print "$separator", "n";
+                               $separator = ", ";
+                       }
+               }
+       } else {
+               print "none";
+       }
+
+       print "\n";
+
+       if ($config_format) {
+               for $configs (@configs) {
+                       $not = $configs =~ /^!/;
+                       $configs =~ s/^!//;
+                       my $existing_config = $existing_config{$configs};
+
+                       if ($not) {
+                               if ($configs !~ /CONFIG_/) {
+                                       print "# $configs\n";
+                               } elsif ($existing_config eq "m") {
+                                       print "# $configs is m\n";
+                                       print "# $configs=n\n";
+                               } elsif ($existing_config eq "y") {
+                                       print "# $configs is set\n";
+                                       print "# $configs=n\n";
+                               } else {
+                                       print "# $configs is not set\n";
+                                       print "# $configs=n\n";
+                               }
+
+                       } else {
+                               if ($configs !~ /CONFIG_/) {
+                                       print "# $configs\n";
+                               } elsif ($existing_config eq "m") {
+                                       print "# $configs is m\n";
+                                       print "# $configs=y\n";
+                               } elsif ($existing_config eq "y") {
+                                       print "# $configs is set\n";
+                                       print "# $configs=y\n";
+                               } else {
+                                       print "# $configs is not set\n";
+                                       print "# $configs=y\n";
+                               }
+                       }
+               }
+       }
+
+       return 1;
+}
+
+
+sub scan_makefile
+{
+       my $pn_arg_ref    = shift;
+       my $driver        = shift;
+
+       # ----- Find Kconfig symbols that enable driver
+
+       my ($dir, $base) = $driver =~ m{(.*)/(.*).c};
+
+       my $makefile = $dir . "/Makefile";
+       if (! -r $makefile) {
+               $makefile = $dir . "/Kbuild";
+       }
+       if (! -r $makefile) {
+               my $config;
+
+               $config = 'no_makefile';
+               push @{ $driver_config{$driver} }, $config;
+               return;
+       }
+
+       if (!open(MAKEFILE_FILE, "<", "$makefile")) {
+               return;
+       }
+
+       my $line;
+       my @config;
+       my @if_config;
+       my @make_var;
+
+       NEXT_LINE:
+       while ($next_line = <MAKEFILE_FILE>) {
+               my $config;
+               my $if_config;
+               my $ifdef;
+               my $ifeq;
+               my $ifndef;
+               my $ifneq;
+               my $ifdef_config;
+               my $ifeq_config;
+               my $ifndef_config;
+               my $ifneq_config;
+
+               chomp($next_line);
+               $line = $line . $next_line;
+               if ($next_line =~ /\\$/) {
+                       $line =~ s/\\$/ /;
+                       next NEXT_LINE;
+               }
+               if ($line =~ /^\s*#/) {
+                       $line = "";
+                       next NEXT_LINE;
+               }
+
+               # -----  condition ... else ... endif
+
+               if ($line =~ /^([ ]\s*|)else\b/) {
+                       $if_config = "!" . pop @if_config;
+                       $if_config =~ s/^!!//;
+                       push @if_config, $if_config;
+                       $line =~ s/^([ ]\s*|)else\b//;
+               }
+
+               ($null, $ifeq_config,  $ifeq_config_val )  = $line =~ /^([ ]\s*|)ifeq\b.*\b(CONFIG_[A-Za-z0-9_]*)(.*)/;
+               ($null, $ifneq_config, $ifneq_config_val)  = $line =~ /^([ ]\s*|)ifneq\b.*\b(CONFIG_[A-Za-z0-9_]*)(.*)/;
+               ($null, $ifdef_config)                     = $line =~ /^([ ]\s*|)ifdef\b.*\b(CONFIG_[A-Za-z0-9_]*)/;
+               ($null, $ifndef_config)                    = $line =~ /^([ ]\s*|)ifndef\b.*\b(CONFIG_[A-Za-z0-9_]*)/;
+
+               ($null, $ifeq)   = $line =~ /^([ ]\s*|)ifeq\b\s*(.*)/;
+               ($null, $ifneq)  = $line =~ /^([ ]\s*|)ifneq\b\s*(.*)/;
+               ($null, $ifdef)  = $line =~ /^([ ]\s*|)ifdef\b\s*(.*)/;
+               ($null, $ifndef) = $line =~ /^([ ]\s*|)ifndef\b\s*(.*)/;
+
+               # Order of tests is important.  Prefer "CONFIG_*" regex match over
+               # less specific regex match.
+               if ($ifdef_config) {
+                       $if_config = $ifdef_config;
+               } elsif ($ifeq_config) {
+                       if ($ifeq_config_val =~ /y/) {
+                               $if_config = $ifeq_config;
+                       } else {
+                               $if_config = "!" . $ifeq_config;
+                       }
+               } elsif ($ifndef_config) {
+                       $if_config = "!" . $ifndef_config;
+               } elsif ($ifneq_config) {
+                       if ($ifneq_config_val =~ /y/) {
+                               $if_config = "!" . $ifneq_config;
+                       } else {
+                               $if_config = $ifneq_config;
+                       }
+               } elsif ($ifdef) {
+                       $if_config = $ifdef;
+               } elsif ($ifeq) {
+                       $if_config = $ifeq;
+               } elsif ($ifndef) {
+                       $if_config = "!" . $ifndef;
+               } elsif ($ifneq) {
+                       $if_config = "!" . $ifneq;
+               } else {
+                       $if_config = "";
+               }
+               $if_config =~ s/^!!//;
+
+               if ($if_config) {
+                       push @if_config, $if_config;
+                       $line = "";
+                       next NEXT_LINE;
+               }
+
+               if ($line =~ /^([ ]\s*|)endif\b/) {
+                       pop @if_config;
+                       $line = "";
+                       next NEXT_LINE;
+               }
+
+               # ----- simple CONFIG_* = *.[co]  or  xxx [+:?]*= *.[co]
+               # Most makefiles select on *.o, but
+               # arch/powerpc/boot/Makefile selects on *.c
+
+               ($config) = $line =~ /(CONFIG_[A-Za-z0-9_]+).*\b$base.[co]\b/;
+
+               # ----- match a make variable instead of *.[co]
+               # Recursively expanded variables are not handled.
+
+               if (!$config) {
+                       my $make_var;
+                       ($make_var) = $line =~ /\s*(\S+?)\s*[+:\?]*=.*\b$base.[co]\b/;
+                       if ($make_var) {
+                               if ($make_var =~ /[a-zA-Z0-9]+-[ym]/) {
+                                       $config = $make_var;
+                               } elsif ($make_var =~ /[a-zA-Z0-9]+-objs/) {
+                                       $config = $make_var;
+                               } else {
+                                       push @make_var, $make_var;
+                               }
+                       }
+               }
+
+               if (!$config) {
+                       for $make_var (@make_var) {
+                               ($config) = $line =~ /(CONFIG_[A-Za-z0-9_]+).*\b$make_var\b/;
+                               last if ($config);
+                       }
+               }
+
+               if (!$config) {
+                       for $make_var (@make_var) {
+                               ($config) = $line =~ /\s*(\S+?)\s*[+:\?]*=.*\b$make_var\b/;
+                               last if ($config);
+                       }
+               }
+
+               # ----- next if no config found
+
+               if (!$config) {
+                       $line = "";
+                       next NEXT_LINE;
+               }
+
+               for $if_config (@if_config) {
+                       $config = $if_config . " && " . $config;
+               }
+
+               push @{ $driver_config{$driver} }, $config;
+
+               $line = "";
+       }
+
+       close(MAKEFILE_FILE);
+
+}
+
+
+sub find_kconfig
+{
+       my $pn_arg_ref    = shift;
+       my $driver        = shift;
+
+       my $lines_printed = 0;
+       my @configs;
+
+       if (!@{ $driver_config{$driver} }) {
+               &scan_makefile($pn_arg_ref, $driver);
+               if (!@{ $driver_config{$driver} }) {
+                       push @{ $driver_config{$driver} }, "no_config";
+               }
+       }
+
+       @configs = @{ $driver_config{$driver} };
+
+       $$pn_arg_ref{config_cnt} = $#configs + 1;
+       for my $config (@configs) {
+               $$pn_arg_ref{config} = $config;
+               $lines_printed += &print_node($pn_arg_ref);
+       }
+
+       return $lines_printed;
+}
+
+
+sub handle_compatible()
+{
+       my $full_node     = shift;
+       my $node          = shift;
+       my $compatible    = shift;
+       my $node_enabled  = shift;
+
+       my $compat;
+       my $lines_printed = 0;
+       my %pn_arg        = ();
+
+       return if (!$node or !$compatible);
+
+       # Do not process compatible property of root node,
+       # it is used to match board, not to bind a driver.
+       return if ($node eq "/");
+
+       $pn_arg{full_node}    = $full_node;
+       $pn_arg{node}         = $node;
+       $pn_arg{node_enabled} = $node_enabled;
+
+       my @compatibles = split('", "', $compatible);
+
+       $compatibles[0] =~ s/^"//;
+       $compatibles[$#compatibles] =~ s/"$//;
+
+       $pn_arg{compatible_cnt} = $#compatibles + 1;
+
+       COMPAT:
+       for $compat (@compatibles) {
+
+               $pn_arg{compat}     = $compat;
+               $pn_arg{driver_cnt} = 0;
+               $pn_arg{white_list} = 0;
+
+               if (exists($compat_white_list{$compat})) {
+                       $pn_arg{white_list} = 1;
+                       $pn_arg{driver}     = "no_driver";
+                       $pn_arg{config_cnt} = 1;
+                       $pn_arg{config}     = "no_config";
+                       $lines_printed += &print_node(\%pn_arg);
+                       next COMPAT;
+               }
+
+               # ----- if compat previously seen, use cached info
+
+               if (exists($compat_driver{$compat})) {
+                       for my $driver (@{ $compat_driver{$compat} }) {
+                               $pn_arg{driver}     = $driver;
+                               $pn_arg{driver_cnt} = $driver_count{$compat};
+                               $pn_arg{config_cnt} = $#{ $driver_config{$driver}} + 1;
+
+                               for my $config (@{ $driver_config{$driver} }) {
+                                       $pn_arg{config} = $config;
+                                       $lines_printed += &print_node(\%pn_arg);
+                               }
+
+                               if (!@{ $driver_config{$driver} }) {
+                                       # no config cached yet
+                                       # $driver in %driver_hard_code_list
+                                       # but not %driver_config_hard_code_list
+                                       $lines_printed += &find_kconfig(\%pn_arg, $driver);
+                               }
+                       }
+                       next COMPAT;
+               }
+
+
+               # ----- Find drivers (source files that contain compatible)
+
+               # this will miss arch/sparc/include/asm/parport.h
+               # It is better to move the compatible out of the .h
+               # than to add *.h. to the files list, because *.h generates
+               # a lot of false negatives.
+               my $files = '"*.c"';
+               my $drivers = `git grep -l '"$compat"' -- $files`;
+               chomp($drivers);
+               if ($drivers eq "") {
+                       $pn_arg{driver} = "no_driver";
+                       $pn_arg{config_cnt} = 1;
+                       $pn_arg{config} = "no_config";
+                       push @{ $compat_driver{$compat} }, "no_driver";
+                       $lines_printed += &print_node(\%pn_arg);
+                       next COMPAT;
+               }
+
+               my @drivers = split("\n", $drivers);
+               $driver_count{$compat} = $#drivers + 1;
+               $pn_arg{driver_cnt}    = $#drivers + 1;
+
+               DRIVER:
+               for my $driver (@drivers) {
+                       push @{ $compat_driver{$compat} }, $driver;
+                       $pn_arg{driver} = $driver;
+
+                       # ----- if driver previously seen, use cached info
+
+                       $pn_arg{config_cnt} = $#{ $driver_config{$driver} } + 1;
+                       for my $config (@{ $driver_config{$driver} }) {
+                               $pn_arg{config} = $config;
+                               $lines_printed += &print_node(\%pn_arg);
+                       }
+                       if (@{ $driver_config{$driver} }) {
+                               next DRIVER;
+                       }
+
+                       if ($black_list_driver) {
+                               for $black (@black_list_driver) {
+                                       next DRIVER if ($driver =~ /^$black$/);
+                               }
+                       }
+
+
+                       # ----- Find Kconfig symbols that enable driver
+
+                       $lines_printed += &find_kconfig(\%pn_arg, $driver);
+
+               }
+       }
+
+       # White space (line) between nodes for readability.
+       # Each node may report several compatibles.
+       # For each compatible, multiple drivers may be reported.
+       # For each driver, multiple CONFIG_ options may be reported.
+       if ($lines_printed) {
+               print "\n";
+       }
+}
+
+sub read_dts()
+{
+       my $file         = shift;
+
+       my $compatible   = "";
+       my $line;
+       my $node         = "";
+       my $node_enabled = "";
+
+       if (! -r $file) {
+               print STDERR "file '$file' is not readable or does not exist\n";
+               exit 3;
+       }
+
+       if (!open(DT_FILE, "-|", "$dtx_diff $file")) {
+               print STDERR "\n";
+               print STDERR "shell command failed:\n";
+               print STDERR "   $dtx_diff $file\n";
+               print STDERR "\n";
+               exit 3;
+       }
+
+       FILE:
+       while ($line = <DT_FILE>) {
+               chomp($line);
+
+               if ($line =~ /{/) {
+
+                       &handle_compatible($full_node, $node, $compatible,
+                                          $node_enabled);
+
+                       while ($end_node_count-- > 0) {
+                               pop @full_node;
+                       };
+                       $end_node_count = 0;
+                       $full_node = @full_node[-1];
+
+                       $node = $line;
+                       $node =~ s/^\s*(.*)\s+\{.*/$1/;
+                       $node =~ s/.*: //;
+                       if ($node eq '/' ) {
+                               $full_node = '/';
+                       } elsif ($full_node ne '/') {
+                               $full_node = $full_node . '/' . $node;
+                       } else {
+                               $full_node = '/' . $node;
+                       }
+                       push @full_node, $full_node;
+
+                       $compatible = "";
+                       $node_enabled = "";
+                       next FILE;
+               }
+
+               if ($line =~ /}/) {
+                       $end_node_count++;
+               }
+
+               if ($line =~ /(\s+|^)status =/) {
+                       $node_enabled = $line;
+                       $node_enabled =~ s/^\t*//;
+                       $node_enabled =~ s/^status = "//;
+                       $node_enabled =~ s/";$//;
+                       next FILE;
+               }
+
+               if ($line =~ /(\s+|^)compatible =/) {
+                       # Extract all compatible entries for this device
+                       # White space matching here and in handle_compatible() is
+                       # precise, because input format is the output of dtc,
+                       # which is invoked by dtx_diff.
+                       $compatible = $line;
+                       $compatible =~ s/^\t*//;
+                       $compatible =~ s/^compatible = //;
+                       $compatible =~ s/;$//;
+               }
+       }
+
+       &handle_compatible($full_node, $node, $compatible, $node_enabled);
+
+       close(DT_FILE);
+}
+
+
+sub read_config_file()
+{
+       if (! -r $config_file) {
+               print STDERR "file '$config_file' is not readable or does not exist\n";
+               exit 2;
+       }
+
+       if (!open(CONFIG_FILE, "<", "$config_file")) {
+               print STDERR "open $config_file failed\n";
+               exit 2;
+       }
+
+       my @line;
+
+       LINE:
+       while ($line = <CONFIG_FILE>) {
+               chomp($line);
+               next LINE if ($line =~ /^\s*#/);
+               next LINE if ($line =~ /^\s*$/);
+               @line = split /=/, $line;
+               $existing_config{@line[0]} = @line[1];
+       }
+
+       close(CONFIG_FILE);
+}
+
+
+sub cmd_line_err()
+{
+       my $msg = shift;
+
+       print STDERR "\n";
+       print STDERR "   ERROR processing command line options\n";
+       print STDERR "         $msg\n" if ($msg ne "");
+       print STDERR "\n";
+       print STDERR "   For help, type '$script_name --help'\n";
+       print STDERR "\n";
+}
+
+
+# -----------------------------------------------------------------------------
+# program entry point
+
+Getopt::Long::Configure("no_ignore_case", "bundling");
+
+if (!GetOptions(
+       "c=s"               => \$config_file,
+       "config=s"          => \$config_file,
+       "config-format"     => \$config_format,
+       "exclude-flag=s"    => \@exclude_flag,
+       "h"                 => \$help,
+       "help"              => \$help,
+       "black-list-driver" => \$black_list_driver,
+       "white-list-config" => \$white_list_config,
+       "white-list-driver" => \$white_list_driver,
+       "include-flag=s"    => \@include_flag,
+       "include-suspect"   => \$include_suspect,
+       "short-name"        => \$short_name,
+       "show-lists"        => \$show_lists,
+       "version"           => \$version,
+       )) {
+
+       &cmd_line_err();
+
+       exit 1;
+}
+
+
+my $exit_after_messages = 0;
+
+if ($version) {
+       print STDERR "\n$script_name  $VUFX\n\n";
+       $exit_after_messages = 1;
+}
+
+
+if ($help) {
+       &usage;
+       $exit_after_messages = 1;
+}
+
+
+if ($show_lists) {
+
+       print "\n";
+       print "These compatibles are hard coded to have no driver.\n";
+       print "\n";
+       for my $compat (sort keys %compat_white_list) {
+               print "   $compat\n";
+       }
+
+
+       print "\n\n";
+       print "The driver for these compatibles is hard coded (white list).\n";
+       print "\n";
+       my $max_compat_len = 0;
+       for my $compat (sort keys %driver_hard_code_list) {
+               if (length $compat > $max_compat_len) {
+                       $max_compat_len = length $compat;
+               }
+       }
+       for my $compat (sort keys %driver_hard_code_list) {
+               if (($driver ne "hardcoded_no_driver") && ($driver ne "no_driver")) {
+                       my $first = 1;
+                       for my $driver (@{ $driver_hard_code_list{$compat} }) {
+                               if ($first) {
+                                       print "   $compat";
+                                       print " " x ($max_compat_len - length $compat);
+                                       $first = 0;
+                               } else {
+                                       print "   ", " " x $max_compat_len;
+                               }
+                               print "  $driver\n";
+                       }
+               }
+       }
+
+
+       print "\n\n";
+       print "The configuration option for these drivers is hard coded (white list).\n";
+       print "\n";
+       my $max_driver_len = 0;
+       for my $driver (sort keys %driver_config_hard_code_list) {
+               if (length $driver > $max_driver_len) {
+                       $max_driver_len = length $driver;
+               }
+       }
+       for my $driver (sort keys %driver_config_hard_code_list) {
+               if (($driver ne "hardcoded_no_driver") && ($driver ne "no_driver")) {
+                       my $first = 1;
+                       for my $config (@{ $driver_config_hard_code_list{$driver} }) {
+                               if ($first) {
+                                       print "   $driver";
+                                       print " " x ($max_driver_len - length $driver);
+                                       $first = 0;
+                               } else {
+                                       print "   ", " " x $max_driver_len;
+                               }
+                               print "  $config\n";
+                       }
+               }
+       }
+
+
+       print "\n\n";
+       print "These drivers are black listed.\n";
+       print "\n";
+       for my $driver (@black_list_driver) {
+               print "   $driver\n";
+       }
+
+       print "\n";
+
+       $exit_after_messages = 1;
+}
+
+
+if ($exit_after_messages) {
+       exit 0;
+}
+
+
+$exclude_flag_pattern = "[";
+for my $exclude_flag (@exclude_flag) {
+       $exclude_flag_pattern = $exclude_flag_pattern . $exclude_flag;
+}
+$exclude_flag_pattern = $exclude_flag_pattern . "]";
+# clean up if empty
+$exclude_flag_pattern =~ s/^\[\]$//;
+
+
+$include_flag_pattern = "[";
+for my $include_flag (@include_flag) {
+       $include_flag_pattern = $include_flag_pattern . $include_flag;
+}
+$include_flag_pattern = $include_flag_pattern . "]";
+# clean up if empty
+$include_flag_pattern =~ s/^\[\]$//;
+
+
+if ($exclude_flag_pattern) {
+       my $found = 0;
+       for $pr_flag_value (@pr_flag_value) {
+               if ($exclude_flag_pattern =~ m/$pr_flag_value/) {
+                       $found = 1;
+               }
+       }
+       if (!$found) {
+               &cmd_line_err("invalid value for FLAG in --exclude-flag\n");
+               exit 1
+       }
+}
+
+if ($include_flag_pattern) {
+       my $found = 0;
+       for $pr_flag_value (@pr_flag_value) {
+               if ($include_flag_pattern =~ m/$pr_flag_value/) {
+                       $found = 1;
+               }
+       }
+       if (!$found) {
+               &cmd_line_err("invalid value for FLAG in --include-flag\n");
+               exit 1
+       }
+}
+
+if ($include_suspect) {
+       $include_flag_pattern =~ s/\[//;
+       $include_flag_pattern =~ s/\]//;
+       $include_flag_pattern = "[" . $include_flag_pattern . "A-Z]";
+}
+
+if ($exclude_flag_pattern =~ m/$include_flag_pattern/) {
+       &cmd_line_err("the same flag appears in both --exclude-flag and --include-flag or --include-suspect\n");
+       exit 1
+}
+
+
+# ($#ARGV < 0) is valid for --help, --version
+if ($#ARGV < 0) {
+       &cmd_line_err("device-tree... is required");
+       exit 1
+}
+
+
+if ($config_file) {
+       &read_config_file();
+}
+
+
+# avoid pushing duplicates for this value
+$driver = "hardcoded_no_driver";
+for $config ( @{ $driver_config_hard_code_list{$driver} } ) {
+       push @{ $driver_config{$driver} }, $config;
+}
+
+if ($white_list_driver) {
+       for my $compat (keys %driver_hard_code_list) {
+               for my $driver (@{ $driver_hard_code_list{$compat} }) {
+                       push @{ $compat_driver{$compat} }, $driver;
+                       if ($driver ne "hardcoded_no_driver") {
+                               $driver_count{$compat} = scalar @{ $compat_driver{$compat} };
+                       }
+               }
+       }
+}
+
+if ($white_list_config) {
+       for my $driver (keys %driver_config_hard_code_list) {
+               if ($driver ne "hardcoded_no_driver") {
+                       for $config ( @{ $driver_config_hard_code_list{$driver} } ) {
+                               push @{ $driver_config{$driver} }, $config;
+                       }
+               }
+       }
+}
+
+if (-x "scripts/dtc/dtx_diff") {
+       $dtx_diff = "scripts/dtc/dtx_diff";
+} else {
+
+       print STDERR "\n";
+       print STDERR "$script_name must be run from the root directory of a Linux kernel tree\n";
+       print STDERR "\n";
+       exit 3;
+}
+
+for $file (@ARGV) {
+       &read_dts($file);
+}
diff --git a/scripts/dtc/dtx_diff b/scripts/dtc/dtx_diff
index 959ab2646d38..ec47f95991a3 100755
--- a/scripts/dtc/dtx_diff
+++ b/scripts/dtc/dtx_diff
@@ -266,7 +266,7 @@ DTC="${__KBUILD_OUTPUT}/scripts/dtc/dtc"
 
 if [ ! -x ${DTC} ] ; then
 	__DTC="dtc"
-	if grep -q "^CONFIG_DTC=y" ${__KBUILD_OUTPUT}/.config ; then
+	if grep -q "^CONFIG_DTC=y" ${__KBUILD_OUTPUT}/.config 2>/dev/null; then
 		make_command='
          make scripts'
 	else
diff --git a/scripts/gcc-plugin.sh b/scripts/gcc-plugin.sh
new file mode 100755
index 000000000000..fb9207565471
--- /dev/null
+++ b/scripts/gcc-plugin.sh
@@ -0,0 +1,51 @@
+#!/bin/sh
+srctree=$(dirname "$0")
+gccplugins_dir=$($3 -print-file-name=plugin)
+plugincc=$($1 -E -x c++ - -o /dev/null -I"${srctree}"/gcc-plugins -I"${gccplugins_dir}"/include 2>&1 <<EOF
+#include "gcc-common.h"
+#if BUILDING_GCC_VERSION >= 4008 || defined(ENABLE_BUILD_WITH_CXX)
+#warning $2 CXX
+#else
+#warning $1 CC
+#endif
+EOF
+)
+
+if [ $? -ne 0 ]
+then
+	exit 1
+fi
+
+case "$plugincc" in
+	*"$1 CC"*)
+		echo "$1"
+		exit 0
+		;;
+
+	*"$2 CXX"*)
+		# the c++ compiler needs another test, see below
+		;;
+
+	*)
+		exit 1
+		;;
+esac
+
+# we need a c++ compiler that supports the designated initializer GNU extension
+plugincc=$($2 -c -x c++ -std=gnu++98 - -fsyntax-only -I"${srctree}"/gcc-plugins -I"${gccplugins_dir}"/include 2>&1 <<EOF
+#include "gcc-common.h"
+class test {
+public:
+	int test;
+} test = {
+	.test = 1
+};
+EOF
+)
+
+if [ $? -eq 0 ]
+then
+	echo "$2"
+	exit 0
+fi
+exit 1
diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile
new file mode 100644
index 000000000000..88c8ec47232b
--- /dev/null
+++ b/scripts/gcc-plugins/Makefile
@@ -0,0 +1,27 @@
+GCC_PLUGINS_DIR := $(shell $(CC) -print-file-name=plugin)
+
+ifeq ($(PLUGINCC),$(HOSTCC))
+  HOSTLIBS := hostlibs
+  HOST_EXTRACFLAGS += -I$(GCC_PLUGINS_DIR)/include -I$(src) -std=gnu99 -ggdb
+  export HOST_EXTRACFLAGS
+else
+  HOSTLIBS := hostcxxlibs
+  HOST_EXTRACXXFLAGS += -I$(GCC_PLUGINS_DIR)/include -I$(src) -std=gnu++98 -fno-rtti
+  HOST_EXTRACXXFLAGS += -fno-exceptions -fasynchronous-unwind-tables -ggdb
+  HOST_EXTRACXXFLAGS += -Wno-narrowing -Wno-unused-variable
+  export HOST_EXTRACXXFLAGS
+endif
+
+export GCCPLUGINS_DIR HOSTLIBS
+
+ifneq ($(CFLAGS_KCOV), $(SANCOV_PLUGIN))
+  GCC_PLUGIN := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGIN))
+endif
+
+$(HOSTLIBS)-y := $(GCC_PLUGIN)
+always := $($(HOSTLIBS)-y)
+
+cyc_complexity_plugin-objs := cyc_complexity_plugin.o
+sancov_plugin-objs := sancov_plugin.o
+
+clean-files += *.so
diff --git a/scripts/gcc-plugins/cyc_complexity_plugin.c b/scripts/gcc-plugins/cyc_complexity_plugin.c
new file mode 100644
index 000000000000..34df974c6ba3
--- /dev/null
+++ b/scripts/gcc-plugins/cyc_complexity_plugin.c
@@ -0,0 +1,73 @@
+/*
+ * Copyright 2011-2016 by Emese Revfy <re.emese@gmail.com>
+ * Licensed under the GPL v2, or (at your option) v3
+ *
+ * Homepage:
+ * https://github.com/ephox-gcc-plugins/cyclomatic_complexity
+ *
+ * http://en.wikipedia.org/wiki/Cyclomatic_complexity
+ * The complexity M is then defined as:
+ * M = E - N + 2P
+ * where
+ *
+ *  E = the number of edges of the graph
+ *  N = the number of nodes of the graph
+ *  P = the number of connected components (exit nodes).
+ *
+ * Usage (4.5 - 5):
+ * $ make clean; make run
+ */
+
+#include "gcc-common.h"
+
+int plugin_is_GPL_compatible;
+
+static struct plugin_info cyc_complexity_plugin_info = {
+	.version	= "20160225",
+	.help		= "Cyclomatic Complexity\n",
+};
+
+static unsigned int cyc_complexity_execute(void)
+{
+	int complexity;
+	expanded_location xloc;
+
+	/* M = E - N + 2P */
+	complexity = n_edges_for_fn(cfun) - n_basic_blocks_for_fn(cfun) + 2;
+
+	xloc = expand_location(DECL_SOURCE_LOCATION(current_function_decl));
+	fprintf(stderr, "Cyclomatic Complexity %d %s:%s\n", complexity,
+		xloc.file, DECL_NAME_POINTER(current_function_decl));
+
+	return 0;
+}
+
+#define PASS_NAME cyc_complexity
+
+#define NO_GATE
+#define TODO_FLAGS_FINISH TODO_dump_func
+
+#include "gcc-generate-gimple-pass.h"
+
+int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version)
+{
+	const char * const plugin_name = plugin_info->base_name;
+	struct register_pass_info cyc_complexity_pass_info;
+
+	cyc_complexity_pass_info.pass				= make_cyc_complexity_pass();
+	cyc_complexity_pass_info.reference_pass_name		= "ssa";
+	cyc_complexity_pass_info.ref_pass_instance_number	= 1;
+	cyc_complexity_pass_info.pos_op				= PASS_POS_INSERT_AFTER;
+
+	if (!plugin_default_version_check(version, &gcc_version)) {
+		error(G_("incompatible gcc/plugin versions"));
+		return 1;
+	}
+
+	register_callback(plugin_name, PLUGIN_INFO, NULL,
+				&cyc_complexity_plugin_info);
+	register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL,
+				&cyc_complexity_pass_info);
+
+	return 0;
+}
diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h
new file mode 100644
index 000000000000..172850bcd0d9
--- /dev/null
+++ b/scripts/gcc-plugins/gcc-common.h
@@ -0,0 +1,830 @@
+#ifndef GCC_COMMON_H_INCLUDED
+#define GCC_COMMON_H_INCLUDED
+
+#include "bversion.h"
+#if BUILDING_GCC_VERSION >= 6000
+#include "gcc-plugin.h"
+#else
+#include "plugin.h"
+#endif
+#include "plugin-version.h"
+#include "config.h"
+#include "system.h"
+#include "coretypes.h"
+#include "tm.h"
+#include "line-map.h"
+#include "input.h"
+#include "tree.h"
+
+#include "tree-inline.h"
+#include "version.h"
+#include "rtl.h"
+#include "tm_p.h"
+#include "flags.h"
+#include "hard-reg-set.h"
+#include "output.h"
+#include "except.h"
+#include "function.h"
+#include "toplev.h"
+#include "basic-block.h"
+#include "intl.h"
+#include "ggc.h"
+#include "timevar.h"
+
+#include "params.h"
+
+#if BUILDING_GCC_VERSION <= 4009
+#include "pointer-set.h"
+#else
+#include "hash-map.h"
+#endif
+
+#include "emit-rtl.h"
+#include "debug.h"
+#include "target.h"
+#include "langhooks.h"
+#include "cfgloop.h"
+#include "cgraph.h"
+#include "opts.h"
+
+#if BUILDING_GCC_VERSION == 4005
+#include <sys/mman.h>
+#endif
+
+#if BUILDING_GCC_VERSION >= 4007
+#include "tree-pretty-print.h"
+#include "gimple-pretty-print.h"
+#endif
+
+#if BUILDING_GCC_VERSION >= 4006
+#include "c-family/c-common.h"
+#else
+#include "c-common.h"
+#endif
+
+#if BUILDING_GCC_VERSION <= 4008
+#include "tree-flow.h"
+#else
+#include "tree-cfgcleanup.h"
+#include "tree-ssa-operands.h"
+#include "tree-into-ssa.h"
+#endif
+
+#if BUILDING_GCC_VERSION >= 4008
+#include "is-a.h"
+#endif
+
+#include "diagnostic.h"
+#include "tree-dump.h"
+#include "tree-pass.h"
+#include "predict.h"
+#include "ipa-utils.h"
+
+#if BUILDING_GCC_VERSION >= 4009
+#include "attribs.h"
+#include "varasm.h"
+#include "stor-layout.h"
+#include "internal-fn.h"
+#include "gimple-expr.h"
+#include "gimple-fold.h"
+#include "context.h"
+#include "tree-ssa-alias.h"
+#include "tree-ssa.h"
+#include "stringpool.h"
+#include "tree-ssanames.h"
+#include "print-tree.h"
+#include "tree-eh.h"
+#include "stmt.h"
+#include "gimplify.h"
+#endif
+
+#include "gimple.h"
+
+#if BUILDING_GCC_VERSION >= 4009
+#include "tree-ssa-operands.h"
+#include "tree-phinodes.h"
+#include "tree-cfg.h"
+#include "gimple-iterator.h"
+#include "gimple-ssa.h"
+#include "ssa-iterators.h"
+#endif
+
+#if BUILDING_GCC_VERSION >= 5000
+#include "builtins.h"
+#endif
+
+/* #include "expr.h" where are you... */
+extern rtx emit_move_insn(rtx x, rtx y);
+
+/* missing from basic_block.h... */
+extern void debug_dominance_info(enum cdi_direction dir);
+extern void debug_dominance_tree(enum cdi_direction dir, basic_block root);
+
+#if BUILDING_GCC_VERSION == 4006
+extern void debug_gimple_stmt(gimple);
+extern void debug_gimple_seq(gimple_seq);
+extern void print_gimple_seq(FILE *, gimple_seq, int, int);
+extern void print_gimple_stmt(FILE *, gimple, int, int);
+extern void print_gimple_expr(FILE *, gimple, int, int);
+extern void dump_gimple_stmt(pretty_printer *, gimple, int, int);
+#endif
+
+#define __unused __attribute__((__unused__))
+
+#define DECL_NAME_POINTER(node) IDENTIFIER_POINTER(DECL_NAME(node))
+#define DECL_NAME_LENGTH(node) IDENTIFIER_LENGTH(DECL_NAME(node))
+#define TYPE_NAME_POINTER(node) IDENTIFIER_POINTER(TYPE_NAME(node))
+#define TYPE_NAME_LENGTH(node) IDENTIFIER_LENGTH(TYPE_NAME(node))
+
+/* should come from c-tree.h if only it were installed for gcc 4.5... */
+#define C_TYPE_FIELDS_READONLY(TYPE) TREE_LANG_FLAG_1(TYPE)
+
+#if BUILDING_GCC_VERSION == 4005
+#define FOR_EACH_LOCAL_DECL(FUN, I, D)			\
+	for (tree vars = (FUN)->local_decls, (I) = 0;	\
+		vars && ((D) = TREE_VALUE(vars));	\
+		vars = TREE_CHAIN(vars), (I)++)
+#define DECL_CHAIN(NODE) (TREE_CHAIN(DECL_MINIMAL_CHECK(NODE)))
+#define FOR_EACH_VEC_ELT(T, V, I, P) \
+	for (I = 0; VEC_iterate(T, (V), (I), (P)); ++(I))
+#define TODO_rebuild_cgraph_edges 0
+#define SCOPE_FILE_SCOPE_P(EXP) (!(EXP))
+
+#ifndef O_BINARY
+#define O_BINARY 0
+#endif
+
+typedef struct varpool_node *varpool_node_ptr;
+
+static inline bool gimple_call_builtin_p(gimple stmt, enum built_in_function code)
+{
+	tree fndecl;
+
+	if (!is_gimple_call(stmt))
+		return false;
+	fndecl = gimple_call_fndecl(stmt);
+	if (!fndecl || DECL_BUILT_IN_CLASS(fndecl) != BUILT_IN_NORMAL)
+		return false;
+	return DECL_FUNCTION_CODE(fndecl) == code;
+}
+
+static inline bool is_simple_builtin(tree decl)
+{
+	if (decl && DECL_BUILT_IN_CLASS(decl) != BUILT_IN_NORMAL)
+		return false;
+
+	switch (DECL_FUNCTION_CODE(decl)) {
+	/* Builtins that expand to constants. */
+	case BUILT_IN_CONSTANT_P:
+	case BUILT_IN_EXPECT:
+	case BUILT_IN_OBJECT_SIZE:
+	case BUILT_IN_UNREACHABLE:
+	/* Simple register moves or loads from stack. */
+	case BUILT_IN_RETURN_ADDRESS:
+	case BUILT_IN_EXTRACT_RETURN_ADDR:
+	case BUILT_IN_FROB_RETURN_ADDR:
+	case BUILT_IN_RETURN:
+	case BUILT_IN_AGGREGATE_INCOMING_ADDRESS:
+	case BUILT_IN_FRAME_ADDRESS:
+	case BUILT_IN_VA_END:
+	case BUILT_IN_STACK_SAVE:
+	case BUILT_IN_STACK_RESTORE:
+	/* Exception state returns or moves registers around. */
+	case BUILT_IN_EH_FILTER:
+	case BUILT_IN_EH_POINTER:
+	case BUILT_IN_EH_COPY_VALUES:
+	return true;
+
+	default:
+	return false;
+	}
+}
+
+static inline void add_local_decl(struct function *fun, tree d)
+{
+	gcc_assert(TREE_CODE(d) == VAR_DECL);
+	fun->local_decls = tree_cons(NULL_TREE, d, fun->local_decls);
+}
+#endif
+
+#if BUILDING_GCC_VERSION <= 4006
+#define ANY_RETURN_P(rtx) (GET_CODE(rtx) == RETURN)
+#define C_DECL_REGISTER(EXP) DECL_LANG_FLAG_4(EXP)
+#define EDGE_PRESERVE 0ULL
+#define HOST_WIDE_INT_PRINT_HEX_PURE "%" HOST_WIDE_INT_PRINT "x"
+#define flag_fat_lto_objects true
+
+#define get_random_seed(noinit) ({						\
+	unsigned HOST_WIDE_INT seed;						\
+	sscanf(get_random_seed(noinit), "%" HOST_WIDE_INT_PRINT "x", &seed);	\
+	seed * seed; })
+
+#define int_const_binop(code, arg1, arg2)	\
+	int_const_binop((code), (arg1), (arg2), 0)
+
+static inline bool gimple_clobber_p(gimple s __unused)
+{
+	return false;
+}
+
+static inline bool gimple_asm_clobbers_memory_p(const_gimple stmt)
+{
+	unsigned i;
+
+	for (i = 0; i < gimple_asm_nclobbers(stmt); i++) {
+		tree op = gimple_asm_clobber_op(stmt, i);
+
+		if (!strcmp(TREE_STRING_POINTER(TREE_VALUE(op)), "memory"))
+			return true;
+	}
+
+	return false;
+}
+
+static inline tree builtin_decl_implicit(enum built_in_function fncode)
+{
+	return implicit_built_in_decls[fncode];
+}
+
+static inline int ipa_reverse_postorder(struct cgraph_node **order)
+{
+	return cgraph_postorder(order);
+}
+
+static inline struct cgraph_node *cgraph_create_node(tree decl)
+{
+	return cgraph_node(decl);
+}
+
+static inline struct cgraph_node *cgraph_get_create_node(tree decl)
+{
+	struct cgraph_node *node = cgraph_get_node(decl);
+
+	return node ? node : cgraph_node(decl);
+}
+
+static inline bool cgraph_function_with_gimple_body_p(struct cgraph_node *node)
+{
+	return node->analyzed && !node->thunk.thunk_p && !node->alias;
+}
+
+static inline struct cgraph_node *cgraph_first_function_with_gimple_body(void)
+{
+	struct cgraph_node *node;
+
+	for (node = cgraph_nodes; node; node = node->next)
+		if (cgraph_function_with_gimple_body_p(node))
+			return node;
+	return NULL;
+}
+
+static inline struct cgraph_node *cgraph_next_function_with_gimple_body(struct cgraph_node *node)
+{
+	for (node = node->next; node; node = node->next)
+		if (cgraph_function_with_gimple_body_p(node))
+			return node;
+	return NULL;
+}
+
+#define FOR_EACH_FUNCTION_WITH_GIMPLE_BODY(node) \
+	for ((node) = cgraph_first_function_with_gimple_body(); (node); \
+		(node) = cgraph_next_function_with_gimple_body(node))
+
+static inline void varpool_add_new_variable(tree decl)
+{
+	varpool_finalize_decl(decl);
+}
+#endif
+
+#if BUILDING_GCC_VERSION <= 4007
+#define FOR_EACH_FUNCTION(node)	\
+	for (node = cgraph_nodes; node; node = node->next)
+#define FOR_EACH_VARIABLE(node)	\
+	for (node = varpool_nodes; node; node = node->next)
+#define PROP_loops 0
+#define NODE_SYMBOL(node) (node)
+#define NODE_DECL(node) (node)->decl
+#define INSN_LOCATION(INSN) RTL_LOCATION(INSN)
+#define vNULL NULL
+
+static inline int bb_loop_depth(const_basic_block bb)
+{
+	return bb->loop_father ? loop_depth(bb->loop_father) : 0;
+}
+
+static inline bool gimple_store_p(gimple gs)
+{
+	tree lhs = gimple_get_lhs(gs);
+
+	return lhs && !is_gimple_reg(lhs);
+}
+
+static inline void gimple_init_singleton(gimple g __unused)
+{
+}
+#endif
+
+#if BUILDING_GCC_VERSION == 4007 || BUILDING_GCC_VERSION == 4008
+static inline struct cgraph_node *cgraph_alias_target(struct cgraph_node *n)
+{
+	return cgraph_alias_aliased_node(n);
+}
+#endif
+
+#if BUILDING_GCC_VERSION >= 4007 && BUILDING_GCC_VERSION <= 4009
+#define cgraph_create_edge(caller, callee, call_stmt, count, freq, nest) \
+	cgraph_create_edge((caller), (callee), (call_stmt), (count), (freq))
+#define cgraph_create_edge_including_clones(caller, callee, old_call_stmt, call_stmt, count, freq, nest, reason) \
+	cgraph_create_edge_including_clones((caller), (callee), (old_call_stmt), (call_stmt), (count), (freq), (reason))
+#endif
+
+#if BUILDING_GCC_VERSION <= 4008
+#define ENTRY_BLOCK_PTR_FOR_FN(FN)	ENTRY_BLOCK_PTR_FOR_FUNCTION(FN)
+#define EXIT_BLOCK_PTR_FOR_FN(FN)	EXIT_BLOCK_PTR_FOR_FUNCTION(FN)
+#define basic_block_info_for_fn(FN)	((FN)->cfg->x_basic_block_info)
+#define n_basic_blocks_for_fn(FN)	((FN)->cfg->x_n_basic_blocks)
+#define n_edges_for_fn(FN)		((FN)->cfg->x_n_edges)
+#define last_basic_block_for_fn(FN)	((FN)->cfg->x_last_basic_block)
+#define label_to_block_map_for_fn(FN)	((FN)->cfg->x_label_to_block_map)
+#define profile_status_for_fn(FN)	((FN)->cfg->x_profile_status)
+#define BASIC_BLOCK_FOR_FN(FN, N)	BASIC_BLOCK_FOR_FUNCTION((FN), (N))
+#define NODE_IMPLICIT_ALIAS(node)	(node)->same_body_alias
+#define VAR_P(NODE)			(TREE_CODE(NODE) == VAR_DECL)
+
+static inline bool tree_fits_shwi_p(const_tree t)
+{
+	if (t == NULL_TREE || TREE_CODE(t) != INTEGER_CST)
+		return false;
+
+	if (TREE_INT_CST_HIGH(t) == 0 && (HOST_WIDE_INT)TREE_INT_CST_LOW(t) >= 0)
+		return true;
+
+	if (TREE_INT_CST_HIGH(t) == -1 && (HOST_WIDE_INT)TREE_INT_CST_LOW(t) < 0 && !TYPE_UNSIGNED(TREE_TYPE(t)))
+		return true;
+
+	return false;
+}
+
+static inline bool tree_fits_uhwi_p(const_tree t)
+{
+	if (t == NULL_TREE || TREE_CODE(t) != INTEGER_CST)
+		return false;
+
+	return TREE_INT_CST_HIGH(t) == 0;
+}
+
+static inline HOST_WIDE_INT tree_to_shwi(const_tree t)
+{
+	gcc_assert(tree_fits_shwi_p(t));
+	return TREE_INT_CST_LOW(t);
+}
+
+static inline unsigned HOST_WIDE_INT tree_to_uhwi(const_tree t)
+{
+	gcc_assert(tree_fits_uhwi_p(t));
+	return TREE_INT_CST_LOW(t);
+}
+
+static inline const char *get_tree_code_name(enum tree_code code)
+{
+	gcc_assert(code < MAX_TREE_CODES);
+	return tree_code_name[code];
+}
+
+#define ipa_remove_stmt_references(cnode, stmt)
+
+typedef union gimple_statement_d gasm;
+typedef union gimple_statement_d gassign;
+typedef union gimple_statement_d gcall;
+typedef union gimple_statement_d gcond;
+typedef union gimple_statement_d gdebug;
+typedef union gimple_statement_d gphi;
+typedef union gimple_statement_d greturn;
+
+static inline gasm *as_a_gasm(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const gasm *as_a_const_gasm(const_gimple stmt)
+{
+	return stmt;
+}
+
+static inline gassign *as_a_gassign(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const gassign *as_a_const_gassign(const_gimple stmt)
+{
+	return stmt;
+}
+
+static inline gcall *as_a_gcall(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const gcall *as_a_const_gcall(const_gimple stmt)
+{
+	return stmt;
+}
+
+static inline gcond *as_a_gcond(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const gcond *as_a_const_gcond(const_gimple stmt)
+{
+	return stmt;
+}
+
+static inline gdebug *as_a_gdebug(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const gdebug *as_a_const_gdebug(const_gimple stmt)
+{
+	return stmt;
+}
+
+static inline gphi *as_a_gphi(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const gphi *as_a_const_gphi(const_gimple stmt)
+{
+	return stmt;
+}
+
+static inline greturn *as_a_greturn(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const greturn *as_a_const_greturn(const_gimple stmt)
+{
+	return stmt;
+}
+#endif
+
+#if BUILDING_GCC_VERSION == 4008
+#define NODE_SYMBOL(node) (&(node)->symbol)
+#define NODE_DECL(node) (node)->symbol.decl
+#endif
+
+#if BUILDING_GCC_VERSION >= 4008
+#define add_referenced_var(var)
+#define mark_sym_for_renaming(var)
+#define varpool_mark_needed_node(node)
+#define create_var_ann(var)
+#define TODO_dump_func 0
+#define TODO_dump_cgraph 0
+#endif
+
+#if BUILDING_GCC_VERSION <= 4009
+#define TODO_verify_il 0
+#define AVAIL_INTERPOSABLE AVAIL_OVERWRITABLE
+
+#define section_name_prefix LTO_SECTION_NAME_PREFIX
+#define fatal_error(loc, gmsgid, ...) fatal_error((gmsgid), __VA_ARGS__)
+
+typedef struct rtx_def rtx_insn;
+
+static inline void set_decl_section_name(tree node, const char *value)
+{
+	if (value)
+		DECL_SECTION_NAME(node) = build_string(strlen(value) + 1, value);
+	else
+		DECL_SECTION_NAME(node) = NULL;
+}
+#endif
+
+#if BUILDING_GCC_VERSION == 4009
+typedef struct gimple_statement_asm gasm;
+typedef struct gimple_statement_base gassign;
+typedef struct gimple_statement_call gcall;
+typedef struct gimple_statement_base gcond;
+typedef struct gimple_statement_base gdebug;
+typedef struct gimple_statement_phi gphi;
+typedef struct gimple_statement_base greturn;
+
+static inline gasm *as_a_gasm(gimple stmt)
+{
+	return as_a<gasm>(stmt);
+}
+
+static inline const gasm *as_a_const_gasm(const_gimple stmt)
+{
+	return as_a<const gasm>(stmt);
+}
+
+static inline gassign *as_a_gassign(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const gassign *as_a_const_gassign(const_gimple stmt)
+{
+	return stmt;
+}
+
+static inline gcall *as_a_gcall(gimple stmt)
+{
+	return as_a<gcall>(stmt);
+}
+
+static inline const gcall *as_a_const_gcall(const_gimple stmt)
+{
+	return as_a<const gcall>(stmt);
+}
+
+static inline gcond *as_a_gcond(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const gcond *as_a_const_gcond(const_gimple stmt)
+{
+	return stmt;
+}
+
+static inline gdebug *as_a_gdebug(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const gdebug *as_a_const_gdebug(const_gimple stmt)
+{
+	return stmt;
+}
+
+static inline gphi *as_a_gphi(gimple stmt)
+{
+	return as_a<gphi>(stmt);
+}
+
+static inline const gphi *as_a_const_gphi(const_gimple stmt)
+{
+	return as_a<const gphi>(stmt);
+}
+
+static inline greturn *as_a_greturn(gimple stmt)
+{
+	return stmt;
+}
+
+static inline const greturn *as_a_const_greturn(const_gimple stmt)
+{
+	return stmt;
+}
+#endif
+
+#if BUILDING_GCC_VERSION >= 4009
+#define TODO_ggc_collect 0
+#define NODE_SYMBOL(node) (node)
+#define NODE_DECL(node) (node)->decl
+#define cgraph_node_name(node) (node)->name()
+#define NODE_IMPLICIT_ALIAS(node) (node)->cpp_implicit_alias
+#endif
+
+#if BUILDING_GCC_VERSION >= 5000 && BUILDING_GCC_VERSION < 6000
+/* gimple related */
+template <>
+template <>
+inline bool is_a_helper<const gassign *>::test(const_gimple gs)
+{
+	return gs->code == GIMPLE_ASSIGN;
+}
+#endif
+
+#if BUILDING_GCC_VERSION >= 5000
+#define TODO_verify_ssa TODO_verify_il
+#define TODO_verify_flow TODO_verify_il
+#define TODO_verify_stmts TODO_verify_il
+#define TODO_verify_rtl_sharing TODO_verify_il
+
+#define INSN_DELETED_P(insn) (insn)->deleted()
+
+/* symtab/cgraph related */
+#define debug_cgraph_node(node) (node)->debug()
+#define cgraph_get_node(decl) cgraph_node::get(decl)
+#define cgraph_get_create_node(decl) cgraph_node::get_create(decl)
+#define cgraph_create_node(decl) cgraph_node::create(decl)
+#define cgraph_n_nodes symtab->cgraph_count
+#define cgraph_max_uid symtab->cgraph_max_uid
+#define varpool_get_node(decl) varpool_node::get(decl)
+
+#define cgraph_create_edge(caller, callee, call_stmt, count, freq, nest) \
+	(caller)->create_edge((callee), (call_stmt), (count), (freq))
+#define cgraph_create_edge_including_clones(caller, callee, old_call_stmt, call_stmt, count, freq, nest, reason) \
+	(caller)->create_edge_including_clones((callee), (old_call_stmt), (call_stmt), (count), (freq), (reason))
+
+typedef struct cgraph_node *cgraph_node_ptr;
+typedef struct cgraph_edge *cgraph_edge_p;
+typedef struct varpool_node *varpool_node_ptr;
+
+static inline void change_decl_assembler_name(tree decl, tree name)
+{
+	symtab->change_decl_assembler_name(decl, name);
+}
+
+static inline void varpool_finalize_decl(tree decl)
+{
+	varpool_node::finalize_decl(decl);
+}
+
+static inline void varpool_add_new_variable(tree decl)
+{
+	varpool_node::add(decl);
+}
+
+static inline unsigned int rebuild_cgraph_edges(void)
+{
+	return cgraph_edge::rebuild_edges();
+}
+
+static inline cgraph_node_ptr cgraph_function_node(cgraph_node_ptr node, enum availability *availability)
+{
+	return node->function_symbol(availability);
+}
+
+static inline cgraph_node_ptr cgraph_function_or_thunk_node(cgraph_node_ptr node, enum availability *availability = NULL)
+{
+	return node->ultimate_alias_target(availability);
+}
+
+static inline bool cgraph_only_called_directly_p(cgraph_node_ptr node)
+{
+	return node->only_called_directly_p();
+}
+
+static inline enum availability cgraph_function_body_availability(cgraph_node_ptr node)
+{
+	return node->get_availability();
+}
+
+static inline cgraph_node_ptr cgraph_alias_target(cgraph_node_ptr node)
+{
+	return node->get_alias_target();
+}
+
+static inline struct cgraph_node_hook_list *cgraph_add_function_insertion_hook(cgraph_node_hook hook, void *data)
+{
+	return symtab->add_cgraph_insertion_hook(hook, data);
+}
+
+static inline void cgraph_remove_function_insertion_hook(struct cgraph_node_hook_list *entry)
+{
+	symtab->remove_cgraph_insertion_hook(entry);
+}
+
+static inline struct cgraph_node_hook_list *cgraph_add_node_removal_hook(cgraph_node_hook hook, void *data)
+{
+	return symtab->add_cgraph_removal_hook(hook, data);
+}
+
+static inline void cgraph_remove_node_removal_hook(struct cgraph_node_hook_list *entry)
+{
+	symtab->remove_cgraph_removal_hook(entry);
+}
+
+static inline struct cgraph_2node_hook_list *cgraph_add_node_duplication_hook(cgraph_2node_hook hook, void *data)
+{
+	return symtab->add_cgraph_duplication_hook(hook, data);
+}
+
+static inline void cgraph_remove_node_duplication_hook(struct cgraph_2node_hook_list *entry)
+{
+	symtab->remove_cgraph_duplication_hook(entry);
+}
+
+static inline void cgraph_call_node_duplication_hooks(cgraph_node_ptr node, cgraph_node_ptr node2)
+{
+	symtab->call_cgraph_duplication_hooks(node, node2);
+}
+
+static inline void cgraph_call_edge_duplication_hooks(cgraph_edge *cs1, cgraph_edge *cs2)
+{
+	symtab->call_edge_duplication_hooks(cs1, cs2);
+}
+
+#if BUILDING_GCC_VERSION >= 6000
+typedef gimple *gimple_ptr;
+typedef const gimple *const_gimple_ptr;
+#define gimple gimple_ptr
+#define const_gimple const_gimple_ptr
+#undef CONST_CAST_GIMPLE
+#define CONST_CAST_GIMPLE(X) CONST_CAST(gimple, (X))
+#endif
+
+/* gimple related */
+static inline gimple gimple_build_assign_with_ops(enum tree_code subcode, tree lhs, tree op1, tree op2 MEM_STAT_DECL)
+{
+	return gimple_build_assign(lhs, subcode, op1, op2 PASS_MEM_STAT);
+}
+
+template <>
+template <>
+inline bool is_a_helper<const greturn *>::test(const_gimple gs)
+{
+	return gs->code == GIMPLE_RETURN;
+}
+
+static inline gasm *as_a_gasm(gimple stmt)
+{
+	return as_a<gasm *>(stmt);
+}
+
+static inline const gasm *as_a_const_gasm(const_gimple stmt)
+{
+	return as_a<const gasm *>(stmt);
+}
+
+static inline gassign *as_a_gassign(gimple stmt)
+{
+	return as_a<gassign *>(stmt);
+}
+
+static inline const gassign *as_a_const_gassign(const_gimple stmt)
+{
+	return as_a<const gassign *>(stmt);
+}
+
+static inline gcall *as_a_gcall(gimple stmt)
+{
+	return as_a<gcall *>(stmt);
+}
+
+static inline const gcall *as_a_const_gcall(const_gimple stmt)
+{
+	return as_a<const gcall *>(stmt);
+}
+
+static inline gphi *as_a_gphi(gimple stmt)
+{
+	return as_a<gphi *>(stmt);
+}
+
+static inline const gphi *as_a_const_gphi(const_gimple stmt)
+{
+	return as_a<const gphi *>(stmt);
+}
+
+static inline greturn *as_a_greturn(gimple stmt)
+{
+	return as_a<greturn *>(stmt);
+}
+
+static inline const greturn *as_a_const_greturn(const_gimple stmt)
+{
+	return as_a<const greturn *>(stmt);
+}
+
+/* IPA/LTO related */
+#define ipa_ref_list_referring_iterate(L, I, P)	\
+	(L)->referring.iterate((I), &(P))
+#define ipa_ref_list_reference_iterate(L, I, P)	\
+	(L)->reference.iterate((I), &(P))
+
+static inline cgraph_node_ptr ipa_ref_referring_node(struct ipa_ref *ref)
+{
+	return dyn_cast<cgraph_node_ptr>(ref->referring);
+}
+
+static inline void ipa_remove_stmt_references(symtab_node *referring_node, gimple stmt)
+{
+	referring_node->remove_stmt_references(stmt);
+}
+#endif
+
+#if BUILDING_GCC_VERSION < 6000
+#define get_inner_reference(exp, pbitsize, pbitpos, poffset, pmode, punsignedp, preversep, pvolatilep, keep_aligning)	\
+	get_inner_reference(exp, pbitsize, pbitpos, poffset, pmode, punsignedp, pvolatilep, keep_aligning)
+#define gen_rtx_set(ARG0, ARG1) gen_rtx_SET(VOIDmode, (ARG0), (ARG1))
+#endif
+
+#if BUILDING_GCC_VERSION >= 6000
+#define gen_rtx_set(ARG0, ARG1) gen_rtx_SET((ARG0), (ARG1))
+#endif
+
+#ifdef __cplusplus
+static inline void debug_tree(const_tree t)
+{
+	debug_tree(CONST_CAST_TREE(t));
+}
+
+static inline void debug_gimple_stmt(const_gimple s)
+{
+	debug_gimple_stmt(CONST_CAST_GIMPLE(s));
+}
+#else
+#define debug_tree(t) debug_tree(CONST_CAST_TREE(t))
+#define debug_gimple_stmt(s) debug_gimple_stmt(CONST_CAST_GIMPLE(s))
+#endif
+
+#endif
diff --git a/scripts/gcc-plugins/gcc-generate-gimple-pass.h b/scripts/gcc-plugins/gcc-generate-gimple-pass.h
new file mode 100644
index 000000000000..526c3c79b68e
--- /dev/null
+++ b/scripts/gcc-plugins/gcc-generate-gimple-pass.h
@@ -0,0 +1,175 @@
+/*
+ * Generator for GIMPLE pass related boilerplate code/data
+ *
+ * Supports gcc 4.5-6
+ *
+ * Usage:
+ *
+ * 1. before inclusion define PASS_NAME
+ * 2. before inclusion define NO_* for unimplemented callbacks
+ *    NO_GATE
+ *    NO_EXECUTE
+ * 3. before inclusion define PROPERTIES_* and TODO_FLAGS_* to override
+ *    the default 0 values
+ * 4. for convenience, all the above will be undefined after inclusion!
+ * 5. the only exported name is make_PASS_NAME_pass() to register with gcc
+ */
+
+#ifndef PASS_NAME
+#error at least PASS_NAME must be defined
+#else
+#define __GCC_PLUGIN_STRINGIFY(n)	#n
+#define _GCC_PLUGIN_STRINGIFY(n)	__GCC_PLUGIN_STRINGIFY(n)
+#define _GCC_PLUGIN_CONCAT2(x, y)	x ## y
+#define _GCC_PLUGIN_CONCAT3(x, y, z)	x ## y ## z
+
+#define __PASS_NAME_PASS_DATA(n)	_GCC_PLUGIN_CONCAT2(n, _pass_data)
+#define _PASS_NAME_PASS_DATA		__PASS_NAME_PASS_DATA(PASS_NAME)
+
+#define __PASS_NAME_PASS(n)		_GCC_PLUGIN_CONCAT2(n, _pass)
+#define _PASS_NAME_PASS			__PASS_NAME_PASS(PASS_NAME)
+
+#define _PASS_NAME_NAME			_GCC_PLUGIN_STRINGIFY(PASS_NAME)
+
+#define __MAKE_PASS_NAME_PASS(n)	_GCC_PLUGIN_CONCAT3(make_, n, _pass)
+#define _MAKE_PASS_NAME_PASS		__MAKE_PASS_NAME_PASS(PASS_NAME)
+
+#ifdef NO_GATE
+#define _GATE NULL
+#define _HAS_GATE false
+#else
+#define __GATE(n)			_GCC_PLUGIN_CONCAT2(n, _gate)
+#define _GATE				__GATE(PASS_NAME)
+#define _HAS_GATE true
+#endif
+
+#ifdef NO_EXECUTE
+#define _EXECUTE NULL
+#define _HAS_EXECUTE false
+#else
+#define __EXECUTE(n)			_GCC_PLUGIN_CONCAT2(n, _execute)
+#define _EXECUTE			__EXECUTE(PASS_NAME)
+#define _HAS_EXECUTE true
+#endif
+
+#ifndef PROPERTIES_REQUIRED
+#define PROPERTIES_REQUIRED 0
+#endif
+
+#ifndef PROPERTIES_PROVIDED
+#define PROPERTIES_PROVIDED 0
+#endif
+
+#ifndef PROPERTIES_DESTROYED
+#define PROPERTIES_DESTROYED 0
+#endif
+
+#ifndef TODO_FLAGS_START
+#define TODO_FLAGS_START 0
+#endif
+
+#ifndef TODO_FLAGS_FINISH
+#define TODO_FLAGS_FINISH 0
+#endif
+
+#if BUILDING_GCC_VERSION >= 4009
+namespace {
+static const pass_data _PASS_NAME_PASS_DATA = {
+#else
+static struct gimple_opt_pass _PASS_NAME_PASS = {
+	.pass = {
+#endif
+		.type			= GIMPLE_PASS,
+		.name			= _PASS_NAME_NAME,
+#if BUILDING_GCC_VERSION >= 4008
+		.optinfo_flags		= OPTGROUP_NONE,
+#endif
+#if BUILDING_GCC_VERSION >= 5000
+#elif BUILDING_GCC_VERSION == 4009
+		.has_gate		= _HAS_GATE,
+		.has_execute		= _HAS_EXECUTE,
+#else
+		.gate			= _GATE,
+		.execute		= _EXECUTE,
+		.sub			= NULL,
+		.next			= NULL,
+		.static_pass_number	= 0,
+#endif
+		.tv_id			= TV_NONE,
+		.properties_required	= PROPERTIES_REQUIRED,
+		.properties_provided	= PROPERTIES_PROVIDED,
+		.properties_destroyed	= PROPERTIES_DESTROYED,
+		.todo_flags_start	= TODO_FLAGS_START,
+		.todo_flags_finish	= TODO_FLAGS_FINISH,
+#if BUILDING_GCC_VERSION < 4009
+	}
+#endif
+};
+
+#if BUILDING_GCC_VERSION >= 4009
+class _PASS_NAME_PASS : public gimple_opt_pass {
+public:
+	_PASS_NAME_PASS() : gimple_opt_pass(_PASS_NAME_PASS_DATA, g) {}
+
+#ifndef NO_GATE
+#if BUILDING_GCC_VERSION >= 5000
+	virtual bool gate(function *) { return _GATE(); }
+#else
+	virtual bool gate(void) { return _GATE(); }
+#endif
+#endif
+
+	virtual opt_pass * clone () { return new _PASS_NAME_PASS(); }
+
+#ifndef NO_EXECUTE
+#if BUILDING_GCC_VERSION >= 5000
+	virtual unsigned int execute(function *) { return _EXECUTE(); }
+#else
+	virtual unsigned int execute(void) { return _EXECUTE(); }
+#endif
+#endif
+};
+}
+
+opt_pass *_MAKE_PASS_NAME_PASS(void)
+{
+	return new _PASS_NAME_PASS();
+}
+#else
+struct opt_pass *_MAKE_PASS_NAME_PASS(void)
+{
+	return &_PASS_NAME_PASS.pass;
+}
+#endif
+
+/* clean up user provided defines */
+#undef PASS_NAME
+#undef NO_GATE
+#undef NO_EXECUTE
+
+#undef PROPERTIES_DESTROYED
+#undef PROPERTIES_PROVIDED
+#undef PROPERTIES_REQUIRED
+#undef TODO_FLAGS_FINISH
+#undef TODO_FLAGS_START
+
+/* clean up generated defines */
+#undef _EXECUTE
+#undef __EXECUTE
+#undef _GATE
+#undef __GATE
+#undef _GCC_PLUGIN_CONCAT2
+#undef _GCC_PLUGIN_CONCAT3
+#undef _GCC_PLUGIN_STRINGIFY
+#undef __GCC_PLUGIN_STRINGIFY
+#undef _HAS_EXECUTE
+#undef _HAS_GATE
+#undef _MAKE_PASS_NAME_PASS
+#undef __MAKE_PASS_NAME_PASS
+#undef _PASS_NAME_NAME
+#undef _PASS_NAME_PASS
+#undef __PASS_NAME_PASS
+#undef _PASS_NAME_PASS_DATA
+#undef __PASS_NAME_PASS_DATA
+
+#endif /* PASS_NAME */
diff --git a/scripts/gcc-plugins/gcc-generate-ipa-pass.h b/scripts/gcc-plugins/gcc-generate-ipa-pass.h
new file mode 100644
index 000000000000..9bd926e072f0
--- /dev/null
+++ b/scripts/gcc-plugins/gcc-generate-ipa-pass.h
@@ -0,0 +1,289 @@
+/*
+ * Generator for IPA pass related boilerplate code/data
+ *
+ * Supports gcc 4.5-6
+ *
+ * Usage:
+ *
+ * 1. before inclusion define PASS_NAME
+ * 2. before inclusion define NO_* for unimplemented callbacks
+ *    NO_GENERATE_SUMMARY
+ *    NO_READ_SUMMARY
+ *    NO_WRITE_SUMMARY
+ *    NO_READ_OPTIMIZATION_SUMMARY
+ *    NO_WRITE_OPTIMIZATION_SUMMARY
+ *    NO_STMT_FIXUP
+ *    NO_FUNCTION_TRANSFORM
+ *    NO_VARIABLE_TRANSFORM
+ *    NO_GATE
+ *    NO_EXECUTE
+ * 3. before inclusion define PROPERTIES_* and *TODO_FLAGS_* to override
+ *    the default 0 values
+ * 4. for convenience, all the above will be undefined after inclusion!
+ * 5. the only exported name is make_PASS_NAME_pass() to register with gcc
+ */
+
+#ifndef PASS_NAME
+#error at least PASS_NAME must be defined
+#else
+#define __GCC_PLUGIN_STRINGIFY(n)	#n
+#define _GCC_PLUGIN_STRINGIFY(n)	__GCC_PLUGIN_STRINGIFY(n)
+#define _GCC_PLUGIN_CONCAT2(x, y)	x ## y
+#define _GCC_PLUGIN_CONCAT3(x, y, z)	x ## y ## z
+
+#define __PASS_NAME_PASS_DATA(n)	_GCC_PLUGIN_CONCAT2(n, _pass_data)
+#define _PASS_NAME_PASS_DATA		__PASS_NAME_PASS_DATA(PASS_NAME)
+
+#define __PASS_NAME_PASS(n)		_GCC_PLUGIN_CONCAT2(n, _pass)
+#define _PASS_NAME_PASS			__PASS_NAME_PASS(PASS_NAME)
+
+#define _PASS_NAME_NAME			_GCC_PLUGIN_STRINGIFY(PASS_NAME)
+
+#define __MAKE_PASS_NAME_PASS(n)	_GCC_PLUGIN_CONCAT3(make_, n, _pass)
+#define _MAKE_PASS_NAME_PASS		__MAKE_PASS_NAME_PASS(PASS_NAME)
+
+#ifdef NO_GENERATE_SUMMARY
+#define _GENERATE_SUMMARY NULL
+#else
+#define __GENERATE_SUMMARY(n)		_GCC_PLUGIN_CONCAT2(n, _generate_summary)
+#define _GENERATE_SUMMARY		__GENERATE_SUMMARY(PASS_NAME)
+#endif
+
+#ifdef NO_READ_SUMMARY
+#define _READ_SUMMARY NULL
+#else
+#define __READ_SUMMARY(n)		_GCC_PLUGIN_CONCAT2(n, _read_summary)
+#define _READ_SUMMARY			__READ_SUMMARY(PASS_NAME)
+#endif
+
+#ifdef NO_WRITE_SUMMARY
+#define _WRITE_SUMMARY NULL
+#else
+#define __WRITE_SUMMARY(n)		_GCC_PLUGIN_CONCAT2(n, _write_summary)
+#define _WRITE_SUMMARY			__WRITE_SUMMARY(PASS_NAME)
+#endif
+
+#ifdef NO_READ_OPTIMIZATION_SUMMARY
+#define _READ_OPTIMIZATION_SUMMARY NULL
+#else
+#define __READ_OPTIMIZATION_SUMMARY(n)	_GCC_PLUGIN_CONCAT2(n, _read_optimization_summary)
+#define _READ_OPTIMIZATION_SUMMARY	__READ_OPTIMIZATION_SUMMARY(PASS_NAME)
+#endif
+
+#ifdef NO_WRITE_OPTIMIZATION_SUMMARY
+#define _WRITE_OPTIMIZATION_SUMMARY NULL
+#else
+#define __WRITE_OPTIMIZATION_SUMMARY(n)	_GCC_PLUGIN_CONCAT2(n, _write_optimization_summary)
+#define _WRITE_OPTIMIZATION_SUMMARY	__WRITE_OPTIMIZATION_SUMMARY(PASS_NAME)
+#endif
+
+#ifdef NO_STMT_FIXUP
+#define _STMT_FIXUP NULL
+#else
+#define __STMT_FIXUP(n)			_GCC_PLUGIN_CONCAT2(n, _stmt_fixup)
+#define _STMT_FIXUP			__STMT_FIXUP(PASS_NAME)
+#endif
+
+#ifdef NO_FUNCTION_TRANSFORM
+#define _FUNCTION_TRANSFORM NULL
+#else
+#define __FUNCTION_TRANSFORM(n)		_GCC_PLUGIN_CONCAT2(n, _function_transform)
+#define _FUNCTION_TRANSFORM		__FUNCTION_TRANSFORM(PASS_NAME)
+#endif
+
+#ifdef NO_VARIABLE_TRANSFORM
+#define _VARIABLE_TRANSFORM NULL
+#else
+#define __VARIABLE_TRANSFORM(n)		_GCC_PLUGIN_CONCAT2(n, _variable_transform)
+#define _VARIABLE_TRANSFORM		__VARIABLE_TRANSFORM(PASS_NAME)
+#endif
+
+#ifdef NO_GATE
+#define _GATE NULL
+#define _HAS_GATE false
+#else
+#define __GATE(n)			_GCC_PLUGIN_CONCAT2(n, _gate)
+#define _GATE				__GATE(PASS_NAME)
+#define _HAS_GATE true
+#endif
+
+#ifdef NO_EXECUTE
+#define _EXECUTE NULL
+#define _HAS_EXECUTE false
+#else
+#define __EXECUTE(n)			_GCC_PLUGIN_CONCAT2(n, _execute)
+#define _EXECUTE			__EXECUTE(PASS_NAME)
+#define _HAS_EXECUTE true
+#endif
+
+#ifndef PROPERTIES_REQUIRED
+#define PROPERTIES_REQUIRED 0
+#endif
+
+#ifndef PROPERTIES_PROVIDED
+#define PROPERTIES_PROVIDED 0
+#endif
+
+#ifndef PROPERTIES_DESTROYED
+#define PROPERTIES_DESTROYED 0
+#endif
+
+#ifndef TODO_FLAGS_START
+#define TODO_FLAGS_START 0
+#endif
+
+#ifndef TODO_FLAGS_FINISH
+#define TODO_FLAGS_FINISH 0
+#endif
+
+#ifndef FUNCTION_TRANSFORM_TODO_FLAGS_START
+#define FUNCTION_TRANSFORM_TODO_FLAGS_START 0
+#endif
+
+#if BUILDING_GCC_VERSION >= 4009
+namespace {
+static const pass_data _PASS_NAME_PASS_DATA = {
+#else
+static struct ipa_opt_pass_d _PASS_NAME_PASS = {
+	.pass = {
+#endif
+		.type			= IPA_PASS,
+		.name			= _PASS_NAME_NAME,
+#if BUILDING_GCC_VERSION >= 4008
+		.optinfo_flags		= OPTGROUP_NONE,
+#endif
+#if BUILDING_GCC_VERSION >= 5000
+#elif BUILDING_GCC_VERSION == 4009
+		.has_gate		= _HAS_GATE,
+		.has_execute		= _HAS_EXECUTE,
+#else
+		.gate			= _GATE,
+		.execute		= _EXECUTE,
+		.sub			= NULL,
+		.next			= NULL,
+		.static_pass_number	= 0,
+#endif
+		.tv_id			= TV_NONE,
+		.properties_required	= PROPERTIES_REQUIRED,
+		.properties_provided	= PROPERTIES_PROVIDED,
+		.properties_destroyed	= PROPERTIES_DESTROYED,
+		.todo_flags_start	= TODO_FLAGS_START,
+		.todo_flags_finish	= TODO_FLAGS_FINISH,
+#if BUILDING_GCC_VERSION < 4009
+	},
+	.generate_summary		= _GENERATE_SUMMARY,
+	.write_summary			= _WRITE_SUMMARY,
+	.read_summary			= _READ_SUMMARY,
+#if BUILDING_GCC_VERSION >= 4006
+	.write_optimization_summary	= _WRITE_OPTIMIZATION_SUMMARY,
+	.read_optimization_summary	= _READ_OPTIMIZATION_SUMMARY,
+#endif
+	.stmt_fixup			= _STMT_FIXUP,
+	.function_transform_todo_flags_start	= FUNCTION_TRANSFORM_TODO_FLAGS_START,
+	.function_transform		= _FUNCTION_TRANSFORM,
+	.variable_transform		= _VARIABLE_TRANSFORM,
+#endif
+};
+
+#if BUILDING_GCC_VERSION >= 4009
+class _PASS_NAME_PASS : public ipa_opt_pass_d {
+public:
+	_PASS_NAME_PASS() : ipa_opt_pass_d(_PASS_NAME_PASS_DATA,
+			 g,
+			 _GENERATE_SUMMARY,
+			 _WRITE_SUMMARY,
+			 _READ_SUMMARY,
+			 _WRITE_OPTIMIZATION_SUMMARY,
+			 _READ_OPTIMIZATION_SUMMARY,
+			 _STMT_FIXUP,
+			 FUNCTION_TRANSFORM_TODO_FLAGS_START,
+			 _FUNCTION_TRANSFORM,
+			 _VARIABLE_TRANSFORM) {}
+
+#ifndef NO_GATE
+#if BUILDING_GCC_VERSION >= 5000
+	virtual bool gate(function *) { return _GATE(); }
+#else
+	virtual bool gate(void) { return _GATE(); }
+#endif
+#endif
+
+	virtual opt_pass *clone() { return new _PASS_NAME_PASS(); }
+
+#ifndef NO_EXECUTE
+#if BUILDING_GCC_VERSION >= 5000
+	virtual unsigned int execute(function *) { return _EXECUTE(); }
+#else
+	virtual unsigned int execute(void) { return _EXECUTE(); }
+#endif
+#endif
+};
+}
+
+opt_pass *_MAKE_PASS_NAME_PASS(void)
+{
+	return new _PASS_NAME_PASS();
+}
+#else
+struct opt_pass *_MAKE_PASS_NAME_PASS(void)
+{
+	return &_PASS_NAME_PASS.pass;
+}
+#endif
+
+/* clean up user provided defines */
+#undef PASS_NAME
+#undef NO_GENERATE_SUMMARY
+#undef NO_WRITE_SUMMARY
+#undef NO_READ_SUMMARY
+#undef NO_WRITE_OPTIMIZATION_SUMMARY
+#undef NO_READ_OPTIMIZATION_SUMMARY
+#undef NO_STMT_FIXUP
+#undef NO_FUNCTION_TRANSFORM
+#undef NO_VARIABLE_TRANSFORM
+#undef NO_GATE
+#undef NO_EXECUTE
+
+#undef FUNCTION_TRANSFORM_TODO_FLAGS_START
+#undef PROPERTIES_DESTROYED
+#undef PROPERTIES_PROVIDED
+#undef PROPERTIES_REQUIRED
+#undef TODO_FLAGS_FINISH
+#undef TODO_FLAGS_START
+
+/* clean up generated defines */
+#undef _EXECUTE
+#undef __EXECUTE
+#undef _FUNCTION_TRANSFORM
+#undef __FUNCTION_TRANSFORM
+#undef _GATE
+#undef __GATE
+#undef _GCC_PLUGIN_CONCAT2
+#undef _GCC_PLUGIN_CONCAT3
+#undef _GCC_PLUGIN_STRINGIFY
+#undef __GCC_PLUGIN_STRINGIFY
+#undef _GENERATE_SUMMARY
+#undef __GENERATE_SUMMARY
+#undef _HAS_EXECUTE
+#undef _HAS_GATE
+#undef _MAKE_PASS_NAME_PASS
+#undef __MAKE_PASS_NAME_PASS
+#undef _PASS_NAME_NAME
+#undef _PASS_NAME_PASS
+#undef __PASS_NAME_PASS
+#undef _PASS_NAME_PASS_DATA
+#undef __PASS_NAME_PASS_DATA
+#undef _READ_OPTIMIZATION_SUMMARY
+#undef __READ_OPTIMIZATION_SUMMARY
+#undef _READ_SUMMARY
+#undef __READ_SUMMARY
+#undef _STMT_FIXUP
+#undef __STMT_FIXUP
+#undef _VARIABLE_TRANSFORM
+#undef __VARIABLE_TRANSFORM
+#undef _WRITE_OPTIMIZATION_SUMMARY
+#undef __WRITE_OPTIMIZATION_SUMMARY
+#undef _WRITE_SUMMARY
+#undef __WRITE_SUMMARY
+
+#endif /* PASS_NAME */
diff --git a/scripts/gcc-plugins/gcc-generate-rtl-pass.h b/scripts/gcc-plugins/gcc-generate-rtl-pass.h
new file mode 100644
index 000000000000..1dc67a5aeadf
--- /dev/null
+++ b/scripts/gcc-plugins/gcc-generate-rtl-pass.h
@@ -0,0 +1,175 @@
+/*
+ * Generator for RTL pass related boilerplate code/data
+ *
+ * Supports gcc 4.5-6
+ *
+ * Usage:
+ *
+ * 1. before inclusion define PASS_NAME
+ * 2. before inclusion define NO_* for unimplemented callbacks
+ *    NO_GATE
+ *    NO_EXECUTE
+ * 3. before inclusion define PROPERTIES_* and TODO_FLAGS_* to override
+ *    the default 0 values
+ * 4. for convenience, all the above will be undefined after inclusion!
+ * 5. the only exported name is make_PASS_NAME_pass() to register with gcc
+ */
+
+#ifndef PASS_NAME
+#error at least PASS_NAME must be defined
+#else
+#define __GCC_PLUGIN_STRINGIFY(n)	#n
+#define _GCC_PLUGIN_STRINGIFY(n)	__GCC_PLUGIN_STRINGIFY(n)
+#define _GCC_PLUGIN_CONCAT2(x, y)	x ## y
+#define _GCC_PLUGIN_CONCAT3(x, y, z)	x ## y ## z
+
+#define __PASS_NAME_PASS_DATA(n)	_GCC_PLUGIN_CONCAT2(n, _pass_data)
+#define _PASS_NAME_PASS_DATA		__PASS_NAME_PASS_DATA(PASS_NAME)
+
+#define __PASS_NAME_PASS(n)		_GCC_PLUGIN_CONCAT2(n, _pass)
+#define _PASS_NAME_PASS			__PASS_NAME_PASS(PASS_NAME)
+
+#define _PASS_NAME_NAME			_GCC_PLUGIN_STRINGIFY(PASS_NAME)
+
+#define __MAKE_PASS_NAME_PASS(n)	_GCC_PLUGIN_CONCAT3(make_, n, _pass)
+#define _MAKE_PASS_NAME_PASS		__MAKE_PASS_NAME_PASS(PASS_NAME)
+
+#ifdef NO_GATE
+#define _GATE NULL
+#define _HAS_GATE false
+#else
+#define __GATE(n)			_GCC_PLUGIN_CONCAT2(n, _gate)
+#define _GATE				__GATE(PASS_NAME)
+#define _HAS_GATE true
+#endif
+
+#ifdef NO_EXECUTE
+#define _EXECUTE NULL
+#define _HAS_EXECUTE false
+#else
+#define __EXECUTE(n)			_GCC_PLUGIN_CONCAT2(n, _execute)
+#define _EXECUTE			__EXECUTE(PASS_NAME)
+#define _HAS_EXECUTE true
+#endif
+
+#ifndef PROPERTIES_REQUIRED
+#define PROPERTIES_REQUIRED 0
+#endif
+
+#ifndef PROPERTIES_PROVIDED
+#define PROPERTIES_PROVIDED 0
+#endif
+
+#ifndef PROPERTIES_DESTROYED
+#define PROPERTIES_DESTROYED 0
+#endif
+
+#ifndef TODO_FLAGS_START
+#define TODO_FLAGS_START 0
+#endif
+
+#ifndef TODO_FLAGS_FINISH
+#define TODO_FLAGS_FINISH 0
+#endif
+
+#if BUILDING_GCC_VERSION >= 4009
+namespace {
+static const pass_data _PASS_NAME_PASS_DATA = {
+#else
+static struct rtl_opt_pass _PASS_NAME_PASS = {
+	.pass = {
+#endif
+		.type			= RTL_PASS,
+		.name			= _PASS_NAME_NAME,
+#if BUILDING_GCC_VERSION >= 4008
+		.optinfo_flags		= OPTGROUP_NONE,
+#endif
+#if BUILDING_GCC_VERSION >= 5000
+#elif BUILDING_GCC_VERSION == 4009
+		.has_gate		= _HAS_GATE,
+		.has_execute		= _HAS_EXECUTE,
+#else
+		.gate			= _GATE,
+		.execute		= _EXECUTE,
+		.sub			= NULL,
+		.next			= NULL,
+		.static_pass_number	= 0,
+#endif
+		.tv_id			= TV_NONE,
+		.properties_required	= PROPERTIES_REQUIRED,
+		.properties_provided	= PROPERTIES_PROVIDED,
+		.properties_destroyed	= PROPERTIES_DESTROYED,
+		.todo_flags_start	= TODO_FLAGS_START,
+		.todo_flags_finish	= TODO_FLAGS_FINISH,
+#if BUILDING_GCC_VERSION < 4009
+	}
+#endif
+};
+
+#if BUILDING_GCC_VERSION >= 4009
+class _PASS_NAME_PASS : public rtl_opt_pass {
+public:
+	_PASS_NAME_PASS() : rtl_opt_pass(_PASS_NAME_PASS_DATA, g) {}
+
+#ifndef NO_GATE
+#if BUILDING_GCC_VERSION >= 5000
+	virtual bool gate(function *) { return _GATE(); }
+#else
+	virtual bool gate(void) { return _GATE(); }
+#endif
+#endif
+
+	virtual opt_pass *clone() { return new _PASS_NAME_PASS(); }
+
+#ifndef NO_EXECUTE
+#if BUILDING_GCC_VERSION >= 5000
+	virtual unsigned int execute(function *) { return _EXECUTE(); }
+#else
+	virtual unsigned int execute(void) { return _EXECUTE(); }
+#endif
+#endif
+};
+}
+
+opt_pass *_MAKE_PASS_NAME_PASS(void)
+{
+	return new _PASS_NAME_PASS();
+}
+#else
+struct opt_pass *_MAKE_PASS_NAME_PASS(void)
+{
+	return &_PASS_NAME_PASS.pass;
+}
+#endif
+
+/* clean up user provided defines */
+#undef PASS_NAME
+#undef NO_GATE
+#undef NO_EXECUTE
+
+#undef PROPERTIES_DESTROYED
+#undef PROPERTIES_PROVIDED
+#undef PROPERTIES_REQUIRED
+#undef TODO_FLAGS_FINISH
+#undef TODO_FLAGS_START
+
+/* clean up generated defines */
+#undef _EXECUTE
+#undef __EXECUTE
+#undef _GATE
+#undef __GATE
+#undef _GCC_PLUGIN_CONCAT2
+#undef _GCC_PLUGIN_CONCAT3
+#undef _GCC_PLUGIN_STRINGIFY
+#undef __GCC_PLUGIN_STRINGIFY
+#undef _HAS_EXECUTE
+#undef _HAS_GATE
+#undef _MAKE_PASS_NAME_PASS
+#undef __MAKE_PASS_NAME_PASS
+#undef _PASS_NAME_NAME
+#undef _PASS_NAME_PASS
+#undef __PASS_NAME_PASS
+#undef _PASS_NAME_PASS_DATA
+#undef __PASS_NAME_PASS_DATA
+
+#endif /* PASS_NAME */
diff --git a/scripts/gcc-plugins/gcc-generate-simple_ipa-pass.h b/scripts/gcc-plugins/gcc-generate-simple_ipa-pass.h
new file mode 100644
index 000000000000..a27e2b36afaa
--- /dev/null
+++ b/scripts/gcc-plugins/gcc-generate-simple_ipa-pass.h
@@ -0,0 +1,175 @@
+/*
+ * Generator for SIMPLE_IPA pass related boilerplate code/data
+ *
+ * Supports gcc 4.5-6
+ *
+ * Usage:
+ *
+ * 1. before inclusion define PASS_NAME
+ * 2. before inclusion define NO_* for unimplemented callbacks
+ *    NO_GATE
+ *    NO_EXECUTE
+ * 3. before inclusion define PROPERTIES_* and TODO_FLAGS_* to override
+ *    the default 0 values
+ * 4. for convenience, all the above will be undefined after inclusion!
+ * 5. the only exported name is make_PASS_NAME_pass() to register with gcc
+ */
+
+#ifndef PASS_NAME
+#error at least PASS_NAME must be defined
+#else
+#define __GCC_PLUGIN_STRINGIFY(n)	#n
+#define _GCC_PLUGIN_STRINGIFY(n)	__GCC_PLUGIN_STRINGIFY(n)
+#define _GCC_PLUGIN_CONCAT2(x, y)	x ## y
+#define _GCC_PLUGIN_CONCAT3(x, y, z)	x ## y ## z
+
+#define __PASS_NAME_PASS_DATA(n)	_GCC_PLUGIN_CONCAT2(n, _pass_data)
+#define _PASS_NAME_PASS_DATA		__PASS_NAME_PASS_DATA(PASS_NAME)
+
+#define __PASS_NAME_PASS(n)		_GCC_PLUGIN_CONCAT2(n, _pass)
+#define _PASS_NAME_PASS			__PASS_NAME_PASS(PASS_NAME)
+
+#define _PASS_NAME_NAME			_GCC_PLUGIN_STRINGIFY(PASS_NAME)
+
+#define __MAKE_PASS_NAME_PASS(n)	_GCC_PLUGIN_CONCAT3(make_, n, _pass)
+#define _MAKE_PASS_NAME_PASS		__MAKE_PASS_NAME_PASS(PASS_NAME)
+
+#ifdef NO_GATE
+#define _GATE NULL
+#define _HAS_GATE false
+#else
+#define __GATE(n)			_GCC_PLUGIN_CONCAT2(n, _gate)
+#define _GATE				__GATE(PASS_NAME)
+#define _HAS_GATE true
+#endif
+
+#ifdef NO_EXECUTE
+#define _EXECUTE NULL
+#define _HAS_EXECUTE false
+#else
+#define __EXECUTE(n)			_GCC_PLUGIN_CONCAT2(n, _execute)
+#define _EXECUTE			__EXECUTE(PASS_NAME)
+#define _HAS_EXECUTE true
+#endif
+
+#ifndef PROPERTIES_REQUIRED
+#define PROPERTIES_REQUIRED 0
+#endif
+
+#ifndef PROPERTIES_PROVIDED
+#define PROPERTIES_PROVIDED 0
+#endif
+
+#ifndef PROPERTIES_DESTROYED
+#define PROPERTIES_DESTROYED 0
+#endif
+
+#ifndef TODO_FLAGS_START
+#define TODO_FLAGS_START 0
+#endif
+
+#ifndef TODO_FLAGS_FINISH
+#define TODO_FLAGS_FINISH 0
+#endif
+
+#if BUILDING_GCC_VERSION >= 4009
+namespace {
+static const pass_data _PASS_NAME_PASS_DATA = {
+#else
+static struct simple_ipa_opt_pass _PASS_NAME_PASS = {
+	.pass = {
+#endif
+		.type			= SIMPLE_IPA_PASS,
+		.name			= _PASS_NAME_NAME,
+#if BUILDING_GCC_VERSION >= 4008
+		.optinfo_flags		= OPTGROUP_NONE,
+#endif
+#if BUILDING_GCC_VERSION >= 5000
+#elif BUILDING_GCC_VERSION == 4009
+		.has_gate		= _HAS_GATE,
+		.has_execute		= _HAS_EXECUTE,
+#else
+		.gate			= _GATE,
+		.execute		= _EXECUTE,
+		.sub			= NULL,
+		.next			= NULL,
+		.static_pass_number	= 0,
+#endif
+		.tv_id			= TV_NONE,
+		.properties_required	= PROPERTIES_REQUIRED,
+		.properties_provided	= PROPERTIES_PROVIDED,
+		.properties_destroyed	= PROPERTIES_DESTROYED,
+		.todo_flags_start	= TODO_FLAGS_START,
+		.todo_flags_finish	= TODO_FLAGS_FINISH,
+#if BUILDING_GCC_VERSION < 4009
+	}
+#endif
+};
+
+#if BUILDING_GCC_VERSION >= 4009
+class _PASS_NAME_PASS : public simple_ipa_opt_pass {
+public:
+	_PASS_NAME_PASS() : simple_ipa_opt_pass(_PASS_NAME_PASS_DATA, g) {}
+
+#ifndef NO_GATE
+#if BUILDING_GCC_VERSION >= 5000
+	virtual bool gate(function *) { return _GATE(); }
+#else
+	virtual bool gate(void) { return _GATE(); }
+#endif
+#endif
+
+	virtual opt_pass *clone() { return new _PASS_NAME_PASS(); }
+
+#ifndef NO_EXECUTE
+#if BUILDING_GCC_VERSION >= 5000
+	virtual unsigned int execute(function *) { return _EXECUTE(); }
+#else
+	virtual unsigned int execute(void) { return _EXECUTE(); }
+#endif
+#endif
+};
+}
+
+opt_pass *_MAKE_PASS_NAME_PASS(void)
+{
+	return new _PASS_NAME_PASS();
+}
+#else
+struct opt_pass *_MAKE_PASS_NAME_PASS(void)
+{
+	return &_PASS_NAME_PASS.pass;
+}
+#endif
+
+/* clean up user provided defines */
+#undef PASS_NAME
+#undef NO_GATE
+#undef NO_EXECUTE
+
+#undef PROPERTIES_DESTROYED
+#undef PROPERTIES_PROVIDED
+#undef PROPERTIES_REQUIRED
+#undef TODO_FLAGS_FINISH
+#undef TODO_FLAGS_START
+
+/* clean up generated defines */
+#undef _EXECUTE
+#undef __EXECUTE
+#undef _GATE
+#undef __GATE
+#undef _GCC_PLUGIN_CONCAT2
+#undef _GCC_PLUGIN_CONCAT3
+#undef _GCC_PLUGIN_STRINGIFY
+#undef __GCC_PLUGIN_STRINGIFY
+#undef _HAS_EXECUTE
+#undef _HAS_GATE
+#undef _MAKE_PASS_NAME_PASS
+#undef __MAKE_PASS_NAME_PASS
+#undef _PASS_NAME_NAME
+#undef _PASS_NAME_PASS
+#undef __PASS_NAME_PASS
+#undef _PASS_NAME_PASS_DATA
+#undef __PASS_NAME_PASS_DATA
+
+#endif /* PASS_NAME */
diff --git a/scripts/gcc-plugins/sancov_plugin.c b/scripts/gcc-plugins/sancov_plugin.c
new file mode 100644
index 000000000000..aedd6113cb73
--- /dev/null
+++ b/scripts/gcc-plugins/sancov_plugin.c
@@ -0,0 +1,144 @@
+/*
+ * Copyright 2011-2016 by Emese Revfy <re.emese@gmail.com>
+ * Licensed under the GPL v2, or (at your option) v3
+ *
+ * Homepage:
+ * https://github.com/ephox-gcc-plugins/sancov
+ *
+ * This plugin inserts a __sanitizer_cov_trace_pc() call at the start of basic blocks.
+ * It supports all gcc versions with plugin support (from gcc-4.5 on).
+ * It is based on the commit "Add fuzzing coverage support" by Dmitry Vyukov <dvyukov@google.com>.
+ *
+ * You can read about it more here:
+ *  https://gcc.gnu.org/viewcvs/gcc?limit_changes=0&view=revision&revision=231296
+ *  http://lwn.net/Articles/674854/
+ *  https://github.com/google/syzkaller
+ *  https://lwn.net/Articles/677764/
+ *
+ * Usage:
+ * make run
+ */
+
+#include "gcc-common.h"
+
+int plugin_is_GPL_compatible;
+
+tree sancov_fndecl;
+
+static struct plugin_info sancov_plugin_info = {
+	.version	= "20160402",
+	.help		= "sancov plugin\n",
+};
+
+static unsigned int sancov_execute(void)
+{
+	basic_block bb;
+
+	/* Remove this line when this plugin and kcov will be in the kernel.
+	if (!strcmp(DECL_NAME_POINTER(current_function_decl), DECL_NAME_POINTER(sancov_fndecl)))
+		return 0;
+	*/
+
+	FOR_EACH_BB_FN(bb, cfun) {
+		const_gimple stmt;
+		gcall *gcall;
+		gimple_stmt_iterator gsi = gsi_after_labels(bb);
+
+		if (gsi_end_p(gsi))
+			continue;
+
+		stmt = gsi_stmt(gsi);
+		gcall = as_a_gcall(gimple_build_call(sancov_fndecl, 0));
+		gimple_set_location(gcall, gimple_location(stmt));
+		gsi_insert_before(&gsi, gcall, GSI_SAME_STMT);
+	}
+	return 0;
+}
+
+#define PASS_NAME sancov
+
+#define NO_GATE
+#define TODO_FLAGS_FINISH TODO_dump_func | TODO_verify_stmts | TODO_update_ssa_no_phi | TODO_verify_flow
+
+#include "gcc-generate-gimple-pass.h"
+
+static void sancov_start_unit(void __unused *gcc_data, void __unused *user_data)
+{
+	tree leaf_attr, nothrow_attr;
+	tree BT_FN_VOID = build_function_type_list(void_type_node, NULL_TREE);
+
+	sancov_fndecl = build_fn_decl("__sanitizer_cov_trace_pc", BT_FN_VOID);
+
+	DECL_ASSEMBLER_NAME(sancov_fndecl);
+	TREE_PUBLIC(sancov_fndecl) = 1;
+	DECL_EXTERNAL(sancov_fndecl) = 1;
+	DECL_ARTIFICIAL(sancov_fndecl) = 1;
+	DECL_PRESERVE_P(sancov_fndecl) = 1;
+	DECL_UNINLINABLE(sancov_fndecl) = 1;
+	TREE_USED(sancov_fndecl) = 1;
+
+	nothrow_attr = tree_cons(get_identifier("nothrow"), NULL, NULL);
+	decl_attributes(&sancov_fndecl, nothrow_attr, 0);
+	gcc_assert(TREE_NOTHROW(sancov_fndecl));
+#if BUILDING_GCC_VERSION > 4005
+	leaf_attr = tree_cons(get_identifier("leaf"), NULL, NULL);
+	decl_attributes(&sancov_fndecl, leaf_attr, 0);
+#endif
+}
+
+int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version)
+{
+	int i;
+	struct register_pass_info sancov_plugin_pass_info;
+	const char * const plugin_name = plugin_info->base_name;
+	const int argc = plugin_info->argc;
+	const struct plugin_argument * const argv = plugin_info->argv;
+	bool enable = true;
+
+	static const struct ggc_root_tab gt_ggc_r_gt_sancov[] = {
+		{
+			.base = &sancov_fndecl,
+			.nelt = 1,
+			.stride = sizeof(sancov_fndecl),
+			.cb = &gt_ggc_mx_tree_node,
+			.pchw = &gt_pch_nx_tree_node
+		},
+		LAST_GGC_ROOT_TAB
+	};
+
+	/* BBs can be split afterwards?? */
+	sancov_plugin_pass_info.pass				= make_sancov_pass();
+#if BUILDING_GCC_VERSION >= 4009
+	sancov_plugin_pass_info.reference_pass_name		= "asan";
+#else
+	sancov_plugin_pass_info.reference_pass_name		= "nrv";
+#endif
+	sancov_plugin_pass_info.ref_pass_instance_number	= 0;
+	sancov_plugin_pass_info.pos_op				= PASS_POS_INSERT_BEFORE;
+
+	if (!plugin_default_version_check(version, &gcc_version)) {
+		error(G_("incompatible gcc/plugin versions"));
+		return 1;
+	}
+
+	for (i = 0; i < argc; ++i) {
+		if (!strcmp(argv[i].key, "no-sancov")) {
+			enable = false;
+			continue;
+		}
+		error(G_("unkown option '-fplugin-arg-%s-%s'"), plugin_name, argv[i].key);
+	}
+
+	register_callback(plugin_name, PLUGIN_INFO, NULL, &sancov_plugin_info);
+
+	if (!enable)
+		return 0;
+
+#if BUILDING_GCC_VERSION < 6000
+	register_callback(plugin_name, PLUGIN_START_UNIT, &sancov_start_unit, NULL);
+	register_callback(plugin_name, PLUGIN_REGISTER_GGC_ROOTS, NULL, (void *)&gt_ggc_r_gt_sancov);
+	register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &sancov_plugin_pass_info);
+#endif
+
+	return 0;
+}
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 1873421f2305..122fcdaf42c8 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -133,6 +133,7 @@ my %VCS_cmds_git = (
     "author_pattern" => "^GitAuthor: (.*)",
     "subject_pattern" => "^GitSubject: (.*)",
     "stat_pattern" => "^(\\d+)\\t(\\d+)\\t\$file\$",
+    "file_exists_cmd" => "git ls-files \$file",
 );
 
 my %VCS_cmds_hg = (
@@ -161,6 +162,7 @@ my %VCS_cmds_hg = (
     "author_pattern" => "^HgAuthor: (.*)",
     "subject_pattern" => "^HgSubject: (.*)",
     "stat_pattern" => "^(\\d+)\t(\\d+)\t\$file\$",
+    "file_exists_cmd" => "hg files \$file",
 );
 
 my $conf = which_conf(".get_maintainer.conf");
@@ -430,7 +432,7 @@ foreach my $file (@ARGV) {
 	    die "$P: file '${file}' not found\n";
 	}
     }
-    if ($from_filename) {
+    if ($from_filename || vcs_file_exists($file)) {
 	$file =~ s/^\Q${cur_path}\E//;	#strip any absolute path
 	$file =~ s/^\Q${lk_path}\E//;	#or the path to the lk tree
 	push(@files, $file);
@@ -2124,6 +2126,22 @@ sub vcs_file_blame {
     }
 }
 
+sub vcs_file_exists {
+    my ($file) = @_;
+
+    my $exists;
+
+    my $vcs_used = vcs_exists();
+    return 0 if (!$vcs_used);
+
+    my $cmd = $VCS_cmds{"file_exists_cmd"};
+    $cmd =~ s/(\$\w+)/$1/eeg;		# interpolate $cmd
+
+    $exists = &{$VCS_cmds{"execute_cmd"}}($cmd);
+
+    return $exists;
+}
+
 sub uniq {
     my (@parms) = @_;
 
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index f0f6d9d75435..4f727eb5ec43 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -180,7 +180,7 @@ else
 fi;
 
 # final build of init/
-${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init
+${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init GCC_PLUGINS_CFLAGS="${GCC_PLUGINS_CFLAGS}"
 
 kallsymso=""
 kallsyms_vmlinux=""
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 86e56fef7473..e1c09e2f9be7 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -26,6 +26,8 @@ create_package() {
 	# Fix ownership and permissions
 	chown -R root:root "$pdir"
 	chmod -R go-w "$pdir"
+	# in case we are in a restrictive umask environment like 0077
+	chmod -R a+rX "$pdir"
 
 	# Create the package
 	dpkg-gencontrol $forcearch -Vkernel:debarch="${debarch}" -p$pname -P"$pdir"
@@ -238,7 +240,8 @@ maintainer="$name <$email>"
 # Try to determine distribution
 if [ -n "$KDEB_CHANGELOG_DIST" ]; then
         distribution=$KDEB_CHANGELOG_DIST
-elif distribution=$(lsb_release -cs 2>/dev/null) && [ -n "$distribution" ]; then
+# In some cases lsb_release returns the codename as n/a, which breaks dpkg-parsechangelog
+elif distribution=$(lsb_release -cs 2>/dev/null) && [ -n "$distribution" ] && [ "$distribution" != "n/a" ]; then
         : # nothing to do in this case
 else
         distribution="unstable"
@@ -322,13 +325,14 @@ fi
 
 # Build kernel header package
 (cd $srctree; find . -name Makefile\* -o -name Kconfig\* -o -name \*.pl) > "$objtree/debian/hdrsrcfiles"
-if grep -q '^CONFIG_STACK_VALIDATION=y' $KCONFIG_CONFIG ; then
-	(cd $srctree; find tools/objtool -type f -executable) >> "$objtree/debian/hdrsrcfiles"
-fi
 (cd $srctree; find arch/*/include include scripts -type f) >> "$objtree/debian/hdrsrcfiles"
 (cd $srctree; find arch/$SRCARCH -name module.lds -o -name Kbuild.platforms -o -name Platform) >> "$objtree/debian/hdrsrcfiles"
 (cd $srctree; find $(find arch/$SRCARCH -name include -o -name scripts -type d) -type f) >> "$objtree/debian/hdrsrcfiles"
+if grep -q '^CONFIG_STACK_VALIDATION=y' $KCONFIG_CONFIG ; then
+	(cd $objtree; find tools/objtool -type f -executable) >> "$objtree/debian/hdrobjfiles"
+fi
 (cd $objtree; find arch/$SRCARCH/include Module.symvers include scripts -type f) >> "$objtree/debian/hdrobjfiles"
+(cd $objtree; find scripts/gcc-plugins -name \*.so -o -name gcc-common.h) >> "$objtree/debian/hdrobjfiles"
 destdir=$kernel_headers_dir/usr/src/linux-headers-$version
 mkdir -p "$destdir"
 (cd $srctree; tar -c -f - -T -) < "$objtree/debian/hdrsrcfiles" | (cd $destdir; tar -xf -)
diff --git a/scripts/setlocalversion b/scripts/setlocalversion
index 63d91e22ed7c..966dd3924ea9 100755
--- a/scripts/setlocalversion
+++ b/scripts/setlocalversion
@@ -143,7 +143,7 @@ fi
 if test -e include/config/auto.conf; then
 	. include/config/auto.conf
 else
-	echo "Error: kernelrelease not valid - run 'make prepare' to update it"
+	echo "Error: kernelrelease not valid - run 'make prepare' to update it" >&2
 	exit 1
 fi
 
diff --git a/sound/Makefile b/sound/Makefile
index 77320709fd26..c41bdf5fdf24 100644
--- a/sound/Makefile
+++ b/sound/Makefile
@@ -2,7 +2,6 @@
 #
 
 obj-$(CONFIG_SOUND) += soundcore.o
-obj-$(CONFIG_SOUND_PRIME) += sound_firmware.o
 obj-$(CONFIG_SOUND_PRIME) += oss/
 obj-$(CONFIG_DMASOUND) += oss/
 obj-$(CONFIG_SND) += core/ i2c/ drivers/ isa/ pci/ ppc/ arm/ sh/ synth/ usb/ \
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 9b3334be9df2..2c498488af6c 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -67,6 +67,8 @@ struct snd_compr_file {
 	struct snd_compr_stream stream;
 };
 
+static void error_delayed_work(struct work_struct *work);
+
 /*
  * a note on stream states used:
  * we use following states in the compressed core
@@ -123,6 +125,9 @@ static int snd_compr_open(struct inode *inode, struct file *f)
 		snd_card_unref(compr->card);
 		return -ENOMEM;
 	}
+
+	INIT_DELAYED_WORK(&data->stream.error_work, error_delayed_work);
+
 	data->stream.ops = compr->ops;
 	data->stream.direction = dirn;
 	data->stream.private_data = compr->private_data;
@@ -153,6 +158,8 @@ static int snd_compr_free(struct inode *inode, struct file *f)
 	struct snd_compr_file *data = f->private_data;
 	struct snd_compr_runtime *runtime = data->stream.runtime;
 
+	cancel_delayed_work_sync(&data->stream.error_work);
+
 	switch (runtime->state) {
 	case SNDRV_PCM_STATE_RUNNING:
 	case SNDRV_PCM_STATE_DRAINING:
@@ -237,6 +244,15 @@ snd_compr_ioctl_avail(struct snd_compr_stream *stream, unsigned long arg)
 	avail = snd_compr_calc_avail(stream, &ioctl_avail);
 	ioctl_avail.avail = avail;
 
+	switch (stream->runtime->state) {
+	case SNDRV_PCM_STATE_OPEN:
+		return -EBADFD;
+	case SNDRV_PCM_STATE_XRUN:
+		return -EPIPE;
+	default:
+		break;
+	}
+
 	if (copy_to_user((__u64 __user *)arg,
 				&ioctl_avail, sizeof(ioctl_avail)))
 		return -EFAULT;
@@ -346,11 +362,13 @@ static ssize_t snd_compr_read(struct file *f, char __user *buf,
 	switch (stream->runtime->state) {
 	case SNDRV_PCM_STATE_OPEN:
 	case SNDRV_PCM_STATE_PREPARED:
-	case SNDRV_PCM_STATE_XRUN:
 	case SNDRV_PCM_STATE_SUSPENDED:
 	case SNDRV_PCM_STATE_DISCONNECTED:
 		retval = -EBADFD;
 		goto out;
+	case SNDRV_PCM_STATE_XRUN:
+		retval = -EPIPE;
+		goto out;
 	}
 
 	avail = snd_compr_get_avail(stream);
@@ -399,10 +417,16 @@ static unsigned int snd_compr_poll(struct file *f, poll_table *wait)
 	stream = &data->stream;
 
 	mutex_lock(&stream->device->lock);
-	if (stream->runtime->state == SNDRV_PCM_STATE_OPEN) {
+
+	switch (stream->runtime->state) {
+	case SNDRV_PCM_STATE_OPEN:
+	case SNDRV_PCM_STATE_XRUN:
 		retval = snd_compr_get_poll(stream) | POLLERR;
 		goto out;
+	default:
+		break;
 	}
+
 	poll_wait(f, &stream->runtime->sleep, wait);
 
 	avail = snd_compr_get_avail(stream);
@@ -697,6 +721,45 @@ static int snd_compr_stop(struct snd_compr_stream *stream)
 	return retval;
 }
 
+static void error_delayed_work(struct work_struct *work)
+{
+	struct snd_compr_stream *stream;
+
+	stream = container_of(work, struct snd_compr_stream, error_work.work);
+
+	mutex_lock(&stream->device->lock);
+
+	stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP);
+	wake_up(&stream->runtime->sleep);
+
+	mutex_unlock(&stream->device->lock);
+}
+
+/*
+ * snd_compr_stop_error: Report a fatal error on a stream
+ * @stream: pointer to stream
+ * @state: state to transition the stream to
+ *
+ * Stop the stream and set its state.
+ *
+ * Should be called with compressed device lock held.
+ */
+int snd_compr_stop_error(struct snd_compr_stream *stream,
+			 snd_pcm_state_t state)
+{
+	if (stream->runtime->state == state)
+		return 0;
+
+	stream->runtime->state = state;
+
+	pr_debug("Changing state to: %d\n", state);
+
+	queue_delayed_work(system_power_efficient_wq, &stream->error_work, 0);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_compr_stop_error);
+
 static int snd_compress_wait_for_drain(struct snd_compr_stream *stream)
 {
 	int ret;
diff --git a/sound/core/control.c b/sound/core/control.c
index b4fe9b002512..fb096cb20a80 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -807,6 +807,36 @@ static int snd_ctl_elem_list(struct snd_card *card,
 	return 0;
 }
 
+static bool validate_element_member_dimension(struct snd_ctl_elem_info *info)
+{
+	unsigned int members;
+	unsigned int i;
+
+	if (info->dimen.d[0] == 0)
+		return true;
+
+	members = 1;
+	for (i = 0; i < ARRAY_SIZE(info->dimen.d); ++i) {
+		if (info->dimen.d[i] == 0)
+			break;
+		members *= info->dimen.d[i];
+
+		/*
+		 * info->count should be validated in advance, to guarantee
+		 * calculation soundness.
+		 */
+		if (members > info->count)
+			return false;
+	}
+
+	for (++i; i < ARRAY_SIZE(info->dimen.d); ++i) {
+		if (info->dimen.d[i] > 0)
+			return false;
+	}
+
+	return members == info->count;
+}
+
 static int snd_ctl_elem_info(struct snd_ctl_file *ctl,
 			     struct snd_ctl_elem_info *info)
 {
@@ -1274,6 +1304,8 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 	if (info->count < 1 ||
 	    info->count > max_value_counts[info->type])
 		return -EINVAL;
+	if (!validate_element_member_dimension(info))
+		return -EINVAL;
 	private_size = value_sizes[info->type] * info->count;
 
 	/*
diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c
index b16dbef04174..cd0e0ebbfdb1 100644
--- a/sound/core/seq/oss/seq_oss_synth.c
+++ b/sound/core/seq/oss/seq_oss_synth.c
@@ -70,11 +70,11 @@ struct seq_oss_synth {
 static int max_synth_devs;
 static struct seq_oss_synth *synth_devs[SNDRV_SEQ_OSS_MAX_SYNTH_DEVS];
 static struct seq_oss_synth midi_synth_dev = {
-	-1, /* seq_device */
-	SYNTH_TYPE_MIDI, /* synth_type */
-	0, /* synth_subtype */
-	16, /* nr_voices */
-	"MIDI", /* name */
+	.seq_device = -1,
+	.synth_type = SYNTH_TYPE_MIDI,
+	.synth_subtype = 0,
+	.nr_voices = 16,
+	.name = "MIDI",
 };
 
 static DEFINE_SPINLOCK(register_lock);
diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c
index 293104926098..dcc102813aef 100644
--- a/sound/core/seq/seq_timer.c
+++ b/sound/core/seq/seq_timer.c
@@ -165,7 +165,7 @@ static void snd_seq_timer_interrupt(struct snd_timer_instance *timeri,
 	snd_seq_timer_update_tick(&tmr->tick, resolution);
 
 	/* register actual time of this timer update */
-	do_gettimeofday(&tmr->last_update);
+	ktime_get_ts64(&tmr->last_update);
 
 	spin_unlock_irqrestore(&tmr->lock, flags);
 
@@ -392,7 +392,7 @@ static int seq_timer_start(struct snd_seq_timer *tmr)
 		return -EINVAL;
 	snd_timer_start(tmr->timeri, tmr->ticks);
 	tmr->running = 1;
-	do_gettimeofday(&tmr->last_update);
+	ktime_get_ts64(&tmr->last_update);
 	return 0;
 }
 
@@ -420,7 +420,7 @@ static int seq_timer_continue(struct snd_seq_timer *tmr)
 	}
 	snd_timer_start(tmr->timeri, tmr->ticks);
 	tmr->running = 1;
-	do_gettimeofday(&tmr->last_update);
+	ktime_get_ts64(&tmr->last_update);
 	return 0;
 }
 
@@ -444,17 +444,12 @@ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr)
 	spin_lock_irqsave(&tmr->lock, flags);
 	cur_time = tmr->cur_time;
 	if (tmr->running) { 
-		struct timeval tm;
-		int usec;
-		do_gettimeofday(&tm);
-		usec = (int)(tm.tv_usec - tmr->last_update.tv_usec);
-		if (usec < 0) {
-			cur_time.tv_nsec += (1000000 + usec) * 1000;
-			cur_time.tv_sec += tm.tv_sec - tmr->last_update.tv_sec - 1;
-		} else {
-			cur_time.tv_nsec += usec * 1000;
-			cur_time.tv_sec += tm.tv_sec - tmr->last_update.tv_sec;
-		}
+		struct timespec64 tm;
+
+		ktime_get_ts64(&tm);
+		tm = timespec64_sub(tm, tmr->last_update);
+		cur_time.tv_nsec = tm.tv_nsec;
+		cur_time.tv_sec = tm.tv_sec;
 		snd_seq_sanity_real_time(&cur_time);
 	}
 	spin_unlock_irqrestore(&tmr->lock, flags);
diff --git a/sound/core/seq/seq_timer.h b/sound/core/seq/seq_timer.h
index 88dfb71805ae..9506b661fe5b 100644
--- a/sound/core/seq/seq_timer.h
+++ b/sound/core/seq/seq_timer.h
@@ -52,7 +52,7 @@ struct snd_seq_timer {
 	unsigned int skew;
 	unsigned int skew_base;
 
-	struct timeval 		last_update;	 /* time of last clock update, used for interpolation */
+	struct timespec64	last_update;	 /* time of last clock update, used for interpolation */
 
 	spinlock_t lock;
 };
diff --git a/sound/hda/hdmi_chmap.c b/sound/hda/hdmi_chmap.c
index c6c75e7e0981..81acc20c2535 100644
--- a/sound/hda/hdmi_chmap.c
+++ b/sound/hda/hdmi_chmap.c
@@ -353,7 +353,8 @@ static void hdmi_std_setup_channel_mapping(struct hdac_chmap *chmap,
 		int hdmi_slot = 0;
 		/* fill actual channel mappings in ALSA channel (i) order */
 		for (i = 0; i < ch_alloc->channels; i++) {
-			while (!ch_alloc->speakers[7 - hdmi_slot] && !WARN_ON(hdmi_slot >= 8))
+			while (!WARN_ON(hdmi_slot >= 8) &&
+			       !ch_alloc->speakers[7 - hdmi_slot])
 				hdmi_slot++; /* skip zero slots */
 
 			hdmi_channel_mapping[ca][i] = (i << 4) | hdmi_slot++;
@@ -430,6 +431,12 @@ static int to_cea_slot(int ordered_ca, unsigned char pos)
 	int mask = snd_hdac_chmap_to_spk_mask(pos);
 	int i;
 
+	/* Add sanity check to pass klockwork check.
+	 * This should never happen.
+	 */
+	if (ordered_ca >= ARRAY_SIZE(channel_allocations))
+		return -1;
+
 	if (mask) {
 		for (i = 0; i < 8; i++) {
 			if (channel_allocations[ordered_ca].speakers[7 - i] == mask)
@@ -456,7 +463,15 @@ EXPORT_SYMBOL_GPL(snd_hdac_spk_to_chmap);
 /* from CEA slot to ALSA API channel position */
 static int from_cea_slot(int ordered_ca, unsigned char slot)
 {
-	int mask = channel_allocations[ordered_ca].speakers[7 - slot];
+	int mask;
+
+	/* Add sanity check to pass klockwork check.
+	 * This should never happen.
+	 */
+	if (slot >= 8)
+		return 0;
+
+	mask = channel_allocations[ordered_ca].speakers[7 - slot];
 
 	return snd_hdac_spk_to_chmap(mask);
 }
@@ -523,7 +538,8 @@ static void hdmi_setup_fake_chmap(unsigned char *map, int ca)
 	int ordered_ca = get_channel_allocation_order(ca);
 
 	for (i = 0; i < 8; i++) {
-		if (i < channel_allocations[ordered_ca].channels)
+		if (ordered_ca < ARRAY_SIZE(channel_allocations) &&
+		    i < channel_allocations[ordered_ca].channels)
 			map[i] = from_cea_slot(ordered_ca, hdmi_channel_mapping[ca][i] & 0x0f);
 		else
 			map[i] = 0;
@@ -551,6 +567,12 @@ int snd_hdac_get_active_channels(int ca)
 {
 	int ordered_ca = get_channel_allocation_order(ca);
 
+	/* Add sanity check to pass klockwork check.
+	 * This should never happen.
+	 */
+	if (ordered_ca >= ARRAY_SIZE(channel_allocations))
+		ordered_ca = 0;
+
 	return channel_allocations[ordered_ca].channels;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_get_active_channels);
diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c
index 5a4cf3fab4ae..d53c9bb36281 100644
--- a/sound/i2c/other/ak4114.c
+++ b/sound/i2c/other/ak4114.c
@@ -121,7 +121,7 @@ int snd_ak4114_create(struct snd_card *card,
 
       __fail:
 	snd_ak4114_free(chip);
-	return err < 0 ? err : -EIO;
+	return err;
 }
 EXPORT_SYMBOL(snd_ak4114_create);
 
diff --git a/sound/i2c/other/ak4117.c b/sound/i2c/other/ak4117.c
index 48848909a5a9..0702f0552d19 100644
--- a/sound/i2c/other/ak4117.c
+++ b/sound/i2c/other/ak4117.c
@@ -110,7 +110,7 @@ int snd_ak4117_create(struct snd_card *card, ak4117_read_t *read, ak4117_write_t
 
       __fail:
 	snd_ak4117_free(chip);
-	return err < 0 ? err : -EIO;
+	return err;
 }
 
 void snd_ak4117_reg_write(struct ak4117 *chip, unsigned char reg, unsigned char mask, unsigned char val)
diff --git a/sound/isa/ad1848/ad1848.c b/sound/isa/ad1848/ad1848.c
index f159da4ec890..a302d1f8d14f 100644
--- a/sound/isa/ad1848/ad1848.c
+++ b/sound/isa/ad1848/ad1848.c
@@ -170,15 +170,4 @@ static struct isa_driver snd_ad1848_driver = {
 	}
 };
 
-static int __init alsa_card_ad1848_init(void)
-{
-	return isa_register_driver(&snd_ad1848_driver, SNDRV_CARDS);
-}
-
-static void __exit alsa_card_ad1848_exit(void)
-{
-	isa_unregister_driver(&snd_ad1848_driver);
-}
-
-module_init(alsa_card_ad1848_init);
-module_exit(alsa_card_ad1848_exit);
+module_isa_driver(snd_ad1848_driver, SNDRV_CARDS);
diff --git a/sound/isa/adlib.c b/sound/isa/adlib.c
index 120c524bb2a0..8d3060fd7ad7 100644
--- a/sound/isa/adlib.c
+++ b/sound/isa/adlib.c
@@ -112,15 +112,4 @@ static struct isa_driver snd_adlib_driver = {
 	}
 };
 
-static int __init alsa_card_adlib_init(void)
-{
-	return isa_register_driver(&snd_adlib_driver, SNDRV_CARDS);
-}
-
-static void __exit alsa_card_adlib_exit(void)
-{
-	isa_unregister_driver(&snd_adlib_driver);
-}
-
-module_init(alsa_card_adlib_init);
-module_exit(alsa_card_adlib_exit);
+module_isa_driver(snd_adlib_driver, SNDRV_CARDS);
diff --git a/sound/isa/cmi8328.c b/sound/isa/cmi8328.c
index 2c89d95da674..787475084f46 100644
--- a/sound/isa/cmi8328.c
+++ b/sound/isa/cmi8328.c
@@ -469,15 +469,4 @@ static struct isa_driver snd_cmi8328_driver = {
 	},
 };
 
-static int __init alsa_card_cmi8328_init(void)
-{
-	return isa_register_driver(&snd_cmi8328_driver, CMI8328_MAX);
-}
-
-static void __exit alsa_card_cmi8328_exit(void)
-{
-	isa_unregister_driver(&snd_cmi8328_driver);
-}
-
-module_init(alsa_card_cmi8328_init)
-module_exit(alsa_card_cmi8328_exit)
+module_isa_driver(snd_cmi8328_driver, CMI8328_MAX);
diff --git a/sound/isa/cs423x/cs4231.c b/sound/isa/cs423x/cs4231.c
index 282cd75d2235..ef7448e9f813 100644
--- a/sound/isa/cs423x/cs4231.c
+++ b/sound/isa/cs423x/cs4231.c
@@ -186,15 +186,4 @@ static struct isa_driver snd_cs4231_driver = {
 	}
 };
 
-static int __init alsa_card_cs4231_init(void)
-{
-	return isa_register_driver(&snd_cs4231_driver, SNDRV_CARDS);
-}
-
-static void __exit alsa_card_cs4231_exit(void)
-{
-	isa_unregister_driver(&snd_cs4231_driver);
-}
-
-module_init(alsa_card_cs4231_init);
-module_exit(alsa_card_cs4231_exit);
+module_isa_driver(snd_cs4231_driver, SNDRV_CARDS);
diff --git a/sound/isa/galaxy/galaxy.c b/sound/isa/galaxy/galaxy.c
index 32278847884f..379abe2cbeb2 100644
--- a/sound/isa/galaxy/galaxy.c
+++ b/sound/isa/galaxy/galaxy.c
@@ -634,15 +634,4 @@ static struct isa_driver snd_galaxy_driver = {
 	}
 };
 
-static int __init alsa_card_galaxy_init(void)
-{
-	return isa_register_driver(&snd_galaxy_driver, SNDRV_CARDS);
-}
-
-static void __exit alsa_card_galaxy_exit(void)
-{
-	isa_unregister_driver(&snd_galaxy_driver);
-}
-
-module_init(alsa_card_galaxy_init);
-module_exit(alsa_card_galaxy_exit);
+module_isa_driver(snd_galaxy_driver, SNDRV_CARDS);
diff --git a/sound/isa/gus/gusclassic.c b/sound/isa/gus/gusclassic.c
index f0019715d82e..c169be49ed71 100644
--- a/sound/isa/gus/gusclassic.c
+++ b/sound/isa/gus/gusclassic.c
@@ -229,15 +229,4 @@ static struct isa_driver snd_gusclassic_driver = {
 	}
 };
 
-static int __init alsa_card_gusclassic_init(void)
-{
-	return isa_register_driver(&snd_gusclassic_driver, SNDRV_CARDS);
-}
-
-static void __exit alsa_card_gusclassic_exit(void)
-{
-	isa_unregister_driver(&snd_gusclassic_driver);
-}
-
-module_init(alsa_card_gusclassic_init);
-module_exit(alsa_card_gusclassic_exit);
+module_isa_driver(snd_gusclassic_driver, SNDRV_CARDS);
diff --git a/sound/isa/gus/gusextreme.c b/sound/isa/gus/gusextreme.c
index 693d95f46804..77ac2fd723b4 100644
--- a/sound/isa/gus/gusextreme.c
+++ b/sound/isa/gus/gusextreme.c
@@ -358,15 +358,4 @@ static struct isa_driver snd_gusextreme_driver = {
 	}
 };
 
-static int __init alsa_card_gusextreme_init(void)
-{
-	return isa_register_driver(&snd_gusextreme_driver, SNDRV_CARDS);
-}
-
-static void __exit alsa_card_gusextreme_exit(void)
-{
-	isa_unregister_driver(&snd_gusextreme_driver);
-}
-
-module_init(alsa_card_gusextreme_init);
-module_exit(alsa_card_gusextreme_exit);
+module_isa_driver(snd_gusextreme_driver, SNDRV_CARDS);
diff --git a/sound/isa/gus/gusmax.c b/sound/isa/gus/gusmax.c
index 8216e8d8f017..dd88c9d33492 100644
--- a/sound/isa/gus/gusmax.c
+++ b/sound/isa/gus/gusmax.c
@@ -370,15 +370,4 @@ static struct isa_driver snd_gusmax_driver = {
 	},
 };
 
-static int __init alsa_card_gusmax_init(void)
-{
-	return isa_register_driver(&snd_gusmax_driver, SNDRV_CARDS);
-}
-
-static void __exit alsa_card_gusmax_exit(void)
-{
-	isa_unregister_driver(&snd_gusmax_driver);
-}
-
-module_init(alsa_card_gusmax_init)
-module_exit(alsa_card_gusmax_exit)
+module_isa_driver(snd_gusmax_driver, SNDRV_CARDS);
diff --git a/sound/isa/sb/jazz16.c b/sound/isa/sb/jazz16.c
index 6b4884d052a5..4d909971eedb 100644
--- a/sound/isa/sb/jazz16.c
+++ b/sound/isa/sb/jazz16.c
@@ -387,15 +387,4 @@ static struct isa_driver snd_jazz16_driver = {
 	},
 };
 
-static int __init alsa_card_jazz16_init(void)
-{
-	return isa_register_driver(&snd_jazz16_driver, SNDRV_CARDS);
-}
-
-static void __exit alsa_card_jazz16_exit(void)
-{
-	isa_unregister_driver(&snd_jazz16_driver);
-}
-
-module_init(alsa_card_jazz16_init)
-module_exit(alsa_card_jazz16_exit)
+module_isa_driver(snd_jazz16_driver, SNDRV_CARDS);
diff --git a/sound/isa/sb/sb8.c b/sound/isa/sb/sb8.c
index b8e2391c33ff..ad42d2364199 100644
--- a/sound/isa/sb/sb8.c
+++ b/sound/isa/sb/sb8.c
@@ -251,15 +251,4 @@ static struct isa_driver snd_sb8_driver = {
 	},
 };
 
-static int __init alsa_card_sb8_init(void)
-{
-	return isa_register_driver(&snd_sb8_driver, SNDRV_CARDS);
-}
-
-static void __exit alsa_card_sb8_exit(void)
-{
-	isa_unregister_driver(&snd_sb8_driver);
-}
-
-module_init(alsa_card_sb8_init)
-module_exit(alsa_card_sb8_exit)
+module_isa_driver(snd_sb8_driver, SNDRV_CARDS);
diff --git a/sound/isa/sc6000.c b/sound/isa/sc6000.c
index 51cfa7615f72..b61a6633d8f2 100644
--- a/sound/isa/sc6000.c
+++ b/sound/isa/sc6000.c
@@ -711,15 +711,4 @@ static struct isa_driver snd_sc6000_driver = {
 };
 
 
-static int __init alsa_card_sc6000_init(void)
-{
-	return isa_register_driver(&snd_sc6000_driver, SNDRV_CARDS);
-}
-
-static void __exit alsa_card_sc6000_exit(void)
-{
-	isa_unregister_driver(&snd_sc6000_driver);
-}
-
-module_init(alsa_card_sc6000_init)
-module_exit(alsa_card_sc6000_exit)
+module_isa_driver(snd_sc6000_driver, SNDRV_CARDS);
diff --git a/sound/oss/ad1848.c b/sound/oss/ad1848.c
index 10c8de1f8d29..6368e5c7d0ba 100644
--- a/sound/oss/ad1848.c
+++ b/sound/oss/ad1848.c
@@ -254,7 +254,7 @@ static void ad_write(ad1848_info * devc, int reg, int data)
 
 static void wait_for_calibration(ad1848_info * devc)
 {
-	int timeout = 0;
+	int timeout;
 
 	/*
 	 * Wait until the auto calibration process has finished.
diff --git a/sound/oss/aedsp16.c b/sound/oss/aedsp16.c
index 35b5912cf3f8..bb477d5c8528 100644
--- a/sound/oss/aedsp16.c
+++ b/sound/oss/aedsp16.c
@@ -482,13 +482,13 @@ static struct orVals orDMA[] __initdata = {
 };
 
 static struct aedsp16_info ae_config = {
-	DEF_AEDSP16_IOB,
-	DEF_AEDSP16_IRQ,
-	DEF_AEDSP16_MRQ,
-	DEF_AEDSP16_DMA,
-	-1,
-	-1,
-	INIT_NONE
+	.base_io = DEF_AEDSP16_IOB,
+	.irq = DEF_AEDSP16_IRQ,
+	.mpu_irq = DEF_AEDSP16_MRQ,
+	.dma = DEF_AEDSP16_DMA,
+	.mss_base = -1,
+	.mpu_base = -1,
+	.init = INIT_NONE
 };
 
 /*
diff --git a/sound/oss/sound_firmware.h b/sound/oss/sound_firmware.h
index 0a0cbfdfb855..da4c67e005ed 100644
--- a/sound/oss/sound_firmware.h
+++ b/sound/oss/sound_firmware.h
@@ -1,2 +1,29 @@
-extern int mod_firmware_load(const char *fn, char **fp);
+#include <linux/fs.h>
 
+/**
+ *	mod_firmware_load - load sound driver firmware
+ *	@fn: filename
+ *	@fp: return for the buffer.
+ *
+ *	Load the firmware for a sound module (up to 128K) into a buffer.
+ *	The buffer is returned in *fp. It is allocated with vmalloc so is
+ *	virtually linear and not DMAable. The caller should free it with
+ *	vfree when finished.
+ *
+ *	The length of the buffer is returned on a successful load, the
+ *	value zero on a failure.
+ *
+ *	Caution: This API is not recommended. Firmware should be loaded via
+ *	request_firmware.
+ */
+static inline int mod_firmware_load(const char *fn, char **fp)
+{
+	loff_t size;
+	int err;
+
+	err = kernel_read_file_from_path((char *)fn, (void **)fp, &size,
+					 131072, READING_FIRMWARE);
+	if (err < 0)
+		return 0;
+	return size;
+}
diff --git a/sound/oss/sound_timer.c b/sound/oss/sound_timer.c
index 8021c85f076d..3a444a6f10eb 100644
--- a/sound/oss/sound_timer.c
+++ b/sound/oss/sound_timer.c
@@ -17,7 +17,7 @@
 #include "sound_config.h"
 
 static volatile int initialized, opened, tmr_running;
-static volatile time_t tmr_offs, tmr_ctr;
+static volatile unsigned int tmr_offs, tmr_ctr;
 static volatile unsigned long ticks_offs;
 static volatile int curr_tempo, curr_timebase;
 static volatile unsigned long curr_ticks;
diff --git a/sound/oss/sys_timer.c b/sound/oss/sys_timer.c
index 2226dda0eff0..d17019d25b99 100644
--- a/sound/oss/sys_timer.c
+++ b/sound/oss/sys_timer.c
@@ -19,7 +19,7 @@
 #include "sound_config.h"
 
 static volatile int opened, tmr_running;
-static volatile time_t tmr_offs, tmr_ctr;
+static volatile unsigned int tmr_offs, tmr_ctr;
 static volatile unsigned long ticks_offs;
 static volatile int curr_tempo, curr_timebase;
 static volatile unsigned long curr_ticks;
diff --git a/sound/pci/ctxfi/cthw20k2.c b/sound/pci/ctxfi/cthw20k2.c
index 9dc2950e1ab7..6414ecf93efa 100644
--- a/sound/pci/ctxfi/cthw20k2.c
+++ b/sound/pci/ctxfi/cthw20k2.c
@@ -1615,23 +1615,23 @@ static int hw_dac_init(struct hw *hw, const struct dac_conf *info)
 	int i;
 	struct regs_cs4382 cs_read = {0};
 	struct regs_cs4382 cs_def = {
-				   0x00000001,  /* Mode Control 1 */
-				   0x00000000,  /* Mode Control 2 */
-				   0x00000084,  /* Mode Control 3 */
-				   0x00000000,  /* Filter Control */
-				   0x00000000,  /* Invert Control */
-				   0x00000024,  /* Mixing Control Pair 1 */
-				   0x00000000,  /* Vol Control A1 */
-				   0x00000000,  /* Vol Control B1 */
-				   0x00000024,  /* Mixing Control Pair 2 */
-				   0x00000000,  /* Vol Control A2 */
-				   0x00000000,  /* Vol Control B2 */
-				   0x00000024,  /* Mixing Control Pair 3 */
-				   0x00000000,  /* Vol Control A3 */
-				   0x00000000,  /* Vol Control B3 */
-				   0x00000024,  /* Mixing Control Pair 4 */
-				   0x00000000,  /* Vol Control A4 */
-				   0x00000000   /* Vol Control B4 */
+		.mode_control_1 = 0x00000001, /* Mode Control 1 */
+		.mode_control_2 = 0x00000000, /* Mode Control 2 */
+		.mode_control_3 = 0x00000084, /* Mode Control 3 */
+		.filter_control = 0x00000000, /* Filter Control */
+		.invert_control = 0x00000000, /* Invert Control */
+		.mix_control_P1 = 0x00000024, /* Mixing Control Pair 1 */
+		.vol_control_A1 = 0x00000000, /* Vol Control A1 */
+		.vol_control_B1 = 0x00000000, /* Vol Control B1 */
+		.mix_control_P2 = 0x00000024, /* Mixing Control Pair 2 */
+		.vol_control_A2 = 0x00000000, /* Vol Control A2 */
+		.vol_control_B2 = 0x00000000, /* Vol Control B2 */
+		.mix_control_P3 = 0x00000024, /* Mixing Control Pair 3 */
+		.vol_control_A3 = 0x00000000, /* Vol Control A3 */
+		.vol_control_B3 = 0x00000000, /* Vol Control B3 */
+		.mix_control_P4 = 0x00000024, /* Mixing Control Pair 4 */
+		.vol_control_A4 = 0x00000000, /* Vol Control A4 */
+		.vol_control_B4 = 0x00000000  /* Vol Control B4 */
 				 };
 
 	if (hw->model == CTSB1270) {
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index 286f5e3686a3..937071760bc4 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -1272,11 +1272,11 @@ static int snd_echo_mixer_info(struct snd_kcontrol *kcontrol,
 
 	chip = snd_kcontrol_chip(kcontrol);
 	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
-	uinfo->count = 1;
 	uinfo->value.integer.min = ECHOGAIN_MINOUT;
 	uinfo->value.integer.max = ECHOGAIN_MAXOUT;
 	uinfo->dimen.d[0] = num_busses_out(chip);
 	uinfo->dimen.d[1] = num_busses_in(chip);
+	uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1];
 	return 0;
 }
 
@@ -1344,11 +1344,11 @@ static int snd_echo_vmixer_info(struct snd_kcontrol *kcontrol,
 
 	chip = snd_kcontrol_chip(kcontrol);
 	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
-	uinfo->count = 1;
 	uinfo->value.integer.min = ECHOGAIN_MINOUT;
 	uinfo->value.integer.max = ECHOGAIN_MAXOUT;
 	uinfo->dimen.d[0] = num_busses_out(chip);
 	uinfo->dimen.d[1] = num_pipes_out(chip);
+	uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1];
 	return 0;
 }
 
@@ -1728,7 +1728,6 @@ static int snd_echo_vumeters_info(struct snd_kcontrol *kcontrol,
 				  struct snd_ctl_elem_info *uinfo)
 {
 	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
-	uinfo->count = 96;
 	uinfo->value.integer.min = ECHOGAIN_MINOUT;
 	uinfo->value.integer.max = 0;
 #ifdef ECHOCARD_HAS_VMIXER
@@ -1738,6 +1737,7 @@ static int snd_echo_vumeters_info(struct snd_kcontrol *kcontrol,
 #endif
 	uinfo->dimen.d[1] = 16;	/* 16 channels */
 	uinfo->dimen.d[2] = 2;	/* 0=level, 1=peak */
+	uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1] * uinfo->dimen.d[2];
 	return 0;
 }
 
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 83741887faa1..9913be8532ab 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -3584,6 +3584,12 @@ static void setup_dig_out_stream(struct hda_codec *codec, hda_nid_t nid,
 	bool reset;
 
 	spdif = snd_hda_spdif_out_of_nid(codec, nid);
+	/* Add sanity check to pass klockwork check.
+	 * This should never happen.
+	 */
+	if (WARN_ON(spdif == NULL))
+		return;
+
 	curr_fmt = snd_hda_codec_read(codec, nid, 0,
 				      AC_VERB_GET_STREAM_FORMAT, 0);
 	reset = codec->spdif_status_reset &&
@@ -3768,7 +3774,7 @@ int snd_hda_multi_out_analog_prepare(struct hda_codec *codec,
 	spdif = snd_hda_spdif_out_of_nid(codec, mout->dig_out_nid);
 	if (mout->dig_out_nid && mout->share_spdif &&
 	    mout->dig_out_used != HDA_DIG_EXCLUSIVE) {
-		if (chs == 2 &&
+		if (chs == 2 && spdif != NULL &&
 		    snd_hda_is_supported_format(codec, mout->dig_out_nid,
 						format) &&
 		    !(spdif->status & IEC958_AES0_NONAUDIO)) {
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 79c7b340acc2..e7c8f4f076d5 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -2492,10 +2492,6 @@ static int create_loopback_mixing_ctl(struct hda_codec *codec)
 	if (!snd_hda_gen_add_kctl(spec, NULL, &loopback_mixing_enum))
 		return -ENOMEM;
 	spec->have_aamix_ctl = 1;
-	/* if no explicit aamix path is present (e.g. for Realtek codecs),
-	 * enable aamix as default -- just for compatibility
-	 */
-	spec->aamix_mode = !has_aamix_out_paths(spec);
 	return 0;
 }
 
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index d0d5ad8beac5..56e5204ac9c1 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1680,6 +1680,11 @@ static bool check_non_pcm_per_cvt(struct hda_codec *codec, hda_nid_t cvt_nid)
 
 	mutex_lock(&codec->spdif_mutex);
 	spdif = snd_hda_spdif_out_of_nid(codec, cvt_nid);
+	/* Add sanity check to pass klockwork check.
+	 * This should never happen.
+	 */
+	if (WARN_ON(spdif == NULL))
+		return true;
 	non_pcm = !!(spdif->status & IEC958_AES0_NONAUDIO);
 	mutex_unlock(&codec->spdif_mutex);
 	return non_pcm;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index abcb5a6a1cd9..ddd29b9819ba 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3718,6 +3718,9 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 	case 0x10ec0295:
 		alc_process_coef_fw(codec, coef0225);
 		break;
+	case 0x10ec0867:
+		alc_update_coefex_idx(codec, 0x57, 0x5, 1<<14, 0);
+		break;
 	}
 	codec_dbg(codec, "Headset jack set to unplugged mode.\n");
 }
@@ -3805,6 +3808,9 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 		alc_process_coef_fw(codec, coef0293);
 		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
 		break;
+	case 0x10ec0867:
+		alc_update_coefex_idx(codec, 0x57, 0x5, 0, 1<<14);
+		/* fallthru */
 	case 0x10ec0662:
 		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
 		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
@@ -3899,6 +3905,9 @@ static void alc_headset_mode_default(struct hda_codec *codec)
 	case 0x10ec0668:
 		alc_process_coef_fw(codec, coef0688);
 		break;
+	case 0x10ec0867:
+		alc_update_coefex_idx(codec, 0x57, 0x5, 1<<14, 0);
+		break;
 	}
 	codec_dbg(codec, "Headset jack set to headphone (default) mode.\n");
 }
@@ -3989,6 +3998,9 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 	case 0x10ec0295:
 		alc_process_coef_fw(codec, coef0225);
 		break;
+	case 0x10ec0867:
+		alc_update_coefex_idx(codec, 0x57, 0x5, 1<<14, 0);
+		break;
 	}
 	codec_dbg(codec, "Headset jack set to iPhone-style headset mode.\n");
 }
@@ -4166,6 +4178,9 @@ static void alc_determine_headset_type(struct hda_codec *codec)
 		val = alc_read_coef_idx(codec, 0x46);
 		is_ctia = (val & 0x00f0) == 0x00f0;
 		break;
+	case 0x10ec0867:
+		is_ctia = true;
+		break;
 	}
 
 	codec_dbg(codec, "Headset jack detected iPhone-style headset: %s\n",
@@ -6532,6 +6547,8 @@ enum {
 	ALC668_FIXUP_DELL_XPS13,
 	ALC662_FIXUP_ASUS_Nx50,
 	ALC668_FIXUP_ASUS_Nx51,
+	ALC891_FIXUP_HEADSET_MODE,
+	ALC891_FIXUP_DELL_MIC_NO_PRESENCE,
 };
 
 static const struct hda_fixup alc662_fixups[] = {
@@ -6787,6 +6804,20 @@ static const struct hda_fixup alc662_fixups[] = {
 		.chained = true,
 		.chain_id = ALC662_FIXUP_BASS_CHMAP,
 	},
+	[ALC891_FIXUP_HEADSET_MODE] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_headset_mode,
+	},
+	[ALC891_FIXUP_DELL_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x03a1913d }, /* use as headphone mic, without its own jack detect */
+			{ 0x1b, 0x03a1113c }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC891_FIXUP_HEADSET_MODE
+	},
 };
 
 static const struct snd_pci_quirk alc662_fixup_tbl[] = {
@@ -6903,6 +6934,11 @@ static const struct hda_model_fixup alc662_fixup_models[] = {
 };
 
 static const struct snd_hda_pin_quirk alc662_pin_fixup_tbl[] = {
+	SND_HDA_PIN_QUIRK(0x10ec0867, 0x1028, "Dell", ALC891_FIXUP_DELL_MIC_NO_PRESENCE,
+		{0x17, 0x02211010},
+		{0x18, 0x01a19030},
+		{0x1a, 0x01813040},
+		{0x21, 0x01014020}),
 	SND_HDA_PIN_QUIRK(0x10ec0662, 0x1028, "Dell", ALC662_FIXUP_DELL_MIC_NO_PRESENCE,
 		{0x14, 0x01014010},
 		{0x18, 0x01a19020},
@@ -7091,7 +7127,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0700, "ALC700", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0701, "ALC701", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0703, "ALC703", patch_alc269),
-	HDA_CODEC_ENTRY(0x10ec0867, "ALC891", patch_alc882),
+	HDA_CODEC_ENTRY(0x10ec0867, "ALC891", patch_alc662),
 	HDA_CODEC_ENTRY(0x10ec0880, "ALC880", patch_alc880),
 	HDA_CODEC_ENTRY(0x10ec0882, "ALC882", patch_alc882),
 	HDA_CODEC_ENTRY(0x10ec0883, "ALC883", patch_alc882),
diff --git a/sound/pci/mixart/mixart_mixer.c b/sound/pci/mixart/mixart_mixer.c
index 58fd79ebac20..51e53497f0ad 100644
--- a/sound/pci/mixart/mixart_mixer.c
+++ b/sound/pci/mixart/mixart_mixer.c
@@ -965,7 +965,7 @@ static int mixart_update_monitoring(struct snd_mixart* chip, int channel)
 	int err;
 	struct mixart_msg request;
 	struct mixart_set_out_audio_level audio_level;
-	u32 resp;
+	u32 resp = 0;
 
 	if(chip->pipe_out_ana.status == PIPE_UNDEFINED)
 		return -EINVAL; /* no pipe defined */
diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c
index 94639d6b5fb5..067a91207d8e 100644
--- a/sound/pci/riptide/riptide.c
+++ b/sound/pci/riptide/riptide.c
@@ -1496,7 +1496,7 @@ static int snd_riptide_prepare(struct snd_pcm_substream *substream)
 		f = PAGE_SIZE;
 		while ((size + (f >> 1) - 1) <= (f << 7) && (f << 1) > period)
 			f = f >> 1;
-		pages = (size + f - 1) / f;
+		pages = DIV_ROUND_UP(size, f);
 		data->size = size;
 		data->pages = pages;
 		snd_printdd
diff --git a/sound/ppc/awacs.c b/sound/ppc/awacs.c
index 09da7b52bc2e..1468e4b7bf93 100644
--- a/sound/ppc/awacs.c
+++ b/sound/ppc/awacs.c
@@ -991,6 +991,7 @@ snd_pmac_awacs_init(struct snd_pmac *chip)
 		if (err < 0)
 			return err;
 	}
+	master_vol = NULL;
 	if (pm7500)
 		err = build_mixers(chip,
 				   ARRAY_SIZE(snd_pmac_awacs_mixers_pmac7500),
diff --git a/sound/sh/aica.c b/sound/sh/aica.c
index ad3d9ae38034..fbbc25279559 100644
--- a/sound/sh/aica.c
+++ b/sound/sh/aica.c
@@ -63,9 +63,6 @@ MODULE_PARM_DESC(id, "ID string for " CARD_NAME " soundcard.");
 module_param(enable, bool, 0644);
 MODULE_PARM_DESC(enable, "Enable " CARD_NAME " soundcard.");
 
-/* Use workqueue */
-static struct workqueue_struct *aica_queue;
-
 /* Simple platform device */
 static struct platform_device *pd;
 static struct resource aica_memory_space[2] = {
@@ -327,7 +324,7 @@ static void aica_period_elapsed(unsigned long timer_var)
 		dreamcastcard->current_period = play_period;
 	if (unlikely(dreamcastcard->dma_check == 0))
 		dreamcastcard->dma_check = 1;
-	queue_work(aica_queue, &(dreamcastcard->spu_dma_work));
+	schedule_work(&(dreamcastcard->spu_dma_work));
 }
 
 static void spu_begin_dma(struct snd_pcm_substream *substream)
@@ -337,7 +334,7 @@ static void spu_begin_dma(struct snd_pcm_substream *substream)
 	runtime = substream->runtime;
 	dreamcastcard = substream->pcm->private_data;
 	/*get the queue to do the work */
-	queue_work(aica_queue, &(dreamcastcard->spu_dma_work));
+	schedule_work(&(dreamcastcard->spu_dma_work));
 	/* Timer may already be running */
 	if (unlikely(dreamcastcard->timer.data)) {
 		mod_timer(&dreamcastcard->timer, jiffies + 4);
@@ -381,7 +378,7 @@ static int snd_aicapcm_pcm_close(struct snd_pcm_substream
 				 *substream)
 {
 	struct snd_card_aica *dreamcastcard = substream->pcm->private_data;
-	flush_workqueue(aica_queue);
+	flush_work(&(dreamcastcard->spu_dma_work));
 	if (dreamcastcard->timer.data)
 		del_timer(&dreamcastcard->timer);
 	kfree(dreamcastcard->channel);
@@ -633,9 +630,6 @@ static int snd_aica_probe(struct platform_device *devptr)
 	if (unlikely(err < 0))
 		goto freedreamcast;
 	platform_set_drvdata(devptr, dreamcastcard);
-	aica_queue = create_workqueue(CARD_NAME);
-	if (unlikely(!aica_queue))
-		goto freedreamcast;
 	snd_printk
 	    ("ALSA Driver for Yamaha AICA Super Intelligent Sound Processor\n");
 	return 0;
@@ -671,10 +665,6 @@ static int __init aica_init(void)
 
 static void __exit aica_exit(void)
 {
-	/* Destroy the aica kernel thread            *
-	 * being extra cautious to check if it exists*/
-	if (likely(aica_queue))
-		destroy_workqueue(aica_queue);
 	platform_device_unregister(pd);
 	platform_driver_unregister(&snd_aica_driver);
 	/* Kill any sound still playing and reset ARM7 to safe state */
diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig
index 06e099e802df..22aec9a1e9a4 100644
--- a/sound/soc/atmel/Kconfig
+++ b/sound/soc/atmel/Kconfig
@@ -10,6 +10,7 @@ if SND_ATMEL_SOC
 
 config SND_ATMEL_SOC_PDC
 	tristate
+	depends on HAS_DMA
 	default m if SND_ATMEL_SOC_SSC_PDC=m && SND_ATMEL_SOC_SSC=m
 	default y if SND_ATMEL_SOC_SSC_PDC=y || (SND_ATMEL_SOC_SSC_PDC=m && SND_ATMEL_SOC_SSC=y)
 
diff --git a/sound/soc/atmel/atmel-classd.c b/sound/soc/atmel/atmel-classd.c
index 6107de9c538b..6d9b8b44e2da 100644
--- a/sound/soc/atmel/atmel-classd.c
+++ b/sound/soc/atmel/atmel-classd.c
@@ -593,11 +593,6 @@ static int atmel_classd_probe(struct platform_device *pdev)
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "no memory resource\n");
-		return -ENXIO;
-	}
-
 	io_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(io_base)) {
 		ret =  PTR_ERR(io_base);
diff --git a/sound/soc/atmel/atmel-pdmic.c b/sound/soc/atmel/atmel-pdmic.c
index aee4787a0b89..5f56da60c92f 100644
--- a/sound/soc/atmel/atmel-pdmic.c
+++ b/sound/soc/atmel/atmel-pdmic.c
@@ -624,11 +624,6 @@ static int atmel_pdmic_probe(struct platform_device *pdev)
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "no memory resource\n");
-		return -ENXIO;
-	}
-
 	io_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(io_base)) {
 		ret = PTR_ERR(io_base);
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index 1267e1af0fae..54c09acd3fed 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -321,7 +321,7 @@ static int atmel_ssc_startup(struct snd_pcm_substream *substream,
 		return ret;
 	}
 
-	dma_params = &ssc_dma_params[dai->id][dir];
+	dma_params = &ssc_dma_params[pdev->id][dir];
 	dma_params->ssc = ssc_p->ssc;
 	dma_params->substream = substream;
 
diff --git a/sound/soc/bcm/Kconfig b/sound/soc/bcm/Kconfig
index 6a834e109f1d..d528aaceaad9 100644
--- a/sound/soc/bcm/Kconfig
+++ b/sound/soc/bcm/Kconfig
@@ -7,3 +7,12 @@ config SND_BCM2835_SOC_I2S
 	  Say Y or M if you want to add support for codecs attached to
 	  the BCM2835 I2S interface. You will also need
 	  to select the audio interfaces to support below.
+
+config SND_SOC_CYGNUS
+	tristate "SoC platform audio for Broadcom Cygnus chips"
+	depends on ARCH_BCM_CYGNUS || COMPILE_TEST
+	help
+	  Say Y if you want to add support for ASoC audio on Broadcom
+	  Cygnus chips (bcm958300, bcm958305, bcm911360)
+
+	  If you don't know what to do here, say N.
\ No newline at end of file
diff --git a/sound/soc/bcm/Makefile b/sound/soc/bcm/Makefile
index bc816b71e5a4..fc739d007884 100644
--- a/sound/soc/bcm/Makefile
+++ b/sound/soc/bcm/Makefile
@@ -3,3 +3,8 @@ snd-soc-bcm2835-i2s-objs := bcm2835-i2s.o
 
 obj-$(CONFIG_SND_BCM2835_SOC_I2S) += snd-soc-bcm2835-i2s.o
 
+# CYGNUS Platform Support
+snd-soc-cygnus-objs := cygnus-pcm.o cygnus-ssp.o
+
+obj-$(CONFIG_SND_SOC_CYGNUS) += snd-soc-cygnus.o
+
diff --git a/sound/soc/bcm/cygnus-pcm.c b/sound/soc/bcm/cygnus-pcm.c
new file mode 100644
index 000000000000..d616e096462e
--- /dev/null
+++ b/sound/soc/bcm/cygnus-pcm.c
@@ -0,0 +1,861 @@
+/*
+ * Copyright (C) 2014-2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/debugfs.h>
+#include <linux/dma-mapping.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/timer.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "cygnus-ssp.h"
+
+/* Register offset needed for ASoC PCM module */
+
+#define INTH_R5F_STATUS_OFFSET     0x040
+#define INTH_R5F_CLEAR_OFFSET      0x048
+#define INTH_R5F_MASK_SET_OFFSET   0x050
+#define INTH_R5F_MASK_CLEAR_OFFSET 0x054
+
+#define BF_REARM_FREE_MARK_OFFSET 0x344
+#define BF_REARM_FULL_MARK_OFFSET 0x348
+
+/* Ring Buffer Ctrl Regs --- Start */
+/* AUD_FMM_BF_CTRL_SOURCECH_RINGBUF_X_RDADDR_REG_BASE */
+#define SRC_RBUF_0_RDADDR_OFFSET 0x500
+#define SRC_RBUF_1_RDADDR_OFFSET 0x518
+#define SRC_RBUF_2_RDADDR_OFFSET 0x530
+#define SRC_RBUF_3_RDADDR_OFFSET 0x548
+#define SRC_RBUF_4_RDADDR_OFFSET 0x560
+#define SRC_RBUF_5_RDADDR_OFFSET 0x578
+#define SRC_RBUF_6_RDADDR_OFFSET 0x590
+
+/* AUD_FMM_BF_CTRL_SOURCECH_RINGBUF_X_WRADDR_REG_BASE */
+#define SRC_RBUF_0_WRADDR_OFFSET 0x504
+#define SRC_RBUF_1_WRADDR_OFFSET 0x51c
+#define SRC_RBUF_2_WRADDR_OFFSET 0x534
+#define SRC_RBUF_3_WRADDR_OFFSET 0x54c
+#define SRC_RBUF_4_WRADDR_OFFSET 0x564
+#define SRC_RBUF_5_WRADDR_OFFSET 0x57c
+#define SRC_RBUF_6_WRADDR_OFFSET 0x594
+
+/* AUD_FMM_BF_CTRL_SOURCECH_RINGBUF_X_BASEADDR_REG_BASE */
+#define SRC_RBUF_0_BASEADDR_OFFSET 0x508
+#define SRC_RBUF_1_BASEADDR_OFFSET 0x520
+#define SRC_RBUF_2_BASEADDR_OFFSET 0x538
+#define SRC_RBUF_3_BASEADDR_OFFSET 0x550
+#define SRC_RBUF_4_BASEADDR_OFFSET 0x568
+#define SRC_RBUF_5_BASEADDR_OFFSET 0x580
+#define SRC_RBUF_6_BASEADDR_OFFSET 0x598
+
+/* AUD_FMM_BF_CTRL_SOURCECH_RINGBUF_X_ENDADDR_REG_BASE */
+#define SRC_RBUF_0_ENDADDR_OFFSET 0x50c
+#define SRC_RBUF_1_ENDADDR_OFFSET 0x524
+#define SRC_RBUF_2_ENDADDR_OFFSET 0x53c
+#define SRC_RBUF_3_ENDADDR_OFFSET 0x554
+#define SRC_RBUF_4_ENDADDR_OFFSET 0x56c
+#define SRC_RBUF_5_ENDADDR_OFFSET 0x584
+#define SRC_RBUF_6_ENDADDR_OFFSET 0x59c
+
+/* AUD_FMM_BF_CTRL_SOURCECH_RINGBUF_X_FREE_MARK_REG_BASE */
+#define SRC_RBUF_0_FREE_MARK_OFFSET 0x510
+#define SRC_RBUF_1_FREE_MARK_OFFSET 0x528
+#define SRC_RBUF_2_FREE_MARK_OFFSET 0x540
+#define SRC_RBUF_3_FREE_MARK_OFFSET 0x558
+#define SRC_RBUF_4_FREE_MARK_OFFSET 0x570
+#define SRC_RBUF_5_FREE_MARK_OFFSET 0x588
+#define SRC_RBUF_6_FREE_MARK_OFFSET 0x5a0
+
+/* AUD_FMM_BF_CTRL_DESTCH_RINGBUF_X_RDADDR_REG_BASE */
+#define DST_RBUF_0_RDADDR_OFFSET 0x5c0
+#define DST_RBUF_1_RDADDR_OFFSET 0x5d8
+#define DST_RBUF_2_RDADDR_OFFSET 0x5f0
+#define DST_RBUF_3_RDADDR_OFFSET 0x608
+#define DST_RBUF_4_RDADDR_OFFSET 0x620
+#define DST_RBUF_5_RDADDR_OFFSET 0x638
+
+/* AUD_FMM_BF_CTRL_DESTCH_RINGBUF_X_WRADDR_REG_BASE */
+#define DST_RBUF_0_WRADDR_OFFSET 0x5c4
+#define DST_RBUF_1_WRADDR_OFFSET 0x5dc
+#define DST_RBUF_2_WRADDR_OFFSET 0x5f4
+#define DST_RBUF_3_WRADDR_OFFSET 0x60c
+#define DST_RBUF_4_WRADDR_OFFSET 0x624
+#define DST_RBUF_5_WRADDR_OFFSET 0x63c
+
+/* AUD_FMM_BF_CTRL_DESTCH_RINGBUF_X_BASEADDR_REG_BASE */
+#define DST_RBUF_0_BASEADDR_OFFSET 0x5c8
+#define DST_RBUF_1_BASEADDR_OFFSET 0x5e0
+#define DST_RBUF_2_BASEADDR_OFFSET 0x5f8
+#define DST_RBUF_3_BASEADDR_OFFSET 0x610
+#define DST_RBUF_4_BASEADDR_OFFSET 0x628
+#define DST_RBUF_5_BASEADDR_OFFSET 0x640
+
+/* AUD_FMM_BF_CTRL_DESTCH_RINGBUF_X_ENDADDR_REG_BASE */
+#define DST_RBUF_0_ENDADDR_OFFSET 0x5cc
+#define DST_RBUF_1_ENDADDR_OFFSET 0x5e4
+#define DST_RBUF_2_ENDADDR_OFFSET 0x5fc
+#define DST_RBUF_3_ENDADDR_OFFSET 0x614
+#define DST_RBUF_4_ENDADDR_OFFSET 0x62c
+#define DST_RBUF_5_ENDADDR_OFFSET 0x644
+
+/* AUD_FMM_BF_CTRL_DESTCH_RINGBUF_X_FULL_MARK_REG_BASE */
+#define DST_RBUF_0_FULL_MARK_OFFSET 0x5d0
+#define DST_RBUF_1_FULL_MARK_OFFSET 0x5e8
+#define DST_RBUF_2_FULL_MARK_OFFSET 0x600
+#define DST_RBUF_3_FULL_MARK_OFFSET 0x618
+#define DST_RBUF_4_FULL_MARK_OFFSET 0x630
+#define DST_RBUF_5_FULL_MARK_OFFSET 0x648
+/* Ring Buffer Ctrl Regs --- End */
+
+/* Error Status Regs --- Start */
+/* AUD_FMM_BF_ESR_ESRX_STATUS_REG_BASE */
+#define ESR0_STATUS_OFFSET 0x900
+#define ESR1_STATUS_OFFSET 0x918
+#define ESR2_STATUS_OFFSET 0x930
+#define ESR3_STATUS_OFFSET 0x948
+#define ESR4_STATUS_OFFSET 0x960
+
+/* AUD_FMM_BF_ESR_ESRX_STATUS_CLEAR_REG_BASE */
+#define ESR0_STATUS_CLR_OFFSET 0x908
+#define ESR1_STATUS_CLR_OFFSET 0x920
+#define ESR2_STATUS_CLR_OFFSET 0x938
+#define ESR3_STATUS_CLR_OFFSET 0x950
+#define ESR4_STATUS_CLR_OFFSET 0x968
+
+/* AUD_FMM_BF_ESR_ESRX_MASK_REG_BASE */
+#define ESR0_MASK_STATUS_OFFSET 0x90c
+#define ESR1_MASK_STATUS_OFFSET 0x924
+#define ESR2_MASK_STATUS_OFFSET 0x93c
+#define ESR3_MASK_STATUS_OFFSET 0x954
+#define ESR4_MASK_STATUS_OFFSET 0x96c
+
+/* AUD_FMM_BF_ESR_ESRX_MASK_SET_REG_BASE */
+#define ESR0_MASK_SET_OFFSET 0x910
+#define ESR1_MASK_SET_OFFSET 0x928
+#define ESR2_MASK_SET_OFFSET 0x940
+#define ESR3_MASK_SET_OFFSET 0x958
+#define ESR4_MASK_SET_OFFSET 0x970
+
+/* AUD_FMM_BF_ESR_ESRX_MASK_CLEAR_REG_BASE */
+#define ESR0_MASK_CLR_OFFSET 0x914
+#define ESR1_MASK_CLR_OFFSET 0x92c
+#define ESR2_MASK_CLR_OFFSET 0x944
+#define ESR3_MASK_CLR_OFFSET 0x95c
+#define ESR4_MASK_CLR_OFFSET 0x974
+/* Error Status Regs --- End */
+
+#define R5F_ESR0_SHIFT  0    /* esr0 = fifo underflow */
+#define R5F_ESR1_SHIFT  1    /* esr1 = ringbuf underflow */
+#define R5F_ESR2_SHIFT  2    /* esr2 = ringbuf overflow */
+#define R5F_ESR3_SHIFT  3    /* esr3 = freemark */
+#define R5F_ESR4_SHIFT  4    /* esr4 = fullmark */
+
+
+/* Mask for R5F register.  Set all relevant interrupt for playback handler */
+#define ANY_PLAYBACK_IRQ  (BIT(R5F_ESR0_SHIFT) | \
+			   BIT(R5F_ESR1_SHIFT) | \
+			   BIT(R5F_ESR3_SHIFT))
+
+/* Mask for R5F register.  Set all relevant interrupt for capture handler */
+#define ANY_CAPTURE_IRQ   (BIT(R5F_ESR2_SHIFT) | BIT(R5F_ESR4_SHIFT))
+
+/*
+ * PERIOD_BYTES_MIN is the number of bytes to at which the interrupt will tick.
+ * This number should be a multiple of 256. Minimum value is 256
+ */
+#define PERIOD_BYTES_MIN 0x100
+
+static const struct snd_pcm_hardware cygnus_pcm_hw = {
+	.info = SNDRV_PCM_INFO_MMAP |
+			SNDRV_PCM_INFO_MMAP_VALID |
+			SNDRV_PCM_INFO_INTERLEAVED,
+	.formats = SNDRV_PCM_FMTBIT_S16_LE |
+			SNDRV_PCM_FMTBIT_S32_LE,
+
+	/* A period is basically an interrupt */
+	.period_bytes_min = PERIOD_BYTES_MIN,
+	.period_bytes_max = 0x10000,
+
+	/* period_min/max gives range of approx interrupts per buffer */
+	.periods_min = 2,
+	.periods_max = 8,
+
+	/*
+	 * maximum buffer size in bytes = period_bytes_max * periods_max
+	 * We allocate this amount of data for each enabled channel
+	 */
+	.buffer_bytes_max = 4 * 0x8000,
+};
+
+static u64 cygnus_dma_dmamask = DMA_BIT_MASK(32);
+
+static struct cygnus_aio_port *cygnus_dai_get_dma_data(
+				struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
+
+	return snd_soc_dai_get_dma_data(soc_runtime->cpu_dai, substream);
+}
+
+static void ringbuf_set_initial(void __iomem *audio_io,
+		struct ringbuf_regs *p_rbuf,
+		bool is_playback,
+		u32 start,
+		u32 periodsize,
+		u32 bufsize)
+{
+	u32 initial_rd;
+	u32 initial_wr;
+	u32 end;
+	u32 fmark_val; /* free or full mark */
+
+	p_rbuf->period_bytes = periodsize;
+	p_rbuf->buf_size = bufsize;
+
+	if (is_playback) {
+		/* Set the pointers to indicate full (flip uppermost bit) */
+		initial_rd = start;
+		initial_wr = initial_rd ^ BIT(31);
+	} else {
+		/* Set the pointers to indicate empty */
+		initial_wr = start;
+		initial_rd = initial_wr;
+	}
+
+	end = start + bufsize - 1;
+
+	/*
+	 * The interrupt will fire when free/full mark is *exceeded*
+	 * The fmark value must be multiple of PERIOD_BYTES_MIN so set fmark
+	 * to be PERIOD_BYTES_MIN less than the period size.
+	 */
+	fmark_val = periodsize - PERIOD_BYTES_MIN;
+
+	writel(start, audio_io + p_rbuf->baseaddr);
+	writel(end, audio_io + p_rbuf->endaddr);
+	writel(fmark_val, audio_io + p_rbuf->fmark);
+	writel(initial_rd, audio_io + p_rbuf->rdaddr);
+	writel(initial_wr, audio_io + p_rbuf->wraddr);
+}
+
+static int configure_ringbuf_regs(struct snd_pcm_substream *substream)
+{
+	struct cygnus_aio_port *aio;
+	struct ringbuf_regs *p_rbuf;
+	int status = 0;
+
+	aio = cygnus_dai_get_dma_data(substream);
+
+	/* Map the ssp portnum to a set of ring buffers. */
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		p_rbuf = &aio->play_rb_regs;
+
+		switch (aio->portnum) {
+		case 0:
+			*p_rbuf = RINGBUF_REG_PLAYBACK(0);
+			break;
+		case 1:
+			*p_rbuf = RINGBUF_REG_PLAYBACK(2);
+			break;
+		case 2:
+			*p_rbuf = RINGBUF_REG_PLAYBACK(4);
+			break;
+		case 3: /* SPDIF */
+			*p_rbuf = RINGBUF_REG_PLAYBACK(6);
+			break;
+		default:
+			status = -EINVAL;
+		}
+	} else {
+		p_rbuf = &aio->capture_rb_regs;
+
+		switch (aio->portnum) {
+		case 0:
+			*p_rbuf = RINGBUF_REG_CAPTURE(0);
+			break;
+		case 1:
+			*p_rbuf = RINGBUF_REG_CAPTURE(2);
+			break;
+		case 2:
+			*p_rbuf = RINGBUF_REG_CAPTURE(4);
+			break;
+		default:
+			status = -EINVAL;
+		}
+	}
+
+	return status;
+}
+
+static struct ringbuf_regs *get_ringbuf(struct snd_pcm_substream *substream)
+{
+	struct cygnus_aio_port *aio;
+	struct ringbuf_regs *p_rbuf = NULL;
+
+	aio = cygnus_dai_get_dma_data(substream);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		p_rbuf = &aio->play_rb_regs;
+	else
+		p_rbuf = &aio->capture_rb_regs;
+
+	return p_rbuf;
+}
+
+static void enable_intr(struct snd_pcm_substream *substream)
+{
+	struct cygnus_aio_port *aio;
+	u32 clear_mask;
+
+	aio = cygnus_dai_get_dma_data(substream);
+
+	/* The port number maps to the bit position to be cleared */
+	clear_mask = BIT(aio->portnum);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		/* Clear interrupt status before enabling them */
+		writel(clear_mask, aio->cygaud->audio + ESR0_STATUS_CLR_OFFSET);
+		writel(clear_mask, aio->cygaud->audio + ESR1_STATUS_CLR_OFFSET);
+		writel(clear_mask, aio->cygaud->audio + ESR3_STATUS_CLR_OFFSET);
+		/* Unmask the interrupts of the given port*/
+		writel(clear_mask, aio->cygaud->audio + ESR0_MASK_CLR_OFFSET);
+		writel(clear_mask, aio->cygaud->audio + ESR1_MASK_CLR_OFFSET);
+		writel(clear_mask, aio->cygaud->audio + ESR3_MASK_CLR_OFFSET);
+
+		writel(ANY_PLAYBACK_IRQ,
+			aio->cygaud->audio + INTH_R5F_MASK_CLEAR_OFFSET);
+	} else {
+		writel(clear_mask, aio->cygaud->audio + ESR2_STATUS_CLR_OFFSET);
+		writel(clear_mask, aio->cygaud->audio + ESR4_STATUS_CLR_OFFSET);
+		writel(clear_mask, aio->cygaud->audio + ESR2_MASK_CLR_OFFSET);
+		writel(clear_mask, aio->cygaud->audio + ESR4_MASK_CLR_OFFSET);
+
+		writel(ANY_CAPTURE_IRQ,
+			aio->cygaud->audio + INTH_R5F_MASK_CLEAR_OFFSET);
+	}
+
+}
+
+static void disable_intr(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct cygnus_aio_port *aio;
+	u32 set_mask;
+
+	aio = cygnus_dai_get_dma_data(substream);
+
+	dev_dbg(rtd->cpu_dai->dev, "%s on port %d\n", __func__, aio->portnum);
+
+	/* The port number maps to the bit position to be set */
+	set_mask = BIT(aio->portnum);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		/* Mask the interrupts of the given port*/
+		writel(set_mask, aio->cygaud->audio + ESR0_MASK_SET_OFFSET);
+		writel(set_mask, aio->cygaud->audio + ESR1_MASK_SET_OFFSET);
+		writel(set_mask, aio->cygaud->audio + ESR3_MASK_SET_OFFSET);
+	} else {
+		writel(set_mask, aio->cygaud->audio + ESR2_MASK_SET_OFFSET);
+		writel(set_mask, aio->cygaud->audio + ESR4_MASK_SET_OFFSET);
+	}
+
+}
+
+static int cygnus_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+{
+	int ret = 0;
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+		enable_intr(substream);
+		break;
+
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+		disable_intr(substream);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static void cygnus_pcm_period_elapsed(struct snd_pcm_substream *substream)
+{
+	struct cygnus_aio_port *aio;
+	struct ringbuf_regs *p_rbuf = NULL;
+	u32 regval;
+
+	aio = cygnus_dai_get_dma_data(substream);
+
+	p_rbuf = get_ringbuf(substream);
+
+	/*
+	 * If free/full mark interrupt occurs, provide timestamp
+	 * to ALSA and update appropriate idx by period_bytes
+	 */
+	snd_pcm_period_elapsed(substream);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		/* Set the ring buffer to full */
+		regval = readl(aio->cygaud->audio + p_rbuf->rdaddr);
+		regval = regval ^ BIT(31);
+		writel(regval, aio->cygaud->audio + p_rbuf->wraddr);
+	} else {
+		/* Set the ring buffer to empty */
+		regval = readl(aio->cygaud->audio + p_rbuf->wraddr);
+		writel(regval, aio->cygaud->audio + p_rbuf->rdaddr);
+	}
+}
+
+/*
+ * ESR0/1/3 status  Description
+ *  0x1	I2S0_out port caused interrupt
+ *  0x2	I2S1_out port caused interrupt
+ *  0x4	I2S2_out port caused interrupt
+ *  0x8	SPDIF_out port caused interrupt
+ */
+static void handle_playback_irq(struct cygnus_audio *cygaud)
+{
+	void __iomem *audio_io;
+	u32 port;
+	u32 esr_status0, esr_status1, esr_status3;
+
+	audio_io = cygaud->audio;
+
+	/*
+	 * ESR status gets updates with/without interrupts enabled.
+	 * So, check the ESR mask, which provides interrupt enable/
+	 * disable status and use it to determine which ESR status
+	 * should be serviced.
+	 */
+	esr_status0 = readl(audio_io + ESR0_STATUS_OFFSET);
+	esr_status0 &= ~readl(audio_io + ESR0_MASK_STATUS_OFFSET);
+	esr_status1 = readl(audio_io + ESR1_STATUS_OFFSET);
+	esr_status1 &= ~readl(audio_io + ESR1_MASK_STATUS_OFFSET);
+	esr_status3 = readl(audio_io + ESR3_STATUS_OFFSET);
+	esr_status3 &= ~readl(audio_io + ESR3_MASK_STATUS_OFFSET);
+
+	for (port = 0; port < CYGNUS_MAX_PLAYBACK_PORTS; port++) {
+		u32 esrmask = BIT(port);
+
+		/*
+		 * Ringbuffer or FIFO underflow
+		 * If we get this interrupt then, it is also true that we have
+		 * not yet responded to the freemark interrupt.
+		 * Log a debug message.  The freemark handler below will
+		 * handle getting everything going again.
+		 */
+		if ((esrmask & esr_status1) || (esrmask & esr_status0)) {
+			dev_dbg(cygaud->dev,
+				"Underrun: esr0=0x%x, esr1=0x%x esr3=0x%x\n",
+				esr_status0, esr_status1, esr_status3);
+		}
+
+		/*
+		 * Freemark is hit. This is the normal interrupt.
+		 * In typical operation the read and write regs will be equal
+		 */
+		if (esrmask & esr_status3) {
+			struct snd_pcm_substream *playstr;
+
+			playstr = cygaud->portinfo[port].play_stream;
+			cygnus_pcm_period_elapsed(playstr);
+		}
+	}
+
+	/* Clear ESR interrupt */
+	writel(esr_status0, audio_io + ESR0_STATUS_CLR_OFFSET);
+	writel(esr_status1, audio_io + ESR1_STATUS_CLR_OFFSET);
+	writel(esr_status3, audio_io + ESR3_STATUS_CLR_OFFSET);
+	/* Rearm freemark logic by writing 1 to the correct bit */
+	writel(esr_status3, audio_io + BF_REARM_FREE_MARK_OFFSET);
+}
+
+/*
+ * ESR2/4 status  Description
+ *  0x1	I2S0_in port caused interrupt
+ *  0x2	I2S1_in port caused interrupt
+ *  0x4	I2S2_in port caused interrupt
+ */
+static void handle_capture_irq(struct cygnus_audio *cygaud)
+{
+	void __iomem *audio_io;
+	u32 port;
+	u32 esr_status2, esr_status4;
+
+	audio_io = cygaud->audio;
+
+	/*
+	 * ESR status gets updates with/without interrupts enabled.
+	 * So, check the ESR mask, which provides interrupt enable/
+	 * disable status and use it to determine which ESR status
+	 * should be serviced.
+	 */
+	esr_status2 = readl(audio_io + ESR2_STATUS_OFFSET);
+	esr_status2 &= ~readl(audio_io + ESR2_MASK_STATUS_OFFSET);
+	esr_status4 = readl(audio_io + ESR4_STATUS_OFFSET);
+	esr_status4 &= ~readl(audio_io + ESR4_MASK_STATUS_OFFSET);
+
+	for (port = 0; port < CYGNUS_MAX_CAPTURE_PORTS; port++) {
+		u32 esrmask = BIT(port);
+
+		/*
+		 * Ringbuffer or FIFO overflow
+		 * If we get this interrupt then, it is also true that we have
+		 * not yet responded to the fullmark interrupt.
+		 * Log a debug message.  The fullmark handler below will
+		 * handle getting everything going again.
+		 */
+		if (esrmask & esr_status2)
+			dev_dbg(cygaud->dev,
+				"Overflow: esr2=0x%x\n", esr_status2);
+
+		if (esrmask & esr_status4) {
+			struct snd_pcm_substream *capstr;
+
+			capstr = cygaud->portinfo[port].capture_stream;
+			cygnus_pcm_period_elapsed(capstr);
+		}
+	}
+
+	writel(esr_status2, audio_io + ESR2_STATUS_CLR_OFFSET);
+	writel(esr_status4, audio_io + ESR4_STATUS_CLR_OFFSET);
+	/* Rearm fullmark logic by writing 1 to the correct bit */
+	writel(esr_status4, audio_io + BF_REARM_FULL_MARK_OFFSET);
+}
+
+static irqreturn_t cygnus_dma_irq(int irq, void *data)
+{
+	u32 r5_status;
+	struct cygnus_audio *cygaud = data;
+
+	/*
+	 * R5 status bits	Description
+	 *  0		ESR0 (playback FIFO interrupt)
+	 *  1		ESR1 (playback rbuf interrupt)
+	 *  2		ESR2 (capture rbuf interrupt)
+	 *  3		ESR3 (Freemark play. interrupt)
+	 *  4		ESR4 (Fullmark capt. interrupt)
+	 */
+	r5_status = readl(cygaud->audio + INTH_R5F_STATUS_OFFSET);
+
+	if (!(r5_status & (ANY_PLAYBACK_IRQ | ANY_CAPTURE_IRQ)))
+		return IRQ_NONE;
+
+	/* If playback interrupt happened */
+	if (ANY_PLAYBACK_IRQ & r5_status) {
+		handle_playback_irq(cygaud);
+		writel(ANY_PLAYBACK_IRQ & r5_status,
+			cygaud->audio + INTH_R5F_CLEAR_OFFSET);
+	}
+
+	/* If  capture interrupt happened */
+	if (ANY_CAPTURE_IRQ & r5_status) {
+		handle_capture_irq(cygaud);
+		writel(ANY_CAPTURE_IRQ & r5_status,
+			cygaud->audio + INTH_R5F_CLEAR_OFFSET);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int cygnus_pcm_open(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct cygnus_aio_port *aio;
+	int ret;
+
+	aio = cygnus_dai_get_dma_data(substream);
+	if (!aio)
+		return -ENODEV;
+
+	dev_dbg(rtd->cpu_dai->dev, "%s port %d\n", __func__, aio->portnum);
+
+	snd_soc_set_runtime_hwparams(substream, &cygnus_pcm_hw);
+
+	ret = snd_pcm_hw_constraint_step(runtime, 0,
+		SNDRV_PCM_HW_PARAM_PERIOD_BYTES, PERIOD_BYTES_MIN);
+	if (ret < 0)
+		return ret;
+
+	ret = snd_pcm_hw_constraint_step(runtime, 0,
+		SNDRV_PCM_HW_PARAM_BUFFER_BYTES, PERIOD_BYTES_MIN);
+	if (ret < 0)
+		return ret;
+	/*
+	 * Keep track of which substream belongs to which port.
+	 * This info is needed by snd_pcm_period_elapsed() in irq_handler
+	 */
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		aio->play_stream = substream;
+	else
+		aio->capture_stream = substream;
+
+	return 0;
+}
+
+static int cygnus_pcm_close(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct cygnus_aio_port *aio;
+
+	aio = cygnus_dai_get_dma_data(substream);
+
+	dev_dbg(rtd->cpu_dai->dev, "%s  port %d\n", __func__, aio->portnum);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		aio->play_stream = NULL;
+	else
+		aio->capture_stream = NULL;
+
+	if (!aio->play_stream && !aio->capture_stream)
+		dev_dbg(rtd->cpu_dai->dev, "freed  port %d\n", aio->portnum);
+
+	return 0;
+}
+
+static int cygnus_pcm_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct cygnus_aio_port *aio;
+	int ret = 0;
+
+	aio = cygnus_dai_get_dma_data(substream);
+	dev_dbg(rtd->cpu_dai->dev, "%s  port %d\n", __func__, aio->portnum);
+
+	snd_pcm_set_runtime_buffer(substream, &substream->dma_buffer);
+	runtime->dma_bytes = params_buffer_bytes(params);
+
+	return ret;
+}
+
+static int cygnus_pcm_hw_free(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct cygnus_aio_port *aio;
+
+	aio = cygnus_dai_get_dma_data(substream);
+	dev_dbg(rtd->cpu_dai->dev, "%s  port %d\n", __func__, aio->portnum);
+
+	snd_pcm_set_runtime_buffer(substream, NULL);
+	return 0;
+}
+
+static int cygnus_pcm_prepare(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct cygnus_aio_port *aio;
+	unsigned long bufsize, periodsize;
+	int ret = 0;
+	bool is_play;
+	u32 start;
+	struct ringbuf_regs *p_rbuf = NULL;
+
+	aio = cygnus_dai_get_dma_data(substream);
+	dev_dbg(rtd->cpu_dai->dev, "%s port %d\n", __func__, aio->portnum);
+
+	bufsize = snd_pcm_lib_buffer_bytes(substream);
+	periodsize = snd_pcm_lib_period_bytes(substream);
+
+	dev_dbg(rtd->cpu_dai->dev, "%s (buf_size %lu) (period_size %lu)\n",
+			__func__, bufsize, periodsize);
+
+	configure_ringbuf_regs(substream);
+
+	p_rbuf = get_ringbuf(substream);
+
+	start = runtime->dma_addr;
+
+	is_play = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ? 1 : 0;
+
+	ringbuf_set_initial(aio->cygaud->audio, p_rbuf, is_play, start,
+				periodsize, bufsize);
+
+	return ret;
+}
+
+static snd_pcm_uframes_t cygnus_pcm_pointer(struct snd_pcm_substream *substream)
+{
+	struct cygnus_aio_port *aio;
+	unsigned int res = 0, cur = 0, base = 0;
+	struct ringbuf_regs *p_rbuf = NULL;
+
+	aio = cygnus_dai_get_dma_data(substream);
+
+	/*
+	 * Get the offset of the current read (for playack) or write
+	 * index (for capture).  Report this value back to the asoc framework.
+	 */
+	p_rbuf = get_ringbuf(substream);
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		cur = readl(aio->cygaud->audio + p_rbuf->rdaddr);
+	else
+		cur = readl(aio->cygaud->audio + p_rbuf->wraddr);
+
+	base = readl(aio->cygaud->audio + p_rbuf->baseaddr);
+
+	/*
+	 * Mask off the MSB of the rdaddr,wraddr and baseaddr
+	 * since MSB is not part of the address
+	 */
+	res = (cur & 0x7fffffff) - (base & 0x7fffffff);
+
+	return bytes_to_frames(substream->runtime, res);
+}
+
+static int cygnus_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
+{
+	struct snd_pcm_substream *substream = pcm->streams[stream].substream;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_dma_buffer *buf = &substream->dma_buffer;
+	size_t size;
+
+	size = cygnus_pcm_hw.buffer_bytes_max;
+
+	buf->dev.type = SNDRV_DMA_TYPE_DEV;
+	buf->dev.dev = pcm->card->dev;
+	buf->private_data = NULL;
+	buf->area = dma_alloc_coherent(pcm->card->dev, size,
+			&buf->addr, GFP_KERNEL);
+
+	dev_dbg(rtd->cpu_dai->dev, "%s: size 0x%zx @ %pK\n",
+				__func__, size, buf->area);
+
+	if (!buf->area) {
+		dev_err(rtd->cpu_dai->dev, "%s: dma_alloc failed\n", __func__);
+		return -ENOMEM;
+	}
+	buf->bytes = size;
+
+	return 0;
+}
+
+
+static const struct snd_pcm_ops cygnus_pcm_ops = {
+	.open		= cygnus_pcm_open,
+	.close		= cygnus_pcm_close,
+	.ioctl		= snd_pcm_lib_ioctl,
+	.hw_params	= cygnus_pcm_hw_params,
+	.hw_free	= cygnus_pcm_hw_free,
+	.prepare	= cygnus_pcm_prepare,
+	.trigger	= cygnus_pcm_trigger,
+	.pointer	= cygnus_pcm_pointer,
+};
+
+static void cygnus_dma_free_dma_buffers(struct snd_pcm *pcm)
+{
+	struct snd_pcm_substream *substream;
+	struct snd_dma_buffer *buf;
+
+	substream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream;
+	if (substream) {
+		buf = &substream->dma_buffer;
+		if (buf->area) {
+			dma_free_coherent(pcm->card->dev, buf->bytes,
+				buf->area, buf->addr);
+			buf->area = NULL;
+		}
+	}
+
+	substream = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream;
+	if (substream) {
+		buf = &substream->dma_buffer;
+		if (buf->area) {
+			dma_free_coherent(pcm->card->dev, buf->bytes,
+				buf->area, buf->addr);
+			buf->area = NULL;
+		}
+	}
+}
+
+static int cygnus_dma_new(struct snd_soc_pcm_runtime *rtd)
+{
+	struct snd_card *card = rtd->card->snd_card;
+	struct snd_pcm *pcm = rtd->pcm;
+	int ret;
+
+	if (!card->dev->dma_mask)
+		card->dev->dma_mask = &cygnus_dma_dmamask;
+	if (!card->dev->coherent_dma_mask)
+		card->dev->coherent_dma_mask = DMA_BIT_MASK(32);
+
+	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) {
+		ret = cygnus_pcm_preallocate_dma_buffer(pcm,
+				SNDRV_PCM_STREAM_PLAYBACK);
+		if (ret)
+			return ret;
+	}
+
+	if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
+		ret = cygnus_pcm_preallocate_dma_buffer(pcm,
+				SNDRV_PCM_STREAM_CAPTURE);
+		if (ret) {
+			cygnus_dma_free_dma_buffers(pcm);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static struct snd_soc_platform_driver cygnus_soc_platform = {
+	.ops		= &cygnus_pcm_ops,
+	.pcm_new	= cygnus_dma_new,
+	.pcm_free	= cygnus_dma_free_dma_buffers,
+};
+
+int cygnus_soc_platform_register(struct device *dev,
+				 struct cygnus_audio *cygaud)
+{
+	int rc = 0;
+
+	dev_dbg(dev, "%s Enter\n", __func__);
+
+	rc = devm_request_irq(dev, cygaud->irq_num, cygnus_dma_irq,
+				IRQF_SHARED, "cygnus-audio", cygaud);
+	if (rc) {
+		dev_err(dev, "%s request_irq error %d\n", __func__, rc);
+		return rc;
+	}
+
+	rc = snd_soc_register_platform(dev, &cygnus_soc_platform);
+	if (rc) {
+		dev_err(dev, "%s failed\n", __func__);
+		return rc;
+	}
+
+	return 0;
+}
+
+int cygnus_soc_platform_unregister(struct device *dev)
+{
+	snd_soc_unregister_platform(dev);
+
+	return 0;
+}
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Broadcom");
+MODULE_DESCRIPTION("Cygnus ASoC PCM module");
diff --git a/sound/soc/bcm/cygnus-ssp.c b/sound/soc/bcm/cygnus-ssp.c
new file mode 100644
index 000000000000..e710bb0c5637
--- /dev/null
+++ b/sound/soc/bcm/cygnus-ssp.c
@@ -0,0 +1,1529 @@
+/*
+ * Copyright (C) 2014-2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "cygnus-ssp.h"
+
+#define DEFAULT_VCO    1354750204
+
+#define CYGNUS_TDM_RATE \
+		(SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 | \
+		SNDRV_PCM_RATE_11025 | SNDRV_PCM_RATE_22050 | \
+		SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_44100 | \
+		SNDRV_PCM_RATE_48000)
+
+#define CAPTURE_FCI_ID_BASE 0x180
+#define CYGNUS_SSP_TRISTATE_MASK 0x001fff
+#define CYGNUS_PLLCLKSEL_MASK 0xf
+
+/* Used with stream_on field to indicate which streams are active */
+#define  PLAYBACK_STREAM_MASK   BIT(0)
+#define  CAPTURE_STREAM_MASK    BIT(1)
+
+#define I2S_STREAM_CFG_MASK      0xff003ff
+#define I2S_CAP_STREAM_CFG_MASK  0xf0
+#define SPDIF_STREAM_CFG_MASK    0x3ff
+#define CH_GRP_STEREO            0x1
+
+/* Begin register offset defines */
+#define AUD_MISC_SEROUT_OE_REG_BASE  0x01c
+#define AUD_MISC_SEROUT_SPDIF_OE  12
+#define AUD_MISC_SEROUT_MCLK_OE   3
+#define AUD_MISC_SEROUT_LRCK_OE   2
+#define AUD_MISC_SEROUT_SCLK_OE   1
+#define AUD_MISC_SEROUT_SDAT_OE   0
+
+/* AUD_FMM_BF_CTRL_xxx regs */
+#define BF_DST_CFG0_OFFSET  0x100
+#define BF_DST_CFG1_OFFSET  0x104
+#define BF_DST_CFG2_OFFSET  0x108
+
+#define BF_DST_CTRL0_OFFSET 0x130
+#define BF_DST_CTRL1_OFFSET 0x134
+#define BF_DST_CTRL2_OFFSET 0x138
+
+#define BF_SRC_CFG0_OFFSET  0x148
+#define BF_SRC_CFG1_OFFSET  0x14c
+#define BF_SRC_CFG2_OFFSET  0x150
+#define BF_SRC_CFG3_OFFSET  0x154
+
+#define BF_SRC_CTRL0_OFFSET 0x1c0
+#define BF_SRC_CTRL1_OFFSET 0x1c4
+#define BF_SRC_CTRL2_OFFSET 0x1c8
+#define BF_SRC_CTRL3_OFFSET 0x1cc
+
+#define BF_SRC_GRP0_OFFSET  0x1fc
+#define BF_SRC_GRP1_OFFSET  0x200
+#define BF_SRC_GRP2_OFFSET  0x204
+#define BF_SRC_GRP3_OFFSET  0x208
+
+#define BF_SRC_GRP_EN_OFFSET        0x320
+#define BF_SRC_GRP_FLOWON_OFFSET    0x324
+#define BF_SRC_GRP_SYNC_DIS_OFFSET  0x328
+
+/* AUD_FMM_IOP_OUT_I2S_xxx regs */
+#define OUT_I2S_0_STREAM_CFG_OFFSET 0xa00
+#define OUT_I2S_0_CFG_OFFSET        0xa04
+#define OUT_I2S_0_MCLK_CFG_OFFSET   0xa0c
+
+#define OUT_I2S_1_STREAM_CFG_OFFSET 0xa40
+#define OUT_I2S_1_CFG_OFFSET        0xa44
+#define OUT_I2S_1_MCLK_CFG_OFFSET   0xa4c
+
+#define OUT_I2S_2_STREAM_CFG_OFFSET 0xa80
+#define OUT_I2S_2_CFG_OFFSET        0xa84
+#define OUT_I2S_2_MCLK_CFG_OFFSET   0xa8c
+
+/* AUD_FMM_IOP_OUT_SPDIF_xxx regs */
+#define SPDIF_STREAM_CFG_OFFSET  0xac0
+#define SPDIF_CTRL_OFFSET        0xac4
+#define SPDIF_FORMAT_CFG_OFFSET  0xad8
+#define SPDIF_MCLK_CFG_OFFSET    0xadc
+
+/* AUD_FMM_IOP_PLL_0_xxx regs */
+#define IOP_PLL_0_MACRO_OFFSET    0xb00
+#define IOP_PLL_0_MDIV_Ch0_OFFSET 0xb14
+#define IOP_PLL_0_MDIV_Ch1_OFFSET 0xb18
+#define IOP_PLL_0_MDIV_Ch2_OFFSET 0xb1c
+
+#define IOP_PLL_0_ACTIVE_MDIV_Ch0_OFFSET 0xb30
+#define IOP_PLL_0_ACTIVE_MDIV_Ch1_OFFSET 0xb34
+#define IOP_PLL_0_ACTIVE_MDIV_Ch2_OFFSET 0xb38
+
+/* AUD_FMM_IOP_xxx regs */
+#define IOP_PLL_0_CONTROL_OFFSET     0xb04
+#define IOP_PLL_0_USER_NDIV_OFFSET   0xb08
+#define IOP_PLL_0_ACTIVE_NDIV_OFFSET 0xb20
+#define IOP_PLL_0_RESET_OFFSET       0xb5c
+
+/* AUD_FMM_IOP_IN_I2S_xxx regs */
+#define IN_I2S_0_STREAM_CFG_OFFSET 0x00
+#define IN_I2S_0_CFG_OFFSET        0x04
+#define IN_I2S_1_STREAM_CFG_OFFSET 0x40
+#define IN_I2S_1_CFG_OFFSET        0x44
+#define IN_I2S_2_STREAM_CFG_OFFSET 0x80
+#define IN_I2S_2_CFG_OFFSET        0x84
+
+/* AUD_FMM_IOP_MISC_xxx regs */
+#define IOP_SW_INIT_LOGIC          0x1c0
+
+/* End register offset defines */
+
+
+/* AUD_FMM_IOP_OUT_I2S_x_MCLK_CFG_0_REG */
+#define I2S_OUT_MCLKRATE_SHIFT 16
+
+/* AUD_FMM_IOP_OUT_I2S_x_MCLK_CFG_REG */
+#define I2S_OUT_PLLCLKSEL_SHIFT  0
+
+/* AUD_FMM_IOP_OUT_I2S_x_STREAM_CFG */
+#define I2S_OUT_STREAM_ENA  31
+#define I2S_OUT_STREAM_CFG_GROUP_ID  20
+#define I2S_OUT_STREAM_CFG_CHANNEL_GROUPING  24
+
+/* AUD_FMM_IOP_IN_I2S_x_CAP */
+#define I2S_IN_STREAM_CFG_CAP_ENA   31
+#define I2S_IN_STREAM_CFG_0_GROUP_ID 4
+
+/* AUD_FMM_IOP_OUT_I2S_x_I2S_CFG_REG */
+#define I2S_OUT_CFGX_CLK_ENA         0
+#define I2S_OUT_CFGX_DATA_ENABLE     1
+#define I2S_OUT_CFGX_DATA_ALIGNMENT  6
+#define I2S_OUT_CFGX_BITS_PER_SLOT  13
+#define I2S_OUT_CFGX_VALID_SLOT     14
+#define I2S_OUT_CFGX_FSYNC_WIDTH    18
+#define I2S_OUT_CFGX_SCLKS_PER_1FS_DIV32 26
+#define I2S_OUT_CFGX_SLAVE_MODE     30
+#define I2S_OUT_CFGX_TDM_MODE       31
+
+/* AUD_FMM_BF_CTRL_SOURCECH_CFGx_REG */
+#define BF_SRC_CFGX_SFIFO_ENA              0
+#define BF_SRC_CFGX_BUFFER_PAIR_ENABLE     1
+#define BF_SRC_CFGX_SAMPLE_CH_MODE         2
+#define BF_SRC_CFGX_SFIFO_SZ_DOUBLE        5
+#define BF_SRC_CFGX_NOT_PAUSE_WHEN_EMPTY  10
+#define BF_SRC_CFGX_BIT_RES               20
+#define BF_SRC_CFGX_PROCESS_SEQ_ID_VALID  31
+
+/* AUD_FMM_BF_CTRL_DESTCH_CFGx_REG */
+#define BF_DST_CFGX_CAP_ENA              0
+#define BF_DST_CFGX_BUFFER_PAIR_ENABLE   1
+#define BF_DST_CFGX_DFIFO_SZ_DOUBLE      2
+#define BF_DST_CFGX_NOT_PAUSE_WHEN_FULL 11
+#define BF_DST_CFGX_FCI_ID              12
+#define BF_DST_CFGX_CAP_MODE            24
+#define BF_DST_CFGX_PROC_SEQ_ID_VALID   31
+
+/* AUD_FMM_IOP_OUT_SPDIF_xxx */
+#define SPDIF_0_OUT_DITHER_ENA     3
+#define SPDIF_0_OUT_STREAM_ENA    31
+
+/* AUD_FMM_IOP_PLL_0_USER */
+#define IOP_PLL_0_USER_NDIV_FRAC   10
+
+/* AUD_FMM_IOP_PLL_0_ACTIVE */
+#define IOP_PLL_0_ACTIVE_NDIV_FRAC 10
+
+
+#define INIT_SSP_REGS(num) (struct cygnus_ssp_regs){ \
+		.i2s_stream_cfg = OUT_I2S_ ##num## _STREAM_CFG_OFFSET, \
+		.i2s_cap_stream_cfg = IN_I2S_ ##num## _STREAM_CFG_OFFSET, \
+		.i2s_cfg = OUT_I2S_ ##num## _CFG_OFFSET, \
+		.i2s_cap_cfg = IN_I2S_ ##num## _CFG_OFFSET, \
+		.i2s_mclk_cfg = OUT_I2S_ ##num## _MCLK_CFG_OFFSET, \
+		.bf_destch_ctrl = BF_DST_CTRL ##num## _OFFSET, \
+		.bf_destch_cfg = BF_DST_CFG ##num## _OFFSET, \
+		.bf_sourcech_ctrl = BF_SRC_CTRL ##num## _OFFSET, \
+		.bf_sourcech_cfg = BF_SRC_CFG ##num## _OFFSET, \
+		.bf_sourcech_grp = BF_SRC_GRP ##num## _OFFSET \
+}
+
+struct pll_macro_entry {
+	u32 mclk;
+	u32 pll_ch_num;
+};
+
+/*
+ * PLL has 3 output channels (1x, 2x, and 4x). Below are
+ * the common MCLK frequencies used by audio driver
+ */
+static const struct pll_macro_entry pll_predef_mclk[] = {
+	{ 4096000, 0},
+	{ 8192000, 1},
+	{16384000, 2},
+
+	{ 5644800, 0},
+	{11289600, 1},
+	{22579200, 2},
+
+	{ 6144000, 0},
+	{12288000, 1},
+	{24576000, 2},
+
+	{12288000, 0},
+	{24576000, 1},
+	{49152000, 2},
+
+	{22579200, 0},
+	{45158400, 1},
+	{90316800, 2},
+
+	{24576000, 0},
+	{49152000, 1},
+	{98304000, 2},
+};
+
+/* List of valid frame sizes for tdm mode */
+static const int ssp_valid_tdm_framesize[] = {32, 64, 128, 256, 512};
+
+/*
+ * Use this relationship to derive the sampling rate (lrclk)
+ * lrclk = (mclk) / ((2*mclk_to_sclk_ratio) * (32 * SCLK))).
+ *
+ * Use mclk and pll_ch from the table above
+ *
+ * Valid SCLK = 0/1/2/4/8/12
+ *
+ * mclk_to_sclk_ratio = number of MCLK per SCLK. Division is twice the
+ * value programmed in this field.
+ * Valid mclk_to_sclk_ratio = 1 through to 15
+ *
+ * eg: To set lrclk = 48khz, set mclk = 12288000, mclk_to_sclk_ratio = 2,
+ * SCLK = 64
+ */
+struct _ssp_clk_coeff {
+	u32 mclk;
+	u32 sclk_rate;
+	u32 rate;
+	u32 mclk_rate;
+};
+
+static const struct _ssp_clk_coeff ssp_clk_coeff[] = {
+	{ 4096000,  32,  16000, 4},
+	{ 4096000,  32,  32000, 2},
+	{ 4096000,  64,   8000, 4},
+	{ 4096000,  64,  16000, 2},
+	{ 4096000,  64,  32000, 1},
+	{ 4096000, 128,   8000, 2},
+	{ 4096000, 128,  16000, 1},
+	{ 4096000, 256,   8000, 1},
+
+	{ 6144000,  32,  16000, 6},
+	{ 6144000,  32,  32000, 3},
+	{ 6144000,  32,  48000, 2},
+	{ 6144000,  32,  96000, 1},
+	{ 6144000,  64,   8000, 6},
+	{ 6144000,  64,  16000, 3},
+	{ 6144000,  64,  48000, 1},
+	{ 6144000, 128,   8000, 3},
+
+	{ 8192000,  32,  32000, 4},
+	{ 8192000,  64,  16000, 4},
+	{ 8192000,  64,  32000, 2},
+	{ 8192000, 128,   8000, 4},
+	{ 8192000, 128,  16000, 2},
+	{ 8192000, 128,  32000, 1},
+	{ 8192000, 256,   8000, 2},
+	{ 8192000, 256,  16000, 1},
+	{ 8192000, 512,   8000, 1},
+
+	{12288000,  32,  32000, 6},
+	{12288000,  32,  48000, 4},
+	{12288000,  32,  96000, 2},
+	{12288000,  32, 192000, 1},
+	{12288000,  64,  16000, 6},
+	{12288000,  64,  32000, 3},
+	{12288000,  64,  48000, 2},
+	{12288000,  64,  96000, 1},
+	{12288000, 128,   8000, 6},
+	{12288000, 128,  16000, 3},
+	{12288000, 128,  48000, 1},
+	{12288000, 256,   8000, 3},
+
+	{16384000,  64,  32000, 4},
+	{16384000, 128,  16000, 4},
+	{16384000, 128,  32000, 2},
+	{16384000, 256,   8000, 4},
+	{16384000, 256,  16000, 2},
+	{16384000, 256,  32000, 1},
+	{16384000, 512,   8000, 2},
+	{16384000, 512,  16000, 1},
+
+	{24576000,  32,  96000, 4},
+	{24576000,  32, 192000, 2},
+	{24576000,  64,  32000, 6},
+	{24576000,  64,  48000, 4},
+	{24576000,  64,  96000, 2},
+	{24576000,  64, 192000, 1},
+	{24576000, 128,  16000, 6},
+	{24576000, 128,  32000, 3},
+	{24576000, 128,  48000, 2},
+	{24576000, 256,   8000, 6},
+	{24576000, 256,  16000, 3},
+	{24576000, 256,  48000, 1},
+	{24576000, 512,   8000, 3},
+
+	{49152000,  32, 192000, 4},
+	{49152000,  64,  96000, 4},
+	{49152000,  64, 192000, 2},
+	{49152000, 128,  32000, 6},
+	{49152000, 128,  48000, 4},
+	{49152000, 128,  96000, 2},
+	{49152000, 128, 192000, 1},
+	{49152000, 256,  16000, 6},
+	{49152000, 256,  32000, 3},
+	{49152000, 256,  48000, 2},
+	{49152000, 256,  96000, 1},
+	{49152000, 512,   8000, 6},
+	{49152000, 512,  16000, 3},
+	{49152000, 512,  48000, 1},
+
+	{ 5644800,  32,  22050, 4},
+	{ 5644800,  32,  44100, 2},
+	{ 5644800,  32,  88200, 1},
+	{ 5644800,  64,  11025, 4},
+	{ 5644800,  64,  22050, 2},
+	{ 5644800,  64,  44100, 1},
+
+	{11289600,  32,  44100, 4},
+	{11289600,  32,  88200, 2},
+	{11289600,  32, 176400, 1},
+	{11289600,  64,  22050, 4},
+	{11289600,  64,  44100, 2},
+	{11289600,  64,  88200, 1},
+	{11289600, 128,  11025, 4},
+	{11289600, 128,  22050, 2},
+	{11289600, 128,  44100, 1},
+
+	{22579200,  32,  88200, 4},
+	{22579200,  32, 176400, 2},
+	{22579200,  64,  44100, 4},
+	{22579200,  64,  88200, 2},
+	{22579200,  64, 176400, 1},
+	{22579200, 128,  22050, 4},
+	{22579200, 128,  44100, 2},
+	{22579200, 128,  88200, 1},
+	{22579200, 256,  11025, 4},
+	{22579200, 256,  22050, 2},
+	{22579200, 256,  44100, 1},
+
+	{45158400,  32, 176400, 4},
+	{45158400,  64,  88200, 4},
+	{45158400,  64, 176400, 2},
+	{45158400, 128,  44100, 4},
+	{45158400, 128,  88200, 2},
+	{45158400, 128, 176400, 1},
+	{45158400, 256,  22050, 4},
+	{45158400, 256,  44100, 2},
+	{45158400, 256,  88200, 1},
+	{45158400, 512,  11025, 4},
+	{45158400, 512,  22050, 2},
+	{45158400, 512,  44100, 1},
+};
+
+static struct cygnus_aio_port *cygnus_dai_get_portinfo(struct snd_soc_dai *dai)
+{
+	struct cygnus_audio *cygaud = snd_soc_dai_get_drvdata(dai);
+
+	return &cygaud->portinfo[dai->id];
+}
+
+static int audio_ssp_init_portregs(struct cygnus_aio_port *aio)
+{
+	u32 value, fci_id;
+	int status = 0;
+
+	switch (aio->port_type) {
+	case PORT_TDM:
+		value = readl(aio->cygaud->audio + aio->regs.i2s_stream_cfg);
+		value &= ~I2S_STREAM_CFG_MASK;
+
+		/* Set Group ID */
+		writel(aio->portnum,
+			aio->cygaud->audio + aio->regs.bf_sourcech_grp);
+
+		/* Configure the AUD_FMM_IOP_OUT_I2S_x_STREAM_CFG reg */
+		value |= aio->portnum << I2S_OUT_STREAM_CFG_GROUP_ID;
+		value |= aio->portnum; /* FCI ID is the port num */
+		value |= CH_GRP_STEREO << I2S_OUT_STREAM_CFG_CHANNEL_GROUPING;
+		writel(value, aio->cygaud->audio + aio->regs.i2s_stream_cfg);
+
+		/* Configure the AUD_FMM_BF_CTRL_SOURCECH_CFGX reg */
+		value = readl(aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+		value &= ~BIT(BF_SRC_CFGX_NOT_PAUSE_WHEN_EMPTY);
+		value |= BIT(BF_SRC_CFGX_SFIFO_SZ_DOUBLE);
+		value |= BIT(BF_SRC_CFGX_PROCESS_SEQ_ID_VALID);
+		writel(value, aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+
+		/* Configure the AUD_FMM_IOP_IN_I2S_x_CAP_STREAM_CFG_0 reg */
+		value = readl(aio->cygaud->i2s_in +
+			aio->regs.i2s_cap_stream_cfg);
+		value &= ~I2S_CAP_STREAM_CFG_MASK;
+		value |= aio->portnum << I2S_IN_STREAM_CFG_0_GROUP_ID;
+		writel(value, aio->cygaud->i2s_in +
+			aio->regs.i2s_cap_stream_cfg);
+
+		/* Configure the AUD_FMM_BF_CTRL_DESTCH_CFGX_REG_BASE reg */
+		fci_id = CAPTURE_FCI_ID_BASE + aio->portnum;
+
+		value = readl(aio->cygaud->audio + aio->regs.bf_destch_cfg);
+		value |= BIT(BF_DST_CFGX_DFIFO_SZ_DOUBLE);
+		value &= ~BIT(BF_DST_CFGX_NOT_PAUSE_WHEN_FULL);
+		value |= (fci_id << BF_DST_CFGX_FCI_ID);
+		value |= BIT(BF_DST_CFGX_PROC_SEQ_ID_VALID);
+		writel(value, aio->cygaud->audio + aio->regs.bf_destch_cfg);
+
+		/* Enable the transmit pin for this port */
+		value = readl(aio->cygaud->audio + AUD_MISC_SEROUT_OE_REG_BASE);
+		value &= ~BIT((aio->portnum * 4) + AUD_MISC_SEROUT_SDAT_OE);
+		writel(value, aio->cygaud->audio + AUD_MISC_SEROUT_OE_REG_BASE);
+		break;
+	case PORT_SPDIF:
+		writel(aio->portnum, aio->cygaud->audio + BF_SRC_GRP3_OFFSET);
+
+		value = readl(aio->cygaud->audio + SPDIF_CTRL_OFFSET);
+		value |= BIT(SPDIF_0_OUT_DITHER_ENA);
+		writel(value, aio->cygaud->audio + SPDIF_CTRL_OFFSET);
+
+		/* Enable and set the FCI ID for the SPDIF channel */
+		value = readl(aio->cygaud->audio + SPDIF_STREAM_CFG_OFFSET);
+		value &= ~SPDIF_STREAM_CFG_MASK;
+		value |= aio->portnum; /* FCI ID is the port num */
+		value |= BIT(SPDIF_0_OUT_STREAM_ENA);
+		writel(value, aio->cygaud->audio + SPDIF_STREAM_CFG_OFFSET);
+
+		value = readl(aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+		value &= ~BIT(BF_SRC_CFGX_NOT_PAUSE_WHEN_EMPTY);
+		value |= BIT(BF_SRC_CFGX_SFIFO_SZ_DOUBLE);
+		value |= BIT(BF_SRC_CFGX_PROCESS_SEQ_ID_VALID);
+		writel(value, aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+
+		/* Enable the spdif output pin */
+		value = readl(aio->cygaud->audio + AUD_MISC_SEROUT_OE_REG_BASE);
+		value &= ~BIT(AUD_MISC_SEROUT_SPDIF_OE);
+		writel(value, aio->cygaud->audio + AUD_MISC_SEROUT_OE_REG_BASE);
+		break;
+	default:
+		dev_err(aio->cygaud->dev, "Port not supported\n");
+		status = -EINVAL;
+	}
+
+	return status;
+}
+
+static void audio_ssp_in_enable(struct cygnus_aio_port *aio)
+{
+	u32 value;
+
+	value = readl(aio->cygaud->audio + aio->regs.bf_destch_cfg);
+	value |= BIT(BF_DST_CFGX_CAP_ENA);
+	writel(value, aio->cygaud->audio + aio->regs.bf_destch_cfg);
+
+	writel(0x1, aio->cygaud->audio + aio->regs.bf_destch_ctrl);
+
+	value = readl(aio->cygaud->audio + aio->regs.i2s_cfg);
+	value |= BIT(I2S_OUT_CFGX_CLK_ENA);
+	value |= BIT(I2S_OUT_CFGX_DATA_ENABLE);
+	writel(value, aio->cygaud->audio + aio->regs.i2s_cfg);
+
+	value = readl(aio->cygaud->i2s_in + aio->regs.i2s_cap_stream_cfg);
+	value |= BIT(I2S_IN_STREAM_CFG_CAP_ENA);
+	writel(value, aio->cygaud->i2s_in + aio->regs.i2s_cap_stream_cfg);
+
+	aio->streams_on |= CAPTURE_STREAM_MASK;
+}
+
+static void audio_ssp_in_disable(struct cygnus_aio_port *aio)
+{
+	u32 value;
+
+	value = readl(aio->cygaud->i2s_in + aio->regs.i2s_cap_stream_cfg);
+	value &= ~BIT(I2S_IN_STREAM_CFG_CAP_ENA);
+	writel(value, aio->cygaud->i2s_in + aio->regs.i2s_cap_stream_cfg);
+
+	aio->streams_on &= ~CAPTURE_STREAM_MASK;
+
+	/* If both playback and capture are off */
+	if (!aio->streams_on) {
+		value = readl(aio->cygaud->audio + aio->regs.i2s_cfg);
+		value &= ~BIT(I2S_OUT_CFGX_CLK_ENA);
+		value &= ~BIT(I2S_OUT_CFGX_DATA_ENABLE);
+		writel(value, aio->cygaud->audio + aio->regs.i2s_cfg);
+	}
+
+	writel(0x0, aio->cygaud->audio + aio->regs.bf_destch_ctrl);
+
+	value = readl(aio->cygaud->audio + aio->regs.bf_destch_cfg);
+	value &= ~BIT(BF_DST_CFGX_CAP_ENA);
+	writel(value, aio->cygaud->audio + aio->regs.bf_destch_cfg);
+}
+
+static int audio_ssp_out_enable(struct cygnus_aio_port *aio)
+{
+	u32 value;
+	int status = 0;
+
+	switch (aio->port_type) {
+	case PORT_TDM:
+		value = readl(aio->cygaud->audio + aio->regs.i2s_stream_cfg);
+		value |= BIT(I2S_OUT_STREAM_ENA);
+		writel(value, aio->cygaud->audio + aio->regs.i2s_stream_cfg);
+
+		writel(1, aio->cygaud->audio + aio->regs.bf_sourcech_ctrl);
+
+		value = readl(aio->cygaud->audio + aio->regs.i2s_cfg);
+		value |= BIT(I2S_OUT_CFGX_CLK_ENA);
+		value |= BIT(I2S_OUT_CFGX_DATA_ENABLE);
+		writel(value, aio->cygaud->audio + aio->regs.i2s_cfg);
+
+		value = readl(aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+		value |= BIT(BF_SRC_CFGX_SFIFO_ENA);
+		writel(value, aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+
+		aio->streams_on |= PLAYBACK_STREAM_MASK;
+		break;
+	case PORT_SPDIF:
+		value = readl(aio->cygaud->audio + SPDIF_FORMAT_CFG_OFFSET);
+		value |= 0x3;
+		writel(value, aio->cygaud->audio + SPDIF_FORMAT_CFG_OFFSET);
+
+		writel(1, aio->cygaud->audio + aio->regs.bf_sourcech_ctrl);
+
+		value = readl(aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+		value |= BIT(BF_SRC_CFGX_SFIFO_ENA);
+		writel(value, aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+		break;
+	default:
+		dev_err(aio->cygaud->dev,
+			"Port not supported %d\n", aio->portnum);
+		status = -EINVAL;
+	}
+
+	return status;
+}
+
+static int audio_ssp_out_disable(struct cygnus_aio_port *aio)
+{
+	u32 value;
+	int status = 0;
+
+	switch (aio->port_type) {
+	case PORT_TDM:
+		aio->streams_on &= ~PLAYBACK_STREAM_MASK;
+
+		/* If both playback and capture are off */
+		if (!aio->streams_on) {
+			value = readl(aio->cygaud->audio + aio->regs.i2s_cfg);
+			value &= ~BIT(I2S_OUT_CFGX_CLK_ENA);
+			value &= ~BIT(I2S_OUT_CFGX_DATA_ENABLE);
+			writel(value, aio->cygaud->audio + aio->regs.i2s_cfg);
+		}
+
+		/* set group_sync_dis = 1 */
+		value = readl(aio->cygaud->audio + BF_SRC_GRP_SYNC_DIS_OFFSET);
+		value |= BIT(aio->portnum);
+		writel(value, aio->cygaud->audio + BF_SRC_GRP_SYNC_DIS_OFFSET);
+
+		writel(0, aio->cygaud->audio + aio->regs.bf_sourcech_ctrl);
+
+		value = readl(aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+		value &= ~BIT(BF_SRC_CFGX_SFIFO_ENA);
+		writel(value, aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+
+		/* set group_sync_dis = 0 */
+		value = readl(aio->cygaud->audio + BF_SRC_GRP_SYNC_DIS_OFFSET);
+		value &= ~BIT(aio->portnum);
+		writel(value, aio->cygaud->audio + BF_SRC_GRP_SYNC_DIS_OFFSET);
+
+		value = readl(aio->cygaud->audio + aio->regs.i2s_stream_cfg);
+		value &= ~BIT(I2S_OUT_STREAM_ENA);
+		writel(value, aio->cygaud->audio + aio->regs.i2s_stream_cfg);
+
+		/* IOP SW INIT on OUT_I2S_x */
+		value = readl(aio->cygaud->i2s_in + IOP_SW_INIT_LOGIC);
+		value |= BIT(aio->portnum);
+		writel(value, aio->cygaud->i2s_in + IOP_SW_INIT_LOGIC);
+		value &= ~BIT(aio->portnum);
+		writel(value, aio->cygaud->i2s_in + IOP_SW_INIT_LOGIC);
+		break;
+	case PORT_SPDIF:
+		value = readl(aio->cygaud->audio + SPDIF_FORMAT_CFG_OFFSET);
+		value &= ~0x3;
+		writel(value, aio->cygaud->audio + SPDIF_FORMAT_CFG_OFFSET);
+		writel(0, aio->cygaud->audio + aio->regs.bf_sourcech_ctrl);
+
+		value = readl(aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+		value &= ~BIT(BF_SRC_CFGX_SFIFO_ENA);
+		writel(value, aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+		break;
+	default:
+		dev_err(aio->cygaud->dev,
+			"Port not supported %d\n", aio->portnum);
+		status = -EINVAL;
+	}
+
+	return status;
+}
+
+static int pll_configure_mclk(struct cygnus_audio *cygaud, u32 mclk,
+	struct cygnus_aio_port *aio)
+{
+	int i = 0, error;
+	bool found = false;
+	const struct pll_macro_entry *p_entry;
+	struct clk *ch_clk;
+
+	for (i = 0; i < ARRAY_SIZE(pll_predef_mclk); i++) {
+		p_entry = &pll_predef_mclk[i];
+		if (p_entry->mclk == mclk) {
+			found = true;
+			break;
+		}
+	}
+	if (!found) {
+		dev_err(cygaud->dev,
+			"%s No valid mclk freq (%u) found!\n", __func__, mclk);
+		return -EINVAL;
+	}
+
+	ch_clk = cygaud->audio_clk[p_entry->pll_ch_num];
+
+	if ((aio->clk_trace.cap_en) && (!aio->clk_trace.cap_clk_en)) {
+		error = clk_prepare_enable(ch_clk);
+		if (error) {
+			dev_err(cygaud->dev, "%s clk_prepare_enable failed %d\n",
+				__func__, error);
+			return error;
+		}
+		aio->clk_trace.cap_clk_en = true;
+	}
+
+	if ((aio->clk_trace.play_en) && (!aio->clk_trace.play_clk_en)) {
+		error = clk_prepare_enable(ch_clk);
+		if (error) {
+			dev_err(cygaud->dev, "%s clk_prepare_enable failed %d\n",
+				__func__, error);
+			return error;
+		}
+		aio->clk_trace.play_clk_en = true;
+	}
+
+	error = clk_set_rate(ch_clk, mclk);
+	if (error) {
+		dev_err(cygaud->dev, "%s Set MCLK rate failed: %d\n",
+			__func__, error);
+		return error;
+	}
+
+	return p_entry->pll_ch_num;
+}
+
+static int cygnus_ssp_set_clocks(struct cygnus_aio_port *aio,
+			struct cygnus_audio *cygaud)
+{
+	u32 value, i = 0;
+	u32 mask = 0xf;
+	u32 sclk;
+	bool found = false;
+	const struct _ssp_clk_coeff *p_entry = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(ssp_clk_coeff); i++) {
+		p_entry = &ssp_clk_coeff[i];
+		if ((p_entry->rate == aio->lrclk) &&
+		    (p_entry->sclk_rate == aio->bit_per_frame) &&
+		    (p_entry->mclk == aio->mclk)) {
+			found = true;
+			break;
+		}
+	}
+	if (!found) {
+		dev_err(aio->cygaud->dev,
+			"No valid match found in ssp_clk_coeff array\n");
+		dev_err(aio->cygaud->dev, "lrclk = %u, bits/frame = %u, mclk = %u\n",
+			aio->lrclk, aio->bit_per_frame, aio->mclk);
+		return -EINVAL;
+	}
+
+	sclk = aio->bit_per_frame;
+	if (sclk == 512)
+		sclk = 0;
+	/* sclks_per_1fs_div = sclk cycles/32 */
+	sclk /= 32;
+	/* Set sclk rate */
+	switch (aio->port_type) {
+	case PORT_TDM:
+		/* Set number of bitclks per frame */
+		value = readl(aio->cygaud->audio + aio->regs.i2s_cfg);
+		value &= ~(mask << I2S_OUT_CFGX_SCLKS_PER_1FS_DIV32);
+		value |= sclk << I2S_OUT_CFGX_SCLKS_PER_1FS_DIV32;
+		writel(value, aio->cygaud->audio + aio->regs.i2s_cfg);
+		dev_dbg(aio->cygaud->dev,
+			"SCLKS_PER_1FS_DIV32 = 0x%x\n", value);
+		break;
+	case PORT_SPDIF:
+		break;
+	default:
+		dev_err(aio->cygaud->dev, "Unknown port type\n");
+		return -EINVAL;
+	}
+
+	/* Set MCLK_RATE ssp port (spdif and ssp are the same) */
+	value = readl(aio->cygaud->audio + aio->regs.i2s_mclk_cfg);
+	value &= ~(0xf << I2S_OUT_MCLKRATE_SHIFT);
+	value |= (p_entry->mclk_rate << I2S_OUT_MCLKRATE_SHIFT);
+	writel(value, aio->cygaud->audio + aio->regs.i2s_mclk_cfg);
+
+	dev_dbg(aio->cygaud->dev, "mclk cfg reg = 0x%x\n", value);
+	dev_dbg(aio->cygaud->dev, "bits per frame = %u, mclk = %u Hz, lrclk = %u Hz\n",
+			aio->bit_per_frame, aio->mclk, aio->lrclk);
+	return 0;
+}
+
+static int cygnus_ssp_hw_params(struct snd_pcm_substream *substream,
+				 struct snd_pcm_hw_params *params,
+				 struct snd_soc_dai *dai)
+{
+	struct cygnus_aio_port *aio = cygnus_dai_get_portinfo(dai);
+	struct cygnus_audio *cygaud = snd_soc_dai_get_drvdata(dai);
+	int rate, bitres;
+	u32 value;
+	u32 mask = 0x1f;
+	int ret = 0;
+
+	dev_dbg(aio->cygaud->dev, "%s port = %d\n", __func__, aio->portnum);
+	dev_dbg(aio->cygaud->dev, "params_channels %d\n",
+			params_channels(params));
+	dev_dbg(aio->cygaud->dev, "rate %d\n", params_rate(params));
+	dev_dbg(aio->cygaud->dev, "format %d\n", params_format(params));
+
+	rate = params_rate(params);
+
+	switch (aio->mode) {
+	case CYGNUS_SSPMODE_TDM:
+		if ((rate == 192000) && (params_channels(params) > 4)) {
+			dev_err(aio->cygaud->dev, "Cannot run %d channels at %dHz\n",
+				params_channels(params), rate);
+			return -EINVAL;
+		}
+		break;
+	case CYGNUS_SSPMODE_I2S:
+		aio->bit_per_frame = 64; /* I2S must be 64 bit per frame */
+		break;
+	default:
+		dev_err(aio->cygaud->dev,
+			"%s port running in unknown mode\n", __func__);
+		return -EINVAL;
+	}
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		value = readl(aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+		value &= ~BIT(BF_SRC_CFGX_BUFFER_PAIR_ENABLE);
+		/* Configure channels as mono or stereo/TDM */
+		if (params_channels(params) == 1)
+			value |= BIT(BF_SRC_CFGX_SAMPLE_CH_MODE);
+		else
+			value &= ~BIT(BF_SRC_CFGX_SAMPLE_CH_MODE);
+		writel(value, aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+
+		switch (params_format(params)) {
+		case SNDRV_PCM_FORMAT_S8:
+			if (aio->port_type == PORT_SPDIF) {
+				dev_err(aio->cygaud->dev,
+				"SPDIF does not support 8bit format\n");
+				return -EINVAL;
+			}
+			bitres = 8;
+			break;
+
+		case SNDRV_PCM_FORMAT_S16_LE:
+			bitres = 16;
+			break;
+
+		case SNDRV_PCM_FORMAT_S32_LE:
+			/* 32 bit mode is coded as 0 */
+			bitres = 0;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+
+		value = readl(aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+		value &= ~(mask << BF_SRC_CFGX_BIT_RES);
+		value |= (bitres << BF_SRC_CFGX_BIT_RES);
+		writel(value, aio->cygaud->audio + aio->regs.bf_sourcech_cfg);
+
+	} else {
+
+		switch (params_format(params)) {
+		case SNDRV_PCM_FORMAT_S16_LE:
+			value = readl(aio->cygaud->audio +
+					aio->regs.bf_destch_cfg);
+			value |= BIT(BF_DST_CFGX_CAP_MODE);
+			writel(value, aio->cygaud->audio +
+					aio->regs.bf_destch_cfg);
+			break;
+
+		case SNDRV_PCM_FORMAT_S32_LE:
+			value = readl(aio->cygaud->audio +
+					aio->regs.bf_destch_cfg);
+			value &= ~BIT(BF_DST_CFGX_CAP_MODE);
+			writel(value, aio->cygaud->audio +
+					aio->regs.bf_destch_cfg);
+			break;
+
+		default:
+			return -EINVAL;
+		}
+	}
+
+	aio->lrclk = rate;
+
+	if (!aio->is_slave)
+		ret = cygnus_ssp_set_clocks(aio, cygaud);
+
+	return ret;
+}
+
+/*
+ * This function sets the mclk frequency for pll clock
+ */
+static int cygnus_ssp_set_sysclk(struct snd_soc_dai *dai,
+			int clk_id, unsigned int freq, int dir)
+{
+	int sel;
+	u32 value;
+	struct cygnus_aio_port *aio = cygnus_dai_get_portinfo(dai);
+	struct cygnus_audio *cygaud = snd_soc_dai_get_drvdata(dai);
+
+	dev_dbg(aio->cygaud->dev,
+		"%s Enter port = %d\n", __func__, aio->portnum);
+	sel = pll_configure_mclk(cygaud, freq, aio);
+	if (sel < 0) {
+		dev_err(aio->cygaud->dev,
+			"%s Setting mclk failed.\n", __func__);
+		return -EINVAL;
+	}
+
+	aio->mclk = freq;
+
+	dev_dbg(aio->cygaud->dev, "%s Setting MCLKSEL to %d\n", __func__, sel);
+	value = readl(aio->cygaud->audio + aio->regs.i2s_mclk_cfg);
+	value &= ~(0xf << I2S_OUT_PLLCLKSEL_SHIFT);
+	value |= (sel << I2S_OUT_PLLCLKSEL_SHIFT);
+	writel(value, aio->cygaud->audio + aio->regs.i2s_mclk_cfg);
+
+	return 0;
+}
+
+static int cygnus_ssp_startup(struct snd_pcm_substream *substream,
+			       struct snd_soc_dai *dai)
+{
+	struct cygnus_aio_port *aio = cygnus_dai_get_portinfo(dai);
+
+	snd_soc_dai_set_dma_data(dai, substream, aio);
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		aio->clk_trace.play_en = true;
+	else
+		aio->clk_trace.cap_en = true;
+
+	return 0;
+}
+
+static void cygnus_ssp_shutdown(struct snd_pcm_substream *substream,
+			       struct snd_soc_dai *dai)
+{
+	struct cygnus_aio_port *aio = cygnus_dai_get_portinfo(dai);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		aio->clk_trace.play_en = false;
+	else
+		aio->clk_trace.cap_en = false;
+
+	if (!aio->is_slave) {
+		u32 val;
+
+		val = readl(aio->cygaud->audio + aio->regs.i2s_mclk_cfg);
+		val &= CYGNUS_PLLCLKSEL_MASK;
+		if (val >= ARRAY_SIZE(aio->cygaud->audio_clk)) {
+			dev_err(aio->cygaud->dev, "Clk index %u is out of bounds\n",
+				val);
+			return;
+		}
+
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+			if (aio->clk_trace.play_clk_en) {
+				clk_disable_unprepare(aio->cygaud->
+						audio_clk[val]);
+				aio->clk_trace.play_clk_en = false;
+			}
+		} else {
+			if (aio->clk_trace.cap_clk_en) {
+				clk_disable_unprepare(aio->cygaud->
+						audio_clk[val]);
+				aio->clk_trace.cap_clk_en = false;
+			}
+		}
+	}
+}
+
+/*
+ * Bit    Update  Notes
+ * 31     Yes     TDM Mode        (1 = TDM, 0 = i2s)
+ * 30     Yes     Slave Mode	  (1 = Slave, 0 = Master)
+ * 29:26  No      Sclks per frame
+ * 25:18  Yes     FS Width
+ * 17:14  No      Valid Slots
+ * 13     No      Bits		  (1 = 16 bits, 0 = 32 bits)
+ * 12:08  No     Bits per samp
+ * 07     Yes     Justifcation    (1 = LSB, 0 = MSB)
+ * 06     Yes     Alignment       (1 = Delay 1 clk, 0 = no delay
+ * 05     Yes     SCLK polarity   (1 = Rising, 0 = Falling)
+ * 04     Yes     LRCLK Polarity  (1 = High for left, 0 = Low for left)
+ * 03:02  Yes     Reserved - write as zero
+ * 01     No      Data Enable
+ * 00     No      CLK Enable
+ */
+#define I2S_OUT_CFG_REG_UPDATE_MASK   0x3C03FF03
+
+/* Input cfg is same as output, but the FS width is not a valid field */
+#define I2S_IN_CFG_REG_UPDATE_MASK  (I2S_OUT_CFG_REG_UPDATE_MASK | 0x03FC0000)
+
+int cygnus_ssp_set_custom_fsync_width(struct snd_soc_dai *cpu_dai, int len)
+{
+	struct cygnus_aio_port *aio = cygnus_dai_get_portinfo(cpu_dai);
+
+	if ((len > 0) && (len < 256)) {
+		aio->fsync_width = len;
+		return 0;
+	} else {
+		return -EINVAL;
+	}
+}
+
+static int cygnus_ssp_set_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt)
+{
+	struct cygnus_aio_port *aio = cygnus_dai_get_portinfo(cpu_dai);
+	u32 ssp_curcfg;
+	u32 ssp_newcfg;
+	u32 ssp_outcfg;
+	u32 ssp_incfg;
+	u32 val;
+	u32 mask;
+
+	dev_dbg(aio->cygaud->dev, "%s Enter  fmt: %x\n", __func__, fmt);
+
+	if (aio->port_type == PORT_SPDIF)
+		return -EINVAL;
+
+	ssp_newcfg = 0;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		ssp_newcfg |= BIT(I2S_OUT_CFGX_SLAVE_MODE);
+		aio->is_slave = 1;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		ssp_newcfg &= ~BIT(I2S_OUT_CFGX_SLAVE_MODE);
+		aio->is_slave = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		ssp_newcfg |= BIT(I2S_OUT_CFGX_DATA_ALIGNMENT);
+		ssp_newcfg |= BIT(I2S_OUT_CFGX_FSYNC_WIDTH);
+		aio->mode = CYGNUS_SSPMODE_I2S;
+		break;
+
+	case SND_SOC_DAIFMT_DSP_A:
+	case SND_SOC_DAIFMT_DSP_B:
+		ssp_newcfg |= BIT(I2S_OUT_CFGX_TDM_MODE);
+
+		/* DSP_A = data after FS, DSP_B = data during FS */
+		if ((fmt & SND_SOC_DAIFMT_FORMAT_MASK) == SND_SOC_DAIFMT_DSP_A)
+			ssp_newcfg |= BIT(I2S_OUT_CFGX_DATA_ALIGNMENT);
+
+		if ((aio->fsync_width > 0) && (aio->fsync_width < 256))
+			ssp_newcfg |=
+				(aio->fsync_width << I2S_OUT_CFGX_FSYNC_WIDTH);
+		else
+			ssp_newcfg |= BIT(I2S_OUT_CFGX_FSYNC_WIDTH);
+
+		aio->mode = CYGNUS_SSPMODE_TDM;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * SSP out cfg.
+	 * Retain bits we do not want to update, then OR in new bits
+	 */
+	ssp_curcfg = readl(aio->cygaud->audio + aio->regs.i2s_cfg);
+	ssp_outcfg = (ssp_curcfg & I2S_OUT_CFG_REG_UPDATE_MASK) | ssp_newcfg;
+	writel(ssp_outcfg, aio->cygaud->audio + aio->regs.i2s_cfg);
+
+	/*
+	 * SSP in cfg.
+	 * Retain bits we do not want to update, then OR in new bits
+	 */
+	ssp_curcfg = readl(aio->cygaud->i2s_in + aio->regs.i2s_cap_cfg);
+	ssp_incfg = (ssp_curcfg & I2S_IN_CFG_REG_UPDATE_MASK) | ssp_newcfg;
+	writel(ssp_incfg, aio->cygaud->i2s_in + aio->regs.i2s_cap_cfg);
+
+	val = readl(aio->cygaud->audio + AUD_MISC_SEROUT_OE_REG_BASE);
+
+	/*
+	 * Configure the word clk and bit clk as output or tristate
+	 * Each port has 4 bits for controlling its pins.
+	 * Shift the mask based upon port number.
+	 */
+	mask = BIT(AUD_MISC_SEROUT_LRCK_OE)
+			| BIT(AUD_MISC_SEROUT_SCLK_OE)
+			| BIT(AUD_MISC_SEROUT_MCLK_OE);
+	mask = mask << (aio->portnum * 4);
+	if (aio->is_slave)
+		/* Set bit for tri-state */
+		val |= mask;
+	else
+		/* Clear bit for drive */
+		val &= ~mask;
+
+	dev_dbg(aio->cygaud->dev, "%s  Set OE bits 0x%x\n", __func__, val);
+	writel(val, aio->cygaud->audio + AUD_MISC_SEROUT_OE_REG_BASE);
+
+	return 0;
+}
+
+static int cygnus_ssp_trigger(struct snd_pcm_substream *substream, int cmd,
+			       struct snd_soc_dai *dai)
+{
+	struct cygnus_aio_port *aio = cygnus_dai_get_portinfo(dai);
+	struct cygnus_audio *cygaud = snd_soc_dai_get_drvdata(dai);
+
+	dev_dbg(aio->cygaud->dev,
+		"%s cmd %d at port = %d\n", __func__, cmd, aio->portnum);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+	case SNDRV_PCM_TRIGGER_RESUME:
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+			audio_ssp_out_enable(aio);
+		else
+			audio_ssp_in_enable(aio);
+		cygaud->active_ports++;
+
+		break;
+
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+			audio_ssp_out_disable(aio);
+		else
+			audio_ssp_in_disable(aio);
+		cygaud->active_ports--;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int cygnus_set_dai_tdm_slot(struct snd_soc_dai *cpu_dai,
+	unsigned int tx_mask, unsigned int rx_mask, int slots, int slot_width)
+{
+	struct cygnus_aio_port *aio = cygnus_dai_get_portinfo(cpu_dai);
+	u32 value;
+	int bits_per_slot = 0;     /* default to 32-bits per slot */
+	int frame_bits;
+	unsigned int active_slots;
+	bool found = false;
+	int i;
+
+	if (tx_mask != rx_mask) {
+		dev_err(aio->cygaud->dev,
+			"%s tx_mask must equal rx_mask\n", __func__);
+		return -EINVAL;
+	}
+
+	active_slots = hweight32(tx_mask);
+
+	if ((active_slots < 0) || (active_slots > 16))
+		return -EINVAL;
+
+	/* Slot value must be even */
+	if (active_slots % 2)
+		return -EINVAL;
+
+	/* We encode 16 slots as 0 in the reg */
+	if (active_slots == 16)
+		active_slots = 0;
+
+	/* Slot Width is either 16 or 32 */
+	switch (slot_width) {
+	case 16:
+		bits_per_slot = 1;
+		break;
+	case 32:
+		bits_per_slot = 0;
+		break;
+	default:
+		bits_per_slot = 0;
+		dev_warn(aio->cygaud->dev,
+			"%s Defaulting Slot Width to 32\n", __func__);
+	}
+
+	frame_bits = slots * slot_width;
+
+	for (i = 0; i < ARRAY_SIZE(ssp_valid_tdm_framesize); i++) {
+		if (ssp_valid_tdm_framesize[i] == frame_bits) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		dev_err(aio->cygaud->dev,
+			"%s In TDM mode, frame bits INVALID (%d)\n",
+			__func__, frame_bits);
+		return -EINVAL;
+	}
+
+	aio->bit_per_frame = frame_bits;
+
+	dev_dbg(aio->cygaud->dev, "%s active_slots %u, bits per frame %d\n",
+			__func__, active_slots, frame_bits);
+
+	/* Set capture side of ssp port */
+	value = readl(aio->cygaud->i2s_in + aio->regs.i2s_cap_cfg);
+	value &= ~(0xf << I2S_OUT_CFGX_VALID_SLOT);
+	value |= (active_slots << I2S_OUT_CFGX_VALID_SLOT);
+	value &= ~BIT(I2S_OUT_CFGX_BITS_PER_SLOT);
+	value |= (bits_per_slot << I2S_OUT_CFGX_BITS_PER_SLOT);
+	writel(value, aio->cygaud->i2s_in + aio->regs.i2s_cap_cfg);
+
+	/* Set playback side of ssp port */
+	value = readl(aio->cygaud->audio + aio->regs.i2s_cfg);
+	value &= ~(0xf << I2S_OUT_CFGX_VALID_SLOT);
+	value |= (active_slots << I2S_OUT_CFGX_VALID_SLOT);
+	value &= ~BIT(I2S_OUT_CFGX_BITS_PER_SLOT);
+	value |= (bits_per_slot << I2S_OUT_CFGX_BITS_PER_SLOT);
+	writel(value, aio->cygaud->audio + aio->regs.i2s_cfg);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int cygnus_ssp_suspend(struct snd_soc_dai *cpu_dai)
+{
+	struct cygnus_aio_port *aio = cygnus_dai_get_portinfo(cpu_dai);
+
+	if (!aio->is_slave) {
+		u32 val;
+
+		val = readl(aio->cygaud->audio + aio->regs.i2s_mclk_cfg);
+		val &= CYGNUS_PLLCLKSEL_MASK;
+		if (val >= ARRAY_SIZE(aio->cygaud->audio_clk)) {
+			dev_err(aio->cygaud->dev, "Clk index %u is out of bounds\n",
+				val);
+			return -EINVAL;
+		}
+
+		if (aio->clk_trace.cap_clk_en)
+			clk_disable_unprepare(aio->cygaud->audio_clk[val]);
+		if (aio->clk_trace.play_clk_en)
+			clk_disable_unprepare(aio->cygaud->audio_clk[val]);
+
+		aio->pll_clk_num = val;
+	}
+
+	return 0;
+}
+
+static int cygnus_ssp_resume(struct snd_soc_dai *cpu_dai)
+{
+	struct cygnus_aio_port *aio = cygnus_dai_get_portinfo(cpu_dai);
+	int error;
+
+	if (!aio->is_slave) {
+		if (aio->clk_trace.cap_clk_en) {
+			error = clk_prepare_enable(aio->cygaud->
+					audio_clk[aio->pll_clk_num]);
+			if (error) {
+				dev_err(aio->cygaud->dev, "%s clk_prepare_enable failed\n",
+					__func__);
+				return -EINVAL;
+			}
+		}
+		if (aio->clk_trace.play_clk_en) {
+			error = clk_prepare_enable(aio->cygaud->
+					audio_clk[aio->pll_clk_num]);
+			if (error) {
+				if (aio->clk_trace.cap_clk_en)
+					clk_disable_unprepare(aio->cygaud->
+						audio_clk[aio->pll_clk_num]);
+				dev_err(aio->cygaud->dev, "%s clk_prepare_enable failed\n",
+					__func__);
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+#else
+#define cygnus_ssp_suspend NULL
+#define cygnus_ssp_resume  NULL
+#endif
+
+static const struct snd_soc_dai_ops cygnus_ssp_dai_ops = {
+	.startup	= cygnus_ssp_startup,
+	.shutdown	= cygnus_ssp_shutdown,
+	.trigger	= cygnus_ssp_trigger,
+	.hw_params	= cygnus_ssp_hw_params,
+	.set_fmt	= cygnus_ssp_set_fmt,
+	.set_sysclk	= cygnus_ssp_set_sysclk,
+	.set_tdm_slot	= cygnus_set_dai_tdm_slot,
+};
+
+
+#define INIT_CPU_DAI(num) { \
+	.name = "cygnus-ssp" #num, \
+	.playback = { \
+		.channels_min = 1, \
+		.channels_max = 16, \
+		.rates = CYGNUS_TDM_RATE | SNDRV_PCM_RATE_88200 | \
+			SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_176400 | \
+			SNDRV_PCM_RATE_192000, \
+		.formats = SNDRV_PCM_FMTBIT_S8 | \
+				SNDRV_PCM_FMTBIT_S16_LE | \
+				SNDRV_PCM_FMTBIT_S32_LE, \
+	}, \
+	.capture = { \
+		.channels_min = 2, \
+		.channels_max = 16, \
+		.rates = CYGNUS_TDM_RATE | SNDRV_PCM_RATE_88200 | \
+			SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_176400 | \
+			SNDRV_PCM_RATE_192000, \
+		.formats =  SNDRV_PCM_FMTBIT_S16_LE | \
+					SNDRV_PCM_FMTBIT_S32_LE, \
+	}, \
+	.ops = &cygnus_ssp_dai_ops, \
+	.suspend = cygnus_ssp_suspend, \
+	.resume = cygnus_ssp_resume, \
+}
+
+static const struct snd_soc_dai_driver cygnus_ssp_dai_info[] = {
+	INIT_CPU_DAI(0),
+	INIT_CPU_DAI(1),
+	INIT_CPU_DAI(2),
+};
+
+static struct snd_soc_dai_driver cygnus_spdif_dai_info = {
+	.name = "cygnus-spdif",
+	.playback = {
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = CYGNUS_TDM_RATE | SNDRV_PCM_RATE_88200 |
+			SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_176400 |
+			SNDRV_PCM_RATE_192000,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE |
+			SNDRV_PCM_FMTBIT_S32_LE,
+	},
+	.ops = &cygnus_ssp_dai_ops,
+	.suspend = cygnus_ssp_suspend,
+	.resume = cygnus_ssp_resume,
+};
+
+static struct snd_soc_dai_driver cygnus_ssp_dai[CYGNUS_MAX_PORTS];
+
+static const struct snd_soc_component_driver cygnus_ssp_component = {
+	.name		= "cygnus-audio",
+};
+
+/*
+ * Return < 0 if error
+ * Return 0 if disabled
+ * Return 1 if enabled and node is parsed successfully
+ */
+static int parse_ssp_child_node(struct platform_device *pdev,
+				struct device_node *dn,
+				struct cygnus_audio *cygaud,
+				struct snd_soc_dai_driver *p_dai)
+{
+	struct cygnus_aio_port *aio;
+	struct cygnus_ssp_regs ssp_regs[3];
+	u32 rawval;
+	int portnum = -1;
+	enum cygnus_audio_port_type port_type;
+
+	if (of_property_read_u32(dn, "reg", &rawval)) {
+		dev_err(&pdev->dev, "Missing reg property\n");
+		return -EINVAL;
+	}
+
+	portnum = rawval;
+	switch (rawval) {
+	case 0:
+		ssp_regs[0] = INIT_SSP_REGS(0);
+		port_type = PORT_TDM;
+		break;
+	case 1:
+		ssp_regs[1] = INIT_SSP_REGS(1);
+		port_type = PORT_TDM;
+		break;
+	case 2:
+		ssp_regs[2] = INIT_SSP_REGS(2);
+		port_type = PORT_TDM;
+		break;
+	case 3:
+		port_type = PORT_SPDIF;
+		break;
+	default:
+		dev_err(&pdev->dev, "Bad value for reg %u\n", rawval);
+		return -EINVAL;
+	}
+
+	aio = &cygaud->portinfo[portnum];
+	aio->cygaud = cygaud;
+	aio->portnum = portnum;
+	aio->port_type = port_type;
+	aio->fsync_width = -1;
+
+	switch (port_type) {
+	case PORT_TDM:
+		aio->regs = ssp_regs[portnum];
+		*p_dai = cygnus_ssp_dai_info[portnum];
+		aio->mode = CYGNUS_SSPMODE_UNKNOWN;
+		break;
+
+	case PORT_SPDIF:
+		aio->regs.bf_sourcech_cfg = BF_SRC_CFG3_OFFSET;
+		aio->regs.bf_sourcech_ctrl = BF_SRC_CTRL3_OFFSET;
+		aio->regs.i2s_mclk_cfg = SPDIF_MCLK_CFG_OFFSET;
+		aio->regs.i2s_stream_cfg = SPDIF_STREAM_CFG_OFFSET;
+		*p_dai = cygnus_spdif_dai_info;
+
+		/* For the purposes of this code SPDIF can be I2S mode */
+		aio->mode = CYGNUS_SSPMODE_I2S;
+		break;
+	default:
+		dev_err(&pdev->dev, "Bad value for port_type %d\n", port_type);
+		return -EINVAL;
+	}
+
+	dev_dbg(&pdev->dev, "%s portnum = %d\n", __func__, aio->portnum);
+	aio->streams_on = 0;
+	aio->cygaud->dev = &pdev->dev;
+	aio->clk_trace.play_en = false;
+	aio->clk_trace.cap_en = false;
+
+	audio_ssp_init_portregs(aio);
+	return 0;
+}
+
+static int audio_clk_init(struct platform_device *pdev,
+						struct cygnus_audio *cygaud)
+{
+	int i;
+	char clk_name[PROP_LEN_MAX];
+
+	for (i = 0; i < ARRAY_SIZE(cygaud->audio_clk); i++) {
+		snprintf(clk_name, PROP_LEN_MAX, "ch%d_audio", i);
+
+		cygaud->audio_clk[i] = devm_clk_get(&pdev->dev, clk_name);
+		if (IS_ERR(cygaud->audio_clk[i]))
+			return PTR_ERR(cygaud->audio_clk[i]);
+	}
+
+	return 0;
+}
+
+static int cygnus_ssp_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *child_node;
+	struct resource *res = pdev->resource;
+	struct cygnus_audio *cygaud;
+	int err = -EINVAL;
+	int node_count;
+	int active_port_count;
+
+	cygaud = devm_kzalloc(dev, sizeof(struct cygnus_audio), GFP_KERNEL);
+	if (!cygaud)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, cygaud);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "aud");
+	cygaud->audio = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cygaud->audio))
+		return PTR_ERR(cygaud->audio);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "i2s_in");
+	cygaud->i2s_in = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cygaud->i2s_in))
+		return PTR_ERR(cygaud->i2s_in);
+
+	/* Tri-state all controlable pins until we know that we need them */
+	writel(CYGNUS_SSP_TRISTATE_MASK,
+			cygaud->audio + AUD_MISC_SEROUT_OE_REG_BASE);
+
+	node_count = of_get_child_count(pdev->dev.of_node);
+	if ((node_count < 1) || (node_count > CYGNUS_MAX_PORTS)) {
+		dev_err(dev, "child nodes is %d.  Must be between 1 and %d\n",
+			node_count, CYGNUS_MAX_PORTS);
+		return -EINVAL;
+	}
+
+	active_port_count = 0;
+
+	for_each_available_child_of_node(pdev->dev.of_node, child_node) {
+		err = parse_ssp_child_node(pdev, child_node, cygaud,
+					&cygnus_ssp_dai[active_port_count]);
+
+		/* negative is err, 0 is active and good, 1 is disabled */
+		if (err < 0)
+			return err;
+		else if (!err) {
+			dev_dbg(dev, "Activating DAI: %s\n",
+				cygnus_ssp_dai[active_port_count].name);
+			active_port_count++;
+		}
+	}
+
+	cygaud->dev = dev;
+	cygaud->active_ports = 0;
+
+	dev_dbg(dev, "Registering %d DAIs\n", active_port_count);
+	err = snd_soc_register_component(dev, &cygnus_ssp_component,
+				cygnus_ssp_dai, active_port_count);
+	if (err) {
+		dev_err(dev, "snd_soc_register_dai failed\n");
+		return err;
+	}
+
+	cygaud->irq_num = platform_get_irq(pdev, 0);
+	if (cygaud->irq_num <= 0) {
+		dev_err(dev, "platform_get_irq failed\n");
+		err = cygaud->irq_num;
+		goto err_irq;
+	}
+
+	err = audio_clk_init(pdev, cygaud);
+	if (err) {
+		dev_err(dev, "audio clock initialization failed\n");
+		goto err_irq;
+	}
+
+	err = cygnus_soc_platform_register(dev, cygaud);
+	if (err) {
+		dev_err(dev, "platform reg error %d\n", err);
+		goto err_irq;
+	}
+
+	return 0;
+
+err_irq:
+	snd_soc_unregister_component(dev);
+	return err;
+}
+
+static int cygnus_ssp_remove(struct platform_device *pdev)
+{
+	cygnus_soc_platform_unregister(&pdev->dev);
+	snd_soc_unregister_component(&pdev->dev);
+
+	return 0;
+}
+
+static const struct of_device_id cygnus_ssp_of_match[] = {
+	{ .compatible = "brcm,cygnus-audio" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, cygnus_ssp_of_match);
+
+static struct platform_driver cygnus_ssp_driver = {
+	.probe		= cygnus_ssp_probe,
+	.remove		= cygnus_ssp_remove,
+	.driver		= {
+		.name	= "cygnus-ssp",
+		.of_match_table = cygnus_ssp_of_match,
+	},
+};
+
+module_platform_driver(cygnus_ssp_driver);
+
+MODULE_ALIAS("platform:cygnus-ssp");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Broadcom");
+MODULE_DESCRIPTION("Cygnus ASoC SSP Interface");
diff --git a/sound/soc/bcm/cygnus-ssp.h b/sound/soc/bcm/cygnus-ssp.h
new file mode 100644
index 000000000000..33dd34305928
--- /dev/null
+++ b/sound/soc/bcm/cygnus-ssp.h
@@ -0,0 +1,139 @@
+/*
+ * Copyright (C) 2014-2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef __CYGNUS_SSP_H__
+#define __CYGNUS_SSP_H__
+
+#define CYGNUS_TDM_DAI_MAX_SLOTS 16
+
+#define CYGNUS_MAX_PLAYBACK_PORTS 4
+#define CYGNUS_MAX_CAPTURE_PORTS 3
+#define CYGNUS_MAX_I2S_PORTS 3
+#define CYGNUS_MAX_PORTS  CYGNUS_MAX_PLAYBACK_PORTS
+#define CYGNUS_AUIDO_MAX_NUM_CLKS 3
+
+#define CYGNUS_SSP_FRAMEBITS_DIV 1
+
+#define CYGNUS_SSPMODE_I2S 0
+#define CYGNUS_SSPMODE_TDM 1
+#define CYGNUS_SSPMODE_UNKNOWN -1
+
+#define CYGNUS_SSP_CLKSRC_PLL      0
+
+/* Max string length of our dt property names */
+#define PROP_LEN_MAX 40
+
+struct ringbuf_regs {
+	unsigned rdaddr;
+	unsigned wraddr;
+	unsigned baseaddr;
+	unsigned endaddr;
+	unsigned fmark;   /* freemark for play, fullmark for caputure */
+	unsigned period_bytes;
+	unsigned buf_size;
+};
+
+#define RINGBUF_REG_PLAYBACK(num) ((struct ringbuf_regs) { \
+	.rdaddr = SRC_RBUF_ ##num## _RDADDR_OFFSET, \
+	.wraddr = SRC_RBUF_ ##num## _WRADDR_OFFSET, \
+	.baseaddr = SRC_RBUF_ ##num## _BASEADDR_OFFSET, \
+	.endaddr = SRC_RBUF_ ##num## _ENDADDR_OFFSET, \
+	.fmark = SRC_RBUF_ ##num## _FREE_MARK_OFFSET, \
+	.period_bytes = 0, \
+	.buf_size = 0, \
+})
+
+#define RINGBUF_REG_CAPTURE(num) ((struct ringbuf_regs)  { \
+	.rdaddr = DST_RBUF_ ##num## _RDADDR_OFFSET, \
+	.wraddr = DST_RBUF_ ##num## _WRADDR_OFFSET, \
+	.baseaddr = DST_RBUF_ ##num## _BASEADDR_OFFSET, \
+	.endaddr = DST_RBUF_ ##num## _ENDADDR_OFFSET, \
+	.fmark = DST_RBUF_ ##num## _FULL_MARK_OFFSET, \
+	.period_bytes = 0, \
+	.buf_size = 0, \
+})
+
+enum cygnus_audio_port_type {
+	PORT_TDM,
+	PORT_SPDIF,
+};
+
+struct cygnus_ssp_regs {
+	u32 i2s_stream_cfg;
+	u32 i2s_cfg;
+	u32 i2s_cap_stream_cfg;
+	u32 i2s_cap_cfg;
+	u32 i2s_mclk_cfg;
+
+	u32 bf_destch_ctrl;
+	u32 bf_destch_cfg;
+	u32 bf_sourcech_ctrl;
+	u32 bf_sourcech_cfg;
+	u32 bf_sourcech_grp;
+};
+
+struct cygnus_track_clk {
+	bool cap_en;
+	bool play_en;
+	bool cap_clk_en;
+	bool play_clk_en;
+};
+
+struct cygnus_aio_port {
+	int portnum;
+	int mode;
+	bool is_slave;
+	int streams_on;   /* will be 0 if both capture and play are off */
+	int fsync_width;
+	int port_type;
+
+	u32 mclk;
+	u32 lrclk;
+	u32 bit_per_frame;
+	u32 pll_clk_num;
+
+	struct cygnus_audio *cygaud;
+	struct cygnus_ssp_regs regs;
+
+	struct ringbuf_regs play_rb_regs;
+	struct ringbuf_regs capture_rb_regs;
+
+	struct snd_pcm_substream *play_stream;
+	struct snd_pcm_substream *capture_stream;
+
+	struct cygnus_track_clk clk_trace;
+};
+
+
+struct cygnus_audio {
+	struct cygnus_aio_port  portinfo[CYGNUS_MAX_PORTS];
+
+	int irq_num;
+	void __iomem *audio;
+	struct device *dev;
+	void __iomem *i2s_in;
+
+	struct clk *audio_clk[CYGNUS_AUIDO_MAX_NUM_CLKS];
+	int active_ports;
+	unsigned long vco_rate;
+};
+
+extern int cygnus_ssp_get_mode(struct snd_soc_dai *cpu_dai);
+extern int cygnus_ssp_add_pll_tweak_controls(struct snd_soc_pcm_runtime *rtd);
+extern int cygnus_ssp_set_custom_fsync_width(struct snd_soc_dai *cpu_dai,
+						int len);
+extern int cygnus_soc_platform_register(struct device *dev,
+					struct cygnus_audio *cygaud);
+extern int cygnus_soc_platform_unregister(struct device *dev);
+extern int cygnus_ssp_set_custom_fsync_width(struct snd_soc_dai *cpu_dai,
+	int len);
+#endif
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index f3fb98f0a995..1cd6ab344d67 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -32,6 +32,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_ADAU1977_SPI if SPI_MASTER
 	select SND_SOC_ADAU1977_I2C if I2C
 	select SND_SOC_ADAU1701 if I2C
+	select SND_SOC_ADAU7002
 	select SND_SOC_ADS117X
 	select SND_SOC_AK4104 if SPI_MASTER
 	select SND_SOC_AK4535 if I2C
@@ -46,6 +47,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_BT_SCO
 	select SND_SOC_CQ0093VC if MFD_DAVINCI_VOICECODEC
 	select SND_SOC_CS35L32 if I2C
+	select SND_SOC_CS35L33 if I2C
 	select SND_SOC_CS42L51_I2C if I2C
 	select SND_SOC_CS42L52 if I2C && INPUT
 	select SND_SOC_CS42L56 if I2C && INPUT
@@ -57,6 +59,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_CS42XX8_I2C if I2C
 	select SND_SOC_CS4349 if I2C
 	select SND_SOC_CS47L24 if MFD_CS47L24
+	select SND_SOC_CS53L30 if I2C
 	select SND_SOC_CX20442 if TTY
 	select SND_SOC_DA7210 if SND_SOC_I2C_AND_SPI
 	select SND_SOC_DA7213 if I2C
@@ -84,6 +87,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_MAX98925 if I2C
 	select SND_SOC_MAX98926 if I2C
 	select SND_SOC_MAX9850 if I2C
+	select SND_SOC_MAX9860 if I2C
 	select SND_SOC_MAX9768 if I2C
 	select SND_SOC_MAX9877 if I2C
 	select SND_SOC_MC13783 if MFD_MC13XXX
@@ -269,8 +273,12 @@ config SND_SOC_AD1980
 config SND_SOC_AD73311
 	tristate
 
+config SND_SOC_ADAU_UTILS
+	tristate
+
 config SND_SOC_ADAU1373
 	tristate
+	select SND_SOC_ADAU_UTILS
 
 config SND_SOC_ADAU1701
 	tristate "Analog Devices ADAU1701 CODEC"
@@ -280,6 +288,7 @@ config SND_SOC_ADAU1701
 config SND_SOC_ADAU17X1
 	tristate
 	select SND_SOC_SIGMADSP_REGMAP
+	select SND_SOC_ADAU_UTILS
 
 config SND_SOC_ADAU1761
 	tristate
@@ -322,6 +331,9 @@ config SND_SOC_ADAU1977_I2C
 	select SND_SOC_ADAU1977
 	select REGMAP_I2C
 
+config SND_SOC_ADAU7002
+	tristate "Analog Devices ADAU7002 Stereo PDM-to-I2S/TDM Converter"
+
 config SND_SOC_ADAV80X
 	tristate
 
@@ -371,7 +383,7 @@ config SND_SOC_ALC5632
 	tristate
 
 config SND_SOC_BT_SCO
-	tristate
+	tristate "Dummy BT SCO codec driver"
 
 config SND_SOC_CQ0093VC
 	tristate
@@ -380,6 +392,10 @@ config SND_SOC_CS35L32
 	tristate "Cirrus Logic CS35L32 CODEC"
 	depends on I2C
 
+config SND_SOC_CS35L33
+	tristate "Cirrus Logic CS35L33 CODEC"
+	depends on I2C
+
 config SND_SOC_CS42L51
 	tristate
 
@@ -450,6 +466,11 @@ config SND_SOC_CS4349
 config SND_SOC_CS47L24
 	tristate
 
+# Cirrus Logic Quad-Channel ADC
+config SND_SOC_CS53L30
+	tristate "Cirrus Logic CS53L30 CODEC"
+	depends on I2C
+
 config SND_SOC_CX20442
 	tristate
 	depends on TTY
@@ -536,6 +557,10 @@ config SND_SOC_MAX98357A
 config SND_SOC_MAX98371
        tristate
 
+config SND_SOC_MAX98504
+	tristate "Maxim MAX98504 speaker amplifier"
+	depends on I2C
+
 config SND_SOC_MAX9867
 	tristate
 
@@ -548,6 +573,11 @@ config SND_SOC_MAX98926
 config SND_SOC_MAX9850
 	tristate
 
+config SND_SOC_MAX9860
+	tristate "Maxim MAX9860 Mono Audio Voice Codec"
+	depends on I2C
+	select REGMAP_I2C
+
 config SND_SOC_PCM1681
 	tristate "Texas Instruments PCM1681 CODEC"
 	depends on I2C
@@ -644,6 +674,9 @@ config SND_SOC_RT298
 config SND_SOC_RT5514
 	tristate
 
+config SND_SOC_RT5514_SPI
+	tristate
+
 config SND_SOC_RT5616
 	tristate "Realtek RT5616 CODEC"
 	depends on I2C
@@ -969,7 +1002,8 @@ config SND_SOC_WM8983
 	tristate
 
 config SND_SOC_WM8985
-	tristate
+	tristate "Wolfson Microelectronics WM8985 and WM8758 codec driver"
+	depends on SND_SOC_I2C_AND_SPI
 
 config SND_SOC_WM8988
 	tristate
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index 0f548fd34ca3..58036af2c7d9 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -7,6 +7,7 @@ snd-soc-ad193x-spi-objs := ad193x-spi.o
 snd-soc-ad193x-i2c-objs := ad193x-i2c.o
 snd-soc-ad1980-objs := ad1980.o
 snd-soc-ad73311-objs := ad73311.o
+snd-soc-adau-utils-objs := adau-utils.o
 snd-soc-adau1373-objs := adau1373.o
 snd-soc-adau1701-objs := adau1701.o
 snd-soc-adau17x1-objs := adau17x1.o
@@ -19,6 +20,7 @@ snd-soc-adau1781-spi-objs := adau1781-spi.o
 snd-soc-adau1977-objs := adau1977.o
 snd-soc-adau1977-spi-objs := adau1977-spi.o
 snd-soc-adau1977-i2c-objs := adau1977-i2c.o
+snd-soc-adau7002-objs := adau7002.o
 snd-soc-adav80x-objs := adav80x.o
 snd-soc-adav801-objs := adav801.o
 snd-soc-adav803-objs := adav803.o
@@ -35,6 +37,7 @@ snd-soc-arizona-objs := arizona.o
 snd-soc-bt-sco-objs := bt-sco.o
 snd-soc-cq93vc-objs := cq93vc.o
 snd-soc-cs35l32-objs := cs35l32.o
+snd-soc-cs35l33-objs := cs35l33.o
 snd-soc-cs42l51-objs := cs42l51.o
 snd-soc-cs42l51-i2c-objs := cs42l51-i2c.o
 snd-soc-cs42l52-objs := cs42l52.o
@@ -49,6 +52,7 @@ snd-soc-cs42xx8-objs := cs42xx8.o
 snd-soc-cs42xx8-i2c-objs := cs42xx8-i2c.o
 snd-soc-cs4349-objs := cs4349.o
 snd-soc-cs47l24-objs := cs47l24.o
+snd-soc-cs53l30-objs := cs53l30.o
 snd-soc-cx20442-objs := cx20442.o
 snd-soc-da7210-objs := da7210.o
 snd-soc-da7213-objs := da7213.o
@@ -79,6 +83,7 @@ snd-soc-max9867-objs := max9867.o
 snd-soc-max98925-objs := max98925.o
 snd-soc-max98926-objs := max98926.o
 snd-soc-max9850-objs := max9850.o
+snd-soc-max9860-objs := max9860.o
 snd-soc-mc13783-objs := mc13783.o
 snd-soc-ml26124-objs := ml26124.o
 snd-soc-nau8825-objs := nau8825.o
@@ -100,6 +105,7 @@ snd-soc-rl6347a-objs := rl6347a.o
 snd-soc-rt286-objs := rt286.o
 snd-soc-rt298-objs := rt298.o
 snd-soc-rt5514-objs := rt5514.o
+snd-soc-rt5514-spi-objs := rt5514-spi.o
 snd-soc-rt5616-objs := rt5616.o
 snd-soc-rt5631-objs := rt5631.o
 snd-soc-rt5640-objs := rt5640.o
@@ -208,6 +214,7 @@ snd-soc-wm-hubs-objs := wm_hubs.o
 
 # Amp
 snd-soc-max9877-objs := max9877.o
+snd-soc-max98504-objs := max98504.o
 snd-soc-tpa6130a2-objs := tpa6130a2.o
 snd-soc-tas2552-objs := tas2552.o
 
@@ -220,6 +227,7 @@ obj-$(CONFIG_SND_SOC_AD193X_SPI)	+= snd-soc-ad193x-spi.o
 obj-$(CONFIG_SND_SOC_AD193X_I2C)	+= snd-soc-ad193x-i2c.o
 obj-$(CONFIG_SND_SOC_AD1980)	+= snd-soc-ad1980.o
 obj-$(CONFIG_SND_SOC_AD73311) += snd-soc-ad73311.o
+obj-$(CONFIG_SND_SOC_ADAU_UTILS)	+= snd-soc-adau-utils.o
 obj-$(CONFIG_SND_SOC_ADAU1373)	+= snd-soc-adau1373.o
 obj-$(CONFIG_SND_SOC_ADAU1701)		+= snd-soc-adau1701.o
 obj-$(CONFIG_SND_SOC_ADAU17X1)		+= snd-soc-adau17x1.o
@@ -232,6 +240,7 @@ obj-$(CONFIG_SND_SOC_ADAU1781_SPI)	+= snd-soc-adau1781-spi.o
 obj-$(CONFIG_SND_SOC_ADAU1977)		+= snd-soc-adau1977.o
 obj-$(CONFIG_SND_SOC_ADAU1977_SPI)	+= snd-soc-adau1977-spi.o
 obj-$(CONFIG_SND_SOC_ADAU1977_I2C)	+= snd-soc-adau1977-i2c.o
+obj-$(CONFIG_SND_SOC_ADAU7002)	+= snd-soc-adau7002.o
 obj-$(CONFIG_SND_SOC_ADAV80X)  += snd-soc-adav80x.o
 obj-$(CONFIG_SND_SOC_ADAV801)  += snd-soc-adav801.o
 obj-$(CONFIG_SND_SOC_ADAV803)  += snd-soc-adav803.o
@@ -250,6 +259,7 @@ obj-$(CONFIG_SND_SOC_ARIZONA)	+= snd-soc-arizona.o
 obj-$(CONFIG_SND_SOC_BT_SCO)	+= snd-soc-bt-sco.o
 obj-$(CONFIG_SND_SOC_CQ0093VC) += snd-soc-cq93vc.o
 obj-$(CONFIG_SND_SOC_CS35L32)	+= snd-soc-cs35l32.o
+obj-$(CONFIG_SND_SOC_CS35L33)	+= snd-soc-cs35l33.o
 obj-$(CONFIG_SND_SOC_CS42L51)	+= snd-soc-cs42l51.o
 obj-$(CONFIG_SND_SOC_CS42L51_I2C)	+= snd-soc-cs42l51-i2c.o
 obj-$(CONFIG_SND_SOC_CS42L52)	+= snd-soc-cs42l52.o
@@ -264,6 +274,7 @@ obj-$(CONFIG_SND_SOC_CS42XX8)	+= snd-soc-cs42xx8.o
 obj-$(CONFIG_SND_SOC_CS42XX8_I2C) += snd-soc-cs42xx8-i2c.o
 obj-$(CONFIG_SND_SOC_CS4349)	+= snd-soc-cs4349.o
 obj-$(CONFIG_SND_SOC_CS47L24)	+= snd-soc-cs47l24.o
+obj-$(CONFIG_SND_SOC_CS53L30)	+= snd-soc-cs53l30.o
 obj-$(CONFIG_SND_SOC_CX20442)	+= snd-soc-cx20442.o
 obj-$(CONFIG_SND_SOC_DA7210)	+= snd-soc-da7210.o
 obj-$(CONFIG_SND_SOC_DA7213)	+= snd-soc-da7213.o
@@ -293,6 +304,7 @@ obj-$(CONFIG_SND_SOC_MAX9867)	+= snd-soc-max9867.o
 obj-$(CONFIG_SND_SOC_MAX98925)	+= snd-soc-max98925.o
 obj-$(CONFIG_SND_SOC_MAX98926)	+= snd-soc-max98926.o
 obj-$(CONFIG_SND_SOC_MAX9850)	+= snd-soc-max9850.o
+obj-$(CONFIG_SND_SOC_MAX9860)	+= snd-soc-max9860.o
 obj-$(CONFIG_SND_SOC_MC13783)	+= snd-soc-mc13783.o
 obj-$(CONFIG_SND_SOC_ML26124)	+= snd-soc-ml26124.o
 obj-$(CONFIG_SND_SOC_NAU8825)   += snd-soc-nau8825.o
@@ -314,6 +326,7 @@ obj-$(CONFIG_SND_SOC_RL6347A)	+= snd-soc-rl6347a.o
 obj-$(CONFIG_SND_SOC_RT286)	+= snd-soc-rt286.o
 obj-$(CONFIG_SND_SOC_RT298)	+= snd-soc-rt298.o
 obj-$(CONFIG_SND_SOC_RT5514)	+= snd-soc-rt5514.o
+obj-$(CONFIG_SND_SOC_RT5514_SPI)	+= snd-soc-rt5514-spi.o
 obj-$(CONFIG_SND_SOC_RT5616)	+= snd-soc-rt5616.o
 obj-$(CONFIG_SND_SOC_RT5631)	+= snd-soc-rt5631.o
 obj-$(CONFIG_SND_SOC_RT5640)	+= snd-soc-rt5640.o
@@ -419,4 +432,5 @@ obj-$(CONFIG_SND_SOC_WM_HUBS)	+= snd-soc-wm-hubs.o
 
 # Amp
 obj-$(CONFIG_SND_SOC_MAX9877)	+= snd-soc-max9877.o
+obj-$(CONFIG_SND_SOC_MAX98504)	+= snd-soc-max98504.o
 obj-$(CONFIG_SND_SOC_TPA6130A2)	+= snd-soc-tpa6130a2.o
diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c
index 8b1d0c1a7839..2fc89155f14a 100644
--- a/sound/soc/codecs/ab8500-codec.c
+++ b/sound/soc/codecs/ab8500-codec.c
@@ -2464,45 +2464,20 @@ static int ab8500_codec_probe(struct snd_soc_codec *codec)
 	struct device *dev = codec->dev;
 	struct device_node *np = dev->of_node;
 	struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(dev);
-	struct ab8500_platform_data *pdata;
+	struct ab8500_codec_platform_data codec_pdata;
 	struct filter_control *fc;
 	int status;
 
 	dev_dbg(dev, "%s: Enter.\n", __func__);
 
-	/* Setup AB8500 according to board-settings */
-	pdata = dev_get_platdata(dev->parent);
+	ab8500_codec_of_probe(dev, np, &codec_pdata);
 
-	if (np) {
-		if (!pdata)
-			pdata = devm_kzalloc(dev,
-					sizeof(struct ab8500_platform_data),
-					GFP_KERNEL);
-
-		if (pdata && !pdata->codec)
-			pdata->codec
-				= devm_kzalloc(dev,
-					sizeof(struct ab8500_codec_platform_data),
-					GFP_KERNEL);
-
-		if (!(pdata && pdata->codec))
-			return -ENOMEM;
-
-		ab8500_codec_of_probe(dev, np, pdata->codec);
-
-	} else {
-		if (!(pdata && pdata->codec)) {
-			dev_err(dev, "No codec platform data or DT found\n");
-			return -EINVAL;
-		}
-	}
-
-	status = ab8500_audio_setup_mics(codec, &pdata->codec->amics);
+	status = ab8500_audio_setup_mics(codec, &codec_pdata.amics);
 	if (status < 0) {
 		pr_err("%s: Failed to setup mics (%d)!\n", __func__, status);
 		return status;
 	}
-	status = ab8500_audio_set_ear_cmv(codec, pdata->codec->ear_cmv);
+	status = ab8500_audio_set_ear_cmv(codec, codec_pdata.ear_cmv);
 	if (status < 0) {
 		pr_err("%s: Failed to set earpiece CM-voltage (%d)!\n",
 			__func__, status);
diff --git a/sound/soc/codecs/adau-utils.c b/sound/soc/codecs/adau-utils.c
new file mode 100644
index 000000000000..19d6a6f41b12
--- /dev/null
+++ b/sound/soc/codecs/adau-utils.c
@@ -0,0 +1,61 @@
+/*
+ * Shared helper functions for devices from the ADAU family
+ *
+ * Copyright 2011-2016 Analog Devices Inc.
+ * Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/gcd.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "adau-utils.h"
+
+int adau_calc_pll_cfg(unsigned int freq_in, unsigned int freq_out,
+	uint8_t regs[5])
+{
+	unsigned int r, n, m, i, j;
+	unsigned int div;
+
+	if (!freq_out) {
+		r = 0;
+		n = 0;
+		m = 0;
+		div = 0;
+	} else {
+		if (freq_out % freq_in != 0) {
+			div = DIV_ROUND_UP(freq_in, 13500000);
+			freq_in /= div;
+			r = freq_out / freq_in;
+			i = freq_out % freq_in;
+			j = gcd(i, freq_in);
+			n = i / j;
+			m = freq_in / j;
+			div--;
+		} else {
+			r = freq_out / freq_in;
+			n = 0;
+			m = 0;
+			div = 0;
+		}
+		if (n > 0xffff || m > 0xffff || div > 3 || r > 8 || r < 2)
+			return -EINVAL;
+	}
+
+	regs[0] = m >> 8;
+	regs[1] = m & 0xff;
+	regs[2] = n >> 8;
+	regs[3] = n & 0xff;
+	regs[4] = (r << 3) | (div << 1);
+	if (m != 0)
+		regs[4] |= 1; /* Fractional mode */
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adau_calc_pll_cfg);
+
+MODULE_DESCRIPTION("ASoC ADAU audio CODECs shared helper functions");
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/adau-utils.h b/sound/soc/codecs/adau-utils.h
new file mode 100644
index 000000000000..939b5f37762f
--- /dev/null
+++ b/sound/soc/codecs/adau-utils.h
@@ -0,0 +1,7 @@
+#ifndef SOUND_SOC_CODECS_ADAU_PLL_H
+#define SOUND_SOC_CODECS_ADAU_PLL_H
+
+int adau_calc_pll_cfg(unsigned int freq_in, unsigned int freq_out,
+	uint8_t regs[5]);
+
+#endif
diff --git a/sound/soc/codecs/adau1373.c b/sound/soc/codecs/adau1373.c
index fe1353a797b9..1556b360fa15 100644
--- a/sound/soc/codecs/adau1373.c
+++ b/sound/soc/codecs/adau1373.c
@@ -23,6 +23,7 @@
 #include <sound/adau1373.h>
 
 #include "adau1373.h"
+#include "adau-utils.h"
 
 struct adau1373_dai {
 	unsigned int clk_src;
@@ -1254,7 +1255,8 @@ static int adau1373_set_pll(struct snd_soc_codec *codec, int pll_id,
 {
 	struct adau1373 *adau1373 = snd_soc_codec_get_drvdata(codec);
 	unsigned int dpll_div = 0;
-	unsigned int x, r, n, m, i, j, mode;
+	uint8_t pll_regs[5];
+	int ret;
 
 	switch (pll_id) {
 	case ADAU1373_PLL1:
@@ -1295,27 +1297,8 @@ static int adau1373_set_pll(struct snd_soc_codec *codec, int pll_id,
 		dpll_div++;
 	}
 
-	if (freq_out % freq_in != 0) {
-		/* fout = fin * (r + (n/m)) / x */
-		x = DIV_ROUND_UP(freq_in, 13500000);
-		freq_in /= x;
-		r = freq_out / freq_in;
-		i = freq_out % freq_in;
-		j = gcd(i, freq_in);
-		n = i / j;
-		m = freq_in / j;
-		x--;
-		mode = 1;
-	} else {
-		/* fout = fin / r */
-		r = freq_out / freq_in;
-		n = 0;
-		m = 0;
-		x = 0;
-		mode = 0;
-	}
-
-	if (r < 2 || r > 8 || x > 3 || m > 0xffff || n > 0xffff)
+	ret = adau_calc_pll_cfg(freq_in, freq_out, pll_regs);
+	if (ret)
 		return -EINVAL;
 
 	if (dpll_div) {
@@ -1330,12 +1313,11 @@ static int adau1373_set_pll(struct snd_soc_codec *codec, int pll_id,
 
 	regmap_write(adau1373->regmap, ADAU1373_DPLL_CTRL(pll_id),
 		(source << 4) | dpll_div);
-	regmap_write(adau1373->regmap, ADAU1373_PLL_CTRL1(pll_id), (m >> 8) & 0xff);
-	regmap_write(adau1373->regmap, ADAU1373_PLL_CTRL2(pll_id), m & 0xff);
-	regmap_write(adau1373->regmap, ADAU1373_PLL_CTRL3(pll_id), (n >> 8) & 0xff);
-	regmap_write(adau1373->regmap, ADAU1373_PLL_CTRL4(pll_id), n & 0xff);
-	regmap_write(adau1373->regmap, ADAU1373_PLL_CTRL5(pll_id),
-		(r << 3) | (x << 1) | mode);
+	regmap_write(adau1373->regmap, ADAU1373_PLL_CTRL1(pll_id), pll_regs[0]);
+	regmap_write(adau1373->regmap, ADAU1373_PLL_CTRL2(pll_id), pll_regs[1]);
+	regmap_write(adau1373->regmap, ADAU1373_PLL_CTRL3(pll_id), pll_regs[2]);
+	regmap_write(adau1373->regmap, ADAU1373_PLL_CTRL4(pll_id), pll_regs[3]);
+	regmap_write(adau1373->regmap, ADAU1373_PLL_CTRL5(pll_id), pll_regs[4]);
 
 	/* Set sysclk to pll_rate / 4 */
 	regmap_update_bits(adau1373->regmap, ADAU1373_CLK_SRC_DIV(pll_id), 0x3f, 0x09);
diff --git a/sound/soc/codecs/adau1761-i2c.c b/sound/soc/codecs/adau1761-i2c.c
index 8de010f758cd..9e7f257f17f8 100644
--- a/sound/soc/codecs/adau1761-i2c.c
+++ b/sound/soc/codecs/adau1761-i2c.c
@@ -31,7 +31,7 @@ static int adau1761_i2c_probe(struct i2c_client *client,
 
 static int adau1761_i2c_remove(struct i2c_client *client)
 {
-	snd_soc_unregister_codec(&client->dev);
+	adau17x1_remove(&client->dev);
 	return 0;
 }
 
diff --git a/sound/soc/codecs/adau1761-spi.c b/sound/soc/codecs/adau1761-spi.c
index d9171245bd9f..a0b214be759a 100644
--- a/sound/soc/codecs/adau1761-spi.c
+++ b/sound/soc/codecs/adau1761-spi.c
@@ -48,7 +48,7 @@ static int adau1761_spi_probe(struct spi_device *spi)
 
 static int adau1761_spi_remove(struct spi_device *spi)
 {
-	snd_soc_unregister_codec(&spi->dev);
+	adau17x1_remove(&spi->dev);
 	return 0;
 }
 
diff --git a/sound/soc/codecs/adau1781-i2c.c b/sound/soc/codecs/adau1781-i2c.c
index 06cbca84cf02..7b9d1802d159 100644
--- a/sound/soc/codecs/adau1781-i2c.c
+++ b/sound/soc/codecs/adau1781-i2c.c
@@ -31,7 +31,7 @@ static int adau1781_i2c_probe(struct i2c_client *client,
 
 static int adau1781_i2c_remove(struct i2c_client *client)
 {
-	snd_soc_unregister_codec(&client->dev);
+	adau17x1_remove(&client->dev);
 	return 0;
 }
 
diff --git a/sound/soc/codecs/adau1781-spi.c b/sound/soc/codecs/adau1781-spi.c
index 3d965a01b99c..9b233544d2e8 100644
--- a/sound/soc/codecs/adau1781-spi.c
+++ b/sound/soc/codecs/adau1781-spi.c
@@ -48,7 +48,7 @@ static int adau1781_spi_probe(struct spi_device *spi)
 
 static int adau1781_spi_remove(struct spi_device *spi)
 {
-	snd_soc_unregister_codec(&spi->dev);
+	adau17x1_remove(&spi->dev);
 	return 0;
 }
 
diff --git a/sound/soc/codecs/adau17x1.c b/sound/soc/codecs/adau17x1.c
index fcf05b254ecd..439aa3ff1f99 100644
--- a/sound/soc/codecs/adau17x1.c
+++ b/sound/soc/codecs/adau17x1.c
@@ -9,6 +9,7 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <sound/core.h>
@@ -23,6 +24,7 @@
 
 #include "sigmadsp.h"
 #include "adau17x1.h"
+#include "adau-utils.h"
 
 static const char * const adau17x1_capture_mixer_boost_text[] = {
 	"Normal operation", "Boost Level 1", "Boost Level 2", "Boost Level 3",
@@ -302,6 +304,116 @@ bool adau17x1_has_dsp(struct adau *adau)
 }
 EXPORT_SYMBOL_GPL(adau17x1_has_dsp);
 
+static int adau17x1_set_dai_pll(struct snd_soc_dai *dai, int pll_id,
+	int source, unsigned int freq_in, unsigned int freq_out)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	struct adau *adau = snd_soc_codec_get_drvdata(codec);
+	int ret;
+
+	if (freq_in < 8000000 || freq_in > 27000000)
+		return -EINVAL;
+
+	ret = adau_calc_pll_cfg(freq_in, freq_out, adau->pll_regs);
+	if (ret < 0)
+		return ret;
+
+	/* The PLL register is 6 bytes long and can only be written at once. */
+	ret = regmap_raw_write(adau->regmap, ADAU17X1_PLL_CONTROL,
+			adau->pll_regs, ARRAY_SIZE(adau->pll_regs));
+	if (ret)
+		return ret;
+
+	adau->pll_freq = freq_out;
+
+	return 0;
+}
+
+static int adau17x1_set_dai_sysclk(struct snd_soc_dai *dai,
+		int clk_id, unsigned int freq, int dir)
+{
+	struct snd_soc_dapm_context *dapm = snd_soc_codec_get_dapm(dai->codec);
+	struct adau *adau = snd_soc_codec_get_drvdata(dai->codec);
+	bool is_pll;
+	bool was_pll;
+
+	switch (clk_id) {
+	case ADAU17X1_CLK_SRC_MCLK:
+		is_pll = false;
+		break;
+	case ADAU17X1_CLK_SRC_PLL_AUTO:
+		if (!adau->mclk)
+			return -EINVAL;
+		/* Fall-through */
+	case ADAU17X1_CLK_SRC_PLL:
+		is_pll = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (adau->clk_src) {
+	case ADAU17X1_CLK_SRC_MCLK:
+		was_pll = false;
+		break;
+	case ADAU17X1_CLK_SRC_PLL:
+	case ADAU17X1_CLK_SRC_PLL_AUTO:
+		was_pll = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	adau->sysclk = freq;
+
+	if (is_pll != was_pll) {
+		if (is_pll) {
+			snd_soc_dapm_add_routes(dapm,
+				&adau17x1_dapm_pll_route, 1);
+		} else {
+			snd_soc_dapm_del_routes(dapm,
+				&adau17x1_dapm_pll_route, 1);
+		}
+	}
+
+	adau->clk_src = clk_id;
+
+	return 0;
+}
+
+static int adau17x1_auto_pll(struct snd_soc_dai *dai,
+	struct snd_pcm_hw_params *params)
+{
+	struct adau *adau = snd_soc_dai_get_drvdata(dai);
+	unsigned int pll_rate;
+
+	switch (params_rate(params)) {
+	case 48000:
+	case 8000:
+	case 12000:
+	case 16000:
+	case 24000:
+	case 32000:
+	case 96000:
+		pll_rate = 48000 * 1024;
+		break;
+	case 44100:
+	case 7350:
+	case 11025:
+	case 14700:
+	case 22050:
+	case 29400:
+	case 88200:
+		pll_rate = 44100 * 1024;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return adau17x1_set_dai_pll(dai, ADAU17X1_PLL, ADAU17X1_PLL_SRC_MCLK,
+		clk_get_rate(adau->mclk), pll_rate);
+}
+
 static int adau17x1_hw_params(struct snd_pcm_substream *substream,
 	struct snd_pcm_hw_params *params, struct snd_soc_dai *dai)
 {
@@ -311,10 +423,19 @@ static int adau17x1_hw_params(struct snd_pcm_substream *substream,
 	unsigned int freq;
 	int ret;
 
-	if (adau->clk_src == ADAU17X1_CLK_SRC_PLL)
+	switch (adau->clk_src) {
+	case ADAU17X1_CLK_SRC_PLL_AUTO:
+		ret = adau17x1_auto_pll(dai, params);
+		if (ret)
+			return ret;
+		/* Fall-through */
+	case ADAU17X1_CLK_SRC_PLL:
 		freq = adau->pll_freq;
-	else
+		break;
+	default:
 		freq = adau->sysclk;
+		break;
+	}
 
 	if (freq % params_rate(params) != 0)
 		return -EINVAL;
@@ -386,93 +507,6 @@ static int adau17x1_hw_params(struct snd_pcm_substream *substream,
 			ADAU17X1_SERIAL_PORT1_DELAY_MASK, val);
 }
 
-static int adau17x1_set_dai_pll(struct snd_soc_dai *dai, int pll_id,
-	int source, unsigned int freq_in, unsigned int freq_out)
-{
-	struct snd_soc_codec *codec = dai->codec;
-	struct adau *adau = snd_soc_codec_get_drvdata(codec);
-	unsigned int r, n, m, i, j;
-	unsigned int div;
-	int ret;
-
-	if (freq_in < 8000000 || freq_in > 27000000)
-		return -EINVAL;
-
-	if (!freq_out) {
-		r = 0;
-		n = 0;
-		m = 0;
-		div = 0;
-	} else {
-		if (freq_out % freq_in != 0) {
-			div = DIV_ROUND_UP(freq_in, 13500000);
-			freq_in /= div;
-			r = freq_out / freq_in;
-			i = freq_out % freq_in;
-			j = gcd(i, freq_in);
-			n = i / j;
-			m = freq_in / j;
-			div--;
-		} else {
-			r = freq_out / freq_in;
-			n = 0;
-			m = 0;
-			div = 0;
-		}
-		if (n > 0xffff || m > 0xffff || div > 3 || r > 8 || r < 2)
-			return -EINVAL;
-	}
-
-	adau->pll_regs[0] = m >> 8;
-	adau->pll_regs[1] = m & 0xff;
-	adau->pll_regs[2] = n >> 8;
-	adau->pll_regs[3] = n & 0xff;
-	adau->pll_regs[4] = (r << 3) | (div << 1);
-	if (m != 0)
-		adau->pll_regs[4] |= 1; /* Fractional mode */
-
-	/* The PLL register is 6 bytes long and can only be written at once. */
-	ret = regmap_raw_write(adau->regmap, ADAU17X1_PLL_CONTROL,
-			adau->pll_regs, ARRAY_SIZE(adau->pll_regs));
-	if (ret)
-		return ret;
-
-	adau->pll_freq = freq_out;
-
-	return 0;
-}
-
-static int adau17x1_set_dai_sysclk(struct snd_soc_dai *dai,
-		int clk_id, unsigned int freq, int dir)
-{
-	struct snd_soc_dapm_context *dapm = snd_soc_codec_get_dapm(dai->codec);
-	struct adau *adau = snd_soc_codec_get_drvdata(dai->codec);
-
-	switch (clk_id) {
-	case ADAU17X1_CLK_SRC_MCLK:
-	case ADAU17X1_CLK_SRC_PLL:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	adau->sysclk = freq;
-
-	if (adau->clk_src != clk_id) {
-		if (clk_id == ADAU17X1_CLK_SRC_PLL) {
-			snd_soc_dapm_add_routes(dapm,
-				&adau17x1_dapm_pll_route, 1);
-		} else {
-			snd_soc_dapm_del_routes(dapm,
-				&adau17x1_dapm_pll_route, 1);
-		}
-	}
-
-	adau->clk_src = clk_id;
-
-	return 0;
-}
-
 static int adau17x1_set_dai_fmt(struct snd_soc_dai *dai,
 		unsigned int fmt)
 {
@@ -857,6 +891,10 @@ int adau17x1_add_routes(struct snd_soc_codec *codec)
 		ret = snd_soc_dapm_add_routes(dapm, adau17x1_no_dsp_dapm_routes,
 			ARRAY_SIZE(adau17x1_no_dsp_dapm_routes));
 	}
+
+	if (adau->clk_src != ADAU17X1_CLK_SRC_MCLK)
+		snd_soc_dapm_add_routes(dapm, &adau17x1_dapm_pll_route, 1);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(adau17x1_add_routes);
@@ -879,6 +917,7 @@ int adau17x1_probe(struct device *dev, struct regmap *regmap,
 	const char *firmware_name)
 {
 	struct adau *adau;
+	int ret;
 
 	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
@@ -887,6 +926,30 @@ int adau17x1_probe(struct device *dev, struct regmap *regmap,
 	if (!adau)
 		return -ENOMEM;
 
+	adau->mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(adau->mclk)) {
+		if (PTR_ERR(adau->mclk) != -ENOENT)
+			return PTR_ERR(adau->mclk);
+		/* Clock is optional (for the driver) */
+		adau->mclk = NULL;
+	} else if (adau->mclk) {
+		adau->clk_src = ADAU17X1_CLK_SRC_PLL_AUTO;
+
+		/*
+		 * Any valid PLL output rate will work at this point, use one
+		 * that is likely to be chosen later as well. The register will
+		 * be written when the PLL is powered up for the first time.
+		 */
+		ret = adau_calc_pll_cfg(clk_get_rate(adau->mclk), 48000 * 1024,
+				adau->pll_regs);
+		if (ret < 0)
+			return ret;
+
+		ret = clk_prepare_enable(adau->mclk);
+		if (ret)
+			return ret;
+	}
+
 	adau->regmap = regmap;
 	adau->switch_mode = switch_mode;
 	adau->type = type;
@@ -910,6 +973,16 @@ int adau17x1_probe(struct device *dev, struct regmap *regmap,
 }
 EXPORT_SYMBOL_GPL(adau17x1_probe);
 
+void adau17x1_remove(struct device *dev)
+{
+	struct adau *adau = dev_get_drvdata(dev);
+
+	snd_soc_unregister_codec(dev);
+	if (adau->mclk)
+		clk_disable_unprepare(adau->mclk);
+}
+EXPORT_SYMBOL_GPL(adau17x1_remove);
+
 MODULE_DESCRIPTION("ASoC ADAU1X61/ADAU1X81 common code");
 MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
 MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/adau17x1.h b/sound/soc/codecs/adau17x1.h
index 5ae87a084d97..bf04b7efee40 100644
--- a/sound/soc/codecs/adau17x1.h
+++ b/sound/soc/codecs/adau17x1.h
@@ -22,13 +22,18 @@ enum adau17x1_pll_src {
 };
 
 enum adau17x1_clk_src {
+	/* Automatically configure PLL based on the sample rate */
+	ADAU17X1_CLK_SRC_PLL_AUTO,
 	ADAU17X1_CLK_SRC_MCLK,
 	ADAU17X1_CLK_SRC_PLL,
 };
 
+struct clk;
+
 struct adau {
 	unsigned int sysclk;
 	unsigned int pll_freq;
+	struct clk *mclk;
 
 	enum adau17x1_clk_src clk_src;
 	enum adau17x1_type type;
@@ -52,6 +57,7 @@ int adau17x1_add_routes(struct snd_soc_codec *codec);
 int adau17x1_probe(struct device *dev, struct regmap *regmap,
 	enum adau17x1_type type, void (*switch_mode)(struct device *dev),
 	const char *firmware_name);
+void adau17x1_remove(struct device *dev);
 int adau17x1_set_micbias_voltage(struct snd_soc_codec *codec,
 	enum adau17x1_micbias_voltage micbias);
 bool adau17x1_readable_register(struct device *dev, unsigned int reg);
diff --git a/sound/soc/codecs/adau7002.c b/sound/soc/codecs/adau7002.c
new file mode 100644
index 000000000000..9df72c6adcca
--- /dev/null
+++ b/sound/soc/codecs/adau7002.c
@@ -0,0 +1,80 @@
+/*
+ * ADAU7002 Stereo PDM-to-I2S/TDM converter driver
+ *
+ * Copyright 2014-2016 Analog Devices
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include <sound/soc.h>
+
+static const struct snd_soc_dapm_widget adau7002_widgets[] = {
+	SND_SOC_DAPM_INPUT("PDM_DAT"),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("IOVDD", 0, 0),
+};
+
+static const struct snd_soc_dapm_route adau7002_routes[] = {
+	{ "Capture", NULL, "PDM_DAT" },
+	{ "Capture", NULL, "IOVDD" },
+};
+
+static struct snd_soc_dai_driver adau7002_dai = {
+	.name = "adau7002-hifi",
+	.capture = {
+		.stream_name = "Capture",
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = SNDRV_PCM_RATE_8000_96000,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S18_3LE |
+			SNDRV_PCM_FMTBIT_S20_3LE | SNDRV_PCM_FMTBIT_S24_LE |
+			SNDRV_PCM_FMTBIT_S24_3LE | SNDRV_PCM_FMTBIT_S32_LE,
+		.sig_bits = 20,
+	},
+};
+
+static const struct snd_soc_codec_driver adau7002_codec_driver = {
+	.dapm_widgets = adau7002_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(adau7002_widgets),
+	.dapm_routes = adau7002_routes,
+	.num_dapm_routes = ARRAY_SIZE(adau7002_routes),
+};
+
+static int adau7002_probe(struct platform_device *pdev)
+{
+	return snd_soc_register_codec(&pdev->dev, &adau7002_codec_driver,
+			&adau7002_dai, 1);
+}
+
+static int adau7002_remove(struct platform_device *pdev)
+{
+	snd_soc_unregister_codec(&pdev->dev);
+	return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id adau7002_dt_ids[] = {
+	{ .compatible = "adi,adau7002", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, adau7002_dt_ids);
+#endif
+
+static struct platform_driver adau7002_driver = {
+	.driver = {
+		.name = "adau7002",
+		.of_match_table	= of_match_ptr(adau7002_dt_ids),
+	},
+	.probe = adau7002_probe,
+	.remove = adau7002_remove,
+};
+module_platform_driver(adau7002_driver);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("ADAU7002 Stereo PDM-to-I2S/TDM Converter driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/ak4613.c b/sound/soc/codecs/ak4613.c
index 5013d2ba0c10..97798d250f08 100644
--- a/sound/soc/codecs/ak4613.c
+++ b/sound/soc/codecs/ak4613.c
@@ -437,15 +437,25 @@ static struct snd_soc_dai_driver ak4613_dai = {
 	.symmetric_rates = 1,
 };
 
-static int ak4613_resume(struct snd_soc_codec *codec)
+static int ak4613_suspend(struct snd_soc_codec *codec)
 {
 	struct regmap *regmap = dev_get_regmap(codec->dev, NULL);
 
+	regcache_cache_only(regmap, true);
 	regcache_mark_dirty(regmap);
+	return 0;
+}
+
+static int ak4613_resume(struct snd_soc_codec *codec)
+{
+	struct regmap *regmap = dev_get_regmap(codec->dev, NULL);
+
+	regcache_cache_only(regmap, false);
 	return regcache_sync(regmap);
 }
 
 static struct snd_soc_codec_driver soc_codec_dev_ak4613 = {
+	.suspend		= ak4613_suspend,
 	.resume			= ak4613_resume,
 	.set_bias_level		= ak4613_set_bias_level,
 	.controls		= ak4613_snd_controls,
diff --git a/sound/soc/codecs/ak4642.c b/sound/soc/codecs/ak4642.c
index 4d8b9e49e8d6..cc941d66ec3d 100644
--- a/sound/soc/codecs/ak4642.c
+++ b/sound/soc/codecs/ak4642.c
@@ -523,15 +523,23 @@ static struct snd_soc_dai_driver ak4642_dai = {
 	.symmetric_rates = 1,
 };
 
-static int ak4642_resume(struct snd_soc_codec *codec)
+static int ak4642_suspend(struct snd_soc_codec *codec)
 {
 	struct regmap *regmap = dev_get_regmap(codec->dev, NULL);
 
+	regcache_cache_only(regmap, true);
 	regcache_mark_dirty(regmap);
-	regcache_sync(regmap);
 	return 0;
 }
 
+static int ak4642_resume(struct snd_soc_codec *codec)
+{
+	struct regmap *regmap = dev_get_regmap(codec->dev, NULL);
+
+	regcache_cache_only(regmap, false);
+	regcache_sync(regmap);
+	return 0;
+}
 static int ak4642_probe(struct snd_soc_codec *codec)
 {
 	struct ak4642_priv *priv = snd_soc_codec_get_drvdata(codec);
@@ -544,6 +552,7 @@ static int ak4642_probe(struct snd_soc_codec *codec)
 
 static struct snd_soc_codec_driver soc_codec_dev_ak4642 = {
 	.probe			= ak4642_probe,
+	.suspend		= ak4642_suspend,
 	.resume			= ak4642_resume,
 	.set_bias_level		= ak4642_set_bias_level,
 	.controls		= ak4642_snd_controls,
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 664a8c044ffb..ecfdbfcae366 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -85,30 +85,9 @@ static int arizona_spk_ev(struct snd_soc_dapm_widget *w,
 {
 	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
 	struct arizona *arizona = dev_get_drvdata(codec->dev->parent);
-	struct arizona_priv *priv = snd_soc_codec_get_drvdata(codec);
-	bool manual_ena = false;
 	int val;
 
-	switch (arizona->type) {
-	case WM5102:
-		switch (arizona->rev) {
-		case 0:
-			break;
-		default:
-			manual_ena = true;
-			break;
-		}
-	default:
-		break;
-	}
-
 	switch (event) {
-	case SND_SOC_DAPM_PRE_PMU:
-		if (!priv->spk_ena && manual_ena) {
-			regmap_write_async(arizona->regmap, 0x4f5, 0x25a);
-			priv->spk_ena_pending = true;
-		}
-		break;
 	case SND_SOC_DAPM_POST_PMU:
 		val = snd_soc_read(codec, ARIZONA_INTERRUPT_RAW_STATUS_3);
 		if (val & ARIZONA_SPK_OVERHEAT_STS) {
@@ -120,33 +99,12 @@ static int arizona_spk_ev(struct snd_soc_dapm_widget *w,
 		regmap_update_bits_async(arizona->regmap,
 					 ARIZONA_OUTPUT_ENABLES_1,
 					 1 << w->shift, 1 << w->shift);
-
-		if (priv->spk_ena_pending) {
-			msleep(75);
-			regmap_write_async(arizona->regmap, 0x4f5, 0xda);
-			priv->spk_ena_pending = false;
-			priv->spk_ena++;
-		}
 		break;
 	case SND_SOC_DAPM_PRE_PMD:
-		if (manual_ena) {
-			priv->spk_ena--;
-			if (!priv->spk_ena)
-				regmap_write_async(arizona->regmap,
-						   0x4f5, 0x25a);
-		}
-
 		regmap_update_bits_async(arizona->regmap,
 					 ARIZONA_OUTPUT_ENABLES_1,
 					 1 << w->shift, 0);
 		break;
-	case SND_SOC_DAPM_POST_PMD:
-		if (manual_ena) {
-			if (!priv->spk_ena)
-				regmap_write_async(arizona->regmap,
-						   0x4f5, 0x0da);
-		}
-		break;
 	default:
 		break;
 	}
@@ -324,6 +282,17 @@ int arizona_init_gpio(struct snd_soc_codec *codec)
 }
 EXPORT_SYMBOL_GPL(arizona_init_gpio);
 
+int arizona_init_notifiers(struct snd_soc_codec *codec)
+{
+	struct arizona_priv *priv = snd_soc_codec_get_drvdata(codec);
+	struct arizona *arizona = priv->arizona;
+
+	BLOCKING_INIT_NOTIFIER_HEAD(&arizona->notifier);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(arizona_init_notifiers);
+
 const char * const arizona_mixer_texts[ARIZONA_NUM_MIXER_INPUTS] = {
 	"None",
 	"Tone Generator 1",
@@ -619,7 +588,7 @@ const struct soc_enum arizona_asrc_rate1 =
 			      arizona_rate_text, arizona_rate_val);
 EXPORT_SYMBOL_GPL(arizona_asrc_rate1);
 
-static const char *arizona_vol_ramp_text[] = {
+static const char * const arizona_vol_ramp_text[] = {
 	"0ms/6dB", "0.5ms/6dB", "1ms/6dB", "2ms/6dB", "4ms/6dB", "8ms/6dB",
 	"15ms/6dB", "30ms/6dB",
 };
@@ -648,7 +617,7 @@ SOC_ENUM_SINGLE_DECL(arizona_out_vi_ramp,
 		     arizona_vol_ramp_text);
 EXPORT_SYMBOL_GPL(arizona_out_vi_ramp);
 
-static const char *arizona_lhpf_mode_text[] = {
+static const char * const arizona_lhpf_mode_text[] = {
 	"Low-pass", "High-pass"
 };
 
@@ -676,7 +645,7 @@ SOC_ENUM_SINGLE_DECL(arizona_lhpf4_mode,
 		     arizona_lhpf_mode_text);
 EXPORT_SYMBOL_GPL(arizona_lhpf4_mode);
 
-static const char *arizona_ng_hold_text[] = {
+static const char * const arizona_ng_hold_text[] = {
 	"30ms", "120ms", "250ms", "500ms",
 };
 
@@ -810,6 +779,14 @@ const struct soc_enum arizona_output_anc_src[] = {
 };
 EXPORT_SYMBOL_GPL(arizona_output_anc_src);
 
+const struct snd_kcontrol_new arizona_voice_trigger_switch[] = {
+	SOC_DAPM_SINGLE("Switch", SND_SOC_NOPM, 0, 1, 0),
+	SOC_DAPM_SINGLE("Switch", SND_SOC_NOPM, 1, 1, 0),
+	SOC_DAPM_SINGLE("Switch", SND_SOC_NOPM, 2, 1, 0),
+	SOC_DAPM_SINGLE("Switch", SND_SOC_NOPM, 3, 1, 0),
+};
+EXPORT_SYMBOL_GPL(arizona_voice_trigger_switch);
+
 static void arizona_in_set_vu(struct snd_soc_codec *codec, int ena)
 {
 	struct arizona_priv *priv = snd_soc_codec_get_drvdata(codec);
@@ -2573,6 +2550,30 @@ int arizona_lhpf_coeff_put(struct snd_kcontrol *kcontrol,
 }
 EXPORT_SYMBOL_GPL(arizona_lhpf_coeff_put);
 
+int arizona_register_notifier(struct snd_soc_codec *codec,
+			      struct notifier_block *nb,
+			      int (*notify)(struct notifier_block *nb,
+					    unsigned long action, void *data))
+{
+	struct arizona_priv *priv = snd_soc_codec_get_drvdata(codec);
+	struct arizona *arizona = priv->arizona;
+
+	nb->notifier_call = notify;
+
+	return blocking_notifier_chain_register(&arizona->notifier, nb);
+}
+EXPORT_SYMBOL_GPL(arizona_register_notifier);
+
+int arizona_unregister_notifier(struct snd_soc_codec *codec,
+				struct notifier_block *nb)
+{
+	struct arizona_priv *priv = snd_soc_codec_get_drvdata(codec);
+	struct arizona *arizona = priv->arizona;
+
+	return blocking_notifier_chain_unregister(&arizona->notifier, nb);
+}
+EXPORT_SYMBOL_GPL(arizona_unregister_notifier);
+
 MODULE_DESCRIPTION("ASoC Wolfson Arizona class device support");
 MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>");
 MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/arizona.h b/sound/soc/codecs/arizona.h
index ce0531b8c632..69da1ef3a17c 100644
--- a/sound/soc/codecs/arizona.h
+++ b/sound/soc/codecs/arizona.h
@@ -63,6 +63,9 @@
 #define ARIZONA_DVFS_SR1_RQ	0x001
 #define ARIZONA_DVFS_ADSP1_RQ	0x100
 
+/* Notifier events */
+#define ARIZONA_NOTIFY_VOICE_TRIGGER   0x1
+
 struct arizona;
 struct wm_adsp;
 
@@ -87,14 +90,15 @@ struct arizona_priv {
 	unsigned int out_down_pending;
 	unsigned int out_down_delay;
 
-	unsigned int spk_ena:2;
-	unsigned int spk_ena_pending:1;
-
 	unsigned int dvfs_reqs;
 	struct mutex dvfs_lock;
 	bool dvfs_cached;
 };
 
+struct arizona_voice_trigger_info {
+	int core;
+};
+
 #define ARIZONA_NUM_MIXER_INPUTS 104
 
 extern const unsigned int arizona_mixer_tlv[];
@@ -248,6 +252,8 @@ extern const struct soc_enum arizona_anc_input_src[];
 extern const struct soc_enum arizona_anc_ng_enum;
 extern const struct soc_enum arizona_output_anc_src[];
 
+extern const struct snd_kcontrol_new arizona_voice_trigger_switch[];
+
 extern int arizona_in_ev(struct snd_soc_dapm_widget *w,
 			 struct snd_kcontrol *kcontrol,
 			 int event);
@@ -306,6 +312,7 @@ extern int arizona_set_fll(struct arizona_fll *fll, int source,
 extern int arizona_init_spk(struct snd_soc_codec *codec);
 extern int arizona_init_gpio(struct snd_soc_codec *codec);
 extern int arizona_init_mono(struct snd_soc_codec *codec);
+extern int arizona_init_notifiers(struct snd_soc_codec *codec);
 
 extern int arizona_free_spk(struct snd_soc_codec *codec);
 
@@ -317,4 +324,13 @@ int arizona_set_output_mode(struct snd_soc_codec *codec, int output,
 extern bool arizona_input_analog(struct snd_soc_codec *codec, int shift);
 
 extern const char *arizona_sample_rate_val_to_name(unsigned int rate_val);
+
+extern int arizona_register_notifier(struct snd_soc_codec *codec,
+				     struct notifier_block *nb,
+				     int (*notify)(struct notifier_block *nb,
+						   unsigned long action,
+						   void *data));
+extern int arizona_unregister_notifier(struct snd_soc_codec *codec,
+				       struct notifier_block *nb);
+
 #endif
diff --git a/sound/soc/codecs/bt-sco.c b/sound/soc/codecs/bt-sco.c
index b084ad113e96..2a8d0ee141d4 100644
--- a/sound/soc/codecs/bt-sco.c
+++ b/sound/soc/codecs/bt-sco.c
@@ -25,22 +25,41 @@ static const struct snd_soc_dapm_route bt_sco_routes[] = {
 	{ "TX", NULL, "Playback" },
 };
 
-static struct snd_soc_dai_driver bt_sco_dai = {
-	.name = "bt-sco-pcm",
-	.playback = {
-		.stream_name = "Playback",
-		.channels_min = 1,
-		.channels_max = 1,
-		.rates = SNDRV_PCM_RATE_8000,
-		.formats = SNDRV_PCM_FMTBIT_S16_LE,
-	},
-	.capture = {
-		 .stream_name = "Capture",
-		.channels_min = 1,
-		.channels_max = 1,
-		.rates = SNDRV_PCM_RATE_8000,
-		.formats = SNDRV_PCM_FMTBIT_S16_LE,
+static struct snd_soc_dai_driver bt_sco_dai[] = {
+	{
+		.name = "bt-sco-pcm",
+		.playback = {
+			.stream_name = "Playback",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = SNDRV_PCM_RATE_8000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		},
+		.capture = {
+			 .stream_name = "Capture",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = SNDRV_PCM_RATE_8000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		},
 	},
+	{
+		.name = "bt-sco-pcm-wb",
+		.playback = {
+			.stream_name = "Playback",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		},
+		.capture = {
+			 .stream_name = "Capture",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		},
+	}
 };
 
 static struct snd_soc_codec_driver soc_codec_dev_bt_sco = {
@@ -53,7 +72,7 @@ static struct snd_soc_codec_driver soc_codec_dev_bt_sco = {
 static int bt_sco_probe(struct platform_device *pdev)
 {
 	return snd_soc_register_codec(&pdev->dev, &soc_codec_dev_bt_sco,
-			&bt_sco_dai, 1);
+				      bt_sco_dai, ARRAY_SIZE(bt_sco_dai));
 }
 
 static int bt_sco_remove(struct platform_device *pdev)
@@ -77,6 +96,7 @@ MODULE_DEVICE_TABLE(platform, bt_sco_driver_ids);
 #if defined(CONFIG_OF)
 static const struct of_device_id bt_sco_codec_of_match[] = {
 	{ .compatible = "delta,dfbmcs320", },
+	{ .compatible = "linux,bt-sco", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, bt_sco_codec_of_match);
diff --git a/sound/soc/codecs/cs35l33.c b/sound/soc/codecs/cs35l33.c
new file mode 100644
index 000000000000..6f9c1addcd7f
--- /dev/null
+++ b/sound/soc/codecs/cs35l33.c
@@ -0,0 +1,1303 @@
+/*
+ * cs35l33.c -- CS35L33 ALSA SoC audio driver
+ *
+ * Copyright 2016 Cirrus Logic, Inc.
+ *
+ * Author: Paul Handrigan <paul.handrigan@cirrus.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/platform_device.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/initval.h>
+#include <sound/tlv.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
+#include <sound/cs35l33.h>
+#include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
+#include <linux/regulator/machine.h>
+#include <linux/of_gpio.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+
+#include "cs35l33.h"
+
+#define CS35L33_BOOT_DELAY	50
+
+struct cs35l33_private {
+	struct snd_soc_codec *codec;
+	struct cs35l33_pdata pdata;
+	struct regmap *regmap;
+	struct gpio_desc *reset_gpio;
+	bool amp_cal;
+	int mclk_int;
+	struct regulator_bulk_data core_supplies[2];
+	int num_core_supplies;
+	bool is_tdm_mode;
+	bool enable_soft_ramp;
+};
+
+static const struct reg_default cs35l33_reg[] = {
+	{CS35L33_PWRCTL1, 0x85},
+	{CS35L33_PWRCTL2, 0xFE},
+	{CS35L33_CLK_CTL, 0x0C},
+	{CS35L33_BST_PEAK_CTL, 0x90},
+	{CS35L33_PROTECT_CTL, 0x55},
+	{CS35L33_BST_CTL1, 0x00},
+	{CS35L33_BST_CTL2, 0x01},
+	{CS35L33_ADSP_CTL, 0x00},
+	{CS35L33_ADC_CTL, 0xC8},
+	{CS35L33_DAC_CTL, 0x14},
+	{CS35L33_DIG_VOL_CTL, 0x00},
+	{CS35L33_CLASSD_CTL, 0x04},
+	{CS35L33_AMP_CTL, 0x90},
+	{CS35L33_INT_MASK_1, 0xFF},
+	{CS35L33_INT_MASK_2, 0xFF},
+	{CS35L33_DIAG_LOCK, 0x00},
+	{CS35L33_DIAG_CTRL_1, 0x40},
+	{CS35L33_DIAG_CTRL_2, 0x00},
+	{CS35L33_HG_MEMLDO_CTL, 0x62},
+	{CS35L33_HG_REL_RATE, 0x03},
+	{CS35L33_LDO_DEL, 0x12},
+	{CS35L33_HG_HEAD, 0x0A},
+	{CS35L33_HG_EN, 0x05},
+	{CS35L33_TX_VMON, 0x00},
+	{CS35L33_TX_IMON, 0x03},
+	{CS35L33_TX_VPMON, 0x02},
+	{CS35L33_TX_VBSTMON, 0x05},
+	{CS35L33_TX_FLAG, 0x06},
+	{CS35L33_TX_EN1, 0x00},
+	{CS35L33_TX_EN2, 0x00},
+	{CS35L33_TX_EN3, 0x00},
+	{CS35L33_TX_EN4, 0x00},
+	{CS35L33_RX_AUD, 0x40},
+	{CS35L33_RX_SPLY, 0x03},
+	{CS35L33_RX_ALIVE, 0x04},
+	{CS35L33_BST_CTL4, 0x63},
+};
+
+static const struct reg_sequence cs35l33_patch[] = {
+	{ 0x00,  0x99, 0 },
+	{ 0x59,  0x02, 0 },
+	{ 0x52,  0x30, 0 },
+	{ 0x39,  0x45, 0 },
+	{ 0x57,  0x30, 0 },
+	{ 0x2C,  0x68, 0 },
+	{ 0x00,  0x00, 0 },
+};
+
+static bool cs35l33_volatile_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case CS35L33_DEVID_AB:
+	case CS35L33_DEVID_CD:
+	case CS35L33_DEVID_E:
+	case CS35L33_REV_ID:
+	case CS35L33_INT_STATUS_1:
+	case CS35L33_INT_STATUS_2:
+	case CS35L33_HG_STATUS:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool cs35l33_writeable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	/* these are read only registers */
+	case CS35L33_DEVID_AB:
+	case CS35L33_DEVID_CD:
+	case CS35L33_DEVID_E:
+	case CS35L33_REV_ID:
+	case CS35L33_INT_STATUS_1:
+	case CS35L33_INT_STATUS_2:
+	case CS35L33_HG_STATUS:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static bool cs35l33_readable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case CS35L33_DEVID_AB:
+	case CS35L33_DEVID_CD:
+	case CS35L33_DEVID_E:
+	case CS35L33_REV_ID:
+	case CS35L33_PWRCTL1:
+	case CS35L33_PWRCTL2:
+	case CS35L33_CLK_CTL:
+	case CS35L33_BST_PEAK_CTL:
+	case CS35L33_PROTECT_CTL:
+	case CS35L33_BST_CTL1:
+	case CS35L33_BST_CTL2:
+	case CS35L33_ADSP_CTL:
+	case CS35L33_ADC_CTL:
+	case CS35L33_DAC_CTL:
+	case CS35L33_DIG_VOL_CTL:
+	case CS35L33_CLASSD_CTL:
+	case CS35L33_AMP_CTL:
+	case CS35L33_INT_MASK_1:
+	case CS35L33_INT_MASK_2:
+	case CS35L33_INT_STATUS_1:
+	case CS35L33_INT_STATUS_2:
+	case CS35L33_DIAG_LOCK:
+	case CS35L33_DIAG_CTRL_1:
+	case CS35L33_DIAG_CTRL_2:
+	case CS35L33_HG_MEMLDO_CTL:
+	case CS35L33_HG_REL_RATE:
+	case CS35L33_LDO_DEL:
+	case CS35L33_HG_HEAD:
+	case CS35L33_HG_EN:
+	case CS35L33_TX_VMON:
+	case CS35L33_TX_IMON:
+	case CS35L33_TX_VPMON:
+	case CS35L33_TX_VBSTMON:
+	case CS35L33_TX_FLAG:
+	case CS35L33_TX_EN1:
+	case CS35L33_TX_EN2:
+	case CS35L33_TX_EN3:
+	case CS35L33_TX_EN4:
+	case CS35L33_RX_AUD:
+	case CS35L33_RX_SPLY:
+	case CS35L33_RX_ALIVE:
+	case CS35L33_BST_CTL4:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static DECLARE_TLV_DB_SCALE(classd_ctl_tlv, 900, 100, 0);
+static DECLARE_TLV_DB_SCALE(dac_tlv, -10200, 50, 0);
+
+static const struct snd_kcontrol_new cs35l33_snd_controls[] = {
+
+	SOC_SINGLE_TLV("SPK Amp Volume", CS35L33_AMP_CTL,
+		       4, 0x09, 0, classd_ctl_tlv),
+	SOC_SINGLE_SX_TLV("DAC Volume", CS35L33_DIG_VOL_CTL,
+			0, 0x34, 0xE4, dac_tlv),
+};
+
+static int cs35l33_spkrdrv_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
+	struct cs35l33_private *priv = snd_soc_codec_get_drvdata(codec);
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		if (!priv->amp_cal) {
+			usleep_range(8000, 9000);
+			priv->amp_cal = true;
+			regmap_update_bits(priv->regmap, CS35L33_CLASSD_CTL,
+				    CS35L33_AMP_CAL, 0);
+			dev_dbg(codec->dev, "Amp calibration done\n");
+		}
+		dev_dbg(codec->dev, "Amp turned on\n");
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		dev_dbg(codec->dev, "Amp turned off\n");
+		break;
+	default:
+		dev_err(codec->dev, "Invalid event = 0x%x\n", event);
+		break;
+	}
+
+	return 0;
+}
+
+static int cs35l33_sdin_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
+	struct cs35l33_private *priv = snd_soc_codec_get_drvdata(codec);
+	unsigned int val;
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		regmap_update_bits(priv->regmap, CS35L33_PWRCTL1,
+				    CS35L33_PDN_BST, 0);
+		val = priv->is_tdm_mode ? 0 : CS35L33_PDN_TDM;
+		regmap_update_bits(priv->regmap, CS35L33_PWRCTL2,
+				    CS35L33_PDN_TDM, val);
+		dev_dbg(codec->dev, "BST turned on\n");
+		break;
+	case SND_SOC_DAPM_POST_PMU:
+		dev_dbg(codec->dev, "SDIN turned on\n");
+		if (!priv->amp_cal) {
+			regmap_update_bits(priv->regmap, CS35L33_CLASSD_CTL,
+				    CS35L33_AMP_CAL, CS35L33_AMP_CAL);
+			dev_dbg(codec->dev, "Amp calibration started\n");
+			usleep_range(10000, 11000);
+		}
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		regmap_update_bits(priv->regmap, CS35L33_PWRCTL2,
+				    CS35L33_PDN_TDM, CS35L33_PDN_TDM);
+		usleep_range(4000, 4100);
+		regmap_update_bits(priv->regmap, CS35L33_PWRCTL1,
+				    CS35L33_PDN_BST, CS35L33_PDN_BST);
+		dev_dbg(codec->dev, "BST and SDIN turned off\n");
+		break;
+	default:
+		dev_err(codec->dev, "Invalid event = 0x%x\n", event);
+
+	}
+
+	return 0;
+}
+
+static int cs35l33_sdout_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
+	struct cs35l33_private *priv = snd_soc_codec_get_drvdata(codec);
+	unsigned int mask = CS35L33_SDOUT_3ST_I2S | CS35L33_PDN_TDM;
+	unsigned int mask2 = CS35L33_SDOUT_3ST_TDM;
+	unsigned int val, val2;
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		if (priv->is_tdm_mode) {
+			/* set sdout_3st_i2s and reset pdn_tdm */
+			val = CS35L33_SDOUT_3ST_I2S;
+			/* reset sdout_3st_tdm */
+			val2 = 0;
+		} else {
+			/* reset sdout_3st_i2s and set pdn_tdm */
+			val = CS35L33_PDN_TDM;
+			/* set sdout_3st_tdm */
+			val2 = CS35L33_SDOUT_3ST_TDM;
+		}
+		dev_dbg(codec->dev, "SDOUT turned on\n");
+		break;
+	case SND_SOC_DAPM_PRE_PMD:
+		val = CS35L33_SDOUT_3ST_I2S | CS35L33_PDN_TDM;
+		val2 = CS35L33_SDOUT_3ST_TDM;
+		dev_dbg(codec->dev, "SDOUT turned off\n");
+		break;
+	default:
+		dev_err(codec->dev, "Invalid event = 0x%x\n", event);
+		return 0;
+	}
+
+	regmap_update_bits(priv->regmap, CS35L33_PWRCTL2,
+		mask, val);
+	regmap_update_bits(priv->regmap, CS35L33_CLK_CTL,
+		mask2, val2);
+
+	return 0;
+}
+
+static const struct snd_soc_dapm_widget cs35l33_dapm_widgets[] = {
+
+	SND_SOC_DAPM_OUTPUT("SPK"),
+	SND_SOC_DAPM_OUT_DRV_E("SPKDRV", CS35L33_PWRCTL1, 7, 1, NULL, 0,
+		cs35l33_spkrdrv_event,
+		SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD),
+	SND_SOC_DAPM_AIF_IN_E("SDIN", NULL, 0, CS35L33_PWRCTL2,
+		2, 1, cs35l33_sdin_event, SND_SOC_DAPM_PRE_PMU |
+		SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD),
+
+	SND_SOC_DAPM_INPUT("MON"),
+
+	SND_SOC_DAPM_ADC("VMON", NULL,
+		CS35L33_PWRCTL2, CS35L33_PDN_VMON_SHIFT, 1),
+	SND_SOC_DAPM_ADC("IMON", NULL,
+		CS35L33_PWRCTL2, CS35L33_PDN_IMON_SHIFT, 1),
+	SND_SOC_DAPM_ADC("VPMON", NULL,
+		CS35L33_PWRCTL2, CS35L33_PDN_VPMON_SHIFT, 1),
+	SND_SOC_DAPM_ADC("VBSTMON", NULL,
+		CS35L33_PWRCTL2, CS35L33_PDN_VBSTMON_SHIFT, 1),
+
+	SND_SOC_DAPM_AIF_OUT_E("SDOUT", NULL, 0, SND_SOC_NOPM, 0, 0,
+		cs35l33_sdout_event, SND_SOC_DAPM_PRE_PMU |
+		SND_SOC_DAPM_PRE_PMD),
+};
+
+static const struct snd_soc_dapm_route cs35l33_audio_map[] = {
+	{"SDIN", NULL, "CS35L33 Playback"},
+	{"SPKDRV", NULL, "SDIN"},
+	{"SPK", NULL, "SPKDRV"},
+
+	{"VMON", NULL, "MON"},
+	{"IMON", NULL, "MON"},
+
+	{"SDOUT", NULL, "VMON"},
+	{"SDOUT", NULL, "IMON"},
+	{"CS35L33 Capture", NULL, "SDOUT"},
+};
+
+static const struct snd_soc_dapm_route cs35l33_vphg_auto_route[] = {
+	{"SPKDRV", NULL, "VPMON"},
+	{"VPMON", NULL, "CS35L33 Playback"},
+};
+
+static const struct snd_soc_dapm_route cs35l33_vp_vbst_mon_route[] = {
+	{"SDOUT", NULL, "VPMON"},
+	{"VPMON", NULL, "MON"},
+	{"SDOUT", NULL, "VBSTMON"},
+	{"VBSTMON", NULL, "MON"},
+};
+
+static int cs35l33_set_bias_level(struct snd_soc_codec *codec,
+				  enum snd_soc_bias_level level)
+{
+	unsigned int val;
+	struct cs35l33_private *priv = snd_soc_codec_get_drvdata(codec);
+
+	switch (level) {
+	case SND_SOC_BIAS_ON:
+		break;
+	case SND_SOC_BIAS_PREPARE:
+		regmap_update_bits(priv->regmap, CS35L33_PWRCTL1,
+				    CS35L33_PDN_ALL, 0);
+		regmap_update_bits(priv->regmap, CS35L33_CLK_CTL,
+				    CS35L33_MCLKDIS, 0);
+		break;
+	case SND_SOC_BIAS_STANDBY:
+		regmap_update_bits(priv->regmap, CS35L33_PWRCTL1,
+				    CS35L33_PDN_ALL, CS35L33_PDN_ALL);
+		regmap_read(priv->regmap, CS35L33_INT_STATUS_2, &val);
+		usleep_range(1000, 1100);
+		if (val & CS35L33_PDN_DONE)
+			regmap_update_bits(priv->regmap, CS35L33_CLK_CTL,
+					    CS35L33_MCLKDIS, CS35L33_MCLKDIS);
+		break;
+	case SND_SOC_BIAS_OFF:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+struct cs35l33_mclk_div {
+	int mclk;
+	int srate;
+	u8 adsp_rate;
+	u8 int_fs_ratio;
+};
+
+static const struct cs35l33_mclk_div cs35l33_mclk_coeffs[] = {
+	/* MCLK, Sample Rate, adsp_rate, int_fs_ratio */
+	{5644800, 11025, 0x4, CS35L33_INT_FS_RATE},
+	{5644800, 22050, 0x8, CS35L33_INT_FS_RATE},
+	{5644800, 44100, 0xC, CS35L33_INT_FS_RATE},
+
+	{6000000,  8000, 0x1, 0},
+	{6000000, 11025, 0x2, 0},
+	{6000000, 11029, 0x3, 0},
+	{6000000, 12000, 0x4, 0},
+	{6000000, 16000, 0x5, 0},
+	{6000000, 22050, 0x6, 0},
+	{6000000, 22059, 0x7, 0},
+	{6000000, 24000, 0x8, 0},
+	{6000000, 32000, 0x9, 0},
+	{6000000, 44100, 0xA, 0},
+	{6000000, 44118, 0xB, 0},
+	{6000000, 48000, 0xC, 0},
+
+	{6144000,  8000, 0x1, CS35L33_INT_FS_RATE},
+	{6144000, 12000, 0x4, CS35L33_INT_FS_RATE},
+	{6144000, 16000, 0x5, CS35L33_INT_FS_RATE},
+	{6144000, 24000, 0x8, CS35L33_INT_FS_RATE},
+	{6144000, 32000, 0x9, CS35L33_INT_FS_RATE},
+	{6144000, 48000, 0xC, CS35L33_INT_FS_RATE},
+};
+
+static int cs35l33_get_mclk_coeff(int mclk, int srate)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cs35l33_mclk_coeffs); i++) {
+		if (cs35l33_mclk_coeffs[i].mclk == mclk &&
+			cs35l33_mclk_coeffs[i].srate == srate)
+			return i;
+	}
+	return -EINVAL;
+}
+
+static int cs35l33_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
+{
+	struct snd_soc_codec *codec = codec_dai->codec;
+	struct cs35l33_private *priv = snd_soc_codec_get_drvdata(codec);
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		regmap_update_bits(priv->regmap, CS35L33_ADSP_CTL,
+			CS35L33_MS_MASK, CS35L33_MS_MASK);
+		dev_dbg(codec->dev, "Audio port in master mode\n");
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		regmap_update_bits(priv->regmap, CS35L33_ADSP_CTL,
+			CS35L33_MS_MASK, 0);
+		dev_dbg(codec->dev, "Audio port in slave mode\n");
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_DSP_A:
+		/*
+		 * tdm mode in cs35l33 resembles dsp-a mode very
+		 * closely, it is dsp-a with fsync shifted left by half bclk
+		 */
+		priv->is_tdm_mode = true;
+		dev_dbg(codec->dev, "Audio port in TDM mode\n");
+		break;
+	case SND_SOC_DAIFMT_I2S:
+		priv->is_tdm_mode = false;
+		dev_dbg(codec->dev, "Audio port in I2S mode\n");
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int cs35l33_pcm_hw_params(struct snd_pcm_substream *substream,
+				 struct snd_pcm_hw_params *params,
+				 struct snd_soc_dai *dai)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	struct cs35l33_private *priv = snd_soc_codec_get_drvdata(codec);
+	int sample_size = params_width(params);
+	int coeff = cs35l33_get_mclk_coeff(priv->mclk_int, params_rate(params));
+
+	if (coeff < 0)
+		return coeff;
+
+	regmap_update_bits(priv->regmap, CS35L33_CLK_CTL,
+		CS35L33_ADSP_FS | CS35L33_INT_FS_RATE,
+		cs35l33_mclk_coeffs[coeff].int_fs_ratio
+		| cs35l33_mclk_coeffs[coeff].adsp_rate);
+
+	if (priv->is_tdm_mode) {
+		sample_size = (sample_size / 8) - 1;
+		if (sample_size > 2)
+			sample_size = 2;
+		regmap_update_bits(priv->regmap, CS35L33_RX_AUD,
+			CS35L33_AUDIN_RX_DEPTH,
+			sample_size << CS35L33_AUDIN_RX_DEPTH_SHIFT);
+	}
+
+	dev_dbg(codec->dev, "sample rate=%d, bits per sample=%d\n",
+		params_rate(params), params_width(params));
+
+	return 0;
+}
+
+static const unsigned int cs35l33_src_rates[] = {
+	8000, 11025, 11029, 12000, 16000, 22050,
+	22059, 24000, 32000, 44100, 44118, 48000
+};
+
+static const struct snd_pcm_hw_constraint_list cs35l33_constraints = {
+	.count  = ARRAY_SIZE(cs35l33_src_rates),
+	.list   = cs35l33_src_rates,
+};
+
+static int cs35l33_pcm_startup(struct snd_pcm_substream *substream,
+			       struct snd_soc_dai *dai)
+{
+	snd_pcm_hw_constraint_list(substream->runtime, 0,
+					SNDRV_PCM_HW_PARAM_RATE,
+					&cs35l33_constraints);
+	return 0;
+}
+
+static int cs35l33_set_tristate(struct snd_soc_dai *dai, int tristate)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	struct cs35l33_private *priv = snd_soc_codec_get_drvdata(codec);
+
+	if (tristate) {
+		regmap_update_bits(priv->regmap, CS35L33_PWRCTL2,
+			CS35L33_SDOUT_3ST_I2S, CS35L33_SDOUT_3ST_I2S);
+		regmap_update_bits(priv->regmap, CS35L33_CLK_CTL,
+			CS35L33_SDOUT_3ST_TDM, CS35L33_SDOUT_3ST_TDM);
+	} else {
+		regmap_update_bits(priv->regmap, CS35L33_PWRCTL2,
+			CS35L33_SDOUT_3ST_I2S, 0);
+		regmap_update_bits(priv->regmap, CS35L33_CLK_CTL,
+			CS35L33_SDOUT_3ST_TDM, 0);
+	}
+
+	return 0;
+}
+
+static int cs35l33_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
+				unsigned int rx_mask, int slots, int slot_width)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	struct snd_soc_dapm_context *dapm = snd_soc_codec_get_dapm(codec);
+	struct cs35l33_private *priv = snd_soc_codec_get_drvdata(codec);
+	unsigned int reg, bit_pos, i;
+	int slot, slot_num;
+
+	if (slot_width != 8)
+		return -EINVAL;
+
+	/* scan rx_mask for aud slot */
+	slot = ffs(rx_mask) - 1;
+	if (slot >= 0) {
+		regmap_update_bits(priv->regmap, CS35L33_RX_AUD,
+			CS35L33_X_LOC, slot);
+		dev_dbg(codec->dev, "Audio starts from slots %d", slot);
+	}
+
+	/*
+	 * scan tx_mask: vmon(2 slots); imon (2 slots);
+	 * vpmon (1 slot) vbstmon (1 slot)
+	 */
+	slot = ffs(tx_mask) - 1;
+	slot_num = 0;
+
+	for (i = 0; i < 2 ; i++) {
+		/* disable vpmon/vbstmon: enable later if set in tx_mask */
+		regmap_update_bits(priv->regmap, CS35L33_TX_VPMON + i,
+			CS35L33_X_STATE | CS35L33_X_LOC, CS35L33_X_STATE
+			| CS35L33_X_LOC);
+	}
+
+	/* disconnect {vp,vbst}_mon routes: eanble later if set in tx_mask*/
+	snd_soc_dapm_del_routes(dapm, cs35l33_vp_vbst_mon_route,
+		ARRAY_SIZE(cs35l33_vp_vbst_mon_route));
+
+	while (slot >= 0) {
+		/* configure VMON_TX_LOC */
+		if (slot_num == 0) {
+			regmap_update_bits(priv->regmap, CS35L33_TX_VMON,
+				CS35L33_X_STATE | CS35L33_X_LOC, slot);
+			dev_dbg(codec->dev, "VMON enabled in slots %d-%d",
+				slot, slot + 1);
+		}
+
+		/* configure IMON_TX_LOC */
+		if (slot_num == 3) {
+			regmap_update_bits(priv->regmap, CS35L33_TX_IMON,
+				CS35L33_X_STATE | CS35L33_X_LOC, slot);
+			dev_dbg(codec->dev, "IMON enabled in slots %d-%d",
+				slot, slot + 1);
+		}
+
+		/* configure VPMON_TX_LOC */
+		if (slot_num == 4) {
+			regmap_update_bits(priv->regmap, CS35L33_TX_VPMON,
+				CS35L33_X_STATE | CS35L33_X_LOC, slot);
+			snd_soc_dapm_add_routes(dapm,
+				&cs35l33_vp_vbst_mon_route[0], 2);
+			dev_dbg(codec->dev, "VPMON enabled in slots %d", slot);
+		}
+
+		/* configure VBSTMON_TX_LOC */
+		if (slot_num == 5) {
+			regmap_update_bits(priv->regmap, CS35L33_TX_VBSTMON,
+				CS35L33_X_STATE | CS35L33_X_LOC, slot);
+			snd_soc_dapm_add_routes(dapm,
+				&cs35l33_vp_vbst_mon_route[2], 2);
+			dev_dbg(codec->dev,
+				"VBSTMON enabled in slots %d", slot);
+		}
+
+		/* Enable the relevant tx slot */
+		reg = CS35L33_TX_EN4 - (slot/8);
+		bit_pos = slot - ((slot / 8) * (8));
+		regmap_update_bits(priv->regmap, reg,
+			1 << bit_pos, 1 << bit_pos);
+
+		tx_mask &= ~(1 << slot);
+		slot = ffs(tx_mask) - 1;
+		slot_num++;
+	}
+
+	return 0;
+}
+
+static int cs35l33_codec_set_sysclk(struct snd_soc_codec *codec,
+		int clk_id, int source, unsigned int freq, int dir)
+{
+	struct cs35l33_private *cs35l33 = snd_soc_codec_get_drvdata(codec);
+
+	switch (freq) {
+	case CS35L33_MCLK_5644:
+	case CS35L33_MCLK_6:
+	case CS35L33_MCLK_6144:
+		regmap_update_bits(cs35l33->regmap, CS35L33_CLK_CTL,
+			CS35L33_MCLKDIV2, 0);
+		cs35l33->mclk_int = freq;
+		break;
+	case CS35L33_MCLK_11289:
+	case CS35L33_MCLK_12:
+	case CS35L33_MCLK_12288:
+		regmap_update_bits(cs35l33->regmap, CS35L33_CLK_CTL,
+			CS35L33_MCLKDIV2, CS35L33_MCLKDIV2);
+		cs35l33->mclk_int = freq/2;
+		break;
+	default:
+		cs35l33->mclk_int = 0;
+		return -EINVAL;
+	}
+
+	dev_dbg(codec->dev, "external mclk freq=%d, internal mclk freq=%d\n",
+		freq, cs35l33->mclk_int);
+
+	return 0;
+}
+
+static const struct snd_soc_dai_ops cs35l33_ops = {
+	.startup = cs35l33_pcm_startup,
+	.set_tristate = cs35l33_set_tristate,
+	.set_fmt = cs35l33_set_dai_fmt,
+	.hw_params = cs35l33_pcm_hw_params,
+	.set_tdm_slot = cs35l33_set_tdm_slot,
+};
+
+static struct snd_soc_dai_driver cs35l33_dai = {
+		.name = "cs35l33-dai",
+		.id = 0,
+		.playback = {
+			.stream_name = "CS35L33 Playback",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = CS35L33_RATES,
+			.formats = CS35L33_FORMATS,
+		},
+		.capture = {
+			.stream_name = "CS35L33 Capture",
+			.channels_min = 2,
+			.channels_max = 2,
+			.rates = CS35L33_RATES,
+			.formats = CS35L33_FORMATS,
+		},
+		.ops = &cs35l33_ops,
+		.symmetric_rates = 1,
+};
+
+static int cs35l33_set_hg_data(struct snd_soc_codec *codec,
+			       struct cs35l33_pdata *pdata)
+{
+	struct cs35l33_hg *hg_config = &pdata->hg_config;
+	struct snd_soc_dapm_context *dapm = snd_soc_codec_get_dapm(codec);
+	struct cs35l33_private *priv = snd_soc_codec_get_drvdata(codec);
+
+	if (hg_config->enable_hg_algo) {
+		regmap_update_bits(priv->regmap, CS35L33_HG_MEMLDO_CTL,
+			CS35L33_MEM_DEPTH_MASK,
+			hg_config->mem_depth << CS35L33_MEM_DEPTH_SHIFT);
+		regmap_write(priv->regmap, CS35L33_HG_REL_RATE,
+			hg_config->release_rate);
+		regmap_update_bits(priv->regmap, CS35L33_HG_HEAD,
+			CS35L33_HD_RM_MASK,
+			hg_config->hd_rm << CS35L33_HD_RM_SHIFT);
+		regmap_update_bits(priv->regmap, CS35L33_HG_MEMLDO_CTL,
+			CS35L33_LDO_THLD_MASK,
+			hg_config->ldo_thld << CS35L33_LDO_THLD_SHIFT);
+		regmap_update_bits(priv->regmap, CS35L33_HG_MEMLDO_CTL,
+			CS35L33_LDO_DISABLE_MASK,
+			hg_config->ldo_path_disable <<
+				CS35L33_LDO_DISABLE_SHIFT);
+		regmap_update_bits(priv->regmap, CS35L33_LDO_DEL,
+			CS35L33_LDO_ENTRY_DELAY_MASK,
+			hg_config->ldo_entry_delay <<
+				CS35L33_LDO_ENTRY_DELAY_SHIFT);
+		if (hg_config->vp_hg_auto) {
+			regmap_update_bits(priv->regmap, CS35L33_HG_EN,
+				CS35L33_VP_HG_AUTO_MASK,
+				CS35L33_VP_HG_AUTO_MASK);
+			snd_soc_dapm_add_routes(dapm, cs35l33_vphg_auto_route,
+				ARRAY_SIZE(cs35l33_vphg_auto_route));
+		}
+		regmap_update_bits(priv->regmap, CS35L33_HG_EN,
+			CS35L33_VP_HG_MASK,
+			hg_config->vp_hg << CS35L33_VP_HG_SHIFT);
+		regmap_update_bits(priv->regmap, CS35L33_LDO_DEL,
+			CS35L33_VP_HG_RATE_MASK,
+			hg_config->vp_hg_rate << CS35L33_VP_HG_RATE_SHIFT);
+		regmap_update_bits(priv->regmap, CS35L33_LDO_DEL,
+			CS35L33_VP_HG_VA_MASK,
+			hg_config->vp_hg_va << CS35L33_VP_HG_VA_SHIFT);
+		regmap_update_bits(priv->regmap, CS35L33_HG_EN,
+			CS35L33_CLASS_HG_EN_MASK, CS35L33_CLASS_HG_EN_MASK);
+	}
+	return 0;
+}
+
+static int cs35l33_set_bst_ipk(struct snd_soc_codec *codec, unsigned int bst)
+{
+	struct cs35l33_private *cs35l33 = snd_soc_codec_get_drvdata(codec);
+	int ret = 0, steps = 0;
+
+	/* Boost current in uA */
+	if (bst > 3600000 || bst < 1850000) {
+		dev_err(codec->dev, "Invalid boost current %d\n", bst);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	if (bst % 15625) {
+		dev_err(codec->dev, "Current not a multiple of 15625uA (%d)\n",
+			bst);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	while (bst > 1850000) {
+		bst -= 15625;
+		steps++;
+	}
+
+	regmap_write(cs35l33->regmap, CS35L33_BST_PEAK_CTL,
+		steps+0x70);
+
+err:
+	return ret;
+}
+
+static int cs35l33_probe(struct snd_soc_codec *codec)
+{
+	struct cs35l33_private *cs35l33 = snd_soc_codec_get_drvdata(codec);
+
+	cs35l33->codec = codec;
+	pm_runtime_get_sync(codec->dev);
+
+	regmap_update_bits(cs35l33->regmap, CS35L33_PROTECT_CTL,
+		CS35L33_ALIVE_WD_DIS, 0x8);
+	regmap_update_bits(cs35l33->regmap, CS35L33_BST_CTL2,
+				CS35L33_ALIVE_WD_DIS2,
+				CS35L33_ALIVE_WD_DIS2);
+
+	/* Set Platform Data */
+	regmap_update_bits(cs35l33->regmap, CS35L33_BST_CTL1,
+		CS35L33_BST_CTL_MASK, cs35l33->pdata.boost_ctl);
+	regmap_update_bits(cs35l33->regmap, CS35L33_CLASSD_CTL,
+		CS35L33_AMP_DRV_SEL_MASK,
+		cs35l33->pdata.amp_drv_sel << CS35L33_AMP_DRV_SEL_SHIFT);
+
+	if (cs35l33->pdata.boost_ipk)
+		cs35l33_set_bst_ipk(codec, cs35l33->pdata.boost_ipk);
+
+	if (cs35l33->enable_soft_ramp) {
+		snd_soc_update_bits(codec, CS35L33_DAC_CTL,
+			CS35L33_DIGSFT, CS35L33_DIGSFT);
+		snd_soc_update_bits(codec, CS35L33_DAC_CTL,
+			CS35L33_DSR_RATE, cs35l33->pdata.ramp_rate);
+	} else {
+		snd_soc_update_bits(codec, CS35L33_DAC_CTL,
+			CS35L33_DIGSFT, 0);
+	}
+
+	/* update IMON scaling rate if different from default of 0x8 */
+	if (cs35l33->pdata.imon_adc_scale != 0x8)
+		snd_soc_update_bits(codec, CS35L33_ADC_CTL,
+			CS35L33_IMON_SCALE, cs35l33->pdata.imon_adc_scale);
+
+	cs35l33_set_hg_data(codec, &(cs35l33->pdata));
+
+	/*
+	 * unmask important interrupts that causes the chip to enter
+	 * speaker safe mode and hence deserves user attention
+	 */
+	regmap_update_bits(cs35l33->regmap, CS35L33_INT_MASK_1,
+		CS35L33_M_OTE | CS35L33_M_OTW | CS35L33_M_AMP_SHORT |
+		CS35L33_M_CAL_ERR, 0);
+
+	pm_runtime_put_sync(codec->dev);
+
+	return 0;
+}
+
+static struct snd_soc_codec_driver soc_codec_dev_cs35l33 = {
+	.probe = cs35l33_probe,
+
+	.set_bias_level = cs35l33_set_bias_level,
+	.set_sysclk = cs35l33_codec_set_sysclk,
+
+	.dapm_widgets = cs35l33_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(cs35l33_dapm_widgets),
+	.dapm_routes = cs35l33_audio_map,
+	.num_dapm_routes = ARRAY_SIZE(cs35l33_audio_map),
+	.controls = cs35l33_snd_controls,
+	.num_controls = ARRAY_SIZE(cs35l33_snd_controls),
+
+	.idle_bias_off = true,
+};
+
+static const struct regmap_config cs35l33_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = CS35L33_MAX_REGISTER,
+	.reg_defaults = cs35l33_reg,
+	.num_reg_defaults = ARRAY_SIZE(cs35l33_reg),
+	.volatile_reg = cs35l33_volatile_register,
+	.readable_reg = cs35l33_readable_register,
+	.writeable_reg = cs35l33_writeable_register,
+	.cache_type = REGCACHE_RBTREE,
+	.use_single_rw = true,
+};
+
+static int __maybe_unused cs35l33_runtime_resume(struct device *dev)
+{
+	struct cs35l33_private *cs35l33 = dev_get_drvdata(dev);
+	int ret;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	if (cs35l33->reset_gpio)
+		gpiod_set_value_cansleep(cs35l33->reset_gpio, 0);
+
+	ret = regulator_bulk_enable(cs35l33->num_core_supplies,
+		cs35l33->core_supplies);
+	if (ret != 0) {
+		dev_err(dev, "Failed to enable core supplies: %d\n", ret);
+		return ret;
+	}
+
+	regcache_cache_only(cs35l33->regmap, false);
+
+	if (cs35l33->reset_gpio)
+		gpiod_set_value_cansleep(cs35l33->reset_gpio, 1);
+
+	msleep(CS35L33_BOOT_DELAY);
+
+	ret = regcache_sync(cs35l33->regmap);
+	if (ret != 0) {
+		dev_err(dev, "Failed to restore register cache\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	regcache_cache_only(cs35l33->regmap, true);
+	regulator_bulk_disable(cs35l33->num_core_supplies,
+		cs35l33->core_supplies);
+
+	return ret;
+}
+
+static int __maybe_unused cs35l33_runtime_suspend(struct device *dev)
+{
+	struct cs35l33_private *cs35l33 = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	/* redo the calibration in next power up */
+	cs35l33->amp_cal = false;
+
+	regcache_cache_only(cs35l33->regmap, true);
+	regcache_mark_dirty(cs35l33->regmap);
+	regulator_bulk_disable(cs35l33->num_core_supplies,
+		cs35l33->core_supplies);
+
+	return 0;
+}
+
+static const struct dev_pm_ops cs35l33_pm_ops = {
+	SET_RUNTIME_PM_OPS(cs35l33_runtime_suspend,
+			   cs35l33_runtime_resume,
+			   NULL)
+};
+
+static int cs35l33_get_hg_data(const struct device_node *np,
+			       struct cs35l33_pdata *pdata)
+{
+	struct device_node *hg;
+	struct cs35l33_hg *hg_config = &pdata->hg_config;
+	u32 val32;
+
+	hg = of_get_child_by_name(np, "cirrus,hg-algo");
+	hg_config->enable_hg_algo = hg ? true : false;
+
+	if (hg_config->enable_hg_algo) {
+		if (of_property_read_u32(hg, "cirrus,mem-depth", &val32) >= 0)
+			hg_config->mem_depth = val32;
+		if (of_property_read_u32(hg, "cirrus,release-rate",
+				&val32) >= 0)
+			hg_config->release_rate = val32;
+		if (of_property_read_u32(hg, "cirrus,ldo-thld", &val32) >= 0)
+			hg_config->ldo_thld = val32;
+		if (of_property_read_u32(hg, "cirrus,ldo-path-disable",
+				&val32) >= 0)
+			hg_config->ldo_path_disable = val32;
+		if (of_property_read_u32(hg, "cirrus,ldo-entry-delay",
+				&val32) >= 0)
+			hg_config->ldo_entry_delay = val32;
+
+		hg_config->vp_hg_auto = of_property_read_bool(hg,
+			"cirrus,vp-hg-auto");
+
+		if (of_property_read_u32(hg, "cirrus,vp-hg", &val32) >= 0)
+			hg_config->vp_hg = val32;
+		if (of_property_read_u32(hg, "cirrus,vp-hg-rate", &val32) >= 0)
+			hg_config->vp_hg_rate = val32;
+		if (of_property_read_u32(hg, "cirrus,vp-hg-va", &val32) >= 0)
+			hg_config->vp_hg_va = val32;
+	}
+
+	of_node_put(hg);
+
+	return 0;
+}
+
+static irqreturn_t cs35l33_irq_thread(int irq, void *data)
+{
+	struct cs35l33_private *cs35l33 = data;
+	struct snd_soc_codec *codec = cs35l33->codec;
+	unsigned int sticky_val1, sticky_val2, current_val, mask1, mask2;
+
+	regmap_read(cs35l33->regmap, CS35L33_INT_STATUS_2,
+		&sticky_val2);
+	regmap_read(cs35l33->regmap, CS35L33_INT_STATUS_1,
+		&sticky_val1);
+	regmap_read(cs35l33->regmap, CS35L33_INT_MASK_2, &mask2);
+	regmap_read(cs35l33->regmap, CS35L33_INT_MASK_1, &mask1);
+
+	/* Check to see if the unmasked bits are active,
+	 *  if not then exit.
+	 */
+	if (!(sticky_val1 & ~mask1) && !(sticky_val2 & ~mask2))
+		return IRQ_NONE;
+
+	regmap_read(cs35l33->regmap, CS35L33_INT_STATUS_1,
+		&current_val);
+
+	/* handle the interrupts */
+
+	if (sticky_val1 & CS35L33_AMP_SHORT) {
+		dev_crit(codec->dev, "Amp short error\n");
+		if (!(current_val & CS35L33_AMP_SHORT)) {
+			dev_dbg(codec->dev,
+				"Amp short error release\n");
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL,
+				CS35L33_AMP_SHORT_RLS, 0);
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL,
+				CS35L33_AMP_SHORT_RLS,
+				CS35L33_AMP_SHORT_RLS);
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL, CS35L33_AMP_SHORT_RLS,
+				0);
+		}
+	}
+
+	if (sticky_val1 & CS35L33_CAL_ERR) {
+		dev_err(codec->dev, "Cal error\n");
+
+		/* redo the calibration in next power up */
+		cs35l33->amp_cal = false;
+
+		if (!(current_val & CS35L33_CAL_ERR)) {
+			dev_dbg(codec->dev, "Cal error release\n");
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL, CS35L33_CAL_ERR_RLS,
+				0);
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL, CS35L33_CAL_ERR_RLS,
+				CS35L33_CAL_ERR_RLS);
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL, CS35L33_CAL_ERR_RLS,
+				0);
+		}
+	}
+
+	if (sticky_val1 & CS35L33_OTE) {
+		dev_crit(codec->dev, "Over temperature error\n");
+		if (!(current_val & CS35L33_OTE)) {
+			dev_dbg(codec->dev,
+				"Over temperature error release\n");
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL, CS35L33_OTE_RLS, 0);
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL, CS35L33_OTE_RLS,
+				CS35L33_OTE_RLS);
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL, CS35L33_OTE_RLS, 0);
+		}
+	}
+
+	if (sticky_val1 & CS35L33_OTW) {
+		dev_err(codec->dev, "Over temperature warning\n");
+		if (!(current_val & CS35L33_OTW)) {
+			dev_dbg(codec->dev,
+				"Over temperature warning release\n");
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL, CS35L33_OTW_RLS, 0);
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL, CS35L33_OTW_RLS,
+				CS35L33_OTW_RLS);
+			regmap_update_bits(cs35l33->regmap,
+				CS35L33_AMP_CTL, CS35L33_OTW_RLS, 0);
+		}
+	}
+	if (CS35L33_ALIVE_ERR & sticky_val1)
+		dev_err(codec->dev, "ERROR: ADSPCLK Interrupt\n");
+
+	if (CS35L33_MCLK_ERR & sticky_val1)
+		dev_err(codec->dev, "ERROR: MCLK Interrupt\n");
+
+	if (CS35L33_VMON_OVFL & sticky_val2)
+		dev_err(codec->dev,
+			"ERROR: VMON Overflow Interrupt\n");
+
+	if (CS35L33_IMON_OVFL & sticky_val2)
+		dev_err(codec->dev,
+			"ERROR: IMON Overflow Interrupt\n");
+
+	if (CS35L33_VPMON_OVFL & sticky_val2)
+		dev_err(codec->dev,
+			"ERROR: VPMON Overflow Interrupt\n");
+
+	return IRQ_HANDLED;
+}
+
+static const char * const cs35l33_core_supplies[] = {
+	"VA",
+	"VP",
+};
+
+static int cs35l33_of_get_pdata(struct device *dev,
+				struct cs35l33_private *cs35l33)
+{
+	struct device_node *np = dev->of_node;
+	struct cs35l33_pdata *pdata = &cs35l33->pdata;
+	u32 val32;
+
+	if (!np)
+		return 0;
+
+	if (of_property_read_u32(np, "cirrus,boost-ctl", &val32) >= 0) {
+		pdata->boost_ctl = val32;
+		pdata->amp_drv_sel = 1;
+	}
+
+	if (of_property_read_u32(np, "cirrus,ramp-rate", &val32) >= 0) {
+		pdata->ramp_rate = val32;
+		cs35l33->enable_soft_ramp = true;
+	}
+
+	if (of_property_read_u32(np, "cirrus,boost-ipk", &val32) >= 0)
+		pdata->boost_ipk = val32;
+
+	if (of_property_read_u32(np, "cirrus,imon-adc-scale", &val32) >= 0) {
+		if ((val32 == 0x0) || (val32 == 0x7) || (val32 == 0x6))
+			pdata->imon_adc_scale = val32;
+		else
+			/* use default value */
+			pdata->imon_adc_scale = 0x8;
+	} else {
+		/* use default value */
+		pdata->imon_adc_scale = 0x8;
+	}
+
+	cs35l33_get_hg_data(np, pdata);
+
+	return 0;
+}
+
+static int cs35l33_i2c_probe(struct i2c_client *i2c_client,
+				       const struct i2c_device_id *id)
+{
+	struct cs35l33_private *cs35l33;
+	struct cs35l33_pdata *pdata = dev_get_platdata(&i2c_client->dev);
+	int ret, devid, i;
+	unsigned int reg;
+
+	cs35l33 = devm_kzalloc(&i2c_client->dev, sizeof(struct cs35l33_private),
+			       GFP_KERNEL);
+	if (!cs35l33)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c_client, cs35l33);
+	cs35l33->regmap = devm_regmap_init_i2c(i2c_client, &cs35l33_regmap);
+	if (IS_ERR(cs35l33->regmap)) {
+		ret = PTR_ERR(cs35l33->regmap);
+		dev_err(&i2c_client->dev, "regmap_init() failed: %d\n", ret);
+		return ret;
+	}
+
+	regcache_cache_only(cs35l33->regmap, true);
+
+	for (i = 0; i < ARRAY_SIZE(cs35l33_core_supplies); i++)
+		cs35l33->core_supplies[i].supply
+			= cs35l33_core_supplies[i];
+	cs35l33->num_core_supplies = ARRAY_SIZE(cs35l33_core_supplies);
+
+	ret = devm_regulator_bulk_get(&i2c_client->dev,
+			cs35l33->num_core_supplies,
+			cs35l33->core_supplies);
+	if (ret != 0) {
+		dev_err(&i2c_client->dev,
+			"Failed to request core supplies: %d\n",
+			ret);
+		return ret;
+	}
+
+	if (pdata) {
+		cs35l33->pdata = *pdata;
+	} else {
+		cs35l33_of_get_pdata(&i2c_client->dev, cs35l33);
+		pdata = &cs35l33->pdata;
+	}
+
+	ret = devm_request_threaded_irq(&i2c_client->dev, i2c_client->irq, NULL,
+			cs35l33_irq_thread, IRQF_ONESHOT | IRQF_TRIGGER_LOW,
+			"cs35l33", cs35l33);
+	if (ret != 0)
+		dev_warn(&i2c_client->dev, "Failed to request IRQ: %d\n", ret);
+
+	/* We could issue !RST or skip it based on AMP topology */
+	cs35l33->reset_gpio = devm_gpiod_get_optional(&i2c_client->dev,
+			"reset-gpios", GPIOD_OUT_HIGH);
+	if (IS_ERR(cs35l33->reset_gpio)) {
+		dev_err(&i2c_client->dev, "%s ERROR: Can't get reset GPIO\n",
+			__func__);
+		return PTR_ERR(cs35l33->reset_gpio);
+	}
+
+	ret = regulator_bulk_enable(cs35l33->num_core_supplies,
+					cs35l33->core_supplies);
+	if (ret != 0) {
+		dev_err(&i2c_client->dev,
+			"Failed to enable core supplies: %d\n",
+			ret);
+		return ret;
+	}
+
+	if (cs35l33->reset_gpio)
+		gpiod_set_value_cansleep(cs35l33->reset_gpio, 1);
+
+	msleep(CS35L33_BOOT_DELAY);
+	regcache_cache_only(cs35l33->regmap, false);
+
+	/* initialize codec */
+	ret = regmap_read(cs35l33->regmap, CS35L33_DEVID_AB, &reg);
+	devid = (reg & 0xFF) << 12;
+	ret = regmap_read(cs35l33->regmap, CS35L33_DEVID_CD, &reg);
+	devid |= (reg & 0xFF) << 4;
+	ret = regmap_read(cs35l33->regmap, CS35L33_DEVID_E, &reg);
+	devid |= (reg & 0xF0) >> 4;
+
+	if (devid != CS35L33_CHIP_ID) {
+		dev_err(&i2c_client->dev,
+			"CS35L33 Device ID (%X). Expected ID %X\n",
+			devid, CS35L33_CHIP_ID);
+		goto err_enable;
+	}
+
+	ret = regmap_read(cs35l33->regmap, CS35L33_REV_ID, &reg);
+	if (ret < 0) {
+		dev_err(&i2c_client->dev, "Get Revision ID failed\n");
+		goto err_enable;
+	}
+
+	dev_info(&i2c_client->dev,
+		 "Cirrus Logic CS35L33, Revision: %02X\n", reg & 0xFF);
+
+	ret = regmap_register_patch(cs35l33->regmap,
+			cs35l33_patch, ARRAY_SIZE(cs35l33_patch));
+	if (ret < 0) {
+		dev_err(&i2c_client->dev,
+			"Error in applying regmap patch: %d\n", ret);
+		goto err_enable;
+	}
+
+	/* disable mclk and tdm */
+	regmap_update_bits(cs35l33->regmap, CS35L33_CLK_CTL,
+		CS35L33_MCLKDIS | CS35L33_SDOUT_3ST_TDM,
+		CS35L33_MCLKDIS | CS35L33_SDOUT_3ST_TDM);
+
+	pm_runtime_set_autosuspend_delay(&i2c_client->dev, 100);
+	pm_runtime_use_autosuspend(&i2c_client->dev);
+	pm_runtime_set_active(&i2c_client->dev);
+	pm_runtime_enable(&i2c_client->dev);
+
+	ret =  snd_soc_register_codec(&i2c_client->dev,
+			&soc_codec_dev_cs35l33, &cs35l33_dai, 1);
+	if (ret < 0) {
+		dev_err(&i2c_client->dev, "%s: Register codec failed\n",
+			__func__);
+		goto err_enable;
+	}
+
+	return 0;
+
+err_enable:
+	regulator_bulk_disable(cs35l33->num_core_supplies,
+			       cs35l33->core_supplies);
+
+	return ret;
+}
+
+static int cs35l33_i2c_remove(struct i2c_client *client)
+{
+	struct cs35l33_private *cs35l33 = i2c_get_clientdata(client);
+
+	snd_soc_unregister_codec(&client->dev);
+
+	if (cs35l33->reset_gpio)
+		gpiod_set_value_cansleep(cs35l33->reset_gpio, 0);
+
+	pm_runtime_disable(&client->dev);
+	regulator_bulk_disable(cs35l33->num_core_supplies,
+		cs35l33->core_supplies);
+
+	return 0;
+}
+
+static const struct of_device_id cs35l33_of_match[] = {
+	{ .compatible = "cirrus,cs35l33", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, cs35l33_of_match);
+
+static const struct i2c_device_id cs35l33_id[] = {
+	{"cs35l33", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, cs35l33_id);
+
+static struct i2c_driver cs35l33_i2c_driver = {
+	.driver = {
+		.name = "cs35l33",
+		.pm = &cs35l33_pm_ops,
+		.of_match_table = cs35l33_of_match,
+
+		},
+	.id_table = cs35l33_id,
+	.probe = cs35l33_i2c_probe,
+	.remove = cs35l33_i2c_remove,
+
+};
+module_i2c_driver(cs35l33_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC CS35L33 driver");
+MODULE_AUTHOR("Paul Handrigan, Cirrus Logic Inc, <paul.handrigan@cirrus.com>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/cs35l33.h b/sound/soc/codecs/cs35l33.h
new file mode 100644
index 000000000000..c045737d1a5f
--- /dev/null
+++ b/sound/soc/codecs/cs35l33.h
@@ -0,0 +1,221 @@
+/*
+ * cs35l33.h -- CS35L33 ALSA SoC audio driver
+ *
+ * Copyright 2016 Cirrus Logic, Inc.
+ *
+ * Author: Paul Handrigan <paul.handrigan@cirrus.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __CS35L33_H__
+#define __CS35L33_H__
+
+#define CS35L33_CHIP_ID		0x00035A33
+#define CS35L33_DEVID_AB	0x01	/* Device ID A & B [RO] */
+#define CS35L33_DEVID_CD	0x02	/* Device ID C & D [RO] */
+#define CS35L33_DEVID_E		0x03	/* Device ID E [RO] */
+#define CS35L33_FAB_ID		0x04	/* Fab ID [RO] */
+#define CS35L33_REV_ID		0x05	/* Revision ID [RO] */
+#define CS35L33_PWRCTL1		0x06	/* Power Ctl 1 */
+#define CS35L33_PWRCTL2		0x07	/* Power Ctl 2 */
+#define CS35L33_CLK_CTL		0x08	/* Clock Ctl */
+#define CS35L33_BST_PEAK_CTL	0x09	/* Max Current for Boost */
+#define CS35L33_PROTECT_CTL	0x0A	/* Amp Protection Parameters */
+#define CS35L33_BST_CTL1	0x0B	/* Boost Converter CTL1 */
+#define CS35L33_BST_CTL2	0x0C	/* Boost Converter CTL2 */
+#define CS35L33_ADSP_CTL	0x0D	/* Serial Port Control */
+#define CS35L33_ADC_CTL		0x0E	/* ADC Control */
+#define CS35L33_DAC_CTL		0x0F	/* DAC Control */
+#define CS35L33_DIG_VOL_CTL	0x10	/* Digital Volume CTL */
+#define CS35L33_CLASSD_CTL	0x11	/* Class D Amp CTL */
+#define CS35L33_AMP_CTL		0x12	/* Amp Gain/Protecton Release CTL */
+#define CS35L33_INT_MASK_1	0x13	/* Interrupt Mask 1 */
+#define CS35L33_INT_MASK_2	0x14	/* Interrupt Mask 2 */
+#define CS35L33_INT_STATUS_1	0x15	/* Interrupt Status 1 [RO] */
+#define CS35L33_INT_STATUS_2	0x16	/* Interrupt Status 2 [RO] */
+#define CS35L33_DIAG_LOCK	0x17	/* Diagnostic Mode Register Lock */
+#define CS35L33_DIAG_CTRL_1	0x18	/* Diagnostic Mode Register Control */
+#define CS35L33_DIAG_CTRL_2	0x19	/* Diagnostic Mode Register Control 2 */
+#define CS35L33_HG_MEMLDO_CTL	0x23	/* H/G Memory/LDO CTL */
+#define CS35L33_HG_REL_RATE	0x24	/* H/G Release Rate */
+#define CS35L33_LDO_DEL		0x25	/* LDO Entry Delay/VPhg Control 1 */
+#define CS35L33_HG_HEAD		0x29	/* H/G Headroom */
+#define CS35L33_HG_EN		0x2A	/* H/G Enable/VPhg CNT2 */
+#define CS35L33_TX_VMON		0x2D	/* TDM TX Control 1 (VMON) */
+#define CS35L33_TX_IMON		0x2E	/* TDM TX Control 2 (IMON) */
+#define CS35L33_TX_VPMON	0x2F	/* TDM TX Control 3 (VPMON) */
+#define CS35L33_TX_VBSTMON	0x30	/* TDM TX Control 4 (VBSTMON) */
+#define CS35L33_TX_FLAG		0x31	/* TDM TX Control 5 (FLAG) */
+#define CS35L33_TX_EN1		0x32	/* TDM TX Enable 1 */
+#define CS35L33_TX_EN2		0x33	/* TDM TX Enable 2 */
+#define CS35L33_TX_EN3		0x34	/* TDM TX Enable 3 */
+#define CS35L33_TX_EN4		0x35	/* TDM TX Enable 4 */
+#define CS35L33_RX_AUD		0x36	/* TDM RX Control 1 */
+#define CS35L33_RX_SPLY		0x37	/* TDM RX Control 2 */
+#define CS35L33_RX_ALIVE	0x38	/* TDM RX Control 3 */
+#define CS35L33_BST_CTL4	0x39	/* Boost Converter Control 4 */
+#define CS35L33_HG_STATUS	0x3F	/* H/G Status */
+#define CS35L33_MAX_REGISTER	0x59
+
+#define CS35L33_MCLK_5644	5644800
+#define CS35L33_MCLK_6144	6144000
+#define CS35L33_MCLK_6		6000000
+#define CS35L33_MCLK_11289	11289600
+#define CS35L33_MCLK_12		12000000
+#define CS35L33_MCLK_12288	12288000
+
+/* CS35L33_PWRCTL1 */
+#define CS35L33_PDN_AMP			(1 << 7)
+#define CS35L33_PDN_BST			(1 << 2)
+#define CS35L33_PDN_ALL			1
+
+/* CS35L33_PWRCTL2 */
+#define CS35L33_PDN_VMON_SHIFT		7
+#define CS35L33_PDN_VMON		(1 << CS35L33_PDN_VMON_SHIFT)
+#define CS35L33_PDN_IMON_SHIFT		6
+#define CS35L33_PDN_IMON		(1 << CS35L33_PDN_IMON_SHIFT)
+#define CS35L33_PDN_VPMON_SHIFT		5
+#define CS35L33_PDN_VPMON		(1 << CS35L33_PDN_VPMON_SHIFT)
+#define CS35L33_PDN_VBSTMON_SHIFT	4
+#define CS35L33_PDN_VBSTMON		(1 << CS35L33_PDN_VBSTMON_SHIFT)
+#define CS35L33_SDOUT_3ST_I2S_SHIFT	3
+#define CS35L33_SDOUT_3ST_I2S		(1 << CS35L33_SDOUT_3ST_I2S_SHIFT)
+#define CS35L33_PDN_SDIN_SHIFT		2
+#define CS35L33_PDN_SDIN		(1 << CS35L33_PDN_SDIN_SHIFT)
+#define CS35L33_PDN_TDM_SHIFT		1
+#define CS35L33_PDN_TDM			(1 << CS35L33_PDN_TDM_SHIFT)
+
+/* CS35L33_CLK_CTL */
+#define CS35L33_MCLKDIS			(1 << 7)
+#define CS35L33_MCLKDIV2		(1 << 6)
+#define CS35L33_SDOUT_3ST_TDM		(1 << 5)
+#define CS35L33_INT_FS_RATE		(1 << 4)
+#define CS35L33_ADSP_FS			0xF
+
+/* CS35L33_PROTECT_CTL */
+#define CS35L33_ALIVE_WD_DIS		(3 << 2)
+
+/* CS35L33_BST_CTL1 */
+#define CS35L33_BST_CTL_SRC		(1 << 6)
+#define CS35L33_BST_CTL_SHIFT		(1 << 5)
+#define CS35L33_BST_CTL_MASK		0x3F
+
+/* CS35L33_BST_CTL2 */
+#define CS35L33_TDM_WD_SEL		(1 << 4)
+#define CS35L33_ALIVE_WD_DIS2		(1 << 3)
+#define CS35L33_VBST_SR_STEP		0x3
+
+/* CS35L33_ADSP_CTL */
+#define CS35L33_ADSP_DRIVE		(1 << 7)
+#define CS35L33_MS_MASK			(1 << 6)
+#define CS35L33_SDIN_LOC		(3 << 4)
+#define CS35L33_ALIVE_RATE		0x3
+
+/* CS35L33_ADC_CTL */
+#define CS35L33_INV_VMON		(1 << 7)
+#define CS35L33_INV_IMON		(1 << 6)
+#define CS35L33_ADC_NOTCH_DIS		(1 << 5)
+#define CS35L33_IMON_SCALE		0xF
+
+/* CS35L33_DAC_CTL */
+#define CS35L33_INV_DAC			(1 << 7)
+#define CS35L33_DAC_NOTCH_DIS		(1 << 5)
+#define CS35L33_DIGSFT			(1 << 4)
+#define CS35L33_DSR_RATE		0xF
+
+/* CS35L33_CLASSD_CTL */
+#define CS35L33_AMP_SD			(1 << 6)
+#define CS35L33_AMP_DRV_SEL_SRC		(1 << 5)
+#define CS35L33_AMP_DRV_SEL_MASK	0x10
+#define CS35L33_AMP_DRV_SEL_SHIFT	4
+#define CS35L33_AMP_CAL			(1 << 3)
+#define CS35L33_GAIN_CHG_ZC_MASK	0x04
+#define CS35L33_GAIN_CHG_ZC_SHIFT	2
+#define CS35L33_CLASS_D_CTL_MASK	0x3F
+
+/* CS35L33_AMP_CTL */
+#define CS35L33_AMP_GAIN		0xF0
+#define CS35L33_CAL_ERR_RLS		(1 << 3)
+#define CS35L33_AMP_SHORT_RLS		(1 << 2)
+#define CS35L33_OTW_RLS			(1 << 1)
+#define CS35L33_OTE_RLS			1
+
+/* CS35L33_INT_MASK_1 */
+#define CS35L33_M_CAL_ERR_SHIFT		6
+#define CS35L33_M_CAL_ERR		(1 << CS35L33_M_CAL_ERR_SHIFT)
+#define CS35L33_M_ALIVE_ERR_SHIFT	5
+#define CS35L33_M_ALIVE_ERR		(1 << CS35L33_M_ALIVE_ERR_SHIFT)
+#define CS35L33_M_AMP_SHORT_SHIFT	2
+#define CS35L33_M_AMP_SHORT		(1 << CS35L33_M_AMP_SHORT_SHIFT)
+#define CS35L33_M_OTW_SHIFT		1
+#define CS35L33_M_OTW			(1 << CS35L33_M_OTW_SHIFT)
+#define CS35L33_M_OTE_SHIFT		0
+#define CS35L33_M_OTE			(1 << CS35L33_M_OTE_SHIFT)
+
+/* CS35L33_INT_STATUS_1 */
+#define CS35L33_CAL_ERR			(1 << 6)
+#define CS35L33_ALIVE_ERR		(1 << 5)
+#define CS35L33_ADSPCLK_ERR		(1 << 4)
+#define CS35L33_MCLK_ERR		(1 << 3)
+#define CS35L33_AMP_SHORT		(1 << 2)
+#define CS35L33_OTW			(1 << 1)
+#define CS35L33_OTE			(1 << 0)
+
+/* CS35L33_INT_STATUS_2 */
+#define CS35L33_VMON_OVFL		(1 << 7)
+#define CS35L33_IMON_OVFL		(1 << 6)
+#define CS35L33_VPMON_OVFL		(1 << 5)
+#define CS35L33_VBSTMON_OVFL		(1 << 4)
+#define CS35L33_PDN_DONE		1
+
+/* CS35L33_BST_CTL4 */
+#define CS35L33_BST_RGS			0x70
+#define CS35L33_BST_COEFF3		0xF
+
+/* CS35L33_HG_MEMLDO_CTL */
+#define CS35L33_MEM_DEPTH_SHIFT		5
+#define CS35L33_MEM_DEPTH_MASK		(0x3 << CS35L33_MEM_DEPTH_SHIFT)
+#define CS35L33_LDO_THLD_SHIFT		1
+#define CS35L33_LDO_THLD_MASK		(0xF << CS35L33_LDO_THLD_SHIFT)
+#define CS35L33_LDO_DISABLE_SHIFT	0
+#define CS35L33_LDO_DISABLE_MASK	(0x1 << CS35L33_LDO_DISABLE_SHIFT)
+
+/* CS35L33_LDO_DEL */
+#define CS35L33_VP_HG_VA_SHIFT		5
+#define CS35L33_VP_HG_VA_MASK		(0x7 << CS35L33_VP_HG_VA_SHIFT)
+#define CS35L33_LDO_ENTRY_DELAY_SHIFT	2
+#define CS35L33_LDO_ENTRY_DELAY_MASK	(0x7 << CS35L33_LDO_ENTRY_DELAY_SHIFT)
+#define CS35L33_VP_HG_RATE_SHIFT	0
+#define CS35L33_VP_HG_RATE_MASK		(0x3 << CS35L33_VP_HG_RATE_SHIFT)
+
+/* CS35L33_HG_HEAD */
+#define CS35L33_HD_RM_SHIFT		0
+#define CS35L33_HD_RM_MASK		(0x7F << CS35L33_HD_RM_SHIFT)
+
+/* CS35L33_HG_EN */
+#define CS35L33_CLASS_HG_ENA_SHIFT	7
+#define CS35L33_CLASS_HG_EN_MASK	(0x1 << CS35L33_CLASS_HG_ENA_SHIFT)
+#define CS35L33_VP_HG_AUTO_SHIFT	6
+#define CS35L33_VP_HG_AUTO_MASK		(0x1 << 6)
+#define CS35L33_VP_HG_SHIFT		0
+#define CS35L33_VP_HG_MASK		(0x1F << CS35L33_VP_HG_SHIFT)
+
+#define CS35L33_RATES (SNDRV_PCM_RATE_8000_48000)
+#define CS35L33_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | \
+			SNDRV_PCM_FMTBIT_S24_LE)
+
+/* CS35L33_{RX,TX}_X */
+#define CS35L33_X_STATE_SHIFT		7
+#define CS35L33_X_STATE			(1 << CS35L33_X_STATE_SHIFT)
+#define CS35L33_X_LOC_SHIFT		0
+#define CS35L33_X_LOC			(0x1F << CS35L33_X_LOC_SHIFT)
+
+/* CS35L33_RX_AUD */
+#define CS35L33_AUDIN_RX_DEPTH_SHIFT	5
+#define CS35L33_AUDIN_RX_DEPTH		(0x7 << CS35L33_AUDIN_RX_DEPTH_SHIFT)
+
+#endif
diff --git a/sound/soc/codecs/cs47l24.c b/sound/soc/codecs/cs47l24.c
index 5ec5a682d186..954a4f5d3338 100644
--- a/sound/soc/codecs/cs47l24.c
+++ b/sound/soc/codecs/cs47l24.c
@@ -359,6 +359,11 @@ SND_SOC_DAPM_INPUT("IN2R"),
 SND_SOC_DAPM_OUTPUT("DRC1 Signal Activity"),
 SND_SOC_DAPM_OUTPUT("DRC2 Signal Activity"),
 
+SND_SOC_DAPM_OUTPUT("DSP Voice Trigger"),
+
+SND_SOC_DAPM_SWITCH("DSP3 Voice Trigger", SND_SOC_NOPM, 2, 0,
+		    &arizona_voice_trigger_switch[2]),
+
 SND_SOC_DAPM_PGA_E("IN1L PGA", ARIZONA_INPUT_ENABLES, ARIZONA_IN1L_ENA_SHIFT,
 		   0, NULL, 0, arizona_in_ev,
 		   SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMD |
@@ -899,10 +904,16 @@ static const struct snd_soc_dapm_route cs47l24_dapm_routes[] = {
 
 	{ "MICSUPP", NULL, "SYSCLK" },
 
+	{ "DRC1 Signal Activity", NULL, "SYSCLK" },
+	{ "DRC2 Signal Activity", NULL, "SYSCLK" },
 	{ "DRC1 Signal Activity", NULL, "DRC1L" },
 	{ "DRC1 Signal Activity", NULL, "DRC1R" },
 	{ "DRC2 Signal Activity", NULL, "DRC2L" },
 	{ "DRC2 Signal Activity", NULL, "DRC2R" },
+
+	{ "DSP Voice Trigger", NULL, "SYSCLK" },
+	{ "DSP Voice Trigger", NULL, "DSP3 Voice Trigger" },
+	{ "DSP3 Voice Trigger", "Switch", "DSP3" },
 };
 
 static int cs47l24_set_fll(struct snd_soc_codec *codec, int fll_id, int source,
@@ -1067,6 +1078,7 @@ static irqreturn_t cs47l24_adsp2_irq(int irq, void *data)
 {
 	struct cs47l24_priv *priv = data;
 	struct arizona *arizona = priv->core.arizona;
+	struct arizona_voice_trigger_info info;
 	int serviced = 0;
 	int i, ret;
 
@@ -1074,6 +1086,12 @@ static irqreturn_t cs47l24_adsp2_irq(int irq, void *data)
 		ret = wm_adsp_compr_handle_irq(&priv->core.adsp[i]);
 		if (ret != -ENODEV)
 			serviced++;
+		if (ret == WM_ADSP_COMPR_VOICE_TRIGGER) {
+			info.core = i;
+			arizona_call_notifiers(arizona,
+					       ARIZONA_NOTIFY_VOICE_TRIGGER,
+					       &info);
+		}
 	}
 
 	if (!serviced) {
@@ -1096,6 +1114,7 @@ static int cs47l24_codec_probe(struct snd_soc_codec *codec)
 	arizona_init_spk(codec);
 	arizona_init_gpio(codec);
 	arizona_init_mono(codec);
+	arizona_init_notifiers(codec);
 
 	ret = arizona_request_irq(arizona, ARIZONA_IRQ_DSP_IRQ1,
 				  "ADSP2 Compressed IRQ", cs47l24_adsp2_irq,
diff --git a/sound/soc/codecs/cs53l30.c b/sound/soc/codecs/cs53l30.c
new file mode 100644
index 000000000000..2c0d9c430a8c
--- /dev/null
+++ b/sound/soc/codecs/cs53l30.c
@@ -0,0 +1,1143 @@
+/*
+ * cs53l30.c  --  CS53l30 ALSA Soc Audio driver
+ *
+ * Copyright 2015 Cirrus Logic, Inc.
+ *
+ * Authors: Paul Handrigan <Paul.Handrigan@cirrus.com>,
+ *          Tim Howe <Tim.Howe@cirrus.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/of_gpio.h>
+#include <linux/gpio/consumer.h>
+#include <linux/regulator/consumer.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/tlv.h>
+
+#include "cs53l30.h"
+
+#define CS53L30_NUM_SUPPLIES 2
+static const char *const cs53l30_supply_names[CS53L30_NUM_SUPPLIES] = {
+	"VA",
+	"VP",
+};
+
+struct cs53l30_private {
+	struct regulator_bulk_data	supplies[CS53L30_NUM_SUPPLIES];
+	struct regmap			*regmap;
+	struct gpio_desc		*reset_gpio;
+	struct gpio_desc		*mute_gpio;
+	struct clk			*mclk;
+	bool				use_sdout2;
+	u32				mclk_rate;
+};
+
+static const struct reg_default cs53l30_reg_defaults[] = {
+	{ CS53L30_PWRCTL,		CS53L30_PWRCTL_DEFAULT },
+	{ CS53L30_MCLKCTL,		CS53L30_MCLKCTL_DEFAULT },
+	{ CS53L30_INT_SR_CTL,		CS53L30_INT_SR_CTL_DEFAULT },
+	{ CS53L30_MICBIAS_CTL,		CS53L30_MICBIAS_CTL_DEFAULT },
+	{ CS53L30_ASPCFG_CTL,		CS53L30_ASPCFG_CTL_DEFAULT },
+	{ CS53L30_ASP_CTL1,		CS53L30_ASP_CTL1_DEFAULT },
+	{ CS53L30_ASP_TDMTX_CTL1,	CS53L30_ASP_TDMTX_CTLx_DEFAULT },
+	{ CS53L30_ASP_TDMTX_CTL2,	CS53L30_ASP_TDMTX_CTLx_DEFAULT },
+	{ CS53L30_ASP_TDMTX_CTL3,	CS53L30_ASP_TDMTX_CTLx_DEFAULT },
+	{ CS53L30_ASP_TDMTX_CTL4,	CS53L30_ASP_TDMTX_CTLx_DEFAULT },
+	{ CS53L30_ASP_TDMTX_EN1,	CS53L30_ASP_TDMTX_ENx_DEFAULT },
+	{ CS53L30_ASP_TDMTX_EN2,	CS53L30_ASP_TDMTX_ENx_DEFAULT },
+	{ CS53L30_ASP_TDMTX_EN3,	CS53L30_ASP_TDMTX_ENx_DEFAULT },
+	{ CS53L30_ASP_TDMTX_EN4,	CS53L30_ASP_TDMTX_ENx_DEFAULT },
+	{ CS53L30_ASP_TDMTX_EN5,	CS53L30_ASP_TDMTX_ENx_DEFAULT },
+	{ CS53L30_ASP_TDMTX_EN6,	CS53L30_ASP_TDMTX_ENx_DEFAULT },
+	{ CS53L30_ASP_CTL2,		CS53L30_ASP_CTL2_DEFAULT },
+	{ CS53L30_SFT_RAMP,		CS53L30_SFT_RMP_DEFAULT },
+	{ CS53L30_LRCK_CTL1,		CS53L30_LRCK_CTLx_DEFAULT },
+	{ CS53L30_LRCK_CTL2,		CS53L30_LRCK_CTLx_DEFAULT },
+	{ CS53L30_MUTEP_CTL1,		CS53L30_MUTEP_CTL1_DEFAULT },
+	{ CS53L30_MUTEP_CTL2,		CS53L30_MUTEP_CTL2_DEFAULT },
+	{ CS53L30_INBIAS_CTL1,		CS53L30_INBIAS_CTL1_DEFAULT },
+	{ CS53L30_INBIAS_CTL2,		CS53L30_INBIAS_CTL2_DEFAULT },
+	{ CS53L30_DMIC1_STR_CTL,	CS53L30_DMIC1_STR_CTL_DEFAULT },
+	{ CS53L30_DMIC2_STR_CTL,	CS53L30_DMIC2_STR_CTL_DEFAULT },
+	{ CS53L30_ADCDMIC1_CTL1,	CS53L30_ADCDMICx_CTL1_DEFAULT },
+	{ CS53L30_ADCDMIC1_CTL2,	CS53L30_ADCDMIC1_CTL2_DEFAULT },
+	{ CS53L30_ADC1_CTL3,		CS53L30_ADCx_CTL3_DEFAULT },
+	{ CS53L30_ADC1_NG_CTL,		CS53L30_ADCx_NG_CTL_DEFAULT },
+	{ CS53L30_ADC1A_AFE_CTL,	CS53L30_ADCxy_AFE_CTL_DEFAULT },
+	{ CS53L30_ADC1B_AFE_CTL,	CS53L30_ADCxy_AFE_CTL_DEFAULT },
+	{ CS53L30_ADC1A_DIG_VOL,	CS53L30_ADCxy_DIG_VOL_DEFAULT },
+	{ CS53L30_ADC1B_DIG_VOL,	CS53L30_ADCxy_DIG_VOL_DEFAULT },
+	{ CS53L30_ADCDMIC2_CTL1,	CS53L30_ADCDMICx_CTL1_DEFAULT },
+	{ CS53L30_ADCDMIC2_CTL2,	CS53L30_ADCDMIC1_CTL2_DEFAULT },
+	{ CS53L30_ADC2_CTL3,		CS53L30_ADCx_CTL3_DEFAULT },
+	{ CS53L30_ADC2_NG_CTL,		CS53L30_ADCx_NG_CTL_DEFAULT },
+	{ CS53L30_ADC2A_AFE_CTL,	CS53L30_ADCxy_AFE_CTL_DEFAULT },
+	{ CS53L30_ADC2B_AFE_CTL,	CS53L30_ADCxy_AFE_CTL_DEFAULT },
+	{ CS53L30_ADC2A_DIG_VOL,	CS53L30_ADCxy_DIG_VOL_DEFAULT },
+	{ CS53L30_ADC2B_DIG_VOL,	CS53L30_ADCxy_DIG_VOL_DEFAULT },
+	{ CS53L30_INT_MASK,		CS53L30_DEVICE_INT_MASK },
+};
+
+static bool cs53l30_volatile_register(struct device *dev, unsigned int reg)
+{
+	if (reg == CS53L30_IS)
+		return true;
+	else
+		return false;
+}
+
+static bool cs53l30_writeable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case CS53L30_DEVID_AB:
+	case CS53L30_DEVID_CD:
+	case CS53L30_DEVID_E:
+	case CS53L30_REVID:
+	case CS53L30_IS:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static bool cs53l30_readable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case CS53L30_DEVID_AB:
+	case CS53L30_DEVID_CD:
+	case CS53L30_DEVID_E:
+	case CS53L30_REVID:
+	case CS53L30_PWRCTL:
+	case CS53L30_MCLKCTL:
+	case CS53L30_INT_SR_CTL:
+	case CS53L30_MICBIAS_CTL:
+	case CS53L30_ASPCFG_CTL:
+	case CS53L30_ASP_CTL1:
+	case CS53L30_ASP_TDMTX_CTL1:
+	case CS53L30_ASP_TDMTX_CTL2:
+	case CS53L30_ASP_TDMTX_CTL3:
+	case CS53L30_ASP_TDMTX_CTL4:
+	case CS53L30_ASP_TDMTX_EN1:
+	case CS53L30_ASP_TDMTX_EN2:
+	case CS53L30_ASP_TDMTX_EN3:
+	case CS53L30_ASP_TDMTX_EN4:
+	case CS53L30_ASP_TDMTX_EN5:
+	case CS53L30_ASP_TDMTX_EN6:
+	case CS53L30_ASP_CTL2:
+	case CS53L30_SFT_RAMP:
+	case CS53L30_LRCK_CTL1:
+	case CS53L30_LRCK_CTL2:
+	case CS53L30_MUTEP_CTL1:
+	case CS53L30_MUTEP_CTL2:
+	case CS53L30_INBIAS_CTL1:
+	case CS53L30_INBIAS_CTL2:
+	case CS53L30_DMIC1_STR_CTL:
+	case CS53L30_DMIC2_STR_CTL:
+	case CS53L30_ADCDMIC1_CTL1:
+	case CS53L30_ADCDMIC1_CTL2:
+	case CS53L30_ADC1_CTL3:
+	case CS53L30_ADC1_NG_CTL:
+	case CS53L30_ADC1A_AFE_CTL:
+	case CS53L30_ADC1B_AFE_CTL:
+	case CS53L30_ADC1A_DIG_VOL:
+	case CS53L30_ADC1B_DIG_VOL:
+	case CS53L30_ADCDMIC2_CTL1:
+	case CS53L30_ADCDMIC2_CTL2:
+	case CS53L30_ADC2_CTL3:
+	case CS53L30_ADC2_NG_CTL:
+	case CS53L30_ADC2A_AFE_CTL:
+	case CS53L30_ADC2B_AFE_CTL:
+	case CS53L30_ADC2A_DIG_VOL:
+	case CS53L30_ADC2B_DIG_VOL:
+	case CS53L30_INT_MASK:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static DECLARE_TLV_DB_SCALE(adc_boost_tlv, 0, 2000, 0);
+static DECLARE_TLV_DB_SCALE(adc_ng_boost_tlv, 0, 3000, 0);
+static DECLARE_TLV_DB_SCALE(pga_tlv, -600, 50, 0);
+static DECLARE_TLV_DB_SCALE(dig_tlv, -9600, 100, 1);
+static DECLARE_TLV_DB_SCALE(pga_preamp_tlv, 0, 10000, 0);
+
+static const char * const input1_sel_text[] = {
+	"DMIC1 On AB In",
+	"DMIC1 On A In",
+	"DMIC1 On B In",
+	"ADC1 On AB In",
+	"ADC1 On A In",
+	"ADC1 On B In",
+	"DMIC1 Off ADC1 Off",
+};
+
+static unsigned int const input1_sel_values[] = {
+	CS53L30_CH_TYPE,
+	CS53L30_ADCxB_PDN | CS53L30_CH_TYPE,
+	CS53L30_ADCxA_PDN | CS53L30_CH_TYPE,
+	CS53L30_DMICx_PDN,
+	CS53L30_ADCxB_PDN | CS53L30_DMICx_PDN,
+	CS53L30_ADCxA_PDN | CS53L30_DMICx_PDN,
+	CS53L30_ADCxA_PDN | CS53L30_ADCxB_PDN | CS53L30_DMICx_PDN,
+};
+
+static const char * const input2_sel_text[] = {
+	"DMIC2 On AB In",
+	"DMIC2 On A In",
+	"DMIC2 On B In",
+	"ADC2 On AB In",
+	"ADC2 On A In",
+	"ADC2 On B In",
+	"DMIC2 Off ADC2 Off",
+};
+
+static unsigned int const input2_sel_values[] = {
+	0x0,
+	CS53L30_ADCxB_PDN,
+	CS53L30_ADCxA_PDN,
+	CS53L30_DMICx_PDN,
+	CS53L30_ADCxB_PDN | CS53L30_DMICx_PDN,
+	CS53L30_ADCxA_PDN | CS53L30_DMICx_PDN,
+	CS53L30_ADCxA_PDN | CS53L30_ADCxB_PDN | CS53L30_DMICx_PDN,
+};
+
+static const char * const input1_route_sel_text[] = {
+	"ADC1_SEL", "DMIC1_SEL",
+};
+
+static const struct soc_enum input1_route_sel_enum =
+	SOC_ENUM_SINGLE(CS53L30_ADCDMIC1_CTL1, CS53L30_CH_TYPE_SHIFT,
+			ARRAY_SIZE(input1_route_sel_text),
+			input1_route_sel_text);
+
+static SOC_VALUE_ENUM_SINGLE_DECL(input1_sel_enum, CS53L30_ADCDMIC1_CTL1, 0,
+				  CS53L30_ADCDMICx_PDN_MASK, input1_sel_text,
+				  input1_sel_values);
+
+static const struct snd_kcontrol_new input1_route_sel_mux =
+	SOC_DAPM_ENUM("Input 1 Route", input1_route_sel_enum);
+
+static const char * const input2_route_sel_text[] = {
+	"ADC2_SEL", "DMIC2_SEL",
+};
+
+/* Note: CS53L30_ADCDMIC1_CTL1 CH_TYPE controls inputs 1 and 2 */
+static const struct soc_enum input2_route_sel_enum =
+	SOC_ENUM_SINGLE(CS53L30_ADCDMIC1_CTL1, 0,
+			ARRAY_SIZE(input2_route_sel_text),
+			input2_route_sel_text);
+
+static SOC_VALUE_ENUM_SINGLE_DECL(input2_sel_enum, CS53L30_ADCDMIC2_CTL1, 0,
+				  CS53L30_ADCDMICx_PDN_MASK, input2_sel_text,
+				  input2_sel_values);
+
+static const struct snd_kcontrol_new input2_route_sel_mux =
+	SOC_DAPM_ENUM("Input 2 Route", input2_route_sel_enum);
+
+/*
+ * TB = 6144*(MCLK(int) scaling factor)/MCLK(internal)
+ * TB - Time base
+ * NOTE: If MCLK_INT_SCALE = 0, then TB=1
+ */
+static const char * const cs53l30_ng_delay_text[] = {
+	"TB*50ms", "TB*100ms", "TB*150ms", "TB*200ms",
+};
+
+static const struct soc_enum adc1_ng_delay_enum =
+	SOC_ENUM_SINGLE(CS53L30_ADC1_NG_CTL, CS53L30_ADCx_NG_DELAY_SHIFT,
+			ARRAY_SIZE(cs53l30_ng_delay_text),
+			cs53l30_ng_delay_text);
+
+static const struct soc_enum adc2_ng_delay_enum =
+	SOC_ENUM_SINGLE(CS53L30_ADC2_NG_CTL, CS53L30_ADCx_NG_DELAY_SHIFT,
+			ARRAY_SIZE(cs53l30_ng_delay_text),
+			cs53l30_ng_delay_text);
+
+/* The noise gate threshold selected will depend on NG Boost */
+static const char * const cs53l30_ng_thres_text[] = {
+	"-64dB/-34dB", "-66dB/-36dB", "-70dB/-40dB", "-73dB/-43dB",
+	"-76dB/-46dB", "-82dB/-52dB", "-58dB", "-64dB",
+};
+
+static const struct soc_enum adc1_ng_thres_enum =
+	SOC_ENUM_SINGLE(CS53L30_ADC1_NG_CTL, CS53L30_ADCx_NG_THRESH_SHIFT,
+			ARRAY_SIZE(cs53l30_ng_thres_text),
+			cs53l30_ng_thres_text);
+
+static const struct soc_enum adc2_ng_thres_enum =
+	SOC_ENUM_SINGLE(CS53L30_ADC2_NG_CTL, CS53L30_ADCx_NG_THRESH_SHIFT,
+			ARRAY_SIZE(cs53l30_ng_thres_text),
+			cs53l30_ng_thres_text);
+
+/* Corner frequencies are with an Fs of 48kHz. */
+static const char * const hpf_corner_freq_text[] = {
+	"1.86Hz", "120Hz", "235Hz", "466Hz",
+};
+
+static const struct soc_enum adc1_hpf_enum =
+	SOC_ENUM_SINGLE(CS53L30_ADC1_CTL3, CS53L30_ADCx_HPF_CF_SHIFT,
+			ARRAY_SIZE(hpf_corner_freq_text), hpf_corner_freq_text);
+
+static const struct soc_enum adc2_hpf_enum =
+	SOC_ENUM_SINGLE(CS53L30_ADC2_CTL3, CS53L30_ADCx_HPF_CF_SHIFT,
+			ARRAY_SIZE(hpf_corner_freq_text), hpf_corner_freq_text);
+
+static const struct snd_kcontrol_new cs53l30_snd_controls[] = {
+	SOC_SINGLE("Digital Soft-Ramp Switch", CS53L30_SFT_RAMP,
+		   CS53L30_DIGSFT_SHIFT, 1, 0),
+	SOC_SINGLE("ADC1 Noise Gate Ganging Switch", CS53L30_ADC1_CTL3,
+		   CS53L30_ADCx_NG_ALL_SHIFT, 1, 0),
+	SOC_SINGLE("ADC2 Noise Gate Ganging Switch", CS53L30_ADC2_CTL3,
+		   CS53L30_ADCx_NG_ALL_SHIFT, 1, 0),
+	SOC_SINGLE("ADC1A Noise Gate Enable Switch", CS53L30_ADC1_NG_CTL,
+		   CS53L30_ADCxA_NG_SHIFT, 1, 0),
+	SOC_SINGLE("ADC1B Noise Gate Enable Switch", CS53L30_ADC1_NG_CTL,
+		   CS53L30_ADCxB_NG_SHIFT, 1, 0),
+	SOC_SINGLE("ADC2A Noise Gate Enable Switch", CS53L30_ADC2_NG_CTL,
+		   CS53L30_ADCxA_NG_SHIFT, 1, 0),
+	SOC_SINGLE("ADC2B Noise Gate Enable Switch", CS53L30_ADC2_NG_CTL,
+		   CS53L30_ADCxB_NG_SHIFT, 1, 0),
+	SOC_SINGLE("ADC1 Notch Filter Switch", CS53L30_ADCDMIC1_CTL2,
+		   CS53L30_ADCx_NOTCH_DIS_SHIFT, 1, 1),
+	SOC_SINGLE("ADC2 Notch Filter Switch", CS53L30_ADCDMIC2_CTL2,
+		   CS53L30_ADCx_NOTCH_DIS_SHIFT, 1, 1),
+	SOC_SINGLE("ADC1A Invert Switch", CS53L30_ADCDMIC1_CTL2,
+		   CS53L30_ADCxA_INV_SHIFT, 1, 0),
+	SOC_SINGLE("ADC1B Invert Switch", CS53L30_ADCDMIC1_CTL2,
+		   CS53L30_ADCxB_INV_SHIFT, 1, 0),
+	SOC_SINGLE("ADC2A Invert Switch", CS53L30_ADCDMIC2_CTL2,
+		   CS53L30_ADCxA_INV_SHIFT, 1, 0),
+	SOC_SINGLE("ADC2B Invert Switch", CS53L30_ADCDMIC2_CTL2,
+		   CS53L30_ADCxB_INV_SHIFT, 1, 0),
+
+	SOC_SINGLE_TLV("ADC1A Digital Boost Volume", CS53L30_ADCDMIC1_CTL2,
+		       CS53L30_ADCxA_DIG_BOOST_SHIFT, 1, 0, adc_boost_tlv),
+	SOC_SINGLE_TLV("ADC1B Digital Boost Volume", CS53L30_ADCDMIC1_CTL2,
+		       CS53L30_ADCxB_DIG_BOOST_SHIFT, 1, 0, adc_boost_tlv),
+	SOC_SINGLE_TLV("ADC2A Digital Boost Volume", CS53L30_ADCDMIC2_CTL2,
+		       CS53L30_ADCxA_DIG_BOOST_SHIFT, 1, 0, adc_boost_tlv),
+	SOC_SINGLE_TLV("ADC2B Digital Boost Volume", CS53L30_ADCDMIC2_CTL2,
+		       CS53L30_ADCxB_DIG_BOOST_SHIFT, 1, 0, adc_boost_tlv),
+	SOC_SINGLE_TLV("ADC1 NG Boost Volume", CS53L30_ADC1_NG_CTL,
+		       CS53L30_ADCx_NG_BOOST_SHIFT, 1, 0, adc_ng_boost_tlv),
+	SOC_SINGLE_TLV("ADC2 NG Boost Volume", CS53L30_ADC2_NG_CTL,
+		       CS53L30_ADCx_NG_BOOST_SHIFT, 1, 0, adc_ng_boost_tlv),
+
+	SOC_DOUBLE_R_TLV("ADC1 Preamplifier Volume", CS53L30_ADC1A_AFE_CTL,
+			 CS53L30_ADC1B_AFE_CTL, CS53L30_ADCxy_PREAMP_SHIFT,
+			 2, 0, pga_preamp_tlv),
+	SOC_DOUBLE_R_TLV("ADC2 Preamplifier Volume", CS53L30_ADC2A_AFE_CTL,
+			 CS53L30_ADC2B_AFE_CTL, CS53L30_ADCxy_PREAMP_SHIFT,
+			 2, 0, pga_preamp_tlv),
+
+	SOC_ENUM("Input 1 Channel Select", input1_sel_enum),
+	SOC_ENUM("Input 2 Channel Select", input2_sel_enum),
+
+	SOC_ENUM("ADC1 HPF Select", adc1_hpf_enum),
+	SOC_ENUM("ADC2 HPF Select", adc2_hpf_enum),
+	SOC_ENUM("ADC1 NG Threshold", adc1_ng_thres_enum),
+	SOC_ENUM("ADC2 NG Threshold", adc2_ng_thres_enum),
+	SOC_ENUM("ADC1 NG Delay", adc1_ng_delay_enum),
+	SOC_ENUM("ADC2 NG Delay", adc2_ng_delay_enum),
+
+	SOC_SINGLE_SX_TLV("ADC1A PGA Volume",
+		    CS53L30_ADC1A_AFE_CTL, 0, 0x34, 0x18, pga_tlv),
+	SOC_SINGLE_SX_TLV("ADC1B PGA Volume",
+		    CS53L30_ADC1B_AFE_CTL, 0, 0x34, 0x18, pga_tlv),
+	SOC_SINGLE_SX_TLV("ADC2A PGA Volume",
+		    CS53L30_ADC2A_AFE_CTL, 0, 0x34, 0x18, pga_tlv),
+	SOC_SINGLE_SX_TLV("ADC2B PGA Volume",
+		    CS53L30_ADC2B_AFE_CTL, 0, 0x34, 0x18, pga_tlv),
+
+	SOC_SINGLE_SX_TLV("ADC1A Digital Volume",
+		    CS53L30_ADC1A_DIG_VOL, 0, 0xA0, 0x0C, dig_tlv),
+	SOC_SINGLE_SX_TLV("ADC1B Digital Volume",
+		    CS53L30_ADC1B_DIG_VOL, 0, 0xA0, 0x0C, dig_tlv),
+	SOC_SINGLE_SX_TLV("ADC2A Digital Volume",
+		    CS53L30_ADC2A_DIG_VOL, 0, 0xA0, 0x0C, dig_tlv),
+	SOC_SINGLE_SX_TLV("ADC2B Digital Volume",
+		    CS53L30_ADC2B_DIG_VOL, 0, 0xA0, 0x0C, dig_tlv),
+};
+
+static const struct snd_soc_dapm_widget cs53l30_dapm_widgets[] = {
+	SND_SOC_DAPM_INPUT("IN1_DMIC1"),
+	SND_SOC_DAPM_INPUT("IN2"),
+	SND_SOC_DAPM_INPUT("IN3_DMIC2"),
+	SND_SOC_DAPM_INPUT("IN4"),
+	SND_SOC_DAPM_SUPPLY("MIC1 Bias", CS53L30_MICBIAS_CTL,
+			    CS53L30_MIC1_BIAS_PDN_SHIFT, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("MIC2 Bias", CS53L30_MICBIAS_CTL,
+			    CS53L30_MIC2_BIAS_PDN_SHIFT, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("MIC3 Bias", CS53L30_MICBIAS_CTL,
+			    CS53L30_MIC3_BIAS_PDN_SHIFT, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("MIC4 Bias", CS53L30_MICBIAS_CTL,
+			    CS53L30_MIC4_BIAS_PDN_SHIFT, 1, NULL, 0),
+
+	SND_SOC_DAPM_AIF_OUT("ASP_SDOUT1", NULL, 0, CS53L30_ASP_CTL1,
+			     CS53L30_ASP_SDOUTx_PDN_SHIFT, 1),
+	SND_SOC_DAPM_AIF_OUT("ASP_SDOUT2", NULL, 0, CS53L30_ASP_CTL2,
+			     CS53L30_ASP_SDOUTx_PDN_SHIFT, 1),
+
+	SND_SOC_DAPM_MUX("Input Mux 1", SND_SOC_NOPM, 0, 0,
+			 &input1_route_sel_mux),
+	SND_SOC_DAPM_MUX("Input Mux 2", SND_SOC_NOPM, 0, 0,
+			 &input2_route_sel_mux),
+
+	SND_SOC_DAPM_ADC("ADC1A", NULL, CS53L30_ADCDMIC1_CTL1,
+			 CS53L30_ADCxA_PDN_SHIFT, 1),
+	SND_SOC_DAPM_ADC("ADC1B", NULL, CS53L30_ADCDMIC1_CTL1,
+			 CS53L30_ADCxB_PDN_SHIFT, 1),
+	SND_SOC_DAPM_ADC("ADC2A", NULL, CS53L30_ADCDMIC2_CTL1,
+			 CS53L30_ADCxA_PDN_SHIFT, 1),
+	SND_SOC_DAPM_ADC("ADC2B", NULL, CS53L30_ADCDMIC2_CTL1,
+			 CS53L30_ADCxB_PDN_SHIFT, 1),
+	SND_SOC_DAPM_ADC("DMIC1", NULL, CS53L30_ADCDMIC1_CTL1,
+			 CS53L30_DMICx_PDN_SHIFT, 1),
+	SND_SOC_DAPM_ADC("DMIC2", NULL, CS53L30_ADCDMIC2_CTL1,
+			 CS53L30_DMICx_PDN_SHIFT, 1),
+};
+
+static const struct snd_soc_dapm_route cs53l30_dapm_routes[] = {
+	/* ADC Input Paths */
+	{"ADC1A", NULL, "IN1_DMIC1"},
+	{"Input Mux 1", "ADC1_SEL", "ADC1A"},
+	{"ADC1B", NULL, "IN2"},
+
+	{"ADC2A", NULL, "IN3_DMIC2"},
+	{"Input Mux 2", "ADC2_SEL", "ADC2A"},
+	{"ADC2B", NULL, "IN4"},
+
+	/* MIC Bias Paths */
+	{"ADC1A", NULL, "MIC1 Bias"},
+	{"ADC1B", NULL, "MIC2 Bias"},
+	{"ADC2A", NULL, "MIC3 Bias"},
+	{"ADC2B", NULL, "MIC4 Bias"},
+
+	/* DMIC Paths */
+	{"DMIC1", NULL, "IN1_DMIC1"},
+	{"Input Mux 1", "DMIC1_SEL", "DMIC1"},
+
+	{"DMIC2", NULL, "IN3_DMIC2"},
+	{"Input Mux 2", "DMIC2_SEL", "DMIC2"},
+};
+
+static const struct snd_soc_dapm_route cs53l30_dapm_routes_sdout1[] = {
+	/* Output Paths when using SDOUT1 only */
+	{"ASP_SDOUT1", NULL, "ADC1A" },
+	{"ASP_SDOUT1", NULL, "Input Mux 1"},
+	{"ASP_SDOUT1", NULL, "ADC1B"},
+
+	{"ASP_SDOUT1", NULL, "ADC2A"},
+	{"ASP_SDOUT1", NULL, "Input Mux 2"},
+	{"ASP_SDOUT1", NULL, "ADC2B"},
+
+	{"Capture", NULL, "ASP_SDOUT1"},
+};
+
+static const struct snd_soc_dapm_route cs53l30_dapm_routes_sdout2[] = {
+	/* Output Paths when using both SDOUT1 and SDOUT2 */
+	{"ASP_SDOUT1", NULL, "ADC1A" },
+	{"ASP_SDOUT1", NULL, "Input Mux 1"},
+	{"ASP_SDOUT1", NULL, "ADC1B"},
+
+	{"ASP_SDOUT2", NULL, "ADC2A"},
+	{"ASP_SDOUT2", NULL, "Input Mux 2"},
+	{"ASP_SDOUT2", NULL, "ADC2B"},
+
+	{"Capture", NULL, "ASP_SDOUT1"},
+	{"Capture", NULL, "ASP_SDOUT2"},
+};
+
+struct cs53l30_mclk_div {
+	u32 mclk_rate;
+	u32 srate;
+	u8 asp_rate;
+	u8 internal_fs_ratio;
+	u8 mclk_int_scale;
+};
+
+static struct cs53l30_mclk_div cs53l30_mclk_coeffs[] = {
+	/* NOTE: Enable MCLK_INT_SCALE to save power. */
+
+	/* MCLK, Sample Rate, asp_rate, internal_fs_ratio, mclk_int_scale */
+	{5644800, 11025, 0x4, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{5644800, 22050, 0x8, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{5644800, 44100, 0xC, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+
+	{6000000,  8000, 0x1, 0, CS53L30_MCLK_INT_SCALE},
+	{6000000, 11025, 0x2, 0, CS53L30_MCLK_INT_SCALE},
+	{6000000, 12000, 0x4, 0, CS53L30_MCLK_INT_SCALE},
+	{6000000, 16000, 0x5, 0, CS53L30_MCLK_INT_SCALE},
+	{6000000, 22050, 0x6, 0, CS53L30_MCLK_INT_SCALE},
+	{6000000, 24000, 0x8, 0, CS53L30_MCLK_INT_SCALE},
+	{6000000, 32000, 0x9, 0, CS53L30_MCLK_INT_SCALE},
+	{6000000, 44100, 0xA, 0, CS53L30_MCLK_INT_SCALE},
+	{6000000, 48000, 0xC, 0, CS53L30_MCLK_INT_SCALE},
+
+	{6144000,  8000, 0x1, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6144000, 11025, 0x2, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6144000, 12000, 0x4, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6144000, 16000, 0x5, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6144000, 22050, 0x6, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6144000, 24000, 0x8, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6144000, 32000, 0x9, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6144000, 44100, 0xA, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6144000, 48000, 0xC, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+
+	{6400000,  8000, 0x1, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6400000, 11025, 0x2, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6400000, 12000, 0x4, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6400000, 16000, 0x5, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6400000, 22050, 0x6, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6400000, 24000, 0x8, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6400000, 32000, 0x9, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6400000, 44100, 0xA, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+	{6400000, 48000, 0xC, CS53L30_INTRNL_FS_RATIO, CS53L30_MCLK_INT_SCALE},
+};
+
+struct cs53l30_mclkx_div {
+	u32 mclkx;
+	u8 ratio;
+	u8 mclkdiv;
+};
+
+static struct cs53l30_mclkx_div cs53l30_mclkx_coeffs[] = {
+	{5644800,  1, CS53L30_MCLK_DIV_BY_1},
+	{6000000,  1, CS53L30_MCLK_DIV_BY_1},
+	{6144000,  1, CS53L30_MCLK_DIV_BY_1},
+	{11289600, 2, CS53L30_MCLK_DIV_BY_2},
+	{12288000, 2, CS53L30_MCLK_DIV_BY_2},
+	{12000000, 2, CS53L30_MCLK_DIV_BY_2},
+	{19200000, 3, CS53L30_MCLK_DIV_BY_3},
+};
+
+static int cs53l30_get_mclkx_coeff(int mclkx)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cs53l30_mclkx_coeffs); i++) {
+		if (cs53l30_mclkx_coeffs[i].mclkx == mclkx)
+			return i;
+	}
+
+	return -EINVAL;
+}
+
+static int cs53l30_get_mclk_coeff(int mclk_rate, int srate)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cs53l30_mclk_coeffs); i++) {
+		if (cs53l30_mclk_coeffs[i].mclk_rate == mclk_rate &&
+		    cs53l30_mclk_coeffs[i].srate == srate)
+			return i;
+	}
+
+	return -EINVAL;
+}
+
+static int cs53l30_set_sysclk(struct snd_soc_dai *dai,
+			      int clk_id, unsigned int freq, int dir)
+{
+	struct cs53l30_private *priv = snd_soc_codec_get_drvdata(dai->codec);
+	int mclkx_coeff;
+	u32 mclk_rate;
+
+	/* MCLKX -> MCLK */
+	mclkx_coeff = cs53l30_get_mclkx_coeff(freq);
+	if (mclkx_coeff < 0)
+		return mclkx_coeff;
+
+	mclk_rate = cs53l30_mclkx_coeffs[mclkx_coeff].mclkx /
+		    cs53l30_mclkx_coeffs[mclkx_coeff].ratio;
+
+	regmap_update_bits(priv->regmap, CS53L30_MCLKCTL,
+			   CS53L30_MCLK_DIV_MASK,
+			   cs53l30_mclkx_coeffs[mclkx_coeff].mclkdiv);
+
+	priv->mclk_rate = mclk_rate;
+
+	return 0;
+}
+
+static int cs53l30_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct cs53l30_private *priv = snd_soc_codec_get_drvdata(dai->codec);
+	u8 aspcfg = 0, aspctl1 = 0;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		aspcfg |= CS53L30_ASP_MS;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* DAI mode */
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		/* Set TDM_PDN to turn off TDM mode -- Reset default */
+		aspctl1 |= CS53L30_ASP_TDM_PDN;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		/*
+		 * Clear TDM_PDN to turn on TDM mode; Use ASP_SCLK_INV = 0
+		 * with SHIFT_LEFT = 1 combination as Figure 4-13 shows in
+		 * the CS53L30 datasheet
+		 */
+		aspctl1 |= CS53L30_SHIFT_LEFT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Check to see if the SCLK is inverted */
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_IB_NF:
+	case SND_SOC_DAIFMT_IB_IF:
+		aspcfg ^= CS53L30_ASP_SCLK_INV;
+		break;
+	default:
+		break;
+	}
+
+	regmap_update_bits(priv->regmap, CS53L30_ASPCFG_CTL,
+			   CS53L30_ASP_MS | CS53L30_ASP_SCLK_INV, aspcfg);
+
+	regmap_update_bits(priv->regmap, CS53L30_ASP_CTL1,
+			   CS53L30_ASP_TDM_PDN | CS53L30_SHIFT_LEFT, aspctl1);
+
+	return 0;
+}
+
+static int cs53l30_pcm_hw_params(struct snd_pcm_substream *substream,
+				 struct snd_pcm_hw_params *params,
+				 struct snd_soc_dai *dai)
+{
+	struct cs53l30_private *priv = snd_soc_codec_get_drvdata(dai->codec);
+	int srate = params_rate(params);
+	int mclk_coeff;
+
+	/* MCLK -> srate */
+	mclk_coeff = cs53l30_get_mclk_coeff(priv->mclk_rate, srate);
+	if (mclk_coeff < 0)
+		return -EINVAL;
+
+	regmap_update_bits(priv->regmap, CS53L30_INT_SR_CTL,
+			   CS53L30_INTRNL_FS_RATIO_MASK,
+			   cs53l30_mclk_coeffs[mclk_coeff].internal_fs_ratio);
+
+	regmap_update_bits(priv->regmap, CS53L30_MCLKCTL,
+			   CS53L30_MCLK_INT_SCALE_MASK,
+			   cs53l30_mclk_coeffs[mclk_coeff].mclk_int_scale);
+
+	regmap_update_bits(priv->regmap, CS53L30_ASPCFG_CTL,
+			   CS53L30_ASP_RATE_MASK,
+			   cs53l30_mclk_coeffs[mclk_coeff].asp_rate);
+
+	return 0;
+}
+
+static int cs53l30_set_bias_level(struct snd_soc_codec *codec,
+				  enum snd_soc_bias_level level)
+{
+	struct snd_soc_dapm_context *dapm = snd_soc_codec_get_dapm(codec);
+	struct cs53l30_private *priv = snd_soc_codec_get_drvdata(codec);
+	unsigned int reg;
+	int i, inter_max_check, ret;
+
+	switch (level) {
+	case SND_SOC_BIAS_ON:
+		break;
+	case SND_SOC_BIAS_PREPARE:
+		if (dapm->bias_level == SND_SOC_BIAS_STANDBY)
+			regmap_update_bits(priv->regmap, CS53L30_PWRCTL,
+					   CS53L30_PDN_LP_MASK, 0);
+		break;
+	case SND_SOC_BIAS_STANDBY:
+		if (dapm->bias_level == SND_SOC_BIAS_OFF) {
+			ret = clk_prepare_enable(priv->mclk);
+			if (ret) {
+				dev_err(codec->dev,
+					"failed to enable MCLK: %d\n", ret);
+				return ret;
+			}
+			regmap_update_bits(priv->regmap, CS53L30_MCLKCTL,
+					   CS53L30_MCLK_DIS_MASK, 0);
+			regmap_update_bits(priv->regmap, CS53L30_PWRCTL,
+					   CS53L30_PDN_ULP_MASK, 0);
+			msleep(50);
+		} else {
+			regmap_update_bits(priv->regmap, CS53L30_PWRCTL,
+					   CS53L30_PDN_ULP_MASK,
+					   CS53L30_PDN_ULP);
+		}
+		break;
+	case SND_SOC_BIAS_OFF:
+		regmap_update_bits(priv->regmap, CS53L30_INT_MASK,
+				   CS53L30_PDN_DONE, 0);
+		/*
+		 * If digital softramp is set, the amount of time required
+		 * for power down increases and depends on the digital
+		 * volume setting.
+		 */
+
+		/* Set the max possible time if digsft is set */
+		regmap_read(priv->regmap, CS53L30_SFT_RAMP, &reg);
+		if (reg & CS53L30_DIGSFT_MASK)
+			inter_max_check = CS53L30_PDN_POLL_MAX;
+		else
+			inter_max_check = 10;
+
+		regmap_update_bits(priv->regmap, CS53L30_PWRCTL,
+				   CS53L30_PDN_ULP_MASK,
+				   CS53L30_PDN_ULP);
+		/* PDN_DONE will take a min of 20ms to be set.*/
+		msleep(20);
+		/* Clr status */
+		regmap_read(priv->regmap, CS53L30_IS, &reg);
+		for (i = 0; i < inter_max_check; i++) {
+			if (inter_max_check < 10) {
+				usleep_range(1000, 1100);
+				regmap_read(priv->regmap, CS53L30_IS, &reg);
+				if (reg & CS53L30_PDN_DONE)
+					break;
+			} else {
+				usleep_range(10000, 10100);
+				regmap_read(priv->regmap, CS53L30_IS, &reg);
+				if (reg & CS53L30_PDN_DONE)
+					break;
+			}
+		}
+		/* PDN_DONE is set. We now can disable the MCLK */
+		regmap_update_bits(priv->regmap, CS53L30_INT_MASK,
+				   CS53L30_PDN_DONE, CS53L30_PDN_DONE);
+		regmap_update_bits(priv->regmap, CS53L30_MCLKCTL,
+				   CS53L30_MCLK_DIS_MASK,
+				   CS53L30_MCLK_DIS);
+		clk_disable_unprepare(priv->mclk);
+		break;
+	}
+
+	return 0;
+}
+
+static int cs53l30_set_tristate(struct snd_soc_dai *dai, int tristate)
+{
+	struct cs53l30_private *priv = snd_soc_codec_get_drvdata(dai->codec);
+	u8 val = tristate ? CS53L30_ASP_3ST : 0;
+
+	return regmap_update_bits(priv->regmap, CS53L30_ASP_CTL1,
+				  CS53L30_ASP_3ST_MASK, val);
+}
+
+static unsigned int const cs53l30_src_rates[] = {
+	8000, 11025, 12000, 16000, 22050, 24000, 32000, 44100, 48000
+};
+
+static struct snd_pcm_hw_constraint_list src_constraints = {
+	.count = ARRAY_SIZE(cs53l30_src_rates),
+	.list = cs53l30_src_rates,
+};
+
+static int cs53l30_pcm_startup(struct snd_pcm_substream *substream,
+			       struct snd_soc_dai *dai)
+{
+	snd_pcm_hw_constraint_list(substream->runtime, 0,
+				   SNDRV_PCM_HW_PARAM_RATE, &src_constraints);
+
+	return 0;
+}
+
+/*
+ * Note: CS53L30 counts the slot number per byte while ASoC counts the slot
+ * number per slot_width. So there is a difference between the slots of ASoC
+ * and the slots of CS53L30.
+ */
+static int cs53l30_set_dai_tdm_slot(struct snd_soc_dai *dai,
+				    unsigned int tx_mask, unsigned int rx_mask,
+				    int slots, int slot_width)
+{
+	struct cs53l30_private *priv = snd_soc_codec_get_drvdata(dai->codec);
+	unsigned int loc[CS53L30_TDM_SLOT_MAX] = {48, 48, 48, 48};
+	unsigned int slot_next, slot_step;
+	u64 tx_enable = 0;
+	int i;
+
+	if (!rx_mask) {
+		dev_err(dai->dev, "rx masks must not be 0\n");
+		return -EINVAL;
+	}
+
+	/* Assuming slot_width is not supposed to be greater than 64 */
+	if (slots <= 0 || slot_width <= 0 || slot_width > 64) {
+		dev_err(dai->dev, "invalid slot number or slot width\n");
+		return -EINVAL;
+	}
+
+	if (slot_width & 0x7) {
+		dev_err(dai->dev, "slot width must count in byte\n");
+		return -EINVAL;
+	}
+
+	/* How many bytes in each ASoC slot */
+	slot_step = slot_width >> 3;
+
+	for (i = 0; rx_mask && i < CS53L30_TDM_SLOT_MAX; i++) {
+		/* Find the first slot from LSB */
+		slot_next = __ffs(rx_mask);
+		/* Save the slot location by converting to CS53L30 slot */
+		loc[i] = slot_next * slot_step;
+		/* Create the mask of CS53L30 slot */
+		tx_enable |= (u64)((u64)(1 << slot_step) - 1) << (u64)loc[i];
+		/* Clear this slot from rx_mask */
+		rx_mask &= ~(1 << slot_next);
+	}
+
+	/* Error out to avoid slot shift */
+	if (rx_mask && i == CS53L30_TDM_SLOT_MAX) {
+		dev_err(dai->dev, "rx_mask exceeds max slot number: %d\n",
+			CS53L30_TDM_SLOT_MAX);
+		return -EINVAL;
+	}
+
+	/* Validate the last active CS53L30 slot */
+	slot_next = loc[i - 1] + slot_step - 1;
+	if (slot_next > 47) {
+		dev_err(dai->dev, "slot selection out of bounds: %u\n",
+			slot_next);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < CS53L30_TDM_SLOT_MAX && loc[i] != 48; i++) {
+		regmap_update_bits(priv->regmap, CS53L30_ASP_TDMTX_CTL(i),
+				   CS53L30_ASP_CHx_TX_LOC_MASK, loc[i]);
+		dev_dbg(dai->dev, "loc[%d]=%x\n", i, loc[i]);
+	}
+
+	for (i = 0; i < CS53L30_ASP_TDMTX_ENx_MAX && tx_enable; i++) {
+		regmap_write(priv->regmap, CS53L30_ASP_TDMTX_ENx(i),
+			     tx_enable & 0xff);
+		tx_enable >>= 8;
+		dev_dbg(dai->dev, "en_reg=%x, tx_enable=%llx\n",
+			CS53L30_ASP_TDMTX_ENx(i), tx_enable & 0xff);
+	}
+
+	return 0;
+}
+
+static int cs53l30_mute_stream(struct snd_soc_dai *dai, int mute, int stream)
+{
+	struct cs53l30_private *priv = snd_soc_codec_get_drvdata(dai->codec);
+
+	if (priv->mute_gpio)
+		gpiod_set_value_cansleep(priv->mute_gpio, mute);
+
+	return 0;
+}
+
+/* SNDRV_PCM_RATE_KNOT -> 12000, 24000 Hz, limit with constraint list */
+#define CS53L30_RATES (SNDRV_PCM_RATE_8000_48000 | SNDRV_PCM_RATE_KNOT)
+
+#define CS53L30_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE |\
+			SNDRV_PCM_FMTBIT_S24_LE)
+
+static const struct snd_soc_dai_ops cs53l30_ops = {
+	.startup = cs53l30_pcm_startup,
+	.hw_params = cs53l30_pcm_hw_params,
+	.set_fmt = cs53l30_set_dai_fmt,
+	.set_sysclk = cs53l30_set_sysclk,
+	.set_tristate = cs53l30_set_tristate,
+	.set_tdm_slot = cs53l30_set_dai_tdm_slot,
+	.mute_stream = cs53l30_mute_stream,
+};
+
+static struct snd_soc_dai_driver cs53l30_dai = {
+	.name = "cs53l30",
+	.capture = {
+		.stream_name = "Capture",
+		.channels_min = 1,
+		.channels_max = 4,
+		.rates = CS53L30_RATES,
+		.formats = CS53L30_FORMATS,
+	},
+	.ops = &cs53l30_ops,
+	.symmetric_rates = 1,
+};
+
+static int cs53l30_codec_probe(struct snd_soc_codec *codec)
+{
+	struct cs53l30_private *priv = snd_soc_codec_get_drvdata(codec);
+	struct snd_soc_dapm_context *dapm = snd_soc_codec_get_dapm(codec);
+
+	if (priv->use_sdout2)
+		snd_soc_dapm_add_routes(dapm, cs53l30_dapm_routes_sdout2,
+					ARRAY_SIZE(cs53l30_dapm_routes_sdout2));
+	else
+		snd_soc_dapm_add_routes(dapm, cs53l30_dapm_routes_sdout1,
+					ARRAY_SIZE(cs53l30_dapm_routes_sdout1));
+
+	return 0;
+}
+
+static struct snd_soc_codec_driver cs53l30_driver = {
+	.probe = cs53l30_codec_probe,
+	.set_bias_level = cs53l30_set_bias_level,
+	.idle_bias_off = true,
+
+	.dapm_widgets = cs53l30_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(cs53l30_dapm_widgets),
+	.dapm_routes = cs53l30_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(cs53l30_dapm_routes),
+
+	.controls = cs53l30_snd_controls,
+	.num_controls = ARRAY_SIZE(cs53l30_snd_controls),
+};
+
+static struct regmap_config cs53l30_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = CS53L30_MAX_REGISTER,
+	.reg_defaults = cs53l30_reg_defaults,
+	.num_reg_defaults = ARRAY_SIZE(cs53l30_reg_defaults),
+	.volatile_reg = cs53l30_volatile_register,
+	.writeable_reg = cs53l30_writeable_register,
+	.readable_reg = cs53l30_readable_register,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static int cs53l30_i2c_probe(struct i2c_client *client,
+			     const struct i2c_device_id *id)
+{
+	const struct device_node *np = client->dev.of_node;
+	struct device *dev = &client->dev;
+	struct cs53l30_private *cs53l30;
+	unsigned int devid = 0;
+	unsigned int reg;
+	int ret = 0, i;
+	u8 val;
+
+	cs53l30 = devm_kzalloc(dev, sizeof(*cs53l30), GFP_KERNEL);
+	if (!cs53l30)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(cs53l30->supplies); i++)
+		cs53l30->supplies[i].supply = cs53l30_supply_names[i];
+
+	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(cs53l30->supplies),
+				      cs53l30->supplies);
+	if (ret) {
+		dev_err(dev, "failed to get supplies: %d\n", ret);
+		return ret;
+	}
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(cs53l30->supplies),
+				    cs53l30->supplies);
+	if (ret) {
+		dev_err(dev, "failed to enable supplies: %d\n", ret);
+		return ret;
+	}
+
+	/* Reset the Device */
+	cs53l30->reset_gpio = devm_gpiod_get_optional(dev, "reset",
+						      GPIOD_OUT_LOW);
+	if (IS_ERR(cs53l30->reset_gpio)) {
+		ret = PTR_ERR(cs53l30->reset_gpio);
+		goto error;
+	}
+
+	if (cs53l30->reset_gpio)
+		gpiod_set_value_cansleep(cs53l30->reset_gpio, 1);
+
+	i2c_set_clientdata(client, cs53l30);
+
+	cs53l30->mclk_rate = 0;
+
+	cs53l30->regmap = devm_regmap_init_i2c(client, &cs53l30_regmap);
+	if (IS_ERR(cs53l30->regmap)) {
+		ret = PTR_ERR(cs53l30->regmap);
+		dev_err(dev, "regmap_init() failed: %d\n", ret);
+		goto error;
+	}
+
+	/* Initialize codec */
+	ret = regmap_read(cs53l30->regmap, CS53L30_DEVID_AB, &reg);
+	devid = reg << 12;
+
+	ret = regmap_read(cs53l30->regmap, CS53L30_DEVID_CD, &reg);
+	devid |= reg << 4;
+
+	ret = regmap_read(cs53l30->regmap, CS53L30_DEVID_E, &reg);
+	devid |= (reg & 0xF0) >> 4;
+
+	if (devid != CS53L30_DEVID) {
+		ret = -ENODEV;
+		dev_err(dev, "Device ID (%X). Expected %X\n",
+			devid, CS53L30_DEVID);
+		goto error;
+	}
+
+	ret = regmap_read(cs53l30->regmap, CS53L30_REVID, &reg);
+	if (ret < 0) {
+		dev_err(dev, "failed to get Revision ID: %d\n", ret);
+		goto error;
+	}
+
+	/* Check if MCLK provided */
+	cs53l30->mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(cs53l30->mclk)) {
+		if (PTR_ERR(cs53l30->mclk) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto error;
+		}
+		/* Otherwise mark the mclk pointer to NULL */
+		cs53l30->mclk = NULL;
+	}
+
+	/* Fetch the MUTE control */
+	cs53l30->mute_gpio = devm_gpiod_get_optional(dev, "mute",
+						     GPIOD_OUT_HIGH);
+	if (IS_ERR(cs53l30->mute_gpio)) {
+		ret = PTR_ERR(cs53l30->mute_gpio);
+		goto error;
+	}
+
+	if (cs53l30->mute_gpio) {
+		/* Enable MUTE controls via MUTE pin */
+		regmap_write(cs53l30->regmap, CS53L30_MUTEP_CTL1,
+			     CS53L30_MUTEP_CTL1_MUTEALL);
+		/* Flip the polarity of MUTE pin */
+		if (gpiod_is_active_low(cs53l30->mute_gpio))
+			regmap_update_bits(cs53l30->regmap, CS53L30_MUTEP_CTL2,
+					   CS53L30_MUTE_PIN_POLARITY, 0);
+	}
+
+	if (!of_property_read_u8(np, "cirrus,micbias-lvl", &val))
+		regmap_update_bits(cs53l30->regmap, CS53L30_MICBIAS_CTL,
+				   CS53L30_MIC_BIAS_CTRL_MASK, val);
+
+	if (of_property_read_bool(np, "cirrus,use-sdout2"))
+		cs53l30->use_sdout2 = true;
+
+	dev_info(dev, "Cirrus Logic CS53L30, Revision: %02X\n", reg & 0xFF);
+
+	ret = snd_soc_register_codec(dev, &cs53l30_driver, &cs53l30_dai, 1);
+	if (ret) {
+		dev_err(dev, "failed to register codec: %d\n", ret);
+		goto error;
+	}
+
+	return 0;
+
+error:
+	regulator_bulk_disable(ARRAY_SIZE(cs53l30->supplies),
+			       cs53l30->supplies);
+	return ret;
+}
+
+static int cs53l30_i2c_remove(struct i2c_client *client)
+{
+	struct cs53l30_private *cs53l30 = i2c_get_clientdata(client);
+
+	snd_soc_unregister_codec(&client->dev);
+
+	/* Hold down reset */
+	if (cs53l30->reset_gpio)
+		gpiod_set_value_cansleep(cs53l30->reset_gpio, 0);
+
+	regulator_bulk_disable(ARRAY_SIZE(cs53l30->supplies),
+			       cs53l30->supplies);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int cs53l30_runtime_suspend(struct device *dev)
+{
+	struct cs53l30_private *cs53l30 = dev_get_drvdata(dev);
+
+	regcache_cache_only(cs53l30->regmap, true);
+
+	/* Hold down reset */
+	if (cs53l30->reset_gpio)
+		gpiod_set_value_cansleep(cs53l30->reset_gpio, 0);
+
+	regulator_bulk_disable(ARRAY_SIZE(cs53l30->supplies),
+			       cs53l30->supplies);
+
+	return 0;
+}
+
+static int cs53l30_runtime_resume(struct device *dev)
+{
+	struct cs53l30_private *cs53l30 = dev_get_drvdata(dev);
+	int ret;
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(cs53l30->supplies),
+				    cs53l30->supplies);
+	if (ret) {
+		dev_err(dev, "failed to enable supplies: %d\n", ret);
+		return ret;
+	}
+
+	if (cs53l30->reset_gpio)
+		gpiod_set_value_cansleep(cs53l30->reset_gpio, 1);
+
+	regcache_cache_only(cs53l30->regmap, false);
+	ret = regcache_sync(cs53l30->regmap);
+	if (ret) {
+		dev_err(dev, "failed to synchronize regcache: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops cs53l30_runtime_pm = {
+	SET_RUNTIME_PM_OPS(cs53l30_runtime_suspend, cs53l30_runtime_resume,
+			   NULL)
+};
+
+static const struct of_device_id cs53l30_of_match[] = {
+	{ .compatible = "cirrus,cs53l30", },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, cs53l30_of_match);
+
+static const struct i2c_device_id cs53l30_id[] = {
+	{ "cs53l30", 0 },
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, cs53l30_id);
+
+static struct i2c_driver cs53l30_i2c_driver = {
+	.driver = {
+		.name = "cs53l30",
+		.pm = &cs53l30_runtime_pm,
+	},
+	.id_table = cs53l30_id,
+	.probe = cs53l30_i2c_probe,
+	.remove = cs53l30_i2c_remove,
+};
+
+module_i2c_driver(cs53l30_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC CS53L30 driver");
+MODULE_AUTHOR("Paul Handrigan, Cirrus Logic Inc, <Paul.Handrigan@cirrus.com>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/cs53l30.h b/sound/soc/codecs/cs53l30.h
new file mode 100644
index 000000000000..5e39da568749
--- /dev/null
+++ b/sound/soc/codecs/cs53l30.h
@@ -0,0 +1,459 @@
+/*
+ * ALSA SoC CS53L30 codec driver
+ *
+ * Copyright 2015 Cirrus Logic, Inc.
+ *
+ * Author: Paul Handrigan <Paul.Handrigan@cirrus.com>,
+ *         Tim Howe <Tim.Howe@cirrus.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __CS53L30_H__
+#define __CS53L30_H__
+
+/* I2C Registers */
+#define CS53L30_DEVID_AB	0x01	 /* Device ID A & B [RO]. */
+#define CS53L30_DEVID_CD	0x02     /* Device ID C & D [RO]. */
+#define CS53L30_DEVID_E		0x03     /* Device ID E [RO]. */
+#define CS53L30_REVID		0x05     /* Revision ID [RO]. */
+#define CS53L30_PWRCTL		0x06     /* Power Control. */
+#define CS53L30_MCLKCTL		0x07     /* MCLK Control. */
+#define CS53L30_INT_SR_CTL	0x08     /* Internal Sample Rate Control. */
+#define CS53L30_MICBIAS_CTL	0x0A     /* Mic Bias Control. */
+#define CS53L30_ASPCFG_CTL	0x0C     /* ASP Config Control. */
+#define CS53L30_ASP_CTL1	0x0D     /* ASP1 Control. */
+#define CS53L30_ASP_TDMTX_CTL1	0x0E     /* ASP1 TDM TX Control 1 */
+#define CS53L30_ASP_TDMTX_CTL2	0x0F     /* ASP1 TDM TX Control 2 */
+#define CS53L30_ASP_TDMTX_CTL3	0x10     /* ASP1 TDM TX Control 3 */
+#define CS53L30_ASP_TDMTX_CTL4	0x11     /* ASP1 TDM TX Control 4 */
+#define CS53L30_ASP_TDMTX_EN1	0x12     /* ASP1 TDM TX Enable 1 */
+#define CS53L30_ASP_TDMTX_EN2	0x13     /* ASP1 TDM TX Enable 2 */
+#define CS53L30_ASP_TDMTX_EN3	0x14     /* ASP1 TDM TX Enable 3 */
+#define CS53L30_ASP_TDMTX_EN4	0x15     /* ASP1 TDM TX Enable 4 */
+#define CS53L30_ASP_TDMTX_EN5	0x16     /* ASP1 TDM TX Enable 5 */
+#define CS53L30_ASP_TDMTX_EN6	0x17     /* ASP1 TDM TX Enable 6 */
+#define CS53L30_ASP_CTL2	0x18     /* ASP2 Control. */
+#define CS53L30_SFT_RAMP	0x1A     /* Soft Ramp Control. */
+#define CS53L30_LRCK_CTL1	0x1B     /* LRCK Control 1. */
+#define CS53L30_LRCK_CTL2	0x1C     /* LRCK Control 2. */
+#define CS53L30_MUTEP_CTL1	0x1F     /* Mute Pin Control 1. */
+#define CS53L30_MUTEP_CTL2	0x20     /* Mute Pin Control 2. */
+#define CS53L30_INBIAS_CTL1	0x21     /* Input Bias Control 1. */
+#define CS53L30_INBIAS_CTL2	0x22     /* Input Bias Control 2. */
+#define CS53L30_DMIC1_STR_CTL   0x23     /* DMIC1 Stereo Control. */
+#define CS53L30_DMIC2_STR_CTL   0x24     /* DMIC2 Stereo Control. */
+#define CS53L30_ADCDMIC1_CTL1   0x25     /* ADC1/DMIC1 Control 1. */
+#define CS53L30_ADCDMIC1_CTL2   0x26     /* ADC1/DMIC1 Control 2. */
+#define CS53L30_ADC1_CTL3	0x27     /* ADC1 Control 3. */
+#define CS53L30_ADC1_NG_CTL	0x28     /* ADC1 Noise Gate Control. */
+#define CS53L30_ADC1A_AFE_CTL	0x29     /* ADC1A AFE Control. */
+#define CS53L30_ADC1B_AFE_CTL	0x2A     /* ADC1B AFE Control. */
+#define CS53L30_ADC1A_DIG_VOL	0x2B     /* ADC1A Digital Volume. */
+#define CS53L30_ADC1B_DIG_VOL	0x2C     /* ADC1B Digital Volume. */
+#define CS53L30_ADCDMIC2_CTL1   0x2D     /* ADC2/DMIC2 Control 1. */
+#define CS53L30_ADCDMIC2_CTL2   0x2E     /* ADC2/DMIC2 Control 2. */
+#define CS53L30_ADC2_CTL3	0x2F     /* ADC2 Control 3. */
+#define CS53L30_ADC2_NG_CTL	0x30     /* ADC2 Noise Gate Control. */
+#define CS53L30_ADC2A_AFE_CTL	0x31     /* ADC2A AFE Control. */
+#define CS53L30_ADC2B_AFE_CTL	0x32     /* ADC2B AFE Control. */
+#define CS53L30_ADC2A_DIG_VOL	0x33     /* ADC2A Digital Volume. */
+#define CS53L30_ADC2B_DIG_VOL	0x34     /* ADC2B Digital Volume. */
+#define CS53L30_INT_MASK	0x35     /* Interrupt Mask. */
+#define CS53L30_IS		0x36     /* Interrupt Status. */
+#define CS53L30_MAX_REGISTER	0x36
+
+#define CS53L30_TDM_SLOT_MAX		4
+#define CS53L30_ASP_TDMTX_CTL(x)	(CS53L30_ASP_TDMTX_CTL1 + (x))
+/* x : index for registers; n : index for slot; 8 slots per register */
+#define CS53L30_ASP_TDMTX_ENx(x)	(CS53L30_ASP_TDMTX_EN6 - (x))
+#define CS53L30_ASP_TDMTX_ENn(n)	CS53L30_ASP_TDMTX_ENx((n) >> 3)
+#define CS53L30_ASP_TDMTX_ENx_MAX	6
+
+/* Device ID */
+#define CS53L30_DEVID		0x53A30
+
+/* PDN_DONE Poll Maximum
+ * If soft ramp is set it will take much longer to power down
+ * the system.
+ */
+#define CS53L30_PDN_POLL_MAX	90
+
+/* Bitfield Definitions */
+
+/* R6 (0x06) CS53L30_PWRCTL - Power Control */
+#define CS53L30_PDN_ULP_SHIFT		7
+#define CS53L30_PDN_ULP_MASK		(1 << CS53L30_PDN_ULP_SHIFT)
+#define CS53L30_PDN_ULP			(1 << CS53L30_PDN_ULP_SHIFT)
+#define CS53L30_PDN_LP_SHIFT		6
+#define CS53L30_PDN_LP_MASK		(1 << CS53L30_PDN_LP_SHIFT)
+#define CS53L30_PDN_LP			(1 << CS53L30_PDN_LP_SHIFT)
+#define CS53L30_DISCHARGE_FILT_SHIFT	5
+#define CS53L30_DISCHARGE_FILT_MASK	(1 << CS53L30_DISCHARGE_FILT_SHIFT)
+#define CS53L30_DISCHARGE_FILT		(1 << CS53L30_DISCHARGE_FILT_SHIFT)
+#define CS53L30_THMS_PDN_SHIFT		4
+#define CS53L30_THMS_PDN_MASK		(1 << CS53L30_THMS_PDN_SHIFT)
+#define CS53L30_THMS_PDN		(1 << CS53L30_THMS_PDN_SHIFT)
+
+#define CS53L30_PWRCTL_DEFAULT		(CS53L30_THMS_PDN)
+
+/* R7 (0x07) CS53L30_MCLKCTL - MCLK Control */
+#define CS53L30_MCLK_DIS_SHIFT		7
+#define CS53L30_MCLK_DIS_MASK		(1 << CS53L30_MCLK_DIS_SHIFT)
+#define CS53L30_MCLK_DIS		(1 << CS53L30_MCLK_DIS_SHIFT)
+#define CS53L30_MCLK_INT_SCALE_SHIFT	6
+#define CS53L30_MCLK_INT_SCALE_MASK	(1 << CS53L30_MCLK_INT_SCALE_SHIFT)
+#define CS53L30_MCLK_INT_SCALE		(1 << CS53L30_MCLK_INT_SCALE_SHIFT)
+#define CS53L30_DMIC_DRIVE_SHIFT	5
+#define CS53L30_DMIC_DRIVE_MASK		(1 << CS53L30_DMIC_DRIVE_SHIFT)
+#define CS53L30_DMIC_DRIVE		(1 << CS53L30_DMIC_DRIVE_SHIFT)
+#define CS53L30_MCLK_DIV_SHIFT		2
+#define CS53L30_MCLK_DIV_WIDTH		2
+#define CS53L30_MCLK_DIV_MASK		(((1 << CS53L30_MCLK_DIV_WIDTH) - 1) << CS53L30_MCLK_DIV_SHIFT)
+#define CS53L30_MCLK_DIV_BY_1		(0x0 << CS53L30_MCLK_DIV_SHIFT)
+#define CS53L30_MCLK_DIV_BY_2		(0x1 << CS53L30_MCLK_DIV_SHIFT)
+#define CS53L30_MCLK_DIV_BY_3		(0x2 << CS53L30_MCLK_DIV_SHIFT)
+#define CS53L30_SYNC_EN_SHIFT		1
+#define CS53L30_SYNC_EN_MASK		(1 << CS53L30_SYNC_EN_SHIFT)
+#define CS53L30_SYNC_EN			(1 << CS53L30_SYNC_EN_SHIFT)
+
+#define CS53L30_MCLKCTL_DEFAULT		(CS53L30_MCLK_DIV_BY_2)
+
+/* R8 (0x08) CS53L30_INT_SR_CTL - Internal Sample Rate Control */
+#define CS53L30_INTRNL_FS_RATIO_SHIFT	4
+#define CS53L30_INTRNL_FS_RATIO_MASK	(1 << CS53L30_INTRNL_FS_RATIO_SHIFT)
+#define CS53L30_INTRNL_FS_RATIO		(1 << CS53L30_INTRNL_FS_RATIO_SHIFT)
+#define CS53L30_MCLK_19MHZ_EN_SHIFT	0
+#define CS53L30_MCLK_19MHZ_EN_MASK	(1 << CS53L30_MCLK_19MHZ_EN_SHIFT)
+#define CS53L30_MCLK_19MHZ_EN		(1 << CS53L30_MCLK_19MHZ_EN_SHIFT)
+
+/* 0x6 << 1 is reserved bits */
+#define CS53L30_INT_SR_CTL_DEFAULT	(CS53L30_INTRNL_FS_RATIO | 0x6 << 1)
+
+/* R10 (0x0A) CS53L30_MICBIAS_CTL - Mic Bias Control */
+#define CS53L30_MIC4_BIAS_PDN_SHIFT	7
+#define CS53L30_MIC4_BIAS_PDN_MASK	(1 << CS53L30_MIC4_BIAS_PDN_SHIFT)
+#define CS53L30_MIC4_BIAS_PDN		(1 << CS53L30_MIC4_BIAS_PDN_SHIFT)
+#define CS53L30_MIC3_BIAS_PDN_SHIFT	6
+#define CS53L30_MIC3_BIAS_PDN_MASK	(1 << CS53L30_MIC3_BIAS_PDN_SHIFT)
+#define CS53L30_MIC3_BIAS_PDN		(1 << CS53L30_MIC3_BIAS_PDN_SHIFT)
+#define CS53L30_MIC2_BIAS_PDN_SHIFT	5
+#define CS53L30_MIC2_BIAS_PDN_MASK	(1 << CS53L30_MIC2_BIAS_PDN_SHIFT)
+#define CS53L30_MIC2_BIAS_PDN		(1 << CS53L30_MIC2_BIAS_PDN_SHIFT)
+#define CS53L30_MIC1_BIAS_PDN_SHIFT	4
+#define CS53L30_MIC1_BIAS_PDN_MASK	(1 << CS53L30_MIC1_BIAS_PDN_SHIFT)
+#define CS53L30_MIC1_BIAS_PDN		(1 << CS53L30_MIC1_BIAS_PDN_SHIFT)
+#define CS53L30_MICx_BIAS_PDN		(0xf << CS53L30_MIC1_BIAS_PDN_SHIFT)
+#define CS53L30_VP_MIN_SHIFT		2
+#define CS53L30_VP_MIN_MASK		(1 << CS53L30_VP_MIN_SHIFT)
+#define CS53L30_VP_MIN			(1 << CS53L30_VP_MIN_SHIFT)
+#define CS53L30_MIC_BIAS_CTRL_SHIFT	0
+#define CS53L30_MIC_BIAS_CTRL_WIDTH	2
+#define CS53L30_MIC_BIAS_CTRL_MASK	(((1 << CS53L30_MIC_BIAS_CTRL_WIDTH) - 1) << CS53L30_MIC_BIAS_CTRL_SHIFT)
+#define CS53L30_MIC_BIAS_CTRL_HIZ	(0 << CS53L30_MIC_BIAS_CTRL_SHIFT)
+#define CS53L30_MIC_BIAS_CTRL_1V8	(1 << CS53L30_MIC_BIAS_CTRL_SHIFT)
+#define CS53L30_MIC_BIAS_CTRL_2V75	(2 << CS53L30_MIC_BIAS_CTRL_SHIFT)
+
+#define CS53L30_MICBIAS_CTL_DEFAULT	(CS53L30_MICx_BIAS_PDN | CS53L30_VP_MIN)
+
+/* R12 (0x0C) CS53L30_ASPCFG_CTL - ASP Configuration Control */
+#define CS53L30_ASP_MS_SHIFT		7
+#define CS53L30_ASP_MS_MASK		(1 << CS53L30_ASP_MS_SHIFT)
+#define CS53L30_ASP_MS			(1 << CS53L30_ASP_MS_SHIFT)
+#define CS53L30_ASP_SCLK_INV_SHIFT	4
+#define CS53L30_ASP_SCLK_INV_MASK	(1 << CS53L30_ASP_SCLK_INV_SHIFT)
+#define CS53L30_ASP_SCLK_INV		(1 << CS53L30_ASP_SCLK_INV_SHIFT)
+#define CS53L30_ASP_RATE_SHIFT		0
+#define CS53L30_ASP_RATE_WIDTH		4
+#define CS53L30_ASP_RATE_MASK		(((1 << CS53L30_ASP_RATE_WIDTH) - 1) << CS53L30_ASP_RATE_SHIFT)
+#define CS53L30_ASP_RATE_48K		(0xc << CS53L30_ASP_RATE_SHIFT)
+
+#define CS53L30_ASPCFG_CTL_DEFAULT	(CS53L30_ASP_RATE_48K)
+
+/* R13/R24 (0x0D/0x18) CS53L30_ASP_CTL1 & CS53L30_ASP_CTL2 - ASP Control 1~2 */
+#define CS53L30_ASP_TDM_PDN_SHIFT	7
+#define CS53L30_ASP_TDM_PDN_MASK	(1 << CS53L30_ASP_TDM_PDN_SHIFT)
+#define CS53L30_ASP_TDM_PDN		(1 << CS53L30_ASP_TDM_PDN_SHIFT)
+#define CS53L30_ASP_SDOUTx_PDN_SHIFT	6
+#define CS53L30_ASP_SDOUTx_PDN_MASK	(1 << CS53L30_ASP_SDOUTx_PDN_SHIFT)
+#define CS53L30_ASP_SDOUTx_PDN		(1 << CS53L30_ASP_SDOUTx_PDN_SHIFT)
+#define CS53L30_ASP_3ST_SHIFT		5
+#define CS53L30_ASP_3ST_MASK		(1 << CS53L30_ASP_3ST_SHIFT)
+#define CS53L30_ASP_3ST			(1 << CS53L30_ASP_3ST_SHIFT)
+#define CS53L30_SHIFT_LEFT_SHIFT	4
+#define CS53L30_SHIFT_LEFT_MASK		(1 << CS53L30_SHIFT_LEFT_SHIFT)
+#define CS53L30_SHIFT_LEFT		(1 << CS53L30_SHIFT_LEFT_SHIFT)
+#define CS53L30_ASP_SDOUTx_DRIVE_SHIFT	0
+#define CS53L30_ASP_SDOUTx_DRIVE_MASK	(1 << CS53L30_ASP_SDOUTx_DRIVE_SHIFT)
+#define CS53L30_ASP_SDOUTx_DRIVE	(1 << CS53L30_ASP_SDOUTx_DRIVE_SHIFT)
+
+#define CS53L30_ASP_CTL1_DEFAULT	(CS53L30_ASP_TDM_PDN)
+#define CS53L30_ASP_CTL2_DEFAULT	(0)
+
+/* R14 (0x0E) ~ R17 (0x11) CS53L30_ASP_TDMTX_CTLx - ASP TDM TX Control 1~4 */
+#define CS53L30_ASP_CHx_TX_STATE_SHIFT	7
+#define CS53L30_ASP_CHx_TX_STATE_MASK	(1 << CS53L30_ASP_CHx_TX_STATE_SHIFT)
+#define CS53L30_ASP_CHx_TX_STATE	(1 << CS53L30_ASP_CHx_TX_STATE_SHIFT)
+#define CS53L30_ASP_CHx_TX_LOC_SHIFT	0
+#define CS53L30_ASP_CHx_TX_LOC_WIDTH	6
+#define CS53L30_ASP_CHx_TX_LOC_MASK	(((1 << CS53L30_ASP_CHx_TX_LOC_WIDTH) - 1) << CS53L30_ASP_CHx_TX_LOC_SHIFT)
+#define CS53L30_ASP_CHx_TX_LOC_MAX	(47 << CS53L30_ASP_CHx_TX_LOC_SHIFT)
+#define CS53L30_ASP_CHx_TX_LOC(x)	((x) << CS53L30_ASP_CHx_TX_LOC_SHIFT)
+
+#define CS53L30_ASP_TDMTX_CTLx_DEFAULT	(CS53L30_ASP_CHx_TX_LOC_MAX)
+
+/* R18 (0x12) ~ R23 (0x17) CS53L30_ASP_TDMTX_ENx - ASP TDM TX Enable 1~6 */
+#define CS53L30_ASP_TDMTX_ENx_DEFAULT	(0)
+
+/* R26 (0x1A) CS53L30_SFT_RAMP - Soft Ramp Control */
+#define CS53L30_DIGSFT_SHIFT		5
+#define CS53L30_DIGSFT_MASK		(1 << CS53L30_DIGSFT_SHIFT)
+#define CS53L30_DIGSFT			(1 << CS53L30_DIGSFT_SHIFT)
+
+#define CS53L30_SFT_RMP_DEFAULT		(0)
+
+/* R28 (0x1C) CS53L30_LRCK_CTL2 - LRCK Control 2 */
+#define CS53L30_LRCK_50_NPW_SHIFT	3
+#define CS53L30_LRCK_50_NPW_MASK	(1 << CS53L30_LRCK_50_NPW_SHIFT)
+#define CS53L30_LRCK_50_NPW		(1 << CS53L30_LRCK_50_NPW_SHIFT)
+#define CS53L30_LRCK_TPWH_SHIFT		0
+#define CS53L30_LRCK_TPWH_WIDTH		3
+#define CS53L30_LRCK_TPWH_MASK		(((1 << CS53L30_LRCK_TPWH_WIDTH) - 1) << CS53L30_LRCK_TPWH_SHIFT)
+#define CS53L30_LRCK_TPWH(x)		(((x) << CS53L30_LRCK_TPWH_SHIFT) & CS53L30_LRCK_TPWH_MASK)
+
+#define CS53L30_LRCK_CTLx_DEFAULT	(0)
+
+/* R31 (0x1F) CS53L30_MUTEP_CTL1 - MUTE Pin Control 1 */
+#define CS53L30_MUTE_PDN_ULP_SHIFT	7
+#define CS53L30_MUTE_PDN_ULP_MASK	(1 << CS53L30_MUTE_PDN_ULP_SHIFT)
+#define CS53L30_MUTE_PDN_ULP		(1 << CS53L30_MUTE_PDN_ULP_SHIFT)
+#define CS53L30_MUTE_PDN_LP_SHIFT	6
+#define CS53L30_MUTE_PDN_LP_MASK	(1 << CS53L30_MUTE_PDN_LP_SHIFT)
+#define CS53L30_MUTE_PDN_LP		(1 << CS53L30_MUTE_PDN_LP_SHIFT)
+#define CS53L30_MUTE_M4B_PDN_SHIFT	4
+#define CS53L30_MUTE_M4B_PDN_MASK	(1 << CS53L30_MUTE_M4B_PDN_SHIFT)
+#define CS53L30_MUTE_M4B_PDN		(1 << CS53L30_MUTE_M4B_PDN_SHIFT)
+#define CS53L30_MUTE_M3B_PDN_SHIFT	3
+#define CS53L30_MUTE_M3B_PDN_MASK	(1 << CS53L30_MUTE_M3B_PDN_SHIFT)
+#define CS53L30_MUTE_M3B_PDN		(1 << CS53L30_MUTE_M3B_PDN_SHIFT)
+#define CS53L30_MUTE_M2B_PDN_SHIFT	2
+#define CS53L30_MUTE_M2B_PDN_MASK	(1 << CS53L30_MUTE_M2B_PDN_SHIFT)
+#define CS53L30_MUTE_M2B_PDN		(1 << CS53L30_MUTE_M2B_PDN_SHIFT)
+#define CS53L30_MUTE_M1B_PDN_SHIFT	1
+#define CS53L30_MUTE_M1B_PDN_MASK	(1 << CS53L30_MUTE_M1B_PDN_SHIFT)
+#define CS53L30_MUTE_M1B_PDN		(1 << CS53L30_MUTE_M1B_PDN_SHIFT)
+/* Note: be careful - x starts from 0 */
+#define CS53L30_MUTE_MxB_PDN_SHIFT(x)	(CS53L30_MUTE_M1B_PDN_SHIFT + (x))
+#define CS53L30_MUTE_MxB_PDN_MASK(x)	(1 << CS53L30_MUTE_MxB_PDN_SHIFT(x))
+#define CS53L30_MUTE_MxB_PDN(x)		(1 << CS53L30_MUTE_MxB_PDN_SHIFT(x))
+#define CS53L30_MUTE_MB_ALL_PDN_SHIFT	0
+#define CS53L30_MUTE_MB_ALL_PDN_MASK	(1 << CS53L30_MUTE_MB_ALL_PDN_SHIFT)
+#define CS53L30_MUTE_MB_ALL_PDN		(1 << CS53L30_MUTE_MB_ALL_PDN_SHIFT)
+
+#define CS53L30_MUTEP_CTL1_MUTEALL	(0xdf)
+#define CS53L30_MUTEP_CTL1_DEFAULT	(0)
+
+/* R32 (0x20) CS53L30_MUTEP_CTL2 - MUTE Pin Control 2 */
+#define CS53L30_MUTE_PIN_POLARITY_SHIFT	7
+#define CS53L30_MUTE_PIN_POLARITY_MASK	(1 << CS53L30_MUTE_PIN_POLARITY_SHIFT)
+#define CS53L30_MUTE_PIN_POLARITY	(1 << CS53L30_MUTE_PIN_POLARITY_SHIFT)
+#define CS53L30_MUTE_ASP_TDM_PDN_SHIFT	6
+#define CS53L30_MUTE_ASP_TDM_PDN_MASK	(1 << CS53L30_MUTE_ASP_TDM_PDN_SHIFT)
+#define CS53L30_MUTE_ASP_TDM_PDN	(1 << CS53L30_MUTE_ASP_TDM_PDN_SHIFT)
+#define CS53L30_MUTE_ASP_SDOUT2_PDN_SHIFT 5
+#define CS53L30_MUTE_ASP_SDOUT2_PDN_MASK (1 << CS53L30_MUTE_ASP_SDOUT2_PDN_SHIFT)
+#define CS53L30_MUTE_ASP_SDOUT2_PDN	(1 << CS53L30_MUTE_ASP_SDOUT2_PDN_SHIFT)
+#define CS53L30_MUTE_ASP_SDOUT1_PDN_SHIFT 4
+#define CS53L30_MUTE_ASP_SDOUT1_PDN_MASK (1 << CS53L30_MUTE_ASP_SDOUT1_PDN_SHIFT)
+#define CS53L30_MUTE_ASP_SDOUT1_PDN	(1 << CS53L30_MUTE_ASP_SDOUT1_PDN_SHIFT)
+/* Note: be careful - x starts from 0 */
+#define CS53L30_MUTE_ASP_SDOUTx_PDN_SHIFT(x) ((x) + CS53L30_MUTE_ASP_SDOUT1_PDN_SHIFT)
+#define CS53L30_MUTE_ASP_SDOUTx_PDN_MASK(x) (1 << CS53L30_MUTE_ASP_SDOUTx_PDN_SHIFT(x))
+#define CS53L30_MUTE_ASP_SDOUTx_PDN	(1 << CS53L30_MUTE_ASP_SDOUTx_PDN_SHIFT(x))
+#define CS53L30_MUTE_ADC2B_PDN_SHIFT	3
+#define CS53L30_MUTE_ADC2B_PDN_MASK	(1 << CS53L30_MUTE_ADC2B_PDN_SHIFT)
+#define CS53L30_MUTE_ADC2B_PDN		(1 << CS53L30_MUTE_ADC2B_PDN_SHIFT)
+#define CS53L30_MUTE_ADC2A_PDN_SHIFT	2
+#define CS53L30_MUTE_ADC2A_PDN_MASK	(1 << CS53L30_MUTE_ADC2A_PDN_SHIFT)
+#define CS53L30_MUTE_ADC2A_PDN		(1 << CS53L30_MUTE_ADC2A_PDN_SHIFT)
+#define CS53L30_MUTE_ADC1B_PDN_SHIFT	1
+#define CS53L30_MUTE_ADC1B_PDN_MASK	(1 << CS53L30_MUTE_ADC1B_PDN_SHIFT)
+#define CS53L30_MUTE_ADC1B_PDN		(1 << CS53L30_MUTE_ADC1B_PDN_SHIFT)
+#define CS53L30_MUTE_ADC1A_PDN_SHIFT	0
+#define CS53L30_MUTE_ADC1A_PDN_MASK	(1 << CS53L30_MUTE_ADC1A_PDN_SHIFT)
+#define CS53L30_MUTE_ADC1A_PDN		(1 << CS53L30_MUTE_ADC1A_PDN_SHIFT)
+
+#define CS53L30_MUTEP_CTL2_DEFAULT	(CS53L30_MUTE_PIN_POLARITY)
+
+/* R33 (0x21) CS53L30_INBIAS_CTL1 - Input Bias Control 1 */
+#define CS53L30_IN4M_BIAS_SHIFT		6
+#define CS53L30_IN4M_BIAS_WIDTH		2
+#define CS53L30_IN4M_BIAS_MASK		(((1 << CS53L30_IN4M_BIAS_WIDTH) - 1) << CS53L30_IN4M_BIAS_SHIFT)
+#define CS53L30_IN4M_BIAS_OPEN		(0 << CS53L30_IN4M_BIAS_SHIFT)
+#define CS53L30_IN4M_BIAS_PULL_DOWN	(1 << CS53L30_IN4M_BIAS_SHIFT)
+#define CS53L30_IN4M_BIAS_VCM		(2 << CS53L30_IN4M_BIAS_SHIFT)
+#define CS53L30_IN4P_BIAS_SHIFT		4
+#define CS53L30_IN4P_BIAS_WIDTH		2
+#define CS53L30_IN4P_BIAS_MASK		(((1 << CS53L30_IN4P_BIAS_WIDTH) - 1) << CS53L30_IN4P_BIAS_SHIFT)
+#define CS53L30_IN4P_BIAS_OPEN		(0 << CS53L30_IN4P_BIAS_SHIFT)
+#define CS53L30_IN4P_BIAS_PULL_DOWN	(1 << CS53L30_IN4P_BIAS_SHIFT)
+#define CS53L30_IN4P_BIAS_VCM		(2 << CS53L30_IN4P_BIAS_SHIFT)
+#define CS53L30_IN3M_BIAS_SHIFT		2
+#define CS53L30_IN3M_BIAS_WIDTH		2
+#define CS53L30_IN3M_BIAS_MASK		(((1 << CS53L30_IN3M_BIAS_WIDTH) - 1) << CS53L30_IN4M_BIAS_SHIFT)
+#define CS53L30_IN3M_BIAS_OPEN		(0 << CS53L30_IN3M_BIAS_SHIFT)
+#define CS53L30_IN3M_BIAS_PULL_DOWN	(1 << CS53L30_IN3M_BIAS_SHIFT)
+#define CS53L30_IN3M_BIAS_VCM		(2 << CS53L30_IN3M_BIAS_SHIFT)
+#define CS53L30_IN3P_BIAS_SHIFT		0
+#define CS53L30_IN3P_BIAS_WIDTH		2
+#define CS53L30_IN3P_BIAS_MASK		(((1 << CS53L30_IN3P_BIAS_WIDTH) - 1) << CS53L30_IN3P_BIAS_SHIFT)
+#define CS53L30_IN3P_BIAS_OPEN		(0 << CS53L30_IN3P_BIAS_SHIFT)
+#define CS53L30_IN3P_BIAS_PULL_DOWN	(1 << CS53L30_IN3P_BIAS_SHIFT)
+#define CS53L30_IN3P_BIAS_VCM		(2 << CS53L30_IN3P_BIAS_SHIFT)
+
+#define CS53L30_INBIAS_CTL1_DEFAULT	(CS53L30_IN4M_BIAS_VCM | CS53L30_IN4P_BIAS_VCM |\
+					 CS53L30_IN3M_BIAS_VCM | CS53L30_IN3P_BIAS_VCM)
+
+/* R34 (0x22) CS53L30_INBIAS_CTL2 - Input Bias Control 2 */
+#define CS53L30_IN2M_BIAS_SHIFT		6
+#define CS53L30_IN2M_BIAS_WIDTH		2
+#define CS53L30_IN2M_BIAS_MASK		(((1 << CS53L30_IN2M_BIAS_WIDTH) - 1) << CS53L30_IN2M_BIAS_SHIFT)
+#define CS53L30_IN2M_BIAS_OPEN		(0 << CS53L30_IN2M_BIAS_SHIFT)
+#define CS53L30_IN2M_BIAS_PULL_DOWN	(1 << CS53L30_IN2M_BIAS_SHIFT)
+#define CS53L30_IN2M_BIAS_VCM		(2 << CS53L30_IN2M_BIAS_SHIFT)
+#define CS53L30_IN2P_BIAS_SHIFT		4
+#define CS53L30_IN2P_BIAS_WIDTH		2
+#define CS53L30_IN2P_BIAS_MASK		(((1 << CS53L30_IN2P_BIAS_WIDTH) - 1) << CS53L30_IN2P_BIAS_SHIFT)
+#define CS53L30_IN2P_BIAS_OPEN		(0 << CS53L30_IN2P_BIAS_SHIFT)
+#define CS53L30_IN2P_BIAS_PULL_DOWN	(1 << CS53L30_IN2P_BIAS_SHIFT)
+#define CS53L30_IN2P_BIAS_VCM		(2 << CS53L30_IN2P_BIAS_SHIFT)
+#define CS53L30_IN1M_BIAS_SHIFT		2
+#define CS53L30_IN1M_BIAS_WIDTH		2
+#define CS53L30_IN1M_BIAS_MASK		(((1 << CS53L30_IN1M_BIAS_WIDTH) - 1) << CS53L30_IN1M_BIAS_SHIFT)
+#define CS53L30_IN1M_BIAS_OPEN		(0 << CS53L30_IN1M_BIAS_SHIFT)
+#define CS53L30_IN1M_BIAS_PULL_DOWN	(1 << CS53L30_IN1M_BIAS_SHIFT)
+#define CS53L30_IN1M_BIAS_VCM		(2 << CS53L30_IN1M_BIAS_SHIFT)
+#define CS53L30_IN1P_BIAS_SHIFT		0
+#define CS53L30_IN1P_BIAS_WIDTH		2
+#define CS53L30_IN1P_BIAS_MASK		(((1 << CS53L30_IN1P_BIAS_WIDTH) - 1) << CS53L30_IN1P_BIAS_SHIFT)
+#define CS53L30_IN1P_BIAS_OPEN		(0 << CS53L30_IN1P_BIAS_SHIFT)
+#define CS53L30_IN1P_BIAS_PULL_DOWN	(1 << CS53L30_IN1P_BIAS_SHIFT)
+#define CS53L30_IN1P_BIAS_VCM		(2 << CS53L30_IN1P_BIAS_SHIFT)
+
+#define CS53L30_INBIAS_CTL2_DEFAULT	(CS53L30_IN2M_BIAS_VCM | CS53L30_IN2P_BIAS_VCM |\
+					 CS53L30_IN1M_BIAS_VCM | CS53L30_IN1P_BIAS_VCM)
+
+/* R35 (0x23) & R36 (0x24) CS53L30_DMICx_STR_CTL - DMIC1 & DMIC2 Stereo Control */
+#define CS53L30_DMICx_STEREO_ENB_SHIFT	5
+#define CS53L30_DMICx_STEREO_ENB_MASK	(1 << CS53L30_DMICx_STEREO_ENB_SHIFT)
+#define CS53L30_DMICx_STEREO_ENB	(1 << CS53L30_DMICx_STEREO_ENB_SHIFT)
+
+/* 0x88 and 0xCC are reserved bits */
+#define CS53L30_DMIC1_STR_CTL_DEFAULT	(CS53L30_DMICx_STEREO_ENB | 0x88)
+#define CS53L30_DMIC2_STR_CTL_DEFAULT	(CS53L30_DMICx_STEREO_ENB | 0xCC)
+
+/* R37/R45 (0x25/0x2D) CS53L30_ADCDMICx_CTL1 - ADC1/DMIC1 & ADC2/DMIC2 Control 1 */
+#define CS53L30_ADCxB_PDN_SHIFT		7
+#define CS53L30_ADCxB_PDN_MASK		(1 << CS53L30_ADCxB_PDN_SHIFT)
+#define CS53L30_ADCxB_PDN		(1 << CS53L30_ADCxB_PDN_SHIFT)
+#define CS53L30_ADCxA_PDN_SHIFT		6
+#define CS53L30_ADCxA_PDN_MASK		(1 << CS53L30_ADCxA_PDN_SHIFT)
+#define CS53L30_ADCxA_PDN		(1 << CS53L30_ADCxA_PDN_SHIFT)
+#define CS53L30_DMICx_PDN_SHIFT		2
+#define CS53L30_DMICx_PDN_MASK		(1 << CS53L30_DMICx_PDN_SHIFT)
+#define CS53L30_DMICx_PDN		(1 << CS53L30_DMICx_PDN_SHIFT)
+#define CS53L30_DMICx_SCLK_DIV_SHIFT	1
+#define CS53L30_DMICx_SCLK_DIV_MASK	(1 << CS53L30_DMICx_SCLK_DIV_SHIFT)
+#define CS53L30_DMICx_SCLK_DIV		(1 << CS53L30_DMICx_SCLK_DIV_SHIFT)
+#define CS53L30_CH_TYPE_SHIFT		0
+#define CS53L30_CH_TYPE_MASK		(1 << CS53L30_CH_TYPE_SHIFT)
+#define CS53L30_CH_TYPE			(1 << CS53L30_CH_TYPE_SHIFT)
+
+#define CS53L30_ADCDMICx_PDN_MASK	0xFF
+#define CS53L30_ADCDMICx_CTL1_DEFAULT	(CS53L30_DMICx_PDN)
+
+/* R38/R46 (0x26/0x2E) CS53L30_ADCDMICx_CTL2 - ADC1/DMIC1 & ADC2/DMIC2 Control 2 */
+#define CS53L30_ADCx_NOTCH_DIS_SHIFT	7
+#define CS53L30_ADCx_NOTCH_DIS_MASK	(1 << CS53L30_ADCx_NOTCH_DIS_SHIFT)
+#define CS53L30_ADCx_NOTCH_DIS		(1 << CS53L30_ADCx_NOTCH_DIS_SHIFT)
+#define CS53L30_ADCxB_INV_SHIFT		5
+#define CS53L30_ADCxB_INV_MASK		(1 << CS53L30_ADCxB_INV_SHIFT)
+#define CS53L30_ADCxB_INV		(1 << CS53L30_ADCxB_INV_SHIFT)
+#define CS53L30_ADCxA_INV_SHIFT		4
+#define CS53L30_ADCxA_INV_MASK		(1 << CS53L30_ADCxA_INV_SHIFT)
+#define CS53L30_ADCxA_INV		(1 << CS53L30_ADCxA_INV_SHIFT)
+#define CS53L30_ADCxB_DIG_BOOST_SHIFT	1
+#define CS53L30_ADCxB_DIG_BOOST_MASK	(1 << CS53L30_ADCxB_DIG_BOOST_SHIFT)
+#define CS53L30_ADCxB_DIG_BOOST		(1 << CS53L30_ADCxB_DIG_BOOST_SHIFT)
+#define CS53L30_ADCxA_DIG_BOOST_SHIFT	0
+#define CS53L30_ADCxA_DIG_BOOST_MASK	(1 << CS53L30_ADCxA_DIG_BOOST_SHIFT)
+#define CS53L30_ADCxA_DIG_BOOST		(1 << CS53L30_ADCxA_DIG_BOOST_SHIFT)
+
+#define CS53L30_ADCDMIC1_CTL2_DEFAULT	(0)
+
+/* R39/R47 (0x27/0x2F) CS53L30_ADCx_CTL3 - ADC1/ADC2 Control 3 */
+#define CS53L30_ADCx_HPF_EN_SHIFT	3
+#define CS53L30_ADCx_HPF_EN_MASK	(1 << CS53L30_ADCx_HPF_EN_SHIFT)
+#define CS53L30_ADCx_HPF_EN		(1 << CS53L30_ADCx_HPF_EN_SHIFT)
+#define CS53L30_ADCx_HPF_CF_SHIFT	1
+#define CS53L30_ADCx_HPF_CF_WIDTH	2
+#define CS53L30_ADCx_HPF_CF_MASK	(((1 << CS53L30_ADCx_HPF_CF_WIDTH) - 1) << CS53L30_ADCx_HPF_CF_SHIFT)
+#define CS53L30_ADCx_HPF_CF_1HZ86	(0 << CS53L30_ADCx_HPF_CF_SHIFT)
+#define CS53L30_ADCx_HPF_CF_120HZ	(1 << CS53L30_ADCx_HPF_CF_SHIFT)
+#define CS53L30_ADCx_HPF_CF_235HZ	(2 << CS53L30_ADCx_HPF_CF_SHIFT)
+#define CS53L30_ADCx_HPF_CF_466HZ	(3 << CS53L30_ADCx_HPF_CF_SHIFT)
+#define CS53L30_ADCx_NG_ALL_SHIFT	0
+#define CS53L30_ADCx_NG_ALL_MASK	(1 << CS53L30_ADCx_NG_ALL_SHIFT)
+#define CS53L30_ADCx_NG_ALL		(1 << CS53L30_ADCx_NG_ALL_SHIFT)
+
+#define CS53L30_ADCx_CTL3_DEFAULT	(CS53L30_ADCx_HPF_EN)
+
+/* R40/R48 (0x28/0x30) CS53L30_ADCx_NG_CTL - ADC1/ADC2 Noise Gate Control */
+#define CS53L30_ADCxB_NG_SHIFT		7
+#define CS53L30_ADCxB_NG_MASK		(1 << CS53L30_ADCxB_NG_SHIFT)
+#define CS53L30_ADCxB_NG		(1 << CS53L30_ADCxB_NG_SHIFT)
+#define CS53L30_ADCxA_NG_SHIFT		6
+#define CS53L30_ADCxA_NG_MASK		(1 << CS53L30_ADCxA_NG_SHIFT)
+#define CS53L30_ADCxA_NG		(1 << CS53L30_ADCxA_NG_SHIFT)
+#define CS53L30_ADCx_NG_BOOST_SHIFT	5
+#define CS53L30_ADCx_NG_BOOST_MASK	(1 << CS53L30_ADCx_NG_BOOST_SHIFT)
+#define CS53L30_ADCx_NG_BOOST		(1 << CS53L30_ADCx_NG_BOOST_SHIFT)
+#define CS53L30_ADCx_NG_THRESH_SHIFT	2
+#define CS53L30_ADCx_NG_THRESH_WIDTH	3
+#define CS53L30_ADCx_NG_THRESH_MASK	(((1 << CS53L30_ADCx_NG_THRESH_WIDTH) - 1) << CS53L30_ADCx_NG_THRESH_SHIFT)
+#define CS53L30_ADCx_NG_DELAY_SHIFT	0
+#define CS53L30_ADCx_NG_DELAY_WIDTH	2
+#define CS53L30_ADCx_NG_DELAY_MASK	(((1 << CS53L30_ADCx_NG_DELAY_WIDTH) - 1) << CS53L30_ADCx_NG_DELAY_SHIFT)
+
+#define CS53L30_ADCx_NG_CTL_DEFAULT	(0)
+
+/* R41/R42/R49/R50 (0x29/0x2A/0x31/0x32) CS53L30_ADCxy_AFE_CTL - ADC1A/1B/2A/2B AFE Control */
+#define CS53L30_ADCxy_PREAMP_SHIFT	6
+#define CS53L30_ADCxy_PREAMP_WIDTH	2
+#define CS53L30_ADCxy_PREAMP_MASK	(((1 << CS53L30_ADCxy_PREAMP_WIDTH) - 1) << CS53L30_ADCxy_PREAMP_SHIFT)
+#define CS53L30_ADCxy_PGA_VOL_SHIFT	0
+#define CS53L30_ADCxy_PGA_VOL_WIDTH	6
+#define CS53L30_ADCxy_PGA_VOL_MASK	(((1 << CS53L30_ADCxy_PGA_VOL_WIDTH) - 1) << CS53L30_ADCxy_PGA_VOL_SHIFT)
+
+#define CS53L30_ADCxy_AFE_CTL_DEFAULT	(0)
+
+/* R43/R44/R51/R52 (0x2B/0x2C/0x33/0x34) CS53L30_ADCxy_DIG_VOL - ADC1A/1B/2A/2B Digital Volume */
+#define CS53L30_ADCxy_VOL_MUTE		(0x80)
+
+#define CS53L30_ADCxy_DIG_VOL_DEFAULT	(0x0)
+
+/* CS53L30_INT */
+#define CS53L30_PDN_DONE		(1 << 7)
+#define CS53L30_THMS_TRIP		(1 << 6)
+#define CS53L30_SYNC_DONE		(1 << 5)
+#define CS53L30_ADC2B_OVFL		(1 << 4)
+#define CS53L30_ADC2A_OVFL		(1 << 3)
+#define CS53L30_ADC1B_OVFL		(1 << 2)
+#define CS53L30_ADC1A_OVFL		(1 << 1)
+#define CS53L30_MUTE_PIN		(1 << 0)
+#define CS53L30_DEVICE_INT_MASK		0xFF
+
+#endif	/* __CS53L30_H__ */
diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c
index 9459593eef13..f0057cd223a4 100644
--- a/sound/soc/codecs/da7219-aad.c
+++ b/sound/soc/codecs/da7219-aad.c
@@ -13,8 +13,8 @@
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
+#include <linux/i2c.h>
+#include <linux/property.h>
 #include <linux/pm_wakeirq.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
@@ -382,11 +382,11 @@ static irqreturn_t da7219_aad_irq_thread(int irq, void *data)
 }
 
 /*
- * DT to pdata conversion
+ * DT/ACPI to pdata conversion
  */
 
 static enum da7219_aad_micbias_pulse_lvl
-	da7219_aad_of_micbias_pulse_lvl(struct snd_soc_codec *codec, u32 val)
+	da7219_aad_fw_micbias_pulse_lvl(struct snd_soc_codec *codec, u32 val)
 {
 	switch (val) {
 	case 2800:
@@ -400,7 +400,7 @@ static enum da7219_aad_micbias_pulse_lvl
 }
 
 static enum da7219_aad_btn_cfg
-	da7219_aad_of_btn_cfg(struct snd_soc_codec *codec, u32 val)
+	da7219_aad_fw_btn_cfg(struct snd_soc_codec *codec, u32 val)
 {
 	switch (val) {
 	case 2:
@@ -424,7 +424,7 @@ static enum da7219_aad_btn_cfg
 }
 
 static enum da7219_aad_mic_det_thr
-	da7219_aad_of_mic_det_thr(struct snd_soc_codec *codec, u32 val)
+	da7219_aad_fw_mic_det_thr(struct snd_soc_codec *codec, u32 val)
 {
 	switch (val) {
 	case 200:
@@ -442,7 +442,7 @@ static enum da7219_aad_mic_det_thr
 }
 
 static enum da7219_aad_jack_ins_deb
-	da7219_aad_of_jack_ins_deb(struct snd_soc_codec *codec, u32 val)
+	da7219_aad_fw_jack_ins_deb(struct snd_soc_codec *codec, u32 val)
 {
 	switch (val) {
 	case 5:
@@ -468,7 +468,7 @@ static enum da7219_aad_jack_ins_deb
 }
 
 static enum da7219_aad_jack_det_rate
-	da7219_aad_of_jack_det_rate(struct snd_soc_codec *codec, const char *str)
+	da7219_aad_fw_jack_det_rate(struct snd_soc_codec *codec, const char *str)
 {
 	if (!strcmp(str, "32ms_64ms")) {
 		return DA7219_AAD_JACK_DET_RATE_32_64MS;
@@ -485,7 +485,7 @@ static enum da7219_aad_jack_det_rate
 }
 
 static enum da7219_aad_jack_rem_deb
-	da7219_aad_of_jack_rem_deb(struct snd_soc_codec *codec, u32 val)
+	da7219_aad_fw_jack_rem_deb(struct snd_soc_codec *codec, u32 val)
 {
 	switch (val) {
 	case 1:
@@ -503,7 +503,7 @@ static enum da7219_aad_jack_rem_deb
 }
 
 static enum da7219_aad_btn_avg
-	da7219_aad_of_btn_avg(struct snd_soc_codec *codec, u32 val)
+	da7219_aad_fw_btn_avg(struct snd_soc_codec *codec, u32 val)
 {
 	switch (val) {
 	case 1:
@@ -521,7 +521,7 @@ static enum da7219_aad_btn_avg
 }
 
 static enum da7219_aad_adc_1bit_rpt
-	da7219_aad_of_adc_1bit_rpt(struct snd_soc_codec *codec, u32 val)
+	da7219_aad_fw_adc_1bit_rpt(struct snd_soc_codec *codec, u32 val)
 {
 	switch (val) {
 	case 1:
@@ -538,97 +538,96 @@ static enum da7219_aad_adc_1bit_rpt
 	}
 }
 
-static struct da7219_aad_pdata *da7219_aad_of_to_pdata(struct snd_soc_codec *codec)
+static struct da7219_aad_pdata *da7219_aad_fw_to_pdata(struct snd_soc_codec *codec)
 {
-	struct device_node *np = codec->dev->of_node;
-	struct device_node *aad_np = of_find_node_by_name(np, "da7219_aad");
+	struct device *dev = codec->dev;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	struct fwnode_handle *aad_np;
 	struct da7219_aad_pdata *aad_pdata;
-	const char *of_str;
-	u32 of_val32;
+	const char *fw_str;
+	u32 fw_val32;
 
+	aad_np = device_get_named_child_node(dev, "da7219_aad");
 	if (!aad_np)
 		return NULL;
 
 	aad_pdata = devm_kzalloc(codec->dev, sizeof(*aad_pdata), GFP_KERNEL);
 	if (!aad_pdata)
-		goto out;
+		return NULL;
 
-	aad_pdata->irq = irq_of_parse_and_map(np, 0);
+	aad_pdata->irq = i2c->irq;
 
-	if (of_property_read_u32(aad_np, "dlg,micbias-pulse-lvl",
-				 &of_val32) >= 0)
+	if (fwnode_property_read_u32(aad_np, "dlg,micbias-pulse-lvl",
+				     &fw_val32) >= 0)
 		aad_pdata->micbias_pulse_lvl =
-			da7219_aad_of_micbias_pulse_lvl(codec, of_val32);
+			da7219_aad_fw_micbias_pulse_lvl(codec, fw_val32);
 	else
 		aad_pdata->micbias_pulse_lvl = DA7219_AAD_MICBIAS_PULSE_LVL_OFF;
 
-	if (of_property_read_u32(aad_np, "dlg,micbias-pulse-time",
-				 &of_val32) >= 0)
-		aad_pdata->micbias_pulse_time = of_val32;
+	if (fwnode_property_read_u32(aad_np, "dlg,micbias-pulse-time",
+				     &fw_val32) >= 0)
+		aad_pdata->micbias_pulse_time = fw_val32;
 
-	if (of_property_read_u32(aad_np, "dlg,btn-cfg", &of_val32) >= 0)
-		aad_pdata->btn_cfg = da7219_aad_of_btn_cfg(codec, of_val32);
+	if (fwnode_property_read_u32(aad_np, "dlg,btn-cfg", &fw_val32) >= 0)
+		aad_pdata->btn_cfg = da7219_aad_fw_btn_cfg(codec, fw_val32);
 	else
 		aad_pdata->btn_cfg = DA7219_AAD_BTN_CFG_10MS;
 
-	if (of_property_read_u32(aad_np, "dlg,mic-det-thr", &of_val32) >= 0)
+	if (fwnode_property_read_u32(aad_np, "dlg,mic-det-thr", &fw_val32) >= 0)
 		aad_pdata->mic_det_thr =
-			da7219_aad_of_mic_det_thr(codec, of_val32);
+			da7219_aad_fw_mic_det_thr(codec, fw_val32);
 	else
 		aad_pdata->mic_det_thr = DA7219_AAD_MIC_DET_THR_500_OHMS;
 
-	if (of_property_read_u32(aad_np, "dlg,jack-ins-deb", &of_val32) >= 0)
+	if (fwnode_property_read_u32(aad_np, "dlg,jack-ins-deb", &fw_val32) >= 0)
 		aad_pdata->jack_ins_deb =
-			da7219_aad_of_jack_ins_deb(codec, of_val32);
+			da7219_aad_fw_jack_ins_deb(codec, fw_val32);
 	else
 		aad_pdata->jack_ins_deb = DA7219_AAD_JACK_INS_DEB_20MS;
 
-	if (!of_property_read_string(aad_np, "dlg,jack-det-rate", &of_str))
+	if (!fwnode_property_read_string(aad_np, "dlg,jack-det-rate", &fw_str))
 		aad_pdata->jack_det_rate =
-			da7219_aad_of_jack_det_rate(codec, of_str);
+			da7219_aad_fw_jack_det_rate(codec, fw_str);
 	else
 		aad_pdata->jack_det_rate = DA7219_AAD_JACK_DET_RATE_256_512MS;
 
-	if (of_property_read_u32(aad_np, "dlg,jack-rem-deb", &of_val32) >= 0)
+	if (fwnode_property_read_u32(aad_np, "dlg,jack-rem-deb", &fw_val32) >= 0)
 		aad_pdata->jack_rem_deb =
-			da7219_aad_of_jack_rem_deb(codec, of_val32);
+			da7219_aad_fw_jack_rem_deb(codec, fw_val32);
 	else
 		aad_pdata->jack_rem_deb = DA7219_AAD_JACK_REM_DEB_1MS;
 
-	if (of_property_read_u32(aad_np, "dlg,a-d-btn-thr", &of_val32) >= 0)
-		aad_pdata->a_d_btn_thr = (u8) of_val32;
+	if (fwnode_property_read_u32(aad_np, "dlg,a-d-btn-thr", &fw_val32) >= 0)
+		aad_pdata->a_d_btn_thr = (u8) fw_val32;
 	else
 		aad_pdata->a_d_btn_thr = 0xA;
 
-	if (of_property_read_u32(aad_np, "dlg,d-b-btn-thr", &of_val32) >= 0)
-		aad_pdata->d_b_btn_thr = (u8) of_val32;
+	if (fwnode_property_read_u32(aad_np, "dlg,d-b-btn-thr", &fw_val32) >= 0)
+		aad_pdata->d_b_btn_thr = (u8) fw_val32;
 	else
 		aad_pdata->d_b_btn_thr = 0x16;
 
-	if (of_property_read_u32(aad_np, "dlg,b-c-btn-thr", &of_val32) >= 0)
-		aad_pdata->b_c_btn_thr = (u8) of_val32;
+	if (fwnode_property_read_u32(aad_np, "dlg,b-c-btn-thr", &fw_val32) >= 0)
+		aad_pdata->b_c_btn_thr = (u8) fw_val32;
 	else
 		aad_pdata->b_c_btn_thr = 0x21;
 
-	if (of_property_read_u32(aad_np, "dlg,c-mic-btn-thr", &of_val32) >= 0)
-		aad_pdata->c_mic_btn_thr = (u8) of_val32;
+	if (fwnode_property_read_u32(aad_np, "dlg,c-mic-btn-thr", &fw_val32) >= 0)
+		aad_pdata->c_mic_btn_thr = (u8) fw_val32;
 	else
 		aad_pdata->c_mic_btn_thr = 0x3E;
 
-	if (of_property_read_u32(aad_np, "dlg,btn-avg", &of_val32) >= 0)
-		aad_pdata->btn_avg = da7219_aad_of_btn_avg(codec, of_val32);
+	if (fwnode_property_read_u32(aad_np, "dlg,btn-avg", &fw_val32) >= 0)
+		aad_pdata->btn_avg = da7219_aad_fw_btn_avg(codec, fw_val32);
 	else
 		aad_pdata->btn_avg = DA7219_AAD_BTN_AVG_2;
 
-	if (of_property_read_u32(aad_np, "dlg,adc-1bit-rpt", &of_val32) >= 0)
+	if (fwnode_property_read_u32(aad_np, "dlg,adc-1bit-rpt", &fw_val32) >= 0)
 		aad_pdata->adc_1bit_rpt =
-			da7219_aad_of_adc_1bit_rpt(codec, of_val32);
+			da7219_aad_fw_adc_1bit_rpt(codec, fw_val32);
 	else
 		aad_pdata->adc_1bit_rpt = DA7219_AAD_ADC_1BIT_RPT_1;
 
-out:
-	of_node_put(aad_np);
-
 	return aad_pdata;
 }
 
@@ -769,9 +768,9 @@ int da7219_aad_init(struct snd_soc_codec *codec)
 	da7219->aad = da7219_aad;
 	da7219_aad->codec = codec;
 
-	/* Handle any DT/platform data */
-	if ((codec->dev->of_node) && (da7219->pdata))
-		da7219->pdata->aad_pdata = da7219_aad_of_to_pdata(codec);
+	/* Handle any DT/ACPI/platform data */
+	if (da7219->pdata && !da7219->pdata->aad_pdata)
+		da7219->pdata->aad_pdata = da7219_aad_fw_to_pdata(codec);
 
 	da7219_aad_handle_pdata(codec);
 
diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c
index 5c93899f1f0e..50ea94317cb3 100644
--- a/sound/soc/codecs/da7219.c
+++ b/sound/soc/codecs/da7219.c
@@ -15,6 +15,7 @@
 #include <linux/clk.h>
 #include <linux/i2c.h>
 #include <linux/of_device.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
 #include <linux/pm.h>
@@ -1418,7 +1419,7 @@ static struct snd_soc_dai_driver da7219_dai = {
 
 
 /*
- * DT
+ * DT/ACPI
  */
 
 static const struct of_device_id da7219_of_match[] = {
@@ -1434,7 +1435,7 @@ static const struct acpi_device_id da7219_acpi_match[] = {
 MODULE_DEVICE_TABLE(acpi, da7219_acpi_match);
 
 static enum da7219_micbias_voltage
-	da7219_of_micbias_lvl(struct snd_soc_codec *codec, u32 val)
+	da7219_fw_micbias_lvl(struct device *dev, u32 val)
 {
 	switch (val) {
 	case 1600:
@@ -1450,13 +1451,13 @@ static enum da7219_micbias_voltage
 	case 2600:
 		return DA7219_MICBIAS_2_6V;
 	default:
-		dev_warn(codec->dev, "Invalid micbias level");
+		dev_warn(dev, "Invalid micbias level");
 		return DA7219_MICBIAS_2_2V;
 	}
 }
 
 static enum da7219_mic_amp_in_sel
-	da7219_of_mic_amp_in_sel(struct snd_soc_codec *codec, const char *str)
+	da7219_fw_mic_amp_in_sel(struct device *dev, const char *str)
 {
 	if (!strcmp(str, "diff")) {
 		return DA7219_MIC_AMP_IN_SEL_DIFF;
@@ -1465,29 +1466,29 @@ static enum da7219_mic_amp_in_sel
 	} else if (!strcmp(str, "se_n")) {
 		return DA7219_MIC_AMP_IN_SEL_SE_N;
 	} else {
-		dev_warn(codec->dev, "Invalid mic input type selection");
+		dev_warn(dev, "Invalid mic input type selection");
 		return DA7219_MIC_AMP_IN_SEL_DIFF;
 	}
 }
 
-static struct da7219_pdata *da7219_of_to_pdata(struct snd_soc_codec *codec)
+static struct da7219_pdata *da7219_fw_to_pdata(struct snd_soc_codec *codec)
 {
-	struct device_node *np = codec->dev->of_node;
+	struct device *dev = codec->dev;
 	struct da7219_pdata *pdata;
 	const char *of_str;
 	u32 of_val32;
 
-	pdata = devm_kzalloc(codec->dev, sizeof(*pdata), GFP_KERNEL);
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return NULL;
 
-	if (of_property_read_u32(np, "dlg,micbias-lvl", &of_val32) >= 0)
-		pdata->micbias_lvl = da7219_of_micbias_lvl(codec, of_val32);
+	if (device_property_read_u32(dev, "dlg,micbias-lvl", &of_val32) >= 0)
+		pdata->micbias_lvl = da7219_fw_micbias_lvl(dev, of_val32);
 	else
 		pdata->micbias_lvl = DA7219_MICBIAS_2_2V;
 
-	if (!of_property_read_string(np, "dlg,mic-amp-in-sel", &of_str))
-		pdata->mic_amp_in_sel = da7219_of_mic_amp_in_sel(codec, of_str);
+	if (!device_property_read_string(dev, "dlg,mic-amp-in-sel", &of_str))
+		pdata->mic_amp_in_sel = da7219_fw_mic_amp_in_sel(dev, of_str);
 	else
 		pdata->mic_amp_in_sel = DA7219_MIC_AMP_IN_SEL_DIFF;
 
@@ -1662,11 +1663,10 @@ static int da7219_probe(struct snd_soc_codec *codec)
 		break;
 	}
 
-	/* Handle DT/Platform data */
-	if (codec->dev->of_node)
-		da7219->pdata = da7219_of_to_pdata(codec);
-	else
-		da7219->pdata = dev_get_platdata(codec->dev);
+	/* Handle DT/ACPI/Platform data */
+	da7219->pdata = dev_get_platdata(codec->dev);
+	if (!da7219->pdata)
+		da7219->pdata = da7219_fw_to_pdata(codec);
 
 	da7219_handle_pdata(codec);
 
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 2abb742fc47b..4e181b270d95 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1124,8 +1124,10 @@ static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin, int repoll)
 			}
 			hdac_hdmi_parse_eld(edev, pin);
 
-			print_hex_dump_bytes("ELD: ", DUMP_PREFIX_OFFSET,
-					pin->eld.eld_buffer, pin->eld.eld_size);
+			print_hex_dump_debug("ELD: ",
+					DUMP_PREFIX_OFFSET, 16, 1,
+					pin->eld.eld_buffer, pin->eld.eld_size,
+					true);
 		} else {
 			pin->eld.monitor_present = false;
 			pin->eld.eld_valid = false;
@@ -1816,6 +1818,7 @@ static const struct dev_pm_ops hdac_hdmi_pm = {
 static const struct hda_device_id hdmi_list[] = {
 	HDA_CODEC_EXT_ENTRY(0x80862809, 0x100000, "Skylake HDMI", 0),
 	HDA_CODEC_EXT_ENTRY(0x8086280a, 0x100000, "Broxton HDMI", 0),
+	HDA_CODEC_EXT_ENTRY(0x8086280b, 0x100000, "Kabylake HDMI", 0),
 	{}
 };
 
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index 8e36e883e453..f27d115626db 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -112,7 +112,7 @@ static int hdmi_codec_startup(struct snd_pcm_substream *substream,
 		return ret;
 
 	if (hcp->hcd.ops->audio_startup) {
-		ret = hcp->hcd.ops->audio_startup(dai->dev->parent);
+		ret = hcp->hcd.ops->audio_startup(dai->dev->parent, hcp->hcd.data);
 		if (ret) {
 			mutex_lock(&hcp->current_stream_lock);
 			hcp->current_stream = NULL;
@@ -122,8 +122,8 @@ static int hdmi_codec_startup(struct snd_pcm_substream *substream,
 	}
 
 	if (hcp->hcd.ops->get_eld) {
-		ret = hcp->hcd.ops->get_eld(dai->dev->parent, hcp->eld,
-					    sizeof(hcp->eld));
+		ret = hcp->hcd.ops->get_eld(dai->dev->parent, hcp->hcd.data,
+					    hcp->eld, sizeof(hcp->eld));
 
 		if (!ret) {
 			ret = snd_pcm_hw_constraint_eld(substream->runtime,
@@ -144,7 +144,7 @@ static void hdmi_codec_shutdown(struct snd_pcm_substream *substream,
 
 	WARN_ON(hcp->current_stream != substream);
 
-	hcp->hcd.ops->audio_shutdown(dai->dev->parent);
+	hcp->hcd.ops->audio_shutdown(dai->dev->parent, hcp->hcd.data);
 
 	mutex_lock(&hcp->current_stream_lock);
 	hcp->current_stream = NULL;
@@ -195,8 +195,8 @@ static int hdmi_codec_hw_params(struct snd_pcm_substream *substream,
 	hp.sample_rate = params_rate(params);
 	hp.channels = params_channels(params);
 
-	return hcp->hcd.ops->hw_params(dai->dev->parent, &hcp->daifmt[dai->id],
-				       &hp);
+	return hcp->hcd.ops->hw_params(dai->dev->parent, hcp->hcd.data,
+				       &hcp->daifmt[dai->id], &hp);
 }
 
 static int hdmi_codec_set_fmt(struct snd_soc_dai *dai,
@@ -280,7 +280,8 @@ static int hdmi_codec_digital_mute(struct snd_soc_dai *dai, int mute)
 	dev_dbg(dai->dev, "%s()\n", __func__);
 
 	if (hcp->hcd.ops->digital_mute)
-		return hcp->hcd.ops->digital_mute(dai->dev->parent, mute);
+		return hcp->hcd.ops->digital_mute(dai->dev->parent,
+						  hcp->hcd.data, mute);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/max98504.c b/sound/soc/codecs/max98504.c
new file mode 100644
index 000000000000..a7320e709890
--- /dev/null
+++ b/sound/soc/codecs/max98504.c
@@ -0,0 +1,383 @@
+/*
+ * MAX98504 ALSA SoC Audio driver
+ *
+ * Copyright 2013 - 2014 Maxim Integrated Products
+ * Copyright 2016 Samsung Electronics Co., Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <sound/soc.h>
+
+#include "max98504.h"
+
+static const char * const max98504_supply_names[] = {
+	"DVDD",
+	"DIOVDD",
+	"PVDD",
+};
+#define MAX98504_NUM_SUPPLIES ARRAY_SIZE(max98504_supply_names)
+
+struct max98504_priv {
+	struct regmap *regmap;
+	struct regulator_bulk_data supplies[MAX98504_NUM_SUPPLIES];
+	unsigned int pcm_rx_channels;
+	bool brownout_enable;
+	unsigned int brownout_threshold;
+	unsigned int brownout_attenuation;
+	unsigned int brownout_attack_hold;
+	unsigned int brownout_timed_hold;
+	unsigned int brownout_release_rate;
+};
+
+static struct reg_default max98504_reg_defaults[] = {
+	{ 0x01,	0},
+	{ 0x02,	0},
+	{ 0x03,	0},
+	{ 0x04,	0},
+	{ 0x10, 0},
+	{ 0x11, 0},
+	{ 0x12, 0},
+	{ 0x13, 0},
+	{ 0x14, 0},
+	{ 0x15, 0},
+	{ 0x16, 0},
+	{ 0x17, 0},
+	{ 0x18, 0},
+	{ 0x19, 0},
+	{ 0x1A, 0},
+	{ 0x20, 0},
+	{ 0x21, 0},
+	{ 0x22, 0},
+	{ 0x23, 0},
+	{ 0x24, 0},
+	{ 0x25, 0},
+	{ 0x26, 0},
+	{ 0x27, 0},
+	{ 0x28, 0},
+	{ 0x30, 0},
+	{ 0x31, 0},
+	{ 0x32, 0},
+	{ 0x33, 0},
+	{ 0x34, 0},
+	{ 0x35, 0},
+	{ 0x36, 0},
+	{ 0x37, 0},
+	{ 0x38, 0},
+	{ 0x39, 0},
+	{ 0x40, 0},
+	{ 0x41, 0},
+};
+
+static bool max98504_volatile_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case MAX98504_INTERRUPT_STATUS:
+	case MAX98504_INTERRUPT_FLAGS:
+	case MAX98504_INTERRUPT_FLAG_CLEARS:
+	case MAX98504_WATCHDOG_CLEAR:
+	case MAX98504_GLOBAL_ENABLE:
+	case MAX98504_SOFTWARE_RESET:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool max98504_readable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case MAX98504_SOFTWARE_RESET:
+	case MAX98504_WATCHDOG_CLEAR:
+	case MAX98504_INTERRUPT_FLAG_CLEARS:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static int max98504_pcm_rx_ev(struct snd_soc_dapm_widget *w,
+			      struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *c = snd_soc_dapm_to_component(w->dapm);
+	struct max98504_priv *max98504 = snd_soc_component_get_drvdata(c);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		regmap_write(max98504->regmap, MAX98504_PCM_RX_ENABLE,
+			     max98504->pcm_rx_channels);
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		regmap_write(max98504->regmap, MAX98504_PCM_RX_ENABLE, 0);
+		break;
+	}
+
+	return 0;
+}
+
+static int max98504_component_probe(struct snd_soc_component *c)
+{
+	struct max98504_priv *max98504 = snd_soc_component_get_drvdata(c);
+	struct regmap *map = max98504->regmap;
+	int ret;
+
+	ret = regulator_bulk_enable(MAX98504_NUM_SUPPLIES, max98504->supplies);
+	if (ret < 0)
+		return ret;
+
+	regmap_write(map, MAX98504_SOFTWARE_RESET, 0x1);
+	msleep(20);
+
+	if (!max98504->brownout_enable)
+		return 0;
+
+	regmap_write(map, MAX98504_PVDD_BROWNOUT_ENABLE, 0x1);
+
+	regmap_write(map, MAX98504_PVDD_BROWNOUT_CONFIG_1,
+		     (max98504->brownout_threshold & 0x1f) << 3 |
+		     (max98504->brownout_attenuation & 0x3));
+
+	regmap_write(map, MAX98504_PVDD_BROWNOUT_CONFIG_2,
+		     max98504->brownout_attack_hold & 0xff);
+
+	regmap_write(map, MAX98504_PVDD_BROWNOUT_CONFIG_3,
+		     max98504->brownout_timed_hold & 0xff);
+
+	regmap_write(map, MAX98504_PVDD_BROWNOUT_CONFIG_4,
+		     max98504->brownout_release_rate & 0xff);
+
+	return 0;
+}
+
+static void max98504_component_remove(struct snd_soc_component *c)
+{
+	struct max98504_priv *max98504 = snd_soc_component_get_drvdata(c);
+
+	regulator_bulk_disable(MAX98504_NUM_SUPPLIES, max98504->supplies);
+}
+
+static const char *spk_source_mux_text[] = {
+	"PCM Monomix", "Analog In", "PDM Left", "PDM Right"
+};
+
+static const struct soc_enum spk_source_mux_enum =
+	SOC_ENUM_SINGLE(MAX98504_SPEAKER_SOURCE_SELECT,
+			0, ARRAY_SIZE(spk_source_mux_text),
+			spk_source_mux_text);
+
+static const struct snd_kcontrol_new spk_source_mux =
+	SOC_DAPM_ENUM("SPK Source", spk_source_mux_enum);
+
+static const struct snd_soc_dapm_route max98504_dapm_routes[] = {
+	{ "SPKOUT", NULL, "Global Enable" },
+	{ "SPK Source", "PCM Monomix", "DAC PCM" },
+	{ "SPK Source", "Analog In", "AIN" },
+	{ "SPK Source", "PDM Left", "DAC PDM" },
+	{ "SPK Source", "PDM Right", "DAC PDM" },
+};
+
+static const struct snd_soc_dapm_widget max98504_dapm_widgets[] = {
+	SND_SOC_DAPM_SUPPLY("Global Enable", MAX98504_GLOBAL_ENABLE,
+		0, 0, NULL, 0),
+	SND_SOC_DAPM_INPUT("AIN"),
+	SND_SOC_DAPM_AIF_OUT("AIF2OUTL", "AIF2 Capture", 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("AIF2OUTR", "AIF2 Capture", 1, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_DAC_E("DAC PCM", NULL, SND_SOC_NOPM, 0, 0,
+		max98504_pcm_rx_ev,
+		SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
+	SND_SOC_DAPM_DAC("DAC PDM", NULL, MAX98504_PDM_RX_ENABLE, 0, 0),
+	SND_SOC_DAPM_MUX("SPK Source", SND_SOC_NOPM, 0, 0, &spk_source_mux),
+	SND_SOC_DAPM_REG(snd_soc_dapm_spk, "SPKOUT",
+		MAX98504_SPEAKER_ENABLE, 0, 1, 1, 0),
+};
+
+static int max98504_set_tdm_slot(struct snd_soc_dai *dai,
+		unsigned int tx_mask, unsigned int rx_mask,
+		int slots, int slot_width)
+{
+	struct max98504_priv *max98504 = snd_soc_dai_get_drvdata(dai);
+	struct regmap *map = max98504->regmap;
+
+
+	switch (dai->id) {
+	case MAX98504_DAI_ID_PCM:
+		regmap_write(map, MAX98504_PCM_TX_ENABLE, tx_mask);
+		max98504->pcm_rx_channels = rx_mask;
+		break;
+
+	case MAX98504_DAI_ID_PDM:
+		regmap_write(map, MAX98504_PDM_TX_ENABLE, tx_mask);
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	return 0;
+}
+static int max98504_set_channel_map(struct snd_soc_dai *dai,
+		unsigned int tx_num, unsigned int *tx_slot,
+		unsigned int rx_num, unsigned int *rx_slot)
+{
+	struct max98504_priv *max98504 = snd_soc_dai_get_drvdata(dai);
+	struct regmap *map = max98504->regmap;
+	unsigned int i, sources = 0;
+
+	for (i = 0; i < tx_num; i++)
+		if (tx_slot[i])
+			sources |= (1 << i);
+
+	switch (dai->id) {
+	case MAX98504_DAI_ID_PCM:
+		regmap_write(map, MAX98504_PCM_TX_CHANNEL_SOURCES,
+			     sources);
+		break;
+
+	case MAX98504_DAI_ID_PDM:
+		regmap_write(map, MAX98504_PDM_TX_CONTROL, sources);
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	regmap_write(map, MAX98504_MEASUREMENT_ENABLE, sources ? 0x3 : 0x01);
+
+	return 0;
+}
+
+static const struct snd_soc_dai_ops max98504_dai_ops = {
+	.set_tdm_slot		= max98504_set_tdm_slot,
+	.set_channel_map	= max98504_set_channel_map,
+};
+
+#define MAX98504_FORMATS	(SNDRV_PCM_FMTBIT_S8|SNDRV_PCM_FMTBIT_S16_LE|\
+				SNDRV_PCM_FMTBIT_S24_LE|SNDRV_PCM_FMTBIT_S32_LE)
+#define MAX98504_PDM_RATES	(SNDRV_PCM_RATE_8000|SNDRV_PCM_RATE_16000|\
+				SNDRV_PCM_RATE_32000|SNDRV_PCM_RATE_44100|\
+				SNDRV_PCM_RATE_48000|SNDRV_PCM_RATE_88200|\
+				SNDRV_PCM_RATE_96000)
+
+static struct snd_soc_dai_driver max98504_dai[] = {
+	/* TODO: Add the PCM interface definitions */
+	{
+		.name = "max98504-aif2",
+		.id = MAX98504_DAI_ID_PDM,
+		.playback = {
+			.stream_name	= "AIF2 Playback",
+			.channels_min	= 1,
+			.channels_max	= 2,
+			.rates		= MAX98504_PDM_RATES,
+			.formats	= MAX98504_FORMATS,
+		},
+		.capture = {
+			.stream_name	= "AIF2 Capture",
+			.channels_min	= 1,
+			.channels_max	= 2,
+			.rates		= MAX98504_PDM_RATES,
+			.formats	= MAX98504_FORMATS,
+		},
+		.ops = &max98504_dai_ops,
+	},
+};
+
+static const struct snd_soc_component_driver max98504_component_driver = {
+	.probe			= max98504_component_probe,
+	.remove			= max98504_component_remove,
+	.dapm_widgets		= max98504_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(max98504_dapm_widgets),
+	.dapm_routes		= max98504_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(max98504_dapm_routes),
+};
+
+static const struct regmap_config max98504_regmap = {
+	.reg_bits		= 16,
+	.val_bits		= 8,
+	.max_register		= MAX98504_MAX_REGISTER,
+	.reg_defaults		= max98504_reg_defaults,
+	.num_reg_defaults	= ARRAY_SIZE(max98504_reg_defaults),
+	.volatile_reg		= max98504_volatile_register,
+	.readable_reg		= max98504_readable_register,
+	.cache_type		= REGCACHE_RBTREE,
+};
+
+static int max98504_i2c_probe(struct i2c_client *client,
+			      const struct i2c_device_id *id)
+{
+	struct device *dev = &client->dev;
+	struct device_node *node = dev->of_node;
+	struct max98504_priv *max98504;
+	int i, ret;
+
+	max98504 = devm_kzalloc(dev, sizeof(*max98504), GFP_KERNEL);
+	if (!max98504)
+		return -ENOMEM;
+
+	if (node) {
+		if (!of_property_read_u32(node, "maxim,brownout-threshold",
+					&max98504->brownout_threshold))
+			max98504->brownout_enable = true;
+
+		of_property_read_u32(node, "maxim,brownout-attenuation",
+					&max98504->brownout_attenuation);
+		of_property_read_u32(node, "maxim,brownout-attack-hold-ms",
+					&max98504->brownout_attack_hold);
+		of_property_read_u32(node, "maxim,brownout-timed-hold-ms",
+					&max98504->brownout_timed_hold);
+		of_property_read_u32(node, "maxim,brownout-release-rate-ms",
+					&max98504->brownout_release_rate);
+	}
+
+	max98504->regmap = devm_regmap_init_i2c(client, &max98504_regmap);
+	if (IS_ERR(max98504->regmap)) {
+		ret = PTR_ERR(max98504->regmap);
+		dev_err(&client->dev, "regmap initialization failed: %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < MAX98504_NUM_SUPPLIES; i++)
+		max98504->supplies[i].supply = max98504_supply_names[i];
+
+	ret = devm_regulator_bulk_get(dev, MAX98504_NUM_SUPPLIES,
+				      max98504->supplies);
+	if (ret < 0)
+		return ret;
+
+	i2c_set_clientdata(client, max98504);
+
+	return devm_snd_soc_register_component(dev, &max98504_component_driver,
+				max98504_dai, ARRAY_SIZE(max98504_dai));
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id max98504_of_match[] = {
+	{ .compatible = "maxim,max98504" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, max98504_of_match);
+#endif
+
+static const struct i2c_device_id max98504_i2c_id[] = {
+	{ "max98504" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, max98504_i2c_id);
+
+static struct i2c_driver max98504_i2c_driver = {
+	.driver = {
+		.name = "max98504",
+		.of_match_table = of_match_ptr(max98504_of_match),
+	},
+	.probe = max98504_i2c_probe,
+	.id_table = max98504_i2c_id,
+};
+module_i2c_driver(max98504_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC MAX98504 driver");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/max98504.h b/sound/soc/codecs/max98504.h
new file mode 100644
index 000000000000..afbefad2d5ce
--- /dev/null
+++ b/sound/soc/codecs/max98504.h
@@ -0,0 +1,59 @@
+/*
+ * MAX98504 ALSA SoC Audio driver
+ *
+ * Copyright 2011 - 2012 Maxim Integrated Products
+ * Copyright 2016 Samsung Electronics Co., Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef MAX98504_H_
+#define MAX98504_H_
+
+/*
+ * MAX98504 Register Definitions
+ */
+#define MAX98504_INTERRUPT_STATUS		0x01
+#define MAX98504_INTERRUPT_FLAGS		0x02
+#define MAX98504_INTERRUPT_ENABLE		0x03
+#define MAX98504_INTERRUPT_FLAG_CLEARS		0x04
+#define MAX98504_GPIO_ENABLE			0x10
+#define MAX98504_GPIO_CONFIG			0x11
+#define MAX98504_WATCHDOG_ENABLE		0x12
+#define MAX98504_WATCHDOG_CONFIG		0x13
+#define MAX98504_WATCHDOG_CLEAR			0x14
+#define MAX98504_CLOCK_MONITOR_ENABLE		0x15
+#define MAX98504_PVDD_BROWNOUT_ENABLE		0x16
+#define MAX98504_PVDD_BROWNOUT_CONFIG_1		0x17
+#define MAX98504_PVDD_BROWNOUT_CONFIG_2		0x18
+#define MAX98504_PVDD_BROWNOUT_CONFIG_3		0x19
+#define MAX98504_PVDD_BROWNOUT_CONFIG_4		0x1a
+#define MAX98504_PCM_RX_ENABLE			0x20
+#define MAX98504_PCM_TX_ENABLE			0x21
+#define MAX98504_PCM_TX_HIZ_CONTROL		0x22
+#define MAX98504_PCM_TX_CHANNEL_SOURCES		0x23
+#define MAX98504_PCM_MODE_CONFIG		0x24
+#define MAX98504_PCM_DSP_CONFIG			0x25
+#define MAX98504_PCM_CLOCK_SETUP		0x26
+#define MAX98504_PCM_SAMPLE_RATE_SETUP		0x27
+#define MAX98504_PCM_TO_SPEAKER_MONOMIX		0x28
+#define MAX98504_PDM_TX_ENABLE			0x30
+#define MAX98504_PDM_TX_HIZ_CONTROL		0x31
+#define MAX98504_PDM_TX_CONTROL			0x32
+#define MAX98504_PDM_RX_ENABLE			0x33
+#define MAX98504_SPEAKER_ENABLE			0x34
+#define MAX98504_SPEAKER_SOURCE_SELECT		0x35
+#define MAX98504_MEASUREMENT_ENABLE		0x36
+#define MAX98504_ANALOGUE_INPUT_GAIN		0x37
+#define MAX98504_TEMPERATURE_LIMIT_CONFIG	0x38
+#define MAX98504_GLOBAL_ENABLE			0x40
+#define MAX98504_SOFTWARE_RESET			0x41
+#define MAX98504_REV_ID				0x7fff
+
+#define MAX98504_MAX_REGISTER			0x7fff
+
+#define MAX98504_DAI_ID_PCM			1
+#define MAX98504_DAI_ID_PDM			2
+
+#endif /* MAX98504_H_ */
diff --git a/sound/soc/codecs/max9860.c b/sound/soc/codecs/max9860.c
new file mode 100644
index 000000000000..68074c92a7c0
--- /dev/null
+++ b/sound/soc/codecs/max9860.c
@@ -0,0 +1,753 @@
+/*
+ * Driver for the MAX9860 Mono Audio Voice Codec
+ *
+ * https://datasheets.maximintegrated.com/en/ds/MAX9860.pdf
+ *
+ * The driver does not support sidetone since the DVST register field is
+ * backwards with the mute near the maximum level instead of the minimum.
+ *
+ * Author: Peter Rosin <peda@axentia.s>
+ *         Copyright 2016 Axentia Technologies
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/kernel.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/i2c.h>
+#include <linux/regulator/consumer.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/pcm_params.h>
+#include <sound/tlv.h>
+
+#include "max9860.h"
+
+struct max9860_priv {
+	struct regmap *regmap;
+	struct regulator *dvddio;
+	struct notifier_block dvddio_nb;
+	u8 psclk;
+	unsigned long pclk_rate;
+	int fmt;
+};
+
+static int max9860_dvddio_event(struct notifier_block *nb,
+				unsigned long event, void *data)
+{
+	struct max9860_priv *max9860 = container_of(nb, struct max9860_priv,
+						    dvddio_nb);
+	if (event & REGULATOR_EVENT_DISABLE) {
+		regcache_mark_dirty(max9860->regmap);
+		regcache_cache_only(max9860->regmap, true);
+	}
+
+	return 0;
+}
+
+static const struct reg_default max9860_reg_defaults[] = {
+	{ MAX9860_PWRMAN,       0x00 },
+	{ MAX9860_INTEN,        0x00 },
+	{ MAX9860_SYSCLK,       0x00 },
+	{ MAX9860_AUDIOCLKHIGH, 0x00 },
+	{ MAX9860_AUDIOCLKLOW,  0x00 },
+	{ MAX9860_IFC1A,        0x00 },
+	{ MAX9860_IFC1B,        0x00 },
+	{ MAX9860_VOICEFLTR,    0x00 },
+	{ MAX9860_DACATTN,      0x00 },
+	{ MAX9860_ADCLEVEL,     0x00 },
+	{ MAX9860_DACGAIN,      0x00 },
+	{ MAX9860_MICGAIN,      0x00 },
+	{ MAX9860_MICADC,       0x00 },
+	{ MAX9860_NOISEGATE,    0x00 },
+};
+
+static bool max9860_readable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case MAX9860_INTRSTATUS ... MAX9860_MICGAIN:
+	case MAX9860_MICADC ... MAX9860_PWRMAN:
+	case MAX9860_REVISION:
+		return true;
+	}
+
+	return false;
+}
+
+static bool max9860_writeable(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case MAX9860_INTEN ... MAX9860_MICGAIN:
+	case MAX9860_MICADC ... MAX9860_PWRMAN:
+		return true;
+	}
+
+	return false;
+}
+
+static bool max9860_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case MAX9860_INTRSTATUS:
+	case MAX9860_MICREADBACK:
+		return true;
+	}
+
+	return false;
+}
+
+static bool max9860_precious(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case MAX9860_INTRSTATUS:
+		return true;
+	}
+
+	return false;
+}
+
+static const struct regmap_config max9860_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.readable_reg = max9860_readable,
+	.writeable_reg = max9860_writeable,
+	.volatile_reg = max9860_volatile,
+	.precious_reg = max9860_precious,
+
+	.max_register = MAX9860_MAX_REGISTER,
+	.reg_defaults = max9860_reg_defaults,
+	.num_reg_defaults = ARRAY_SIZE(max9860_reg_defaults),
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static const DECLARE_TLV_DB_SCALE(dva_tlv, -9100, 100, 1);
+static const DECLARE_TLV_DB_SCALE(dvg_tlv, 0, 600, 0);
+static const DECLARE_TLV_DB_SCALE(adc_tlv, -1200, 100, 0);
+static const DECLARE_TLV_DB_RANGE(pam_tlv,
+	0, MAX9860_PAM_MAX - 1,             TLV_DB_SCALE_ITEM(-2000, 2000, 1),
+	MAX9860_PAM_MAX, MAX9860_PAM_MAX,   TLV_DB_SCALE_ITEM(3000, 0, 0));
+static const DECLARE_TLV_DB_SCALE(pgam_tlv, 0, 100, 0);
+static const DECLARE_TLV_DB_SCALE(anth_tlv, -7600, 400, 1);
+static const DECLARE_TLV_DB_SCALE(agcth_tlv, -1800, 100, 0);
+
+static const char * const agchld_text[] = {
+	"AGC Disabled", "50ms", "100ms", "400ms"
+};
+
+static SOC_ENUM_SINGLE_DECL(agchld_enum, MAX9860_MICADC,
+			    MAX9860_AGCHLD_SHIFT, agchld_text);
+
+static const char * const agcsrc_text[] = {
+	"Left ADC", "Left/Right ADC"
+};
+
+static SOC_ENUM_SINGLE_DECL(agcsrc_enum, MAX9860_MICADC,
+			    MAX9860_AGCSRC_SHIFT, agcsrc_text);
+
+static const char * const agcatk_text[] = {
+	"3ms", "12ms", "50ms", "200ms"
+};
+
+static SOC_ENUM_SINGLE_DECL(agcatk_enum, MAX9860_MICADC,
+			    MAX9860_AGCATK_SHIFT, agcatk_text);
+
+static const char * const agcrls_text[] = {
+	"78ms", "156ms", "312ms", "625ms",
+	"1.25s", "2.5s", "5s", "10s"
+};
+
+static SOC_ENUM_SINGLE_DECL(agcrls_enum, MAX9860_MICADC,
+			    MAX9860_AGCRLS_SHIFT, agcrls_text);
+
+static const char * const filter_text[] = {
+	"Disabled",
+	"Elliptical HP 217Hz notch (16kHz)",
+	"Butterworth HP 500Hz (16kHz)",
+	"Elliptical HP 217Hz notch (8kHz)",
+	"Butterworth HP 500Hz (8kHz)",
+	"Butterworth HP 200Hz (48kHz)"
+};
+
+static SOC_ENUM_SINGLE_DECL(avflt_enum, MAX9860_VOICEFLTR,
+			    MAX9860_AVFLT_SHIFT, filter_text);
+
+static SOC_ENUM_SINGLE_DECL(dvflt_enum, MAX9860_VOICEFLTR,
+			    MAX9860_DVFLT_SHIFT, filter_text);
+
+static const struct snd_kcontrol_new max9860_controls[] = {
+SOC_SINGLE_TLV("Master Playback Volume", MAX9860_DACATTN,
+	       MAX9860_DVA_SHIFT, MAX9860_DVA_MUTE, 1, dva_tlv),
+SOC_SINGLE_TLV("DAC Gain Volume", MAX9860_DACGAIN,
+	       MAX9860_DVG_SHIFT, MAX9860_DVG_MAX, 0, dvg_tlv),
+SOC_DOUBLE_TLV("Line Capture Volume", MAX9860_ADCLEVEL,
+	       MAX9860_ADCLL_SHIFT, MAX9860_ADCRL_SHIFT, MAX9860_ADCxL_MIN, 1,
+	       adc_tlv),
+
+SOC_ENUM("AGC Hold Time", agchld_enum),
+SOC_ENUM("AGC/Noise Gate Source", agcsrc_enum),
+SOC_ENUM("AGC Attack Time", agcatk_enum),
+SOC_ENUM("AGC Release Time", agcrls_enum),
+
+SOC_SINGLE_TLV("Noise Gate Threshold Volume", MAX9860_NOISEGATE,
+	       MAX9860_ANTH_SHIFT, MAX9860_ANTH_MAX, 0, anth_tlv),
+SOC_SINGLE_TLV("AGC Signal Threshold Volume", MAX9860_NOISEGATE,
+	       MAX9860_AGCTH_SHIFT, MAX9860_AGCTH_MIN, 1, agcth_tlv),
+
+SOC_SINGLE_TLV("Mic PGA Volume", MAX9860_MICGAIN,
+	       MAX9860_PGAM_SHIFT, MAX9860_PGAM_MIN, 1, pgam_tlv),
+SOC_SINGLE_TLV("Mic Preamp Volume", MAX9860_MICGAIN,
+	       MAX9860_PAM_SHIFT, MAX9860_PAM_MAX, 0, pam_tlv),
+
+SOC_ENUM("ADC Filter", avflt_enum),
+SOC_ENUM("DAC Filter", dvflt_enum),
+};
+
+static const struct snd_soc_dapm_widget max9860_dapm_widgets[] = {
+SND_SOC_DAPM_INPUT("MICL"),
+SND_SOC_DAPM_INPUT("MICR"),
+
+SND_SOC_DAPM_ADC("ADCL", NULL, MAX9860_PWRMAN, MAX9860_ADCLEN_SHIFT, 0),
+SND_SOC_DAPM_ADC("ADCR", NULL, MAX9860_PWRMAN, MAX9860_ADCREN_SHIFT, 0),
+
+SND_SOC_DAPM_AIF_OUT("AIFOUTL", "Capture", 0, SND_SOC_NOPM, 0, 0),
+SND_SOC_DAPM_AIF_OUT("AIFOUTR", "Capture", 1, SND_SOC_NOPM, 0, 0),
+
+SND_SOC_DAPM_AIF_IN("AIFINL", "Playback", 0, SND_SOC_NOPM, 0, 0),
+SND_SOC_DAPM_AIF_IN("AIFINR", "Playback", 1, SND_SOC_NOPM, 0, 0),
+
+SND_SOC_DAPM_DAC("DAC", NULL, MAX9860_PWRMAN, MAX9860_DACEN_SHIFT, 0),
+
+SND_SOC_DAPM_OUTPUT("OUT"),
+
+SND_SOC_DAPM_SUPPLY("Supply", SND_SOC_NOPM, 0, 0,
+		    NULL, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+SND_SOC_DAPM_REGULATOR_SUPPLY("AVDD", 0, 0),
+SND_SOC_DAPM_REGULATOR_SUPPLY("DVDD", 0, 0),
+SND_SOC_DAPM_CLOCK_SUPPLY("mclk"),
+};
+
+static const struct snd_soc_dapm_route max9860_dapm_routes[] = {
+	{ "ADCL", NULL, "MICL" },
+	{ "ADCR", NULL, "MICR" },
+	{ "AIFOUTL", NULL, "ADCL" },
+	{ "AIFOUTR", NULL, "ADCR" },
+
+	{ "DAC", NULL, "AIFINL" },
+	{ "DAC", NULL, "AIFINR" },
+	{ "OUT", NULL, "DAC" },
+
+	{ "Supply", NULL, "AVDD" },
+	{ "Supply", NULL, "DVDD" },
+	{ "Supply", NULL, "mclk" },
+
+	{ "DAC", NULL, "Supply" },
+	{ "ADCL", NULL, "Supply" },
+	{ "ADCR", NULL, "Supply" },
+};
+
+static int max9860_hw_params(struct snd_pcm_substream *substream,
+			     struct snd_pcm_hw_params *params,
+			     struct snd_soc_dai *dai)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	struct max9860_priv *max9860 = snd_soc_codec_get_drvdata(codec);
+	u8 master;
+	u8 ifc1a = 0;
+	u8 ifc1b = 0;
+	u8 sysclk = 0;
+	unsigned long n;
+	int ret;
+
+	dev_dbg(codec->dev, "hw_params %u Hz, %u channels\n",
+		params_rate(params),
+		params_channels(params));
+
+	if (params_channels(params) == 2)
+		ifc1b |= MAX9860_ST;
+
+	switch (max9860->fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBS_CFS:
+		master = 0;
+		break;
+	case SND_SOC_DAIFMT_CBM_CFM:
+		master = MAX9860_MASTER;
+		break;
+	default:
+		return -EINVAL;
+	}
+	ifc1a |= master;
+
+	if (master) {
+		if (params_width(params) * params_channels(params) > 48)
+			ifc1b |= MAX9860_BSEL_64X;
+		else
+			ifc1b |= MAX9860_BSEL_48X;
+	}
+
+	switch (max9860->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		ifc1a |= MAX9860_DDLY;
+		ifc1b |= MAX9860_ADLY;
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		ifc1a |= MAX9860_WCI;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		if (params_width(params) != 16) {
+			dev_err(codec->dev,
+				"DSP_A works for 16 bits per sample only.\n");
+			return -EINVAL;
+		}
+		ifc1a |= MAX9860_DDLY | MAX9860_WCI | MAX9860_HIZ | MAX9860_TDM;
+		ifc1b |= MAX9860_ADLY;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		if (params_width(params) != 16) {
+			dev_err(codec->dev,
+				"DSP_B works for 16 bits per sample only.\n");
+			return -EINVAL;
+		}
+		ifc1a |= MAX9860_WCI | MAX9860_HIZ | MAX9860_TDM;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (max9860->fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		break;
+	case SND_SOC_DAIFMT_NB_IF:
+		switch (max9860->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+		case SND_SOC_DAIFMT_DSP_A:
+		case SND_SOC_DAIFMT_DSP_B:
+			return -EINVAL;
+		}
+		ifc1a ^= MAX9860_WCI;
+		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		switch (max9860->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+		case SND_SOC_DAIFMT_DSP_A:
+		case SND_SOC_DAIFMT_DSP_B:
+			return -EINVAL;
+		}
+		ifc1a ^= MAX9860_WCI;
+		/* fall through */
+	case SND_SOC_DAIFMT_IB_NF:
+		ifc1a ^= MAX9860_DBCI;
+		ifc1b ^= MAX9860_ABCI;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	dev_dbg(codec->dev, "IFC1A  %02x\n", ifc1a);
+	ret = regmap_write(max9860->regmap, MAX9860_IFC1A, ifc1a);
+	if (ret) {
+		dev_err(codec->dev, "Failed to set IFC1A: %d\n", ret);
+		return ret;
+	}
+	dev_dbg(codec->dev, "IFC1B  %02x\n", ifc1b);
+	ret = regmap_write(max9860->regmap, MAX9860_IFC1B, ifc1b);
+	if (ret) {
+		dev_err(codec->dev, "Failed to set IFC1B: %d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * Check if Integer Clock Mode is possible, but avoid it in slave mode
+	 * since we then do not know if lrclk is derived from pclk and the
+	 * datasheet mentions that the frequencies have to match exactly in
+	 * order for this to work.
+	 */
+	if (params_rate(params) == 8000 || params_rate(params) == 16000) {
+		if (master) {
+			switch (max9860->pclk_rate) {
+			case 12000000:
+				sysclk = MAX9860_FREQ_12MHZ;
+				break;
+			case 13000000:
+				sysclk = MAX9860_FREQ_13MHZ;
+				break;
+			case 19200000:
+				sysclk = MAX9860_FREQ_19_2MHZ;
+				break;
+			default:
+				/*
+				 * Integer Clock Mode not possible. Leave
+				 * sysclk at zero and fall through to the
+				 * code below for PLL mode.
+				 */
+				break;
+			}
+
+			if (sysclk && params_rate(params) == 16000)
+				sysclk |= MAX9860_16KHZ;
+		}
+	}
+
+	/*
+	 * Largest possible n:
+	 *    65536 * 96 * 48kHz / 10MHz -> 30199
+	 * Smallest possible n:
+	 *    65536 * 96 *  8kHz / 20MHz -> 2517
+	 * Both fit nicely in the available 15 bits, no need to apply any mask.
+	 */
+	n = DIV_ROUND_CLOSEST_ULL(65536ULL * 96 * params_rate(params),
+				  max9860->pclk_rate);
+
+	if (!sysclk) {
+		/* PLL mode */
+		if (params_rate(params) > 24000)
+			sysclk |= MAX9860_16KHZ;
+
+		if (!master)
+			n |= 1; /* trigger rapid pll lock mode */
+	}
+
+	sysclk |= max9860->psclk;
+	dev_dbg(codec->dev, "SYSCLK %02x\n", sysclk);
+	ret = regmap_write(max9860->regmap,
+			   MAX9860_SYSCLK, sysclk);
+	if (ret) {
+		dev_err(codec->dev, "Failed to set SYSCLK: %d\n", ret);
+		return ret;
+	}
+	dev_dbg(codec->dev, "N %lu\n", n);
+	ret = regmap_write(max9860->regmap,
+			   MAX9860_AUDIOCLKHIGH, n >> 8);
+	if (ret) {
+		dev_err(codec->dev, "Failed to set NHI: %d\n", ret);
+		return ret;
+	}
+	ret = regmap_write(max9860->regmap,
+			   MAX9860_AUDIOCLKLOW, n & 0xff);
+	if (ret) {
+		dev_err(codec->dev, "Failed to set NLO: %d\n", ret);
+		return ret;
+	}
+
+	if (!master) {
+		dev_dbg(codec->dev, "Enable PLL\n");
+		ret = regmap_update_bits(max9860->regmap, MAX9860_AUDIOCLKHIGH,
+					 MAX9860_PLL, MAX9860_PLL);
+		if (ret) {
+			dev_err(codec->dev, "Failed to enable PLL: %d\n", ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int max9860_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	struct max9860_priv *max9860 = snd_soc_codec_get_drvdata(codec);
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+	case SND_SOC_DAIFMT_CBS_CFS:
+		max9860->fmt = fmt;
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct snd_soc_dai_ops max9860_dai_ops = {
+	.hw_params = max9860_hw_params,
+	.set_fmt = max9860_set_fmt,
+};
+
+static struct snd_soc_dai_driver max9860_dai = {
+	.name = "max9860-hifi",
+	.playback = {
+		.stream_name = "Playback",
+		.channels_min = 1,
+		.channels_max = 2,
+		.rates = SNDRV_PCM_RATE_CONTINUOUS,
+		.rate_min = 8000,
+		.rate_max = 48000,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE |
+			   SNDRV_PCM_FMTBIT_S24_LE |
+			   SNDRV_PCM_FMTBIT_S32_LE,
+	},
+	.capture = {
+		.stream_name = "Capture",
+		.channels_min = 1,
+		.channels_max = 2,
+		.rates = SNDRV_PCM_RATE_CONTINUOUS,
+		.rate_min = 8000,
+		.rate_max = 48000,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE |
+			   SNDRV_PCM_FMTBIT_S24_LE |
+			   SNDRV_PCM_FMTBIT_S32_LE,
+	},
+	.ops = &max9860_dai_ops,
+	.symmetric_rates = 1,
+};
+
+static int max9860_set_bias_level(struct snd_soc_codec *codec,
+				  enum snd_soc_bias_level level)
+{
+	struct max9860_priv *max9860 = dev_get_drvdata(codec->dev);
+	int ret;
+
+	switch (level) {
+	case SND_SOC_BIAS_ON:
+	case SND_SOC_BIAS_PREPARE:
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		ret = regmap_update_bits(max9860->regmap, MAX9860_PWRMAN,
+					 MAX9860_SHDN, MAX9860_SHDN);
+		if (ret) {
+			dev_err(codec->dev, "Failed to remove SHDN: %d\n", ret);
+			return ret;
+		}
+		break;
+
+	case SND_SOC_BIAS_OFF:
+		ret = regmap_update_bits(max9860->regmap, MAX9860_PWRMAN,
+					 MAX9860_SHDN, 0);
+		if (ret) {
+			dev_err(codec->dev, "Failed to request SHDN: %d\n",
+				ret);
+			return ret;
+		}
+		break;
+	}
+
+	return 0;
+}
+
+static struct snd_soc_codec_driver max9860_codec_driver = {
+	.set_bias_level = max9860_set_bias_level,
+	.idle_bias_off = true,
+
+	.controls = max9860_controls,
+	.num_controls = ARRAY_SIZE(max9860_controls),
+	.dapm_widgets = max9860_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(max9860_dapm_widgets),
+	.dapm_routes = max9860_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(max9860_dapm_routes),
+};
+
+#ifdef CONFIG_PM
+static int max9860_suspend(struct device *dev)
+{
+	struct max9860_priv *max9860 = dev_get_drvdata(dev);
+	int ret;
+
+	ret = regmap_update_bits(max9860->regmap, MAX9860_SYSCLK,
+				 MAX9860_PSCLK, MAX9860_PSCLK_OFF);
+	if (ret) {
+		dev_err(dev, "Failed to disable clock: %d\n", ret);
+		return ret;
+	}
+
+	regulator_disable(max9860->dvddio);
+
+	return 0;
+}
+
+static int max9860_resume(struct device *dev)
+{
+	struct max9860_priv *max9860 = dev_get_drvdata(dev);
+	int ret;
+
+	ret = regulator_enable(max9860->dvddio);
+	if (ret) {
+		dev_err(dev, "Failed to enable DVDDIO: %d\n", ret);
+		return ret;
+	}
+
+	regcache_cache_only(max9860->regmap, false);
+	ret = regcache_sync(max9860->regmap);
+	if (ret) {
+		dev_err(dev, "Failed to sync cache: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_update_bits(max9860->regmap, MAX9860_SYSCLK,
+				 MAX9860_PSCLK, max9860->psclk);
+	if (ret) {
+		dev_err(dev, "Failed to enable clock: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops max9860_pm_ops = {
+	SET_RUNTIME_PM_OPS(max9860_suspend, max9860_resume, NULL)
+};
+
+static int max9860_probe(struct i2c_client *i2c,
+			 const struct i2c_device_id *id)
+{
+	struct device *dev = &i2c->dev;
+	struct max9860_priv *max9860;
+	int ret;
+	struct clk *mclk;
+	unsigned long mclk_rate;
+	int i;
+	int intr;
+
+	max9860 = devm_kzalloc(dev, sizeof(struct max9860_priv), GFP_KERNEL);
+	if (!max9860)
+		return -ENOMEM;
+
+	max9860->dvddio = devm_regulator_get(dev, "DVDDIO");
+	if (IS_ERR(max9860->dvddio)) {
+		ret = PTR_ERR(max9860->dvddio);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get DVDDIO supply: %d\n", ret);
+		return ret;
+	}
+
+	max9860->dvddio_nb.notifier_call = max9860_dvddio_event;
+
+	ret = regulator_register_notifier(max9860->dvddio, &max9860->dvddio_nb);
+	if (ret)
+		dev_err(dev, "Failed to register DVDDIO notifier: %d\n", ret);
+
+	ret = regulator_enable(max9860->dvddio);
+	if (ret != 0) {
+		dev_err(dev, "Failed to enable DVDDIO: %d\n", ret);
+		return ret;
+	}
+
+	max9860->regmap = devm_regmap_init_i2c(i2c, &max9860_regmap);
+	if (IS_ERR(max9860->regmap)) {
+		ret = PTR_ERR(max9860->regmap);
+		goto err_regulator;
+	}
+
+	dev_set_drvdata(dev, max9860);
+
+	/*
+	 * mclk has to be in the 10MHz to 60MHz range.
+	 * psclk is used to scale mclk into pclk so that
+	 * pclk is in the 10MHz to 20MHz range.
+	 */
+	mclk = clk_get(dev, "mclk");
+
+	if (IS_ERR(mclk)) {
+		ret = PTR_ERR(mclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get MCLK: %d\n", ret);
+		goto err_regulator;
+	}
+
+	mclk_rate = clk_get_rate(mclk);
+	clk_put(mclk);
+
+	if (mclk_rate > 60000000 || mclk_rate < 10000000) {
+		dev_err(dev, "Bad mclk %luHz (needs 10MHz - 60MHz)\n",
+			mclk_rate);
+		ret = -EINVAL;
+		goto err_regulator;
+	}
+	if (mclk_rate >= 40000000)
+		max9860->psclk = 3;
+	else if (mclk_rate >= 20000000)
+		max9860->psclk = 2;
+	else
+		max9860->psclk = 1;
+	max9860->pclk_rate = mclk_rate >> (max9860->psclk - 1);
+	max9860->psclk <<= MAX9860_PSCLK_SHIFT;
+	dev_dbg(dev, "mclk %lu pclk %lu\n", mclk_rate, max9860->pclk_rate);
+
+	regcache_cache_bypass(max9860->regmap, true);
+	for (i = 0; i < max9860_regmap.num_reg_defaults; ++i) {
+		ret = regmap_write(max9860->regmap,
+				   max9860_regmap.reg_defaults[i].reg,
+				   max9860_regmap.reg_defaults[i].def);
+		if (ret) {
+			dev_err(dev, "Failed to initialize register %u: %d\n",
+				max9860_regmap.reg_defaults[i].reg, ret);
+			goto err_regulator;
+		}
+	}
+	regcache_cache_bypass(max9860->regmap, false);
+
+	ret = regmap_read(max9860->regmap, MAX9860_INTRSTATUS, &intr);
+	if (ret) {
+		dev_err(dev, "Failed to clear INTRSTATUS: %d\n", ret);
+		goto err_regulator;
+	}
+
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+	pm_runtime_idle(dev);
+
+	ret = snd_soc_register_codec(dev, &max9860_codec_driver,
+				     &max9860_dai, 1);
+	if (ret) {
+		dev_err(dev, "Failed to register CODEC: %d\n", ret);
+		goto err_pm;
+	}
+
+	return 0;
+
+err_pm:
+	pm_runtime_disable(dev);
+err_regulator:
+	regulator_disable(max9860->dvddio);
+	return ret;
+}
+
+static int max9860_remove(struct i2c_client *i2c)
+{
+	struct device *dev = &i2c->dev;
+	struct max9860_priv *max9860 = dev_get_drvdata(dev);
+
+	snd_soc_unregister_codec(dev);
+	pm_runtime_disable(dev);
+	regulator_disable(max9860->dvddio);
+	return 0;
+}
+
+static const struct i2c_device_id max9860_i2c_id[] = {
+	{ "max9860", },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, max9860_i2c_id);
+
+static const struct of_device_id max9860_of_match[] = {
+	{ .compatible = "maxim,max9860", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, max9860_of_match);
+
+static struct i2c_driver max9860_i2c_driver = {
+	.probe	        = max9860_probe,
+	.remove         = max9860_remove,
+	.id_table       = max9860_i2c_id,
+	.driver         = {
+		.name           = "max9860",
+		.of_match_table = max9860_of_match,
+		.pm             = &max9860_pm_ops,
+	},
+};
+
+module_i2c_driver(max9860_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC MAX9860 Mono Audio Voice Codec driver");
+MODULE_AUTHOR("Peter Rosin <peda@axentia.se>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/max9860.h b/sound/soc/codecs/max9860.h
new file mode 100644
index 000000000000..22041bd67a7d
--- /dev/null
+++ b/sound/soc/codecs/max9860.h
@@ -0,0 +1,162 @@
+/*
+ * Driver for the MAX9860 Mono Audio Voice Codec
+ *
+ * Author: Peter Rosin <peda@axentia.s>
+ *         Copyright 2016 Axentia Technologies
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _SND_SOC_MAX9860
+#define _SND_SOC_MAX9860
+
+#define MAX9860_INTRSTATUS   0x00
+#define MAX9860_MICREADBACK  0x01
+#define MAX9860_INTEN        0x02
+#define MAX9860_SYSCLK       0x03
+#define MAX9860_AUDIOCLKHIGH 0x04
+#define MAX9860_AUDIOCLKLOW  0x05
+#define MAX9860_IFC1A        0x06
+#define MAX9860_IFC1B        0x07
+#define MAX9860_VOICEFLTR    0x08
+#define MAX9860_DACATTN      0x09
+#define MAX9860_ADCLEVEL     0x0a
+#define MAX9860_DACGAIN      0x0b
+#define MAX9860_MICGAIN      0x0c
+#define MAX9860_RESERVED     0x0d
+#define MAX9860_MICADC       0x0e
+#define MAX9860_NOISEGATE    0x0f
+#define MAX9860_PWRMAN       0x10
+#define MAX9860_REVISION     0xff
+
+#define MAX9860_MAX_REGISTER 0xff
+
+/* INTRSTATUS */
+#define MAX9860_CLD          0x80
+#define MAX9860_SLD          0x40
+#define MAX9860_ULK          0x20
+
+/* MICREADBACK */
+#define MAX9860_NG           0xe0
+#define MAX9860_AGC          0x1f
+
+/* INTEN */
+#define MAX9860_ICLD         0x80
+#define MAX9860_ISLD         0x40
+#define MAX9860_IULK         0x20
+
+/* SYSCLK */
+#define MAX9860_PSCLK        0x30
+#define MAX9860_PSCLK_OFF    0x00
+#define MAX9860_PSCLK_SHIFT  4
+#define MAX9860_FREQ         0x06
+#define MAX9860_FREQ_NORMAL  0x00
+#define MAX9860_FREQ_12MHZ   0x02
+#define MAX9860_FREQ_13MHZ   0x04
+#define MAX9860_FREQ_19_2MHZ 0x06
+#define MAX9860_16KHZ        0x01
+
+/* AUDIOCLKHIGH */
+#define MAX9860_PLL          0x80
+#define MAX9860_NHI          0x7f
+
+/* AUDIOCLKLOW */
+#define MAX9860_NLO          0xff
+
+/* IFC1A */
+#define MAX9860_MASTER       0x80
+#define MAX9860_WCI          0x40
+#define MAX9860_DBCI         0x20
+#define MAX9860_DDLY         0x10
+#define MAX9860_HIZ          0x08
+#define MAX9860_TDM          0x04
+
+/* IFC1B */
+#define MAX9860_ABCI         0x20
+#define MAX9860_ADLY         0x10
+#define MAX9860_ST           0x08
+#define MAX9860_BSEL         0x07
+#define MAX9860_BSEL_OFF     0x00
+#define MAX9860_BSEL_64X     0x01
+#define MAX9860_BSEL_48X     0x02
+#define MAX9860_BSEL_PCLK_2  0x04
+#define MAX9860_BSEL_PCLK_4  0x05
+#define MAX9860_BSEL_PCLK_8  0x06
+#define MAX9860_BSEL_PCLK_16 0x07
+
+/* VOICEFLTR */
+#define MAX9860_AVFLT        0xf0
+#define MAX9860_AVFLT_SHIFT  4
+#define MAX9860_AVFLT_COUNT  6
+#define MAX9860_DVFLT        0x0f
+#define MAX9860_DVFLT_SHIFT  0
+#define MAX9860_DVFLT_COUNT  6
+
+/* DACATTN */
+#define MAX9860_DVA          0xfe
+#define MAX9860_DVA_SHIFT    1
+#define MAX9860_DVA_MUTE     0x5e
+
+/* ADCLEVEL */
+#define MAX9860_ADCRL        0xf0
+#define MAX9860_ADCRL_SHIFT  4
+#define MAX9860_ADCLL        0x0f
+#define MAX9860_ADCLL_SHIFT  0
+#define MAX9860_ADCxL_MIN    15
+
+/* DACGAIN */
+#define MAX9860_DVG          0x60
+#define MAX9860_DVG_SHIFT    5
+#define MAX9860_DVG_MAX      3
+#define MAX9860_DVST         0x1f
+#define MAX9860_DVST_SHIFT   0
+#define MAX9860_DVST_MIN     31
+
+/* MICGAIN */
+#define MAX9860_PAM          0x60
+#define MAX9860_PAM_SHIFT    5
+#define MAX9860_PAM_MAX      3
+#define MAX9860_PGAM         0x1f
+#define MAX9860_PGAM_SHIFT   0
+#define MAX9860_PGAM_MIN     20
+
+/* MICADC */
+#define MAX9860_AGCSRC       0x80
+#define MAX9860_AGCSRC_SHIFT 7
+#define MAX9860_AGCSRC_COUNT 2
+#define MAX9860_AGCRLS       0x70
+#define MAX9860_AGCRLS_SHIFT 4
+#define MAX9860_AGCRLS_COUNT 8
+#define MAX9860_AGCATK       0x0c
+#define MAX9860_AGCATK_SHIFT 2
+#define MAX9860_AGCATK_COUNT 4
+#define MAX9860_AGCHLD       0x03
+#define MAX9860_AGCHLD_OFF   0x00
+#define MAX9860_AGCHLD_SHIFT 0
+#define MAX9860_AGCHLD_COUNT 4
+
+/* NOISEGATE */
+#define MAX9860_ANTH         0xf0
+#define MAX9860_ANTH_SHIFT   4
+#define MAX9860_ANTH_MAX     15
+#define MAX9860_AGCTH        0x0f
+#define MAX9860_AGCTH_SHIFT  0
+#define MAX9860_AGCTH_MIN    15
+
+/* PWRMAN */
+#define MAX9860_SHDN         0x80
+#define MAX9860_DACEN        0x08
+#define MAX9860_DACEN_SHIFT  3
+#define MAX9860_ADCLEN       0x02
+#define MAX9860_ADCLEN_SHIFT 1
+#define MAX9860_ADCREN       0x01
+#define MAX9860_ADCREN_SHIFT 0
+
+#endif /* _SND_SOC_MAX9860 */
diff --git a/sound/soc/codecs/max9867.c b/sound/soc/codecs/max9867.c
index 2a22fddeb6af..2a22fddeb6af 100755..100644
--- a/sound/soc/codecs/max9867.c
+++ b/sound/soc/codecs/max9867.c
diff --git a/sound/soc/codecs/max9867.h b/sound/soc/codecs/max9867.h
index 65590b4ad62a..65590b4ad62a 100755..100644
--- a/sound/soc/codecs/max9867.h
+++ b/sound/soc/codecs/max9867.h
diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c
index 683769f0f246..5c9707ac4bbf 100644
--- a/sound/soc/codecs/nau8825.c
+++ b/sound/soc/codecs/nau8825.c
@@ -18,6 +18,7 @@
 #include <linux/clk.h>
 #include <linux/acpi.h>
 #include <linux/math64.h>
+#include <linux/semaphore.h>
 
 #include <sound/initval.h>
 #include <sound/tlv.h>
@@ -30,10 +31,22 @@
 
 #include "nau8825.h"
 
+
+#define NUVOTON_CODEC_DAI "nau8825-hifi"
+
 #define NAU_FREF_MAX 13500000
-#define NAU_FVCO_MAX 100000000
+#define NAU_FVCO_MAX 124000000
 #define NAU_FVCO_MIN 90000000
 
+/* cross talk suppression detection */
+#define LOG10_MAGIC 646456993
+#define GAIN_AUGMENT 22500
+#define SIDETONE_BASE 207000
+
+
+static int nau8825_configure_sysclk(struct nau8825 *nau8825,
+		int clk_id, unsigned int freq);
+
 struct nau8825_fll {
 	int mclk_src;
 	int ratio;
@@ -156,6 +169,661 @@ static const struct reg_default nau8825_reg_defaults[] = {
 	{ NAU8825_REG_CHARGE_PUMP, 0x0 },
 };
 
+/* register backup table when cross talk detection */
+static struct reg_default nau8825_xtalk_baktab[] = {
+	{ NAU8825_REG_ADC_DGAIN_CTRL, 0 },
+	{ NAU8825_REG_HSVOL_CTRL, 0 },
+	{ NAU8825_REG_DACL_CTRL, 0 },
+	{ NAU8825_REG_DACR_CTRL, 0 },
+};
+
+static const unsigned short logtable[256] = {
+	0x0000, 0x0171, 0x02e0, 0x044e, 0x05ba, 0x0725, 0x088e, 0x09f7,
+	0x0b5d, 0x0cc3, 0x0e27, 0x0f8a, 0x10eb, 0x124b, 0x13aa, 0x1508,
+	0x1664, 0x17bf, 0x1919, 0x1a71, 0x1bc8, 0x1d1e, 0x1e73, 0x1fc6,
+	0x2119, 0x226a, 0x23ba, 0x2508, 0x2656, 0x27a2, 0x28ed, 0x2a37,
+	0x2b80, 0x2cc8, 0x2e0f, 0x2f54, 0x3098, 0x31dc, 0x331e, 0x345f,
+	0x359f, 0x36de, 0x381b, 0x3958, 0x3a94, 0x3bce, 0x3d08, 0x3e41,
+	0x3f78, 0x40af, 0x41e4, 0x4319, 0x444c, 0x457f, 0x46b0, 0x47e1,
+	0x4910, 0x4a3f, 0x4b6c, 0x4c99, 0x4dc5, 0x4eef, 0x5019, 0x5142,
+	0x526a, 0x5391, 0x54b7, 0x55dc, 0x5700, 0x5824, 0x5946, 0x5a68,
+	0x5b89, 0x5ca8, 0x5dc7, 0x5ee5, 0x6003, 0x611f, 0x623a, 0x6355,
+	0x646f, 0x6588, 0x66a0, 0x67b7, 0x68ce, 0x69e4, 0x6af8, 0x6c0c,
+	0x6d20, 0x6e32, 0x6f44, 0x7055, 0x7165, 0x7274, 0x7383, 0x7490,
+	0x759d, 0x76aa, 0x77b5, 0x78c0, 0x79ca, 0x7ad3, 0x7bdb, 0x7ce3,
+	0x7dea, 0x7ef0, 0x7ff6, 0x80fb, 0x81ff, 0x8302, 0x8405, 0x8507,
+	0x8608, 0x8709, 0x8809, 0x8908, 0x8a06, 0x8b04, 0x8c01, 0x8cfe,
+	0x8dfa, 0x8ef5, 0x8fef, 0x90e9, 0x91e2, 0x92db, 0x93d2, 0x94ca,
+	0x95c0, 0x96b6, 0x97ab, 0x98a0, 0x9994, 0x9a87, 0x9b7a, 0x9c6c,
+	0x9d5e, 0x9e4f, 0x9f3f, 0xa02e, 0xa11e, 0xa20c, 0xa2fa, 0xa3e7,
+	0xa4d4, 0xa5c0, 0xa6ab, 0xa796, 0xa881, 0xa96a, 0xaa53, 0xab3c,
+	0xac24, 0xad0c, 0xadf2, 0xaed9, 0xafbe, 0xb0a4, 0xb188, 0xb26c,
+	0xb350, 0xb433, 0xb515, 0xb5f7, 0xb6d9, 0xb7ba, 0xb89a, 0xb97a,
+	0xba59, 0xbb38, 0xbc16, 0xbcf4, 0xbdd1, 0xbead, 0xbf8a, 0xc065,
+	0xc140, 0xc21b, 0xc2f5, 0xc3cf, 0xc4a8, 0xc580, 0xc658, 0xc730,
+	0xc807, 0xc8de, 0xc9b4, 0xca8a, 0xcb5f, 0xcc34, 0xcd08, 0xcddc,
+	0xceaf, 0xcf82, 0xd054, 0xd126, 0xd1f7, 0xd2c8, 0xd399, 0xd469,
+	0xd538, 0xd607, 0xd6d6, 0xd7a4, 0xd872, 0xd93f, 0xda0c, 0xdad9,
+	0xdba5, 0xdc70, 0xdd3b, 0xde06, 0xded0, 0xdf9a, 0xe063, 0xe12c,
+	0xe1f5, 0xe2bd, 0xe385, 0xe44c, 0xe513, 0xe5d9, 0xe69f, 0xe765,
+	0xe82a, 0xe8ef, 0xe9b3, 0xea77, 0xeb3b, 0xebfe, 0xecc1, 0xed83,
+	0xee45, 0xef06, 0xefc8, 0xf088, 0xf149, 0xf209, 0xf2c8, 0xf387,
+	0xf446, 0xf505, 0xf5c3, 0xf680, 0xf73e, 0xf7fb, 0xf8b7, 0xf973,
+	0xfa2f, 0xfaea, 0xfba5, 0xfc60, 0xfd1a, 0xfdd4, 0xfe8e, 0xff47
+};
+
+static struct snd_soc_dai *nau8825_get_codec_dai(struct nau8825 *nau8825)
+{
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(nau8825->dapm);
+	struct snd_soc_component *component = &codec->component;
+	struct snd_soc_dai *codec_dai, *_dai;
+
+	list_for_each_entry_safe(codec_dai, _dai, &component->dai_list, list) {
+		if (!strncmp(codec_dai->name, NUVOTON_CODEC_DAI,
+			strlen(NUVOTON_CODEC_DAI)))
+			return codec_dai;
+	}
+	return NULL;
+}
+
+static bool nau8825_dai_is_active(struct nau8825 *nau8825)
+{
+	struct snd_soc_dai *codec_dai = nau8825_get_codec_dai(nau8825);
+
+	if (codec_dai) {
+		if (codec_dai->playback_active || codec_dai->capture_active)
+			return true;
+	}
+	return false;
+}
+
+/**
+ * nau8825_sema_acquire - acquire the semaphore of nau88l25
+ * @nau8825:  component to register the codec private data with
+ * @timeout: how long in jiffies to wait before failure or zero to wait
+ * until release
+ *
+ * Attempts to acquire the semaphore with number of jiffies. If no more
+ * tasks are allowed to acquire the semaphore, calling this function will
+ * put the task to sleep. If the semaphore is not released within the
+ * specified number of jiffies, this function returns.
+ * Acquires the semaphore without jiffies. If no more tasks are allowed
+ * to acquire the semaphore, calling this function will put the task to
+ * sleep until the semaphore is released.
+ * It returns if the semaphore was acquired.
+ */
+static void nau8825_sema_acquire(struct nau8825 *nau8825, long timeout)
+{
+	int ret;
+
+	if (timeout)
+		ret = down_timeout(&nau8825->xtalk_sem, timeout);
+	else
+		ret = down_interruptible(&nau8825->xtalk_sem);
+
+	if (ret < 0)
+		dev_warn(nau8825->dev, "Acquire semaphone fail\n");
+}
+
+/**
+ * nau8825_sema_release - release the semaphore of nau88l25
+ * @nau8825:  component to register the codec private data with
+ *
+ * Release the semaphore which may be called from any context and
+ * even by tasks which have never called down().
+ */
+static inline void nau8825_sema_release(struct nau8825 *nau8825)
+{
+	up(&nau8825->xtalk_sem);
+}
+
+/**
+ * nau8825_sema_reset - reset the semaphore for nau88l25
+ * @nau8825:  component to register the codec private data with
+ *
+ * Reset the counter of the semaphore. Call this function to restart
+ * a new round task management.
+ */
+static inline void nau8825_sema_reset(struct nau8825 *nau8825)
+{
+	nau8825->xtalk_sem.count = 1;
+}
+
+/**
+ * Ramp up the headphone volume change gradually to target level.
+ *
+ * @nau8825:  component to register the codec private data with
+ * @vol_from: the volume to start up
+ * @vol_to: the target volume
+ * @step: the volume span to move on
+ *
+ * The headphone volume is from 0dB to minimum -54dB and -1dB per step.
+ * If the volume changes sharp, there is a pop noise heard in headphone. We
+ * provide the function to ramp up the volume up or down by delaying 10ms
+ * per step.
+ */
+static void nau8825_hpvol_ramp(struct nau8825 *nau8825,
+	unsigned int vol_from, unsigned int vol_to, unsigned int step)
+{
+	unsigned int value, volume, ramp_up, from, to;
+
+	if (vol_from == vol_to || step == 0) {
+		return;
+	} else if (vol_from < vol_to) {
+		ramp_up = true;
+		from = vol_from;
+		to = vol_to;
+	} else {
+		ramp_up = false;
+		from = vol_to;
+		to = vol_from;
+	}
+	/* only handle volume from 0dB to minimum -54dB */
+	if (to > NAU8825_HP_VOL_MIN)
+		to = NAU8825_HP_VOL_MIN;
+
+	for (volume = from; volume < to; volume += step) {
+		if (ramp_up)
+			value = volume;
+		else
+			value = to - volume + from;
+		regmap_update_bits(nau8825->regmap, NAU8825_REG_HSVOL_CTRL,
+			NAU8825_HPL_VOL_MASK | NAU8825_HPR_VOL_MASK,
+			(value << NAU8825_HPL_VOL_SFT) | value);
+		usleep_range(10000, 10500);
+	}
+	if (ramp_up)
+		value = to;
+	else
+		value = from;
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_HSVOL_CTRL,
+		NAU8825_HPL_VOL_MASK | NAU8825_HPR_VOL_MASK,
+		(value << NAU8825_HPL_VOL_SFT) | value);
+}
+
+/**
+ * Computes log10 of a value; the result is round off to 3 decimal. This func-
+ * tion takes reference to dvb-math. The source code locates as the following.
+ * Linux/drivers/media/dvb-core/dvb_math.c
+ *
+ * return log10(value) * 1000
+ */
+static u32 nau8825_intlog10_dec3(u32 value)
+{
+	u32 msb, logentry, significand, interpolation, log10val;
+	u64 log2val;
+
+	/* first detect the msb (count begins at 0) */
+	msb = fls(value) - 1;
+	/**
+	 *      now we use a logtable after the following method:
+	 *
+	 *      log2(2^x * y) * 2^24 = x * 2^24 + log2(y) * 2^24
+	 *      where x = msb and therefore 1 <= y < 2
+	 *      first y is determined by shifting the value left
+	 *      so that msb is bit 31
+	 *              0x00231f56 -> 0x8C7D5800
+	 *      the result is y * 2^31 -> "significand"
+	 *      then the highest 9 bits are used for a table lookup
+	 *      the highest bit is discarded because it's always set
+	 *      the highest nine bits in our example are 100011000
+	 *      so we would use the entry 0x18
+	 */
+	significand = value << (31 - msb);
+	logentry = (significand >> 23) & 0xff;
+	/**
+	 *      last step we do is interpolation because of the
+	 *      limitations of the log table the error is that part of
+	 *      the significand which isn't used for lookup then we
+	 *      compute the ratio between the error and the next table entry
+	 *      and interpolate it between the log table entry used and the
+	 *      next one the biggest error possible is 0x7fffff
+	 *      (in our example it's 0x7D5800)
+	 *      needed value for next table entry is 0x800000
+	 *      so the interpolation is
+	 *      (error / 0x800000) * (logtable_next - logtable_current)
+	 *      in the implementation the division is moved to the end for
+	 *      better accuracy there is also an overflow correction if
+	 *      logtable_next is 256
+	 */
+	interpolation = ((significand & 0x7fffff) *
+		((logtable[(logentry + 1) & 0xff] -
+		logtable[logentry]) & 0xffff)) >> 15;
+
+	log2val = ((msb << 24) + (logtable[logentry] << 8) + interpolation);
+	/**
+	 *      log10(x) = log2(x) * log10(2)
+	 */
+	log10val = (log2val * LOG10_MAGIC) >> 31;
+	/**
+	 *      the result is round off to 3 decimal
+	 */
+	return log10val / ((1 << 24) / 1000);
+}
+
+/**
+ * computes cross talk suppression sidetone gain.
+ *
+ * @sig_org: orignal signal level
+ * @sig_cros: cross talk signal level
+ *
+ * The orignal and cross talk signal vlues need to be characterized.
+ * Once these values have been characterized, this sidetone value
+ * can be converted to decibel with the equation below.
+ * sidetone = 20 * log (original signal level / crosstalk signal level)
+ *
+ * return cross talk sidetone gain
+ */
+static u32 nau8825_xtalk_sidetone(u32 sig_org, u32 sig_cros)
+{
+	u32 gain, sidetone;
+
+	if (unlikely(sig_org == 0) || unlikely(sig_cros == 0)) {
+		WARN_ON(1);
+		return 0;
+	}
+
+	sig_org = nau8825_intlog10_dec3(sig_org);
+	sig_cros = nau8825_intlog10_dec3(sig_cros);
+	if (sig_org >= sig_cros)
+		gain = (sig_org - sig_cros) * 20 + GAIN_AUGMENT;
+	else
+		gain = (sig_cros - sig_org) * 20 + GAIN_AUGMENT;
+	sidetone = SIDETONE_BASE - gain * 2;
+	sidetone /= 1000;
+
+	return sidetone;
+}
+
+static int nau8825_xtalk_baktab_index_by_reg(unsigned int reg)
+{
+	int index;
+
+	for (index = 0; index < ARRAY_SIZE(nau8825_xtalk_baktab); index++)
+		if (nau8825_xtalk_baktab[index].reg == reg)
+			return index;
+	return -EINVAL;
+}
+
+static void nau8825_xtalk_backup(struct nau8825 *nau8825)
+{
+	int i;
+
+	/* Backup some register values to backup table */
+	for (i = 0; i < ARRAY_SIZE(nau8825_xtalk_baktab); i++)
+		regmap_read(nau8825->regmap, nau8825_xtalk_baktab[i].reg,
+				&nau8825_xtalk_baktab[i].def);
+}
+
+static void nau8825_xtalk_restore(struct nau8825 *nau8825)
+{
+	int i, volume;
+
+	/* Restore register values from backup table; When the driver restores
+	 * the headphone volumem, it needs recover to original level gradually
+	 * with 3dB per step for less pop noise.
+	 */
+	for (i = 0; i < ARRAY_SIZE(nau8825_xtalk_baktab); i++) {
+		if (nau8825_xtalk_baktab[i].reg == NAU8825_REG_HSVOL_CTRL) {
+			/* Ramping up the volume change to reduce pop noise */
+			volume = nau8825_xtalk_baktab[i].def &
+				NAU8825_HPR_VOL_MASK;
+			nau8825_hpvol_ramp(nau8825, 0, volume, 3);
+			continue;
+		}
+		regmap_write(nau8825->regmap, nau8825_xtalk_baktab[i].reg,
+				nau8825_xtalk_baktab[i].def);
+	}
+}
+
+static void nau8825_xtalk_prepare_dac(struct nau8825 *nau8825)
+{
+	/* Enable power of DAC path */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_ENA_CTRL,
+		NAU8825_ENABLE_DACR | NAU8825_ENABLE_DACL |
+		NAU8825_ENABLE_ADC | NAU8825_ENABLE_ADC_CLK |
+		NAU8825_ENABLE_DAC_CLK, NAU8825_ENABLE_DACR |
+		NAU8825_ENABLE_DACL | NAU8825_ENABLE_ADC |
+		NAU8825_ENABLE_ADC_CLK | NAU8825_ENABLE_DAC_CLK);
+	/* Prevent startup click by letting charge pump to ramp up and
+	 * change bump enable
+	 */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_CHARGE_PUMP,
+		NAU8825_JAMNODCLOW | NAU8825_CHANRGE_PUMP_EN,
+		NAU8825_JAMNODCLOW | NAU8825_CHANRGE_PUMP_EN);
+	/* Enable clock sync of DAC and DAC clock */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_RDAC,
+		NAU8825_RDAC_EN | NAU8825_RDAC_CLK_EN |
+		NAU8825_RDAC_FS_BCLK_ENB,
+		NAU8825_RDAC_EN | NAU8825_RDAC_CLK_EN);
+	/* Power up output driver with 2 stage */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_POWER_UP_CONTROL,
+		NAU8825_POWERUP_INTEGR_R | NAU8825_POWERUP_INTEGR_L |
+		NAU8825_POWERUP_DRV_IN_R | NAU8825_POWERUP_DRV_IN_L,
+		NAU8825_POWERUP_INTEGR_R | NAU8825_POWERUP_INTEGR_L |
+		NAU8825_POWERUP_DRV_IN_R | NAU8825_POWERUP_DRV_IN_L);
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_POWER_UP_CONTROL,
+		NAU8825_POWERUP_HP_DRV_R | NAU8825_POWERUP_HP_DRV_L,
+		NAU8825_POWERUP_HP_DRV_R | NAU8825_POWERUP_HP_DRV_L);
+	/* HP outputs not shouted to ground  */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_HSD_CTRL,
+		NAU8825_SPKR_DWN1R | NAU8825_SPKR_DWN1L, 0);
+	/* Enable HP boost driver */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_BOOST,
+		NAU8825_HP_BOOST_DIS, NAU8825_HP_BOOST_DIS);
+	/* Enable class G compare path to supply 1.8V or 0.9V. */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_CLASSG_CTRL,
+		NAU8825_CLASSG_LDAC_EN | NAU8825_CLASSG_RDAC_EN,
+		NAU8825_CLASSG_LDAC_EN | NAU8825_CLASSG_RDAC_EN);
+}
+
+static void nau8825_xtalk_prepare_adc(struct nau8825 *nau8825)
+{
+	/* Power up left ADC and raise 5dB than Vmid for Vref  */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_ANALOG_ADC_2,
+		NAU8825_POWERUP_ADCL | NAU8825_ADC_VREFSEL_MASK,
+		NAU8825_POWERUP_ADCL | NAU8825_ADC_VREFSEL_VMID_PLUS_0_5DB);
+}
+
+static void nau8825_xtalk_clock(struct nau8825 *nau8825)
+{
+	/* Recover FLL default value */
+	regmap_write(nau8825->regmap, NAU8825_REG_FLL1, 0x0);
+	regmap_write(nau8825->regmap, NAU8825_REG_FLL2, 0x3126);
+	regmap_write(nau8825->regmap, NAU8825_REG_FLL3, 0x0008);
+	regmap_write(nau8825->regmap, NAU8825_REG_FLL4, 0x0010);
+	regmap_write(nau8825->regmap, NAU8825_REG_FLL5, 0x0);
+	regmap_write(nau8825->regmap, NAU8825_REG_FLL6, 0x6000);
+	/* Enable internal VCO clock for detection signal generated */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_CLK_DIVIDER,
+		NAU8825_CLK_SRC_MASK, NAU8825_CLK_SRC_VCO);
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL6, NAU8825_DCO_EN,
+		NAU8825_DCO_EN);
+	/* Given specific clock frequency of internal clock to
+	 * generate signal.
+	 */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_CLK_DIVIDER,
+		NAU8825_CLK_MCLK_SRC_MASK, 0xf);
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL1,
+		NAU8825_FLL_RATIO_MASK, 0x10);
+}
+
+static void nau8825_xtalk_prepare(struct nau8825 *nau8825)
+{
+	int volume, index;
+
+	/* Backup those registers changed by cross talk detection */
+	nau8825_xtalk_backup(nau8825);
+	/* Config IIS as master to output signal by codec */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2,
+		NAU8825_I2S_MS_MASK | NAU8825_I2S_DRV_MASK |
+		NAU8825_I2S_BLK_DIV_MASK, NAU8825_I2S_MS_MASTER |
+		(0x2 << NAU8825_I2S_DRV_SFT) | 0x1);
+	/* Ramp up headphone volume to 0dB to get better performance and
+	 * avoid pop noise in headphone.
+	 */
+	index = nau8825_xtalk_baktab_index_by_reg(NAU8825_REG_HSVOL_CTRL);
+	if (index != -EINVAL) {
+		volume = nau8825_xtalk_baktab[index].def &
+				NAU8825_HPR_VOL_MASK;
+		nau8825_hpvol_ramp(nau8825, volume, 0, 3);
+	}
+	nau8825_xtalk_clock(nau8825);
+	nau8825_xtalk_prepare_dac(nau8825);
+	nau8825_xtalk_prepare_adc(nau8825);
+	/* Config channel path and digital gain */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_DACL_CTRL,
+		NAU8825_DACL_CH_SEL_MASK | NAU8825_DACL_CH_VOL_MASK,
+		NAU8825_DACL_CH_SEL_L | 0xab);
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_DACR_CTRL,
+		NAU8825_DACR_CH_SEL_MASK | NAU8825_DACR_CH_VOL_MASK,
+		NAU8825_DACR_CH_SEL_R | 0xab);
+	/* Config cross talk parameters and generate the 23Hz sine wave with
+	 * 1/16 full scale of signal level for impedance measurement.
+	 */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_IMM_MODE_CTRL,
+		NAU8825_IMM_THD_MASK | NAU8825_IMM_GEN_VOL_MASK |
+		NAU8825_IMM_CYC_MASK | NAU8825_IMM_DAC_SRC_MASK,
+		(0x9 << NAU8825_IMM_THD_SFT) | NAU8825_IMM_GEN_VOL_1_16th |
+		NAU8825_IMM_CYC_8192 | NAU8825_IMM_DAC_SRC_SIN);
+	/* RMS intrruption enable */
+	regmap_update_bits(nau8825->regmap,
+		NAU8825_REG_INTERRUPT_MASK, NAU8825_IRQ_RMS_EN, 0);
+	/* Power up left and right DAC */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_CHARGE_PUMP,
+		NAU8825_POWER_DOWN_DACR | NAU8825_POWER_DOWN_DACL, 0);
+}
+
+static void nau8825_xtalk_clean_dac(struct nau8825 *nau8825)
+{
+	/* Disable HP boost driver */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_BOOST,
+		NAU8825_HP_BOOST_DIS, 0);
+	/* HP outputs shouted to ground  */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_HSD_CTRL,
+		NAU8825_SPKR_DWN1R | NAU8825_SPKR_DWN1L,
+		NAU8825_SPKR_DWN1R | NAU8825_SPKR_DWN1L);
+	/* Power down left and right DAC */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_CHARGE_PUMP,
+		NAU8825_POWER_DOWN_DACR | NAU8825_POWER_DOWN_DACL,
+		NAU8825_POWER_DOWN_DACR | NAU8825_POWER_DOWN_DACL);
+	/* Enable the TESTDAC and  disable L/R HP impedance */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_BIAS_ADJ,
+		NAU8825_BIAS_HPR_IMP | NAU8825_BIAS_HPL_IMP |
+		NAU8825_BIAS_TESTDAC_EN, NAU8825_BIAS_TESTDAC_EN);
+	/* Power down output driver with 2 stage */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_POWER_UP_CONTROL,
+		NAU8825_POWERUP_HP_DRV_R | NAU8825_POWERUP_HP_DRV_L, 0);
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_POWER_UP_CONTROL,
+		NAU8825_POWERUP_INTEGR_R | NAU8825_POWERUP_INTEGR_L |
+		NAU8825_POWERUP_DRV_IN_R | NAU8825_POWERUP_DRV_IN_L, 0);
+	/* Disable clock sync of DAC and DAC clock */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_RDAC,
+		NAU8825_RDAC_EN | NAU8825_RDAC_CLK_EN, 0);
+	/* Disable charge pump ramp up function and change bump */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_CHARGE_PUMP,
+		NAU8825_JAMNODCLOW | NAU8825_CHANRGE_PUMP_EN, 0);
+	/* Disable power of DAC path */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_ENA_CTRL,
+		NAU8825_ENABLE_DACR | NAU8825_ENABLE_DACL |
+		NAU8825_ENABLE_ADC_CLK | NAU8825_ENABLE_DAC_CLK, 0);
+	if (!nau8825->irq)
+		regmap_update_bits(nau8825->regmap,
+			NAU8825_REG_ENA_CTRL, NAU8825_ENABLE_ADC, 0);
+}
+
+static void nau8825_xtalk_clean_adc(struct nau8825 *nau8825)
+{
+	/* Power down left ADC and restore voltage to Vmid */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_ANALOG_ADC_2,
+		NAU8825_POWERUP_ADCL | NAU8825_ADC_VREFSEL_MASK, 0);
+}
+
+static void nau8825_xtalk_clean(struct nau8825 *nau8825)
+{
+	/* Enable internal VCO needed for interruptions */
+	nau8825_configure_sysclk(nau8825, NAU8825_CLK_INTERNAL, 0);
+	nau8825_xtalk_clean_dac(nau8825);
+	nau8825_xtalk_clean_adc(nau8825);
+	/* Clear cross talk parameters and disable */
+	regmap_write(nau8825->regmap, NAU8825_REG_IMM_MODE_CTRL, 0);
+	/* RMS intrruption disable */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_INTERRUPT_MASK,
+		NAU8825_IRQ_RMS_EN, NAU8825_IRQ_RMS_EN);
+	/* Recover default value for IIS */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2,
+		NAU8825_I2S_MS_MASK | NAU8825_I2S_DRV_MASK |
+		NAU8825_I2S_BLK_DIV_MASK, NAU8825_I2S_MS_SLAVE);
+	/* Restore value of specific register for cross talk */
+	nau8825_xtalk_restore(nau8825);
+}
+
+static void nau8825_xtalk_imm_start(struct nau8825 *nau8825, int vol)
+{
+	/* Apply ADC volume for better cross talk performance */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_ADC_DGAIN_CTRL,
+				NAU8825_ADC_DIG_VOL_MASK, vol);
+	/* Disables JKTIP(HPL) DAC channel for right to left measurement.
+	 * Do it before sending signal in order to erase pop noise.
+	 */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_BIAS_ADJ,
+		NAU8825_BIAS_TESTDACR_EN | NAU8825_BIAS_TESTDACL_EN,
+		NAU8825_BIAS_TESTDACL_EN);
+	switch (nau8825->xtalk_state) {
+	case NAU8825_XTALK_HPR_R2L:
+		/* Enable right headphone impedance */
+		regmap_update_bits(nau8825->regmap, NAU8825_REG_BIAS_ADJ,
+			NAU8825_BIAS_HPR_IMP | NAU8825_BIAS_HPL_IMP,
+			NAU8825_BIAS_HPR_IMP);
+		break;
+	case NAU8825_XTALK_HPL_R2L:
+		/* Enable left headphone impedance */
+		regmap_update_bits(nau8825->regmap, NAU8825_REG_BIAS_ADJ,
+			NAU8825_BIAS_HPR_IMP | NAU8825_BIAS_HPL_IMP,
+			NAU8825_BIAS_HPL_IMP);
+		break;
+	default:
+		break;
+	}
+	msleep(100);
+	/* Impedance measurement mode enable */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_IMM_MODE_CTRL,
+				NAU8825_IMM_EN, NAU8825_IMM_EN);
+}
+
+static void nau8825_xtalk_imm_stop(struct nau8825 *nau8825)
+{
+	/* Impedance measurement mode disable */
+	regmap_update_bits(nau8825->regmap,
+		NAU8825_REG_IMM_MODE_CTRL, NAU8825_IMM_EN, 0);
+}
+
+/* The cross talk measurement function can reduce cross talk across the
+ * JKTIP(HPL) and JKR1(HPR) outputs which measures the cross talk signal
+ * level to determine what cross talk reduction gain is. This system works by
+ * sending a 23Hz -24dBV sine wave into the headset output DAC and through
+ * the PGA. The output of the PGA is then connected to an internal current
+ * sense which measures the attenuated 23Hz signal and passing the output to
+ * an ADC which converts the measurement to a binary code. With two separated
+ * measurement, one for JKR1(HPR) and the other JKTIP(HPL), measurement data
+ * can be separated read in IMM_RMS_L for HSR and HSL after each measurement.
+ * Thus, the measurement function has four states to complete whole sequence.
+ * 1. Prepare state : Prepare the resource for detection and transfer to HPR
+ *     IMM stat to make JKR1(HPR) impedance measure.
+ * 2. HPR IMM state : Read out orignal signal level of JKR1(HPR) and transfer
+ *     to HPL IMM state to make JKTIP(HPL) impedance measure.
+ * 3. HPL IMM state : Read out cross talk signal level of JKTIP(HPL) and
+ *     transfer to IMM state to determine suppression sidetone gain.
+ * 4. IMM state : Computes cross talk suppression sidetone gain with orignal
+ *     and cross talk signal level. Apply this gain and then restore codec
+ *     configuration. Then transfer to Done state for ending.
+ */
+static void nau8825_xtalk_measure(struct nau8825 *nau8825)
+{
+	u32 sidetone;
+
+	switch (nau8825->xtalk_state) {
+	case NAU8825_XTALK_PREPARE:
+		/* In prepare state, set up clock, intrruption, DAC path, ADC
+		 * path and cross talk detection parameters for preparation.
+		 */
+		nau8825_xtalk_prepare(nau8825);
+		msleep(280);
+		/* Trigger right headphone impedance detection */
+		nau8825->xtalk_state = NAU8825_XTALK_HPR_R2L;
+		nau8825_xtalk_imm_start(nau8825, 0x00d2);
+		break;
+	case NAU8825_XTALK_HPR_R2L:
+		/* In right headphone IMM state, read out right headphone
+		 * impedance measure result, and then start up left side.
+		 */
+		regmap_read(nau8825->regmap, NAU8825_REG_IMM_RMS_L,
+			&nau8825->imp_rms[NAU8825_XTALK_HPR_R2L]);
+		dev_dbg(nau8825->dev, "HPR_R2L imm: %x\n",
+			nau8825->imp_rms[NAU8825_XTALK_HPR_R2L]);
+		/* Disable then re-enable IMM mode to update */
+		nau8825_xtalk_imm_stop(nau8825);
+		/* Trigger left headphone impedance detection */
+		nau8825->xtalk_state = NAU8825_XTALK_HPL_R2L;
+		nau8825_xtalk_imm_start(nau8825, 0x00ff);
+		break;
+	case NAU8825_XTALK_HPL_R2L:
+		/* In left headphone IMM state, read out left headphone
+		 * impedance measure result, and delay some time to wait
+		 * detection sine wave output finish. Then, we can calculate
+		 * the cross talk suppresstion side tone according to the L/R
+		 * headphone imedance.
+		 */
+		regmap_read(nau8825->regmap, NAU8825_REG_IMM_RMS_L,
+			&nau8825->imp_rms[NAU8825_XTALK_HPL_R2L]);
+		dev_dbg(nau8825->dev, "HPL_R2L imm: %x\n",
+			nau8825->imp_rms[NAU8825_XTALK_HPL_R2L]);
+		nau8825_xtalk_imm_stop(nau8825);
+		msleep(150);
+		nau8825->xtalk_state = NAU8825_XTALK_IMM;
+		break;
+	case NAU8825_XTALK_IMM:
+		/* In impedance measure state, the orignal and cross talk
+		 * signal level vlues are ready. The side tone gain is deter-
+		 * mined with these signal level. After all, restore codec
+		 * configuration.
+		 */
+		sidetone = nau8825_xtalk_sidetone(
+			nau8825->imp_rms[NAU8825_XTALK_HPR_R2L],
+			nau8825->imp_rms[NAU8825_XTALK_HPL_R2L]);
+		dev_dbg(nau8825->dev, "cross talk sidetone: %x\n", sidetone);
+		regmap_write(nau8825->regmap, NAU8825_REG_DAC_DGAIN_CTRL,
+					(sidetone << 8) | sidetone);
+		nau8825_xtalk_clean(nau8825);
+		nau8825->xtalk_state = NAU8825_XTALK_DONE;
+		break;
+	default:
+		break;
+	}
+}
+
+static void nau8825_xtalk_work(struct work_struct *work)
+{
+	struct nau8825 *nau8825 = container_of(
+		work, struct nau8825, xtalk_work);
+
+	nau8825_xtalk_measure(nau8825);
+	/* To determine the cross talk side tone gain when reach
+	 * the impedance measure state.
+	 */
+	if (nau8825->xtalk_state == NAU8825_XTALK_IMM)
+		nau8825_xtalk_measure(nau8825);
+
+	/* Delay jack report until cross talk detection process
+	 * completed. It can avoid application to do playback
+	 * preparation before cross talk detection is still working.
+	 * Meanwhile, the protection of the cross talk detection
+	 * is released.
+	 */
+	if (nau8825->xtalk_state == NAU8825_XTALK_DONE) {
+		snd_soc_jack_report(nau8825->jack, nau8825->xtalk_event,
+				nau8825->xtalk_event_mask);
+		nau8825_sema_release(nau8825);
+		nau8825->xtalk_protect = false;
+	}
+}
+
+static void nau8825_xtalk_cancel(struct nau8825 *nau8825)
+{
+	/* If the xtalk_protect is true, that means the process is still
+	 * on going. The driver forces to cancel the cross talk task and
+	 * restores the configuration to original status.
+	 */
+	if (nau8825->xtalk_protect) {
+		cancel_work_sync(&nau8825->xtalk_work);
+		nau8825_xtalk_clean(nau8825);
+	}
+	/* Reset parameters for cross talk suppression function */
+	nau8825_sema_reset(nau8825);
+	nau8825->xtalk_state = NAU8825_XTALK_DONE;
+	nau8825->xtalk_protect = false;
+}
+
 static bool nau8825_readable_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
@@ -217,12 +885,36 @@ static bool nau8825_volatile_reg(struct device *dev, unsigned int reg)
 	case NAU8825_REG_SARDOUT_RAM_STATUS:
 	case NAU8825_REG_CHARGE_PUMP_INPUT_READ:
 	case NAU8825_REG_GENERAL_STATUS:
+	case NAU8825_REG_BIQ_CTRL ... NAU8825_REG_BIQ_COF10:
 		return true;
 	default:
 		return false;
 	}
 }
 
+static int nau8825_adc_event(struct snd_soc_dapm_widget *w,
+		struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
+	struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec);
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		regmap_update_bits(nau8825->regmap, NAU8825_REG_ENA_CTRL,
+			NAU8825_ENABLE_ADC, NAU8825_ENABLE_ADC);
+		break;
+	case SND_SOC_DAPM_POST_PMD:
+		if (!nau8825->irq)
+			regmap_update_bits(nau8825->regmap,
+				NAU8825_REG_ENA_CTRL, NAU8825_ENABLE_ADC, 0);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int nau8825_pump_event(struct snd_soc_dapm_widget *w,
 	struct snd_kcontrol *kcontrol, int event)
 {
@@ -270,6 +962,54 @@ static int nau8825_output_dac_event(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
+static int nau8825_biq_coeff_get(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct soc_bytes_ext *params = (void *)kcontrol->private_value;
+
+	if (!component->regmap)
+		return -EINVAL;
+
+	regmap_raw_read(component->regmap, NAU8825_REG_BIQ_COF1,
+		ucontrol->value.bytes.data, params->max);
+	return 0;
+}
+
+static int nau8825_biq_coeff_put(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct soc_bytes_ext *params = (void *)kcontrol->private_value;
+	void *data;
+
+	if (!component->regmap)
+		return -EINVAL;
+
+	data = kmemdup(ucontrol->value.bytes.data,
+		params->max, GFP_KERNEL | GFP_DMA);
+	if (!data)
+		return -ENOMEM;
+
+	regmap_update_bits(component->regmap, NAU8825_REG_BIQ_CTRL,
+		NAU8825_BIQ_WRT_EN, 0);
+	regmap_raw_write(component->regmap, NAU8825_REG_BIQ_COF1,
+		data, params->max);
+	regmap_update_bits(component->regmap, NAU8825_REG_BIQ_CTRL,
+		NAU8825_BIQ_WRT_EN, NAU8825_BIQ_WRT_EN);
+
+	kfree(data);
+	return 0;
+}
+
+static const char * const nau8825_biq_path[] = {
+	"ADC", "DAC"
+};
+
+static const struct soc_enum nau8825_biq_path_enum =
+	SOC_ENUM_SINGLE(NAU8825_REG_BIQ_CTRL, NAU8825_BIQ_PATH_SFT,
+		ARRAY_SIZE(nau8825_biq_path), nau8825_biq_path);
+
 static const char * const nau8825_adc_decimation[] = {
 	"32", "64", "128", "256"
 };
@@ -306,6 +1046,10 @@ static const struct snd_kcontrol_new nau8825_controls[] = {
 
 	SOC_ENUM("ADC Decimation Rate", nau8825_adc_decimation_enum),
 	SOC_ENUM("DAC Oversampling Rate", nau8825_dac_oversampl_enum),
+	/* programmable biquad filter */
+	SOC_ENUM("BIQ Path Select", nau8825_biq_path_enum),
+	SND_SOC_BYTES_EXT("BIQ Coefficients", 20,
+		  nau8825_biq_coeff_get, nau8825_biq_coeff_put),
 };
 
 /* DAC Mux 0x33[9] and 0x34[9] */
@@ -338,7 +1082,9 @@ static const struct snd_soc_dapm_widget nau8825_dapm_widgets[] = {
 	SND_SOC_DAPM_PGA("Frontend PGA", NAU8825_REG_POWER_UP_CONTROL, 14, 0,
 		NULL, 0),
 
-	SND_SOC_DAPM_ADC("ADC", NULL, NAU8825_REG_ENA_CTRL, 8, 0),
+	SND_SOC_DAPM_ADC_E("ADC", NULL, SND_SOC_NOPM, 0, 0,
+		nau8825_adc_event, SND_SOC_DAPM_POST_PMU |
+		SND_SOC_DAPM_POST_PMD),
 	SND_SOC_DAPM_SUPPLY("ADC Clock", NAU8825_REG_ENA_CTRL, 7, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("ADC Power", NAU8825_REG_ANALOG_ADC_2, 6, 0, NULL,
 		0),
@@ -592,9 +1338,6 @@ int nau8825_enable_jack_detect(struct snd_soc_codec *codec,
 		NAU8825_HSD_AUTO_MODE | NAU8825_SPKR_DWN1R | NAU8825_SPKR_DWN1L,
 		NAU8825_HSD_AUTO_MODE | NAU8825_SPKR_DWN1R | NAU8825_SPKR_DWN1L);
 
-	regmap_update_bits(regmap, NAU8825_REG_INTERRUPT_MASK,
-		NAU8825_IRQ_HEADSET_COMPLETE_EN | NAU8825_IRQ_EJECT_EN, 0);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nau8825_enable_jack_detect);
@@ -602,24 +1345,21 @@ EXPORT_SYMBOL_GPL(nau8825_enable_jack_detect);
 
 static bool nau8825_is_jack_inserted(struct regmap *regmap)
 {
-	int status;
+	bool active_high, is_high;
+	int status, jkdet;
 
+	regmap_read(regmap, NAU8825_REG_JACK_DET_CTRL, &jkdet);
+	active_high = jkdet & NAU8825_JACK_POLARITY;
 	regmap_read(regmap, NAU8825_REG_I2C_DEVICE_ID, &status);
-	return !(status & NAU8825_GPIO2JD1);
+	is_high = status & NAU8825_GPIO2JD1;
+	/* return jack connection status according to jack insertion logic
+	 * active high or active low.
+	 */
+	return active_high == is_high;
 }
 
 static void nau8825_restart_jack_detection(struct regmap *regmap)
 {
-	/* Chip needs one FSCLK cycle in order to generate interrupts,
-	 * as we cannot guarantee one will be provided by the system. Turning
-	 * master mode on then off enables us to generate that FSCLK cycle
-	 * with a minimum of contention on the clock bus.
-	 */
-	regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2,
-		NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_MASTER);
-	regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2,
-		NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_SLAVE);
-
 	/* this will restart the entire jack detection process including MIC/GND
 	 * switching and create interrupts. We have to go from 0 to 1 and back
 	 * to 0 to restart.
@@ -630,11 +1370,30 @@ static void nau8825_restart_jack_detection(struct regmap *regmap)
 		NAU8825_JACK_DET_RESTART, 0);
 }
 
+static void nau8825_int_status_clear_all(struct regmap *regmap)
+{
+	int active_irq, clear_irq, i;
+
+	/* Reset the intrruption status from rightmost bit if the corres-
+	 * ponding irq event occurs.
+	 */
+	regmap_read(regmap, NAU8825_REG_IRQ_STATUS, &active_irq);
+	for (i = 0; i < NAU8825_REG_DATA_LEN; i++) {
+		clear_irq = (0x1 << i);
+		if (active_irq & clear_irq)
+			regmap_write(regmap,
+				NAU8825_REG_INT_CLR_KEY_STATUS, clear_irq);
+	}
+}
+
 static void nau8825_eject_jack(struct nau8825 *nau8825)
 {
 	struct snd_soc_dapm_context *dapm = nau8825->dapm;
 	struct regmap *regmap = nau8825->regmap;
 
+	/* Force to cancel the cross talk detection process */
+	nau8825_xtalk_cancel(nau8825);
+
 	snd_soc_dapm_disable_pin(dapm, "SAR");
 	snd_soc_dapm_disable_pin(dapm, "MICBIAS");
 	/* Detach 2kOhm Resistors from MICBIAS to MICGND1/2 */
@@ -644,6 +1403,69 @@ static void nau8825_eject_jack(struct nau8825 *nau8825)
 	regmap_update_bits(regmap, NAU8825_REG_HSD_CTRL, 0xf, 0xf);
 
 	snd_soc_dapm_sync(dapm);
+
+	/* Clear all interruption status */
+	nau8825_int_status_clear_all(regmap);
+
+	/* Enable the insertion interruption, disable the ejection inter-
+	 * ruption, and then bypass de-bounce circuit.
+	 */
+	regmap_update_bits(regmap, NAU8825_REG_INTERRUPT_DIS_CTRL,
+		NAU8825_IRQ_EJECT_DIS | NAU8825_IRQ_INSERT_DIS,
+		NAU8825_IRQ_EJECT_DIS);
+	regmap_update_bits(regmap, NAU8825_REG_INTERRUPT_MASK,
+		NAU8825_IRQ_OUTPUT_EN | NAU8825_IRQ_EJECT_EN |
+		NAU8825_IRQ_HEADSET_COMPLETE_EN | NAU8825_IRQ_INSERT_EN,
+		NAU8825_IRQ_OUTPUT_EN | NAU8825_IRQ_EJECT_EN |
+		NAU8825_IRQ_HEADSET_COMPLETE_EN);
+	regmap_update_bits(regmap, NAU8825_REG_JACK_DET_CTRL,
+		NAU8825_JACK_DET_DB_BYPASS, NAU8825_JACK_DET_DB_BYPASS);
+
+	/* Disable ADC needed for interruptions at audo mode */
+	regmap_update_bits(regmap, NAU8825_REG_ENA_CTRL,
+		NAU8825_ENABLE_ADC, 0);
+
+	/* Close clock for jack type detection at manual mode */
+	nau8825_configure_sysclk(nau8825, NAU8825_CLK_DIS, 0);
+}
+
+/* Enable audo mode interruptions with internal clock. */
+static void nau8825_setup_auto_irq(struct nau8825 *nau8825)
+{
+	struct regmap *regmap = nau8825->regmap;
+
+	/* Enable headset jack type detection complete interruption and
+	 * jack ejection interruption.
+	 */
+	regmap_update_bits(regmap, NAU8825_REG_INTERRUPT_MASK,
+		NAU8825_IRQ_HEADSET_COMPLETE_EN | NAU8825_IRQ_EJECT_EN, 0);
+
+	/* Enable internal VCO needed for interruptions */
+	nau8825_configure_sysclk(nau8825, NAU8825_CLK_INTERNAL, 0);
+
+	/* Enable ADC needed for interruptions */
+	regmap_update_bits(regmap, NAU8825_REG_ENA_CTRL,
+		NAU8825_ENABLE_ADC, NAU8825_ENABLE_ADC);
+
+	/* Chip needs one FSCLK cycle in order to generate interruptions,
+	 * as we cannot guarantee one will be provided by the system. Turning
+	 * master mode on then off enables us to generate that FSCLK cycle
+	 * with a minimum of contention on the clock bus.
+	 */
+	regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2,
+		NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_MASTER);
+	regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2,
+		NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_SLAVE);
+
+	/* Not bypass de-bounce circuit */
+	regmap_update_bits(regmap, NAU8825_REG_JACK_DET_CTRL,
+		NAU8825_JACK_DET_DB_BYPASS, 0);
+
+	/* Unmask all interruptions */
+	regmap_write(regmap, NAU8825_REG_INTERRUPT_DIS_CTRL, 0);
+
+	/* Restart the jack detection process at auto mode */
+	nau8825_restart_jack_detection(regmap);
 }
 
 static int nau8825_button_decode(int value)
@@ -676,6 +1498,11 @@ static int nau8825_jack_insert(struct nau8825 *nau8825)
 
 	regmap_read(regmap, NAU8825_REG_GENERAL_STATUS, &jack_status_reg);
 	mic_detected = (jack_status_reg >> 10) & 3;
+	/* The JKSLV and JKR2 all detected in high impedance headset */
+	if (mic_detected == 0x3)
+		nau8825->high_imped = true;
+	else
+		nau8825->high_imped = false;
 
 	switch (mic_detected) {
 	case 0:
@@ -773,6 +1600,33 @@ static irqreturn_t nau8825_interrupt(int irq, void *data)
 	} else if (active_irq & NAU8825_HEADSET_COMPLETION_IRQ) {
 		if (nau8825_is_jack_inserted(regmap)) {
 			event |= nau8825_jack_insert(nau8825);
+			if (!nau8825->high_imped) {
+				/* Apply the cross talk suppression in the
+				 * headset without high impedance.
+				 */
+				if (!nau8825->xtalk_protect) {
+					/* Raise protection for cross talk de-
+					 * tection if no protection before.
+					 * The driver has to cancel the pro-
+					 * cess and restore changes if process
+					 * is ongoing when ejection.
+					 */
+					nau8825->xtalk_protect = true;
+					nau8825_sema_acquire(nau8825, 0);
+				}
+				/* Startup cross talk detection process */
+				nau8825->xtalk_state = NAU8825_XTALK_PREPARE;
+				schedule_work(&nau8825->xtalk_work);
+			} else {
+				/* The cross talk suppression shouldn't apply
+				 * in the headset with high impedance. Thus,
+				 * relieve the protection raised before.
+				 */
+				if (nau8825->xtalk_protect) {
+					nau8825_sema_release(nau8825);
+					nau8825->xtalk_protect = false;
+				}
+			}
 		} else {
 			dev_warn(nau8825->dev, "Headset completion IRQ fired but no headset connected\n");
 			nau8825_eject_jack(nau8825);
@@ -780,6 +1634,37 @@ static irqreturn_t nau8825_interrupt(int irq, void *data)
 
 		event_mask |= SND_JACK_HEADSET;
 		clear_irq = NAU8825_HEADSET_COMPLETION_IRQ;
+		/* Record the interruption report event for driver to report
+		 * the event later. The jack report will delay until cross
+		 * talk detection process is done.
+		 */
+		if (nau8825->xtalk_state == NAU8825_XTALK_PREPARE) {
+			nau8825->xtalk_event = event;
+			nau8825->xtalk_event_mask = event_mask;
+		}
+	} else if (active_irq & NAU8825_IMPEDANCE_MEAS_IRQ) {
+		schedule_work(&nau8825->xtalk_work);
+		clear_irq = NAU8825_IMPEDANCE_MEAS_IRQ;
+	} else if ((active_irq & NAU8825_JACK_INSERTION_IRQ_MASK) ==
+		NAU8825_JACK_INSERTION_DETECTED) {
+		/* One more step to check GPIO status directly. Thus, the
+		 * driver can confirm the real insertion interruption because
+		 * the intrruption at manual mode has bypassed debounce
+		 * circuit which can get rid of unstable status.
+		 */
+		if (nau8825_is_jack_inserted(regmap)) {
+			/* Turn off insertion interruption at manual mode */
+			regmap_update_bits(regmap,
+				NAU8825_REG_INTERRUPT_DIS_CTRL,
+				NAU8825_IRQ_INSERT_DIS,
+				NAU8825_IRQ_INSERT_DIS);
+			regmap_update_bits(regmap, NAU8825_REG_INTERRUPT_MASK,
+				NAU8825_IRQ_INSERT_EN, NAU8825_IRQ_INSERT_EN);
+			/* Enable interruption for jack type detection at audo
+			 * mode which can detect microphone and jack type.
+			 */
+			nau8825_setup_auto_irq(nau8825);
+		}
 	}
 
 	if (!clear_irq)
@@ -787,7 +1672,12 @@ static irqreturn_t nau8825_interrupt(int irq, void *data)
 	/* clears the rightmost interruption */
 	regmap_write(regmap, NAU8825_REG_INT_CLR_KEY_STATUS, clear_irq);
 
-	if (event_mask)
+	/* Delay jack report until cross talk detection is done. It can avoid
+	 * application to do playback preparation when cross talk detection
+	 * process is still working. Otherwise, the resource like clock and
+	 * power will be issued by them at the same time and conflict happens.
+	 */
+	if (event_mask && nau8825->xtalk_state == NAU8825_XTALK_DONE)
 		snd_soc_jack_report(nau8825->jack, event, event_mask);
 
 	return IRQ_HANDLED;
@@ -921,11 +1811,16 @@ static void nau8825_init_regs(struct nau8825 *nau8825)
 		NAU8825_RDAC_CLK_DELAY_MASK | NAU8825_RDAC_VREF_MASK,
 		(0x2 << NAU8825_RDAC_CLK_DELAY_SFT) |
 		(0x3 << NAU8825_RDAC_VREF_SFT));
+	/* Config L/R channel */
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_DACL_CTRL,
+		NAU8825_DACL_CH_SEL_MASK, NAU8825_DACL_CH_SEL_L);
+	regmap_update_bits(nau8825->regmap, NAU8825_REG_DACR_CTRL,
+		NAU8825_DACL_CH_SEL_MASK, NAU8825_DACL_CH_SEL_R);
 }
 
 static const struct regmap_config nau8825_regmap_config = {
-	.val_bits = 16,
-	.reg_bits = 16,
+	.val_bits = NAU8825_REG_DATA_LEN,
+	.reg_bits = NAU8825_REG_ADDR_LEN,
 
 	.max_register = NAU8825_REG_MAX,
 	.readable_reg = nau8825_readable_reg,
@@ -944,18 +1839,15 @@ static int nau8825_codec_probe(struct snd_soc_codec *codec)
 
 	nau8825->dapm = dapm;
 
-	/* The interrupt clock is gated by x1[10:8],
-	 * one of them needs to be enabled all the time for
-	 * interrupts to happen.
-	 */
-	snd_soc_dapm_force_enable_pin(dapm, "DDACR");
-	snd_soc_dapm_sync(dapm);
+	return 0;
+}
 
-	/* Unmask interruptions. Handler uses dapm object so we can enable
-	 * interruptions only after dapm is fully initialized.
-	 */
-	regmap_write(nau8825->regmap, NAU8825_REG_INTERRUPT_DIS_CTRL, 0);
-	nau8825_restart_jack_detection(nau8825->regmap);
+static int nau8825_codec_remove(struct snd_soc_codec *codec)
+{
+	struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec);
+
+	/* Cancel and reset cross tak suppresstion detection funciton */
+	nau8825_xtalk_cancel(nau8825);
 
 	return 0;
 }
@@ -973,8 +1865,8 @@ static int nau8825_codec_probe(struct snd_soc_codec *codec)
 static int nau8825_calc_fll_param(unsigned int fll_in, unsigned int fs,
 		struct nau8825_fll *fll_param)
 {
-	u64 fvco;
-	unsigned int fref, i;
+	u64 fvco, fvco_max;
+	unsigned int fref, i, fvco_sel;
 
 	/* Ensure the reference clock frequency (FREF) is <= 13.5MHz by dividing
 	 * freq_in by 1, 2, 4, or 8 using FLL pre-scalar.
@@ -999,18 +1891,23 @@ static int nau8825_calc_fll_param(unsigned int fll_in, unsigned int fs,
 	fll_param->ratio = fll_ratio[i].val;
 
 	/* Calculate the frequency of DCO (FDCO) given freq_out = 256 * Fs.
-	 * FDCO must be within the 90MHz - 100MHz or the FFL cannot be
+	 * FDCO must be within the 90MHz - 124MHz or the FFL cannot be
 	 * guaranteed across the full range of operation.
 	 * FDCO = freq_out * 2 * mclk_src_scaling
 	 */
+	fvco_max = 0;
+	fvco_sel = ARRAY_SIZE(mclk_src_scaling);
 	for (i = 0; i < ARRAY_SIZE(mclk_src_scaling); i++) {
 		fvco = 256 * fs * 2 * mclk_src_scaling[i].param;
-		if (NAU_FVCO_MIN < fvco && fvco < NAU_FVCO_MAX)
-			break;
+		if (fvco > NAU_FVCO_MIN && fvco < NAU_FVCO_MAX &&
+			fvco_max < fvco) {
+			fvco_max = fvco;
+			fvco_sel = i;
+		}
 	}
-	if (i == ARRAY_SIZE(mclk_src_scaling))
+	if (ARRAY_SIZE(mclk_src_scaling) == fvco_sel)
 		return -EINVAL;
-	fll_param->mclk_src = mclk_src_scaling[i].val;
+	fll_param->mclk_src = mclk_src_scaling[fvco_sel].val;
 
 	/* Calculate the FLL 10-bit integer input and the FLL 16-bit fractional
 	 * input based on FDCO, FREF and FLL ratio.
@@ -1025,7 +1922,8 @@ static void nau8825_fll_apply(struct nau8825 *nau8825,
 		struct nau8825_fll *fll_param)
 {
 	regmap_update_bits(nau8825->regmap, NAU8825_REG_CLK_DIVIDER,
-		NAU8825_CLK_MCLK_SRC_MASK, fll_param->mclk_src);
+		NAU8825_CLK_SRC_MASK | NAU8825_CLK_MCLK_SRC_MASK,
+		NAU8825_CLK_SRC_MCLK | fll_param->mclk_src);
 	regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL1,
 			NAU8825_FLL_RATIO_MASK, fll_param->ratio);
 	/* FLL 16-bit fractional input */
@@ -1038,10 +1936,25 @@ static void nau8825_fll_apply(struct nau8825 *nau8825,
 			NAU8825_FLL_REF_DIV_MASK, fll_param->clk_ref_div);
 	/* select divided VCO input */
 	regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL5,
-			NAU8825_FLL_FILTER_SW_MASK, 0x0000);
-	/* FLL sigma delta modulator enable */
-	regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL6,
-			NAU8825_SDM_EN_MASK, NAU8825_SDM_EN);
+		NAU8825_FLL_CLK_SW_MASK, NAU8825_FLL_CLK_SW_REF);
+	/* Disable free-running mode */
+	regmap_update_bits(nau8825->regmap,
+		NAU8825_REG_FLL6, NAU8825_DCO_EN, 0);
+	if (fll_param->fll_frac) {
+		regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL5,
+			NAU8825_FLL_PDB_DAC_EN | NAU8825_FLL_LOOP_FTR_EN |
+			NAU8825_FLL_FTR_SW_MASK,
+			NAU8825_FLL_PDB_DAC_EN | NAU8825_FLL_LOOP_FTR_EN |
+			NAU8825_FLL_FTR_SW_FILTER);
+		regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL6,
+			NAU8825_SDM_EN, NAU8825_SDM_EN);
+	} else {
+		regmap_update_bits(nau8825->regmap, NAU8825_REG_FLL5,
+			NAU8825_FLL_PDB_DAC_EN | NAU8825_FLL_LOOP_FTR_EN |
+			NAU8825_FLL_FTR_SW_MASK, NAU8825_FLL_FTR_SW_ACCU);
+		regmap_update_bits(nau8825->regmap,
+			NAU8825_REG_FLL6, NAU8825_SDM_EN, 0);
+	}
 }
 
 /* freq_out must be 256*Fs in order to achieve the best performance */
@@ -1069,6 +1982,45 @@ static int nau8825_set_pll(struct snd_soc_codec *codec, int pll_id, int source,
 	return 0;
 }
 
+static int nau8825_mclk_prepare(struct nau8825 *nau8825, unsigned int freq)
+{
+	int ret = 0;
+
+	nau8825->mclk = devm_clk_get(nau8825->dev, "mclk");
+	if (IS_ERR(nau8825->mclk)) {
+		dev_info(nau8825->dev, "No 'mclk' clock found, assume MCLK is managed externally");
+		return 0;
+	}
+
+	if (!nau8825->mclk_freq) {
+		ret = clk_prepare_enable(nau8825->mclk);
+		if (ret) {
+			dev_err(nau8825->dev, "Unable to prepare codec mclk\n");
+			return ret;
+		}
+	}
+
+	if (nau8825->mclk_freq != freq) {
+		freq = clk_round_rate(nau8825->mclk, freq);
+		ret = clk_set_rate(nau8825->mclk, freq);
+		if (ret) {
+			dev_err(nau8825->dev, "Unable to set mclk rate\n");
+			return ret;
+		}
+		nau8825->mclk_freq = freq;
+	}
+
+	return 0;
+}
+
+static void nau8825_configure_mclk_as_sysclk(struct regmap *regmap)
+{
+	regmap_update_bits(regmap, NAU8825_REG_CLK_DIVIDER,
+		NAU8825_CLK_SRC_MASK, NAU8825_CLK_SRC_MCLK);
+	regmap_update_bits(regmap, NAU8825_REG_FLL6,
+		NAU8825_DCO_EN, 0);
+}
+
 static int nau8825_configure_sysclk(struct nau8825 *nau8825, int clk_id,
 	unsigned int freq)
 {
@@ -1076,40 +2028,106 @@ static int nau8825_configure_sysclk(struct nau8825 *nau8825, int clk_id,
 	int ret;
 
 	switch (clk_id) {
+	case NAU8825_CLK_DIS:
+		/* Clock provided externally and disable internal VCO clock */
+		nau8825_configure_mclk_as_sysclk(regmap);
+		if (nau8825->mclk_freq) {
+			clk_disable_unprepare(nau8825->mclk);
+			nau8825->mclk_freq = 0;
+		}
+
+		break;
 	case NAU8825_CLK_MCLK:
+		/* Acquire the semaphone to synchronize the playback and
+		 * interrupt handler. In order to avoid the playback inter-
+		 * fered by cross talk process, the driver make the playback
+		 * preparation halted until cross talk process finish.
+		 */
+		nau8825_sema_acquire(nau8825, 2 * HZ);
+		nau8825_configure_mclk_as_sysclk(regmap);
+		/* MCLK not changed by clock tree */
 		regmap_update_bits(regmap, NAU8825_REG_CLK_DIVIDER,
-			NAU8825_CLK_SRC_MASK, NAU8825_CLK_SRC_MCLK);
-		regmap_update_bits(regmap, NAU8825_REG_FLL6, NAU8825_DCO_EN, 0);
+			NAU8825_CLK_MCLK_SRC_MASK, 0);
+		/* Release the semaphone. */
+		nau8825_sema_release(nau8825);
 
-		/* We selected MCLK source but the clock itself managed externally */
-		if (!nau8825->mclk)
-			break;
+		ret = nau8825_mclk_prepare(nau8825, freq);
+		if (ret)
+			return ret;
 
-		if (!nau8825->mclk_freq) {
-			ret = clk_prepare_enable(nau8825->mclk);
-			if (ret) {
-				dev_err(nau8825->dev, "Unable to prepare codec mclk\n");
-				return ret;
-			}
+		break;
+	case NAU8825_CLK_INTERNAL:
+		if (nau8825_is_jack_inserted(nau8825->regmap)) {
+			regmap_update_bits(regmap, NAU8825_REG_FLL6,
+				NAU8825_DCO_EN, NAU8825_DCO_EN);
+			regmap_update_bits(regmap, NAU8825_REG_CLK_DIVIDER,
+				NAU8825_CLK_SRC_MASK, NAU8825_CLK_SRC_VCO);
+			/* Decrease the VCO frequency for power saving */
+			regmap_update_bits(regmap, NAU8825_REG_CLK_DIVIDER,
+				NAU8825_CLK_MCLK_SRC_MASK, 0xf);
+			regmap_update_bits(regmap, NAU8825_REG_FLL1,
+				NAU8825_FLL_RATIO_MASK, 0x10);
+			regmap_update_bits(regmap, NAU8825_REG_FLL6,
+				NAU8825_SDM_EN, NAU8825_SDM_EN);
+		} else {
+			/* The clock turns off intentionally for power saving
+			 * when no headset connected.
+			 */
+			nau8825_configure_mclk_as_sysclk(regmap);
+			dev_warn(nau8825->dev, "Disable clock for power saving when no headset connected\n");
+		}
+		if (nau8825->mclk_freq) {
+			clk_disable_unprepare(nau8825->mclk);
+			nau8825->mclk_freq = 0;
 		}
 
-		if (nau8825->mclk_freq != freq) {
-			nau8825->mclk_freq = freq;
+		break;
+	case NAU8825_CLK_FLL_MCLK:
+		/* Acquire the semaphone to synchronize the playback and
+		 * interrupt handler. In order to avoid the playback inter-
+		 * fered by cross talk process, the driver make the playback
+		 * preparation halted until cross talk process finish.
+		 */
+		nau8825_sema_acquire(nau8825, 2 * HZ);
+		regmap_update_bits(regmap, NAU8825_REG_FLL3,
+			NAU8825_FLL_CLK_SRC_MASK, NAU8825_FLL_CLK_SRC_MCLK);
+		/* Release the semaphone. */
+		nau8825_sema_release(nau8825);
 
-			freq = clk_round_rate(nau8825->mclk, freq);
-			ret = clk_set_rate(nau8825->mclk, freq);
-			if (ret) {
-				dev_err(nau8825->dev, "Unable to set mclk rate\n");
-				return ret;
-			}
+		ret = nau8825_mclk_prepare(nau8825, freq);
+		if (ret)
+			return ret;
+
+		break;
+	case NAU8825_CLK_FLL_BLK:
+		/* Acquire the semaphone to synchronize the playback and
+		 * interrupt handler. In order to avoid the playback inter-
+		 * fered by cross talk process, the driver make the playback
+		 * preparation halted until cross talk process finish.
+		 */
+		nau8825_sema_acquire(nau8825, 2 * HZ);
+		regmap_update_bits(regmap, NAU8825_REG_FLL3,
+			NAU8825_FLL_CLK_SRC_MASK, NAU8825_FLL_CLK_SRC_BLK);
+		/* Release the semaphone. */
+		nau8825_sema_release(nau8825);
+
+		if (nau8825->mclk_freq) {
+			clk_disable_unprepare(nau8825->mclk);
+			nau8825->mclk_freq = 0;
 		}
 
 		break;
-	case NAU8825_CLK_INTERNAL:
-		regmap_update_bits(regmap, NAU8825_REG_FLL6, NAU8825_DCO_EN,
-			NAU8825_DCO_EN);
-		regmap_update_bits(regmap, NAU8825_REG_CLK_DIVIDER,
-			NAU8825_CLK_SRC_MASK, NAU8825_CLK_SRC_VCO);
+	case NAU8825_CLK_FLL_FS:
+		/* Acquire the semaphone to synchronize the playback and
+		 * interrupt handler. In order to avoid the playback inter-
+		 * fered by cross talk process, the driver make the playback
+		 * preparation halted until cross talk process finish.
+		 */
+		nau8825_sema_acquire(nau8825, 2 * HZ);
+		regmap_update_bits(regmap, NAU8825_REG_FLL3,
+			NAU8825_FLL_CLK_SRC_MASK, NAU8825_FLL_CLK_SRC_FS);
+		/* Release the semaphone. */
+		nau8825_sema_release(nau8825);
 
 		if (nau8825->mclk_freq) {
 			clk_disable_unprepare(nau8825->mclk);
@@ -1135,6 +2153,31 @@ static int nau8825_set_sysclk(struct snd_soc_codec *codec, int clk_id,
 	return nau8825_configure_sysclk(nau8825, clk_id, freq);
 }
 
+static int nau8825_resume_setup(struct nau8825 *nau8825)
+{
+	struct regmap *regmap = nau8825->regmap;
+
+	/* Close clock when jack type detection at manual mode */
+	nau8825_configure_sysclk(nau8825, NAU8825_CLK_DIS, 0);
+
+	/* Clear all interruption status */
+	nau8825_int_status_clear_all(regmap);
+
+	/* Enable both insertion and ejection interruptions, and then
+	 * bypass de-bounce circuit.
+	 */
+	regmap_update_bits(regmap, NAU8825_REG_INTERRUPT_MASK,
+		NAU8825_IRQ_OUTPUT_EN | NAU8825_IRQ_HEADSET_COMPLETE_EN |
+		NAU8825_IRQ_EJECT_EN | NAU8825_IRQ_INSERT_EN,
+		NAU8825_IRQ_OUTPUT_EN | NAU8825_IRQ_HEADSET_COMPLETE_EN);
+	regmap_update_bits(regmap, NAU8825_REG_JACK_DET_CTRL,
+		NAU8825_JACK_DET_DB_BYPASS, NAU8825_JACK_DET_DB_BYPASS);
+	regmap_update_bits(regmap, NAU8825_REG_INTERRUPT_DIS_CTRL,
+		NAU8825_IRQ_INSERT_DIS | NAU8825_IRQ_EJECT_DIS, 0);
+
+	return 0;
+}
+
 static int nau8825_set_bias_level(struct snd_soc_codec *codec,
 				   enum snd_soc_bias_level level)
 {
@@ -1157,10 +2200,22 @@ static int nau8825_set_bias_level(struct snd_soc_codec *codec,
 					return ret;
 				}
 			}
+			/* Setup codec configuration after resume */
+			nau8825_resume_setup(nau8825);
 		}
 		break;
 
 	case SND_SOC_BIAS_OFF:
+		/* Cancel and reset cross talk detection funciton */
+		nau8825_xtalk_cancel(nau8825);
+		/* Turn off all interruptions before system shutdown. Keep the
+		 * interruption quiet before resume setup completes.
+		 */
+		regmap_write(nau8825->regmap,
+			NAU8825_REG_INTERRUPT_DIS_CTRL, 0xffff);
+		/* Disable ADC needed for interruptions at audo mode */
+		regmap_update_bits(nau8825->regmap, NAU8825_REG_ENA_CTRL,
+			NAU8825_ENABLE_ADC, 0);
 		if (nau8825->mclk_freq)
 			clk_disable_unprepare(nau8825->mclk);
 		break;
@@ -1168,57 +2223,46 @@ static int nau8825_set_bias_level(struct snd_soc_codec *codec,
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int nau8825_suspend(struct snd_soc_codec *codec)
+static int __maybe_unused nau8825_suspend(struct snd_soc_codec *codec)
 {
 	struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec);
 
 	disable_irq(nau8825->irq);
+	snd_soc_codec_force_bias_level(codec, SND_SOC_BIAS_OFF);
 	regcache_cache_only(nau8825->regmap, true);
 	regcache_mark_dirty(nau8825->regmap);
 
 	return 0;
 }
 
-static int nau8825_resume(struct snd_soc_codec *codec)
+static int __maybe_unused nau8825_resume(struct snd_soc_codec *codec)
 {
 	struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec);
 
-	/* The chip may lose power and reset in S3. regcache_sync restores
-	 * register values including configurations for sysclk, irq, and
-	 * jack/button detection.
-	 */
 	regcache_cache_only(nau8825->regmap, false);
 	regcache_sync(nau8825->regmap);
-
-	/* Check the jack plug status directly. If the headset is unplugged
-	 * during S3 when the chip has no power, there will be no jack
-	 * detection irq even after the nau8825_restart_jack_detection below,
-	 * because the chip just thinks no headset has ever been plugged in.
-	 */
-	if (!nau8825_is_jack_inserted(nau8825->regmap)) {
-		nau8825_eject_jack(nau8825);
-		snd_soc_jack_report(nau8825->jack, 0, SND_JACK_HEADSET);
+	if (nau8825_is_jack_inserted(nau8825->regmap)) {
+		/* If the jack is inserted, we need to check whether the play-
+		 * back is active before suspend. If active, the driver has to
+		 * raise the protection for cross talk function to avoid the
+		 * playback recovers before cross talk process finish. Other-
+		 * wise, the playback will be interfered by cross talk func-
+		 * tion. It is better to apply hardware related parameters
+		 * before starting playback or record.
+		 */
+		if (nau8825_dai_is_active(nau8825)) {
+			nau8825->xtalk_protect = true;
+			nau8825_sema_acquire(nau8825, 0);
+		}
 	}
-
 	enable_irq(nau8825->irq);
 
-	/* Run jack detection to check the type (OMTP or CTIA) of the headset
-	 * if there is one. This handles the case where a different type of
-	 * headset is plugged in during S3. This triggers an IRQ iff a headset
-	 * is already plugged in.
-	 */
-	nau8825_restart_jack_detection(nau8825->regmap);
-
 	return 0;
 }
-#else
-#define nau8825_suspend NULL
-#define nau8825_resume NULL
-#endif
 
 static struct snd_soc_codec_driver nau8825_codec_driver = {
 	.probe = nau8825_codec_probe,
+	.remove = nau8825_codec_remove,
 	.set_sysclk = nau8825_set_sysclk,
 	.set_pll = nau8825_set_pll,
 	.set_bias_level = nau8825_set_bias_level,
@@ -1318,22 +2362,8 @@ static int nau8825_read_device_properties(struct device *dev,
 
 static int nau8825_setup_irq(struct nau8825 *nau8825)
 {
-	struct regmap *regmap = nau8825->regmap;
 	int ret;
 
-	/* IRQ Output Enable */
-	regmap_update_bits(regmap, NAU8825_REG_INTERRUPT_MASK,
-		NAU8825_IRQ_OUTPUT_EN, NAU8825_IRQ_OUTPUT_EN);
-
-	/* Enable internal VCO needed for interruptions */
-	nau8825_configure_sysclk(nau8825, NAU8825_CLK_INTERNAL, 0);
-
-	/* Enable DDACR needed for interrupts
-	 * It is the same as force_enable_pin("DDACR") we do later
-	 */
-	regmap_update_bits(regmap, NAU8825_REG_ENA_CTRL,
-		NAU8825_ENABLE_DACR, NAU8825_ENABLE_DACR);
-
 	ret = devm_request_threaded_irq(nau8825->dev, nau8825->irq, NULL,
 		nau8825_interrupt, IRQF_TRIGGER_LOW | IRQF_ONESHOT,
 		"nau8825", nau8825);
@@ -1370,6 +2400,13 @@ static int nau8825_i2c_probe(struct i2c_client *i2c,
 		return PTR_ERR(nau8825->regmap);
 	nau8825->dev = dev;
 	nau8825->irq = i2c->irq;
+	/* Initiate parameters, semaphone and work queue which are needed in
+	 * cross talk suppression measurment function.
+	 */
+	nau8825->xtalk_state = NAU8825_XTALK_DONE;
+	nau8825->xtalk_protect = false;
+	sema_init(&nau8825->xtalk_sem, 1);
+	INIT_WORK(&nau8825->xtalk_work, nau8825_xtalk_work);
 
 	nau8825_print_device_properties(nau8825);
 
@@ -1405,6 +2442,7 @@ static const struct i2c_device_id nau8825_i2c_ids[] = {
 	{ "nau8825", 0 },
 	{ }
 };
+MODULE_DEVICE_TABLE(i2c, nau8825_i2c_ids);
 
 #ifdef CONFIG_OF
 static const struct of_device_id nau8825_of_ids[] = {
diff --git a/sound/soc/codecs/nau8825.h b/sound/soc/codecs/nau8825.h
index 8ceb5f385478..1c63e2abafa9 100644
--- a/sound/soc/codecs/nau8825.h
+++ b/sound/soc/codecs/nau8825.h
@@ -93,12 +93,21 @@
 #define NAU8825_REG_CHARGE_PUMP_INPUT_READ		0x81
 #define NAU8825_REG_GENERAL_STATUS		0x82
 #define NAU8825_REG_MAX		NAU8825_REG_GENERAL_STATUS
+/* 16-bit control register address, and 16-bits control register data */
+#define NAU8825_REG_ADDR_LEN		16
+#define NAU8825_REG_DATA_LEN		16
 
 /* ENA_CTRL (0x1) */
 #define NAU8825_ENABLE_DACR_SFT	10
 #define NAU8825_ENABLE_DACR	(1 << NAU8825_ENABLE_DACR_SFT)
 #define NAU8825_ENABLE_DACL_SFT	9
+#define NAU8825_ENABLE_DACL		(1 << NAU8825_ENABLE_DACL_SFT)
 #define NAU8825_ENABLE_ADC_SFT	8
+#define NAU8825_ENABLE_ADC		(1 << NAU8825_ENABLE_ADC_SFT)
+#define NAU8825_ENABLE_ADC_CLK_SFT	7
+#define NAU8825_ENABLE_ADC_CLK	(1 << NAU8825_ENABLE_ADC_CLK_SFT)
+#define NAU8825_ENABLE_DAC_CLK_SFT	6
+#define NAU8825_ENABLE_DAC_CLK	(1 << NAU8825_ENABLE_DAC_CLK_SFT)
 #define NAU8825_ENABLE_SAR_SFT	1
 
 /* CLK_DIVIDER (0x3) */
@@ -113,20 +122,28 @@
 
 /* FLL3 (0x06) */
 #define NAU8825_FLL_INTEGER_MASK		(0x3ff << 0)
+#define NAU8825_FLL_CLK_SRC_SFT		10
+#define NAU8825_FLL_CLK_SRC_MASK		(0x3 << NAU8825_FLL_CLK_SRC_SFT)
+#define NAU8825_FLL_CLK_SRC_MCLK		(0 << NAU8825_FLL_CLK_SRC_SFT)
+#define NAU8825_FLL_CLK_SRC_BLK		(0x2 << NAU8825_FLL_CLK_SRC_SFT)
+#define NAU8825_FLL_CLK_SRC_FS			(0x3 << NAU8825_FLL_CLK_SRC_SFT)
 
 /* FLL4 (0x07) */
 #define NAU8825_FLL_REF_DIV_MASK		(0x3 << 10)
 
 /* FLL5 (0x08) */
-#define NAU8825_FLL_FILTER_SW_MASK		(0x1 << 14)
+#define NAU8825_FLL_PDB_DAC_EN		(0x1 << 15)
+#define NAU8825_FLL_LOOP_FTR_EN		(0x1 << 14)
+#define NAU8825_FLL_CLK_SW_MASK		(0x1 << 13)
+#define NAU8825_FLL_CLK_SW_N2			(0x1 << 13)
+#define NAU8825_FLL_CLK_SW_REF		(0x0 << 13)
+#define NAU8825_FLL_FTR_SW_MASK		(0x1 << 12)
+#define NAU8825_FLL_FTR_SW_ACCU		(0x1 << 12)
+#define NAU8825_FLL_FTR_SW_FILTER		(0x0 << 12)
 
 /* FLL6 (0x9) */
-#define NAU8825_DCO_EN_MASK			(0x1 << 15)
 #define NAU8825_DCO_EN				(0x1 << 15)
-#define NAU8825_DCO_DIS				(0x0 << 15)
-#define NAU8825_SDM_EN_MASK			(0x1 << 14)
 #define NAU8825_SDM_EN				(0x1 << 14)
-#define NAU8825_SDM_DIS				(0x0 << 14)
 
 /* HSD_CTRL (0xc) */
 #define NAU8825_HSD_AUTO_MODE	(1 << 6)
@@ -136,6 +153,7 @@
 
 /* JACK_DET_CTRL (0xd) */
 #define NAU8825_JACK_DET_RESTART	(1 << 9)
+#define NAU8825_JACK_DET_DB_BYPASS	(1 << 8)
 #define NAU8825_JACK_INSERT_DEBOUNCE_SFT	5
 #define NAU8825_JACK_INSERT_DEBOUNCE_MASK	(0x7 << NAU8825_JACK_INSERT_DEBOUNCE_SFT)
 #define NAU8825_JACK_EJECT_DEBOUNCE_SFT		2
@@ -145,9 +163,11 @@
 /* INTERRUPT_MASK (0xf) */
 #define NAU8825_IRQ_OUTPUT_EN (1 << 11)
 #define NAU8825_IRQ_HEADSET_COMPLETE_EN (1 << 10)
+#define NAU8825_IRQ_RMS_EN (1 << 8)
 #define NAU8825_IRQ_KEY_RELEASE_EN (1 << 7)
 #define NAU8825_IRQ_KEY_SHORT_PRESS_EN (1 << 5)
 #define NAU8825_IRQ_EJECT_EN (1 << 2)
+#define NAU8825_IRQ_INSERT_EN (1 << 0)
 
 /* IRQ_STATUS (0x10) */
 #define NAU8825_HEADSET_COMPLETION_IRQ	(1 << 10)
@@ -168,6 +188,7 @@
 #define NAU8825_IRQ_KEY_RELEASE_DIS (1 << 7)
 #define NAU8825_IRQ_KEY_SHORT_PRESS_DIS (1 << 5)
 #define NAU8825_IRQ_EJECT_DIS (1 << 2)
+#define NAU8825_IRQ_INSERT_DIS (1 << 0)
 
 /* SAR_CTRL (0x13) */
 #define NAU8825_SAR_ADC_EN_SFT	12
@@ -217,10 +238,21 @@
 
 /* I2S_PCM_CTRL2 (0x1d) */
 #define NAU8825_I2S_TRISTATE	(1 << 15) /* 0 - normal mode, 1 - Hi-Z output */
+#define NAU8825_I2S_DRV_SFT	12
+#define NAU8825_I2S_DRV_MASK	(0x3 << NAU8825_I2S_DRV_SFT)
 #define NAU8825_I2S_MS_SFT	3
 #define NAU8825_I2S_MS_MASK	(1 << NAU8825_I2S_MS_SFT)
 #define NAU8825_I2S_MS_MASTER	(1 << NAU8825_I2S_MS_SFT)
 #define NAU8825_I2S_MS_SLAVE	(0 << NAU8825_I2S_MS_SFT)
+#define NAU8825_I2S_BLK_DIV_MASK	0x7
+
+/* BIQ_CTRL (0x20) */
+#define NAU8825_BIQ_WRT_SFT   4
+#define NAU8825_BIQ_WRT_EN     (1 << NAU8825_BIQ_WRT_SFT)
+#define NAU8825_BIQ_PATH_SFT   0
+#define NAU8825_BIQ_PATH_MASK  (1 << NAU8825_BIQ_PATH_SFT)
+#define NAU8825_BIQ_PATH_ADC   (0 << NAU8825_BIQ_PATH_SFT)
+#define NAU8825_BIQ_PATH_DAC   (1 << NAU8825_BIQ_PATH_SFT)
 
 /* ADC_RATE (0x2b) */
 #define NAU8825_ADC_SYNC_DOWN_SFT	0
@@ -239,22 +271,72 @@
 #define NAU8825_DAC_OVERSAMPLE_128	2
 #define NAU8825_DAC_OVERSAMPLE_32	4
 
+/* ADC_DGAIN_CTRL (0x30) */
+#define NAU8825_ADC_DIG_VOL_MASK	0xff
+
 /* MUTE_CTRL (0x31) */
 #define NAU8825_DAC_ZERO_CROSSING_EN	(1 << 9)
 #define NAU8825_DAC_SOFT_MUTE	(1 << 9)
 
 /* HSVOL_CTRL (0x32) */
 #define NAU8825_HP_MUTE	(1 << 15)
+#define NAU8825_HP_MUTE_AUTO	(1 << 14)
+#define NAU8825_HPL_MUTE	(1 << 13)
+#define NAU8825_HPR_MUTE	(1 << 12)
+#define NAU8825_HPL_VOL_SFT	6
+#define NAU8825_HPL_VOL_MASK	(0x3f << NAU8825_HPL_VOL_SFT)
+#define NAU8825_HPR_VOL_SFT	0
+#define NAU8825_HPR_VOL_MASK	(0x3f << NAU8825_HPR_VOL_SFT)
+#define NAU8825_HP_VOL_MIN	0x36
 
 /* DACL_CTRL (0x33) */
 #define NAU8825_DACL_CH_SEL_SFT	9
+#define NAU8825_DACL_CH_SEL_MASK (0x1 << NAU8825_DACL_CH_SEL_SFT)
+#define NAU8825_DACL_CH_SEL_L    (0x0 << NAU8825_DACL_CH_SEL_SFT)
+#define NAU8825_DACL_CH_SEL_R    (0x1 << NAU8825_DACL_CH_SEL_SFT)
+#define NAU8825_DACL_CH_VOL_MASK	0xff
 
 /* DACR_CTRL (0x34) */
 #define NAU8825_DACR_CH_SEL_SFT	9
+#define NAU8825_DACR_CH_SEL_MASK (0x1 << NAU8825_DACR_CH_SEL_SFT)
+#define NAU8825_DACR_CH_SEL_L    (0x0 << NAU8825_DACR_CH_SEL_SFT)
+#define NAU8825_DACR_CH_SEL_R    (0x1 << NAU8825_DACR_CH_SEL_SFT)
+#define NAU8825_DACR_CH_VOL_MASK	0xff
+
+/* IMM_MODE_CTRL (0x4C) */
+#define NAU8825_IMM_THD_SFT		8
+#define NAU8825_IMM_THD_MASK		(0x3f << NAU8825_IMM_THD_SFT)
+#define NAU8825_IMM_GEN_VOL_SFT	6
+#define NAU8825_IMM_GEN_VOL_MASK	(0x3 << NAU8825_IMM_GEN_VOL_SFT)
+#define NAU8825_IMM_GEN_VOL_1_2nd	(0x0 << NAU8825_IMM_GEN_VOL_SFT)
+#define NAU8825_IMM_GEN_VOL_1_4th	(0x1 << NAU8825_IMM_GEN_VOL_SFT)
+#define NAU8825_IMM_GEN_VOL_1_8th	(0x2 << NAU8825_IMM_GEN_VOL_SFT)
+#define NAU8825_IMM_GEN_VOL_1_16th	(0x3 << NAU8825_IMM_GEN_VOL_SFT)
+
+#define NAU8825_IMM_CYC_SFT		4
+#define NAU8825_IMM_CYC_MASK		(0x3 << NAU8825_IMM_CYC_SFT)
+#define NAU8825_IMM_CYC_1024		(0x0 << NAU8825_IMM_CYC_SFT)
+#define NAU8825_IMM_CYC_2048		(0x1 << NAU8825_IMM_CYC_SFT)
+#define NAU8825_IMM_CYC_4096		(0x2 << NAU8825_IMM_CYC_SFT)
+#define NAU8825_IMM_CYC_8192		(0x3 << NAU8825_IMM_CYC_SFT)
+#define NAU8825_IMM_EN			(1 << 3)
+#define NAU8825_IMM_DAC_SRC_MASK	0x7
+#define NAU8825_IMM_DAC_SRC_BIQ	0x0
+#define NAU8825_IMM_DAC_SRC_DRC	0x1
+#define NAU8825_IMM_DAC_SRC_MIX	0x2
+#define NAU8825_IMM_DAC_SRC_SIN	0x3
 
 /* CLASSG_CTRL (0x50) */
 #define NAU8825_CLASSG_TIMER_SFT	8
 #define NAU8825_CLASSG_TIMER_MASK	(0x3f << NAU8825_CLASSG_TIMER_SFT)
+#define NAU8825_CLASSG_TIMER_1ms	(0x1 << NAU8825_CLASSG_TIMER_SFT)
+#define NAU8825_CLASSG_TIMER_2ms	(0x2 << NAU8825_CLASSG_TIMER_SFT)
+#define NAU8825_CLASSG_TIMER_8ms	(0x4 << NAU8825_CLASSG_TIMER_SFT)
+#define NAU8825_CLASSG_TIMER_16ms	(0x8 << NAU8825_CLASSG_TIMER_SFT)
+#define NAU8825_CLASSG_TIMER_32ms	(0x10 << NAU8825_CLASSG_TIMER_SFT)
+#define NAU8825_CLASSG_TIMER_64ms	(0x20 << NAU8825_CLASSG_TIMER_SFT)
+#define NAU8825_CLASSG_LDAC_EN		(0x1 << 2)
+#define NAU8825_CLASSG_RDAC_EN		(0x1 << 1)
 #define NAU8825_CLASSG_EN		(1 << 0)
 
 /* I2C_DEVICE_ID (0x58) */
@@ -263,7 +345,12 @@
 #define NAU8825_SOFTWARE_ID_NAU8825	0x0
 
 /* BIAS_ADJ (0x66) */
-#define NAU8825_BIAS_TESTDAC_EN	(0x3 << 8)
+#define NAU8825_BIAS_HPR_IMP		(1 << 15)
+#define NAU8825_BIAS_HPL_IMP		(1 << 14)
+#define NAU8825_BIAS_TESTDAC_SFT	8
+#define NAU8825_BIAS_TESTDAC_EN	(0x3 << NAU8825_BIAS_TESTDAC_SFT)
+#define NAU8825_BIAS_TESTDACR_EN	(0x2 << NAU8825_BIAS_TESTDAC_SFT)
+#define NAU8825_BIAS_TESTDACL_EN	(0x1 << NAU8825_BIAS_TESTDAC_SFT)
 #define NAU8825_BIAS_VMID	(1 << 6)
 #define NAU8825_BIAS_VMID_SEL_SFT	4
 #define NAU8825_BIAS_VMID_SEL_MASK	(3 << NAU8825_BIAS_VMID_SEL_SFT)
@@ -282,6 +369,11 @@
 #define NAU8825_POWERUP_ADCL	(1 << 6)
 
 /* RDAC (0x73) */
+#define NAU8825_RDAC_FS_BCLK_ENB	(1 << 15)
+#define NAU8825_RDAC_EN_SFT		12
+#define NAU8825_RDAC_EN		(0x3 << NAU8825_RDAC_EN_SFT)
+#define NAU8825_RDAC_CLK_EN_SFT	8
+#define NAU8825_RDAC_CLK_EN		(0x3 << NAU8825_RDAC_CLK_EN_SFT)
 #define NAU8825_RDAC_CLK_DELAY_SFT	4
 #define NAU8825_RDAC_CLK_DELAY_MASK	(0x7 << NAU8825_RDAC_CLK_DELAY_SFT)
 #define NAU8825_RDAC_VREF_SFT	2
@@ -318,8 +410,21 @@
 
 /* System Clock Source */
 enum {
-	NAU8825_CLK_MCLK = 0,
+	NAU8825_CLK_DIS = 0,
+	NAU8825_CLK_MCLK,
 	NAU8825_CLK_INTERNAL,
+	NAU8825_CLK_FLL_MCLK,
+	NAU8825_CLK_FLL_BLK,
+	NAU8825_CLK_FLL_FS,
+};
+
+/* Cross talk detection state */
+enum {
+	NAU8825_XTALK_PREPARE = 0,
+	NAU8825_XTALK_HPR_R2L,
+	NAU8825_XTALK_HPL_R2L,
+	NAU8825_XTALK_IMM,
+	NAU8825_XTALK_DONE,
 };
 
 struct nau8825 {
@@ -328,6 +433,8 @@ struct nau8825 {
 	struct snd_soc_dapm_context *dapm;
 	struct snd_soc_jack *jack;
 	struct clk *mclk;
+	struct work_struct xtalk_work;
+	struct semaphore xtalk_sem;
 	int irq;
 	int mclk_freq; /* 0 - mclk is disabled */
 	int button_pressed;
@@ -346,6 +453,12 @@ struct nau8825 {
 	int key_debounce;
 	int jack_insert_debounce;
 	int jack_eject_debounce;
+	int high_imped;
+	int xtalk_state;
+	int xtalk_event;
+	int xtalk_event_mask;
+	bool xtalk_protect;
+	int imp_rms[NAU8825_XTALK_IMM];
 };
 
 int nau8825_enable_jack_detect(struct snd_soc_codec *codec,
diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c
index 58325234285c..33e1fc2d1598 100644
--- a/sound/soc/codecs/pcm1681.c
+++ b/sound/soc/codecs/pcm1681.c
@@ -73,7 +73,7 @@ static bool pcm1681_accessible_reg(struct device *dev, unsigned int reg)
 	return !((reg == 0x00) || (reg == 0x0f));
 }
 
-static bool pcm1681_writeable_reg(struct device *dev, unsigned register reg)
+static bool pcm1681_writeable_reg(struct device *dev, unsigned int reg)
 {
 	return pcm1681_accessible_reg(dev, reg) &&
 		(reg != PCM1681_ZERO_DETECT_STATUS);
diff --git a/sound/soc/codecs/pcm179x.c b/sound/soc/codecs/pcm179x.c
index 06a66579ca6d..88fbdd184aa0 100644
--- a/sound/soc/codecs/pcm179x.c
+++ b/sound/soc/codecs/pcm179x.c
@@ -59,7 +59,7 @@ static bool pcm179x_accessible_reg(struct device *dev, unsigned int reg)
 	return reg >= 0x10 && reg <= 0x17;
 }
 
-static bool pcm179x_writeable_reg(struct device *dev, unsigned register reg)
+static bool pcm179x_writeable_reg(struct device *dev, unsigned int reg)
 {
 	bool accessible;
 
diff --git a/sound/soc/codecs/pcm5102a.c b/sound/soc/codecs/pcm5102a.c
index ed515677409b..8ba322a00363 100644
--- a/sound/soc/codecs/pcm5102a.c
+++ b/sound/soc/codecs/pcm5102a.c
@@ -57,7 +57,6 @@ static struct platform_driver pcm5102a_codec_driver = {
 	.remove		= pcm5102a_remove,
 	.driver		= {
 		.name	= "pcm5102a-codec",
-		.owner	= THIS_MODULE,
 		.of_match_table = pcm5102a_of_match,
 	},
 };
diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c
index 1bd31644a782..74c0e4eb3788 100644
--- a/sound/soc/codecs/rt286.c
+++ b/sound/soc/codecs/rt286.c
@@ -1100,6 +1100,13 @@ static const struct dmi_system_id force_combo_jack_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Skylake Client platform")
 		}
 	},
+	{
+		.ident = "Intel Kabylake RVP",
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "Kabylake Client platform")
+		}
+	},
+
 	{ }
 };
 
diff --git a/sound/soc/codecs/rt5514-spi.c b/sound/soc/codecs/rt5514-spi.c
new file mode 100644
index 000000000000..77ff8ebe6dfb
--- /dev/null
+++ b/sound/soc/codecs/rt5514-spi.c
@@ -0,0 +1,447 @@
+/*
+ * rt5514-spi.c  --  RT5514 SPI driver
+ *
+ * Copyright 2015 Realtek Semiconductor Corp.
+ * Author: Oder Chiou <oder_chiou@realtek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/input.h>
+#include <linux/spi/spi.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/gpio.h>
+#include <linux/sched.h>
+#include <linux/kthread.h>
+#include <linux/uaccess.h>
+#include <linux/miscdevice.h>
+#include <linux/regulator/consumer.h>
+#include <linux/pm_qos.h>
+#include <linux/sysfs.h>
+#include <linux/clk.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/initval.h>
+#include <sound/tlv.h>
+
+#include "rt5514-spi.h"
+
+static struct spi_device *rt5514_spi;
+
+struct rt5514_dsp {
+	struct device *dev;
+	struct delayed_work copy_work;
+	struct mutex dma_lock;
+	struct snd_pcm_substream *substream;
+	unsigned int buf_base, buf_limit, buf_rp;
+	size_t buf_size;
+	size_t dma_offset;
+	size_t dsp_offset;
+};
+
+static const struct snd_pcm_hardware rt5514_spi_pcm_hardware = {
+	.info			= SNDRV_PCM_INFO_MMAP |
+				  SNDRV_PCM_INFO_MMAP_VALID |
+				  SNDRV_PCM_INFO_INTERLEAVED,
+	.formats		= SNDRV_PCM_FMTBIT_S16_LE,
+	.period_bytes_min	= PAGE_SIZE,
+	.period_bytes_max	= 0x20000 / 8,
+	.periods_min		= 8,
+	.periods_max		= 8,
+	.channels_min		= 1,
+	.channels_max		= 1,
+	.buffer_bytes_max	= 0x20000,
+};
+
+static struct snd_soc_dai_driver rt5514_spi_dai = {
+	.name = "rt5514-dsp-cpu-dai",
+	.id = 0,
+	.capture = {
+		.stream_name = "DSP Capture",
+		.channels_min = 1,
+		.channels_max = 1,
+		.rates = SNDRV_PCM_RATE_16000,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE,
+	},
+};
+
+static void rt5514_spi_copy_work(struct work_struct *work)
+{
+	struct rt5514_dsp *rt5514_dsp =
+		container_of(work, struct rt5514_dsp, copy_work.work);
+	struct snd_pcm_runtime *runtime;
+	size_t period_bytes, truncated_bytes = 0;
+
+	mutex_lock(&rt5514_dsp->dma_lock);
+	if (!rt5514_dsp->substream) {
+		dev_err(rt5514_dsp->dev, "No pcm substream\n");
+		goto done;
+	}
+
+	runtime = rt5514_dsp->substream->runtime;
+	period_bytes = snd_pcm_lib_period_bytes(rt5514_dsp->substream);
+
+	if (rt5514_dsp->buf_size - rt5514_dsp->dsp_offset <  period_bytes)
+		period_bytes = rt5514_dsp->buf_size - rt5514_dsp->dsp_offset;
+
+	if (rt5514_dsp->buf_rp + period_bytes <= rt5514_dsp->buf_limit) {
+		rt5514_spi_burst_read(rt5514_dsp->buf_rp,
+			runtime->dma_area + rt5514_dsp->dma_offset,
+			period_bytes);
+
+		if (rt5514_dsp->buf_rp + period_bytes == rt5514_dsp->buf_limit)
+			rt5514_dsp->buf_rp = rt5514_dsp->buf_base;
+		else
+			rt5514_dsp->buf_rp += period_bytes;
+	} else {
+		truncated_bytes = rt5514_dsp->buf_limit - rt5514_dsp->buf_rp;
+		rt5514_spi_burst_read(rt5514_dsp->buf_rp,
+			runtime->dma_area + rt5514_dsp->dma_offset,
+			truncated_bytes);
+
+		rt5514_spi_burst_read(rt5514_dsp->buf_base,
+			runtime->dma_area + rt5514_dsp->dma_offset +
+			truncated_bytes, period_bytes - truncated_bytes);
+
+			rt5514_dsp->buf_rp = rt5514_dsp->buf_base +
+				period_bytes - truncated_bytes;
+	}
+
+	rt5514_dsp->dma_offset += period_bytes;
+	if (rt5514_dsp->dma_offset >= runtime->dma_bytes)
+		rt5514_dsp->dma_offset = 0;
+
+	rt5514_dsp->dsp_offset += period_bytes;
+
+	snd_pcm_period_elapsed(rt5514_dsp->substream);
+
+	if (rt5514_dsp->dsp_offset < rt5514_dsp->buf_size)
+		schedule_delayed_work(&rt5514_dsp->copy_work, 5);
+done:
+	mutex_unlock(&rt5514_dsp->dma_lock);
+}
+
+/* PCM for streaming audio from the DSP buffer */
+static int rt5514_spi_pcm_open(struct snd_pcm_substream *substream)
+{
+	snd_soc_set_runtime_hwparams(substream, &rt5514_spi_pcm_hardware);
+
+	return 0;
+}
+
+static int rt5514_spi_hw_params(struct snd_pcm_substream *substream,
+			       struct snd_pcm_hw_params *hw_params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct rt5514_dsp *rt5514_dsp =
+			snd_soc_platform_get_drvdata(rtd->platform);
+	int ret;
+
+	mutex_lock(&rt5514_dsp->dma_lock);
+	ret = snd_pcm_lib_alloc_vmalloc_buffer(substream,
+			params_buffer_bytes(hw_params));
+	rt5514_dsp->substream = substream;
+	mutex_unlock(&rt5514_dsp->dma_lock);
+
+	return ret;
+}
+
+static int rt5514_spi_hw_free(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct rt5514_dsp *rt5514_dsp =
+			snd_soc_platform_get_drvdata(rtd->platform);
+
+	mutex_lock(&rt5514_dsp->dma_lock);
+	rt5514_dsp->substream = NULL;
+	mutex_unlock(&rt5514_dsp->dma_lock);
+
+	cancel_delayed_work_sync(&rt5514_dsp->copy_work);
+
+	return snd_pcm_lib_free_vmalloc_buffer(substream);
+}
+
+static int rt5514_spi_prepare(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct rt5514_dsp *rt5514_dsp =
+			snd_soc_platform_get_drvdata(rtd->platform);
+	u8 buf[8];
+
+	rt5514_dsp->dma_offset = 0;
+	rt5514_dsp->dsp_offset = 0;
+
+	/**
+	 * The address area x1800XXXX is the register address, and it cannot
+	 * support spi burst read perfectly. So we use the spi burst read
+	 * individually to make sure the data correctly.
+	*/
+	rt5514_spi_burst_read(RT5514_BUFFER_VOICE_BASE, (u8 *)&buf,
+		sizeof(buf));
+	rt5514_dsp->buf_base = buf[0] | buf[1] << 8 | buf[2] << 16 |
+				buf[3] << 24;
+
+	rt5514_spi_burst_read(RT5514_BUFFER_VOICE_LIMIT, (u8 *)&buf,
+		sizeof(buf));
+	rt5514_dsp->buf_limit = buf[0] | buf[1] << 8 | buf[2] << 16 |
+				buf[3] << 24;
+
+	rt5514_spi_burst_read(RT5514_BUFFER_VOICE_RP, (u8 *)&buf,
+		sizeof(buf));
+	rt5514_dsp->buf_rp = buf[0] | buf[1] << 8 | buf[2] << 16 |
+				buf[3] << 24;
+
+	rt5514_spi_burst_read(RT5514_BUFFER_VOICE_SIZE, (u8 *)&buf,
+		sizeof(buf));
+	rt5514_dsp->buf_size = buf[0] | buf[1] << 8 | buf[2] << 16 |
+				buf[3] << 24;
+
+	return 0;
+}
+
+static int rt5514_spi_trigger(struct snd_pcm_substream *substream, int cmd)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct rt5514_dsp *rt5514_dsp =
+			snd_soc_platform_get_drvdata(rtd->platform);
+
+	if (cmd == SNDRV_PCM_TRIGGER_START) {
+		if (rt5514_dsp->buf_base && rt5514_dsp->buf_limit &&
+			rt5514_dsp->buf_rp && rt5514_dsp->buf_size)
+			schedule_delayed_work(&rt5514_dsp->copy_work, 0);
+	}
+
+	return 0;
+}
+
+static snd_pcm_uframes_t rt5514_spi_pcm_pointer(
+		struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct rt5514_dsp *rt5514_dsp =
+		snd_soc_platform_get_drvdata(rtd->platform);
+
+	return bytes_to_frames(runtime, rt5514_dsp->dma_offset);
+}
+
+static struct snd_pcm_ops rt5514_spi_pcm_ops = {
+	.open		= rt5514_spi_pcm_open,
+	.hw_params	= rt5514_spi_hw_params,
+	.hw_free	= rt5514_spi_hw_free,
+	.trigger	= rt5514_spi_trigger,
+	.prepare	= rt5514_spi_prepare,
+	.pointer	= rt5514_spi_pcm_pointer,
+	.mmap		= snd_pcm_lib_mmap_vmalloc,
+	.page		= snd_pcm_lib_get_vmalloc_page,
+};
+
+static int rt5514_spi_pcm_probe(struct snd_soc_platform *platform)
+{
+	struct rt5514_dsp *rt5514_dsp;
+
+	rt5514_dsp = devm_kzalloc(platform->dev, sizeof(*rt5514_dsp),
+			GFP_KERNEL);
+
+	rt5514_dsp->dev = &rt5514_spi->dev;
+	mutex_init(&rt5514_dsp->dma_lock);
+	INIT_DELAYED_WORK(&rt5514_dsp->copy_work, rt5514_spi_copy_work);
+	snd_soc_platform_set_drvdata(platform, rt5514_dsp);
+
+	return 0;
+}
+
+static struct snd_soc_platform_driver rt5514_spi_platform = {
+	.probe = rt5514_spi_pcm_probe,
+	.ops = &rt5514_spi_pcm_ops,
+};
+
+static const struct snd_soc_component_driver rt5514_spi_dai_component = {
+	.name		= "rt5514-spi-dai",
+};
+
+/**
+ * rt5514_spi_burst_read - Read data from SPI by rt5514 address.
+ * @addr: Start address.
+ * @rxbuf: Data Buffer for reading.
+ * @len: Data length, it must be a multiple of 8.
+ *
+ *
+ * Returns true for success.
+ */
+int rt5514_spi_burst_read(unsigned int addr, u8 *rxbuf, size_t len)
+{
+	u8 spi_cmd = RT5514_SPI_CMD_BURST_READ;
+	int status;
+	u8 write_buf[8];
+	unsigned int i, end, offset = 0;
+
+	struct spi_message message;
+	struct spi_transfer x[3];
+
+	while (offset < len) {
+		if (offset + RT5514_SPI_BUF_LEN <= len)
+			end = RT5514_SPI_BUF_LEN;
+		else
+			end = len % RT5514_SPI_BUF_LEN;
+
+		write_buf[0] = spi_cmd;
+		write_buf[1] = ((addr + offset) & 0xff000000) >> 24;
+		write_buf[2] = ((addr + offset) & 0x00ff0000) >> 16;
+		write_buf[3] = ((addr + offset) & 0x0000ff00) >> 8;
+		write_buf[4] = ((addr + offset) & 0x000000ff) >> 0;
+
+		spi_message_init(&message);
+		memset(x, 0, sizeof(x));
+
+		x[0].len = 5;
+		x[0].tx_buf = write_buf;
+		spi_message_add_tail(&x[0], &message);
+
+		x[1].len = 4;
+		x[1].tx_buf = write_buf;
+		spi_message_add_tail(&x[1], &message);
+
+		x[2].len = end;
+		x[2].rx_buf = rxbuf + offset;
+		spi_message_add_tail(&x[2], &message);
+
+		status = spi_sync(rt5514_spi, &message);
+
+		if (status)
+			return false;
+
+		offset += RT5514_SPI_BUF_LEN;
+	}
+
+	for (i = 0; i < len; i += 8) {
+		write_buf[0] = rxbuf[i + 0];
+		write_buf[1] = rxbuf[i + 1];
+		write_buf[2] = rxbuf[i + 2];
+		write_buf[3] = rxbuf[i + 3];
+		write_buf[4] = rxbuf[i + 4];
+		write_buf[5] = rxbuf[i + 5];
+		write_buf[6] = rxbuf[i + 6];
+		write_buf[7] = rxbuf[i + 7];
+
+		rxbuf[i + 0] = write_buf[7];
+		rxbuf[i + 1] = write_buf[6];
+		rxbuf[i + 2] = write_buf[5];
+		rxbuf[i + 3] = write_buf[4];
+		rxbuf[i + 4] = write_buf[3];
+		rxbuf[i + 5] = write_buf[2];
+		rxbuf[i + 6] = write_buf[1];
+		rxbuf[i + 7] = write_buf[0];
+	}
+
+	return true;
+}
+
+/**
+ * rt5514_spi_burst_write - Write data to SPI by rt5514 address.
+ * @addr: Start address.
+ * @txbuf: Data Buffer for writng.
+ * @len: Data length, it must be a multiple of 8.
+ *
+ *
+ * Returns true for success.
+ */
+int rt5514_spi_burst_write(u32 addr, const u8 *txbuf, size_t len)
+{
+	u8 spi_cmd = RT5514_SPI_CMD_BURST_WRITE;
+	u8 *write_buf;
+	unsigned int i, end, offset = 0;
+
+	write_buf = kmalloc(RT5514_SPI_BUF_LEN + 6, GFP_KERNEL);
+
+	if (write_buf == NULL)
+		return -ENOMEM;
+
+	while (offset < len) {
+		if (offset + RT5514_SPI_BUF_LEN <= len)
+			end = RT5514_SPI_BUF_LEN;
+		else
+			end = len % RT5514_SPI_BUF_LEN;
+
+		write_buf[0] = spi_cmd;
+		write_buf[1] = ((addr + offset) & 0xff000000) >> 24;
+		write_buf[2] = ((addr + offset) & 0x00ff0000) >> 16;
+		write_buf[3] = ((addr + offset) & 0x0000ff00) >> 8;
+		write_buf[4] = ((addr + offset) & 0x000000ff) >> 0;
+
+		for (i = 0; i < end; i += 8) {
+			write_buf[i + 12] = txbuf[offset + i + 0];
+			write_buf[i + 11] = txbuf[offset + i + 1];
+			write_buf[i + 10] = txbuf[offset + i + 2];
+			write_buf[i +  9] = txbuf[offset + i + 3];
+			write_buf[i +  8] = txbuf[offset + i + 4];
+			write_buf[i +  7] = txbuf[offset + i + 5];
+			write_buf[i +  6] = txbuf[offset + i + 6];
+			write_buf[i +  5] = txbuf[offset + i + 7];
+		}
+
+		write_buf[end + 5] = spi_cmd;
+
+		spi_write(rt5514_spi, write_buf, end + 6);
+
+		offset += RT5514_SPI_BUF_LEN;
+	}
+
+	kfree(write_buf);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rt5514_spi_burst_write);
+
+static int rt5514_spi_probe(struct spi_device *spi)
+{
+	int ret;
+
+	rt5514_spi = spi;
+
+	ret = devm_snd_soc_register_platform(&spi->dev, &rt5514_spi_platform);
+	if (ret < 0) {
+		dev_err(&spi->dev, "Failed to register platform.\n");
+		return ret;
+	}
+
+	ret = devm_snd_soc_register_component(&spi->dev,
+					      &rt5514_spi_dai_component,
+					      &rt5514_spi_dai, 1);
+	if (ret < 0) {
+		dev_err(&spi->dev, "Failed to register component.\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id rt5514_of_match[] = {
+	{ .compatible = "realtek,rt5514", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, rt5514_of_match);
+
+static struct spi_driver rt5514_spi_driver = {
+	.driver = {
+		.name = "rt5514",
+		.of_match_table = of_match_ptr(rt5514_of_match),
+	},
+	.probe = rt5514_spi_probe,
+};
+module_spi_driver(rt5514_spi_driver);
+
+MODULE_DESCRIPTION("RT5514 SPI driver");
+MODULE_AUTHOR("Oder Chiou <oder_chiou@realtek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/rt5514-spi.h b/sound/soc/codecs/rt5514-spi.h
new file mode 100644
index 000000000000..f69b1cdf2f9b
--- /dev/null
+++ b/sound/soc/codecs/rt5514-spi.h
@@ -0,0 +1,38 @@
+/*
+ * rt5514-spi.h  --  RT5514 driver
+ *
+ * Copyright 2015 Realtek Semiconductor Corp.
+ * Author: Oder Chiou <oder_chiou@realtek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __RT5514_SPI_H__
+#define __RT5514_SPI_H__
+
+/**
+ * RT5514_SPI_BUF_LEN is the buffer size of SPI master controller.
+*/
+#define RT5514_SPI_BUF_LEN		240
+
+#define RT5514_BUFFER_VOICE_BASE	0x18001034
+#define RT5514_BUFFER_VOICE_LIMIT	0x18001038
+#define RT5514_BUFFER_VOICE_RP		0x1800103c
+#define RT5514_BUFFER_VOICE_SIZE	0x18001040
+
+/* SPI Command */
+enum {
+	RT5514_SPI_CMD_16_READ = 0,
+	RT5514_SPI_CMD_16_WRITE,
+	RT5514_SPI_CMD_32_READ,
+	RT5514_SPI_CMD_32_WRITE,
+	RT5514_SPI_CMD_BURST_READ,
+	RT5514_SPI_CMD_BURST_WRITE,
+};
+
+int rt5514_spi_burst_read(unsigned int addr, u8 *rxbuf, size_t len);
+int rt5514_spi_burst_write(u32 addr, const u8 *txbuf, size_t len);
+
+#endif /* __RT5514_SPI_H__ */
diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c
index 879bf60f4965..7162f05101d9 100644
--- a/sound/soc/codecs/rt5514.c
+++ b/sound/soc/codecs/rt5514.c
@@ -30,6 +30,9 @@
 
 #include "rl6231.h"
 #include "rt5514.h"
+#if defined(CONFIG_SND_SOC_RT5514_SPI)
+#include "rt5514-spi.h"
+#endif
 
 static const struct reg_sequence rt5514_i2c_patch[] = {
 	{0x1800101c, 0x00000000},
@@ -110,6 +113,35 @@ static const struct reg_default rt5514_reg[] = {
 	{RT5514_VENDOR_ID2,		0x10ec5514},
 };
 
+static void rt5514_enable_dsp_prepare(struct rt5514_priv *rt5514)
+{
+	/* Reset */
+	regmap_write(rt5514->i2c_regmap, 0x18002000, 0x000010ec);
+	/* LDO_I_limit */
+	regmap_write(rt5514->i2c_regmap, 0x18002200, 0x00028604);
+	/* I2C bypass enable */
+	regmap_write(rt5514->i2c_regmap, 0xfafafafa, 0x00000001);
+	/* mini-core reset */
+	regmap_write(rt5514->i2c_regmap, 0x18002f00, 0x0005514b);
+	regmap_write(rt5514->i2c_regmap, 0x18002f00, 0x00055149);
+	/* I2C bypass disable */
+	regmap_write(rt5514->i2c_regmap, 0xfafafafa, 0x00000000);
+	/* PIN config */
+	regmap_write(rt5514->i2c_regmap, 0x18002070, 0x00000040);
+	/* PLL3(QN)=RCOSC*(10+2) */
+	regmap_write(rt5514->i2c_regmap, 0x18002240, 0x0000000a);
+	/* PLL3 source=RCOSC, fsi=rt_clk */
+	regmap_write(rt5514->i2c_regmap, 0x18002100, 0x0000000b);
+	/* Power on RCOSC, pll3 */
+	regmap_write(rt5514->i2c_regmap, 0x18002004, 0x00808b81);
+	/* DSP clk source = pll3, ENABLE DSP clk */
+	regmap_write(rt5514->i2c_regmap, 0x18002f08, 0x00000005);
+	/* Enable DSP clk auto switch */
+	regmap_write(rt5514->i2c_regmap, 0x18001114, 0x00000001);
+	/* Reduce DSP power */
+	regmap_write(rt5514->i2c_regmap, 0x18001118, 0x00000001);
+}
+
 static bool rt5514_volatile_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
@@ -248,6 +280,74 @@ static const DECLARE_TLV_DB_RANGE(bst_tlv,
 
 static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0);
 
+static int rt5514_dsp_voice_wake_up_get(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct rt5514_priv *rt5514 = snd_soc_component_get_drvdata(component);
+
+	ucontrol->value.integer.value[0] = rt5514->dsp_enabled;
+
+	return 0;
+}
+
+static int rt5514_dsp_voice_wake_up_put(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct rt5514_priv *rt5514 = snd_soc_component_get_drvdata(component);
+	struct snd_soc_codec *codec = rt5514->codec;
+	const struct firmware *fw = NULL;
+
+	if (ucontrol->value.integer.value[0] == rt5514->dsp_enabled)
+		return 0;
+
+	if (snd_soc_codec_get_bias_level(codec) == SND_SOC_BIAS_OFF) {
+		rt5514->dsp_enabled = ucontrol->value.integer.value[0];
+
+		if (rt5514->dsp_enabled) {
+			rt5514_enable_dsp_prepare(rt5514);
+
+			request_firmware(&fw, RT5514_FIRMWARE1, codec->dev);
+			if (fw) {
+#if defined(CONFIG_SND_SOC_RT5514_SPI)
+				rt5514_spi_burst_write(0x4ff60000, fw->data,
+					((fw->size/8)+1)*8);
+#else
+				dev_err(codec->dev, "There is no SPI driver for"
+					" loading the firmware\n");
+#endif
+				release_firmware(fw);
+				fw = NULL;
+			}
+
+			request_firmware(&fw, RT5514_FIRMWARE2, codec->dev);
+			if (fw) {
+#if defined(CONFIG_SND_SOC_RT5514_SPI)
+				rt5514_spi_burst_write(0x4ffc0000, fw->data,
+					((fw->size/8)+1)*8);
+#else
+				dev_err(codec->dev, "There is no SPI driver for"
+					" loading the firmware\n");
+#endif
+				release_firmware(fw);
+				fw = NULL;
+			}
+
+			/* DSP run */
+			regmap_write(rt5514->i2c_regmap, 0x18002f00,
+				0x00055148);
+		} else {
+			regmap_multi_reg_write(rt5514->i2c_regmap,
+				rt5514_i2c_patch, ARRAY_SIZE(rt5514_i2c_patch));
+			regcache_mark_dirty(rt5514->regmap);
+			regcache_sync(rt5514->regmap);
+		}
+	}
+
+	return 0;
+}
+
 static const struct snd_kcontrol_new rt5514_snd_controls[] = {
 	SOC_DOUBLE_TLV("MIC Boost Volume", RT5514_ANA_CTRL_MICBST,
 		RT5514_SEL_BSTL_SFT, RT5514_SEL_BSTR_SFT, 8, 0, bst_tlv),
@@ -257,6 +357,8 @@ static const struct snd_kcontrol_new rt5514_snd_controls[] = {
 	SOC_DOUBLE_R_TLV("ADC2 Capture Volume", RT5514_DOWNFILTER1_CTRL1,
 		RT5514_DOWNFILTER1_CTRL2, RT5514_AD_GAIN_SFT, 127, 0,
 		adc_vol_tlv),
+	SOC_SINGLE_EXT("DSP Voice Wake Up", SND_SOC_NOPM, 0, 1, 0,
+		rt5514_dsp_voice_wake_up_get, rt5514_dsp_voice_wake_up_put),
 };
 
 /* ADC Mixer*/
@@ -365,6 +467,35 @@ static int rt5514_is_sys_clk_from_pll(struct snd_soc_dapm_widget *source,
 		return 0;
 }
 
+static int rt5514_pre_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
+	struct rt5514_priv *rt5514 = snd_soc_codec_get_drvdata(codec);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/**
+		 * If the DSP is enabled in start of recording, the DSP
+		 * should be disabled, and sync back to normal recording
+		 * settings to make sure recording properly.
+		*/
+		if (rt5514->dsp_enabled) {
+			rt5514->dsp_enabled = 0;
+			regmap_multi_reg_write(rt5514->i2c_regmap,
+				rt5514_i2c_patch, ARRAY_SIZE(rt5514_i2c_patch));
+			regcache_mark_dirty(rt5514->regmap);
+			regcache_sync(rt5514->regmap);
+		}
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
 static const struct snd_soc_dapm_widget rt5514_dapm_widgets[] = {
 	/* Input Lines */
 	SND_SOC_DAPM_INPUT("DMIC1L"),
@@ -472,6 +603,8 @@ static const struct snd_soc_dapm_widget rt5514_dapm_widgets[] = {
 
 	/* Audio Interface */
 	SND_SOC_DAPM_AIF_OUT("AIF1TX", "AIF1 Capture", 0, SND_SOC_NOPM, 0, 0),
+
+	SND_SOC_DAPM_PRE("DAPM Pre", rt5514_pre_event),
 };
 
 static const struct snd_soc_dapm_route rt5514_dapm_routes[] = {
@@ -799,10 +932,41 @@ static int rt5514_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
 	return 0;
 }
 
+static int rt5514_set_bias_level(struct snd_soc_codec *codec,
+			enum snd_soc_bias_level level)
+{
+	struct rt5514_priv *rt5514 = snd_soc_codec_get_drvdata(codec);
+	int ret;
+
+	switch (level) {
+	case SND_SOC_BIAS_PREPARE:
+		if (IS_ERR(rt5514->mclk))
+			break;
+
+		if (snd_soc_codec_get_bias_level(codec) == SND_SOC_BIAS_ON) {
+			clk_disable_unprepare(rt5514->mclk);
+		} else {
+			ret = clk_prepare_enable(rt5514->mclk);
+			if (ret)
+				return ret;
+		}
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static int rt5514_probe(struct snd_soc_codec *codec)
 {
 	struct rt5514_priv *rt5514 = snd_soc_codec_get_drvdata(codec);
 
+	rt5514->mclk = devm_clk_get(codec->dev, "mclk");
+	if (PTR_ERR(rt5514->mclk) == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
 	rt5514->codec = codec;
 
 	return 0;
@@ -858,6 +1022,7 @@ struct snd_soc_dai_driver rt5514_dai[] = {
 static struct snd_soc_codec_driver soc_codec_dev_rt5514 = {
 	.probe = rt5514_probe,
 	.idle_bias_off = true,
+	.set_bias_level = rt5514_set_bias_level,
 	.controls = rt5514_snd_controls,
 	.num_controls = ARRAY_SIZE(rt5514_snd_controls),
 	.dapm_widgets = rt5514_dapm_widgets,
@@ -871,7 +1036,6 @@ static const struct regmap_config rt5514_i2c_regmap = {
 	.reg_bits = 32,
 	.val_bits = 32,
 
-	.max_register = RT5514_DSP_MAPPING | RT5514_VENDOR_ID2,
 	.readable_reg = rt5514_i2c_readable_register,
 
 	.cache_type = REGCACHE_NONE,
@@ -944,7 +1108,7 @@ static int rt5514_i2c_probe(struct i2c_client *i2c,
 		return -ENODEV;
 	}
 
-	ret = regmap_register_patch(rt5514->i2c_regmap, rt5514_i2c_patch,
+	ret = regmap_multi_reg_write(rt5514->i2c_regmap, rt5514_i2c_patch,
 				    ARRAY_SIZE(rt5514_i2c_patch));
 	if (ret != 0)
 		dev_warn(&i2c->dev, "Failed to apply i2c_regmap patch: %d\n",
diff --git a/sound/soc/codecs/rt5514.h b/sound/soc/codecs/rt5514.h
index 6ad8a612f659..68883c68e999 100644
--- a/sound/soc/codecs/rt5514.h
+++ b/sound/soc/codecs/rt5514.h
@@ -12,6 +12,8 @@
 #ifndef __RT5514_H__
 #define __RT5514_H__
 
+#include <linux/clk.h>
+
 #define RT5514_DEVICE_ID			0x10ec5514
 
 #define RT5514_RESET				0x2000
@@ -225,6 +227,9 @@
 #define RT5514_PLL_INP_MAX			40000000
 #define RT5514_PLL_INP_MIN			256000
 
+#define RT5514_FIRMWARE1	"rt5514_dsp_fw1.bin"
+#define RT5514_FIRMWARE2	"rt5514_dsp_fw2.bin"
+
 /* System Clock Source */
 enum {
 	RT5514_SCLK_S_MCLK,
@@ -240,6 +245,7 @@ enum {
 struct rt5514_priv {
 	struct snd_soc_codec *codec;
 	struct regmap *i2c_regmap, *regmap;
+	struct clk *mclk;
 	int sysclk;
 	int sysclk_src;
 	int lrck;
@@ -247,6 +253,7 @@ struct rt5514_priv {
 	int pll_src;
 	int pll_in;
 	int pll_out;
+	int dsp_enabled;
 };
 
 #endif /* __RT5514_H__ */
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index d70847c9eeb0..490bfe661346 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -63,6 +63,7 @@ static const struct reg_sequence init_list[] = {
 	{RT5645_PR_BASE + 0x20,	0x611f},
 	{RT5645_PR_BASE + 0x21,	0x4040},
 	{RT5645_PR_BASE + 0x23,	0x0004},
+	{RT5645_ASRC_4, 0x0120},
 };
 
 static const struct reg_sequence rt5650_init_list[] = {
@@ -157,7 +158,7 @@ static const struct reg_default rt5645_reg[] = {
 	{ 0x83, 0x0000 },
 	{ 0x84, 0x0000 },
 	{ 0x85, 0x0000 },
-	{ 0x8a, 0x0000 },
+	{ 0x8a, 0x0120 },
 	{ 0x8e, 0x0004 },
 	{ 0x8f, 0x1100 },
 	{ 0x90, 0x0646 },
@@ -314,7 +315,7 @@ static const struct reg_default rt5650_reg[] = {
 	{ 0x83, 0x0000 },
 	{ 0x84, 0x0000 },
 	{ 0x85, 0x0000 },
-	{ 0x8a, 0x0000 },
+	{ 0x8a, 0x0120 },
 	{ 0x8e, 0x0004 },
 	{ 0x8f, 0x1100 },
 	{ 0x90, 0x0646 },
@@ -440,6 +441,7 @@ static bool rt5645_volatile_register(struct device *dev, unsigned int reg)
 
 	switch (reg) {
 	case RT5645_RESET:
+	case RT5645_PRIV_INDEX:
 	case RT5645_PRIV_DATA:
 	case RT5645_IN1_CTRL1:
 	case RT5645_IN1_CTRL2:
@@ -740,6 +742,14 @@ static int rt5645_spk_put_volsw(struct snd_kcontrol *kcontrol,
 	return ret;
 }
 
+static const char * const rt5645_dac1_vol_ctrl_mode_text[] = {
+	"immediately", "zero crossing", "soft ramp"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5645_dac1_vol_ctrl_mode, RT5645_PR_BASE,
+	RT5645_DA1_ZDET_SFT, rt5645_dac1_vol_ctrl_mode_text);
+
 static const struct snd_kcontrol_new rt5645_snd_controls[] = {
 	/* Speaker Output Volume */
 	SOC_DOUBLE("Speaker Channel Switch", RT5645_SPK_VOL,
@@ -806,6 +816,9 @@ static const struct snd_kcontrol_new rt5645_snd_controls[] = {
 	SOC_SINGLE("I2S2 Func Switch", RT5645_GPIO_CTRL1, RT5645_I2S2_SEL_SFT,
 		1, 1),
 	RT5645_HWEQ("Speaker HWEQ"),
+
+	/* Digital Soft Volume Control */
+	SOC_ENUM("DAC1 Digital Volume Control Func", rt5645_dac1_vol_ctrl_mode),
 };
 
 /**
@@ -3531,6 +3544,7 @@ MODULE_DEVICE_TABLE(i2c, rt5645_i2c_id);
 static const struct acpi_device_id rt5645_acpi_match[] = {
 	{ "10EC5645", 0 },
 	{ "10EC5650", 0 },
+	{ "10EC5640", 0 },
 	{},
 };
 MODULE_DEVICE_TABLE(acpi, rt5645_acpi_match);
@@ -3561,6 +3575,12 @@ static const struct dmi_system_id dmi_platform_intel_braswell[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Setzer"),
 		},
 	},
+	{
+		.ident = "Microsoft Surface 3",
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "Surface 3"),
+		},
+	},
 	{ }
 };
 
diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h
index 205e0715c99a..cfc5f97549eb 100644
--- a/sound/soc/codecs/rt5645.h
+++ b/sound/soc/codecs/rt5645.h
@@ -2018,6 +2018,9 @@
 
 
 /* Codec Private Register definition */
+/* DAC ADC Digital Volume (0x00) */
+#define RT5645_DA1_ZDET_SFT			6
+
 /* 3D Speaker Control (0x63) */
 #define RT5645_3D_SPK_MASK			(0x1 << 15)
 #define RT5645_3D_SPK_SFT			15
diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c
index 0af5ddbef1da..8ef467f64f03 100644
--- a/sound/soc/codecs/rt5670.c
+++ b/sound/soc/codecs/rt5670.c
@@ -55,6 +55,7 @@ static const struct reg_sequence init_list[] = {
 	{ RT5670_PR_BASE + 0x14, 0x9a8a },
 	{ RT5670_PR_BASE + 0x38, 0x3ba1 },
 	{ RT5670_PR_BASE + 0x3d, 0x3640 },
+	{ 0x8a, 0x0123 },
 };
 
 static const struct reg_default rt5670_reg[] = {
@@ -131,7 +132,7 @@ static const struct reg_default rt5670_reg[] = {
 	{ 0x87, 0x0000 },
 	{ 0x88, 0x0000 },
 	{ 0x89, 0x0000 },
-	{ 0x8a, 0x0000 },
+	{ 0x8a, 0x0123 },
 	{ 0x8b, 0x0000 },
 	{ 0x8c, 0x0003 },
 	{ 0x8d, 0x0000 },
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 08b40460663c..527b759c1562 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -38,7 +38,6 @@
 /* default value of sgtl5000 registers */
 static const struct reg_default sgtl5000_reg_defaults[] = {
 	{ SGTL5000_CHIP_DIG_POWER,		0x0000 },
-	{ SGTL5000_CHIP_CLK_CTRL,		0x0008 },
 	{ SGTL5000_CHIP_I2S_CTRL,		0x0010 },
 	{ SGTL5000_CHIP_SSS_CTRL,		0x0010 },
 	{ SGTL5000_CHIP_ADCDAC_CTRL,		0x020c },
@@ -47,12 +46,10 @@ static const struct reg_default sgtl5000_reg_defaults[] = {
 	{ SGTL5000_CHIP_ANA_ADC_CTRL,		0x0000 },
 	{ SGTL5000_CHIP_ANA_HP_CTRL,		0x1818 },
 	{ SGTL5000_CHIP_ANA_CTRL,		0x0111 },
-	{ SGTL5000_CHIP_LINREG_CTRL,		0x0000 },
 	{ SGTL5000_CHIP_REF_CTRL,		0x0000 },
 	{ SGTL5000_CHIP_MIC_CTRL,		0x0000 },
 	{ SGTL5000_CHIP_LINE_OUT_CTRL,		0x0000 },
 	{ SGTL5000_CHIP_LINE_OUT_VOL,		0x0404 },
-	{ SGTL5000_CHIP_ANA_POWER,		0x7060 },
 	{ SGTL5000_CHIP_PLL_CTRL,		0x5000 },
 	{ SGTL5000_CHIP_CLK_TOP_CTRL,		0x0000 },
 	{ SGTL5000_CHIP_ANA_STATUS,		0x0000 },
@@ -92,35 +89,8 @@ static const char *supply_names[SGTL5000_SUPPLY_NUM] = {
 	"VDDD"
 };
 
-#define LDO_CONSUMER_NAME	"VDDD_LDO"
 #define LDO_VOLTAGE		1200000
-
-static struct regulator_consumer_supply ldo_consumer[] = {
-	REGULATOR_SUPPLY(LDO_CONSUMER_NAME, NULL),
-};
-
-static struct regulator_init_data ldo_init_data = {
-	.constraints = {
-		.min_uV                 = 1200000,
-		.max_uV                 = 1200000,
-		.valid_modes_mask       = REGULATOR_MODE_NORMAL,
-		.valid_ops_mask         = REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies = 1,
-	.consumer_supplies = &ldo_consumer[0],
-};
-
-/*
- * sgtl5000 internal ldo regulator,
- * enabled when VDDD not provided
- */
-struct ldo_regulator {
-	struct regulator_desc desc;
-	struct regulator_dev *dev;
-	int voltage;
-	void *codec_data;
-	bool enabled;
-};
+#define LINREG_VDDD	((1600 - LDO_VOLTAGE / 1000) / 50)
 
 enum sgtl5000_micbias_resistor {
 	SGTL5000_MICBIAS_OFF = 0,
@@ -135,7 +105,7 @@ struct sgtl5000_priv {
 	int master;	/* i2s master or not */
 	int fmt;	/* i2s data format */
 	struct regulator_bulk_data supplies[SGTL5000_SUPPLY_NUM];
-	struct ldo_regulator *ldo;
+	int num_supplies;
 	struct regmap *regmap;
 	struct clk *mclk;
 	int revision;
@@ -415,6 +385,9 @@ static const DECLARE_TLV_DB_RANGE(mic_gain_tlv,
 /* tlv for hp volume, -51.5db to 12.0db, step .5db */
 static const DECLARE_TLV_DB_SCALE(headphone_volume, -5150, 50, 0);
 
+/* tlv for lineout volume, 31 steps of .5db each */
+static const DECLARE_TLV_DB_SCALE(lineout_volume, -1550, 50, 0);
+
 static const struct snd_kcontrol_new sgtl5000_snd_controls[] = {
 	/* SOC_DOUBLE_S8_TLV with invert */
 	{
@@ -443,6 +416,13 @@ static const struct snd_kcontrol_new sgtl5000_snd_controls[] = {
 
 	SOC_SINGLE_TLV("Mic Volume", SGTL5000_CHIP_MIC_CTRL,
 			0, 3, 0, mic_gain_tlv),
+
+	SOC_DOUBLE_TLV("Lineout Playback Volume",
+			SGTL5000_CHIP_LINE_OUT_VOL,
+			SGTL5000_LINE_OUT_VOL_LEFT_SHIFT,
+			SGTL5000_LINE_OUT_VOL_RIGHT_SHIFT,
+			0x1f, 1,
+			lineout_volume),
 };
 
 /* mute the codec used by alsa core */
@@ -778,155 +758,6 @@ static int sgtl5000_pcm_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-#ifdef CONFIG_REGULATOR
-static int ldo_regulator_is_enabled(struct regulator_dev *dev)
-{
-	struct ldo_regulator *ldo = rdev_get_drvdata(dev);
-
-	return ldo->enabled;
-}
-
-static int ldo_regulator_enable(struct regulator_dev *dev)
-{
-	struct ldo_regulator *ldo = rdev_get_drvdata(dev);
-	struct snd_soc_codec *codec = (struct snd_soc_codec *)ldo->codec_data;
-	int reg;
-
-	if (ldo_regulator_is_enabled(dev))
-		return 0;
-
-	/* set regulator value firstly */
-	reg = (1600 - ldo->voltage / 1000) / 50;
-	reg = clamp(reg, 0x0, 0xf);
-
-	/* amend the voltage value, unit: uV */
-	ldo->voltage = (1600 - reg * 50) * 1000;
-
-	/* set voltage to register */
-	snd_soc_update_bits(codec, SGTL5000_CHIP_LINREG_CTRL,
-				SGTL5000_LINREG_VDDD_MASK, reg);
-
-	snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
-				SGTL5000_LINEREG_D_POWERUP,
-				SGTL5000_LINEREG_D_POWERUP);
-
-	/* when internal ldo is enabled, simple digital power can be disabled */
-	snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
-				SGTL5000_LINREG_SIMPLE_POWERUP,
-				0);
-
-	ldo->enabled = 1;
-	return 0;
-}
-
-static int ldo_regulator_disable(struct regulator_dev *dev)
-{
-	struct ldo_regulator *ldo = rdev_get_drvdata(dev);
-	struct snd_soc_codec *codec = (struct snd_soc_codec *)ldo->codec_data;
-
-	snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
-				SGTL5000_LINEREG_D_POWERUP,
-				0);
-
-	/* clear voltage info */
-	snd_soc_update_bits(codec, SGTL5000_CHIP_LINREG_CTRL,
-				SGTL5000_LINREG_VDDD_MASK, 0);
-
-	ldo->enabled = 0;
-
-	return 0;
-}
-
-static int ldo_regulator_get_voltage(struct regulator_dev *dev)
-{
-	struct ldo_regulator *ldo = rdev_get_drvdata(dev);
-
-	return ldo->voltage;
-}
-
-static struct regulator_ops ldo_regulator_ops = {
-	.is_enabled = ldo_regulator_is_enabled,
-	.enable = ldo_regulator_enable,
-	.disable = ldo_regulator_disable,
-	.get_voltage = ldo_regulator_get_voltage,
-};
-
-static int ldo_regulator_register(struct snd_soc_codec *codec,
-				struct regulator_init_data *init_data,
-				int voltage)
-{
-	struct ldo_regulator *ldo;
-	struct sgtl5000_priv *sgtl5000 = snd_soc_codec_get_drvdata(codec);
-	struct regulator_config config = { };
-
-	ldo = kzalloc(sizeof(struct ldo_regulator), GFP_KERNEL);
-
-	if (!ldo)
-		return -ENOMEM;
-
-	ldo->desc.name = kstrdup(dev_name(codec->dev), GFP_KERNEL);
-	if (!ldo->desc.name) {
-		kfree(ldo);
-		dev_err(codec->dev, "failed to allocate decs name memory\n");
-		return -ENOMEM;
-	}
-
-	ldo->desc.type  = REGULATOR_VOLTAGE;
-	ldo->desc.owner = THIS_MODULE;
-	ldo->desc.ops   = &ldo_regulator_ops;
-	ldo->desc.n_voltages = 1;
-
-	ldo->codec_data = codec;
-	ldo->voltage = voltage;
-
-	config.dev = codec->dev;
-	config.driver_data = ldo;
-	config.init_data = init_data;
-
-	ldo->dev = regulator_register(&ldo->desc, &config);
-	if (IS_ERR(ldo->dev)) {
-		int ret = PTR_ERR(ldo->dev);
-
-		dev_err(codec->dev, "failed to register regulator\n");
-		kfree(ldo->desc.name);
-		kfree(ldo);
-
-		return ret;
-	}
-	sgtl5000->ldo = ldo;
-
-	return 0;
-}
-
-static int ldo_regulator_remove(struct snd_soc_codec *codec)
-{
-	struct sgtl5000_priv *sgtl5000 = snd_soc_codec_get_drvdata(codec);
-	struct ldo_regulator *ldo = sgtl5000->ldo;
-
-	if (!ldo)
-		return 0;
-
-	regulator_unregister(ldo->dev);
-	kfree(ldo->desc.name);
-	kfree(ldo);
-
-	return 0;
-}
-#else
-static int ldo_regulator_register(struct snd_soc_codec *codec,
-				struct regulator_init_data *init_data,
-				int voltage)
-{
-	dev_err(codec->dev, "this setup needs regulator support in the kernel\n");
-	return -EINVAL;
-}
-
-static int ldo_regulator_remove(struct snd_soc_codec *codec)
-{
-	return 0;
-}
-#endif
-
 /*
  * set dac bias
  * common state changes:
@@ -940,42 +771,17 @@ static int ldo_regulator_remove(struct snd_soc_codec *codec)
 static int sgtl5000_set_bias_level(struct snd_soc_codec *codec,
 				   enum snd_soc_bias_level level)
 {
-	int ret;
-	struct sgtl5000_priv *sgtl5000 = snd_soc_codec_get_drvdata(codec);
-
 	switch (level) {
 	case SND_SOC_BIAS_ON:
 	case SND_SOC_BIAS_PREPARE:
-		break;
 	case SND_SOC_BIAS_STANDBY:
-		if (snd_soc_codec_get_bias_level(codec) == SND_SOC_BIAS_OFF) {
-			ret = regulator_bulk_enable(
-						ARRAY_SIZE(sgtl5000->supplies),
-						sgtl5000->supplies);
-			if (ret)
-				return ret;
-			udelay(10);
-
-			regcache_cache_only(sgtl5000->regmap, false);
-
-			ret = regcache_sync(sgtl5000->regmap);
-			if (ret != 0) {
-				dev_err(codec->dev,
-					"Failed to restore cache: %d\n", ret);
-
-				regcache_cache_only(sgtl5000->regmap, true);
-				regulator_bulk_disable(ARRAY_SIZE(sgtl5000->supplies),
-						       sgtl5000->supplies);
-
-				return ret;
-			}
-		}
-
+		snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
+				    SGTL5000_REFTOP_POWERUP,
+				    SGTL5000_REFTOP_POWERUP);
 		break;
 	case SND_SOC_BIAS_OFF:
-		regcache_cache_only(sgtl5000->regmap, true);
-		regulator_bulk_disable(ARRAY_SIZE(sgtl5000->supplies),
-					sgtl5000->supplies);
+		snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
+				    SGTL5000_REFTOP_POWERUP, 0);
 		break;
 	}
 
@@ -1113,7 +919,6 @@ static const u8 vol_quot_table[] = {
  * and should be set according to:
  * 1. vddd provided by external or not
  * 2. vdda and vddio voltage value. > 3.1v or not
- * 3. chip revision >=0x11 or not. If >=0x11, not use external vddd.
  */
 static int sgtl5000_set_power_regs(struct snd_soc_codec *codec)
 {
@@ -1131,7 +936,9 @@ static int sgtl5000_set_power_regs(struct snd_soc_codec *codec)
 
 	vdda  = regulator_get_voltage(sgtl5000->supplies[VDDA].consumer);
 	vddio = regulator_get_voltage(sgtl5000->supplies[VDDIO].consumer);
-	vddd  = regulator_get_voltage(sgtl5000->supplies[VDDD].consumer);
+	vddd  = (sgtl5000->num_supplies > VDDD)
+		? regulator_get_voltage(sgtl5000->supplies[VDDD].consumer)
+		: LDO_VOLTAGE;
 
 	vdda  = vdda / 1000;
 	vddio = vddio / 1000;
@@ -1178,25 +985,6 @@ static int sgtl5000_set_power_regs(struct snd_soc_codec *codec)
 
 	snd_soc_write(codec, SGTL5000_CHIP_ANA_POWER, ana_pwr);
 
-	/* set voltage to register */
-	snd_soc_update_bits(codec, SGTL5000_CHIP_LINREG_CTRL,
-				SGTL5000_LINREG_VDDD_MASK, 0x8);
-
-	/*
-	 * if vddd linear reg has been enabled,
-	 * simple digital supply should be clear to get
-	 * proper VDDD voltage.
-	 */
-	if (ana_pwr & SGTL5000_LINEREG_D_POWERUP)
-		snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
-				SGTL5000_LINREG_SIMPLE_POWERUP,
-				0);
-	else
-		snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
-				SGTL5000_LINREG_SIMPLE_POWERUP |
-				SGTL5000_STARTUP_POWERUP,
-				0);
-
 	/*
 	 * set ADC/DAC VAG to vdda / 2,
 	 * should stay in range (0.8v, 1.575v)
@@ -1256,78 +1044,43 @@ static int sgtl5000_set_power_regs(struct snd_soc_codec *codec)
 	return 0;
 }
 
-static int sgtl5000_replace_vddd_with_ldo(struct snd_soc_codec *codec)
-{
-	struct sgtl5000_priv *sgtl5000 = snd_soc_codec_get_drvdata(codec);
-	int ret;
-
-	/* set internal ldo to 1.2v */
-	ret = ldo_regulator_register(codec, &ldo_init_data, LDO_VOLTAGE);
-	if (ret) {
-		dev_err(codec->dev,
-			"Failed to register vddd internal supplies: %d\n", ret);
-		return ret;
-	}
-
-	sgtl5000->supplies[VDDD].supply = LDO_CONSUMER_NAME;
-
-	dev_info(codec->dev, "Using internal LDO instead of VDDD\n");
-	return 0;
-}
-
-static int sgtl5000_enable_regulators(struct snd_soc_codec *codec)
+static int sgtl5000_enable_regulators(struct i2c_client *client)
 {
 	int ret;
 	int i;
 	int external_vddd = 0;
-	struct sgtl5000_priv *sgtl5000 = snd_soc_codec_get_drvdata(codec);
 	struct regulator *vddd;
+	struct sgtl5000_priv *sgtl5000 = i2c_get_clientdata(client);
 
 	for (i = 0; i < ARRAY_SIZE(sgtl5000->supplies); i++)
 		sgtl5000->supplies[i].supply = supply_names[i];
 
-	/* External VDDD only works before revision 0x11 */
-	if (sgtl5000->revision < 0x11) {
-		vddd = regulator_get_optional(codec->dev, "VDDD");
-		if (IS_ERR(vddd)) {
-			/* See if it's just not registered yet */
-			if (PTR_ERR(vddd) == -EPROBE_DEFER)
-				return -EPROBE_DEFER;
-		} else {
-			external_vddd = 1;
-			regulator_put(vddd);
-		}
-	}
-
-	if (!external_vddd) {
-		ret = sgtl5000_replace_vddd_with_ldo(codec);
-		if (ret)
-			return ret;
+	vddd = regulator_get_optional(&client->dev, "VDDD");
+	if (IS_ERR(vddd)) {
+		/* See if it's just not registered yet */
+		if (PTR_ERR(vddd) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+	} else {
+		external_vddd = 1;
+		regulator_put(vddd);
 	}
 
-	ret = regulator_bulk_get(codec->dev, ARRAY_SIZE(sgtl5000->supplies),
+	sgtl5000->num_supplies = ARRAY_SIZE(sgtl5000->supplies)
+				 - 1 + external_vddd;
+	ret = regulator_bulk_get(&client->dev, sgtl5000->num_supplies,
 				 sgtl5000->supplies);
 	if (ret)
-		goto err_ldo_remove;
-
-	ret = regulator_bulk_enable(ARRAY_SIZE(sgtl5000->supplies),
-					sgtl5000->supplies);
-	if (ret)
-		goto err_regulator_free;
-
-	/* wait for all power rails bring up */
-	udelay(10);
+		return ret;
 
-	return 0;
+	ret = regulator_bulk_enable(sgtl5000->num_supplies,
+				    sgtl5000->supplies);
+	if (!ret)
+		usleep_range(10, 20);
+	else
+		regulator_bulk_free(sgtl5000->num_supplies,
+				    sgtl5000->supplies);
 
-err_regulator_free:
-	regulator_bulk_free(ARRAY_SIZE(sgtl5000->supplies),
-				sgtl5000->supplies);
-err_ldo_remove:
-	if (!external_vddd)
-		ldo_regulator_remove(codec);
 	return ret;
-
 }
 
 static int sgtl5000_probe(struct snd_soc_codec *codec)
@@ -1335,10 +1088,6 @@ static int sgtl5000_probe(struct snd_soc_codec *codec)
 	int ret;
 	struct sgtl5000_priv *sgtl5000 = snd_soc_codec_get_drvdata(codec);
 
-	ret = sgtl5000_enable_regulators(codec);
-	if (ret)
-		return ret;
-
 	/* power up sgtl5000 */
 	ret = sgtl5000_set_power_regs(codec);
 	if (ret)
@@ -1389,25 +1138,11 @@ static int sgtl5000_probe(struct snd_soc_codec *codec)
 	return 0;
 
 err:
-	regulator_bulk_disable(ARRAY_SIZE(sgtl5000->supplies),
-						sgtl5000->supplies);
-	regulator_bulk_free(ARRAY_SIZE(sgtl5000->supplies),
-				sgtl5000->supplies);
-	ldo_regulator_remove(codec);
-
 	return ret;
 }
 
 static int sgtl5000_remove(struct snd_soc_codec *codec)
 {
-	struct sgtl5000_priv *sgtl5000 = snd_soc_codec_get_drvdata(codec);
-
-	regulator_bulk_disable(ARRAY_SIZE(sgtl5000->supplies),
-						sgtl5000->supplies);
-	regulator_bulk_free(ARRAY_SIZE(sgtl5000->supplies),
-				sgtl5000->supplies);
-	ldo_regulator_remove(codec);
-
 	return 0;
 }
 
@@ -1448,8 +1183,9 @@ static const struct regmap_config sgtl5000_regmap = {
  * and avoid problems like, not being able to probe after an audio playback
  * followed by a system reset or a 'reboot' command in Linux
  */
-static int sgtl5000_fill_defaults(struct sgtl5000_priv *sgtl5000)
+static void sgtl5000_fill_defaults(struct i2c_client *client)
 {
+	struct sgtl5000_priv *sgtl5000 = i2c_get_clientdata(client);
 	int i, ret, val, index;
 
 	for (i = 0; i < ARRAY_SIZE(sgtl5000_reg_defaults); i++) {
@@ -1457,10 +1193,10 @@ static int sgtl5000_fill_defaults(struct sgtl5000_priv *sgtl5000)
 		index = sgtl5000_reg_defaults[i].reg;
 		ret = regmap_write(sgtl5000->regmap, index, val);
 		if (ret)
-			return ret;
+			dev_err(&client->dev,
+				"%s: error %d setting reg 0x%02x to 0x%04x\n",
+				__func__, ret, index, val);
 	}
-
-	return 0;
 }
 
 static int sgtl5000_i2c_probe(struct i2c_client *client,
@@ -1470,16 +1206,23 @@ static int sgtl5000_i2c_probe(struct i2c_client *client,
 	int ret, reg, rev;
 	struct device_node *np = client->dev.of_node;
 	u32 value;
+	u16 ana_pwr;
 
 	sgtl5000 = devm_kzalloc(&client->dev, sizeof(*sgtl5000), GFP_KERNEL);
 	if (!sgtl5000)
 		return -ENOMEM;
 
+	i2c_set_clientdata(client, sgtl5000);
+
+	ret = sgtl5000_enable_regulators(client);
+	if (ret)
+		return ret;
+
 	sgtl5000->regmap = devm_regmap_init_i2c(client, &sgtl5000_regmap);
 	if (IS_ERR(sgtl5000->regmap)) {
 		ret = PTR_ERR(sgtl5000->regmap);
 		dev_err(&client->dev, "Failed to allocate regmap: %d\n", ret);
-		return ret;
+		goto disable_regs;
 	}
 
 	sgtl5000->mclk = devm_clk_get(&client->dev, NULL);
@@ -1488,21 +1231,25 @@ static int sgtl5000_i2c_probe(struct i2c_client *client,
 		dev_err(&client->dev, "Failed to get mclock: %d\n", ret);
 		/* Defer the probe to see if the clk will be provided later */
 		if (ret == -ENOENT)
-			return -EPROBE_DEFER;
-		return ret;
+			ret = -EPROBE_DEFER;
+		goto disable_regs;
 	}
 
 	ret = clk_prepare_enable(sgtl5000->mclk);
-	if (ret)
-		return ret;
+	if (ret) {
+		dev_err(&client->dev, "Error enabling clock %d\n", ret);
+		goto disable_regs;
+	}
 
 	/* Need 8 clocks before I2C accesses */
 	udelay(1);
 
 	/* read chip information */
 	ret = regmap_read(sgtl5000->regmap, SGTL5000_CHIP_ID, &reg);
-	if (ret)
+	if (ret) {
+		dev_err(&client->dev, "Error reading chip id %d\n", ret);
 		goto disable_clk;
+	}
 
 	if (((reg & SGTL5000_PARTID_MASK) >> SGTL5000_PARTID_SHIFT) !=
 	    SGTL5000_PARTID_PART_ID) {
@@ -1516,6 +1263,44 @@ static int sgtl5000_i2c_probe(struct i2c_client *client,
 	dev_info(&client->dev, "sgtl5000 revision 0x%x\n", rev);
 	sgtl5000->revision = rev;
 
+	/* reconfigure the clocks in case we're using the PLL */
+	ret = regmap_write(sgtl5000->regmap,
+			   SGTL5000_CHIP_CLK_CTRL,
+			   SGTL5000_CHIP_CLK_CTRL_DEFAULT);
+	if (ret)
+		dev_err(&client->dev,
+			"Error %d initializing CHIP_CLK_CTRL\n", ret);
+
+	/* Follow section 2.2.1.1 of AN3663 */
+	ana_pwr = SGTL5000_ANA_POWER_DEFAULT;
+	if (sgtl5000->num_supplies <= VDDD) {
+		/* internal VDDD at 1.2V */
+		ret = regmap_update_bits(sgtl5000->regmap,
+					 SGTL5000_CHIP_LINREG_CTRL,
+					 SGTL5000_LINREG_VDDD_MASK,
+					 LINREG_VDDD);
+		if (ret)
+			dev_err(&client->dev,
+				"Error %d setting LINREG_VDDD\n", ret);
+
+		ana_pwr |= SGTL5000_LINEREG_D_POWERUP;
+		dev_info(&client->dev,
+			 "Using internal LDO instead of VDDD: check ER1\n");
+	} else {
+		/* using external LDO for VDDD
+		 * Clear startup powerup and simple powerup
+		 * bits to save power
+		 */
+		ana_pwr &= ~(SGTL5000_STARTUP_POWERUP
+			     | SGTL5000_LINREG_SIMPLE_POWERUP);
+		dev_dbg(&client->dev, "Using external VDDD\n");
+	}
+	ret = regmap_write(sgtl5000->regmap, SGTL5000_CHIP_ANA_POWER, ana_pwr);
+	if (ret)
+		dev_err(&client->dev,
+			"Error %d setting CHIP_ANA_POWER to %04x\n",
+			ret, ana_pwr);
+
 	if (np) {
 		if (!of_property_read_u32(np,
 			"micbias-resistor-k-ohms", &value)) {
@@ -1557,12 +1342,8 @@ static int sgtl5000_i2c_probe(struct i2c_client *client,
 		}
 	}
 
-	i2c_set_clientdata(client, sgtl5000);
-
 	/* Ensure sgtl5000 will start with sane register values */
-	ret = sgtl5000_fill_defaults(sgtl5000);
-	if (ret)
-		goto disable_clk;
+	sgtl5000_fill_defaults(client);
 
 	ret = snd_soc_register_codec(&client->dev,
 			&sgtl5000_driver, &sgtl5000_dai, 1);
@@ -1573,6 +1354,11 @@ static int sgtl5000_i2c_probe(struct i2c_client *client,
 
 disable_clk:
 	clk_disable_unprepare(sgtl5000->mclk);
+
+disable_regs:
+	regulator_bulk_disable(sgtl5000->num_supplies, sgtl5000->supplies);
+	regulator_bulk_free(sgtl5000->num_supplies, sgtl5000->supplies);
+
 	return ret;
 }
 
@@ -1582,6 +1368,9 @@ static int sgtl5000_i2c_remove(struct i2c_client *client)
 
 	snd_soc_unregister_codec(&client->dev);
 	clk_disable_unprepare(sgtl5000->mclk);
+	regulator_bulk_disable(sgtl5000->num_supplies, sgtl5000->supplies);
+	regulator_bulk_free(sgtl5000->num_supplies, sgtl5000->supplies);
+
 	return 0;
 }
 
diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h
index 1c317de26176..22f3442af982 100644
--- a/sound/soc/codecs/sgtl5000.h
+++ b/sound/soc/codecs/sgtl5000.h
@@ -92,6 +92,7 @@
 /*
  * SGTL5000_CHIP_CLK_CTRL
  */
+#define SGTL5000_CHIP_CLK_CTRL_DEFAULT		0x0008
 #define SGTL5000_RATE_MODE_MASK			0x0030
 #define SGTL5000_RATE_MODE_SHIFT		4
 #define SGTL5000_RATE_MODE_WIDTH		2
@@ -325,6 +326,7 @@
 /*
  * SGTL5000_CHIP_ANA_POWER
  */
+#define SGTL5000_ANA_POWER_DEFAULT		0x7060
 #define SGTL5000_DAC_STEREO			0x4000
 #define SGTL5000_LINREG_SIMPLE_POWERUP		0x2000
 #define SGTL5000_STARTUP_POWERUP		0x1000
diff --git a/sound/soc/codecs/tas571x.c b/sound/soc/codecs/tas571x.c
index b8d19b77bde9..d8baca3f8413 100644
--- a/sound/soc/codecs/tas571x.c
+++ b/sound/soc/codecs/tas571x.c
@@ -28,6 +28,7 @@
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
 #include <sound/tlv.h>
+#include <asm/unaligned.h>
 
 #include "tas571x.h"
 
@@ -63,6 +64,10 @@ static int tas571x_register_size(struct tas571x_private *priv, unsigned int reg)
 	case TAS571X_INPUT_MUX_REG:
 	case TAS571X_CH4_SRC_SELECT_REG:
 	case TAS571X_PWM_MUX_REG:
+	case TAS5717_CH1_RIGHT_CH_MIX_REG:
+	case TAS5717_CH1_LEFT_CH_MIX_REG:
+	case TAS5717_CH2_LEFT_CH_MIX_REG:
+	case TAS5717_CH2_RIGHT_CH_MIX_REG:
 		return 4;
 	default:
 		return 1;
@@ -135,6 +140,129 @@ static int tas571x_reg_read(void *context, unsigned int reg,
 	return 0;
 }
 
+/*
+ * register write for 8- and 20-byte registers
+ */
+static int tas571x_reg_write_multiword(struct i2c_client *client,
+		unsigned int reg, const long values[], size_t len)
+{
+	size_t i;
+	uint8_t *buf, *p;
+	int ret;
+	size_t send_size = 1 + len * sizeof(uint32_t);
+
+	buf = kzalloc(send_size, GFP_KERNEL | GFP_DMA);
+	if (!buf)
+		return -ENOMEM;
+	buf[0] = reg;
+
+	for (i = 0, p = buf + 1; i < len; i++, p += sizeof(uint32_t))
+		put_unaligned_be32(values[i], p);
+
+	ret = i2c_master_send(client, buf, send_size);
+
+	kfree(buf);
+
+	if (ret == send_size)
+		return 0;
+	else if (ret < 0)
+		return ret;
+	else
+		return -EIO;
+}
+
+/*
+ * register read for 8- and 20-byte registers
+ */
+static int tas571x_reg_read_multiword(struct i2c_client *client,
+		unsigned int reg, long values[], size_t len)
+{
+	unsigned int i;
+	uint8_t send_buf;
+	uint8_t *recv_buf, *p;
+	struct i2c_msg msgs[2];
+	unsigned int recv_size = len * sizeof(uint32_t);
+	int ret;
+
+	recv_buf = kzalloc(recv_size, GFP_KERNEL | GFP_DMA);
+	if (!recv_buf)
+		return -ENOMEM;
+
+	send_buf = reg;
+
+	msgs[0].addr = client->addr;
+	msgs[0].len = sizeof(send_buf);
+	msgs[0].buf = &send_buf;
+	msgs[0].flags = 0;
+
+	msgs[1].addr = client->addr;
+	msgs[1].len = recv_size;
+	msgs[1].buf = recv_buf;
+	msgs[1].flags = I2C_M_RD;
+
+	ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret < 0)
+		goto err_ret;
+	else if (ret != ARRAY_SIZE(msgs)) {
+		ret = -EIO;
+		goto err_ret;
+	}
+
+	for (i = 0, p = recv_buf; i < len; i++, p += sizeof(uint32_t))
+		values[i] = get_unaligned_be32(p);
+
+err_ret:
+	kfree(recv_buf);
+	return ret;
+}
+
+/*
+ * Integer array controls for setting biquad, mixer, DRC coefficients.
+ * According to the datasheet each coefficient is effectively 26bits,
+ * i.e. stored as 32bits, where bits [31:26] are ignored.
+ * TI's TAS57xx Graphical Development Environment tool however produces
+ * coefficients with more than 26 bits. For this reason we allow values
+ * in the full 32-bits reange.
+ * The coefficients are ordered as given in the TAS571x data sheet:
+ * b0, b1, b2, a1, a2
+ */
+
+static int tas571x_coefficient_info(struct snd_kcontrol *kcontrol,
+				   struct snd_ctl_elem_info *uinfo)
+{
+	int numcoef = kcontrol->private_value >> 16;
+
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
+	uinfo->count = numcoef;
+	uinfo->value.integer.min = 0;
+	uinfo->value.integer.max = 0xffffffff;
+	return 0;
+}
+
+static int tas571x_coefficient_get(struct snd_kcontrol *kcontrol,
+				  struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
+	struct i2c_client *i2c = to_i2c_client(codec->dev);
+	int numcoef = kcontrol->private_value >> 16;
+	int index = kcontrol->private_value & 0xffff;
+
+	return tas571x_reg_read_multiword(i2c, index,
+		ucontrol->value.integer.value, numcoef);
+}
+
+static int tas571x_coefficient_put(struct snd_kcontrol *kcontrol,
+				  struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
+	struct i2c_client *i2c = to_i2c_client(codec->dev);
+	int numcoef = kcontrol->private_value >> 16;
+	int index = kcontrol->private_value & 0xffff;
+
+	return tas571x_reg_write_multiword(i2c, index,
+		ucontrol->value.integer.value, numcoef);
+}
+
 static int tas571x_set_dai_fmt(struct snd_soc_dai *dai, unsigned int format)
 {
 	struct tas571x_private *priv = snd_soc_codec_get_drvdata(dai->codec);
@@ -241,6 +369,15 @@ static const struct snd_soc_dai_ops tas571x_dai_ops = {
 	.digital_mute	= tas571x_mute,
 };
 
+
+#define BIQUAD_COEFS(xname, reg) \
+{	.iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \
+	.info = tas571x_coefficient_info, \
+	.get = tas571x_coefficient_get,\
+	.put = tas571x_coefficient_put, \
+	.access = SNDRV_CTL_ELEM_ACCESS_READWRITE, \
+	.private_value = reg | (5 << 16) }
+
 static const char *const tas5711_supply_names[] = {
 	"AVDD",
 	"DVDD",
@@ -264,6 +401,16 @@ static const struct snd_kcontrol_new tas5711_controls[] = {
 		   TAS571X_SOFT_MUTE_REG,
 		   TAS571X_SOFT_MUTE_CH1_SHIFT, TAS571X_SOFT_MUTE_CH2_SHIFT,
 		   1, 1),
+
+	SOC_DOUBLE_R_RANGE("CH1 Mixer Volume",
+			   TAS5717_CH1_LEFT_CH_MIX_REG,
+			   TAS5717_CH1_RIGHT_CH_MIX_REG,
+			   16, 0, 0x80, 0),
+
+	SOC_DOUBLE_R_RANGE("CH2 Mixer Volume",
+			   TAS5717_CH2_LEFT_CH_MIX_REG,
+			   TAS5717_CH2_RIGHT_CH_MIX_REG,
+			   16, 0, 0x80, 0),
 };
 
 static const struct regmap_range tas571x_readonly_regs_range[] = {
@@ -340,6 +487,43 @@ static const struct snd_kcontrol_new tas5717_controls[] = {
 		   TAS571X_SOFT_MUTE_REG,
 		   TAS571X_SOFT_MUTE_CH1_SHIFT, TAS571X_SOFT_MUTE_CH2_SHIFT,
 		   1, 1),
+
+	/*
+	 * The biquads are named according to the register names.
+	 * Please note that TI's TAS57xx Graphical Development Environment
+	 * tool names them different.
+	 */
+	BIQUAD_COEFS("CH1 - Biquad 0", TAS5717_CH1_BQ0_REG),
+	BIQUAD_COEFS("CH1 - Biquad 1", TAS5717_CH1_BQ1_REG),
+	BIQUAD_COEFS("CH1 - Biquad 2", TAS5717_CH1_BQ2_REG),
+	BIQUAD_COEFS("CH1 - Biquad 3", TAS5717_CH1_BQ3_REG),
+	BIQUAD_COEFS("CH1 - Biquad 4", TAS5717_CH1_BQ4_REG),
+	BIQUAD_COEFS("CH1 - Biquad 5", TAS5717_CH1_BQ5_REG),
+	BIQUAD_COEFS("CH1 - Biquad 6", TAS5717_CH1_BQ6_REG),
+	BIQUAD_COEFS("CH1 - Biquad 7", TAS5717_CH1_BQ7_REG),
+	BIQUAD_COEFS("CH1 - Biquad 8", TAS5717_CH1_BQ8_REG),
+	BIQUAD_COEFS("CH1 - Biquad 9", TAS5717_CH1_BQ9_REG),
+	BIQUAD_COEFS("CH1 - Biquad 10", TAS5717_CH1_BQ10_REG),
+	BIQUAD_COEFS("CH1 - Biquad 11", TAS5717_CH1_BQ11_REG),
+
+	BIQUAD_COEFS("CH2 - Biquad 0", TAS5717_CH2_BQ0_REG),
+	BIQUAD_COEFS("CH2 - Biquad 1", TAS5717_CH2_BQ1_REG),
+	BIQUAD_COEFS("CH2 - Biquad 2", TAS5717_CH2_BQ2_REG),
+	BIQUAD_COEFS("CH2 - Biquad 3", TAS5717_CH2_BQ3_REG),
+	BIQUAD_COEFS("CH2 - Biquad 4", TAS5717_CH2_BQ4_REG),
+	BIQUAD_COEFS("CH2 - Biquad 5", TAS5717_CH2_BQ5_REG),
+	BIQUAD_COEFS("CH2 - Biquad 6", TAS5717_CH2_BQ6_REG),
+	BIQUAD_COEFS("CH2 - Biquad 7", TAS5717_CH2_BQ7_REG),
+	BIQUAD_COEFS("CH2 - Biquad 8", TAS5717_CH2_BQ8_REG),
+	BIQUAD_COEFS("CH2 - Biquad 9", TAS5717_CH2_BQ9_REG),
+	BIQUAD_COEFS("CH2 - Biquad 10", TAS5717_CH2_BQ10_REG),
+	BIQUAD_COEFS("CH2 - Biquad 11", TAS5717_CH2_BQ11_REG),
+
+	BIQUAD_COEFS("CH3 - Biquad 0", TAS5717_CH3_BQ0_REG),
+	BIQUAD_COEFS("CH3 - Biquad 1", TAS5717_CH3_BQ1_REG),
+
+	BIQUAD_COEFS("CH4 - Biquad 0", TAS5717_CH4_BQ0_REG),
+	BIQUAD_COEFS("CH4 - Biquad 1", TAS5717_CH4_BQ1_REG),
 };
 
 static const struct reg_default tas5717_reg_defaults[] = {
@@ -350,6 +534,10 @@ static const struct reg_default tas5717_reg_defaults[] = {
 	{ 0x08, 0x00c0 },
 	{ 0x09, 0x00c0 },
 	{ 0x1b, 0x82 },
+	{ TAS5717_CH1_RIGHT_CH_MIX_REG, 0x0 },
+	{ TAS5717_CH1_LEFT_CH_MIX_REG, 0x800000},
+	{ TAS5717_CH2_LEFT_CH_MIX_REG, 0x0 },
+	{ TAS5717_CH2_RIGHT_CH_MIX_REG, 0x800000},
 };
 
 static const struct regmap_config tas5717_regmap_config = {
diff --git a/sound/soc/codecs/tas571x.h b/sound/soc/codecs/tas571x.h
index cf800c364f0f..c45677bc26ad 100644
--- a/sound/soc/codecs/tas571x.h
+++ b/sound/soc/codecs/tas571x.h
@@ -52,4 +52,44 @@
 #define TAS571X_CH4_SRC_SELECT_REG	0x21
 #define TAS571X_PWM_MUX_REG		0x25
 
+/* 20-byte biquad registers */
+#define TAS5717_CH1_BQ0_REG		0x26
+#define TAS5717_CH1_BQ1_REG		0x27
+#define TAS5717_CH1_BQ2_REG		0x28
+#define TAS5717_CH1_BQ3_REG		0x29
+#define TAS5717_CH1_BQ4_REG		0x2a
+#define TAS5717_CH1_BQ5_REG		0x2b
+#define TAS5717_CH1_BQ6_REG		0x2c
+#define TAS5717_CH1_BQ7_REG		0x2d
+#define TAS5717_CH1_BQ8_REG		0x2e
+#define TAS5717_CH1_BQ9_REG		0x2f
+
+#define TAS5717_CH2_BQ0_REG		0x30
+#define TAS5717_CH2_BQ1_REG		0x31
+#define TAS5717_CH2_BQ2_REG		0x32
+#define TAS5717_CH2_BQ3_REG		0x33
+#define TAS5717_CH2_BQ4_REG		0x34
+#define TAS5717_CH2_BQ5_REG		0x35
+#define TAS5717_CH2_BQ6_REG		0x36
+#define TAS5717_CH2_BQ7_REG		0x37
+#define TAS5717_CH2_BQ8_REG		0x38
+#define TAS5717_CH2_BQ9_REG		0x39
+
+#define TAS5717_CH1_BQ10_REG		0x58
+#define TAS5717_CH1_BQ11_REG		0x59
+
+#define TAS5717_CH4_BQ0_REG		0x5a
+#define TAS5717_CH4_BQ1_REG		0x5b
+
+#define TAS5717_CH2_BQ10_REG		0x5c
+#define TAS5717_CH2_BQ11_REG		0x5d
+
+#define TAS5717_CH3_BQ0_REG		0x5e
+#define TAS5717_CH3_BQ1_REG		0x5f
+
+#define TAS5717_CH1_RIGHT_CH_MIX_REG	0x72
+#define TAS5717_CH1_LEFT_CH_MIX_REG	0x73
+#define TAS5717_CH2_LEFT_CH_MIX_REG	0x76
+#define TAS5717_CH2_RIGHT_CH_MIX_REG	0x77
+
 #endif /* _TAS571X_H */
diff --git a/sound/soc/codecs/tlv320aic31xx.h b/sound/soc/codecs/tlv320aic31xx.h
index fe16c34607bb..ac9b146526eb 100644
--- a/sound/soc/codecs/tlv320aic31xx.h
+++ b/sound/soc/codecs/tlv320aic31xx.h
@@ -38,141 +38,143 @@ struct aic31xx_pdata {
 	int micbias_vg;
 };
 
+#define AIC31XX_REG(page, reg)	((page * 128) + reg)
+
 /* Page Control Register */
-#define AIC31XX_PAGECTL				0x00
+#define AIC31XX_PAGECTL		AIC31XX_REG(0, 0)
 
 /* Page 0 Registers */
 /* Software reset register */
-#define AIC31XX_RESET				0x01
+#define AIC31XX_RESET		AIC31XX_REG(0, 1)
 /* OT FLAG register */
-#define AIC31XX_OT_FLAG				0x03
+#define AIC31XX_OT_FLAG		AIC31XX_REG(0, 3)
 /* Clock clock Gen muxing, Multiplexers*/
-#define AIC31XX_CLKMUX				0x04
+#define AIC31XX_CLKMUX		AIC31XX_REG(0, 4)
 /* PLL P and R-VAL register */
-#define AIC31XX_PLLPR				0x05
+#define AIC31XX_PLLPR		AIC31XX_REG(0, 5)
 /* PLL J-VAL register */
-#define AIC31XX_PLLJ				0x06
+#define AIC31XX_PLLJ		AIC31XX_REG(0, 6)
 /* PLL D-VAL MSB register */
-#define AIC31XX_PLLDMSB				0x07
+#define AIC31XX_PLLDMSB		AIC31XX_REG(0, 7)
 /* PLL D-VAL LSB register */
-#define AIC31XX_PLLDLSB				0x08
+#define AIC31XX_PLLDLSB		AIC31XX_REG(0, 8)
 /* DAC NDAC_VAL register*/
-#define AIC31XX_NDAC				0x0B
+#define AIC31XX_NDAC		AIC31XX_REG(0, 11)
 /* DAC MDAC_VAL register */
-#define AIC31XX_MDAC				0x0C
+#define AIC31XX_MDAC		AIC31XX_REG(0, 12)
 /* DAC OSR setting register 1, MSB value */
-#define AIC31XX_DOSRMSB				0x0D
+#define AIC31XX_DOSRMSB		AIC31XX_REG(0, 13)
 /* DAC OSR setting register 2, LSB value */
-#define AIC31XX_DOSRLSB				0x0E
-#define AIC31XX_MINI_DSP_INPOL			0x10
+#define AIC31XX_DOSRLSB		AIC31XX_REG(0, 14)
+#define AIC31XX_MINI_DSP_INPOL	AIC31XX_REG(0, 16)
 /* Clock setting register 8, PLL */
-#define AIC31XX_NADC				0x12
+#define AIC31XX_NADC		AIC31XX_REG(0, 18)
 /* Clock setting register 9, PLL */
-#define AIC31XX_MADC				0x13
+#define AIC31XX_MADC		AIC31XX_REG(0, 19)
 /* ADC Oversampling (AOSR) Register */
-#define AIC31XX_AOSR				0x14
+#define AIC31XX_AOSR		AIC31XX_REG(0, 20)
 /* Clock setting register 9, Multiplexers */
-#define AIC31XX_CLKOUTMUX			0x19
+#define AIC31XX_CLKOUTMUX	AIC31XX_REG(0, 25)
 /* Clock setting register 10, CLOCKOUT M divider value */
-#define AIC31XX_CLKOUTMVAL			0x1A
+#define AIC31XX_CLKOUTMVAL	AIC31XX_REG(0, 26)
 /* Audio Interface Setting Register 1 */
-#define AIC31XX_IFACE1				0x1B
+#define AIC31XX_IFACE1		AIC31XX_REG(0, 27)
 /* Audio Data Slot Offset Programming */
-#define AIC31XX_DATA_OFFSET			0x1C
+#define AIC31XX_DATA_OFFSET	AIC31XX_REG(0, 28)
 /* Audio Interface Setting Register 2 */
-#define AIC31XX_IFACE2				0x1D
+#define AIC31XX_IFACE2		AIC31XX_REG(0, 29)
 /* Clock setting register 11, BCLK N Divider */
-#define AIC31XX_BCLKN				0x1E
+#define AIC31XX_BCLKN		AIC31XX_REG(0, 30)
 /* Audio Interface Setting Register 3, Secondary Audio Interface */
-#define AIC31XX_IFACESEC1			0x1F
+#define AIC31XX_IFACESEC1	AIC31XX_REG(0, 31)
 /* Audio Interface Setting Register 4 */
-#define AIC31XX_IFACESEC2			0x20
+#define AIC31XX_IFACESEC2	AIC31XX_REG(0, 32)
 /* Audio Interface Setting Register 5 */
-#define AIC31XX_IFACESEC3			0x21
+#define AIC31XX_IFACESEC3	AIC31XX_REG(0, 33)
 /* I2C Bus Condition */
-#define AIC31XX_I2C				0x22
+#define AIC31XX_I2C		AIC31XX_REG(0, 34)
 /* ADC FLAG */
-#define AIC31XX_ADCFLAG				0x24
+#define AIC31XX_ADCFLAG		AIC31XX_REG(0, 36)
 /* DAC Flag Registers */
-#define AIC31XX_DACFLAG1			0x25
-#define AIC31XX_DACFLAG2			0x26
+#define AIC31XX_DACFLAG1	AIC31XX_REG(0, 37)
+#define AIC31XX_DACFLAG2	AIC31XX_REG(0, 38)
 /* Sticky Interrupt flag (overflow) */
-#define AIC31XX_OFFLAG				0x27
+#define AIC31XX_OFFLAG		AIC31XX_REG(0, 39)
 /* Sticy DAC Interrupt flags */
-#define AIC31XX_INTRDACFLAG			0x2C
+#define AIC31XX_INTRDACFLAG	AIC31XX_REG(0, 44)
 /* Sticy ADC Interrupt flags */
-#define AIC31XX_INTRADCFLAG			0x2D
+#define AIC31XX_INTRADCFLAG	AIC31XX_REG(0, 45)
 /* DAC Interrupt flags 2 */
-#define AIC31XX_INTRDACFLAG2			0x2E
+#define AIC31XX_INTRDACFLAG2	AIC31XX_REG(0, 46)
 /* ADC Interrupt flags 2 */
-#define AIC31XX_INTRADCFLAG2			0x2F
+#define AIC31XX_INTRADCFLAG2	AIC31XX_REG(0, 47)
 /* INT1 interrupt control */
-#define AIC31XX_INT1CTRL			0x30
+#define AIC31XX_INT1CTRL	AIC31XX_REG(0, 48)
 /* INT2 interrupt control */
-#define AIC31XX_INT2CTRL			0x31
+#define AIC31XX_INT2CTRL	AIC31XX_REG(0, 49)
 /* GPIO1 control */
-#define AIC31XX_GPIO1				0x33
+#define AIC31XX_GPIO1		AIC31XX_REG(0, 50)
 
-#define AIC31XX_DACPRB				0x3C
+#define AIC31XX_DACPRB		AIC31XX_REG(0, 60)
 /* ADC Instruction Set Register */
-#define AIC31XX_ADCPRB				0x3D
+#define AIC31XX_ADCPRB		AIC31XX_REG(0, 61)
 /* DAC channel setup register */
-#define AIC31XX_DACSETUP			0x3F
+#define AIC31XX_DACSETUP	AIC31XX_REG(0, 63)
 /* DAC Mute and volume control register */
-#define AIC31XX_DACMUTE				0x40
+#define AIC31XX_DACMUTE		AIC31XX_REG(0, 64)
 /* Left DAC channel digital volume control */
-#define AIC31XX_LDACVOL				0x41
+#define AIC31XX_LDACVOL		AIC31XX_REG(0, 65)
 /* Right DAC channel digital volume control */
-#define AIC31XX_RDACVOL				0x42
+#define AIC31XX_RDACVOL		AIC31XX_REG(0, 66)
 /* Headset detection */
-#define AIC31XX_HSDETECT			0x43
+#define AIC31XX_HSDETECT	AIC31XX_REG(0, 67)
 /* ADC Digital Mic */
-#define AIC31XX_ADCSETUP			0x51
+#define AIC31XX_ADCSETUP	AIC31XX_REG(0, 81)
 /* ADC Digital Volume Control Fine Adjust */
-#define AIC31XX_ADCFGA				0x52
+#define AIC31XX_ADCFGA		AIC31XX_REG(0, 82)
 /* ADC Digital Volume Control Coarse Adjust */
-#define AIC31XX_ADCVOL				0x53
+#define AIC31XX_ADCVOL		AIC31XX_REG(0, 83)
 
 
 /* Page 1 Registers */
 /* Headphone drivers */
-#define AIC31XX_HPDRIVER			0x9F
+#define AIC31XX_HPDRIVER	AIC31XX_REG(1, 31)
 /* Class-D Speakear Amplifier */
-#define AIC31XX_SPKAMP				0xA0
+#define AIC31XX_SPKAMP		AIC31XX_REG(1, 32)
 /* HP Output Drivers POP Removal Settings */
-#define AIC31XX_HPPOP				0xA1
+#define AIC31XX_HPPOP		AIC31XX_REG(1, 33)
 /* Output Driver PGA Ramp-Down Period Control */
-#define AIC31XX_SPPGARAMP			0xA2
+#define AIC31XX_SPPGARAMP	AIC31XX_REG(1, 34)
 /* DAC_L and DAC_R Output Mixer Routing */
-#define AIC31XX_DACMIXERROUTE			0xA3
+#define AIC31XX_DACMIXERROUTE	AIC31XX_REG(1, 35)
 /* Left Analog Vol to HPL */
-#define AIC31XX_LANALOGHPL			0xA4
+#define AIC31XX_LANALOGHPL	AIC31XX_REG(1, 36)
 /* Right Analog Vol to HPR */
-#define AIC31XX_RANALOGHPR			0xA5
+#define AIC31XX_RANALOGHPR	AIC31XX_REG(1, 37)
 /* Left Analog Vol to SPL */
-#define AIC31XX_LANALOGSPL			0xA6
+#define AIC31XX_LANALOGSPL	AIC31XX_REG(1, 38)
 /* Right Analog Vol to SPR */
-#define AIC31XX_RANALOGSPR			0xA7
+#define AIC31XX_RANALOGSPR	AIC31XX_REG(1, 39)
 /* HPL Driver */
-#define AIC31XX_HPLGAIN				0xA8
+#define AIC31XX_HPLGAIN		AIC31XX_REG(1, 40)
 /* HPR Driver */
-#define AIC31XX_HPRGAIN				0xA9
+#define AIC31XX_HPRGAIN		AIC31XX_REG(1, 41)
 /* SPL Driver */
-#define AIC31XX_SPLGAIN				0xAA
+#define AIC31XX_SPLGAIN		AIC31XX_REG(1, 42)
 /* SPR Driver */
-#define AIC31XX_SPRGAIN				0xAB
+#define AIC31XX_SPRGAIN		AIC31XX_REG(1, 43)
 /* HP Driver Control */
-#define AIC31XX_HPCONTROL			0xAC
+#define AIC31XX_HPCONTROL	AIC31XX_REG(1, 44)
 /* MIC Bias Control */
-#define AIC31XX_MICBIAS				0xAE
+#define AIC31XX_MICBIAS		AIC31XX_REG(1, 46)
 /* MIC PGA*/
-#define AIC31XX_MICPGA				0xAF
+#define AIC31XX_MICPGA		AIC31XX_REG(1, 47)
 /* Delta-Sigma Mono ADC Channel Fine-Gain Input Selection for P-Terminal */
-#define AIC31XX_MICPGAPI			0xB0
+#define AIC31XX_MICPGAPI	AIC31XX_REG(1, 48)
 /* ADC Input Selection for M-Terminal */
-#define AIC31XX_MICPGAMI			0xB1
+#define AIC31XX_MICPGAMI	AIC31XX_REG(1, 49)
 /* Input CM Settings */
-#define AIC31XX_MICPGACM			0xB2
+#define AIC31XX_MICPGACM	AIC31XX_REG(1, 50)
 
 /* Bits, masks and shifts */
 
diff --git a/sound/soc/codecs/tpa6130a2.c b/sound/soc/codecs/tpa6130a2.c
index 11d85c5c787a..f1ea052a822e 100644
--- a/sound/soc/codecs/tpa6130a2.c
+++ b/sound/soc/codecs/tpa6130a2.c
@@ -32,6 +32,7 @@
 #include <sound/tlv.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
+#include <linux/regmap.h>
 
 #include "tpa6130a2.h"
 
@@ -40,219 +41,72 @@ enum tpa_model {
 	TPA6140A2,
 };
 
-static struct i2c_client *tpa6130a2_client;
-
 /* This struct is used to save the context */
 struct tpa6130a2_data {
-	struct mutex mutex;
-	unsigned char regs[TPA6130A2_CACHEREGNUM];
+	struct device *dev;
+	struct regmap *regmap;
 	struct regulator *supply;
 	int power_gpio;
-	u8 power_state:1;
 	enum tpa_model id;
 };
 
-static int tpa6130a2_i2c_read(int reg)
-{
-	struct tpa6130a2_data *data;
-	int val;
-
-	if (WARN_ON(!tpa6130a2_client))
-		return -EINVAL;
-	data = i2c_get_clientdata(tpa6130a2_client);
-
-	/* If powered off, return the cached value */
-	if (data->power_state) {
-		val = i2c_smbus_read_byte_data(tpa6130a2_client, reg);
-		if (val < 0)
-			dev_err(&tpa6130a2_client->dev, "Read failed\n");
-		else
-			data->regs[reg] = val;
-	} else {
-		val = data->regs[reg];
-	}
-
-	return val;
-}
-
-static int tpa6130a2_i2c_write(int reg, u8 value)
-{
-	struct tpa6130a2_data *data;
-	int val = 0;
-
-	if (WARN_ON(!tpa6130a2_client))
-		return -EINVAL;
-	data = i2c_get_clientdata(tpa6130a2_client);
-
-	if (data->power_state) {
-		val = i2c_smbus_write_byte_data(tpa6130a2_client, reg, value);
-		if (val < 0) {
-			dev_err(&tpa6130a2_client->dev, "Write failed\n");
-			return val;
-		}
-	}
-
-	/* Either powered on or off, we save the context */
-	data->regs[reg] = value;
-
-	return val;
-}
-
-static u8 tpa6130a2_read(int reg)
-{
-	struct tpa6130a2_data *data;
-
-	if (WARN_ON(!tpa6130a2_client))
-		return 0;
-	data = i2c_get_clientdata(tpa6130a2_client);
-
-	return data->regs[reg];
-}
-
-static int tpa6130a2_initialize(void)
-{
-	struct tpa6130a2_data *data;
-	int i, ret = 0;
-
-	if (WARN_ON(!tpa6130a2_client))
-		return -EINVAL;
-	data = i2c_get_clientdata(tpa6130a2_client);
-
-	for (i = 1; i < TPA6130A2_REG_VERSION; i++) {
-		ret = tpa6130a2_i2c_write(i, data->regs[i]);
-		if (ret < 0)
-			break;
-	}
-
-	return ret;
-}
-
-static int tpa6130a2_power(u8 power)
+static int tpa6130a2_power(struct tpa6130a2_data *data, bool enable)
 {
-	struct	tpa6130a2_data *data;
-	u8	val;
-	int	ret = 0;
-
-	if (WARN_ON(!tpa6130a2_client))
-		return -EINVAL;
-	data = i2c_get_clientdata(tpa6130a2_client);
-
-	mutex_lock(&data->mutex);
-	if (power == data->power_state)
-		goto exit;
+	int ret;
 
-	if (power) {
+	if (enable) {
 		ret = regulator_enable(data->supply);
 		if (ret != 0) {
-			dev_err(&tpa6130a2_client->dev,
+			dev_err(data->dev,
 				"Failed to enable supply: %d\n", ret);
-			goto exit;
+			return ret;
 		}
 		/* Power on */
 		if (data->power_gpio >= 0)
 			gpio_set_value(data->power_gpio, 1);
-
-		data->power_state = 1;
-		ret = tpa6130a2_initialize();
-		if (ret < 0) {
-			dev_err(&tpa6130a2_client->dev,
-				"Failed to initialize chip\n");
-			if (data->power_gpio >= 0)
-				gpio_set_value(data->power_gpio, 0);
-			regulator_disable(data->supply);
-			data->power_state = 0;
-			goto exit;
-		}
 	} else {
-		/* set SWS */
-		val = tpa6130a2_read(TPA6130A2_REG_CONTROL);
-		val |= TPA6130A2_SWS;
-		tpa6130a2_i2c_write(TPA6130A2_REG_CONTROL, val);
-
 		/* Power off */
 		if (data->power_gpio >= 0)
 			gpio_set_value(data->power_gpio, 0);
 
 		ret = regulator_disable(data->supply);
 		if (ret != 0) {
-			dev_err(&tpa6130a2_client->dev,
+			dev_err(data->dev,
 				"Failed to disable supply: %d\n", ret);
-			goto exit;
+			return ret;
 		}
 
-		data->power_state = 0;
+		/* device regs does not match the cache state anymore */
+		regcache_mark_dirty(data->regmap);
 	}
 
-exit:
-	mutex_unlock(&data->mutex);
 	return ret;
 }
 
-static int tpa6130a2_get_volsw(struct snd_kcontrol *kcontrol,
-		struct snd_ctl_elem_value *ucontrol)
+static int tpa6130a2_power_event(struct snd_soc_dapm_widget *w,
+				 struct snd_kcontrol *kctrl, int event)
 {
-	struct soc_mixer_control *mc =
-		(struct soc_mixer_control *)kcontrol->private_value;
-	struct tpa6130a2_data *data;
-	unsigned int reg = mc->reg;
-	unsigned int shift = mc->shift;
-	int max = mc->max;
-	unsigned int mask = (1 << fls(max)) - 1;
-	unsigned int invert = mc->invert;
-
-	if (WARN_ON(!tpa6130a2_client))
-		return -EINVAL;
-	data = i2c_get_clientdata(tpa6130a2_client);
-
-	mutex_lock(&data->mutex);
-
-	ucontrol->value.integer.value[0] =
-		(tpa6130a2_read(reg) >> shift) & mask;
-
-	if (invert)
-		ucontrol->value.integer.value[0] =
-			max - ucontrol->value.integer.value[0];
-
-	mutex_unlock(&data->mutex);
-	return 0;
-}
+	struct snd_soc_component *c = snd_soc_dapm_to_component(w->dapm);
+	struct tpa6130a2_data *data = snd_soc_component_get_drvdata(c);
+	int ret;
 
-static int tpa6130a2_put_volsw(struct snd_kcontrol *kcontrol,
-		struct snd_ctl_elem_value *ucontrol)
-{
-	struct soc_mixer_control *mc =
-		(struct soc_mixer_control *)kcontrol->private_value;
-	struct tpa6130a2_data *data;
-	unsigned int reg = mc->reg;
-	unsigned int shift = mc->shift;
-	int max = mc->max;
-	unsigned int mask = (1 << fls(max)) - 1;
-	unsigned int invert = mc->invert;
-	unsigned int val = (ucontrol->value.integer.value[0] & mask);
-	unsigned int val_reg;
-
-	if (WARN_ON(!tpa6130a2_client))
-		return -EINVAL;
-	data = i2c_get_clientdata(tpa6130a2_client);
-
-	if (invert)
-		val = max - val;
-
-	mutex_lock(&data->mutex);
-
-	val_reg = tpa6130a2_read(reg);
-	if (((val_reg >> shift) & mask) == val) {
-		mutex_unlock(&data->mutex);
-		return 0;
+	/* before widget power up */
+	if (SND_SOC_DAPM_EVENT_ON(event)) {
+		/* Turn on the chip */
+		tpa6130a2_power(data, true);
+		/* Sync the registers */
+		ret = regcache_sync(data->regmap);
+		if (ret < 0) {
+			dev_err(c->dev, "Failed to initialize chip\n");
+			tpa6130a2_power(data, false);
+			return ret;
+		}
+	/* after widget power down */
+	} else {
+		tpa6130a2_power(data, false);
 	}
 
-	val_reg &= ~(mask << shift);
-	val_reg |= val << shift;
-	tpa6130a2_i2c_write(reg, val_reg);
-
-	mutex_unlock(&data->mutex);
-
-	return 1;
+	return 0;
 }
 
 /*
@@ -273,9 +127,8 @@ static const DECLARE_TLV_DB_RANGE(tpa6130_tlv,
 );
 
 static const struct snd_kcontrol_new tpa6130a2_controls[] = {
-	SOC_SINGLE_EXT_TLV("TPA6130A2 Headphone Playback Volume",
+	SOC_SINGLE_TLV("Headphone Playback Volume",
 		       TPA6130A2_REG_VOL_MUTE, 0, 0x3f, 0,
-		       tpa6130a2_get_volsw, tpa6130a2_put_volsw,
 		       tpa6130_tlv),
 };
 
@@ -286,85 +139,79 @@ static const DECLARE_TLV_DB_RANGE(tpa6140_tlv,
 );
 
 static const struct snd_kcontrol_new tpa6140a2_controls[] = {
-	SOC_SINGLE_EXT_TLV("TPA6140A2 Headphone Playback Volume",
+	SOC_SINGLE_TLV("Headphone Playback Volume",
 		       TPA6130A2_REG_VOL_MUTE, 1, 0x1f, 0,
-		       tpa6130a2_get_volsw, tpa6130a2_put_volsw,
 		       tpa6140_tlv),
 };
 
-/*
- * Enable or disable channel (left or right)
- * The bit number for mute and amplifier are the same per channel:
- * bit 6: Right channel
- * bit 7: Left channel
- * in both registers.
- */
-static void tpa6130a2_channel_enable(u8 channel, int enable)
+static int tpa6130a2_component_probe(struct snd_soc_component *component)
 {
-	u8	val;
+	struct tpa6130a2_data *data = snd_soc_component_get_drvdata(component);
 
-	if (enable) {
-		/* Enable channel */
-		/* Enable amplifier */
-		val = tpa6130a2_read(TPA6130A2_REG_CONTROL);
-		val |= channel;
-		val &= ~TPA6130A2_SWS;
-		tpa6130a2_i2c_write(TPA6130A2_REG_CONTROL, val);
-
-		/* Unmute channel */
-		val = tpa6130a2_read(TPA6130A2_REG_VOL_MUTE);
-		val &= ~channel;
-		tpa6130a2_i2c_write(TPA6130A2_REG_VOL_MUTE, val);
-	} else {
-		/* Disable channel */
-		/* Mute channel */
-		val = tpa6130a2_read(TPA6130A2_REG_VOL_MUTE);
-		val |= channel;
-		tpa6130a2_i2c_write(TPA6130A2_REG_VOL_MUTE, val);
-
-		/* Disable amplifier */
-		val = tpa6130a2_read(TPA6130A2_REG_CONTROL);
-		val &= ~channel;
-		tpa6130a2_i2c_write(TPA6130A2_REG_CONTROL, val);
-	}
+	if (data->id == TPA6140A2)
+		return snd_soc_add_component_controls(component,
+			tpa6140a2_controls, ARRAY_SIZE(tpa6140a2_controls));
+	else
+		return snd_soc_add_component_controls(component,
+			tpa6130a2_controls, ARRAY_SIZE(tpa6130a2_controls));
 }
 
-int tpa6130a2_stereo_enable(struct snd_soc_codec *codec, int enable)
-{
-	int ret = 0;
-	if (enable) {
-		ret = tpa6130a2_power(1);
-		if (ret < 0)
-			return ret;
-		tpa6130a2_channel_enable(TPA6130A2_HP_EN_R | TPA6130A2_HP_EN_L,
-					 1);
-	} else {
-		tpa6130a2_channel_enable(TPA6130A2_HP_EN_R | TPA6130A2_HP_EN_L,
-					 0);
-		ret = tpa6130a2_power(0);
-	}
+static const struct snd_soc_dapm_widget tpa6130a2_dapm_widgets[] = {
+	SND_SOC_DAPM_INPUT("LEFTIN"),
+	SND_SOC_DAPM_INPUT("RIGHTIN"),
+	SND_SOC_DAPM_OUTPUT("HPLEFT"),
+	SND_SOC_DAPM_OUTPUT("HPRIGHT"),
+
+	SND_SOC_DAPM_PGA("Left Mute", TPA6130A2_REG_VOL_MUTE,
+			 TPA6130A2_HP_EN_L_SHIFT, 1, NULL, 0),
+	SND_SOC_DAPM_PGA("Right Mute", TPA6130A2_REG_VOL_MUTE,
+			 TPA6130A2_HP_EN_R_SHIFT, 1, NULL, 0),
+	SND_SOC_DAPM_PGA("Left PGA", TPA6130A2_REG_CONTROL,
+			 TPA6130A2_HP_EN_L_SHIFT, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("Right PGA", TPA6130A2_REG_CONTROL,
+			 TPA6130A2_HP_EN_R_SHIFT, 0, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("Power", TPA6130A2_REG_CONTROL,
+			    TPA6130A2_SWS_SHIFT, 1, tpa6130a2_power_event,
+			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
+};
 
-	return ret;
-}
-EXPORT_SYMBOL_GPL(tpa6130a2_stereo_enable);
+static const struct snd_soc_dapm_route tpa6130a2_dapm_routes[] = {
+	{ "Left PGA", NULL, "LEFTIN" },
+	{ "Right PGA", NULL, "RIGHTIN" },
 
-int tpa6130a2_add_controls(struct snd_soc_codec *codec)
-{
-	struct	tpa6130a2_data *data;
+	{ "Left Mute", NULL, "Left PGA" },
+	{ "Right Mute", NULL, "Right PGA" },
 
-	if (tpa6130a2_client == NULL)
-		return -ENODEV;
+	{ "HPLEFT", NULL, "Left Mute" },
+	{ "HPRIGHT", NULL, "Right Mute" },
 
-	data = i2c_get_clientdata(tpa6130a2_client);
+	{ "Left PGA", NULL, "Power" },
+	{ "Right PGA", NULL, "Power" },
+};
 
-	if (data->id == TPA6140A2)
-		return snd_soc_add_codec_controls(codec, tpa6140a2_controls,
-						ARRAY_SIZE(tpa6140a2_controls));
-	else
-		return snd_soc_add_codec_controls(codec, tpa6130a2_controls,
-						ARRAY_SIZE(tpa6130a2_controls));
-}
-EXPORT_SYMBOL_GPL(tpa6130a2_add_controls);
+struct snd_soc_component_driver tpa6130a2_component_driver = {
+	.name = "tpa6130a2",
+	.probe = tpa6130a2_component_probe,
+	.dapm_widgets = tpa6130a2_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(tpa6130a2_dapm_widgets),
+	.dapm_routes = tpa6130a2_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(tpa6130a2_dapm_routes),
+};
+
+static const struct reg_default tpa6130a2_reg_defaults[] = {
+	{ TPA6130A2_REG_CONTROL, TPA6130A2_SWS },
+	{ TPA6130A2_REG_VOL_MUTE, TPA6130A2_MUTE_R | TPA6130A2_MUTE_L },
+};
+
+static const struct regmap_config tpa6130a2_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = TPA6130A2_REG_VERSION,
+	.reg_defaults = tpa6130a2_reg_defaults,
+	.num_reg_defaults = ARRAY_SIZE(tpa6130a2_reg_defaults),
+	.cache_type = REGCACHE_RBTREE,
+};
 
 static int tpa6130a2_probe(struct i2c_client *client,
 			   const struct i2c_device_id *id)
@@ -374,6 +221,7 @@ static int tpa6130a2_probe(struct i2c_client *client,
 	struct tpa6130a2_platform_data *pdata = client->dev.platform_data;
 	struct device_node *np = client->dev.of_node;
 	const char *regulator;
+	unsigned int version;
 	int ret;
 
 	dev = &client->dev;
@@ -382,6 +230,12 @@ static int tpa6130a2_probe(struct i2c_client *client,
 	if (!data)
 		return -ENOMEM;
 
+	data->dev = dev;
+
+	data->regmap = devm_regmap_init_i2c(client, &tpa6130a2_regmap_config);
+	if (IS_ERR(data->regmap))
+		return PTR_ERR(data->regmap);
+
 	if (pdata) {
 		data->power_gpio = pdata->power_gpio;
 	} else if (np) {
@@ -392,26 +246,17 @@ static int tpa6130a2_probe(struct i2c_client *client,
 		return -ENODEV;
 	}
 
-	tpa6130a2_client = client;
-
-	i2c_set_clientdata(tpa6130a2_client, data);
+	i2c_set_clientdata(client, data);
 
 	data->id = id->driver_data;
 
-	mutex_init(&data->mutex);
-
-	/* Set default register values */
-	data->regs[TPA6130A2_REG_CONTROL] =	TPA6130A2_SWS;
-	data->regs[TPA6130A2_REG_VOL_MUTE] =	TPA6130A2_MUTE_R |
-						TPA6130A2_MUTE_L;
-
 	if (data->power_gpio >= 0) {
 		ret = devm_gpio_request(dev, data->power_gpio,
 					"tpa6130a2 enable");
 		if (ret < 0) {
 			dev_err(dev, "Failed to request power GPIO (%d)\n",
 				data->power_gpio);
-			goto err_gpio;
+			return ret;
 		}
 		gpio_direction_output(data->power_gpio, 0);
 	}
@@ -432,39 +277,27 @@ static int tpa6130a2_probe(struct i2c_client *client,
 	if (IS_ERR(data->supply)) {
 		ret = PTR_ERR(data->supply);
 		dev_err(dev, "Failed to request supply: %d\n", ret);
-		goto err_gpio;
+		return ret;
 	}
 
-	ret = tpa6130a2_power(1);
+	ret = tpa6130a2_power(data, true);
 	if (ret != 0)
-		goto err_gpio;
+		return ret;
 
 
 	/* Read version */
-	ret = tpa6130a2_i2c_read(TPA6130A2_REG_VERSION) &
-				 TPA6130A2_VERSION_MASK;
-	if ((ret != 1) && (ret != 2))
-		dev_warn(dev, "UNTESTED version detected (%d)\n", ret);
+	regmap_read(data->regmap, TPA6130A2_REG_VERSION, &version);
+	version &= TPA6130A2_VERSION_MASK;
+	if ((version != 1) && (version != 2))
+		dev_warn(dev, "UNTESTED version detected (%d)\n", version);
 
 	/* Disable the chip */
-	ret = tpa6130a2_power(0);
+	ret = tpa6130a2_power(data, false);
 	if (ret != 0)
-		goto err_gpio;
-
-	return 0;
-
-err_gpio:
-	tpa6130a2_client = NULL;
+		return ret;
 
-	return ret;
-}
-
-static int tpa6130a2_remove(struct i2c_client *client)
-{
-	tpa6130a2_power(0);
-	tpa6130a2_client = NULL;
-
-	return 0;
+	return devm_snd_soc_register_component(&client->dev,
+			&tpa6130a2_component_driver, NULL, 0);
 }
 
 static const struct i2c_device_id tpa6130a2_id[] = {
@@ -489,7 +322,6 @@ static struct i2c_driver tpa6130a2_i2c_driver = {
 		.of_match_table = of_match_ptr(tpa6130a2_of_match),
 	},
 	.probe = tpa6130a2_probe,
-	.remove = tpa6130a2_remove,
 	.id_table = tpa6130a2_id,
 };
 
diff --git a/sound/soc/codecs/tpa6130a2.h b/sound/soc/codecs/tpa6130a2.h
index 417444020ba6..f19cad5d4172 100644
--- a/sound/soc/codecs/tpa6130a2.h
+++ b/sound/soc/codecs/tpa6130a2.h
@@ -30,19 +30,20 @@
 #define TPA6130A2_REG_OUT_IMPEDANCE	0x03
 #define TPA6130A2_REG_VERSION		0x04
 
-#define TPA6130A2_CACHEREGNUM	(TPA6130A2_REG_VERSION + 1)
-
 /* Register bits */
 /* TPA6130A2_REG_CONTROL (0x01) */
-#define TPA6130A2_SWS			(0x01 << 0)
+#define TPA6130A2_SWS_SHIFT		0
+#define TPA6130A2_SWS			(0x01 << TPA6130A2_SWS_SHIFT)
 #define TPA6130A2_TERMAL		(0x01 << 1)
 #define TPA6130A2_MODE(x)		(x << 4)
 #define TPA6130A2_MODE_STEREO		(0x00)
 #define TPA6130A2_MODE_DUAL_MONO	(0x01)
 #define TPA6130A2_MODE_BRIDGE		(0x02)
 #define TPA6130A2_MODE_MASK		(0x03)
-#define TPA6130A2_HP_EN_R		(0x01 << 6)
-#define TPA6130A2_HP_EN_L		(0x01 << 7)
+#define TPA6130A2_HP_EN_R_SHIFT		6
+#define TPA6130A2_HP_EN_R		(0x01 << TPA6130A2_HP_EN_R_SHIFT)
+#define TPA6130A2_HP_EN_L_SHIFT		7
+#define TPA6130A2_HP_EN_L		(0x01 << TPA6130A2_HP_EN_L_SHIFT)
 
 /* TPA6130A2_REG_VOL_MUTE (0x02) */
 #define TPA6130A2_VOLUME(x)		((x & 0x3f) << 0)
@@ -56,7 +57,4 @@
 /* TPA6130A2_REG_VERSION (0x04) */
 #define TPA6130A2_VERSION_MASK		(0x0f)
 
-extern int tpa6130a2_add_controls(struct snd_soc_codec *codec);
-extern int tpa6130a2_stereo_enable(struct snd_soc_codec *codec, int enable);
-
 #endif /* __TPA6130A2_H__ */
diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c
index e7fe6b7b95b7..846deed6af41 100644
--- a/sound/soc/codecs/wm5102.c
+++ b/sound/soc/codecs/wm5102.c
@@ -1713,6 +1713,7 @@ static const struct snd_soc_dapm_route wm5102_dapm_routes[] = {
 
 	{ "MICSUPP", NULL, "SYSCLK" },
 
+	{ "DRC1 Signal Activity", NULL, "SYSCLK" },
 	{ "DRC1 Signal Activity", NULL, "DRC1L" },
 	{ "DRC1 Signal Activity", NULL, "DRC1R" },
 };
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index d54f1b46c9ec..156547026a40 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -1104,6 +1104,11 @@ SND_SOC_DAPM_INPUT("IN4R"),
 SND_SOC_DAPM_OUTPUT("DRC1 Signal Activity"),
 SND_SOC_DAPM_OUTPUT("DRC2 Signal Activity"),
 
+SND_SOC_DAPM_OUTPUT("DSP Voice Trigger"),
+
+SND_SOC_DAPM_SWITCH("DSP3 Voice Trigger", SND_SOC_NOPM, 2, 0,
+		    &arizona_voice_trigger_switch[2]),
+
 SND_SOC_DAPM_PGA_E("IN1L PGA", ARIZONA_INPUT_ENABLES, ARIZONA_IN1L_ENA_SHIFT,
 		   0, NULL, 0, wm5110_in_ev,
 		   SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMD |
@@ -1998,10 +2003,16 @@ static const struct snd_soc_dapm_route wm5110_dapm_routes[] = {
 
 	{ "MICSUPP", NULL, "SYSCLK" },
 
+	{ "DRC1 Signal Activity", NULL, "SYSCLK" },
+	{ "DRC2 Signal Activity", NULL, "SYSCLK" },
 	{ "DRC1 Signal Activity", NULL, "DRC1L" },
 	{ "DRC1 Signal Activity", NULL, "DRC1R" },
 	{ "DRC2 Signal Activity", NULL, "DRC2L" },
 	{ "DRC2 Signal Activity", NULL, "DRC2R" },
+
+	{ "DSP Voice Trigger", NULL, "SYSCLK" },
+	{ "DSP Voice Trigger", NULL, "DSP3 Voice Trigger" },
+	{ "DSP3 Voice Trigger", "Switch", "DSP3" },
 };
 
 static int wm5110_set_fll(struct snd_soc_codec *codec, int fll_id, int source,
@@ -2223,6 +2234,7 @@ static irqreturn_t wm5110_adsp2_irq(int irq, void *data)
 {
 	struct wm5110_priv *priv = data;
 	struct arizona *arizona = priv->core.arizona;
+	struct arizona_voice_trigger_info info;
 	int serviced = 0;
 	int i, ret;
 
@@ -2230,6 +2242,12 @@ static irqreturn_t wm5110_adsp2_irq(int irq, void *data)
 		ret = wm_adsp_compr_handle_irq(&priv->core.adsp[i]);
 		if (ret != -ENODEV)
 			serviced++;
+		if (ret == WM_ADSP_COMPR_VOICE_TRIGGER) {
+			info.core = i;
+			arizona_call_notifiers(arizona,
+					       ARIZONA_NOTIFY_VOICE_TRIGGER,
+					       &info);
+		}
 	}
 
 	if (!serviced) {
@@ -2252,6 +2270,7 @@ static int wm5110_codec_probe(struct snd_soc_codec *codec)
 	arizona_init_spk(codec);
 	arizona_init_gpio(codec);
 	arizona_init_mono(codec);
+	arizona_init_notifiers(codec);
 
 	ret = arizona_request_irq(arizona, ARIZONA_IRQ_DSP_IRQ1,
 				  "ADSP2 Compressed IRQ", wm5110_adsp2_irq,
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index 4bcf5f8ece50..d18261a44256 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -358,6 +358,9 @@ static int wm8731_hw_params(struct snd_pcm_substream *substream,
 	case 24:
 		iface |= 0x0008;
 		break;
+	case 32:
+		iface |= 0x000c;
+		break;
 	}
 
 	wm8731_set_deemph(codec);
@@ -541,7 +544,7 @@ static int wm8731_startup(struct snd_pcm_substream *substream,
 #define WM8731_RATES SNDRV_PCM_RATE_8000_96000
 
 #define WM8731_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE |\
-	SNDRV_PCM_FMTBIT_S24_LE)
+	SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S32_LE)
 
 static const struct snd_soc_dai_ops wm8731_dai_ops = {
 	.startup	= wm8731_startup,
diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c
index 6f1024f48b19..cdcc91282e8a 100644
--- a/sound/soc/codecs/wm8753.c
+++ b/sound/soc/codecs/wm8753.c
@@ -32,7 +32,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/moduleparam.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/delay.h>
@@ -486,7 +485,7 @@ SND_SOC_DAPM_DAC("Voice DAC", "Voice Playback", WM8753_PWR1, 4, 0),
 SND_SOC_DAPM_OUTPUT("MONO1"),
 SND_SOC_DAPM_MUX("Mono 2 Mux", SND_SOC_NOPM, 0, 0, &wm8753_mono2_controls),
 SND_SOC_DAPM_OUTPUT("MONO2"),
-SND_SOC_DAPM_MIXER("Out3 Left + Right", -1, 0, 0, NULL, 0),
+SND_SOC_DAPM_MIXER("Out3 Left + Right", SND_SOC_NOPM, 0, 0, NULL, 0),
 SND_SOC_DAPM_MUX("Out3 Mux", SND_SOC_NOPM, 0, 0, &wm8753_out3_controls),
 SND_SOC_DAPM_PGA("Out 3", WM8753_PWR3, 4, 0, NULL, 0),
 SND_SOC_DAPM_OUTPUT("OUT3"),
diff --git a/sound/soc/codecs/wm8985.c b/sound/soc/codecs/wm8985.c
index 6ac76fe116b0..7347abff4b2c 100644
--- a/sound/soc/codecs/wm8985.c
+++ b/sound/soc/codecs/wm8985.c
@@ -1,10 +1,13 @@
 /*
- * wm8985.c  --  WM8985 ALSA SoC Audio driver
+ * wm8985.c  --  WM8985 / WM8758 ALSA SoC Audio driver
  *
  * Copyright 2010 Wolfson Microelectronics plc
- *
  * Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
  *
+ * WM8758 support:
+ * Copyright: 2016 Barix AG
+ * Author: Petr Kulhavy <petr@barix.com>
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
@@ -40,6 +43,11 @@ static const char *wm8985_supply_names[WM8985_NUM_SUPPLIES] = {
 	"AVDD2"
 };
 
+enum wm8985_type {
+	WM8985,
+	WM8758,
+};
+
 static const struct reg_default wm8985_reg_defaults[] = {
 	{ 1,  0x0000 },     /* R1  - Power management 1 */
 	{ 2,  0x0000 },     /* R2  - Power management 2 */
@@ -181,6 +189,7 @@ static const int volume_update_regs[] = {
 struct wm8985_priv {
 	struct regmap *regmap;
 	struct regulator_bulk_data supplies[WM8985_NUM_SUPPLIES];
+	enum wm8985_type dev_type;
 	unsigned int sysclk;
 	unsigned int bclk;
 };
@@ -289,7 +298,7 @@ static const char *depth_3d_text[] = {
 };
 static SOC_ENUM_SINGLE_DECL(depth_3d, WM8985_3D_CONTROL, 0, depth_3d_text);
 
-static const struct snd_kcontrol_new wm8985_snd_controls[] = {
+static const struct snd_kcontrol_new wm8985_common_snd_controls[] = {
 	SOC_SINGLE("Digital Loopback Switch", WM8985_COMPANDING_CONTROL,
 		0, 1, 0),
 
@@ -355,10 +364,6 @@ static const struct snd_kcontrol_new wm8985_snd_controls[] = {
 	SOC_ENUM("High Pass Filter Mode", filter_mode),
 	SOC_SINGLE("High Pass Filter Cutoff", WM8985_ADC_CONTROL, 4, 7, 0),
 
-	SOC_DOUBLE_R_TLV("Aux Bypass Volume",
-		WM8985_LEFT_MIXER_CTRL, WM8985_RIGHT_MIXER_CTRL, 6, 7, 0,
-		aux_tlv),
-
 	SOC_DOUBLE_R_TLV("Input PGA Bypass Volume",
 		WM8985_LEFT_MIXER_CTRL, WM8985_RIGHT_MIXER_CTRL, 2, 7, 0,
 		bypass_tlv),
@@ -379,20 +384,30 @@ static const struct snd_kcontrol_new wm8985_snd_controls[] = {
 	SOC_SINGLE_TLV("EQ5 Volume", WM8985_EQ5_HIGH_SHELF, 0, 24, 1, eq_tlv),
 
 	SOC_ENUM("3D Depth", depth_3d),
+};
+
+static const struct snd_kcontrol_new wm8985_specific_snd_controls[] = {
+	SOC_DOUBLE_R_TLV("Aux Bypass Volume",
+		WM8985_LEFT_MIXER_CTRL, WM8985_RIGHT_MIXER_CTRL, 6, 7, 0,
+		aux_tlv),
 
 	SOC_ENUM("Speaker Mode", speaker_mode)
 };
 
 static const struct snd_kcontrol_new left_out_mixer[] = {
 	SOC_DAPM_SINGLE("Line Switch", WM8985_LEFT_MIXER_CTRL, 1, 1, 0),
-	SOC_DAPM_SINGLE("Aux Switch", WM8985_LEFT_MIXER_CTRL, 5, 1, 0),
 	SOC_DAPM_SINGLE("PCM Switch", WM8985_LEFT_MIXER_CTRL, 0, 1, 0),
+
+	/* --- WM8985 only --- */
+	SOC_DAPM_SINGLE("Aux Switch", WM8985_LEFT_MIXER_CTRL, 5, 1, 0),
 };
 
 static const struct snd_kcontrol_new right_out_mixer[] = {
 	SOC_DAPM_SINGLE("Line Switch", WM8985_RIGHT_MIXER_CTRL, 1, 1, 0),
-	SOC_DAPM_SINGLE("Aux Switch", WM8985_RIGHT_MIXER_CTRL, 5, 1, 0),
 	SOC_DAPM_SINGLE("PCM Switch", WM8985_RIGHT_MIXER_CTRL, 0, 1, 0),
+
+	/* --- WM8985 only --- */
+	SOC_DAPM_SINGLE("Aux Switch", WM8985_RIGHT_MIXER_CTRL, 5, 1, 0),
 };
 
 static const struct snd_kcontrol_new left_input_mixer[] = {
@@ -410,6 +425,8 @@ static const struct snd_kcontrol_new right_input_mixer[] = {
 static const struct snd_kcontrol_new left_boost_mixer[] = {
 	SOC_DAPM_SINGLE_TLV("L2 Volume", WM8985_LEFT_ADC_BOOST_CTRL,
 		4, 7, 0, boost_tlv),
+
+	/* --- WM8985 only --- */
 	SOC_DAPM_SINGLE_TLV("AUXL Volume", WM8985_LEFT_ADC_BOOST_CTRL,
 		0, 7, 0, boost_tlv)
 };
@@ -417,11 +434,13 @@ static const struct snd_kcontrol_new left_boost_mixer[] = {
 static const struct snd_kcontrol_new right_boost_mixer[] = {
 	SOC_DAPM_SINGLE_TLV("R2 Volume", WM8985_RIGHT_ADC_BOOST_CTRL,
 		4, 7, 0, boost_tlv),
+
+	/* --- WM8985 only --- */
 	SOC_DAPM_SINGLE_TLV("AUXR Volume", WM8985_RIGHT_ADC_BOOST_CTRL,
 		0, 7, 0, boost_tlv)
 };
 
-static const struct snd_soc_dapm_widget wm8985_dapm_widgets[] = {
+static const struct snd_soc_dapm_widget wm8985_common_dapm_widgets[] = {
 	SND_SOC_DAPM_DAC("Left DAC", "Left Playback", WM8985_POWER_MANAGEMENT_3,
 		0, 0),
 	SND_SOC_DAPM_DAC("Right DAC", "Right Playback", WM8985_POWER_MANAGEMENT_3,
@@ -431,21 +450,11 @@ static const struct snd_soc_dapm_widget wm8985_dapm_widgets[] = {
 	SND_SOC_DAPM_ADC("Right ADC", "Right Capture", WM8985_POWER_MANAGEMENT_2,
 		1, 0),
 
-	SND_SOC_DAPM_MIXER("Left Output Mixer", WM8985_POWER_MANAGEMENT_3,
-		2, 0, left_out_mixer, ARRAY_SIZE(left_out_mixer)),
-	SND_SOC_DAPM_MIXER("Right Output Mixer", WM8985_POWER_MANAGEMENT_3,
-		3, 0, right_out_mixer, ARRAY_SIZE(right_out_mixer)),
-
 	SND_SOC_DAPM_MIXER("Left Input Mixer", WM8985_POWER_MANAGEMENT_2,
 		2, 0, left_input_mixer, ARRAY_SIZE(left_input_mixer)),
 	SND_SOC_DAPM_MIXER("Right Input Mixer", WM8985_POWER_MANAGEMENT_2,
 		3, 0, right_input_mixer, ARRAY_SIZE(right_input_mixer)),
 
-	SND_SOC_DAPM_MIXER("Left Boost Mixer", WM8985_POWER_MANAGEMENT_2,
-		4, 0, left_boost_mixer, ARRAY_SIZE(left_boost_mixer)),
-	SND_SOC_DAPM_MIXER("Right Boost Mixer", WM8985_POWER_MANAGEMENT_2,
-		5, 0, right_boost_mixer, ARRAY_SIZE(right_boost_mixer)),
-
 	SND_SOC_DAPM_PGA("Left Capture PGA", WM8985_LEFT_INP_PGA_GAIN_CTRL,
 		6, 1, NULL, 0),
 	SND_SOC_DAPM_PGA("Right Capture PGA", WM8985_RIGHT_INP_PGA_GAIN_CTRL,
@@ -468,8 +477,6 @@ static const struct snd_soc_dapm_widget wm8985_dapm_widgets[] = {
 	SND_SOC_DAPM_INPUT("LIP"),
 	SND_SOC_DAPM_INPUT("RIN"),
 	SND_SOC_DAPM_INPUT("RIP"),
-	SND_SOC_DAPM_INPUT("AUXL"),
-	SND_SOC_DAPM_INPUT("AUXR"),
 	SND_SOC_DAPM_INPUT("L2"),
 	SND_SOC_DAPM_INPUT("R2"),
 	SND_SOC_DAPM_OUTPUT("HPL"),
@@ -478,13 +485,42 @@ static const struct snd_soc_dapm_widget wm8985_dapm_widgets[] = {
 	SND_SOC_DAPM_OUTPUT("SPKR")
 };
 
-static const struct snd_soc_dapm_route wm8985_dapm_routes[] = {
+static const struct snd_soc_dapm_widget wm8985_dapm_widgets[] = {
+	SND_SOC_DAPM_MIXER("Left Output Mixer", WM8985_POWER_MANAGEMENT_3,
+		2, 0, left_out_mixer, ARRAY_SIZE(left_out_mixer)),
+	SND_SOC_DAPM_MIXER("Right Output Mixer", WM8985_POWER_MANAGEMENT_3,
+		3, 0, right_out_mixer, ARRAY_SIZE(right_out_mixer)),
+
+	SND_SOC_DAPM_MIXER("Left Boost Mixer", WM8985_POWER_MANAGEMENT_2,
+		4, 0, left_boost_mixer, ARRAY_SIZE(left_boost_mixer)),
+	SND_SOC_DAPM_MIXER("Right Boost Mixer", WM8985_POWER_MANAGEMENT_2,
+		5, 0, right_boost_mixer, ARRAY_SIZE(right_boost_mixer)),
+
+	SND_SOC_DAPM_INPUT("AUXL"),
+	SND_SOC_DAPM_INPUT("AUXR"),
+};
+
+static const struct snd_soc_dapm_widget wm8758_dapm_widgets[] = {
+	SND_SOC_DAPM_MIXER("Left Output Mixer", WM8985_POWER_MANAGEMENT_3,
+		2, 0, left_out_mixer,
+		ARRAY_SIZE(left_out_mixer) - 1),
+	SND_SOC_DAPM_MIXER("Right Output Mixer", WM8985_POWER_MANAGEMENT_3,
+		3, 0, right_out_mixer,
+		ARRAY_SIZE(right_out_mixer) - 1),
+
+	SND_SOC_DAPM_MIXER("Left Boost Mixer", WM8985_POWER_MANAGEMENT_2,
+		4, 0, left_boost_mixer,
+		ARRAY_SIZE(left_boost_mixer) - 1),
+	SND_SOC_DAPM_MIXER("Right Boost Mixer", WM8985_POWER_MANAGEMENT_2,
+		5, 0, right_boost_mixer,
+		ARRAY_SIZE(right_boost_mixer) - 1),
+};
+
+static const struct snd_soc_dapm_route wm8985_common_dapm_routes[] = {
 	{ "Right Output Mixer", "PCM Switch", "Right DAC" },
-	{ "Right Output Mixer", "Aux Switch", "AUXR" },
 	{ "Right Output Mixer", "Line Switch", "Right Boost Mixer" },
 
 	{ "Left Output Mixer", "PCM Switch", "Left DAC" },
-	{ "Left Output Mixer", "Aux Switch", "AUXL" },
 	{ "Left Output Mixer", "Line Switch", "Left Boost Mixer" },
 
 	{ "Right Headphone Out", NULL, "Right Output Mixer" },
@@ -501,13 +537,11 @@ static const struct snd_soc_dapm_route wm8985_dapm_routes[] = {
 
 	{ "Right ADC", NULL, "Right Boost Mixer" },
 
-	{ "Right Boost Mixer", "AUXR Volume", "AUXR" },
 	{ "Right Boost Mixer", NULL, "Right Capture PGA" },
 	{ "Right Boost Mixer", "R2 Volume", "R2" },
 
 	{ "Left ADC", NULL, "Left Boost Mixer" },
 
-	{ "Left Boost Mixer", "AUXL Volume", "AUXL" },
 	{ "Left Boost Mixer", NULL, "Left Capture PGA" },
 	{ "Left Boost Mixer", "L2 Volume", "L2" },
 
@@ -522,6 +556,38 @@ static const struct snd_soc_dapm_route wm8985_dapm_routes[] = {
 	{ "Left Input Mixer", "MicN Switch", "LIN" },
 	{ "Left Input Mixer", "MicP Switch", "LIP" },
 };
+static const struct snd_soc_dapm_route wm8985_aux_dapm_routes[] = {
+	{ "Right Output Mixer", "Aux Switch", "AUXR" },
+	{ "Left Output Mixer", "Aux Switch", "AUXL" },
+
+	{ "Right Boost Mixer", "AUXR Volume", "AUXR" },
+	{ "Left Boost Mixer", "AUXL Volume", "AUXL" },
+};
+
+static int wm8985_add_widgets(struct snd_soc_codec *codec)
+{
+	struct wm8985_priv *wm8985 = snd_soc_codec_get_drvdata(codec);
+	struct snd_soc_dapm_context *dapm = snd_soc_codec_get_dapm(codec);
+
+	switch (wm8985->dev_type) {
+	case WM8758:
+		snd_soc_dapm_new_controls(dapm, wm8758_dapm_widgets,
+					  ARRAY_SIZE(wm8758_dapm_widgets));
+		break;
+
+	case WM8985:
+		snd_soc_add_codec_controls(codec, wm8985_specific_snd_controls,
+			ARRAY_SIZE(wm8985_specific_snd_controls));
+
+		snd_soc_dapm_new_controls(dapm, wm8985_dapm_widgets,
+			ARRAY_SIZE(wm8985_dapm_widgets));
+		snd_soc_dapm_add_routes(dapm, wm8985_aux_dapm_routes,
+			ARRAY_SIZE(wm8985_aux_dapm_routes));
+		break;
+	}
+
+	return 0;
+}
 
 static int eqmode_get(struct snd_kcontrol *kcontrol,
 		      struct snd_ctl_elem_value *ucontrol)
@@ -999,6 +1065,8 @@ static int wm8985_probe(struct snd_soc_codec *codec)
 	snd_soc_update_bits(codec, WM8985_BIAS_CTRL, WM8985_BIASCUT,
 			    WM8985_BIASCUT);
 
+	wm8985_add_widgets(codec);
+
 	return 0;
 
 err_reg_enable:
@@ -1042,12 +1110,12 @@ static struct snd_soc_codec_driver soc_codec_dev_wm8985 = {
 	.set_bias_level = wm8985_set_bias_level,
 	.suspend_bias_off = true,
 
-	.controls = wm8985_snd_controls,
-	.num_controls = ARRAY_SIZE(wm8985_snd_controls),
-	.dapm_widgets = wm8985_dapm_widgets,
-	.num_dapm_widgets = ARRAY_SIZE(wm8985_dapm_widgets),
-	.dapm_routes = wm8985_dapm_routes,
-	.num_dapm_routes = ARRAY_SIZE(wm8985_dapm_routes),
+	.controls = wm8985_common_snd_controls,
+	.num_controls = ARRAY_SIZE(wm8985_common_snd_controls),
+	.dapm_widgets = wm8985_common_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(wm8985_common_dapm_widgets),
+	.dapm_routes = wm8985_common_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(wm8985_common_dapm_routes),
 };
 
 static const struct regmap_config wm8985_regmap = {
@@ -1074,6 +1142,8 @@ static int wm8985_spi_probe(struct spi_device *spi)
 
 	spi_set_drvdata(spi, wm8985);
 
+	wm8985->dev_type = WM8985;
+
 	wm8985->regmap = devm_regmap_init_spi(spi, &wm8985_regmap);
 	if (IS_ERR(wm8985->regmap)) {
 		ret = PTR_ERR(wm8985->regmap);
@@ -1115,6 +1185,8 @@ static int wm8985_i2c_probe(struct i2c_client *i2c,
 
 	i2c_set_clientdata(i2c, wm8985);
 
+	wm8985->dev_type = id->driver_data;
+
 	wm8985->regmap = devm_regmap_init_i2c(i2c, &wm8985_regmap);
 	if (IS_ERR(wm8985->regmap)) {
 		ret = PTR_ERR(wm8985->regmap);
@@ -1135,7 +1207,8 @@ static int wm8985_i2c_remove(struct i2c_client *i2c)
 }
 
 static const struct i2c_device_id wm8985_i2c_id[] = {
-	{ "wm8985", 0 },
+	{ "wm8985", WM8985 },
+	{ "wm8758", WM8758 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, wm8985_i2c_id);
@@ -1183,6 +1256,6 @@ static void __exit wm8985_exit(void)
 }
 module_exit(wm8985_exit);
 
-MODULE_DESCRIPTION("ASoC WM8985 driver");
+MODULE_DESCRIPTION("ASoC WM8985 / WM8758 driver");
 MODULE_AUTHOR("Dimitris Papastamos <dp@opensource.wolfsonmicro.com>");
 MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/wm8985.h b/sound/soc/codecs/wm8985.h
index 2e71ff507638..41b1048e3c97 100644
--- a/sound/soc/codecs/wm8985.h
+++ b/sound/soc/codecs/wm8985.h
@@ -290,6 +290,9 @@
 #define WM8985_GPIO1GPD_MASK                    0x0040  /* GPIO1GPD */
 #define WM8985_GPIO1GPD_SHIFT                        6  /* GPIO1GPD */
 #define WM8985_GPIO1GPD_WIDTH                        1  /* GPIO1GPD */
+#define WM8758_OPCLKDIV_MASK                    0x0030  /* OPCLKDIV - [1:0] */
+#define WM8758_OPCLKDIV_SHIFT                        4  /* OPCLKDIV - [1:0] */
+#define WM8758_OPCLKDIV_WIDTH                        2  /* OPCLKDIV - [1:0] */
 #define WM8985_GPIO1POL                         0x0008  /* GPIO1POL */
 #define WM8985_GPIO1POL_MASK                    0x0008  /* GPIO1POL */
 #define WM8985_GPIO1POL_SHIFT                        3  /* GPIO1POL */
@@ -301,6 +304,12 @@
 /*
  * R9 (0x09) - Jack Detect Control 1
  */
+#define WM8758_JD_VMID1_MASK                    0x0100  /* JD_VMID1 */
+#define WM8758_JD_VMID1_SHIFT                        8  /* JD_VMID1 */
+#define WM8758_JD_VMID1_WIDTH                        1  /* JD_VMID1 */
+#define WM8758_JD_VMID0_MASK                    0x0080  /* JD_VMID0 */
+#define WM8758_JD_VMID0_SHIFT                        7  /* JD_VMID0 */
+#define WM8758_JD_VMID0_WIDTH                        1  /* JD_VMID0 */
 #define WM8985_JD_EN                            0x0040  /* JD_EN */
 #define WM8985_JD_EN_MASK                       0x0040  /* JD_EN */
 #define WM8985_JD_EN_SHIFT                           6  /* JD_EN */
@@ -649,6 +658,12 @@
 #define WM8985_OUT4_2LNR_MASK                   0x0020  /* OUT4_2LNR */
 #define WM8985_OUT4_2LNR_SHIFT                       5  /* OUT4_2LNR */
 #define WM8985_OUT4_2LNR_WIDTH                       1  /* OUT4_2LNR */
+#define WM8758_VMIDTOG_MASK                     0x0010  /* VMIDTOG */
+#define WM8758_VMIDTOG_SHIFT                         4  /* VMIDTOG */
+#define WM8758_VMIDTOG_WIDTH                         1  /* VMIDTOG */
+#define WM8758_OUT2DEL_MASK                     0x0008  /* OUT2DEL */
+#define WM8758_OUT2DEL_SHIFT                         3  /* OUT2DEL */
+#define WM8758_OUT2DEL_WIDTH                         1  /* OUT2DEL */
 #define WM8985_POBCTRL                          0x0004  /* POBCTRL */
 #define WM8985_POBCTRL_MASK                     0x0004  /* POBCTRL */
 #define WM8985_POBCTRL_SHIFT                         2  /* POBCTRL */
@@ -684,6 +699,9 @@
 #define WM8985_BEEPVOL_MASK                     0x000E  /* BEEPVOL - [3:1] */
 #define WM8985_BEEPVOL_SHIFT                         1  /* BEEPVOL - [3:1] */
 #define WM8985_BEEPVOL_WIDTH                         3  /* BEEPVOL - [3:1] */
+#define WM8758_DELEN2_MASK                      0x0004  /* DELEN2 */
+#define WM8758_DELEN2_SHIFT                          2  /* DELEN2 */
+#define WM8758_DELEN2_WIDTH                          1  /* DELEN2 */
 #define WM8985_BEEPEN                           0x0001  /* BEEPEN */
 #define WM8985_BEEPEN_MASK                      0x0001  /* BEEPEN */
 #define WM8985_BEEPEN_SHIFT                          0  /* BEEPEN */
@@ -790,6 +808,14 @@
 /*
  * R49 (0x31) - Output ctrl
  */
+#define WM8758_HP_COM                           0x0100  /* HP_COM */
+#define WM8758_HP_COM_MASK                      0x0100  /* HP_COM */
+#define WM8758_HP_COM_SHIFT                          8  /* HP_COM */
+#define WM8758_HP_COM_WIDTH                          1  /* HP_COM */
+#define WM8758_LINE_COM                         0x0080  /* LINE_COM */
+#define WM8758_LINE_COM_MASK                    0x0080  /* LINE_COM */
+#define WM8758_LINE_COM_SHIFT                        7  /* LINE_COM */
+#define WM8758_LINE_COM_WIDTH                        1  /* LINE_COM */
 #define WM8985_DACL2RMIX                        0x0040  /* DACL2RMIX */
 #define WM8985_DACL2RMIX_MASK                   0x0040  /* DACL2RMIX */
 #define WM8985_DACL2RMIX_SHIFT                       6  /* DACL2RMIX */
@@ -806,6 +832,14 @@
 #define WM8985_OUT3BOOST_MASK                   0x0008  /* OUT3BOOST */
 #define WM8985_OUT3BOOST_SHIFT                       3  /* OUT3BOOST */
 #define WM8985_OUT3BOOST_WIDTH                       1  /* OUT3BOOST */
+#define WM8758_OUT4ENDEL                        0x0010  /* OUT4ENDEL */
+#define WM8758_OUT4ENDEL_MASK                   0x0010  /* OUT4ENDEL */
+#define WM8758_OUT4ENDEL_SHIFT                       4  /* OUT4ENDEL */
+#define WM8758_OUT4ENDEL_WIDTH                       1  /* OUT4ENDEL */
+#define WM8758_OUT3ENDEL                        0x0008  /* OUT3ENDEL */
+#define WM8758_OUT3ENDEL_MASK                   0x0008  /* OUT3ENDEL */
+#define WM8758_OUT3ENDEL_SHIFT                       3  /* OUT3ENDEL */
+#define WM8758_OUT3ENDEL_WIDTH                       1  /* OUT3ENDEL */
 #define WM8985_TSOPCTRL                         0x0004  /* TSOPCTRL */
 #define WM8985_TSOPCTRL_MASK                    0x0004  /* TSOPCTRL */
 #define WM8985_TSOPCTRL_SHIFT                        2  /* TSOPCTRL */
@@ -1021,6 +1055,10 @@
 #define WM8985_HALFIPBIAS_MASK                  0x0080  /* HALFIPBIAS */
 #define WM8985_HALFIPBIAS_SHIFT                      7  /* HALFIPBIAS */
 #define WM8985_HALFIPBIAS_WIDTH                      1  /* HALFIPBIAS */
+#define WM8758_HALFIPBIAS                       0x0040  /* HALFI_IPGA */
+#define WM8758_HALFI_IPGA_MASK                  0x0040  /* HALFI_IPGA */
+#define WM8758_HALFI_IPGA_SHIFT                      6  /* HALFI_IPGA */
+#define WM8758_HALFI_IPGA_WIDTH                      1  /* HALFI_IPGA */
 #define WM8985_VBBIASTST_MASK                   0x0060  /* VBBIASTST - [6:5] */
 #define WM8985_VBBIASTST_SHIFT                       5  /* VBBIASTST - [6:5] */
 #define WM8985_VBBIASTST_WIDTH                       2  /* VBBIASTST - [6:5] */
diff --git a/sound/soc/codecs/wm8998.c b/sound/soc/codecs/wm8998.c
index 449f66636205..3a5c896a2d13 100644
--- a/sound/soc/codecs/wm8998.c
+++ b/sound/soc/codecs/wm8998.c
@@ -1166,6 +1166,7 @@ static const struct snd_soc_dapm_route wm8998_dapm_routes[] = {
 
 	{ "MICSUPP", NULL, "SYSCLK" },
 
+	{ "DRC1 Signal Activity", NULL, "SYSCLK" },
 	{ "DRC1 Signal Activity", NULL, "DRC1L" },
 	{ "DRC1 Signal Activity", NULL, "DRC1R" },
 };
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index a07bd7c2c587..21fbe7d07063 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -394,6 +394,7 @@ static const struct {
 	int compr_direction;
 	int num_caps;
 	const struct wm_adsp_fw_caps *caps;
+	bool voice_trigger;
 } wm_adsp_fw[WM_ADSP_NUM_FW] = {
 	[WM_ADSP_FW_MBC_VSS] =  { .file = "mbc-vss" },
 	[WM_ADSP_FW_HIFI] =     { .file = "hifi" },
@@ -406,6 +407,7 @@ static const struct {
 		.compr_direction = SND_COMPRESS_CAPTURE,
 		.num_caps = ARRAY_SIZE(ctrl_caps),
 		.caps = ctrl_caps,
+		.voice_trigger = true,
 	},
 	[WM_ADSP_FW_ASR] =      { .file = "asr" },
 	[WM_ADSP_FW_TRACE] =    {
@@ -2366,13 +2368,15 @@ int wm_adsp2_event(struct snd_soc_dapm_widget *w,
 		dsp->running = false;
 
 		regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL,
-				   ADSP2_SYS_ENA | ADSP2_CORE_ENA |
-				   ADSP2_START, 0);
+				   ADSP2_CORE_ENA | ADSP2_START, 0);
 
 		/* Make sure DMAs are quiesced */
+		regmap_write(dsp->regmap, dsp->base + ADSP2_RDMA_CONFIG_1, 0);
 		regmap_write(dsp->regmap, dsp->base + ADSP2_WDMA_CONFIG_1, 0);
 		regmap_write(dsp->regmap, dsp->base + ADSP2_WDMA_CONFIG_2, 0);
-		regmap_write(dsp->regmap, dsp->base + ADSP2_RDMA_CONFIG_1, 0);
+
+		regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL,
+				   ADSP2_SYS_ENA, 0);
 
 		list_for_each_entry(ctl, &dsp->ctl_list, list)
 			ctl->enabled = 0;
@@ -2998,6 +3002,9 @@ int wm_adsp_compr_handle_irq(struct wm_adsp *dsp)
 		goto out;
 	}
 
+	if (wm_adsp_fw[dsp->fw].voice_trigger && buf->irq_count == 2)
+		ret = WM_ADSP_COMPR_VOICE_TRIGGER;
+
 out_notify:
 	if (compr && compr->stream)
 		snd_compr_fragment_elapsed(compr->stream);
@@ -3037,12 +3044,8 @@ int wm_adsp_compr_pointer(struct snd_compr_stream *stream,
 
 	buf = compr->buf;
 
-	if (!compr->buf) {
-		ret = -ENXIO;
-		goto out;
-	}
-
-	if (compr->buf->error) {
+	if (!compr->buf || compr->buf->error) {
+		snd_compr_stop_error(stream, SNDRV_PCM_STATE_XRUN);
 		ret = -EIO;
 		goto out;
 	}
@@ -3060,8 +3063,12 @@ int wm_adsp_compr_pointer(struct snd_compr_stream *stream,
 		 */
 		if (buf->avail < wm_adsp_compr_frag_words(compr)) {
 			ret = wm_adsp_buffer_get_error(buf);
-			if (ret < 0)
+			if (ret < 0) {
+				if (compr->buf->error)
+					snd_compr_stop_error(stream,
+							SNDRV_PCM_STATE_XRUN);
 				goto out;
+			}
 
 			ret = wm_adsp_buffer_reenable_irq(buf);
 			if (ret < 0) {
@@ -3156,11 +3163,10 @@ static int wm_adsp_compr_read(struct wm_adsp_compr *compr,
 
 	adsp_dbg(dsp, "Requested read of %zu bytes\n", count);
 
-	if (!compr->buf)
-		return -ENXIO;
-
-	if (compr->buf->error)
+	if (!compr->buf || compr->buf->error) {
+		snd_compr_stop_error(compr->stream, SNDRV_PCM_STATE_XRUN);
 		return -EIO;
+	}
 
 	count /= WM_ADSP_DATA_WORD_SIZE;
 
diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h
index feb61e2c4bb4..be3b5bcb7f17 100644
--- a/sound/soc/codecs/wm_adsp.h
+++ b/sound/soc/codecs/wm_adsp.h
@@ -19,6 +19,10 @@
 
 #include "wmfw.h"
 
+/* Return values for wm_adsp_compr_handle_irq */
+#define WM_ADSP_COMPR_OK                 0
+#define WM_ADSP_COMPR_VOICE_TRIGGER      1
+
 struct wm_adsp_region {
 	int type;
 	unsigned int base;
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 237dc67002ef..05c2d33aa74d 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -1599,7 +1599,14 @@ static struct davinci_mcasp_pdata *davinci_mcasp_set_pdata_from_of(
 		pdata = pdev->dev.platform_data;
 		return pdata;
 	} else if (match) {
-		pdata = (struct davinci_mcasp_pdata*) match->data;
+		pdata = devm_kmemdup(&pdev->dev, match->data, sizeof(*pdata),
+				     GFP_KERNEL);
+		if (!pdata) {
+			dev_err(&pdev->dev,
+				"Failed to allocate memory for pdata\n");
+			ret = -ENOMEM;
+			return pdata;
+		}
 	} else {
 		/* control shouldn't reach here. something is wrong */
 		ret = -EINVAL;
diff --git a/sound/soc/dwc/Kconfig b/sound/soc/dwc/Kconfig
index d50e08517dce..c297efe43861 100644
--- a/sound/soc/dwc/Kconfig
+++ b/sound/soc/dwc/Kconfig
@@ -7,4 +7,13 @@ config SND_DESIGNWARE_I2S
 	 Synopsys desigwnware I2S device. The device supports upto
 	 maximum of 8 channels each for play and record.
 
+config SND_DESIGNWARE_PCM
+	tristate "PCM PIO extension for I2S driver"
+	depends on SND_DESIGNWARE_I2S
+	help
+	 Say Y, M or N if you want to add a custom ALSA extension that registers
+	 a PCM and uses PIO to transfer data.
+
+	 This functionality is specially suited for I2S devices that don't have
+	 DMA support.
 
diff --git a/sound/soc/dwc/Makefile b/sound/soc/dwc/Makefile
index 319371f690f4..38f1ca31c5fa 100644
--- a/sound/soc/dwc/Makefile
+++ b/sound/soc/dwc/Makefile
@@ -1,3 +1,5 @@
 # SYNOPSYS Platform Support
 obj-$(CONFIG_SND_DESIGNWARE_I2S) += designware_i2s.o
-
+ifdef CONFIG_SND_DESIGNWARE_PCM
+obj-$(CONFIG_SND_DESIGNWARE_I2S) += designware_pcm.o
+endif
diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c
index 0db69b7e9617..dc97f4349e66 100644
--- a/sound/soc/dwc/designware_i2s.c
+++ b/sound/soc/dwc/designware_i2s.c
@@ -24,90 +24,7 @@
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
 #include <sound/dmaengine_pcm.h>
-
-/* common register for all channel */
-#define IER		0x000
-#define IRER		0x004
-#define ITER		0x008
-#define CER		0x00C
-#define CCR		0x010
-#define RXFFR		0x014
-#define TXFFR		0x018
-
-/* I2STxRxRegisters for all channels */
-#define LRBR_LTHR(x)	(0x40 * x + 0x020)
-#define RRBR_RTHR(x)	(0x40 * x + 0x024)
-#define RER(x)		(0x40 * x + 0x028)
-#define TER(x)		(0x40 * x + 0x02C)
-#define RCR(x)		(0x40 * x + 0x030)
-#define TCR(x)		(0x40 * x + 0x034)
-#define ISR(x)		(0x40 * x + 0x038)
-#define IMR(x)		(0x40 * x + 0x03C)
-#define ROR(x)		(0x40 * x + 0x040)
-#define TOR(x)		(0x40 * x + 0x044)
-#define RFCR(x)		(0x40 * x + 0x048)
-#define TFCR(x)		(0x40 * x + 0x04C)
-#define RFF(x)		(0x40 * x + 0x050)
-#define TFF(x)		(0x40 * x + 0x054)
-
-/* I2SCOMPRegisters */
-#define I2S_COMP_PARAM_2	0x01F0
-#define I2S_COMP_PARAM_1	0x01F4
-#define I2S_COMP_VERSION	0x01F8
-#define I2S_COMP_TYPE		0x01FC
-
-/*
- * Component parameter register fields - define the I2S block's
- * configuration.
- */
-#define	COMP1_TX_WORDSIZE_3(r)	(((r) & GENMASK(27, 25)) >> 25)
-#define	COMP1_TX_WORDSIZE_2(r)	(((r) & GENMASK(24, 22)) >> 22)
-#define	COMP1_TX_WORDSIZE_1(r)	(((r) & GENMASK(21, 19)) >> 19)
-#define	COMP1_TX_WORDSIZE_0(r)	(((r) & GENMASK(18, 16)) >> 16)
-#define	COMP1_TX_CHANNELS(r)	(((r) & GENMASK(10, 9)) >> 9)
-#define	COMP1_RX_CHANNELS(r)	(((r) & GENMASK(8, 7)) >> 7)
-#define	COMP1_RX_ENABLED(r)	(((r) & BIT(6)) >> 6)
-#define	COMP1_TX_ENABLED(r)	(((r) & BIT(5)) >> 5)
-#define	COMP1_MODE_EN(r)	(((r) & BIT(4)) >> 4)
-#define	COMP1_FIFO_DEPTH_GLOBAL(r)	(((r) & GENMASK(3, 2)) >> 2)
-#define	COMP1_APB_DATA_WIDTH(r)	(((r) & GENMASK(1, 0)) >> 0)
-
-#define	COMP2_RX_WORDSIZE_3(r)	(((r) & GENMASK(12, 10)) >> 10)
-#define	COMP2_RX_WORDSIZE_2(r)	(((r) & GENMASK(9, 7)) >> 7)
-#define	COMP2_RX_WORDSIZE_1(r)	(((r) & GENMASK(5, 3)) >> 3)
-#define	COMP2_RX_WORDSIZE_0(r)	(((r) & GENMASK(2, 0)) >> 0)
-
-/* Number of entries in WORDSIZE and DATA_WIDTH parameter registers */
-#define	COMP_MAX_WORDSIZE	(1 << 3)
-#define	COMP_MAX_DATA_WIDTH	(1 << 2)
-
-#define MAX_CHANNEL_NUM		8
-#define MIN_CHANNEL_NUM		2
-
-union dw_i2s_snd_dma_data {
-	struct i2s_dma_data pd;
-	struct snd_dmaengine_dai_dma_data dt;
-};
-
-struct dw_i2s_dev {
-	void __iomem *i2s_base;
-	struct clk *clk;
-	int active;
-	unsigned int capability;
-	unsigned int quirks;
-	unsigned int i2s_reg_comp1;
-	unsigned int i2s_reg_comp2;
-	struct device *dev;
-	u32 ccr;
-	u32 xfer_resolution;
-	u32 fifo_th;
-
-	/* data related to DMA transfers b/w i2s and DMAC */
-	union dw_i2s_snd_dma_data play_dma_data;
-	union dw_i2s_snd_dma_data capture_dma_data;
-	struct i2s_clk_config_data config;
-	int (*i2s_clk_cfg)(struct i2s_clk_config_data *config);
-};
+#include "local.h"
 
 static inline void i2s_write_reg(void __iomem *io_base, int reg, u32 val)
 {
@@ -145,51 +62,115 @@ static inline void i2s_clear_irqs(struct dw_i2s_dev *dev, u32 stream)
 	}
 }
 
-static void i2s_start(struct dw_i2s_dev *dev,
-		      struct snd_pcm_substream *substream)
+static inline void i2s_disable_irqs(struct dw_i2s_dev *dev, u32 stream,
+				    int chan_nr)
+{
+	u32 i, irq;
+
+	if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		for (i = 0; i < (chan_nr / 2); i++) {
+			irq = i2s_read_reg(dev->i2s_base, IMR(i));
+			i2s_write_reg(dev->i2s_base, IMR(i), irq | 0x30);
+		}
+	} else {
+		for (i = 0; i < (chan_nr / 2); i++) {
+			irq = i2s_read_reg(dev->i2s_base, IMR(i));
+			i2s_write_reg(dev->i2s_base, IMR(i), irq | 0x03);
+		}
+	}
+}
+
+static inline void i2s_enable_irqs(struct dw_i2s_dev *dev, u32 stream,
+				   int chan_nr)
 {
-	struct i2s_clk_config_data *config = &dev->config;
 	u32 i, irq;
-	i2s_write_reg(dev->i2s_base, IER, 1);
 
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		for (i = 0; i < (config->chan_nr / 2); i++) {
+	if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		for (i = 0; i < (chan_nr / 2); i++) {
 			irq = i2s_read_reg(dev->i2s_base, IMR(i));
 			i2s_write_reg(dev->i2s_base, IMR(i), irq & ~0x30);
 		}
-		i2s_write_reg(dev->i2s_base, ITER, 1);
 	} else {
-		for (i = 0; i < (config->chan_nr / 2); i++) {
+		for (i = 0; i < (chan_nr / 2); i++) {
 			irq = i2s_read_reg(dev->i2s_base, IMR(i));
 			i2s_write_reg(dev->i2s_base, IMR(i), irq & ~0x03);
 		}
-		i2s_write_reg(dev->i2s_base, IRER, 1);
+	}
+}
+
+static irqreturn_t i2s_irq_handler(int irq, void *dev_id)
+{
+	struct dw_i2s_dev *dev = dev_id;
+	bool irq_valid = false;
+	u32 isr[4];
+	int i;
+
+	for (i = 0; i < 4; i++)
+		isr[i] = i2s_read_reg(dev->i2s_base, ISR(i));
+
+	i2s_clear_irqs(dev, SNDRV_PCM_STREAM_PLAYBACK);
+	i2s_clear_irqs(dev, SNDRV_PCM_STREAM_CAPTURE);
+
+	for (i = 0; i < 4; i++) {
+		/*
+		 * Check if TX fifo is empty. If empty fill FIFO with samples
+		 * NOTE: Only two channels supported
+		 */
+		if ((isr[i] & ISR_TXFE) && (i == 0) && dev->use_pio) {
+			dw_pcm_push_tx(dev);
+			irq_valid = true;
+		}
+
+		/* Data available. Record mode not supported in PIO mode */
+		if (isr[i] & ISR_RXDA)
+			irq_valid = true;
+
+		/* Error Handling: TX */
+		if (isr[i] & ISR_TXFO) {
+			dev_err(dev->dev, "TX overrun (ch_id=%d)\n", i);
+			irq_valid = true;
+		}
+
+		/* Error Handling: TX */
+		if (isr[i] & ISR_RXFO) {
+			dev_err(dev->dev, "RX overrun (ch_id=%d)\n", i);
+			irq_valid = true;
+		}
 	}
 
+	if (irq_valid)
+		return IRQ_HANDLED;
+	else
+		return IRQ_NONE;
+}
+
+static void i2s_start(struct dw_i2s_dev *dev,
+		      struct snd_pcm_substream *substream)
+{
+	struct i2s_clk_config_data *config = &dev->config;
+
+	i2s_write_reg(dev->i2s_base, IER, 1);
+	i2s_enable_irqs(dev, substream->stream, config->chan_nr);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		i2s_write_reg(dev->i2s_base, ITER, 1);
+	else
+		i2s_write_reg(dev->i2s_base, IRER, 1);
+
 	i2s_write_reg(dev->i2s_base, CER, 1);
 }
 
 static void i2s_stop(struct dw_i2s_dev *dev,
 		struct snd_pcm_substream *substream)
 {
-	u32 i = 0, irq;
 
 	i2s_clear_irqs(dev, substream->stream);
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		i2s_write_reg(dev->i2s_base, ITER, 0);
-
-		for (i = 0; i < 4; i++) {
-			irq = i2s_read_reg(dev->i2s_base, IMR(i));
-			i2s_write_reg(dev->i2s_base, IMR(i), irq | 0x30);
-		}
-	} else {
+	else
 		i2s_write_reg(dev->i2s_base, IRER, 0);
 
-		for (i = 0; i < 4; i++) {
-			irq = i2s_read_reg(dev->i2s_base, IMR(i));
-			i2s_write_reg(dev->i2s_base, IMR(i), irq | 0x03);
-		}
-	}
+	i2s_disable_irqs(dev, substream->stream, 8);
 
 	if (!dev->active) {
 		i2s_write_reg(dev->i2s_base, CER, 0);
@@ -223,7 +204,7 @@ static int dw_i2s_startup(struct snd_pcm_substream *substream,
 
 static void dw_i2s_config(struct dw_i2s_dev *dev, int stream)
 {
-	u32 ch_reg, irq;
+	u32 ch_reg;
 	struct i2s_clk_config_data *config = &dev->config;
 
 
@@ -235,16 +216,12 @@ static void dw_i2s_config(struct dw_i2s_dev *dev, int stream)
 				      dev->xfer_resolution);
 			i2s_write_reg(dev->i2s_base, TFCR(ch_reg),
 				      dev->fifo_th - 1);
-			irq = i2s_read_reg(dev->i2s_base, IMR(ch_reg));
-			i2s_write_reg(dev->i2s_base, IMR(ch_reg), irq & ~0x30);
 			i2s_write_reg(dev->i2s_base, TER(ch_reg), 1);
 		} else {
 			i2s_write_reg(dev->i2s_base, RCR(ch_reg),
 				      dev->xfer_resolution);
 			i2s_write_reg(dev->i2s_base, RFCR(ch_reg),
 				      dev->fifo_th - 1);
-			irq = i2s_read_reg(dev->i2s_base, IMR(ch_reg));
-			i2s_write_reg(dev->i2s_base, IMR(ch_reg), irq & ~0x03);
 			i2s_write_reg(dev->i2s_base, RER(ch_reg), 1);
 		}
 
@@ -278,7 +255,7 @@ static int dw_i2s_hw_params(struct snd_pcm_substream *substream,
 		break;
 
 	default:
-		dev_err(dev->dev, "designware-i2s: unsuppted PCM fmt");
+		dev_err(dev->dev, "designware-i2s: unsupported PCM fmt");
 		return -EINVAL;
 	}
 
@@ -626,7 +603,7 @@ static int dw_i2s_probe(struct platform_device *pdev)
 	const struct i2s_platform_data *pdata = pdev->dev.platform_data;
 	struct dw_i2s_dev *dev;
 	struct resource *res;
-	int ret;
+	int ret, irq;
 	struct snd_soc_dai_driver *dw_i2s_dai;
 	const char *clk_id;
 
@@ -651,6 +628,16 @@ static int dw_i2s_probe(struct platform_device *pdev)
 
 	dev->dev = &pdev->dev;
 
+	irq = platform_get_irq(pdev, 0);
+	if (irq >= 0) {
+		ret = devm_request_irq(&pdev->dev, irq, i2s_irq_handler, 0,
+				pdev->name, dev);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to request irq\n");
+			return ret;
+		}
+	}
+
 	dev->i2s_reg_comp1 = I2S_COMP_PARAM_1;
 	dev->i2s_reg_comp2 = I2S_COMP_PARAM_2;
 	if (pdata) {
@@ -697,12 +684,24 @@ static int dw_i2s_probe(struct platform_device *pdev)
 
 	if (!pdata) {
 		ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
-		if (ret) {
+		if (ret == -EPROBE_DEFER) {
+			dev_err(&pdev->dev,
+				"failed to register PCM, deferring probe\n");
+			return ret;
+		} else if (ret) {
 			dev_err(&pdev->dev,
-				"Could not register PCM: %d\n", ret);
-			goto err_clk_disable;
+				"Could not register DMA PCM: %d\n"
+				"falling back to PIO mode\n", ret);
+			ret = dw_pcm_register(pdev);
+			if (ret) {
+				dev_err(&pdev->dev,
+					"Could not register PIO PCM: %d\n",
+					ret);
+				goto err_clk_disable;
+			}
 		}
 	}
+
 	pm_runtime_enable(&pdev->dev);
 	return 0;
 
diff --git a/sound/soc/dwc/designware_pcm.c b/sound/soc/dwc/designware_pcm.c
new file mode 100644
index 000000000000..4a83a22fa3cb
--- /dev/null
+++ b/sound/soc/dwc/designware_pcm.c
@@ -0,0 +1,225 @@
+/*
+ * ALSA SoC Synopsys PIO PCM for I2S driver
+ *
+ * sound/soc/dwc/designware_pcm.c
+ *
+ * Copyright (C) 2016 Synopsys
+ * Jose Abreu <joabreu@synopsys.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/io.h>
+#include <linux/rcupdate.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include "local.h"
+
+#define BUFFER_BYTES_MAX	(3 * 2 * 8 * PERIOD_BYTES_MIN)
+#define PERIOD_BYTES_MIN	4096
+#define PERIODS_MIN		2
+
+#define dw_pcm_tx_fn(sample_bits) \
+static unsigned int dw_pcm_tx_##sample_bits(struct dw_i2s_dev *dev, \
+		struct snd_pcm_runtime *runtime, unsigned int tx_ptr, \
+		bool *period_elapsed) \
+{ \
+	const u##sample_bits (*p)[2] = (void *)runtime->dma_area; \
+	unsigned int period_pos = tx_ptr % runtime->period_size; \
+	int i; \
+\
+	for (i = 0; i < dev->fifo_th; i++) { \
+		iowrite32(p[tx_ptr][0], dev->i2s_base + LRBR_LTHR(0)); \
+		iowrite32(p[tx_ptr][1], dev->i2s_base + RRBR_RTHR(0)); \
+		period_pos++; \
+		if (++tx_ptr >= runtime->buffer_size) \
+			tx_ptr = 0; \
+	} \
+	*period_elapsed = period_pos >= runtime->period_size; \
+	return tx_ptr; \
+}
+
+dw_pcm_tx_fn(16);
+dw_pcm_tx_fn(32);
+
+#undef dw_pcm_tx_fn
+
+static const struct snd_pcm_hardware dw_pcm_hardware = {
+	.info = SNDRV_PCM_INFO_INTERLEAVED |
+		SNDRV_PCM_INFO_MMAP |
+		SNDRV_PCM_INFO_MMAP_VALID |
+		SNDRV_PCM_INFO_BLOCK_TRANSFER,
+	.rates = SNDRV_PCM_RATE_32000 |
+		SNDRV_PCM_RATE_44100 |
+		SNDRV_PCM_RATE_48000,
+	.rate_min = 32000,
+	.rate_max = 48000,
+	.formats = SNDRV_PCM_FMTBIT_S16_LE |
+		SNDRV_PCM_FMTBIT_S32_LE,
+	.channels_min = 2,
+	.channels_max = 2,
+	.buffer_bytes_max = BUFFER_BYTES_MAX,
+	.period_bytes_min = PERIOD_BYTES_MIN,
+	.period_bytes_max = BUFFER_BYTES_MAX / PERIODS_MIN,
+	.periods_min = PERIODS_MIN,
+	.periods_max = BUFFER_BYTES_MAX / PERIOD_BYTES_MIN,
+	.fifo_size = 16,
+};
+
+void dw_pcm_push_tx(struct dw_i2s_dev *dev)
+{
+	struct snd_pcm_substream *tx_substream;
+	bool tx_active, period_elapsed;
+
+	rcu_read_lock();
+	tx_substream = rcu_dereference(dev->tx_substream);
+	tx_active = tx_substream && snd_pcm_running(tx_substream);
+	if (tx_active) {
+		unsigned int tx_ptr = READ_ONCE(dev->tx_ptr);
+		unsigned int new_tx_ptr = dev->tx_fn(dev, tx_substream->runtime,
+				tx_ptr, &period_elapsed);
+		cmpxchg(&dev->tx_ptr, tx_ptr, new_tx_ptr);
+
+		if (period_elapsed)
+			snd_pcm_period_elapsed(tx_substream);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(dw_pcm_push_tx);
+
+static int dw_pcm_open(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(rtd->cpu_dai);
+
+	snd_soc_set_runtime_hwparams(substream, &dw_pcm_hardware);
+	snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS);
+	runtime->private_data = dev;
+
+	return 0;
+}
+
+static int dw_pcm_close(struct snd_pcm_substream *substream)
+{
+	synchronize_rcu();
+	return 0;
+}
+
+static int dw_pcm_hw_params(struct snd_pcm_substream *substream,
+		struct snd_pcm_hw_params *hw_params)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct dw_i2s_dev *dev = runtime->private_data;
+	int ret;
+
+	switch (params_channels(hw_params)) {
+	case 2:
+		break;
+	default:
+		dev_err(dev->dev, "invalid channels number\n");
+		return -EINVAL;
+	}
+
+	switch (params_format(hw_params)) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		dev->tx_fn = dw_pcm_tx_16;
+		break;
+	case SNDRV_PCM_FORMAT_S32_LE:
+		dev->tx_fn = dw_pcm_tx_32;
+		break;
+	default:
+		dev_err(dev->dev, "invalid format\n");
+		return -EINVAL;
+	}
+
+	if (substream->stream != SNDRV_PCM_STREAM_PLAYBACK) {
+		dev_err(dev->dev, "only playback is available\n");
+		return -EINVAL;
+	}
+
+	ret = snd_pcm_lib_malloc_pages(substream,
+			params_buffer_bytes(hw_params));
+	if (ret < 0)
+		return ret;
+	else
+		return 0;
+}
+
+static int dw_pcm_hw_free(struct snd_pcm_substream *substream)
+{
+	return snd_pcm_lib_free_pages(substream);
+}
+
+static int dw_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct dw_i2s_dev *dev = runtime->private_data;
+	int ret = 0;
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		WRITE_ONCE(dev->tx_ptr, 0);
+		rcu_assign_pointer(dev->tx_substream, substream);
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		rcu_assign_pointer(dev->tx_substream, NULL);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static snd_pcm_uframes_t dw_pcm_pointer(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct dw_i2s_dev *dev = runtime->private_data;
+	snd_pcm_uframes_t pos = READ_ONCE(dev->tx_ptr);
+
+	return pos < runtime->buffer_size ? pos : 0;
+}
+
+static int dw_pcm_new(struct snd_soc_pcm_runtime *rtd)
+{
+	size_t size = dw_pcm_hardware.buffer_bytes_max;
+
+	return snd_pcm_lib_preallocate_pages_for_all(rtd->pcm,
+			SNDRV_DMA_TYPE_CONTINUOUS,
+			snd_dma_continuous_data(GFP_KERNEL), size, size);
+}
+
+static void dw_pcm_free(struct snd_pcm *pcm)
+{
+	snd_pcm_lib_preallocate_free_for_all(pcm);
+}
+
+static const struct snd_pcm_ops dw_pcm_ops = {
+	.open = dw_pcm_open,
+	.close = dw_pcm_close,
+	.ioctl = snd_pcm_lib_ioctl,
+	.hw_params = dw_pcm_hw_params,
+	.hw_free = dw_pcm_hw_free,
+	.trigger = dw_pcm_trigger,
+	.pointer = dw_pcm_pointer,
+};
+
+static const struct snd_soc_platform_driver dw_pcm_platform = {
+	.pcm_new = dw_pcm_new,
+	.pcm_free = dw_pcm_free,
+	.ops = &dw_pcm_ops,
+};
+
+int dw_pcm_register(struct platform_device *pdev)
+{
+	return devm_snd_soc_register_platform(&pdev->dev, &dw_pcm_platform);
+}
+EXPORT_SYMBOL_GPL(dw_pcm_register);
diff --git a/sound/soc/dwc/local.h b/sound/soc/dwc/local.h
new file mode 100644
index 000000000000..68afd7577343
--- /dev/null
+++ b/sound/soc/dwc/local.h
@@ -0,0 +1,128 @@
+/*
+ * Copyright (ST) 2012 Rajeev Kumar (rajeevkumar.linux@gmail.com)
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __DESIGNWARE_LOCAL_H
+#define __DESIGNWARE_LOCAL_H
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/types.h>
+#include <sound/dmaengine_pcm.h>
+#include <sound/pcm.h>
+#include <sound/designware_i2s.h>
+
+/* common register for all channel */
+#define IER		0x000
+#define IRER		0x004
+#define ITER		0x008
+#define CER		0x00C
+#define CCR		0x010
+#define RXFFR		0x014
+#define TXFFR		0x018
+
+/* Interrupt status register fields */
+#define ISR_TXFO	BIT(5)
+#define ISR_TXFE	BIT(4)
+#define ISR_RXFO	BIT(1)
+#define ISR_RXDA	BIT(0)
+
+/* I2STxRxRegisters for all channels */
+#define LRBR_LTHR(x)	(0x40 * x + 0x020)
+#define RRBR_RTHR(x)	(0x40 * x + 0x024)
+#define RER(x)		(0x40 * x + 0x028)
+#define TER(x)		(0x40 * x + 0x02C)
+#define RCR(x)		(0x40 * x + 0x030)
+#define TCR(x)		(0x40 * x + 0x034)
+#define ISR(x)		(0x40 * x + 0x038)
+#define IMR(x)		(0x40 * x + 0x03C)
+#define ROR(x)		(0x40 * x + 0x040)
+#define TOR(x)		(0x40 * x + 0x044)
+#define RFCR(x)		(0x40 * x + 0x048)
+#define TFCR(x)		(0x40 * x + 0x04C)
+#define RFF(x)		(0x40 * x + 0x050)
+#define TFF(x)		(0x40 * x + 0x054)
+
+/* I2SCOMPRegisters */
+#define I2S_COMP_PARAM_2	0x01F0
+#define I2S_COMP_PARAM_1	0x01F4
+#define I2S_COMP_VERSION	0x01F8
+#define I2S_COMP_TYPE		0x01FC
+
+/*
+ * Component parameter register fields - define the I2S block's
+ * configuration.
+ */
+#define	COMP1_TX_WORDSIZE_3(r)	(((r) & GENMASK(27, 25)) >> 25)
+#define	COMP1_TX_WORDSIZE_2(r)	(((r) & GENMASK(24, 22)) >> 22)
+#define	COMP1_TX_WORDSIZE_1(r)	(((r) & GENMASK(21, 19)) >> 19)
+#define	COMP1_TX_WORDSIZE_0(r)	(((r) & GENMASK(18, 16)) >> 16)
+#define	COMP1_TX_CHANNELS(r)	(((r) & GENMASK(10, 9)) >> 9)
+#define	COMP1_RX_CHANNELS(r)	(((r) & GENMASK(8, 7)) >> 7)
+#define	COMP1_RX_ENABLED(r)	(((r) & BIT(6)) >> 6)
+#define	COMP1_TX_ENABLED(r)	(((r) & BIT(5)) >> 5)
+#define	COMP1_MODE_EN(r)	(((r) & BIT(4)) >> 4)
+#define	COMP1_FIFO_DEPTH_GLOBAL(r)	(((r) & GENMASK(3, 2)) >> 2)
+#define	COMP1_APB_DATA_WIDTH(r)	(((r) & GENMASK(1, 0)) >> 0)
+
+#define	COMP2_RX_WORDSIZE_3(r)	(((r) & GENMASK(12, 10)) >> 10)
+#define	COMP2_RX_WORDSIZE_2(r)	(((r) & GENMASK(9, 7)) >> 7)
+#define	COMP2_RX_WORDSIZE_1(r)	(((r) & GENMASK(5, 3)) >> 3)
+#define	COMP2_RX_WORDSIZE_0(r)	(((r) & GENMASK(2, 0)) >> 0)
+
+/* Number of entries in WORDSIZE and DATA_WIDTH parameter registers */
+#define	COMP_MAX_WORDSIZE	(1 << 3)
+#define	COMP_MAX_DATA_WIDTH	(1 << 2)
+
+#define MAX_CHANNEL_NUM		8
+#define MIN_CHANNEL_NUM		2
+
+union dw_i2s_snd_dma_data {
+	struct i2s_dma_data pd;
+	struct snd_dmaengine_dai_dma_data dt;
+};
+
+struct dw_i2s_dev {
+	void __iomem *i2s_base;
+	struct clk *clk;
+	int active;
+	unsigned int capability;
+	unsigned int quirks;
+	unsigned int i2s_reg_comp1;
+	unsigned int i2s_reg_comp2;
+	struct device *dev;
+	u32 ccr;
+	u32 xfer_resolution;
+	u32 fifo_th;
+
+	/* data related to DMA transfers b/w i2s and DMAC */
+	union dw_i2s_snd_dma_data play_dma_data;
+	union dw_i2s_snd_dma_data capture_dma_data;
+	struct i2s_clk_config_data config;
+	int (*i2s_clk_cfg)(struct i2s_clk_config_data *config);
+
+	/* data related to PIO transfers (TX) */
+	bool use_pio;
+	struct snd_pcm_substream __rcu *tx_substream;
+	unsigned int (*tx_fn)(struct dw_i2s_dev *dev,
+			struct snd_pcm_runtime *runtime, unsigned int tx_ptr,
+			bool *period_elapsed);
+	unsigned int tx_ptr;
+};
+
+#if IS_ENABLED(CONFIG_SND_DESIGNWARE_PCM)
+void dw_pcm_push_tx(struct dw_i2s_dev *dev);
+int dw_pcm_register(struct platform_device *pdev);
+#else
+void dw_pcm_push_tx(struct dw_i2s_dev *dev) { }
+int dw_pcm_register(struct platform_device *pdev)
+{
+	return -EINVAL;
+}
+#endif
+
+#endif
diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig
index 35aabf9dc503..19bdcac71775 100644
--- a/sound/soc/fsl/Kconfig
+++ b/sound/soc/fsl/Kconfig
@@ -4,6 +4,7 @@ comment "Common SoC Audio options for Freescale CPUs:"
 
 config SND_SOC_FSL_ASRC
 	tristate "Asynchronous Sample Rate Converter (ASRC) module support"
+	depends on HAS_DMA
 	select REGMAP_MMIO
 	select SND_SOC_GENERIC_DMAENGINE_PCM
 	help
diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c
index 151849f79863..beec7934a265 100644
--- a/sound/soc/fsl/fsl_spdif.c
+++ b/sound/soc/fsl/fsl_spdif.c
@@ -172,7 +172,7 @@ static void spdif_irq_uqrx_full(struct fsl_spdif_priv *spdif_priv, char name)
 	if (*pos >= size * 2) {
 		*pos = 0;
 	} else if (unlikely((*pos % size) + 3 > size)) {
-		dev_err(&pdev->dev, "User bit receivce buffer overflow\n");
+		dev_err(&pdev->dev, "User bit receive buffer overflow\n");
 		return;
 	}
 
diff --git a/sound/soc/generic/Kconfig b/sound/soc/generic/Kconfig
index 610f61251640..c01c5dd68601 100644
--- a/sound/soc/generic/Kconfig
+++ b/sound/soc/generic/Kconfig
@@ -1,4 +1,8 @@
+config SND_SIMPLE_CARD_UTILS
+       tristate
+
 config SND_SIMPLE_CARD
 	tristate "ASoC Simple sound card support"
+	select SND_SIMPLE_CARD_UTILS
 	help
 	  This option enables generic simple sound card support
diff --git a/sound/soc/generic/Makefile b/sound/soc/generic/Makefile
index 9c3b246792bf..45602ca8536e 100644
--- a/sound/soc/generic/Makefile
+++ b/sound/soc/generic/Makefile
@@ -1,3 +1,5 @@
+obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) := simple-card-utils.o
+
 snd-soc-simple-card-objs	:= simple-card.o
 
 obj-$(CONFIG_SND_SIMPLE_CARD)	+= snd-soc-simple-card.o
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
new file mode 100644
index 000000000000..d89a9a1b2471
--- /dev/null
+++ b/sound/soc/generic/simple-card-utils.c
@@ -0,0 +1,97 @@
+/*
+ * simple-card-core.c
+ *
+ * Copyright (c) 2016 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/of.h>
+#include <sound/simple_card_utils.h>
+
+int asoc_simple_card_parse_daifmt(struct device *dev,
+				  struct device_node *node,
+				  struct device_node *codec,
+				  char *prefix,
+				  unsigned int *retfmt)
+{
+	struct device_node *bitclkmaster = NULL;
+	struct device_node *framemaster = NULL;
+	int prefix_len = prefix ? strlen(prefix) : 0;
+	unsigned int daifmt;
+
+	daifmt = snd_soc_of_parse_daifmt(node, prefix,
+					 &bitclkmaster, &framemaster);
+	daifmt &= ~SND_SOC_DAIFMT_MASTER_MASK;
+
+	if (prefix_len && !bitclkmaster && !framemaster) {
+		/*
+		 * No dai-link level and master setting was not found from
+		 * sound node level, revert back to legacy DT parsing and
+		 * take the settings from codec node.
+		 */
+		dev_dbg(dev, "Revert to legacy daifmt parsing\n");
+
+		daifmt = snd_soc_of_parse_daifmt(codec, NULL, NULL, NULL) |
+			(daifmt & ~SND_SOC_DAIFMT_CLOCK_MASK);
+	} else {
+		if (codec == bitclkmaster)
+			daifmt |= (codec == framemaster) ?
+				SND_SOC_DAIFMT_CBM_CFM : SND_SOC_DAIFMT_CBM_CFS;
+		else
+			daifmt |= (codec == framemaster) ?
+				SND_SOC_DAIFMT_CBS_CFM : SND_SOC_DAIFMT_CBS_CFS;
+	}
+
+	of_node_put(bitclkmaster);
+	of_node_put(framemaster);
+
+	*retfmt = daifmt;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(asoc_simple_card_parse_daifmt);
+
+int asoc_simple_card_set_dailink_name(struct device *dev,
+				      struct snd_soc_dai_link *dai_link,
+				      const char *fmt, ...)
+{
+	va_list ap;
+	char *name = NULL;
+	int ret = -ENOMEM;
+
+	va_start(ap, fmt);
+	name = devm_kvasprintf(dev, GFP_KERNEL, fmt, ap);
+	va_end(ap);
+
+	if (name) {
+		ret = 0;
+
+		dai_link->name		= name;
+		dai_link->stream_name	= name;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(asoc_simple_card_set_dailink_name);
+
+int asoc_simple_card_parse_card_name(struct snd_soc_card *card,
+				     char *prefix)
+{
+	char prop[128];
+	int ret;
+
+	snprintf(prop, sizeof(prop), "%sname", prefix);
+
+	/* Parse the card name from DT */
+	ret = snd_soc_of_parse_card_name(card, prop);
+	if (ret < 0)
+		return ret;
+
+	if (!card->name && card->dai_link)
+		card->name = card->dai_link->name;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(asoc_simple_card_parse_card_name);
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 466492b7d4f5..43295f024982 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -21,6 +21,12 @@
 #include <sound/soc-dai.h>
 #include <sound/soc.h>
 
+struct asoc_simple_jack {
+	struct snd_soc_jack jack;
+	struct snd_soc_jack_pin pin;
+	struct snd_soc_jack_gpio gpio;
+};
+
 struct simple_card_data {
 	struct snd_soc_card snd_card;
 	struct simple_dai_props {
@@ -29,10 +35,8 @@ struct simple_card_data {
 		unsigned int mclk_fs;
 	} *dai_props;
 	unsigned int mclk_fs;
-	int gpio_hp_det;
-	int gpio_hp_det_invert;
-	int gpio_mic_det;
-	int gpio_mic_det_invert;
+	struct asoc_simple_jack hp_jack;
+	struct asoc_simple_jack mic_jack;
 	struct snd_soc_dai_link dai_link[];	/* dynamically allocated */
 };
 
@@ -40,6 +44,69 @@ struct simple_card_data {
 #define simple_priv_to_link(priv, i) ((priv)->snd_card.dai_link + i)
 #define simple_priv_to_props(priv, i) ((priv)->dai_props + i)
 
+#define PREFIX	"simple-audio-card,"
+
+#define asoc_simple_card_init_hp(card, sjack, prefix)\
+	asoc_simple_card_init_jack(card, sjack, 1, prefix)
+#define asoc_simple_card_init_mic(card, sjack, prefix)\
+	asoc_simple_card_init_jack(card, sjack, 0, prefix)
+static int asoc_simple_card_init_jack(struct snd_soc_card *card,
+				      struct asoc_simple_jack *sjack,
+				      int is_hp, char *prefix)
+{
+	struct device *dev = card->dev;
+	enum of_gpio_flags flags;
+	char prop[128];
+	char *pin_name;
+	char *gpio_name;
+	int mask;
+	int det;
+
+	sjack->gpio.gpio = -ENOENT;
+
+	if (is_hp) {
+		snprintf(prop, sizeof(prop), "%shp-det-gpio", prefix);
+		pin_name	= "Headphones";
+		gpio_name	= "Headphone detection";
+		mask		= SND_JACK_HEADPHONE;
+	} else {
+		snprintf(prop, sizeof(prop), "%smic-det-gpio", prefix);
+		pin_name	= "Mic Jack";
+		gpio_name	= "Mic detection";
+		mask		= SND_JACK_MICROPHONE;
+	}
+
+	det = of_get_named_gpio_flags(dev->of_node, prop, 0, &flags);
+	if (det == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
+	if (gpio_is_valid(det)) {
+		sjack->pin.pin		= pin_name;
+		sjack->pin.mask		= mask;
+
+		sjack->gpio.name	= gpio_name;
+		sjack->gpio.report	= mask;
+		sjack->gpio.gpio	= det;
+		sjack->gpio.invert	= !!(flags & OF_GPIO_ACTIVE_LOW);
+		sjack->gpio.debounce_time = 150;
+
+		snd_soc_card_jack_new(card, pin_name, mask,
+				      &sjack->jack,
+				      &sjack->pin, 1);
+
+		snd_soc_jack_add_gpios(&sjack->jack, 1,
+				       &sjack->gpio);
+	}
+
+	return 0;
+}
+
+static void asoc_simple_card_remove_jack(struct asoc_simple_jack *sjack)
+{
+	if (gpio_is_valid(sjack->gpio.gpio))
+		snd_soc_jack_free_gpios(&sjack->jack, 1, &sjack->gpio);
+}
+
 static int asoc_simple_card_startup(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -110,32 +177,6 @@ static struct snd_soc_ops asoc_simple_card_ops = {
 	.hw_params = asoc_simple_card_hw_params,
 };
 
-static struct snd_soc_jack simple_card_hp_jack;
-static struct snd_soc_jack_pin simple_card_hp_jack_pins[] = {
-	{
-		.pin = "Headphones",
-		.mask = SND_JACK_HEADPHONE,
-	},
-};
-static struct snd_soc_jack_gpio simple_card_hp_jack_gpio = {
-	.name = "Headphone detection",
-	.report = SND_JACK_HEADPHONE,
-	.debounce_time = 150,
-};
-
-static struct snd_soc_jack simple_card_mic_jack;
-static struct snd_soc_jack_pin simple_card_mic_jack_pins[] = {
-	{
-		.pin = "Mic Jack",
-		.mask = SND_JACK_MICROPHONE,
-	},
-};
-static struct snd_soc_jack_gpio simple_card_mic_jack_gpio = {
-	.name = "Mic detection",
-	.report = SND_JACK_MICROPHONE,
-	.debounce_time = 150,
-};
-
 static int __asoc_simple_card_dai_init(struct snd_soc_dai *dai,
 				       struct asoc_simple_dai *set)
 {
@@ -184,30 +225,14 @@ static int asoc_simple_card_dai_init(struct snd_soc_pcm_runtime *rtd)
 	if (ret < 0)
 		return ret;
 
-	if (gpio_is_valid(priv->gpio_hp_det)) {
-		snd_soc_card_jack_new(rtd->card, "Headphones",
-				      SND_JACK_HEADPHONE,
-				      &simple_card_hp_jack,
-				      simple_card_hp_jack_pins,
-				      ARRAY_SIZE(simple_card_hp_jack_pins));
-
-		simple_card_hp_jack_gpio.gpio = priv->gpio_hp_det;
-		simple_card_hp_jack_gpio.invert = priv->gpio_hp_det_invert;
-		snd_soc_jack_add_gpios(&simple_card_hp_jack, 1,
-				       &simple_card_hp_jack_gpio);
-	}
+	ret = asoc_simple_card_init_hp(rtd->card, &priv->hp_jack, PREFIX);
+	if (ret < 0)
+		return ret;
+
+	ret = asoc_simple_card_init_mic(rtd->card, &priv->hp_jack, PREFIX);
+	if (ret < 0)
+		return ret;
 
-	if (gpio_is_valid(priv->gpio_mic_det)) {
-		snd_soc_card_jack_new(rtd->card, "Mic Jack",
-				      SND_JACK_MICROPHONE,
-				      &simple_card_mic_jack,
-				      simple_card_mic_jack_pins,
-				      ARRAY_SIZE(simple_card_mic_jack_pins));
-		simple_card_mic_jack_gpio.gpio = priv->gpio_mic_det;
-		simple_card_mic_jack_gpio.invert = priv->gpio_mic_det_invert;
-		snd_soc_jack_add_gpios(&simple_card_mic_jack, 1,
-				       &simple_card_mic_jack_gpio);
-	}
 	return 0;
 }
 
@@ -223,6 +248,9 @@ asoc_simple_card_sub_parse_of(struct device_node *np,
 	u32 val;
 	int ret;
 
+	if (!np)
+		return 0;
+
 	/*
 	 * Get node via "sound-dai = <&phandle port>"
 	 * it will be used as xxx_of_node on soc_bind_dai_link()
@@ -238,9 +266,14 @@ asoc_simple_card_sub_parse_of(struct device_node *np,
 		*args_count = args.args_count;
 
 	/* Get dai->name */
-	ret = snd_soc_of_get_dai_name(np, name);
-	if (ret < 0)
-		return ret;
+	if (name) {
+		ret = snd_soc_of_get_dai_name(np, name);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (!dai)
+		return 0;
 
 	/* Parse TDM slot */
 	ret = snd_soc_of_parse_tdm_slot(np, &dai->tx_slot_mask,
@@ -275,48 +308,6 @@ asoc_simple_card_sub_parse_of(struct device_node *np,
 	return 0;
 }
 
-static int asoc_simple_card_parse_daifmt(struct device_node *node,
-					 struct simple_card_data *priv,
-					 struct device_node *codec,
-					 char *prefix, int idx)
-{
-	struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, idx);
-	struct device *dev = simple_priv_to_dev(priv);
-	struct device_node *bitclkmaster = NULL;
-	struct device_node *framemaster = NULL;
-	unsigned int daifmt;
-
-	daifmt = snd_soc_of_parse_daifmt(node, prefix,
-					 &bitclkmaster, &framemaster);
-	daifmt &= ~SND_SOC_DAIFMT_MASTER_MASK;
-
-	if (strlen(prefix) && !bitclkmaster && !framemaster) {
-		/*
-		 * No dai-link level and master setting was not found from
-		 * sound node level, revert back to legacy DT parsing and
-		 * take the settings from codec node.
-		 */
-		dev_dbg(dev, "Revert to legacy daifmt parsing\n");
-
-		daifmt = snd_soc_of_parse_daifmt(codec, NULL, NULL, NULL) |
-			(daifmt & ~SND_SOC_DAIFMT_CLOCK_MASK);
-	} else {
-		if (codec == bitclkmaster)
-			daifmt |= (codec == framemaster) ?
-				SND_SOC_DAIFMT_CBM_CFM : SND_SOC_DAIFMT_CBM_CFS;
-		else
-			daifmt |= (codec == framemaster) ?
-				SND_SOC_DAIFMT_CBS_CFM : SND_SOC_DAIFMT_CBS_CFS;
-	}
-
-	dai_link->dai_fmt = daifmt;
-
-	of_node_put(bitclkmaster);
-	of_node_put(framemaster);
-
-	return 0;
-}
-
 static int asoc_simple_card_dai_link_of(struct device_node *node,
 					struct simple_card_data *priv,
 					int idx,
@@ -328,7 +319,6 @@ static int asoc_simple_card_dai_link_of(struct device_node *node,
 	struct device_node *cpu = NULL;
 	struct device_node *plat = NULL;
 	struct device_node *codec = NULL;
-	char *name;
 	char prop[128];
 	char *prefix = "";
 	int ret, cpu_args;
@@ -336,7 +326,7 @@ static int asoc_simple_card_dai_link_of(struct device_node *node,
 
 	/* For single DAI link & old style of DT node */
 	if (is_top_level_node)
-		prefix = "simple-audio-card,";
+		prefix = PREFIX;
 
 	snprintf(prop, sizeof(prop), "%scpu", prefix);
 	cpu = of_get_child_by_name(node, prop);
@@ -353,8 +343,8 @@ static int asoc_simple_card_dai_link_of(struct device_node *node,
 		goto dai_link_of_err;
 	}
 
-	ret = asoc_simple_card_parse_daifmt(node, priv,
-					    codec, prefix, idx);
+	ret = asoc_simple_card_parse_daifmt(dev, node, codec,
+					    prefix, &dai_link->dai_fmt);
 	if (ret < 0)
 		goto dai_link_of_err;
 
@@ -374,35 +364,28 @@ static int asoc_simple_card_dai_link_of(struct device_node *node,
 	if (ret < 0)
 		goto dai_link_of_err;
 
+	ret = asoc_simple_card_sub_parse_of(plat, NULL,
+					    &dai_link->platform_of_node,
+					    NULL, NULL);
+	if (ret < 0)
+		goto dai_link_of_err;
+
 	if (!dai_link->cpu_dai_name || !dai_link->codec_dai_name) {
 		ret = -EINVAL;
 		goto dai_link_of_err;
 	}
 
-	if (plat) {
-		struct of_phandle_args args;
-
-		ret = of_parse_phandle_with_args(plat, "sound-dai",
-						 "#sound-dai-cells", 0, &args);
-		dai_link->platform_of_node = args.np;
-	} else {
-		/* Assumes platform == cpu */
+	/* Assumes platform == cpu */
+	if (!dai_link->platform_of_node)
 		dai_link->platform_of_node = dai_link->cpu_of_node;
-	}
 
-	/* DAI link name is created from CPU/CODEC dai name */
-	name = devm_kzalloc(dev,
-			    strlen(dai_link->cpu_dai_name)   +
-			    strlen(dai_link->codec_dai_name) + 2,
-			    GFP_KERNEL);
-	if (!name) {
-		ret = -ENOMEM;
+	ret = asoc_simple_card_set_dailink_name(dev, dai_link,
+						"%s-%s",
+						dai_link->cpu_dai_name,
+						dai_link->codec_dai_name);
+	if (ret < 0)
 		goto dai_link_of_err;
-	}
 
-	sprintf(name, "%s-%s", dai_link->cpu_dai_name,
-				dai_link->codec_dai_name);
-	dai_link->name = dai_link->stream_name = name;
 	dai_link->ops = &asoc_simple_card_ops;
 	dai_link->init = asoc_simple_card_dai_init;
 
@@ -438,42 +421,35 @@ static int asoc_simple_card_parse_of(struct device_node *node,
 				     struct simple_card_data *priv)
 {
 	struct device *dev = simple_priv_to_dev(priv);
-	enum of_gpio_flags flags;
 	u32 val;
 	int ret;
 
 	if (!node)
 		return -EINVAL;
 
-	/* Parse the card name from DT */
-	snd_soc_of_parse_card_name(&priv->snd_card, "simple-audio-card,name");
-
 	/* The off-codec widgets */
-	if (of_property_read_bool(node, "simple-audio-card,widgets")) {
+	if (of_property_read_bool(node, PREFIX "widgets")) {
 		ret = snd_soc_of_parse_audio_simple_widgets(&priv->snd_card,
-					"simple-audio-card,widgets");
+					PREFIX "widgets");
 		if (ret)
 			return ret;
 	}
 
 	/* DAPM routes */
-	if (of_property_read_bool(node, "simple-audio-card,routing")) {
+	if (of_property_read_bool(node, PREFIX "routing")) {
 		ret = snd_soc_of_parse_audio_routing(&priv->snd_card,
-					"simple-audio-card,routing");
+					PREFIX "routing");
 		if (ret)
 			return ret;
 	}
 
 	/* Factor to mclk, used in hw_params() */
-	ret = of_property_read_u32(node, "simple-audio-card,mclk-fs", &val);
+	ret = of_property_read_u32(node, PREFIX "mclk-fs", &val);
 	if (ret == 0)
 		priv->mclk_fs = val;
 
-	dev_dbg(dev, "New simple-card: %s\n", priv->snd_card.name ?
-		priv->snd_card.name : "");
-
 	/* Single/Muti DAI link(s) & New style of DT node */
-	if (of_get_child_by_name(node, "simple-audio-card,dai-link")) {
+	if (of_get_child_by_name(node, PREFIX "dai-link")) {
 		struct device_node *np = NULL;
 		int i = 0;
 
@@ -494,20 +470,9 @@ static int asoc_simple_card_parse_of(struct device_node *node,
 			return ret;
 	}
 
-	priv->gpio_hp_det = of_get_named_gpio_flags(node,
-				"simple-audio-card,hp-det-gpio", 0, &flags);
-	priv->gpio_hp_det_invert = !!(flags & OF_GPIO_ACTIVE_LOW);
-	if (priv->gpio_hp_det == -EPROBE_DEFER)
-		return -EPROBE_DEFER;
-
-	priv->gpio_mic_det = of_get_named_gpio_flags(node,
-				"simple-audio-card,mic-det-gpio", 0, &flags);
-	priv->gpio_mic_det_invert = !!(flags & OF_GPIO_ACTIVE_LOW);
-	if (priv->gpio_mic_det == -EPROBE_DEFER)
-		return -EPROBE_DEFER;
-
-	if (!priv->snd_card.name)
-		priv->snd_card.name = priv->snd_card.dai_link->name;
+	ret = asoc_simple_card_parse_card_name(&priv->snd_card, PREFIX);
+	if (ret)
+		return ret;
 
 	return 0;
 }
@@ -536,7 +501,7 @@ static int asoc_simple_card_probe(struct platform_device *pdev)
 	int num_links, ret;
 
 	/* Get the number of DAI links */
-	if (np && of_get_child_by_name(np, "simple-audio-card,dai-link"))
+	if (np && of_get_child_by_name(np, PREFIX "dai-link"))
 		num_links = of_get_child_count(np);
 	else
 		num_links = 1;
@@ -555,9 +520,6 @@ static int asoc_simple_card_probe(struct platform_device *pdev)
 	priv->snd_card.dai_link = dai_link;
 	priv->snd_card.num_links = num_links;
 
-	priv->gpio_hp_det = -ENOENT;
-	priv->gpio_mic_det = -ENOENT;
-
 	/* Get room for the other properties */
 	priv->dai_props = devm_kzalloc(dev,
 			sizeof(*priv->dai_props) * num_links,
@@ -624,12 +586,8 @@ static int asoc_simple_card_remove(struct platform_device *pdev)
 	struct snd_soc_card *card = platform_get_drvdata(pdev);
 	struct simple_card_data *priv = snd_soc_card_get_drvdata(card);
 
-	if (gpio_is_valid(priv->gpio_hp_det))
-		snd_soc_jack_free_gpios(&simple_card_hp_jack, 1,
-					&simple_card_hp_jack_gpio);
-	if (gpio_is_valid(priv->gpio_mic_det))
-		snd_soc_jack_free_gpios(&simple_card_mic_jack, 1,
-					&simple_card_mic_jack_gpio);
+	asoc_simple_card_remove_jack(&priv->hp_jack);
+	asoc_simple_card_remove_jack(&priv->mic_jack);
 
 	return asoc_simple_card_unref(card);
 }
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index 91c15abb625e..a20c3dfbcb5d 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -7,7 +7,7 @@ config SND_MFLD_MACHINE
 	help
           This adds support for ASoC machine driver for Intel(R) MID Medfield platform
           used as alsa device in audio substem in Intel(R) MID devices
-          Say Y if you have such a device
+          Say Y if you have such a device.
           If unsure select "N".
 
 config SND_SST_MFLD_PLATFORM
@@ -25,7 +25,6 @@ config SND_SST_IPC_ACPI
 	tristate
 	select SND_SST_IPC
 	select SND_SOC_INTEL_SST
-	depends on ACPI
 
 config SND_SOC_INTEL_SST
 	tristate
@@ -33,6 +32,12 @@ config SND_SOC_INTEL_SST
 	select SND_SOC_INTEL_SST_MATCH if ACPI
 	depends on (X86 || COMPILE_TEST)
 
+# firmware stuff depends DW_DMAC_CORE; since there is no depends-on from
+# the reverse selection, each machine driver needs to select
+# SND_SOC_INTEL_SST_FIRMWARE carefully depending on DW_DMAC_CORE
+config SND_SOC_INTEL_SST_FIRMWARE
+	tristate
+
 config SND_SOC_INTEL_SST_ACPI
 	tristate
 
@@ -48,16 +53,33 @@ config SND_SOC_INTEL_BAYTRAIL
 config SND_SOC_INTEL_HASWELL_MACH
 	tristate "ASoC Audio DSP support for Intel Haswell Lynxpoint"
 	depends on X86_INTEL_LPSS && I2C && I2C_DESIGNWARE_PLATFORM
-	depends on DW_DMAC_CORE=y
+	depends on DW_DMAC_CORE
 	select SND_SOC_INTEL_SST
+	select SND_SOC_INTEL_SST_FIRMWARE
 	select SND_SOC_INTEL_HASWELL
 	select SND_SOC_RT5640
 	help
 	  This adds support for the Lynxpoint Audio DSP on Intel(R) Haswell
 	  Ultrabook platforms.
-	  Say Y if you have such a device
+	  Say Y if you have such a device.
 	  If unsure select "N".
 
+config SND_SOC_INTEL_BXT_DA7219_MAX98357A_MACH
+	tristate "ASoC Audio driver for Broxton with DA7219 and MAX98357A in I2S Mode"
+	depends on X86 && ACPI && I2C
+	select SND_SOC_INTEL_SST
+	select SND_SOC_INTEL_SKYLAKE
+	select SND_SOC_DA7219
+	select SND_SOC_MAX98357A
+	select SND_SOC_DMIC
+	select SND_SOC_HDAC_HDMI
+	select SND_HDA_DSP_LOADER
+	help
+	   This adds support for ASoC machine driver for Broxton-P platforms
+	   with DA7219 + MAX98357A I2S audio codec.
+	   Say Y if you have such a device.
+	   If unsure select "N".
+
 config SND_SOC_INTEL_BXT_RT298_MACH
 	tristate "ASoC Audio driver for Broxton with RT298 I2S mode"
 	depends on X86 && ACPI && I2C
@@ -70,26 +92,28 @@ config SND_SOC_INTEL_BXT_RT298_MACH
 	help
 	   This adds support for ASoC machine driver for Broxton platforms
 	   with RT286 I2S audio codec.
-	   Say Y if you have such a device
+	   Say Y if you have such a device.
 	   If unsure select "N".
 
 config SND_SOC_INTEL_BYT_RT5640_MACH
 	tristate "ASoC Audio driver for Intel Baytrail with RT5640 codec"
 	depends on X86_INTEL_LPSS && I2C
-	depends on DW_DMAC_CORE=y && (SND_SST_IPC_ACPI = n)
+	depends on DW_DMAC_CORE && (SND_SST_IPC_ACPI = n)
 	select SND_SOC_INTEL_SST
+	select SND_SOC_INTEL_SST_FIRMWARE
 	select SND_SOC_INTEL_BAYTRAIL
 	select SND_SOC_RT5640
 	help
 	  This adds audio driver for Intel Baytrail platform based boards
 	  with the RT5640 audio codec. This driver is deprecated, use
-	  SND_SOC_INTEL_BYTCR_RT5640_MACH instead for better functionality
+	  SND_SOC_INTEL_BYTCR_RT5640_MACH instead for better functionality.
 
 config SND_SOC_INTEL_BYT_MAX98090_MACH
 	tristate "ASoC Audio driver for Intel Baytrail with MAX98090 codec"
 	depends on X86_INTEL_LPSS && I2C
-	depends on DW_DMAC_CORE=y && (SND_SST_IPC_ACPI = n)
+	depends on DW_DMAC_CORE && (SND_SST_IPC_ACPI = n)
 	select SND_SOC_INTEL_SST
+	select SND_SOC_INTEL_SST_FIRMWARE
 	select SND_SOC_INTEL_BAYTRAIL
 	select SND_SOC_MAX98090
 	help
@@ -100,19 +124,20 @@ config SND_SOC_INTEL_BROADWELL_MACH
 	tristate "ASoC Audio DSP support for Intel Broadwell Wildcatpoint"
 	depends on X86_INTEL_LPSS && I2C && DW_DMAC && \
 		   I2C_DESIGNWARE_PLATFORM
-	depends on DW_DMAC_CORE=y
+	depends on DW_DMAC_CORE
 	select SND_SOC_INTEL_SST
+	select SND_SOC_INTEL_SST_FIRMWARE
 	select SND_SOC_INTEL_HASWELL
 	select SND_SOC_RT286
 	help
 	  This adds support for the Wilcatpoint Audio DSP on Intel(R) Broadwell
 	  Ultrabook platforms.
-	  Say Y if you have such a device
+	  Say Y if you have such a device.
 	  If unsure select "N".
 
 config SND_SOC_INTEL_BYTCR_RT5640_MACH
         tristate "ASoC Audio driver for Intel Baytrail and Baytrail-CR with RT5640 codec"
-	depends on X86 && I2C
+	depends on X86 && I2C && ACPI
 	select SND_SOC_RT5640
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
@@ -120,12 +145,12 @@ config SND_SOC_INTEL_BYTCR_RT5640_MACH
 	help
           This adds support for ASoC machine driver for Intel(R) Baytrail and Baytrail-CR
           platforms with RT5640 audio codec.
-          Say Y if you have such a device
+          Say Y if you have such a device.
           If unsure select "N".
 
 config SND_SOC_INTEL_BYTCR_RT5651_MACH
         tristate "ASoC Audio driver for Intel Baytrail and Baytrail-CR with RT5651 codec"
-	depends on X86 && I2C
+	depends on X86 && I2C && ACPI
 	select SND_SOC_RT5651
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
@@ -133,12 +158,12 @@ config SND_SOC_INTEL_BYTCR_RT5651_MACH
 	help
           This adds support for ASoC machine driver for Intel(R) Baytrail and Baytrail-CR
           platforms with RT5651 audio codec.
-          Say Y if you have such a device
+          Say Y if you have such a device.
           If unsure select "N".
 
 config SND_SOC_INTEL_CHT_BSW_RT5672_MACH
         tristate "ASoC Audio driver for Intel Cherrytrail & Braswell with RT5672 codec"
-        depends on X86_INTEL_LPSS && I2C
+        depends on X86_INTEL_LPSS && I2C && ACPI
         select SND_SOC_RT5670
         select SND_SST_MFLD_PLATFORM
         select SND_SST_IPC_ACPI
@@ -146,12 +171,12 @@ config SND_SOC_INTEL_CHT_BSW_RT5672_MACH
         help
           This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
           platforms with RT5672 audio codec.
-          Say Y if you have such a device
+          Say Y if you have such a device.
           If unsure select "N".
 
 config SND_SOC_INTEL_CHT_BSW_RT5645_MACH
 	tristate "ASoC Audio driver for Intel Cherrytrail & Braswell with RT5645/5650 codec"
-	depends on X86_INTEL_LPSS && I2C
+	depends on X86_INTEL_LPSS && I2C && ACPI
 	select SND_SOC_RT5645
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
@@ -163,16 +188,16 @@ config SND_SOC_INTEL_CHT_BSW_RT5645_MACH
 
 config SND_SOC_INTEL_CHT_BSW_MAX98090_TI_MACH
 	tristate "ASoC Audio driver for Intel Cherrytrail & Braswell with MAX98090 & TI codec"
-	depends on X86_INTEL_LPSS && I2C
+	depends on X86_INTEL_LPSS && I2C && ACPI
 	select SND_SOC_MAX98090
 	select SND_SOC_TS3A227E
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
 	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
-      This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
-      platforms with MAX98090 audio codec it also can support TI jack chip as aux device.
-      If unsure select "N".
+	  This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
+	  platforms with MAX98090 audio codec it also can support TI jack chip as aux device.
+	  If unsure select "N".
 
 config SND_SOC_INTEL_SKYLAKE
 	tristate
@@ -192,7 +217,7 @@ config SND_SOC_INTEL_SKL_RT286_MACH
 	help
 	   This adds support for ASoC machine driver for Skylake platforms
 	   with RT286 I2S audio codec.
-	   Say Y if you have such a device
+	   Say Y if you have such a device.
 	   If unsure select "N".
 
 config SND_SOC_INTEL_SKL_NAU88L25_SSM4567_MACH
@@ -207,7 +232,7 @@ config SND_SOC_INTEL_SKL_NAU88L25_SSM4567_MACH
 	help
 	  This adds support for ASoC Onboard Codec I2S machine driver. This will
 	  create an alsa sound card for NAU88L25 + SSM4567.
-	  Say Y if you have such a device
+	  Say Y if you have such a device.
 	  If unsure select "N".
 
 config SND_SOC_INTEL_SKL_NAU88L25_MAX98357A_MACH
@@ -222,5 +247,5 @@ config SND_SOC_INTEL_SKL_NAU88L25_MAX98357A_MACH
 	help
 	  This adds support for ASoC Onboard Codec I2S machine driver. This will
 	  create an alsa sound card for NAU88L25 + MAX98357A.
-	  Say Y if you have such a device
+	  Say Y if you have such a device.
 	  If unsure select "N".
diff --git a/sound/soc/intel/atom/sst/sst_acpi.c b/sound/soc/intel/atom/sst/sst_acpi.c
index 3bc4b63b2f9d..4d3184971227 100644
--- a/sound/soc/intel/atom/sst/sst_acpi.c
+++ b/sound/soc/intel/atom/sst/sst_acpi.c
@@ -28,6 +28,7 @@
 #include <linux/firmware.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_qos.h>
+#include <linux/dmi.h>
 #include <linux/acpi.h>
 #include <asm/platform_sst_audio.h>
 #include <sound/core.h>
@@ -237,6 +238,9 @@ static int sst_acpi_probe(struct platform_device *pdev)
 		dev_err(dev, "No matching machine driver found\n");
 		return -ENODEV;
 	}
+	if (mach->machine_quirk)
+		mach = mach->machine_quirk(mach);
+
 	pdata = mach->pdata;
 
 	ret = kstrtouint(id->id, 16, &dev_id);
@@ -320,6 +324,44 @@ static int sst_acpi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static unsigned long cht_machine_id;
+
+#define CHT_SURFACE_MACH 1
+
+static int cht_surface_quirk_cb(const struct dmi_system_id *id)
+{
+	cht_machine_id = CHT_SURFACE_MACH;
+	return 1;
+}
+
+
+static const struct dmi_system_id cht_table[] = {
+	{
+		.callback = cht_surface_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Surface 3"),
+		},
+	},
+};
+
+
+static struct sst_acpi_mach cht_surface_mach = {
+	"10EC5640", "cht-bsw-rt5645", "intel/fw_sst_22a8.bin", "cht-bsw", NULL,
+								&chv_platform_data };
+
+static struct sst_acpi_mach *cht_quirk(void *arg)
+{
+	struct sst_acpi_mach *mach = arg;
+
+	dmi_check_system(cht_table);
+
+	if (cht_machine_id == CHT_SURFACE_MACH)
+		return &cht_surface_mach;
+	else
+		return mach;
+}
+
 static struct sst_acpi_mach sst_acpi_bytcr[] = {
 	{"10EC5640", "bytcr_rt5640", "intel/fw_sst_0f28.bin", "bytcr_rt5640", NULL,
 						&byt_rvp_platform_data },
@@ -343,7 +385,7 @@ static struct sst_acpi_mach sst_acpi_chv[] = {
 	{"193C9890", "cht-bsw-max98090", "intel/fw_sst_22a8.bin", "cht-bsw", NULL,
 						&chv_platform_data },
 	/* some CHT-T platforms rely on RT5640, use Baytrail machine driver */
-	{"10EC5640", "bytcr_rt5640", "intel/fw_sst_22a8.bin", "bytcr_rt5640", NULL,
+	{"10EC5640", "bytcr_rt5640", "intel/fw_sst_22a8.bin", "bytcr_rt5640", cht_quirk,
 						&chv_platform_data },
 
 	{},
diff --git a/sound/soc/intel/boards/Makefile b/sound/soc/intel/boards/Makefile
index a8506774f510..dac03a06bfd8 100644
--- a/sound/soc/intel/boards/Makefile
+++ b/sound/soc/intel/boards/Makefile
@@ -2,6 +2,7 @@ snd-soc-sst-haswell-objs := haswell.o
 snd-soc-sst-byt-rt5640-mach-objs := byt-rt5640.o
 snd-soc-sst-byt-max98090-mach-objs := byt-max98090.o
 snd-soc-sst-broadwell-objs := broadwell.o
+snd-soc-sst-bxt-da7219_max98357a-objs := bxt_da7219_max98357a.o
 snd-soc-sst-bxt-rt298-objs := bxt_rt298.o
 snd-soc-sst-bytcr-rt5640-objs := bytcr_rt5640.o
 snd-soc-sst-bytcr-rt5651-objs := bytcr_rt5651.o
@@ -15,6 +16,7 @@ snd-soc-skl_nau88l25_ssm4567-objs := skl_nau88l25_ssm4567.o
 obj-$(CONFIG_SND_SOC_INTEL_HASWELL_MACH) += snd-soc-sst-haswell.o
 obj-$(CONFIG_SND_SOC_INTEL_BYT_RT5640_MACH) += snd-soc-sst-byt-rt5640-mach.o
 obj-$(CONFIG_SND_SOC_INTEL_BYT_MAX98090_MACH) += snd-soc-sst-byt-max98090-mach.o
+obj-$(CONFIG_SND_SOC_INTEL_BXT_DA7219_MAX98357A_MACH) += snd-soc-sst-bxt-da7219_max98357a.o
 obj-$(CONFIG_SND_SOC_INTEL_BXT_RT298_MACH) += snd-soc-sst-bxt-rt298.o
 obj-$(CONFIG_SND_SOC_INTEL_BROADWELL_MACH) += snd-soc-sst-broadwell.o
 obj-$(CONFIG_SND_SOC_INTEL_BYTCR_RT5640_MACH) += snd-soc-sst-bytcr-rt5640.o
diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
new file mode 100644
index 000000000000..3774b117d365
--- /dev/null
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -0,0 +1,460 @@
+/*
+ * Intel Broxton-P I2S Machine Driver
+ *
+ * Copyright (C) 2016, Intel Corporation. All rights reserved.
+ *
+ * Modified from:
+ *   Intel Skylake I2S Machine driver
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <sound/core.h>
+#include <sound/jack.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include "../../codecs/hdac_hdmi.h"
+#include "../../codecs/da7219.h"
+#include "../../codecs/da7219-aad.h"
+
+#define BXT_DIALOG_CODEC_DAI	"da7219-hifi"
+#define BXT_MAXIM_CODEC_DAI	"HiFi"
+#define DUAL_CHANNEL		2
+
+static struct snd_soc_jack broxton_headset;
+
+enum {
+	BXT_DPCM_AUDIO_PB = 0,
+	BXT_DPCM_AUDIO_CP,
+	BXT_DPCM_AUDIO_REF_CP,
+	BXT_DPCM_AUDIO_HDMI1_PB,
+	BXT_DPCM_AUDIO_HDMI2_PB,
+	BXT_DPCM_AUDIO_HDMI3_PB,
+};
+
+static const struct snd_kcontrol_new broxton_controls[] = {
+	SOC_DAPM_PIN_SWITCH("Headphone Jack"),
+	SOC_DAPM_PIN_SWITCH("Headset Mic"),
+	SOC_DAPM_PIN_SWITCH("Spk"),
+};
+
+static const struct snd_soc_dapm_widget broxton_widgets[] = {
+	SND_SOC_DAPM_HP("Headphone Jack", NULL),
+	SND_SOC_DAPM_MIC("Headset Mic", NULL),
+	SND_SOC_DAPM_SPK("Spk", NULL),
+	SND_SOC_DAPM_MIC("SoC DMIC", NULL),
+	SND_SOC_DAPM_SPK("HDMI1", NULL),
+	SND_SOC_DAPM_SPK("HDMI2", NULL),
+	SND_SOC_DAPM_SPK("HDMI3", NULL),
+};
+
+static const struct snd_soc_dapm_route broxton_map[] = {
+	/* HP jack connectors - unknown if we have jack detection */
+	{"Headphone Jack", NULL, "HPL"},
+	{"Headphone Jack", NULL, "HPR"},
+
+	/* speaker */
+	{"Spk", NULL, "Speaker"},
+
+	/* other jacks */
+	{"MIC", NULL, "Headset Mic"},
+
+	/* digital mics */
+	{"DMic", NULL, "SoC DMIC"},
+
+	/* CODEC BE connections */
+	{"HiFi Playback", NULL, "ssp5 Tx"},
+	{"ssp5 Tx", NULL, "codec0_out"},
+
+	{"Playback", NULL, "ssp1 Tx"},
+	{"ssp1 Tx", NULL, "codec1_out"},
+
+	{"codec0_in", NULL, "ssp1 Rx"},
+	{"ssp1 Rx", NULL, "Capture"},
+
+	{"HDMI1", NULL, "hif5 Output"},
+	{"HDMI2", NULL, "hif6 Output"},
+	{"HDMI3", NULL, "hif7 Output"},
+
+	{"hifi3", NULL, "iDisp3 Tx"},
+	{"iDisp3 Tx", NULL, "iDisp3_out"},
+	{"hifi2", NULL, "iDisp2 Tx"},
+	{"iDisp2 Tx", NULL, "iDisp2_out"},
+	{"hifi1", NULL, "iDisp1 Tx"},
+	{"iDisp1 Tx", NULL, "iDisp1_out"},
+
+	/* DMIC */
+	{"dmic01_hifi", NULL, "DMIC01 Rx"},
+	{"DMIC01 Rx", NULL, "DMIC AIF"},
+};
+
+static int broxton_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
+			struct snd_pcm_hw_params *params)
+{
+	struct snd_interval *rate = hw_param_interval(params,
+			SNDRV_PCM_HW_PARAM_RATE);
+	struct snd_interval *channels = hw_param_interval(params,
+			SNDRV_PCM_HW_PARAM_CHANNELS);
+	struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
+
+	/* The ADSP will convert the FE rate to 48k, stereo */
+	rate->min = rate->max = 48000;
+	channels->min = channels->max = DUAL_CHANNEL;
+
+	/* set SSP to 24 bit */
+	snd_mask_none(fmt);
+	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+
+	return 0;
+}
+
+static int broxton_da7219_codec_init(struct snd_soc_pcm_runtime *rtd)
+{
+	int ret;
+	struct snd_soc_codec *codec = rtd->codec;
+
+	/*
+	 * Headset buttons map to the google Reference headset.
+	 * These can be configured by userspace.
+	 */
+	ret = snd_soc_card_jack_new(rtd->card, "Headset Jack",
+			SND_JACK_HEADSET | SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+			SND_JACK_BTN_2 | SND_JACK_BTN_3, &broxton_headset,
+			NULL, 0);
+	if (ret) {
+		dev_err(rtd->dev, "Headset Jack creation failed: %d\n", ret);
+		return ret;
+	}
+
+	da7219_aad_jack_det(codec, &broxton_headset);
+
+	snd_soc_dapm_ignore_suspend(&rtd->card->dapm, "SoC DMIC");
+
+	return ret;
+}
+
+static int broxton_hdmi_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct snd_soc_dai *dai = rtd->codec_dai;
+
+	return hdac_hdmi_jack_init(dai, BXT_DPCM_AUDIO_HDMI1_PB + dai->id);
+}
+
+static int broxton_da7219_fe_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct snd_soc_dapm_context *dapm;
+	struct snd_soc_component *component = rtd->cpu_dai->component;
+
+	dapm = snd_soc_component_get_dapm(component);
+	snd_soc_dapm_ignore_suspend(dapm, "Reference Capture");
+
+	return 0;
+}
+
+static unsigned int rates[] = {
+	48000,
+};
+
+static struct snd_pcm_hw_constraint_list constraints_rates = {
+	.count = ARRAY_SIZE(rates),
+	.list  = rates,
+	.mask = 0,
+};
+
+static unsigned int channels[] = {
+	DUAL_CHANNEL,
+};
+
+static struct snd_pcm_hw_constraint_list constraints_channels = {
+	.count = ARRAY_SIZE(channels),
+	.list = channels,
+	.mask = 0,
+};
+
+static int bxt_fe_startup(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+
+	/*
+	 * On this platform for PCM device we support,
+	 * 48Khz
+	 * stereo
+	 * 16 bit audio
+	 */
+
+	runtime->hw.channels_max = DUAL_CHANNEL;
+	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
+					   &constraints_channels);
+
+	runtime->hw.formats = SNDRV_PCM_FMTBIT_S16_LE;
+	snd_pcm_hw_constraint_msbits(runtime, 0, 16, 16);
+
+	snd_pcm_hw_constraint_list(runtime, 0,
+				SNDRV_PCM_HW_PARAM_RATE, &constraints_rates);
+
+	return 0;
+}
+
+static const struct snd_soc_ops broxton_da7219_fe_ops = {
+	.startup = bxt_fe_startup,
+};
+
+static int broxton_da7219_hw_params(struct snd_pcm_substream *substream,
+				struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	int ret;
+
+	ret = snd_soc_dai_set_sysclk(codec_dai,
+			DA7219_CLKSRC_MCLK, 19200000, SND_SOC_CLOCK_IN);
+	if (ret < 0)
+		dev_err(codec_dai->dev, "can't set codec sysclk configuration\n");
+
+	ret = snd_soc_dai_set_pll(codec_dai, 0,
+			DA7219_SYSCLK_PLL_SRM, 0, DA7219_PLL_FREQ_OUT_98304);
+	if (ret < 0) {
+		dev_err(codec_dai->dev, "failed to start PLL: %d\n", ret);
+		return -EIO;
+	}
+
+	return ret;
+}
+
+static int broxton_da7219_hw_free(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	int ret;
+
+	ret = snd_soc_dai_set_pll(codec_dai, 0,
+			DA7219_SYSCLK_MCLK, 0, 0);
+	if (ret < 0) {
+		dev_err(codec_dai->dev, "failed to stop PLL: %d\n", ret);
+		return -EIO;
+	}
+
+	return ret;
+}
+
+static struct snd_soc_ops broxton_da7219_ops = {
+	.hw_params = broxton_da7219_hw_params,
+	.hw_free = broxton_da7219_hw_free,
+};
+
+/* broxton digital audio interface glue - connects codec <--> CPU */
+static struct snd_soc_dai_link broxton_dais[] = {
+	/* Front End DAI links */
+	[BXT_DPCM_AUDIO_PB]
+	{
+		.name = "Bxt Audio Port",
+		.stream_name = "Audio",
+		.cpu_dai_name = "System Pin",
+		.platform_name = "0000:00:0e.0",
+		.dynamic = 1,
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.nonatomic = 1,
+		.init = broxton_da7219_fe_init,
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.dpcm_playback = 1,
+		.ops = &broxton_da7219_fe_ops,
+	},
+	[BXT_DPCM_AUDIO_CP]
+	{
+		.name = "Bxt Audio Capture Port",
+		.stream_name = "Audio Record",
+		.cpu_dai_name = "System Pin",
+		.platform_name = "0000:00:0e.0",
+		.dynamic = 1,
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.nonatomic = 1,
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.dpcm_capture = 1,
+		.ops = &broxton_da7219_fe_ops,
+	},
+	[BXT_DPCM_AUDIO_REF_CP]
+	{
+		.name = "Bxt Audio Reference cap",
+		.stream_name = "Refcap",
+		.cpu_dai_name = "Reference Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.init = NULL,
+		.dpcm_capture = 1,
+		.ignore_suspend = 1,
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	[BXT_DPCM_AUDIO_HDMI1_PB]
+	{
+		.name = "Bxt HDMI Port1",
+		.stream_name = "Hdmi1",
+		.cpu_dai_name = "HDMI1 Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.dpcm_playback = 1,
+		.init = NULL,
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	[BXT_DPCM_AUDIO_HDMI2_PB]
+	{
+		.name = "Bxt HDMI Port2",
+		.stream_name = "Hdmi2",
+		.cpu_dai_name = "HDMI2 Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.dpcm_playback = 1,
+		.init = NULL,
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	[BXT_DPCM_AUDIO_HDMI3_PB]
+	{
+		.name = "Bxt HDMI Port3",
+		.stream_name = "Hdmi3",
+		.cpu_dai_name = "HDMI3 Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.dpcm_playback = 1,
+		.init = NULL,
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	/* Back End DAI links */
+	{
+		/* SSP5 - Codec */
+		.name = "SSP5-Codec",
+		.id = 0,
+		.cpu_dai_name = "SSP5 Pin",
+		.platform_name = "0000:00:0e.0",
+		.no_pcm = 1,
+		.codec_name = "MX98357A:00",
+		.codec_dai_name = BXT_MAXIM_CODEC_DAI,
+		.dai_fmt = SND_SOC_DAIFMT_I2S |
+			SND_SOC_DAIFMT_NB_NF |
+			SND_SOC_DAIFMT_CBS_CFS,
+		.ignore_pmdown_time = 1,
+		.be_hw_params_fixup = broxton_ssp_fixup,
+		.dpcm_playback = 1,
+	},
+	{
+		/* SSP1 - Codec */
+		.name = "SSP1-Codec",
+		.id = 1,
+		.cpu_dai_name = "SSP1 Pin",
+		.platform_name = "0000:00:0e.0",
+		.no_pcm = 1,
+		.codec_name = "i2c-DLGS7219:00",
+		.codec_dai_name = BXT_DIALOG_CODEC_DAI,
+		.init = broxton_da7219_codec_init,
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
+			SND_SOC_DAIFMT_CBS_CFS,
+		.ignore_pmdown_time = 1,
+		.be_hw_params_fixup = broxton_ssp_fixup,
+		.ops = &broxton_da7219_ops,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+	},
+	{
+		.name = "dmic01",
+		.id = 2,
+		.cpu_dai_name = "DMIC01 Pin",
+		.codec_name = "dmic-codec",
+		.codec_dai_name = "dmic-hifi",
+		.platform_name = "0000:00:0e.0",
+		.ignore_suspend = 1,
+		.dpcm_capture = 1,
+		.no_pcm = 1,
+	},
+	{
+		.name = "iDisp1",
+		.id = 3,
+		.cpu_dai_name = "iDisp1 Pin",
+		.codec_name = "ehdaudio0D2",
+		.codec_dai_name = "intel-hdmi-hifi1",
+		.platform_name = "0000:00:0e.0",
+		.init = broxton_hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+	},
+	{
+		.name = "iDisp2",
+		.id = 4,
+		.cpu_dai_name = "iDisp2 Pin",
+		.codec_name = "ehdaudio0D2",
+		.codec_dai_name = "intel-hdmi-hifi2",
+		.platform_name = "0000:00:0e.0",
+		.init = broxton_hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+	},
+	{
+		.name = "iDisp3",
+		.id = 5,
+		.cpu_dai_name = "iDisp3 Pin",
+		.codec_name = "ehdaudio0D2",
+		.codec_dai_name = "intel-hdmi-hifi3",
+		.platform_name = "0000:00:0e.0",
+		.init = broxton_hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+	},
+};
+
+/* broxton audio machine driver for SPT + da7219 */
+static struct snd_soc_card broxton_audio_card = {
+	.name = "bxtda7219max",
+	.owner = THIS_MODULE,
+	.dai_link = broxton_dais,
+	.num_links = ARRAY_SIZE(broxton_dais),
+	.controls = broxton_controls,
+	.num_controls = ARRAY_SIZE(broxton_controls),
+	.dapm_widgets = broxton_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(broxton_widgets),
+	.dapm_routes = broxton_map,
+	.num_dapm_routes = ARRAY_SIZE(broxton_map),
+	.fully_routed = true,
+};
+
+static int broxton_audio_probe(struct platform_device *pdev)
+{
+	broxton_audio_card.dev = &pdev->dev;
+	return devm_snd_soc_register_card(&pdev->dev, &broxton_audio_card);
+}
+
+static struct platform_driver broxton_audio = {
+	.probe = broxton_audio_probe,
+	.driver = {
+		.name = "bxt_da7219_max98357a_i2s",
+		.pm = &snd_soc_pm_ops,
+	},
+};
+module_platform_driver(broxton_audio)
+
+/* Module information */
+MODULE_DESCRIPTION("Audio Machine driver-DA7219 & MAX98357A in I2S mode");
+MODULE_AUTHOR("Sathyanarayana Nujella <sathyanarayana.nujella@intel.com>");
+MODULE_AUTHOR("Rohit Ainapure <rohit.m.ainapure@intel.com>");
+MODULE_AUTHOR("Harsha Priya <harshapriya.n@intel.com>");
+MODULE_AUTHOR("Conrad Cooke <conrad.cooke@intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:bxt_da7219_max98357a_i2s");
diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c
index f4787515c0ed..253d7bfbf511 100644
--- a/sound/soc/intel/boards/bxt_rt298.c
+++ b/sound/soc/intel/boards/bxt_rt298.c
@@ -33,6 +33,7 @@ enum {
 	BXT_DPCM_AUDIO_PB = 0,
 	BXT_DPCM_AUDIO_CP,
 	BXT_DPCM_AUDIO_REF_CP,
+	BXT_DPCM_AUDIO_DMIC_CP,
 	BXT_DPCM_AUDIO_HDMI1_PB,
 	BXT_DPCM_AUDIO_HDMI2_PB,
 	BXT_DPCM_AUDIO_HDMI3_PB,
@@ -88,6 +89,7 @@ static const struct snd_soc_dapm_route broxton_rt298_map[] = {
 	/* CODEC BE connections */
 	{ "AIF1 Playback", NULL, "ssp5 Tx"},
 	{ "ssp5 Tx", NULL, "codec0_out"},
+	{ "ssp5 Tx", NULL, "codec1_out"},
 
 	{ "codec0_in", NULL, "ssp5 Rx" },
 	{ "ssp5 Rx", NULL, "AIF1 Capture" },
@@ -104,6 +106,17 @@ static const struct snd_soc_dapm_route broxton_rt298_map[] = {
 
 };
 
+static int broxton_rt298_fe_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct snd_soc_dapm_context *dapm;
+	struct snd_soc_component *component = rtd->cpu_dai->component;
+
+	dapm = snd_soc_component_get_dapm(component);
+	snd_soc_dapm_ignore_suspend(dapm, "Reference Capture");
+
+	return 0;
+}
+
 static int broxton_rt298_codec_init(struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_soc_codec *codec = rtd->codec;
@@ -118,6 +131,9 @@ static int broxton_rt298_codec_init(struct snd_soc_pcm_runtime *rtd)
 		return ret;
 
 	rt298_mic_detect(codec, &broxton_headset);
+
+	snd_soc_dapm_ignore_suspend(&rtd->card->dapm, "SoC DMIC");
+
 	return 0;
 }
 
@@ -169,6 +185,89 @@ static struct snd_soc_ops broxton_rt298_ops = {
 	.hw_params = broxton_rt298_hw_params,
 };
 
+static unsigned int rates[] = {
+	48000,
+};
+
+static struct snd_pcm_hw_constraint_list constraints_rates = {
+	.count = ARRAY_SIZE(rates),
+	.list  = rates,
+	.mask = 0,
+};
+
+static int broxton_dmic_fixup(struct snd_soc_pcm_runtime *rtd,
+				struct snd_pcm_hw_params *params)
+{
+	struct snd_interval *channels = hw_param_interval(params,
+						SNDRV_PCM_HW_PARAM_CHANNELS);
+	if (params_channels(params) == 2)
+		channels->min = channels->max = 2;
+	else
+		channels->min = channels->max = 4;
+
+	return 0;
+}
+
+static unsigned int channels_dmic[] = {
+	2, 4,
+};
+
+static struct snd_pcm_hw_constraint_list constraints_dmic_channels = {
+	.count = ARRAY_SIZE(channels_dmic),
+	.list = channels_dmic,
+	.mask = 0,
+};
+
+static int broxton_dmic_startup(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+
+	runtime->hw.channels_max = 4;
+	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
+					&constraints_dmic_channels);
+
+	return snd_pcm_hw_constraint_list(substream->runtime, 0,
+				SNDRV_PCM_HW_PARAM_RATE, &constraints_rates);
+}
+
+static struct snd_soc_ops broxton_dmic_ops = {
+	.startup = broxton_dmic_startup,
+};
+
+static unsigned int channels[] = {
+	2,
+};
+
+static struct snd_pcm_hw_constraint_list constraints_channels = {
+	.count = ARRAY_SIZE(channels),
+	.list = channels,
+	.mask = 0,
+};
+
+static int bxt_fe_startup(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+
+	/*
+	 * on this platform for PCM device we support:
+	 *      48Khz
+	 *      stereo
+	 */
+
+	runtime->hw.channels_max = 2;
+	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
+				&constraints_channels);
+
+	snd_pcm_hw_constraint_list(runtime, 0,
+				SNDRV_PCM_HW_PARAM_RATE, &constraints_rates);
+
+	return 0;
+}
+
+static const struct snd_soc_ops broxton_rt286_fe_ops = {
+	.startup = bxt_fe_startup,
+};
+
 /* broxton digital audio interface glue - connects codec <--> CPU */
 static struct snd_soc_dai_link broxton_rt298_dais[] = {
 	/* Front End DAI links */
@@ -182,8 +281,10 @@ static struct snd_soc_dai_link broxton_rt298_dais[] = {
 		.dynamic = 1,
 		.codec_name = "snd-soc-dummy",
 		.codec_dai_name = "snd-soc-dummy-dai",
+		.init = broxton_rt298_fe_init,
 		.trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
 		.dpcm_playback = 1,
+		.ops = &broxton_rt286_fe_ops,
 	},
 	[BXT_DPCM_AUDIO_CP]
 	{
@@ -197,6 +298,7 @@ static struct snd_soc_dai_link broxton_rt298_dais[] = {
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
 		.dpcm_capture = 1,
+		.ops = &broxton_rt286_fe_ops,
 	},
 	[BXT_DPCM_AUDIO_REF_CP]
 	{
@@ -211,6 +313,20 @@ static struct snd_soc_dai_link broxton_rt298_dais[] = {
 		.nonatomic = 1,
 		.dynamic = 1,
 	},
+	[BXT_DPCM_AUDIO_DMIC_CP]
+	{
+		.name = "Bxt Audio DMIC cap",
+		.stream_name = "dmiccap",
+		.cpu_dai_name = "DMIC Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.init = NULL,
+		.dpcm_capture = 1,
+		.nonatomic = 1,
+		.dynamic = 1,
+		.ops = &broxton_dmic_ops,
+	},
 	[BXT_DPCM_AUDIO_HDMI1_PB]
 	{
 		.name = "Bxt HDMI Port1",
@@ -276,6 +392,7 @@ static struct snd_soc_dai_link broxton_rt298_dais[] = {
 		.codec_name = "dmic-codec",
 		.codec_dai_name = "dmic-hifi",
 		.platform_name = "0000:00:0e.0",
+		.be_hw_params_fixup = broxton_dmic_fixup,
 		.ignore_suspend = 1,
 		.dpcm_capture = 1,
 		.no_pcm = 1,
@@ -341,6 +458,7 @@ static struct platform_driver broxton_audio = {
 	.probe = broxton_audio_probe,
 	.driver = {
 		.name = "bxt_alc298s_i2s",
+		.pm = &snd_soc_pm_ops,
 	},
 };
 module_platform_driver(broxton_audio)
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index d7ef292c402d..56056ed7fcfd 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -30,6 +30,7 @@
 #include <sound/jack.h>
 #include "../../codecs/rt5645.h"
 #include "../atom/sst-atom-controls.h"
+#include "../common/sst-acpi.h"
 
 #define CHT_PLAT_CLK_3_HZ	19200000
 #define CHT_CODEC_DAI	"rt5645-aif1"
@@ -340,10 +341,13 @@ static struct snd_soc_card snd_soc_card_chtrt5650 = {
 };
 
 static struct cht_acpi_card snd_soc_cards[] = {
+	{"10EC5640", CODEC_TYPE_RT5645, &snd_soc_card_chtrt5645},
 	{"10EC5645", CODEC_TYPE_RT5645, &snd_soc_card_chtrt5645},
 	{"10EC5650", CODEC_TYPE_RT5650, &snd_soc_card_chtrt5650},
 };
 
+static char cht_rt5640_codec_name[16]; /* i2c-<HID>:00 with HID being 8 chars */
+
 static int snd_cht_mc_probe(struct platform_device *pdev)
 {
 	int ret_val = 0;
@@ -351,6 +355,9 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	struct cht_mc_private *drv;
 	struct snd_soc_card *card = snd_soc_cards[0].soc_card;
 	char codec_name[16];
+	struct sst_acpi_mach *mach;
+	const char *i2c_name = NULL;
+	int dai_index = 0;
 
 	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_ATOMIC);
 	if (!drv)
@@ -366,12 +373,23 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 		}
 	}
 	card->dev = &pdev->dev;
+	mach = card->dev->platform_data;
 	sprintf(codec_name, "i2c-%s:00", drv->acpi_card->codec_id);
 
 	/* set correct codec name */
 	for (i = 0; i < ARRAY_SIZE(cht_dailink); i++)
-		if (!strcmp(card->dai_link[i].codec_name, "i2c-10EC5645:00"))
+		if (!strcmp(card->dai_link[i].codec_name, "i2c-10EC5645:00")) {
 			card->dai_link[i].codec_name = kstrdup(codec_name, GFP_KERNEL);
+			dai_index = i;
+		}
+
+	/* fixup codec name based on HID */
+	i2c_name = sst_acpi_find_name_from_hid(mach->id);
+	if (i2c_name != NULL) {
+		snprintf(cht_rt5640_codec_name, sizeof(cht_rt5640_codec_name),
+			"%s%s", "i2c-", i2c_name);
+		cht_dailink[dai_index].codec_name = cht_rt5640_codec_name;
+	}
 
 	snd_soc_card_set_drvdata(card, drv);
 	ret_val = devm_snd_soc_register_card(&pdev->dev, card);
diff --git a/sound/soc/intel/boards/skl_nau88l25_max98357a.c b/sound/soc/intel/boards/skl_nau88l25_max98357a.c
index d2808652b974..25db5be7fdfa 100644
--- a/sound/soc/intel/boards/skl_nau88l25_max98357a.c
+++ b/sound/soc/intel/boards/skl_nau88l25_max98357a.c
@@ -23,12 +23,15 @@
 #include <sound/soc.h>
 #include "../../codecs/nau8825.h"
 #include "../../codecs/hdac_hdmi.h"
+#include "../skylake/skl.h"
 
 #define SKL_NUVOTON_CODEC_DAI	"nau8825-hifi"
 #define SKL_MAXIM_CODEC_DAI "HiFi"
+#define DMIC_CH(p)     p->list[p->count-1]
 
 static struct snd_soc_jack skylake_headset;
 static struct snd_soc_card skylake_audio_card;
+static const struct snd_pcm_hw_constraint_list *dmic_constraints;
 
 struct skl_hdmi_pcm {
 	struct list_head head;
@@ -339,7 +342,7 @@ static int skylake_dmic_fixup(struct snd_soc_pcm_runtime *rtd,
 	struct snd_interval *channels = hw_param_interval(params,
 				SNDRV_PCM_HW_PARAM_CHANNELS);
 
-	if (params_channels(params) == 2)
+	if (params_channels(params) == 2 || DMIC_CH(dmic_constraints) == 2)
 		channels->min = channels->max = 2;
 	else
 		channels->min = channels->max = 4;
@@ -357,13 +360,23 @@ static struct snd_pcm_hw_constraint_list constraints_dmic_channels = {
 	.mask = 0,
 };
 
+static const unsigned int dmic_2ch[] = {
+	2,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_dmic_2ch = {
+	.count = ARRAY_SIZE(dmic_2ch),
+	.list = dmic_2ch,
+	.mask = 0,
+};
+
 static int skylake_dmic_startup(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 
-	runtime->hw.channels_max = 4;
+	runtime->hw.channels_max = DMIC_CH(dmic_constraints);
 	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
-			&constraints_dmic_channels);
+			dmic_constraints);
 
 	return snd_pcm_hw_constraint_list(substream->runtime, 0,
 			SNDRV_PCM_HW_PARAM_RATE, &constraints_rates);
@@ -382,8 +395,22 @@ static struct snd_pcm_hw_constraint_list constraints_16000 = {
 	.list  = rates_16000,
 };
 
+static const unsigned int ch_mono[] = {
+	1,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_refcap = {
+	.count = ARRAY_SIZE(ch_mono),
+	.list  = ch_mono,
+};
+
 static int skylake_refcap_startup(struct snd_pcm_substream *substream)
 {
+	substream->runtime->hw.channels_max = 1;
+	snd_pcm_hw_constraint_list(substream->runtime, 0,
+					SNDRV_PCM_HW_PARAM_CHANNELS,
+					&constraints_refcap);
+
 	return snd_pcm_hw_constraint_list(substream->runtime, 0,
 				SNDRV_PCM_HW_PARAM_RATE,
 				&constraints_16000);
@@ -610,6 +637,7 @@ static struct snd_soc_card skylake_audio_card = {
 static int skylake_audio_probe(struct platform_device *pdev)
 {
 	struct skl_nau8825_private *ctx;
+	struct skl_machine_pdata *pdata;
 
 	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
 	if (!ctx)
@@ -620,15 +648,27 @@ static int skylake_audio_probe(struct platform_device *pdev)
 	skylake_audio_card.dev = &pdev->dev;
 	snd_soc_card_set_drvdata(&skylake_audio_card, ctx);
 
+	pdata = dev_get_drvdata(&pdev->dev);
+	if (pdata)
+		dmic_constraints = pdata->dmic_num == 2 ?
+			&constraints_dmic_2ch : &constraints_dmic_channels;
+
 	return devm_snd_soc_register_card(&pdev->dev, &skylake_audio_card);
 }
 
+static const struct platform_device_id skl_board_ids[] = {
+	{ .name = "skl_n88l25_m98357a" },
+	{ .name = "kbl_n88l25_m98357a" },
+	{ }
+};
+
 static struct platform_driver skylake_audio = {
 	.probe = skylake_audio_probe,
 	.driver = {
-		.name = "skl_nau88l25_max98357a_i2s",
+		.name = "skl_n88l25_m98357a",
 		.pm = &snd_soc_pm_ops,
 	},
+	.id_table = skl_board_ids,
 };
 
 module_platform_driver(skylake_audio)
@@ -637,4 +677,5 @@ module_platform_driver(skylake_audio)
 MODULE_DESCRIPTION("Audio Machine driver-NAU88L25 & MAX98357A in I2S mode");
 MODULE_AUTHOR("Rohit Ainapure <rohit.m.ainapure@intel.com");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:skl_nau88l25_max98357a_i2s");
+MODULE_ALIAS("platform:skl_n88l25_m98357a");
+MODULE_ALIAS("platform:kbl_n88l25_m98357a");
diff --git a/sound/soc/intel/boards/skl_nau88l25_ssm4567.c b/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
index e19aa99c4f72..69c5d5da4e86 100644
--- a/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
+++ b/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
@@ -27,12 +27,15 @@
 #include <sound/pcm_params.h>
 #include "../../codecs/nau8825.h"
 #include "../../codecs/hdac_hdmi.h"
+#include "../skylake/skl.h"
 
 #define SKL_NUVOTON_CODEC_DAI	"nau8825-hifi"
 #define SKL_SSM_CODEC_DAI	"ssm4567-hifi"
+#define DMIC_CH(p)     p->list[p->count-1]
 
 static struct snd_soc_jack skylake_headset;
 static struct snd_soc_card skylake_audio_card;
+static const struct snd_pcm_hw_constraint_list *dmic_constraints;
 
 struct skl_hdmi_pcm {
 	struct list_head head;
@@ -367,7 +370,7 @@ static int skylake_dmic_fixup(struct snd_soc_pcm_runtime *rtd,
 {
 	struct snd_interval *channels = hw_param_interval(params,
 						SNDRV_PCM_HW_PARAM_CHANNELS);
-	if (params_channels(params) == 2)
+	if (params_channels(params) == 2 || DMIC_CH(dmic_constraints) == 2)
 		channels->min = channels->max = 2;
 	else
 		channels->min = channels->max = 4;
@@ -405,13 +408,23 @@ static struct snd_pcm_hw_constraint_list constraints_dmic_channels = {
 	.mask = 0,
 };
 
+static const unsigned int dmic_2ch[] = {
+	2,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_dmic_2ch = {
+	.count = ARRAY_SIZE(dmic_2ch),
+	.list = dmic_2ch,
+	.mask = 0,
+};
+
 static int skylake_dmic_startup(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 
-	runtime->hw.channels_max = 4;
+	runtime->hw.channels_max = DMIC_CH(dmic_constraints);
 	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
-			&constraints_dmic_channels);
+			dmic_constraints);
 
 	return snd_pcm_hw_constraint_list(substream->runtime, 0,
 			SNDRV_PCM_HW_PARAM_RATE, &constraints_rates);
@@ -430,8 +443,22 @@ static struct snd_pcm_hw_constraint_list constraints_16000 = {
 	.list  = rates_16000,
 };
 
+static const unsigned int ch_mono[] = {
+	1,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_refcap = {
+	.count = ARRAY_SIZE(ch_mono),
+	.list  = ch_mono,
+};
+
 static int skylake_refcap_startup(struct snd_pcm_substream *substream)
 {
+	substream->runtime->hw.channels_max = 1;
+	snd_pcm_hw_constraint_list(substream->runtime, 0,
+					SNDRV_PCM_HW_PARAM_CHANNELS,
+					&constraints_refcap);
+
 	return snd_pcm_hw_constraint_list(substream->runtime, 0,
 			SNDRV_PCM_HW_PARAM_RATE,
 			&constraints_16000);
@@ -662,6 +689,7 @@ static struct snd_soc_card skylake_audio_card = {
 static int skylake_audio_probe(struct platform_device *pdev)
 {
 	struct skl_nau88125_private *ctx;
+	struct skl_machine_pdata *pdata;
 
 	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
 	if (!ctx)
@@ -672,15 +700,27 @@ static int skylake_audio_probe(struct platform_device *pdev)
 	skylake_audio_card.dev = &pdev->dev;
 	snd_soc_card_set_drvdata(&skylake_audio_card, ctx);
 
+	pdata = dev_get_drvdata(&pdev->dev);
+	if (pdata)
+		dmic_constraints = pdata->dmic_num == 2 ?
+			&constraints_dmic_2ch : &constraints_dmic_channels;
+
 	return devm_snd_soc_register_card(&pdev->dev, &skylake_audio_card);
 }
 
+static const struct platform_device_id skl_board_ids[] = {
+	{ .name = "skl_n88l25_s4567" },
+	{ .name = "kbl_n88l25_s4567" },
+	{ }
+};
+
 static struct platform_driver skylake_audio = {
 	.probe = skylake_audio_probe,
 	.driver = {
-		.name = "skl_nau88l25_ssm4567_i2s",
+		.name = "skl_n88l25_s4567",
 		.pm = &snd_soc_pm_ops,
 	},
+	.id_table = skl_board_ids,
 };
 
 module_platform_driver(skylake_audio)
@@ -693,4 +733,5 @@ MODULE_AUTHOR("Sathya Prakash M R <sathya.prakash.m.r@intel.com>");
 MODULE_AUTHOR("Yong Zhi <yong.zhi@intel.com>");
 MODULE_DESCRIPTION("Intel Audio Machine driver for SKL with NAU88L25 and SSM4567 in I2S Mode");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:skl_nau88l25_ssm4567_i2s");
+MODULE_ALIAS("platform:skl_n88l25_s4567");
+MODULE_ALIAS("platform:kbl_n88l25_s4567");
diff --git a/sound/soc/intel/boards/skl_rt286.c b/sound/soc/intel/boards/skl_rt286.c
index 426b48233fdb..88c61e8cb87f 100644
--- a/sound/soc/intel/boards/skl_rt286.c
+++ b/sound/soc/intel/boards/skl_rt286.c
@@ -505,12 +505,20 @@ static int skylake_audio_probe(struct platform_device *pdev)
 	return devm_snd_soc_register_card(&pdev->dev, &skylake_rt286);
 }
 
+static const struct platform_device_id skl_board_ids[] = {
+	{ .name = "skl_alc286s_i2s" },
+	{ .name = "kbl_alc286s_i2s" },
+	{ }
+};
+
 static struct platform_driver skylake_audio = {
 	.probe = skylake_audio_probe,
 	.driver = {
 		.name = "skl_alc286s_i2s",
 		.pm = &snd_soc_pm_ops,
 	},
+	.id_table = skl_board_ids,
+
 };
 
 module_platform_driver(skylake_audio)
@@ -520,3 +528,4 @@ MODULE_AUTHOR("Omair Mohammed Abdullah <omair.m.abdullah@intel.com>");
 MODULE_DESCRIPTION("Intel SST Audio for Skylake");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:skl_alc286s_i2s");
+MODULE_ALIAS("platform:kbl_alc286s_i2s");
diff --git a/sound/soc/intel/common/Makefile b/sound/soc/intel/common/Makefile
index fbbb25c2ceed..1a35149bcad7 100644
--- a/sound/soc/intel/common/Makefile
+++ b/sound/soc/intel/common/Makefile
@@ -2,9 +2,9 @@ snd-soc-sst-dsp-objs := sst-dsp.o
 snd-soc-sst-acpi-objs := sst-acpi.o
 snd-soc-sst-match-objs := sst-match-acpi.o
 snd-soc-sst-ipc-objs := sst-ipc.o
-
-snd-soc-sst-dsp-$(CONFIG_DW_DMAC_CORE) += sst-firmware.o
+snd-soc-sst-firmware-objs := sst-firmware.o
 
 obj-$(CONFIG_SND_SOC_INTEL_SST) += snd-soc-sst-dsp.o snd-soc-sst-ipc.o
 obj-$(CONFIG_SND_SOC_INTEL_SST_ACPI) += snd-soc-sst-acpi.o
 obj-$(CONFIG_SND_SOC_INTEL_SST_MATCH) += snd-soc-sst-match.o
+obj-$(CONFIG_SND_SOC_INTEL_SST_FIRMWARE) += snd-soc-sst-firmware.o
diff --git a/sound/soc/intel/common/sst-acpi.h b/sound/soc/intel/common/sst-acpi.h
index 8398cb227ba9..5d2949324d0e 100644
--- a/sound/soc/intel/common/sst-acpi.h
+++ b/sound/soc/intel/common/sst-acpi.h
@@ -20,7 +20,7 @@
 #if IS_ENABLED(CONFIG_ACPI)
 const char *sst_acpi_find_name_from_hid(const u8 hid[ACPI_ID_LEN]);
 #else
-inline const char *sst_acpi_find_name_from_hid(const u8 hid[ACPI_ID_LEN])
+static inline const char *sst_acpi_find_name_from_hid(const u8 hid[ACPI_ID_LEN])
 {
 	return NULL;
 }
@@ -40,6 +40,6 @@ struct sst_acpi_mach {
 
 	/* board name */
 	const char *board;
-	void (*machine_quirk)(void);
+	struct sst_acpi_mach * (*machine_quirk)(void *arg);
 	void *pdata;
 };
diff --git a/sound/soc/intel/common/sst-dsp-priv.h b/sound/soc/intel/common/sst-dsp-priv.h
index 97dc1ae05e69..d13c84364c3c 100644
--- a/sound/soc/intel/common/sst-dsp-priv.h
+++ b/sound/soc/intel/common/sst-dsp-priv.h
@@ -383,10 +383,6 @@ struct sst_mem_block *sst_mem_block_register(struct sst_dsp *dsp, u32 offset,
 	u32 index, void *private);
 void sst_mem_block_unregister_all(struct sst_dsp *dsp);
 
-/* Create/Free DMA resources */
-int sst_dma_new(struct sst_dsp *sst);
-void sst_dma_free(struct sst_dma *dma);
-
 u32 sst_dsp_get_offset(struct sst_dsp *dsp, u32 offset,
 	enum sst_mem_type type);
 #endif
diff --git a/sound/soc/intel/common/sst-dsp.c b/sound/soc/intel/common/sst-dsp.c
index b5bbdf4fe93a..c00ede4ea4d7 100644
--- a/sound/soc/intel/common/sst-dsp.c
+++ b/sound/soc/intel/common/sst-dsp.c
@@ -285,7 +285,7 @@ int sst_dsp_register_poll(struct sst_dsp *ctx, u32 offset, u32 mask,
 	}
 
 	reg = sst_dsp_shim_read_unlocked(ctx, offset);
-	dev_info(ctx->dev, "FW Poll Status: reg=%#x %s %s\n", reg, operation,
+	dev_dbg(ctx->dev, "FW Poll Status: reg=%#x %s %s\n", reg, operation,
 			(time < timeout) ? "successful" : "timedout");
 	ret = time < timeout ? 0 : -ETIME;
 
@@ -420,73 +420,6 @@ void sst_dsp_inbox_read(struct sst_dsp *sst, void *message, size_t bytes)
 }
 EXPORT_SYMBOL_GPL(sst_dsp_inbox_read);
 
-#ifdef CONFIG_DW_DMAC_CORE
-struct sst_dsp *sst_dsp_new(struct device *dev,
-	struct sst_dsp_device *sst_dev, struct sst_pdata *pdata)
-{
-	struct sst_dsp *sst;
-	int err;
-
-	dev_dbg(dev, "initialising audio DSP id 0x%x\n", pdata->id);
-
-	sst = devm_kzalloc(dev, sizeof(*sst), GFP_KERNEL);
-	if (sst == NULL)
-		return NULL;
-
-	spin_lock_init(&sst->spinlock);
-	mutex_init(&sst->mutex);
-	sst->dev = dev;
-	sst->dma_dev = pdata->dma_dev;
-	sst->thread_context = sst_dev->thread_context;
-	sst->sst_dev = sst_dev;
-	sst->id = pdata->id;
-	sst->irq = pdata->irq;
-	sst->ops = sst_dev->ops;
-	sst->pdata = pdata;
-	INIT_LIST_HEAD(&sst->used_block_list);
-	INIT_LIST_HEAD(&sst->free_block_list);
-	INIT_LIST_HEAD(&sst->module_list);
-	INIT_LIST_HEAD(&sst->fw_list);
-	INIT_LIST_HEAD(&sst->scratch_block_list);
-
-	/* Initialise SST Audio DSP */
-	if (sst->ops->init) {
-		err = sst->ops->init(sst, pdata);
-		if (err < 0)
-			return NULL;
-	}
-
-	/* Register the ISR */
-	err = request_threaded_irq(sst->irq, sst->ops->irq_handler,
-		sst_dev->thread, IRQF_SHARED, "AudioDSP", sst);
-	if (err)
-		goto irq_err;
-
-	err = sst_dma_new(sst);
-	if (err)
-		dev_warn(dev, "sst_dma_new failed %d\n", err);
-
-	return sst;
-
-irq_err:
-	if (sst->ops->free)
-		sst->ops->free(sst);
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(sst_dsp_new);
-
-void sst_dsp_free(struct sst_dsp *sst)
-{
-	free_irq(sst->irq, sst);
-	if (sst->ops->free)
-		sst->ops->free(sst);
-
-	sst_dma_free(sst->dma);
-}
-EXPORT_SYMBOL_GPL(sst_dsp_free);
-#endif
-
 /* Module information */
 MODULE_AUTHOR("Liam Girdwood");
 MODULE_DESCRIPTION("Intel SST Core");
diff --git a/sound/soc/intel/common/sst-dsp.h b/sound/soc/intel/common/sst-dsp.h
index 0b84c719ec48..859f0de00339 100644
--- a/sound/soc/intel/common/sst-dsp.h
+++ b/sound/soc/intel/common/sst-dsp.h
@@ -216,7 +216,7 @@ struct sst_pdata {
 	void *dsp;
 };
 
-#ifdef CONFIG_DW_DMAC_CORE
+#if IS_ENABLED(CONFIG_DW_DMAC_CORE)
 /* Initialization */
 struct sst_dsp *sst_dsp_new(struct device *dev,
 	struct sst_dsp_device *sst_dev, struct sst_pdata *pdata);
diff --git a/sound/soc/intel/common/sst-firmware.c b/sound/soc/intel/common/sst-firmware.c
index 25993527370b..a086c35f91bb 100644
--- a/sound/soc/intel/common/sst-firmware.c
+++ b/sound/soc/intel/common/sst-firmware.c
@@ -1211,3 +1211,71 @@ u32 sst_dsp_get_offset(struct sst_dsp *dsp, u32 offset,
 	}
 }
 EXPORT_SYMBOL_GPL(sst_dsp_get_offset);
+
+struct sst_dsp *sst_dsp_new(struct device *dev,
+	struct sst_dsp_device *sst_dev, struct sst_pdata *pdata)
+{
+	struct sst_dsp *sst;
+	int err;
+
+	dev_dbg(dev, "initialising audio DSP id 0x%x\n", pdata->id);
+
+	sst = devm_kzalloc(dev, sizeof(*sst), GFP_KERNEL);
+	if (sst == NULL)
+		return NULL;
+
+	spin_lock_init(&sst->spinlock);
+	mutex_init(&sst->mutex);
+	sst->dev = dev;
+	sst->dma_dev = pdata->dma_dev;
+	sst->thread_context = sst_dev->thread_context;
+	sst->sst_dev = sst_dev;
+	sst->id = pdata->id;
+	sst->irq = pdata->irq;
+	sst->ops = sst_dev->ops;
+	sst->pdata = pdata;
+	INIT_LIST_HEAD(&sst->used_block_list);
+	INIT_LIST_HEAD(&sst->free_block_list);
+	INIT_LIST_HEAD(&sst->module_list);
+	INIT_LIST_HEAD(&sst->fw_list);
+	INIT_LIST_HEAD(&sst->scratch_block_list);
+
+	/* Initialise SST Audio DSP */
+	if (sst->ops->init) {
+		err = sst->ops->init(sst, pdata);
+		if (err < 0)
+			return NULL;
+	}
+
+	/* Register the ISR */
+	err = request_threaded_irq(sst->irq, sst->ops->irq_handler,
+		sst_dev->thread, IRQF_SHARED, "AudioDSP", sst);
+	if (err)
+		goto irq_err;
+
+	err = sst_dma_new(sst);
+	if (err)
+		dev_warn(dev, "sst_dma_new failed %d\n", err);
+
+	return sst;
+
+irq_err:
+	if (sst->ops->free)
+		sst->ops->free(sst);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(sst_dsp_new);
+
+void sst_dsp_free(struct sst_dsp *sst)
+{
+	free_irq(sst->irq, sst);
+	if (sst->ops->free)
+		sst->ops->free(sst);
+
+	sst_dma_free(sst->dma);
+}
+EXPORT_SYMBOL_GPL(sst_dsp_free);
+
+MODULE_DESCRIPTION("Intel SST Firmware Loader");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/intel/haswell/sst-haswell-pcm.c b/sound/soc/intel/haswell/sst-haswell-pcm.c
index 994256b39b9c..3154525c2b83 100644
--- a/sound/soc/intel/haswell/sst-haswell-pcm.c
+++ b/sound/soc/intel/haswell/sst-haswell-pcm.c
@@ -819,7 +819,6 @@ static int hsw_pcm_open(struct snd_pcm_substream *substream)
 	mutex_lock(&pcm_data->mutex);
 	pm_runtime_get_sync(pdata->dev);
 
-	snd_soc_pcm_set_drvdata(rtd, pcm_data);
 	pcm_data->substream = substream;
 
 	snd_soc_set_runtime_hwparams(substream, &hsw_pcm_hardware);
diff --git a/sound/soc/intel/skylake/Makefile b/sound/soc/intel/skylake/Makefile
index c28f5d0e1d99..60fbc9bbe473 100644
--- a/sound/soc/intel/skylake/Makefile
+++ b/sound/soc/intel/skylake/Makefile
@@ -5,6 +5,6 @@ obj-$(CONFIG_SND_SOC_INTEL_SKYLAKE) += snd-soc-skl.o
 
 # Skylake IPC Support
 snd-soc-skl-ipc-objs := skl-sst-ipc.o skl-sst-dsp.o skl-sst-cldma.o \
-		skl-sst.o bxt-sst.o
+		skl-sst.o bxt-sst.o skl-sst-utils.o
 
 obj-$(CONFIG_SND_SOC_INTEL_SKYLAKE) += snd-soc-skl-ipc.o
diff --git a/sound/soc/intel/skylake/bxt-sst.c b/sound/soc/intel/skylake/bxt-sst.c
index 8b95e09e23e8..2663781278aa 100644
--- a/sound/soc/intel/skylake/bxt-sst.c
+++ b/sound/soc/intel/skylake/bxt-sst.c
@@ -37,11 +37,19 @@
 
 #define BXT_ADSP_SRAM1_BASE	0xA0000
 
+#define BXT_INSTANCE_ID 0
+#define BXT_BASE_FW_MODULE_ID 0
+
 static unsigned int bxt_get_errorcode(struct sst_dsp *ctx)
 {
 	 return sst_dsp_shim_read(ctx, BXT_ADSP_ERROR_CODE);
 }
 
+/*
+ * First boot sequence has some extra steps. Core 0 waits for power
+ * status on core 1, so power up core 1 also momentarily, keep it in
+ * reset/stall and then turn it off
+ */
 static int sst_bxt_prepare_fw(struct sst_dsp *ctx,
 			const void *fwdata, u32 fwsize)
 {
@@ -49,7 +57,7 @@ static int sst_bxt_prepare_fw(struct sst_dsp *ctx,
 	u32 reg;
 
 	stream_tag = ctx->dsp_ops.prepare(ctx->dev, 0x40, fwsize, &ctx->dmab);
-	if (stream_tag < 0) {
+	if (stream_tag <= 0) {
 		dev_err(ctx->dev, "Failed to prepare DMA FW loading err: %x\n",
 				stream_tag);
 		return stream_tag;
@@ -58,17 +66,27 @@ static int sst_bxt_prepare_fw(struct sst_dsp *ctx,
 	ctx->dsp_ops.stream_tag = stream_tag;
 	memcpy(ctx->dmab.area, fwdata, fwsize);
 
-	/* Purge FW request */
+	/* Step 1: Power up core 0 and core1 */
+	ret = skl_dsp_core_power_up(ctx, SKL_DSP_CORE0_MASK |
+				SKL_DSP_CORE_MASK(1));
+	if (ret < 0) {
+		dev_err(ctx->dev, "dsp core0/1 power up failed\n");
+		goto base_fw_load_failed;
+	}
+
+	/* Step 2: Purge FW request */
 	sst_dsp_shim_write(ctx, SKL_ADSP_REG_HIPCI, SKL_ADSP_REG_HIPCI_BUSY |
-					 BXT_IPC_PURGE_FW | (stream_tag - 1));
+				(BXT_IPC_PURGE_FW | ((stream_tag - 1) << 9)));
 
-	ret = skl_dsp_enable_core(ctx);
+	/* Step 3: Unset core0 reset state & unstall/run core0 */
+	ret = skl_dsp_start_core(ctx, SKL_DSP_CORE0_MASK);
 	if (ret < 0) {
-		dev_err(ctx->dev, "Boot dsp core failed ret: %d\n", ret);
+		dev_err(ctx->dev, "Start dsp core failed ret: %d\n", ret);
 		ret = -EIO;
 		goto base_fw_load_failed;
 	}
 
+	/* Step 4: Wait for DONE Bit */
 	for (i = BXT_INIT_TIMEOUT; i > 0; --i) {
 		reg = sst_dsp_shim_read(ctx, SKL_ADSP_REG_HIPCIE);
 
@@ -88,10 +106,18 @@ static int sst_bxt_prepare_fw(struct sst_dsp *ctx,
 				SKL_ADSP_REG_HIPCIE_DONE);
 	}
 
-	/* enable Interrupt */
+	/* Step 5: power down core1 */
+	ret = skl_dsp_core_power_down(ctx, SKL_DSP_CORE_MASK(1));
+	if (ret < 0) {
+		dev_err(ctx->dev, "dsp core1 power down failed\n");
+		goto base_fw_load_failed;
+	}
+
+	/* Step 6: Enable Interrupt */
 	skl_ipc_int_enable(ctx);
 	skl_ipc_op_int_enable(ctx);
 
+	/* Step 7: Wait for ROM init */
 	for (i = BXT_INIT_TIMEOUT; i > 0; --i) {
 		if (SKL_FW_INIT ==
 				(sst_dsp_shim_read(ctx, BXT_ADSP_FW_STATUS) &
@@ -112,7 +138,8 @@ static int sst_bxt_prepare_fw(struct sst_dsp *ctx,
 
 base_fw_load_failed:
 	ctx->dsp_ops.cleanup(ctx->dev, &ctx->dmab, stream_tag);
-	skl_dsp_disable_core(ctx);
+	skl_dsp_core_power_down(ctx, SKL_DSP_CORE_MASK(1));
+	skl_dsp_disable_core(ctx, SKL_DSP_CORE0_MASK);
 	return ret;
 }
 
@@ -130,23 +157,41 @@ static int sst_transfer_fw_host_dma(struct sst_dsp *ctx)
 	return ret;
 }
 
+#define BXT_ADSP_FW_BIN_HDR_OFFSET 0x2000
+
 static int bxt_load_base_firmware(struct sst_dsp *ctx)
 {
-	const struct firmware *fw = NULL;
+	struct firmware stripped_fw;
 	struct skl_sst *skl = ctx->thread_context;
 	int ret;
 
-	ret = request_firmware(&fw, ctx->fw_name, ctx->dev);
+	ret = request_firmware(&ctx->fw, ctx->fw_name, ctx->dev);
 	if (ret < 0) {
 		dev_err(ctx->dev, "Request firmware failed %d\n", ret);
 		goto sst_load_base_firmware_failed;
 	}
 
-	ret = sst_bxt_prepare_fw(ctx, fw->data, fw->size);
+	/* check for extended manifest */
+	if (ctx->fw == NULL)
+		goto sst_load_base_firmware_failed;
+
+	ret = snd_skl_parse_uuids(ctx, BXT_ADSP_FW_BIN_HDR_OFFSET);
+	if (ret < 0)
+		goto sst_load_base_firmware_failed;
+
+	stripped_fw.data = ctx->fw->data;
+	stripped_fw.size = ctx->fw->size;
+	skl_dsp_strip_extended_manifest(&stripped_fw);
+
+	ret = sst_bxt_prepare_fw(ctx, stripped_fw.data, stripped_fw.size);
 	/* Retry Enabling core and ROM load. Retry seemed to help */
 	if (ret < 0) {
-		ret = sst_bxt_prepare_fw(ctx, fw->data, fw->size);
+		ret = sst_bxt_prepare_fw(ctx, stripped_fw.data, stripped_fw.size);
 		if (ret < 0) {
+			dev_err(ctx->dev, "Error code=0x%x: FW status=0x%x\n",
+			sst_dsp_shim_read(ctx, BXT_ADSP_ERROR_CODE),
+			sst_dsp_shim_read(ctx, BXT_ADSP_FW_STATUS));
+
 			dev_err(ctx->dev, "Core En/ROM load fail:%d\n", ret);
 			goto sst_load_base_firmware_failed;
 		}
@@ -159,83 +204,135 @@ static int bxt_load_base_firmware(struct sst_dsp *ctx)
 			sst_dsp_shim_read(ctx, BXT_ADSP_ERROR_CODE),
 			sst_dsp_shim_read(ctx, BXT_ADSP_FW_STATUS));
 
-		skl_dsp_disable_core(ctx);
+		skl_dsp_disable_core(ctx, SKL_DSP_CORE0_MASK);
 	} else {
 		dev_dbg(ctx->dev, "Firmware download successful\n");
 		ret = wait_event_timeout(skl->boot_wait, skl->boot_complete,
 					msecs_to_jiffies(SKL_IPC_BOOT_MSECS));
 		if (ret == 0) {
 			dev_err(ctx->dev, "DSP boot fail, FW Ready timeout\n");
-			skl_dsp_disable_core(ctx);
+			skl_dsp_disable_core(ctx, SKL_DSP_CORE0_MASK);
 			ret = -EIO;
 		} else {
-			skl_dsp_set_state_locked(ctx, SKL_DSP_RUNNING);
 			ret = 0;
+			skl->fw_loaded = true;
 		}
 	}
 
 sst_load_base_firmware_failed:
-	release_firmware(fw);
+	release_firmware(ctx->fw);
 	return ret;
 }
 
-static int bxt_set_dsp_D0(struct sst_dsp *ctx)
+static int bxt_set_dsp_D0(struct sst_dsp *ctx, unsigned int core_id)
 {
 	struct skl_sst *skl = ctx->thread_context;
 	int ret;
+	struct skl_ipc_dxstate_info dx;
+	unsigned int core_mask = SKL_DSP_CORE_MASK(core_id);
 
-	skl->boot_complete = false;
-
-	ret = skl_dsp_enable_core(ctx);
-	if (ret < 0) {
-		dev_err(ctx->dev, "enable dsp core failed ret: %d\n", ret);
+	if (skl->fw_loaded == false) {
+		skl->boot_complete = false;
+		ret = bxt_load_base_firmware(ctx);
+		if (ret < 0)
+			dev_err(ctx->dev, "reload fw failed: %d\n", ret);
 		return ret;
 	}
 
-	/* enable interrupt */
-	skl_ipc_int_enable(ctx);
-	skl_ipc_op_int_enable(ctx);
+	/* If core 0 is being turned on, turn on core 1 as well */
+	if (core_id == SKL_DSP_CORE0_ID)
+		ret = skl_dsp_core_power_up(ctx, core_mask |
+				SKL_DSP_CORE_MASK(1));
+	else
+		ret = skl_dsp_core_power_up(ctx, core_mask);
+
+	if (ret < 0)
+		goto err;
+
+	if (core_id == SKL_DSP_CORE0_ID) {
+
+		/*
+		 * Enable interrupt after SPA is set and before
+		 * DSP is unstalled
+		 */
+		skl_ipc_int_enable(ctx);
+		skl_ipc_op_int_enable(ctx);
+		skl->boot_complete = false;
+	}
 
-	ret = wait_event_timeout(skl->boot_wait, skl->boot_complete,
-					msecs_to_jiffies(SKL_IPC_BOOT_MSECS));
-	if (ret == 0) {
-		dev_err(ctx->dev, "ipc: error DSP boot timeout\n");
-		dev_err(ctx->dev, "Error code=0x%x: FW status=0x%x\n",
-			sst_dsp_shim_read(ctx, BXT_ADSP_ERROR_CODE),
-			sst_dsp_shim_read(ctx, BXT_ADSP_FW_STATUS));
-		return -EIO;
+	ret = skl_dsp_start_core(ctx, core_mask);
+	if (ret < 0)
+		goto err;
+
+	if (core_id == SKL_DSP_CORE0_ID) {
+		ret = wait_event_timeout(skl->boot_wait,
+				skl->boot_complete,
+				msecs_to_jiffies(SKL_IPC_BOOT_MSECS));
+
+	/* If core 1 was turned on for booting core 0, turn it off */
+		skl_dsp_core_power_down(ctx, SKL_DSP_CORE_MASK(1));
+		if (ret == 0) {
+			dev_err(ctx->dev, "%s: DSP boot timeout\n", __func__);
+			dev_err(ctx->dev, "Error code=0x%x: FW status=0x%x\n",
+				sst_dsp_shim_read(ctx, BXT_ADSP_ERROR_CODE),
+				sst_dsp_shim_read(ctx, BXT_ADSP_FW_STATUS));
+			dev_err(ctx->dev, "Failed to set core0 to D0 state\n");
+			ret = -EIO;
+			goto err;
+		}
+	}
+
+	/* Tell FW if additional core in now On */
+
+	if (core_id != SKL_DSP_CORE0_ID) {
+		dx.core_mask = core_mask;
+		dx.dx_mask = core_mask;
+
+		ret = skl_ipc_set_dx(&skl->ipc, BXT_INSTANCE_ID,
+					BXT_BASE_FW_MODULE_ID, &dx);
+		if (ret < 0) {
+			dev_err(ctx->dev, "IPC set_dx for core %d fail: %d\n",
+								core_id, ret);
+			goto err;
+		}
 	}
 
-	skl_dsp_set_state_locked(ctx, SKL_DSP_RUNNING);
+	skl->cores.state[core_id] = SKL_DSP_RUNNING;
 	return 0;
+err:
+	if (core_id == SKL_DSP_CORE0_ID)
+		core_mask |= SKL_DSP_CORE_MASK(1);
+	skl_dsp_disable_core(ctx, core_mask);
+
+	return ret;
 }
 
-static int bxt_set_dsp_D3(struct sst_dsp *ctx)
+static int bxt_set_dsp_D3(struct sst_dsp *ctx, unsigned int core_id)
 {
+	int ret;
 	struct skl_ipc_dxstate_info dx;
 	struct skl_sst *skl = ctx->thread_context;
-	int ret = 0;
+	unsigned int core_mask = SKL_DSP_CORE_MASK(core_id);
 
-	if (!is_skl_dsp_running(ctx))
-		return ret;
-
-	dx.core_mask = SKL_DSP_CORE0_MASK;
+	dx.core_mask = core_mask;
 	dx.dx_mask = SKL_IPC_D3_MASK;
 
-	ret = skl_ipc_set_dx(&skl->ipc, SKL_INSTANCE_ID,
-				SKL_BASE_FW_MODULE_ID, &dx);
-	if (ret < 0) {
-		dev_err(ctx->dev, "Failed to set DSP to D3 state: %d\n", ret);
-		return ret;
-	}
+	dev_dbg(ctx->dev, "core mask=%x dx_mask=%x\n",
+			dx.core_mask, dx.dx_mask);
+
+	ret = skl_ipc_set_dx(&skl->ipc, BXT_INSTANCE_ID,
+				BXT_BASE_FW_MODULE_ID, &dx);
+	if (ret < 0)
+		dev_err(ctx->dev,
+		"Failed to set DSP to D3:core id = %d;Continue reset\n",
+		core_id);
 
-	ret = skl_dsp_disable_core(ctx);
+	ret = skl_dsp_disable_core(ctx, core_mask);
 	if (ret < 0) {
-		dev_err(ctx->dev, "disbale dsp core failed: %d\n", ret);
-		ret = -EIO;
+		dev_err(ctx->dev, "Failed to disable core %d", ret);
+		return ret;
 	}
-
-	skl_dsp_set_state_locked(ctx, SKL_DSP_RESET);
+	skl->cores.state[core_id] = SKL_DSP_RESET;
 	return 0;
 }
 
@@ -274,6 +371,7 @@ int bxt_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 
 	skl->dev = dev;
 	skl_dev.thread_context = skl;
+	INIT_LIST_HEAD(&skl->uuid_list);
 
 	skl->dsp = skl_dsp_ctx_init(dev, &skl_dev, irq);
 	if (!skl->dsp) {
@@ -296,6 +394,7 @@ int bxt_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 	if (ret)
 		return ret;
 
+	skl->cores.count = 2;
 	skl->boot_complete = false;
 	init_waitqueue_head(&skl->boot_wait);
 
@@ -305,6 +404,8 @@ int bxt_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 		return ret;
 	}
 
+	skl_dsp_init_core_state(sst);
+
 	if (dsp)
 		*dsp = skl;
 
@@ -315,6 +416,7 @@ EXPORT_SYMBOL_GPL(bxt_sst_dsp_init);
 
 void bxt_sst_dsp_cleanup(struct device *dev, struct skl_sst *ctx)
 {
+	skl_freeup_uuid_list(ctx);
 	skl_ipc_free(&ctx->ipc);
 	ctx->dsp->cl_dev.ops.cl_cleanup_controller(ctx->dsp);
 
diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c
index 226db84ba20f..44ab595ce21a 100644
--- a/sound/soc/intel/skylake/skl-messages.c
+++ b/sound/soc/intel/skylake/skl-messages.c
@@ -206,6 +206,12 @@ static const struct skl_dsp_ops dsp_ops[] = {
 		.cleanup = skl_sst_dsp_cleanup
 	},
 	{
+		.id = 0x9d71,
+		.loader_ops = skl_get_loader_ops,
+		.init = skl_sst_dsp_init,
+		.cleanup = skl_sst_dsp_cleanup
+	},
+	{
 		.id = 0x5a98,
 		.loader_ops = bxt_get_loader_ops,
 		.init = bxt_sst_dsp_init,
@@ -730,7 +736,7 @@ static int skl_set_module_format(struct skl_sst *ctx,
 
 	dev_dbg(ctx->dev, "Module type=%d config size: %d bytes\n",
 			module_config->id.module_id, param_size);
-	print_hex_dump(KERN_DEBUG, "Module params:", DUMP_PREFIX_OFFSET, 8, 4,
+	print_hex_dump_debug("Module params:", DUMP_PREFIX_OFFSET, 8, 4,
 			*param_data, param_size, false);
 	return 0;
 }
@@ -1046,7 +1052,7 @@ int skl_delete_pipe(struct skl_sst *ctx, struct skl_pipe *pipe)
 
 	dev_dbg(ctx->dev, "%s: pipe = %d\n", __func__, pipe->ppl_id);
 
-	/* If pipe is not started, do not try to stop the pipe in FW. */
+	/* If pipe is started, do stop the pipe in FW. */
 	if (pipe->state > SKL_PIPE_STARTED) {
 		ret = skl_set_pipe_state(ctx, pipe, PPL_PAUSED);
 		if (ret < 0) {
@@ -1055,18 +1061,20 @@ int skl_delete_pipe(struct skl_sst *ctx, struct skl_pipe *pipe)
 		}
 
 		pipe->state = SKL_PIPE_PAUSED;
-	} else {
-		/* If pipe was not created in FW, do not try to delete it */
-		if (pipe->state < SKL_PIPE_CREATED)
-			return 0;
+	}
 
-		ret = skl_ipc_delete_pipeline(&ctx->ipc, pipe->ppl_id);
-		if (ret < 0)
-			dev_err(ctx->dev, "Failed to delete pipeline\n");
+	/* If pipe was not created in FW, do not try to delete it */
+	if (pipe->state < SKL_PIPE_CREATED)
+		return 0;
 
-		pipe->state = SKL_PIPE_INVALID;
+	ret = skl_ipc_delete_pipeline(&ctx->ipc, pipe->ppl_id);
+	if (ret < 0) {
+		dev_err(ctx->dev, "Failed to delete pipeline\n");
+		return ret;
 	}
 
+	pipe->state = SKL_PIPE_INVALID;
+
 	return ret;
 }
 
@@ -1125,7 +1133,30 @@ int skl_stop_pipe(struct skl_sst *ctx, struct skl_pipe *pipe)
 		return ret;
 	}
 
-	pipe->state = SKL_PIPE_CREATED;
+	pipe->state = SKL_PIPE_PAUSED;
+
+	return 0;
+}
+
+/*
+ * Reset the pipeline by sending set pipe state IPC this will reset the DMA
+ * from the DSP side
+ */
+int skl_reset_pipe(struct skl_sst *ctx, struct skl_pipe *pipe)
+{
+	int ret;
+
+	/* If pipe was not created in FW, do not try to pause or delete */
+	if (pipe->state < SKL_PIPE_PAUSED)
+		return 0;
+
+	ret = skl_set_pipe_state(ctx, pipe, PPL_RESET);
+	if (ret < 0) {
+		dev_dbg(ctx->dev, "Failed to reset pipe ret=%d\n", ret);
+		return ret;
+	}
+
+	pipe->state = SKL_PIPE_RESET;
 
 	return 0;
 }
diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c
index 7d73648e5f9a..3f8e6f0b7eb5 100644
--- a/sound/soc/intel/skylake/skl-nhlt.c
+++ b/sound/soc/intel/skylake/skl-nhlt.c
@@ -17,6 +17,7 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
  */
+#include <linux/pci.h>
 #include "skl.h"
 
 /* Unique identification for getting NHLT blobs */
@@ -149,6 +150,45 @@ struct nhlt_specific_cfg
 	return NULL;
 }
 
+int skl_get_dmic_geo(struct skl *skl)
+{
+	struct nhlt_acpi_table *nhlt = (struct nhlt_acpi_table *)skl->nhlt;
+	struct nhlt_endpoint *epnt;
+	struct nhlt_dmic_array_config *cfg;
+	struct device *dev = &skl->pci->dev;
+	unsigned int dmic_geo = 0;
+	u8 j;
+
+	epnt = (struct nhlt_endpoint *)nhlt->desc;
+
+	for (j = 0; j < nhlt->endpoint_count; j++) {
+		if (epnt->linktype == NHLT_LINK_DMIC) {
+			cfg = (struct nhlt_dmic_array_config  *)
+					(epnt->config.caps);
+			switch (cfg->array_type) {
+			case NHLT_MIC_ARRAY_2CH_SMALL:
+			case NHLT_MIC_ARRAY_2CH_BIG:
+				dmic_geo |= MIC_ARRAY_2CH;
+				break;
+
+			case NHLT_MIC_ARRAY_4CH_1ST_GEOM:
+			case NHLT_MIC_ARRAY_4CH_L_SHAPED:
+			case NHLT_MIC_ARRAY_4CH_2ND_GEOM:
+				dmic_geo |= MIC_ARRAY_4CH;
+				break;
+
+			default:
+				dev_warn(dev, "undefined DMIC array_type 0x%0x\n",
+						cfg->array_type);
+
+			}
+		}
+		epnt = (struct nhlt_endpoint *)((u8 *)epnt + epnt->length);
+	}
+
+	return dmic_geo;
+}
+
 static void skl_nhlt_trim_space(struct skl *skl)
 {
 	char *s = skl->tplg_name;
diff --git a/sound/soc/intel/skylake/skl-nhlt.h b/sound/soc/intel/skylake/skl-nhlt.h
index 3769f9fefe2b..116534e7b3c5 100644
--- a/sound/soc/intel/skylake/skl-nhlt.h
+++ b/sound/soc/intel/skylake/skl-nhlt.h
@@ -103,4 +103,26 @@ struct nhlt_resource_desc  {
 	u64 length;
 } __packed;
 
+#define MIC_ARRAY_2CH 2
+#define MIC_ARRAY_4CH 4
+
+struct nhlt_tdm_config {
+	u8 virtual_slot;
+	u8 config_type;
+} __packed;
+
+struct nhlt_dmic_array_config {
+	struct nhlt_tdm_config tdm_config;
+	u8 array_type;
+} __packed;
+
+enum {
+	NHLT_MIC_ARRAY_2CH_SMALL = 0xa,
+	NHLT_MIC_ARRAY_2CH_BIG = 0xb,
+	NHLT_MIC_ARRAY_4CH_1ST_GEOM = 0xc,
+	NHLT_MIC_ARRAY_4CH_L_SHAPED = 0xd,
+	NHLT_MIC_ARRAY_4CH_2ND_GEOM = 0xe,
+	NHLT_MIC_ARRAY_VENDOR_DEFINED = 0xf,
+};
+
 #endif
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index 7c81b31748ff..6e05bf8622f7 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -227,16 +227,25 @@ static int skl_pcm_prepare(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
+	struct skl *skl = get_skl_ctx(dai->dev);
 	unsigned int format_val;
 	int err;
+	struct skl_module_cfg *mconfig;
 
 	dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
 
+	mconfig = skl_tplg_fe_get_cpr_module(dai, substream->stream);
+
 	format_val = skl_get_format(substream, dai);
 	dev_dbg(dai->dev, "stream_tag=%d formatvalue=%d\n",
 				hdac_stream(stream)->stream_tag, format_val);
 	snd_hdac_stream_reset(hdac_stream(stream));
 
+	/* In case of XRUN recovery, reset the FW pipe to clean state */
+	if (mconfig && (substream->runtime->status->state ==
+					SNDRV_PCM_STATE_XRUN))
+		skl_reset_pipe(skl->skl_sst, mconfig->pipe);
+
 	err = snd_hdac_stream_set_params(hdac_stream(stream), format_val);
 	if (err < 0)
 		return err;
@@ -521,6 +530,8 @@ static int skl_link_pcm_prepare(struct snd_pcm_substream *substream,
 	struct skl_dma_params *dma_params;
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
 	struct hdac_ext_link *link;
+	struct skl *skl = get_skl_ctx(dai->dev);
+	struct skl_module_cfg *mconfig = NULL;
 
 	dma_params  = (struct skl_dma_params *)
 			snd_soc_dai_get_dma_data(codec_dai, substream);
@@ -535,6 +546,12 @@ static int skl_link_pcm_prepare(struct snd_pcm_substream *substream,
 
 	snd_hdac_ext_link_stream_reset(link_dev);
 
+	/* In case of XRUN recovery, reset the FW pipe to clean state */
+	mconfig = skl_tplg_be_get_cpr_module(dai, substream->stream);
+	if (mconfig && (substream->runtime->status->state ==
+					SNDRV_PCM_STATE_XRUN))
+		skl_reset_pipe(skl->skl_sst, mconfig->pipe);
+
 	snd_hdac_ext_link_stream_setup(link_dev, format_val);
 
 	snd_hdac_ext_link_set_stream_id(link, hdac_stream(link_dev)->stream_tag);
@@ -1009,51 +1026,11 @@ static int skl_platform_pcm_trigger(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-/* calculate runtime delay from LPIB */
-static int skl_get_delay_from_lpib(struct hdac_ext_bus *ebus,
-				struct hdac_ext_stream *sstream,
-				unsigned int pos)
-{
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
-	struct hdac_stream *hstream = hdac_stream(sstream);
-	struct snd_pcm_substream *substream = hstream->substream;
-	int stream = substream->stream;
-	unsigned int lpib_pos = snd_hdac_stream_get_pos_lpib(hstream);
-	int delay;
-
-	if (stream == SNDRV_PCM_STREAM_PLAYBACK)
-		delay = pos - lpib_pos;
-	else
-		delay = lpib_pos - pos;
-
-	if (delay < 0) {
-		if (delay >= hstream->delay_negative_threshold)
-			delay = 0;
-		else
-			delay += hstream->bufsize;
-	}
-
-	if (hstream->bufsize == delay)
-		delay = 0;
-
-	if (delay >= hstream->period_bytes) {
-		dev_info(bus->dev,
-			 "Unstable LPIB (%d >= %d); disabling LPIB delay counting\n",
-			 delay, hstream->period_bytes);
-		delay = 0;
-	}
-
-	return bytes_to_frames(substream->runtime, delay);
-}
-
-static unsigned int skl_get_position(struct hdac_ext_stream *hstream,
-					int codec_delay)
+static snd_pcm_uframes_t skl_platform_pcm_pointer
+			(struct snd_pcm_substream *substream)
 {
-	struct hdac_stream *hstr = hdac_stream(hstream);
-	struct snd_pcm_substream *substream = hstr->substream;
-	struct hdac_ext_bus *ebus;
+	struct hdac_ext_stream *hstream = get_hdac_ext_stream(substream);
 	unsigned int pos;
-	int delay;
 
 	/* use the position buffer as default */
 	pos = snd_hdac_stream_get_pos_posbuf(hdac_stream(hstream));
@@ -1061,23 +1038,7 @@ static unsigned int skl_get_position(struct hdac_ext_stream *hstream,
 	if (pos >= hdac_stream(hstream)->bufsize)
 		pos = 0;
 
-	if (substream->runtime) {
-		ebus = get_bus_ctx(substream);
-		delay = skl_get_delay_from_lpib(ebus, hstream, pos)
-						 + codec_delay;
-		substream->runtime->delay += delay;
-	}
-
-	return pos;
-}
-
-static snd_pcm_uframes_t skl_platform_pcm_pointer
-			(struct snd_pcm_substream *substream)
-{
-	struct hdac_ext_stream *hstream = get_hdac_ext_stream(substream);
-
-	return bytes_to_frames(substream->runtime,
-			       skl_get_position(hstream, 0));
+	return bytes_to_frames(substream->runtime, pos);
 }
 
 static u64 skl_adjust_codec_delay(struct snd_pcm_substream *substream,
@@ -1180,9 +1141,17 @@ static int skl_pcm_new(struct snd_soc_pcm_runtime *rtd)
 static int skl_platform_soc_probe(struct snd_soc_platform *platform)
 {
 	struct hdac_ext_bus *ebus = dev_get_drvdata(platform->dev);
+	struct skl *skl = ebus_to_skl(ebus);
+	int ret;
 
-	if (ebus->ppcap)
-		return skl_tplg_init(platform, ebus);
+	if (ebus->ppcap) {
+		ret = skl_tplg_init(platform, ebus);
+		if (ret < 0) {
+			dev_err(platform->dev, "Failed to init topology!\n");
+			return ret;
+		}
+		skl->platform = platform;
+	}
 
 	return 0;
 }
diff --git a/sound/soc/intel/skylake/skl-sst-dsp.c b/sound/soc/intel/skylake/skl-sst-dsp.c
index 13c19855ee1a..c3deefab65d6 100644
--- a/sound/soc/intel/skylake/skl-sst-dsp.c
+++ b/sound/soc/intel/skylake/skl-sst-dsp.c
@@ -34,33 +34,84 @@ void skl_dsp_set_state_locked(struct sst_dsp *ctx, int state)
 	mutex_unlock(&ctx->mutex);
 }
 
-static int skl_dsp_core_set_reset_state(struct sst_dsp *ctx)
+/*
+ * Initialize core power state and usage count. To be called after
+ * successful first boot. Hence core 0 will be running and other cores
+ * will be reset
+ */
+void skl_dsp_init_core_state(struct sst_dsp *ctx)
+{
+	struct skl_sst *skl = ctx->thread_context;
+	int i;
+
+	skl->cores.state[SKL_DSP_CORE0_ID] = SKL_DSP_RUNNING;
+	skl->cores.usage_count[SKL_DSP_CORE0_ID] = 1;
+
+	for (i = SKL_DSP_CORE0_ID + 1; i < SKL_DSP_CORES_MAX; i++) {
+		skl->cores.state[i] = SKL_DSP_RESET;
+		skl->cores.usage_count[i] = 0;
+	}
+}
+
+/* Get the mask for all enabled cores */
+unsigned int skl_dsp_get_enabled_cores(struct sst_dsp *ctx)
+{
+	struct skl_sst *skl = ctx->thread_context;
+	unsigned int core_mask, en_cores_mask;
+	u32 val;
+
+	core_mask = SKL_DSP_CORES_MASK(skl->cores.count);
+
+	val = sst_dsp_shim_read_unlocked(ctx, SKL_ADSP_REG_ADSPCS);
+
+	/* Cores having CPA bit set */
+	en_cores_mask = (val & SKL_ADSPCS_CPA_MASK(core_mask)) >>
+			SKL_ADSPCS_CPA_SHIFT;
+
+	/* And cores having CRST bit cleared */
+	en_cores_mask &= (~val & SKL_ADSPCS_CRST_MASK(core_mask)) >>
+			SKL_ADSPCS_CRST_SHIFT;
+
+	/* And cores having CSTALL bit cleared */
+	en_cores_mask &= (~val & SKL_ADSPCS_CSTALL_MASK(core_mask)) >>
+			SKL_ADSPCS_CSTALL_SHIFT;
+	en_cores_mask &= core_mask;
+
+	dev_dbg(ctx->dev, "DSP enabled cores mask = %x\n", en_cores_mask);
+
+	return en_cores_mask;
+}
+
+static int
+skl_dsp_core_set_reset_state(struct sst_dsp *ctx, unsigned int core_mask)
 {
 	int ret;
 
 	/* update bits */
 	sst_dsp_shim_update_bits_unlocked(ctx,
-			SKL_ADSP_REG_ADSPCS, SKL_ADSPCS_CRST_MASK,
-			SKL_ADSPCS_CRST(SKL_DSP_CORES_MASK));
+			SKL_ADSP_REG_ADSPCS, SKL_ADSPCS_CRST_MASK(core_mask),
+			SKL_ADSPCS_CRST_MASK(core_mask));
 
 	/* poll with timeout to check if operation successful */
 	ret = sst_dsp_register_poll(ctx,
 			SKL_ADSP_REG_ADSPCS,
-			SKL_ADSPCS_CRST_MASK,
-			SKL_ADSPCS_CRST(SKL_DSP_CORES_MASK),
+			SKL_ADSPCS_CRST_MASK(core_mask),
+			SKL_ADSPCS_CRST_MASK(core_mask),
 			SKL_DSP_RESET_TO,
 			"Set reset");
 	if ((sst_dsp_shim_read_unlocked(ctx, SKL_ADSP_REG_ADSPCS) &
-				SKL_ADSPCS_CRST(SKL_DSP_CORES_MASK)) !=
-				SKL_ADSPCS_CRST(SKL_DSP_CORES_MASK)) {
-		dev_err(ctx->dev, "Set reset state failed\n");
+				SKL_ADSPCS_CRST_MASK(core_mask)) !=
+				SKL_ADSPCS_CRST_MASK(core_mask)) {
+		dev_err(ctx->dev, "Set reset state failed: core_mask %x\n",
+							core_mask);
 		ret = -EIO;
 	}
 
 	return ret;
 }
 
-static int skl_dsp_core_unset_reset_state(struct sst_dsp *ctx)
+int skl_dsp_core_unset_reset_state(
+		struct sst_dsp *ctx, unsigned int core_mask)
 {
 	int ret;
 
@@ -68,152 +119,160 @@ static int skl_dsp_core_unset_reset_state(struct sst_dsp *ctx)
 
 	/* update bits */
 	sst_dsp_shim_update_bits_unlocked(ctx, SKL_ADSP_REG_ADSPCS,
-					SKL_ADSPCS_CRST_MASK, 0);
+				SKL_ADSPCS_CRST_MASK(core_mask), 0);
 
 	/* poll with timeout to check if operation successful */
 	ret = sst_dsp_register_poll(ctx,
 			SKL_ADSP_REG_ADSPCS,
-			SKL_ADSPCS_CRST_MASK,
+			SKL_ADSPCS_CRST_MASK(core_mask),
 			0,
 			SKL_DSP_RESET_TO,
 			"Unset reset");
 
 	if ((sst_dsp_shim_read_unlocked(ctx, SKL_ADSP_REG_ADSPCS) &
-				 SKL_ADSPCS_CRST(SKL_DSP_CORES_MASK)) != 0) {
-		dev_err(ctx->dev, "Unset reset state failed\n");
+				SKL_ADSPCS_CRST_MASK(core_mask)) != 0) {
+		dev_err(ctx->dev, "Unset reset state failed: core_mask %x\n",
+				core_mask);
 		ret = -EIO;
 	}
 
 	return ret;
 }
 
-static bool is_skl_dsp_core_enable(struct sst_dsp *ctx)
+static bool
+is_skl_dsp_core_enable(struct sst_dsp *ctx, unsigned int core_mask)
 {
 	int val;
 	bool is_enable;
 
 	val = sst_dsp_shim_read_unlocked(ctx, SKL_ADSP_REG_ADSPCS);
 
-	is_enable = ((val & SKL_ADSPCS_CPA(SKL_DSP_CORES_MASK)) &&
-			(val & SKL_ADSPCS_SPA(SKL_DSP_CORES_MASK)) &&
-			!(val & SKL_ADSPCS_CRST(SKL_DSP_CORES_MASK)) &&
-			!(val & SKL_ADSPCS_CSTALL(SKL_DSP_CORES_MASK)));
+	is_enable = ((val & SKL_ADSPCS_CPA_MASK(core_mask)) &&
+			(val & SKL_ADSPCS_SPA_MASK(core_mask)) &&
+			!(val & SKL_ADSPCS_CRST_MASK(core_mask)) &&
+			!(val & SKL_ADSPCS_CSTALL_MASK(core_mask)));
+
+	dev_dbg(ctx->dev, "DSP core(s) enabled? %d : core_mask %x\n",
+						is_enable, core_mask);
 
-	dev_dbg(ctx->dev, "DSP core is enabled=%d\n", is_enable);
 	return is_enable;
 }
 
-static int skl_dsp_reset_core(struct sst_dsp *ctx)
+static int skl_dsp_reset_core(struct sst_dsp *ctx, unsigned int core_mask)
 {
 	/* stall core */
-	sst_dsp_shim_write_unlocked(ctx, SKL_ADSP_REG_ADSPCS,
-			 sst_dsp_shim_read_unlocked(ctx, SKL_ADSP_REG_ADSPCS) &
-				SKL_ADSPCS_CSTALL(SKL_DSP_CORES_MASK));
+	sst_dsp_shim_update_bits_unlocked(ctx, SKL_ADSP_REG_ADSPCS,
+			SKL_ADSPCS_CSTALL_MASK(core_mask),
+			SKL_ADSPCS_CSTALL_MASK(core_mask));
 
 	/* set reset state */
-	return skl_dsp_core_set_reset_state(ctx);
+	return skl_dsp_core_set_reset_state(ctx, core_mask);
 }
 
-static int skl_dsp_start_core(struct sst_dsp *ctx)
+int skl_dsp_start_core(struct sst_dsp *ctx, unsigned int core_mask)
 {
 	int ret;
 
 	/* unset reset state */
-	ret = skl_dsp_core_unset_reset_state(ctx);
-	if (ret < 0) {
-		dev_dbg(ctx->dev, "dsp unset reset fails\n");
+	ret = skl_dsp_core_unset_reset_state(ctx, core_mask);
+	if (ret < 0)
 		return ret;
-	}
 
 	/* run core */
-	dev_dbg(ctx->dev, "run core...\n");
-	sst_dsp_shim_write_unlocked(ctx, SKL_ADSP_REG_ADSPCS,
-			 sst_dsp_shim_read_unlocked(ctx, SKL_ADSP_REG_ADSPCS) &
-				~SKL_ADSPCS_CSTALL(SKL_DSP_CORES_MASK));
-
-	if (!is_skl_dsp_core_enable(ctx)) {
-		skl_dsp_reset_core(ctx);
-		dev_err(ctx->dev, "DSP core enable failed\n");
+	dev_dbg(ctx->dev, "unstall/run core: core_mask = %x\n", core_mask);
+	sst_dsp_shim_update_bits_unlocked(ctx, SKL_ADSP_REG_ADSPCS,
+			SKL_ADSPCS_CSTALL_MASK(core_mask), 0);
+
+	if (!is_skl_dsp_core_enable(ctx, core_mask)) {
+		skl_dsp_reset_core(ctx, core_mask);
+		dev_err(ctx->dev, "DSP start core failed: core_mask %x\n",
+							core_mask);
 		ret = -EIO;
 	}
 
 	return ret;
 }
 
-static int skl_dsp_core_power_up(struct sst_dsp *ctx)
+int skl_dsp_core_power_up(struct sst_dsp *ctx, unsigned int core_mask)
 {
 	int ret;
 
 	/* update bits */
 	sst_dsp_shim_update_bits_unlocked(ctx, SKL_ADSP_REG_ADSPCS,
-			SKL_ADSPCS_SPA_MASK, SKL_ADSPCS_SPA(SKL_DSP_CORES_MASK));
+			SKL_ADSPCS_SPA_MASK(core_mask),
+			SKL_ADSPCS_SPA_MASK(core_mask));
 
 	/* poll with timeout to check if operation successful */
 	ret = sst_dsp_register_poll(ctx,
 			SKL_ADSP_REG_ADSPCS,
-			SKL_ADSPCS_CPA_MASK,
-			SKL_ADSPCS_CPA(SKL_DSP_CORES_MASK),
+			SKL_ADSPCS_CPA_MASK(core_mask),
+			SKL_ADSPCS_CPA_MASK(core_mask),
 			SKL_DSP_PU_TO,
 			"Power up");
 
 	if ((sst_dsp_shim_read_unlocked(ctx, SKL_ADSP_REG_ADSPCS) &
-			SKL_ADSPCS_CPA(SKL_DSP_CORES_MASK)) !=
-			SKL_ADSPCS_CPA(SKL_DSP_CORES_MASK)) {
-		dev_err(ctx->dev, "DSP core power up failed\n");
+			SKL_ADSPCS_CPA_MASK(core_mask)) !=
+			SKL_ADSPCS_CPA_MASK(core_mask)) {
+		dev_err(ctx->dev, "DSP core power up failed: core_mask %x\n",
+				core_mask);
 		ret = -EIO;
 	}
 
 	return ret;
 }
 
-static int skl_dsp_core_power_down(struct sst_dsp *ctx)
+int skl_dsp_core_power_down(struct sst_dsp  *ctx, unsigned int core_mask)
 {
 	/* update bits */
 	sst_dsp_shim_update_bits_unlocked(ctx, SKL_ADSP_REG_ADSPCS,
-					SKL_ADSPCS_SPA_MASK, 0);
+				SKL_ADSPCS_SPA_MASK(core_mask), 0);
 
 	/* poll with timeout to check if operation successful */
 	return sst_dsp_register_poll(ctx,
 			SKL_ADSP_REG_ADSPCS,
-			SKL_ADSPCS_CPA_MASK,
+			SKL_ADSPCS_CPA_MASK(core_mask),
 			0,
 			SKL_DSP_PD_TO,
 			"Power down");
 }
 
-int skl_dsp_enable_core(struct sst_dsp *ctx)
+int skl_dsp_enable_core(struct sst_dsp  *ctx, unsigned int core_mask)
 {
 	int ret;
 
 	/* power up */
-	ret = skl_dsp_core_power_up(ctx);
+	ret = skl_dsp_core_power_up(ctx, core_mask);
 	if (ret < 0) {
-		dev_dbg(ctx->dev, "dsp core power up failed\n");
+		dev_err(ctx->dev, "dsp core power up failed: core_mask %x\n",
+							core_mask);
 		return ret;
 	}
 
-	return skl_dsp_start_core(ctx);
+	return skl_dsp_start_core(ctx, core_mask);
 }
 
-int skl_dsp_disable_core(struct sst_dsp *ctx)
+int skl_dsp_disable_core(struct sst_dsp *ctx, unsigned int core_mask)
 {
 	int ret;
 
-	ret = skl_dsp_reset_core(ctx);
+	ret = skl_dsp_reset_core(ctx, core_mask);
 	if (ret < 0) {
-		dev_err(ctx->dev, "dsp core reset failed\n");
+		dev_err(ctx->dev, "dsp core reset failed: core_mask %x\n",
+							core_mask);
 		return ret;
 	}
 
 	/* power down core*/
-	ret = skl_dsp_core_power_down(ctx);
+	ret = skl_dsp_core_power_down(ctx, core_mask);
 	if (ret < 0) {
-		dev_err(ctx->dev, "dsp core power down failed\n");
+		dev_err(ctx->dev, "dsp core power down fail mask %x: %d\n",
+							core_mask, ret);
 		return ret;
 	}
 
-	if (is_skl_dsp_core_enable(ctx)) {
-		dev_err(ctx->dev, "DSP core disable failed\n");
+	if (is_skl_dsp_core_enable(ctx, core_mask)) {
+		dev_err(ctx->dev, "dsp core disable fail mask %x: %d\n",
+							core_mask, ret);
 		ret = -EIO;
 	}
 
@@ -224,28 +283,25 @@ int skl_dsp_boot(struct sst_dsp *ctx)
 {
 	int ret;
 
-	if (is_skl_dsp_core_enable(ctx)) {
-		dev_dbg(ctx->dev, "dsp core is already enabled, so reset the dap core\n");
-		ret = skl_dsp_reset_core(ctx);
+	if (is_skl_dsp_core_enable(ctx, SKL_DSP_CORE0_MASK)) {
+		ret = skl_dsp_reset_core(ctx, SKL_DSP_CORE0_MASK);
 		if (ret < 0) {
-			dev_err(ctx->dev, "dsp reset failed\n");
+			dev_err(ctx->dev, "dsp core0 reset fail: %d\n", ret);
 			return ret;
 		}
 
-		ret = skl_dsp_start_core(ctx);
+		ret = skl_dsp_start_core(ctx, SKL_DSP_CORE0_MASK);
 		if (ret < 0) {
-			dev_err(ctx->dev, "dsp start failed\n");
+			dev_err(ctx->dev, "dsp core0 start fail: %d\n", ret);
 			return ret;
 		}
 	} else {
-		dev_dbg(ctx->dev, "disable and enable to make sure DSP is invalid state\n");
-		ret = skl_dsp_disable_core(ctx);
-
+		ret = skl_dsp_disable_core(ctx, SKL_DSP_CORE0_MASK);
 		if (ret < 0) {
-			dev_err(ctx->dev, "dsp disable core failes\n");
+			dev_err(ctx->dev, "dsp core0 disable fail: %d\n", ret);
 			return ret;
 		}
-		ret = skl_dsp_enable_core(ctx);
+		ret = skl_dsp_enable_core(ctx, SKL_DSP_CORE0_MASK);
 	}
 
 	return ret;
@@ -281,16 +337,74 @@ irqreturn_t skl_dsp_sst_interrupt(int irq, void *dev_id)
 
 	return result;
 }
+/*
+ * skl_dsp_get_core/skl_dsp_put_core will be called inside DAPM context
+ * within the dapm mutex. Hence no separate lock is used.
+ */
+int skl_dsp_get_core(struct sst_dsp *ctx, unsigned int core_id)
+{
+	struct skl_sst *skl = ctx->thread_context;
+	int ret = 0;
+
+	if (core_id >= skl->cores.count) {
+		dev_err(ctx->dev, "invalid core id: %d\n", core_id);
+		return -EINVAL;
+	}
+
+	if (skl->cores.state[core_id] == SKL_DSP_RESET) {
+		ret = ctx->fw_ops.set_state_D0(ctx, core_id);
+		if (ret < 0) {
+			dev_err(ctx->dev, "unable to get core%d\n", core_id);
+			return ret;
+		}
+	}
+
+	skl->cores.usage_count[core_id]++;
+
+	dev_dbg(ctx->dev, "core id %d state %d usage_count %d\n",
+			core_id, skl->cores.state[core_id],
+			skl->cores.usage_count[core_id]);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(skl_dsp_get_core);
+
+int skl_dsp_put_core(struct sst_dsp *ctx, unsigned int core_id)
+{
+	struct skl_sst *skl = ctx->thread_context;
+	int ret = 0;
+
+	if (core_id >= skl->cores.count) {
+		dev_err(ctx->dev, "invalid core id: %d\n", core_id);
+		return -EINVAL;
+	}
+
+	if (--skl->cores.usage_count[core_id] == 0) {
+		ret = ctx->fw_ops.set_state_D3(ctx, core_id);
+		if (ret < 0) {
+			dev_err(ctx->dev, "unable to put core %d: %d\n",
+					core_id, ret);
+			skl->cores.usage_count[core_id]++;
+		}
+	}
+
+	dev_dbg(ctx->dev, "core id %d state %d usage_count %d\n",
+			core_id, skl->cores.state[core_id],
+			skl->cores.usage_count[core_id]);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(skl_dsp_put_core);
 
 int skl_dsp_wake(struct sst_dsp *ctx)
 {
-	return ctx->fw_ops.set_state_D0(ctx);
+	return skl_dsp_get_core(ctx, SKL_DSP_CORE0_ID);
 }
 EXPORT_SYMBOL_GPL(skl_dsp_wake);
 
 int skl_dsp_sleep(struct sst_dsp *ctx)
 {
-	return ctx->fw_ops.set_state_D3(ctx);
+	return skl_dsp_put_core(ctx, SKL_DSP_CORE0_ID);
 }
 EXPORT_SYMBOL_GPL(skl_dsp_sleep);
 
@@ -337,9 +451,7 @@ void skl_dsp_free(struct sst_dsp *dsp)
 
 	free_irq(dsp->irq, dsp);
 	skl_ipc_op_int_disable(dsp);
-	skl_ipc_int_disable(dsp);
-
-	skl_dsp_disable_core(dsp);
+	skl_dsp_disable_core(dsp, SKL_DSP_CORE0_MASK);
 }
 EXPORT_SYMBOL_GPL(skl_dsp_free);
 
diff --git a/sound/soc/intel/skylake/skl-sst-dsp.h b/sound/soc/intel/skylake/skl-sst-dsp.h
index deabe7308d3b..0f8629ef79ac 100644
--- a/sound/soc/intel/skylake/skl-sst-dsp.h
+++ b/sound/soc/intel/skylake/skl-sst-dsp.h
@@ -19,6 +19,7 @@
 #include <linux/interrupt.h>
 #include <sound/memalloc.h>
 #include "skl-sst-cldma.h"
+#include "skl-tplg-interface.h"
 
 struct sst_dsp;
 struct skl_sst;
@@ -76,35 +77,53 @@ struct sst_dsp_device;
 #define SKL_ADSPIC_IPC			1
 #define SKL_ADSPIS_IPC			1
 
+/* Core ID of core0 */
+#define SKL_DSP_CORE0_ID		0
+
+/* Mask for a given core index, c = 0.. number of supported cores - 1 */
+#define SKL_DSP_CORE_MASK(c)		BIT(c)
+
+/*
+ * Core 0 mask = SKL_DSP_CORE_MASK(0); Defined separately
+ * since Core0 is primary core and it is used often
+ */
+#define SKL_DSP_CORE0_MASK		BIT(0)
+
+/*
+ * Mask for a given number of cores
+ * nc = number of supported cores
+ */
+#define SKL_DSP_CORES_MASK(nc)	GENMASK((nc - 1), 0)
+
 /* ADSPCS - Audio DSP Control & Status */
-#define SKL_DSP_CORES		1
-#define SKL_DSP_CORE0_MASK	1
-#define SKL_DSP_CORES_MASK	((1 << SKL_DSP_CORES) - 1)
-
-/* Core Reset - asserted high */
-#define SKL_ADSPCS_CRST_SHIFT	0
-#define SKL_ADSPCS_CRST_MASK	(SKL_DSP_CORES_MASK << SKL_ADSPCS_CRST_SHIFT)
-#define SKL_ADSPCS_CRST(x)	((x << SKL_ADSPCS_CRST_SHIFT) & SKL_ADSPCS_CRST_MASK)
-
-/* Core run/stall - when set to '1' core is stalled */
-#define SKL_ADSPCS_CSTALL_SHIFT	8
-#define SKL_ADSPCS_CSTALL_MASK	(SKL_DSP_CORES_MASK <<	\
-					SKL_ADSPCS_CSTALL_SHIFT)
-#define SKL_ADSPCS_CSTALL(x)	((x << SKL_ADSPCS_CSTALL_SHIFT) &	\
-				SKL_ADSPCS_CSTALL_MASK)
-
-/* Set Power Active - when set to '1' turn cores on */
-#define SKL_ADSPCS_SPA_SHIFT	16
-#define SKL_ADSPCS_SPA_MASK	(SKL_DSP_CORES_MASK << SKL_ADSPCS_SPA_SHIFT)
-#define SKL_ADSPCS_SPA(x)	((x << SKL_ADSPCS_SPA_SHIFT) & SKL_ADSPCS_SPA_MASK)
-
-/* Current Power Active - power status of cores, set by hardware */
-#define SKL_ADSPCS_CPA_SHIFT	24
-#define SKL_ADSPCS_CPA_MASK	(SKL_DSP_CORES_MASK << SKL_ADSPCS_CPA_SHIFT)
-#define SKL_ADSPCS_CPA(x)	((x << SKL_ADSPCS_CPA_SHIFT) & SKL_ADSPCS_CPA_MASK)
-
-#define SST_DSP_POWER_D0	0x0  /* full On */
-#define SST_DSP_POWER_D3	0x3  /* Off */
+
+/*
+ * Core Reset - asserted high
+ * CRST Mask for a given core mask pattern, cm
+ */
+#define SKL_ADSPCS_CRST_SHIFT		0
+#define SKL_ADSPCS_CRST_MASK(cm)	((cm) << SKL_ADSPCS_CRST_SHIFT)
+
+/*
+ * Core run/stall - when set to '1' core is stalled
+ * CSTALL Mask for a given core mask pattern, cm
+ */
+#define SKL_ADSPCS_CSTALL_SHIFT		8
+#define SKL_ADSPCS_CSTALL_MASK(cm)	((cm) << SKL_ADSPCS_CSTALL_SHIFT)
+
+/*
+ * Set Power Active - when set to '1' turn cores on
+ * SPA Mask for a given core mask pattern, cm
+ */
+#define SKL_ADSPCS_SPA_SHIFT		16
+#define SKL_ADSPCS_SPA_MASK(cm)		((cm) << SKL_ADSPCS_SPA_SHIFT)
+
+/*
+ * Current Power Active - power status of cores, set by hardware
+ * CPA Mask for a given core mask pattern, cm
+ */
+#define SKL_ADSPCS_CPA_SHIFT		24
+#define SKL_ADSPCS_CPA_MASK(cm)		((cm) << SKL_ADSPCS_CPA_SHIFT)
 
 enum skl_dsp_states {
 	SKL_DSP_RUNNING = 1,
@@ -115,8 +134,8 @@ struct skl_dsp_fw_ops {
 	int (*load_fw)(struct sst_dsp  *ctx);
 	/* FW module parser/loader */
 	int (*parse_fw)(struct sst_dsp *ctx);
-	int (*set_state_D0)(struct sst_dsp *ctx);
-	int (*set_state_D3)(struct sst_dsp *ctx);
+	int (*set_state_D0)(struct sst_dsp *ctx, unsigned int core_id);
+	int (*set_state_D3)(struct sst_dsp *ctx, unsigned int core_id);
 	unsigned int (*get_fw_errcode)(struct sst_dsp *ctx);
 	int (*load_mod)(struct sst_dsp *ctx, u16 mod_id, u8 *mod_name);
 	int (*unload_mod)(struct sst_dsp *ctx, u16 mod_id);
@@ -157,14 +176,26 @@ int skl_cldma_prepare(struct sst_dsp *ctx);
 void skl_dsp_set_state_locked(struct sst_dsp *ctx, int state);
 struct sst_dsp *skl_dsp_ctx_init(struct device *dev,
 		struct sst_dsp_device *sst_dev, int irq);
-int skl_dsp_enable_core(struct sst_dsp *ctx);
-int skl_dsp_disable_core(struct sst_dsp *ctx);
 bool is_skl_dsp_running(struct sst_dsp *ctx);
+
+unsigned int skl_dsp_get_enabled_cores(struct sst_dsp *ctx);
+void skl_dsp_init_core_state(struct sst_dsp *ctx);
+int skl_dsp_enable_core(struct sst_dsp *ctx, unsigned int core_mask);
+int skl_dsp_disable_core(struct sst_dsp *ctx, unsigned int core_mask);
+int skl_dsp_core_power_up(struct sst_dsp *ctx, unsigned int core_mask);
+int skl_dsp_core_power_down(struct sst_dsp *ctx, unsigned int core_mask);
+int skl_dsp_core_unset_reset_state(struct sst_dsp *ctx,
+					unsigned int core_mask);
+int skl_dsp_start_core(struct sst_dsp *ctx, unsigned int core_mask);
+
 irqreturn_t skl_dsp_sst_interrupt(int irq, void *dev_id);
 int skl_dsp_wake(struct sst_dsp *ctx);
 int skl_dsp_sleep(struct sst_dsp *ctx);
 void skl_dsp_free(struct sst_dsp *dsp);
 
+int skl_dsp_get_core(struct sst_dsp *ctx, unsigned int core_id);
+int skl_dsp_put_core(struct sst_dsp *ctx, unsigned int core_id);
+
 int skl_dsp_boot(struct sst_dsp *ctx);
 int skl_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 		const char *fw_name, struct skl_dsp_loader_ops dsp_ops,
@@ -175,4 +206,11 @@ int bxt_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 void skl_sst_dsp_cleanup(struct device *dev, struct skl_sst *ctx);
 void bxt_sst_dsp_cleanup(struct device *dev, struct skl_sst *ctx);
 
+int snd_skl_get_module_info(struct skl_sst *ctx, u8 *uuid,
+		struct skl_dfw_module *dfw_config);
+int snd_skl_parse_uuids(struct sst_dsp *ctx, unsigned int offset);
+void skl_freeup_uuid_list(struct skl_sst *ctx);
+
+int skl_dsp_strip_extended_manifest(struct firmware *fw);
+
 #endif /*__SKL_SST_DSP_H__*/
diff --git a/sound/soc/intel/skylake/skl-sst-ipc.c b/sound/soc/intel/skylake/skl-sst-ipc.c
index 543460293b00..96f2f6889b18 100644
--- a/sound/soc/intel/skylake/skl-sst-ipc.c
+++ b/sound/soc/intel/skylake/skl-sst-ipc.c
@@ -363,7 +363,7 @@ static void skl_ipc_process_reply(struct sst_generic_ipc *ipc,
 	/* first process the header */
 	switch (reply) {
 	case IPC_GLB_REPLY_SUCCESS:
-		dev_info(ipc->dev, "ipc FW reply %x: success\n", header.primary);
+		dev_dbg(ipc->dev, "ipc FW reply %x: success\n", header.primary);
 		/* copy the rx data from the mailbox */
 		sst_dsp_inbox_read(ipc->dsp, msg->rx_data, msg->rx_size);
 		break;
@@ -692,7 +692,7 @@ int skl_ipc_init_instance(struct sst_generic_ipc *ipc,
 	 /* param_block_size must be in dwords */
 	u16 param_block_size = msg->param_data_size / sizeof(u32);
 
-	print_hex_dump(KERN_DEBUG, NULL, DUMP_PREFIX_NONE,
+	print_hex_dump_debug("Param data:", DUMP_PREFIX_NONE,
 		16, 4, buffer, param_block_size, false);
 
 	header.primary = IPC_MSG_TARGET(IPC_MOD_MSG);
diff --git a/sound/soc/intel/skylake/skl-sst-ipc.h b/sound/soc/intel/skylake/skl-sst-ipc.h
index d59d1ba62a43..2e3d4e80ef97 100644
--- a/sound/soc/intel/skylake/skl-sst-ipc.h
+++ b/sound/soc/intel/skylake/skl-sst-ipc.h
@@ -45,6 +45,14 @@ struct skl_ipc_header {
 	u32 extension;
 };
 
+#define SKL_DSP_CORES_MAX  2
+
+struct skl_dsp_cores {
+	unsigned int count;
+	enum skl_dsp_states state[SKL_DSP_CORES_MAX];
+	int usage_count[SKL_DSP_CORES_MAX];
+};
+
 struct skl_sst {
 	struct device *dev;
 	struct sst_dsp *dsp;
@@ -60,6 +68,15 @@ struct skl_sst {
 	void (*enable_miscbdcge)(struct device *dev, bool enable);
 	/*Is CGCTL.MISCBDCGE disabled*/
 	bool miscbdcg_disabled;
+
+	/* Populate module information */
+	struct list_head uuid_list;
+
+	/* Is firmware loaded */
+	bool fw_loaded;
+
+	/* multi-core */
+	struct skl_dsp_cores cores;
 };
 
 struct skl_ipc_init_instance_msg {
@@ -136,5 +153,6 @@ void skl_ipc_int_disable(struct sst_dsp *dsp);
 bool skl_ipc_int_status(struct sst_dsp *dsp);
 void skl_ipc_free(struct sst_generic_ipc *ipc);
 int skl_ipc_init(struct device *dev, struct skl_sst *skl);
+void skl_clear_module_cnt(struct sst_dsp *ctx);
 
 #endif /* __SKL_IPC_H */
diff --git a/sound/soc/intel/skylake/skl-sst-utils.c b/sound/soc/intel/skylake/skl-sst-utils.c
new file mode 100644
index 000000000000..25fcb796bd86
--- /dev/null
+++ b/sound/soc/intel/skylake/skl-sst-utils.c
@@ -0,0 +1,256 @@
+/*
+ *  skl-sst-utils.c - SKL sst utils functions
+ *
+ *  Copyright (C) 2016 Intel Corp
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/uuid.h>
+#include "skl-sst-dsp.h"
+#include "../common/sst-dsp.h"
+#include "../common/sst-dsp-priv.h"
+#include "skl-sst-ipc.h"
+
+
+#define UUID_STR_SIZE 37
+#define DEFAULT_HASH_SHA256_LEN 32
+
+/* FW Extended Manifest Header id = $AE1 */
+#define SKL_EXT_MANIFEST_HEADER_MAGIC   0x31454124
+
+struct skl_dfw_module_mod {
+	char name[100];
+	struct skl_dfw_module skl_dfw_mod;
+};
+
+struct UUID {
+	u8 id[16];
+};
+
+union seg_flags {
+	u32 ul;
+	struct {
+		u32 contents : 1;
+		u32 alloc    : 1;
+		u32 load     : 1;
+		u32 read_only : 1;
+		u32 code     : 1;
+		u32 data     : 1;
+		u32 _rsvd0   : 2;
+		u32 type     : 4;
+		u32 _rsvd1   : 4;
+		u32 length   : 16;
+	} r;
+} __packed;
+
+struct segment_desc {
+	union seg_flags flags;
+	u32 v_base_addr;
+	u32 file_offset;
+};
+
+struct module_type {
+	u32 load_type  : 4;
+	u32 auto_start : 1;
+	u32 domain_ll  : 1;
+	u32 domain_dp  : 1;
+	u32 rsvd       : 25;
+} __packed;
+
+struct adsp_module_entry {
+	u32 struct_id;
+	u8  name[8];
+	struct UUID uuid;
+	struct module_type type;
+	u8  hash1[DEFAULT_HASH_SHA256_LEN];
+	u32 entry_point;
+	u16 cfg_offset;
+	u16 cfg_count;
+	u32 affinity_mask;
+	u16 instance_max_count;
+	u16 instance_bss_size;
+	struct segment_desc segments[3];
+} __packed;
+
+struct adsp_fw_hdr {
+	u32 id;
+	u32 len;
+	u8  name[8];
+	u32 preload_page_count;
+	u32 fw_image_flags;
+	u32 feature_mask;
+	u16 major;
+	u16 minor;
+	u16 hotfix;
+	u16 build;
+	u32 num_modules;
+	u32 hw_buf_base;
+	u32 hw_buf_length;
+	u32 load_offset;
+} __packed;
+
+struct uuid_module {
+	uuid_le uuid;
+	int id;
+	int is_loadable;
+
+	struct list_head list;
+};
+
+struct skl_ext_manifest_hdr {
+	u32 id;
+	u32 len;
+	u16 version_major;
+	u16 version_minor;
+	u32 entries;
+};
+
+int snd_skl_get_module_info(struct skl_sst *ctx, u8 *uuid,
+			struct skl_dfw_module *dfw_config)
+{
+	struct uuid_module *module;
+	uuid_le *uuid_mod;
+
+	uuid_mod = (uuid_le *)uuid;
+
+	list_for_each_entry(module, &ctx->uuid_list, list) {
+		if (uuid_le_cmp(*uuid_mod, module->uuid) == 0) {
+			dfw_config->module_id = module->id;
+			dfw_config->is_loadable = module->is_loadable;
+
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(snd_skl_get_module_info);
+
+/*
+ * Parse the firmware binary to get the UUID, module id
+ * and loadable flags
+ */
+int snd_skl_parse_uuids(struct sst_dsp *ctx, unsigned int offset)
+{
+	struct adsp_fw_hdr *adsp_hdr;
+	struct adsp_module_entry *mod_entry;
+	int i, num_entry;
+	uuid_le *uuid_bin;
+	const char *buf;
+	struct skl_sst *skl = ctx->thread_context;
+	struct uuid_module *module;
+	struct firmware stripped_fw;
+	unsigned int safe_file;
+
+	/* Get the FW pointer to derive ADSP header */
+	stripped_fw.data = ctx->fw->data;
+	stripped_fw.size = ctx->fw->size;
+
+	skl_dsp_strip_extended_manifest(&stripped_fw);
+
+	buf = stripped_fw.data;
+
+	/* check if we have enough space in file to move to header */
+	safe_file = sizeof(*adsp_hdr) + offset;
+	if (stripped_fw.size <= safe_file) {
+		dev_err(ctx->dev, "Small fw file size, No space for hdr\n");
+		return -EINVAL;
+	}
+
+	adsp_hdr = (struct adsp_fw_hdr *)(buf + offset);
+
+	/* check 1st module entry is in file */
+	safe_file += adsp_hdr->len + sizeof(*mod_entry);
+	if (stripped_fw.size <= safe_file) {
+		dev_err(ctx->dev, "Small fw file size, No module entry\n");
+		return -EINVAL;
+	}
+
+	mod_entry = (struct adsp_module_entry *)
+		(buf + offset + adsp_hdr->len);
+
+	num_entry = adsp_hdr->num_modules;
+
+	/* check all entries are in file */
+	safe_file += num_entry * sizeof(*mod_entry);
+	if (stripped_fw.size <= safe_file) {
+		dev_err(ctx->dev, "Small fw file size, No modules\n");
+		return -EINVAL;
+	}
+
+
+	/*
+	 * Read the UUID(GUID) from FW Manifest.
+	 *
+	 * The 16 byte UUID format is: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXX
+	 * Populate the UUID table to store module_id and loadable flags
+	 * for the module.
+	 */
+
+	for (i = 0; i < num_entry; i++, mod_entry++) {
+		module = kzalloc(sizeof(*module), GFP_KERNEL);
+		if (!module)
+			return -ENOMEM;
+
+		uuid_bin = (uuid_le *)mod_entry->uuid.id;
+		memcpy(&module->uuid, uuid_bin, sizeof(module->uuid));
+
+		module->id = i;
+		module->is_loadable = mod_entry->type.load_type;
+
+		list_add_tail(&module->list, &skl->uuid_list);
+
+		dev_dbg(ctx->dev,
+			"Adding uuid :%pUL   mod id: %d  Loadable: %d\n",
+			&module->uuid, module->id, module->is_loadable);
+	}
+
+	return 0;
+}
+
+void skl_freeup_uuid_list(struct skl_sst *ctx)
+{
+	struct uuid_module *uuid, *_uuid;
+
+	list_for_each_entry_safe(uuid, _uuid, &ctx->uuid_list, list) {
+		list_del(&uuid->list);
+		kfree(uuid);
+	}
+}
+
+/*
+ * some firmware binary contains some extended manifest. This needs
+ * to be stripped in that case before we load and use that image.
+ *
+ * Get the module id for the module by checking
+ * the table for the UUID for the module
+ */
+int skl_dsp_strip_extended_manifest(struct firmware *fw)
+{
+	struct skl_ext_manifest_hdr *hdr;
+
+	/* check if fw file is greater than header we are looking */
+	if (fw->size < sizeof(hdr)) {
+		pr_err("%s: Firmware file small, no hdr\n", __func__);
+		return -EINVAL;
+	}
+
+	hdr = (struct skl_ext_manifest_hdr *)fw->data;
+
+	if (hdr->id == SKL_EXT_MANIFEST_HEADER_MAGIC) {
+		fw->size -= hdr->len;
+		fw->data += hdr->len;
+	}
+
+	return 0;
+}
diff --git a/sound/soc/intel/skylake/skl-sst.c b/sound/soc/intel/skylake/skl-sst.c
index 13ec8d53b526..588f899ceb65 100644
--- a/sound/soc/intel/skylake/skl-sst.c
+++ b/sound/soc/intel/skylake/skl-sst.c
@@ -68,10 +68,13 @@ static int skl_transfer_firmware(struct sst_dsp *ctx,
 	return ret;
 }
 
+#define SKL_ADSP_FW_BIN_HDR_OFFSET 0x284
+
 static int skl_load_base_firmware(struct sst_dsp *ctx)
 {
 	int ret = 0, i;
 	struct skl_sst *skl = ctx->thread_context;
+	struct firmware stripped_fw;
 	u32 reg;
 
 	skl->boot_complete = false;
@@ -81,11 +84,25 @@ static int skl_load_base_firmware(struct sst_dsp *ctx)
 		ret = request_firmware(&ctx->fw, ctx->fw_name, ctx->dev);
 		if (ret < 0) {
 			dev_err(ctx->dev, "Request firmware failed %d\n", ret);
-			skl_dsp_disable_core(ctx);
 			return -EIO;
 		}
 	}
 
+	ret = snd_skl_parse_uuids(ctx, SKL_ADSP_FW_BIN_HDR_OFFSET);
+	if (ret < 0) {
+		dev_err(ctx->dev,
+				"UUID parsing err: %d\n", ret);
+		release_firmware(ctx->fw);
+		skl_dsp_disable_core(ctx, SKL_DSP_CORE0_MASK);
+		return ret;
+	}
+
+	/* check for extended manifest */
+	stripped_fw.data = ctx->fw->data;
+	stripped_fw.size = ctx->fw->size;
+
+	skl_dsp_strip_extended_manifest(&stripped_fw);
+
 	ret = skl_dsp_boot(ctx);
 	if (ret < 0) {
 		dev_err(ctx->dev, "Boot dsp core failed ret: %d", ret);
@@ -119,7 +136,7 @@ static int skl_load_base_firmware(struct sst_dsp *ctx)
 		goto transfer_firmware_failed;
 	}
 
-	ret = skl_transfer_firmware(ctx, ctx->fw->data, ctx->fw->size);
+	ret = skl_transfer_firmware(ctx, stripped_fw.data, stripped_fw.size);
 	if (ret < 0) {
 		dev_err(ctx->dev, "Transfer firmware failed%d\n", ret);
 		goto transfer_firmware_failed;
@@ -133,67 +150,87 @@ static int skl_load_base_firmware(struct sst_dsp *ctx)
 		}
 
 		dev_dbg(ctx->dev, "Download firmware successful%d\n", ret);
-		skl_dsp_set_state_locked(ctx, SKL_DSP_RUNNING);
+		skl->fw_loaded = true;
 	}
 	return 0;
 transfer_firmware_failed:
 	ctx->cl_dev.ops.cl_cleanup_controller(ctx);
 skl_load_base_firmware_failed:
-	skl_dsp_disable_core(ctx);
+	skl_dsp_disable_core(ctx, SKL_DSP_CORE0_MASK);
 	release_firmware(ctx->fw);
 	ctx->fw = NULL;
 	return ret;
 }
 
-static int skl_set_dsp_D0(struct sst_dsp *ctx)
+static int skl_set_dsp_D0(struct sst_dsp *ctx, unsigned int core_id)
 {
 	int ret;
+	struct skl_ipc_dxstate_info dx;
+	struct skl_sst *skl = ctx->thread_context;
+	unsigned int core_mask = SKL_DSP_CORE_MASK(core_id);
 
-	ret = skl_load_base_firmware(ctx);
-	if (ret < 0) {
-		dev_err(ctx->dev, "unable to load firmware\n");
-		return ret;
+	/* If core0 is being turned on, we need to load the FW */
+	if (core_id == SKL_DSP_CORE0_ID) {
+		ret = skl_load_base_firmware(ctx);
+		if (ret < 0) {
+			dev_err(ctx->dev, "unable to load firmware\n");
+			return ret;
+		}
 	}
 
-	skl_dsp_set_state_locked(ctx, SKL_DSP_RUNNING);
+	/*
+	 * If any core other than core 0 is being moved to D0, enable the
+	 * core and send the set dx IPC for the core.
+	 */
+	if (core_id != SKL_DSP_CORE0_ID) {
+		ret = skl_dsp_enable_core(ctx, core_mask);
+		if (ret < 0)
+			return ret;
+
+		dx.core_mask = core_mask;
+		dx.dx_mask = core_mask;
+
+		ret = skl_ipc_set_dx(&skl->ipc, SKL_INSTANCE_ID,
+					SKL_BASE_FW_MODULE_ID, &dx);
+		if (ret < 0) {
+			dev_err(ctx->dev, "Failed to set dsp to D0:core id= %d\n",
+					core_id);
+			skl_dsp_disable_core(ctx, core_mask);
+		}
+	}
+
+	skl->cores.state[core_id] = SKL_DSP_RUNNING;
 
 	return ret;
 }
 
-static int skl_set_dsp_D3(struct sst_dsp *ctx)
+static int skl_set_dsp_D3(struct sst_dsp *ctx, unsigned int core_id)
 {
 	int ret;
 	struct skl_ipc_dxstate_info dx;
 	struct skl_sst *skl = ctx->thread_context;
+	unsigned int core_mask = SKL_DSP_CORE_MASK(core_id);
 
-	dev_dbg(ctx->dev, "In %s:\n", __func__);
-	mutex_lock(&ctx->mutex);
-	if (!is_skl_dsp_running(ctx)) {
-		mutex_unlock(&ctx->mutex);
-		return 0;
-	}
-	mutex_unlock(&ctx->mutex);
-
-	dx.core_mask = SKL_DSP_CORE0_MASK;
+	dx.core_mask = core_mask;
 	dx.dx_mask = SKL_IPC_D3_MASK;
+
 	ret = skl_ipc_set_dx(&skl->ipc, SKL_INSTANCE_ID, SKL_BASE_FW_MODULE_ID, &dx);
 	if (ret < 0)
-		dev_err(ctx->dev,
-			"D3 request to FW failed, continuing reset: %d", ret);
-
-	/* disable Interrupt */
-	ctx->cl_dev.ops.cl_cleanup_controller(ctx);
-	skl_cldma_int_disable(ctx);
-	skl_ipc_op_int_disable(ctx);
-	skl_ipc_int_disable(ctx);
-
-	ret = skl_dsp_disable_core(ctx);
-	if (ret < 0) {
-		dev_err(ctx->dev, "disable dsp core failed ret: %d\n", ret);
-		ret = -EIO;
+		dev_err(ctx->dev, "set Dx core %d fail: %d\n", core_id, ret);
+
+	if (core_id == SKL_DSP_CORE0_ID) {
+		/* disable Interrupt */
+		ctx->cl_dev.ops.cl_cleanup_controller(ctx);
+		skl_cldma_int_disable(ctx);
+		skl_ipc_op_int_disable(ctx);
+		skl_ipc_int_disable(ctx);
 	}
-	skl_dsp_set_state_locked(ctx, SKL_DSP_RESET);
 
+	ret = skl_dsp_disable_core(ctx, core_mask);
+	if (ret < 0)
+		return ret;
+
+	skl->cores.state[core_id] = SKL_DSP_RESET;
 	return ret;
 }
 
@@ -360,6 +397,19 @@ static int skl_unload_module(struct sst_dsp *ctx, u16 mod_id)
 	return ret;
 }
 
+void skl_clear_module_cnt(struct sst_dsp *ctx)
+{
+	struct skl_module_table *module;
+
+	if (list_empty(&ctx->module_list))
+		return;
+
+	list_for_each_entry(module, &ctx->module_list, list) {
+		module->usage_cnt = 0;
+	}
+}
+EXPORT_SYMBOL_GPL(skl_clear_module_cnt);
+
 static void skl_clear_module_table(struct sst_dsp *ctx)
 {
 	struct skl_module_table *module, *tmp;
@@ -409,6 +459,7 @@ int skl_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 
 	skl->dev = dev;
 	skl_dev.thread_context = skl;
+	INIT_LIST_HEAD(&skl->uuid_list);
 
 	skl->dsp = skl_dsp_ctx_init(dev, &skl_dev, irq);
 	if (!skl->dsp) {
@@ -432,12 +483,16 @@ int skl_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 	if (ret)
 		return ret;
 
+	skl->cores.count = 2;
+
 	ret = sst->fw_ops.load_fw(sst);
 	if (ret < 0) {
 		dev_err(dev, "Load base fw failed : %d", ret);
 		goto cleanup;
 	}
 
+	skl_dsp_init_core_state(sst);
+
 	if (dsp)
 		*dsp = skl;
 
@@ -452,6 +507,7 @@ EXPORT_SYMBOL_GPL(skl_sst_dsp_init);
 void skl_sst_dsp_cleanup(struct device *dev, struct skl_sst *ctx)
 {
 	skl_clear_module_table(ctx->dsp);
+	skl_freeup_uuid_list(ctx);
 	skl_ipc_free(&ctx->ipc);
 	ctx->dsp->ops->free(ctx->dsp);
 	if (ctx->boot_complete) {
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index 3e036b0349b9..cc0150fc2601 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -379,43 +379,6 @@ static void skl_tplg_update_module_params(struct snd_soc_dapm_widget *w,
 }
 
 /*
- * A pipe can have multiple modules, each of them will be a DAPM widget as
- * well. While managing a pipeline we need to get the list of all the
- * widgets in a pipelines, so this helper - skl_tplg_get_pipe_widget() helps
- * to get the SKL type widgets in that pipeline
- */
-static int skl_tplg_alloc_pipe_widget(struct device *dev,
-	struct snd_soc_dapm_widget *w, struct skl_pipe *pipe)
-{
-	struct skl_module_cfg *src_module = NULL;
-	struct snd_soc_dapm_path *p = NULL;
-	struct skl_pipe_module *p_module = NULL;
-
-	p_module = devm_kzalloc(dev, sizeof(*p_module), GFP_KERNEL);
-	if (!p_module)
-		return -ENOMEM;
-
-	p_module->w = w;
-	list_add_tail(&p_module->node, &pipe->w_list);
-
-	snd_soc_dapm_widget_for_each_sink_path(w, p) {
-		if ((p->sink->priv == NULL)
-				&& (!is_skl_dsp_widget_type(w)))
-			continue;
-
-		if ((p->sink->priv != NULL) && p->connect
-				&& is_skl_dsp_widget_type(p->sink)) {
-
-			src_module = p->sink->priv;
-			if (pipe->ppl_id == src_module->pipe->ppl_id)
-				skl_tplg_alloc_pipe_widget(dev,
-							p->sink, pipe);
-		}
-	}
-	return 0;
-}
-
-/*
  * some modules can have multiple params set from user control and
  * need to be set after module is initialized. If set_param flag is
  * set module params will be done after module is initialised.
@@ -448,7 +411,7 @@ static int skl_tplg_set_module_params(struct snd_soc_dapm_widget *w,
 
 			if (bc->set_params == SKL_PARAM_SET) {
 				ret = skl_set_module_params(ctx,
-						(u32 *)bc->params, bc->max,
+						(u32 *)bc->params, bc->size,
 						bc->param_id, mconfig);
 				if (ret < 0)
 					return ret;
@@ -483,7 +446,7 @@ static int skl_tplg_set_module_init_data(struct snd_soc_dapm_widget *w)
 				continue;
 
 			mconfig->formats_config.caps = (u32 *)&bc->params;
-			mconfig->formats_config.caps_size = bc->max;
+			mconfig->formats_config.caps_size = bc->size;
 
 			break;
 		}
@@ -514,8 +477,6 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe)
 		if (!skl_is_pipe_mcps_avail(skl, mconfig))
 			return -ENOMEM;
 
-		skl_tplg_alloc_pipe_mcps(skl, mconfig);
-
 		if (mconfig->is_loadable && ctx->dsp->fw_ops.load_mod) {
 			ret = ctx->dsp->fw_ops.load_mod(ctx->dsp,
 				mconfig->id.module_id, mconfig->guid);
@@ -539,6 +500,7 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe)
 		if (ret < 0)
 			return ret;
 
+		skl_tplg_alloc_pipe_mcps(skl, mconfig);
 		ret = skl_tplg_set_module_params(w, ctx);
 		if (ret < 0)
 			return ret;
@@ -591,9 +553,6 @@ static int skl_tplg_mixer_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w,
 	if (!skl_is_pipe_mem_avail(skl, mconfig))
 		return -ENOMEM;
 
-	skl_tplg_alloc_pipe_mem(skl, mconfig);
-	skl_tplg_alloc_pipe_mcps(skl, mconfig);
-
 	/*
 	 * Create a list of modules for pipe.
 	 * This list contains modules from source to sink
@@ -602,19 +561,8 @@ static int skl_tplg_mixer_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w,
 	if (ret < 0)
 		return ret;
 
-	/*
-	 * we create a w_list of all widgets in that pipe. This list is not
-	 * freed on PMD event as widgets within a pipe are static. This
-	 * saves us cycles to get widgets in pipe every time.
-	 *
-	 * So if we have already initialized all the widgets of a pipeline
-	 * we skip, so check for list_empty and create the list if empty
-	 */
-	if (list_empty(&s_pipe->w_list)) {
-		ret = skl_tplg_alloc_pipe_widget(ctx->dev, w, s_pipe);
-		if (ret < 0)
-			return ret;
-	}
+	skl_tplg_alloc_pipe_mem(skl, mconfig);
+	skl_tplg_alloc_pipe_mcps(skl, mconfig);
 
 	/* Init all pipe modules from source to sink */
 	ret = skl_tplg_init_pipe_modules(skl, s_pipe);
@@ -949,13 +897,17 @@ static int skl_tplg_mixer_dapm_post_pmd_event(struct snd_soc_dapm_widget *w,
 	struct skl_pipe *s_pipe = mconfig->pipe;
 	int ret = 0;
 
+	if (s_pipe->state == SKL_PIPE_INVALID)
+		return -EINVAL;
+
 	skl_tplg_free_pipe_mcps(skl, mconfig);
 	skl_tplg_free_pipe_mem(skl, mconfig);
 
 	list_for_each_entry(w_module, &s_pipe->w_list, node) {
 		dst_module = w_module->w->priv;
 
-		skl_tplg_free_pipe_mcps(skl, dst_module);
+		if (mconfig->m_state >= SKL_MODULE_INIT_DONE)
+			skl_tplg_free_pipe_mcps(skl, dst_module);
 		if (src_module == NULL) {
 			src_module = dst_module;
 			continue;
@@ -1102,7 +1054,7 @@ static int skl_tplg_tlv_control_get(struct snd_kcontrol *kcontrol,
 
 	if (w->power)
 		skl_get_module_params(skl->skl_sst, (u32 *)bc->params,
-				      bc->max, bc->param_id, mconfig);
+				      bc->size, bc->param_id, mconfig);
 
 	/* decrement size for TLV header */
 	size -= 2 * sizeof(u32);
@@ -1136,6 +1088,10 @@ static int skl_tplg_tlv_control_set(struct snd_kcontrol *kcontrol,
 	struct skl *skl = get_skl_ctx(w->dapm->dev);
 
 	if (ac->params) {
+		if (size > ac->max)
+			return -EINVAL;
+
+		ac->size = size;
 		/*
 		 * if the param_is is of type Vendor, firmware expects actual
 		 * parameter id and size from the control.
@@ -1151,7 +1107,7 @@ static int skl_tplg_tlv_control_set(struct snd_kcontrol *kcontrol,
 
 		if (w->power)
 			return skl_set_module_params(skl->skl_sst,
-						(u32 *)ac->params, ac->max,
+						(u32 *)ac->params, ac->size,
 						ac->param_id, mconfig);
 	}
 
@@ -1159,6 +1115,39 @@ static int skl_tplg_tlv_control_set(struct snd_kcontrol *kcontrol,
 }
 
 /*
+ * Fill the dma id for host and link. In case of passthrough
+ * pipeline, this will both host and link in the same
+ * pipeline, so need to copy the link and host based on dev_type
+ */
+static void skl_tplg_fill_dma_id(struct skl_module_cfg *mcfg,
+				struct skl_pipe_params *params)
+{
+	struct skl_pipe *pipe = mcfg->pipe;
+
+	if (pipe->passthru) {
+		switch (mcfg->dev_type) {
+		case SKL_DEVICE_HDALINK:
+			pipe->p_params->link_dma_id = params->link_dma_id;
+			break;
+
+		case SKL_DEVICE_HDAHOST:
+			pipe->p_params->host_dma_id = params->host_dma_id;
+			break;
+
+		default:
+			break;
+		}
+		pipe->p_params->s_fmt = params->s_fmt;
+		pipe->p_params->ch = params->ch;
+		pipe->p_params->s_freq = params->s_freq;
+		pipe->p_params->stream = params->stream;
+
+	} else {
+		memcpy(pipe->p_params, params, sizeof(*params));
+	}
+}
+
+/*
  * The FE params are passed by hw_params of the DAI.
  * On hw_params, the params are stored in Gateway module of the FE and we
  * need to calculate the format in DSP module configuration, that
@@ -1168,10 +1157,9 @@ int skl_tplg_update_pipe_params(struct device *dev,
 			struct skl_module_cfg *mconfig,
 			struct skl_pipe_params *params)
 {
-	struct skl_pipe *pipe = mconfig->pipe;
 	struct skl_module_fmt *format = NULL;
 
-	memcpy(pipe->p_params, params, sizeof(*params));
+	skl_tplg_fill_dma_id(mconfig, params);
 
 	if (params->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		format = &mconfig->in_fmt[0];
@@ -1358,12 +1346,11 @@ static int skl_tplg_be_fill_pipe_params(struct snd_soc_dai *dai,
 				struct skl_module_cfg *mconfig,
 				struct skl_pipe_params *params)
 {
-	struct skl_pipe *pipe = mconfig->pipe;
 	struct nhlt_specific_cfg *cfg;
 	struct skl *skl = get_skl_ctx(dai->dev);
 	int link_type = skl_tplg_be_link_type(mconfig->dev_type);
 
-	memcpy(pipe->p_params, params, sizeof(*params));
+	skl_tplg_fill_dma_id(mconfig, params);
 
 	if (link_type == NHLT_LINK_HDA)
 		return 0;
@@ -1554,6 +1541,55 @@ static void skl_tplg_fill_fmt(struct skl_module_fmt *dst_fmt,
 	}
 }
 
+static void skl_clear_pin_config(struct snd_soc_platform *platform,
+				struct snd_soc_dapm_widget *w)
+{
+	int i;
+	struct skl_module_cfg *mconfig;
+	struct skl_pipe *pipe;
+
+	if (!strncmp(w->dapm->component->name, platform->component.name,
+					strlen(platform->component.name))) {
+		mconfig = w->priv;
+		pipe = mconfig->pipe;
+		for (i = 0; i < mconfig->max_in_queue; i++) {
+			mconfig->m_in_pin[i].in_use = false;
+			mconfig->m_in_pin[i].pin_state = SKL_PIN_UNBIND;
+		}
+		for (i = 0; i < mconfig->max_out_queue; i++) {
+			mconfig->m_out_pin[i].in_use = false;
+			mconfig->m_out_pin[i].pin_state = SKL_PIN_UNBIND;
+		}
+		pipe->state = SKL_PIPE_INVALID;
+		mconfig->m_state = SKL_MODULE_UNINIT;
+	}
+}
+
+void skl_cleanup_resources(struct skl *skl)
+{
+	struct skl_sst *ctx = skl->skl_sst;
+	struct snd_soc_platform *soc_platform = skl->platform;
+	struct snd_soc_dapm_widget *w;
+	struct snd_soc_card *card;
+
+	if (soc_platform == NULL)
+		return;
+
+	card = soc_platform->component.card;
+	if (!card || !card->instantiated)
+		return;
+
+	skl->resource.mem = 0;
+	skl->resource.mcps = 0;
+
+	list_for_each_entry(w, &card->widgets, list) {
+		if (is_skl_dsp_widget_type(w) && (w->priv != NULL))
+			skl_clear_pin_config(soc_platform, w);
+	}
+
+	skl_clear_module_cnt(ctx->dsp);
+}
+
 /*
  * Topology core widget load callback
  *
@@ -1585,6 +1621,10 @@ static int skl_tplg_widget_load(struct snd_soc_component *cmpnt,
 	w->priv = mconfig;
 	memcpy(&mconfig->guid, &dfw_config->uuid, 16);
 
+	ret = snd_skl_get_module_info(skl->skl_sst, mconfig->guid, dfw_config);
+	if (ret < 0)
+		return ret;
+
 	mconfig->id.module_id = dfw_config->module_id;
 	mconfig->id.instance_id = dfw_config->instance_id;
 	mconfig->mcps = dfw_config->max_mcps;
@@ -1683,6 +1723,7 @@ static int skl_init_algo_data(struct device *dev, struct soc_bytes_ext *be,
 	ac->max = dfw_ac->max;
 	ac->param_id = dfw_ac->param_id;
 	ac->set_params = dfw_ac->set_params;
+	ac->size = dfw_ac->max;
 
 	if (ac->max) {
 		ac->params = (char *) devm_kzalloc(dev, ac->max, GFP_KERNEL);
@@ -1733,6 +1774,60 @@ static struct snd_soc_tplg_ops skl_tplg_ops  = {
 	.bytes_ext_ops_count = ARRAY_SIZE(skl_tlv_ops),
 };
 
+/*
+ * A pipe can have multiple modules, each of them will be a DAPM widget as
+ * well. While managing a pipeline we need to get the list of all the
+ * widgets in a pipelines, so this helper - skl_tplg_create_pipe_widget_list()
+ * helps to get the SKL type widgets in that pipeline
+ */
+static int skl_tplg_create_pipe_widget_list(struct snd_soc_platform *platform)
+{
+	struct snd_soc_dapm_widget *w;
+	struct skl_module_cfg *mcfg = NULL;
+	struct skl_pipe_module *p_module = NULL;
+	struct skl_pipe *pipe;
+
+	list_for_each_entry(w, &platform->component.card->widgets, list) {
+		if (is_skl_dsp_widget_type(w) && w->priv != NULL) {
+			mcfg = w->priv;
+			pipe = mcfg->pipe;
+
+			p_module = devm_kzalloc(platform->dev,
+						sizeof(*p_module), GFP_KERNEL);
+			if (!p_module)
+				return -ENOMEM;
+
+			p_module->w = w;
+			list_add_tail(&p_module->node, &pipe->w_list);
+		}
+	}
+
+	return 0;
+}
+
+static void skl_tplg_set_pipe_type(struct skl *skl, struct skl_pipe *pipe)
+{
+	struct skl_pipe_module *w_module;
+	struct snd_soc_dapm_widget *w;
+	struct skl_module_cfg *mconfig;
+	bool host_found = false, link_found = false;
+
+	list_for_each_entry(w_module, &pipe->w_list, node) {
+		w = w_module->w;
+		mconfig = w->priv;
+
+		if (mconfig->dev_type == SKL_DEVICE_HDAHOST)
+			host_found = true;
+		else if (mconfig->dev_type != SKL_DEVICE_NONE)
+			link_found = true;
+	}
+
+	if (host_found && link_found)
+		pipe->passthru = true;
+	else
+		pipe->passthru = false;
+}
+
 /* This will be read from topology manifest, currently defined here */
 #define SKL_MAX_MCPS 30000000
 #define SKL_FW_MAX_MEM 1000000
@@ -1746,6 +1841,7 @@ int skl_tplg_init(struct snd_soc_platform *platform, struct hdac_ext_bus *ebus)
 	const struct firmware *fw;
 	struct hdac_bus *bus = ebus_to_hbus(ebus);
 	struct skl *skl = ebus_to_skl(ebus);
+	struct skl_pipeline *ppl;
 
 	ret = request_firmware(&fw, skl->tplg_name, bus->dev);
 	if (ret < 0) {
@@ -1775,6 +1871,12 @@ int skl_tplg_init(struct snd_soc_platform *platform, struct hdac_ext_bus *ebus)
 	skl->resource.max_mem = SKL_FW_MAX_MEM;
 
 	skl->tplg = fw;
+	ret = skl_tplg_create_pipe_widget_list(platform);
+	if (ret < 0)
+		return ret;
+
+	list_for_each_entry(ppl, &skl->ppl_list, node)
+		skl_tplg_set_pipe_type(skl, ppl->pipe);
 
 	return 0;
 }
diff --git a/sound/soc/intel/skylake/skl-topology.h b/sound/soc/intel/skylake/skl-topology.h
index e4b399cd7868..22d3ef83817d 100644
--- a/sound/soc/intel/skylake/skl-topology.h
+++ b/sound/soc/intel/skylake/skl-topology.h
@@ -244,7 +244,8 @@ enum skl_pipe_state {
 	SKL_PIPE_INVALID = 0,
 	SKL_PIPE_CREATED = 1,
 	SKL_PIPE_PAUSED = 2,
-	SKL_PIPE_STARTED = 3
+	SKL_PIPE_STARTED = 3,
+	SKL_PIPE_RESET = 4
 };
 
 struct skl_pipe_module {
@@ -270,6 +271,7 @@ struct skl_pipe {
 	struct skl_pipe_params *p_params;
 	enum skl_pipe_state state;
 	struct list_head w_list;
+	bool passthru;
 };
 
 enum skl_module_state {
@@ -319,6 +321,7 @@ struct skl_algo_data {
 	u32 param_id;
 	u32 set_params;
 	u32 max;
+	u32 size;
 	char *params;
 };
 
@@ -357,6 +360,8 @@ int skl_delete_pipe(struct skl_sst *ctx, struct skl_pipe *pipe);
 
 int skl_stop_pipe(struct skl_sst *ctx, struct skl_pipe *pipe);
 
+int skl_reset_pipe(struct skl_sst *ctx, struct skl_pipe *pipe);
+
 int skl_init_module(struct skl_sst *ctx, struct skl_module_cfg *module_config);
 
 int skl_bind_modules(struct skl_sst *ctx, struct skl_module_cfg
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 06d8c263c68f..cd59536a761d 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -35,6 +35,8 @@
 #include "skl-sst-dsp.h"
 #include "skl-sst-ipc.h"
 
+static struct skl_machine_pdata skl_dmic_data;
+
 /*
  * initialize the PCI registers
  */
@@ -184,6 +186,7 @@ static int _skl_suspend(struct hdac_ext_bus *ebus)
 {
 	struct skl *skl = ebus_to_skl(ebus);
 	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct pci_dev *pci = to_pci_dev(bus->dev);
 	int ret;
 
 	snd_hdac_ext_bus_link_power_down_all(ebus);
@@ -193,9 +196,12 @@ static int _skl_suspend(struct hdac_ext_bus *ebus)
 		return ret;
 
 	snd_hdac_bus_stop_chip(bus);
+	update_pci_dword(pci, AZX_PCIREG_PGCTL,
+		AZX_PGCTL_LSRMD_MASK, AZX_PGCTL_LSRMD_MASK);
 	skl_enable_miscbdcge(bus->dev, false);
 	snd_hdac_bus_enter_link_reset(bus);
 	skl_enable_miscbdcge(bus->dev, true);
+	skl_cleanup_resources(skl);
 
 	return 0;
 }
@@ -242,6 +248,7 @@ static int skl_suspend(struct device *dev)
 		ret = _skl_suspend(ebus);
 		if (ret < 0)
 			return ret;
+		skl->skl_sst->fw_loaded = false;
 	}
 
 	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) {
@@ -397,6 +404,10 @@ static int skl_machine_device_register(struct skl *skl, void *driver_data)
 		platform_device_put(pdev);
 		return -EIO;
 	}
+
+	if (mach->pdata)
+		dev_set_drvdata(&pdev->dev, mach->pdata);
+
 	skl->i2s_dev = pdev;
 
 	return 0;
@@ -657,6 +668,8 @@ static int skl_probe(struct pci_dev *pci,
 
 	skl->pci_id = pci->device;
 
+	device_disable_async_suspend(bus->dev);
+
 	skl->nhlt = skl_nhlt_init(bus->dev);
 
 	if (skl->nhlt == NULL)
@@ -666,6 +679,8 @@ static int skl_probe(struct pci_dev *pci,
 
 	pci_set_drvdata(skl->pci, ebus);
 
+	skl_dmic_data.dmic_num = skl_get_dmic_geo(skl);
+
 	/* check if dsp is there */
 	if (ebus->ppcap) {
 		err = skl_machine_device_register(skl,
@@ -713,7 +728,7 @@ static int skl_probe(struct pci_dev *pci,
 	list_for_each_entry(hlink, &ebus->hlink_list, list)
 		snd_hdac_ext_bus_link_put(ebus, hlink);
 
-	/*configure PM */
+	/* configure PM */
 	pm_runtime_put_noidle(bus->dev);
 	pm_runtime_allow(bus->dev);
 
@@ -766,8 +781,7 @@ static void skl_remove(struct pci_dev *pci)
 	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
 	struct skl *skl = ebus_to_skl(ebus);
 
-	if (skl->tplg)
-		release_firmware(skl->tplg);
+	release_firmware(skl->tplg);
 
 	if (pci_dev_run_wake(pci))
 		pm_runtime_get_noresume(&pci->dev);
@@ -786,15 +800,23 @@ static void skl_remove(struct pci_dev *pci)
 
 static struct sst_acpi_mach sst_skl_devdata[] = {
 	{ "INT343A", "skl_alc286s_i2s", "intel/dsp_fw_release.bin", NULL, NULL, NULL },
-	{ "INT343B", "skl_nau88l25_ssm4567_i2s", "intel/dsp_fw_release.bin",
-				NULL, NULL, NULL },
-	{ "MX98357A", "skl_nau88l25_max98357a_i2s", "intel/dsp_fw_release.bin",
-				NULL, NULL, NULL },
+	{ "INT343B", "skl_n88l25_s4567", "intel/dsp_fw_release.bin",
+				NULL, NULL, &skl_dmic_data },
+	{ "MX98357A", "skl_n88l25_m98357a", "intel/dsp_fw_release.bin",
+				NULL, NULL, &skl_dmic_data },
 	{}
 };
 
 static struct sst_acpi_mach sst_bxtp_devdata[] = {
 	{ "INT343A", "bxt_alc298s_i2s", "intel/dsp_fw_bxtn.bin", NULL, NULL, NULL },
+	{ "DLGS7219", "bxt_da7219_max98357a_i2s", "intel/dsp_fw_bxtn.bin", NULL, NULL, NULL },
+};
+
+static struct sst_acpi_mach sst_kbl_devdata[] = {
+	{ "INT343A", "kbl_alc286s_i2s", "intel/dsp_fw_kbl.bin", NULL, NULL, NULL },
+	{ "INT343B", "kbl_n88l25_s4567", "intel/dsp_fw_kbl.bin", NULL, NULL, &skl_dmic_data },
+	{ "MX98357A", "kbl_n88l25_m98357a", "intel/dsp_fw_kbl.bin", NULL, NULL, &skl_dmic_data },
+	{}
 };
 
 /* PCI IDs */
@@ -805,6 +827,9 @@ static const struct pci_device_id skl_ids[] = {
 	/* BXT-P */
 	{ PCI_DEVICE(0x8086, 0x5a98),
 		.driver_data = (unsigned long)&sst_bxtp_devdata},
+	/* KBL */
+	{ PCI_DEVICE(0x8086, 0x9D71),
+		.driver_data = (unsigned long)&sst_kbl_devdata},
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, skl_ids);
diff --git a/sound/soc/intel/skylake/skl.h b/sound/soc/intel/skylake/skl.h
index 4b4b3876aea9..9064e5b0d676 100644
--- a/sound/soc/intel/skylake/skl.h
+++ b/sound/soc/intel/skylake/skl.h
@@ -48,6 +48,8 @@
 #define AZX_REG_VS_SDXEFIFOS_XBASE	0x1094
 #define AZX_REG_VS_SDXEFIFOS_XINTERVAL	0x20
 
+#define AZX_PCIREG_PGCTL		0x44
+#define AZX_PGCTL_LSRMD_MASK		(1 << 4)
 #define AZX_PCIREG_CGCTL		0x48
 #define AZX_CGCTL_MISCBDCGE_MASK	(1 << 6)
 
@@ -65,6 +67,7 @@ struct skl {
 	unsigned int init_failed:1; /* delayed init failed */
 	struct platform_device *dmic_dev;
 	struct platform_device *i2s_dev;
+	struct snd_soc_platform *platform;
 
 	struct nhlt_acpi_table *nhlt; /* nhlt ptr */
 	struct skl_sst *skl_sst; /* sst skl ctx */
@@ -90,6 +93,11 @@ struct skl_dma_params {
 	u8 stream_tag;
 };
 
+/* to pass dmic data */
+struct skl_machine_pdata {
+	u32 dmic_num;
+};
+
 struct skl_dsp_ops {
 	int id;
 	struct skl_dsp_loader_ops (*loader_ops)(void);
@@ -108,9 +116,11 @@ void skl_nhlt_free(struct nhlt_acpi_table *addr);
 struct nhlt_specific_cfg *skl_get_ep_blob(struct skl *skl, u32 instance,
 			u8 link_type, u8 s_fmt, u8 no_ch, u32 s_rate, u8 dirn);
 
+int skl_get_dmic_geo(struct skl *skl);
 int skl_nhlt_update_topology_bin(struct skl *skl);
 int skl_init_dsp(struct skl *skl);
 int skl_free_dsp(struct skl *skl);
 int skl_suspend_dsp(struct skl *skl);
 int skl_resume_dsp(struct skl *skl);
+void skl_cleanup_resources(struct skl *skl);
 #endif /* __SOUND_SOC_SKL_H */
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 3abf51c07851..05cf809cf9e1 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -1,15 +1,40 @@
 config SND_SOC_MEDIATEK
-	tristate "ASoC support for Mediatek chip"
+	tristate
+
+config SND_SOC_MT2701
+	tristate "ASoC support for Mediatek MT2701 chip"
+	depends on ARCH_MEDIATEK
+	select SND_SOC_MEDIATEK
+	help
+	  This adds ASoC driver for Mediatek MT2701 boards
+	  that can be used with other codecs.
+	  Select Y if you have such device.
+	  If unsure select "N".
+
+config SND_SOC_MT2701_CS42448
+	tristate "ASoc Audio driver for MT2701 with CS42448 codec"
+	depends on SND_SOC_MT2701
+	select SND_SOC_CS42XX8_I2C
+	select SND_SOC_BT_SCO
+	help
+	  This adds ASoC driver for Mediatek MT2701 boards
+	  with the CS42448 codecs.
+	  Select Y if you have such device.
+	  If unsure select "N".
+
+config SND_SOC_MT8173
+	tristate "ASoC support for Mediatek MT8173 chip"
 	depends on ARCH_MEDIATEK
+	select SND_SOC_MEDIATEK
 	help
-	  This adds ASoC platform driver support for Mediatek chip
+	  This adds ASoC platform driver support for Mediatek MT8173 chip
 	  that can be used with other codecs.
 	  Select Y if you have such device.
 	  Ex: MT8173
 
 config SND_SOC_MT8173_MAX98090
 	tristate "ASoC Audio driver for MT8173 with MAX98090 codec"
-	depends on SND_SOC_MEDIATEK && I2C
+	depends on SND_SOC_MT8173 && I2C
 	select SND_SOC_MAX98090
 	help
 	  This adds ASoC driver for Mediatek MT8173 boards
@@ -19,8 +44,9 @@ config SND_SOC_MT8173_MAX98090
 
 config SND_SOC_MT8173_RT5650
 	tristate "ASoC Audio driver for MT8173 with RT5650 codec"
-	depends on SND_SOC_MEDIATEK && I2C
+	depends on SND_SOC_MT8173 && I2C
 	select SND_SOC_RT5645
+	select SND_SOC_HDMI_CODEC
 	help
 	  This adds ASoC driver for Mediatek MT8173 boards
 	  with the RT5650 audio codec.
@@ -29,7 +55,7 @@ config SND_SOC_MT8173_RT5650
 
 config SND_SOC_MT8173_RT5650_RT5514
 	tristate "ASoC Audio driver for MT8173 with RT5650 RT5514 codecs"
-	depends on SND_SOC_MEDIATEK && I2C
+	depends on SND_SOC_MT8173 && I2C
 	select SND_SOC_RT5645
 	select SND_SOC_RT5514
 	help
@@ -40,7 +66,7 @@ config SND_SOC_MT8173_RT5650_RT5514
 
 config SND_SOC_MT8173_RT5650_RT5676
 	tristate "ASoC Audio driver for MT8173 with RT5650 RT5676 codecs"
-	depends on SND_SOC_MEDIATEK && I2C
+	depends on SND_SOC_MT8173 && I2C
 	select SND_SOC_RT5645
 	select SND_SOC_RT5677
 	select SND_SOC_HDMI_CODEC
diff --git a/sound/soc/mediatek/Makefile b/sound/soc/mediatek/Makefile
index d486860c0a88..6bcab35dc828 100644
--- a/sound/soc/mediatek/Makefile
+++ b/sound/soc/mediatek/Makefile
@@ -1,7 +1,3 @@
-# MTK Platform Support
-obj-$(CONFIG_SND_SOC_MEDIATEK) += mtk-afe-pcm.o
-# Machine support
-obj-$(CONFIG_SND_SOC_MT8173_MAX98090) += mt8173-max98090.o
-obj-$(CONFIG_SND_SOC_MT8173_RT5650) += mt8173-rt5650.o
-obj-$(CONFIG_SND_SOC_MT8173_RT5650_RT5514) += mt8173-rt5650-rt5514.o
-obj-$(CONFIG_SND_SOC_MT8173_RT5650_RT5676) += mt8173-rt5650-rt5676.o
+obj-$(CONFIG_SND_SOC_MEDIATEK) += common/
+obj-$(CONFIG_SND_SOC_MT2701) += mt2701/
+obj-$(CONFIG_SND_SOC_MT8173) += mt8173/
diff --git a/sound/soc/mediatek/common/Makefile b/sound/soc/mediatek/common/Makefile
new file mode 100644
index 000000000000..a55d33bc7b01
--- /dev/null
+++ b/sound/soc/mediatek/common/Makefile
@@ -0,0 +1,16 @@
+#
+# Copyright (C) 2015 MediaTek Inc.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+
+# platform driver
+snd-soc-mtk-common-objs := mtk-afe-platform-driver.o mtk-afe-fe-dai.o
+obj-$(CONFIG_SND_SOC_MEDIATEK) += snd-soc-mtk-common.o
diff --git a/sound/soc/mediatek/common/mtk-afe-fe-dai.c b/sound/soc/mediatek/common/mtk-afe-fe-dai.c
new file mode 100644
index 000000000000..b788791b0a35
--- /dev/null
+++ b/sound/soc/mediatek/common/mtk-afe-fe-dai.c
@@ -0,0 +1,379 @@
+/*
+ * mtk-afe-fe-dais.c  --  Mediatek afe fe dai operator
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Garlic Tseng <garlic.tseng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+#include "mtk-afe-fe-dai.h"
+#include "mtk-base-afe.h"
+
+#define AFE_BASE_END_OFFSET 8
+
+int mtk_regmap_update_bits(struct regmap *map, int reg, unsigned int mask,
+			   unsigned int val)
+{
+	if (reg < 0)
+		return 0;
+	return regmap_update_bits(map, reg, mask, val);
+}
+
+int mtk_regmap_write(struct regmap *map, int reg, unsigned int val)
+{
+	if (reg < 0)
+		return 0;
+	return regmap_write(map, reg, val);
+}
+
+int mtk_afe_fe_startup(struct snd_pcm_substream *substream,
+		       struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	int memif_num = rtd->cpu_dai->id;
+	struct mtk_base_afe_memif *memif = &afe->memif[memif_num];
+	const struct snd_pcm_hardware *mtk_afe_hardware = afe->mtk_afe_hardware;
+	int ret;
+
+	memif->substream = substream;
+
+	snd_pcm_hw_constraint_step(substream->runtime, 0,
+				   SNDRV_PCM_HW_PARAM_BUFFER_BYTES, 16);
+	/* enable agent */
+	mtk_regmap_update_bits(afe->regmap, memif->data->agent_disable_reg,
+			       1 << memif->data->agent_disable_shift,
+			       0 << memif->data->agent_disable_shift);
+
+	snd_soc_set_runtime_hwparams(substream, mtk_afe_hardware);
+
+	/*
+	 * Capture cannot use ping-pong buffer since hw_ptr at IRQ may be
+	 * smaller than period_size due to AFE's internal buffer.
+	 * This easily leads to overrun when avail_min is period_size.
+	 * One more period can hold the possible unread buffer.
+	 */
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+		int periods_max = mtk_afe_hardware->periods_max;
+
+		ret = snd_pcm_hw_constraint_minmax(runtime,
+						   SNDRV_PCM_HW_PARAM_PERIODS,
+						   3, periods_max);
+		if (ret < 0) {
+			dev_err(afe->dev, "hw_constraint_minmax failed\n");
+			return ret;
+		}
+	}
+
+	ret = snd_pcm_hw_constraint_integer(runtime,
+					    SNDRV_PCM_HW_PARAM_PERIODS);
+	if (ret < 0)
+		dev_err(afe->dev, "snd_pcm_hw_constraint_integer failed\n");
+
+	/* dynamic allocate irq to memif */
+	if (memif->irq_usage < 0) {
+		int irq_id = mtk_dynamic_irq_acquire(afe);
+
+		if (irq_id != afe->irqs_size) {
+			/* link */
+			memif->irq_usage = irq_id;
+		} else {
+			dev_err(afe->dev, "%s() error: no more asys irq\n",
+				__func__);
+			ret = -EBUSY;
+		}
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mtk_afe_fe_startup);
+
+void mtk_afe_fe_shutdown(struct snd_pcm_substream *substream,
+			 struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
+	int irq_id;
+
+	irq_id = memif->irq_usage;
+
+	mtk_regmap_update_bits(afe->regmap, memif->data->agent_disable_reg,
+			       1 << memif->data->agent_disable_shift,
+			       1 << memif->data->agent_disable_shift);
+
+	if (!memif->const_irq) {
+		mtk_dynamic_irq_release(afe, irq_id);
+		memif->irq_usage = -1;
+		memif->substream = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(mtk_afe_fe_shutdown);
+
+int mtk_afe_fe_hw_params(struct snd_pcm_substream *substream,
+			 struct snd_pcm_hw_params *params,
+			 struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
+	int msb_at_bit33 = 0;
+	int ret, fs = 0;
+
+	ret = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(params));
+	if (ret < 0)
+		return ret;
+
+	msb_at_bit33 = upper_32_bits(substream->runtime->dma_addr) ? 1 : 0;
+	memif->phys_buf_addr = lower_32_bits(substream->runtime->dma_addr);
+	memif->buffer_size = substream->runtime->dma_bytes;
+
+	/* start */
+	mtk_regmap_write(afe->regmap, memif->data->reg_ofs_base,
+			 memif->phys_buf_addr);
+	/* end */
+	mtk_regmap_write(afe->regmap,
+			 memif->data->reg_ofs_base + AFE_BASE_END_OFFSET,
+			 memif->phys_buf_addr + memif->buffer_size - 1);
+
+	/* set MSB to 33-bit */
+	mtk_regmap_update_bits(afe->regmap, memif->data->msb_reg,
+			       1 << memif->data->msb_shift,
+			       msb_at_bit33 << memif->data->msb_shift);
+
+	/* set channel */
+	if (memif->data->mono_shift >= 0) {
+		unsigned int mono = (params_channels(params) == 1) ? 1 : 0;
+
+		mtk_regmap_update_bits(afe->regmap, memif->data->mono_reg,
+				       1 << memif->data->mono_shift,
+				       mono << memif->data->mono_shift);
+	}
+
+	/* set rate */
+	if (memif->data->fs_shift < 0)
+		return 0;
+
+	fs = afe->memif_fs(substream, params_rate(params));
+
+	if (fs < 0)
+		return -EINVAL;
+
+	mtk_regmap_update_bits(afe->regmap, memif->data->fs_reg,
+			       memif->data->fs_maskbit << memif->data->fs_shift,
+			       fs << memif->data->fs_shift);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mtk_afe_fe_hw_params);
+
+int mtk_afe_fe_hw_free(struct snd_pcm_substream *substream,
+		       struct snd_soc_dai *dai)
+{
+	return snd_pcm_lib_free_pages(substream);
+}
+EXPORT_SYMBOL_GPL(mtk_afe_fe_hw_free);
+
+int mtk_afe_fe_trigger(struct snd_pcm_substream *substream, int cmd,
+		       struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_pcm_runtime * const runtime = substream->runtime;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
+	struct mtk_base_afe_irq *irqs = &afe->irqs[memif->irq_usage];
+	const struct mtk_base_irq_data *irq_data = irqs->irq_data;
+	unsigned int counter = runtime->period_size;
+	int fs;
+
+	dev_dbg(afe->dev, "%s %s cmd=%d\n", __func__, memif->data->name, cmd);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+		if (memif->data->enable_shift >= 0)
+			mtk_regmap_update_bits(afe->regmap,
+					       memif->data->enable_reg,
+					       1 << memif->data->enable_shift,
+					       1 << memif->data->enable_shift);
+
+		/* set irq counter */
+		mtk_regmap_update_bits(afe->regmap, irq_data->irq_cnt_reg,
+				       irq_data->irq_cnt_maskbit
+				       << irq_data->irq_cnt_shift,
+				       counter << irq_data->irq_cnt_shift);
+
+		/* set irq fs */
+		fs = afe->irq_fs(substream, runtime->rate);
+
+		if (fs < 0)
+			return -EINVAL;
+
+		mtk_regmap_update_bits(afe->regmap, irq_data->irq_fs_reg,
+				       irq_data->irq_fs_maskbit
+				       << irq_data->irq_fs_shift,
+				       fs << irq_data->irq_fs_shift);
+
+		/* enable interrupt */
+		mtk_regmap_update_bits(afe->regmap, irq_data->irq_en_reg,
+				       1 << irq_data->irq_en_shift,
+				       1 << irq_data->irq_en_shift);
+
+		return 0;
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+		mtk_regmap_update_bits(afe->regmap, memif->data->enable_reg,
+				       1 << memif->data->enable_shift, 0);
+		/* disable interrupt */
+		mtk_regmap_update_bits(afe->regmap, irq_data->irq_en_reg,
+				       1 << irq_data->irq_en_shift,
+				       0 << irq_data->irq_en_shift);
+		/* and clear pending IRQ */
+		mtk_regmap_write(afe->regmap, irq_data->irq_clr_reg,
+				 1 << irq_data->irq_clr_shift);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL_GPL(mtk_afe_fe_trigger);
+
+int mtk_afe_fe_prepare(struct snd_pcm_substream *substream,
+		       struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd  = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
+	int hd_audio = 0;
+
+	/* set hd mode */
+	switch (substream->runtime->format) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		hd_audio = 0;
+		break;
+	case SNDRV_PCM_FORMAT_S32_LE:
+		hd_audio = 1;
+		break;
+	case SNDRV_PCM_FORMAT_S24_LE:
+		hd_audio = 1;
+		break;
+	default:
+		dev_err(afe->dev, "%s() error: unsupported format %d\n",
+			__func__, substream->runtime->format);
+		break;
+	}
+
+	mtk_regmap_update_bits(afe->regmap, memif->data->hd_reg,
+			       1 << memif->data->hd_shift,
+			       hd_audio << memif->data->hd_shift);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mtk_afe_fe_prepare);
+
+const struct snd_soc_dai_ops mtk_afe_fe_ops = {
+	.startup	= mtk_afe_fe_startup,
+	.shutdown	= mtk_afe_fe_shutdown,
+	.hw_params	= mtk_afe_fe_hw_params,
+	.hw_free	= mtk_afe_fe_hw_free,
+	.prepare	= mtk_afe_fe_prepare,
+	.trigger	= mtk_afe_fe_trigger,
+};
+EXPORT_SYMBOL_GPL(mtk_afe_fe_ops);
+
+static DEFINE_MUTEX(irqs_lock);
+int mtk_dynamic_irq_acquire(struct mtk_base_afe *afe)
+{
+	int i;
+
+	mutex_lock(&afe->irq_alloc_lock);
+	for (i = 0; i < afe->irqs_size; ++i) {
+		if (afe->irqs[i].irq_occupyed == 0) {
+			afe->irqs[i].irq_occupyed = 1;
+			mutex_unlock(&afe->irq_alloc_lock);
+			return i;
+		}
+	}
+	mutex_unlock(&afe->irq_alloc_lock);
+	return afe->irqs_size;
+}
+EXPORT_SYMBOL_GPL(mtk_dynamic_irq_acquire);
+
+int mtk_dynamic_irq_release(struct mtk_base_afe *afe, int irq_id)
+{
+	mutex_lock(&afe->irq_alloc_lock);
+	if (irq_id >= 0 && irq_id < afe->irqs_size) {
+		afe->irqs[irq_id].irq_occupyed = 0;
+		mutex_unlock(&afe->irq_alloc_lock);
+		return 0;
+	}
+	mutex_unlock(&afe->irq_alloc_lock);
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(mtk_dynamic_irq_release);
+
+int mtk_afe_dai_suspend(struct snd_soc_dai *dai)
+{
+	struct mtk_base_afe *afe = dev_get_drvdata(dai->dev);
+	struct device *dev = afe->dev;
+	struct regmap *regmap = afe->regmap;
+	int i;
+
+	if (pm_runtime_status_suspended(dev) || afe->suspended)
+		return 0;
+
+	if (!afe->reg_back_up)
+		afe->reg_back_up =
+			devm_kcalloc(dev, afe->reg_back_up_list_num,
+				     sizeof(unsigned int), GFP_KERNEL);
+
+	for (i = 0; i < afe->reg_back_up_list_num; i++)
+		regmap_read(regmap, afe->reg_back_up_list[i],
+			    &afe->reg_back_up[i]);
+
+	afe->suspended = true;
+	afe->runtime_suspend(dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mtk_afe_dai_suspend);
+
+int mtk_afe_dai_resume(struct snd_soc_dai *dai)
+{
+	struct mtk_base_afe *afe = dev_get_drvdata(dai->dev);
+	struct device *dev = afe->dev;
+	struct regmap *regmap = afe->regmap;
+	int i = 0;
+
+	if (pm_runtime_status_suspended(dev) || !afe->suspended)
+		return 0;
+
+	afe->runtime_resume(dev);
+
+	if (!afe->reg_back_up)
+		dev_dbg(dev, "%s no reg_backup\n", __func__);
+
+	for (i = 0; i < afe->reg_back_up_list_num; i++)
+		mtk_regmap_write(regmap, afe->reg_back_up_list[i],
+				 afe->reg_back_up[i]);
+
+	afe->suspended = false;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mtk_afe_dai_resume);
+
+MODULE_DESCRIPTION("Mediatek simple fe dai operator");
+MODULE_AUTHOR("Garlic Tseng <garlic.tseng@mediatek.com>");
+MODULE_LICENSE("GPL v2");
+
diff --git a/sound/soc/mediatek/common/mtk-afe-fe-dai.h b/sound/soc/mediatek/common/mtk-afe-fe-dai.h
new file mode 100644
index 000000000000..28cb17854da1
--- /dev/null
+++ b/sound/soc/mediatek/common/mtk-afe-fe-dai.h
@@ -0,0 +1,45 @@
+/*
+ * mtk-afe-fe-dais.h  --  Mediatek afe fe dai operator definition
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Garlic Tseng <garlic.tseng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _MTK_AFE_FE_DAI_H_
+#define _MTK_AFE_FE_DAI_H_
+
+struct snd_soc_dai_ops;
+struct mtk_base_afe;
+struct mtk_base_afe_memif;
+
+int mtk_afe_fe_startup(struct snd_pcm_substream *substream,
+		       struct snd_soc_dai *dai);
+void mtk_afe_fe_shutdown(struct snd_pcm_substream *substream,
+			 struct snd_soc_dai *dai);
+int mtk_afe_fe_hw_params(struct snd_pcm_substream *substream,
+			 struct snd_pcm_hw_params *params,
+			 struct snd_soc_dai *dai);
+int mtk_afe_fe_hw_free(struct snd_pcm_substream *substream,
+		       struct snd_soc_dai *dai);
+int mtk_afe_fe_prepare(struct snd_pcm_substream *substream,
+		       struct snd_soc_dai *dai);
+int mtk_afe_fe_trigger(struct snd_pcm_substream *substream, int cmd,
+		       struct snd_soc_dai *dai);
+
+extern const struct snd_soc_dai_ops mtk_afe_fe_ops;
+
+int mtk_dynamic_irq_acquire(struct mtk_base_afe *afe);
+int mtk_dynamic_irq_release(struct mtk_base_afe *afe, int irq_id);
+int mtk_afe_dai_suspend(struct snd_soc_dai *dai);
+int mtk_afe_dai_resume(struct snd_soc_dai *dai);
+
+#endif
diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.c b/sound/soc/mediatek/common/mtk-afe-platform-driver.c
new file mode 100644
index 000000000000..82d439c15f4e
--- /dev/null
+++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.c
@@ -0,0 +1,90 @@
+/*
+ * mtk-afe-platform-driver.c  --  Mediatek afe platform driver
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Garlic Tseng <garlic.tseng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+#include <sound/soc.h>
+
+#include "mtk-afe-platform-driver.h"
+#include "mtk-base-afe.h"
+
+static snd_pcm_uframes_t mtk_afe_pcm_pointer
+			 (struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
+	const struct mtk_base_memif_data *memif_data = memif->data;
+	struct regmap *regmap = afe->regmap;
+	struct device *dev = afe->dev;
+	int reg_ofs_base = memif_data->reg_ofs_base;
+	int reg_ofs_cur = memif_data->reg_ofs_cur;
+	unsigned int hw_ptr = 0, hw_base = 0;
+	int ret, pcm_ptr_bytes;
+
+	ret = regmap_read(regmap, reg_ofs_cur, &hw_ptr);
+	if (ret || hw_ptr == 0) {
+		dev_err(dev, "%s hw_ptr err\n", __func__);
+		pcm_ptr_bytes = 0;
+		goto POINTER_RETURN_FRAMES;
+	}
+
+	ret = regmap_read(regmap, reg_ofs_base, &hw_base);
+	if (ret || hw_base == 0) {
+		dev_err(dev, "%s hw_ptr err\n", __func__);
+		pcm_ptr_bytes = 0;
+		goto POINTER_RETURN_FRAMES;
+	}
+
+	pcm_ptr_bytes = hw_ptr - hw_base;
+
+POINTER_RETURN_FRAMES:
+	return bytes_to_frames(substream->runtime, pcm_ptr_bytes);
+}
+
+static const struct snd_pcm_ops mtk_afe_pcm_ops = {
+	.ioctl = snd_pcm_lib_ioctl,
+	.pointer = mtk_afe_pcm_pointer,
+};
+
+static int mtk_afe_pcm_new(struct snd_soc_pcm_runtime *rtd)
+{
+	size_t size;
+	struct snd_card *card = rtd->card->snd_card;
+	struct snd_pcm *pcm = rtd->pcm;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+
+	size = afe->mtk_afe_hardware->buffer_bytes_max;
+	return snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
+						     card->dev, size, size);
+}
+
+static void mtk_afe_pcm_free(struct snd_pcm *pcm)
+{
+	snd_pcm_lib_preallocate_free_for_all(pcm);
+}
+
+const struct snd_soc_platform_driver mtk_afe_pcm_platform = {
+	.ops = &mtk_afe_pcm_ops,
+	.pcm_new = mtk_afe_pcm_new,
+	.pcm_free = mtk_afe_pcm_free,
+};
+EXPORT_SYMBOL_GPL(mtk_afe_pcm_platform);
+
+MODULE_DESCRIPTION("Mediatek simple platform driver");
+MODULE_AUTHOR("Garlic Tseng <garlic.tseng@mediatek.com>");
+MODULE_LICENSE("GPL v2");
+
diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.h b/sound/soc/mediatek/common/mtk-afe-platform-driver.h
new file mode 100644
index 000000000000..a973fc9253b4
--- /dev/null
+++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.h
@@ -0,0 +1,23 @@
+/*
+ * mtk-afe-platform-driver.h  --  Mediatek afe platform driver definition
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Garlic Tseng <garlic.tseng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _MTK_AFE_PLATFORM_DRIVER_H_
+#define _MTK_AFE_PLATFORM_DRIVER_H_
+
+extern const struct snd_soc_platform_driver mtk_afe_pcm_platform;
+
+#endif
+
diff --git a/sound/soc/mediatek/common/mtk-base-afe.h b/sound/soc/mediatek/common/mtk-base-afe.h
new file mode 100644
index 000000000000..3a78f6f17195
--- /dev/null
+++ b/sound/soc/mediatek/common/mtk-base-afe.h
@@ -0,0 +1,104 @@
+/*
+ * mtk-base-afe.h  --  Mediatek base afe structure
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Garlic Tseng <garlic.tseng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _MTK_BASE_AFE_H_
+#define _MTK_BASE_AFE_H_
+
+struct mtk_base_memif_data {
+	int id;
+	const char *name;
+	int reg_ofs_base;
+	int reg_ofs_cur;
+	int fs_reg;
+	int fs_shift;
+	int fs_maskbit;
+	int mono_reg;
+	int mono_shift;
+	int enable_reg;
+	int enable_shift;
+	int hd_reg;
+	int hd_shift;
+	int msb_reg;
+	int msb_shift;
+	int agent_disable_reg;
+	int agent_disable_shift;
+};
+
+struct mtk_base_irq_data {
+	int id;
+	int irq_cnt_reg;
+	int irq_cnt_shift;
+	int irq_cnt_maskbit;
+	int irq_fs_reg;
+	int irq_fs_shift;
+	int irq_fs_maskbit;
+	int irq_en_reg;
+	int irq_en_shift;
+	int irq_clr_reg;
+	int irq_clr_shift;
+};
+
+struct device;
+struct mtk_base_afe_memif;
+struct mtk_base_afe_irq;
+struct regmap;
+struct snd_pcm_substream;
+struct snd_soc_dai;
+
+struct mtk_base_afe {
+	void __iomem *base_addr;
+	struct device *dev;
+	struct regmap *regmap;
+	struct mutex irq_alloc_lock; /* dynamic alloc irq lock */
+
+	unsigned int const *reg_back_up_list;
+	unsigned int *reg_back_up;
+	unsigned int reg_back_up_list_num;
+
+	int (*runtime_suspend)(struct device *dev);
+	int (*runtime_resume)(struct device *dev);
+	bool suspended;
+
+	struct mtk_base_afe_memif *memif;
+	int memif_size;
+	struct mtk_base_afe_irq *irqs;
+	int irqs_size;
+
+	const struct snd_pcm_hardware *mtk_afe_hardware;
+	int (*memif_fs)(struct snd_pcm_substream *substream,
+			unsigned int rate);
+	int (*irq_fs)(struct snd_pcm_substream *substream,
+		      unsigned int rate);
+
+	void *platform_priv;
+};
+
+struct mtk_base_afe_memif {
+	unsigned int phys_buf_addr;
+	int buffer_size;
+	struct snd_pcm_substream *substream;
+	const struct mtk_base_memif_data *data;
+	int irq_usage;
+	int const_irq;
+};
+
+struct mtk_base_afe_irq {
+	const struct mtk_base_irq_data *irq_data;
+	int irq_occupyed;
+};
+
+#endif
+
diff --git a/sound/soc/mediatek/mt2701/Makefile b/sound/soc/mediatek/mt2701/Makefile
new file mode 100644
index 000000000000..31c3d04d4942
--- /dev/null
+++ b/sound/soc/mediatek/mt2701/Makefile
@@ -0,0 +1,19 @@
+#
+# Copyright (C) 2015 MediaTek Inc.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+
+# platform driver
+snd-soc-mt2701-afe-objs := mt2701-afe-pcm.o mt2701-afe-clock-ctrl.o
+obj-$(CONFIG_SND_SOC_MT2701) += snd-soc-mt2701-afe.o
+
+# machine driver
+obj-$(CONFIG_SND_SOC_MT2701_CS42448) += mt2701-cs42448.o
diff --git a/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.c b/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.c
new file mode 100644
index 000000000000..b815ecc6bbf6
--- /dev/null
+++ b/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.c
@@ -0,0 +1,464 @@
+/*
+ * mt2701-afe-clock-ctrl.c  --  Mediatek 2701 afe clock ctrl
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Garlic Tseng <garlic.tseng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <sound/soc.h>
+#include <linux/regmap.h>
+#include <linux/pm_runtime.h>
+
+#include "mt2701-afe-common.h"
+#include "mt2701-afe-clock-ctrl.h"
+
+static const char *aud_clks[MT2701_CLOCK_NUM] = {
+	[MT2701_AUD_INFRA_SYS_AUDIO] = "infra_sys_audio_clk",
+	[MT2701_AUD_AUD_MUX1_SEL] = "top_audio_mux1_sel",
+	[MT2701_AUD_AUD_MUX2_SEL] = "top_audio_mux2_sel",
+	[MT2701_AUD_AUD_MUX1_DIV] = "top_audio_mux1_div",
+	[MT2701_AUD_AUD_MUX2_DIV] = "top_audio_mux2_div",
+	[MT2701_AUD_AUD_48K_TIMING] = "top_audio_48k_timing",
+	[MT2701_AUD_AUD_44K_TIMING] = "top_audio_44k_timing",
+	[MT2701_AUD_AUDPLL_MUX_SEL] = "top_audpll_mux_sel",
+	[MT2701_AUD_APLL_SEL] = "top_apll_sel",
+	[MT2701_AUD_AUD1PLL_98M] = "top_aud1_pll_98M",
+	[MT2701_AUD_AUD2PLL_90M] = "top_aud2_pll_90M",
+	[MT2701_AUD_HADDS2PLL_98M] = "top_hadds2_pll_98M",
+	[MT2701_AUD_HADDS2PLL_294M] = "top_hadds2_pll_294M",
+	[MT2701_AUD_AUDPLL] = "top_audpll",
+	[MT2701_AUD_AUDPLL_D4] = "top_audpll_d4",
+	[MT2701_AUD_AUDPLL_D8] = "top_audpll_d8",
+	[MT2701_AUD_AUDPLL_D16] = "top_audpll_d16",
+	[MT2701_AUD_AUDPLL_D24] = "top_audpll_d24",
+	[MT2701_AUD_AUDINTBUS] = "top_audintbus_sel",
+	[MT2701_AUD_CLK_26M] = "clk_26m",
+	[MT2701_AUD_SYSPLL1_D4] = "top_syspll1_d4",
+	[MT2701_AUD_AUD_K1_SRC_SEL] = "top_aud_k1_src_sel",
+	[MT2701_AUD_AUD_K2_SRC_SEL] = "top_aud_k2_src_sel",
+	[MT2701_AUD_AUD_K3_SRC_SEL] = "top_aud_k3_src_sel",
+	[MT2701_AUD_AUD_K4_SRC_SEL] = "top_aud_k4_src_sel",
+	[MT2701_AUD_AUD_K5_SRC_SEL] = "top_aud_k5_src_sel",
+	[MT2701_AUD_AUD_K6_SRC_SEL] = "top_aud_k6_src_sel",
+	[MT2701_AUD_AUD_K1_SRC_DIV] = "top_aud_k1_src_div",
+	[MT2701_AUD_AUD_K2_SRC_DIV] = "top_aud_k2_src_div",
+	[MT2701_AUD_AUD_K3_SRC_DIV] = "top_aud_k3_src_div",
+	[MT2701_AUD_AUD_K4_SRC_DIV] = "top_aud_k4_src_div",
+	[MT2701_AUD_AUD_K5_SRC_DIV] = "top_aud_k5_src_div",
+	[MT2701_AUD_AUD_K6_SRC_DIV] = "top_aud_k6_src_div",
+	[MT2701_AUD_AUD_I2S1_MCLK] = "top_aud_i2s1_mclk",
+	[MT2701_AUD_AUD_I2S2_MCLK] = "top_aud_i2s2_mclk",
+	[MT2701_AUD_AUD_I2S3_MCLK] = "top_aud_i2s3_mclk",
+	[MT2701_AUD_AUD_I2S4_MCLK] = "top_aud_i2s4_mclk",
+	[MT2701_AUD_AUD_I2S5_MCLK] = "top_aud_i2s5_mclk",
+	[MT2701_AUD_AUD_I2S6_MCLK] = "top_aud_i2s6_mclk",
+	[MT2701_AUD_ASM_M_SEL] = "top_asm_m_sel",
+	[MT2701_AUD_ASM_H_SEL] = "top_asm_h_sel",
+	[MT2701_AUD_UNIVPLL2_D4] = "top_univpll2_d4",
+	[MT2701_AUD_UNIVPLL2_D2] = "top_univpll2_d2",
+	[MT2701_AUD_SYSPLL_D5] = "top_syspll_d5",
+};
+
+int mt2701_init_clock(struct mtk_base_afe *afe)
+{
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int i = 0;
+
+	for (i = 0; i < MT2701_CLOCK_NUM; i++) {
+		afe_priv->clocks[i] = devm_clk_get(afe->dev, aud_clks[i]);
+		if (IS_ERR(aud_clks[i])) {
+			dev_warn(afe->dev, "%s devm_clk_get %s fail\n",
+				 __func__, aud_clks[i]);
+			return PTR_ERR(aud_clks[i]);
+		}
+	}
+
+	return 0;
+}
+
+int mt2701_afe_enable_clock(struct mtk_base_afe *afe)
+{
+	int ret = 0;
+
+	ret = mt2701_turn_on_a1sys_clock(afe);
+	if (ret) {
+		dev_err(afe->dev, "%s turn_on_a1sys_clock fail %d\n",
+			__func__, ret);
+		return ret;
+	}
+
+	ret = mt2701_turn_on_a2sys_clock(afe);
+	if (ret) {
+		dev_err(afe->dev, "%s turn_on_a2sys_clock fail %d\n",
+			__func__, ret);
+		mt2701_turn_off_a1sys_clock(afe);
+		return ret;
+	}
+
+	ret = mt2701_turn_on_afe_clock(afe);
+	if (ret) {
+		dev_err(afe->dev, "%s turn_on_afe_clock fail %d\n",
+			__func__, ret);
+		mt2701_turn_off_a1sys_clock(afe);
+		mt2701_turn_off_a2sys_clock(afe);
+		return ret;
+	}
+
+	regmap_update_bits(afe->regmap, ASYS_TOP_CON,
+			   AUDIO_TOP_CON0_A1SYS_A2SYS_ON,
+			   AUDIO_TOP_CON0_A1SYS_A2SYS_ON);
+	regmap_update_bits(afe->regmap, AFE_DAC_CON0,
+			   AFE_DAC_CON0_AFE_ON,
+			   AFE_DAC_CON0_AFE_ON);
+	regmap_write(afe->regmap, PWR2_TOP_CON,
+		     PWR2_TOP_CON_INIT_VAL);
+	regmap_write(afe->regmap, PWR1_ASM_CON1,
+		     PWR1_ASM_CON1_INIT_VAL);
+	regmap_write(afe->regmap, PWR2_ASM_CON1,
+		     PWR2_ASM_CON1_INIT_VAL);
+
+	return 0;
+}
+
+void mt2701_afe_disable_clock(struct mtk_base_afe *afe)
+{
+	mt2701_turn_off_afe_clock(afe);
+	mt2701_turn_off_a1sys_clock(afe);
+	mt2701_turn_off_a2sys_clock(afe);
+	regmap_update_bits(afe->regmap, ASYS_TOP_CON,
+			   AUDIO_TOP_CON0_A1SYS_A2SYS_ON, 0);
+	regmap_update_bits(afe->regmap, AFE_DAC_CON0,
+			   AFE_DAC_CON0_AFE_ON, 0);
+}
+
+int mt2701_turn_on_a1sys_clock(struct mtk_base_afe *afe)
+{
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int ret = 0;
+
+	/* Set Mux */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_AUD_MUX1_SEL]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_AUD_MUX1_SEL], ret);
+		goto A1SYS_CLK_AUD_MUX1_SEL_ERR;
+	}
+
+	ret = clk_set_parent(afe_priv->clocks[MT2701_AUD_AUD_MUX1_SEL],
+			     afe_priv->clocks[MT2701_AUD_AUD1PLL_98M]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_set_parent %s-%s fail %d\n", __func__,
+			aud_clks[MT2701_AUD_AUD_MUX1_SEL],
+			aud_clks[MT2701_AUD_AUD1PLL_98M], ret);
+		goto A1SYS_CLK_AUD_MUX1_SEL_ERR;
+	}
+
+	/* Set Divider */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_AUD_MUX1_DIV]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__,
+			aud_clks[MT2701_AUD_AUD_MUX1_DIV],
+			ret);
+		goto A1SYS_CLK_AUD_MUX1_DIV_ERR;
+	}
+
+	ret = clk_set_rate(afe_priv->clocks[MT2701_AUD_AUD_MUX1_DIV],
+			   MT2701_AUD_AUD_MUX1_DIV_RATE);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_set_parent %s-%d fail %d\n", __func__,
+			aud_clks[MT2701_AUD_AUD_MUX1_DIV],
+			MT2701_AUD_AUD_MUX1_DIV_RATE, ret);
+		goto A1SYS_CLK_AUD_MUX1_DIV_ERR;
+	}
+
+	/* Enable clock gate */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_AUD_48K_TIMING]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_AUD_48K_TIMING], ret);
+		goto A1SYS_CLK_AUD_48K_ERR;
+	}
+
+	/* Enable infra audio */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_INFRA_SYS_AUDIO]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_INFRA_SYS_AUDIO], ret);
+		goto A1SYS_CLK_INFRA_ERR;
+	}
+
+	return 0;
+
+A1SYS_CLK_INFRA_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_INFRA_SYS_AUDIO]);
+A1SYS_CLK_AUD_48K_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_48K_TIMING]);
+A1SYS_CLK_AUD_MUX1_DIV_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_MUX1_DIV]);
+A1SYS_CLK_AUD_MUX1_SEL_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_MUX1_SEL]);
+
+	return ret;
+}
+
+void mt2701_turn_off_a1sys_clock(struct mtk_base_afe *afe)
+{
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_INFRA_SYS_AUDIO]);
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_48K_TIMING]);
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_MUX1_DIV]);
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_MUX1_SEL]);
+}
+
+int mt2701_turn_on_a2sys_clock(struct mtk_base_afe *afe)
+{
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int ret = 0;
+
+	/* Set Mux */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_AUD_MUX2_SEL]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_AUD_MUX2_SEL], ret);
+		goto A2SYS_CLK_AUD_MUX2_SEL_ERR;
+	}
+
+	ret = clk_set_parent(afe_priv->clocks[MT2701_AUD_AUD_MUX2_SEL],
+			     afe_priv->clocks[MT2701_AUD_AUD2PLL_90M]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_set_parent %s-%s fail %d\n", __func__,
+			aud_clks[MT2701_AUD_AUD_MUX2_SEL],
+			aud_clks[MT2701_AUD_AUD2PLL_90M], ret);
+		goto A2SYS_CLK_AUD_MUX2_SEL_ERR;
+	}
+
+	/* Set Divider */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_AUD_MUX2_DIV]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_AUD_MUX2_DIV], ret);
+		goto A2SYS_CLK_AUD_MUX2_DIV_ERR;
+	}
+
+	ret = clk_set_rate(afe_priv->clocks[MT2701_AUD_AUD_MUX2_DIV],
+			   MT2701_AUD_AUD_MUX2_DIV_RATE);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_set_parent %s-%d fail %d\n", __func__,
+			aud_clks[MT2701_AUD_AUD_MUX2_DIV],
+			MT2701_AUD_AUD_MUX2_DIV_RATE, ret);
+		goto A2SYS_CLK_AUD_MUX2_DIV_ERR;
+	}
+
+	/* Enable clock gate */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_AUD_44K_TIMING]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_AUD_44K_TIMING], ret);
+		goto A2SYS_CLK_AUD_44K_ERR;
+	}
+
+	/* Enable infra audio */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_INFRA_SYS_AUDIO]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_INFRA_SYS_AUDIO], ret);
+		goto A2SYS_CLK_INFRA_ERR;
+	}
+
+	return 0;
+
+A2SYS_CLK_INFRA_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_INFRA_SYS_AUDIO]);
+A2SYS_CLK_AUD_44K_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_44K_TIMING]);
+A2SYS_CLK_AUD_MUX2_DIV_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_MUX2_DIV]);
+A2SYS_CLK_AUD_MUX2_SEL_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_MUX2_SEL]);
+
+	return ret;
+}
+
+void mt2701_turn_off_a2sys_clock(struct mtk_base_afe *afe)
+{
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_INFRA_SYS_AUDIO]);
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_44K_TIMING]);
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_MUX2_DIV]);
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUD_MUX2_SEL]);
+}
+
+int mt2701_turn_on_afe_clock(struct mtk_base_afe *afe)
+{
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int ret;
+
+	/* enable INFRA_SYS */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_INFRA_SYS_AUDIO]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_INFRA_SYS_AUDIO], ret);
+		goto AFE_AUD_INFRA_ERR;
+	}
+
+	/* Set MT2701_AUD_AUDINTBUS to MT2701_AUD_SYSPLL1_D4 */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_AUDINTBUS]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_AUDINTBUS], ret);
+		goto AFE_AUD_AUDINTBUS_ERR;
+	}
+
+	ret = clk_set_parent(afe_priv->clocks[MT2701_AUD_AUDINTBUS],
+			     afe_priv->clocks[MT2701_AUD_SYSPLL1_D4]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_set_parent %s-%s fail %d\n", __func__,
+			aud_clks[MT2701_AUD_AUDINTBUS],
+			aud_clks[MT2701_AUD_SYSPLL1_D4], ret);
+		goto AFE_AUD_AUDINTBUS_ERR;
+	}
+
+	/* Set MT2701_AUD_ASM_H_SEL to MT2701_AUD_UNIVPLL2_D2 */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_ASM_H_SEL]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_ASM_H_SEL], ret);
+		goto AFE_AUD_ASM_H_ERR;
+	}
+
+	ret = clk_set_parent(afe_priv->clocks[MT2701_AUD_ASM_H_SEL],
+			     afe_priv->clocks[MT2701_AUD_UNIVPLL2_D2]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_set_parent %s-%s fail %d\n", __func__,
+			aud_clks[MT2701_AUD_ASM_H_SEL],
+			aud_clks[MT2701_AUD_UNIVPLL2_D2], ret);
+		goto AFE_AUD_ASM_H_ERR;
+	}
+
+	/* Set MT2701_AUD_ASM_M_SEL to MT2701_AUD_UNIVPLL2_D4 */
+	ret = clk_prepare_enable(afe_priv->clocks[MT2701_AUD_ASM_M_SEL]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[MT2701_AUD_ASM_M_SEL], ret);
+		goto AFE_AUD_ASM_M_ERR;
+	}
+
+	ret = clk_set_parent(afe_priv->clocks[MT2701_AUD_ASM_M_SEL],
+			     afe_priv->clocks[MT2701_AUD_UNIVPLL2_D4]);
+	if (ret) {
+		dev_err(afe->dev, "%s clk_set_parent %s-%s fail %d\n", __func__,
+			aud_clks[MT2701_AUD_ASM_M_SEL],
+			aud_clks[MT2701_AUD_UNIVPLL2_D4], ret);
+		goto AFE_AUD_ASM_M_ERR;
+	}
+
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON0,
+			   AUDIO_TOP_CON0_PDN_AFE, 0);
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON0,
+			   AUDIO_TOP_CON0_PDN_APLL_CK, 0);
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON4,
+			   AUDIO_TOP_CON4_PDN_A1SYS, 0);
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON4,
+			   AUDIO_TOP_CON4_PDN_A2SYS, 0);
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON4,
+			   AUDIO_TOP_CON4_PDN_AFE_CONN, 0);
+
+	return 0;
+
+AFE_AUD_ASM_M_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_ASM_M_SEL]);
+AFE_AUD_ASM_H_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_ASM_H_SEL]);
+AFE_AUD_AUDINTBUS_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUDINTBUS]);
+AFE_AUD_INFRA_ERR:
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_INFRA_SYS_AUDIO]);
+
+	return ret;
+}
+
+void mt2701_turn_off_afe_clock(struct mtk_base_afe *afe)
+{
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_INFRA_SYS_AUDIO]);
+
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_AUDINTBUS]);
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_ASM_H_SEL]);
+	clk_disable_unprepare(afe_priv->clocks[MT2701_AUD_ASM_M_SEL]);
+
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON0,
+			   AUDIO_TOP_CON0_PDN_AFE, AUDIO_TOP_CON0_PDN_AFE);
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON0,
+			   AUDIO_TOP_CON0_PDN_APLL_CK,
+			   AUDIO_TOP_CON0_PDN_APLL_CK);
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON4,
+			   AUDIO_TOP_CON4_PDN_A1SYS,
+			   AUDIO_TOP_CON4_PDN_A1SYS);
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON4,
+			   AUDIO_TOP_CON4_PDN_A2SYS,
+			   AUDIO_TOP_CON4_PDN_A2SYS);
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON4,
+			   AUDIO_TOP_CON4_PDN_AFE_CONN,
+			   AUDIO_TOP_CON4_PDN_AFE_CONN);
+}
+
+void mt2701_mclk_configuration(struct mtk_base_afe *afe, int id, int domain,
+			       int mclk)
+{
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int ret;
+	int aud_src_div_id = MT2701_AUD_AUD_K1_SRC_DIV + id;
+	int aud_src_clk_id = MT2701_AUD_AUD_K1_SRC_SEL + id;
+
+	/* Set MCLK Kx_SRC_SEL(domain) */
+	ret = clk_prepare_enable(afe_priv->clocks[aud_src_clk_id]);
+	if (ret)
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[aud_src_clk_id], ret);
+
+	if (domain == 0) {
+		ret = clk_set_parent(afe_priv->clocks[aud_src_clk_id],
+				     afe_priv->clocks[MT2701_AUD_AUD_MUX1_SEL]);
+		if (ret)
+			dev_err(afe->dev, "%s clk_set_parent %s-%s fail %d\n",
+				__func__, aud_clks[aud_src_clk_id],
+				aud_clks[MT2701_AUD_AUD_MUX1_SEL], ret);
+	} else {
+		ret = clk_set_parent(afe_priv->clocks[aud_src_clk_id],
+				     afe_priv->clocks[MT2701_AUD_AUD_MUX2_SEL]);
+		if (ret)
+			dev_err(afe->dev, "%s clk_set_parent %s-%s fail %d\n",
+				__func__, aud_clks[aud_src_clk_id],
+				aud_clks[MT2701_AUD_AUD_MUX2_SEL], ret);
+	}
+	clk_disable_unprepare(afe_priv->clocks[aud_src_clk_id]);
+
+	/* Set MCLK Kx_SRC_DIV(divider) */
+	ret = clk_prepare_enable(afe_priv->clocks[aud_src_div_id]);
+	if (ret)
+		dev_err(afe->dev, "%s clk_prepare_enable %s fail %d\n",
+			__func__, aud_clks[aud_src_div_id], ret);
+
+	ret = clk_set_rate(afe_priv->clocks[aud_src_div_id], mclk);
+	if (ret)
+		dev_err(afe->dev, "%s clk_set_rate %s-%d fail %d\n", __func__,
+			aud_clks[aud_src_div_id], mclk, ret);
+	clk_disable_unprepare(afe_priv->clocks[aud_src_div_id]);
+}
+
+MODULE_DESCRIPTION("MT2701 afe clock control");
+MODULE_AUTHOR("Garlic Tseng <garlic.tseng@mediatek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.h b/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.h
new file mode 100644
index 000000000000..6497d570cf09
--- /dev/null
+++ b/sound/soc/mediatek/mt2701/mt2701-afe-clock-ctrl.h
@@ -0,0 +1,38 @@
+/*
+ * mt2701-afe-clock-ctrl.h  --  Mediatek 2701 afe clock ctrl definition
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Garlic Tseng <garlic.tseng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _MT2701_AFE_CLOCK_CTRL_H_
+#define _MT2701_AFE_CLOCK_CTRL_H_
+
+struct mtk_base_afe;
+
+int mt2701_init_clock(struct mtk_base_afe *afe);
+int mt2701_afe_enable_clock(struct mtk_base_afe *afe);
+void mt2701_afe_disable_clock(struct mtk_base_afe *afe);
+
+int mt2701_turn_on_a1sys_clock(struct mtk_base_afe *afe);
+void mt2701_turn_off_a1sys_clock(struct mtk_base_afe *afe);
+
+int mt2701_turn_on_a2sys_clock(struct mtk_base_afe *afe);
+void mt2701_turn_off_a2sys_clock(struct mtk_base_afe *afe);
+
+int mt2701_turn_on_afe_clock(struct mtk_base_afe *afe);
+void mt2701_turn_off_afe_clock(struct mtk_base_afe *afe);
+
+void mt2701_mclk_configuration(struct mtk_base_afe *afe, int id, int domain,
+			       int mclk);
+
+#endif
diff --git a/sound/soc/mediatek/mt2701/mt2701-afe-common.h b/sound/soc/mediatek/mt2701/mt2701-afe-common.h
new file mode 100644
index 000000000000..c19430e98adf
--- /dev/null
+++ b/sound/soc/mediatek/mt2701/mt2701-afe-common.h
@@ -0,0 +1,172 @@
+/*
+ * mt2701-afe-common.h  --  Mediatek 2701 audio driver definitions
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Garlic Tseng <garlic.tseng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _MT_2701_AFE_COMMON_H_
+#define _MT_2701_AFE_COMMON_H_
+#include <sound/soc.h>
+#include <linux/clk.h>
+#include <linux/regmap.h>
+#include "mt2701-reg.h"
+#include "../common/mtk-base-afe.h"
+
+#define MT2701_STREAM_DIR_NUM (SNDRV_PCM_STREAM_LAST + 1)
+#define MT2701_PLL_DOMAIN_0_RATE	98304000
+#define MT2701_PLL_DOMAIN_1_RATE	90316800
+#define MT2701_AUD_AUD_MUX1_DIV_RATE (MT2701_PLL_DOMAIN_0_RATE / 2)
+#define MT2701_AUD_AUD_MUX2_DIV_RATE (MT2701_PLL_DOMAIN_1_RATE / 2)
+
+enum {
+	MT2701_I2S_1,
+	MT2701_I2S_2,
+	MT2701_I2S_3,
+	MT2701_I2S_4,
+	MT2701_I2S_NUM,
+};
+
+enum {
+	MT2701_MEMIF_DL1,
+	MT2701_MEMIF_DL2,
+	MT2701_MEMIF_DL3,
+	MT2701_MEMIF_DL4,
+	MT2701_MEMIF_DL5,
+	MT2701_MEMIF_DL_SINGLE_NUM,
+	MT2701_MEMIF_DLM = MT2701_MEMIF_DL_SINGLE_NUM,
+	MT2701_MEMIF_UL1,
+	MT2701_MEMIF_UL2,
+	MT2701_MEMIF_UL3,
+	MT2701_MEMIF_UL4,
+	MT2701_MEMIF_UL5,
+	MT2701_MEMIF_DLBT,
+	MT2701_MEMIF_ULBT,
+	MT2701_MEMIF_NUM,
+	MT2701_IO_I2S = MT2701_MEMIF_NUM,
+	MT2701_IO_2ND_I2S,
+	MT2701_IO_3RD_I2S,
+	MT2701_IO_4TH_I2S,
+	MT2701_IO_5TH_I2S,
+	MT2701_IO_6TH_I2S,
+	MT2701_IO_MRG,
+};
+
+enum {
+	MT2701_IRQ_ASYS_START,
+	MT2701_IRQ_ASYS_IRQ1 = MT2701_IRQ_ASYS_START,
+	MT2701_IRQ_ASYS_IRQ2,
+	MT2701_IRQ_ASYS_IRQ3,
+	MT2701_IRQ_ASYS_END,
+};
+
+/* 2701 clock def */
+enum audio_system_clock_type {
+	MT2701_AUD_INFRA_SYS_AUDIO,
+	MT2701_AUD_AUD_MUX1_SEL,
+	MT2701_AUD_AUD_MUX2_SEL,
+	MT2701_AUD_AUD_MUX1_DIV,
+	MT2701_AUD_AUD_MUX2_DIV,
+	MT2701_AUD_AUD_48K_TIMING,
+	MT2701_AUD_AUD_44K_TIMING,
+	MT2701_AUD_AUDPLL_MUX_SEL,
+	MT2701_AUD_APLL_SEL,
+	MT2701_AUD_AUD1PLL_98M,
+	MT2701_AUD_AUD2PLL_90M,
+	MT2701_AUD_HADDS2PLL_98M,
+	MT2701_AUD_HADDS2PLL_294M,
+	MT2701_AUD_AUDPLL,
+	MT2701_AUD_AUDPLL_D4,
+	MT2701_AUD_AUDPLL_D8,
+	MT2701_AUD_AUDPLL_D16,
+	MT2701_AUD_AUDPLL_D24,
+	MT2701_AUD_AUDINTBUS,
+	MT2701_AUD_CLK_26M,
+	MT2701_AUD_SYSPLL1_D4,
+	MT2701_AUD_AUD_K1_SRC_SEL,
+	MT2701_AUD_AUD_K2_SRC_SEL,
+	MT2701_AUD_AUD_K3_SRC_SEL,
+	MT2701_AUD_AUD_K4_SRC_SEL,
+	MT2701_AUD_AUD_K5_SRC_SEL,
+	MT2701_AUD_AUD_K6_SRC_SEL,
+	MT2701_AUD_AUD_K1_SRC_DIV,
+	MT2701_AUD_AUD_K2_SRC_DIV,
+	MT2701_AUD_AUD_K3_SRC_DIV,
+	MT2701_AUD_AUD_K4_SRC_DIV,
+	MT2701_AUD_AUD_K5_SRC_DIV,
+	MT2701_AUD_AUD_K6_SRC_DIV,
+	MT2701_AUD_AUD_I2S1_MCLK,
+	MT2701_AUD_AUD_I2S2_MCLK,
+	MT2701_AUD_AUD_I2S3_MCLK,
+	MT2701_AUD_AUD_I2S4_MCLK,
+	MT2701_AUD_AUD_I2S5_MCLK,
+	MT2701_AUD_AUD_I2S6_MCLK,
+	MT2701_AUD_ASM_M_SEL,
+	MT2701_AUD_ASM_H_SEL,
+	MT2701_AUD_UNIVPLL2_D4,
+	MT2701_AUD_UNIVPLL2_D2,
+	MT2701_AUD_SYSPLL_D5,
+	MT2701_CLOCK_NUM
+};
+
+static const unsigned int mt2701_afe_backup_list[] = {
+	AUDIO_TOP_CON0,
+	AUDIO_TOP_CON4,
+	AUDIO_TOP_CON5,
+	ASYS_TOP_CON,
+	AFE_CONN0,
+	AFE_CONN1,
+	AFE_CONN2,
+	AFE_CONN3,
+	AFE_CONN15,
+	AFE_CONN16,
+	AFE_CONN17,
+	AFE_CONN18,
+	AFE_CONN19,
+	AFE_CONN20,
+	AFE_CONN21,
+	AFE_CONN22,
+	AFE_DAC_CON0,
+	AFE_MEMIF_PBUF_SIZE,
+};
+
+struct snd_pcm_substream;
+struct mtk_base_irq_data;
+
+struct mt2701_i2s_data {
+	int i2s_ctrl_reg;
+	int i2s_pwn_shift;
+	int i2s_asrc_fs_shift;
+	int i2s_asrc_fs_mask;
+};
+
+enum mt2701_i2s_dir {
+	I2S_OUT,
+	I2S_IN,
+	I2S_DIR_NUM,
+};
+
+struct mt2701_i2s_path {
+	int dai_id;
+	int mclk_rate;
+	int on[I2S_DIR_NUM];
+	int occupied[I2S_DIR_NUM];
+	const struct mt2701_i2s_data *i2s_data[2];
+};
+
+struct mt2701_afe_private {
+	struct clk *clocks[MT2701_CLOCK_NUM];
+	struct mt2701_i2s_path i2s_path[MT2701_I2S_NUM];
+	bool mrg_enable[MT2701_STREAM_DIR_NUM];
+};
+
+#endif
diff --git a/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c b/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c
new file mode 100644
index 000000000000..34a6123480d3
--- /dev/null
+++ b/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c
@@ -0,0 +1,1656 @@
+/*
+ * Mediatek ALSA SoC AFE platform driver for 2701
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Garlic Tseng <garlic.tseng@mediatek.com>
+ *             Ir Lian <ir.lian@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/pm_runtime.h>
+#include <sound/soc.h>
+
+#include "mt2701-afe-common.h"
+
+#include "mt2701-afe-clock-ctrl.h"
+#include "../common/mtk-afe-platform-driver.h"
+#include "../common/mtk-afe-fe-dai.h"
+
+#define AFE_IRQ_STATUS_BITS	0xff
+
+static const struct snd_pcm_hardware mt2701_afe_hardware = {
+	.info = SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_INTERLEAVED
+		| SNDRV_PCM_INFO_RESUME | SNDRV_PCM_INFO_MMAP_VALID,
+	.formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE
+		   | SNDRV_PCM_FMTBIT_S32_LE,
+	.period_bytes_min = 1024,
+	.period_bytes_max = 1024 * 256,
+	.periods_min = 4,
+	.periods_max = 1024,
+	.buffer_bytes_max = 1024 * 1024 * 16,
+	.fifo_size = 0,
+};
+
+struct mt2701_afe_rate {
+	unsigned int rate;
+	unsigned int regvalue;
+};
+
+static const struct mt2701_afe_rate mt2701_afe_i2s_rates[] = {
+	{ .rate = 8000, .regvalue = 0 },
+	{ .rate = 12000, .regvalue = 1 },
+	{ .rate = 16000, .regvalue = 2 },
+	{ .rate = 24000, .regvalue = 3 },
+	{ .rate = 32000, .regvalue = 4 },
+	{ .rate = 48000, .regvalue = 5 },
+	{ .rate = 96000, .regvalue = 6 },
+	{ .rate = 192000, .regvalue = 7 },
+	{ .rate = 384000, .regvalue = 8 },
+	{ .rate = 7350, .regvalue = 16 },
+	{ .rate = 11025, .regvalue = 17 },
+	{ .rate = 14700, .regvalue = 18 },
+	{ .rate = 22050, .regvalue = 19 },
+	{ .rate = 29400, .regvalue = 20 },
+	{ .rate = 44100, .regvalue = 21 },
+	{ .rate = 88200, .regvalue = 22 },
+	{ .rate = 176400, .regvalue = 23 },
+	{ .rate = 352800, .regvalue = 24 },
+};
+
+static int mt2701_dai_num_to_i2s(struct mtk_base_afe *afe, int num)
+{
+	int val = num - MT2701_IO_I2S;
+
+	if (val < 0 || val >= MT2701_I2S_NUM) {
+		dev_err(afe->dev, "%s, num not available, num %d, val %d\n",
+			__func__, num, val);
+		return -EINVAL;
+	}
+	return val;
+}
+
+static int mt2701_afe_i2s_fs(unsigned int sample_rate)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mt2701_afe_i2s_rates); i++)
+		if (mt2701_afe_i2s_rates[i].rate == sample_rate)
+			return mt2701_afe_i2s_rates[i].regvalue;
+
+	return -EINVAL;
+}
+
+static int mt2701_afe_i2s_startup(struct snd_pcm_substream *substream,
+				  struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
+	int clk_num = MT2701_AUD_AUD_I2S1_MCLK + i2s_num;
+	int ret = 0;
+
+	if (i2s_num < 0)
+		return i2s_num;
+
+	/* enable mclk */
+	ret = clk_prepare_enable(afe_priv->clocks[clk_num]);
+	if (ret)
+		dev_err(afe->dev, "Failed to enable mclk for I2S: %d\n",
+			i2s_num);
+
+	return ret;
+}
+
+static int mt2701_afe_i2s_path_shutdown(struct snd_pcm_substream *substream,
+					struct snd_soc_dai *dai,
+					int dir_invert)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
+	struct mt2701_i2s_path *i2s_path;
+	const struct mt2701_i2s_data *i2s_data;
+	int stream_dir = substream->stream;
+
+	if (i2s_num < 0)
+		return i2s_num;
+
+	i2s_path = &afe_priv->i2s_path[i2s_num];
+
+	if (dir_invert)	{
+		if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK)
+			stream_dir = SNDRV_PCM_STREAM_CAPTURE;
+		else
+			stream_dir = SNDRV_PCM_STREAM_PLAYBACK;
+	}
+	i2s_data = i2s_path->i2s_data[stream_dir];
+
+	i2s_path->on[stream_dir]--;
+	if (i2s_path->on[stream_dir] < 0) {
+		dev_warn(afe->dev, "i2s_path->on: %d, dir: %d\n",
+			 i2s_path->on[stream_dir], stream_dir);
+		i2s_path->on[stream_dir] = 0;
+	}
+	if (i2s_path->on[stream_dir])
+		return 0;
+
+	/* disable i2s */
+	regmap_update_bits(afe->regmap, i2s_data->i2s_ctrl_reg,
+			   ASYS_I2S_CON_I2S_EN, 0);
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON4,
+			   1 << i2s_data->i2s_pwn_shift,
+			   1 << i2s_data->i2s_pwn_shift);
+	return 0;
+}
+
+static void mt2701_afe_i2s_shutdown(struct snd_pcm_substream *substream,
+				    struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
+	struct mt2701_i2s_path *i2s_path;
+	int clk_num = MT2701_AUD_AUD_I2S1_MCLK + i2s_num;
+
+	if (i2s_num < 0)
+		return;
+
+	i2s_path = &afe_priv->i2s_path[i2s_num];
+
+	if (i2s_path->occupied[substream->stream])
+		i2s_path->occupied[substream->stream] = 0;
+	else
+		goto I2S_UNSTART;
+
+	mt2701_afe_i2s_path_shutdown(substream, dai, 0);
+
+	/* need to disable i2s-out path when disable i2s-in */
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
+		mt2701_afe_i2s_path_shutdown(substream, dai, 1);
+
+I2S_UNSTART:
+	/* disable mclk */
+	clk_disable_unprepare(afe_priv->clocks[clk_num]);
+}
+
+static int mt2701_i2s_path_prepare_enable(struct snd_pcm_substream *substream,
+					  struct snd_soc_dai *dai,
+					  int dir_invert)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
+	struct mt2701_i2s_path *i2s_path;
+	const struct mt2701_i2s_data *i2s_data;
+	struct snd_pcm_runtime * const runtime = substream->runtime;
+	int reg, fs, w_len = 1; /* now we support bck 64bits only */
+	int stream_dir = substream->stream;
+	unsigned int mask = 0, val = 0;
+
+	if (i2s_num < 0)
+		return i2s_num;
+
+	i2s_path = &afe_priv->i2s_path[i2s_num];
+
+	if (dir_invert) {
+		if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK)
+			stream_dir = SNDRV_PCM_STREAM_CAPTURE;
+		else
+			stream_dir = SNDRV_PCM_STREAM_PLAYBACK;
+	}
+	i2s_data = i2s_path->i2s_data[stream_dir];
+
+	/* no need to enable if already done */
+	i2s_path->on[stream_dir]++;
+
+	if (i2s_path->on[stream_dir] != 1)
+		return 0;
+
+	fs = mt2701_afe_i2s_fs(runtime->rate);
+
+	mask = ASYS_I2S_CON_FS |
+	       ASYS_I2S_CON_I2S_COUPLE_MODE | /* 0 */
+	       ASYS_I2S_CON_I2S_MODE |
+	       ASYS_I2S_CON_WIDE_MODE;
+
+	val = ASYS_I2S_CON_FS_SET(fs) |
+	      ASYS_I2S_CON_I2S_MODE |
+	      ASYS_I2S_CON_WIDE_MODE_SET(w_len);
+
+	if (stream_dir == SNDRV_PCM_STREAM_CAPTURE) {
+		mask |= ASYS_I2S_IN_PHASE_FIX;
+		val |= ASYS_I2S_IN_PHASE_FIX;
+	}
+
+	regmap_update_bits(afe->regmap, i2s_data->i2s_ctrl_reg, mask, val);
+
+	if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK)
+		reg = ASMO_TIMING_CON1;
+	else
+		reg = ASMI_TIMING_CON1;
+
+	regmap_update_bits(afe->regmap, reg,
+			   i2s_data->i2s_asrc_fs_mask
+			   << i2s_data->i2s_asrc_fs_shift,
+			   fs << i2s_data->i2s_asrc_fs_shift);
+
+	/* enable i2s */
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON4,
+			   1 << i2s_data->i2s_pwn_shift,
+			   0 << i2s_data->i2s_pwn_shift);
+
+	/* reset i2s hw status before enable */
+	regmap_update_bits(afe->regmap, i2s_data->i2s_ctrl_reg,
+			   ASYS_I2S_CON_RESET, ASYS_I2S_CON_RESET);
+	udelay(1);
+	regmap_update_bits(afe->regmap, i2s_data->i2s_ctrl_reg,
+			   ASYS_I2S_CON_RESET, 0);
+	udelay(1);
+	regmap_update_bits(afe->regmap, i2s_data->i2s_ctrl_reg,
+			   ASYS_I2S_CON_I2S_EN, ASYS_I2S_CON_I2S_EN);
+	return 0;
+}
+
+static int mt2701_afe_i2s_prepare(struct snd_pcm_substream *substream,
+				  struct snd_soc_dai *dai)
+{
+	int clk_domain;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
+	struct mt2701_i2s_path *i2s_path;
+	int mclk_rate;
+
+	if (i2s_num < 0)
+		return i2s_num;
+
+	i2s_path = &afe_priv->i2s_path[i2s_num];
+	mclk_rate = i2s_path->mclk_rate;
+
+	if (i2s_path->occupied[substream->stream])
+		return -EBUSY;
+	i2s_path->occupied[substream->stream] = 1;
+
+	if (MT2701_PLL_DOMAIN_0_RATE % mclk_rate == 0) {
+		clk_domain = 0;
+	} else if (MT2701_PLL_DOMAIN_1_RATE % mclk_rate == 0) {
+		clk_domain = 1;
+	} else {
+		dev_err(dai->dev, "%s() bad mclk rate %d\n",
+			__func__, mclk_rate);
+		return -EINVAL;
+	}
+	mt2701_mclk_configuration(afe, i2s_num, clk_domain, mclk_rate);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		mt2701_i2s_path_prepare_enable(substream, dai, 0);
+	} else {
+		/* need to enable i2s-out path when enable i2s-in */
+		/* prepare for another direction "out" */
+		mt2701_i2s_path_prepare_enable(substream, dai, 1);
+		/* prepare for "in" */
+		mt2701_i2s_path_prepare_enable(substream, dai, 0);
+	}
+
+	return 0;
+}
+
+static int mt2701_afe_i2s_set_sysclk(struct snd_soc_dai *dai, int clk_id,
+				     unsigned int freq, int dir)
+{
+	struct mtk_base_afe *afe = dev_get_drvdata(dai->dev);
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+	int i2s_num = mt2701_dai_num_to_i2s(afe, dai->id);
+
+	if (i2s_num < 0)
+		return i2s_num;
+
+	/* mclk */
+	if (dir == SND_SOC_CLOCK_IN) {
+		dev_warn(dai->dev,
+			 "%s() warning: mt2701 doesn't support mclk input\n",
+			__func__);
+		return -EINVAL;
+	}
+	afe_priv->i2s_path[i2s_num].mclk_rate = freq;
+	return 0;
+}
+
+static int mt2701_btmrg_startup(struct snd_pcm_substream *substream,
+				struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+
+	regmap_update_bits(afe->regmap, AUDIO_TOP_CON4,
+			   AUDIO_TOP_CON4_PDN_MRGIF, 0);
+
+	afe_priv->mrg_enable[substream->stream] = 1;
+	return 0;
+}
+
+static int mt2701_btmrg_hw_params(struct snd_pcm_substream *substream,
+				  struct snd_pcm_hw_params *params,
+				  struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	int stream_fs;
+	u32 val, msk;
+
+	stream_fs = params_rate(params);
+
+	if ((stream_fs != 8000) && (stream_fs != 16000)) {
+		dev_err(afe->dev, "%s() btmgr not supprt this stream_fs %d\n",
+			__func__, stream_fs);
+		return -EINVAL;
+	}
+
+	regmap_update_bits(afe->regmap, AFE_MRGIF_CON,
+			   AFE_MRGIF_CON_I2S_MODE_MASK,
+			   AFE_MRGIF_CON_I2S_MODE_32K);
+
+	val = AFE_DAIBT_CON0_BT_FUNC_EN | AFE_DAIBT_CON0_BT_FUNC_RDY
+	      | AFE_DAIBT_CON0_MRG_USE;
+	msk = val;
+
+	if (stream_fs == 16000)
+		val |= AFE_DAIBT_CON0_BT_WIDE_MODE_EN;
+
+	msk |= AFE_DAIBT_CON0_BT_WIDE_MODE_EN;
+
+	regmap_update_bits(afe->regmap, AFE_DAIBT_CON0, msk, val);
+
+	regmap_update_bits(afe->regmap, AFE_DAIBT_CON0,
+			   AFE_DAIBT_CON0_DAIBT_EN,
+			   AFE_DAIBT_CON0_DAIBT_EN);
+	regmap_update_bits(afe->regmap, AFE_MRGIF_CON,
+			   AFE_MRGIF_CON_MRG_I2S_EN,
+			   AFE_MRGIF_CON_MRG_I2S_EN);
+	regmap_update_bits(afe->regmap, AFE_MRGIF_CON,
+			   AFE_MRGIF_CON_MRG_EN,
+			   AFE_MRGIF_CON_MRG_EN);
+	return 0;
+}
+
+static void mt2701_btmrg_shutdown(struct snd_pcm_substream *substream,
+				  struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt2701_afe_private *afe_priv = afe->platform_priv;
+
+	/* if the other direction stream is not occupied */
+	if (!afe_priv->mrg_enable[!substream->stream]) {
+		regmap_update_bits(afe->regmap, AFE_DAIBT_CON0,
+				   AFE_DAIBT_CON0_DAIBT_EN, 0);
+		regmap_update_bits(afe->regmap, AFE_MRGIF_CON,
+				   AFE_MRGIF_CON_MRG_EN, 0);
+		regmap_update_bits(afe->regmap, AFE_MRGIF_CON,
+				   AFE_MRGIF_CON_MRG_I2S_EN, 0);
+		regmap_update_bits(afe->regmap, AUDIO_TOP_CON4,
+				   AUDIO_TOP_CON4_PDN_MRGIF,
+				   AUDIO_TOP_CON4_PDN_MRGIF);
+	}
+	afe_priv->mrg_enable[substream->stream] = 0;
+}
+
+static int mt2701_simple_fe_startup(struct snd_pcm_substream *substream,
+				    struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	int stream_dir = substream->stream;
+	int memif_num = rtd->cpu_dai->id;
+	struct mtk_base_afe_memif *memif_tmp;
+
+	/* can't run single DL & DLM at the same time */
+	if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK) {
+		memif_tmp = &afe->memif[MT2701_MEMIF_DLM];
+		if (memif_tmp->substream) {
+			dev_warn(afe->dev, "%s memif is not available, stream_dir %d, memif_num %d\n",
+				 __func__, stream_dir, memif_num);
+			return -EBUSY;
+		}
+	}
+	return mtk_afe_fe_startup(substream, dai);
+}
+
+static int mt2701_simple_fe_hw_params(struct snd_pcm_substream *substream,
+				      struct snd_pcm_hw_params *params,
+				      struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	int stream_dir = substream->stream;
+
+	/* single DL use PAIR_INTERLEAVE */
+	if (stream_dir == SNDRV_PCM_STREAM_PLAYBACK) {
+		regmap_update_bits(afe->regmap,
+				   AFE_MEMIF_PBUF_SIZE,
+				   AFE_MEMIF_PBUF_SIZE_DLM_MASK,
+				   AFE_MEMIF_PBUF_SIZE_PAIR_INTERLEAVE);
+	}
+	return mtk_afe_fe_hw_params(substream, params, dai);
+}
+
+static int mt2701_dlm_fe_startup(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe_memif *memif_tmp;
+	const struct mtk_base_memif_data *memif_data;
+	int i;
+
+	for (i = MT2701_MEMIF_DL1; i < MT2701_MEMIF_DL_SINGLE_NUM; ++i) {
+		memif_tmp = &afe->memif[i];
+		if (memif_tmp->substream)
+			return -EBUSY;
+	}
+
+	/* enable agent for all signal DL (due to hw design) */
+	for (i = MT2701_MEMIF_DL1; i < MT2701_MEMIF_DL_SINGLE_NUM; ++i) {
+		memif_data = afe->memif[i].data;
+		regmap_update_bits(afe->regmap,
+				   memif_data->agent_disable_reg,
+				   1 << memif_data->agent_disable_shift,
+				   0 << memif_data->agent_disable_shift);
+	}
+
+	return mtk_afe_fe_startup(substream, dai);
+}
+
+static void mt2701_dlm_fe_shutdown(struct snd_pcm_substream *substream,
+				   struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	const struct mtk_base_memif_data *memif_data;
+	int i;
+
+	for (i = MT2701_MEMIF_DL1; i < MT2701_MEMIF_DL_SINGLE_NUM; ++i) {
+		memif_data = afe->memif[i].data;
+		regmap_update_bits(afe->regmap,
+				   memif_data->agent_disable_reg,
+				   1 << memif_data->agent_disable_shift,
+				   1 << memif_data->agent_disable_shift);
+	}
+	return mtk_afe_fe_shutdown(substream, dai);
+}
+
+static int mt2701_dlm_fe_hw_params(struct snd_pcm_substream *substream,
+				   struct snd_pcm_hw_params *params,
+				   struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	int channels = params_channels(params);
+
+	regmap_update_bits(afe->regmap,
+			   AFE_MEMIF_PBUF_SIZE,
+			   AFE_MEMIF_PBUF_SIZE_DLM_MASK,
+			   AFE_MEMIF_PBUF_SIZE_FULL_INTERLEAVE);
+	regmap_update_bits(afe->regmap,
+			   AFE_MEMIF_PBUF_SIZE,
+			   AFE_MEMIF_PBUF_SIZE_DLM_BYTE_MASK,
+			   AFE_MEMIF_PBUF_SIZE_DLM_32BYTES);
+	regmap_update_bits(afe->regmap,
+			   AFE_MEMIF_PBUF_SIZE,
+			   AFE_MEMIF_PBUF_SIZE_DLM_CH_MASK,
+			   AFE_MEMIF_PBUF_SIZE_DLM_CH(channels));
+
+	return mtk_afe_fe_hw_params(substream, params, dai);
+}
+
+static int mt2701_dlm_fe_trigger(struct snd_pcm_substream *substream,
+				 int cmd, struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe_memif *memif_tmp = &afe->memif[MT2701_MEMIF_DL1];
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+		regmap_update_bits(afe->regmap, memif_tmp->data->enable_reg,
+				   1 << memif_tmp->data->enable_shift,
+				   1 << memif_tmp->data->enable_shift);
+		mtk_afe_fe_trigger(substream, cmd, dai);
+		return 0;
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+		mtk_afe_fe_trigger(substream, cmd, dai);
+		regmap_update_bits(afe->regmap, memif_tmp->data->enable_reg,
+				   1 << memif_tmp->data->enable_shift, 0);
+
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int mt2701_memif_fs(struct snd_pcm_substream *substream,
+			   unsigned int rate)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	int fs;
+
+	if (rtd->cpu_dai->id != MT2701_MEMIF_ULBT)
+		fs = mt2701_afe_i2s_fs(rate);
+	else
+		fs = (rate == 16000 ? 1 : 0);
+	return fs;
+}
+
+static int mt2701_irq_fs(struct snd_pcm_substream *substream, unsigned int rate)
+{
+	return mt2701_afe_i2s_fs(rate);
+}
+
+/* FE DAIs */
+static const struct snd_soc_dai_ops mt2701_single_memif_dai_ops = {
+	.startup	= mt2701_simple_fe_startup,
+	.shutdown	= mtk_afe_fe_shutdown,
+	.hw_params	= mt2701_simple_fe_hw_params,
+	.hw_free	= mtk_afe_fe_hw_free,
+	.prepare	= mtk_afe_fe_prepare,
+	.trigger	= mtk_afe_fe_trigger,
+
+};
+
+static const struct snd_soc_dai_ops mt2701_dlm_memif_dai_ops = {
+	.startup	= mt2701_dlm_fe_startup,
+	.shutdown	= mt2701_dlm_fe_shutdown,
+	.hw_params	= mt2701_dlm_fe_hw_params,
+	.hw_free	= mtk_afe_fe_hw_free,
+	.prepare	= mtk_afe_fe_prepare,
+	.trigger	= mt2701_dlm_fe_trigger,
+};
+
+/* I2S BE DAIs */
+static const struct snd_soc_dai_ops mt2701_afe_i2s_ops = {
+	.startup	= mt2701_afe_i2s_startup,
+	.shutdown	= mt2701_afe_i2s_shutdown,
+	.prepare	= mt2701_afe_i2s_prepare,
+	.set_sysclk	= mt2701_afe_i2s_set_sysclk,
+};
+
+/* MRG BE DAIs */
+static struct snd_soc_dai_ops mt2701_btmrg_ops = {
+	.startup = mt2701_btmrg_startup,
+	.shutdown = mt2701_btmrg_shutdown,
+	.hw_params = mt2701_btmrg_hw_params,
+};
+
+static struct snd_soc_dai_driver mt2701_afe_pcm_dais[] = {
+	/* FE DAIs: memory intefaces to CPU */
+	{
+		.name = "PCM_multi",
+		.id = MT2701_MEMIF_DLM,
+		.suspend = mtk_afe_dai_suspend,
+		.resume = mtk_afe_dai_resume,
+		.playback = {
+			.stream_name = "DLM",
+			.channels_min = 1,
+			.channels_max = 8,
+			.rates = SNDRV_PCM_RATE_8000_192000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+
+		},
+		.ops = &mt2701_dlm_memif_dai_ops,
+	},
+	{
+		.name = "PCM0",
+		.id = MT2701_MEMIF_UL1,
+		.suspend = mtk_afe_dai_suspend,
+		.resume = mtk_afe_dai_resume,
+		.capture = {
+			.stream_name = "UL1",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_48000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+		},
+		.ops = &mt2701_single_memif_dai_ops,
+	},
+	{
+		.name = "PCM1",
+		.id = MT2701_MEMIF_UL2,
+		.suspend = mtk_afe_dai_suspend,
+		.resume = mtk_afe_dai_resume,
+		.capture = {
+			.stream_name = "UL2",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_192000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+
+		},
+		.ops = &mt2701_single_memif_dai_ops,
+	},
+	{
+		.name = "PCM_BT_DL",
+		.id = MT2701_MEMIF_DLBT,
+		.suspend = mtk_afe_dai_suspend,
+		.resume = mtk_afe_dai_resume,
+		.playback = {
+			.stream_name = "DLBT",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = (SNDRV_PCM_RATE_8000
+				| SNDRV_PCM_RATE_16000),
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		},
+		.ops = &mt2701_single_memif_dai_ops,
+	},
+	{
+		.name = "PCM_BT_UL",
+		.id = MT2701_MEMIF_ULBT,
+		.suspend = mtk_afe_dai_suspend,
+		.resume = mtk_afe_dai_resume,
+		.capture = {
+			.stream_name = "ULBT",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = (SNDRV_PCM_RATE_8000
+				| SNDRV_PCM_RATE_16000),
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		},
+		.ops = &mt2701_single_memif_dai_ops,
+	},
+	/* BE DAIs */
+	{
+		.name = "I2S0",
+		.id = MT2701_IO_I2S,
+		.playback = {
+			.stream_name = "I2S0 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_192000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+
+		},
+		.capture = {
+			.stream_name = "I2S0 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_192000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+
+		},
+		.ops = &mt2701_afe_i2s_ops,
+		.symmetric_rates = 1,
+	},
+	{
+		.name = "I2S1",
+		.id = MT2701_IO_2ND_I2S,
+		.playback = {
+			.stream_name = "I2S1 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_192000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+			},
+		.capture = {
+			.stream_name = "I2S1 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_192000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+			},
+		.ops = &mt2701_afe_i2s_ops,
+		.symmetric_rates = 1,
+	},
+	{
+		.name = "I2S2",
+		.id = MT2701_IO_3RD_I2S,
+		.playback = {
+			.stream_name = "I2S2 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_192000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+			},
+		.capture = {
+			.stream_name = "I2S2 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_192000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+			},
+		.ops = &mt2701_afe_i2s_ops,
+		.symmetric_rates = 1,
+	},
+	{
+		.name = "I2S3",
+		.id = MT2701_IO_4TH_I2S,
+		.playback = {
+			.stream_name = "I2S3 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_192000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+			},
+		.capture = {
+			.stream_name = "I2S3 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = SNDRV_PCM_RATE_8000_192000,
+			.formats = (SNDRV_PCM_FMTBIT_S16_LE
+				| SNDRV_PCM_FMTBIT_S24_LE
+				| SNDRV_PCM_FMTBIT_S32_LE)
+			},
+		.ops = &mt2701_afe_i2s_ops,
+		.symmetric_rates = 1,
+	},
+	{
+		.name = "MRG BT",
+		.id = MT2701_IO_MRG,
+		.playback = {
+			.stream_name = "BT Playback",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = (SNDRV_PCM_RATE_8000
+				| SNDRV_PCM_RATE_16000),
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		},
+		.capture = {
+			.stream_name = "BT Capture",
+			.channels_min = 1,
+			.channels_max = 1,
+			.rates = (SNDRV_PCM_RATE_8000
+				| SNDRV_PCM_RATE_16000),
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+		},
+		.ops = &mt2701_btmrg_ops,
+		.symmetric_rates = 1,
+	}
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o00_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I00 Switch", AFE_CONN0, 0, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o01_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I01 Switch", AFE_CONN1, 1, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o02_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I02 Switch", AFE_CONN2, 2, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o03_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I03 Switch", AFE_CONN3, 3, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o14_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I26 Switch", AFE_CONN14, 26, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o15_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I12 Switch", AFE_CONN15, 12, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o16_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I13 Switch", AFE_CONN16, 13, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o17_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I14 Switch", AFE_CONN17, 14, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o18_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I15 Switch", AFE_CONN18, 15, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o19_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I16 Switch", AFE_CONN19, 16, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o20_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I17 Switch", AFE_CONN20, 17, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o21_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I18 Switch", AFE_CONN21, 18, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o22_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I19 Switch", AFE_CONN22, 19, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o23_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I20 Switch", AFE_CONN23, 20, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o24_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I21 Switch", AFE_CONN24, 21, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_o31_mix[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("I35 Switch", AFE_CONN41, 9, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_i02_mix[] = {
+	SOC_DAPM_SINGLE("I2S0 Switch", SND_SOC_NOPM, 0, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_multi_ch_out_i2s0[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("Multich I2S0 Out Switch",
+				    ASYS_I2SO1_CON, 26, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_multi_ch_out_i2s1[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("Multich I2S1 Out Switch",
+				    ASYS_I2SO2_CON, 26, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_multi_ch_out_i2s2[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("Multich I2S2 Out Switch",
+				    PWR2_TOP_CON, 17, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_multi_ch_out_i2s3[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("Multich I2S3 Out Switch",
+				    PWR2_TOP_CON, 18, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_multi_ch_out_i2s4[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("Multich I2S4 Out Switch",
+				    PWR2_TOP_CON, 19, 1, 0),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_multi_ch_out_asrc0[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("Asrc0 out Switch", AUDIO_TOP_CON4, 14, 1,
+				    1),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_multi_ch_out_asrc1[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("Asrc1 out Switch", AUDIO_TOP_CON4, 15, 1,
+				    1),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_multi_ch_out_asrc2[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("Asrc2 out Switch", PWR2_TOP_CON, 6, 1,
+				    1),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_multi_ch_out_asrc3[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("Asrc3 out Switch", PWR2_TOP_CON, 7, 1,
+				    1),
+};
+
+static const struct snd_kcontrol_new mt2701_afe_multi_ch_out_asrc4[] = {
+	SOC_DAPM_SINGLE_AUTODISABLE("Asrc4 out Switch", PWR2_TOP_CON, 8, 1,
+				    1),
+};
+
+static const struct snd_soc_dapm_widget mt2701_afe_pcm_widgets[] = {
+	/* inter-connections */
+	SND_SOC_DAPM_MIXER("I00", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I01", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I02", SND_SOC_NOPM, 0, 0, mt2701_afe_i02_mix,
+			   ARRAY_SIZE(mt2701_afe_i02_mix)),
+	SND_SOC_DAPM_MIXER("I03", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I12", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I13", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I14", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I15", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I16", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I17", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I18", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I19", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I26", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_MIXER("I35", SND_SOC_NOPM, 0, 0, NULL, 0),
+
+	SND_SOC_DAPM_MIXER("O00", SND_SOC_NOPM, 0, 0, mt2701_afe_o00_mix,
+			   ARRAY_SIZE(mt2701_afe_o00_mix)),
+	SND_SOC_DAPM_MIXER("O01", SND_SOC_NOPM, 0, 0, mt2701_afe_o01_mix,
+			   ARRAY_SIZE(mt2701_afe_o01_mix)),
+	SND_SOC_DAPM_MIXER("O02", SND_SOC_NOPM, 0, 0, mt2701_afe_o02_mix,
+			   ARRAY_SIZE(mt2701_afe_o02_mix)),
+	SND_SOC_DAPM_MIXER("O03", SND_SOC_NOPM, 0, 0, mt2701_afe_o03_mix,
+			   ARRAY_SIZE(mt2701_afe_o03_mix)),
+	SND_SOC_DAPM_MIXER("O14", SND_SOC_NOPM, 0, 0, mt2701_afe_o14_mix,
+			   ARRAY_SIZE(mt2701_afe_o14_mix)),
+	SND_SOC_DAPM_MIXER("O15", SND_SOC_NOPM, 0, 0, mt2701_afe_o15_mix,
+			   ARRAY_SIZE(mt2701_afe_o15_mix)),
+	SND_SOC_DAPM_MIXER("O16", SND_SOC_NOPM, 0, 0, mt2701_afe_o16_mix,
+			   ARRAY_SIZE(mt2701_afe_o16_mix)),
+	SND_SOC_DAPM_MIXER("O17", SND_SOC_NOPM, 0, 0, mt2701_afe_o17_mix,
+			   ARRAY_SIZE(mt2701_afe_o17_mix)),
+	SND_SOC_DAPM_MIXER("O18", SND_SOC_NOPM, 0, 0, mt2701_afe_o18_mix,
+			   ARRAY_SIZE(mt2701_afe_o18_mix)),
+	SND_SOC_DAPM_MIXER("O19", SND_SOC_NOPM, 0, 0, mt2701_afe_o19_mix,
+			   ARRAY_SIZE(mt2701_afe_o19_mix)),
+	SND_SOC_DAPM_MIXER("O20", SND_SOC_NOPM, 0, 0, mt2701_afe_o20_mix,
+			   ARRAY_SIZE(mt2701_afe_o20_mix)),
+	SND_SOC_DAPM_MIXER("O21", SND_SOC_NOPM, 0, 0, mt2701_afe_o21_mix,
+			   ARRAY_SIZE(mt2701_afe_o21_mix)),
+	SND_SOC_DAPM_MIXER("O22", SND_SOC_NOPM, 0, 0, mt2701_afe_o22_mix,
+			   ARRAY_SIZE(mt2701_afe_o22_mix)),
+	SND_SOC_DAPM_MIXER("O31", SND_SOC_NOPM, 0, 0, mt2701_afe_o31_mix,
+			   ARRAY_SIZE(mt2701_afe_o31_mix)),
+
+	SND_SOC_DAPM_MIXER("I12I13", SND_SOC_NOPM, 0, 0,
+			   mt2701_afe_multi_ch_out_i2s0,
+			   ARRAY_SIZE(mt2701_afe_multi_ch_out_i2s0)),
+	SND_SOC_DAPM_MIXER("I14I15", SND_SOC_NOPM, 0, 0,
+			   mt2701_afe_multi_ch_out_i2s1,
+			   ARRAY_SIZE(mt2701_afe_multi_ch_out_i2s1)),
+	SND_SOC_DAPM_MIXER("I16I17", SND_SOC_NOPM, 0, 0,
+			   mt2701_afe_multi_ch_out_i2s2,
+			   ARRAY_SIZE(mt2701_afe_multi_ch_out_i2s2)),
+	SND_SOC_DAPM_MIXER("I18I19", SND_SOC_NOPM, 0, 0,
+			   mt2701_afe_multi_ch_out_i2s3,
+			   ARRAY_SIZE(mt2701_afe_multi_ch_out_i2s3)),
+
+	SND_SOC_DAPM_MIXER("ASRC_O0", SND_SOC_NOPM, 0, 0,
+			   mt2701_afe_multi_ch_out_asrc0,
+			   ARRAY_SIZE(mt2701_afe_multi_ch_out_asrc0)),
+	SND_SOC_DAPM_MIXER("ASRC_O1", SND_SOC_NOPM, 0, 0,
+			   mt2701_afe_multi_ch_out_asrc1,
+			   ARRAY_SIZE(mt2701_afe_multi_ch_out_asrc1)),
+	SND_SOC_DAPM_MIXER("ASRC_O2", SND_SOC_NOPM, 0, 0,
+			   mt2701_afe_multi_ch_out_asrc2,
+			   ARRAY_SIZE(mt2701_afe_multi_ch_out_asrc2)),
+	SND_SOC_DAPM_MIXER("ASRC_O3", SND_SOC_NOPM, 0, 0,
+			   mt2701_afe_multi_ch_out_asrc3,
+			   ARRAY_SIZE(mt2701_afe_multi_ch_out_asrc3)),
+};
+
+static const struct snd_soc_dapm_route mt2701_afe_pcm_routes[] = {
+	{"I12", NULL, "DL1"},
+	{"I13", NULL, "DL1"},
+	{"I35", NULL, "DLBT"},
+
+	{"I2S0 Playback", NULL, "O15"},
+	{"I2S0 Playback", NULL, "O16"},
+
+	{"I2S1 Playback", NULL, "O17"},
+	{"I2S1 Playback", NULL, "O18"},
+	{"I2S2 Playback", NULL, "O19"},
+	{"I2S2 Playback", NULL, "O20"},
+	{"I2S3 Playback", NULL, "O21"},
+	{"I2S3 Playback", NULL, "O22"},
+	{"BT Playback", NULL, "O31"},
+
+	{"UL1", NULL, "O00"},
+	{"UL1", NULL, "O01"},
+	{"UL2", NULL, "O02"},
+	{"UL2", NULL, "O03"},
+	{"ULBT", NULL, "O14"},
+
+	{"I00", NULL, "I2S0 Capture"},
+	{"I01", NULL, "I2S0 Capture"},
+
+	{"I02", NULL, "I2S1 Capture"},
+	{"I03", NULL, "I2S1 Capture"},
+	/* I02,03 link to UL2, also need to open I2S0 */
+	{"I02", "I2S0 Switch", "I2S0 Capture"},
+
+	{"I26", NULL, "BT Capture"},
+
+	{"ASRC_O0", "Asrc0 out Switch", "DLM"},
+	{"ASRC_O1", "Asrc1 out Switch", "DLM"},
+	{"ASRC_O2", "Asrc2 out Switch", "DLM"},
+	{"ASRC_O3", "Asrc3 out Switch", "DLM"},
+
+	{"I12I13", "Multich I2S0 Out Switch", "ASRC_O0"},
+	{"I14I15", "Multich I2S1 Out Switch", "ASRC_O1"},
+	{"I16I17", "Multich I2S2 Out Switch", "ASRC_O2"},
+	{"I18I19", "Multich I2S3 Out Switch", "ASRC_O3"},
+
+	{ "I12", NULL, "I12I13" },
+	{ "I13", NULL, "I12I13" },
+	{ "I14", NULL, "I14I15" },
+	{ "I15", NULL, "I14I15" },
+	{ "I16", NULL, "I16I17" },
+	{ "I17", NULL, "I16I17" },
+	{ "I18", NULL, "I18I19" },
+	{ "I19", NULL, "I18I19" },
+
+	{ "O00", "I00 Switch", "I00" },
+	{ "O01", "I01 Switch", "I01" },
+	{ "O02", "I02 Switch", "I02" },
+	{ "O03", "I03 Switch", "I03" },
+	{ "O14", "I26 Switch", "I26" },
+	{ "O15", "I12 Switch", "I12" },
+	{ "O16", "I13 Switch", "I13" },
+	{ "O17", "I14 Switch", "I14" },
+	{ "O18", "I15 Switch", "I15" },
+	{ "O19", "I16 Switch", "I16" },
+	{ "O20", "I17 Switch", "I17" },
+	{ "O21", "I18 Switch", "I18" },
+	{ "O22", "I19 Switch", "I19" },
+	{ "O31", "I35 Switch", "I35" },
+
+};
+
+static const struct snd_soc_component_driver mt2701_afe_pcm_dai_component = {
+	.name = "mt2701-afe-pcm-dai",
+	.dapm_widgets = mt2701_afe_pcm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(mt2701_afe_pcm_widgets),
+	.dapm_routes = mt2701_afe_pcm_routes,
+	.num_dapm_routes = ARRAY_SIZE(mt2701_afe_pcm_routes),
+};
+
+static const struct mtk_base_memif_data memif_data[MT2701_MEMIF_NUM] = {
+	{
+		.name = "DL1",
+		.id = MT2701_MEMIF_DL1,
+		.reg_ofs_base = AFE_DL1_BASE,
+		.reg_ofs_cur = AFE_DL1_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = 0,
+		.fs_maskbit = 0x1f,
+		.mono_reg = AFE_DAC_CON3,
+		.mono_shift = 16,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 1,
+		.hd_reg = AFE_MEMIF_HD_CON0,
+		.hd_shift = 0,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 6,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "DL2",
+		.id = MT2701_MEMIF_DL2,
+		.reg_ofs_base = AFE_DL2_BASE,
+		.reg_ofs_cur = AFE_DL2_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = 5,
+		.fs_maskbit = 0x1f,
+		.mono_reg = AFE_DAC_CON3,
+		.mono_shift = 17,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 2,
+		.hd_reg = AFE_MEMIF_HD_CON0,
+		.hd_shift = 2,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 7,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "DL3",
+		.id = MT2701_MEMIF_DL3,
+		.reg_ofs_base = AFE_DL3_BASE,
+		.reg_ofs_cur = AFE_DL3_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = 10,
+		.fs_maskbit = 0x1f,
+		.mono_reg = AFE_DAC_CON3,
+		.mono_shift = 18,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 3,
+		.hd_reg = AFE_MEMIF_HD_CON0,
+		.hd_shift = 4,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 8,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "DL4",
+		.id = MT2701_MEMIF_DL4,
+		.reg_ofs_base = AFE_DL4_BASE,
+		.reg_ofs_cur = AFE_DL4_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = 15,
+		.fs_maskbit = 0x1f,
+		.mono_reg = AFE_DAC_CON3,
+		.mono_shift = 19,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 4,
+		.hd_reg = AFE_MEMIF_HD_CON0,
+		.hd_shift = 6,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 9,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "DL5",
+		.id = MT2701_MEMIF_DL5,
+		.reg_ofs_base = AFE_DL5_BASE,
+		.reg_ofs_cur = AFE_DL5_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = 20,
+		.fs_maskbit = 0x1f,
+		.mono_reg = AFE_DAC_CON3,
+		.mono_shift = 20,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 5,
+		.hd_reg = AFE_MEMIF_HD_CON0,
+		.hd_shift = 8,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 10,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "DLM",
+		.id = MT2701_MEMIF_DLM,
+		.reg_ofs_base = AFE_DLMCH_BASE,
+		.reg_ofs_cur = AFE_DLMCH_CUR,
+		.fs_reg = AFE_DAC_CON1,
+		.fs_shift = 0,
+		.fs_maskbit = 0x1f,
+		.mono_reg = -1,
+		.mono_shift = -1,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 7,
+		.hd_reg = AFE_MEMIF_PBUF_SIZE,
+		.hd_shift = 28,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 12,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "UL1",
+		.id = MT2701_MEMIF_UL1,
+		.reg_ofs_base = AFE_VUL_BASE,
+		.reg_ofs_cur = AFE_VUL_CUR,
+		.fs_reg = AFE_DAC_CON2,
+		.fs_shift = 0,
+		.fs_maskbit = 0x1f,
+		.mono_reg = AFE_DAC_CON4,
+		.mono_shift = 0,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 10,
+		.hd_reg = AFE_MEMIF_HD_CON1,
+		.hd_shift = 0,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 0,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "UL2",
+		.id = MT2701_MEMIF_UL2,
+		.reg_ofs_base = AFE_UL2_BASE,
+		.reg_ofs_cur = AFE_UL2_CUR,
+		.fs_reg = AFE_DAC_CON2,
+		.fs_shift = 5,
+		.fs_maskbit = 0x1f,
+		.mono_reg = AFE_DAC_CON4,
+		.mono_shift = 2,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 11,
+		.hd_reg = AFE_MEMIF_HD_CON1,
+		.hd_shift = 2,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 1,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "UL3",
+		.id = MT2701_MEMIF_UL3,
+		.reg_ofs_base = AFE_UL3_BASE,
+		.reg_ofs_cur = AFE_UL3_CUR,
+		.fs_reg = AFE_DAC_CON2,
+		.fs_shift = 10,
+		.fs_maskbit = 0x1f,
+		.mono_reg = AFE_DAC_CON4,
+		.mono_shift = 4,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 12,
+		.hd_reg = AFE_MEMIF_HD_CON0,
+		.hd_shift = 0,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 2,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "UL4",
+		.id = MT2701_MEMIF_UL4,
+		.reg_ofs_base = AFE_UL4_BASE,
+		.reg_ofs_cur = AFE_UL4_CUR,
+		.fs_reg = AFE_DAC_CON2,
+		.fs_shift = 15,
+		.fs_maskbit = 0x1f,
+		.mono_reg = AFE_DAC_CON4,
+		.mono_shift = 6,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 13,
+		.hd_reg = AFE_MEMIF_HD_CON0,
+		.hd_shift = 6,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 3,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "UL5",
+		.id = MT2701_MEMIF_UL5,
+		.reg_ofs_base = AFE_UL5_BASE,
+		.reg_ofs_cur = AFE_UL5_CUR,
+		.fs_reg = AFE_DAC_CON2,
+		.fs_shift = 20,
+		.mono_reg = AFE_DAC_CON4,
+		.mono_shift = 8,
+		.fs_maskbit = 0x1f,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 14,
+		.hd_reg = AFE_MEMIF_HD_CON0,
+		.hd_shift = 8,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 4,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "DLBT",
+		.id = MT2701_MEMIF_DLBT,
+		.reg_ofs_base = AFE_ARB1_BASE,
+		.reg_ofs_cur = AFE_ARB1_CUR,
+		.fs_reg = AFE_DAC_CON3,
+		.fs_shift = 10,
+		.fs_maskbit = 0x1f,
+		.mono_reg = AFE_DAC_CON3,
+		.mono_shift = 22,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 8,
+		.hd_reg = AFE_MEMIF_HD_CON0,
+		.hd_shift = 14,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 13,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+	{
+		.name = "ULBT",
+		.id = MT2701_MEMIF_ULBT,
+		.reg_ofs_base = AFE_DAI_BASE,
+		.reg_ofs_cur = AFE_DAI_CUR,
+		.fs_reg = AFE_DAC_CON2,
+		.fs_shift = 30,
+		.fs_maskbit = 0x1,
+		.mono_reg = -1,
+		.mono_shift = -1,
+		.enable_reg = AFE_DAC_CON0,
+		.enable_shift = 17,
+		.hd_reg = AFE_MEMIF_HD_CON1,
+		.hd_shift = 20,
+		.agent_disable_reg = AUDIO_TOP_CON5,
+		.agent_disable_shift = 16,
+		.msb_reg = -1,
+		.msb_shift = -1,
+	},
+};
+
+static const struct mtk_base_irq_data irq_data[MT2701_IRQ_ASYS_END] = {
+	{
+		.id = MT2701_IRQ_ASYS_IRQ1,
+		.irq_cnt_reg = ASYS_IRQ1_CON,
+		.irq_cnt_shift = 0,
+		.irq_cnt_maskbit = 0xffffff,
+		.irq_fs_reg = ASYS_IRQ1_CON,
+		.irq_fs_shift = 24,
+		.irq_fs_maskbit = 0x1f,
+		.irq_en_reg = ASYS_IRQ1_CON,
+		.irq_en_shift = 31,
+		.irq_clr_reg = ASYS_IRQ_CLR,
+		.irq_clr_shift = 0,
+	},
+	{
+		.id = MT2701_IRQ_ASYS_IRQ2,
+		.irq_cnt_reg = ASYS_IRQ2_CON,
+		.irq_cnt_shift = 0,
+		.irq_cnt_maskbit = 0xffffff,
+		.irq_fs_reg = ASYS_IRQ2_CON,
+		.irq_fs_shift = 24,
+		.irq_fs_maskbit = 0x1f,
+		.irq_en_reg = ASYS_IRQ2_CON,
+		.irq_en_shift = 31,
+		.irq_clr_reg = ASYS_IRQ_CLR,
+		.irq_clr_shift = 1,
+	},
+	{
+		.id = MT2701_IRQ_ASYS_IRQ3,
+		.irq_cnt_reg = ASYS_IRQ3_CON,
+		.irq_cnt_shift = 0,
+		.irq_cnt_maskbit = 0xffffff,
+		.irq_fs_reg = ASYS_IRQ3_CON,
+		.irq_fs_shift = 24,
+		.irq_fs_maskbit = 0x1f,
+		.irq_en_reg = ASYS_IRQ3_CON,
+		.irq_en_shift = 31,
+		.irq_clr_reg = ASYS_IRQ_CLR,
+		.irq_clr_shift = 2,
+	}
+};
+
+static const struct mt2701_i2s_data mt2701_i2s_data[MT2701_I2S_NUM][2] = {
+	{
+		{
+			.i2s_ctrl_reg = ASYS_I2SO1_CON,
+			.i2s_pwn_shift = 6,
+			.i2s_asrc_fs_shift = 0,
+			.i2s_asrc_fs_mask = 0x1f,
+
+		},
+		{
+			.i2s_ctrl_reg = ASYS_I2SIN1_CON,
+			.i2s_pwn_shift = 0,
+			.i2s_asrc_fs_shift = 0,
+			.i2s_asrc_fs_mask = 0x1f,
+
+		},
+	},
+	{
+		{
+			.i2s_ctrl_reg = ASYS_I2SO2_CON,
+			.i2s_pwn_shift = 7,
+			.i2s_asrc_fs_shift = 5,
+			.i2s_asrc_fs_mask = 0x1f,
+
+		},
+		{
+			.i2s_ctrl_reg = ASYS_I2SIN2_CON,
+			.i2s_pwn_shift = 1,
+			.i2s_asrc_fs_shift = 5,
+			.i2s_asrc_fs_mask = 0x1f,
+
+		},
+	},
+	{
+		{
+			.i2s_ctrl_reg = ASYS_I2SO3_CON,
+			.i2s_pwn_shift = 8,
+			.i2s_asrc_fs_shift = 10,
+			.i2s_asrc_fs_mask = 0x1f,
+
+		},
+		{
+			.i2s_ctrl_reg = ASYS_I2SIN3_CON,
+			.i2s_pwn_shift = 2,
+			.i2s_asrc_fs_shift = 10,
+			.i2s_asrc_fs_mask = 0x1f,
+
+		},
+	},
+	{
+		{
+			.i2s_ctrl_reg = ASYS_I2SO4_CON,
+			.i2s_pwn_shift = 9,
+			.i2s_asrc_fs_shift = 15,
+			.i2s_asrc_fs_mask = 0x1f,
+
+		},
+		{
+			.i2s_ctrl_reg = ASYS_I2SIN4_CON,
+			.i2s_pwn_shift = 3,
+			.i2s_asrc_fs_shift = 15,
+			.i2s_asrc_fs_mask = 0x1f,
+
+		},
+	},
+};
+
+static const struct regmap_config mt2701_afe_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.max_register = AFE_END_ADDR,
+	.cache_type = REGCACHE_NONE,
+};
+
+static irqreturn_t mt2701_asys_isr(int irq_id, void *dev)
+{
+	int id;
+	struct mtk_base_afe *afe = dev;
+	struct mtk_base_afe_memif *memif;
+	struct mtk_base_afe_irq *irq;
+	u32 status;
+
+	regmap_read(afe->regmap, ASYS_IRQ_STATUS, &status);
+	regmap_write(afe->regmap, ASYS_IRQ_CLR, status);
+
+	for (id = 0; id < MT2701_MEMIF_NUM; ++id) {
+		memif = &afe->memif[id];
+		if (memif->irq_usage < 0)
+			continue;
+		irq = &afe->irqs[memif->irq_usage];
+		if (status & 1 << (irq->irq_data->irq_clr_shift))
+			snd_pcm_period_elapsed(memif->substream);
+	}
+	return IRQ_HANDLED;
+}
+
+static int mt2701_afe_runtime_suspend(struct device *dev)
+{
+	struct mtk_base_afe *afe = dev_get_drvdata(dev);
+
+	mt2701_afe_disable_clock(afe);
+	return 0;
+}
+
+static int mt2701_afe_runtime_resume(struct device *dev)
+{
+	struct mtk_base_afe *afe = dev_get_drvdata(dev);
+
+	return mt2701_afe_enable_clock(afe);
+}
+
+static int mt2701_afe_pcm_dev_probe(struct platform_device *pdev)
+{
+	int ret, i;
+	unsigned int irq_id;
+	struct mtk_base_afe *afe;
+	struct mt2701_afe_private *afe_priv;
+	struct resource *res;
+	struct device *dev;
+
+	ret = 0;
+	afe = devm_kzalloc(&pdev->dev, sizeof(*afe), GFP_KERNEL);
+	if (!afe)
+		return -ENOMEM;
+	afe->platform_priv = devm_kzalloc(&pdev->dev, sizeof(*afe_priv),
+					  GFP_KERNEL);
+	if (!afe->platform_priv)
+		return -ENOMEM;
+	afe_priv = afe->platform_priv;
+
+	afe->dev = &pdev->dev;
+	dev = afe->dev;
+
+	irq_id = platform_get_irq(pdev, 0);
+	if (!irq_id) {
+		dev_err(dev, "%s no irq found\n", dev->of_node->name);
+		return -ENXIO;
+	}
+	ret = devm_request_irq(dev, irq_id, mt2701_asys_isr,
+			       IRQF_TRIGGER_NONE, "asys-isr", (void *)afe);
+	if (ret) {
+		dev_err(dev, "could not request_irq for asys-isr\n");
+		return ret;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	afe->base_addr = devm_ioremap_resource(&pdev->dev, res);
+
+	if (IS_ERR(afe->base_addr))
+		return PTR_ERR(afe->base_addr);
+
+	afe->regmap = devm_regmap_init_mmio(&pdev->dev, afe->base_addr,
+		&mt2701_afe_regmap_config);
+	if (IS_ERR(afe->regmap))
+		return PTR_ERR(afe->regmap);
+
+	mutex_init(&afe->irq_alloc_lock);
+
+	/* memif initialize */
+	afe->memif_size = MT2701_MEMIF_NUM;
+	afe->memif = devm_kcalloc(dev, afe->memif_size, sizeof(*afe->memif),
+				  GFP_KERNEL);
+
+	if (!afe->memif)
+		return -ENOMEM;
+
+	for (i = 0; i < afe->memif_size; i++) {
+		afe->memif[i].data = &memif_data[i];
+		afe->memif[i].irq_usage = -1;
+	}
+
+	/* irq initialize */
+	afe->irqs_size = MT2701_IRQ_ASYS_END;
+	afe->irqs = devm_kcalloc(dev, afe->irqs_size, sizeof(*afe->irqs),
+				 GFP_KERNEL);
+
+	if (!afe->irqs)
+		return -ENOMEM;
+
+	for (i = 0; i < afe->irqs_size; i++)
+		afe->irqs[i].irq_data = &irq_data[i];
+
+	/* I2S initialize */
+	for (i = 0; i < MT2701_I2S_NUM; i++) {
+		afe_priv->i2s_path[i].i2s_data[I2S_OUT]
+			= &mt2701_i2s_data[i][I2S_OUT];
+		afe_priv->i2s_path[i].i2s_data[I2S_IN]
+			= &mt2701_i2s_data[i][I2S_IN];
+	}
+
+	afe->mtk_afe_hardware = &mt2701_afe_hardware;
+	afe->memif_fs = mt2701_memif_fs;
+	afe->irq_fs = mt2701_irq_fs;
+
+	afe->reg_back_up_list = mt2701_afe_backup_list;
+	afe->reg_back_up_list_num = ARRAY_SIZE(mt2701_afe_backup_list);
+	afe->runtime_resume = mt2701_afe_runtime_resume;
+	afe->runtime_suspend = mt2701_afe_runtime_suspend;
+
+	/* initial audio related clock */
+	ret = mt2701_init_clock(afe);
+	if (ret) {
+		dev_err(dev, "init clock error\n");
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, afe);
+	pm_runtime_enable(&pdev->dev);
+	if (!pm_runtime_enabled(&pdev->dev))
+		goto err_pm_disable;
+
+	ret = snd_soc_register_platform(&pdev->dev, &mtk_afe_pcm_platform);
+	if (ret) {
+		dev_warn(dev, "err_platform\n");
+		goto err_platform;
+	}
+
+	ret = snd_soc_register_component(&pdev->dev,
+					 &mt2701_afe_pcm_dai_component,
+					 mt2701_afe_pcm_dais,
+					 ARRAY_SIZE(mt2701_afe_pcm_dais));
+	if (ret) {
+		dev_warn(dev, "err_dai_component\n");
+		goto err_dai_component;
+	}
+
+	mt2701_afe_runtime_resume(&pdev->dev);
+
+	return 0;
+
+err_dai_component:
+	snd_soc_unregister_component(&pdev->dev);
+
+err_platform:
+	snd_soc_unregister_platform(&pdev->dev);
+
+err_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+
+	return ret;
+}
+
+static int mt2701_afe_pcm_dev_remove(struct platform_device *pdev)
+{
+	struct mtk_base_afe *afe = platform_get_drvdata(pdev);
+
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		mt2701_afe_runtime_suspend(&pdev->dev);
+
+	snd_soc_unregister_component(&pdev->dev);
+	snd_soc_unregister_platform(&pdev->dev);
+	/* disable afe clock */
+	mt2701_afe_disable_clock(afe);
+	return 0;
+}
+
+static const struct of_device_id mt2701_afe_pcm_dt_match[] = {
+	{ .compatible = "mediatek,mt2701-audio", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mt2701_afe_pcm_dt_match);
+
+static const struct dev_pm_ops mt2701_afe_pm_ops = {
+	SET_RUNTIME_PM_OPS(mt2701_afe_runtime_suspend,
+			   mt2701_afe_runtime_resume, NULL)
+};
+
+static struct platform_driver mt2701_afe_pcm_driver = {
+	.driver = {
+		   .name = "mt2701-audio",
+		   .of_match_table = mt2701_afe_pcm_dt_match,
+#ifdef CONFIG_PM
+		   .pm = &mt2701_afe_pm_ops,
+#endif
+	},
+	.probe = mt2701_afe_pcm_dev_probe,
+	.remove = mt2701_afe_pcm_dev_remove,
+};
+
+module_platform_driver(mt2701_afe_pcm_driver);
+
+MODULE_DESCRIPTION("Mediatek ALSA SoC AFE platform driver for 2701");
+MODULE_AUTHOR("Garlic Tseng <garlic.tseng@mediatek.com>");
+MODULE_LICENSE("GPL v2");
+
diff --git a/sound/soc/mediatek/mt2701/mt2701-cs42448.c b/sound/soc/mediatek/mt2701/mt2701-cs42448.c
new file mode 100644
index 000000000000..1e7e8d43fd8a
--- /dev/null
+++ b/sound/soc/mediatek/mt2701/mt2701-cs42448.c
@@ -0,0 +1,412 @@
+/*
+ * mt2701-cs42448.c  --  MT2701 CS42448 ALSA SoC machine driver
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Ir Lian <ir.lian@mediatek.com>
+ *              Garlic Tseng <garlic.tseng@mediatek.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <sound/soc.h>
+#include <linux/delay.h>
+#include <linux/gpio.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/of_gpio.h>
+
+#include "mt2701-afe-common.h"
+
+struct mt2701_cs42448_private {
+	int i2s1_in_mux;
+	int i2s1_in_mux_gpio_sel_1;
+	int i2s1_in_mux_gpio_sel_2;
+};
+
+static const char * const i2sin_mux_switch_text[] = {
+	"ADC_SDOUT2",
+	"ADC_SDOUT3",
+	"I2S_IN_1",
+	"I2S_IN_2",
+};
+
+static const struct soc_enum i2sin_mux_enum =
+	SOC_ENUM_SINGLE_EXT(4, i2sin_mux_switch_text);
+
+static int mt2701_cs42448_i2sin1_mux_get(struct snd_kcontrol *kcontrol,
+					 struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
+	struct mt2701_cs42448_private *priv = snd_soc_card_get_drvdata(card);
+
+	ucontrol->value.integer.value[0] = priv->i2s1_in_mux;
+	return 0;
+}
+
+static int mt2701_cs42448_i2sin1_mux_set(struct snd_kcontrol *kcontrol,
+					 struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
+	struct mt2701_cs42448_private *priv = snd_soc_card_get_drvdata(card);
+
+	if (ucontrol->value.integer.value[0] == priv->i2s1_in_mux)
+		return 0;
+
+	switch (ucontrol->value.integer.value[0]) {
+	case 0:
+		gpio_set_value(priv->i2s1_in_mux_gpio_sel_1, 0);
+		gpio_set_value(priv->i2s1_in_mux_gpio_sel_2, 0);
+		break;
+	case 1:
+		gpio_set_value(priv->i2s1_in_mux_gpio_sel_1, 1);
+		gpio_set_value(priv->i2s1_in_mux_gpio_sel_2, 0);
+		break;
+	case 2:
+		gpio_set_value(priv->i2s1_in_mux_gpio_sel_1, 0);
+		gpio_set_value(priv->i2s1_in_mux_gpio_sel_2, 1);
+		break;
+	case 3:
+		gpio_set_value(priv->i2s1_in_mux_gpio_sel_1, 1);
+		gpio_set_value(priv->i2s1_in_mux_gpio_sel_2, 1);
+		break;
+	default:
+		dev_warn(card->dev, "%s invalid setting\n", __func__);
+	}
+
+	priv->i2s1_in_mux = ucontrol->value.integer.value[0];
+	return 0;
+}
+
+static const struct snd_soc_dapm_widget
+			mt2701_cs42448_asoc_card_dapm_widgets[] = {
+	SND_SOC_DAPM_LINE("Line Out Jack", NULL),
+	SND_SOC_DAPM_MIC("AMIC", NULL),
+	SND_SOC_DAPM_LINE("Tuner In", NULL),
+	SND_SOC_DAPM_LINE("Satellite Tuner In", NULL),
+	SND_SOC_DAPM_LINE("AUX In", NULL),
+};
+
+static const struct snd_kcontrol_new mt2701_cs42448_controls[] = {
+	SOC_DAPM_PIN_SWITCH("Line Out Jack"),
+	SOC_DAPM_PIN_SWITCH("AMIC"),
+	SOC_DAPM_PIN_SWITCH("Tuner In"),
+	SOC_DAPM_PIN_SWITCH("Satellite Tuner In"),
+	SOC_DAPM_PIN_SWITCH("AUX In"),
+	SOC_ENUM_EXT("I2SIN1_MUX_Switch", i2sin_mux_enum,
+		     mt2701_cs42448_i2sin1_mux_get,
+		     mt2701_cs42448_i2sin1_mux_set),
+};
+
+static const unsigned int mt2701_cs42448_sampling_rates[] = {48000};
+
+static struct snd_pcm_hw_constraint_list mt2701_cs42448_constraints_rates = {
+		.count = ARRAY_SIZE(mt2701_cs42448_sampling_rates),
+		.list = mt2701_cs42448_sampling_rates,
+		.mask = 0,
+};
+
+static int mt2701_cs42448_fe_ops_startup(struct snd_pcm_substream *substream)
+{
+	int err;
+
+	err = snd_pcm_hw_constraint_list(substream->runtime, 0,
+					 SNDRV_PCM_HW_PARAM_RATE,
+					 &mt2701_cs42448_constraints_rates);
+	if (err < 0) {
+		dev_err(substream->pcm->card->dev,
+			"%s snd_pcm_hw_constraint_list failed: 0x%x\n",
+			__func__, err);
+		return err;
+	}
+	return 0;
+}
+
+static struct snd_soc_ops mt2701_cs42448_48k_fe_ops = {
+	.startup = mt2701_cs42448_fe_ops_startup,
+};
+
+static int mt2701_cs42448_be_ops_hw_params(struct snd_pcm_substream *substream,
+					   struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	unsigned int mclk_rate;
+	unsigned int rate = params_rate(params);
+	unsigned int div_mclk_over_bck = rate > 192000 ? 2 : 4;
+	unsigned int div_bck_over_lrck = 64;
+
+	mclk_rate = rate * div_bck_over_lrck * div_mclk_over_bck;
+
+	/* mt2701 mclk */
+	snd_soc_dai_set_sysclk(cpu_dai, 0, mclk_rate, SND_SOC_CLOCK_OUT);
+
+	/* codec mclk */
+	snd_soc_dai_set_sysclk(codec_dai, 0, mclk_rate, SND_SOC_CLOCK_IN);
+
+	return 0;
+}
+
+static struct snd_soc_ops mt2701_cs42448_be_ops = {
+	.hw_params = mt2701_cs42448_be_ops_hw_params
+};
+
+enum {
+	DAI_LINK_FE_MULTI_CH_OUT,
+	DAI_LINK_FE_PCM0_IN,
+	DAI_LINK_FE_PCM1_IN,
+	DAI_LINK_FE_BT_OUT,
+	DAI_LINK_FE_BT_IN,
+	DAI_LINK_BE_I2S0,
+	DAI_LINK_BE_I2S1,
+	DAI_LINK_BE_I2S2,
+	DAI_LINK_BE_I2S3,
+	DAI_LINK_BE_MRG_BT,
+};
+
+static struct snd_soc_dai_link mt2701_cs42448_dai_links[] = {
+	/* FE */
+	[DAI_LINK_FE_MULTI_CH_OUT] = {
+		.name = "mt2701-cs42448-multi-ch-out",
+		.stream_name = "mt2701-cs42448-multi-ch-out",
+		.cpu_dai_name = "PCM_multi",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_POST,
+			    SND_SOC_DPCM_TRIGGER_POST},
+		.ops = &mt2701_cs42448_48k_fe_ops,
+		.dynamic = 1,
+		.dpcm_playback = 1,
+	},
+	[DAI_LINK_FE_PCM0_IN] = {
+		.name = "mt2701-cs42448-pcm0",
+		.stream_name = "mt2701-cs42448-pcm0-data-UL",
+		.cpu_dai_name = "PCM0",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_POST,
+			    SND_SOC_DPCM_TRIGGER_POST},
+		.ops = &mt2701_cs42448_48k_fe_ops,
+		.dynamic = 1,
+		.dpcm_capture = 1,
+	},
+	[DAI_LINK_FE_PCM1_IN] = {
+		.name = "mt2701-cs42448-pcm1-data-UL",
+		.stream_name = "mt2701-cs42448-pcm1-data-UL",
+		.cpu_dai_name = "PCM1",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_POST,
+			    SND_SOC_DPCM_TRIGGER_POST},
+		.ops = &mt2701_cs42448_48k_fe_ops,
+		.dynamic = 1,
+		.dpcm_capture = 1,
+	},
+	[DAI_LINK_FE_BT_OUT] = {
+		.name = "mt2701-cs42448-pcm-BT-out",
+		.stream_name = "mt2701-cs42448-pcm-BT",
+		.cpu_dai_name = "PCM_BT_DL",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_POST,
+			    SND_SOC_DPCM_TRIGGER_POST},
+		.dynamic = 1,
+		.dpcm_playback = 1,
+	},
+	[DAI_LINK_FE_BT_IN] = {
+		.name = "mt2701-cs42448-pcm-BT-in",
+		.stream_name = "mt2701-cs42448-pcm-BT",
+		.cpu_dai_name = "PCM_BT_UL",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_POST,
+			    SND_SOC_DPCM_TRIGGER_POST},
+		.dynamic = 1,
+		.dpcm_capture = 1,
+	},
+	/* BE */
+	[DAI_LINK_BE_I2S0] = {
+		.name = "mt2701-cs42448-I2S0",
+		.cpu_dai_name = "I2S0",
+		.no_pcm = 1,
+		.codec_dai_name = "cs42448",
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS
+			 | SND_SOC_DAIFMT_GATED,
+		.ops = &mt2701_cs42448_be_ops,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+	},
+	[DAI_LINK_BE_I2S1] = {
+		.name = "mt2701-cs42448-I2S1",
+		.cpu_dai_name = "I2S1",
+		.no_pcm = 1,
+		.codec_dai_name = "cs42448",
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS
+			 | SND_SOC_DAIFMT_GATED,
+		.ops = &mt2701_cs42448_be_ops,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+	},
+	[DAI_LINK_BE_I2S2] = {
+		.name = "mt2701-cs42448-I2S2",
+		.cpu_dai_name = "I2S2",
+		.no_pcm = 1,
+		.codec_dai_name = "cs42448",
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS
+			 | SND_SOC_DAIFMT_GATED,
+		.ops = &mt2701_cs42448_be_ops,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+	},
+	[DAI_LINK_BE_I2S3] = {
+		.name = "mt2701-cs42448-I2S3",
+		.cpu_dai_name = "I2S3",
+		.no_pcm = 1,
+		.codec_dai_name = "cs42448",
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS
+			 | SND_SOC_DAIFMT_GATED,
+		.ops = &mt2701_cs42448_be_ops,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+	},
+	[DAI_LINK_BE_MRG_BT] = {
+		.name = "mt2701-cs42448-MRG-BT",
+		.cpu_dai_name = "MRG BT",
+		.no_pcm = 1,
+		.codec_dai_name = "bt-sco-pcm-wb",
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+	},
+};
+
+static struct snd_soc_card mt2701_cs42448_soc_card = {
+	.name = "mt2701-cs42448",
+	.owner = THIS_MODULE,
+	.dai_link = mt2701_cs42448_dai_links,
+	.num_links = ARRAY_SIZE(mt2701_cs42448_dai_links),
+	.controls = mt2701_cs42448_controls,
+	.num_controls = ARRAY_SIZE(mt2701_cs42448_controls),
+	.dapm_widgets = mt2701_cs42448_asoc_card_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(mt2701_cs42448_asoc_card_dapm_widgets),
+};
+
+static int mt2701_cs42448_machine_probe(struct platform_device *pdev)
+{
+	struct snd_soc_card *card = &mt2701_cs42448_soc_card;
+	int ret;
+	int i;
+	struct device_node *platform_node, *codec_node, *codec_node_bt_mrg;
+	struct mt2701_cs42448_private *priv =
+		devm_kzalloc(&pdev->dev, sizeof(struct mt2701_cs42448_private),
+			     GFP_KERNEL);
+	struct device *dev = &pdev->dev;
+
+	if (!priv)
+		return -ENOMEM;
+
+	platform_node = of_parse_phandle(pdev->dev.of_node,
+					 "mediatek,platform", 0);
+	if (!platform_node) {
+		dev_err(&pdev->dev, "Property 'platform' missing or invalid\n");
+		return -EINVAL;
+	}
+	for (i = 0; i < card->num_links; i++) {
+		if (mt2701_cs42448_dai_links[i].platform_name)
+			continue;
+		mt2701_cs42448_dai_links[i].platform_of_node = platform_node;
+	}
+
+	card->dev = dev;
+
+	codec_node = of_parse_phandle(pdev->dev.of_node,
+				      "mediatek,audio-codec", 0);
+	if (!codec_node) {
+		dev_err(&pdev->dev,
+			"Property 'audio-codec' missing or invalid\n");
+		return -EINVAL;
+	}
+	for (i = 0; i < card->num_links; i++) {
+		if (mt2701_cs42448_dai_links[i].codec_name)
+			continue;
+		mt2701_cs42448_dai_links[i].codec_of_node = codec_node;
+	}
+
+	codec_node_bt_mrg = of_parse_phandle(pdev->dev.of_node,
+					     "mediatek,audio-codec-bt-mrg", 0);
+	if (!codec_node_bt_mrg) {
+		dev_err(&pdev->dev,
+			"Property 'audio-codec-bt-mrg' missing or invalid\n");
+		return -EINVAL;
+	}
+	mt2701_cs42448_dai_links[DAI_LINK_BE_MRG_BT].codec_of_node
+							= codec_node_bt_mrg;
+
+	ret = snd_soc_of_parse_audio_routing(card, "audio-routing");
+	if (ret) {
+		dev_err(&pdev->dev, "failed to parse audio-routing: %d\n", ret);
+		return ret;
+	}
+
+	priv->i2s1_in_mux_gpio_sel_1 =
+		of_get_named_gpio(dev->of_node, "i2s1-in-sel-gpio1", 0);
+	if (gpio_is_valid(priv->i2s1_in_mux_gpio_sel_1)) {
+		ret = devm_gpio_request(dev, priv->i2s1_in_mux_gpio_sel_1,
+					"i2s1_in_mux_gpio_sel_1");
+		if (ret)
+			dev_warn(&pdev->dev, "%s devm_gpio_request fail %d\n",
+				 __func__, ret);
+		gpio_direction_output(priv->i2s1_in_mux_gpio_sel_1, 0);
+	}
+
+	priv->i2s1_in_mux_gpio_sel_2 =
+		of_get_named_gpio(dev->of_node, "i2s1-in-sel-gpio2", 0);
+	if (gpio_is_valid(priv->i2s1_in_mux_gpio_sel_2)) {
+		ret = devm_gpio_request(dev, priv->i2s1_in_mux_gpio_sel_2,
+					"i2s1_in_mux_gpio_sel_2");
+		if (ret)
+			dev_warn(&pdev->dev, "%s devm_gpio_request fail2 %d\n",
+				 __func__, ret);
+		gpio_direction_output(priv->i2s1_in_mux_gpio_sel_2, 0);
+	}
+	snd_soc_card_set_drvdata(card, priv);
+
+	ret = devm_snd_soc_register_card(&pdev->dev, card);
+
+	if (ret)
+		dev_err(&pdev->dev, "%s snd_soc_register_card fail %d\n",
+			__func__, ret);
+	return ret;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id mt2701_cs42448_machine_dt_match[] = {
+	{.compatible = "mediatek,mt2701-cs42448-machine",},
+	{}
+};
+#endif
+
+static struct platform_driver mt2701_cs42448_machine = {
+	.driver = {
+		.name = "mt2701-cs42448",
+		   #ifdef CONFIG_OF
+		   .of_match_table = mt2701_cs42448_machine_dt_match,
+		   #endif
+	},
+	.probe = mt2701_cs42448_machine_probe,
+};
+
+module_platform_driver(mt2701_cs42448_machine);
+
+/* Module information */
+MODULE_DESCRIPTION("MT2701 CS42448 ALSA SoC machine driver");
+MODULE_AUTHOR("Ir Lian <ir.lian@mediatek.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("mt2701 cs42448 soc card");
diff --git a/sound/soc/mediatek/mt2701/mt2701-reg.h b/sound/soc/mediatek/mt2701/mt2701-reg.h
new file mode 100644
index 000000000000..bb62b1c55957
--- /dev/null
+++ b/sound/soc/mediatek/mt2701/mt2701-reg.h
@@ -0,0 +1,186 @@
+/*
+ * mt2701-reg.h  --  Mediatek 2701 audio driver reg definition
+ *
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Garlic Tseng <garlic.tseng@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _MT2701_REG_H_
+#define _MT2701_REG_H_
+
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/pm_runtime.h>
+#include <sound/soc.h>
+#include "mt2701-afe-common.h"
+
+/*****************************************************************************
+ *                  R E G I S T E R       D E F I N I T I O N
+ *****************************************************************************/
+#define AUDIO_TOP_CON0 0x0000
+#define AUDIO_TOP_CON4 0x0010
+#define AUDIO_TOP_CON5 0x0014
+#define AFE_DAIBT_CON0 0x001c
+#define AFE_MRGIF_CON 0x003c
+#define ASMI_TIMING_CON1 0x0100
+#define ASMO_TIMING_CON1 0x0104
+#define PWR1_ASM_CON1 0x0108
+#define ASYS_TOP_CON 0x0600
+#define ASYS_I2SIN1_CON 0x0604
+#define ASYS_I2SIN2_CON 0x0608
+#define ASYS_I2SIN3_CON 0x060c
+#define ASYS_I2SIN4_CON 0x0610
+#define ASYS_I2SIN5_CON 0x0614
+#define ASYS_I2SO1_CON 0x061C
+#define ASYS_I2SO2_CON 0x0620
+#define ASYS_I2SO3_CON 0x0624
+#define ASYS_I2SO4_CON 0x0628
+#define ASYS_I2SO5_CON 0x062c
+#define PWR2_TOP_CON 0x0634
+#define AFE_CONN0 0x06c0
+#define AFE_CONN1 0x06c4
+#define AFE_CONN2 0x06c8
+#define AFE_CONN3 0x06cc
+#define AFE_CONN14 0x06f8
+#define AFE_CONN15 0x06fc
+#define AFE_CONN16 0x0700
+#define AFE_CONN17 0x0704
+#define AFE_CONN18 0x0708
+#define AFE_CONN19 0x070c
+#define AFE_CONN20 0x0710
+#define AFE_CONN21 0x0714
+#define AFE_CONN22 0x0718
+#define AFE_CONN23 0x071c
+#define AFE_CONN24 0x0720
+#define AFE_CONN41 0x0764
+#define ASYS_IRQ1_CON 0x0780
+#define ASYS_IRQ2_CON 0x0784
+#define ASYS_IRQ3_CON 0x0788
+#define ASYS_IRQ_CLR 0x07c0
+#define ASYS_IRQ_STATUS 0x07c4
+#define PWR2_ASM_CON1 0x1070
+#define AFE_DAC_CON0 0x1200
+#define AFE_DAC_CON1 0x1204
+#define AFE_DAC_CON2 0x1208
+#define AFE_DAC_CON3 0x120c
+#define AFE_DAC_CON4 0x1210
+#define AFE_MEMIF_HD_CON1 0x121c
+#define AFE_MEMIF_PBUF_SIZE 0x1238
+#define AFE_MEMIF_HD_CON0 0x123c
+#define AFE_DL1_BASE 0x1240
+#define AFE_DL1_CUR 0x1244
+#define AFE_DL2_BASE 0x1250
+#define AFE_DL2_CUR 0x1254
+#define AFE_DL3_BASE 0x1260
+#define AFE_DL3_CUR 0x1264
+#define AFE_DL4_BASE 0x1270
+#define AFE_DL4_CUR 0x1274
+#define AFE_DL5_BASE 0x1280
+#define AFE_DL5_CUR 0x1284
+#define AFE_DLMCH_BASE 0x12a0
+#define AFE_DLMCH_CUR 0x12a4
+#define AFE_ARB1_BASE 0x12b0
+#define AFE_ARB1_CUR 0x12b4
+#define AFE_VUL_BASE 0x1300
+#define AFE_VUL_CUR 0x130c
+#define AFE_UL2_BASE 0x1310
+#define AFE_UL2_END 0x1318
+#define AFE_UL2_CUR 0x131c
+#define AFE_UL3_BASE 0x1320
+#define AFE_UL3_END 0x1328
+#define AFE_UL3_CUR 0x132c
+#define AFE_UL4_BASE 0x1330
+#define AFE_UL4_END 0x1338
+#define AFE_UL4_CUR 0x133c
+#define AFE_UL5_BASE 0x1340
+#define AFE_UL5_END 0x1348
+#define AFE_UL5_CUR 0x134c
+#define AFE_DAI_BASE 0x1370
+#define AFE_DAI_CUR 0x137c
+
+/* AUDIO_TOP_CON0 (0x0000) */
+#define AUDIO_TOP_CON0_A1SYS_A2SYS_ON	(0x3 << 0)
+#define AUDIO_TOP_CON0_PDN_AFE		(0x1 << 2)
+#define AUDIO_TOP_CON0_PDN_APLL_CK	(0x1 << 23)
+
+/* AUDIO_TOP_CON4 (0x0010) */
+#define AUDIO_TOP_CON4_I2SO1_PWN	(0x1 << 6)
+#define AUDIO_TOP_CON4_PDN_A1SYS	(0x1 << 21)
+#define AUDIO_TOP_CON4_PDN_A2SYS	(0x1 << 22)
+#define AUDIO_TOP_CON4_PDN_AFE_CONN	(0x1 << 23)
+#define AUDIO_TOP_CON4_PDN_MRGIF	(0x1 << 25)
+
+/* AFE_DAIBT_CON0 (0x001c) */
+#define AFE_DAIBT_CON0_DAIBT_EN		(0x1 << 0)
+#define AFE_DAIBT_CON0_BT_FUNC_EN	(0x1 << 1)
+#define AFE_DAIBT_CON0_BT_FUNC_RDY	(0x1 << 3)
+#define AFE_DAIBT_CON0_BT_WIDE_MODE_EN	(0x1 << 9)
+#define AFE_DAIBT_CON0_MRG_USE		(0x1 << 12)
+
+/* PWR1_ASM_CON1 (0x0108) */
+#define PWR1_ASM_CON1_INIT_VAL		(0x492)
+
+/* AFE_MRGIF_CON (0x003c) */
+#define AFE_MRGIF_CON_MRG_EN		(0x1 << 0)
+#define AFE_MRGIF_CON_MRG_I2S_EN	(0x1 << 16)
+#define AFE_MRGIF_CON_I2S_MODE_MASK	(0xf << 20)
+#define AFE_MRGIF_CON_I2S_MODE_32K	(0x4 << 20)
+
+/* ASYS_I2SO1_CON (0x061c) */
+#define ASYS_I2SO1_CON_FS		(0x1f << 8)
+#define ASYS_I2SO1_CON_FS_SET(x)	((x) << 8)
+#define ASYS_I2SO1_CON_MULTI_CH		(0x1 << 16)
+#define ASYS_I2SO1_CON_SIDEGEN		(0x1 << 30)
+#define ASYS_I2SO1_CON_I2S_EN		(0x1 << 0)
+/* 0:EIAJ 1:I2S */
+#define ASYS_I2SO1_CON_I2S_MODE		(0x1 << 3)
+#define ASYS_I2SO1_CON_WIDE_MODE	(0x1 << 1)
+#define ASYS_I2SO1_CON_WIDE_MODE_SET(x)	((x) << 1)
+
+/* PWR2_TOP_CON (0x0634) */
+#define PWR2_TOP_CON_INIT_VAL		(0xffe1ffff)
+
+/* ASYS_IRQ_CLR (0x07c0) */
+#define ASYS_IRQ_CLR_ALL		(0xffffffff)
+
+/* PWR2_ASM_CON1 (0x1070) */
+#define PWR2_ASM_CON1_INIT_VAL		(0x492492)
+
+/* AFE_DAC_CON0 (0x1200) */
+#define AFE_DAC_CON0_AFE_ON		(0x1 << 0)
+
+/* AFE_MEMIF_PBUF_SIZE (0x1238) */
+#define AFE_MEMIF_PBUF_SIZE_DLM_MASK		(0x1 << 29)
+#define AFE_MEMIF_PBUF_SIZE_PAIR_INTERLEAVE	(0x0 << 29)
+#define AFE_MEMIF_PBUF_SIZE_FULL_INTERLEAVE	(0x1 << 29)
+#define DLMCH_BIT_WIDTH_MASK			(0x1 << 28)
+#define AFE_MEMIF_PBUF_SIZE_DLM_CH_MASK		(0xf << 24)
+#define AFE_MEMIF_PBUF_SIZE_DLM_CH(x)		((x) << 24)
+#define AFE_MEMIF_PBUF_SIZE_DLM_BYTE_MASK	(0x3 << 12)
+#define AFE_MEMIF_PBUF_SIZE_DLM_32BYTES		(0x1 << 12)
+
+/* I2S in/out register bit control */
+#define ASYS_I2S_CON_FS			(0x1f << 8)
+#define ASYS_I2S_CON_FS_SET(x)		((x) << 8)
+#define ASYS_I2S_CON_RESET		(0x1 << 30)
+#define ASYS_I2S_CON_I2S_EN		(0x1 << 0)
+#define ASYS_I2S_CON_I2S_COUPLE_MODE	(0x1 << 17)
+/* 0:EIAJ 1:I2S */
+#define ASYS_I2S_CON_I2S_MODE		(0x1 << 3)
+#define ASYS_I2S_CON_WIDE_MODE		(0x1 << 1)
+#define ASYS_I2S_CON_WIDE_MODE_SET(x)	((x) << 1)
+#define ASYS_I2S_IN_PHASE_FIX		(0x1 << 31)
+
+#define AFE_END_ADDR 0x15e0
+#endif
diff --git a/sound/soc/mediatek/mt8173/Makefile b/sound/soc/mediatek/mt8173/Makefile
new file mode 100644
index 000000000000..0357b27d29f2
--- /dev/null
+++ b/sound/soc/mediatek/mt8173/Makefile
@@ -0,0 +1,7 @@
+# MTK Platform Support
+obj-$(CONFIG_SND_SOC_MT8173) += mt8173-afe-pcm.o
+# Machine support
+obj-$(CONFIG_SND_SOC_MT8173_MAX98090) += mt8173-max98090.o
+obj-$(CONFIG_SND_SOC_MT8173_RT5650) += mt8173-rt5650.o
+obj-$(CONFIG_SND_SOC_MT8173_RT5650_RT5514) += mt8173-rt5650-rt5514.o
+obj-$(CONFIG_SND_SOC_MT8173_RT5650_RT5676) += mt8173-rt5650-rt5676.o
diff --git a/sound/soc/mediatek/mt8173/mt8173-afe-common.h b/sound/soc/mediatek/mt8173/mt8173-afe-common.h
new file mode 100644
index 000000000000..9a4837cc181a
--- /dev/null
+++ b/sound/soc/mediatek/mt8173/mt8173-afe-common.h
@@ -0,0 +1,73 @@
+/*
+ * mt8173_afe_common.h  --  Mediatek 8173 audio driver common definitions
+ *
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Koro Chen <koro.chen@mediatek.com>
+ *             Sascha Hauer <s.hauer@pengutronix.de>
+ *             Hidalgo Huang <hidalgo.huang@mediatek.com>
+ *             Ir Lian <ir.lian@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _MT8173_AFE_COMMON_H_
+#define _MT8173_AFE_COMMON_H_
+
+#include <linux/clk.h>
+#include <linux/regmap.h>
+
+enum {
+	MT8173_AFE_MEMIF_DL1,
+	MT8173_AFE_MEMIF_DL2,
+	MT8173_AFE_MEMIF_VUL,
+	MT8173_AFE_MEMIF_DAI,
+	MT8173_AFE_MEMIF_AWB,
+	MT8173_AFE_MEMIF_MOD_DAI,
+	MT8173_AFE_MEMIF_HDMI,
+	MT8173_AFE_MEMIF_NUM,
+	MT8173_AFE_IO_MOD_PCM1 = MT8173_AFE_MEMIF_NUM,
+	MT8173_AFE_IO_MOD_PCM2,
+	MT8173_AFE_IO_PMIC,
+	MT8173_AFE_IO_I2S,
+	MT8173_AFE_IO_2ND_I2S,
+	MT8173_AFE_IO_HW_GAIN1,
+	MT8173_AFE_IO_HW_GAIN2,
+	MT8173_AFE_IO_MRG_O,
+	MT8173_AFE_IO_MRG_I,
+	MT8173_AFE_IO_DAIBT,
+	MT8173_AFE_IO_HDMI,
+};
+
+enum {
+	MT8173_AFE_IRQ_DL1,
+	MT8173_AFE_IRQ_DL2,
+	MT8173_AFE_IRQ_VUL,
+	MT8173_AFE_IRQ_DAI,
+	MT8173_AFE_IRQ_AWB,
+	MT8173_AFE_IRQ_MOD_DAI,
+	MT8173_AFE_IRQ_HDMI,
+	MT8173_AFE_IRQ_NUM,
+};
+
+enum {
+	MT8173_CLK_INFRASYS_AUD,
+	MT8173_CLK_TOP_PDN_AUD,
+	MT8173_CLK_TOP_PDN_AUD_BUS,
+	MT8173_CLK_I2S0_M,
+	MT8173_CLK_I2S1_M,
+	MT8173_CLK_I2S2_M,
+	MT8173_CLK_I2S3_M,
+	MT8173_CLK_I2S3_B,
+	MT8173_CLK_BCK0,
+	MT8173_CLK_BCK1,
+	MT8173_CLK_NUM
+};
+
+#endif
diff --git a/sound/soc/mediatek/mtk-afe-pcm.c b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c
index 2b5df2ef51a3..8a643a35d3d4 100644
--- a/sound/soc/mediatek/mtk-afe-pcm.c
+++ b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c
@@ -1,5 +1,5 @@
 /*
- * Mediatek ALSA SoC AFE platform driver
+ * Mediatek 8173 ALSA SoC AFE platform driver
  *
  * Copyright (c) 2015 MediaTek Inc.
  * Author: Koro Chen <koro.chen@mediatek.com>
@@ -24,7 +24,10 @@
 #include <linux/dma-mapping.h>
 #include <linux/pm_runtime.h>
 #include <sound/soc.h>
-#include "mtk-afe-common.h"
+#include "mt8173-afe-common.h"
+#include "../common/mtk-base-afe.h"
+#include "../common/mtk-afe-platform-driver.h"
+#include "../common/mtk-afe-fe-dai.h"
 
 /*****************************************************************************
  *                  R E G I S T E R       D E F I N I T I O N
@@ -81,7 +84,6 @@
 #define AFE_TDM_CON1		0x0548
 #define AFE_TDM_CON2		0x054c
 
-#define AFE_BASE_END_OFFSET	8
 #define AFE_IRQ_STATUS_BITS	0xff
 
 /* AUDIO_TOP_CON0 (0x0000) */
@@ -135,7 +137,7 @@ enum afe_tdm_ch_start {
 	AFE_TDM_CH_ZERO,
 };
 
-static const unsigned int mtk_afe_backup_list[] = {
+static const unsigned int mt8173_afe_backup_list[] = {
 	AUDIO_TOP_CON0,
 	AFE_CONN1,
 	AFE_CONN2,
@@ -152,18 +154,11 @@ static const unsigned int mtk_afe_backup_list[] = {
 	AFE_DAC_CON0,
 };
 
-struct mtk_afe {
-	/* address for ioremap audio hardware register */
-	void __iomem *base_addr;
-	struct device *dev;
-	struct regmap *regmap;
-	struct mtk_afe_memif memif[MTK_AFE_MEMIF_NUM];
-	struct clk *clocks[MTK_CLK_NUM];
-	unsigned int backup_regs[ARRAY_SIZE(mtk_afe_backup_list)];
-	bool suspended;
+struct mt8173_afe_private {
+	struct clk *clocks[MT8173_CLK_NUM];
 };
 
-static const struct snd_pcm_hardware mtk_afe_hardware = {
+static const struct snd_pcm_hardware mt8173_afe_hardware = {
 	.info = (SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_INTERLEAVED |
 		 SNDRV_PCM_INFO_MMAP_VALID),
 	.buffer_bytes_max = 256 * 1024,
@@ -174,59 +169,12 @@ static const struct snd_pcm_hardware mtk_afe_hardware = {
 	.fifo_size = 0,
 };
 
-static snd_pcm_uframes_t mtk_afe_pcm_pointer
-			 (struct snd_pcm_substream *substream)
-{
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
-	struct mtk_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
-	unsigned int hw_ptr;
-	int ret;
-
-	ret = regmap_read(afe->regmap, memif->data->reg_ofs_cur, &hw_ptr);
-	if (ret || hw_ptr == 0) {
-		dev_err(afe->dev, "%s hw_ptr err\n", __func__);
-		hw_ptr = memif->phys_buf_addr;
-	}
-
-	return bytes_to_frames(substream->runtime,
-			       hw_ptr - memif->phys_buf_addr);
-}
-
-static const struct snd_pcm_ops mtk_afe_pcm_ops = {
-	.ioctl = snd_pcm_lib_ioctl,
-	.pointer = mtk_afe_pcm_pointer,
-};
-
-static int mtk_afe_pcm_new(struct snd_soc_pcm_runtime *rtd)
-{
-	size_t size;
-	struct snd_card *card = rtd->card->snd_card;
-	struct snd_pcm *pcm = rtd->pcm;
-
-	size = mtk_afe_hardware.buffer_bytes_max;
-
-	return snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
-						     card->dev, size, size);
-}
-
-static void mtk_afe_pcm_free(struct snd_pcm *pcm)
-{
-	snd_pcm_lib_preallocate_free_for_all(pcm);
-}
-
-static const struct snd_soc_platform_driver mtk_afe_pcm_platform = {
-	.ops = &mtk_afe_pcm_ops,
-	.pcm_new = mtk_afe_pcm_new,
-	.pcm_free = mtk_afe_pcm_free,
-};
-
-struct mtk_afe_rate {
+struct mt8173_afe_rate {
 	unsigned int rate;
 	unsigned int regvalue;
 };
 
-static const struct mtk_afe_rate mtk_afe_i2s_rates[] = {
+static const struct mt8173_afe_rate mt8173_afe_i2s_rates[] = {
 	{ .rate = 8000, .regvalue = 0 },
 	{ .rate = 11025, .regvalue = 1 },
 	{ .rate = 12000, .regvalue = 2 },
@@ -242,21 +190,21 @@ static const struct mtk_afe_rate mtk_afe_i2s_rates[] = {
 	{ .rate = 192000, .regvalue = 14 },
 };
 
-static int mtk_afe_i2s_fs(unsigned int sample_rate)
+static int mt8173_afe_i2s_fs(unsigned int sample_rate)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(mtk_afe_i2s_rates); i++)
-		if (mtk_afe_i2s_rates[i].rate == sample_rate)
-			return mtk_afe_i2s_rates[i].regvalue;
+	for (i = 0; i < ARRAY_SIZE(mt8173_afe_i2s_rates); i++)
+		if (mt8173_afe_i2s_rates[i].rate == sample_rate)
+			return mt8173_afe_i2s_rates[i].regvalue;
 
 	return -EINVAL;
 }
 
-static int mtk_afe_set_i2s(struct mtk_afe *afe, unsigned int rate)
+static int mt8173_afe_set_i2s(struct mtk_base_afe *afe, unsigned int rate)
 {
 	unsigned int val;
-	int fs = mtk_afe_i2s_fs(rate);
+	int fs = mt8173_afe_i2s_fs(rate);
 
 	if (fs < 0)
 		return -EINVAL;
@@ -281,7 +229,7 @@ static int mtk_afe_set_i2s(struct mtk_afe *afe, unsigned int rate)
 	return 0;
 }
 
-static void mtk_afe_set_i2s_enable(struct mtk_afe *afe, bool enable)
+static void mt8173_afe_set_i2s_enable(struct mtk_base_afe *afe, bool enable)
 {
 	unsigned int val;
 
@@ -296,8 +244,8 @@ static void mtk_afe_set_i2s_enable(struct mtk_afe *afe, bool enable)
 	regmap_update_bits(afe->regmap, AFE_I2S_CON1, 0x1, enable);
 }
 
-static int mtk_afe_dais_enable_clks(struct mtk_afe *afe,
-				    struct clk *m_ck, struct clk *b_ck)
+static int mt8173_afe_dais_enable_clks(struct mtk_base_afe *afe,
+				       struct clk *m_ck, struct clk *b_ck)
 {
 	int ret;
 
@@ -319,9 +267,9 @@ static int mtk_afe_dais_enable_clks(struct mtk_afe *afe,
 	return 0;
 }
 
-static int mtk_afe_dais_set_clks(struct mtk_afe *afe,
-				 struct clk *m_ck, unsigned int mck_rate,
-				 struct clk *b_ck, unsigned int bck_rate)
+static int mt8173_afe_dais_set_clks(struct mtk_base_afe *afe,
+				    struct clk *m_ck, unsigned int mck_rate,
+				    struct clk *b_ck, unsigned int bck_rate)
 {
 	int ret;
 
@@ -343,8 +291,8 @@ static int mtk_afe_dais_set_clks(struct mtk_afe *afe,
 	return 0;
 }
 
-static void mtk_afe_dais_disable_clks(struct mtk_afe *afe,
-				      struct clk *m_ck, struct clk *b_ck)
+static void mt8173_afe_dais_disable_clks(struct mtk_base_afe *afe,
+					 struct clk *m_ck, struct clk *b_ck)
 {
 	if (m_ck)
 		clk_disable_unprepare(m_ck);
@@ -352,102 +300,101 @@ static void mtk_afe_dais_disable_clks(struct mtk_afe *afe,
 		clk_disable_unprepare(b_ck);
 }
 
-static int mtk_afe_i2s_startup(struct snd_pcm_substream *substream,
-			       struct snd_soc_dai *dai)
+static int mt8173_afe_i2s_startup(struct snd_pcm_substream *substream,
+				  struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
 
 	if (dai->active)
 		return 0;
 
-	mtk_afe_dais_enable_clks(afe, afe->clocks[MTK_CLK_I2S1_M], NULL);
-	mtk_afe_dais_enable_clks(afe, afe->clocks[MTK_CLK_I2S2_M], NULL);
 	regmap_update_bits(afe->regmap, AUDIO_TOP_CON0,
 			   AUD_TCON0_PDN_22M | AUD_TCON0_PDN_24M, 0);
 	return 0;
 }
 
-static void mtk_afe_i2s_shutdown(struct snd_pcm_substream *substream,
-				 struct snd_soc_dai *dai)
+static void mt8173_afe_i2s_shutdown(struct snd_pcm_substream *substream,
+				    struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
 
 	if (dai->active)
 		return;
 
-	mtk_afe_set_i2s_enable(afe, false);
+	mt8173_afe_set_i2s_enable(afe, false);
 	regmap_update_bits(afe->regmap, AUDIO_TOP_CON0,
 			   AUD_TCON0_PDN_22M | AUD_TCON0_PDN_24M,
 			   AUD_TCON0_PDN_22M | AUD_TCON0_PDN_24M);
-	mtk_afe_dais_disable_clks(afe, afe->clocks[MTK_CLK_I2S1_M], NULL);
-	mtk_afe_dais_disable_clks(afe, afe->clocks[MTK_CLK_I2S2_M], NULL);
 }
 
-static int mtk_afe_i2s_prepare(struct snd_pcm_substream *substream,
-			       struct snd_soc_dai *dai)
+static int mt8173_afe_i2s_prepare(struct snd_pcm_substream *substream,
+				  struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime * const runtime = substream->runtime;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt8173_afe_private *afe_priv = afe->platform_priv;
 	int ret;
 
-	mtk_afe_dais_set_clks(afe,
-			      afe->clocks[MTK_CLK_I2S1_M], runtime->rate * 256,
-			      NULL, 0);
-	mtk_afe_dais_set_clks(afe,
-			      afe->clocks[MTK_CLK_I2S2_M], runtime->rate * 256,
-			      NULL, 0);
+	mt8173_afe_dais_set_clks(afe, afe_priv->clocks[MT8173_CLK_I2S1_M],
+				 runtime->rate * 256, NULL, 0);
+	mt8173_afe_dais_set_clks(afe, afe_priv->clocks[MT8173_CLK_I2S2_M],
+				 runtime->rate * 256, NULL, 0);
 	/* config I2S */
-	ret = mtk_afe_set_i2s(afe, substream->runtime->rate);
+	ret = mt8173_afe_set_i2s(afe, substream->runtime->rate);
 	if (ret)
 		return ret;
 
-	mtk_afe_set_i2s_enable(afe, true);
+	mt8173_afe_set_i2s_enable(afe, true);
 
 	return 0;
 }
 
-static int mtk_afe_hdmi_startup(struct snd_pcm_substream *substream,
-				struct snd_soc_dai *dai)
+static int mt8173_afe_hdmi_startup(struct snd_pcm_substream *substream,
+				   struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt8173_afe_private *afe_priv = afe->platform_priv;
 
 	if (dai->active)
 		return 0;
 
-	mtk_afe_dais_enable_clks(afe, afe->clocks[MTK_CLK_I2S3_M],
-				 afe->clocks[MTK_CLK_I2S3_B]);
+	mt8173_afe_dais_enable_clks(afe, afe_priv->clocks[MT8173_CLK_I2S3_M],
+				    afe_priv->clocks[MT8173_CLK_I2S3_B]);
 	return 0;
 }
 
-static void mtk_afe_hdmi_shutdown(struct snd_pcm_substream *substream,
-				  struct snd_soc_dai *dai)
+static void mt8173_afe_hdmi_shutdown(struct snd_pcm_substream *substream,
+				     struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt8173_afe_private *afe_priv = afe->platform_priv;
 
 	if (dai->active)
 		return;
 
-	mtk_afe_dais_disable_clks(afe, afe->clocks[MTK_CLK_I2S3_M],
-				  afe->clocks[MTK_CLK_I2S3_B]);
+	mt8173_afe_dais_disable_clks(afe, afe_priv->clocks[MT8173_CLK_I2S3_M],
+				     afe_priv->clocks[MT8173_CLK_I2S3_B]);
 }
 
-static int mtk_afe_hdmi_prepare(struct snd_pcm_substream *substream,
-				struct snd_soc_dai *dai)
+static int mt8173_afe_hdmi_prepare(struct snd_pcm_substream *substream,
+				   struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime * const runtime = substream->runtime;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mt8173_afe_private *afe_priv = afe->platform_priv;
+
 	unsigned int val;
 
-	mtk_afe_dais_set_clks(afe,
-			      afe->clocks[MTK_CLK_I2S3_M], runtime->rate * 128,
-			      afe->clocks[MTK_CLK_I2S3_B],
-			      runtime->rate * runtime->channels * 32);
+	mt8173_afe_dais_set_clks(afe, afe_priv->clocks[MT8173_CLK_I2S3_M],
+				 runtime->rate * 128,
+				 afe_priv->clocks[MT8173_CLK_I2S3_B],
+				 runtime->rate * runtime->channels * 32);
 
 	val = AFE_TDM_CON1_BCK_INV |
 	      AFE_TDM_CON1_LRCK_INV |
@@ -498,11 +445,11 @@ static int mtk_afe_hdmi_prepare(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int mtk_afe_hdmi_trigger(struct snd_pcm_substream *substream, int cmd,
-				struct snd_soc_dai *dai)
+static int mt8173_afe_hdmi_trigger(struct snd_pcm_substream *substream, int cmd,
+				   struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
 
 	dev_info(afe->dev, "%s cmd=%d %s\n", __func__, cmd, dai->name);
 
@@ -514,10 +461,14 @@ static int mtk_afe_hdmi_trigger(struct snd_pcm_substream *substream, int cmd,
 
 		/* set connections:  O30~O37: L/R/LS/RS/C/LFE/CH7/CH8 */
 		regmap_write(afe->regmap, AFE_HDMI_CONN0,
-			     AFE_HDMI_CONN0_O30_I30 | AFE_HDMI_CONN0_O31_I31 |
-			     AFE_HDMI_CONN0_O32_I34 | AFE_HDMI_CONN0_O33_I35 |
-			     AFE_HDMI_CONN0_O34_I32 | AFE_HDMI_CONN0_O35_I33 |
-			     AFE_HDMI_CONN0_O36_I36 | AFE_HDMI_CONN0_O37_I37);
+				 AFE_HDMI_CONN0_O30_I30 |
+				 AFE_HDMI_CONN0_O31_I31 |
+				 AFE_HDMI_CONN0_O32_I34 |
+				 AFE_HDMI_CONN0_O33_I35 |
+				 AFE_HDMI_CONN0_O34_I32 |
+				 AFE_HDMI_CONN0_O35_I33 |
+				 AFE_HDMI_CONN0_O36_I36 |
+				 AFE_HDMI_CONN0_O37_I37);
 
 		/* enable Out control */
 		regmap_update_bits(afe->regmap, AFE_HDMI_OUT_CON0, 0x1, 0x1);
@@ -537,284 +488,65 @@ static int mtk_afe_hdmi_trigger(struct snd_pcm_substream *substream, int cmd,
 		regmap_update_bits(afe->regmap, AUDIO_TOP_CON0,
 				   AUD_TCON0_PDN_HDMI | AUD_TCON0_PDN_SPDF,
 				   AUD_TCON0_PDN_HDMI | AUD_TCON0_PDN_SPDF);
-
 		return 0;
 	default:
 		return -EINVAL;
 	}
 }
 
-static int mtk_afe_dais_startup(struct snd_pcm_substream *substream,
-				struct snd_soc_dai *dai)
-{
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct mtk_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
-	int ret;
-
-	memif->substream = substream;
-
-	snd_soc_set_runtime_hwparams(substream, &mtk_afe_hardware);
-
-	/*
-	 * Capture cannot use ping-pong buffer since hw_ptr at IRQ may be
-	 * smaller than period_size due to AFE's internal buffer.
-	 * This easily leads to overrun when avail_min is period_size.
-	 * One more period can hold the possible unread buffer.
-	 */
-	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
-		ret = snd_pcm_hw_constraint_minmax(runtime,
-						   SNDRV_PCM_HW_PARAM_PERIODS,
-						   3,
-						   mtk_afe_hardware.periods_max);
-		if (ret < 0) {
-			dev_err(afe->dev, "hw_constraint_minmax failed\n");
-			return ret;
-		}
-	}
-	ret = snd_pcm_hw_constraint_integer(runtime,
-					    SNDRV_PCM_HW_PARAM_PERIODS);
-	if (ret < 0)
-		dev_err(afe->dev, "snd_pcm_hw_constraint_integer failed\n");
-	return ret;
-}
-
-static void mtk_afe_dais_shutdown(struct snd_pcm_substream *substream,
-				  struct snd_soc_dai *dai)
+static int mt8173_memif_fs(struct snd_pcm_substream *substream,
+			   unsigned int rate)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
-	struct mtk_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
-
-	memif->substream = NULL;
-}
-
-static int mtk_afe_dais_hw_params(struct snd_pcm_substream *substream,
-				  struct snd_pcm_hw_params *params,
-				  struct snd_soc_dai *dai)
-{
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
-	struct mtk_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
-	int msb_at_bit33 = 0;
-	int ret;
-
-	dev_dbg(afe->dev,
-		"%s period = %u, rate= %u, channels=%u\n",
-		__func__, params_period_size(params), params_rate(params),
-		params_channels(params));
+	struct mtk_base_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
+	struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
+	int fs;
 
-	ret = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(params));
-	if (ret < 0)
-		return ret;
-
-	msb_at_bit33 = upper_32_bits(substream->runtime->dma_addr) ? 1 : 0;
-	memif->phys_buf_addr = lower_32_bits(substream->runtime->dma_addr);
-	memif->buffer_size = substream->runtime->dma_bytes;
-
-	/* start */
-	regmap_write(afe->regmap,
-		     memif->data->reg_ofs_base, memif->phys_buf_addr);
-	/* end */
-	regmap_write(afe->regmap,
-		     memif->data->reg_ofs_base + AFE_BASE_END_OFFSET,
-		     memif->phys_buf_addr + memif->buffer_size - 1);
-
-	/* set MSB to 33-bit */
-	regmap_update_bits(afe->regmap, AFE_MEMIF_MSB,
-			   1 << memif->data->msb_shift,
-			   msb_at_bit33 << memif->data->msb_shift);
-
-	/* set channel */
-	if (memif->data->mono_shift >= 0) {
-		unsigned int mono = (params_channels(params) == 1) ? 1 : 0;
-
-		regmap_update_bits(afe->regmap, AFE_DAC_CON1,
-				   1 << memif->data->mono_shift,
-				   mono << memif->data->mono_shift);
-	}
-
-	/* set rate */
-	if (memif->data->fs_shift < 0)
-		return 0;
-	if (memif->data->id == MTK_AFE_MEMIF_DAI ||
-	    memif->data->id == MTK_AFE_MEMIF_MOD_DAI) {
-		unsigned int val;
-
-		switch (params_rate(params)) {
+	if (memif->data->id == MT8173_AFE_MEMIF_DAI ||
+	    memif->data->id == MT8173_AFE_MEMIF_MOD_DAI) {
+		switch (rate) {
 		case 8000:
-			val = 0;
+			fs = 0;
 			break;
 		case 16000:
-			val = 1;
+			fs = 1;
 			break;
 		case 32000:
-			val = 2;
+			fs = 2;
 			break;
 		default:
 			return -EINVAL;
 		}
-
-		if (memif->data->id == MTK_AFE_MEMIF_DAI)
-			regmap_update_bits(afe->regmap, AFE_DAC_CON0,
-					   0x3 << memif->data->fs_shift,
-					   val << memif->data->fs_shift);
-		else
-			regmap_update_bits(afe->regmap, AFE_DAC_CON1,
-					   0x3 << memif->data->fs_shift,
-					   val << memif->data->fs_shift);
-
 	} else {
-		int fs = mtk_afe_i2s_fs(params_rate(params));
-
-		if (fs < 0)
-			return -EINVAL;
-
-		regmap_update_bits(afe->regmap, AFE_DAC_CON1,
-				   0xf << memif->data->fs_shift,
-				   fs << memif->data->fs_shift);
+		fs = mt8173_afe_i2s_fs(rate);
 	}
-
-	return 0;
+	return fs;
 }
 
-static int mtk_afe_dais_hw_free(struct snd_pcm_substream *substream,
-				struct snd_soc_dai *dai)
+static int mt8173_irq_fs(struct snd_pcm_substream *substream, unsigned int rate)
 {
-	return snd_pcm_lib_free_pages(substream);
+	return mt8173_afe_i2s_fs(rate);
 }
 
-static int mtk_afe_dais_trigger(struct snd_pcm_substream *substream, int cmd,
-				struct snd_soc_dai *dai)
-{
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_pcm_runtime * const runtime = substream->runtime;
-	struct mtk_afe *afe = snd_soc_platform_get_drvdata(rtd->platform);
-	struct mtk_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
-	unsigned int counter = runtime->period_size;
-
-	dev_info(afe->dev, "%s %s cmd=%d\n", __func__, memif->data->name, cmd);
-
-	switch (cmd) {
-	case SNDRV_PCM_TRIGGER_START:
-	case SNDRV_PCM_TRIGGER_RESUME:
-		if (memif->data->enable_shift >= 0)
-			regmap_update_bits(afe->regmap, AFE_DAC_CON0,
-					   1 << memif->data->enable_shift,
-					   1 << memif->data->enable_shift);
-
-		/* set irq counter */
-		regmap_update_bits(afe->regmap,
-				   memif->data->irq_reg_cnt,
-				   0x3ffff << memif->data->irq_cnt_shift,
-				   counter << memif->data->irq_cnt_shift);
-
-		/* set irq fs */
-		if (memif->data->irq_fs_shift >= 0) {
-			int fs = mtk_afe_i2s_fs(runtime->rate);
-
-			if (fs < 0)
-				return -EINVAL;
-
-			regmap_update_bits(afe->regmap,
-					   AFE_IRQ_MCU_CON,
-					   0xf << memif->data->irq_fs_shift,
-					   fs << memif->data->irq_fs_shift);
-		}
-		/* enable interrupt */
-		regmap_update_bits(afe->regmap, AFE_IRQ_MCU_CON,
-				   1 << memif->data->irq_en_shift,
-				   1 << memif->data->irq_en_shift);
-
-		return 0;
-	case SNDRV_PCM_TRIGGER_STOP:
-	case SNDRV_PCM_TRIGGER_SUSPEND:
-		if (memif->data->enable_shift >= 0)
-			regmap_update_bits(afe->regmap, AFE_DAC_CON0,
-					   1 << memif->data->enable_shift, 0);
-		/* disable interrupt */
-		regmap_update_bits(afe->regmap, AFE_IRQ_MCU_CON,
-				   1 << memif->data->irq_en_shift,
-				   0 << memif->data->irq_en_shift);
-		/* and clear pending IRQ */
-		regmap_write(afe->regmap, AFE_IRQ_CLR,
-			     1 << memif->data->irq_clr_shift);
-		return 0;
-	default:
-		return -EINVAL;
-	}
-}
-
-/* FE DAIs */
-static const struct snd_soc_dai_ops mtk_afe_dai_ops = {
-	.startup	= mtk_afe_dais_startup,
-	.shutdown	= mtk_afe_dais_shutdown,
-	.hw_params	= mtk_afe_dais_hw_params,
-	.hw_free	= mtk_afe_dais_hw_free,
-	.trigger	= mtk_afe_dais_trigger,
-};
-
 /* BE DAIs */
-static const struct snd_soc_dai_ops mtk_afe_i2s_ops = {
-	.startup	= mtk_afe_i2s_startup,
-	.shutdown	= mtk_afe_i2s_shutdown,
-	.prepare	= mtk_afe_i2s_prepare,
+static const struct snd_soc_dai_ops mt8173_afe_i2s_ops = {
+	.startup	= mt8173_afe_i2s_startup,
+	.shutdown	= mt8173_afe_i2s_shutdown,
+	.prepare	= mt8173_afe_i2s_prepare,
 };
 
-static const struct snd_soc_dai_ops mtk_afe_hdmi_ops = {
-	.startup	= mtk_afe_hdmi_startup,
-	.shutdown	= mtk_afe_hdmi_shutdown,
-	.prepare	= mtk_afe_hdmi_prepare,
-	.trigger	= mtk_afe_hdmi_trigger,
-
+static const struct snd_soc_dai_ops mt8173_afe_hdmi_ops = {
+	.startup	= mt8173_afe_hdmi_startup,
+	.shutdown	= mt8173_afe_hdmi_shutdown,
+	.prepare	= mt8173_afe_hdmi_prepare,
+	.trigger	= mt8173_afe_hdmi_trigger,
 };
 
-static int mtk_afe_runtime_suspend(struct device *dev);
-static int mtk_afe_runtime_resume(struct device *dev);
-
-static int mtk_afe_dai_suspend(struct snd_soc_dai *dai)
-{
-	struct mtk_afe *afe = snd_soc_dai_get_drvdata(dai);
-	int i;
-
-	dev_dbg(afe->dev, "%s\n", __func__);
-	if (pm_runtime_status_suspended(afe->dev) || afe->suspended)
-		return 0;
-
-	for (i = 0; i < ARRAY_SIZE(mtk_afe_backup_list); i++)
-		regmap_read(afe->regmap, mtk_afe_backup_list[i],
-			    &afe->backup_regs[i]);
-
-	afe->suspended = true;
-	mtk_afe_runtime_suspend(afe->dev);
-	return 0;
-}
-
-static int mtk_afe_dai_resume(struct snd_soc_dai *dai)
-{
-	struct mtk_afe *afe = snd_soc_dai_get_drvdata(dai);
-	int i = 0;
-
-	dev_dbg(afe->dev, "%s\n", __func__);
-	if (pm_runtime_status_suspended(afe->dev) || !afe->suspended)
-		return 0;
-
-	mtk_afe_runtime_resume(afe->dev);
-
-	for (i = 0; i < ARRAY_SIZE(mtk_afe_backup_list); i++)
-		regmap_write(afe->regmap, mtk_afe_backup_list[i],
-			     afe->backup_regs[i]);
-
-	afe->suspended = false;
-	return 0;
-}
-
-static struct snd_soc_dai_driver mtk_afe_pcm_dais[] = {
+static struct snd_soc_dai_driver mt8173_afe_pcm_dais[] = {
 	/* FE DAIs: memory intefaces to CPU */
 	{
 		.name = "DL1", /* downlink 1 */
-		.id = MTK_AFE_MEMIF_DL1,
+		.id = MT8173_AFE_MEMIF_DL1,
 		.suspend = mtk_afe_dai_suspend,
 		.resume = mtk_afe_dai_resume,
 		.playback = {
@@ -824,10 +556,10 @@ static struct snd_soc_dai_driver mtk_afe_pcm_dais[] = {
 			.rates = SNDRV_PCM_RATE_8000_48000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
 		},
-		.ops = &mtk_afe_dai_ops,
+		.ops = &mtk_afe_fe_ops,
 	}, {
 		.name = "VUL", /* voice uplink */
-		.id = MTK_AFE_MEMIF_VUL,
+		.id = MT8173_AFE_MEMIF_VUL,
 		.suspend = mtk_afe_dai_suspend,
 		.resume = mtk_afe_dai_resume,
 		.capture = {
@@ -837,11 +569,11 @@ static struct snd_soc_dai_driver mtk_afe_pcm_dais[] = {
 			.rates = SNDRV_PCM_RATE_8000_48000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
 		},
-		.ops = &mtk_afe_dai_ops,
+		.ops = &mtk_afe_fe_ops,
 	}, {
 	/* BE DAIs */
 		.name = "I2S",
-		.id = MTK_AFE_IO_I2S,
+		.id = MT8173_AFE_IO_I2S,
 		.playback = {
 			.stream_name = "I2S Playback",
 			.channels_min = 1,
@@ -856,16 +588,16 @@ static struct snd_soc_dai_driver mtk_afe_pcm_dais[] = {
 			.rates = SNDRV_PCM_RATE_8000_48000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
 		},
-		.ops = &mtk_afe_i2s_ops,
+		.ops = &mt8173_afe_i2s_ops,
 		.symmetric_rates = 1,
 	},
 };
 
-static struct snd_soc_dai_driver mtk_afe_hdmi_dais[] = {
+static struct snd_soc_dai_driver mt8173_afe_hdmi_dais[] = {
 	/* FE DAIs */
 	{
 		.name = "HDMI",
-		.id = MTK_AFE_MEMIF_HDMI,
+		.id = MT8173_AFE_MEMIF_HDMI,
 		.suspend = mtk_afe_dai_suspend,
 		.resume = mtk_afe_dai_resume,
 		.playback = {
@@ -878,11 +610,11 @@ static struct snd_soc_dai_driver mtk_afe_hdmi_dais[] = {
 				SNDRV_PCM_RATE_192000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
 		},
-		.ops = &mtk_afe_dai_ops,
+		.ops = &mtk_afe_fe_ops,
 	}, {
 	/* BE DAIs */
 		.name = "HDMIO",
-		.id = MTK_AFE_IO_HDMI,
+		.id = MT8173_AFE_IO_HDMI,
 		.playback = {
 			.stream_name = "HDMIO Playback",
 			.channels_min = 2,
@@ -893,29 +625,29 @@ static struct snd_soc_dai_driver mtk_afe_hdmi_dais[] = {
 				SNDRV_PCM_RATE_192000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
 		},
-		.ops = &mtk_afe_hdmi_ops,
+		.ops = &mt8173_afe_hdmi_ops,
 	},
 };
 
-static const struct snd_kcontrol_new mtk_afe_o03_mix[] = {
+static const struct snd_kcontrol_new mt8173_afe_o03_mix[] = {
 	SOC_DAPM_SINGLE_AUTODISABLE("I05 Switch", AFE_CONN1, 21, 1, 0),
 };
 
-static const struct snd_kcontrol_new mtk_afe_o04_mix[] = {
+static const struct snd_kcontrol_new mt8173_afe_o04_mix[] = {
 	SOC_DAPM_SINGLE_AUTODISABLE("I06 Switch", AFE_CONN2, 6, 1, 0),
 };
 
-static const struct snd_kcontrol_new mtk_afe_o09_mix[] = {
+static const struct snd_kcontrol_new mt8173_afe_o09_mix[] = {
 	SOC_DAPM_SINGLE_AUTODISABLE("I03 Switch", AFE_CONN3, 0, 1, 0),
 	SOC_DAPM_SINGLE_AUTODISABLE("I17 Switch", AFE_CONN7, 30, 1, 0),
 };
 
-static const struct snd_kcontrol_new mtk_afe_o10_mix[] = {
+static const struct snd_kcontrol_new mt8173_afe_o10_mix[] = {
 	SOC_DAPM_SINGLE_AUTODISABLE("I04 Switch", AFE_CONN3, 3, 1, 0),
 	SOC_DAPM_SINGLE_AUTODISABLE("I18 Switch", AFE_CONN8, 0, 1, 0),
 };
 
-static const struct snd_soc_dapm_widget mtk_afe_pcm_widgets[] = {
+static const struct snd_soc_dapm_widget mt8173_afe_pcm_widgets[] = {
 	/* inter-connections */
 	SND_SOC_DAPM_MIXER("I03", SND_SOC_NOPM, 0, 0, NULL, 0),
 	SND_SOC_DAPM_MIXER("I04", SND_SOC_NOPM, 0, 0, NULL, 0),
@@ -925,16 +657,16 @@ static const struct snd_soc_dapm_widget mtk_afe_pcm_widgets[] = {
 	SND_SOC_DAPM_MIXER("I18", SND_SOC_NOPM, 0, 0, NULL, 0),
 
 	SND_SOC_DAPM_MIXER("O03", SND_SOC_NOPM, 0, 0,
-			   mtk_afe_o03_mix, ARRAY_SIZE(mtk_afe_o03_mix)),
+			   mt8173_afe_o03_mix, ARRAY_SIZE(mt8173_afe_o03_mix)),
 	SND_SOC_DAPM_MIXER("O04", SND_SOC_NOPM, 0, 0,
-			   mtk_afe_o04_mix, ARRAY_SIZE(mtk_afe_o04_mix)),
+			   mt8173_afe_o04_mix, ARRAY_SIZE(mt8173_afe_o04_mix)),
 	SND_SOC_DAPM_MIXER("O09", SND_SOC_NOPM, 0, 0,
-			   mtk_afe_o09_mix, ARRAY_SIZE(mtk_afe_o09_mix)),
+			   mt8173_afe_o09_mix, ARRAY_SIZE(mt8173_afe_o09_mix)),
 	SND_SOC_DAPM_MIXER("O10", SND_SOC_NOPM, 0, 0,
-			   mtk_afe_o10_mix, ARRAY_SIZE(mtk_afe_o10_mix)),
+			   mt8173_afe_o10_mix, ARRAY_SIZE(mt8173_afe_o10_mix)),
 };
 
-static const struct snd_soc_dapm_route mtk_afe_pcm_routes[] = {
+static const struct snd_soc_dapm_route mt8173_afe_pcm_routes[] = {
 	{"I05", NULL, "DL1"},
 	{"I06", NULL, "DL1"},
 	{"I2S Playback", NULL, "O03"},
@@ -953,140 +685,257 @@ static const struct snd_soc_dapm_route mtk_afe_pcm_routes[] = {
 	{ "O10", "I04 Switch", "I04" },
 };
 
-static const struct snd_soc_dapm_route mtk_afe_hdmi_routes[] = {
+static const struct snd_soc_dapm_route mt8173_afe_hdmi_routes[] = {
 	{"HDMIO Playback", NULL, "HDMI"},
 };
 
-static const struct snd_soc_component_driver mtk_afe_pcm_dai_component = {
-	.name = "mtk-afe-pcm-dai",
-	.dapm_widgets = mtk_afe_pcm_widgets,
-	.num_dapm_widgets = ARRAY_SIZE(mtk_afe_pcm_widgets),
-	.dapm_routes = mtk_afe_pcm_routes,
-	.num_dapm_routes = ARRAY_SIZE(mtk_afe_pcm_routes),
+static const struct snd_soc_component_driver mt8173_afe_pcm_dai_component = {
+	.name = "mt8173-afe-pcm-dai",
+	.dapm_widgets = mt8173_afe_pcm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(mt8173_afe_pcm_widgets),
+	.dapm_routes = mt8173_afe_pcm_routes,
+	.num_dapm_routes = ARRAY_SIZE(mt8173_afe_pcm_routes),
 };
 
-static const struct snd_soc_component_driver mtk_afe_hdmi_dai_component = {
-	.name = "mtk-afe-hdmi-dai",
-	.dapm_routes = mtk_afe_hdmi_routes,
-	.num_dapm_routes = ARRAY_SIZE(mtk_afe_hdmi_routes),
+static const struct snd_soc_component_driver mt8173_afe_hdmi_dai_component = {
+	.name = "mt8173-afe-hdmi-dai",
+	.dapm_routes = mt8173_afe_hdmi_routes,
+	.num_dapm_routes = ARRAY_SIZE(mt8173_afe_hdmi_routes),
 };
 
-static const char *aud_clks[MTK_CLK_NUM] = {
-	[MTK_CLK_INFRASYS_AUD] = "infra_sys_audio_clk",
-	[MTK_CLK_TOP_PDN_AUD] = "top_pdn_audio",
-	[MTK_CLK_TOP_PDN_AUD_BUS] = "top_pdn_aud_intbus",
-	[MTK_CLK_I2S0_M] =  "i2s0_m",
-	[MTK_CLK_I2S1_M] =  "i2s1_m",
-	[MTK_CLK_I2S2_M] =  "i2s2_m",
-	[MTK_CLK_I2S3_M] =  "i2s3_m",
-	[MTK_CLK_I2S3_B] =  "i2s3_b",
-	[MTK_CLK_BCK0] =  "bck0",
-	[MTK_CLK_BCK1] =  "bck1",
+static const char *aud_clks[MT8173_CLK_NUM] = {
+	[MT8173_CLK_INFRASYS_AUD] = "infra_sys_audio_clk",
+	[MT8173_CLK_TOP_PDN_AUD] = "top_pdn_audio",
+	[MT8173_CLK_TOP_PDN_AUD_BUS] = "top_pdn_aud_intbus",
+	[MT8173_CLK_I2S0_M] =  "i2s0_m",
+	[MT8173_CLK_I2S1_M] =  "i2s1_m",
+	[MT8173_CLK_I2S2_M] =  "i2s2_m",
+	[MT8173_CLK_I2S3_M] =  "i2s3_m",
+	[MT8173_CLK_I2S3_B] =  "i2s3_b",
+	[MT8173_CLK_BCK0] =  "bck0",
+	[MT8173_CLK_BCK1] =  "bck1",
 };
 
-static const struct mtk_afe_memif_data memif_data[MTK_AFE_MEMIF_NUM] = {
+static const struct mtk_base_memif_data memif_data[MT8173_AFE_MEMIF_NUM] = {
 	{
 		.name = "DL1",
-		.id = MTK_AFE_MEMIF_DL1,
+		.id = MT8173_AFE_MEMIF_DL1,
 		.reg_ofs_base = AFE_DL1_BASE,
 		.reg_ofs_cur = AFE_DL1_CUR,
+		.fs_reg = AFE_DAC_CON1,
 		.fs_shift = 0,
+		.fs_maskbit = 0xf,
+		.mono_reg = AFE_DAC_CON1,
 		.mono_shift = 21,
+		.hd_reg = -1,
+		.hd_shift = -1,
+		.enable_reg = AFE_DAC_CON0,
 		.enable_shift = 1,
-		.irq_reg_cnt = AFE_IRQ_CNT1,
-		.irq_cnt_shift = 0,
-		.irq_en_shift = 0,
-		.irq_fs_shift = 4,
-		.irq_clr_shift = 0,
+		.msb_reg = AFE_MEMIF_MSB,
 		.msb_shift = 0,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
 	}, {
 		.name = "DL2",
-		.id = MTK_AFE_MEMIF_DL2,
+		.id = MT8173_AFE_MEMIF_DL2,
 		.reg_ofs_base = AFE_DL2_BASE,
 		.reg_ofs_cur = AFE_DL2_CUR,
+		.fs_reg = AFE_DAC_CON1,
 		.fs_shift = 4,
+		.fs_maskbit = 0xf,
+		.mono_reg = AFE_DAC_CON1,
 		.mono_shift = 22,
+		.hd_reg = -1,
+		.hd_shift = -1,
+		.enable_reg = AFE_DAC_CON0,
 		.enable_shift = 2,
-		.irq_reg_cnt = AFE_IRQ_CNT1,
-		.irq_cnt_shift = 20,
-		.irq_en_shift = 2,
-		.irq_fs_shift = 16,
-		.irq_clr_shift = 2,
+		.msb_reg = AFE_MEMIF_MSB,
 		.msb_shift = 1,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
 	}, {
 		.name = "VUL",
-		.id = MTK_AFE_MEMIF_VUL,
+		.id = MT8173_AFE_MEMIF_VUL,
 		.reg_ofs_base = AFE_VUL_BASE,
 		.reg_ofs_cur = AFE_VUL_CUR,
+		.fs_reg = AFE_DAC_CON1,
 		.fs_shift = 16,
+		.fs_maskbit = 0xf,
+		.mono_reg = AFE_DAC_CON1,
 		.mono_shift = 27,
+		.hd_reg = -1,
+		.hd_shift = -1,
+		.enable_reg = AFE_DAC_CON0,
 		.enable_shift = 3,
-		.irq_reg_cnt = AFE_IRQ_CNT2,
-		.irq_cnt_shift = 0,
-		.irq_en_shift = 1,
-		.irq_fs_shift = 8,
-		.irq_clr_shift = 1,
+		.msb_reg = AFE_MEMIF_MSB,
 		.msb_shift = 6,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
 	}, {
 		.name = "DAI",
-		.id = MTK_AFE_MEMIF_DAI,
+		.id = MT8173_AFE_MEMIF_DAI,
 		.reg_ofs_base = AFE_DAI_BASE,
 		.reg_ofs_cur = AFE_DAI_CUR,
+		.fs_reg = AFE_DAC_CON0,
 		.fs_shift = 24,
+		.fs_maskbit = 0x3,
+		.mono_reg = -1,
 		.mono_shift = -1,
+		.hd_reg = -1,
+		.hd_shift = -1,
+		.enable_reg = AFE_DAC_CON0,
 		.enable_shift = 4,
-		.irq_reg_cnt = AFE_IRQ_CNT2,
-		.irq_cnt_shift = 20,
-		.irq_en_shift = 3,
-		.irq_fs_shift = 20,
-		.irq_clr_shift = 3,
+		.msb_reg = AFE_MEMIF_MSB,
 		.msb_shift = 5,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
 	}, {
 		.name = "AWB",
-		.id = MTK_AFE_MEMIF_AWB,
+		.id = MT8173_AFE_MEMIF_AWB,
 		.reg_ofs_base = AFE_AWB_BASE,
 		.reg_ofs_cur = AFE_AWB_CUR,
+		.fs_reg = AFE_DAC_CON1,
 		.fs_shift = 12,
+		.fs_maskbit = 0xf,
+		.mono_reg = AFE_DAC_CON1,
 		.mono_shift = 24,
+		.hd_reg = -1,
+		.hd_shift = -1,
+		.enable_reg = AFE_DAC_CON0,
 		.enable_shift = 6,
-		.irq_reg_cnt = AFE_IRQ_CNT7,
-		.irq_cnt_shift = 0,
-		.irq_en_shift = 14,
-		.irq_fs_shift = 24,
-		.irq_clr_shift = 6,
+		.msb_reg = AFE_MEMIF_MSB,
 		.msb_shift = 3,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
 	}, {
 		.name = "MOD_DAI",
-		.id = MTK_AFE_MEMIF_MOD_DAI,
+		.id = MT8173_AFE_MEMIF_MOD_DAI,
 		.reg_ofs_base = AFE_MOD_PCM_BASE,
 		.reg_ofs_cur = AFE_MOD_PCM_CUR,
+		.fs_reg = AFE_DAC_CON1,
 		.fs_shift = 30,
+		.fs_maskbit = 0x3,
+		.mono_reg = AFE_DAC_CON1,
 		.mono_shift = 30,
+		.hd_reg = -1,
+		.hd_shift = -1,
+		.enable_reg = AFE_DAC_CON0,
 		.enable_shift = 7,
-		.irq_reg_cnt = AFE_IRQ_CNT2,
-		.irq_cnt_shift = 20,
-		.irq_en_shift = 3,
-		.irq_fs_shift = 20,
-		.irq_clr_shift = 3,
+		.msb_reg = AFE_MEMIF_MSB,
 		.msb_shift = 4,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
 	}, {
 		.name = "HDMI",
-		.id = MTK_AFE_MEMIF_HDMI,
+		.id = MT8173_AFE_MEMIF_HDMI,
 		.reg_ofs_base = AFE_HDMI_OUT_BASE,
 		.reg_ofs_cur = AFE_HDMI_OUT_CUR,
+		.fs_reg = -1,
 		.fs_shift = -1,
+		.fs_maskbit = -1,
+		.mono_reg = -1,
 		.mono_shift = -1,
+		.hd_reg = -1,
+		.hd_shift = -1,
+		.enable_reg = -1,
 		.enable_shift = -1,
-		.irq_reg_cnt = AFE_IRQ_CNT5,
+		.msb_reg = AFE_MEMIF_MSB,
+		.msb_shift = 8,
+		.agent_disable_reg = -1,
+		.agent_disable_shift = -1,
+	},
+};
+
+static const struct mtk_base_irq_data irq_data[MT8173_AFE_IRQ_NUM] = {
+	{
+		.id = MT8173_AFE_IRQ_DL1,
+		.irq_cnt_reg = AFE_IRQ_CNT1,
+		.irq_cnt_shift = 0,
+		.irq_cnt_maskbit = 0x3ffff,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = 0,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = 4,
+		.irq_fs_maskbit = 0xf,
+		.irq_clr_reg = AFE_IRQ_CLR,
+		.irq_clr_shift = 0,
+	}, {
+		.id = MT8173_AFE_IRQ_DL2,
+		.irq_cnt_reg = AFE_IRQ_CNT1,
+		.irq_cnt_shift = 20,
+		.irq_cnt_maskbit = 0x3ffff,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = 2,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = 16,
+		.irq_fs_maskbit = 0xf,
+		.irq_clr_reg = AFE_IRQ_CLR,
+		.irq_clr_shift = 2,
+
+	}, {
+		.id = MT8173_AFE_IRQ_VUL,
+		.irq_cnt_reg = AFE_IRQ_CNT2,
+		.irq_cnt_shift = 0,
+		.irq_cnt_maskbit = 0x3ffff,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = 1,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = 8,
+		.irq_fs_maskbit = 0xf,
+		.irq_clr_reg = AFE_IRQ_CLR,
+		.irq_clr_shift = 1,
+	}, {
+		.id = MT8173_AFE_IRQ_DAI,
+		.irq_cnt_reg = AFE_IRQ_CNT2,
+		.irq_cnt_shift = 20,
+		.irq_cnt_maskbit = 0x3ffff,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = 3,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = 20,
+		.irq_fs_maskbit = 0xf,
+		.irq_clr_reg = AFE_IRQ_CLR,
+		.irq_clr_shift = 3,
+	}, {
+		.id = MT8173_AFE_IRQ_AWB,
+		.irq_cnt_reg = AFE_IRQ_CNT7,
 		.irq_cnt_shift = 0,
+		.irq_cnt_maskbit = 0x3ffff,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = 14,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = 24,
+		.irq_fs_maskbit = 0xf,
+		.irq_clr_reg = AFE_IRQ_CLR,
+		.irq_clr_shift = 6,
+	}, {
+		.id = MT8173_AFE_IRQ_DAI,
+		.irq_cnt_reg = AFE_IRQ_CNT2,
+		.irq_cnt_shift = 20,
+		.irq_cnt_maskbit = 0x3ffff,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
+		.irq_en_shift = 3,
+		.irq_fs_reg = AFE_IRQ_MCU_CON,
+		.irq_fs_shift = 20,
+		.irq_fs_maskbit = 0xf,
+		.irq_clr_reg = AFE_IRQ_CLR,
+		.irq_clr_shift = 3,
+	}, {
+		.id = MT8173_AFE_IRQ_HDMI,
+		.irq_cnt_reg = AFE_IRQ_CNT5,
+		.irq_cnt_shift = 0,
+		.irq_cnt_maskbit = 0x3ffff,
+		.irq_en_reg = AFE_IRQ_MCU_CON,
 		.irq_en_shift = 12,
+		.irq_fs_reg = -1,
 		.irq_fs_shift = -1,
+		.irq_fs_maskbit = -1,
+		.irq_clr_reg = AFE_IRQ_CLR,
 		.irq_clr_shift = 4,
-		.msb_shift = 8,
 	},
 };
 
-static const struct regmap_config mtk_afe_regmap_config = {
+static const struct regmap_config mt8173_afe_regmap_config = {
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
@@ -1094,9 +943,9 @@ static const struct regmap_config mtk_afe_regmap_config = {
 	.cache_type = REGCACHE_NONE,
 };
 
-static irqreturn_t mtk_afe_irq_handler(int irq, void *dev_id)
+static irqreturn_t mt8173_afe_irq_handler(int irq, void *dev_id)
 {
-	struct mtk_afe *afe = dev_id;
+	struct mtk_base_afe *afe = dev_id;
 	unsigned int reg_value;
 	int i, ret;
 
@@ -1107,10 +956,16 @@ static irqreturn_t mtk_afe_irq_handler(int irq, void *dev_id)
 		goto err_irq;
 	}
 
-	for (i = 0; i < MTK_AFE_MEMIF_NUM; i++) {
-		struct mtk_afe_memif *memif = &afe->memif[i];
+	for (i = 0; i < MT8173_AFE_MEMIF_NUM; i++) {
+		struct mtk_base_afe_memif *memif = &afe->memif[i];
+		struct mtk_base_afe_irq *irq;
 
-		if (!(reg_value & (1 << memif->data->irq_clr_shift)))
+		if (memif->irq_usage < 0)
+			continue;
+
+		irq = &afe->irqs[memif->irq_usage];
+
+		if (!(reg_value & (1 << irq->irq_data->irq_clr_shift)))
 			continue;
 
 		snd_pcm_period_elapsed(memif->substream);
@@ -1118,14 +973,16 @@ static irqreturn_t mtk_afe_irq_handler(int irq, void *dev_id)
 
 err_irq:
 	/* clear irq */
-	regmap_write(afe->regmap, AFE_IRQ_CLR, reg_value & AFE_IRQ_STATUS_BITS);
+	regmap_write(afe->regmap, AFE_IRQ_CLR,
+		     reg_value & AFE_IRQ_STATUS_BITS);
 
 	return IRQ_HANDLED;
 }
 
-static int mtk_afe_runtime_suspend(struct device *dev)
+static int mt8173_afe_runtime_suspend(struct device *dev)
 {
-	struct mtk_afe *afe = dev_get_drvdata(dev);
+	struct mtk_base_afe *afe = dev_get_drvdata(dev);
+	struct mt8173_afe_private *afe_priv = afe->platform_priv;
 
 	/* disable AFE */
 	regmap_update_bits(afe->regmap, AFE_DAC_CON0, 0x1, 0);
@@ -1134,38 +991,47 @@ static int mtk_afe_runtime_suspend(struct device *dev)
 	regmap_update_bits(afe->regmap, AUDIO_TOP_CON0,
 			   AUD_TCON0_PDN_AFE, AUD_TCON0_PDN_AFE);
 
-	clk_disable_unprepare(afe->clocks[MTK_CLK_BCK0]);
-	clk_disable_unprepare(afe->clocks[MTK_CLK_BCK1]);
-	clk_disable_unprepare(afe->clocks[MTK_CLK_TOP_PDN_AUD]);
-	clk_disable_unprepare(afe->clocks[MTK_CLK_TOP_PDN_AUD_BUS]);
-	clk_disable_unprepare(afe->clocks[MTK_CLK_INFRASYS_AUD]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_I2S1_M]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_I2S2_M]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_BCK0]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_BCK1]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_TOP_PDN_AUD]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_TOP_PDN_AUD_BUS]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_INFRASYS_AUD]);
 	return 0;
 }
 
-static int mtk_afe_runtime_resume(struct device *dev)
+static int mt8173_afe_runtime_resume(struct device *dev)
 {
-	struct mtk_afe *afe = dev_get_drvdata(dev);
+	struct mtk_base_afe *afe = dev_get_drvdata(dev);
+	struct mt8173_afe_private *afe_priv = afe->platform_priv;
 	int ret;
 
-	ret = clk_prepare_enable(afe->clocks[MTK_CLK_INFRASYS_AUD]);
+	ret = clk_prepare_enable(afe_priv->clocks[MT8173_CLK_INFRASYS_AUD]);
 	if (ret)
 		return ret;
 
-	ret = clk_prepare_enable(afe->clocks[MTK_CLK_TOP_PDN_AUD_BUS]);
+	ret = clk_prepare_enable(afe_priv->clocks[MT8173_CLK_TOP_PDN_AUD_BUS]);
 	if (ret)
 		goto err_infra;
 
-	ret = clk_prepare_enable(afe->clocks[MTK_CLK_TOP_PDN_AUD]);
+	ret = clk_prepare_enable(afe_priv->clocks[MT8173_CLK_TOP_PDN_AUD]);
 	if (ret)
 		goto err_top_aud_bus;
 
-	ret = clk_prepare_enable(afe->clocks[MTK_CLK_BCK0]);
+	ret = clk_prepare_enable(afe_priv->clocks[MT8173_CLK_BCK0]);
 	if (ret)
 		goto err_top_aud;
 
-	ret = clk_prepare_enable(afe->clocks[MTK_CLK_BCK1]);
+	ret = clk_prepare_enable(afe_priv->clocks[MT8173_CLK_BCK1]);
 	if (ret)
 		goto err_bck0;
+	ret = clk_prepare_enable(afe_priv->clocks[MT8173_CLK_I2S1_M]);
+	if (ret)
+		goto err_i2s1_m;
+	ret = clk_prepare_enable(afe_priv->clocks[MT8173_CLK_I2S2_M]);
+	if (ret)
+		goto err_i2s2_m;
 
 	/* enable AFE clk */
 	regmap_update_bits(afe->regmap, AUDIO_TOP_CON0, AUD_TCON0_PDN_AFE, 0);
@@ -1181,39 +1047,45 @@ static int mtk_afe_runtime_resume(struct device *dev)
 	regmap_update_bits(afe->regmap, AFE_DAC_CON0, 0x1, 0x1);
 	return 0;
 
+err_i2s1_m:
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_I2S1_M]);
+err_i2s2_m:
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_I2S2_M]);
 err_bck0:
-	clk_disable_unprepare(afe->clocks[MTK_CLK_BCK0]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_BCK0]);
 err_top_aud:
-	clk_disable_unprepare(afe->clocks[MTK_CLK_TOP_PDN_AUD]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_TOP_PDN_AUD]);
 err_top_aud_bus:
-	clk_disable_unprepare(afe->clocks[MTK_CLK_TOP_PDN_AUD_BUS]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_TOP_PDN_AUD_BUS]);
 err_infra:
-	clk_disable_unprepare(afe->clocks[MTK_CLK_INFRASYS_AUD]);
+	clk_disable_unprepare(afe_priv->clocks[MT8173_CLK_INFRASYS_AUD]);
 	return ret;
 }
 
-static int mtk_afe_init_audio_clk(struct mtk_afe *afe)
+static int mt8173_afe_init_audio_clk(struct mtk_base_afe *afe)
 {
 	size_t i;
+	struct mt8173_afe_private *afe_priv = afe->platform_priv;
 
 	for (i = 0; i < ARRAY_SIZE(aud_clks); i++) {
-		afe->clocks[i] = devm_clk_get(afe->dev, aud_clks[i]);
-		if (IS_ERR(afe->clocks[i])) {
+		afe_priv->clocks[i] = devm_clk_get(afe->dev, aud_clks[i]);
+		if (IS_ERR(afe_priv->clocks[i])) {
 			dev_err(afe->dev, "%s devm_clk_get %s fail\n",
 				__func__, aud_clks[i]);
-			return PTR_ERR(afe->clocks[i]);
+			return PTR_ERR(afe_priv->clocks[i]);
 		}
 	}
-	clk_set_rate(afe->clocks[MTK_CLK_BCK0], 22579200); /* 22M */
-	clk_set_rate(afe->clocks[MTK_CLK_BCK1], 24576000); /* 24M */
+	clk_set_rate(afe_priv->clocks[MT8173_CLK_BCK0], 22579200); /* 22M */
+	clk_set_rate(afe_priv->clocks[MT8173_CLK_BCK1], 24576000); /* 24M */
 	return 0;
 }
 
-static int mtk_afe_pcm_dev_probe(struct platform_device *pdev)
+static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev)
 {
 	int ret, i;
 	unsigned int irq_id;
-	struct mtk_afe *afe;
+	struct mtk_base_afe *afe;
+	struct mt8173_afe_private *afe_priv;
 	struct resource *res;
 
 	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(33));
@@ -1224,6 +1096,12 @@ static int mtk_afe_pcm_dev_probe(struct platform_device *pdev)
 	if (!afe)
 		return -ENOMEM;
 
+	afe->platform_priv = devm_kzalloc(&pdev->dev, sizeof(*afe_priv),
+					  GFP_KERNEL);
+	afe_priv = afe->platform_priv;
+	if (!afe_priv)
+		return -ENOMEM;
+
 	afe->dev = &pdev->dev;
 
 	irq_id = platform_get_irq(pdev, 0);
@@ -1231,7 +1109,7 @@ static int mtk_afe_pcm_dev_probe(struct platform_device *pdev)
 		dev_err(afe->dev, "np %s no irq\n", afe->dev->of_node->name);
 		return -ENXIO;
 	}
-	ret = devm_request_irq(afe->dev, irq_id, mtk_afe_irq_handler,
+	ret = devm_request_irq(afe->dev, irq_id, mt8173_afe_irq_handler,
 			       0, "Afe_ISR_Handle", (void *)afe);
 	if (ret) {
 		dev_err(afe->dev, "could not request_irq\n");
@@ -1244,48 +1122,75 @@ static int mtk_afe_pcm_dev_probe(struct platform_device *pdev)
 		return PTR_ERR(afe->base_addr);
 
 	afe->regmap = devm_regmap_init_mmio(&pdev->dev, afe->base_addr,
-		&mtk_afe_regmap_config);
+		&mt8173_afe_regmap_config);
 	if (IS_ERR(afe->regmap))
 		return PTR_ERR(afe->regmap);
 
 	/* initial audio related clock */
-	ret = mtk_afe_init_audio_clk(afe);
+	ret = mt8173_afe_init_audio_clk(afe);
 	if (ret) {
-		dev_err(afe->dev, "mtk_afe_init_audio_clk fail\n");
+		dev_err(afe->dev, "mt8173_afe_init_audio_clk fail\n");
 		return ret;
 	}
 
-	for (i = 0; i < MTK_AFE_MEMIF_NUM; i++)
+	/* memif % irq initialize*/
+	afe->memif_size = MT8173_AFE_MEMIF_NUM;
+	afe->memif = devm_kcalloc(afe->dev, afe->memif_size,
+				  sizeof(*afe->memif), GFP_KERNEL);
+	if (!afe->memif)
+		return -ENOMEM;
+
+	afe->irqs_size = MT8173_AFE_IRQ_NUM;
+	afe->irqs = devm_kcalloc(afe->dev, afe->irqs_size,
+				 sizeof(*afe->irqs), GFP_KERNEL);
+	if (!afe->irqs)
+		return -ENOMEM;
+
+	for (i = 0; i < afe->irqs_size; i++) {
 		afe->memif[i].data = &memif_data[i];
+		afe->irqs[i].irq_data = &irq_data[i];
+		afe->irqs[i].irq_occupyed = true;
+		afe->memif[i].irq_usage = i;
+		afe->memif[i].const_irq = 1;
+	}
+
+	afe->mtk_afe_hardware = &mt8173_afe_hardware;
+	afe->memif_fs = mt8173_memif_fs;
+	afe->irq_fs = mt8173_irq_fs;
 
 	platform_set_drvdata(pdev, afe);
 
 	pm_runtime_enable(&pdev->dev);
 	if (!pm_runtime_enabled(&pdev->dev)) {
-		ret = mtk_afe_runtime_resume(&pdev->dev);
+		ret = mt8173_afe_runtime_resume(&pdev->dev);
 		if (ret)
 			goto err_pm_disable;
 	}
 
+	afe->reg_back_up_list = mt8173_afe_backup_list;
+	afe->reg_back_up_list_num = ARRAY_SIZE(mt8173_afe_backup_list);
+	afe->runtime_resume = mt8173_afe_runtime_resume;
+	afe->runtime_suspend = mt8173_afe_runtime_suspend;
+
 	ret = snd_soc_register_platform(&pdev->dev, &mtk_afe_pcm_platform);
 	if (ret)
 		goto err_pm_disable;
 
 	ret = snd_soc_register_component(&pdev->dev,
-					 &mtk_afe_pcm_dai_component,
-					 mtk_afe_pcm_dais,
-					 ARRAY_SIZE(mtk_afe_pcm_dais));
+					 &mt8173_afe_pcm_dai_component,
+					 mt8173_afe_pcm_dais,
+					 ARRAY_SIZE(mt8173_afe_pcm_dais));
 	if (ret)
 		goto err_platform;
 
 	ret = snd_soc_register_component(&pdev->dev,
-					 &mtk_afe_hdmi_dai_component,
-					 mtk_afe_hdmi_dais,
-					 ARRAY_SIZE(mtk_afe_hdmi_dais));
+					 &mt8173_afe_hdmi_dai_component,
+					 mt8173_afe_hdmi_dais,
+					 ARRAY_SIZE(mt8173_afe_hdmi_dais));
 	if (ret)
 		goto err_comp;
 
-	dev_info(&pdev->dev, "MTK AFE driver initialized.\n");
+	dev_info(&pdev->dev, "MT8173 AFE driver initialized.\n");
 	return 0;
 
 err_comp:
@@ -1297,38 +1202,38 @@ err_pm_disable:
 	return ret;
 }
 
-static int mtk_afe_pcm_dev_remove(struct platform_device *pdev)
+static int mt8173_afe_pcm_dev_remove(struct platform_device *pdev)
 {
 	pm_runtime_disable(&pdev->dev);
 	if (!pm_runtime_status_suspended(&pdev->dev))
-		mtk_afe_runtime_suspend(&pdev->dev);
+		mt8173_afe_runtime_suspend(&pdev->dev);
 	snd_soc_unregister_component(&pdev->dev);
 	snd_soc_unregister_platform(&pdev->dev);
 	return 0;
 }
 
-static const struct of_device_id mtk_afe_pcm_dt_match[] = {
+static const struct of_device_id mt8173_afe_pcm_dt_match[] = {
 	{ .compatible = "mediatek,mt8173-afe-pcm", },
 	{ }
 };
-MODULE_DEVICE_TABLE(of, mtk_afe_pcm_dt_match);
+MODULE_DEVICE_TABLE(of, mt8173_afe_pcm_dt_match);
 
-static const struct dev_pm_ops mtk_afe_pm_ops = {
-	SET_RUNTIME_PM_OPS(mtk_afe_runtime_suspend, mtk_afe_runtime_resume,
-			   NULL)
+static const struct dev_pm_ops mt8173_afe_pm_ops = {
+	SET_RUNTIME_PM_OPS(mt8173_afe_runtime_suspend,
+			   mt8173_afe_runtime_resume, NULL)
 };
 
-static struct platform_driver mtk_afe_pcm_driver = {
+static struct platform_driver mt8173_afe_pcm_driver = {
 	.driver = {
-		   .name = "mtk-afe-pcm",
-		   .of_match_table = mtk_afe_pcm_dt_match,
-		   .pm = &mtk_afe_pm_ops,
+		   .name = "mt8173-afe-pcm",
+		   .of_match_table = mt8173_afe_pcm_dt_match,
+		   .pm = &mt8173_afe_pm_ops,
 	},
-	.probe = mtk_afe_pcm_dev_probe,
-	.remove = mtk_afe_pcm_dev_remove,
+	.probe = mt8173_afe_pcm_dev_probe,
+	.remove = mt8173_afe_pcm_dev_remove,
 };
 
-module_platform_driver(mtk_afe_pcm_driver);
+module_platform_driver(mt8173_afe_pcm_driver);
 
 MODULE_DESCRIPTION("Mediatek ALSA SoC AFE platform driver");
 MODULE_AUTHOR("Koro Chen <koro.chen@mediatek.com>");
diff --git a/sound/soc/mediatek/mt8173-max98090.c b/sound/soc/mediatek/mt8173/mt8173-max98090.c
index 71a1a35047ba..5524a2c727ec 100644
--- a/sound/soc/mediatek/mt8173-max98090.c
+++ b/sound/soc/mediatek/mt8173/mt8173-max98090.c
@@ -18,7 +18,7 @@
 #include <sound/soc.h>
 #include <sound/jack.h>
 #include <linux/gpio.h>
-#include "../codecs/max98090.h"
+#include "../../codecs/max98090.h"
 
 static struct snd_soc_jack mt8173_max98090_jack;
 
diff --git a/sound/soc/mediatek/mt8173-rt5650-rt5514.c b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c
index 58e083642dea..467f7049a288 100644
--- a/sound/soc/mediatek/mt8173-rt5650-rt5514.c
+++ b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5514.c
@@ -19,7 +19,7 @@
 #include <linux/of_gpio.h>
 #include <sound/soc.h>
 #include <sound/jack.h>
-#include "../codecs/rt5645.h"
+#include "../../codecs/rt5645.h"
 
 #define MCLK_FOR_CODECS		12288000
 
diff --git a/sound/soc/mediatek/mt8173-rt5650-rt5676.c b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5676.c
index bb593926c62d..1b8b2a778845 100644
--- a/sound/soc/mediatek/mt8173-rt5650-rt5676.c
+++ b/sound/soc/mediatek/mt8173/mt8173-rt5650-rt5676.c
@@ -19,8 +19,8 @@
 #include <linux/of_gpio.h>
 #include <sound/soc.h>
 #include <sound/jack.h>
-#include "../codecs/rt5645.h"
-#include "../codecs/rt5677.h"
+#include "../../codecs/rt5645.h"
+#include "../../codecs/rt5677.h"
 
 #define MCLK_FOR_CODECS		12288000
 
diff --git a/sound/soc/mediatek/mt8173-rt5650.c b/sound/soc/mediatek/mt8173/mt8173-rt5650.c
index a27a6673dbe3..ba65f4157a7e 100644
--- a/sound/soc/mediatek/mt8173-rt5650.c
+++ b/sound/soc/mediatek/mt8173/mt8173-rt5650.c
@@ -19,10 +19,24 @@
 #include <linux/of_gpio.h>
 #include <sound/soc.h>
 #include <sound/jack.h>
-#include "../codecs/rt5645.h"
+#include "../../codecs/rt5645.h"
 
 #define MCLK_FOR_CODECS		12288000
 
+enum mt8173_rt5650_mclk {
+	MT8173_RT5650_MCLK_EXTERNAL = 0,
+	MT8173_RT5650_MCLK_INTERNAL,
+};
+
+struct mt8173_rt5650_platform_data {
+	enum mt8173_rt5650_mclk pll_from;
+	/* 0 = external oscillator; 1 = internal source from mt8173 */
+};
+
+static struct mt8173_rt5650_platform_data mt8173_rt5650_priv = {
+	.pll_from = MT8173_RT5650_MCLK_EXTERNAL,
+};
+
 static const struct snd_soc_dapm_widget mt8173_rt5650_widgets[] = {
 	SND_SOC_DAPM_SPK("Speaker", NULL),
 	SND_SOC_DAPM_MIC("Int Mic", NULL),
@@ -54,13 +68,29 @@ static int mt8173_rt5650_hw_params(struct snd_pcm_substream *substream,
 				   struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	unsigned int mclk_clock;
 	int i, ret;
 
+	switch (mt8173_rt5650_priv.pll_from) {
+	case MT8173_RT5650_MCLK_EXTERNAL:
+		/* mclk = 12.288M */
+		mclk_clock = MCLK_FOR_CODECS;
+		break;
+	case MT8173_RT5650_MCLK_INTERNAL:
+		/* mclk = sampling rate*256 */
+		mclk_clock = params_rate(params) * 256;
+		break;
+	default:
+		/* mclk = 12.288M */
+		mclk_clock = MCLK_FOR_CODECS;
+		break;
+	}
+
 	for (i = 0; i < rtd->num_codecs; i++) {
 		struct snd_soc_dai *codec_dai = rtd->codec_dais[i];
 
-		/* pll from mclk 12.288M */
-		ret = snd_soc_dai_set_pll(codec_dai, 0, 0, MCLK_FOR_CODECS,
+		/* pll from mclk */
+		ret = snd_soc_dai_set_pll(codec_dai, 0, 0, mclk_clock,
 					  params_rate(params) * 512);
 		if (ret)
 			return ret;
@@ -139,7 +169,9 @@ static struct snd_soc_dai_link_component mt8173_rt5650_codecs[] = {
 enum {
 	DAI_LINK_PLAYBACK,
 	DAI_LINK_CAPTURE,
+	DAI_LINK_HDMI,
 	DAI_LINK_CODEC_I2S,
+	DAI_LINK_HDMI_I2S,
 };
 
 /* Digital audio interface glue - connects codec <---> CPU */
@@ -165,6 +197,16 @@ static struct snd_soc_dai_link mt8173_rt5650_dais[] = {
 		.dynamic = 1,
 		.dpcm_capture = 1,
 	},
+	[DAI_LINK_HDMI] = {
+		.name = "HDMI",
+		.stream_name = "HDMI PCM",
+		.cpu_dai_name = "HDMI",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.dynamic = 1,
+		.dpcm_playback = 1,
+	},
 	/* Back End DAI links */
 	[DAI_LINK_CODEC_I2S] = {
 		.name = "Codec",
@@ -180,6 +222,13 @@ static struct snd_soc_dai_link mt8173_rt5650_dais[] = {
 		.dpcm_playback = 1,
 		.dpcm_capture = 1,
 	},
+	[DAI_LINK_HDMI_I2S] = {
+		.name = "HDMI BE",
+		.cpu_dai_name = "HDMIO",
+		.no_pcm = 1,
+		.codec_dai_name = "i2s-hifi",
+		.dpcm_playback = 1,
+	},
 };
 
 static struct snd_soc_card mt8173_rt5650_card = {
@@ -243,6 +292,24 @@ static int mt8173_rt5650_dev_probe(struct platform_device *pdev)
 		mt8173_rt5650_codecs[1].dai_name = codec_capture_dai;
 	}
 
+	if (device_property_present(&pdev->dev, "mediatek,mclk")) {
+		ret = device_property_read_u32(&pdev->dev,
+					       "mediatek,mclk",
+					       &mt8173_rt5650_priv.pll_from);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"%s snd_soc_register_card fail %d\n",
+				__func__, ret);
+		}
+	}
+
+	mt8173_rt5650_dais[DAI_LINK_HDMI_I2S].codec_of_node =
+		of_parse_phandle(pdev->dev.of_node, "mediatek,audio-codec", 1);
+	if (!mt8173_rt5650_dais[DAI_LINK_HDMI_I2S].codec_of_node) {
+		dev_err(&pdev->dev,
+			"Property 'audio-codec' missing or invalid\n");
+		return -EINVAL;
+	}
 	card->dev = &pdev->dev;
 	platform_set_drvdata(pdev, card);
 
diff --git a/sound/soc/mediatek/mtk-afe-common.h b/sound/soc/mediatek/mtk-afe-common.h
deleted file mode 100644
index f341f623e887..000000000000
--- a/sound/soc/mediatek/mtk-afe-common.h
+++ /dev/null
@@ -1,101 +0,0 @@
-/*
- * mtk_afe_common.h  --  Mediatek audio driver common definitions
- *
- * Copyright (c) 2015 MediaTek Inc.
- * Author: Koro Chen <koro.chen@mediatek.com>
- *             Sascha Hauer <s.hauer@pengutronix.de>
- *             Hidalgo Huang <hidalgo.huang@mediatek.com>
- *             Ir Lian <ir.lian@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef _MTK_AFE_COMMON_H_
-#define _MTK_AFE_COMMON_H_
-
-#include <linux/clk.h>
-#include <linux/regmap.h>
-
-enum {
-	MTK_AFE_MEMIF_DL1,
-	MTK_AFE_MEMIF_DL2,
-	MTK_AFE_MEMIF_VUL,
-	MTK_AFE_MEMIF_DAI,
-	MTK_AFE_MEMIF_AWB,
-	MTK_AFE_MEMIF_MOD_DAI,
-	MTK_AFE_MEMIF_HDMI,
-	MTK_AFE_MEMIF_NUM,
-	MTK_AFE_IO_MOD_PCM1 = MTK_AFE_MEMIF_NUM,
-	MTK_AFE_IO_MOD_PCM2,
-	MTK_AFE_IO_PMIC,
-	MTK_AFE_IO_I2S,
-	MTK_AFE_IO_2ND_I2S,
-	MTK_AFE_IO_HW_GAIN1,
-	MTK_AFE_IO_HW_GAIN2,
-	MTK_AFE_IO_MRG_O,
-	MTK_AFE_IO_MRG_I,
-	MTK_AFE_IO_DAIBT,
-	MTK_AFE_IO_HDMI,
-};
-
-enum {
-	MTK_AFE_IRQ_1,
-	MTK_AFE_IRQ_2,
-	MTK_AFE_IRQ_3,
-	MTK_AFE_IRQ_4,
-	MTK_AFE_IRQ_5,
-	MTK_AFE_IRQ_6,
-	MTK_AFE_IRQ_7,
-	MTK_AFE_IRQ_8,
-	MTK_AFE_IRQ_NUM,
-};
-
-enum {
-	MTK_CLK_INFRASYS_AUD,
-	MTK_CLK_TOP_PDN_AUD,
-	MTK_CLK_TOP_PDN_AUD_BUS,
-	MTK_CLK_I2S0_M,
-	MTK_CLK_I2S1_M,
-	MTK_CLK_I2S2_M,
-	MTK_CLK_I2S3_M,
-	MTK_CLK_I2S3_B,
-	MTK_CLK_BCK0,
-	MTK_CLK_BCK1,
-	MTK_CLK_NUM
-};
-
-struct mtk_afe;
-struct snd_pcm_substream;
-
-struct mtk_afe_memif_data {
-	int id;
-	const char *name;
-	int reg_ofs_base;
-	int reg_ofs_cur;
-	int fs_shift;
-	int mono_shift;
-	int enable_shift;
-	int irq_reg_cnt;
-	int irq_cnt_shift;
-	int irq_en_shift;
-	int irq_fs_shift;
-	int irq_clr_shift;
-	int msb_shift;
-};
-
-struct mtk_afe_memif {
-	unsigned int phys_buf_addr;
-	int buffer_size;
-	struct snd_pcm_substream *substream;
-	const struct mtk_afe_memif_data *data;
-	const struct mtk_afe_irq_data *irqdata;
-};
-
-#endif
diff --git a/sound/soc/omap/Kconfig b/sound/soc/omap/Kconfig
index 5185a3844da9..f5451c78ede5 100644
--- a/sound/soc/omap/Kconfig
+++ b/sound/soc/omap/Kconfig
@@ -100,13 +100,14 @@ config SND_OMAP_SOC_OMAP_TWL4030
 
 config SND_OMAP_SOC_OMAP_ABE_TWL6040
 	tristate "SoC Audio support for OMAP boards using ABE and twl6040 codec"
-	depends on TWL6040_CORE && SND_OMAP_SOC
+	depends on TWL6040_CORE && SND_OMAP_SOC && COMMON_CLK
 	depends on ARCH_OMAP4 || (SOC_OMAP5 && MFD_PALMAS) || COMPILE_TEST
 	select SND_OMAP_SOC_DMIC
 	select SND_OMAP_SOC_MCPDM
 	select SND_SOC_TWL6040
 	select SND_SOC_DMIC
 	select COMMON_CLK_PALMAS if (SOC_OMAP5 && MFD_PALMAS)
+	select CLK_TWL6040
 	help
 	  Say Y if you want to add support for SoC audio on OMAP boards using
 	  ABE and twl6040 codec. This driver currently supports:
diff --git a/sound/soc/omap/mcbsp.c b/sound/soc/omap/mcbsp.c
index 4a16e778966b..76ce33199bf9 100644
--- a/sound/soc/omap/mcbsp.c
+++ b/sound/soc/omap/mcbsp.c
@@ -257,8 +257,8 @@ static void omap_st_on(struct omap_mcbsp *mcbsp)
 {
 	unsigned int w;
 
-	if (mcbsp->pdata->enable_st_clock)
-		mcbsp->pdata->enable_st_clock(mcbsp->id, 1);
+	if (mcbsp->pdata->force_ick_on)
+		mcbsp->pdata->force_ick_on(mcbsp->st_data->mcbsp_iclk, true);
 
 	/* Disable Sidetone clock auto-gating for normal operation */
 	w = MCBSP_ST_READ(mcbsp, SYSCONFIG);
@@ -287,8 +287,8 @@ static void omap_st_off(struct omap_mcbsp *mcbsp)
 	w = MCBSP_ST_READ(mcbsp, SYSCONFIG);
 	MCBSP_ST_WRITE(mcbsp, SYSCONFIG, w | ST_AUTOIDLE);
 
-	if (mcbsp->pdata->enable_st_clock)
-		mcbsp->pdata->enable_st_clock(mcbsp->id, 0);
+	if (mcbsp->pdata->force_ick_on)
+		mcbsp->pdata->force_ick_on(mcbsp->st_data->mcbsp_iclk, false);
 }
 
 static void omap_st_fir_write(struct omap_mcbsp *mcbsp, s16 *fir)
@@ -946,6 +946,13 @@ static int omap_st_add(struct omap_mcbsp *mcbsp, struct resource *res)
 	if (!st_data)
 		return -ENOMEM;
 
+	st_data->mcbsp_iclk = clk_get(mcbsp->dev, "ick");
+	if (IS_ERR(st_data->mcbsp_iclk)) {
+		dev_warn(mcbsp->dev,
+			 "Failed to get ick, sidetone might be broken\n");
+		st_data->mcbsp_iclk = NULL;
+	}
+
 	st_data->io_base_st = devm_ioremap(mcbsp->dev, res->start,
 					   resource_size(res));
 	if (!st_data->io_base_st)
@@ -1088,11 +1095,13 @@ err_thres:
 	return ret;
 }
 
-void omap_mcbsp_sysfs_remove(struct omap_mcbsp *mcbsp)
+void omap_mcbsp_cleanup(struct omap_mcbsp *mcbsp)
 {
 	if (mcbsp->pdata->buffer_size)
 		sysfs_remove_group(&mcbsp->dev->kobj, &additional_attr_group);
 
-	if (mcbsp->st_data)
+	if (mcbsp->st_data) {
 		sysfs_remove_group(&mcbsp->dev->kobj, &sidetone_attr_group);
+		clk_put(mcbsp->st_data->mcbsp_iclk);
+	}
 }
diff --git a/sound/soc/omap/mcbsp.h b/sound/soc/omap/mcbsp.h
index 96d1b086bcf8..61e93b1c185d 100644
--- a/sound/soc/omap/mcbsp.h
+++ b/sound/soc/omap/mcbsp.h
@@ -280,6 +280,7 @@ struct omap_mcbsp_reg_cfg {
 
 struct omap_mcbsp_st_data {
 	void __iomem *io_base_st;
+	struct clk *mcbsp_iclk;
 	bool running;
 	bool enabled;
 	s16 taps[128];	/* Sidetone filter coefficients */
@@ -349,6 +350,6 @@ int omap_st_disable(struct omap_mcbsp *mcbsp);
 int omap_st_is_enabled(struct omap_mcbsp *mcbsp);
 
 int omap_mcbsp_init(struct platform_device *pdev);
-void omap_mcbsp_sysfs_remove(struct omap_mcbsp *mcbsp);
+void omap_mcbsp_cleanup(struct omap_mcbsp *mcbsp);
 
 #endif /* __ASOC_MCBSP_H */
diff --git a/sound/soc/omap/omap-hdmi-audio.c b/sound/soc/omap/omap-hdmi-audio.c
index 64425d352962..888133f9e65d 100644
--- a/sound/soc/omap/omap-hdmi-audio.c
+++ b/sound/soc/omap/omap-hdmi-audio.c
@@ -28,7 +28,6 @@
 #include <sound/asoundef.h>
 #include <sound/omap-pcm.h>
 #include <sound/omap-hdmi-audio.h>
-#include <video/omapdss.h>
 
 #define DRV_NAME "omap-hdmi-audio"
 
diff --git a/sound/soc/omap/omap-mcbsp.c b/sound/soc/omap/omap-mcbsp.c
index fd99d89de6a8..d018e966e533 100644
--- a/sound/soc/omap/omap-mcbsp.c
+++ b/sound/soc/omap/omap-mcbsp.c
@@ -788,6 +788,7 @@ static int asoc_mcbsp_probe(struct platform_device *pdev)
 	match = of_match_device(omap_mcbsp_of_match, &pdev->dev);
 	if (match) {
 		struct device_node *node = pdev->dev.of_node;
+		struct omap_mcbsp_platform_data *pdata_quirk = pdata;
 		int buffer_size;
 
 		pdata = devm_kzalloc(&pdev->dev,
@@ -799,6 +800,8 @@ static int asoc_mcbsp_probe(struct platform_device *pdev)
 		memcpy(pdata, match->data, sizeof(*pdata));
 		if (!of_property_read_u32(node, "ti,buffer-size", &buffer_size))
 			pdata->buffer_size = buffer_size;
+		if (pdata_quirk)
+			pdata->force_ick_on = pdata_quirk->force_ick_on;
 	} else if (!pdata) {
 		dev_err(&pdev->dev, "missing platform data.\n");
 		return -EINVAL;
@@ -832,7 +835,7 @@ static int asoc_mcbsp_remove(struct platform_device *pdev)
 	if (mcbsp->pdata->ops && mcbsp->pdata->ops->free)
 		mcbsp->pdata->ops->free(mcbsp->id);
 
-	omap_mcbsp_sysfs_remove(mcbsp);
+	omap_mcbsp_cleanup(mcbsp);
 
 	clk_put(mcbsp->fclk);
 
diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c
index b837265ac3e9..e7cdc51fd806 100644
--- a/sound/soc/omap/omap-mcpdm.c
+++ b/sound/soc/omap/omap-mcpdm.c
@@ -31,6 +31,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/irq.h>
+#include <linux/clk.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
 #include <linux/of_device.h>
@@ -54,6 +55,7 @@ struct omap_mcpdm {
 	unsigned long phys_base;
 	void __iomem *io_base;
 	int irq;
+	struct clk *pdmclk;
 
 	struct mutex mutex;
 
@@ -66,6 +68,9 @@ struct omap_mcpdm {
 	/* McPDM needs to be restarted due to runtime reconfiguration */
 	bool restart;
 
+	/* pm state for suspend/resume handling */
+	int pm_active_count;
+
 	struct snd_dmaengine_dai_dma_data dma_data[2];
 };
 
@@ -173,6 +178,10 @@ static inline int omap_mcpdm_active(struct omap_mcpdm *mcpdm)
  */
 static void omap_mcpdm_open_streams(struct omap_mcpdm *mcpdm)
 {
+	u32 ctrl = omap_mcpdm_read(mcpdm, MCPDM_REG_CTRL);
+
+	omap_mcpdm_write(mcpdm, MCPDM_REG_CTRL, ctrl | MCPDM_WD_EN);
+
 	omap_mcpdm_write(mcpdm, MCPDM_REG_IRQENABLE_SET,
 			MCPDM_DN_IRQ_EMPTY | MCPDM_DN_IRQ_FULL |
 			MCPDM_UP_IRQ_EMPTY | MCPDM_UP_IRQ_FULL);
@@ -258,12 +267,9 @@ static int omap_mcpdm_dai_startup(struct snd_pcm_substream *substream,
 
 	mutex_lock(&mcpdm->mutex);
 
-	if (!dai->active) {
-		u32 ctrl = omap_mcpdm_read(mcpdm, MCPDM_REG_CTRL);
-
-		omap_mcpdm_write(mcpdm, MCPDM_REG_CTRL, ctrl | MCPDM_WD_EN);
+	if (!dai->active)
 		omap_mcpdm_open_streams(mcpdm);
-	}
+
 	mutex_unlock(&mcpdm->mutex);
 
 	return 0;
@@ -384,6 +390,7 @@ static int omap_mcpdm_probe(struct snd_soc_dai *dai)
 	struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
 	int ret;
 
+	clk_prepare_enable(mcpdm->pdmclk);
 	pm_runtime_enable(mcpdm->dev);
 
 	/* Disable lines while request is ongoing */
@@ -418,8 +425,54 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai)
 
 	pm_runtime_disable(mcpdm->dev);
 
+	clk_disable_unprepare(mcpdm->pdmclk);
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int omap_mcpdm_suspend(struct snd_soc_dai *dai)
+{
+	struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
+
+	if (dai->active) {
+		omap_mcpdm_stop(mcpdm);
+		omap_mcpdm_close_streams(mcpdm);
+	}
+
+	mcpdm->pm_active_count = 0;
+	while (pm_runtime_active(mcpdm->dev)) {
+		pm_runtime_put_sync(mcpdm->dev);
+		mcpdm->pm_active_count++;
+	}
+
+	clk_disable_unprepare(mcpdm->pdmclk);
+
+	return 0;
+}
+
+static int omap_mcpdm_resume(struct snd_soc_dai *dai)
+{
+	struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
+
+	clk_prepare_enable(mcpdm->pdmclk);
+
+	if (mcpdm->pm_active_count) {
+		while (mcpdm->pm_active_count--)
+			pm_runtime_get_sync(mcpdm->dev);
+
+		if (dai->active) {
+			omap_mcpdm_open_streams(mcpdm);
+			omap_mcpdm_start(mcpdm);
+		}
+	}
+
+
 	return 0;
 }
+#else
+#define omap_mcpdm_suspend NULL
+#define omap_mcpdm_resume NULL
+#endif
 
 #define OMAP_MCPDM_RATES	(SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000)
 #define OMAP_MCPDM_FORMATS	SNDRV_PCM_FMTBIT_S32_LE
@@ -427,6 +480,8 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai)
 static struct snd_soc_dai_driver omap_mcpdm_dai = {
 	.probe = omap_mcpdm_probe,
 	.remove = omap_mcpdm_remove,
+	.suspend = omap_mcpdm_suspend,
+	.resume = omap_mcpdm_resume,
 	.probe_order = SND_SOC_COMP_ORDER_LATE,
 	.remove_order = SND_SOC_COMP_ORDER_EARLY,
 	.playback = {
@@ -494,6 +549,15 @@ static int asoc_mcpdm_probe(struct platform_device *pdev)
 
 	mcpdm->dev = &pdev->dev;
 
+	mcpdm->pdmclk = devm_clk_get(&pdev->dev, "pdmclk");
+	if (IS_ERR(mcpdm->pdmclk)) {
+		if (PTR_ERR(mcpdm->pdmclk) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		dev_warn(&pdev->dev, "Error getting pdmclk (%ld)!\n",
+			 PTR_ERR(mcpdm->pdmclk));
+		mcpdm->pdmclk = NULL;
+	}
+
 	ret =  devm_snd_soc_register_component(&pdev->dev,
 					       &omap_mcpdm_component,
 					       &omap_mcpdm_dai, 1);
diff --git a/sound/soc/omap/rx51.c b/sound/soc/omap/rx51.c
index 54949242bc70..a76845748a10 100644
--- a/sound/soc/omap/rx51.c
+++ b/sound/soc/omap/rx51.c
@@ -33,7 +33,6 @@
 #include <sound/pcm.h>
 #include <sound/soc.h>
 #include <linux/platform_data/asoc-ti-mcbsp.h>
-#include "../codecs/tpa6130a2.h"
 
 #include <asm/mach-types.h>
 
@@ -164,19 +163,6 @@ static int rx51_spk_event(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
-static int rx51_hp_event(struct snd_soc_dapm_widget *w,
-			 struct snd_kcontrol *k, int event)
-{
-	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
-
-	if (SND_SOC_DAPM_EVENT_ON(event))
-		tpa6130a2_stereo_enable(codec, 1);
-	else
-		tpa6130a2_stereo_enable(codec, 0);
-
-	return 0;
-}
-
 static int rx51_get_input(struct snd_kcontrol *kcontrol,
 			  struct snd_ctl_elem_value *ucontrol)
 {
@@ -235,7 +221,7 @@ static struct snd_soc_jack_gpio rx51_av_jack_gpios[] = {
 static const struct snd_soc_dapm_widget aic34_dapm_widgets[] = {
 	SND_SOC_DAPM_SPK("Ext Spk", rx51_spk_event),
 	SND_SOC_DAPM_MIC("DMic", NULL),
-	SND_SOC_DAPM_HP("Headphone Jack", rx51_hp_event),
+	SND_SOC_DAPM_HP("Headphone Jack", NULL),
 	SND_SOC_DAPM_MIC("HS Mic", NULL),
 	SND_SOC_DAPM_LINE("FM Transmitter", NULL),
 	SND_SOC_DAPM_SPK("Earphone", NULL),
@@ -246,11 +232,14 @@ static const struct snd_soc_dapm_route audio_map[] = {
 	{"Ext Spk", NULL, "HPROUT"},
 	{"Ext Spk", NULL, "HPLCOM"},
 	{"Ext Spk", NULL, "HPRCOM"},
-	{"Headphone Jack", NULL, "LLOUT"},
-	{"Headphone Jack", NULL, "RLOUT"},
 	{"FM Transmitter", NULL, "LLOUT"},
 	{"FM Transmitter", NULL, "RLOUT"},
 
+	{"Headphone Jack", NULL, "TPA6130A2 HPLEFT"},
+	{"Headphone Jack", NULL, "TPA6130A2 HPRIGHT"},
+	{"TPA6130A2 LEFTIN", NULL, "LLOUT"},
+	{"TPA6130A2 RIGHTIN", NULL, "RLOUT"},
+
 	{"DMic Rate 64", NULL, "DMic"},
 	{"DMic", NULL, "Mic Bias"},
 
@@ -286,16 +275,10 @@ static const struct snd_kcontrol_new aic34_rx51_controls[] = {
 
 static int rx51_aic34_init(struct snd_soc_pcm_runtime *rtd)
 {
-	struct snd_soc_codec *codec = rtd->codec;
 	struct snd_soc_card *card = rtd->card;
 	struct rx51_audio_pdata *pdata = snd_soc_card_get_drvdata(card);
 	int err;
 
-	err = tpa6130a2_add_controls(codec);
-	if (err < 0) {
-		dev_err(card->dev, "Failed to add TPA6130A2 controls\n");
-		return err;
-	}
 	snd_soc_limit_volume(card, "TPA6130A2 Headphone Playback Volume", 42);
 
 	err = omap_mcbsp_st_add_controls(rtd, 2);
@@ -357,6 +340,10 @@ static struct snd_soc_aux_dev rx51_aux_dev[] = {
 		.name = "TLV320AIC34b",
 		.codec_name = "tlv320aic3x-codec.2-0019",
 	},
+	{
+		.name = "TPA61320A2",
+		.codec_name = "tpa6130a2.2-0060",
+	},
 };
 
 static struct snd_soc_codec_conf rx51_codec_conf[] = {
@@ -364,6 +351,10 @@ static struct snd_soc_codec_conf rx51_codec_conf[] = {
 		.dev_name = "tlv320aic3x-codec.2-0019",
 		.name_prefix = "b",
 	},
+	{
+		.dev_name = "tpa6130a2.2-0060",
+		.name_prefix = "TPA6130A2",
+	},
 };
 
 /* Audio card */
@@ -435,11 +426,10 @@ static int rx51_soc_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "Headphone amplifier node is not provided\n");
 			return -EINVAL;
 		}
-
-		/* TODO: tpa6130a2a driver supports only a single instance, so
-		 * this driver ignores the headphone-amplifier node for now.
-		 * It's already mandatory in the DT binding to be future proof.
-		 */
+		rx51_aux_dev[1].codec_name = NULL;
+		rx51_aux_dev[1].codec_of_node = dai_node;
+		rx51_codec_conf[1].dev_name = NULL;
+		rx51_codec_conf[1].of_node = dai_node;
 	}
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c
index 574c6af28c06..652e8c5ea166 100644
--- a/sound/soc/rockchip/rockchip_i2s.c
+++ b/sound/soc/rockchip/rockchip_i2s.c
@@ -11,8 +11,10 @@
  */
 
 #include <linux/module.h>
+#include <linux/mfd/syscon.h>
 #include <linux/delay.h>
 #include <linux/of_gpio.h>
+#include <linux/of_device.h>
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
@@ -23,6 +25,11 @@
 
 #define DRV_NAME "rockchip-i2s"
 
+struct rk_i2s_pins {
+	u32 reg_offset;
+	u32 shift;
+};
+
 struct rk_i2s_dev {
 	struct device *dev;
 
@@ -33,6 +40,7 @@ struct rk_i2s_dev {
 	struct snd_dmaengine_dai_dma_data playback_dma_data;
 
 	struct regmap *regmap;
+	struct regmap *grf;
 
 /*
  * Used to indicate the tx/rx status.
@@ -42,6 +50,7 @@ struct rk_i2s_dev {
 	bool tx_start;
 	bool rx_start;
 	bool is_master_mode;
+	const struct rk_i2s_pins *pins;
 };
 
 static int i2s_runtime_suspend(struct device *dev)
@@ -300,14 +309,38 @@ static int rockchip_i2s_hw_params(struct snd_pcm_substream *substream,
 				   I2S_TXCR_VDW_MASK | I2S_TXCR_CSR_MASK,
 				   val);
 
+	if (!IS_ERR(i2s->grf) && i2s->pins) {
+		regmap_read(i2s->regmap, I2S_TXCR, &val);
+		val &= I2S_TXCR_CSR_MASK;
+
+		switch (val) {
+		case I2S_CHN_4:
+			val = I2S_IO_4CH_OUT_6CH_IN;
+			break;
+		case I2S_CHN_6:
+			val = I2S_IO_6CH_OUT_4CH_IN;
+			break;
+		case I2S_CHN_8:
+			val = I2S_IO_8CH_OUT_2CH_IN;
+			break;
+		default:
+			val = I2S_IO_2CH_OUT_8CH_IN;
+			break;
+		}
+
+		val <<= i2s->pins->shift;
+		val |= (I2S_IO_DIRECTION_MASK << i2s->pins->shift) << 16;
+		regmap_write(i2s->grf, i2s->pins->reg_offset, val);
+	}
+
 	regmap_update_bits(i2s->regmap, I2S_DMACR, I2S_DMACR_TDL_MASK,
 			   I2S_DMACR_TDL(16));
 	regmap_update_bits(i2s->regmap, I2S_DMACR, I2S_DMACR_RDL_MASK,
 			   I2S_DMACR_RDL(16));
 
 	val = I2S_CKR_TRCM_TXRX;
-	if (dai->driver->symmetric_rates || rtd->dai_link->symmetric_rates)
-		val = I2S_CKR_TRCM_TXSHARE;
+	if (dai->driver->symmetric_rates && rtd->dai_link->symmetric_rates)
+		val = I2S_CKR_TRCM_TXONLY;
 
 	regmap_update_bits(i2s->regmap, I2S_CKR,
 			   I2S_CKR_TRCM_MASK,
@@ -485,9 +518,23 @@ static const struct regmap_config rockchip_i2s_regmap_config = {
 	.cache_type = REGCACHE_FLAT,
 };
 
+static const struct rk_i2s_pins rk3399_i2s_pins = {
+	.reg_offset = 0xe220,
+	.shift = 11,
+};
+
+static const struct of_device_id rockchip_i2s_match[] = {
+	{ .compatible = "rockchip,rk3066-i2s", },
+	{ .compatible = "rockchip,rk3188-i2s", },
+	{ .compatible = "rockchip,rk3288-i2s", },
+	{ .compatible = "rockchip,rk3399-i2s", .data = &rk3399_i2s_pins },
+	{},
+};
+
 static int rockchip_i2s_probe(struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
+	const struct of_device_id *of_id;
 	struct rk_i2s_dev *i2s;
 	struct snd_soc_dai_driver *soc_dai;
 	struct resource *res;
@@ -501,6 +548,17 @@ static int rockchip_i2s_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	i2s->dev = &pdev->dev;
+
+	i2s->grf = syscon_regmap_lookup_by_phandle(node, "rockchip,grf");
+	if (!IS_ERR(i2s->grf)) {
+		of_id = of_match_device(rockchip_i2s_match, &pdev->dev);
+		if (!of_id || !of_id->data)
+			return -EINVAL;
+
+		i2s->pins = of_id->data;
+	}
+
 	/* try to prepare related clocks */
 	i2s->hclk = devm_clk_get(&pdev->dev, "i2s_hclk");
 	if (IS_ERR(i2s->hclk)) {
@@ -540,7 +598,6 @@ static int rockchip_i2s_probe(struct platform_device *pdev)
 	i2s->capture_dma_data.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	i2s->capture_dma_data.maxburst = 4;
 
-	i2s->dev = &pdev->dev;
 	dev_set_drvdata(&pdev->dev, i2s);
 
 	pm_runtime_enable(&pdev->dev);
@@ -606,14 +663,6 @@ static int rockchip_i2s_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id rockchip_i2s_match[] = {
-	{ .compatible = "rockchip,rk3066-i2s", },
-	{ .compatible = "rockchip,rk3188-i2s", },
-	{ .compatible = "rockchip,rk3288-i2s", },
-	{ .compatible = "rockchip,rk3399-i2s", },
-	{},
-};
-
 static const struct dev_pm_ops rockchip_i2s_pm_ops = {
 	SET_RUNTIME_PM_OPS(i2s_runtime_suspend, i2s_runtime_resume,
 			   NULL)
diff --git a/sound/soc/rockchip/rockchip_i2s.h b/sound/soc/rockchip/rockchip_i2s.h
index dc6e2c74d088..31f11fd25393 100644
--- a/sound/soc/rockchip/rockchip_i2s.h
+++ b/sound/soc/rockchip/rockchip_i2s.h
@@ -81,8 +81,8 @@
 #define I2S_CKR_TRCM_SHIFT	28
 #define I2S_CKR_TRCM(x)	(x << I2S_CKR_TRCM_SHIFT)
 #define I2S_CKR_TRCM_TXRX	(0 << I2S_CKR_TRCM_SHIFT)
-#define I2S_CKR_TRCM_TXSHARE	(1 << I2S_CKR_TRCM_SHIFT)
-#define I2S_CKR_TRCM_RXSHARE	(2 << I2S_CKR_TRCM_SHIFT)
+#define I2S_CKR_TRCM_TXONLY	(1 << I2S_CKR_TRCM_SHIFT)
+#define I2S_CKR_TRCM_RXONLY	(2 << I2S_CKR_TRCM_SHIFT)
 #define I2S_CKR_TRCM_MASK	(3 << I2S_CKR_TRCM_SHIFT)
 #define I2S_CKR_MSS_SHIFT	27
 #define I2S_CKR_MSS_MASTER	(0 << I2S_CKR_MSS_SHIFT)
@@ -236,4 +236,11 @@ enum {
 #define I2S_TXDR	(0x0024)
 #define I2S_RXDR	(0x0028)
 
+/* io direction cfg register */
+#define I2S_IO_DIRECTION_MASK	(7)
+#define I2S_IO_8CH_OUT_2CH_IN	(0)
+#define I2S_IO_6CH_OUT_4CH_IN	(4)
+#define I2S_IO_4CH_OUT_6CH_IN	(6)
+#define I2S_IO_2CH_OUT_8CH_IN	(7)
+
 #endif /* _ROCKCHIP_IIS_H */
diff --git a/sound/soc/rockchip/rockchip_max98090.c b/sound/soc/rockchip/rockchip_max98090.c
index 543610282cdb..e70ffad07184 100644
--- a/sound/soc/rockchip/rockchip_max98090.c
+++ b/sound/soc/rockchip/rockchip_max98090.c
@@ -34,13 +34,18 @@
 #define DRV_NAME "rockchip-snd-max98090"
 
 static struct snd_soc_jack headset_jack;
+
+/* Headset jack detection DAPM pins */
 static struct snd_soc_jack_pin headset_jack_pins[] = {
 	{
-		.pin = "Headset Jack",
-		.mask = SND_JACK_HEADPHONE | SND_JACK_MICROPHONE |
-			SND_JACK_BTN_0 | SND_JACK_BTN_1 |
-			SND_JACK_BTN_2 | SND_JACK_BTN_3,
+		.pin = "Headphone",
+		.mask = SND_JACK_HEADPHONE,
+	},
+	{
+		.pin = "Headset Mic",
+		.mask = SND_JACK_MICROPHONE,
 	},
+
 };
 
 static const struct snd_soc_dapm_widget rk_dapm_widgets[] = {
@@ -53,7 +58,7 @@ static const struct snd_soc_dapm_widget rk_dapm_widgets[] = {
 static const struct snd_soc_dapm_route rk_audio_map[] = {
 	{"IN34", NULL, "Headset Mic"},
 	{"IN34", NULL, "MICBIAS"},
-	{"MICBIAS", NULL, "Headset Mic"},
+	{"Headset Mic", NULL, "MICBIAS"},
 	{"DMICL", NULL, "Int Mic"},
 	{"Headphone", NULL, "HPL"},
 	{"Headphone", NULL, "HPR"},
@@ -114,43 +119,27 @@ static int rk_aif1_hw_params(struct snd_pcm_substream *substream,
 	return ret;
 }
 
-static int rk_init(struct snd_soc_pcm_runtime *runtime)
-{
-	/* Enable Headset and 4 Buttons Jack detection */
-	return snd_soc_card_jack_new(runtime->card, "Headset Jack",
-			       SND_JACK_HEADSET |
-			       SND_JACK_BTN_0 | SND_JACK_BTN_1 |
-			       SND_JACK_BTN_2 | SND_JACK_BTN_3,
-			       &headset_jack,
-			       headset_jack_pins,
-			       ARRAY_SIZE(headset_jack_pins));
-}
-
-static int rk_98090_headset_init(struct snd_soc_component *component)
-{
-	return ts3a227e_enable_jack_detect(component, &headset_jack);
-}
-
 static struct snd_soc_ops rk_aif1_ops = {
 	.hw_params = rk_aif1_hw_params,
 };
 
-static struct snd_soc_aux_dev rk_98090_headset_dev = {
-	.name = "Headset Chip",
-	.init = rk_98090_headset_init,
-};
-
 static struct snd_soc_dai_link rk_dailink = {
 	.name = "max98090",
 	.stream_name = "Audio",
 	.codec_dai_name = "HiFi",
-	.init = rk_init,
 	.ops = &rk_aif1_ops,
 	/* set max98090 as slave */
 	.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
 		SND_SOC_DAIFMT_CBS_CFS,
 };
 
+static int rk_98090_headset_init(struct snd_soc_component *component);
+
+static struct snd_soc_aux_dev rk_98090_headset_dev = {
+	.name = "Headset Chip",
+	.init = rk_98090_headset_init,
+};
+
 static struct snd_soc_card snd_soc_card_rk = {
 	.name = "ROCKCHIP-I2S",
 	.owner = THIS_MODULE,
@@ -166,6 +155,26 @@ static struct snd_soc_card snd_soc_card_rk = {
 	.num_controls = ARRAY_SIZE(rk_mc_controls),
 };
 
+static int rk_98090_headset_init(struct snd_soc_component *component)
+{
+	int ret;
+
+	/* Enable Headset and 4 Buttons Jack detection */
+	ret = snd_soc_card_jack_new(&snd_soc_card_rk, "Headset Jack",
+				    SND_JACK_HEADSET |
+				    SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+				    SND_JACK_BTN_2 | SND_JACK_BTN_3,
+				    &headset_jack,
+				    headset_jack_pins,
+				    ARRAY_SIZE(headset_jack_pins));
+	if (ret)
+		return ret;
+
+	ret = ts3a227e_enable_jack_detect(component, &headset_jack);
+
+	return ret;
+}
+
 static int snd_rk_mc_probe(struct platform_device *pdev)
 {
 	int ret = 0;
diff --git a/sound/soc/rockchip/rockchip_spdif.c b/sound/soc/rockchip/rockchip_spdif.c
index 100781e37848..4ca265737eda 100644
--- a/sound/soc/rockchip/rockchip_spdif.c
+++ b/sound/soc/rockchip/rockchip_spdif.c
@@ -101,21 +101,7 @@ static int rk_spdif_hw_params(struct snd_pcm_substream *substream,
 	int ret;
 
 	srate = params_rate(params);
-	switch (srate) {
-	case 32000:
-	case 48000:
-	case 96000:
-		mclk = 96000 * 128; /* 12288000 hz */
-		break;
-	case 44100:
-		mclk = 44100 * 256; /* 11289600 hz */
-		break;
-	case 192000:
-		mclk = 192000 * 128; /* 24576000 hz */
-		break;
-	default:
-		return -EINVAL;
-	}
+	mclk = srate * 128;
 
 	switch (params_format(params)) {
 	case SNDRV_PCM_FORMAT_S16_LE:
@@ -139,7 +125,6 @@ static int rk_spdif_hw_params(struct snd_pcm_substream *substream,
 		return ret;
 	}
 
-	val |= SPDIF_CFGR_CLK_DIV(mclk/(srate * 256));
 	ret = regmap_update_bits(spdif->regmap, SPDIF_CFGR,
 		SPDIF_CFGR_CLK_DIV_MASK | SPDIF_CFGR_HALFWORD_ENABLE |
 		SDPIF_CFGR_VDW_MASK,
diff --git a/sound/soc/samsung/Kconfig b/sound/soc/samsung/Kconfig
index 78baa26e938b..7b722b0094d9 100644
--- a/sound/soc/samsung/Kconfig
+++ b/sound/soc/samsung/Kconfig
@@ -224,14 +224,6 @@ config SND_SOC_SNOW
 	  Say Y if you want to add audio support for various Snow
 	  boards based on Exynos5 series of SoCs.
 
-config SND_SOC_ODROIDX2
-	tristate "Audio support for Odroid-X2 and Odroid-U3"
-	depends on SND_SOC_SAMSUNG && I2C
-	select SND_SOC_MAX98090
-	select SND_SAMSUNG_I2S
-	help
-	  Say Y here to enable audio support for the Odroid-X2/U3.
-
 config SND_SOC_ARNDALE_RT5631_ALC5631
         tristate "Audio support for RT5631(ALC5631) on Arndale Board"
         depends on SND_SOC_SAMSUNG && I2C
diff --git a/sound/soc/samsung/Makefile b/sound/soc/samsung/Makefile
index 052fe71be518..5d03f5ce6916 100644
--- a/sound/soc/samsung/Makefile
+++ b/sound/soc/samsung/Makefile
@@ -43,7 +43,6 @@ snd-soc-tobermory-objs := tobermory.o
 snd-soc-lowland-objs := lowland.o
 snd-soc-littlemill-objs := littlemill.o
 snd-soc-bells-objs := bells.o
-snd-soc-odroidx2-max98090-objs := odroidx2_max98090.o
 snd-soc-arndale-rt5631-objs := arndale_rt5631.o
 
 obj-$(CONFIG_SND_SOC_SAMSUNG_JIVE_WM8750) += snd-soc-jive-wm8750.o
@@ -69,5 +68,4 @@ obj-$(CONFIG_SND_SOC_TOBERMORY) += snd-soc-tobermory.o
 obj-$(CONFIG_SND_SOC_LOWLAND) += snd-soc-lowland.o
 obj-$(CONFIG_SND_SOC_LITTLEMILL) += snd-soc-littlemill.o
 obj-$(CONFIG_SND_SOC_BELLS) += snd-soc-bells.o
-obj-$(CONFIG_SND_SOC_ODROIDX2) += snd-soc-odroidx2-max98090.o
 obj-$(CONFIG_SND_SOC_ARNDALE_RT5631_ALC5631) += snd-soc-arndale-rt5631.o
diff --git a/sound/soc/samsung/ac97.c b/sound/soc/samsung/ac97.c
index 4a7a503fe13c..547d31032088 100644
--- a/sound/soc/samsung/ac97.c
+++ b/sound/soc/samsung/ac97.c
@@ -389,7 +389,8 @@ static int s3c_ac97_probe(struct platform_device *pdev)
 		goto err5;
 
 	ret = samsung_asoc_dma_platform_register(&pdev->dev,
-						 ac97_pdata->dma_filter);
+						 ac97_pdata->dma_filter,
+						 NULL, NULL);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to get register DMA: %d\n", ret);
 		goto err5;
diff --git a/sound/soc/samsung/dma.h b/sound/soc/samsung/dma.h
index a7616cc9b39e..3830f297e0b6 100644
--- a/sound/soc/samsung/dma.h
+++ b/sound/soc/samsung/dma.h
@@ -26,7 +26,10 @@ struct s3c_dma_params {
 void samsung_asoc_init_dma_data(struct snd_soc_dai *dai,
 				struct s3c_dma_params *playback,
 				struct s3c_dma_params *capture);
-int samsung_asoc_dma_platform_register(struct device *dev,
-				       dma_filter_fn fn);
-
+/*
+ * @tx, @rx arguments can be NULL if the DMA channel names are "tx", "rx",
+ * otherwise actual DMA channel names must be passed to this function.
+ */
+int samsung_asoc_dma_platform_register(struct device *dev, dma_filter_fn filter,
+				       const char *tx, const char *rx);
 #endif
diff --git a/sound/soc/samsung/dmaengine.c b/sound/soc/samsung/dmaengine.c
index 063125937311..2c87f380bfc4 100644
--- a/sound/soc/samsung/dmaengine.c
+++ b/sound/soc/samsung/dmaengine.c
@@ -28,10 +28,6 @@
 
 #include "dma.h"
 
-static struct snd_dmaengine_pcm_config samsung_dmaengine_pcm_config = {
-	.prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config,
-};
-
 void samsung_asoc_init_dma_data(struct snd_soc_dai *dai,
 				struct s3c_dma_params *playback,
 				struct s3c_dma_params *capture)
@@ -58,15 +54,28 @@ void samsung_asoc_init_dma_data(struct snd_soc_dai *dai,
 }
 EXPORT_SYMBOL_GPL(samsung_asoc_init_dma_data);
 
-int samsung_asoc_dma_platform_register(struct device *dev,
-				       dma_filter_fn filter)
+int samsung_asoc_dma_platform_register(struct device *dev, dma_filter_fn filter,
+				       const char *tx, const char *rx)
 {
-	samsung_dmaengine_pcm_config.compat_filter_fn = filter;
+	unsigned int flags = SND_DMAENGINE_PCM_FLAG_COMPAT;
+
+	struct snd_dmaengine_pcm_config *pcm_conf;
+
+	pcm_conf = devm_kzalloc(dev, sizeof(*pcm_conf), GFP_KERNEL);
+	if (!pcm_conf)
+		return -ENOMEM;
+
+	pcm_conf->prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config;
+	pcm_conf->compat_filter_fn = filter;
+
+	if (dev->of_node) {
+		pcm_conf->chan_names[SNDRV_PCM_STREAM_PLAYBACK] = tx;
+		pcm_conf->chan_names[SNDRV_PCM_STREAM_CAPTURE] = rx;
+	} else {
+		flags |= SND_DMAENGINE_PCM_FLAG_CUSTOM_CHANNEL_NAME;
+	}
 
-	return devm_snd_dmaengine_pcm_register(dev,
-			&samsung_dmaengine_pcm_config,
-			SND_DMAENGINE_PCM_FLAG_CUSTOM_CHANNEL_NAME |
-			SND_DMAENGINE_PCM_FLAG_COMPAT);
+	return devm_snd_dmaengine_pcm_register(dev, pcm_conf, flags);
 }
 EXPORT_SYMBOL_GPL(samsung_asoc_dma_platform_register);
 
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 70a2559b63f9..50635ee8ff20 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -18,6 +18,7 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/of_gpio.h>
 #include <linux/pm_runtime.h>
 
@@ -1106,19 +1107,9 @@ static struct i2s_dai *i2s_alloc_dai(struct platform_device *pdev, bool sec)
 	return i2s;
 }
 
-static const struct of_device_id exynos_i2s_match[];
-
-static inline const struct samsung_i2s_dai_data *samsung_i2s_get_driver_data(
-						struct platform_device *pdev)
+static void i2s_free_sec_dai(struct i2s_dai *i2s)
 {
-	if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node) {
-		const struct of_device_id *match;
-		match = of_match_node(exynos_i2s_match, pdev->dev.of_node);
-		return match ? match->data : NULL;
-	} else {
-		return (struct samsung_i2s_dai_data *)
-				platform_get_device_id(pdev)->driver_data;
-	}
+	platform_device_del(i2s->pdev);
 }
 
 #ifdef CONFIG_PM
@@ -1233,9 +1224,13 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 	const struct samsung_i2s_dai_data *i2s_dai_data;
 	int ret;
 
-	/* Call during Seconday interface registration */
-	i2s_dai_data = samsung_i2s_get_driver_data(pdev);
+	if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node)
+		i2s_dai_data = of_device_get_match_data(&pdev->dev);
+	else
+		i2s_dai_data = (struct samsung_i2s_dai_data *)
+				platform_get_device_id(pdev)->driver_data;
 
+	/* Call during the secondary interface registration */
 	if (i2s_dai_data->dai_type == TYPE_SEC) {
 		sec_dai = dev_get_drvdata(&pdev->dev);
 		if (!sec_dai) {
@@ -1249,7 +1244,7 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 			return ret;
 
 		return samsung_asoc_dma_platform_register(&pdev->dev,
-							  sec_dai->filter);
+					sec_dai->filter, "tx-sec", NULL);
 	}
 
 	pri_dai = i2s_alloc_dai(pdev, false);
@@ -1350,17 +1345,28 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	devm_snd_soc_register_component(&pri_dai->pdev->dev,
+	ret = devm_snd_soc_register_component(&pri_dai->pdev->dev,
 					&samsung_i2s_component,
 					&pri_dai->i2s_dai_drv, 1);
+	if (ret < 0)
+		goto err_free_dai;
+
+	ret = samsung_asoc_dma_platform_register(&pdev->dev, pri_dai->filter,
+						 NULL, NULL);
+	if (ret < 0)
+		goto err_free_dai;
 
 	pm_runtime_enable(&pdev->dev);
 
-	ret = samsung_asoc_dma_platform_register(&pdev->dev, pri_dai->filter);
-	if (ret != 0)
-		return ret;
+	ret = i2s_register_clock_provider(pdev);
+	if (!ret)
+		return 0;
 
-	return i2s_register_clock_provider(pdev);
+	pm_runtime_disable(&pdev->dev);
+err_free_dai:
+	if (sec_dai)
+		i2s_free_sec_dai(sec_dai);
+	return ret;
 }
 
 static int samsung_i2s_remove(struct platform_device *pdev)
@@ -1477,10 +1483,6 @@ static const struct samsung_i2s_dai_data i2sv5_dai_type_i2s1 = {
 	.i2s_variant_regs = &i2sv5_i2s1_regs,
 };
 
-static const struct samsung_i2s_dai_data samsung_dai_type_pri = {
-	.dai_type = TYPE_PRI,
-};
-
 static const struct samsung_i2s_dai_data samsung_dai_type_sec = {
 	.dai_type = TYPE_SEC,
 };
@@ -1492,9 +1494,6 @@ static const struct platform_device_id samsung_i2s_driver_ids[] = {
 	}, {
 		.name           = "samsung-i2s-sec",
 		.driver_data    = (kernel_ulong_t)&samsung_dai_type_sec,
-	}, {
-		.name		= "samsung-i2sv4",
-		.driver_data	= (kernel_ulong_t)&i2sv5_dai_type,
 	},
 	{},
 };
diff --git a/sound/soc/samsung/odroidx2_max98090.c b/sound/soc/samsung/odroidx2_max98090.c
deleted file mode 100644
index 04217279fe25..000000000000
--- a/sound/soc/samsung/odroidx2_max98090.c
+++ /dev/null
@@ -1,185 +0,0 @@
-/*
- * Copyright (C) 2014 Samsung Electronics Co., Ltd.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <linux/of.h>
-#include <linux/module.h>
-#include <sound/soc.h>
-#include <sound/pcm_params.h>
-#include "i2s.h"
-
-struct odroidx2_drv_data {
-	const struct snd_soc_dapm_widget *dapm_widgets;
-	unsigned int num_dapm_widgets;
-};
-
-/* The I2S CDCLK output clock frequency for the MAX98090 codec */
-#define MAX98090_MCLK 19200000
-
-static struct snd_soc_dai_link odroidx2_dai[];
-
-static int odroidx2_late_probe(struct snd_soc_card *card)
-{
-	struct snd_soc_pcm_runtime *rtd;
-	struct snd_soc_dai *codec_dai;
-	struct snd_soc_dai *cpu_dai;
-	int ret;
-
-	rtd = snd_soc_get_pcm_runtime(card, card->dai_link[0].name);
-	codec_dai = rtd->codec_dai;
-	cpu_dai = rtd->cpu_dai;
-
-	ret = snd_soc_dai_set_sysclk(codec_dai, 0, MAX98090_MCLK,
-						SND_SOC_CLOCK_IN);
-
-	if (ret < 0 || of_find_property(odroidx2_dai[0].codec_of_node,
-					"clocks", NULL))
-		return ret;
-
-	/* Set the cpu DAI configuration in order to use CDCLK */
-	return snd_soc_dai_set_sysclk(cpu_dai, SAMSUNG_I2S_CDCLK,
-					0, SND_SOC_CLOCK_OUT);
-}
-
-static const struct snd_soc_dapm_widget odroidx2_dapm_widgets[] = {
-	SND_SOC_DAPM_HP("Headphone Jack", NULL),
-	SND_SOC_DAPM_MIC("Mic Jack", NULL),
-	SND_SOC_DAPM_MIC("DMIC", NULL),
-};
-
-static const struct snd_soc_dapm_widget odroidu3_dapm_widgets[] = {
-	SND_SOC_DAPM_HP("Headphone Jack", NULL),
-	SND_SOC_DAPM_SPK("Speakers", NULL),
-};
-
-static struct snd_soc_dai_link odroidx2_dai[] = {
-	{
-		.name		= "MAX98090",
-		.stream_name	= "MAX98090 PCM",
-		.codec_dai_name	= "HiFi",
-		.dai_fmt	= SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
-				  SND_SOC_DAIFMT_CBM_CFM,
-	}
-};
-
-static struct snd_soc_card odroidx2 = {
-	.owner			= THIS_MODULE,
-	.dai_link		= odroidx2_dai,
-	.num_links		= ARRAY_SIZE(odroidx2_dai),
-	.fully_routed		= true,
-	.late_probe		= odroidx2_late_probe,
-};
-
-static const struct odroidx2_drv_data odroidx2_drvdata = {
-	.dapm_widgets		= odroidx2_dapm_widgets,
-	.num_dapm_widgets	= ARRAY_SIZE(odroidx2_dapm_widgets),
-};
-
-static const struct odroidx2_drv_data odroidu3_drvdata = {
-	.dapm_widgets		= odroidu3_dapm_widgets,
-	.num_dapm_widgets	= ARRAY_SIZE(odroidu3_dapm_widgets),
-};
-
-static const struct of_device_id odroidx2_audio_of_match[] = {
-	{
-		.compatible	= "samsung,odroidx2-audio",
-		.data		= &odroidx2_drvdata,
-	}, {
-		.compatible	= "samsung,odroidu3-audio",
-		.data		= &odroidu3_drvdata,
-	},
-	{ },
-};
-MODULE_DEVICE_TABLE(of, odroidx2_audio_of_match);
-
-static int odroidx2_audio_probe(struct platform_device *pdev)
-{
-	struct device_node *snd_node = pdev->dev.of_node;
-	struct snd_soc_card *card = &odroidx2;
-	struct device_node *i2s_node, *codec_node;
-	struct odroidx2_drv_data *dd;
-	const struct of_device_id *of_id;
-	int ret;
-
-	of_id = of_match_node(odroidx2_audio_of_match, snd_node);
-	dd = (struct odroidx2_drv_data *)of_id->data;
-
-	card->num_dapm_widgets = dd->num_dapm_widgets;
-	card->dapm_widgets = dd->dapm_widgets;
-
-	card->dev = &pdev->dev;
-
-	ret = snd_soc_of_parse_card_name(card, "samsung,model");
-	if (ret < 0)
-		return ret;
-
-	ret = snd_soc_of_parse_audio_routing(card, "samsung,audio-routing");
-	if (ret < 0)
-		return ret;
-
-	codec_node = of_parse_phandle(snd_node, "samsung,audio-codec", 0);
-	if (!codec_node) {
-		dev_err(&pdev->dev,
-			"Failed parsing samsung,i2s-codec property\n");
-		return -EINVAL;
-	}
-
-	i2s_node = of_parse_phandle(snd_node, "samsung,i2s-controller", 0);
-	if (!i2s_node) {
-		dev_err(&pdev->dev,
-			"Failed parsing samsung,i2s-controller property\n");
-		ret = -EINVAL;
-		goto err_put_codec_n;
-	}
-
-	odroidx2_dai[0].codec_of_node = codec_node;
-	odroidx2_dai[0].cpu_of_node = i2s_node;
-	odroidx2_dai[0].platform_of_node = i2s_node;
-
-	ret = snd_soc_register_card(card);
-	if (ret) {
-		dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n",
-			ret);
-		goto err_put_i2s_n;
-	}
-	return 0;
-
-err_put_i2s_n:
-	of_node_put(i2s_node);
-err_put_codec_n:
-	of_node_put(codec_node);
-	return ret;
-}
-
-static int odroidx2_audio_remove(struct platform_device *pdev)
-{
-	struct snd_soc_card *card = platform_get_drvdata(pdev);
-
-	snd_soc_unregister_card(card);
-
-	of_node_put(odroidx2_dai[0].cpu_of_node);
-	of_node_put(odroidx2_dai[0].codec_of_node);
-
-	return 0;
-}
-
-static struct platform_driver odroidx2_audio_driver = {
-	.driver = {
-		.name		= "odroidx2-audio",
-		.of_match_table	= odroidx2_audio_of_match,
-		.pm		= &snd_soc_pm_ops,
-	},
-	.probe	= odroidx2_audio_probe,
-	.remove	= odroidx2_audio_remove,
-};
-module_platform_driver(odroidx2_audio_driver);
-
-MODULE_AUTHOR("Chen Zhen <zhen1.chen@samsung.com>");
-MODULE_AUTHOR("Sylwester Nawrocki <s.nawrocki@samsung.com>");
-MODULE_DESCRIPTION("ALSA SoC Odroid X2/U3 Audio Support");
-MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/samsung/pcm.c b/sound/soc/samsung/pcm.c
index 498f563a4c9c..490c1a87fd66 100644
--- a/sound/soc/samsung/pcm.c
+++ b/sound/soc/samsung/pcm.c
@@ -576,7 +576,8 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev)
 		goto err5;
 	}
 
-	ret = samsung_asoc_dma_platform_register(&pdev->dev, filter);
+	ret = samsung_asoc_dma_platform_register(&pdev->dev, filter,
+						 NULL, NULL);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to get register DMA: %d\n", ret);
 		goto err5;
diff --git a/sound/soc/samsung/s3c-i2s-v2.c b/sound/soc/samsung/s3c-i2s-v2.c
index b6ab3fc5789e..bf8ae79b0fd2 100644
--- a/sound/soc/samsung/s3c-i2s-v2.c
+++ b/sound/soc/samsung/s3c-i2s-v2.c
@@ -268,7 +268,7 @@ static int s3c2412_i2s_set_fmt(struct snd_soc_dai *cpu_dai,
 		iismod &= ~S3C2412_IISMOD_SLAVE;
 		break;
 	default:
-		pr_err("unknwon master/slave format\n");
+		pr_err("unknown master/slave format\n");
 		return -EINVAL;
 	}
 
diff --git a/sound/soc/samsung/s3c2412-i2s.c b/sound/soc/samsung/s3c2412-i2s.c
index 204029d12f5b..d45dffb297d8 100644
--- a/sound/soc/samsung/s3c2412-i2s.c
+++ b/sound/soc/samsung/s3c2412-i2s.c
@@ -177,7 +177,8 @@ static int s3c2412_iis_dev_probe(struct platform_device *pdev)
 	}
 
 	ret = samsung_asoc_dma_platform_register(&pdev->dev,
-						 pdata->dma_filter);
+						 pdata->dma_filter,
+						 NULL, NULL);
 	if (ret)
 		pr_err("failed to register the DMA: %d\n", ret);
 
diff --git a/sound/soc/samsung/s3c24xx-i2s.c b/sound/soc/samsung/s3c24xx-i2s.c
index b3a475d73ba7..3e76f2a75a24 100644
--- a/sound/soc/samsung/s3c24xx-i2s.c
+++ b/sound/soc/samsung/s3c24xx-i2s.c
@@ -482,7 +482,8 @@ static int s3c24xx_iis_dev_probe(struct platform_device *pdev)
 	}
 
 	ret = samsung_asoc_dma_platform_register(&pdev->dev,
-						 pdata->dma_filter);
+						 pdata->dma_filter,
+						 NULL, NULL);
 	if (ret)
 		pr_err("failed to register the dma: %d\n", ret);
 
diff --git a/sound/soc/samsung/spdif.c b/sound/soc/samsung/spdif.c
index 4687f521197c..0cb9c8567546 100644
--- a/sound/soc/samsung/spdif.c
+++ b/sound/soc/samsung/spdif.c
@@ -435,7 +435,8 @@ static int spdif_probe(struct platform_device *pdev)
 
 	spdif->dma_playback = &spdif_stereo_out;
 
-	ret = samsung_asoc_dma_platform_register(&pdev->dev, filter);
+	ret = samsung_asoc_dma_platform_register(&pdev->dev, filter,
+						 NULL, NULL);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register DMA: %d\n", ret);
 		goto err4;
diff --git a/sound/soc/sh/Kconfig b/sound/soc/sh/Kconfig
index c9902a6d6fa0..9311f119feb5 100644
--- a/sound/soc/sh/Kconfig
+++ b/sound/soc/sh/Kconfig
@@ -44,6 +44,7 @@ config SND_SOC_RCAR
 
 config SND_SOC_RSRC_CARD
 	tristate "Renesas Sampling Rate Convert Sound Card"
+	select SND_SIMPLE_CARD_UTILS
 	help
 	  This option enables simple sound if you need sampling rate convert
 
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index c4c51a4d3c8f..2145957d0229 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -33,11 +33,15 @@ struct rsnd_adg {
 	struct clk *clkout[CLKOUTMAX];
 	struct clk_onecell_data onecell;
 	struct rsnd_mod mod;
+	u32 flags;
 
 	int rbga_rate_for_441khz; /* RBGA */
 	int rbgb_rate_for_48khz;  /* RBGB */
 };
 
+#define LRCLK_ASYNC	(1 << 0)
+#define adg_mode_flags(adg)	(adg->flags)
+
 #define for_each_rsnd_clk(pos, adg, i)		\
 	for (i = 0;				\
 	     (i < CLKMAX) &&			\
@@ -355,6 +359,16 @@ found_clock:
 
 	rsnd_adg_set_ssi_clk(ssi_mod, data);
 
+	if (!(adg_mode_flags(adg) & LRCLK_ASYNC)) {
+		struct rsnd_mod *adg_mod = rsnd_mod_get(adg);
+		u32 ckr = 0;
+
+		if (0 == (rate % 8000))
+			ckr = 0x80000000;
+
+		rsnd_mod_bset(adg_mod, SSICKR, 0x80000000, ckr);
+	}
+
 	dev_dbg(dev, "ADG: %s[%d] selects 0x%x for %d\n",
 		rsnd_mod_name(ssi_mod), rsnd_mod_id(ssi_mod),
 		data, rate);
@@ -532,6 +546,7 @@ int rsnd_adg_probe(struct rsnd_priv *priv)
 {
 	struct rsnd_adg *adg;
 	struct device *dev = rsnd_priv_to_dev(priv);
+	struct device_node *np = dev->of_node;
 
 	adg = devm_kzalloc(dev, sizeof(*adg), GFP_KERNEL);
 	if (!adg) {
@@ -545,6 +560,9 @@ int rsnd_adg_probe(struct rsnd_priv *priv)
 	rsnd_adg_get_clkin(priv, adg);
 	rsnd_adg_get_clkout(priv, adg);
 
+	if (of_get_property(np, "clkout-lr-asynchronous", NULL))
+		adg->flags = LRCLK_ASYNC;
+
 	priv->adg = adg;
 
 	return 0;
diff --git a/sound/soc/sh/rcar/gen.c b/sound/soc/sh/rcar/gen.c
index 46c0ba7b6414..7d2fdf8dd188 100644
--- a/sound/soc/sh/rcar/gen.c
+++ b/sound/soc/sh/rcar/gen.c
@@ -206,7 +206,7 @@ static int _rsnd_gen_regmap_init(struct rsnd_priv *priv,
  */
 static int rsnd_gen2_probe(struct rsnd_priv *priv)
 {
-	const static struct rsnd_regmap_field_conf conf_ssiu[] = {
+	static const struct rsnd_regmap_field_conf conf_ssiu[] = {
 		RSND_GEN_S_REG(SSI_MODE0,	0x800),
 		RSND_GEN_S_REG(SSI_MODE1,	0x804),
 		RSND_GEN_S_REG(SSI_MODE2,	0x808),
@@ -221,7 +221,7 @@ static int rsnd_gen2_probe(struct rsnd_priv *priv)
 		RSND_GEN_M_REG(SSI_INT_ENABLE,	0x18,	0x80),
 	};
 
-	const static struct rsnd_regmap_field_conf conf_scu[] = {
+	static const struct rsnd_regmap_field_conf conf_scu[] = {
 		RSND_GEN_M_REG(SRC_I_BUSIF_MODE,0x0,	0x20),
 		RSND_GEN_M_REG(SRC_O_BUSIF_MODE,0x4,	0x20),
 		RSND_GEN_M_REG(SRC_BUSIF_DALIGN,0x8,	0x20),
@@ -308,7 +308,7 @@ static int rsnd_gen2_probe(struct rsnd_priv *priv)
 		RSND_GEN_M_REG(DVC_VOL7R,	0xe44,	0x100),
 		RSND_GEN_M_REG(DVC_DVUER,	0xe48,	0x100),
 	};
-	const static struct rsnd_regmap_field_conf conf_adg[] = {
+	static const struct rsnd_regmap_field_conf conf_adg[] = {
 		RSND_GEN_S_REG(BRRA,		0x00),
 		RSND_GEN_S_REG(BRRB,		0x04),
 		RSND_GEN_S_REG(SSICKR,		0x08),
@@ -328,7 +328,7 @@ static int rsnd_gen2_probe(struct rsnd_priv *priv)
 		RSND_GEN_S_REG(SRCOUT_TIMSEL4,	0x58),
 		RSND_GEN_S_REG(CMDOUT_TIMSEL,	0x5c),
 	};
-	const static struct rsnd_regmap_field_conf conf_ssi[] = {
+	static const struct rsnd_regmap_field_conf conf_ssi[] = {
 		RSND_GEN_M_REG(SSICR,		0x00,	0x40),
 		RSND_GEN_M_REG(SSISR,		0x04,	0x40),
 		RSND_GEN_M_REG(SSITDR,		0x08,	0x40),
@@ -359,14 +359,14 @@ static int rsnd_gen2_probe(struct rsnd_priv *priv)
 
 static int rsnd_gen1_probe(struct rsnd_priv *priv)
 {
-	const static struct rsnd_regmap_field_conf conf_adg[] = {
+	static const struct rsnd_regmap_field_conf conf_adg[] = {
 		RSND_GEN_S_REG(BRRA,		0x00),
 		RSND_GEN_S_REG(BRRB,		0x04),
 		RSND_GEN_S_REG(SSICKR,		0x08),
 		RSND_GEN_S_REG(AUDIO_CLK_SEL0,	0x0c),
 		RSND_GEN_S_REG(AUDIO_CLK_SEL1,	0x10),
 	};
-	const static struct rsnd_regmap_field_conf conf_ssi[] = {
+	static const struct rsnd_regmap_field_conf conf_ssi[] = {
 		RSND_GEN_M_REG(SSICR,		0x00,	0x40),
 		RSND_GEN_M_REG(SSISR,		0x04,	0x40),
 		RSND_GEN_M_REG(SSITDR,		0x08,	0x40),
diff --git a/sound/soc/sh/rcar/rsrc-card.c b/sound/soc/sh/rcar/rsrc-card.c
index 1bc7ecfc42a9..fa37f842b62f 100644
--- a/sound/soc/sh/rcar/rsrc-card.c
+++ b/sound/soc/sh/rcar/rsrc-card.c
@@ -20,6 +20,7 @@
 #include <sound/jack.h>
 #include <sound/soc.h>
 #include <sound/soc-dai.h>
+#include <sound/simple_card_utils.h>
 
 struct rsrc_card_of_data {
 	const char *prefix;
@@ -46,25 +47,13 @@ static const struct of_device_id rsrc_card_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, rsrc_card_of_match);
 
-#define DAI_NAME_NUM	32
-struct rsrc_card_dai {
-	unsigned int sysclk;
-	unsigned int tx_slot_mask;
-	unsigned int rx_slot_mask;
-	int slots;
-	int slot_width;
-	struct clk *clk;
-	char dai_name[DAI_NAME_NUM];
-};
-
 #define IDX_CPU		0
 #define IDX_CODEC	1
 struct rsrc_card_priv {
 	struct snd_soc_card snd_card;
 	struct snd_soc_codec_conf codec_conf;
-	struct rsrc_card_dai *dai_props;
+	struct asoc_simple_dai *dai_props;
 	struct snd_soc_dai_link *dai_link;
-	int dai_num;
 	u32 convert_rate;
 	u32 convert_channels;
 };
@@ -77,7 +66,7 @@ static int rsrc_card_startup(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct rsrc_card_priv *priv =	snd_soc_card_get_drvdata(rtd->card);
-	struct rsrc_card_dai *dai_props =
+	struct asoc_simple_dai *dai_props =
 		rsrc_priv_to_props(priv, rtd->num);
 
 	return clk_prepare_enable(dai_props->clk);
@@ -87,7 +76,7 @@ static void rsrc_card_shutdown(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct rsrc_card_priv *priv =	snd_soc_card_get_drvdata(rtd->card);
-	struct rsrc_card_dai *dai_props =
+	struct asoc_simple_dai *dai_props =
 		rsrc_priv_to_props(priv, rtd->num);
 
 	clk_disable_unprepare(dai_props->clk);
@@ -103,7 +92,7 @@ static int rsrc_card_dai_init(struct snd_soc_pcm_runtime *rtd)
 	struct rsrc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card);
 	struct snd_soc_dai *dai;
 	struct snd_soc_dai_link *dai_link;
-	struct rsrc_card_dai *dai_props;
+	struct asoc_simple_dai *dai_props;
 	int num = rtd->num;
 	int ret;
 
@@ -159,44 +148,13 @@ static int rsrc_card_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
 	return 0;
 }
 
-static int rsrc_card_parse_daifmt(struct device_node *node,
-				  struct device_node *codec,
-				  struct rsrc_card_priv *priv,
-				  struct snd_soc_dai_link *dai_link,
-				  unsigned int *retfmt)
-{
-	struct device_node *bitclkmaster = NULL;
-	struct device_node *framemaster = NULL;
-	unsigned int daifmt;
-
-	daifmt = snd_soc_of_parse_daifmt(node, NULL,
-					 &bitclkmaster, &framemaster);
-	daifmt &= ~SND_SOC_DAIFMT_MASTER_MASK;
-
-	if (!bitclkmaster && !framemaster)
-		return -EINVAL;
-
-	if (codec == bitclkmaster)
-		daifmt |= (codec == framemaster) ?
-			SND_SOC_DAIFMT_CBM_CFM : SND_SOC_DAIFMT_CBM_CFS;
-	else
-		daifmt |= (codec == framemaster) ?
-			SND_SOC_DAIFMT_CBS_CFM : SND_SOC_DAIFMT_CBS_CFS;
-
-	of_node_put(bitclkmaster);
-	of_node_put(framemaster);
-
-	*retfmt = daifmt;
-
-	return 0;
-}
-
 static int rsrc_card_parse_links(struct device_node *np,
 				 struct rsrc_card_priv *priv,
 				 int idx, bool is_fe)
 {
+	struct device *dev = rsrc_priv_to_dev(priv);
 	struct snd_soc_dai_link *dai_link = rsrc_priv_to_link(priv, idx);
-	struct rsrc_card_dai *dai_props = rsrc_priv_to_props(priv, idx);
+	struct asoc_simple_dai *dai_props = rsrc_priv_to_props(priv, idx);
 	struct of_phandle_args args;
 	int ret;
 
@@ -232,9 +190,11 @@ static int rsrc_card_parse_links(struct device_node *np,
 		if (ret < 0)
 			return ret;
 
-		/* set dai_name */
-		snprintf(dai_props->dai_name, DAI_NAME_NUM, "fe.%s",
-			 dai_link->cpu_dai_name);
+		ret = asoc_simple_card_set_dailink_name(dev, dai_link,
+							"fe.%s",
+							dai_link->cpu_dai_name);
+		if (ret < 0)
+			return ret;
 
 		/*
 		 * In soc_bind_dai_link() will check cpu name after
@@ -248,7 +208,6 @@ static int rsrc_card_parse_links(struct device_node *np,
 		if (!args.args_count)
 			dai_link->cpu_dai_name = NULL;
 	} else {
-		struct device *dev = rsrc_priv_to_dev(priv);
 		const struct rsrc_card_of_data *of_data;
 
 		of_data = of_device_get_match_data(dev);
@@ -266,6 +225,12 @@ static int rsrc_card_parse_links(struct device_node *np,
 		if (ret < 0)
 			return ret;
 
+		ret = asoc_simple_card_set_dailink_name(dev, dai_link,
+							"be.%s",
+							dai_link->codec_dai_name);
+		if (ret < 0)
+			return ret;
+
 		/* additional name prefix */
 		if (of_data) {
 			priv->codec_conf.of_node = dai_link->codec_of_node;
@@ -276,18 +241,12 @@ static int rsrc_card_parse_links(struct device_node *np,
 						      dai_link->codec_of_node,
 						      "audio-prefix");
 		}
-
-		/* set dai_name */
-		snprintf(dai_props->dai_name, DAI_NAME_NUM, "be.%s",
-			 dai_link->codec_dai_name);
 	}
 
 	/* Simple Card assumes platform == cpu */
 	dai_link->platform_of_node	= dai_link->cpu_of_node;
 	dai_link->dpcm_playback		= 1;
 	dai_link->dpcm_capture		= 1;
-	dai_link->name			= dai_props->dai_name;
-	dai_link->stream_name		= dai_props->dai_name;
 	dai_link->ops			= &rsrc_card_ops;
 	dai_link->init			= rsrc_card_dai_init;
 
@@ -299,7 +258,7 @@ static int rsrc_card_parse_clk(struct device_node *np,
 			       int idx, bool is_fe)
 {
 	struct snd_soc_dai_link *dai_link = rsrc_priv_to_link(priv, idx);
-	struct rsrc_card_dai *dai_props = rsrc_priv_to_props(priv, idx);
+	struct asoc_simple_dai *dai_props = rsrc_priv_to_props(priv, idx);
 	struct clk *clk;
 	struct device_node *of_np = is_fe ?	dai_link->cpu_of_node :
 						dai_link->codec_of_node;
@@ -336,7 +295,7 @@ static int rsrc_card_dai_sub_link_of(struct device_node *node,
 {
 	struct device *dev = rsrc_priv_to_dev(priv);
 	struct snd_soc_dai_link *dai_link = rsrc_priv_to_link(priv, idx);
-	struct rsrc_card_dai *dai_props = rsrc_priv_to_props(priv, idx);
+	struct asoc_simple_dai *dai_props = rsrc_priv_to_props(priv, idx);
 	int ret;
 
 	ret = rsrc_card_parse_links(np, priv, idx, is_fe);
@@ -348,7 +307,7 @@ static int rsrc_card_dai_sub_link_of(struct device_node *node,
 		return ret;
 
 	dev_dbg(dev, "\t%s / %04x / %d\n",
-		dai_props->dai_name,
+		dai_link->name,
 		dai_link->dai_fmt,
 		dai_props->sysclk);
 
@@ -358,6 +317,7 @@ static int rsrc_card_dai_sub_link_of(struct device_node *node,
 static int rsrc_card_dai_link_of(struct device_node *node,
 				 struct rsrc_card_priv *priv)
 {
+	struct device *dev = rsrc_priv_to_dev(priv);
 	struct snd_soc_dai_link *dai_link;
 	struct device_node *np;
 	unsigned int daifmt = 0;
@@ -370,8 +330,8 @@ static int rsrc_card_dai_link_of(struct device_node *node,
 		dai_link = rsrc_priv_to_link(priv, i);
 
 		if (strcmp(np->name, "codec") == 0) {
-			ret = rsrc_card_parse_daifmt(node, np, priv,
-						     dai_link, &daifmt);
+			ret = asoc_simple_card_parse_daifmt(dev, node, np,
+							    NULL, &daifmt);
 			if (ret < 0)
 				return ret;
 			break;
@@ -402,7 +362,7 @@ static int rsrc_card_parse_of(struct device_node *node,
 			      struct device *dev)
 {
 	const struct rsrc_card_of_data *of_data = of_device_get_match_data(dev);
-	struct rsrc_card_dai *props;
+	struct asoc_simple_dai *props;
 	struct snd_soc_dai_link *links;
 	int ret;
 	int num;
@@ -418,7 +378,6 @@ static int rsrc_card_parse_of(struct device_node *node,
 
 	priv->dai_props	= props;
 	priv->dai_link	= links;
-	priv->dai_num	= num;
 
 	/* Init snd_soc_card */
 	priv->snd_card.owner			= THIS_MODULE;
@@ -436,9 +395,6 @@ static int rsrc_card_parse_of(struct device_node *node,
 					       "audio-routing");
 	}
 
-	/* Parse the card name from DT */
-	snd_soc_of_parse_card_name(&priv->snd_card, "card-name");
-
 	/* sampling rate convert */
 	of_property_read_u32(node, "convert-rate", &priv->convert_rate);
 
@@ -454,8 +410,9 @@ static int rsrc_card_parse_of(struct device_node *node,
 	if (ret < 0)
 		return ret;
 
-	if (!priv->snd_card.name)
-		priv->snd_card.name = priv->snd_card.dai_link->name;
+	ret = asoc_simple_card_parse_card_name(&priv->snd_card, "card-");
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index 875733c52953..d2df46c14c68 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -530,14 +530,15 @@ static int soc_compr_pointer(struct snd_compr_stream *cstream,
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
 	struct snd_soc_platform *platform = rtd->platform;
+	int ret = 0;
 
 	mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
 
 	if (platform->driver->compr_ops && platform->driver->compr_ops->pointer)
-		 platform->driver->compr_ops->pointer(cstream, tstamp);
+		ret = platform->driver->compr_ops->pointer(cstream, tstamp);
 
 	mutex_unlock(&rtd->pcm_mutex);
-	return 0;
+	return ret;
 }
 
 static int soc_compr_copy(struct snd_compr_stream *cstream,
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index c4464858bf01..8698c26773b3 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1073,7 +1073,11 @@ static int dapm_widget_list_create(struct snd_soc_dapm_widget_list **list,
  */
 static __always_inline int is_connected_ep(struct snd_soc_dapm_widget *widget,
 	struct list_head *list, enum snd_soc_dapm_direction dir,
-	int (*fn)(struct snd_soc_dapm_widget *, struct list_head *))
+	int (*fn)(struct snd_soc_dapm_widget *, struct list_head *,
+		  bool (*custom_stop_condition)(struct snd_soc_dapm_widget *,
+						enum snd_soc_dapm_direction)),
+	bool (*custom_stop_condition)(struct snd_soc_dapm_widget *,
+				      enum snd_soc_dapm_direction))
 {
 	enum snd_soc_dapm_direction rdir = SND_SOC_DAPM_DIR_REVERSE(dir);
 	struct snd_soc_dapm_path *path;
@@ -1088,6 +1092,11 @@ static __always_inline int is_connected_ep(struct snd_soc_dapm_widget *widget,
 	if (list)
 		list_add_tail(&widget->work_list, list);
 
+	if (custom_stop_condition && custom_stop_condition(widget, dir)) {
+		widget->endpoints[dir] = 1;
+		return widget->endpoints[dir];
+	}
+
 	if ((widget->is_ep & SND_SOC_DAPM_DIR_TO_EP(dir)) && widget->connected) {
 		widget->endpoints[dir] = snd_soc_dapm_suspend_check(widget);
 		return widget->endpoints[dir];
@@ -1106,7 +1115,7 @@ static __always_inline int is_connected_ep(struct snd_soc_dapm_widget *widget,
 
 		if (path->connect) {
 			path->walking = 1;
-			con += fn(path->node[dir], list);
+			con += fn(path->node[dir], list, custom_stop_condition);
 			path->walking = 0;
 		}
 	}
@@ -1119,23 +1128,37 @@ static __always_inline int is_connected_ep(struct snd_soc_dapm_widget *widget,
 /*
  * Recursively check for a completed path to an active or physically connected
  * output widget. Returns number of complete paths.
+ *
+ * Optionally, can be supplied with a function acting as a stopping condition.
+ * This function takes the dapm widget currently being examined and the walk
+ * direction as an arguments, it should return true if the walk should be
+ * stopped and false otherwise.
  */
 static int is_connected_output_ep(struct snd_soc_dapm_widget *widget,
-	struct list_head *list)
+	struct list_head *list,
+	bool (*custom_stop_condition)(struct snd_soc_dapm_widget *i,
+				      enum snd_soc_dapm_direction))
 {
 	return is_connected_ep(widget, list, SND_SOC_DAPM_DIR_OUT,
-			is_connected_output_ep);
+			is_connected_output_ep, custom_stop_condition);
 }
 
 /*
  * Recursively check for a completed path to an active or physically connected
  * input widget. Returns number of complete paths.
+ *
+ * Optionally, can be supplied with a function acting as a stopping condition.
+ * This function takes the dapm widget currently being examined and the walk
+ * direction as an arguments, it should return true if the walk should be
+ * stopped and false otherwise.
  */
 static int is_connected_input_ep(struct snd_soc_dapm_widget *widget,
-	struct list_head *list)
+	struct list_head *list,
+	bool (*custom_stop_condition)(struct snd_soc_dapm_widget *i,
+				      enum snd_soc_dapm_direction))
 {
 	return is_connected_ep(widget, list, SND_SOC_DAPM_DIR_IN,
-			is_connected_input_ep);
+			is_connected_input_ep, custom_stop_condition);
 }
 
 /**
@@ -1143,15 +1166,24 @@ static int is_connected_input_ep(struct snd_soc_dapm_widget *widget,
  * @dai: the soc DAI.
  * @stream: stream direction.
  * @list: list of active widgets for this stream.
+ * @custom_stop_condition: (optional) a function meant to stop the widget graph
+ *                         walk based on custom logic.
  *
  * Queries DAPM graph as to whether an valid audio stream path exists for
  * the initial stream specified by name. This takes into account
  * current mixer and mux kcontrol settings. Creates list of valid widgets.
  *
+ * Optionally, can be supplied with a function acting as a stopping condition.
+ * This function takes the dapm widget currently being examined and the walk
+ * direction as an arguments, it should return true if the walk should be
+ * stopped and false otherwise.
+ *
  * Returns the number of valid paths or negative error.
  */
 int snd_soc_dapm_dai_get_connected_widgets(struct snd_soc_dai *dai, int stream,
-	struct snd_soc_dapm_widget_list **list)
+	struct snd_soc_dapm_widget_list **list,
+	bool (*custom_stop_condition)(struct snd_soc_dapm_widget *,
+				      enum snd_soc_dapm_direction))
 {
 	struct snd_soc_card *card = dai->component->card;
 	struct snd_soc_dapm_widget *w;
@@ -1171,9 +1203,11 @@ int snd_soc_dapm_dai_get_connected_widgets(struct snd_soc_dai *dai, int stream,
 	}
 
 	if (stream == SNDRV_PCM_STREAM_PLAYBACK)
-		paths = is_connected_output_ep(dai->playback_widget, &widgets);
+		paths = is_connected_output_ep(dai->playback_widget, &widgets,
+				custom_stop_condition);
 	else
-		paths = is_connected_input_ep(dai->capture_widget, &widgets);
+		paths = is_connected_input_ep(dai->capture_widget, &widgets,
+				custom_stop_condition);
 
 	/* Drop starting point */
 	list_del(widgets.next);
@@ -1268,8 +1302,8 @@ static int dapm_generic_check_power(struct snd_soc_dapm_widget *w)
 
 	DAPM_UPDATE_STAT(w, power_checks);
 
-	in = is_connected_input_ep(w, NULL);
-	out = is_connected_output_ep(w, NULL);
+	in = is_connected_input_ep(w, NULL, NULL);
+	out = is_connected_output_ep(w, NULL, NULL);
 	return out != 0 && in != 0;
 }
 
@@ -1928,8 +1962,8 @@ static ssize_t dapm_widget_power_read_file(struct file *file,
 		in = 0;
 		out = 0;
 	} else {
-		in = is_connected_input_ep(w, NULL);
-		out = is_connected_output_ep(w, NULL);
+		in = is_connected_input_ep(w, NULL, NULL);
+		out = is_connected_output_ep(w, NULL, NULL);
 	}
 
 	ret = snprintf(buf, PAGE_SIZE, "%s: %s%s  in %d out %d",
@@ -3282,6 +3316,7 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm,
 	mutex_unlock(&dapm->card->dapm_mutex);
 	return w;
 }
+EXPORT_SYMBOL_GPL(snd_soc_dapm_new_control);
 
 struct snd_soc_dapm_widget *
 snd_soc_dapm_new_control_unlocked(struct snd_soc_dapm_context *dapm,
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index aa99dac31b3b..60d702f8b9f0 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1287,6 +1287,46 @@ static int widget_in_list(struct snd_soc_dapm_widget_list *list,
 	return 0;
 }
 
+static bool dpcm_end_walk_at_be(struct snd_soc_dapm_widget *widget,
+		enum snd_soc_dapm_direction dir)
+{
+	struct snd_soc_card *card = widget->dapm->card;
+	struct snd_soc_pcm_runtime *rtd;
+	int i;
+
+	if (dir == SND_SOC_DAPM_DIR_OUT) {
+		list_for_each_entry(rtd, &card->rtd_list, list) {
+			if (!rtd->dai_link->no_pcm)
+				continue;
+
+			if (rtd->cpu_dai->playback_widget == widget)
+				return true;
+
+			for (i = 0; i < rtd->num_codecs; ++i) {
+				struct snd_soc_dai *dai = rtd->codec_dais[i];
+				if (dai->playback_widget == widget)
+					return true;
+			}
+		}
+	} else { /* SND_SOC_DAPM_DIR_IN */
+		list_for_each_entry(rtd, &card->rtd_list, list) {
+			if (!rtd->dai_link->no_pcm)
+				continue;
+
+			if (rtd->cpu_dai->capture_widget == widget)
+				return true;
+
+			for (i = 0; i < rtd->num_codecs; ++i) {
+				struct snd_soc_dai *dai = rtd->codec_dais[i];
+				if (dai->capture_widget == widget)
+					return true;
+			}
+		}
+	}
+
+	return false;
+}
+
 int dpcm_path_get(struct snd_soc_pcm_runtime *fe,
 	int stream, struct snd_soc_dapm_widget_list **list)
 {
@@ -1294,7 +1334,8 @@ int dpcm_path_get(struct snd_soc_pcm_runtime *fe,
 	int paths;
 
 	/* get number of valid DAI paths and their widgets */
-	paths = snd_soc_dapm_dai_get_connected_widgets(cpu_dai, stream, list);
+	paths = snd_soc_dapm_dai_get_connected_widgets(cpu_dai, stream, list,
+			dpcm_end_walk_at_be);
 
 	dev_dbg(fe->dev, "ASoC: found %d audio %s paths\n", paths,
 			stream ? "capture" : "playback");
diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index ee1c7c245bc7..1ac2db205a0d 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -1029,9 +1029,9 @@ static int uni_player_parse_dt_audio_glue(struct platform_device *pdev,
 
 	regmap = syscon_regmap_lookup_by_phandle(node, "st,syscfg");
 
-	if (!regmap) {
+	if (IS_ERR(regmap)) {
 		dev_err(&pdev->dev, "sti-audio-clk-glue syscf not found\n");
-		return -EINVAL;
+		return PTR_ERR(regmap);
 	}
 
 	player->clk_sel = regmap_field_alloc(regmap, regfield[0]);
diff --git a/sound/soc/sunxi/Kconfig b/sound/soc/sunxi/Kconfig
index ae42294ef688..2a954bd01fd8 100644
--- a/sound/soc/sunxi/Kconfig
+++ b/sound/soc/sunxi/Kconfig
@@ -8,6 +8,15 @@ config SND_SUN4I_CODEC
 	  Select Y or M to add support for the Codec embedded in the Allwinner
 	  A10 and affiliated SoCs.
 
+config SND_SUN4I_I2S
+	tristate "Allwinner A10 I2S Support"
+	select SND_SOC_GENERIC_DMAENGINE_PCM
+	select REGMAP_MMIO
+	help
+	  Say Y or M if you want to add support for codecs attached to
+	  the Allwinner A10 I2S. You will also need to select the
+	  individual machine drivers to support below.
+
 config SND_SUN4I_SPDIF
 	tristate "Allwinner A10 SPDIF Support"
 	depends on OF
diff --git a/sound/soc/sunxi/Makefile b/sound/soc/sunxi/Makefile
index 8f5e889667f1..604c7b842837 100644
--- a/sound/soc/sunxi/Makefile
+++ b/sound/soc/sunxi/Makefile
@@ -1,3 +1,3 @@
 obj-$(CONFIG_SND_SUN4I_CODEC) += sun4i-codec.o
-
+obj-$(CONFIG_SND_SUN4I_I2S) += sun4i-i2s.o
 obj-$(CONFIG_SND_SUN4I_SPDIF) += sun4i-spdif.o
diff --git a/sound/soc/sunxi/sun4i-i2s.c b/sound/soc/sunxi/sun4i-i2s.c
new file mode 100644
index 000000000000..687a8f83dbe5
--- /dev/null
+++ b/sound/soc/sunxi/sun4i-i2s.c
@@ -0,0 +1,701 @@
+/*
+ * Copyright (C) 2015 Andrea Venturi
+ * Andrea Venturi <be17068@iperbole.bo.it>
+ *
+ * Copyright (C) 2016 Maxime Ripard
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/dmaengine.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+
+#include <sound/dmaengine_pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#define SUN4I_I2S_CTRL_REG		0x00
+#define SUN4I_I2S_CTRL_SDO_EN_MASK		GENMASK(11, 8)
+#define SUN4I_I2S_CTRL_SDO_EN(sdo)			BIT(8 + (sdo))
+#define SUN4I_I2S_CTRL_MODE_MASK		BIT(5)
+#define SUN4I_I2S_CTRL_MODE_SLAVE			(1 << 5)
+#define SUN4I_I2S_CTRL_MODE_MASTER			(0 << 5)
+#define SUN4I_I2S_CTRL_TX_EN			BIT(2)
+#define SUN4I_I2S_CTRL_RX_EN			BIT(1)
+#define SUN4I_I2S_CTRL_GL_EN			BIT(0)
+
+#define SUN4I_I2S_FMT0_REG		0x04
+#define SUN4I_I2S_FMT0_LRCLK_POLARITY_MASK	BIT(7)
+#define SUN4I_I2S_FMT0_LRCLK_POLARITY_INVERTED		(1 << 7)
+#define SUN4I_I2S_FMT0_LRCLK_POLARITY_NORMAL		(0 << 7)
+#define SUN4I_I2S_FMT0_BCLK_POLARITY_MASK	BIT(6)
+#define SUN4I_I2S_FMT0_BCLK_POLARITY_INVERTED		(1 << 6)
+#define SUN4I_I2S_FMT0_BCLK_POLARITY_NORMAL		(0 << 6)
+#define SUN4I_I2S_FMT0_SR_MASK			GENMASK(5, 4)
+#define SUN4I_I2S_FMT0_SR(sr)				((sr) << 4)
+#define SUN4I_I2S_FMT0_WSS_MASK			GENMASK(3, 2)
+#define SUN4I_I2S_FMT0_WSS(wss)				((wss) << 2)
+#define SUN4I_I2S_FMT0_FMT_MASK			GENMASK(1, 0)
+#define SUN4I_I2S_FMT0_FMT_RIGHT_J			(2 << 0)
+#define SUN4I_I2S_FMT0_FMT_LEFT_J			(1 << 0)
+#define SUN4I_I2S_FMT0_FMT_I2S				(0 << 0)
+
+#define SUN4I_I2S_FMT1_REG		0x08
+#define SUN4I_I2S_FIFO_TX_REG		0x0c
+#define SUN4I_I2S_FIFO_RX_REG		0x10
+
+#define SUN4I_I2S_FIFO_CTRL_REG		0x14
+#define SUN4I_I2S_FIFO_CTRL_FLUSH_TX		BIT(25)
+#define SUN4I_I2S_FIFO_CTRL_FLUSH_RX		BIT(24)
+#define SUN4I_I2S_FIFO_CTRL_TX_MODE_MASK	BIT(2)
+#define SUN4I_I2S_FIFO_CTRL_TX_MODE(mode)		((mode) << 2)
+#define SUN4I_I2S_FIFO_CTRL_RX_MODE_MASK	GENMASK(1, 0)
+#define SUN4I_I2S_FIFO_CTRL_RX_MODE(mode)		(mode)
+
+#define SUN4I_I2S_FIFO_STA_REG		0x18
+
+#define SUN4I_I2S_DMA_INT_CTRL_REG	0x1c
+#define SUN4I_I2S_DMA_INT_CTRL_TX_DRQ_EN	BIT(7)
+#define SUN4I_I2S_DMA_INT_CTRL_RX_DRQ_EN	BIT(3)
+
+#define SUN4I_I2S_INT_STA_REG		0x20
+
+#define SUN4I_I2S_CLK_DIV_REG		0x24
+#define SUN4I_I2S_CLK_DIV_MCLK_EN		BIT(7)
+#define SUN4I_I2S_CLK_DIV_BCLK_MASK		GENMASK(6, 4)
+#define SUN4I_I2S_CLK_DIV_BCLK(bclk)			((bclk) << 4)
+#define SUN4I_I2S_CLK_DIV_MCLK_MASK		GENMASK(3, 0)
+#define SUN4I_I2S_CLK_DIV_MCLK(mclk)			((mclk) << 0)
+
+#define SUN4I_I2S_RX_CNT_REG		0x28
+#define SUN4I_I2S_TX_CNT_REG		0x2c
+
+#define SUN4I_I2S_TX_CHAN_SEL_REG	0x30
+#define SUN4I_I2S_TX_CHAN_SEL(num_chan)		(((num_chan) - 1) << 0)
+
+#define SUN4I_I2S_TX_CHAN_MAP_REG	0x34
+#define SUN4I_I2S_TX_CHAN_MAP(chan, sample)	((sample) << (chan << 2))
+
+#define SUN4I_I2S_RX_CHAN_SEL_REG	0x38
+#define SUN4I_I2S_RX_CHAN_MAP_REG	0x3c
+
+struct sun4i_i2s {
+	struct clk	*bus_clk;
+	struct clk	*mod_clk;
+	struct regmap	*regmap;
+
+	struct snd_dmaengine_dai_dma_data	playback_dma_data;
+};
+
+struct sun4i_i2s_clk_div {
+	u8	div;
+	u8	val;
+};
+
+static const struct sun4i_i2s_clk_div sun4i_i2s_bclk_div[] = {
+	{ .div = 2, .val = 0 },
+	{ .div = 4, .val = 1 },
+	{ .div = 6, .val = 2 },
+	{ .div = 8, .val = 3 },
+	{ .div = 12, .val = 4 },
+	{ .div = 16, .val = 5 },
+};
+
+static const struct sun4i_i2s_clk_div sun4i_i2s_mclk_div[] = {
+	{ .div = 1, .val = 0 },
+	{ .div = 2, .val = 1 },
+	{ .div = 4, .val = 2 },
+	{ .div = 6, .val = 3 },
+	{ .div = 8, .val = 4 },
+	{ .div = 12, .val = 5 },
+	{ .div = 16, .val = 6 },
+	{ .div = 24, .val = 7 },
+};
+
+static int sun4i_i2s_get_bclk_div(struct sun4i_i2s *i2s,
+				  unsigned int oversample_rate,
+				  unsigned int word_size)
+{
+	int div = oversample_rate / word_size / 2;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sun4i_i2s_bclk_div); i++) {
+		const struct sun4i_i2s_clk_div *bdiv = &sun4i_i2s_bclk_div[i];
+
+		if (bdiv->div == div)
+			return bdiv->val;
+	}
+
+	return -EINVAL;
+}
+
+static int sun4i_i2s_get_mclk_div(struct sun4i_i2s *i2s,
+				  unsigned int oversample_rate,
+				  unsigned int module_rate,
+				  unsigned int sampling_rate)
+{
+	int div = module_rate / sampling_rate / oversample_rate;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sun4i_i2s_mclk_div); i++) {
+		const struct sun4i_i2s_clk_div *mdiv = &sun4i_i2s_mclk_div[i];
+
+		if (mdiv->div == div)
+			return mdiv->val;
+	}
+
+	return -EINVAL;
+}
+
+static int sun4i_i2s_oversample_rates[] = { 128, 192, 256, 384, 512, 768 };
+
+static int sun4i_i2s_set_clk_rate(struct sun4i_i2s *i2s,
+				  unsigned int rate,
+				  unsigned int word_size)
+{
+	unsigned int clk_rate;
+	int bclk_div, mclk_div;
+	int ret, i;
+
+	switch (rate) {
+	case 176400:
+	case 88200:
+	case 44100:
+	case 22050:
+	case 11025:
+		clk_rate = 22579200;
+		break;
+
+	case 192000:
+	case 128000:
+	case 96000:
+	case 64000:
+	case 48000:
+	case 32000:
+	case 24000:
+	case 16000:
+	case 12000:
+	case 8000:
+		clk_rate = 24576000;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	ret = clk_set_rate(i2s->mod_clk, clk_rate);
+	if (ret)
+		return ret;
+
+	/* Always favor the highest oversampling rate */
+	for (i = (ARRAY_SIZE(sun4i_i2s_oversample_rates) - 1); i >= 0; i--) {
+		unsigned int oversample_rate = sun4i_i2s_oversample_rates[i];
+
+		bclk_div = sun4i_i2s_get_bclk_div(i2s, oversample_rate,
+						  word_size);
+		mclk_div = sun4i_i2s_get_mclk_div(i2s, oversample_rate,
+						  clk_rate,
+						  rate);
+
+		if ((bclk_div >= 0) && (mclk_div >= 0))
+			break;
+	}
+
+	if ((bclk_div < 0) || (mclk_div < 0))
+		return -EINVAL;
+
+	regmap_write(i2s->regmap, SUN4I_I2S_CLK_DIV_REG,
+		     SUN4I_I2S_CLK_DIV_BCLK(bclk_div) |
+		     SUN4I_I2S_CLK_DIV_MCLK(mclk_div) |
+		     SUN4I_I2S_CLK_DIV_MCLK_EN);
+
+	return 0;
+}
+
+static int sun4i_i2s_hw_params(struct snd_pcm_substream *substream,
+			       struct snd_pcm_hw_params *params,
+			       struct snd_soc_dai *dai)
+{
+	struct sun4i_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+	int sr, wss;
+	u32 width;
+
+	if (params_channels(params) != 2)
+		return -EINVAL;
+
+	switch (params_physical_width(params)) {
+	case 16:
+		width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+		break;
+	default:
+		return -EINVAL;
+	}
+	i2s->playback_dma_data.addr_width = width;
+
+	switch (params_width(params)) {
+	case 16:
+		sr = 0;
+		wss = 0;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_FMT0_REG,
+			   SUN4I_I2S_FMT0_WSS_MASK | SUN4I_I2S_FMT0_SR_MASK,
+			   SUN4I_I2S_FMT0_WSS(wss) | SUN4I_I2S_FMT0_SR(sr));
+
+	return sun4i_i2s_set_clk_rate(i2s, params_rate(params),
+				      params_width(params));
+}
+
+static int sun4i_i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct sun4i_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+	u32 val;
+
+	/* DAI Mode */
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		val = SUN4I_I2S_FMT0_FMT_I2S;
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		val = SUN4I_I2S_FMT0_FMT_LEFT_J;
+		break;
+	case SND_SOC_DAIFMT_RIGHT_J:
+		val = SUN4I_I2S_FMT0_FMT_RIGHT_J;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_FMT0_REG,
+			   SUN4I_I2S_FMT0_FMT_MASK,
+			   val);
+
+	/* DAI clock polarity */
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_IB_IF:
+		/* Invert both clocks */
+		val = SUN4I_I2S_FMT0_BCLK_POLARITY_INVERTED |
+			SUN4I_I2S_FMT0_LRCLK_POLARITY_INVERTED;
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		/* Invert bit clock */
+		val = SUN4I_I2S_FMT0_BCLK_POLARITY_INVERTED |
+			SUN4I_I2S_FMT0_LRCLK_POLARITY_NORMAL;
+		break;
+	case SND_SOC_DAIFMT_NB_IF:
+		/* Invert frame clock */
+		val = SUN4I_I2S_FMT0_LRCLK_POLARITY_INVERTED |
+			SUN4I_I2S_FMT0_BCLK_POLARITY_NORMAL;
+		break;
+	case SND_SOC_DAIFMT_NB_NF:
+		/* Nothing to do for both normal cases */
+		val = SUN4I_I2S_FMT0_BCLK_POLARITY_NORMAL |
+			SUN4I_I2S_FMT0_LRCLK_POLARITY_NORMAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_FMT0_REG,
+			   SUN4I_I2S_FMT0_BCLK_POLARITY_MASK |
+			   SUN4I_I2S_FMT0_LRCLK_POLARITY_MASK,
+			   val);
+
+	/* DAI clock master masks */
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBS_CFS:
+		/* BCLK and LRCLK master */
+		val = SUN4I_I2S_CTRL_MODE_MASTER;
+		break;
+	case SND_SOC_DAIFMT_CBM_CFM:
+		/* BCLK and LRCLK slave */
+		val = SUN4I_I2S_CTRL_MODE_SLAVE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_CTRL_REG,
+			   SUN4I_I2S_CTRL_MODE_MASK,
+			   val);
+
+	/* Set significant bits in our FIFOs */
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_FIFO_CTRL_REG,
+			   SUN4I_I2S_FIFO_CTRL_TX_MODE_MASK |
+			   SUN4I_I2S_FIFO_CTRL_RX_MODE_MASK,
+			   SUN4I_I2S_FIFO_CTRL_TX_MODE(1) |
+			   SUN4I_I2S_FIFO_CTRL_RX_MODE(1));
+	return 0;
+}
+
+static void sun4i_i2s_start_playback(struct sun4i_i2s *i2s)
+{
+	/* Flush TX FIFO */
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_FIFO_CTRL_REG,
+			   SUN4I_I2S_FIFO_CTRL_FLUSH_TX,
+			   SUN4I_I2S_FIFO_CTRL_FLUSH_TX);
+
+	/* Clear TX counter */
+	regmap_write(i2s->regmap, SUN4I_I2S_TX_CNT_REG, 0);
+
+	/* Enable TX Block */
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_CTRL_REG,
+			   SUN4I_I2S_CTRL_TX_EN,
+			   SUN4I_I2S_CTRL_TX_EN);
+
+	/* Enable TX DRQ */
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_DMA_INT_CTRL_REG,
+			   SUN4I_I2S_DMA_INT_CTRL_TX_DRQ_EN,
+			   SUN4I_I2S_DMA_INT_CTRL_TX_DRQ_EN);
+}
+
+
+static void sun4i_i2s_stop_playback(struct sun4i_i2s *i2s)
+{
+	/* Disable TX Block */
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_CTRL_REG,
+			   SUN4I_I2S_CTRL_TX_EN,
+			   0);
+
+	/* Disable TX DRQ */
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_DMA_INT_CTRL_REG,
+			   SUN4I_I2S_DMA_INT_CTRL_TX_DRQ_EN,
+			   0);
+}
+
+static int sun4i_i2s_trigger(struct snd_pcm_substream *substream, int cmd,
+			     struct snd_soc_dai *dai)
+{
+	struct sun4i_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+	case SNDRV_PCM_TRIGGER_RESUME:
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+			sun4i_i2s_start_playback(i2s);
+		else
+			return -EINVAL;
+		break;
+
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+			sun4i_i2s_stop_playback(i2s);
+		else
+			return -EINVAL;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int sun4i_i2s_startup(struct snd_pcm_substream *substream,
+			     struct snd_soc_dai *dai)
+{
+	struct sun4i_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+
+	/* Enable the whole hardware block */
+	regmap_write(i2s->regmap, SUN4I_I2S_CTRL_REG,
+		     SUN4I_I2S_CTRL_GL_EN);
+
+	/* Enable the first output line */
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_CTRL_REG,
+			   SUN4I_I2S_CTRL_SDO_EN_MASK,
+			   SUN4I_I2S_CTRL_SDO_EN(0));
+
+	/* Enable the first two channels */
+	regmap_write(i2s->regmap, SUN4I_I2S_TX_CHAN_SEL_REG,
+		     SUN4I_I2S_TX_CHAN_SEL(2));
+
+	/* Map them to the two first samples coming in */
+	regmap_write(i2s->regmap, SUN4I_I2S_TX_CHAN_MAP_REG,
+		     SUN4I_I2S_TX_CHAN_MAP(0, 0) | SUN4I_I2S_TX_CHAN_MAP(1, 1));
+
+	return clk_prepare_enable(i2s->mod_clk);
+}
+
+static void sun4i_i2s_shutdown(struct snd_pcm_substream *substream,
+			       struct snd_soc_dai *dai)
+{
+	struct sun4i_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+
+	clk_disable_unprepare(i2s->mod_clk);
+
+	/* Disable our output lines */
+	regmap_update_bits(i2s->regmap, SUN4I_I2S_CTRL_REG,
+			   SUN4I_I2S_CTRL_SDO_EN_MASK, 0);
+
+	/* Disable the whole hardware block */
+	regmap_write(i2s->regmap, SUN4I_I2S_CTRL_REG, 0);
+}
+
+static const struct snd_soc_dai_ops sun4i_i2s_dai_ops = {
+	.hw_params	= sun4i_i2s_hw_params,
+	.set_fmt	= sun4i_i2s_set_fmt,
+	.shutdown	= sun4i_i2s_shutdown,
+	.startup	= sun4i_i2s_startup,
+	.trigger	= sun4i_i2s_trigger,
+};
+
+static int sun4i_i2s_dai_probe(struct snd_soc_dai *dai)
+{
+	struct sun4i_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+
+	snd_soc_dai_init_dma_data(dai, &i2s->playback_dma_data, NULL);
+
+	snd_soc_dai_set_drvdata(dai, i2s);
+
+	return 0;
+}
+
+static struct snd_soc_dai_driver sun4i_i2s_dai = {
+	.probe = sun4i_i2s_dai_probe,
+	.playback = {
+		.stream_name = "Playback",
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = SNDRV_PCM_RATE_8000_192000,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE,
+	},
+	.ops = &sun4i_i2s_dai_ops,
+	.symmetric_rates = 1,
+};
+
+static const struct snd_soc_component_driver sun4i_i2s_component = {
+	.name	= "sun4i-dai",
+};
+
+static bool sun4i_i2s_rd_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case SUN4I_I2S_FIFO_TX_REG:
+		return false;
+
+	default:
+		return true;
+	}
+}
+
+static bool sun4i_i2s_wr_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case SUN4I_I2S_FIFO_RX_REG:
+	case SUN4I_I2S_FIFO_STA_REG:
+		return false;
+
+	default:
+		return true;
+	}
+}
+
+static bool sun4i_i2s_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case SUN4I_I2S_FIFO_RX_REG:
+	case SUN4I_I2S_INT_STA_REG:
+	case SUN4I_I2S_RX_CNT_REG:
+	case SUN4I_I2S_TX_CNT_REG:
+		return true;
+
+	default:
+		return false;
+	}
+}
+
+static const struct reg_default sun4i_i2s_reg_defaults[] = {
+	{ SUN4I_I2S_CTRL_REG, 0x00000000 },
+	{ SUN4I_I2S_FMT0_REG, 0x0000000c },
+	{ SUN4I_I2S_FMT1_REG, 0x00004020 },
+	{ SUN4I_I2S_FIFO_CTRL_REG, 0x000400f0 },
+	{ SUN4I_I2S_DMA_INT_CTRL_REG, 0x00000000 },
+	{ SUN4I_I2S_CLK_DIV_REG, 0x00000000 },
+	{ SUN4I_I2S_TX_CHAN_SEL_REG, 0x00000001 },
+	{ SUN4I_I2S_TX_CHAN_MAP_REG, 0x76543210 },
+	{ SUN4I_I2S_RX_CHAN_SEL_REG, 0x00000001 },
+	{ SUN4I_I2S_RX_CHAN_MAP_REG, 0x00003210 },
+};
+
+static const struct regmap_config sun4i_i2s_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= SUN4I_I2S_RX_CHAN_MAP_REG,
+
+	.cache_type	= REGCACHE_FLAT,
+	.reg_defaults	= sun4i_i2s_reg_defaults,
+	.num_reg_defaults	= ARRAY_SIZE(sun4i_i2s_reg_defaults),
+	.writeable_reg	= sun4i_i2s_wr_reg,
+	.readable_reg	= sun4i_i2s_rd_reg,
+	.volatile_reg	= sun4i_i2s_volatile_reg,
+};
+
+static int sun4i_i2s_runtime_resume(struct device *dev)
+{
+	struct sun4i_i2s *i2s = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(i2s->bus_clk);
+	if (ret) {
+		dev_err(dev, "Failed to enable bus clock\n");
+		return ret;
+	}
+
+	regcache_cache_only(i2s->regmap, false);
+	regcache_mark_dirty(i2s->regmap);
+
+	ret = regcache_sync(i2s->regmap);
+	if (ret) {
+		dev_err(dev, "Failed to sync regmap cache\n");
+		goto err_disable_clk;
+	}
+
+	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(i2s->bus_clk);
+	return ret;
+}
+
+static int sun4i_i2s_runtime_suspend(struct device *dev)
+{
+	struct sun4i_i2s *i2s = dev_get_drvdata(dev);
+
+	regcache_cache_only(i2s->regmap, true);
+
+	clk_disable_unprepare(i2s->bus_clk);
+
+	return 0;
+}
+
+static int sun4i_i2s_probe(struct platform_device *pdev)
+{
+	struct sun4i_i2s *i2s;
+	struct resource *res;
+	void __iomem *regs;
+	int irq, ret;
+
+	i2s = devm_kzalloc(&pdev->dev, sizeof(*i2s), GFP_KERNEL);
+	if (!i2s)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, i2s);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "Can't retrieve our interrupt\n");
+		return irq;
+	}
+
+	i2s->bus_clk = devm_clk_get(&pdev->dev, "apb");
+	if (IS_ERR(i2s->bus_clk)) {
+		dev_err(&pdev->dev, "Can't get our bus clock\n");
+		return PTR_ERR(i2s->bus_clk);
+	}
+
+	i2s->regmap = devm_regmap_init_mmio(&pdev->dev, regs,
+					    &sun4i_i2s_regmap_config);
+	if (IS_ERR(i2s->regmap)) {
+		dev_err(&pdev->dev, "Regmap initialisation failed\n");
+		return PTR_ERR(i2s->regmap);
+	}
+
+	i2s->mod_clk = devm_clk_get(&pdev->dev, "mod");
+	if (IS_ERR(i2s->mod_clk)) {
+		dev_err(&pdev->dev, "Can't get our mod clock\n");
+		return PTR_ERR(i2s->mod_clk);
+	}
+	
+	i2s->playback_dma_data.addr = res->start + SUN4I_I2S_FIFO_TX_REG;
+	i2s->playback_dma_data.maxburst = 4;
+
+	pm_runtime_enable(&pdev->dev);
+	if (!pm_runtime_enabled(&pdev->dev)) {
+		ret = sun4i_i2s_runtime_resume(&pdev->dev);
+		if (ret)
+			goto err_pm_disable;
+	}
+
+	ret = devm_snd_soc_register_component(&pdev->dev,
+					      &sun4i_i2s_component,
+					      &sun4i_i2s_dai, 1);
+	if (ret) {
+		dev_err(&pdev->dev, "Could not register DAI\n");
+		goto err_suspend;
+	}
+
+	ret = snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+	if (ret) {
+		dev_err(&pdev->dev, "Could not register PCM\n");
+		goto err_suspend;
+	}
+
+	return 0;
+
+err_suspend:
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		sun4i_i2s_runtime_suspend(&pdev->dev);
+err_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+
+	return ret;
+}
+
+static int sun4i_i2s_remove(struct platform_device *pdev)
+{
+	snd_dmaengine_pcm_unregister(&pdev->dev);
+
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		sun4i_i2s_runtime_suspend(&pdev->dev);
+
+	return 0;
+}
+
+static const struct of_device_id sun4i_i2s_match[] = {
+	{ .compatible = "allwinner,sun4i-a10-i2s", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sun4i_i2s_match);
+
+static const struct dev_pm_ops sun4i_i2s_pm_ops = {
+	.runtime_resume		= sun4i_i2s_runtime_resume,
+	.runtime_suspend	= sun4i_i2s_runtime_suspend,
+};
+
+static struct platform_driver sun4i_i2s_driver = {
+	.probe	= sun4i_i2s_probe,
+	.remove	= sun4i_i2s_remove,
+	.driver	= {
+		.name		= "sun4i-i2s",
+		.of_match_table	= sun4i_i2s_match,
+		.pm		= &sun4i_i2s_pm_ops,
+	},
+};
+module_platform_driver(sun4i_i2s_driver);
+
+MODULE_AUTHOR("Andrea Venturi <be17068@iperbole.bo.it>");
+MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner A10 I2S driver");
+MODULE_LICENSE("GPL");
diff --git a/sound/sound_firmware.c b/sound/sound_firmware.c
deleted file mode 100644
index 026347643c81..000000000000
--- a/sound/sound_firmware.c
+++ /dev/null
@@ -1,77 +0,0 @@
-#include <linux/vmalloc.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <asm/uaccess.h>
-#include "oss/sound_firmware.h"
-
-static int do_mod_firmware_load(const char *fn, char **fp)
-{
-	struct file* filp;
-	long l;
-	char *dp;
-
-	filp = filp_open(fn, 0, 0);
-	if (IS_ERR(filp))
-	{
-		printk(KERN_INFO "Unable to load '%s'.\n", fn);
-		return 0;
-	}
-	l = i_size_read(file_inode(filp));
-	if (l <= 0 || l > 131072)
-	{
-		printk(KERN_INFO "Invalid firmware '%s'\n", fn);
-		fput(filp);
-		return 0;
-	}
-	dp = vmalloc(l);
-	if (dp == NULL)
-	{
-		printk(KERN_INFO "Out of memory loading '%s'.\n", fn);
-		fput(filp);
-		return 0;
-	}
-	if (kernel_read(filp, 0, dp, l) != l)
-	{
-		printk(KERN_INFO "Failed to read '%s'.\n", fn);
-		vfree(dp);
-		fput(filp);
-		return 0;
-	}
-	fput(filp);
-	*fp = dp;
-	return (int) l;
-}
-
-/**
- *	mod_firmware_load - load sound driver firmware
- *	@fn: filename
- *	@fp: return for the buffer.
- *
- *	Load the firmware for a sound module (up to 128K) into a buffer.
- *	The buffer is returned in *fp. It is allocated with vmalloc so is
- *	virtually linear and not DMAable. The caller should free it with
- *	vfree when finished.
- *
- *	The length of the buffer is returned on a successful load, the
- *	value zero on a failure.
- *
- *	Caution: This API is not recommended. Firmware should be loaded via
- *	request_firmware.
- */
- 
-int mod_firmware_load(const char *fn, char **fp)
-{
-	int r;
-	mm_segment_t fs = get_fs();
-
-	set_fs(get_ds());
-	r = do_mod_firmware_load(fn, fp);
-	set_fs(fs);
-	return r;
-}
-EXPORT_SYMBOL(mod_firmware_load);
-
-MODULE_LICENSE("GPL");
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 1f8fb0d904e0..9038b2e7df73 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -107,8 +107,10 @@ static struct usbmix_name_map extigy_map[] = {
  * e.g. no Master and fake PCM volume
  *			Pavel Mihaylov <bin@bash.info>
  */
-static struct usbmix_dB_map mp3plus_dB_1 = {-4781, 0};	/* just guess */
-static struct usbmix_dB_map mp3plus_dB_2 = {-1781, 618}; /* just guess */
+static struct usbmix_dB_map mp3plus_dB_1 = {.min = -4781, .max = 0};
+						/* just guess */
+static struct usbmix_dB_map mp3plus_dB_2 = {.min = -1781, .max = 618};
+						/* just guess */
 
 static struct usbmix_name_map mp3plus_map[] = {
 	/* 1: IT pcm */
diff --git a/tools/lib/api/Build b/tools/lib/api/Build
index 954c644f7ad9..6e2373db5598 100644
--- a/tools/lib/api/Build
+++ b/tools/lib/api/Build
@@ -2,3 +2,8 @@ libapi-y += fd/
 libapi-y += fs/
 libapi-y += cpu.o
 libapi-y += debug.o
+libapi-y += str_error_r.o
+
+$(OUTPUT)str_error_r.o: ../str_error_r.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 32e6b6bc6f7d..b699aea9a025 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -37,6 +37,10 @@
 #include "libbpf.h"
 #include "bpf.h"
 
+#ifndef EM_BPF
+#define EM_BPF 247
+#endif
+
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
 __printf(1, 2)
@@ -439,7 +443,8 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	}
 	ep = &obj->efile.ehdr;
 
-	if ((ep->e_type != ET_REL) || (ep->e_machine != 0)) {
+	/* Old LLVM set e_machine to EM_NONE */
+	if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
 		pr_warning("%s is not an eBPF object file\n",
 			obj->path);
 		err = -LIBBPF_ERRNO__FORMAT;
diff --git a/tools/objtool/.gitignore b/tools/objtool/.gitignore
index a0b3128bb31f..d3102c865a95 100644
--- a/tools/objtool/.gitignore
+++ b/tools/objtool/.gitignore
@@ -1,2 +1,3 @@
 arch/x86/insn/inat-tables.c
 objtool
+fixdep
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 0b437700f688..041b493ad3ab 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -51,7 +51,7 @@ $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN)
 	diff -I'^#include' arch/x86/insn/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
 	diff -I'^#include' arch/x86/insn/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
 	diff -I'^#include' arch/x86/insn/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
-	|| echo "Warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true
+	|| echo "warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true
 	$(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@
 
 
diff --git a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk b/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk
index 093a892026f9..a3d2c62fd805 100644
--- a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk
+++ b/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk
@@ -72,12 +72,14 @@ BEGIN {
 	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
-	# All opcodes starting with lower-case 'v' or with (v1) superscript
+	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
 	# accepts VEX prefix
-	vexok_opcode_expr = "^v.*"
+	vexok_opcode_expr = "^[vk].*"
 	vexok_expr = "\\(v1\\)"
 	# All opcodes with (v) superscript supports *only* VEX prefix
 	vexonly_expr = "\\(v\\)"
+	# All opcodes with (ev) superscript supports *only* EVEX prefix
+	evexonly_expr = "\\(ev\\)"
 
 	prefix_expr = "\\(Prefix\\)"
 	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -95,6 +97,7 @@ BEGIN {
 	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
 	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
 	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+	prefix_num["EVEX"] = "INAT_PFX_EVEX"
 
 	clear_vars()
 }
@@ -319,7 +322,9 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 			flags = add_flags(flags, "INAT_MODRM")
 
 		# check VEX codes
-		if (match(ext, vexonly_expr))
+		if (match(ext, evexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+		else if (match(ext, vexonly_expr))
 			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
 		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
 			flags = add_flags(flags, "INAT_VEXOK")
diff --git a/tools/objtool/arch/x86/insn/inat.h b/tools/objtool/arch/x86/insn/inat.h
index 611645e903a8..125ecd2a300d 100644
--- a/tools/objtool/arch/x86/insn/inat.h
+++ b/tools/objtool/arch/x86/insn/inat.h
@@ -48,6 +48,7 @@
 /* AVX VEX prefixes */
 #define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
+#define INAT_PFX_EVEX	15	/* EVEX prefix */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11
@@ -89,6 +90,7 @@
 #define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
 #define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
+#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
 static inline int inat_is_vex_prefix(insn_attr_t attr)
 {
 	attr &= INAT_PFX_MASK;
-	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
+	       attr == INAT_PFX_EVEX;
+}
+
+static inline int inat_is_evex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
 }
 
 static inline int inat_is_vex3_prefix(insn_attr_t attr)
@@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr)
 
 static inline int inat_must_vex(insn_attr_t attr)
 {
-	return attr & INAT_VEXONLY;
+	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
+}
+
+static inline int inat_must_evex(insn_attr_t attr)
+{
+	return attr & INAT_EVEXONLY;
 }
 #endif
diff --git a/tools/objtool/arch/x86/insn/insn.c b/tools/objtool/arch/x86/insn/insn.c
index 9f26eae6c9f0..ca983e2bea8b 100644
--- a/tools/objtool/arch/x86/insn/insn.c
+++ b/tools/objtool/arch/x86/insn/insn.c
@@ -155,14 +155,24 @@ found:
 			/*
 			 * In 32-bits mode, if the [7:6] bits (mod bits of
 			 * ModRM) on the second byte are not 11b, it is
-			 * LDS or LES.
+			 * LDS or LES or BOUND.
 			 */
 			if (X86_MODRM_MOD(b2) != 3)
 				goto vex_end;
 		}
 		insn->vex_prefix.bytes[0] = b;
 		insn->vex_prefix.bytes[1] = b2;
-		if (inat_is_vex3_prefix(attr)) {
+		if (inat_is_evex_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
+			insn->vex_prefix.bytes[3] = b2;
+			insn->vex_prefix.nbytes = 4;
+			insn->next_byte += 4;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		} else if (inat_is_vex3_prefix(attr)) {
 			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
 			insn->vex_prefix.bytes[2] = b2;
 			insn->vex_prefix.nbytes = 3;
@@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn)
 		m = insn_vex_m_bits(insn);
 		p = insn_vex_p_bits(insn);
 		insn->attr = inat_get_avx_attribute(op, m, p);
-		if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
+		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
+		    (!inat_accept_vex(insn->attr) &&
+		     !inat_is_group(insn->attr)))
 			insn->attr = 0;	/* This instruction is bad */
 		goto end;	/* VEX has only 1 byte for opcode */
 	}
diff --git a/tools/objtool/arch/x86/insn/insn.h b/tools/objtool/arch/x86/insn/insn.h
index dd12da0f4593..e23578c7b1be 100644
--- a/tools/objtool/arch/x86/insn/insn.h
+++ b/tools/objtool/arch/x86/insn/insn.h
@@ -91,6 +91,7 @@ struct insn {
 #define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
 #define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
 /* VEX bit fields */
+#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
 #define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
 #define X86_VEX2_M	1			/* VEX2.M always 1 */
 #define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
@@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn)
 	return (insn->vex_prefix.value != 0);
 }
 
+static inline int insn_is_evex(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.nbytes == 4);
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {
@@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
 	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
 		return X86_VEX2_M;
-	else
+	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
 		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+	else					/* EVEX */
+		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
 }
 
 static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
diff --git a/tools/objtool/arch/x86/insn/x86-opcode-map.txt b/tools/objtool/arch/x86/insn/x86-opcode-map.txt
index 28632ee68377..767be7c76034 100644
--- a/tools/objtool/arch/x86/insn/x86-opcode-map.txt
+++ b/tools/objtool/arch/x86/insn/x86-opcode-map.txt
@@ -13,12 +13,17 @@
 # opcode: escape # escaped-name
 # EndTable
 #
+# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
+# mnemonics that begin with lowercase 'k' accept a VEX prefix
+#
 #<group maps>
 # GrpTable: GrpXXX
 # reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
 # EndTable
 #
 # AVX Superscripts
+#  (ev): this opcode requires EVEX prefix.
+#  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
 #  (v): this opcode requires VEX prefix.
 #  (v1): this opcode only supports 128bit VEX.
 #
@@ -137,7 +142,7 @@ AVXcode:
 # 0x60 - 0x6f
 60: PUSHA/PUSHAD (i64)
 61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix)
 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
 64: SEG=FS (Prefix)
 65: SEG=GS (Prefix)
@@ -399,17 +404,17 @@ AVXcode: 1
 3f:
 # 0x0f 0x40-0x4f
 40: CMOVO Gv,Ev
-41: CMOVNO Gv,Ev
-42: CMOVB/C/NAE Gv,Ev
+41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
+42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
 43: CMOVAE/NB/NC Gv,Ev
-44: CMOVE/Z Gv,Ev
-45: CMOVNE/NZ Gv,Ev
-46: CMOVBE/NA Gv,Ev
-47: CMOVA/NBE Gv,Ev
+44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
+45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
+46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
+47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
 48: CMOVS Gv,Ev
 49: CMOVNS Gv,Ev
-4a: CMOVP/PE Gv,Ev
-4b: CMOVNP/PO Gv,Ev
+4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
+4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
 4c: CMOVL/NGE Gv,Ev
 4d: CMOVNL/GE Gv,Ev
 4e: CMOVLE/NG Gv,Ev
@@ -426,7 +431,7 @@ AVXcode: 1
 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
-5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
@@ -447,7 +452,7 @@ AVXcode: 1
 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
-6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
 # 0x0f 0x70-0x7f
 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
 71: Grp12 (1A)
@@ -458,14 +463,14 @@ AVXcode: 1
 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
 # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
 77: emms | vzeroupper | vzeroall
-78: VMREAD Ey,Gy
-79: VMWRITE Gy,Ey
-7a:
-7b:
+78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
+79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
+7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
+7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
-7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3)
+7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
 # 0x0f 0x80-0x8f
 # Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
 80: JO Jz (f64)
@@ -485,16 +490,16 @@ AVXcode: 1
 8e: JLE/JNG Jz (f64)
 8f: JNLE/JG Jz (f64)
 # 0x0f 0x90-0x9f
-90: SETO Eb
-91: SETNO Eb
-92: SETB/C/NAE Eb
-93: SETAE/NB/NC Eb
+90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
+91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
+92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
+93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
 94: SETE/Z Eb
 95: SETNE/NZ Eb
 96: SETBE/NA Eb
 97: SETA/NBE Eb
-98: SETS Eb
-99: SETNS Eb
+98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
+99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
 9a: SETP/PE Eb
 9b: SETNP/PO Eb
 9c: SETL/NGE Eb
@@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
 d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
 d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
 da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
-db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
 dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
 dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
 de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
-df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xe0-0xef
 e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
 e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
@@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
 e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
 e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
 e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
-e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
 e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
 e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
 e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
 ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
-eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
 ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
 ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
 ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
-ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xf0-0xff
 f0: vlddqu Vx,Mx (F2)
 f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
@@ -626,81 +631,105 @@ AVXcode: 2
 0e: vtestps Vx,Wx (66),(v)
 0f: vtestpd Vx,Wx (66),(v)
 # 0x0f 0x38 0x10-0x1f
-10: pblendvb Vdq,Wdq (66)
-11:
-12:
-13: vcvtph2ps Vx,Wx,Ib (66),(v)
-14: blendvps Vdq,Wdq (66)
-15: blendvpd Vdq,Wdq (66)
-16: vpermps Vqq,Hqq,Wqq (66),(v)
+10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
+11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
+12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
+13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
+14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
+15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
+16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
 17: vptest Vx,Wx (66)
 18: vbroadcastss Vx,Wd (66),(v)
-19: vbroadcastsd Vqq,Wq (66),(v)
-1a: vbroadcastf128 Vqq,Mdq (66),(v)
-1b:
+19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
+1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
+1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
-1f:
+1f: vpabsq Vx,Wx (66),(ev)
 # 0x0f 0x38 0x20-0x2f
-20: vpmovsxbw Vx,Ux/Mq (66),(v1)
-21: vpmovsxbd Vx,Ux/Md (66),(v1)
-22: vpmovsxbq Vx,Ux/Mw (66),(v1)
-23: vpmovsxwd Vx,Ux/Mq (66),(v1)
-24: vpmovsxwq Vx,Ux/Md (66),(v1)
-25: vpmovsxdq Vx,Ux/Mq (66),(v1)
-26:
-27:
-28: vpmuldq Vx,Hx,Wx (66),(v1)
-29: vpcmpeqq Vx,Hx,Wx (66),(v1)
-2a: vmovntdqa Vx,Mx (66),(v1)
+20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
+21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
+24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
+26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
+27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
+28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
+2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
 2b: vpackusdw Vx,Hx,Wx (66),(v1)
-2c: vmaskmovps Vx,Hx,Mx (66),(v)
-2d: vmaskmovpd Vx,Hx,Mx (66),(v)
+2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
 2e: vmaskmovps Mx,Hx,Vx (66),(v)
 2f: vmaskmovpd Mx,Hx,Vx (66),(v)
 # 0x0f 0x38 0x30-0x3f
-30: vpmovzxbw Vx,Ux/Mq (66),(v1)
-31: vpmovzxbd Vx,Ux/Md (66),(v1)
-32: vpmovzxbq Vx,Ux/Mw (66),(v1)
-33: vpmovzxwd Vx,Ux/Mq (66),(v1)
-34: vpmovzxwq Vx,Ux/Md (66),(v1)
-35: vpmovzxdq Vx,Ux/Mq (66),(v1)
-36: vpermd Vqq,Hqq,Wqq (66),(v)
+30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
+31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
+34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
+36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
 37: vpcmpgtq Vx,Hx,Wx (66),(v1)
-38: vpminsb Vx,Hx,Wx (66),(v1)
-39: vpminsd Vx,Hx,Wx (66),(v1)
-3a: vpminuw Vx,Hx,Wx (66),(v1)
-3b: vpminud Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
+39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
+3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
+3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
 3c: vpmaxsb Vx,Hx,Wx (66),(v1)
-3d: vpmaxsd Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
 3e: vpmaxuw Vx,Hx,Wx (66),(v1)
-3f: vpmaxud Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0x38 0x40-0x8f
-40: vpmulld Vx,Hx,Wx (66),(v1)
+40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
 41: vphminposuw Vdq,Wdq (66),(v1)
-42:
-43:
-44:
+42: vgetexpps/d Vx,Wx (66),(ev)
+43: vgetexpss/d Vx,Hx,Wx (66),(ev)
+44: vplzcntd/q Vx,Wx (66),(ev)
 45: vpsrlvd/q Vx,Hx,Wx (66),(v)
-46: vpsravd Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
 47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x57
+# Skip 0x48-0x4b
+4c: vrcp14ps/d Vpd,Wpd (66),(ev)
+4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
+4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
+4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
+# Skip 0x50-0x57
 58: vpbroadcastd Vx,Wx (66),(v)
-59: vpbroadcastq Vx,Wx (66),(v)
-5a: vbroadcasti128 Vqq,Mdq (66),(v)
-# Skip 0x5b-0x77
+59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
+5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
+5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
+# Skip 0x5c-0x63
+64: vpblendmd/q Vx,Hx,Wx (66),(ev)
+65: vblendmps/d Vx,Hx,Wx (66),(ev)
+66: vpblendmb/w Vx,Hx,Wx (66),(ev)
+# Skip 0x67-0x74
+75: vpermi2b/w Vx,Hx,Wx (66),(ev)
+76: vpermi2d/q Vx,Hx,Wx (66),(ev)
+77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
 78: vpbroadcastb Vx,Wx (66),(v)
 79: vpbroadcastw Vx,Wx (66),(v)
-# Skip 0x7a-0x7f
+7a: vpbroadcastb Vx,Rv (66),(ev)
+7b: vpbroadcastw Vx,Rv (66),(ev)
+7c: vpbroadcastd/q Vx,Rv (66),(ev)
+7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
+7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
+7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
 81: INVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
+83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
+88: vexpandps/d Vpd,Wpd (66),(ev)
+89: vpexpandd/q Vx,Wx (66),(ev)
+8a: vcompressps/d Wx,Vx (66),(ev)
+8b: vpcompressd/q Wx,Vx (66),(ev)
 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8d: vpermb/w Vx,Hx,Wx (66),(ev)
 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
 # 0x0f 0x38 0x90-0xbf (FMA)
-90: vgatherdd/q Vx,Hx,Wx (66),(v)
-91: vgatherqd/q Vx,Hx,Wx (66),(v)
+90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
+91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
 92: vgatherdps/d Vx,Hx,Wx (66),(v)
 93: vgatherqps/d Vx,Hx,Wx (66),(v)
 94:
@@ -715,6 +744,10 @@ AVXcode: 2
 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a0: vpscatterdd/q Wx,Vx (66),(ev)
+a1: vpscatterqd/q Wx,Vx (66),(ev)
+a2: vscatterdps/d Wx,Vx (66),(ev)
+a3: vscatterqps/d Wx,Vx (66),(ev)
 a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
 a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
 a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
@@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
 ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
 ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
 af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
+b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
 b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
 b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
 b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
@@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
 be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
 bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
 # 0x0f 0x38 0xc0-0xff
-c8: sha1nexte Vdq,Wdq
+c4: vpconflictd/q Vx,Wx (66),(ev)
+c6: Grp18 (1A)
+c7: Grp19 (1A)
+c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
 c9: sha1msg1 Vdq,Wdq
-ca: sha1msg2 Vdq,Wdq
-cb: sha256rnds2 Vdq,Wdq
-cc: sha256msg1 Vdq,Wdq
-cd: sha256msg2 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
 db: VAESIMC Vdq,Wdq (66),(v1)
 dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
 dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
@@ -763,15 +801,15 @@ AVXcode: 3
 00: vpermq Vqq,Wqq,Ib (66),(v)
 01: vpermpd Vqq,Wqq,Ib (66),(v)
 02: vpblendd Vx,Hx,Wx,Ib (66),(v)
-03:
+03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
 04: vpermilps Vx,Wx,Ib (66),(v)
 05: vpermilpd Vx,Wx,Ib (66),(v)
 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
 07:
-08: vroundps Vx,Wx,Ib (66)
-09: vroundpd Vx,Wx,Ib (66)
-0a: vroundss Vss,Wss,Ib (66),(v1)
-0b: vroundsd Vsd,Wsd,Ib (66),(v1)
+08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
+09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
+0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
 0c: vblendps Vx,Hx,Wx,Ib (66)
 0d: vblendpd Vx,Hx,Wx,Ib (66)
 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
@@ -780,26 +818,51 @@ AVXcode: 3
 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
 16: vpextrd/q Ey,Vdq,Ib (66),(v1)
 17: vextractps Ed,Vdq,Ib (66),(v1)
-18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v)
-19: vextractf128 Wdq,Vqq,Ib (66),(v)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
 1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
+1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
-38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
-39: vextracti128 Wdq,Vqq,Ib (66),(v)
+23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
+25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
+26: vgetmantps/d Vx,Wx,Ib (66),(ev)
+27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
+30: kshiftrb/w Vk,Uk,Ib (66),(v)
+31: kshiftrd/q Vk,Uk,Ib (66),(v)
+32: kshiftlb/w Vk,Uk,Ib (66),(v)
+33: kshiftld/q Vk,Uk,Ib (66),(v)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
+3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
+3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
 40: vdpps Vx,Hx,Wx,Ib (66)
 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
-42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
+43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
 4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
+51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
+54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
+55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
+56: vreduceps/d Vx,Wx,Ib (66),(ev)
+57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
 61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
 63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+66: vfpclassps/d Vk,Wx,Ib (66),(ev)
+67: vfpclassss/d Vk,Wx,Ib (66),(ev)
 cc: sha1rnds4 Vdq,Wdq,Ib
 df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
 f0: RORX Gy,Ey,Ib (F2),(v)
@@ -927,8 +990,10 @@ GrpTable: Grp12
 EndTable
 
 GrpTable: Grp13
+0: vprord/q Hx,Wx,Ib (66),(ev)
+1: vprold/q Hx,Wx,Ib (66),(ev)
 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
-4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
 EndTable
 
@@ -963,6 +1028,20 @@ GrpTable: Grp17
 3: BLSI By,Ey (v)
 EndTable
 
+GrpTable: Grp18
+1: vgatherpf0dps/d Wx (66),(ev)
+2: vgatherpf1dps/d Wx (66),(ev)
+5: vscatterpf0dps/d Wx (66),(ev)
+6: vscatterpf1dps/d Wx (66),(ev)
+EndTable
+
+GrpTable: Grp19
+1: vgatherpf0qps/d Wx (66),(ev)
+2: vgatherpf1qps/d Wx (66),(ev)
+5: vscatterpf0qps/d Wx (66),(ev)
+6: vscatterpf1qps/d Wx (66),(ev)
+EndTable
+
 # AMD's Prefetch Group
 GrpTable: GrpP
 0: PREFETCH
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 17fa7fc34fdf..bd09d0effef8 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -107,6 +107,12 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file,
 		insn->offset < func->offset + func->len;		\
 	     insn = list_next_entry(insn, list))
 
+#define func_for_each_insn_continue_reverse(file, func, insn)		\
+	for (insn = list_prev_entry(insn, list);			\
+	     &insn->list != &file->insn_list &&				\
+		insn->sec == func->sec && insn->offset >= func->offset;	\
+	     insn = list_prev_entry(insn, list))
+
 #define sec_for_each_insn_from(file, insn)				\
 	for (; insn; insn = next_insn_same_sec(file, insn))
 
@@ -664,65 +670,95 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func,
 	return 0;
 }
 
-static int add_func_switch_tables(struct objtool_file *file,
-				  struct symbol *func)
+/*
+ * find_switch_table() - Given a dynamic jump, find the switch jump table in
+ * .rodata associated with it.
+ *
+ * There are 3 basic patterns:
+ *
+ * 1. jmpq *[rodata addr](,%reg,8)
+ *
+ *    This is the most common case by far.  It jumps to an address in a simple
+ *    jump table which is stored in .rodata.
+ *
+ * 2. jmpq *[rodata addr](%rip)
+ *
+ *    This is caused by a rare GCC quirk, currently only seen in three driver
+ *    functions in the kernel, only with certain obscure non-distro configs.
+ *
+ *    As part of an optimization, GCC makes a copy of an existing switch jump
+ *    table, modifies it, and then hard-codes the jump (albeit with an indirect
+ *    jump) to use a single entry in the table.  The rest of the jump table and
+ *    some of its jump targets remain as dead code.
+ *
+ *    In such a case we can just crudely ignore all unreachable instruction
+ *    warnings for the entire object file.  Ideally we would just ignore them
+ *    for the function, but that would require redesigning the code quite a
+ *    bit.  And honestly that's just not worth doing: unreachable instruction
+ *    warnings are of questionable value anyway, and this is such a rare issue.
+ *
+ * 3. mov [rodata addr],%reg1
+ *    ... some instructions ...
+ *    jmpq *(%reg1,%reg2,8)
+ *
+ *    This is a fairly uncommon pattern which is new for GCC 6.  As of this
+ *    writing, there are 11 occurrences of it in the allmodconfig kernel.
+ *
+ *    TODO: Once we have DWARF CFI and smarter instruction decoding logic,
+ *    ensure the same register is used in the mov and jump instructions.
+ */
+static struct rela *find_switch_table(struct objtool_file *file,
+				      struct symbol *func,
+				      struct instruction *insn)
 {
-	struct instruction *insn, *prev_jump;
-	struct rela *text_rela, *rodata_rela, *prev_rela = NULL;
-	int ret;
+	struct rela *text_rela, *rodata_rela;
 
-	prev_jump = NULL;
+	text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
+	if (text_rela && text_rela->sym == file->rodata->sym) {
+		/* case 1 */
+		rodata_rela = find_rela_by_dest(file->rodata,
+						text_rela->addend);
+		if (rodata_rela)
+			return rodata_rela;
 
-	func_for_each_insn(file, func, insn) {
-		if (insn->type != INSN_JUMP_DYNAMIC)
-			continue;
+		/* case 2 */
+		rodata_rela = find_rela_by_dest(file->rodata,
+						text_rela->addend + 4);
+		if (!rodata_rela)
+			return NULL;
+		file->ignore_unreachables = true;
+		return rodata_rela;
+	}
+
+	/* case 3 */
+	func_for_each_insn_continue_reverse(file, func, insn) {
+		if (insn->type == INSN_JUMP_UNCONDITIONAL ||
+		    insn->type == INSN_JUMP_DYNAMIC)
+			break;
 
 		text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
 						    insn->len);
-		if (!text_rela || text_rela->sym != file->rodata->sym)
-			continue;
+		if (text_rela && text_rela->sym == file->rodata->sym)
+			return find_rela_by_dest(file->rodata,
+						 text_rela->addend);
+	}
 
-		/* common case: jmpq *[addr](,%rax,8) */
-		rodata_rela = find_rela_by_dest(file->rodata,
-						text_rela->addend);
+	return NULL;
+}
 
-		/*
-		 * rare case:   jmpq *[addr](%rip)
-		 *
-		 * This check is for a rare gcc quirk, currently only seen in
-		 * three driver functions in the kernel, only with certain
-		 * obscure non-distro configs.
-		 *
-		 * As part of an optimization, gcc makes a copy of an existing
-		 * switch jump table, modifies it, and then hard-codes the jump
-		 * (albeit with an indirect jump) to use a single entry in the
-		 * table.  The rest of the jump table and some of its jump
-		 * targets remain as dead code.
-		 *
-		 * In such a case we can just crudely ignore all unreachable
-		 * instruction warnings for the entire object file.  Ideally we
-		 * would just ignore them for the function, but that would
-		 * require redesigning the code quite a bit.  And honestly
-		 * that's just not worth doing: unreachable instruction
-		 * warnings are of questionable value anyway, and this is such
-		 * a rare issue.
-		 *
-		 * kbuild reports:
-		 * - https://lkml.kernel.org/r/201603231906.LWcVUpxm%25fengguang.wu@intel.com
-		 * - https://lkml.kernel.org/r/201603271114.K9i45biy%25fengguang.wu@intel.com
-		 * - https://lkml.kernel.org/r/201603291058.zuJ6ben1%25fengguang.wu@intel.com
-		 *
-		 * gcc bug:
-		 * - https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70604
-		 */
-		if (!rodata_rela) {
-			rodata_rela = find_rela_by_dest(file->rodata,
-							text_rela->addend + 4);
-			if (rodata_rela)
-				file->ignore_unreachables = true;
-		}
+static int add_func_switch_tables(struct objtool_file *file,
+				  struct symbol *func)
+{
+	struct instruction *insn, *prev_jump = NULL;
+	struct rela *rela, *prev_rela = NULL;
+	int ret;
 
-		if (!rodata_rela)
+	func_for_each_insn(file, func, insn) {
+		if (insn->type != INSN_JUMP_DYNAMIC)
+			continue;
+
+		rela = find_switch_table(file, func, insn);
+		if (!rela)
 			continue;
 
 		/*
@@ -732,13 +768,13 @@ static int add_func_switch_tables(struct objtool_file *file,
 		 */
 		if (prev_jump) {
 			ret = add_switch_table(file, func, prev_jump, prev_rela,
-					       rodata_rela);
+					       rela);
 			if (ret)
 				return ret;
 		}
 
 		prev_jump = insn;
-		prev_rela = rodata_rela;
+		prev_rela = rela;
 	}
 
 	if (prev_jump) {
diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index 8a61372bb47a..5bd7b9260cc0 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -2,3 +2,5 @@ libperf-y += header.o
 libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
+
+libperf-y += machine.o
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
new file mode 100644
index 000000000000..b9a95a1a8e69
--- /dev/null
+++ b/tools/perf/arch/s390/util/machine.c
@@ -0,0 +1,19 @@
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include "util.h"
+#include "machine.h"
+#include "api/fs/fs.h"
+
+int arch__fix_module_text_start(u64 *start, const char *name)
+{
+	char path[PATH_MAX];
+
+	snprintf(path, PATH_MAX, "module/%.*s/sections/.text",
+				(int)strlen(name) - 2, name + 1);
+
+	if (sysfs__read_ull(path, (unsigned long long *)start) < 0)
+		return -1;
+
+	return 0;
+}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 2fa7d8b69873..91c5f6e1af59 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -70,7 +70,6 @@ libperf-y += stat.o
 libperf-y += stat-shadow.o
 libperf-y += record.o
 libperf-y += srcline.o
-libperf-y += str_error_r.o
 libperf-y += data.o
 libperf-y += tsc.o
 libperf-y += cloexec.o
@@ -176,10 +175,6 @@ $(OUTPUT)util/libstring.o: ../lib/string.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/str_error_r.o: ../lib/str_error_r.c FORCE
-	$(call rule_mkdir)
-	$(call if_changed_dep,cc_o_c)
-
 $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index bc2cdbd09a25..cb6388dbdd98 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1093,12 +1093,20 @@ static int machine__set_modules_path(struct machine *machine)
 
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
+int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+				const char *name __maybe_unused)
+{
+	return 0;
+}
 
 static int machine__create_module(void *arg, const char *name, u64 start)
 {
 	struct machine *machine = arg;
 	struct map *map;
 
+	if (arch__fix_module_text_start(&start, name) < 0)
+		return -1;
+
 	map = machine__findnew_module_map(machine, start, name);
 	if (map == NULL)
 		return -1;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 41ac9cfd416b..20739f746bc4 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -216,6 +216,7 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
+int arch__fix_module_text_start(u64 *start, const char *name);
 
 int __machine__load_kallsyms(struct machine *machine, const char *filename,
 			     enum map_type type, bool no_kcore, symbol_filter_t filter);
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 5065ec98049c..b7d4f4aeee61 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -13,7 +13,6 @@ util/cpumap.c
 ../lib/bitmap.c
 ../lib/find_bit.c
 ../lib/hweight.c
-../lib/str_error_r.c
 ../lib/vsprintf.c
 util/thread_map.c
 util/util.c
diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h
index 0e37f7a760eb..5201b915f631 100644
--- a/tools/testing/radix-tree/linux/gfp.h
+++ b/tools/testing/radix-tree/linux/gfp.h
@@ -1,7 +1,7 @@
 #ifndef _GFP_H
 #define _GFP_H
 
-#define __GFP_BITS_SHIFT 22
+#define __GFP_BITS_SHIFT 26
 #define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 #define __GFP_WAIT 1
 #define __GFP_ACCOUNT 0
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index 4e400eb83657..d4300602bf37 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -18,7 +18,8 @@ execveat.denatured: execveat
 	$(CC) $(CFLAGS) -o $@ $^
 
 TEST_PROGS := execveat
-TEST_FILES := $(DEPS)
+# Makefile is a run-time dependency, since it's accessed by the execveat test
+TEST_FILES := $(DEPS) Makefile
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/lib/printf.sh b/tools/testing/selftests/lib/printf.sh
index 4fdc70fe6980..4fdc70fe6980 100644..100755
--- a/tools/testing/selftests/lib/printf.sh
+++ b/tools/testing/selftests/lib/printf.sh
diff --git a/tools/testing/selftests/media_tests/.gitignore b/tools/testing/selftests/media_tests/.gitignore
index 1c0711708b98..8745eba39012 100644
--- a/tools/testing/selftests/media_tests/.gitignore
+++ b/tools/testing/selftests/media_tests/.gitignore
@@ -1 +1,3 @@
 media_device_test
+media_device_open
+video_device_test
diff --git a/tools/testing/selftests/media_tests/Makefile b/tools/testing/selftests/media_tests/Makefile
index 7071bcc1d066..6b34a0199468 100644
--- a/tools/testing/selftests/media_tests/Makefile
+++ b/tools/testing/selftests/media_tests/Makefile
@@ -1,7 +1,7 @@
-TEST_PROGS := media_device_test
+TEST_PROGS := media_device_test media_device_open video_device_test
 all: $(TEST_PROGS)
 
 include ../lib.mk
 
 clean:
-	rm -fr media_device_test
+	rm -fr media_device_test media_device_open video_device_test
diff --git a/tools/testing/selftests/media_tests/bind_unbind_sample.sh b/tools/testing/selftests/media_tests/bind_unbind_sample.sh
new file mode 100755
index 000000000000..9f362f10631a
--- /dev/null
+++ b/tools/testing/selftests/media_tests/bind_unbind_sample.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+# Find device number in /sys/bus/usb/drivers/drivername
+# Edit this file to update the driver numer and name
+# Example test for uvcvideo driver
+#i=0
+# while :; do
+#  i=$((i+1))
+#  echo 1-5:1.0 > /sys/bus/usb/drivers/uvcvideo/unbind;
+#  echo 1-5:1.0 > /sys/bus/usb/drivers/uvcvideo/bind;
+#  clear
+#	echo $i
+#done
diff --git a/tools/testing/selftests/media_tests/media_device_open.c b/tools/testing/selftests/media_tests/media_device_open.c
new file mode 100644
index 000000000000..44343c091a20
--- /dev/null
+++ b/tools/testing/selftests/media_tests/media_device_open.c
@@ -0,0 +1,81 @@
+/*
+ * media_device_open.c - Media Controller Device Open Test
+ *
+ * Copyright (c) 2016 Shuah Khan <shuahkh@osg.samsung.com>
+ * Copyright (c) 2016 Samsung Electronics Co., Ltd.
+ *
+ * This file is released under the GPLv2.
+ */
+
+/*
+ * This file adds a test for Media Controller API.
+ * This test should be run as root and should not be
+ * included in the Kselftest run. This test should be
+ * run when hardware and driver that makes use Media
+ * Controller API are present in the system.
+ *
+ * This test opens user specified Media Device and calls
+ * MEDIA_IOC_DEVICE_INFO ioctl, closes the file, and exits.
+ *
+ * Usage:
+ *	sudo ./media_device_open -d /dev/mediaX
+ *
+ *	Run this test is a loop and run bind/unbind on the driver.
+*/
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <string.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <linux/media.h>
+
+int main(int argc, char **argv)
+{
+	int opt;
+	char media_device[256];
+	int count = 0;
+	struct media_device_info mdi;
+	int ret;
+	int fd;
+
+	if (argc < 2) {
+		printf("Usage: %s [-d </dev/mediaX>]\n", argv[0]);
+		exit(-1);
+	}
+
+	/* Process arguments */
+	while ((opt = getopt(argc, argv, "d:")) != -1) {
+		switch (opt) {
+		case 'd':
+			strncpy(media_device, optarg, sizeof(media_device) - 1);
+			media_device[sizeof(media_device)-1] = '\0';
+			break;
+		default:
+			printf("Usage: %s [-d </dev/mediaX>]\n", argv[0]);
+			exit(-1);
+		}
+	}
+
+	if (getuid() != 0) {
+		printf("Please run the test as root - Exiting.\n");
+		exit(-1);
+	}
+
+	/* Open Media device and keep it open */
+	fd = open(media_device, O_RDWR);
+	if (fd == -1) {
+		printf("Media Device open errno %s\n", strerror(errno));
+		exit(-1);
+	}
+
+	ret = ioctl(fd, MEDIA_IOC_DEVICE_INFO, &mdi);
+	if (ret < 0)
+		printf("Media Device Info errno %s\n", strerror(errno));
+	else
+		printf("Media device model %s driver %s\n",
+			mdi.model, mdi.driver);
+}
diff --git a/tools/testing/selftests/media_tests/media_device_test.c b/tools/testing/selftests/media_tests/media_device_test.c
index cbf53a032ab5..5d49943e77d0 100644
--- a/tools/testing/selftests/media_tests/media_device_test.c
+++ b/tools/testing/selftests/media_tests/media_device_test.c
@@ -1,5 +1,5 @@
 /*
- * media_devkref_test.c - Media Controller Device Kref API Test
+ * media_device_test.c - Media Controller Device ioctl loop Test
  *
  * Copyright (c) 2016 Shuah Khan <shuahkh@osg.samsung.com>
  * Copyright (c) 2016 Samsung Electronics Co., Ltd.
@@ -35,13 +35,14 @@
 #include <fcntl.h>
 #include <sys/ioctl.h>
 #include <sys/stat.h>
+#include <time.h>
 #include <linux/media.h>
 
 int main(int argc, char **argv)
 {
 	int opt;
 	char media_device[256];
-	int count = 0;
+	int count;
 	struct media_device_info mdi;
 	int ret;
 	int fd;
@@ -69,6 +70,10 @@ int main(int argc, char **argv)
 		exit(-1);
 	}
 
+	/* Generate random number of interations */
+	srand((unsigned int) time(NULL));
+	count = rand();
+
 	/* Open Media device and keep it open */
 	fd = open(media_device, O_RDWR);
 	if (fd == -1) {
@@ -82,14 +87,16 @@ int main(int argc, char **argv)
 	       "other Oops in the dmesg. Enable KaSan kernel\n"
 	       "config option for use-after-free error detection.\n\n");
 
-	while (count < 100) {
+	printf("Running test for %d iternations\n", count);
+
+	while (count > 0) {
 		ret = ioctl(fd, MEDIA_IOC_DEVICE_INFO, &mdi);
 		if (ret < 0)
 			printf("Media Device Info errno %s\n", strerror(errno));
 		else
-			printf("Media device model %s driver %s\n",
-				mdi.model, mdi.driver);
+			printf("Media device model %s driver %s - count %d\n",
+				mdi.model, mdi.driver, count);
 		sleep(10);
-		count++;
+		count--;
 	}
 }
diff --git a/tools/testing/selftests/media_tests/open_loop_test.sh b/tools/testing/selftests/media_tests/open_loop_test.sh
new file mode 100755
index 000000000000..dcd3c17efc17
--- /dev/null
+++ b/tools/testing/selftests/media_tests/open_loop_test.sh
@@ -0,0 +1,10 @@
+#!/bin/bash
+ i=0
+file=/dev/media$1
+ while :; do
+  echo $file
+  i=$((i+1))
+  R=$(./media_device_open -d $file);
+ # clear
+  echo -e "Loop $i\n$R"
+ done
diff --git a/tools/testing/selftests/media_tests/regression_test.txt b/tools/testing/selftests/media_tests/regression_test.txt
new file mode 100644
index 000000000000..2627367681f7
--- /dev/null
+++ b/tools/testing/selftests/media_tests/regression_test.txt
@@ -0,0 +1,43 @@
+Testing for regressions in Media Controller API register, ioctl, syscall,
+and unregister paths. There have a few problems that result in user-after
+free on media_device, media_devnode, and cdev pointers when the driver is
+unbound while ioctl is in progress.
+
+Test Procedure:
+
+Run bin/unbind loop while ioctls are in progress.
+Run rmmod and modprobe.
+Disconnect the device.
+
+Setup:
+
+Build media_device_test
+cd tools/testing/selftests/media_tests
+make
+
+Regressions test for cdev user-after free error on /dev/mediaX when driver
+is unbound:
+
+Start media_device_test to regression test media devnode dynamic alloc
+and cdev user-after-free fixes. This opens media dev files and sits in
+a loop running media ioctl MEDIA_IOC_DEVICE_INFO command once every 10
+seconds. The idea is when device file goes away, media devnode and cdev
+should stick around until this test exits.
+
+The test for a random number of iterations or until user kills it with a
+sleep 10 in between the ioctl calls.
+
+sudo ./media_device_test -d /dev/mediaX
+
+Regression test for media_devnode unregister race with ioctl_syscall:
+
+Start 6 open_loop_test.sh tests with different /dev/mediaX files. When
+device file goes away after unbind, device file name changes. Start the
+test with possible device names. If we start with /dev/media0 for example,
+after unbind, /dev/media1 or /dev/media2 could get created. The idea is
+keep ioctls going while bind/unbind runs.
+
+Copy bind_unbind_sample.txt and make changes to specify the driver name
+and number to run bind and unbind. Start the bind_unbind.sh
+
+Run dmesg looking for any user-after free errors or mutex lock errors.
diff --git a/tools/testing/selftests/media_tests/video_device_test.c b/tools/testing/selftests/media_tests/video_device_test.c
new file mode 100644
index 000000000000..66d419c28653
--- /dev/null
+++ b/tools/testing/selftests/media_tests/video_device_test.c
@@ -0,0 +1,100 @@
+/*
+ * video_device_test - Video Device Test
+ *
+ * Copyright (c) 2016 Shuah Khan <shuahkh@osg.samsung.com>
+ * Copyright (c) 2016 Samsung Electronics Co., Ltd.
+ *
+ * This file is released under the GPLv2.
+ */
+
+/*
+ * This file adds a test for Video Device. This test should not be included
+ * in the Kselftest run. This test should be run when hardware and driver
+ * that makes use of V4L2 API is present.
+ *
+ * This test opens user specified Video Device and calls video ioctls in a
+ * loop once every 10 seconds.
+ *
+ * Usage:
+ *	sudo ./video_device_test -d /dev/videoX
+ *
+ *	While test is running, remove the device or unbind the driver and
+ *	ensure there are no use after free errors and other Oops in the
+ *	dmesg.
+ *	When possible, enable KaSan kernel config option for use-after-free
+ *	error detection.
+*/
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <string.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <time.h>
+#include <linux/videodev2.h>
+
+int main(int argc, char **argv)
+{
+	int opt;
+	char video_dev[256];
+	int count;
+	struct v4l2_tuner vtuner;
+	struct v4l2_capability vcap;
+	int ret;
+	int fd;
+
+	if (argc < 2) {
+		printf("Usage: %s [-d </dev/videoX>]\n", argv[0]);
+		exit(-1);
+	}
+
+	/* Process arguments */
+	while ((opt = getopt(argc, argv, "d:")) != -1) {
+		switch (opt) {
+		case 'd':
+			strncpy(video_dev, optarg, sizeof(video_dev) - 1);
+			video_dev[sizeof(video_dev)-1] = '\0';
+			break;
+		default:
+			printf("Usage: %s [-d </dev/videoX>]\n", argv[0]);
+			exit(-1);
+		}
+	}
+
+	/* Generate random number of interations */
+	srand((unsigned int) time(NULL));
+	count = rand();
+
+	/* Open Video device and keep it open */
+	fd = open(video_dev, O_RDWR);
+	if (fd == -1) {
+		printf("Video Device open errno %s\n", strerror(errno));
+		exit(-1);
+	}
+
+	printf("\nNote:\n"
+	       "While test is running, remove the device or unbind\n"
+	       "driver and ensure there are no use after free errors\n"
+	       "and other Oops in the dmesg. When possible, enable KaSan\n"
+	       "kernel config option for use-after-free error detection.\n\n");
+
+	while (count > 0) {
+		ret = ioctl(fd, VIDIOC_QUERYCAP, &vcap);
+		if (ret < 0)
+			printf("VIDIOC_QUERYCAP errno %s\n", strerror(errno));
+		else
+			printf("Video device driver %s\n", vcap.driver);
+
+		ret = ioctl(fd, VIDIOC_G_TUNER, &vtuner);
+		if (ret < 0)
+			printf("VIDIOC_G_TUNER, errno %s\n", strerror(errno));
+		else
+			printf("type %d rangelow %d rangehigh %d\n",
+				vtuner.type, vtuner.rangelow, vtuner.rangehigh);
+		sleep(10);
+		count--;
+	}
+}
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 4ca83fe80654..3c40c9d0e6c7 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -12,7 +12,8 @@ CFLAGS := -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $
 
 export CFLAGS
 
-SUB_DIRS = benchmarks 		\
+SUB_DIRS = alignment		\
+	   benchmarks		\
 	   copyloops		\
 	   context_switch	\
 	   dscr			\
diff --git a/tools/testing/selftests/powerpc/alignment/.gitignore b/tools/testing/selftests/powerpc/alignment/.gitignore
new file mode 100644
index 000000000000..1d980e3d7039
--- /dev/null
+++ b/tools/testing/selftests/powerpc/alignment/.gitignore
@@ -0,0 +1,5 @@
+copy_unaligned
+copy_first_unaligned
+paste_unaligned
+paste_last_unaligned
+copy_paste_unaligned_common
diff --git a/tools/testing/selftests/powerpc/alignment/Makefile b/tools/testing/selftests/powerpc/alignment/Makefile
new file mode 100644
index 000000000000..ad6a4e49da91
--- /dev/null
+++ b/tools/testing/selftests/powerpc/alignment/Makefile
@@ -0,0 +1,10 @@
+TEST_PROGS := copy_unaligned copy_first_unaligned paste_unaligned paste_last_unaligned
+
+all: $(TEST_PROGS)
+
+$(TEST_PROGS): ../harness.c ../utils.c copy_paste_unaligned_common.c
+
+include ../../lib.mk
+
+clean:
+	rm -f $(TEST_PROGS)
diff --git a/tools/testing/selftests/powerpc/alignment/copy_first_unaligned.c b/tools/testing/selftests/powerpc/alignment/copy_first_unaligned.c
new file mode 100644
index 000000000000..47b73b3a08bd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/alignment/copy_first_unaligned.c
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2016, Chris Smart, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Calls to copy_first which are not 128-byte aligned should be
+ * caught and sent a SIGBUS.
+ *
+ */
+
+#include <string.h>
+#include <unistd.h>
+#include "utils.h"
+#include "instructions.h"
+#include "copy_paste_unaligned_common.h"
+
+unsigned int expected_instruction = PPC_INST_COPY_FIRST;
+unsigned int instruction_mask = 0xfc2007fe;
+
+int test_copy_first_unaligned(void)
+{
+	/* Only run this test on a P9 or later */
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00));
+
+	/* Register our signal handler with SIGBUS */
+	setup_signal_handler();
+
+	/* +1 makes buf unaligned */
+	copy_first(cacheline_buf+1);
+
+	/* We should not get here */
+	return 1;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_copy_first_unaligned, "test_copy_first_unaligned");
+}
diff --git a/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.c b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.c
new file mode 100644
index 000000000000..d35fa5f5d2d3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.c
@@ -0,0 +1,53 @@
+/*
+ * Copyright 2016, Chris Smart, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Common code for copy, copy_first, paste and paste_last unaligned
+ * tests.
+ *
+ */
+
+#include <signal.h>
+#include <string.h>
+#include <unistd.h>
+#include "utils.h"
+#include "instructions.h"
+#include "copy_paste_unaligned_common.h"
+
+unsigned int expected_instruction;
+unsigned int instruction_mask;
+
+char cacheline_buf[128] __cacheline_aligned;
+
+void signal_action_handler(int signal_num, siginfo_t *info, void *ptr)
+{
+	ucontext_t *ctx = ptr;
+#if defined(__powerpc64__)
+	unsigned int *pc = (unsigned int *)ctx->uc_mcontext.gp_regs[PT_NIP];
+#else
+	unsigned int *pc = (unsigned int *)ctx->uc_mcontext.uc_regs->gregs[PT_NIP];
+#endif
+
+	/*
+	 * Check that the signal was on the correct instruction, using a
+	 * mask because the compiler assigns the register at RB.
+	 */
+	if ((*pc & instruction_mask) == expected_instruction)
+		_exit(0); /* We hit the right instruction */
+
+	_exit(1);
+}
+
+void setup_signal_handler(void)
+{
+	struct sigaction signal_action;
+
+	memset(&signal_action, 0, sizeof(signal_action));
+	signal_action.sa_sigaction = signal_action_handler;
+	signal_action.sa_flags = SA_SIGINFO;
+	sigaction(SIGBUS, &signal_action, NULL);
+}
diff --git a/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.h b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.h
new file mode 100644
index 000000000000..053899fe506e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright 2016, Chris Smart, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Declarations for common code for copy, copy_first, paste and
+ * paste_last unaligned tests.
+ *
+ */
+
+#ifndef _SELFTESTS_POWERPC_COPY_PASTE_H
+#define _SELFTESTS_POWERPC_COPY_PASTE_H
+
+#include <signal.h>
+
+int main(int argc, char *argv[]);
+void signal_action_handler(int signal_num, siginfo_t *info, void *ptr);
+void setup_signal_handler(void);
+extern char cacheline_buf[128] __cacheline_aligned;
+extern unsigned int expected_instruction;
+extern unsigned int instruction_mask;
+
+#endif /* _SELFTESTS_POWERPC_COPY_PASTE_H */
diff --git a/tools/testing/selftests/powerpc/alignment/copy_unaligned.c b/tools/testing/selftests/powerpc/alignment/copy_unaligned.c
new file mode 100644
index 000000000000..3a4e26461554
--- /dev/null
+++ b/tools/testing/selftests/powerpc/alignment/copy_unaligned.c
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2016, Chris Smart, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Calls to copy which are not 128-byte aligned should be caught
+ * and sent a SIGBUS.
+ *
+ */
+
+#include <string.h>
+#include <unistd.h>
+#include "utils.h"
+#include "instructions.h"
+#include "copy_paste_unaligned_common.h"
+
+unsigned int expected_instruction = PPC_INST_COPY;
+unsigned int instruction_mask = 0xfc0007fe;
+
+int test_copy_unaligned(void)
+{
+	/* Only run this test on a P9 or later */
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00));
+
+	/* Register our signal handler with SIGBUS */
+	setup_signal_handler();
+
+	/* +1 makes buf unaligned */
+	copy(cacheline_buf+1);
+
+	/* We should not get here */
+	return 1;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_copy_unaligned, "test_copy_unaligned");
+}
diff --git a/tools/testing/selftests/powerpc/alignment/paste_last_unaligned.c b/tools/testing/selftests/powerpc/alignment/paste_last_unaligned.c
new file mode 100644
index 000000000000..6e0ad045fcc3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/alignment/paste_last_unaligned.c
@@ -0,0 +1,43 @@
+/*
+ * Copyright 2016, Chris Smart, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Calls to paste_last which are not 128-byte aligned should be
+ * caught and sent a SIGBUS.
+ *
+ */
+
+#include <string.h>
+#include <unistd.h>
+#include "utils.h"
+#include "instructions.h"
+#include "copy_paste_unaligned_common.h"
+
+unsigned int expected_instruction = PPC_INST_PASTE_LAST;
+unsigned int instruction_mask = 0xfc2007ff;
+
+int test_paste_last_unaligned(void)
+{
+	/* Only run this test on a P9 or later */
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00));
+
+	/* Register our signal handler with SIGBUS */
+	setup_signal_handler();
+
+	copy(cacheline_buf);
+
+	/* +1 makes buf unaligned */
+	paste_last(cacheline_buf+1);
+
+	/* We should not get here */
+	return 1;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_paste_last_unaligned, "test_paste_last_unaligned");
+}
diff --git a/tools/testing/selftests/powerpc/alignment/paste_unaligned.c b/tools/testing/selftests/powerpc/alignment/paste_unaligned.c
new file mode 100644
index 000000000000..6f982b45e4bd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/alignment/paste_unaligned.c
@@ -0,0 +1,43 @@
+/*
+ * Copyright 2016, Chris Smart, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Calls to paste which are not 128-byte aligned should be caught
+ * and sent a SIGBUS.
+ *
+ */
+
+#include <string.h>
+#include <unistd.h>
+#include "utils.h"
+#include "instructions.h"
+#include "copy_paste_unaligned_common.h"
+
+unsigned int expected_instruction = PPC_INST_PASTE;
+unsigned int instruction_mask = 0xfc0007fe;
+
+int test_paste_unaligned(void)
+{
+	/* Only run this test on a P9 or later */
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00));
+
+	/* Register our signal handler with SIGBUS */
+	setup_signal_handler();
+
+	copy(cacheline_buf);
+
+	/* +1 makes buf unaligned */
+	paste(cacheline_buf+1);
+
+	/* We should not get here */
+	return 1;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_paste_unaligned, "test_paste_unaligned");
+}
diff --git a/tools/testing/selftests/powerpc/benchmarks/.gitignore b/tools/testing/selftests/powerpc/benchmarks/.gitignore
index 6fa673316ac2..bce49ebd869e 100644
--- a/tools/testing/selftests/powerpc/benchmarks/.gitignore
+++ b/tools/testing/selftests/powerpc/benchmarks/.gitignore
@@ -1,2 +1,4 @@
 gettimeofday
 context_switch
+mmap_bench
+futex_bench
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile
index 912445ff7ce7..a9adfb7de78f 100644
--- a/tools/testing/selftests/powerpc/benchmarks/Makefile
+++ b/tools/testing/selftests/powerpc/benchmarks/Makefile
@@ -1,4 +1,4 @@
-TEST_PROGS := gettimeofday context_switch
+TEST_PROGS := gettimeofday context_switch mmap_bench futex_bench
 
 CFLAGS += -O2
 
@@ -7,6 +7,7 @@ all: $(TEST_PROGS)
 $(TEST_PROGS): ../harness.c
 
 context_switch: ../utils.c
+context_switch: CFLAGS += -maltivec -mvsx -mabi=altivec
 context_switch: LDLIBS += -lpthread
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
index 7b785941adec..a36883ad48a4 100644
--- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c
+++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
@@ -25,7 +25,9 @@
 #include <sys/types.h>
 #include <sys/shm.h>
 #include <linux/futex.h>
-
+#ifdef __powerpc__
+#include <altivec.h>
+#endif
 #include "../utils.h"
 
 static unsigned int timeout = 30;
@@ -37,12 +39,15 @@ static int touch_fp = 1;
 double fp;
 
 static int touch_vector = 1;
-typedef int v4si __attribute__ ((vector_size (16)));
-v4si a, b, c;
+vector int a, b, c;
 
 #ifdef __powerpc__
 static int touch_altivec = 1;
 
+/*
+ * Note: LTO (Link Time Optimisation) doesn't play well with this function
+ * attribute. Be very careful enabling LTO for this test.
+ */
 static void __attribute__((__target__("no-vsx"))) altivec_touch_fn(void)
 {
 	c = a + b;
@@ -369,11 +374,11 @@ static void usage(void)
 	fprintf(stderr, "\t\t--process\tUse processes (default threads)\n");
 	fprintf(stderr, "\t\t--timeout=X\tDuration in seconds to run (default 30)\n");
 	fprintf(stderr, "\t\t--vdso\t\ttouch VDSO\n");
-	fprintf(stderr, "\t\t--fp\t\ttouch FP\n");
+	fprintf(stderr, "\t\t--no-fp\t\tDon't touch FP\n");
 #ifdef __powerpc__
-	fprintf(stderr, "\t\t--altivec\ttouch altivec\n");
+	fprintf(stderr, "\t\t--no-altivec\tDon't touch altivec\n");
 #endif
-	fprintf(stderr, "\t\t--vector\ttouch vector\n");
+	fprintf(stderr, "\t\t--no-vector\tDon't touch vector\n");
 }
 
 int main(int argc, char *argv[])
diff --git a/tools/testing/selftests/powerpc/benchmarks/futex_bench.c b/tools/testing/selftests/powerpc/benchmarks/futex_bench.c
new file mode 100644
index 000000000000..2fc711d9150d
--- /dev/null
+++ b/tools/testing/selftests/powerpc/benchmarks/futex_bench.c
@@ -0,0 +1,42 @@
+/*
+ * Copyright 2016, Anton Blanchard, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <sys/syscall.h>
+#include <time.h>
+#include <unistd.h>
+#include <linux/futex.h>
+
+#include "utils.h"
+
+#define ITERATIONS 100000000
+
+#define futex(A, B, C, D, E, F)	 syscall(__NR_futex, A, B, C, D, E, F)
+
+int test_futex(void)
+{
+	struct timespec ts_start, ts_end;
+	unsigned long i = ITERATIONS;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts_start);
+
+	while (i--) {
+		unsigned int addr = 0;
+		futex(&addr, FUTEX_WAKE, 1, NULL, NULL, 0);
+	}
+
+	clock_gettime(CLOCK_MONOTONIC, &ts_end);
+
+	printf("time = %.6f\n", ts_end.tv_sec - ts_start.tv_sec + (ts_end.tv_nsec - ts_start.tv_nsec) / 1e9);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_futex, "futex_bench");
+}
diff --git a/tools/testing/selftests/powerpc/benchmarks/mmap_bench.c b/tools/testing/selftests/powerpc/benchmarks/mmap_bench.c
new file mode 100644
index 000000000000..8d084a2d6e74
--- /dev/null
+++ b/tools/testing/selftests/powerpc/benchmarks/mmap_bench.c
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2016, Anton Blanchard, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <time.h>
+
+#include "utils.h"
+
+#define ITERATIONS 5000000
+
+#define MEMSIZE (128 * 1024 * 1024)
+
+int test_mmap(void)
+{
+	struct timespec ts_start, ts_end;
+	unsigned long i = ITERATIONS;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts_start);
+
+	while (i--) {
+		char *c = mmap(NULL, MEMSIZE, PROT_READ|PROT_WRITE,
+			       MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
+		FAIL_IF(c == MAP_FAILED);
+		munmap(c, MEMSIZE);
+	}
+
+	clock_gettime(CLOCK_MONOTONIC, &ts_end);
+
+	printf("time = %.6f\n", ts_end.tv_sec - ts_start.tv_sec + (ts_end.tv_nsec - ts_start.tv_nsec) / 1e9);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_mmap, "mmap_bench");
+}
diff --git a/tools/testing/selftests/powerpc/instructions.h b/tools/testing/selftests/powerpc/instructions.h
new file mode 100644
index 000000000000..0fb0bd3b28c9
--- /dev/null
+++ b/tools/testing/selftests/powerpc/instructions.h
@@ -0,0 +1,68 @@
+#ifndef _SELFTESTS_POWERPC_INSTRUCTIONS_H
+#define _SELFTESTS_POWERPC_INSTRUCTIONS_H
+
+#include <stdio.h>
+#include <stdlib.h>
+
+/* This defines the "copy" instruction from Power ISA 3.0 Book II, section 4.4. */
+#define __COPY(RA, RB, L) \
+	(0x7c00060c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10))
+#define COPY(RA, RB, L) \
+	.long __COPY((RA), (RB), (L))
+
+static inline void copy(void *i)
+{
+	asm volatile(str(COPY(0, %0, 0))";"
+			:
+			: "b" (i)
+			: "memory"
+		    );
+}
+
+static inline void copy_first(void *i)
+{
+	asm volatile(str(COPY(0, %0, 1))";"
+			:
+			: "b" (i)
+			: "memory"
+		    );
+}
+
+/* This defines the "paste" instruction from Power ISA 3.0 Book II, section 4.4. */
+#define __PASTE(RA, RB, L, RC) \
+	(0x7c00070c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10) | (RC) << (31-31))
+#define PASTE(RA, RB, L, RC) \
+	.long __PASTE((RA), (RB), (L), (RC))
+
+static inline int paste(void *i)
+{
+	int cr;
+
+	asm volatile(str(PASTE(0, %1, 0, 0))";"
+			"mfcr %0;"
+			: "=r" (cr)
+			: "b" (i)
+			: "memory"
+		    );
+	return cr;
+}
+
+static inline int paste_last(void *i)
+{
+	int cr;
+
+	asm volatile(str(PASTE(0, %1, 1, 1))";"
+			"mfcr %0;"
+			: "=r" (cr)
+			: "b" (i)
+			: "memory"
+		    );
+	return cr;
+}
+
+#define PPC_INST_COPY                  __COPY(0, 0, 0)
+#define PPC_INST_COPY_FIRST            __COPY(0, 0, 1)
+#define PPC_INST_PASTE                 __PASTE(0, 0, 0, 0)
+#define PPC_INST_PASTE_LAST            __PASTE(0, 0, 1, 1)
+
+#endif /* _SELFTESTS_POWERPC_INSTRUCTIONS_H */
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index b43ade0ec861..e715a3f2fbf4 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -1,3 +1,4 @@
 hugetlb_vs_thp_test
 subpage_prot
 tempfile
+prot_sao
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index ee179e22308c..3bdb96eae558 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -1,13 +1,15 @@
 noarg:
 	$(MAKE) -C ../
 
-TEST_PROGS := hugetlb_vs_thp_test subpage_prot
+TEST_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao
 TEST_FILES := tempfile
 
 all: $(TEST_PROGS) $(TEST_FILES)
 
 $(TEST_PROGS): ../harness.c
 
+prot_sao: ../utils.c
+
 include ../../lib.mk
 
 tempfile:
diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c
new file mode 100644
index 000000000000..611530d43fa9
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/prot_sao.c
@@ -0,0 +1,42 @@
+/*
+ * Copyright 2016, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+
+#include <asm/cputable.h>
+
+#include "utils.h"
+
+#define SIZE (64 * 1024)
+
+int test_prot_sao(void)
+{
+	char *p;
+
+	/* 2.06 or later should support SAO */
+	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
+
+	/*
+	 * Ensure we can ask for PROT_SAO.
+	 * We can't really verify that it does the right thing, but at least we
+	 * confirm the kernel will accept it.
+	 */
+	p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO,
+		 MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	FAIL_IF(p == MAP_FAILED);
+
+	/* Write to the mapping, to at least cause a fault */
+	memset(p, 0xaa, SIZE);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_prot_sao, "prot-sao");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore
index 42bddbed8b64..44b7df14a936 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore
+++ b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore
@@ -20,3 +20,5 @@ back_to_back_ebbs_test
 lost_exception_test
 no_handler_test
 cycles_with_mmcr2_test
+ebb_lmr
+ebb_lmr_regs
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index 8d2279c4bb4b..6b0453e60d53 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -14,7 +14,7 @@ TEST_PROGS := reg_access_test event_attributes_test cycles_test	\
 	 fork_cleanup_test ebb_on_child_test			\
 	 ebb_on_willing_child_test back_to_back_ebbs_test	\
 	 lost_exception_test no_handler_test			\
-	 cycles_with_mmcr2_test
+	 cycles_with_mmcr2_test ebb_lmr ebb_lmr_regs
 
 all: $(TEST_PROGS)
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.c
new file mode 100644
index 000000000000..c47ebd55ba4d
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.c
@@ -0,0 +1,143 @@
+/*
+ * Copyright 2016, Jack Miller, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+
+#include "ebb.h"
+#include "ebb_lmr.h"
+
+#define SIZE		(32 * 1024 * 1024)	/* 32M */
+#define LM_SIZE		0	/* Smallest encoding, 32M */
+
+#define SECTIONS	64	/* 1 per bit in LMSER */
+#define SECTION_SIZE	(SIZE / SECTIONS)
+#define SECTION_LONGS   (SECTION_SIZE / sizeof(long))
+
+static unsigned long *test_mem;
+
+static int lmr_count = 0;
+
+void ebb_lmr_handler(void)
+{
+	lmr_count++;
+}
+
+void ldmx_full_section(unsigned long *mem, int section)
+{
+	unsigned long *ptr;
+	int i;
+
+	for (i = 0; i < SECTION_LONGS; i++) {
+		ptr = &mem[(SECTION_LONGS * section) + i];
+		ldmx((unsigned long) &ptr);
+		ebb_lmr_reset();
+	}
+}
+
+unsigned long section_masks[] = {
+	0x8000000000000000,
+	0xFF00000000000000,
+	0x0000000F70000000,
+	0x8000000000000001,
+	0xF0F0F0F0F0F0F0F0,
+	0x0F0F0F0F0F0F0F0F,
+	0x0
+};
+
+int ebb_lmr_section_test(unsigned long *mem)
+{
+	unsigned long *mask = section_masks;
+	int i;
+
+	for (; *mask; mask++) {
+		mtspr(SPRN_LMSER, *mask);
+		printf("Testing mask 0x%016lx\n", mfspr(SPRN_LMSER));
+
+		for (i = 0; i < 64; i++) {
+			lmr_count = 0;
+			ldmx_full_section(mem, i);
+			if (*mask & (1UL << (63 - i)))
+				FAIL_IF(lmr_count != SECTION_LONGS);
+			else
+				FAIL_IF(lmr_count);
+		}
+	}
+
+	return 0;
+}
+
+int ebb_lmr(void)
+{
+	int i;
+
+	SKIP_IF(!lmr_is_supported());
+
+	setup_ebb_handler(ebb_lmr_handler);
+
+	ebb_global_enable();
+
+	FAIL_IF(posix_memalign((void **)&test_mem, SIZE, SIZE) != 0);
+
+	mtspr(SPRN_LMSER, 0);
+
+	FAIL_IF(mfspr(SPRN_LMSER) != 0);
+
+	mtspr(SPRN_LMRR, ((unsigned long)test_mem | LM_SIZE));
+
+	FAIL_IF(mfspr(SPRN_LMRR) != ((unsigned long)test_mem | LM_SIZE));
+
+	/* Read every single byte to ensure we get no false positives */
+	for (i = 0; i < SECTIONS; i++)
+		ldmx_full_section(test_mem, i);
+
+	FAIL_IF(lmr_count != 0);
+
+	/* Turn on the first section */
+
+	mtspr(SPRN_LMSER, (1UL << 63));
+	FAIL_IF(mfspr(SPRN_LMSER) != (1UL << 63));
+
+	/* Enable LM (BESCR) */
+
+	mtspr(SPRN_BESCR, mfspr(SPRN_BESCR) | BESCR_LME);
+	FAIL_IF(!(mfspr(SPRN_BESCR) & BESCR_LME));
+
+	ldmx((unsigned long)&test_mem);
+
+	FAIL_IF(lmr_count != 1);	// exactly one exception
+	FAIL_IF(mfspr(SPRN_BESCR) & BESCR_LME);	// LM now disabled
+	FAIL_IF(!(mfspr(SPRN_BESCR) & BESCR_LMEO));	// occurred bit set
+
+	printf("Simple LMR EBB OK\n");
+
+	/* This shouldn't cause an EBB since it's been disabled */
+	ldmx((unsigned long)&test_mem);
+	FAIL_IF(lmr_count != 1);
+
+	printf("LMR disable on EBB OK\n");
+
+	ebb_lmr_reset();
+
+	/* This should cause an EBB or reset is broken */
+	ldmx((unsigned long)&test_mem);
+	FAIL_IF(lmr_count != 2);
+
+	printf("LMR reset EBB OK\n");
+
+	ebb_lmr_reset();
+
+	return ebb_lmr_section_test(test_mem);
+}
+
+int main(void)
+{
+	int ret = test_harness(ebb_lmr, "ebb_lmr");
+
+	if (test_mem)
+		free(test_mem);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.h b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.h
new file mode 100644
index 000000000000..ef50abd557cd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.h
@@ -0,0 +1,39 @@
+#ifndef _SELFTESTS_POWERPC_PMU_EBB_LMR_H
+#define _SELFTESTS_POWERPC_PMU_EBB_LMR_H
+
+#include "reg.h"
+
+#ifndef PPC_FEATURE2_ARCH_3_00
+#define PPC_FEATURE2_ARCH_3_00 0x00800000
+#endif
+
+#define lmr_is_supported() have_hwcap2(PPC_FEATURE2_ARCH_3_00)
+
+static inline void ebb_lmr_reset(void)
+{
+	unsigned long bescr = mfspr(SPRN_BESCR);
+	bescr &= ~(BESCR_LMEO);
+	bescr |= BESCR_LME;
+	mtspr(SPRN_BESCR, bescr);
+}
+
+#define LDMX(t, a, b)\
+	(0x7c00026a |				\
+	 (((t) & 0x1f) << 21) |			\
+	 (((a) & 0x1f) << 16) |			\
+	 (((b) & 0x1f) << 11))
+
+static inline unsigned long ldmx(unsigned long address)
+{
+	unsigned long ret;
+
+	asm volatile ("mr 9, %1\r\n"
+		      ".long " __stringify(LDMX(9, 0, 9)) "\r\n"
+		      "mr %0, 9\r\n":"=r"(ret)
+		      :"r"(address)
+		      :"r9");
+
+	return ret;
+}
+
+#endif
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr_regs.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr_regs.c
new file mode 100644
index 000000000000..aff4241fd88a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr_regs.c
@@ -0,0 +1,37 @@
+/*
+ * Copyright 2016, Jack Miller, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include "ebb.h"
+#include "ebb_lmr.h"
+
+#define CHECKS 10000
+
+int ebb_lmr_regs(void)
+{
+	int i;
+
+	SKIP_IF(!lmr_is_supported());
+
+	ebb_global_enable();
+
+	for (i = 0; i < CHECKS; i++) {
+		mtspr(SPRN_LMRR, i << 25);	// skip size and rsvd bits
+		mtspr(SPRN_LMSER, i);
+
+		FAIL_IF(mfspr(SPRN_LMRR) != (i << 25));
+		FAIL_IF(mfspr(SPRN_LMSER) != i);
+	}
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(ebb_lmr_regs, "ebb_lmr_regs");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c b/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c
index 5da355135df2..ae9a79086111 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c
@@ -51,7 +51,7 @@ static int do_count_loop(struct event *event, uint64_t instructions,
 		printf("Looped for %lu instructions, overhead %lu\n", instructions, overhead);
 		printf("Expected %lu\n", expected);
 		printf("Actual   %llu\n", event->result.value);
-		printf("Error    %ld, %f%%\n", difference, percentage);
+		printf("Delta    %ld, %f%%\n", difference, percentage);
 		printf("Took %d EBBs\n", ebb_state.stats.ebb_count);
 	}
 
diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c
index a361ad3334ce..8b992fa5b478 100644
--- a/tools/testing/selftests/powerpc/pmu/lib.c
+++ b/tools/testing/selftests/powerpc/pmu/lib.c
@@ -190,7 +190,7 @@ int parse_proc_maps(void)
 
 bool require_paranoia_below(int level)
 {
-	unsigned long current;
+	long current;
 	char *end, buf[16];
 	FILE *f;
 	int rc;
@@ -208,7 +208,7 @@ bool require_paranoia_below(int level)
 		goto out_close;
 	}
 
-	current = strtoul(buf, &end, 10);
+	current = strtol(buf, &end, 10);
 
 	if (end == buf) {
 		printf("Couldn't parse " PARANOID_PATH "?\n");
@@ -216,7 +216,7 @@ bool require_paranoia_below(int level)
 	}
 
 	if (current >= level)
-		goto out;
+		goto out_close;
 
 	rc = 0;
 out_close:
diff --git a/tools/testing/selftests/powerpc/reg.h b/tools/testing/selftests/powerpc/reg.h
index 65bfdeeebdee..fddf368ed82f 100644
--- a/tools/testing/selftests/powerpc/reg.h
+++ b/tools/testing/selftests/powerpc/reg.h
@@ -34,6 +34,11 @@
 
 #define BESCR_PMEO     0x1     /* PMU Event-based exception Occurred */
 #define BESCR_PME      (0x1ul << 32) /* PMU Event-based exception Enable */
+#define BESCR_LME      (0x1ul << 34) /* Load Monitor Enable */
+#define BESCR_LMEO     (0x1ul << 2)  /* Load Monitor Exception Occurred */
+
+#define SPRN_LMRR      813     /* Load Monitor Region Register */
+#define SPRN_LMSER     814     /* Load Monitor Section Enable Register */
 
 #define SPRN_PMC1      771
 #define SPRN_PMC2      772
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index bb942db845bf..82c0a9ce6e74 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -6,3 +6,4 @@ tm-vmxcopy
 tm-fork
 tm-tar
 tm-tmspr
+tm-exec
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index d0505dbd22d5..9d301d785d9e 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -1,11 +1,14 @@
-TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack tm-vmxcopy tm-fork tm-tar tm-tmspr
+TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
+	tm-vmxcopy tm-fork tm-tar tm-tmspr tm-exec tm-execed
 
 all: $(TEST_PROGS)
 
 $(TEST_PROGS): ../harness.c ../utils.c
 
+CFLAGS += -mhtm
+
 tm-syscall: tm-syscall-asm.S
-tm-syscall: CFLAGS += -mhtm -I../../../../../usr/include
+tm-syscall: CFLAGS += -I../../../../../usr/include
 tm-tmspr: CFLAGS += -pthread
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/tm/tm-exec.c b/tools/testing/selftests/powerpc/tm/tm-exec.c
new file mode 100644
index 000000000000..3d27fa0ece04
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-exec.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright 2016, Cyril Bur, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Syscalls can be performed provided the transactions are suspended.
+ * The exec() class of syscall is unique as a new process is loaded.
+ *
+ * It makes little sense for after an exec() call for the previously
+ * suspended transaction to still exist.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <inttypes.h>
+#include <libgen.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "utils.h"
+#include "tm.h"
+
+static char *path;
+
+static int test_exec(void)
+{
+	SKIP_IF(!have_htm());
+
+	asm __volatile__(
+		"tbegin.;"
+		"blt    1f; "
+		"tsuspend.;"
+		"1: ;"
+		: : : "memory");
+
+	execl(path, "tm-exec", "--child", NULL);
+
+	/* Shouldn't get here */
+	perror("execl() failed");
+	return 1;
+}
+
+static int after_exec(void)
+{
+	asm __volatile__(
+		"tbegin.;"
+		"blt    1f;"
+		"tsuspend.;"
+		"1: ;"
+		: : : "memory");
+
+	FAIL_IF(failure_is_nesting());
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	path = argv[0];
+
+	if (argc > 1 && strcmp(argv[1], "--child") == 0)
+		return after_exec();
+
+	return test_harness(test_exec, "tm_exec");
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c
index 60560cb20e38..454b965a2db3 100644
--- a/tools/testing/selftests/powerpc/tm/tm-syscall.c
+++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c
@@ -27,21 +27,6 @@ unsigned retries = 0;
 #define TEST_DURATION 10 /* seconds */
 #define TM_RETRIES 100
 
-long failure_code(void)
-{
-	return __builtin_get_texasru() >> 24;
-}
-
-bool failure_is_persistent(void)
-{
-	return (failure_code() & TM_CAUSE_PERSISTENT) == TM_CAUSE_PERSISTENT;
-}
-
-bool failure_is_syscall(void)
-{
-	return (failure_code() & TM_CAUSE_SYSCALL) == TM_CAUSE_SYSCALL;
-}
-
 pid_t getppid_tm(bool suspend)
 {
 	int i;
diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h
index 24144b25772c..60318bad7d7a 100644
--- a/tools/testing/selftests/powerpc/tm/tm.h
+++ b/tools/testing/selftests/powerpc/tm/tm.h
@@ -6,8 +6,9 @@
 #ifndef _SELFTESTS_POWERPC_TM_TM_H
 #define _SELFTESTS_POWERPC_TM_TM_H
 
-#include <stdbool.h>
+#include <asm/tm.h>
 #include <asm/cputable.h>
+#include <stdbool.h>
 
 #include "../utils.h"
 
@@ -31,4 +32,24 @@ static inline bool have_htm_nosc(void)
 #endif
 }
 
+static inline long failure_code(void)
+{
+	return __builtin_get_texasru() >> 24;
+}
+
+static inline bool failure_is_persistent(void)
+{
+	return (failure_code() & TM_CAUSE_PERSISTENT) == TM_CAUSE_PERSISTENT;
+}
+
+static inline bool failure_is_syscall(void)
+{
+	return (failure_code() & TM_CAUSE_SYSCALL) == TM_CAUSE_SYSCALL;
+}
+
+static inline bool failure_is_nesting(void)
+{
+	return (__builtin_get_texasru() & 0x400000);
+}
+
 #endif /* _SELFTESTS_POWERPC_TM_TM_H */
diff --git a/tools/testing/selftests/powerpc/utils.h b/tools/testing/selftests/powerpc/utils.h
index a985cfaa535e..fbd33e52ef8f 100644
--- a/tools/testing/selftests/powerpc/utils.h
+++ b/tools/testing/selftests/powerpc/utils.h
@@ -27,6 +27,11 @@ int test_harness(int (test_function)(void), char *name);
 extern void *get_auxv_entry(int type);
 int pick_online_cpu(void);
 
+static inline bool have_hwcap(unsigned long ftr)
+{
+	return ((unsigned long)get_auxv_entry(AT_HWCAP) & ftr) == ftr;
+}
+
 static inline bool have_hwcap2(unsigned long ftr2)
 {
 	return ((unsigned long)get_auxv_entry(AT_HWCAP2) & ftr2) == ftr2;
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index 4a1be1b75a7f..1d5556869137 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -10,7 +10,7 @@ TEST_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \
 
 TEST_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex adjtick change_skew \
 		      skew_consistency clocksource-switch leap-a-day \
-		      leapcrash set-tai set-2038
+		      leapcrash set-tai set-2038 set-tz
 
 bins = $(TEST_PROGS) $(TEST_PROGS_EXTENDED)
 
@@ -30,6 +30,7 @@ run_destructive_tests: run_tests
 	./clocksource-switch
 	./leap-a-day -s -i 10
 	./leapcrash
+	./set-tz
 	./set-tai
 	./set-2038
 
diff --git a/tools/testing/selftests/timers/set-tz.c b/tools/testing/selftests/timers/set-tz.c
new file mode 100644
index 000000000000..f4184928b16b
--- /dev/null
+++ b/tools/testing/selftests/timers/set-tz.c
@@ -0,0 +1,119 @@
+/* Set tz value
+ *              by: John Stultz <john.stultz@linaro.org>
+ *              (C) Copyright Linaro 2016
+ *              Licensed under the GPLv2
+ *
+ *   This program is free software: you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation, either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *   GNU General Public License for more details.
+ */
+
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <sys/time.h>
+#include <sys/timex.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#ifdef KTEST
+#include "../kselftest.h"
+#else
+static inline int ksft_exit_pass(void)
+{
+	exit(0);
+}
+static inline int ksft_exit_fail(void)
+{
+	exit(1);
+}
+#endif
+
+int set_tz(int min, int dst)
+{
+	struct timezone tz;
+
+	tz.tz_minuteswest = min;
+	tz.tz_dsttime = dst;
+
+	return settimeofday(0, &tz);
+}
+
+int get_tz_min(void)
+{
+	struct timezone tz;
+	struct timeval tv;
+
+	memset(&tz, 0, sizeof(tz));
+	gettimeofday(&tv, &tz);
+	return tz.tz_minuteswest;
+}
+
+int get_tz_dst(void)
+{
+	struct timezone tz;
+	struct timeval tv;
+
+	memset(&tz, 0, sizeof(tz));
+	gettimeofday(&tv, &tz);
+	return tz.tz_dsttime;
+}
+
+int main(int argc, char **argv)
+{
+	int i, ret;
+	int min, dst;
+
+	min = get_tz_min();
+	dst = get_tz_dst();
+	printf("tz_minuteswest started at %i, dst at %i\n", min, dst);
+
+	printf("Checking tz_minuteswest can be properly set: ");
+	for (i = -15*60; i < 15*60; i += 30) {
+		ret = set_tz(i, dst);
+		ret = get_tz_min();
+		if (ret != i) {
+			printf("[FAILED] expected: %i got %i\n", i, ret);
+			goto err;
+		}
+	}
+	printf("[OK]\n");
+
+	printf("Checking invalid tz_minuteswest values are caught: ");
+
+	if (!set_tz(-15*60-1, dst)) {
+		printf("[FAILED] %i didn't return failure!\n", -15*60-1);
+		goto err;
+	}
+
+	if (!set_tz(15*60+1, dst)) {
+		printf("[FAILED] %i didn't return failure!\n", 15*60+1);
+		goto err;
+	}
+
+	if (!set_tz(-24*60, dst)) {
+		printf("[FAILED] %i didn't return failure!\n", -24*60);
+		goto err;
+	}
+
+	if (!set_tz(24*60, dst)) {
+		printf("[FAILED] %i didn't return failure!\n", 24*60);
+		goto err;
+	}
+
+	printf("[OK]\n");
+
+	set_tz(min, dst);
+	return ksft_exit_pass();
+
+err:
+	set_tz(min, dst);
+	return ksft_exit_fail();
+}
diff --git a/tools/testing/selftests/vm/compaction_test.c b/tools/testing/selftests/vm/compaction_test.c
index 00c4f65d12da..6d1437f895b8 100644
--- a/tools/testing/selftests/vm/compaction_test.c
+++ b/tools/testing/selftests/vm/compaction_test.c
@@ -101,7 +101,7 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 
 	/* Start with the initial condition of 0 huge pages*/
 	if (write(fd, "0", sizeof(char)) != sizeof(char)) {
-		perror("Failed to write to /proc/sys/vm/nr_hugepages\n");
+		perror("Failed to write 0 to /proc/sys/vm/nr_hugepages\n");
 		goto close_fd;
 	}
 
@@ -110,14 +110,14 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 	/* Request a large number of huge pages. The Kernel will allocate
 	   as much as it can */
 	if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) {
-		perror("Failed to write to /proc/sys/vm/nr_hugepages\n");
+		perror("Failed to write 100000 to /proc/sys/vm/nr_hugepages\n");
 		goto close_fd;
 	}
 
 	lseek(fd, 0, SEEK_SET);
 
 	if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) {
-		perror("Failed to read from /proc/sys/vm/nr_hugepages\n");
+		perror("Failed to re-read from /proc/sys/vm/nr_hugepages\n");
 		goto close_fd;
 	}
 
@@ -138,7 +138,7 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)
 
 	if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages))
 	    != strlen(initial_nr_hugepages)) {
-		perror("Failed to write to /proc/sys/vm/nr_hugepages\n");
+		perror("Failed to write value to /proc/sys/vm/nr_hugepages\n");
 		goto close_fd;
 	}
 
diff --git a/tools/testing/selftests/vm/on-fault-limit.c b/tools/testing/selftests/vm/on-fault-limit.c
index 245acccce42d..0ae458f32fdb 100644
--- a/tools/testing/selftests/vm/on-fault-limit.c
+++ b/tools/testing/selftests/vm/on-fault-limit.c
@@ -20,7 +20,7 @@ static int test_limit(void)
 		return ret;
 	}
 
-	if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+	if (mlockall(MCL_ONFAULT | MCL_FUTURE)) {
 		perror("mlockall");
 		return ret;
 	}
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index e5d6108f5e85..b0cc1a34db27 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -16,9 +16,6 @@ config HAVE_KVM_EVENTFD
        bool
        select EVENTFD
 
-config KVM_APIC_ARCHITECTURE
-       bool
-
 config KVM_MMIO
        bool
 
diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c
index 3a3a699b7489..7cffd9338c49 100644
--- a/virt/kvm/arm/hyp/vgic-v2-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v2-sr.c
@@ -21,18 +21,11 @@
 
 #include <asm/kvm_hyp.h>
 
-#ifdef CONFIG_KVM_NEW_VGIC
-extern struct vgic_global kvm_vgic_global_state;
-#define vgic_v2_params kvm_vgic_global_state
-#else
-extern struct vgic_params vgic_v2_params;
-#endif
-
 static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
 					    void __iomem *base)
 {
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
+	int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
 	u32 eisr0, eisr1;
 	int i;
 	bool expect_mi;
@@ -74,7 +67,7 @@ static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
 static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
 {
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
+	int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
 	u32 elrsr0, elrsr1;
 
 	elrsr0 = readl_relaxed(base + GICH_ELRSR0);
@@ -93,7 +86,7 @@ static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
 static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
 {
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
+	int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
 	int i;
 
 	for (i = 0; i < nr_lr; i++) {
@@ -147,7 +140,7 @@ void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
 	struct vgic_dist *vgic = &kvm->arch.vgic;
 	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
-	int nr_lr = (kern_hyp_va(&vgic_v2_params))->nr_lr;
+	int nr_lr = (kern_hyp_va(&kvm_vgic_global_state))->nr_lr;
 	int i;
 	u64 live_lrs = 0;
 
diff --git a/virt/kvm/arm/vgic-v2-emul.c b/virt/kvm/arm/vgic-v2-emul.c
deleted file mode 100644
index 1b0bee095427..000000000000
--- a/virt/kvm/arm/vgic-v2-emul.c
+++ /dev/null
@@ -1,856 +0,0 @@
-/*
- * Contains GICv2 specific emulation code, was in vgic.c before.
- *
- * Copyright (C) 2012 ARM Ltd.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/cpu.h>
-#include <linux/kvm.h>
-#include <linux/kvm_host.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/uaccess.h>
-
-#include <linux/irqchip/arm-gic.h>
-
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_mmu.h>
-
-#include "vgic.h"
-
-#define GICC_ARCH_VERSION_V2		0x2
-
-static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg);
-static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi)
-{
-	return dist->irq_sgi_sources + vcpu_id * VGIC_NR_SGIS + sgi;
-}
-
-static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
-			     struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
-	u32 reg;
-	u32 word_offset = offset & 3;
-
-	switch (offset & ~3) {
-	case 0:			/* GICD_CTLR */
-		reg = vcpu->kvm->arch.vgic.enabled;
-		vgic_reg_access(mmio, &reg, word_offset,
-				ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
-		if (mmio->is_write) {
-			vcpu->kvm->arch.vgic.enabled = reg & 1;
-			vgic_update_state(vcpu->kvm);
-			return true;
-		}
-		break;
-
-	case 4:			/* GICD_TYPER */
-		reg  = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5;
-		reg |= (vcpu->kvm->arch.vgic.nr_irqs >> 5) - 1;
-		vgic_reg_access(mmio, &reg, word_offset,
-				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-		break;
-
-	case 8:			/* GICD_IIDR */
-		reg = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
-		vgic_reg_access(mmio, &reg, word_offset,
-				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-		break;
-	}
-
-	return false;
-}
-
-static bool handle_mmio_set_enable_reg(struct kvm_vcpu *vcpu,
-				       struct kvm_exit_mmio *mmio,
-				       phys_addr_t offset)
-{
-	return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
-				      vcpu->vcpu_id, ACCESS_WRITE_SETBIT);
-}
-
-static bool handle_mmio_clear_enable_reg(struct kvm_vcpu *vcpu,
-					 struct kvm_exit_mmio *mmio,
-					 phys_addr_t offset)
-{
-	return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
-				      vcpu->vcpu_id, ACCESS_WRITE_CLEARBIT);
-}
-
-static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
-					struct kvm_exit_mmio *mmio,
-					phys_addr_t offset)
-{
-	return vgic_handle_set_pending_reg(vcpu->kvm, mmio, offset,
-					   vcpu->vcpu_id);
-}
-
-static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
-					  struct kvm_exit_mmio *mmio,
-					  phys_addr_t offset)
-{
-	return vgic_handle_clear_pending_reg(vcpu->kvm, mmio, offset,
-					     vcpu->vcpu_id);
-}
-
-static bool handle_mmio_set_active_reg(struct kvm_vcpu *vcpu,
-				       struct kvm_exit_mmio *mmio,
-				       phys_addr_t offset)
-{
-	return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset,
-					  vcpu->vcpu_id);
-}
-
-static bool handle_mmio_clear_active_reg(struct kvm_vcpu *vcpu,
-					 struct kvm_exit_mmio *mmio,
-					 phys_addr_t offset)
-{
-	return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset,
-					    vcpu->vcpu_id);
-}
-
-static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu,
-				     struct kvm_exit_mmio *mmio,
-				     phys_addr_t offset)
-{
-	u32 *reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority,
-					vcpu->vcpu_id, offset);
-	vgic_reg_access(mmio, reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
-	return false;
-}
-
-#define GICD_ITARGETSR_SIZE	32
-#define GICD_CPUTARGETS_BITS	8
-#define GICD_IRQS_PER_ITARGETSR	(GICD_ITARGETSR_SIZE / GICD_CPUTARGETS_BITS)
-static u32 vgic_get_target_reg(struct kvm *kvm, int irq)
-{
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	int i;
-	u32 val = 0;
-
-	irq -= VGIC_NR_PRIVATE_IRQS;
-
-	for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++)
-		val |= 1 << (dist->irq_spi_cpu[irq + i] + i * 8);
-
-	return val;
-}
-
-static void vgic_set_target_reg(struct kvm *kvm, u32 val, int irq)
-{
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	struct kvm_vcpu *vcpu;
-	int i, c;
-	unsigned long *bmap;
-	u32 target;
-
-	irq -= VGIC_NR_PRIVATE_IRQS;
-
-	/*
-	 * Pick the LSB in each byte. This ensures we target exactly
-	 * one vcpu per IRQ. If the byte is null, assume we target
-	 * CPU0.
-	 */
-	for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++) {
-		int shift = i * GICD_CPUTARGETS_BITS;
-
-		target = ffs((val >> shift) & 0xffU);
-		target = target ? (target - 1) : 0;
-		dist->irq_spi_cpu[irq + i] = target;
-		kvm_for_each_vcpu(c, vcpu, kvm) {
-			bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]);
-			if (c == target)
-				set_bit(irq + i, bmap);
-			else
-				clear_bit(irq + i, bmap);
-		}
-	}
-}
-
-static bool handle_mmio_target_reg(struct kvm_vcpu *vcpu,
-				   struct kvm_exit_mmio *mmio,
-				   phys_addr_t offset)
-{
-	u32 reg;
-
-	/* We treat the banked interrupts targets as read-only */
-	if (offset < 32) {
-		u32 roreg;
-
-		roreg = 1 << vcpu->vcpu_id;
-		roreg |= roreg << 8;
-		roreg |= roreg << 16;
-
-		vgic_reg_access(mmio, &roreg, offset,
-				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-		return false;
-	}
-
-	reg = vgic_get_target_reg(vcpu->kvm, offset & ~3U);
-	vgic_reg_access(mmio, &reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
-	if (mmio->is_write) {
-		vgic_set_target_reg(vcpu->kvm, reg, offset & ~3U);
-		vgic_update_state(vcpu->kvm);
-		return true;
-	}
-
-	return false;
-}
-
-static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
-				struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
-	u32 *reg;
-
-	reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
-				  vcpu->vcpu_id, offset >> 1);
-
-	return vgic_handle_cfg_reg(reg, mmio, offset);
-}
-
-static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu,
-				struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
-	u32 reg;
-
-	vgic_reg_access(mmio, &reg, offset,
-			ACCESS_READ_RAZ | ACCESS_WRITE_VALUE);
-	if (mmio->is_write) {
-		vgic_dispatch_sgi(vcpu, reg);
-		vgic_update_state(vcpu->kvm);
-		return true;
-	}
-
-	return false;
-}
-
-/* Handle reads of GICD_CPENDSGIRn and GICD_SPENDSGIRn */
-static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
-					struct kvm_exit_mmio *mmio,
-					phys_addr_t offset)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	int sgi;
-	int min_sgi = (offset & ~0x3);
-	int max_sgi = min_sgi + 3;
-	int vcpu_id = vcpu->vcpu_id;
-	u32 reg = 0;
-
-	/* Copy source SGIs from distributor side */
-	for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
-		u8 sources = *vgic_get_sgi_sources(dist, vcpu_id, sgi);
-
-		reg |= ((u32)sources) << (8 * (sgi - min_sgi));
-	}
-
-	mmio_data_write(mmio, ~0, reg);
-	return false;
-}
-
-static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
-					 struct kvm_exit_mmio *mmio,
-					 phys_addr_t offset, bool set)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	int sgi;
-	int min_sgi = (offset & ~0x3);
-	int max_sgi = min_sgi + 3;
-	int vcpu_id = vcpu->vcpu_id;
-	u32 reg;
-	bool updated = false;
-
-	reg = mmio_data_read(mmio, ~0);
-
-	/* Clear pending SGIs on the distributor */
-	for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
-		u8 mask = reg >> (8 * (sgi - min_sgi));
-		u8 *src = vgic_get_sgi_sources(dist, vcpu_id, sgi);
-
-		if (set) {
-			if ((*src & mask) != mask)
-				updated = true;
-			*src |= mask;
-		} else {
-			if (*src & mask)
-				updated = true;
-			*src &= ~mask;
-		}
-	}
-
-	if (updated)
-		vgic_update_state(vcpu->kvm);
-
-	return updated;
-}
-
-static bool handle_mmio_sgi_set(struct kvm_vcpu *vcpu,
-				struct kvm_exit_mmio *mmio,
-				phys_addr_t offset)
-{
-	if (!mmio->is_write)
-		return read_set_clear_sgi_pend_reg(vcpu, mmio, offset);
-	else
-		return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, true);
-}
-
-static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
-				  struct kvm_exit_mmio *mmio,
-				  phys_addr_t offset)
-{
-	if (!mmio->is_write)
-		return read_set_clear_sgi_pend_reg(vcpu, mmio, offset);
-	else
-		return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, false);
-}
-
-static const struct vgic_io_range vgic_dist_ranges[] = {
-	{
-		.base		= GIC_DIST_SOFTINT,
-		.len		= 4,
-		.handle_mmio	= handle_mmio_sgi_reg,
-	},
-	{
-		.base		= GIC_DIST_CTRL,
-		.len		= 12,
-		.bits_per_irq	= 0,
-		.handle_mmio	= handle_mmio_misc,
-	},
-	{
-		.base		= GIC_DIST_IGROUP,
-		.len		= VGIC_MAX_IRQS / 8,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		.base		= GIC_DIST_ENABLE_SET,
-		.len		= VGIC_MAX_IRQS / 8,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_enable_reg,
-	},
-	{
-		.base		= GIC_DIST_ENABLE_CLEAR,
-		.len		= VGIC_MAX_IRQS / 8,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_enable_reg,
-	},
-	{
-		.base		= GIC_DIST_PENDING_SET,
-		.len		= VGIC_MAX_IRQS / 8,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_pending_reg,
-	},
-	{
-		.base		= GIC_DIST_PENDING_CLEAR,
-		.len		= VGIC_MAX_IRQS / 8,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_pending_reg,
-	},
-	{
-		.base		= GIC_DIST_ACTIVE_SET,
-		.len		= VGIC_MAX_IRQS / 8,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_active_reg,
-	},
-	{
-		.base		= GIC_DIST_ACTIVE_CLEAR,
-		.len		= VGIC_MAX_IRQS / 8,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_active_reg,
-	},
-	{
-		.base		= GIC_DIST_PRI,
-		.len		= VGIC_MAX_IRQS,
-		.bits_per_irq	= 8,
-		.handle_mmio	= handle_mmio_priority_reg,
-	},
-	{
-		.base		= GIC_DIST_TARGET,
-		.len		= VGIC_MAX_IRQS,
-		.bits_per_irq	= 8,
-		.handle_mmio	= handle_mmio_target_reg,
-	},
-	{
-		.base		= GIC_DIST_CONFIG,
-		.len		= VGIC_MAX_IRQS / 4,
-		.bits_per_irq	= 2,
-		.handle_mmio	= handle_mmio_cfg_reg,
-	},
-	{
-		.base		= GIC_DIST_SGI_PENDING_CLEAR,
-		.len		= VGIC_NR_SGIS,
-		.handle_mmio	= handle_mmio_sgi_clear,
-	},
-	{
-		.base		= GIC_DIST_SGI_PENDING_SET,
-		.len		= VGIC_NR_SGIS,
-		.handle_mmio	= handle_mmio_sgi_set,
-	},
-	{}
-};
-
-static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
-{
-	struct kvm *kvm = vcpu->kvm;
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	int nrcpus = atomic_read(&kvm->online_vcpus);
-	u8 target_cpus;
-	int sgi, mode, c, vcpu_id;
-
-	vcpu_id = vcpu->vcpu_id;
-
-	sgi = reg & 0xf;
-	target_cpus = (reg >> 16) & 0xff;
-	mode = (reg >> 24) & 3;
-
-	switch (mode) {
-	case 0:
-		if (!target_cpus)
-			return;
-		break;
-
-	case 1:
-		target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff;
-		break;
-
-	case 2:
-		target_cpus = 1 << vcpu_id;
-		break;
-	}
-
-	kvm_for_each_vcpu(c, vcpu, kvm) {
-		if (target_cpus & 1) {
-			/* Flag the SGI as pending */
-			vgic_dist_irq_set_pending(vcpu, sgi);
-			*vgic_get_sgi_sources(dist, c, sgi) |= 1 << vcpu_id;
-			kvm_debug("SGI%d from CPU%d to CPU%d\n",
-				  sgi, vcpu_id, c);
-		}
-
-		target_cpus >>= 1;
-	}
-}
-
-static bool vgic_v2_queue_sgi(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	unsigned long sources;
-	int vcpu_id = vcpu->vcpu_id;
-	int c;
-
-	sources = *vgic_get_sgi_sources(dist, vcpu_id, irq);
-
-	for_each_set_bit(c, &sources, dist->nr_cpus) {
-		if (vgic_queue_irq(vcpu, c, irq))
-			clear_bit(c, &sources);
-	}
-
-	*vgic_get_sgi_sources(dist, vcpu_id, irq) = sources;
-
-	/*
-	 * If the sources bitmap has been cleared it means that we
-	 * could queue all the SGIs onto link registers (see the
-	 * clear_bit above), and therefore we are done with them in
-	 * our emulated gic and can get rid of them.
-	 */
-	if (!sources) {
-		vgic_dist_irq_clear_pending(vcpu, irq);
-		vgic_cpu_irq_clear(vcpu, irq);
-		return true;
-	}
-
-	return false;
-}
-
-/**
- * kvm_vgic_map_resources - Configure global VGIC state before running any VCPUs
- * @kvm: pointer to the kvm struct
- *
- * Map the virtual CPU interface into the VM before running any VCPUs.  We
- * can't do this at creation time, because user space must first set the
- * virtual CPU interface address in the guest physical address space.
- */
-static int vgic_v2_map_resources(struct kvm *kvm,
-				 const struct vgic_params *params)
-{
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	int ret = 0;
-
-	if (!irqchip_in_kernel(kvm))
-		return 0;
-
-	mutex_lock(&kvm->lock);
-
-	if (vgic_ready(kvm))
-		goto out;
-
-	if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
-	    IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) {
-		kvm_err("Need to set vgic cpu and dist addresses first\n");
-		ret = -ENXIO;
-		goto out;
-	}
-
-	vgic_register_kvm_io_dev(kvm, dist->vgic_dist_base,
-				 KVM_VGIC_V2_DIST_SIZE,
-				 vgic_dist_ranges, -1, &dist->dist_iodev);
-
-	/*
-	 * Initialize the vgic if this hasn't already been done on demand by
-	 * accessing the vgic state from userspace.
-	 */
-	ret = vgic_init(kvm);
-	if (ret) {
-		kvm_err("Unable to allocate maps\n");
-		goto out_unregister;
-	}
-
-	ret = kvm_phys_addr_ioremap(kvm, dist->vgic_cpu_base,
-				    params->vcpu_base, KVM_VGIC_V2_CPU_SIZE,
-				    true);
-	if (ret) {
-		kvm_err("Unable to remap VGIC CPU to VCPU\n");
-		goto out_unregister;
-	}
-
-	dist->ready = true;
-	goto out;
-
-out_unregister:
-	kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dist->dist_iodev.dev);
-
-out:
-	if (ret)
-		kvm_vgic_destroy(kvm);
-	mutex_unlock(&kvm->lock);
-	return ret;
-}
-
-static void vgic_v2_add_sgi_source(struct kvm_vcpu *vcpu, int irq, int source)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	*vgic_get_sgi_sources(dist, vcpu->vcpu_id, irq) |= 1 << source;
-}
-
-static int vgic_v2_init_model(struct kvm *kvm)
-{
-	int i;
-
-	for (i = VGIC_NR_PRIVATE_IRQS; i < kvm->arch.vgic.nr_irqs; i += 4)
-		vgic_set_target_reg(kvm, 0, i);
-
-	return 0;
-}
-
-void vgic_v2_init_emulation(struct kvm *kvm)
-{
-	struct vgic_dist *dist = &kvm->arch.vgic;
-
-	dist->vm_ops.queue_sgi = vgic_v2_queue_sgi;
-	dist->vm_ops.add_sgi_source = vgic_v2_add_sgi_source;
-	dist->vm_ops.init_model = vgic_v2_init_model;
-	dist->vm_ops.map_resources = vgic_v2_map_resources;
-
-	kvm->arch.max_vcpus = VGIC_V2_MAX_CPUS;
-}
-
-static bool handle_cpu_mmio_misc(struct kvm_vcpu *vcpu,
-				 struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
-	bool updated = false;
-	struct vgic_vmcr vmcr;
-	u32 *vmcr_field;
-	u32 reg;
-
-	vgic_get_vmcr(vcpu, &vmcr);
-
-	switch (offset & ~0x3) {
-	case GIC_CPU_CTRL:
-		vmcr_field = &vmcr.ctlr;
-		break;
-	case GIC_CPU_PRIMASK:
-		vmcr_field = &vmcr.pmr;
-		break;
-	case GIC_CPU_BINPOINT:
-		vmcr_field = &vmcr.bpr;
-		break;
-	case GIC_CPU_ALIAS_BINPOINT:
-		vmcr_field = &vmcr.abpr;
-		break;
-	default:
-		BUG();
-	}
-
-	if (!mmio->is_write) {
-		reg = *vmcr_field;
-		mmio_data_write(mmio, ~0, reg);
-	} else {
-		reg = mmio_data_read(mmio, ~0);
-		if (reg != *vmcr_field) {
-			*vmcr_field = reg;
-			vgic_set_vmcr(vcpu, &vmcr);
-			updated = true;
-		}
-	}
-	return updated;
-}
-
-static bool handle_mmio_abpr(struct kvm_vcpu *vcpu,
-			     struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
-	return handle_cpu_mmio_misc(vcpu, mmio, GIC_CPU_ALIAS_BINPOINT);
-}
-
-static bool handle_cpu_mmio_ident(struct kvm_vcpu *vcpu,
-				  struct kvm_exit_mmio *mmio,
-				  phys_addr_t offset)
-{
-	u32 reg;
-
-	if (mmio->is_write)
-		return false;
-
-	/* GICC_IIDR */
-	reg = (PRODUCT_ID_KVM << 20) |
-	      (GICC_ARCH_VERSION_V2 << 16) |
-	      (IMPLEMENTER_ARM << 0);
-	mmio_data_write(mmio, ~0, reg);
-	return false;
-}
-
-/*
- * CPU Interface Register accesses - these are not accessed by the VM, but by
- * user space for saving and restoring VGIC state.
- */
-static const struct vgic_io_range vgic_cpu_ranges[] = {
-	{
-		.base		= GIC_CPU_CTRL,
-		.len		= 12,
-		.handle_mmio	= handle_cpu_mmio_misc,
-	},
-	{
-		.base		= GIC_CPU_ALIAS_BINPOINT,
-		.len		= 4,
-		.handle_mmio	= handle_mmio_abpr,
-	},
-	{
-		.base		= GIC_CPU_ACTIVEPRIO,
-		.len		= 16,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		.base		= GIC_CPU_IDENT,
-		.len		= 4,
-		.handle_mmio	= handle_cpu_mmio_ident,
-	},
-};
-
-static int vgic_attr_regs_access(struct kvm_device *dev,
-				 struct kvm_device_attr *attr,
-				 u32 *reg, bool is_write)
-{
-	const struct vgic_io_range *r = NULL, *ranges;
-	phys_addr_t offset;
-	int ret, cpuid, c;
-	struct kvm_vcpu *vcpu, *tmp_vcpu;
-	struct vgic_dist *vgic;
-	struct kvm_exit_mmio mmio;
-	u32 data;
-
-	offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
-	cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >>
-		KVM_DEV_ARM_VGIC_CPUID_SHIFT;
-
-	mutex_lock(&dev->kvm->lock);
-
-	ret = vgic_init(dev->kvm);
-	if (ret)
-		goto out;
-
-	if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	vcpu = kvm_get_vcpu(dev->kvm, cpuid);
-	vgic = &dev->kvm->arch.vgic;
-
-	mmio.len = 4;
-	mmio.is_write = is_write;
-	mmio.data = &data;
-	if (is_write)
-		mmio_data_write(&mmio, ~0, *reg);
-	switch (attr->group) {
-	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
-		mmio.phys_addr = vgic->vgic_dist_base + offset;
-		ranges = vgic_dist_ranges;
-		break;
-	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
-		mmio.phys_addr = vgic->vgic_cpu_base + offset;
-		ranges = vgic_cpu_ranges;
-		break;
-	default:
-		BUG();
-	}
-	r = vgic_find_range(ranges, 4, offset);
-
-	if (unlikely(!r || !r->handle_mmio)) {
-		ret = -ENXIO;
-		goto out;
-	}
-
-
-	spin_lock(&vgic->lock);
-
-	/*
-	 * Ensure that no other VCPU is running by checking the vcpu->cpu
-	 * field.  If no other VPCUs are running we can safely access the VGIC
-	 * state, because even if another VPU is run after this point, that
-	 * VCPU will not touch the vgic state, because it will block on
-	 * getting the vgic->lock in kvm_vgic_sync_hwstate().
-	 */
-	kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm) {
-		if (unlikely(tmp_vcpu->cpu != -1)) {
-			ret = -EBUSY;
-			goto out_vgic_unlock;
-		}
-	}
-
-	/*
-	 * Move all pending IRQs from the LRs on all VCPUs so the pending
-	 * state can be properly represented in the register state accessible
-	 * through this API.
-	 */
-	kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm)
-		vgic_unqueue_irqs(tmp_vcpu);
-
-	offset -= r->base;
-	r->handle_mmio(vcpu, &mmio, offset);
-
-	if (!is_write)
-		*reg = mmio_data_read(&mmio, ~0);
-
-	ret = 0;
-out_vgic_unlock:
-	spin_unlock(&vgic->lock);
-out:
-	mutex_unlock(&dev->kvm->lock);
-	return ret;
-}
-
-static int vgic_v2_create(struct kvm_device *dev, u32 type)
-{
-	return kvm_vgic_create(dev->kvm, type);
-}
-
-static void vgic_v2_destroy(struct kvm_device *dev)
-{
-	kfree(dev);
-}
-
-static int vgic_v2_set_attr(struct kvm_device *dev,
-			    struct kvm_device_attr *attr)
-{
-	int ret;
-
-	ret = vgic_set_common_attr(dev, attr);
-	if (ret != -ENXIO)
-		return ret;
-
-	switch (attr->group) {
-	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
-	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
-		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
-		u32 reg;
-
-		if (get_user(reg, uaddr))
-			return -EFAULT;
-
-		return vgic_attr_regs_access(dev, attr, &reg, true);
-	}
-
-	}
-
-	return -ENXIO;
-}
-
-static int vgic_v2_get_attr(struct kvm_device *dev,
-			    struct kvm_device_attr *attr)
-{
-	int ret;
-
-	ret = vgic_get_common_attr(dev, attr);
-	if (ret != -ENXIO)
-		return ret;
-
-	switch (attr->group) {
-	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
-	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
-		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
-		u32 reg = 0;
-
-		ret = vgic_attr_regs_access(dev, attr, &reg, false);
-		if (ret)
-			return ret;
-		return put_user(reg, uaddr);
-	}
-
-	}
-
-	return -ENXIO;
-}
-
-static int vgic_v2_has_attr(struct kvm_device *dev,
-			    struct kvm_device_attr *attr)
-{
-	phys_addr_t offset;
-
-	switch (attr->group) {
-	case KVM_DEV_ARM_VGIC_GRP_ADDR:
-		switch (attr->attr) {
-		case KVM_VGIC_V2_ADDR_TYPE_DIST:
-		case KVM_VGIC_V2_ADDR_TYPE_CPU:
-			return 0;
-		}
-		break;
-	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
-		offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
-		return vgic_has_attr_regs(vgic_dist_ranges, offset);
-	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
-		offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
-		return vgic_has_attr_regs(vgic_cpu_ranges, offset);
-	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
-		return 0;
-	case KVM_DEV_ARM_VGIC_GRP_CTRL:
-		switch (attr->attr) {
-		case KVM_DEV_ARM_VGIC_CTRL_INIT:
-			return 0;
-		}
-	}
-	return -ENXIO;
-}
-
-struct kvm_device_ops kvm_arm_vgic_v2_ops = {
-	.name = "kvm-arm-vgic-v2",
-	.create = vgic_v2_create,
-	.destroy = vgic_v2_destroy,
-	.set_attr = vgic_v2_set_attr,
-	.get_attr = vgic_v2_get_attr,
-	.has_attr = vgic_v2_has_attr,
-};
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
deleted file mode 100644
index 334cd7a89106..000000000000
--- a/virt/kvm/arm/vgic-v2.c
+++ /dev/null
@@ -1,274 +0,0 @@
-/*
- * Copyright (C) 2012,2013 ARM Limited, All Rights Reserved.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/cpu.h>
-#include <linux/kvm.h>
-#include <linux/kvm_host.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-
-#include <linux/irqchip/arm-gic.h>
-
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_mmu.h>
-
-static struct vgic_lr vgic_v2_get_lr(const struct kvm_vcpu *vcpu, int lr)
-{
-	struct vgic_lr lr_desc;
-	u32 val = vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr];
-
-	lr_desc.irq	= val & GICH_LR_VIRTUALID;
-	if (lr_desc.irq <= 15)
-		lr_desc.source	= (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7;
-	else
-		lr_desc.source = 0;
-	lr_desc.state	= 0;
-
-	if (val & GICH_LR_PENDING_BIT)
-		lr_desc.state |= LR_STATE_PENDING;
-	if (val & GICH_LR_ACTIVE_BIT)
-		lr_desc.state |= LR_STATE_ACTIVE;
-	if (val & GICH_LR_EOI)
-		lr_desc.state |= LR_EOI_INT;
-	if (val & GICH_LR_HW) {
-		lr_desc.state |= LR_HW;
-		lr_desc.hwirq = (val & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT;
-	}
-
-	return lr_desc;
-}
-
-static void vgic_v2_set_lr(struct kvm_vcpu *vcpu, int lr,
-			   struct vgic_lr lr_desc)
-{
-	u32 lr_val;
-
-	lr_val = lr_desc.irq;
-
-	if (lr_desc.state & LR_STATE_PENDING)
-		lr_val |= GICH_LR_PENDING_BIT;
-	if (lr_desc.state & LR_STATE_ACTIVE)
-		lr_val |= GICH_LR_ACTIVE_BIT;
-	if (lr_desc.state & LR_EOI_INT)
-		lr_val |= GICH_LR_EOI;
-
-	if (lr_desc.state & LR_HW) {
-		lr_val |= GICH_LR_HW;
-		lr_val |= (u32)lr_desc.hwirq << GICH_LR_PHYSID_CPUID_SHIFT;
-	}
-
-	if (lr_desc.irq < VGIC_NR_SGIS)
-		lr_val |= (lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT);
-
-	vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = lr_val;
-
-	if (!(lr_desc.state & LR_STATE_MASK))
-		vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr);
-	else
-		vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr &= ~(1ULL << lr);
-}
-
-static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr;
-}
-
-static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
-}
-
-static void vgic_v2_clear_eisr(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr = 0;
-}
-
-static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu)
-{
-	u32 misr = vcpu->arch.vgic_cpu.vgic_v2.vgic_misr;
-	u32 ret = 0;
-
-	if (misr & GICH_MISR_EOI)
-		ret |= INT_STATUS_EOI;
-	if (misr & GICH_MISR_U)
-		ret |= INT_STATUS_UNDERFLOW;
-
-	return ret;
-}
-
-static void vgic_v2_enable_underflow(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr |= GICH_HCR_UIE;
-}
-
-static void vgic_v2_disable_underflow(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr &= ~GICH_HCR_UIE;
-}
-
-static void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
-{
-	u32 vmcr = vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr;
-
-	vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >> GICH_VMCR_CTRL_SHIFT;
-	vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >> GICH_VMCR_ALIAS_BINPOINT_SHIFT;
-	vmcrp->bpr  = (vmcr & GICH_VMCR_BINPOINT_MASK) >> GICH_VMCR_BINPOINT_SHIFT;
-	vmcrp->pmr  = (vmcr & GICH_VMCR_PRIMASK_MASK) >> GICH_VMCR_PRIMASK_SHIFT;
-}
-
-static void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
-{
-	u32 vmcr;
-
-	vmcr  = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK;
-	vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) & GICH_VMCR_ALIAS_BINPOINT_MASK;
-	vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) & GICH_VMCR_BINPOINT_MASK;
-	vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK;
-
-	vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
-}
-
-static void vgic_v2_enable(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * By forcing VMCR to zero, the GIC will restore the binary
-	 * points to their reset values. Anything else resets to zero
-	 * anyway.
-	 */
-	vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = 0;
-	vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr = ~0;
-
-	/* Get the show on the road... */
-	vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr = GICH_HCR_EN;
-}
-
-static const struct vgic_ops vgic_v2_ops = {
-	.get_lr			= vgic_v2_get_lr,
-	.set_lr			= vgic_v2_set_lr,
-	.get_elrsr		= vgic_v2_get_elrsr,
-	.get_eisr		= vgic_v2_get_eisr,
-	.clear_eisr		= vgic_v2_clear_eisr,
-	.get_interrupt_status	= vgic_v2_get_interrupt_status,
-	.enable_underflow	= vgic_v2_enable_underflow,
-	.disable_underflow	= vgic_v2_disable_underflow,
-	.get_vmcr		= vgic_v2_get_vmcr,
-	.set_vmcr		= vgic_v2_set_vmcr,
-	.enable			= vgic_v2_enable,
-};
-
-struct vgic_params __section(.hyp.text) vgic_v2_params;
-
-static void vgic_cpu_init_lrs(void *params)
-{
-	struct vgic_params *vgic = params;
-	int i;
-
-	for (i = 0; i < vgic->nr_lr; i++)
-		writel_relaxed(0, vgic->vctrl_base + GICH_LR0 + (i * 4));
-}
-
-/**
- * vgic_v2_probe - probe for a GICv2 compatible interrupt controller
- * @gic_kvm_info:	pointer to the GIC description
- * @ops:		address of a pointer to the GICv2 operations
- * @params:		address of a pointer to HW-specific parameters
- *
- * Returns 0 if a GICv2 has been found, with the low level operations
- * in *ops and the HW parameters in *params. Returns an error code
- * otherwise.
- */
-int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info,
-		   const struct vgic_ops **ops,
-		   const struct vgic_params **params)
-{
-	int ret;
-	struct vgic_params *vgic = &vgic_v2_params;
-	const struct resource *vctrl_res = &gic_kvm_info->vctrl;
-	const struct resource *vcpu_res = &gic_kvm_info->vcpu;
-
-	memset(vgic, 0, sizeof(*vgic));
-
-	if (!gic_kvm_info->maint_irq) {
-		kvm_err("error getting vgic maintenance irq\n");
-		ret = -ENXIO;
-		goto out;
-	}
-	vgic->maint_irq = gic_kvm_info->maint_irq;
-
-	if (!gic_kvm_info->vctrl.start) {
-		kvm_err("GICH not present in the firmware table\n");
-		ret = -ENXIO;
-		goto out;
-	}
-
-	vgic->vctrl_base = ioremap(gic_kvm_info->vctrl.start,
-				   resource_size(&gic_kvm_info->vctrl));
-	if (!vgic->vctrl_base) {
-		kvm_err("Cannot ioremap GICH\n");
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	vgic->nr_lr = readl_relaxed(vgic->vctrl_base + GICH_VTR);
-	vgic->nr_lr = (vgic->nr_lr & 0x3f) + 1;
-
-	ret = create_hyp_io_mappings(vgic->vctrl_base,
-				     vgic->vctrl_base + resource_size(vctrl_res),
-				     vctrl_res->start);
-	if (ret) {
-		kvm_err("Cannot map VCTRL into hyp\n");
-		goto out_unmap;
-	}
-
-	if (!PAGE_ALIGNED(vcpu_res->start)) {
-		kvm_err("GICV physical address 0x%llx not page aligned\n",
-			(unsigned long long)vcpu_res->start);
-		ret = -ENXIO;
-		goto out_unmap;
-	}
-
-	if (!PAGE_ALIGNED(resource_size(vcpu_res))) {
-		kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
-			(unsigned long long)resource_size(vcpu_res),
-			PAGE_SIZE);
-		ret = -ENXIO;
-		goto out_unmap;
-	}
-
-	vgic->can_emulate_gicv2 = true;
-	kvm_register_device_ops(&kvm_arm_vgic_v2_ops, KVM_DEV_TYPE_ARM_VGIC_V2);
-
-	vgic->vcpu_base = vcpu_res->start;
-
-	kvm_info("GICH base=0x%llx, GICV base=0x%llx, IRQ=%d\n",
-		 gic_kvm_info->vctrl.start, vgic->vcpu_base, vgic->maint_irq);
-
-	vgic->type = VGIC_V2;
-	vgic->max_gic_vcpus = VGIC_V2_MAX_CPUS;
-
-	on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
-
-	*ops = &vgic_v2_ops;
-	*params = vgic;
-	goto out;
-
-out_unmap:
-	iounmap(vgic->vctrl_base);
-out:
-	return ret;
-}
diff --git a/virt/kvm/arm/vgic-v3-emul.c b/virt/kvm/arm/vgic-v3-emul.c
deleted file mode 100644
index e661e7fb9d91..000000000000
--- a/virt/kvm/arm/vgic-v3-emul.c
+++ /dev/null
@@ -1,1074 +0,0 @@
-/*
- * GICv3 distributor and redistributor emulation
- *
- * GICv3 emulation is currently only supported on a GICv3 host (because
- * we rely on the hardware's CPU interface virtualization support), but
- * supports both hardware with or without the optional GICv2 backwards
- * compatibility features.
- *
- * Limitations of the emulation:
- * (RAZ/WI: read as zero, write ignore, RAO/WI: read as one, write ignore)
- * - We do not support LPIs (yet). TYPER.LPIS is reported as 0 and is RAZ/WI.
- * - We do not support the message based interrupts (MBIs) triggered by
- *   writes to the GICD_{SET,CLR}SPI_* registers. TYPER.MBIS is reported as 0.
- * - We do not support the (optional) backwards compatibility feature.
- *   GICD_CTLR.ARE resets to 1 and is RAO/WI. If the _host_ GIC supports
- *   the compatiblity feature, you can use a GICv2 in the guest, though.
- * - We only support a single security state. GICD_CTLR.DS is 1 and is RAO/WI.
- * - Priorities are not emulated (same as the GICv2 emulation). Linux
- *   as a guest is fine with this, because it does not use priorities.
- * - We only support Group1 interrupts. Again Linux uses only those.
- *
- * Copyright (C) 2014 ARM Ltd.
- * Author: Andre Przywara <andre.przywara@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/cpu.h>
-#include <linux/kvm.h>
-#include <linux/kvm_host.h>
-#include <linux/interrupt.h>
-
-#include <linux/irqchip/arm-gic-v3.h>
-#include <kvm/arm_vgic.h>
-
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_mmu.h>
-
-#include "vgic.h"
-
-static bool handle_mmio_rao_wi(struct kvm_vcpu *vcpu,
-			       struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
-	u32 reg = 0xffffffff;
-
-	vgic_reg_access(mmio, &reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-
-	return false;
-}
-
-static bool handle_mmio_ctlr(struct kvm_vcpu *vcpu,
-			     struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
-	u32 reg = 0;
-
-	/*
-	 * Force ARE and DS to 1, the guest cannot change this.
-	 * For the time being we only support Group1 interrupts.
-	 */
-	if (vcpu->kvm->arch.vgic.enabled)
-		reg = GICD_CTLR_ENABLE_SS_G1;
-	reg |= GICD_CTLR_ARE_NS | GICD_CTLR_DS;
-
-	vgic_reg_access(mmio, &reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
-	if (mmio->is_write) {
-		vcpu->kvm->arch.vgic.enabled = !!(reg & GICD_CTLR_ENABLE_SS_G1);
-		vgic_update_state(vcpu->kvm);
-		return true;
-	}
-	return false;
-}
-
-/*
- * As this implementation does not provide compatibility
- * with GICv2 (ARE==1), we report zero CPUs in bits [5..7].
- * Also LPIs and MBIs are not supported, so we set the respective bits to 0.
- * Also we report at most 2**10=1024 interrupt IDs (to match 1024 SPIs).
- */
-#define INTERRUPT_ID_BITS 10
-static bool handle_mmio_typer(struct kvm_vcpu *vcpu,
-			      struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
-	u32 reg;
-
-	reg = (min(vcpu->kvm->arch.vgic.nr_irqs, 1024) >> 5) - 1;
-
-	reg |= (INTERRUPT_ID_BITS - 1) << 19;
-
-	vgic_reg_access(mmio, &reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-
-	return false;
-}
-
-static bool handle_mmio_iidr(struct kvm_vcpu *vcpu,
-			     struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
-	u32 reg;
-
-	reg = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
-	vgic_reg_access(mmio, &reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-
-	return false;
-}
-
-static bool handle_mmio_set_enable_reg_dist(struct kvm_vcpu *vcpu,
-					    struct kvm_exit_mmio *mmio,
-					    phys_addr_t offset)
-{
-	if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
-		return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
-					      vcpu->vcpu_id,
-					      ACCESS_WRITE_SETBIT);
-
-	vgic_reg_access(mmio, NULL, offset,
-			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-static bool handle_mmio_clear_enable_reg_dist(struct kvm_vcpu *vcpu,
-					      struct kvm_exit_mmio *mmio,
-					      phys_addr_t offset)
-{
-	if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
-		return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
-					      vcpu->vcpu_id,
-					      ACCESS_WRITE_CLEARBIT);
-
-	vgic_reg_access(mmio, NULL, offset,
-			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-static bool handle_mmio_set_pending_reg_dist(struct kvm_vcpu *vcpu,
-					     struct kvm_exit_mmio *mmio,
-					     phys_addr_t offset)
-{
-	if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
-		return vgic_handle_set_pending_reg(vcpu->kvm, mmio, offset,
-						   vcpu->vcpu_id);
-
-	vgic_reg_access(mmio, NULL, offset,
-			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-static bool handle_mmio_clear_pending_reg_dist(struct kvm_vcpu *vcpu,
-					       struct kvm_exit_mmio *mmio,
-					       phys_addr_t offset)
-{
-	if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
-		return vgic_handle_clear_pending_reg(vcpu->kvm, mmio, offset,
-						     vcpu->vcpu_id);
-
-	vgic_reg_access(mmio, NULL, offset,
-			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-static bool handle_mmio_set_active_reg_dist(struct kvm_vcpu *vcpu,
-					    struct kvm_exit_mmio *mmio,
-					    phys_addr_t offset)
-{
-	if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
-		return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset,
-						   vcpu->vcpu_id);
-
-	vgic_reg_access(mmio, NULL, offset,
-			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-static bool handle_mmio_clear_active_reg_dist(struct kvm_vcpu *vcpu,
-					      struct kvm_exit_mmio *mmio,
-					      phys_addr_t offset)
-{
-	if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
-		return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset,
-						    vcpu->vcpu_id);
-
-	vgic_reg_access(mmio, NULL, offset,
-			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-static bool handle_mmio_priority_reg_dist(struct kvm_vcpu *vcpu,
-					  struct kvm_exit_mmio *mmio,
-					  phys_addr_t offset)
-{
-	u32 *reg;
-
-	if (unlikely(offset < VGIC_NR_PRIVATE_IRQS)) {
-		vgic_reg_access(mmio, NULL, offset,
-				ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-		return false;
-	}
-
-	reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority,
-				   vcpu->vcpu_id, offset);
-	vgic_reg_access(mmio, reg, offset,
-		ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
-	return false;
-}
-
-static bool handle_mmio_cfg_reg_dist(struct kvm_vcpu *vcpu,
-				     struct kvm_exit_mmio *mmio,
-				     phys_addr_t offset)
-{
-	u32 *reg;
-
-	if (unlikely(offset < VGIC_NR_PRIVATE_IRQS / 4)) {
-		vgic_reg_access(mmio, NULL, offset,
-				ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-		return false;
-	}
-
-	reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
-				  vcpu->vcpu_id, offset >> 1);
-
-	return vgic_handle_cfg_reg(reg, mmio, offset);
-}
-
-/*
- * We use a compressed version of the MPIDR (all 32 bits in one 32-bit word)
- * when we store the target MPIDR written by the guest.
- */
-static u32 compress_mpidr(unsigned long mpidr)
-{
-	u32 ret;
-
-	ret = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-	ret |= MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8;
-	ret |= MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16;
-	ret |= MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24;
-
-	return ret;
-}
-
-static unsigned long uncompress_mpidr(u32 value)
-{
-	unsigned long mpidr;
-
-	mpidr  = ((value >>  0) & 0xFF) << MPIDR_LEVEL_SHIFT(0);
-	mpidr |= ((value >>  8) & 0xFF) << MPIDR_LEVEL_SHIFT(1);
-	mpidr |= ((value >> 16) & 0xFF) << MPIDR_LEVEL_SHIFT(2);
-	mpidr |= (u64)((value >> 24) & 0xFF) << MPIDR_LEVEL_SHIFT(3);
-
-	return mpidr;
-}
-
-/*
- * Lookup the given MPIDR value to get the vcpu_id (if there is one)
- * and store that in the irq_spi_cpu[] array.
- * This limits the number of VCPUs to 255 for now, extending the data
- * type (or storing kvm_vcpu pointers) should lift the limit.
- * Store the original MPIDR value in an extra array to support read-as-written.
- * Unallocated MPIDRs are translated to a special value and caught
- * before any array accesses.
- */
-static bool handle_mmio_route_reg(struct kvm_vcpu *vcpu,
-				  struct kvm_exit_mmio *mmio,
-				  phys_addr_t offset)
-{
-	struct kvm *kvm = vcpu->kvm;
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	int spi;
-	u32 reg;
-	int vcpu_id;
-	unsigned long *bmap, mpidr;
-
-	/*
-	 * The upper 32 bits of each 64 bit register are zero,
-	 * as we don't support Aff3.
-	 */
-	if ((offset & 4)) {
-		vgic_reg_access(mmio, NULL, offset,
-				ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-		return false;
-	}
-
-	/* This region only covers SPIs, so no handling of private IRQs here. */
-	spi = offset / 8;
-
-	/* get the stored MPIDR for this IRQ */
-	mpidr = uncompress_mpidr(dist->irq_spi_mpidr[spi]);
-	reg = mpidr;
-
-	vgic_reg_access(mmio, &reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
-
-	if (!mmio->is_write)
-		return false;
-
-	/*
-	 * Now clear the currently assigned vCPU from the map, making room
-	 * for the new one to be written below
-	 */
-	vcpu = kvm_mpidr_to_vcpu(kvm, mpidr);
-	if (likely(vcpu)) {
-		vcpu_id = vcpu->vcpu_id;
-		bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]);
-		__clear_bit(spi, bmap);
-	}
-
-	dist->irq_spi_mpidr[spi] = compress_mpidr(reg);
-	vcpu = kvm_mpidr_to_vcpu(kvm, reg & MPIDR_HWID_BITMASK);
-
-	/*
-	 * The spec says that non-existent MPIDR values should not be
-	 * forwarded to any existent (v)CPU, but should be able to become
-	 * pending anyway. We simply keep the irq_spi_target[] array empty, so
-	 * the interrupt will never be injected.
-	 * irq_spi_cpu[irq] gets a magic value in this case.
-	 */
-	if (likely(vcpu)) {
-		vcpu_id = vcpu->vcpu_id;
-		dist->irq_spi_cpu[spi] = vcpu_id;
-		bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]);
-		__set_bit(spi, bmap);
-	} else {
-		dist->irq_spi_cpu[spi] = VCPU_NOT_ALLOCATED;
-	}
-
-	vgic_update_state(kvm);
-
-	return true;
-}
-
-/*
- * We should be careful about promising too much when a guest reads
- * this register. Don't claim to be like any hardware implementation,
- * but just report the GIC as version 3 - which is what a Linux guest
- * would check.
- */
-static bool handle_mmio_idregs(struct kvm_vcpu *vcpu,
-			       struct kvm_exit_mmio *mmio,
-			       phys_addr_t offset)
-{
-	u32 reg = 0;
-
-	switch (offset + GICD_IDREGS) {
-	case GICD_PIDR2:
-		reg = 0x3b;
-		break;
-	}
-
-	vgic_reg_access(mmio, &reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-
-	return false;
-}
-
-static const struct vgic_io_range vgic_v3_dist_ranges[] = {
-	{
-		.base           = GICD_CTLR,
-		.len            = 0x04,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_ctlr,
-	},
-	{
-		.base           = GICD_TYPER,
-		.len            = 0x04,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_typer,
-	},
-	{
-		.base           = GICD_IIDR,
-		.len            = 0x04,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_iidr,
-	},
-	{
-		/* this register is optional, it is RAZ/WI if not implemented */
-		.base           = GICD_STATUSR,
-		.len            = 0x04,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_raz_wi,
-	},
-	{
-		/* this write only register is WI when TYPER.MBIS=0 */
-		.base		= GICD_SETSPI_NSR,
-		.len		= 0x04,
-		.bits_per_irq	= 0,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		/* this write only register is WI when TYPER.MBIS=0 */
-		.base		= GICD_CLRSPI_NSR,
-		.len		= 0x04,
-		.bits_per_irq	= 0,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		/* this is RAZ/WI when DS=1 */
-		.base		= GICD_SETSPI_SR,
-		.len		= 0x04,
-		.bits_per_irq	= 0,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		/* this is RAZ/WI when DS=1 */
-		.base		= GICD_CLRSPI_SR,
-		.len		= 0x04,
-		.bits_per_irq	= 0,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		.base		= GICD_IGROUPR,
-		.len		= 0x80,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_rao_wi,
-	},
-	{
-		.base		= GICD_ISENABLER,
-		.len		= 0x80,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_enable_reg_dist,
-	},
-	{
-		.base		= GICD_ICENABLER,
-		.len		= 0x80,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_enable_reg_dist,
-	},
-	{
-		.base		= GICD_ISPENDR,
-		.len		= 0x80,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_pending_reg_dist,
-	},
-	{
-		.base		= GICD_ICPENDR,
-		.len		= 0x80,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_pending_reg_dist,
-	},
-	{
-		.base		= GICD_ISACTIVER,
-		.len		= 0x80,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_active_reg_dist,
-	},
-	{
-		.base		= GICD_ICACTIVER,
-		.len		= 0x80,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_active_reg_dist,
-	},
-	{
-		.base		= GICD_IPRIORITYR,
-		.len		= 0x400,
-		.bits_per_irq	= 8,
-		.handle_mmio	= handle_mmio_priority_reg_dist,
-	},
-	{
-		/* TARGETSRn is RES0 when ARE=1 */
-		.base		= GICD_ITARGETSR,
-		.len		= 0x400,
-		.bits_per_irq	= 8,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		.base		= GICD_ICFGR,
-		.len		= 0x100,
-		.bits_per_irq	= 2,
-		.handle_mmio	= handle_mmio_cfg_reg_dist,
-	},
-	{
-		/* this is RAZ/WI when DS=1 */
-		.base		= GICD_IGRPMODR,
-		.len		= 0x80,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		/* this is RAZ/WI when DS=1 */
-		.base		= GICD_NSACR,
-		.len		= 0x100,
-		.bits_per_irq	= 2,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		/* this is RAZ/WI when ARE=1 */
-		.base		= GICD_SGIR,
-		.len		= 0x04,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		/* this is RAZ/WI when ARE=1 */
-		.base		= GICD_CPENDSGIR,
-		.len		= 0x10,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		/* this is RAZ/WI when ARE=1 */
-		.base           = GICD_SPENDSGIR,
-		.len            = 0x10,
-		.handle_mmio    = handle_mmio_raz_wi,
-	},
-	{
-		.base		= GICD_IROUTER + 0x100,
-		.len		= 0x1ee0,
-		.bits_per_irq	= 64,
-		.handle_mmio	= handle_mmio_route_reg,
-	},
-	{
-		.base           = GICD_IDREGS,
-		.len            = 0x30,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_idregs,
-	},
-	{},
-};
-
-static bool handle_mmio_ctlr_redist(struct kvm_vcpu *vcpu,
-				    struct kvm_exit_mmio *mmio,
-				    phys_addr_t offset)
-{
-	/* since we don't support LPIs, this register is zero for now */
-	vgic_reg_access(mmio, NULL, offset,
-			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-static bool handle_mmio_typer_redist(struct kvm_vcpu *vcpu,
-				     struct kvm_exit_mmio *mmio,
-				     phys_addr_t offset)
-{
-	u32 reg;
-	u64 mpidr;
-	struct kvm_vcpu *redist_vcpu = mmio->private;
-	int target_vcpu_id = redist_vcpu->vcpu_id;
-
-	/* the upper 32 bits contain the affinity value */
-	if ((offset & ~3) == 4) {
-		mpidr = kvm_vcpu_get_mpidr_aff(redist_vcpu);
-		reg = compress_mpidr(mpidr);
-
-		vgic_reg_access(mmio, &reg, offset,
-				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-		return false;
-	}
-
-	reg = redist_vcpu->vcpu_id << 8;
-	if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1)
-		reg |= GICR_TYPER_LAST;
-	vgic_reg_access(mmio, &reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-static bool handle_mmio_set_enable_reg_redist(struct kvm_vcpu *vcpu,
-					      struct kvm_exit_mmio *mmio,
-					      phys_addr_t offset)
-{
-	struct kvm_vcpu *redist_vcpu = mmio->private;
-
-	return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
-				      redist_vcpu->vcpu_id,
-				      ACCESS_WRITE_SETBIT);
-}
-
-static bool handle_mmio_clear_enable_reg_redist(struct kvm_vcpu *vcpu,
-						struct kvm_exit_mmio *mmio,
-						phys_addr_t offset)
-{
-	struct kvm_vcpu *redist_vcpu = mmio->private;
-
-	return vgic_handle_enable_reg(vcpu->kvm, mmio, offset,
-				      redist_vcpu->vcpu_id,
-				      ACCESS_WRITE_CLEARBIT);
-}
-
-static bool handle_mmio_set_active_reg_redist(struct kvm_vcpu *vcpu,
-					      struct kvm_exit_mmio *mmio,
-					      phys_addr_t offset)
-{
-	struct kvm_vcpu *redist_vcpu = mmio->private;
-
-	return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset,
-					  redist_vcpu->vcpu_id);
-}
-
-static bool handle_mmio_clear_active_reg_redist(struct kvm_vcpu *vcpu,
-						struct kvm_exit_mmio *mmio,
-						phys_addr_t offset)
-{
-	struct kvm_vcpu *redist_vcpu = mmio->private;
-
-	return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset,
-					     redist_vcpu->vcpu_id);
-}
-
-static bool handle_mmio_set_pending_reg_redist(struct kvm_vcpu *vcpu,
-					       struct kvm_exit_mmio *mmio,
-					       phys_addr_t offset)
-{
-	struct kvm_vcpu *redist_vcpu = mmio->private;
-
-	return vgic_handle_set_pending_reg(vcpu->kvm, mmio, offset,
-					   redist_vcpu->vcpu_id);
-}
-
-static bool handle_mmio_clear_pending_reg_redist(struct kvm_vcpu *vcpu,
-						 struct kvm_exit_mmio *mmio,
-						 phys_addr_t offset)
-{
-	struct kvm_vcpu *redist_vcpu = mmio->private;
-
-	return vgic_handle_clear_pending_reg(vcpu->kvm, mmio, offset,
-					     redist_vcpu->vcpu_id);
-}
-
-static bool handle_mmio_priority_reg_redist(struct kvm_vcpu *vcpu,
-					    struct kvm_exit_mmio *mmio,
-					    phys_addr_t offset)
-{
-	struct kvm_vcpu *redist_vcpu = mmio->private;
-	u32 *reg;
-
-	reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority,
-				   redist_vcpu->vcpu_id, offset);
-	vgic_reg_access(mmio, reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
-	return false;
-}
-
-static bool handle_mmio_cfg_reg_redist(struct kvm_vcpu *vcpu,
-				       struct kvm_exit_mmio *mmio,
-				       phys_addr_t offset)
-{
-	struct kvm_vcpu *redist_vcpu = mmio->private;
-
-	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
-				       redist_vcpu->vcpu_id, offset >> 1);
-
-	return vgic_handle_cfg_reg(reg, mmio, offset);
-}
-
-#define SGI_base(x) ((x) + SZ_64K)
-
-static const struct vgic_io_range vgic_redist_ranges[] = {
-	{
-		.base           = GICR_CTLR,
-		.len            = 0x04,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_ctlr_redist,
-	},
-	{
-		.base           = GICR_TYPER,
-		.len            = 0x08,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_typer_redist,
-	},
-	{
-		.base           = GICR_IIDR,
-		.len            = 0x04,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_iidr,
-	},
-	{
-		.base           = GICR_WAKER,
-		.len            = 0x04,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_raz_wi,
-	},
-	{
-		.base           = GICR_IDREGS,
-		.len            = 0x30,
-		.bits_per_irq   = 0,
-		.handle_mmio    = handle_mmio_idregs,
-	},
-	{
-		.base		= SGI_base(GICR_IGROUPR0),
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_rao_wi,
-	},
-	{
-		.base		= SGI_base(GICR_ISENABLER0),
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_enable_reg_redist,
-	},
-	{
-		.base		= SGI_base(GICR_ICENABLER0),
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_enable_reg_redist,
-	},
-	{
-		.base		= SGI_base(GICR_ISPENDR0),
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_pending_reg_redist,
-	},
-	{
-		.base		= SGI_base(GICR_ICPENDR0),
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_pending_reg_redist,
-	},
-	{
-		.base		= SGI_base(GICR_ISACTIVER0),
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_set_active_reg_redist,
-	},
-	{
-		.base		= SGI_base(GICR_ICACTIVER0),
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_clear_active_reg_redist,
-	},
-	{
-		.base		= SGI_base(GICR_IPRIORITYR0),
-		.len		= 0x20,
-		.bits_per_irq	= 8,
-		.handle_mmio	= handle_mmio_priority_reg_redist,
-	},
-	{
-		.base		= SGI_base(GICR_ICFGR0),
-		.len		= 0x08,
-		.bits_per_irq	= 2,
-		.handle_mmio	= handle_mmio_cfg_reg_redist,
-	},
-	{
-		.base		= SGI_base(GICR_IGRPMODR0),
-		.len		= 0x04,
-		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{
-		.base		= SGI_base(GICR_NSACR),
-		.len		= 0x04,
-		.handle_mmio	= handle_mmio_raz_wi,
-	},
-	{},
-};
-
-static bool vgic_v3_queue_sgi(struct kvm_vcpu *vcpu, int irq)
-{
-	if (vgic_queue_irq(vcpu, 0, irq)) {
-		vgic_dist_irq_clear_pending(vcpu, irq);
-		vgic_cpu_irq_clear(vcpu, irq);
-		return true;
-	}
-
-	return false;
-}
-
-static int vgic_v3_map_resources(struct kvm *kvm,
-				 const struct vgic_params *params)
-{
-	int ret = 0;
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	gpa_t rdbase = dist->vgic_redist_base;
-	struct vgic_io_device *iodevs = NULL;
-	int i;
-
-	if (!irqchip_in_kernel(kvm))
-		return 0;
-
-	mutex_lock(&kvm->lock);
-
-	if (vgic_ready(kvm))
-		goto out;
-
-	if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
-	    IS_VGIC_ADDR_UNDEF(dist->vgic_redist_base)) {
-		kvm_err("Need to set vgic distributor addresses first\n");
-		ret = -ENXIO;
-		goto out;
-	}
-
-	/*
-	 * For a VGICv3 we require the userland to explicitly initialize
-	 * the VGIC before we need to use it.
-	 */
-	if (!vgic_initialized(kvm)) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	ret = vgic_register_kvm_io_dev(kvm, dist->vgic_dist_base,
-				       GIC_V3_DIST_SIZE, vgic_v3_dist_ranges,
-				       -1, &dist->dist_iodev);
-	if (ret)
-		goto out;
-
-	iodevs = kcalloc(dist->nr_cpus, sizeof(iodevs[0]), GFP_KERNEL);
-	if (!iodevs) {
-		ret = -ENOMEM;
-		goto out_unregister;
-	}
-
-	for (i = 0; i < dist->nr_cpus; i++) {
-		ret = vgic_register_kvm_io_dev(kvm, rdbase,
-					       SZ_128K, vgic_redist_ranges,
-					       i, &iodevs[i]);
-		if (ret)
-			goto out_unregister;
-		rdbase += GIC_V3_REDIST_SIZE;
-	}
-
-	dist->redist_iodevs = iodevs;
-	dist->ready = true;
-	goto out;
-
-out_unregister:
-	kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dist->dist_iodev.dev);
-	if (iodevs) {
-		for (i = 0; i < dist->nr_cpus; i++) {
-			if (iodevs[i].dev.ops)
-				kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
-							  &iodevs[i].dev);
-		}
-	}
-
-out:
-	if (ret)
-		kvm_vgic_destroy(kvm);
-	mutex_unlock(&kvm->lock);
-	return ret;
-}
-
-static int vgic_v3_init_model(struct kvm *kvm)
-{
-	int i;
-	u32 mpidr;
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	int nr_spis = dist->nr_irqs - VGIC_NR_PRIVATE_IRQS;
-
-	dist->irq_spi_mpidr = kcalloc(nr_spis, sizeof(dist->irq_spi_mpidr[0]),
-				      GFP_KERNEL);
-
-	if (!dist->irq_spi_mpidr)
-		return -ENOMEM;
-
-	/* Initialize the target VCPUs for each IRQ to VCPU 0 */
-	mpidr = compress_mpidr(kvm_vcpu_get_mpidr_aff(kvm_get_vcpu(kvm, 0)));
-	for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i++) {
-		dist->irq_spi_cpu[i - VGIC_NR_PRIVATE_IRQS] = 0;
-		dist->irq_spi_mpidr[i - VGIC_NR_PRIVATE_IRQS] = mpidr;
-		vgic_bitmap_set_irq_val(dist->irq_spi_target, 0, i, 1);
-	}
-
-	return 0;
-}
-
-/* GICv3 does not keep track of SGI sources anymore. */
-static void vgic_v3_add_sgi_source(struct kvm_vcpu *vcpu, int irq, int source)
-{
-}
-
-void vgic_v3_init_emulation(struct kvm *kvm)
-{
-	struct vgic_dist *dist = &kvm->arch.vgic;
-
-	dist->vm_ops.queue_sgi = vgic_v3_queue_sgi;
-	dist->vm_ops.add_sgi_source = vgic_v3_add_sgi_source;
-	dist->vm_ops.init_model = vgic_v3_init_model;
-	dist->vm_ops.map_resources = vgic_v3_map_resources;
-
-	kvm->arch.max_vcpus = KVM_MAX_VCPUS;
-}
-
-/*
- * Compare a given affinity (level 1-3 and a level 0 mask, from the SGI
- * generation register ICC_SGI1R_EL1) with a given VCPU.
- * If the VCPU's MPIDR matches, return the level0 affinity, otherwise
- * return -1.
- */
-static int match_mpidr(u64 sgi_aff, u16 sgi_cpu_mask, struct kvm_vcpu *vcpu)
-{
-	unsigned long affinity;
-	int level0;
-
-	/*
-	 * Split the current VCPU's MPIDR into affinity level 0 and the
-	 * rest as this is what we have to compare against.
-	 */
-	affinity = kvm_vcpu_get_mpidr_aff(vcpu);
-	level0 = MPIDR_AFFINITY_LEVEL(affinity, 0);
-	affinity &= ~MPIDR_LEVEL_MASK;
-
-	/* bail out if the upper three levels don't match */
-	if (sgi_aff != affinity)
-		return -1;
-
-	/* Is this VCPU's bit set in the mask ? */
-	if (!(sgi_cpu_mask & BIT(level0)))
-		return -1;
-
-	return level0;
-}
-
-#define SGI_AFFINITY_LEVEL(reg, level) \
-	((((reg) & ICC_SGI1R_AFFINITY_## level ##_MASK) \
-	>> ICC_SGI1R_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level))
-
-/**
- * vgic_v3_dispatch_sgi - handle SGI requests from VCPUs
- * @vcpu: The VCPU requesting a SGI
- * @reg: The value written into the ICC_SGI1R_EL1 register by that VCPU
- *
- * With GICv3 (and ARE=1) CPUs trigger SGIs by writing to a system register.
- * This will trap in sys_regs.c and call this function.
- * This ICC_SGI1R_EL1 register contains the upper three affinity levels of the
- * target processors as well as a bitmask of 16 Aff0 CPUs.
- * If the interrupt routing mode bit is not set, we iterate over all VCPUs to
- * check for matching ones. If this bit is set, we signal all, but not the
- * calling VCPU.
- */
-void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
-{
-	struct kvm *kvm = vcpu->kvm;
-	struct kvm_vcpu *c_vcpu;
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	u16 target_cpus;
-	u64 mpidr;
-	int sgi, c;
-	int vcpu_id = vcpu->vcpu_id;
-	bool broadcast;
-	int updated = 0;
-
-	sgi = (reg & ICC_SGI1R_SGI_ID_MASK) >> ICC_SGI1R_SGI_ID_SHIFT;
-	broadcast = reg & BIT(ICC_SGI1R_IRQ_ROUTING_MODE_BIT);
-	target_cpus = (reg & ICC_SGI1R_TARGET_LIST_MASK) >> ICC_SGI1R_TARGET_LIST_SHIFT;
-	mpidr = SGI_AFFINITY_LEVEL(reg, 3);
-	mpidr |= SGI_AFFINITY_LEVEL(reg, 2);
-	mpidr |= SGI_AFFINITY_LEVEL(reg, 1);
-
-	/*
-	 * We take the dist lock here, because we come from the sysregs
-	 * code path and not from the MMIO one (which already takes the lock).
-	 */
-	spin_lock(&dist->lock);
-
-	/*
-	 * We iterate over all VCPUs to find the MPIDRs matching the request.
-	 * If we have handled one CPU, we clear it's bit to detect early
-	 * if we are already finished. This avoids iterating through all
-	 * VCPUs when most of the times we just signal a single VCPU.
-	 */
-	kvm_for_each_vcpu(c, c_vcpu, kvm) {
-
-		/* Exit early if we have dealt with all requested CPUs */
-		if (!broadcast && target_cpus == 0)
-			break;
-
-		 /* Don't signal the calling VCPU */
-		if (broadcast && c == vcpu_id)
-			continue;
-
-		if (!broadcast) {
-			int level0;
-
-			level0 = match_mpidr(mpidr, target_cpus, c_vcpu);
-			if (level0 == -1)
-				continue;
-
-			/* remove this matching VCPU from the mask */
-			target_cpus &= ~BIT(level0);
-		}
-
-		/* Flag the SGI as pending */
-		vgic_dist_irq_set_pending(c_vcpu, sgi);
-		updated = 1;
-		kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c);
-	}
-	if (updated)
-		vgic_update_state(vcpu->kvm);
-	spin_unlock(&dist->lock);
-	if (updated)
-		vgic_kick_vcpus(vcpu->kvm);
-}
-
-static int vgic_v3_create(struct kvm_device *dev, u32 type)
-{
-	return kvm_vgic_create(dev->kvm, type);
-}
-
-static void vgic_v3_destroy(struct kvm_device *dev)
-{
-	kfree(dev);
-}
-
-static int vgic_v3_set_attr(struct kvm_device *dev,
-			    struct kvm_device_attr *attr)
-{
-	int ret;
-
-	ret = vgic_set_common_attr(dev, attr);
-	if (ret != -ENXIO)
-		return ret;
-
-	switch (attr->group) {
-	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
-	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
-		return -ENXIO;
-	}
-
-	return -ENXIO;
-}
-
-static int vgic_v3_get_attr(struct kvm_device *dev,
-			    struct kvm_device_attr *attr)
-{
-	int ret;
-
-	ret = vgic_get_common_attr(dev, attr);
-	if (ret != -ENXIO)
-		return ret;
-
-	switch (attr->group) {
-	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
-	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
-		return -ENXIO;
-	}
-
-	return -ENXIO;
-}
-
-static int vgic_v3_has_attr(struct kvm_device *dev,
-			    struct kvm_device_attr *attr)
-{
-	switch (attr->group) {
-	case KVM_DEV_ARM_VGIC_GRP_ADDR:
-		switch (attr->attr) {
-		case KVM_VGIC_V2_ADDR_TYPE_DIST:
-		case KVM_VGIC_V2_ADDR_TYPE_CPU:
-			return -ENXIO;
-		case KVM_VGIC_V3_ADDR_TYPE_DIST:
-		case KVM_VGIC_V3_ADDR_TYPE_REDIST:
-			return 0;
-		}
-		break;
-	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
-	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
-		return -ENXIO;
-	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
-		return 0;
-	case KVM_DEV_ARM_VGIC_GRP_CTRL:
-		switch (attr->attr) {
-		case KVM_DEV_ARM_VGIC_CTRL_INIT:
-			return 0;
-		}
-	}
-	return -ENXIO;
-}
-
-struct kvm_device_ops kvm_arm_vgic_v3_ops = {
-	.name = "kvm-arm-vgic-v3",
-	.create = vgic_v3_create,
-	.destroy = vgic_v3_destroy,
-	.set_attr = vgic_v3_set_attr,
-	.get_attr = vgic_v3_get_attr,
-	.has_attr = vgic_v3_has_attr,
-};
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
deleted file mode 100644
index 75b02fa86436..000000000000
--- a/virt/kvm/arm/vgic-v3.c
+++ /dev/null
@@ -1,279 +0,0 @@
-/*
- * Copyright (C) 2013 ARM Limited, All Rights Reserved.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/cpu.h>
-#include <linux/kvm.h>
-#include <linux/kvm_host.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-
-#include <linux/irqchip/arm-gic-v3.h>
-#include <linux/irqchip/arm-gic-common.h>
-
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_mmu.h>
-
-static u32 ich_vtr_el2;
-
-static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr)
-{
-	struct vgic_lr lr_desc;
-	u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr];
-
-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
-		lr_desc.irq = val & ICH_LR_VIRTUAL_ID_MASK;
-	else
-		lr_desc.irq = val & GICH_LR_VIRTUALID;
-
-	lr_desc.source = 0;
-	if (lr_desc.irq <= 15 &&
-	    vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2)
-		lr_desc.source = (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7;
-
-	lr_desc.state = 0;
-
-	if (val & ICH_LR_PENDING_BIT)
-		lr_desc.state |= LR_STATE_PENDING;
-	if (val & ICH_LR_ACTIVE_BIT)
-		lr_desc.state |= LR_STATE_ACTIVE;
-	if (val & ICH_LR_EOI)
-		lr_desc.state |= LR_EOI_INT;
-	if (val & ICH_LR_HW) {
-		lr_desc.state |= LR_HW;
-		lr_desc.hwirq = (val >> ICH_LR_PHYS_ID_SHIFT) & GENMASK(9, 0);
-	}
-
-	return lr_desc;
-}
-
-static void vgic_v3_set_lr(struct kvm_vcpu *vcpu, int lr,
-			   struct vgic_lr lr_desc)
-{
-	u64 lr_val;
-
-	lr_val = lr_desc.irq;
-
-	/*
-	 * Currently all guest IRQs are Group1, as Group0 would result
-	 * in a FIQ in the guest, which it wouldn't expect.
-	 * Eventually we want to make this configurable, so we may revisit
-	 * this in the future.
-	 */
-	switch (vcpu->kvm->arch.vgic.vgic_model) {
-	case KVM_DEV_TYPE_ARM_VGIC_V3:
-		lr_val |= ICH_LR_GROUP;
-		break;
-	case  KVM_DEV_TYPE_ARM_VGIC_V2:
-		if (lr_desc.irq < VGIC_NR_SGIS)
-			lr_val |= (u32)lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT;
-		break;
-	default:
-		BUG();
-	}
-
-	if (lr_desc.state & LR_STATE_PENDING)
-		lr_val |= ICH_LR_PENDING_BIT;
-	if (lr_desc.state & LR_STATE_ACTIVE)
-		lr_val |= ICH_LR_ACTIVE_BIT;
-	if (lr_desc.state & LR_EOI_INT)
-		lr_val |= ICH_LR_EOI;
-	if (lr_desc.state & LR_HW) {
-		lr_val |= ICH_LR_HW;
-		lr_val |= ((u64)lr_desc.hwirq) << ICH_LR_PHYS_ID_SHIFT;
-	}
-
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = lr_val;
-
-	if (!(lr_desc.state & LR_STATE_MASK))
-		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
-	else
-		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr &= ~(1U << lr);
-}
-
-static u64 vgic_v3_get_elrsr(const struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr;
-}
-
-static u64 vgic_v3_get_eisr(const struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr;
-}
-
-static void vgic_v3_clear_eisr(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr = 0;
-}
-
-static u32 vgic_v3_get_interrupt_status(const struct kvm_vcpu *vcpu)
-{
-	u32 misr = vcpu->arch.vgic_cpu.vgic_v3.vgic_misr;
-	u32 ret = 0;
-
-	if (misr & ICH_MISR_EOI)
-		ret |= INT_STATUS_EOI;
-	if (misr & ICH_MISR_U)
-		ret |= INT_STATUS_UNDERFLOW;
-
-	return ret;
-}
-
-static void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
-{
-	u32 vmcr = vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr;
-
-	vmcrp->ctlr = (vmcr & ICH_VMCR_CTLR_MASK) >> ICH_VMCR_CTLR_SHIFT;
-	vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT;
-	vmcrp->bpr  = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
-	vmcrp->pmr  = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
-}
-
-static void vgic_v3_enable_underflow(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr |= ICH_HCR_UIE;
-}
-
-static void vgic_v3_disable_underflow(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr &= ~ICH_HCR_UIE;
-}
-
-static void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
-{
-	u32 vmcr;
-
-	vmcr  = (vmcrp->ctlr << ICH_VMCR_CTLR_SHIFT) & ICH_VMCR_CTLR_MASK;
-	vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK;
-	vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK;
-	vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK;
-
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = vmcr;
-}
-
-static void vgic_v3_enable(struct kvm_vcpu *vcpu)
-{
-	struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3;
-
-	/*
-	 * By forcing VMCR to zero, the GIC will restore the binary
-	 * points to their reset values. Anything else resets to zero
-	 * anyway.
-	 */
-	vgic_v3->vgic_vmcr = 0;
-	vgic_v3->vgic_elrsr = ~0;
-
-	/*
-	 * If we are emulating a GICv3, we do it in an non-GICv2-compatible
-	 * way, so we force SRE to 1 to demonstrate this to the guest.
-	 * This goes with the spec allowing the value to be RAO/WI.
-	 */
-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
-		vgic_v3->vgic_sre = ICC_SRE_EL1_SRE;
-	else
-		vgic_v3->vgic_sre = 0;
-
-	/* Get the show on the road... */
-	vgic_v3->vgic_hcr = ICH_HCR_EN;
-}
-
-static const struct vgic_ops vgic_v3_ops = {
-	.get_lr			= vgic_v3_get_lr,
-	.set_lr			= vgic_v3_set_lr,
-	.get_elrsr		= vgic_v3_get_elrsr,
-	.get_eisr		= vgic_v3_get_eisr,
-	.clear_eisr		= vgic_v3_clear_eisr,
-	.get_interrupt_status	= vgic_v3_get_interrupt_status,
-	.enable_underflow	= vgic_v3_enable_underflow,
-	.disable_underflow	= vgic_v3_disable_underflow,
-	.get_vmcr		= vgic_v3_get_vmcr,
-	.set_vmcr		= vgic_v3_set_vmcr,
-	.enable			= vgic_v3_enable,
-};
-
-static struct vgic_params vgic_v3_params;
-
-static void vgic_cpu_init_lrs(void *params)
-{
-	kvm_call_hyp(__vgic_v3_init_lrs);
-}
-
-/**
- * vgic_v3_probe - probe for a GICv3 compatible interrupt controller
- * @gic_kvm_info:	pointer to the GIC description
- * @ops:		address of a pointer to the GICv3 operations
- * @params:		address of a pointer to HW-specific parameters
- *
- * Returns 0 if a GICv3 has been found, with the low level operations
- * in *ops and the HW parameters in *params. Returns an error code
- * otherwise.
- */
-int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
-		  const struct vgic_ops **ops,
-		  const struct vgic_params **params)
-{
-	int ret = 0;
-	struct vgic_params *vgic = &vgic_v3_params;
-	const struct resource *vcpu_res = &gic_kvm_info->vcpu;
-
-	vgic->maint_irq = gic_kvm_info->maint_irq;
-
-	ich_vtr_el2 = kvm_call_hyp(__vgic_v3_get_ich_vtr_el2);
-
-	/*
-	 * The ListRegs field is 5 bits, but there is a architectural
-	 * maximum of 16 list registers. Just ignore bit 4...
-	 */
-	vgic->nr_lr = (ich_vtr_el2 & 0xf) + 1;
-	vgic->can_emulate_gicv2 = false;
-
-	if (!vcpu_res->start) {
-		kvm_info("GICv3: no GICV resource entry\n");
-		vgic->vcpu_base = 0;
-	} else if (!PAGE_ALIGNED(vcpu_res->start)) {
-		pr_warn("GICV physical address 0x%llx not page aligned\n",
-			(unsigned long long)vcpu_res->start);
-		vgic->vcpu_base = 0;
-	} else if (!PAGE_ALIGNED(resource_size(vcpu_res))) {
-		pr_warn("GICV size 0x%llx not a multiple of page size 0x%lx\n",
-			(unsigned long long)resource_size(vcpu_res),
-			PAGE_SIZE);
-	} else {
-		vgic->vcpu_base = vcpu_res->start;
-		vgic->can_emulate_gicv2 = true;
-		kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
-					KVM_DEV_TYPE_ARM_VGIC_V2);
-	}
-	if (vgic->vcpu_base == 0)
-		kvm_info("disabling GICv2 emulation\n");
-	kvm_register_device_ops(&kvm_arm_vgic_v3_ops, KVM_DEV_TYPE_ARM_VGIC_V3);
-
-	vgic->vctrl_base = NULL;
-	vgic->type = VGIC_V3;
-	vgic->max_gic_vcpus = VGIC_V3_MAX_CPUS;
-
-	kvm_info("GICV base=0x%llx, IRQ=%d\n",
-		 vgic->vcpu_base, vgic->maint_irq);
-
-	on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
-
-	*ops = &vgic_v3_ops;
-	*params = vgic;
-
-	return ret;
-}
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
deleted file mode 100644
index 67cb5e948be2..000000000000
--- a/virt/kvm/arm/vgic.c
+++ /dev/null
@@ -1,2417 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#include <linux/cpu.h>
-#include <linux/kvm.h>
-#include <linux/kvm_host.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/rculist.h>
-#include <linux/uaccess.h>
-
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_mmu.h>
-#include <trace/events/kvm.h>
-#include <asm/kvm.h>
-#include <kvm/iodev.h>
-#include <linux/irqchip/arm-gic-common.h>
-
-#define CREATE_TRACE_POINTS
-#include "trace.h"
-
-/*
- * How the whole thing works (courtesy of Christoffer Dall):
- *
- * - At any time, the dist->irq_pending_on_cpu is the oracle that knows if
- *   something is pending on the CPU interface.
- * - Interrupts that are pending on the distributor are stored on the
- *   vgic.irq_pending vgic bitmap (this bitmap is updated by both user land
- *   ioctls and guest mmio ops, and other in-kernel peripherals such as the
- *   arch. timers).
- * - Every time the bitmap changes, the irq_pending_on_cpu oracle is
- *   recalculated
- * - To calculate the oracle, we need info for each cpu from
- *   compute_pending_for_cpu, which considers:
- *   - PPI: dist->irq_pending & dist->irq_enable
- *   - SPI: dist->irq_pending & dist->irq_enable & dist->irq_spi_target
- *   - irq_spi_target is a 'formatted' version of the GICD_ITARGETSRn
- *     registers, stored on each vcpu. We only keep one bit of
- *     information per interrupt, making sure that only one vcpu can
- *     accept the interrupt.
- * - If any of the above state changes, we must recalculate the oracle.
- * - The same is true when injecting an interrupt, except that we only
- *   consider a single interrupt at a time. The irq_spi_cpu array
- *   contains the target CPU for each SPI.
- *
- * The handling of level interrupts adds some extra complexity. We
- * need to track when the interrupt has been EOIed, so we can sample
- * the 'line' again. This is achieved as such:
- *
- * - When a level interrupt is moved onto a vcpu, the corresponding
- *   bit in irq_queued is set. As long as this bit is set, the line
- *   will be ignored for further interrupts. The interrupt is injected
- *   into the vcpu with the GICH_LR_EOI bit set (generate a
- *   maintenance interrupt on EOI).
- * - When the interrupt is EOIed, the maintenance interrupt fires,
- *   and clears the corresponding bit in irq_queued. This allows the
- *   interrupt line to be sampled again.
- * - Note that level-triggered interrupts can also be set to pending from
- *   writes to GICD_ISPENDRn and lowering the external input line does not
- *   cause the interrupt to become inactive in such a situation.
- *   Conversely, writes to GICD_ICPENDRn do not cause the interrupt to become
- *   inactive as long as the external input line is held high.
- *
- *
- * Initialization rules: there are multiple stages to the vgic
- * initialization, both for the distributor and the CPU interfaces.
- *
- * Distributor:
- *
- * - kvm_vgic_early_init(): initialization of static data that doesn't
- *   depend on any sizing information or emulation type. No allocation
- *   is allowed there.
- *
- * - vgic_init(): allocation and initialization of the generic data
- *   structures that depend on sizing information (number of CPUs,
- *   number of interrupts). Also initializes the vcpu specific data
- *   structures. Can be executed lazily for GICv2.
- *   [to be renamed to kvm_vgic_init??]
- *
- * CPU Interface:
- *
- * - kvm_vgic_cpu_early_init(): initialization of static data that
- *   doesn't depend on any sizing information or emulation type. No
- *   allocation is allowed there.
- */
-
-#include "vgic.h"
-
-static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
-static void vgic_retire_lr(int lr_nr, struct kvm_vcpu *vcpu);
-static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr);
-static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc);
-static u64 vgic_get_elrsr(struct kvm_vcpu *vcpu);
-static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu,
-						int virt_irq);
-static int compute_pending_for_cpu(struct kvm_vcpu *vcpu);
-
-static const struct vgic_ops *vgic_ops;
-static const struct vgic_params *vgic;
-
-static void add_sgi_source(struct kvm_vcpu *vcpu, int irq, int source)
-{
-	vcpu->kvm->arch.vgic.vm_ops.add_sgi_source(vcpu, irq, source);
-}
-
-static bool queue_sgi(struct kvm_vcpu *vcpu, int irq)
-{
-	return vcpu->kvm->arch.vgic.vm_ops.queue_sgi(vcpu, irq);
-}
-
-int kvm_vgic_map_resources(struct kvm *kvm)
-{
-	return kvm->arch.vgic.vm_ops.map_resources(kvm, vgic);
-}
-
-/*
- * struct vgic_bitmap contains a bitmap made of unsigned longs, but
- * extracts u32s out of them.
- *
- * This does not work on 64-bit BE systems, because the bitmap access
- * will store two consecutive 32-bit words with the higher-addressed
- * register's bits at the lower index and the lower-addressed register's
- * bits at the higher index.
- *
- * Therefore, swizzle the register index when accessing the 32-bit word
- * registers to access the right register's value.
- */
-#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 64
-#define REG_OFFSET_SWIZZLE	1
-#else
-#define REG_OFFSET_SWIZZLE	0
-#endif
-
-static int vgic_init_bitmap(struct vgic_bitmap *b, int nr_cpus, int nr_irqs)
-{
-	int nr_longs;
-
-	nr_longs = nr_cpus + BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);
-
-	b->private = kzalloc(sizeof(unsigned long) * nr_longs, GFP_KERNEL);
-	if (!b->private)
-		return -ENOMEM;
-
-	b->shared = b->private + nr_cpus;
-
-	return 0;
-}
-
-static void vgic_free_bitmap(struct vgic_bitmap *b)
-{
-	kfree(b->private);
-	b->private = NULL;
-	b->shared = NULL;
-}
-
-/*
- * Call this function to convert a u64 value to an unsigned long * bitmask
- * in a way that works on both 32-bit and 64-bit LE and BE platforms.
- *
- * Warning: Calling this function may modify *val.
- */
-static unsigned long *u64_to_bitmask(u64 *val)
-{
-#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 32
-	*val = (*val >> 32) | (*val << 32);
-#endif
-	return (unsigned long *)val;
-}
-
-u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x, int cpuid, u32 offset)
-{
-	offset >>= 2;
-	if (!offset)
-		return (u32 *)(x->private + cpuid) + REG_OFFSET_SWIZZLE;
-	else
-		return (u32 *)(x->shared) + ((offset - 1) ^ REG_OFFSET_SWIZZLE);
-}
-
-static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x,
-				   int cpuid, int irq)
-{
-	if (irq < VGIC_NR_PRIVATE_IRQS)
-		return test_bit(irq, x->private + cpuid);
-
-	return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared);
-}
-
-void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
-			     int irq, int val)
-{
-	unsigned long *reg;
-
-	if (irq < VGIC_NR_PRIVATE_IRQS) {
-		reg = x->private + cpuid;
-	} else {
-		reg = x->shared;
-		irq -= VGIC_NR_PRIVATE_IRQS;
-	}
-
-	if (val)
-		set_bit(irq, reg);
-	else
-		clear_bit(irq, reg);
-}
-
-static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid)
-{
-	return x->private + cpuid;
-}
-
-unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x)
-{
-	return x->shared;
-}
-
-static int vgic_init_bytemap(struct vgic_bytemap *x, int nr_cpus, int nr_irqs)
-{
-	int size;
-
-	size  = nr_cpus * VGIC_NR_PRIVATE_IRQS;
-	size += nr_irqs - VGIC_NR_PRIVATE_IRQS;
-
-	x->private = kzalloc(size, GFP_KERNEL);
-	if (!x->private)
-		return -ENOMEM;
-
-	x->shared = x->private + nr_cpus * VGIC_NR_PRIVATE_IRQS / sizeof(u32);
-	return 0;
-}
-
-static void vgic_free_bytemap(struct vgic_bytemap *b)
-{
-	kfree(b->private);
-	b->private = NULL;
-	b->shared = NULL;
-}
-
-u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
-{
-	u32 *reg;
-
-	if (offset < VGIC_NR_PRIVATE_IRQS) {
-		reg = x->private;
-		offset += cpuid * VGIC_NR_PRIVATE_IRQS;
-	} else {
-		reg = x->shared;
-		offset -= VGIC_NR_PRIVATE_IRQS;
-	}
-
-	return reg + (offset / sizeof(u32));
-}
-
-#define VGIC_CFG_LEVEL	0
-#define VGIC_CFG_EDGE	1
-
-static bool vgic_irq_is_edge(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	int irq_val;
-
-	irq_val = vgic_bitmap_get_irq_val(&dist->irq_cfg, vcpu->vcpu_id, irq);
-	return irq_val == VGIC_CFG_EDGE;
-}
-
-static int vgic_irq_is_enabled(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	return vgic_bitmap_get_irq_val(&dist->irq_enabled, vcpu->vcpu_id, irq);
-}
-
-static int vgic_irq_is_queued(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	return vgic_bitmap_get_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq);
-}
-
-static int vgic_irq_is_active(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	return vgic_bitmap_get_irq_val(&dist->irq_active, vcpu->vcpu_id, irq);
-}
-
-static void vgic_irq_set_queued(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 1);
-}
-
-static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0);
-}
-
-static void vgic_irq_set_active(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 1);
-}
-
-static void vgic_irq_clear_active(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 0);
-}
-
-static int vgic_dist_irq_get_level(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	return vgic_bitmap_get_irq_val(&dist->irq_level, vcpu->vcpu_id, irq);
-}
-
-static void vgic_dist_irq_set_level(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 1);
-}
-
-static void vgic_dist_irq_clear_level(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 0);
-}
-
-static int vgic_dist_irq_soft_pend(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	return vgic_bitmap_get_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq);
-}
-
-static void vgic_dist_irq_clear_soft_pend(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	vgic_bitmap_set_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq, 0);
-	if (!vgic_dist_irq_get_level(vcpu, irq)) {
-		vgic_dist_irq_clear_pending(vcpu, irq);
-		if (!compute_pending_for_cpu(vcpu))
-			clear_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
-	}
-}
-
-static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	return vgic_bitmap_get_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq);
-}
-
-void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 1);
-}
-
-void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 0);
-}
-
-static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq)
-{
-	if (irq < VGIC_NR_PRIVATE_IRQS)
-		set_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);
-	else
-		set_bit(irq - VGIC_NR_PRIVATE_IRQS,
-			vcpu->arch.vgic_cpu.pending_shared);
-}
-
-void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
-{
-	if (irq < VGIC_NR_PRIVATE_IRQS)
-		clear_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);
-	else
-		clear_bit(irq - VGIC_NR_PRIVATE_IRQS,
-			  vcpu->arch.vgic_cpu.pending_shared);
-}
-
-static bool vgic_can_sample_irq(struct kvm_vcpu *vcpu, int irq)
-{
-	return !vgic_irq_is_queued(vcpu, irq);
-}
-
-/**
- * vgic_reg_access - access vgic register
- * @mmio:   pointer to the data describing the mmio access
- * @reg:    pointer to the virtual backing of vgic distributor data
- * @offset: least significant 2 bits used for word offset
- * @mode:   ACCESS_ mode (see defines above)
- *
- * Helper to make vgic register access easier using one of the access
- * modes defined for vgic register access
- * (read,raz,write-ignored,setbit,clearbit,write)
- */
-void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg,
-		     phys_addr_t offset, int mode)
-{
-	int word_offset = (offset & 3) * 8;
-	u32 mask = (1UL << (mmio->len * 8)) - 1;
-	u32 regval;
-
-	/*
-	 * Any alignment fault should have been delivered to the guest
-	 * directly (ARM ARM B3.12.7 "Prioritization of aborts").
-	 */
-
-	if (reg) {
-		regval = *reg;
-	} else {
-		BUG_ON(mode != (ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED));
-		regval = 0;
-	}
-
-	if (mmio->is_write) {
-		u32 data = mmio_data_read(mmio, mask) << word_offset;
-		switch (ACCESS_WRITE_MASK(mode)) {
-		case ACCESS_WRITE_IGNORED:
-			return;
-
-		case ACCESS_WRITE_SETBIT:
-			regval |= data;
-			break;
-
-		case ACCESS_WRITE_CLEARBIT:
-			regval &= ~data;
-			break;
-
-		case ACCESS_WRITE_VALUE:
-			regval = (regval & ~(mask << word_offset)) | data;
-			break;
-		}
-		*reg = regval;
-	} else {
-		switch (ACCESS_READ_MASK(mode)) {
-		case ACCESS_READ_RAZ:
-			regval = 0;
-			/* fall through */
-
-		case ACCESS_READ_VALUE:
-			mmio_data_write(mmio, mask, regval >> word_offset);
-		}
-	}
-}
-
-bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
-			phys_addr_t offset)
-{
-	vgic_reg_access(mmio, NULL, offset,
-			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
-	return false;
-}
-
-bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
-			    phys_addr_t offset, int vcpu_id, int access)
-{
-	u32 *reg;
-	int mode = ACCESS_READ_VALUE | access;
-	struct kvm_vcpu *target_vcpu = kvm_get_vcpu(kvm, vcpu_id);
-
-	reg = vgic_bitmap_get_reg(&kvm->arch.vgic.irq_enabled, vcpu_id, offset);
-	vgic_reg_access(mmio, reg, offset, mode);
-	if (mmio->is_write) {
-		if (access & ACCESS_WRITE_CLEARBIT) {
-			if (offset < 4) /* Force SGI enabled */
-				*reg |= 0xffff;
-			vgic_retire_disabled_irqs(target_vcpu);
-		}
-		vgic_update_state(kvm);
-		return true;
-	}
-
-	return false;
-}
-
-bool vgic_handle_set_pending_reg(struct kvm *kvm,
-				 struct kvm_exit_mmio *mmio,
-				 phys_addr_t offset, int vcpu_id)
-{
-	u32 *reg, orig;
-	u32 level_mask;
-	int mode = ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT;
-	struct vgic_dist *dist = &kvm->arch.vgic;
-
-	reg = vgic_bitmap_get_reg(&dist->irq_cfg, vcpu_id, offset);
-	level_mask = (~(*reg));
-
-	/* Mark both level and edge triggered irqs as pending */
-	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
-	orig = *reg;
-	vgic_reg_access(mmio, reg, offset, mode);
-
-	if (mmio->is_write) {
-		/* Set the soft-pending flag only for level-triggered irqs */
-		reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
-					  vcpu_id, offset);
-		vgic_reg_access(mmio, reg, offset, mode);
-		*reg &= level_mask;
-
-		/* Ignore writes to SGIs */
-		if (offset < 2) {
-			*reg &= ~0xffff;
-			*reg |= orig & 0xffff;
-		}
-
-		vgic_update_state(kvm);
-		return true;
-	}
-
-	return false;
-}
-
-bool vgic_handle_clear_pending_reg(struct kvm *kvm,
-				   struct kvm_exit_mmio *mmio,
-				   phys_addr_t offset, int vcpu_id)
-{
-	u32 *level_active;
-	u32 *reg, orig;
-	int mode = ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT;
-	struct vgic_dist *dist = &kvm->arch.vgic;
-
-	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
-	orig = *reg;
-	vgic_reg_access(mmio, reg, offset, mode);
-	if (mmio->is_write) {
-		/* Re-set level triggered level-active interrupts */
-		level_active = vgic_bitmap_get_reg(&dist->irq_level,
-					  vcpu_id, offset);
-		reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu_id, offset);
-		*reg |= *level_active;
-
-		/* Ignore writes to SGIs */
-		if (offset < 2) {
-			*reg &= ~0xffff;
-			*reg |= orig & 0xffff;
-		}
-
-		/* Clear soft-pending flags */
-		reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
-					  vcpu_id, offset);
-		vgic_reg_access(mmio, reg, offset, mode);
-
-		vgic_update_state(kvm);
-		return true;
-	}
-	return false;
-}
-
-bool vgic_handle_set_active_reg(struct kvm *kvm,
-				struct kvm_exit_mmio *mmio,
-				phys_addr_t offset, int vcpu_id)
-{
-	u32 *reg;
-	struct vgic_dist *dist = &kvm->arch.vgic;
-
-	reg = vgic_bitmap_get_reg(&dist->irq_active, vcpu_id, offset);
-	vgic_reg_access(mmio, reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
-
-	if (mmio->is_write) {
-		vgic_update_state(kvm);
-		return true;
-	}
-
-	return false;
-}
-
-bool vgic_handle_clear_active_reg(struct kvm *kvm,
-				  struct kvm_exit_mmio *mmio,
-				  phys_addr_t offset, int vcpu_id)
-{
-	u32 *reg;
-	struct vgic_dist *dist = &kvm->arch.vgic;
-
-	reg = vgic_bitmap_get_reg(&dist->irq_active, vcpu_id, offset);
-	vgic_reg_access(mmio, reg, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
-
-	if (mmio->is_write) {
-		vgic_update_state(kvm);
-		return true;
-	}
-
-	return false;
-}
-
-static u32 vgic_cfg_expand(u16 val)
-{
-	u32 res = 0;
-	int i;
-
-	/*
-	 * Turn a 16bit value like abcd...mnop into a 32bit word
-	 * a0b0c0d0...m0n0o0p0, which is what the HW cfg register is.
-	 */
-	for (i = 0; i < 16; i++)
-		res |= ((val >> i) & VGIC_CFG_EDGE) << (2 * i + 1);
-
-	return res;
-}
-
-static u16 vgic_cfg_compress(u32 val)
-{
-	u16 res = 0;
-	int i;
-
-	/*
-	 * Turn a 32bit word a0b0c0d0...m0n0o0p0 into 16bit value like
-	 * abcd...mnop which is what we really care about.
-	 */
-	for (i = 0; i < 16; i++)
-		res |= ((val >> (i * 2 + 1)) & VGIC_CFG_EDGE) << i;
-
-	return res;
-}
-
-/*
- * The distributor uses 2 bits per IRQ for the CFG register, but the
- * LSB is always 0. As such, we only keep the upper bit, and use the
- * two above functions to compress/expand the bits
- */
-bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
-			 phys_addr_t offset)
-{
-	u32 val;
-
-	if (offset & 4)
-		val = *reg >> 16;
-	else
-		val = *reg & 0xffff;
-
-	val = vgic_cfg_expand(val);
-	vgic_reg_access(mmio, &val, offset,
-			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
-	if (mmio->is_write) {
-		/* Ignore writes to read-only SGI and PPI bits */
-		if (offset < 8)
-			return false;
-
-		val = vgic_cfg_compress(val);
-		if (offset & 4) {
-			*reg &= 0xffff;
-			*reg |= val << 16;
-		} else {
-			*reg &= 0xffff << 16;
-			*reg |= val;
-		}
-	}
-
-	return false;
-}
-
-/**
- * vgic_unqueue_irqs - move pending/active IRQs from LRs to the distributor
- * @vgic_cpu: Pointer to the vgic_cpu struct holding the LRs
- *
- * Move any IRQs that have already been assigned to LRs back to the
- * emulated distributor state so that the complete emulated state can be read
- * from the main emulation structures without investigating the LRs.
- */
-void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
-{
-	u64 elrsr = vgic_get_elrsr(vcpu);
-	unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr);
-	int i;
-
-	for_each_clear_bit(i, elrsr_ptr, vgic->nr_lr) {
-		struct vgic_lr lr = vgic_get_lr(vcpu, i);
-
-		/*
-		 * There are three options for the state bits:
-		 *
-		 * 01: pending
-		 * 10: active
-		 * 11: pending and active
-		 */
-		BUG_ON(!(lr.state & LR_STATE_MASK));
-
-		/* Reestablish SGI source for pending and active IRQs */
-		if (lr.irq < VGIC_NR_SGIS)
-			add_sgi_source(vcpu, lr.irq, lr.source);
-
-		/*
-		 * If the LR holds an active (10) or a pending and active (11)
-		 * interrupt then move the active state to the
-		 * distributor tracking bit.
-		 */
-		if (lr.state & LR_STATE_ACTIVE)
-			vgic_irq_set_active(vcpu, lr.irq);
-
-		/*
-		 * Reestablish the pending state on the distributor and the
-		 * CPU interface and mark the LR as free for other use.
-		 */
-		vgic_retire_lr(i, vcpu);
-
-		/* Finally update the VGIC state. */
-		vgic_update_state(vcpu->kvm);
-	}
-}
-
-const
-struct vgic_io_range *vgic_find_range(const struct vgic_io_range *ranges,
-				      int len, gpa_t offset)
-{
-	while (ranges->len) {
-		if (offset >= ranges->base &&
-		    (offset + len) <= (ranges->base + ranges->len))
-			return ranges;
-		ranges++;
-	}
-
-	return NULL;
-}
-
-static bool vgic_validate_access(const struct vgic_dist *dist,
-				 const struct vgic_io_range *range,
-				 unsigned long offset)
-{
-	int irq;
-
-	if (!range->bits_per_irq)
-		return true;	/* Not an irq-based access */
-
-	irq = offset * 8 / range->bits_per_irq;
-	if (irq >= dist->nr_irqs)
-		return false;
-
-	return true;
-}
-
-/*
- * Call the respective handler function for the given range.
- * We split up any 64 bit accesses into two consecutive 32 bit
- * handler calls and merge the result afterwards.
- * We do this in a little endian fashion regardless of the host's
- * or guest's endianness, because the GIC is always LE and the rest of
- * the code (vgic_reg_access) also puts it in a LE fashion already.
- * At this point we have already identified the handle function, so
- * range points to that one entry and offset is relative to this.
- */
-static bool call_range_handler(struct kvm_vcpu *vcpu,
-			       struct kvm_exit_mmio *mmio,
-			       unsigned long offset,
-			       const struct vgic_io_range *range)
-{
-	struct kvm_exit_mmio mmio32;
-	bool ret;
-
-	if (likely(mmio->len <= 4))
-		return range->handle_mmio(vcpu, mmio, offset);
-
-	/*
-	 * Any access bigger than 4 bytes (that we currently handle in KVM)
-	 * is actually 8 bytes long, caused by a 64-bit access
-	 */
-
-	mmio32.len = 4;
-	mmio32.is_write = mmio->is_write;
-	mmio32.private = mmio->private;
-
-	mmio32.phys_addr = mmio->phys_addr + 4;
-	mmio32.data = &((u32 *)mmio->data)[1];
-	ret = range->handle_mmio(vcpu, &mmio32, offset + 4);
-
-	mmio32.phys_addr = mmio->phys_addr;
-	mmio32.data = &((u32 *)mmio->data)[0];
-	ret |= range->handle_mmio(vcpu, &mmio32, offset);
-
-	return ret;
-}
-
-/**
- * vgic_handle_mmio_access - handle an in-kernel MMIO access
- * This is called by the read/write KVM IO device wrappers below.
- * @vcpu:	pointer to the vcpu performing the access
- * @this:	pointer to the KVM IO device in charge
- * @addr:	guest physical address of the access
- * @len:	size of the access
- * @val:	pointer to the data region
- * @is_write:	read or write access
- *
- * returns true if the MMIO access could be performed
- */
-static int vgic_handle_mmio_access(struct kvm_vcpu *vcpu,
-				   struct kvm_io_device *this, gpa_t addr,
-				   int len, void *val, bool is_write)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	struct vgic_io_device *iodev = container_of(this,
-						    struct vgic_io_device, dev);
-	const struct vgic_io_range *range;
-	struct kvm_exit_mmio mmio;
-	bool updated_state;
-	gpa_t offset;
-
-	offset = addr - iodev->addr;
-	range = vgic_find_range(iodev->reg_ranges, len, offset);
-	if (unlikely(!range || !range->handle_mmio)) {
-		pr_warn("Unhandled access %d %08llx %d\n", is_write, addr, len);
-		return -ENXIO;
-	}
-
-	mmio.phys_addr = addr;
-	mmio.len = len;
-	mmio.is_write = is_write;
-	mmio.data = val;
-	mmio.private = iodev->redist_vcpu;
-
-	spin_lock(&dist->lock);
-	offset -= range->base;
-	if (vgic_validate_access(dist, range, offset)) {
-		updated_state = call_range_handler(vcpu, &mmio, offset, range);
-	} else {
-		if (!is_write)
-			memset(val, 0, len);
-		updated_state = false;
-	}
-	spin_unlock(&dist->lock);
-
-	if (updated_state)
-		vgic_kick_vcpus(vcpu->kvm);
-
-	return 0;
-}
-
-static int vgic_handle_mmio_read(struct kvm_vcpu *vcpu,
-				 struct kvm_io_device *this,
-				 gpa_t addr, int len, void *val)
-{
-	return vgic_handle_mmio_access(vcpu, this, addr, len, val, false);
-}
-
-static int vgic_handle_mmio_write(struct kvm_vcpu *vcpu,
-				  struct kvm_io_device *this,
-				  gpa_t addr, int len, const void *val)
-{
-	return vgic_handle_mmio_access(vcpu, this, addr, len, (void *)val,
-				       true);
-}
-
-static struct kvm_io_device_ops vgic_io_ops = {
-	.read	= vgic_handle_mmio_read,
-	.write	= vgic_handle_mmio_write,
-};
-
-/**
- * vgic_register_kvm_io_dev - register VGIC register frame on the KVM I/O bus
- * @kvm:            The VM structure pointer
- * @base:           The (guest) base address for the register frame
- * @len:            Length of the register frame window
- * @ranges:         Describing the handler functions for each register
- * @redist_vcpu_id: The VCPU ID to pass on to the handlers on call
- * @iodev:          Points to memory to be passed on to the handler
- *
- * @iodev stores the parameters of this function to be usable by the handler
- * respectively the dispatcher function (since the KVM I/O bus framework lacks
- * an opaque parameter). Initialization is done in this function, but the
- * reference should be valid and unique for the whole VGIC lifetime.
- * If the register frame is not mapped for a specific VCPU, pass -1 to
- * @redist_vcpu_id.
- */
-int vgic_register_kvm_io_dev(struct kvm *kvm, gpa_t base, int len,
-			     const struct vgic_io_range *ranges,
-			     int redist_vcpu_id,
-			     struct vgic_io_device *iodev)
-{
-	struct kvm_vcpu *vcpu = NULL;
-	int ret;
-
-	if (redist_vcpu_id >= 0)
-		vcpu = kvm_get_vcpu(kvm, redist_vcpu_id);
-
-	iodev->addr		= base;
-	iodev->len		= len;
-	iodev->reg_ranges	= ranges;
-	iodev->redist_vcpu	= vcpu;
-
-	kvm_iodevice_init(&iodev->dev, &vgic_io_ops);
-
-	mutex_lock(&kvm->slots_lock);
-
-	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, base, len,
-				      &iodev->dev);
-	mutex_unlock(&kvm->slots_lock);
-
-	/* Mark the iodev as invalid if registration fails. */
-	if (ret)
-		iodev->dev.ops = NULL;
-
-	return ret;
-}
-
-static int vgic_nr_shared_irqs(struct vgic_dist *dist)
-{
-	return dist->nr_irqs - VGIC_NR_PRIVATE_IRQS;
-}
-
-static int compute_active_for_cpu(struct kvm_vcpu *vcpu)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	unsigned long *active, *enabled, *act_percpu, *act_shared;
-	unsigned long active_private, active_shared;
-	int nr_shared = vgic_nr_shared_irqs(dist);
-	int vcpu_id;
-
-	vcpu_id = vcpu->vcpu_id;
-	act_percpu = vcpu->arch.vgic_cpu.active_percpu;
-	act_shared = vcpu->arch.vgic_cpu.active_shared;
-
-	active = vgic_bitmap_get_cpu_map(&dist->irq_active, vcpu_id);
-	enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
-	bitmap_and(act_percpu, active, enabled, VGIC_NR_PRIVATE_IRQS);
-
-	active = vgic_bitmap_get_shared_map(&dist->irq_active);
-	enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
-	bitmap_and(act_shared, active, enabled, nr_shared);
-	bitmap_and(act_shared, act_shared,
-		   vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
-		   nr_shared);
-
-	active_private = find_first_bit(act_percpu, VGIC_NR_PRIVATE_IRQS);
-	active_shared = find_first_bit(act_shared, nr_shared);
-
-	return (active_private < VGIC_NR_PRIVATE_IRQS ||
-		active_shared < nr_shared);
-}
-
-static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	unsigned long *pending, *enabled, *pend_percpu, *pend_shared;
-	unsigned long pending_private, pending_shared;
-	int nr_shared = vgic_nr_shared_irqs(dist);
-	int vcpu_id;
-
-	vcpu_id = vcpu->vcpu_id;
-	pend_percpu = vcpu->arch.vgic_cpu.pending_percpu;
-	pend_shared = vcpu->arch.vgic_cpu.pending_shared;
-
-	if (!dist->enabled) {
-		bitmap_zero(pend_percpu, VGIC_NR_PRIVATE_IRQS);
-		bitmap_zero(pend_shared, nr_shared);
-		return 0;
-	}
-
-	pending = vgic_bitmap_get_cpu_map(&dist->irq_pending, vcpu_id);
-	enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
-	bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS);
-
-	pending = vgic_bitmap_get_shared_map(&dist->irq_pending);
-	enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
-	bitmap_and(pend_shared, pending, enabled, nr_shared);
-	bitmap_and(pend_shared, pend_shared,
-		   vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
-		   nr_shared);
-
-	pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS);
-	pending_shared = find_first_bit(pend_shared, nr_shared);
-	return (pending_private < VGIC_NR_PRIVATE_IRQS ||
-		pending_shared < vgic_nr_shared_irqs(dist));
-}
-
-/*
- * Update the interrupt state and determine which CPUs have pending
- * or active interrupts. Must be called with distributor lock held.
- */
-void vgic_update_state(struct kvm *kvm)
-{
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	struct kvm_vcpu *vcpu;
-	int c;
-
-	kvm_for_each_vcpu(c, vcpu, kvm) {
-		if (compute_pending_for_cpu(vcpu))
-			set_bit(c, dist->irq_pending_on_cpu);
-
-		if (compute_active_for_cpu(vcpu))
-			set_bit(c, dist->irq_active_on_cpu);
-		else
-			clear_bit(c, dist->irq_active_on_cpu);
-	}
-}
-
-static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr)
-{
-	return vgic_ops->get_lr(vcpu, lr);
-}
-
-static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr,
-			       struct vgic_lr vlr)
-{
-	vgic_ops->set_lr(vcpu, lr, vlr);
-}
-
-static inline u64 vgic_get_elrsr(struct kvm_vcpu *vcpu)
-{
-	return vgic_ops->get_elrsr(vcpu);
-}
-
-static inline u64 vgic_get_eisr(struct kvm_vcpu *vcpu)
-{
-	return vgic_ops->get_eisr(vcpu);
-}
-
-static inline void vgic_clear_eisr(struct kvm_vcpu *vcpu)
-{
-	vgic_ops->clear_eisr(vcpu);
-}
-
-static inline u32 vgic_get_interrupt_status(struct kvm_vcpu *vcpu)
-{
-	return vgic_ops->get_interrupt_status(vcpu);
-}
-
-static inline void vgic_enable_underflow(struct kvm_vcpu *vcpu)
-{
-	vgic_ops->enable_underflow(vcpu);
-}
-
-static inline void vgic_disable_underflow(struct kvm_vcpu *vcpu)
-{
-	vgic_ops->disable_underflow(vcpu);
-}
-
-void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
-{
-	vgic_ops->get_vmcr(vcpu, vmcr);
-}
-
-void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
-{
-	vgic_ops->set_vmcr(vcpu, vmcr);
-}
-
-static inline void vgic_enable(struct kvm_vcpu *vcpu)
-{
-	vgic_ops->enable(vcpu);
-}
-
-static void vgic_retire_lr(int lr_nr, struct kvm_vcpu *vcpu)
-{
-	struct vgic_lr vlr = vgic_get_lr(vcpu, lr_nr);
-
-	vgic_irq_clear_queued(vcpu, vlr.irq);
-
-	/*
-	 * We must transfer the pending state back to the distributor before
-	 * retiring the LR, otherwise we may loose edge-triggered interrupts.
-	 */
-	if (vlr.state & LR_STATE_PENDING) {
-		vgic_dist_irq_set_pending(vcpu, vlr.irq);
-		vlr.hwirq = 0;
-	}
-
-	vlr.state = 0;
-	vgic_set_lr(vcpu, lr_nr, vlr);
-}
-
-static bool dist_active_irq(struct kvm_vcpu *vcpu)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	return test_bit(vcpu->vcpu_id, dist->irq_active_on_cpu);
-}
-
-bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq)
-{
-	int i;
-
-	for (i = 0; i < vgic->nr_lr; i++) {
-		struct vgic_lr vlr = vgic_get_lr(vcpu, i);
-
-		if (vlr.irq == virt_irq && vlr.state & LR_STATE_ACTIVE)
-			return true;
-	}
-
-	return vgic_irq_is_active(vcpu, virt_irq);
-}
-
-/*
- * An interrupt may have been disabled after being made pending on the
- * CPU interface (the classic case is a timer running while we're
- * rebooting the guest - the interrupt would kick as soon as the CPU
- * interface gets enabled, with deadly consequences).
- *
- * The solution is to examine already active LRs, and check the
- * interrupt is still enabled. If not, just retire it.
- */
-static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
-{
-	u64 elrsr = vgic_get_elrsr(vcpu);
-	unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr);
-	int lr;
-
-	for_each_clear_bit(lr, elrsr_ptr, vgic->nr_lr) {
-		struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
-
-		if (!vgic_irq_is_enabled(vcpu, vlr.irq))
-			vgic_retire_lr(lr, vcpu);
-	}
-}
-
-static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq,
-				 int lr_nr, struct vgic_lr vlr)
-{
-	if (vgic_irq_is_active(vcpu, irq)) {
-		vlr.state |= LR_STATE_ACTIVE;
-		kvm_debug("Set active, clear distributor: 0x%x\n", vlr.state);
-		vgic_irq_clear_active(vcpu, irq);
-		vgic_update_state(vcpu->kvm);
-	} else {
-		WARN_ON(!vgic_dist_irq_is_pending(vcpu, irq));
-		vlr.state |= LR_STATE_PENDING;
-		kvm_debug("Set pending: 0x%x\n", vlr.state);
-	}
-
-	if (!vgic_irq_is_edge(vcpu, irq))
-		vlr.state |= LR_EOI_INT;
-
-	if (vlr.irq >= VGIC_NR_SGIS) {
-		struct irq_phys_map *map;
-		map = vgic_irq_map_search(vcpu, irq);
-
-		if (map) {
-			vlr.hwirq = map->phys_irq;
-			vlr.state |= LR_HW;
-			vlr.state &= ~LR_EOI_INT;
-
-			/*
-			 * Make sure we're not going to sample this
-			 * again, as a HW-backed interrupt cannot be
-			 * in the PENDING_ACTIVE stage.
-			 */
-			vgic_irq_set_queued(vcpu, irq);
-		}
-	}
-
-	vgic_set_lr(vcpu, lr_nr, vlr);
-}
-
-/*
- * Queue an interrupt to a CPU virtual interface. Return true on success,
- * or false if it wasn't possible to queue it.
- * sgi_source must be zero for any non-SGI interrupts.
- */
-bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	u64 elrsr = vgic_get_elrsr(vcpu);
-	unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr);
-	struct vgic_lr vlr;
-	int lr;
-
-	/* Sanitize the input... */
-	BUG_ON(sgi_source_id & ~7);
-	BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS);
-	BUG_ON(irq >= dist->nr_irqs);
-
-	kvm_debug("Queue IRQ%d\n", irq);
-
-	/* Do we have an active interrupt for the same CPUID? */
-	for_each_clear_bit(lr, elrsr_ptr, vgic->nr_lr) {
-		vlr = vgic_get_lr(vcpu, lr);
-		if (vlr.irq == irq && vlr.source == sgi_source_id) {
-			kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq);
-			vgic_queue_irq_to_lr(vcpu, irq, lr, vlr);
-			return true;
-		}
-	}
-
-	/* Try to use another LR for this interrupt */
-	lr = find_first_bit(elrsr_ptr, vgic->nr_lr);
-	if (lr >= vgic->nr_lr)
-		return false;
-
-	kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id);
-
-	vlr.irq = irq;
-	vlr.source = sgi_source_id;
-	vlr.state = 0;
-	vgic_queue_irq_to_lr(vcpu, irq, lr, vlr);
-
-	return true;
-}
-
-static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
-{
-	if (!vgic_can_sample_irq(vcpu, irq))
-		return true; /* level interrupt, already queued */
-
-	if (vgic_queue_irq(vcpu, 0, irq)) {
-		if (vgic_irq_is_edge(vcpu, irq)) {
-			vgic_dist_irq_clear_pending(vcpu, irq);
-			vgic_cpu_irq_clear(vcpu, irq);
-		} else {
-			vgic_irq_set_queued(vcpu, irq);
-		}
-
-		return true;
-	}
-
-	return false;
-}
-
-/*
- * Fill the list registers with pending interrupts before running the
- * guest.
- */
-static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
-{
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	unsigned long *pa_percpu, *pa_shared;
-	int i, vcpu_id;
-	int overflow = 0;
-	int nr_shared = vgic_nr_shared_irqs(dist);
-
-	vcpu_id = vcpu->vcpu_id;
-
-	pa_percpu = vcpu->arch.vgic_cpu.pend_act_percpu;
-	pa_shared = vcpu->arch.vgic_cpu.pend_act_shared;
-
-	bitmap_or(pa_percpu, vgic_cpu->pending_percpu, vgic_cpu->active_percpu,
-		  VGIC_NR_PRIVATE_IRQS);
-	bitmap_or(pa_shared, vgic_cpu->pending_shared, vgic_cpu->active_shared,
-		  nr_shared);
-	/*
-	 * We may not have any pending interrupt, or the interrupts
-	 * may have been serviced from another vcpu. In all cases,
-	 * move along.
-	 */
-	if (!kvm_vgic_vcpu_pending_irq(vcpu) && !dist_active_irq(vcpu))
-		goto epilog;
-
-	/* SGIs */
-	for_each_set_bit(i, pa_percpu, VGIC_NR_SGIS) {
-		if (!queue_sgi(vcpu, i))
-			overflow = 1;
-	}
-
-	/* PPIs */
-	for_each_set_bit_from(i, pa_percpu, VGIC_NR_PRIVATE_IRQS) {
-		if (!vgic_queue_hwirq(vcpu, i))
-			overflow = 1;
-	}
-
-	/* SPIs */
-	for_each_set_bit(i, pa_shared, nr_shared) {
-		if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS))
-			overflow = 1;
-	}
-
-
-
-
-epilog:
-	if (overflow) {
-		vgic_enable_underflow(vcpu);
-	} else {
-		vgic_disable_underflow(vcpu);
-		/*
-		 * We're about to run this VCPU, and we've consumed
-		 * everything the distributor had in store for
-		 * us. Claim we don't have anything pending. We'll
-		 * adjust that if needed while exiting.
-		 */
-		clear_bit(vcpu_id, dist->irq_pending_on_cpu);
-	}
-}
-
-static int process_queued_irq(struct kvm_vcpu *vcpu,
-				   int lr, struct vgic_lr vlr)
-{
-	int pending = 0;
-
-	/*
-	 * If the IRQ was EOIed (called from vgic_process_maintenance) or it
-	 * went from active to non-active (called from vgic_sync_hwirq) it was
-	 * also ACKed and we we therefore assume we can clear the soft pending
-	 * state (should it had been set) for this interrupt.
-	 *
-	 * Note: if the IRQ soft pending state was set after the IRQ was
-	 * acked, it actually shouldn't be cleared, but we have no way of
-	 * knowing that unless we start trapping ACKs when the soft-pending
-	 * state is set.
-	 */
-	vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq);
-
-	/*
-	 * Tell the gic to start sampling this interrupt again.
-	 */
-	vgic_irq_clear_queued(vcpu, vlr.irq);
-
-	/* Any additional pending interrupt? */
-	if (vgic_irq_is_edge(vcpu, vlr.irq)) {
-		BUG_ON(!(vlr.state & LR_HW));
-		pending = vgic_dist_irq_is_pending(vcpu, vlr.irq);
-	} else {
-		if (vgic_dist_irq_get_level(vcpu, vlr.irq)) {
-			vgic_cpu_irq_set(vcpu, vlr.irq);
-			pending = 1;
-		} else {
-			vgic_dist_irq_clear_pending(vcpu, vlr.irq);
-			vgic_cpu_irq_clear(vcpu, vlr.irq);
-		}
-	}
-
-	/*
-	 * Despite being EOIed, the LR may not have
-	 * been marked as empty.
-	 */
-	vlr.state = 0;
-	vlr.hwirq = 0;
-	vgic_set_lr(vcpu, lr, vlr);
-
-	return pending;
-}
-
-static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
-{
-	u32 status = vgic_get_interrupt_status(vcpu);
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	struct kvm *kvm = vcpu->kvm;
-	int level_pending = 0;
-
-	kvm_debug("STATUS = %08x\n", status);
-
-	if (status & INT_STATUS_EOI) {
-		/*
-		 * Some level interrupts have been EOIed. Clear their
-		 * active bit.
-		 */
-		u64 eisr = vgic_get_eisr(vcpu);
-		unsigned long *eisr_ptr = u64_to_bitmask(&eisr);
-		int lr;
-
-		for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
-			struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
-
-			WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq));
-			WARN_ON(vlr.state & LR_STATE_MASK);
-
-
-			/*
-			 * kvm_notify_acked_irq calls kvm_set_irq()
-			 * to reset the IRQ level, which grabs the dist->lock
-			 * so we call this before taking the dist->lock.
-			 */
-			kvm_notify_acked_irq(kvm, 0,
-					     vlr.irq - VGIC_NR_PRIVATE_IRQS);
-
-			spin_lock(&dist->lock);
-			level_pending |= process_queued_irq(vcpu, lr, vlr);
-			spin_unlock(&dist->lock);
-		}
-	}
-
-	if (status & INT_STATUS_UNDERFLOW)
-		vgic_disable_underflow(vcpu);
-
-	/*
-	 * In the next iterations of the vcpu loop, if we sync the vgic state
-	 * after flushing it, but before entering the guest (this happens for
-	 * pending signals and vmid rollovers), then make sure we don't pick
-	 * up any old maintenance interrupts here.
-	 */
-	vgic_clear_eisr(vcpu);
-
-	return level_pending;
-}
-
-/*
- * Save the physical active state, and reset it to inactive.
- *
- * Return true if there's a pending forwarded interrupt to queue.
- */
-static bool vgic_sync_hwirq(struct kvm_vcpu *vcpu, int lr, struct vgic_lr vlr)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	bool level_pending;
-
-	if (!(vlr.state & LR_HW))
-		return false;
-
-	if (vlr.state & LR_STATE_ACTIVE)
-		return false;
-
-	spin_lock(&dist->lock);
-	level_pending = process_queued_irq(vcpu, lr, vlr);
-	spin_unlock(&dist->lock);
-	return level_pending;
-}
-
-/* Sync back the VGIC state after a guest run */
-static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	u64 elrsr;
-	unsigned long *elrsr_ptr;
-	int lr, pending;
-	bool level_pending;
-
-	level_pending = vgic_process_maintenance(vcpu);
-
-	/* Deal with HW interrupts, and clear mappings for empty LRs */
-	for (lr = 0; lr < vgic->nr_lr; lr++) {
-		struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
-
-		level_pending |= vgic_sync_hwirq(vcpu, lr, vlr);
-		BUG_ON(vlr.irq >= dist->nr_irqs);
-	}
-
-	/* Check if we still have something up our sleeve... */
-	elrsr = vgic_get_elrsr(vcpu);
-	elrsr_ptr = u64_to_bitmask(&elrsr);
-	pending = find_first_zero_bit(elrsr_ptr, vgic->nr_lr);
-	if (level_pending || pending < vgic->nr_lr)
-		set_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
-}
-
-void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	if (!irqchip_in_kernel(vcpu->kvm))
-		return;
-
-	spin_lock(&dist->lock);
-	__kvm_vgic_flush_hwstate(vcpu);
-	spin_unlock(&dist->lock);
-}
-
-void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
-{
-	if (!irqchip_in_kernel(vcpu->kvm))
-		return;
-
-	__kvm_vgic_sync_hwstate(vcpu);
-}
-
-int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-	if (!irqchip_in_kernel(vcpu->kvm))
-		return 0;
-
-	return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
-}
-
-void vgic_kick_vcpus(struct kvm *kvm)
-{
-	struct kvm_vcpu *vcpu;
-	int c;
-
-	/*
-	 * We've injected an interrupt, time to find out who deserves
-	 * a good kick...
-	 */
-	kvm_for_each_vcpu(c, vcpu, kvm) {
-		if (kvm_vgic_vcpu_pending_irq(vcpu))
-			kvm_vcpu_kick(vcpu);
-	}
-}
-
-static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
-{
-	int edge_triggered = vgic_irq_is_edge(vcpu, irq);
-
-	/*
-	 * Only inject an interrupt if:
-	 * - edge triggered and we have a rising edge
-	 * - level triggered and we change level
-	 */
-	if (edge_triggered) {
-		int state = vgic_dist_irq_is_pending(vcpu, irq);
-		return level > state;
-	} else {
-		int state = vgic_dist_irq_get_level(vcpu, irq);
-		return level != state;
-	}
-}
-
-static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
-				   unsigned int irq_num, bool level)
-{
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	struct kvm_vcpu *vcpu;
-	int edge_triggered, level_triggered;
-	int enabled;
-	bool ret = true, can_inject = true;
-
-	trace_vgic_update_irq_pending(cpuid, irq_num, level);
-
-	if (irq_num >= min(kvm->arch.vgic.nr_irqs, 1020))
-		return -EINVAL;
-
-	spin_lock(&dist->lock);
-
-	vcpu = kvm_get_vcpu(kvm, cpuid);
-	edge_triggered = vgic_irq_is_edge(vcpu, irq_num);
-	level_triggered = !edge_triggered;
-
-	if (!vgic_validate_injection(vcpu, irq_num, level)) {
-		ret = false;
-		goto out;
-	}
-
-	if (irq_num >= VGIC_NR_PRIVATE_IRQS) {
-		cpuid = dist->irq_spi_cpu[irq_num - VGIC_NR_PRIVATE_IRQS];
-		if (cpuid == VCPU_NOT_ALLOCATED) {
-			/* Pretend we use CPU0, and prevent injection */
-			cpuid = 0;
-			can_inject = false;
-		}
-		vcpu = kvm_get_vcpu(kvm, cpuid);
-	}
-
-	kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid);
-
-	if (level) {
-		if (level_triggered)
-			vgic_dist_irq_set_level(vcpu, irq_num);
-		vgic_dist_irq_set_pending(vcpu, irq_num);
-	} else {
-		if (level_triggered) {
-			vgic_dist_irq_clear_level(vcpu, irq_num);
-			if (!vgic_dist_irq_soft_pend(vcpu, irq_num)) {
-				vgic_dist_irq_clear_pending(vcpu, irq_num);
-				vgic_cpu_irq_clear(vcpu, irq_num);
-				if (!compute_pending_for_cpu(vcpu))
-					clear_bit(cpuid, dist->irq_pending_on_cpu);
-			}
-		}
-
-		ret = false;
-		goto out;
-	}
-
-	enabled = vgic_irq_is_enabled(vcpu, irq_num);
-
-	if (!enabled || !can_inject) {
-		ret = false;
-		goto out;
-	}
-
-	if (!vgic_can_sample_irq(vcpu, irq_num)) {
-		/*
-		 * Level interrupt in progress, will be picked up
-		 * when EOId.
-		 */
-		ret = false;
-		goto out;
-	}
-
-	if (level) {
-		vgic_cpu_irq_set(vcpu, irq_num);
-		set_bit(cpuid, dist->irq_pending_on_cpu);
-	}
-
-out:
-	spin_unlock(&dist->lock);
-
-	if (ret) {
-		/* kick the specified vcpu */
-		kvm_vcpu_kick(kvm_get_vcpu(kvm, cpuid));
-	}
-
-	return 0;
-}
-
-static int vgic_lazy_init(struct kvm *kvm)
-{
-	int ret = 0;
-
-	if (unlikely(!vgic_initialized(kvm))) {
-		/*
-		 * We only provide the automatic initialization of the VGIC
-		 * for the legacy case of a GICv2. Any other type must
-		 * be explicitly initialized once setup with the respective
-		 * KVM device call.
-		 */
-		if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2)
-			return -EBUSY;
-
-		mutex_lock(&kvm->lock);
-		ret = vgic_init(kvm);
-		mutex_unlock(&kvm->lock);
-	}
-
-	return ret;
-}
-
-/**
- * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
- * @kvm:     The VM structure pointer
- * @cpuid:   The CPU for PPIs
- * @irq_num: The IRQ number that is assigned to the device. This IRQ
- *           must not be mapped to a HW interrupt.
- * @level:   Edge-triggered:  true:  to trigger the interrupt
- *			      false: to ignore the call
- *	     Level-sensitive  true:  raise the input signal
- *			      false: lower the input signal
- *
- * The GIC is not concerned with devices being active-LOW or active-HIGH for
- * level-sensitive interrupts.  You can think of the level parameter as 1
- * being HIGH and 0 being LOW and all devices being active-HIGH.
- */
-int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
-			bool level)
-{
-	struct irq_phys_map *map;
-	int ret;
-
-	ret = vgic_lazy_init(kvm);
-	if (ret)
-		return ret;
-
-	map = vgic_irq_map_search(kvm_get_vcpu(kvm, cpuid), irq_num);
-	if (map)
-		return -EINVAL;
-
-	return vgic_update_irq_pending(kvm, cpuid, irq_num, level);
-}
-
-/**
- * kvm_vgic_inject_mapped_irq - Inject a physically mapped IRQ to the vgic
- * @kvm:     The VM structure pointer
- * @cpuid:   The CPU for PPIs
- * @virt_irq: The virtual IRQ to be injected
- * @level:   Edge-triggered:  true:  to trigger the interrupt
- *			      false: to ignore the call
- *	     Level-sensitive  true:  raise the input signal
- *			      false: lower the input signal
- *
- * The GIC is not concerned with devices being active-LOW or active-HIGH for
- * level-sensitive interrupts.  You can think of the level parameter as 1
- * being HIGH and 0 being LOW and all devices being active-HIGH.
- */
-int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
-			       unsigned int virt_irq, bool level)
-{
-	int ret;
-
-	ret = vgic_lazy_init(kvm);
-	if (ret)
-		return ret;
-
-	return vgic_update_irq_pending(kvm, cpuid, virt_irq, level);
-}
-
-static irqreturn_t vgic_maintenance_handler(int irq, void *data)
-{
-	/*
-	 * We cannot rely on the vgic maintenance interrupt to be
-	 * delivered synchronously. This means we can only use it to
-	 * exit the VM, and we perform the handling of EOIed
-	 * interrupts on the exit path (see vgic_process_maintenance).
-	 */
-	return IRQ_HANDLED;
-}
-
-static struct list_head *vgic_get_irq_phys_map_list(struct kvm_vcpu *vcpu,
-						    int virt_irq)
-{
-	if (virt_irq < VGIC_NR_PRIVATE_IRQS)
-		return &vcpu->arch.vgic_cpu.irq_phys_map_list;
-	else
-		return &vcpu->kvm->arch.vgic.irq_phys_map_list;
-}
-
-/**
- * kvm_vgic_map_phys_irq - map a virtual IRQ to a physical IRQ
- * @vcpu: The VCPU pointer
- * @virt_irq: The virtual IRQ number for the guest
- * @phys_irq: The hardware IRQ number of the host
- *
- * Establish a mapping between a guest visible irq (@virt_irq) and a
- * hardware irq (@phys_irq). On injection, @virt_irq will be associated with
- * the physical interrupt represented by @phys_irq. This mapping can be
- * established multiple times as long as the parameters are the same.
- *
- * Returns 0 on success or an error value otherwise.
- */
-int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int phys_irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	struct list_head *root = vgic_get_irq_phys_map_list(vcpu, virt_irq);
-	struct irq_phys_map *map;
-	struct irq_phys_map_entry *entry;
-	int ret = 0;
-
-	/* Create a new mapping */
-	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		return -ENOMEM;
-
-	spin_lock(&dist->irq_phys_map_lock);
-
-	/* Try to match an existing mapping */
-	map = vgic_irq_map_search(vcpu, virt_irq);
-	if (map) {
-		/* Make sure this mapping matches */
-		if (map->phys_irq != phys_irq)
-			ret = -EINVAL;
-
-		/* Found an existing, valid mapping */
-		goto out;
-	}
-
-	map           = &entry->map;
-	map->virt_irq = virt_irq;
-	map->phys_irq = phys_irq;
-
-	list_add_tail_rcu(&entry->entry, root);
-
-out:
-	spin_unlock(&dist->irq_phys_map_lock);
-	/* If we've found a hit in the existing list, free the useless
-	 * entry */
-	if (ret || map != &entry->map)
-		kfree(entry);
-	return ret;
-}
-
-static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu,
-						int virt_irq)
-{
-	struct list_head *root = vgic_get_irq_phys_map_list(vcpu, virt_irq);
-	struct irq_phys_map_entry *entry;
-	struct irq_phys_map *map;
-
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(entry, root, entry) {
-		map = &entry->map;
-		if (map->virt_irq == virt_irq) {
-			rcu_read_unlock();
-			return map;
-		}
-	}
-
-	rcu_read_unlock();
-
-	return NULL;
-}
-
-static void vgic_free_phys_irq_map_rcu(struct rcu_head *rcu)
-{
-	struct irq_phys_map_entry *entry;
-
-	entry = container_of(rcu, struct irq_phys_map_entry, rcu);
-	kfree(entry);
-}
-
-/**
- * kvm_vgic_unmap_phys_irq - Remove a virtual to physical IRQ mapping
- * @vcpu: The VCPU pointer
- * @virt_irq: The virtual IRQ number to be unmapped
- *
- * Remove an existing mapping between virtual and physical interrupts.
- */
-int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq)
-{
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-	struct irq_phys_map_entry *entry;
-	struct list_head *root;
-
-	root = vgic_get_irq_phys_map_list(vcpu, virt_irq);
-
-	spin_lock(&dist->irq_phys_map_lock);
-
-	list_for_each_entry(entry, root, entry) {
-		if (entry->map.virt_irq == virt_irq) {
-			list_del_rcu(&entry->entry);
-			call_rcu(&entry->rcu, vgic_free_phys_irq_map_rcu);
-			break;
-		}
-	}
-
-	spin_unlock(&dist->irq_phys_map_lock);
-
-	return 0;
-}
-
-static void vgic_destroy_irq_phys_map(struct kvm *kvm, struct list_head *root)
-{
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	struct irq_phys_map_entry *entry;
-
-	spin_lock(&dist->irq_phys_map_lock);
-
-	list_for_each_entry(entry, root, entry) {
-		list_del_rcu(&entry->entry);
-		call_rcu(&entry->rcu, vgic_free_phys_irq_map_rcu);
-	}
-
-	spin_unlock(&dist->irq_phys_map_lock);
-}
-
-void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
-{
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-
-	kfree(vgic_cpu->pending_shared);
-	kfree(vgic_cpu->active_shared);
-	kfree(vgic_cpu->pend_act_shared);
-	vgic_destroy_irq_phys_map(vcpu->kvm, &vgic_cpu->irq_phys_map_list);
-	vgic_cpu->pending_shared = NULL;
-	vgic_cpu->active_shared = NULL;
-	vgic_cpu->pend_act_shared = NULL;
-}
-
-static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
-{
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	int nr_longs = BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);
-	int sz = nr_longs * sizeof(unsigned long);
-	vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
-	vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL);
-	vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL);
-
-	if (!vgic_cpu->pending_shared
-		|| !vgic_cpu->active_shared
-		|| !vgic_cpu->pend_act_shared) {
-		kvm_vgic_vcpu_destroy(vcpu);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-/**
- * kvm_vgic_vcpu_early_init - Earliest possible per-vcpu vgic init stage
- *
- * No memory allocation should be performed here, only static init.
- */
-void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu)
-{
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	INIT_LIST_HEAD(&vgic_cpu->irq_phys_map_list);
-}
-
-/**
- * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
- *
- * The host's GIC naturally limits the maximum amount of VCPUs a guest
- * can use.
- */
-int kvm_vgic_get_max_vcpus(void)
-{
-	return vgic->max_gic_vcpus;
-}
-
-void kvm_vgic_destroy(struct kvm *kvm)
-{
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	struct kvm_vcpu *vcpu;
-	int i;
-
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vgic_vcpu_destroy(vcpu);
-
-	vgic_free_bitmap(&dist->irq_enabled);
-	vgic_free_bitmap(&dist->irq_level);
-	vgic_free_bitmap(&dist->irq_pending);
-	vgic_free_bitmap(&dist->irq_soft_pend);
-	vgic_free_bitmap(&dist->irq_queued);
-	vgic_free_bitmap(&dist->irq_cfg);
-	vgic_free_bytemap(&dist->irq_priority);
-	if (dist->irq_spi_target) {
-		for (i = 0; i < dist->nr_cpus; i++)
-			vgic_free_bitmap(&dist->irq_spi_target[i]);
-	}
-	kfree(dist->irq_sgi_sources);
-	kfree(dist->irq_spi_cpu);
-	kfree(dist->irq_spi_mpidr);
-	kfree(dist->irq_spi_target);
-	kfree(dist->irq_pending_on_cpu);
-	kfree(dist->irq_active_on_cpu);
-	vgic_destroy_irq_phys_map(kvm, &dist->irq_phys_map_list);
-	dist->irq_sgi_sources = NULL;
-	dist->irq_spi_cpu = NULL;
-	dist->irq_spi_target = NULL;
-	dist->irq_pending_on_cpu = NULL;
-	dist->irq_active_on_cpu = NULL;
-	dist->nr_cpus = 0;
-}
-
-/*
- * Allocate and initialize the various data structures. Must be called
- * with kvm->lock held!
- */
-int vgic_init(struct kvm *kvm)
-{
-	struct vgic_dist *dist = &kvm->arch.vgic;
-	struct kvm_vcpu *vcpu;
-	int nr_cpus, nr_irqs;
-	int ret, i, vcpu_id;
-
-	if (vgic_initialized(kvm))
-		return 0;
-
-	nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus);
-	if (!nr_cpus)		/* No vcpus? Can't be good... */
-		return -ENODEV;
-
-	/*
-	 * If nobody configured the number of interrupts, use the
-	 * legacy one.
-	 */
-	if (!dist->nr_irqs)
-		dist->nr_irqs = VGIC_NR_IRQS_LEGACY;
-
-	nr_irqs = dist->nr_irqs;
-
-	ret  = vgic_init_bitmap(&dist->irq_enabled, nr_cpus, nr_irqs);
-	ret |= vgic_init_bitmap(&dist->irq_level, nr_cpus, nr_irqs);
-	ret |= vgic_init_bitmap(&dist->irq_pending, nr_cpus, nr_irqs);
-	ret |= vgic_init_bitmap(&dist->irq_soft_pend, nr_cpus, nr_irqs);
-	ret |= vgic_init_bitmap(&dist->irq_queued, nr_cpus, nr_irqs);
-	ret |= vgic_init_bitmap(&dist->irq_active, nr_cpus, nr_irqs);
-	ret |= vgic_init_bitmap(&dist->irq_cfg, nr_cpus, nr_irqs);
-	ret |= vgic_init_bytemap(&dist->irq_priority, nr_cpus, nr_irqs);
-
-	if (ret)
-		goto out;
-
-	dist->irq_sgi_sources = kzalloc(nr_cpus * VGIC_NR_SGIS, GFP_KERNEL);
-	dist->irq_spi_cpu = kzalloc(nr_irqs - VGIC_NR_PRIVATE_IRQS, GFP_KERNEL);
-	dist->irq_spi_target = kzalloc(sizeof(*dist->irq_spi_target) * nr_cpus,
-				       GFP_KERNEL);
-	dist->irq_pending_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
-					   GFP_KERNEL);
-	dist->irq_active_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
-					   GFP_KERNEL);
-	if (!dist->irq_sgi_sources ||
-	    !dist->irq_spi_cpu ||
-	    !dist->irq_spi_target ||
-	    !dist->irq_pending_on_cpu ||
-	    !dist->irq_active_on_cpu) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	for (i = 0; i < nr_cpus; i++)
-		ret |= vgic_init_bitmap(&dist->irq_spi_target[i],
-					nr_cpus, nr_irqs);
-
-	if (ret)
-		goto out;
-
-	ret = kvm->arch.vgic.vm_ops.init_model(kvm);
-	if (ret)
-		goto out;
-
-	kvm_for_each_vcpu(vcpu_id, vcpu, kvm) {
-		ret = vgic_vcpu_init_maps(vcpu, nr_irqs);
-		if (ret) {
-			kvm_err("VGIC: Failed to allocate vcpu memory\n");
-			break;
-		}
-
-		/*
-		 * Enable and configure all SGIs to be edge-triggere and
-		 * configure all PPIs as level-triggered.
-		 */
-		for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
-			if (i < VGIC_NR_SGIS) {
-				/* SGIs */
-				vgic_bitmap_set_irq_val(&dist->irq_enabled,
-							vcpu->vcpu_id, i, 1);
-				vgic_bitmap_set_irq_val(&dist->irq_cfg,
-							vcpu->vcpu_id, i,
-							VGIC_CFG_EDGE);
-			} else if (i < VGIC_NR_PRIVATE_IRQS) {
-				/* PPIs */
-				vgic_bitmap_set_irq_val(&dist->irq_cfg,
-							vcpu->vcpu_id, i,
-							VGIC_CFG_LEVEL);
-			}
-		}
-
-		vgic_enable(vcpu);
-	}
-
-out:
-	if (ret)
-		kvm_vgic_destroy(kvm);
-
-	return ret;
-}
-
-static int init_vgic_model(struct kvm *kvm, int type)
-{
-	switch (type) {
-	case KVM_DEV_TYPE_ARM_VGIC_V2:
-		vgic_v2_init_emulation(kvm);
-		break;
-#ifdef CONFIG_KVM_ARM_VGIC_V3
-	case KVM_DEV_TYPE_ARM_VGIC_V3:
-		vgic_v3_init_emulation(kvm);
-		break;
-#endif
-	default:
-		return -ENODEV;
-	}
-
-	if (atomic_read(&kvm->online_vcpus) > kvm->arch.max_vcpus)
-		return -E2BIG;
-
-	return 0;
-}
-
-/**
- * kvm_vgic_early_init - Earliest possible vgic initialization stage
- *
- * No memory allocation should be performed here, only static init.
- */
-void kvm_vgic_early_init(struct kvm *kvm)
-{
-	spin_lock_init(&kvm->arch.vgic.lock);
-	spin_lock_init(&kvm->arch.vgic.irq_phys_map_lock);
-	INIT_LIST_HEAD(&kvm->arch.vgic.irq_phys_map_list);
-}
-
-int kvm_vgic_create(struct kvm *kvm, u32 type)
-{
-	int i, vcpu_lock_idx = -1, ret;
-	struct kvm_vcpu *vcpu;
-
-	mutex_lock(&kvm->lock);
-
-	if (irqchip_in_kernel(kvm)) {
-		ret = -EEXIST;
-		goto out;
-	}
-
-	/*
-	 * This function is also called by the KVM_CREATE_IRQCHIP handler,
-	 * which had no chance yet to check the availability of the GICv2
-	 * emulation. So check this here again. KVM_CREATE_DEVICE does
-	 * the proper checks already.
-	 */
-	if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !vgic->can_emulate_gicv2) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	/*
-	 * Any time a vcpu is run, vcpu_load is called which tries to grab the
-	 * vcpu->mutex.  By grabbing the vcpu->mutex of all VCPUs we ensure
-	 * that no other VCPUs are run while we create the vgic.
-	 */
-	ret = -EBUSY;
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (!mutex_trylock(&vcpu->mutex))
-			goto out_unlock;
-		vcpu_lock_idx = i;
-	}
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (vcpu->arch.has_run_once)
-			goto out_unlock;
-	}
-	ret = 0;
-
-	ret = init_vgic_model(kvm, type);
-	if (ret)
-		goto out_unlock;
-
-	kvm->arch.vgic.in_kernel = true;
-	kvm->arch.vgic.vgic_model = type;
-	kvm->arch.vgic.vctrl_base = vgic->vctrl_base;
-	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
-	kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
-	kvm->arch.vgic.vgic_redist_base = VGIC_ADDR_UNDEF;
-
-out_unlock:
-	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
-		vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
-		mutex_unlock(&vcpu->mutex);
-	}
-
-out:
-	mutex_unlock(&kvm->lock);
-	return ret;
-}
-
-static int vgic_ioaddr_overlap(struct kvm *kvm)
-{
-	phys_addr_t dist = kvm->arch.vgic.vgic_dist_base;
-	phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base;
-
-	if (IS_VGIC_ADDR_UNDEF(dist) || IS_VGIC_ADDR_UNDEF(cpu))
-		return 0;
-	if ((dist <= cpu && dist + KVM_VGIC_V2_DIST_SIZE > cpu) ||
-	    (cpu <= dist && cpu + KVM_VGIC_V2_CPU_SIZE > dist))
-		return -EBUSY;
-	return 0;
-}
-
-static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
-			      phys_addr_t addr, phys_addr_t size)
-{
-	int ret;
-
-	if (addr & ~KVM_PHYS_MASK)
-		return -E2BIG;
-
-	if (addr & (SZ_4K - 1))
-		return -EINVAL;
-
-	if (!IS_VGIC_ADDR_UNDEF(*ioaddr))
-		return -EEXIST;
-	if (addr + size < addr)
-		return -EINVAL;
-
-	*ioaddr = addr;
-	ret = vgic_ioaddr_overlap(kvm);
-	if (ret)
-		*ioaddr = VGIC_ADDR_UNDEF;
-
-	return ret;
-}
-
-/**
- * kvm_vgic_addr - set or get vgic VM base addresses
- * @kvm:   pointer to the vm struct
- * @type:  the VGIC addr type, one of KVM_VGIC_V[23]_ADDR_TYPE_XXX
- * @addr:  pointer to address value
- * @write: if true set the address in the VM address space, if false read the
- *          address
- *
- * Set or get the vgic base addresses for the distributor and the virtual CPU
- * interface in the VM physical address space.  These addresses are properties
- * of the emulated core/SoC and therefore user space initially knows this
- * information.
- */
-int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
-{
-	int r = 0;
-	struct vgic_dist *vgic = &kvm->arch.vgic;
-	int type_needed;
-	phys_addr_t *addr_ptr, block_size;
-	phys_addr_t alignment;
-
-	mutex_lock(&kvm->lock);
-	switch (type) {
-	case KVM_VGIC_V2_ADDR_TYPE_DIST:
-		type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
-		addr_ptr = &vgic->vgic_dist_base;
-		block_size = KVM_VGIC_V2_DIST_SIZE;
-		alignment = SZ_4K;
-		break;
-	case KVM_VGIC_V2_ADDR_TYPE_CPU:
-		type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
-		addr_ptr = &vgic->vgic_cpu_base;
-		block_size = KVM_VGIC_V2_CPU_SIZE;
-		alignment = SZ_4K;
-		break;
-#ifdef CONFIG_KVM_ARM_VGIC_V3
-	case KVM_VGIC_V3_ADDR_TYPE_DIST:
-		type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
-		addr_ptr = &vgic->vgic_dist_base;
-		block_size = KVM_VGIC_V3_DIST_SIZE;
-		alignment = SZ_64K;
-		break;
-	case KVM_VGIC_V3_ADDR_TYPE_REDIST:
-		type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
-		addr_ptr = &vgic->vgic_redist_base;
-		block_size = KVM_VGIC_V3_REDIST_SIZE;
-		alignment = SZ_64K;
-		break;
-#endif
-	default:
-		r = -ENODEV;
-		goto out;
-	}
-
-	if (vgic->vgic_model != type_needed) {
-		r = -ENODEV;
-		goto out;
-	}
-
-	if (write) {
-		if (!IS_ALIGNED(*addr, alignment))
-			r = -EINVAL;
-		else
-			r = vgic_ioaddr_assign(kvm, addr_ptr, *addr,
-					       block_size);
-	} else {
-		*addr = *addr_ptr;
-	}
-
-out:
-	mutex_unlock(&kvm->lock);
-	return r;
-}
-
-int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
-{
-	int r;
-
-	switch (attr->group) {
-	case KVM_DEV_ARM_VGIC_GRP_ADDR: {
-		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
-		u64 addr;
-		unsigned long type = (unsigned long)attr->attr;
-
-		if (copy_from_user(&addr, uaddr, sizeof(addr)))
-			return -EFAULT;
-
-		r = kvm_vgic_addr(dev->kvm, type, &addr, true);
-		return (r == -ENODEV) ? -ENXIO : r;
-	}
-	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
-		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
-		u32 val;
-		int ret = 0;
-
-		if (get_user(val, uaddr))
-			return -EFAULT;
-
-		/*
-		 * We require:
-		 * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs
-		 * - at most 1024 interrupts
-		 * - a multiple of 32 interrupts
-		 */
-		if (val < (VGIC_NR_PRIVATE_IRQS + 32) ||
-		    val > VGIC_MAX_IRQS ||
-		    (val & 31))
-			return -EINVAL;
-
-		mutex_lock(&dev->kvm->lock);
-
-		if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_irqs)
-			ret = -EBUSY;
-		else
-			dev->kvm->arch.vgic.nr_irqs = val;
-
-		mutex_unlock(&dev->kvm->lock);
-
-		return ret;
-	}
-	case KVM_DEV_ARM_VGIC_GRP_CTRL: {
-		switch (attr->attr) {
-		case KVM_DEV_ARM_VGIC_CTRL_INIT:
-			r = vgic_init(dev->kvm);
-			return r;
-		}
-		break;
-	}
-	}
-
-	return -ENXIO;
-}
-
-int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
-{
-	int r = -ENXIO;
-
-	switch (attr->group) {
-	case KVM_DEV_ARM_VGIC_GRP_ADDR: {
-		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
-		u64 addr;
-		unsigned long type = (unsigned long)attr->attr;
-
-		r = kvm_vgic_addr(dev->kvm, type, &addr, false);
-		if (r)
-			return (r == -ENODEV) ? -ENXIO : r;
-
-		if (copy_to_user(uaddr, &addr, sizeof(addr)))
-			return -EFAULT;
-		break;
-	}
-	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
-		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
-
-		r = put_user(dev->kvm->arch.vgic.nr_irqs, uaddr);
-		break;
-	}
-
-	}
-
-	return r;
-}
-
-int vgic_has_attr_regs(const struct vgic_io_range *ranges, phys_addr_t offset)
-{
-	if (vgic_find_range(ranges, 4, offset))
-		return 0;
-	else
-		return -ENXIO;
-}
-
-static int vgic_starting_cpu(unsigned int cpu)
-{
-	enable_percpu_irq(vgic->maint_irq, 0);
-	return 0;
-}
-
-static int vgic_dying_cpu(unsigned int cpu)
-{
-	disable_percpu_irq(vgic->maint_irq);
-	return 0;
-}
-
-static int kvm_vgic_probe(void)
-{
-	const struct gic_kvm_info *gic_kvm_info;
-	int ret;
-
-	gic_kvm_info = gic_get_kvm_info();
-	if (!gic_kvm_info)
-		return -ENODEV;
-
-	switch (gic_kvm_info->type) {
-	case GIC_V2:
-		ret = vgic_v2_probe(gic_kvm_info, &vgic_ops, &vgic);
-		break;
-	case GIC_V3:
-		ret = vgic_v3_probe(gic_kvm_info, &vgic_ops, &vgic);
-		break;
-	default:
-		ret = -ENODEV;
-	}
-
-	return ret;
-}
-
-int kvm_vgic_hyp_init(void)
-{
-	int ret;
-
-	ret = kvm_vgic_probe();
-	if (ret) {
-		kvm_err("error: KVM vGIC probing failed\n");
-		return ret;
-	}
-
-	ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
-				 "vgic", kvm_get_running_vcpus());
-	if (ret) {
-		kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
-		return ret;
-	}
-
-	cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_STARTING,
-			  "AP_KVM_ARM_VGIC_STARTING", vgic_starting_cpu,
-			  vgic_dying_cpu);
-	return 0;
-}
-
-int kvm_irq_map_gsi(struct kvm *kvm,
-		    struct kvm_kernel_irq_routing_entry *entries,
-		    int gsi)
-{
-	return 0;
-}
-
-int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
-{
-	return pin;
-}
-
-int kvm_set_irq(struct kvm *kvm, int irq_source_id,
-		u32 irq, int level, bool line_status)
-{
-	unsigned int spi = irq + VGIC_NR_PRIVATE_IRQS;
-
-	trace_kvm_set_irq(irq, level, irq_source_id);
-
-	BUG_ON(!vgic_initialized(kvm));
-
-	return kvm_vgic_inject_irq(kvm, 0, spi, level);
-}
-
-/* MSI not implemented yet */
-int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
-		struct kvm *kvm, int irq_source_id,
-		int level, bool line_status)
-{
-	return 0;
-}
diff --git a/virt/kvm/arm/vgic.h b/virt/kvm/arm/vgic.h
deleted file mode 100644
index 0df74cbb6200..000000000000
--- a/virt/kvm/arm/vgic.h
+++ /dev/null
@@ -1,140 +0,0 @@
-/*
- * Copyright (C) 2012-2014 ARM Ltd.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * Derived from virt/kvm/arm/vgic.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __KVM_VGIC_H__
-#define __KVM_VGIC_H__
-
-#include <kvm/iodev.h>
-
-#define VGIC_ADDR_UNDEF		(-1)
-#define IS_VGIC_ADDR_UNDEF(_x)  ((_x) == VGIC_ADDR_UNDEF)
-
-#define PRODUCT_ID_KVM		0x4b	/* ASCII code K */
-#define IMPLEMENTER_ARM		0x43b
-
-#define ACCESS_READ_VALUE	(1 << 0)
-#define ACCESS_READ_RAZ		(0 << 0)
-#define ACCESS_READ_MASK(x)	((x) & (1 << 0))
-#define ACCESS_WRITE_IGNORED	(0 << 1)
-#define ACCESS_WRITE_SETBIT	(1 << 1)
-#define ACCESS_WRITE_CLEARBIT	(2 << 1)
-#define ACCESS_WRITE_VALUE	(3 << 1)
-#define ACCESS_WRITE_MASK(x)	((x) & (3 << 1))
-
-#define VCPU_NOT_ALLOCATED	((u8)-1)
-
-unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x);
-
-void vgic_update_state(struct kvm *kvm);
-int vgic_init_common_maps(struct kvm *kvm);
-
-u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x, int cpuid, u32 offset);
-u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset);
-
-void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq);
-void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq);
-void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq);
-void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
-			     int irq, int val);
-
-void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
-void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
-
-bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq);
-void vgic_unqueue_irqs(struct kvm_vcpu *vcpu);
-
-struct kvm_exit_mmio {
-	phys_addr_t	phys_addr;
-	void		*data;
-	u32		len;
-	bool		is_write;
-	void		*private;
-};
-
-void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg,
-		     phys_addr_t offset, int mode);
-bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
-			phys_addr_t offset);
-
-static inline
-u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask)
-{
-	return le32_to_cpu(*((u32 *)mmio->data)) & mask;
-}
-
-static inline
-void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value)
-{
-	*((u32 *)mmio->data) = cpu_to_le32(value) & mask;
-}
-
-struct vgic_io_range {
-	phys_addr_t base;
-	unsigned long len;
-	int bits_per_irq;
-	bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
-			    phys_addr_t offset);
-};
-
-int vgic_register_kvm_io_dev(struct kvm *kvm, gpa_t base, int len,
-			     const struct vgic_io_range *ranges,
-			     int redist_id,
-			     struct vgic_io_device *iodev);
-
-static inline bool is_in_range(phys_addr_t addr, unsigned long len,
-			       phys_addr_t baseaddr, unsigned long size)
-{
-	return (addr >= baseaddr) && (addr + len <= baseaddr + size);
-}
-
-const
-struct vgic_io_range *vgic_find_range(const struct vgic_io_range *ranges,
-				      int len, gpa_t offset);
-
-bool vgic_handle_enable_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
-			    phys_addr_t offset, int vcpu_id, int access);
-
-bool vgic_handle_set_pending_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
-				 phys_addr_t offset, int vcpu_id);
-
-bool vgic_handle_clear_pending_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio,
-				   phys_addr_t offset, int vcpu_id);
-
-bool vgic_handle_set_active_reg(struct kvm *kvm,
-				struct kvm_exit_mmio *mmio,
-				phys_addr_t offset, int vcpu_id);
-
-bool vgic_handle_clear_active_reg(struct kvm *kvm,
-				  struct kvm_exit_mmio *mmio,
-				  phys_addr_t offset, int vcpu_id);
-
-bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio,
-			 phys_addr_t offset);
-
-void vgic_kick_vcpus(struct kvm *kvm);
-
-int vgic_has_attr_regs(const struct vgic_io_range *ranges, phys_addr_t offset);
-int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr);
-int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr);
-
-int vgic_init(struct kvm *kvm);
-void vgic_v2_init_emulation(struct kvm *kvm);
-void vgic_v3_init_emulation(struct kvm *kvm);
-
-#endif
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 2c7f0d5a62ea..1e30ce08700d 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -157,6 +157,9 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 	struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0);
 	int i;
 
+	INIT_LIST_HEAD(&dist->lpi_list_head);
+	spin_lock_init(&dist->lpi_list_lock);
+
 	dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL);
 	if (!dist->spis)
 		return  -ENOMEM;
@@ -177,6 +180,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 		spin_lock_init(&irq->irq_lock);
 		irq->vcpu = NULL;
 		irq->target_vcpu = vcpu0;
+		kref_init(&irq->refcount);
 		if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2)
 			irq->targets = 0;
 		else
@@ -211,6 +215,7 @@ static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 		irq->vcpu = NULL;
 		irq->target_vcpu = vcpu;
 		irq->targets = 1U << vcpu->vcpu_id;
+		kref_init(&irq->refcount);
 		if (vgic_irq_is_sgi(i)) {
 			/* SGIs */
 			irq->enabled = 1;
@@ -253,6 +258,9 @@ int vgic_init(struct kvm *kvm)
 	if (ret)
 		goto out;
 
+	if (vgic_has_its(kvm))
+		dist->msis_require_devid = true;
+
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_vgic_vcpu_init(vcpu);
 
@@ -271,7 +279,6 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm)
 	dist->initialized = false;
 
 	kfree(dist->spis);
-	kfree(dist->redist_iodevs);
 	dist->nr_spis = 0;
 
 	mutex_unlock(&kvm->lock);
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
new file mode 100644
index 000000000000..07411cf967b9
--- /dev/null
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -0,0 +1,1500 @@
+/*
+ * GICv3 ITS emulation
+ *
+ * Copyright (C) 2015,2016 ARM Ltd.
+ * Author: Andre Przywara <andre.przywara@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/uaccess.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+#include "vgic.h"
+#include "vgic-mmio.h"
+
+/*
+ * Creates a new (reference to a) struct vgic_irq for a given LPI.
+ * If this LPI is already mapped on another ITS, we increase its refcount
+ * and return a pointer to the existing structure.
+ * If this is a "new" LPI, we allocate and initialize a new struct vgic_irq.
+ * This function returns a pointer to the _unlocked_ structure.
+ */
+static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq;
+
+	/* In this case there is no put, since we keep the reference. */
+	if (irq)
+		return irq;
+
+	irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL);
+	if (!irq)
+		return NULL;
+
+	INIT_LIST_HEAD(&irq->lpi_list);
+	INIT_LIST_HEAD(&irq->ap_list);
+	spin_lock_init(&irq->irq_lock);
+
+	irq->config = VGIC_CONFIG_EDGE;
+	kref_init(&irq->refcount);
+	irq->intid = intid;
+
+	spin_lock(&dist->lpi_list_lock);
+
+	/*
+	 * There could be a race with another vgic_add_lpi(), so we need to
+	 * check that we don't add a second list entry with the same LPI.
+	 */
+	list_for_each_entry(oldirq, &dist->lpi_list_head, lpi_list) {
+		if (oldirq->intid != intid)
+			continue;
+
+		/* Someone was faster with adding this LPI, lets use that. */
+		kfree(irq);
+		irq = oldirq;
+
+		/*
+		 * This increases the refcount, the caller is expected to
+		 * call vgic_put_irq() on the returned pointer once it's
+		 * finished with the IRQ.
+		 */
+		vgic_get_irq_kref(irq);
+
+		goto out_unlock;
+	}
+
+	list_add_tail(&irq->lpi_list, &dist->lpi_list_head);
+	dist->lpi_list_count++;
+
+out_unlock:
+	spin_unlock(&dist->lpi_list_lock);
+
+	return irq;
+}
+
+struct its_device {
+	struct list_head dev_list;
+
+	/* the head for the list of ITTEs */
+	struct list_head itt_head;
+	u32 device_id;
+};
+
+#define COLLECTION_NOT_MAPPED ((u32)~0)
+
+struct its_collection {
+	struct list_head coll_list;
+
+	u32 collection_id;
+	u32 target_addr;
+};
+
+#define its_is_collection_mapped(coll) ((coll) && \
+				((coll)->target_addr != COLLECTION_NOT_MAPPED))
+
+struct its_itte {
+	struct list_head itte_list;
+
+	struct vgic_irq *irq;
+	struct its_collection *collection;
+	u32 lpi;
+	u32 event_id;
+};
+
+/*
+ * Find and returns a device in the device table for an ITS.
+ * Must be called with the its_lock mutex held.
+ */
+static struct its_device *find_its_device(struct vgic_its *its, u32 device_id)
+{
+	struct its_device *device;
+
+	list_for_each_entry(device, &its->device_list, dev_list)
+		if (device_id == device->device_id)
+			return device;
+
+	return NULL;
+}
+
+/*
+ * Find and returns an interrupt translation table entry (ITTE) for a given
+ * Device ID/Event ID pair on an ITS.
+ * Must be called with the its_lock mutex held.
+ */
+static struct its_itte *find_itte(struct vgic_its *its, u32 device_id,
+				  u32 event_id)
+{
+	struct its_device *device;
+	struct its_itte *itte;
+
+	device = find_its_device(its, device_id);
+	if (device == NULL)
+		return NULL;
+
+	list_for_each_entry(itte, &device->itt_head, itte_list)
+		if (itte->event_id == event_id)
+			return itte;
+
+	return NULL;
+}
+
+/* To be used as an iterator this macro misses the enclosing parentheses */
+#define for_each_lpi_its(dev, itte, its) \
+	list_for_each_entry(dev, &(its)->device_list, dev_list) \
+		list_for_each_entry(itte, &(dev)->itt_head, itte_list)
+
+/*
+ * We only implement 48 bits of PA at the moment, although the ITS
+ * supports more. Let's be restrictive here.
+ */
+#define BASER_ADDRESS(x)	((x) & GENMASK_ULL(47, 16))
+#define CBASER_ADDRESS(x)	((x) & GENMASK_ULL(47, 12))
+#define PENDBASER_ADDRESS(x)	((x) & GENMASK_ULL(47, 16))
+#define PROPBASER_ADDRESS(x)	((x) & GENMASK_ULL(47, 12))
+
+#define GIC_LPI_OFFSET 8192
+
+/*
+ * Finds and returns a collection in the ITS collection table.
+ * Must be called with the its_lock mutex held.
+ */
+static struct its_collection *find_collection(struct vgic_its *its, int coll_id)
+{
+	struct its_collection *collection;
+
+	list_for_each_entry(collection, &its->collection_list, coll_list) {
+		if (coll_id == collection->collection_id)
+			return collection;
+	}
+
+	return NULL;
+}
+
+#define LPI_PROP_ENABLE_BIT(p)	((p) & LPI_PROP_ENABLED)
+#define LPI_PROP_PRIORITY(p)	((p) & 0xfc)
+
+/*
+ * Reads the configuration data for a given LPI from guest memory and
+ * updates the fields in struct vgic_irq.
+ * If filter_vcpu is not NULL, applies only if the IRQ is targeting this
+ * VCPU. Unconditionally applies if filter_vcpu is NULL.
+ */
+static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
+			     struct kvm_vcpu *filter_vcpu)
+{
+	u64 propbase = PROPBASER_ADDRESS(kvm->arch.vgic.propbaser);
+	u8 prop;
+	int ret;
+
+	ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
+			     &prop, 1);
+
+	if (ret)
+		return ret;
+
+	spin_lock(&irq->irq_lock);
+
+	if (!filter_vcpu || filter_vcpu == irq->target_vcpu) {
+		irq->priority = LPI_PROP_PRIORITY(prop);
+		irq->enabled = LPI_PROP_ENABLE_BIT(prop);
+
+		vgic_queue_irq_unlock(kvm, irq);
+	} else {
+		spin_unlock(&irq->irq_lock);
+	}
+
+	return 0;
+}
+
+/*
+ * Create a snapshot of the current LPI list, so that we can enumerate all
+ * LPIs without holding any lock.
+ * Returns the array length and puts the kmalloc'ed array into intid_ptr.
+ */
+static int vgic_copy_lpi_list(struct kvm *kvm, u32 **intid_ptr)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct vgic_irq *irq;
+	u32 *intids;
+	int irq_count = dist->lpi_list_count, i = 0;
+
+	/*
+	 * We use the current value of the list length, which may change
+	 * after the kmalloc. We don't care, because the guest shouldn't
+	 * change anything while the command handling is still running,
+	 * and in the worst case we would miss a new IRQ, which one wouldn't
+	 * expect to be covered by this command anyway.
+	 */
+	intids = kmalloc_array(irq_count, sizeof(intids[0]), GFP_KERNEL);
+	if (!intids)
+		return -ENOMEM;
+
+	spin_lock(&dist->lpi_list_lock);
+	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
+		/* We don't need to "get" the IRQ, as we hold the list lock. */
+		intids[i] = irq->intid;
+		if (++i == irq_count)
+			break;
+	}
+	spin_unlock(&dist->lpi_list_lock);
+
+	*intid_ptr = intids;
+	return irq_count;
+}
+
+/*
+ * Promotes the ITS view of affinity of an ITTE (which redistributor this LPI
+ * is targeting) to the VGIC's view, which deals with target VCPUs.
+ * Needs to be called whenever either the collection for a LPIs has
+ * changed or the collection itself got retargeted.
+ */
+static void update_affinity_itte(struct kvm *kvm, struct its_itte *itte)
+{
+	struct kvm_vcpu *vcpu;
+
+	if (!its_is_collection_mapped(itte->collection))
+		return;
+
+	vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
+
+	spin_lock(&itte->irq->irq_lock);
+	itte->irq->target_vcpu = vcpu;
+	spin_unlock(&itte->irq->irq_lock);
+}
+
+/*
+ * Updates the target VCPU for every LPI targeting this collection.
+ * Must be called with the its_lock mutex held.
+ */
+static void update_affinity_collection(struct kvm *kvm, struct vgic_its *its,
+				       struct its_collection *coll)
+{
+	struct its_device *device;
+	struct its_itte *itte;
+
+	for_each_lpi_its(device, itte, its) {
+		if (!itte->collection || coll != itte->collection)
+			continue;
+
+		update_affinity_itte(kvm, itte);
+	}
+}
+
+static u32 max_lpis_propbaser(u64 propbaser)
+{
+	int nr_idbits = (propbaser & 0x1f) + 1;
+
+	return 1U << min(nr_idbits, INTERRUPT_ID_BITS_ITS);
+}
+
+/*
+ * Scan the whole LPI pending table and sync the pending bit in there
+ * with our own data structures. This relies on the LPI being
+ * mapped before.
+ */
+static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
+{
+	gpa_t pendbase = PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+	struct vgic_irq *irq;
+	int last_byte_offset = -1;
+	int ret = 0;
+	u32 *intids;
+	int nr_irqs, i;
+
+	nr_irqs = vgic_copy_lpi_list(vcpu->kvm, &intids);
+	if (nr_irqs < 0)
+		return nr_irqs;
+
+	for (i = 0; i < nr_irqs; i++) {
+		int byte_offset, bit_nr;
+		u8 pendmask;
+
+		byte_offset = intids[i] / BITS_PER_BYTE;
+		bit_nr = intids[i] % BITS_PER_BYTE;
+
+		/*
+		 * For contiguously allocated LPIs chances are we just read
+		 * this very same byte in the last iteration. Reuse that.
+		 */
+		if (byte_offset != last_byte_offset) {
+			ret = kvm_read_guest(vcpu->kvm, pendbase + byte_offset,
+					     &pendmask, 1);
+			if (ret) {
+				kfree(intids);
+				return ret;
+			}
+			last_byte_offset = byte_offset;
+		}
+
+		irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]);
+		spin_lock(&irq->irq_lock);
+		irq->pending = pendmask & (1U << bit_nr);
+		vgic_queue_irq_unlock(vcpu->kvm, irq);
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+
+	kfree(intids);
+
+	return ret;
+}
+
+static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu,
+					     struct vgic_its *its,
+					     gpa_t addr, unsigned int len)
+{
+	u32 reg = 0;
+
+	mutex_lock(&its->cmd_lock);
+	if (its->creadr == its->cwriter)
+		reg |= GITS_CTLR_QUIESCENT;
+	if (its->enabled)
+		reg |= GITS_CTLR_ENABLE;
+	mutex_unlock(&its->cmd_lock);
+
+	return reg;
+}
+
+static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
+				     gpa_t addr, unsigned int len,
+				     unsigned long val)
+{
+	its->enabled = !!(val & GITS_CTLR_ENABLE);
+}
+
+static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm,
+					      struct vgic_its *its,
+					      gpa_t addr, unsigned int len)
+{
+	u64 reg = GITS_TYPER_PLPIS;
+
+	/*
+	 * We use linear CPU numbers for redistributor addressing,
+	 * so GITS_TYPER.PTA is 0.
+	 * Also we force all PROPBASER registers to be the same, so
+	 * CommonLPIAff is 0 as well.
+	 * To avoid memory waste in the guest, we keep the number of IDBits and
+	 * DevBits low - as least for the time being.
+	 */
+	reg |= 0x0f << GITS_TYPER_DEVBITS_SHIFT;
+	reg |= 0x0f << GITS_TYPER_IDBITS_SHIFT;
+
+	return extract_bytes(reg, addr & 7, len);
+}
+
+static unsigned long vgic_mmio_read_its_iidr(struct kvm *kvm,
+					     struct vgic_its *its,
+					     gpa_t addr, unsigned int len)
+{
+	return (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
+}
+
+static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm,
+					       struct vgic_its *its,
+					       gpa_t addr, unsigned int len)
+{
+	switch (addr & 0xffff) {
+	case GITS_PIDR0:
+		return 0x92;	/* part number, bits[7:0] */
+	case GITS_PIDR1:
+		return 0xb4;	/* part number, bits[11:8] */
+	case GITS_PIDR2:
+		return GIC_PIDR2_ARCH_GICv3 | 0x0b;
+	case GITS_PIDR4:
+		return 0x40;	/* This is a 64K software visible page */
+	/* The following are the ID registers for (any) GIC. */
+	case GITS_CIDR0:
+		return 0x0d;
+	case GITS_CIDR1:
+		return 0xf0;
+	case GITS_CIDR2:
+		return 0x05;
+	case GITS_CIDR3:
+		return 0xb1;
+	}
+
+	return 0;
+}
+
+/*
+ * Find the target VCPU and the LPI number for a given devid/eventid pair
+ * and make this IRQ pending, possibly injecting it.
+ * Must be called with the its_lock mutex held.
+ */
+static void vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
+				 u32 devid, u32 eventid)
+{
+	struct its_itte *itte;
+
+	if (!its->enabled)
+		return;
+
+	itte = find_itte(its, devid, eventid);
+	/* Triggering an unmapped IRQ gets silently dropped. */
+	if (itte && its_is_collection_mapped(itte->collection)) {
+		struct kvm_vcpu *vcpu;
+
+		vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
+		if (vcpu && vcpu->arch.vgic_cpu.lpis_enabled) {
+			spin_lock(&itte->irq->irq_lock);
+			itte->irq->pending = true;
+			vgic_queue_irq_unlock(kvm, itte->irq);
+		}
+	}
+}
+
+/*
+ * Queries the KVM IO bus framework to get the ITS pointer from the given
+ * doorbell address.
+ * We then call vgic_its_trigger_msi() with the decoded data.
+ */
+int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
+{
+	u64 address;
+	struct kvm_io_device *kvm_io_dev;
+	struct vgic_io_device *iodev;
+
+	if (!vgic_has_its(kvm))
+		return -ENODEV;
+
+	if (!(msi->flags & KVM_MSI_VALID_DEVID))
+		return -EINVAL;
+
+	address = (u64)msi->address_hi << 32 | msi->address_lo;
+
+	kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address);
+	if (!kvm_io_dev)
+		return -ENODEV;
+
+	iodev = container_of(kvm_io_dev, struct vgic_io_device, dev);
+
+	mutex_lock(&iodev->its->its_lock);
+	vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data);
+	mutex_unlock(&iodev->its->its_lock);
+
+	return 0;
+}
+
+/* Requires the its_lock to be held. */
+static void its_free_itte(struct kvm *kvm, struct its_itte *itte)
+{
+	list_del(&itte->itte_list);
+
+	/* This put matches the get in vgic_add_lpi. */
+	vgic_put_irq(kvm, itte->irq);
+
+	kfree(itte);
+}
+
+static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size)
+{
+	return (le64_to_cpu(its_cmd[word]) >> shift) & (BIT_ULL(size) - 1);
+}
+
+#define its_cmd_get_command(cmd)	its_cmd_mask_field(cmd, 0,  0,  8)
+#define its_cmd_get_deviceid(cmd)	its_cmd_mask_field(cmd, 0, 32, 32)
+#define its_cmd_get_id(cmd)		its_cmd_mask_field(cmd, 1,  0, 32)
+#define its_cmd_get_physical_id(cmd)	its_cmd_mask_field(cmd, 1, 32, 32)
+#define its_cmd_get_collection(cmd)	its_cmd_mask_field(cmd, 2,  0, 16)
+#define its_cmd_get_target_addr(cmd)	its_cmd_mask_field(cmd, 2, 16, 32)
+#define its_cmd_get_validbit(cmd)	its_cmd_mask_field(cmd, 2, 63,  1)
+
+/*
+ * The DISCARD command frees an Interrupt Translation Table Entry (ITTE).
+ * Must be called with the its_lock mutex held.
+ */
+static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its,
+				       u64 *its_cmd)
+{
+	u32 device_id = its_cmd_get_deviceid(its_cmd);
+	u32 event_id = its_cmd_get_id(its_cmd);
+	struct its_itte *itte;
+
+
+	itte = find_itte(its, device_id, event_id);
+	if (itte && itte->collection) {
+		/*
+		 * Though the spec talks about removing the pending state, we
+		 * don't bother here since we clear the ITTE anyway and the
+		 * pending state is a property of the ITTE struct.
+		 */
+		its_free_itte(kvm, itte);
+		return 0;
+	}
+
+	return E_ITS_DISCARD_UNMAPPED_INTERRUPT;
+}
+
+/*
+ * The MOVI command moves an ITTE to a different collection.
+ * Must be called with the its_lock mutex held.
+ */
+static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its,
+				    u64 *its_cmd)
+{
+	u32 device_id = its_cmd_get_deviceid(its_cmd);
+	u32 event_id = its_cmd_get_id(its_cmd);
+	u32 coll_id = its_cmd_get_collection(its_cmd);
+	struct kvm_vcpu *vcpu;
+	struct its_itte *itte;
+	struct its_collection *collection;
+
+	itte = find_itte(its, device_id, event_id);
+	if (!itte)
+		return E_ITS_MOVI_UNMAPPED_INTERRUPT;
+
+	if (!its_is_collection_mapped(itte->collection))
+		return E_ITS_MOVI_UNMAPPED_COLLECTION;
+
+	collection = find_collection(its, coll_id);
+	if (!its_is_collection_mapped(collection))
+		return E_ITS_MOVI_UNMAPPED_COLLECTION;
+
+	itte->collection = collection;
+	vcpu = kvm_get_vcpu(kvm, collection->target_addr);
+
+	spin_lock(&itte->irq->irq_lock);
+	itte->irq->target_vcpu = vcpu;
+	spin_unlock(&itte->irq->irq_lock);
+
+	return 0;
+}
+
+/*
+ * Check whether an ID can be stored into the corresponding guest table.
+ * For a direct table this is pretty easy, but gets a bit nasty for
+ * indirect tables. We check whether the resulting guest physical address
+ * is actually valid (covered by a memslot and guest accessbible).
+ * For this we have to read the respective first level entry.
+ */
+static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
+{
+	int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
+	int index;
+	u64 indirect_ptr;
+	gfn_t gfn;
+
+	if (!(baser & GITS_BASER_INDIRECT)) {
+		phys_addr_t addr;
+
+		if (id >= (l1_tbl_size / GITS_BASER_ENTRY_SIZE(baser)))
+			return false;
+
+		addr = BASER_ADDRESS(baser) + id * GITS_BASER_ENTRY_SIZE(baser);
+		gfn = addr >> PAGE_SHIFT;
+
+		return kvm_is_visible_gfn(its->dev->kvm, gfn);
+	}
+
+	/* calculate and check the index into the 1st level */
+	index = id / (SZ_64K / GITS_BASER_ENTRY_SIZE(baser));
+	if (index >= (l1_tbl_size / sizeof(u64)))
+		return false;
+
+	/* Each 1st level entry is represented by a 64-bit value. */
+	if (kvm_read_guest(its->dev->kvm,
+			   BASER_ADDRESS(baser) + index * sizeof(indirect_ptr),
+			   &indirect_ptr, sizeof(indirect_ptr)))
+		return false;
+
+	indirect_ptr = le64_to_cpu(indirect_ptr);
+
+	/* check the valid bit of the first level entry */
+	if (!(indirect_ptr & BIT_ULL(63)))
+		return false;
+
+	/*
+	 * Mask the guest physical address and calculate the frame number.
+	 * Any address beyond our supported 48 bits of PA will be caught
+	 * by the actual check in the final step.
+	 */
+	indirect_ptr &= GENMASK_ULL(51, 16);
+
+	/* Find the address of the actual entry */
+	index = id % (SZ_64K / GITS_BASER_ENTRY_SIZE(baser));
+	indirect_ptr += index * GITS_BASER_ENTRY_SIZE(baser);
+	gfn = indirect_ptr >> PAGE_SHIFT;
+
+	return kvm_is_visible_gfn(its->dev->kvm, gfn);
+}
+
+static int vgic_its_alloc_collection(struct vgic_its *its,
+				     struct its_collection **colp,
+				     u32 coll_id)
+{
+	struct its_collection *collection;
+
+	if (!vgic_its_check_id(its, its->baser_coll_table, coll_id))
+		return E_ITS_MAPC_COLLECTION_OOR;
+
+	collection = kzalloc(sizeof(*collection), GFP_KERNEL);
+
+	collection->collection_id = coll_id;
+	collection->target_addr = COLLECTION_NOT_MAPPED;
+
+	list_add_tail(&collection->coll_list, &its->collection_list);
+	*colp = collection;
+
+	return 0;
+}
+
+static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id)
+{
+	struct its_collection *collection;
+	struct its_device *device;
+	struct its_itte *itte;
+
+	/*
+	 * Clearing the mapping for that collection ID removes the
+	 * entry from the list. If there wasn't any before, we can
+	 * go home early.
+	 */
+	collection = find_collection(its, coll_id);
+	if (!collection)
+		return;
+
+	for_each_lpi_its(device, itte, its)
+		if (itte->collection &&
+		    itte->collection->collection_id == coll_id)
+			itte->collection = NULL;
+
+	list_del(&collection->coll_list);
+	kfree(collection);
+}
+
+/*
+ * The MAPTI and MAPI commands map LPIs to ITTEs.
+ * Must be called with its_lock mutex held.
+ */
+static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
+				    u64 *its_cmd)
+{
+	u32 device_id = its_cmd_get_deviceid(its_cmd);
+	u32 event_id = its_cmd_get_id(its_cmd);
+	u32 coll_id = its_cmd_get_collection(its_cmd);
+	struct its_itte *itte;
+	struct its_device *device;
+	struct its_collection *collection, *new_coll = NULL;
+	int lpi_nr;
+
+	device = find_its_device(its, device_id);
+	if (!device)
+		return E_ITS_MAPTI_UNMAPPED_DEVICE;
+
+	if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI)
+		lpi_nr = its_cmd_get_physical_id(its_cmd);
+	else
+		lpi_nr = event_id;
+	if (lpi_nr < GIC_LPI_OFFSET ||
+	    lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser))
+		return E_ITS_MAPTI_PHYSICALID_OOR;
+
+	collection = find_collection(its, coll_id);
+	if (!collection) {
+		int ret = vgic_its_alloc_collection(its, &collection, coll_id);
+		if (ret)
+			return ret;
+		new_coll = collection;
+	}
+
+	itte = find_itte(its, device_id, event_id);
+	if (!itte) {
+		itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL);
+		if (!itte) {
+			if (new_coll)
+				vgic_its_free_collection(its, coll_id);
+			return -ENOMEM;
+		}
+
+		itte->event_id	= event_id;
+		list_add_tail(&itte->itte_list, &device->itt_head);
+	}
+
+	itte->collection = collection;
+	itte->lpi = lpi_nr;
+	itte->irq = vgic_add_lpi(kvm, lpi_nr);
+	update_affinity_itte(kvm, itte);
+
+	/*
+	 * We "cache" the configuration table entries in out struct vgic_irq's.
+	 * However we only have those structs for mapped IRQs, so we read in
+	 * the respective config data from memory here upon mapping the LPI.
+	 */
+	update_lpi_config(kvm, itte->irq, NULL);
+
+	return 0;
+}
+
+/* Requires the its_lock to be held. */
+static void vgic_its_unmap_device(struct kvm *kvm, struct its_device *device)
+{
+	struct its_itte *itte, *temp;
+
+	/*
+	 * The spec says that unmapping a device with still valid
+	 * ITTEs associated is UNPREDICTABLE. We remove all ITTEs,
+	 * since we cannot leave the memory unreferenced.
+	 */
+	list_for_each_entry_safe(itte, temp, &device->itt_head, itte_list)
+		its_free_itte(kvm, itte);
+
+	list_del(&device->dev_list);
+	kfree(device);
+}
+
+/*
+ * MAPD maps or unmaps a device ID to Interrupt Translation Tables (ITTs).
+ * Must be called with the its_lock mutex held.
+ */
+static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its,
+				    u64 *its_cmd)
+{
+	u32 device_id = its_cmd_get_deviceid(its_cmd);
+	bool valid = its_cmd_get_validbit(its_cmd);
+	struct its_device *device;
+
+	if (!vgic_its_check_id(its, its->baser_device_table, device_id))
+		return E_ITS_MAPD_DEVICE_OOR;
+
+	device = find_its_device(its, device_id);
+
+	/*
+	 * The spec says that calling MAPD on an already mapped device
+	 * invalidates all cached data for this device. We implement this
+	 * by removing the mapping and re-establishing it.
+	 */
+	if (device)
+		vgic_its_unmap_device(kvm, device);
+
+	/*
+	 * The spec does not say whether unmapping a not-mapped device
+	 * is an error, so we are done in any case.
+	 */
+	if (!valid)
+		return 0;
+
+	device = kzalloc(sizeof(struct its_device), GFP_KERNEL);
+	if (!device)
+		return -ENOMEM;
+
+	device->device_id = device_id;
+	INIT_LIST_HEAD(&device->itt_head);
+
+	list_add_tail(&device->dev_list, &its->device_list);
+
+	return 0;
+}
+
+/*
+ * The MAPC command maps collection IDs to redistributors.
+ * Must be called with the its_lock mutex held.
+ */
+static int vgic_its_cmd_handle_mapc(struct kvm *kvm, struct vgic_its *its,
+				    u64 *its_cmd)
+{
+	u16 coll_id;
+	u32 target_addr;
+	struct its_collection *collection;
+	bool valid;
+
+	valid = its_cmd_get_validbit(its_cmd);
+	coll_id = its_cmd_get_collection(its_cmd);
+	target_addr = its_cmd_get_target_addr(its_cmd);
+
+	if (target_addr >= atomic_read(&kvm->online_vcpus))
+		return E_ITS_MAPC_PROCNUM_OOR;
+
+	if (!valid) {
+		vgic_its_free_collection(its, coll_id);
+	} else {
+		collection = find_collection(its, coll_id);
+
+		if (!collection) {
+			int ret;
+
+			ret = vgic_its_alloc_collection(its, &collection,
+							coll_id);
+			if (ret)
+				return ret;
+			collection->target_addr = target_addr;
+		} else {
+			collection->target_addr = target_addr;
+			update_affinity_collection(kvm, its, collection);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * The CLEAR command removes the pending state for a particular LPI.
+ * Must be called with the its_lock mutex held.
+ */
+static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its,
+				     u64 *its_cmd)
+{
+	u32 device_id = its_cmd_get_deviceid(its_cmd);
+	u32 event_id = its_cmd_get_id(its_cmd);
+	struct its_itte *itte;
+
+
+	itte = find_itte(its, device_id, event_id);
+	if (!itte)
+		return E_ITS_CLEAR_UNMAPPED_INTERRUPT;
+
+	itte->irq->pending = false;
+
+	return 0;
+}
+
+/*
+ * The INV command syncs the configuration bits from the memory table.
+ * Must be called with the its_lock mutex held.
+ */
+static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its,
+				   u64 *its_cmd)
+{
+	u32 device_id = its_cmd_get_deviceid(its_cmd);
+	u32 event_id = its_cmd_get_id(its_cmd);
+	struct its_itte *itte;
+
+
+	itte = find_itte(its, device_id, event_id);
+	if (!itte)
+		return E_ITS_INV_UNMAPPED_INTERRUPT;
+
+	return update_lpi_config(kvm, itte->irq, NULL);
+}
+
+/*
+ * The INVALL command requests flushing of all IRQ data in this collection.
+ * Find the VCPU mapped to that collection, then iterate over the VM's list
+ * of mapped LPIs and update the configuration for each IRQ which targets
+ * the specified vcpu. The configuration will be read from the in-memory
+ * configuration table.
+ * Must be called with the its_lock mutex held.
+ */
+static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its,
+				      u64 *its_cmd)
+{
+	u32 coll_id = its_cmd_get_collection(its_cmd);
+	struct its_collection *collection;
+	struct kvm_vcpu *vcpu;
+	struct vgic_irq *irq;
+	u32 *intids;
+	int irq_count, i;
+
+	collection = find_collection(its, coll_id);
+	if (!its_is_collection_mapped(collection))
+		return E_ITS_INVALL_UNMAPPED_COLLECTION;
+
+	vcpu = kvm_get_vcpu(kvm, collection->target_addr);
+
+	irq_count = vgic_copy_lpi_list(kvm, &intids);
+	if (irq_count < 0)
+		return irq_count;
+
+	for (i = 0; i < irq_count; i++) {
+		irq = vgic_get_irq(kvm, NULL, intids[i]);
+		if (!irq)
+			continue;
+		update_lpi_config(kvm, irq, vcpu);
+		vgic_put_irq(kvm, irq);
+	}
+
+	kfree(intids);
+
+	return 0;
+}
+
+/*
+ * The MOVALL command moves the pending state of all IRQs targeting one
+ * redistributor to another. We don't hold the pending state in the VCPUs,
+ * but in the IRQs instead, so there is really not much to do for us here.
+ * However the spec says that no IRQ must target the old redistributor
+ * afterwards, so we make sure that no LPI is using the associated target_vcpu.
+ * This command affects all LPIs in the system that target that redistributor.
+ */
+static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its,
+				      u64 *its_cmd)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	u32 target1_addr = its_cmd_get_target_addr(its_cmd);
+	u32 target2_addr = its_cmd_mask_field(its_cmd, 3, 16, 32);
+	struct kvm_vcpu *vcpu1, *vcpu2;
+	struct vgic_irq *irq;
+
+	if (target1_addr >= atomic_read(&kvm->online_vcpus) ||
+	    target2_addr >= atomic_read(&kvm->online_vcpus))
+		return E_ITS_MOVALL_PROCNUM_OOR;
+
+	if (target1_addr == target2_addr)
+		return 0;
+
+	vcpu1 = kvm_get_vcpu(kvm, target1_addr);
+	vcpu2 = kvm_get_vcpu(kvm, target2_addr);
+
+	spin_lock(&dist->lpi_list_lock);
+
+	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
+		spin_lock(&irq->irq_lock);
+
+		if (irq->target_vcpu == vcpu1)
+			irq->target_vcpu = vcpu2;
+
+		spin_unlock(&irq->irq_lock);
+	}
+
+	spin_unlock(&dist->lpi_list_lock);
+
+	return 0;
+}
+
+/*
+ * The INT command injects the LPI associated with that DevID/EvID pair.
+ * Must be called with the its_lock mutex held.
+ */
+static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its,
+				   u64 *its_cmd)
+{
+	u32 msi_data = its_cmd_get_id(its_cmd);
+	u64 msi_devid = its_cmd_get_deviceid(its_cmd);
+
+	vgic_its_trigger_msi(kvm, its, msi_devid, msi_data);
+
+	return 0;
+}
+
+/*
+ * This function is called with the its_cmd lock held, but the ITS data
+ * structure lock dropped.
+ */
+static int vgic_its_handle_command(struct kvm *kvm, struct vgic_its *its,
+				   u64 *its_cmd)
+{
+	int ret = -ENODEV;
+
+	mutex_lock(&its->its_lock);
+	switch (its_cmd_get_command(its_cmd)) {
+	case GITS_CMD_MAPD:
+		ret = vgic_its_cmd_handle_mapd(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_MAPC:
+		ret = vgic_its_cmd_handle_mapc(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_MAPI:
+		ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_MAPTI:
+		ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_MOVI:
+		ret = vgic_its_cmd_handle_movi(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_DISCARD:
+		ret = vgic_its_cmd_handle_discard(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_CLEAR:
+		ret = vgic_its_cmd_handle_clear(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_MOVALL:
+		ret = vgic_its_cmd_handle_movall(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_INT:
+		ret = vgic_its_cmd_handle_int(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_INV:
+		ret = vgic_its_cmd_handle_inv(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_INVALL:
+		ret = vgic_its_cmd_handle_invall(kvm, its, its_cmd);
+		break;
+	case GITS_CMD_SYNC:
+		/* we ignore this command: we are in sync all of the time */
+		ret = 0;
+		break;
+	}
+	mutex_unlock(&its->its_lock);
+
+	return ret;
+}
+
+static u64 vgic_sanitise_its_baser(u64 reg)
+{
+	reg = vgic_sanitise_field(reg, GITS_BASER_SHAREABILITY_MASK,
+				  GITS_BASER_SHAREABILITY_SHIFT,
+				  vgic_sanitise_shareability);
+	reg = vgic_sanitise_field(reg, GITS_BASER_INNER_CACHEABILITY_MASK,
+				  GITS_BASER_INNER_CACHEABILITY_SHIFT,
+				  vgic_sanitise_inner_cacheability);
+	reg = vgic_sanitise_field(reg, GITS_BASER_OUTER_CACHEABILITY_MASK,
+				  GITS_BASER_OUTER_CACHEABILITY_SHIFT,
+				  vgic_sanitise_outer_cacheability);
+
+	/* Bits 15:12 contain bits 51:48 of the PA, which we don't support. */
+	reg &= ~GENMASK_ULL(15, 12);
+
+	/* We support only one (ITS) page size: 64K */
+	reg = (reg & ~GITS_BASER_PAGE_SIZE_MASK) | GITS_BASER_PAGE_SIZE_64K;
+
+	return reg;
+}
+
+static u64 vgic_sanitise_its_cbaser(u64 reg)
+{
+	reg = vgic_sanitise_field(reg, GITS_CBASER_SHAREABILITY_MASK,
+				  GITS_CBASER_SHAREABILITY_SHIFT,
+				  vgic_sanitise_shareability);
+	reg = vgic_sanitise_field(reg, GITS_CBASER_INNER_CACHEABILITY_MASK,
+				  GITS_CBASER_INNER_CACHEABILITY_SHIFT,
+				  vgic_sanitise_inner_cacheability);
+	reg = vgic_sanitise_field(reg, GITS_CBASER_OUTER_CACHEABILITY_MASK,
+				  GITS_CBASER_OUTER_CACHEABILITY_SHIFT,
+				  vgic_sanitise_outer_cacheability);
+
+	/*
+	 * Sanitise the physical address to be 64k aligned.
+	 * Also limit the physical addresses to 48 bits.
+	 */
+	reg &= ~(GENMASK_ULL(51, 48) | GENMASK_ULL(15, 12));
+
+	return reg;
+}
+
+static unsigned long vgic_mmio_read_its_cbaser(struct kvm *kvm,
+					       struct vgic_its *its,
+					       gpa_t addr, unsigned int len)
+{
+	return extract_bytes(its->cbaser, addr & 7, len);
+}
+
+static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its,
+				       gpa_t addr, unsigned int len,
+				       unsigned long val)
+{
+	/* When GITS_CTLR.Enable is 1, this register is RO. */
+	if (its->enabled)
+		return;
+
+	mutex_lock(&its->cmd_lock);
+	its->cbaser = update_64bit_reg(its->cbaser, addr & 7, len, val);
+	its->cbaser = vgic_sanitise_its_cbaser(its->cbaser);
+	its->creadr = 0;
+	/*
+	 * CWRITER is architecturally UNKNOWN on reset, but we need to reset
+	 * it to CREADR to make sure we start with an empty command buffer.
+	 */
+	its->cwriter = its->creadr;
+	mutex_unlock(&its->cmd_lock);
+}
+
+#define ITS_CMD_BUFFER_SIZE(baser)	((((baser) & 0xff) + 1) << 12)
+#define ITS_CMD_SIZE			32
+#define ITS_CMD_OFFSET(reg)		((reg) & GENMASK(19, 5))
+
+/*
+ * By writing to CWRITER the guest announces new commands to be processed.
+ * To avoid any races in the first place, we take the its_cmd lock, which
+ * protects our ring buffer variables, so that there is only one user
+ * per ITS handling commands at a given time.
+ */
+static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its,
+					gpa_t addr, unsigned int len,
+					unsigned long val)
+{
+	gpa_t cbaser;
+	u64 cmd_buf[4];
+	u32 reg;
+
+	if (!its)
+		return;
+
+	mutex_lock(&its->cmd_lock);
+
+	reg = update_64bit_reg(its->cwriter, addr & 7, len, val);
+	reg = ITS_CMD_OFFSET(reg);
+	if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
+		mutex_unlock(&its->cmd_lock);
+		return;
+	}
+
+	its->cwriter = reg;
+	cbaser = CBASER_ADDRESS(its->cbaser);
+
+	while (its->cwriter != its->creadr) {
+		int ret = kvm_read_guest(kvm, cbaser + its->creadr,
+					 cmd_buf, ITS_CMD_SIZE);
+		/*
+		 * If kvm_read_guest() fails, this could be due to the guest
+		 * programming a bogus value in CBASER or something else going
+		 * wrong from which we cannot easily recover.
+		 * According to section 6.3.2 in the GICv3 spec we can just
+		 * ignore that command then.
+		 */
+		if (!ret)
+			vgic_its_handle_command(kvm, its, cmd_buf);
+
+		its->creadr += ITS_CMD_SIZE;
+		if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser))
+			its->creadr = 0;
+	}
+
+	mutex_unlock(&its->cmd_lock);
+}
+
+static unsigned long vgic_mmio_read_its_cwriter(struct kvm *kvm,
+						struct vgic_its *its,
+						gpa_t addr, unsigned int len)
+{
+	return extract_bytes(its->cwriter, addr & 0x7, len);
+}
+
+static unsigned long vgic_mmio_read_its_creadr(struct kvm *kvm,
+					       struct vgic_its *its,
+					       gpa_t addr, unsigned int len)
+{
+	return extract_bytes(its->creadr, addr & 0x7, len);
+}
+
+#define BASER_INDEX(addr) (((addr) / sizeof(u64)) & 0x7)
+static unsigned long vgic_mmio_read_its_baser(struct kvm *kvm,
+					      struct vgic_its *its,
+					      gpa_t addr, unsigned int len)
+{
+	u64 reg;
+
+	switch (BASER_INDEX(addr)) {
+	case 0:
+		reg = its->baser_device_table;
+		break;
+	case 1:
+		reg = its->baser_coll_table;
+		break;
+	default:
+		reg = 0;
+		break;
+	}
+
+	return extract_bytes(reg, addr & 7, len);
+}
+
+#define GITS_BASER_RO_MASK	(GENMASK_ULL(52, 48) | GENMASK_ULL(58, 56))
+static void vgic_mmio_write_its_baser(struct kvm *kvm,
+				      struct vgic_its *its,
+				      gpa_t addr, unsigned int len,
+				      unsigned long val)
+{
+	u64 entry_size, device_type;
+	u64 reg, *regptr, clearbits = 0;
+
+	/* When GITS_CTLR.Enable is 1, we ignore write accesses. */
+	if (its->enabled)
+		return;
+
+	switch (BASER_INDEX(addr)) {
+	case 0:
+		regptr = &its->baser_device_table;
+		entry_size = 8;
+		device_type = GITS_BASER_TYPE_DEVICE;
+		break;
+	case 1:
+		regptr = &its->baser_coll_table;
+		entry_size = 8;
+		device_type = GITS_BASER_TYPE_COLLECTION;
+		clearbits = GITS_BASER_INDIRECT;
+		break;
+	default:
+		return;
+	}
+
+	reg = update_64bit_reg(*regptr, addr & 7, len, val);
+	reg &= ~GITS_BASER_RO_MASK;
+	reg &= ~clearbits;
+
+	reg |= (entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT;
+	reg |= device_type << GITS_BASER_TYPE_SHIFT;
+	reg = vgic_sanitise_its_baser(reg);
+
+	*regptr = reg;
+}
+
+#define REGISTER_ITS_DESC(off, rd, wr, length, acc)		\
+{								\
+	.reg_offset = off,					\
+	.len = length,						\
+	.access_flags = acc,					\
+	.its_read = rd,						\
+	.its_write = wr,					\
+}
+
+static void its_mmio_write_wi(struct kvm *kvm, struct vgic_its *its,
+			      gpa_t addr, unsigned int len, unsigned long val)
+{
+	/* Ignore */
+}
+
+static struct vgic_register_region its_registers[] = {
+	REGISTER_ITS_DESC(GITS_CTLR,
+		vgic_mmio_read_its_ctlr, vgic_mmio_write_its_ctlr, 4,
+		VGIC_ACCESS_32bit),
+	REGISTER_ITS_DESC(GITS_IIDR,
+		vgic_mmio_read_its_iidr, its_mmio_write_wi, 4,
+		VGIC_ACCESS_32bit),
+	REGISTER_ITS_DESC(GITS_TYPER,
+		vgic_mmio_read_its_typer, its_mmio_write_wi, 8,
+		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_ITS_DESC(GITS_CBASER,
+		vgic_mmio_read_its_cbaser, vgic_mmio_write_its_cbaser, 8,
+		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_ITS_DESC(GITS_CWRITER,
+		vgic_mmio_read_its_cwriter, vgic_mmio_write_its_cwriter, 8,
+		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_ITS_DESC(GITS_CREADR,
+		vgic_mmio_read_its_creadr, its_mmio_write_wi, 8,
+		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_ITS_DESC(GITS_BASER,
+		vgic_mmio_read_its_baser, vgic_mmio_write_its_baser, 0x40,
+		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
+	REGISTER_ITS_DESC(GITS_IDREGS_BASE,
+		vgic_mmio_read_its_idregs, its_mmio_write_wi, 0x30,
+		VGIC_ACCESS_32bit),
+};
+
+/* This is called on setting the LPI enable bit in the redistributor. */
+void vgic_enable_lpis(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.vgic_cpu.pendbaser & GICR_PENDBASER_PTZ))
+		its_sync_lpi_pending_table(vcpu);
+}
+
+static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its)
+{
+	struct vgic_io_device *iodev = &its->iodev;
+	int ret;
+
+	if (its->initialized)
+		return 0;
+
+	if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base))
+		return -ENXIO;
+
+	iodev->regions = its_registers;
+	iodev->nr_regions = ARRAY_SIZE(its_registers);
+	kvm_iodevice_init(&iodev->dev, &kvm_io_gic_ops);
+
+	iodev->base_addr = its->vgic_its_base;
+	iodev->iodev_type = IODEV_ITS;
+	iodev->its = its;
+	mutex_lock(&kvm->slots_lock);
+	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, iodev->base_addr,
+				      KVM_VGIC_V3_ITS_SIZE, &iodev->dev);
+	mutex_unlock(&kvm->slots_lock);
+
+	if (!ret)
+		its->initialized = true;
+
+	return ret;
+}
+
+#define INITIAL_BASER_VALUE						  \
+	(GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb)		| \
+	 GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner)		| \
+	 GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)		| \
+	 ((8ULL - 1) << GITS_BASER_ENTRY_SIZE_SHIFT)			| \
+	 GITS_BASER_PAGE_SIZE_64K)
+
+#define INITIAL_PROPBASER_VALUE						  \
+	(GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWb)		| \
+	 GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, SameAsInner)	| \
+	 GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable))
+
+static int vgic_its_create(struct kvm_device *dev, u32 type)
+{
+	struct vgic_its *its;
+
+	if (type != KVM_DEV_TYPE_ARM_VGIC_ITS)
+		return -ENODEV;
+
+	its = kzalloc(sizeof(struct vgic_its), GFP_KERNEL);
+	if (!its)
+		return -ENOMEM;
+
+	mutex_init(&its->its_lock);
+	mutex_init(&its->cmd_lock);
+
+	its->vgic_its_base = VGIC_ADDR_UNDEF;
+
+	INIT_LIST_HEAD(&its->device_list);
+	INIT_LIST_HEAD(&its->collection_list);
+
+	dev->kvm->arch.vgic.has_its = true;
+	its->initialized = false;
+	its->enabled = false;
+	its->dev = dev;
+
+	its->baser_device_table = INITIAL_BASER_VALUE			|
+		((u64)GITS_BASER_TYPE_DEVICE << GITS_BASER_TYPE_SHIFT);
+	its->baser_coll_table = INITIAL_BASER_VALUE |
+		((u64)GITS_BASER_TYPE_COLLECTION << GITS_BASER_TYPE_SHIFT);
+	dev->kvm->arch.vgic.propbaser = INITIAL_PROPBASER_VALUE;
+
+	dev->private = its;
+
+	return 0;
+}
+
+static void vgic_its_destroy(struct kvm_device *kvm_dev)
+{
+	struct kvm *kvm = kvm_dev->kvm;
+	struct vgic_its *its = kvm_dev->private;
+	struct its_device *dev;
+	struct its_itte *itte;
+	struct list_head *dev_cur, *dev_temp;
+	struct list_head *cur, *temp;
+
+	/*
+	 * We may end up here without the lists ever having been initialized.
+	 * Check this and bail out early to avoid dereferencing a NULL pointer.
+	 */
+	if (!its->device_list.next)
+		return;
+
+	mutex_lock(&its->its_lock);
+	list_for_each_safe(dev_cur, dev_temp, &its->device_list) {
+		dev = container_of(dev_cur, struct its_device, dev_list);
+		list_for_each_safe(cur, temp, &dev->itt_head) {
+			itte = (container_of(cur, struct its_itte, itte_list));
+			its_free_itte(kvm, itte);
+		}
+		list_del(dev_cur);
+		kfree(dev);
+	}
+
+	list_for_each_safe(cur, temp, &its->collection_list) {
+		list_del(cur);
+		kfree(container_of(cur, struct its_collection, coll_list));
+	}
+	mutex_unlock(&its->its_lock);
+
+	kfree(its);
+}
+
+static int vgic_its_has_attr(struct kvm_device *dev,
+			     struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_ARM_VGIC_GRP_ADDR:
+		switch (attr->attr) {
+		case KVM_VGIC_ITS_ADDR_TYPE:
+			return 0;
+		}
+		break;
+	case KVM_DEV_ARM_VGIC_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_ARM_VGIC_CTRL_INIT:
+			return 0;
+		}
+		break;
+	}
+	return -ENXIO;
+}
+
+static int vgic_its_set_attr(struct kvm_device *dev,
+			     struct kvm_device_attr *attr)
+{
+	struct vgic_its *its = dev->private;
+	int ret;
+
+	switch (attr->group) {
+	case KVM_DEV_ARM_VGIC_GRP_ADDR: {
+		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+		unsigned long type = (unsigned long)attr->attr;
+		u64 addr;
+
+		if (type != KVM_VGIC_ITS_ADDR_TYPE)
+			return -ENODEV;
+
+		if (its->initialized)
+			return -EBUSY;
+
+		if (copy_from_user(&addr, uaddr, sizeof(addr)))
+			return -EFAULT;
+
+		ret = vgic_check_ioaddr(dev->kvm, &its->vgic_its_base,
+					addr, SZ_64K);
+		if (ret)
+			return ret;
+
+		its->vgic_its_base = addr;
+
+		return 0;
+	}
+	case KVM_DEV_ARM_VGIC_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_ARM_VGIC_CTRL_INIT:
+			return vgic_its_init_its(dev->kvm, its);
+		}
+		break;
+	}
+	return -ENXIO;
+}
+
+static int vgic_its_get_attr(struct kvm_device *dev,
+			     struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_ARM_VGIC_GRP_ADDR: {
+		struct vgic_its *its = dev->private;
+		u64 addr = its->vgic_its_base;
+		u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+		unsigned long type = (unsigned long)attr->attr;
+
+		if (type != KVM_VGIC_ITS_ADDR_TYPE)
+			return -ENODEV;
+
+		if (copy_to_user(uaddr, &addr, sizeof(addr)))
+			return -EFAULT;
+		break;
+	default:
+		return -ENXIO;
+	}
+	}
+
+	return 0;
+}
+
+static struct kvm_device_ops kvm_arm_vgic_its_ops = {
+	.name = "kvm-arm-vgic-its",
+	.create = vgic_its_create,
+	.destroy = vgic_its_destroy,
+	.set_attr = vgic_its_set_attr,
+	.get_attr = vgic_its_get_attr,
+	.has_attr = vgic_its_has_attr,
+};
+
+int kvm_vgic_register_its_device(void)
+{
+	return kvm_register_device_ops(&kvm_arm_vgic_its_ops,
+				       KVM_DEV_TYPE_ARM_VGIC_ITS);
+}
diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c
index 0130c4b147b7..1813f93b5cde 100644
--- a/virt/kvm/arm/vgic/vgic-kvm-device.c
+++ b/virt/kvm/arm/vgic/vgic-kvm-device.c
@@ -21,8 +21,8 @@
 
 /* common helpers */
 
-static int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
-			     phys_addr_t addr, phys_addr_t alignment)
+int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
+		      phys_addr_t addr, phys_addr_t alignment)
 {
 	if (addr & ~KVM_PHYS_MASK)
 		return -E2BIG;
@@ -210,20 +210,27 @@ static void vgic_destroy(struct kvm_device *dev)
 	kfree(dev);
 }
 
-void kvm_register_vgic_device(unsigned long type)
+int kvm_register_vgic_device(unsigned long type)
 {
+	int ret = -ENODEV;
+
 	switch (type) {
 	case KVM_DEV_TYPE_ARM_VGIC_V2:
-		kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
-					KVM_DEV_TYPE_ARM_VGIC_V2);
+		ret = kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
+					      KVM_DEV_TYPE_ARM_VGIC_V2);
 		break;
 #ifdef CONFIG_KVM_ARM_VGIC_V3
 	case KVM_DEV_TYPE_ARM_VGIC_V3:
-		kvm_register_device_ops(&kvm_arm_vgic_v3_ops,
-					KVM_DEV_TYPE_ARM_VGIC_V3);
+		ret = kvm_register_device_ops(&kvm_arm_vgic_v3_ops,
+					      KVM_DEV_TYPE_ARM_VGIC_V3);
+		if (ret)
+			break;
+		ret = kvm_vgic_register_its_device();
 		break;
 #endif
 	}
+
+	return ret;
 }
 
 /** vgic_attr_regs_access: allows user space to read/write VGIC registers
@@ -428,4 +435,3 @@ struct kvm_device_ops kvm_arm_vgic_v3_ops = {
 };
 
 #endif /* CONFIG_KVM_ARM_VGIC_V3 */
-
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c
index a21393637e4b..b44b359cbbad 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v2.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c
@@ -102,6 +102,7 @@ static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu,
 		irq->source |= 1U << source_vcpu->vcpu_id;
 
 		vgic_queue_irq_unlock(source_vcpu->kvm, irq);
+		vgic_put_irq(source_vcpu->kvm, irq);
 	}
 }
 
@@ -116,6 +117,8 @@ static unsigned long vgic_mmio_read_target(struct kvm_vcpu *vcpu,
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
 		val |= (u64)irq->targets << (i * 8);
+
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 
 	return val;
@@ -143,6 +146,7 @@ static void vgic_mmio_write_target(struct kvm_vcpu *vcpu,
 		irq->target_vcpu = kvm_get_vcpu(vcpu->kvm, target);
 
 		spin_unlock(&irq->irq_lock);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -157,6 +161,8 @@ static unsigned long vgic_mmio_read_sgipend(struct kvm_vcpu *vcpu,
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
 		val |= (u64)irq->source << (i * 8);
+
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 	return val;
 }
@@ -178,6 +184,7 @@ static void vgic_mmio_write_sgipendc(struct kvm_vcpu *vcpu,
 			irq->pending = false;
 
 		spin_unlock(&irq->irq_lock);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -201,6 +208,7 @@ static void vgic_mmio_write_sgipends(struct kvm_vcpu *vcpu,
 		} else {
 			spin_unlock(&irq->irq_lock);
 		}
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -429,6 +437,7 @@ int vgic_v2_cpuif_uaccess(struct kvm_vcpu *vcpu, bool is_write,
 	struct vgic_io_device dev = {
 		.regions = vgic_v2_cpu_registers,
 		.nr_regions = ARRAY_SIZE(vgic_v2_cpu_registers),
+		.iodev_type = IODEV_CPUIF,
 	};
 
 	return vgic_uaccess(vcpu, &dev, is_write, offset, val);
@@ -440,6 +449,7 @@ int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
 	struct vgic_io_device dev = {
 		.regions = vgic_v2_dist_registers,
 		.nr_regions = ARRAY_SIZE(vgic_v2_dist_registers),
+		.iodev_type = IODEV_DIST,
 	};
 
 	return vgic_uaccess(vcpu, &dev, is_write, offset, val);
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index a0c515a412a7..ff668e0dd586 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -23,12 +23,35 @@
 #include "vgic-mmio.h"
 
 /* extract @num bytes at @offset bytes offset in data */
-static unsigned long extract_bytes(unsigned long data, unsigned int offset,
-				   unsigned int num)
+unsigned long extract_bytes(unsigned long data, unsigned int offset,
+			    unsigned int num)
 {
 	return (data >> (offset * 8)) & GENMASK_ULL(num * 8 - 1, 0);
 }
 
+/* allows updates of any half of a 64-bit register (or the whole thing) */
+u64 update_64bit_reg(u64 reg, unsigned int offset, unsigned int len,
+		     unsigned long val)
+{
+	int lower = (offset & 4) * 8;
+	int upper = lower + 8 * len - 1;
+
+	reg &= ~GENMASK_ULL(upper, lower);
+	val &= GENMASK_ULL(len * 8 - 1, 0);
+
+	return reg | ((u64)val << lower);
+}
+
+bool vgic_has_its(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+
+	if (dist->vgic_model != KVM_DEV_TYPE_ARM_VGIC_V3)
+		return false;
+
+	return dist->has_its;
+}
+
 static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu,
 					    gpa_t addr, unsigned int len)
 {
@@ -43,7 +66,12 @@ static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu,
 	case GICD_TYPER:
 		value = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
 		value = (value >> 5) - 1;
-		value |= (INTERRUPT_ID_BITS_SPIS - 1) << 19;
+		if (vgic_has_its(vcpu->kvm)) {
+			value |= (INTERRUPT_ID_BITS_ITS - 1) << 19;
+			value |= GICD_TYPER_LPIS;
+		} else {
+			value |= (INTERRUPT_ID_BITS_SPIS - 1) << 19;
+		}
 		break;
 	case GICD_IIDR:
 		value = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
@@ -80,15 +108,17 @@ static unsigned long vgic_mmio_read_irouter(struct kvm_vcpu *vcpu,
 {
 	int intid = VGIC_ADDR_TO_INTID(addr, 64);
 	struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid);
+	unsigned long ret = 0;
 
 	if (!irq)
 		return 0;
 
 	/* The upper word is RAZ for us. */
-	if (addr & 4)
-		return 0;
+	if (!(addr & 4))
+		ret = extract_bytes(READ_ONCE(irq->mpidr), addr & 7, len);
 
-	return extract_bytes(READ_ONCE(irq->mpidr), addr & 7, len);
+	vgic_put_irq(vcpu->kvm, irq);
+	return ret;
 }
 
 static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu,
@@ -96,15 +126,17 @@ static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu,
 				    unsigned long val)
 {
 	int intid = VGIC_ADDR_TO_INTID(addr, 64);
-	struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid);
-
-	if (!irq)
-		return;
+	struct vgic_irq *irq;
 
 	/* The upper word is WI for us since we don't implement Aff3. */
 	if (addr & 4)
 		return;
 
+	irq = vgic_get_irq(vcpu->kvm, NULL, intid);
+
+	if (!irq)
+		return;
+
 	spin_lock(&irq->irq_lock);
 
 	/* We only care about and preserve Aff0, Aff1 and Aff2. */
@@ -112,6 +144,32 @@ static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu,
 	irq->target_vcpu = kvm_mpidr_to_vcpu(vcpu->kvm, irq->mpidr);
 
 	spin_unlock(&irq->irq_lock);
+	vgic_put_irq(vcpu->kvm, irq);
+}
+
+static unsigned long vgic_mmio_read_v3r_ctlr(struct kvm_vcpu *vcpu,
+					     gpa_t addr, unsigned int len)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	return vgic_cpu->lpis_enabled ? GICR_CTLR_ENABLE_LPIS : 0;
+}
+
+
+static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu,
+				     gpa_t addr, unsigned int len,
+				     unsigned long val)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	bool was_enabled = vgic_cpu->lpis_enabled;
+
+	if (!vgic_has_its(vcpu->kvm))
+		return;
+
+	vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS;
+
+	if (!was_enabled && vgic_cpu->lpis_enabled)
+		vgic_enable_lpis(vcpu);
 }
 
 static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu,
@@ -125,6 +183,8 @@ static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu,
 	value |= ((target_vcpu_id & 0xffff) << 8);
 	if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1)
 		value |= GICR_TYPER_LAST;
+	if (vgic_has_its(vcpu->kvm))
+		value |= GICR_TYPER_PLPIS;
 
 	return extract_bytes(value, addr & 7, len);
 }
@@ -147,6 +207,142 @@ static unsigned long vgic_mmio_read_v3_idregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+/* We want to avoid outer shareable. */
+u64 vgic_sanitise_shareability(u64 field)
+{
+	switch (field) {
+	case GIC_BASER_OuterShareable:
+		return GIC_BASER_InnerShareable;
+	default:
+		return field;
+	}
+}
+
+/* Avoid any inner non-cacheable mapping. */
+u64 vgic_sanitise_inner_cacheability(u64 field)
+{
+	switch (field) {
+	case GIC_BASER_CACHE_nCnB:
+	case GIC_BASER_CACHE_nC:
+		return GIC_BASER_CACHE_RaWb;
+	default:
+		return field;
+	}
+}
+
+/* Non-cacheable or same-as-inner are OK. */
+u64 vgic_sanitise_outer_cacheability(u64 field)
+{
+	switch (field) {
+	case GIC_BASER_CACHE_SameAsInner:
+	case GIC_BASER_CACHE_nC:
+		return field;
+	default:
+		return GIC_BASER_CACHE_nC;
+	}
+}
+
+u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift,
+			u64 (*sanitise_fn)(u64))
+{
+	u64 field = (reg & field_mask) >> field_shift;
+
+	field = sanitise_fn(field) << field_shift;
+	return (reg & ~field_mask) | field;
+}
+
+#define PROPBASER_RES0_MASK						\
+	(GENMASK_ULL(63, 59) | GENMASK_ULL(55, 52) | GENMASK_ULL(6, 5))
+#define PENDBASER_RES0_MASK						\
+	(BIT_ULL(63) | GENMASK_ULL(61, 59) | GENMASK_ULL(55, 52) |	\
+	 GENMASK_ULL(15, 12) | GENMASK_ULL(6, 0))
+
+static u64 vgic_sanitise_pendbaser(u64 reg)
+{
+	reg = vgic_sanitise_field(reg, GICR_PENDBASER_SHAREABILITY_MASK,
+				  GICR_PENDBASER_SHAREABILITY_SHIFT,
+				  vgic_sanitise_shareability);
+	reg = vgic_sanitise_field(reg, GICR_PENDBASER_INNER_CACHEABILITY_MASK,
+				  GICR_PENDBASER_INNER_CACHEABILITY_SHIFT,
+				  vgic_sanitise_inner_cacheability);
+	reg = vgic_sanitise_field(reg, GICR_PENDBASER_OUTER_CACHEABILITY_MASK,
+				  GICR_PENDBASER_OUTER_CACHEABILITY_SHIFT,
+				  vgic_sanitise_outer_cacheability);
+
+	reg &= ~PENDBASER_RES0_MASK;
+	reg &= ~GENMASK_ULL(51, 48);
+
+	return reg;
+}
+
+static u64 vgic_sanitise_propbaser(u64 reg)
+{
+	reg = vgic_sanitise_field(reg, GICR_PROPBASER_SHAREABILITY_MASK,
+				  GICR_PROPBASER_SHAREABILITY_SHIFT,
+				  vgic_sanitise_shareability);
+	reg = vgic_sanitise_field(reg, GICR_PROPBASER_INNER_CACHEABILITY_MASK,
+				  GICR_PROPBASER_INNER_CACHEABILITY_SHIFT,
+				  vgic_sanitise_inner_cacheability);
+	reg = vgic_sanitise_field(reg, GICR_PROPBASER_OUTER_CACHEABILITY_MASK,
+				  GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT,
+				  vgic_sanitise_outer_cacheability);
+
+	reg &= ~PROPBASER_RES0_MASK;
+	reg &= ~GENMASK_ULL(51, 48);
+	return reg;
+}
+
+static unsigned long vgic_mmio_read_propbase(struct kvm_vcpu *vcpu,
+					     gpa_t addr, unsigned int len)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	return extract_bytes(dist->propbaser, addr & 7, len);
+}
+
+static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu,
+				     gpa_t addr, unsigned int len,
+				     unsigned long val)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	u64 propbaser = dist->propbaser;
+
+	/* Storing a value with LPIs already enabled is undefined */
+	if (vgic_cpu->lpis_enabled)
+		return;
+
+	propbaser = update_64bit_reg(propbaser, addr & 4, len, val);
+	propbaser = vgic_sanitise_propbaser(propbaser);
+
+	dist->propbaser = propbaser;
+}
+
+static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu,
+					     gpa_t addr, unsigned int len)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	return extract_bytes(vgic_cpu->pendbaser, addr & 7, len);
+}
+
+static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu,
+				     gpa_t addr, unsigned int len,
+				     unsigned long val)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	u64 pendbaser = vgic_cpu->pendbaser;
+
+	/* Storing a value with LPIs already enabled is undefined */
+	if (vgic_cpu->lpis_enabled)
+		return;
+
+	pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val);
+	pendbaser = vgic_sanitise_pendbaser(pendbaser);
+
+	vgic_cpu->pendbaser = pendbaser;
+}
+
 /*
  * The GICv3 per-IRQ registers are split to control PPIs and SGIs in the
  * redistributors, while SPIs are covered by registers in the distributor
@@ -218,7 +414,7 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = {
 
 static const struct vgic_register_region vgic_v3_rdbase_registers[] = {
 	REGISTER_DESC_WITH_LENGTH(GICR_CTLR,
-		vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
+		vgic_mmio_read_v3r_ctlr, vgic_mmio_write_v3r_ctlr, 4,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_IIDR,
 		vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4,
@@ -227,10 +423,10 @@ static const struct vgic_register_region vgic_v3_rdbase_registers[] = {
 		vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8,
 		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_PROPBASER,
-		vgic_mmio_read_raz, vgic_mmio_write_wi, 8,
+		vgic_mmio_read_propbase, vgic_mmio_write_propbase, 8,
 		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_PENDBASER,
-		vgic_mmio_read_raz, vgic_mmio_write_wi, 8,
+		vgic_mmio_read_pendbase, vgic_mmio_write_pendbase, 8,
 		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(GICR_IDREGS,
 		vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48,
@@ -285,24 +481,18 @@ unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev)
 
 int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t redist_base_address)
 {
-	int nr_vcpus = atomic_read(&kvm->online_vcpus);
 	struct kvm_vcpu *vcpu;
-	struct vgic_io_device *devices;
 	int c, ret = 0;
 
-	devices = kmalloc(sizeof(struct vgic_io_device) * nr_vcpus * 2,
-			  GFP_KERNEL);
-	if (!devices)
-		return -ENOMEM;
-
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		gpa_t rd_base = redist_base_address + c * SZ_64K * 2;
 		gpa_t sgi_base = rd_base + SZ_64K;
-		struct vgic_io_device *rd_dev = &devices[c * 2];
-		struct vgic_io_device *sgi_dev = &devices[c * 2 + 1];
+		struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
+		struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
 
 		kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
 		rd_dev->base_addr = rd_base;
+		rd_dev->iodev_type = IODEV_REDIST;
 		rd_dev->regions = vgic_v3_rdbase_registers;
 		rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers);
 		rd_dev->redist_vcpu = vcpu;
@@ -317,6 +507,7 @@ int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t redist_base_address)
 
 		kvm_iodevice_init(&sgi_dev->dev, &kvm_io_gic_ops);
 		sgi_dev->base_addr = sgi_base;
+		sgi_dev->iodev_type = IODEV_REDIST;
 		sgi_dev->regions = vgic_v3_sgibase_registers;
 		sgi_dev->nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers);
 		sgi_dev->redist_vcpu = vcpu;
@@ -335,14 +526,15 @@ int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t redist_base_address)
 	if (ret) {
 		/* The current c failed, so we start with the previous one. */
 		for (c--; c >= 0; c--) {
+			struct vgic_cpu *vgic_cpu;
+
+			vcpu = kvm_get_vcpu(kvm, c);
+			vgic_cpu = &vcpu->arch.vgic_cpu;
 			kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
-						  &devices[c * 2].dev);
+						  &vgic_cpu->rd_iodev.dev);
 			kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
-						  &devices[c * 2 + 1].dev);
+						  &vgic_cpu->sgi_iodev.dev);
 		}
-		kfree(devices);
-	} else {
-		kvm->arch.vgic.redist_iodevs = devices;
 	}
 
 	return ret;
@@ -451,5 +643,6 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
 		irq->pending = true;
 
 		vgic_queue_irq_unlock(vcpu->kvm, irq);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 9f6fab74dce7..3bad3c5ed431 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -56,6 +56,8 @@ unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu,
 
 		if (irq->enabled)
 			value |= (1U << i);
+
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 
 	return value;
@@ -74,6 +76,8 @@ void vgic_mmio_write_senable(struct kvm_vcpu *vcpu,
 		spin_lock(&irq->irq_lock);
 		irq->enabled = true;
 		vgic_queue_irq_unlock(vcpu->kvm, irq);
+
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -92,6 +96,7 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu,
 		irq->enabled = false;
 
 		spin_unlock(&irq->irq_lock);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -108,6 +113,8 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 
 		if (irq->pending)
 			value |= (1U << i);
+
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 
 	return value;
@@ -129,6 +136,7 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 			irq->soft_pending = true;
 
 		vgic_queue_irq_unlock(vcpu->kvm, irq);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -152,6 +160,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 		}
 
 		spin_unlock(&irq->irq_lock);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -168,6 +177,8 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
 
 		if (irq->active)
 			value |= (1U << i);
+
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 
 	return value;
@@ -242,6 +253,7 @@ void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 		vgic_mmio_change_active(vcpu, irq, false);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 	vgic_change_active_finish(vcpu, intid);
 }
@@ -257,6 +269,7 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 		vgic_mmio_change_active(vcpu, irq, true);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 	vgic_change_active_finish(vcpu, intid);
 }
@@ -272,6 +285,8 @@ unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu,
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
 		val |= (u64)irq->priority << (i * 8);
+
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 
 	return val;
@@ -298,6 +313,8 @@ void vgic_mmio_write_priority(struct kvm_vcpu *vcpu,
 		/* Narrow the priority range to what we actually support */
 		irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS);
 		spin_unlock(&irq->irq_lock);
+
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -313,6 +330,8 @@ unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu,
 
 		if (irq->config == VGIC_CONFIG_EDGE)
 			value |= (2U << (i * 2));
+
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 
 	return value;
@@ -326,7 +345,7 @@ void vgic_mmio_write_config(struct kvm_vcpu *vcpu,
 	int i;
 
 	for (i = 0; i < len * 4; i++) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+		struct vgic_irq *irq;
 
 		/*
 		 * The configuration cannot be changed for SGIs in general,
@@ -337,14 +356,18 @@ void vgic_mmio_write_config(struct kvm_vcpu *vcpu,
 		if (intid + i < VGIC_NR_PRIVATE_IRQS)
 			continue;
 
+		irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 		spin_lock(&irq->irq_lock);
+
 		if (test_bit(i * 2 + 1, &val)) {
 			irq->config = VGIC_CONFIG_EDGE;
 		} else {
 			irq->config = VGIC_CONFIG_LEVEL;
 			irq->pending = irq->line_level | irq->soft_pending;
 		}
+
 		spin_unlock(&irq->irq_lock);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -450,8 +473,7 @@ static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
 {
 	struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev);
 	const struct vgic_register_region *region;
-	struct kvm_vcpu *r_vcpu;
-	unsigned long data;
+	unsigned long data = 0;
 
 	region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
 				       addr - iodev->base_addr);
@@ -460,8 +482,21 @@ static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
 		return 0;
 	}
 
-	r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu;
-	data = region->read(r_vcpu, addr, len);
+	switch (iodev->iodev_type) {
+	case IODEV_CPUIF:
+		data = region->read(vcpu, addr, len);
+		break;
+	case IODEV_DIST:
+		data = region->read(vcpu, addr, len);
+		break;
+	case IODEV_REDIST:
+		data = region->read(iodev->redist_vcpu, addr, len);
+		break;
+	case IODEV_ITS:
+		data = region->its_read(vcpu->kvm, iodev->its, addr, len);
+		break;
+	}
+
 	vgic_data_host_to_mmio_bus(val, len, data);
 	return 0;
 }
@@ -471,7 +506,6 @@ static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
 {
 	struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev);
 	const struct vgic_register_region *region;
-	struct kvm_vcpu *r_vcpu;
 	unsigned long data = vgic_data_mmio_bus_to_host(val, len);
 
 	region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
@@ -482,8 +516,21 @@ static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
 	if (!check_region(region, addr, len))
 		return 0;
 
-	r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu;
-	region->write(r_vcpu, addr, len, data);
+	switch (iodev->iodev_type) {
+	case IODEV_CPUIF:
+		region->write(vcpu, addr, len, data);
+		break;
+	case IODEV_DIST:
+		region->write(vcpu, addr, len, data);
+		break;
+	case IODEV_REDIST:
+		region->write(iodev->redist_vcpu, addr, len, data);
+		break;
+	case IODEV_ITS:
+		region->its_write(vcpu->kvm, iodev->its, addr, len, data);
+		break;
+	}
+
 	return 0;
 }
 
@@ -513,6 +560,7 @@ int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
 	}
 
 	io_device->base_addr = dist_base_address;
+	io_device->iodev_type = IODEV_DIST;
 	io_device->redist_vcpu = NULL;
 
 	mutex_lock(&kvm->slots_lock);
diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h
index 850901482aec..0b3ecf9d100e 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.h
+++ b/virt/kvm/arm/vgic/vgic-mmio.h
@@ -21,10 +21,19 @@ struct vgic_register_region {
 	unsigned int len;
 	unsigned int bits_per_irq;
 	unsigned int access_flags;
-	unsigned long (*read)(struct kvm_vcpu *vcpu, gpa_t addr,
-			      unsigned int len);
-	void (*write)(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len,
-		      unsigned long val);
+	union {
+		unsigned long (*read)(struct kvm_vcpu *vcpu, gpa_t addr,
+				      unsigned int len);
+		unsigned long (*its_read)(struct kvm *kvm, struct vgic_its *its,
+					  gpa_t addr, unsigned int len);
+	};
+	union {
+		void (*write)(struct kvm_vcpu *vcpu, gpa_t addr,
+			      unsigned int len, unsigned long val);
+		void (*its_write)(struct kvm *kvm, struct vgic_its *its,
+				  gpa_t addr, unsigned int len,
+				  unsigned long val);
+	};
 };
 
 extern struct kvm_io_device_ops kvm_io_gic_ops;
@@ -87,6 +96,12 @@ unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len);
 void vgic_data_host_to_mmio_bus(void *buf, unsigned int len,
 				unsigned long data);
 
+unsigned long extract_bytes(unsigned long data, unsigned int offset,
+			    unsigned int num);
+
+u64 update_64bit_reg(u64 reg, unsigned int offset, unsigned int len,
+		     unsigned long val);
+
 unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu,
 				 gpa_t addr, unsigned int len);
 
@@ -147,4 +162,12 @@ unsigned int vgic_v2_init_dist_iodev(struct vgic_io_device *dev);
 
 unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev);
 
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+u64 vgic_sanitise_outer_cacheability(u64 reg);
+u64 vgic_sanitise_inner_cacheability(u64 reg);
+u64 vgic_sanitise_shareability(u64 reg);
+u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift,
+			u64 (*sanitise_fn)(u64));
+#endif
+
 #endif
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index e31405ee5515..0bf6709d1006 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -124,6 +124,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 		}
 
 		spin_unlock(&irq->irq_lock);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -332,20 +333,25 @@ int vgic_v2_probe(const struct gic_kvm_info *info)
 	vtr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_VTR);
 	kvm_vgic_global_state.nr_lr = (vtr & 0x3f) + 1;
 
+	ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2);
+	if (ret) {
+		kvm_err("Cannot register GICv2 KVM device\n");
+		iounmap(kvm_vgic_global_state.vctrl_base);
+		return ret;
+	}
+
 	ret = create_hyp_io_mappings(kvm_vgic_global_state.vctrl_base,
 				     kvm_vgic_global_state.vctrl_base +
 					 resource_size(&info->vctrl),
 				     info->vctrl.start);
-
 	if (ret) {
 		kvm_err("Cannot map VCTRL into hyp\n");
+		kvm_unregister_device_ops(KVM_DEV_TYPE_ARM_VGIC_V2);
 		iounmap(kvm_vgic_global_state.vctrl_base);
 		return ret;
 	}
 
 	kvm_vgic_global_state.can_emulate_gicv2 = true;
-	kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2);
-
 	kvm_vgic_global_state.vcpu_base = info->vcpu.start;
 	kvm_vgic_global_state.type = VGIC_V2;
 	kvm_vgic_global_state.max_gic_vcpus = VGIC_V2_MAX_CPUS;
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 346b4ad12b49..0506543df38a 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -81,6 +81,8 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 		else
 			intid = val & GICH_LR_VIRTUALID;
 		irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
+		if (!irq)	/* An LPI could have been unmapped. */
+			continue;
 
 		spin_lock(&irq->irq_lock);
 
@@ -113,6 +115,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 		}
 
 		spin_unlock(&irq->irq_lock);
+		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
@@ -190,6 +193,11 @@ void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 	vmcrp->pmr  = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
 }
 
+#define INITIAL_PENDBASER_VALUE						  \
+	(GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWb)		| \
+	GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, SameAsInner)	| \
+	GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable))
+
 void vgic_v3_enable(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3;
@@ -207,10 +215,12 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
 	 * way, so we force SRE to 1 to demonstrate this to the guest.
 	 * This goes with the spec allowing the value to be RAO/WI.
 	 */
-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
 		vgic_v3->vgic_sre = ICC_SRE_EL1_SRE;
-	else
+		vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE;
+	} else {
 		vgic_v3->vgic_sre = 0;
+	}
 
 	/* Get the show on the road... */
 	vgic_v3->vgic_hcr = ICH_HCR_EN;
@@ -296,6 +306,7 @@ out:
 int vgic_v3_probe(const struct gic_kvm_info *info)
 {
 	u32 ich_vtr_el2 = kvm_call_hyp(__vgic_v3_get_ich_vtr_el2);
+	int ret;
 
 	/*
 	 * The ListRegs field is 5 bits, but there is a architectural
@@ -319,12 +330,22 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	} else {
 		kvm_vgic_global_state.vcpu_base = info->vcpu.start;
 		kvm_vgic_global_state.can_emulate_gicv2 = true;
-		kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2);
+		ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2);
+		if (ret) {
+			kvm_err("Cannot register GICv2 KVM device.\n");
+			return ret;
+		}
 		kvm_info("vgic-v2@%llx\n", info->vcpu.start);
 	}
+	ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V3);
+	if (ret) {
+		kvm_err("Cannot register GICv3 KVM device.\n");
+		kvm_unregister_device_ops(KVM_DEV_TYPE_ARM_VGIC_V2);
+		return ret;
+	}
+
 	if (kvm_vgic_global_state.vcpu_base == 0)
 		kvm_info("disabling GICv2 emulation\n");
-	kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V3);
 
 	kvm_vgic_global_state.vctrl_base = NULL;
 	kvm_vgic_global_state.type = VGIC_V3;
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index 69b61abefa19..39f3358c6d91 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -33,10 +33,17 @@ struct vgic_global __section(.hyp.text) kvm_vgic_global_state;
 
 /*
  * Locking order is always:
- *   vgic_cpu->ap_list_lock
- *     vgic_irq->irq_lock
+ * its->cmd_lock (mutex)
+ *   its->its_lock (mutex)
+ *     vgic_cpu->ap_list_lock
+ *       kvm->lpi_list_lock
+ *         vgic_irq->irq_lock
  *
- * (that is, always take the ap_list_lock before the struct vgic_irq lock).
+ * If you need to take multiple locks, always take the upper lock first,
+ * then the lower ones, e.g. first take the its_lock, then the irq_lock.
+ * If you are already holding a lock and need to take a higher one, you
+ * have to drop the lower ranking lock first and re-aquire it after having
+ * taken the upper one.
  *
  * When taking more than one ap_list_lock at the same time, always take the
  * lowest numbered VCPU's ap_list_lock first, so:
@@ -45,6 +52,41 @@ struct vgic_global __section(.hyp.text) kvm_vgic_global_state;
  *     spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock);
  */
 
+/*
+ * Iterate over the VM's list of mapped LPIs to find the one with a
+ * matching interrupt ID and return a reference to the IRQ structure.
+ */
+static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct vgic_irq *irq = NULL;
+
+	spin_lock(&dist->lpi_list_lock);
+
+	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
+		if (irq->intid != intid)
+			continue;
+
+		/*
+		 * This increases the refcount, the caller is expected to
+		 * call vgic_put_irq() later once it's finished with the IRQ.
+		 */
+		vgic_get_irq_kref(irq);
+		goto out_unlock;
+	}
+	irq = NULL;
+
+out_unlock:
+	spin_unlock(&dist->lpi_list_lock);
+
+	return irq;
+}
+
+/*
+ * This looks up the virtual interrupt ID to get the corresponding
+ * struct vgic_irq. It also increases the refcount, so any caller is expected
+ * to call vgic_put_irq() once it's finished with this IRQ.
+ */
 struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
 			      u32 intid)
 {
@@ -56,14 +98,43 @@ struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	if (intid <= VGIC_MAX_SPI)
 		return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];
 
-	/* LPIs are not yet covered */
+	/* LPIs */
 	if (intid >= VGIC_MIN_LPI)
-		return NULL;
+		return vgic_get_lpi(kvm, intid);
 
 	WARN(1, "Looking up struct vgic_irq for reserved INTID");
 	return NULL;
 }
 
+/*
+ * We can't do anything in here, because we lack the kvm pointer to
+ * lock and remove the item from the lpi_list. So we keep this function
+ * empty and use the return value of kref_put() to trigger the freeing.
+ */
+static void vgic_irq_release(struct kref *ref)
+{
+}
+
+void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
+{
+	struct vgic_dist *dist;
+
+	if (irq->intid < VGIC_MIN_LPI)
+		return;
+
+	if (!kref_put(&irq->refcount, vgic_irq_release))
+		return;
+
+	dist = &kvm->arch.vgic;
+
+	spin_lock(&dist->lpi_list_lock);
+	list_del(&irq->lpi_list);
+	dist->lpi_list_count--;
+	spin_unlock(&dist->lpi_list_lock);
+
+	kfree(irq);
+}
+
 /**
  * kvm_vgic_target_oracle - compute the target vcpu for an irq
  *
@@ -236,6 +307,11 @@ retry:
 		goto retry;
 	}
 
+	/*
+	 * Grab a reference to the irq to reflect the fact that it is
+	 * now in the ap_list.
+	 */
+	vgic_get_irq_kref(irq);
 	list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head);
 	irq->vcpu = vcpu;
 
@@ -269,14 +345,17 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 	if (!irq)
 		return -EINVAL;
 
-	if (irq->hw != mapped_irq)
+	if (irq->hw != mapped_irq) {
+		vgic_put_irq(kvm, irq);
 		return -EINVAL;
+	}
 
 	spin_lock(&irq->irq_lock);
 
 	if (!vgic_validate_injection(irq, level)) {
 		/* Nothing to see here, move along... */
 		spin_unlock(&irq->irq_lock);
+		vgic_put_irq(kvm, irq);
 		return 0;
 	}
 
@@ -288,6 +367,7 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 	}
 
 	vgic_queue_irq_unlock(kvm, irq);
+	vgic_put_irq(kvm, irq);
 
 	return 0;
 }
@@ -330,25 +410,28 @@ int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq)
 	irq->hwintid = phys_irq;
 
 	spin_unlock(&irq->irq_lock);
+	vgic_put_irq(vcpu->kvm, irq);
 
 	return 0;
 }
 
 int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq)
 {
-	struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, virt_irq);
-
-	BUG_ON(!irq);
+	struct vgic_irq *irq;
 
 	if (!vgic_initialized(vcpu->kvm))
 		return -EAGAIN;
 
+	irq = vgic_get_irq(vcpu->kvm, vcpu, virt_irq);
+	BUG_ON(!irq);
+
 	spin_lock(&irq->irq_lock);
 
 	irq->hw = false;
 	irq->hwintid = 0;
 
 	spin_unlock(&irq->irq_lock);
+	vgic_put_irq(vcpu->kvm, irq);
 
 	return 0;
 }
@@ -386,6 +469,15 @@ retry:
 			list_del(&irq->ap_list);
 			irq->vcpu = NULL;
 			spin_unlock(&irq->irq_lock);
+
+			/*
+			 * This vgic_put_irq call matches the
+			 * vgic_get_irq_kref in vgic_queue_irq_unlock,
+			 * where we added the LPI to the ap_list. As
+			 * we remove the irq from the list, we drop
+			 * also drop the refcount.
+			 */
+			vgic_put_irq(vcpu->kvm, irq);
 			continue;
 		}
 
@@ -614,6 +706,15 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq)
 	spin_lock(&irq->irq_lock);
 	map_is_active = irq->hw && irq->active;
 	spin_unlock(&irq->irq_lock);
+	vgic_put_irq(vcpu->kvm, irq);
 
 	return map_is_active;
 }
+
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
+{
+	if (vgic_has_its(kvm))
+		return vgic_its_inject_msi(kvm, msi);
+	else
+		return -ENODEV;
+}
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index 7b300ca370b7..1d8e21d5c13f 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -25,6 +25,7 @@
 #define IS_VGIC_ADDR_UNDEF(_x)  ((_x) == VGIC_ADDR_UNDEF)
 
 #define INTERRUPT_ID_BITS_SPIS	10
+#define INTERRUPT_ID_BITS_ITS	16
 #define VGIC_PRI_BITS		5
 
 #define vgic_irq_is_sgi(intid) ((intid) < VGIC_NR_SGIS)
@@ -38,9 +39,13 @@ struct vgic_vmcr {
 
 struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
 			      u32 intid);
+void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq);
 bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq);
 void vgic_kick_vcpus(struct kvm *kvm);
 
+int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
+		      phys_addr_t addr, phys_addr_t alignment);
+
 void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu);
 void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu);
 void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
@@ -59,6 +64,14 @@ int vgic_v2_map_resources(struct kvm *kvm);
 int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
 			     enum vgic_type);
 
+static inline void vgic_get_irq_kref(struct vgic_irq *irq)
+{
+	if (irq->intid < VGIC_MIN_LPI)
+		return;
+
+	kref_get(&irq->refcount);
+}
+
 #ifdef CONFIG_KVM_ARM_VGIC_V3
 void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu);
 void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu);
@@ -71,6 +84,10 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu);
 int vgic_v3_probe(const struct gic_kvm_info *info);
 int vgic_v3_map_resources(struct kvm *kvm);
 int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
+bool vgic_has_its(struct kvm *kvm);
+int kvm_vgic_register_its_device(void);
+void vgic_enable_lpis(struct kvm_vcpu *vcpu);
+int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi);
 #else
 static inline void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu)
 {
@@ -122,9 +139,28 @@ static inline int vgic_register_redist_iodevs(struct kvm *kvm,
 {
 	return -ENODEV;
 }
+
+static inline bool vgic_has_its(struct kvm *kvm)
+{
+	return false;
+}
+
+static inline int kvm_vgic_register_its_device(void)
+{
+	return -ENODEV;
+}
+
+static inline void vgic_enable_lpis(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
+{
+	return -ENODEV;
+}
 #endif
 
-void kvm_register_vgic_device(unsigned long type);
+int kvm_register_vgic_device(unsigned long type);
 int vgic_lazy_init(struct kvm *kvm);
 int vgic_init(struct kvm *kvm);
 
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 8db197bb6c7a..df99e9c3b64d 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -135,7 +135,8 @@ void kvm_free_irq_routing(struct kvm *kvm)
 	free_irq_routing_table(rt);
 }
 
-static int setup_routing_entry(struct kvm_irq_routing_table *rt,
+static int setup_routing_entry(struct kvm *kvm,
+			       struct kvm_irq_routing_table *rt,
 			       struct kvm_kernel_irq_routing_entry *e,
 			       const struct kvm_irq_routing_entry *ue)
 {
@@ -154,7 +155,7 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt,
 
 	e->gsi = ue->gsi;
 	e->type = ue->type;
-	r = kvm_set_routing_entry(e, ue);
+	r = kvm_set_routing_entry(kvm, e, ue);
 	if (r)
 		goto out;
 	if (e->type == KVM_IRQ_ROUTING_IRQCHIP)
@@ -211,7 +212,7 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			kfree(e);
 			goto out;
 		}
-		r = setup_routing_entry(new, e, ue);
+		r = setup_routing_entry(kvm, new, e, ue);
 		if (r) {
 			kfree(e);
 			goto out;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2e791367c576..cc081ccfcaa3 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1444,6 +1444,52 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault)
 	return true;
 }
 
+static int hva_to_pfn_remapped(struct vm_area_struct *vma,
+			       unsigned long addr, bool *async,
+			       bool write_fault, kvm_pfn_t *p_pfn)
+{
+	unsigned long pfn;
+	int r;
+
+	r = follow_pfn(vma, addr, &pfn);
+	if (r) {
+		/*
+		 * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does
+		 * not call the fault handler, so do it here.
+		 */
+		bool unlocked = false;
+		r = fixup_user_fault(current, current->mm, addr,
+				     (write_fault ? FAULT_FLAG_WRITE : 0),
+				     &unlocked);
+		if (unlocked)
+			return -EAGAIN;
+		if (r)
+			return r;
+
+		r = follow_pfn(vma, addr, &pfn);
+		if (r)
+			return r;
+
+	}
+
+
+	/*
+	 * Get a reference here because callers of *hva_to_pfn* and
+	 * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the
+	 * returned pfn.  This is only needed if the VMA has VM_MIXEDMAP
+	 * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will
+	 * simply do nothing for reserved pfns.
+	 *
+	 * Whoever called remap_pfn_range is also going to call e.g.
+	 * unmap_mapping_range before the underlying pages are freed,
+	 * causing a call to our MMU notifier.
+	 */ 
+	kvm_get_pfn(pfn);
+
+	*p_pfn = pfn;
+	return 0;
+}
+
 /*
  * Pin guest page in memory and return its pfn.
  * @addr: host virtual address which maps memory to the guest
@@ -1463,7 +1509,7 @@ static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
 {
 	struct vm_area_struct *vma;
 	kvm_pfn_t pfn = 0;
-	int npages;
+	int npages, r;
 
 	/* we can do it either atomically or asynchronously, not both */
 	BUG_ON(atomic && async);
@@ -1485,14 +1531,17 @@ static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
 		goto exit;
 	}
 
+retry:
 	vma = find_vma_intersection(current->mm, addr, addr + 1);
 
 	if (vma == NULL)
 		pfn = KVM_PFN_ERR_FAULT;
-	else if ((vma->vm_flags & VM_PFNMAP)) {
-		pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) +
-			vma->vm_pgoff;
-		BUG_ON(!kvm_is_reserved_pfn(pfn));
+	else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) {
+		r = hva_to_pfn_remapped(vma, addr, async, write_fault, &pfn);
+		if (r == -EAGAIN)
+			goto retry;
+		if (r < 0)
+			pfn = KVM_PFN_ERR_FAULT;
 	} else {
 		if (async && vma_is_valid(vma, write_fault))
 			*async = true;
@@ -2348,9 +2397,20 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	if (id >= KVM_MAX_VCPU_ID)
 		return -EINVAL;
 
+	mutex_lock(&kvm->lock);
+	if (kvm->created_vcpus == KVM_MAX_VCPUS) {
+		mutex_unlock(&kvm->lock);
+		return -EINVAL;
+	}
+
+	kvm->created_vcpus++;
+	mutex_unlock(&kvm->lock);
+
 	vcpu = kvm_arch_vcpu_create(kvm, id);
-	if (IS_ERR(vcpu))
-		return PTR_ERR(vcpu);
+	if (IS_ERR(vcpu)) {
+		r = PTR_ERR(vcpu);
+		goto vcpu_decrement;
+	}
 
 	preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
 
@@ -2359,14 +2419,6 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 		goto vcpu_destroy;
 
 	mutex_lock(&kvm->lock);
-	if (!kvm_vcpu_compatible(vcpu)) {
-		r = -EINVAL;
-		goto unlock_vcpu_destroy;
-	}
-	if (atomic_read(&kvm->online_vcpus) == KVM_MAX_VCPUS) {
-		r = -EINVAL;
-		goto unlock_vcpu_destroy;
-	}
 	if (kvm_get_vcpu_by_id(kvm, id)) {
 		r = -EEXIST;
 		goto unlock_vcpu_destroy;
@@ -2399,6 +2451,10 @@ unlock_vcpu_destroy:
 	mutex_unlock(&kvm->lock);
 vcpu_destroy:
 	kvm_arch_vcpu_destroy(vcpu);
+vcpu_decrement:
+	mutex_lock(&kvm->lock);
+	kvm->created_vcpus--;
+	mutex_unlock(&kvm->lock);
 	return r;
 }
 
@@ -3487,6 +3543,30 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	return r;
 }
 
+struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+					 gpa_t addr)
+{
+	struct kvm_io_bus *bus;
+	int dev_idx, srcu_idx;
+	struct kvm_io_device *iodev = NULL;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+
+	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+
+	dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1);
+	if (dev_idx < 0)
+		goto out_unlock;
+
+	iodev = bus->range[dev_idx].dev;
+
+out_unlock:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	return iodev;
+}
+EXPORT_SYMBOL_GPL(kvm_io_bus_get_dev);
+
 static int kvm_debugfs_open(struct inode *inode, struct file *file,
 			   int (*get)(void *, u64 *), int (*set)(void *, u64),
 			   const char *fmt)